diff --git a/decoders/crossreg_reg4/eval_v2/adhd200_dx__patch__logistic/eval_table.csv b/decoders/crossreg_reg4/eval_v2/adhd200_dx__patch__logistic/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..fbb99028971fb589b3b423dda6931b88d7e04d83 --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/adhd200_dx__patch__logistic/eval_table.csv @@ -0,0 +1,203 @@ +model,repr,clf,dataset,trial,C,split,acc,acc_std,f1,f1_std,bacc,bacc_std +flat_mae,patch,logistic,adhd200_dx,,0.005994842503189409,train,0.7424657534246575,0.021904998996738183,0.7317351598173516,0.023336040318595548,0.7287964828723209,0.022882418202841488 +flat_mae,patch,logistic,adhd200_dx,,0.005994842503189409,test,0.5846153846153846,0.05747490525201247,0.5501153550371699,0.0649772448058626,0.556949806949807,0.05949809369980641 +flat_mae,patch,logistic,adhd200_dx,1,0.005994842503189409,train,0.7315068493150685,0.02175946294856782,0.7161111111111111,0.023687396156063766,0.7133479880319961,0.022699840669655757 +flat_mae,patch,logistic,adhd200_dx,1,0.005994842503189409,test,0.5846153846153846,0.0595373961343754,0.5699583435432491,0.061553726399329114,0.5699806949806949,0.06028514680245595 +flat_mae,patch,logistic,adhd200_dx,2,0.3593813663804626,train,0.958904109589041,0.010228133723195108,0.9580527271473556,0.010483771568235135,0.9564175367893998,0.010892055823648775 +flat_mae,patch,logistic,adhd200_dx,2,0.3593813663804626,test,0.5846153846153846,0.06186923411662306,0.578226387887527,0.06294971050534451,0.5786679536679536,0.06281953395438065 +flat_mae,patch,logistic,adhd200_dx,3,0.005994842503189409,train,0.7397260273972602,0.0229039647370395,0.7272712972211954,0.024897916295657085,0.7242168895402088,0.02425350564676892 +flat_mae,patch,logistic,adhd200_dx,3,0.005994842503189409,test,0.6,0.056654301006059615,0.570630081300813,0.0629693519564316,0.5748069498069498,0.05860606934204386 +flat_mae,patch,logistic,adhd200_dx,4,0.005994842503189409,train,0.7205479452054795,0.02427381860862127,0.7089041095890412,0.025619520916078338,0.706509128656042,0.025038369760472984 +flat_mae,patch,logistic,adhd200_dx,4,0.005994842503189409,test,0.6307692307692307,0.05718021754161582,0.6264367816091954,0.05816225509061837,0.627895752895753,0.05866661248897376 +flat_mae,patch,logistic,adhd200_dx,5,0.046415888336127774,train,0.8356164383561644,0.019340680580432475,0.8312060673325934,0.020140055010896152,0.8285400256457227,0.020331923833431437 +flat_mae,patch,logistic,adhd200_dx,5,0.046415888336127774,test,0.5692307692307692,0.06097359211093965,0.5666666666666667,0.06144937965341382,0.5694980694980695,0.06208679449276509 +flat_mae,patch,logistic,adhd200_dx,6,0.3593813663804626,train,0.9534246575342465,0.010953438363008551,0.9523018856321441,0.01130584772176831,0.9494107589912683,0.011886781727977814 +flat_mae,patch,logistic,adhd200_dx,6,0.3593813663804626,test,0.6615384615384615,0.059135956082362856,0.6575670498084292,0.059942574087972475,0.6592664092664093,0.06033058277089562 +flat_mae,patch,logistic,adhd200_dx,7,0.046415888336127774,train,0.8410958904109589,0.019123523176318054,0.8362165005879805,0.020052715949169946,0.8326769249557306,0.020238647422966088 +flat_mae,patch,logistic,adhd200_dx,7,0.046415888336127774,test,0.5846153846153846,0.05917168681650083,0.5830363506771205,0.05919782582612036,0.5873552123552124,0.05994967511895883 +flat_mae,patch,logistic,adhd200_dx,8,0.005994842503189409,train,0.7315068493150685,0.022803403827525912,0.7183109683109683,0.024956083596163036,0.7155003968980888,0.02419498300613208 +flat_mae,patch,logistic,adhd200_dx,8,0.005994842503189409,test,0.6307692307692307,0.06192692009096418,0.6198830409356726,0.06462276479873824,0.6192084942084942,0.06344098862392855 +flat_mae,patch,logistic,adhd200_dx,9,0.005994842503189409,train,0.7452054794520548,0.02305588045530142,0.7354763296317943,0.024523043363115803,0.7326586065824021,0.02422583777514946 +flat_mae,patch,logistic,adhd200_dx,9,0.005994842503189409,test,0.6307692307692307,0.054095563041976026,0.5962732919254659,0.06156816960167578,0.6018339768339769,0.055989328273165724 +flat_mae,patch,logistic,adhd200_dx,10,0.005994842503189409,train,0.7424657534246575,0.022914004548061827,0.7329212853406402,0.024156020773037724,0.7302314221163827,0.023809908653756675 +flat_mae,patch,logistic,adhd200_dx,10,0.005994842503189409,test,0.5846153846153846,0.05909105600180356,0.5578231292517006,0.06407308875457003,0.5612934362934363,0.060402412127793625 +flat_mae,patch,logistic,adhd200_dx,11,0.005994842503189409,train,0.7013698630136986,0.02221617195008163,0.683816926145801,0.02431744764948055,0.6823441411735971,0.023212493901744093 +flat_mae,patch,logistic,adhd200_dx,11,0.005994842503189409,test,0.6,0.05412110898595687,0.5626293995859213,0.062306311625395884,0.5704633204633205,0.05602142058640619 +flat_mae,patch,logistic,adhd200_dx,12,0.005994842503189409,train,0.726027397260274,0.023221860919076725,0.7139498432601881,0.024878197678231764,0.7113634975880808,0.02426849239439832 +flat_mae,patch,logistic,adhd200_dx,12,0.005994842503189409,test,0.5846153846153846,0.056831785422591874,0.5699583435432491,0.05977686042399589,0.5699806949806949,0.058273607132441826 +flat_mae,patch,logistic,adhd200_dx,13,0.005994842503189409,train,0.7589041095890411,0.020850981158566873,0.7482758620689656,0.022332588561961048,0.7447945289124992,0.021929752294809205 +flat_mae,patch,logistic,adhd200_dx,13,0.005994842503189409,test,0.49230769230769234,0.0588737773274718,0.4743935309973046,0.060543653424304386,0.47586872586872586,0.059637690826888815 +flat_mae,patch,logistic,adhd200_dx,14,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adhd200_dx,14,1291.5496650148827,test,0.6,0.057080124314125104,0.5833333333333333,0.06070381533140116,0.5834942084942085,0.058669222582869274 +flat_mae,patch,logistic,adhd200_dx,15,0.005994842503189409,train,0.726027397260274,0.022219753045615607,0.7118360386534454,0.02414592096639806,0.7092110887219881,0.023307827685588735 +flat_mae,patch,logistic,adhd200_dx,15,0.005994842503189409,test,0.5384615384615384,0.061283927446873124,0.5294401544401545,0.0623149636534173,0.5294401544401545,0.06222626850432534 +flat_mae,patch,logistic,adhd200_dx,16,0.005994842503189409,train,0.7232876712328767,0.021793275667674784,0.7133381544466995,0.02293349533438079,0.7110887219881541,0.022593524141794323 +flat_mae,patch,logistic,adhd200_dx,16,0.005994842503189409,test,0.5846153846153846,0.062481171601801194,0.5745454545454545,0.06394244463034299,0.5743243243243243,0.06344919493891837 +flat_mae,patch,logistic,adhd200_dx,17,0.046415888336127774,train,0.8356164383561644,0.018018927102044696,0.8308932542624166,0.01874021067288798,0.8278225560236918,0.018824477702043735 +flat_mae,patch,logistic,adhd200_dx,17,0.046415888336127774,test,0.6153846153846154,0.056206643251150754,0.5966741126830479,0.06061578789763127,0.597007722007722,0.05831458026482621 +flat_mae,patch,logistic,adhd200_dx,18,0.3593813663804626,train,0.9698630136986301,0.008740498956674862,0.9691886208934148,0.008994420012140777,0.9668437442755083,0.009678730503850482 +flat_mae,patch,logistic,adhd200_dx,18,0.3593813663804626,test,0.5692307692307692,0.05923596380818011,0.5608108108108107,0.06037803594609343,0.5608108108108107,0.060218470396470755 +flat_mae,patch,logistic,adhd200_dx,19,0.000774263682681127,train,0.6328767123287671,0.023010616231931746,0.5924166666666667,0.027261834319406555,0.6022928497282775,0.02406024823718003 +flat_mae,patch,logistic,adhd200_dx,19,0.000774263682681127,test,0.6307692307692307,0.05238849867002689,0.587737843551797,0.0629310560687302,0.5974903474903475,0.055048676802358774 +flat_mae,patch,logistic,adhd200_dx,20,0.005994842503189409,train,0.7095890410958904,0.0229524893775056,0.701244749196936,0.023724193633656646,0.6996702692800879,0.023507540272789867 +flat_mae,patch,logistic,adhd200_dx,20,0.005994842503189409,test,0.6307692307692307,0.05634593909121585,0.6036585365853658,0.06289556976806442,0.6061776061776062,0.058661890473261515 +flat_mae,patch,logistic,adhd200_dx,21,0.005994842503189409,train,0.726027397260274,0.023098341409458226,0.7095244158655376,0.025617669985713853,0.7070586798558954,0.02439054946883275 +flat_mae,patch,logistic,adhd200_dx,21,0.005994842503189409,test,0.7230769230769231,0.05417740746187419,0.7149122807017544,0.05636841728510411,0.7133204633204633,0.05579711314188372 +flat_mae,patch,logistic,adhd200_dx,22,0.005994842503189409,train,0.7178082191780822,0.021734313402037447,0.7028086734492217,0.023821578651592547,0.7004945960798681,0.022933319859288752 +flat_mae,patch,logistic,adhd200_dx,22,0.005994842503189409,test,0.6307692307692307,0.06171500829231663,0.6235521235521235,0.06334497042852516,0.6235521235521235,0.06326613240265587 +flat_mae,patch,logistic,adhd200_dx,23,0.000774263682681127,train,0.6602739726027397,0.02229287038061088,0.6377577154565246,0.02476154092559909,0.6387616779629969,0.02321867248197043 +flat_mae,patch,logistic,adhd200_dx,23,0.000774263682681127,test,0.6153846153846154,0.05174945558985287,0.5656241646618552,0.06406613287543482,0.5796332046332047,0.054493023528735494 +flat_mae,patch,logistic,adhd200_dx,24,0.005994842503189409,train,0.7205479452054795,0.021686796274929466,0.7068134568134568,0.02346880306398429,0.7043567197899493,0.022737337739779803 +flat_mae,patch,logistic,adhd200_dx,24,0.005994842503189409,test,0.5846153846153846,0.05588169244301624,0.5501153550371699,0.06169691487186124,0.556949806949807,0.05693022347504732 +flat_mae,patch,logistic,adhd200_dx,25,0.000774263682681127,train,0.6520547945205479,0.021670064911463217,0.6114450004610188,0.026221653172145115,0.6207180802344752,0.02278685906566446 +flat_mae,patch,logistic,adhd200_dx,25,0.000774263682681127,test,0.6,0.05099025083752161,0.5427489177489178,0.06181938637330176,0.5617760617760618,0.05255712965330673 +flat_mae,patch,logistic,adhd200_dx,26,0.005994842503189409,train,0.7205479452054795,0.021968759271678243,0.7053096504559271,0.024160845427025433,0.7029217805458875,0.023234977827076238 +flat_mae,patch,logistic,adhd200_dx,26,0.005994842503189409,test,0.6307692307692307,0.05501583204085829,0.6036585365853658,0.061749572456848666,0.6061776061776062,0.05731640220304975 +flat_mae,patch,logistic,adhd200_dx,27,0.046415888336127774,train,0.821917808219178,0.020108931346790333,0.8166268617494068,0.020990003327584165,0.8135342248275019,0.02107974775547443 +flat_mae,patch,logistic,adhd200_dx,27,0.046415888336127774,test,0.6153846153846154,0.060639308047448666,0.6018132810585641,0.06333183184019378,0.6013513513513513,0.06192042359549878 +flat_mae,patch,logistic,adhd200_dx,28,0.005994842503189409,train,0.726027397260274,0.021827360636567844,0.7146118721461188,0.0232255707691606,0.7120809672101117,0.022738620292532444 +flat_mae,patch,logistic,adhd200_dx,28,0.005994842503189409,test,0.5846153846153846,0.0546718148343194,0.5501153550371699,0.06075232455253754,0.556949806949807,0.0559985707062253 +flat_mae,patch,logistic,adhd200_dx,29,0.005994842503189409,train,0.7205479452054795,0.023599615150275935,0.7075320512820513,0.025331520243230213,0.7050741894119802,0.02460199328954945 +flat_mae,patch,logistic,adhd200_dx,29,0.005994842503189409,test,0.6153846153846154,0.05950202820868164,0.5966741126830479,0.06341831262949778,0.597007722007722,0.061315369217520205 +flat_mae,patch,logistic,adhd200_dx,30,0.3593813663804626,train,0.9506849315068493,0.011509994351675637,0.9496227456753772,0.011818357288142189,0.9477010441472797,0.012220399808541461 +flat_mae,patch,logistic,adhd200_dx,30,0.3593813663804626,test,0.5692307692307692,0.06032451884569405,0.564176245210728,0.06047048488448265,0.5651544401544402,0.06061516498236156 +flat_mae,patch,logistic,adhd200_dx,31,0.3593813663804626,train,0.9506849315068493,0.01138222928754019,0.9496227456753772,0.011690226536236527,0.9477010441472797,0.012122024347066197 +flat_mae,patch,logistic,adhd200_dx,31,0.3593813663804626,test,0.6,0.061585797179229435,0.5921814671814671,0.06290748518584183,0.5921814671814671,0.06264103536840496 +flat_mae,patch,logistic,adhd200_dx,32,0.046415888336127774,train,0.8273972602739726,0.019370352050558662,0.8219222637827288,0.020277634696192738,0.8183885937595408,0.020282488371607732 +flat_mae,patch,logistic,adhd200_dx,32,0.046415888336127774,test,0.5538461538461539,0.06633448682255583,0.543030303030303,0.0677295747450472,0.542953667953668,0.06714117747970659 +flat_mae,patch,logistic,adhd200_dx,33,0.3593813663804626,train,0.9698630136986301,0.008270471907532133,0.9692386665747275,0.008478910561300812,0.9675612138975392,0.00896411037959371 +flat_mae,patch,logistic,adhd200_dx,33,0.3593813663804626,test,0.5538461538461539,0.06428263037592144,0.5521501544309813,0.06465589680292005,0.555984555984556,0.06493353033693425 +flat_mae,patch,logistic,adhd200_dx,34,0.046415888336127774,train,0.8328767123287671,0.019746244586437308,0.8282352941176471,0.02052135708102231,0.8253953715576724,0.020590510236745532 +flat_mae,patch,logistic,adhd200_dx,34,0.046415888336127774,test,0.6,0.05947099337706104,0.5953065134099617,0.06066406774404732,0.5965250965250966,0.06074520327848402 +flat_mae,patch,logistic,adhd200_dx,35,0.005994842503189409,train,0.7232876712328767,0.022077181524813458,0.7078125371525494,0.024220170236057145,0.7053489650119069,0.023256156645309 +flat_mae,patch,logistic,adhd200_dx,35,0.005994842503189409,test,0.5846153846153846,0.05892026504638361,0.5578231292517006,0.06423842231664416,0.5612934362934363,0.06053049391752815 +flat_mae,patch,logistic,adhd200_dx,36,0.000774263682681127,train,0.6520547945205479,0.023169790284662508,0.6295304695304695,0.02543052246104817,0.6307626549429077,0.02403092433972 +flat_mae,patch,logistic,adhd200_dx,36,0.000774263682681127,test,0.5230769230769231,0.05727286293177918,0.49987589972697943,0.059762560808738124,0.502895752895753,0.05766843127488071 +flat_mae,patch,logistic,adhd200_dx,37,0.005994842503189409,train,0.7205479452054795,0.022443698495942428,0.7045238095238096,0.024447890864901657,0.7022043109238566,0.023452631688816224 +flat_mae,patch,logistic,adhd200_dx,37,0.005994842503189409,test,0.6615384615384615,0.05682256406553869,0.6425000000000001,0.0619619253833288,0.6418918918918919,0.05898029206476128 +flat_mae,patch,logistic,adhd200_dx,38,0.005994842503189409,train,0.726027397260274,0.022915081595614787,0.7170542635658914,0.024071946250538167,0.7149508456982353,0.02378857968540285 +flat_mae,patch,logistic,adhd200_dx,38,0.005994842503189409,test,0.5384615384615384,0.057453132945097955,0.5192307692307693,0.05989794466165466,0.5207528957528957,0.05786402876580633 +flat_mae,patch,logistic,adhd200_dx,39,0.005994842503189409,train,0.726027397260274,0.02197036096923327,0.7110878926038501,0.02402823161951898,0.7084936190999572,0.023113348312872126 +flat_mae,patch,logistic,adhd200_dx,39,0.005994842503189409,test,0.6615384615384615,0.0560774696607318,0.6366869918699187,0.061839426323924813,0.6375482625482626,0.05808815409906013 +flat_mae,patch,logistic,adhd200_dx,40,0.005994842503189409,train,0.7205479452054795,0.02220244965935824,0.7068134568134568,0.023900226148545648,0.7043567197899493,0.023197602316128895 +flat_mae,patch,logistic,adhd200_dx,40,0.005994842503189409,test,0.6307692307692307,0.05205004419394585,0.587737843551797,0.06211088417396741,0.5974903474903475,0.054455122466531274 +flat_mae,patch,logistic,adhd200_dx,41,0.005994842503189409,train,0.7041095890410959,0.02182693490296788,0.687974924012158,0.023838853673666244,0.6862062648836783,0.02291902835682879 +flat_mae,patch,logistic,adhd200_dx,41,0.005994842503189409,test,0.5538461538461539,0.06111759932086307,0.5469838981014179,0.06205525189766619,0.5472972972972974,0.06190522647687008 +flat_mae,patch,logistic,adhd200_dx,42,0.005994842503189409,train,0.7342465753424657,0.023362355022582017,0.7222026065328092,0.02487370188479026,0.71936252060817,0.024262331763589464 +flat_mae,patch,logistic,adhd200_dx,42,0.005994842503189409,test,0.5384615384615384,0.06275487015212963,0.5330459770114943,0.06314375194502904,0.5337837837837838,0.06324572364060993 +flat_mae,patch,logistic,adhd200_dx,43,0.046415888336127774,train,0.8328767123287671,0.019165280267290002,0.8264952269627899,0.020429761572947177,0.8218080234475178,0.020498523821229027 +flat_mae,patch,logistic,adhd200_dx,43,0.046415888336127774,test,0.6,0.05912898347164893,0.5921814671814671,0.06041647484088127,0.5921814671814671,0.06011477287930213 +flat_mae,patch,logistic,adhd200_dx,44,0.046415888336127774,train,0.8054794520547945,0.020761267110831375,0.7993092179138691,0.021871281528614218,0.7961012395432618,0.02195356415166546 +flat_mae,patch,logistic,adhd200_dx,44,0.046415888336127774,test,0.6,0.057710840100355126,0.5775,0.06206447144136149,0.5791505791505791,0.05918403745742286 +flat_mae,patch,logistic,adhd200_dx,45,0.005994842503189409,train,0.7561643835616438,0.02229662970054,0.7444962679230146,0.024160604216939094,0.740932405202418,0.02359544868750415 +flat_mae,patch,logistic,adhd200_dx,45,0.005994842503189409,test,0.5076923076923077,0.05994455031465357,0.4871794871794872,0.061936053646823204,0.48938223938223935,0.06010449539992708 +flat_mae,patch,logistic,adhd200_dx,46,0.000774263682681127,train,0.6383561643835617,0.02145938117340014,0.6000199242877067,0.02552124954726054,0.6085821579043781,0.02253711183856456 +flat_mae,patch,logistic,adhd200_dx,46,0.000774263682681127,test,0.6615384615384615,0.05471973563035206,0.6299171842650104,0.06391608106189291,0.6332046332046332,0.05748081521955596 +flat_mae,patch,logistic,adhd200_dx,47,0.005994842503189409,train,0.7589041095890411,0.021763169550492133,0.747674710910005,0.023390517237837544,0.7440770592904683,0.022835243895963475 +flat_mae,patch,logistic,adhd200_dx,47,0.005994842503189409,test,0.5538461538461539,0.0607249225031844,0.5381034060279344,0.06240298791904154,0.5386100386100386,0.06119743641907058 +flat_mae,patch,logistic,adhd200_dx,48,0.3593813663804626,train,0.9561643835616438,0.01088831512528878,0.9552202183781131,0.011179413235158527,0.9532728827013495,0.01165244919462919 +flat_mae,patch,logistic,adhd200_dx,48,0.3593813663804626,test,0.6307692307692307,0.06416737728544239,0.6299810246679317,0.06424466597952602,0.6365830115830116,0.06423716187867733 +flat_mae,patch,logistic,adhd200_dx,49,0.005994842503189409,train,0.7397260273972602,0.020729336352759125,0.7244275961821202,0.02276909768838598,0.7213470110520852,0.021807210011172997 +flat_mae,patch,logistic,adhd200_dx,49,0.005994842503189409,test,0.5076923076923077,0.06062066357333121,0.48,0.0632875825966212,0.48503861003861004,0.061067542538412366 +flat_mae,patch,logistic,adhd200_dx,50,0.005994842503189409,train,0.7397260273972602,0.02222856143605805,0.7265917602996255,0.024070064097153746,0.7234994199181779,0.023332671951150376 +flat_mae,patch,logistic,adhd200_dx,50,0.005994842503189409,test,0.6307692307692307,0.05310687226392461,0.5962732919254659,0.06153319367059387,0.6018339768339769,0.05562395056913396 +flat_mae,patch,logistic,adhd200_dx,51,0.005994842503189409,train,0.7315068493150685,0.02164172627141272,0.7196708463949844,0.022973817232989892,0.7169353361421505,0.022415529048109274 +flat_mae,patch,logistic,adhd200_dx,51,0.005994842503189409,test,0.5538461538461539,0.062097849870827906,0.5469838981014179,0.0631569322999681,0.5472972972972974,0.06323941349555502 +flat_mae,patch,logistic,adhd200_dx,52,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adhd200_dx,52,166.81005372000556,test,0.5846153846153846,0.05991440837862748,0.5842217484008528,0.0600633172409386,0.5916988416988418,0.06048731269124607 +flat_mae,patch,logistic,adhd200_dx,53,0.005994842503189409,train,0.7123287671232876,0.022800594554276937,0.6992914812984017,0.02445117657662805,0.697075166391891,0.023792587411843282 +flat_mae,patch,logistic,adhd200_dx,53,0.005994842503189409,test,0.6,0.05603781478957341,0.570630081300813,0.06217061649701836,0.5748069498069498,0.05791292411609699 +flat_mae,patch,logistic,adhd200_dx,54,0.005994842503189409,train,0.7424657534246575,0.02150399143388654,0.7329212853406402,0.022833648803330095,0.7302314221163827,0.02248525324468077 +flat_mae,patch,logistic,adhd200_dx,54,0.005994842503189409,test,0.5846153846153846,0.06114006424286208,0.5699583435432491,0.06361913080694286,0.5699806949806949,0.062218178015642917 +flat_mae,patch,logistic,adhd200_dx,55,0.005994842503189409,train,0.7287671232876712,0.02189059337794961,0.7184102863822326,0.023214704130838114,0.7159430909201929,0.02282367625310187 +flat_mae,patch,logistic,adhd200_dx,55,0.005994842503189409,test,0.5538461538461539,0.0615722983897311,0.5500119360229172,0.062283864775608454,0.5516409266409266,0.06254055242144516 +flat_mae,patch,logistic,adhd200_dx,56,0.046415888336127774,train,0.8273972602739726,0.018062338623838468,0.8226036644165864,0.018719882960673097,0.8198235330036027,0.018794635786012343 +flat_mae,patch,logistic,adhd200_dx,56,0.046415888336127774,test,0.6307692307692307,0.059886282769139425,0.6235521235521235,0.06123199746900422,0.6235521235521235,0.06081287917056077 +flat_mae,patch,logistic,adhd200_dx,57,0.046415888336127774,train,0.8273972602739726,0.019640462062968714,0.8219222637827288,0.020512098878076365,0.8183885937595408,0.020519810816742468 +flat_mae,patch,logistic,adhd200_dx,57,0.046415888336127774,test,0.47692307692307695,0.061380250471377136,0.4666988416988417,0.06210337530946148,0.4666988416988417,0.061938623429712535 +flat_mae,patch,logistic,adhd200_dx,58,10000.0,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adhd200_dx,58,10000.0,test,0.5846153846153846,0.06182958829044295,0.5810455956075435,0.06238142369611767,0.583011583011583,0.06273800949872903 +flat_mae,patch,logistic,adhd200_dx,59,0.005994842503189409,train,0.736986301369863,0.022914332122625974,0.726027397260274,0.024133596287808083,0.7232246443182512,0.023646910849835705 +flat_mae,patch,logistic,adhd200_dx,59,0.005994842503189409,test,0.5846153846153846,0.05534578981010337,0.5411764705882354,0.06181641099500292,0.5526061776061776,0.056166560066473796 +flat_mae,patch,logistic,adhd200_dx,60,0.005994842503189409,train,0.7397260273972602,0.022836827835171818,0.729787648548607,0.02391043781111711,0.7270867680283324,0.02346507037206614 +flat_mae,patch,logistic,adhd200_dx,60,0.005994842503189409,test,0.6615384615384615,0.056132252961066935,0.6425000000000001,0.06006833363648928,0.6418918918918919,0.05772516890499275 +flat_mae,patch,logistic,adhd200_dx,61,0.005994842503189409,train,0.7041095890410959,0.023303740467139702,0.6917808219178082,0.024649862280958786,0.6897936129938328,0.024067836688138063 +flat_mae,patch,logistic,adhd200_dx,61,0.005994842503189409,test,0.6,0.061166096499177924,0.5833333333333333,0.06477892257281674,0.5834942084942085,0.06280781966608415 +flat_mae,patch,logistic,adhd200_dx,62,0.005994842503189409,train,0.7150684931506849,0.02295458749102437,0.705736434108527,0.024052135037160877,0.7038071685900958,0.02377186536689152 +flat_mae,patch,logistic,adhd200_dx,62,0.005994842503189409,test,0.5692307692307692,0.057135230429333335,0.5512820512820513,0.06024928311266914,0.5521235521235521,0.05848726018596496 +flat_mae,patch,logistic,adhd200_dx,63,0.005994842503189409,train,0.7287671232876712,0.023559667964300826,0.7177857092650011,0.02486981895731557,0.715225621298162,0.02437249304770905 +flat_mae,patch,logistic,adhd200_dx,63,0.005994842503189409,test,0.6,0.054644793815369644,0.570630081300813,0.05967058236001123,0.5748069498069498,0.056116287203535634 +flat_mae,patch,logistic,adhd200_dx,64,0.005994842503189409,train,0.7178082191780822,0.022598665303170146,0.7028086734492217,0.02461694271285539,0.7004945960798681,0.02373507999284538 +flat_mae,patch,logistic,adhd200_dx,64,0.005994842503189409,test,0.6307692307692307,0.05592199977800864,0.6036585365853658,0.06227386364878947,0.6061776061776062,0.05792586044684726 +flat_mae,patch,logistic,adhd200_dx,65,0.005994842503189409,train,0.7205479452054795,0.023266382533645276,0.7045238095238096,0.025512710667900215,0.7022043109238566,0.024469664743134594 +flat_mae,patch,logistic,adhd200_dx,65,0.005994842503189409,test,0.676923076923077,0.05373611613723858,0.6612062546537603,0.05776392214398613,0.6597490347490347,0.055688565931782875 +flat_mae,patch,logistic,adhd200_dx,66,0.005994842503189409,train,0.7424657534246575,0.022769794281447535,0.7317351598173516,0.02415137953584078,0.7287964828723209,0.023651629008550848 +flat_mae,patch,logistic,adhd200_dx,66,0.005994842503189409,test,0.6153846153846154,0.05826989641660921,0.5966741126830479,0.06189744657713271,0.597007722007722,0.059638607200298205 +flat_mae,patch,logistic,adhd200_dx,67,0.046415888336127774,train,0.8191780821917808,0.020216314902893544,0.8132558139534884,0.021275944961961703,0.8096721011174208,0.021303597716987244 +flat_mae,patch,logistic,adhd200_dx,67,0.046415888336127774,test,0.6,0.0547095612729124,0.5626293995859213,0.06242501864664253,0.5704633204633205,0.056400707961241414 +flat_mae,patch,logistic,adhd200_dx,68,0.3593813663804626,train,0.9561643835616438,0.010683345157969416,0.9552915237628614,0.010946145806773175,0.9539903523233804,0.011364740577253448 +flat_mae,patch,logistic,adhd200_dx,68,0.3593813663804626,test,0.5846153846153846,0.05780803981675578,0.5644080416976918,0.06163621427551431,0.5656370656370656,0.05918942817174904 +flat_mae,patch,logistic,adhd200_dx,69,0.005994842503189409,train,0.7342465753424657,0.022627827670821474,0.7246910988250481,0.023923773200905718,0.7222323990962936,0.023594600749455144 +flat_mae,patch,logistic,adhd200_dx,69,0.005994842503189409,test,0.4461538461538462,0.06193028338381796,0.4230769230769231,0.06270234320564441,0.4266409266409266,0.0616888681227142 +flat_mae,patch,logistic,adhd200_dx,70,0.005994842503189409,train,0.7232876712328767,0.022441283031214385,0.7093238714764439,0.02428303004496929,0.7067839042559687,0.02350081520282437 +flat_mae,patch,logistic,adhd200_dx,70,0.005994842503189409,test,0.5230769230769231,0.06104710762282211,0.5062484685126194,0.0635014107595719,0.5072393822393823,0.06190383000831069 +flat_mae,patch,logistic,adhd200_dx,71,0.005994842503189409,train,0.7232876712328767,0.022100115775325526,0.7107470439156054,0.023726550328457937,0.7082188435000305,0.023076836256939837 +flat_mae,patch,logistic,adhd200_dx,71,0.005994842503189409,test,0.5692307692307692,0.05659594147742377,0.5376016260162602,0.062044019075676825,0.5434362934362934,0.057753081923810734 +flat_mae,patch,logistic,adhd200_dx,72,0.005994842503189409,train,0.7232876712328767,0.02307402400100976,0.7107470439156054,0.024822190995863188,0.7082188435000305,0.024160571553970608 +flat_mae,patch,logistic,adhd200_dx,72,0.005994842503189409,test,0.6307692307692307,0.05609029913277994,0.6036585365853658,0.06115136061865767,0.6061776061776062,0.057341517022094335 +flat_mae,patch,logistic,adhd200_dx,73,0.000774263682681127,train,0.6575342465753424,0.02307242279353255,0.6332071163848894,0.025697876621656443,0.6348995542529157,0.02398940136684095 +flat_mae,patch,logistic,adhd200_dx,73,0.000774263682681127,test,0.5692307692307692,0.060231223104685414,0.545,0.06383778070712375,0.5477799227799228,0.061274607351757174 +flat_mae,patch,logistic,adhd200_dx,74,0.005994842503189409,train,0.7123287671232876,0.021518120072669285,0.6992914812984017,0.02307937963393897,0.697075166391891,0.022467433233319872 +flat_mae,patch,logistic,adhd200_dx,74,0.005994842503189409,test,0.6,0.06086725492326306,0.588206627680312,0.06293773736882363,0.5878378378378378,0.06173305166009477 +flat_mae,patch,logistic,adhd200_dx,75,0.000774263682681127,train,0.6493150684931507,0.024211490752969772,0.6271467790333909,0.026410490894806075,0.6283354704768883,0.025028103942272818 +flat_mae,patch,logistic,adhd200_dx,75,0.000774263682681127,test,0.5692307692307692,0.06144790259828085,0.5512820512820513,0.06439173788759277,0.5521235521235521,0.06257055113749697 +flat_mae,patch,logistic,adhd200_dx,76,0.005994842503189409,train,0.736986301369863,0.021762281072142658,0.722644376899696,0.02369644272299936,0.7196372962080967,0.022865534010131413 +flat_mae,patch,logistic,adhd200_dx,76,0.005994842503189409,test,0.5846153846153846,0.05334802558970225,0.5308740978348035,0.06315106954948436,0.5482625482625483,0.05494262135581445 +flat_mae,patch,logistic,adhd200_dx,77,0.005994842503189409,train,0.7287671232876712,0.02124986611506177,0.7143500841890578,0.02297012302648463,0.7116382731880075,0.022119485509107886 +flat_mae,patch,logistic,adhd200_dx,77,0.005994842503189409,test,0.6923076923076923,0.04830603622835012,0.6564482029598309,0.059567725263369425,0.6602316602316602,0.05192352376469467 +flat_mae,patch,logistic,adhd200_dx,78,0.046415888336127774,train,0.8136986301369863,0.020500328389188124,0.8079779662065978,0.021334896646349515,0.8048177321853819,0.021261613119241796 +flat_mae,patch,logistic,adhd200_dx,78,0.046415888336127774,test,0.5076923076923077,0.060007691814658856,0.4871794871794872,0.06246715479628248,0.48938223938223935,0.06073682705315684 +flat_mae,patch,logistic,adhd200_dx,79,0.046415888336127774,train,0.8356164383561644,0.01839559943135128,0.8302325581395349,0.019292304084109084,0.82638761677963,0.019337215031205886 +flat_mae,patch,logistic,adhd200_dx,79,0.046415888336127774,test,0.5692307692307692,0.06071768797587812,0.5608108108108107,0.06181523711408662,0.5608108108108107,0.06143627732299396 +flat_mae,patch,logistic,adhd200_dx,80,0.005994842503189409,train,0.736986301369863,0.021911381934621478,0.726027397260274,0.02330160014239652,0.7232246443182512,0.02288122930677169 +flat_mae,patch,logistic,adhd200_dx,80,0.005994842503189409,test,0.5692307692307692,0.062282243615837125,0.5512820512820513,0.06525275785157907,0.5521235521235521,0.06337668133097127 +flat_mae,patch,logistic,adhd200_dx,81,0.005994842503189409,train,0.7452054794520548,0.022841902151556792,0.7354763296317943,0.024188971345863692,0.7326586065824021,0.02382873835766544 +flat_mae,patch,logistic,adhd200_dx,81,0.005994842503189409,test,0.5076923076923077,0.05577023871768183,0.4715447154471545,0.05882071122044139,0.4806949806949807,0.05586864545332324 +flat_mae,patch,logistic,adhd200_dx,82,0.005994842503189409,train,0.7150684931506849,0.022610110213810392,0.7003094801995832,0.024566268007424483,0.6980674116138487,0.02368182611539774 +flat_mae,patch,logistic,adhd200_dx,82,0.005994842503189409,test,0.6923076923076923,0.05898531358681508,0.6886973180076628,0.059702359059180116,0.6906370656370657,0.05973689950897015 +flat_mae,patch,logistic,adhd200_dx,83,0.005994842503189409,train,0.7315068493150685,0.021311968644545688,0.7190013826043238,0.02263767872958227,0.7162178665201197,0.022025541376126653 +flat_mae,patch,logistic,adhd200_dx,83,0.005994842503189409,test,0.6307692307692307,0.058050180292163286,0.6198830409356726,0.06017459518282782,0.6192084942084942,0.05946718303394383 +flat_mae,patch,logistic,adhd200_dx,84,0.005994842503189409,train,0.7452054794520548,0.020639719072161434,0.732347723240686,0.022134426808788587,0.7290712584722476,0.02146654898469891 +flat_mae,patch,logistic,adhd200_dx,84,0.005994842503189409,test,0.5538461538461539,0.06545242456667899,0.5500119360229172,0.06612552498382575,0.5516409266409266,0.06640017639902036 +flat_mae,patch,logistic,adhd200_dx,85,0.005994842503189409,train,0.7123287671232876,0.022778800559420973,0.6978119455943228,0.024617930175374354,0.6956402271478292,0.02379168819421414 +flat_mae,patch,logistic,adhd200_dx,85,0.005994842503189409,test,0.6,0.058201039052112824,0.5833333333333333,0.06141692894530669,0.5834942084942085,0.05955812962727085 +flat_mae,patch,logistic,adhd200_dx,86,0.3593813663804626,train,0.9643835616438357,0.009436119185371733,0.9635865519649449,0.00970654487022802,0.9612719057214386,0.010276125068230193 +flat_mae,patch,logistic,adhd200_dx,86,0.3593813663804626,test,0.5692307692307692,0.06266370465953001,0.5608108108108107,0.0638736425392196,0.5608108108108107,0.06345222216046117 +flat_mae,patch,logistic,adhd200_dx,87,0.3593813663804626,train,0.9616438356164384,0.009990223781983642,0.960817691080849,0.010257933471132514,0.9588447212554192,0.010741585299082484 +flat_mae,patch,logistic,adhd200_dx,87,0.3593813663804626,test,0.5692307692307692,0.06240130479594706,0.5565302144249512,0.06437824570753099,0.5564671814671815,0.06360930550576196 +flat_mae,patch,logistic,adhd200_dx,88,0.000774263682681127,train,0.6438356164383562,0.02389033241158383,0.6191080143847932,0.026266485726360658,0.6213286926787568,0.024641759416660892 +flat_mae,patch,logistic,adhd200_dx,88,0.000774263682681127,test,0.5692307692307692,0.059721634350270884,0.545,0.06365544719042884,0.5477799227799228,0.0608539734283045 +flat_mae,patch,logistic,adhd200_dx,89,0.005994842503189409,train,0.7178082191780822,0.023099302629036932,0.7063831116595465,0.02454637526937608,0.7040819441900226,0.024067561676940522 +flat_mae,patch,logistic,adhd200_dx,89,0.005994842503189409,test,0.6307692307692307,0.055941431756634984,0.61,0.060568572762768585,0.6105212355212355,0.05787304586244429 +flat_mae,patch,logistic,adhd200_dx,90,0.005994842503189409,train,0.7150684931506849,0.022625052332687735,0.6995314083080041,0.02456208746660161,0.6973499419918178,0.023608987808412706 +flat_mae,patch,logistic,adhd200_dx,90,0.005994842503189409,test,0.5846153846153846,0.06087096450300937,0.5699583435432491,0.0636951798511443,0.5699806949806949,0.06205491313918357 +flat_mae,patch,logistic,adhd200_dx,91,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adhd200_dx,91,2.782559402207126,test,0.5846153846153846,0.06010026336718279,0.5699583435432491,0.062378846189696247,0.5699806949806949,0.06085861925311064 +flat_mae,patch,logistic,adhd200_dx,92,0.046415888336127774,train,0.8328767123287671,0.019084247153022194,0.8272276497838891,0.020036944980048273,0.8232429626915796,0.02009860975432427 +flat_mae,patch,logistic,adhd200_dx,92,0.046415888336127774,test,0.5692307692307692,0.06146311541252215,0.545,0.0649635730538412,0.5477799227799228,0.06227455677545912 +flat_mae,patch,logistic,adhd200_dx,93,0.005994842503189409,train,0.7287671232876712,0.022431162812377923,0.7157879834199825,0.023833123163598657,0.7130732124320693,0.023163644158809425 +flat_mae,patch,logistic,adhd200_dx,93,0.005994842503189409,test,0.6615384615384615,0.0484503039480943,0.622093023255814,0.05827237282747697,0.6288610038610039,0.05124235322205058 +flat_mae,patch,logistic,adhd200_dx,94,0.005994842503189409,train,0.7506849315068493,0.021484262810442502,0.7399979647590196,0.022820196617862182,0.73679550589241,0.022382206926051834 +flat_mae,patch,logistic,adhd200_dx,94,0.005994842503189409,test,0.5846153846153846,0.05223686607669715,0.5308740978348035,0.06316885300951601,0.5482625482625483,0.05419932100442337 +flat_mae,patch,logistic,adhd200_dx,95,0.005994842503189409,train,0.726027397260274,0.023790210254629258,0.7176146561861731,0.024915563232096937,0.7156683153202662,0.024708669055984844 +flat_mae,patch,logistic,adhd200_dx,95,0.005994842503189409,test,0.5538461538461539,0.0584713433073474,0.5381034060279344,0.0615082809429967,0.5386100386100386,0.06012061507801641 +flat_mae,patch,logistic,adhd200_dx,96,0.000774263682681127,train,0.6438356164383562,0.023349988497744733,0.6191080143847932,0.02573508257713248,0.6213286926787568,0.024120585609006095 +flat_mae,patch,logistic,adhd200_dx,96,0.000774263682681127,test,0.5692307692307692,0.06177741300343071,0.545,0.06570498395186582,0.5477799227799228,0.0629116938929283 +flat_mae,patch,logistic,adhd200_dx,97,0.046415888336127774,train,0.8191780821917808,0.020801544466815838,0.812872856077554,0.02189961753690149,0.8089546314953899,0.021857929605452256 +flat_mae,patch,logistic,adhd200_dx,97,0.046415888336127774,test,0.5692307692307692,0.059707174992308334,0.545,0.06421285537688758,0.5477799227799228,0.061117784635458534 +flat_mae,patch,logistic,adhd200_dx,98,0.005994842503189409,train,0.7178082191780822,0.022158782162991136,0.7020266467991345,0.024032354101946648,0.6997771264578372,0.023049639705691287 +flat_mae,patch,logistic,adhd200_dx,98,0.005994842503189409,test,0.676923076923077,0.058956158618529875,0.6655231560891939,0.06125211219336189,0.6640926640926641,0.05999044654691344 +flat_mae,patch,logistic,adhd200_dx,99,0.005994842503189409,train,0.7452054794520548,0.02399249272714593,0.7354763296317943,0.02523875162762978,0.7326586065824021,0.02481433006707826 +flat_mae,patch,logistic,adhd200_dx,99,0.005994842503189409,test,0.5538461538461539,0.059182109882780574,0.5321419707123356,0.061894703318438216,0.5342664092664092,0.060017085576320815 +flat_mae,patch,logistic,adhd200_dx,100,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adhd200_dx,100,2.782559402207126,test,0.6,0.06010618611646771,0.5976190476190476,0.060400606376468,0.6008687258687259,0.060382175832968454 diff --git a/decoders/crossreg_reg4/eval_v2/adhd200_dx__patch__logistic/log.txt b/decoders/crossreg_reg4/eval_v2/adhd200_dx__patch__logistic/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..019eaaff8d3f61a8e1bff6829206d89b0489fd7b --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/adhd200_dx__patch__logistic/log.txt @@ -0,0 +1,241 @@ +fMRI foundation model logistic probe eval +version: 0.1.dev66+g7ddd3aa04 +sha: aef99c83a386cf95c3d8ca503ecc968d8d5694af, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-03-07 21:46:50 +config: +output_root: experiments/decoders/output +name_prefix: eval_logistic +remote_root: null +notes: decoder ablations crossreg_reg4; eval v2 (adhd200_dx patch logistic) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: decoders/crossreg_reg4/eval_v2/adhd200_dx__patch__logistic +model: flat_mae +representation: patch +dataset: adhd200_dx +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg4/eval_v2/adhd200_dx__patch__logistic +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=False, reg_tokens=4, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: adhd200_dx (flat) +train (n=301): +HFDataset( + dataset=Dataset({ + features: ['sub', 'site', 'gender', 'dx', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 301 +}), + labels=['ADHD' 'Control'], + counts=[131 170] +) + +validation (n=64): +HFDataset( + dataset=Dataset({ + features: ['sub', 'site', 'gender', 'dx', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 64 +}), + labels=['ADHD' 'Control'], + counts=[28 36] +) + +test (n=65): +HFDataset( + dataset=Dataset({ + features: ['sub', 'site', 'gender', 'dx', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 65 +}), + labels=['ADHD' 'Control'], + counts=[28 37] +) + +extracting features for all splits +extract (train) [ 0/151] eta: 0:12:55 time: 5.1370 data: 4.0069 max mem: 2698 +extract (train) [ 20/151] eta: 0:00:57 time: 0.2012 data: 0.0728 max mem: 2852 +extract (train) [ 40/151] eta: 0:00:36 time: 0.2069 data: 0.0758 max mem: 2852 +extract (train) [ 60/151] eta: 0:00:25 time: 0.1998 data: 0.0713 max mem: 2852 +extract (train) [ 80/151] eta: 0:00:18 time: 0.1969 data: 0.0723 max mem: 2852 +extract (train) [100/151] eta: 0:00:12 time: 0.1763 data: 0.0595 max mem: 2852 +extract (train) [120/151] eta: 0:00:07 time: 0.1676 data: 0.0540 max mem: 2852 +extract (train) [140/151] eta: 0:00:02 time: 0.1740 data: 0.0579 max mem: 2852 +extract (train) [150/151] eta: 0:00:00 time: 0.1668 data: 0.0555 max mem: 2852 +extract (train) Total time: 0:00:33 (0.2224 s / it) +extract (validation) [ 0/32] eta: 0:02:00 time: 3.7666 data: 3.6335 max mem: 2852 +extract (validation) [20/32] eta: 0:00:04 time: 0.1810 data: 0.0604 max mem: 2852 +extract (validation) [31/32] eta: 0:00:00 time: 0.1594 data: 0.0494 max mem: 2852 +extract (validation) Total time: 0:00:09 (0.2979 s / it) +extract (test) [ 0/33] eta: 0:02:03 time: 3.7426 data: 3.6112 max mem: 2852 +extract (test) [20/33] eta: 0:00:04 time: 0.1942 data: 0.0679 max mem: 2852 +extract (test) [32/33] eta: 0:00:00 time: 0.1507 data: 0.0468 max mem: 2852 +extract (test) Total time: 0:00:09 (0.2954 s / it) +feature extraction time: 0:00:52 +train features: (301, 768) +validation features: (64, 768) +test features: (65, 768) +evaluating fixed splits +eval results (fixed splits): + +| model | repr | clf | dataset | trial | C | split | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:-----------|:--------|----------:|:--------|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | adhd200_dx | | 0.0059948 | train | 0.74247 | 0.021905 | 0.73174 | 0.023336 | 0.7288 | 0.022882 | +| flat_mae | patch | logistic | adhd200_dx | | 0.0059948 | test | 0.58462 | 0.057475 | 0.55012 | 0.064977 | 0.55695 | 0.059498 | + + +evaluating random splits (n=100) +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 1, "C": 0.005994842503189409, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.0595373961343754, "f1": 0.5699583435432491, "f1_std": 0.061553726399329114, "bacc": 0.5699806949806949, "bacc_std": 0.06028514680245595} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 2, "C": 0.3593813663804626, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.06186923411662306, "f1": 0.578226387887527, "f1_std": 0.06294971050534451, "bacc": 0.5786679536679536, "bacc_std": 0.06281953395438065} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 3, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.056654301006059615, "f1": 0.570630081300813, "f1_std": 0.0629693519564316, "bacc": 0.5748069498069498, "bacc_std": 0.05860606934204386} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 4, "C": 0.005994842503189409, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.05718021754161582, "f1": 0.6264367816091954, "f1_std": 0.05816225509061837, "bacc": 0.627895752895753, "bacc_std": 0.05866661248897376} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 5, "C": 0.046415888336127774, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.06097359211093965, "f1": 0.5666666666666667, "f1_std": 0.06144937965341382, "bacc": 0.5694980694980695, "bacc_std": 0.06208679449276509} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 6, "C": 0.3593813663804626, "split": "test", "acc": 0.6615384615384615, "acc_std": 0.059135956082362856, "f1": 0.6575670498084292, "f1_std": 0.059942574087972475, "bacc": 0.6592664092664093, "bacc_std": 0.06033058277089562} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 7, "C": 0.046415888336127774, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.05917168681650083, "f1": 0.5830363506771205, "f1_std": 0.05919782582612036, "bacc": 0.5873552123552124, "bacc_std": 0.05994967511895883} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 8, "C": 0.005994842503189409, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.06192692009096418, "f1": 0.6198830409356726, "f1_std": 0.06462276479873824, "bacc": 0.6192084942084942, "bacc_std": 0.06344098862392855} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 9, "C": 0.005994842503189409, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.054095563041976026, "f1": 0.5962732919254659, "f1_std": 0.06156816960167578, "bacc": 0.6018339768339769, "bacc_std": 0.055989328273165724} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 10, "C": 0.005994842503189409, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.05909105600180356, "f1": 0.5578231292517006, "f1_std": 0.06407308875457003, "bacc": 0.5612934362934363, "bacc_std": 0.060402412127793625} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 11, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.05412110898595687, "f1": 0.5626293995859213, "f1_std": 0.062306311625395884, "bacc": 0.5704633204633205, "bacc_std": 0.05602142058640619} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 12, "C": 0.005994842503189409, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.056831785422591874, "f1": 0.5699583435432491, "f1_std": 0.05977686042399589, "bacc": 0.5699806949806949, "bacc_std": 0.058273607132441826} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 13, "C": 0.005994842503189409, "split": "test", "acc": 0.49230769230769234, "acc_std": 0.0588737773274718, "f1": 0.4743935309973046, "f1_std": 0.060543653424304386, "bacc": 0.47586872586872586, "bacc_std": 0.059637690826888815} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 14, "C": 1291.5496650148827, "split": "test", "acc": 0.6, "acc_std": 0.057080124314125104, "f1": 0.5833333333333333, "f1_std": 0.06070381533140116, "bacc": 0.5834942084942085, "bacc_std": 0.058669222582869274} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 15, "C": 0.005994842503189409, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.061283927446873124, "f1": 0.5294401544401545, "f1_std": 0.0623149636534173, "bacc": 0.5294401544401545, "bacc_std": 0.06222626850432534} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 16, "C": 0.005994842503189409, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.062481171601801194, "f1": 0.5745454545454545, "f1_std": 0.06394244463034299, "bacc": 0.5743243243243243, "bacc_std": 0.06344919493891837} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 17, "C": 0.046415888336127774, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.056206643251150754, "f1": 0.5966741126830479, "f1_std": 0.06061578789763127, "bacc": 0.597007722007722, "bacc_std": 0.05831458026482621} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 18, "C": 0.3593813663804626, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.05923596380818011, "f1": 0.5608108108108107, "f1_std": 0.06037803594609343, "bacc": 0.5608108108108107, "bacc_std": 0.060218470396470755} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 19, "C": 0.000774263682681127, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.05238849867002689, "f1": 0.587737843551797, "f1_std": 0.0629310560687302, "bacc": 0.5974903474903475, "bacc_std": 0.055048676802358774} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 20, "C": 0.005994842503189409, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.05634593909121585, "f1": 0.6036585365853658, "f1_std": 0.06289556976806442, "bacc": 0.6061776061776062, "bacc_std": 0.058661890473261515} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 21, "C": 0.005994842503189409, "split": "test", "acc": 0.7230769230769231, "acc_std": 0.05417740746187419, "f1": 0.7149122807017544, "f1_std": 0.05636841728510411, "bacc": 0.7133204633204633, "bacc_std": 0.05579711314188372} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 22, "C": 0.005994842503189409, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.06171500829231663, "f1": 0.6235521235521235, "f1_std": 0.06334497042852516, "bacc": 0.6235521235521235, "bacc_std": 0.06326613240265587} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 23, "C": 0.000774263682681127, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.05174945558985287, "f1": 0.5656241646618552, "f1_std": 0.06406613287543482, "bacc": 0.5796332046332047, "bacc_std": 0.054493023528735494} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 24, "C": 0.005994842503189409, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.05588169244301624, "f1": 0.5501153550371699, "f1_std": 0.06169691487186124, "bacc": 0.556949806949807, "bacc_std": 0.05693022347504732} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 25, "C": 0.000774263682681127, "split": "test", "acc": 0.6, "acc_std": 0.05099025083752161, "f1": 0.5427489177489178, "f1_std": 0.06181938637330176, "bacc": 0.5617760617760618, "bacc_std": 0.05255712965330673} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 26, "C": 0.005994842503189409, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.05501583204085829, "f1": 0.6036585365853658, "f1_std": 0.061749572456848666, "bacc": 0.6061776061776062, "bacc_std": 0.05731640220304975} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 27, "C": 0.046415888336127774, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.060639308047448666, "f1": 0.6018132810585641, "f1_std": 0.06333183184019378, "bacc": 0.6013513513513513, "bacc_std": 0.06192042359549878} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 28, "C": 0.005994842503189409, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.0546718148343194, "f1": 0.5501153550371699, "f1_std": 0.06075232455253754, "bacc": 0.556949806949807, "bacc_std": 0.0559985707062253} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 29, "C": 0.005994842503189409, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.05950202820868164, "f1": 0.5966741126830479, "f1_std": 0.06341831262949778, "bacc": 0.597007722007722, "bacc_std": 0.061315369217520205} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 30, "C": 0.3593813663804626, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.06032451884569405, "f1": 0.564176245210728, "f1_std": 0.06047048488448265, "bacc": 0.5651544401544402, "bacc_std": 0.06061516498236156} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 31, "C": 0.3593813663804626, "split": "test", "acc": 0.6, "acc_std": 0.061585797179229435, "f1": 0.5921814671814671, "f1_std": 0.06290748518584183, "bacc": 0.5921814671814671, "bacc_std": 0.06264103536840496} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 32, "C": 0.046415888336127774, "split": "test", "acc": 0.5538461538461539, "acc_std": 0.06633448682255583, "f1": 0.543030303030303, "f1_std": 0.0677295747450472, "bacc": 0.542953667953668, "bacc_std": 0.06714117747970659} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 33, "C": 0.3593813663804626, "split": "test", "acc": 0.5538461538461539, "acc_std": 0.06428263037592144, "f1": 0.5521501544309813, "f1_std": 0.06465589680292005, "bacc": 0.555984555984556, "bacc_std": 0.06493353033693425} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 34, "C": 0.046415888336127774, "split": "test", "acc": 0.6, "acc_std": 0.05947099337706104, "f1": 0.5953065134099617, "f1_std": 0.06066406774404732, "bacc": 0.5965250965250966, "bacc_std": 0.06074520327848402} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 35, "C": 0.005994842503189409, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.05892026504638361, "f1": 0.5578231292517006, "f1_std": 0.06423842231664416, "bacc": 0.5612934362934363, "bacc_std": 0.06053049391752815} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 36, "C": 0.000774263682681127, "split": "test", "acc": 0.5230769230769231, "acc_std": 0.05727286293177918, "f1": 0.49987589972697943, "f1_std": 0.059762560808738124, "bacc": 0.502895752895753, "bacc_std": 0.05766843127488071} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 37, "C": 0.005994842503189409, "split": "test", "acc": 0.6615384615384615, "acc_std": 0.05682256406553869, "f1": 0.6425000000000001, "f1_std": 0.0619619253833288, "bacc": 0.6418918918918919, "bacc_std": 0.05898029206476128} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 38, "C": 0.005994842503189409, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.057453132945097955, "f1": 0.5192307692307693, "f1_std": 0.05989794466165466, "bacc": 0.5207528957528957, "bacc_std": 0.05786402876580633} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 39, "C": 0.005994842503189409, "split": "test", "acc": 0.6615384615384615, "acc_std": 0.0560774696607318, "f1": 0.6366869918699187, "f1_std": 0.061839426323924813, "bacc": 0.6375482625482626, "bacc_std": 0.05808815409906013} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 40, "C": 0.005994842503189409, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.05205004419394585, "f1": 0.587737843551797, "f1_std": 0.06211088417396741, "bacc": 0.5974903474903475, "bacc_std": 0.054455122466531274} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 41, "C": 0.005994842503189409, "split": "test", "acc": 0.5538461538461539, "acc_std": 0.06111759932086307, "f1": 0.5469838981014179, "f1_std": 0.06205525189766619, "bacc": 0.5472972972972974, "bacc_std": 0.06190522647687008} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 42, "C": 0.005994842503189409, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.06275487015212963, "f1": 0.5330459770114943, "f1_std": 0.06314375194502904, "bacc": 0.5337837837837838, "bacc_std": 0.06324572364060993} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 43, "C": 0.046415888336127774, "split": "test", "acc": 0.6, "acc_std": 0.05912898347164893, "f1": 0.5921814671814671, "f1_std": 0.06041647484088127, "bacc": 0.5921814671814671, "bacc_std": 0.06011477287930213} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 44, "C": 0.046415888336127774, "split": "test", "acc": 0.6, "acc_std": 0.057710840100355126, "f1": 0.5775, "f1_std": 0.06206447144136149, "bacc": 0.5791505791505791, "bacc_std": 0.05918403745742286} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 45, "C": 0.005994842503189409, "split": "test", "acc": 0.5076923076923077, "acc_std": 0.05994455031465357, "f1": 0.4871794871794872, "f1_std": 0.061936053646823204, "bacc": 0.48938223938223935, "bacc_std": 0.06010449539992708} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 46, "C": 0.000774263682681127, "split": "test", "acc": 0.6615384615384615, "acc_std": 0.05471973563035206, "f1": 0.6299171842650104, "f1_std": 0.06391608106189291, "bacc": 0.6332046332046332, "bacc_std": 0.05748081521955596} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 47, "C": 0.005994842503189409, "split": "test", "acc": 0.5538461538461539, "acc_std": 0.0607249225031844, "f1": 0.5381034060279344, "f1_std": 0.06240298791904154, "bacc": 0.5386100386100386, "bacc_std": 0.06119743641907058} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 48, "C": 0.3593813663804626, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.06416737728544239, "f1": 0.6299810246679317, "f1_std": 0.06424466597952602, "bacc": 0.6365830115830116, "bacc_std": 0.06423716187867733} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 49, "C": 0.005994842503189409, "split": "test", "acc": 0.5076923076923077, "acc_std": 0.06062066357333121, "f1": 0.48, "f1_std": 0.0632875825966212, "bacc": 0.48503861003861004, "bacc_std": 0.061067542538412366} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 50, "C": 0.005994842503189409, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.05310687226392461, "f1": 0.5962732919254659, "f1_std": 0.06153319367059387, "bacc": 0.6018339768339769, "bacc_std": 0.05562395056913396} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 51, "C": 0.005994842503189409, "split": "test", "acc": 0.5538461538461539, "acc_std": 0.062097849870827906, "f1": 0.5469838981014179, "f1_std": 0.0631569322999681, "bacc": 0.5472972972972974, "bacc_std": 0.06323941349555502} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 52, "C": 166.81005372000556, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.05991440837862748, "f1": 0.5842217484008528, "f1_std": 0.0600633172409386, "bacc": 0.5916988416988418, "bacc_std": 0.06048731269124607} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 53, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.05603781478957341, "f1": 0.570630081300813, "f1_std": 0.06217061649701836, "bacc": 0.5748069498069498, "bacc_std": 0.05791292411609699} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 54, "C": 0.005994842503189409, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.06114006424286208, "f1": 0.5699583435432491, "f1_std": 0.06361913080694286, "bacc": 0.5699806949806949, "bacc_std": 0.062218178015642917} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 55, "C": 0.005994842503189409, "split": "test", "acc": 0.5538461538461539, "acc_std": 0.0615722983897311, "f1": 0.5500119360229172, "f1_std": 0.062283864775608454, "bacc": 0.5516409266409266, "bacc_std": 0.06254055242144516} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 56, "C": 0.046415888336127774, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.059886282769139425, "f1": 0.6235521235521235, "f1_std": 0.06123199746900422, "bacc": 0.6235521235521235, "bacc_std": 0.06081287917056077} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 57, "C": 0.046415888336127774, "split": "test", "acc": 0.47692307692307695, "acc_std": 0.061380250471377136, "f1": 0.4666988416988417, "f1_std": 0.06210337530946148, "bacc": 0.4666988416988417, "bacc_std": 0.061938623429712535} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 58, "C": 10000.0, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.06182958829044295, "f1": 0.5810455956075435, "f1_std": 0.06238142369611767, "bacc": 0.583011583011583, "bacc_std": 0.06273800949872903} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 59, "C": 0.005994842503189409, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.05534578981010337, "f1": 0.5411764705882354, "f1_std": 0.06181641099500292, "bacc": 0.5526061776061776, "bacc_std": 0.056166560066473796} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 60, "C": 0.005994842503189409, "split": "test", "acc": 0.6615384615384615, "acc_std": 0.056132252961066935, "f1": 0.6425000000000001, "f1_std": 0.06006833363648928, "bacc": 0.6418918918918919, "bacc_std": 0.05772516890499275} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 61, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.061166096499177924, "f1": 0.5833333333333333, "f1_std": 0.06477892257281674, "bacc": 0.5834942084942085, "bacc_std": 0.06280781966608415} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 62, "C": 0.005994842503189409, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.057135230429333335, "f1": 0.5512820512820513, "f1_std": 0.06024928311266914, "bacc": 0.5521235521235521, "bacc_std": 0.05848726018596496} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 63, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.054644793815369644, "f1": 0.570630081300813, "f1_std": 0.05967058236001123, "bacc": 0.5748069498069498, "bacc_std": 0.056116287203535634} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 64, "C": 0.005994842503189409, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.05592199977800864, "f1": 0.6036585365853658, "f1_std": 0.06227386364878947, "bacc": 0.6061776061776062, "bacc_std": 0.05792586044684726} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 65, "C": 0.005994842503189409, "split": "test", "acc": 0.676923076923077, "acc_std": 0.05373611613723858, "f1": 0.6612062546537603, "f1_std": 0.05776392214398613, "bacc": 0.6597490347490347, "bacc_std": 0.055688565931782875} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 66, "C": 0.005994842503189409, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.05826989641660921, "f1": 0.5966741126830479, "f1_std": 0.06189744657713271, "bacc": 0.597007722007722, "bacc_std": 0.059638607200298205} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 67, "C": 0.046415888336127774, "split": "test", "acc": 0.6, "acc_std": 0.0547095612729124, "f1": 0.5626293995859213, "f1_std": 0.06242501864664253, "bacc": 0.5704633204633205, "bacc_std": 0.056400707961241414} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 68, "C": 0.3593813663804626, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.05780803981675578, "f1": 0.5644080416976918, "f1_std": 0.06163621427551431, "bacc": 0.5656370656370656, "bacc_std": 0.05918942817174904} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 69, "C": 0.005994842503189409, "split": "test", "acc": 0.4461538461538462, "acc_std": 0.06193028338381796, "f1": 0.4230769230769231, "f1_std": 0.06270234320564441, "bacc": 0.4266409266409266, "bacc_std": 0.0616888681227142} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 70, "C": 0.005994842503189409, "split": "test", "acc": 0.5230769230769231, "acc_std": 0.06104710762282211, "f1": 0.5062484685126194, "f1_std": 0.0635014107595719, "bacc": 0.5072393822393823, "bacc_std": 0.06190383000831069} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 71, "C": 0.005994842503189409, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.05659594147742377, "f1": 0.5376016260162602, "f1_std": 0.062044019075676825, "bacc": 0.5434362934362934, "bacc_std": 0.057753081923810734} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 72, "C": 0.005994842503189409, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.05609029913277994, "f1": 0.6036585365853658, "f1_std": 0.06115136061865767, "bacc": 0.6061776061776062, "bacc_std": 0.057341517022094335} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 73, "C": 0.000774263682681127, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.060231223104685414, "f1": 0.545, "f1_std": 0.06383778070712375, "bacc": 0.5477799227799228, "bacc_std": 0.061274607351757174} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 74, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.06086725492326306, "f1": 0.588206627680312, "f1_std": 0.06293773736882363, "bacc": 0.5878378378378378, "bacc_std": 0.06173305166009477} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 75, "C": 0.000774263682681127, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.06144790259828085, "f1": 0.5512820512820513, "f1_std": 0.06439173788759277, "bacc": 0.5521235521235521, "bacc_std": 0.06257055113749697} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 76, "C": 0.005994842503189409, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.05334802558970225, "f1": 0.5308740978348035, "f1_std": 0.06315106954948436, "bacc": 0.5482625482625483, "bacc_std": 0.05494262135581445} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 77, "C": 0.005994842503189409, "split": "test", "acc": 0.6923076923076923, "acc_std": 0.04830603622835012, "f1": 0.6564482029598309, "f1_std": 0.059567725263369425, "bacc": 0.6602316602316602, "bacc_std": 0.05192352376469467} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 78, "C": 0.046415888336127774, "split": "test", "acc": 0.5076923076923077, "acc_std": 0.060007691814658856, "f1": 0.4871794871794872, "f1_std": 0.06246715479628248, "bacc": 0.48938223938223935, "bacc_std": 0.06073682705315684} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 79, "C": 0.046415888336127774, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.06071768797587812, "f1": 0.5608108108108107, "f1_std": 0.06181523711408662, "bacc": 0.5608108108108107, "bacc_std": 0.06143627732299396} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 80, "C": 0.005994842503189409, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.062282243615837125, "f1": 0.5512820512820513, "f1_std": 0.06525275785157907, "bacc": 0.5521235521235521, "bacc_std": 0.06337668133097127} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 81, "C": 0.005994842503189409, "split": "test", "acc": 0.5076923076923077, "acc_std": 0.05577023871768183, "f1": 0.4715447154471545, "f1_std": 0.05882071122044139, "bacc": 0.4806949806949807, "bacc_std": 0.05586864545332324} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 82, "C": 0.005994842503189409, "split": "test", "acc": 0.6923076923076923, "acc_std": 0.05898531358681508, "f1": 0.6886973180076628, "f1_std": 0.059702359059180116, "bacc": 0.6906370656370657, "bacc_std": 0.05973689950897015} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 83, "C": 0.005994842503189409, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.058050180292163286, "f1": 0.6198830409356726, "f1_std": 0.06017459518282782, "bacc": 0.6192084942084942, "bacc_std": 0.05946718303394383} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 84, "C": 0.005994842503189409, "split": "test", "acc": 0.5538461538461539, "acc_std": 0.06545242456667899, "f1": 0.5500119360229172, "f1_std": 0.06612552498382575, "bacc": 0.5516409266409266, "bacc_std": 0.06640017639902036} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 85, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.058201039052112824, "f1": 0.5833333333333333, "f1_std": 0.06141692894530669, "bacc": 0.5834942084942085, "bacc_std": 0.05955812962727085} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 86, "C": 0.3593813663804626, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.06266370465953001, "f1": 0.5608108108108107, "f1_std": 0.0638736425392196, "bacc": 0.5608108108108107, "bacc_std": 0.06345222216046117} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 87, "C": 0.3593813663804626, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.06240130479594706, "f1": 0.5565302144249512, "f1_std": 0.06437824570753099, "bacc": 0.5564671814671815, "bacc_std": 0.06360930550576196} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 88, "C": 0.000774263682681127, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.059721634350270884, "f1": 0.545, "f1_std": 0.06365544719042884, "bacc": 0.5477799227799228, "bacc_std": 0.0608539734283045} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 89, "C": 0.005994842503189409, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.055941431756634984, "f1": 0.61, "f1_std": 0.060568572762768585, "bacc": 0.6105212355212355, "bacc_std": 0.05787304586244429} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 90, "C": 0.005994842503189409, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.06087096450300937, "f1": 0.5699583435432491, "f1_std": 0.0636951798511443, "bacc": 0.5699806949806949, "bacc_std": 0.06205491313918357} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 91, "C": 2.782559402207126, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.06010026336718279, "f1": 0.5699583435432491, "f1_std": 0.062378846189696247, "bacc": 0.5699806949806949, "bacc_std": 0.06085861925311064} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 92, "C": 0.046415888336127774, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.06146311541252215, "f1": 0.545, "f1_std": 0.0649635730538412, "bacc": 0.5477799227799228, "bacc_std": 0.06227455677545912} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 93, "C": 0.005994842503189409, "split": "test", "acc": 0.6615384615384615, "acc_std": 0.0484503039480943, "f1": 0.622093023255814, "f1_std": 0.05827237282747697, "bacc": 0.6288610038610039, "bacc_std": 0.05124235322205058} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 94, "C": 0.005994842503189409, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.05223686607669715, "f1": 0.5308740978348035, "f1_std": 0.06316885300951601, "bacc": 0.5482625482625483, "bacc_std": 0.05419932100442337} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 95, "C": 0.005994842503189409, "split": "test", "acc": 0.5538461538461539, "acc_std": 0.0584713433073474, "f1": 0.5381034060279344, "f1_std": 0.0615082809429967, "bacc": 0.5386100386100386, "bacc_std": 0.06012061507801641} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 96, "C": 0.000774263682681127, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.06177741300343071, "f1": 0.545, "f1_std": 0.06570498395186582, "bacc": 0.5477799227799228, "bacc_std": 0.0629116938929283} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 97, "C": 0.046415888336127774, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.059707174992308334, "f1": 0.545, "f1_std": 0.06421285537688758, "bacc": 0.5477799227799228, "bacc_std": 0.061117784635458534} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 98, "C": 0.005994842503189409, "split": "test", "acc": 0.676923076923077, "acc_std": 0.058956158618529875, "f1": 0.6655231560891939, "f1_std": 0.06125211219336189, "bacc": 0.6640926640926641, "bacc_std": 0.05999044654691344} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 99, "C": 0.005994842503189409, "split": "test", "acc": 0.5538461538461539, "acc_std": 0.059182109882780574, "f1": 0.5321419707123356, "f1_std": 0.061894703318438216, "bacc": 0.5342664092664092, "bacc_std": 0.060017085576320815} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 100, "C": 2.782559402207126, "split": "test", "acc": 0.6, "acc_std": 0.06010618611646771, "f1": 0.5976190476190476, "f1_std": 0.060400606376468, "bacc": 0.6008687258687259, "bacc_std": 0.060382175832968454} +eval results (random splits): + +| model | repr | clf | dataset | split | n_trials | C | C_std | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:-----------|:--------|-----------:|-------:|--------:|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | adhd200_dx | train | 100 | 114.69 | 1006.9 | 0.77258 | 0.096606 | 0.76138 | 0.10314 | 0.75948 | 0.10258 | +| flat_mae | patch | logistic | adhd200_dx | test | 100 | 114.69 | 1006.9 | 0.59123 | 0.047115 | 0.5718 | 0.047856 | 0.57458 | 0.047088 | + + +done! total time: 0:04:48 diff --git a/decoders/crossreg_reg4/eval_v2/adhd200_dx__reg__logistic/config.yaml b/decoders/crossreg_reg4/eval_v2/adhd200_dx__reg__logistic/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..cb7aa474257ee12b2fe91bec8d4f0e68e7997661 --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/adhd200_dx__reg__logistic/config.yaml @@ -0,0 +1,30 @@ +output_root: experiments/decoders/output +name_prefix: eval_logistic +remote_root: null +notes: decoder ablations crossreg_reg4; eval v2 (adhd200_dx reg logistic) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: decoders/crossreg_reg4/eval_v2/adhd200_dx__reg__logistic +model: flat_mae +representation: reg +dataset: adhd200_dx +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg4/eval_v2/adhd200_dx__reg__logistic +remote_dir: null diff --git a/decoders/crossreg_reg4/eval_v2/adhd200_dx__reg__logistic/eval_table.csv b/decoders/crossreg_reg4/eval_v2/adhd200_dx__reg__logistic/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..b6e318ae4c718d1d8bdd0bfe25d91d6ebe5dc4a8 --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/adhd200_dx__reg__logistic/eval_table.csv @@ -0,0 +1,203 @@ +model,repr,clf,dataset,trial,C,split,acc,acc_std,f1,f1_std,bacc,bacc_std +flat_mae,reg,logistic,adhd200_dx,,0.005994842503189409,train,0.7424657534246575,0.021432767270098234,0.7329212853406402,0.0227187920646136,0.7302314221163827,0.02238807596624753 +flat_mae,reg,logistic,adhd200_dx,,0.005994842503189409,test,0.6307692307692307,0.05831768536246534,0.6036585365853658,0.06489270617713994,0.6061776061776062,0.06058231523849871 +flat_mae,reg,logistic,adhd200_dx,1,0.000774263682681127,train,0.7013698630136986,0.02304642422061071,0.682037962037962,0.02541632754350979,0.6809092019295353,0.02407710497437812 +flat_mae,reg,logistic,adhd200_dx,1,0.000774263682681127,test,0.6153846153846154,0.05411907974919205,0.5905769715293525,0.05803834559566884,0.5926640926640927,0.055124868248523945 +flat_mae,reg,logistic,adhd200_dx,2,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adhd200_dx,2,1291.5496650148827,test,0.6153846153846154,0.05982351954811971,0.61207925519217,0.05981363839382905,0.6143822393822393,0.05986497517915926 +flat_mae,reg,logistic,adhd200_dx,3,0.005994842503189409,train,0.7479452054794521,0.023249991111728194,0.7386038111844564,0.024648198527342884,0.7358032606704524,0.024378936098951278 +flat_mae,reg,logistic,adhd200_dx,3,0.005994842503189409,test,0.5538461538461539,0.060202254769152454,0.5321419707123356,0.0636341211291953,0.5342664092664092,0.061413303360600593 +flat_mae,reg,logistic,adhd200_dx,4,0.046415888336127774,train,0.8547945205479452,0.018185074684058288,0.8510330276218419,0.018842934900027218,0.8484001953959822,0.019027185030518316 +flat_mae,reg,logistic,adhd200_dx,4,0.046415888336127774,test,0.6461538461538462,0.05993241953436056,0.6407113674597452,0.061089912956029384,0.6414092664092663,0.060926841989675636 +flat_mae,reg,logistic,adhd200_dx,5,0.005994842503189409,train,0.7726027397260274,0.02138304897018664,0.7649163103616852,0.022612783110910736,0.7619527385968126,0.02249119771561826 +flat_mae,reg,logistic,adhd200_dx,5,0.005994842503189409,test,0.47692307692307695,0.06159348309491283,0.47078544061302685,0.062117338927684625,0.471042471042471,0.062499876082523505 +flat_mae,reg,logistic,adhd200_dx,6,0.005994842503189409,train,0.7397260273972602,0.020798504500418563,0.7279303878414111,0.022090635981922742,0.7249343591622397,0.02154517603989293 +flat_mae,reg,logistic,adhd200_dx,6,0.005994842503189409,test,0.7384615384615385,0.053718697504113615,0.7257383966244726,0.058208076716623855,0.7224903474903475,0.056404911743680015 +flat_mae,reg,logistic,adhd200_dx,7,0.046415888336127774,train,0.8301369863013699,0.01791263299229994,0.8255796029103466,0.018667046943875654,0.822968187091653,0.01887327657820457 +flat_mae,reg,logistic,adhd200_dx,7,0.046415888336127774,test,0.6307692307692307,0.056917080765269724,0.6198830409356726,0.058583785673106514,0.6192084942084942,0.05773996728003387 +flat_mae,reg,logistic,adhd200_dx,8,0.000774263682681127,train,0.6821917808219178,0.023722356639701497,0.6630483224040238,0.026608127465403652,0.6624839714233376,0.02515418969944185 +flat_mae,reg,logistic,adhd200_dx,8,0.000774263682681127,test,0.6461538461538462,0.06106987752426234,0.6289401836684041,0.0653821254722588,0.6283783783783784,0.06295308465640816 +flat_mae,reg,logistic,adhd200_dx,9,0.000774263682681127,train,0.7041095890410959,0.02425270350542799,0.6937919463087248,0.025495257997463203,0.6919460218599255,0.025124258012071896 +flat_mae,reg,logistic,adhd200_dx,9,0.000774263682681127,test,0.5384615384615384,0.05281294444160177,0.4846723044397463,0.06004305365181408,0.5033783783783784,0.053475815367940965 +flat_mae,reg,logistic,adhd200_dx,10,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adhd200_dx,10,2.782559402207126,test,0.5538461538461539,0.05879770554634587,0.5250692869740489,0.0635217987613546,0.5299227799227799,0.060001900121408776 +flat_mae,reg,logistic,adhd200_dx,11,0.000774263682681127,train,0.6794520547945205,0.02182284633716653,0.6499274524752232,0.025218409094760103,0.6528820907370092,0.02289642306486321 +flat_mae,reg,logistic,adhd200_dx,11,0.000774263682681127,test,0.6153846153846154,0.053510160512808304,0.5834401435529352,0.06111724552426378,0.5883204633204633,0.05553877742815464 +flat_mae,reg,logistic,adhd200_dx,12,0.005994842503189409,train,0.7589041095890411,0.023487155271573124,0.751976772918211,0.024292478379561354,0.7498168162667155,0.02408962731701068 +flat_mae,reg,logistic,adhd200_dx,12,0.005994842503189409,test,0.5538461538461539,0.05688007523359899,0.5321419707123356,0.060712565554667496,0.5342664092664092,0.05823910805825308 +flat_mae,reg,logistic,adhd200_dx,13,0.3593813663804626,train,0.9808219178082191,0.007022255054729113,0.9804551539491299,0.00717393691057325,0.9794223606277096,0.007561225095708522 +flat_mae,reg,logistic,adhd200_dx,13,0.3593813663804626,test,0.5384615384615384,0.060106383006353896,0.5294401544401545,0.061881266227136356,0.5294401544401545,0.06160227225701969 +flat_mae,reg,logistic,adhd200_dx,14,0.005994842503189409,train,0.7534246575342466,0.02216630636629756,0.7442863370282725,0.023292926587379276,0.7413750992245222,0.023006980497255344 +flat_mae,reg,logistic,adhd200_dx,14,0.005994842503189409,test,0.6461538461538462,0.05608597795418141,0.6233308138070043,0.061928870062683036,0.6240347490347491,0.05848052685892671 +flat_mae,reg,logistic,adhd200_dx,15,0.005994842503189409,train,0.7616438356164383,0.021972080750811307,0.7519935020813646,0.023376915649536808,0.7486566526225804,0.023008531648180043 +flat_mae,reg,logistic,adhd200_dx,15,0.005994842503189409,test,0.6461538461538462,0.058649890913300196,0.6407113674597452,0.05924847460360398,0.6414092664092663,0.059291018842661025 +flat_mae,reg,logistic,adhd200_dx,16,0.005994842503189409,train,0.7479452054794521,0.021429657126076224,0.7429262616364527,0.021988685828156107,0.7422604872687305,0.022045359695777537 +flat_mae,reg,logistic,adhd200_dx,16,0.005994842503189409,test,0.6307692307692307,0.05970876854717504,0.6198830409356726,0.06181351128591715,0.6192084942084942,0.06102563711942756 +flat_mae,reg,logistic,adhd200_dx,17,0.046415888336127774,train,0.8602739726027397,0.017523060644309675,0.8558418325860186,0.018274017709909614,0.8518196250839593,0.018350568811968268 +flat_mae,reg,logistic,adhd200_dx,17,0.046415888336127774,test,0.6153846153846154,0.05645310354097713,0.5905769715293525,0.062467746307242854,0.5926640926640927,0.05874038912674361 +flat_mae,reg,logistic,adhd200_dx,18,0.000774263682681127,train,0.684931506849315,0.02305297105739498,0.6625505470740982,0.025870807605397433,0.6627587470232643,0.024152588164445512 +flat_mae,reg,logistic,adhd200_dx,18,0.000774263682681127,test,0.6307692307692307,0.05155016170292421,0.587737843551797,0.06202705212374842,0.5974903474903475,0.05398135472476604 +flat_mae,reg,logistic,adhd200_dx,19,0.005994842503189409,train,0.7479452054794521,0.023945631167652776,0.7386038111844564,0.025268604078505005,0.7358032606704524,0.024901641656825742 +flat_mae,reg,logistic,adhd200_dx,19,0.005994842503189409,test,0.6923076923076923,0.053726072698215756,0.6697154471544715,0.060637238627391545,0.6689189189189189,0.0566715544766336 +flat_mae,reg,logistic,adhd200_dx,20,0.046415888336127774,train,0.8767123287671232,0.01641901693449214,0.8737402854968521,0.01694082423186053,0.871405019234292,0.017166366333024544 +flat_mae,reg,logistic,adhd200_dx,20,0.046415888336127774,test,0.6,0.055196055085861166,0.588206627680312,0.05765580387147078,0.5878378378378378,0.0566229473123185 +flat_mae,reg,logistic,adhd200_dx,21,0.005994842503189409,train,0.7506849315068493,0.022937833859816008,0.74059090447591,0.024358071143080633,0.737512975514441,0.023928879725356338 +flat_mae,reg,logistic,adhd200_dx,21,0.005994842503189409,test,0.6615384615384615,0.059167070643396824,0.6515594541910331,0.061347152699184,0.6505791505791505,0.06070435213929338 +flat_mae,reg,logistic,adhd200_dx,22,0.005994842503189409,train,0.7479452054794521,0.02131442334481628,0.7374429223744292,0.02254563754942046,0.7343683214263906,0.022112255922936624 +flat_mae,reg,logistic,adhd200_dx,22,0.005994842503189409,test,0.676923076923077,0.05792256818654922,0.6690909090909091,0.05927840706231435,0.6684362934362934,0.05876856765235649 +flat_mae,reg,logistic,adhd200_dx,23,0.005994842503189409,train,0.7616438356164383,0.02109528623934705,0.7530734597709193,0.022275355082248677,0.7500915918666422,0.02203220466244194 +flat_mae,reg,logistic,adhd200_dx,23,0.005994842503189409,test,0.5846153846153846,0.05426927383741408,0.5411764705882354,0.06215790303130002,0.5526061776061776,0.05567246337907471 +flat_mae,reg,logistic,adhd200_dx,24,0.005994842503189409,train,0.7589041095890411,0.020917929326559552,0.7515008974438324,0.021766369970395452,0.7490993466446846,0.021614116519920075 +flat_mae,reg,logistic,adhd200_dx,24,0.005994842503189409,test,0.676923076923077,0.05266031370067268,0.6500897205844656,0.0600487333055939,0.6510617760617761,0.05519130375835446 +flat_mae,reg,logistic,adhd200_dx,25,0.000774263682681127,train,0.673972602739726,0.022710543413478355,0.6486438388299722,0.02557879722762291,0.6501801306710631,0.02367818329277033 +flat_mae,reg,logistic,adhd200_dx,25,0.000774263682681127,test,0.6,0.05597844893851678,0.5626293995859213,0.06369848285291128,0.5704633204633205,0.05755100879334684 +flat_mae,reg,logistic,adhd200_dx,26,0.005994842503189409,train,0.7452054794520548,0.02214989180305054,0.7354763296317943,0.023511789538119717,0.7326586065824021,0.023139669715843768 +flat_mae,reg,logistic,adhd200_dx,26,0.005994842503189409,test,0.5538461538461539,0.058837688682233734,0.5381034060279344,0.06061713559113523,0.5386100386100386,0.0594176832945171 +flat_mae,reg,logistic,adhd200_dx,27,0.000774263682681127,train,0.684931506849315,0.02371374860226925,0.6706525747553924,0.025381640396760524,0.6692159736215424,0.024567572477019625 +flat_mae,reg,logistic,adhd200_dx,27,0.000774263682681127,test,0.5846153846153846,0.05810045575191198,0.5644080416976918,0.061223062076996924,0.5656370656370656,0.059142547955176164 +flat_mae,reg,logistic,adhd200_dx,28,0.005994842503189409,train,0.7643835616438356,0.020554927763372893,0.7576136644427971,0.021224727931052827,0.7553886548207852,0.021077732165782303 +flat_mae,reg,logistic,adhd200_dx,28,0.005994842503189409,test,0.5692307692307692,0.056173391751152095,0.545,0.05990328108932862,0.5477799227799228,0.057244263596738974 +flat_mae,reg,logistic,adhd200_dx,29,0.000774263682681127,train,0.6931506849315069,0.024383260579948367,0.6755555555555555,0.02619558065059491,0.674345118153508,0.025052829859681044 +flat_mae,reg,logistic,adhd200_dx,29,0.000774263682681127,test,0.6153846153846154,0.05356550157125276,0.5751633986928104,0.06256352385242225,0.583976833976834,0.0557865532664454 +flat_mae,reg,logistic,adhd200_dx,30,0.000774263682681127,train,0.6931506849315069,0.023546665516241544,0.6788587229763701,0.025734910444985017,0.6772149966416315,0.024854097442394734 +flat_mae,reg,logistic,adhd200_dx,30,0.000774263682681127,test,0.5846153846153846,0.05932626866613266,0.5578231292517006,0.06523901397147255,0.5612934362934363,0.06115253981183368 +flat_mae,reg,logistic,adhd200_dx,31,0.005994842503189409,train,0.7561643835616438,0.022577083986557823,0.7484298647089345,0.023434953979992876,0.7459546925566343,0.023179336800088667 +flat_mae,reg,logistic,adhd200_dx,31,0.005994842503189409,test,0.6153846153846154,0.058603196794681886,0.5905769715293525,0.0635328202944105,0.5926640926640927,0.060246074437261904 +flat_mae,reg,logistic,adhd200_dx,32,0.046415888336127774,train,0.863013698630137,0.0181830016776489,0.8588073280930866,0.019017806171317625,0.8549642791720096,0.019226617681662315 +flat_mae,reg,logistic,adhd200_dx,32,0.046415888336127774,test,0.5538461538461539,0.06127886784994003,0.5469838981014179,0.06226163907065569,0.5472972972972974,0.062280828805024564 +flat_mae,reg,logistic,adhd200_dx,33,0.3593813663804626,train,0.9780821917808219,0.006942057052981699,0.9776457618814307,0.007099990537129171,0.9762777065396593,0.007482900932862325 +flat_mae,reg,logistic,adhd200_dx,33,0.3593813663804626,test,0.6,0.061925513568877495,0.5953065134099617,0.06290342684129337,0.5965250965250966,0.06320772560998983 +flat_mae,reg,logistic,adhd200_dx,34,0.005994842503189409,train,0.7479452054794521,0.020606845991263133,0.7416446113128577,0.02121415364396825,0.7401080784026378,0.02114539141424023 +flat_mae,reg,logistic,adhd200_dx,34,0.005994842503189409,test,0.5846153846153846,0.059881342235532715,0.5810455956075435,0.06020453016925911,0.583011583011583,0.06033649823807296 +flat_mae,reg,logistic,adhd200_dx,35,0.005994842503189409,train,0.7534246575342466,0.02159453653720562,0.7425548589341693,0.02303682313429695,0.7392226903584295,0.02255250192219167 +flat_mae,reg,logistic,adhd200_dx,35,0.005994842503189409,test,0.5692307692307692,0.057396748562633146,0.5512820512820513,0.06075726221488239,0.5521235521235521,0.05890187492733762 +flat_mae,reg,logistic,adhd200_dx,36,0.005994842503189409,train,0.736986301369863,0.023348088588964106,0.7289100699387263,0.024407238139724938,0.7268119924284057,0.02425788152373696 +flat_mae,reg,logistic,adhd200_dx,36,0.005994842503189409,test,0.7230769230769231,0.05386394431381182,0.7149122807017544,0.056342636739836464,0.7133204633204633,0.05546971450442966 +flat_mae,reg,logistic,adhd200_dx,37,0.000774263682681127,train,0.6657534246575343,0.022335184219499322,0.642547521191883,0.02476569263412069,0.6436160468950357,0.023295470723575216 +flat_mae,reg,logistic,adhd200_dx,37,0.000774263682681127,test,0.676923076923077,0.04783300338696862,0.6351242983159583,0.05987041344292248,0.6423745173745173,0.051200731611956665 +flat_mae,reg,logistic,adhd200_dx,38,0.000774263682681127,train,0.6958904109589041,0.0241019732678938,0.6842781998831093,0.02542472445672463,0.6825120595957745,0.02489126691342445 +flat_mae,reg,logistic,adhd200_dx,38,0.000774263682681127,test,0.5230769230769231,0.06064992377932448,0.5115151515151515,0.061714609204104924,0.5115830115830116,0.0610801540411007 +flat_mae,reg,logistic,adhd200_dx,39,0.005994842503189409,train,0.7452054794520548,0.02238943535548907,0.734283634314163,0.02397634474925081,0.7312236673383403,0.02348873167729606 +flat_mae,reg,logistic,adhd200_dx,39,0.005994842503189409,test,0.6307692307692307,0.056621036507184586,0.6036585365853658,0.06219801627552449,0.6061776061776062,0.05833223636472194 +flat_mae,reg,logistic,adhd200_dx,40,10000.0,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adhd200_dx,40,10000.0,test,0.6,0.058673453973525636,0.5833333333333333,0.06058733046494953,0.5834942084942085,0.059312206242286496 +flat_mae,reg,logistic,adhd200_dx,41,0.005994842503189409,train,0.7863013698630137,0.020115617027929734,0.7783814920911696,0.021323852328439044,0.7748061305489405,0.021161157073443425 +flat_mae,reg,logistic,adhd200_dx,41,0.005994842503189409,test,0.5538461538461539,0.06032153687242134,0.5521501544309813,0.06052284569814894,0.555984555984556,0.06046982366147405 +flat_mae,reg,logistic,adhd200_dx,42,0.005994842503189409,train,0.7561643835616438,0.021688986372246803,0.7457122952038764,0.022763403077116686,0.7423673444464798,0.022309199254823133 +flat_mae,reg,logistic,adhd200_dx,42,0.005994842503189409,test,0.5384615384615384,0.06173270114398481,0.5374762808349146,0.0618262721673731,0.5424710424710424,0.06221652257362289 +flat_mae,reg,logistic,adhd200_dx,43,0.005994842503189409,train,0.7506849315068493,0.021999226175851577,0.74059090447591,0.023208868952126725,0.737512975514441,0.022750280865841875 +flat_mae,reg,logistic,adhd200_dx,43,0.005994842503189409,test,0.6153846153846154,0.0595263036682303,0.5966741126830479,0.06296582066821696,0.597007722007722,0.06068776921401086 +flat_mae,reg,logistic,adhd200_dx,44,0.005994842503189409,train,0.7479452054794521,0.022493717977929577,0.7380328278100231,0.023957101507183734,0.7350857910484215,0.023603705615218212 +flat_mae,reg,logistic,adhd200_dx,44,0.005994842503189409,test,0.6615384615384615,0.05573682029049267,0.6425000000000001,0.06073148828822711,0.6418918918918919,0.05809082562166728 +flat_mae,reg,logistic,adhd200_dx,45,0.005994842503189409,train,0.7726027397260274,0.022927756031113373,0.763396099686819,0.024488438140326658,0.7598003297307199,0.024196809060950585 +flat_mae,reg,logistic,adhd200_dx,45,0.005994842503189409,test,0.5230769230769231,0.06299233352432847,0.5062484685126194,0.06532016945212119,0.5072393822393823,0.06397253542919706 +flat_mae,reg,logistic,adhd200_dx,46,0.005994842503189409,train,0.7561643835616438,0.021738368897053252,0.7484298647089345,0.02269408552061702,0.7459546925566343,0.022538139806854894 +flat_mae,reg,logistic,adhd200_dx,46,0.005994842503189409,test,0.676923076923077,0.05643008975347992,0.656084656084656,0.06234477923313667,0.6554054054054055,0.05861205218561572 +flat_mae,reg,logistic,adhd200_dx,47,0.046415888336127774,train,0.8712328767123287,0.017134221166927466,0.8674071154188019,0.017995946575237984,0.8636807718141296,0.0183746087539179 +flat_mae,reg,logistic,adhd200_dx,47,0.046415888336127774,test,0.46153846153846156,0.06234833242527836,0.4484848484848485,0.062453538488762374,0.4488416988416989,0.06218658668910828 +flat_mae,reg,logistic,adhd200_dx,48,0.3593813663804626,train,0.9780821917808219,0.007980640866231637,0.9776457618814307,0.008172440564953318,0.9762777065396593,0.008675571382909449 +flat_mae,reg,logistic,adhd200_dx,48,0.3593813663804626,test,0.5692307692307692,0.06280399489799936,0.5666666666666667,0.06318806739640898,0.5694980694980695,0.06343270481017102 +flat_mae,reg,logistic,adhd200_dx,49,0.005994842503189409,train,0.7534246575342466,0.021693484930315893,0.7419400452488687,0.023095609813974294,0.7385052207363986,0.022531806730338985 +flat_mae,reg,logistic,adhd200_dx,49,0.005994842503189409,test,0.5846153846153846,0.0621158756827457,0.5699583435432491,0.06474627044543364,0.5699806949806949,0.06336489636056991 +flat_mae,reg,logistic,adhd200_dx,50,0.005994842503189409,train,0.7643835616438356,0.021669583436527546,0.7551176433876303,0.023207623751255957,0.7518013067106307,0.022898686829651068 +flat_mae,reg,logistic,adhd200_dx,50,0.005994842503189409,test,0.6,0.06033609221410216,0.5921814671814671,0.061513932952100905,0.5921814671814671,0.06099065790483331 +flat_mae,reg,logistic,adhd200_dx,51,0.005994842503189409,train,0.736986301369863,0.02251999799348507,0.7294292068198666,0.023325480869851655,0.7275294620504366,0.023157145967618722 +flat_mae,reg,logistic,adhd200_dx,51,0.005994842503189409,test,0.5846153846153846,0.06178359637529276,0.578226387887527,0.062920359380333,0.5786679536679536,0.0629802191214737 +flat_mae,reg,logistic,adhd200_dx,52,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adhd200_dx,52,21.54434690031882,test,0.6615384615384615,0.057219651525590914,0.6474358974358974,0.06013768427786563,0.6462355212355213,0.058820055283587996 +flat_mae,reg,logistic,adhd200_dx,53,0.005994842503189409,train,0.7287671232876712,0.02204774838520243,0.7164748252242072,0.02375588459307742,0.7137906820541002,0.023150719186480213 +flat_mae,reg,logistic,adhd200_dx,53,0.005994842503189409,test,0.676923076923077,0.05364590456803835,0.6431372549019607,0.06376578705762419,0.6467181467181468,0.05706349375027341 +flat_mae,reg,logistic,adhd200_dx,54,0.005994842503189409,train,0.7479452054794521,0.02089669341867548,0.7396899224806202,0.022032944345160215,0.7372381999145142,0.0218885581747688 +flat_mae,reg,logistic,adhd200_dx,54,0.005994842503189409,test,0.5692307692307692,0.058525179934713,0.5512820512820513,0.06211518037030336,0.5521235521235521,0.060094851279050426 +flat_mae,reg,logistic,adhd200_dx,55,0.046415888336127774,train,0.8684931506849315,0.01747241151632794,0.865874571288584,0.017876019713317017,0.8648409354582647,0.018043306517012383 +flat_mae,reg,logistic,adhd200_dx,55,0.046415888336127774,test,0.5692307692307692,0.06259961245319288,0.5666666666666667,0.06275244593889474,0.5694980694980695,0.0630294216601441 +flat_mae,reg,logistic,adhd200_dx,56,0.046415888336127774,train,0.8657534246575342,0.01755551022330597,0.8622758179900047,0.018139984459181076,0.8595438725041217,0.018257867290157565 +flat_mae,reg,logistic,adhd200_dx,56,0.046415888336127774,test,0.5538461538461539,0.06114817777309814,0.543030303030303,0.06277857389640336,0.542953667953668,0.061992414940413895 +flat_mae,reg,logistic,adhd200_dx,57,0.005994842503189409,train,0.7616438356164383,0.02218637106394491,0.752542372881356,0.023454888880720216,0.7493741222446113,0.023099047994873688 +flat_mae,reg,logistic,adhd200_dx,57,0.005994842503189409,test,0.6,0.05858267611528516,0.5833333333333333,0.06128363991719677,0.5834942084942085,0.059470954111315665 +flat_mae,reg,logistic,adhd200_dx,58,0.005994842503189409,train,0.7616438356164383,0.020893529342821054,0.7554693094924574,0.021611016491538963,0.7536789399767967,0.021579351029848752 +flat_mae,reg,logistic,adhd200_dx,58,0.005994842503189409,test,0.6153846153846154,0.05920079161472971,0.61207925519217,0.05991549883732456,0.6143822393822393,0.06017431376178625 +flat_mae,reg,logistic,adhd200_dx,59,0.000774263682681127,train,0.6958904109589041,0.02180147207529868,0.6805440567711414,0.023532635128757633,0.6789247114856201,0.022703938798496547 +flat_mae,reg,logistic,adhd200_dx,59,0.000774263682681127,test,0.6,0.05949921982482892,0.570630081300813,0.06512401365319602,0.5748069498069498,0.0609204679930452 +flat_mae,reg,logistic,adhd200_dx,60,0.005994842503189409,train,0.7479452054794521,0.0224685136961152,0.7416446113128577,0.023124939291092887,0.7401080784026378,0.02302797313141784 +flat_mae,reg,logistic,adhd200_dx,60,0.005994842503189409,test,0.6307692307692307,0.05391348757047567,0.61,0.057791572418128816,0.6105212355212355,0.055212965029909834 +flat_mae,reg,logistic,adhd200_dx,61,0.046415888336127774,train,0.8712328767123287,0.016785381767951853,0.8681287426300456,0.01731063454777775,0.8658331806802223,0.017536402153138092 +flat_mae,reg,logistic,adhd200_dx,61,0.046415888336127774,test,0.5692307692307692,0.05782168877080374,0.5512820512820513,0.06142783058378694,0.5521235521235521,0.0593999195454249 +flat_mae,reg,logistic,adhd200_dx,62,0.005994842503189409,train,0.7424657534246575,0.022063773548712313,0.7329212853406402,0.02343638130777813,0.7302314221163827,0.02314394581113892 +flat_mae,reg,logistic,adhd200_dx,62,0.005994842503189409,test,0.6,0.058634529479968354,0.5833333333333333,0.062153574966849055,0.5834942084942085,0.06036296920771857 +flat_mae,reg,logistic,adhd200_dx,63,0.005994842503189409,train,0.7589041095890411,0.022616865656459765,0.7515008974438324,0.02359278470886471,0.7490993466446846,0.023487318084081672 +flat_mae,reg,logistic,adhd200_dx,63,0.005994842503189409,test,0.5846153846153846,0.05859721907087602,0.5644080416976918,0.06171730498480744,0.5656370656370656,0.059677807764307776 +flat_mae,reg,logistic,adhd200_dx,64,0.005994842503189409,train,0.7506849315068493,0.02183332416080239,0.7393859504586148,0.023346164489483106,0.7360780362703792,0.02281094482993573 +flat_mae,reg,logistic,adhd200_dx,64,0.005994842503189409,test,0.6615384615384615,0.0562814482766599,0.6474358974358974,0.05967887286854398,0.6462355212355213,0.05805761168703123 +flat_mae,reg,logistic,adhd200_dx,65,0.000774263682681127,train,0.6821917808219178,0.023650343395571805,0.6630483224040238,0.025770354139461417,0.6624839714233376,0.024555299809935673 +flat_mae,reg,logistic,adhd200_dx,65,0.000774263682681127,test,0.5846153846153846,0.05821222141349264,0.5644080416976918,0.06191015276644697,0.5656370656370656,0.05957531362836289 +flat_mae,reg,logistic,adhd200_dx,66,0.005994842503189409,train,0.7479452054794521,0.02332096186160634,0.7386038111844564,0.024541357718368156,0.7358032606704524,0.024160544231172032 +flat_mae,reg,logistic,adhd200_dx,66,0.005994842503189409,test,0.6,0.05811557552277354,0.5833333333333333,0.061461961473551985,0.5834942084942085,0.0596798708976062 +flat_mae,reg,logistic,adhd200_dx,67,0.046415888336127774,train,0.852054794520548,0.018431426978645228,0.848085460599334,0.019189122910162986,0.8452555413079319,0.019436176348117066 +flat_mae,reg,logistic,adhd200_dx,67,0.046415888336127774,test,0.5230769230769231,0.05411358643341235,0.47320261437908495,0.059891286755037826,0.48986486486486486,0.05437409992054961 +flat_mae,reg,logistic,adhd200_dx,68,0.000774263682681127,train,0.6794520547945205,0.023078447726915165,0.6566818609362564,0.02599347806870773,0.6571869084691946,0.024302414786853407 +flat_mae,reg,logistic,adhd200_dx,68,0.000774263682681127,test,0.6153846153846154,0.05406548735632486,0.5834401435529352,0.060554709999589944,0.5883204633204633,0.05568895352250174 +flat_mae,reg,logistic,adhd200_dx,69,0.005994842503189409,train,0.7424657534246575,0.020449922174546727,0.732337889284154,0.02188352179916429,0.7295139524943518,0.021518657614676813 +flat_mae,reg,logistic,adhd200_dx,69,0.005994842503189409,test,0.5692307692307692,0.06026038961219067,0.5512820512820513,0.06256330745060376,0.5521235521235521,0.060852241961177354 +flat_mae,reg,logistic,adhd200_dx,70,0.000774263682681127,train,0.6767123287671233,0.023462966991437455,0.6562759369214071,0.025961263415341312,0.656194663247237,0.02450813716978358 +flat_mae,reg,logistic,adhd200_dx,70,0.000774263682681127,test,0.5538461538461539,0.059221905430678574,0.5321419707123356,0.06277704698561554,0.5342664092664092,0.0603208493686423 +flat_mae,reg,logistic,adhd200_dx,71,0.005994842503189409,train,0.7424657534246575,0.02252822320297486,0.732337889284154,0.02390465128166366,0.7295139524943518,0.023473984550725437 +flat_mae,reg,logistic,adhd200_dx,71,0.005994842503189409,test,0.6307692307692307,0.0554689528811191,0.61,0.060005201893700184,0.6105212355212355,0.05734453590027393 +flat_mae,reg,logistic,adhd200_dx,72,0.046415888336127774,train,0.8465753424657534,0.019143072545872265,0.841864207464257,0.020017202399587066,0.8382487635098004,0.020156941406506573 +flat_mae,reg,logistic,adhd200_dx,72,0.046415888336127774,test,0.6615384615384615,0.056923401246477316,0.6549227799227799,0.058000950235487084,0.6549227799227799,0.05761686566928672 +flat_mae,reg,logistic,adhd200_dx,73,0.000774263682681127,train,0.6876712328767123,0.024171066699219538,0.6723209223209223,0.02579035067267978,0.6709256884655309,0.024927662687461025 +flat_mae,reg,logistic,adhd200_dx,73,0.000774263682681127,test,0.6153846153846154,0.0615741127499759,0.5966741126830479,0.06519819896992515,0.597007722007722,0.06321107991353545 +flat_mae,reg,logistic,adhd200_dx,74,0.046415888336127774,train,0.8273972602739726,0.019368829097980066,0.8229260517014346,0.02005076725077155,0.8205410026256335,0.020147351140727375 +flat_mae,reg,logistic,adhd200_dx,74,0.046415888336127774,test,0.6461538461538462,0.06184462301970725,0.6431129147767964,0.062243731224664554,0.6457528957528957,0.062227302638423444 +flat_mae,reg,logistic,adhd200_dx,75,0.005994842503189409,train,0.7397260273972602,0.02204794992914451,0.7303675710142223,0.023184269460216296,0.7278042376503633,0.022857538155276864 +flat_mae,reg,logistic,adhd200_dx,75,0.005994842503189409,test,0.5846153846153846,0.0629935659342478,0.5830363506771205,0.0631466371586398,0.5873552123552124,0.06282279914818478 +flat_mae,reg,logistic,adhd200_dx,76,0.005994842503189409,train,0.7534246575342466,0.021475685300137163,0.7442863370282725,0.022619060555884814,0.7413750992245222,0.022269204530152315 +flat_mae,reg,logistic,adhd200_dx,76,0.005994842503189409,test,0.5692307692307692,0.05725392418271019,0.5289855072463768,0.06415230853343244,0.5390926640926641,0.0586922045248185 +flat_mae,reg,logistic,adhd200_dx,77,0.005994842503189409,train,0.7397260273972602,0.022739672553163733,0.729787648548607,0.024069764976024196,0.7270867680283324,0.023682906175033325 +flat_mae,reg,logistic,adhd200_dx,77,0.005994842503189409,test,0.7230769230769231,0.05086942095370932,0.7027439024390244,0.05787094737523379,0.7002895752895753,0.05402382190280039 +flat_mae,reg,logistic,adhd200_dx,78,0.046415888336127774,train,0.852054794520548,0.01953539853276905,0.8488682370261318,0.01997978533674775,0.8474079501740246,0.020002518716981648 +flat_mae,reg,logistic,adhd200_dx,78,0.046415888336127774,test,0.6153846153846154,0.06143279389447035,0.5966741126830479,0.06496056282255665,0.597007722007722,0.06261017182595881 +flat_mae,reg,logistic,adhd200_dx,79,0.005994842503189409,train,0.7671232876712328,0.021669735847016907,0.7592516431414847,0.022840145259893446,0.7563809000427428,0.022640456904089855 +flat_mae,reg,logistic,adhd200_dx,79,0.005994842503189409,test,0.5538461538461539,0.06175202174300945,0.5469838981014179,0.06275857001581663,0.5472972972972974,0.06263433558866377 +flat_mae,reg,logistic,adhd200_dx,80,0.005994842503189409,train,0.7506849315068493,0.021937960598437927,0.74059090447591,0.023306162882120354,0.737512975514441,0.02291692571854121 +flat_mae,reg,logistic,adhd200_dx,80,0.005994842503189409,test,0.6307692307692307,0.057260736571080904,0.5962732919254659,0.06572039762313099,0.6018339768339769,0.05971898122035945 +flat_mae,reg,logistic,adhd200_dx,81,0.000774263682681127,train,0.6821917808219178,0.024607557266989172,0.6673893916540976,0.026451070354174468,0.6660713195334921,0.025585212914469566 +flat_mae,reg,logistic,adhd200_dx,81,0.000774263682681127,test,0.676923076923077,0.04622558527187958,0.6259249109345026,0.06105849841764585,0.638030888030888,0.05003641377447831 +flat_mae,reg,logistic,adhd200_dx,82,0.005994842503189409,train,0.7315068493150685,0.022606657360777264,0.7232623630624497,0.023637004154921457,0.7212401538743359,0.023426185085978383 +flat_mae,reg,logistic,adhd200_dx,82,0.005994842503189409,test,0.6461538461538462,0.05731725475201767,0.644808743169399,0.05751726403773977,0.6500965250965252,0.057629030371378766 +flat_mae,reg,logistic,adhd200_dx,83,0.046415888336127774,train,0.8410958904109589,0.018045495349829466,0.835891472868217,0.01887964552888314,0.8319594553336997,0.018876637433863273 +flat_mae,reg,logistic,adhd200_dx,83,0.046415888336127774,test,0.7076923076923077,0.056523160671601624,0.6973780936045086,0.05901089982264924,0.6954633204633205,0.058281666753759793 +flat_mae,reg,logistic,adhd200_dx,84,0.005994842503189409,train,0.7287671232876712,0.02225445234728408,0.7177857092650011,0.023262081442072657,0.715225621298162,0.022738192589196196 +flat_mae,reg,logistic,adhd200_dx,84,0.005994842503189409,test,0.5692307692307692,0.06326329689265182,0.5608108108108107,0.06466085650148116,0.5608108108108107,0.06416369857028685 +flat_mae,reg,logistic,adhd200_dx,85,0.005994842503189409,train,0.7589041095890411,0.020941352486126767,0.747674710910005,0.022479079866986346,0.7440770592904683,0.021942427536242343 +flat_mae,reg,logistic,adhd200_dx,85,0.005994842503189409,test,0.6461538461538462,0.05842074690244087,0.6289401836684041,0.06293966442834756,0.6283783783783784,0.06063115315592142 +flat_mae,reg,logistic,adhd200_dx,86,0.005994842503189409,train,0.7506849315068493,0.022565559124972528,0.74059090447591,0.02403135160574751,0.737512975514441,0.02362074213561687 +flat_mae,reg,logistic,adhd200_dx,86,0.005994842503189409,test,0.5692307692307692,0.059017149247701246,0.5289855072463768,0.06665568052195199,0.5390926640926641,0.06069359024486291 +flat_mae,reg,logistic,adhd200_dx,87,0.000774263682681127,train,0.684931506849315,0.023000909688538004,0.6673113046786453,0.024847999616828646,0.6663460951334188,0.023811602202798765 +flat_mae,reg,logistic,adhd200_dx,87,0.000774263682681127,test,0.6615384615384615,0.05484675584953895,0.6299171842650104,0.06414568418164646,0.6332046332046332,0.05796768037251713 +flat_mae,reg,logistic,adhd200_dx,88,0.005994842503189409,train,0.7589041095890411,0.021526771333174304,0.751976772918211,0.022325447068227547,0.7498168162667155,0.022272923469937242 +flat_mae,reg,logistic,adhd200_dx,88,0.005994842503189409,test,0.6615384615384615,0.05805115882926127,0.6549227799227799,0.059667220267746526,0.6549227799227799,0.05961911702342157 +flat_mae,reg,logistic,adhd200_dx,89,0.000774263682681127,train,0.6794520547945205,0.0220234024865342,0.6632761679479597,0.023811810164930183,0.6622091958234109,0.02289076827814951 +flat_mae,reg,logistic,adhd200_dx,89,0.000774263682681127,test,0.6153846153846154,0.056099143007303114,0.5905769715293525,0.06136589239568586,0.5926640926640927,0.057735868699971354 +flat_mae,reg,logistic,adhd200_dx,90,0.000774263682681127,train,0.684931506849315,0.02287999254639028,0.6664123532730928,0.025002871088435356,0.6656286255113879,0.02384144272162364 +flat_mae,reg,logistic,adhd200_dx,90,0.000774263682681127,test,0.6,0.05530143326090255,0.5626293995859213,0.06388592380212471,0.5704633204633205,0.05731430090760336 +flat_mae,reg,logistic,adhd200_dx,91,0.005994842503189409,train,0.7616438356164383,0.021959945112439143,0.7519935020813646,0.023302449125030895,0.7486566526225804,0.022929980089565778 +flat_mae,reg,logistic,adhd200_dx,91,0.005994842503189409,test,0.6153846153846154,0.048978768495273634,0.5656241646618552,0.06027529294877572,0.5796332046332047,0.051299403091889045 +flat_mae,reg,logistic,adhd200_dx,92,0.005994842503189409,train,0.7397260273972602,0.02124530683441102,0.729787648548607,0.022458543317968416,0.7270867680283324,0.022095855987365857 +flat_mae,reg,logistic,adhd200_dx,92,0.005994842503189409,test,0.6,0.05826529004191637,0.570630081300813,0.06320303222900987,0.5748069498069498,0.05936981050674195 +flat_mae,reg,logistic,adhd200_dx,93,0.000774263682681127,train,0.6876712328767123,0.022710643227771048,0.664975845410628,0.025117962276566857,0.6651859314892837,0.023563096516942158 +flat_mae,reg,logistic,adhd200_dx,93,0.000774263682681127,test,0.6461538461538462,0.044685260929960995,0.5787545787545787,0.06231896123216173,0.6023166023166023,0.04794562836932044 +flat_mae,reg,logistic,adhd200_dx,94,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adhd200_dx,94,2.782559402207126,test,0.5076923076923077,0.06053623102136594,0.4715447154471545,0.06457680492433392,0.4806949806949807,0.06095776993353349 +flat_mae,reg,logistic,adhd200_dx,95,0.005994842503189409,train,0.7561643835616438,0.023236998212867992,0.74891985685688,0.024209439389893624,0.7466721621786652,0.024076971819372208 +flat_mae,reg,logistic,adhd200_dx,95,0.005994842503189409,test,0.5538461538461539,0.06043705904913702,0.5250692869740489,0.06469297773329087,0.5299227799227799,0.06129013832218233 +flat_mae,reg,logistic,adhd200_dx,96,0.005994842503189409,train,0.7424657534246575,0.02423066175401206,0.734031007751938,0.025373844090475557,0.7316663613604445,0.025146860490887206 +flat_mae,reg,logistic,adhd200_dx,96,0.005994842503189409,test,0.6,0.06206985185156913,0.5921814671814671,0.06370793698504675,0.5921814671814671,0.06340233085636056 +flat_mae,reg,logistic,adhd200_dx,97,0.005994842503189409,train,0.7506849315068493,0.021558314828908545,0.7411650107149814,0.02291181976520443,0.7382304451364718,0.022596383773597125 +flat_mae,reg,logistic,adhd200_dx,97,0.005994842503189409,test,0.5846153846153846,0.05306973418428373,0.5308740978348035,0.06383967896359853,0.5482625482625483,0.05516302619925288 +flat_mae,reg,logistic,adhd200_dx,98,0.3593813663804626,train,0.9808219178082191,0.007104030872990247,0.9804246060020994,0.00728531492705078,0.9787048910056787,0.007922362478625919 +flat_mae,reg,logistic,adhd200_dx,98,0.3593813663804626,test,0.6307692307692307,0.06178017146139056,0.6235521235521235,0.06267651123743039,0.6235521235521235,0.062255694841437746 +flat_mae,reg,logistic,adhd200_dx,99,0.005994842503189409,train,0.7616438356164383,0.023434882972050017,0.7545621072645906,0.024450675372950013,0.7522440007327349,0.024288332711246047 +flat_mae,reg,logistic,adhd200_dx,99,0.005994842503189409,test,0.5538461538461539,0.05793553650854149,0.5381034060279344,0.05950087924458394,0.5386100386100386,0.05837661897131186 +flat_mae,reg,logistic,adhd200_dx,100,0.3593813663804626,train,0.9835616438356164,0.006392139571516355,0.9832599523023299,0.006523881601514422,0.9825670147157599,0.0068471649720416765 +flat_mae,reg,logistic,adhd200_dx,100,0.3593813663804626,test,0.6,0.057642029373503656,0.5921814671814671,0.058544257057188034,0.5921814671814671,0.058299775323032925 diff --git a/decoders/crossreg_reg4/eval_v2/adhd200_dx__reg__logistic/log.txt b/decoders/crossreg_reg4/eval_v2/adhd200_dx__reg__logistic/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..782f6dcc2f82d6178b1f81d6ffc805aa82ee0b99 --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/adhd200_dx__reg__logistic/log.txt @@ -0,0 +1,241 @@ +fMRI foundation model logistic probe eval +version: 0.1.dev66+g7ddd3aa04 +sha: aef99c83a386cf95c3d8ca503ecc968d8d5694af, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-03-07 21:19:16 +config: +output_root: experiments/decoders/output +name_prefix: eval_logistic +remote_root: null +notes: decoder ablations crossreg_reg4; eval v2 (adhd200_dx reg logistic) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: decoders/crossreg_reg4/eval_v2/adhd200_dx__reg__logistic +model: flat_mae +representation: reg +dataset: adhd200_dx +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg4/eval_v2/adhd200_dx__reg__logistic +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=False, reg_tokens=4, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: adhd200_dx (flat) +train (n=301): +HFDataset( + dataset=Dataset({ + features: ['sub', 'site', 'gender', 'dx', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 301 +}), + labels=['ADHD' 'Control'], + counts=[131 170] +) + +validation (n=64): +HFDataset( + dataset=Dataset({ + features: ['sub', 'site', 'gender', 'dx', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 64 +}), + labels=['ADHD' 'Control'], + counts=[28 36] +) + +test (n=65): +HFDataset( + dataset=Dataset({ + features: ['sub', 'site', 'gender', 'dx', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 65 +}), + labels=['ADHD' 'Control'], + counts=[28 37] +) + +extracting features for all splits +extract (train) [ 0/151] eta: 0:10:12 time: 4.0532 data: 3.2006 max mem: 2698 +extract (train) [ 20/151] eta: 0:00:55 time: 0.2408 data: 0.0889 max mem: 2852 +extract (train) [ 40/151] eta: 0:00:32 time: 0.1622 data: 0.0441 max mem: 2852 +extract (train) [ 60/151] eta: 0:00:23 time: 0.1770 data: 0.0584 max mem: 2852 +extract (train) [ 80/151] eta: 0:00:16 time: 0.1758 data: 0.0514 max mem: 2852 +extract (train) [100/151] eta: 0:00:11 time: 0.1642 data: 0.0486 max mem: 2852 +extract (train) [120/151] eta: 0:00:06 time: 0.1905 data: 0.0638 max mem: 2852 +extract (train) [140/151] eta: 0:00:02 time: 0.1611 data: 0.0479 max mem: 2852 +extract (train) [150/151] eta: 0:00:00 time: 0.1545 data: 0.0465 max mem: 2852 +extract (train) Total time: 0:00:31 (0.2072 s / it) +extract (validation) [ 0/32] eta: 0:01:53 time: 3.5614 data: 3.3840 max mem: 2852 +extract (validation) [20/32] eta: 0:00:04 time: 0.1896 data: 0.0577 max mem: 2852 +extract (validation) [31/32] eta: 0:00:00 time: 0.1607 data: 0.0458 max mem: 2852 +extract (validation) Total time: 0:00:09 (0.2957 s / it) +extract (test) [ 0/33] eta: 0:02:22 time: 4.3322 data: 4.1131 max mem: 2852 +extract (test) [20/33] eta: 0:00:05 time: 0.2033 data: 0.0683 max mem: 2852 +extract (test) [32/33] eta: 0:00:00 time: 0.1679 data: 0.0524 max mem: 2852 +extract (test) Total time: 0:00:10 (0.3232 s / it) +feature extraction time: 0:00:51 +train features: (301, 768) +validation features: (64, 768) +test features: (65, 768) +evaluating fixed splits +eval results (fixed splits): + +| model | repr | clf | dataset | trial | C | split | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:-----------|:--------|----------:|:--------|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | reg | logistic | adhd200_dx | | 0.0059948 | train | 0.74247 | 0.021433 | 0.73292 | 0.022719 | 0.73023 | 0.022388 | +| flat_mae | reg | logistic | adhd200_dx | | 0.0059948 | test | 0.63077 | 0.058318 | 0.60366 | 0.064893 | 0.60618 | 0.060582 | + + +evaluating random splits (n=100) +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 1, "C": 0.000774263682681127, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.05411907974919205, "f1": 0.5905769715293525, "f1_std": 0.05803834559566884, "bacc": 0.5926640926640927, "bacc_std": 0.055124868248523945} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 2, "C": 1291.5496650148827, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.05982351954811971, "f1": 0.61207925519217, "f1_std": 0.05981363839382905, "bacc": 0.6143822393822393, "bacc_std": 0.05986497517915926} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 3, "C": 0.005994842503189409, "split": "test", "acc": 0.5538461538461539, "acc_std": 0.060202254769152454, "f1": 0.5321419707123356, "f1_std": 0.0636341211291953, "bacc": 0.5342664092664092, "bacc_std": 0.061413303360600593} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 4, "C": 0.046415888336127774, "split": "test", "acc": 0.6461538461538462, "acc_std": 0.05993241953436056, "f1": 0.6407113674597452, "f1_std": 0.061089912956029384, "bacc": 0.6414092664092663, "bacc_std": 0.060926841989675636} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 5, "C": 0.005994842503189409, "split": "test", "acc": 0.47692307692307695, "acc_std": 0.06159348309491283, "f1": 0.47078544061302685, "f1_std": 0.062117338927684625, "bacc": 0.471042471042471, "bacc_std": 0.062499876082523505} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 6, "C": 0.005994842503189409, "split": "test", "acc": 0.7384615384615385, "acc_std": 0.053718697504113615, "f1": 0.7257383966244726, "f1_std": 0.058208076716623855, "bacc": 0.7224903474903475, "bacc_std": 0.056404911743680015} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 7, "C": 0.046415888336127774, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.056917080765269724, "f1": 0.6198830409356726, "f1_std": 0.058583785673106514, "bacc": 0.6192084942084942, "bacc_std": 0.05773996728003387} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 8, "C": 0.000774263682681127, "split": "test", "acc": 0.6461538461538462, "acc_std": 0.06106987752426234, "f1": 0.6289401836684041, "f1_std": 0.0653821254722588, "bacc": 0.6283783783783784, "bacc_std": 0.06295308465640816} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 9, "C": 0.000774263682681127, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.05281294444160177, "f1": 0.4846723044397463, "f1_std": 0.06004305365181408, "bacc": 0.5033783783783784, "bacc_std": 0.053475815367940965} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 10, "C": 2.782559402207126, "split": "test", "acc": 0.5538461538461539, "acc_std": 0.05879770554634587, "f1": 0.5250692869740489, "f1_std": 0.0635217987613546, "bacc": 0.5299227799227799, "bacc_std": 0.060001900121408776} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 11, "C": 0.000774263682681127, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.053510160512808304, "f1": 0.5834401435529352, "f1_std": 0.06111724552426378, "bacc": 0.5883204633204633, "bacc_std": 0.05553877742815464} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 12, "C": 0.005994842503189409, "split": "test", "acc": 0.5538461538461539, "acc_std": 0.05688007523359899, "f1": 0.5321419707123356, "f1_std": 0.060712565554667496, "bacc": 0.5342664092664092, "bacc_std": 0.05823910805825308} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 13, "C": 0.3593813663804626, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.060106383006353896, "f1": 0.5294401544401545, "f1_std": 0.061881266227136356, "bacc": 0.5294401544401545, "bacc_std": 0.06160227225701969} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 14, "C": 0.005994842503189409, "split": "test", "acc": 0.6461538461538462, "acc_std": 0.05608597795418141, "f1": 0.6233308138070043, "f1_std": 0.061928870062683036, "bacc": 0.6240347490347491, "bacc_std": 0.05848052685892671} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 15, "C": 0.005994842503189409, "split": "test", "acc": 0.6461538461538462, "acc_std": 0.058649890913300196, "f1": 0.6407113674597452, "f1_std": 0.05924847460360398, "bacc": 0.6414092664092663, "bacc_std": 0.059291018842661025} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 16, "C": 0.005994842503189409, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.05970876854717504, "f1": 0.6198830409356726, "f1_std": 0.06181351128591715, "bacc": 0.6192084942084942, "bacc_std": 0.06102563711942756} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 17, "C": 0.046415888336127774, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.05645310354097713, "f1": 0.5905769715293525, "f1_std": 0.062467746307242854, "bacc": 0.5926640926640927, "bacc_std": 0.05874038912674361} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 18, "C": 0.000774263682681127, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.05155016170292421, "f1": 0.587737843551797, "f1_std": 0.06202705212374842, "bacc": 0.5974903474903475, "bacc_std": 0.05398135472476604} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 19, "C": 0.005994842503189409, "split": "test", "acc": 0.6923076923076923, "acc_std": 0.053726072698215756, "f1": 0.6697154471544715, "f1_std": 0.060637238627391545, "bacc": 0.6689189189189189, "bacc_std": 0.0566715544766336} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 20, "C": 0.046415888336127774, "split": "test", "acc": 0.6, "acc_std": 0.055196055085861166, "f1": 0.588206627680312, "f1_std": 0.05765580387147078, "bacc": 0.5878378378378378, "bacc_std": 0.0566229473123185} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 21, "C": 0.005994842503189409, "split": "test", "acc": 0.6615384615384615, "acc_std": 0.059167070643396824, "f1": 0.6515594541910331, "f1_std": 0.061347152699184, "bacc": 0.6505791505791505, "bacc_std": 0.06070435213929338} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 22, "C": 0.005994842503189409, "split": "test", "acc": 0.676923076923077, "acc_std": 0.05792256818654922, "f1": 0.6690909090909091, "f1_std": 0.05927840706231435, "bacc": 0.6684362934362934, "bacc_std": 0.05876856765235649} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 23, "C": 0.005994842503189409, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.05426927383741408, "f1": 0.5411764705882354, "f1_std": 0.06215790303130002, "bacc": 0.5526061776061776, "bacc_std": 0.05567246337907471} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 24, "C": 0.005994842503189409, "split": "test", "acc": 0.676923076923077, "acc_std": 0.05266031370067268, "f1": 0.6500897205844656, "f1_std": 0.0600487333055939, "bacc": 0.6510617760617761, "bacc_std": 0.05519130375835446} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 25, "C": 0.000774263682681127, "split": "test", "acc": 0.6, "acc_std": 0.05597844893851678, "f1": 0.5626293995859213, "f1_std": 0.06369848285291128, "bacc": 0.5704633204633205, "bacc_std": 0.05755100879334684} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 26, "C": 0.005994842503189409, "split": "test", "acc": 0.5538461538461539, "acc_std": 0.058837688682233734, "f1": 0.5381034060279344, "f1_std": 0.06061713559113523, "bacc": 0.5386100386100386, "bacc_std": 0.0594176832945171} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 27, "C": 0.000774263682681127, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.05810045575191198, "f1": 0.5644080416976918, "f1_std": 0.061223062076996924, "bacc": 0.5656370656370656, "bacc_std": 0.059142547955176164} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 28, "C": 0.005994842503189409, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.056173391751152095, "f1": 0.545, "f1_std": 0.05990328108932862, "bacc": 0.5477799227799228, "bacc_std": 0.057244263596738974} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 29, "C": 0.000774263682681127, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.05356550157125276, "f1": 0.5751633986928104, "f1_std": 0.06256352385242225, "bacc": 0.583976833976834, "bacc_std": 0.0557865532664454} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 30, "C": 0.000774263682681127, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.05932626866613266, "f1": 0.5578231292517006, "f1_std": 0.06523901397147255, "bacc": 0.5612934362934363, "bacc_std": 0.06115253981183368} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 31, "C": 0.005994842503189409, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.058603196794681886, "f1": 0.5905769715293525, "f1_std": 0.0635328202944105, "bacc": 0.5926640926640927, "bacc_std": 0.060246074437261904} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 32, "C": 0.046415888336127774, "split": "test", "acc": 0.5538461538461539, "acc_std": 0.06127886784994003, "f1": 0.5469838981014179, "f1_std": 0.06226163907065569, "bacc": 0.5472972972972974, "bacc_std": 0.062280828805024564} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 33, "C": 0.3593813663804626, "split": "test", "acc": 0.6, "acc_std": 0.061925513568877495, "f1": 0.5953065134099617, "f1_std": 0.06290342684129337, "bacc": 0.5965250965250966, "bacc_std": 0.06320772560998983} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 34, "C": 0.005994842503189409, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.059881342235532715, "f1": 0.5810455956075435, "f1_std": 0.06020453016925911, "bacc": 0.583011583011583, "bacc_std": 0.06033649823807296} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 35, "C": 0.005994842503189409, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.057396748562633146, "f1": 0.5512820512820513, "f1_std": 0.06075726221488239, "bacc": 0.5521235521235521, "bacc_std": 0.05890187492733762} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 36, "C": 0.005994842503189409, "split": "test", "acc": 0.7230769230769231, "acc_std": 0.05386394431381182, "f1": 0.7149122807017544, "f1_std": 0.056342636739836464, "bacc": 0.7133204633204633, "bacc_std": 0.05546971450442966} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 37, "C": 0.000774263682681127, "split": "test", "acc": 0.676923076923077, "acc_std": 0.04783300338696862, "f1": 0.6351242983159583, "f1_std": 0.05987041344292248, "bacc": 0.6423745173745173, "bacc_std": 0.051200731611956665} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 38, "C": 0.000774263682681127, "split": "test", "acc": 0.5230769230769231, "acc_std": 0.06064992377932448, "f1": 0.5115151515151515, "f1_std": 0.061714609204104924, "bacc": 0.5115830115830116, "bacc_std": 0.0610801540411007} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 39, "C": 0.005994842503189409, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.056621036507184586, "f1": 0.6036585365853658, "f1_std": 0.06219801627552449, "bacc": 0.6061776061776062, "bacc_std": 0.05833223636472194} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 40, "C": 10000.0, "split": "test", "acc": 0.6, "acc_std": 0.058673453973525636, "f1": 0.5833333333333333, "f1_std": 0.06058733046494953, "bacc": 0.5834942084942085, "bacc_std": 0.059312206242286496} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 41, "C": 0.005994842503189409, "split": "test", "acc": 0.5538461538461539, "acc_std": 0.06032153687242134, "f1": 0.5521501544309813, "f1_std": 0.06052284569814894, "bacc": 0.555984555984556, "bacc_std": 0.06046982366147405} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 42, "C": 0.005994842503189409, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.06173270114398481, "f1": 0.5374762808349146, "f1_std": 0.0618262721673731, "bacc": 0.5424710424710424, "bacc_std": 0.06221652257362289} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 43, "C": 0.005994842503189409, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.0595263036682303, "f1": 0.5966741126830479, "f1_std": 0.06296582066821696, "bacc": 0.597007722007722, "bacc_std": 0.06068776921401086} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 44, "C": 0.005994842503189409, "split": "test", "acc": 0.6615384615384615, "acc_std": 0.05573682029049267, "f1": 0.6425000000000001, "f1_std": 0.06073148828822711, "bacc": 0.6418918918918919, "bacc_std": 0.05809082562166728} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 45, "C": 0.005994842503189409, "split": "test", "acc": 0.5230769230769231, "acc_std": 0.06299233352432847, "f1": 0.5062484685126194, "f1_std": 0.06532016945212119, "bacc": 0.5072393822393823, "bacc_std": 0.06397253542919706} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 46, "C": 0.005994842503189409, "split": "test", "acc": 0.676923076923077, "acc_std": 0.05643008975347992, "f1": 0.656084656084656, "f1_std": 0.06234477923313667, "bacc": 0.6554054054054055, "bacc_std": 0.05861205218561572} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 47, "C": 0.046415888336127774, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.06234833242527836, "f1": 0.4484848484848485, "f1_std": 0.062453538488762374, "bacc": 0.4488416988416989, "bacc_std": 0.06218658668910828} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 48, "C": 0.3593813663804626, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.06280399489799936, "f1": 0.5666666666666667, "f1_std": 0.06318806739640898, "bacc": 0.5694980694980695, "bacc_std": 0.06343270481017102} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 49, "C": 0.005994842503189409, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.0621158756827457, "f1": 0.5699583435432491, "f1_std": 0.06474627044543364, "bacc": 0.5699806949806949, "bacc_std": 0.06336489636056991} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 50, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.06033609221410216, "f1": 0.5921814671814671, "f1_std": 0.061513932952100905, "bacc": 0.5921814671814671, "bacc_std": 0.06099065790483331} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 51, "C": 0.005994842503189409, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.06178359637529276, "f1": 0.578226387887527, "f1_std": 0.062920359380333, "bacc": 0.5786679536679536, "bacc_std": 0.0629802191214737} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 52, "C": 21.54434690031882, "split": "test", "acc": 0.6615384615384615, "acc_std": 0.057219651525590914, "f1": 0.6474358974358974, "f1_std": 0.06013768427786563, "bacc": 0.6462355212355213, "bacc_std": 0.058820055283587996} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 53, "C": 0.005994842503189409, "split": "test", "acc": 0.676923076923077, "acc_std": 0.05364590456803835, "f1": 0.6431372549019607, "f1_std": 0.06376578705762419, "bacc": 0.6467181467181468, "bacc_std": 0.05706349375027341} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 54, "C": 0.005994842503189409, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.058525179934713, "f1": 0.5512820512820513, "f1_std": 0.06211518037030336, "bacc": 0.5521235521235521, "bacc_std": 0.060094851279050426} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 55, "C": 0.046415888336127774, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.06259961245319288, "f1": 0.5666666666666667, "f1_std": 0.06275244593889474, "bacc": 0.5694980694980695, "bacc_std": 0.0630294216601441} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 56, "C": 0.046415888336127774, "split": "test", "acc": 0.5538461538461539, "acc_std": 0.06114817777309814, "f1": 0.543030303030303, "f1_std": 0.06277857389640336, "bacc": 0.542953667953668, "bacc_std": 0.061992414940413895} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 57, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.05858267611528516, "f1": 0.5833333333333333, "f1_std": 0.06128363991719677, "bacc": 0.5834942084942085, "bacc_std": 0.059470954111315665} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 58, "C": 0.005994842503189409, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.05920079161472971, "f1": 0.61207925519217, "f1_std": 0.05991549883732456, "bacc": 0.6143822393822393, "bacc_std": 0.06017431376178625} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 59, "C": 0.000774263682681127, "split": "test", "acc": 0.6, "acc_std": 0.05949921982482892, "f1": 0.570630081300813, "f1_std": 0.06512401365319602, "bacc": 0.5748069498069498, "bacc_std": 0.0609204679930452} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 60, "C": 0.005994842503189409, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.05391348757047567, "f1": 0.61, "f1_std": 0.057791572418128816, "bacc": 0.6105212355212355, "bacc_std": 0.055212965029909834} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 61, "C": 0.046415888336127774, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.05782168877080374, "f1": 0.5512820512820513, "f1_std": 0.06142783058378694, "bacc": 0.5521235521235521, "bacc_std": 0.0593999195454249} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 62, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.058634529479968354, "f1": 0.5833333333333333, "f1_std": 0.062153574966849055, "bacc": 0.5834942084942085, "bacc_std": 0.06036296920771857} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 63, "C": 0.005994842503189409, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.05859721907087602, "f1": 0.5644080416976918, "f1_std": 0.06171730498480744, "bacc": 0.5656370656370656, "bacc_std": 0.059677807764307776} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 64, "C": 0.005994842503189409, "split": "test", "acc": 0.6615384615384615, "acc_std": 0.0562814482766599, "f1": 0.6474358974358974, "f1_std": 0.05967887286854398, "bacc": 0.6462355212355213, "bacc_std": 0.05805761168703123} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 65, "C": 0.000774263682681127, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.05821222141349264, "f1": 0.5644080416976918, "f1_std": 0.06191015276644697, "bacc": 0.5656370656370656, "bacc_std": 0.05957531362836289} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 66, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.05811557552277354, "f1": 0.5833333333333333, "f1_std": 0.061461961473551985, "bacc": 0.5834942084942085, "bacc_std": 0.0596798708976062} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 67, "C": 0.046415888336127774, "split": "test", "acc": 0.5230769230769231, "acc_std": 0.05411358643341235, "f1": 0.47320261437908495, "f1_std": 0.059891286755037826, "bacc": 0.48986486486486486, "bacc_std": 0.05437409992054961} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 68, "C": 0.000774263682681127, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.05406548735632486, "f1": 0.5834401435529352, "f1_std": 0.060554709999589944, "bacc": 0.5883204633204633, "bacc_std": 0.05568895352250174} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 69, "C": 0.005994842503189409, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.06026038961219067, "f1": 0.5512820512820513, "f1_std": 0.06256330745060376, "bacc": 0.5521235521235521, "bacc_std": 0.060852241961177354} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 70, "C": 0.000774263682681127, "split": "test", "acc": 0.5538461538461539, "acc_std": 0.059221905430678574, "f1": 0.5321419707123356, "f1_std": 0.06277704698561554, "bacc": 0.5342664092664092, "bacc_std": 0.0603208493686423} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 71, "C": 0.005994842503189409, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.0554689528811191, "f1": 0.61, "f1_std": 0.060005201893700184, "bacc": 0.6105212355212355, "bacc_std": 0.05734453590027393} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 72, "C": 0.046415888336127774, "split": "test", "acc": 0.6615384615384615, "acc_std": 0.056923401246477316, "f1": 0.6549227799227799, "f1_std": 0.058000950235487084, "bacc": 0.6549227799227799, "bacc_std": 0.05761686566928672} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 73, "C": 0.000774263682681127, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.0615741127499759, "f1": 0.5966741126830479, "f1_std": 0.06519819896992515, "bacc": 0.597007722007722, "bacc_std": 0.06321107991353545} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 74, "C": 0.046415888336127774, "split": "test", "acc": 0.6461538461538462, "acc_std": 0.06184462301970725, "f1": 0.6431129147767964, "f1_std": 0.062243731224664554, "bacc": 0.6457528957528957, "bacc_std": 0.062227302638423444} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 75, "C": 0.005994842503189409, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.0629935659342478, "f1": 0.5830363506771205, "f1_std": 0.0631466371586398, "bacc": 0.5873552123552124, "bacc_std": 0.06282279914818478} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 76, "C": 0.005994842503189409, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.05725392418271019, "f1": 0.5289855072463768, "f1_std": 0.06415230853343244, "bacc": 0.5390926640926641, "bacc_std": 0.0586922045248185} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 77, "C": 0.005994842503189409, "split": "test", "acc": 0.7230769230769231, "acc_std": 0.05086942095370932, "f1": 0.7027439024390244, "f1_std": 0.05787094737523379, "bacc": 0.7002895752895753, "bacc_std": 0.05402382190280039} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 78, "C": 0.046415888336127774, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.06143279389447035, "f1": 0.5966741126830479, "f1_std": 0.06496056282255665, "bacc": 0.597007722007722, "bacc_std": 0.06261017182595881} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 79, "C": 0.005994842503189409, "split": "test", "acc": 0.5538461538461539, "acc_std": 0.06175202174300945, "f1": 0.5469838981014179, "f1_std": 0.06275857001581663, "bacc": 0.5472972972972974, "bacc_std": 0.06263433558866377} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 80, "C": 0.005994842503189409, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.057260736571080904, "f1": 0.5962732919254659, "f1_std": 0.06572039762313099, "bacc": 0.6018339768339769, "bacc_std": 0.05971898122035945} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 81, "C": 0.000774263682681127, "split": "test", "acc": 0.676923076923077, "acc_std": 0.04622558527187958, "f1": 0.6259249109345026, "f1_std": 0.06105849841764585, "bacc": 0.638030888030888, "bacc_std": 0.05003641377447831} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 82, "C": 0.005994842503189409, "split": "test", "acc": 0.6461538461538462, "acc_std": 0.05731725475201767, "f1": 0.644808743169399, "f1_std": 0.05751726403773977, "bacc": 0.6500965250965252, "bacc_std": 0.057629030371378766} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 83, "C": 0.046415888336127774, "split": "test", "acc": 0.7076923076923077, "acc_std": 0.056523160671601624, "f1": 0.6973780936045086, "f1_std": 0.05901089982264924, "bacc": 0.6954633204633205, "bacc_std": 0.058281666753759793} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 84, "C": 0.005994842503189409, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.06326329689265182, "f1": 0.5608108108108107, "f1_std": 0.06466085650148116, "bacc": 0.5608108108108107, "bacc_std": 0.06416369857028685} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 85, "C": 0.005994842503189409, "split": "test", "acc": 0.6461538461538462, "acc_std": 0.05842074690244087, "f1": 0.6289401836684041, "f1_std": 0.06293966442834756, "bacc": 0.6283783783783784, "bacc_std": 0.06063115315592142} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 86, "C": 0.005994842503189409, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.059017149247701246, "f1": 0.5289855072463768, "f1_std": 0.06665568052195199, "bacc": 0.5390926640926641, "bacc_std": 0.06069359024486291} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 87, "C": 0.000774263682681127, "split": "test", "acc": 0.6615384615384615, "acc_std": 0.05484675584953895, "f1": 0.6299171842650104, "f1_std": 0.06414568418164646, "bacc": 0.6332046332046332, "bacc_std": 0.05796768037251713} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 88, "C": 0.005994842503189409, "split": "test", "acc": 0.6615384615384615, "acc_std": 0.05805115882926127, "f1": 0.6549227799227799, "f1_std": 0.059667220267746526, "bacc": 0.6549227799227799, "bacc_std": 0.05961911702342157} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 89, "C": 0.000774263682681127, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.056099143007303114, "f1": 0.5905769715293525, "f1_std": 0.06136589239568586, "bacc": 0.5926640926640927, "bacc_std": 0.057735868699971354} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 90, "C": 0.000774263682681127, "split": "test", "acc": 0.6, "acc_std": 0.05530143326090255, "f1": 0.5626293995859213, "f1_std": 0.06388592380212471, "bacc": 0.5704633204633205, "bacc_std": 0.05731430090760336} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 91, "C": 0.005994842503189409, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.048978768495273634, "f1": 0.5656241646618552, "f1_std": 0.06027529294877572, "bacc": 0.5796332046332047, "bacc_std": 0.051299403091889045} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 92, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.05826529004191637, "f1": 0.570630081300813, "f1_std": 0.06320303222900987, "bacc": 0.5748069498069498, "bacc_std": 0.05936981050674195} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 93, "C": 0.000774263682681127, "split": "test", "acc": 0.6461538461538462, "acc_std": 0.044685260929960995, "f1": 0.5787545787545787, "f1_std": 0.06231896123216173, "bacc": 0.6023166023166023, "bacc_std": 0.04794562836932044} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 94, "C": 2.782559402207126, "split": "test", "acc": 0.5076923076923077, "acc_std": 0.06053623102136594, "f1": 0.4715447154471545, "f1_std": 0.06457680492433392, "bacc": 0.4806949806949807, "bacc_std": 0.06095776993353349} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 95, "C": 0.005994842503189409, "split": "test", "acc": 0.5538461538461539, "acc_std": 0.06043705904913702, "f1": 0.5250692869740489, "f1_std": 0.06469297773329087, "bacc": 0.5299227799227799, "bacc_std": 0.06129013832218233} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 96, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.06206985185156913, "f1": 0.5921814671814671, "f1_std": 0.06370793698504675, "bacc": 0.5921814671814671, "bacc_std": 0.06340233085636056} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 97, "C": 0.005994842503189409, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.05306973418428373, "f1": 0.5308740978348035, "f1_std": 0.06383967896359853, "bacc": 0.5482625482625483, "bacc_std": 0.05516302619925288} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 98, "C": 0.3593813663804626, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.06178017146139056, "f1": 0.6235521235521235, "f1_std": 0.06267651123743039, "bacc": 0.6235521235521235, "bacc_std": 0.062255694841437746} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 99, "C": 0.005994842503189409, "split": "test", "acc": 0.5538461538461539, "acc_std": 0.05793553650854149, "f1": 0.5381034060279344, "f1_std": 0.05950087924458394, "bacc": 0.5386100386100386, "bacc_std": 0.05837661897131186} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 100, "C": 0.3593813663804626, "split": "test", "acc": 0.6, "acc_std": 0.057642029373503656, "f1": 0.5921814671814671, "f1_std": 0.058544257057188034, "bacc": 0.5921814671814671, "bacc_std": 0.058299775323032925} +eval results (random splits): + +| model | repr | clf | dataset | split | n_trials | C | C_std | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:-----------|:--------|-----------:|-------:|--------:|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | reg | logistic | adhd200_dx | train | 100 | 113.21 | 1007 | 0.7763 | 0.087812 | 0.76689 | 0.092902 | 0.76483 | 0.092879 | +| flat_mae | reg | logistic | adhd200_dx | test | 100 | 113.21 | 1007 | 0.60554 | 0.051585 | 0.58546 | 0.053233 | 0.58827 | 0.051522 | + + +done! total time: 0:04:50 diff --git a/decoders/crossreg_reg4/eval_v2/adni_ad_vs_cn__patch__logistic/config.yaml b/decoders/crossreg_reg4/eval_v2/adni_ad_vs_cn__patch__logistic/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..fe4d424352312a624bd940c8c8f1fdd2a4613b99 --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/adni_ad_vs_cn__patch__logistic/config.yaml @@ -0,0 +1,30 @@ +output_root: experiments/decoders/output +name_prefix: eval_logistic +remote_root: null +notes: decoder ablations crossreg_reg4; eval v2 (adni_ad_vs_cn patch logistic) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: decoders/crossreg_reg4/eval_v2/adni_ad_vs_cn__patch__logistic +model: flat_mae +representation: patch +dataset: adni_ad_vs_cn +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg4/eval_v2/adni_ad_vs_cn__patch__logistic +remote_dir: null diff --git a/decoders/crossreg_reg4/eval_v2/adni_ad_vs_cn__patch__logistic/eval_table.csv b/decoders/crossreg_reg4/eval_v2/adni_ad_vs_cn__patch__logistic/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..eee093d0b80cca2860f38d435560cc50df02e637 --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/adni_ad_vs_cn__patch__logistic/eval_table.csv @@ -0,0 +1,203 @@ +model,repr,clf,dataset,trial,C,split,acc,acc_std,f1,f1_std,bacc,bacc_std +flat_mae,patch,logistic,adni_ad_vs_cn,,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,,166.81005372000556,test,0.6585365853658537,0.06721052012495501,0.5017361111111112,0.07684463515541452,0.5017361111111112,0.07654227112140105 +flat_mae,patch,logistic,adni_ad_vs_cn,1,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,1,166.81005372000556,test,0.7804878048780488,0.06175586637339688,0.7119437939110069,0.07982166095879796,0.7193548387096774,0.08516609223998574 +flat_mae,patch,logistic,adni_ad_vs_cn,2,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,2,2.782559402207126,test,0.7317073170731707,0.06428491014860176,0.6232247284878863,0.09162267407571494,0.6193548387096774,0.08786441042986236 +flat_mae,patch,logistic,adni_ad_vs_cn,3,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,3,21.54434690031882,test,0.6829268292682927,0.06948437611929524,0.5839188134270101,0.08497702446519155,0.5870967741935484,0.08792274414851722 +flat_mae,patch,logistic,adni_ad_vs_cn,4,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,4,166.81005372000556,test,0.8048780487804879,0.06127466177863133,0.783068783068783,0.05915914345251882,0.8709677419354839,0.040520340853611066 +flat_mae,patch,logistic,adni_ad_vs_cn,5,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,5,166.81005372000556,test,0.6829268292682927,0.0604363274265884,0.5547201336675021,0.0811416666945755,0.5532258064516129,0.07772808309192142 +flat_mae,patch,logistic,adni_ad_vs_cn,6,0.3593813663804626,train,0.975609756097561,0.007708574789036132,0.9648738695859115,0.011449808348987367,0.9517215876407263,0.015417822803499251 +flat_mae,patch,logistic,adni_ad_vs_cn,6,0.3593813663804626,test,0.7317073170731707,0.06479200235603146,0.6232247284878863,0.08930198197826686,0.6193548387096774,0.08677124800133185 +flat_mae,patch,logistic,adni_ad_vs_cn,7,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,7,166.81005372000556,test,0.7560975609756098,0.06372417884650156,0.6893939393939394,0.0784376993864998,0.7032258064516128,0.084067210612129 +flat_mae,patch,logistic,adni_ad_vs_cn,8,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,8,166.81005372000556,test,0.7317073170731707,0.06641316068338539,0.6479313036690086,0.08202671334913557,0.6532258064516129,0.0854468406709409 +flat_mae,patch,logistic,adni_ad_vs_cn,9,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,9,166.81005372000556,test,0.7804878048780488,0.0619757777327563,0.7119437939110069,0.08030073846778696,0.7193548387096774,0.08475320178801186 +flat_mae,patch,logistic,adni_ad_vs_cn,10,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,10,2.782559402207126,test,0.7317073170731707,0.06399665369003064,0.6479313036690086,0.08319998345571941,0.6532258064516129,0.08832318716066874 +flat_mae,patch,logistic,adni_ad_vs_cn,11,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,11,166.81005372000556,test,0.8048780487804879,0.05120557301614695,0.6893939393939394,0.09174013333260418,0.667741935483871,0.08241255189397681 +flat_mae,patch,logistic,adni_ad_vs_cn,12,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,12,166.81005372000556,test,0.7073170731707317,0.06106450106001445,0.5729166666666666,0.08751751006546477,0.5693548387096774,0.08186769382609813 +flat_mae,patch,logistic,adni_ad_vs_cn,13,0.046415888336127774,train,0.907859078590786,0.014137782041226739,0.8577551020408163,0.023699210872975725,0.8266085956118004,0.02589682684477505 +flat_mae,patch,logistic,adni_ad_vs_cn,13,0.046415888336127774,test,0.7560975609756098,0.05345814020626708,0.6117424242424243,0.09202468610571168,0.6016129032258064,0.0791058140916389 +flat_mae,patch,logistic,adni_ad_vs_cn,14,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,14,21.54434690031882,test,0.7560975609756098,0.06369536361170726,0.6693548387096775,0.08657520433598431,0.6693548387096775,0.08820304807605202 +flat_mae,patch,logistic,adni_ad_vs_cn,15,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,15,2.782559402207126,test,0.7560975609756098,0.06447931754782824,0.6693548387096775,0.08742264337378126,0.6693548387096775,0.08954270364040907 +flat_mae,patch,logistic,adni_ad_vs_cn,16,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,16,166.81005372000556,test,0.8292682926829268,0.04575690362803435,0.7144278606965174,0.09279895838312108,0.6838709677419355,0.07932248822621175 +flat_mae,patch,logistic,adni_ad_vs_cn,17,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,17,1291.5496650148827,test,0.6585365853658537,0.0711080986208361,0.5651515151515152,0.0852582525873165,0.5709677419354839,0.08977297363352293 +flat_mae,patch,logistic,adni_ad_vs_cn,18,0.3593813663804626,train,0.9701897018970189,0.008288273089307956,0.9566924513203521,0.012549269658976547,0.9400936806639822,0.017195936895224584 +flat_mae,patch,logistic,adni_ad_vs_cn,18,0.3593813663804626,test,0.8780487804878049,0.03814609194603692,0.7960199004975124,0.08301462416148489,0.75,0.07819948848937569 +flat_mae,patch,logistic,adni_ad_vs_cn,19,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,19,1291.5496650148827,test,0.7560975609756098,0.060457486500875714,0.6440972222222222,0.08494828399370564,0.635483870967742,0.08026925623399012 +flat_mae,patch,logistic,adni_ad_vs_cn,20,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,20,2.782559402207126,test,0.8048780487804879,0.06407793811820159,0.764367816091954,0.07146125035822799,0.8032258064516129,0.07456277628052574 +flat_mae,patch,logistic,adni_ad_vs_cn,21,10000.0,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,21,10000.0,test,0.7560975609756098,0.058075808423928135,0.6440972222222222,0.08780002288873556,0.635483870967742,0.08256684587327397 +flat_mae,patch,logistic,adni_ad_vs_cn,22,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,22,166.81005372000556,test,0.8292682926829268,0.051874648712642704,0.7402714932126697,0.08889597556100112,0.717741935483871,0.08333749263987081 +flat_mae,patch,logistic,adni_ad_vs_cn,23,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,23,1291.5496650148827,test,0.7073170731707317,0.06808896444446465,0.6272727272727273,0.08379512140986728,0.6370967741935484,0.0899293051054737 +flat_mae,patch,logistic,adni_ad_vs_cn,24,0.3593813663804626,train,0.983739837398374,0.0065384704279851,0.9766829555986183,0.00964648513664028,0.9651162790697674,0.014027299929805235 +flat_mae,patch,logistic,adni_ad_vs_cn,24,0.3593813663804626,test,0.6585365853658537,0.0730399481610212,0.5651515151515152,0.08570021624212107,0.5709677419354839,0.0912322758576622 +flat_mae,patch,logistic,adni_ad_vs_cn,25,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,25,21.54434690031882,test,0.7560975609756098,0.06502429875755188,0.6693548387096775,0.08661123117886423,0.6693548387096775,0.08749686576815639 +flat_mae,patch,logistic,adni_ad_vs_cn,26,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,26,2.782559402207126,test,0.7073170731707317,0.06437876837875586,0.603225806451613,0.08250327793555129,0.603225806451613,0.08280767299952495 +flat_mae,patch,logistic,adni_ad_vs_cn,27,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,27,166.81005372000556,test,0.7317073170731707,0.06309206892481466,0.6232247284878863,0.08547873759960081,0.6193548387096774,0.08351086534453545 +flat_mae,patch,logistic,adni_ad_vs_cn,28,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,28,2.782559402207126,test,0.7317073170731707,0.061738043058860034,0.6232247284878863,0.08457621269232801,0.6193548387096774,0.08213022222486381 +flat_mae,patch,logistic,adni_ad_vs_cn,29,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,29,1291.5496650148827,test,0.7073170731707317,0.07105567523251301,0.6272727272727273,0.08378732150900603,0.6370967741935484,0.08966387946055397 +flat_mae,patch,logistic,adni_ad_vs_cn,30,0.3593813663804626,train,0.983739837398374,0.006559159158815651,0.9768796992481203,0.009479445150930505,0.9691634481058427,0.012714895190838198 +flat_mae,patch,logistic,adni_ad_vs_cn,30,0.3593813663804626,test,0.7804878048780488,0.04778185109921527,0.6328358208955224,0.09319085105882638,0.6177419354838709,0.07593114487288175 +flat_mae,patch,logistic,adni_ad_vs_cn,31,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,31,21.54434690031882,test,0.7317073170731707,0.05097528299580182,0.5512437810945273,0.08895511919602032,0.5516129032258065,0.07090380837178853 +flat_mae,patch,logistic,adni_ad_vs_cn,32,0.046415888336127774,train,0.8943089430894309,0.013554222689814526,0.8308632543926662,0.025235333292744886,0.7934916591338648,0.0272427568828056 +flat_mae,patch,logistic,adni_ad_vs_cn,32,0.046415888336127774,test,0.6829268292682927,0.060572010624942316,0.5176470588235295,0.08190754554917075,0.5193548387096775,0.07278577578846016 +flat_mae,patch,logistic,adni_ad_vs_cn,33,0.3593813663804626,train,0.981029810298103,0.007124400959681112,0.9729123189697663,0.010422202997663934,0.9633494946174705,0.014179217743666121 +flat_mae,patch,logistic,adni_ad_vs_cn,33,0.3593813663804626,test,0.7560975609756098,0.06147417637105602,0.6893939393939394,0.07571128957091285,0.7032258064516128,0.08194897494976601 +flat_mae,patch,logistic,adni_ad_vs_cn,34,0.3593813663804626,train,0.9728997289972899,0.008204313324002887,0.9608013937282229,0.01230811473248259,0.9459076341523543,0.01656423681111059 +flat_mae,patch,logistic,adni_ad_vs_cn,34,0.3593813663804626,test,0.7804878048780488,0.062007195759818313,0.7119437939110069,0.07932457979132376,0.7193548387096774,0.08408095202384551 +flat_mae,patch,logistic,adni_ad_vs_cn,35,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,35,2.782559402207126,test,0.8292682926829268,0.05069360670594106,0.7402714932126697,0.08787541773146086,0.717741935483871,0.08333689079468769 +flat_mae,patch,logistic,adni_ad_vs_cn,36,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,36,166.81005372000556,test,0.6829268292682927,0.07224472587268083,0.5839188134270101,0.08441764447486973,0.5870967741935484,0.08659274535656608 +flat_mae,patch,logistic,adni_ad_vs_cn,37,0.3593813663804626,train,0.975609756097561,0.007619223721560962,0.9648738695859115,0.011305089118887153,0.9517215876407263,0.01532224775225614 +flat_mae,patch,logistic,adni_ad_vs_cn,37,0.3593813663804626,test,0.7073170731707317,0.05848117295950731,0.5729166666666666,0.0864804969138768,0.5693548387096774,0.07968586869134761 +flat_mae,patch,logistic,adni_ad_vs_cn,38,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,38,166.81005372000556,test,0.7317073170731707,0.06711712971906027,0.6479313036690086,0.08419349273094341,0.6532258064516129,0.08785933908891233 +flat_mae,patch,logistic,adni_ad_vs_cn,39,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,39,2.782559402207126,test,0.6829268292682927,0.06702252633471767,0.5547201336675021,0.08647402444083507,0.5532258064516129,0.08406115972553356 +flat_mae,patch,logistic,adni_ad_vs_cn,40,0.005994842503189409,train,0.8238482384823849,0.013158234002658847,0.6787307285318189,0.030644591915016183,0.6504232065083408,0.02491712736724843 +flat_mae,patch,logistic,adni_ad_vs_cn,40,0.005994842503189409,test,0.7317073170731707,0.04141989107375309,0.4972129319955407,0.07434953475605574,0.5177419354838709,0.05316787697999455 +flat_mae,patch,logistic,adni_ad_vs_cn,41,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,41,1291.5496650148827,test,0.7317073170731707,0.06787837743012205,0.6479313036690086,0.0851149835833768,0.6532258064516129,0.08764715534317276 +flat_mae,patch,logistic,adni_ad_vs_cn,42,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,42,166.81005372000556,test,0.6097560975609756,0.06637732172945972,0.47096774193548385,0.0727034266598651,0.47096774193548385,0.07333956454307135 +flat_mae,patch,logistic,adni_ad_vs_cn,43,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,43,166.81005372000556,test,0.7560975609756098,0.05879366313225619,0.6440972222222222,0.08787938032120693,0.635483870967742,0.08440252251237289 +flat_mae,patch,logistic,adni_ad_vs_cn,44,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,44,1291.5496650148827,test,0.7804878048780488,0.053685558606160026,0.6660633484162897,0.09088552881025565,0.6516129032258065,0.08400442304147263 +flat_mae,patch,logistic,adni_ad_vs_cn,45,0.005994842503189409,train,0.8238482384823849,0.012812434930479106,0.66522437015842,0.03335021052656857,0.638281699400115,0.025531601804187433 +flat_mae,patch,logistic,adni_ad_vs_cn,45,0.005994842503189409,test,0.8292682926829268,0.03504395132812059,0.6800445930880714,0.09352338117352493,0.65,0.07184010022264724 +flat_mae,patch,logistic,adni_ad_vs_cn,46,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,46,21.54434690031882,test,0.8048780487804879,0.053717838627345894,0.7152777777777778,0.08634601572777,0.7016129032258065,0.0851015784674308 +flat_mae,patch,logistic,adni_ad_vs_cn,47,10000.0,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,47,10000.0,test,0.7317073170731707,0.05180846067259221,0.5512437810945273,0.08654368574712812,0.5516129032258065,0.06887771184022792 +flat_mae,patch,logistic,adni_ad_vs_cn,48,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,48,21.54434690031882,test,0.7073170731707317,0.07177524574147591,0.646551724137931,0.08069310588351807,0.6709677419354838,0.09070532385276033 +flat_mae,patch,logistic,adni_ad_vs_cn,49,0.3593813663804626,train,0.981029810298103,0.006848965014229861,0.9729123189697663,0.010020162666062555,0.9633494946174705,0.013738646042460334 +flat_mae,patch,logistic,adni_ad_vs_cn,49,0.3593813663804626,test,0.6829268292682927,0.06505340322129365,0.5547201336675021,0.08618118501625521,0.5532258064516129,0.08281085000319596 +flat_mae,patch,logistic,adni_ad_vs_cn,50,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,50,21.54434690031882,test,0.7804878048780488,0.05796173017929806,0.6917293233082706,0.082836555047868,0.685483870967742,0.08079937068969135 +flat_mae,patch,logistic,adni_ad_vs_cn,51,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,51,1291.5496650148827,test,0.7073170731707317,0.06379389403478483,0.603225806451613,0.0842392921222764,0.603225806451613,0.08491606457492491 +flat_mae,patch,logistic,adni_ad_vs_cn,52,10000.0,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,52,10000.0,test,0.6097560975609756,0.0723268409477098,0.5287356321839081,0.07849295074799864,0.5387096774193548,0.08671881936254502 +flat_mae,patch,logistic,adni_ad_vs_cn,53,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,53,166.81005372000556,test,0.7560975609756098,0.05463414634146341,0.6117424242424243,0.09245079057319427,0.6016129032258064,0.07855340091304261 +flat_mae,patch,logistic,adni_ad_vs_cn,54,0.005994842503189409,train,0.8265582655826558,0.01307658590850382,0.6772006560962274,0.03129827302541176,0.6481428219245624,0.024816675539712823 +flat_mae,patch,logistic,adni_ad_vs_cn,54,0.005994842503189409,test,0.7560975609756098,0.043246701792655724,0.569327731092437,0.08661224222477408,0.567741935483871,0.06507710139450365 +flat_mae,patch,logistic,adni_ad_vs_cn,55,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,55,166.81005372000556,test,0.6829268292682927,0.07491260027493644,0.6259649122807017,0.07967230381546084,0.6548387096774193,0.08799429854531957 +flat_mae,patch,logistic,adni_ad_vs_cn,56,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,56,2.782559402207126,test,0.7560975609756098,0.06456399322146954,0.6693548387096775,0.08350107478969533,0.6693548387096775,0.08552273802962136 +flat_mae,patch,logistic,adni_ad_vs_cn,57,0.046415888336127774,train,0.8970189701897019,0.014490204467636533,0.8377684191040355,0.025952902301689142,0.8033527816583121,0.02804637318616214 +flat_mae,patch,logistic,adni_ad_vs_cn,57,0.046415888336127774,test,0.7073170731707317,0.06265693681558678,0.5729166666666666,0.08851241615812118,0.5693548387096774,0.08031695899487994 +flat_mae,patch,logistic,adni_ad_vs_cn,58,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,58,21.54434690031882,test,0.7804878048780488,0.06301145755703659,0.7119437939110069,0.08059125331526244,0.7193548387096774,0.08491596500908126 +flat_mae,patch,logistic,adni_ad_vs_cn,59,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,59,166.81005372000556,test,0.6829268292682927,0.06620653423560834,0.5839188134270101,0.08236688301326865,0.5870967741935484,0.08558086250473963 +flat_mae,patch,logistic,adni_ad_vs_cn,60,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,60,166.81005372000556,test,0.7317073170731707,0.06909857256497813,0.6676492262343405,0.08115322014834417,0.6870967741935483,0.08707174096641203 +flat_mae,patch,logistic,adni_ad_vs_cn,61,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,61,2.782559402207126,test,0.7073170731707317,0.06908674250022279,0.646551724137931,0.07872518273436985,0.6709677419354838,0.08707151581180167 +flat_mae,patch,logistic,adni_ad_vs_cn,62,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,62,166.81005372000556,test,0.6097560975609756,0.07572358072732534,0.5287356321839081,0.08277261956763161,0.5387096774193548,0.09205784562266699 +flat_mae,patch,logistic,adni_ad_vs_cn,63,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,63,166.81005372000556,test,0.6829268292682927,0.0734152661831638,0.6259649122807017,0.08025615812395835,0.6548387096774193,0.08996184785051084 +flat_mae,patch,logistic,adni_ad_vs_cn,64,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,64,21.54434690031882,test,0.7317073170731707,0.06738905659997667,0.6479313036690086,0.08728104520261751,0.6532258064516129,0.09135951418689889 +flat_mae,patch,logistic,adni_ad_vs_cn,65,0.046415888336127774,train,0.9051490514905149,0.013138443923635432,0.851341551849166,0.022812890984969258,0.8167474730873532,0.025038613147335433 +flat_mae,patch,logistic,adni_ad_vs_cn,65,0.046415888336127774,test,0.6585365853658537,0.05693606629763894,0.4564393939393939,0.0689541429669208,0.4693548387096774,0.06066977631889546 +flat_mae,patch,logistic,adni_ad_vs_cn,66,0.046415888336127774,train,0.8997289972899729,0.014385051554063727,0.8428467833834041,0.02517726875059078,0.8091667351466842,0.027314934931126078 +flat_mae,patch,logistic,adni_ad_vs_cn,66,0.046415888336127774,test,0.7560975609756098,0.05811496534376152,0.6440972222222222,0.0883637958972104,0.635483870967742,0.08271046870689876 +flat_mae,patch,logistic,adni_ad_vs_cn,67,0.3593813663804626,train,0.975609756097561,0.007574379819315634,0.9648738695859115,0.01124975992953432,0.9517215876407263,0.015042054484084388 +flat_mae,patch,logistic,adni_ad_vs_cn,67,0.3593813663804626,test,0.8536585365853658,0.04583027426562429,0.7670454545454546,0.08723058539747552,0.7338709677419355,0.08246891250438924 +flat_mae,patch,logistic,adni_ad_vs_cn,68,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,68,166.81005372000556,test,0.5853658536585366,0.07401906598765423,0.4863669859985261,0.08002417651154202,0.4887096774193548,0.08731729854014975 +flat_mae,patch,logistic,adni_ad_vs_cn,69,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,69,21.54434690031882,test,0.7560975609756098,0.06311846410995943,0.6893939393939394,0.07791947521483165,0.7032258064516128,0.08371906691078246 +flat_mae,patch,logistic,adni_ad_vs_cn,70,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,70,166.81005372000556,test,0.7073170731707317,0.054348031306029526,0.5340909090909092,0.08348737885347941,0.535483870967742,0.07056282217321602 +flat_mae,patch,logistic,adni_ad_vs_cn,71,0.046415888336127774,train,0.9051490514905149,0.013348935503183838,0.851341551849166,0.02344744741716075,0.8167474730873532,0.026260800659585477 +flat_mae,patch,logistic,adni_ad_vs_cn,71,0.046415888336127774,test,0.6829268292682927,0.050431947420682396,0.4696517412935323,0.06966787464617082,0.4854838709677419,0.05737906741775723 +flat_mae,patch,logistic,adni_ad_vs_cn,72,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,72,21.54434690031882,test,0.7317073170731707,0.039054866148776776,0.4972129319955407,0.07117770726827559,0.5177419354838709,0.0502263592071848 +flat_mae,patch,logistic,adni_ad_vs_cn,73,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,73,21.54434690031882,test,0.8048780487804879,0.06222086506928569,0.7354838709677419,0.08379770716347627,0.7354838709677419,0.08570259030759712 +flat_mae,patch,logistic,adni_ad_vs_cn,74,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,74,166.81005372000556,test,0.7560975609756098,0.0591854283720946,0.6440972222222222,0.0879698454449336,0.635483870967742,0.08222180832861987 +flat_mae,patch,logistic,adni_ad_vs_cn,75,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,75,2.782559402207126,test,0.8048780487804879,0.057072649570270084,0.7152777777777778,0.08873922328495465,0.7016129032258065,0.08743770525172663 +flat_mae,patch,logistic,adni_ad_vs_cn,76,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,76,21.54434690031882,test,0.7073170731707317,0.06581590607116995,0.603225806451613,0.08495157671395279,0.603225806451613,0.08502532376640316 +flat_mae,patch,logistic,adni_ad_vs_cn,77,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,77,166.81005372000556,test,0.7804878048780488,0.05596078766509243,0.6660633484162897,0.09223254185416252,0.6516129032258065,0.0852674496561477 +flat_mae,patch,logistic,adni_ad_vs_cn,78,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,78,166.81005372000556,test,0.7560975609756098,0.06717368964562526,0.7054597701149425,0.07507979001414222,0.7370967741935484,0.08133086616951436 +flat_mae,patch,logistic,adni_ad_vs_cn,79,0.3593813663804626,train,0.975609756097561,0.007465323414233344,0.9648738695859115,0.011107240241222735,0.9517215876407263,0.014977646220472533 +flat_mae,patch,logistic,adni_ad_vs_cn,79,0.3593813663804626,test,0.8536585365853658,0.05086874081777024,0.8016129032258064,0.07080787710040606,0.8016129032258064,0.0760470725436277 +flat_mae,patch,logistic,adni_ad_vs_cn,80,0.005994842503189409,train,0.8184281842818428,0.0138037235523689,0.6597299640777902,0.033433408262326596,0.6347481304955214,0.02601925090819029 +flat_mae,patch,logistic,adni_ad_vs_cn,80,0.005994842503189409,test,0.7560975609756098,0.04653287810564446,0.569327731092437,0.09082647728295093,0.567741935483871,0.06927126329752148 +flat_mae,patch,logistic,adni_ad_vs_cn,81,0.005994842503189409,train,0.8211382113821138,0.012468806121412535,0.6576417004048583,0.032476081067111535,0.6324677459117429,0.024563884736420162 +flat_mae,patch,logistic,adni_ad_vs_cn,81,0.005994842503189409,test,0.8048780487804879,0.03243440275164686,0.6095238095238095,0.09923652315029885,0.6,0.06649052564087607 +flat_mae,patch,logistic,adni_ad_vs_cn,82,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,82,2.782559402207126,test,0.7804878048780488,0.06339316709820725,0.7410526315789474,0.06983750868286032,0.7870967741935484,0.07512549583776422 +flat_mae,patch,logistic,adni_ad_vs_cn,83,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,83,1291.5496650148827,test,0.7560975609756098,0.05954359427574256,0.6440972222222222,0.08815069104446678,0.635483870967742,0.0839670799175816 +flat_mae,patch,logistic,adni_ad_vs_cn,84,0.046415888336127774,train,0.8888888888888888,0.01405966134057904,0.8240507065185788,0.02505437313369703,0.7899580902292711,0.026487319574584705 +flat_mae,patch,logistic,adni_ad_vs_cn,84,0.046415888336127774,test,0.7317073170731707,0.06004955320380165,0.5918552036199095,0.09122675202019988,0.5854838709677419,0.08151191635463105 +flat_mae,patch,logistic,adni_ad_vs_cn,85,0.3593813663804626,train,0.9728997289972899,0.007670853181249552,0.9608013937282229,0.011479427457058183,0.9459076341523543,0.015269017669144085 +flat_mae,patch,logistic,adni_ad_vs_cn,85,0.3593813663804626,test,0.8536585365853658,0.05588719836515769,0.8016129032258064,0.07605139267403929,0.8016129032258064,0.07898267042109322 +flat_mae,patch,logistic,adni_ad_vs_cn,86,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,86,2.782559402207126,test,0.6829268292682927,0.06103458611281899,0.5547201336675021,0.07988054022907731,0.5532258064516129,0.0777431176459443 +flat_mae,patch,logistic,adni_ad_vs_cn,87,0.005994842503189409,train,0.8211382113821138,0.013633525515117949,0.6671131765992345,0.032165534630711534,0.6405620839838935,0.025181131172370214 +flat_mae,patch,logistic,adni_ad_vs_cn,87,0.005994842503189409,test,0.8048780487804879,0.03149161149082581,0.6095238095238095,0.09722792853269492,0.6,0.06455780355619295 +flat_mae,patch,logistic,adni_ad_vs_cn,88,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,88,21.54434690031882,test,0.7073170731707317,0.07111024026170445,0.6620879120879121,0.0757924017478316,0.7048387096774194,0.08472392449535054 +flat_mae,patch,logistic,adni_ad_vs_cn,89,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,89,166.81005372000556,test,0.7560975609756098,0.06625776642881673,0.7054597701149425,0.07523037894605458,0.7370967741935484,0.08163465450295516 +flat_mae,patch,logistic,adni_ad_vs_cn,90,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,90,2.782559402207126,test,0.7560975609756098,0.06554580254154335,0.6893939393939394,0.07941124009353895,0.7032258064516128,0.08448739199944477 +flat_mae,patch,logistic,adni_ad_vs_cn,91,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,91,166.81005372000556,test,0.6341463414634146,0.0653331552725744,0.5199063231850116,0.07647618156375047,0.5209677419354839,0.0803545641077397 +flat_mae,patch,logistic,adni_ad_vs_cn,92,0.3593813663804626,train,0.975609756097561,0.007798346785477701,0.9648738695859115,0.011602399887716544,0.9517215876407263,0.01574706113489123 +flat_mae,patch,logistic,adni_ad_vs_cn,92,0.3593813663804626,test,0.6829268292682927,0.06160824979330037,0.5547201336675021,0.0821168795678255,0.5532258064516129,0.07936587020097206 +flat_mae,patch,logistic,adni_ad_vs_cn,93,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,93,2.782559402207126,test,0.6829268292682927,0.06310006406077198,0.5547201336675021,0.08275078503274196,0.5532258064516129,0.0796312035222479 +flat_mae,patch,logistic,adni_ad_vs_cn,94,0.046415888336127774,train,0.9024390243902439,0.014027112836810532,0.8493877551020408,0.02363886833492022,0.8190278576711316,0.02572259716768545 +flat_mae,patch,logistic,adni_ad_vs_cn,94,0.046415888336127774,test,0.6585365853658537,0.05667016354352588,0.4564393939393939,0.06808356982840677,0.4693548387096774,0.05991912204183492 +flat_mae,patch,logistic,adni_ad_vs_cn,95,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,95,166.81005372000556,test,0.7804878048780488,0.05992460065145339,0.6917293233082706,0.08260908925667741,0.685483870967742,0.08349758892878209 +flat_mae,patch,logistic,adni_ad_vs_cn,96,0.3593813663804626,train,0.975609756097561,0.00805657648046619,0.9648738695859115,0.012032566686906486,0.9517215876407263,0.01648970949118496 +flat_mae,patch,logistic,adni_ad_vs_cn,96,0.3593813663804626,test,0.7560975609756098,0.0329243359489596,0.5119047619047619,0.07887369477154188,0.5338709677419355,0.05146099934604913 +flat_mae,patch,logistic,adni_ad_vs_cn,97,0.046415888336127774,train,0.8970189701897019,0.012783926019707197,0.8343179884677191,0.02369689063426384,0.7952584435861616,0.025257049816878374 +flat_mae,patch,logistic,adni_ad_vs_cn,97,0.046415888336127774,test,0.7073170731707317,0.034281405355135894,0.4142857142857143,0.01198068442848582,0.46774193548387094,0.022669961605815688 +flat_mae,patch,logistic,adni_ad_vs_cn,98,0.005994842503189409,train,0.8265582655826558,0.012387113816980542,0.6772006560962274,0.030512394849135333,0.6481428219245624,0.024218525055412284 +flat_mae,patch,logistic,adni_ad_vs_cn,98,0.005994842503189409,test,0.7317073170731707,0.05482840030560244,0.5918552036199095,0.08798511562641391,0.5854838709677419,0.07903013367783404 +flat_mae,patch,logistic,adni_ad_vs_cn,99,0.3593813663804626,train,0.983739837398374,0.006637997713035651,0.9766829555986183,0.009808844220459231,0.9651162790697674,0.014240820675059026 +flat_mae,patch,logistic,adni_ad_vs_cn,99,0.3593813663804626,test,0.8048780487804879,0.0430785566889253,0.6554621848739496,0.09396380328489887,0.6338709677419355,0.07389995881318914 +flat_mae,patch,logistic,adni_ad_vs_cn,100,0.046415888336127774,train,0.9024390243902439,0.01429182683271312,0.8463069233617179,0.02517205755009012,0.8109335195989811,0.02733477685839864 +flat_mae,patch,logistic,adni_ad_vs_cn,100,0.046415888336127774,test,0.7317073170731707,0.055358095513176074,0.5918552036199095,0.08881939160398047,0.5854838709677419,0.07944307152233746 diff --git a/decoders/crossreg_reg4/eval_v2/adni_ad_vs_cn__patch__logistic/log.txt b/decoders/crossreg_reg4/eval_v2/adni_ad_vs_cn__patch__logistic/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..079d7515b38172e8fc8a5c93fdf41a23c48545a2 --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/adni_ad_vs_cn__patch__logistic/log.txt @@ -0,0 +1,240 @@ +fMRI foundation model logistic probe eval +version: 0.1.dev66+g7ddd3aa04 +sha: aef99c83a386cf95c3d8ca503ecc968d8d5694af, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-03-07 21:47:01 +config: +output_root: experiments/decoders/output +name_prefix: eval_logistic +remote_root: null +notes: decoder ablations crossreg_reg4; eval v2 (adni_ad_vs_cn patch logistic) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: decoders/crossreg_reg4/eval_v2/adni_ad_vs_cn__patch__logistic +model: flat_mae +representation: patch +dataset: adni_ad_vs_cn +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg4/eval_v2/adni_ad_vs_cn__patch__logistic +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=False, reg_tokens=4, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: adni_ad_vs_cn (flat) +train (n=328): +ADNIDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'bold', 'mean', 'std'], + num_rows: 525 +}), + labels=[0 1], + counts=[251 77] +) + +validation (n=41): +ADNIDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'bold', 'mean', 'std'], + num_rows: 66 +}), + labels=[0 1], + counts=[31 10] +) + +test (n=41): +ADNIDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'bold', 'mean', 'std'], + num_rows: 66 +}), + labels=[0 1], + counts=[32 9] +) + +extracting features for all splits +extract (train) [ 0/164] eta: 0:11:10 time: 4.0894 data: 3.2760 max mem: 2698 +extract (train) [ 20/164] eta: 0:00:55 time: 0.1966 data: 0.0707 max mem: 2852 +extract (train) [ 40/164] eta: 0:00:33 time: 0.1567 data: 0.0475 max mem: 2852 +extract (train) [ 60/164] eta: 0:00:24 time: 0.1638 data: 0.0534 max mem: 2852 +extract (train) [ 80/164] eta: 0:00:18 time: 0.1691 data: 0.0549 max mem: 2852 +extract (train) [100/164] eta: 0:00:13 time: 0.1675 data: 0.0548 max mem: 2852 +extract (train) [120/164] eta: 0:00:08 time: 0.1714 data: 0.0559 max mem: 2852 +extract (train) [140/164] eta: 0:00:04 time: 0.1572 data: 0.0492 max mem: 2852 +extract (train) [160/164] eta: 0:00:00 time: 0.1522 data: 0.0480 max mem: 2852 +extract (train) [163/164] eta: 0:00:00 time: 0.1508 data: 0.0474 max mem: 2852 +extract (train) Total time: 0:00:31 (0.1928 s / it) +extract (validation) [ 0/21] eta: 0:01:13 time: 3.4934 data: 3.3892 max mem: 2852 +extract (validation) [20/21] eta: 0:00:00 time: 0.1421 data: 0.0416 max mem: 2852 +extract (validation) Total time: 0:00:06 (0.3166 s / it) +extract (test) [ 0/21] eta: 0:01:12 time: 3.4665 data: 3.3663 max mem: 2852 +extract (test) [20/21] eta: 0:00:00 time: 0.1396 data: 0.0420 max mem: 2852 +extract (test) Total time: 0:00:06 (0.3112 s / it) +feature extraction time: 0:00:44 +train features: (328, 768) +validation features: (41, 768) +test features: (41, 768) +evaluating fixed splits +eval results (fixed splits): + +| model | repr | clf | dataset | trial | C | split | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:--------------|:--------|-------:|:--------|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | adni_ad_vs_cn | | 166.81 | train | 1 | 0 | 1 | 0 | 1 | 0 | +| flat_mae | patch | logistic | adni_ad_vs_cn | | 166.81 | test | 0.65854 | 0.067211 | 0.50174 | 0.076845 | 0.50174 | 0.076542 | + + +evaluating random splits (n=100) +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 1, "C": 166.81005372000556, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.06175586637339688, "f1": 0.7119437939110069, "f1_std": 0.07982166095879796, "bacc": 0.7193548387096774, "bacc_std": 0.08516609223998574} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 2, "C": 2.782559402207126, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.06428491014860176, "f1": 0.6232247284878863, "f1_std": 0.09162267407571494, "bacc": 0.6193548387096774, "bacc_std": 0.08786441042986236} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 3, "C": 21.54434690031882, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.06948437611929524, "f1": 0.5839188134270101, "f1_std": 0.08497702446519155, "bacc": 0.5870967741935484, "bacc_std": 0.08792274414851722} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 4, "C": 166.81005372000556, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.06127466177863133, "f1": 0.783068783068783, "f1_std": 0.05915914345251882, "bacc": 0.8709677419354839, "bacc_std": 0.040520340853611066} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 5, "C": 166.81005372000556, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.0604363274265884, "f1": 0.5547201336675021, "f1_std": 0.0811416666945755, "bacc": 0.5532258064516129, "bacc_std": 0.07772808309192142} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 6, "C": 0.3593813663804626, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.06479200235603146, "f1": 0.6232247284878863, "f1_std": 0.08930198197826686, "bacc": 0.6193548387096774, "bacc_std": 0.08677124800133185} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 7, "C": 166.81005372000556, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.06372417884650156, "f1": 0.6893939393939394, "f1_std": 0.0784376993864998, "bacc": 0.7032258064516128, "bacc_std": 0.084067210612129} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 8, "C": 166.81005372000556, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.06641316068338539, "f1": 0.6479313036690086, "f1_std": 0.08202671334913557, "bacc": 0.6532258064516129, "bacc_std": 0.0854468406709409} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 9, "C": 166.81005372000556, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.0619757777327563, "f1": 0.7119437939110069, "f1_std": 0.08030073846778696, "bacc": 0.7193548387096774, "bacc_std": 0.08475320178801186} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 10, "C": 2.782559402207126, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.06399665369003064, "f1": 0.6479313036690086, "f1_std": 0.08319998345571941, "bacc": 0.6532258064516129, "bacc_std": 0.08832318716066874} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 11, "C": 166.81005372000556, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.05120557301614695, "f1": 0.6893939393939394, "f1_std": 0.09174013333260418, "bacc": 0.667741935483871, "bacc_std": 0.08241255189397681} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 12, "C": 166.81005372000556, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.06106450106001445, "f1": 0.5729166666666666, "f1_std": 0.08751751006546477, "bacc": 0.5693548387096774, "bacc_std": 0.08186769382609813} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 13, "C": 0.046415888336127774, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.05345814020626708, "f1": 0.6117424242424243, "f1_std": 0.09202468610571168, "bacc": 0.6016129032258064, "bacc_std": 0.0791058140916389} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 14, "C": 21.54434690031882, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.06369536361170726, "f1": 0.6693548387096775, "f1_std": 0.08657520433598431, "bacc": 0.6693548387096775, "bacc_std": 0.08820304807605202} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 15, "C": 2.782559402207126, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.06447931754782824, "f1": 0.6693548387096775, "f1_std": 0.08742264337378126, "bacc": 0.6693548387096775, "bacc_std": 0.08954270364040907} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 16, "C": 166.81005372000556, "split": "test", "acc": 0.8292682926829268, "acc_std": 0.04575690362803435, "f1": 0.7144278606965174, "f1_std": 0.09279895838312108, "bacc": 0.6838709677419355, "bacc_std": 0.07932248822621175} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 17, "C": 1291.5496650148827, "split": "test", "acc": 0.6585365853658537, "acc_std": 0.0711080986208361, "f1": 0.5651515151515152, "f1_std": 0.0852582525873165, "bacc": 0.5709677419354839, "bacc_std": 0.08977297363352293} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 18, "C": 0.3593813663804626, "split": "test", "acc": 0.8780487804878049, "acc_std": 0.03814609194603692, "f1": 0.7960199004975124, "f1_std": 0.08301462416148489, "bacc": 0.75, "bacc_std": 0.07819948848937569} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 19, "C": 1291.5496650148827, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.060457486500875714, "f1": 0.6440972222222222, "f1_std": 0.08494828399370564, "bacc": 0.635483870967742, "bacc_std": 0.08026925623399012} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 20, "C": 2.782559402207126, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.06407793811820159, "f1": 0.764367816091954, "f1_std": 0.07146125035822799, "bacc": 0.8032258064516129, "bacc_std": 0.07456277628052574} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 21, "C": 10000.0, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.058075808423928135, "f1": 0.6440972222222222, "f1_std": 0.08780002288873556, "bacc": 0.635483870967742, "bacc_std": 0.08256684587327397} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 22, "C": 166.81005372000556, "split": "test", "acc": 0.8292682926829268, "acc_std": 0.051874648712642704, "f1": 0.7402714932126697, "f1_std": 0.08889597556100112, "bacc": 0.717741935483871, "bacc_std": 0.08333749263987081} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 23, "C": 1291.5496650148827, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.06808896444446465, "f1": 0.6272727272727273, "f1_std": 0.08379512140986728, "bacc": 0.6370967741935484, "bacc_std": 0.0899293051054737} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 24, "C": 0.3593813663804626, "split": "test", "acc": 0.6585365853658537, "acc_std": 0.0730399481610212, "f1": 0.5651515151515152, "f1_std": 0.08570021624212107, "bacc": 0.5709677419354839, "bacc_std": 0.0912322758576622} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 25, "C": 21.54434690031882, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.06502429875755188, "f1": 0.6693548387096775, "f1_std": 0.08661123117886423, "bacc": 0.6693548387096775, "bacc_std": 0.08749686576815639} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 26, "C": 2.782559402207126, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.06437876837875586, "f1": 0.603225806451613, "f1_std": 0.08250327793555129, "bacc": 0.603225806451613, "bacc_std": 0.08280767299952495} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 27, "C": 166.81005372000556, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.06309206892481466, "f1": 0.6232247284878863, "f1_std": 0.08547873759960081, "bacc": 0.6193548387096774, "bacc_std": 0.08351086534453545} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 28, "C": 2.782559402207126, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.061738043058860034, "f1": 0.6232247284878863, "f1_std": 0.08457621269232801, "bacc": 0.6193548387096774, "bacc_std": 0.08213022222486381} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 29, "C": 1291.5496650148827, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.07105567523251301, "f1": 0.6272727272727273, "f1_std": 0.08378732150900603, "bacc": 0.6370967741935484, "bacc_std": 0.08966387946055397} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 30, "C": 0.3593813663804626, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.04778185109921527, "f1": 0.6328358208955224, "f1_std": 0.09319085105882638, "bacc": 0.6177419354838709, "bacc_std": 0.07593114487288175} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 31, "C": 21.54434690031882, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.05097528299580182, "f1": 0.5512437810945273, "f1_std": 0.08895511919602032, "bacc": 0.5516129032258065, "bacc_std": 0.07090380837178853} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 32, "C": 0.046415888336127774, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.060572010624942316, "f1": 0.5176470588235295, "f1_std": 0.08190754554917075, "bacc": 0.5193548387096775, "bacc_std": 0.07278577578846016} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 33, "C": 0.3593813663804626, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.06147417637105602, "f1": 0.6893939393939394, "f1_std": 0.07571128957091285, "bacc": 0.7032258064516128, "bacc_std": 0.08194897494976601} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 34, "C": 0.3593813663804626, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.062007195759818313, "f1": 0.7119437939110069, "f1_std": 0.07932457979132376, "bacc": 0.7193548387096774, "bacc_std": 0.08408095202384551} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 35, "C": 2.782559402207126, "split": "test", "acc": 0.8292682926829268, "acc_std": 0.05069360670594106, "f1": 0.7402714932126697, "f1_std": 0.08787541773146086, "bacc": 0.717741935483871, "bacc_std": 0.08333689079468769} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 36, "C": 166.81005372000556, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.07224472587268083, "f1": 0.5839188134270101, "f1_std": 0.08441764447486973, "bacc": 0.5870967741935484, "bacc_std": 0.08659274535656608} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 37, "C": 0.3593813663804626, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.05848117295950731, "f1": 0.5729166666666666, "f1_std": 0.0864804969138768, "bacc": 0.5693548387096774, "bacc_std": 0.07968586869134761} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 38, "C": 166.81005372000556, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.06711712971906027, "f1": 0.6479313036690086, "f1_std": 0.08419349273094341, "bacc": 0.6532258064516129, "bacc_std": 0.08785933908891233} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 39, "C": 2.782559402207126, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.06702252633471767, "f1": 0.5547201336675021, "f1_std": 0.08647402444083507, "bacc": 0.5532258064516129, "bacc_std": 0.08406115972553356} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 40, "C": 0.005994842503189409, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.04141989107375309, "f1": 0.4972129319955407, "f1_std": 0.07434953475605574, "bacc": 0.5177419354838709, "bacc_std": 0.05316787697999455} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 41, "C": 1291.5496650148827, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.06787837743012205, "f1": 0.6479313036690086, "f1_std": 0.0851149835833768, "bacc": 0.6532258064516129, "bacc_std": 0.08764715534317276} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 42, "C": 166.81005372000556, "split": "test", "acc": 0.6097560975609756, "acc_std": 0.06637732172945972, "f1": 0.47096774193548385, "f1_std": 0.0727034266598651, "bacc": 0.47096774193548385, "bacc_std": 0.07333956454307135} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 43, "C": 166.81005372000556, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.05879366313225619, "f1": 0.6440972222222222, "f1_std": 0.08787938032120693, "bacc": 0.635483870967742, "bacc_std": 0.08440252251237289} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 44, "C": 1291.5496650148827, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.053685558606160026, "f1": 0.6660633484162897, "f1_std": 0.09088552881025565, "bacc": 0.6516129032258065, "bacc_std": 0.08400442304147263} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 45, "C": 0.005994842503189409, "split": "test", "acc": 0.8292682926829268, "acc_std": 0.03504395132812059, "f1": 0.6800445930880714, "f1_std": 0.09352338117352493, "bacc": 0.65, "bacc_std": 0.07184010022264724} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 46, "C": 21.54434690031882, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.053717838627345894, "f1": 0.7152777777777778, "f1_std": 0.08634601572777, "bacc": 0.7016129032258065, "bacc_std": 0.0851015784674308} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 47, "C": 10000.0, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.05180846067259221, "f1": 0.5512437810945273, "f1_std": 0.08654368574712812, "bacc": 0.5516129032258065, "bacc_std": 0.06887771184022792} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 48, "C": 21.54434690031882, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.07177524574147591, "f1": 0.646551724137931, "f1_std": 0.08069310588351807, "bacc": 0.6709677419354838, "bacc_std": 0.09070532385276033} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 49, "C": 0.3593813663804626, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.06505340322129365, "f1": 0.5547201336675021, "f1_std": 0.08618118501625521, "bacc": 0.5532258064516129, "bacc_std": 0.08281085000319596} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 50, "C": 21.54434690031882, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.05796173017929806, "f1": 0.6917293233082706, "f1_std": 0.082836555047868, "bacc": 0.685483870967742, "bacc_std": 0.08079937068969135} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 51, "C": 1291.5496650148827, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.06379389403478483, "f1": 0.603225806451613, "f1_std": 0.0842392921222764, "bacc": 0.603225806451613, "bacc_std": 0.08491606457492491} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 52, "C": 10000.0, "split": "test", "acc": 0.6097560975609756, "acc_std": 0.0723268409477098, "f1": 0.5287356321839081, "f1_std": 0.07849295074799864, "bacc": 0.5387096774193548, "bacc_std": 0.08671881936254502} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 53, "C": 166.81005372000556, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.05463414634146341, "f1": 0.6117424242424243, "f1_std": 0.09245079057319427, "bacc": 0.6016129032258064, "bacc_std": 0.07855340091304261} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 54, "C": 0.005994842503189409, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.043246701792655724, "f1": 0.569327731092437, "f1_std": 0.08661224222477408, "bacc": 0.567741935483871, "bacc_std": 0.06507710139450365} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 55, "C": 166.81005372000556, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.07491260027493644, "f1": 0.6259649122807017, "f1_std": 0.07967230381546084, "bacc": 0.6548387096774193, "bacc_std": 0.08799429854531957} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 56, "C": 2.782559402207126, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.06456399322146954, "f1": 0.6693548387096775, "f1_std": 0.08350107478969533, "bacc": 0.6693548387096775, "bacc_std": 0.08552273802962136} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 57, "C": 0.046415888336127774, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.06265693681558678, "f1": 0.5729166666666666, "f1_std": 0.08851241615812118, "bacc": 0.5693548387096774, "bacc_std": 0.08031695899487994} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 58, "C": 21.54434690031882, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.06301145755703659, "f1": 0.7119437939110069, "f1_std": 0.08059125331526244, "bacc": 0.7193548387096774, "bacc_std": 0.08491596500908126} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 59, "C": 166.81005372000556, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.06620653423560834, "f1": 0.5839188134270101, "f1_std": 0.08236688301326865, "bacc": 0.5870967741935484, "bacc_std": 0.08558086250473963} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 60, "C": 166.81005372000556, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.06909857256497813, "f1": 0.6676492262343405, "f1_std": 0.08115322014834417, "bacc": 0.6870967741935483, "bacc_std": 0.08707174096641203} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 61, "C": 2.782559402207126, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.06908674250022279, "f1": 0.646551724137931, "f1_std": 0.07872518273436985, "bacc": 0.6709677419354838, "bacc_std": 0.08707151581180167} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 62, "C": 166.81005372000556, "split": "test", "acc": 0.6097560975609756, "acc_std": 0.07572358072732534, "f1": 0.5287356321839081, "f1_std": 0.08277261956763161, "bacc": 0.5387096774193548, "bacc_std": 0.09205784562266699} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 63, "C": 166.81005372000556, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.0734152661831638, "f1": 0.6259649122807017, "f1_std": 0.08025615812395835, "bacc": 0.6548387096774193, "bacc_std": 0.08996184785051084} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 64, "C": 21.54434690031882, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.06738905659997667, "f1": 0.6479313036690086, "f1_std": 0.08728104520261751, "bacc": 0.6532258064516129, "bacc_std": 0.09135951418689889} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 65, "C": 0.046415888336127774, "split": "test", "acc": 0.6585365853658537, "acc_std": 0.05693606629763894, "f1": 0.4564393939393939, "f1_std": 0.0689541429669208, "bacc": 0.4693548387096774, "bacc_std": 0.06066977631889546} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 66, "C": 0.046415888336127774, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.05811496534376152, "f1": 0.6440972222222222, "f1_std": 0.0883637958972104, "bacc": 0.635483870967742, "bacc_std": 0.08271046870689876} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 67, "C": 0.3593813663804626, "split": "test", "acc": 0.8536585365853658, "acc_std": 0.04583027426562429, "f1": 0.7670454545454546, "f1_std": 0.08723058539747552, "bacc": 0.7338709677419355, "bacc_std": 0.08246891250438924} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 68, "C": 166.81005372000556, "split": "test", "acc": 0.5853658536585366, "acc_std": 0.07401906598765423, "f1": 0.4863669859985261, "f1_std": 0.08002417651154202, "bacc": 0.4887096774193548, "bacc_std": 0.08731729854014975} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 69, "C": 21.54434690031882, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.06311846410995943, "f1": 0.6893939393939394, "f1_std": 0.07791947521483165, "bacc": 0.7032258064516128, "bacc_std": 0.08371906691078246} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 70, "C": 166.81005372000556, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.054348031306029526, "f1": 0.5340909090909092, "f1_std": 0.08348737885347941, "bacc": 0.535483870967742, "bacc_std": 0.07056282217321602} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 71, "C": 0.046415888336127774, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.050431947420682396, "f1": 0.4696517412935323, "f1_std": 0.06966787464617082, "bacc": 0.4854838709677419, "bacc_std": 0.05737906741775723} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 72, "C": 21.54434690031882, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.039054866148776776, "f1": 0.4972129319955407, "f1_std": 0.07117770726827559, "bacc": 0.5177419354838709, "bacc_std": 0.0502263592071848} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 73, "C": 21.54434690031882, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.06222086506928569, "f1": 0.7354838709677419, "f1_std": 0.08379770716347627, "bacc": 0.7354838709677419, "bacc_std": 0.08570259030759712} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 74, "C": 166.81005372000556, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.0591854283720946, "f1": 0.6440972222222222, "f1_std": 0.0879698454449336, "bacc": 0.635483870967742, "bacc_std": 0.08222180832861987} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 75, "C": 2.782559402207126, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.057072649570270084, "f1": 0.7152777777777778, "f1_std": 0.08873922328495465, "bacc": 0.7016129032258065, "bacc_std": 0.08743770525172663} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 76, "C": 21.54434690031882, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.06581590607116995, "f1": 0.603225806451613, "f1_std": 0.08495157671395279, "bacc": 0.603225806451613, "bacc_std": 0.08502532376640316} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 77, "C": 166.81005372000556, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.05596078766509243, "f1": 0.6660633484162897, "f1_std": 0.09223254185416252, "bacc": 0.6516129032258065, "bacc_std": 0.0852674496561477} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 78, "C": 166.81005372000556, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.06717368964562526, "f1": 0.7054597701149425, "f1_std": 0.07507979001414222, "bacc": 0.7370967741935484, "bacc_std": 0.08133086616951436} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 79, "C": 0.3593813663804626, "split": "test", "acc": 0.8536585365853658, "acc_std": 0.05086874081777024, "f1": 0.8016129032258064, "f1_std": 0.07080787710040606, "bacc": 0.8016129032258064, "bacc_std": 0.0760470725436277} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 80, "C": 0.005994842503189409, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.04653287810564446, "f1": 0.569327731092437, "f1_std": 0.09082647728295093, "bacc": 0.567741935483871, "bacc_std": 0.06927126329752148} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 81, "C": 0.005994842503189409, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.03243440275164686, "f1": 0.6095238095238095, "f1_std": 0.09923652315029885, "bacc": 0.6, "bacc_std": 0.06649052564087607} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 82, "C": 2.782559402207126, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.06339316709820725, "f1": 0.7410526315789474, "f1_std": 0.06983750868286032, "bacc": 0.7870967741935484, "bacc_std": 0.07512549583776422} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 83, "C": 1291.5496650148827, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.05954359427574256, "f1": 0.6440972222222222, "f1_std": 0.08815069104446678, "bacc": 0.635483870967742, "bacc_std": 0.0839670799175816} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 84, "C": 0.046415888336127774, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.06004955320380165, "f1": 0.5918552036199095, "f1_std": 0.09122675202019988, "bacc": 0.5854838709677419, "bacc_std": 0.08151191635463105} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 85, "C": 0.3593813663804626, "split": "test", "acc": 0.8536585365853658, "acc_std": 0.05588719836515769, "f1": 0.8016129032258064, "f1_std": 0.07605139267403929, "bacc": 0.8016129032258064, "bacc_std": 0.07898267042109322} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 86, "C": 2.782559402207126, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.06103458611281899, "f1": 0.5547201336675021, "f1_std": 0.07988054022907731, "bacc": 0.5532258064516129, "bacc_std": 0.0777431176459443} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 87, "C": 0.005994842503189409, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.03149161149082581, "f1": 0.6095238095238095, "f1_std": 0.09722792853269492, "bacc": 0.6, "bacc_std": 0.06455780355619295} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 88, "C": 21.54434690031882, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.07111024026170445, "f1": 0.6620879120879121, "f1_std": 0.0757924017478316, "bacc": 0.7048387096774194, "bacc_std": 0.08472392449535054} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 89, "C": 166.81005372000556, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.06625776642881673, "f1": 0.7054597701149425, "f1_std": 0.07523037894605458, "bacc": 0.7370967741935484, "bacc_std": 0.08163465450295516} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 90, "C": 2.782559402207126, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.06554580254154335, "f1": 0.6893939393939394, "f1_std": 0.07941124009353895, "bacc": 0.7032258064516128, "bacc_std": 0.08448739199944477} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 91, "C": 166.81005372000556, "split": "test", "acc": 0.6341463414634146, "acc_std": 0.0653331552725744, "f1": 0.5199063231850116, "f1_std": 0.07647618156375047, "bacc": 0.5209677419354839, "bacc_std": 0.0803545641077397} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 92, "C": 0.3593813663804626, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.06160824979330037, "f1": 0.5547201336675021, "f1_std": 0.0821168795678255, "bacc": 0.5532258064516129, "bacc_std": 0.07936587020097206} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 93, "C": 2.782559402207126, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.06310006406077198, "f1": 0.5547201336675021, "f1_std": 0.08275078503274196, "bacc": 0.5532258064516129, "bacc_std": 0.0796312035222479} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 94, "C": 0.046415888336127774, "split": "test", "acc": 0.6585365853658537, "acc_std": 0.05667016354352588, "f1": 0.4564393939393939, "f1_std": 0.06808356982840677, "bacc": 0.4693548387096774, "bacc_std": 0.05991912204183492} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 95, "C": 166.81005372000556, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.05992460065145339, "f1": 0.6917293233082706, "f1_std": 0.08260908925667741, "bacc": 0.685483870967742, "bacc_std": 0.08349758892878209} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 96, "C": 0.3593813663804626, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.0329243359489596, "f1": 0.5119047619047619, "f1_std": 0.07887369477154188, "bacc": 0.5338709677419355, "bacc_std": 0.05146099934604913} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 97, "C": 0.046415888336127774, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.034281405355135894, "f1": 0.4142857142857143, "f1_std": 0.01198068442848582, "bacc": 0.46774193548387094, "bacc_std": 0.022669961605815688} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 98, "C": 0.005994842503189409, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.05482840030560244, "f1": 0.5918552036199095, "f1_std": 0.08798511562641391, "bacc": 0.5854838709677419, "bacc_std": 0.07903013367783404} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 99, "C": 0.3593813663804626, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.0430785566889253, "f1": 0.6554621848739496, "f1_std": 0.09396380328489887, "bacc": 0.6338709677419355, "bacc_std": 0.07389995881318914} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 100, "C": 0.046415888336127774, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.055358095513176074, "f1": 0.5918552036199095, "f1_std": 0.08881939160398047, "bacc": 0.5854838709677419, "bacc_std": 0.07944307152233746} +eval results (random splits): + +| model | repr | clf | dataset | split | n_trials | C | C_std | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:--------------|:--------|-----------:|-------:|--------:|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | adni_ad_vs_cn | train | 100 | 455.19 | 1721.6 | 0.97444 | 0.051405 | 0.95652 | 0.092261 | 0.94942 | 0.10257 | +| flat_mae | patch | logistic | adni_ad_vs_cn | test | 100 | 455.19 | 1721.6 | 0.73878 | 0.056783 | 0.62697 | 0.081969 | 0.62979 | 0.081878 | + + +done! total time: 0:04:29 diff --git a/decoders/crossreg_reg4/eval_v2/adni_ad_vs_cn__reg__logistic/config.yaml b/decoders/crossreg_reg4/eval_v2/adni_ad_vs_cn__reg__logistic/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..36c3f3d36fa21f0f06bbb035c7c0be2ac8e8e719 --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/adni_ad_vs_cn__reg__logistic/config.yaml @@ -0,0 +1,30 @@ +output_root: experiments/decoders/output +name_prefix: eval_logistic +remote_root: null +notes: decoder ablations crossreg_reg4; eval v2 (adni_ad_vs_cn reg logistic) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: decoders/crossreg_reg4/eval_v2/adni_ad_vs_cn__reg__logistic +model: flat_mae +representation: reg +dataset: adni_ad_vs_cn +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg4/eval_v2/adni_ad_vs_cn__reg__logistic +remote_dir: null diff --git a/decoders/crossreg_reg4/eval_v2/adni_ad_vs_cn__reg__logistic/eval_table.csv b/decoders/crossreg_reg4/eval_v2/adni_ad_vs_cn__reg__logistic/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..ad4f3625469874b149b37f263318902ce929976b --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/adni_ad_vs_cn__reg__logistic/eval_table.csv @@ -0,0 +1,203 @@ +model,repr,clf,dataset,trial,C,split,acc,acc_std,f1,f1_std,bacc,bacc_std +flat_mae,reg,logistic,adni_ad_vs_cn,,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,,21.54434690031882,test,0.7317073170731707,0.061503103716848896,0.5918552036199095,0.08573707634043229,0.5885416666666666,0.08348856664257005 +flat_mae,reg,logistic,adni_ad_vs_cn,1,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,1,1291.5496650148827,test,0.7804878048780488,0.05965197498965619,0.6917293233082706,0.08421119542537488,0.685483870967742,0.08393276104532095 +flat_mae,reg,logistic,adni_ad_vs_cn,2,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,2,166.81005372000556,test,0.7804878048780488,0.060952795732066516,0.6917293233082706,0.08639343869179594,0.685483870967742,0.08576363132386826 +flat_mae,reg,logistic,adni_ad_vs_cn,3,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,3,21.54434690031882,test,0.6829268292682927,0.06567274155042077,0.5547201336675021,0.087446297612882,0.5532258064516129,0.08359551859045979 +flat_mae,reg,logistic,adni_ad_vs_cn,4,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,4,2.782559402207126,test,0.8780487804878049,0.04999700169475366,0.8287385129490392,0.07348973685417326,0.8177419354838709,0.07690595220053496 +flat_mae,reg,logistic,adni_ad_vs_cn,5,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,5,21.54434690031882,test,0.7560975609756098,0.04297104153345551,0.569327731092437,0.08611760164225671,0.567741935483871,0.06503548219094353 +flat_mae,reg,logistic,adni_ad_vs_cn,6,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,6,1291.5496650148827,test,0.6829268292682927,0.06638268088317434,0.5839188134270101,0.08277286962308099,0.5870967741935484,0.08582816236372913 +flat_mae,reg,logistic,adni_ad_vs_cn,7,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,7,1291.5496650148827,test,0.7317073170731707,0.06694010747894036,0.6479313036690086,0.08462423368279873,0.6532258064516129,0.087403401174901 +flat_mae,reg,logistic,adni_ad_vs_cn,8,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,8,21.54434690031882,test,0.7804878048780488,0.05315549121475575,0.6660633484162897,0.08475383202565291,0.6516129032258065,0.07784234253517273 +flat_mae,reg,logistic,adni_ad_vs_cn,9,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,9,166.81005372000556,test,0.7804878048780488,0.06612365608547857,0.7280766396462786,0.07837400086085841,0.7532258064516129,0.08378285793692576 +flat_mae,reg,logistic,adni_ad_vs_cn,10,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,10,166.81005372000556,test,0.7560975609756098,0.06383834059499562,0.6693548387096775,0.08516590831766294,0.6693548387096775,0.0883888507007518 +flat_mae,reg,logistic,adni_ad_vs_cn,11,0.3593813663804626,train,0.997289972899729,0.0026130283104582475,0.9961941891766453,0.0036965715345039585,0.9941860465116279,0.005605857247436579 +flat_mae,reg,logistic,adni_ad_vs_cn,11,0.3593813663804626,test,0.8048780487804879,0.047657812611521855,0.6893939393939394,0.08683037374702807,0.667741935483871,0.07779467064289844 +flat_mae,reg,logistic,adni_ad_vs_cn,12,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,12,1291.5496650148827,test,0.7317073170731707,0.06135900927358825,0.6232247284878863,0.0847216698151674,0.6193548387096774,0.08315368943466846 +flat_mae,reg,logistic,adni_ad_vs_cn,13,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,13,166.81005372000556,test,0.8048780487804879,0.05510293218186004,0.7152777777777778,0.0854177483880803,0.7016129032258065,0.08431675443257824 +flat_mae,reg,logistic,adni_ad_vs_cn,14,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,14,2.782559402207126,test,0.8048780487804879,0.056206871231079474,0.7152777777777778,0.08764975410828699,0.7016129032258065,0.08555144371272728 +flat_mae,reg,logistic,adni_ad_vs_cn,15,0.3593813663804626,train,0.991869918699187,0.005010253072471148,0.9884880564885973,0.007238768213460641,0.9825581395348837,0.010748740603150363 +flat_mae,reg,logistic,adni_ad_vs_cn,15,0.3593813663804626,test,0.7804878048780488,0.06187635191920471,0.7119437939110069,0.08057680751526211,0.7193548387096774,0.0849466671759876 +flat_mae,reg,logistic,adni_ad_vs_cn,16,0.046415888336127774,train,0.9186991869918699,0.01293309887559064,0.8719224361347648,0.02318690969873031,0.8336757334209877,0.026417961547204792 +flat_mae,reg,logistic,adni_ad_vs_cn,16,0.046415888336127774,test,0.7560975609756098,0.04553796358320358,0.569327731092437,0.0882871089406134,0.567741935483871,0.0665605567188106 +flat_mae,reg,logistic,adni_ad_vs_cn,17,0.3593813663804626,train,0.997289972899729,0.0028031428328590575,0.9961941891766453,0.003970995437953729,0.9941860465116279,0.0060137192170057665 +flat_mae,reg,logistic,adni_ad_vs_cn,17,0.3593813663804626,test,0.8048780487804879,0.05758403837273237,0.7152777777777778,0.0890620732247795,0.7016129032258065,0.08537799286076218 +flat_mae,reg,logistic,adni_ad_vs_cn,18,0.3593813663804626,train,0.997289972899729,0.0025586789432252076,0.9961941891766453,0.0036181555244458206,0.9941860465116279,0.005489258895640111 +flat_mae,reg,logistic,adni_ad_vs_cn,18,0.3593813663804626,test,0.8536585365853658,0.04516901961671339,0.7670454545454546,0.0846177698850047,0.7338709677419355,0.07993524538484041 +flat_mae,reg,logistic,adni_ad_vs_cn,19,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,19,166.81005372000556,test,0.7317073170731707,0.05950747682215606,0.5918552036199095,0.0884153461176964,0.5854838709677419,0.07815662887328642 +flat_mae,reg,logistic,adni_ad_vs_cn,20,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,20,166.81005372000556,test,0.8536585365853658,0.05659327110465348,0.8136363636363637,0.06858781424200065,0.8354838709677419,0.07111708121383084 +flat_mae,reg,logistic,adni_ad_vs_cn,21,0.3593813663804626,train,0.991869918699187,0.004525907531615195,0.9884880564885973,0.00650970253559408,0.9825581395348837,0.009709650460267538 +flat_mae,reg,logistic,adni_ad_vs_cn,21,0.3593813663804626,test,0.8292682926829268,0.04505614185763996,0.7144278606965174,0.0975771118188164,0.6838709677419355,0.08241832907637679 +flat_mae,reg,logistic,adni_ad_vs_cn,22,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,22,21.54434690031882,test,0.6829268292682927,0.06592906252139064,0.5547201336675021,0.08585452757079653,0.5532258064516129,0.08427651307195332 +flat_mae,reg,logistic,adni_ad_vs_cn,23,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,23,166.81005372000556,test,0.7804878048780488,0.059625222535461715,0.6660633484162897,0.09619101759136134,0.6516129032258065,0.08917984868248081 +flat_mae,reg,logistic,adni_ad_vs_cn,24,0.3593813663804626,train,0.994579945799458,0.0037225317364751646,0.9923570836785418,0.005310895002197235,0.9883720930232558,0.007986129132321749 +flat_mae,reg,logistic,adni_ad_vs_cn,24,0.3593813663804626,test,0.7804878048780488,0.05419973197226676,0.6660633484162897,0.09112898780124525,0.6516129032258065,0.08338953256565988 +flat_mae,reg,logistic,adni_ad_vs_cn,25,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,25,166.81005372000556,test,0.7317073170731707,0.05691516590029985,0.5918552036199095,0.08838742606970534,0.5854838709677419,0.07953571380877775 +flat_mae,reg,logistic,adni_ad_vs_cn,26,0.046415888336127774,train,0.9132791327913279,0.012600683008105858,0.861952861952862,0.02278275646182898,0.8220478264442436,0.025635743595965443 +flat_mae,reg,logistic,adni_ad_vs_cn,26,0.046415888336127774,test,0.8048780487804879,0.05156489820554526,0.6893939393939394,0.0923113828438389,0.667741935483871,0.08182558568335797 +flat_mae,reg,logistic,adni_ad_vs_cn,27,0.046415888336127774,train,0.9051490514905149,0.01405086303946133,0.851341551849166,0.024467684791434408,0.8167474730873532,0.02667977666821483 +flat_mae,reg,logistic,adni_ad_vs_cn,27,0.046415888336127774,test,0.8048780487804879,0.049591214128501086,0.6893939393939394,0.08944368214047783,0.667741935483871,0.07884346449681522 +flat_mae,reg,logistic,adni_ad_vs_cn,28,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,28,21.54434690031882,test,0.7804878048780488,0.04781980851961939,0.6328358208955224,0.08942107078387601,0.6177419354838709,0.07419629525069428 +flat_mae,reg,logistic,adni_ad_vs_cn,29,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,29,2.782559402207126,test,0.6829268292682927,0.072968484718037,0.5839188134270101,0.08879885560928677,0.5870967741935484,0.09131133099201774 +flat_mae,reg,logistic,adni_ad_vs_cn,30,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,30,2.782559402207126,test,0.7073170731707317,0.061711057439902794,0.5729166666666666,0.08717477286339652,0.5693548387096774,0.08016214700652118 +flat_mae,reg,logistic,adni_ad_vs_cn,31,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,31,21.54434690031882,test,0.7560975609756098,0.059906014034895344,0.6440972222222222,0.09155689710746522,0.635483870967742,0.08651491778276979 +flat_mae,reg,logistic,adni_ad_vs_cn,32,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,32,1291.5496650148827,test,0.6341463414634146,0.07794651837223623,0.5858585858585859,0.08061991945745695,0.6225806451612903,0.09214856455774029 +flat_mae,reg,logistic,adni_ad_vs_cn,33,0.3593813663804626,train,0.997289972899729,0.003059000035483591,0.9961941891766453,0.004338876103463684,0.9941860465116279,0.006562622169147942 +flat_mae,reg,logistic,adni_ad_vs_cn,33,0.3593813663804626,test,0.6585365853658537,0.07007493227434483,0.5876436781609196,0.08178028971133995,0.6048387096774194,0.09067111756713982 +flat_mae,reg,logistic,adni_ad_vs_cn,34,0.046415888336127774,train,0.9186991869918699,0.012458415195933334,0.8719224361347648,0.02242585939264016,0.8336757334209877,0.025662137996899034 +flat_mae,reg,logistic,adni_ad_vs_cn,34,0.046415888336127774,test,0.7560975609756098,0.06018055324352879,0.6440972222222222,0.0899098719239102,0.635483870967742,0.08489291356876348 +flat_mae,reg,logistic,adni_ad_vs_cn,35,0.3593813663804626,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,35,0.3593813663804626,test,0.7560975609756098,0.059202934956267585,0.6440972222222222,0.08909329156291687,0.635483870967742,0.08434189476955956 +flat_mae,reg,logistic,adni_ad_vs_cn,36,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,36,166.81005372000556,test,0.5853658536585366,0.07539519517241305,0.5108771929824562,0.07668583182122167,0.5225806451612903,0.08555055530507844 +flat_mae,reg,logistic,adni_ad_vs_cn,37,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,37,166.81005372000556,test,0.7560975609756098,0.06205850130941747,0.6693548387096775,0.08402566855862001,0.6693548387096775,0.0869573466434881 +flat_mae,reg,logistic,adni_ad_vs_cn,38,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,38,21.54434690031882,test,0.7317073170731707,0.0706569663986105,0.6676492262343405,0.08392506774076239,0.6870967741935483,0.0901794286677328 +flat_mae,reg,logistic,adni_ad_vs_cn,39,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,39,21.54434690031882,test,0.6829268292682927,0.06415411248486724,0.5547201336675021,0.08445878953795607,0.5532258064516129,0.08042621918609777 +flat_mae,reg,logistic,adni_ad_vs_cn,40,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,40,21.54434690031882,test,0.7317073170731707,0.06689544524766987,0.6479313036690086,0.08348594721613219,0.6532258064516129,0.0866521325829056 +flat_mae,reg,logistic,adni_ad_vs_cn,41,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,41,2.782559402207126,test,0.6341463414634146,0.07105311332898664,0.5684210526315789,0.07619345303127505,0.5887096774193548,0.08778585066810832 +flat_mae,reg,logistic,adni_ad_vs_cn,42,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,42,1291.5496650148827,test,0.8292682926829268,0.051537133652849725,0.7402714932126697,0.08541743756073045,0.717741935483871,0.08257709821011713 +flat_mae,reg,logistic,adni_ad_vs_cn,43,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,43,2.782559402207126,test,0.8048780487804879,0.05821219057439226,0.7152777777777778,0.08983117682872478,0.7016129032258065,0.08668411465551701 +flat_mae,reg,logistic,adni_ad_vs_cn,44,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,44,166.81005372000556,test,0.8292682926829268,0.045681982723045474,0.7144278606965174,0.09295168511434643,0.6838709677419355,0.08154485343507693 +flat_mae,reg,logistic,adni_ad_vs_cn,45,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,45,166.81005372000556,test,0.7804878048780488,0.06406367668062286,0.7280766396462786,0.07657020332749781,0.7532258064516129,0.08305472187794433 +flat_mae,reg,logistic,adni_ad_vs_cn,46,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,46,21.54434690031882,test,0.8048780487804879,0.054857101693279356,0.7354838709677419,0.07788234853373478,0.7354838709677419,0.08207292733066335 +flat_mae,reg,logistic,adni_ad_vs_cn,47,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,47,21.54434690031882,test,0.7073170731707317,0.062241379259203776,0.5729166666666666,0.08683763851162027,0.5693548387096774,0.08206348111286849 +flat_mae,reg,logistic,adni_ad_vs_cn,48,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,48,21.54434690031882,test,0.6829268292682927,0.07145652176863818,0.5839188134270101,0.0870668817515905,0.5870967741935484,0.09073478154889847 +flat_mae,reg,logistic,adni_ad_vs_cn,49,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,49,2.782559402207126,test,0.7317073170731707,0.05199862717265304,0.5512437810945273,0.09039742888627253,0.5516129032258065,0.07205512075237205 +flat_mae,reg,logistic,adni_ad_vs_cn,50,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,50,21.54434690031882,test,0.8292682926829268,0.05878200585024896,0.7759562841530054,0.0766716918114474,0.7854838709677419,0.08059190008953519 +flat_mae,reg,logistic,adni_ad_vs_cn,51,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,51,21.54434690031882,test,0.6829268292682927,0.07209569620348251,0.6259649122807017,0.07865515971011627,0.6548387096774193,0.08860048153245872 +flat_mae,reg,logistic,adni_ad_vs_cn,52,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,52,166.81005372000556,test,0.7560975609756098,0.05413260647593688,0.6117424242424243,0.09191297635254492,0.6016129032258064,0.07879840609637905 +flat_mae,reg,logistic,adni_ad_vs_cn,53,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,53,166.81005372000556,test,0.7073170731707317,0.05852184773826586,0.5729166666666666,0.08533728565060335,0.5693548387096774,0.07863301157837932 +flat_mae,reg,logistic,adni_ad_vs_cn,54,0.046415888336127774,train,0.9186991869918699,0.012219307543989796,0.8719224361347648,0.021768864080769633,0.8336757334209877,0.024718358947797506 +flat_mae,reg,logistic,adni_ad_vs_cn,54,0.046415888336127774,test,0.7073170731707317,0.059563732182869866,0.5729166666666666,0.08375471949209458,0.5693548387096774,0.07763501655854649 +flat_mae,reg,logistic,adni_ad_vs_cn,55,0.3593813663804626,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,55,0.3593813663804626,test,0.7560975609756098,0.059685872125239035,0.6440972222222222,0.09056736965829243,0.635483870967742,0.08535591220401186 +flat_mae,reg,logistic,adni_ad_vs_cn,56,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,56,166.81005372000556,test,0.7317073170731707,0.05257441399144382,0.5512437810945273,0.0882881544227209,0.5516129032258065,0.07113187025279717 +flat_mae,reg,logistic,adni_ad_vs_cn,57,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,57,2.782559402207126,test,0.7317073170731707,0.06456856313739374,0.6479313036690086,0.08245623609374042,0.6532258064516129,0.08598236539668559 +flat_mae,reg,logistic,adni_ad_vs_cn,58,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,58,21.54434690031882,test,0.8048780487804879,0.05875720619796659,0.7152777777777778,0.08769526628535422,0.7016129032258065,0.08484627367237413 +flat_mae,reg,logistic,adni_ad_vs_cn,59,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,59,2.782559402207126,test,0.7804878048780488,0.05655749944618306,0.6660633484162897,0.09321834066404755,0.6516129032258065,0.08649535701180368 +flat_mae,reg,logistic,adni_ad_vs_cn,60,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,60,2.782559402207126,test,0.8780487804878049,0.04847033105175277,0.8287385129490392,0.07333204559007016,0.8177419354838709,0.07820235258642817 +flat_mae,reg,logistic,adni_ad_vs_cn,61,0.046415888336127774,train,0.924119241192412,0.01281720317057954,0.8828571428571428,0.022009622409507105,0.8493508094338073,0.025891173853371845 +flat_mae,reg,logistic,adni_ad_vs_cn,61,0.046415888336127774,test,0.7317073170731707,0.04893874329081201,0.5512437810945273,0.08810481853024506,0.5516129032258065,0.06974457777513789 +flat_mae,reg,logistic,adni_ad_vs_cn,62,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,62,2.782559402207126,test,0.8536585365853658,0.05534459675744239,0.8016129032258064,0.07580692980956008,0.8016129032258064,0.08022866714746085 +flat_mae,reg,logistic,adni_ad_vs_cn,63,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,63,21.54434690031882,test,0.7804878048780488,0.060204272538465095,0.7119437939110069,0.07803112756648595,0.7193548387096774,0.08221201114359575 +flat_mae,reg,logistic,adni_ad_vs_cn,64,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,64,21.54434690031882,test,0.7073170731707317,0.06578200256899232,0.5729166666666666,0.09125109978236295,0.5693548387096774,0.08493307373177764 +flat_mae,reg,logistic,adni_ad_vs_cn,65,0.046415888336127774,train,0.9132791327913279,0.012815745377767435,0.8647732478240953,0.022223798272055943,0.8301421645163941,0.02493051215023349 +flat_mae,reg,logistic,adni_ad_vs_cn,65,0.046415888336127774,test,0.7804878048780488,0.05620416170516529,0.6660633484162897,0.09020495655759604,0.6516129032258065,0.0828187233451739 +flat_mae,reg,logistic,adni_ad_vs_cn,66,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,66,166.81005372000556,test,0.8292682926829268,0.0480918217522762,0.7402714932126697,0.08265546278534666,0.717741935483871,0.07863693756786329 +flat_mae,reg,logistic,adni_ad_vs_cn,67,0.046415888336127774,train,0.9132791327913279,0.01301833836122437,0.861952861952862,0.023584640443634203,0.8220478264442436,0.026463870722474605 +flat_mae,reg,logistic,adni_ad_vs_cn,67,0.046415888336127774,test,0.8292682926829268,0.04484672820105256,0.7144278606965174,0.09250793822282488,0.6838709677419355,0.08073356567395498 +flat_mae,reg,logistic,adni_ad_vs_cn,68,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,68,2.782559402207126,test,0.6829268292682927,0.0628885495214838,0.5547201336675021,0.0833917942345513,0.5532258064516129,0.08051352320793594 +flat_mae,reg,logistic,adni_ad_vs_cn,69,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,69,166.81005372000556,test,0.7804878048780488,0.06387962728192434,0.7119437939110069,0.08194811343093335,0.7193548387096774,0.08543176567816362 +flat_mae,reg,logistic,adni_ad_vs_cn,70,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,70,21.54434690031882,test,0.8048780487804879,0.054270983764463314,0.7152777777777778,0.08579718952741154,0.7016129032258065,0.08392429173353842 +flat_mae,reg,logistic,adni_ad_vs_cn,71,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,71,166.81005372000556,test,0.6585365853658537,0.06914492621255675,0.5651515151515152,0.08211122033999584,0.5709677419354839,0.08671599943350904 +flat_mae,reg,logistic,adni_ad_vs_cn,72,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,72,2.782559402207126,test,0.6829268292682927,0.0389172614930417,0.4057971014492754,0.013931014571946607,0.45161290322580644,0.02573560840668887 +flat_mae,reg,logistic,adni_ad_vs_cn,73,0.046415888336127774,train,0.9105691056910569,0.012475004496142717,0.8568842921784099,0.022953237454800768,0.8162338729558715,0.025369187275369486 +flat_mae,reg,logistic,adni_ad_vs_cn,73,0.046415888336127774,test,0.8536585365853658,0.050436854225144684,0.7864583333333333,0.07938752523206534,0.7677419354838709,0.08293850234780074 +flat_mae,reg,logistic,adni_ad_vs_cn,74,0.046415888336127774,train,0.924119241192412,0.011860292343370915,0.8816765918460834,0.020708989660686794,0.8453036403977319,0.024104130835493856 +flat_mae,reg,logistic,adni_ad_vs_cn,74,0.046415888336127774,test,0.7073170731707317,0.033799070348968036,0.4142857142857143,0.011755025975526823,0.46774193548387094,0.022350998133995006 +flat_mae,reg,logistic,adni_ad_vs_cn,75,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,75,166.81005372000556,test,0.6585365853658537,0.06499851277299176,0.5370967741935484,0.07952403284750914,0.5370967741935484,0.07833145536158176 +flat_mae,reg,logistic,adni_ad_vs_cn,76,0.3593813663804626,train,0.994579945799458,0.003836276687532417,0.9923570836785418,0.005476299414689379,0.9883720930232558,0.00823015173081086 +flat_mae,reg,logistic,adni_ad_vs_cn,76,0.3593813663804626,test,0.7073170731707317,0.05996983179698337,0.5729166666666666,0.08345813132615776,0.5693548387096774,0.0783107529465472 +flat_mae,reg,logistic,adni_ad_vs_cn,77,10000.0,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,77,10000.0,test,0.7560975609756098,0.06449132863698401,0.6893939393939394,0.07994717234162295,0.7032258064516128,0.08617110244729557 +flat_mae,reg,logistic,adni_ad_vs_cn,78,0.3593813663804626,train,0.991869918699187,0.0046970203461552396,0.9884880564885973,0.0067715079588420365,0.9825581395348837,0.01007674713797263 +flat_mae,reg,logistic,adni_ad_vs_cn,78,0.3593813663804626,test,0.8048780487804879,0.05647632471067588,0.7152777777777778,0.08684678224415845,0.7016129032258065,0.0841359872446731 +flat_mae,reg,logistic,adni_ad_vs_cn,79,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,79,21.54434690031882,test,0.9024390243902439,0.04799613309825579,0.8757575757575757,0.05817015566432631,0.9016129032258065,0.05613435820115493 +flat_mae,reg,logistic,adni_ad_vs_cn,80,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,80,21.54434690031882,test,0.6829268292682927,0.06847326299651309,0.5839188134270101,0.08383691342986946,0.5870967741935484,0.08590296754773238 +flat_mae,reg,logistic,adni_ad_vs_cn,81,0.046415888336127774,train,0.9105691056910569,0.012976224421871204,0.859836320314928,0.02294412090442928,0.824328211028022,0.025956560139363236 +flat_mae,reg,logistic,adni_ad_vs_cn,81,0.046415888336127774,test,0.8048780487804879,0.03243440275164686,0.6095238095238095,0.09923652315029885,0.6,0.06649052564087607 +flat_mae,reg,logistic,adni_ad_vs_cn,82,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,82,166.81005372000556,test,0.7560975609756098,0.06358646513593161,0.6693548387096775,0.08301033633603491,0.6693548387096775,0.08329853505150835 +flat_mae,reg,logistic,adni_ad_vs_cn,83,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,83,21.54434690031882,test,0.7317073170731707,0.06351097747137437,0.6479313036690086,0.07913038193372654,0.6532258064516129,0.08292518066262645 +flat_mae,reg,logistic,adni_ad_vs_cn,84,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,84,166.81005372000556,test,0.7804878048780488,0.05483030985904191,0.6660633484162897,0.0902142186547496,0.6516129032258065,0.08328298136108757 +flat_mae,reg,logistic,adni_ad_vs_cn,85,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,85,21.54434690031882,test,0.8292682926829268,0.05048165392011647,0.7402714932126697,0.08745252243279043,0.717741935483871,0.08344078629721811 +flat_mae,reg,logistic,adni_ad_vs_cn,86,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,86,1291.5496650148827,test,0.6097560975609756,0.06851634107748343,0.5030303030303029,0.07481504565310759,0.5048387096774194,0.08021132105241745 +flat_mae,reg,logistic,adni_ad_vs_cn,87,0.046415888336127774,train,0.907859078590786,0.012782138079552238,0.8548454276194002,0.02274282412910148,0.81851425753965,0.025430776500154444 +flat_mae,reg,logistic,adni_ad_vs_cn,87,0.046415888336127774,test,0.8292682926829268,0.04671928140720097,0.7144278606965174,0.09910780874344727,0.6838709677419355,0.08430175372779433 +flat_mae,reg,logistic,adni_ad_vs_cn,88,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,88,2.782559402207126,test,0.7317073170731707,0.06125485327200916,0.6479313036690086,0.07993610002148978,0.6532258064516129,0.08593059773719361 +flat_mae,reg,logistic,adni_ad_vs_cn,89,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,89,2.782559402207126,test,0.8048780487804879,0.06160052457729155,0.7515151515151515,0.07495851243586206,0.7693548387096774,0.08066976263469468 +flat_mae,reg,logistic,adni_ad_vs_cn,90,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,90,166.81005372000556,test,0.7073170731707317,0.06670303192193607,0.603225806451613,0.08847945773979611,0.603225806451613,0.08773534723842394 +flat_mae,reg,logistic,adni_ad_vs_cn,91,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,91,2.782559402207126,test,0.7317073170731707,0.06135949402852056,0.6232247284878863,0.08261580552971312,0.6193548387096774,0.08075232744074175 +flat_mae,reg,logistic,adni_ad_vs_cn,92,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,92,21.54434690031882,test,0.6585365853658537,0.06914828147147303,0.5370967741935484,0.08847396521713383,0.5370967741935484,0.0875774532181361 +flat_mae,reg,logistic,adni_ad_vs_cn,93,0.046415888336127774,train,0.924119241192412,0.01213931827394878,0.8828571428571428,0.020512909281761492,0.8493508094338073,0.02370005916281869 +flat_mae,reg,logistic,adni_ad_vs_cn,93,0.046415888336127774,test,0.7317073170731707,0.06862877230334495,0.6479313036690086,0.08529350536364876,0.6532258064516129,0.08989633635650889 +flat_mae,reg,logistic,adni_ad_vs_cn,94,0.046415888336127774,train,0.9214092140921409,0.011979501836242357,0.8780665671539749,0.020658386205241637,0.8435368559454351,0.023667072950013735 +flat_mae,reg,logistic,adni_ad_vs_cn,94,0.046415888336127774,test,0.7317073170731707,0.04362797676870197,0.4972129319955407,0.07627781221575902,0.5177419354838709,0.05503232084101854 +flat_mae,reg,logistic,adni_ad_vs_cn,95,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,95,166.81005372000556,test,0.7317073170731707,0.059721722317740165,0.5918552036199095,0.09019059005179225,0.5854838709677419,0.08060899731078766 +flat_mae,reg,logistic,adni_ad_vs_cn,96,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,96,21.54434690031882,test,0.7317073170731707,0.05803711709021023,0.5918552036199095,0.0865822025837848,0.5854838709677419,0.07840331466373182 +flat_mae,reg,logistic,adni_ad_vs_cn,97,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,97,166.81005372000556,test,0.7560975609756098,0.05908273673327025,0.6440972222222222,0.08791019771882562,0.635483870967742,0.0844447270412904 +flat_mae,reg,logistic,adni_ad_vs_cn,98,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,98,2.782559402207126,test,0.7073170731707317,0.06181663891797104,0.5729166666666666,0.08532454535139765,0.5693548387096774,0.07922126779843966 +flat_mae,reg,logistic,adni_ad_vs_cn,99,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,99,21.54434690031882,test,0.7073170731707317,0.05934875598028067,0.5729166666666666,0.08340847340715268,0.5693548387096774,0.07742467582521038 +flat_mae,reg,logistic,adni_ad_vs_cn,100,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,100,2.782559402207126,test,0.7317073170731707,0.06114082981765291,0.6232247284878863,0.08670443589806903,0.6193548387096774,0.08472381745729438 diff --git a/decoders/crossreg_reg4/eval_v2/adni_ad_vs_cn__reg__logistic/log.txt b/decoders/crossreg_reg4/eval_v2/adni_ad_vs_cn__reg__logistic/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..c9ef2d18b02377f254aa4600b440132987130352 --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/adni_ad_vs_cn__reg__logistic/log.txt @@ -0,0 +1,240 @@ +fMRI foundation model logistic probe eval +version: 0.1.dev66+g7ddd3aa04 +sha: aef99c83a386cf95c3d8ca503ecc968d8d5694af, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-03-07 21:19:26 +config: +output_root: experiments/decoders/output +name_prefix: eval_logistic +remote_root: null +notes: decoder ablations crossreg_reg4; eval v2 (adni_ad_vs_cn reg logistic) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: decoders/crossreg_reg4/eval_v2/adni_ad_vs_cn__reg__logistic +model: flat_mae +representation: reg +dataset: adni_ad_vs_cn +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg4/eval_v2/adni_ad_vs_cn__reg__logistic +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=False, reg_tokens=4, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: adni_ad_vs_cn (flat) +train (n=328): +ADNIDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'bold', 'mean', 'std'], + num_rows: 525 +}), + labels=[0 1], + counts=[251 77] +) + +validation (n=41): +ADNIDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'bold', 'mean', 'std'], + num_rows: 66 +}), + labels=[0 1], + counts=[31 10] +) + +test (n=41): +ADNIDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'bold', 'mean', 'std'], + num_rows: 66 +}), + labels=[0 1], + counts=[32 9] +) + +extracting features for all splits +extract (train) [ 0/164] eta: 0:12:27 time: 4.5608 data: 3.7108 max mem: 2698 +extract (train) [ 20/164] eta: 0:00:57 time: 0.1878 data: 0.0668 max mem: 2852 +extract (train) [ 40/164] eta: 0:00:34 time: 0.1627 data: 0.0509 max mem: 2852 +extract (train) [ 60/164] eta: 0:00:25 time: 0.1627 data: 0.0532 max mem: 2852 +extract (train) [ 80/164] eta: 0:00:18 time: 0.1618 data: 0.0522 max mem: 2852 +extract (train) [100/164] eta: 0:00:13 time: 0.1761 data: 0.0607 max mem: 2852 +extract (train) [120/164] eta: 0:00:09 time: 0.1717 data: 0.0566 max mem: 2852 +extract (train) [140/164] eta: 0:00:04 time: 0.1746 data: 0.0569 max mem: 2852 +extract (train) [160/164] eta: 0:00:00 time: 0.1652 data: 0.0530 max mem: 2852 +extract (train) [163/164] eta: 0:00:00 time: 0.1640 data: 0.0527 max mem: 2852 +extract (train) Total time: 0:00:33 (0.2024 s / it) +extract (validation) [ 0/21] eta: 0:01:24 time: 4.0446 data: 3.9344 max mem: 2852 +extract (validation) [20/21] eta: 0:00:00 time: 0.1479 data: 0.0418 max mem: 2852 +extract (validation) Total time: 0:00:07 (0.3533 s / it) +extract (test) [ 0/21] eta: 0:01:21 time: 3.9047 data: 3.7845 max mem: 2852 +extract (test) [20/21] eta: 0:00:00 time: 0.1374 data: 0.0368 max mem: 2852 +extract (test) Total time: 0:00:06 (0.3303 s / it) +feature extraction time: 0:00:47 +train features: (328, 768) +validation features: (41, 768) +test features: (41, 768) +evaluating fixed splits +eval results (fixed splits): + +| model | repr | clf | dataset | trial | C | split | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:--------------|:--------|-------:|:--------|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | reg | logistic | adni_ad_vs_cn | | 21.544 | train | 1 | 0 | 1 | 0 | 1 | 0 | +| flat_mae | reg | logistic | adni_ad_vs_cn | | 21.544 | test | 0.73171 | 0.061503 | 0.59186 | 0.085737 | 0.58854 | 0.083489 | + + +evaluating random splits (n=100) +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 1, "C": 1291.5496650148827, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.05965197498965619, "f1": 0.6917293233082706, "f1_std": 0.08421119542537488, "bacc": 0.685483870967742, "bacc_std": 0.08393276104532095} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 2, "C": 166.81005372000556, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.060952795732066516, "f1": 0.6917293233082706, "f1_std": 0.08639343869179594, "bacc": 0.685483870967742, "bacc_std": 0.08576363132386826} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 3, "C": 21.54434690031882, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.06567274155042077, "f1": 0.5547201336675021, "f1_std": 0.087446297612882, "bacc": 0.5532258064516129, "bacc_std": 0.08359551859045979} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 4, "C": 2.782559402207126, "split": "test", "acc": 0.8780487804878049, "acc_std": 0.04999700169475366, "f1": 0.8287385129490392, "f1_std": 0.07348973685417326, "bacc": 0.8177419354838709, "bacc_std": 0.07690595220053496} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 5, "C": 21.54434690031882, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.04297104153345551, "f1": 0.569327731092437, "f1_std": 0.08611760164225671, "bacc": 0.567741935483871, "bacc_std": 0.06503548219094353} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 6, "C": 1291.5496650148827, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.06638268088317434, "f1": 0.5839188134270101, "f1_std": 0.08277286962308099, "bacc": 0.5870967741935484, "bacc_std": 0.08582816236372913} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 7, "C": 1291.5496650148827, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.06694010747894036, "f1": 0.6479313036690086, "f1_std": 0.08462423368279873, "bacc": 0.6532258064516129, "bacc_std": 0.087403401174901} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 8, "C": 21.54434690031882, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.05315549121475575, "f1": 0.6660633484162897, "f1_std": 0.08475383202565291, "bacc": 0.6516129032258065, "bacc_std": 0.07784234253517273} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 9, "C": 166.81005372000556, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.06612365608547857, "f1": 0.7280766396462786, "f1_std": 0.07837400086085841, "bacc": 0.7532258064516129, "bacc_std": 0.08378285793692576} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 10, "C": 166.81005372000556, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.06383834059499562, "f1": 0.6693548387096775, "f1_std": 0.08516590831766294, "bacc": 0.6693548387096775, "bacc_std": 0.0883888507007518} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 11, "C": 0.3593813663804626, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.047657812611521855, "f1": 0.6893939393939394, "f1_std": 0.08683037374702807, "bacc": 0.667741935483871, "bacc_std": 0.07779467064289844} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 12, "C": 1291.5496650148827, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.06135900927358825, "f1": 0.6232247284878863, "f1_std": 0.0847216698151674, "bacc": 0.6193548387096774, "bacc_std": 0.08315368943466846} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 13, "C": 166.81005372000556, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.05510293218186004, "f1": 0.7152777777777778, "f1_std": 0.0854177483880803, "bacc": 0.7016129032258065, "bacc_std": 0.08431675443257824} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 14, "C": 2.782559402207126, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.056206871231079474, "f1": 0.7152777777777778, "f1_std": 0.08764975410828699, "bacc": 0.7016129032258065, "bacc_std": 0.08555144371272728} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 15, "C": 0.3593813663804626, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.06187635191920471, "f1": 0.7119437939110069, "f1_std": 0.08057680751526211, "bacc": 0.7193548387096774, "bacc_std": 0.0849466671759876} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 16, "C": 0.046415888336127774, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.04553796358320358, "f1": 0.569327731092437, "f1_std": 0.0882871089406134, "bacc": 0.567741935483871, "bacc_std": 0.0665605567188106} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 17, "C": 0.3593813663804626, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.05758403837273237, "f1": 0.7152777777777778, "f1_std": 0.0890620732247795, "bacc": 0.7016129032258065, "bacc_std": 0.08537799286076218} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 18, "C": 0.3593813663804626, "split": "test", "acc": 0.8536585365853658, "acc_std": 0.04516901961671339, "f1": 0.7670454545454546, "f1_std": 0.0846177698850047, "bacc": 0.7338709677419355, "bacc_std": 0.07993524538484041} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 19, "C": 166.81005372000556, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.05950747682215606, "f1": 0.5918552036199095, "f1_std": 0.0884153461176964, "bacc": 0.5854838709677419, "bacc_std": 0.07815662887328642} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 20, "C": 166.81005372000556, "split": "test", "acc": 0.8536585365853658, "acc_std": 0.05659327110465348, "f1": 0.8136363636363637, "f1_std": 0.06858781424200065, "bacc": 0.8354838709677419, "bacc_std": 0.07111708121383084} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 21, "C": 0.3593813663804626, "split": "test", "acc": 0.8292682926829268, "acc_std": 0.04505614185763996, "f1": 0.7144278606965174, "f1_std": 0.0975771118188164, "bacc": 0.6838709677419355, "bacc_std": 0.08241832907637679} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 22, "C": 21.54434690031882, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.06592906252139064, "f1": 0.5547201336675021, "f1_std": 0.08585452757079653, "bacc": 0.5532258064516129, "bacc_std": 0.08427651307195332} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 23, "C": 166.81005372000556, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.059625222535461715, "f1": 0.6660633484162897, "f1_std": 0.09619101759136134, "bacc": 0.6516129032258065, "bacc_std": 0.08917984868248081} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 24, "C": 0.3593813663804626, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.05419973197226676, "f1": 0.6660633484162897, "f1_std": 0.09112898780124525, "bacc": 0.6516129032258065, "bacc_std": 0.08338953256565988} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 25, "C": 166.81005372000556, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.05691516590029985, "f1": 0.5918552036199095, "f1_std": 0.08838742606970534, "bacc": 0.5854838709677419, "bacc_std": 0.07953571380877775} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 26, "C": 0.046415888336127774, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.05156489820554526, "f1": 0.6893939393939394, "f1_std": 0.0923113828438389, "bacc": 0.667741935483871, "bacc_std": 0.08182558568335797} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 27, "C": 0.046415888336127774, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.049591214128501086, "f1": 0.6893939393939394, "f1_std": 0.08944368214047783, "bacc": 0.667741935483871, "bacc_std": 0.07884346449681522} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 28, "C": 21.54434690031882, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.04781980851961939, "f1": 0.6328358208955224, "f1_std": 0.08942107078387601, "bacc": 0.6177419354838709, "bacc_std": 0.07419629525069428} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 29, "C": 2.782559402207126, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.072968484718037, "f1": 0.5839188134270101, "f1_std": 0.08879885560928677, "bacc": 0.5870967741935484, "bacc_std": 0.09131133099201774} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 30, "C": 2.782559402207126, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.061711057439902794, "f1": 0.5729166666666666, "f1_std": 0.08717477286339652, "bacc": 0.5693548387096774, "bacc_std": 0.08016214700652118} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 31, "C": 21.54434690031882, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.059906014034895344, "f1": 0.6440972222222222, "f1_std": 0.09155689710746522, "bacc": 0.635483870967742, "bacc_std": 0.08651491778276979} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 32, "C": 1291.5496650148827, "split": "test", "acc": 0.6341463414634146, "acc_std": 0.07794651837223623, "f1": 0.5858585858585859, "f1_std": 0.08061991945745695, "bacc": 0.6225806451612903, "bacc_std": 0.09214856455774029} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 33, "C": 0.3593813663804626, "split": "test", "acc": 0.6585365853658537, "acc_std": 0.07007493227434483, "f1": 0.5876436781609196, "f1_std": 0.08178028971133995, "bacc": 0.6048387096774194, "bacc_std": 0.09067111756713982} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 34, "C": 0.046415888336127774, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.06018055324352879, "f1": 0.6440972222222222, "f1_std": 0.0899098719239102, "bacc": 0.635483870967742, "bacc_std": 0.08489291356876348} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 35, "C": 0.3593813663804626, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.059202934956267585, "f1": 0.6440972222222222, "f1_std": 0.08909329156291687, "bacc": 0.635483870967742, "bacc_std": 0.08434189476955956} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 36, "C": 166.81005372000556, "split": "test", "acc": 0.5853658536585366, "acc_std": 0.07539519517241305, "f1": 0.5108771929824562, "f1_std": 0.07668583182122167, "bacc": 0.5225806451612903, "bacc_std": 0.08555055530507844} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 37, "C": 166.81005372000556, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.06205850130941747, "f1": 0.6693548387096775, "f1_std": 0.08402566855862001, "bacc": 0.6693548387096775, "bacc_std": 0.0869573466434881} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 38, "C": 21.54434690031882, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.0706569663986105, "f1": 0.6676492262343405, "f1_std": 0.08392506774076239, "bacc": 0.6870967741935483, "bacc_std": 0.0901794286677328} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 39, "C": 21.54434690031882, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.06415411248486724, "f1": 0.5547201336675021, "f1_std": 0.08445878953795607, "bacc": 0.5532258064516129, "bacc_std": 0.08042621918609777} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 40, "C": 21.54434690031882, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.06689544524766987, "f1": 0.6479313036690086, "f1_std": 0.08348594721613219, "bacc": 0.6532258064516129, "bacc_std": 0.0866521325829056} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 41, "C": 2.782559402207126, "split": "test", "acc": 0.6341463414634146, "acc_std": 0.07105311332898664, "f1": 0.5684210526315789, "f1_std": 0.07619345303127505, "bacc": 0.5887096774193548, "bacc_std": 0.08778585066810832} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 42, "C": 1291.5496650148827, "split": "test", "acc": 0.8292682926829268, "acc_std": 0.051537133652849725, "f1": 0.7402714932126697, "f1_std": 0.08541743756073045, "bacc": 0.717741935483871, "bacc_std": 0.08257709821011713} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 43, "C": 2.782559402207126, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.05821219057439226, "f1": 0.7152777777777778, "f1_std": 0.08983117682872478, "bacc": 0.7016129032258065, "bacc_std": 0.08668411465551701} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 44, "C": 166.81005372000556, "split": "test", "acc": 0.8292682926829268, "acc_std": 0.045681982723045474, "f1": 0.7144278606965174, "f1_std": 0.09295168511434643, "bacc": 0.6838709677419355, "bacc_std": 0.08154485343507693} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 45, "C": 166.81005372000556, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.06406367668062286, "f1": 0.7280766396462786, "f1_std": 0.07657020332749781, "bacc": 0.7532258064516129, "bacc_std": 0.08305472187794433} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 46, "C": 21.54434690031882, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.054857101693279356, "f1": 0.7354838709677419, "f1_std": 0.07788234853373478, "bacc": 0.7354838709677419, "bacc_std": 0.08207292733066335} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 47, "C": 21.54434690031882, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.062241379259203776, "f1": 0.5729166666666666, "f1_std": 0.08683763851162027, "bacc": 0.5693548387096774, "bacc_std": 0.08206348111286849} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 48, "C": 21.54434690031882, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.07145652176863818, "f1": 0.5839188134270101, "f1_std": 0.0870668817515905, "bacc": 0.5870967741935484, "bacc_std": 0.09073478154889847} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 49, "C": 2.782559402207126, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.05199862717265304, "f1": 0.5512437810945273, "f1_std": 0.09039742888627253, "bacc": 0.5516129032258065, "bacc_std": 0.07205512075237205} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 50, "C": 21.54434690031882, "split": "test", "acc": 0.8292682926829268, "acc_std": 0.05878200585024896, "f1": 0.7759562841530054, "f1_std": 0.0766716918114474, "bacc": 0.7854838709677419, "bacc_std": 0.08059190008953519} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 51, "C": 21.54434690031882, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.07209569620348251, "f1": 0.6259649122807017, "f1_std": 0.07865515971011627, "bacc": 0.6548387096774193, "bacc_std": 0.08860048153245872} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 52, "C": 166.81005372000556, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.05413260647593688, "f1": 0.6117424242424243, "f1_std": 0.09191297635254492, "bacc": 0.6016129032258064, "bacc_std": 0.07879840609637905} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 53, "C": 166.81005372000556, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.05852184773826586, "f1": 0.5729166666666666, "f1_std": 0.08533728565060335, "bacc": 0.5693548387096774, "bacc_std": 0.07863301157837932} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 54, "C": 0.046415888336127774, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.059563732182869866, "f1": 0.5729166666666666, "f1_std": 0.08375471949209458, "bacc": 0.5693548387096774, "bacc_std": 0.07763501655854649} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 55, "C": 0.3593813663804626, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.059685872125239035, "f1": 0.6440972222222222, "f1_std": 0.09056736965829243, "bacc": 0.635483870967742, "bacc_std": 0.08535591220401186} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 56, "C": 166.81005372000556, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.05257441399144382, "f1": 0.5512437810945273, "f1_std": 0.0882881544227209, "bacc": 0.5516129032258065, "bacc_std": 0.07113187025279717} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 57, "C": 2.782559402207126, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.06456856313739374, "f1": 0.6479313036690086, "f1_std": 0.08245623609374042, "bacc": 0.6532258064516129, "bacc_std": 0.08598236539668559} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 58, "C": 21.54434690031882, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.05875720619796659, "f1": 0.7152777777777778, "f1_std": 0.08769526628535422, "bacc": 0.7016129032258065, "bacc_std": 0.08484627367237413} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 59, "C": 2.782559402207126, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.05655749944618306, "f1": 0.6660633484162897, "f1_std": 0.09321834066404755, "bacc": 0.6516129032258065, "bacc_std": 0.08649535701180368} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 60, "C": 2.782559402207126, "split": "test", "acc": 0.8780487804878049, "acc_std": 0.04847033105175277, "f1": 0.8287385129490392, "f1_std": 0.07333204559007016, "bacc": 0.8177419354838709, "bacc_std": 0.07820235258642817} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 61, "C": 0.046415888336127774, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.04893874329081201, "f1": 0.5512437810945273, "f1_std": 0.08810481853024506, "bacc": 0.5516129032258065, "bacc_std": 0.06974457777513789} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 62, "C": 2.782559402207126, "split": "test", "acc": 0.8536585365853658, "acc_std": 0.05534459675744239, "f1": 0.8016129032258064, "f1_std": 0.07580692980956008, "bacc": 0.8016129032258064, "bacc_std": 0.08022866714746085} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 63, "C": 21.54434690031882, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.060204272538465095, "f1": 0.7119437939110069, "f1_std": 0.07803112756648595, "bacc": 0.7193548387096774, "bacc_std": 0.08221201114359575} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 64, "C": 21.54434690031882, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.06578200256899232, "f1": 0.5729166666666666, "f1_std": 0.09125109978236295, "bacc": 0.5693548387096774, "bacc_std": 0.08493307373177764} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 65, "C": 0.046415888336127774, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.05620416170516529, "f1": 0.6660633484162897, "f1_std": 0.09020495655759604, "bacc": 0.6516129032258065, "bacc_std": 0.0828187233451739} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 66, "C": 166.81005372000556, "split": "test", "acc": 0.8292682926829268, "acc_std": 0.0480918217522762, "f1": 0.7402714932126697, "f1_std": 0.08265546278534666, "bacc": 0.717741935483871, "bacc_std": 0.07863693756786329} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 67, "C": 0.046415888336127774, "split": "test", "acc": 0.8292682926829268, "acc_std": 0.04484672820105256, "f1": 0.7144278606965174, "f1_std": 0.09250793822282488, "bacc": 0.6838709677419355, "bacc_std": 0.08073356567395498} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 68, "C": 2.782559402207126, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.0628885495214838, "f1": 0.5547201336675021, "f1_std": 0.0833917942345513, "bacc": 0.5532258064516129, "bacc_std": 0.08051352320793594} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 69, "C": 166.81005372000556, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.06387962728192434, "f1": 0.7119437939110069, "f1_std": 0.08194811343093335, "bacc": 0.7193548387096774, "bacc_std": 0.08543176567816362} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 70, "C": 21.54434690031882, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.054270983764463314, "f1": 0.7152777777777778, "f1_std": 0.08579718952741154, "bacc": 0.7016129032258065, "bacc_std": 0.08392429173353842} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 71, "C": 166.81005372000556, "split": "test", "acc": 0.6585365853658537, "acc_std": 0.06914492621255675, "f1": 0.5651515151515152, "f1_std": 0.08211122033999584, "bacc": 0.5709677419354839, "bacc_std": 0.08671599943350904} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 72, "C": 2.782559402207126, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.0389172614930417, "f1": 0.4057971014492754, "f1_std": 0.013931014571946607, "bacc": 0.45161290322580644, "bacc_std": 0.02573560840668887} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 73, "C": 0.046415888336127774, "split": "test", "acc": 0.8536585365853658, "acc_std": 0.050436854225144684, "f1": 0.7864583333333333, "f1_std": 0.07938752523206534, "bacc": 0.7677419354838709, "bacc_std": 0.08293850234780074} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 74, "C": 0.046415888336127774, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.033799070348968036, "f1": 0.4142857142857143, "f1_std": 0.011755025975526823, "bacc": 0.46774193548387094, "bacc_std": 0.022350998133995006} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 75, "C": 166.81005372000556, "split": "test", "acc": 0.6585365853658537, "acc_std": 0.06499851277299176, "f1": 0.5370967741935484, "f1_std": 0.07952403284750914, "bacc": 0.5370967741935484, "bacc_std": 0.07833145536158176} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 76, "C": 0.3593813663804626, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.05996983179698337, "f1": 0.5729166666666666, "f1_std": 0.08345813132615776, "bacc": 0.5693548387096774, "bacc_std": 0.0783107529465472} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 77, "C": 10000.0, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.06449132863698401, "f1": 0.6893939393939394, "f1_std": 0.07994717234162295, "bacc": 0.7032258064516128, "bacc_std": 0.08617110244729557} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 78, "C": 0.3593813663804626, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.05647632471067588, "f1": 0.7152777777777778, "f1_std": 0.08684678224415845, "bacc": 0.7016129032258065, "bacc_std": 0.0841359872446731} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 79, "C": 21.54434690031882, "split": "test", "acc": 0.9024390243902439, "acc_std": 0.04799613309825579, "f1": 0.8757575757575757, "f1_std": 0.05817015566432631, "bacc": 0.9016129032258065, "bacc_std": 0.05613435820115493} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 80, "C": 21.54434690031882, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.06847326299651309, "f1": 0.5839188134270101, "f1_std": 0.08383691342986946, "bacc": 0.5870967741935484, "bacc_std": 0.08590296754773238} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 81, "C": 0.046415888336127774, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.03243440275164686, "f1": 0.6095238095238095, "f1_std": 0.09923652315029885, "bacc": 0.6, "bacc_std": 0.06649052564087607} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 82, "C": 166.81005372000556, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.06358646513593161, "f1": 0.6693548387096775, "f1_std": 0.08301033633603491, "bacc": 0.6693548387096775, "bacc_std": 0.08329853505150835} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 83, "C": 21.54434690031882, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.06351097747137437, "f1": 0.6479313036690086, "f1_std": 0.07913038193372654, "bacc": 0.6532258064516129, "bacc_std": 0.08292518066262645} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 84, "C": 166.81005372000556, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.05483030985904191, "f1": 0.6660633484162897, "f1_std": 0.0902142186547496, "bacc": 0.6516129032258065, "bacc_std": 0.08328298136108757} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 85, "C": 21.54434690031882, "split": "test", "acc": 0.8292682926829268, "acc_std": 0.05048165392011647, "f1": 0.7402714932126697, "f1_std": 0.08745252243279043, "bacc": 0.717741935483871, "bacc_std": 0.08344078629721811} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 86, "C": 1291.5496650148827, "split": "test", "acc": 0.6097560975609756, "acc_std": 0.06851634107748343, "f1": 0.5030303030303029, "f1_std": 0.07481504565310759, "bacc": 0.5048387096774194, "bacc_std": 0.08021132105241745} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 87, "C": 0.046415888336127774, "split": "test", "acc": 0.8292682926829268, "acc_std": 0.04671928140720097, "f1": 0.7144278606965174, "f1_std": 0.09910780874344727, "bacc": 0.6838709677419355, "bacc_std": 0.08430175372779433} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 88, "C": 2.782559402207126, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.06125485327200916, "f1": 0.6479313036690086, "f1_std": 0.07993610002148978, "bacc": 0.6532258064516129, "bacc_std": 0.08593059773719361} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 89, "C": 2.782559402207126, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.06160052457729155, "f1": 0.7515151515151515, "f1_std": 0.07495851243586206, "bacc": 0.7693548387096774, "bacc_std": 0.08066976263469468} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 90, "C": 166.81005372000556, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.06670303192193607, "f1": 0.603225806451613, "f1_std": 0.08847945773979611, "bacc": 0.603225806451613, "bacc_std": 0.08773534723842394} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 91, "C": 2.782559402207126, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.06135949402852056, "f1": 0.6232247284878863, "f1_std": 0.08261580552971312, "bacc": 0.6193548387096774, "bacc_std": 0.08075232744074175} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 92, "C": 21.54434690031882, "split": "test", "acc": 0.6585365853658537, "acc_std": 0.06914828147147303, "f1": 0.5370967741935484, "f1_std": 0.08847396521713383, "bacc": 0.5370967741935484, "bacc_std": 0.0875774532181361} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 93, "C": 0.046415888336127774, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.06862877230334495, "f1": 0.6479313036690086, "f1_std": 0.08529350536364876, "bacc": 0.6532258064516129, "bacc_std": 0.08989633635650889} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 94, "C": 0.046415888336127774, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.04362797676870197, "f1": 0.4972129319955407, "f1_std": 0.07627781221575902, "bacc": 0.5177419354838709, "bacc_std": 0.05503232084101854} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 95, "C": 166.81005372000556, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.059721722317740165, "f1": 0.5918552036199095, "f1_std": 0.09019059005179225, "bacc": 0.5854838709677419, "bacc_std": 0.08060899731078766} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 96, "C": 21.54434690031882, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.05803711709021023, "f1": 0.5918552036199095, "f1_std": 0.0865822025837848, "bacc": 0.5854838709677419, "bacc_std": 0.07840331466373182} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 97, "C": 166.81005372000556, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.05908273673327025, "f1": 0.6440972222222222, "f1_std": 0.08791019771882562, "bacc": 0.635483870967742, "bacc_std": 0.0844447270412904} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 98, "C": 2.782559402207126, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.06181663891797104, "f1": 0.5729166666666666, "f1_std": 0.08532454535139765, "bacc": 0.5693548387096774, "bacc_std": 0.07922126779843966} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 99, "C": 21.54434690031882, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.05934875598028067, "f1": 0.5729166666666666, "f1_std": 0.08340847340715268, "bacc": 0.5693548387096774, "bacc_std": 0.07742467582521038} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 100, "C": 2.782559402207126, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.06114082981765291, "f1": 0.6232247284878863, "f1_std": 0.08670443589806903, "bacc": 0.6193548387096774, "bacc_std": 0.08472381745729438} +eval results (random splits): + +| model | repr | clf | dataset | split | n_trials | C | C_std | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:--------------|:--------|-----------:|-------:|--------:|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | reg | logistic | adni_ad_vs_cn | train | 100 | 236.38 | 1038.5 | 0.98778 | 0.029245 | 0.98088 | 0.045972 | 0.9754 | 0.058683 | +| flat_mae | reg | logistic | adni_ad_vs_cn | test | 100 | 236.38 | 1038.5 | 0.75341 | 0.061712 | 0.64527 | 0.085747 | 0.64319 | 0.08146 | + + +done! total time: 0:04:45 diff --git a/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__attn/config.yaml b/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__attn/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..d3e048e6ff5e733c27434c8545ed180b0d644ad4 --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__attn/config.yaml @@ -0,0 +1,96 @@ +output_root: experiments/decoders/output +name_prefix: eval_probe +remote_root: null +notes: decoder ablations crossreg_reg4; eval v2 (hcpya_task21 patch attn) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +dataset_kwargs: {} +classifier_kwargs: + embed_dim: null + dropout: 0.0 + xavier_init: false + norm: false +lr_scale_grid: +- 0.02 +- 0.023 +- 0.028 +- 0.033 +- 0.038 +- 0.045 +- 0.053 +- 0.062 +- 0.074 +- 0.087 +- 0.1 +- 0.12 +- 0.14 +- 0.17 +- 0.2 +- 0.23 +- 0.27 +- 0.32 +- 0.38 +- 0.44 +- 0.52 +- 0.61 +- 0.72 +- 0.85 +- 1 +- 1.2 +- 1.4 +- 1.6 +- 1.9 +- 2.3 +- 2.7 +- 3.1 +- 3.7 +- 4.3 +- 5.1 +- 6 +- 7.1 +- 8.3 +- 9.8 +- 12 +- 14 +- 16 +- 19 +- 22 +- 26 +- 31 +- 36 +- 43 +- 50 +wd_scale_grid: +- 1.0 +num_workers: 8 +prefetch_factor: null +balanced_sampling: false +epochs: 20 +steps_per_epoch: 200 +batch_size: 64 +accum_iter: 2 +lr: 0.0003 +warmup_epochs: 5 +no_decay: false +weight_decay: 0.05 +clip_grad: 1.0 +metrics: +- acc +- f1 +cv_metric: acc +early_stopping: true +amp: true +device: cuda +seed: 4466 +debug: false +wandb: false +wandb_entity: null +wandb_project: fMRI-fm-eval +name: decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__attn +model: flat_mae +representation: patch +classifier: attn +dataset: hcpya_task21 +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__attn +remote_dir: null diff --git a/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__attn/eval_log.json b/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__attn/eval_log.json new file mode 100644 index 0000000000000000000000000000000000000000..5b7a8efe680141601b367995e554ab62c2f58d73 --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__attn/eval_log.json @@ -0,0 +1 @@ +{"eval/epoch": 17, "eval/id_best": 43, "eval/lr_best": 0.006599999999999999, "eval/wd_best": 0.05, "eval/train/loss": 0.0001459822669858113, "eval/train/acc": 1.0, "eval/train/acc_std": 0.0, "eval/train/f1": 1.0, "eval/train/f1_std": 0.0, "eval/validation/loss": 0.0525173656642437, "eval/validation/acc": 0.9880952380952381, "eval/validation/acc_std": 0.0016299318625606525, "eval/validation/f1": 0.9857562615366776, "eval/validation/f1_std": 0.0022326693782531346, "eval/test/loss": 0.07207445800304413, "eval/test/acc": 0.9861111111111112, "eval/test/acc_std": 0.0015754859836431907, "eval/test/f1": 0.983203683100717, "eval/test/f1_std": 0.002095390680912686} diff --git a/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__attn/eval_log_best.json b/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__attn/eval_log_best.json new file mode 100644 index 0000000000000000000000000000000000000000..59332512bb2d14eb7e3d7d625ff18a88ab3fdb52 --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__attn/eval_log_best.json @@ -0,0 +1 @@ +{"eval/best/epoch": 17, "eval/best/id_best": 43, "eval/best/lr_best": 0.006599999999999999, "eval/best/wd_best": 0.05, "eval/best/train/loss": 0.0001459822669858113, "eval/best/train/acc": 1.0, "eval/best/train/acc_std": 0.0, "eval/best/train/f1": 1.0, "eval/best/train/f1_std": 0.0, "eval/best/validation/loss": 0.0525173656642437, "eval/best/validation/acc": 0.9880952380952381, "eval/best/validation/acc_std": 0.0016299318625606525, "eval/best/validation/f1": 0.9857562615366776, "eval/best/validation/f1_std": 0.0022326693782531346, "eval/best/test/loss": 0.07207445800304413, "eval/best/test/acc": 0.9861111111111112, "eval/best/test/acc_std": 0.0015754859836431907, "eval/best/test/f1": 0.983203683100717, "eval/best/test/f1_std": 0.002095390680912686} diff --git a/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__attn/eval_log_last.json b/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__attn/eval_log_last.json new file mode 100644 index 0000000000000000000000000000000000000000..3c2ba40b5ee3ec4a886112ce81806dc8a0df95c1 --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__attn/eval_log_last.json @@ -0,0 +1 @@ +{"eval/last/epoch": 19, "eval/last/id_best": 43, "eval/last/lr_best": 0.006599999999999999, "eval/last/wd_best": 0.05, "eval/last/train/loss": 0.00014662370085716248, "eval/last/train/acc": 1.0, "eval/last/train/acc_std": 0.0, "eval/last/train/f1": 1.0, "eval/last/train/f1_std": 0.0, "eval/last/validation/loss": 0.05252598226070404, "eval/last/validation/acc": 0.9878472222222222, "eval/last/validation/acc_std": 0.0016466534949246495, "eval/last/validation/f1": 0.9855294027870821, "eval/last/validation/f1_std": 0.002239532859910713, "eval/last/test/loss": 0.07176008820533752, "eval/last/test/acc": 0.9861111111111112, "eval/last/test/acc_std": 0.0015754859836431907, "eval/last/test/f1": 0.9832299793100557, "eval/last/test/f1_std": 0.0020954409398735822} diff --git a/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__attn/eval_table.csv b/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__attn/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..cf6434931df685095a016eda2d0b772bfdbffd54 --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__attn/eval_table.csv @@ -0,0 +1,4 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,patch,attn,hcpya_task21,best,17,0.006599999999999999,0.05,43,"[22, 1.0]",train,0.0001459822669858113,1.0,0.0,1.0,0.0 +flat_mae,patch,attn,hcpya_task21,best,17,0.006599999999999999,0.05,43,"[22, 1.0]",validation,0.0525173656642437,0.9880952380952381,0.0016299318625606525,0.9857562615366776,0.0022326693782531346 +flat_mae,patch,attn,hcpya_task21,best,17,0.006599999999999999,0.05,43,"[22, 1.0]",test,0.07207445800304413,0.9861111111111112,0.0015754859836431907,0.983203683100717,0.002095390680912686 diff --git a/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__attn/eval_table_best.csv b/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__attn/eval_table_best.csv new file mode 100644 index 0000000000000000000000000000000000000000..cf6434931df685095a016eda2d0b772bfdbffd54 --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__attn/eval_table_best.csv @@ -0,0 +1,4 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,patch,attn,hcpya_task21,best,17,0.006599999999999999,0.05,43,"[22, 1.0]",train,0.0001459822669858113,1.0,0.0,1.0,0.0 +flat_mae,patch,attn,hcpya_task21,best,17,0.006599999999999999,0.05,43,"[22, 1.0]",validation,0.0525173656642437,0.9880952380952381,0.0016299318625606525,0.9857562615366776,0.0022326693782531346 +flat_mae,patch,attn,hcpya_task21,best,17,0.006599999999999999,0.05,43,"[22, 1.0]",test,0.07207445800304413,0.9861111111111112,0.0015754859836431907,0.983203683100717,0.002095390680912686 diff --git a/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__attn/eval_table_last.csv b/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__attn/eval_table_last.csv new file mode 100644 index 0000000000000000000000000000000000000000..d50ad31e8663236f0f310a9103241e02d4cc4c70 --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__attn/eval_table_last.csv @@ -0,0 +1,4 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,patch,attn,hcpya_task21,last,19,0.006599999999999999,0.05,43,"[22, 1.0]",train,0.00014662370085716248,1.0,0.0,1.0,0.0 +flat_mae,patch,attn,hcpya_task21,last,19,0.006599999999999999,0.05,43,"[22, 1.0]",validation,0.05252598226070404,0.9878472222222222,0.0016466534949246495,0.9855294027870821,0.002239532859910713 +flat_mae,patch,attn,hcpya_task21,last,19,0.006599999999999999,0.05,43,"[22, 1.0]",test,0.07176008820533752,0.9861111111111112,0.0015754859836431907,0.9832299793100557,0.0020954409398735822 diff --git a/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__attn/log.txt b/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__attn/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..e04d5ffca254319b1b471b1800b4ef4c6cb50c9d --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__attn/log.txt @@ -0,0 +1,1212 @@ +fMRI foundation model probe eval +version: 0.1.dev65+g4003a1397 +sha: 6c01b606db98add5848cecd23e5d599250c0bf86, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-02-24 22:21:22 +config: +output_root: experiments/decoders/output +name_prefix: eval_probe +remote_root: null +notes: decoder ablations crossreg_reg4; eval v2 (hcpya_task21 patch attn) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +dataset_kwargs: {} +classifier_kwargs: + embed_dim: null + dropout: 0.0 + xavier_init: false + norm: false +lr_scale_grid: +- 0.02 +- 0.023 +- 0.028 +- 0.033 +- 0.038 +- 0.045 +- 0.053 +- 0.062 +- 0.074 +- 0.087 +- 0.1 +- 0.12 +- 0.14 +- 0.17 +- 0.2 +- 0.23 +- 0.27 +- 0.32 +- 0.38 +- 0.44 +- 0.52 +- 0.61 +- 0.72 +- 0.85 +- 1 +- 1.2 +- 1.4 +- 1.6 +- 1.9 +- 2.3 +- 2.7 +- 3.1 +- 3.7 +- 4.3 +- 5.1 +- 6 +- 7.1 +- 8.3 +- 9.8 +- 12 +- 14 +- 16 +- 19 +- 22 +- 26 +- 31 +- 36 +- 43 +- 50 +wd_scale_grid: +- 1.0 +num_workers: 8 +prefetch_factor: null +balanced_sampling: false +epochs: 20 +steps_per_epoch: 200 +batch_size: 64 +accum_iter: 2 +lr: 0.0003 +warmup_epochs: 5 +no_decay: false +weight_decay: 0.05 +clip_grad: 1.0 +metrics: +- acc +- f1 +cv_metric: acc +early_stopping: true +amp: true +device: cuda +seed: 4466 +debug: false +wandb: false +wandb_entity: null +wandb_project: fMRI-fm-eval +name: decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__attn +model: flat_mae +representation: patch +classifier: attn +dataset: hcpya_task21 +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__attn +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=False, reg_tokens=4, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: hcpya_task21 (flat) +train (n=18999): +HFDataset( + dataset=Dataset({ + features: ['sub', 'task', 'cond', 'cond_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 18999 +}), + labels=[ 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20], + counts=[ 832 1248 3201 1660 832 832 832 832 832 1248 1247 1243 832 416 + 416 416 416 416 416 416 416] +) + +validation (n=4032): +HFDataset( + dataset=Dataset({ + features: ['sub', 'task', 'cond', 'cond_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 4032 +}), + labels=[ 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20], + counts=[176 264 688 352 176 176 176 176 176 264 264 264 176 88 88 88 88 88 + 88 88 88] +) + +test (n=5040): +HFDataset( + dataset=Dataset({ + features: ['sub', 'task', 'cond', 'cond_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 5040 +}), + labels=[ 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20], + counts=[220 330 860 440 220 220 220 220 220 330 330 330 220 110 110 110 110 110 + 110 110 110] +) + +running backbone on example batch to get embedding dim +embedding feature dim (patch): 768 +initializing sweep of classifier heads +classifiers: +ModuleList( + (0-48): 49 x AttnPoolClassifier( + (kv): Linear(in_features=768, out_features=1536, bias=True) + (linear): Linear(in_features=768, out_features=21, bias=True) + ) +) +classifier params (train): 58.7M (58.7M) +setting up optimizer +total batch size: 128 = 64 bs per gpu x 2 accum +lr: 3.00e-04 +full schedule: epochs = 20 (steps = 4000) (decay = True) +warmup: epochs = 5 (steps = 1000) +start training for 20 epochs +train: [0] [ 0/400] eta: 0:23:43 lr: nan time: 3.5582 data: 2.9497 max mem: 21740 +train: [0] [ 20/400] eta: 0:03:56 lr: 0.000003 loss: 3.0401 (3.0425) grad: 0.0894 (0.0888) time: 0.4754 data: 0.0030 max mem: 22446 +train: [0] [ 40/400] eta: 0:03:14 lr: 0.000006 loss: 3.0356 (3.0301) grad: 0.0894 (0.0916) time: 0.4554 data: 0.0037 max mem: 22446 +train: [0] [ 60/400] eta: 0:02:56 lr: 0.000009 loss: 3.0058 (3.0171) grad: 0.0873 (0.0903) time: 0.4752 data: 0.0037 max mem: 22446 +train: [0] [ 80/400] eta: 0:02:42 lr: 0.000012 loss: 2.9810 (3.0033) grad: 0.0852 (0.0906) time: 0.4697 data: 0.0036 max mem: 22446 +train: [0] [100/400] eta: 0:02:29 lr: 0.000015 loss: 2.9540 (2.9916) grad: 0.0840 (0.0895) time: 0.4706 data: 0.0037 max mem: 22446 +train: [0] [120/400] eta: 0:02:18 lr: 0.000018 loss: 2.9227 (2.9768) grad: 0.0864 (0.0903) time: 0.4712 data: 0.0035 max mem: 22446 +train: [0] [140/400] eta: 0:02:07 lr: 0.000021 loss: 2.8803 (2.9621) grad: 0.0813 (0.0890) time: 0.4687 data: 0.0035 max mem: 22446 +train: [0] [160/400] eta: 0:01:57 lr: 0.000024 loss: 2.8727 (2.9461) grad: 0.0776 (0.0880) time: 0.4654 data: 0.0035 max mem: 22446 +train: [0] [180/400] eta: 0:01:46 lr: 0.000027 loss: 2.7917 (2.9277) grad: 0.0795 (0.0873) time: 0.4703 data: 0.0034 max mem: 22446 +train: [0] [200/400] eta: 0:01:36 lr: 0.000030 loss: 2.7504 (2.9059) grad: 0.0828 (0.0868) time: 0.4598 data: 0.0034 max mem: 22446 +train: [0] [220/400] eta: 0:01:26 lr: 0.000033 loss: 2.6666 (2.8809) grad: 0.0867 (0.0872) time: 0.4793 data: 0.0036 max mem: 22446 +train: [0] [240/400] eta: 0:01:17 lr: 0.000036 loss: 2.6110 (2.8567) grad: 0.0867 (0.0870) time: 0.4722 data: 0.0035 max mem: 22446 +train: [0] [260/400] eta: 0:01:07 lr: 0.000039 loss: 2.5231 (2.8293) grad: 0.0815 (0.0865) time: 0.4682 data: 0.0036 max mem: 22446 +train: [0] [280/400] eta: 0:00:57 lr: 0.000042 loss: 2.4746 (2.8021) grad: 0.0799 (0.0862) time: 0.4639 data: 0.0034 max mem: 22446 +train: [0] [300/400] eta: 0:00:48 lr: 0.000045 loss: 2.4106 (2.7736) grad: 0.0804 (0.0861) time: 0.6309 data: 0.1758 max mem: 22446 +train: [0] [320/400] eta: 0:00:39 lr: 0.000048 loss: 2.3496 (2.7459) grad: 0.0829 (0.0861) time: 0.4658 data: 0.0032 max mem: 22446 +train: [0] [340/400] eta: 0:00:29 lr: 0.000051 loss: 2.3044 (2.7208) grad: 0.0789 (0.0857) time: 0.4627 data: 0.0034 max mem: 22446 +train: [0] [360/400] eta: 0:00:19 lr: 0.000054 loss: 2.2825 (2.6947) grad: 0.0803 (0.0856) time: 0.4775 data: 0.0035 max mem: 22446 +train: [0] [380/400] eta: 0:00:09 lr: 0.000057 loss: 2.2204 (2.6684) grad: 0.0810 (0.0854) time: 0.4728 data: 0.0035 max mem: 22446 +train: [0] [399/400] eta: 0:00:00 lr: 0.000060 loss: 2.1598 (2.6413) grad: 0.0784 (0.0850) time: 0.4568 data: 0.0035 max mem: 22446 +train: [0] Total time: 0:03:13 (0.4846 s / it) +train: [0] Summary: lr: 0.000060 loss: 2.1598 (2.6413) grad: 0.0784 (0.0850) +eval (validation): [0] [ 0/63] eta: 0:03:09 time: 3.0006 data: 2.7586 max mem: 22446 +eval (validation): [0] [20/63] eta: 0:00:20 time: 0.3485 data: 0.0039 max mem: 22446 +eval (validation): [0] [40/63] eta: 0:00:09 time: 0.3415 data: 0.0033 max mem: 22446 +eval (validation): [0] [60/63] eta: 0:00:01 time: 0.3440 data: 0.0031 max mem: 22446 +eval (validation): [0] [62/63] eta: 0:00:00 time: 0.3429 data: 0.0034 max mem: 22446 +eval (validation): [0] Total time: 0:00:24 (0.3910 s / it) +cv: [0] best hparam: (36, 1.0) (046) ('046_lr3.6e+01_wd1.0e+00') loss: 0.152 acc: 0.953 f1: 0.948 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__attn/checkpoint-best.pth +train: [1] [ 0/400] eta: 0:21:13 lr: nan time: 3.1829 data: 2.8421 max mem: 22446 +train: [1] [ 20/400] eta: 0:03:51 lr: 0.000063 loss: 2.0838 (2.1010) grad: 0.0767 (0.0755) time: 0.4808 data: 0.0033 max mem: 22446 +train: [1] [ 40/400] eta: 0:03:12 lr: 0.000066 loss: 2.0770 (2.0884) grad: 0.0772 (0.0778) time: 0.4573 data: 0.0029 max mem: 22446 +train: [1] [ 60/400] eta: 0:02:54 lr: 0.000069 loss: 2.0486 (2.0651) grad: 0.0744 (0.0766) time: 0.4706 data: 0.0036 max mem: 22446 +train: [1] [ 80/400] eta: 0:02:40 lr: 0.000072 loss: 1.9934 (2.0422) grad: 0.0744 (0.0761) time: 0.4673 data: 0.0035 max mem: 22446 +train: [1] [100/400] eta: 0:02:27 lr: 0.000075 loss: 1.9809 (2.0292) grad: 0.0762 (0.0768) time: 0.4507 data: 0.0036 max mem: 22446 +train: [1] [120/400] eta: 0:02:15 lr: 0.000078 loss: 1.9476 (2.0156) grad: 0.0752 (0.0764) time: 0.4494 data: 0.0035 max mem: 22446 +train: [1] [140/400] eta: 0:02:04 lr: 0.000081 loss: 1.8979 (1.9931) grad: 0.0752 (0.0767) time: 0.4534 data: 0.0036 max mem: 22446 +train: [1] [160/400] eta: 0:01:54 lr: 0.000084 loss: 1.8696 (1.9823) grad: 0.0738 (0.0763) time: 0.4623 data: 0.0037 max mem: 22446 +train: [1] [180/400] eta: 0:01:45 lr: 0.000087 loss: 1.8795 (1.9678) grad: 0.0743 (0.0765) time: 0.4686 data: 0.0034 max mem: 22446 +train: [1] [200/400] eta: 0:01:35 lr: 0.000090 loss: 1.8181 (1.9525) grad: 0.0741 (0.0761) time: 0.4607 data: 0.0035 max mem: 22446 +train: [1] [220/400] eta: 0:01:25 lr: 0.000093 loss: 1.8013 (1.9368) grad: 0.0727 (0.0760) time: 0.4524 data: 0.0035 max mem: 22446 +train: [1] [240/400] eta: 0:01:15 lr: 0.000096 loss: 1.7782 (1.9247) grad: 0.0720 (0.0754) time: 0.4494 data: 0.0034 max mem: 22446 +train: [1] [260/400] eta: 0:01:05 lr: 0.000099 loss: 1.7487 (1.9074) grad: 0.0689 (0.0751) time: 0.4645 data: 0.0035 max mem: 22446 +train: [1] [280/400] eta: 0:00:56 lr: 0.000102 loss: 1.6928 (1.8931) grad: 0.0715 (0.0751) time: 0.4568 data: 0.0036 max mem: 22446 +train: [1] [300/400] eta: 0:00:48 lr: 0.000105 loss: 1.7132 (1.8812) grad: 0.0728 (0.0749) time: 0.6324 data: 0.1770 max mem: 22446 +train: [1] [320/400] eta: 0:00:38 lr: 0.000108 loss: 1.6882 (1.8679) grad: 0.0726 (0.0748) time: 0.4526 data: 0.0030 max mem: 22446 +train: [1] [340/400] eta: 0:00:28 lr: 0.000111 loss: 1.6662 (1.8554) grad: 0.0742 (0.0749) time: 0.4580 data: 0.0037 max mem: 22446 +train: [1] [360/400] eta: 0:00:19 lr: 0.000114 loss: 1.6489 (1.8444) grad: 0.0744 (0.0749) time: 0.4679 data: 0.0036 max mem: 22446 +train: [1] [380/400] eta: 0:00:09 lr: 0.000117 loss: 1.6179 (1.8316) grad: 0.0732 (0.0747) time: 0.4511 data: 0.0035 max mem: 22446 +train: [1] [399/400] eta: 0:00:00 lr: 0.000120 loss: 1.5837 (1.8193) grad: 0.0748 (0.0747) time: 0.4586 data: 0.0035 max mem: 22446 +train: [1] Total time: 0:03:10 (0.4754 s / it) +train: [1] Summary: lr: 0.000120 loss: 1.5837 (1.8193) grad: 0.0748 (0.0747) +eval (validation): [1] [ 0/63] eta: 0:03:27 time: 3.3002 data: 3.0105 max mem: 22446 +eval (validation): [1] [20/63] eta: 0:00:21 time: 0.3520 data: 0.0041 max mem: 22446 +eval (validation): [1] [40/63] eta: 0:00:09 time: 0.3477 data: 0.0031 max mem: 22446 +eval (validation): [1] [60/63] eta: 0:00:01 time: 0.3497 data: 0.0033 max mem: 22446 +eval (validation): [1] [62/63] eta: 0:00:00 time: 0.3457 data: 0.0033 max mem: 22446 +eval (validation): [1] Total time: 0:00:25 (0.4015 s / it) +cv: [1] best hparam: (12, 1.0) (039) ('039_lr1.2e+01_wd1.0e+00') loss: 0.094 acc: 0.971 f1: 0.969 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__attn/checkpoint-best.pth +train: [2] [ 0/400] eta: 0:22:32 lr: nan time: 3.3804 data: 2.9745 max mem: 22446 +train: [2] [ 20/400] eta: 0:03:56 lr: 0.000123 loss: 1.5390 (1.5458) grad: 0.0678 (0.0704) time: 0.4838 data: 0.0040 max mem: 22446 +train: [2] [ 40/400] eta: 0:03:16 lr: 0.000126 loss: 1.5412 (1.5452) grad: 0.0680 (0.0705) time: 0.4647 data: 0.0034 max mem: 22446 +train: [2] [ 60/400] eta: 0:02:57 lr: 0.000129 loss: 1.5412 (1.5463) grad: 0.0689 (0.0709) time: 0.4751 data: 0.0037 max mem: 22446 +train: [2] [ 80/400] eta: 0:02:41 lr: 0.000132 loss: 1.5240 (1.5371) grad: 0.0732 (0.0728) time: 0.4562 data: 0.0035 max mem: 22446 +train: [2] [100/400] eta: 0:02:29 lr: 0.000135 loss: 1.5032 (1.5312) grad: 0.0781 (0.0739) time: 0.4720 data: 0.0036 max mem: 22446 +train: [2] [120/400] eta: 0:02:17 lr: 0.000138 loss: 1.4862 (1.5223) grad: 0.0780 (0.0739) time: 0.4588 data: 0.0033 max mem: 22446 +train: [2] [140/400] eta: 0:02:07 lr: 0.000141 loss: 1.4690 (1.5138) grad: 0.0740 (0.0741) time: 0.4684 data: 0.0035 max mem: 22446 +train: [2] [160/400] eta: 0:01:56 lr: 0.000144 loss: 1.4439 (1.5035) grad: 0.0740 (0.0743) time: 0.4626 data: 0.0034 max mem: 22446 +train: [2] [180/400] eta: 0:01:46 lr: 0.000147 loss: 1.4393 (1.4966) grad: 0.0741 (0.0745) time: 0.4516 data: 0.0034 max mem: 22446 +train: [2] [200/400] eta: 0:01:36 lr: 0.000150 loss: 1.4406 (1.4893) grad: 0.0761 (0.0746) time: 0.4640 data: 0.0035 max mem: 22446 +train: [2] [220/400] eta: 0:01:26 lr: 0.000153 loss: 1.4367 (1.4831) grad: 0.0761 (0.0751) time: 0.4605 data: 0.0035 max mem: 22446 +train: [2] [240/400] eta: 0:01:16 lr: 0.000156 loss: 1.4016 (1.4762) grad: 0.0798 (0.0755) time: 0.4592 data: 0.0034 max mem: 22446 +train: [2] [260/400] eta: 0:01:06 lr: 0.000159 loss: 1.3776 (1.4691) grad: 0.0812 (0.0760) time: 0.4562 data: 0.0037 max mem: 22446 +train: [2] [280/400] eta: 0:00:56 lr: 0.000162 loss: 1.3618 (1.4615) grad: 0.0822 (0.0764) time: 0.4610 data: 0.0036 max mem: 22446 +train: [2] [300/400] eta: 0:00:48 lr: 0.000165 loss: 1.3506 (1.4542) grad: 0.0838 (0.0778) time: 0.6172 data: 0.1754 max mem: 22446 +train: [2] [320/400] eta: 0:00:38 lr: 0.000168 loss: 1.3292 (1.4466) grad: 0.0860 (0.0784) time: 0.4504 data: 0.0032 max mem: 22446 +train: [2] [340/400] eta: 0:00:28 lr: 0.000171 loss: 1.3315 (1.4405) grad: 0.0897 (0.0792) time: 0.4522 data: 0.0036 max mem: 22446 +train: [2] [360/400] eta: 0:00:19 lr: 0.000174 loss: 1.3044 (1.4337) grad: 0.0925 (0.0801) time: 0.4561 data: 0.0036 max mem: 22446 +train: [2] [380/400] eta: 0:00:09 lr: 0.000177 loss: 1.2871 (1.4265) grad: 0.0916 (0.0808) time: 0.4533 data: 0.0036 max mem: 22446 +train: [2] [399/400] eta: 0:00:00 lr: 0.000180 loss: 1.2746 (1.4186) grad: 0.0955 (0.0819) time: 0.4610 data: 0.0036 max mem: 22446 +train: [2] Total time: 0:03:10 (0.4768 s / it) +train: [2] Summary: lr: 0.000180 loss: 1.2746 (1.4186) grad: 0.0955 (0.0819) +eval (validation): [2] [ 0/63] eta: 0:03:25 time: 3.2540 data: 3.0069 max mem: 22446 +eval (validation): [2] [20/63] eta: 0:00:20 time: 0.3462 data: 0.0039 max mem: 22446 +eval (validation): [2] [40/63] eta: 0:00:09 time: 0.3553 data: 0.0031 max mem: 22446 +eval (validation): [2] [60/63] eta: 0:00:01 time: 0.3508 data: 0.0032 max mem: 22446 +eval (validation): [2] [62/63] eta: 0:00:00 time: 0.3504 data: 0.0028 max mem: 22446 +eval (validation): [2] Total time: 0:00:25 (0.4016 s / it) +cv: [2] best hparam: (9.8, 1.0) (038) ('038_lr9.8e+00_wd1.0e+00') loss: 0.064 acc: 0.980 f1: 0.978 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__attn/checkpoint-best.pth +train: [3] [ 0/400] eta: 0:27:00 lr: nan time: 4.0504 data: 3.6989 max mem: 22446 +train: [3] [ 20/400] eta: 0:04:02 lr: 0.000183 loss: 1.2801 (1.2864) grad: 0.1046 (0.1048) time: 0.4680 data: 0.0023 max mem: 22446 +train: [3] [ 40/400] eta: 0:03:20 lr: 0.000186 loss: 1.2747 (1.2810) grad: 0.1106 (0.1131) time: 0.4698 data: 0.0033 max mem: 22446 +train: [3] [ 60/400] eta: 0:02:59 lr: 0.000189 loss: 1.2692 (1.2809) grad: 0.1167 (0.1148) time: 0.4689 data: 0.0034 max mem: 22446 +train: [3] [ 80/400] eta: 0:02:44 lr: 0.000192 loss: 1.2654 (1.2779) grad: 0.1162 (0.1167) time: 0.4679 data: 0.0034 max mem: 22446 +train: [3] [100/400] eta: 0:02:31 lr: 0.000195 loss: 1.2852 (1.2835) grad: 0.1236 (0.1196) time: 0.4773 data: 0.0035 max mem: 22446 +train: [3] [120/400] eta: 0:02:19 lr: 0.000198 loss: 1.2852 (1.2812) grad: 0.1354 (0.1222) time: 0.4652 data: 0.0035 max mem: 22446 +train: [3] [140/400] eta: 0:02:08 lr: 0.000201 loss: 1.2633 (1.2757) grad: 0.1324 (0.1227) time: 0.4565 data: 0.0034 max mem: 22446 +train: [3] [160/400] eta: 0:01:57 lr: 0.000204 loss: 1.1980 (1.2655) grad: 0.1219 (0.1220) time: 0.4574 data: 0.0036 max mem: 22446 +train: [3] [180/400] eta: 0:01:46 lr: 0.000207 loss: 1.1958 (1.2590) grad: 0.1083 (0.1223) time: 0.4573 data: 0.0035 max mem: 22446 +train: [3] [200/400] eta: 0:01:36 lr: 0.000210 loss: 1.1775 (1.2500) grad: 0.1196 (0.1219) time: 0.4581 data: 0.0037 max mem: 22446 +train: [3] [220/400] eta: 0:01:26 lr: 0.000213 loss: 1.1631 (1.2454) grad: 0.1188 (0.1221) time: 0.4576 data: 0.0034 max mem: 22446 +train: [3] [240/400] eta: 0:01:16 lr: 0.000216 loss: 1.2002 (1.2433) grad: 0.1188 (0.1222) time: 0.4617 data: 0.0034 max mem: 22446 +train: [3] [260/400] eta: 0:01:06 lr: 0.000219 loss: 1.2002 (1.2382) grad: 0.1215 (0.1225) time: 0.4564 data: 0.0035 max mem: 22446 +train: [3] [280/400] eta: 0:00:57 lr: 0.000222 loss: 1.1761 (1.2321) grad: 0.1252 (0.1233) time: 0.4547 data: 0.0036 max mem: 22446 +train: [3] [300/400] eta: 0:00:48 lr: 0.000225 loss: 1.1751 (1.2284) grad: 0.1360 (0.1237) time: 0.6479 data: 0.1836 max mem: 22446 +train: [3] [320/400] eta: 0:00:38 lr: 0.000228 loss: 1.1398 (1.2233) grad: 0.1211 (0.1241) time: 0.4647 data: 0.0034 max mem: 22446 +train: [3] [340/400] eta: 0:00:29 lr: 0.000231 loss: 1.1379 (1.2200) grad: 0.1348 (0.1254) time: 0.4578 data: 0.0035 max mem: 22446 +train: [3] [360/400] eta: 0:00:19 lr: 0.000234 loss: 1.1379 (1.2167) grad: 0.1381 (0.1266) time: 0.4737 data: 0.0037 max mem: 22446 +train: [3] [380/400] eta: 0:00:09 lr: 0.000237 loss: 1.1024 (1.2112) grad: 0.1298 (0.1265) time: 0.4515 data: 0.0034 max mem: 22446 +train: [3] [399/400] eta: 0:00:00 lr: 0.000240 loss: 1.1087 (1.2058) grad: 0.1229 (0.1260) time: 0.4622 data: 0.0035 max mem: 22446 +train: [3] Total time: 0:03:12 (0.4810 s / it) +train: [3] Summary: lr: 0.000240 loss: 1.1087 (1.2058) grad: 0.1229 (0.1260) +eval (validation): [3] [ 0/63] eta: 0:03:22 time: 3.2202 data: 2.9271 max mem: 22446 +eval (validation): [3] [20/63] eta: 0:00:21 time: 0.3519 data: 0.0069 max mem: 22446 +eval (validation): [3] [40/63] eta: 0:00:10 time: 0.3890 data: 0.0036 max mem: 22446 +eval (validation): [3] [60/63] eta: 0:00:01 time: 0.3390 data: 0.0029 max mem: 22446 +eval (validation): [3] [62/63] eta: 0:00:00 time: 0.3379 data: 0.0032 max mem: 22446 +eval (validation): [3] Total time: 0:00:25 (0.4099 s / it) +cv: [3] best hparam: (9.8, 1.0) (038) ('038_lr9.8e+00_wd1.0e+00') loss: 0.074 acc: 0.977 f1: 0.973 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [4] [ 0/400] eta: 0:22:47 lr: nan time: 3.4175 data: 3.0357 max mem: 22446 +train: [4] [ 20/400] eta: 0:03:52 lr: 0.000243 loss: 1.0442 (1.0395) grad: 0.1127 (0.1177) time: 0.4727 data: 0.0034 max mem: 22446 +train: [4] [ 40/400] eta: 0:03:17 lr: 0.000246 loss: 1.0736 (1.0729) grad: 0.1235 (0.1262) time: 0.4809 data: 0.0030 max mem: 22446 +train: [4] [ 60/400] eta: 0:02:58 lr: 0.000249 loss: 1.0877 (1.0752) grad: 0.1437 (0.1361) time: 0.4779 data: 0.0037 max mem: 22446 +train: [4] [ 80/400] eta: 0:02:43 lr: 0.000252 loss: 1.0877 (1.0882) grad: 0.1562 (0.1462) time: 0.4720 data: 0.0035 max mem: 22446 +train: [4] [100/400] eta: 0:02:30 lr: 0.000255 loss: 1.0858 (1.0910) grad: 0.1634 (0.1520) time: 0.4644 data: 0.0034 max mem: 22446 +train: [4] [120/400] eta: 0:02:19 lr: 0.000258 loss: 1.1054 (1.1005) grad: 0.1596 (0.1560) time: 0.4824 data: 0.0036 max mem: 22446 +train: [4] [140/400] eta: 0:02:08 lr: 0.000261 loss: 1.1054 (1.0946) grad: 0.1895 (0.1607) time: 0.4586 data: 0.0036 max mem: 22446 +train: [4] [160/400] eta: 0:01:57 lr: 0.000264 loss: 1.0688 (1.0953) grad: 0.1753 (0.1639) time: 0.4564 data: 0.0035 max mem: 22446 +train: [4] [180/400] eta: 0:01:46 lr: 0.000267 loss: 1.0456 (1.0928) grad: 0.1600 (0.1648) time: 0.4627 data: 0.0036 max mem: 22446 +train: [4] [200/400] eta: 0:01:36 lr: 0.000270 loss: 1.0626 (1.0934) grad: 0.1858 (0.1696) time: 0.4584 data: 0.0035 max mem: 22446 +train: [4] [220/400] eta: 0:01:26 lr: 0.000273 loss: 1.0795 (1.0974) grad: 0.2103 (0.1742) time: 0.4600 data: 0.0035 max mem: 22446 +train: [4] [240/400] eta: 0:01:16 lr: 0.000276 loss: 1.1068 (1.0988) grad: 0.2022 (0.1774) time: 0.4604 data: 0.0035 max mem: 22446 +train: [4] [260/400] eta: 0:01:06 lr: 0.000279 loss: 1.0809 (1.0995) grad: 0.2379 (0.1865) time: 0.4611 data: 0.0037 max mem: 22446 +train: [4] [280/400] eta: 0:00:57 lr: 0.000282 loss: 1.0857 (1.1026) grad: 0.2752 (0.1936) time: 0.4540 data: 0.0036 max mem: 22446 +train: [4] [300/400] eta: 0:00:48 lr: 0.000285 loss: 1.0959 (1.1026) grad: 0.2550 (0.1992) time: 0.6082 data: 0.1791 max mem: 22446 +train: [4] [320/400] eta: 0:00:38 lr: 0.000288 loss: 1.0796 (1.1007) grad: 0.2680 (0.2036) time: 0.4568 data: 0.0033 max mem: 22446 +train: [4] [340/400] eta: 0:00:28 lr: 0.000291 loss: 1.0845 (1.1037) grad: 0.2791 (0.2147) time: 0.4578 data: 0.0035 max mem: 22446 +train: [4] [360/400] eta: 0:00:19 lr: 0.000294 loss: 1.1518 (1.1109) grad: 0.3508 (0.2243) time: 0.4607 data: 0.0036 max mem: 22446 +train: [4] [380/400] eta: 0:00:09 lr: 0.000297 loss: 1.1756 (1.1132) grad: 0.3509 (0.2398) time: 0.4612 data: 0.0035 max mem: 22446 +train: [4] [399/400] eta: 0:00:00 lr: 0.000300 loss: 1.1899 (1.1277) grad: 0.4786 (0.2534) time: 0.4638 data: 0.0034 max mem: 22446 +train: [4] Total time: 0:03:11 (0.4792 s / it) +train: [4] Summary: lr: 0.000300 loss: 1.1899 (1.1277) grad: 0.4786 (0.2534) +eval (validation): [4] [ 0/63] eta: 0:03:20 time: 3.1843 data: 2.9484 max mem: 22446 +eval (validation): [4] [20/63] eta: 0:00:21 time: 0.3698 data: 0.0041 max mem: 22446 +eval (validation): [4] [40/63] eta: 0:00:10 time: 0.3635 data: 0.0033 max mem: 22446 +eval (validation): [4] [60/63] eta: 0:00:01 time: 0.3449 data: 0.0033 max mem: 22446 +eval (validation): [4] [62/63] eta: 0:00:00 time: 0.3414 data: 0.0032 max mem: 22446 +eval (validation): [4] Total time: 0:00:25 (0.4096 s / it) +cv: [4] best hparam: (5.1, 1.0) (034) ('034_lr5.1e+00_wd1.0e+00') loss: 0.082 acc: 0.976 f1: 0.976 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [5] [ 0/400] eta: 0:22:52 lr: nan time: 3.4320 data: 3.0187 max mem: 22446 +train: [5] [ 20/400] eta: 0:03:45 lr: 0.000300 loss: 1.2028 (1.2349) grad: 0.4257 (0.5273) time: 0.4525 data: 0.0029 max mem: 22446 +train: [5] [ 40/400] eta: 0:03:12 lr: 0.000300 loss: 1.2028 (1.2080) grad: 0.4808 (0.5256) time: 0.4714 data: 0.0032 max mem: 22446 +train: [5] [ 60/400] eta: 0:02:55 lr: 0.000300 loss: 1.2252 (1.2706) grad: 0.4460 (0.5002) time: 0.4813 data: 0.0037 max mem: 22446 +train: [5] [ 80/400] eta: 0:02:42 lr: 0.000300 loss: 1.2954 (1.2802) grad: 0.4400 (0.4995) time: 0.4738 data: 0.0036 max mem: 22446 +train: [5] [100/400] eta: 0:02:28 lr: 0.000300 loss: 1.1905 (1.2680) grad: 0.4296 (0.4830) time: 0.4552 data: 0.0036 max mem: 22446 +train: [5] [120/400] eta: 0:02:17 lr: 0.000300 loss: 1.1826 (1.2549) grad: 0.3846 (0.4723) time: 0.4698 data: 0.0035 max mem: 22446 +train: [5] [140/400] eta: 0:02:08 lr: 0.000300 loss: 1.1817 (1.2630) grad: 0.3874 (0.4653) time: 0.4970 data: 0.0037 max mem: 22446 +train: [5] [160/400] eta: 0:01:57 lr: 0.000299 loss: 1.1817 (1.2603) grad: 0.4381 (0.4641) time: 0.4628 data: 0.0036 max mem: 22446 +train: [5] [180/400] eta: 0:01:46 lr: 0.000299 loss: 1.1276 (1.2496) grad: 0.3653 (0.4507) time: 0.4497 data: 0.0034 max mem: 22446 +train: [5] [200/400] eta: 0:01:36 lr: 0.000299 loss: 1.2109 (1.2523) grad: 0.3653 (0.4523) time: 0.4676 data: 0.0035 max mem: 22446 +train: [5] [220/400] eta: 0:01:26 lr: 0.000299 loss: 1.2005 (1.2446) grad: 0.3918 (0.4443) time: 0.4573 data: 0.0035 max mem: 22446 +train: [5] [240/400] eta: 0:01:16 lr: 0.000299 loss: 1.1521 (1.2383) grad: 0.3742 (0.4481) time: 0.4632 data: 0.0035 max mem: 22446 +train: [5] [260/400] eta: 0:01:06 lr: 0.000299 loss: 1.2606 (1.2471) grad: 0.4685 (0.4483) time: 0.4578 data: 0.0035 max mem: 22446 +train: [5] [280/400] eta: 0:00:57 lr: 0.000298 loss: 1.2606 (1.2406) grad: 0.3854 (0.4426) time: 0.4557 data: 0.0036 max mem: 22446 +train: [5] [300/400] eta: 0:00:48 lr: 0.000298 loss: 1.0524 (1.2261) grad: 0.3155 (0.4333) time: 0.6196 data: 0.1745 max mem: 22446 +train: [5] [320/400] eta: 0:00:38 lr: 0.000298 loss: 0.9965 (1.2150) grad: 0.2932 (0.4263) time: 0.4629 data: 0.0036 max mem: 22446 +train: [5] [340/400] eta: 0:00:28 lr: 0.000298 loss: 1.0312 (1.2003) grad: 0.2700 (0.4171) time: 0.4678 data: 0.0034 max mem: 22446 +train: [5] [360/400] eta: 0:00:19 lr: 0.000297 loss: 0.9624 (1.1866) grad: 0.2405 (0.4093) time: 0.4680 data: 0.0037 max mem: 22446 +train: [5] [380/400] eta: 0:00:09 lr: 0.000297 loss: 0.8987 (1.1732) grad: 0.2650 (0.4032) time: 0.4646 data: 0.0036 max mem: 22446 +train: [5] [399/400] eta: 0:00:00 lr: 0.000297 loss: 0.9164 (1.1676) grad: 0.2760 (0.3986) time: 0.4664 data: 0.0036 max mem: 22446 +train: [5] Total time: 0:03:12 (0.4809 s / it) +train: [5] Summary: lr: 0.000297 loss: 0.9164 (1.1676) grad: 0.2760 (0.3986) +eval (validation): [5] [ 0/63] eta: 0:03:21 time: 3.2024 data: 2.9682 max mem: 22446 +eval (validation): [5] [20/63] eta: 0:00:21 time: 0.3535 data: 0.0042 max mem: 22446 +eval (validation): [5] [40/63] eta: 0:00:09 time: 0.3585 data: 0.0033 max mem: 22446 +eval (validation): [5] [60/63] eta: 0:00:01 time: 0.3623 data: 0.0037 max mem: 22446 +eval (validation): [5] [62/63] eta: 0:00:00 time: 0.3610 data: 0.0036 max mem: 22446 +eval (validation): [5] Total time: 0:00:25 (0.4065 s / it) +cv: [5] best hparam: (7.1, 1.0) (036) ('036_lr7.1e+00_wd1.0e+00') loss: 0.084 acc: 0.977 f1: 0.975 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [6] [ 0/400] eta: 0:23:02 lr: nan time: 3.4564 data: 3.1010 max mem: 22446 +train: [6] [ 20/400] eta: 0:03:48 lr: 0.000296 loss: 0.8591 (0.8939) grad: 0.2231 (0.2480) time: 0.4584 data: 0.0029 max mem: 22446 +train: [6] [ 40/400] eta: 0:03:12 lr: 0.000296 loss: 0.8789 (0.9221) grad: 0.2231 (0.2349) time: 0.4665 data: 0.0035 max mem: 22446 +train: [6] [ 60/400] eta: 0:02:54 lr: 0.000296 loss: 0.8861 (0.9180) grad: 0.2046 (0.2356) time: 0.4647 data: 0.0035 max mem: 22446 +train: [6] [ 80/400] eta: 0:02:41 lr: 0.000295 loss: 0.8862 (0.9094) grad: 0.2373 (0.2367) time: 0.4858 data: 0.0037 max mem: 22446 +train: [6] [100/400] eta: 0:02:29 lr: 0.000295 loss: 0.8826 (0.9191) grad: 0.2373 (0.2363) time: 0.4649 data: 0.0033 max mem: 22446 +train: [6] [120/400] eta: 0:02:17 lr: 0.000295 loss: 0.8983 (0.9220) grad: 0.2336 (0.2368) time: 0.4638 data: 0.0034 max mem: 22446 +train: [6] [140/400] eta: 0:02:07 lr: 0.000294 loss: 0.8729 (0.9141) grad: 0.2336 (0.2375) time: 0.4725 data: 0.0035 max mem: 22446 +train: [6] [160/400] eta: 0:01:57 lr: 0.000294 loss: 0.8596 (0.9089) grad: 0.1989 (0.2333) time: 0.4994 data: 0.0039 max mem: 22446 +train: [6] [180/400] eta: 0:01:47 lr: 0.000293 loss: 0.8334 (0.9141) grad: 0.1990 (0.2316) time: 0.4725 data: 0.0035 max mem: 22446 +train: [6] [200/400] eta: 0:01:37 lr: 0.000293 loss: 0.8918 (0.9103) grad: 0.2177 (0.2305) time: 0.4581 data: 0.0035 max mem: 22446 +train: [6] [220/400] eta: 0:01:26 lr: 0.000292 loss: 0.8067 (0.8987) grad: 0.1928 (0.2259) time: 0.4582 data: 0.0034 max mem: 22446 +train: [6] [240/400] eta: 0:01:17 lr: 0.000292 loss: 0.8067 (0.8968) grad: 0.1874 (0.2246) time: 0.4632 data: 0.0035 max mem: 22446 +train: [6] [260/400] eta: 0:01:07 lr: 0.000291 loss: 0.8574 (0.8920) grad: 0.2262 (0.2265) time: 0.4605 data: 0.0034 max mem: 22446 +train: [6] [280/400] eta: 0:00:57 lr: 0.000291 loss: 0.7678 (0.8844) grad: 0.2376 (0.2254) time: 0.4581 data: 0.0036 max mem: 22446 +train: [6] [300/400] eta: 0:00:48 lr: 0.000290 loss: 0.7678 (0.8803) grad: 0.2366 (0.2274) time: 0.6175 data: 0.1797 max mem: 22446 +train: [6] [320/400] eta: 0:00:38 lr: 0.000290 loss: 0.8179 (0.8770) grad: 0.2213 (0.2254) time: 0.4451 data: 0.0030 max mem: 22446 +train: [6] [340/400] eta: 0:00:28 lr: 0.000289 loss: 0.7587 (0.8714) grad: 0.2144 (0.2269) time: 0.4512 data: 0.0030 max mem: 22446 +train: [6] [360/400] eta: 0:00:19 lr: 0.000288 loss: 0.7508 (0.8661) grad: 0.2141 (0.2255) time: 0.4653 data: 0.0035 max mem: 22446 +train: [6] [380/400] eta: 0:00:09 lr: 0.000288 loss: 0.7695 (0.8634) grad: 0.1925 (0.2243) time: 0.4623 data: 0.0036 max mem: 22446 +train: [6] [399/400] eta: 0:00:00 lr: 0.000287 loss: 0.8037 (0.8591) grad: 0.2001 (0.2224) time: 0.4586 data: 0.0035 max mem: 22446 +train: [6] Total time: 0:03:12 (0.4802 s / it) +train: [6] Summary: lr: 0.000287 loss: 0.8037 (0.8591) grad: 0.2001 (0.2224) +eval (validation): [6] [ 0/63] eta: 0:03:21 time: 3.2051 data: 2.9106 max mem: 22446 +eval (validation): [6] [20/63] eta: 0:00:22 time: 0.3989 data: 0.0038 max mem: 22446 +eval (validation): [6] [40/63] eta: 0:00:10 time: 0.3632 data: 0.0040 max mem: 22446 +eval (validation): [6] [60/63] eta: 0:00:01 time: 0.3392 data: 0.0027 max mem: 22446 +eval (validation): [6] [62/63] eta: 0:00:00 time: 0.3390 data: 0.0029 max mem: 22446 +eval (validation): [6] Total time: 0:00:26 (0.4160 s / it) +cv: [6] best hparam: (3.7, 1.0) (032) ('032_lr3.7e+00_wd1.0e+00') loss: 0.063 acc: 0.981 f1: 0.980 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__attn/checkpoint-best.pth +train: [7] [ 0/400] eta: 0:22:31 lr: nan time: 3.3780 data: 2.9902 max mem: 22446 +train: [7] [ 20/400] eta: 0:03:45 lr: 0.000286 loss: 0.7857 (0.7821) grad: 0.1963 (0.2186) time: 0.4539 data: 0.0032 max mem: 22446 +train: [7] [ 40/400] eta: 0:03:12 lr: 0.000286 loss: 0.7857 (0.7901) grad: 0.2050 (0.2252) time: 0.4753 data: 0.0035 max mem: 22446 +train: [7] [ 60/400] eta: 0:02:55 lr: 0.000285 loss: 0.7545 (0.7807) grad: 0.2083 (0.2246) time: 0.4781 data: 0.0036 max mem: 22446 +train: [7] [ 80/400] eta: 0:02:41 lr: 0.000284 loss: 0.7727 (0.7900) grad: 0.2529 (0.2439) time: 0.4690 data: 0.0037 max mem: 22446 +train: [7] [100/400] eta: 0:02:28 lr: 0.000284 loss: 0.8185 (0.7992) grad: 0.2627 (0.2506) time: 0.4551 data: 0.0034 max mem: 22446 +train: [7] [120/400] eta: 0:02:17 lr: 0.000283 loss: 0.8185 (0.8151) grad: 0.2747 (0.2595) time: 0.4674 data: 0.0033 max mem: 22446 +train: [7] [140/400] eta: 0:02:06 lr: 0.000282 loss: 0.8667 (0.8176) grad: 0.2693 (0.2593) time: 0.4611 data: 0.0034 max mem: 22446 +train: [7] [160/400] eta: 0:01:56 lr: 0.000282 loss: 0.7801 (0.8162) grad: 0.2624 (0.2620) time: 0.4626 data: 0.0035 max mem: 22446 +train: [7] [180/400] eta: 0:01:45 lr: 0.000281 loss: 0.7801 (0.8211) grad: 0.2945 (0.2648) time: 0.4591 data: 0.0034 max mem: 22446 +train: [7] [200/400] eta: 0:01:35 lr: 0.000280 loss: 0.7874 (0.8164) grad: 0.2483 (0.2671) time: 0.4594 data: 0.0034 max mem: 22446 +train: [7] [220/400] eta: 0:01:25 lr: 0.000279 loss: 0.7898 (0.8180) grad: 0.2472 (0.2711) time: 0.4594 data: 0.0035 max mem: 22446 +train: [7] [240/400] eta: 0:01:16 lr: 0.000278 loss: 0.7898 (0.8166) grad: 0.3107 (0.2784) time: 0.4586 data: 0.0035 max mem: 22446 +train: [7] [260/400] eta: 0:01:06 lr: 0.000278 loss: 0.7411 (0.8091) grad: 0.3099 (0.2763) time: 0.4674 data: 0.0034 max mem: 22446 +train: [7] [280/400] eta: 0:00:56 lr: 0.000277 loss: 0.7068 (0.8089) grad: 0.2268 (0.2750) time: 0.4576 data: 0.0037 max mem: 22446 +train: [7] [300/400] eta: 0:00:48 lr: 0.000276 loss: 0.7592 (0.8039) grad: 0.2290 (0.2779) time: 0.6257 data: 0.1815 max mem: 22446 +train: [7] [320/400] eta: 0:00:38 lr: 0.000275 loss: 0.6866 (0.7966) grad: 0.2234 (0.2741) time: 0.4707 data: 0.0033 max mem: 22446 +train: [7] [340/400] eta: 0:00:28 lr: 0.000274 loss: 0.6919 (0.7910) grad: 0.1973 (0.2699) time: 0.4598 data: 0.0034 max mem: 22446 +train: [7] [360/400] eta: 0:00:19 lr: 0.000273 loss: 0.6571 (0.7835) grad: 0.1753 (0.2653) time: 0.4545 data: 0.0035 max mem: 22446 +train: [7] [380/400] eta: 0:00:09 lr: 0.000272 loss: 0.6546 (0.7774) grad: 0.2026 (0.2637) time: 0.4632 data: 0.0034 max mem: 22446 +train: [7] [399/400] eta: 0:00:00 lr: 0.000271 loss: 0.6595 (0.7724) grad: 0.2091 (0.2608) time: 0.4633 data: 0.0035 max mem: 22446 +train: [7] Total time: 0:03:11 (0.4786 s / it) +train: [7] Summary: lr: 0.000271 loss: 0.6595 (0.7724) grad: 0.2091 (0.2608) +eval (validation): [7] [ 0/63] eta: 0:03:26 time: 3.2782 data: 2.9715 max mem: 22446 +eval (validation): [7] [20/63] eta: 0:00:23 time: 0.4168 data: 0.0044 max mem: 22446 +eval (validation): [7] [40/63] eta: 0:00:10 time: 0.3834 data: 0.0034 max mem: 22446 +eval (validation): [7] [60/63] eta: 0:00:01 time: 0.3668 data: 0.0036 max mem: 22446 +eval (validation): [7] [62/63] eta: 0:00:00 time: 0.3596 data: 0.0036 max mem: 22446 +eval (validation): [7] Total time: 0:00:27 (0.4377 s / it) +cv: [7] best hparam: (5.1, 1.0) (034) ('034_lr5.1e+00_wd1.0e+00') loss: 0.063 acc: 0.984 f1: 0.981 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__attn/checkpoint-best.pth +train: [8] [ 0/400] eta: 0:21:48 lr: nan time: 3.2708 data: 2.9237 max mem: 22446 +train: [8] [ 20/400] eta: 0:03:45 lr: 0.000270 loss: 0.6592 (0.6868) grad: 0.1405 (0.1553) time: 0.4586 data: 0.0041 max mem: 22446 +train: [8] [ 40/400] eta: 0:03:11 lr: 0.000270 loss: 0.6554 (0.6638) grad: 0.1405 (0.1510) time: 0.4676 data: 0.0034 max mem: 22446 +train: [8] [ 60/400] eta: 0:02:53 lr: 0.000269 loss: 0.6092 (0.6525) grad: 0.1323 (0.1535) time: 0.4676 data: 0.0036 max mem: 22446 +train: [8] [ 80/400] eta: 0:02:40 lr: 0.000268 loss: 0.6448 (0.6651) grad: 0.1524 (0.1617) time: 0.4679 data: 0.0036 max mem: 22446 +train: [8] [100/400] eta: 0:02:27 lr: 0.000267 loss: 0.6775 (0.6669) grad: 0.1580 (0.1575) time: 0.4624 data: 0.0035 max mem: 22446 +train: [8] [120/400] eta: 0:02:16 lr: 0.000266 loss: 0.6431 (0.6629) grad: 0.1340 (0.1539) time: 0.4705 data: 0.0036 max mem: 22446 +train: [8] [140/400] eta: 0:02:06 lr: 0.000265 loss: 0.6170 (0.6625) grad: 0.1240 (0.1503) time: 0.4631 data: 0.0035 max mem: 22446 +train: [8] [160/400] eta: 0:01:55 lr: 0.000264 loss: 0.6540 (0.6624) grad: 0.1212 (0.1483) time: 0.4471 data: 0.0033 max mem: 22446 +train: [8] [180/400] eta: 0:01:45 lr: 0.000263 loss: 0.6401 (0.6602) grad: 0.1394 (0.1506) time: 0.4572 data: 0.0033 max mem: 22446 +train: [8] [200/400] eta: 0:01:35 lr: 0.000262 loss: 0.6053 (0.6560) grad: 0.1497 (0.1485) time: 0.4630 data: 0.0037 max mem: 22446 +train: [8] [220/400] eta: 0:01:25 lr: 0.000260 loss: 0.5988 (0.6511) grad: 0.1308 (0.1463) time: 0.4561 data: 0.0035 max mem: 22446 +train: [8] [240/400] eta: 0:01:15 lr: 0.000259 loss: 0.6183 (0.6501) grad: 0.1356 (0.1476) time: 0.4471 data: 0.0035 max mem: 22446 +train: [8] [260/400] eta: 0:01:05 lr: 0.000258 loss: 0.6475 (0.6503) grad: 0.1559 (0.1484) time: 0.4543 data: 0.0035 max mem: 22446 +train: [8] [280/400] eta: 0:00:56 lr: 0.000257 loss: 0.6329 (0.6469) grad: 0.1264 (0.1458) time: 0.4682 data: 0.0040 max mem: 22446 +train: [8] [300/400] eta: 0:00:48 lr: 0.000256 loss: 0.5982 (0.6436) grad: 0.1152 (0.1444) time: 0.6291 data: 0.1720 max mem: 22446 +train: [8] [320/400] eta: 0:00:38 lr: 0.000255 loss: 0.5837 (0.6394) grad: 0.1055 (0.1416) time: 0.4644 data: 0.0036 max mem: 22446 +train: [8] [340/400] eta: 0:00:28 lr: 0.000254 loss: 0.5752 (0.6355) grad: 0.0901 (0.1384) time: 0.4664 data: 0.0037 max mem: 22446 +train: [8] [360/400] eta: 0:00:19 lr: 0.000253 loss: 0.5752 (0.6326) grad: 0.0836 (0.1357) time: 0.4698 data: 0.0037 max mem: 22446 +train: [8] [380/400] eta: 0:00:09 lr: 0.000252 loss: 0.5780 (0.6305) grad: 0.0852 (0.1333) time: 0.4563 data: 0.0035 max mem: 22446 +train: [8] [399/400] eta: 0:00:00 lr: 0.000250 loss: 0.5632 (0.6275) grad: 0.0852 (0.1314) time: 0.4695 data: 0.0036 max mem: 22446 +train: [8] Total time: 0:03:11 (0.4776 s / it) +train: [8] Summary: lr: 0.000250 loss: 0.5632 (0.6275) grad: 0.0852 (0.1314) +eval (validation): [8] [ 0/63] eta: 0:03:49 time: 3.6430 data: 3.3559 max mem: 22446 +eval (validation): [8] [20/63] eta: 0:00:23 time: 0.3823 data: 0.0030 max mem: 22446 +eval (validation): [8] [40/63] eta: 0:00:10 time: 0.3584 data: 0.0033 max mem: 22446 +eval (validation): [8] [60/63] eta: 0:00:01 time: 0.3419 data: 0.0034 max mem: 22446 +eval (validation): [8] [62/63] eta: 0:00:00 time: 0.3384 data: 0.0033 max mem: 22446 +eval (validation): [8] Total time: 0:00:26 (0.4157 s / it) +cv: [8] best hparam: (12, 1.0) (039) ('039_lr1.2e+01_wd1.0e+00') loss: 0.063 acc: 0.984 f1: 0.981 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [9] [ 0/400] eta: 0:28:58 lr: nan time: 4.3468 data: 3.9255 max mem: 22446 +train: [9] [ 20/400] eta: 0:04:06 lr: 0.000249 loss: 0.5626 (0.5649) grad: 0.1022 (0.1057) time: 0.4645 data: 0.0021 max mem: 22446 +train: [9] [ 40/400] eta: 0:03:20 lr: 0.000248 loss: 0.5663 (0.5697) grad: 0.0899 (0.0985) time: 0.4578 data: 0.0035 max mem: 22446 +train: [9] [ 60/400] eta: 0:02:59 lr: 0.000247 loss: 0.5696 (0.5740) grad: 0.0837 (0.0986) time: 0.4705 data: 0.0037 max mem: 22446 +train: [9] [ 80/400] eta: 0:02:43 lr: 0.000246 loss: 0.5764 (0.5779) grad: 0.0943 (0.1015) time: 0.4643 data: 0.0035 max mem: 22446 +train: [9] [100/400] eta: 0:02:30 lr: 0.000244 loss: 0.5764 (0.5802) grad: 0.0969 (0.1015) time: 0.4562 data: 0.0037 max mem: 22446 +train: [9] [120/400] eta: 0:02:18 lr: 0.000243 loss: 0.5621 (0.5762) grad: 0.0886 (0.0985) time: 0.4577 data: 0.0034 max mem: 22446 +train: [9] [140/400] eta: 0:02:07 lr: 0.000242 loss: 0.5520 (0.5744) grad: 0.0859 (0.0985) time: 0.4637 data: 0.0036 max mem: 22446 +train: [9] [160/400] eta: 0:01:56 lr: 0.000241 loss: 0.5462 (0.5722) grad: 0.0884 (0.0970) time: 0.4581 data: 0.0034 max mem: 22446 +train: [9] [180/400] eta: 0:01:46 lr: 0.000240 loss: 0.5475 (0.5707) grad: 0.0840 (0.0952) time: 0.4531 data: 0.0035 max mem: 22446 +train: [9] [200/400] eta: 0:01:35 lr: 0.000238 loss: 0.5756 (0.5724) grad: 0.0846 (0.0945) time: 0.4587 data: 0.0036 max mem: 22446 +train: [9] [220/400] eta: 0:01:26 lr: 0.000237 loss: 0.5756 (0.5697) grad: 0.0877 (0.0931) time: 0.4578 data: 0.0035 max mem: 22446 +train: [9] [240/400] eta: 0:01:16 lr: 0.000236 loss: 0.5378 (0.5682) grad: 0.0750 (0.0916) time: 0.4496 data: 0.0035 max mem: 22446 +train: [9] [260/400] eta: 0:01:06 lr: 0.000234 loss: 0.5500 (0.5667) grad: 0.0720 (0.0903) time: 0.4406 data: 0.0035 max mem: 22446 +train: [9] [280/400] eta: 0:00:56 lr: 0.000233 loss: 0.5600 (0.5684) grad: 0.0783 (0.0904) time: 0.4629 data: 0.0031 max mem: 22446 +train: [9] [300/400] eta: 0:00:48 lr: 0.000232 loss: 0.5600 (0.5674) grad: 0.0827 (0.0897) time: 0.6221 data: 0.1827 max mem: 22446 +train: [9] [320/400] eta: 0:00:38 lr: 0.000230 loss: 0.5472 (0.5656) grad: 0.0790 (0.0896) time: 0.4409 data: 0.0032 max mem: 22446 +train: [9] [340/400] eta: 0:00:28 lr: 0.000229 loss: 0.5321 (0.5638) grad: 0.0770 (0.0888) time: 0.4594 data: 0.0032 max mem: 22446 +train: [9] [360/400] eta: 0:00:19 lr: 0.000228 loss: 0.5399 (0.5630) grad: 0.0728 (0.0876) time: 0.4635 data: 0.0037 max mem: 22446 +train: [9] [380/400] eta: 0:00:09 lr: 0.000226 loss: 0.5066 (0.5596) grad: 0.0580 (0.0860) time: 0.4602 data: 0.0036 max mem: 22446 +train: [9] [399/400] eta: 0:00:00 lr: 0.000225 loss: 0.5137 (0.5580) grad: 0.0580 (0.0849) time: 0.4610 data: 0.0034 max mem: 22446 +train: [9] Total time: 0:03:10 (0.4761 s / it) +train: [9] Summary: lr: 0.000225 loss: 0.5137 (0.5580) grad: 0.0580 (0.0849) +eval (validation): [9] [ 0/63] eta: 0:03:32 time: 3.3697 data: 3.0627 max mem: 22446 +eval (validation): [9] [20/63] eta: 0:00:22 time: 0.3803 data: 0.0038 max mem: 22446 +eval (validation): [9] [40/63] eta: 0:00:10 time: 0.3564 data: 0.0035 max mem: 22446 +eval (validation): [9] [60/63] eta: 0:00:01 time: 0.3281 data: 0.0033 max mem: 22446 +eval (validation): [9] [62/63] eta: 0:00:00 time: 0.3271 data: 0.0032 max mem: 22446 +eval (validation): [9] Total time: 0:00:25 (0.4066 s / it) +cv: [9] best hparam: (5.1, 1.0) (034) ('034_lr5.1e+00_wd1.0e+00') loss: 0.059 acc: 0.984 f1: 0.981 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__attn/checkpoint-best.pth +train: [10] [ 0/400] eta: 0:23:53 lr: nan time: 3.5841 data: 3.1923 max mem: 22446 +train: [10] [ 20/400] eta: 0:03:49 lr: 0.000224 loss: 0.5161 (0.5246) grad: 0.0554 (0.0580) time: 0.4551 data: 0.0028 max mem: 22446 +train: [10] [ 40/400] eta: 0:03:10 lr: 0.000222 loss: 0.5161 (0.5219) grad: 0.0582 (0.0616) time: 0.4524 data: 0.0034 max mem: 22446 +train: [10] [ 60/400] eta: 0:02:53 lr: 0.000221 loss: 0.5159 (0.5228) grad: 0.0639 (0.0634) time: 0.4664 data: 0.0035 max mem: 22446 +train: [10] [ 80/400] eta: 0:02:38 lr: 0.000220 loss: 0.5288 (0.5244) grad: 0.0625 (0.0626) time: 0.4555 data: 0.0034 max mem: 22446 +train: [10] [100/400] eta: 0:02:25 lr: 0.000218 loss: 0.5273 (0.5235) grad: 0.0606 (0.0629) time: 0.4423 data: 0.0034 max mem: 22446 +train: [10] [120/400] eta: 0:02:14 lr: 0.000217 loss: 0.5283 (0.5247) grad: 0.0560 (0.0620) time: 0.4556 data: 0.0034 max mem: 22446 +train: [10] [140/400] eta: 0:02:04 lr: 0.000215 loss: 0.5229 (0.5237) grad: 0.0559 (0.0623) time: 0.4579 data: 0.0036 max mem: 22446 +train: [10] [160/400] eta: 0:01:53 lr: 0.000214 loss: 0.5195 (0.5231) grad: 0.0662 (0.0627) time: 0.4454 data: 0.0035 max mem: 22446 +train: [10] [180/400] eta: 0:01:43 lr: 0.000213 loss: 0.5104 (0.5213) grad: 0.0662 (0.0635) time: 0.4490 data: 0.0036 max mem: 22446 +train: [10] [200/400] eta: 0:01:33 lr: 0.000211 loss: 0.5086 (0.5210) grad: 0.0647 (0.0633) time: 0.4375 data: 0.0036 max mem: 22446 +train: [10] [220/400] eta: 0:01:23 lr: 0.000210 loss: 0.5079 (0.5193) grad: 0.0623 (0.0632) time: 0.4416 data: 0.0035 max mem: 22446 +train: [10] [240/400] eta: 0:01:14 lr: 0.000208 loss: 0.5046 (0.5187) grad: 0.0647 (0.0633) time: 0.4389 data: 0.0036 max mem: 22446 +train: [10] [260/400] eta: 0:01:04 lr: 0.000207 loss: 0.5019 (0.5174) grad: 0.0574 (0.0629) time: 0.4449 data: 0.0035 max mem: 22446 +train: [10] [280/400] eta: 0:00:55 lr: 0.000205 loss: 0.5149 (0.5174) grad: 0.0562 (0.0628) time: 0.4453 data: 0.0036 max mem: 22446 +train: [10] [300/400] eta: 0:00:47 lr: 0.000204 loss: 0.5178 (0.5175) grad: 0.0583 (0.0626) time: 0.6082 data: 0.1758 max mem: 22446 +train: [10] [320/400] eta: 0:00:37 lr: 0.000202 loss: 0.5012 (0.5166) grad: 0.0567 (0.0622) time: 0.4304 data: 0.0034 max mem: 22446 +train: [10] [340/400] eta: 0:00:27 lr: 0.000201 loss: 0.4903 (0.5149) grad: 0.0527 (0.0617) time: 0.4410 data: 0.0035 max mem: 22446 +train: [10] [360/400] eta: 0:00:18 lr: 0.000199 loss: 0.5067 (0.5148) grad: 0.0519 (0.0613) time: 0.4478 data: 0.0035 max mem: 22446 +train: [10] [380/400] eta: 0:00:09 lr: 0.000198 loss: 0.5042 (0.5133) grad: 0.0491 (0.0606) time: 0.4422 data: 0.0036 max mem: 22446 +train: [10] [399/400] eta: 0:00:00 lr: 0.000196 loss: 0.4894 (0.5126) grad: 0.0510 (0.0603) time: 0.4529 data: 0.0034 max mem: 22446 +train: [10] Total time: 0:03:05 (0.4637 s / it) +train: [10] Summary: lr: 0.000196 loss: 0.4894 (0.5126) grad: 0.0510 (0.0603) +eval (validation): [10] [ 0/63] eta: 0:03:31 time: 3.3617 data: 3.0899 max mem: 22446 +eval (validation): [10] [20/63] eta: 0:00:20 time: 0.3354 data: 0.0035 max mem: 22446 +eval (validation): [10] [40/63] eta: 0:00:09 time: 0.3477 data: 0.0034 max mem: 22446 +eval (validation): [10] [60/63] eta: 0:00:01 time: 0.3161 data: 0.0032 max mem: 22446 +eval (validation): [10] [62/63] eta: 0:00:00 time: 0.3119 data: 0.0029 max mem: 22446 +eval (validation): [10] Total time: 0:00:24 (0.3854 s / it) +cv: [10] best hparam: (8.3, 1.0) (037) ('037_lr8.3e+00_wd1.0e+00') loss: 0.065 acc: 0.986 f1: 0.983 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__attn/checkpoint-best.pth +train: [11] [ 0/400] eta: 0:22:43 lr: nan time: 3.4096 data: 3.0284 max mem: 22446 +train: [11] [ 20/400] eta: 0:03:45 lr: 0.000195 loss: 0.4773 (0.4888) grad: 0.0503 (0.0512) time: 0.4526 data: 0.0026 max mem: 22446 +train: [11] [ 40/400] eta: 0:03:07 lr: 0.000193 loss: 0.4811 (0.4927) grad: 0.0503 (0.0511) time: 0.4465 data: 0.0036 max mem: 22446 +train: [11] [ 60/400] eta: 0:02:51 lr: 0.000192 loss: 0.4897 (0.4919) grad: 0.0509 (0.0510) time: 0.4711 data: 0.0037 max mem: 22446 +train: [11] [ 80/400] eta: 0:02:38 lr: 0.000190 loss: 0.4854 (0.4871) grad: 0.0512 (0.0510) time: 0.4603 data: 0.0036 max mem: 22446 +train: [11] [100/400] eta: 0:02:25 lr: 0.000189 loss: 0.4865 (0.4912) grad: 0.0497 (0.0518) time: 0.4512 data: 0.0035 max mem: 22446 +train: [11] [120/400] eta: 0:02:14 lr: 0.000187 loss: 0.4849 (0.4885) grad: 0.0513 (0.0522) time: 0.4625 data: 0.0033 max mem: 22446 +train: [11] [140/400] eta: 0:02:04 lr: 0.000186 loss: 0.4768 (0.4894) grad: 0.0513 (0.0519) time: 0.4603 data: 0.0036 max mem: 22446 +train: [11] [160/400] eta: 0:01:53 lr: 0.000184 loss: 0.4797 (0.4870) grad: 0.0512 (0.0518) time: 0.4419 data: 0.0036 max mem: 22446 +train: [11] [180/400] eta: 0:01:43 lr: 0.000183 loss: 0.4922 (0.4883) grad: 0.0510 (0.0521) time: 0.4425 data: 0.0036 max mem: 22446 +train: [11] [200/400] eta: 0:01:33 lr: 0.000181 loss: 0.5024 (0.4892) grad: 0.0510 (0.0523) time: 0.4342 data: 0.0036 max mem: 22446 +train: [11] [220/400] eta: 0:01:23 lr: 0.000180 loss: 0.4930 (0.4900) grad: 0.0520 (0.0523) time: 0.4443 data: 0.0037 max mem: 22446 +train: [11] [240/400] eta: 0:01:14 lr: 0.000178 loss: 0.4930 (0.4899) grad: 0.0511 (0.0522) time: 0.4482 data: 0.0037 max mem: 22446 +train: [11] [260/400] eta: 0:01:04 lr: 0.000177 loss: 0.4931 (0.4900) grad: 0.0507 (0.0522) time: 0.4459 data: 0.0037 max mem: 22446 +train: [11] [280/400] eta: 0:00:55 lr: 0.000175 loss: 0.4740 (0.4888) grad: 0.0481 (0.0519) time: 0.4439 data: 0.0037 max mem: 22446 +train: [11] [300/400] eta: 0:00:47 lr: 0.000174 loss: 0.4703 (0.4882) grad: 0.0465 (0.0519) time: 0.6087 data: 0.1759 max mem: 22446 +train: [11] [320/400] eta: 0:00:37 lr: 0.000172 loss: 0.4639 (0.4870) grad: 0.0483 (0.0515) time: 0.4385 data: 0.0027 max mem: 22446 +train: [11] [340/400] eta: 0:00:28 lr: 0.000170 loss: 0.4665 (0.4861) grad: 0.0472 (0.0513) time: 0.4375 data: 0.0040 max mem: 22446 +train: [11] [360/400] eta: 0:00:18 lr: 0.000169 loss: 0.4792 (0.4857) grad: 0.0474 (0.0513) time: 0.4567 data: 0.0040 max mem: 22446 +train: [11] [380/400] eta: 0:00:09 lr: 0.000167 loss: 0.4797 (0.4853) grad: 0.0469 (0.0510) time: 0.4412 data: 0.0036 max mem: 22446 +train: [11] [399/400] eta: 0:00:00 lr: 0.000166 loss: 0.4748 (0.4846) grad: 0.0460 (0.0510) time: 0.4522 data: 0.0035 max mem: 22446 +train: [11] Total time: 0:03:05 (0.4647 s / it) +train: [11] Summary: lr: 0.000166 loss: 0.4748 (0.4846) grad: 0.0460 (0.0510) +eval (validation): [11] [ 0/63] eta: 0:03:26 time: 3.2725 data: 3.0235 max mem: 22446 +eval (validation): [11] [20/63] eta: 0:00:21 time: 0.3662 data: 0.0038 max mem: 22446 +eval (validation): [11] [40/63] eta: 0:00:09 time: 0.3451 data: 0.0035 max mem: 22446 +eval (validation): [11] [60/63] eta: 0:00:01 time: 0.3240 data: 0.0033 max mem: 22446 +eval (validation): [11] [62/63] eta: 0:00:00 time: 0.3286 data: 0.0033 max mem: 22446 +eval (validation): [11] Total time: 0:00:24 (0.3961 s / it) +cv: [11] best hparam: (16, 1.0) (041) ('041_lr1.6e+01_wd1.0e+00') loss: 0.067 acc: 0.987 f1: 0.985 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__attn/checkpoint-best.pth +train: [12] [ 0/400] eta: 0:22:25 lr: nan time: 3.3630 data: 3.0009 max mem: 22446 +train: [12] [ 20/400] eta: 0:03:46 lr: 0.000164 loss: 0.4379 (0.4503) grad: 0.0471 (0.0501) time: 0.4571 data: 0.0031 max mem: 22446 +train: [12] [ 40/400] eta: 0:03:07 lr: 0.000163 loss: 0.4567 (0.4619) grad: 0.0499 (0.0509) time: 0.4407 data: 0.0034 max mem: 22446 +train: [12] [ 60/400] eta: 0:02:50 lr: 0.000161 loss: 0.4683 (0.4685) grad: 0.0479 (0.0499) time: 0.4679 data: 0.0036 max mem: 22446 +train: [12] [ 80/400] eta: 0:02:37 lr: 0.000160 loss: 0.4826 (0.4723) grad: 0.0462 (0.0501) time: 0.4642 data: 0.0036 max mem: 22446 +train: [12] [100/400] eta: 0:02:24 lr: 0.000158 loss: 0.4759 (0.4712) grad: 0.0458 (0.0496) time: 0.4404 data: 0.0034 max mem: 22446 +train: [12] [120/400] eta: 0:02:13 lr: 0.000156 loss: 0.4637 (0.4691) grad: 0.0456 (0.0496) time: 0.4562 data: 0.0034 max mem: 22446 +train: [12] [140/400] eta: 0:02:03 lr: 0.000155 loss: 0.4553 (0.4677) grad: 0.0456 (0.0495) time: 0.4537 data: 0.0035 max mem: 22446 +train: [12] [160/400] eta: 0:01:52 lr: 0.000153 loss: 0.4567 (0.4659) grad: 0.0477 (0.0494) time: 0.4403 data: 0.0034 max mem: 22446 +train: [12] [180/400] eta: 0:01:42 lr: 0.000152 loss: 0.4599 (0.4657) grad: 0.0472 (0.0492) time: 0.4426 data: 0.0035 max mem: 22446 +train: [12] [200/400] eta: 0:01:33 lr: 0.000150 loss: 0.4744 (0.4660) grad: 0.0469 (0.0493) time: 0.4441 data: 0.0035 max mem: 22446 +train: [12] [220/400] eta: 0:01:23 lr: 0.000149 loss: 0.4677 (0.4653) grad: 0.0472 (0.0490) time: 0.4450 data: 0.0035 max mem: 22446 +train: [12] [240/400] eta: 0:01:13 lr: 0.000147 loss: 0.4545 (0.4648) grad: 0.0472 (0.0490) time: 0.4431 data: 0.0035 max mem: 22446 +train: [12] [260/400] eta: 0:01:04 lr: 0.000145 loss: 0.4534 (0.4638) grad: 0.0485 (0.0488) time: 0.4495 data: 0.0035 max mem: 22446 +train: [12] [280/400] eta: 0:00:55 lr: 0.000144 loss: 0.4564 (0.4639) grad: 0.0467 (0.0487) time: 0.4481 data: 0.0036 max mem: 22446 +train: [12] [300/400] eta: 0:00:47 lr: 0.000142 loss: 0.4564 (0.4635) grad: 0.0454 (0.0483) time: 0.6235 data: 0.1758 max mem: 22446 +train: [12] [320/400] eta: 0:00:37 lr: 0.000141 loss: 0.4541 (0.4629) grad: 0.0422 (0.0480) time: 0.4409 data: 0.0034 max mem: 22446 +train: [12] [340/400] eta: 0:00:28 lr: 0.000139 loss: 0.4443 (0.4614) grad: 0.0428 (0.0477) time: 0.4508 data: 0.0036 max mem: 22446 +train: [12] [360/400] eta: 0:00:18 lr: 0.000138 loss: 0.4404 (0.4605) grad: 0.0441 (0.0475) time: 0.4488 data: 0.0034 max mem: 22446 +train: [12] [380/400] eta: 0:00:09 lr: 0.000136 loss: 0.4414 (0.4600) grad: 0.0449 (0.0473) time: 0.4580 data: 0.0034 max mem: 22446 +train: [12] [399/400] eta: 0:00:00 lr: 0.000134 loss: 0.4585 (0.4602) grad: 0.0449 (0.0472) time: 0.4589 data: 0.0034 max mem: 22446 +train: [12] Total time: 0:03:06 (0.4662 s / it) +train: [12] Summary: lr: 0.000134 loss: 0.4585 (0.4602) grad: 0.0449 (0.0472) +eval (validation): [12] [ 0/63] eta: 0:04:25 time: 4.2074 data: 3.9685 max mem: 22446 +eval (validation): [12] [20/63] eta: 0:00:22 time: 0.3504 data: 0.0054 max mem: 22446 +eval (validation): [12] [40/63] eta: 0:00:09 time: 0.3296 data: 0.0031 max mem: 22446 +eval (validation): [12] [60/63] eta: 0:00:01 time: 0.3417 data: 0.0031 max mem: 22446 +eval (validation): [12] [62/63] eta: 0:00:00 time: 0.3433 data: 0.0034 max mem: 22446 +eval (validation): [12] Total time: 0:00:25 (0.4066 s / it) +cv: [12] best hparam: (22, 1.0) (043) ('043_lr2.2e+01_wd1.0e+00') loss: 0.069 acc: 0.988 f1: 0.984 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__attn/checkpoint-best.pth +train: [13] [ 0/400] eta: 0:22:08 lr: nan time: 3.3213 data: 2.9251 max mem: 22446 +train: [13] [ 20/400] eta: 0:03:43 lr: 0.000133 loss: 0.4591 (0.4539) grad: 0.0464 (0.0484) time: 0.4526 data: 0.0031 max mem: 22446 +train: [13] [ 40/400] eta: 0:03:08 lr: 0.000131 loss: 0.4471 (0.4454) grad: 0.0472 (0.0479) time: 0.4542 data: 0.0035 max mem: 22446 +train: [13] [ 60/400] eta: 0:02:54 lr: 0.000130 loss: 0.4375 (0.4459) grad: 0.0472 (0.0475) time: 0.4903 data: 0.0039 max mem: 22446 +train: [13] [ 80/400] eta: 0:02:40 lr: 0.000128 loss: 0.4438 (0.4467) grad: 0.0441 (0.0465) time: 0.4659 data: 0.0035 max mem: 22446 +train: [13] [100/400] eta: 0:02:26 lr: 0.000127 loss: 0.4476 (0.4486) grad: 0.0447 (0.0463) time: 0.4390 data: 0.0033 max mem: 22446 +train: [13] [120/400] eta: 0:02:16 lr: 0.000125 loss: 0.4448 (0.4484) grad: 0.0457 (0.0461) time: 0.4733 data: 0.0036 max mem: 22446 +train: [13] [140/400] eta: 0:02:04 lr: 0.000124 loss: 0.4507 (0.4491) grad: 0.0438 (0.0462) time: 0.4421 data: 0.0035 max mem: 22446 +train: [13] [160/400] eta: 0:01:54 lr: 0.000122 loss: 0.4464 (0.4487) grad: 0.0456 (0.0460) time: 0.4448 data: 0.0036 max mem: 22446 +train: [13] [180/400] eta: 0:01:43 lr: 0.000120 loss: 0.4464 (0.4492) grad: 0.0456 (0.0459) time: 0.4475 data: 0.0036 max mem: 22446 +train: [13] [200/400] eta: 0:01:34 lr: 0.000119 loss: 0.4470 (0.4482) grad: 0.0446 (0.0459) time: 0.4526 data: 0.0034 max mem: 22446 +train: [13] [220/400] eta: 0:01:24 lr: 0.000117 loss: 0.4477 (0.4495) grad: 0.0476 (0.0462) time: 0.4564 data: 0.0035 max mem: 22446 +train: [13] [240/400] eta: 0:01:14 lr: 0.000116 loss: 0.4403 (0.4474) grad: 0.0476 (0.0462) time: 0.4524 data: 0.0035 max mem: 22446 +train: [13] [260/400] eta: 0:01:05 lr: 0.000114 loss: 0.4254 (0.4454) grad: 0.0427 (0.0460) time: 0.4521 data: 0.0034 max mem: 22446 +train: [13] [280/400] eta: 0:00:55 lr: 0.000113 loss: 0.4267 (0.4449) grad: 0.0435 (0.0461) time: 0.4444 data: 0.0035 max mem: 22446 +train: [13] [300/400] eta: 0:00:47 lr: 0.000111 loss: 0.4267 (0.4443) grad: 0.0447 (0.0462) time: 0.6283 data: 0.1774 max mem: 22446 +train: [13] [320/400] eta: 0:00:37 lr: 0.000110 loss: 0.4318 (0.4436) grad: 0.0462 (0.0461) time: 0.4416 data: 0.0027 max mem: 22446 +train: [13] [340/400] eta: 0:00:28 lr: 0.000108 loss: 0.4420 (0.4431) grad: 0.0444 (0.0458) time: 0.4589 data: 0.0034 max mem: 22446 +train: [13] [360/400] eta: 0:00:18 lr: 0.000107 loss: 0.4358 (0.4424) grad: 0.0409 (0.0455) time: 0.4547 data: 0.0034 max mem: 22446 +train: [13] [380/400] eta: 0:00:09 lr: 0.000105 loss: 0.4369 (0.4427) grad: 0.0417 (0.0455) time: 0.4700 data: 0.0036 max mem: 22446 +train: [13] [399/400] eta: 0:00:00 lr: 0.000104 loss: 0.4369 (0.4426) grad: 0.0443 (0.0455) time: 0.4540 data: 0.0035 max mem: 22446 +train: [13] Total time: 0:03:08 (0.4712 s / it) +train: [13] Summary: lr: 0.000104 loss: 0.4369 (0.4426) grad: 0.0443 (0.0455) +eval (validation): [13] [ 0/63] eta: 0:03:34 time: 3.4085 data: 3.1190 max mem: 22446 +eval (validation): [13] [20/63] eta: 0:00:21 time: 0.3541 data: 0.0029 max mem: 22446 +eval (validation): [13] [40/63] eta: 0:00:09 time: 0.3371 data: 0.0034 max mem: 22446 +eval (validation): [13] [60/63] eta: 0:00:01 time: 0.3279 data: 0.0034 max mem: 22446 +eval (validation): [13] [62/63] eta: 0:00:00 time: 0.3260 data: 0.0033 max mem: 22446 +eval (validation): [13] Total time: 0:00:24 (0.3927 s / it) +cv: [13] best hparam: (8.3, 1.0) (037) ('037_lr8.3e+00_wd1.0e+00') loss: 0.052 acc: 0.987 f1: 0.985 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [14] [ 0/400] eta: 0:22:38 lr: nan time: 3.3958 data: 3.0152 max mem: 22446 +train: [14] [ 20/400] eta: 0:03:44 lr: 0.000102 loss: 0.4325 (0.4380) grad: 0.0439 (0.0450) time: 0.4510 data: 0.0024 max mem: 22446 +train: [14] [ 40/400] eta: 0:03:08 lr: 0.000101 loss: 0.4445 (0.4461) grad: 0.0451 (0.0454) time: 0.4519 data: 0.0035 max mem: 22446 +train: [14] [ 60/400] eta: 0:02:52 lr: 0.000099 loss: 0.4466 (0.4441) grad: 0.0431 (0.0447) time: 0.4738 data: 0.0037 max mem: 22446 +train: [14] [ 80/400] eta: 0:02:38 lr: 0.000098 loss: 0.4317 (0.4408) grad: 0.0438 (0.0447) time: 0.4601 data: 0.0036 max mem: 22446 +train: [14] [100/400] eta: 0:02:25 lr: 0.000096 loss: 0.4306 (0.4414) grad: 0.0447 (0.0444) time: 0.4466 data: 0.0033 max mem: 22446 +train: [14] [120/400] eta: 0:02:15 lr: 0.000095 loss: 0.4498 (0.4423) grad: 0.0423 (0.0442) time: 0.4820 data: 0.0033 max mem: 22446 +train: [14] [140/400] eta: 0:02:04 lr: 0.000093 loss: 0.4504 (0.4423) grad: 0.0438 (0.0445) time: 0.4491 data: 0.0034 max mem: 22446 +train: [14] [160/400] eta: 0:01:54 lr: 0.000092 loss: 0.4317 (0.4404) grad: 0.0448 (0.0445) time: 0.4569 data: 0.0035 max mem: 22446 +train: [14] [180/400] eta: 0:01:44 lr: 0.000090 loss: 0.4319 (0.4400) grad: 0.0457 (0.0448) time: 0.4536 data: 0.0034 max mem: 22446 +train: [14] [200/400] eta: 0:01:34 lr: 0.000089 loss: 0.4319 (0.4393) grad: 0.0447 (0.0446) time: 0.4510 data: 0.0035 max mem: 22446 +train: [14] [220/400] eta: 0:01:24 lr: 0.000088 loss: 0.4291 (0.4375) grad: 0.0423 (0.0445) time: 0.4488 data: 0.0036 max mem: 22446 +train: [14] [240/400] eta: 0:01:14 lr: 0.000086 loss: 0.4376 (0.4376) grad: 0.0439 (0.0446) time: 0.4515 data: 0.0035 max mem: 22446 +train: [14] [260/400] eta: 0:01:05 lr: 0.000085 loss: 0.4330 (0.4368) grad: 0.0440 (0.0447) time: 0.4462 data: 0.0034 max mem: 22446 +train: [14] [280/400] eta: 0:00:55 lr: 0.000083 loss: 0.4201 (0.4361) grad: 0.0455 (0.0448) time: 0.4468 data: 0.0035 max mem: 22446 +train: [14] [300/400] eta: 0:00:47 lr: 0.000082 loss: 0.4244 (0.4358) grad: 0.0450 (0.0449) time: 0.6111 data: 0.1780 max mem: 22446 +train: [14] [320/400] eta: 0:00:37 lr: 0.000081 loss: 0.4269 (0.4358) grad: 0.0450 (0.0448) time: 0.4563 data: 0.0031 max mem: 22446 +train: [14] [340/400] eta: 0:00:28 lr: 0.000079 loss: 0.4311 (0.4361) grad: 0.0428 (0.0447) time: 0.4455 data: 0.0035 max mem: 22446 +train: [14] [360/400] eta: 0:00:18 lr: 0.000078 loss: 0.4275 (0.4356) grad: 0.0428 (0.0447) time: 0.4505 data: 0.0033 max mem: 22446 +train: [14] [380/400] eta: 0:00:09 lr: 0.000076 loss: 0.4275 (0.4356) grad: 0.0428 (0.0447) time: 0.4670 data: 0.0036 max mem: 22446 +train: [14] [399/400] eta: 0:00:00 lr: 0.000075 loss: 0.4292 (0.4353) grad: 0.0423 (0.0446) time: 0.4420 data: 0.0035 max mem: 22446 +train: [14] Total time: 0:03:07 (0.4697 s / it) +train: [14] Summary: lr: 0.000075 loss: 0.4292 (0.4353) grad: 0.0423 (0.0446) +eval (validation): [14] [ 0/63] eta: 0:03:28 time: 3.3100 data: 3.0733 max mem: 22446 +eval (validation): [14] [20/63] eta: 0:00:21 time: 0.3610 data: 0.0038 max mem: 22446 +eval (validation): [14] [40/63] eta: 0:00:09 time: 0.3368 data: 0.0028 max mem: 22446 +eval (validation): [14] [60/63] eta: 0:00:01 time: 0.3248 data: 0.0032 max mem: 22446 +eval (validation): [14] [62/63] eta: 0:00:00 time: 0.3253 data: 0.0032 max mem: 22446 +eval (validation): [14] Total time: 0:00:24 (0.3919 s / it) +cv: [14] best hparam: (8.3, 1.0) (037) ('037_lr8.3e+00_wd1.0e+00') loss: 0.051 acc: 0.988 f1: 0.985 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [15] [ 0/400] eta: 0:21:58 lr: nan time: 3.2971 data: 2.9618 max mem: 22446 +train: [15] [ 20/400] eta: 0:03:38 lr: 0.000074 loss: 0.4303 (0.4411) grad: 0.0433 (0.0436) time: 0.4393 data: 0.0031 max mem: 22446 +train: [15] [ 40/400] eta: 0:03:05 lr: 0.000072 loss: 0.4326 (0.4349) grad: 0.0441 (0.0442) time: 0.4534 data: 0.0036 max mem: 22446 +train: [15] [ 60/400] eta: 0:02:50 lr: 0.000071 loss: 0.4298 (0.4299) grad: 0.0441 (0.0439) time: 0.4701 data: 0.0036 max mem: 22446 +train: [15] [ 80/400] eta: 0:02:37 lr: 0.000070 loss: 0.4094 (0.4281) grad: 0.0424 (0.0435) time: 0.4650 data: 0.0036 max mem: 22446 +train: [15] [100/400] eta: 0:02:25 lr: 0.000068 loss: 0.4166 (0.4245) grad: 0.0422 (0.0435) time: 0.4536 data: 0.0035 max mem: 22446 +train: [15] [120/400] eta: 0:02:14 lr: 0.000067 loss: 0.4206 (0.4262) grad: 0.0422 (0.0438) time: 0.4676 data: 0.0034 max mem: 22446 +train: [15] [140/400] eta: 0:02:04 lr: 0.000066 loss: 0.4381 (0.4276) grad: 0.0434 (0.0439) time: 0.4684 data: 0.0036 max mem: 22446 +train: [15] [160/400] eta: 0:01:54 lr: 0.000064 loss: 0.4209 (0.4259) grad: 0.0447 (0.0440) time: 0.4426 data: 0.0034 max mem: 22446 +train: [15] [180/400] eta: 0:01:43 lr: 0.000063 loss: 0.4220 (0.4274) grad: 0.0450 (0.0443) time: 0.4485 data: 0.0034 max mem: 22446 +train: [15] [200/400] eta: 0:01:34 lr: 0.000062 loss: 0.4271 (0.4270) grad: 0.0417 (0.0441) time: 0.4560 data: 0.0035 max mem: 22446 +train: [15] [220/400] eta: 0:01:24 lr: 0.000061 loss: 0.4199 (0.4270) grad: 0.0417 (0.0440) time: 0.4417 data: 0.0035 max mem: 22446 +train: [15] [240/400] eta: 0:01:14 lr: 0.000059 loss: 0.4210 (0.4260) grad: 0.0440 (0.0441) time: 0.4492 data: 0.0035 max mem: 22446 +train: [15] [260/400] eta: 0:01:05 lr: 0.000058 loss: 0.4180 (0.4260) grad: 0.0440 (0.0441) time: 0.4532 data: 0.0036 max mem: 22446 +train: [15] [280/400] eta: 0:00:55 lr: 0.000057 loss: 0.4184 (0.4258) grad: 0.0429 (0.0440) time: 0.4527 data: 0.0036 max mem: 22446 +train: [15] [300/400] eta: 0:00:47 lr: 0.000056 loss: 0.4198 (0.4260) grad: 0.0425 (0.0439) time: 0.6022 data: 0.1740 max mem: 22446 +train: [15] [320/400] eta: 0:00:37 lr: 0.000054 loss: 0.4217 (0.4255) grad: 0.0441 (0.0440) time: 0.4584 data: 0.0031 max mem: 22446 +train: [15] [340/400] eta: 0:00:28 lr: 0.000053 loss: 0.4217 (0.4259) grad: 0.0446 (0.0440) time: 0.4590 data: 0.0034 max mem: 22446 +train: [15] [360/400] eta: 0:00:18 lr: 0.000052 loss: 0.4223 (0.4267) grad: 0.0441 (0.0440) time: 0.4508 data: 0.0035 max mem: 22446 +train: [15] [380/400] eta: 0:00:09 lr: 0.000051 loss: 0.4493 (0.4277) grad: 0.0427 (0.0440) time: 0.4630 data: 0.0035 max mem: 22446 +train: [15] [399/400] eta: 0:00:00 lr: 0.000050 loss: 0.4287 (0.4275) grad: 0.0427 (0.0440) time: 0.4539 data: 0.0034 max mem: 22446 +train: [15] Total time: 0:03:07 (0.4698 s / it) +train: [15] Summary: lr: 0.000050 loss: 0.4287 (0.4275) grad: 0.0427 (0.0440) +eval (validation): [15] [ 0/63] eta: 0:03:26 time: 3.2779 data: 3.0287 max mem: 22446 +eval (validation): [15] [20/63] eta: 0:00:20 time: 0.3410 data: 0.0043 max mem: 22446 +eval (validation): [15] [40/63] eta: 0:00:09 time: 0.3508 data: 0.0032 max mem: 22446 +eval (validation): [15] [60/63] eta: 0:00:01 time: 0.3231 data: 0.0035 max mem: 22446 +eval (validation): [15] [62/63] eta: 0:00:00 time: 0.3201 data: 0.0033 max mem: 22446 +eval (validation): [15] Total time: 0:00:24 (0.3884 s / it) +cv: [15] best hparam: (22, 1.0) (043) ('043_lr2.2e+01_wd1.0e+00') loss: 0.054 acc: 0.988 f1: 0.986 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__attn/checkpoint-best.pth +train: [16] [ 0/400] eta: 0:22:03 lr: nan time: 3.3100 data: 2.9731 max mem: 22446 +train: [16] [ 20/400] eta: 0:03:39 lr: 0.000048 loss: 0.4184 (0.4279) grad: 0.0458 (0.0468) time: 0.4399 data: 0.0036 max mem: 22446 +train: [16] [ 40/400] eta: 0:03:05 lr: 0.000047 loss: 0.4249 (0.4243) grad: 0.0431 (0.0446) time: 0.4485 data: 0.0032 max mem: 22446 +train: [16] [ 60/400] eta: 0:02:52 lr: 0.000046 loss: 0.4249 (0.4232) grad: 0.0413 (0.0432) time: 0.4975 data: 0.0036 max mem: 22446 +train: [16] [ 80/400] eta: 0:02:38 lr: 0.000045 loss: 0.4154 (0.4226) grad: 0.0403 (0.0427) time: 0.4599 data: 0.0036 max mem: 22446 +train: [16] [100/400] eta: 0:02:26 lr: 0.000044 loss: 0.4076 (0.4195) grad: 0.0411 (0.0425) time: 0.4518 data: 0.0033 max mem: 22446 +train: [16] [120/400] eta: 0:02:15 lr: 0.000043 loss: 0.4065 (0.4197) grad: 0.0428 (0.0430) time: 0.4720 data: 0.0034 max mem: 22446 +train: [16] [140/400] eta: 0:02:04 lr: 0.000042 loss: 0.4280 (0.4216) grad: 0.0453 (0.0433) time: 0.4509 data: 0.0035 max mem: 22446 +train: [16] [160/400] eta: 0:01:54 lr: 0.000041 loss: 0.4223 (0.4202) grad: 0.0433 (0.0434) time: 0.4453 data: 0.0034 max mem: 22446 +train: [16] [180/400] eta: 0:01:44 lr: 0.000040 loss: 0.4114 (0.4213) grad: 0.0432 (0.0436) time: 0.4519 data: 0.0035 max mem: 22446 +train: [16] [200/400] eta: 0:01:34 lr: 0.000039 loss: 0.4186 (0.4208) grad: 0.0443 (0.0438) time: 0.4567 data: 0.0034 max mem: 22446 +train: [16] [220/400] eta: 0:01:24 lr: 0.000038 loss: 0.4202 (0.4212) grad: 0.0433 (0.0437) time: 0.4478 data: 0.0035 max mem: 22446 +train: [16] [240/400] eta: 0:01:14 lr: 0.000036 loss: 0.4240 (0.4218) grad: 0.0435 (0.0442) time: 0.4561 data: 0.0035 max mem: 22446 +train: [16] [260/400] eta: 0:01:05 lr: 0.000035 loss: 0.4227 (0.4211) grad: 0.0445 (0.0442) time: 0.4457 data: 0.0032 max mem: 22446 +train: [16] [280/400] eta: 0:00:55 lr: 0.000034 loss: 0.4265 (0.4216) grad: 0.0431 (0.0442) time: 0.4551 data: 0.0036 max mem: 22446 +train: [16] [300/400] eta: 0:00:47 lr: 0.000033 loss: 0.4266 (0.4211) grad: 0.0454 (0.0443) time: 0.6266 data: 0.1738 max mem: 22446 +train: [16] [320/400] eta: 0:00:37 lr: 0.000032 loss: 0.4173 (0.4218) grad: 0.0456 (0.0443) time: 0.4429 data: 0.0026 max mem: 22446 +train: [16] [340/400] eta: 0:00:28 lr: 0.000031 loss: 0.4247 (0.4216) grad: 0.0426 (0.0442) time: 0.4474 data: 0.0035 max mem: 22446 +train: [16] [360/400] eta: 0:00:18 lr: 0.000031 loss: 0.4282 (0.4226) grad: 0.0425 (0.0442) time: 0.4715 data: 0.0037 max mem: 22446 +train: [16] [380/400] eta: 0:00:09 lr: 0.000030 loss: 0.4222 (0.4220) grad: 0.0408 (0.0441) time: 0.4704 data: 0.0036 max mem: 22446 +train: [16] [399/400] eta: 0:00:00 lr: 0.000029 loss: 0.4114 (0.4220) grad: 0.0408 (0.0440) time: 0.4509 data: 0.0035 max mem: 22446 +train: [16] Total time: 0:03:08 (0.4719 s / it) +train: [16] Summary: lr: 0.000029 loss: 0.4114 (0.4220) grad: 0.0408 (0.0440) +eval (validation): [16] [ 0/63] eta: 0:03:20 time: 3.1902 data: 2.9543 max mem: 22446 +eval (validation): [16] [20/63] eta: 0:00:20 time: 0.3464 data: 0.0039 max mem: 22446 +eval (validation): [16] [40/63] eta: 0:00:09 time: 0.3474 data: 0.0028 max mem: 22446 +eval (validation): [16] [60/63] eta: 0:00:01 time: 0.3322 data: 0.0031 max mem: 22446 +eval (validation): [16] [62/63] eta: 0:00:00 time: 0.3316 data: 0.0034 max mem: 22446 +eval (validation): [16] Total time: 0:00:24 (0.3909 s / it) +cv: [16] best hparam: (8.3, 1.0) (037) ('037_lr8.3e+00_wd1.0e+00') loss: 0.051 acc: 0.988 f1: 0.985 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [17] [ 0/400] eta: 0:22:18 lr: nan time: 3.3462 data: 3.0036 max mem: 22446 +train: [17] [ 20/400] eta: 0:03:44 lr: 0.000028 loss: 0.4110 (0.4200) grad: 0.0404 (0.0420) time: 0.4536 data: 0.0033 max mem: 22446 +train: [17] [ 40/400] eta: 0:03:09 lr: 0.000027 loss: 0.4156 (0.4177) grad: 0.0408 (0.0423) time: 0.4587 data: 0.0034 max mem: 22446 +train: [17] [ 60/400] eta: 0:02:53 lr: 0.000026 loss: 0.4065 (0.4143) grad: 0.0425 (0.0428) time: 0.4743 data: 0.0034 max mem: 22446 +train: [17] [ 80/400] eta: 0:02:39 lr: 0.000025 loss: 0.4151 (0.4176) grad: 0.0433 (0.0432) time: 0.4641 data: 0.0037 max mem: 22446 +train: [17] [100/400] eta: 0:02:27 lr: 0.000024 loss: 0.4198 (0.4199) grad: 0.0447 (0.0439) time: 0.4600 data: 0.0036 max mem: 22446 +train: [17] [120/400] eta: 0:02:16 lr: 0.000023 loss: 0.4155 (0.4198) grad: 0.0439 (0.0437) time: 0.4627 data: 0.0034 max mem: 22446 +train: [17] [140/400] eta: 0:02:05 lr: 0.000023 loss: 0.4178 (0.4202) grad: 0.0415 (0.0434) time: 0.4698 data: 0.0036 max mem: 22446 +train: [17] [160/400] eta: 0:01:55 lr: 0.000022 loss: 0.4135 (0.4192) grad: 0.0411 (0.0432) time: 0.4471 data: 0.0035 max mem: 22446 +train: [17] [180/400] eta: 0:01:44 lr: 0.000021 loss: 0.4057 (0.4186) grad: 0.0408 (0.0431) time: 0.4507 data: 0.0034 max mem: 22446 +train: [17] [200/400] eta: 0:01:34 lr: 0.000020 loss: 0.3995 (0.4166) grad: 0.0415 (0.0432) time: 0.4560 data: 0.0035 max mem: 22446 +train: [17] [220/400] eta: 0:01:24 lr: 0.000019 loss: 0.4144 (0.4176) grad: 0.0437 (0.0434) time: 0.4511 data: 0.0035 max mem: 22446 +train: [17] [240/400] eta: 0:01:15 lr: 0.000019 loss: 0.4191 (0.4171) grad: 0.0447 (0.0434) time: 0.4492 data: 0.0034 max mem: 22446 +train: [17] [260/400] eta: 0:01:05 lr: 0.000018 loss: 0.4168 (0.4178) grad: 0.0447 (0.0435) time: 0.4568 data: 0.0034 max mem: 22446 +train: [17] [280/400] eta: 0:00:56 lr: 0.000017 loss: 0.4156 (0.4175) grad: 0.0455 (0.0437) time: 0.4583 data: 0.0035 max mem: 22446 +train: [17] [300/400] eta: 0:00:47 lr: 0.000016 loss: 0.4152 (0.4180) grad: 0.0445 (0.0436) time: 0.6360 data: 0.1776 max mem: 22446 +train: [17] [320/400] eta: 0:00:38 lr: 0.000016 loss: 0.4143 (0.4180) grad: 0.0419 (0.0436) time: 0.4443 data: 0.0032 max mem: 22446 +train: [17] [340/400] eta: 0:00:28 lr: 0.000015 loss: 0.4063 (0.4175) grad: 0.0430 (0.0436) time: 0.4498 data: 0.0033 max mem: 22446 +train: [17] [360/400] eta: 0:00:18 lr: 0.000014 loss: 0.3984 (0.4170) grad: 0.0424 (0.0436) time: 0.4525 data: 0.0033 max mem: 22446 +train: [17] [380/400] eta: 0:00:09 lr: 0.000014 loss: 0.4296 (0.4181) grad: 0.0417 (0.0435) time: 0.4707 data: 0.0037 max mem: 22446 +train: [17] [399/400] eta: 0:00:00 lr: 0.000013 loss: 0.4296 (0.4183) grad: 0.0430 (0.0435) time: 0.4543 data: 0.0035 max mem: 22446 +train: [17] Total time: 0:03:09 (0.4735 s / it) +train: [17] Summary: lr: 0.000013 loss: 0.4296 (0.4183) grad: 0.0430 (0.0435) +eval (validation): [17] [ 0/63] eta: 0:03:32 time: 3.3750 data: 3.0841 max mem: 22446 +eval (validation): [17] [20/63] eta: 0:00:20 time: 0.3371 data: 0.0042 max mem: 22446 +eval (validation): [17] [40/63] eta: 0:00:09 time: 0.3426 data: 0.0031 max mem: 22446 +eval (validation): [17] [60/63] eta: 0:00:01 time: 0.3425 data: 0.0034 max mem: 22446 +eval (validation): [17] [62/63] eta: 0:00:00 time: 0.3418 data: 0.0034 max mem: 22446 +eval (validation): [17] Total time: 0:00:24 (0.3938 s / it) +cv: [17] best hparam: (22, 1.0) (043) ('043_lr2.2e+01_wd1.0e+00') loss: 0.053 acc: 0.988 f1: 0.986 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__attn/checkpoint-best.pth +train: [18] [ 0/400] eta: 0:22:26 lr: nan time: 3.3656 data: 3.0285 max mem: 22446 +train: [18] [ 20/400] eta: 0:03:42 lr: 0.000012 loss: 0.4154 (0.4218) grad: 0.0446 (0.0450) time: 0.4475 data: 0.0027 max mem: 22446 +train: [18] [ 40/400] eta: 0:03:09 lr: 0.000012 loss: 0.4260 (0.4269) grad: 0.0443 (0.0452) time: 0.4612 data: 0.0034 max mem: 22446 +train: [18] [ 60/400] eta: 0:02:53 lr: 0.000011 loss: 0.4228 (0.4239) grad: 0.0443 (0.0448) time: 0.4838 data: 0.0035 max mem: 22446 +train: [18] [ 80/400] eta: 0:02:40 lr: 0.000011 loss: 0.4190 (0.4214) grad: 0.0422 (0.0437) time: 0.4717 data: 0.0034 max mem: 22446 +train: [18] [100/400] eta: 0:02:27 lr: 0.000010 loss: 0.4090 (0.4190) grad: 0.0422 (0.0438) time: 0.4469 data: 0.0033 max mem: 22446 +train: [18] [120/400] eta: 0:02:16 lr: 0.000009 loss: 0.4014 (0.4169) grad: 0.0426 (0.0436) time: 0.4773 data: 0.0034 max mem: 22446 +train: [18] [140/400] eta: 0:02:06 lr: 0.000009 loss: 0.4199 (0.4189) grad: 0.0428 (0.0440) time: 0.4672 data: 0.0034 max mem: 22446 +train: [18] [160/400] eta: 0:01:55 lr: 0.000008 loss: 0.4290 (0.4192) grad: 0.0431 (0.0439) time: 0.4476 data: 0.0036 max mem: 22446 +fMRI foundation model probe eval +version: 0.1.dev65+g4003a1397 +train: [18] [180/400] eta: 0:01:45 lr: 0.000008 loss: 0.4202 (0.4181) grad: 0.0425 (0.0438) time: 0.4517 data: 0.0035 max mem: 22446 +sha: 6c01b606db98add5848cecd23e5d599250c0bf86, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-02-24 23:30:02 +config: +output_root: experiments/decoders/output +name_prefix: eval_probe +remote_root: null +notes: decoder ablations crossreg_reg4; eval v2 (hcpya_task21 patch attn) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +dataset_kwargs: {} +classifier_kwargs: + embed_dim: null + dropout: 0.0 + xavier_init: false + norm: false +lr_scale_grid: +- 0.02 +- 0.023 +- 0.028 +- 0.033 +- 0.038 +- 0.045 +- 0.053 +- 0.062 +- 0.074 +- 0.087 +- 0.1 +- 0.12 +- 0.14 +- 0.17 +- 0.2 +- 0.23 +- 0.27 +- 0.32 +- 0.38 +- 0.44 +- 0.52 +- 0.61 +- 0.72 +- 0.85 +- 1 +- 1.2 +- 1.4 +- 1.6 +- 1.9 +- 2.3 +- 2.7 +- 3.1 +- 3.7 +- 4.3 +- 5.1 +- 6 +- 7.1 +- 8.3 +- 9.8 +- 12 +- 14 +- 16 +- 19 +- 22 +- 26 +- 31 +- 36 +- 43 +- 50 +wd_scale_grid: +- 1.0 +num_workers: 8 +prefetch_factor: null +balanced_sampling: false +epochs: 20 +steps_per_epoch: 200 +batch_size: 64 +accum_iter: 2 +lr: 0.0003 +warmup_epochs: 5 +no_decay: false +weight_decay: 0.05 +clip_grad: 1.0 +metrics: +- acc +- f1 +cv_metric: acc +early_stopping: true +amp: true +device: cuda +seed: 4466 +debug: false +wandb: false +wandb_entity: null +wandb_project: fMRI-fm-eval +name: decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__attn +model: flat_mae +representation: patch +classifier: attn +dataset: hcpya_task21 +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__attn +remote_dir: null + +creating frozen backbone model: flat_mae +train: [18] [200/400] eta: 0:01:34 lr: 0.000007 loss: 0.4108 (0.4167) grad: 0.0429 (0.0437) time: 0.4444 data: 0.0034 max mem: 22446 +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=False, reg_tokens=4, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: hcpya_task21 (flat) +train: [18] [220/400] eta: 0:01:24 lr: 0.000007 loss: 0.4129 (0.4170) grad: 0.0424 (0.0437) time: 0.4492 data: 0.0034 max mem: 22446 +train: [18] [240/400] eta: 0:01:15 lr: 0.000006 loss: 0.4170 (0.4174) grad: 0.0403 (0.0436) time: 0.4503 data: 0.0034 max mem: 22446 +train: [18] [260/400] eta: 0:01:05 lr: 0.000006 loss: 0.4158 (0.4176) grad: 0.0426 (0.0437) time: 0.4504 data: 0.0036 max mem: 22446 +train: [18] [280/400] eta: 0:00:56 lr: 0.000006 loss: 0.4075 (0.4164) grad: 0.0428 (0.0436) time: 0.4469 data: 0.0036 max mem: 22446 +train: [18] [300/400] eta: 0:00:47 lr: 0.000005 loss: 0.4045 (0.4157) grad: 0.0428 (0.0436) time: 0.6157 data: 0.1796 max mem: 22446 +train: [18] [320/400] eta: 0:00:38 lr: 0.000005 loss: 0.4080 (0.4156) grad: 0.0422 (0.0435) time: 0.4581 data: 0.0039 max mem: 22446 +train (n=18999): +HFDataset( + dataset=Dataset({ + features: ['sub', 'task', 'cond', 'cond_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 18999 +}), + labels=[ 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20], + counts=[ 832 1248 3201 1660 832 832 832 832 832 1248 1247 1243 832 416 + 416 416 416 416 416 416 416] +) + +validation (n=4032): +HFDataset( + dataset=Dataset({ + features: ['sub', 'task', 'cond', 'cond_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 4032 +}), + labels=[ 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20], + counts=[176 264 688 352 176 176 176 176 176 264 264 264 176 88 88 88 88 88 + 88 88 88] +) + +test (n=5040): +HFDataset( + dataset=Dataset({ + features: ['sub', 'task', 'cond', 'cond_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 5040 +}), + labels=[ 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20], + counts=[220 330 860 440 220 220 220 220 220 330 330 330 220 110 110 110 110 110 + 110 110 110] +) + +running backbone on example batch to get embedding dim +embedding feature dim (patch): 768 +initializing sweep of classifier heads +classifiers: +ModuleList( + (0-48): 49 x AttnPoolClassifier( + (kv): Linear(in_features=768, out_features=1536, bias=True) + (linear): Linear(in_features=768, out_features=21, bias=True) + ) +) +classifier params (train): 58.7M (58.7M) +setting up optimizer +total batch size: 128 = 64 bs per gpu x 2 accum +lr: 3.00e-04 +full schedule: epochs = 20 (steps = 4000) (decay = True) +warmup: epochs = 5 (steps = 1000) +loaded model and optimizer state, resuming training from 18 +start training for 20 epochs +train: [18] [340/400] eta: 0:00:28 lr: 0.000004 loss: 0.4213 (0.4168) grad: 0.0423 (0.0435) time: 0.4510 data: 0.0033 max mem: 22446 +train: [18] [ 0/400] eta: 0:24:03 lr: nan time: 3.6089 data: 2.9817 max mem: 22188 +train: [18] [360/400] eta: 0:00:18 lr: 0.000004 loss: 0.4215 (0.4169) grad: 0.0432 (0.0435) time: 0.4510 data: 0.0037 max mem: 22446 +train: [18] [ 20/400] eta: 0:03:45 lr: 0.000012 loss: 0.4111 (0.4251) grad: 0.0429 (0.0435) time: 0.4431 data: 0.0046 max mem: 22444 +train: [18] [380/400] eta: 0:00:09 lr: 0.000004 loss: 0.4193 (0.4169) grad: 0.0425 (0.0435) time: 0.4488 data: 0.0038 max mem: 22446 +train: [18] [ 40/400] eta: 0:03:10 lr: 0.000012 loss: 0.4158 (0.4205) grad: 0.0434 (0.0440) time: 0.4630 data: 0.0038 max mem: 22444 +train: [18] [399/400] eta: 0:00:00 lr: 0.000003 loss: 0.4199 (0.4174) grad: 0.0425 (0.0434) time: 0.4493 data: 0.0036 max mem: 22446 +train: [18] Total time: 0:03:08 (0.4711 s / it) +train: [18] Summary: lr: 0.000003 loss: 0.4199 (0.4174) grad: 0.0425 (0.0434) +train: [18] [ 60/400] eta: 0:02:52 lr: 0.000011 loss: 0.4158 (0.4178) grad: 0.0419 (0.0430) time: 0.4581 data: 0.0042 max mem: 22444 +eval (validation): [18] [ 0/63] eta: 0:03:31 time: 3.3588 data: 3.1199 max mem: 22446 +train: [18] [ 80/400] eta: 0:02:37 lr: 0.000011 loss: 0.4128 (0.4175) grad: 0.0419 (0.0438) time: 0.4499 data: 0.0043 max mem: 22444 +eval (validation): [18] [20/63] eta: 0:00:20 time: 0.3289 data: 0.0034 max mem: 22446 +eval (validation): [18] [40/63] eta: 0:00:09 time: 0.3646 data: 0.0028 max mem: 22446 +train: [18] [100/400] eta: 0:02:25 lr: 0.000010 loss: 0.4111 (0.4189) grad: 0.0439 (0.0436) time: 0.4531 data: 0.0040 max mem: 22444 +eval (validation): [18] [60/63] eta: 0:00:01 time: 0.3269 data: 0.0034 max mem: 22446 +eval (validation): [18] [62/63] eta: 0:00:00 time: 0.3273 data: 0.0033 max mem: 22446 +eval (validation): [18] Total time: 0:00:24 (0.3923 s / it) +cv: [18] best hparam: (22, 1.0) (043) ('043_lr2.2e+01_wd1.0e+00') loss: 0.052 acc: 0.988 f1: 0.986 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [18] [120/400] eta: 0:02:14 lr: 0.000009 loss: 0.4111 (0.4170) grad: 0.0439 (0.0439) time: 0.4525 data: 0.0041 max mem: 22444 +train: [19] [ 0/400] eta: 0:22:50 lr: nan time: 3.4273 data: 3.0393 max mem: 22446 +train: [18] [140/400] eta: 0:02:03 lr: 0.000009 loss: 0.4085 (0.4166) grad: 0.0439 (0.0439) time: 0.4559 data: 0.0042 max mem: 22444 +train: [19] [ 20/400] eta: 0:03:44 lr: 0.000003 loss: 0.4183 (0.4207) grad: 0.0394 (0.0396) time: 0.4489 data: 0.0028 max mem: 22446 +train: [18] [160/400] eta: 0:01:53 lr: 0.000008 loss: 0.4101 (0.4155) grad: 0.0430 (0.0440) time: 0.4599 data: 0.0041 max mem: 22444 +train: [19] [ 40/400] eta: 0:03:07 lr: 0.000003 loss: 0.4120 (0.4132) grad: 0.0394 (0.0401) time: 0.4498 data: 0.0036 max mem: 22446 +train: [18] [180/400] eta: 0:01:43 lr: 0.000008 loss: 0.4095 (0.4161) grad: 0.0424 (0.0439) time: 0.4617 data: 0.0041 max mem: 22444 +train: [19] [ 60/400] eta: 0:02:53 lr: 0.000002 loss: 0.4014 (0.4116) grad: 0.0414 (0.0414) time: 0.4908 data: 0.0036 max mem: 22446 +train: [18] [200/400] eta: 0:01:34 lr: 0.000007 loss: 0.4099 (0.4161) grad: 0.0420 (0.0438) time: 0.4510 data: 0.0042 max mem: 22444 +train: [19] [ 80/400] eta: 0:02:41 lr: 0.000002 loss: 0.4021 (0.4130) grad: 0.0432 (0.0420) time: 0.4822 data: 0.0036 max mem: 22446 +train: [18] [220/400] eta: 0:01:24 lr: 0.000007 loss: 0.4154 (0.4165) grad: 0.0465 (0.0441) time: 0.4509 data: 0.0043 max mem: 22444 +train: [19] [100/400] eta: 0:02:28 lr: 0.000002 loss: 0.4071 (0.4134) grad: 0.0432 (0.0423) time: 0.4585 data: 0.0035 max mem: 22446 +train: [18] [240/400] eta: 0:01:14 lr: 0.000006 loss: 0.4224 (0.4170) grad: 0.0470 (0.0443) time: 0.4571 data: 0.0043 max mem: 22444 +train: [19] [120/400] eta: 0:02:17 lr: 0.000002 loss: 0.4198 (0.4143) grad: 0.0409 (0.0425) time: 0.4617 data: 0.0034 max mem: 22446 +train: [18] [260/400] eta: 0:01:05 lr: 0.000006 loss: 0.4191 (0.4171) grad: 0.0424 (0.0441) time: 0.4586 data: 0.0041 max mem: 22444 +train: [19] [140/400] eta: 0:02:07 lr: 0.000001 loss: 0.4229 (0.4164) grad: 0.0440 (0.0431) time: 0.4858 data: 0.0035 max mem: 22446 +train: [18] [280/400] eta: 0:00:56 lr: 0.000006 loss: 0.4191 (0.4173) grad: 0.0418 (0.0440) time: 0.4622 data: 0.0040 max mem: 22444 +train: [19] [160/400] eta: 0:01:56 lr: 0.000001 loss: 0.4229 (0.4167) grad: 0.0462 (0.0435) time: 0.4532 data: 0.0037 max mem: 22446 +train: [18] [300/400] eta: 0:00:47 lr: 0.000005 loss: 0.4075 (0.4169) grad: 0.0443 (0.0440) time: 0.6117 data: 0.1726 max mem: 22444 +train: [19] [180/400] eta: 0:01:45 lr: 0.000001 loss: 0.4199 (0.4177) grad: 0.0427 (0.0431) time: 0.4487 data: 0.0034 max mem: 22446 +train: [18] [320/400] eta: 0:00:38 lr: 0.000005 loss: 0.4069 (0.4169) grad: 0.0445 (0.0441) time: 0.4644 data: 0.0035 max mem: 22444 +train: [19] [200/400] eta: 0:01:35 lr: 0.000001 loss: 0.4304 (0.4194) grad: 0.0412 (0.0431) time: 0.4593 data: 0.0035 max mem: 22446 +train: [18] [340/400] eta: 0:00:28 lr: 0.000004 loss: 0.4266 (0.4184) grad: 0.0427 (0.0441) time: 0.4646 data: 0.0042 max mem: 22444 +train: [19] [220/400] eta: 0:01:25 lr: 0.000001 loss: 0.4304 (0.4205) grad: 0.0413 (0.0432) time: 0.4554 data: 0.0036 max mem: 22446 +train: [18] [360/400] eta: 0:00:18 lr: 0.000004 loss: 0.4266 (0.4190) grad: 0.0433 (0.0441) time: 0.4552 data: 0.0043 max mem: 22444 +train: [19] [240/400] eta: 0:01:15 lr: 0.000001 loss: 0.4250 (0.4217) grad: 0.0429 (0.0432) time: 0.4556 data: 0.0037 max mem: 22446 +train: [18] [380/400] eta: 0:00:09 lr: 0.000004 loss: 0.4220 (0.4193) grad: 0.0439 (0.0441) time: 0.4610 data: 0.0042 max mem: 22444 +train: [19] [260/400] eta: 0:01:06 lr: 0.000000 loss: 0.4168 (0.4206) grad: 0.0413 (0.0433) time: 0.4491 data: 0.0035 max mem: 22446 +train: [18] [399/400] eta: 0:00:00 lr: 0.000003 loss: 0.4151 (0.4188) grad: 0.0414 (0.0439) time: 0.4643 data: 0.0043 max mem: 22444 +train: [18] Total time: 0:03:09 (0.4734 s / it) +train: [18] Summary: lr: 0.000003 loss: 0.4151 (0.4188) grad: 0.0414 (0.0439) +train: [19] [280/400] eta: 0:00:56 lr: 0.000000 loss: 0.4043 (0.4202) grad: 0.0414 (0.0433) time: 0.4564 data: 0.0034 max mem: 22446 +eval (validation): [18] [ 0/63] eta: 0:03:23 time: 3.2260 data: 2.9783 max mem: 22444 +eval (validation): [18] [20/63] eta: 0:00:20 time: 0.3505 data: 0.0028 max mem: 22444 +train: [19] [300/400] eta: 0:00:48 lr: 0.000000 loss: 0.4204 (0.4208) grad: 0.0416 (0.0433) time: 0.6086 data: 0.1706 max mem: 22446 +eval (validation): [18] [40/63] eta: 0:00:10 time: 0.3817 data: 0.0036 max mem: 22444 +train: [19] [320/400] eta: 0:00:38 lr: 0.000000 loss: 0.4258 (0.4215) grad: 0.0422 (0.0434) time: 0.4412 data: 0.0034 max mem: 22446 +eval (validation): [18] [60/63] eta: 0:00:01 time: 0.3481 data: 0.0037 max mem: 22444 +eval (validation): [18] [62/63] eta: 0:00:00 time: 0.3475 data: 0.0037 max mem: 22444 +eval (validation): [18] Total time: 0:00:25 (0.4106 s / it) +cv: [18] best hparam: (22, 1.0) (043) ('043_lr2.2e+01_wd1.0e+00') loss: 0.052 acc: 0.988 f1: 0.986 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [19] [340/400] eta: 0:00:28 lr: 0.000000 loss: 0.4258 (0.4215) grad: 0.0438 (0.0434) time: 0.4556 data: 0.0032 max mem: 22446 +train: [19] [ 0/400] eta: 0:22:59 lr: nan time: 3.4479 data: 3.0199 max mem: 22444 +train: [19] [360/400] eta: 0:00:19 lr: 0.000000 loss: 0.4256 (0.4216) grad: 0.0419 (0.0433) time: 0.4527 data: 0.0037 max mem: 22446 +train: [19] [ 20/400] eta: 0:03:50 lr: 0.000003 loss: 0.4145 (0.4190) grad: 0.0408 (0.0423) time: 0.4636 data: 0.0036 max mem: 22444 +train: [19] [380/400] eta: 0:00:09 lr: 0.000000 loss: 0.4254 (0.4219) grad: 0.0422 (0.0434) time: 0.4591 data: 0.0037 max mem: 22446 +train: [19] [ 40/400] eta: 0:03:13 lr: 0.000003 loss: 0.4259 (0.4231) grad: 0.0423 (0.0431) time: 0.4671 data: 0.0039 max mem: 22444 +train: [19] [399/400] eta: 0:00:00 lr: 0.000000 loss: 0.4222 (0.4220) grad: 0.0431 (0.0434) time: 0.4446 data: 0.0034 max mem: 22446 +train: [19] Total time: 0:03:09 (0.4736 s / it) +train: [19] Summary: lr: 0.000000 loss: 0.4222 (0.4220) grad: 0.0431 (0.0434) +eval (validation): [19] [ 0/63] eta: 0:03:26 time: 3.2833 data: 3.0410 max mem: 22446 +train: [19] [ 60/400] eta: 0:02:53 lr: 0.000002 loss: 0.4271 (0.4206) grad: 0.0424 (0.0426) time: 0.4575 data: 0.0043 max mem: 22444 +eval (validation): [19] [20/63] eta: 0:00:20 time: 0.3368 data: 0.0046 max mem: 22446 +train: [19] [ 80/400] eta: 0:02:39 lr: 0.000002 loss: 0.4112 (0.4171) grad: 0.0402 (0.0420) time: 0.4522 data: 0.0041 max mem: 22444 +eval (validation): [19] [40/63] eta: 0:00:09 time: 0.3404 data: 0.0029 max mem: 22446 +train: [19] [100/400] eta: 0:02:26 lr: 0.000002 loss: 0.4226 (0.4198) grad: 0.0418 (0.0426) time: 0.4517 data: 0.0044 max mem: 22444 +eval (validation): [19] [60/63] eta: 0:00:01 time: 0.3320 data: 0.0033 max mem: 22446 +eval (validation): [19] [62/63] eta: 0:00:00 time: 0.3300 data: 0.0032 max mem: 22446 +eval (validation): [19] Total time: 0:00:24 (0.3870 s / it) +cv: [19] best hparam: (22, 1.0) (043) ('043_lr2.2e+01_wd1.0e+00') loss: 0.052 acc: 0.988 f1: 0.986 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +evaluating last checkpoint: experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +eval model info: +{"score": 0.9878472222222222, "hparam": [22, 1.0], "hparam_id": 43, "epoch": 19, "is_best": false, "best_score": 0.9880952380952381} +train: [19] [120/400] eta: 0:02:14 lr: 0.000002 loss: 0.4233 (0.4212) grad: 0.0433 (0.0428) time: 0.4466 data: 0.0043 max mem: 22444 +eval (train): [20] [ 0/297] eta: 0:14:39 time: 2.9612 data: 2.6951 max mem: 22446 +eval (train): [20] [ 20/297] eta: 0:02:12 time: 0.3525 data: 0.0035 max mem: 22446 +train: [19] [140/400] eta: 0:02:04 lr: 0.000001 loss: 0.4057 (0.4174) grad: 0.0424 (0.0428) time: 0.4549 data: 0.0040 max mem: 22444 +eval (train): [20] [ 40/297] eta: 0:01:44 time: 0.3354 data: 0.0035 max mem: 22446 +train: [19] [160/400] eta: 0:01:54 lr: 0.000001 loss: 0.4106 (0.4197) grad: 0.0424 (0.0429) time: 0.4617 data: 0.0042 max mem: 22444 +eval (train): [20] [ 60/297] eta: 0:01:31 time: 0.3427 data: 0.0036 max mem: 22446 +train: [19] [180/400] eta: 0:01:43 lr: 0.000001 loss: 0.4215 (0.4203) grad: 0.0424 (0.0429) time: 0.4466 data: 0.0042 max mem: 22444 +eval (train): [20] [ 80/297] eta: 0:01:23 time: 0.3756 data: 0.0035 max mem: 22446 +eval (train): [20] [100/297] eta: 0:01:14 time: 0.3519 data: 0.0038 max mem: 22446 +train: [19] [200/400] eta: 0:01:34 lr: 0.000001 loss: 0.4151 (0.4201) grad: 0.0424 (0.0431) time: 0.4548 data: 0.0043 max mem: 22444 +eval (train): [20] [120/297] eta: 0:01:06 time: 0.3763 data: 0.0036 max mem: 22446 +train: [19] [220/400] eta: 0:01:24 lr: 0.000001 loss: 0.4185 (0.4195) grad: 0.0431 (0.0431) time: 0.4563 data: 0.0044 max mem: 22444 +eval (train): [20] [140/297] eta: 0:00:58 time: 0.3493 data: 0.0035 max mem: 22446 +train: [19] [240/400] eta: 0:01:14 lr: 0.000001 loss: 0.4244 (0.4206) grad: 0.0431 (0.0429) time: 0.4604 data: 0.0044 max mem: 22444 +eval (train): [20] [160/297] eta: 0:00:50 time: 0.3575 data: 0.0033 max mem: 22446 +train: [19] [260/400] eta: 0:01:05 lr: 0.000000 loss: 0.4218 (0.4190) grad: 0.0415 (0.0429) time: 0.4571 data: 0.0042 max mem: 22444 +eval (train): [20] [180/297] eta: 0:00:43 time: 0.3605 data: 0.0035 max mem: 22446 +eval (train): [20] [200/297] eta: 0:00:35 time: 0.3423 data: 0.0035 max mem: 22446 +train: [19] [280/400] eta: 0:00:56 lr: 0.000000 loss: 0.4048 (0.4187) grad: 0.0415 (0.0430) time: 0.4610 data: 0.0043 max mem: 22444 +eval (train): [20] [220/297] eta: 0:00:28 time: 0.3444 data: 0.0036 max mem: 22446 +eval (train): [20] [240/297] eta: 0:00:20 time: 0.3428 data: 0.0033 max mem: 22446 +train: [19] [300/400] eta: 0:00:47 lr: 0.000000 loss: 0.4210 (0.4196) grad: 0.0425 (0.0431) time: 0.6324 data: 0.1788 max mem: 22444 +eval (train): [20] [260/297] eta: 0:00:13 time: 0.3387 data: 0.0034 max mem: 22446 +train: [19] [320/400] eta: 0:00:38 lr: 0.000000 loss: 0.4240 (0.4198) grad: 0.0431 (0.0432) time: 0.4712 data: 0.0035 max mem: 22444 +eval (train): [20] [280/297] eta: 0:00:06 time: 0.3393 data: 0.0034 max mem: 22446 +eval (train): [20] [296/297] eta: 0:00:00 time: 0.3180 data: 0.0033 max mem: 22446 +eval (train): [20] Total time: 0:01:46 (0.3597 s / it) +train: [19] [340/400] eta: 0:00:28 lr: 0.000000 loss: 0.4236 (0.4201) grad: 0.0459 (0.0434) time: 0.4703 data: 0.0042 max mem: 22444 +eval (validation): [20] [ 0/63] eta: 0:03:00 time: 2.8707 data: 2.6445 max mem: 22446 +train: [19] [360/400] eta: 0:00:19 lr: 0.000000 loss: 0.4236 (0.4211) grad: 0.0428 (0.0434) time: 0.4615 data: 0.0043 max mem: 22444 +eval (validation): [20] [20/63] eta: 0:00:19 time: 0.3411 data: 0.0041 max mem: 22446 +train: [19] [380/400] eta: 0:00:09 lr: 0.000000 loss: 0.4188 (0.4209) grad: 0.0429 (0.0434) time: 0.4647 data: 0.0044 max mem: 22444 +eval (validation): [20] [40/63] eta: 0:00:09 time: 0.3515 data: 0.0033 max mem: 22446 +eval (validation): [20] [60/63] eta: 0:00:01 time: 0.3264 data: 0.0033 max mem: 22446 +train: [19] [399/400] eta: 0:00:00 lr: 0.000000 loss: 0.4182 (0.4209) grad: 0.0432 (0.0434) time: 0.4669 data: 0.0041 max mem: 22444 +train: [19] Total time: 0:03:10 (0.4760 s / it) +eval (validation): [20] [62/63] eta: 0:00:00 time: 0.3276 data: 0.0033 max mem: 22446 +train: [19] Summary: lr: 0.000000 loss: 0.4182 (0.4209) grad: 0.0432 (0.0434) +eval (validation): [20] Total time: 0:00:24 (0.3835 s / it) +eval (test): [20] [ 0/79] eta: 0:03:46 time: 2.8700 data: 2.6360 max mem: 22446 +eval (validation): [19] [ 0/63] eta: 0:03:17 time: 3.1311 data: 2.8778 max mem: 22444 +eval (test): [20] [20/79] eta: 0:00:27 time: 0.3544 data: 0.0042 max mem: 22446 +eval (validation): [19] [20/63] eta: 0:00:21 time: 0.3682 data: 0.0042 max mem: 22444 +eval (test): [20] [40/79] eta: 0:00:16 time: 0.3777 data: 0.0038 max mem: 22446 +eval (validation): [19] [40/63] eta: 0:00:10 time: 0.3831 data: 0.0037 max mem: 22444 +eval (test): [20] [60/79] eta: 0:00:07 time: 0.3508 data: 0.0037 max mem: 22446 +eval (validation): [19] [60/63] eta: 0:00:01 time: 0.3423 data: 0.0036 max mem: 22444 +eval (validation): [19] [62/63] eta: 0:00:00 time: 0.3360 data: 0.0036 max mem: 22444 +eval (validation): [19] Total time: 0:00:25 (0.4126 s / it) +cv: [19] best hparam: (22, 1.0) (043) ('043_lr2.2e+01_wd1.0e+00') loss: 0.053 acc: 0.988 f1: 0.986 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +eval (test): [20] [78/79] eta: 0:00:00 time: 0.3170 data: 0.0030 max mem: 22446 +eval (test): [20] Total time: 0:00:30 (0.3867 s / it) +evaluating last checkpoint: experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +eval model info: +{"score": 0.9878472222222222, "hparam": [22, 1.0], "hparam_id": 43, "epoch": 19, "is_best": false, "best_score": 0.9880952380952381} +evaluating best checkpoint: experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__attn/checkpoint-best.pth +eval model info: +{"score": 0.9880952380952381, "hparam": [22, 1.0], "hparam_id": 43, "epoch": 17, "is_best": true, "best_score": 0.9880952380952381} +eval (train): [20] [ 0/297] eta: 0:15:11 time: 3.0693 data: 2.7836 max mem: 22444 +eval (train): [20] [ 0/297] eta: 0:14:17 time: 2.8878 data: 2.6200 max mem: 22446 +eval (train): [20] [ 20/297] eta: 0:02:17 time: 0.3678 data: 0.0036 max mem: 22444 +eval (train): [20] [ 20/297] eta: 0:02:20 time: 0.3889 data: 0.0099 max mem: 22446 +eval (train): [20] [ 40/297] eta: 0:01:49 time: 0.3529 data: 0.0030 max mem: 22444 +eval (train): [20] [ 40/297] eta: 0:01:54 time: 0.3839 data: 0.0034 max mem: 22446 +eval (train): [20] [ 60/297] eta: 0:01:36 time: 0.3732 data: 0.0036 max mem: 22444 +eval (train): [20] [ 60/297] eta: 0:01:38 time: 0.3488 data: 0.0031 max mem: 22446 +eval (train): [20] [ 80/297] eta: 0:01:25 time: 0.3565 data: 0.0037 max mem: 22444 +eval (train): [20] [ 80/297] eta: 0:01:26 time: 0.3564 data: 0.0036 max mem: 22446 +eval (train): [20] [100/297] eta: 0:01:16 time: 0.3557 data: 0.0032 max mem: 22444 +eval (train): [20] [100/297] eta: 0:01:17 time: 0.3575 data: 0.0035 max mem: 22446 +eval (train): [20] [120/297] eta: 0:01:07 time: 0.3412 data: 0.0032 max mem: 22444 +eval (train): [20] [120/297] eta: 0:01:07 time: 0.3383 data: 0.0035 max mem: 22446 +eval (train): [20] [140/297] eta: 0:00:59 time: 0.3520 data: 0.0032 max mem: 22444 +eval (train): [20] [140/297] eta: 0:00:59 time: 0.3427 data: 0.0034 max mem: 22446 +eval (train): [20] [160/297] eta: 0:00:51 time: 0.3372 data: 0.0033 max mem: 22446 +eval (train): [20] [160/297] eta: 0:00:51 time: 0.3960 data: 0.0037 max mem: 22444 +eval (train): [20] [180/297] eta: 0:00:43 time: 0.3439 data: 0.0034 max mem: 22446 +eval (train): [20] [180/297] eta: 0:00:44 time: 0.3737 data: 0.0037 max mem: 22444 +eval (train): [20] [200/297] eta: 0:00:35 time: 0.3481 data: 0.0035 max mem: 22446 +eval (train): [20] [200/297] eta: 0:00:36 time: 0.3685 data: 0.0034 max mem: 22444 +eval (train): [20] [220/297] eta: 0:00:28 time: 0.3674 data: 0.0036 max mem: 22446 +eval (train): [20] [220/297] eta: 0:00:29 time: 0.3789 data: 0.0038 max mem: 22444 +eval (train): [20] [240/297] eta: 0:00:20 time: 0.3816 data: 0.0037 max mem: 22446 +eval (train): [20] [240/297] eta: 0:00:21 time: 0.3379 data: 0.0036 max mem: 22444 +eval (train): [20] [260/297] eta: 0:00:13 time: 0.3506 data: 0.0030 max mem: 22444 +eval (train): [20] [260/297] eta: 0:00:13 time: 0.3833 data: 0.0037 max mem: 22446 +eval (train): [20] [280/297] eta: 0:00:06 time: 0.3641 data: 0.0035 max mem: 22444 +eval (train): [20] [280/297] eta: 0:00:06 time: 0.3534 data: 0.0033 max mem: 22446 +eval (train): [20] [296/297] eta: 0:00:00 time: 0.3352 data: 0.0032 max mem: 22446 +eval (train): [20] [296/297] eta: 0:00:00 time: 0.3417 data: 0.0038 max mem: 22444 +eval (train): [20] Total time: 0:01:49 (0.3681 s / it) +eval (train): [20] Total time: 0:01:50 (0.3720 s / it) +eval (validation): [20] [ 0/63] eta: 0:03:07 time: 2.9814 data: 2.6900 max mem: 22444 +eval (validation): [20] [ 0/63] eta: 0:03:14 time: 3.0794 data: 2.7891 max mem: 22446 +eval (validation): [20] [20/63] eta: 0:00:20 time: 0.3446 data: 0.0140 max mem: 22446 +eval (validation): [20] [20/63] eta: 0:00:21 time: 0.3863 data: 0.0036 max mem: 22444 +eval (validation): [20] [40/63] eta: 0:00:09 time: 0.3644 data: 0.0038 max mem: 22446 +eval (validation): [20] [40/63] eta: 0:00:09 time: 0.3530 data: 0.0035 max mem: 22444 +eval (validation): [20] [60/63] eta: 0:00:01 time: 0.3294 data: 0.0030 max mem: 22446 +eval (validation): [20] [60/63] eta: 0:00:01 time: 0.3428 data: 0.0034 max mem: 22444 +eval (validation): [20] [62/63] eta: 0:00:00 time: 0.3274 data: 0.0032 max mem: 22446 +eval (validation): [20] Total time: 0:00:24 (0.3928 s / it) +eval (validation): [20] [62/63] eta: 0:00:00 time: 0.3357 data: 0.0033 max mem: 22444 +eval (validation): [20] Total time: 0:00:25 (0.4058 s / it) +eval (test): [20] [ 0/79] eta: 0:03:52 time: 2.9421 data: 2.7074 max mem: 22446 +eval (test): [20] [ 0/79] eta: 0:03:52 time: 2.9424 data: 2.6460 max mem: 22444 +eval (test): [20] [20/79] eta: 0:00:28 time: 0.3533 data: 0.0032 max mem: 22446 +eval (test): [20] [20/79] eta: 0:00:29 time: 0.3811 data: 0.0039 max mem: 22444 +eval (test): [20] [40/79] eta: 0:00:16 time: 0.3800 data: 0.0030 max mem: 22446 +eval (test): [20] [40/79] eta: 0:00:16 time: 0.3428 data: 0.0032 max mem: 22444 +eval (test): [20] [60/79] eta: 0:00:07 time: 0.3496 data: 0.0035 max mem: 22446 +eval (test): [20] [60/79] eta: 0:00:07 time: 0.3522 data: 0.0034 max mem: 22444 +eval (test): [20] [78/79] eta: 0:00:00 time: 0.3240 data: 0.0034 max mem: 22446 +eval (test): [20] Total time: 0:00:30 (0.3894 s / it) +eval (test): [20] [78/79] eta: 0:00:00 time: 0.3272 data: 0.0032 max mem: 22444 +eval (test): [20] Total time: 0:00:30 (0.3880 s / it) +eval results: + +| model | repr | clf | dataset | ckpt | epoch | lr | wd | hparam_id | hparam | split | loss | acc | acc_std | f1 | f1_std | +|:---------|:-------|:------|:-------------|:-------|--------:|-------:|-----:|------------:|:----------|:-----------|-----------:|--------:|----------:|--------:|----------:| +| flat_mae | patch | attn | hcpya_task21 | best | 17 | 0.0066 | 0.05 | 43 | [22, 1.0] | train | 0.00014598 | 1 | 0 | 1 | 0 | +| flat_mae | patch | attn | hcpya_task21 | best | 17 | 0.0066 | 0.05 | 43 | [22, 1.0] | validation | 0.052517 | 0.9881 | 0.0016299 | 0.98576 | 0.0022327 | +| flat_mae | patch | attn | hcpya_task21 | best | 17 | 0.0066 | 0.05 | 43 | [22, 1.0] | test | 0.072074 | 0.98611 | 0.0015755 | 0.9832 | 0.0020954 | + + +done! total time: 1:19:36 +evaluating best checkpoint: experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__attn/checkpoint-best.pth +eval model info: +{"score": 0.9880952380952381, "hparam": [22, 1.0], "hparam_id": 43, "epoch": 17, "is_best": true, "best_score": 0.9880952380952381} +eval (train): [20] [ 0/297] eta: 0:13:41 time: 2.7648 data: 2.5395 max mem: 22444 +eval (train): [20] [ 20/297] eta: 0:02:22 time: 0.4020 data: 0.0624 max mem: 22444 +eval (train): [20] [ 40/297] eta: 0:01:50 time: 0.3422 data: 0.0028 max mem: 22444 +eval (train): [20] [ 60/297] eta: 0:01:34 time: 0.3365 data: 0.0032 max mem: 22444 +eval (train): [20] [ 80/297] eta: 0:01:23 time: 0.3410 data: 0.0032 max mem: 22444 +eval (train): [20] [100/297] eta: 0:01:16 time: 0.3983 data: 0.0038 max mem: 22444 +eval (train): [20] [120/297] eta: 0:01:08 time: 0.3727 data: 0.0036 max mem: 22444 +eval (train): [20] [140/297] eta: 0:00:59 time: 0.3436 data: 0.0036 max mem: 22444 +eval (train): [20] [160/297] eta: 0:00:50 time: 0.3220 data: 0.0031 max mem: 22444 +eval (train): [20] [180/297] eta: 0:00:43 time: 0.3415 data: 0.0031 max mem: 22444 +eval (train): [20] [200/297] eta: 0:00:35 time: 0.3402 data: 0.0033 max mem: 22444 +eval (train): [20] [220/297] eta: 0:00:27 time: 0.3337 data: 0.0030 max mem: 22444 +eval (train): [20] [240/297] eta: 0:00:20 time: 0.3408 data: 0.0035 max mem: 22444 +eval (train): [20] [260/297] eta: 0:00:13 time: 0.3353 data: 0.0033 max mem: 22444 +eval (train): [20] [280/297] eta: 0:00:06 time: 0.3536 data: 0.0035 max mem: 22444 +eval (train): [20] [296/297] eta: 0:00:00 time: 0.3358 data: 0.0036 max mem: 22444 +eval (train): [20] Total time: 0:01:46 (0.3592 s / it) +eval (validation): [20] [ 0/63] eta: 0:03:08 time: 2.9997 data: 2.7446 max mem: 22444 +eval (validation): [20] [20/63] eta: 0:00:26 time: 0.5075 data: 0.1041 max mem: 22444 +eval (validation): [20] [40/63] eta: 0:00:11 time: 0.3495 data: 0.0029 max mem: 22444 +eval (validation): [20] [60/63] eta: 0:00:01 time: 0.3433 data: 0.0034 max mem: 22444 +eval (validation): [20] [62/63] eta: 0:00:00 time: 0.3441 data: 0.0034 max mem: 22444 +eval (validation): [20] Total time: 0:00:27 (0.4441 s / it) +eval (test): [20] [ 0/79] eta: 0:05:45 time: 4.3715 data: 4.0676 max mem: 22444 +eval (test): [20] [20/79] eta: 0:00:33 time: 0.3854 data: 0.0036 max mem: 22444 +eval (test): [20] [40/79] eta: 0:00:18 time: 0.3500 data: 0.0031 max mem: 22444 +eval (test): [20] [60/79] eta: 0:00:08 time: 0.3786 data: 0.0038 max mem: 22444 +eval (test): [20] [78/79] eta: 0:00:00 time: 0.3309 data: 0.0035 max mem: 22444 +eval (test): [20] Total time: 0:00:32 (0.4166 s / it) +eval results: + +| model | repr | clf | dataset | ckpt | epoch | lr | wd | hparam_id | hparam | split | loss | acc | acc_std | f1 | f1_std | +|:---------|:-------|:------|:-------------|:-------|--------:|-------:|-----:|------------:|:----------|:-----------|-----------:|--------:|----------:|--------:|----------:| +| flat_mae | patch | attn | hcpya_task21 | best | 17 | 0.0066 | 0.05 | 43 | [22, 1.0] | train | 0.00014598 | 1 | 0 | 1 | 0 | +| flat_mae | patch | attn | hcpya_task21 | best | 17 | 0.0066 | 0.05 | 43 | [22, 1.0] | validation | 0.052517 | 0.9881 | 0.0016299 | 0.98576 | 0.0022327 | +| flat_mae | patch | attn | hcpya_task21 | best | 17 | 0.0066 | 0.05 | 43 | [22, 1.0] | test | 0.072074 | 0.98611 | 0.0015755 | 0.9832 | 0.0020954 | + + +done! total time: 0:13:15 diff --git a/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__attn/train_log.json b/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__attn/train_log.json new file mode 100644 index 0000000000000000000000000000000000000000..fbe0e84161f0a27a3b028eb0bb7266758dbbc6d5 --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__attn/train_log.json @@ -0,0 +1,22 @@ +{"epoch": 0, "train/lr": 2.987987987987988e-05, "train/loss": 2.641285091638565, "train/grad": 0.08497005995362997, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.040467529296875, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.0396435546875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.03827880859375, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.0369677734375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.03561767578125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.03379150390625, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.031685791015625, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.0293994140625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.02632080078125, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.0230712890625, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.019869384765625, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.0150634765625, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.010479736328125, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.003798828125, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.99747802734375, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.9914111328125, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.98395263671875, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.9752734375, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.9660577392578125, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.95788330078125, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.9483087158203123, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.93900634765625, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.9293829345703126, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.9195556640625, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.9094830322265626, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.8975677490234375, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.886727294921875, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.87660888671875, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.8621295166015623, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.8434823608398436, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.8249676513671873, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.80613037109375, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.7762937927246094, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.743352508544922, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.6922913360595704, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.619255623817444, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.516852237582207, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.4048761454224588, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.276511031240225, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.119988142251968, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.001857306659222, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.9038251589983701, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.7815821593999863, "train/loss_043_lr2.2e+01_wd1.0e+00": 1.688138133212924, "train/loss_044_lr2.6e+01_wd1.0e+00": 1.5861467505991458, "train/loss_045_lr3.1e+01_wd1.0e+00": 1.4769999619945884, "train/loss_046_lr3.6e+01_wd1.0e+00": 1.3957993098720909, "train/loss_047_lr4.3e+01_wd1.0e+00": 1.3039650969579817, "train/loss_048_lr5.0e+01_wd1.0e+00": 1.2353749339282514, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.01340270861517638, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.013385856254026295, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.013359733880497516, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.013333936901763082, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.013306734911166131, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.013269284064881504, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.0132296213041991, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.013185604852624237, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.013126883278600872, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.01306726023554802, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.013008653153665364, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.012921848725527525, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.012838744544424116, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.012716544498689473, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.01259689562022686, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.012481294847093522, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.012331219734624027, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.012150188109371811, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.01194976079510525, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.011775188772007823, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.011584066615905613, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.01142452154541388, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.01128060262883082, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.011158501929603517, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.011053306928370149, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.010947222232352942, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.010865716198459267, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.010802284460514783, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.010727254322264344, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.010663519420195371, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.01063262996962294, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.01062534592114389, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.010639550208579748, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.01066830161958933, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.010723617349285633, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.010829959032125771, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.01097654232988134, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.011202848358079791, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.011452130386605858, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.011774171288125216, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.011977402644697576, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.012014245877508075, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.012013585821259767, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.012145949502009899, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.012277186790015548, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.012081242299173027, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.012003326914273202, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.012098098429851234, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.012475947779603303, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.0283420085906982, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.025851249694824, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.0217363834381104, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.0176079273223877, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.0136194229125977, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.008021593093872, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.0018370151519775, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.9949662685394287, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.986041307449341, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.976752281188965, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.967722177505493, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.954396963119507, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.9418060779571533, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.924315929412842, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.9083566665649414, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.8940975666046143, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.8774235248565674, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.8602757453918457, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.8442914485931396, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.832131862640381, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.8197152614593506, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.8086283206939697, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.7970523834228516, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.78422212600708, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.7698512077331543, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.7502989768981934, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.7300496101379395, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.708702564239502, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.6741080284118652, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.622060775756836, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.561906576156616, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.4928269386291504, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.3690083026885986, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.207782745361328, "validation/loss_034_lr5.1e+00_wd1.0e+00": 1.886340618133545, "validation/loss_035_lr6.0e+00_wd1.0e+00": 1.4067965745925903, "validation/loss_036_lr7.1e+00_wd1.0e+00": 1.0208308696746826, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.766514003276825, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.5189921259880066, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.3694706857204437, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.3040400743484497, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.2663535475730896, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.2265518456697464, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.20147424936294556, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.1840001493692398, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.1619873195886612, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.1516580581665039, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.15562830865383148, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.1483239382505417, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.17063492063492064, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.17063492063492064, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.17063492063492064, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.17063492063492064, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.17063492063492064, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.17063492063492064, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.17559523809523808, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.2058531746031746, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.2698412698412698, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.359375, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.47767857142857145, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.623015873015873, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.7135416666666666, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.7891865079365079, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.8405257936507936, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.8807043650793651, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.90625, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9141865079365079, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9300595238095238, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9379960317460317, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.941468253968254, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.949156746031746, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.953125, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9506448412698413, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9523809523809523, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.013882163034705408, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.013882163034705408, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.013882163034705408, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.013882163034705408, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.013882163034705408, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.013882163034705408, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.020031087698605305, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.05020566450899653, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.10065745691653165, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.16454442527986377, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.2528900523554626, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.41549043957065884, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.567780998659397, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.691092856745085, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.7745138273533556, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.8422653368853882, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.8750770290468948, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.8866542904211563, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9139089243140507, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9281289006457272, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9313253820078241, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9419289508894696, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9481065997584641, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9475306803170644, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9506569490186733, "id_best": 46, "lr_best": 0.010799999999999999, "wd_best": 0.05, "train/loss_best": 1.3957993098720909, "validation/loss_best": 0.1516580581665039, "validation/acc_best": 0.953125, "validation/f1_best": 0.9481065997584641} +{"epoch": 1, "train/lr": 8.993993993993998e-05, "train/loss": 1.8193004029989241, "train/grad": 0.07470881879329681, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.007783203125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.002578125, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.994129638671875, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.985908203125, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.978004150390625, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.9673193359375, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.95593994140625, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.943883056640625, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.929349365234375, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.915203857421875, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.9027520751953126, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.8863494873046873, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.872685546875, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.8559912109375, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.842412109375, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.8308941650390627, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.817784423828125, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.80319580078125, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.7871136474609375, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.7714495849609375, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.7503726196289064, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.725286865234375, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.691631164550781, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.646370086669922, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.583719253540039, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.468962526321411, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.3118931329250336, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.1432753416895864, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.8983435742557049, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.6077440014481545, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.3607013149559497, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.160804410353303, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.920430564135313, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.7373493407666684, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.5576475555077195, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.4251715886220336, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.32956436710432174, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.2632168148085475, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.21191443176008762, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.17265555248595774, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.15253901448100804, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.1388451928831637, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.12739455092698335, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.1218215196300298, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.1125543177407235, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.10916097468696534, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.10666667637415231, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.13062049515545368, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.12833733979612588, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.012699061213061214, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.012603775886818767, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.012453683852218091, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.012309446628205479, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.012170038116164506, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.011976725715212523, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.01176120163174346, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.011523864686023445, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.011218268123921007, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.010904735487420112, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.010621298071928322, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.01025693480623886, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.009975240502972155, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.009686588027980178, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.009504394400864839, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.009391725133173167, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.009308985588140785, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.009269699803553522, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.009276189852971583, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.009310984851326793, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.00937206226401031, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.009444710684474557, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.009531541783362628, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.009635151498951017, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.009762570522725581, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.01003827333683148, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.010334921292960644, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.010608653109520673, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.010959336136002093, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.011454451417084783, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.011772123544942588, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.012035284549929201, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.012154349614866078, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.012153662755154074, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.011878614528104663, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.011561860609799624, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.011269295571837574, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.010843110862188041, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.010202027969062328, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.009383054404752329, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.00883940696134232, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.00857635522610508, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.008533516406314447, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.008457997030345723, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.008098692632047459, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.008139317245222629, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.008272932446561753, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.009790087933652103, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.010340309413149952, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.981184959411621, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.9725892543792725, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.9589507579803467, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.945965528488159, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.933784008026123, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.917968988418579, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.9016547203063965, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.8855271339416504, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.867520570755005, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.851933240890503, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.839658737182617, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.8251214027404785, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.8138811588287354, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.799919843673706, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.787379503250122, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.7752127647399902, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.7588329315185547, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.73762583732605, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.7106971740722656, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.6815357208251953, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.638676166534424, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.5835604667663574, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.503598690032959, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.38541841506958, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.194143772125244, "validation/loss_025_lr1.2e+00_wd1.0e+00": 1.7324289083480835, "validation/loss_026_lr1.4e+00_wd1.0e+00": 1.2638204097747803, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.9925628900527954, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.675403892993927, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.4394908547401428, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.3297747075557709, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.2737230360507965, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.22683070600032806, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.19902819395065308, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.1703317016363144, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.14830806851387024, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.1307675689458847, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.11525589972734451, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.10228671133518219, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.0940142273902893, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.09264149516820908, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.09064648300409317, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.1012745350599289, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.1280488520860672, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.12029097974300385, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.10304995626211166, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.20233847200870514, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.14448975026607513, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.14529022574424744, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.17559523809523808, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.2105654761904762, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.26339285714285715, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.35987103174603174, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.5538194444444444, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.6502976190476191, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.7214781746031746, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.8234126984126984, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.878968253968254, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9126984126984127, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9260912698412699, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9379960317460317, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.941468253968254, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.951140873015873, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9573412698412699, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9620535714285714, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9652777777777778, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.96875, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9712301587301587, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9697420634920635, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.970734126984127, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9665178571428571, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9578373015873016, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9593253968253969, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9670138888888888, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9432043650793651, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9635416666666666, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9580853174603174, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.013885104794195705, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.01993315083936374, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.052746766279621576, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.08552294105808723, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.16052279344783962, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.3562084476422385, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.44507212391047835, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.5842385603021134, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.778348194427023, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.8585835181352612, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9024423030297645, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9172380687917804, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9322179197885683, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.935818371380896, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9453530548694319, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9534223058976794, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9576920262663872, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9621933323252202, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9655712447030883, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9688504225555897, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9675292875869297, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9679365918930042, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9611784822716181, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9499878927690678, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9459296096751486, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9667734944149059, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9418704400469474, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9597885347811377, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9538075800589163, "id_best": 39, "lr_best": 0.0036, "wd_best": 0.05, "train/loss_best": 0.17265555248595774, "validation/loss_best": 0.0940142273902893, "validation/acc_best": 0.9712301587301587, "validation/f1_best": 0.9688504225555897} +{"epoch": 2, "train/lr": 0.00014999999999999988, "train/loss": 1.4185909193754196, "train/grad": 0.08191409414634108, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.95177734375, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.940335693359375, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.922957763671875, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.907520751953125, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.89368408203125, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.877337646484375, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.8620367431640625, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.8479833984375, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.83325927734375, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.8205078125, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.8096136474609374, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.7947930908203125, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.780928955078125, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.7602252197265624, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.7389111328125, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.716285400390625, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.6836648559570313, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.6375253295898435, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.572227325439453, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.490955123901367, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.3334867668151857, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.0851686799526217, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.776012845337391, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.4388198351860046, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.1002514025568961, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.7687677449733019, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.5651410038024187, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.4384934589266777, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.3217318730428815, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.24383127776905894, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.20048098649829627, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.17352654576301574, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.14496392643079162, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.12629902790300548, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.10965298412367702, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.0956899412535131, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.08544005790725351, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.07784882470034063, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.0712011693418026, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.06899418894201517, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.0724496731813997, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.07902354446239769, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.08381313886493444, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.08730893142521381, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.10257204136811197, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.13414344024844468, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.2131382433604449, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.27040854006074366, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.3997657410427928, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.011783489130903036, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.011569963076617569, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.01122065972071141, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.010882285989355296, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.010565361513290555, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.01018234112067148, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.009837303038220852, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.009566476671025156, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.009358353489078581, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.009263424936216324, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.00924315637908876, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.00927454984281212, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.009330519172362984, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.009411412817426025, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.009481752272695303, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.009544894259888678, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.009629480035509914, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.009740909801330418, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.009883025311864913, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.01004081488121301, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.01043572178343311, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.010804908373393119, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.01103109076153487, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.011375054172240197, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.011651659153867512, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.011775882686488331, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.011761646876111627, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.011607621789444238, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.011184809654951096, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.010537297017872333, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.009953961542341858, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.009384169362019747, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.00860723599093035, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.008078090954804794, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.007640582723543048, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.007272919608512893, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0069891644618473945, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.00682164128345903, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.00662400707078632, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.006579331870307214, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.007055214760475792, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.007749188573798165, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.008311156243435107, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.008115020469995215, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.009686730174580589, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.011865940960124135, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.01705457254429348, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.02241948258364573, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.030068247460294514, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.9172396659851074, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.9033467769622803, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.8831069469451904, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.866408348083496, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.85276198387146, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.837834358215332, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.824775457382202, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.813284158706665, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.800605058670044, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.788254737854004, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.776315689086914, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.7578632831573486, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.7386655807495117, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.7077486515045166, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.673835277557373, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.63616943359375, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.5789482593536377, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.493359327316284, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.3602447509765625, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.163719654083252, "validation/loss_020_lr5.2e-01_wd1.0e+00": 1.6823281049728394, "validation/loss_021_lr6.1e-01_wd1.0e+00": 1.2182979583740234, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.9055193066596985, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.6006495952606201, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.41864216327667236, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.3062804043292999, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.2507014572620392, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.21947254240512848, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.18880003690719604, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.16230398416519165, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.14448896050453186, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.13013920187950134, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.11371167749166489, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.1028873473405838, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.09368814527988434, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.08624353259801865, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.0806313008069992, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.07374224811792374, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.06374964863061905, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.06379664689302444, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.0927518904209137, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.09147993475198746, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.1123674064874649, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.1196211725473404, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.15591959655284882, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.2809492349624634, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.4213777780532837, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.530767560005188, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.8140301704406738, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.1736111111111111, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.19543650793650794, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.23933531746031747, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.30357142857142855, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.3898809523809524, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.5753968253968254, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.6500496031746031, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.7552083333333334, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.8469742063492064, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.8876488095238095, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9166666666666666, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9312996031746031, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9399801587301587, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9451884920634921, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9521329365079365, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.957093253968254, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9613095238095238, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9642857142857143, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9672619047619048, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9697420634920635, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9717261904761905, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9729662698412699, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9749503968253969, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.980406746031746, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9794146825396826, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9702380952380952, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9714781746031746, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9642857142857143, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9625496031746031, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9533730158730159, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9397321428571429, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9412202380952381, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9379960317460317, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9124503968253969, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.017243462454972342, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.04000809380181362, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.06896316943275467, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.10942124376596335, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.17500064918397268, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.3664752526563489, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.44360165666910606, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.6288982260752649, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.8095343161865545, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.866969820890281, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9027783126301733, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9191085786225331, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.931767818786373, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9373607624773712, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9448913137671049, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9527075218882414, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9582167172072351, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9620531360828009, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9636636063117959, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.965256159882391, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.967893542321548, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9696278214015569, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.97282059344236, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9777108846116604, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9742098389167071, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.966965004169448, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9666950702486632, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9526703019468175, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9507981150250606, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9482494416245894, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.92491665624843, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9359776259017456, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9257938852600476, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.91035954180265, "id_best": 38, "lr_best": 0.00294, "wd_best": 0.05, "train/loss_best": 0.0712011693418026, "validation/loss_best": 0.06374964863061905, "validation/acc_best": 0.980406746031746, "validation/f1_best": 0.9777108846116604} +{"epoch": 3, "train/lr": 0.0002100600600600602, "train/loss": 1.2058254876732826, "train/grad": 0.12596554756164552, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.8903424072265627, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.876614990234375, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.858121337890625, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.8438592529296876, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.832557373046875, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.819654541015625, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.807489013671875, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.7951422119140625, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.779432373046875, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.76232666015625, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.7446484375, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.7155401611328127, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.683704833984375, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.6295404052734375, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.565328369140625, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.4874140930175783, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.3442752838134764, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.0652230954170228, "train/loss_018_lr3.8e-01_wd1.0e+00": 1.685352326631546, "train/loss_019_lr4.4e-01_wd1.0e+00": 1.3312495711445809, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.9527290201187134, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.6871209882199765, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.4857437396794558, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.3523442519456148, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.27248374581336976, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.21513473406434058, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.18043015711009502, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.15718076469376682, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.13193592677824198, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.10979598205536605, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.09553085749037564, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.08543272097595037, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.07404579340480268, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.06721532505005598, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.06191752552986145, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.05548520877026022, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.05213297144509852, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.05196322103030979, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.05533116147853434, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.06275783359073102, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.0771169107966125, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.07193076101131737, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.1020879396982491, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.16637367870658637, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.17931156356818975, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.2858355580922216, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.5431240219902247, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.9932491562142968, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.94189219920896, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.010521230567246676, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.010194367843214423, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.009774169318843633, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.009507371846120804, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.009367658265400678, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.009303702660836279, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.009323935429565609, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.0093834497500211, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.009467609142884612, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.009544845030177385, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.009606616843957454, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.009686149810440838, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.009759779279120267, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.009869411254767329, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.009983374283183365, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.010101750092580915, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.010415549108292907, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.011021853263955564, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.011318849232047797, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.011604161059949547, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.011720683281309903, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.011784201944246888, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.011730727036483585, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.011467792787589132, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.011010699619073422, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.01034007762093097, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.009742024899460376, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.009205461696255952, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.008602909414330498, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.007949552664067596, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.00752416474162601, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.007197657177457586, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.006819782429374754, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.006609363647876307, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.006511623398400843, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.00604979048599489, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0059109150531003254, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.006136277803452685, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.006480695678037591, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.00713251780369319, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.008100977062131278, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.008256819528178312, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.010525305668124929, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.015144673435715959, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.015912292167777196, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.02359714437043294, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.03941618090495467, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.061387283462099734, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.06403296483680605, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.859328031539917, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.8463807106018066, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.8299922943115234, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.8175997734069824, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.8074426651000977, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.7949488162994385, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.781611442565918, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.7666752338409424, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.7463483810424805, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.723095178604126, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.698220729827881, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.6561737060546875, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.608506679534912, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.523282766342163, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.4147226810455322, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.267462730407715, "validation/loss_016_lr2.7e-01_wd1.0e+00": 1.9104981422424316, "validation/loss_017_lr3.2e-01_wd1.0e+00": 1.3562325239181519, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.9991055727005005, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.7176098227500916, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.4783497452735901, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.35190847516059875, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.27280667424201965, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.22638216614723206, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.19496957957744598, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.1676456779241562, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.14613695442676544, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.130503311753273, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.11306485533714294, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.0999125987291336, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.09305296838283539, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.08752293139696121, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.08248261362314224, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.08268905431032181, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.09577126055955887, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.09428334981203079, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.0782630667090416, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.07711274176836014, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.07387393712997437, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.1081157699227333, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.1169716864824295, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.104373037815094, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.18733292818069458, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.24836428463459015, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.2090267837047577, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.34787678718566895, "validation/loss_046_lr3.6e+01_wd1.0e+00": 1.3580362796783447, "validation/loss_047_lr4.3e+01_wd1.0e+00": 1.1354954242706299, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.8161561489105225, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.1708829365079365, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.17509920634920634, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.21006944444444445, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.26066468253968256, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.32961309523809523, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.48933531746031744, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.6398809523809523, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.7358630952380952, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.8115079365079365, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.8725198412698413, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9089781746031746, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9295634920634921, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.941468253968254, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9464285714285714, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9518849206349206, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9573412698412699, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9618055555555556, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9682539682539683, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9714781746031746, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.972718253968254, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9737103174603174, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9729662698412699, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9719742063492064, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9699900793650794, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9697420634920635, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9751984126984127, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9744543650793651, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9769345238095238, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9692460317460317, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9655257936507936, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.970734126984127, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9533730158730159, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9536210317460317, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9558531746031746, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9615575396825397, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9154265873015873, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9255952380952381, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9441964285714286, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.014157081968061916, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.01872004156299286, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.05121517563418319, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.0799762007800698, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.1311123029696175, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.28517468789758, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.4390967246447795, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.5939720466881032, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.7364922501697234, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.8472876577546764, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.8945120884704649, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9200393020481269, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9331715557114248, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9389594532253073, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.945791425209609, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9504884662583257, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9552439406189479, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9624792281376862, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9665572577376835, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9674198376160225, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.969281441985388, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9684757373553973, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9678997951811896, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9646956768199046, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9645906788212448, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9704907568917773, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9705813700782455, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9734149356047636, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9653837771178911, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9625758292706249, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9694839243903766, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9456667034013687, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9426186583301276, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9434205020130848, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9552312211908752, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9071203804005731, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9165735220214283, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9406347383865733, "id_best": 38, "lr_best": 0.00294, "wd_best": 0.05, "train/loss_best": 0.05533116147853434, "validation/loss_best": 0.07387393712997437, "validation/acc_best": 0.9769345238095238, "validation/f1_best": 0.9734149356047636} +{"epoch": 4, "train/lr": 0.0002701201201201201, "train/loss": 1.1276831525564193, "train/grad": 0.2534354615956545, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.84056396484375, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.829124755859375, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.8141217041015625, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.80168701171875, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.790526123046875, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.77527587890625, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.7577496337890626, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.7374969482421876, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.7084649658203124, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.674006042480469, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.63575927734375, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.5676309204101564, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.4843649291992187, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.3074615097045896, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.0098385047912597, "train/loss_015_lr2.3e-01_wd1.0e+00": 1.660387306213379, "train/loss_016_lr2.7e-01_wd1.0e+00": 1.2456764161586762, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.8781851994991302, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.6125087492913007, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.4480246367305517, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.3302185680344701, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.25906106643378735, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.21012969084084035, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.17558845903724432, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.1487298435345292, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.12426451547071338, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.1059359026607126, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.09357502710074186, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.07985431444831192, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.06761762444861233, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.059449390368536116, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.053497021459043025, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.04727917792275548, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.045039178729057314, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.042925093537196514, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.040148747554048896, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.04022244361229241, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.04674917440861463, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.0674771982524544, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.08079518639482558, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.08019595219753682, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.13347029665485025, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.19618972417898475, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.3161288990546018, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.433453479539603, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.5173492804169655, "train/loss_046_lr3.6e+01_wd1.0e+00": 1.2712929697614164, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.5902102987747639, "train/loss_048_lr5.0e+01_wd1.0e+00": 5.020772519083693, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.009733478128910065, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.009601588821969926, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.009551238634157926, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.009590905508957803, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.009651701890397817, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.00972877445165068, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.009799624788574874, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.009858969922643155, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.009925785101950168, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.009993888970930129, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.010065024585928768, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.010185717479325831, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.010316501723136752, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.010670983244199305, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.011345652411691845, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.011597062144428492, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.011831840379163622, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.01188414154574275, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.012216923355590553, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.01218864890979603, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.011851289719343185, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.011259254957549274, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.010537546596024185, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.009810092600528151, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.009102436869870872, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.008339789558667689, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.007679676435654983, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.007151776608079672, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.006632600283483043, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.006170356309157796, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.005838902990799397, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.005602010820293799, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.005381606453447603, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.005414421053428669, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.005486489649047144, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.005498682823381387, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.005810189395124326, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.00649579597346019, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.008321396854589692, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.009661989035084844, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.00953128756955266, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.012655627632630057, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0180315952168894, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.024667563737602906, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.03357133956160396, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.03743634442798793, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.07950102769769728, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.04633417109027505, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.2010584773030132, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.8211207389831543, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.8110249042510986, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.7966785430908203, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.783573865890503, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.7706997394561768, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.7522895336151123, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.730257272720337, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.703646183013916, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.66474986076355, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.616990566253662, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.5623347759246826, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.4602863788604736, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.3253705501556396, "validation/loss_013_lr1.7e-01_wd1.0e+00": 1.9502075910568237, "validation/loss_014_lr2.0e-01_wd1.0e+00": 1.4162756204605103, "validation/loss_015_lr2.3e-01_wd1.0e+00": 1.1026474237442017, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.7957451343536377, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.5229222178459167, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.3739588260650635, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.29633980989456177, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.24194082617759705, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.20455916225910187, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.17507901787757874, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.15391100943088531, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.13776123523712158, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.12224216759204865, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.11132209748029709, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.10501346737146378, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.09749575704336166, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.0926855206489563, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.09064424782991409, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.08759200572967529, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.08455901592969894, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.08865479379892349, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.08244367688894272, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.09396550059318542, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.08679142594337463, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.08256105333566666, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.0996493250131607, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.17875072360038757, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.10556250810623169, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.3929108679294586, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.4588799476623535, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.32535025477409363, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.4865112006664276, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.1422207355499268, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.7758911848068237, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.6852637529373169, "validation/loss_048_lr5.0e+01_wd1.0e+00": 13.268083572387695, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.171875, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.18229166666666666, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.21552579365079366, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.26612103174603174, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.328125, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.4871031746031746, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.6165674603174603, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.6827876984126984, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.7819940476190477, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.8588789682539683, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.8995535714285714, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.917906746031746, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9332837301587301, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9439484126984127, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9506448412698413, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.955109126984127, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9583333333333334, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9620535714285714, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9632936507936508, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9642857142857143, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9675099206349206, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9682539682539683, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9699900793650794, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.970734126984127, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9714781746031746, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.970734126984127, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9759424603174603, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9692460317460317, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9724702380952381, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.972718253968254, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9699900793650794, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9546130952380952, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9709821428571429, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9295634920634921, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9325396825396826, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9503968253968254, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9518849206349206, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.8844246031746031, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.953125, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9543650793650794, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.8673115079365079, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.015228483394867095, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.02710225777363587, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.05525314417561351, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.08288140688408535, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.12155152446748918, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.276203557510256, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.4058663805298645, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.5034396195765106, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.6804767635997131, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.8232327209753689, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.8826575047346845, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9015835905684566, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9203472274994859, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9345858717979703, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.942862666233994, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9474234495760319, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9528296624114312, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9579717541041516, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9605996219310075, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9612623354200197, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9664571476387035, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9677700005988585, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.969345815438101, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9705740829388124, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9713672117499157, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9719822197485306, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9760653051311624, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9682207834700234, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9686500801365595, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9700518005347456, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.966681351353846, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9392179162705576, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9646416833212712, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9154976928633121, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.930198740734079, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.944677874052047, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9512903174691199, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.8516247828288602, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9485146149062778, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9437561558418253, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.8422516685657969, "id_best": 34, "lr_best": 0.0015299999999999997, "wd_best": 0.05, "train/loss_best": 0.042925093537196514, "validation/loss_best": 0.08244367688894272, "validation/acc_best": 0.9759424603174603, "validation/f1_best": 0.9760653051311624} +{"epoch": 5, "train/lr": 0.00029891323817685334, "train/loss": 1.1675775679945946, "train/grad": 0.3985579250007868, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.8114654541015627, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.800947265625, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.7849237060546876, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.768944091796875, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.7526519775390623, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.728690185546875, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.6993743896484377, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.6629605102539062, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.607955017089844, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.53767822265625, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.452707061767578, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.2696004486083985, "train/loss_012_lr1.4e-01_wd1.0e+00": 1.956965265274048, "train/loss_013_lr1.7e-01_wd1.0e+00": 1.4123266169428825, "train/loss_014_lr2.0e-01_wd1.0e+00": 1.0281216901540757, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.7675588610768318, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.5297892934828997, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.3719287334382534, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.2809585202112794, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.2312354611232877, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.19024237625300885, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.1595900696143508, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.1334142671711743, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.11207154468633235, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.09490961434319616, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.07909543457441032, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.06806161026470363, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.06100554436445236, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.05214653952047229, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.04320565287023783, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.03719949590042233, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.0325278283841908, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.02955236166715622, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.02823645028285682, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.025440051993355153, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.02982523314654827, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.0302638020273298, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.04458642865531146, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.04647245794534683, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.11436492186971009, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.13853784212842585, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.1837927095312625, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.26169661596417426, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.2088673433009535, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.4773289661947638, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.8117508956976235, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.5088345684763044, "train/loss_047_lr4.3e+01_wd1.0e+00": 1.2139151441864668, "train/loss_048_lr5.0e+01_wd1.0e+00": 13.537583520486951, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.009407631647773087, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.009457899804692716, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.009553377542179078, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.009629338649101555, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.009687992287799716, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.009752730077598243, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.009815748871769756, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.009885460087098182, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.009987848824821413, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.010109933805651963, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.010239657284691929, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.010586165767163038, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.011476767137646676, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.011703771627508104, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.011487028044648469, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.011782668859232216, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.011898229499347508, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.011541734761558474, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.010883042190689593, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.010329417439643294, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.009730459987185896, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.009096719352528452, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.008431503402534872, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.007814110949402675, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.007247384915826842, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.006717132815392688, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.006355486973188817, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0061168010794790464, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0057825804443564265, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.005335003911168315, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.004998518021602649, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.004738310473330784, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.004769644332845928, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.004739915688987822, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.004695241861627437, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0054979370872024445, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.005308216705016093, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.007181050996150589, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0069015669958025685, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.012211385547707322, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.01455843545612879, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.01836981122032739, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.02206651870976202, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.01967852767877048, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.03604174608364701, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.05406974155455828, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.04109626697136719, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.08206772662233561, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.3677099204808474, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.797166347503662, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.786051034927368, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.7678582668304443, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.749335527420044, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.7299227714538574, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.7009031772613525, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.664438486099243, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.6184756755828857, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.5469119548797607, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.451876163482666, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.329730987548828, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.0057828426361084, "validation/loss_012_lr1.4e-01_wd1.0e+00": 1.4994498491287231, "validation/loss_013_lr1.7e-01_wd1.0e+00": 1.0478023290634155, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.727294385433197, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.5179975032806396, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.3729310631752014, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.28219130635261536, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.23090781271457672, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.20025411248207092, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.1735636442899704, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.15405814349651337, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.13738687336444855, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.12281245738267899, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.1107664406299591, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.09990930557250977, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.09333056956529617, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.08953602612018585, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.08558841049671173, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.0835351049900055, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.08595485985279083, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.08617951720952988, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.09484977275133133, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.09325066208839417, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.08651535212993622, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.09103752672672272, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.08366860449314117, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.10085231810808182, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.10490703582763672, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.1291559636592865, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.40874922275543213, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.20353908836841583, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.3858483135700226, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.43502435088157654, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.3236978352069855, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.5425469279289246, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.2888679504394531, "validation/loss_047_lr4.3e+01_wd1.0e+00": 1.0936729907989502, "validation/loss_048_lr5.0e+01_wd1.0e+00": 9.093242645263672, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.17162698412698413, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.18353174603174602, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.23214285714285715, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.28422619047619047, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.33804563492063494, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.44915674603174605, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.6026785714285714, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.7093253968253969, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.808531746031746, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.8673115079365079, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9005456349206349, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.923859126984127, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9392361111111112, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9459325396825397, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.951140873015873, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9558531746031746, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9605654761904762, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9627976190476191, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9652777777777778, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9672619047619048, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.96875, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9692460317460317, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9699900793650794, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9712301587301587, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9719742063492064, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9737103174603174, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9704861111111112, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9709821428571429, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9739583333333334, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9712301587301587, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9769345238095238, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.972718253968254, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9744543650793651, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9682539682539683, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9347718253968254, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9655257936507936, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9464285714285714, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9389880952380952, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9657738095238095, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9593253968253969, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9742063492063492, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9526289682539683, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.910218253968254, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.014963930260150577, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.02833694091177829, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.06293415928013149, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.08650291445979998, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.1235700710297835, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.21854427445340596, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.39057105934536634, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.5610709934660079, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.7403433287411377, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.8390220242599198, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.886411081092126, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9122251924448919, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9312940982263145, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9391432218734822, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9448275217382494, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9491117418793591, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9554972304073404, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9587451018334067, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.961104577241634, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.963266739043489, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.964669478619659, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9649147941776979, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9668915518336876, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9683726653595424, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9692387120054582, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9717184270878302, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.96845938321301, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9697640149726836, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9722566207300422, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9661394600103367, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9750295328687422, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9647420448356778, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9704424099185739, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9611238686658959, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9372070399665853, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9604957518836034, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9362133272296966, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9387910242083256, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9605486953151603, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9463453567444573, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9692974112792336, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9447606964539706, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.8956004625763784, "id_best": 36, "lr_best": 0.0021299999999999995, "wd_best": 0.05, "train/loss_best": 0.0302638020273298, "validation/loss_best": 0.08366860449314117, "validation/acc_best": 0.9769345238095238, "validation/f1_best": 0.9750295328687422} +{"epoch": 6, "train/lr": 0.0002924170901991409, "train/loss": 0.8591405367851257, "train/grad": 0.22242678191512824, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.7829217529296875, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.7701190185546873, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.748638916015625, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.725958251953125, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.7020684814453126, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.6655917358398438, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.618944091796875, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.5586578369140627, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.4612911987304686, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.322800750732422, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.1050848007202148, "train/loss_011_lr1.2e-01_wd1.0e+00": 1.586163468360901, "train/loss_012_lr1.4e-01_wd1.0e+00": 1.1771660393476486, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.7916195088624954, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.5352485954761506, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.3973629430681467, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.2948858693242073, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.23032071962952613, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.18905601425096394, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.16221157057210803, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.13679856771603227, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.11624426461756229, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.09728376504033803, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.0813436109572649, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.06882196354679763, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.05713075893931091, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.04832104662433267, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.04210354401730001, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.03437326777726412, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.026945382487028838, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.02241663483902812, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.019571915650740266, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.018812498999759553, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.01583586385473609, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.018532013818621636, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.01709133345633745, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.02122632451355457, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.02663984425365925, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.04166253237053752, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.06424730565398931, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.11476973187178373, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.10012195348739623, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.12397865309379995, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.13296348568052052, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.21114267234690487, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.36335577390156687, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.1670904046948999, "train/loss_047_lr4.3e+01_wd1.0e+00": 1.91789141850546, "train/loss_048_lr5.0e+01_wd1.0e+00": 4.165059069832787, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.009136712229810655, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.00919536038301885, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.009273261677008123, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.009335002393927426, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.009390278381761163, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.009466598168946802, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.009562690081074833, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.00968285397393629, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.009858505844604223, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.010084135464858264, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.01076836695894599, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.011784209748730063, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.011123335198499262, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.011513045458123088, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.011655228377785534, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.011318182568065821, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.010750581757165492, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.0101944740395993, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.009544734652154148, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.009003548342734575, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.00844535275362432, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.007872959498781711, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.007291446387534961, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.006805660175159573, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.006395391973201186, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0059581248444737864, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.005550802181242034, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.005180911329225637, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.004701469569990877, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.004087208508572075, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0037759608431952073, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.003545533053256804, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.003578978853474837, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0031197177581634605, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.003600587186301709, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.004011858136800583, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.004716701199795352, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.00544193284586072, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.006908085503418988, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.008954275480646175, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.012794265254196944, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.012077832894246967, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.01509536425337501, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.01683010526605358, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.02333111002638816, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.032941246395348574, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.020404401448397492, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.12949447277831497, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.14845915940764826, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.776542901992798, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.7625269889831543, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.7383077144622803, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.712535858154297, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.6847195625305176, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.6417078971862793, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.585574150085449, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.511370897293091, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.38742733001709, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.195465326309204, "validation/loss_010_lr1.0e-01_wd1.0e+00": 1.8365089893341064, "validation/loss_011_lr1.2e-01_wd1.0e+00": 1.2809728384017944, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.970729649066925, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.6019057631492615, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.4197051525115967, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.3246157765388489, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.25942057371139526, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.21558362245559692, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.1848738044500351, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.16357354819774628, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.14253462851047516, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.1248282715678215, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.1085837259888649, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.09646124392747879, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.08798005431890488, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.08050926774740219, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.07558111101388931, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.07210216671228409, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.06692565232515335, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.061991918832063675, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.06073549762368202, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.0596095435321331, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.06311503052711487, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.06741655617952347, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.06514521688222885, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.07595231384038925, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.09195785224437714, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.08143578469753265, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.10519325733184814, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.11738283932209015, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.20888498425483704, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.1613529771566391, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.3467915654182434, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.3942756950855255, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.3771072030067444, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.3961601257324219, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.2288672775030136, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.93526029586792, "validation/loss_048_lr5.0e+01_wd1.0e+00": 4.28347635269165, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.17509920634920634, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.19940476190476192, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.24603174603174602, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.30183531746031744, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.38467261904761907, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.5369543650793651, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.6532738095238095, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.7415674603174603, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.8526785714285714, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.8903769841269841, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9151785714285714, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9330357142857143, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9427083333333334, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9486607142857143, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9548611111111112, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9608134920634921, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9650297619047619, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9685019841269841, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9717261904761905, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9734623015873016, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9739583333333334, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9747023809523809, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9766865079365079, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9759424603174603, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9781746031746031, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9799107142857143, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9811507936507936, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9813988095238095, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9794146825396826, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9813988095238095, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9766865079365079, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9764384920634921, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9789186507936508, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9756944444444444, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9747023809523809, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9680059523809523, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9712301587301587, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9640376984126984, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9516369047619048, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9670138888888888, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.964781746031746, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9764384920634921, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9226190476190477, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9429563492063492, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.013885104794195705, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.018712324322898072, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.04075210488522281, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.06762889225840737, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.10206933457945039, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.17119220634885593, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.333091984502353, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.449235399150333, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.6097066746794899, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.815788832218418, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.8752097939144864, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9044795802967213, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9261974041484065, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9359955010274867, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9433316291105476, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9485416724638818, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9541058610480692, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9599695281589563, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9642222419520056, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9672744412286214, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9696624874159109, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9702353166306464, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9711164052936719, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9729812332563887, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9727003940338218, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9758738874632462, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9777723731675072, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9791243916427893, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9798389734606959, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.977956166175195, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9774174977524865, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9741882157439002, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9726455105371866, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9764017149235481, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9702489108033647, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9711868922139906, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9591505069234069, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9675159874178337, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9428788928328047, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9423703296001181, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9626073057526519, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9618759208303257, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9727061942435429, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9057506460079511, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9399011424546141, "id_best": 32, "lr_best": 0.0011099999999999999, "wd_best": 0.05, "train/loss_best": 0.018812498999759553, "validation/loss_best": 0.06311503052711487, "validation/acc_best": 0.9813988095238095, "validation/f1_best": 0.9798389734606959} +{"epoch": 7, "train/lr": 0.00027969249556793234, "train/loss": 0.7724479177594185, "train/grad": 0.26082837749272586, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.768333740234375, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.752294921875, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.7241949462890624, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.6935455322265627, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.66011474609375, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.6078256225585936, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.5383480834960936, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.444296569824219, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.277685546875, "train/loss_009_lr8.7e-02_wd1.0e+00": 1.9654532623291017, "train/loss_010_lr1.0e-01_wd1.0e+00": 1.5385994505882263, "train/loss_011_lr1.2e-01_wd1.0e+00": 1.0899084314703942, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.7860041047632694, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.4940948800742626, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.3560433684289455, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.2826345092430711, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.22797780960798264, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.18650578580796717, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.15576542058959603, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.13411801250651478, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.11250929008238017, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.0947242798563093, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.07870657419785858, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.0652674184832722, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.05425782295875251, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.04288016848266125, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.0341977079026401, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.028364025335758925, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.02163462762720883, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.015459963604807853, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.011419948963448405, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.008744065491482616, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.006319100698456168, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.005196233820170164, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.01142918367870152, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.008409553822129965, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.01654349229298532, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.017467776872217657, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.03138135491870344, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.03765482114627958, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.08818033189512789, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.06646993640810252, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.1747030176781118, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.13007451819255947, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.14232454399578273, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.20950588721781968, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.1006878631003201, "train/loss_047_lr4.3e+01_wd1.0e+00": 4.326266851713881, "train/loss_048_lr5.0e+01_wd1.0e+00": 1.2254235880728812, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.009273498323746026, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.00932589458534494, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.009396246462129056, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.009460384752601384, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.009524631595704705, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.009625453136395663, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.009751367399003357, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.009899836473632604, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.010151765961199998, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.011280082305893302, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.01183753449935466, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.011012308583594858, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.01149182417197153, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.011638969448395074, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.011184029143769293, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.010636053835041822, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.009979895534925162, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.009332192812580615, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.00866574848536402, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.008141399479936808, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.007562283894512803, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.006960489233024419, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.006342290863394737, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.005792136331438087, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.005293423084949609, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.004718618611223064, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.004219760286505334, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0038208644829865078, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0033062101219547913, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0026934284533490426, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0021759948842372976, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0017700469012197572, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0013801543542285798, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0012542008683521998, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0026976259097864384, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.001821230566038139, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.00375260987009824, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0038560371518815374, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.005463992268560105, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.006080567452672767, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.010369113190536154, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.008802936286865588, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.017456660275056494, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.014887036425416228, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.015431126201315806, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.023022726543710768, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.01270803754296594, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.2323584197461605, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.08292005176524705, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.7568230628967285, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.73909854888916, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.707796335220337, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.673349380493164, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.635401487350464, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.575040817260742, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.493497371673584, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.3800458908081055, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.1639037132263184, "validation/loss_009_lr8.7e-02_wd1.0e+00": 1.7188847064971924, "validation/loss_010_lr1.0e-01_wd1.0e+00": 1.303330898284912, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.9331021904945374, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.6322203278541565, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.40804994106292725, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.3021117150783539, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.2500128746032715, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.20941098034381866, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.17784063518047333, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.15355220437049866, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.13618654012680054, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.11830205470323563, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.10373333841562271, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.09170570224523544, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.08321383595466614, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.07711496949195862, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.07113990932703018, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.0670112818479538, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.06533902883529663, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.06330602616071701, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.06049986183643341, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.05940606817603111, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.05775978043675423, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.055589426308870316, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.057054080069065094, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.06257424503564835, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.07372536510229111, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.09746375679969788, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.08674773573875427, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.13585422933101654, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.1083933487534523, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.12931443750858307, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.10333198308944702, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.24672478437423706, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.5011885166168213, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.1698821485042572, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.3754265308380127, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.2486390620470047, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.2527823448181152, "validation/loss_048_lr5.0e+01_wd1.0e+00": 2.51098895072937, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.17385912698412698, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.2013888888888889, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.24603174603174602, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.2976190476190476, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.3916170634920635, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.5682043650793651, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.6465773809523809, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.7559523809523809, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.8449900793650794, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.8958333333333334, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9216269841269841, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9352678571428571, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9427083333333334, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9503968253968254, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9558531746031746, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9608134920634921, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9655257936507936, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9699900793650794, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9747023809523809, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9759424603174603, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9756944444444444, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9759424603174603, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9764384920634921, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9769345238095238, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9779265873015873, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9794146825396826, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9821428571428571, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9818948412698413, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9821428571428571, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9831349206349206, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9836309523809523, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9794146825396826, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9709821428571429, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9734623015873016, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9697420634920635, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9724702380952381, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.972718253968254, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9794146825396826, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9685019841269841, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9506448412698413, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9801587301587301, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9709821428571429, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9709821428571429, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9471726190476191, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.955109126984127, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.013885104794195705, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.017488714804344302, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.04458026051249088, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.06777927300799118, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.09772600350640415, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.17418613250285078, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.3621590810631544, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.43881085206261583, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.632778133742538, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.8082464418056992, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.8812795286055319, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9117400748622742, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9287069129091399, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9346184190759627, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9440348249894119, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.949341469887871, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.954283545554339, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9597422443734012, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9638796382493643, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9702911195128592, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9718455600317061, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9722477037696652, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9718849880232437, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.972809336260803, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9733489447754659, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9747043726661999, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.976328827185621, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9797089091615903, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9791003470278082, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9787930503143236, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9807805653818875, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9811728374712088, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9758215314270634, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9672051696140394, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9719355287495011, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9641730431924923, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9661152327350502, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9654007588748638, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9770180427283044, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9657795040765145, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9501133738877945, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9789644840492829, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9674970872838587, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9710696185112321, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9374496089741315, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.953227241907347, "id_best": 34, "lr_best": 0.0015299999999999997, "wd_best": 0.05, "train/loss_best": 0.01142918367870152, "validation/loss_best": 0.06257424503564835, "validation/acc_best": 0.9836309523809523, "validation/f1_best": 0.9811728374712088} +{"epoch": 8, "train/lr": 0.0002612959497061927, "train/loss": 0.6275359016656875, "train/grad": 0.1313826110586524, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.7458770751953123, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.7256805419921877, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.6898150634765625, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.6498260498046875, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.6054367065429687, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.533937683105469, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.4355400085449217, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.293807373046875, "train/loss_008_lr7.4e-02_wd1.0e+00": 1.9838626098632812, "train/loss_009_lr8.7e-02_wd1.0e+00": 1.487113754749298, "train/loss_010_lr1.0e-01_wd1.0e+00": 1.1397597831487656, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.7844673471152782, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.5363246808946133, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.35902126841247084, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.2721309408172965, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.22555252104997636, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.18568239595741035, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.15268417712301016, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.127233035415411, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.10857235812582075, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.08979096228256822, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.07478456660173834, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.06166672855615616, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.05061003224924207, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.04145369830541313, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.03233893858268857, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.02533034767024219, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.02050072791054845, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.014932316932827235, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.010118959005922079, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0068987399991601705, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.004697062503546476, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.0031504095811396835, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.0021888929046690463, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.0034636316262185575, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.003533032825216651, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.018168147979304196, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.03151420372538269, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.017353287590667607, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.015818865010514854, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.037450218927115204, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.030292252264916896, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.0862589415628463, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.07265444870106876, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.04559488325379789, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.13207778454758226, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.06106121262535453, "train/loss_047_lr4.3e+01_wd1.0e+00": 1.1800348115246744, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.5331963056046516, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.009627428506501019, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.00967651949264109, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.009753056988120078, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.009829059785697609, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.00991261977236718, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.010036205542273819, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.010179700555745512, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.010358680088538677, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.011347795189358294, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.01205896866042167, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.011123394155874848, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.011585890431888402, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.011762555935420096, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.011291909327264876, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.010778241979423911, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.010277618595864624, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.009680322532076388, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.009055113629437983, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.00835495613166131, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.007770977003965527, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.007140682238386944, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.006530891127185896, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.005945927990251221, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0054110470094019545, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.004903886021929793, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.004307013545476366, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.00372873750369763, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0032397055957699194, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.00260810006497195, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0019735908780421597, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0015271017506165662, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.001135989618996973, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0009185509020244354, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.000656683166653238, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0011894837631007248, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0010612747040613614, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.004480302077936358, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.006222457338171807, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.004136375091002264, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.003548295601594873, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.006612346538533984, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.006140927655819723, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.010955203581218029, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.011201196891006475, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.007642631584152754, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.01521112713855537, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.009774449677272567, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.09646737939704671, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.05197608243473096, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.7375643253326416, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.715858221054077, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.6765596866607666, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.6326537132263184, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.5831894874572754, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.502673864364624, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.3899283409118652, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.2206475734710693, "validation/loss_008_lr7.4e-02_wd1.0e+00": 1.8051402568817139, "validation/loss_009_lr8.7e-02_wd1.0e+00": 1.3173342943191528, "validation/loss_010_lr1.0e-01_wd1.0e+00": 1.0271384716033936, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.6679468750953674, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.46000874042510986, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.3127039670944214, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.2467779517173767, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.21097427606582642, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.18023063242435455, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.15436193346977234, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.13406534492969513, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.11896143853664398, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.10353515297174454, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.09215327352285385, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.0833890363574028, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.07716330885887146, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.07266701012849808, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.06853274255990982, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.06592005491256714, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.06532564759254456, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.062192704528570175, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.05924944207072258, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.06057633459568024, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.06005997955799103, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.05919361859560013, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.05837361142039299, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.05797550454735756, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.06653600931167603, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.07628339529037476, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.0970703735947609, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.09825503826141357, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.06296832859516144, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.14587540924549103, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.12013684213161469, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.2522260248661041, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.295305997133255, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.16209085285663605, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.29147496819496155, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.16247504949569702, "validation/loss_047_lr4.3e+01_wd1.0e+00": 1.1662617921829224, "validation/loss_048_lr5.0e+01_wd1.0e+00": 1.2419058084487915, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.17410714285714285, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.1966765873015873, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.2400793650793651, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.29464285714285715, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.3665674603174603, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.5416666666666666, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.644593253968254, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.7234623015873016, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.8395337301587301, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.8846726190476191, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9174107142857143, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9345238095238095, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9424603174603174, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9484126984126984, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9553571428571429, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9608134920634921, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9640376984126984, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9704861111111112, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9729662698412699, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9761904761904762, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9771825396825397, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9766865079365079, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9771825396825397, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9779265873015873, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9784226190476191, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9796626984126984, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9821428571428571, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9813988095238095, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9818948412698413, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9813988095238095, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.982390873015873, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9833829365079365, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9801587301587301, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9781746031746031, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9796626984126984, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9766865079365079, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9836309523809523, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9717261904761905, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9806547619047619, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9660218253968254, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.966765873015873, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9779265873015873, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9670138888888888, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9761904761904762, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9685019841269841, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9660218253968254, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.017850403036434766, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.04145284872817264, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.06571713589986973, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.09579058049477485, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.15446989797964394, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.3344085931620229, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.43591602039691046, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.575119740090393, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.797800975383898, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.8674141861358586, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.905559460400307, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9268626753212844, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9350934320421896, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9407168836024418, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.94855081555561, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9553571140500177, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9574506248602722, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9660193445969576, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9686971072612446, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9747743452808398, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9749880115502082, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9750636061897475, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9756328864377447, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9759702646240808, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9772860109898199, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9787278335556877, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9811081049025459, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9802595206284457, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9807126133884048, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9800216724521837, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9800465204189047, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9808003737443253, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9766192706679997, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9742315789608588, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9767602992635526, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9710394451801369, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.981494660104452, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9587314527850372, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9779212897651013, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9625013825156427, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9620283756584666, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9762883261176876, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9632354545261264, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9734741440150436, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9668391993652311, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9642784031618079, "id_best": 39, "lr_best": 0.0036, "wd_best": 0.05, "train/loss_best": 0.015818865010514854, "validation/loss_best": 0.06296832859516144, "validation/acc_best": 0.9836309523809523, "validation/f1_best": 0.981494660104452} +{"epoch": 9, "train/lr": 0.00023803200426111704, "train/loss": 0.5579537911713124, "train/grad": 0.08494491953402758, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.7288946533203124, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.7047125244140626, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.66043701171875, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.6103811645507813, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.5537579345703123, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.460623321533203, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.327920684814453, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.1149004745483397, "train/loss_008_lr7.4e-02_wd1.0e+00": 1.622659878730774, "train/loss_009_lr8.7e-02_wd1.0e+00": 1.1844011077284813, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.9089590203762055, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.5771848517656326, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.40918730095028877, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.28382006295025347, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.2245401806011796, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.18966236002743245, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.15813119381666182, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.13122325007803737, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.10987006342038512, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.094057248942554, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.0776984322629869, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.06435468630865217, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.05200557713396847, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.041248075338080524, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.03211055014282465, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.022941137887537478, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.016661900570616128, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.012702840948477387, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.00842778000049293, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.005167614044621587, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0033476054389029743, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.0023312951903790235, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.0015741203725337981, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.00115003053098917, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.0009828604012727738, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.0014228676073253154, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.01081462251022458, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.01907295481301844, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.012474205046892166, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.005590684087947011, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.03213413801975548, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.02214314604178071, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.03074934004805982, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.05290743760764599, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.05787843214347958, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.04421061690896749, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.060553355971351266, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.3597899914439768, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.23196561513468622, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.009507494915742426, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.00955741315614432, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.009637881545349955, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.009726981406565756, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.00982000176794827, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.009947595493867993, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.01009449150878936, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.01048806197475642, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.01207205215934664, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.01099813150241971, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.011142813870683312, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.01160834654700011, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.011396563139278441, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.010812118051107973, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.010245894566178321, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.009717209881637245, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.00912160929525271, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.008505740317050368, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.007814013526076451, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.007261280701495707, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.006668037828640081, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.006114114482770674, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.005576261830283329, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.00500850703130709, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.004378933475236408, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0036074822732189205, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.002948776628181804, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.002430980717181228, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0017937754925515038, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0012018554477981524, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0008381530712358653, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0006174411826214055, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.00040226507997431326, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.00029048801818134964, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0003589213002305769, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0005398200430317957, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0034142154200389996, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.004505386239834479, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0034922372804976477, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.002047750161189015, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.005637996383647988, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.004802002067843886, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.007372166647469385, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.009826829088315493, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.009370704613097018, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.007342209983488601, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.009384363628078667, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.04430193358015817, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.03228806986440419, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.7191741466522217, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.693333864212036, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.6459062099456787, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.5919322967529297, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.530280590057373, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.427964448928833, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.278078079223633, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.0163192749023438, "validation/loss_008_lr7.4e-02_wd1.0e+00": 1.4762566089630127, "validation/loss_009_lr8.7e-02_wd1.0e+00": 1.0954798460006714, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.8230457901954651, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.5144391655921936, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.3683241307735443, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.2641293704509735, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.21671676635742188, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.1884133368730545, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.16265709698200226, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.14023487269878387, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.12222591042518616, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.1090625524520874, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.09562640637159348, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.08616029471158981, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.0789809599518776, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.0736822560429573, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.06985227018594742, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.0660192221403122, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.06373610347509384, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.063059002161026, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.06209529936313629, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.06109163537621498, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.061202678829431534, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.06061846762895584, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.059809356927871704, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.05883330479264259, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.05879471078515053, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.062369946390390396, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.09033971279859543, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.09475966542959213, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.09468385577201843, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.06636173278093338, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.10583490133285522, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.10025116801261902, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.13066618144512177, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.1551373451948166, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.18182286620140076, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.18263189494609833, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.12414630502462387, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.677703320980072, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.7702437043190002, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.17311507936507936, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.18973214285714285, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.2251984126984127, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.2693452380952381, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.3382936507936508, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.4476686507936508, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.6217757936507936, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.7038690476190477, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.7919146825396826, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.8745039682539683, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9040178571428571, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9298115079365079, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9419642857142857, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9479166666666666, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9538690476190477, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9610615079365079, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.964781746031746, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9682539682539683, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9719742063492064, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9744543650793651, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9747023809523809, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9751984126984127, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9761904761904762, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9769345238095238, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9774305555555556, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9784226190476191, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.980406746031746, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9813988095238095, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9818948412698413, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9816468253968254, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9818948412698413, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9828869047619048, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9838789682539683, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9831349206349206, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9786706349206349, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9796626984126984, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9799107142857143, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9836309523809523, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9811507936507936, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.982390873015873, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9811507936507936, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9776785714285714, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9751984126984127, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9761904761904762, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9809027777777778, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9766865079365079, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9709821428571429, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.016735490498117123, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.034557213568848395, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.06032450363216719, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.08219717023564077, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.13309449358775488, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.22992762548986206, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.4136745706905917, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.5413604281411769, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.7082981156982342, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.8506236215492942, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.8906662648365824, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9215277946964963, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9348626746298446, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9404713910673185, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9473811221062615, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9541031796983889, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9582990412412927, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9626988438785604, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9672850936656049, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9704064502426578, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9712101034433199, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.971790499643611, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.973635281533471, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9753090782105707, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9755540207200747, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9767111436866032, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9791703014349048, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9798108780865353, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9803463480120314, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9798937499254976, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9802706424787011, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9799929346812568, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9811617207623486, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9797089620423182, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9762312443118502, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9789173840583972, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9774720863475389, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9798136484260139, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9793231970967201, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9784291904844354, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9778905769835973, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9748802422833669, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.969680541844685, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9737081493933853, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.979751282660223, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9731652763092293, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9677291355304322, "id_best": 34, "lr_best": 0.0015299999999999997, "wd_best": 0.05, "train/loss_best": 0.0009828604012727738, "validation/loss_best": 0.05879471078515053, "validation/acc_best": 0.9838789682539683, "validation/f1_best": 0.9811617207623486} +{"epoch": 10, "train/lr": 0.00021091808096876188, "train/loss": 0.5125776031613349, "train/grad": 0.060282892603427174, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.7178125, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.6893463134765625, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.6370184326171877, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.5770697021484374, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.508123779296875, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.3924827575683594, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.2185591888427734, "train/loss_007_lr6.2e-02_wd1.0e+00": 1.8901995468139647, "train/loss_008_lr7.4e-02_wd1.0e+00": 1.357376914024353, "train/loss_009_lr8.7e-02_wd1.0e+00": 1.0102991318702699, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.7333819934725762, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.46571602918207644, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.3351270033419132, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.2421244005486369, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.1950173480436206, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.16560952948406338, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.13793802924454213, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.11345989097841085, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.09356453066691756, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.07874772911891341, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.06349062671884895, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.051347106555476786, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.04028604392893612, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.030940883764997124, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.02345373833552003, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.016394196394830942, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.011577146090567113, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.00854549371637404, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.005662775943055749, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0036365800630301236, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0024386355187743904, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.0016902997624129057, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.0010916792694479227, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.000862687285989523, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.0005721662659198046, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.0008523360081017017, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.003079832121729851, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.004097475251182914, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.014749310277402401, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.0024840873293578624, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.0074416459165513515, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.003960361303761602, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.021483901496976612, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.029676149813458324, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.026128601375967266, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.02387614540755749, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.01887745109386742, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.07204513494856656, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.06658585106953979, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.009336075508035719, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.009389385576359927, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.009484290855471044, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.009587972473818809, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.009694031944964081, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.009841080117039382, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.010056141382083297, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.011316266627982258, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.011323439688421786, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.010780589138157666, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.011259166342206299, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.011281343312002718, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.010944257783703506, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.010395588502287865, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.00983421121025458, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.009311702398117632, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.008732377644628286, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.008103109668008984, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.007402398000704124, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.006826568300602957, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.006179985553608276, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.005574418988544494, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.004965570008498617, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.004365734350285493, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.003747218340577092, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.003055601872038096, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0024682534456951545, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0019701107215951198, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0013822081728721968, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0008896765843383037, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0005861301217373693, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.00042126021515286993, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.000262953466608451, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.00021202288606218646, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0001639249852814828, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.00027717769598893937, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0016401179240551754, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0015950565993216514, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.00345925251547186, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0010491315945978387, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.002648861259859814, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0015769523712418731, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.004803093007068071, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.006473293257925548, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0057137561001421484, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0062252702771201564, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.005555949476916453, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.017201952197006307, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.017774991614000254, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.7020537853240967, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.67210054397583, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.61664080619812, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.5527055263519287, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.478757858276367, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.3534915447235107, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.159064292907715, "validation/loss_007_lr6.2e-02_wd1.0e+00": 1.775823950767517, "validation/loss_008_lr7.4e-02_wd1.0e+00": 1.2642407417297363, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.9401564002037048, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.6660522818565369, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.4303114712238312, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.31455671787261963, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.237718403339386, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.19878540933132172, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.17431877553462982, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.15074636042118073, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.12987644970417023, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.11345464736223221, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.10191549360752106, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.09103117883205414, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.08344243466854095, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.07789230346679688, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.07417227327823639, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.07104366272687912, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.0682513415813446, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.06655368208885193, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.06650654226541519, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.06495129317045212, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.06336626410484314, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.06293711811304092, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.06225021556019783, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.0618802085518837, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.06017815321683884, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.05808870494365692, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.06226310878992081, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.07191096246242523, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.06452613323926926, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.08390781283378601, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.07386449724435806, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.07777586579322815, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.0830540806055069, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.12815657258033752, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.14400599896907806, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.10448642075061798, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.17601047456264496, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.09822291135787964, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.37106263637542725, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.6914583444595337, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.17857142857142858, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.21502976190476192, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.2527281746031746, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.31572420634920634, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.40153769841269843, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.5548115079365079, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.654265873015873, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.7527281746031746, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.8363095238095238, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.8918650793650794, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9174107142857143, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9377480158730159, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9474206349206349, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9523809523809523, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9575892857142857, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9630456349206349, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9672619047619048, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9709821428571429, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9719742063492064, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9742063492063492, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9742063492063492, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9751984126984127, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9754464285714286, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9747023809523809, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9761904761904762, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9781746031746031, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9794146825396826, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9801587301587301, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9821428571428571, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9821428571428571, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9818948412698413, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9826388888888888, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9836309523809523, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9828869047619048, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9813988095238095, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9858630952380952, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9831349206349206, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9826388888888888, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9836309523809523, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9836309523809523, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9784226190476191, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9774305555555556, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9816468253968254, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9769345238095238, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9821428571428571, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9813988095238095, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9677579365079365, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.013885104794195705, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.023179330174948394, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.05492674502606907, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.07255057137162521, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.11437932947955544, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.1826551914164168, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.3463030155376063, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.44934122454953335, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.6327627452728586, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.7928316573041805, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.8776921638416768, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9066232560787848, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9302228051398693, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9397003835567238, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9459584636587699, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9519708081974275, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9582443838072081, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9616594703900668, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.966049830698268, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9673252877382963, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9694979064688334, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9701802717756614, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9710765856732664, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9716288251381711, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9705770676642028, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.972918802950798, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9753245106041862, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.977733968057711, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9785703046838233, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9806141717055512, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9807488223789326, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.980805997752017, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9806408214275151, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9814481923078678, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9798074906379289, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9785772999639161, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9833050845243146, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9812179308493237, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9802318832561399, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9818253276989986, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9808278407380422, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9773687923180913, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9764785979221545, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9796641208340832, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9755971152263301, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9809309340508331, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9790099169788969, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9642623697727428, "id_best": 37, "lr_best": 0.00249, "wd_best": 0.05, "train/loss_best": 0.004097475251182914, "validation/loss_best": 0.06452613323926926, "validation/acc_best": 0.9858630952380952, "validation/f1_best": 0.9833050845243146} +{"epoch": 11, "train/lr": 0.00018113997589164516, "train/loss": 0.4846209478378296, "train/grad": 0.050955908205360174, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.6974285888671874, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.66513671875, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.604874267578125, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.535350341796875, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.454578399658203, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.31654670715332, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.0949958419799803, "train/loss_007_lr6.2e-02_wd1.0e+00": 1.6755430316925048, "train/loss_008_lr7.4e-02_wd1.0e+00": 1.1959481477737426, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.8756840181350708, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.6145234316587448, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.40796517990529535, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.30145179003477096, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.22598569899797438, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.1839492844417691, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.1563856548257172, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.12976504182443022, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.10614529641345144, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.08706289588473737, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.07316792102530599, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.05931827263906598, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.04804086292162538, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.03751259750686586, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.028222975153476, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.020643796231597664, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.013704768773168325, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.009225081400945783, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.006445876378566026, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0039004264026880264, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0023690545186400413, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0016708566341549157, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.0012584810703992844, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.0009003283362835645, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.000723673440515995, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.00048727826215326785, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.0005041107814759016, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.0015497657656669617, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.0006275308597832918, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.00157988210208714, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.0003284810576587915, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.0003416146896779537, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.0031918451096862553, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.007644419427961111, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.009338268795982003, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.011325017223134637, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.009953735973685979, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.008622734127566218, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.03256917300634086, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.02193769729696214, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.009435718504246324, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.009498440134339035, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.009613299265038223, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.009734360771253704, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.009853927607182414, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.010014343014918268, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.010400510837789624, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.011909031043760478, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.010835380982607603, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.010952981757000088, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.011197500596754253, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.01090998887317255, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.01049113469896838, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.009923760720994323, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.00939782062312588, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.008910302370786667, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.008355749978218228, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.0077495117811486125, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.007053194445325062, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.006496324017643928, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.005893564571160823, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.005308651080122217, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0046738273545634005, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.003998037717537955, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0033032654313137756, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.002522383179166354, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0019135505359736272, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.001475861487851944, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0009740924686775543, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0005773703212616965, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0003980613596650073, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0003019027913978789, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0002154779627744574, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.00017353137896861882, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0001222799359493365, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.00013693484038412862, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.001039383441852806, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.00044946807422093117, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0008358329506302198, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.00016447739341174383, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.00030834646092898766, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.001137660001178773, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.002127502446909233, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.002626387692823471, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.002829300396728742, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0028064965518595475, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0025308776954497602, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.008931489088846232, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.008771473519452285, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.6866705417633057, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.6530263423919678, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.59004282951355, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.5167524814605713, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.4313268661499023, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.283365488052368, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.0347373485565186, "validation/loss_007_lr6.2e-02_wd1.0e+00": 1.581343173980713, "validation/loss_008_lr7.4e-02_wd1.0e+00": 1.1302286386489868, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.8143188953399658, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.5647242665290833, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.3752271831035614, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.2816500961780548, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.21892181038856506, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.18478907644748688, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.16297008097171783, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.14143970608711243, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.12200120836496353, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.1065845638513565, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.09613118320703506, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.08598816394805908, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.07913239300251007, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.07438872009515762, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.07126016169786453, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.06929697841405869, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.06747090816497803, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.06628163903951645, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.06593717634677887, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.06412793695926666, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.06272844225168228, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.062402885407209396, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.06194262206554413, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.06049152836203575, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.05894407629966736, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.057079944759607315, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.05997234210371971, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.07541191577911377, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.05494799464941025, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.061384811997413635, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.0587371326982975, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.06605041027069092, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.06702836602926254, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.11722180247306824, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.0872463658452034, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.11041915416717529, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.13225969672203064, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.06255470961332321, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.35942405462265015, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.4631614089012146, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.1728670634920635, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.19717261904761904, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.2408234126984127, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.2777777777777778, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.34325396825396826, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.4392361111111111, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.6009424603174603, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.6924603174603174, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.7973710317460317, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.8638392857142857, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9025297619047619, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9273313492063492, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9417162698412699, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9479166666666666, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9528769841269841, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9600694444444444, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9652777777777778, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9702380952380952, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9729662698412699, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9739583333333334, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9761904761904762, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9769345238095238, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9771825396825397, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9771825396825397, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9776785714285714, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9774305555555556, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9779265873015873, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9796626984126984, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9806547619047619, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9816468253968254, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9813988095238095, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9816468253968254, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9821428571428571, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9836309523809523, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.984375, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.982390873015873, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9866071428571429, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9846230158730159, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9858630952380952, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.984375, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9873511904761905, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9794146825396826, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.986359126984127, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9831349206349206, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9799107142857143, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9858630952380952, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9816468253968254, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9756944444444444, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.01626883999916295, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.040567595582894016, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.0659032799908391, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.08414993718652963, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.13550741267510286, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.21900928985218365, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.3935580867986175, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.5220242553930645, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.7204285097694716, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.8373771844218822, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.8887241450292869, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9171036236450473, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9344587721874111, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9401038993227983, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9455865676882669, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9543556884769138, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9602678032986625, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9657021910018331, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9693389293909815, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9707542727998412, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.973404780277931, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9735558298910599, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9749675481733, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9742623808961126, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9757910758364801, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9748438108490863, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9755721679697045, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.977982053037495, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9793443350984594, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9800642835194557, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9799653483330841, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9803543903690448, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9798956692076951, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9810540527702974, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.981388904095753, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9808746416608488, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.98421714996782, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9833300167975753, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9836075085739091, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9839667660513763, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9853521929996648, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9776072768199814, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9834277252091612, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9804208557780969, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9789196945204298, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9847325373054522, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9793119111200852, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.973309447813165, "id_best": 41, "lr_best": 0.0048, "wd_best": 0.05, "train/loss_best": 0.0031918451096862553, "validation/loss_best": 0.06702836602926254, "validation/acc_best": 0.9873511904761905, "validation/f1_best": 0.9853521929996648} +{"epoch": 12, "train/lr": 0.0001499999999999999, "train/loss": 0.4601671555638313, "train/grad": 0.047215741481632, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.6762957763671875, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.6400277709960935, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.5719720458984376, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.4926496887207032, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.399860076904297, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.2383102416992187, "train/loss_006_lr5.3e-02_wd1.0e+00": 1.9580332946777343, "train/loss_007_lr6.2e-02_wd1.0e+00": 1.493289451599121, "train/loss_008_lr7.4e-02_wd1.0e+00": 1.0677428567409515, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.7511533105373382, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.5247776569426059, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.353288312703371, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.26604252118617294, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.20283826999366283, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.1664774570427835, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.1424067553691566, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.11868586194701493, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.097028025155887, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.07965150191448629, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.06680296372622252, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.05367411459796131, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.04286842266097665, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.03268910585902631, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.023896656148135662, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.01675852878019214, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.010485145356506109, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.0067763178795576095, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.004709609551355243, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0030036237183958293, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0019469239097088574, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0014074734039604664, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.0010859679710119963, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.0007949742674827576, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.0006598309334367513, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.0004601784236729145, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.00035665363073349, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.0007755518611520529, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.00018813167698681355, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.0002497920021414757, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.00016336779110133647, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.0001950418297201395, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.00020855231210589409, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.005587247954681515, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.0026109903957694768, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.0014586192462593317, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.0015613253228366375, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.0006070453021675349, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.011323566567152738, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.014354428816586733, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.009531695523764937, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.009596012390684337, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.009713166183792055, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.009831638163886965, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.009941471277270466, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.010098808330949395, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.010868703667074441, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.011913481815718115, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.010605335524305702, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.010980018659029155, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.011065861324314029, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.010675933721940964, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.010254870674107224, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.009629510168451816, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.009047793962527067, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.008536830767989159, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.007976466983091086, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.007365900048753247, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.006697856473037973, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.006157244024798274, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.005570485449861735, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.004974627368501388, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.004322977234260179, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.003639469146728516, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.002936741953599267, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.002187925775506301, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.001606830801756587, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0011750806565396488, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0007539722498768242, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0004745986757188803, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0003365946718986379, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.00025927516871888657, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.000191875980963232, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.00015614960530001553, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.00011143382618683973, "train/grad_035_lr6.0e+00_wd1.0e+00": 9.298807101004058e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0004707192466548804, "train/grad_037_lr8.3e+00_wd1.0e+00": 8.415117136564731e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0001620764830670396, "train/grad_039_lr1.2e+01_wd1.0e+00": 6.260932306645373e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.00010418164335561642, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0001440978670888171, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0016509159512049364, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0007620981400128812, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0007994597470049314, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0007794311167502599, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.00034973964428729686, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.003730862923498361, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.005919023527403617, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.673367977142334, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.636475086212158, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.5668978691101074, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.485508441925049, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.389653444290161, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.2204396724700928, "validation/loss_006_lr5.3e-02_wd1.0e+00": 1.9136340618133545, "validation/loss_007_lr6.2e-02_wd1.0e+00": 1.4410045146942139, "validation/loss_008_lr7.4e-02_wd1.0e+00": 1.0373101234436035, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.7196704745292664, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.5022815465927124, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.3380093276500702, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.26038658618927, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.2056952714920044, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.17464950680732727, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.15418066084384918, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.13399620354175568, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.1155836433172226, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.10134698450565338, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.09159991890192032, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.08256426453590393, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.07664322108030319, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.07249927520751953, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.07008131593465805, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.06870954483747482, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.0675245076417923, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.06672801822423935, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.06664146482944489, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.06505338847637177, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.06375710666179657, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.06357879191637039, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.06264752894639969, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.0617973767220974, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.05956196039915085, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.05675007775425911, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.05870349705219269, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.06373356282711029, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.05300426483154297, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.055561743676662445, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.05523768067359924, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.05838484317064285, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.058228496462106705, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.07513914257287979, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.06938990950584412, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.07886429876089096, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.07585596293210983, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.05082274600863457, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.26072314381599426, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.38980886340141296, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.17113095238095238, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.1753472222222222, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.2130456349206349, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.2562003968253968, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.3003472222222222, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.3725198412698413, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.4972718253968254, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.6237599206349206, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.720734126984127, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.8184523809523809, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.8740079365079365, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.910218253968254, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9317956349206349, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9427083333333334, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9513888888888888, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9568452380952381, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9620535714285714, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9672619047619048, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9709821428571429, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.972718253968254, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9747023809523809, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9764384920634921, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9766865079365079, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9764384920634921, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9771825396825397, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9766865079365079, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9779265873015873, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9776785714285714, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9794146825396826, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9799107142857143, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.982390873015873, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9818948412698413, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9813988095238095, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9826388888888888, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9833829365079365, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9833829365079365, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9838789682539683, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9868551587301587, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9856150793650794, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9856150793650794, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9858630952380952, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9868551587301587, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9858630952380952, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9875992063492064, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9858630952380952, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9851190476190477, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9868551587301587, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9813988095238095, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9732142857142857, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.014428983036925398, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.019077032326521262, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.05299903872605659, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.07211918589991072, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.10009419873046446, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.1571425819943286, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.28286732716405194, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.4143139386337218, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.575791165648064, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.7598644899571995, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.8519709985048747, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.8973263432126715, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9243431447760851, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9351386183341438, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9443704768301283, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9506898298811902, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.955236565091737, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9611888406177366, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9655266572760477, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9680496140078629, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9701449141767249, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9716216881443284, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9721022685051725, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9728485687831853, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9750226846194949, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9748571952004648, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9757098997983272, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9755024694635358, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9775107878761782, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9782740803646855, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9806780017346299, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9803749523882549, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9801235889329393, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9803002784881488, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9808587969614881, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9800329357948874, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9805448605334118, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9842779899690081, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9842247467027507, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.983039361279275, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9852013303451115, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9847540675736394, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9844258443385059, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9844148172399583, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9853455846047919, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9833953013718518, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9852158309169677, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.979106607073115, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.971065408422822, "id_best": 43, "lr_best": 0.006599999999999999, "wd_best": 0.05, "train/loss_best": 0.0026109903957694768, "validation/loss_best": 0.06938990950584412, "validation/acc_best": 0.9875992063492064, "validation/f1_best": 0.9844148172399583} +{"epoch": 13, "train/lr": 0.00011886002410835478, "train/loss": 0.44255323216319087, "train/grad": 0.045494131855666635, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.660675354003906, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.6215310668945313, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.5475259399414063, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.460929260253906, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.358831024169922, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.1778246688842775, "train/loss_006_lr5.3e-02_wd1.0e+00": 1.8432533359527588, "train/loss_007_lr6.2e-02_wd1.0e+00": 1.3701375389099122, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.9807940337061882, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.6681573140621185, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.4730698366463184, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.32055901154875754, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.2456770285218954, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.18779836554080248, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.15309185786172747, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.129935521222651, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.10690169416368007, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.08582831900566816, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.06906688941642641, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.056965084671974184, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.04465139917097986, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.03458635911345482, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.025494076646864414, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.018018952319398523, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.012406893959268927, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.007729401802644134, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.005061182826757431, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.003626086683943868, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0024127104319632054, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0015991235058754683, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0011775870248675346, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.0009263949282467365, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.0007058251742273569, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.0005828123912215233, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.0004148848634213209, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.00032190204598009587, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.00019965658895671368, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.00018203426152467727, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.0005315000470727682, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.00016311250627040863, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.0001398150622844696, "train/loss_041_lr1.6e+01_wd1.0e+00": 9.922722354531288e-05, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.0004973193071782589, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.00041788610629737375, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.00022361516021192075, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.00021991990506649018, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.00048074545338749886, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.0020887281745672224, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.0015965679939836264, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.009700542758218944, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.009764593120198697, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.009875944154337048, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.009981602195184678, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.010076918676495551, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.010238086236640812, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.011418449692428112, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.011606777389533817, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.010740193270612508, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.011238940302282572, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.011236491752788425, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.010794575640466065, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.010326936759520322, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.009650174432899804, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.009056141718756407, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.008528761768247932, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.007927954732440411, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.007278444619150832, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.006587257203646005, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.006020004715537652, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.005368646998540498, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.004717536855023355, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.004008869036915712, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0032703145904815754, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0025673352266312576, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0018277143735031132, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0012761937199684326, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0009214547277952078, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0006157310064008925, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.00041405116953683316, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.00030012285251359574, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0002333436464687111, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0001734253623180848, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.00014290651140981935, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.00010057078116005868, "train/grad_035_lr6.0e+00_wd1.0e+00": 8.666999914566987e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 7.782842690630787e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 6.627106897667545e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.00019386567117720687, "train/grad_039_lr1.2e+01_wd1.0e+00": 6.166404229361433e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 6.707132107749204e-05, "train/grad_041_lr1.6e+01_wd1.0e+00": 4.8867460674841825e-05, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.00019503320518840183, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0001708729715227264, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.00011935294103921024, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.00012981175512017274, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.00020716917271329294, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0015598182806140374, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0015829058503049834, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.6626882553100586, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.6230576038360596, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.548034906387329, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.459942579269409, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.3556113243103027, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.16798996925354, "validation/loss_006_lr5.3e-02_wd1.0e+00": 1.8138371706008911, "validation/loss_007_lr6.2e-02_wd1.0e+00": 1.3471590280532837, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.9692964553833008, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.6537611484527588, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.46231189370155334, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.314318984746933, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.247019961476326, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.1974116414785385, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.1684727519750595, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.1490621268749237, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.12959963083267212, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.11176415532827377, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.09830819070339203, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.08934469521045685, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.08110065758228302, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.07562615722417831, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.07210797071456909, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.07005508989095688, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.0691143348813057, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.06847958266735077, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.06768473982810974, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.0674232542514801, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.06573427468538284, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.06426101922988892, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.06404346227645874, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.0636415183544159, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.0626106858253479, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.06023380532860756, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.05728515610098839, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.05855446308851242, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.06179952993988991, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.0520777702331543, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.05564311146736145, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.05397811159491539, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.05574315786361694, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.054932381957769394, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.06223120912909508, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.06128754839301109, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.06725193560123444, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.0664791688323021, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.04786141589283943, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.20266415178775787, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.30333006381988525, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.17212301587301587, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.17981150793650794, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.22321428571428573, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.2666170634920635, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.31299603174603174, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.3888888888888889, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.5319940476190477, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.6393849206349206, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.746031746031746, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.841765873015873, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.8841765873015873, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9166666666666666, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9332837301587301, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9449404761904762, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9523809523809523, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9575892857142857, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9632936507936508, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9682539682539683, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9717261904761905, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9737103174603174, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9751984126984127, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9766865079365079, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9761904761904762, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9769345238095238, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9771825396825397, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9771825396825397, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9774305555555556, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9776785714285714, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9794146825396826, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9799107142857143, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9818948412698413, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9813988095238095, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9813988095238095, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.982390873015873, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9833829365079365, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9838789682539683, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9841269841269841, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9873511904761905, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9851190476190477, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9858630952380952, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9866071428571429, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9866071428571429, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9868551587301587, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9868551587301587, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9868551587301587, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9851190476190477, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9873511904761905, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9833829365079365, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9749503968253969, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.015491588460140286, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.023764707122586357, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.05795666042432503, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.07683139092290592, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.10676415278489083, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.17003093180427975, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.32488103584641775, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.4324081244440831, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.6204093335736536, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.8006218774747671, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.8659944486650107, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9055848591793175, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9251027498644743, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9370165196951662, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9465792345554467, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9508250427699322, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9569965145305785, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9629041319625432, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9672685886951798, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9695071240772393, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9717502796596447, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9735609427600006, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9732948930226399, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9751614540038521, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9752444517767627, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9748216205360892, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9753975441728256, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9750113728222447, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9778649003823888, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9784263719388457, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.980394260935225, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9799783474397772, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9799075286117165, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9803106439306956, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.98078627146215, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9803525190524454, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9813953041172518, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9845131650209638, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9838085223841898, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9835749078578876, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9859906001632255, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9843951741249446, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9856990961165119, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9844184384078344, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9863819723299301, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9845535884954637, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9860739506215198, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9803224084578972, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9727789632411205, "id_best": 37, "lr_best": 0.00249, "wd_best": 0.05, "train/loss_best": 0.00018203426152467727, "validation/loss_best": 0.0520777702331543, "validation/acc_best": 0.9873511904761905, "validation/f1_best": 0.9845131650209638} +{"epoch": 14, "train/lr": 8.9081919031238e-05, "train/loss": 0.43525714620947836, "train/grad": 0.04456586621701717, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.6619668579101563, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.6203958129882814, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.54162109375, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.449060974121094, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.339159927368164, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.141208152770996, "train/loss_006_lr5.3e-02_wd1.0e+00": 1.7717844676971435, "train/loss_007_lr6.2e-02_wd1.0e+00": 1.3079422104358673, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.9335078340768814, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.6249997471272946, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.44824590161442757, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.306894446015358, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.23885786090046168, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.18457809954881668, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.15176693726330995, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.1296091328933835, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.10729233695194125, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.08646944758482278, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.06969028663821518, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.057278501754626635, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.044403861155733464, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.03374438832513988, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.024240627745166422, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.01659881099127233, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.011099858870729805, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.006818473888561129, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.004495429946109653, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0032519687712192534, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0021830071602016686, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0014792649261653424, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0011015546321868897, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.0008712836448103189, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.0006559187266975641, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.0005445283465087414, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.00038889379240572455, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.0003225344326347113, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.00016404422000050546, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.00017012536525726318, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.000118269519880414, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.0001669761724770069, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.00015976651571691035, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.00013054460287094117, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.00013582092709839343, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.00011231271550059319, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.0001760705094784498, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.0003096801321953535, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.0006426701787859201, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.00033292408101260663, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.0004509890452027321, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.009572818593587726, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.009648078780155629, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.00978165281470865, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.009913031260948628, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.010033809125889092, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.010260258531197906, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.011630096132867038, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.01133429942186922, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.010839461325667798, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.011220182492397725, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.011136831301264465, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.010640134336426854, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.010166022549383343, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.009499274126719684, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.0089107835595496, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.008368956574704498, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.007748250552685932, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.007074810565682128, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.006367390246596188, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.005805592921096832, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.005185596715891734, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.004540862775756977, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.003823274254100397, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0030845417390810326, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0023618140531471, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0016092862267396413, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0010957073769532143, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0007955621965811588, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0005346726893913, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0003607095158076845, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0002632287979213288, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0002045689825536101, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.00015487404678424355, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.00012864179472671822, "train/grad_034_lr5.1e+00_wd1.0e+00": 9.547645170641772e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 8.060224226028368e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 5.6678538041978757e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 5.9884819200988204e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 4.994228062514594e-05, "train/grad_039_lr1.2e+01_wd1.0e+00": 6.092313234717039e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 6.598415262544677e-05, "train/grad_041_lr1.6e+01_wd1.0e+00": 5.289234341773863e-05, "train/grad_042_lr1.9e+01_wd1.0e+00": 7.218807543445394e-05, "train/grad_043_lr2.2e+01_wd1.0e+00": 5.6359759487918384e-05, "train/grad_044_lr2.6e+01_wd1.0e+00": 8.17226557126105e-05, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0001442339192851705, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.00022608792018445457, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0003866695296781837, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.000589783164395865, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.654472827911377, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.6128153800964355, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.5336520671844482, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.4404704570770264, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.329503297805786, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.126940965652466, "validation/loss_006_lr5.3e-02_wd1.0e+00": 1.7421969175338745, "validation/loss_007_lr6.2e-02_wd1.0e+00": 1.2859996557235718, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.9209577441215515, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.6117731928825378, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.437121719121933, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.3002820611000061, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.2388174831867218, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.19189245998859406, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.16413584351539612, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.1453065127134323, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.1263168305158615, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.10906784236431122, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.0959911048412323, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.08748520165681839, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.079731784760952, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.07461968064308167, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.07115393877029419, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.06945719569921494, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.06898332387208939, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.068592868745327, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.06818539649248123, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.06802632659673691, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.06627467274665833, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.06453806906938553, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.06432288885116577, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.06346199661493301, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.06278158724308014, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.060400038957595825, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.05719790980219841, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.058754224330186844, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.060802359133958817, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.05134078487753868, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.054570272564888, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.05271816998720169, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.054246388375759125, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.05288571119308472, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.05734613537788391, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.05669868737459183, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.0615701824426651, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.06197046861052513, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.04476451128721237, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.1751626580953598, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.25272297859191895, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.1728670634920635, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.1827876984126984, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.22891865079365079, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.27356150793650796, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.32688492063492064, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.4072420634920635, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.5592757936507936, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.6540178571428571, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.7633928571428571, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.8541666666666666, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.8908730158730159, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9216269841269841, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9360119047619048, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9471726190476191, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9536210317460317, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9590773809523809, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9640376984126984, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9689980158730159, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9729662698412699, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9754464285714286, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9756944444444444, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9749503968253969, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9764384920634921, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9756944444444444, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9759424603174603, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9754464285714286, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9759424603174603, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9774305555555556, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9799107142857143, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9809027777777778, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9813988095238095, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9821428571428571, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9813988095238095, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9828869047619048, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9836309523809523, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.984375, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9841269841269841, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9875992063492064, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9853670634920635, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9858630952380952, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.986359126984127, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9871031746031746, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9875992063492064, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9873511904761905, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9866071428571429, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9851190476190477, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9871031746031746, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9833829365079365, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9774305555555556, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.016272334696900786, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.02707367610766582, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.06048536734450159, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.0824910182596677, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.12007684166773037, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.18632999657154692, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.3528700036230626, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.45292214765404604, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.6518053681472464, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.8208997683924741, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.8760742349990636, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9114764273263719, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9290375879180786, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9396583891907975, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9472888523765066, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9523647493367549, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9578337547407316, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9637152066912146, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9688003643466998, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9716233689231706, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9714417627465208, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9704070229172773, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9726235275737893, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9725208943213043, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9727670821297991, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9725647132900125, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.973080257125669, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9742716161941087, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9777790813452635, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9793864514445058, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9798954758894696, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9811441488941367, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9797172111080353, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.98097593010688, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9809646683653904, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9812839558923213, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9814521924131261, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.984687592105529, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9843651370573832, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9835749078578876, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9858106383999125, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9849781334006371, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9866559358906366, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.985185623548927, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9861996439738786, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9835870888674203, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9861347571380977, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9809189339704548, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9755061648266028, "id_best": 37, "lr_best": 0.00249, "wd_best": 0.05, "train/loss_best": 0.00017012536525726318, "validation/loss_best": 0.05134078487753868, "validation/acc_best": 0.9875992063492064, "validation/f1_best": 0.984687592105529} +{"epoch": 15, "train/lr": 6.196799573888289e-05, "train/loss": 0.4275392758846283, "train/grad": 0.043953359369188545, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.6501922607421875, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.6072152709960936, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.5254052734375, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.429269104003906, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.3147534942626953, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.105066795349121, "train/loss_006_lr5.3e-02_wd1.0e+00": 1.7094412994384767, "train/loss_007_lr6.2e-02_wd1.0e+00": 1.2560014629364014, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.8942724591493607, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.5932178665697575, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.4283291156589985, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.2939660618454218, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.23054427560418844, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.17908660802990198, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.14764775667339564, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.12600390440784395, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.10413545705378055, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.08364181898534298, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.06728699021041393, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.05531785361468792, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.04286471750587225, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.03269483327865601, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.023425800036638977, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.015973928663879634, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.010523451045155525, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.006209410540759563, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.004036916894838214, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.002925607869401574, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.001987961791455746, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0013588258158415557, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0010222132410854102, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.0008112060278654098, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.0006292412616312504, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.0005257688276469707, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.00038630864582955837, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.0003030697349458933, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.00016467847861349584, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.00019034783355891704, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.00011990120634436608, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.00018330635502934457, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.00016744360327720643, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.0001596333086490631, "train/loss_042_lr1.9e+01_wd1.0e+00": 9.909966960549355e-05, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.0001346022728830576, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.0002123485505580902, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.0003816323447972536, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.0007652391958981752, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.00030267786234617234, "train/loss_048_lr5.0e+01_wd1.0e+00": 6.952800787985325e-05, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.009662646274082363, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.009733473882079124, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.009853729223832488, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.009965369997080415, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.010062834632117301, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.01028985918033868, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.011762546906247735, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.011063668057322501, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.010716566760092973, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.011043887042906136, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.010896670289803297, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.010390900494530796, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.009927596380002797, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.009275615278165788, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.008713175270240753, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.008191654096590355, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.007577690969919786, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.006901121198898181, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.006196189292240888, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.005638085487880744, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.004998798160813749, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.004328492260538041, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.003579852001857944, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.00281879181653494, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.002102259987150319, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.001402967451576842, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0009583027209737338, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0007049710118008079, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0004851665932073956, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0003313417729805224, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.00024792949901893737, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.00019457555126791703, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.00014897693479724695, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.00012430052016497938, "train/grad_034_lr5.1e+00_wd1.0e+00": 9.265484981369809e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 7.633772146618867e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 5.436749581804179e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 6.182507951507432e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 4.581761642214133e-05, "train/grad_039_lr1.2e+01_wd1.0e+00": 5.862891545575621e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 6.631467848421834e-05, "train/grad_041_lr1.6e+01_wd1.0e+00": 5.678311487145038e-05, "train/grad_042_lr1.9e+01_wd1.0e+00": 6.061465374017416e-05, "train/grad_043_lr2.2e+01_wd1.0e+00": 6.055433998426451e-05, "train/grad_044_lr2.6e+01_wd1.0e+00": 9.274293672660861e-05, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0001448743479238601, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.00024056373758867266, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.00024509809466971317, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0002935037642101741, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.6486551761627197, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.605605363845825, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.5235960483551025, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.4267630577087402, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.3112587928771973, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.0979928970336914, "validation/loss_006_lr5.3e-02_wd1.0e+00": 1.6948187351226807, "validation/loss_007_lr6.2e-02_wd1.0e+00": 1.2475591897964478, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.8883711695671082, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.5853267312049866, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.42049795389175415, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.29070189595222473, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.23283806443214417, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.1876976042985916, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.1606268584728241, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.14201194047927856, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.12353530526161194, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.10645175725221634, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.0938059613108635, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.0855378583073616, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.0779494196176529, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.07288970798254013, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.06977276504039764, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.06832516193389893, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.06800562888383865, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.0681091770529747, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.06796030700206757, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.06787604838609695, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.06604111939668655, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.06458956003189087, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.06432268023490906, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.06364550441503525, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.06271884590387344, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.060503315180540085, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.05709872022271156, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.05831727012991905, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.06003521382808685, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.05112822726368904, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.05434881150722504, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.05200712010264397, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.05308956652879715, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.051338352262973785, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.05431268364191055, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.05445775389671326, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.059108272194862366, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.059284307062625885, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.04407758265733719, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.15334077179431915, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.2321900576353073, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.17336309523809523, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.18675595238095238, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.23363095238095238, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.27976190476190477, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.33606150793650796, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.4193948412698413, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.5739087301587301, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.6624503968253969, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.7752976190476191, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.8581349206349206, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.8938492063492064, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9250992063492064, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9372519841269841, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9484126984126984, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9543650793650794, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9600694444444444, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9645337301587301, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9699900793650794, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9732142857142857, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9759424603174603, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9769345238095238, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9769345238095238, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9776785714285714, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9769345238095238, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9766865079365079, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9766865079365079, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9766865079365079, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9779265873015873, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9801587301587301, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9806547619047619, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9811507936507936, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9811507936507936, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9809027777777778, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9831349206349206, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9836309523809523, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.984375, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.984375, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9873511904761905, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9853670634920635, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9858630952380952, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9861111111111112, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9868551587301587, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9875992063492064, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9878472222222222, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9868551587301587, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9853670634920635, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9871031746031746, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9838789682539683, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9779265873015873, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.016776172166589203, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.030919840973407508, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.06282034556916993, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.08846472709240893, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.12780595000712489, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.19725684387165407, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.36740393763374324, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.46645920515708267, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.6731224621461083, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.8276366430215246, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.8787934391581532, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9149152576112178, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9300793329456928, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9406032932567147, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9479301441336951, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9535520595282312, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9574507451126921, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9651161500924337, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9690885870871929, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9722504552420113, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9729545271355485, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9734921668056358, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9743273078253614, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9743079139153549, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9734478247032653, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9738520674295698, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.974134640797666, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9751052669768312, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.978222198994068, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9795300246262083, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9795340085093688, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9794840216155233, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9793668820689828, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9811303020301465, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9809646683653904, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9812040350740192, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9821069496212745, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9845074667320026, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9840347095889586, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9835749078578876, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9853564556914601, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9847635193249408, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.986651098069873, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9856351300722513, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9867136732591888, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9841009645006485, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.986135705773556, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9815006658599785, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9759805365509661, "id_best": 43, "lr_best": 0.006599999999999999, "wd_best": 0.05, "train/loss_best": 0.0001346022728830576, "validation/loss_best": 0.05445775389671326, "validation/acc_best": 0.9878472222222222, "validation/f1_best": 0.9856351300722513} +{"epoch": 16, "train/lr": 3.870405029380728e-05, "train/loss": 0.4219899645447731, "train/grad": 0.04395923848263919, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.648397216796875, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.603656921386719, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.518470458984375, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.4182502746582033, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.2986483764648438, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.0782815742492677, "train/loss_006_lr5.3e-02_wd1.0e+00": 1.668110957145691, "train/loss_007_lr6.2e-02_wd1.0e+00": 1.2251830625534057, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.8673146212100983, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.5707236595451832, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.41242705687880515, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.2828150236606598, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.2214316003769636, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.17143050488084555, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.14085215650498867, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.12003450891934335, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.09892684283666313, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.07944121042266489, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.06367136339657009, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.052229907242581246, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.04012646199204028, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.030217109750956296, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.021486952779814602, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.014583032093942166, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.009567341916263104, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.005633467016741634, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.0036369686014950274, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0026644914876669647, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0018218112364411353, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0012620889116078614, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0009512364491820335, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.0007559973280876874, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.0005859700683504343, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.0004868179839104414, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.00036601043306291105, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.0002928830310702324, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.00015828912146389484, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.00015979436226189138, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.00012078091502189637, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.00017320035956799984, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.0001697452086955309, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.00015272757038474084, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.00011286018416285515, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.0001335565745830536, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.00022847614251077176, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.0003841394558548927, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.0007776480820029974, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.00012407828122377396, "train/loss_048_lr5.0e+01_wd1.0e+00": 7.736478000879288e-05, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.009595682562794536, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.009671314812730997, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.009803387406282126, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.009929564539343119, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.010045839122030885, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.010326823838986456, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.011819598213769496, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.011052657035179436, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.010925641155336053, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.01118371514370665, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.011033361318986863, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.010488801167812199, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.00997771700611338, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.009279323441442102, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.008698010719381272, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.008170401349198074, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.007550325442571193, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.0068736057926435026, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.0061660336796194315, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.005593558172695339, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.0049164200865197925, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.004221141470479779, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.003454530815943144, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.002691820256295614, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.001995994110766333, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0013277744813240133, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0009014433358970564, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0006620482571452158, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0004547799590363866, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.000313030176293978, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.00023326745180384022, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.00018406676515951405, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0001409261900698766, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.00011796165237683454, "train/grad_034_lr5.1e+00_wd1.0e+00": 8.840010295898537e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 7.349844101099734e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 5.160960390639957e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 5.74717954418702e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 4.567119124317287e-05, "train/grad_039_lr1.2e+01_wd1.0e+00": 5.7766245058701314e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 6.526585659969442e-05, "train/grad_041_lr1.6e+01_wd1.0e+00": 5.8238505672250086e-05, "train/grad_042_lr1.9e+01_wd1.0e+00": 6.099150703278156e-05, "train/grad_043_lr2.2e+01_wd1.0e+00": 6.586554763558183e-05, "train/grad_044_lr2.6e+01_wd1.0e+00": 9.278576276187778e-05, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0001551409064472864, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.00022847717069453212, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.00015199616767087588, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.00011745064269621676, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.6451070308685303, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.6010749340057373, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.517194986343384, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.4182236194610596, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.299727201461792, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.0797719955444336, "validation/loss_006_lr5.3e-02_wd1.0e+00": 1.6663236618041992, "validation/loss_007_lr6.2e-02_wd1.0e+00": 1.2250324487686157, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.8682008385658264, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.5697751641273499, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.4105316698551178, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.28504621982574463, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.22908273339271545, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.18520532548427582, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.15864259004592896, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.14024235308170319, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.1219065710902214, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.10492022335529327, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.09260005503892899, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.08441406488418579, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.07695482671260834, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.07193344086408615, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.06887105107307434, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.06763273477554321, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.06751679629087448, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.06780438870191574, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.06780040264129639, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.06771963834762573, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.06593488901853561, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.06451386213302612, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.06437832862138748, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.06369395554065704, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.06265679746866226, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.060335658490657806, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.05705757066607475, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.058342114090919495, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.05956347659230232, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.050717052072286606, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.053683917969465256, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.05157461017370224, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.05300874263048172, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.050704196095466614, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.05286284163594246, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.05319623649120331, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.057279352098703384, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.057256653904914856, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.04297524318099022, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.1485843062400818, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.2200331836938858, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.17385912698412698, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.18874007936507936, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.2390873015873016, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.28596230158730157, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.33978174603174605, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.4263392857142857, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.5796130952380952, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.6659226190476191, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.7819940476190477, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.8621031746031746, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.8938492063492064, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.925843253968254, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9384920634920635, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9496527777777778, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9541170634920635, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9603174603174603, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9650297619047619, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9704861111111112, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9737103174603174, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9756944444444444, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9764384920634921, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9779265873015873, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9779265873015873, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9779265873015873, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9779265873015873, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9769345238095238, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9766865079365079, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9776785714285714, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9801587301587301, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.980406746031746, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9818948412698413, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9818948412698413, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9806547619047619, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9831349206349206, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9836309523809523, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9838789682539683, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9846230158730159, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9875992063492064, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9851190476190477, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9858630952380952, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.986359126984127, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9866071428571429, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9875992063492064, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9875992063492064, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9868551587301587, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9841269841269841, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9866071428571429, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9836309523809523, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9779265873015873, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.01749342239328548, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.03260619208970573, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.06541894370493646, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.09182217883942145, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.13029479124496188, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.20257049884631062, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.37370834383818097, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.4714605001582558, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.6833531477398946, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.8346241139245398, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.8798060209162993, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9167786078910402, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9311986420945508, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.941778627645524, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9474794920552438, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9530877102767076, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.958087592474406, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9652431454737073, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9698029942874721, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9712844126355955, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9725786185571584, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9750297889839843, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.974443378704436, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9755425013091921, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9757600603753903, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9744920121856774, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9740690782400462, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9751485380245379, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9783186754075217, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9793508848233949, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9802905735190793, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9807606362102754, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9791047462198739, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9811706029788825, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9809646683653904, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9807772777821944, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9822846602647525, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.984687592105529, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9838114384437595, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9835749078578876, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9856018908436509, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9845261974482068, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9865981298601415, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9853070713324497, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9865303305105529, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9825367018208282, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9853375440560274, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9810484965043229, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9761509100795646, "id_best": 37, "lr_best": 0.00249, "wd_best": 0.05, "train/loss_best": 0.00015979436226189138, "validation/loss_best": 0.050717052072286606, "validation/acc_best": 0.9875992063492064, "validation/f1_best": 0.984687592105529} +{"epoch": 17, "train/lr": 2.030750443206766e-05, "train/loss": 0.4182752920687199, "train/grad": 0.043535023219883444, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.639088439941406, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.5936904907226563, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.5074224853515625, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.405628509521484, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.284070358276367, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.0589093017578124, "train/loss_006_lr5.3e-02_wd1.0e+00": 1.6406489944458007, "train/loss_007_lr6.2e-02_wd1.0e+00": 1.2019697678089143, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.8471512234210968, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.5565290024876595, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.40325214169919493, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.277704009488225, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.21889331571757795, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.17074413560330867, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.14094761934131383, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.12041071133688092, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.09928999605588615, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.07949586731381714, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.06361474805511534, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.05192824373021722, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.03976605169475079, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.02984504362568259, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.021149782221764325, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.014204932525753975, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.009119890164583921, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.0052970537543296815, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.0034523929003626107, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0025180804915726183, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0017252578400075436, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.001191049702465534, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0008960709534585476, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.0007153324969112873, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.0005512103252112865, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.0004595186933875084, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.0003446727152913809, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.0002817476261407137, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.00014833848923444747, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.00015974515117704867, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.00011542314663529396, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.0001594468206167221, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.00017002659849822522, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.00014267208054661752, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.0001121158991008997, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.0001360417902469635, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.00021086766384541988, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.00032631308771669866, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.0006832089833915234, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.0001337908860296011, "train/loss_048_lr5.0e+01_wd1.0e+00": 8.432501927018166e-05, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.009607236585579812, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.009680336236488073, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.009803553586825728, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.009915029297117144, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.01000801351154223, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.010267789997160435, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.01169059009756893, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.010825753696262836, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.010795593487564474, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.011080369069240988, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.010878608785569668, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.010302269901148974, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.00983250729041174, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.009200338150840252, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.008635232858359813, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.008097484820755198, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.007469402286224067, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.006776504934532568, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.00606850937474519, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.00550313443178311, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.0048495167208602655, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.004159209721256048, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0034062128962250426, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.002652954782533925, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0019493063908885234, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0012748273662873545, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.000857843644625973, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0006300098054634873, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.00043125542637426404, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0002955099231621716, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.00022073315223678947, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.00017444592023821315, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.00013411594609351595, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.00011199587312148652, "train/grad_034_lr5.1e+00_wd1.0e+00": 8.537058703041112e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 7.114200943760806e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 5.1667024770267745e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 5.482499858771916e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 4.482840091895923e-05, "train/grad_039_lr1.2e+01_wd1.0e+00": 5.46350963736586e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 6.84500149611722e-05, "train/grad_041_lr1.6e+01_wd1.0e+00": 5.878136289425129e-05, "train/grad_042_lr1.9e+01_wd1.0e+00": 6.184970542335577e-05, "train/grad_043_lr2.2e+01_wd1.0e+00": 6.481949070803239e-05, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.00010012973532411707, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0001611103474670017, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.00023137261511692485, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0001788657896732282, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.00013268178941976044, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.6431386470794678, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.598653554916382, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.5138700008392334, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.4137303829193115, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.2937114238739014, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.0703046321868896, "validation/loss_006_lr5.3e-02_wd1.0e+00": 1.6519272327423096, "validation/loss_007_lr6.2e-02_wd1.0e+00": 1.213614821434021, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.8578073382377625, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.5618350505828857, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.40549442172050476, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.282096266746521, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.22741606831550598, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.18415673077106476, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.15790198743343353, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.1397993266582489, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.12162021547555923, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.10476815700531006, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.09249561280012131, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.08460460603237152, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.07725712656974792, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.07226497679948807, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.06928101181983948, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.06809834390878677, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.06798332929611206, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.06811085343360901, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.06814099103212357, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.06790945678949356, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.06611403077840805, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.06476273387670517, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.0644959807395935, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.06391026079654694, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.06291386485099792, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.06051979586482048, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.05733461678028107, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.058475494384765625, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.05928918719291687, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.05063394457101822, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.053627993911504745, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.051553402096033096, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.05253523588180542, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.05038010701537132, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.0519617423415184, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.0525173656642437, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.05659633129835129, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.05639784783124924, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.04317917674779892, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.14452186226844788, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.21424584090709686, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.17385912698412698, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.1892361111111111, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.2400793650793651, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.28695436507936506, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.341765873015873, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.42757936507936506, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.5813492063492064, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.6686507936507936, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.7849702380952381, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.8630952380952381, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.8960813492063492, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9268353174603174, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9389880952380952, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9489087301587301, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9548611111111112, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9600694444444444, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9650297619047619, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9702380952380952, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9744543650793651, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9759424603174603, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9751984126984127, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9764384920634921, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9769345238095238, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9761904761904762, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9769345238095238, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9764384920634921, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9769345238095238, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9774305555555556, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9796626984126984, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.980406746031746, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9816468253968254, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9813988095238095, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9806547619047619, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9828869047619048, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9836309523809523, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9836309523809523, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9848710317460317, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9875992063492064, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9853670634920635, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9856150793650794, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.986359126984127, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9866071428571429, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9875992063492064, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9880952380952381, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9871031746031746, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.984375, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9871031746031746, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9833829365079365, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9789186507936508, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.017488714804344302, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.03306047743823602, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.06569158710180568, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.09268174042897238, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.13173375717024033, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.20231215928932708, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.37569704234211504, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.4780152790124128, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.6896344512564676, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.8356808968994517, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.8817543092909444, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9179787020427781, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9316181948436593, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9405785323653226, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9482060196543218, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9529527445159095, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9583118833786327, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9653231793237047, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9702747301335447, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9719574274769136, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9716672108088014, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9724033227683064, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9735547804409428, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9729836940587282, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.97398166607946, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.973415765412405, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9744893587675433, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9748882616736684, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9773135494962462, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9792163439050096, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9801314682150981, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9800441136029343, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9789505986357021, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.98097593010688, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9809646683653904, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9803932854565874, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9825122092702633, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.98486418150167, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9841796531324308, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9832293840320032, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9857847368735322, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9845261974482068, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9865981298601415, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9857562615366776, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.986730532684781, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9825834634684043, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9859203061845699, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.980681785159648, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9772121765151618, "id_best": 43, "lr_best": 0.006599999999999999, "wd_best": 0.05, "train/loss_best": 0.0001360417902469635, "validation/loss_best": 0.0525173656642437, "validation/acc_best": 0.9880952380952381, "validation/f1_best": 0.9857562615366776} +{"epoch": 18, "train/lr": 7.5829098008590064e-06, "train/loss": 0.4174356900155544, "train/grad": 0.04342013284564018, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.65171875, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.606179504394531, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.5196855163574217, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.417310333251953, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.2950421142578126, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.0678061294555663, "train/loss_006_lr5.3e-02_wd1.0e+00": 1.6462642002105712, "train/loss_007_lr6.2e-02_wd1.0e+00": 1.2031199830770491, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.8405371934175492, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.546322274506092, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.3925565677881241, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.2676676229760051, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.20913667611777784, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.16112347887828946, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.13161893848329784, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.1114622081629932, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.09101877151057124, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.07204828542657196, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.05725200855173171, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.04641436710953713, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.03518135299906135, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.02626012868247926, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.018491948172450066, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.01248932097107172, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.008230688255280257, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.004988721050322056, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.0033052580058574674, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0024228925816714765, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0016635954566299915, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.001153808580711484, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0008746275212615729, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.0006967992801219225, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.0005464873183518648, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.0004531435295939445, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.0003406277112662792, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.00027870007790625095, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.00015029039233922957, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.00016408572904765605, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.00012623108923435212, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.00016244488768279552, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.00016019286587834358, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.00014250175096094608, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.00011163542978465558, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.00012640931643545628, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.00021987913176417352, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.0003869956452399492, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.0007362914737313985, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.00011179344728589058, "train/loss_048_lr5.0e+01_wd1.0e+00": 8.732530288398266e-05, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.009616729617118836, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.009690859641414135, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.009814404004719108, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.009925080775283278, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.010020881427917629, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.010288464915938676, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.011725896149873733, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.010863006152212619, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.01082621097099036, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.01104577554622665, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.010803977029863744, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.010264462898485363, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.00982330458238721, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.009145983897615223, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.008539682498667388, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.007987952777184545, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.007356118250172585, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.006690824938705191, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.0060078803356736895, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.005445434646098875, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.0047799112962093205, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.004084618933266029, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.003326302003697492, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.002571986564726103, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0018843926952104085, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0012256274139508605, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.000831924585509114, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0006103735663054977, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.00042124105297261847, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.00029048314474493963, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0002170897832183982, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.00017193860690895235, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.00013252171765998355, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.00011061983252147912, "train/grad_034_lr5.1e+00_wd1.0e+00": 8.46598336192983e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 6.948475921490171e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 4.993797721681403e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 5.253629745084254e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 4.386793011690315e-05, "train/grad_039_lr1.2e+01_wd1.0e+00": 5.526874203155785e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 6.519427794728472e-05, "train/grad_041_lr1.6e+01_wd1.0e+00": 5.660181827238375e-05, "train/grad_042_lr1.9e+01_wd1.0e+00": 5.8218512930920954e-05, "train/grad_043_lr2.2e+01_wd1.0e+00": 6.834408314261964e-05, "train/grad_044_lr2.6e+01_wd1.0e+00": 9.663468135826747e-05, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0001529103595032666, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0002246968717963682, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.00016487437667479289, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.00012464037644155157, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.64239239692688, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.5977561473846436, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.512641191482544, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.4120335578918457, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.2915496826171875, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.0669498443603516, "validation/loss_006_lr5.3e-02_wd1.0e+00": 1.6466784477233887, "validation/loss_007_lr6.2e-02_wd1.0e+00": 1.20920729637146, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.8540788292884827, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.5589487552642822, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.403760701417923, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.28122976422309875, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.22671331465244293, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.1838391125202179, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.15746645629405975, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.13954320549964905, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.12116154283285141, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.10445737093687057, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.09224548190832138, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.08441109210252762, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.07706227898597717, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.07223858684301376, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.0692608505487442, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.06814809888601303, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.06810992956161499, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.06843557208776474, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.06821254640817642, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.06811897456645966, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.06629342585802078, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.06462008506059647, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.06451002508401871, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.06388749182224274, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.06287210434675217, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.06045236438512802, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.05739404261112213, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.05851004645228386, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.0593663789331913, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.050636157393455505, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.05347288399934769, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.05144217982888222, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.05254998803138733, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.05029290169477463, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.05177459120750427, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.05239608883857727, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.056446317583322525, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.05628102645277977, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.04284236952662468, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.14339686930179596, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.2119058519601822, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.17385912698412698, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.18948412698412698, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.24057539682539683, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.2881944444444444, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.3412698412698413, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.4290674603174603, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.5823412698412699, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.6706349206349206, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.7854662698412699, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.8645833333333334, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.8960813492063492, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9268353174603174, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9389880952380952, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9496527777777778, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.955109126984127, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9600694444444444, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9650297619047619, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9702380952380952, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9737103174603174, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9751984126984127, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9759424603174603, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9766865079365079, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9771825396825397, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9766865079365079, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9771825396825397, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9761904761904762, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9771825396825397, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9774305555555556, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9799107142857143, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9801587301587301, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9816468253968254, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9813988095238095, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9806547619047619, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9826388888888888, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9836309523809523, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9841269841269841, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9848710317460317, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9875992063492064, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9851190476190477, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9858630952380952, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.986359126984127, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9866071428571429, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9873511904761905, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9878472222222222, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9868551587301587, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.984375, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9868551587301587, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9833829365079365, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9786706349206349, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.017488714804344302, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.03325031013962257, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.06581653769590555, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.09355420234819282, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.13076665829288542, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.20403835581847676, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.37660570488574613, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.48178572449445833, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.6901891610777235, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.8379608077120063, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.8813211966064733, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9179909821485875, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9315441124070836, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9420736841593728, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9485738812639161, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9528820318958999, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9583118833786327, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9653540487511947, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.969265432647755, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9711066842151914, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9722965469506333, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.972659938188693, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9737044199404817, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.973803938943602, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9738750594173128, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9732078431773904, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9747481372771939, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9747989689737989, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9778607894502656, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9786750960756262, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9801314682150981, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9800112362277927, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9789505986357021, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9804407996149921, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9809646683653904, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9810054939784594, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9825122092702633, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.98486418150167, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9838114384437595, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9835749078578876, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9857192753680912, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9845261974482068, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9863759698737644, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9855294027870821, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9865271215606506, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9825834634684043, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9856936838110648, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.980681785159648, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9771088588532282, "id_best": 43, "lr_best": 0.006599999999999999, "wd_best": 0.05, "train/loss_best": 0.00012640931643545628, "validation/loss_best": 0.05239608883857727, "validation/acc_best": 0.9878472222222222, "validation/f1_best": 0.9855294027870821} +{"epoch": 18, "train/lr": 7.5829098008590064e-06, "train/loss": 0.41875764697790147, "train/grad": 0.04389699172228575, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.6503057861328125, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.6050909423828124, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.519081726074219, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.417428436279297, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.2957767486572265, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.0699303436279295, "train/loss_006_lr5.3e-02_wd1.0e+00": 1.6509922122955323, "train/loss_007_lr6.2e-02_wd1.0e+00": 1.2110820466279983, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.8500702744722366, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.5541875021159649, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.3992147408425808, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.27369660168886184, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.21459698885679246, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.1655664209276438, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.13506641143932938, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.1142604542337358, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.09319287681020796, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.07367254637181758, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.058165344195440415, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.04689174061641097, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.03539383147843182, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.026268451185896994, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.018599846167489886, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.01267845606431365, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.008375848345458507, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.005011169817298651, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.003332320097833872, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.002448299741372466, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0016756770759820939, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0011547560337930919, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0008745487686246633, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.0006995798833668232, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.0005441650375723839, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.00045392814092338086, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.0003420062642544508, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.0002871205285191536, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.00015369098633527756, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.00015453819185495376, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.00012707723304629327, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.00017126127146184446, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.0001655910350382328, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.00015555462799966336, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.00011375637724995613, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.00014811594970524312, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.00023399673402309417, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.0003756939060986042, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.000710136890411377, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.00011835272423923016, "train/loss_048_lr5.0e+01_wd1.0e+00": 8.71196761727333e-05, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.009798077763989568, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.009872243597637862, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.009995323338080198, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.010106314092408865, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.010197600002866238, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.010447759171947837, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.011831279378384352, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.010940772658213973, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.010961635950952769, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.01120637400308624, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.010977572419214994, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.010414889294188469, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.009926675441674889, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.009228371765930206, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.008602194678969681, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.008025834895670414, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.0073562250752002, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.006652409207308665, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.005937696393812075, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.005366380136692896, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.00468273880018387, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.003980678960797377, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0032098736485932024, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0024777780077420175, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.001815403592045186, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0011937911587301642, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0008073635655455291, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0006003015425812919, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.00041462507098913195, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0002873825227288762, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0002159122375451261, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.00017144931363873183, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.00013303745363373308, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.00011084232692155638, "train/grad_034_lr5.1e+00_wd1.0e+00": 8.419965911343752e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 6.994779449087218e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 4.9728725043678425e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 5.470363570339032e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 4.481850757770189e-05, "train/grad_039_lr1.2e+01_wd1.0e+00": 5.5828631843724e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 6.647367039505525e-05, "train/grad_041_lr1.6e+01_wd1.0e+00": 5.7604989851824936e-05, "train/grad_042_lr1.9e+01_wd1.0e+00": 6.066371859787978e-05, "train/grad_043_lr2.2e+01_wd1.0e+00": 6.673885492233466e-05, "train/grad_044_lr2.6e+01_wd1.0e+00": 9.569520537183962e-05, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0001458319731091251, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.00022174259868734225, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.00016368418467182955, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0001273778019354753, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.642399311065674, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.5977609157562256, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.512662410736084, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.412020206451416, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.2915544509887695, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.066953420639038, "validation/loss_006_lr5.3e-02_wd1.0e+00": 1.6467299461364746, "validation/loss_007_lr6.2e-02_wd1.0e+00": 1.2092726230621338, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.8541335463523865, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.5590351223945618, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.40368300676345825, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.2812047600746155, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.22677190601825714, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.18375952541828156, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.15739357471466064, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.13943666219711304, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.121117502450943, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.10440472513437271, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.09214502573013306, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.08425796031951904, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.0770295187830925, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.07219409197568893, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.06920100748538971, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.06816679239273071, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.06813665479421616, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.06838248670101166, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.06826139241456985, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.06814844161272049, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.06635989993810654, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.0648823231458664, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.06443789601325989, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.06393188238143921, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.06300938129425049, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.060612235218286514, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.05738161504268646, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.05841304361820221, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.059286028146743774, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.05067390576004982, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.05354054272174835, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.05150297284126282, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.05253305658698082, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.05029797926545143, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.05178859829902649, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.05248884856700897, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.0565464086830616, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.056465111672878265, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.04297536984086037, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.14370493590831757, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.21192611753940582, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.17385912698412698, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.1892361111111111, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.24057539682539683, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.28794642857142855, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.34226190476190477, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.4288194444444444, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.5828373015873016, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.6706349206349206, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.7859623015873016, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.8630952380952381, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.8963293650793651, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9265873015873016, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9387400793650794, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9496527777777778, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9556051587301587, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9605654761904762, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9652777777777778, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9702380952380952, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9742063492063492, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9756944444444444, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9761904761904762, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9769345238095238, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9771825396825397, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9766865079365079, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9774305555555556, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9754464285714286, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9769345238095238, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9776785714285714, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9799107142857143, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.980406746031746, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9811507936507936, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9813988095238095, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9809027777777778, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9828869047619048, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9836309523809523, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9838789682539683, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9848710317460317, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9875992063492064, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9853670634920635, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9858630952380952, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.986359126984127, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9866071428571429, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9873511904761905, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9878472222222222, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9868551587301587, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.984375, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9871031746031746, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9833829365079365, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9786706349206349, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.017488714804344302, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.03306047743823602, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.06581653769590555, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.09351153575769165, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.13259595154684387, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.20346436874387064, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.37686163564513225, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.48184180212194233, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.6908446552575458, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.83619166944829, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.881878354950796, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9178223933154196, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.931074225379942, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9422682477033336, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9490987726192919, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9538165598639995, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9584888282647955, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9650328525636337, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9702298872924935, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9714589379815964, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9724733154310437, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9730046954021712, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9735714486342792, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.973803938943602, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9744296061418658, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9726379750632086, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9743612702042861, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9751485380245379, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9778607894502656, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9791689546952195, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9794879089435753, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9800441136029343, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9793668820689828, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.98097593010688, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9809646683653904, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9807772777821944, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9825122092702633, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.98486418150167, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9839901062899172, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9835749078578876, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9855364293382097, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9845261974482068, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9863759698737644, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9855294027870821, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9865271215606506, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9825834634684043, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9860525090166424, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.980681785159648, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9771088588532282, "id_best": 43, "lr_best": 0.006599999999999999, "wd_best": 0.05, "train/loss_best": 0.00014811594970524312, "validation/loss_best": 0.05248884856700897, "validation/acc_best": 0.9878472222222222, "validation/f1_best": 0.9855294027870821} +{"epoch": 19, "train/lr": 1.0867618231465446e-06, "train/loss": 0.4220352192223072, "train/grad": 0.04343860033899546, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.652059326171875, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.60688232421875, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.5208509826660155, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.4192996215820313, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.2980084228515625, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.072932548522949, "train/loss_006_lr5.3e-02_wd1.0e+00": 1.656343812942505, "train/loss_007_lr6.2e-02_wd1.0e+00": 1.2173903250694276, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.8577304437756539, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.5638096924126148, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.41054001078009605, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.2856178143620491, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.22610560655593873, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.17640605252236127, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.14562256898730994, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.12427454108372331, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.10247445433400572, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.08216810835525394, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.0659570067282766, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.05413847473450005, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.04172195954248309, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.031504973731935025, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.022327646296471357, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.01494996689260006, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.009542200956493616, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.005499545941129327, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.0035745479818433522, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0025966470036655667, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.001769490959122777, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.001223632600158453, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0009217382036149502, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.000735423443838954, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.0005731986556202173, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.00048202629201114176, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.0003634128998965025, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.0002993512712419033, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.00016536302864551545, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.0001728476770222187, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.00013477022759616374, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.00017779811285436152, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.00017658891156315803, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.00016766449436545372, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.00013629861176013946, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.0001576764415949583, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.00025555333122611045, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.0004182098526507616, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.0008313482999801635, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.00014240559190511703, "train/loss_048_lr5.0e+01_wd1.0e+00": 9.18229203671217e-05, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.009580784575082362, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.009654561132192612, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.009779646564275025, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.00989374125842005, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.009993656964506954, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.010276167527772486, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.011765712345950306, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.010881807100959122, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.010827402309514582, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.011076231179758906, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.010890547465533019, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.010355495500843971, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.0098769901227206, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.009203630487900228, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.008613943161908538, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.008063942501321435, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.007418720049317926, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.006708719773450866, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.005970224273623898, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.005378978761145845, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.004695012394222431, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.003994244478526525, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0032255230555892924, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.002476167012937367, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0017937419319059699, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.001159448792313924, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0007865681489784038, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0005822318480932153, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.00040497285182937047, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0002805404791797628, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.00021124370083271061, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.00016759830792580034, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0001295798015598848, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.00010911500483416603, "train/grad_034_lr5.1e+00_wd1.0e+00": 8.279418171696307e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 6.918717584085243e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 4.888278761654874e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 5.3075403698130686e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 4.251970320069631e-05, "train/grad_039_lr1.2e+01_wd1.0e+00": 5.3193198227745596e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 6.354099814871007e-05, "train/grad_041_lr1.6e+01_wd1.0e+00": 5.649671142919033e-05, "train/grad_042_lr1.9e+01_wd1.0e+00": 5.869674638674383e-05, "train/grad_043_lr2.2e+01_wd1.0e+00": 6.677879369362927e-05, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0001013761797355528, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0001536233588961977, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.00021732684488597441, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.00018713365190393461, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.00013239130586137238, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.642324209213257, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.5976269245147705, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.5124716758728027, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.41180157661438, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.2911956310272217, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.0664288997650146, "validation/loss_006_lr5.3e-02_wd1.0e+00": 1.6460397243499756, "validation/loss_007_lr6.2e-02_wd1.0e+00": 1.2085659503936768, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.8534805774688721, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.5585917234420776, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.40344327688217163, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.28105756640434265, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.22662818431854248, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.18371109664440155, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.15734699368476868, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.1394045203924179, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.12121652066707611, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.10443466156721115, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.09219597280025482, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.08435580134391785, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.07705004513263702, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.0721944123506546, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.06931427121162415, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.06811902672052383, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.0681130662560463, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.06846357136964798, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.06824420392513275, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.06812870502471924, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.06631125509738922, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.06474407762289047, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.06442773342132568, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.06385277211666107, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.06292155385017395, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.060568373650312424, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.057439129799604416, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.05848577618598938, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.05930870398879051, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.050642747431993484, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.05352235212922096, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.051499079912900925, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.0526752807199955, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.050403911620378494, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.05173813924193382, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.05242673307657242, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.05635456368327141, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.056272320449352264, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.042825017124414444, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.14376382529735565, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.21104206144809723, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.17385912698412698, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.18998015873015872, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.2408234126984127, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.2881944444444444, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.34226190476190477, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.4288194444444444, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.5833333333333334, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.6706349206349206, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.7869543650793651, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.8645833333333334, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.8960813492063492, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9268353174603174, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9392361111111112, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9494047619047619, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9553571428571429, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9598214285714286, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9650297619047619, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9704861111111112, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9742063492063492, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9751984126984127, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9761904761904762, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9769345238095238, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9769345238095238, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9766865079365079, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9771825396825397, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9761904761904762, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9771825396825397, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9774305555555556, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9799107142857143, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.980406746031746, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9816468253968254, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9813988095238095, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9806547619047619, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9826388888888888, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9836309523809523, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9838789682539683, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9848710317460317, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9875992063492064, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9853670634920635, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9858630952380952, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.986359126984127, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.986359126984127, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9873511904761905, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9878472222222222, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9868551587301587, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.984375, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9868551587301587, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9833829365079365, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9786706349206349, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.017488714804344302, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.03375975201646135, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.06589926995823535, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.09346561934444908, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.13214175574319584, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.2037604147329524, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.3781318993872216, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.4817787854301186, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.6915924525704641, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.8379884269896843, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.8813211966064733, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.917996581067627, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9317280716594348, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9417132528491275, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9487492179516185, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9529344035263756, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9583118833786327, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9658979570861118, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9700467816118703, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9710536102447462, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9724733154310437, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9730096462037665, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.973347654119988, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.973803938943602, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9738750594173128, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9733647090127446, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9747481372771939, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9747989689737989, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9778607894502656, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9788547130083638, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9801314682150981, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9800441136029343, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9789505986357021, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9804407996149921, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9809646683653904, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9806215016528524, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9825122092702633, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.98486418150167, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9839901062899172, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9835749078578876, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9855364293382097, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9841707479426409, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9863759698737644, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9855294027870821, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9865271215606506, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9825834634684043, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9856936838110648, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.980681785159648, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9771088588532282, "id_best": 43, "lr_best": 0.006599999999999999, "wd_best": 0.05, "train/loss_best": 0.0001576764415949583, "validation/loss_best": 0.05242673307657242, "validation/acc_best": 0.9878472222222222, "validation/f1_best": 0.9855294027870821} +{"epoch": 19, "train/lr": 1.0867618231465446e-06, "train/loss": 0.4209229350090027, "train/grad": 0.04337915416806936, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.6468072509765626, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.601623840332031, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.515441589355469, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.4136428833007812, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.291637649536133, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.0644543838500975, "train/loss_006_lr5.3e-02_wd1.0e+00": 1.642655668258667, "train/loss_007_lr6.2e-02_wd1.0e+00": 1.2068517315387726, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.8553234067559242, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.5667993922531605, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.4142677329480648, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.2883319930359721, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.22784908700734377, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.17724778193980456, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.14560560590587557, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.12391304353252053, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.10201205505989491, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.08176618807949126, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.06574191560037435, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.05394485405646265, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.04142140286974609, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.031097402069717645, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.02193352537229657, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.014558038655668498, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.009285540506243705, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.005442535197362304, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.0035439393017441035, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0025750398449599743, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0017642000783234834, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0012201786041259766, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0009223554562777281, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.0007371691893786192, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.0005776553321629762, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.0004880926478654146, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.0003666156716644764, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.0002941375318914652, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.00016275203786790372, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.00018364093266427518, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.00013141674920916558, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.00018432158976793288, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.00019897574558854102, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.0001751958765089512, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.00013290350325405597, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.00015634060837328435, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.00024786509573459625, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.0004397295136004686, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.0008305535186082125, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.00014561842195689678, "train/loss_048_lr5.0e+01_wd1.0e+00": 8.905313909053803e-05, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.009520206989254803, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.00959940518019721, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.009733983122278005, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.00985839509870857, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.009967488215770572, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.010259447386488318, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.011739142430014908, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.010813975539058447, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.010778297309298069, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.011028810658026487, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.010880021450575442, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.01036744704004377, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.009885865778196603, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.009186912642326206, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.008581460972782224, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.008026832906762139, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.007385976909426972, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.0066671218734700236, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.005935465366928838, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.005361278391210362, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.004674514312064275, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.0039799254594254305, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0032308101688977332, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.002497195121250115, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0018222592851088848, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0011850467570184264, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.000804567608211073, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0005915016918879701, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.000407775225394289, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.00028114300777815516, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.00021097993731018506, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.00016669384223860106, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.00012886360525953932, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.00010769776963570621, "train/grad_034_lr5.1e+00_wd1.0e+00": 8.322198954374471e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 6.872208390632295e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 4.9943214280574464e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 5.4419760008386217e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 4.317015742572039e-05, "train/grad_039_lr1.2e+01_wd1.0e+00": 5.6103863421412825e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 6.514420161579437e-05, "train/grad_041_lr1.6e+01_wd1.0e+00": 5.892402299195965e-05, "train/grad_042_lr1.9e+01_wd1.0e+00": 6.0141672053219965e-05, "train/grad_043_lr2.2e+01_wd1.0e+00": 6.849696781699777e-05, "train/grad_044_lr2.6e+01_wd1.0e+00": 9.587286002329166e-05, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.00015665552837958784, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0002192490981951778, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.00017726963775101855, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.00012288215488158395, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.642320394515991, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.5976274013519287, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.5124964714050293, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.411766767501831, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.291206121444702, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.0664572715759277, "validation/loss_006_lr5.3e-02_wd1.0e+00": 1.6460634469985962, "validation/loss_007_lr6.2e-02_wd1.0e+00": 1.2086694240570068, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.8535147309303284, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.5586263537406921, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.403363972902298, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.2810070812702179, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.22658810019493103, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.18364502489566803, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.1573009043931961, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.13930168747901917, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.12110305577516556, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.10440117120742798, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.09214317053556442, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.08435887843370438, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.07706800103187561, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.07219921797513962, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.06926129013299942, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.0681062638759613, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.06816688179969788, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.06850407272577286, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.06825164705514908, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.06816750764846802, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.06639483571052551, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.06489460915327072, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.06444115191698074, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.06399568170309067, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.06302596628665924, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.06056269630789757, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.057422738522291183, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.058474402874708176, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.059378042817115784, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.05064773932099342, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.05353792756795883, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.051543280482292175, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.052626654505729675, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.050205644220113754, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.05175448954105377, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.05252598226070404, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.056400276720523834, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.0562809482216835, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.04287353903055191, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.14370252192020416, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.21113447844982147, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.17385912698412698, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.1892361111111111, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.24032738095238096, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.2881944444444444, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.34250992063492064, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.42931547619047616, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.5830853174603174, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.6703869047619048, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.7862103174603174, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.863343253968254, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.8963293650793651, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9268353174603174, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9389880952380952, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9496527777777778, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9556051587301587, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9600694444444444, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9655257936507936, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9702380952380952, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9737103174603174, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9754464285714286, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9761904761904762, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9766865079365079, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9771825396825397, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9764384920634921, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9769345238095238, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9754464285714286, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9774305555555556, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9776785714285714, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9799107142857143, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9799107142857143, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9813988095238095, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9816468253968254, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9809027777777778, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9826388888888888, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9836309523809523, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9838789682539683, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9848710317460317, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9875992063492064, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9853670634920635, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9858630952380952, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.986359126984127, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9866071428571429, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9873511904761905, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9878472222222222, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9866071428571429, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.984375, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9868551587301587, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9836309523809523, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9789186507936508, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.017488714804344302, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.03306047743823602, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.06573340604893968, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.09358765617827178, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.1327669719439441, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.20420896878313635, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.37791263527212754, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.48123643002313526, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.6906716244893095, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.8365308674877939, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.8814918488146093, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.917996581067627, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9313162588669665, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9422682477033336, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9490987726192919, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9530450301853008, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9586104061588328, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9650328525636337, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9691232431072052, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9712828329565049, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9724733154310437, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9724527211480465, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9735714486342792, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9732525377789633, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.973503836704744, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9726379750632086, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9751482743117135, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9751485380245379, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9778607894502656, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9782081891189763, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9796081180267491, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9805792440948221, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9793668820689828, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9804407996149921, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9809646683653904, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9807772777821944, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9825122092702633, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.98486418150167, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9839901062899172, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9835749078578876, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9857192753680912, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9845261974482068, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9863759698737644, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9855294027870821, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9859890357562209, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9825834634684043, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9856936838110648, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9812238022675368, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9772121765151618, "id_best": 43, "lr_best": 0.006599999999999999, "wd_best": 0.05, "train/loss_best": 0.00015634060837328435, "validation/loss_best": 0.05252598226070404, "validation/acc_best": 0.9878472222222222, "validation/f1_best": 0.9855294027870821} diff --git a/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__linear/config.yaml b/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__linear/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..359c2c152b7ab76f34d90638427d6f3619ef3e59 --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__linear/config.yaml @@ -0,0 +1,96 @@ +output_root: experiments/decoders/output +name_prefix: eval_probe +remote_root: null +notes: decoder ablations crossreg_reg4; eval v2 (hcpya_task21 patch linear) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +dataset_kwargs: {} +classifier_kwargs: + embed_dim: null + dropout: 0.0 + xavier_init: false + norm: false +lr_scale_grid: +- 0.02 +- 0.023 +- 0.028 +- 0.033 +- 0.038 +- 0.045 +- 0.053 +- 0.062 +- 0.074 +- 0.087 +- 0.1 +- 0.12 +- 0.14 +- 0.17 +- 0.2 +- 0.23 +- 0.27 +- 0.32 +- 0.38 +- 0.44 +- 0.52 +- 0.61 +- 0.72 +- 0.85 +- 1 +- 1.2 +- 1.4 +- 1.6 +- 1.9 +- 2.3 +- 2.7 +- 3.1 +- 3.7 +- 4.3 +- 5.1 +- 6 +- 7.1 +- 8.3 +- 9.8 +- 12 +- 14 +- 16 +- 19 +- 22 +- 26 +- 31 +- 36 +- 43 +- 50 +wd_scale_grid: +- 1.0 +num_workers: 8 +prefetch_factor: null +balanced_sampling: false +epochs: 20 +steps_per_epoch: 200 +batch_size: 64 +accum_iter: 2 +lr: 0.0003 +warmup_epochs: 5 +no_decay: false +weight_decay: 0.05 +clip_grad: 1.0 +metrics: +- acc +- f1 +cv_metric: acc +early_stopping: true +amp: true +device: cuda +seed: 4466 +debug: false +wandb: false +wandb_entity: null +wandb_project: fMRI-fm-eval +name: decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__linear +model: flat_mae +representation: patch +classifier: linear +dataset: hcpya_task21 +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__linear +remote_dir: null diff --git a/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__linear/eval_log.json b/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__linear/eval_log.json new file mode 100644 index 0000000000000000000000000000000000000000..9439837ce61653a6c37c903ec42e5467fee7f9eb --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__linear/eval_log.json @@ -0,0 +1 @@ +{"eval/epoch": 18, "eval/id_best": 48, "eval/lr_best": 0.015, "eval/wd_best": 0.05, "eval/train/loss": 0.30549120903015137, "eval/train/acc": 0.9457866203484394, "eval/train/acc_std": 0.0015117116549057134, "eval/train/f1": 0.9424528099876407, "eval/train/f1_std": 0.0018296477406085077, "eval/validation/loss": 0.339051216840744, "eval/validation/acc": 0.9320436507936508, "eval/validation/acc_std": 0.0038815927504984933, "eval/validation/f1": 0.9251783585297395, "eval/validation/f1_std": 0.0047207324832681035, "eval/test/loss": 0.34095045924186707, "eval/test/acc": 0.9327380952380953, "eval/test/acc_std": 0.003278294931146475, "eval/test/f1": 0.9250129678240288, "eval/test/f1_std": 0.004080640658782675} diff --git a/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__linear/eval_log_best.json b/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__linear/eval_log_best.json new file mode 100644 index 0000000000000000000000000000000000000000..ef963250a7c67aa706c99675f4ed4b66d016878d --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__linear/eval_log_best.json @@ -0,0 +1 @@ +{"eval/best/epoch": 18, "eval/best/id_best": 48, "eval/best/lr_best": 0.015, "eval/best/wd_best": 0.05, "eval/best/train/loss": 0.30549120903015137, "eval/best/train/acc": 0.9457866203484394, "eval/best/train/acc_std": 0.0015117116549057134, "eval/best/train/f1": 0.9424528099876407, "eval/best/train/f1_std": 0.0018296477406085077, "eval/best/validation/loss": 0.339051216840744, "eval/best/validation/acc": 0.9320436507936508, "eval/best/validation/acc_std": 0.0038815927504984933, "eval/best/validation/f1": 0.9251783585297395, "eval/best/validation/f1_std": 0.0047207324832681035, "eval/best/test/loss": 0.34095045924186707, "eval/best/test/acc": 0.9327380952380953, "eval/best/test/acc_std": 0.003278294931146475, "eval/best/test/f1": 0.9250129678240288, "eval/best/test/f1_std": 0.004080640658782675} diff --git a/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__linear/eval_log_last.json b/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__linear/eval_log_last.json new file mode 100644 index 0000000000000000000000000000000000000000..474ce6f72910ca2ff632a00d7ecb7bfb8f39f279 --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__linear/eval_log_last.json @@ -0,0 +1 @@ +{"eval/last/epoch": 19, "eval/last/id_best": 48, "eval/last/lr_best": 0.015, "eval/last/wd_best": 0.05, "eval/last/train/loss": 0.30505988001823425, "eval/last/train/acc": 0.9450497394599716, "eval/last/train/acc_std": 0.0015442731153987098, "eval/last/train/f1": 0.94144574298719, "eval/last/train/f1_std": 0.001868007935164643, "eval/last/validation/loss": 0.3388846814632416, "eval/last/validation/acc": 0.9317956349206349, "eval/last/validation/acc_std": 0.0038951688379079744, "eval/last/validation/f1": 0.9241029616907658, "eval/last/validation/f1_std": 0.0047618741708175955, "eval/last/test/loss": 0.3405951261520386, "eval/last/test/acc": 0.9331349206349207, "eval/last/test/acc_std": 0.003325990211103103, "eval/last/test/f1": 0.9250078020719377, "eval/last/test/f1_std": 0.0041453204889727235} diff --git a/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__linear/eval_table.csv b/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__linear/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..1544d01a70791e0e4686fb0967f40e23f139dde3 --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__linear/eval_table.csv @@ -0,0 +1,4 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,patch,linear,hcpya_task21,best,18,0.015,0.05,48,"[50, 1.0]",train,0.30549120903015137,0.9457866203484394,0.0015117116549057134,0.9424528099876407,0.0018296477406085077 +flat_mae,patch,linear,hcpya_task21,best,18,0.015,0.05,48,"[50, 1.0]",validation,0.339051216840744,0.9320436507936508,0.0038815927504984933,0.9251783585297395,0.0047207324832681035 +flat_mae,patch,linear,hcpya_task21,best,18,0.015,0.05,48,"[50, 1.0]",test,0.34095045924186707,0.9327380952380953,0.003278294931146475,0.9250129678240288,0.004080640658782675 diff --git a/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__linear/eval_table_best.csv b/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__linear/eval_table_best.csv new file mode 100644 index 0000000000000000000000000000000000000000..1544d01a70791e0e4686fb0967f40e23f139dde3 --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__linear/eval_table_best.csv @@ -0,0 +1,4 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,patch,linear,hcpya_task21,best,18,0.015,0.05,48,"[50, 1.0]",train,0.30549120903015137,0.9457866203484394,0.0015117116549057134,0.9424528099876407,0.0018296477406085077 +flat_mae,patch,linear,hcpya_task21,best,18,0.015,0.05,48,"[50, 1.0]",validation,0.339051216840744,0.9320436507936508,0.0038815927504984933,0.9251783585297395,0.0047207324832681035 +flat_mae,patch,linear,hcpya_task21,best,18,0.015,0.05,48,"[50, 1.0]",test,0.34095045924186707,0.9327380952380953,0.003278294931146475,0.9250129678240288,0.004080640658782675 diff --git a/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__linear/eval_table_last.csv b/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__linear/eval_table_last.csv new file mode 100644 index 0000000000000000000000000000000000000000..fde214856ef7b569a86d0c7dbc65c9fc7459b54d --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__linear/eval_table_last.csv @@ -0,0 +1,4 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,patch,linear,hcpya_task21,last,19,0.015,0.05,48,"[50, 1.0]",train,0.30505988001823425,0.9450497394599716,0.0015442731153987098,0.94144574298719,0.001868007935164643 +flat_mae,patch,linear,hcpya_task21,last,19,0.015,0.05,48,"[50, 1.0]",validation,0.3388846814632416,0.9317956349206349,0.0038951688379079744,0.9241029616907658,0.0047618741708175955 +flat_mae,patch,linear,hcpya_task21,last,19,0.015,0.05,48,"[50, 1.0]",test,0.3405951261520386,0.9331349206349207,0.003325990211103103,0.9250078020719377,0.0041453204889727235 diff --git a/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__linear/log.txt b/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__linear/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..0947cfbeff9a9035c062a4d56caaecc0df916c85 --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__linear/log.txt @@ -0,0 +1,892 @@ +fMRI foundation model probe eval +version: 0.1.dev66+g7ddd3aa04 +sha: aef99c83a386cf95c3d8ca503ecc968d8d5694af, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-03-07 23:04:47 +config: +output_root: experiments/decoders/output +name_prefix: eval_probe +remote_root: null +notes: decoder ablations crossreg_reg4; eval v2 (hcpya_task21 patch linear) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +dataset_kwargs: {} +classifier_kwargs: + embed_dim: null + dropout: 0.0 + xavier_init: false + norm: false +lr_scale_grid: +- 0.02 +- 0.023 +- 0.028 +- 0.033 +- 0.038 +- 0.045 +- 0.053 +- 0.062 +- 0.074 +- 0.087 +- 0.1 +- 0.12 +- 0.14 +- 0.17 +- 0.2 +- 0.23 +- 0.27 +- 0.32 +- 0.38 +- 0.44 +- 0.52 +- 0.61 +- 0.72 +- 0.85 +- 1 +- 1.2 +- 1.4 +- 1.6 +- 1.9 +- 2.3 +- 2.7 +- 3.1 +- 3.7 +- 4.3 +- 5.1 +- 6 +- 7.1 +- 8.3 +- 9.8 +- 12 +- 14 +- 16 +- 19 +- 22 +- 26 +- 31 +- 36 +- 43 +- 50 +wd_scale_grid: +- 1.0 +num_workers: 8 +prefetch_factor: null +balanced_sampling: false +epochs: 20 +steps_per_epoch: 200 +batch_size: 64 +accum_iter: 2 +lr: 0.0003 +warmup_epochs: 5 +no_decay: false +weight_decay: 0.05 +clip_grad: 1.0 +metrics: +- acc +- f1 +cv_metric: acc +early_stopping: true +amp: true +device: cuda +seed: 4466 +debug: false +wandb: false +wandb_entity: null +wandb_project: fMRI-fm-eval +name: decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__linear +model: flat_mae +representation: patch +classifier: linear +dataset: hcpya_task21 +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__linear +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=False, reg_tokens=4, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: hcpya_task21 (flat) +train (n=18999): +HFDataset( + dataset=Dataset({ + features: ['sub', 'task', 'cond', 'cond_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 18999 +}), + labels=[ 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20], + counts=[ 832 1248 3201 1660 832 832 832 832 832 1248 1247 1243 832 416 + 416 416 416 416 416 416 416] +) + +validation (n=4032): +HFDataset( + dataset=Dataset({ + features: ['sub', 'task', 'cond', 'cond_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 4032 +}), + labels=[ 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20], + counts=[176 264 688 352 176 176 176 176 176 264 264 264 176 88 88 88 88 88 + 88 88 88] +) + +test (n=5040): +HFDataset( + dataset=Dataset({ + features: ['sub', 'task', 'cond', 'cond_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 5040 +}), + labels=[ 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20], + counts=[220 330 860 440 220 220 220 220 220 330 330 330 220 110 110 110 110 110 + 110 110 110] +) + +running backbone on example batch to get embedding dim +embedding feature dim (patch): 768 +initializing sweep of classifier heads +classifiers: +ModuleList( + (0-48): 49 x LinearClassifier( + (linear): Linear(in_features=768, out_features=21, bias=True) + ) +) +classifier params (train): 0.8M (0.8M) +setting up optimizer +total batch size: 128 = 64 bs per gpu x 2 accum +lr: 3.00e-04 +full schedule: epochs = 20 (steps = 4000) (decay = True) +warmup: epochs = 5 (steps = 1000) +start training for 20 epochs +train: [0] [ 0/400] eta: 0:22:27 lr: nan time: 3.3682 data: 2.9601 max mem: 3914 +train: [0] [ 20/400] eta: 0:03:06 lr: 0.000003 loss: 3.0382 (3.0385) grad: 0.1210 (0.1172) time: 0.3477 data: 0.0039 max mem: 3956 +train: [0] [ 40/400] eta: 0:02:24 lr: 0.000006 loss: 3.0382 (3.0376) grad: 0.1146 (0.1120) time: 0.3072 data: 0.0029 max mem: 3956 +train: [0] [ 60/400] eta: 0:02:06 lr: 0.000009 loss: 3.0277 (3.0325) grad: 0.1057 (0.1130) time: 0.3108 data: 0.0031 max mem: 3956 +train: [0] [ 80/400] eta: 0:01:54 lr: 0.000012 loss: 3.0120 (3.0273) grad: 0.1127 (0.1136) time: 0.3147 data: 0.0033 max mem: 3956 +train: [0] [100/400] eta: 0:01:45 lr: 0.000015 loss: 3.0005 (3.0205) grad: 0.1145 (0.1152) time: 0.3284 data: 0.0033 max mem: 3956 +train: [0] [120/400] eta: 0:01:37 lr: 0.000018 loss: 2.9888 (3.0151) grad: 0.1130 (0.1140) time: 0.3351 data: 0.0033 max mem: 3956 +train: [0] [140/400] eta: 0:01:31 lr: 0.000021 loss: 2.9867 (3.0109) grad: 0.1098 (0.1140) time: 0.3632 data: 0.0033 max mem: 3956 +train: [0] [160/400] eta: 0:01:24 lr: 0.000024 loss: 2.9737 (3.0065) grad: 0.1036 (0.1125) time: 0.3520 data: 0.0033 max mem: 3956 +train: [0] [180/400] eta: 0:01:17 lr: 0.000027 loss: 2.9626 (2.9992) grad: 0.0998 (0.1116) time: 0.3405 data: 0.0032 max mem: 3956 +train: [0] [200/400] eta: 0:01:09 lr: 0.000030 loss: 2.9351 (2.9934) grad: 0.0984 (0.1105) time: 0.3477 data: 0.0032 max mem: 3956 +train: [0] [220/400] eta: 0:01:03 lr: 0.000033 loss: 2.9427 (2.9891) grad: 0.0978 (0.1096) time: 0.3579 data: 0.0033 max mem: 3956 +train: [0] [240/400] eta: 0:00:56 lr: 0.000036 loss: 2.9285 (2.9828) grad: 0.1017 (0.1092) time: 0.3547 data: 0.0032 max mem: 3956 +train: [0] [260/400] eta: 0:00:49 lr: 0.000039 loss: 2.8943 (2.9757) grad: 0.1074 (0.1090) time: 0.3451 data: 0.0032 max mem: 3956 +train: [0] [280/400] eta: 0:00:42 lr: 0.000042 loss: 2.8881 (2.9712) grad: 0.0976 (0.1080) time: 0.3691 data: 0.0032 max mem: 3956 +train: [0] [300/400] eta: 0:00:36 lr: 0.000045 loss: 2.8880 (2.9660) grad: 0.0909 (0.1073) time: 0.5296 data: 0.1932 max mem: 3956 +train: [0] [320/400] eta: 0:00:29 lr: 0.000048 loss: 2.8672 (2.9606) grad: 0.0961 (0.1069) time: 0.3469 data: 0.0037 max mem: 3956 +train: [0] [340/400] eta: 0:00:21 lr: 0.000051 loss: 2.8573 (2.9548) grad: 0.1065 (0.1067) time: 0.3597 data: 0.0026 max mem: 3956 +train: [0] [360/400] eta: 0:00:14 lr: 0.000054 loss: 2.8433 (2.9493) grad: 0.0923 (0.1058) time: 0.3593 data: 0.0034 max mem: 3956 +train: [0] [380/400] eta: 0:00:07 lr: 0.000057 loss: 2.8414 (2.9428) grad: 0.0894 (0.1052) time: 0.4274 data: 0.0038 max mem: 3956 +train: [0] [399/400] eta: 0:00:00 lr: 0.000060 loss: 2.8296 (2.9365) grad: 0.0926 (0.1049) time: 0.3535 data: 0.0034 max mem: 3956 +train: [0] Total time: 0:02:26 (0.3652 s / it) +train: [0] Summary: lr: 0.000060 loss: 2.8296 (2.9365) grad: 0.0926 (0.1049) +eval (validation): [0] [ 0/63] eta: 0:03:38 time: 3.4642 data: 3.2269 max mem: 3956 +eval (validation): [0] [20/63] eta: 0:00:23 time: 0.3987 data: 0.0363 max mem: 3956 +eval (validation): [0] [40/63] eta: 0:00:10 time: 0.3591 data: 0.0026 max mem: 3956 +eval (validation): [0] [60/63] eta: 0:00:01 time: 0.3728 data: 0.0033 max mem: 3956 +eval (validation): [0] [62/63] eta: 0:00:00 time: 0.3727 data: 0.0032 max mem: 3956 +eval (validation): [0] Total time: 0:00:27 (0.4301 s / it) +cv: [0] best hparam: (50, 1.0) (048) ('048_lr5.0e+01_wd1.0e+00') loss: 2.103 acc: 0.407 f1: 0.202 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__linear/checkpoint-best.pth +train: [1] [ 0/400] eta: 0:25:30 lr: nan time: 3.8252 data: 3.5139 max mem: 3956 +train: [1] [ 20/400] eta: 0:03:22 lr: 0.000063 loss: 2.7878 (2.8015) grad: 0.0811 (0.0858) time: 0.3670 data: 0.0107 max mem: 3956 +train: [1] [ 40/400] eta: 0:02:40 lr: 0.000066 loss: 2.8068 (2.8159) grad: 0.0824 (0.0865) time: 0.3579 data: 0.0030 max mem: 3956 +train: [1] [ 60/400] eta: 0:02:23 lr: 0.000069 loss: 2.8002 (2.8045) grad: 0.0891 (0.0893) time: 0.3673 data: 0.0030 max mem: 3956 +train: [1] [ 80/400] eta: 0:02:13 lr: 0.000072 loss: 2.7775 (2.8027) grad: 0.0902 (0.0881) time: 0.4020 data: 0.0036 max mem: 3956 +train: [1] [100/400] eta: 0:02:01 lr: 0.000075 loss: 2.7775 (2.7961) grad: 0.0902 (0.0892) time: 0.3610 data: 0.0032 max mem: 3956 +train: [1] [120/400] eta: 0:01:52 lr: 0.000078 loss: 2.7386 (2.7856) grad: 0.0897 (0.0896) time: 0.3913 data: 0.0035 max mem: 3956 +train: [1] [140/400] eta: 0:01:43 lr: 0.000081 loss: 2.7294 (2.7810) grad: 0.0877 (0.0894) time: 0.3599 data: 0.0035 max mem: 3956 +train: [1] [160/400] eta: 0:01:35 lr: 0.000084 loss: 2.7393 (2.7744) grad: 0.0871 (0.0894) time: 0.4032 data: 0.0034 max mem: 3956 +train: [1] [180/400] eta: 0:01:27 lr: 0.000087 loss: 2.7183 (2.7665) grad: 0.0912 (0.0895) time: 0.3860 data: 0.0033 max mem: 3956 +train: [1] [200/400] eta: 0:01:19 lr: 0.000090 loss: 2.6855 (2.7566) grad: 0.0917 (0.0899) time: 0.3870 data: 0.0034 max mem: 3956 +train: [1] [220/400] eta: 0:01:11 lr: 0.000093 loss: 2.6808 (2.7491) grad: 0.0917 (0.0902) time: 0.3992 data: 0.0035 max mem: 3956 +train: [1] [240/400] eta: 0:01:03 lr: 0.000096 loss: 2.6750 (2.7424) grad: 0.0885 (0.0899) time: 0.3723 data: 0.0032 max mem: 3956 +train: [1] [260/400] eta: 0:00:54 lr: 0.000099 loss: 2.6692 (2.7380) grad: 0.0833 (0.0894) time: 0.3627 data: 0.0033 max mem: 3956 +train: [1] [280/400] eta: 0:00:46 lr: 0.000102 loss: 2.6618 (2.7317) grad: 0.0846 (0.0895) time: 0.3907 data: 0.0035 max mem: 3956 +train: [1] [300/400] eta: 0:00:40 lr: 0.000105 loss: 2.6550 (2.7250) grad: 0.0838 (0.0892) time: 0.5890 data: 0.2012 max mem: 3956 +train: [1] [320/400] eta: 0:00:32 lr: 0.000108 loss: 2.6159 (2.7168) grad: 0.0836 (0.0889) time: 0.3803 data: 0.0037 max mem: 3956 +train: [1] [340/400] eta: 0:00:24 lr: 0.000111 loss: 2.5978 (2.7115) grad: 0.0793 (0.0882) time: 0.3767 data: 0.0030 max mem: 3956 +train: [1] [360/400] eta: 0:00:15 lr: 0.000114 loss: 2.6142 (2.7054) grad: 0.0782 (0.0879) time: 0.3673 data: 0.0034 max mem: 3956 +train: [1] [380/400] eta: 0:00:07 lr: 0.000117 loss: 2.5867 (2.6997) grad: 0.0811 (0.0875) time: 0.3737 data: 0.0033 max mem: 3956 +train: [1] [399/400] eta: 0:00:00 lr: 0.000120 loss: 2.5848 (2.6938) grad: 0.0837 (0.0874) time: 0.3651 data: 0.0033 max mem: 3956 +train: [1] Total time: 0:02:38 (0.3969 s / it) +train: [1] Summary: lr: 0.000120 loss: 2.5848 (2.6938) grad: 0.0837 (0.0874) +eval (validation): [1] [ 0/63] eta: 0:03:48 time: 3.6260 data: 3.3944 max mem: 3956 +eval (validation): [1] [20/63] eta: 0:00:23 time: 0.3875 data: 0.0035 max mem: 3956 +eval (validation): [1] [40/63] eta: 0:00:10 time: 0.3481 data: 0.0037 max mem: 3956 +eval (validation): [1] [60/63] eta: 0:00:01 time: 0.3285 data: 0.0032 max mem: 3956 +eval (validation): [1] [62/63] eta: 0:00:00 time: 0.3265 data: 0.0031 max mem: 3956 +eval (validation): [1] Total time: 0:00:25 (0.4102 s / it) +cv: [1] best hparam: (50, 1.0) (048) ('048_lr5.0e+01_wd1.0e+00') loss: 1.237 acc: 0.736 f1: 0.661 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__linear/checkpoint-best.pth +train: [2] [ 0/400] eta: 0:23:20 lr: nan time: 3.5017 data: 3.2263 max mem: 3956 +train: [2] [ 20/400] eta: 0:03:14 lr: 0.000123 loss: 2.5009 (2.5217) grad: 0.0809 (0.0843) time: 0.3631 data: 0.0137 max mem: 3956 +train: [2] [ 40/400] eta: 0:02:38 lr: 0.000126 loss: 2.5347 (2.5388) grad: 0.0840 (0.0853) time: 0.3639 data: 0.0034 max mem: 3956 +train: [2] [ 60/400] eta: 0:02:19 lr: 0.000129 loss: 2.5432 (2.5391) grad: 0.0801 (0.0824) time: 0.3498 data: 0.0025 max mem: 3956 +train: [2] [ 80/400] eta: 0:02:08 lr: 0.000132 loss: 2.5429 (2.5420) grad: 0.0732 (0.0807) time: 0.3718 data: 0.0035 max mem: 3956 +train: [2] [100/400] eta: 0:01:57 lr: 0.000135 loss: 2.5269 (2.5358) grad: 0.0800 (0.0815) time: 0.3554 data: 0.0034 max mem: 3956 +train: [2] [120/400] eta: 0:01:47 lr: 0.000138 loss: 2.5052 (2.5308) grad: 0.0819 (0.0812) time: 0.3430 data: 0.0033 max mem: 3956 +train: [2] [140/400] eta: 0:01:38 lr: 0.000141 loss: 2.5027 (2.5271) grad: 0.0780 (0.0808) time: 0.3581 data: 0.0036 max mem: 3956 +train: [2] [160/400] eta: 0:01:30 lr: 0.000144 loss: 2.4808 (2.5219) grad: 0.0780 (0.0810) time: 0.3540 data: 0.0034 max mem: 3956 +train: [2] [180/400] eta: 0:01:22 lr: 0.000147 loss: 2.4620 (2.5141) grad: 0.0842 (0.0817) time: 0.3564 data: 0.0033 max mem: 3956 +train: [2] [200/400] eta: 0:01:14 lr: 0.000150 loss: 2.4639 (2.5108) grad: 0.0821 (0.0813) time: 0.3642 data: 0.0035 max mem: 3956 +train: [2] [220/400] eta: 0:01:07 lr: 0.000153 loss: 2.4606 (2.5035) grad: 0.0755 (0.0814) time: 0.3649 data: 0.0035 max mem: 3956 +train: [2] [240/400] eta: 0:00:59 lr: 0.000156 loss: 2.4371 (2.4980) grad: 0.0770 (0.0808) time: 0.3570 data: 0.0031 max mem: 3956 +train: [2] [260/400] eta: 0:00:51 lr: 0.000159 loss: 2.4487 (2.4941) grad: 0.0760 (0.0804) time: 0.3589 data: 0.0033 max mem: 3956 +train: [2] [280/400] eta: 0:00:44 lr: 0.000162 loss: 2.4487 (2.4899) grad: 0.0760 (0.0801) time: 0.3506 data: 0.0036 max mem: 3956 +train: [2] [300/400] eta: 0:00:37 lr: 0.000165 loss: 2.4291 (2.4853) grad: 0.0750 (0.0800) time: 0.5270 data: 0.1889 max mem: 3956 +train: [2] [320/400] eta: 0:00:30 lr: 0.000168 loss: 2.4186 (2.4806) grad: 0.0785 (0.0801) time: 0.3652 data: 0.0035 max mem: 3956 +train: [2] [340/400] eta: 0:00:22 lr: 0.000171 loss: 2.4186 (2.4771) grad: 0.0738 (0.0796) time: 0.3510 data: 0.0030 max mem: 3956 +train: [2] [360/400] eta: 0:00:15 lr: 0.000174 loss: 2.3784 (2.4702) grad: 0.0695 (0.0794) time: 0.3616 data: 0.0034 max mem: 3956 +train: [2] [380/400] eta: 0:00:07 lr: 0.000177 loss: 2.3712 (2.4656) grad: 0.0697 (0.0790) time: 0.3434 data: 0.0035 max mem: 3956 +train: [2] [399/400] eta: 0:00:00 lr: 0.000180 loss: 2.3904 (2.4613) grad: 0.0749 (0.0788) time: 0.3404 data: 0.0033 max mem: 3956 +train: [2] Total time: 0:02:29 (0.3732 s / it) +train: [2] Summary: lr: 0.000180 loss: 2.3904 (2.4613) grad: 0.0749 (0.0788) +eval (validation): [2] [ 0/63] eta: 0:04:27 time: 4.2458 data: 4.0183 max mem: 3956 +eval (validation): [2] [20/63] eta: 0:00:22 time: 0.3456 data: 0.0033 max mem: 3956 +eval (validation): [2] [40/63] eta: 0:00:10 time: 0.3342 data: 0.0034 max mem: 3956 +eval (validation): [2] [60/63] eta: 0:00:01 time: 0.3273 data: 0.0033 max mem: 3956 +eval (validation): [2] [62/63] eta: 0:00:00 time: 0.3270 data: 0.0033 max mem: 3956 +eval (validation): [2] Total time: 0:00:25 (0.4026 s / it) +cv: [2] best hparam: (50, 1.0) (048) ('048_lr5.0e+01_wd1.0e+00') loss: 0.835 acc: 0.832 f1: 0.785 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__linear/checkpoint-best.pth +train: [3] [ 0/400] eta: 0:23:05 lr: nan time: 3.4640 data: 3.1862 max mem: 3956 +train: [3] [ 20/400] eta: 0:03:07 lr: 0.000183 loss: 2.3519 (2.3505) grad: 0.0732 (0.0740) time: 0.3452 data: 0.0041 max mem: 3956 +train: [3] [ 40/400] eta: 0:02:37 lr: 0.000186 loss: 2.3421 (2.3411) grad: 0.0744 (0.0749) time: 0.3763 data: 0.0033 max mem: 3956 +train: [3] [ 60/400] eta: 0:02:19 lr: 0.000189 loss: 2.3062 (2.3301) grad: 0.0730 (0.0740) time: 0.3587 data: 0.0031 max mem: 3956 +train: [3] [ 80/400] eta: 0:02:08 lr: 0.000192 loss: 2.3246 (2.3326) grad: 0.0717 (0.0748) time: 0.3717 data: 0.0034 max mem: 3956 +train: [3] [100/400] eta: 0:01:57 lr: 0.000195 loss: 2.3183 (2.3243) grad: 0.0722 (0.0738) time: 0.3479 data: 0.0032 max mem: 3956 +train: [3] [120/400] eta: 0:01:47 lr: 0.000198 loss: 2.2664 (2.3162) grad: 0.0719 (0.0736) time: 0.3585 data: 0.0033 max mem: 3956 +train: [3] [140/400] eta: 0:01:39 lr: 0.000201 loss: 2.2821 (2.3162) grad: 0.0726 (0.0736) time: 0.3761 data: 0.0035 max mem: 3956 +train: [3] [160/400] eta: 0:01:31 lr: 0.000204 loss: 2.2821 (2.3120) grad: 0.0704 (0.0733) time: 0.3535 data: 0.0033 max mem: 3956 +train: [3] [180/400] eta: 0:01:23 lr: 0.000207 loss: 2.2835 (2.3095) grad: 0.0717 (0.0735) time: 0.3699 data: 0.0033 max mem: 3956 +train: [3] [200/400] eta: 0:01:15 lr: 0.000210 loss: 2.2832 (2.3059) grad: 0.0725 (0.0734) time: 0.3579 data: 0.0033 max mem: 3956 +train: [3] [220/400] eta: 0:01:07 lr: 0.000213 loss: 2.2792 (2.3052) grad: 0.0697 (0.0732) time: 0.3586 data: 0.0034 max mem: 3956 +train: [3] [240/400] eta: 0:00:59 lr: 0.000216 loss: 2.2792 (2.3027) grad: 0.0697 (0.0732) time: 0.3567 data: 0.0033 max mem: 3956 +train: [3] [260/400] eta: 0:00:52 lr: 0.000219 loss: 2.2596 (2.3003) grad: 0.0759 (0.0736) time: 0.3631 data: 0.0033 max mem: 3956 +train: [3] [280/400] eta: 0:00:44 lr: 0.000222 loss: 2.2382 (2.2959) grad: 0.0727 (0.0731) time: 0.3644 data: 0.0035 max mem: 3956 +train: [3] [300/400] eta: 0:00:38 lr: 0.000225 loss: 2.2275 (2.2907) grad: 0.0648 (0.0730) time: 0.5245 data: 0.1859 max mem: 3956 +train: [3] [320/400] eta: 0:00:30 lr: 0.000228 loss: 2.2097 (2.2874) grad: 0.0648 (0.0726) time: 0.3995 data: 0.0043 max mem: 3956 +train: [3] [340/400] eta: 0:00:22 lr: 0.000231 loss: 2.2049 (2.2819) grad: 0.0663 (0.0723) time: 0.3439 data: 0.0027 max mem: 3956 +train: [3] [360/400] eta: 0:00:15 lr: 0.000234 loss: 2.2022 (2.2783) grad: 0.0646 (0.0718) time: 0.3949 data: 0.0035 max mem: 3956 +train: [3] [380/400] eta: 0:00:07 lr: 0.000237 loss: 2.2240 (2.2765) grad: 0.0645 (0.0715) time: 0.3790 data: 0.0035 max mem: 3956 +train: [3] [399/400] eta: 0:00:00 lr: 0.000240 loss: 2.2224 (2.2716) grad: 0.0678 (0.0714) time: 0.3647 data: 0.0035 max mem: 3956 +train: [3] Total time: 0:02:32 (0.3813 s / it) +train: [3] Summary: lr: 0.000240 loss: 2.2224 (2.2716) grad: 0.0678 (0.0714) +eval (validation): [3] [ 0/63] eta: 0:03:52 time: 3.6954 data: 3.4600 max mem: 3956 +eval (validation): [3] [20/63] eta: 0:00:23 time: 0.3887 data: 0.0030 max mem: 3956 +eval (validation): [3] [40/63] eta: 0:00:10 time: 0.3527 data: 0.0034 max mem: 3956 +eval (validation): [3] [60/63] eta: 0:00:01 time: 0.3287 data: 0.0033 max mem: 3956 +eval (validation): [3] [62/63] eta: 0:00:00 time: 0.3289 data: 0.0033 max mem: 3956 +eval (validation): [3] Total time: 0:00:26 (0.4144 s / it) +cv: [3] best hparam: (50, 1.0) (048) ('048_lr5.0e+01_wd1.0e+00') loss: 0.638 acc: 0.872 f1: 0.852 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__linear/checkpoint-best.pth +train: [4] [ 0/400] eta: 0:22:52 lr: nan time: 3.4305 data: 3.1927 max mem: 3956 +train: [4] [ 20/400] eta: 0:03:12 lr: 0.000243 loss: 2.1948 (2.2009) grad: 0.0624 (0.0686) time: 0.3595 data: 0.0060 max mem: 3956 +train: [4] [ 40/400] eta: 0:02:37 lr: 0.000246 loss: 2.1636 (2.1912) grad: 0.0641 (0.0676) time: 0.3648 data: 0.0032 max mem: 3956 +train: [4] [ 60/400] eta: 0:02:20 lr: 0.000249 loss: 2.1632 (2.1759) grad: 0.0652 (0.0687) time: 0.3615 data: 0.0029 max mem: 3956 +train: [4] [ 80/400] eta: 0:02:07 lr: 0.000252 loss: 2.1584 (2.1672) grad: 0.0675 (0.0682) time: 0.3533 data: 0.0035 max mem: 3956 +train: [4] [100/400] eta: 0:01:56 lr: 0.000255 loss: 2.1609 (2.1658) grad: 0.0649 (0.0675) time: 0.3477 data: 0.0031 max mem: 3956 +train: [4] [120/400] eta: 0:01:47 lr: 0.000258 loss: 2.1711 (2.1662) grad: 0.0649 (0.0671) time: 0.3651 data: 0.0033 max mem: 3956 +train: [4] [140/400] eta: 0:01:39 lr: 0.000261 loss: 2.1459 (2.1594) grad: 0.0678 (0.0673) time: 0.3662 data: 0.0034 max mem: 3956 +train: [4] [160/400] eta: 0:01:30 lr: 0.000264 loss: 2.1264 (2.1559) grad: 0.0668 (0.0669) time: 0.3579 data: 0.0032 max mem: 3956 +train: [4] [180/400] eta: 0:01:22 lr: 0.000267 loss: 2.1317 (2.1523) grad: 0.0663 (0.0668) time: 0.3576 data: 0.0034 max mem: 3956 +train: [4] [200/400] eta: 0:01:14 lr: 0.000270 loss: 2.1037 (2.1457) grad: 0.0644 (0.0668) time: 0.3508 data: 0.0035 max mem: 3956 +train: [4] [220/400] eta: 0:01:06 lr: 0.000273 loss: 2.1036 (2.1444) grad: 0.0622 (0.0661) time: 0.3510 data: 0.0033 max mem: 3956 +train: [4] [240/400] eta: 0:00:59 lr: 0.000276 loss: 2.1010 (2.1392) grad: 0.0611 (0.0662) time: 0.3734 data: 0.0035 max mem: 3956 +train: [4] [260/400] eta: 0:00:52 lr: 0.000279 loss: 2.0573 (2.1336) grad: 0.0643 (0.0659) time: 0.3687 data: 0.0035 max mem: 3956 +train: [4] [280/400] eta: 0:00:44 lr: 0.000282 loss: 2.0792 (2.1316) grad: 0.0609 (0.0656) time: 0.3554 data: 0.0035 max mem: 3956 +train: [4] [300/400] eta: 0:00:38 lr: 0.000285 loss: 2.1022 (2.1283) grad: 0.0606 (0.0654) time: 0.5426 data: 0.2144 max mem: 3956 +train: [4] [320/400] eta: 0:00:30 lr: 0.000288 loss: 2.0829 (2.1243) grad: 0.0655 (0.0657) time: 0.3732 data: 0.0123 max mem: 3956 +train: [4] [340/400] eta: 0:00:22 lr: 0.000291 loss: 2.0829 (2.1223) grad: 0.0631 (0.0654) time: 0.3461 data: 0.0043 max mem: 3956 +train: [4] [360/400] eta: 0:00:15 lr: 0.000294 loss: 2.0690 (2.1195) grad: 0.0616 (0.0653) time: 0.3493 data: 0.0034 max mem: 3956 +train: [4] [380/400] eta: 0:00:07 lr: 0.000297 loss: 2.0690 (2.1168) grad: 0.0616 (0.0651) time: 0.3754 data: 0.0034 max mem: 3956 +train: [4] [399/400] eta: 0:00:00 lr: 0.000300 loss: 2.0624 (2.1131) grad: 0.0589 (0.0649) time: 0.3757 data: 0.0033 max mem: 3956 +train: [4] Total time: 0:02:31 (0.3776 s / it) +train: [4] Summary: lr: 0.000300 loss: 2.0624 (2.1131) grad: 0.0589 (0.0649) +eval (validation): [4] [ 0/63] eta: 0:03:44 time: 3.5711 data: 3.3217 max mem: 3956 +eval (validation): [4] [20/63] eta: 0:00:23 time: 0.3861 data: 0.0039 max mem: 3956 +eval (validation): [4] [40/63] eta: 0:00:10 time: 0.3536 data: 0.0032 max mem: 3956 +eval (validation): [4] [60/63] eta: 0:00:01 time: 0.3682 data: 0.0033 max mem: 3956 +eval (validation): [4] [62/63] eta: 0:00:00 time: 0.3739 data: 0.0033 max mem: 3956 +eval (validation): [4] Total time: 0:00:26 (0.4256 s / it) +cv: [4] best hparam: (50, 1.0) (048) ('048_lr5.0e+01_wd1.0e+00') loss: 0.533 acc: 0.890 f1: 0.872 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__linear/checkpoint-best.pth +train: [5] [ 0/400] eta: 0:24:13 lr: nan time: 3.6329 data: 3.3237 max mem: 3956 +train: [5] [ 20/400] eta: 0:03:21 lr: 0.000300 loss: 2.0223 (2.0412) grad: 0.0590 (0.0602) time: 0.3751 data: 0.0042 max mem: 3956 +train: [5] [ 40/400] eta: 0:02:42 lr: 0.000300 loss: 2.0567 (2.0572) grad: 0.0577 (0.0597) time: 0.3683 data: 0.0032 max mem: 3956 +train: [5] [ 60/400] eta: 0:02:23 lr: 0.000300 loss: 2.0382 (2.0416) grad: 0.0645 (0.0621) time: 0.3647 data: 0.0035 max mem: 3956 +train: [5] [ 80/400] eta: 0:02:09 lr: 0.000300 loss: 1.9948 (2.0353) grad: 0.0645 (0.0617) time: 0.3515 data: 0.0035 max mem: 3956 +train: [5] [100/400] eta: 0:01:58 lr: 0.000300 loss: 1.9896 (2.0257) grad: 0.0646 (0.0629) time: 0.3610 data: 0.0036 max mem: 3956 +train: [5] [120/400] eta: 0:01:49 lr: 0.000300 loss: 2.0153 (2.0236) grad: 0.0665 (0.0635) time: 0.3731 data: 0.0035 max mem: 3956 +train: [5] [140/400] eta: 0:01:40 lr: 0.000300 loss: 2.0186 (2.0206) grad: 0.0637 (0.0633) time: 0.3521 data: 0.0034 max mem: 3956 +train: [5] [160/400] eta: 0:01:32 lr: 0.000299 loss: 1.9782 (2.0163) grad: 0.0609 (0.0632) time: 0.3629 data: 0.0034 max mem: 3956 +train: [5] [180/400] eta: 0:01:23 lr: 0.000299 loss: 1.9904 (2.0164) grad: 0.0603 (0.0630) time: 0.3619 data: 0.0038 max mem: 3956 +train: [5] [200/400] eta: 0:01:15 lr: 0.000299 loss: 2.0021 (2.0171) grad: 0.0616 (0.0630) time: 0.3594 data: 0.0036 max mem: 3956 +train: [5] [220/400] eta: 0:01:07 lr: 0.000299 loss: 1.9935 (2.0134) grad: 0.0597 (0.0628) time: 0.3573 data: 0.0036 max mem: 3956 +train: [5] [240/400] eta: 0:01:00 lr: 0.000299 loss: 1.9692 (2.0098) grad: 0.0590 (0.0627) time: 0.3567 data: 0.0033 max mem: 3956 +train: [5] [260/400] eta: 0:00:52 lr: 0.000299 loss: 1.9796 (2.0085) grad: 0.0563 (0.0624) time: 0.3510 data: 0.0033 max mem: 3956 +train: [5] [280/400] eta: 0:00:44 lr: 0.000298 loss: 1.9796 (2.0062) grad: 0.0559 (0.0621) time: 0.3635 data: 0.0033 max mem: 3956 +train: [5] [300/400] eta: 0:00:38 lr: 0.000298 loss: 1.9642 (2.0042) grad: 0.0560 (0.0616) time: 0.5563 data: 0.1949 max mem: 3956 +train: [5] [320/400] eta: 0:00:30 lr: 0.000298 loss: 1.9673 (2.0031) grad: 0.0577 (0.0612) time: 0.3599 data: 0.0034 max mem: 3956 +train: [5] [340/400] eta: 0:00:22 lr: 0.000298 loss: 1.9637 (2.0012) grad: 0.0591 (0.0612) time: 0.3456 data: 0.0032 max mem: 3956 +train: [5] [360/400] eta: 0:00:15 lr: 0.000297 loss: 1.9784 (1.9999) grad: 0.0591 (0.0611) time: 0.3400 data: 0.0034 max mem: 3956 +train: [5] [380/400] eta: 0:00:07 lr: 0.000297 loss: 1.9973 (1.9994) grad: 0.0614 (0.0612) time: 0.3531 data: 0.0034 max mem: 3956 +train: [5] [399/400] eta: 0:00:00 lr: 0.000297 loss: 1.9507 (1.9964) grad: 0.0617 (0.0611) time: 0.3680 data: 0.0034 max mem: 3956 +train: [5] Total time: 0:02:31 (0.3776 s / it) +train: [5] Summary: lr: 0.000297 loss: 1.9507 (1.9964) grad: 0.0617 (0.0611) +eval (validation): [5] [ 0/63] eta: 0:03:43 time: 3.5461 data: 3.2695 max mem: 3956 +eval (validation): [5] [20/63] eta: 0:00:21 time: 0.3439 data: 0.0127 max mem: 3956 +eval (validation): [5] [40/63] eta: 0:00:09 time: 0.3437 data: 0.0035 max mem: 3956 +eval (validation): [5] [60/63] eta: 0:00:01 time: 0.3300 data: 0.0030 max mem: 3956 +eval (validation): [5] [62/63] eta: 0:00:00 time: 0.3291 data: 0.0033 max mem: 3956 +eval (validation): [5] Total time: 0:00:24 (0.3947 s / it) +cv: [5] best hparam: (36, 1.0) (046) ('046_lr3.6e+01_wd1.0e+00') loss: 0.524 acc: 0.895 f1: 0.879 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__linear/checkpoint-best.pth +train: [6] [ 0/400] eta: 0:23:25 lr: nan time: 3.5137 data: 3.2326 max mem: 3956 +train: [6] [ 20/400] eta: 0:03:12 lr: 0.000296 loss: 1.9619 (1.9624) grad: 0.0543 (0.0545) time: 0.3557 data: 0.0035 max mem: 3956 +train: [6] [ 40/400] eta: 0:02:38 lr: 0.000296 loss: 1.9481 (1.9541) grad: 0.0543 (0.0566) time: 0.3728 data: 0.0032 max mem: 3956 +train: [6] [ 60/400] eta: 0:02:22 lr: 0.000296 loss: 1.9322 (1.9467) grad: 0.0596 (0.0573) time: 0.3741 data: 0.0033 max mem: 3956 +train: [6] [ 80/400] eta: 0:02:09 lr: 0.000295 loss: 1.9021 (1.9356) grad: 0.0585 (0.0573) time: 0.3599 data: 0.0034 max mem: 3956 +train: [6] [100/400] eta: 0:01:57 lr: 0.000295 loss: 1.9092 (1.9318) grad: 0.0559 (0.0572) time: 0.3440 data: 0.0036 max mem: 3956 +train: [6] [120/400] eta: 0:01:48 lr: 0.000295 loss: 1.9093 (1.9263) grad: 0.0572 (0.0574) time: 0.3686 data: 0.0035 max mem: 3956 +train: [6] [140/400] eta: 0:01:40 lr: 0.000294 loss: 1.8930 (1.9193) grad: 0.0602 (0.0585) time: 0.3657 data: 0.0035 max mem: 3956 +train: [6] [160/400] eta: 0:01:32 lr: 0.000294 loss: 1.8864 (1.9177) grad: 0.0602 (0.0589) time: 0.3752 data: 0.0035 max mem: 3956 +train: [6] [180/400] eta: 0:01:24 lr: 0.000293 loss: 1.9140 (1.9183) grad: 0.0572 (0.0591) time: 0.3815 data: 0.0034 max mem: 3956 +train: [6] [200/400] eta: 0:01:16 lr: 0.000293 loss: 1.9310 (1.9183) grad: 0.0568 (0.0590) time: 0.3819 data: 0.0036 max mem: 3956 +train: [6] [220/400] eta: 0:01:09 lr: 0.000292 loss: 1.8974 (1.9150) grad: 0.0554 (0.0590) time: 0.3876 data: 0.0032 max mem: 3956 +train: [6] [240/400] eta: 0:01:01 lr: 0.000292 loss: 1.8893 (1.9136) grad: 0.0567 (0.0591) time: 0.3686 data: 0.0034 max mem: 3956 +train: [6] [260/400] eta: 0:00:53 lr: 0.000291 loss: 1.8855 (1.9128) grad: 0.0578 (0.0593) time: 0.3810 data: 0.0036 max mem: 3956 +train: [6] [280/400] eta: 0:00:45 lr: 0.000291 loss: 1.8645 (1.9088) grad: 0.0553 (0.0590) time: 0.3846 data: 0.0032 max mem: 3956 +train: [6] [300/400] eta: 0:00:39 lr: 0.000290 loss: 1.8635 (1.9061) grad: 0.0532 (0.0587) time: 0.5316 data: 0.1928 max mem: 3956 +train: [6] [320/400] eta: 0:00:31 lr: 0.000290 loss: 1.8621 (1.9023) grad: 0.0551 (0.0585) time: 0.4282 data: 0.0034 max mem: 3956 +train: [6] [340/400] eta: 0:00:23 lr: 0.000289 loss: 1.8558 (1.9006) grad: 0.0601 (0.0585) time: 0.3646 data: 0.0029 max mem: 3956 +train: [6] [360/400] eta: 0:00:15 lr: 0.000288 loss: 1.8489 (1.8973) grad: 0.0603 (0.0586) time: 0.3973 data: 0.0031 max mem: 3956 +train: [6] [380/400] eta: 0:00:07 lr: 0.000288 loss: 1.8426 (1.8967) grad: 0.0569 (0.0585) time: 0.3686 data: 0.0033 max mem: 3956 +train: [6] [399/400] eta: 0:00:00 lr: 0.000287 loss: 1.8567 (1.8950) grad: 0.0575 (0.0586) time: 0.3775 data: 0.0031 max mem: 3956 +train: [6] Total time: 0:02:36 (0.3915 s / it) +train: [6] Summary: lr: 0.000287 loss: 1.8567 (1.8950) grad: 0.0575 (0.0586) +eval (validation): [6] [ 0/63] eta: 0:03:53 time: 3.7134 data: 3.4028 max mem: 3956 +eval (validation): [6] [20/63] eta: 0:00:22 time: 0.3718 data: 0.0041 max mem: 3956 +eval (validation): [6] [40/63] eta: 0:00:10 time: 0.3732 data: 0.0028 max mem: 3956 +eval (validation): [6] [60/63] eta: 0:00:01 time: 0.3564 data: 0.0034 max mem: 3956 +eval (validation): [6] [62/63] eta: 0:00:00 time: 0.3569 data: 0.0034 max mem: 3956 +eval (validation): [6] Total time: 0:00:26 (0.4245 s / it) +cv: [6] best hparam: (50, 1.0) (048) ('048_lr5.0e+01_wd1.0e+00') loss: 0.443 acc: 0.909 f1: 0.889 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__linear/checkpoint-best.pth +train: [7] [ 0/400] eta: 0:25:15 lr: nan time: 3.7887 data: 3.4544 max mem: 3956 +train: [7] [ 20/400] eta: 0:03:49 lr: 0.000286 loss: 1.8169 (1.8531) grad: 0.0581 (0.0566) time: 0.4443 data: 0.0030 max mem: 3956 +train: [7] [ 40/400] eta: 0:02:57 lr: 0.000286 loss: 1.8248 (1.8516) grad: 0.0555 (0.0569) time: 0.3762 data: 0.0033 max mem: 3956 +train: [7] [ 60/400] eta: 0:02:35 lr: 0.000285 loss: 1.8248 (1.8404) grad: 0.0600 (0.0591) time: 0.3892 data: 0.0032 max mem: 3956 +train: [7] [ 80/400] eta: 0:02:22 lr: 0.000284 loss: 1.8725 (1.8525) grad: 0.0557 (0.0577) time: 0.4000 data: 0.0036 max mem: 3956 +train: [7] [100/400] eta: 0:02:08 lr: 0.000284 loss: 1.8551 (1.8452) grad: 0.0508 (0.0565) time: 0.3695 data: 0.0033 max mem: 3956 +train: [7] [120/400] eta: 0:01:58 lr: 0.000283 loss: 1.8241 (1.8420) grad: 0.0546 (0.0564) time: 0.3889 data: 0.0038 max mem: 3956 +train: [7] [140/400] eta: 0:01:48 lr: 0.000282 loss: 1.8455 (1.8436) grad: 0.0538 (0.0558) time: 0.3974 data: 0.0036 max mem: 3956 +train: [7] [160/400] eta: 0:01:39 lr: 0.000282 loss: 1.8286 (1.8417) grad: 0.0526 (0.0555) time: 0.3967 data: 0.0036 max mem: 3956 +train: [7] [180/400] eta: 0:01:31 lr: 0.000281 loss: 1.8136 (1.8390) grad: 0.0526 (0.0554) time: 0.4090 data: 0.0036 max mem: 3956 +train: [7] [200/400] eta: 0:01:22 lr: 0.000280 loss: 1.8132 (1.8390) grad: 0.0525 (0.0550) time: 0.3772 data: 0.0033 max mem: 3956 +train: [7] [220/400] eta: 0:01:13 lr: 0.000279 loss: 1.8443 (1.8397) grad: 0.0532 (0.0552) time: 0.3710 data: 0.0034 max mem: 3956 +train: [7] [240/400] eta: 0:01:04 lr: 0.000278 loss: 1.8495 (1.8395) grad: 0.0554 (0.0552) time: 0.3829 data: 0.0035 max mem: 3956 +train: [7] [260/400] eta: 0:00:56 lr: 0.000278 loss: 1.8149 (1.8382) grad: 0.0543 (0.0550) time: 0.3748 data: 0.0034 max mem: 3956 +train: [7] [280/400] eta: 0:00:48 lr: 0.000277 loss: 1.8303 (1.8380) grad: 0.0513 (0.0548) time: 0.3690 data: 0.0034 max mem: 3956 +train: [7] [300/400] eta: 0:00:41 lr: 0.000276 loss: 1.8279 (1.8375) grad: 0.0507 (0.0545) time: 0.5592 data: 0.2241 max mem: 3956 +train: [7] [320/400] eta: 0:00:32 lr: 0.000275 loss: 1.8255 (1.8342) grad: 0.0515 (0.0546) time: 0.3877 data: 0.0032 max mem: 3956 +train: [7] [340/400] eta: 0:00:24 lr: 0.000274 loss: 1.7815 (1.8305) grad: 0.0562 (0.0548) time: 0.3856 data: 0.0031 max mem: 3956 +train: [7] [360/400] eta: 0:00:16 lr: 0.000273 loss: 1.8128 (1.8317) grad: 0.0557 (0.0549) time: 0.3672 data: 0.0033 max mem: 3956 +train: [7] [380/400] eta: 0:00:08 lr: 0.000272 loss: 1.8286 (1.8304) grad: 0.0557 (0.0552) time: 0.3615 data: 0.0034 max mem: 3956 +train: [7] [399/400] eta: 0:00:00 lr: 0.000271 loss: 1.8149 (1.8296) grad: 0.0565 (0.0553) time: 0.3770 data: 0.0033 max mem: 3956 +train: [7] Total time: 0:02:41 (0.4030 s / it) +train: [7] Summary: lr: 0.000271 loss: 1.8149 (1.8296) grad: 0.0565 (0.0553) +eval (validation): [7] [ 0/63] eta: 0:03:55 time: 3.7348 data: 3.4152 max mem: 3956 +eval (validation): [7] [20/63] eta: 0:00:23 time: 0.3908 data: 0.0041 max mem: 3956 +eval (validation): [7] [40/63] eta: 0:00:10 time: 0.3740 data: 0.0030 max mem: 3956 +eval (validation): [7] [60/63] eta: 0:00:01 time: 0.3654 data: 0.0032 max mem: 3956 +eval (validation): [7] [62/63] eta: 0:00:00 time: 0.3618 data: 0.0032 max mem: 3956 +eval (validation): [7] Total time: 0:00:27 (0.4332 s / it) +cv: [7] best hparam: (50, 1.0) (048) ('048_lr5.0e+01_wd1.0e+00') loss: 0.439 acc: 0.897 f1: 0.872 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__linear/checkpoint-last.pth +train: [8] [ 0/400] eta: 0:24:20 lr: nan time: 3.6522 data: 3.3708 max mem: 3956 +train: [8] [ 20/400] eta: 0:03:25 lr: 0.000270 loss: 1.7738 (1.7676) grad: 0.0509 (0.0520) time: 0.3863 data: 0.0036 max mem: 3956 +train: [8] [ 40/400] eta: 0:02:44 lr: 0.000270 loss: 1.7958 (1.8000) grad: 0.0517 (0.0550) time: 0.3695 data: 0.0030 max mem: 3956 +train: [8] [ 60/400] eta: 0:02:25 lr: 0.000269 loss: 1.8185 (1.8046) grad: 0.0536 (0.0555) time: 0.3704 data: 0.0035 max mem: 3956 +train: [8] [ 80/400] eta: 0:02:09 lr: 0.000268 loss: 1.8310 (1.8119) grad: 0.0527 (0.0545) time: 0.3355 data: 0.0033 max mem: 3956 +train: [8] [100/400] eta: 0:01:58 lr: 0.000267 loss: 1.8067 (1.8043) grad: 0.0508 (0.0540) time: 0.3518 data: 0.0035 max mem: 3956 +train: [8] [120/400] eta: 0:01:49 lr: 0.000266 loss: 1.7793 (1.8020) grad: 0.0522 (0.0537) time: 0.3608 data: 0.0035 max mem: 3956 +train: [8] [140/400] eta: 0:01:40 lr: 0.000265 loss: 1.7958 (1.8009) grad: 0.0534 (0.0538) time: 0.3616 data: 0.0033 max mem: 3956 +train: [8] [160/400] eta: 0:01:31 lr: 0.000264 loss: 1.7710 (1.7930) grad: 0.0515 (0.0536) time: 0.3580 data: 0.0034 max mem: 3956 +train: [8] [180/400] eta: 0:01:23 lr: 0.000263 loss: 1.7448 (1.7881) grad: 0.0546 (0.0543) time: 0.3601 data: 0.0033 max mem: 3956 +train: [8] [200/400] eta: 0:01:15 lr: 0.000262 loss: 1.7708 (1.7881) grad: 0.0568 (0.0543) time: 0.3575 data: 0.0032 max mem: 3956 +train: [8] [220/400] eta: 0:01:07 lr: 0.000260 loss: 1.7915 (1.7889) grad: 0.0543 (0.0546) time: 0.3557 data: 0.0035 max mem: 3956 +train: [8] [240/400] eta: 0:00:59 lr: 0.000259 loss: 1.7638 (1.7841) grad: 0.0543 (0.0547) time: 0.3610 data: 0.0037 max mem: 3956 +train: [8] [260/400] eta: 0:00:52 lr: 0.000258 loss: 1.7432 (1.7819) grad: 0.0533 (0.0546) time: 0.3658 data: 0.0035 max mem: 3956 +train: [8] [280/400] eta: 0:00:44 lr: 0.000257 loss: 1.7435 (1.7795) grad: 0.0518 (0.0547) time: 0.3709 data: 0.0033 max mem: 3956 +train: [8] [300/400] eta: 0:00:38 lr: 0.000256 loss: 1.7452 (1.7785) grad: 0.0516 (0.0544) time: 0.5332 data: 0.1957 max mem: 3956 +train: [8] [320/400] eta: 0:00:30 lr: 0.000255 loss: 1.7569 (1.7766) grad: 0.0495 (0.0541) time: 0.3653 data: 0.0037 max mem: 3956 +train: [8] [340/400] eta: 0:00:22 lr: 0.000254 loss: 1.7569 (1.7754) grad: 0.0498 (0.0539) time: 0.3599 data: 0.0033 max mem: 3956 +train: [8] [360/400] eta: 0:00:15 lr: 0.000253 loss: 1.7267 (1.7734) grad: 0.0509 (0.0538) time: 0.3526 data: 0.0033 max mem: 3956 +train: [8] [380/400] eta: 0:00:07 lr: 0.000252 loss: 1.7350 (1.7725) grad: 0.0520 (0.0537) time: 0.3380 data: 0.0032 max mem: 3956 +train: [8] [399/400] eta: 0:00:00 lr: 0.000250 loss: 1.7686 (1.7727) grad: 0.0528 (0.0538) time: 0.3618 data: 0.0036 max mem: 3956 +train: [8] Total time: 0:02:30 (0.3773 s / it) +train: [8] Summary: lr: 0.000250 loss: 1.7686 (1.7727) grad: 0.0528 (0.0538) +eval (validation): [8] [ 0/63] eta: 0:03:37 time: 3.4582 data: 3.2299 max mem: 3956 +eval (validation): [8] [20/63] eta: 0:00:21 time: 0.3473 data: 0.0044 max mem: 3956 +eval (validation): [8] [40/63] eta: 0:00:09 time: 0.3691 data: 0.0034 max mem: 3956 +eval (validation): [8] [60/63] eta: 0:00:01 time: 0.3460 data: 0.0030 max mem: 3956 +eval (validation): [8] [62/63] eta: 0:00:00 time: 0.3434 data: 0.0032 max mem: 3956 +eval (validation): [8] Total time: 0:00:25 (0.4074 s / it) +cv: [8] best hparam: (26, 1.0) (044) ('044_lr2.6e+01_wd1.0e+00') loss: 0.469 acc: 0.907 f1: 0.896 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__linear/checkpoint-last.pth +train: [9] [ 0/400] eta: 0:24:00 lr: nan time: 3.6003 data: 3.2898 max mem: 3956 +train: [9] [ 20/400] eta: 0:03:12 lr: 0.000249 loss: 1.7352 (1.7469) grad: 0.0531 (0.0530) time: 0.3515 data: 0.0028 max mem: 3956 +train: [9] [ 40/400] eta: 0:02:39 lr: 0.000248 loss: 1.7352 (1.7467) grad: 0.0509 (0.0518) time: 0.3785 data: 0.0033 max mem: 3956 +train: [9] [ 60/400] eta: 0:02:24 lr: 0.000247 loss: 1.7195 (1.7392) grad: 0.0489 (0.0516) time: 0.3859 data: 0.0035 max mem: 3956 +train: [9] [ 80/400] eta: 0:02:11 lr: 0.000246 loss: 1.7152 (1.7361) grad: 0.0541 (0.0528) time: 0.3668 data: 0.0034 max mem: 3956 +train: [9] [100/400] eta: 0:01:59 lr: 0.000244 loss: 1.7063 (1.7281) grad: 0.0541 (0.0526) time: 0.3447 data: 0.0033 max mem: 3956 +train: [9] [120/400] eta: 0:01:50 lr: 0.000243 loss: 1.7063 (1.7312) grad: 0.0494 (0.0521) time: 0.3719 data: 0.0033 max mem: 3956 +train: [9] [140/400] eta: 0:01:42 lr: 0.000242 loss: 1.7598 (1.7350) grad: 0.0496 (0.0523) time: 0.3935 data: 0.0033 max mem: 3956 +train: [9] [160/400] eta: 0:01:34 lr: 0.000241 loss: 1.7262 (1.7311) grad: 0.0502 (0.0521) time: 0.3902 data: 0.0033 max mem: 3956 +train: [9] [180/400] eta: 0:01:26 lr: 0.000240 loss: 1.7110 (1.7332) grad: 0.0514 (0.0519) time: 0.3902 data: 0.0033 max mem: 3956 +train: [9] [200/400] eta: 0:01:18 lr: 0.000238 loss: 1.7479 (1.7356) grad: 0.0508 (0.0522) time: 0.4061 data: 0.0034 max mem: 3956 +train: [9] [220/400] eta: 0:01:10 lr: 0.000237 loss: 1.7541 (1.7365) grad: 0.0516 (0.0523) time: 0.3964 data: 0.0032 max mem: 3956 +train: [9] [240/400] eta: 0:01:02 lr: 0.000236 loss: 1.7123 (1.7337) grad: 0.0495 (0.0521) time: 0.3754 data: 0.0035 max mem: 3956 +train: [9] [260/400] eta: 0:00:55 lr: 0.000234 loss: 1.6978 (1.7314) grad: 0.0511 (0.0521) time: 0.4038 data: 0.0036 max mem: 3956 +train: [9] [280/400] eta: 0:00:47 lr: 0.000233 loss: 1.7276 (1.7325) grad: 0.0511 (0.0520) time: 0.4271 data: 0.0035 max mem: 3956 +train: [9] [300/400] eta: 0:00:40 lr: 0.000232 loss: 1.7187 (1.7303) grad: 0.0473 (0.0519) time: 0.5728 data: 0.1879 max mem: 3956 +train: [9] [320/400] eta: 0:00:32 lr: 0.000230 loss: 1.6939 (1.7283) grad: 0.0530 (0.0522) time: 0.4569 data: 0.0040 max mem: 3956 +train: [9] [340/400] eta: 0:00:24 lr: 0.000229 loss: 1.6876 (1.7270) grad: 0.0530 (0.0520) time: 0.4165 data: 0.0033 max mem: 3956 +train: [9] [360/400] eta: 0:00:16 lr: 0.000228 loss: 1.7151 (1.7273) grad: 0.0523 (0.0521) time: 0.4018 data: 0.0035 max mem: 3956 +train: [9] [380/400] eta: 0:00:08 lr: 0.000226 loss: 1.7158 (1.7268) grad: 0.0539 (0.0521) time: 0.3748 data: 0.0033 max mem: 3956 +train: [9] [399/400] eta: 0:00:00 lr: 0.000225 loss: 1.7203 (1.7277) grad: 0.0515 (0.0521) time: 0.3682 data: 0.0035 max mem: 3956 +train: [9] Total time: 0:02:42 (0.4070 s / it) +train: [9] Summary: lr: 0.000225 loss: 1.7203 (1.7277) grad: 0.0515 (0.0521) +eval (validation): [9] [ 0/63] eta: 0:03:53 time: 3.7124 data: 3.3933 max mem: 3956 +eval (validation): [9] [20/63] eta: 0:00:25 time: 0.4381 data: 0.0038 max mem: 3956 +eval (validation): [9] [40/63] eta: 0:00:11 time: 0.3723 data: 0.0035 max mem: 3956 +eval (validation): [9] [60/63] eta: 0:00:01 time: 0.3560 data: 0.0034 max mem: 3956 +eval (validation): [9] [62/63] eta: 0:00:00 time: 0.3595 data: 0.0034 max mem: 3956 +eval (validation): [9] Total time: 0:00:28 (0.4457 s / it) +cv: [9] best hparam: (43, 1.0) (047) ('047_lr4.3e+01_wd1.0e+00') loss: 0.395 acc: 0.921 f1: 0.908 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__linear/checkpoint-best.pth +train: [10] [ 0/400] eta: 0:22:25 lr: nan time: 3.3631 data: 3.1362 max mem: 3956 +train: [10] [ 20/400] eta: 0:03:18 lr: 0.000224 loss: 1.7470 (1.7583) grad: 0.0523 (0.0523) time: 0.3803 data: 0.0039 max mem: 3956 +train: [10] [ 40/400] eta: 0:02:41 lr: 0.000222 loss: 1.6973 (1.7121) grad: 0.0518 (0.0525) time: 0.3697 data: 0.0030 max mem: 3956 +train: [10] [ 60/400] eta: 0:02:25 lr: 0.000221 loss: 1.6710 (1.7087) grad: 0.0513 (0.0521) time: 0.3841 data: 0.0033 max mem: 3956 +train: [10] [ 80/400] eta: 0:02:11 lr: 0.000220 loss: 1.7079 (1.7049) grad: 0.0522 (0.0523) time: 0.3623 data: 0.0035 max mem: 3956 +train: [10] [100/400] eta: 0:02:00 lr: 0.000218 loss: 1.6989 (1.7050) grad: 0.0508 (0.0514) time: 0.3698 data: 0.0034 max mem: 3956 +train: [10] [120/400] eta: 0:01:51 lr: 0.000217 loss: 1.7184 (1.7048) grad: 0.0505 (0.0516) time: 0.3689 data: 0.0035 max mem: 3956 +train: [10] [140/400] eta: 0:01:41 lr: 0.000215 loss: 1.6718 (1.7024) grad: 0.0490 (0.0510) time: 0.3574 data: 0.0034 max mem: 3956 +train: [10] [160/400] eta: 0:01:33 lr: 0.000214 loss: 1.6654 (1.6974) grad: 0.0477 (0.0511) time: 0.3633 data: 0.0036 max mem: 3956 +train: [10] [180/400] eta: 0:01:24 lr: 0.000213 loss: 1.6907 (1.7036) grad: 0.0472 (0.0507) time: 0.3548 data: 0.0034 max mem: 3956 +train: [10] [200/400] eta: 0:01:16 lr: 0.000211 loss: 1.7050 (1.7038) grad: 0.0476 (0.0509) time: 0.3600 data: 0.0035 max mem: 3956 +train: [10] [220/400] eta: 0:01:08 lr: 0.000210 loss: 1.6929 (1.7021) grad: 0.0516 (0.0510) time: 0.3668 data: 0.0035 max mem: 3956 +train: [10] [240/400] eta: 0:01:00 lr: 0.000208 loss: 1.6774 (1.6978) grad: 0.0516 (0.0510) time: 0.3717 data: 0.0035 max mem: 3956 +train: [10] [260/400] eta: 0:00:53 lr: 0.000207 loss: 1.6549 (1.6949) grad: 0.0526 (0.0512) time: 0.3707 data: 0.0033 max mem: 3956 +train: [10] [280/400] eta: 0:00:45 lr: 0.000205 loss: 1.6826 (1.6937) grad: 0.0550 (0.0517) time: 0.3824 data: 0.0035 max mem: 3956 +train: [10] [300/400] eta: 0:00:38 lr: 0.000204 loss: 1.6859 (1.6934) grad: 0.0534 (0.0515) time: 0.5251 data: 0.1894 max mem: 3956 +train: [10] [320/400] eta: 0:00:31 lr: 0.000202 loss: 1.6859 (1.6941) grad: 0.0505 (0.0516) time: 0.3783 data: 0.0039 max mem: 3956 +train: [10] [340/400] eta: 0:00:23 lr: 0.000201 loss: 1.6661 (1.6914) grad: 0.0503 (0.0515) time: 0.3811 data: 0.0029 max mem: 3956 +train: [10] [360/400] eta: 0:00:15 lr: 0.000199 loss: 1.6594 (1.6904) grad: 0.0491 (0.0514) time: 0.3801 data: 0.0034 max mem: 3956 +train: [10] [380/400] eta: 0:00:07 lr: 0.000198 loss: 1.6594 (1.6875) grad: 0.0500 (0.0514) time: 0.3619 data: 0.0033 max mem: 3956 +train: [10] [399/400] eta: 0:00:00 lr: 0.000196 loss: 1.6212 (1.6840) grad: 0.0548 (0.0517) time: 0.3714 data: 0.0034 max mem: 3956 +train: [10] Total time: 0:02:34 (0.3858 s / it) +train: [10] Summary: lr: 0.000196 loss: 1.6212 (1.6840) grad: 0.0548 (0.0517) +eval (validation): [10] [ 0/63] eta: 0:03:57 time: 3.7734 data: 3.4727 max mem: 3956 +eval (validation): [10] [20/63] eta: 0:00:25 time: 0.4244 data: 0.0047 max mem: 3956 +eval (validation): [10] [40/63] eta: 0:00:10 time: 0.3547 data: 0.0030 max mem: 3956 +eval (validation): [10] [60/63] eta: 0:00:01 time: 0.3334 data: 0.0035 max mem: 3956 +eval (validation): [10] [62/63] eta: 0:00:00 time: 0.3331 data: 0.0035 max mem: 3956 +eval (validation): [10] Total time: 0:00:26 (0.4283 s / it) +cv: [10] best hparam: (50, 1.0) (048) ('048_lr5.0e+01_wd1.0e+00') loss: 0.377 acc: 0.924 f1: 0.915 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__linear/checkpoint-best.pth +train: [11] [ 0/400] eta: 0:23:15 lr: nan time: 3.4882 data: 3.2618 max mem: 3956 +train: [11] [ 20/400] eta: 0:03:24 lr: 0.000195 loss: 1.6671 (1.6665) grad: 0.0505 (0.0498) time: 0.3901 data: 0.0029 max mem: 3956 +train: [11] [ 40/400] eta: 0:02:46 lr: 0.000193 loss: 1.6523 (1.6458) grad: 0.0505 (0.0516) time: 0.3848 data: 0.0033 max mem: 3956 +train: [11] [ 60/400] eta: 0:02:25 lr: 0.000192 loss: 1.6446 (1.6509) grad: 0.0488 (0.0509) time: 0.3522 data: 0.0033 max mem: 3956 +train: [11] [ 80/400] eta: 0:02:11 lr: 0.000190 loss: 1.6414 (1.6487) grad: 0.0488 (0.0508) time: 0.3606 data: 0.0033 max mem: 3956 +train: [11] [100/400] eta: 0:01:59 lr: 0.000189 loss: 1.6316 (1.6518) grad: 0.0502 (0.0513) time: 0.3560 data: 0.0033 max mem: 3956 +train: [11] [120/400] eta: 0:01:50 lr: 0.000187 loss: 1.6661 (1.6529) grad: 0.0540 (0.0512) time: 0.3685 data: 0.0035 max mem: 3956 +train: [11] [140/400] eta: 0:01:41 lr: 0.000186 loss: 1.6839 (1.6635) grad: 0.0531 (0.0513) time: 0.3579 data: 0.0033 max mem: 3956 +train: [11] [160/400] eta: 0:01:32 lr: 0.000184 loss: 1.6836 (1.6615) grad: 0.0485 (0.0508) time: 0.3671 data: 0.0035 max mem: 3956 +train: [11] [180/400] eta: 0:01:24 lr: 0.000183 loss: 1.6577 (1.6608) grad: 0.0480 (0.0509) time: 0.3622 data: 0.0033 max mem: 3956 +train: [11] [200/400] eta: 0:01:16 lr: 0.000181 loss: 1.6667 (1.6614) grad: 0.0515 (0.0511) time: 0.3613 data: 0.0033 max mem: 3956 +train: [11] [220/400] eta: 0:01:08 lr: 0.000180 loss: 1.6626 (1.6640) grad: 0.0486 (0.0508) time: 0.3638 data: 0.0033 max mem: 3956 +train: [11] [240/400] eta: 0:01:00 lr: 0.000178 loss: 1.6644 (1.6660) grad: 0.0486 (0.0507) time: 0.3698 data: 0.0035 max mem: 3956 +train: [11] [260/400] eta: 0:00:52 lr: 0.000177 loss: 1.6503 (1.6653) grad: 0.0493 (0.0506) time: 0.3598 data: 0.0035 max mem: 3956 +train: [11] [280/400] eta: 0:00:45 lr: 0.000175 loss: 1.6147 (1.6626) grad: 0.0465 (0.0504) time: 0.3471 data: 0.0036 max mem: 3956 +train: [11] [300/400] eta: 0:00:38 lr: 0.000174 loss: 1.6147 (1.6613) grad: 0.0465 (0.0501) time: 0.5652 data: 0.1993 max mem: 3956 +train: [11] [320/400] eta: 0:00:31 lr: 0.000172 loss: 1.6476 (1.6620) grad: 0.0469 (0.0501) time: 0.3872 data: 0.0037 max mem: 3956 +train: [11] [340/400] eta: 0:00:23 lr: 0.000170 loss: 1.6476 (1.6613) grad: 0.0479 (0.0501) time: 0.3623 data: 0.0032 max mem: 3956 +train: [11] [360/400] eta: 0:00:15 lr: 0.000169 loss: 1.6551 (1.6615) grad: 0.0514 (0.0503) time: 0.3578 data: 0.0034 max mem: 3956 +train: [11] [380/400] eta: 0:00:07 lr: 0.000167 loss: 1.6657 (1.6601) grad: 0.0514 (0.0503) time: 0.3869 data: 0.0037 max mem: 3956 +train: [11] [399/400] eta: 0:00:00 lr: 0.000166 loss: 1.6633 (1.6596) grad: 0.0472 (0.0502) time: 0.3452 data: 0.0035 max mem: 3956 +train: [11] Total time: 0:02:33 (0.3832 s / it) +train: [11] Summary: lr: 0.000166 loss: 1.6633 (1.6596) grad: 0.0472 (0.0502) +eval (validation): [11] [ 0/63] eta: 0:03:43 time: 3.5403 data: 3.2599 max mem: 3956 +eval (validation): [11] [20/63] eta: 0:00:23 time: 0.3938 data: 0.0037 max mem: 3956 +eval (validation): [11] [40/63] eta: 0:00:10 time: 0.3411 data: 0.0036 max mem: 3956 +eval (validation): [11] [60/63] eta: 0:00:01 time: 0.3297 data: 0.0031 max mem: 3956 +eval (validation): [11] [62/63] eta: 0:00:00 time: 0.3283 data: 0.0029 max mem: 3956 +eval (validation): [11] Total time: 0:00:25 (0.4091 s / it) +cv: [11] best hparam: (43, 1.0) (047) ('047_lr4.3e+01_wd1.0e+00') loss: 0.385 acc: 0.920 f1: 0.911 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__linear/checkpoint-last.pth +train: [12] [ 0/400] eta: 0:26:13 lr: nan time: 3.9344 data: 3.6976 max mem: 3956 +train: [12] [ 20/400] eta: 0:03:22 lr: 0.000164 loss: 1.5948 (1.6058) grad: 0.0538 (0.0540) time: 0.3633 data: 0.0028 max mem: 3956 +train: [12] [ 40/400] eta: 0:02:40 lr: 0.000163 loss: 1.6326 (1.6365) grad: 0.0532 (0.0504) time: 0.3542 data: 0.0029 max mem: 3956 +train: [12] [ 60/400] eta: 0:02:21 lr: 0.000161 loss: 1.6366 (1.6319) grad: 0.0501 (0.0516) time: 0.3577 data: 0.0035 max mem: 3956 +train: [12] [ 80/400] eta: 0:02:09 lr: 0.000160 loss: 1.6371 (1.6378) grad: 0.0491 (0.0505) time: 0.3624 data: 0.0034 max mem: 3956 +train: [12] [100/400] eta: 0:01:59 lr: 0.000158 loss: 1.6310 (1.6345) grad: 0.0488 (0.0507) time: 0.3838 data: 0.0033 max mem: 3956 +train: [12] [120/400] eta: 0:01:50 lr: 0.000156 loss: 1.6037 (1.6317) grad: 0.0498 (0.0504) time: 0.3735 data: 0.0035 max mem: 3956 +train: [12] [140/400] eta: 0:01:42 lr: 0.000155 loss: 1.5995 (1.6297) grad: 0.0505 (0.0509) time: 0.3789 data: 0.0034 max mem: 3956 +train: [12] [160/400] eta: 0:01:33 lr: 0.000153 loss: 1.6118 (1.6308) grad: 0.0505 (0.0508) time: 0.3712 data: 0.0034 max mem: 3956 +train: [12] [180/400] eta: 0:01:25 lr: 0.000152 loss: 1.6337 (1.6339) grad: 0.0469 (0.0505) time: 0.3705 data: 0.0038 max mem: 3956 +train: [12] [200/400] eta: 0:01:17 lr: 0.000150 loss: 1.6549 (1.6370) grad: 0.0481 (0.0505) time: 0.3748 data: 0.0035 max mem: 3956 +train: [12] [220/400] eta: 0:01:09 lr: 0.000149 loss: 1.6661 (1.6382) grad: 0.0485 (0.0504) time: 0.3561 data: 0.0034 max mem: 3956 +train: [12] [240/400] eta: 0:01:01 lr: 0.000147 loss: 1.6558 (1.6396) grad: 0.0489 (0.0503) time: 0.3693 data: 0.0033 max mem: 3956 +train: [12] [260/400] eta: 0:00:53 lr: 0.000145 loss: 1.6288 (1.6397) grad: 0.0522 (0.0507) time: 0.3656 data: 0.0033 max mem: 3956 +train: [12] [280/400] eta: 0:00:45 lr: 0.000144 loss: 1.6236 (1.6364) grad: 0.0535 (0.0506) time: 0.3393 data: 0.0035 max mem: 3956 +train: [12] [300/400] eta: 0:00:39 lr: 0.000142 loss: 1.6007 (1.6349) grad: 0.0489 (0.0505) time: 0.5523 data: 0.1932 max mem: 3956 +train: [12] [320/400] eta: 0:00:31 lr: 0.000141 loss: 1.6056 (1.6362) grad: 0.0503 (0.0505) time: 0.3622 data: 0.0033 max mem: 3956 +train: [12] [340/400] eta: 0:00:23 lr: 0.000139 loss: 1.6059 (1.6345) grad: 0.0479 (0.0502) time: 0.3688 data: 0.0032 max mem: 3956 +train: [12] [360/400] eta: 0:00:15 lr: 0.000138 loss: 1.6069 (1.6356) grad: 0.0479 (0.0504) time: 0.3540 data: 0.0034 max mem: 3956 +train: [12] [380/400] eta: 0:00:07 lr: 0.000136 loss: 1.6131 (1.6333) grad: 0.0515 (0.0505) time: 0.4086 data: 0.0034 max mem: 3956 +train: [12] [399/400] eta: 0:00:00 lr: 0.000134 loss: 1.6133 (1.6339) grad: 0.0503 (0.0503) time: 0.3738 data: 0.0035 max mem: 3956 +train: [12] Total time: 0:02:34 (0.3862 s / it) +train: [12] Summary: lr: 0.000134 loss: 1.6133 (1.6339) grad: 0.0503 (0.0503) +eval (validation): [12] [ 0/63] eta: 0:03:42 time: 3.5309 data: 3.2356 max mem: 3956 +eval (validation): [12] [20/63] eta: 0:00:23 time: 0.3854 data: 0.0291 max mem: 3956 +eval (validation): [12] [40/63] eta: 0:00:10 time: 0.3618 data: 0.0035 max mem: 3956 +eval (validation): [12] [60/63] eta: 0:00:01 time: 0.3200 data: 0.0033 max mem: 3956 +eval (validation): [12] [62/63] eta: 0:00:00 time: 0.3198 data: 0.0031 max mem: 3956 +eval (validation): [12] Total time: 0:00:25 (0.4113 s / it) +cv: [12] best hparam: (50, 1.0) (048) ('048_lr5.0e+01_wd1.0e+00') loss: 0.363 acc: 0.926 f1: 0.914 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__linear/checkpoint-best.pth +train: [13] [ 0/400] eta: 0:22:47 lr: nan time: 3.4189 data: 3.1868 max mem: 3956 +train: [13] [ 20/400] eta: 0:03:26 lr: 0.000133 loss: 1.5923 (1.6336) grad: 0.0467 (0.0472) time: 0.4007 data: 0.0026 max mem: 3956 +train: [13] [ 40/400] eta: 0:02:44 lr: 0.000131 loss: 1.5923 (1.6136) grad: 0.0456 (0.0461) time: 0.3663 data: 0.0034 max mem: 3956 +train: [13] [ 60/400] eta: 0:02:24 lr: 0.000130 loss: 1.5921 (1.6164) grad: 0.0453 (0.0467) time: 0.3613 data: 0.0034 max mem: 3956 +train: [13] [ 80/400] eta: 0:02:10 lr: 0.000128 loss: 1.6256 (1.6192) grad: 0.0488 (0.0477) time: 0.3513 data: 0.0033 max mem: 3956 +train: [13] [100/400] eta: 0:01:59 lr: 0.000127 loss: 1.6332 (1.6200) grad: 0.0481 (0.0475) time: 0.3672 data: 0.0037 max mem: 3956 +train: [13] [120/400] eta: 0:01:49 lr: 0.000125 loss: 1.6257 (1.6205) grad: 0.0481 (0.0472) time: 0.3572 data: 0.0033 max mem: 3956 +train: [13] [140/400] eta: 0:01:40 lr: 0.000124 loss: 1.5942 (1.6175) grad: 0.0489 (0.0477) time: 0.3564 data: 0.0035 max mem: 3956 +train: [13] [160/400] eta: 0:01:32 lr: 0.000122 loss: 1.5953 (1.6189) grad: 0.0484 (0.0477) time: 0.3637 data: 0.0033 max mem: 3956 +train: [13] [180/400] eta: 0:01:23 lr: 0.000120 loss: 1.5953 (1.6133) grad: 0.0481 (0.0480) time: 0.3578 data: 0.0034 max mem: 3956 +train: [13] [200/400] eta: 0:01:16 lr: 0.000119 loss: 1.5880 (1.6146) grad: 0.0502 (0.0484) time: 0.3736 data: 0.0034 max mem: 3956 +train: [13] [220/400] eta: 0:01:08 lr: 0.000117 loss: 1.6098 (1.6146) grad: 0.0502 (0.0485) time: 0.3716 data: 0.0034 max mem: 3956 +train: [13] [240/400] eta: 0:01:00 lr: 0.000116 loss: 1.5974 (1.6140) grad: 0.0476 (0.0487) time: 0.3643 data: 0.0034 max mem: 3956 +train: [13] [260/400] eta: 0:00:52 lr: 0.000114 loss: 1.6031 (1.6130) grad: 0.0474 (0.0485) time: 0.3621 data: 0.0034 max mem: 3956 +train: [13] [280/400] eta: 0:00:45 lr: 0.000113 loss: 1.5924 (1.6127) grad: 0.0429 (0.0484) time: 0.3505 data: 0.0033 max mem: 3956 +train: [13] [300/400] eta: 0:00:38 lr: 0.000111 loss: 1.5924 (1.6125) grad: 0.0435 (0.0482) time: 0.5630 data: 0.1884 max mem: 3956 +train: [13] [320/400] eta: 0:00:30 lr: 0.000110 loss: 1.6430 (1.6154) grad: 0.0465 (0.0483) time: 0.3703 data: 0.0036 max mem: 3956 +train: [13] [340/400] eta: 0:00:23 lr: 0.000108 loss: 1.6249 (1.6129) grad: 0.0459 (0.0480) time: 0.3703 data: 0.0031 max mem: 3956 +train: [13] [360/400] eta: 0:00:15 lr: 0.000107 loss: 1.6163 (1.6144) grad: 0.0444 (0.0480) time: 0.3541 data: 0.0032 max mem: 3956 +train: [13] [380/400] eta: 0:00:07 lr: 0.000105 loss: 1.6336 (1.6144) grad: 0.0460 (0.0480) time: 0.3694 data: 0.0034 max mem: 3956 +train: [13] [399/400] eta: 0:00:00 lr: 0.000104 loss: 1.5822 (1.6129) grad: 0.0466 (0.0479) time: 0.3675 data: 0.0037 max mem: 3956 +train: [13] Total time: 0:02:33 (0.3828 s / it) +train: [13] Summary: lr: 0.000104 loss: 1.5822 (1.6129) grad: 0.0466 (0.0479) +eval (validation): [13] [ 0/63] eta: 0:03:33 time: 3.3908 data: 3.1174 max mem: 3956 +eval (validation): [13] [20/63] eta: 0:00:21 time: 0.3674 data: 0.0039 max mem: 3956 +eval (validation): [13] [40/63] eta: 0:00:09 time: 0.3541 data: 0.0033 max mem: 3956 +eval (validation): [13] [60/63] eta: 0:00:01 time: 0.3370 data: 0.0033 max mem: 3956 +eval (validation): [13] [62/63] eta: 0:00:00 time: 0.3285 data: 0.0033 max mem: 3956 +eval (validation): [13] Total time: 0:00:25 (0.4047 s / it) +cv: [13] best hparam: (43, 1.0) (047) ('047_lr4.3e+01_wd1.0e+00') loss: 0.363 acc: 0.926 f1: 0.917 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__linear/checkpoint-last.pth +train: [14] [ 0/400] eta: 0:22:56 lr: nan time: 3.4408 data: 3.1544 max mem: 3956 +train: [14] [ 20/400] eta: 0:03:29 lr: 0.000102 loss: 1.5654 (1.5819) grad: 0.0521 (0.0533) time: 0.4070 data: 0.0040 max mem: 3956 +train: [14] [ 40/400] eta: 0:02:45 lr: 0.000101 loss: 1.5890 (1.5914) grad: 0.0513 (0.0506) time: 0.3637 data: 0.0031 max mem: 3956 +train: [14] [ 60/400] eta: 0:02:24 lr: 0.000099 loss: 1.5932 (1.5969) grad: 0.0474 (0.0495) time: 0.3537 data: 0.0036 max mem: 3956 +train: [14] [ 80/400] eta: 0:02:10 lr: 0.000098 loss: 1.5946 (1.6058) grad: 0.0466 (0.0491) time: 0.3596 data: 0.0035 max mem: 3956 +train: [14] [100/400] eta: 0:02:00 lr: 0.000096 loss: 1.5941 (1.6049) grad: 0.0481 (0.0490) time: 0.3794 data: 0.0035 max mem: 3956 +train: [14] [120/400] eta: 0:01:52 lr: 0.000095 loss: 1.5975 (1.6048) grad: 0.0512 (0.0493) time: 0.3903 data: 0.0037 max mem: 3956 +train: [14] [140/400] eta: 0:01:43 lr: 0.000093 loss: 1.6061 (1.6071) grad: 0.0504 (0.0493) time: 0.3743 data: 0.0034 max mem: 3956 +train: [14] [160/400] eta: 0:01:34 lr: 0.000092 loss: 1.5766 (1.6034) grad: 0.0475 (0.0492) time: 0.3593 data: 0.0037 max mem: 3956 +train: [14] [180/400] eta: 0:01:25 lr: 0.000090 loss: 1.5766 (1.6010) grad: 0.0470 (0.0490) time: 0.3699 data: 0.0036 max mem: 3956 +train: [14] [200/400] eta: 0:01:17 lr: 0.000089 loss: 1.6223 (1.6040) grad: 0.0470 (0.0490) time: 0.3710 data: 0.0035 max mem: 3956 +train: [14] [220/400] eta: 0:01:09 lr: 0.000088 loss: 1.6223 (1.6051) grad: 0.0495 (0.0494) time: 0.3909 data: 0.0034 max mem: 3956 +train: [14] [240/400] eta: 0:01:01 lr: 0.000086 loss: 1.5933 (1.6046) grad: 0.0495 (0.0493) time: 0.3728 data: 0.0035 max mem: 3956 +train: [14] [260/400] eta: 0:00:54 lr: 0.000085 loss: 1.5856 (1.6032) grad: 0.0474 (0.0490) time: 0.3723 data: 0.0034 max mem: 3956 +train: [14] [280/400] eta: 0:00:46 lr: 0.000083 loss: 1.5824 (1.6026) grad: 0.0479 (0.0491) time: 0.3511 data: 0.0035 max mem: 3956 +train: [14] [300/400] eta: 0:00:39 lr: 0.000082 loss: 1.5896 (1.6026) grad: 0.0518 (0.0492) time: 0.5736 data: 0.2072 max mem: 3956 +train: [14] [320/400] eta: 0:00:31 lr: 0.000081 loss: 1.5809 (1.6022) grad: 0.0535 (0.0494) time: 0.3986 data: 0.0044 max mem: 3956 +train: [14] [340/400] eta: 0:00:23 lr: 0.000079 loss: 1.5749 (1.6003) grad: 0.0523 (0.0495) time: 0.3570 data: 0.0023 max mem: 3956 +train: [14] [360/400] eta: 0:00:15 lr: 0.000078 loss: 1.5582 (1.5977) grad: 0.0506 (0.0497) time: 0.3583 data: 0.0032 max mem: 3956 +train: [14] [380/400] eta: 0:00:07 lr: 0.000076 loss: 1.5847 (1.5993) grad: 0.0498 (0.0497) time: 0.3731 data: 0.0035 max mem: 3956 +train: [14] [399/400] eta: 0:00:00 lr: 0.000075 loss: 1.6240 (1.6014) grad: 0.0472 (0.0496) time: 0.3848 data: 0.0037 max mem: 3956 +train: [14] Total time: 0:02:36 (0.3911 s / it) +train: [14] Summary: lr: 0.000075 loss: 1.6240 (1.6014) grad: 0.0472 (0.0496) +eval (validation): [14] [ 0/63] eta: 0:03:34 time: 3.4109 data: 3.1326 max mem: 3956 +eval (validation): [14] [20/63] eta: 0:00:21 time: 0.3493 data: 0.0036 max mem: 3956 +eval (validation): [14] [40/63] eta: 0:00:10 time: 0.3731 data: 0.0041 max mem: 3956 +eval (validation): [14] [60/63] eta: 0:00:01 time: 0.3409 data: 0.0033 max mem: 3956 +eval (validation): [14] [62/63] eta: 0:00:00 time: 0.3338 data: 0.0032 max mem: 3956 +eval (validation): [14] Total time: 0:00:25 (0.4076 s / it) +cv: [14] best hparam: (50, 1.0) (048) ('048_lr5.0e+01_wd1.0e+00') loss: 0.355 acc: 0.926 f1: 0.916 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__linear/checkpoint-last.pth +train: [15] [ 0/400] eta: 0:22:45 lr: nan time: 3.4132 data: 3.1803 max mem: 3956 +train: [15] [ 20/400] eta: 0:03:16 lr: 0.000074 loss: 1.6107 (1.6070) grad: 0.0478 (0.0495) time: 0.3716 data: 0.0050 max mem: 3956 +train: [15] [ 40/400] eta: 0:02:42 lr: 0.000072 loss: 1.5834 (1.5871) grad: 0.0503 (0.0500) time: 0.3834 data: 0.0031 max mem: 3956 +train: [15] [ 60/400] eta: 0:02:23 lr: 0.000071 loss: 1.5840 (1.5960) grad: 0.0503 (0.0497) time: 0.3618 data: 0.0033 max mem: 3956 +train: [15] [ 80/400] eta: 0:02:11 lr: 0.000070 loss: 1.5879 (1.5883) grad: 0.0470 (0.0486) time: 0.3764 data: 0.0034 max mem: 3956 +train: [15] [100/400] eta: 0:02:01 lr: 0.000068 loss: 1.5822 (1.5902) grad: 0.0477 (0.0487) time: 0.3846 data: 0.0034 max mem: 3956 +train: [15] [120/400] eta: 0:01:52 lr: 0.000067 loss: 1.5857 (1.5896) grad: 0.0476 (0.0483) time: 0.3917 data: 0.0034 max mem: 3956 +train: [15] [140/400] eta: 0:01:43 lr: 0.000066 loss: 1.5754 (1.5894) grad: 0.0466 (0.0483) time: 0.3700 data: 0.0035 max mem: 3956 +train: [15] [160/400] eta: 0:01:35 lr: 0.000064 loss: 1.5741 (1.5893) grad: 0.0469 (0.0481) time: 0.3778 data: 0.0034 max mem: 3956 +train: [15] [180/400] eta: 0:01:26 lr: 0.000063 loss: 1.5748 (1.5891) grad: 0.0467 (0.0478) time: 0.3765 data: 0.0036 max mem: 3956 +train: [15] [200/400] eta: 0:01:18 lr: 0.000062 loss: 1.5660 (1.5895) grad: 0.0457 (0.0479) time: 0.3905 data: 0.0035 max mem: 3956 +train: [15] [220/400] eta: 0:01:10 lr: 0.000061 loss: 1.5839 (1.5896) grad: 0.0465 (0.0479) time: 0.3861 data: 0.0035 max mem: 3956 +train: [15] [240/400] eta: 0:01:02 lr: 0.000059 loss: 1.5867 (1.5904) grad: 0.0471 (0.0479) time: 0.3705 data: 0.0034 max mem: 3956 +train: [15] [260/400] eta: 0:00:54 lr: 0.000058 loss: 1.5924 (1.5921) grad: 0.0489 (0.0481) time: 0.3681 data: 0.0035 max mem: 3956 +train: [15] [280/400] eta: 0:00:46 lr: 0.000057 loss: 1.5979 (1.5921) grad: 0.0489 (0.0483) time: 0.3685 data: 0.0035 max mem: 3956 +train: [15] [300/400] eta: 0:00:39 lr: 0.000056 loss: 1.5940 (1.5911) grad: 0.0488 (0.0481) time: 0.5677 data: 0.2058 max mem: 3956 +train: [15] [320/400] eta: 0:00:31 lr: 0.000054 loss: 1.5853 (1.5907) grad: 0.0428 (0.0479) time: 0.3702 data: 0.0041 max mem: 3956 +train: [15] [340/400] eta: 0:00:23 lr: 0.000053 loss: 1.5883 (1.5924) grad: 0.0424 (0.0477) time: 0.3649 data: 0.0040 max mem: 3956 +train: [15] [360/400] eta: 0:00:15 lr: 0.000052 loss: 1.5932 (1.5904) grad: 0.0430 (0.0476) time: 0.3602 data: 0.0035 max mem: 3956 +train: [15] [380/400] eta: 0:00:07 lr: 0.000051 loss: 1.5960 (1.5924) grad: 0.0483 (0.0478) time: 0.3611 data: 0.0034 max mem: 3956 +train: [15] [399/400] eta: 0:00:00 lr: 0.000050 loss: 1.5960 (1.5910) grad: 0.0483 (0.0477) time: 0.3743 data: 0.0035 max mem: 3956 +train: [15] Total time: 0:02:36 (0.3917 s / it) +train: [15] Summary: lr: 0.000050 loss: 1.5960 (1.5910) grad: 0.0483 (0.0477) +eval (validation): [15] [ 0/63] eta: 0:03:46 time: 3.5995 data: 3.3537 max mem: 3956 +eval (validation): [15] [20/63] eta: 0:00:21 time: 0.3337 data: 0.0038 max mem: 3956 +eval (validation): [15] [40/63] eta: 0:00:09 time: 0.3504 data: 0.0034 max mem: 3956 +eval (validation): [15] [60/63] eta: 0:00:01 time: 0.3419 data: 0.0036 max mem: 3956 +eval (validation): [15] [62/63] eta: 0:00:00 time: 0.3371 data: 0.0035 max mem: 3956 +eval (validation): [15] Total time: 0:00:25 (0.3983 s / it) +cv: [15] best hparam: (50, 1.0) (048) ('048_lr5.0e+01_wd1.0e+00') loss: 0.347 acc: 0.930 f1: 0.920 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__linear/checkpoint-best.pth +train: [16] [ 0/400] eta: 0:23:02 lr: nan time: 3.4555 data: 3.2237 max mem: 3956 +train: [16] [ 20/400] eta: 0:03:29 lr: 0.000048 loss: 1.5776 (1.5634) grad: 0.0444 (0.0472) time: 0.4058 data: 0.0119 max mem: 3956 +train: [16] [ 40/400] eta: 0:02:47 lr: 0.000047 loss: 1.5776 (1.5745) grad: 0.0465 (0.0467) time: 0.3754 data: 0.0028 max mem: 3956 +train: [16] [ 60/400] eta: 0:02:27 lr: 0.000046 loss: 1.5747 (1.5778) grad: 0.0484 (0.0482) time: 0.3648 data: 0.0035 max mem: 3956 +train: [16] [ 80/400] eta: 0:02:12 lr: 0.000045 loss: 1.5578 (1.5697) grad: 0.0454 (0.0467) time: 0.3549 data: 0.0033 max mem: 3956 +train: [16] [100/400] eta: 0:02:00 lr: 0.000044 loss: 1.5577 (1.5750) grad: 0.0442 (0.0473) time: 0.3604 data: 0.0034 max mem: 3956 +train: [16] [120/400] eta: 0:01:51 lr: 0.000043 loss: 1.5774 (1.5790) grad: 0.0459 (0.0472) time: 0.3854 data: 0.0036 max mem: 3956 +train: [16] [140/400] eta: 0:01:42 lr: 0.000042 loss: 1.5681 (1.5755) grad: 0.0461 (0.0472) time: 0.3661 data: 0.0034 max mem: 3956 +train: [16] [160/400] eta: 0:01:34 lr: 0.000041 loss: 1.5579 (1.5752) grad: 0.0494 (0.0475) time: 0.3715 data: 0.0035 max mem: 3956 +train: [16] [180/400] eta: 0:01:25 lr: 0.000040 loss: 1.5946 (1.5804) grad: 0.0479 (0.0474) time: 0.3657 data: 0.0033 max mem: 3956 +train: [16] [200/400] eta: 0:01:17 lr: 0.000039 loss: 1.5762 (1.5786) grad: 0.0428 (0.0471) time: 0.3826 data: 0.0034 max mem: 3956 +train: [16] [220/400] eta: 0:01:09 lr: 0.000038 loss: 1.5551 (1.5772) grad: 0.0457 (0.0476) time: 0.3659 data: 0.0034 max mem: 3956 +train: [16] [240/400] eta: 0:01:02 lr: 0.000036 loss: 1.5832 (1.5794) grad: 0.0501 (0.0477) time: 0.4121 data: 0.0036 max mem: 3956 +train: [16] [260/400] eta: 0:00:54 lr: 0.000035 loss: 1.5942 (1.5798) grad: 0.0456 (0.0475) time: 0.3969 data: 0.0034 max mem: 3956 +train: [16] [280/400] eta: 0:00:46 lr: 0.000034 loss: 1.6071 (1.5822) grad: 0.0450 (0.0475) time: 0.3598 data: 0.0033 max mem: 3956 +train: [16] [300/400] eta: 0:00:39 lr: 0.000033 loss: 1.6089 (1.5846) grad: 0.0474 (0.0476) time: 0.5396 data: 0.1931 max mem: 3956 +train: [16] [320/400] eta: 0:00:31 lr: 0.000032 loss: 1.5793 (1.5842) grad: 0.0465 (0.0474) time: 0.3681 data: 0.0034 max mem: 3956 +train: [16] [340/400] eta: 0:00:23 lr: 0.000031 loss: 1.5702 (1.5830) grad: 0.0449 (0.0475) time: 0.3700 data: 0.0032 max mem: 3956 +train: [16] [360/400] eta: 0:00:15 lr: 0.000031 loss: 1.5691 (1.5830) grad: 0.0449 (0.0473) time: 0.3597 data: 0.0033 max mem: 3956 +train: [16] [380/400] eta: 0:00:07 lr: 0.000030 loss: 1.5560 (1.5816) grad: 0.0454 (0.0473) time: 0.3746 data: 0.0033 max mem: 3956 +train: [16] [399/400] eta: 0:00:00 lr: 0.000029 loss: 1.5578 (1.5807) grad: 0.0464 (0.0473) time: 0.3810 data: 0.0035 max mem: 3956 +train: [16] Total time: 0:02:36 (0.3910 s / it) +train: [16] Summary: lr: 0.000029 loss: 1.5578 (1.5807) grad: 0.0464 (0.0473) +eval (validation): [16] [ 0/63] eta: 0:03:50 time: 3.6586 data: 3.4113 max mem: 3956 +eval (validation): [16] [20/63] eta: 0:00:21 time: 0.3487 data: 0.0127 max mem: 3956 +eval (validation): [16] [40/63] eta: 0:00:09 time: 0.3405 data: 0.0035 max mem: 3956 +eval (validation): [16] [60/63] eta: 0:00:01 time: 0.3374 data: 0.0026 max mem: 3956 +eval (validation): [16] [62/63] eta: 0:00:00 time: 0.3345 data: 0.0029 max mem: 3956 +eval (validation): [16] Total time: 0:00:25 (0.3995 s / it) +cv: [16] best hparam: (50, 1.0) (048) ('048_lr5.0e+01_wd1.0e+00') loss: 0.343 acc: 0.930 f1: 0.921 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__linear/checkpoint-best.pth +train: [17] [ 0/400] eta: 0:22:20 lr: nan time: 3.3517 data: 3.0691 max mem: 3956 +train: [17] [ 20/400] eta: 0:03:23 lr: 0.000028 loss: 1.5988 (1.5997) grad: 0.0505 (0.0531) time: 0.3950 data: 0.0034 max mem: 3956 +train: [17] [ 40/400] eta: 0:02:42 lr: 0.000027 loss: 1.5672 (1.5672) grad: 0.0493 (0.0502) time: 0.3608 data: 0.0031 max mem: 3956 +train: [17] [ 60/400] eta: 0:02:22 lr: 0.000026 loss: 1.5523 (1.5639) grad: 0.0472 (0.0497) time: 0.3552 data: 0.0035 max mem: 3956 +train: [17] [ 80/400] eta: 0:02:09 lr: 0.000025 loss: 1.5572 (1.5706) grad: 0.0487 (0.0493) time: 0.3563 data: 0.0032 max mem: 3956 +train: [17] [100/400] eta: 0:02:00 lr: 0.000024 loss: 1.5980 (1.5785) grad: 0.0488 (0.0492) time: 0.3873 data: 0.0032 max mem: 3956 +train: [17] [120/400] eta: 0:01:50 lr: 0.000023 loss: 1.5830 (1.5749) grad: 0.0483 (0.0493) time: 0.3628 data: 0.0035 max mem: 3956 +train: [17] [140/400] eta: 0:01:41 lr: 0.000023 loss: 1.5830 (1.5807) grad: 0.0481 (0.0493) time: 0.3556 data: 0.0032 max mem: 3956 +train: [17] [160/400] eta: 0:01:32 lr: 0.000022 loss: 1.6127 (1.5843) grad: 0.0511 (0.0496) time: 0.3699 data: 0.0032 max mem: 3956 +train: [17] [180/400] eta: 0:01:24 lr: 0.000021 loss: 1.6086 (1.5880) grad: 0.0484 (0.0490) time: 0.3727 data: 0.0033 max mem: 3956 +train: [17] [200/400] eta: 0:01:16 lr: 0.000020 loss: 1.5728 (1.5844) grad: 0.0450 (0.0486) time: 0.3604 data: 0.0034 max mem: 3956 +train: [17] [220/400] eta: 0:01:08 lr: 0.000019 loss: 1.5547 (1.5809) grad: 0.0473 (0.0487) time: 0.3591 data: 0.0035 max mem: 3956 +train: [17] [240/400] eta: 0:01:00 lr: 0.000019 loss: 1.5607 (1.5835) grad: 0.0512 (0.0487) time: 0.3751 data: 0.0035 max mem: 3956 +train: [17] [260/400] eta: 0:00:53 lr: 0.000018 loss: 1.6051 (1.5839) grad: 0.0498 (0.0490) time: 0.3821 data: 0.0035 max mem: 3956 +train: [17] [280/400] eta: 0:00:45 lr: 0.000017 loss: 1.5834 (1.5842) grad: 0.0474 (0.0487) time: 0.3479 data: 0.0032 max mem: 3956 +train: [17] [300/400] eta: 0:00:38 lr: 0.000016 loss: 1.5847 (1.5850) grad: 0.0422 (0.0483) time: 0.5534 data: 0.2017 max mem: 3956 +train: [17] [320/400] eta: 0:00:31 lr: 0.000016 loss: 1.5678 (1.5845) grad: 0.0449 (0.0482) time: 0.3645 data: 0.0039 max mem: 3956 +train: [17] [340/400] eta: 0:00:23 lr: 0.000015 loss: 1.5647 (1.5821) grad: 0.0460 (0.0480) time: 0.3586 data: 0.0027 max mem: 3956 +train: [17] [360/400] eta: 0:00:15 lr: 0.000014 loss: 1.5778 (1.5823) grad: 0.0452 (0.0479) time: 0.3502 data: 0.0035 max mem: 3956 +train: [17] [380/400] eta: 0:00:07 lr: 0.000014 loss: 1.5778 (1.5826) grad: 0.0453 (0.0478) time: 0.3659 data: 0.0035 max mem: 3956 +train: [17] [399/400] eta: 0:00:00 lr: 0.000013 loss: 1.5497 (1.5805) grad: 0.0455 (0.0477) time: 0.3672 data: 0.0033 max mem: 3956 +train: [17] Total time: 0:02:33 (0.3827 s / it) +train: [17] Summary: lr: 0.000013 loss: 1.5497 (1.5805) grad: 0.0455 (0.0477) +eval (validation): [17] [ 0/63] eta: 0:03:41 time: 3.5150 data: 3.2879 max mem: 3956 +eval (validation): [17] [20/63] eta: 0:00:23 time: 0.3879 data: 0.0043 max mem: 3956 +eval (validation): [17] [40/63] eta: 0:00:10 time: 0.3416 data: 0.0032 max mem: 3956 +eval (validation): [17] [60/63] eta: 0:00:01 time: 0.3392 data: 0.0033 max mem: 3956 +eval (validation): [17] [62/63] eta: 0:00:00 time: 0.3408 data: 0.0033 max mem: 3956 +eval (validation): [17] Total time: 0:00:25 (0.4103 s / it) +cv: [17] best hparam: (50, 1.0) (048) ('048_lr5.0e+01_wd1.0e+00') loss: 0.340 acc: 0.932 f1: 0.924 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__linear/checkpoint-best.pth +train: [18] [ 0/400] eta: 0:22:19 lr: nan time: 3.3483 data: 3.0924 max mem: 3956 +train: [18] [ 20/400] eta: 0:03:20 lr: 0.000012 loss: 1.5210 (1.5343) grad: 0.0464 (0.0455) time: 0.3854 data: 0.0038 max mem: 3956 +train: [18] [ 40/400] eta: 0:02:42 lr: 0.000012 loss: 1.5677 (1.5492) grad: 0.0468 (0.0464) time: 0.3741 data: 0.0030 max mem: 3956 +train: [18] [ 60/400] eta: 0:02:24 lr: 0.000011 loss: 1.5753 (1.5559) grad: 0.0455 (0.0460) time: 0.3666 data: 0.0032 max mem: 3956 +train: [18] [ 80/400] eta: 0:02:10 lr: 0.000011 loss: 1.5995 (1.5698) grad: 0.0463 (0.0470) time: 0.3527 data: 0.0034 max mem: 3956 +train: [18] [100/400] eta: 0:01:59 lr: 0.000010 loss: 1.5821 (1.5736) grad: 0.0469 (0.0473) time: 0.3638 data: 0.0034 max mem: 3956 +train: [18] [120/400] eta: 0:01:51 lr: 0.000009 loss: 1.5657 (1.5720) grad: 0.0470 (0.0477) time: 0.3892 data: 0.0038 max mem: 3956 +train: [18] [140/400] eta: 0:01:42 lr: 0.000009 loss: 1.5610 (1.5709) grad: 0.0477 (0.0479) time: 0.3780 data: 0.0034 max mem: 3956 +train: [18] [160/400] eta: 0:01:33 lr: 0.000008 loss: 1.5803 (1.5763) grad: 0.0470 (0.0477) time: 0.3739 data: 0.0033 max mem: 3956 +train: [18] [180/400] eta: 0:01:25 lr: 0.000008 loss: 1.5964 (1.5777) grad: 0.0459 (0.0479) time: 0.3789 data: 0.0034 max mem: 3956 +train: [18] [200/400] eta: 0:01:17 lr: 0.000007 loss: 1.6002 (1.5800) grad: 0.0456 (0.0476) time: 0.3714 data: 0.0039 max mem: 3956 +train: [18] [220/400] eta: 0:01:09 lr: 0.000007 loss: 1.6049 (1.5801) grad: 0.0438 (0.0478) time: 0.3852 data: 0.0030 max mem: 3956 +train: [18] [240/400] eta: 0:01:02 lr: 0.000006 loss: 1.5985 (1.5828) grad: 0.0457 (0.0476) time: 0.4050 data: 0.0036 max mem: 3956 +train: [18] [260/400] eta: 0:00:54 lr: 0.000006 loss: 1.5985 (1.5818) grad: 0.0450 (0.0476) time: 0.3942 data: 0.0035 max mem: 3956 +train: [18] [280/400] eta: 0:00:46 lr: 0.000006 loss: 1.5707 (1.5809) grad: 0.0448 (0.0475) time: 0.3578 data: 0.0039 max mem: 3956 +train: [18] [300/400] eta: 0:00:40 lr: 0.000005 loss: 1.5707 (1.5807) grad: 0.0478 (0.0476) time: 0.5794 data: 0.2080 max mem: 3956 +train: [18] [320/400] eta: 0:00:32 lr: 0.000005 loss: 1.5474 (1.5796) grad: 0.0478 (0.0476) time: 0.4044 data: 0.0034 max mem: 3956 +train: [18] [340/400] eta: 0:00:23 lr: 0.000004 loss: 1.5668 (1.5806) grad: 0.0443 (0.0475) time: 0.3793 data: 0.0034 max mem: 3956 +train: [18] [360/400] eta: 0:00:15 lr: 0.000004 loss: 1.5819 (1.5822) grad: 0.0489 (0.0477) time: 0.3543 data: 0.0034 max mem: 3956 +train: [18] [380/400] eta: 0:00:07 lr: 0.000004 loss: 1.5970 (1.5827) grad: 0.0489 (0.0477) time: 0.3706 data: 0.0033 max mem: 3956 +train: [18] [399/400] eta: 0:00:00 lr: 0.000003 loss: 1.5852 (1.5823) grad: 0.0457 (0.0477) time: 0.3774 data: 0.0034 max mem: 3956 +train: [18] Total time: 0:02:37 (0.3947 s / it) +train: [18] Summary: lr: 0.000003 loss: 1.5852 (1.5823) grad: 0.0457 (0.0477) +eval (validation): [18] [ 0/63] eta: 0:03:45 time: 3.5733 data: 3.2718 max mem: 3956 +eval (validation): [18] [20/63] eta: 0:00:21 time: 0.3575 data: 0.0046 max mem: 3956 +eval (validation): [18] [40/63] eta: 0:00:10 time: 0.3567 data: 0.0030 max mem: 3956 +eval (validation): [18] [60/63] eta: 0:00:01 time: 0.3292 data: 0.0032 max mem: 3956 +eval (validation): [18] [62/63] eta: 0:00:00 time: 0.3291 data: 0.0032 max mem: 3956 +eval (validation): [18] Total time: 0:00:25 (0.4030 s / it) +cv: [18] best hparam: (50, 1.0) (048) ('048_lr5.0e+01_wd1.0e+00') loss: 0.339 acc: 0.932 f1: 0.925 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__linear/checkpoint-best.pth +train: [19] [ 0/400] eta: 0:22:43 lr: nan time: 3.4097 data: 3.1715 max mem: 3956 +train: [19] [ 20/400] eta: 0:03:19 lr: 0.000003 loss: 1.5982 (1.6074) grad: 0.0457 (0.0477) time: 0.3814 data: 0.0033 max mem: 3956 +train: [19] [ 40/400] eta: 0:02:40 lr: 0.000003 loss: 1.5971 (1.5930) grad: 0.0492 (0.0494) time: 0.3641 data: 0.0032 max mem: 3956 +train: [19] [ 60/400] eta: 0:02:21 lr: 0.000002 loss: 1.5581 (1.5768) grad: 0.0458 (0.0484) time: 0.3564 data: 0.0036 max mem: 3956 +train: [19] [ 80/400] eta: 0:02:08 lr: 0.000002 loss: 1.5604 (1.5776) grad: 0.0451 (0.0481) time: 0.3541 data: 0.0032 max mem: 3956 +train: [19] [100/400] eta: 0:01:58 lr: 0.000002 loss: 1.5809 (1.5747) grad: 0.0493 (0.0484) time: 0.3673 data: 0.0033 max mem: 3956 +train: [19] [120/400] eta: 0:01:48 lr: 0.000002 loss: 1.5643 (1.5763) grad: 0.0493 (0.0484) time: 0.3580 data: 0.0038 max mem: 3956 +train: [19] [140/400] eta: 0:01:39 lr: 0.000001 loss: 1.5835 (1.5771) grad: 0.0478 (0.0483) time: 0.3534 data: 0.0035 max mem: 3956 +train: [19] [160/400] eta: 0:01:31 lr: 0.000001 loss: 1.5852 (1.5754) grad: 0.0460 (0.0479) time: 0.3560 data: 0.0035 max mem: 3956 +train: [19] [180/400] eta: 0:01:23 lr: 0.000001 loss: 1.5303 (1.5702) grad: 0.0450 (0.0477) time: 0.3648 data: 0.0036 max mem: 3956 +train: [19] [200/400] eta: 0:01:15 lr: 0.000001 loss: 1.5680 (1.5723) grad: 0.0459 (0.0479) time: 0.3533 data: 0.0032 max mem: 3956 +train: [19] [220/400] eta: 0:01:07 lr: 0.000001 loss: 1.5878 (1.5730) grad: 0.0482 (0.0479) time: 0.3761 data: 0.0034 max mem: 3956 +train: [19] [240/400] eta: 0:01:00 lr: 0.000001 loss: 1.5857 (1.5744) grad: 0.0459 (0.0477) time: 0.3732 data: 0.0035 max mem: 3956 +train: [19] [260/400] eta: 0:00:52 lr: 0.000000 loss: 1.5857 (1.5756) grad: 0.0433 (0.0473) time: 0.3649 data: 0.0033 max mem: 3956 +train: [19] [280/400] eta: 0:00:44 lr: 0.000000 loss: 1.5896 (1.5773) grad: 0.0415 (0.0472) time: 0.3550 data: 0.0035 max mem: 3956 +train: [19] [300/400] eta: 0:00:38 lr: 0.000000 loss: 1.5896 (1.5789) grad: 0.0464 (0.0472) time: 0.5553 data: 0.2111 max mem: 3956 +train: [19] [320/400] eta: 0:00:30 lr: 0.000000 loss: 1.5978 (1.5797) grad: 0.0467 (0.0473) time: 0.4040 data: 0.0039 max mem: 3956 +train: [19] [340/400] eta: 0:00:23 lr: 0.000000 loss: 1.5669 (1.5774) grad: 0.0450 (0.0471) time: 0.3665 data: 0.0034 max mem: 3956 +train: [19] [360/400] eta: 0:00:15 lr: 0.000000 loss: 1.5320 (1.5768) grad: 0.0453 (0.0472) time: 0.3529 data: 0.0035 max mem: 3956 +train: [19] [380/400] eta: 0:00:07 lr: 0.000000 loss: 1.5473 (1.5772) grad: 0.0474 (0.0471) time: 0.3590 data: 0.0035 max mem: 3956 +train: [19] [399/400] eta: 0:00:00 lr: 0.000000 loss: 1.5519 (1.5741) grad: 0.0506 (0.0474) time: 0.3603 data: 0.0035 max mem: 3956 +train: [19] Total time: 0:02:32 (0.3817 s / it) +train: [19] Summary: lr: 0.000000 loss: 1.5519 (1.5741) grad: 0.0506 (0.0474) +eval (validation): [19] [ 0/63] eta: 0:03:43 time: 3.5531 data: 3.2582 max mem: 3956 +eval (validation): [19] [20/63] eta: 0:00:21 time: 0.3532 data: 0.0040 max mem: 3956 +eval (validation): [19] [40/63] eta: 0:00:10 time: 0.3631 data: 0.0032 max mem: 3956 +eval (validation): [19] [60/63] eta: 0:00:01 time: 0.3259 data: 0.0032 max mem: 3956 +eval (validation): [19] [62/63] eta: 0:00:00 time: 0.3234 data: 0.0031 max mem: 3956 +eval (validation): [19] Total time: 0:00:25 (0.4027 s / it) +cv: [19] best hparam: (50, 1.0) (048) ('048_lr5.0e+01_wd1.0e+00') loss: 0.339 acc: 0.932 f1: 0.924 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__linear/checkpoint-last.pth +evaluating last checkpoint: experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__linear/checkpoint-last.pth +eval model info: +{"score": 0.9317956349206349, "hparam": [50, 1.0], "hparam_id": 48, "epoch": 19, "is_best": false, "best_score": 0.9320436507936508} +eval (train): [20] [ 0/297] eta: 0:16:47 time: 3.3919 data: 3.1609 max mem: 3956 +eval (train): [20] [ 20/297] eta: 0:02:20 time: 0.3643 data: 0.0132 max mem: 3956 +eval (train): [20] [ 40/297] eta: 0:01:50 time: 0.3509 data: 0.0035 max mem: 3956 +eval (train): [20] [ 60/297] eta: 0:01:34 time: 0.3377 data: 0.0030 max mem: 3956 +eval (train): [20] [ 80/297] eta: 0:01:23 time: 0.3417 data: 0.0034 max mem: 3956 +eval (train): [20] [100/297] eta: 0:01:15 time: 0.3691 data: 0.0036 max mem: 3956 +eval (train): [20] [120/297] eta: 0:01:07 time: 0.3775 data: 0.0039 max mem: 3956 +eval (train): [20] [140/297] eta: 0:00:59 time: 0.3585 data: 0.0034 max mem: 3956 +eval (train): [20] [160/297] eta: 0:00:51 time: 0.3526 data: 0.0035 max mem: 3956 +eval (train): [20] [180/297] eta: 0:00:43 time: 0.3536 data: 0.0034 max mem: 3956 +eval (train): [20] [200/297] eta: 0:00:35 time: 0.3495 data: 0.0034 max mem: 3956 +eval (train): [20] [220/297] eta: 0:00:28 time: 0.3538 data: 0.0035 max mem: 3956 +eval (train): [20] [240/297] eta: 0:00:20 time: 0.3522 data: 0.0036 max mem: 3956 +eval (train): [20] [260/297] eta: 0:00:13 time: 0.3503 data: 0.0035 max mem: 3956 +eval (train): [20] [280/297] eta: 0:00:06 time: 0.3524 data: 0.0033 max mem: 3956 +eval (train): [20] [296/297] eta: 0:00:00 time: 0.3295 data: 0.0032 max mem: 3956 +eval (train): [20] Total time: 0:01:48 (0.3655 s / it) +eval (validation): [20] [ 0/63] eta: 0:03:39 time: 3.4893 data: 3.2487 max mem: 3956 +eval (validation): [20] [20/63] eta: 0:00:22 time: 0.3805 data: 0.0279 max mem: 3956 +eval (validation): [20] [40/63] eta: 0:00:10 time: 0.3716 data: 0.0033 max mem: 3956 +eval (validation): [20] [60/63] eta: 0:00:01 time: 0.3274 data: 0.0026 max mem: 3956 +eval (validation): [20] [62/63] eta: 0:00:00 time: 0.3279 data: 0.0029 max mem: 3956 +eval (validation): [20] Total time: 0:00:26 (0.4129 s / it) +eval (test): [20] [ 0/79] eta: 0:04:36 time: 3.4943 data: 3.1974 max mem: 3956 +eval (test): [20] [20/79] eta: 0:00:31 time: 0.3945 data: 0.0175 max mem: 3956 +eval (test): [20] [40/79] eta: 0:00:17 time: 0.3508 data: 0.0031 max mem: 3956 +eval (test): [20] [60/79] eta: 0:00:07 time: 0.3440 data: 0.0037 max mem: 3956 +eval (test): [20] [78/79] eta: 0:00:00 time: 0.3385 data: 0.0033 max mem: 3956 +eval (test): [20] Total time: 0:00:31 (0.4028 s / it) +evaluating best checkpoint: experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__linear/checkpoint-best.pth +eval model info: +{"score": 0.9320436507936508, "hparam": [50, 1.0], "hparam_id": 48, "epoch": 18, "is_best": true, "best_score": 0.9320436507936508} +eval (train): [20] [ 0/297] eta: 0:17:54 time: 3.6173 data: 3.3291 max mem: 3956 +eval (train): [20] [ 20/297] eta: 0:02:21 time: 0.3541 data: 0.0046 max mem: 3956 +eval (train): [20] [ 40/297] eta: 0:01:50 time: 0.3489 data: 0.0034 max mem: 3956 +eval (train): [20] [ 60/297] eta: 0:01:34 time: 0.3339 data: 0.0033 max mem: 3956 +eval (train): [20] [ 80/297] eta: 0:01:24 time: 0.3610 data: 0.0034 max mem: 3956 +eval (train): [20] [100/297] eta: 0:01:14 time: 0.3259 data: 0.0035 max mem: 3956 +eval (train): [20] [120/297] eta: 0:01:05 time: 0.3425 data: 0.0035 max mem: 3956 +eval (train): [20] [140/297] eta: 0:00:57 time: 0.3381 data: 0.0035 max mem: 3956 +eval (train): [20] [160/297] eta: 0:00:50 time: 0.3569 data: 0.0035 max mem: 3956 +eval (train): [20] [180/297] eta: 0:00:42 time: 0.3574 data: 0.0038 max mem: 3956 +eval (train): [20] [200/297] eta: 0:00:35 time: 0.3361 data: 0.0034 max mem: 3956 +eval (train): [20] [220/297] eta: 0:00:27 time: 0.3627 data: 0.0037 max mem: 3956 +eval (train): [20] [240/297] eta: 0:00:20 time: 0.3430 data: 0.0035 max mem: 3956 +eval (train): [20] [260/297] eta: 0:00:13 time: 0.3573 data: 0.0036 max mem: 3956 +eval (train): [20] [280/297] eta: 0:00:06 time: 0.3440 data: 0.0036 max mem: 3956 +eval (train): [20] [296/297] eta: 0:00:00 time: 0.3297 data: 0.0033 max mem: 3956 +eval (train): [20] Total time: 0:01:46 (0.3598 s / it) +eval (validation): [20] [ 0/63] eta: 0:03:53 time: 3.7013 data: 3.4093 max mem: 3956 +eval (validation): [20] [20/63] eta: 0:00:21 time: 0.3465 data: 0.0104 max mem: 3956 +eval (validation): [20] [40/63] eta: 0:00:09 time: 0.3350 data: 0.0036 max mem: 3956 +eval (validation): [20] [60/63] eta: 0:00:01 time: 0.3230 data: 0.0035 max mem: 3956 +eval (validation): [20] [62/63] eta: 0:00:00 time: 0.3129 data: 0.0028 max mem: 3956 +eval (validation): [20] Total time: 0:00:24 (0.3925 s / it) +eval (test): [20] [ 0/79] eta: 0:04:51 time: 3.6948 data: 3.4539 max mem: 3956 +eval (test): [20] [20/79] eta: 0:00:30 time: 0.3615 data: 0.0033 max mem: 3956 +eval (test): [20] [40/79] eta: 0:00:16 time: 0.3327 data: 0.0030 max mem: 3956 +eval (test): [20] [60/79] eta: 0:00:07 time: 0.3567 data: 0.0036 max mem: 3956 +eval (test): [20] [78/79] eta: 0:00:00 time: 0.3240 data: 0.0032 max mem: 3956 +eval (test): [20] Total time: 0:00:30 (0.3914 s / it) +eval results: + +| model | repr | clf | dataset | ckpt | epoch | lr | wd | hparam_id | hparam | split | loss | acc | acc_std | f1 | f1_std | +|:---------|:-------|:-------|:-------------|:-------|--------:|------:|-----:|------------:|:----------|:-----------|--------:|--------:|----------:|--------:|----------:| +| flat_mae | patch | linear | hcpya_task21 | best | 18 | 0.015 | 0.05 | 48 | [50, 1.0] | train | 0.30549 | 0.94579 | 0.0015117 | 0.94245 | 0.0018296 | +| flat_mae | patch | linear | hcpya_task21 | best | 18 | 0.015 | 0.05 | 48 | [50, 1.0] | validation | 0.33905 | 0.93204 | 0.0038816 | 0.92518 | 0.0047207 | +| flat_mae | patch | linear | hcpya_task21 | best | 18 | 0.015 | 0.05 | 48 | [50, 1.0] | test | 0.34095 | 0.93274 | 0.0032783 | 0.92501 | 0.0040806 | + + +done! total time: 1:07:00 diff --git a/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__linear/train_log.json b/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__linear/train_log.json new file mode 100644 index 0000000000000000000000000000000000000000..c7fc1427eeb191d80c4b6412c8fd04e7284c4d19 --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/hcpya_task21__patch__linear/train_log.json @@ -0,0 +1,20 @@ +{"epoch": 0, "train/lr": 2.987987987987988e-05, "train/loss": 2.9365020859241486, "train/grad": 0.10487890530377626, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.04253662109375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.042330322265625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.042001953125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.041666259765625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.0413818359375, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.0409423828125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.040452880859375, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.039830322265625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.039041748046875, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.038167724609375, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.03738525390625, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.036102294921875, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.0348486328125, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.032987060546875, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.0311279296875, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.029395751953125, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.026983642578125, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.0240576171875, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.020689697265625, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.017281494140625, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.013082275390625, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.008541259765625, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.0031201171875, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.99698486328125, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.990341796875, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.98212646484375, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.974547119140625, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.967572021484375, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.957911376953125, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.9466796875, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.9369183349609376, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.9282879638671875, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.916917724609375, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.9072308349609375, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.8958856201171876, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.8846728515625, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.872457275390625, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.86043701171875, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.8465386962890626, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.8280377197265625, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.812294921875, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.7973663330078127, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.775936279296875, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.7557464599609376, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.7299835205078127, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.6995144653320313, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.6706668090820314, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.632615966796875, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.5969781494140625, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.017334518092684447, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.017329508517868818, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.017321042604744433, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.017313055670820178, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.01730410891585052, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.017292243796400725, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.017278259969316423, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.01726229857187718, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.017240255246870218, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.017217176649719477, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.017195341400802134, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.01716053101234138, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.017126927743665876, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.017077936455607415, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.017030311743728817, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.01698309857863933, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.016919784974306823, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.01683938957285136, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.016746679842472075, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.01665440257638693, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.01653243387117982, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.01639952912926674, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.016238135225139557, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.016055412210989745, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.01584983479231596, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.015585714881308377, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.01533131524687633, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.015090692930389196, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.014751064598094672, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.01433562338585034, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.013969222486484795, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.013647892656736075, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.013242758396081626, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.012912192684598266, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.01255929453065619, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.012245650188997387, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.01194552460219711, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.011689565107226373, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.011437959223985671, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.011158968096133322, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.010967539860866965, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.010816086423583329, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.010642493155319243, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.01051027695182711, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.010377517589367925, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.010251296502538025, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.010158063846174627, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.010062596099451183, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.009997500760946423, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.040713310241699, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.040090322494507, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.039094924926758, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.038130521774292, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.037177085876465, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.0358028411865234, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.034287691116333, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.032518148422241, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.030226945877075, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.0277631282806396, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.0253746509552, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.0216870307922363, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.018038272857666, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.0126662254333496, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.0074846744537354, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.00235915184021, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.9957542419433594, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.987778425216675, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.978580951690674, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.9697840213775635, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.958686113357544, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.9469923973083496, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.9337353706359863, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.919435501098633, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.9045255184173584, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.887068033218384, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.871993064880371, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.858877420425415, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.8423500061035156, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.8248250484466553, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.8109936714172363, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.799669027328491, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.785338878631592, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.772672176361084, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.7566373348236084, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.7392780780792236, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.718363046646118, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.6959502696990967, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.668304443359375, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.6284677982330322, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.593045234680176, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.5585174560546875, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.5085196495056152, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.4605824947357178, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.400369882583618, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.330631732940674, "validation/loss_046_lr3.6e+01_wd1.0e+00": 2.2661616802215576, "validation/loss_047_lr4.3e+01_wd1.0e+00": 2.182053327560425, "validation/loss_048_lr5.0e+01_wd1.0e+00": 2.1026225090026855, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.030257936507936508, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.031001984126984128, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.031746031746031744, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.03521825396825397, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.03695436507936508, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.03993055555555555, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.04141865079365079, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.04563492063492063, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.050347222222222224, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.05357142857142857, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.05654761904761905, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.05853174603174603, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06001984126984127, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.061507936507936505, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06522817460317461, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.07614087301587301, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.11631944444444445, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.1691468253968254, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.20114087301587302, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.18973214285714285, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.1746031746031746, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.1708829365079365, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.17063492063492064, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.17063492063492064, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.17063492063492064, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.17063492063492064, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.17063492063492064, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.17063492063492064, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.17063492063492064, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.17063492063492064, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.17063492063492064, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.17063492063492064, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.17063492063492064, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.17063492063492064, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.17063492063492064, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.17063492063492064, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.17063492063492064, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.17435515873015872, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.18824404761904762, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.21155753968253968, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.23462301587301587, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.25570436507936506, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.2728174603174603, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.296875, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.3308531746031746, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.3715277777777778, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.4072420634920635, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.014090249590239978, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.014341291866977754, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.013942784600229671, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.014431088644973349, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.014278453313197235, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.013942960468171318, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.012703562105952677, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.011542324126676742, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.011030358685878957, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.010336103389838645, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.009891110261893517, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.009651077296424464, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.008648253799924836, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.009305781193491371, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.011330930242853436, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.01669987588665482, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.030618055711123273, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.03638838752190478, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.03374793208093238, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.028412315928562266, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.019362840916605856, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.014256826530400299, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.013882163034705408, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.013882163034705408, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.013882163034705408, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.013882163034705408, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.013882163034705408, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.013882163034705408, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.013882163034705408, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.013882163034705408, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.013882163034705408, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.013882163034705408, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.013882163034705408, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.013882163034705408, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.013882163034705408, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.013882163034705408, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.013882163034705408, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.018413581340630612, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.03414666980004444, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.053592200517143355, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.0657913454827502, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.07267677509958845, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.08124368149512357, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.10274119146872873, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.13123520315094225, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.16717390195215429, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.20170340971722356, "id_best": 48, "lr_best": 0.015, "wd_best": 0.05, "train/loss_best": 2.5969781494140625, "validation/loss_best": 2.1026225090026855, "validation/acc_best": 0.4072420634920635, "validation/f1_best": 0.20170340971722356} +{"epoch": 1, "train/lr": 8.993993993993998e-05, "train/loss": 2.6937504529953005, "train/grad": 0.08742681408300995, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.035257568359375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.03393310546875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.0317724609375, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.02950927734375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.0275439453125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.024559326171875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.021280517578125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.0175830078125, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.012860107421875, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.007860107421875, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.00293212890625, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.9956396484375, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.988677978515625, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.97873291015625, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.9693798828125, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.9604931640625, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.949371337890625, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.93672119140625, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.9229833984375, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.91060302734375, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.8959716796875, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.881700439453125, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.8669024658203126, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.851968994140625, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.8375836181640626, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.8215399169921875, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.807989501953125, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.795833740234375, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.779483642578125, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.759556884765625, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.740908203125, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.723031005859375, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.6967095947265625, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.6710455322265627, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.637652587890625, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.6009085083007815, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.5574688720703125, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.511622009277344, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.45678955078125, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.3808169555664063, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.31632080078125, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.255777587890625, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.1717700958251953, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.0949323272705076, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.0024135589599608, "train/loss_045_lr3.1e+01_wd1.0e+00": 1.899987850189209, "train/loss_046_lr3.6e+01_wd1.0e+00": 1.8100160598754882, "train/loss_047_lr4.3e+01_wd1.0e+00": 1.7011436939239502, "train/loss_048_lr5.0e+01_wd1.0e+00": 1.6082351875305176, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.01716301980894059, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.017125507392920555, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.01706460535991937, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.01700509157963097, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.016948999455198645, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.016869669668376445, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.01678245186805725, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.01668560822494328, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.016554734050296248, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.0164144878461957, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.016278438279405238, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.01606881813611835, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.015865052561275662, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.015564745804294945, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.015274724643677472, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.014993446776643396, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.014632462370209397, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.014200115124695004, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.013710269355215132, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.013250334919430316, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.012684206070844084, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.012111696971114725, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.011508951948489993, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.010922126886434853, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.010393683149013669, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.009881311797071248, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.009527966938912868, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.009278713727835565, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.009037624555639922, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.008865619504358619, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.008785234892275184, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.008750068459194153, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.008731057257391513, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.008724703267216683, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.008718326035887004, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.00870981243206188, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.00869810743490234, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.008684707465581596, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.00866550070932135, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.008635464832186699, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.008605668449308723, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.00857572881039232, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.00853159250691533, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.00848836540710181, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.008424744445364922, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0083376757777296, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.008246958537492901, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.008136022605467587, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.008051202201750129, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.0291907787323, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.0269477367401123, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.023266553878784, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.0196142196655273, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.0160274505615234, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.0111262798309326, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.0056440830230713, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.9996752738952637, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.9919588565826416, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.983858585357666, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.9761059284210205, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.9648044109344482, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.9541728496551514, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.9393904209136963, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.9258666038513184, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.913518190383911, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.898710250854492, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.882383346557617, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.8655619621276855, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.8513362407684326, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.83550763130188, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.820984363555908, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.8066210746765137, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.7926743030548096, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.7788214683532715, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.7620668411254883, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.7461400032043457, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.7304887771606445, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.7074482440948486, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.677241563796997, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.6476263999938965, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.61857533454895, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.5761468410491943, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.5350544452667236, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.482147455215454, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.4252240657806396, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.35902738571167, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.290835380554199, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.2109222412109375, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.1042730808258057, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.0172338485717773, "validation/loss_041_lr1.6e+01_wd1.0e+00": 1.9382494688034058, "validation/loss_042_lr1.9e+01_wd1.0e+00": 1.8330835103988647, "validation/loss_043_lr2.2e+01_wd1.0e+00": 1.7410175800323486, "validation/loss_044_lr2.6e+01_wd1.0e+00": 1.6349602937698364, "validation/loss_045_lr3.1e+01_wd1.0e+00": 1.5234957933425903, "validation/loss_046_lr3.6e+01_wd1.0e+00": 1.4301856756210327, "validation/loss_047_lr4.3e+01_wd1.0e+00": 1.3233696222305298, "validation/loss_048_lr5.0e+01_wd1.0e+00": 1.2370288372039795, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.052083333333333336, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.05530753968253968, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.05803571428571429, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.058779761904761904, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06001984126984127, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.061507936507936505, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06919642857142858, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.08903769841269842, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.14087301587301587, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.18874007936507936, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.19915674603174602, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.18129960317460317, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.17237103174603174, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.17063492063492064, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.17063492063492064, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.17063492063492064, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.17063492063492064, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.17063492063492064, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.17063492063492064, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.17063492063492064, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.17063492063492064, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.17311507936507936, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.17881944444444445, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.20287698412698413, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.23065476190476192, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.2725694444444444, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.31398809523809523, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.3601190476190476, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.42063492063492064, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.46552579365079366, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.49950396825396826, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.5503472222222222, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.5813492063492064, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.6237599206349206, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.6622023809523809, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.6867559523809523, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.7175099206349206, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.7356150793650794, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.010631939498590218, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.01034818467195821, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.0098109468217115, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.008378373064001758, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.008577072478959377, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.009136992651534614, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.013196076494282928, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.021933334814594568, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.03467032347792192, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.0354467914037151, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.031309946730847624, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.023674524195236992, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.016627864676526, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.013888047800722664, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.013882163034705408, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.013882163034705408, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.013882163034705408, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.013882163034705408, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.013882163034705408, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.013882163034705408, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.013882163034705408, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.013882163034705408, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.01701495692069842, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.023996304244654282, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.04785379970794742, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.07462031099510477, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.10678763997665017, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.1406840540723363, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.1848666600629533, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.24246016296808234, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.29436391124754757, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.3307077141616359, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.3837865520594855, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.4304275219572817, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.5014480449996763, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.560764130127544, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.6020205855844352, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.6420233948428725, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.661238737153964, "id_best": 48, "lr_best": 0.015, "wd_best": 0.05, "train/loss_best": 1.6082351875305176, "validation/loss_best": 1.2370288372039795, "validation/acc_best": 0.7356150793650794, "validation/f1_best": 0.661238737153964} +{"epoch": 2, "train/lr": 0.00014999999999999988, "train/loss": 2.4612569534778594, "train/grad": 0.07876329744234681, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.021605224609375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.018375244140625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.01288330078125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.007598876953125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.002445068359375, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.995498046875, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.98784912109375, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.97963623046875, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.969168701171875, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.95859375, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.948731689453125, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.93468505859375, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.921907958984375, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.90505859375, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.89021728515625, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.877359619140625, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.862645263671875, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.8471429443359373, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.8320550537109375, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.8194024658203123, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.8050994873046875, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.7909918212890625, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.775640869140625, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.75853515625, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.7395611572265626, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.7148876953125, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.690789794921875, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.667008056640625, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.632120361328125, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.5869232177734376, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.543177490234375, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.5008999633789064, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.4399710083007813, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.3819931030273436, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.309012756347656, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.2324453735351564, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.1462403869628908, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.060497589111328, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.9638638305664062, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.840087547302246, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.7427503967285156, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.6571762466430664, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.546948356628418, "train/loss_043_lr2.2e+01_wd1.0e+00": 1.4542273044586183, "train/loss_044_lr2.6e+01_wd1.0e+00": 1.3511941862106323, "train/loss_045_lr3.1e+01_wd1.0e+00": 1.246946964263916, "train/loss_046_lr3.6e+01_wd1.0e+00": 1.1630240488052368, "train/loss_047_lr4.3e+01_wd1.0e+00": 1.069877370595932, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.9968421173095703, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.016773271691054106, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.0166882984014228, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.016545376679860054, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.016399886403232814, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.01625337059609592, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.016054909969680013, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.015830704835243525, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.01558378073386848, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.015268735978752375, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.014939422132447361, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.014621435557492077, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.014153603413142264, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.013710165151860566, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.01308655702508986, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.012520264866761863, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.012004454152192921, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.011397176650352775, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.010767834114376455, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.010184823097661137, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.009758170912973582, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.00937647576443851, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.009118684702552855, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.008949152491986752, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.008854935113340616, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.008808776761870831, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.008781616890337319, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.008765793894417584, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.00875278610503301, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.008732506423257291, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.008707285572309048, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.008682517388369887, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.00865777857368812, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.008619686558376997, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.008583444547839462, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.008535567026119678, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.008485032829921692, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.008428758338559418, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.008375423746183514, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.008318890903610736, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.008235907123889774, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.008148796430323273, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.008056515341158955, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.007931661594193428, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.007835117515642196, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.007741178262513131, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.007645105582196265, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.007551321752835065, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.007403040931094438, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.007282869727350772, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.011256456375122, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.006638288497925, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.999176025390625, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.9919540882110596, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.9850120544433594, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.9756147861480713, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.965568780899048, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.9548075199127197, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.941504716873169, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.9282591342926025, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.9161317348480225, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.8994028568267822, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.88470721244812, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.8658382892608643, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.8501017093658447, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.8369011878967285, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.822279214859009, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.8074090480804443, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.792782783508301, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.7800683975219727, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.764709234237671, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.7482848167419434, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.72890567779541, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.706360101699829, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.680786371231079, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.6473195552825928, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.614576816558838, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.5825226306915283, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.535710573196411, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.4757163524627686, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.418498992919922, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.3640332221984863, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.286966562271118, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.2152504920959473, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.1273586750030518, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.0377166271209717, "validation/loss_036_lr7.1e+00_wd1.0e+00": 1.9396556615829468, "validation/loss_037_lr8.3e+00_wd1.0e+00": 1.845023512840271, "validation/loss_038_lr9.8e+00_wd1.0e+00": 1.7414778470993042, "validation/loss_039_lr1.2e+01_wd1.0e+00": 1.6123305559158325, "validation/loss_040_lr1.4e+01_wd1.0e+00": 1.5131109952926636, "validation/loss_041_lr1.6e+01_wd1.0e+00": 1.4286353588104248, "validation/loss_042_lr1.9e+01_wd1.0e+00": 1.3233574628829956, "validation/loss_043_lr2.2e+01_wd1.0e+00": 1.2369765043258667, "validation/loss_044_lr2.6e+01_wd1.0e+00": 1.142378807067871, "validation/loss_045_lr3.1e+01_wd1.0e+00": 1.0489859580993652, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.97507244348526, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.8932514786720276, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.834950864315033, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.061755952380952384, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06721230158730158, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.0900297619047619, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.14087301587301587, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.1827876984126984, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.19915674603174602, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.18204365079365079, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.17261904761904762, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.17063492063492064, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.17063492063492064, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.17162698412698413, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.17609126984126985, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.19072420634920634, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.21552579365079366, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.2400793650793651, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.2648809523809524, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.2976190476190476, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.33581349206349204, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.3821924603174603, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.42956349206349204, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.4851190476190476, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.53125, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.5766369047619048, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.6334325396825397, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.673859126984127, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.7006448412698413, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.7291666666666666, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.7517361111111112, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.7688492063492064, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.7874503968253969, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.8013392857142857, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.8194444444444444, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.8315972222222222, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.009278057455222286, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.012088197672113166, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.022265168076616985, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.034610038323590935, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.03559187901714202, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.03130646565569818, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.023842084138176685, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.016934522547302988, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.013890992055079397, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.013882163034705408, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.013882163034705408, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.015058155570537074, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.02078404404483789, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.03690172797203914, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.05727908817663764, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.07831619193004606, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.09667611665690093, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.12028260474559276, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.15534592016140558, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.19951269532509555, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.2488230763335702, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.3166619835214187, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.3776794008959225, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.4420584007801834, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.5344300781028003, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.597914941895102, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.6388795220305297, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.6741254145580451, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.7016078494100852, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.7179288311449431, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.7371427812393636, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.7499053422511566, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.7699659673132553, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.785244567135612, "id_best": 48, "lr_best": 0.015, "wd_best": 0.05, "train/loss_best": 0.9968421173095703, "validation/loss_best": 0.834950864315033, "validation/acc_best": 0.8315972222222222, "validation/f1_best": 0.785244567135612} +{"epoch": 3, "train/lr": 0.0002100600600600602, "train/loss": 2.271589922904968, "train/grad": 0.07136647025123238, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.001273193359375, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.99552490234375, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.9862255859375, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.9773779296875, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.968922119140625, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.95782958984375, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.946036376953125, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.93390380859375, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.919073486328125, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.904683837890625, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.892164306640625, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.875189208984375, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.860963134765625, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.84335693359375, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.82907958984375, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.81713623046875, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.8034930419921875, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.7887713623046877, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.7726531982421876, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.7574578857421876, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.73783935546875, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.7162310791015627, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.6903070068359374, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.6601324462890625, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.62614501953125, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.582020263671875, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.5391171264648436, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.4976708984375, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.437808837890625, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.3622250366210937, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.2914028930664063, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.2248390197753904, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.132282409667969, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.0479083251953125, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.9463033294677734, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.8452462768554687, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.7373074913024902, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.6359315299987793, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.5280290126800538, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.3988066291809083, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.3034221029281616, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.223576889038086, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.1255201959609986, "train/loss_043_lr2.2e+01_wd1.0e+00": 1.0470557153224944, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.9641647243499756, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.8849156862497329, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.8240132606029511, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.7585423365235329, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.7080276930332183, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.01616770001128316, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.015998358097858725, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.01572544053196907, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.015462985844351351, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.015211851713247597, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.01486303189303726, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.01448468742892146, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.014077862803824247, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.013565308377146722, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.013044273839332163, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.012561326860450209, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.011889867421705275, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.011304363808594644, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.010583715748507529, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.010037486678920687, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.009642546293325721, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.009293797737918795, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.009045834068674595, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.00889932133955881, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.008831482036039234, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.008788307893555612, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.00876282477285713, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.008740770041476935, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.008718383267987519, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.008692672764882446, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.008659553481265903, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.008625199683010579, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.008591943143401296, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.008540030149742962, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.008472079285420478, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.008404707428999245, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.008337313504889608, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.008239205738063901, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.008142545316368342, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.00801676218630746, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.007884443919174373, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.00773752523586154, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.007595862213056534, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.007437402175273746, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0072384759783744815, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.007083605884108692, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.006945408750325442, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.006759048365056515, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0066007302945945414, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0064369452465325595, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.006305268759606406, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.006235198830254376, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.006162404463393614, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.006067461281782016, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.9884204864501953, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.9812023639678955, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.9696497917175293, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.958829641342163, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.948625087738037, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.935401678085327, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.921538829803467, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.907480239868164, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.8908493518829346, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.8752834796905518, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.8617255687713623, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.844188690185547, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.8298134803771973, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.8124730587005615, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.7984397411346436, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.786412239074707, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.7721097469329834, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.7555205821990967, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.7364628314971924, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.7178051471710205, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.6933887004852295, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.666335105895996, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.6339521408081055, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.596548557281494, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.55452299118042, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.500459909439087, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.4485361576080322, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.3986480236053467, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.327491521835327, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.239010810852051, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.1573452949523926, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.081876039505005, "validation/loss_032_lr3.7e+00_wd1.0e+00": 1.9794508218765259, "validation/loss_033_lr4.3e+00_wd1.0e+00": 1.8883612155914307, "validation/loss_034_lr5.1e+00_wd1.0e+00": 1.7822109460830688, "validation/loss_035_lr6.0e+00_wd1.0e+00": 1.679479956626892, "validation/loss_036_lr7.1e+00_wd1.0e+00": 1.5721834897994995, "validation/loss_037_lr8.3e+00_wd1.0e+00": 1.472405195236206, "validation/loss_038_lr9.8e+00_wd1.0e+00": 1.3668811321258545, "validation/loss_039_lr1.2e+01_wd1.0e+00": 1.2405210733413696, "validation/loss_040_lr1.4e+01_wd1.0e+00": 1.149246335029602, "validation/loss_041_lr1.6e+01_wd1.0e+00": 1.074845790863037, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.9868243336677551, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.918922483921051, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.8485140204429626, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.7808610200881958, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.7290709018707275, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.6764585971832275, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.6383401155471802, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.16046626984126985, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.19444444444444445, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.18948412698412698, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.1753472222222222, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.17113095238095238, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.17137896825396826, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.17410714285714285, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.18427579365079366, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.21254960317460317, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.24404761904761904, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.27455357142857145, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.31200396825396826, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.3501984126984127, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.38293650793650796, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.41393849206349204, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.45436507936507936, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.49181547619047616, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.5257936507936508, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.5639880952380952, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.6041666666666666, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.6453373015873016, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.6912202380952381, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.7395833333333334, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.7693452380952381, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.7859623015873016, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.8043154761904762, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.8204365079365079, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.8355654761904762, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.8499503968253969, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.859375, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.8658234126984127, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.8715277777777778, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.035316098515549205, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.034123920890827816, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.026609585918511057, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.019702024143255864, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.014614060404505318, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.014695821028922454, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.017869661405610495, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.028929806421029797, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.054300452993524054, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.0826229994717488, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.1040258181474405, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.12951717590977693, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.15676273825103712, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.18612233708385992, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.22618722286070164, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.2835845246709647, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.33337763748830723, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.376859529835558, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.43800244808701894, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.5002865182266937, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.5712298466106911, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.6388685200727474, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.7031357843719358, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.7366268993821125, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.7565288935771962, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.77323252933351, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.7913613177497509, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.8077124052389875, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.8226260217798469, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.8342355075078348, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.844430882910164, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.8519149009129656, "id_best": 48, "lr_best": 0.015, "wd_best": 0.05, "train/loss_best": 0.7080276930332183, "validation/loss_best": 0.6383401155471802, "validation/acc_best": 0.8715277777777778, "validation/f1_best": 0.8519149009129656} +{"epoch": 4, "train/lr": 0.0002701201201201201, "train/loss": 2.1131314450502394, "train/grad": 0.06488859362900257, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.975697021484375, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.967276611328125, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.953974609375, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.941806640625, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.93033447265625, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.9158349609375, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.90099365234375, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.8863330078125, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.86935791015625, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.854013671875, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.840948486328125, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.8242401123046874, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.8106951904296875, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.793780517578125, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.7792999267578127, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.765977783203125, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.749100341796875, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.7287939453125, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.704873046875, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.681461181640625, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.65075439453125, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.6168963623046877, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.5763934326171873, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.53018310546875, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.478497314453125, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.412716064453125, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.350187072753906, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.290915222167969, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.2074285888671876, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.1058779907226564, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.0142159271240234, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.9310946655273438, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.8203104400634766, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.723559455871582, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.6123886871337891, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.5064916133880615, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.3984592247009278, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.3008979320526124, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.2013185214996338, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.0872162461280823, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.0064318203926086, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.9411952066421508, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.8639394438266754, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.8042935466766358, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.7434124898910522, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.6866834855079651, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.6435767817497253, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.598250285089016, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.5650639900565148, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.015387068944983184, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.015134739391505718, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.014718553493730724, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.014326083292253315, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.013947492921724916, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.01344902790384367, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.012906635515391826, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.012343732432927936, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.011669875448569655, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.011033043034840375, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.01049075429327786, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.009837493186350911, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.009379184194840491, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.00895938917528838, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.008742020707577467, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.008631662458647042, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.008561913562007249, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.008522745152004064, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.008498114005196839, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.008478886135853826, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.008456566398963332, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.008432042768690735, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.00840187691617757, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.008366592184174806, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.00832482049940154, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.008269445041660219, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0082138044340536, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.008157900294754654, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.008074424276128412, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.00796407562913373, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.007858526264317333, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.007759225307963789, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.007621237775310874, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.007499427979346365, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.007353088413365186, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.007203022610628978, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.007033193177776411, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.006861213117372244, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.00666907548904419, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0064357072720304135, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.006265468380879611, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.00612679677316919, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.005964406247949227, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.005842959790024907, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.00572764735785313, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.005615378536749632, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.005511316463816911, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.005440287300152704, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.005437450309982523, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.9624783992767334, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.9527533054351807, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.937631845474243, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.923912286758423, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.911355495452881, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.895651340484619, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.8799493312835693, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.8647520542144775, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.8476202487945557, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.832422971725464, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.8197994232177734, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.803907871246338, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.79067325592041, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.773521900177002, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.757807731628418, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.7427151203155518, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.723111629486084, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.699092388153076, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.670753240585327, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.642841100692749, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.6064743995666504, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.566615343093872, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.5193796157836914, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.4655468463897705, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.4061219692230225, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.3311877250671387, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.2608048915863037, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.194671869277954, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.102843761444092, "validation/loss_029_lr2.3e+00_wd1.0e+00": 1.9927029609680176, "validation/loss_030_lr2.7e+00_wd1.0e+00": 1.8948651552200317, "validation/loss_031_lr3.1e+00_wd1.0e+00": 1.807664394378662, "validation/loss_032_lr3.7e+00_wd1.0e+00": 1.6932860612869263, "validation/loss_033_lr4.3e+00_wd1.0e+00": 1.5951263904571533, "validation/loss_034_lr5.1e+00_wd1.0e+00": 1.4840503931045532, "validation/loss_035_lr6.0e+00_wd1.0e+00": 1.379622220993042, "validation/loss_036_lr7.1e+00_wd1.0e+00": 1.274364948272705, "validation/loss_037_lr8.3e+00_wd1.0e+00": 1.1808550357818604, "validation/loss_038_lr9.8e+00_wd1.0e+00": 1.0877704620361328, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.9848765730857849, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.913896381855011, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.8568412065505981, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.7889648675918579, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.736426055431366, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.6841630339622498, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.6381675601005554, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.6009097695350647, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.5595793724060059, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.5329174995422363, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.1800595238095238, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.17212301587301587, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.1708829365079365, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.17410714285714285, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.18328373015873015, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.2123015873015873, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.24479166666666666, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.28100198412698413, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.3187003968253968, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.3524305555555556, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.3802083333333333, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.4114583333333333, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.46304563492063494, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.5069444444444444, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.5421626984126984, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.582093253968254, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.6207837301587301, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.6629464285714286, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.7046130952380952, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.746031746031746, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.7740575396825397, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.7993551587301587, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.8199404761904762, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.8318452380952381, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.8439980158730159, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.8506944444444444, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.8576388888888888, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.8621031746031746, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.8606150793650794, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.8665674603174603, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.8809523809523809, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.8903769841269841, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.02287041805675346, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.016277315648232153, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.013888047800722664, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.014154901097986342, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.01796727657221108, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.028230740407502293, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.05357473087329226, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.075642227834638, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.10043448152155857, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.1283990176230314, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.1515425401291564, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.17661695519313667, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.21260004290513, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.2880724801776727, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.3494503663369727, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.3935326910959269, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.44614531383814304, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.5049143241516066, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.5700936380731427, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.6338437468412927, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.6938102978901914, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.7295256096424593, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.7622771629459909, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.7865824145499448, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.7971201997698495, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.8117733469966708, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.8196293436363329, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.8289214219740403, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.839794932963238, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.8427841528427258, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.8519550001259905, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.8645677200778162, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.871586198085389, "id_best": 48, "lr_best": 0.015, "wd_best": 0.05, "train/loss_best": 0.5650639900565148, "validation/loss_best": 0.5329174995422363, "validation/acc_best": 0.8903769841269841, "validation/f1_best": 0.871586198085389} +{"epoch": 5, "train/lr": 0.00029891323817685334, "train/loss": 1.9964056199789046, "train/grad": 0.06111551327630878, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.95264404296875, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.94225830078125, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.926461181640625, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.912314453125, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.8996044921875, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.884066162109375, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.86891357421875, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.85443115234375, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.838515625, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.8246044921875, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.81281982421875, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.7974188232421877, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.783948974609375, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.76501953125, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.7469085693359374, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.7291436767578126, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.70576171875, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.6770947265625, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.643284912109375, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.610135498046875, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.5671868896484376, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.520152587890625, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.4649664306640626, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.4025503540039064, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.3342242431640625, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.249140167236328, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.17013671875, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.0968386840820314, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.996651840209961, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.878775520324707, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.7758934020996093, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.6855495643615723, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.5690310287475586, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.4705159187316894, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.3609510040283204, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.2600767517089844, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.1603752946853638, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.0733942675590515, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.9871895956993103, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.8915615880489349, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.8258644211292266, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.7738471156358719, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.7133260959386826, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.6671163579821586, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.6208227437734604, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.5788255627453327, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.5473879562318325, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.5148844133317471, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.4912914232909679, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.014583690324798226, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.014240996045991779, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.013700954355299473, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.013192677162587643, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.012712831567041576, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.012096785192843526, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.01147522866493091, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.010868236760143191, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.010203722938895226, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.009673123524989932, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.009305323620792479, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.008962206754367798, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.008785978532396257, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.008669353290461004, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.00862145095365122, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.00859517379431054, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.008570884123910218, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.008546522764954717, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.008518178625963628, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.008490602718666196, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.008454077411442995, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.008411833194550127, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.008361816776450724, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.008301299074664712, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.008231117608956992, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.008137778074014931, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.008044804453384131, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.007955373027361929, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.007827842589467764, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.007671751331072301, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.00753070117207244, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.007400671397335828, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.007225906900130212, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.007067914601648227, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.006879834163701162, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0066926590877119455, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.00649375865701586, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.006315222634002566, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.006134732540231198, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.005939391248393804, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.005807853260776028, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.005703640981810167, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.005580439325422048, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.005496465085307136, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.005453260240610689, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.005445575638441369, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.005410151543328539, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0053602946677710865, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.005337034277617931, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.937661647796631, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.926062822341919, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.908576011657715, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.893155097961426, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.879591226577759, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.8631625175476074, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.8473548889160156, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.832636594772339, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.816601276397705, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.80263614654541, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.7906241416931152, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.77445912361145, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.759716510772705, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.738572597503662, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.7180674076080322, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.697864294052124, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.6713147163391113, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.638735294342041, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.600555419921875, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.5632882118225098, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.5150046348571777, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.462726593017578, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.401470184326172, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.332902431488037, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.2586498260498047, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.166949510574341, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.0832326412200928, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.0065479278564453, "validation/loss_028_lr1.9e+00_wd1.0e+00": 1.902899146080017, "validation/loss_029_lr2.3e+00_wd1.0e+00": 1.7827363014221191, "validation/loss_030_lr2.7e+00_wd1.0e+00": 1.6792066097259521, "validation/loss_031_lr3.1e+00_wd1.0e+00": 1.589047908782959, "validation/loss_032_lr3.7e+00_wd1.0e+00": 1.473956823348999, "validation/loss_033_lr4.3e+00_wd1.0e+00": 1.3778935670852661, "validation/loss_034_lr5.1e+00_wd1.0e+00": 1.272744059562683, "validation/loss_035_lr6.0e+00_wd1.0e+00": 1.1779813766479492, "validation/loss_036_lr7.1e+00_wd1.0e+00": 1.0858415365219116, "validation/loss_037_lr8.3e+00_wd1.0e+00": 1.0058927536010742, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.9268452525138855, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.838426947593689, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.7776841521263123, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.730972170829773, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.6767969727516174, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.6346672177314758, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.5911704301834106, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.5502548217773438, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.52359539270401, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.5023157596588135, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.48517003655433655, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.17261904761904762, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.17881944444444445, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.203125, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.22916666666666666, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.26587301587301587, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.30183531746031744, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.3412698412698413, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.3990575396825397, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.4444444444444444, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.48586309523809523, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.5384424603174603, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.5858134920634921, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.6215277777777778, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.6505456349206349, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.6892361111111112, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.7130456349206349, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.7428075396825397, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.7626488095238095, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.78125, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.7961309523809523, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.8115079365079365, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.8283730158730159, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.84375, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.8506944444444444, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.8628472222222222, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.8700396825396826, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.8764880952380952, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.8916170634920635, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.8953373015873016, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.8891369047619048, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.892609126984127, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.013885104794195705, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.016119924720630417, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.02378331312874635, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.04752837295021156, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.07084998083309205, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.09733976119931895, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.12436795259548057, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.15721278404437675, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.2203657140297739, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.27160639275151954, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.3298597117706378, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.38722971073758955, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.4414442644894593, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.4844773345245108, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.5312463335745121, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.5939983742023627, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.6312686850126421, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.6750856669019312, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.6997766208211997, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.7209245694818216, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.7384268972113978, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.7604686988962251, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.7882753092847239, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.811341116586201, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.8231365228677053, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.8419017626021438, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.8508382067801192, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.8594185244303205, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.8742750192111932, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.8786653310510437, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.8719561853880547, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.8756491862684302, "id_best": 46, "lr_best": 0.010799999999999999, "wd_best": 0.05, "train/loss_best": 0.5473879562318325, "validation/loss_best": 0.52359539270401, "validation/acc_best": 0.8953373015873016, "validation/f1_best": 0.8786653310510437} +{"epoch": 6, "train/lr": 0.0002924170901991409, "train/loss": 1.8950360971689224, "train/grad": 0.05863769678398967, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.926502685546875, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.914246826171875, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.895941162109375, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.8799755859375, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.866104736328125, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.849581298828125, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.833922119140625, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.8194500732421877, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.8036572265625, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.78954833984375, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.777108154296875, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.759661865234375, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.74318115234375, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.7192510986328124, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.6956597900390626, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.6725079345703127, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.642156982421875, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.6050439453125, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.5616656494140626, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.519503173828125, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.4651568603515623, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.406666564941406, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.338595275878906, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.263001251220703, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.181737518310547, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.082587890625, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.9927135467529298, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.9111222076416015, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.8022436141967773, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.6776336860656738, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.571925506591797, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.4813586235046388, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.3673901748657227, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.2734414052963257, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.1713227653503417, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.0795202088356017, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.9910078775882721, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.9151009273529053, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.8413067382574081, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.760796847641468, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.7062935930490494, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.6635529178380967, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.6146796715259552, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.578454647064209, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.5424022181332111, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.51008454144001, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.48665071830153467, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.46181281805038454, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.44354084357619283, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.013979636109434068, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.013566501480527222, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.01291559892706573, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.012314981690142304, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.011782133947126567, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.011124259510543197, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.01049382119672373, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.009949392494745553, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.009455736135132611, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.009137759392615408, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.008959745592437684, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.008830804598983378, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.008774552259128541, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.008734591477550567, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.008708295843098313, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.008686513435095548, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.008657617517746985, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.008622361661400646, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.008581215930171311, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.008538807092700154, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.008483548802323639, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.00841878880513832, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.008340413249097765, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.008248989316634835, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.008145698881708085, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.008011854367796332, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.007884673012886196, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0077648201119154695, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.007596703986637294, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.007394879038911313, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.007216002938803285, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.007055069026537239, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0068439129460603, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.006659635412506759, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.00644981175661087, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.006253986848751083, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.006058083955431357, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0058811673184391115, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.005697904066182673, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.005491274719825015, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.005357311760308221, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.005253439934458584, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.005149864662671462, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.005102963977260515, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.005061357627855614, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.00505396316642873, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.005068412092514336, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.00506112247123383, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.005083800641587004, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.916541337966919, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.9037721157073975, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.885056257247925, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.8690662384033203, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.85530948638916, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.839181661605835, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.824087619781494, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.8101751804351807, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.7950029373168945, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.7809267044067383, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.768197536468506, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.7497975826263428, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.731987714767456, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.705827474594116, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.6801323890686035, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.654834270477295, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.6217610836029053, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.5813863277435303, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.534376859664917, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.488774299621582, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.4303643703460693, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.367734432220459, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.295367956161499, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.215491771697998, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.1303231716156006, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.0273544788360596, "validation/loss_026_lr1.4e+00_wd1.0e+00": 1.9348734617233276, "validation/loss_027_lr1.6e+00_wd1.0e+00": 1.8516857624053955, "validation/loss_028_lr1.9e+00_wd1.0e+00": 1.741532325744629, "validation/loss_029_lr2.3e+00_wd1.0e+00": 1.6170767545700073, "validation/loss_030_lr2.7e+00_wd1.0e+00": 1.512486457824707, "validation/loss_031_lr3.1e+00_wd1.0e+00": 1.4236804246902466, "validation/loss_032_lr3.7e+00_wd1.0e+00": 1.3127347230911255, "validation/loss_033_lr4.3e+00_wd1.0e+00": 1.222214698791504, "validation/loss_034_lr5.1e+00_wd1.0e+00": 1.124575138092041, "validation/loss_035_lr6.0e+00_wd1.0e+00": 1.0372281074523926, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.9532778263092041, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.8814761638641357, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.812161386013031, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.7377752661705017, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.6877351403236389, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.6487316489219666, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.6040301322937012, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.5709220767021179, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.5358695983886719, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.5014366507530212, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.4795083701610565, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.4584457576274872, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.4428858160972595, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.1708829365079365, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.1746031746031746, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.18625992063492064, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.2095734126984127, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.23462301587301587, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.2638888888888889, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.2986111111111111, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.3395337301587302, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.3878968253968254, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.4402281746031746, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.4871031746031746, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.5252976190476191, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.5776289682539683, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.6359126984126984, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.6713789682539683, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.699156746031746, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.736359126984127, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.7564484126984127, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.7795138888888888, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.798859126984127, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.8169642857142857, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.8328373015873016, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.8464781746031746, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.8601190476190477, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.8663194444444444, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.8712797619047619, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.8794642857142857, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.8831845238095238, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.8888888888888888, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.8978174603174603, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9032738095238095, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9069940476190477, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9087301587301587, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.014154901097986342, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.018668139455646292, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.032251779232139864, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.05289791541253536, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.07273273481808275, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.09598115629028448, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.1246894048747799, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.1605921388862852, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.20772696546003916, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.2704346520900665, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.3264959069275711, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.3712694432834197, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.4379573571040102, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.515690378569168, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.5703074289252138, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.6144374441894075, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.6698831122052422, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.698332531599748, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.7331516932672342, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.7586795382947071, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.7826990504447527, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.8028071810666537, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.8179057448329472, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.8330677479127393, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.8387947350003235, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.8457104293954677, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.8570451095848275, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.8633875880305679, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.8702293169767753, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.8801167971476579, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.8870460032020976, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.8906960541519615, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.8887564718449348, "id_best": 48, "lr_best": 0.015, "wd_best": 0.05, "train/loss_best": 0.44354084357619283, "validation/loss_best": 0.4428858160972595, "validation/acc_best": 0.9087301587301587, "validation/f1_best": 0.8887564718449348} +{"epoch": 7, "train/lr": 0.00027969249556793234, "train/loss": 1.8296281069517135, "train/grad": 0.05534654714167118, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.90889404296875, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.896104736328125, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.87755126953125, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.86197509765625, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.848739013671875, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.83330078125, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.819000244140625, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.8057489013671875, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.79075927734375, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.776402587890625, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.7629296875, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.7427838134765623, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.7231365966796877, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.694210205078125, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.6657177734375, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.637738037109375, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.6011505126953125, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.5566241455078127, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.5050079345703127, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.4551400756835937, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.3915646362304686, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.323747253417969, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.2458840942382814, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.1604803466796874, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.0702894592285155, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.9620819854736329, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.8658006286621094, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.7798555755615235, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.6670122337341309, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.5406377983093262, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.4354939842224121, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.3467763710021972, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.2369170379638672, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.147978768348694, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.0526738524436952, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.9683537447452545, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.8880039930343628, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.8199307072162628, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.7542535790801048, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.6833971571922303, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.6358286553621292, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.5985978060960769, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.555916220843792, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.5237945230305194, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.49185829937458037, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.46351778641343117, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.443420332968235, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.42372117906808854, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.41107653707265857, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.013226377218961716, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.012738126346375793, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.011994565774220972, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.011349889971315861, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.01077848315006122, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.010118205940816551, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.009565901041496546, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.009152704125735909, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.008837577165104448, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.008676525081973523, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.008602658547461032, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.008552482770755886, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.008525624049361795, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.008497336255386472, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.008473268139641731, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.008449500363785773, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.008417835112195462, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.008377657108940183, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.008329691011458635, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.008280355671886355, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.008215299299918115, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.00814140675822273, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.008052046382799745, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.007947435884270817, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.007831809045746922, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.00768344869138673, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.007544274916872382, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.007413187543861568, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.00723286995664239, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.007017903067171574, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.006828139565186575, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.006659313988639042, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.006440922444453463, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.006254239476984367, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.006046784307109192, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.005853549777530134, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.00566239524167031, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.00549389478401281, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.005323351445840671, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.005137630988610908, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0050205321342218666, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0049333161790855225, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0048307449521962555, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.004730862346477806, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.004621932476293295, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.004558287692489103, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.004552021173294634, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.00458316693897359, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.004663984332000837, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.898726224899292, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.885362386703491, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.866180419921875, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.850217580795288, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.8368258476257324, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.8213443756103516, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.8070201873779297, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.7936513423919678, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.778278112411499, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.7631678581237793, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.748756170272827, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.727330207824707, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.7062289714813232, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.6751961708068848, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.644685745239258, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.6147780418395996, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.5757243633270264, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.528447151184082, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.473647117614746, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.4210028648376465, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.354116678237915, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.283076286315918, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.201976776123047, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.1136348247528076, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.0208470821380615, "validation/loss_025_lr1.2e+00_wd1.0e+00": 1.9104151725769043, "validation/loss_026_lr1.4e+00_wd1.0e+00": 1.8129329681396484, "validation/loss_027_lr1.6e+00_wd1.0e+00": 1.7263753414154053, "validation/loss_028_lr1.9e+00_wd1.0e+00": 1.6135919094085693, "validation/loss_029_lr2.3e+00_wd1.0e+00": 1.4883522987365723, "validation/loss_030_lr2.7e+00_wd1.0e+00": 1.3849848508834839, "validation/loss_031_lr3.1e+00_wd1.0e+00": 1.2983322143554688, "validation/loss_032_lr3.7e+00_wd1.0e+00": 1.1919071674346924, "validation/loss_033_lr4.3e+00_wd1.0e+00": 1.106653094291687, "validation/loss_034_lr5.1e+00_wd1.0e+00": 1.016315221786499, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.9374223351478577, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.8634185791015625, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.8018313646316528, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.7429199814796448, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.6787062883377075, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.6348721981048584, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.6005394458770752, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.559891402721405, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.5277326107025146, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.4975042939186096, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.476570725440979, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.46558815240859985, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.4527609050273895, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.4385293424129486, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.17261904761904762, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.17807539682539683, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.20238095238095238, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.22643849206349206, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.25570436507936506, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.28794642857142855, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.32068452380952384, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.3635912698412698, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.4097222222222222, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.4583333333333333, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.5079365079365079, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.5550595238095238, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.5927579365079365, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.6408730158730159, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.6867559523809523, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.7194940476190477, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.7465277777777778, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.7688492063492064, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.7886904761904762, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.8035714285714286, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.8149801587301587, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.8268849206349206, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.8350694444444444, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.8452380952380952, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.8559027777777778, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.8650793650793651, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.8720238095238095, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.8812003968253969, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.8874007936507936, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.8943452380952381, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.8940972222222222, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.8896329365079365, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.8898809523809523, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.8968253968253969, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.016119924720630417, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.02280184033324849, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.046377300449353474, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.0653622649913729, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.08793299749312417, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.11103359963733742, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.13534651151003466, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.1742365486866858, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.22407500540201206, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.2821582128903479, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.3454603164444168, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.39802113664030037, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.4497121689656544, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.5183043390080198, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.5872046599421388, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.6363189773211945, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.6812548769382775, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.7131528875186091, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.7397351422098987, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.7619957679399866, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.7756488559335951, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.7909302401669797, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.8008933419071059, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.814803836466314, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.8274442366158432, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.836199997234939, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.8443267256729896, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.85537404162198, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.863439022457152, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.8724818089020031, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.8733499461294982, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.8696140850436671, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.8689780032940035, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.8715890577536621, "id_best": 48, "lr_best": 0.015, "wd_best": 0.05, "train/loss_best": 0.41107653707265857, "validation/loss_best": 0.4385293424129486, "validation/acc_best": 0.8968253968253969, "validation/f1_best": 0.8715890577536621} +{"epoch": 8, "train/lr": 0.0002612959497061927, "train/loss": 1.7727301180362702, "train/grad": 0.0537624148465693, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.892076416015625, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.8788330078125, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.859967041015625, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.84442626953125, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.8315472412109375, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.816614990234375, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.802755126953125, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.7893768310546876, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.7735882568359376, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.7576104736328126, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.742125244140625, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.7186663818359373, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.6956903076171876, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.6616241455078127, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.628424072265625, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.5958575439453124, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.5533123779296876, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.50193359375, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.4427554321289064, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.3860598754882814, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.31425537109375, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.2384904479980468, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.1526365661621094, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.05958740234375, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.962674560546875, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.8481723022460939, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.748107681274414, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.659969654083252, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.5459338569641112, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.4205341148376465, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.3180870008468628, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.2327954626083375, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.1288270616531373, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.0458824801445008, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.958257076740265, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.8816917955875396, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.8095403319597244, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.7490095242857933, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.6911320871114731, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.6289750690758228, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.5875542661547661, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.5553316298127174, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.5187749110162259, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.4918819499015808, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.4656995429098606, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.4426288053393364, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.42616174519062044, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.4098427997529507, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.3980972954630852, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.012611895115114749, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.012081707522738724, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.01131014472572133, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.010643146126531064, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.010094198354054243, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.009526935338508338, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.00910508969798684, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.008830745117738842, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.008656112926546484, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.008577564440201968, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.008540721284225583, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.008509839493781328, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.008487438193988055, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.008457591107580811, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.008427935182116925, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.00839924113592133, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.00835998241091147, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.008310638838447631, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.00825233644573018, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.008193599521182477, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.008115421927068383, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.008029032982885837, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.007926521906629205, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.007807609387673438, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.007676684022881091, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.007514391897711903, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.007364448066800833, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.007225775683764368, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.007036217225249857, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.006813582181930542, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0066175570257473735, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0064426557417027654, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.006216930713271722, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.006027233663480729, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.005817700807237997, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.005630244360072538, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.005448951014550403, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0052899713173974305, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0051322754251305015, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.004957393676741049, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.004841828403295949, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.004753481987863779, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.004667372942203656, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.00462636400363408, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.004603911774465814, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.004608020021114498, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.004627812680555507, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.004648542802315205, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0046423203416634355, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.88413143157959, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.8704888820648193, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.851289749145508, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.8356359004974365, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.8227298259735107, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.8079328536987305, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.7939300537109375, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.7804007530212402, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.7640888690948486, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.7473676204681396, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.7310802936553955, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.706516981124878, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.6823062896728516, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.646679162979126, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.6118147373199463, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.5777318477630615, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.5333757400512695, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.4799015522003174, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.4184696674346924, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.3597826957702637, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.285861015319824, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.2080252170562744, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.120225429534912, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.0256011486053467, "validation/loss_024_lr1.0e+00_wd1.0e+00": 1.9274299144744873, "validation/loss_025_lr1.2e+00_wd1.0e+00": 1.8122111558914185, "validation/loss_026_lr1.4e+00_wd1.0e+00": 1.7119486331939697, "validation/loss_027_lr1.6e+00_wd1.0e+00": 1.624013066291809, "validation/loss_028_lr1.9e+00_wd1.0e+00": 1.510832667350769, "validation/loss_029_lr2.3e+00_wd1.0e+00": 1.3870681524276733, "validation/loss_030_lr2.7e+00_wd1.0e+00": 1.286372423171997, "validation/loss_031_lr3.1e+00_wd1.0e+00": 1.2027614116668701, "validation/loss_032_lr3.7e+00_wd1.0e+00": 1.1012953519821167, "validation/loss_033_lr4.3e+00_wd1.0e+00": 1.0208457708358765, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.9361169934272766, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.8623119592666626, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.7927535176277161, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.7343164086341858, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.6786350607872009, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.6197224259376526, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.5812831521034241, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.5517607927322388, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.5187240839004517, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.4931555986404419, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.46906498074531555, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.4506106376647949, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.43979135155677795, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.4327846169471741, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.43396440148353577, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.17137896825396826, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.1746031746031746, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.18700396825396826, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.2123015873015873, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.24280753968253968, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.27306547619047616, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.31026785714285715, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.357390873015873, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.40153769841269843, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.4521329365079365, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.5022321428571429, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.5533234126984127, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.5949900793650794, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.6376488095238095, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.6793154761904762, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.7212301587301587, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.7502480158730159, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.7728174603174603, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.7931547619047619, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.810515873015873, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.8271329365079365, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.8405257936507936, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.8529265873015873, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.8608630952380952, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.8702876984126984, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.8807043650793651, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.8888888888888888, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.8921130952380952, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.8960813492063492, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9045138888888888, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9069940476190477, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9064980158730159, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.904265873015873, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.8983134920634921, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.8901289682539683, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.014695821028922454, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.018668139455646292, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.032997319124556196, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.054965784943275496, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.08012752913737231, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.10457952780608866, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.13449446806178525, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.1746834855317467, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.22168720572868875, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.27962016781445326, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.34456060056093557, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.40459111291296485, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.45850174612697703, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.5206916163682989, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.5882930099199449, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.6504935573847906, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.6922110622697498, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.725214030492997, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.7494478610164336, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.7747386997454706, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.7945528712235653, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.8120697971979767, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.8278982390685347, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.8399308617839706, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.8505199513529408, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.8631356845315374, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.8742884108191289, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.8790519019464785, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.8842990076758693, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.8919807188151277, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.8957860134780176, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.8944066328696734, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.888735824646657, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.8781601795940471, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.8687375093700482, "id_best": 44, "lr_best": 0.0078, "wd_best": 0.05, "train/loss_best": 0.4656995429098606, "validation/loss_best": 0.46906498074531555, "validation/acc_best": 0.9069940476190477, "validation/f1_best": 0.8957860134780176} +{"epoch": 9, "train/lr": 0.00023803200426111704, "train/loss": 1.727652690410614, "train/grad": 0.05206295082345605, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.88276611328125, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.869552001953125, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.8511865234375, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.8364434814453126, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.8242486572265624, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.8101092529296876, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.796531982421875, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.7829461669921876, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.765953369140625, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.7481768798828123, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.730888671875, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.704375, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.678289794921875, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.639998779296875, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.6026312255859376, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.56605224609375, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.5187115478515625, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.4616293334960937, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.3962457275390623, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.33396728515625, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.2559161376953125, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.174254150390625, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.0822802734375, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.9838875579833983, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.882499237060547, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.7640965270996094, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.661710548400879, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.5724337196350098, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.4580333518981934, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.3335614109039307, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.2328289318084718, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.149706313610077, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.0491183471679688, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.9693633937835693, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.8857116365432739, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.8129620176553726, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.7447008916735649, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.6876080703735351, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.6332158014178276, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.5752104365825653, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.5368204386532307, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.5072285455465316, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.4740662556886673, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.4498293295502663, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.42656341403722764, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.40651841804385186, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.39282276973128316, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.37988647907972334, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.3714450454711914, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.012053236574865877, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.011507810251787305, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.010712562811095267, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.010070678868796677, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.009590428483206778, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.009138755921740085, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.008841802903916687, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.008676113144028932, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.008582196414936334, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.008539198995567859, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.008514872291125358, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.008487563855014741, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.00846225769026205, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.008428633108269423, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.008393901537638158, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.008358259296510368, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.00831165739800781, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.00825441372115165, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.008184443970676511, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.00811351418728009, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.008020583165343851, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.00791790014365688, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.007794246482662856, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.007655701800249517, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0075054498645477, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.007321874175686389, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.00715271175140515, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.006999294578563422, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.006788148593623191, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.006540612208191306, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.006323636705055833, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.006133545293705538, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.00588769895141013, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.005681253136135638, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.005458722740877419, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.00525520236347802, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.005056819318560883, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.004882339662872255, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.004715813350630924, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.00454272254020907, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.004429062544368208, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0043460937193594874, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.004262166213011369, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.004215047252364457, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.004205271688988432, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.004259585267864168, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.004341346742003225, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.004464237946085632, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.004575332668609917, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.872122287750244, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.8584015369415283, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.839498281478882, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.8243582248687744, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.811872959136963, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.7973990440368652, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.783489227294922, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.769365072250366, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.751704216003418, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.7332944869995117, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.715149164199829, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.6877167224884033, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.6606786251068115, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.6210176944732666, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.5822629928588867, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.5445103645324707, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.495654344558716, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.4369170665740967, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.369837760925293, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.306211233139038, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.2266528606414795, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.143540143966675, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.0505716800689697, "validation/loss_023_lr8.5e-01_wd1.0e+00": 1.951533317565918, "validation/loss_024_lr1.0e+00_wd1.0e+00": 1.8498008251190186, "validation/loss_025_lr1.2e+00_wd1.0e+00": 1.7318673133850098, "validation/loss_026_lr1.4e+00_wd1.0e+00": 1.6303240060806274, "validation/loss_027_lr1.6e+00_wd1.0e+00": 1.542132019996643, "validation/loss_028_lr1.9e+00_wd1.0e+00": 1.429699182510376, "validation/loss_029_lr2.3e+00_wd1.0e+00": 1.3081501722335815, "validation/loss_030_lr2.7e+00_wd1.0e+00": 1.2104995250701904, "validation/loss_031_lr3.1e+00_wd1.0e+00": 1.1305768489837646, "validation/loss_032_lr3.7e+00_wd1.0e+00": 1.034618854522705, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.9593718647956848, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.8809217214584351, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.813103973865509, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.7499638795852661, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.697060227394104, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.646388590335846, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.5917777419090271, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.5543643832206726, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.5247295498847961, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.49117958545684814, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.46699076890945435, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.444417804479599, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.4248260259628296, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.410247266292572, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.39537158608436584, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.386130690574646, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.17137896825396826, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.17485119047619047, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.1857638888888889, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.21279761904761904, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.24107142857142858, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.27380952380952384, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.30481150793650796, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.3464781746031746, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.39112103174603174, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.44246031746031744, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.4935515873015873, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.5434027777777778, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.5912698412698413, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.6336805555555556, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.6703869047619048, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.7053571428571429, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.7395833333333334, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.7671130952380952, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.783234126984127, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.8030753968253969, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.8191964285714286, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.8308531746031746, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.8442460317460317, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.8541666666666666, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.8638392857142857, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.8705357142857143, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.8821924603174603, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.8878968253968254, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.8948412698412699, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9020337301587301, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9079861111111112, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9122023809523809, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9154265873015873, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9181547619047619, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9206349206349206, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9203869047619048, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.014695821028922454, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.018924861767393084, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.03148313213834754, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.05518873647813332, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.07802944217340392, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.10198154768530951, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.12850921707549984, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.1623851777675223, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.20944187088484342, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.27170798340002683, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.3350120120853386, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.39582410916084415, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.4511261121776591, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.5152345178905176, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.5722793022954551, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.6276628680925085, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.6813515442076788, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.7193938012383528, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.7408852224779816, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.7667886297861285, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.7885301987476616, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.8043466967775418, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.8209486318539605, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.834055038181807, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.8458818343281207, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.8532351305575803, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.8678876384521198, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.8736577840827098, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.8828169644087984, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.8891298748811264, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.8941918539266667, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.8986325832439197, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9012593445117361, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9043134615204264, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9081577722445507, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9096168117695788, "id_best": 47, "lr_best": 0.012899999999999998, "wd_best": 0.05, "train/loss_best": 0.37988647907972334, "validation/loss_best": 0.39537158608436584, "validation/acc_best": 0.9206349206349206, "validation/f1_best": 0.9081577722445507} +{"epoch": 10, "train/lr": 0.00021091808096876188, "train/loss": 1.68401546895504, "train/grad": 0.05166336301714182, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.87085205078125, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.85749267578125, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.8391192626953123, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.8244781494140625, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.8123297119140624, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.7981683349609376, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.7841168212890626, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.7694952392578127, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.7509765625, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.7313153076171877, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.711895751953125, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.6825714111328125, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.653543701171875, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.6109539794921877, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.5694921875, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.5290762329101564, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.476961669921875, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.4143991088867187, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.343147888183594, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.275837707519531, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.1917921447753907, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.104615020751953, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.0073577117919923, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.9043339920043945, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.7991097640991212, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.6776698303222657, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.5737936973571778, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.4839677619934082, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.3700276374816895, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.2476042938232421, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.149759075641632, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.0697868883609771, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.9740460479259491, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.8990081059932709, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.820958309173584, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.7535574427247047, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.6908692824840545, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.6387844090163708, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.5894559800624848, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.5372613584995269, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.5028798072040082, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.4764476798474789, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.44686793521046636, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.42512406647205353, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.40398109078407285, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.38552042216062543, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.3726637214422226, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.36048140332102774, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.3528108704090118, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.01180853656725958, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.011247892586980016, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.010451641643885522, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.009856981597840786, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.009439094068948179, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.0090728027257137, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.00885775568895042, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.008746225503273308, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.008683764946181328, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.008650272749364377, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.008627736696507782, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.008597611247096211, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.008570456870365888, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.008529919849243015, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.00848953147418797, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.008447952673304827, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.00839430609717965, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.008326780868228524, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.00824711739551276, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.008167363645043224, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.008063951558433473, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.00794942248146981, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.00781608755933121, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.007665857872925699, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.007502757334150374, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.007300682750064879, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0071163716283626855, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.006948620462790132, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.006721267753746361, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.006460071760229767, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.006237461745040491, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.006044573829276487, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.005801661747973412, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.005599637113045901, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.005376781385857612, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.005175138550112024, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.004979396478738636, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.004812994784442708, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.004648279899265617, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.004470001534791664, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.004348242717096582, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.004253421212779358, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.004154768532607704, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.004093747088918462, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.00404466888285242, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.004012357630999759, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.003999528797576204, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0040090477641206235, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.004044734901399351, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.8625028133392334, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.8488805294036865, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.830310821533203, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.8155972957611084, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.8033809661865234, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.789071559906006, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.774780035018921, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.75990891456604, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.7409300804138184, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.720844268798828, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.7010338306427, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.6710307598114014, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.6415674686431885, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.5982613563537598, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.5562427043914795, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.515347719192505, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.4626128673553467, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.3995745182037354, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.3277721405029297, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.2601840496063232, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.176081657409668, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.088902473449707, "validation/loss_022_lr7.2e-01_wd1.0e+00": 1.9921678304672241, "validation/loss_023_lr8.5e-01_wd1.0e+00": 1.8898797035217285, "validation/loss_024_lr1.0e+00_wd1.0e+00": 1.7857799530029297, "validation/loss_025_lr1.2e+00_wd1.0e+00": 1.6661030054092407, "validation/loss_026_lr1.4e+00_wd1.0e+00": 1.5639560222625732, "validation/loss_027_lr1.6e+00_wd1.0e+00": 1.4758836030960083, "validation/loss_028_lr1.9e+00_wd1.0e+00": 1.3645089864730835, "validation/loss_029_lr2.3e+00_wd1.0e+00": 1.2452194690704346, "validation/loss_030_lr2.7e+00_wd1.0e+00": 1.1501044034957886, "validation/loss_031_lr3.1e+00_wd1.0e+00": 1.072465419769287, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.9796570539474487, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.9069529175758362, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.8313776850700378, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.7659636735916138, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.7054889798164368, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.6554950475692749, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.608611524105072, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.5588033199310303, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.5257536768913269, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.5000051856040955, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.4711916744709015, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.4502919912338257, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.43068239092826843, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.4137323200702667, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.4006553888320923, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.38614755868911743, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.37652820348739624, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.1728670634920635, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.17906746031746032, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.19940476190476192, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.22123015873015872, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.2569444444444444, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.28918650793650796, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.32217261904761907, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.36408730158730157, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.4055059523809524, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.45907738095238093, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.5106646825396826, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.5577876984126984, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.6123511904761905, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.6495535714285714, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.6857638888888888, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.7160218253968254, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.753968253968254, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.7795138888888888, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.7961309523809523, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.8159722222222222, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.8298611111111112, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.8442460317460317, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.8598710317460317, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.8685515873015873, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.8762400793650794, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.8797123015873016, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.8903769841269841, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.8950892857142857, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9002976190476191, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9030257936507936, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.90625, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9107142857142857, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9114583333333334, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9154265873015873, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9206349206349206, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9243551587301587, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.01638156538686886, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.024011428455167582, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.04397713472119533, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.06266743512567297, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.09103978649877617, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.11336578680074358, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.1415338983185709, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.18046313298000363, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.22710656086616154, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.29732386156513485, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.3631220334355025, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.41691827950952404, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.49404278379376104, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.5419133630020829, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.6034469613537096, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.6493586982517308, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.7035680602066987, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.7354616482279401, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.7581992362385912, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.7843084631795401, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.8000157344777729, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.815682749467316, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.8342270821584886, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.8431929466896497, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.8540059708274884, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.8584212559122452, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.8735140602524054, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.8784652002503519, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.8849024217441268, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.8888768638396533, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.8932365311315852, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.8981609888650705, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9014239433084286, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9065116816281853, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9119436723589922, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9145010555867403, "id_best": 48, "lr_best": 0.015, "wd_best": 0.05, "train/loss_best": 0.3528108704090118, "validation/loss_best": 0.37652820348739624, "validation/acc_best": 0.9243551587301587, "validation/f1_best": 0.9145010555867403} +{"epoch": 11, "train/lr": 0.00018113997589164516, "train/loss": 1.6596311169862747, "train/grad": 0.05022193897515535, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.862138671875, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.848939208984375, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.8310931396484373, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.8168524169921874, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.80513427734375, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.7909478759765625, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.7765728759765627, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.7612213134765624, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.7413653564453124, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.720224609375, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.6992718505859377, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.667723388671875, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.636719970703125, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.591138916015625, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.546981201171875, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.5039901733398438, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.4486874389648436, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.3827020263671876, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.307762451171875, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.2372286987304686, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.149808197021484, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.059488983154297, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.9594678497314453, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.8541655349731445, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.7473350143432618, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.6248931694030762, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.5208403968811035, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.4314465713500977, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.318886456489563, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.1988733530044555, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.1037264156341553, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.026356146335602, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.9343771588802338, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.8626933604478836, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.7883876413106918, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.7247673302888871, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.6656411030888557, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.6167565754055977, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.570596352815628, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.5218796384334564, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.4898265558481216, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.4651580180227757, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.43759326986968516, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.4174060094356537, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.39791151955723764, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.3808086158335209, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.3688483619689941, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.35739365451037886, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.34989755183458326, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.01135732141789049, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.01077898289076984, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.010003845209721475, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.009464216749183834, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.009109192038886249, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008824172406457364, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.008673126460053027, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.0086012846021913, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.008558432790450751, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.008531185600440949, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.008510218576993793, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.008480064952746034, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.008451105547137558, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.008407802756410091, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.008364497141446919, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.008321020430885255, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.00826228729216382, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.008189504256006331, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.008104127580299974, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.008018272381741553, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.007906481630634517, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.007783429014962167, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.00764032059814781, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.007480428502894938, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.007309682776685804, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.007099518845789135, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.006910164193250239, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.006736497315578163, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0065034119575284426, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.00623445633566007, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.006004613232798875, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.005805349923903123, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0055534773773979395, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.005345415188930929, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.005118778509786353, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.004916603318415582, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.004725833113770932, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.004566696003312245, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.004420103956945241, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.004268635879270732, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.004171357491286471, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.004092267222004012, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0039992773160338405, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.003936647189548239, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0038914177403785288, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0038649842189624906, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.003873444148339331, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.003913614795310423, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0039608646254055205, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.8547871112823486, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.841312885284424, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.8231379985809326, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.8086841106414795, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.7967498302459717, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.7823500633239746, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.767582654953003, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.7519614696502686, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.7316794395446777, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.7101197242736816, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.6889030933380127, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.6567163467407227, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.625213623046875, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.5789906978607178, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.534137487411499, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.490659475326538, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.4346935749053955, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.3681013584136963, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.2925705909729004, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.221788167953491, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.134122848510742, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.0437865257263184, "validation/loss_022_lr7.2e-01_wd1.0e+00": 1.9442343711853027, "validation/loss_023_lr8.5e-01_wd1.0e+00": 1.8396228551864624, "validation/loss_024_lr1.0e+00_wd1.0e+00": 1.7337733507156372, "validation/loss_025_lr1.2e+00_wd1.0e+00": 1.6128277778625488, "validation/loss_026_lr1.4e+00_wd1.0e+00": 1.5104018449783325, "validation/loss_027_lr1.6e+00_wd1.0e+00": 1.422550916671753, "validation/loss_028_lr1.9e+00_wd1.0e+00": 1.3120712041854858, "validation/loss_029_lr2.3e+00_wd1.0e+00": 1.1945370435714722, "validation/loss_030_lr2.7e+00_wd1.0e+00": 1.1015650033950806, "validation/loss_031_lr3.1e+00_wd1.0e+00": 1.0261839628219604, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.9365859031677246, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.866892397403717, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.7947062253952026, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.7327250838279724, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.6753183603286743, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.6278773546218872, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.5830789804458618, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.5362133383750916, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.5059435963630676, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.4829482436180115, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.45716550946235657, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.4383728504180908, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.4202823340892792, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.4050770103931427, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.3949096202850342, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.3852633833885193, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.38049250841140747, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.1708829365079365, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.1746031746031746, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.18874007936507936, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.2105654761904762, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.2371031746031746, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.2700892857142857, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.30927579365079366, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.345734126984127, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.3896329365079365, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.4337797619047619, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.4871031746031746, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.5384424603174603, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.5808531746031746, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.6321924603174603, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.6711309523809523, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.7001488095238095, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.7358630952380952, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.7698412698412699, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.7909226190476191, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.8065476190476191, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.8271329365079365, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.8387896825396826, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.8539186507936508, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.8635912698412699, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.871031746031746, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.8799603174603174, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.886656746031746, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.8933531746031746, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.8993055555555556, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9050099206349206, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9094742063492064, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9134424603174603, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9181547619047619, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9191468253968254, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9201388888888888, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9203869047619048, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9191468253968254, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.014154901097986342, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.018668139455646292, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.03488720952804712, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.05382824512637006, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.07592112566801633, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.10119010307632538, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.13033074636587197, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.1597950051545599, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.20652003361042418, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.2588071505133878, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.3294957690558294, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.389256234070337, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.44324822905672384, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.5124222300377025, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.5737667920848112, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.6221618388572139, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.6767922249493065, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.7250461097903793, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.751017582507411, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.7716905731642731, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.7955409182207414, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.8092659496092245, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.8269367892279827, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.8378606217219454, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.8466397668907933, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.8582810592248743, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.8672345643064643, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.875624511229253, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.8835813651127832, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.8914507636672572, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.8970729763038896, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9019682816886032, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9077559657365187, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9087508126265066, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9100797394166475, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.910640715034396, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9095339895005692, "id_best": 47, "lr_best": 0.012899999999999998, "wd_best": 0.05, "train/loss_best": 0.35739365451037886, "validation/loss_best": 0.3852633833885193, "validation/acc_best": 0.9203869047619048, "validation/f1_best": 0.910640715034396} +{"epoch": 12, "train/lr": 0.0001499999999999999, "train/loss": 1.6338518863916398, "train/grad": 0.05028931581415236, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.853214111328125, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.83984130859375, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.8219158935546873, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.8075677490234376, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.79565185546875, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.7811279296875, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.7659552001953127, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.74975830078125, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.7286187744140626, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.7061956787109374, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.6840045166015627, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.6503460693359373, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.61740234375, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.5691412353515624, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.522406005859375, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.477170104980469, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.4190609741210936, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.3498654174804687, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.2715626525878907, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.198489990234375, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.108037109375, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.015272979736328, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.9131014251708984, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.8063317489624025, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.6986505126953124, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.576240291595459, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.4729234409332275, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.3846490383148193, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.2739585781097411, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.156757547855377, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.0641082286834718, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.9890815711021423, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.9000650984048844, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.8307001477479935, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.7589475199580192, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.6973646786808968, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.6403267964720726, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.5930903682112694, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.5485100975632667, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.5014482825994492, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.4703615041077137, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.4465586940944195, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.41976675018668175, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.40006641432642936, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.3811118872463703, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.36497511878609656, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.35407894730567935, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.3443058405816555, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.33865711607038973, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.011163975277449936, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.010592087276745588, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.009866415709257125, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.009391798730939626, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.009101081546396017, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008889518959913403, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.008787145128007979, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.00873884954256937, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.008706192197278141, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.008681451752781868, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.008659867462702095, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.008628001199103891, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.008595596672967077, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.008546316204592586, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.00849772381130606, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.008449194480199367, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.008383374731056391, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.008300505662336945, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.008202160520013421, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.008104839716106654, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.007976966791320593, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.007837912579998375, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.007677486001048237, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.00749904868658632, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.007310438794083893, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.007079573583323509, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.006873533562757075, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.006687412989558652, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.006439492995850742, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.006159046852262691, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.005922514614649117, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.005720697991782799, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0054681516194250435, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.005259658735012635, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.005034243494737894, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.004833602005383, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.004640987041639164, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.004479658958734945, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.004327164365677163, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0041675454669166355, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.004068330739391968, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.003993422802304849, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.003913176886271685, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0038547330314759164, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0038052788830827923, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0037776847393251956, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.003783605124335736, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0038477710948791356, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0039639504393562675, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.8488357067108154, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.8355205059051514, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.8176441192626953, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.8035078048706055, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.7916102409362793, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.7770543098449707, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.761789083480835, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.74537992477417, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.7241036891937256, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.7013139724731445, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.678856372833252, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.6449811458587646, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.6116578578948975, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.5630970001220703, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.5160067081451416, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.470428466796875, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.412029981613159, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.342508316040039, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.264192581176758, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.190878391265869, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.1006131172180176, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.008002996444702, "validation/loss_022_lr7.2e-01_wd1.0e+00": 1.9063615798950195, "validation/loss_023_lr8.5e-01_wd1.0e+00": 1.8002310991287231, "validation/loss_024_lr1.0e+00_wd1.0e+00": 1.6934312582015991, "validation/loss_025_lr1.2e+00_wd1.0e+00": 1.57210111618042, "validation/loss_026_lr1.4e+00_wd1.0e+00": 1.4698952436447144, "validation/loss_027_lr1.6e+00_wd1.0e+00": 1.3826143741607666, "validation/loss_028_lr1.9e+00_wd1.0e+00": 1.273546576499939, "validation/loss_029_lr2.3e+00_wd1.0e+00": 1.1581355333328247, "validation/loss_030_lr2.7e+00_wd1.0e+00": 1.0672308206558228, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.9938905835151672, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.9066613912582397, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.8390472531318665, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.7692898511886597, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.7097086906433105, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.6544671654701233, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.6088634729385376, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.5660377740859985, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.5208888053894043, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.491575688123703, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.46905988454818726, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.44369590282440186, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.4251610338687897, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.4074536859989166, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.39227294921875, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.3810257315635681, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.3702473044395447, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.36322763562202454, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.17162698412698413, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.17807539682539683, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.19866071428571427, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.21899801587301587, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.25049603174603174, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.2839781746031746, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.3263888888888889, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.3658234126984127, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.40649801587301587, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.45907738095238093, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.5104166666666666, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.558531746031746, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.6068948412698413, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.6510416666666666, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.6875, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.7152777777777778, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.7507440476190477, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.7827380952380952, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.8025793650793651, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.8191964285714286, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.8380456349206349, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.8501984126984127, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.8645833333333334, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.8742559523809523, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.8844246031746031, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.8903769841269841, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.894593253968254, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9015376984126984, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9064980158730159, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9084821428571429, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9114583333333334, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9136904761904762, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9184027777777778, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9208829365079365, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9228670634920635, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9233630952380952, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9260912698412699, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.015058155570537074, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.023172983404157556, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.04399050670668447, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.05929788987405212, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.08528244684484534, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.11036275646635235, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.14448733826534482, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.1796346759623169, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.22317881824583208, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.2874960067243209, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.35124623511295294, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.4073159052692463, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.4732645732212991, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.5407514131769217, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.5992627219445188, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.6472481625366485, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.6981436909464409, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.7411766851008531, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.7671903633839331, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.7879324292576755, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.8102269963390892, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.8261266440659905, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.8434465006888556, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.8543923315505774, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.8662240752315934, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.8745640707368956, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.8786456202568002, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.8865822677629795, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.8919347323576882, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.8939862611716133, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.8970053175351883, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.8998194437829389, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9054170028352191, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9086724117581103, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.911281671133588, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9114333806632186, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9142478331787154, "id_best": 48, "lr_best": 0.015, "wd_best": 0.05, "train/loss_best": 0.33865711607038973, "validation/loss_best": 0.36322763562202454, "validation/acc_best": 0.9260912698412699, "validation/f1_best": 0.9142478331787154} +{"epoch": 13, "train/lr": 0.00011886002410835478, "train/loss": 1.6128644239902497, "train/grad": 0.04794407311826945, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.8493994140625, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.836417236328125, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.8189752197265623, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.8051947021484374, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.7934173583984374, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.7787921142578127, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.7633148193359376, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.7463427734375, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.72427490234375, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.700577392578125, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.677357177734375, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.6418426513671873, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.607310791015625, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.5566748046875, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.5078009033203124, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.4602902221679686, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.39952880859375, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.3274880981445314, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.2463557434082033, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.170511016845703, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.0772901916503907, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.9818389892578125, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.8774308776855468, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.7684722900390626, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.659296989440918, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.5356208419799804, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.4317369556427002, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.3432591199874877, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.2329906272888183, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.116563262939453, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.0250701308250427, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.951281498670578, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.8639098972082138, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.7962695455551148, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.7265582180023193, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.6670678240060807, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.6120940434932709, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.5668583345413208, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.5242747013270855, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.47938389047980307, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.4500890326499939, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.4276586291193962, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.4025722114741802, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.3843512341380119, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.36686725080013277, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.3517803505063057, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.3413352488726378, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.33139676846563815, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.3251731285452843, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.010695764832198619, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.010121051631867885, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.009418984712101518, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.008981771238613873, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.008728054251987487, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008555126551073045, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.00847555157262832, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.008437052965164185, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.008407571190036833, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.008381689777597784, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.008359083402901889, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.008323821588419378, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.008288452981505543, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.008235622870270163, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.008180996377486736, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.00812802681233734, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.008056272561661899, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.007966694734059275, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.00786053367657587, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.007756235480774194, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.007621259540319443, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.00747590831713751, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.007307465437334031, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.007121705571189523, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.006925235295202583, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.00669004871044308, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0064789951173588635, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.006291437897598371, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.00604537833482027, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0057691947475541384, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0055403467814903705, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.005346814305521547, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.005107114028651267, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.004913905794965103, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.004705660954350606, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.004521799350623041, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.004345483524957672, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0041971897403709595, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.004053682202938944, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.00390360789722763, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0038086465653032063, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0037366292998194696, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0036595200351439415, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0036021825741045176, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0035548011562787, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.003518421559710987, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0035038725001504643, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0035156859376002103, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0035563659452600405, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.8443870544433594, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.8312175273895264, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.8135986328125, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.799598455429077, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.7877037525177, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.772934675216675, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.7572648525238037, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.740269422531128, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.7179815769195557, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.694317102432251, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.6710071563720703, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.6355693340301514, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.6010241508483887, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.550567865371704, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.501713991165161, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.454519510269165, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.3940703868865967, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.3224422931671143, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.2418406009674072, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.1666760444641113, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.0743868350982666, "validation/loss_021_lr6.1e-01_wd1.0e+00": 1.980076789855957, "validation/loss_022_lr7.2e-01_wd1.0e+00": 1.8769718408584595, "validation/loss_023_lr8.5e-01_wd1.0e+00": 1.7696316242218018, "validation/loss_024_lr1.0e+00_wd1.0e+00": 1.662221074104309, "validation/loss_025_lr1.2e+00_wd1.0e+00": 1.540563941001892, "validation/loss_026_lr1.4e+00_wd1.0e+00": 1.438489556312561, "validation/loss_027_lr1.6e+00_wd1.0e+00": 1.3516141176223755, "validation/loss_028_lr1.9e+00_wd1.0e+00": 1.243456482887268, "validation/loss_029_lr2.3e+00_wd1.0e+00": 1.1294047832489014, "validation/loss_030_lr2.7e+00_wd1.0e+00": 1.039852499961853, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.9677477478981018, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.8824288249015808, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.816417932510376, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.7482723593711853, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.6901134848594666, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.6365292072296143, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.5923376083374023, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.5506465435028076, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.5069243311882019, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.4782610535621643, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.4563167095184326, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.4320598542690277, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.41454508900642395, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.39757129549980164, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.3831525444984436, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.372954398393631, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.363435298204422, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.35740426182746887, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.17237103174603174, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.18055555555555555, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.20610119047619047, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.22420634920634921, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.25992063492063494, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.29216269841269843, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.33556547619047616, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.37475198412698413, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.41889880952380953, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.47197420634920634, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.5250496031746031, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.5701884920634921, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.6163194444444444, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.6634424603174603, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.6981646825396826, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.7247023809523809, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.7554563492063492, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.7867063492063492, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.8028273809523809, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.8209325396825397, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.8368055555555556, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.8489583333333334, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.8621031746031746, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.8720238095238095, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.8799603174603174, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.8876488095238095, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.8943452380952381, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9030257936507936, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.908234126984127, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9131944444444444, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9171626984126984, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9193948412698413, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9213789682539683, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9233630952380952, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9246031746031746, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9255952380952381, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9255952380952381, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.015856844150941102, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.025824357120618008, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.049893219467478336, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.06460411726126984, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.09321983017795621, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.11672150872519091, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.15198803174969688, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.1899676710732798, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.23676423449107348, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.30959723157328295, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.373474279629328, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.430823292045469, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.49319760103116617, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.563994509548683, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.6203709304173229, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.6633897003227159, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.70841796458373, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.7480123216901232, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.7661912703277386, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.789112177322789, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.8088000753305424, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.826368847900502, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.8424044050416809, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.8542994202638804, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.8640743268022368, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.8712961605323513, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.8794486239185852, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.8910351435089506, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.8965224961866173, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9016987656889979, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9070414399862679, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9110396261923273, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9130598573844194, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9144984250562096, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9155641157525071, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9167654087070364, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9162366006072753, "id_best": 47, "lr_best": 0.012899999999999998, "wd_best": 0.05, "train/loss_best": 0.33139676846563815, "validation/loss_best": 0.363435298204422, "validation/acc_best": 0.9255952380952381, "validation/f1_best": 0.9167654087070364} +{"epoch": 14, "train/lr": 8.9081919031238e-05, "train/loss": 1.6013922268152236, "train/grad": 0.04960410559549928, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.846317138671875, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.8336077880859376, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.816583251953125, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.8029736328125, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.791357421875, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.7765966796875, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.7607196044921873, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.7433026123046873, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.7204345703125, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.6960760498046876, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.671971435546875, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.6355621337890627, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.5998114013671874, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.547840576171875, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.49762939453125, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.448999328613281, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.3869277954101564, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.3133639526367187, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.2306248474121095, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.153585968017578, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.0589286041259767, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.962596664428711, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.8571407318115234, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.7477507781982422, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.6381353950500488, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.5145113277435303, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.4108477306365967, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.3228227281570435, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.2133277940750122, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.0979442667961121, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.0075083601474761, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.9345902180671692, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.848437425494194, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.7816401544213295, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.7128936710953713, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.6540371480584145, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.5997129520773887, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.5549911190569401, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.5129074142873287, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.46870808288455007, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.4397488524019718, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.4176851683855057, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.3929271876811981, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.3748177710175514, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.3573409593105316, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.342125873118639, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.33166773319244386, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.3220651038736105, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.3161244038492441, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.010800776288378984, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.010237434934824706, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.009565288340672851, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.009154012750368565, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.00892247215146199, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008764762149658054, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.008691331518348307, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.008652973037678749, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.008622763764578848, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.008598060812801123, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.008575415415689349, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.008541156714782118, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.008508131371345371, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.008457125849090516, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.008405954116024078, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.008355859518051147, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.008289155401289463, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.008206462482921778, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.008107385076582431, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.00801164638949558, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.007888109090272337, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.007755665553268045, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0076017082040198145, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0074334563664160665, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.007253383740317076, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.007036451839376241, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.006840915835928172, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0066656491509638725, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.006430356621276587, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.00616128389025107, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.005933539721881971, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.005738024187739939, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.005489981283899397, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.005284645193023607, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.005060305782826617, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.004856075610732659, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0046568747831042855, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0044869950320571665, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0043225686985533685, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.004150075302459299, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.004037631407845766, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.003955191132845357, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.003860401517013088, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.003796050464734435, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0037388076627394183, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.003704468120704405, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.003697620408493094, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0037253243272425606, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.00376820360426791, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.8410868644714355, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.828026056289673, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.8105719089508057, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.796717643737793, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.7848260402679443, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.7699267864227295, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.7538857460021973, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.7363572120666504, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.7134830951690674, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.6890709400177, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.664989471435547, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.628601551055908, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.592984437942505, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.5411107540130615, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.490954637527466, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.4425458908081055, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.3806259632110596, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.307425022125244, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.2251174449920654, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.148599863052368, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.054828405380249, "validation/loss_021_lr6.1e-01_wd1.0e+00": 1.9592863321304321, "validation/loss_022_lr7.2e-01_wd1.0e+00": 1.8549872636795044, "validation/loss_023_lr8.5e-01_wd1.0e+00": 1.7469671964645386, "validation/loss_024_lr1.0e+00_wd1.0e+00": 1.6389204263687134, "validation/loss_025_lr1.2e+00_wd1.0e+00": 1.517025351524353, "validation/loss_026_lr1.4e+00_wd1.0e+00": 1.4150875806808472, "validation/loss_027_lr1.6e+00_wd1.0e+00": 1.328607439994812, "validation/loss_028_lr1.9e+00_wd1.0e+00": 1.2209943532943726, "validation/loss_029_lr2.3e+00_wd1.0e+00": 1.1078941822052002, "validation/loss_030_lr2.7e+00_wd1.0e+00": 1.0193603038787842, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.9481208324432373, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.8640777468681335, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.7991907000541687, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.7325329184532166, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.6757796406745911, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.6235952973365784, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.5805339217185974, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.5401827096939087, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.49804553389549255, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.47053298354148865, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.4495065212249756, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.4263371527194977, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.4094937741756439, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.39341336488723755, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.37955009937286377, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.3700891435146332, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.3609313666820526, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.3549351692199707, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.17336309523809523, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.18377976190476192, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.2105654761904762, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.2326388888888889, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.26240079365079366, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.2986111111111111, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.3420138888888889, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.3821924603174603, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.4273313492063492, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.47767857142857145, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.5282738095238095, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.5731646825396826, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.623015873015873, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.6721230158730159, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.7056051587301587, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.7306547619047619, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.7626488095238095, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.7901785714285714, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.808531746031746, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.8239087301587301, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.8407738095238095, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.8536706349206349, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.8665674603174603, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.8767361111111112, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.8861607142857143, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.8940972222222222, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.8998015873015873, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9050099206349206, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9109623015873016, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9141865079365079, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9164186507936508, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9176587301587301, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9208829365079365, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.921875, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9228670634920635, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9236111111111112, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.925843253968254, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.017190862587710125, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.02949541469533519, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.053652195486021126, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.0720901533178667, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.09484255504523767, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.12152638689792662, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.1568170514659036, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.19858447168020965, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.2517411396894219, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.31833977974744143, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.3776294481452451, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.4333628649340977, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.5031977277547303, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.578471691246868, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.632513519230236, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.6696349704097673, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.7140428015949475, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.7495160162360518, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.774161717404836, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.7905197724076284, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.8134312149651424, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.8286995560205991, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.8419534627656697, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.8556104569327542, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.8663792809192347, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.8767286214224348, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.8837829190495855, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.8905142170724493, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.8971510090624428, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9001436961871713, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9024691634871835, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9047549598131148, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9094062253689579, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9110642969055454, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9124799547811648, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.913713460553474, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.915534779813364, "id_best": 48, "lr_best": 0.015, "wd_best": 0.05, "train/loss_best": 0.3161244038492441, "validation/loss_best": 0.3549351692199707, "validation/acc_best": 0.925843253968254, "validation/f1_best": 0.915534779813364} +{"epoch": 15, "train/lr": 6.196799573888289e-05, "train/loss": 1.591017426252365, "train/grad": 0.0476881115604192, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.8426171875, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.8299822998046875, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.8131427001953124, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.799510498046875, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.7877435302734375, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.7726556396484376, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.7564654541015625, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.7384149169921876, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.714783935546875, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.689693603515625, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.6648638916015623, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.627288818359375, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.5905853271484376, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.5371234130859377, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.4854196166992186, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.435610656738281, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.372003479003906, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.2966455078125, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.212217254638672, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.1337907409667967, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.0378231811523437, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.9401368713378906, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.833736915588379, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.723693199157715, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.6139038276672364, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.4903110980987548, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.3872238159179688, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.2998766136169433, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.1915501689910888, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.0778795409202575, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.9890354108810425, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.9176907849311828, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.8335455739498139, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.7684714779257774, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.7017084610462189, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.6447422370314598, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.5922181582450867, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.5489428490400314, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.5083021104335785, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.46554567620158194, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.43749283865094185, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.4160140477120876, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.39201718717813494, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.37457564800977705, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.35765303440392016, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.3430379195511341, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.3328061823546886, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.3229481963068247, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.31641382962465286, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.01036795719526708, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.009819173444993794, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.009189410870894789, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.008826483297161758, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.008637550717685372, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008520166692323982, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.008468805262818933, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.008441267812158912, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.008415885302238166, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.008392560433130712, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.008370603721123188, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.008335073892958463, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.008299749717116356, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.008245607167482375, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.008193056874442845, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.008139446313725785, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.008068768944358453, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.007979856447782367, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.007874741913983598, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.007771714066620916, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.007638631132431328, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.007495927250711247, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.007331273994641379, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.007149531270842999, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.006958440548041836, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.006727076063398272, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.006521149328909815, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.006335852694464847, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.006089599882252514, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.005811341864755377, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0055774751072749495, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.005378822189522907, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.005130636867834255, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.004929581849137321, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.004712426625192165, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.004517837758176029, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.004332979813916608, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.004175129137001932, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.004021333996206522, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.003855797970900312, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0037468382832594217, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0036626821151003242, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0035694153362419456, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0035054564999882133, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.003445741534233093, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.003400750492583029, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0033771436975803225, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0033614315709564833, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0033609743014676495, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.838895797729492, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.825939178466797, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.8086297512054443, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.7948238849639893, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.7829205989837646, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.767794132232666, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.7515146732330322, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.733670234680176, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.7103047370910645, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.6853818893432617, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.6607718467712402, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.6236538887023926, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.587397575378418, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.5345101356506348, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.4835221767425537, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.4342613220214844, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.371385097503662, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.2970499992370605, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.2136995792388916, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.136277675628662, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.0414910316467285, "validation/loss_021_lr6.1e-01_wd1.0e+00": 1.9451402425765991, "validation/loss_022_lr7.2e-01_wd1.0e+00": 1.8401920795440674, "validation/loss_023_lr8.5e-01_wd1.0e+00": 1.731616497039795, "validation/loss_024_lr1.0e+00_wd1.0e+00": 1.6232786178588867, "validation/loss_025_lr1.2e+00_wd1.0e+00": 1.501366376876831, "validation/loss_026_lr1.4e+00_wd1.0e+00": 1.3996444940567017, "validation/loss_027_lr1.6e+00_wd1.0e+00": 1.3133440017700195, "validation/loss_028_lr1.9e+00_wd1.0e+00": 1.2063149213790894, "validation/loss_029_lr2.3e+00_wd1.0e+00": 1.0942745208740234, "validation/loss_030_lr2.7e+00_wd1.0e+00": 1.0065951347351074, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.9361060857772827, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.853209376335144, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.7891741991043091, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.7234771251678467, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.6674845218658447, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.6159217953681946, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.5734700560569763, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.5335150957107544, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.49159055948257446, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.4641592800617218, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.44330596923828125, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.42010486125946045, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.4032590389251709, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.38701117038726807, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.3727777302265167, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.36286845803260803, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.3533056378364563, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.34730106592178345, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.1708829365079365, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.17410714285714285, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.18774801587301587, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.21378968253968253, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.2408234126984127, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.2718253968253968, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.30952380952380953, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.35466269841269843, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.3943452380952381, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.4461805555555556, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.4962797619047619, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.5466269841269841, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.5922619047619048, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.6351686507936508, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.6830357142857143, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.7180059523809523, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.7413194444444444, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.7710813492063492, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.7973710317460317, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.816468253968254, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.830109126984127, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.8432539682539683, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.8566468253968254, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.8675595238095238, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.8797123015873016, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.8861607142857143, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.8943452380952381, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.8998015873015873, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9077380952380952, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9099702380952381, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9141865079365079, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9169146825396826, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9191468253968254, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9228670634920635, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9255952380952381, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9275793650793651, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9293154761904762, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9295634920634921, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.014154901097986342, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.018060881183419825, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.03369051698022631, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.05578366997479446, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.07812367474451316, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.10060654751606389, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.1304863848724982, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.16779153562926408, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.20993337587282093, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.26942693914710053, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.3365837664790135, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.39453553875484965, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.452765338159365, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.5110846784595182, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.5862751826825738, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.646317973288839, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.6805069757575545, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.7222313675960752, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.7557299337535605, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.7797988046856194, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.7963495092805507, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.8129442482929784, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.8306170060166986, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.8437915660597144, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.8587545744351007, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.8669268827219072, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.8777992358586462, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.8844696627148048, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.8947601182996264, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.897616658314829, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9020346146858047, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9053917525196056, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9091579060344619, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9134254633856747, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9175261197251524, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9185960551540431, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9202357711432431, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9202239353776765, "id_best": 48, "lr_best": 0.015, "wd_best": 0.05, "train/loss_best": 0.31641382962465286, "validation/loss_best": 0.34730106592178345, "validation/acc_best": 0.9295634920634921, "validation/f1_best": 0.9202239353776765} +{"epoch": 16, "train/lr": 3.870405029380728e-05, "train/loss": 1.5806732285022735, "train/grad": 0.047251280061900616, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.838170166015625, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.825286865234375, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.8082110595703127, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.79428955078125, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.7824169921875, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.767110595703125, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.75058837890625, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.732171630859375, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.708250732421875, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.682730712890625, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.657496337890625, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.619354248046875, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.5820697021484373, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.5276998901367187, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.475369873046875, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.4248040771484374, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.3602639770507814, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.2840615844726564, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.1986711120605467, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.119373321533203, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.0224222564697265, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.9239698791503905, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.8171240234375, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.706418571472168, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.596332778930664, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.4726994800567628, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.3697170829772949, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.2826421785354614, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.1748883676528932, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.0621394205093384, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.9742629408836365, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.9036424368619919, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.8205944448709488, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.7564269113540649, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.6905721470713615, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.6343996897339821, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.5825265988707542, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.5398047123849392, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.4996956741809845, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.45741762533783914, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.42970793068408963, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.4085190638899803, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.38474285408854486, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.3674332876503468, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.35059137374162674, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.3358990934491157, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.32559815891087057, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.3155688279122114, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.30884092681109904, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.010418364380020648, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.009867873827461153, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.009235018223989755, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.008869616740848869, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.0086748182377778, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008551529685501009, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.008493123701773584, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.00845971259754151, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.008429572861641645, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.008402266667690127, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.008374999987427145, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.008333593874704092, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.008293402595445514, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.008231026423163711, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.008170337351039052, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.008109211954288185, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.008027833648957311, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.007927404008805752, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.007808761133346707, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.007693637975025922, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.00754590927157551, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.007389415842480957, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.007210848587565124, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0070167748373933135, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.006814117168541998, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.006573183475993573, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.006361423134803772, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.006172287636436522, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.00592585704755038, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.005650614339392632, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.00542153264512308, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.005228519709780812, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.004988427895586938, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.004793131174519658, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.004581082402728498, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.004391376187559217, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.004207649210002273, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.004049833971075714, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.003897250152658671, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.003730718666920438, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0036186372360680254, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.00353231567540206, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.003432471083942801, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0033595400844933466, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.003288699564873241, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0032263240619795396, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0031873417022870855, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.003153169209836051, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.003138259071856737, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.8375349044799805, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.824603796005249, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.8074214458465576, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.793626308441162, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.7816836833953857, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.766512155532837, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.7500157356262207, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.7319812774658203, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.7082831859588623, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.6830973625183105, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.65818190574646, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.6206295490264893, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.5838983058929443, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.5303852558135986, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.478827953338623, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.4291250705718994, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.3656117916107178, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.2905380725860596, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.206437587738037, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.12850284576416, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.0331008434295654, "validation/loss_021_lr6.1e-01_wd1.0e+00": 1.9362825155258179, "validation/loss_022_lr7.2e-01_wd1.0e+00": 1.8308583498001099, "validation/loss_023_lr8.5e-01_wd1.0e+00": 1.7219349145889282, "validation/loss_024_lr1.0e+00_wd1.0e+00": 1.613477349281311, "validation/loss_025_lr1.2e+00_wd1.0e+00": 1.4915331602096558, "validation/loss_026_lr1.4e+00_wd1.0e+00": 1.3897606134414673, "validation/loss_027_lr1.6e+00_wd1.0e+00": 1.3037079572677612, "validation/loss_028_lr1.9e+00_wd1.0e+00": 1.1972296237945557, "validation/loss_029_lr2.3e+00_wd1.0e+00": 1.0854297876358032, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.9982420206069946, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.9282845854759216, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.8459786176681519, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.7825232744216919, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.7173545360565186, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.6618921160697937, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.6105906963348389, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.5685125589370728, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.528978168964386, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.4872995913028717, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.46011820435523987, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.43931445479393005, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.4161827862262726, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.39941537380218506, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.38316014409065247, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.36915236711502075, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.3593251407146454, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.3496800363063812, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.34325990080833435, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.17113095238095238, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.17435515873015872, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.18948412698412698, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.21502976190476192, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.24231150793650794, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.27331349206349204, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.30952380952380953, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.3568948412698413, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.3950892857142857, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.4466765873015873, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.49603174603174605, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.546875, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.5930059523809523, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.6383928571428571, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.6815476190476191, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.7177579365079365, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.7423115079365079, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.769593253968254, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.7973710317460317, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.8167162698412699, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.8296130952380952, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.84375, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.857390873015873, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.8695436507936508, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.8794642857142857, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.8871527777777778, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.8931051587301587, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9005456349206349, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9087301587301587, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9136904761904762, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9166666666666666, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9193948412698413, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9211309523809523, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.923859126984127, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9243551587301587, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9263392857142857, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9278273809523809, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9298115079365079, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.014426116135401169, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.018318999090360156, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.03544822171708516, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.05639280203833265, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.07869785461198962, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.10139027558089547, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.13030769229811365, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.1701773545724737, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.21068621041320565, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.2712365475535769, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.337970641998855, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.39655116594369133, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.4546203606245046, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.5190373906181718, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.5873124279514402, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.646259337939807, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.685223392310047, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.723069671554616, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.7603533702134653, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.7829316137281908, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.7994606558178065, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.8167927869435972, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.8333876150749975, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.8478764331598737, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.8597961176462017, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.8697852520783661, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.8766009241710416, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.8863655127998863, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.896603088648212, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9020333916408899, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9062363877605626, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.909287428484227, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9118137727002149, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9145066937912557, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9146845984107692, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9172470556793639, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9188465228099804, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9212748984569333, "id_best": 48, "lr_best": 0.015, "wd_best": 0.05, "train/loss_best": 0.30884092681109904, "validation/loss_best": 0.34325990080833435, "validation/acc_best": 0.9298115079365079, "validation/f1_best": 0.9212748984569333} +{"epoch": 17, "train/lr": 2.030750443206766e-05, "train/loss": 1.5805279278755189, "train/grad": 0.047697148080915214, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.8396728515625, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.8270611572265625, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.8102392578125, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.79660888671875, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.7847247314453125, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.76944091796875, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.7526947021484376, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.7342095947265626, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.7101104736328123, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.68435546875, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.65883544921875, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.6204864501953127, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.5829205322265625, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.5282577514648437, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.4755853271484374, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.4247250366210937, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.3599063110351564, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.2832627868652344, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.1975091552734374, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.118033142089844, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.0207347869873047, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.922033157348633, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.8148693084716796, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.7040879821777344, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.5939485931396484, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.470390691757202, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.3675662469863892, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.280717453956604, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.173201003074646, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.0608573210239411, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.9732013857364654, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.9029440486431122, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.8202058428525925, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.7563055527210235, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.6906227360665799, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.6345358522236347, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.5828415839374066, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.5401380370557308, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.4999826900660992, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.4575775134563446, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.4296990768611431, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.4083506965637207, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.38443145498633385, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.3668614765256643, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.34985833153128626, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.33495206892490387, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.3244984168559313, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.3142966388165951, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.30751962676644323, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.010306299545336515, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.009779023670125753, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.009192400681786238, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.00886842392385006, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.008707148435059936, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.00861201758729294, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.008570020806510002, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.00854512041201815, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.008521017907187343, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.008495845519937574, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.008471176763996481, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.008433493878692388, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.008394444917794317, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.008337245911825449, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.008278610613197089, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.008219735396560282, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.00814281357685104, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.00804625396616757, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.007931140426080674, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.007819691172335297, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.00767575369682163, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.007521600092295557, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.007345294542610645, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.007151196079794317, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.006946674340870231, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.006703619039617479, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.006486053573898971, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.00629238071036525, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.006038561265449971, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.005753305406542495, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.005516065149568022, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.005314717903966084, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.005065220979740843, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.004861024307319895, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.004641656208550557, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.004444621367147192, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.004254009353462607, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0040905927715357395, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.003931069775717333, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.003755635878769681, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0036350972077343613, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.003542042727349326, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0034354093600995838, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.003356362269259989, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0032786335970740764, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0032126222585793585, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0031685456732520835, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.003128046820056625, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.003108397156465799, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.8367977142333984, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.8239312171936035, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.80678391456604, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.7929461002349854, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.781018018722534, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.765803337097168, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.7492361068725586, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.731076717376709, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.7072455883026123, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.6818931102752686, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.656827449798584, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.6190004348754883, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.5820889472961426, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.528285264968872, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.476348638534546, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.426340103149414, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.362521171569824, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.2871904373168945, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.2027435302734375, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.124483585357666, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.0286738872528076, "validation/loss_021_lr6.1e-01_wd1.0e+00": 1.9316104650497437, "validation/loss_022_lr7.2e-01_wd1.0e+00": 1.8259671926498413, "validation/loss_023_lr8.5e-01_wd1.0e+00": 1.716871976852417, "validation/loss_024_lr1.0e+00_wd1.0e+00": 1.6082531213760376, "validation/loss_025_lr1.2e+00_wd1.0e+00": 1.4862929582595825, "validation/loss_026_lr1.4e+00_wd1.0e+00": 1.3846534490585327, "validation/loss_027_lr1.6e+00_wd1.0e+00": 1.298729419708252, "validation/loss_028_lr1.9e+00_wd1.0e+00": 1.192299723625183, "validation/loss_029_lr2.3e+00_wd1.0e+00": 1.0808119773864746, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.9938415288925171, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.924117386341095, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.8420553207397461, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.7788072824478149, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.7139622569084167, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.6587057113647461, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.6077312231063843, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.5659058094024658, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.5264504551887512, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.4850899279117584, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.4578719735145569, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.4372282922267914, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.4139854907989502, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.39709585905075073, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.3807503283023834, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.36650434136390686, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.3564700782299042, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.3468782305717468, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.3403211236000061, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.17113095238095238, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.1746031746031746, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.1909722222222222, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.2160218253968254, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.24379960317460317, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.27554563492063494, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.3117559523809524, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.359375, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.39657738095238093, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.44816468253968256, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.49851190476190477, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.5505952380952381, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.5959821428571429, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.6398809523809523, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.6842757936507936, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.7192460317460317, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.7457837301587301, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.7728174603174603, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.7996031746031746, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.8179563492063492, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.8318452380952381, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.8454861111111112, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.8578869047619048, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.8707837301587301, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.8807043650793651, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.888640873015873, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.8943452380952381, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9020337301587301, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9094742063492064, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9122023809523809, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9171626984126984, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9203869047619048, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9226190476190477, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.925843253968254, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9288194444444444, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9305555555555556, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9310515873015873, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9317956349206349, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.014426116135401169, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.018668139455646292, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.036850471712063404, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.05708532095832985, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.08039175085205784, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.10296249816694941, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.13271492627507064, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.17375879904439961, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.21220494444858382, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.2721884394527043, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.34039479566861613, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.4006075804492284, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.4579614427823658, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.5225309857879374, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.5923402186950169, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.6494030954003241, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.6908267232253686, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.7279697714474653, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.7626163396959256, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.7836633803933646, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.8016751713815854, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.8183164795542135, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.8332141313662215, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.8485275830596909, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.8608955742646716, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.8694728306748474, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.8774395392585568, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.8870084867668583, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.8967331193093266, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9002141515478221, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9066847125223046, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9099910288888304, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9128543715394815, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9165892354149062, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9204164986219967, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9226809745184584, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.92300081691692, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9241788149769077, "id_best": 48, "lr_best": 0.015, "wd_best": 0.05, "train/loss_best": 0.30751962676644323, "validation/loss_best": 0.3403211236000061, "validation/acc_best": 0.9317956349206349, "validation/f1_best": 0.9241788149769077} +{"epoch": 18, "train/lr": 7.5829098008590064e-06, "train/loss": 1.582263160943985, "train/grad": 0.047667269948869946, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.838697509765625, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.8259783935546876, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.8090338134765624, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.7953424072265625, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.7835430908203125, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.7681658935546873, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.751500244140625, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.733016357421875, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.70902099609375, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.6832745361328123, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.6578802490234374, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.619488525390625, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.5820611572265624, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.527471618652344, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.4748831176757813, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.4242791748046875, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.3595956420898436, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.2831280517578123, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.1976362609863282, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.118429412841797, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.021470184326172, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.9232979583740235, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.8164804840087891, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.7061779403686523, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.5965269660949708, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.4733971977233886, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.3708132743835448, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.2842057371139526, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.1769119834899902, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.0646720480918885, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.9770424699783326, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.9068203926086426, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.8240187233686447, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.7601781022548676, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.6945175653696061, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.6385067600011826, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.5868819561600686, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.5443123497068882, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.5041936637461185, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.4618818251788616, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.43405996724963186, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.412801970243454, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.3887566919624805, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.37116572737693787, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.35398493021726607, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.3388971894234419, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.3282105005532503, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.31769060268998145, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.3105949993431568, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.01039808030007407, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.009863156736828386, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.009260535524226725, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.008925615488551556, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.008755831697490066, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008651023716665804, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.00860311875352636, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.008575122028123588, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.00854713911889121, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.008519779045600443, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.008494069913867862, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.008453637205529958, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.008414303122553974, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.008355420776642858, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.008295809063129126, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.00823752264957875, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.008158086666371673, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.00806104897055775, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.00794564865063876, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.007834013821557163, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.007689097344409674, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.007534583590459078, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.007357202460989356, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.007161607558373362, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.00695499918423593, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.006706402087584138, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.006484019469935447, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.006285557475639508, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.006021145289996639, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0057245888584293424, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0054765371873509135, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.005266604488715529, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.005005565118044615, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.004793006385443732, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.004563265171600506, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0043574940413236615, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.004158366792835295, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.003987445839447901, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.003820214706938714, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.003637819968862459, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.003514001626172103, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0034177149744937197, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0033053938183002173, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0032224826671881602, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0031394325784640385, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0030667545465985313, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.003014252952998504, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0029616956022800876, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.002928026695153676, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.836533546447754, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.8236916065216064, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.8065643310546875, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.7927439212799072, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.780771017074585, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.7655346393585205, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.7489147186279297, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.730769634246826, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.706864595413208, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.6814303398132324, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.6563377380371094, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.6183948516845703, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.581392526626587, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.527437448501587, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.4754602909088135, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.4253923892974854, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.3613970279693604, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.285872220993042, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.2013099193573, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.1228883266448975, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.027041435241699, "validation/loss_021_lr6.1e-01_wd1.0e+00": 1.9298509359359741, "validation/loss_022_lr7.2e-01_wd1.0e+00": 1.8241854906082153, "validation/loss_023_lr8.5e-01_wd1.0e+00": 1.71487295627594, "validation/loss_024_lr1.0e+00_wd1.0e+00": 1.6062873601913452, "validation/loss_025_lr1.2e+00_wd1.0e+00": 1.4843782186508179, "validation/loss_026_lr1.4e+00_wd1.0e+00": 1.382699966430664, "validation/loss_027_lr1.6e+00_wd1.0e+00": 1.2967309951782227, "validation/loss_028_lr1.9e+00_wd1.0e+00": 1.1902997493743896, "validation/loss_029_lr2.3e+00_wd1.0e+00": 1.0788837671279907, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.9920416474342346, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.9223790168762207, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.8403680324554443, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.7771825194358826, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.7123685479164124, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.6572206020355225, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.6063210368156433, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.5644537806510925, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.5251648426055908, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.48383834958076477, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.4566371738910675, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.436017781496048, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.4127791225910187, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.3959357440471649, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.37958914041519165, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.3653428256511688, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.3553517758846283, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.34558433294296265, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.339051216840744, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.17113095238095238, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.1746031746031746, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.19146825396825398, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.21626984126984128, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.24479166666666666, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.27628968253968256, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.3132440476190476, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.3603670634920635, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.3968253968253968, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.4494047619047619, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.5, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.5503472222222222, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.5964781746031746, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.6413690476190477, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.683531746031746, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.7194940476190477, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.7440476190476191, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.7723214285714286, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.7976190476190477, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.816468253968254, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.8313492063492064, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.8439980158730159, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.8586309523809523, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.8712797619047619, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.8797123015873016, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.8881448412698413, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.894593253968254, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9007936507936508, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9097222222222222, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9154265873015873, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.917906746031746, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9206349206349206, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9228670634920635, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9265873015873016, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9288194444444444, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9300595238095238, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9310515873015873, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9320436507936508, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.014426116135401169, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.018668139455646292, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.03727028215687981, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.05718166454762607, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.08089771890504285, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.10357545498301801, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.1338183731900302, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.17446397347819398, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.21208104634008088, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.2738641460988397, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.34204231012987724, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.40035456800488894, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.45944040242082657, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.5240957145749015, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.5913387537800551, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.6498182948675526, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.6870868544544664, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.7265974237436078, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.7589066811812408, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.7823078106861523, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.8010308075348801, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.8168791193352957, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.8339704523173856, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.849143608465984, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.8600874306214834, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.8698534560428098, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.8780342517930058, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.8856492048874086, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.8975858082363178, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9041775158805253, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9068903391900209, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9096142641532843, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9134138857313291, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9177157764650423, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9205526467812769, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.922373611636546, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.923610477186648, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9251783585297395, "id_best": 48, "lr_best": 0.015, "wd_best": 0.05, "train/loss_best": 0.3105949993431568, "validation/loss_best": 0.339051216840744, "validation/acc_best": 0.9320436507936508, "validation/f1_best": 0.9251783585297395} +{"epoch": 19, "train/lr": 1.0867618231465446e-06, "train/loss": 1.5740928864479065, "train/grad": 0.047413062267005444, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.83604736328125, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.82305908203125, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.8056732177734376, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.7915484619140627, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.779453125, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.7638604736328123, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.746895751953125, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.72817138671875, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.7038031005859375, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.6778533935546873, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.6521343994140625, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.6134527587890624, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.5756231689453126, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.520589599609375, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.467437438964844, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.416416015625, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.351163635253906, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.2740684509277345, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.187957000732422, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.108174133300781, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.0106441497802736, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.9119435882568359, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.804627685546875, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.6940179061889649, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.5840763854980469, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.460862054824829, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.358284730911255, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.2717724084854125, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.1646372818946837, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.052664760351181, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.9654059791564942, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.895393637418747, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.8130284577608109, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.7494541126489639, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.6842903307080269, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.6286954760551453, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.5774240854382515, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.5352774214744568, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.49552423000335694, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.4537521328032017, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.42629739120602606, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.4052499929070473, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.38157128408551216, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.36427946224808694, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.34733485788106916, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.33250364013016226, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.32196582183241845, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.3116325479745865, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.3045592404901981, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.01038947055581957, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.009849340340588241, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.009237482035532594, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.008893658872693777, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.008716791642364115, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008605535519309341, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.008553486247546972, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.008521892661228776, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.008493368581403047, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.00846565272193402, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.008438900886103511, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.00839851052267477, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.008358326377347111, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.0082973539410159, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.008236442666966468, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.008175965978298337, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.008095244937576353, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.007994894478470087, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.00787772012874484, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.007762599033303559, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.007615491538308561, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.007458602141123265, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.007279141081962735, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.007084097557235509, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.006877981713041663, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.006631458294577897, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.006412024761084467, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.006216146384831518, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.00595805868273601, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.005669666932662949, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.005430043212836608, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.005227412430103868, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.004977475944906473, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.004774147755233571, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.004556884352350608, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.004361969433957711, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.004173651782330126, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.00401303012156859, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.003853969549527392, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0036805198655929417, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0035619674785993993, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.003468080441234633, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0033592058112844824, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.003276772488607094, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0031952822231687606, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.003121237554005347, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0030687447811942547, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0030155624612234534, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.002978730537579395, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.8364884853363037, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.8236441612243652, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.8065381050109863, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.792701482772827, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.780738592147827, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.7654995918273926, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.7488787174224854, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.7307252883911133, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.706799030303955, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.681344985961914, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.6562674045562744, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.618319034576416, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.581296920776367, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.5273492336273193, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.475314140319824, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.425225257873535, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.36120343208313, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.2856976985931396, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.2011096477508545, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.1226980686187744, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.026808738708496, "validation/loss_021_lr6.1e-01_wd1.0e+00": 1.9295834302902222, "validation/loss_022_lr7.2e-01_wd1.0e+00": 1.8239166736602783, "validation/loss_023_lr8.5e-01_wd1.0e+00": 1.7146728038787842, "validation/loss_024_lr1.0e+00_wd1.0e+00": 1.6060326099395752, "validation/loss_025_lr1.2e+00_wd1.0e+00": 1.4840483665466309, "validation/loss_026_lr1.4e+00_wd1.0e+00": 1.3823894262313843, "validation/loss_027_lr1.6e+00_wd1.0e+00": 1.296452283859253, "validation/loss_028_lr1.9e+00_wd1.0e+00": 1.190017580986023, "validation/loss_029_lr2.3e+00_wd1.0e+00": 1.0786181688308716, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.9917905926704407, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.9221261739730835, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.8401496410369873, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.776968240737915, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.7122301459312439, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.6570141315460205, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.6061716079711914, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.5643526315689087, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.5250211358070374, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.483786016702652, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.45663848519325256, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.43592536449432373, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.4127614200115204, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.39594897627830505, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.379524290561676, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.365272581577301, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.3552013635635376, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.3454511761665344, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.3388846814632416, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.17113095238095238, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.1746031746031746, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.19196428571428573, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.21626984126984128, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.24454365079365079, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.2767857142857143, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.31374007936507936, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.3603670634920635, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.3975694444444444, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.4494047619047619, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.49975198412698413, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.5498511904761905, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.5967261904761905, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.6408730158730159, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.6837797619047619, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.7194940476190477, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.7445436507936508, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.7725694444444444, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.7971230158730159, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.8169642857142857, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.8315972222222222, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.8444940476190477, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.8581349206349206, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.8712797619047619, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.8799603174603174, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.8883928571428571, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.894593253968254, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9010416666666666, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9094742063492064, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9151785714285714, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9181547619047619, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9206349206349206, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9233630952380952, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9268353174603174, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9283234126984127, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9308035714285714, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9312996031746031, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9317956349206349, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.014426116135401169, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.018668139455646292, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.037748955019390434, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.05718166454762607, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.08073208743506356, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.10429027139554738, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.134214090708693, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.17446397347819398, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.2128752299682927, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.2738920455650231, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.3418257126816682, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.3994596516581457, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.45960050571865774, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.5238320105161333, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.5916327667771951, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.6499177139620674, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.6878515586078965, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.7270601317177551, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.7585312141992739, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.7831289155509286, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.8015095406920251, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.8176090336538031, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.8328611990581651, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.8493383344672916, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.8599325596851166, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.8699856877675042, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.8783925272624027, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.8855634682509745, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.897263452529675, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9039351365344563, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.907070451867422, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9092061707991442, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9133169651719781, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9177436558343621, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9190320873105987, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9220885205412149, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9232880846690383, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9241029616907658, "id_best": 48, "lr_best": 0.015, "wd_best": 0.05, "train/loss_best": 0.3045592404901981, "validation/loss_best": 0.3388846814632416, "validation/acc_best": 0.9317956349206349, "validation/f1_best": 0.9241029616907658} diff --git a/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__attn/config.yaml b/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__attn/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..49dba07e4e7a8e0fd638b754f634594d3ae6feab --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__attn/config.yaml @@ -0,0 +1,96 @@ +output_root: experiments/decoders/output +name_prefix: eval_probe +remote_root: null +notes: decoder ablations crossreg_reg4; eval v2 (hcpya_task21 reg attn) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +dataset_kwargs: {} +classifier_kwargs: + embed_dim: null + dropout: 0.0 + xavier_init: false + norm: false +lr_scale_grid: +- 0.02 +- 0.023 +- 0.028 +- 0.033 +- 0.038 +- 0.045 +- 0.053 +- 0.062 +- 0.074 +- 0.087 +- 0.1 +- 0.12 +- 0.14 +- 0.17 +- 0.2 +- 0.23 +- 0.27 +- 0.32 +- 0.38 +- 0.44 +- 0.52 +- 0.61 +- 0.72 +- 0.85 +- 1 +- 1.2 +- 1.4 +- 1.6 +- 1.9 +- 2.3 +- 2.7 +- 3.1 +- 3.7 +- 4.3 +- 5.1 +- 6 +- 7.1 +- 8.3 +- 9.8 +- 12 +- 14 +- 16 +- 19 +- 22 +- 26 +- 31 +- 36 +- 43 +- 50 +wd_scale_grid: +- 1.0 +num_workers: 8 +prefetch_factor: null +balanced_sampling: false +epochs: 20 +steps_per_epoch: 200 +batch_size: 64 +accum_iter: 2 +lr: 0.0003 +warmup_epochs: 5 +no_decay: false +weight_decay: 0.05 +clip_grad: 1.0 +metrics: +- acc +- f1 +cv_metric: acc +early_stopping: true +amp: true +device: cuda +seed: 4466 +debug: false +wandb: false +wandb_entity: null +wandb_project: fMRI-fm-eval +name: decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__attn +model: flat_mae +representation: reg +classifier: attn +dataset: hcpya_task21 +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__attn +remote_dir: null diff --git a/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__attn/eval_log.json b/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__attn/eval_log.json new file mode 100644 index 0000000000000000000000000000000000000000..6687ae39714abd8bb07a2ecc4e0a9814353ccf36 --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__attn/eval_log.json @@ -0,0 +1 @@ +{"eval/epoch": 8, "eval/id_best": 23, "eval/lr_best": 0.00025499999999999996, "eval/wd_best": 0.05, "eval/train/loss": 0.035422105342149734, "eval/train/acc": 0.9938417811463761, "eval/train/acc_std": 0.0005515012840441916, "eval/train/f1": 0.9936347787478754, "eval/train/f1_std": 0.00062564819864731, "eval/validation/loss": 0.06714221090078354, "eval/validation/acc": 0.9818948412698413, "eval/validation/acc_std": 0.001929209224017128, "eval/validation/f1": 0.9799099655473743, "eval/validation/f1_std": 0.0024497399729675874, "eval/test/loss": 0.08606162667274475, "eval/test/acc": 0.9742063492063492, "eval/test/acc_std": 0.0022554523674217113, "eval/test/f1": 0.968385237238162, "eval/test/f1_std": 0.0030263738926539128} diff --git a/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__attn/eval_log_best.json b/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__attn/eval_log_best.json new file mode 100644 index 0000000000000000000000000000000000000000..fc9d637be96476c9c50849d4524351ee312132bb --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__attn/eval_log_best.json @@ -0,0 +1 @@ +{"eval/best/epoch": 8, "eval/best/id_best": 23, "eval/best/lr_best": 0.00025499999999999996, "eval/best/wd_best": 0.05, "eval/best/train/loss": 0.035422105342149734, "eval/best/train/acc": 0.9938417811463761, "eval/best/train/acc_std": 0.0005515012840441916, "eval/best/train/f1": 0.9936347787478754, "eval/best/train/f1_std": 0.00062564819864731, "eval/best/validation/loss": 0.06714221090078354, "eval/best/validation/acc": 0.9818948412698413, "eval/best/validation/acc_std": 0.001929209224017128, "eval/best/validation/f1": 0.9799099655473743, "eval/best/validation/f1_std": 0.0024497399729675874, "eval/best/test/loss": 0.08606162667274475, "eval/best/test/acc": 0.9742063492063492, "eval/best/test/acc_std": 0.0022554523674217113, "eval/best/test/f1": 0.968385237238162, "eval/best/test/f1_std": 0.0030263738926539128} diff --git a/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__attn/eval_log_last.json b/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__attn/eval_log_last.json new file mode 100644 index 0000000000000000000000000000000000000000..8f19faf5a57b1f584c22290179dddbdcfcb6ec24 --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__attn/eval_log_last.json @@ -0,0 +1 @@ +{"eval/last/epoch": 19, "eval/last/id_best": 23, "eval/last/lr_best": 0.00025499999999999996, "eval/last/wd_best": 0.05, "eval/last/train/loss": 0.01573818549513817, "eval/last/train/acc": 0.9980525290804779, "eval/last/train/acc_std": 0.0003204039388166683, "eval/last/train/f1": 0.9981245127681868, "eval/last/train/f1_std": 0.0003248137248363995, "eval/last/validation/loss": 0.06250125169754028, "eval/last/validation/acc": 0.9809027777777778, "eval/last/validation/acc_std": 0.0020652798650272228, "eval/last/validation/f1": 0.9783232753219386, "eval/last/validation/f1_std": 0.002647813729125984, "eval/last/test/loss": 0.08106201887130737, "eval/last/test/acc": 0.9759920634920635, "eval/last/test/acc_std": 0.0021589489851741514, "eval/last/test/f1": 0.970003878850155, "eval/last/test/f1_std": 0.0029274843494945402} diff --git a/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__attn/eval_table.csv b/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__attn/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..4fe4d3b6c1baa37a1233e4bf27ac12b5720de264 --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__attn/eval_table.csv @@ -0,0 +1,4 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,reg,attn,hcpya_task21,best,8,0.00025499999999999996,0.05,23,"[0.85, 1.0]",train,0.035422105342149734,0.9938417811463761,0.0005515012840441916,0.9936347787478754,0.00062564819864731 +flat_mae,reg,attn,hcpya_task21,best,8,0.00025499999999999996,0.05,23,"[0.85, 1.0]",validation,0.06714221090078354,0.9818948412698413,0.001929209224017128,0.9799099655473743,0.0024497399729675874 +flat_mae,reg,attn,hcpya_task21,best,8,0.00025499999999999996,0.05,23,"[0.85, 1.0]",test,0.08606162667274475,0.9742063492063492,0.0022554523674217113,0.968385237238162,0.0030263738926539128 diff --git a/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__attn/eval_table_best.csv b/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__attn/eval_table_best.csv new file mode 100644 index 0000000000000000000000000000000000000000..4fe4d3b6c1baa37a1233e4bf27ac12b5720de264 --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__attn/eval_table_best.csv @@ -0,0 +1,4 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,reg,attn,hcpya_task21,best,8,0.00025499999999999996,0.05,23,"[0.85, 1.0]",train,0.035422105342149734,0.9938417811463761,0.0005515012840441916,0.9936347787478754,0.00062564819864731 +flat_mae,reg,attn,hcpya_task21,best,8,0.00025499999999999996,0.05,23,"[0.85, 1.0]",validation,0.06714221090078354,0.9818948412698413,0.001929209224017128,0.9799099655473743,0.0024497399729675874 +flat_mae,reg,attn,hcpya_task21,best,8,0.00025499999999999996,0.05,23,"[0.85, 1.0]",test,0.08606162667274475,0.9742063492063492,0.0022554523674217113,0.968385237238162,0.0030263738926539128 diff --git a/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__attn/eval_table_last.csv b/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__attn/eval_table_last.csv new file mode 100644 index 0000000000000000000000000000000000000000..f9b12fdcbb25cf316be13d719f946f5558092976 --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__attn/eval_table_last.csv @@ -0,0 +1,4 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,reg,attn,hcpya_task21,last,19,0.00025499999999999996,0.05,23,"[0.85, 1.0]",train,0.01573818549513817,0.9980525290804779,0.0003204039388166683,0.9981245127681868,0.0003248137248363995 +flat_mae,reg,attn,hcpya_task21,last,19,0.00025499999999999996,0.05,23,"[0.85, 1.0]",validation,0.06250125169754028,0.9809027777777778,0.0020652798650272228,0.9783232753219386,0.002647813729125984 +flat_mae,reg,attn,hcpya_task21,last,19,0.00025499999999999996,0.05,23,"[0.85, 1.0]",test,0.08106201887130737,0.9759920634920635,0.0021589489851741514,0.970003878850155,0.0029274843494945402 diff --git a/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__attn/log.txt b/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__attn/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..b791301d8b25df912884272104dcfd2e921ee41c --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__attn/log.txt @@ -0,0 +1,886 @@ +fMRI foundation model probe eval +version: 0.1.dev65+g4003a1397 +sha: 6c01b606db98add5848cecd23e5d599250c0bf86, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-02-24 23:41:57 +config: +output_root: experiments/decoders/output +name_prefix: eval_probe +remote_root: null +notes: decoder ablations crossreg_reg4; eval v2 (hcpya_task21 reg attn) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +dataset_kwargs: {} +classifier_kwargs: + embed_dim: null + dropout: 0.0 + xavier_init: false + norm: false +lr_scale_grid: +- 0.02 +- 0.023 +- 0.028 +- 0.033 +- 0.038 +- 0.045 +- 0.053 +- 0.062 +- 0.074 +- 0.087 +- 0.1 +- 0.12 +- 0.14 +- 0.17 +- 0.2 +- 0.23 +- 0.27 +- 0.32 +- 0.38 +- 0.44 +- 0.52 +- 0.61 +- 0.72 +- 0.85 +- 1 +- 1.2 +- 1.4 +- 1.6 +- 1.9 +- 2.3 +- 2.7 +- 3.1 +- 3.7 +- 4.3 +- 5.1 +- 6 +- 7.1 +- 8.3 +- 9.8 +- 12 +- 14 +- 16 +- 19 +- 22 +- 26 +- 31 +- 36 +- 43 +- 50 +wd_scale_grid: +- 1.0 +num_workers: 8 +prefetch_factor: null +balanced_sampling: false +epochs: 20 +steps_per_epoch: 200 +batch_size: 64 +accum_iter: 2 +lr: 0.0003 +warmup_epochs: 5 +no_decay: false +weight_decay: 0.05 +clip_grad: 1.0 +metrics: +- acc +- f1 +cv_metric: acc +early_stopping: true +amp: true +device: cuda +seed: 4466 +debug: false +wandb: false +wandb_entity: null +wandb_project: fMRI-fm-eval +name: decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__attn +model: flat_mae +representation: reg +classifier: attn +dataset: hcpya_task21 +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__attn +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=False, reg_tokens=4, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: hcpya_task21 (flat) +train (n=18999): +HFDataset( + dataset=Dataset({ + features: ['sub', 'task', 'cond', 'cond_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 18999 +}), + labels=[ 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20], + counts=[ 832 1248 3201 1660 832 832 832 832 832 1248 1247 1243 832 416 + 416 416 416 416 416 416 416] +) + +validation (n=4032): +HFDataset( + dataset=Dataset({ + features: ['sub', 'task', 'cond', 'cond_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 4032 +}), + labels=[ 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20], + counts=[176 264 688 352 176 176 176 176 176 264 264 264 176 88 88 88 88 88 + 88 88 88] +) + +test (n=5040): +HFDataset( + dataset=Dataset({ + features: ['sub', 'task', 'cond', 'cond_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 5040 +}), + labels=[ 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20], + counts=[220 330 860 440 220 220 220 220 220 330 330 330 220 110 110 110 110 110 + 110 110 110] +) + +running backbone on example batch to get embedding dim +embedding feature dim (reg): 768 +initializing sweep of classifier heads +classifiers: +ModuleList( + (0-48): 49 x AttnPoolClassifier( + (kv): Linear(in_features=768, out_features=1536, bias=True) + (linear): Linear(in_features=768, out_features=21, bias=True) + ) +) +classifier params (train): 58.7M (58.7M) +setting up optimizer +total batch size: 128 = 64 bs per gpu x 2 accum +lr: 3.00e-04 +full schedule: epochs = 20 (steps = 4000) (decay = True) +warmup: epochs = 5 (steps = 1000) +start training for 20 epochs +train: [0] [ 0/400] eta: 0:22:58 lr: nan time: 3.4469 data: 3.0362 max mem: 4135 +train: [0] [ 20/400] eta: 0:03:22 lr: 0.000003 loss: 3.0347 (3.0349) grad: 0.0859 (0.0857) time: 0.3863 data: 0.0031 max mem: 4840 +train: [0] [ 40/400] eta: 0:02:38 lr: 0.000006 loss: 3.0255 (3.0204) grad: 0.0861 (0.0882) time: 0.3415 data: 0.0037 max mem: 4840 +train: [0] [ 60/400] eta: 0:02:18 lr: 0.000009 loss: 2.9749 (2.9961) grad: 0.0864 (0.0882) time: 0.3382 data: 0.0041 max mem: 4840 +train: [0] [ 80/400] eta: 0:02:04 lr: 0.000012 loss: 2.9128 (2.9637) grad: 0.0868 (0.0887) time: 0.3435 data: 0.0039 max mem: 4840 +train: [0] [100/400] eta: 0:01:54 lr: 0.000015 loss: 2.8187 (2.9260) grad: 0.0868 (0.0882) time: 0.3442 data: 0.0040 max mem: 4840 +train: [0] [120/400] eta: 0:01:45 lr: 0.000018 loss: 2.7005 (2.8807) grad: 0.0872 (0.0889) time: 0.3489 data: 0.0038 max mem: 4840 +train: [0] [140/400] eta: 0:01:36 lr: 0.000021 loss: 2.5915 (2.8327) grad: 0.0837 (0.0880) time: 0.3407 data: 0.0042 max mem: 4840 +train: [0] [160/400] eta: 0:01:28 lr: 0.000024 loss: 2.4918 (2.7833) grad: 0.0803 (0.0871) time: 0.3539 data: 0.0041 max mem: 4840 +train: [0] [180/400] eta: 0:01:21 lr: 0.000027 loss: 2.3732 (2.7357) grad: 0.0811 (0.0865) time: 0.3833 data: 0.0044 max mem: 4840 +train: [0] [200/400] eta: 0:01:13 lr: 0.000030 loss: 2.3194 (2.6891) grad: 0.0824 (0.0859) time: 0.3576 data: 0.0043 max mem: 4840 +train: [0] [220/400] eta: 0:01:06 lr: 0.000033 loss: 2.2266 (2.6442) grad: 0.0831 (0.0859) time: 0.3596 data: 0.0042 max mem: 4840 +train: [0] [240/400] eta: 0:00:58 lr: 0.000036 loss: 2.1643 (2.6023) grad: 0.0808 (0.0851) time: 0.3483 data: 0.0041 max mem: 4840 +train: [0] [260/400] eta: 0:00:50 lr: 0.000039 loss: 2.0924 (2.5606) grad: 0.0750 (0.0843) time: 0.3277 data: 0.0041 max mem: 4840 +train: [0] [280/400] eta: 0:00:43 lr: 0.000042 loss: 2.0384 (2.5212) grad: 0.0750 (0.0838) time: 0.3246 data: 0.0041 max mem: 4840 +train: [0] [300/400] eta: 0:00:36 lr: 0.000045 loss: 1.9733 (2.4832) grad: 0.0764 (0.0834) time: 0.4762 data: 0.1620 max mem: 4840 +train: [0] [320/400] eta: 0:00:29 lr: 0.000048 loss: 1.9234 (2.4470) grad: 0.0773 (0.0829) time: 0.3296 data: 0.0036 max mem: 4840 +train: [0] [340/400] eta: 0:00:21 lr: 0.000051 loss: 1.8917 (2.4141) grad: 0.0741 (0.0823) time: 0.3231 data: 0.0032 max mem: 4840 +train: [0] [360/400] eta: 0:00:14 lr: 0.000054 loss: 1.8509 (2.3815) grad: 0.0714 (0.0818) time: 0.3373 data: 0.0040 max mem: 4840 +train: [0] [380/400] eta: 0:00:07 lr: 0.000057 loss: 1.8141 (2.3500) grad: 0.0716 (0.0814) time: 0.3282 data: 0.0041 max mem: 4840 +train: [0] [399/400] eta: 0:00:00 lr: 0.000060 loss: 1.7458 (2.3183) grad: 0.0723 (0.0810) time: 0.3318 data: 0.0041 max mem: 4840 +train: [0] Total time: 0:02:23 (0.3595 s / it) +train: [0] Summary: lr: 0.000060 loss: 1.7458 (2.3183) grad: 0.0723 (0.0810) +eval (validation): [0] [ 0/63] eta: 0:03:06 time: 2.9591 data: 2.7170 max mem: 4840 +eval (validation): [0] [20/63] eta: 0:00:19 time: 0.3282 data: 0.0038 max mem: 4840 +eval (validation): [0] [40/63] eta: 0:00:08 time: 0.2903 data: 0.0030 max mem: 4840 +eval (validation): [0] [60/63] eta: 0:00:01 time: 0.3028 data: 0.0031 max mem: 4840 +eval (validation): [0] [62/63] eta: 0:00:00 time: 0.3043 data: 0.0031 max mem: 4840 +eval (validation): [0] Total time: 0:00:22 (0.3539 s / it) +cv: [0] best hparam: (19, 1.0) (042) ('042_lr1.9e+01_wd1.0e+00') loss: 0.112 acc: 0.970 f1: 0.967 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__attn/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__attn/checkpoint-best.pth +train: [1] [ 0/400] eta: 0:20:01 lr: nan time: 3.0032 data: 2.7767 max mem: 4840 +train: [1] [ 20/400] eta: 0:02:54 lr: 0.000063 loss: 1.6774 (1.6939) grad: 0.0679 (0.0707) time: 0.3317 data: 0.0035 max mem: 4840 +train: [1] [ 40/400] eta: 0:02:23 lr: 0.000066 loss: 1.6774 (1.6788) grad: 0.0683 (0.0709) time: 0.3330 data: 0.0030 max mem: 4840 +train: [1] [ 60/400] eta: 0:02:07 lr: 0.000069 loss: 1.6434 (1.6597) grad: 0.0708 (0.0713) time: 0.3252 data: 0.0040 max mem: 4840 +train: [1] [ 80/400] eta: 0:01:59 lr: 0.000072 loss: 1.5837 (1.6377) grad: 0.0717 (0.0712) time: 0.3713 data: 0.0042 max mem: 4840 +train: [1] [100/400] eta: 0:01:50 lr: 0.000075 loss: 1.5705 (1.6254) grad: 0.0691 (0.0709) time: 0.3560 data: 0.0043 max mem: 4840 +train: [1] [120/400] eta: 0:01:42 lr: 0.000078 loss: 1.5591 (1.6117) grad: 0.0673 (0.0704) time: 0.3582 data: 0.0042 max mem: 4840 +train: [1] [140/400] eta: 0:01:34 lr: 0.000081 loss: 1.4840 (1.5897) grad: 0.0691 (0.0707) time: 0.3426 data: 0.0039 max mem: 4840 +train: [1] [160/400] eta: 0:01:26 lr: 0.000084 loss: 1.4654 (1.5772) grad: 0.0692 (0.0702) time: 0.3344 data: 0.0040 max mem: 4840 +train: [1] [180/400] eta: 0:01:19 lr: 0.000087 loss: 1.4674 (1.5631) grad: 0.0667 (0.0700) time: 0.3635 data: 0.0042 max mem: 4840 +train: [1] [200/400] eta: 0:01:12 lr: 0.000090 loss: 1.4233 (1.5491) grad: 0.0667 (0.0697) time: 0.3583 data: 0.0039 max mem: 4840 +train: [1] [220/400] eta: 0:01:05 lr: 0.000093 loss: 1.4027 (1.5347) grad: 0.0665 (0.0695) time: 0.3760 data: 0.0039 max mem: 4840 +train: [1] [240/400] eta: 0:00:58 lr: 0.000096 loss: 1.3869 (1.5235) grad: 0.0656 (0.0692) time: 0.3708 data: 0.0041 max mem: 4840 +train: [1] [260/400] eta: 0:00:50 lr: 0.000099 loss: 1.3462 (1.5082) grad: 0.0652 (0.0690) time: 0.3304 data: 0.0041 max mem: 4840 +train: [1] [280/400] eta: 0:00:43 lr: 0.000102 loss: 1.3164 (1.4947) grad: 0.0677 (0.0690) time: 0.3492 data: 0.0046 max mem: 4840 +train: [1] [300/400] eta: 0:00:37 lr: 0.000105 loss: 1.3244 (1.4833) grad: 0.0659 (0.0688) time: 0.5221 data: 0.1868 max mem: 4840 +train: [1] [320/400] eta: 0:00:29 lr: 0.000108 loss: 1.2948 (1.4709) grad: 0.0638 (0.0686) time: 0.3601 data: 0.0030 max mem: 4840 +train: [1] [340/400] eta: 0:00:22 lr: 0.000111 loss: 1.2721 (1.4583) grad: 0.0650 (0.0685) time: 0.3550 data: 0.0037 max mem: 4840 +train: [1] [360/400] eta: 0:00:14 lr: 0.000114 loss: 1.2497 (1.4474) grad: 0.0637 (0.0682) time: 0.3393 data: 0.0040 max mem: 4840 +train: [1] [380/400] eta: 0:00:07 lr: 0.000117 loss: 1.2332 (1.4352) grad: 0.0646 (0.0681) time: 0.3695 data: 0.0042 max mem: 4840 +train: [1] [399/400] eta: 0:00:00 lr: 0.000120 loss: 1.1928 (1.4233) grad: 0.0677 (0.0682) time: 0.3653 data: 0.0038 max mem: 4840 +train: [1] Total time: 0:02:27 (0.3676 s / it) +train: [1] Summary: lr: 0.000120 loss: 1.1928 (1.4233) grad: 0.0677 (0.0682) +eval (validation): [1] [ 0/63] eta: 0:03:29 time: 3.3323 data: 3.0395 max mem: 4840 +eval (validation): [1] [20/63] eta: 0:00:20 time: 0.3435 data: 0.0043 max mem: 4840 +eval (validation): [1] [40/63] eta: 0:00:09 time: 0.3130 data: 0.0031 max mem: 4840 +eval (validation): [1] [60/63] eta: 0:00:01 time: 0.2925 data: 0.0033 max mem: 4840 +eval (validation): [1] [62/63] eta: 0:00:00 time: 0.2933 data: 0.0033 max mem: 4840 +eval (validation): [1] Total time: 0:00:23 (0.3686 s / it) +cv: [1] best hparam: (22, 1.0) (043) ('043_lr2.2e+01_wd1.0e+00') loss: 0.087 acc: 0.974 f1: 0.973 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__attn/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__attn/checkpoint-best.pth +train: [2] [ 0/400] eta: 0:20:14 lr: nan time: 3.0351 data: 2.7609 max mem: 4840 +train: [2] [ 20/400] eta: 0:03:04 lr: 0.000123 loss: 1.1577 (1.1685) grad: 0.0615 (0.0643) time: 0.3578 data: 0.0030 max mem: 4840 +train: [2] [ 40/400] eta: 0:02:26 lr: 0.000126 loss: 1.1581 (1.1740) grad: 0.0650 (0.0654) time: 0.3224 data: 0.0039 max mem: 4840 +train: [2] [ 60/400] eta: 0:02:09 lr: 0.000129 loss: 1.1667 (1.1712) grad: 0.0665 (0.0656) time: 0.3303 data: 0.0042 max mem: 4840 +train: [2] [ 80/400] eta: 0:01:58 lr: 0.000132 loss: 1.1459 (1.1609) grad: 0.0667 (0.0663) time: 0.3345 data: 0.0041 max mem: 4840 +train: [2] [100/400] eta: 0:01:49 lr: 0.000135 loss: 1.1409 (1.1560) grad: 0.0673 (0.0660) time: 0.3390 data: 0.0040 max mem: 4840 +train: [2] [120/400] eta: 0:01:40 lr: 0.000138 loss: 1.1099 (1.1464) grad: 0.0638 (0.0655) time: 0.3343 data: 0.0041 max mem: 4840 +train: [2] [140/400] eta: 0:01:31 lr: 0.000141 loss: 1.0895 (1.1365) grad: 0.0607 (0.0649) time: 0.3239 data: 0.0041 max mem: 4840 +train: [2] [160/400] eta: 0:01:24 lr: 0.000144 loss: 1.0812 (1.1270) grad: 0.0625 (0.0649) time: 0.3244 data: 0.0040 max mem: 4840 +train: [2] [180/400] eta: 0:01:16 lr: 0.000147 loss: 1.0643 (1.1183) grad: 0.0629 (0.0645) time: 0.3176 data: 0.0040 max mem: 4840 +train: [2] [200/400] eta: 0:01:08 lr: 0.000150 loss: 1.0504 (1.1100) grad: 0.0605 (0.0641) time: 0.3286 data: 0.0039 max mem: 4840 +train: [2] [220/400] eta: 0:01:01 lr: 0.000153 loss: 1.0341 (1.1032) grad: 0.0605 (0.0640) time: 0.3229 data: 0.0040 max mem: 4840 +train: [2] [240/400] eta: 0:00:54 lr: 0.000156 loss: 1.0191 (1.0967) grad: 0.0621 (0.0638) time: 0.3287 data: 0.0041 max mem: 4840 +train: [2] [260/400] eta: 0:00:47 lr: 0.000159 loss: 1.0065 (1.0892) grad: 0.0633 (0.0640) time: 0.3371 data: 0.0041 max mem: 4840 +train: [2] [280/400] eta: 0:00:40 lr: 0.000162 loss: 0.9867 (1.0822) grad: 0.0627 (0.0637) time: 0.3328 data: 0.0040 max mem: 4840 +train: [2] [300/400] eta: 0:00:35 lr: 0.000165 loss: 0.9747 (1.0743) grad: 0.0625 (0.0638) time: 0.5270 data: 0.1810 max mem: 4840 +train: [2] [320/400] eta: 0:00:28 lr: 0.000168 loss: 0.9490 (1.0664) grad: 0.0643 (0.0639) time: 0.4102 data: 0.0042 max mem: 4840 +train: [2] [340/400] eta: 0:00:21 lr: 0.000171 loss: 0.9416 (1.0599) grad: 0.0652 (0.0641) time: 0.3593 data: 0.0042 max mem: 4840 +train: [2] [360/400] eta: 0:00:14 lr: 0.000174 loss: 0.9225 (1.0524) grad: 0.0668 (0.0642) time: 0.3502 data: 0.0043 max mem: 4840 +train: [2] [380/400] eta: 0:00:07 lr: 0.000177 loss: 0.9036 (1.0453) grad: 0.0655 (0.0643) time: 0.3657 data: 0.0040 max mem: 4840 +train: [2] [399/400] eta: 0:00:00 lr: 0.000180 loss: 0.8949 (1.0375) grad: 0.0661 (0.0646) time: 0.3609 data: 0.0043 max mem: 4840 +train: [2] Total time: 0:02:23 (0.3575 s / it) +train: [2] Summary: lr: 0.000180 loss: 0.8949 (1.0375) grad: 0.0661 (0.0646) +eval (validation): [2] [ 0/63] eta: 0:03:28 time: 3.3137 data: 3.0760 max mem: 4840 +eval (validation): [2] [20/63] eta: 0:00:21 time: 0.3704 data: 0.0040 max mem: 4840 +eval (validation): [2] [40/63] eta: 0:00:09 time: 0.3370 data: 0.0027 max mem: 4840 +eval (validation): [2] [60/63] eta: 0:00:01 time: 0.3254 data: 0.0033 max mem: 4840 +eval (validation): [2] [62/63] eta: 0:00:00 time: 0.3228 data: 0.0033 max mem: 4840 +eval (validation): [2] Total time: 0:00:24 (0.3950 s / it) +cv: [2] best hparam: (5.1, 1.0) (034) ('034_lr5.1e+00_wd1.0e+00') loss: 0.081 acc: 0.977 f1: 0.976 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__attn/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__attn/checkpoint-best.pth +train: [3] [ 0/400] eta: 0:22:11 lr: nan time: 3.3285 data: 3.0833 max mem: 4840 +train: [3] [ 20/400] eta: 0:03:20 lr: 0.000183 loss: 0.8712 (0.8937) grad: 0.0702 (0.0709) time: 0.3885 data: 0.0035 max mem: 4840 +train: [3] [ 40/400] eta: 0:02:34 lr: 0.000186 loss: 0.8712 (0.8929) grad: 0.0702 (0.0715) time: 0.3274 data: 0.0034 max mem: 4840 +train: [3] [ 60/400] eta: 0:02:14 lr: 0.000189 loss: 0.8898 (0.8960) grad: 0.0745 (0.0756) time: 0.3279 data: 0.0044 max mem: 4840 +train: [3] [ 80/400] eta: 0:02:02 lr: 0.000192 loss: 0.8873 (0.8935) grad: 0.0819 (0.0789) time: 0.3411 data: 0.0037 max mem: 4840 +train: [3] [100/400] eta: 0:01:53 lr: 0.000195 loss: 0.9034 (0.8983) grad: 0.0867 (0.0813) time: 0.3574 data: 0.0040 max mem: 4840 +train: [3] [120/400] eta: 0:01:46 lr: 0.000198 loss: 0.8975 (0.8979) grad: 0.0891 (0.0842) time: 0.3913 data: 0.0042 max mem: 4840 +train: [3] [140/400] eta: 0:01:38 lr: 0.000201 loss: 0.8698 (0.8973) grad: 0.0891 (0.0850) time: 0.3760 data: 0.0042 max mem: 4840 +train: [3] [160/400] eta: 0:01:30 lr: 0.000204 loss: 0.8517 (0.8910) grad: 0.0888 (0.0861) time: 0.3519 data: 0.0041 max mem: 4840 +train: [3] [180/400] eta: 0:01:22 lr: 0.000207 loss: 0.8207 (0.8859) grad: 0.0888 (0.0865) time: 0.3656 data: 0.0043 max mem: 4840 +train: [3] [200/400] eta: 0:01:14 lr: 0.000210 loss: 0.8351 (0.8835) grad: 0.0932 (0.0877) time: 0.3558 data: 0.0045 max mem: 4840 +train: [3] [220/400] eta: 0:01:07 lr: 0.000213 loss: 0.8468 (0.8809) grad: 0.0987 (0.0895) time: 0.3753 data: 0.0044 max mem: 4840 +train: [3] [240/400] eta: 0:00:59 lr: 0.000216 loss: 0.8468 (0.8798) grad: 0.0980 (0.0904) time: 0.3623 data: 0.0041 max mem: 4840 +train: [3] [260/400] eta: 0:00:51 lr: 0.000219 loss: 0.8320 (0.8753) grad: 0.0933 (0.0907) time: 0.3446 data: 0.0041 max mem: 4840 +train: [3] [280/400] eta: 0:00:44 lr: 0.000222 loss: 0.7963 (0.8698) grad: 0.0926 (0.0911) time: 0.3321 data: 0.0043 max mem: 4840 +train: [3] [300/400] eta: 0:00:37 lr: 0.000225 loss: 0.8118 (0.8685) grad: 0.0963 (0.0917) time: 0.5185 data: 0.1853 max mem: 4840 +train: [3] [320/400] eta: 0:00:29 lr: 0.000228 loss: 0.8167 (0.8653) grad: 0.1019 (0.0926) time: 0.3326 data: 0.0031 max mem: 4840 +train: [3] [340/400] eta: 0:00:22 lr: 0.000231 loss: 0.8125 (0.8614) grad: 0.0995 (0.0928) time: 0.3703 data: 0.0037 max mem: 4840 +train: [3] [360/400] eta: 0:00:14 lr: 0.000234 loss: 0.7880 (0.8580) grad: 0.0951 (0.0931) time: 0.3354 data: 0.0042 max mem: 4840 +train: [3] [380/400] eta: 0:00:07 lr: 0.000237 loss: 0.7695 (0.8538) grad: 0.0933 (0.0931) time: 0.3929 data: 0.0045 max mem: 4840 +train: [3] [399/400] eta: 0:00:00 lr: 0.000240 loss: 0.7695 (0.8496) grad: 0.0894 (0.0930) time: 0.3698 data: 0.0044 max mem: 4840 +train: [3] Total time: 0:02:29 (0.3737 s / it) +train: [3] Summary: lr: 0.000240 loss: 0.7695 (0.8496) grad: 0.0894 (0.0930) +eval (validation): [3] [ 0/63] eta: 0:03:22 time: 3.2064 data: 2.9753 max mem: 4840 +eval (validation): [3] [20/63] eta: 0:00:21 time: 0.3675 data: 0.0046 max mem: 4840 +eval (validation): [3] [40/63] eta: 0:00:09 time: 0.3496 data: 0.0034 max mem: 4840 +eval (validation): [3] [60/63] eta: 0:00:01 time: 0.3188 data: 0.0038 max mem: 4840 +eval (validation): [3] [62/63] eta: 0:00:00 time: 0.3184 data: 0.0039 max mem: 4840 +eval (validation): [3] Total time: 0:00:24 (0.3947 s / it) +cv: [3] best hparam: (2.7, 1.0) (030) ('030_lr2.7e+00_wd1.0e+00') loss: 0.075 acc: 0.979 f1: 0.975 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__attn/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__attn/checkpoint-best.pth +train: [4] [ 0/400] eta: 0:22:57 lr: nan time: 3.4425 data: 3.1314 max mem: 4840 +train: [4] [ 20/400] eta: 0:03:08 lr: 0.000243 loss: 0.6823 (0.6854) grad: 0.0800 (0.0840) time: 0.3474 data: 0.0023 max mem: 4840 +train: [4] [ 40/400] eta: 0:02:29 lr: 0.000246 loss: 0.7244 (0.7352) grad: 0.0896 (0.0902) time: 0.3301 data: 0.0034 max mem: 4840 +train: [4] [ 60/400] eta: 0:02:11 lr: 0.000249 loss: 0.7558 (0.7298) grad: 0.0911 (0.0903) time: 0.3342 data: 0.0043 max mem: 4840 +train: [4] [ 80/400] eta: 0:02:02 lr: 0.000252 loss: 0.7404 (0.7362) grad: 0.0911 (0.0915) time: 0.3666 data: 0.0040 max mem: 4840 +train: [4] [100/400] eta: 0:01:53 lr: 0.000255 loss: 0.7391 (0.7358) grad: 0.0934 (0.0919) time: 0.3570 data: 0.0041 max mem: 4840 +train: [4] [120/400] eta: 0:01:44 lr: 0.000258 loss: 0.7402 (0.7459) grad: 0.0947 (0.0929) time: 0.3457 data: 0.0045 max mem: 4840 +train: [4] [140/400] eta: 0:01:36 lr: 0.000261 loss: 0.7329 (0.7349) grad: 0.0883 (0.0922) time: 0.3526 data: 0.0041 max mem: 4840 +train: [4] [160/400] eta: 0:01:28 lr: 0.000264 loss: 0.7065 (0.7318) grad: 0.0881 (0.0928) time: 0.3529 data: 0.0042 max mem: 4840 +train: [4] [180/400] eta: 0:01:20 lr: 0.000267 loss: 0.7295 (0.7325) grad: 0.0910 (0.0931) time: 0.3466 data: 0.0041 max mem: 4840 +train: [4] [200/400] eta: 0:01:12 lr: 0.000270 loss: 0.6747 (0.7266) grad: 0.0912 (0.0933) time: 0.3522 data: 0.0042 max mem: 4840 +train: [4] [220/400] eta: 0:01:05 lr: 0.000273 loss: 0.6634 (0.7255) grad: 0.0912 (0.0929) time: 0.3575 data: 0.0043 max mem: 4840 +train: [4] [240/400] eta: 0:00:58 lr: 0.000276 loss: 0.6831 (0.7259) grad: 0.0921 (0.0936) time: 0.3565 data: 0.0039 max mem: 4840 +train: [4] [260/400] eta: 0:00:50 lr: 0.000279 loss: 0.6817 (0.7240) grad: 0.0972 (0.0939) time: 0.3624 data: 0.0042 max mem: 4840 +train: [4] [280/400] eta: 0:00:43 lr: 0.000282 loss: 0.6496 (0.7209) grad: 0.0999 (0.0951) time: 0.3530 data: 0.0042 max mem: 4840 +train: [4] [300/400] eta: 0:00:37 lr: 0.000285 loss: 0.6579 (0.7197) grad: 0.1016 (0.0965) time: 0.5019 data: 0.1652 max mem: 4840 +train: [4] [320/400] eta: 0:00:29 lr: 0.000288 loss: 0.6720 (0.7170) grad: 0.0986 (0.0972) time: 0.3577 data: 0.0041 max mem: 4840 +train: [4] [340/400] eta: 0:00:22 lr: 0.000291 loss: 0.6245 (0.7125) grad: 0.0969 (0.0980) time: 0.3451 data: 0.0036 max mem: 4840 +train: [4] [360/400] eta: 0:00:14 lr: 0.000294 loss: 0.6245 (0.7092) grad: 0.1016 (0.0983) time: 0.3411 data: 0.0041 max mem: 4840 +train: [4] [380/400] eta: 0:00:07 lr: 0.000297 loss: 0.6157 (0.7069) grad: 0.0939 (0.0981) time: 0.3532 data: 0.0039 max mem: 4840 +train: [4] [399/400] eta: 0:00:00 lr: 0.000300 loss: 0.6157 (0.7075) grad: 0.0976 (0.0986) time: 0.3619 data: 0.0041 max mem: 4840 +train: [4] Total time: 0:02:26 (0.3671 s / it) +train: [4] Summary: lr: 0.000300 loss: 0.6157 (0.7075) grad: 0.0976 (0.0986) +eval (validation): [4] [ 0/63] eta: 0:03:55 time: 3.7431 data: 3.4714 max mem: 4840 +eval (validation): [4] [20/63] eta: 0:00:21 time: 0.3292 data: 0.0028 max mem: 4840 +eval (validation): [4] [40/63] eta: 0:00:09 time: 0.3350 data: 0.0033 max mem: 4840 +eval (validation): [4] [60/63] eta: 0:00:01 time: 0.3070 data: 0.0034 max mem: 4840 +eval (validation): [4] [62/63] eta: 0:00:00 time: 0.3043 data: 0.0034 max mem: 4840 +eval (validation): [4] Total time: 0:00:24 (0.3818 s / it) +cv: [4] best hparam: (3.7, 1.0) (032) ('032_lr3.7e+00_wd1.0e+00') loss: 0.069 acc: 0.979 f1: 0.977 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__attn/checkpoint-last.pth +train: [5] [ 0/400] eta: 0:27:49 lr: nan time: 4.1737 data: 3.8651 max mem: 4840 +train: [5] [ 20/400] eta: 0:03:29 lr: 0.000300 loss: 0.5889 (0.5851) grad: 0.0897 (0.0924) time: 0.3715 data: 0.0021 max mem: 4840 +train: [5] [ 40/400] eta: 0:02:44 lr: 0.000300 loss: 0.5889 (0.5738) grad: 0.0948 (0.0946) time: 0.3542 data: 0.0039 max mem: 4840 +train: [5] [ 60/400] eta: 0:02:21 lr: 0.000300 loss: 0.5567 (0.5777) grad: 0.1015 (0.0978) time: 0.3324 data: 0.0040 max mem: 4840 +train: [5] [ 80/400] eta: 0:02:07 lr: 0.000300 loss: 0.5825 (0.5858) grad: 0.1015 (0.1007) time: 0.3506 data: 0.0041 max mem: 4840 +train: [5] [100/400] eta: 0:01:57 lr: 0.000300 loss: 0.5769 (0.5872) grad: 0.0996 (0.1013) time: 0.3657 data: 0.0040 max mem: 4840 +train: [5] [120/400] eta: 0:01:49 lr: 0.000300 loss: 0.5887 (0.6007) grad: 0.1082 (0.1040) time: 0.3777 data: 0.0043 max mem: 4840 +train: [5] [140/400] eta: 0:01:40 lr: 0.000300 loss: 0.6197 (0.6065) grad: 0.1159 (0.1049) time: 0.3668 data: 0.0041 max mem: 4840 +train: [5] [160/400] eta: 0:01:32 lr: 0.000299 loss: 0.5940 (0.6046) grad: 0.1090 (0.1044) time: 0.3594 data: 0.0044 max mem: 4840 +train: [5] [180/400] eta: 0:01:23 lr: 0.000299 loss: 0.5692 (0.6059) grad: 0.0991 (0.1044) time: 0.3636 data: 0.0041 max mem: 4840 +train: [5] [200/400] eta: 0:01:15 lr: 0.000299 loss: 0.6002 (0.6114) grad: 0.1006 (0.1050) time: 0.3660 data: 0.0041 max mem: 4840 +train: [5] [220/400] eta: 0:01:08 lr: 0.000299 loss: 0.5821 (0.6098) grad: 0.1092 (0.1059) time: 0.3621 data: 0.0043 max mem: 4840 +train: [5] [240/400] eta: 0:01:00 lr: 0.000299 loss: 0.5743 (0.6103) grad: 0.1092 (0.1065) time: 0.3588 data: 0.0043 max mem: 4840 +train: [5] [260/400] eta: 0:00:52 lr: 0.000299 loss: 0.6440 (0.6152) grad: 0.1192 (0.1081) time: 0.3568 data: 0.0040 max mem: 4840 +train: [5] [280/400] eta: 0:00:44 lr: 0.000298 loss: 0.6440 (0.6158) grad: 0.1159 (0.1080) time: 0.3642 data: 0.0042 max mem: 4840 +train: [5] [300/400] eta: 0:00:38 lr: 0.000298 loss: 0.5472 (0.6108) grad: 0.0970 (0.1070) time: 0.5047 data: 0.1743 max mem: 4840 +train: [5] [320/400] eta: 0:00:30 lr: 0.000298 loss: 0.4968 (0.6045) grad: 0.0947 (0.1066) time: 0.3234 data: 0.0035 max mem: 4840 +train: [5] [340/400] eta: 0:00:22 lr: 0.000298 loss: 0.4979 (0.6000) grad: 0.0999 (0.1062) time: 0.3452 data: 0.0036 max mem: 4840 +train: [5] [360/400] eta: 0:00:15 lr: 0.000297 loss: 0.5106 (0.5963) grad: 0.0988 (0.1061) time: 0.3591 data: 0.0040 max mem: 4840 +train: [5] [380/400] eta: 0:00:07 lr: 0.000297 loss: 0.5168 (0.5915) grad: 0.0939 (0.1055) time: 0.3424 data: 0.0040 max mem: 4840 +train: [5] [399/400] eta: 0:00:00 lr: 0.000297 loss: 0.5151 (0.5896) grad: 0.0916 (0.1050) time: 0.3555 data: 0.0040 max mem: 4840 +train: [5] Total time: 0:02:29 (0.3742 s / it) +train: [5] Summary: lr: 0.000297 loss: 0.5151 (0.5896) grad: 0.0916 (0.1050) +eval (validation): [5] [ 0/63] eta: 0:03:24 time: 3.2503 data: 3.0189 max mem: 4840 +eval (validation): [5] [20/63] eta: 0:00:19 time: 0.3240 data: 0.0034 max mem: 4840 +eval (validation): [5] [40/63] eta: 0:00:09 time: 0.3633 data: 0.0040 max mem: 4840 +eval (validation): [5] [60/63] eta: 0:00:01 time: 0.3060 data: 0.0028 max mem: 4840 +eval (validation): [5] [62/63] eta: 0:00:00 time: 0.3028 data: 0.0031 max mem: 4840 +eval (validation): [5] Total time: 0:00:23 (0.3808 s / it) +cv: [5] best hparam: (2.3, 1.0) (029) ('029_lr2.3e+00_wd1.0e+00') loss: 0.066 acc: 0.980 f1: 0.977 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__attn/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__attn/checkpoint-best.pth +train: [6] [ 0/400] eta: 0:22:13 lr: nan time: 3.3346 data: 3.0934 max mem: 4840 +train: [6] [ 20/400] eta: 0:03:09 lr: 0.000296 loss: 0.4370 (0.4841) grad: 0.0921 (0.0999) time: 0.3563 data: 0.0037 max mem: 4840 +train: [6] [ 40/400] eta: 0:02:31 lr: 0.000296 loss: 0.4602 (0.4967) grad: 0.0894 (0.0945) time: 0.3393 data: 0.0035 max mem: 4840 +train: [6] [ 60/400] eta: 0:02:12 lr: 0.000296 loss: 0.5017 (0.5014) grad: 0.0857 (0.0920) time: 0.3230 data: 0.0030 max mem: 4840 +train: [6] [ 80/400] eta: 0:02:01 lr: 0.000295 loss: 0.5017 (0.5013) grad: 0.0857 (0.0908) time: 0.3538 data: 0.0040 max mem: 4840 +train: [6] [100/400] eta: 0:01:53 lr: 0.000295 loss: 0.4658 (0.5074) grad: 0.0903 (0.0911) time: 0.3635 data: 0.0044 max mem: 4840 +train: [6] [120/400] eta: 0:01:44 lr: 0.000295 loss: 0.4676 (0.5106) grad: 0.0908 (0.0914) time: 0.3502 data: 0.0039 max mem: 4840 +train: [6] [140/400] eta: 0:01:36 lr: 0.000294 loss: 0.4498 (0.5065) grad: 0.0965 (0.0918) time: 0.3594 data: 0.0043 max mem: 4840 +train: [6] [160/400] eta: 0:01:28 lr: 0.000294 loss: 0.4498 (0.5025) grad: 0.0881 (0.0910) time: 0.3592 data: 0.0042 max mem: 4840 +train: [6] [180/400] eta: 0:01:21 lr: 0.000293 loss: 0.4862 (0.5015) grad: 0.0838 (0.0911) time: 0.3654 data: 0.0044 max mem: 4840 +train: [6] [200/400] eta: 0:01:13 lr: 0.000293 loss: 0.4790 (0.5000) grad: 0.1039 (0.0945) time: 0.3551 data: 0.0041 max mem: 4840 +train: [6] [220/400] eta: 0:01:06 lr: 0.000292 loss: 0.4682 (0.4983) grad: 0.0949 (0.0940) time: 0.3609 data: 0.0043 max mem: 4840 +train: [6] [240/400] eta: 0:00:58 lr: 0.000292 loss: 0.4682 (0.4990) grad: 0.0896 (0.0946) time: 0.3718 data: 0.0042 max mem: 4840 +train: [6] [260/400] eta: 0:00:51 lr: 0.000291 loss: 0.4652 (0.4954) grad: 0.0947 (0.0944) time: 0.3507 data: 0.0041 max mem: 4840 +train: [6] [280/400] eta: 0:00:43 lr: 0.000291 loss: 0.3949 (0.4890) grad: 0.0759 (0.0929) time: 0.3685 data: 0.0043 max mem: 4840 +train: [6] [300/400] eta: 0:00:37 lr: 0.000290 loss: 0.4080 (0.4842) grad: 0.0866 (0.0928) time: 0.5443 data: 0.1817 max mem: 4840 +train: [6] [320/400] eta: 0:00:30 lr: 0.000290 loss: 0.4208 (0.4820) grad: 0.0864 (0.0921) time: 0.3509 data: 0.0036 max mem: 4840 +train: [6] [340/400] eta: 0:00:22 lr: 0.000289 loss: 0.4157 (0.4772) grad: 0.0838 (0.0918) time: 0.3380 data: 0.0041 max mem: 4840 +train: [6] [360/400] eta: 0:00:14 lr: 0.000288 loss: 0.3918 (0.4741) grad: 0.0867 (0.0913) time: 0.3504 data: 0.0043 max mem: 4840 +train: [6] [380/400] eta: 0:00:07 lr: 0.000288 loss: 0.4211 (0.4718) grad: 0.0783 (0.0907) time: 0.3492 data: 0.0041 max mem: 4840 +train: [6] [399/400] eta: 0:00:00 lr: 0.000287 loss: 0.3958 (0.4683) grad: 0.0749 (0.0899) time: 0.3604 data: 0.0043 max mem: 4840 +train: [6] Total time: 0:02:28 (0.3714 s / it) +train: [6] Summary: lr: 0.000287 loss: 0.3958 (0.4683) grad: 0.0749 (0.0899) +eval (validation): [6] [ 0/63] eta: 0:03:26 time: 3.2833 data: 3.0492 max mem: 4840 +eval (validation): [6] [20/63] eta: 0:00:20 time: 0.3391 data: 0.0034 max mem: 4840 +eval (validation): [6] [40/63] eta: 0:00:09 time: 0.3586 data: 0.0031 max mem: 4840 +eval (validation): [6] [60/63] eta: 0:00:01 time: 0.3151 data: 0.0032 max mem: 4840 +eval (validation): [6] [62/63] eta: 0:00:00 time: 0.3140 data: 0.0032 max mem: 4840 +eval (validation): [6] Total time: 0:00:24 (0.3880 s / it) +cv: [6] best hparam: (1.6, 1.0) (027) ('027_lr1.6e+00_wd1.0e+00') loss: 0.066 acc: 0.981 f1: 0.979 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__attn/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__attn/checkpoint-best.pth +train: [7] [ 0/400] eta: 0:21:56 lr: nan time: 3.2914 data: 3.0386 max mem: 4840 +train: [7] [ 20/400] eta: 0:03:15 lr: 0.000286 loss: 0.3650 (0.3892) grad: 0.0647 (0.0674) time: 0.3754 data: 0.0041 max mem: 4840 +train: [7] [ 40/400] eta: 0:02:38 lr: 0.000286 loss: 0.3706 (0.3936) grad: 0.0657 (0.0672) time: 0.3645 data: 0.0038 max mem: 4840 +train: [7] [ 60/400] eta: 0:02:19 lr: 0.000285 loss: 0.3605 (0.3820) grad: 0.0642 (0.0650) time: 0.3441 data: 0.0041 max mem: 4840 +train: [7] [ 80/400] eta: 0:02:04 lr: 0.000284 loss: 0.3555 (0.3754) grad: 0.0633 (0.0647) time: 0.3322 data: 0.0042 max mem: 4840 +train: [7] [100/400] eta: 0:01:55 lr: 0.000284 loss: 0.3580 (0.3756) grad: 0.0645 (0.0654) time: 0.3707 data: 0.0043 max mem: 4840 +train: [7] [120/400] eta: 0:01:47 lr: 0.000283 loss: 0.4003 (0.3819) grad: 0.0688 (0.0663) time: 0.3612 data: 0.0043 max mem: 4840 +train: [7] [140/400] eta: 0:01:38 lr: 0.000282 loss: 0.4004 (0.3833) grad: 0.0702 (0.0681) time: 0.3610 data: 0.0042 max mem: 4840 +train: [7] [160/400] eta: 0:01:30 lr: 0.000282 loss: 0.3659 (0.3830) grad: 0.0702 (0.0682) time: 0.3483 data: 0.0042 max mem: 4840 +train: [7] [180/400] eta: 0:01:21 lr: 0.000281 loss: 0.3612 (0.3839) grad: 0.0677 (0.0688) time: 0.3414 data: 0.0043 max mem: 4840 +train: [7] [200/400] eta: 0:01:14 lr: 0.000280 loss: 0.3694 (0.3812) grad: 0.0677 (0.0688) time: 0.3630 data: 0.0041 max mem: 4840 +train: [7] [220/400] eta: 0:01:06 lr: 0.000279 loss: 0.3687 (0.3805) grad: 0.0677 (0.0686) time: 0.3604 data: 0.0037 max mem: 4840 +train: [7] [240/400] eta: 0:00:59 lr: 0.000278 loss: 0.3836 (0.3816) grad: 0.0712 (0.0693) time: 0.3612 data: 0.0042 max mem: 4840 +train: [7] [260/400] eta: 0:00:51 lr: 0.000278 loss: 0.3649 (0.3800) grad: 0.0772 (0.0701) time: 0.3605 data: 0.0043 max mem: 4840 +train: [7] [280/400] eta: 0:00:44 lr: 0.000277 loss: 0.3529 (0.3823) grad: 0.0790 (0.0706) time: 0.3661 data: 0.0043 max mem: 4840 +train: [7] [300/400] eta: 0:00:37 lr: 0.000276 loss: 0.3529 (0.3798) grad: 0.0720 (0.0705) time: 0.5297 data: 0.1804 max mem: 4840 +train: [7] [320/400] eta: 0:00:30 lr: 0.000275 loss: 0.3309 (0.3771) grad: 0.0602 (0.0697) time: 0.3737 data: 0.0041 max mem: 4840 +train: [7] [340/400] eta: 0:00:22 lr: 0.000274 loss: 0.3287 (0.3746) grad: 0.0589 (0.0694) time: 0.3459 data: 0.0035 max mem: 4840 +train: [7] [360/400] eta: 0:00:14 lr: 0.000273 loss: 0.3061 (0.3715) grad: 0.0583 (0.0689) time: 0.3438 data: 0.0041 max mem: 4840 +train: [7] [380/400] eta: 0:00:07 lr: 0.000272 loss: 0.3001 (0.3677) grad: 0.0564 (0.0682) time: 0.3461 data: 0.0040 max mem: 4840 +train: [7] [399/400] eta: 0:00:00 lr: 0.000271 loss: 0.3001 (0.3643) grad: 0.0581 (0.0678) time: 0.3517 data: 0.0043 max mem: 4840 +train: [7] Total time: 0:02:29 (0.3730 s / it) +train: [7] Summary: lr: 0.000271 loss: 0.3001 (0.3643) grad: 0.0581 (0.0678) +eval (validation): [7] [ 0/63] eta: 0:03:37 time: 3.4584 data: 3.1499 max mem: 4840 +eval (validation): [7] [20/63] eta: 0:00:20 time: 0.3375 data: 0.0038 max mem: 4840 +eval (validation): [7] [40/63] eta: 0:00:09 time: 0.3510 data: 0.0030 max mem: 4840 +eval (validation): [7] [60/63] eta: 0:00:01 time: 0.3097 data: 0.0033 max mem: 4840 +eval (validation): [7] [62/63] eta: 0:00:00 time: 0.3097 data: 0.0030 max mem: 4840 +eval (validation): [7] Total time: 0:00:24 (0.3865 s / it) +cv: [7] best hparam: (1.9, 1.0) (028) ('028_lr1.9e+00_wd1.0e+00') loss: 0.066 acc: 0.980 f1: 0.977 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__attn/checkpoint-last.pth +train: [8] [ 0/400] eta: 0:22:46 lr: nan time: 3.4166 data: 3.0987 max mem: 4840 +train: [8] [ 20/400] eta: 0:03:18 lr: 0.000270 loss: 0.3193 (0.3326) grad: 0.0631 (0.0648) time: 0.3773 data: 0.0033 max mem: 4840 +train: [8] [ 40/400] eta: 0:02:40 lr: 0.000270 loss: 0.3094 (0.3243) grad: 0.0630 (0.0610) time: 0.3633 data: 0.0035 max mem: 4840 +train: [8] [ 60/400] eta: 0:02:22 lr: 0.000269 loss: 0.2893 (0.3160) grad: 0.0523 (0.0589) time: 0.3640 data: 0.0039 max mem: 4840 +train: [8] [ 80/400] eta: 0:02:08 lr: 0.000268 loss: 0.2928 (0.3229) grad: 0.0603 (0.0597) time: 0.3454 data: 0.0037 max mem: 4840 +train: [8] [100/400] eta: 0:01:56 lr: 0.000267 loss: 0.3198 (0.3239) grad: 0.0623 (0.0599) time: 0.3473 data: 0.0040 max mem: 4840 +train: [8] [120/400] eta: 0:01:48 lr: 0.000266 loss: 0.3106 (0.3195) grad: 0.0628 (0.0603) time: 0.3670 data: 0.0042 max mem: 4840 +train: [8] [140/400] eta: 0:01:39 lr: 0.000265 loss: 0.2912 (0.3172) grad: 0.0578 (0.0596) time: 0.3610 data: 0.0043 max mem: 4840 +train: [8] [160/400] eta: 0:01:31 lr: 0.000264 loss: 0.2912 (0.3173) grad: 0.0529 (0.0602) time: 0.3883 data: 0.0041 max mem: 4840 +train: [8] [180/400] eta: 0:01:23 lr: 0.000263 loss: 0.2973 (0.3160) grad: 0.0575 (0.0607) time: 0.3664 data: 0.0041 max mem: 4840 +train: [8] [200/400] eta: 0:01:15 lr: 0.000262 loss: 0.2902 (0.3133) grad: 0.0554 (0.0600) time: 0.3617 data: 0.0040 max mem: 4840 +train: [8] [220/400] eta: 0:01:08 lr: 0.000260 loss: 0.2660 (0.3118) grad: 0.0588 (0.0602) time: 0.3697 data: 0.0041 max mem: 4840 +train: [8] [240/400] eta: 0:01:00 lr: 0.000259 loss: 0.2881 (0.3106) grad: 0.0593 (0.0601) time: 0.3727 data: 0.0038 max mem: 4840 +train: [8] [260/400] eta: 0:00:52 lr: 0.000258 loss: 0.3040 (0.3127) grad: 0.0587 (0.0604) time: 0.3737 data: 0.0043 max mem: 4840 +train: [8] [280/400] eta: 0:00:45 lr: 0.000257 loss: 0.3086 (0.3112) grad: 0.0588 (0.0601) time: 0.3565 data: 0.0042 max mem: 4840 +train: [8] [300/400] eta: 0:00:38 lr: 0.000256 loss: 0.2885 (0.3098) grad: 0.0559 (0.0601) time: 0.4977 data: 0.1693 max mem: 4840 +train: [8] [320/400] eta: 0:00:30 lr: 0.000255 loss: 0.2648 (0.3071) grad: 0.0539 (0.0601) time: 0.3619 data: 0.0037 max mem: 4840 +train: [8] [340/400] eta: 0:00:22 lr: 0.000254 loss: 0.2597 (0.3051) grad: 0.0498 (0.0595) time: 0.3565 data: 0.0029 max mem: 4840 +train: [8] [360/400] eta: 0:00:15 lr: 0.000253 loss: 0.2560 (0.3030) grad: 0.0492 (0.0591) time: 0.3334 data: 0.0039 max mem: 4840 +train: [8] [380/400] eta: 0:00:07 lr: 0.000252 loss: 0.2656 (0.3022) grad: 0.0506 (0.0588) time: 0.3458 data: 0.0041 max mem: 4840 +train: [8] [399/400] eta: 0:00:00 lr: 0.000250 loss: 0.2640 (0.3005) grad: 0.0497 (0.0585) time: 0.3514 data: 0.0042 max mem: 4840 +train: [8] Total time: 0:02:30 (0.3763 s / it) +train: [8] Summary: lr: 0.000250 loss: 0.2640 (0.3005) grad: 0.0497 (0.0585) +eval (validation): [8] [ 0/63] eta: 0:03:52 time: 3.6940 data: 3.3908 max mem: 4840 +eval (validation): [8] [20/63] eta: 0:00:20 time: 0.3275 data: 0.0028 max mem: 4840 +eval (validation): [8] [40/63] eta: 0:00:09 time: 0.3220 data: 0.0034 max mem: 4840 +eval (validation): [8] [60/63] eta: 0:00:01 time: 0.3209 data: 0.0026 max mem: 4840 +eval (validation): [8] [62/63] eta: 0:00:00 time: 0.3207 data: 0.0029 max mem: 4840 +eval (validation): [8] Total time: 0:00:24 (0.3817 s / it) +cv: [8] best hparam: (0.85, 1.0) (023) ('023_lr8.5e-01_wd1.0e+00') loss: 0.067 acc: 0.982 f1: 0.980 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__attn/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__attn/checkpoint-best.pth +train: [9] [ 0/400] eta: 0:20:42 lr: nan time: 3.1062 data: 2.8409 max mem: 4840 +train: [9] [ 20/400] eta: 0:03:07 lr: 0.000249 loss: 0.2395 (0.2504) grad: 0.0490 (0.0529) time: 0.3622 data: 0.0042 max mem: 4840 +train: [9] [ 40/400] eta: 0:02:36 lr: 0.000248 loss: 0.2456 (0.2540) grad: 0.0490 (0.0504) time: 0.3724 data: 0.0029 max mem: 4840 +train: [9] [ 60/400] eta: 0:02:20 lr: 0.000247 loss: 0.2549 (0.2600) grad: 0.0440 (0.0527) time: 0.3706 data: 0.0042 max mem: 4840 +train: [9] [ 80/400] eta: 0:02:06 lr: 0.000246 loss: 0.2616 (0.2641) grad: 0.0478 (0.0535) time: 0.3462 data: 0.0044 max mem: 4840 +train: [9] [100/400] eta: 0:01:56 lr: 0.000244 loss: 0.2658 (0.2662) grad: 0.0520 (0.0539) time: 0.3507 data: 0.0042 max mem: 4840 +train: [9] [120/400] eta: 0:01:47 lr: 0.000243 loss: 0.2477 (0.2663) grad: 0.0480 (0.0532) time: 0.3566 data: 0.0041 max mem: 4840 +train: [9] [140/400] eta: 0:01:39 lr: 0.000242 loss: 0.2507 (0.2651) grad: 0.0461 (0.0523) time: 0.3723 data: 0.0041 max mem: 4840 +train: [9] [160/400] eta: 0:01:30 lr: 0.000241 loss: 0.2391 (0.2634) grad: 0.0461 (0.0516) time: 0.3661 data: 0.0044 max mem: 4840 +train: [9] [180/400] eta: 0:01:22 lr: 0.000240 loss: 0.2313 (0.2612) grad: 0.0474 (0.0509) time: 0.3544 data: 0.0047 max mem: 4840 +train: [9] [200/400] eta: 0:01:14 lr: 0.000238 loss: 0.2499 (0.2613) grad: 0.0470 (0.0506) time: 0.3595 data: 0.0043 max mem: 4840 +train: [9] [220/400] eta: 0:01:07 lr: 0.000237 loss: 0.2532 (0.2598) grad: 0.0483 (0.0506) time: 0.3550 data: 0.0042 max mem: 4840 +train: [9] [240/400] eta: 0:00:59 lr: 0.000236 loss: 0.2495 (0.2604) grad: 0.0517 (0.0509) time: 0.3644 data: 0.0041 max mem: 4840 +train: [9] [260/400] eta: 0:00:52 lr: 0.000234 loss: 0.2594 (0.2612) grad: 0.0517 (0.0510) time: 0.3628 data: 0.0040 max mem: 4840 +train: [9] [280/400] eta: 0:00:44 lr: 0.000233 loss: 0.2793 (0.2637) grad: 0.0546 (0.0520) time: 0.3615 data: 0.0044 max mem: 4840 +train: [9] [300/400] eta: 0:00:38 lr: 0.000232 loss: 0.2763 (0.2632) grad: 0.0578 (0.0524) time: 0.5488 data: 0.1781 max mem: 4840 +train: [9] [320/400] eta: 0:00:30 lr: 0.000230 loss: 0.2437 (0.2621) grad: 0.0490 (0.0522) time: 0.4174 data: 0.0033 max mem: 4840 +train: [9] [340/400] eta: 0:00:22 lr: 0.000229 loss: 0.2458 (0.2611) grad: 0.0478 (0.0518) time: 0.3475 data: 0.0044 max mem: 4840 +train: [9] [360/400] eta: 0:00:15 lr: 0.000228 loss: 0.2481 (0.2609) grad: 0.0443 (0.0514) time: 0.3478 data: 0.0040 max mem: 4840 +train: [9] [380/400] eta: 0:00:07 lr: 0.000226 loss: 0.2154 (0.2586) grad: 0.0429 (0.0511) time: 0.3473 data: 0.0040 max mem: 4840 +train: [9] [399/400] eta: 0:00:00 lr: 0.000225 loss: 0.2230 (0.2577) grad: 0.0447 (0.0509) time: 0.3498 data: 0.0041 max mem: 4840 +train: [9] Total time: 0:02:31 (0.3781 s / it) +train: [9] Summary: lr: 0.000225 loss: 0.2230 (0.2577) grad: 0.0447 (0.0509) +eval (validation): [9] [ 0/63] eta: 0:03:11 time: 3.0474 data: 2.8013 max mem: 4840 +eval (validation): [9] [20/63] eta: 0:00:20 time: 0.3451 data: 0.0048 max mem: 4840 +eval (validation): [9] [40/63] eta: 0:00:09 time: 0.3381 data: 0.0032 max mem: 4840 +eval (validation): [9] [60/63] eta: 0:00:01 time: 0.3073 data: 0.0030 max mem: 4840 +eval (validation): [9] [62/63] eta: 0:00:00 time: 0.3080 data: 0.0033 max mem: 4840 +eval (validation): [9] Total time: 0:00:23 (0.3779 s / it) +cv: [9] best hparam: (0.72, 1.0) (022) ('022_lr7.2e-01_wd1.0e+00') loss: 0.069 acc: 0.981 f1: 0.978 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__attn/checkpoint-last.pth +train: [10] [ 0/400] eta: 0:22:07 lr: nan time: 3.3182 data: 3.0618 max mem: 4840 +train: [10] [ 20/400] eta: 0:03:13 lr: 0.000224 loss: 0.2403 (0.2403) grad: 0.0437 (0.0467) time: 0.3674 data: 0.0038 max mem: 4840 +train: [10] [ 40/400] eta: 0:02:35 lr: 0.000222 loss: 0.2418 (0.2403) grad: 0.0438 (0.0477) time: 0.3543 data: 0.0034 max mem: 4840 +train: [10] [ 60/400] eta: 0:02:19 lr: 0.000221 loss: 0.2378 (0.2368) grad: 0.0438 (0.0465) time: 0.3636 data: 0.0041 max mem: 4840 +train: [10] [ 80/400] eta: 0:02:06 lr: 0.000220 loss: 0.2365 (0.2378) grad: 0.0416 (0.0467) time: 0.3472 data: 0.0039 max mem: 4840 +train: [10] [100/400] eta: 0:01:55 lr: 0.000218 loss: 0.2441 (0.2394) grad: 0.0442 (0.0471) time: 0.3396 data: 0.0043 max mem: 4840 +train: [10] [120/400] eta: 0:01:46 lr: 0.000217 loss: 0.2351 (0.2385) grad: 0.0442 (0.0465) time: 0.3540 data: 0.0039 max mem: 4840 +train: [10] [140/400] eta: 0:01:37 lr: 0.000215 loss: 0.2264 (0.2361) grad: 0.0426 (0.0460) time: 0.3560 data: 0.0039 max mem: 4840 +train: [10] [160/400] eta: 0:01:31 lr: 0.000214 loss: 0.2190 (0.2347) grad: 0.0420 (0.0456) time: 0.4047 data: 0.0043 max mem: 4840 +train: [10] [180/400] eta: 0:01:23 lr: 0.000213 loss: 0.2176 (0.2335) grad: 0.0427 (0.0459) time: 0.3817 data: 0.0040 max mem: 4840 +train: [10] [200/400] eta: 0:01:15 lr: 0.000211 loss: 0.2163 (0.2330) grad: 0.0431 (0.0459) time: 0.3718 data: 0.0044 max mem: 4840 +train: [10] [220/400] eta: 0:01:08 lr: 0.000210 loss: 0.2163 (0.2318) grad: 0.0410 (0.0456) time: 0.3716 data: 0.0043 max mem: 4840 +train: [10] [240/400] eta: 0:01:00 lr: 0.000208 loss: 0.2170 (0.2312) grad: 0.0401 (0.0452) time: 0.3689 data: 0.0041 max mem: 4840 +train: [10] [260/400] eta: 0:00:52 lr: 0.000207 loss: 0.2099 (0.2296) grad: 0.0393 (0.0447) time: 0.3666 data: 0.0041 max mem: 4840 +train: [10] [280/400] eta: 0:00:45 lr: 0.000205 loss: 0.2226 (0.2303) grad: 0.0446 (0.0449) time: 0.3619 data: 0.0043 max mem: 4840 +train: [10] [300/400] eta: 0:00:38 lr: 0.000204 loss: 0.2303 (0.2302) grad: 0.0445 (0.0446) time: 0.5522 data: 0.1873 max mem: 4840 +train: [10] [320/400] eta: 0:00:30 lr: 0.000202 loss: 0.2092 (0.2291) grad: 0.0381 (0.0444) time: 0.3688 data: 0.0031 max mem: 4840 +train: [10] [340/400] eta: 0:00:23 lr: 0.000201 loss: 0.2049 (0.2279) grad: 0.0387 (0.0442) time: 0.3687 data: 0.0035 max mem: 4840 +train: [10] [360/400] eta: 0:00:15 lr: 0.000199 loss: 0.2206 (0.2278) grad: 0.0385 (0.0440) time: 0.3523 data: 0.0040 max mem: 4840 +train: [10] [380/400] eta: 0:00:07 lr: 0.000198 loss: 0.2085 (0.2265) grad: 0.0363 (0.0437) time: 0.3303 data: 0.0042 max mem: 4840 +train: [10] [399/400] eta: 0:00:00 lr: 0.000196 loss: 0.2004 (0.2256) grad: 0.0362 (0.0433) time: 0.3690 data: 0.0042 max mem: 4840 +train: [10] Total time: 0:02:32 (0.3805 s / it) +train: [10] Summary: lr: 0.000196 loss: 0.2004 (0.2256) grad: 0.0362 (0.0433) +eval (validation): [10] [ 0/63] eta: 0:03:24 time: 3.2469 data: 2.9799 max mem: 4840 +eval (validation): [10] [20/63] eta: 0:00:21 time: 0.3647 data: 0.0037 max mem: 4840 +eval (validation): [10] [40/63] eta: 0:00:09 time: 0.3093 data: 0.0029 max mem: 4840 +eval (validation): [10] [60/63] eta: 0:00:01 time: 0.3171 data: 0.0033 max mem: 4840 +eval (validation): [10] [62/63] eta: 0:00:00 time: 0.3179 data: 0.0033 max mem: 4840 +eval (validation): [10] Total time: 0:00:24 (0.3814 s / it) +cv: [10] best hparam: (1.2, 1.0) (025) ('025_lr1.2e+00_wd1.0e+00') loss: 0.064 acc: 0.982 f1: 0.979 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__attn/checkpoint-last.pth +train: [11] [ 0/400] eta: 0:22:09 lr: nan time: 3.3226 data: 3.0579 max mem: 4840 +train: [11] [ 20/400] eta: 0:03:09 lr: 0.000195 loss: 0.1903 (0.1983) grad: 0.0365 (0.0367) time: 0.3565 data: 0.0032 max mem: 4840 +train: [11] [ 40/400] eta: 0:02:33 lr: 0.000193 loss: 0.2052 (0.2107) grad: 0.0366 (0.0380) time: 0.3542 data: 0.0034 max mem: 4840 +train: [11] [ 60/400] eta: 0:02:16 lr: 0.000192 loss: 0.2061 (0.2071) grad: 0.0366 (0.0375) time: 0.3507 data: 0.0038 max mem: 4840 +train: [11] [ 80/400] eta: 0:02:04 lr: 0.000190 loss: 0.1863 (0.2036) grad: 0.0371 (0.0377) time: 0.3473 data: 0.0042 max mem: 4840 +train: [11] [100/400] eta: 0:01:53 lr: 0.000189 loss: 0.1947 (0.2051) grad: 0.0385 (0.0381) time: 0.3426 data: 0.0042 max mem: 4840 +train: [11] [120/400] eta: 0:01:45 lr: 0.000187 loss: 0.1989 (0.2038) grad: 0.0365 (0.0379) time: 0.3649 data: 0.0044 max mem: 4840 +train: [11] [140/400] eta: 0:01:37 lr: 0.000186 loss: 0.1995 (0.2038) grad: 0.0364 (0.0378) time: 0.3514 data: 0.0042 max mem: 4840 +train: [11] [160/400] eta: 0:01:28 lr: 0.000184 loss: 0.2037 (0.2025) grad: 0.0364 (0.0375) time: 0.3461 data: 0.0041 max mem: 4840 +train: [11] [180/400] eta: 0:01:21 lr: 0.000183 loss: 0.2094 (0.2031) grad: 0.0373 (0.0376) time: 0.3619 data: 0.0041 max mem: 4840 +train: [11] [200/400] eta: 0:01:13 lr: 0.000181 loss: 0.2039 (0.2034) grad: 0.0373 (0.0375) time: 0.3602 data: 0.0042 max mem: 4840 +train: [11] [220/400] eta: 0:01:06 lr: 0.000180 loss: 0.2014 (0.2042) grad: 0.0362 (0.0376) time: 0.3535 data: 0.0042 max mem: 4840 +train: [11] [240/400] eta: 0:00:58 lr: 0.000178 loss: 0.2062 (0.2044) grad: 0.0361 (0.0375) time: 0.3619 data: 0.0042 max mem: 4840 +train: [11] [260/400] eta: 0:00:51 lr: 0.000177 loss: 0.1941 (0.2043) grad: 0.0341 (0.0372) time: 0.3443 data: 0.0041 max mem: 4840 +train: [11] [280/400] eta: 0:00:43 lr: 0.000175 loss: 0.1941 (0.2038) grad: 0.0353 (0.0372) time: 0.3591 data: 0.0043 max mem: 4840 +train: [11] [300/400] eta: 0:00:37 lr: 0.000174 loss: 0.1993 (0.2036) grad: 0.0356 (0.0372) time: 0.5099 data: 0.1725 max mem: 4840 +train: [11] [320/400] eta: 0:00:29 lr: 0.000172 loss: 0.1863 (0.2031) grad: 0.0348 (0.0371) time: 0.3726 data: 0.0044 max mem: 4840 +train: [11] [340/400] eta: 0:00:22 lr: 0.000170 loss: 0.1793 (0.2018) grad: 0.0331 (0.0369) time: 0.3573 data: 0.0026 max mem: 4840 +train: [11] [360/400] eta: 0:00:14 lr: 0.000169 loss: 0.1862 (0.2015) grad: 0.0327 (0.0367) time: 0.3627 data: 0.0034 max mem: 4840 +train: [11] [380/400] eta: 0:00:07 lr: 0.000167 loss: 0.2017 (0.2013) grad: 0.0327 (0.0365) time: 0.3785 data: 0.0036 max mem: 4840 +train: [11] [399/400] eta: 0:00:00 lr: 0.000166 loss: 0.1907 (0.2005) grad: 0.0333 (0.0364) time: 0.3425 data: 0.0040 max mem: 4840 +train: [11] Total time: 0:02:28 (0.3719 s / it) +train: [11] Summary: lr: 0.000166 loss: 0.1907 (0.2005) grad: 0.0333 (0.0364) +eval (validation): [11] [ 0/63] eta: 0:03:22 time: 3.2068 data: 2.9420 max mem: 4840 +eval (validation): [11] [20/63] eta: 0:00:22 time: 0.3861 data: 0.0057 max mem: 4840 +eval (validation): [11] [40/63] eta: 0:00:09 time: 0.3286 data: 0.0036 max mem: 4840 +eval (validation): [11] [60/63] eta: 0:00:01 time: 0.3140 data: 0.0035 max mem: 4840 +eval (validation): [11] [62/63] eta: 0:00:00 time: 0.3135 data: 0.0035 max mem: 4840 +eval (validation): [11] Total time: 0:00:24 (0.3924 s / it) +cv: [11] best hparam: (1, 1.0) (024) ('024_lr1.0e+00_wd1.0e+00') loss: 0.062 acc: 0.982 f1: 0.979 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__attn/checkpoint-last.pth +train: [12] [ 0/400] eta: 0:22:10 lr: nan time: 3.3274 data: 3.0633 max mem: 4840 +train: [12] [ 20/400] eta: 0:03:21 lr: 0.000164 loss: 0.1641 (0.1778) grad: 0.0336 (0.0358) time: 0.3915 data: 0.0147 max mem: 4840 +train: [12] [ 40/400] eta: 0:02:40 lr: 0.000163 loss: 0.1801 (0.1863) grad: 0.0335 (0.0354) time: 0.3582 data: 0.0037 max mem: 4840 +train: [12] [ 60/400] eta: 0:02:22 lr: 0.000161 loss: 0.1848 (0.1920) grad: 0.0326 (0.0345) time: 0.3585 data: 0.0040 max mem: 4840 +train: [12] [ 80/400] eta: 0:02:07 lr: 0.000160 loss: 0.1870 (0.1913) grad: 0.0331 (0.0344) time: 0.3442 data: 0.0037 max mem: 4840 +train: [12] [100/400] eta: 0:01:56 lr: 0.000158 loss: 0.1875 (0.1908) grad: 0.0335 (0.0342) time: 0.3403 data: 0.0041 max mem: 4840 +train: [12] [120/400] eta: 0:01:47 lr: 0.000156 loss: 0.1858 (0.1894) grad: 0.0344 (0.0343) time: 0.3621 data: 0.0042 max mem: 4840 +train: [12] [140/400] eta: 0:01:40 lr: 0.000155 loss: 0.1828 (0.1882) grad: 0.0345 (0.0343) time: 0.3909 data: 0.0041 max mem: 4840 +train: [12] [160/400] eta: 0:01:31 lr: 0.000153 loss: 0.1712 (0.1868) grad: 0.0335 (0.0342) time: 0.3673 data: 0.0044 max mem: 4840 +train: [12] [180/400] eta: 0:01:23 lr: 0.000152 loss: 0.1715 (0.1866) grad: 0.0325 (0.0342) time: 0.3542 data: 0.0040 max mem: 4840 +train: [12] [200/400] eta: 0:01:15 lr: 0.000150 loss: 0.1891 (0.1872) grad: 0.0328 (0.0346) time: 0.3816 data: 0.0042 max mem: 4840 +train: [12] [220/400] eta: 0:01:08 lr: 0.000149 loss: 0.1841 (0.1865) grad: 0.0318 (0.0343) time: 0.3731 data: 0.0042 max mem: 4840 +train: [12] [240/400] eta: 0:01:00 lr: 0.000147 loss: 0.1796 (0.1861) grad: 0.0315 (0.0342) time: 0.3593 data: 0.0043 max mem: 4840 +train: [12] [260/400] eta: 0:00:52 lr: 0.000145 loss: 0.1725 (0.1860) grad: 0.0325 (0.0341) time: 0.3635 data: 0.0042 max mem: 4840 +train: [12] [280/400] eta: 0:00:44 lr: 0.000144 loss: 0.1836 (0.1859) grad: 0.0324 (0.0340) time: 0.3492 data: 0.0041 max mem: 4840 +train: [12] [300/400] eta: 0:00:38 lr: 0.000142 loss: 0.1836 (0.1857) grad: 0.0318 (0.0338) time: 0.5108 data: 0.1831 max mem: 4840 +train: [12] [320/400] eta: 0:00:30 lr: 0.000141 loss: 0.1810 (0.1849) grad: 0.0297 (0.0336) time: 0.4149 data: 0.0042 max mem: 4840 +train: [12] [340/400] eta: 0:00:23 lr: 0.000139 loss: 0.1671 (0.1835) grad: 0.0296 (0.0334) time: 0.3865 data: 0.0037 max mem: 4840 +train: [12] [360/400] eta: 0:00:15 lr: 0.000138 loss: 0.1671 (0.1829) grad: 0.0298 (0.0333) time: 0.3790 data: 0.0040 max mem: 4840 +train: [12] [380/400] eta: 0:00:07 lr: 0.000136 loss: 0.1763 (0.1827) grad: 0.0306 (0.0332) time: 0.3494 data: 0.0040 max mem: 4840 +train: [12] [399/400] eta: 0:00:00 lr: 0.000134 loss: 0.1806 (0.1825) grad: 0.0314 (0.0332) time: 0.3546 data: 0.0040 max mem: 4840 +train: [12] Total time: 0:02:33 (0.3826 s / it) +train: [12] Summary: lr: 0.000134 loss: 0.1806 (0.1825) grad: 0.0314 (0.0332) +eval (validation): [12] [ 0/63] eta: 0:03:15 time: 3.1098 data: 2.9053 max mem: 4840 +eval (validation): [12] [20/63] eta: 0:00:21 time: 0.3749 data: 0.0114 max mem: 4840 +eval (validation): [12] [40/63] eta: 0:00:09 time: 0.3190 data: 0.0036 max mem: 4840 +eval (validation): [12] [60/63] eta: 0:00:01 time: 0.3157 data: 0.0025 max mem: 4840 +eval (validation): [12] [62/63] eta: 0:00:00 time: 0.3140 data: 0.0023 max mem: 4840 +eval (validation): [12] Total time: 0:00:24 (0.3849 s / it) +cv: [12] best hparam: (1.2, 1.0) (025) ('025_lr1.2e+00_wd1.0e+00') loss: 0.062 acc: 0.981 f1: 0.980 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__attn/checkpoint-last.pth +train: [13] [ 0/400] eta: 0:22:44 lr: nan time: 3.4114 data: 3.1151 max mem: 4840 +train: [13] [ 20/400] eta: 0:03:19 lr: 0.000133 loss: 0.1726 (0.1761) grad: 0.0306 (0.0320) time: 0.3811 data: 0.0039 max mem: 4840 +train: [13] [ 40/400] eta: 0:02:43 lr: 0.000131 loss: 0.1689 (0.1734) grad: 0.0306 (0.0319) time: 0.3813 data: 0.0041 max mem: 4840 +train: [13] [ 60/400] eta: 0:02:23 lr: 0.000130 loss: 0.1693 (0.1728) grad: 0.0313 (0.0319) time: 0.3526 data: 0.0040 max mem: 4840 +train: [13] [ 80/400] eta: 0:02:07 lr: 0.000128 loss: 0.1695 (0.1720) grad: 0.0313 (0.0320) time: 0.3250 data: 0.0038 max mem: 4840 +train: [13] [100/400] eta: 0:01:55 lr: 0.000127 loss: 0.1722 (0.1740) grad: 0.0301 (0.0318) time: 0.3376 data: 0.0044 max mem: 4840 +train: [13] [120/400] eta: 0:01:46 lr: 0.000125 loss: 0.1758 (0.1732) grad: 0.0296 (0.0315) time: 0.3556 data: 0.0043 max mem: 4840 +train: [13] [140/400] eta: 0:01:36 lr: 0.000124 loss: 0.1682 (0.1735) grad: 0.0305 (0.0317) time: 0.3242 data: 0.0045 max mem: 4840 +train: [13] [160/400] eta: 0:01:28 lr: 0.000122 loss: 0.1704 (0.1734) grad: 0.0307 (0.0316) time: 0.3262 data: 0.0041 max mem: 4840 +train: [13] [180/400] eta: 0:01:19 lr: 0.000120 loss: 0.1727 (0.1735) grad: 0.0295 (0.0315) time: 0.3260 data: 0.0040 max mem: 4840 +train: [13] [200/400] eta: 0:01:11 lr: 0.000119 loss: 0.1701 (0.1727) grad: 0.0295 (0.0313) time: 0.3284 data: 0.0041 max mem: 4840 +train: [13] [220/400] eta: 0:01:04 lr: 0.000117 loss: 0.1673 (0.1731) grad: 0.0317 (0.0314) time: 0.3376 data: 0.0041 max mem: 4840 +train: [13] [240/400] eta: 0:00:56 lr: 0.000116 loss: 0.1604 (0.1718) grad: 0.0311 (0.0313) time: 0.3382 data: 0.0040 max mem: 4840 +train: [13] [260/400] eta: 0:00:49 lr: 0.000114 loss: 0.1560 (0.1706) grad: 0.0303 (0.0312) time: 0.3332 data: 0.0042 max mem: 4840 +train: [13] [280/400] eta: 0:00:42 lr: 0.000113 loss: 0.1656 (0.1709) grad: 0.0298 (0.0312) time: 0.3230 data: 0.0043 max mem: 4840 +train: [13] [300/400] eta: 0:00:36 lr: 0.000111 loss: 0.1669 (0.1703) grad: 0.0298 (0.0312) time: 0.4881 data: 0.1657 max mem: 4840 +train: [13] [320/400] eta: 0:00:28 lr: 0.000110 loss: 0.1566 (0.1696) grad: 0.0286 (0.0311) time: 0.3312 data: 0.0033 max mem: 4840 +train: [13] [340/400] eta: 0:00:21 lr: 0.000108 loss: 0.1614 (0.1693) grad: 0.0287 (0.0310) time: 0.3371 data: 0.0031 max mem: 4840 +train: [13] [360/400] eta: 0:00:14 lr: 0.000107 loss: 0.1676 (0.1688) grad: 0.0287 (0.0308) time: 0.3340 data: 0.0042 max mem: 4840 +train: [13] [380/400] eta: 0:00:07 lr: 0.000105 loss: 0.1676 (0.1692) grad: 0.0291 (0.0308) time: 0.3270 data: 0.0038 max mem: 4840 +train: [13] [399/400] eta: 0:00:00 lr: 0.000104 loss: 0.1629 (0.1688) grad: 0.0296 (0.0307) time: 0.3323 data: 0.0039 max mem: 4840 +train: [13] Total time: 0:02:21 (0.3541 s / it) +train: [13] Summary: lr: 0.000104 loss: 0.1629 (0.1688) grad: 0.0296 (0.0307) +eval (validation): [13] [ 0/63] eta: 0:03:07 time: 2.9726 data: 2.7274 max mem: 4840 +eval (validation): [13] [20/63] eta: 0:00:19 time: 0.3236 data: 0.0181 max mem: 4840 +eval (validation): [13] [40/63] eta: 0:00:08 time: 0.3189 data: 0.0032 max mem: 4840 +eval (validation): [13] [60/63] eta: 0:00:01 time: 0.3273 data: 0.0032 max mem: 4840 +eval (validation): [13] [62/63] eta: 0:00:00 time: 0.3237 data: 0.0029 max mem: 4840 +eval (validation): [13] Total time: 0:00:23 (0.3699 s / it) +cv: [13] best hparam: (0.72, 1.0) (022) ('022_lr7.2e-01_wd1.0e+00') loss: 0.064 acc: 0.980 f1: 0.978 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__attn/checkpoint-last.pth +train: [14] [ 0/400] eta: 0:23:40 lr: nan time: 3.5516 data: 3.2291 max mem: 4840 +train: [14] [ 20/400] eta: 0:03:24 lr: 0.000102 loss: 0.1722 (0.1720) grad: 0.0292 (0.0299) time: 0.3867 data: 0.0030 max mem: 4840 +train: [14] [ 40/400] eta: 0:02:40 lr: 0.000101 loss: 0.1722 (0.1756) grad: 0.0297 (0.0308) time: 0.3497 data: 0.0030 max mem: 4840 +train: [14] [ 60/400] eta: 0:02:20 lr: 0.000099 loss: 0.1654 (0.1719) grad: 0.0286 (0.0300) time: 0.3503 data: 0.0041 max mem: 4840 +train: [14] [ 80/400] eta: 0:02:07 lr: 0.000098 loss: 0.1597 (0.1688) grad: 0.0284 (0.0300) time: 0.3438 data: 0.0036 max mem: 4840 +train: [14] [100/400] eta: 0:01:56 lr: 0.000096 loss: 0.1583 (0.1679) grad: 0.0294 (0.0299) time: 0.3518 data: 0.0037 max mem: 4840 +train: [14] [120/400] eta: 0:01:46 lr: 0.000095 loss: 0.1622 (0.1676) grad: 0.0287 (0.0297) time: 0.3370 data: 0.0042 max mem: 4840 +train: [14] [140/400] eta: 0:01:37 lr: 0.000093 loss: 0.1636 (0.1676) grad: 0.0287 (0.0296) time: 0.3563 data: 0.0043 max mem: 4840 +train: [14] [160/400] eta: 0:01:30 lr: 0.000092 loss: 0.1612 (0.1663) grad: 0.0295 (0.0296) time: 0.3705 data: 0.0042 max mem: 4840 +train: [14] [180/400] eta: 0:01:22 lr: 0.000090 loss: 0.1619 (0.1659) grad: 0.0290 (0.0297) time: 0.3766 data: 0.0042 max mem: 4840 +train: [14] [200/400] eta: 0:01:15 lr: 0.000089 loss: 0.1584 (0.1650) grad: 0.0290 (0.0296) time: 0.3692 data: 0.0042 max mem: 4840 +train: [14] [220/400] eta: 0:01:07 lr: 0.000088 loss: 0.1558 (0.1638) grad: 0.0284 (0.0295) time: 0.3580 data: 0.0043 max mem: 4840 +train: [14] [240/400] eta: 0:00:59 lr: 0.000086 loss: 0.1614 (0.1638) grad: 0.0284 (0.0295) time: 0.3674 data: 0.0042 max mem: 4840 +train: [14] [260/400] eta: 0:00:52 lr: 0.000085 loss: 0.1574 (0.1632) grad: 0.0306 (0.0297) time: 0.3638 data: 0.0043 max mem: 4840 +train: [14] [280/400] eta: 0:00:44 lr: 0.000083 loss: 0.1530 (0.1631) grad: 0.0306 (0.0298) time: 0.3617 data: 0.0044 max mem: 4840 +train: [14] [300/400] eta: 0:00:38 lr: 0.000082 loss: 0.1530 (0.1630) grad: 0.0291 (0.0297) time: 0.5414 data: 0.1783 max mem: 4840 +train: [14] [320/400] eta: 0:00:30 lr: 0.000081 loss: 0.1575 (0.1627) grad: 0.0294 (0.0297) time: 0.3751 data: 0.0040 max mem: 4840 +train: [14] [340/400] eta: 0:00:22 lr: 0.000079 loss: 0.1550 (0.1627) grad: 0.0290 (0.0297) time: 0.3612 data: 0.0040 max mem: 4840 +train: [14] [360/400] eta: 0:00:15 lr: 0.000078 loss: 0.1605 (0.1628) grad: 0.0281 (0.0296) time: 0.3480 data: 0.0042 max mem: 4840 +train: [14] [380/400] eta: 0:00:07 lr: 0.000076 loss: 0.1652 (0.1627) grad: 0.0284 (0.0296) time: 0.3844 data: 0.0043 max mem: 4840 +train: [14] [399/400] eta: 0:00:00 lr: 0.000075 loss: 0.1537 (0.1624) grad: 0.0286 (0.0296) time: 0.3720 data: 0.0044 max mem: 4840 +train: [14] Total time: 0:02:31 (0.3797 s / it) +train: [14] Summary: lr: 0.000075 loss: 0.1537 (0.1624) grad: 0.0286 (0.0296) +eval (validation): [14] [ 0/63] eta: 0:03:09 time: 3.0006 data: 2.8056 max mem: 4840 +eval (validation): [14] [20/63] eta: 0:00:19 time: 0.3328 data: 0.0303 max mem: 4840 +eval (validation): [14] [40/63] eta: 0:00:09 time: 0.3375 data: 0.0032 max mem: 4840 +eval (validation): [14] [60/63] eta: 0:00:01 time: 0.3057 data: 0.0029 max mem: 4840 +eval (validation): [14] [62/63] eta: 0:00:00 time: 0.3100 data: 0.0033 max mem: 4840 +eval (validation): [14] Total time: 0:00:23 (0.3728 s / it) +cv: [14] best hparam: (0.61, 1.0) (021) ('021_lr6.1e-01_wd1.0e+00') loss: 0.065 acc: 0.981 f1: 0.979 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__attn/checkpoint-last.pth +train: [15] [ 0/400] eta: 0:22:29 lr: nan time: 3.3740 data: 3.0795 max mem: 4840 +train: [15] [ 20/400] eta: 0:03:17 lr: 0.000074 loss: 0.1667 (0.1695) grad: 0.0281 (0.0290) time: 0.3774 data: 0.0041 max mem: 4840 +train: [15] [ 40/400] eta: 0:02:38 lr: 0.000072 loss: 0.1667 (0.1658) grad: 0.0289 (0.0298) time: 0.3543 data: 0.0027 max mem: 4840 +train: [15] [ 60/400] eta: 0:02:17 lr: 0.000071 loss: 0.1606 (0.1640) grad: 0.0294 (0.0296) time: 0.3301 data: 0.0039 max mem: 4840 +train: [15] [ 80/400] eta: 0:02:03 lr: 0.000070 loss: 0.1458 (0.1623) grad: 0.0274 (0.0294) time: 0.3381 data: 0.0040 max mem: 4840 +train: [15] [100/400] eta: 0:01:53 lr: 0.000068 loss: 0.1458 (0.1584) grad: 0.0281 (0.0292) time: 0.3495 data: 0.0041 max mem: 4840 +train: [15] [120/400] eta: 0:01:44 lr: 0.000067 loss: 0.1588 (0.1607) grad: 0.0281 (0.0293) time: 0.3397 data: 0.0040 max mem: 4840 +train: [15] [140/400] eta: 0:01:36 lr: 0.000066 loss: 0.1609 (0.1608) grad: 0.0294 (0.0293) time: 0.3519 data: 0.0043 max mem: 4840 +train: [15] [160/400] eta: 0:01:28 lr: 0.000064 loss: 0.1483 (0.1591) grad: 0.0294 (0.0293) time: 0.3645 data: 0.0038 max mem: 4840 +train: [15] [180/400] eta: 0:01:21 lr: 0.000063 loss: 0.1511 (0.1599) grad: 0.0284 (0.0294) time: 0.3756 data: 0.0041 max mem: 4840 +train: [15] [200/400] eta: 0:01:14 lr: 0.000062 loss: 0.1554 (0.1594) grad: 0.0279 (0.0292) time: 0.3690 data: 0.0042 max mem: 4840 +train: [15] [220/400] eta: 0:01:06 lr: 0.000061 loss: 0.1496 (0.1589) grad: 0.0276 (0.0291) time: 0.3651 data: 0.0043 max mem: 4840 +train: [15] [240/400] eta: 0:00:59 lr: 0.000059 loss: 0.1416 (0.1574) grad: 0.0296 (0.0293) time: 0.3677 data: 0.0043 max mem: 4840 +train: [15] [260/400] eta: 0:00:51 lr: 0.000058 loss: 0.1419 (0.1572) grad: 0.0291 (0.0293) time: 0.3791 data: 0.0042 max mem: 4840 +train: [15] [280/400] eta: 0:00:44 lr: 0.000057 loss: 0.1499 (0.1570) grad: 0.0274 (0.0291) time: 0.3741 data: 0.0045 max mem: 4840 +train: [15] [300/400] eta: 0:00:38 lr: 0.000056 loss: 0.1517 (0.1566) grad: 0.0272 (0.0290) time: 0.5477 data: 0.1822 max mem: 4840 +train: [15] [320/400] eta: 0:00:30 lr: 0.000054 loss: 0.1454 (0.1560) grad: 0.0270 (0.0289) time: 0.4231 data: 0.0040 max mem: 4840 +train: [15] [340/400] eta: 0:00:23 lr: 0.000053 loss: 0.1539 (0.1566) grad: 0.0273 (0.0289) time: 0.3715 data: 0.0041 max mem: 4840 +train: [15] [360/400] eta: 0:00:15 lr: 0.000052 loss: 0.1633 (0.1573) grad: 0.0273 (0.0289) time: 0.3673 data: 0.0043 max mem: 4840 +train: [15] [380/400] eta: 0:00:07 lr: 0.000051 loss: 0.1643 (0.1578) grad: 0.0282 (0.0289) time: 0.3648 data: 0.0043 max mem: 4840 +train: [15] [399/400] eta: 0:00:00 lr: 0.000050 loss: 0.1512 (0.1573) grad: 0.0282 (0.0289) time: 0.3709 data: 0.0043 max mem: 4840 +train: [15] Total time: 0:02:32 (0.3821 s / it) +train: [15] Summary: lr: 0.000050 loss: 0.1512 (0.1573) grad: 0.0282 (0.0289) +eval (validation): [15] [ 0/63] eta: 0:03:07 time: 2.9818 data: 2.7785 max mem: 4840 +eval (validation): [15] [20/63] eta: 0:00:18 time: 0.3148 data: 0.0032 max mem: 4840 +eval (validation): [15] [40/63] eta: 0:00:08 time: 0.3369 data: 0.0037 max mem: 4840 +eval (validation): [15] [60/63] eta: 0:00:01 time: 0.2993 data: 0.0026 max mem: 4840 +eval (validation): [15] [62/63] eta: 0:00:00 time: 0.2928 data: 0.0029 max mem: 4840 +eval (validation): [15] Total time: 0:00:22 (0.3632 s / it) +cv: [15] best hparam: (0.52, 1.0) (020) ('020_lr5.2e-01_wd1.0e+00') loss: 0.066 acc: 0.981 f1: 0.979 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__attn/checkpoint-last.pth +train: [16] [ 0/400] eta: 0:24:13 lr: nan time: 3.6339 data: 3.3106 max mem: 4840 +train: [16] [ 20/400] eta: 0:03:43 lr: 0.000048 loss: 0.1512 (0.1607) grad: 0.0290 (0.0308) time: 0.4353 data: 0.0036 max mem: 4840 +train: [16] [ 40/400] eta: 0:02:51 lr: 0.000047 loss: 0.1549 (0.1567) grad: 0.0287 (0.0294) time: 0.3588 data: 0.0041 max mem: 4840 +train: [16] [ 60/400] eta: 0:02:29 lr: 0.000046 loss: 0.1584 (0.1574) grad: 0.0275 (0.0289) time: 0.3653 data: 0.0044 max mem: 4840 +train: [16] [ 80/400] eta: 0:02:15 lr: 0.000045 loss: 0.1578 (0.1553) grad: 0.0275 (0.0286) time: 0.3687 data: 0.0039 max mem: 4840 +train: [16] [100/400] eta: 0:02:02 lr: 0.000044 loss: 0.1397 (0.1517) grad: 0.0276 (0.0286) time: 0.3534 data: 0.0040 max mem: 4840 +train: [16] [120/400] eta: 0:01:50 lr: 0.000043 loss: 0.1368 (0.1526) grad: 0.0282 (0.0286) time: 0.3311 data: 0.0040 max mem: 4840 +train: [16] [140/400] eta: 0:01:41 lr: 0.000042 loss: 0.1581 (0.1534) grad: 0.0287 (0.0288) time: 0.3501 data: 0.0043 max mem: 4840 +train: [16] [160/400] eta: 0:01:33 lr: 0.000041 loss: 0.1541 (0.1527) grad: 0.0280 (0.0286) time: 0.3782 data: 0.0041 max mem: 4840 +train: [16] [180/400] eta: 0:01:24 lr: 0.000040 loss: 0.1526 (0.1536) grad: 0.0285 (0.0288) time: 0.3626 data: 0.0040 max mem: 4840 +train: [16] [200/400] eta: 0:01:16 lr: 0.000039 loss: 0.1501 (0.1536) grad: 0.0280 (0.0289) time: 0.3454 data: 0.0037 max mem: 4840 +train: [16] [220/400] eta: 0:01:07 lr: 0.000038 loss: 0.1501 (0.1538) grad: 0.0279 (0.0288) time: 0.3397 data: 0.0041 max mem: 4840 +train: [16] [240/400] eta: 0:00:59 lr: 0.000036 loss: 0.1542 (0.1547) grad: 0.0281 (0.0290) time: 0.3398 data: 0.0043 max mem: 4840 +train: [16] [260/400] eta: 0:00:52 lr: 0.000035 loss: 0.1536 (0.1543) grad: 0.0273 (0.0288) time: 0.3534 data: 0.0043 max mem: 4840 +train: [16] [280/400] eta: 0:00:44 lr: 0.000034 loss: 0.1509 (0.1541) grad: 0.0272 (0.0289) time: 0.3738 data: 0.0043 max mem: 4840 +train: [16] [300/400] eta: 0:00:38 lr: 0.000033 loss: 0.1482 (0.1539) grad: 0.0289 (0.0289) time: 0.5404 data: 0.1848 max mem: 4840 +train: [16] [320/400] eta: 0:00:30 lr: 0.000032 loss: 0.1574 (0.1544) grad: 0.0289 (0.0289) time: 0.3787 data: 0.0040 max mem: 4840 +train: [16] [340/400] eta: 0:00:22 lr: 0.000031 loss: 0.1440 (0.1534) grad: 0.0277 (0.0288) time: 0.3637 data: 0.0040 max mem: 4840 +train: [16] [360/400] eta: 0:00:15 lr: 0.000031 loss: 0.1484 (0.1545) grad: 0.0279 (0.0288) time: 0.3666 data: 0.0042 max mem: 4840 +train: [16] [380/400] eta: 0:00:07 lr: 0.000030 loss: 0.1524 (0.1539) grad: 0.0279 (0.0287) time: 0.3567 data: 0.0043 max mem: 4840 +train: [16] [399/400] eta: 0:00:00 lr: 0.000029 loss: 0.1492 (0.1540) grad: 0.0279 (0.0288) time: 0.3763 data: 0.0041 max mem: 4840 +train: [16] Total time: 0:02:32 (0.3807 s / it) +train: [16] Summary: lr: 0.000029 loss: 0.1492 (0.1540) grad: 0.0279 (0.0288) +eval (validation): [16] [ 0/63] eta: 0:03:33 time: 3.3902 data: 3.0855 max mem: 4840 +eval (validation): [16] [20/63] eta: 0:00:21 time: 0.3484 data: 0.0044 max mem: 4840 +eval (validation): [16] [40/63] eta: 0:00:09 time: 0.3416 data: 0.0031 max mem: 4840 +eval (validation): [16] [60/63] eta: 0:00:01 time: 0.3040 data: 0.0039 max mem: 4840 +eval (validation): [16] [62/63] eta: 0:00:00 time: 0.3032 data: 0.0040 max mem: 4840 +eval (validation): [16] Total time: 0:00:24 (0.3841 s / it) +cv: [16] best hparam: (0.44, 1.0) (019) ('019_lr4.4e-01_wd1.0e+00') loss: 0.069 acc: 0.981 f1: 0.979 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__attn/checkpoint-last.pth +train: [17] [ 0/400] eta: 0:22:35 lr: nan time: 3.3896 data: 3.1371 max mem: 4840 +train: [17] [ 20/400] eta: 0:03:36 lr: 0.000028 loss: 0.1444 (0.1514) grad: 0.0262 (0.0272) time: 0.4285 data: 0.0035 max mem: 4840 +train: [17] [ 40/400] eta: 0:02:49 lr: 0.000027 loss: 0.1444 (0.1489) grad: 0.0277 (0.0277) time: 0.3675 data: 0.0038 max mem: 4840 +train: [17] [ 60/400] eta: 0:02:26 lr: 0.000026 loss: 0.1322 (0.1481) grad: 0.0275 (0.0280) time: 0.3515 data: 0.0043 max mem: 4840 +train: [17] [ 80/400] eta: 0:02:13 lr: 0.000025 loss: 0.1520 (0.1502) grad: 0.0278 (0.0281) time: 0.3686 data: 0.0044 max mem: 4840 +train: [17] [100/400] eta: 0:02:02 lr: 0.000024 loss: 0.1557 (0.1514) grad: 0.0284 (0.0283) time: 0.3716 data: 0.0040 max mem: 4840 +train: [17] [120/400] eta: 0:01:51 lr: 0.000023 loss: 0.1536 (0.1519) grad: 0.0275 (0.0281) time: 0.3476 data: 0.0041 max mem: 4840 +train: [17] [140/400] eta: 0:01:42 lr: 0.000023 loss: 0.1498 (0.1520) grad: 0.0276 (0.0281) time: 0.3710 data: 0.0043 max mem: 4840 +train: [17] [160/400] eta: 0:01:33 lr: 0.000022 loss: 0.1451 (0.1511) grad: 0.0284 (0.0281) time: 0.3628 data: 0.0045 max mem: 4840 +train: [17] [180/400] eta: 0:01:25 lr: 0.000021 loss: 0.1451 (0.1508) grad: 0.0272 (0.0280) time: 0.3757 data: 0.0042 max mem: 4840 +train: [17] [200/400] eta: 0:01:17 lr: 0.000020 loss: 0.1410 (0.1494) grad: 0.0273 (0.0281) time: 0.3680 data: 0.0040 max mem: 4840 +train: [17] [220/400] eta: 0:01:08 lr: 0.000019 loss: 0.1450 (0.1503) grad: 0.0287 (0.0282) time: 0.3499 data: 0.0039 max mem: 4840 +train: [17] [240/400] eta: 0:01:00 lr: 0.000019 loss: 0.1517 (0.1498) grad: 0.0293 (0.0281) time: 0.3589 data: 0.0041 max mem: 4840 +train: [17] [260/400] eta: 0:00:53 lr: 0.000018 loss: 0.1482 (0.1505) grad: 0.0279 (0.0282) time: 0.3598 data: 0.0040 max mem: 4840 +train: [17] [280/400] eta: 0:00:45 lr: 0.000017 loss: 0.1482 (0.1505) grad: 0.0280 (0.0283) time: 0.3651 data: 0.0043 max mem: 4840 +train: [17] [300/400] eta: 0:00:39 lr: 0.000016 loss: 0.1502 (0.1507) grad: 0.0278 (0.0282) time: 0.5578 data: 0.1904 max mem: 4840 +train: [17] [320/400] eta: 0:00:31 lr: 0.000016 loss: 0.1502 (0.1506) grad: 0.0266 (0.0281) time: 0.3578 data: 0.0032 max mem: 4840 +train: [17] [340/400] eta: 0:00:23 lr: 0.000015 loss: 0.1420 (0.1502) grad: 0.0276 (0.0282) time: 0.3554 data: 0.0034 max mem: 4840 +train: [17] [360/400] eta: 0:00:15 lr: 0.000014 loss: 0.1413 (0.1501) grad: 0.0280 (0.0282) time: 0.3456 data: 0.0044 max mem: 4840 +train: [17] [380/400] eta: 0:00:07 lr: 0.000014 loss: 0.1515 (0.1508) grad: 0.0280 (0.0282) time: 0.3595 data: 0.0043 max mem: 4840 +train: [17] [399/400] eta: 0:00:00 lr: 0.000013 loss: 0.1575 (0.1510) grad: 0.0278 (0.0282) time: 0.3497 data: 0.0040 max mem: 4840 +train: [17] Total time: 0:02:32 (0.3817 s / it) +train: [17] Summary: lr: 0.000013 loss: 0.1575 (0.1510) grad: 0.0278 (0.0282) +eval (validation): [17] [ 0/63] eta: 0:03:32 time: 3.3742 data: 3.0932 max mem: 4840 +eval (validation): [17] [20/63] eta: 0:00:21 time: 0.3610 data: 0.0044 max mem: 4840 +eval (validation): [17] [40/63] eta: 0:00:09 time: 0.3248 data: 0.0033 max mem: 4840 +eval (validation): [17] [60/63] eta: 0:00:01 time: 0.3213 data: 0.0036 max mem: 4840 +eval (validation): [17] [62/63] eta: 0:00:00 time: 0.3125 data: 0.0036 max mem: 4840 +eval (validation): [17] Total time: 0:00:24 (0.3868 s / it) +cv: [17] best hparam: (1, 1.0) (024) ('024_lr1.0e+00_wd1.0e+00') loss: 0.063 acc: 0.981 f1: 0.979 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__attn/checkpoint-last.pth +train: [18] [ 0/400] eta: 0:22:45 lr: nan time: 3.4142 data: 3.1027 max mem: 4840 +train: [18] [ 20/400] eta: 0:03:21 lr: 0.000012 loss: 0.1561 (0.1573) grad: 0.0280 (0.0288) time: 0.3863 data: 0.0042 max mem: 4840 +train: [18] [ 40/400] eta: 0:02:41 lr: 0.000012 loss: 0.1540 (0.1565) grad: 0.0282 (0.0289) time: 0.3624 data: 0.0037 max mem: 4840 +train: [18] [ 60/400] eta: 0:02:22 lr: 0.000011 loss: 0.1527 (0.1536) grad: 0.0280 (0.0286) time: 0.3632 data: 0.0042 max mem: 4840 +train: [18] [ 80/400] eta: 0:02:10 lr: 0.000011 loss: 0.1482 (0.1519) grad: 0.0271 (0.0284) time: 0.3635 data: 0.0044 max mem: 4840 +train: [18] [100/400] eta: 0:01:59 lr: 0.000010 loss: 0.1434 (0.1503) grad: 0.0277 (0.0282) time: 0.3614 data: 0.0044 max mem: 4840 +train: [18] [120/400] eta: 0:01:49 lr: 0.000009 loss: 0.1418 (0.1498) grad: 0.0272 (0.0282) time: 0.3574 data: 0.0043 max mem: 4840 +train: [18] [140/400] eta: 0:01:39 lr: 0.000009 loss: 0.1469 (0.1506) grad: 0.0283 (0.0285) time: 0.3395 data: 0.0043 max mem: 4840 +train: [18] [160/400] eta: 0:01:31 lr: 0.000008 loss: 0.1491 (0.1510) grad: 0.0274 (0.0283) time: 0.3573 data: 0.0045 max mem: 4840 +train: [18] [180/400] eta: 0:01:23 lr: 0.000008 loss: 0.1428 (0.1498) grad: 0.0271 (0.0283) time: 0.3813 data: 0.0040 max mem: 4840 +train: [18] [200/400] eta: 0:01:15 lr: 0.000007 loss: 0.1359 (0.1486) grad: 0.0275 (0.0282) time: 0.3633 data: 0.0043 max mem: 4840 +train: [18] [220/400] eta: 0:01:08 lr: 0.000007 loss: 0.1359 (0.1489) grad: 0.0280 (0.0283) time: 0.3704 data: 0.0041 max mem: 4840 +train: [18] [240/400] eta: 0:01:00 lr: 0.000006 loss: 0.1496 (0.1493) grad: 0.0278 (0.0283) time: 0.3658 data: 0.0044 max mem: 4840 +train: [18] [260/400] eta: 0:00:52 lr: 0.000006 loss: 0.1496 (0.1493) grad: 0.0274 (0.0283) time: 0.3522 data: 0.0042 max mem: 4840 +train: [18] [280/400] eta: 0:00:44 lr: 0.000006 loss: 0.1427 (0.1484) grad: 0.0274 (0.0282) time: 0.3594 data: 0.0044 max mem: 4840 +train: [18] [300/400] eta: 0:00:38 lr: 0.000005 loss: 0.1436 (0.1482) grad: 0.0293 (0.0284) time: 0.5491 data: 0.1856 max mem: 4840 +train: [18] [320/400] eta: 0:00:30 lr: 0.000005 loss: 0.1464 (0.1482) grad: 0.0291 (0.0283) time: 0.3977 data: 0.0039 max mem: 4840 +train: [18] [340/400] eta: 0:00:23 lr: 0.000004 loss: 0.1554 (0.1489) grad: 0.0279 (0.0284) time: 0.3613 data: 0.0043 max mem: 4840 +train: [18] [360/400] eta: 0:00:15 lr: 0.000004 loss: 0.1562 (0.1491) grad: 0.0287 (0.0284) time: 0.3614 data: 0.0044 max mem: 4840 +train: [18] [380/400] eta: 0:00:07 lr: 0.000004 loss: 0.1455 (0.1488) grad: 0.0284 (0.0284) time: 0.3605 data: 0.0044 max mem: 4840 +train: [18] [399/400] eta: 0:00:00 lr: 0.000003 loss: 0.1454 (0.1490) grad: 0.0274 (0.0283) time: 0.3534 data: 0.0039 max mem: 4840 +train: [18] Total time: 0:02:32 (0.3815 s / it) +train: [18] Summary: lr: 0.000003 loss: 0.1454 (0.1490) grad: 0.0274 (0.0283) +eval (validation): [18] [ 0/63] eta: 0:03:26 time: 3.2789 data: 3.0582 max mem: 4840 +eval (validation): [18] [20/63] eta: 0:00:20 time: 0.3336 data: 0.0183 max mem: 4840 +eval (validation): [18] [40/63] eta: 0:00:09 time: 0.3304 data: 0.0068 max mem: 4840 +eval (validation): [18] [60/63] eta: 0:00:01 time: 0.3074 data: 0.0029 max mem: 4840 +eval (validation): [18] [62/63] eta: 0:00:00 time: 0.3048 data: 0.0029 max mem: 4840 +eval (validation): [18] Total time: 0:00:23 (0.3749 s / it) +cv: [18] best hparam: (0.85, 1.0) (023) ('023_lr8.5e-01_wd1.0e+00') loss: 0.063 acc: 0.981 f1: 0.978 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__attn/checkpoint-last.pth +train: [19] [ 0/400] eta: 0:24:04 lr: nan time: 3.6123 data: 3.3470 max mem: 4840 +train: [19] [ 20/400] eta: 0:03:09 lr: 0.000003 loss: 0.1507 (0.1509) grad: 0.0276 (0.0277) time: 0.3423 data: 0.0036 max mem: 4840 +train: [19] [ 40/400] eta: 0:02:35 lr: 0.000003 loss: 0.1428 (0.1439) grad: 0.0269 (0.0277) time: 0.3638 data: 0.0035 max mem: 4840 +train: [19] [ 60/400] eta: 0:02:18 lr: 0.000002 loss: 0.1407 (0.1431) grad: 0.0269 (0.0281) time: 0.3537 data: 0.0031 max mem: 4840 +train: [19] [ 80/400] eta: 0:02:05 lr: 0.000002 loss: 0.1460 (0.1456) grad: 0.0275 (0.0280) time: 0.3478 data: 0.0041 max mem: 4840 +train: [19] [100/400] eta: 0:01:56 lr: 0.000002 loss: 0.1535 (0.1461) grad: 0.0275 (0.0281) time: 0.3771 data: 0.0042 max mem: 4840 +train: [19] [120/400] eta: 0:01:48 lr: 0.000002 loss: 0.1554 (0.1477) grad: 0.0279 (0.0281) time: 0.3791 data: 0.0042 max mem: 4840 +train: [19] [140/400] eta: 0:01:39 lr: 0.000001 loss: 0.1560 (0.1496) grad: 0.0283 (0.0281) time: 0.3469 data: 0.0039 max mem: 4840 +train: [19] [160/400] eta: 0:01:30 lr: 0.000001 loss: 0.1481 (0.1499) grad: 0.0283 (0.0283) time: 0.3493 data: 0.0043 max mem: 4840 +train: [19] [180/400] eta: 0:01:22 lr: 0.000001 loss: 0.1473 (0.1503) grad: 0.0275 (0.0281) time: 0.3663 data: 0.0044 max mem: 4840 +train: [19] [200/400] eta: 0:01:15 lr: 0.000001 loss: 0.1525 (0.1511) grad: 0.0270 (0.0281) time: 0.3809 data: 0.0043 max mem: 4840 +train: [19] [220/400] eta: 0:01:07 lr: 0.000001 loss: 0.1530 (0.1524) grad: 0.0271 (0.0281) time: 0.3563 data: 0.0039 max mem: 4840 +train: [19] [240/400] eta: 0:00:59 lr: 0.000001 loss: 0.1582 (0.1533) grad: 0.0274 (0.0282) time: 0.3571 data: 0.0040 max mem: 4840 +train: [19] [260/400] eta: 0:00:52 lr: 0.000000 loss: 0.1488 (0.1528) grad: 0.0283 (0.0282) time: 0.3881 data: 0.0042 max mem: 4840 +train: [19] [280/400] eta: 0:00:44 lr: 0.000000 loss: 0.1419 (0.1526) grad: 0.0279 (0.0282) time: 0.3752 data: 0.0041 max mem: 4840 +train: [19] [300/400] eta: 0:00:38 lr: 0.000000 loss: 0.1481 (0.1533) grad: 0.0269 (0.0282) time: 0.5551 data: 0.1854 max mem: 4840 +train: [19] [320/400] eta: 0:00:30 lr: 0.000000 loss: 0.1572 (0.1537) grad: 0.0271 (0.0282) time: 0.3716 data: 0.0034 max mem: 4840 +train: [19] [340/400] eta: 0:00:23 lr: 0.000000 loss: 0.1565 (0.1536) grad: 0.0274 (0.0282) time: 0.3707 data: 0.0041 max mem: 4840 +train: [19] [360/400] eta: 0:00:15 lr: 0.000000 loss: 0.1600 (0.1536) grad: 0.0271 (0.0282) time: 0.3681 data: 0.0042 max mem: 4840 +train: [19] [380/400] eta: 0:00:07 lr: 0.000000 loss: 0.1594 (0.1541) grad: 0.0278 (0.0283) time: 0.3515 data: 0.0040 max mem: 4840 +train: [19] [399/400] eta: 0:00:00 lr: 0.000000 loss: 0.1579 (0.1544) grad: 0.0278 (0.0283) time: 0.3727 data: 0.0044 max mem: 4840 +train: [19] Total time: 0:02:32 (0.3823 s / it) +train: [19] Summary: lr: 0.000000 loss: 0.1579 (0.1544) grad: 0.0278 (0.0283) +eval (validation): [19] [ 0/63] eta: 0:03:29 time: 3.3249 data: 3.1005 max mem: 4840 +eval (validation): [19] [20/63] eta: 0:00:19 time: 0.3208 data: 0.0049 max mem: 4840 +eval (validation): [19] [40/63] eta: 0:00:09 time: 0.3273 data: 0.0023 max mem: 4840 +eval (validation): [19] [60/63] eta: 0:00:01 time: 0.3213 data: 0.0033 max mem: 4840 +eval (validation): [19] [62/63] eta: 0:00:00 time: 0.3191 data: 0.0032 max mem: 4840 +eval (validation): [19] Total time: 0:00:23 (0.3757 s / it) +cv: [19] best hparam: (0.85, 1.0) (023) ('023_lr8.5e-01_wd1.0e+00') loss: 0.063 acc: 0.981 f1: 0.978 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__attn/checkpoint-last.pth +evaluating last checkpoint: experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__attn/checkpoint-last.pth +eval model info: +{"score": 0.9809027777777778, "hparam": [0.85, 1.0], "hparam_id": 23, "epoch": 19, "is_best": false, "best_score": 0.9818948412698413} +eval (train): [20] [ 0/297] eta: 0:13:45 time: 2.7781 data: 2.5479 max mem: 4840 +eval (train): [20] [ 20/297] eta: 0:01:57 time: 0.3056 data: 0.0026 max mem: 4840 +eval (train): [20] [ 40/297] eta: 0:01:40 time: 0.3540 data: 0.0040 max mem: 4840 +eval (train): [20] [ 60/297] eta: 0:01:31 time: 0.3802 data: 0.0041 max mem: 4840 +eval (train): [20] [ 80/297] eta: 0:01:21 time: 0.3434 data: 0.0036 max mem: 4840 +eval (train): [20] [100/297] eta: 0:01:12 time: 0.3366 data: 0.0034 max mem: 4840 +eval (train): [20] [120/297] eta: 0:01:04 time: 0.3381 data: 0.0034 max mem: 4840 +eval (train): [20] [140/297] eta: 0:00:56 time: 0.3362 data: 0.0034 max mem: 4840 +eval (train): [20] [160/297] eta: 0:00:48 time: 0.3420 data: 0.0035 max mem: 4840 +eval (train): [20] [180/297] eta: 0:00:41 time: 0.3591 data: 0.0037 max mem: 4840 +eval (train): [20] [200/297] eta: 0:00:34 time: 0.3441 data: 0.0033 max mem: 4840 +eval (train): [20] [220/297] eta: 0:00:27 time: 0.3522 data: 0.0037 max mem: 4840 +eval (train): [20] [240/297] eta: 0:00:20 time: 0.3545 data: 0.0034 max mem: 4840 +eval (train): [20] [260/297] eta: 0:00:13 time: 0.3387 data: 0.0037 max mem: 4840 +eval (train): [20] [280/297] eta: 0:00:06 time: 0.3649 data: 0.0038 max mem: 4840 +eval (train): [20] [296/297] eta: 0:00:00 time: 0.3369 data: 0.0037 max mem: 4840 +eval (train): [20] Total time: 0:01:45 (0.3545 s / it) +eval (validation): [20] [ 0/63] eta: 0:03:17 time: 3.1380 data: 2.8735 max mem: 4840 +eval (validation): [20] [20/63] eta: 0:00:20 time: 0.3492 data: 0.0044 max mem: 4840 +eval (validation): [20] [40/63] eta: 0:00:09 time: 0.3500 data: 0.0034 max mem: 4840 +eval (validation): [20] [60/63] eta: 0:00:01 time: 0.3266 data: 0.0031 max mem: 4840 +eval (validation): [20] [62/63] eta: 0:00:00 time: 0.3150 data: 0.0032 max mem: 4840 +eval (validation): [20] Total time: 0:00:24 (0.3891 s / it) +eval (test): [20] [ 0/79] eta: 0:04:08 time: 3.1514 data: 2.8668 max mem: 4840 +eval (test): [20] [20/79] eta: 0:00:30 time: 0.3868 data: 0.0043 max mem: 4840 +eval (test): [20] [40/79] eta: 0:00:17 time: 0.3575 data: 0.0034 max mem: 4840 +eval (test): [20] [60/79] eta: 0:00:07 time: 0.3336 data: 0.0037 max mem: 4840 +eval (test): [20] [78/79] eta: 0:00:00 time: 0.2950 data: 0.0030 max mem: 4840 +eval (test): [20] Total time: 0:00:30 (0.3832 s / it) +evaluating best checkpoint: experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__attn/checkpoint-best.pth +eval model info: +{"score": 0.9818948412698413, "hparam": [0.85, 1.0], "hparam_id": 23, "epoch": 8, "is_best": true, "best_score": 0.9818948412698413} +eval (train): [20] [ 0/297] eta: 0:15:37 time: 3.1577 data: 2.8724 max mem: 4840 +eval (train): [20] [ 20/297] eta: 0:02:21 time: 0.3779 data: 0.0046 max mem: 4840 +eval (train): [20] [ 40/297] eta: 0:01:48 time: 0.3306 data: 0.0030 max mem: 4840 +eval (train): [20] [ 60/297] eta: 0:01:31 time: 0.3149 data: 0.0032 max mem: 4840 +eval (train): [20] [ 80/297] eta: 0:01:20 time: 0.3213 data: 0.0035 max mem: 4840 +eval (train): [20] [100/297] eta: 0:01:13 time: 0.3824 data: 0.0039 max mem: 4840 +eval (train): [20] [120/297] eta: 0:01:05 time: 0.3626 data: 0.0037 max mem: 4840 +eval (train): [20] [140/297] eta: 0:00:58 time: 0.3713 data: 0.0037 max mem: 4840 +eval (train): [20] [160/297] eta: 0:00:50 time: 0.3432 data: 0.0038 max mem: 4840 +eval (train): [20] [180/297] eta: 0:00:42 time: 0.3187 data: 0.0033 max mem: 4840 +eval (train): [20] [200/297] eta: 0:00:35 time: 0.3490 data: 0.0039 max mem: 4840 +eval (train): [20] [220/297] eta: 0:00:28 time: 0.3907 data: 0.0040 max mem: 4840 +eval (train): [20] [240/297] eta: 0:00:20 time: 0.3616 data: 0.0034 max mem: 4840 +eval (train): [20] [260/297] eta: 0:00:13 time: 0.3412 data: 0.0037 max mem: 4840 +eval (train): [20] [280/297] eta: 0:00:06 time: 0.3214 data: 0.0031 max mem: 4840 +eval (train): [20] [296/297] eta: 0:00:00 time: 0.2961 data: 0.0033 max mem: 4840 +eval (train): [20] Total time: 0:01:46 (0.3579 s / it) +eval (validation): [20] [ 0/63] eta: 0:03:13 time: 3.0700 data: 2.8401 max mem: 4840 +eval (validation): [20] [20/63] eta: 0:00:21 time: 0.3734 data: 0.0037 max mem: 4840 +eval (validation): [20] [40/63] eta: 0:00:10 time: 0.3928 data: 0.0033 max mem: 4840 +eval (validation): [20] [60/63] eta: 0:00:01 time: 0.3164 data: 0.0030 max mem: 4840 +eval (validation): [20] [62/63] eta: 0:00:00 time: 0.3156 data: 0.0032 max mem: 4840 +eval (validation): [20] Total time: 0:00:25 (0.4062 s / it) +eval (test): [20] [ 0/79] eta: 0:04:06 time: 3.1213 data: 2.8250 max mem: 4840 +eval (test): [20] [20/79] eta: 0:00:28 time: 0.3435 data: 0.0037 max mem: 4840 +eval (test): [20] [40/79] eta: 0:00:16 time: 0.3537 data: 0.0032 max mem: 4840 +eval (test): [20] [60/79] eta: 0:00:07 time: 0.3345 data: 0.0030 max mem: 4840 +eval (test): [20] [78/79] eta: 0:00:00 time: 0.3188 data: 0.0034 max mem: 4840 +eval (test): [20] Total time: 0:00:29 (0.3757 s / it) +eval results: + +| model | repr | clf | dataset | ckpt | epoch | lr | wd | hparam_id | hparam | split | loss | acc | acc_std | f1 | f1_std | +|:---------|:-------|:------|:-------------|:-------|--------:|---------:|-----:|------------:|:------------|:-----------|---------:|--------:|----------:|--------:|-----------:| +| flat_mae | reg | attn | hcpya_task21 | best | 8 | 0.000255 | 0.05 | 23 | [0.85, 1.0] | train | 0.035422 | 0.99384 | 0.0005515 | 0.99363 | 0.00062565 | +| flat_mae | reg | attn | hcpya_task21 | best | 8 | 0.000255 | 0.05 | 23 | [0.85, 1.0] | validation | 0.067142 | 0.98189 | 0.0019292 | 0.97991 | 0.0024497 | +| flat_mae | reg | attn | hcpya_task21 | best | 8 | 0.000255 | 0.05 | 23 | [0.85, 1.0] | test | 0.086062 | 0.97421 | 0.0022555 | 0.96839 | 0.0030264 | + + +done! total time: 1:06:05 diff --git a/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__attn/train_log.json b/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__attn/train_log.json new file mode 100644 index 0000000000000000000000000000000000000000..23825abf025a3238dc5cee45624e5a2f9f2ab544 --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__attn/train_log.json @@ -0,0 +1,20 @@ +{"epoch": 0, "train/lr": 2.987987987987988e-05, "train/loss": 2.318310110569, "train/grad": 0.08097647909075022, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.03273681640625, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.031824951171875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.0303369140625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.0289013671875, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.027420654296875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.025384521484375, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.023028564453125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.020250244140625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.016868896484375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.01293212890625, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.009195556640625, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.003271484375, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.99744140625, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.9887890625, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.980086669921875, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.971341552734375, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.959786376953125, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.9453521728515626, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.928099365234375, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.91083740234375, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.8878924560546877, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.86212646484375, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.830894775390625, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.7944375610351564, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.7530226135253906, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.698677215576172, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.64515998840332, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.592171936035156, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.5137693786621096, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.412235813140869, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.3154266929626464, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.22463632106781, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.1007599115371702, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.9913378059864044, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.8661803692579269, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.7488606241345406, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.6314548727869989, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.5274377108365298, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.4227432274073362, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.30329475030303, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.2186984680965542, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.1497676226496696, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.0671994645148515, "train/loss_043_lr2.2e+01_wd1.0e+00": 1.0020818641968072, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.9333872061595321, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.8670817799586803, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.8155673902295529, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.7599133197125048, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.7170942603424192, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.012684944798238576, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.012681132457219064, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.012675428381189704, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.012670026975683868, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.012664889418520033, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.012657125117257237, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.012648677686229348, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.012639566813595593, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.012628564075566829, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.012617647503502668, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.012607602374628187, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.012594124139286577, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.012582428324967622, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.012568863420747221, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.012558778026141226, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.012551869614981115, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.012546814610250295, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.012546184356324375, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.0125502695934847, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.01255782148335129, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.01256762855220586, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.012571402858011425, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.012561876513063907, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.012533700447529555, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.012489523314870894, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.01243657510727644, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.012397049115970732, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.01236276885960251, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.01230320462025702, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.012190418215468526, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.012038944335654379, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.011859364463016392, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.011569044853094965, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.011284447195939719, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.010935696507804096, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.010580786704085767, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.010184986698441208, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.009812288727844135, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.009447539895772935, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.009043790313880891, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.008744096104055642, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.008485549145843834, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.008174361002165825, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.007943270601099357, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.007696757504018024, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.007476097338367254, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.007339967001462356, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.007242287457338534, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.007203951042611152, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.020576238632202, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.017874002456665, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.0133962631225586, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.008848190307617, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.004317283630371, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.998016357421875, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.990819215774536, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.9827311038970947, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.9720075130462646, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.96037220954895, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.9488112926483154, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.931058168411255, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.9133410453796387, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.886854887008667, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.8604280948638916, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.8339409828186035, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.798743486404419, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.754641532897949, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.7018303871154785, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.649031400680542, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.5790469646453857, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.501413345336914, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.408607006072998, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.3022916316986084, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.182441234588623, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.0249714851379395, "validation/loss_026_lr1.4e+00_wd1.0e+00": 1.8682596683502197, "validation/loss_027_lr1.6e+00_wd1.0e+00": 1.713599443435669, "validation/loss_028_lr1.9e+00_wd1.0e+00": 1.491042971611023, "validation/loss_029_lr2.3e+00_wd1.0e+00": 1.2236757278442383, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.9988510012626648, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.818135142326355, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.6180427074432373, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.4813240170478821, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.3632878065109253, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.2833274006843567, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.22745247185230255, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.192575603723526, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.16604644060134888, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.1430409997701645, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.130295068025589, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.12101920694112778, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.11173788458108902, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.10608742386102676, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.10282745212316513, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.10437458008527756, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.1098693236708641, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.11554619669914246, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.11898266524076462, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.15079365079365079, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.16989087301587302, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.1956845238095238, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.21106150793650794, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.22073412698412698, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.22842261904761904, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.23288690476190477, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.23462301587301587, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.23363095238095238, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.23065476190476192, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.23040674603174602, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.2269345238095238, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.2251984126984127, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.22321428571428573, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.22172619047619047, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.22098214285714285, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.22395833333333334, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.22643849206349206, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.23214285714285715, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.2425595238095238, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.2586805555555556, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.27901785714285715, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.3117559523809524, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.36607142857142855, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.466765873015873, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.6130952380952381, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.6917162698412699, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.7189980158730159, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.7584325396825397, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.8214285714285714, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.8737599206349206, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9072420634920635, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9295634920634921, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9389880952380952, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9446924603174603, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9516369047619048, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9548611111111112, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9590773809523809, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9623015873015873, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9652777777777778, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9672619047619048, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9677579365079365, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9702380952380952, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9699900793650794, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9694940476190477, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9677579365079365, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9650297619047619, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9618055555555556, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9615575396825397, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.04921390301043273, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.052620011607161066, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.058292930818379475, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.0610800880388625, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.06466180781542696, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.0676373903589349, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.07068362139861505, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.07606328332682788, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.07953945353832707, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.08312672735900213, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.08601103620583618, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.08561123289418052, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.08474116479369019, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.08267156081070033, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.08016357353682392, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.07836197231909448, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.08122147961675481, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.083787577349407, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.09103145720456836, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.10232248645396691, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.11937352728374578, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.14080570799693531, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.17234234302907106, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.22445391883820653, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.3171873088948943, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.41817279798610424, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.47092212967719826, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.5037154822048251, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.5874684992096976, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.7155045980543566, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.8110584984075957, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.8812252774651218, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9172987781785442, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9293035858335986, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9357213275448043, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9441625100516917, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9478710638145174, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9526072023651496, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9562716287730111, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9596094335344526, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9628755946168025, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9631601989965448, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.966663142627301, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9657320775745758, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9648513534821167, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.962939498659264, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9577416333483748, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9546616957340051, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9566424562168085, "id_best": 42, "lr_best": 0.005699999999999999, "wd_best": 0.05, "train/loss_best": 1.0671994645148515, "validation/loss_best": 0.11173788458108902, "validation/acc_best": 0.9702380952380952, "validation/f1_best": 0.966663142627301} +{"epoch": 1, "train/lr": 8.993993993993998e-05, "train/loss": 1.4233188039064408, "train/grad": 0.06817602306604385, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.996439208984375, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.990087890625, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.979703369140625, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.96919677734375, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.9587744140625, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.944246826171875, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.927493896484375, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.9087890625, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.884013671875, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.8569500732421873, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.830096435546875, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.7887274169921876, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.7473248291015624, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.685648193359375, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.624581298828125, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.564217071533203, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.4847967529296877, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.386708221435547, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.2701873779296875, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.155091094970703, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.0049067878723146, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.8429113578796388, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.658941855430603, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.4643298482894898, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.2710671675205232, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.0597825828194618, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.8920687535405158, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.7584336158633233, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.6063004432618618, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.4663579499721527, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.3726072413474321, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.30823522303253414, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.24499784793704749, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.20537393853999675, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.17231861753389238, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.14947017507627605, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.13205962828360499, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.11983061908744276, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.10999190837144851, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.10150113156996668, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.09682310844771563, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.09360574123449623, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.09010899691842496, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.08723063126206398, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.08513037217780947, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.08728190579451621, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.09119637358002365, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.09890252556651831, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.11778226820752025, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.012493577543646097, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.012478654300794005, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.012455792087130248, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.012437932761386036, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.012423793720081448, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.012409719601273538, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.012401034021750093, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.012399549908004702, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.012407370735891163, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.012425857610069216, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.012449888056144118, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.01248818145133555, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.01251636705826968, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.012527907178737223, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.012500522038899363, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.012449525776319206, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.012370948898606002, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.01228151195216924, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.012182581960223616, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.012073976099491119, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.011886285576038063, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.01161713657900691, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.011233613640069962, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.010754556066822261, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.010207896714564412, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.009507817889098078, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.008857357762753964, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.008267537605715915, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.007508429668378085, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.006741481153294444, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.006199919580249116, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.00581574384123087, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.00540757566341199, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.005123953814618289, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.00487752492132131, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.004719088005949743, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.004618768992368132, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.004564740986097604, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.004568614370073192, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.004652345875510946, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0047586370131466535, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0048493091436102986, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.004889268531696871, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.004856471744715236, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.004921196065261028, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.005280194794177078, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.005571857217000797, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0061680353683186695, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.006998706997837872, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.9661412239074707, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.955366611480713, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.9374337196350098, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.919567108154297, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.901731014251709, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.876826047897339, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.8483214378356934, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.816274881362915, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.773496150970459, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.7271125316619873, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.680661916732788, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.6095738410949707, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.539048671722412, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.4354190826416016, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.3346431255340576, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.235867738723755, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.1055891513824463, "validation/loss_017_lr3.2e-01_wd1.0e+00": 1.9429175853729248, "validation/loss_018_lr3.8e-01_wd1.0e+00": 1.7484098672866821, "validation/loss_019_lr4.4e-01_wd1.0e+00": 1.559279203414917, "validation/loss_020_lr5.2e-01_wd1.0e+00": 1.3249123096466064, "validation/loss_021_lr6.1e-01_wd1.0e+00": 1.0954207181930542, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.8693944215774536, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.6719406843185425, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.515735387802124, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.3849357068538666, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.30579233169555664, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.25572139024734497, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.20971423387527466, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.17504878342151642, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.15444280207157135, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.14088067412376404, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.12731832265853882, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.11810518056154251, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.10913972556591034, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.10286711156368256, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.09814378619194031, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.09462112188339233, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.09326563775539398, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.0975428894162178, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.10119505971670151, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.09997899830341339, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.0944485142827034, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.08672387897968292, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.09458101540803909, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.16670116782188416, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.1444685459136963, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.1513611227273941, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.2637236714363098, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.22842261904761904, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.22668650793650794, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.22271825396825398, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.21726190476190477, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.21478174603174602, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.21205357142857142, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.21205357142857142, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.2113095238095238, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.2130456349206349, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.21676587301587302, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.2204861111111111, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.2309027777777778, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.2509920634920635, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.29290674603174605, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.34598214285714285, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.42931547619047616, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.5617559523809523, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.6733630952380952, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.7247023809523809, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.7631448412698413, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.8080357142857143, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.8591269841269841, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9030257936507936, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9312996031746031, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9422123015873016, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9518849206349206, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.955109126984127, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9593253968253969, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9600694444444444, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9640376984126984, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9652777777777778, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9675099206349206, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9675099206349206, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9682539682539683, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.96875, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9680059523809523, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9694940476190477, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9709821428571429, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9699900793650794, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9682539682539683, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9680059523809523, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9682539682539683, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.96875, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9744543650793651, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.970734126984127, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9516369047619048, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9568452380952381, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9600694444444444, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9399801587301587, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.07920433523738206, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.08217568112713033, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.08108276101013699, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.07680890087409105, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.07498635004556696, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.07046135121433775, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.06995246565894056, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.06797983311839856, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.06938766101172546, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.07398807945763727, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.07906267212124315, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.09150938172900207, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.11358891581957757, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.15885422096781665, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.21321304358354362, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.29366553211415497, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.3972373081898117, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.46700569488259674, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.5131751024421475, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.5869686606600204, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.6792522490194661, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.7766346863006416, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.8686210269056228, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9187184341841272, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.933609478545215, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.944600330778161, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9473771761319046, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9526386959432659, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9542045875309519, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9593764869994439, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9612421051393722, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9645635173625219, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9653757064252411, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9672076010520134, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9681035598038344, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9674025753661781, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9691840681655189, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9712251726010702, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9709588323086155, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9690853728870936, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9691904792439042, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9688914092647049, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9680056413662768, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.972548297994358, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9645614316616123, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9339383151466749, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9417080327825824, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9583812438514128, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9314058810978919, "id_best": 43, "lr_best": 0.006599999999999999, "wd_best": 0.05, "train/loss_best": 0.08723063126206398, "validation/loss_best": 0.08672387897968292, "validation/acc_best": 0.9744543650793651, "validation/f1_best": 0.972548297994358} +{"epoch": 2, "train/lr": 0.00014999999999999988, "train/loss": 1.0375088176131249, "train/grad": 0.06462855277583003, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.923521728515625, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.90632568359375, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.87800048828125, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.849539794921875, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.82107177734375, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.7813177490234375, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.735684814453125, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.6845452880859373, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.6167257690429686, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.5440191650390624, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.4723031616210935, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.363709259033203, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.2565579986572266, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.0973072814941407, "train/loss_014_lr2.0e-01_wd1.0e+00": 1.940189094543457, "train/loss_015_lr2.3e-01_wd1.0e+00": 1.7869211959838867, "train/loss_016_lr2.7e-01_wd1.0e+00": 1.5921971035003661, "train/loss_017_lr3.2e-01_wd1.0e+00": 1.3705327987670899, "train/loss_018_lr3.8e-01_wd1.0e+00": 1.1414076900482177, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.9528534185886383, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.7568615996837615, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.5964688262343407, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.46173970490694044, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.35885927818715574, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.28485630594193934, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.22617580719292163, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.19096125438809394, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.16787287028506398, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.1450034507550299, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.1257100151758641, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.11302161794155836, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.10375749085098505, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.09362590198405087, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.08597740617580713, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.0782361058332026, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.07179107849486172, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.06623923472128808, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.062284794151782986, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.05899296577088535, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.05624929034151137, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.05599860943853855, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.056883726101368666, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.05961860983632505, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.06490995600819588, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.07653373540379108, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.10556475684046746, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.12068415503017604, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.1820644414704293, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.29625889216549695, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.012448095777072012, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.012445814344100654, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.012454741992987692, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.012476638788357378, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.012507089599967002, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.012555162701755763, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.01260727300774306, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.012645926824770868, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.01265085170045495, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.012597375088371337, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.012505583902820945, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.012344974945299327, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.012205661125481129, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.012044552224688232, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.011898090303875506, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.01171861213631928, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.011395936193875968, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.010872824520338326, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.010157089310232549, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.009438532765489071, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.008558444469235838, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.00772261927369982, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.006921779945259914, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.00623221326386556, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.00568499319255352, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.005220520700095222, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.004935858249664307, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.004752585475798697, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0045833828276954595, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.004458041600883007, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.004385722457664087, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.004330545829143375, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.004254170415224507, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.004164349444909021, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.004060161044471897, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.003994097262038849, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.003971697682864032, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.003993260111310519, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0040234022645745425, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.004034751807630528, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.004091049087583088, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.004190254645363893, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.004410761365143116, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.004809451356122736, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.005609194115677383, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.006734446681221016, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.007496619592420757, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.011106874992838129, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.015585769419558346, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.8759765625, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.8517866134643555, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.811574935913086, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.771183967590332, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.730790615081787, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.6742522716522217, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.6098883152008057, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.5381431579589844, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.444370746612549, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.3453636169433594, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.2483623027801514, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.1007885932922363, "validation/loss_012_lr1.4e-01_wd1.0e+00": 1.9532631635665894, "validation/loss_013_lr1.7e-01_wd1.0e+00": 1.733370304107666, "validation/loss_014_lr2.0e-01_wd1.0e+00": 1.5213778018951416, "validation/loss_015_lr2.3e-01_wd1.0e+00": 1.3249311447143555, "validation/loss_016_lr2.7e-01_wd1.0e+00": 1.0960102081298828, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.8665919899940491, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.6657534241676331, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.5263650417327881, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.40340128540992737, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.3175337314605713, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.25441473722457886, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.2104540467262268, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.17953704297542572, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.1537545919418335, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.13707105815410614, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.1251969188451767, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.11262424290180206, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.1014445498585701, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.09389135986566544, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.0888686403632164, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.08443766087293625, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.08230289071798325, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.08138611167669296, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.08174564689397812, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.08115494251251221, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.08065468817949295, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.07975059002637863, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.08178610354661942, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.0853191390633583, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.08769581466913223, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.09096498042345047, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.09369014203548431, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.11218155175447464, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.2106534242630005, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.19931645691394806, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.380033403635025, "validation/loss_048_lr5.0e+01_wd1.0e+00": 1.0183351039886475, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.2140376984126984, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.2123015873015873, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.2123015873015873, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.21453373015873015, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.21750992063492064, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.22247023809523808, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.2326388888888889, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.2554563492063492, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.2916666666666667, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.34697420634920634, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.42757936507936506, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.5734126984126984, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.6688988095238095, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.7251984126984127, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.7604166666666666, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.7986111111111112, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.8516865079365079, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.8931051587301587, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9250992063492064, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9384920634920635, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9469246031746031, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9516369047619048, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9558531746031746, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9593253968253969, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9623015873015873, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9665178571428571, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9677579365079365, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9685019841269841, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9719742063492064, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9742063492063492, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9749503968253969, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9754464285714286, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9751984126984127, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9759424603174603, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9766865079365079, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9751984126984127, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9732142857142857, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9744543650793651, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9754464285714286, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9737103174603174, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9722222222222222, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9734623015873016, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9754464285714286, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9737103174603174, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9670138888888888, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9568452380952381, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9561011904761905, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9479166666666666, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9228670634920635, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.0731298519055451, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.07079005666098827, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.06940638134172114, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.07218305711697989, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.07600671054693442, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.08257030315331161, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.09552084934122923, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.12115142883369112, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.15987868930344162, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.21552840558466949, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.29358561305795966, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.4029268603429819, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.4622720746611598, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.5114331994928539, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.5793866284934484, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.6562372787547156, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.762519466943175, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.8425277151061555, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9061246908180374, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9270573810763177, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9388998254685182, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9440642124013562, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9483861188818308, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9522251623332819, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.956076683157093, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9618254963134015, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9635187729097178, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9647622385029515, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9695165071531969, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9718501249667453, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9727048706127668, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.97325436328226, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9738248710284239, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9749957977094122, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.975566706467494, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9735343538158542, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9708036317075536, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9726909105556785, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9742321617630251, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9720714138575799, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9696357354103362, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9703121295967685, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9714964427451336, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9718468938241879, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9629216739353778, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9562798195827847, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9443213421090548, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9417388384258291, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.923876974878707, "id_best": 34, "lr_best": 0.0015299999999999997, "wd_best": 0.05, "train/loss_best": 0.0782361058332026, "validation/loss_best": 0.08138611167669296, "validation/acc_best": 0.9766865079365079, "validation/f1_best": 0.975566706467494} +{"epoch": 3, "train/lr": 0.0002100600600600602, "train/loss": 0.8496207591891288, "train/grad": 0.09296301232650876, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.8160003662109374, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.7827374267578127, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.72736328125, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.672003173828125, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.6168887329101564, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.540460510253906, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.4545648193359373, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.3596751403808596, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.235150909423828, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.1015189361572264, "train/loss_010_lr1.0e-01_wd1.0e+00": 1.9687845993041992, "train/loss_011_lr1.2e-01_wd1.0e+00": 1.7677064895629884, "train/loss_012_lr1.4e-01_wd1.0e+00": 1.5750943756103515, "train/loss_013_lr1.7e-01_wd1.0e+00": 1.312532720565796, "train/loss_014_lr2.0e-01_wd1.0e+00": 1.0895916414260864, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.907300922870636, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.7196803045272827, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.5540613156557083, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.4237086436152458, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.3400586760044098, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.2699039063602686, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.22194888323545456, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.18594878446310759, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.15932169975712895, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.13926256788894534, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.121413986524567, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.10890978469513357, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.09950182169675827, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.08893780222162605, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.07869895653799176, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.07134041485376656, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.06564832035452127, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.0592797312233597, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.054440090991556646, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.04960458646528423, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.04644310954026878, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.044418455194681884, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.04390874806791544, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.0440625336393714, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.04908438944257796, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.05605990132316947, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.06781628164462745, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.08577566912397742, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.10650397635065019, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.13731146981939674, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.24865313719958068, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.6260187971871346, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.9914082051254809, "train/loss_048_lr5.0e+01_wd1.0e+00": 1.3449090457335116, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.012523911981843413, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.01256948952563107, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.012642794381827116, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.01269134437199682, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.012700841361656785, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.012648472259752453, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.012519928594119847, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.012351129297167062, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.012167762690223754, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.012044274942018091, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.011956511796452105, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.011780867092311383, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.011483582989312709, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.0108324686717242, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.010071303511504084, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.009323047380894423, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.008439340263139456, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.007545012373011559, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.006732424867805093, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.006142526193289086, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.005601269465405494, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.005201932666823268, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.004891724383924156, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.00465969531214796, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0044928811595309525, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.004355351595440879, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.004269317430444061, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.004212079846765846, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.004148823822033592, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.004076322513865307, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.004012298441375605, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.003950639208778739, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0038842354755615816, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.003806647690362297, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.00370192498434335, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0036751423554960637, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0037473513442091645, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0038475951424334198, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.003902503565332154, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.004291802887746598, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.004683120350819081, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.005281298952468205, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.006511948111583479, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.007802046820870601, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.009382155088242144, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.015358016738318839, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.029634897825308145, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.03887736442964524, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.04735369590111077, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.750497817993164, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.7074522972106934, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.6357693672180176, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.564558506011963, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.4944941997528076, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.39844012260437, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.291508913040161, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.173130750656128, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.0160093307495117, "validation/loss_009_lr8.7e-02_wd1.0e+00": 1.845872163772583, "validation/loss_010_lr1.0e-01_wd1.0e+00": 1.6779987812042236, "validation/loss_011_lr1.2e-01_wd1.0e+00": 1.432766318321228, "validation/loss_012_lr1.4e-01_wd1.0e+00": 1.21311616897583, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.942553699016571, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.7406806945800781, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.5940222144126892, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.4592883586883545, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.35308489203453064, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.2774296998977661, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.23191671073436737, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.1943466067314148, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.16780737042427063, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.146695077419281, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.13002993166446686, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.11667975038290024, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.10454101860523224, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.09611000120639801, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.09000805020332336, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.0835174024105072, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.07817947864532471, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.0748814046382904, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.0728430300951004, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.07148215919733047, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.07106908410787582, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.07186934351921082, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.07329080998897552, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.07560998201370239, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.0757487490773201, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.07728736847639084, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.09928292036056519, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.10704394429922104, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.12701070308685303, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.2000267654657364, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.23307888209819794, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.32219186425209045, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.4551032483577728, "validation/loss_046_lr3.6e+01_wd1.0e+00": 1.374983549118042, "validation/loss_047_lr4.3e+01_wd1.0e+00": 2.279351234436035, "validation/loss_048_lr5.0e+01_wd1.0e+00": 1.836580514907837, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.21478174603174602, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.21924603174603174, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.2286706349206349, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.2472718253968254, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.27157738095238093, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.31646825396825395, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.3896329365079365, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.5064484126984127, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.6374007936507936, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.7006448412698413, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.7378472222222222, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.7854662698412699, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.832093253968254, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.8849206349206349, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9216269841269841, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9365079365079365, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9444444444444444, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9499007936507936, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9528769841269841, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9573412698412699, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9605654761904762, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9637896825396826, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9662698412698413, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.96875, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9714781746031746, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9739583333333334, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9759424603174603, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9766865079365079, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9776785714285714, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9774305555555556, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9786706349206349, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9786706349206349, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9774305555555556, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9766865079365079, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9764384920634921, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9771825396825397, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9769345238095238, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9766865079365079, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9769345238095238, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9722222222222222, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9694940476190477, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9662698412698413, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9553571428571429, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9546130952380952, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9513888888888888, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9556051587301587, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9345238095238095, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9278273809523809, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9538690476190477, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.07193798247737813, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.07793674432781508, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.08842327027458483, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.10995999365079158, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.1363567725404408, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.18225665980516598, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.25532936129751793, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.3540681343115099, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.44322874213897706, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.48587148247717515, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.5351511353743318, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.6315079596828881, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.7240038511986999, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.8249909993636668, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.8996661428610864, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9232557061468638, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9346556545793192, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.940587956105151, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9443331126390566, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9496742985068367, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9546056276039668, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9580143028075299, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9618757076433883, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9646406295692846, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9678821282547526, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9702585738912587, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9720516912356039, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9732453726611124, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9742485203960923, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9742294277164422, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9751616614583043, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9751152635826477, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9732015629770795, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9722979467005748, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9722928659596752, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9723246235467181, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9733421984669842, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9731102567896234, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9738040582082144, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9687880920169851, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9649585511868045, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9642205952164131, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9521657692037192, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9414982548584069, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9431826975408415, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9472060642259457, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.922692770317896, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9260388936237973, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9479950658401746, "id_best": 30, "lr_best": 0.00081, "wd_best": 0.05, "train/loss_best": 0.07134041485376656, "validation/loss_best": 0.0748814046382904, "validation/acc_best": 0.9786706349206349, "validation/f1_best": 0.9751616614583043} +{"epoch": 4, "train/lr": 0.0002701201201201201, "train/loss": 0.7075029969215393, "train/grad": 0.09860769987106323, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.6701409912109373, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.615230712890625, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.524947509765625, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.4363031005859375, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.349526672363281, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.230054931640625, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.094732360839844, "train/loss_007_lr6.2e-02_wd1.0e+00": 1.9432937240600585, "train/loss_008_lr7.4e-02_wd1.0e+00": 1.744151782989502, "train/loss_009_lr8.7e-02_wd1.0e+00": 1.53752742767334, "train/loss_010_lr1.0e-01_wd1.0e+00": 1.346948699951172, "train/loss_011_lr1.2e-01_wd1.0e+00": 1.0934260416030883, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.8902048015594483, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.6673797994852066, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.5173787260055542, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.4156522673368454, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.3271406212449074, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.2601414766162634, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.21268060334026814, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.18310682248324156, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.15740802172571422, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.13818920319899916, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.12198062151670457, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.10845295089296997, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.09711638128384947, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.08619425753131509, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.07807283263653517, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.07162701992318034, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.06382813756354153, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.055904763964936134, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.05017133099958301, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.046080202916637066, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.04190720329992473, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.039502157755196096, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.03761899304576218, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.0363857989013195, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.0365775896795094, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.03954364748671651, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.04518534862436354, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.07193775382824243, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.09646611798554659, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.09392425631172956, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.11552470924332738, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.2386542109400034, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.4072049550432712, "train/loss_045_lr3.1e+01_wd1.0e+00": 1.0160145909525453, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.7232424191012978, "train/loss_047_lr4.3e+01_wd1.0e+00": 1.0835937505215407, "train/loss_048_lr5.0e+01_wd1.0e+00": 1.4093692146334797, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.01283825587015599, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.012857734179124235, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.01279672326054424, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.01265094761736691, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.012483109175227582, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.012293324563652277, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.012166598080657422, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.01207570279482752, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.011898082233965396, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.011552544427104294, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.01106990012805909, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.010206294164527207, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.0093548489571549, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.008261461439542473, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.007399368153419346, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.0067187747312709685, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.006034928716253489, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.005454746838659048, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.005020792478462681, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.004756380240432918, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.004540886282920837, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.004395654342370108, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.004285280733602122, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.004194806333398447, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.004126593155087903, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.00405136861896608, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.003985644887434319, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.003919823917676694, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0037954868510132658, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.003644769992097281, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0035414982523070647, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0034760367771377787, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0034135485329898074, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0033896047581220045, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0033771106485801284, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.003401237501821015, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0035204575974785257, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.003770373487350298, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.004152691763956682, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.005810843465878861, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.006816963355813641, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.006749493048992008, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.007999941978050628, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.014710430660343263, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.019855828745057806, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.038686978053301575, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.03041477027712972, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.03732492756338244, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.04365875564362796, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.58866024017334, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.5224835872650146, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.414757490158081, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.3100645542144775, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.2072393894195557, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.064486026763916, "validation/loss_006_lr5.3e-02_wd1.0e+00": 1.9013521671295166, "validation/loss_007_lr6.2e-02_wd1.0e+00": 1.7195130586624146, "validation/loss_008_lr7.4e-02_wd1.0e+00": 1.4872639179229736, "validation/loss_009_lr8.7e-02_wd1.0e+00": 1.259342908859253, "validation/loss_010_lr1.0e-01_wd1.0e+00": 1.06272292137146, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.8232294321060181, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.6493553519248962, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.4758657217025757, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.3689012825489044, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.30078670382499695, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.24403521418571472, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.20204180479049683, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.17152585089206696, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.15186649560928345, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.13419891893863678, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.12046198546886444, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.10894796997308731, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.09954188019037247, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.09194266051054001, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.08466217666864395, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.08022303134202957, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.07842712849378586, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.0773676261305809, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.07481377571821213, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.07290082424879074, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.07113873958587646, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.06948305666446686, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.06947409361600876, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.07344226539134979, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.07943925261497498, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.07923900336027145, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.07532842457294464, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.10377883911132812, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.11188963055610657, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.13290199637413025, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.16006842255592346, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.28437235951423645, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.47083166241645813, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.8387252688407898, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.5472776889801025, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.96013343334198, "validation/loss_047_lr4.3e+01_wd1.0e+00": 1.4099278450012207, "validation/loss_048_lr5.0e+01_wd1.0e+00": 1.4821068048477173, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.23759920634920634, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.25992063492063494, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.30654761904761907, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.3722718253968254, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.4680059523809524, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.5997023809523809, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.6850198412698413, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.7256944444444444, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.7708333333333334, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.8184523809523809, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.8601190476190477, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9017857142857143, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9303075396825397, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9434523809523809, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9518849206349206, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9553571428571429, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9580853174603174, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9625496031746031, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9655257936507936, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9670138888888888, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9682539682539683, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9704861111111112, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9714781746031746, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9732142857142857, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9754464285714286, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9764384920634921, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9776785714285714, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9766865079365079, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9756944444444444, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9769345238095238, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9766865079365079, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9764384920634921, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9786706349206349, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9779265873015873, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9747023809523809, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.972718253968254, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9729662698412699, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9747023809523809, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9694940476190477, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9685019841269841, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9625496031746031, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9650297619047619, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9513888888888888, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9546130952380952, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9434523809523809, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9332837301587301, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9672619047619048, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9573412698412699, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9590773809523809, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.09983127089593485, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.1244567747460031, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.1730529001137292, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.2384245981226346, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.3250051018068656, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.4196582409238211, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.47487288026865326, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.5218995343829237, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.6010207011315213, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.6945175552561952, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.7710355968908399, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.859833526219555, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9147218978327574, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9332269002039721, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9437704677127233, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9481695348871193, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9514472387673886, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9565922397710697, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9602199149209765, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9621749216445552, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9642727825139232, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9663085673266905, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9670542662151198, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9699322266796235, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9723126910370135, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9733118935191478, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9742965792599341, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9737147173557155, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9737333494690473, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9751423896388961, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9746982507326523, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9744291914937614, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.97668112251504, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9764229150660183, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9727836932030085, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9719458948804646, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.973059164859419, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9732346726861091, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9633687763009471, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9632999589646956, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9578080939084078, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9604296366034502, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9487978869569162, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9486049800907536, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9371635734360424, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9013131610011293, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9616527295299413, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9520287582772801, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9541183739956012, "id_best": 32, "lr_best": 0.0011099999999999999, "wd_best": 0.05, "train/loss_best": 0.04190720329992473, "validation/loss_best": 0.06948305666446686, "validation/acc_best": 0.9786706349206349, "validation/f1_best": 0.97668112251504} +{"epoch": 5, "train/lr": 0.00029891323817685334, "train/loss": 0.5895618531107902, "train/grad": 0.10498281242325902, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.4972259521484377, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.4192715454101563, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.2926040649414063, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.1683765411376954, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.0448554229736327, "train/loss_005_lr4.5e-02_wd1.0e+00": 1.8725879669189454, "train/loss_006_lr5.3e-02_wd1.0e+00": 1.6793316078186036, "train/loss_007_lr6.2e-02_wd1.0e+00": 1.4724717712402344, "train/loss_008_lr7.4e-02_wd1.0e+00": 1.2249148845672608, "train/loss_009_lr8.7e-02_wd1.0e+00": 1.0006536960601806, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.822114486694336, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.6213676512241364, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.48599195569753645, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.3585330918431282, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.2832843789458275, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.236197257861495, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.19665054097771645, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.16594449397176503, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.14244825202971698, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.12651781588792801, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.11135506842285395, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.09917569602839649, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.08829517564736307, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.0786570985801518, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.0703146875090897, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.06178235907107592, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.055282191764563324, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.050221954155713316, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.04437874821014702, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.038910837955772874, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.03522045047953725, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.03282128215767443, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.030587519481778146, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.029096201779320836, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.027829103618860245, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.028981511713936925, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.032127564456313845, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.03732103934511542, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.046968015413731336, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.0630226435791701, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.09782931786030531, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.12915010411292316, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.28321057856082915, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.4773426811490208, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.5360615261364728, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.9101481131836772, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.87493009025231, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.9086730367690324, "train/loss_048_lr5.0e+01_wd1.0e+00": 1.4974935141392052, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.012665960676968098, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.012523629930801689, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.012282538381405174, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.012133390624076128, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.012063160580582917, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.01198859375435859, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.01180254910606891, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.011417660331353545, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.010709114880301058, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.009863519947975874, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.00906300483737141, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.00802042377879843, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.00718997678020969, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.006256238631904125, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.005613956925226375, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.005192995852557942, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.004846305352402851, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.004599935847800225, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.004430215863976628, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.004320483828196302, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.004216203221585601, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.004119939089869149, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0040251808578614144, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.003923208785126917, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0038188595743849875, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0036921932754921728, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0035726578885805793, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0034715862257871776, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0033375047406298108, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0032072824635542927, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.003123286823683884, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.003082707312569255, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.003072750855644699, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.003069764736428624, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.003098110456849099, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0032777448096021544, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0035947545145609185, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.00421997712837765, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0049123775384214245, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.005710079272685107, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.007681092715793056, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.009947723026853055, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.017194313027721363, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.024838312550036788, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.02593089763482567, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.03535561130153095, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.03577661312047988, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.03758048550776274, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0474823120101886, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.41694974899292, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.329242706298828, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.1860547065734863, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.044189929962158, "validation/loss_004_lr3.8e-02_wd1.0e+00": 1.9023295640945435, "validation/loss_005_lr4.5e-02_wd1.0e+00": 1.7059149742126465, "validation/loss_006_lr5.3e-02_wd1.0e+00": 1.4909778833389282, "validation/loss_007_lr6.2e-02_wd1.0e+00": 1.2704675197601318, "validation/loss_008_lr7.4e-02_wd1.0e+00": 1.0216319561004639, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.8114844560623169, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.6544066071510315, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.4883323013782501, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.38251492381095886, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.2878555357456207, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.23410995304584503, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.2006891518831253, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.17192776501178741, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.14913319051265717, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.13129007816314697, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.11908186972141266, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.10741662234067917, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.09813649952411652, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.0901876911520958, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.08378916233778, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.07839056104421616, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.07373948395252228, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.07102027535438538, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.06933189928531647, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.06754760444164276, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.06627544015645981, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.06589200347661972, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.06598422676324844, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.0668274387717247, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.06874597817659378, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.07221868634223938, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.07768645882606506, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.0887332335114479, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.1013881266117096, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.11050846427679062, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.11407209187746048, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.13841357827186584, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.21249791979789734, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.42704275250434875, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.6946684122085571, "validation/loss_044_lr2.6e+01_wd1.0e+00": 1.026554822921753, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.9699256420135498, "validation/loss_046_lr3.6e+01_wd1.0e+00": 1.299934983253479, "validation/loss_047_lr4.3e+01_wd1.0e+00": 1.4819086790084839, "validation/loss_048_lr5.0e+01_wd1.0e+00": 2.4990243911743164, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.3040674603174603, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.3539186507936508, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.486359126984127, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.6155753968253969, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.6812996031746031, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.7269345238095238, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.7698412698412699, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.8169642857142857, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.8675595238095238, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9055059523809523, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9290674603174603, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9437003968253969, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9494047619047619, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9553571428571429, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9575892857142857, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9605654761904762, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9627976190476191, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9655257936507936, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9675099206349206, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9697420634920635, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9712301587301587, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9734623015873016, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9744543650793651, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9766865079365079, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9784226190476191, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9786706349206349, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9789186507936508, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9791666666666666, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9794146825396826, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9796626984126984, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9784226190476191, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9786706349206349, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9784226190476191, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9776785714285714, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9771825396825397, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9774305555555556, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9744543650793651, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9732142857142857, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9724702380952381, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9737103174603174, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9697420634920635, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9660218253968254, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9588293650793651, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9565972222222222, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9429563492063492, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.964781746031746, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9536210317460317, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9613095238095238, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9526289682539683, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.17064144797390596, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.22080440849744037, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.33496870190732253, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.42587637153546953, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.470503375497885, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.5256578059210731, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.6065501485972369, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.6962279275793067, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.7904855393505643, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.8681981497418906, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9117926431543593, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9338644779274562, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9408980443987403, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9489283030389443, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9521588892672949, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9550969455662374, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9585216162620511, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9612839096717681, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9646983122639593, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.966738749443974, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9679005194221791, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9711304590945663, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9718671368329378, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9742469995666567, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9757246685328567, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9768236705661366, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9770114609467819, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9779132093997567, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9773956067401741, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.977441451427949, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9760396368958311, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9760521355443902, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9763527875655782, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9765351222253265, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9748178141986343, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9759298274910723, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9729353192576442, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9715320618636718, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9685453036573661, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9705648091505542, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9650926197006633, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9602117097644425, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.956682544682482, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9484409951688848, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.93685228449436, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9595619575165564, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9472828678153951, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9547012627407787, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9518505145978947, "id_best": 29, "lr_best": 0.0006899999999999999, "wd_best": 0.05, "train/loss_best": 0.038910837955772874, "validation/loss_best": 0.06627544015645981, "validation/acc_best": 0.9796626984126984, "validation/f1_best": 0.977441451427949} +{"epoch": 6, "train/lr": 0.0002924170901991409, "train/loss": 0.4682562130689621, "train/grad": 0.08985282091423868, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.3251828002929686, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.225426025390625, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.0613275146484376, "train/loss_003_lr3.3e-02_wd1.0e+00": 1.8982703399658203, "train/loss_004_lr3.8e-02_wd1.0e+00": 1.7373163223266601, "train/loss_005_lr4.5e-02_wd1.0e+00": 1.520946273803711, "train/loss_006_lr5.3e-02_wd1.0e+00": 1.2950338745117187, "train/loss_007_lr6.2e-02_wd1.0e+00": 1.0759217548370361, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.843798041343689, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.6597570884227753, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.5285895520448685, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.39563522338867185, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.3138248457014561, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.24179703764617444, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.20036019802093505, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.17364740505814552, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.14975792493671178, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.12981873590499163, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.113473238684237, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.10166288018226624, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.09000073871575295, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.08019037760794162, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.07101296048611402, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.06269498827867209, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.05520629069767893, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.047593132564797996, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.04174727391451597, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.03723174479790032, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.031990171540528536, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.02715180634520948, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.023996612234041096, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.021857155142351984, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.019864743305370212, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.018742215000092984, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.019259636579081415, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.020558404782786966, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.02713605258613825, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.03317680276930332, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.05001576646231115, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.0474147975910455, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.05299004001542926, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.11981121734715998, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.15476023270748557, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.3914706077054143, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.34279070726595817, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.5150508573278785, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.6001409524586052, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.8228720751963556, "train/loss_048_lr5.0e+01_wd1.0e+00": 1.1262794487550856, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.012213430157862604, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.012054941258393228, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.011932834279723465, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.011872726432047785, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.011754956524819136, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.011416221521794796, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.010829879031516611, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.0100637670699507, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.009067960744723678, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.008141365658957511, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.007380276827607304, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.00646716641029343, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.00580795866320841, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.0051749212865252045, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.004811705682659522, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.004589182960335165, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.0043998482695315035, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.004249549324158579, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.004129001545952633, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.004037140660220757, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.003944325288757682, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.0038596724829403684, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0037668871629284693, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0036615390807855875, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.003540457108756527, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0033931980226770977, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0032578683449537493, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0031422913301503287, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0029886495001846926, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0028452606973587537, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0027510040937340817, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0026773449216852896, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0025793496398546266, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0025210516076185742, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0026121666157268917, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0029109290667111054, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0034738848956476433, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.004226502596429782, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.004991320902263396, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0049694990305579265, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.00549223263937165, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.009193171172009898, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.010689004880914581, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.02202223413272373, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.02048332490077314, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.025597438157574287, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.02968031753453631, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.035144876605820184, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.039774749659375906, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.2567920684814453, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.1481447219848633, "validation/loss_002_lr2.8e-02_wd1.0e+00": 1.9679019451141357, "validation/loss_003_lr3.3e-02_wd1.0e+00": 1.7887823581695557, "validation/loss_004_lr3.8e-02_wd1.0e+00": 1.614121437072754, "validation/loss_005_lr4.5e-02_wd1.0e+00": 1.3844940662384033, "validation/loss_006_lr5.3e-02_wd1.0e+00": 1.1531535387039185, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.937868595123291, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.7205488681793213, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.5563068985939026, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.4440954029560089, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.33451220393180847, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.269287109375, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.2129300832748413, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.18026377260684967, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.15903741121292114, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.13990408182144165, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.12405268102884293, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.11135682463645935, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.10243505984544754, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.09394354373216629, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.08739149570465088, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.08148451149463654, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.07671738415956497, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.07301880419254303, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.06976314634084702, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.0677979439496994, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.06643378734588623, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.06588634103536606, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.06641006469726562, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.06744662672281265, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.06844044476747513, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.06999601423740387, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.0702165737748146, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.07478661835193634, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.08316321671009064, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.08913237601518631, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.1038007140159607, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.13228867948055267, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.134002223610878, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.1510571390390396, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.21159479022026062, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.22575317323207855, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.4437935948371887, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.5241507887840271, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.6615498661994934, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.8791239857673645, "validation/loss_047_lr4.3e+01_wd1.0e+00": 1.0979551076889038, "validation/loss_048_lr5.0e+01_wd1.0e+00": 1.286863923072815, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.4208829365079365, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.5270337301587301, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.6624503968253969, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.7132936507936508, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.7477678571428571, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.794890873015873, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.8442460317460317, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.8829365079365079, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9243551587301587, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9387400793650794, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9451884920634921, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9528769841269841, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.957093253968254, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9615575396825397, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9642857142857143, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.966765873015873, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9675099206349206, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.970734126984127, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9722222222222222, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9734623015873016, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9749503968253969, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9766865079365079, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9776785714285714, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9791666666666666, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9791666666666666, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.980406746031746, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9809027777777778, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9811507936507936, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9806547619047619, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9809027777777778, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.980406746031746, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9799107142857143, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9794146825396826, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9801587301587301, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9796626984126984, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9766865079365079, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9771825396825397, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9754464285714286, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9697420634920635, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.972718253968254, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.970734126984127, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9675099206349206, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9704861111111112, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9692460317460317, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9660218253968254, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9697420634920635, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9717261904761905, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9655257936507936, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9699900793650794, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.28411041187823455, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.36626752035085225, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.45775107884307786, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.5010540165230275, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.5600662383637216, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.6519881350167628, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.7455779724345659, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.8240413230567344, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9043999662414913, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9272277518521117, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9360079113362352, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9446665728772266, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9504510644485548, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.955741195084824, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9594369921107135, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9626803917927353, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9635227941536338, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9669841659861685, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9692713121095634, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9704339484920217, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9726401203020291, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9739112284411597, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9745662280868078, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9769611079086007, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9769319321515534, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9789532632878959, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.978552098202275, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9792772311256472, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9789204883274563, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9792717668720423, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9784904041206075, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9780781316601945, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9768654082392386, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9783082059848586, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9778554534879232, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9747564578010339, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9745574695982132, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9728358689553944, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9683306073662634, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9679239017889487, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.967766082117456, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9641994192299951, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9660148691675593, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9673893196922579, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9615200362582748, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9662866278380122, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9684753665285377, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.959609015389532, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.96551410249018, "id_best": 27, "lr_best": 0.00047999999999999996, "wd_best": 0.05, "train/loss_best": 0.03723174479790032, "validation/loss_best": 0.06643378734588623, "validation/acc_best": 0.9811507936507936, "validation/f1_best": 0.9792772311256472} +{"epoch": 7, "train/lr": 0.00027969249556793234, "train/loss": 0.36434192076325417, "train/grad": 0.06779243495315314, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.1729978942871093, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.052428741455078, "train/loss_002_lr2.8e-02_wd1.0e+00": 1.8527252197265625, "train/loss_003_lr3.3e-02_wd1.0e+00": 1.6571371459960937, "train/loss_004_lr3.8e-02_wd1.0e+00": 1.4711274909973144, "train/loss_005_lr4.5e-02_wd1.0e+00": 1.2351200008392333, "train/loss_006_lr5.3e-02_wd1.0e+00": 1.0076973962783813, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.8058257126808166, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.6115132510662079, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.47066167056560515, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.37707187205553055, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.28793680742383004, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.23537270367145538, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.18934060335159303, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.16176382150501012, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.1430993039906025, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.1256469052657485, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.11028947012498974, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.09709714324213564, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.08707615826278925, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.07688794351182877, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.06790108042769134, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.059369561085477474, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.05155565879307687, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.0444876803830266, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.03738943497650325, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.03204947170801461, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.02789333830587566, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.023212168188765644, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.019179862393066287, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.01667202349752188, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.014910175306722522, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.013124578623101115, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.012206509802490472, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.01220606748946011, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.01350164677016437, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.015036630798131228, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.017337814336642624, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.029642981318756936, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.0334178904350847, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.027450557593256236, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.06809662059880793, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.08791362796910107, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.14589625783264637, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.16841395972296597, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.2140137661062181, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.3213407603930682, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.5320711046364158, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.5176459162682295, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.012007511081174016, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.011934834704734385, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.011850964562036097, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.011651506931520998, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.011293936921283602, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.010616633258759976, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.009766555544920265, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.008870935598388315, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.007868977168109269, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.0070009799534454945, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.00631746236467734, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.005558609176659957, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.005070620037149638, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.004642537982435897, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.0043943825596943495, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.004233052951749414, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.004085749273071997, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.003954171348013915, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.0038349596672924233, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.003733448080602102, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.0036207656853366643, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.003506612292258069, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.00337628042063443, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.003236285597959068, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0030913160581258125, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0029138296612654813, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0027563955218647606, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.00261248010530835, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.002440516854840098, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0022826916674966924, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0021718454355868742, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0020700173563091085, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.001920752458900097, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0018074713591340697, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.001867341315955855, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.002103320662754413, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0021574509104902973, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0025790864900045564, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0037759293131603045, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.004186173565194622, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0034050584449914823, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.006526097008809302, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.007656623189877792, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.012580083227664716, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.012523582022723412, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.01741512857307928, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.020430488561963882, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.024897758906777246, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.027008175201324994, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.108344554901123, "validation/loss_001_lr2.3e-02_wd1.0e+00": 1.9785692691802979, "validation/loss_002_lr2.8e-02_wd1.0e+00": 1.76419997215271, "validation/loss_003_lr3.3e-02_wd1.0e+00": 1.5572388172149658, "validation/loss_004_lr3.8e-02_wd1.0e+00": 1.3642786741256714, "validation/loss_005_lr4.5e-02_wd1.0e+00": 1.1262311935424805, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.9043169021606445, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.7137422561645508, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.5366233587265015, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.4125531315803528, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.33247748017311096, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.25789085030555725, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.21434186398983002, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.17601658403873444, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.15262623131275177, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.13676555454730988, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.12198836356401443, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.10927420109510422, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.0988718569278717, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.0914708822965622, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.08455964177846909, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.07901425659656525, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.07439954578876495, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.07082157582044601, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.06817369163036346, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.06623093783855438, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.06538756936788559, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.06514754146337509, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.06561245769262314, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.06755685806274414, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.06983476877212524, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.07187316566705704, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.07413352280855179, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.07601702213287354, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.08287694305181503, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.08634649217128754, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.09157510101795197, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.10890095680952072, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.12532077729701996, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.13192057609558105, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.1498001217842102, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.20536991953849792, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.22573243081569672, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.3626824617385864, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.5097557902336121, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.698020875453949, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.9145607352256775, "validation/loss_047_lr4.3e+01_wd1.0e+00": 1.2636576890945435, "validation/loss_048_lr5.0e+01_wd1.0e+00": 1.4938713312149048, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.5657242063492064, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.660218253968254, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.7229662698412699, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.761656746031746, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.8018353174603174, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.8506944444444444, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.8888888888888888, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.9228670634920635, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9379960317460317, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9481646825396826, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9521329365079365, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9580853174603174, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9613095238095238, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9640376984126984, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9665178571428571, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9665178571428571, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.96875, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9714781746031746, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9739583333333334, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9759424603174603, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9761904761904762, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9771825396825397, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9786706349206349, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9794146825396826, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9791666666666666, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9786706349206349, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9794146825396826, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9794146825396826, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9796626984126984, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9791666666666666, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9776785714285714, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9779265873015873, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9781746031746031, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9779265873015873, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9761904761904762, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9754464285714286, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9761904761904762, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9729662698412699, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9747023809523809, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9737103174603174, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9709821428571429, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9652777777777778, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.96875, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9714781746031746, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9672619047619048, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9660218253968254, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.964781746031746, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9605654761904762, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9553571428571429, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.3965636956849853, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.4578762640181728, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.512190280771683, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.5870473622722061, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.6656742470302157, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.760214712445618, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.8362397788596672, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9036650393088793, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9263060509325959, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9398294721052112, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9446919997953591, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9507889398520748, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9555184531379647, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9586771054752729, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9623623998503851, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9625984560868417, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9649656451933482, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9686873964373985, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9715333057646809, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9737797112026295, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9736754497634308, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9744281019799219, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9758567539312085, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9771924168349584, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9772244811467632, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9763492610696599, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9770490752857245, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9764989229714252, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9765710384533722, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9766590084159522, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9748174623018552, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9753252200221235, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9763265823152951, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9765441472757891, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9740075728168053, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9737544483755319, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9741211345120494, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9705396421558019, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9715775636443253, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9689502933763108, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9658030882871057, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.962475770734933, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9675436598352305, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9684038550115972, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9620737841093836, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9600184272462988, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9653556974842404, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9580547086526824, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9509830015725304, "id_best": 28, "lr_best": 0.00057, "wd_best": 0.05, "train/loss_best": 0.023212168188765644, "validation/loss_best": 0.06561245769262314, "validation/acc_best": 0.9796626984126984, "validation/f1_best": 0.9765710384533722} +{"epoch": 8, "train/lr": 0.0002612959497061927, "train/loss": 0.3004863734543324, "train/grad": 0.05848927607759833, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.0267920684814453, "train/loss_001_lr2.3e-02_wd1.0e+00": 1.8854203033447265, "train/loss_002_lr2.8e-02_wd1.0e+00": 1.6545903015136718, "train/loss_003_lr3.3e-02_wd1.0e+00": 1.4373095703125, "train/loss_004_lr3.8e-02_wd1.0e+00": 1.2407066917419434, "train/loss_005_lr4.5e-02_wd1.0e+00": 1.006232533454895, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.7960695838928222, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.6222960925102234, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.46597377449274063, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.3593165636062622, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.29158017054200175, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.22884827680885791, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.19176539715379476, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.15791315760463476, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.13665116634219884, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.12179540915414691, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.10743997117504478, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.0945860345941037, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.08323791651055217, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.07464808410964906, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.06574981484562159, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.05785272020846605, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.05033051053062081, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.04318708488717675, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.03667192691937089, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.029887951519340275, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.02479472410865128, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.021071941880509256, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.017033438310027123, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.013663120474666357, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.01149561457335949, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.009862782089039684, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.00849364790134132, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.007767418893054128, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.00733667598105967, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.010036488110199571, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.009703202676028012, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.01169551357626915, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.01437068815343082, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.020462601110339165, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.029243801087141037, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.03201046518981457, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.0319786558393389, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.06762390938587487, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.07603424968197942, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.1496586698666215, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.20394787202589215, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.252117379643023, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.4265767644532025, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.012075327425263823, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.012016733991913497, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.011791071575134992, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.011348228259012104, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.010762913590297104, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.009881511786952615, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.008945818080101163, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.008048501049634069, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.007079060608521104, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.006262222649529576, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.005661255677696317, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.005071618241490796, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.004729312059935182, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.004442887603072449, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.004277491964166984, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.004170814350945875, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.00406650289776735, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.003967221063212492, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.0038689889805391432, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.0037852732790634035, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.003680895756697282, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.003567841212498024, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.003445807144162245, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0033022302942117675, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.003136302311322652, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.002909652864036616, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0027056507157976737, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0025411185174016282, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.002341415303526446, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0021342842991725775, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.001960242685308913, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0018080317707790527, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0016847310685625416, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0016060000098877935, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.001538325926194375, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0018418378483329434, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0017646668066481652, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0021391165338172867, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0026019995526439742, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0032303925445012283, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.004236156009901606, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.004776175983506619, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.004979638207876178, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.007982229558970105, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.008850899685572684, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.014326097943164388, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.01550322752037069, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.01760847706902722, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.025010145118650115, "validation/loss_000_lr2.0e-02_wd1.0e+00": 1.9720876216888428, "validation/loss_001_lr2.3e-02_wd1.0e+00": 1.823588490486145, "validation/loss_002_lr2.8e-02_wd1.0e+00": 1.5833144187927246, "validation/loss_003_lr3.3e-02_wd1.0e+00": 1.360729455947876, "validation/loss_004_lr3.8e-02_wd1.0e+00": 1.162878394126892, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.9318444728851318, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.7298052310943604, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.5668665766716003, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.42376866936683655, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.32840412855148315, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.2690313458442688, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.2145499885082245, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.18208394944667816, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.15251456201076508, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.1339535266160965, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.12121554464101791, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.10919446498155594, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.09885154664516449, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.09029235690832138, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.08410164713859558, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.07823862880468369, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.07354522496461868, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.06978567689657211, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.06714221090078354, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.06570293009281158, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.06480097025632858, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.0644030049443245, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.06475156545639038, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.06641553342342377, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.07040546089410782, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.07348574697971344, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.07561871409416199, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.07836627960205078, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.07994574308395386, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.0850905030965805, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.08993217349052429, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.09206539392471313, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.1070021539926529, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.12662926316261292, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.12306846678256989, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.18586893379688263, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.18238167464733124, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.18753178417682648, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.3329010605812073, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.3987002372741699, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.6457213759422302, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.666813850402832, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.7869446873664856, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.9953566789627075, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.6619543650793651, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.7100694444444444, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.7554563492063492, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.8015873015873016, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.8405257936507936, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.8846726190476191, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9216269841269841, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.9370039682539683, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9466765873015873, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9521329365079365, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9558531746031746, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9600694444444444, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9642857142857143, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9665178571428571, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.96875, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.970734126984127, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9722222222222222, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9737103174603174, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9766865079365079, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9764384920634921, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9784226190476191, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9796626984126984, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9806547619047619, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9818948412698413, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9811507936507936, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9816468253968254, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9811507936507936, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9811507936507936, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.980406746031746, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9774305555555556, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9769345238095238, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9769345238095238, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9771825396825397, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9766865079365079, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9766865079365079, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9759424603174603, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9771825396825397, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9747023809523809, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9719742063492064, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9724702380952381, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9657738095238095, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.972718253968254, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.972718253968254, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9717261904761905, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9709821428571429, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9680059523809523, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9692460317460317, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9694940476190477, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9689980158730159, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.4584500146540825, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.4976367546277839, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.5748923138384593, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.6650413448829842, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.7430627095883044, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.8270327457570554, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.9006188977004213, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9249614426055951, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9383555871348377, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9438654763942802, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9494286400103901, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9546444685763259, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.959461429912996, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9624170690212894, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9645554431993508, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9670971511405456, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9689769178780078, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9706561493472754, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.973965002758281, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9735960122848248, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9756681793498096, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.977299329700338, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9785021124510371, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9799099655473743, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.978891270610727, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.979460747326683, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9784952860067367, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9785001532763331, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.97833633533617, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9762017970868371, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9761283639708964, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.976223978138027, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.976448112416198, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9759831654502478, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9751859785581372, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9741342848358802, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9758988457465465, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9738189515316478, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9693247225457527, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9696158218412402, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9644689894747532, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9700287213662141, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9711433315717202, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9674999852740471, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9686232624807771, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.963248939201047, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9677542562606924, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9641756564670401, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9636628835733295, "id_best": 23, "lr_best": 0.00025499999999999996, "wd_best": 0.05, "train/loss_best": 0.04318708488717675, "validation/loss_best": 0.06714221090078354, "validation/acc_best": 0.9818948412698413, "validation/f1_best": 0.9799099655473743} +{"epoch": 9, "train/lr": 0.00023803200426111704, "train/loss": 0.25773952804505823, "train/grad": 0.05091216254979372, "train/loss_000_lr2.0e-02_wd1.0e+00": 1.8985771179199218, "train/loss_001_lr2.3e-02_wd1.0e+00": 1.740938835144043, "train/loss_002_lr2.8e-02_wd1.0e+00": 1.4898552513122558, "train/loss_003_lr3.3e-02_wd1.0e+00": 1.2627476978302001, "train/loss_004_lr3.8e-02_wd1.0e+00": 1.0660056972503662, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.8427453708648681, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.6537446498870849, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.505637782216072, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.37876537054777143, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.29567357897758484, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.2441800285130739, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.19630382910370828, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.16707869354635477, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.13935117080807685, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.121178048979491, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.10813459867611527, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.09526703608222306, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.08339435282163322, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.072804821934551, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.06471896123141051, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.056297394065186385, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.048902783822268245, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.04192528111860156, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.03552548184990883, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.02980498687364161, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.024208222776651384, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.020154693331569433, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.017109436746686697, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.013775102943181992, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.011111602438613772, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.009737241379916668, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.00897721890360117, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.008553455350920558, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.008335206080228091, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.008154064500704408, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.007089134082198143, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.0075098526757210494, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.010979595612734556, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.013249704642221331, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.012906322414055467, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.029815078461542726, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.020467460192739963, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.029052984099835158, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.025128628443926573, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.05134428299963474, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.09728997999802232, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.12805660913698375, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.17778596182353795, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.2488864945899695, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.011896800361573695, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.011775535917840897, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.011353059839457273, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.010722991847433149, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.010020018378272653, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.009071366812568158, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.00813334982842207, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.0072684181248769165, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.0063741751736961305, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.005680925918277353, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.0052149412548169495, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.0047766643739305436, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.004518422278342768, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.004286198044428602, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.004138321989448741, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.004032295976066962, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.00391833608795423, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.003800871606217697, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.0036787484533851965, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.0035721022431971505, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.0034415527677629145, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.003301023825770244, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.003150061627384275, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.002981393818336073, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0028104178824287372, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0026141752005787566, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0024343937293451745, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0022568830088857796, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.002009364844634547, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0017899249702168162, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0016959625503659482, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0016412471732110134, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0015848590125824558, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0015472692067487514, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0015219113803323124, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0014172235848673154, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0014230701374526688, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0019534500824738643, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0023515858266000577, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0021948533290310477, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.004283892761723109, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0037070622078350366, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.004514343665301226, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.004544686249280687, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.007094226977292634, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.009620247101494379, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.011393214524603918, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.014833580610034168, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.01938691116845719, "validation/loss_000_lr2.0e-02_wd1.0e+00": 1.8510284423828125, "validation/loss_001_lr2.3e-02_wd1.0e+00": 1.6876709461212158, "validation/loss_002_lr2.8e-02_wd1.0e+00": 1.430748701095581, "validation/loss_003_lr3.3e-02_wd1.0e+00": 1.2020609378814697, "validation/loss_004_lr3.8e-02_wd1.0e+00": 1.006966233253479, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.7891595959663391, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.6083663105964661, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.4692666232585907, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.3521367609500885, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.2767679989337921, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.23068486154079437, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.1882036179304123, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.16247542202472687, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.13840797543525696, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.12311579287052155, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.11223652213811874, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.10203424096107483, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.09321607649326324, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.08575554937124252, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.08066243678331375, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.07573693990707397, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.07203370332717896, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.068987637758255, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.06671537458896637, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.06536058336496353, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.06451340019702911, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.06453700363636017, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.06527383625507355, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.06653419137001038, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.06906074285507202, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.07225599884986877, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.07541899383068085, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.07962767034769058, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.08275754004716873, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.08865465223789215, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.08940696716308594, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.08950461447238922, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.11172174662351608, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.12725991010665894, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.10852919518947601, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.18857432901859283, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.18229158222675323, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.15813739597797394, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.2925024628639221, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.3422425389289856, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.4823557734489441, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.5739999413490295, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.7160243391990662, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.787483811378479, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.703125, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.7353670634920635, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.7857142857142857, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.8313492063492064, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.8725198412698413, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.9112103174603174, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9342757936507936, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.9437003968253969, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9499007936507936, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9561011904761905, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9593253968253969, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9630456349206349, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9662698412698413, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9680059523809523, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9702380952380952, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9722222222222222, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9747023809523809, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9764384920634921, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9771825396825397, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9774305555555556, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9786706349206349, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9799107142857143, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9806547619047619, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9799107142857143, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9799107142857143, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9791666666666666, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.980406746031746, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9796626984126984, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9796626984126984, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9786706349206349, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9771825396825397, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9756944444444444, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9749503968253969, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9759424603174603, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9756944444444444, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9756944444444444, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9771825396825397, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9734623015873016, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9712301587301587, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9764384920634921, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9682539682539683, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.972718253968254, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9739583333333334, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9747023809523809, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9702380952380952, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.970734126984127, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9694940476190477, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9672619047619048, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9717261904761905, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.4900845375495525, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.5342548133168398, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.6343598369283086, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.7257956078354361, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.8051247638644453, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.8843603871180705, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.9225624030226182, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9350089614390209, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9415834102671903, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9490831959207673, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9530441892985115, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9574858422683893, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9622733903910785, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9638196875184418, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9665466421044817, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9687822159243538, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9710763161122704, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9735609669375735, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9738667228104728, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.974412774586024, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9757455006902311, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9776468828528356, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9780350527847614, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9770839963086773, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9769924497918762, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9765679158737917, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.978206373499517, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9772138243627896, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9774693475842052, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9765955905981207, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9756453441660069, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.974604726599277, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9735265286332464, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9742899650278548, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.974568539414119, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9735440292532906, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9759991540165506, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9734767769232361, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9691970843871199, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9745581603416967, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9655937391966298, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9695012776228827, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9739391346218405, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.972079285843091, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9688006526164369, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9680688985178366, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9660797609564062, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.964025757874165, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9683764952700967, "id_best": 22, "lr_best": 0.00021599999999999996, "wd_best": 0.05, "train/loss_best": 0.04192528111860156, "validation/loss_best": 0.068987637758255, "validation/acc_best": 0.9806547619047619, "validation/f1_best": 0.9780350527847614} +{"epoch": 10, "train/lr": 0.00021091808096876188, "train/loss": 0.22563982896506787, "train/grad": 0.04326046656817198, "train/loss_000_lr2.0e-02_wd1.0e+00": 1.7920594024658203, "train/loss_001_lr2.3e-02_wd1.0e+00": 1.6220085144042968, "train/loss_002_lr2.8e-02_wd1.0e+00": 1.3584942054748534, "train/loss_003_lr3.3e-02_wd1.0e+00": 1.1288883590698242, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.9367749834060669, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.7269140982627869, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.5563912832736969, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.42759107768535615, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.3209150056540966, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.2531533523648977, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.2116098254173994, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.17269311618059874, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.14852064169943333, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.12507196312770247, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.10936865005642175, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.09788815236650407, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.08622929812408983, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.07531370523385704, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.0653366074617952, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.05748493112623691, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.04922921121120453, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.04188797479495406, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.03497429941780865, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.028716060360893608, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.02330749824643135, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.01821214026771486, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.014699732046574354, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.012248995043337344, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.00970721929334104, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.007578251538798213, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.006262377109378576, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.005548311993479728, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.005032297316938638, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.004846204249188304, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.004376847269013524, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.0035289567802101376, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.003592123994603753, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.0052792958635836836, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.007425542445853353, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.007025812147185206, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.01640479260124266, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.011754992250353098, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.01517746426165104, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.016025487827137114, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.03266413489356637, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.04895483191125095, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.08574221592396497, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.10880560174584389, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.15463604575023054, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.011737632313743234, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.011524225799366832, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.010913057839497925, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.010147428903728724, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.009375526797957718, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008400012629572302, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.007473058246541768, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.006639831950888037, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.00581898215226829, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.005236700284294784, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.004874220220372081, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.004548113058554008, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.004355872647138313, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.004177162935375236, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.004050891743390821, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.003951468082959764, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.0038393201667349785, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.0037170125561533495, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.003581789483432658, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.0034577465848997235, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.003303249173914082, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.0031362209736835213, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.002942619168316014, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0027298846683697776, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.002497579735063482, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0022302006467361936, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0020116205207887108, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0018408935064508113, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0016275769696221687, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0014113040698430267, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.001271689362838515, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0012016072437836555, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.001152168134431122, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.001144557616480597, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0010801954569615191, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0008824677005213744, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0009030145598171658, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0011281380572336274, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.001518331923216465, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0013946825740595158, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.002812522339877432, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.002496733765547674, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.002697302859020283, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.003534164487029683, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.004719969700496502, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.007170077111846949, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.008343737285842881, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.012064537050930245, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.01336921499108994, "validation/loss_000_lr2.0e-02_wd1.0e+00": 1.7463852167129517, "validation/loss_001_lr2.3e-02_wd1.0e+00": 1.5725243091583252, "validation/loss_002_lr2.8e-02_wd1.0e+00": 1.306095838546753, "validation/loss_003_lr3.3e-02_wd1.0e+00": 1.0773473978042603, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.8886005282402039, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.6857473254203796, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.5239779949188232, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.40349796414375305, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.30534037947654724, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.2435324341058731, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.205860435962677, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.17055001854896545, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.1487172394990921, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.12782332301139832, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.11423877626657486, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.10462742298841476, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.095529705286026, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.08751630783081055, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.08087968081235886, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.0763288214802742, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.07204761356115341, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.06882294267416, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.06634587794542313, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.06470634788274765, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.06399782001972198, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.06400006264448166, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.06447422504425049, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.06523539870977402, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.06670968234539032, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.06856565922498703, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.07055015861988068, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.07231591641902924, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.07407817244529724, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.07563937455415726, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.07880500704050064, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.08255691826343536, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.08446679264307022, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.0970081090927124, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.10926993191242218, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.10200606286525726, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.14202703535556793, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.15173375606536865, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.152383491396904, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.25239184498786926, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.2987971901893616, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.44513842463493347, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.396198570728302, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.6570266485214233, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.5703026056289673, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.722718253968254, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.7566964285714286, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.8095238095238095, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.8588789682539683, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.8943452380952381, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.9265873015873016, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9402281746031746, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.9481646825396826, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9541170634920635, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9588293650793651, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9600694444444444, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9645337301587301, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9662698412698413, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9694940476190477, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9717261904761905, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9734623015873016, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9742063492063492, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9766865079365079, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9776785714285714, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9784226190476191, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9794146825396826, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.980406746031746, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9811507936507936, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9811507936507936, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9811507936507936, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9816468253968254, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9809027777777778, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9806547619047619, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9796626984126984, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9789186507936508, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9784226190476191, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9779265873015873, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9771825396825397, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9771825396825397, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9769345238095238, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9776785714285714, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9781746031746031, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9774305555555556, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9761904761904762, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9779265873015873, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9717261904761905, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.970734126984127, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9734623015873016, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9717261904761905, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9699900793650794, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9699900793650794, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9747023809523809, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.96875, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9737103174603174, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.5118143335373063, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.575876483734388, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.6820773228448729, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.7815212561086772, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.8516609228590475, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.9105516290891165, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.9301756368298093, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9399839137040991, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9470460837799987, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9527138295871264, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9540563928321898, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9599243389461402, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9624392274519893, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9661102300327771, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9677605800286823, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9698011763313055, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9710872551611877, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9738137664494205, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9749340429534774, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.975354169701082, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9766601463919845, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9775921491697203, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9783451204569735, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9786583059478309, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.978841735501283, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9792007438791211, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9788324561815968, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9786686093460536, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.978172357957724, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9775335789283306, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9771824937193268, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9768886185987304, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9753667685639487, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9756511182441191, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9755035293391886, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9753305356853755, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9766870982732849, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9761638748311828, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9742145834142126, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.975462255243607, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9687992910006352, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9673147703978933, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9713346003879683, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9708632861209798, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9653889248221074, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9679953726177104, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9715271011190632, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9642180822938645, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.970387154155304, "id_best": 25, "lr_best": 0.00035999999999999997, "wd_best": 0.05, "train/loss_best": 0.01821214026771486, "validation/loss_best": 0.06400006264448166, "validation/acc_best": 0.9816468253968254, "validation/f1_best": 0.9792007438791211} +{"epoch": 11, "train/lr": 0.00018113997589164516, "train/loss": 0.20046523571014405, "train/grad": 0.03638857244513929, "train/loss_000_lr2.0e-02_wd1.0e+00": 1.6931359100341796, "train/loss_001_lr2.3e-02_wd1.0e+00": 1.5142350578308106, "train/loss_002_lr2.8e-02_wd1.0e+00": 1.244262409210205, "train/loss_003_lr3.3e-02_wd1.0e+00": 1.0168127870559693, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.8325542545318604, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.6385024440288544, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.4865026921033859, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.37513385355472567, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.28509826079010964, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.2284823451191187, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.19347599737346172, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.15979644257575273, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.13833064191043376, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.11703550128266216, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.10253250155597925, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.09175309853628277, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.08078840987756848, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.07041567246429623, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.060903470600023865, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.05339571574702859, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.04541831636801362, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.03841122585348785, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.031717502577230335, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.02576639473438263, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.020646040383726357, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.01583773585036397, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.012538221077993511, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.010203769281506538, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.00782263120636344, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.005983891636133194, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.004970746515318751, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.004361005192622542, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.003655010601505637, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.003290423769503832, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.0030950371734797953, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.002292943857610226, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.0021279882546514275, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.0031196721736341717, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.0030308250244706868, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.0027423569187521933, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.006454717963933944, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.00436857296153903, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.006327299382537604, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.006468275766819715, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.00921641024760902, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.017270069494843485, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.02892905951477587, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.05546155496500432, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.05812156977131963, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.011649397620931267, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.011327277696691453, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.010565153839997947, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.00971795842051506, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.008912397217936813, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.007932180552743376, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.007019879529252648, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.006226896494626999, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.005483308971161022, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.00498990586027503, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.004689395810710266, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.004413339974125847, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.004246909432113171, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.004080942256841809, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.003960893080802635, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.003863351778127253, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.003750175850582309, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.003629375763703138, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.0034968897310318427, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.0033718417381169274, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.0032121301349252464, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.003039863185258582, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.002836109605268575, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0026062695385189725, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0023478184785926713, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0020363041199743747, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0017664778050675524, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.001555157419643365, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0013252910124720075, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0011229134944005636, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0009778005432599457, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0008704035137270694, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0007559721491998062, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0006808086932142032, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0005675928561140608, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0005076302997349557, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0004506856614261778, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.000639457090378528, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0006629900434677439, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0007460572816125932, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0011799510004971126, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0012905165348990977, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0012869377841883533, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.001706295535072746, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.002693628916985862, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.003535804226510312, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.00509361480335446, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.007100272217341277, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.007833107596498917, "validation/loss_000_lr2.0e-02_wd1.0e+00": 1.6593033075332642, "validation/loss_001_lr2.3e-02_wd1.0e+00": 1.4783648252487183, "validation/loss_002_lr2.8e-02_wd1.0e+00": 1.2074347734451294, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.9813323616981506, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.7998784780502319, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.610870361328125, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.46435633301734924, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.35828688740730286, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.2737943232059479, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.22139781713485718, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.18929363787174225, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.1586887389421463, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.1394025981426239, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.12097923457622528, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.10873910784721375, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.10008265823125839, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.09165608882904053, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.08441587537527084, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.07820314168930054, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.0737871527671814, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.06970380246639252, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.06656065583229065, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.06419331580400467, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.06275785714387894, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.061825942248106, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.06172248348593712, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.06233961135149002, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.06314247101545334, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.0646757110953331, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.06659886240959167, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.06867048889398575, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.07042475789785385, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.07363161444664001, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.07589609920978546, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.07761411368846893, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.08054211735725403, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.08160421252250671, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.093480683863163, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.09531401842832565, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.10073355585336685, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.12623737752437592, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.148273766040802, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.12875014543533325, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.21475698053836823, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.23540763556957245, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.30629244446754456, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.4259556829929352, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.4101581871509552, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.4451315104961395, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.7390873015873016, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.7752976190476191, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.8286210317460317, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.8764880952380952, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9112103174603174, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.9360119047619048, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9451884920634921, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.9503968253968254, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9565972222222222, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9598214285714286, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9627976190476191, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9662698412698413, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9670138888888888, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9704861111111112, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9732142857142857, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9737103174603174, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9754464285714286, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9764384920634921, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9776785714285714, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9784226190476191, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9806547619047619, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9811507936507936, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9811507936507936, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9811507936507936, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9816468253968254, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9816468253968254, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9806547619047619, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.980406746031746, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9799107142857143, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9799107142857143, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9779265873015873, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9781746031746031, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9776785714285714, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9769345238095238, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9779265873015873, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9784226190476191, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9789186507936508, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9774305555555556, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9781746031746031, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9781746031746031, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9739583333333334, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9732142857142857, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9789186507936508, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9766865079365079, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9737103174603174, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9759424603174603, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9724702380952381, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9719742063492064, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9756944444444444, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.5433027040990028, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.6151168644217817, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.7238325024396922, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.8123510730706792, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.8842232554647137, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.9244075811294008, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.9360824798529526, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9416439262365367, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9498658108095793, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9535931357391082, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9573175489521959, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9622371290022445, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9630876072619114, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9666827657330244, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9702324562127622, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9707297415471601, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9733861905011048, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.974028369069817, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.975040778831291, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9758998549677285, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9787304196021752, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9793352904483792, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9791557839734553, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9787164749077275, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9788885096180172, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9787570961931399, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9771327237158164, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9772238293434725, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9768665899413117, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9774994060587342, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9755935948595814, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9761182705189025, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9760894348422489, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9747317853831022, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9759644084060708, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9764465796694581, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9777409410029008, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9762925324987939, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.976269134495837, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9762842535225661, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9704009640918213, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9686323140703379, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9767952105446566, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9752357468260862, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9695808933972558, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9725125871878908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9707806669529379, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9694190805327836, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.971685140222595, "id_best": 24, "lr_best": 0.0003, "wd_best": 0.05, "train/loss_best": 0.020646040383726357, "validation/loss_best": 0.061825942248106, "validation/acc_best": 0.9816468253968254, "validation/f1_best": 0.9788885096180172} +{"epoch": 12, "train/lr": 0.0001499999999999999, "train/loss": 0.1825221372395754, "train/grad": 0.03320393898524344, "train/loss_000_lr2.0e-02_wd1.0e+00": 1.6056570434570312, "train/loss_001_lr2.3e-02_wd1.0e+00": 1.4215681648254395, "train/loss_002_lr2.8e-02_wd1.0e+00": 1.1496193599700928, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.9263816452026368, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.750200788974762, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.5695628100633621, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.431927527487278, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.3334972605109215, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.25557736575603485, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.2069689305871725, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.17664416011422873, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.14701801996678113, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.12784800048917533, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.10856361500918865, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.095316724749282, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.08539954342879355, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.07531343087553978, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.06573949985206128, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.05695422946475446, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.05004024587571621, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.04271965434774756, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.03617831385694444, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.02994802000001073, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.024188697133213283, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.019200552729889752, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.014437431329861283, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.011214982615783811, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.008940712381154299, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.006707334043458104, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.004981439746916294, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0039201953541487455, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.00329247560352087, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.0028149422444403173, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.0026343593932688235, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.001983218314126134, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.0017175123374909163, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.0016865648329257965, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.001896355738863349, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.001861084047704935, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.001544514996930957, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.0024690758995711804, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.0041525672934949395, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.002196979746222496, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.002737626517191529, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.004624644313007593, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.003189767487347126, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.017332109808921813, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.01966354965232313, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.025551885487511753, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.011531316475011408, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.011117303813807666, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.010246222205460072, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.009351767199113965, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.008540566123556345, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.007574323788285256, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.006686229291372001, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.005920728698838502, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.005236331158084795, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.004804761330597103, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.00455242425436154, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.004323672822210938, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.004185076735448092, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.004044515555724501, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.003938543432159349, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.0038431286421837284, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.003726800477015786, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.0035926264949375764, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.0034327354113338517, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.0032794609741540626, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.0030848838685778902, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.0028751140600070356, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0026373225028510205, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.00238071210013004, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.002117445667099673, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0018096514880016912, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0015630546343163587, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0013626315335568506, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0011395448615803617, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0009283990255062235, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0007698599253490101, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0006544105309876613, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0005776916294780676, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0005119053253474703, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.00039020118749249377, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.00034259863130500887, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0003332117020363512, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0003547517405195322, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.00044306825900548575, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.000459674560311214, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0006679656184223859, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0008895387468851368, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0006299220260228822, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0009572588752834577, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0013953200929536535, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0010672304701779137, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0035903421759661837, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.004759985471878334, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.004260593470020185, "validation/loss_000_lr2.0e-02_wd1.0e+00": 1.5893748998641968, "validation/loss_001_lr2.3e-02_wd1.0e+00": 1.4039921760559082, "validation/loss_002_lr2.8e-02_wd1.0e+00": 1.1314759254455566, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.9093086123466492, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.7348663806915283, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.5570305585861206, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.42270147800445557, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.3273056149482727, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.25248801708221436, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.2063271850347519, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.17770898342132568, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.15012092888355255, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.13261543214321136, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.115618035197258, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.10427899658679962, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.09627851098775864, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.08848441392183304, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.08174606412649155, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.07616160809993744, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.07223314791917801, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.06862426549196243, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.0659637376666069, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.06406334787607193, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.06275971233844757, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.062180981040000916, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.06210875138640404, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.06277550756931305, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.06365938484668732, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.06538591533899307, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.06770198792219162, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.06997346132993698, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.07195331156253815, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.07418225705623627, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.07605668902397156, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.07986678928136826, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.08275921642780304, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.08369015157222748, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.09594178944826126, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.09703551977872849, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.09882236272096634, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.1361042559146881, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.12342825531959534, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.12438240647315979, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.1907508820295334, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.20955802500247955, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.3001236319541931, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.3255946636199951, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.34175345301628113, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.3832542300224304, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.751984126984127, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.7911706349206349, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.8472222222222222, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.8908730158730159, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9213789682539683, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.9387400793650794, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9469246031746031, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.9528769841269841, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9575892857142857, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9608134920634921, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9640376984126984, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9665178571428571, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9682539682539683, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9712301587301587, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9722222222222222, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9747023809523809, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9766865079365079, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9776785714285714, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9796626984126984, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9796626984126984, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.980406746031746, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9811507936507936, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9809027777777778, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9801587301587301, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9806547619047619, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9813988095238095, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9811507936507936, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9813988095238095, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9809027777777778, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9799107142857143, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9791666666666666, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9791666666666666, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9786706349206349, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9786706349206349, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9779265873015873, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9781746031746031, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9784226190476191, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9776785714285714, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9774305555555556, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9771825396825397, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9722222222222222, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9774305555555556, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9786706349206349, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9771825396825397, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9747023809523809, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9742063492063492, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9764384920634921, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9744543650793651, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9779265873015873, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.5693295032746122, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.6458468536223714, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.7573454842895833, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.8458258163607423, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.9019187265136982, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.9275013232931099, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.9375353769394618, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9448393701247061, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9516541328827793, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9551705736866494, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9592224785114946, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9625604682636277, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9642199819387042, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9678525119379177, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9688606290730428, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9712121334121241, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9738513275874068, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9750158284765876, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9767299527007661, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9768379573767841, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9781476544187611, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.978880894354669, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.979140018141828, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9783302508440012, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9790051003971891, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9795722631657416, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9793872168982107, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9799731316614204, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9793610079414362, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9786782240692414, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9777517874209096, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9776446701432503, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.977072335993188, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9771429908760337, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9765426618116491, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9768475430897287, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.977046549230618, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9764399770358094, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.975433583566878, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9749669550128746, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9691372449055345, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9746715026537719, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9755776465158044, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9750814215944504, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9709827667651655, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9717858892927944, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9730449930859736, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9706474367735803, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9750004083124156, "id_best": 25, "lr_best": 0.00035999999999999997, "wd_best": 0.05, "train/loss_best": 0.014437431329861283, "validation/loss_best": 0.06210875138640404, "validation/acc_best": 0.9813988095238095, "validation/f1_best": 0.9795722631657416} +{"epoch": 13, "train/lr": 0.00011886002410835478, "train/loss": 0.16882756039500235, "train/grad": 0.030734676923602818, "train/loss_000_lr2.0e-02_wd1.0e+00": 1.5370103454589843, "train/loss_001_lr2.3e-02_wd1.0e+00": 1.3495750904083252, "train/loss_002_lr2.8e-02_wd1.0e+00": 1.0781019115447998, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.86007253408432, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.6912235260009766, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.5213966363668442, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.3945372647047043, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.3051350027322769, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.23519800424575807, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.19145249858498573, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.16381322976201773, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.13651152316480875, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.11854896208271384, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.10025663143023848, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.08746327953413129, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.0777921745274216, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.06783886070363224, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.058318478772416714, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.04957539446651935, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.04271573249250651, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.03555651318281889, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.029328144546598198, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.02363726120442152, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.018660662304610012, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.01460196454077959, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.010974283860996366, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.008564684698358178, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.006906158868223429, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.005259045194834471, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0038826354034245014, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0030164445843547582, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.0025344968214631083, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.002302929274737835, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.0021200575958937404, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.0018156079947948456, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.0018032036256045102, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.0016817563772201537, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.0016732399817556143, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.0014661165140569211, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.0015043857786804437, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.0018679574970155955, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.0020838332176208495, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.0006117452960461378, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.0015691682510077954, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.0016100408043712377, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.002052907310426235, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.005705190962180496, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.006022332180291415, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.007200753651559353, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.011437179753556848, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.01096469066105783, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.010039994278922677, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.009133994474541395, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.008331477635074407, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.007386595294810831, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.006521445200778544, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.005786599819548428, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.005152504139114171, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.004763890258036554, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.004535301857395098, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.004322142395540141, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.004182837590342388, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.004031264981604181, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.0039103945414535705, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.003803384086641017, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.0036716989713022484, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.0035187993646832185, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.0033472192886983975, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.003187225449073594, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.0029854427033569665, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.00277297109758365, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0025354663201142104, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0022670529436436483, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.001990077480149921, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0016799224255373702, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.001430519559435197, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0012341635087068426, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0010104588327521924, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0007993070425800397, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0006461861082061659, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0005503868122468703, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.000483498420126125, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0004245446086315496, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.00033893969010023283, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0002987633487282437, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.00026115371839750877, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0002929892864585781, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0002911445514155275, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0003120843993258404, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.00039772952405201065, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0006516622338892831, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0002939167770955464, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0006458408706438945, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0005939439951925252, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0008008057493016202, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.001313799935656198, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0020081204422197512, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0014935042787020724, "validation/loss_000_lr2.0e-02_wd1.0e+00": 1.5357905626296997, "validation/loss_001_lr2.3e-02_wd1.0e+00": 1.3475768566131592, "validation/loss_002_lr2.8e-02_wd1.0e+00": 1.0748947858810425, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.8565228581428528, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.6879741549491882, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.5190247893333435, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.39329561591148376, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.3056034743785858, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.23769162595272064, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.19568629562854767, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.1695849746465683, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.1442468911409378, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.12802754342556, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.11189251393079758, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.10127196460962296, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.09372668713331223, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.08633431792259216, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.07999451458454132, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.07472328096628189, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.07113362103700638, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.06782087683677673, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.06564197689294815, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.0639268308877945, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.06315281242132187, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.06287527829408646, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.0631927028298378, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.06417427957057953, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.06537428498268127, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.06725975126028061, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.0694093108177185, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.07134576141834259, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.07339982688426971, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.07568368315696716, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.07718655467033386, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.08011004328727722, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.08265358954668045, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.083297498524189, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.09420216828584671, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.09644590318202972, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.09674496203660965, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.12019938230514526, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.12183663249015808, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.12238442152738571, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.1892477422952652, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.2018301784992218, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.2558995187282562, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.2764956057071686, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.2868053913116455, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.35016247630119324, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.7594246031746031, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.8033234126984127, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.8598710317460317, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.9010416666666666, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9265873015873016, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.939484126984127, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.949156746031746, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.9533730158730159, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9580853174603174, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9615575396825397, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9650297619047619, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9662698412698413, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9680059523809523, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9712301587301587, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9732142857142857, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9749503968253969, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9759424603174603, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9774305555555556, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9776785714285714, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9789186507936508, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9794146825396826, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9791666666666666, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.980406746031746, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9799107142857143, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9799107142857143, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9801587301587301, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9799107142857143, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9796626984126984, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9791666666666666, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9789186507936508, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9781746031746031, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9776785714285714, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9779265873015873, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9776785714285714, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9774305555555556, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9781746031746031, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9786706349206349, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9786706349206349, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9771825396825397, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9786706349206349, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9756944444444444, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9796626984126984, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9786706349206349, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9771825396825397, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9754464285714286, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9759424603174603, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9764384920634921, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9781746031746031, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9764384920634921, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.5849740673811601, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.6690444002763071, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.784042672518104, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.8658349587273038, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.9099586790265003, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.9285425144498611, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.9405788766051427, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9457797297233453, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9517523317582247, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.956238395516905, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9602583666509497, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9623690121276456, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.964132750235783, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9679737417634958, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9700719297803134, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9727604723447341, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9736549999785247, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9747986682800984, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9749767629730218, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9764908358402808, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9770072209087631, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9764906095096794, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9781347590476721, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9773348779314341, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.977590153019156, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9783480286496061, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9777558954763764, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9768368239664127, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9766766023080122, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9769351390541653, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9762395299849344, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9758798180887881, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9761069794599561, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9759457840484002, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9757616136545542, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9762494358378763, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9773393846979417, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9778270042931838, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9753121330460752, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9770684712328233, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9723644485432301, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.976850742263225, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9764873037478258, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9752452768731298, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9718253578741997, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9735964622016398, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9717831686644687, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9753065339167438, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9730105933397097, "id_best": 22, "lr_best": 0.00021599999999999996, "wd_best": 0.05, "train/loss_best": 0.02363726120442152, "validation/loss_best": 0.0639268308877945, "validation/acc_best": 0.980406746031746, "validation/f1_best": 0.9781347590476721} +{"epoch": 14, "train/lr": 8.9081919031238e-05, "train/loss": 0.16240245066583156, "train/grad": 0.0295558047760278, "train/loss_000_lr2.0e-02_wd1.0e+00": 1.5018753623962402, "train/loss_001_lr2.3e-02_wd1.0e+00": 1.3109413146972657, "train/loss_002_lr2.8e-02_wd1.0e+00": 1.0371920204162597, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.8207241177558899, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.6557642614841461, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.49235427379608154, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.3722441628575325, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.28886192381381987, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.22435039803385734, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.1842020257934928, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.1587512667104602, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.13343915943056345, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.11665004011243582, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.09940251467749477, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.08721234424971044, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.07785883596166969, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.06812975776381791, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.058714332822710276, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.04994514386169612, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.04305273968726397, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.03574774070642889, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.02939916823990643, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.023541722884401678, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.018486682334914805, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.014325226647779346, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.0105527981556952, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.008035825602710246, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0062832550704479215, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.004545041685923934, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0032318278960883615, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.002478773156180978, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.0020058331824839115, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.0015814324654638767, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.0013258436974138022, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.0010960560105741023, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.0009426605235785246, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.000804312378168106, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.0007412503566592932, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.0005053597036749124, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.0004765327274799347, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.0005374080035835504, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.00035722718574106695, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.00041818219237029554, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.0007944376487284899, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.00030994242988526823, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.0004930672328919173, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.00048765509389340876, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.006364081110805273, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.00018491419032216073, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.011339323418214918, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.010828768289647996, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.009861275721341371, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.00893247185042128, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.008122537850867957, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.007182069963309914, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.006340545094572008, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.005652497808914632, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.005075540114194155, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.004721394261578098, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.004506036040838808, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.004296585307456553, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.004156968424795195, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.004003607191843912, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.003884085488971323, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.0037804565770784395, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.0036553088010987268, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.003515603691339493, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.0033508981904014946, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.0031965743389446286, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.002990556051081512, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.00276548001304036, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.00249918379180599, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0022069417977763806, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0019057016372971702, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0015775537959416396, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.001330336194660049, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0011322960789402715, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.000901051591426949, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0006821974807462538, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0005460251126714866, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.000454923522338504, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.00036404922988367614, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.00030630934174041613, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0002530749881225347, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.00021479173722582345, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.00018676881724786655, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0001927710981817654, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.00016792310385881136, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0001581329798227671, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.00018644137034272036, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0001654036523478908, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.00017831892646654523, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.00040382622898363254, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.00017767534283620988, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.00017221052162443183, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.00025943134148975305, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0007692125121732996, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.00027722542409260384, "validation/loss_000_lr2.0e-02_wd1.0e+00": 1.4966628551483154, "validation/loss_001_lr2.3e-02_wd1.0e+00": 1.3067265748977661, "validation/loss_002_lr2.8e-02_wd1.0e+00": 1.0345072746276855, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.8192480206489563, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.6551119089126587, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.4926869869232178, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.3734525740146637, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.29095160961151123, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.22753065824508667, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.18841545283794403, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.16381575167179108, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.13981887698173523, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.12443631887435913, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.10924357920885086, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.09906402230262756, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.09182697534561157, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.08488209545612335, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.07880322635173798, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.07376667112112045, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.07026484608650208, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.0671563446521759, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.06493774056434631, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.06345832347869873, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.06265981495380402, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.06272120028734207, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.06322494894266129, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.06432466208934784, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.06563117355108261, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.06732232868671417, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.06948762387037277, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.07157227396965027, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.07324834913015366, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.07577935606241226, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.07754762470722198, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.08055391907691956, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.08326194435358047, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.0838351771235466, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.09438874572515488, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.09650642424821854, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.0957549437880516, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.12007269263267517, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.11940993368625641, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.11861251294612885, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.18536919355392456, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.19112278521060944, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.2393876612186432, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.249330535531044, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.2518562972545624, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.31200775504112244, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.7700892857142857, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.8100198412698413, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.8663194444444444, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.9072420634920635, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9300595238095238, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.9427083333333334, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.949156746031746, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.9556051587301587, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9585813492063492, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9623015873015873, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9657738095238095, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9670138888888888, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9689980158730159, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.972718253968254, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9744543650793651, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9766865079365079, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9774305555555556, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9781746031746031, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9794146825396826, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9794146825396826, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9801587301587301, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9813988095238095, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9809027777777778, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9811507936507936, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9811507936507936, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9806547619047619, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9806547619047619, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9809027777777778, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.980406746031746, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9791666666666666, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9789186507936508, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9786706349206349, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9779265873015873, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9779265873015873, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9774305555555556, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9786706349206349, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9791666666666666, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9779265873015873, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9769345238095238, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9779265873015873, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9749503968253969, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9786706349206349, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9786706349206349, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9769345238095238, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9749503968253969, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9756944444444444, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9769345238095238, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9791666666666666, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9789186507936508, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.6046396192563819, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.6825519826721036, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.793786574138034, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.876949780064815, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.9155462988513184, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.9333712085202117, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.9405650512056545, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9488358901788978, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9523015520342917, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9568939169062007, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9612734387654953, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9631663697437206, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9652670718751031, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9690112780570938, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9715693781563944, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9744106460024378, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9751017050264381, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9758994966036413, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9771567110836072, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9767872166678225, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9774845376673178, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9789941971526153, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9787835838370869, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9789904970342129, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.979057271422234, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9784399112777513, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9787090677285661, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9792356264737062, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9786846170030193, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9776498921967564, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9765832710624271, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9768785626919952, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9761970841409596, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9764686661627275, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9755802182732578, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9772837000413963, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9781526001596903, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9771072817534865, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9751268859503952, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9759785986406455, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9713166402613693, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9765649430879028, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9766458071057291, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9749143203929412, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9713283655172863, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9724848011052849, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9735762234445693, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9766421879409638, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9756912542789655, "id_best": 21, "lr_best": 0.00018299999999999998, "wd_best": 0.05, "train/loss_best": 0.02939916823990643, "validation/loss_best": 0.06493774056434631, "validation/acc_best": 0.9813988095238095, "validation/f1_best": 0.9789941971526153} +{"epoch": 15, "train/lr": 6.196799573888289e-05, "train/loss": 0.15732623860239983, "train/grad": 0.02890737629495561, "train/loss_000_lr2.0e-02_wd1.0e+00": 1.4681718444824219, "train/loss_001_lr2.3e-02_wd1.0e+00": 1.2771037006378174, "train/loss_002_lr2.8e-02_wd1.0e+00": 1.00511661529541, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.7920701313018799, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.6309195172786712, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.4725843501091003, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.3570604366064072, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.27754961237311365, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.21635646782815457, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.17820901568979025, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.15393291160464287, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.12966677010059358, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.11344889543950558, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.09674993923865259, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.08491996034979821, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.07582472413778304, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.06639754869043828, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.05727260421030223, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.04873781300149858, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.0420119690336287, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.034863611245527865, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.028619743697345257, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.022786822021007538, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.01781775018200278, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.01371145191602409, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.010092197097837924, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.0076918058842420575, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0060462111607193945, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.004449558109045028, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0031953143794089555, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.002457096064463258, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.00197333044372499, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.0015107340179383755, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.0012323626782745124, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.0009745346195995807, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.0007519628945738077, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.0006492379400879145, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.0005568598676472902, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.0004605095833539963, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.00038794740103185175, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.00040164144709706304, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.00040921979583799837, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.00042247152887284754, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.0007293205149471759, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.00030559535138309003, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.0009727187268435955, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.00041568368673324587, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.0009239146299660206, "train/loss_048_lr5.0e+01_wd1.0e+00": 7.145336829125881e-05, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.011249206801876426, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.010711367656476796, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.009724218263290823, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.008790650579612702, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.007975172081496567, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.007023136648349464, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.006167573789134621, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.005476102635730058, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.004904598153661937, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.004555804940173403, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.004347313445759937, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.004152089984854683, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.00402629823423922, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.0038925855979323387, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.0037838472018484025, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.003687133399071172, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.0035709330870304255, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.003431725986301899, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.003269998425676022, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.0031116405359352937, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.0029041063087061046, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.00267506839329144, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.002405309930909425, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0021147870205459186, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0018226814951049163, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.001508725859603146, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0012642181127739604, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0010662594212044495, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0008350410681305221, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0006289679117617198, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.000498251635071938, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.00040689227469556497, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.00031626538682758107, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0002578144829385565, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.00020043256034114166, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.00015862704216488055, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.00013126694848324404, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.00012646498922549653, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.00011273884311322036, "train/grad_039_lr1.2e+01_wd1.0e+00": 9.819810519275052e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0001221231135673406, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0001231935407167839, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0001711409302993161, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0002994269353132495, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0001556585268988897, "train/grad_045_lr3.1e+01_wd1.0e+00": 9.808159386998417e-05, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.00011428218168374026, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0005691014425410756, "train/grad_048_lr5.0e+01_wd1.0e+00": 6.276879979812338e-05, "validation/loss_000_lr2.0e-02_wd1.0e+00": 1.4698222875595093, "validation/loss_001_lr2.3e-02_wd1.0e+00": 1.278984546661377, "validation/loss_002_lr2.8e-02_wd1.0e+00": 1.0072581768035889, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.7942849397659302, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.6331586241722107, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.4751959443092346, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.3601285219192505, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.2811180651187897, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.22089974582195282, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.18362241983413696, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.16004890203475952, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.1369526982307434, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.12208323925733566, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.10723692923784256, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.09738706052303314, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.0902954488992691, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.08331811428070068, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.07731644809246063, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.07228831946849823, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.06889728456735611, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.06583059579133987, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.06387139856815338, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.06253188103437424, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.06205497309565544, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.06225348263978958, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.06317165493965149, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.06444600224494934, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.06570573151111603, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.06773824244737625, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.07008655369281769, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.0719282329082489, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.07400188595056534, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.07636633515357971, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.07804053276777267, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.08096609264612198, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.08329411596059799, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.08425209671258926, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.09480777382850647, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.09627673029899597, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.09515605866909027, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.11947073042392731, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.11855264753103256, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.1163998693227768, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.1763748675584793, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.1872296780347824, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.22895175218582153, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.22812995314598083, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.2407449334859848, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.29001396894454956, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.7752976190476191, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.8159722222222222, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.871031746031746, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.9112103174603174, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9315476190476191, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.9441964285714286, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9501488095238095, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.9558531746031746, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9593253968253969, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9630456349206349, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9662698412698413, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9677579365079365, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9692460317460317, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9724702380952381, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9756944444444444, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9761904761904762, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9781746031746031, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9794146825396826, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.980406746031746, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9809027777777778, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9811507936507936, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.980406746031746, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9809027777777778, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9801587301587301, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9801587301587301, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.980406746031746, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9801587301587301, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9799107142857143, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9794146825396826, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9794146825396826, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9789186507936508, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9779265873015873, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9776785714285714, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9779265873015873, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9771825396825397, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9779265873015873, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9789186507936508, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9774305555555556, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9766865079365079, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9779265873015873, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9749503968253969, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9784226190476191, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9786706349206349, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9774305555555556, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9749503968253969, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9756944444444444, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9769345238095238, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9779265873015873, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9789186507936508, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.616560631841312, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.6972285330751874, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.8039342136030725, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.8841201010245472, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.917940275490529, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.9350795121062144, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.9417456463864324, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9487550918679941, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9532077617387458, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9581628880628152, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9618724759870185, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.963820273663486, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9654922816676251, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9693023602051434, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9729555875914709, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9737019290280431, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9754554976838415, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9768676017367139, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9782225533878036, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.978772668229411, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9790148295800398, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9783720135522485, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9788303749755688, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.977411450730742, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9776743161312351, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9782024723878874, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.977654109795111, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.977800133611647, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9774467165687396, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9774967549724907, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9771432735547747, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9763180778105965, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9761263907315681, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9760715408429096, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9751007582269696, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.976326136932415, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9776216875040911, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9768170871229264, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9748570917417174, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9762910992574195, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9720087844722901, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9764314078013921, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9764868292015192, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9755668341193048, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.971638613953757, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9722338192765263, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9733107404362454, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9761597218165237, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9756593152204279, "id_best": 20, "lr_best": 0.000156, "wd_best": 0.05, "train/loss_best": 0.034863611245527865, "validation/loss_best": 0.06583059579133987, "validation/acc_best": 0.9811507936507936, "validation/f1_best": 0.9790148295800398} +{"epoch": 16, "train/lr": 3.870405029380728e-05, "train/loss": 0.1540222465991974, "train/grad": 0.02877298920415342, "train/loss_000_lr2.0e-02_wd1.0e+00": 1.4479934120178222, "train/loss_001_lr2.3e-02_wd1.0e+00": 1.255897045135498, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.9838416051864624, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.7723489093780518, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.6134293270111084, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.45867988348007205, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.34666005805134775, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.26996890738606455, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.21128704845905305, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.17456371311098337, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.15109968069940805, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.12758571127429605, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.11181918028742074, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.09553720737807453, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.0839397899247706, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.07499941845424474, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.06559633020311594, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.05650623818859458, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.04797629320062697, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.04119442451745272, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.034049851754680276, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.02785712164826691, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.022099951915442943, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.017187096634879707, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.01323179092258215, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.00966813124716282, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.007311814473941922, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.005662727113813162, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0040668455976992845, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.002844990435987711, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0021480968222022056, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.001719456547871232, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.0013229881785809994, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.0010809095297008753, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.00085651527158916, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.0006689519807696342, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.0005779386218637228, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.00046582545153796675, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.0003757205419242382, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.00033664405345916747, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.0003050590120255947, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.00030058134347200395, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.0003337649442255497, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.00041796868667006495, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.00024376860819756984, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.00012015578337013721, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.0005554889515042305, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.0003201149497181177, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.581126220524311e-05, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.011225167298689484, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.010670410329475999, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.009672715789638459, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.008741937864106148, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.00793085878714919, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.00698009290965274, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.006129362685605884, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.005452687509823591, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.004911123280180618, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.004584100411739201, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.004383077915990725, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.004192145837005228, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.004060466947848908, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.00392043307016138, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.0038089867949020117, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.0037086655374150724, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.0035851674363948406, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.003438207725994289, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.0032639881514478475, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.003096100889670197, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.0028680461723706685, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.002623652353649959, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.002338134965102654, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0020316536325844935, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0017295997154724318, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0014132668990350795, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0011725896129064495, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.000978984180619591, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0007554567455372307, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.000558076997695025, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0004309120852849446, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.00034825901388103376, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0002686013468701276, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.00021813438563185626, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.00016998531266835927, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.00013457233349072338, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.00011263216486440798, "train/grad_037_lr8.3e+00_wd1.0e+00": 9.715995984606707e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 8.842049671329732e-05, "train/grad_039_lr1.2e+01_wd1.0e+00": 8.101987963755165e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 8.95300235515606e-05, "train/grad_041_lr1.6e+01_wd1.0e+00": 9.680228915385669e-05, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0001318840901353724, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.00020177750086283197, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.00012377486816930627, "train/grad_045_lr3.1e+01_wd1.0e+00": 7.15991152769635e-05, "train/grad_046_lr3.6e+01_wd1.0e+00": 9.21965580540476e-05, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.00019081131466724187, "train/grad_048_lr5.0e+01_wd1.0e+00": 4.300967927980612e-05, "validation/loss_000_lr2.0e-02_wd1.0e+00": 1.4533429145812988, "validation/loss_001_lr2.3e-02_wd1.0e+00": 1.2620083093643188, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.990601658821106, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.7790158987045288, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.6199867129325867, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.4644984006881714, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.35214895009994507, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.2754412889480591, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.2169458419084549, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.1807229071855545, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.15782418847084045, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.13540753722190857, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.12073859572410583, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.10623311996459961, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.09650295227766037, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.08956964313983917, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.08281037956476212, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.07688897103071213, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.0721161738038063, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.0687723308801651, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.06597718596458435, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.06400936096906662, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.06286551058292389, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.062435753643512726, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.06263524293899536, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.0636616125702858, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.06504198908805847, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.06637393683195114, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.06850077956914902, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.0706838071346283, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.07274609059095383, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.07457006722688675, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.07689949870109558, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.07868083566427231, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.08122565597295761, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.08376423269510269, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.08440133929252625, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.09498204290866852, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.09613718092441559, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.09507302939891815, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.11826717108488083, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.11784709244966507, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.11533929407596588, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.17389385402202606, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.18400076031684875, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.2241867184638977, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.22782406210899353, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.22933360934257507, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.2780567705631256, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.7782738095238095, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.8199404761904762, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.8735119047619048, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.9134424603174603, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9325396825396826, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.9446924603174603, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9508928571428571, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.9563492063492064, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9593253968253969, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9632936507936508, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9665178571428571, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9672619047619048, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9689980158730159, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9729662698412699, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9749503968253969, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9761904761904762, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9779265873015873, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9784226190476191, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9794146825396826, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9809027777777778, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9806547619047619, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9799107142857143, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9806547619047619, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9809027777777778, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9809027777777778, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9806547619047619, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9801587301587301, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9799107142857143, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9794146825396826, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9789186507936508, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9779265873015873, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9776785714285714, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9774305555555556, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9774305555555556, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9774305555555556, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9786706349206349, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9794146825396826, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9774305555555556, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9769345238095238, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9781746031746031, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9756944444444444, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9781746031746031, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9781746031746031, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9774305555555556, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9747023809523809, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9751984126984127, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9776785714285714, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9789186507936508, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9789186507936508, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.6213296444469696, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.7050440744602914, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.8083653381603829, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.8878986119587603, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.9195550873959706, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.9357126129005986, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.9419938147000799, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9496825613464646, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9533958939591626, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9587046665948681, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9624168358417232, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9635269739523418, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9653052455011005, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9696627975507468, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9721056701154803, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9736916011199883, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9757620853082601, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9761049776339971, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9770417700923008, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9791336119167307, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9781052433218342, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9775262010065499, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9786507673747503, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9783232552913714, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9788315779013436, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9788743995635197, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.978145676955103, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9777760259113222, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9776321448009304, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9773207893216328, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9762227184944686, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9758710787055246, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9760415270903958, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.975650298364035, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9757644108360239, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9773752890069183, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9785169028666458, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9768170871229264, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9753099471188941, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9764726261343222, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9727357364972213, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.975904173812569, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9762874244062748, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9754165970548688, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9715175664574787, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.97190383026412, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9736126578970781, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9765846435930018, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9756479815537805, "id_best": 19, "lr_best": 0.00013199999999999998, "wd_best": 0.05, "train/loss_best": 0.04119442451745272, "validation/loss_best": 0.0687723308801651, "validation/acc_best": 0.9809027777777778, "validation/f1_best": 0.9791336119167307} +{"epoch": 17, "train/lr": 2.030750443206766e-05, "train/loss": 0.1510133921355009, "train/grad": 0.028239298863336443, "train/loss_000_lr2.0e-02_wd1.0e+00": 1.4259317588806153, "train/loss_001_lr2.3e-02_wd1.0e+00": 1.2340735626220702, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.9640890836715699, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.7552709031105042, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.5993116891384125, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.4478139281272888, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.33877016872167587, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.26459077224135397, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.2077958729863167, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.17225649811327456, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.149381929859519, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.12628011602908373, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.11072209801524878, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.09448965555988252, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.0828975432086736, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.07399013157002628, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.0645595867652446, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.055384018160402775, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.04686687108129263, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.04008937488310039, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.03294048863463104, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.02667232754640281, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.020881820879876615, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.01596299652941525, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.012037712903693319, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.008636388294398785, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.006471516415476799, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.005028419140726328, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.003621094189584255, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.002531583746895194, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0019319634698331356, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.001549486294388771, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.001200333135202527, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.000982393231242895, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.0007874664757400751, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.000626696003600955, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.0005264429654926061, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.0004248510953038931, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.0003448249399662018, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.0002933678310364485, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.0002600975800305605, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.00022708032280206682, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.0003121150191873312, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.0003302133642137051, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.00021303998306393624, "train/loss_045_lr3.1e+01_wd1.0e+00": 7.84775149077177e-05, "train/loss_046_lr3.6e+01_wd1.0e+00": 6.263005547225475e-05, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.00011535984463989735, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.959257155656814e-05, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.01109640855807811, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.010522571988403798, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.009509770818985998, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.008580020333174615, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.007775499138515443, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.00683648043544963, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.006000153876375407, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.005341651770286262, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.004821352541912347, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.0045156820653937755, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.004332147422246635, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.004158718220423907, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.00403926462167874, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.0039055996399838477, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.003792615683050826, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.003690309496014379, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.003558090743026696, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.003397407993616071, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.0032122875237837432, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.003028716139669996, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.002796816865447909, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.002544824428332504, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.002255125916271936, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0019463234771683346, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0016376419413427358, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0013149856309610185, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0010638545070105465, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0008708001939521637, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0006564992224957677, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0004753089530640864, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.00036825425857387015, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.00029729190979196576, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.00023124325585740734, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.00018969559202560048, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.00014976029360695974, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.00011985370759703074, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.00010087892484534677, "train/grad_037_lr8.3e+00_wd1.0e+00": 8.808229935766576e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 8.297294476960815e-05, "train/grad_039_lr1.2e+01_wd1.0e+00": 7.343981948451983e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 7.795185253939963e-05, "train/grad_041_lr1.6e+01_wd1.0e+00": 8.22361542532235e-05, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0001153177865910493, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.00016454681809705107, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.00011441817153635015, "train/grad_045_lr3.1e+01_wd1.0e+00": 5.803862636289736e-05, "train/grad_046_lr3.6e+01_wd1.0e+00": 5.6442744128726295e-05, "train/grad_047_lr4.3e+01_wd1.0e+00": 9.037571067462835e-05, "train/grad_048_lr5.0e+01_wd1.0e+00": 4.1785197907106936e-05, "validation/loss_000_lr2.0e-02_wd1.0e+00": 1.4447377920150757, "validation/loss_001_lr2.3e-02_wd1.0e+00": 1.2530171871185303, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.98178631067276, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.7710540294647217, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.6129890084266663, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.45903968811035156, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.34792277216911316, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.2724039554595947, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.21483269333839417, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.179183691740036, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.1566820591688156, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.134465292096138, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.11995457857847214, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.10558947175741196, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.09603983163833618, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.0892094224691391, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.08247624337673187, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.07675265520811081, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.07202646881341934, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.06880729645490646, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.06604890525341034, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.06413032859563828, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.06299151480197906, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.06262370944023132, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.06289225816726685, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.06378202140331268, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.06519796699285507, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.06651812791824341, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.06865966320037842, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.07081113755702972, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.07298729568719864, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.07500667124986649, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.07733246684074402, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.07899989932775497, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.0816686749458313, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.08409295976161957, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.0848008543252945, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.0953291654586792, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.09624778479337692, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.09512574225664139, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.11798123270273209, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.11726761609315872, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.11481670290231705, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.17284871637821198, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.1826719492673874, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.2205895185470581, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.22474926710128784, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.22591063380241394, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.2720223665237427, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.779265873015873, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.8206845238095238, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.8757440476190477, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.9151785714285714, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9337797619047619, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.9441964285714286, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.951140873015873, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.9563492063492064, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9590773809523809, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9637896825396826, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9665178571428571, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9677579365079365, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9699900793650794, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9724702380952381, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9751984126984127, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9764384920634921, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9776785714285714, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9786706349206349, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.980406746031746, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9801587301587301, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9796626984126984, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9801587301587301, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9801587301587301, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9801587301587301, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9806547619047619, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9806547619047619, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.980406746031746, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9801587301587301, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9794146825396826, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9784226190476191, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9779265873015873, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9771825396825397, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9771825396825397, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9771825396825397, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9771825396825397, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9784226190476191, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9794146825396826, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9774305555555556, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9771825396825397, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9779265873015873, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9749503968253969, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9781746031746031, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9784226190476191, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9774305555555556, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9747023809523809, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9751984126984127, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9779265873015873, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9786706349206349, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9789186507936508, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.6235618899166768, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.7076871400485993, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.8130746066663631, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.8908877259336989, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.9212357780407985, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.9348760298466209, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.9425441399765688, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9496825613464646, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9528558086226072, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9594002968122153, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9624170690212894, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9639817343779681, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9663878145016883, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9693917295201101, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9726499850828173, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9738698389022062, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9749812121217545, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9755486726471199, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9778968042782165, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9775045817990635, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.976706021072847, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9777967290216244, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9780112667228578, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9777430728894311, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.978533214246915, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9786846347327514, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.978461320327064, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9780706377475171, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9774967549724907, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9768293101371658, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9763619297501014, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9754677703943146, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.975238325136474, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9755046001070915, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9757215374125812, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9771479303855712, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9787004375204267, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.976881390634284, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9752304583052828, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9762372410355032, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9714552570982459, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.975904173812569, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.976466016754809, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9756014630181169, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9715175664574787, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.97190383026412, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9741575205071203, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9765836078950185, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9756479815537805, "id_best": 24, "lr_best": 0.0003, "wd_best": 0.05, "train/loss_best": 0.012037712903693319, "validation/loss_best": 0.06289225816726685, "validation/acc_best": 0.9806547619047619, "validation/f1_best": 0.978533214246915} +{"epoch": 18, "train/lr": 7.5829098008590064e-06, "train/loss": 0.14903156150132418, "train/grad": 0.02831465182825923, "train/loss_000_lr2.0e-02_wd1.0e+00": 1.430989761352539, "train/loss_001_lr2.3e-02_wd1.0e+00": 1.23719220161438, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.964094090461731, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.7529757499694825, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.5954584586620331, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.44259857028722766, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.3326697155833244, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.2578878158330917, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.20082337833940983, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.1652069152891636, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.14240928880870343, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.11955248923972249, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.1042145019955933, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.08834371787495911, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.07709855540655554, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.06844377793371677, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.05939641264267266, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.050666799331083895, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.042627143859863284, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.03630090182647109, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.02974801885895431, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.024176493054255843, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.01906171692535281, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.014722669394686819, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.011232613390311598, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.008150886353105307, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.006120156776160002, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0047273034788668155, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0033888800628483293, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0023924195766448974, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0018277611769735814, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.0014709354937076568, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.001148555725812912, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.0009423579555004835, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.000757473399862647, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.0005972613301128149, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.0005063693784177303, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.00041580870747566224, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.0003337719384580851, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.0002799649443477392, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.00025087833404541015, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.00022841580212116242, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.0002983429655432701, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.0003122019395232201, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.00021842578426003456, "train/loss_045_lr3.1e+01_wd1.0e+00": 7.440178655087948e-05, "train/loss_046_lr3.6e+01_wd1.0e+00": 6.233318708837032e-05, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.00010832872241735459, "train/loss_048_lr5.0e+01_wd1.0e+00": 4.1675232350826266e-05, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.011114732720889151, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.010534937605261802, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.009515493051148951, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.008578624569345265, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.007772034874651581, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.006836032625287771, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.0060110538802109655, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.005362945473752916, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.0048526337451767175, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.004547428730875254, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.0043611085892189295, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.0041831363935489205, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.004061334262369201, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.003923436914337799, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.0038078366062836723, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.0037039719364838674, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.003574078085948713, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.0034159946406725795, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.0032327584840822965, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.0030552005011122672, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.002820016171899624, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.0025737286210642195, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0022896811738610267, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.00197887601389084, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0016620224404323381, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0013340684573631733, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.001086421164436615, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0008886362388875568, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0006704746669856832, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.00048827302205609155, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.00037640675400325564, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.00030319974255689887, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.000236678368619323, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0001942416851488815, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.00015240078972055926, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.00012160570499872848, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.00010115923852026754, "train/grad_037_lr8.3e+00_wd1.0e+00": 8.753594740483095e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 8.132894661230238e-05, "train/grad_039_lr1.2e+01_wd1.0e+00": 7.17040412064307e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 7.755331860494152e-05, "train/grad_041_lr1.6e+01_wd1.0e+00": 8.14058701587328e-05, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0001123616477076439, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.00017117358717428033, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0001158012433765876, "train/grad_045_lr3.1e+01_wd1.0e+00": 5.043099083509972e-05, "train/grad_046_lr3.6e+01_wd1.0e+00": 5.261809205671653e-05, "train/grad_047_lr4.3e+01_wd1.0e+00": 9.383566948881317e-05, "train/grad_048_lr5.0e+01_wd1.0e+00": 4.159760592598143e-05, "validation/loss_000_lr2.0e-02_wd1.0e+00": 1.4415465593338013, "validation/loss_001_lr2.3e-02_wd1.0e+00": 1.2496737241744995, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.9786727428436279, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.7681957483291626, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.6103837490081787, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.4569794833660126, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.34636443853378296, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.27118855714797974, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.21405485272407532, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.17857420444488525, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.15618255734443665, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.1340380758047104, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.11962935328483582, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.10539624094963074, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.09583374857902527, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.08899524062871933, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.08236625045537949, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.0766100361943245, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.0719749853014946, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.06869829446077347, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.06592348963022232, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.064022958278656, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.06282968819141388, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.06258423626422882, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.0627611055970192, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.06365741044282913, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.0650891661643982, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.06646736711263657, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.06856153160333633, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.07087216526269913, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.07294001430273056, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.07472813874483109, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.07708976417779922, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.07889799773693085, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.08153660595417023, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.08401504158973694, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.08464829623699188, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.09537095576524734, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.0962144136428833, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.0950082540512085, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.1177028939127922, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.11719398945569992, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.1146901324391365, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.17248640954494476, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.18175692856311798, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.220240980386734, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.22338157892227173, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.22452566027641296, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.2700769007205963, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.7800099206349206, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.8216765873015873, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.8754960317460317, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.9154265873015873, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9340277777777778, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.9444444444444444, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9516369047619048, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.9565972222222222, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9595734126984127, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9635416666666666, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9665178571428571, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9677579365079365, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9699900793650794, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9724702380952381, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9749503968253969, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9764384920634921, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9779265873015873, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9789186507936508, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9801587301587301, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9799107142857143, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9799107142857143, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9801587301587301, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9799107142857143, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9806547619047619, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9801587301587301, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.980406746031746, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.980406746031746, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9799107142857143, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9791666666666666, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9786706349206349, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9776785714285714, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9774305555555556, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9774305555555556, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9774305555555556, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9771825396825397, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9786706349206349, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9794146825396826, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9774305555555556, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9764384920634921, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9779265873015873, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9749503968253969, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9781746031746031, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9784226190476191, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9776785714285714, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9747023809523809, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9749503968253969, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9774305555555556, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9784226190476191, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9789186507936508, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.6254527767859566, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.7084981866875478, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.8131042187367786, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.8924762953292736, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.9212130095908717, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.9350569326112091, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.9429018701017408, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.95010054615978, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9537796617309037, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9592707003174107, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9624170690212894, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9640292058889298, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9660719544156801, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9692684379116071, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9724700607972164, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9738707570933304, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9753968357139853, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9760900108581775, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9777180940523287, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9775035534341777, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9768386480279231, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9777967290216244, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9778707380602759, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9781441620921089, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.977821796593281, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9783240039588763, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9784603940528556, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9778916963420224, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9773909733142936, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9769453598670439, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9760174958787211, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.975656319553319, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9756689816237719, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9757532265740015, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9755428553671207, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.977372468707111, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9787446527269287, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.976881390634284, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9745727929198841, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9759762783408051, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9718245676780656, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.975904173812569, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.976466016754809, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9757799567858099, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9715175664574787, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9716750873316213, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9737535657543452, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9762271941568331, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9756479815537805, "id_best": 23, "lr_best": 0.00025499999999999996, "wd_best": 0.05, "train/loss_best": 0.014722669394686819, "validation/loss_best": 0.06258423626422882, "validation/acc_best": 0.9806547619047619, "validation/f1_best": 0.9781441620921089} +{"epoch": 19, "train/lr": 1.0867618231465446e-06, "train/loss": 0.15444730054587125, "train/grad": 0.028252207674086094, "train/loss_000_lr2.0e-02_wd1.0e+00": 1.4431160354614259, "train/loss_001_lr2.3e-02_wd1.0e+00": 1.2502382850646974, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.9781087875366211, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.7676475977897644, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.6104320478439331, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.4577958360314369, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.3478792430460453, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.2728899177908897, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.21542582906782626, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.17932074412703514, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.15613475788384676, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.13260567253455519, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.11671748299151659, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.10006130178458988, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.08805138764902949, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.0787497316300869, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.06886425442062319, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.05919202443212271, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.05002205456607044, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.04268411949276924, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.034913858352229, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.028111108988523485, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.0218650474678725, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.016590704713016748, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.012528539104387164, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.008971940148621798, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.00671519547700882, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.005211070459336042, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0037213523406535386, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.002616984397172928, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0019857349433004857, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.0015969137474894524, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.001244396921247244, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.001027662670239806, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.0008175663277506829, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.0006383250467479229, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.0005476810317486525, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.00044298806227743625, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.0003537345863878727, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.00030918060801923277, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.00027820637449622155, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.0002635850477963686, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.0003067870624363422, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.0003375802468508482, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.00024884392507374287, "train/loss_045_lr3.1e+01_wd1.0e+00": 8.538926020264626e-05, "train/loss_046_lr3.6e+01_wd1.0e+00": 7.435153238475323e-05, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.0001308103371411562, "train/loss_048_lr5.0e+01_wd1.0e+00": 4.5227445662021636e-05, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.011089152586646379, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.010513749006204307, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.009499103440903127, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.008563661377411335, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.007755198762752115, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.006821636194363236, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.006004136418923735, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.00535973826656118, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.0048468894162215295, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.004535772418603301, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.004346771388081833, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.004160712055163458, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.00403362289420329, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.003895113810431212, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.003780464109731838, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.003680379573488608, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.003551250530872494, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.0033945358102209864, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.0032113991197547874, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.0030318753953906706, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.0027965655067237094, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.0025437855307245626, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0022498155033099463, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0019337080777040684, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0016313495517533737, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0013089551367738749, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0010658014498767443, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0008767857958446257, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0006615199592488353, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0004818334730589413, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.00036967216179618846, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.00029795206188282464, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.00023291561972655473, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.00019179026876372517, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.00014966859369451414, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.00011801130261119398, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0001001459453618736, "train/grad_037_lr8.3e+00_wd1.0e+00": 8.769328004746058e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 8.030551931369701e-05, "train/grad_039_lr1.2e+01_wd1.0e+00": 7.387810407635698e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 7.665219468890428e-05, "train/grad_041_lr1.6e+01_wd1.0e+00": 8.305080066747905e-05, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.00010848940725622924, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0001691630861023441, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.00011417098272815451, "train/grad_045_lr3.1e+01_wd1.0e+00": 5.7603103720418204e-05, "train/grad_046_lr3.6e+01_wd1.0e+00": 5.9782326611824146e-05, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0001069815364203948, "train/grad_048_lr5.0e+01_wd1.0e+00": 4.336072354593666e-05, "validation/loss_000_lr2.0e-02_wd1.0e+00": 1.441043496131897, "validation/loss_001_lr2.3e-02_wd1.0e+00": 1.2492105960845947, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.9782201647758484, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.7677403688430786, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.6100424528121948, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.45664820075035095, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.3461354076862335, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.2710101008415222, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.21392503380775452, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.17849136888980865, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.15609057247638702, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.1339787095785141, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.11959993094205856, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.1053658202290535, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.0957942083477974, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.08896001428365707, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.08238395303487778, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.07662289589643478, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.07194488495588303, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.06868907064199448, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.06583939492702484, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.06406249850988388, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.06284582614898682, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.06250125169754028, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.06278929114341736, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.06370671838521957, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.06507547944784164, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.06649843603372574, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.0685841515660286, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.0708693265914917, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.07288245856761932, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.07473662495613098, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.0770297572016716, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.0788966715335846, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.08161716163158417, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.08407537639141083, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.08458655327558517, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.09531831741333008, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.09622090309858322, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.09503120929002762, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.11761067062616348, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.11718636751174927, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.11471640318632126, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.17244064807891846, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.18166889250278473, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.21952217817306519, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.22327405214309692, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.22415809333324432, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.26974043250083923, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.7795138888888888, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.8214285714285714, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.8754960317460317, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.9156746031746031, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9342757936507936, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.9446924603174603, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9513888888888888, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.9565972222222222, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9593253968253969, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9635416666666666, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9665178571428571, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9677579365079365, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9704861111111112, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9724702380952381, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9747023809523809, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9764384920634921, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9779265873015873, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9789186507936508, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9801587301587301, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9799107142857143, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9801587301587301, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9801587301587301, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9799107142857143, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9809027777777778, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9801587301587301, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.980406746031746, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.980406746031746, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9799107142857143, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9791666666666666, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9789186507936508, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9776785714285714, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9774305555555556, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9774305555555556, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9774305555555556, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9771825396825397, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9786706349206349, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9794146825396826, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9774305555555556, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9764384920634921, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9779265873015873, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9749503968253969, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9781746031746031, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9784226190476191, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9774305555555556, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9747023809523809, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9749503968253969, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9774305555555556, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9784226190476191, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9789186507936508, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.6252030730858608, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.7083807537711013, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.8130180671879201, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.8921356152554873, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.9217634232755705, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.9352377102437779, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.9427268141902778, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.95010054615978, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9533958939591626, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9592707003174107, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9624170690212894, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9640292058889298, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9667946860954916, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9692684379116071, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9719225514488656, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9738707570933304, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9753968357139853, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9760900108581775, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9777180940523287, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9775035534341777, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9773739549912619, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9780806360982487, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9779027107172281, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9783232753219386, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.977821796593281, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9783240039588763, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9784603940528556, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9778916963420224, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9773909733142936, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9772168251190182, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9760020393828216, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.975656319553319, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9756689816237719, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9756904218278987, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9755428553671207, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.977372468707111, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9785633658005102, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.976881390634284, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9745727929198841, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9759762783408051, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9716410081818788, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.975904173812569, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.976466016754809, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9756014630181169, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9715175664574787, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9716750873316213, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9737535657543452, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9762271941568331, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9755811916939033, "id_best": 23, "lr_best": 0.00025499999999999996, "wd_best": 0.05, "train/loss_best": 0.016590704713016748, "validation/loss_best": 0.06250125169754028, "validation/acc_best": 0.9809027777777778, "validation/f1_best": 0.9783232753219386} diff --git a/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__linear/config.yaml b/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__linear/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..9a8d5bd7e78a2cb6ed5ef806d5ae228f8405b277 --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__linear/config.yaml @@ -0,0 +1,96 @@ +output_root: experiments/decoders/output +name_prefix: eval_probe +remote_root: null +notes: decoder ablations crossreg_reg4; eval v2 (hcpya_task21 reg linear) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +dataset_kwargs: {} +classifier_kwargs: + embed_dim: null + dropout: 0.0 + xavier_init: false + norm: false +lr_scale_grid: +- 0.02 +- 0.023 +- 0.028 +- 0.033 +- 0.038 +- 0.045 +- 0.053 +- 0.062 +- 0.074 +- 0.087 +- 0.1 +- 0.12 +- 0.14 +- 0.17 +- 0.2 +- 0.23 +- 0.27 +- 0.32 +- 0.38 +- 0.44 +- 0.52 +- 0.61 +- 0.72 +- 0.85 +- 1 +- 1.2 +- 1.4 +- 1.6 +- 1.9 +- 2.3 +- 2.7 +- 3.1 +- 3.7 +- 4.3 +- 5.1 +- 6 +- 7.1 +- 8.3 +- 9.8 +- 12 +- 14 +- 16 +- 19 +- 22 +- 26 +- 31 +- 36 +- 43 +- 50 +wd_scale_grid: +- 1.0 +num_workers: 8 +prefetch_factor: null +balanced_sampling: false +epochs: 20 +steps_per_epoch: 200 +batch_size: 64 +accum_iter: 2 +lr: 0.0003 +warmup_epochs: 5 +no_decay: false +weight_decay: 0.05 +clip_grad: 1.0 +metrics: +- acc +- f1 +cv_metric: acc +early_stopping: true +amp: true +device: cuda +seed: 4466 +debug: false +wandb: false +wandb_entity: null +wandb_project: fMRI-fm-eval +name: decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__linear +model: flat_mae +representation: reg +classifier: linear +dataset: hcpya_task21 +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__linear +remote_dir: null diff --git a/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__linear/eval_log.json b/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__linear/eval_log.json new file mode 100644 index 0000000000000000000000000000000000000000..2bc6d32a90b96b7ab7f2ea8834d47d1e1a0305d3 --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__linear/eval_log.json @@ -0,0 +1 @@ +{"eval/epoch": 16, "eval/id_best": 47, "eval/lr_best": 0.012899999999999998, "eval/wd_best": 0.05, "eval/train/loss": 0.045580506324768066, "eval/train/acc": 0.9932628033054371, "eval/train/acc_std": 0.0005759690612889856, "eval/train/f1": 0.9945752581741296, "eval/train/f1_std": 0.0004984929288620381, "eval/validation/loss": 0.11011836677789688, "eval/validation/acc": 0.9692460317460317, "eval/validation/acc_std": 0.002672485185662656, "eval/validation/f1": 0.9634397574434674, "eval/validation/f1_std": 0.0036045798428122238, "eval/test/loss": 0.13361142575740814, "eval/test/acc": 0.9626984126984127, "eval/test/acc_std": 0.002597767655873538, "eval/test/f1": 0.9567782414613959, "eval/test/f1_std": 0.0034142196925447286} diff --git a/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__linear/eval_log_best.json b/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__linear/eval_log_best.json new file mode 100644 index 0000000000000000000000000000000000000000..715a7b2c6c72ea5bd0c4ba39a1fac4ee6fbe837c --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__linear/eval_log_best.json @@ -0,0 +1 @@ +{"eval/best/epoch": 16, "eval/best/id_best": 47, "eval/best/lr_best": 0.012899999999999998, "eval/best/wd_best": 0.05, "eval/best/train/loss": 0.045580506324768066, "eval/best/train/acc": 0.9932628033054371, "eval/best/train/acc_std": 0.0005759690612889856, "eval/best/train/f1": 0.9945752581741296, "eval/best/train/f1_std": 0.0004984929288620381, "eval/best/validation/loss": 0.11011836677789688, "eval/best/validation/acc": 0.9692460317460317, "eval/best/validation/acc_std": 0.002672485185662656, "eval/best/validation/f1": 0.9634397574434674, "eval/best/validation/f1_std": 0.0036045798428122238, "eval/best/test/loss": 0.13361142575740814, "eval/best/test/acc": 0.9626984126984127, "eval/best/test/acc_std": 0.002597767655873538, "eval/best/test/f1": 0.9567782414613959, "eval/best/test/f1_std": 0.0034142196925447286} diff --git a/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__linear/eval_log_last.json b/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__linear/eval_log_last.json new file mode 100644 index 0000000000000000000000000000000000000000..5f89db494bc2835c88851e4f218b66e162a245cb --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__linear/eval_log_last.json @@ -0,0 +1 @@ +{"eval/last/epoch": 19, "eval/last/id_best": 43, "eval/last/lr_best": 0.006599999999999999, "eval/last/wd_best": 0.05, "eval/last/train/loss": 0.05881621316075325, "eval/last/train/acc": 0.990157376704037, "eval/last/train/acc_std": 0.0007111911502121867, "eval/last/train/f1": 0.9912159372513739, "eval/last/train/f1_std": 0.0007002959171880783, "eval/last/validation/loss": 0.11311419308185577, "eval/last/validation/acc": 0.9682539682539683, "eval/last/validation/acc_std": 0.0027225725311416115, "eval/last/validation/f1": 0.9626198768348221, "eval/last/validation/f1_std": 0.003632717506997901, "eval/last/test/loss": 0.13546596467494965, "eval/last/test/acc": 0.9625, "eval/last/test/acc_std": 0.002650503619719388, "eval/last/test/f1": 0.9569064705527082, "eval/last/test/f1_std": 0.0034210302434791212} diff --git a/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__linear/eval_table.csv b/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__linear/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..295343d0815c4309149d659631f1105991d575ee --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__linear/eval_table.csv @@ -0,0 +1,4 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,reg,linear,hcpya_task21,best,16,0.012899999999999998,0.05,47,"[43, 1.0]",train,0.045580506324768066,0.9932628033054371,0.0005759690612889856,0.9945752581741296,0.0004984929288620381 +flat_mae,reg,linear,hcpya_task21,best,16,0.012899999999999998,0.05,47,"[43, 1.0]",validation,0.11011836677789688,0.9692460317460317,0.002672485185662656,0.9634397574434674,0.0036045798428122238 +flat_mae,reg,linear,hcpya_task21,best,16,0.012899999999999998,0.05,47,"[43, 1.0]",test,0.13361142575740814,0.9626984126984127,0.002597767655873538,0.9567782414613959,0.0034142196925447286 diff --git a/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__linear/eval_table_best.csv b/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__linear/eval_table_best.csv new file mode 100644 index 0000000000000000000000000000000000000000..295343d0815c4309149d659631f1105991d575ee --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__linear/eval_table_best.csv @@ -0,0 +1,4 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,reg,linear,hcpya_task21,best,16,0.012899999999999998,0.05,47,"[43, 1.0]",train,0.045580506324768066,0.9932628033054371,0.0005759690612889856,0.9945752581741296,0.0004984929288620381 +flat_mae,reg,linear,hcpya_task21,best,16,0.012899999999999998,0.05,47,"[43, 1.0]",validation,0.11011836677789688,0.9692460317460317,0.002672485185662656,0.9634397574434674,0.0036045798428122238 +flat_mae,reg,linear,hcpya_task21,best,16,0.012899999999999998,0.05,47,"[43, 1.0]",test,0.13361142575740814,0.9626984126984127,0.002597767655873538,0.9567782414613959,0.0034142196925447286 diff --git a/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__linear/eval_table_last.csv b/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__linear/eval_table_last.csv new file mode 100644 index 0000000000000000000000000000000000000000..09417d285a3e6c195d0aac2d0c6635c1a92e128e --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__linear/eval_table_last.csv @@ -0,0 +1,4 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,reg,linear,hcpya_task21,last,19,0.006599999999999999,0.05,43,"[22, 1.0]",train,0.05881621316075325,0.990157376704037,0.0007111911502121867,0.9912159372513739,0.0007002959171880783 +flat_mae,reg,linear,hcpya_task21,last,19,0.006599999999999999,0.05,43,"[22, 1.0]",validation,0.11311419308185577,0.9682539682539683,0.0027225725311416115,0.9626198768348221,0.003632717506997901 +flat_mae,reg,linear,hcpya_task21,last,19,0.006599999999999999,0.05,43,"[22, 1.0]",test,0.13546596467494965,0.9625,0.002650503619719388,0.9569064705527082,0.0034210302434791212 diff --git a/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__linear/log.txt b/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__linear/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..d34707d8bb201555285e921cacddf16fbf3b8166 --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__linear/log.txt @@ -0,0 +1,887 @@ +fMRI foundation model probe eval +version: 0.1.dev65+g4003a1397 +sha: 6c01b606db98add5848cecd23e5d599250c0bf86, status: clean, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-02-24 21:17:48 +config: +output_root: experiments/decoders/output +name_prefix: eval_probe +remote_root: null +notes: decoder ablations crossreg_reg4; eval v2 (hcpya_task21 reg linear) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +dataset_kwargs: {} +classifier_kwargs: + embed_dim: null + dropout: 0.0 + xavier_init: false + norm: false +lr_scale_grid: +- 0.02 +- 0.023 +- 0.028 +- 0.033 +- 0.038 +- 0.045 +- 0.053 +- 0.062 +- 0.074 +- 0.087 +- 0.1 +- 0.12 +- 0.14 +- 0.17 +- 0.2 +- 0.23 +- 0.27 +- 0.32 +- 0.38 +- 0.44 +- 0.52 +- 0.61 +- 0.72 +- 0.85 +- 1 +- 1.2 +- 1.4 +- 1.6 +- 1.9 +- 2.3 +- 2.7 +- 3.1 +- 3.7 +- 4.3 +- 5.1 +- 6 +- 7.1 +- 8.3 +- 9.8 +- 12 +- 14 +- 16 +- 19 +- 22 +- 26 +- 31 +- 36 +- 43 +- 50 +wd_scale_grid: +- 1.0 +num_workers: 8 +prefetch_factor: null +balanced_sampling: false +epochs: 20 +steps_per_epoch: 200 +batch_size: 64 +accum_iter: 2 +lr: 0.0003 +warmup_epochs: 5 +no_decay: false +weight_decay: 0.05 +clip_grad: 1.0 +metrics: +- acc +- f1 +cv_metric: acc +early_stopping: true +amp: true +device: cuda +seed: 4466 +debug: false +wandb: false +wandb_entity: null +wandb_project: fMRI-fm-eval +name: decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__linear +model: flat_mae +representation: reg +classifier: linear +dataset: hcpya_task21 +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__linear +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=False, reg_tokens=4, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: hcpya_task21 (flat) +train (n=18999): +HFDataset( + dataset=Dataset({ + features: ['sub', 'task', 'cond', 'cond_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 18999 +}), + labels=[ 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20], + counts=[ 832 1248 3201 1660 832 832 832 832 832 1248 1247 1243 832 416 + 416 416 416 416 416 416 416] +) + +validation (n=4032): +HFDataset( + dataset=Dataset({ + features: ['sub', 'task', 'cond', 'cond_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 4032 +}), + labels=[ 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20], + counts=[176 264 688 352 176 176 176 176 176 264 264 264 176 88 88 88 88 88 + 88 88 88] +) + +test (n=5040): +HFDataset( + dataset=Dataset({ + features: ['sub', 'task', 'cond', 'cond_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 5040 +}), + labels=[ 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20], + counts=[220 330 860 440 220 220 220 220 220 330 330 330 220 110 110 110 110 110 + 110 110 110] +) + +running backbone on example batch to get embedding dim +embedding feature dim (reg): 768 +initializing sweep of classifier heads +classifiers: +ModuleList( + (0-48): 49 x LinearClassifier( + (linear): Linear(in_features=768, out_features=21, bias=True) + ) +) +classifier params (train): 0.8M (0.8M) +setting up optimizer +total batch size: 128 = 64 bs per gpu x 2 accum +lr: 3.00e-04 +full schedule: epochs = 20 (steps = 4000) (decay = True) +warmup: epochs = 5 (steps = 1000) +start training for 20 epochs +train: [0] [ 0/400] eta: 0:21:38 lr: nan time: 3.2469 data: 2.8724 max mem: 3914 +train: [0] [ 20/400] eta: 0:03:07 lr: 0.000003 loss: 3.0185 (3.0137) grad: 0.1066 (0.1051) time: 0.3554 data: 0.0041 max mem: 3956 +train: [0] [ 40/400] eta: 0:02:30 lr: 0.000006 loss: 3.0185 (3.0139) grad: 0.1030 (0.1025) time: 0.3416 data: 0.0041 max mem: 3956 +train: [0] [ 60/400] eta: 0:02:16 lr: 0.000009 loss: 3.0020 (3.0067) grad: 0.1026 (0.1039) time: 0.3649 data: 0.0038 max mem: 3956 +train: [0] [ 80/400] eta: 0:02:02 lr: 0.000012 loss: 2.9815 (2.9998) grad: 0.1052 (0.1047) time: 0.3298 data: 0.0037 max mem: 3956 +train: [0] [100/400] eta: 0:01:52 lr: 0.000015 loss: 2.9654 (2.9902) grad: 0.1078 (0.1063) time: 0.3374 data: 0.0041 max mem: 3956 +train: [0] [120/400] eta: 0:01:42 lr: 0.000018 loss: 2.9373 (2.9780) grad: 0.1092 (0.1059) time: 0.3320 data: 0.0041 max mem: 3956 +train: [0] [140/400] eta: 0:01:34 lr: 0.000021 loss: 2.9045 (2.9665) grad: 0.1041 (0.1063) time: 0.3331 data: 0.0041 max mem: 3956 +train: [0] [160/400] eta: 0:01:26 lr: 0.000024 loss: 2.8766 (2.9544) grad: 0.1005 (0.1054) time: 0.3315 data: 0.0041 max mem: 3956 +train: [0] [180/400] eta: 0:01:18 lr: 0.000027 loss: 2.8463 (2.9378) grad: 0.0989 (0.1051) time: 0.3422 data: 0.0042 max mem: 3956 +train: [0] [200/400] eta: 0:01:11 lr: 0.000030 loss: 2.7871 (2.9214) grad: 0.0989 (0.1046) time: 0.3639 data: 0.0041 max mem: 3956 +train: [0] [220/400] eta: 0:01:04 lr: 0.000033 loss: 2.7667 (2.9060) grad: 0.0990 (0.1040) time: 0.3361 data: 0.0042 max mem: 3956 +train: [0] [240/400] eta: 0:00:56 lr: 0.000036 loss: 2.7244 (2.8881) grad: 0.0991 (0.1039) time: 0.3230 data: 0.0039 max mem: 3956 +train: [0] [260/400] eta: 0:00:49 lr: 0.000039 loss: 2.6737 (2.8697) grad: 0.1040 (0.1038) time: 0.3627 data: 0.0045 max mem: 3956 +train: [0] [280/400] eta: 0:00:42 lr: 0.000042 loss: 2.6433 (2.8526) grad: 0.0973 (0.1031) time: 0.3384 data: 0.0044 max mem: 3956 +train: [0] [300/400] eta: 0:00:36 lr: 0.000045 loss: 2.6005 (2.8346) grad: 0.0905 (0.1026) time: 0.4930 data: 0.1794 max mem: 3956 +train: [0] [320/400] eta: 0:00:28 lr: 0.000048 loss: 2.5648 (2.8161) grad: 0.0949 (0.1024) time: 0.3390 data: 0.0032 max mem: 3956 +train: [0] [340/400] eta: 0:00:21 lr: 0.000051 loss: 2.5061 (2.7977) grad: 0.1002 (0.1022) time: 0.3271 data: 0.0033 max mem: 3956 +train: [0] [360/400] eta: 0:00:14 lr: 0.000054 loss: 2.4902 (2.7805) grad: 0.0900 (0.1015) time: 0.3226 data: 0.0036 max mem: 3956 +train: [0] [380/400] eta: 0:00:07 lr: 0.000057 loss: 2.4540 (2.7620) grad: 0.0894 (0.1010) time: 0.3411 data: 0.0039 max mem: 3956 +train: [0] [399/400] eta: 0:00:00 lr: 0.000060 loss: 2.4033 (2.7436) grad: 0.0900 (0.1006) time: 0.3335 data: 0.0038 max mem: 3956 +train: [0] Total time: 0:02:22 (0.3552 s / it) +train: [0] Summary: lr: 0.000060 loss: 2.4033 (2.7436) grad: 0.0900 (0.1006) +eval (validation): [0] [ 0/63] eta: 0:03:21 time: 3.1955 data: 2.9930 max mem: 3956 +eval (validation): [0] [20/63] eta: 0:00:19 time: 0.3064 data: 0.0033 max mem: 3956 +eval (validation): [0] [40/63] eta: 0:00:09 time: 0.3578 data: 0.0038 max mem: 3956 +eval (validation): [0] [60/63] eta: 0:00:01 time: 0.3121 data: 0.0026 max mem: 3956 +eval (validation): [0] [62/63] eta: 0:00:00 time: 0.3054 data: 0.0028 max mem: 3956 +eval (validation): [0] Total time: 0:00:23 (0.3754 s / it) +cv: [0] best hparam: (50, 1.0) (048) ('048_lr5.0e+01_wd1.0e+00') loss: 0.522 acc: 0.932 f1: 0.928 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__linear/checkpoint-best.pth +train: [1] [ 0/400] eta: 0:20:53 lr: nan time: 3.1338 data: 2.9243 max mem: 3956 +train: [1] [ 20/400] eta: 0:02:50 lr: 0.000063 loss: 2.3715 (2.3656) grad: 0.0824 (0.0866) time: 0.3151 data: 0.0033 max mem: 3956 +train: [1] [ 40/400] eta: 0:02:23 lr: 0.000066 loss: 2.3599 (2.3607) grad: 0.0825 (0.0863) time: 0.3429 data: 0.0034 max mem: 3956 +train: [1] [ 60/400] eta: 0:02:07 lr: 0.000069 loss: 2.3333 (2.3436) grad: 0.0868 (0.0880) time: 0.3292 data: 0.0040 max mem: 3956 +train: [1] [ 80/400] eta: 0:01:56 lr: 0.000072 loss: 2.3071 (2.3376) grad: 0.0864 (0.0867) time: 0.3363 data: 0.0037 max mem: 3956 +train: [1] [100/400] eta: 0:01:47 lr: 0.000075 loss: 2.2919 (2.3241) grad: 0.0872 (0.0874) time: 0.3291 data: 0.0041 max mem: 3956 +train: [1] [120/400] eta: 0:01:38 lr: 0.000078 loss: 2.2210 (2.3061) grad: 0.0872 (0.0877) time: 0.3270 data: 0.0036 max mem: 3956 +train: [1] [140/400] eta: 0:01:30 lr: 0.000081 loss: 2.2164 (2.2922) grad: 0.0861 (0.0873) time: 0.3311 data: 0.0039 max mem: 3956 +train: [1] [160/400] eta: 0:01:23 lr: 0.000084 loss: 2.1965 (2.2797) grad: 0.0849 (0.0872) time: 0.3208 data: 0.0040 max mem: 3956 +train: [1] [180/400] eta: 0:01:15 lr: 0.000087 loss: 2.1697 (2.2650) grad: 0.0876 (0.0873) time: 0.3343 data: 0.0040 max mem: 3956 +train: [1] [200/400] eta: 0:01:08 lr: 0.000090 loss: 2.1403 (2.2501) grad: 0.0876 (0.0877) time: 0.3296 data: 0.0034 max mem: 3956 +train: [1] [220/400] eta: 0:01:02 lr: 0.000093 loss: 2.1134 (2.2360) grad: 0.0870 (0.0878) time: 0.3682 data: 0.0042 max mem: 3956 +train: [1] [240/400] eta: 0:00:55 lr: 0.000096 loss: 2.0867 (2.2230) grad: 0.0862 (0.0876) time: 0.3336 data: 0.0029 max mem: 3956 +train: [1] [260/400] eta: 0:00:48 lr: 0.000099 loss: 2.0867 (2.2127) grad: 0.0822 (0.0871) time: 0.3414 data: 0.0041 max mem: 3956 +train: [1] [280/400] eta: 0:00:41 lr: 0.000102 loss: 2.0539 (2.2014) grad: 0.0822 (0.0871) time: 0.3469 data: 0.0043 max mem: 3956 +train: [1] [300/400] eta: 0:00:35 lr: 0.000105 loss: 2.0466 (2.1899) grad: 0.0807 (0.0869) time: 0.4923 data: 0.1813 max mem: 3956 +train: [1] [320/400] eta: 0:00:28 lr: 0.000108 loss: 2.0009 (2.1767) grad: 0.0807 (0.0867) time: 0.3310 data: 0.0036 max mem: 3956 +train: [1] [340/400] eta: 0:00:21 lr: 0.000111 loss: 1.9939 (2.1666) grad: 0.0805 (0.0861) time: 0.3470 data: 0.0031 max mem: 3956 +train: [1] [360/400] eta: 0:00:14 lr: 0.000114 loss: 1.9939 (2.1561) grad: 0.0796 (0.0858) time: 0.3489 data: 0.0040 max mem: 3956 +train: [1] [380/400] eta: 0:00:07 lr: 0.000117 loss: 1.9697 (2.1453) grad: 0.0796 (0.0855) time: 0.3703 data: 0.0216 max mem: 3956 +train: [1] [399/400] eta: 0:00:00 lr: 0.000120 loss: 1.9443 (2.1350) grad: 0.0812 (0.0854) time: 0.3497 data: 0.0092 max mem: 3956 +train: [1] Total time: 0:02:21 (0.3533 s / it) +train: [1] Summary: lr: 0.000120 loss: 1.9443 (2.1350) grad: 0.0812 (0.0854) +eval (validation): [1] [ 0/63] eta: 0:03:25 time: 3.2601 data: 2.9842 max mem: 3956 +eval (validation): [1] [20/63] eta: 0:00:21 time: 0.3683 data: 0.0199 max mem: 3956 +eval (validation): [1] [40/63] eta: 0:00:09 time: 0.3377 data: 0.0034 max mem: 3956 +eval (validation): [1] [60/63] eta: 0:00:01 time: 0.3032 data: 0.0033 max mem: 3956 +eval (validation): [1] [62/63] eta: 0:00:00 time: 0.3017 data: 0.0033 max mem: 3956 +eval (validation): [1] Total time: 0:00:24 (0.3863 s / it) +cv: [1] best hparam: (50, 1.0) (048) ('048_lr5.0e+01_wd1.0e+00') loss: 0.230 acc: 0.949 f1: 0.946 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__linear/checkpoint-best.pth +train: [2] [ 0/400] eta: 0:20:46 lr: nan time: 3.1165 data: 2.8584 max mem: 3956 +train: [2] [ 20/400] eta: 0:02:52 lr: 0.000123 loss: 1.8838 (1.8871) grad: 0.0791 (0.0824) time: 0.3214 data: 0.0037 max mem: 3956 +train: [2] [ 40/400] eta: 0:02:32 lr: 0.000126 loss: 1.8939 (1.9002) grad: 0.0795 (0.0817) time: 0.3913 data: 0.0033 max mem: 3956 +train: [2] [ 60/400] eta: 0:02:16 lr: 0.000129 loss: 1.8939 (1.8940) grad: 0.0770 (0.0798) time: 0.3564 data: 0.0043 max mem: 3956 +train: [2] [ 80/400] eta: 0:02:02 lr: 0.000132 loss: 1.8776 (1.8906) grad: 0.0734 (0.0784) time: 0.3281 data: 0.0043 max mem: 3956 +train: [2] [100/400] eta: 0:01:52 lr: 0.000135 loss: 1.8664 (1.8810) grad: 0.0752 (0.0788) time: 0.3402 data: 0.0044 max mem: 3956 +train: [2] [120/400] eta: 0:01:43 lr: 0.000138 loss: 1.8262 (1.8724) grad: 0.0777 (0.0786) time: 0.3484 data: 0.0043 max mem: 3956 +train: [2] [140/400] eta: 0:01:35 lr: 0.000141 loss: 1.8282 (1.8665) grad: 0.0765 (0.0784) time: 0.3434 data: 0.0041 max mem: 3956 +train: [2] [160/400] eta: 0:01:26 lr: 0.000144 loss: 1.8113 (1.8591) grad: 0.0762 (0.0783) time: 0.3235 data: 0.0038 max mem: 3956 +train: [2] [180/400] eta: 0:01:19 lr: 0.000147 loss: 1.7929 (1.8497) grad: 0.0794 (0.0786) time: 0.3489 data: 0.0041 max mem: 3956 +train: [2] [200/400] eta: 0:01:11 lr: 0.000150 loss: 1.7854 (1.8434) grad: 0.0775 (0.0782) time: 0.3322 data: 0.0036 max mem: 3956 +train: [2] [220/400] eta: 0:01:04 lr: 0.000153 loss: 1.7854 (1.8353) grad: 0.0752 (0.0783) time: 0.3556 data: 0.0034 max mem: 3956 +train: [2] [240/400] eta: 0:00:56 lr: 0.000156 loss: 1.7289 (1.8273) grad: 0.0752 (0.0780) time: 0.3342 data: 0.0041 max mem: 3956 +train: [2] [260/400] eta: 0:00:49 lr: 0.000159 loss: 1.7306 (1.8218) grad: 0.0764 (0.0777) time: 0.3608 data: 0.0042 max mem: 3956 +train: [2] [280/400] eta: 0:00:42 lr: 0.000162 loss: 1.7243 (1.8138) grad: 0.0735 (0.0775) time: 0.3282 data: 0.0042 max mem: 3956 +train: [2] [300/400] eta: 0:00:36 lr: 0.000165 loss: 1.7089 (1.8077) grad: 0.0727 (0.0774) time: 0.4930 data: 0.1811 max mem: 3956 +train: [2] [320/400] eta: 0:00:28 lr: 0.000168 loss: 1.7017 (1.8004) grad: 0.0727 (0.0772) time: 0.3555 data: 0.0110 max mem: 3956 +train: [2] [340/400] eta: 0:00:21 lr: 0.000171 loss: 1.6937 (1.7944) grad: 0.0700 (0.0768) time: 0.3406 data: 0.0025 max mem: 3956 +train: [2] [360/400] eta: 0:00:14 lr: 0.000174 loss: 1.6850 (1.7874) grad: 0.0695 (0.0766) time: 0.3966 data: 0.0441 max mem: 3956 +train: [2] [380/400] eta: 0:00:07 lr: 0.000177 loss: 1.6776 (1.7812) grad: 0.0695 (0.0763) time: 0.3569 data: 0.0040 max mem: 3956 +train: [2] [399/400] eta: 0:00:00 lr: 0.000180 loss: 1.6556 (1.7744) grad: 0.0713 (0.0762) time: 0.3406 data: 0.0042 max mem: 3956 +train: [2] Total time: 0:02:24 (0.3624 s / it) +train: [2] Summary: lr: 0.000180 loss: 1.6556 (1.7744) grad: 0.0713 (0.0762) +eval (validation): [2] [ 0/63] eta: 0:03:28 time: 3.3038 data: 3.0373 max mem: 3956 +eval (validation): [2] [20/63] eta: 0:00:21 time: 0.3544 data: 0.0035 max mem: 3956 +eval (validation): [2] [40/63] eta: 0:00:09 time: 0.3069 data: 0.0033 max mem: 3956 +eval (validation): [2] [60/63] eta: 0:00:01 time: 0.3199 data: 0.0036 max mem: 3956 +eval (validation): [2] [62/63] eta: 0:00:00 time: 0.3156 data: 0.0037 max mem: 3956 +eval (validation): [2] Total time: 0:00:23 (0.3787 s / it) +cv: [2] best hparam: (50, 1.0) (048) ('048_lr5.0e+01_wd1.0e+00') loss: 0.169 acc: 0.956 f1: 0.952 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__linear/checkpoint-best.pth +train: [3] [ 0/400] eta: 0:21:25 lr: nan time: 3.2146 data: 2.9676 max mem: 3956 +train: [3] [ 20/400] eta: 0:03:10 lr: 0.000183 loss: 1.6312 (1.6241) grad: 0.0691 (0.0720) time: 0.3659 data: 0.0032 max mem: 3956 +train: [3] [ 40/400] eta: 0:02:31 lr: 0.000186 loss: 1.6104 (1.6131) grad: 0.0691 (0.0722) time: 0.3363 data: 0.0040 max mem: 3956 +train: [3] [ 60/400] eta: 0:02:12 lr: 0.000189 loss: 1.5797 (1.6007) grad: 0.0697 (0.0718) time: 0.3232 data: 0.0042 max mem: 3956 +train: [3] [ 80/400] eta: 0:01:59 lr: 0.000192 loss: 1.5850 (1.6024) grad: 0.0702 (0.0720) time: 0.3297 data: 0.0041 max mem: 3956 +train: [3] [100/400] eta: 0:01:51 lr: 0.000195 loss: 1.5912 (1.5966) grad: 0.0700 (0.0716) time: 0.3569 data: 0.0042 max mem: 3956 +train: [3] [120/400] eta: 0:01:41 lr: 0.000198 loss: 1.5505 (1.5882) grad: 0.0689 (0.0715) time: 0.3282 data: 0.0041 max mem: 3956 +train: [3] [140/400] eta: 0:01:33 lr: 0.000201 loss: 1.5513 (1.5872) grad: 0.0691 (0.0715) time: 0.3275 data: 0.0039 max mem: 3956 +train: [3] [160/400] eta: 0:01:24 lr: 0.000204 loss: 1.5492 (1.5832) grad: 0.0691 (0.0713) time: 0.3210 data: 0.0043 max mem: 3956 +train: [3] [180/400] eta: 0:01:17 lr: 0.000207 loss: 1.5468 (1.5786) grad: 0.0689 (0.0712) time: 0.3340 data: 0.0032 max mem: 3956 +train: [3] [200/400] eta: 0:01:09 lr: 0.000210 loss: 1.5505 (1.5748) grad: 0.0685 (0.0712) time: 0.3337 data: 0.0039 max mem: 3956 +train: [3] [220/400] eta: 0:01:02 lr: 0.000213 loss: 1.5363 (1.5712) grad: 0.0660 (0.0708) time: 0.3308 data: 0.0041 max mem: 3956 +train: [3] [240/400] eta: 0:00:55 lr: 0.000216 loss: 1.5239 (1.5670) grad: 0.0656 (0.0708) time: 0.3315 data: 0.0039 max mem: 3956 +train: [3] [260/400] eta: 0:00:48 lr: 0.000219 loss: 1.5132 (1.5634) grad: 0.0720 (0.0709) time: 0.3486 data: 0.0038 max mem: 3956 +train: [3] [280/400] eta: 0:00:41 lr: 0.000222 loss: 1.4907 (1.5578) grad: 0.0677 (0.0706) time: 0.3415 data: 0.0043 max mem: 3956 +train: [3] [300/400] eta: 0:00:35 lr: 0.000225 loss: 1.4844 (1.5536) grad: 0.0650 (0.0705) time: 0.5292 data: 0.2139 max mem: 3956 +train: [3] [320/400] eta: 0:00:28 lr: 0.000228 loss: 1.4775 (1.5499) grad: 0.0650 (0.0702) time: 0.3445 data: 0.0065 max mem: 3956 +train: [3] [340/400] eta: 0:00:21 lr: 0.000231 loss: 1.4665 (1.5445) grad: 0.0670 (0.0700) time: 0.3397 data: 0.0020 max mem: 3956 +train: [3] [360/400] eta: 0:00:14 lr: 0.000234 loss: 1.4556 (1.5401) grad: 0.0659 (0.0696) time: 0.3353 data: 0.0089 max mem: 3956 +train: [3] [380/400] eta: 0:00:07 lr: 0.000237 loss: 1.4514 (1.5359) grad: 0.0608 (0.0694) time: 0.3519 data: 0.0031 max mem: 3956 +train: [3] [399/400] eta: 0:00:00 lr: 0.000240 loss: 1.4472 (1.5300) grad: 0.0662 (0.0693) time: 0.3365 data: 0.0032 max mem: 3956 +train: [3] Total time: 0:02:22 (0.3551 s / it) +train: [3] Summary: lr: 0.000240 loss: 1.4472 (1.5300) grad: 0.0662 (0.0693) +eval (validation): [3] [ 0/63] eta: 0:03:27 time: 3.2987 data: 3.0479 max mem: 3956 +eval (validation): [3] [20/63] eta: 0:00:21 time: 0.3653 data: 0.0044 max mem: 3956 +eval (validation): [3] [40/63] eta: 0:00:09 time: 0.3443 data: 0.0032 max mem: 3956 +eval (validation): [3] [60/63] eta: 0:00:01 time: 0.3069 data: 0.0036 max mem: 3956 +eval (validation): [3] [62/63] eta: 0:00:00 time: 0.3052 data: 0.0035 max mem: 3956 +eval (validation): [3] Total time: 0:00:24 (0.3890 s / it) +cv: [3] best hparam: (50, 1.0) (048) ('048_lr5.0e+01_wd1.0e+00') loss: 0.143 acc: 0.962 f1: 0.957 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__linear/checkpoint-best.pth +train: [4] [ 0/400] eta: 0:20:12 lr: nan time: 3.0313 data: 2.7540 max mem: 3956 +train: [4] [ 20/400] eta: 0:03:06 lr: 0.000243 loss: 1.4146 (1.4406) grad: 0.0633 (0.0667) time: 0.3643 data: 0.0037 max mem: 3956 +train: [4] [ 40/400] eta: 0:02:31 lr: 0.000246 loss: 1.4096 (1.4261) grad: 0.0658 (0.0665) time: 0.3484 data: 0.0035 max mem: 3956 +train: [4] [ 60/400] eta: 0:02:13 lr: 0.000249 loss: 1.3985 (1.4163) grad: 0.0660 (0.0667) time: 0.3323 data: 0.0043 max mem: 3956 +train: [4] [ 80/400] eta: 0:02:01 lr: 0.000252 loss: 1.3977 (1.4114) grad: 0.0660 (0.0668) time: 0.3400 data: 0.0062 max mem: 3956 +train: [4] [100/400] eta: 0:01:50 lr: 0.000255 loss: 1.4034 (1.4088) grad: 0.0641 (0.0661) time: 0.3265 data: 0.0039 max mem: 3956 +train: [4] [120/400] eta: 0:01:41 lr: 0.000258 loss: 1.4145 (1.4083) grad: 0.0624 (0.0657) time: 0.3393 data: 0.0041 max mem: 3956 +train: [4] [140/400] eta: 0:01:34 lr: 0.000261 loss: 1.3536 (1.4009) grad: 0.0665 (0.0658) time: 0.3484 data: 0.0044 max mem: 3956 +train: [4] [160/400] eta: 0:01:26 lr: 0.000264 loss: 1.3536 (1.3983) grad: 0.0647 (0.0655) time: 0.3434 data: 0.0041 max mem: 3956 +train: [4] [180/400] eta: 0:01:18 lr: 0.000267 loss: 1.3609 (1.3937) grad: 0.0651 (0.0655) time: 0.3511 data: 0.0042 max mem: 3956 +train: [4] [200/400] eta: 0:01:11 lr: 0.000270 loss: 1.3371 (1.3866) grad: 0.0652 (0.0654) time: 0.3466 data: 0.0043 max mem: 3956 +train: [4] [220/400] eta: 0:01:03 lr: 0.000273 loss: 1.3360 (1.3834) grad: 0.0610 (0.0648) time: 0.3205 data: 0.0038 max mem: 3956 +train: [4] [240/400] eta: 0:00:56 lr: 0.000276 loss: 1.3355 (1.3777) grad: 0.0613 (0.0648) time: 0.3196 data: 0.0037 max mem: 3956 +train: [4] [260/400] eta: 0:00:49 lr: 0.000279 loss: 1.3181 (1.3736) grad: 0.0623 (0.0647) time: 0.3424 data: 0.0040 max mem: 3956 +train: [4] [280/400] eta: 0:00:41 lr: 0.000282 loss: 1.3146 (1.3702) grad: 0.0604 (0.0644) time: 0.3331 data: 0.0037 max mem: 3956 +train: [4] [300/400] eta: 0:00:35 lr: 0.000285 loss: 1.3036 (1.3653) grad: 0.0602 (0.0643) time: 0.4982 data: 0.1862 max mem: 3956 +train: [4] [320/400] eta: 0:00:28 lr: 0.000288 loss: 1.3090 (1.3621) grad: 0.0635 (0.0644) time: 0.3377 data: 0.0035 max mem: 3956 +train: [4] [340/400] eta: 0:00:21 lr: 0.000291 loss: 1.3227 (1.3586) grad: 0.0605 (0.0641) time: 0.3148 data: 0.0038 max mem: 3956 +train: [4] [360/400] eta: 0:00:14 lr: 0.000294 loss: 1.2832 (1.3544) grad: 0.0601 (0.0639) time: 0.3350 data: 0.0031 max mem: 3956 +train: [4] [380/400] eta: 0:00:07 lr: 0.000297 loss: 1.2865 (1.3521) grad: 0.0596 (0.0637) time: 0.3386 data: 0.0068 max mem: 3956 +train: [4] [399/400] eta: 0:00:00 lr: 0.000300 loss: 1.2865 (1.3480) grad: 0.0592 (0.0636) time: 0.3804 data: 0.0526 max mem: 3956 +train: [4] Total time: 0:02:22 (0.3553 s / it) +train: [4] Summary: lr: 0.000300 loss: 1.2865 (1.3480) grad: 0.0592 (0.0636) +eval (validation): [4] [ 0/63] eta: 0:03:29 time: 3.3282 data: 3.0629 max mem: 3956 +eval (validation): [4] [20/63] eta: 0:00:20 time: 0.3302 data: 0.0038 max mem: 3956 +eval (validation): [4] [40/63] eta: 0:00:09 time: 0.3178 data: 0.0034 max mem: 3956 +eval (validation): [4] [60/63] eta: 0:00:01 time: 0.2928 data: 0.0035 max mem: 3956 +eval (validation): [4] [62/63] eta: 0:00:00 time: 0.2920 data: 0.0035 max mem: 3956 +eval (validation): [4] Total time: 0:00:22 (0.3649 s / it) +cv: [4] best hparam: (50, 1.0) (048) ('048_lr5.0e+01_wd1.0e+00') loss: 0.129 acc: 0.963 f1: 0.957 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__linear/checkpoint-best.pth +train: [5] [ 0/400] eta: 0:21:42 lr: nan time: 3.2571 data: 2.9840 max mem: 3956 +train: [5] [ 20/400] eta: 0:02:58 lr: 0.000300 loss: 1.2425 (1.2610) grad: 0.0550 (0.0585) time: 0.3302 data: 0.0270 max mem: 3956 +train: [5] [ 40/400] eta: 0:02:32 lr: 0.000300 loss: 1.2573 (1.2730) grad: 0.0594 (0.0590) time: 0.3757 data: 0.0499 max mem: 3956 +train: [5] [ 60/400] eta: 0:02:12 lr: 0.000300 loss: 1.2626 (1.2633) grad: 0.0612 (0.0605) time: 0.3190 data: 0.0035 max mem: 3956 +train: [5] [ 80/400] eta: 0:01:59 lr: 0.000300 loss: 1.2417 (1.2587) grad: 0.0612 (0.0603) time: 0.3237 data: 0.0041 max mem: 3956 +train: [5] [100/400] eta: 0:01:48 lr: 0.000300 loss: 1.2284 (1.2523) grad: 0.0611 (0.0610) time: 0.3192 data: 0.0038 max mem: 3956 +train: [5] [120/400] eta: 0:01:39 lr: 0.000300 loss: 1.2284 (1.2502) grad: 0.0625 (0.0613) time: 0.3209 data: 0.0039 max mem: 3956 +train: [5] [140/400] eta: 0:01:31 lr: 0.000300 loss: 1.2295 (1.2478) grad: 0.0607 (0.0611) time: 0.3301 data: 0.0043 max mem: 3956 +train: [5] [160/400] eta: 0:01:23 lr: 0.000299 loss: 1.2108 (1.2442) grad: 0.0594 (0.0610) time: 0.3171 data: 0.0040 max mem: 3956 +train: [5] [180/400] eta: 0:01:16 lr: 0.000299 loss: 1.2128 (1.2426) grad: 0.0575 (0.0607) time: 0.3510 data: 0.0041 max mem: 3956 +train: [5] [200/400] eta: 0:01:09 lr: 0.000299 loss: 1.2078 (1.2400) grad: 0.0572 (0.0605) time: 0.3363 data: 0.0041 max mem: 3956 +train: [5] [220/400] eta: 0:01:02 lr: 0.000299 loss: 1.2059 (1.2363) grad: 0.0589 (0.0605) time: 0.3348 data: 0.0042 max mem: 3956 +train: [5] [240/400] eta: 0:00:55 lr: 0.000299 loss: 1.1929 (1.2328) grad: 0.0582 (0.0605) time: 0.3434 data: 0.0043 max mem: 3956 +train: [5] [260/400] eta: 0:00:48 lr: 0.000299 loss: 1.1929 (1.2308) grad: 0.0570 (0.0603) time: 0.3410 data: 0.0043 max mem: 3956 +train: [5] [280/400] eta: 0:00:41 lr: 0.000298 loss: 1.1916 (1.2276) grad: 0.0568 (0.0601) time: 0.3284 data: 0.0043 max mem: 3956 +train: [5] [300/400] eta: 0:00:35 lr: 0.000298 loss: 1.1752 (1.2248) grad: 0.0550 (0.0598) time: 0.5280 data: 0.1803 max mem: 3956 +train: [5] [320/400] eta: 0:00:28 lr: 0.000298 loss: 1.1752 (1.2222) grad: 0.0562 (0.0596) time: 0.4032 data: 0.0322 max mem: 3956 +train: [5] [340/400] eta: 0:00:21 lr: 0.000298 loss: 1.1721 (1.2192) grad: 0.0568 (0.0594) time: 0.3499 data: 0.0328 max mem: 3956 +train: [5] [360/400] eta: 0:00:14 lr: 0.000297 loss: 1.1709 (1.2165) grad: 0.0577 (0.0593) time: 0.3366 data: 0.0039 max mem: 3956 +train: [5] [380/400] eta: 0:00:07 lr: 0.000297 loss: 1.1765 (1.2155) grad: 0.0570 (0.0592) time: 0.3235 data: 0.0023 max mem: 3956 +train: [5] [399/400] eta: 0:00:00 lr: 0.000297 loss: 1.1646 (1.2117) grad: 0.0587 (0.0592) time: 0.3252 data: 0.0022 max mem: 3956 +train: [5] Total time: 0:02:21 (0.3548 s / it) +train: [5] Summary: lr: 0.000297 loss: 1.1646 (1.2117) grad: 0.0587 (0.0592) +eval (validation): [5] [ 0/63] eta: 0:03:28 time: 3.3082 data: 3.1031 max mem: 3956 +eval (validation): [5] [20/63] eta: 0:00:25 time: 0.4595 data: 0.1448 max mem: 3956 +eval (validation): [5] [40/63] eta: 0:00:10 time: 0.3421 data: 0.0036 max mem: 3956 +eval (validation): [5] [60/63] eta: 0:00:01 time: 0.2923 data: 0.0033 max mem: 3956 +eval (validation): [5] [62/63] eta: 0:00:00 time: 0.2955 data: 0.0032 max mem: 3956 +eval (validation): [5] Total time: 0:00:26 (0.4153 s / it) +cv: [5] best hparam: (43, 1.0) (047) ('047_lr4.3e+01_wd1.0e+00') loss: 0.129 acc: 0.964 f1: 0.959 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__linear/checkpoint-best.pth +train: [6] [ 0/400] eta: 0:21:08 lr: nan time: 3.1724 data: 2.9456 max mem: 3956 +train: [6] [ 20/400] eta: 0:03:40 lr: 0.000296 loss: 1.1560 (1.1665) grad: 0.0547 (0.0564) time: 0.4515 data: 0.1134 max mem: 3956 +train: [6] [ 40/400] eta: 0:02:43 lr: 0.000296 loss: 1.1592 (1.1660) grad: 0.0546 (0.0562) time: 0.3236 data: 0.0035 max mem: 3956 +train: [6] [ 60/400] eta: 0:02:20 lr: 0.000296 loss: 1.1581 (1.1617) grad: 0.0555 (0.0568) time: 0.3230 data: 0.0040 max mem: 3956 +train: [6] [ 80/400] eta: 0:02:05 lr: 0.000295 loss: 1.1203 (1.1536) grad: 0.0565 (0.0567) time: 0.3262 data: 0.0035 max mem: 3956 +train: [6] [100/400] eta: 0:01:55 lr: 0.000295 loss: 1.1096 (1.1471) grad: 0.0562 (0.0564) time: 0.3530 data: 0.0035 max mem: 3956 +train: [6] [120/400] eta: 0:01:44 lr: 0.000295 loss: 1.1112 (1.1438) grad: 0.0545 (0.0564) time: 0.3328 data: 0.0041 max mem: 3956 +train: [6] [140/400] eta: 0:01:35 lr: 0.000294 loss: 1.1061 (1.1381) grad: 0.0555 (0.0569) time: 0.3267 data: 0.0040 max mem: 3956 +train: [6] [160/400] eta: 0:01:27 lr: 0.000294 loss: 1.1061 (1.1346) grad: 0.0571 (0.0571) time: 0.3452 data: 0.0042 max mem: 3956 +train: [6] [180/400] eta: 0:01:19 lr: 0.000293 loss: 1.1287 (1.1338) grad: 0.0566 (0.0572) time: 0.3365 data: 0.0042 max mem: 3956 +train: [6] [200/400] eta: 0:01:11 lr: 0.000293 loss: 1.1267 (1.1318) grad: 0.0554 (0.0570) time: 0.3258 data: 0.0037 max mem: 3956 +train: [6] [220/400] eta: 0:01:04 lr: 0.000292 loss: 1.0909 (1.1275) grad: 0.0553 (0.0569) time: 0.3374 data: 0.0039 max mem: 3956 +train: [6] [240/400] eta: 0:00:56 lr: 0.000292 loss: 1.0869 (1.1250) grad: 0.0549 (0.0567) time: 0.3372 data: 0.0044 max mem: 3956 +train: [6] [260/400] eta: 0:00:49 lr: 0.000291 loss: 1.1026 (1.1242) grad: 0.0554 (0.0567) time: 0.3365 data: 0.0041 max mem: 3956 +train: [6] [280/400] eta: 0:00:42 lr: 0.000291 loss: 1.0823 (1.1207) grad: 0.0549 (0.0566) time: 0.3339 data: 0.0040 max mem: 3956 +train: [6] [300/400] eta: 0:00:36 lr: 0.000290 loss: 1.0508 (1.1175) grad: 0.0545 (0.0564) time: 0.4875 data: 0.1818 max mem: 3956 +train: [6] [320/400] eta: 0:00:29 lr: 0.000290 loss: 1.0508 (1.1138) grad: 0.0549 (0.0563) time: 0.4131 data: 0.0606 max mem: 3956 +train: [6] [340/400] eta: 0:00:21 lr: 0.000289 loss: 1.0619 (1.1122) grad: 0.0556 (0.0562) time: 0.3521 data: 0.0041 max mem: 3956 +train: [6] [360/400] eta: 0:00:14 lr: 0.000288 loss: 1.0701 (1.1091) grad: 0.0562 (0.0563) time: 0.3373 data: 0.0042 max mem: 3956 +train: [6] [380/400] eta: 0:00:07 lr: 0.000288 loss: 1.0679 (1.1078) grad: 0.0529 (0.0561) time: 0.3553 data: 0.0044 max mem: 3956 +train: [6] [399/400] eta: 0:00:00 lr: 0.000287 loss: 1.0846 (1.1062) grad: 0.0530 (0.0562) time: 0.3460 data: 0.0044 max mem: 3956 +train: [6] Total time: 0:02:24 (0.3617 s / it) +train: [6] Summary: lr: 0.000287 loss: 1.0846 (1.1062) grad: 0.0530 (0.0562) +eval (validation): [6] [ 0/63] eta: 0:03:25 time: 3.2566 data: 3.0383 max mem: 3956 +eval (validation): [6] [20/63] eta: 0:00:22 time: 0.3948 data: 0.0648 max mem: 3956 +eval (validation): [6] [40/63] eta: 0:00:10 time: 0.3899 data: 0.0029 max mem: 3956 +eval (validation): [6] [60/63] eta: 0:00:01 time: 0.3329 data: 0.0037 max mem: 3956 +eval (validation): [6] [62/63] eta: 0:00:00 time: 0.3257 data: 0.0037 max mem: 3956 +eval (validation): [6] Total time: 0:00:26 (0.4222 s / it) +cv: [6] best hparam: (50, 1.0) (048) ('048_lr5.0e+01_wd1.0e+00') loss: 0.119 acc: 0.968 f1: 0.963 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__linear/checkpoint-best.pth +train: [7] [ 0/400] eta: 0:36:44 lr: nan time: 5.5107 data: 5.2551 max mem: 3956 +train: [7] [ 20/400] eta: 0:03:43 lr: 0.000286 loss: 1.0392 (1.0661) grad: 0.0533 (0.0556) time: 0.3416 data: 0.0208 max mem: 3956 +train: [7] [ 40/400] eta: 0:02:43 lr: 0.000286 loss: 1.0579 (1.0654) grad: 0.0534 (0.0555) time: 0.3125 data: 0.0027 max mem: 3956 +train: [7] [ 60/400] eta: 0:02:19 lr: 0.000285 loss: 1.0564 (1.0565) grad: 0.0539 (0.0562) time: 0.3254 data: 0.0039 max mem: 3956 +train: [7] [ 80/400] eta: 0:02:06 lr: 0.000284 loss: 1.0570 (1.0620) grad: 0.0532 (0.0552) time: 0.3405 data: 0.0044 max mem: 3956 +train: [7] [100/400] eta: 0:01:54 lr: 0.000284 loss: 1.0540 (1.0566) grad: 0.0520 (0.0546) time: 0.3291 data: 0.0037 max mem: 3956 +train: [7] [120/400] eta: 0:01:43 lr: 0.000283 loss: 1.0347 (1.0552) grad: 0.0529 (0.0545) time: 0.3140 data: 0.0042 max mem: 3956 +train: [7] [140/400] eta: 0:01:34 lr: 0.000282 loss: 1.0416 (1.0535) grad: 0.0530 (0.0542) time: 0.3366 data: 0.0042 max mem: 3956 +train: [7] [160/400] eta: 0:01:26 lr: 0.000282 loss: 1.0316 (1.0502) grad: 0.0530 (0.0540) time: 0.3301 data: 0.0036 max mem: 3956 +train: [7] [180/400] eta: 0:01:18 lr: 0.000281 loss: 1.0260 (1.0472) grad: 0.0518 (0.0539) time: 0.3302 data: 0.0037 max mem: 3956 +train: [7] [200/400] eta: 0:01:11 lr: 0.000280 loss: 1.0260 (1.0473) grad: 0.0533 (0.0538) time: 0.3327 data: 0.0043 max mem: 3956 +train: [7] [220/400] eta: 0:01:03 lr: 0.000279 loss: 1.0440 (1.0476) grad: 0.0537 (0.0538) time: 0.3274 data: 0.0038 max mem: 3956 +train: [7] [240/400] eta: 0:00:56 lr: 0.000278 loss: 1.0281 (1.0468) grad: 0.0523 (0.0537) time: 0.3470 data: 0.0039 max mem: 3956 +train: [7] [260/400] eta: 0:00:49 lr: 0.000278 loss: 1.0041 (1.0439) grad: 0.0519 (0.0536) time: 0.3458 data: 0.0038 max mem: 3956 +train: [7] [280/400] eta: 0:00:42 lr: 0.000277 loss: 1.0190 (1.0424) grad: 0.0498 (0.0534) time: 0.3381 data: 0.0038 max mem: 3956 +train: [7] [300/400] eta: 0:00:36 lr: 0.000276 loss: 1.0193 (1.0410) grad: 0.0493 (0.0532) time: 0.5547 data: 0.2312 max mem: 3956 +train: [7] [320/400] eta: 0:00:29 lr: 0.000275 loss: 1.0086 (1.0388) grad: 0.0515 (0.0532) time: 0.3487 data: 0.0035 max mem: 3956 +train: [7] [340/400] eta: 0:00:21 lr: 0.000274 loss: 0.9791 (1.0350) grad: 0.0538 (0.0533) time: 0.3363 data: 0.0036 max mem: 3956 +train: [7] [360/400] eta: 0:00:14 lr: 0.000273 loss: 1.0008 (1.0352) grad: 0.0536 (0.0532) time: 0.3380 data: 0.0036 max mem: 3956 +train: [7] [380/400] eta: 0:00:07 lr: 0.000272 loss: 1.0389 (1.0340) grad: 0.0531 (0.0533) time: 0.3422 data: 0.0037 max mem: 3956 +train: [7] [399/400] eta: 0:00:00 lr: 0.000271 loss: 0.9997 (1.0321) grad: 0.0520 (0.0533) time: 0.3293 data: 0.0042 max mem: 3956 +train: [7] Total time: 0:02:23 (0.3585 s / it) +train: [7] Summary: lr: 0.000271 loss: 0.9997 (1.0321) grad: 0.0520 (0.0533) +eval (validation): [7] [ 0/63] eta: 0:06:48 time: 6.4913 data: 6.2382 max mem: 3956 +eval (validation): [7] [20/63] eta: 0:00:25 time: 0.3014 data: 0.0029 max mem: 3956 +eval (validation): [7] [40/63] eta: 0:00:10 time: 0.3126 data: 0.0030 max mem: 3956 +eval (validation): [7] [60/63] eta: 0:00:01 time: 0.2997 data: 0.0033 max mem: 3956 +eval (validation): [7] [62/63] eta: 0:00:00 time: 0.2989 data: 0.0031 max mem: 3956 +eval (validation): [7] Total time: 0:00:25 (0.4088 s / it) +cv: [7] best hparam: (43, 1.0) (047) ('047_lr4.3e+01_wd1.0e+00') loss: 0.118 acc: 0.968 f1: 0.963 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__linear/checkpoint-last.pth +train: [8] [ 0/400] eta: 0:21:16 lr: nan time: 3.1914 data: 2.9813 max mem: 3956 +train: [8] [ 20/400] eta: 0:03:14 lr: 0.000270 loss: 0.9779 (0.9844) grad: 0.0488 (0.0514) time: 0.3765 data: 0.0039 max mem: 3956 +train: [8] [ 40/400] eta: 0:02:32 lr: 0.000270 loss: 0.9861 (0.9936) grad: 0.0506 (0.0509) time: 0.3303 data: 0.0035 max mem: 3956 +train: [8] [ 60/400] eta: 0:02:13 lr: 0.000269 loss: 0.9942 (0.9971) grad: 0.0512 (0.0514) time: 0.3302 data: 0.0042 max mem: 3956 +train: [8] [ 80/400] eta: 0:02:00 lr: 0.000268 loss: 1.0144 (1.0022) grad: 0.0500 (0.0511) time: 0.3309 data: 0.0043 max mem: 3956 +train: [8] [100/400] eta: 0:01:50 lr: 0.000267 loss: 1.0038 (0.9991) grad: 0.0491 (0.0511) time: 0.3276 data: 0.0043 max mem: 3956 +train: [8] [120/400] eta: 0:01:41 lr: 0.000266 loss: 0.9876 (0.9975) grad: 0.0523 (0.0513) time: 0.3290 data: 0.0040 max mem: 3956 +train: [8] [140/400] eta: 0:01:33 lr: 0.000265 loss: 0.9806 (0.9956) grad: 0.0504 (0.0512) time: 0.3491 data: 0.0040 max mem: 3956 +train: [8] [160/400] eta: 0:01:25 lr: 0.000264 loss: 0.9605 (0.9905) grad: 0.0492 (0.0512) time: 0.3441 data: 0.0037 max mem: 3956 +train: [8] [180/400] eta: 0:01:18 lr: 0.000263 loss: 0.9505 (0.9873) grad: 0.0514 (0.0515) time: 0.3324 data: 0.0039 max mem: 3956 +train: [8] [200/400] eta: 0:01:10 lr: 0.000262 loss: 0.9725 (0.9862) grad: 0.0504 (0.0515) time: 0.3172 data: 0.0038 max mem: 3956 +train: [8] [220/400] eta: 0:01:02 lr: 0.000260 loss: 0.9792 (0.9863) grad: 0.0503 (0.0515) time: 0.3142 data: 0.0040 max mem: 3956 +train: [8] [240/400] eta: 0:00:55 lr: 0.000259 loss: 0.9638 (0.9831) grad: 0.0533 (0.0517) time: 0.3431 data: 0.0036 max mem: 3956 +train: [8] [260/400] eta: 0:00:48 lr: 0.000258 loss: 0.9638 (0.9823) grad: 0.0516 (0.0516) time: 0.3515 data: 0.0041 max mem: 3956 +train: [8] [280/400] eta: 0:00:41 lr: 0.000257 loss: 0.9532 (0.9801) grad: 0.0499 (0.0516) time: 0.3396 data: 0.0041 max mem: 3956 +train: [8] [300/400] eta: 0:00:35 lr: 0.000256 loss: 0.9529 (0.9793) grad: 0.0499 (0.0515) time: 0.4939 data: 0.1688 max mem: 3956 +train: [8] [320/400] eta: 0:00:28 lr: 0.000255 loss: 0.9577 (0.9774) grad: 0.0478 (0.0513) time: 0.3580 data: 0.0040 max mem: 3956 +train: [8] [340/400] eta: 0:00:21 lr: 0.000254 loss: 0.9577 (0.9766) grad: 0.0485 (0.0512) time: 0.3915 data: 0.0041 max mem: 3956 +train: [8] [360/400] eta: 0:00:14 lr: 0.000253 loss: 0.9417 (0.9746) grad: 0.0498 (0.0512) time: 0.3287 data: 0.0039 max mem: 3956 +train: [8] [380/400] eta: 0:00:07 lr: 0.000252 loss: 0.9417 (0.9742) grad: 0.0496 (0.0511) time: 0.3428 data: 0.0041 max mem: 3956 +train: [8] [399/400] eta: 0:00:00 lr: 0.000250 loss: 0.9564 (0.9735) grad: 0.0484 (0.0511) time: 0.3346 data: 0.0035 max mem: 3956 +train: [8] Total time: 0:02:22 (0.3558 s / it) +train: [8] Summary: lr: 0.000250 loss: 0.9564 (0.9735) grad: 0.0484 (0.0511) +eval (validation): [8] [ 0/63] eta: 0:03:17 time: 3.1306 data: 2.9324 max mem: 3956 +eval (validation): [8] [20/63] eta: 0:00:19 time: 0.3133 data: 0.0136 max mem: 3956 +eval (validation): [8] [40/63] eta: 0:00:09 time: 0.3462 data: 0.0032 max mem: 3956 +eval (validation): [8] [60/63] eta: 0:00:01 time: 0.3156 data: 0.0031 max mem: 3956 +eval (validation): [8] [62/63] eta: 0:00:00 time: 0.3104 data: 0.0024 max mem: 3956 +eval (validation): [8] Total time: 0:00:23 (0.3730 s / it) +cv: [8] best hparam: (36, 1.0) (046) ('046_lr3.6e+01_wd1.0e+00') loss: 0.117 acc: 0.968 f1: 0.963 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__linear/checkpoint-last.pth +train: [9] [ 0/400] eta: 0:21:43 lr: nan time: 3.2597 data: 3.0418 max mem: 3956 +train: [9] [ 20/400] eta: 0:03:05 lr: 0.000249 loss: 0.9247 (0.9298) grad: 0.0521 (0.0513) time: 0.3493 data: 0.0041 max mem: 3956 +train: [9] [ 40/400] eta: 0:02:30 lr: 0.000248 loss: 0.9247 (0.9353) grad: 0.0514 (0.0510) time: 0.3426 data: 0.0035 max mem: 3956 +train: [9] [ 60/400] eta: 0:02:13 lr: 0.000247 loss: 0.9209 (0.9333) grad: 0.0488 (0.0504) time: 0.3413 data: 0.0041 max mem: 3956 +train: [9] [ 80/400] eta: 0:02:01 lr: 0.000246 loss: 0.9273 (0.9322) grad: 0.0487 (0.0507) time: 0.3392 data: 0.0039 max mem: 3956 +train: [9] [100/400] eta: 0:01:51 lr: 0.000244 loss: 0.9224 (0.9266) grad: 0.0513 (0.0508) time: 0.3376 data: 0.0034 max mem: 3956 +train: [9] [120/400] eta: 0:01:41 lr: 0.000243 loss: 0.9224 (0.9281) grad: 0.0486 (0.0504) time: 0.3294 data: 0.0037 max mem: 3956 +train: [9] [140/400] eta: 0:01:34 lr: 0.000242 loss: 0.9391 (0.9298) grad: 0.0473 (0.0502) time: 0.3535 data: 0.0036 max mem: 3956 +train: [9] [160/400] eta: 0:01:26 lr: 0.000241 loss: 0.9245 (0.9274) grad: 0.0481 (0.0500) time: 0.3545 data: 0.0041 max mem: 3956 +train: [9] [180/400] eta: 0:01:19 lr: 0.000240 loss: 0.9095 (0.9287) grad: 0.0476 (0.0498) time: 0.3440 data: 0.0042 max mem: 3956 +train: [9] [200/400] eta: 0:01:11 lr: 0.000238 loss: 0.9266 (0.9288) grad: 0.0470 (0.0497) time: 0.3525 data: 0.0038 max mem: 3956 +train: [9] [220/400] eta: 0:01:04 lr: 0.000237 loss: 0.9189 (0.9288) grad: 0.0474 (0.0495) time: 0.3486 data: 0.0036 max mem: 3956 +train: [9] [240/400] eta: 0:00:57 lr: 0.000236 loss: 0.9189 (0.9281) grad: 0.0485 (0.0496) time: 0.3529 data: 0.0036 max mem: 3956 +train: [9] [260/400] eta: 0:00:49 lr: 0.000234 loss: 0.9143 (0.9259) grad: 0.0493 (0.0496) time: 0.3385 data: 0.0039 max mem: 3956 +train: [9] [280/400] eta: 0:00:42 lr: 0.000233 loss: 0.9142 (0.9262) grad: 0.0490 (0.0495) time: 0.3435 data: 0.0040 max mem: 3956 +train: [9] [300/400] eta: 0:00:36 lr: 0.000232 loss: 0.9142 (0.9250) grad: 0.0481 (0.0493) time: 0.4710 data: 0.1606 max mem: 3956 +train: [9] [320/400] eta: 0:00:28 lr: 0.000230 loss: 0.8975 (0.9233) grad: 0.0471 (0.0494) time: 0.3546 data: 0.0041 max mem: 3956 +train: [9] [340/400] eta: 0:00:21 lr: 0.000229 loss: 0.9041 (0.9221) grad: 0.0472 (0.0493) time: 0.3506 data: 0.0034 max mem: 3956 +train: [9] [360/400] eta: 0:00:14 lr: 0.000228 loss: 0.9072 (0.9227) grad: 0.0473 (0.0493) time: 0.3758 data: 0.0041 max mem: 3956 +train: [9] [380/400] eta: 0:00:07 lr: 0.000226 loss: 0.9180 (0.9218) grad: 0.0477 (0.0493) time: 0.3616 data: 0.0043 max mem: 3956 +train: [9] [399/400] eta: 0:00:00 lr: 0.000225 loss: 0.9161 (0.9216) grad: 0.0476 (0.0492) time: 0.3306 data: 0.0040 max mem: 3956 +train: [9] Total time: 0:02:24 (0.3613 s / it) +train: [9] Summary: lr: 0.000225 loss: 0.9161 (0.9216) grad: 0.0476 (0.0492) +eval (validation): [9] [ 0/63] eta: 0:03:31 time: 3.3587 data: 3.0815 max mem: 3956 +eval (validation): [9] [20/63] eta: 0:00:20 time: 0.3430 data: 0.0043 max mem: 3956 +eval (validation): [9] [40/63] eta: 0:00:09 time: 0.3379 data: 0.0031 max mem: 3956 +eval (validation): [9] [60/63] eta: 0:00:01 time: 0.3207 data: 0.0038 max mem: 3956 +eval (validation): [9] [62/63] eta: 0:00:00 time: 0.3182 data: 0.0039 max mem: 3956 +eval (validation): [9] Total time: 0:00:24 (0.3859 s / it) +cv: [9] best hparam: (50, 1.0) (048) ('048_lr5.0e+01_wd1.0e+00') loss: 0.118 acc: 0.965 f1: 0.960 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__linear/checkpoint-last.pth +train: [10] [ 0/400] eta: 0:20:24 lr: nan time: 3.0616 data: 2.8085 max mem: 3956 +train: [10] [ 20/400] eta: 0:03:06 lr: 0.000224 loss: 0.9126 (0.9278) grad: 0.0468 (0.0470) time: 0.3610 data: 0.0038 max mem: 3956 +train: [10] [ 40/400] eta: 0:02:32 lr: 0.000222 loss: 0.8986 (0.9017) grad: 0.0479 (0.0492) time: 0.3530 data: 0.0038 max mem: 3956 +train: [10] [ 60/400] eta: 0:02:16 lr: 0.000221 loss: 0.8661 (0.8986) grad: 0.0502 (0.0492) time: 0.3545 data: 0.0041 max mem: 3956 +train: [10] [ 80/400] eta: 0:02:04 lr: 0.000220 loss: 0.8924 (0.8966) grad: 0.0467 (0.0487) time: 0.3504 data: 0.0042 max mem: 3956 +train: [10] [100/400] eta: 0:01:53 lr: 0.000218 loss: 0.8992 (0.8993) grad: 0.0463 (0.0483) time: 0.3342 data: 0.0038 max mem: 3956 +train: [10] [120/400] eta: 0:01:43 lr: 0.000217 loss: 0.9080 (0.8963) grad: 0.0475 (0.0482) time: 0.3385 data: 0.0039 max mem: 3956 +train: [10] [140/400] eta: 0:01:36 lr: 0.000215 loss: 0.8786 (0.8950) grad: 0.0459 (0.0479) time: 0.3671 data: 0.0041 max mem: 3956 +train: [10] [160/400] eta: 0:01:28 lr: 0.000214 loss: 0.8650 (0.8920) grad: 0.0472 (0.0480) time: 0.3546 data: 0.0040 max mem: 3956 +train: [10] [180/400] eta: 0:01:20 lr: 0.000213 loss: 0.8895 (0.8967) grad: 0.0472 (0.0477) time: 0.3489 data: 0.0042 max mem: 3956 +train: [10] [200/400] eta: 0:01:12 lr: 0.000211 loss: 0.8982 (0.8966) grad: 0.0461 (0.0477) time: 0.3510 data: 0.0041 max mem: 3956 +train: [10] [220/400] eta: 0:01:05 lr: 0.000210 loss: 0.8982 (0.8962) grad: 0.0476 (0.0478) time: 0.3390 data: 0.0041 max mem: 3956 +train: [10] [240/400] eta: 0:00:57 lr: 0.000208 loss: 0.8864 (0.8930) grad: 0.0486 (0.0480) time: 0.3586 data: 0.0043 max mem: 3956 +train: [10] [260/400] eta: 0:00:50 lr: 0.000207 loss: 0.8538 (0.8911) grad: 0.0481 (0.0480) time: 0.3455 data: 0.0043 max mem: 3956 +train: [10] [280/400] eta: 0:00:43 lr: 0.000205 loss: 0.8635 (0.8907) grad: 0.0494 (0.0482) time: 0.3612 data: 0.0045 max mem: 3956 +train: [10] [300/400] eta: 0:00:37 lr: 0.000204 loss: 0.8817 (0.8903) grad: 0.0494 (0.0481) time: 0.5029 data: 0.1813 max mem: 3956 +train: [10] [320/400] eta: 0:00:29 lr: 0.000202 loss: 0.8776 (0.8899) grad: 0.0477 (0.0480) time: 0.3623 data: 0.0046 max mem: 3956 +train: [10] [340/400] eta: 0:00:22 lr: 0.000201 loss: 0.8621 (0.8875) grad: 0.0470 (0.0479) time: 0.3933 data: 0.0032 max mem: 3956 +train: [10] [360/400] eta: 0:00:14 lr: 0.000199 loss: 0.8537 (0.8861) grad: 0.0470 (0.0479) time: 0.3487 data: 0.0040 max mem: 3956 +train: [10] [380/400] eta: 0:00:07 lr: 0.000198 loss: 0.8520 (0.8842) grad: 0.0480 (0.0479) time: 0.3532 data: 0.0042 max mem: 3956 +train: [10] [399/400] eta: 0:00:00 lr: 0.000196 loss: 0.8510 (0.8819) grad: 0.0499 (0.0481) time: 0.3520 data: 0.0043 max mem: 3956 +train: [10] Total time: 0:02:27 (0.3688 s / it) +train: [10] Summary: lr: 0.000196 loss: 0.8510 (0.8819) grad: 0.0499 (0.0481) +eval (validation): [10] [ 0/63] eta: 0:03:31 time: 3.3511 data: 3.0817 max mem: 3956 +eval (validation): [10] [20/63] eta: 0:00:21 time: 0.3607 data: 0.0036 max mem: 3956 +eval (validation): [10] [40/63] eta: 0:00:09 time: 0.3355 data: 0.0033 max mem: 3956 +eval (validation): [10] [60/63] eta: 0:00:01 time: 0.3362 data: 0.0037 max mem: 3956 +eval (validation): [10] [62/63] eta: 0:00:00 time: 0.3365 data: 0.0036 max mem: 3956 +eval (validation): [10] Total time: 0:00:24 (0.3961 s / it) +cv: [10] best hparam: (26, 1.0) (044) ('044_lr2.6e+01_wd1.0e+00') loss: 0.117 acc: 0.968 f1: 0.961 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__linear/checkpoint-last.pth +train: [11] [ 0/400] eta: 0:21:38 lr: nan time: 3.2454 data: 2.9815 max mem: 3956 +train: [11] [ 20/400] eta: 0:03:11 lr: 0.000195 loss: 0.8617 (0.8563) grad: 0.0455 (0.0459) time: 0.3661 data: 0.0186 max mem: 3956 +train: [11] [ 40/400] eta: 0:02:34 lr: 0.000193 loss: 0.8610 (0.8483) grad: 0.0463 (0.0477) time: 0.3505 data: 0.0033 max mem: 3956 +train: [11] [ 60/400] eta: 0:02:16 lr: 0.000192 loss: 0.8570 (0.8543) grad: 0.0453 (0.0472) time: 0.3419 data: 0.0040 max mem: 3956 +train: [11] [ 80/400] eta: 0:02:03 lr: 0.000190 loss: 0.8563 (0.8522) grad: 0.0463 (0.0474) time: 0.3471 data: 0.0039 max mem: 3956 +train: [11] [100/400] eta: 0:01:53 lr: 0.000189 loss: 0.8399 (0.8528) grad: 0.0491 (0.0476) time: 0.3473 data: 0.0043 max mem: 3956 +train: [11] [120/400] eta: 0:01:44 lr: 0.000187 loss: 0.8503 (0.8546) grad: 0.0491 (0.0478) time: 0.3366 data: 0.0038 max mem: 3956 +train: [11] [140/400] eta: 0:01:35 lr: 0.000186 loss: 0.8552 (0.8576) grad: 0.0465 (0.0474) time: 0.3477 data: 0.0038 max mem: 3956 +train: [11] [160/400] eta: 0:01:27 lr: 0.000184 loss: 0.8543 (0.8568) grad: 0.0447 (0.0473) time: 0.3325 data: 0.0041 max mem: 3956 +train: [11] [180/400] eta: 0:01:19 lr: 0.000183 loss: 0.8412 (0.8560) grad: 0.0464 (0.0474) time: 0.3439 data: 0.0043 max mem: 3956 +train: [11] [200/400] eta: 0:01:12 lr: 0.000181 loss: 0.8526 (0.8572) grad: 0.0463 (0.0473) time: 0.3423 data: 0.0041 max mem: 3956 +train: [11] [220/400] eta: 0:01:04 lr: 0.000180 loss: 0.8608 (0.8580) grad: 0.0449 (0.0472) time: 0.3687 data: 0.0041 max mem: 3956 +train: [11] [240/400] eta: 0:00:57 lr: 0.000178 loss: 0.8658 (0.8599) grad: 0.0460 (0.0472) time: 0.3550 data: 0.0042 max mem: 3956 +train: [11] [260/400] eta: 0:00:50 lr: 0.000177 loss: 0.8678 (0.8601) grad: 0.0456 (0.0471) time: 0.3361 data: 0.0041 max mem: 3956 +train: [11] [280/400] eta: 0:00:43 lr: 0.000175 loss: 0.8522 (0.8582) grad: 0.0441 (0.0469) time: 0.3625 data: 0.0041 max mem: 3956 +train: [11] [300/400] eta: 0:00:36 lr: 0.000174 loss: 0.8328 (0.8574) grad: 0.0433 (0.0468) time: 0.4705 data: 0.1678 max mem: 3956 +train: [11] [320/400] eta: 0:00:29 lr: 0.000172 loss: 0.8330 (0.8566) grad: 0.0450 (0.0467) time: 0.3430 data: 0.0060 max mem: 3956 +train: [11] [340/400] eta: 0:00:21 lr: 0.000170 loss: 0.8616 (0.8573) grad: 0.0460 (0.0467) time: 0.3422 data: 0.0031 max mem: 3956 +train: [11] [360/400] eta: 0:00:14 lr: 0.000169 loss: 0.8713 (0.8573) grad: 0.0473 (0.0468) time: 0.3297 data: 0.0042 max mem: 3956 +train: [11] [380/400] eta: 0:00:07 lr: 0.000167 loss: 0.8467 (0.8562) grad: 0.0460 (0.0468) time: 0.3307 data: 0.0040 max mem: 3956 +train: [11] [399/400] eta: 0:00:00 lr: 0.000166 loss: 0.8467 (0.8554) grad: 0.0461 (0.0467) time: 0.3542 data: 0.0042 max mem: 3956 +train: [11] Total time: 0:02:24 (0.3602 s / it) +train: [11] Summary: lr: 0.000166 loss: 0.8467 (0.8554) grad: 0.0461 (0.0467) +eval (validation): [11] [ 0/63] eta: 0:03:26 time: 3.2801 data: 3.0205 max mem: 3956 +eval (validation): [11] [20/63] eta: 0:00:20 time: 0.3258 data: 0.0194 max mem: 3956 +eval (validation): [11] [40/63] eta: 0:00:09 time: 0.3324 data: 0.0039 max mem: 3956 +eval (validation): [11] [60/63] eta: 0:00:01 time: 0.2884 data: 0.0026 max mem: 3956 +eval (validation): [11] [62/63] eta: 0:00:00 time: 0.2855 data: 0.0027 max mem: 3956 +eval (validation): [11] Total time: 0:00:23 (0.3659 s / it) +cv: [11] best hparam: (26, 1.0) (044) ('044_lr2.6e+01_wd1.0e+00') loss: 0.117 acc: 0.968 f1: 0.962 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__linear/checkpoint-last.pth +train: [12] [ 0/400] eta: 0:19:53 lr: nan time: 2.9842 data: 2.7634 max mem: 3956 +train: [12] [ 20/400] eta: 0:02:53 lr: 0.000164 loss: 0.8304 (0.8296) grad: 0.0491 (0.0483) time: 0.3294 data: 0.0031 max mem: 3956 +train: [12] [ 40/400] eta: 0:02:21 lr: 0.000163 loss: 0.8372 (0.8381) grad: 0.0474 (0.0467) time: 0.3262 data: 0.0038 max mem: 3956 +train: [12] [ 60/400] eta: 0:02:06 lr: 0.000161 loss: 0.8234 (0.8337) grad: 0.0459 (0.0471) time: 0.3260 data: 0.0042 max mem: 3956 +train: [12] [ 80/400] eta: 0:01:54 lr: 0.000160 loss: 0.8212 (0.8337) grad: 0.0457 (0.0466) time: 0.3215 data: 0.0041 max mem: 3956 +train: [12] [100/400] eta: 0:01:45 lr: 0.000158 loss: 0.8140 (0.8294) grad: 0.0457 (0.0468) time: 0.3302 data: 0.0042 max mem: 3956 +train: [12] [120/400] eta: 0:01:37 lr: 0.000156 loss: 0.8102 (0.8289) grad: 0.0459 (0.0468) time: 0.3232 data: 0.0039 max mem: 3956 +train: [12] [140/400] eta: 0:01:29 lr: 0.000155 loss: 0.8148 (0.8277) grad: 0.0454 (0.0470) time: 0.3278 data: 0.0039 max mem: 3956 +train: [12] [160/400] eta: 0:01:22 lr: 0.000153 loss: 0.8120 (0.8258) grad: 0.0453 (0.0468) time: 0.3265 data: 0.0043 max mem: 3956 +train: [12] [180/400] eta: 0:01:14 lr: 0.000152 loss: 0.8117 (0.8262) grad: 0.0446 (0.0466) time: 0.3196 data: 0.0036 max mem: 3956 +train: [12] [200/400] eta: 0:01:07 lr: 0.000150 loss: 0.8429 (0.8288) grad: 0.0446 (0.0465) time: 0.3149 data: 0.0038 max mem: 3956 +train: [12] [220/400] eta: 0:01:00 lr: 0.000149 loss: 0.8544 (0.8308) grad: 0.0453 (0.0464) time: 0.3189 data: 0.0042 max mem: 3956 +train: [12] [240/400] eta: 0:00:53 lr: 0.000147 loss: 0.8405 (0.8316) grad: 0.0443 (0.0462) time: 0.3219 data: 0.0039 max mem: 3956 +train: [12] [260/400] eta: 0:00:46 lr: 0.000145 loss: 0.8229 (0.8314) grad: 0.0453 (0.0463) time: 0.3241 data: 0.0036 max mem: 3956 +train: [12] [280/400] eta: 0:00:40 lr: 0.000144 loss: 0.8138 (0.8296) grad: 0.0470 (0.0462) time: 0.3566 data: 0.0043 max mem: 3956 +train: [12] [300/400] eta: 0:00:34 lr: 0.000142 loss: 0.8118 (0.8286) grad: 0.0464 (0.0462) time: 0.4690 data: 0.1631 max mem: 3956 +train: [12] [320/400] eta: 0:00:27 lr: 0.000141 loss: 0.8166 (0.8288) grad: 0.0454 (0.0462) time: 0.3235 data: 0.0029 max mem: 3956 +train: [12] [340/400] eta: 0:00:20 lr: 0.000139 loss: 0.8186 (0.8280) grad: 0.0437 (0.0461) time: 0.3620 data: 0.0031 max mem: 3956 +train: [12] [360/400] eta: 0:00:13 lr: 0.000138 loss: 0.8214 (0.8288) grad: 0.0435 (0.0461) time: 0.3653 data: 0.0044 max mem: 3956 +train: [12] [380/400] eta: 0:00:06 lr: 0.000136 loss: 0.8179 (0.8269) grad: 0.0471 (0.0462) time: 0.3497 data: 0.0041 max mem: 3956 +train: [12] [399/400] eta: 0:00:00 lr: 0.000134 loss: 0.8166 (0.8270) grad: 0.0464 (0.0461) time: 0.3506 data: 0.0045 max mem: 3956 +train: [12] Total time: 0:02:18 (0.3463 s / it) +train: [12] Summary: lr: 0.000134 loss: 0.8166 (0.8270) grad: 0.0464 (0.0461) +eval (validation): [12] [ 0/63] eta: 0:03:25 time: 3.2651 data: 3.0508 max mem: 3956 +eval (validation): [12] [20/63] eta: 0:00:21 time: 0.3596 data: 0.0041 max mem: 3956 +eval (validation): [12] [40/63] eta: 0:00:09 time: 0.3452 data: 0.0032 max mem: 3956 +eval (validation): [12] [60/63] eta: 0:00:01 time: 0.3093 data: 0.0033 max mem: 3956 +eval (validation): [12] [62/63] eta: 0:00:00 time: 0.3066 data: 0.0032 max mem: 3956 +eval (validation): [12] Total time: 0:00:24 (0.3888 s / it) +cv: [12] best hparam: (26, 1.0) (044) ('044_lr2.6e+01_wd1.0e+00') loss: 0.115 acc: 0.969 f1: 0.963 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__linear/checkpoint-best.pth +train: [13] [ 0/400] eta: 0:22:12 lr: nan time: 3.3317 data: 3.0861 max mem: 3956 +train: [13] [ 20/400] eta: 0:03:06 lr: 0.000133 loss: 0.7946 (0.8238) grad: 0.0429 (0.0440) time: 0.3500 data: 0.0039 max mem: 3956 +train: [13] [ 40/400] eta: 0:02:32 lr: 0.000131 loss: 0.7974 (0.8095) grad: 0.0439 (0.0439) time: 0.3535 data: 0.0032 max mem: 3956 +train: [13] [ 60/400] eta: 0:02:14 lr: 0.000130 loss: 0.7974 (0.8123) grad: 0.0440 (0.0438) time: 0.3350 data: 0.0044 max mem: 3956 +train: [13] [ 80/400] eta: 0:02:02 lr: 0.000128 loss: 0.8081 (0.8107) grad: 0.0440 (0.0443) time: 0.3452 data: 0.0044 max mem: 3956 +train: [13] [100/400] eta: 0:01:52 lr: 0.000127 loss: 0.8108 (0.8132) grad: 0.0443 (0.0442) time: 0.3496 data: 0.0044 max mem: 3956 +train: [13] [120/400] eta: 0:01:42 lr: 0.000125 loss: 0.8108 (0.8131) grad: 0.0440 (0.0441) time: 0.3191 data: 0.0039 max mem: 3956 +train: [13] [140/400] eta: 0:01:34 lr: 0.000124 loss: 0.7970 (0.8109) grad: 0.0441 (0.0444) time: 0.3350 data: 0.0041 max mem: 3956 +train: [13] [160/400] eta: 0:01:26 lr: 0.000122 loss: 0.7961 (0.8117) grad: 0.0458 (0.0444) time: 0.3338 data: 0.0042 max mem: 3956 +train: [13] [180/400] eta: 0:01:18 lr: 0.000120 loss: 0.7922 (0.8082) grad: 0.0458 (0.0447) time: 0.3486 data: 0.0045 max mem: 3956 +train: [13] [200/400] eta: 0:01:11 lr: 0.000119 loss: 0.7919 (0.8094) grad: 0.0456 (0.0448) time: 0.3359 data: 0.0042 max mem: 3956 +train: [13] [220/400] eta: 0:01:03 lr: 0.000117 loss: 0.7959 (0.8091) grad: 0.0453 (0.0448) time: 0.3332 data: 0.0043 max mem: 3956 +train: [13] [240/400] eta: 0:00:56 lr: 0.000116 loss: 0.8024 (0.8094) grad: 0.0453 (0.0449) time: 0.3404 data: 0.0040 max mem: 3956 +train: [13] [260/400] eta: 0:00:49 lr: 0.000114 loss: 0.8079 (0.8087) grad: 0.0439 (0.0449) time: 0.3419 data: 0.0040 max mem: 3956 +train: [13] [280/400] eta: 0:00:42 lr: 0.000113 loss: 0.7805 (0.8076) grad: 0.0445 (0.0449) time: 0.3671 data: 0.0043 max mem: 3956 +train: [13] [300/400] eta: 0:00:36 lr: 0.000111 loss: 0.7830 (0.8072) grad: 0.0445 (0.0448) time: 0.5141 data: 0.1702 max mem: 3956 +train: [13] [320/400] eta: 0:00:28 lr: 0.000110 loss: 0.8279 (0.8091) grad: 0.0441 (0.0448) time: 0.3379 data: 0.0036 max mem: 3956 +train: [13] [340/400] eta: 0:00:21 lr: 0.000108 loss: 0.8138 (0.8076) grad: 0.0438 (0.0447) time: 0.3339 data: 0.0037 max mem: 3956 +train: [13] [360/400] eta: 0:00:14 lr: 0.000107 loss: 0.7944 (0.8078) grad: 0.0434 (0.0447) time: 0.3420 data: 0.0040 max mem: 3956 +train: [13] [380/400] eta: 0:00:07 lr: 0.000105 loss: 0.8071 (0.8081) grad: 0.0434 (0.0447) time: 0.3541 data: 0.0042 max mem: 3956 +train: [13] [399/400] eta: 0:00:00 lr: 0.000104 loss: 0.7961 (0.8069) grad: 0.0434 (0.0447) time: 0.3383 data: 0.0044 max mem: 3956 +train: [13] Total time: 0:02:23 (0.3585 s / it) +train: [13] Summary: lr: 0.000104 loss: 0.7961 (0.8069) grad: 0.0434 (0.0447) +eval (validation): [13] [ 0/63] eta: 0:03:20 time: 3.1828 data: 2.9779 max mem: 3956 +eval (validation): [13] [20/63] eta: 0:00:21 time: 0.3676 data: 0.0237 max mem: 3956 +eval (validation): [13] [40/63] eta: 0:00:09 time: 0.3400 data: 0.0034 max mem: 3956 +eval (validation): [13] [60/63] eta: 0:00:01 time: 0.3140 data: 0.0037 max mem: 3956 +eval (validation): [13] [62/63] eta: 0:00:00 time: 0.3120 data: 0.0037 max mem: 3956 +eval (validation): [13] Total time: 0:00:24 (0.3897 s / it) +cv: [13] best hparam: (36, 1.0) (046) ('046_lr3.6e+01_wd1.0e+00') loss: 0.113 acc: 0.967 f1: 0.962 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__linear/checkpoint-last.pth +train: [14] [ 0/400] eta: 0:21:56 lr: nan time: 3.2921 data: 3.0138 max mem: 3956 +train: [14] [ 20/400] eta: 0:03:09 lr: 0.000102 loss: 0.7662 (0.7854) grad: 0.0469 (0.0479) time: 0.3578 data: 0.0050 max mem: 3956 +train: [14] [ 40/400] eta: 0:02:30 lr: 0.000101 loss: 0.7674 (0.7843) grad: 0.0448 (0.0452) time: 0.3339 data: 0.0042 max mem: 3956 +train: [14] [ 60/400] eta: 0:02:12 lr: 0.000099 loss: 0.7938 (0.7894) grad: 0.0439 (0.0450) time: 0.3363 data: 0.0026 max mem: 3956 +train: [14] [ 80/400] eta: 0:02:00 lr: 0.000098 loss: 0.8004 (0.7949) grad: 0.0449 (0.0450) time: 0.3348 data: 0.0035 max mem: 3956 +train: [14] [100/400] eta: 0:01:50 lr: 0.000096 loss: 0.8121 (0.7957) grad: 0.0440 (0.0448) time: 0.3372 data: 0.0026 max mem: 3956 +train: [14] [120/400] eta: 0:01:41 lr: 0.000095 loss: 0.7980 (0.7966) grad: 0.0440 (0.0449) time: 0.3313 data: 0.0036 max mem: 3956 +train: [14] [140/400] eta: 0:01:33 lr: 0.000093 loss: 0.8036 (0.7982) grad: 0.0449 (0.0449) time: 0.3452 data: 0.0025 max mem: 3956 +train: [14] [160/400] eta: 0:01:25 lr: 0.000092 loss: 0.7934 (0.7970) grad: 0.0453 (0.0450) time: 0.3243 data: 0.0038 max mem: 3956 +train: [14] [180/400] eta: 0:01:18 lr: 0.000090 loss: 0.7901 (0.7978) grad: 0.0446 (0.0449) time: 0.3623 data: 0.0038 max mem: 3956 +train: [14] [200/400] eta: 0:01:12 lr: 0.000089 loss: 0.8125 (0.7999) grad: 0.0421 (0.0447) time: 0.4137 data: 0.0043 max mem: 3956 +train: [14] [220/400] eta: 0:01:05 lr: 0.000088 loss: 0.7953 (0.7985) grad: 0.0423 (0.0447) time: 0.3572 data: 0.0041 max mem: 3956 +train: [14] [240/400] eta: 0:00:57 lr: 0.000086 loss: 0.7813 (0.7976) grad: 0.0449 (0.0448) time: 0.3396 data: 0.0042 max mem: 3956 +train: [14] [260/400] eta: 0:00:50 lr: 0.000085 loss: 0.7813 (0.7957) grad: 0.0446 (0.0447) time: 0.3509 data: 0.0043 max mem: 3956 +train: [14] [280/400] eta: 0:00:43 lr: 0.000083 loss: 0.7824 (0.7955) grad: 0.0446 (0.0447) time: 0.3472 data: 0.0042 max mem: 3956 +train: [14] [300/400] eta: 0:00:36 lr: 0.000082 loss: 0.7845 (0.7953) grad: 0.0456 (0.0448) time: 0.4841 data: 0.1761 max mem: 3956 +train: [14] [320/400] eta: 0:00:29 lr: 0.000081 loss: 0.7845 (0.7953) grad: 0.0447 (0.0448) time: 0.3527 data: 0.0287 max mem: 3956 +train: [14] [340/400] eta: 0:00:21 lr: 0.000079 loss: 0.7782 (0.7938) grad: 0.0459 (0.0449) time: 0.3314 data: 0.0027 max mem: 3956 +train: [14] [360/400] eta: 0:00:14 lr: 0.000078 loss: 0.7635 (0.7926) grad: 0.0462 (0.0450) time: 0.3565 data: 0.0043 max mem: 3956 +train: [14] [380/400] eta: 0:00:07 lr: 0.000076 loss: 0.7800 (0.7929) grad: 0.0455 (0.0450) time: 0.3580 data: 0.0043 max mem: 3956 +train: [14] [399/400] eta: 0:00:00 lr: 0.000075 loss: 0.7965 (0.7934) grad: 0.0441 (0.0450) time: 0.3472 data: 0.0044 max mem: 3956 +train: [14] Total time: 0:02:25 (0.3629 s / it) +train: [14] Summary: lr: 0.000075 loss: 0.7965 (0.7934) grad: 0.0441 (0.0450) +eval (validation): [14] [ 0/63] eta: 0:03:26 time: 3.2773 data: 3.0644 max mem: 3956 +eval (validation): [14] [20/63] eta: 0:00:21 time: 0.3676 data: 0.0041 max mem: 3956 +eval (validation): [14] [40/63] eta: 0:00:09 time: 0.3462 data: 0.0030 max mem: 3956 +eval (validation): [14] [60/63] eta: 0:00:01 time: 0.3309 data: 0.0036 max mem: 3956 +eval (validation): [14] [62/63] eta: 0:00:00 time: 0.3276 data: 0.0036 max mem: 3956 +eval (validation): [14] Total time: 0:00:25 (0.3987 s / it) +cv: [14] best hparam: (26, 1.0) (044) ('044_lr2.6e+01_wd1.0e+00') loss: 0.113 acc: 0.969 f1: 0.963 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__linear/checkpoint-last.pth +train: [15] [ 0/400] eta: 0:22:06 lr: nan time: 3.3175 data: 3.0274 max mem: 3956 +train: [15] [ 20/400] eta: 0:03:15 lr: 0.000074 loss: 0.7923 (0.7923) grad: 0.0435 (0.0444) time: 0.3752 data: 0.0046 max mem: 3956 +train: [15] [ 40/400] eta: 0:02:34 lr: 0.000072 loss: 0.7747 (0.7812) grad: 0.0449 (0.0451) time: 0.3387 data: 0.0038 max mem: 3956 +train: [15] [ 60/400] eta: 0:02:18 lr: 0.000071 loss: 0.7713 (0.7835) grad: 0.0458 (0.0449) time: 0.3615 data: 0.0043 max mem: 3956 +train: [15] [ 80/400] eta: 0:02:06 lr: 0.000070 loss: 0.7679 (0.7773) grad: 0.0433 (0.0445) time: 0.3623 data: 0.0042 max mem: 3956 +train: [15] [100/400] eta: 0:01:55 lr: 0.000068 loss: 0.7679 (0.7788) grad: 0.0434 (0.0447) time: 0.3421 data: 0.0042 max mem: 3956 +train: [15] [120/400] eta: 0:01:45 lr: 0.000067 loss: 0.7938 (0.7807) grad: 0.0452 (0.0447) time: 0.3331 data: 0.0037 max mem: 3956 +train: [15] [140/400] eta: 0:01:37 lr: 0.000066 loss: 0.7823 (0.7826) grad: 0.0452 (0.0445) time: 0.3581 data: 0.0042 max mem: 3956 +train: [15] [160/400] eta: 0:01:30 lr: 0.000064 loss: 0.7794 (0.7835) grad: 0.0432 (0.0443) time: 0.3859 data: 0.0043 max mem: 3956 +train: [15] [180/400] eta: 0:01:21 lr: 0.000063 loss: 0.7787 (0.7837) grad: 0.0426 (0.0441) time: 0.3448 data: 0.0042 max mem: 3956 +train: [15] [200/400] eta: 0:01:14 lr: 0.000062 loss: 0.7873 (0.7849) grad: 0.0425 (0.0441) time: 0.3511 data: 0.0038 max mem: 3956 +train: [15] [220/400] eta: 0:01:06 lr: 0.000061 loss: 0.7920 (0.7843) grad: 0.0440 (0.0441) time: 0.3468 data: 0.0037 max mem: 3956 +train: [15] [240/400] eta: 0:00:58 lr: 0.000059 loss: 0.7746 (0.7840) grad: 0.0440 (0.0442) time: 0.3292 data: 0.0036 max mem: 3956 +train: [15] [260/400] eta: 0:00:50 lr: 0.000058 loss: 0.7772 (0.7847) grad: 0.0434 (0.0441) time: 0.3369 data: 0.0037 max mem: 3956 +train: [15] [280/400] eta: 0:00:43 lr: 0.000057 loss: 0.7772 (0.7842) grad: 0.0438 (0.0442) time: 0.3647 data: 0.0040 max mem: 3956 +train: [15] [300/400] eta: 0:00:37 lr: 0.000056 loss: 0.7901 (0.7838) grad: 0.0438 (0.0442) time: 0.4781 data: 0.1711 max mem: 3956 +train: [15] [320/400] eta: 0:00:29 lr: 0.000054 loss: 0.7889 (0.7839) grad: 0.0442 (0.0442) time: 0.3242 data: 0.0041 max mem: 3956 +train: [15] [340/400] eta: 0:00:21 lr: 0.000053 loss: 0.7957 (0.7853) grad: 0.0426 (0.0440) time: 0.3515 data: 0.0027 max mem: 3956 +train: [15] [360/400] eta: 0:00:14 lr: 0.000052 loss: 0.7957 (0.7846) grad: 0.0413 (0.0440) time: 0.3555 data: 0.0039 max mem: 3956 +train: [15] [380/400] eta: 0:00:07 lr: 0.000051 loss: 0.7946 (0.7859) grad: 0.0423 (0.0440) time: 0.3383 data: 0.0040 max mem: 3956 +train: [15] [399/400] eta: 0:00:00 lr: 0.000050 loss: 0.7915 (0.7853) grad: 0.0416 (0.0439) time: 0.3398 data: 0.0041 max mem: 3956 +train: [15] Total time: 0:02:25 (0.3639 s / it) +train: [15] Summary: lr: 0.000050 loss: 0.7915 (0.7853) grad: 0.0416 (0.0439) +eval (validation): [15] [ 0/63] eta: 0:03:07 time: 2.9737 data: 2.7693 max mem: 3956 +eval (validation): [15] [20/63] eta: 0:00:19 time: 0.3289 data: 0.0039 max mem: 3956 +eval (validation): [15] [40/63] eta: 0:00:09 time: 0.3920 data: 0.0047 max mem: 3956 +eval (validation): [15] [60/63] eta: 0:00:01 time: 0.3343 data: 0.0036 max mem: 3956 +eval (validation): [15] [62/63] eta: 0:00:00 time: 0.3256 data: 0.0039 max mem: 3956 +eval (validation): [15] Total time: 0:00:25 (0.3975 s / it) +cv: [15] best hparam: (26, 1.0) (044) ('044_lr2.6e+01_wd1.0e+00') loss: 0.113 acc: 0.968 f1: 0.962 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__linear/checkpoint-last.pth +train: [16] [ 0/400] eta: 0:21:48 lr: nan time: 3.2721 data: 2.9934 max mem: 3956 +train: [16] [ 20/400] eta: 0:03:12 lr: 0.000048 loss: 0.7286 (0.7557) grad: 0.0431 (0.0446) time: 0.3690 data: 0.0046 max mem: 3956 +train: [16] [ 40/400] eta: 0:02:33 lr: 0.000047 loss: 0.7665 (0.7678) grad: 0.0431 (0.0439) time: 0.3388 data: 0.0032 max mem: 3956 +train: [16] [ 60/400] eta: 0:02:15 lr: 0.000046 loss: 0.7708 (0.7713) grad: 0.0428 (0.0441) time: 0.3416 data: 0.0045 max mem: 3956 +train: [16] [ 80/400] eta: 0:02:03 lr: 0.000045 loss: 0.7571 (0.7707) grad: 0.0435 (0.0439) time: 0.3456 data: 0.0042 max mem: 3956 +train: [16] [100/400] eta: 0:01:52 lr: 0.000044 loss: 0.7792 (0.7759) grad: 0.0433 (0.0441) time: 0.3379 data: 0.0041 max mem: 3956 +train: [16] [120/400] eta: 0:01:42 lr: 0.000043 loss: 0.7877 (0.7798) grad: 0.0434 (0.0439) time: 0.3278 data: 0.0041 max mem: 3956 +train: [16] [140/400] eta: 0:01:35 lr: 0.000042 loss: 0.7804 (0.7770) grad: 0.0434 (0.0439) time: 0.3538 data: 0.0041 max mem: 3956 +train: [16] [160/400] eta: 0:01:27 lr: 0.000041 loss: 0.7622 (0.7759) grad: 0.0436 (0.0440) time: 0.3610 data: 0.0042 max mem: 3956 +train: [16] [180/400] eta: 0:01:19 lr: 0.000040 loss: 0.7697 (0.7785) grad: 0.0432 (0.0438) time: 0.3480 data: 0.0045 max mem: 3956 +train: [16] [200/400] eta: 0:01:12 lr: 0.000039 loss: 0.7680 (0.7769) grad: 0.0421 (0.0438) time: 0.3411 data: 0.0043 max mem: 3956 +train: [16] [220/400] eta: 0:01:04 lr: 0.000038 loss: 0.7495 (0.7766) grad: 0.0423 (0.0440) time: 0.3271 data: 0.0042 max mem: 3956 +train: [16] [240/400] eta: 0:00:56 lr: 0.000036 loss: 0.7920 (0.7782) grad: 0.0431 (0.0439) time: 0.3310 data: 0.0041 max mem: 3956 +train: [16] [260/400] eta: 0:00:49 lr: 0.000035 loss: 0.7923 (0.7772) grad: 0.0431 (0.0438) time: 0.3535 data: 0.0044 max mem: 3956 +train: [16] [280/400] eta: 0:00:42 lr: 0.000034 loss: 0.7859 (0.7785) grad: 0.0434 (0.0439) time: 0.3461 data: 0.0040 max mem: 3956 +train: [16] [300/400] eta: 0:00:36 lr: 0.000033 loss: 0.7859 (0.7792) grad: 0.0423 (0.0438) time: 0.4823 data: 0.1709 max mem: 3956 +train: [16] [320/400] eta: 0:00:28 lr: 0.000032 loss: 0.7700 (0.7796) grad: 0.0423 (0.0437) time: 0.3445 data: 0.0042 max mem: 3956 +train: [16] [340/400] eta: 0:00:21 lr: 0.000031 loss: 0.7649 (0.7786) grad: 0.0431 (0.0437) time: 0.3202 data: 0.0030 max mem: 3956 +train: [16] [360/400] eta: 0:00:14 lr: 0.000031 loss: 0.7678 (0.7787) grad: 0.0420 (0.0437) time: 0.3538 data: 0.0040 max mem: 3956 +train: [16] [380/400] eta: 0:00:07 lr: 0.000030 loss: 0.7678 (0.7778) grad: 0.0420 (0.0436) time: 0.3451 data: 0.0039 max mem: 3956 +train: [16] [399/400] eta: 0:00:00 lr: 0.000029 loss: 0.7675 (0.7773) grad: 0.0430 (0.0437) time: 0.3230 data: 0.0040 max mem: 3956 +train: [16] Total time: 0:02:23 (0.3576 s / it) +train: [16] Summary: lr: 0.000029 loss: 0.7675 (0.7773) grad: 0.0430 (0.0437) +eval (validation): [16] [ 0/63] eta: 0:03:09 time: 3.0058 data: 2.8027 max mem: 3956 +eval (validation): [16] [20/63] eta: 0:00:19 time: 0.3218 data: 0.0030 max mem: 3956 +eval (validation): [16] [40/63] eta: 0:00:08 time: 0.3072 data: 0.0028 max mem: 3956 +eval (validation): [16] [60/63] eta: 0:00:01 time: 0.3008 data: 0.0031 max mem: 3956 +eval (validation): [16] [62/63] eta: 0:00:00 time: 0.2990 data: 0.0031 max mem: 3956 +eval (validation): [16] Total time: 0:00:22 (0.3569 s / it) +cv: [16] best hparam: (43, 1.0) (047) ('047_lr4.3e+01_wd1.0e+00') loss: 0.110 acc: 0.969 f1: 0.963 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__linear/checkpoint-best.pth +train: [17] [ 0/400] eta: 0:21:19 lr: nan time: 3.1987 data: 2.9249 max mem: 3956 +train: [17] [ 20/400] eta: 0:03:12 lr: 0.000028 loss: 0.7841 (0.7928) grad: 0.0417 (0.0445) time: 0.3724 data: 0.0030 max mem: 3956 +train: [17] [ 40/400] eta: 0:02:30 lr: 0.000027 loss: 0.7618 (0.7750) grad: 0.0417 (0.0439) time: 0.3271 data: 0.0039 max mem: 3956 +train: [17] [ 60/400] eta: 0:02:11 lr: 0.000026 loss: 0.7593 (0.7744) grad: 0.0430 (0.0443) time: 0.3227 data: 0.0041 max mem: 3956 +train: [17] [ 80/400] eta: 0:01:58 lr: 0.000025 loss: 0.7657 (0.7750) grad: 0.0442 (0.0444) time: 0.3235 data: 0.0040 max mem: 3956 +train: [17] [100/400] eta: 0:01:48 lr: 0.000024 loss: 0.7862 (0.7798) grad: 0.0442 (0.0443) time: 0.3144 data: 0.0040 max mem: 3956 +train: [17] [120/400] eta: 0:01:39 lr: 0.000023 loss: 0.7804 (0.7779) grad: 0.0440 (0.0444) time: 0.3288 data: 0.0040 max mem: 3956 +train: [17] [140/400] eta: 0:01:31 lr: 0.000023 loss: 0.7804 (0.7796) grad: 0.0433 (0.0443) time: 0.3294 data: 0.0042 max mem: 3956 +train: [17] [160/400] eta: 0:01:23 lr: 0.000022 loss: 0.7926 (0.7807) grad: 0.0445 (0.0443) time: 0.3126 data: 0.0039 max mem: 3956 +train: [17] [180/400] eta: 0:01:15 lr: 0.000021 loss: 0.7917 (0.7822) grad: 0.0428 (0.0440) time: 0.3289 data: 0.0041 max mem: 3956 +train: [17] [200/400] eta: 0:01:08 lr: 0.000020 loss: 0.7720 (0.7795) grad: 0.0426 (0.0439) time: 0.3364 data: 0.0041 max mem: 3956 +train: [17] [220/400] eta: 0:01:01 lr: 0.000019 loss: 0.7435 (0.7767) grad: 0.0436 (0.0440) time: 0.3297 data: 0.0042 max mem: 3956 +train: [17] [240/400] eta: 0:00:54 lr: 0.000019 loss: 0.7588 (0.7771) grad: 0.0435 (0.0439) time: 0.3327 data: 0.0042 max mem: 3956 +train: [17] [260/400] eta: 0:00:48 lr: 0.000018 loss: 0.7883 (0.7771) grad: 0.0425 (0.0440) time: 0.3569 data: 0.0042 max mem: 3956 +train: [17] [280/400] eta: 0:00:41 lr: 0.000017 loss: 0.7717 (0.7765) grad: 0.0421 (0.0439) time: 0.3271 data: 0.0041 max mem: 3956 +train: [17] [300/400] eta: 0:00:35 lr: 0.000016 loss: 0.7730 (0.7770) grad: 0.0421 (0.0438) time: 0.5107 data: 0.1733 max mem: 3956 +train: [17] [320/400] eta: 0:00:28 lr: 0.000016 loss: 0.7749 (0.7773) grad: 0.0424 (0.0438) time: 0.3338 data: 0.0041 max mem: 3956 +train: [17] [340/400] eta: 0:00:21 lr: 0.000015 loss: 0.7661 (0.7764) grad: 0.0424 (0.0437) time: 0.3348 data: 0.0038 max mem: 3956 +train: [17] [360/400] eta: 0:00:13 lr: 0.000014 loss: 0.7659 (0.7763) grad: 0.0418 (0.0436) time: 0.3298 data: 0.0040 max mem: 3956 +train: [17] [380/400] eta: 0:00:06 lr: 0.000014 loss: 0.7699 (0.7759) grad: 0.0418 (0.0436) time: 0.3252 data: 0.0040 max mem: 3956 +train: [17] [399/400] eta: 0:00:00 lr: 0.000013 loss: 0.7517 (0.7745) grad: 0.0417 (0.0435) time: 0.3309 data: 0.0037 max mem: 3956 +train: [17] Total time: 0:02:19 (0.3481 s / it) +train: [17] Summary: lr: 0.000013 loss: 0.7517 (0.7745) grad: 0.0417 (0.0435) +eval (validation): [17] [ 0/63] eta: 0:03:23 time: 3.2313 data: 2.9642 max mem: 3956 +eval (validation): [17] [20/63] eta: 0:00:19 time: 0.3186 data: 0.0036 max mem: 3956 +eval (validation): [17] [40/63] eta: 0:00:09 time: 0.3413 data: 0.0037 max mem: 3956 +eval (validation): [17] [60/63] eta: 0:00:01 time: 0.3068 data: 0.0033 max mem: 3956 +eval (validation): [17] [62/63] eta: 0:00:00 time: 0.3051 data: 0.0028 max mem: 3956 +eval (validation): [17] Total time: 0:00:23 (0.3728 s / it) +cv: [17] best hparam: (31, 1.0) (045) ('045_lr3.1e+01_wd1.0e+00') loss: 0.111 acc: 0.969 f1: 0.963 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__linear/checkpoint-last.pth +train: [18] [ 0/400] eta: 0:20:58 lr: nan time: 3.1460 data: 2.9365 max mem: 3956 +train: [18] [ 20/400] eta: 0:03:08 lr: 0.000012 loss: 0.7415 (0.7573) grad: 0.0434 (0.0435) time: 0.3627 data: 0.0035 max mem: 3956 +train: [18] [ 40/400] eta: 0:02:32 lr: 0.000012 loss: 0.7465 (0.7566) grad: 0.0433 (0.0433) time: 0.3485 data: 0.0032 max mem: 3956 +train: [18] [ 60/400] eta: 0:02:14 lr: 0.000011 loss: 0.7615 (0.7659) grad: 0.0429 (0.0434) time: 0.3375 data: 0.0040 max mem: 3956 +train: [18] [ 80/400] eta: 0:02:03 lr: 0.000011 loss: 0.7818 (0.7722) grad: 0.0433 (0.0438) time: 0.3522 data: 0.0039 max mem: 3956 +train: [18] [100/400] eta: 0:01:52 lr: 0.000010 loss: 0.7665 (0.7726) grad: 0.0426 (0.0437) time: 0.3366 data: 0.0041 max mem: 3956 +train: [18] [120/400] eta: 0:01:42 lr: 0.000009 loss: 0.7665 (0.7726) grad: 0.0424 (0.0438) time: 0.3170 data: 0.0041 max mem: 3956 +train: [18] [140/400] eta: 0:01:33 lr: 0.000009 loss: 0.7719 (0.7728) grad: 0.0426 (0.0438) time: 0.3320 data: 0.0042 max mem: 3956 +train: [18] [160/400] eta: 0:01:25 lr: 0.000008 loss: 0.7654 (0.7756) grad: 0.0425 (0.0437) time: 0.3196 data: 0.0040 max mem: 3956 +train: [18] [180/400] eta: 0:01:18 lr: 0.000008 loss: 0.7836 (0.7755) grad: 0.0434 (0.0437) time: 0.3532 data: 0.0044 max mem: 3956 +train: [18] [200/400] eta: 0:01:10 lr: 0.000007 loss: 0.7803 (0.7756) grad: 0.0432 (0.0435) time: 0.3164 data: 0.0040 max mem: 3956 +train: [18] [220/400] eta: 0:01:02 lr: 0.000007 loss: 0.7709 (0.7745) grad: 0.0423 (0.0436) time: 0.3342 data: 0.0042 max mem: 3956 +train: [18] [240/400] eta: 0:00:55 lr: 0.000006 loss: 0.7917 (0.7766) grad: 0.0430 (0.0435) time: 0.3360 data: 0.0040 max mem: 3956 +train: [18] [260/400] eta: 0:00:48 lr: 0.000006 loss: 0.7887 (0.7754) grad: 0.0430 (0.0435) time: 0.3320 data: 0.0038 max mem: 3956 +train: [18] [280/400] eta: 0:00:41 lr: 0.000006 loss: 0.7616 (0.7754) grad: 0.0430 (0.0436) time: 0.3318 data: 0.0039 max mem: 3956 +train: [18] [300/400] eta: 0:00:35 lr: 0.000005 loss: 0.7558 (0.7749) grad: 0.0441 (0.0436) time: 0.5152 data: 0.1823 max mem: 3956 +train: [18] [320/400] eta: 0:00:28 lr: 0.000005 loss: 0.7524 (0.7732) grad: 0.0424 (0.0436) time: 0.3382 data: 0.0045 max mem: 3956 +train: [18] [340/400] eta: 0:00:21 lr: 0.000004 loss: 0.7544 (0.7735) grad: 0.0417 (0.0436) time: 0.3344 data: 0.0038 max mem: 3956 +train: [18] [360/400] eta: 0:00:14 lr: 0.000004 loss: 0.7776 (0.7745) grad: 0.0429 (0.0436) time: 0.3562 data: 0.0043 max mem: 3956 +train: [18] [380/400] eta: 0:00:07 lr: 0.000004 loss: 0.7952 (0.7751) grad: 0.0426 (0.0436) time: 0.3355 data: 0.0038 max mem: 3956 +train: [18] [399/400] eta: 0:00:00 lr: 0.000003 loss: 0.7952 (0.7751) grad: 0.0431 (0.0436) time: 0.3264 data: 0.0040 max mem: 3956 +train: [18] Total time: 0:02:21 (0.3534 s / it) +train: [18] Summary: lr: 0.000003 loss: 0.7952 (0.7751) grad: 0.0431 (0.0436) +eval (validation): [18] [ 0/63] eta: 0:03:14 time: 3.0883 data: 2.8733 max mem: 3956 +eval (validation): [18] [20/63] eta: 0:00:20 time: 0.3449 data: 0.0037 max mem: 3956 +eval (validation): [18] [40/63] eta: 0:00:09 time: 0.3335 data: 0.0030 max mem: 3956 +eval (validation): [18] [60/63] eta: 0:00:01 time: 0.2946 data: 0.0031 max mem: 3956 +eval (validation): [18] [62/63] eta: 0:00:00 time: 0.2927 data: 0.0024 max mem: 3956 +eval (validation): [18] Total time: 0:00:23 (0.3718 s / it) +cv: [18] best hparam: (31, 1.0) (045) ('045_lr3.1e+01_wd1.0e+00') loss: 0.111 acc: 0.968 f1: 0.963 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__linear/checkpoint-last.pth +train: [19] [ 0/400] eta: 0:21:23 lr: nan time: 3.2096 data: 2.9818 max mem: 3956 +train: [19] [ 20/400] eta: 0:03:01 lr: 0.000003 loss: 0.7778 (0.7916) grad: 0.0418 (0.0418) time: 0.3418 data: 0.0035 max mem: 3956 +train: [19] [ 40/400] eta: 0:02:29 lr: 0.000003 loss: 0.7922 (0.7855) grad: 0.0431 (0.0432) time: 0.3487 data: 0.0029 max mem: 3956 +train: [19] [ 60/400] eta: 0:02:11 lr: 0.000002 loss: 0.7604 (0.7734) grad: 0.0439 (0.0437) time: 0.3297 data: 0.0040 max mem: 3956 +train: [19] [ 80/400] eta: 0:02:00 lr: 0.000002 loss: 0.7658 (0.7765) grad: 0.0434 (0.0437) time: 0.3420 data: 0.0042 max mem: 3956 +train: [19] [100/400] eta: 0:01:49 lr: 0.000002 loss: 0.7780 (0.7757) grad: 0.0442 (0.0439) time: 0.3268 data: 0.0041 max mem: 3956 +train: [19] [120/400] eta: 0:01:40 lr: 0.000002 loss: 0.7733 (0.7767) grad: 0.0450 (0.0440) time: 0.3268 data: 0.0040 max mem: 3956 +train: [19] [140/400] eta: 0:01:32 lr: 0.000001 loss: 0.7816 (0.7766) grad: 0.0437 (0.0439) time: 0.3448 data: 0.0042 max mem: 3956 +train: [19] [160/400] eta: 0:01:24 lr: 0.000001 loss: 0.7849 (0.7762) grad: 0.0437 (0.0438) time: 0.3226 data: 0.0038 max mem: 3956 +train: [19] [180/400] eta: 0:01:16 lr: 0.000001 loss: 0.7514 (0.7723) grad: 0.0427 (0.0437) time: 0.3236 data: 0.0042 max mem: 3956 +train: [19] [200/400] eta: 0:01:09 lr: 0.000001 loss: 0.7541 (0.7719) grad: 0.0433 (0.0438) time: 0.3490 data: 0.0044 max mem: 3956 +train: [19] [220/400] eta: 0:01:02 lr: 0.000001 loss: 0.7669 (0.7722) grad: 0.0447 (0.0438) time: 0.3405 data: 0.0045 max mem: 3956 +train: [19] [240/400] eta: 0:00:55 lr: 0.000001 loss: 0.7683 (0.7729) grad: 0.0435 (0.0436) time: 0.3357 data: 0.0040 max mem: 3956 +train: [19] [260/400] eta: 0:00:48 lr: 0.000000 loss: 0.7688 (0.7730) grad: 0.0418 (0.0435) time: 0.3329 data: 0.0043 max mem: 3956 +train: [19] [280/400] eta: 0:00:41 lr: 0.000000 loss: 0.7749 (0.7743) grad: 0.0411 (0.0435) time: 0.3124 data: 0.0038 max mem: 3956 +train: [19] [300/400] eta: 0:00:35 lr: 0.000000 loss: 0.7749 (0.7750) grad: 0.0422 (0.0435) time: 0.4755 data: 0.1688 max mem: 3956 +train: [19] [320/400] eta: 0:00:28 lr: 0.000000 loss: 0.7764 (0.7754) grad: 0.0422 (0.0435) time: 0.3179 data: 0.0039 max mem: 3956 +train: [19] [340/400] eta: 0:00:20 lr: 0.000000 loss: 0.7640 (0.7749) grad: 0.0421 (0.0435) time: 0.3079 data: 0.0030 max mem: 3956 +train: [19] [360/400] eta: 0:00:13 lr: 0.000000 loss: 0.7490 (0.7741) grad: 0.0423 (0.0435) time: 0.3257 data: 0.0041 max mem: 3956 +train: [19] [380/400] eta: 0:00:06 lr: 0.000000 loss: 0.7497 (0.7743) grad: 0.0423 (0.0435) time: 0.3231 data: 0.0040 max mem: 3956 +train: [19] [399/400] eta: 0:00:00 lr: 0.000000 loss: 0.7659 (0.7733) grad: 0.0456 (0.0436) time: 0.3139 data: 0.0038 max mem: 3956 +train: [19] Total time: 0:02:17 (0.3449 s / it) +train: [19] Summary: lr: 0.000000 loss: 0.7659 (0.7733) grad: 0.0456 (0.0436) +eval (validation): [19] [ 0/63] eta: 0:03:06 time: 2.9555 data: 2.7500 max mem: 3956 +eval (validation): [19] [20/63] eta: 0:00:19 time: 0.3218 data: 0.0049 max mem: 3956 +eval (validation): [19] [40/63] eta: 0:00:08 time: 0.2897 data: 0.0028 max mem: 3956 +eval (validation): [19] [60/63] eta: 0:00:01 time: 0.2813 data: 0.0032 max mem: 3956 +eval (validation): [19] [62/63] eta: 0:00:00 time: 0.2778 data: 0.0032 max mem: 3956 +eval (validation): [19] Total time: 0:00:21 (0.3444 s / it) +cv: [19] best hparam: (22, 1.0) (043) ('043_lr2.2e+01_wd1.0e+00') loss: 0.113 acc: 0.968 f1: 0.963 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__linear/checkpoint-last.pth +evaluating last checkpoint: experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__linear/checkpoint-last.pth +eval model info: +{"score": 0.9682539682539683, "hparam": [22, 1.0], "hparam_id": 43, "epoch": 19, "is_best": false, "best_score": 0.9692460317460317} +eval (train): [20] [ 0/297] eta: 0:14:41 time: 2.9676 data: 2.7317 max mem: 3956 +eval (train): [20] [ 20/297] eta: 0:02:04 time: 0.3245 data: 0.0029 max mem: 3956 +eval (train): [20] [ 40/297] eta: 0:01:41 time: 0.3334 data: 0.0035 max mem: 3956 +eval (train): [20] [ 60/297] eta: 0:01:26 time: 0.3085 data: 0.0032 max mem: 3956 +eval (train): [20] [ 80/297] eta: 0:01:16 time: 0.3109 data: 0.0033 max mem: 3956 +eval (train): [20] [100/297] eta: 0:01:07 time: 0.2965 data: 0.0031 max mem: 3956 +eval (train): [20] [120/297] eta: 0:00:59 time: 0.3155 data: 0.0033 max mem: 3956 +eval (train): [20] [140/297] eta: 0:00:52 time: 0.3181 data: 0.0036 max mem: 3956 +eval (train): [20] [160/297] eta: 0:00:45 time: 0.3209 data: 0.0032 max mem: 3956 +eval (train): [20] [180/297] eta: 0:00:38 time: 0.3153 data: 0.0031 max mem: 3956 +eval (train): [20] [200/297] eta: 0:00:32 time: 0.3356 data: 0.0036 max mem: 3956 +eval (train): [20] [220/297] eta: 0:00:25 time: 0.3341 data: 0.0036 max mem: 3956 +eval (train): [20] [240/297] eta: 0:00:18 time: 0.3053 data: 0.0033 max mem: 3956 +eval (train): [20] [260/297] eta: 0:00:12 time: 0.3222 data: 0.0036 max mem: 3956 +eval (train): [20] [280/297] eta: 0:00:05 time: 0.3157 data: 0.0036 max mem: 3956 +eval (train): [20] [296/297] eta: 0:00:00 time: 0.2879 data: 0.0034 max mem: 3956 +eval (train): [20] Total time: 0:01:37 (0.3276 s / it) +eval (validation): [20] [ 0/63] eta: 0:03:16 time: 3.1202 data: 2.9159 max mem: 3956 +eval (validation): [20] [20/63] eta: 0:00:19 time: 0.3176 data: 0.0035 max mem: 3956 +eval (validation): [20] [40/63] eta: 0:00:08 time: 0.3193 data: 0.0031 max mem: 3956 +eval (validation): [20] [60/63] eta: 0:00:01 time: 0.2951 data: 0.0034 max mem: 3956 +eval (validation): [20] [62/63] eta: 0:00:00 time: 0.2932 data: 0.0033 max mem: 3956 +eval (validation): [20] Total time: 0:00:22 (0.3596 s / it) +eval (test): [20] [ 0/79] eta: 0:04:46 time: 3.6329 data: 3.3887 max mem: 3956 +eval (test): [20] [20/79] eta: 0:00:26 time: 0.2967 data: 0.0027 max mem: 3956 +eval (test): [20] [40/79] eta: 0:00:14 time: 0.3064 data: 0.0031 max mem: 3956 +eval (test): [20] [60/79] eta: 0:00:06 time: 0.3029 data: 0.0028 max mem: 3956 +eval (test): [20] [78/79] eta: 0:00:00 time: 0.2919 data: 0.0033 max mem: 3956 +eval (test): [20] Total time: 0:00:27 (0.3453 s / it) +evaluating best checkpoint: experiments/decoders/output/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__linear/checkpoint-best.pth +eval model info: +{"score": 0.9692460317460317, "hparam": [43, 1.0], "hparam_id": 47, "epoch": 16, "is_best": true, "best_score": 0.9692460317460317} +eval (train): [20] [ 0/297] eta: 0:15:26 time: 3.1198 data: 2.8595 max mem: 3956 +eval (train): [20] [ 20/297] eta: 0:02:10 time: 0.3380 data: 0.0049 max mem: 3956 +eval (train): [20] [ 40/297] eta: 0:01:40 time: 0.3064 data: 0.0029 max mem: 3956 +eval (train): [20] [ 60/297] eta: 0:01:25 time: 0.3007 data: 0.0032 max mem: 3956 +eval (train): [20] [ 80/297] eta: 0:01:16 time: 0.3256 data: 0.0034 max mem: 3956 +eval (train): [20] [100/297] eta: 0:01:09 time: 0.3452 data: 0.0036 max mem: 3956 +eval (train): [20] [120/297] eta: 0:01:00 time: 0.3122 data: 0.0033 max mem: 3956 +eval (train): [20] [140/297] eta: 0:00:53 time: 0.3152 data: 0.0035 max mem: 3956 +eval (train): [20] [160/297] eta: 0:00:46 time: 0.3122 data: 0.0032 max mem: 3956 +eval (train): [20] [180/297] eta: 0:00:39 time: 0.3120 data: 0.0034 max mem: 3956 +eval (train): [20] [200/297] eta: 0:00:31 time: 0.2892 data: 0.0030 max mem: 3956 +eval (train): [20] [220/297] eta: 0:00:25 time: 0.3180 data: 0.0033 max mem: 3956 +eval (train): [20] [240/297] eta: 0:00:18 time: 0.3166 data: 0.0034 max mem: 3956 +eval (train): [20] [260/297] eta: 0:00:12 time: 0.3461 data: 0.0039 max mem: 3956 +eval (train): [20] [280/297] eta: 0:00:05 time: 0.3614 data: 0.0036 max mem: 3956 +eval (train): [20] [296/297] eta: 0:00:00 time: 0.3206 data: 0.0036 max mem: 3956 +eval (train): [20] Total time: 0:01:38 (0.3327 s / it) +eval (validation): [20] [ 0/63] eta: 0:03:09 time: 3.0022 data: 2.7954 max mem: 3956 +eval (validation): [20] [20/63] eta: 0:00:19 time: 0.3182 data: 0.0035 max mem: 3956 +eval (validation): [20] [40/63] eta: 0:00:09 time: 0.3481 data: 0.0031 max mem: 3956 +eval (validation): [20] [60/63] eta: 0:00:01 time: 0.3062 data: 0.0033 max mem: 3956 +eval (validation): [20] [62/63] eta: 0:00:00 time: 0.3012 data: 0.0035 max mem: 3956 +eval (validation): [20] Total time: 0:00:23 (0.3703 s / it) +eval (test): [20] [ 0/79] eta: 0:03:48 time: 2.8983 data: 2.6931 max mem: 3956 +eval (test): [20] [20/79] eta: 0:00:25 time: 0.3148 data: 0.0026 max mem: 3956 +eval (test): [20] [40/79] eta: 0:00:15 time: 0.3719 data: 0.0036 max mem: 3956 +eval (test): [20] [60/79] eta: 0:00:07 time: 0.3239 data: 0.0034 max mem: 3956 +eval (test): [20] [78/79] eta: 0:00:00 time: 0.2919 data: 0.0031 max mem: 3956 +eval (test): [20] Total time: 0:00:28 (0.3624 s / it) +eval results: + +| model | repr | clf | dataset | ckpt | epoch | lr | wd | hparam_id | hparam | split | loss | acc | acc_std | f1 | f1_std | +|:---------|:-------|:-------|:-------------|:-------|--------:|-------:|-----:|------------:|:----------|:-----------|---------:|--------:|-----------:|--------:|-----------:| +| flat_mae | reg | linear | hcpya_task21 | best | 16 | 0.0129 | 0.05 | 47 | [43, 1.0] | train | 0.045581 | 0.99326 | 0.00057597 | 0.99458 | 0.00049849 | +| flat_mae | reg | linear | hcpya_task21 | best | 16 | 0.0129 | 0.05 | 47 | [43, 1.0] | validation | 0.11012 | 0.96925 | 0.0026725 | 0.96344 | 0.0036046 | +| flat_mae | reg | linear | hcpya_task21 | best | 16 | 0.0129 | 0.05 | 47 | [43, 1.0] | test | 0.13361 | 0.9627 | 0.0025978 | 0.95678 | 0.0034142 | + + +done! total time: 1:02:02 diff --git a/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__linear/train_log.json b/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__linear/train_log.json new file mode 100644 index 0000000000000000000000000000000000000000..353735a4c3b081e315a4161a942f92d29aa738fa --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/hcpya_task21__reg__linear/train_log.json @@ -0,0 +1,20 @@ +{"epoch": 0, "train/lr": 2.987987987987988e-05, "train/loss": 2.743629469871521, "train/grad": 0.10064485918730498, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.016380615234375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.0161767578125, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.01580078125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.0154296875, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.015068359375, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.014610595703125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.014049072265625, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.013465576171875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.01264892578125, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.01181396484375, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.010965576171875, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.009632568359375, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.00839599609375, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.006319580078125, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.004412841796875, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.002376708984375, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.99971923828125, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.996470947265625, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.99259521484375, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.988699951171875, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.983519287109375, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.977711181640625, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.97072998046875, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.9624072265625, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.953016357421875, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.940404052734375, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.928153076171875, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.915960693359375, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.89790283203125, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.8743896484375, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.8512744140625, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.828748779296875, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.7956805419921875, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.7638165283203127, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.7227239990234375, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.67818603515625, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.626619567871094, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.573037109375, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.510051727294922, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.424604644775391, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.353384475708008, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.287399368286133, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.197477264404297, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.116877326965332, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.021769027709961, "train/loss_045_lr3.1e+01_wd1.0e+00": 1.9191956233978271, "train/loss_046_lr3.6e+01_wd1.0e+00": 1.8312088584899902, "train/loss_047_lr4.3e+01_wd1.0e+00": 1.7269335031509399, "train/loss_048_lr5.0e+01_wd1.0e+00": 1.6396304702758788, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.015593439433723688, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.015592438708990812, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.015590586219914257, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.015588673413731158, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.01558685660827905, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.01558420125860721, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.01558127464260906, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.0155782999843359, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.015574059337377549, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.015569391213357448, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.015564556890167296, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.01555773064494133, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.015550775406882166, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.015539483278989791, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.01552892338950187, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.015518427360802889, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.015504425540566445, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.015487345862202346, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.015465839700773358, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.015444912617094814, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.015416798419319094, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.015385906668379903, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.015348455966450274, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.015304066576063632, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.015253725280053913, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.01518666566349566, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.015120473071001471, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.015054134088568389, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.014955437388271093, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.01482593767810613, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.01469788831193, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.014572722651064397, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.014386863862164319, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.014205640046857298, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.013971459032036363, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.013719923947937786, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.013431356991641224, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.013140016426332295, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.012808907316066325, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.01237796229077503, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.012032464288640767, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.011721276079770178, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.011305766669102013, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.01093949685106054, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.010511789061129094, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.010054030483588576, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.00966237963642925, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.00920032526482828, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.00881379597587511, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.015233039855957, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.0146398544311523, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.013676881790161, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.012700080871582, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.0116755962371826, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.010281801223755, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.0087199211120605, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.0069167613983154, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.0045864582061768, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.001966953277588, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.9994137287139893, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.995540142059326, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.991579294204712, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.9856820106506348, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.979827880859375, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.9739930629730225, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.966231346130371, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.9565975666046143, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.9450645446777344, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.933635950088501, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.918503522872925, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.9015848636627197, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.881160259246826, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.857266426086426, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.830137252807617, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.7945075035095215, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.7596287727355957, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.7254157066345215, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.675226926803589, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.6104071140289307, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.5479135513305664, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.4876198768615723, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.401033878326416, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.3189635276794434, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.2157185077667236, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.1075081825256348, "validation/loss_036_lr7.1e+00_wd1.0e+00": 1.9853720664978027, "validation/loss_037_lr8.3e+00_wd1.0e+00": 1.8634322881698608, "validation/loss_038_lr9.8e+00_wd1.0e+00": 1.7255498170852661, "validation/loss_039_lr1.2e+01_wd1.0e+00": 1.548600196838379, "validation/loss_040_lr1.4e+01_wd1.0e+00": 1.4103842973709106, "validation/loss_041_lr1.6e+01_wd1.0e+00": 1.2909504175186157, "validation/loss_042_lr1.9e+01_wd1.0e+00": 1.1409727334976196, "validation/loss_043_lr2.2e+01_wd1.0e+00": 1.0194485187530518, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.8913446664810181, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.7708756923675537, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.6808823347091675, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.5888693928718567, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.5224392414093018, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.08035714285714286, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.08209325396825397, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.08531746031746032, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.08903769841269842, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.09151785714285714, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.09821428571428571, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.10342261904761904, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.11185515873015874, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.12351190476190477, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.13368055555555555, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.14186507936507936, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.15699404761904762, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.1691468253968254, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.18948412698412698, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.2041170634920635, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.2204861111111111, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.24156746031746032, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.2594246031746032, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.279265873015873, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.2978670634920635, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.3239087301587302, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.34771825396825395, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.375, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.4037698412698413, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.4310515873015873, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.4595734126984127, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.47842261904761907, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.49603174603174605, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.5158730158730159, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.5334821428571429, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.5528273809523809, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.5704365079365079, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.5942460317460317, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.6190476190476191, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.6416170634920635, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.671875, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.7061011904761905, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.7338789682539683, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.7735615079365079, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.8239087301587301, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.8621031746031746, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.8819444444444444, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.8995535714285714, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9089781746031746, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9159226190476191, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9223710317460317, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9246031746031746, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9268353174603174, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9317956349206349, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.039039824106447726, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.039667569726456846, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.04078361775113486, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.042097939640634414, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.04323901827407791, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.04556588914647799, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.04713670002498811, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.05006263493376333, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.05343406439468289, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.05659207864266924, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.05843365000316049, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.06205597469806808, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.06576335385498402, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.07277079618081932, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.07765199784562779, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.08253831759126715, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.09332642277272166, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.10102289615377222, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.11189963248181292, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.12366785012820232, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.14368917432590828, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.16452552353544425, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.1885573590746167, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.21541920393182704, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.242591198530737, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.2721215476234641, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.2946354595876218, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.31055494889449087, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.3321820776560892, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.35166833402705594, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.37195323217150156, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.3905533844138148, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.41466643516209795, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.44074946388393615, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.4694253841889145, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.5064064641017182, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.5452318589263119, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.5859422010541186, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.6555307437438059, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.7520126963756596, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.8263343559784528, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.8604994792233405, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.8872890392007968, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9006954176905023, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9093353209574233, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9165870830476693, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9186350745136125, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9219966295965678, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9279871986130691, "id_best": 48, "lr_best": 0.015, "wd_best": 0.05, "train/loss_best": 1.6396304702758788, "validation/loss_best": 0.5224392414093018, "validation/acc_best": 0.9317956349206349, "validation/f1_best": 0.9279871986130691} +{"epoch": 1, "train/lr": 8.993993993993998e-05, "train/loss": 2.134965007901192, "train/grad": 0.0853664180263877, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.008934326171875, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.007530517578125, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.0052001953125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.002896728515625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.000618896484375, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.99727294921875, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.993642578125, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.9894677734375, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.98405517578125, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.978115234375, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.972215576171875, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.96322509765625, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.954296875, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.940860595703125, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.927679443359375, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.91444580078125, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.8971240234375, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.875692138671875, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.850238037109375, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.825311279296875, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.7926239013671874, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.756441650390625, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.71344482421875, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.6639007568359374, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.60883056640625, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.5381298828125, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.470511779785156, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.405717468261719, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.313692932128906, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.199586181640625, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.0941087341308595, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.9966600036621094, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.8635497283935547, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.744390106201172, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.604165267944336, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.4681010818481446, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.3273446655273438, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.1994386577606202, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.068834056854248, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.9205096435546875, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.8175917768478393, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.7361763072013855, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.6424031114578247, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.5721324157714843, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.5025302094221115, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.44035642385482787, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.3954368659853935, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.35014325618743897, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.31771191641688346, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.01560169700998813, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.015593973458744586, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.015581676638685166, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.015569268418475985, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.015556644974276423, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.015539025496691465, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.015519766448996962, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.01549721262883395, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.015468008974567056, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.01543658229522407, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.015404954440891743, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.015356335341930389, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.015308426027186215, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.015237374994903803, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.015166554250754416, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.015096814916469158, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.015003300891257822, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.01488826346118003, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.014750811937265098, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.01461582500487566, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.01443769491277635, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.014239502153359354, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.014002260430715978, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.013726949086412787, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.013417588127776981, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.013020062264986336, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.012639505732804536, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.012279822533018887, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.011779834758490324, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.01118613688275218, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.010665671902243047, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.010206132465973496, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.00960814173333347, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.009094555848278105, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.008509302099701016, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.007954619363881648, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.007385285515338183, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.006866454789415002, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.006328022684901953, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.005700304956408217, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.005250138548435643, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.00488546073785983, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.004454867751337588, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.004126368723809719, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0037954404356423765, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0034973867947701363, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.003282495919847861, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0030656899738823996, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0029127504263306036, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.0033786296844482, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.0009970664978027, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.9970295429229736, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.9931347370147705, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.9891881942749023, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.9837162494659424, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.9774913787841797, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.970521926879883, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.9612443447113037, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.951199531555176, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.941225528717041, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.9260735511779785, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.9110000133514404, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.8886024951934814, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.8665425777435303, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.844733476638794, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.8160173892974854, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.780778169631958, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.7394258975982666, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.6989760398864746, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.6464593410491943, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.589242696762085, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.5216658115386963, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.445133686065674, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.3611745834350586, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.2557573318481445, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.157013416290283, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.064535617828369, "validation/loss_028_lr1.9e+00_wd1.0e+00": 1.9365777969360352, "validation/loss_029_lr2.3e+00_wd1.0e+00": 1.7830674648284912, "validation/loss_030_lr2.7e+00_wd1.0e+00": 1.6469327211380005, "validation/loss_031_lr3.1e+00_wd1.0e+00": 1.5257728099822998, "validation/loss_032_lr3.7e+00_wd1.0e+00": 1.3687992095947266, "validation/loss_033_lr4.3e+00_wd1.0e+00": 1.236730694770813, "validation/loss_034_lr5.1e+00_wd1.0e+00": 1.0922831296920776, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.9635108113288879, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.8419578075408936, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.741293728351593, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.6477634310722351, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.5515636205673218, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.49034959077835083, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.44461819529533386, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.39445939660072327, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.3583213984966278, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.32327109575271606, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.2921050786972046, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.26944461464881897, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.24648287892341614, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.22963793575763702, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.12723214285714285, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.13690476190476192, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.15104166666666666, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.16468253968253968, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.1783234126984127, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.1949404761904762, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.2095734126984127, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.22941468253968253, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.24875992063492064, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.2683531746031746, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.2864583333333333, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.31547619047619047, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.3375496031746032, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.36929563492063494, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.39856150793650796, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.4226190476190476, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.4523809523809524, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.47867063492063494, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.5004960317460317, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.5205853174603174, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.5404265873015873, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.560515873015873, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.5818452380952381, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.6081349206349206, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.6307043650793651, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.6579861111111112, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.6810515873015873, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.7041170634920635, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.732390873015873, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.7661210317460317, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.8010912698412699, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.8323412698412699, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.8759920634920635, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.8963293650793651, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9117063492063492, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9188988095238095, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9243551587301587, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9278273809523809, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9298115079365079, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9330357142857143, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9350198412698413, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9372519841269841, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9397321428571429, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9409722222222222, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9419642857142857, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9459325396825397, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9471726190476191, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9486607142857143, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9494047619047619, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.054619510092739694, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.0572655821687608, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.060674825623405856, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.0644057282589339, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.0682696407278966, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.07457950867204637, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.07878823371696135, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.08869308104519967, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.09719291332763465, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.10595205488444555, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.11777041351315327, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.13776921785509147, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.15616904223452188, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.1846473206973203, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.21288265837213277, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.23386574936852295, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.2659511736744434, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.29440579236351777, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.3161253024785835, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.3384082488706037, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.3597829895101745, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.38083151807110277, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.40380997277391484, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.4288136275437284, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.45218849348906387, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.4848161380981891, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.5078654629741929, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.5361679358826388, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.5764042113971446, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.6316549528742523, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.7008174886125382, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.7724864503510376, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.8517856327922098, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.8825219394475807, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9053491641946996, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9122123203002909, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9180068094103876, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9220244006767809, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9247410251479466, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9277404941792494, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.929967903306685, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9317751193063631, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9339154072725823, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9359650760504105, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.936105664229809, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9402626884214026, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.941854492726641, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9441627287389648, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9455030359254687, "id_best": 48, "lr_best": 0.015, "wd_best": 0.05, "train/loss_best": 0.31771191641688346, "validation/loss_best": 0.22963793575763702, "validation/acc_best": 0.9494047619047619, "validation/f1_best": 0.9455030359254687} +{"epoch": 2, "train/lr": 0.00014999999999999988, "train/loss": 1.7744123166799546, "train/grad": 0.07616400247439742, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.99365966796875, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.98993896484375, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.983773193359375, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.97761962890625, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.97141845703125, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.962845458984375, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.953160400390625, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.942216796875, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.927705078125, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.912257080078125, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.896884765625, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.8734814453125, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.850487060546875, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.8164453125, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.783084716796875, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.7503009033203125, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.7075732421875, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.6555859375, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.5952667236328124, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.5369622802734373, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.462293701171875, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.3822412109375, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.28969482421875, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.1869586181640623, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.0769317626953123, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.942551727294922, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.8208699798583985, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.7103456115722657, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.5631102752685546, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.3963853073120118, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.2575051116943359, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.1411472511291505, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.9999534034729004, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.889157772064209, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.7752562427520752, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.6794498872756958, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.5932096338272095, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.5244878435134888, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.46202132701873777, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.3988564932346344, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.3587387931346893, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.3287749856710434, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.2955911520123482, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.2713500472903252, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.2474128058552742, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.2259892275929451, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.2100749521702528, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.19367344439029693, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.18150512151420117, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.015487164477817714, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.015466917641460895, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.015434357682242989, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.015401225467212499, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.015368380369618535, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.015322670373134315, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.015271484986878931, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.01521299209445715, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.015136844897642731, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.015056563434191048, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.014975301381200552, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.014851317261345684, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.014729862036183476, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.014546169782988727, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.01436787014361471, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.014191441698931157, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.013959930762648582, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.013677703295834363, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.013348248968832195, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.013026916580274701, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.012615299127064645, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.012174577214755117, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.011674318546429276, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.01113873053342104, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.01059333308134228, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.009971649018116296, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.00944624435622245, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.008993890597485005, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.008414298705756664, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.007770638524089008, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.007229733944404871, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.006767595435958356, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.006187844476662576, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.005715728425420821, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.005212804019683972, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.004773855347884819, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.004366961786290631, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.004034349692519754, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.003726850686362013, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.003410948384553194, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0032079487829469143, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0030552511173300447, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.002885876449290663, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.002759845022810623, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.002634775968035683, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0025212984351674094, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.002435329854488373, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0023459647165145724, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.002279662627261132, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.983816385269165, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.978614330291748, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.9698636531829834, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.961167097091675, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.9525184631347656, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.940460681915283, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.926828622817993, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.9116411209106445, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.891521453857422, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.8699734210968018, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.8487188816070557, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.8165013790130615, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.7848551273345947, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.738407611846924, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.693134307861328, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.648961067199707, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.5917460918426514, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.5228230953216553, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.443634510040283, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.3680646419525146, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.2726035118103027, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.171851873397827, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.057386875152588, "validation/loss_023_lr8.5e-01_wd1.0e+00": 1.9331296682357788, "validation/loss_024_lr1.0e+00_wd1.0e+00": 1.8029459714889526, "validation/loss_025_lr1.2e+00_wd1.0e+00": 1.6487486362457275, "validation/loss_026_lr1.4e+00_wd1.0e+00": 1.513695240020752, "validation/loss_027_lr1.6e+00_wd1.0e+00": 1.3953728675842285, "validation/loss_028_lr1.9e+00_wd1.0e+00": 1.244493842124939, "validation/loss_029_lr2.3e+00_wd1.0e+00": 1.0834147930145264, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.9574362635612488, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.8577151894569397, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.7432274222373962, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.6580860614776611, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.5746004581451416, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.5070488452911377, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.4477636516094208, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.4012748599052429, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.3592277467250824, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.31677326560020447, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.28976061940193176, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.26940178871154785, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.2467346489429474, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.2301013469696045, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.21351946890354156, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.19879823923110962, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.18783357739448547, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.17699599266052246, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.1692749261856079, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.19295634920634921, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.20535714285714285, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.22991071428571427, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.2490079365079365, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.26512896825396826, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.2876984126984127, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.3149801587301587, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.3365575396825397, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.3685515873015873, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.3975694444444444, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.4243551587301587, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.4556051587301587, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.47966269841269843, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.5104166666666666, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.5297619047619048, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.5463789682539683, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.5682043650793651, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.589781746031746, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.6125992063492064, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.6354166666666666, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.6587301587301587, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.6850198412698413, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.7127976190476191, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.738343253968254, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.7683531746031746, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.8013392857142857, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.8395337301587301, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.8692956349206349, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.8933531746031746, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9099702380952381, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9184027777777778, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9231150793650794, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9265873015873016, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9300595238095238, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9327876984126984, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9352678571428571, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9384920634920635, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9417162698412699, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9434523809523809, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9446924603174603, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9464285714285714, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9476686507936508, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9496527777777778, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9513888888888888, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9523809523809523, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9541170634920635, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9541170634920635, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9553571428571429, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9561011904761905, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.07344429435803722, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.07875417408120335, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.08900585162861283, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.09773326585985952, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.10450051971920095, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.11901921178615067, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.13721426216715032, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.15601376011775872, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.18533734193561, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.21216949859289397, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.23604401172303444, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.26804767723324535, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.2947271587297036, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.3244125613636242, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.3472807494784672, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.36580462731504587, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.38632653163956654, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.41017925834787694, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.4328491513610303, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.4573846971983194, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.48495833792619925, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.5152217150565337, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.5476647581324342, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.5847825374351395, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.6333881749216508, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.7007930828076403, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.7803921811572937, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.8394326532823105, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.8762647340852856, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9015881957391895, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9129901982691324, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9190588191108963, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9224551441938247, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.925984560951873, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.928815581211442, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9315480963245081, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9348583862477424, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9372895960248121, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9381003725908338, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9389937015152787, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.941255566060135, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9426219984678587, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9451172611784381, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9474720700592966, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9484201968412365, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9500870286695099, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9497571684248656, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9512183742027726, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9518816148358094, "id_best": 48, "lr_best": 0.015, "wd_best": 0.05, "train/loss_best": 0.18150512151420117, "validation/loss_best": 0.1692749261856079, "validation/acc_best": 0.9561011904761905, "validation/f1_best": 0.9518816148358094} +{"epoch": 3, "train/lr": 0.0002100600600600602, "train/loss": 1.5300151264667512, "train/grad": 0.06926060551777483, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.9694921875, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.96232177734375, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.950458984375, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.938624267578125, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.92692138671875, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.910712890625, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.89229248046875, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.8718701171875, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.844871826171875, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.81614501953125, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.7878369140625, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.745218505859375, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.703546142578125, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.6429193115234373, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.5842938232421875, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.5275537109375, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.45476806640625, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.367979736328125, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.2697830200195312, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.1773471069335937, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.06252685546875, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.9435150146484375, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.8112806701660156, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.671390914916992, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.529374237060547, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.3677792358398437, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.2327410888671875, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.1192761802673339, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.9812472915649414, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.8415805244445801, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.7375550317764282, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.6579555606842041, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.5693057131767273, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.504908242225647, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.44261669397354125, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.3925375878810883, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.348693373799324, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.31420908838510514, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.2828290182352066, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.2507211492955685, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.2299419805407524, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.21408423386514186, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.1960923670977354, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.18264547750353813, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.16913872487843037, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.15668968841433525, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.1474232540652156, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.13761308684945106, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.13011342886835336, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.015318967965431512, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.015280355275608599, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.015217097066342831, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.015155842993408442, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.01509418684989214, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.015009457119740546, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.01491456645540893, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.014807367199100554, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.01466519579757005, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.0145112482085824, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.014359877333045007, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.014133099936880172, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.013910350687801838, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.01358480186201632, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.01326730138156563, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.012959041334688663, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.012562291990034282, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.012090117954649031, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.011563253486528993, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.01108283485751599, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.010514383022673428, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.00996345647610724, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.009391308994963765, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.008822123825084419, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.008264327859506012, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.007635318953543901, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.007102361139841378, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0066439782897941765, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.006069127228111029, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.005464153829962015, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.004996774605242536, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.004629011963261292, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.004209260095376521, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.003897874492686242, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.003592635716777295, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.003344827078981325, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0031256668968126177, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0029514671862125395, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.002793017582735047, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.002628685430972837, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0025203491584397855, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.002435825538705103, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.002336550994659774, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.002263202035683207, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0021916291769593955, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0021288855344755576, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.002083184667280875, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.002032571652089246, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0019909455033484845, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.956782579421997, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.9476161003112793, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.932399272918701, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.9173412322998047, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.902425765991211, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.881716251373291, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.8583080768585205, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.8323605060577393, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.7983744144439697, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.7622642517089844, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.726853609085083, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.6736767292022705, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.622049570083618, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.5473973751068115, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.4758729934692383, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.4071977138519287, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.3199920654296875, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.217451333999634, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.102905035018921, "validation/loss_019_lr4.4e-01_wd1.0e+00": 1.996873378753662, "validation/loss_020_lr5.2e-01_wd1.0e+00": 1.867218017578125, "validation/loss_021_lr6.1e-01_wd1.0e+00": 1.7355444431304932, "validation/loss_022_lr7.2e-01_wd1.0e+00": 1.5927666425704956, "validation/loss_023_lr8.5e-01_wd1.0e+00": 1.446302890777588, "validation/loss_024_lr1.0e+00_wd1.0e+00": 1.3025976419448853, "validation/loss_025_lr1.2e+00_wd1.0e+00": 1.1458461284637451, "validation/loss_026_lr1.4e+00_wd1.0e+00": 1.020451307296753, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.9189634323120117, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.8003525137901306, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.6854056119918823, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.6026506423950195, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.5409774780273438, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.4732828438282013, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.4247535765171051, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.37803226709365845, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.3403334319591522, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.30720701813697815, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.28102704882621765, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.25716933608055115, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.23269197344779968, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.21694467961788177, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.20495587587356567, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.19155524671077728, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.1814500391483307, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.17135460674762726, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.16182544827461243, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.15473119914531708, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.147699236869812, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.14325037598609924, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.25892857142857145, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.27628968253968256, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.3062996031746032, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.3323412698412698, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.35143849206349204, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.3851686507936508, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.4156746031746032, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.4466765873015873, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.4739583333333333, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.49702380952380953, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.5198412698412699, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.5424107142857143, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.5662202380952381, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.5885416666666666, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.6150793650793651, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.6336805555555556, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.654265873015873, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.6822916666666666, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.7095734126984127, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.7309027777777778, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.7589285714285714, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.7854662698412699, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.8177083333333334, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.855406746031746, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.8851686507936508, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9067460317460317, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9166666666666666, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9203869047619048, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9248511904761905, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9288194444444444, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9330357142857143, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9357638888888888, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9357638888888888, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9389880952380952, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9417162698412699, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9434523809523809, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9454365079365079, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9474206349206349, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9489087301587301, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9501488095238095, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9523809523809523, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9528769841269841, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9546130952380952, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9556051587301587, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9565972222222222, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9585813492063492, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9610615079365079, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9620535714285714, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9623015873015873, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.1022598372543726, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.11281668206140294, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.13191259995153878, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.15158010537012861, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.16855490534963852, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.20022518771958367, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.2274124652608289, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.2575406232388293, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.28710814617969077, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.3112733938360714, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.33315185784043977, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.3598068188263274, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.3835361426264027, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.40588954976124375, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.43341098740324524, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.4520765760315727, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.47654704269711523, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.5106460319807529, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.5413165412194019, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.5675173734660282, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.6109573804104494, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.6571832215641306, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.7272150004153028, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.8108608846134004, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.8629308768622694, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.8957588765947341, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9103205952086472, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9145725645499458, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9196951538127449, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.924090274335725, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9286139506175068, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9312798692081885, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9312611224422327, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9346407280584886, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9363308700664348, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9383089628814181, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9402356981553879, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.94241165608041, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9441075708261495, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9456788819599221, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9477906418482321, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.948167632158158, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9501260824078014, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.951543772764804, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9524103807736717, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9540702498632373, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.956094670705746, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9567390921258743, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9573408388725365, "id_best": 48, "lr_best": 0.015, "wd_best": 0.05, "train/loss_best": 0.13011342886835336, "validation/loss_best": 0.14325037598609924, "validation/acc_best": 0.9623015873015873, "validation/f1_best": 0.9573408388725365} +{"epoch": 4, "train/lr": 0.0002701201201201201, "train/loss": 1.3480076056718826, "train/grad": 0.06355697145685553, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.937738037109375, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.92611083984375, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.906790771484375, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.887755126953125, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.868922119140625, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.8428857421875, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.813455810546875, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.78104736328125, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.7387060546875, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.693890380859375, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.650155029296875, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.58488037109375, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.5219915771484374, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.43170654296875, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.3461358642578123, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.264826354980469, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.1627447509765627, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.0442355346679686, "train/loss_018_lr3.8e-01_wd1.0e+00": 1.9139776611328125, "train/loss_019_lr4.4e-01_wd1.0e+00": 1.7956578063964843, "train/loss_020_lr5.2e-01_wd1.0e+00": 1.6539615631103515, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.5138053894042969, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.3664907455444335, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.2208798980712892, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.0836618804931641, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.940079174041748, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.8296451568603516, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.7432325077056885, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.6447775030136108, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.5519216108322144, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.4862346911430359, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.4375752866268158, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.3845225739479065, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.3464190238714218, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.30962290585041047, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.2797950941324234, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.25332284092903135, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.2322346393764019, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.21260482653975488, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.1920291915535927, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.17839032970368862, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.16777036890387534, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.1555518927052617, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.14623738300055267, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.13664678070694208, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.1276862127892673, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.12099638706073165, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.11389809848740697, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.10876678667962551, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.015116004776209592, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.01505505410488695, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.014955385108478367, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.014856139733456074, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.014757213830016554, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.014619081132113933, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.014462136435322464, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.014288401631638407, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.014062929931096733, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.013824041802436113, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.013588686711154879, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.013235310893505811, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.012893267231993378, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.012400520541705191, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.011933191604912281, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.011495908116921782, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.010963185308501124, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.010375912063755094, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.009777624695561826, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.009270048358011991, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.008697966891340912, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.00815079965395853, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.00757945439312607, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.007005090322345495, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.006447867623064667, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.005841687389183789, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.005357309587998316, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.004965748885879293, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.004505425542593002, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.004059005890740082, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0037368610221892597, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0034952178911771626, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0032300977082923054, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0030386227066628636, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.00285097420157399, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0026974906772375107, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0025588226626859977, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0024481025169370697, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.002342902448726818, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0022321043058764188, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0021565039036795497, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.002097212123335339, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0020263100048759954, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0019705082464497536, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0019129775947658344, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0018627841584384441, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0018291553171002307, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0017993912112433464, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0017804023093776777, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.922586679458618, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.908511161804199, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.8853113651275635, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.8624486923217773, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.8398525714874268, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.8086767196655273, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.7737274169921875, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.735145330429077, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.684983491897583, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.6322054862976074, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.581005573272705, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.5050177574157715, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.432295322418213, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.3289451599121094, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.231893301010132, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.1406197547912598, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.0273146629333496, "validation/loss_017_lr3.2e-01_wd1.0e+00": 1.8975584506988525, "validation/loss_018_lr3.8e-01_wd1.0e+00": 1.7573702335357666, "validation/loss_019_lr4.4e-01_wd1.0e+00": 1.6319199800491333, "validation/loss_020_lr5.2e-01_wd1.0e+00": 1.484970211982727, "validation/loss_021_lr6.1e-01_wd1.0e+00": 1.3432936668395996, "validation/loss_022_lr7.2e-01_wd1.0e+00": 1.1989054679870605, "validation/loss_023_lr8.5e-01_wd1.0e+00": 1.0606361627578735, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.9346396327018738, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.807134211063385, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.7118933796882629, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.6390351057052612, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.5576767325401306, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.48197340965270996, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.42904922366142273, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.389940083026886, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.34732866287231445, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.3166164755821228, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.28686580061912537, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.2626660466194153, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.24122250080108643, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.22415173053741455, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.2082744538784027, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.1921515315771103, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.18152812123298645, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.17353148758411407, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.16421356797218323, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.15705522894859314, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.14941523969173431, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.14249254763126373, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.13729389011859894, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.13216815888881683, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.12855210900306702, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.3246527777777778, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.34375, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.38070436507936506, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.4104662698412698, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.435515873015873, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.4645337301587302, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.4888392857142857, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.5138888888888888, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.5357142857142857, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.5597718253968254, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.5793650793650794, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.6061507936507936, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.6267361111111112, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.6537698412698413, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.6800595238095238, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.7008928571428571, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.7261904761904762, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.7527281746031746, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.7810019841269841, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.8067956349206349, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.8449900793650794, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.8802083333333334, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.8995535714285714, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9149305555555556, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9203869047619048, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9253472222222222, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9293154761904762, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9312996031746031, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9340277777777778, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9382440476190477, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9399801587301587, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9409722222222222, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9434523809523809, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9464285714285714, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9486607142857143, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9508928571428571, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9516369047619048, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9516369047619048, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9538690476190477, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9541170634920635, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9556051587301587, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9563492063492064, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.957093253968254, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9580853174603174, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9593253968253969, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9605654761904762, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9623015873015873, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9627976190476191, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9632936507936508, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.14421736139620017, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.16056853328430862, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.1949476038076366, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.2212229259400353, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.2452390394768574, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.2759518470448131, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.3017061481436149, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.32754770048291765, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.35203893252101476, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.3772531001091453, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.39730373007217873, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.42433100392487605, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.4471147991955331, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.47627096974037464, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.5074161900967116, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.5299020489140441, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.5612097470394845, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.6040168561610274, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.6517551545600758, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.7044146729367936, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.7899871406237482, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.8554379911132567, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.885516508446767, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.907678483761403, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.914124354851046, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9201177570174824, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9240564200830416, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9263773906995697, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9291549211623573, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9334541464993057, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9347301287432437, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.935328449176905, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.936990788073191, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9410061446626224, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9435840998153202, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9456147634452905, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9462586386748242, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9461540075157083, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9488230112129479, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9487077661114082, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9501414352422141, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9509172704650817, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9513077447951261, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9523308354105184, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9533151018875226, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9538802475389877, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9560378978809141, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9563118954533242, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9569555571885372, "id_best": 48, "lr_best": 0.015, "wd_best": 0.05, "train/loss_best": 0.10876678667962551, "validation/loss_best": 0.12855210900306702, "validation/acc_best": 0.9632936507936508, "validation/f1_best": 0.9569555571885372} +{"epoch": 5, "train/lr": 0.00029891323817685334, "train/loss": 1.2117191344499587, "train/grad": 0.05916368130594492, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.902669677734375, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.8859033203125, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.858502197265625, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.831341552734375, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.804661865234375, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.76795654296875, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.72681884765625, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.6816754150390625, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.6231829833984377, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.56187744140625, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.5027276611328126, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.4154351806640624, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.3324346923828125, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.215509033203125, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.1068316650390626, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.0058163452148436, "train/loss_016_lr2.7e-01_wd1.0e+00": 1.881390380859375, "train/loss_017_lr3.2e-01_wd1.0e+00": 1.7410983276367187, "train/loss_018_lr3.8e-01_wd1.0e+00": 1.5921340942382813, "train/loss_019_lr4.4e-01_wd1.0e+00": 1.4618473052978516, "train/loss_020_lr5.2e-01_wd1.0e+00": 1.312977294921875, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.1736719512939453, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.035859603881836, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.9078991508483887, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.7948804569244384, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.6834817934036255, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.6021388864517212, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.54068941116333, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.4725725042819977, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.4097165906429291, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.3656768387556076, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.33296680092811587, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.29718153476715087, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.2711829152703285, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.24570104494690895, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.22469044968485832, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.20572282500565053, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.19026074461638928, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.17566711604595184, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.16009023185819388, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.1495990039408207, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.14134580940008162, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.13175378449261188, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.12436837375164032, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.11670047674328089, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.10954336242750287, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.10421502187848092, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.09881100369617343, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.09505922192707658, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.014908564169891178, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.014822617000900208, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.014676511618308723, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.014531738851219415, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.014388021766208112, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.014190849186852574, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.013972631129436195, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.013730432409793138, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.013414237275719642, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.013081797501072287, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.012759580332785845, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.012282027201727032, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.011830633068457245, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.011207521073520183, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.010654790559783578, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.010168748907744884, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.009611265119165182, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.009026566208340227, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.00843814217718318, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.007933865732047707, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.007354020019993186, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.00679910354083404, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0062311314488761125, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.00568377401214093, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.005181563554797322, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.004668808585265651, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.00428314374294132, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.003986131310230121, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0036528504034504293, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0033406213263515385, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0031209049676544963, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0029558024159632625, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0027758868399541826, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.002643937923130579, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0025143265491351487, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0024064723786432294, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.002308572062756866, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.002228339631692506, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0021523322217399253, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.002071006480255164, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0020164303353521974, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0019704461860237644, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0019151897256961092, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0018679047294426709, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0018145168060436844, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0017654270844650454, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.001731983481149655, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.001708008529385552, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0016933359589893372, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.885411262512207, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.8661911487579346, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.834587812423706, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.8034942150115967, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.7729949951171875, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.7310497760772705, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.6843738555908203, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.633236885070801, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.5672595500946045, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.498530864715576, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.432407855987549, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.3357648849487305, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.244533061981201, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.117319345474243, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.0003576278686523, "validation/loss_015_lr2.3e-01_wd1.0e+00": 1.8924800157546997, "validation/loss_016_lr2.7e-01_wd1.0e+00": 1.7615419626235962, "validation/loss_017_lr3.2e-01_wd1.0e+00": 1.6158602237701416, "validation/loss_018_lr3.8e-01_wd1.0e+00": 1.464173674583435, "validation/loss_019_lr4.4e-01_wd1.0e+00": 1.334087610244751, "validation/loss_020_lr5.2e-01_wd1.0e+00": 1.188651204109192, "validation/loss_021_lr6.1e-01_wd1.0e+00": 1.055752158164978, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.9275590777397156, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.8112499713897705, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.7103757262229919, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.6128126382827759, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.5423447489738464, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.489518940448761, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.43124815821647644, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.3775010406970978, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.3399283289909363, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.3121267855167389, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.2815827429294586, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.2594532370567322, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.2379334717988968, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.22027255594730377, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.20457763969898224, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.19183754920959473, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.1800190508365631, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.16770102083683014, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.15957987308502197, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.15343932807445526, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.14667317271232605, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.1416880041360855, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.13691885769367218, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.13315224647521973, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.13086730241775513, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.12927371263504028, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.12909074127674103, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.38095238095238093, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.4069940476190476, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.4427083333333333, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.4722222222222222, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.4895833333333333, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.5181051587301587, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.5386904761904762, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.560515873015873, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.5850694444444444, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.6091269841269841, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.6274801587301587, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.6515376984126984, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.6753472222222222, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.7048611111111112, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.7289186507936508, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.7532242063492064, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.7782738095238095, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.8112599206349206, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.8514384920634921, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.8807043650793651, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9002976190476191, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9144345238095238, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9206349206349206, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9263392857142857, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9298115079365079, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9337797619047619, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9350198412698413, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9372519841269841, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9399801587301587, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9439484126984127, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9454365079365079, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9479166666666666, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.949156746031746, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9503968253968254, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9506448412698413, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9521329365079365, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9533730158730159, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9558531746031746, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9558531746031746, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9578373015873016, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9598214285714286, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9600694444444444, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9610615079365079, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9623015873015873, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9627976190476191, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9632936507936508, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9630456349206349, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9637896825396826, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9623015873015873, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.19615376825108904, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.21868497476141058, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.2533647233543756, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.2844668983043557, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.30307275177686616, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.33193242319340655, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.3556497128495009, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.37825626536043155, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.40255447961584007, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.42803073072786496, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.4477749690436923, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.47423128839050765, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.5031348682599782, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.5349778270042855, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.566202115226553, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.6031944230440375, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.6452943063914779, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.7163395780095833, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.8047564089395871, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.8570558206056941, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.887626011813021, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9087692653644053, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9160698989737849, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9220577894150126, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.924874719199518, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9296168886735208, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9316318574568874, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9334309221538966, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.936453286041764, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9395456871633695, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9409880570654581, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9432980897234124, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9441872196159731, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9457263601838752, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9465356268327819, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.947959207102379, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9491557096432393, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9508183053809551, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9509806244775699, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9526567058086334, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9540626089294129, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.953874166642409, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9549189110861631, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9559964644646632, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9569961465747825, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9573089583109828, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9572177898865843, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9586166569765153, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9571462497438459, "id_best": 47, "lr_best": 0.012899999999999998, "wd_best": 0.05, "train/loss_best": 0.09881100369617343, "validation/loss_best": 0.12927371263504028, "validation/acc_best": 0.9637896825396826, "validation/f1_best": 0.9586166569765153} +{"epoch": 6, "train/lr": 0.0002924170901991409, "train/loss": 1.1061773172020912, "train/grad": 0.05615853099152446, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.863994140625, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.84197021484375, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.80582763671875, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.77049072265625, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.73570068359375, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.6881683349609373, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.6353216552734375, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.5776556396484374, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.50357177734375, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.426734619140625, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.3532171630859375, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.246329345703125, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.146401672363281, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.008050537109375, "train/loss_014_lr2.0e-01_wd1.0e+00": 1.8823817443847657, "train/loss_015_lr2.3e-01_wd1.0e+00": 1.76768798828125, "train/loss_016_lr2.7e-01_wd1.0e+00": 1.6300550079345704, "train/loss_017_lr3.2e-01_wd1.0e+00": 1.4797367858886719, "train/loss_018_lr3.8e-01_wd1.0e+00": 1.3264420700073243, "train/loss_019_lr4.4e-01_wd1.0e+00": 1.1978489303588866, "train/loss_020_lr5.2e-01_wd1.0e+00": 1.0573386001586913, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.93227689743042, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.8142408275604248, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.7095973873138428, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.6203707790374756, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.5352401995658874, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.47436258316040036, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.42875980615615844, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.3786372435092926, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.33232506692409514, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.29960915982723235, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.2752895319461823, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.24825383365154266, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.22836986407637597, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.20858556717634202, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.19210899837315082, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.17701042883098125, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.16445472154766322, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.1525335183367133, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.13960464261472225, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.13075917053967714, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.12374451082199812, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.11558168768882751, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.10928165422752499, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.10285955803468823, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.09695708509534598, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.09272467376664281, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.08847134666517377, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.08575367419980466, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.014809086467139423, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.014693404412828386, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.01450122265610844, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.014313808470033109, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.014131013602018357, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.0138797711674124, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.013596447631716729, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.013287840215489267, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.012887433380819857, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.012468923954293132, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.012068494674749672, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.011493069240823389, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.010971031310036778, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.010290133105590939, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.009717640904709697, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.009229768943041563, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.008674341947771608, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.00808315138798207, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.007479295658413321, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.006961608100682497, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.006377279472071677, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.005837860940955579, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.005309998609591276, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.004825102221220731, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0043996183818671855, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.003984590611653402, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.003683490625116974, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0034553258086089046, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0032032952713780104, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0029689157276879996, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.002802606493933126, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0026777931698597967, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.002536699616466649, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0024322970077628268, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.002326129049761221, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.002235289661330171, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0021509162819711492, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.002078411018010229, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0020073457044782117, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0019268868962535634, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0018700756039470433, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0018250996008282528, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0017719886498525738, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0017321961559355259, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0016903488655225375, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0016529696926590987, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.001630574325681664, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0016181414210586808, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0016260660765692592, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.849764585494995, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.8256566524505615, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.7862141132354736, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.747551679611206, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.7097597122192383, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.658109188079834, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.6008615493774414, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.5386548042297363, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.4590351581573486, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.376770496368408, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.298572301864624, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.185412883758545, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.080183267593384, "validation/loss_013_lr1.7e-01_wd1.0e+00": 1.9355993270874023, "validation/loss_014_lr2.0e-01_wd1.0e+00": 1.805235505104065, "validation/loss_015_lr2.3e-01_wd1.0e+00": 1.687332034111023, "validation/loss_016_lr2.7e-01_wd1.0e+00": 1.5472590923309326, "validation/loss_017_lr3.2e-01_wd1.0e+00": 1.3962312936782837, "validation/loss_018_lr3.8e-01_wd1.0e+00": 1.2445027828216553, "validation/loss_019_lr4.4e-01_wd1.0e+00": 1.1192251443862915, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.9847200512886047, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.8666341304779053, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.7569640278816223, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.6607222557067871, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.579554557800293, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.5025392174720764, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.4477103650569916, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.4066642224788666, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.3616929054260254, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.3201580047607422, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.2909235656261444, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.2692834138870239, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.24533362686634064, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.22784365713596344, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.2106933444738388, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.1966582089662552, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.1839265078306198, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.17361226677894592, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.164004847407341, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.15383782982826233, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.147199809551239, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.1421637386083603, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.13637715578079224, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.13212719559669495, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.1281227469444275, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.12451992183923721, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.1220521330833435, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.11992029845714569, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.11879200488328934, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.42683531746031744, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.44990079365079366, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.4809027777777778, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.5029761904761905, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.527281746031746, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.5473710317460317, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.5714285714285714, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.589781746031746, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.6185515873015873, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.6369047619047619, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.6592261904761905, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.6877480158730159, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.7130456349206349, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.7435515873015873, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.7690972222222222, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.792906746031746, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.8266369047619048, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.8707837301587301, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.8950892857142857, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9099702380952381, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9184027777777778, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9243551587301587, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9280753968253969, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9310515873015873, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9340277777777778, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9377480158730159, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9399801587301587, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9409722222222222, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9437003968253969, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9459325396825397, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9466765873015873, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9476686507936508, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9501488095238095, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.951140873015873, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9538690476190477, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9548611111111112, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9561011904761905, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9568452380952381, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9585813492063492, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9598214285714286, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9610615079365079, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9627976190476191, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9627976190476191, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9640376984126984, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9650297619047619, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9650297619047619, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9662698412698413, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9665178571428571, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9682539682539683, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.2364972410137395, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.2600423110443553, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.29384089071548325, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.31642336712399105, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.34171616098974267, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.36448581644248773, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.3894117188905591, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.40862929390753244, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.4374756901613335, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.4584199916980444, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.4833716190820939, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.5178882903005033, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.5467519693882859, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.588109240469848, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.6293657124866144, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.6757237673244738, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.7530003106629974, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.8389926638445606, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.8798531400769339, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9009995971812966, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9134760183598296, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9202421655492097, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9237708757039955, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.926645643186016, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9298615617665518, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9336258232939111, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.935959514668174, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9362763705394125, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9386175269741381, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9407613789764481, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9415118170690626, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9427887960222725, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9454051507335415, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9460508801356372, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9488471205884453, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9501912415957133, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.951034137553025, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9520315946967637, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9535117373550425, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.95446200048747, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.955521970560983, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9569204297723831, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9568270386414294, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9588480540951758, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9599053636087805, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9594876268967452, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.960926161480751, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.96073586986874, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9626419967589763, "id_best": 48, "lr_best": 0.015, "wd_best": 0.05, "train/loss_best": 0.08575367419980466, "validation/loss_best": 0.11879200488328934, "validation/acc_best": 0.9682539682539683, "validation/f1_best": 0.9626419967589763} +{"epoch": 7, "train/lr": 0.00027969249556793234, "train/loss": 1.0320674553513527, "train/grad": 0.053268984723836184, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.830386962890625, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.803848876953125, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.76052734375, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.71814453125, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.6767413330078127, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.6204083251953123, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.557900390625, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.4902349853515626, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.4039923095703126, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.3152960205078124, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.231192932128906, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.110220642089844, "train/loss_012_lr1.4e-01_wd1.0e+00": 1.9983319091796874, "train/loss_013_lr1.7e-01_wd1.0e+00": 1.8457830810546876, "train/loss_014_lr2.0e-01_wd1.0e+00": 1.7093705749511718, "train/loss_015_lr2.3e-01_wd1.0e+00": 1.5872579956054687, "train/loss_016_lr2.7e-01_wd1.0e+00": 1.4440185546875, "train/loss_017_lr3.2e-01_wd1.0e+00": 1.2918870162963867, "train/loss_018_lr3.8e-01_wd1.0e+00": 1.1420735549926757, "train/loss_019_lr4.4e-01_wd1.0e+00": 1.020595245361328, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.8924774265289307, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.7821007156372071, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.6809989595413208, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.5935997295379639, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.520466320514679, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.45144048213958743, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.4024464416503906, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.36583763003349307, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.3255209195613861, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.28802387058734896, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.26140561282634733, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.2414590361714363, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.21906758606433868, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.20247284531593324, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.1858335965871811, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.1718333800137043, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.15887649428099393, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.14805136412382125, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.13765189863741398, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.12623456021770835, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.11839636854827404, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.1121471244841814, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.10474777437746524, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.0990051625110209, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.09315890176221728, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.08783943084999919, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.08392584826797247, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.08020679503679276, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.07786750277504324, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.014582026004791259, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.0144384350720793, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.014204835849814117, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.01397770970594138, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.013754495638422667, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.013446462731808424, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.01310520303901285, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.012732286779209971, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.012254825327545404, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.01176547447219491, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.01131137658841908, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.010684163980185986, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.010140632782131433, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.009461616231128574, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.008901005785446614, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.008421336035244167, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.007865697611123323, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.00727095399517566, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.006668729765806347, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.006164278695359826, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.00561329354532063, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.005122323574032635, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.004658251197542995, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.004246017712866887, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0038938306097406894, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0035564341139979663, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.003314324488164857, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0031323843263089657, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.002931493459036574, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0027433992165606467, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.002608397293370217, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0025060116348322482, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.002389607215882279, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.00230203939427156, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.00221142802212853, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0021328155946685, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0020574655826203526, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0019931484886910765, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0019277998834149911, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.001852291650720872, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0017984968863311223, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0017543318471871317, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0016994305088883265, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.001656254095141776, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0016147890617139637, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0015790603760979138, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0015584632428362966, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0015519522214890457, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0015623768389923499, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.8162171840667725, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.787601947784424, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.740935802459717, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.695466995239258, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.651073455810547, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.5907773971557617, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.524338483810425, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.452465772628784, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.3611879348754883, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.2678000926971436, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.1798274517059326, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.0537524223327637, "validation/loss_012_lr1.4e-01_wd1.0e+00": 1.9379940032958984, "validation/loss_013_lr1.7e-01_wd1.0e+00": 1.7813150882720947, "validation/loss_014_lr2.0e-01_wd1.0e+00": 1.642441749572754, "validation/loss_015_lr2.3e-01_wd1.0e+00": 1.5192763805389404, "validation/loss_016_lr2.7e-01_wd1.0e+00": 1.3762019872665405, "validation/loss_017_lr3.2e-01_wd1.0e+00": 1.2262059450149536, "validation/loss_018_lr3.8e-01_wd1.0e+00": 1.080599308013916, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.9639298915863037, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.8422467708587646, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.7386720180511475, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.6445133686065674, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.5635952949523926, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.4962998628616333, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.432981938123703, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.38822296261787415, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.3547879755496979, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.3180007040500641, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.28386157751083374, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.25981035828590393, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.2418731153011322, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.22200199961662292, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.2074289172887802, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.19303803145885468, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.1811150312423706, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.17032799124717712, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.1616193950176239, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.15368936955928802, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.1457425355911255, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.1409701108932495, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.13744957745075226, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.13323044776916504, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.12982630729675293, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.12596368789672852, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.12240785360336304, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.12002315372228622, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.11798127740621567, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.11674180626869202, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.45610119047619047, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.4791666666666667, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.5059523809523809, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.5302579365079365, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.548859126984127, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.5744047619047619, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.59375, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.6195436507936508, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.6411210317460317, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.6639384920634921, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.6870039682539683, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.7175099206349206, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.7428075396825397, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.7735615079365079, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.8043154761904762, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.8340773809523809, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.8732638888888888, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.8960813492063492, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9126984126984127, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9174107142857143, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9243551587301587, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9288194444444444, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9327876984126984, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9340277777777778, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9379960317460317, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9402281746031746, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9434523809523809, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9444444444444444, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9466765873015873, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9481646825396826, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.949156746031746, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9513888888888888, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9523809523809523, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9543650793650794, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9553571428571429, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9573412698412699, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9583333333333334, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9590773809523809, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9593253968253969, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9605654761904762, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9613095238095238, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9615575396825397, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9605654761904762, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9618055555555556, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9632936507936508, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9655257936507936, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9662698412698413, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9677579365079365, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9672619047619048, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.26601903560835016, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.292488931164313, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.3191589356806471, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.3461646257042437, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.3668023437407933, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.39143323587301093, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.41351801364775137, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.4384865781530508, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.46258039883996827, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.4900424440698424, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.5159613035324351, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.5521722671430366, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.5850524367429318, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.635573768098072, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.6974974777997174, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.7665077058544865, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.8431170325665123, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.8799090288631097, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9051485680572298, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9117351658421518, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9192529291452127, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.924026013425142, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.928874712773053, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9298652320784548, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9334902368881889, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9352881215222979, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9385682098174751, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9395538696409838, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.941799104272347, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.94365167106722, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9445571118808184, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9471334342881206, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9476884472867072, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9495869177802441, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9504710583345506, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9528457258741305, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9533820744862185, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9540380250771204, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9543874773202775, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9557838574462623, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9565186742000613, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9567180263223417, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9553268146773306, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9564990163459612, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9582886677018037, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9606059909509655, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9611229904977338, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9627325016705179, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.961827438106902, "id_best": 47, "lr_best": 0.012899999999999998, "wd_best": 0.05, "train/loss_best": 0.08020679503679276, "validation/loss_best": 0.11798127740621567, "validation/acc_best": 0.9677579365079365, "validation/f1_best": 0.9627325016705179} +{"epoch": 8, "train/lr": 0.0002612959497061927, "train/loss": 0.9735064515471459, "train/grad": 0.05106607649475336, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.797470703125, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.766483154296875, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.7160693359375, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.666890869140625, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.6191058349609375, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.5541656494140623, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.482728271484375, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.405902099609375, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.3085845947265624, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.2093472290039062, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.1161093139648437, "train/loss_011_lr1.2e-01_wd1.0e+00": 1.9834014892578125, "train/loss_012_lr1.4e-01_wd1.0e+00": 1.8622569274902343, "train/loss_013_lr1.7e-01_wd1.0e+00": 1.6994754028320314, "train/loss_014_lr2.0e-01_wd1.0e+00": 1.5566487884521485, "train/loss_015_lr2.3e-01_wd1.0e+00": 1.4313519287109375, "train/loss_016_lr2.7e-01_wd1.0e+00": 1.2876543045043944, "train/loss_017_lr3.2e-01_wd1.0e+00": 1.1393632888793945, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.9976423072814942, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.8861885166168213, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.7716035842895508, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.6753596496582032, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.589048261642456, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.5156337475776672, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.454890695810318, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.39799206852912905, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.35761143147945407, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.3274047338962555, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.29404078543186185, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.26279834866523744, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.24043106600642206, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.223462792634964, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.20429783158004283, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.18992568038403987, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.17532597471028566, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.16288858212530613, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.15123473599553108, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.14138576425611973, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.13180177809670568, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.1212053295597434, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.11385931801050901, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.10788400411605835, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.10088204683735967, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.09541304470971226, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.08975982831791043, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.08461662990041077, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.08102596707642079, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.0776214649528265, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.0755720154196024, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.01438932347111404, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.014222372891381382, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.013953399700112641, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.0136879238858819, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.013427106318995357, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.013072365340776741, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.012679339665919543, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.012253065300174058, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.011714916457422078, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.011179114188998938, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.010695075821131468, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.01004966642241925, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.009508656300604344, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.008839619946666061, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.008283903824631124, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.007802551605273038, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.007245651793200522, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.006654414441436529, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.006068295510485769, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.005588422827422619, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.005076812189072371, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.004632254838943481, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.00422144676791504, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0038640017062425615, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0035632859764155, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0032787863432895393, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.003074669280322269, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.002921303258044645, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0027509637631010263, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0025898443278856574, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.002473035076400265, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0023834071221062914, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.00227929605927784, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0021999177022371443, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0021164039842551576, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.002042775598820299, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0019718396908137946, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0019102519028820098, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0018485676328418776, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.001779703532520216, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0017323499801568686, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.001694377582753077, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.001648685350373853, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.001609663594281301, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.001564051776076667, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0015227751006023026, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0014985994662856683, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0014843859674874692, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0014882540141115896, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.785431146621704, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.752774953842163, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.6996307373046875, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.6480443477630615, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.5978596210479736, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.5299930572509766, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.455526351928711, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.37546968460083, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.2745068073272705, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.1720848083496094, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.0762994289398193, "validation/loss_011_lr1.2e-01_wd1.0e+00": 1.940287470817566, "validation/loss_012_lr1.4e-01_wd1.0e+00": 1.816684603691101, "validation/loss_013_lr1.7e-01_wd1.0e+00": 1.6517267227172852, "validation/loss_014_lr2.0e-01_wd1.0e+00": 1.508086085319519, "validation/loss_015_lr2.3e-01_wd1.0e+00": 1.3830667734146118, "validation/loss_016_lr2.7e-01_wd1.0e+00": 1.2407326698303223, "validation/loss_017_lr3.2e-01_wd1.0e+00": 1.095206618309021, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.9576693773269653, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.8501901030540466, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.7405307292938232, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.6489205956459045, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.5670261979103088, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.497526079416275, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.4400187134742737, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.38615667819976807, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.34794294834136963, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.31951314210891724, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.28816744685173035, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.25904980301856995, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.23841255903244019, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.22286444902420044, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.2056296169757843, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.19289670884609222, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.1803499311208725, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.16988472640514374, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.16040408611297607, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.1527627855539322, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.14556239545345306, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.13809987902641296, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.13340194523334503, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.12980054318904877, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.12585100531578064, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.12310559302568436, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.12058384716510773, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.11850829422473907, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.11727003008127213, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.11653762310743332, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.11623865365982056, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.4816468253968254, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.49851190476190477, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.5290178571428571, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.5478670634920635, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.5704365079365079, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.589781746031746, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.6185515873015873, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.636656746031746, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.6617063492063492, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.6875, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.7108134920634921, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.7388392857142857, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.7673611111111112, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.7996031746031746, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.8375496031746031, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.8702876984126984, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.8916170634920635, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9109623015873016, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.917906746031746, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9233630952380952, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9288194444444444, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9322916666666666, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9347718253968254, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9379960317460317, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9402281746031746, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9434523809523809, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9456845238095238, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9466765873015873, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9479166666666666, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.949156746031746, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9501488095238095, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9523809523809523, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9528769841269841, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.955109126984127, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9565972222222222, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9585813492063492, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9605654761904762, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9615575396825397, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9615575396825397, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9625496031746031, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9630456349206349, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9637896825396826, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9655257936507936, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9655257936507936, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9657738095238095, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9665178571428571, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9682539682539683, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9677579365079365, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9675099206349206, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.2944957321063995, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.31257006401564214, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.3445452825688424, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.3670976076210546, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.38777615366992874, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.4107373322827915, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.43765068031793775, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.4588191685107069, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.4870625471691094, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.5171644763857579, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.5447733648542838, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.5798056620927975, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.6260213402149444, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.6895332746447755, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.7740556282082673, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.8371886131486113, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.8722787892827865, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9031178724745826, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9119307781013223, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9179097225620148, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9242505686054938, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9279856261971637, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9305719386584159, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.933880331109384, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9359541291700536, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9391022558963953, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9406084577187912, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.941707697959481, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9432502673062076, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9446054520060921, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9459723638398022, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9479710403570193, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.948308401482687, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9498447671958824, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9514730966892603, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9534578829202702, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9551631873155361, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9560583692280198, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9559407713417214, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9569036899735606, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9567780373762046, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9571566007150785, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9594532339702353, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9592643045353219, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9594438593783055, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9604300105741285, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9626606193809198, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9623557578039408, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9626468789442081, "id_best": 46, "lr_best": 0.010799999999999999, "wd_best": 0.05, "train/loss_best": 0.08102596707642079, "validation/loss_best": 0.11727003008127213, "validation/acc_best": 0.9682539682539683, "validation/f1_best": 0.9626606193809198} +{"epoch": 9, "train/lr": 0.00023803200426111704, "train/loss": 0.9216110944747925, "train/grad": 0.04921656234189868, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.769178466796875, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.734420166015625, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.6779351806640626, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.623125, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.570029296875, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.4981146240234375, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.4194140625, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.335037841796875, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.2288632202148437, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.121507263183594, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.021264953613281, "train/loss_011_lr1.2e-01_wd1.0e+00": 1.8795059204101563, "train/loss_012_lr1.4e-01_wd1.0e+00": 1.75136962890625, "train/loss_013_lr1.7e-01_wd1.0e+00": 1.581387481689453, "train/loss_014_lr2.0e-01_wd1.0e+00": 1.4348114013671875, "train/loss_015_lr2.3e-01_wd1.0e+00": 1.3083055877685548, "train/loss_016_lr2.7e-01_wd1.0e+00": 1.1661545944213867, "train/loss_017_lr3.2e-01_wd1.0e+00": 1.0227504348754883, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.8890480327606202, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.7859681034088135, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.6819462394714355, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.5960081529617309, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.5197369146347046, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.45533531069755556, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.4022277498245239, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.35244323253631593, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.31712704539299014, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.29063452005386353, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.26111445277929307, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.23329438894987106, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.21325038135051727, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.19795647896826268, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.18055440805852413, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.16739540450274945, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.15396734699606895, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.1424598463252187, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.13162680711597205, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.12249517865478993, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.11355172196403146, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.1037994758784771, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.09708762094378472, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.09178565981797875, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.08560145433060824, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.08096364710479975, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.07625203320756554, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.07205419202335178, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.06912428705953061, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.06637541918084025, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.06458396001718938, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.014219006118364632, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.01403354485053569, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.01372849584557116, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.013429903318174183, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.01313778226263821, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.012742531411349773, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.012305434574373067, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.011838041990995408, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.011261256407015025, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.010701081501320004, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.010207798308692872, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.009566052793525159, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.009032747694291174, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.008365949285216629, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.007802787930704653, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.007313076942227781, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.006749233666341752, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.006160855621565133, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.005590064655989408, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.005134443189017474, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.00465862687677145, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.004253924881340936, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0038863001402933152, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.003570184918353334, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0033056321437470613, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0030542541074100884, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0028740472404751925, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.002736527522210963, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.002582111349911429, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.002433308410109021, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0023242882621707394, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0022393373056547716, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0021382147195981816, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0020602249074727296, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0019768769678194078, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0019044019712600856, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0018325873999856413, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0017695073928916828, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0017059408692875876, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0016329960580333137, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0015822853430290705, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0015414211599272677, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0014922980070696213, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0014562555542215706, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0014194548965315334, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0013904468226246536, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0013714425213402137, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.001355864874785766, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0013431476915138775, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.75766921043396, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.7214772701263428, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.6626460552215576, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.6057374477386475, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.5505735874176025, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.4761202335357666, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.3948843479156494, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.3079917430877686, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.199094772338867, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.089411735534668, "validation/loss_010_lr1.0e-01_wd1.0e+00": 1.987257719039917, "validation/loss_011_lr1.2e-01_wd1.0e+00": 1.8436259031295776, "validation/loss_012_lr1.4e-01_wd1.0e+00": 1.7144449949264526, "validation/loss_013_lr1.7e-01_wd1.0e+00": 1.5442720651626587, "validation/loss_014_lr2.0e-01_wd1.0e+00": 1.3984792232513428, "validation/loss_015_lr2.3e-01_wd1.0e+00": 1.2735992670059204, "validation/loss_016_lr2.7e-01_wd1.0e+00": 1.1341115236282349, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.9944795370101929, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.8652496933937073, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.7660703659057617, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.6664580702781677, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.5844460129737854, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.5118741393089294, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.45060211420059204, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.40016213059425354, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.35309287905693054, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.3196830451488495, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.2947830855846405, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.26726198196411133, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.241609588265419, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.22344179451465607, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.20974771678447723, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.19440586864948273, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.18329161405563354, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.17202645540237427, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.16280336678028107, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.15451228618621826, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.14785808324813843, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.1418484002351761, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.13569201529026031, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.13189421594142914, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.12913770973682404, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.12627549469470978, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.12428340315818787, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.1225818619132042, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.1210964024066925, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.12021735310554504, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.11898597329854965, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.11767231673002243, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.4965277777777778, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.5183531746031746, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.5401785714285714, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.5672123015873016, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.5818452380952381, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.6096230158730159, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.6312003968253969, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.6537698412698413, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.6793154761904762, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.7068452380952381, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.7286706349206349, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.7604166666666666, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.7859623015873016, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.8266369047619048, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.8668154761904762, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.8881448412698413, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9050099206349206, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9159226190476191, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9228670634920635, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9278273809523809, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9317956349206349, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9342757936507936, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9377480158730159, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9397321428571429, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9427083333333334, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9454365079365079, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9476686507936508, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9476686507936508, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9481646825396826, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.951140873015873, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9521329365079365, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.953125, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9553571428571429, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9553571428571429, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9575892857142857, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9600694444444444, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9603174603174603, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9600694444444444, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9598214285714286, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9605654761904762, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9615575396825397, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9615575396825397, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9618055555555556, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9627976190476191, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9635416666666666, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9645337301587301, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9637896825396826, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9642857142857143, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.964781746031746, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.31017558280526125, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.3333628301517109, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.3582099483816909, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.3851469833991462, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.40158051857603894, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.4285814344130171, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.45269456213770287, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.47766172457314066, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.5084933479653289, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.5394474255790471, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.5671444765969115, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.6152925073945844, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.6601923524742856, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.7512932583794901, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.8312201872631604, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.8664045072011133, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.8941039531779101, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9091045748449996, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9174339745422024, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9225530885845628, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.927392104904092, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9302501367663613, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9333768817357686, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.935255916592822, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9380221656222781, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9401260049788608, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9428847021528626, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9434242100065379, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9437636264469428, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9466090441180306, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9479189903695178, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9485634719444695, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9510565292488206, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.951012713041242, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9531787626817461, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9550140471350093, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9555162887579878, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9549857842357116, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9547518096281111, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9555544576780673, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9561891404272219, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9563062363228736, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9575113121194092, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9587334391778084, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9590995491914308, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9599891746629801, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9594725885363476, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.959789704688839, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.960418535682609, "id_best": 48, "lr_best": 0.015, "wd_best": 0.05, "train/loss_best": 0.06458396001718938, "validation/loss_best": 0.11767231673002243, "validation/acc_best": 0.964781746031746, "validation/f1_best": 0.960418535682609} +{"epoch": 10, "train/lr": 0.00021091808096876188, "train/loss": 0.8819177255034447, "train/grad": 0.04810653131455183, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.742347412109375, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.704267578125, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.642314453125, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.5823565673828126, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.5244866943359376, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.446199951171875, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.36097900390625, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.2699575805664063, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.156219177246094, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.0416384887695314, "train/loss_010_lr1.0e-01_wd1.0e+00": 1.93553466796875, "train/loss_011_lr1.2e-01_wd1.0e+00": 1.786678466796875, "train/loss_012_lr1.4e-01_wd1.0e+00": 1.6533495330810546, "train/loss_013_lr1.7e-01_wd1.0e+00": 1.4789977264404297, "train/loss_014_lr2.0e-01_wd1.0e+00": 1.3310447692871095, "train/loss_015_lr2.3e-01_wd1.0e+00": 1.2055069351196288, "train/loss_016_lr2.7e-01_wd1.0e+00": 1.066771354675293, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.9295747756958008, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.8040893840789795, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.7089895582199097, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.6144356679916382, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.5373251605033874, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.469535311460495, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.4125330698490143, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.3657245010137558, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.3219330960512161, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.2907847434282303, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.267438580095768, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.2412898363173008, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.2166290335357189, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.19867760717868804, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.18494982406497001, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.16928060822188853, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.1573398209363222, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.14516561277210713, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.13462358061224222, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.12464999102056026, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.11623292921110988, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.10797645123675466, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.09882947269827128, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.0925038685463369, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.0874481429066509, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.0815404986217618, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.07697676138952375, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.0724332461412996, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.06827741302549839, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.06532555596902967, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.06238084049895406, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.0604242698289454, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.014178561763837933, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.013975113541819155, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.013638709518127144, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.013309608967974782, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.012990769250318408, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.012556185047142208, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.012079533231444657, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.011576506495475768, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.010966554544866084, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.010387390260584653, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.009886777945794165, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.00924246036913246, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.008706254761200398, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.008027637857012451, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.007452728708740324, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.006954735915642231, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.006388032112736255, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.005806697155348956, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.005253387377597392, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.004819306517019868, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.004373787499498576, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.003999542794190347, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.003663599643623456, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.003375086592277512, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.003135173988994211, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0029068148019723594, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0027423662872752175, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0026171676884405317, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.002474807706894353, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0023377382662147284, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.002235725072096102, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0021567473752656953, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0020639070903416723, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.001990619512507692, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0019141958106774837, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0018453585967654362, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0017783942818641663, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.00171969201794127, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0016594013987923971, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0015905802353518084, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0015406034572515636, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.00149967645178549, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.001450592970359139, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.001413877872109879, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.001376018989831209, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.001344113695959095, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0013244433351792394, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0013057800437672996, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0012944422459986527, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.7334160804748535, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.694149971008301, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.6304402351379395, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.5689146518707275, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.5095036029815674, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.429558038711548, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.342660903930664, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.250194787979126, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.134727954864502, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.0191702842712402, "validation/loss_010_lr1.0e-01_wd1.0e+00": 1.912213683128357, "validation/loss_011_lr1.2e-01_wd1.0e+00": 1.7627817392349243, "validation/loss_012_lr1.4e-01_wd1.0e+00": 1.6295909881591797, "validation/loss_013_lr1.7e-01_wd1.0e+00": 1.456275224685669, "validation/loss_014_lr2.0e-01_wd1.0e+00": 1.3100687265396118, "validation/loss_015_lr2.3e-01_wd1.0e+00": 1.1865324974060059, "validation/loss_016_lr2.7e-01_wd1.0e+00": 1.050668716430664, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.9170240163803101, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.7951869368553162, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.7031146883964539, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.6117558479309082, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.5371825695037842, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.47154706716537476, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.41644230484962463, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.3710798919200897, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.3287383019924164, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.2987395226955414, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.27621832489967346, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.25132063031196594, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.22799843549728394, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.2113708108663559, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.19889171421527863, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.18481920659542084, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.1744356006383896, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.1641109436750412, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.15553301572799683, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.14772823452949524, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.1415165215730667, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.13582317531108856, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.12994733452796936, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.12632408738136292, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.1234903633594513, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.1206943616271019, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.11874323338270187, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.11712822318077087, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.11604369431734085, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.11540327966213226, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.11499336361885071, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.1147608533501625, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.5096726190476191, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.5305059523809523, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.5548115079365079, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.5766369047619048, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.5939980158730159, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.6232638888888888, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.6433531746031746, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.6659226190476191, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.6959325396825397, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.7214781746031746, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.7452876984126984, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.7743055555555556, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.8033234126984127, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.8489583333333334, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.8839285714285714, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9012896825396826, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9136904761904762, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9211309523809523, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9275793650793651, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9312996031746031, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9332837301587301, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.935515873015873, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9384920634920635, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9429563492063492, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9446924603174603, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9461805555555556, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9479166666666666, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9481646825396826, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9494047619047619, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9523809523809523, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9546130952380952, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9561011904761905, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.957093253968254, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9580853174603174, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9600694444444444, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9615575396825397, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9620535714285714, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9623015873015873, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9642857142857143, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9655257936507936, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9655257936507936, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9660218253968254, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9672619047619048, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9670138888888888, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9675099206349206, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9670138888888888, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9665178571428571, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.966765873015873, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9665178571428571, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.3247187693278392, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.3472662120661352, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.37533433501502256, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.3964775481549981, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.41503314640937156, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.4441141658880687, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.4672394779694878, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.4931004119812888, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.5264453615234337, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.5580463691847337, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.59111636176274, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.6373016637435347, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.6978155112847666, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.8000626285586042, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.8603809438656362, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.8883470350287442, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9071008034368824, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9154065021028621, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9229737585850253, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9270406662147253, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9292796199021948, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9313199393453292, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.934434985015808, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9386123490432089, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9400933634195141, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9415590305613245, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9431778710234685, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.943472056767459, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9452582553575282, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9480968953942115, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9501946746001347, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9513049186388892, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9523125844613961, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9527817946605444, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.954447085126903, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9559448963614336, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.956734386635954, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9564301179343297, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9578121603990091, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.95922324752082, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9594029544962576, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.959749829857383, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9611070899172198, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.961335785334382, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9613350833043034, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9605558110414928, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9596355300925843, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9610384528685052, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9614800952294664, "id_best": 44, "lr_best": 0.0078, "wd_best": 0.05, "train/loss_best": 0.0724332461412996, "validation/loss_best": 0.11712822318077087, "validation/acc_best": 0.9675099206349206, "validation/f1_best": 0.9613350833043034} +{"epoch": 11, "train/lr": 0.00018113997589164516, "train/loss": 0.8553669047355652, "train/grad": 0.04673364603891969, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.7210302734375, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.6801873779296876, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.614105224609375, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.5502685546875, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.4885101318359375, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.4057586669921873, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.3157257080078124, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.220073547363281, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.1009185791015623, "train/loss_009_lr8.7e-02_wd1.0e+00": 1.9816415405273438, "train/loss_010_lr1.0e-01_wd1.0e+00": 1.8715248107910156, "train/loss_011_lr1.2e-01_wd1.0e+00": 1.7181376647949218, "train/loss_012_lr1.4e-01_wd1.0e+00": 1.5819908142089845, "train/loss_013_lr1.7e-01_wd1.0e+00": 1.4057386779785157, "train/loss_014_lr2.0e-01_wd1.0e+00": 1.2583405685424804, "train/loss_015_lr2.3e-01_wd1.0e+00": 1.1348138046264649, "train/loss_016_lr2.7e-01_wd1.0e+00": 1.000179557800293, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.8689482784271241, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.7507234668731689, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.6621432733535767, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.5748156213760376, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.5039954829216003, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.44187435150146487, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.389838217496872, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.34699422955513, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.3067620402574539, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.27807326197624205, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.2564172729849815, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.23212014377117157, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.20896376118063928, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.19213746897876263, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.17912779353559016, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.16416181415319442, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.1527669632807374, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.14107477348297834, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.13090056266635655, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.12126800505444407, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.11307908371090888, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.10508057548664511, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.09611421624198556, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.08987327978014946, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.08491010294295848, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.07909695168957115, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.07460855563171208, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.07006061097607016, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.06600537477992476, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.06312000803649426, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.060361127303913235, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.05861698749475181, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.014001660873182118, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.013779065390117466, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.013414946589618922, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.013061982789076864, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.012718601617962122, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.01225248318631202, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.011748339948244393, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.011222840845584869, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.010598245086148381, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.010017978330142795, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.009524169862270355, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.008889724472537637, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.008357695508748294, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.007679878503549844, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.007104245712980628, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.006607217437122017, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.006046707951463759, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.005477529733907431, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.00494399641174823, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.004529917368199676, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.004111277817282826, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.003763865577057004, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.003455215623835102, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0031939218926709144, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0029776914918329565, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.002773975236341357, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0026280866912566127, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.002517315764562227, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0023914337944006547, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.002268586699501611, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.002177403186797164, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.002105810496141203, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.002019397252006456, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0019524228613590822, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.001879643876454793, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0018144819198641926, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0017488417355343699, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.001690214998088777, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0016308213211596013, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0015608915351913312, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0015101063015754335, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0014673956730985082, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0014181127658230252, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0013796118830214255, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0013421141034632455, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0013136806988040916, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.001297277073317673, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0012873877308447845, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0012833706356468611, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.7127511501312256, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.670855760574341, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.603107452392578, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.537789821624756, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.4748497009277344, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.3904151916503906, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.2989587783813477, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.201869487762451, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.0814502239227295, "validation/loss_009_lr8.7e-02_wd1.0e+00": 1.9611681699752808, "validation/loss_010_lr1.0e-01_wd1.0e+00": 1.8505384922027588, "validation/loss_011_lr1.2e-01_wd1.0e+00": 1.6968870162963867, "validation/loss_012_lr1.4e-01_wd1.0e+00": 1.5610218048095703, "validation/loss_013_lr1.7e-01_wd1.0e+00": 1.3859219551086426, "validation/loss_014_lr2.0e-01_wd1.0e+00": 1.2401949167251587, "validation/loss_015_lr2.3e-01_wd1.0e+00": 1.1185903549194336, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.9863283634185791, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.857959508895874, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.7425775527954102, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.6561956405639648, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.5711182951927185, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.5022464394569397, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.44188252091407776, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.39138853549957275, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.3498907685279846, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.31106504797935486, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.28357696533203125, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.2629829943180084, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.24008093774318695, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.21860986948013306, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.20327222347259521, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.19165688753128052, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.17859995365142822, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.16891366243362427, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.15934528410434723, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.15143240988254547, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.14417648315429688, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.13852213323116302, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.13338561356067657, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.12813732028007507, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.12487779557704926, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.12252669781446457, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.11991956830024719, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.11823663115501404, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.1167355328798294, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.11570698767900467, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.11524148285388947, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.11528845876455307, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.11558402329683304, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.5220734126984127, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.5372023809523809, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.5674603174603174, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.5845734126984127, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.6068948412698413, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.6284722222222222, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.6530257936507936, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.6768353174603174, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.7063492063492064, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.7316468253968254, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.7559523809523809, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.7872023809523809, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.8199404761904762, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.8685515873015873, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.8933531746031746, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9077380952380952, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9184027777777778, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9231150793650794, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9290674603174603, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9325396825396826, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9337797619047619, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9365079365079365, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9402281746031746, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9439484126984127, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9449404761904762, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9474206349206349, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9484126984126984, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9494047619047619, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9506448412698413, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9536210317460317, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9543650793650794, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9561011904761905, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9565972222222222, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9585813492063492, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9605654761904762, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9613095238095238, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9627976190476191, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9635416666666666, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.964781746031746, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9652777777777778, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9660218253968254, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9665178571428571, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.966765873015873, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9672619047619048, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9677579365079365, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9677579365079365, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9665178571428571, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9662698412698413, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9657738095238095, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.337433670676256, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.3557325948527679, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.38689160687834734, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.4058004426428474, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.4286346397999903, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.450291014236489, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.4783692196487631, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.5075732471225708, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.540448366872666, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.5702251752312489, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.6093892407175712, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.6645353179311765, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.7387902459624461, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.8371929493895687, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.8765480035371195, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.899179046574781, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9127740290421916, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9173602919768873, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9247716086484749, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9279243773654086, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9301147907441212, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9322891108030675, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9361770164623694, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9390195280893159, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9402160301332343, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9423820694115393, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9434476731280473, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9442850758912383, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9460783949086488, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9493645101287852, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9500177920113745, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9518108652010514, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9517880358106003, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9535144678314964, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.955244760936524, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9564487676218147, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9574246053190533, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.957451942129956, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9588400427395, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9593206584922543, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.959827696818356, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9605089644287842, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9610560226297008, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9614645676370401, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.961864864459962, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9619952057726419, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.960794071551266, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9603766299063181, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9600719605923959, "id_best": 44, "lr_best": 0.0078, "wd_best": 0.05, "train/loss_best": 0.07006061097607016, "validation/loss_best": 0.1167355328798294, "validation/acc_best": 0.9677579365079365, "validation/f1_best": 0.961864864459962} +{"epoch": 12, "train/lr": 0.0001499999999999999, "train/loss": 0.8270362496376038, "train/grad": 0.04609653983265161, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.699527587890625, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.65611328125, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.5857623291015623, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.5180133056640623, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.4527667236328123, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.3653594970703127, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.2707135009765627, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.170423583984375, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.046134338378906, "train/loss_009_lr8.7e-02_wd1.0e+00": 1.92236572265625, "train/loss_010_lr1.0e-01_wd1.0e+00": 1.8086766052246093, "train/loss_011_lr1.2e-01_wd1.0e+00": 1.6513086700439452, "train/loss_012_lr1.4e-01_wd1.0e+00": 1.5128358459472657, "train/loss_013_lr1.7e-01_wd1.0e+00": 1.3355335235595702, "train/loss_014_lr2.0e-01_wd1.0e+00": 1.1889479446411133, "train/loss_015_lr2.3e-01_wd1.0e+00": 1.0675683212280274, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.936795654296875, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.8109316253662109, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.6988522815704346, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.6156999778747558, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.5343025493621826, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.4686343860626221, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.41135475397109983, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.3634426373243332, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.32397606849670413, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.28704647183418275, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.26055078774690626, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.24056082889437674, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.21809739485383034, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.19655933924019336, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.18078501030802727, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.1685883156955242, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.1544833990931511, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.1436567883938551, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.13245227731764317, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.12266994498670102, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.11341697724536061, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.10554455153644085, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.09778754407539964, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.08923505927436054, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.08336290233768523, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.07865918197669089, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.07311015863902867, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.06889193188399076, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.06467054958455265, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.06087259526364505, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.058141810093075036, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.05558957154862583, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.05400297570973635, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.013946960964240133, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.013709919797256588, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.013324865251779556, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.012951193992048502, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.012588555635884404, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.012099524750374258, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.011574911000207067, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.011036332575604319, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.010406731623224913, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.009829564304091036, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.009342202688567341, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.008713252046145498, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.008179517048411071, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.007494616510812193, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.006912758520338684, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.006414109184406698, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.0058576991781592366, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.005299791854340583, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.004783963022055105, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.004389884419506416, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.003995668719289825, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.003672413198510185, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0033866799820680173, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.003145608324557543, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.002946652767714113, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.002757337914663367, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.002620291372295469, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0025147840240970255, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.002393411546945572, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0022734878002665937, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.00218203671684023, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0021090733929304407, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.002021806727279909, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0019519093632698059, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.001877701831399463, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0018098191462922841, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0017429046047618612, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0016835101533797569, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.00162288359424565, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0015520506401662715, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0015017945412546397, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0014598287382978014, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0014095172577071936, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.001369818414677866, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0013311005226569251, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0012964919887599536, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0012712964173988439, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.001250096513540484, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0012415932602016255, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.6958155632019043, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.6517841815948486, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.5806691646575928, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.5123796463012695, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.446614980697632, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.358578681945801, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.263437509536743, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.162876605987549, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.0383222103118896, "validation/loss_009_lr8.7e-02_wd1.0e+00": 1.914470911026001, "validation/loss_010_lr1.0e-01_wd1.0e+00": 1.8010691404342651, "validation/loss_011_lr1.2e-01_wd1.0e+00": 1.6443229913711548, "validation/loss_012_lr1.4e-01_wd1.0e+00": 1.506587266921997, "validation/loss_013_lr1.7e-01_wd1.0e+00": 1.330889105796814, "validation/loss_014_lr2.0e-01_wd1.0e+00": 1.1858618259429932, "validation/loss_015_lr2.3e-01_wd1.0e+00": 1.066127061843872, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.9372018575668335, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.8132860064506531, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.7030194997787476, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.6211393475532532, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.5409879684448242, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.47621044516563416, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.419884592294693, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.37258440256118774, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.333896279335022, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.2976877689361572, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.27200230956077576, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.25266212224960327, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.23128780722618103, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.21114036440849304, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.1967490166425705, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.1857515126466751, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.1735864281654358, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.16450771689414978, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.15547914803028107, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.14799818396568298, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.14117677509784698, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.1356356143951416, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.13064715266227722, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.12560062110424042, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.12244029343128204, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.12016632407903671, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.11781556904315948, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.11632885783910751, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.11481758952140808, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.11373943835496902, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.11318845301866531, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.1128101795911789, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.11283933371305466, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.5287698412698413, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.5443948412698413, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.5734126984126984, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.5910218253968254, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.6158234126984127, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.6341765873015873, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.6607142857142857, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.6832837301587301, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.7152777777777778, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.7405753968253969, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.7661210317460317, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.7973710317460317, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.8325892857142857, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.8802083333333334, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9002976190476191, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9126984126984127, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9196428571428571, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9246031746031746, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9305555555555556, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9330357142857143, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.935515873015873, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9375, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9419642857142857, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9441964285714286, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9451884920634921, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9479166666666666, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9484126984126984, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.951140873015873, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9523809523809523, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9543650793650794, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9558531746031746, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9563492063492064, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9563492063492064, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9608134920634921, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9613095238095238, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9630456349206349, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9640376984126984, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9640376984126984, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9657738095238095, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9660218253968254, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9672619047619048, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9672619047619048, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9680059523809523, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9685019841269841, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.96875, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9685019841269841, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9682539682539683, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.96875, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9680059523809523, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.3449050290738062, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.3629698354575426, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.3930803163031673, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.41257947286187635, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.4361926592522095, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.45757546006883987, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.4872716497639625, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.514327805135431, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.5507931633744759, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.5843534375899365, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.6257718289004474, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.6861384080827081, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.7668181587504037, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.855583169475191, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.8868569379687717, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9052490246673647, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9139328634638876, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9197044954325045, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9261687945587685, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9287276677560402, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9312806807358223, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9335166036254082, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9376865574426774, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9397578899566907, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9404746008900747, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9430465259248977, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9439940801072595, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9466123330453853, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9480998179749757, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9496473082332499, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9510373754171214, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.951879290716631, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9513252044698115, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9547224407109558, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9557511469357096, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9572339381929448, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9580482062720602, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9579408955941204, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9600191927181688, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9603336021232997, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9617148030306344, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9615418808716815, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9620703824620982, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9627434837568436, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9630287573340452, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9628633729354765, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9625072709693706, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9629694445294752, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.961722901648613, "id_best": 44, "lr_best": 0.0078, "wd_best": 0.05, "train/loss_best": 0.06467054958455265, "validation/loss_best": 0.11481758952140808, "validation/acc_best": 0.96875, "validation/f1_best": 0.9630287573340452} +{"epoch": 13, "train/lr": 0.00011886002410835478, "train/loss": 0.8068537762761117, "train/grad": 0.04473386457189918, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.6838470458984376, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.63844482421875, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.5651873779296874, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.49475341796875, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.4268878173828123, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.3362445068359374, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.238251037597656, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.1346295166015623, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.00674560546875, "train/loss_009_lr8.7e-02_wd1.0e+00": 1.8796255493164062, "train/loss_010_lr1.0e-01_wd1.0e+00": 1.76333251953125, "train/loss_011_lr1.2e-01_wd1.0e+00": 1.6030520629882812, "train/loss_012_lr1.4e-01_wd1.0e+00": 1.4628880310058594, "train/loss_013_lr1.7e-01_wd1.0e+00": 1.2848360443115234, "train/loss_014_lr2.0e-01_wd1.0e+00": 1.1391230773925782, "train/loss_015_lr2.3e-01_wd1.0e+00": 1.019491024017334, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.8916536140441894, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.7698233890533447, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.6621308183670044, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.5828531646728515, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.5055528593063354, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.4434916126728058, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.38946073651313784, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.3442893135547638, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.30718774139881133, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.272325237095356, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.24730797946453095, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.22846550539135932, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.2071804691851139, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.18679380603134632, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.1718959917873144, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.1603392267972231, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.1470194500312209, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.13677192844450473, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.1262328139320016, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.11704253375530244, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.10831258736550808, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.10088902667164802, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.09361155042424799, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.08548652444966137, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.07986665235832334, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.0753899961244315, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.0701316084433347, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.06611126312986017, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.06209062753245234, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.058392479456961154, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.05578689392656088, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.05315915902145207, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.051450008023530246, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.013762162798084319, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.013512216042727232, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.013106581596657634, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.012713654739782214, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.012331857257522642, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.011819952283985913, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.011275545312091708, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.010721050170250237, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.010080282771959902, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.009498907588422298, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.009008719436824322, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.008373520735185594, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.007832799009047448, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.007139618305955082, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.006555950862821192, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.006061548069119453, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.005515787580516189, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.004977183307055384, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.004485577506711707, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.00411446243408136, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.003746954513480887, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.003447032973635942, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0031840447254944592, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.002962349435547367, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0027785922697512433, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.002604038746794686, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.002476666732691228, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.002379118694807403, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0022663044987712056, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.002154224779224023, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0020695270341821014, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0020011316239833834, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0019188458618009463, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0018536289862822741, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0017814389627892524, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0017161347588989884, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0016499813640257343, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0015900482685538009, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0015286870364798232, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0014553841750603168, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0014028367504943162, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0013588961321511306, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0013063159488956443, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0012655422260286287, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0012257452221820131, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0011893499693542253, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0011641355557367205, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0011397525412030517, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0011253165343077854, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.6824536323547363, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.6367952823638916, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.5631396770477295, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.4924278259277344, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.4244163036346436, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.33359432220459, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.2356865406036377, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.1323935985565186, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.0048747062683105, "validation/loss_009_lr8.7e-02_wd1.0e+00": 1.8783797025680542, "validation/loss_010_lr1.0e-01_wd1.0e+00": 1.7628493309020996, "validation/loss_011_lr1.2e-01_wd1.0e+00": 1.6038166284561157, "validation/loss_012_lr1.4e-01_wd1.0e+00": 1.4648897647857666, "validation/loss_013_lr1.7e-01_wd1.0e+00": 1.2888357639312744, "validation/loss_014_lr2.0e-01_wd1.0e+00": 1.1447958946228027, "validation/loss_015_lr2.3e-01_wd1.0e+00": 1.0266616344451904, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.9004443883895874, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.7801843881607056, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.6739183664321899, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.5953906774520874, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.5189712047576904, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.4573487639427185, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.403756320476532, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.3591024577617645, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.32234910130500793, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.2880396842956543, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.26359257102012634, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.2453818917274475, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.22500373423099518, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.20583565533161163, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.19208306074142456, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.18168310821056366, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.17005078494548798, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.16131965816020966, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.15264679491519928, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.1455441117286682, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.13915826380252838, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.13400110602378845, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.12931717932224274, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.12467563152313232, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.12168916314840317, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.11953376233577728, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.11732953786849976, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.115748330950737, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.11443576961755753, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.11329730600118637, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.11263813823461533, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.11185967922210693, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.11127889901399612, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.5324900793650794, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.550843253968254, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.5768849206349206, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.5974702380952381, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.6200396825396826, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.640625, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.6651785714285714, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.6909722222222222, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.7214781746031746, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.7504960317460317, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.7720734126984127, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.8070436507936508, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.8447420634920635, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.8844246031746031, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9035218253968254, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9151785714285714, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9216269841269841, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9278273809523809, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9317956349206349, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9340277777777778, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9362599206349206, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.939484126984127, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9422123015873016, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9451884920634921, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9461805555555556, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9481646825396826, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9499007936507936, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9516369047619048, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9526289682539683, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9538690476190477, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9561011904761905, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.957093253968254, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9580853174603174, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9598214285714286, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9600694444444444, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9618055555555556, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9618055555555556, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9625496031746031, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9632936507936508, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9642857142857143, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9650297619047619, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9657738095238095, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9655257936507936, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9660218253968254, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9660218253968254, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9662698412698413, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9670138888888888, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.966765873015873, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.966765873015873, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.3515197736914863, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.37100210196783473, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.3974860346372919, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.419433548470783, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.4412921813812286, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.46527985972569186, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.49349786493408393, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.5218522466331883, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.5584629597616482, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.6021675897822307, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.6326865293284983, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.7065042333991843, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.7908576666095728, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.8616444812379904, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.8919198283222647, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9086401133580756, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9161471849424258, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9232238764276649, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9277901963658877, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9301505027487005, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9319350864324625, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.935843580915663, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9377763668953869, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9403793147863844, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9412543048537491, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.943189692277352, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9445998903947344, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9466021928476002, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9482935414151661, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9496684189032116, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.951235747819372, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9523510064377486, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9527474166632627, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9546910743379696, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9549901617444461, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9568334876798511, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9567266554570806, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9573583800195141, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9581144472544029, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9593368262486596, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.960004597876296, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9608556233715895, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9606679331801798, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9611855124545086, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9611016799393193, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9613823813294745, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9620220635512049, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.961474217468639, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9613625962557667, "id_best": 46, "lr_best": 0.010799999999999999, "wd_best": 0.05, "train/loss_best": 0.05578689392656088, "validation/loss_best": 0.11263813823461533, "validation/acc_best": 0.9670138888888888, "validation/f1_best": 0.9620220635512049} +{"epoch": 14, "train/lr": 8.9081919031238e-05, "train/loss": 0.7933656254410744, "train/grad": 0.04497876381501555, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.673653564453125, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.6269683837890625, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.551556396484375, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.4792083740234374, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.4097113037109374, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.3169091796875, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.216719665527344, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.111136779785156, "train/loss_008_lr7.4e-02_wd1.0e+00": 1.980821533203125, "train/loss_009_lr8.7e-02_wd1.0e+00": 1.8517045593261718, "train/loss_010_lr1.0e-01_wd1.0e+00": 1.7338714599609375, "train/loss_011_lr1.2e-01_wd1.0e+00": 1.5718931579589843, "train/loss_012_lr1.4e-01_wd1.0e+00": 1.4308572387695313, "train/loss_013_lr1.7e-01_wd1.0e+00": 1.2527458190917968, "train/loss_014_lr2.0e-01_wd1.0e+00": 1.1078609657287597, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.9896480751037597, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.8640852355957032, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.744984769821167, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.6403438949584961, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.5635475659370422, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.4888609504699707, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.4288667356967926, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.37669878125190737, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.3329983621835709, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.2970032280683517, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.2631919473409653, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.23890764400362968, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.22047640413045883, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.19975941523909568, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.1799117863178253, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.16532775469124317, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.15404823422431946, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.1410662703216076, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.13108875460922717, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.12079159613698721, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.11184324901551009, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.10334636725485324, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.096076774680987, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.08895980890840292, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.08104910346679389, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.07557894000783563, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.07124326304532587, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.0661083747446537, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.06223675081506372, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.058255200246348976, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.054550995621830224, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.05188465117476881, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.049215139523148536, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.047341658994555474, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.013837118195369839, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.013578856703825295, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.013161650034599006, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.012757293498143554, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.012364540002308785, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.011840660953894258, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.01128777649719268, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.010730185518041254, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.01009251046460122, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.009519199933856725, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.009036843024659902, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.008409679241012782, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.007873918015975504, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.0071873680618591606, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.006609152739401907, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.0061197031149640676, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.0055801085033454, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.005047101252712309, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.004561225816141814, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.004193625369807706, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.0038275899004656822, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.0035280162049457432, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0032631906098686157, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0030397058371454478, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0028520351770566776, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0026725171285215763, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0025398781441617756, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0024381785310106352, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.002319976132712327, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.002202138928696513, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0021131447330117225, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0020407574070850387, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.001955888178781606, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0018870734004303813, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0018126766243949533, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0017442555114394055, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.001677109901793301, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0016164525609929114, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0015540419286116957, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.001481481097289361, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0014274515202851036, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0013828675274271517, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.001328169806220103, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0012856130843283608, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0012412464659428224, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0011993510468164459, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0011687791591975837, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0011410102338413708, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0011227398719347549, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.672440767288208, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.6255905628204346, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.5499420166015625, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.477475643157959, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.407928705215454, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.3150522708892822, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.2150862216949463, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.109703779220581, "validation/loss_008_lr7.4e-02_wd1.0e+00": 1.9799604415893555, "validation/loss_009_lr8.7e-02_wd1.0e+00": 1.8516490459442139, "validation/loss_010_lr1.0e-01_wd1.0e+00": 1.7345150709152222, "validation/loss_011_lr1.2e-01_wd1.0e+00": 1.5740039348602295, "validation/loss_012_lr1.4e-01_wd1.0e+00": 1.4343565702438354, "validation/loss_013_lr1.7e-01_wd1.0e+00": 1.2581093311309814, "validation/loss_014_lr2.0e-01_wd1.0e+00": 1.1150157451629639, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.9981456995010376, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.8740420937538147, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.7563057541847229, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.6529583930969238, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.5769752264022827, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.5030926465988159, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.44380277395248413, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.39227497577667236, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.34936511516571045, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.3139941394329071, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.2810192406177521, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.25746962428092957, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.23979398608207703, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.22019921243190765, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.2017313688993454, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.18838389217853546, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.17831282317638397, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.16692376136779785, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.1585618257522583, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.1501324623823166, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.14317087829113007, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.1368974894285202, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.1319991797208786, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.12736524641513824, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.12280862033367157, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.12000635266304016, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.11805487424135208, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.11585772037506104, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.11454985290765762, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.1132829487323761, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.11227747052907944, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.11177462339401245, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.11132010072469711, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.11108336597681046, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.5359623015873016, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.5550595238095238, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.5786210317460317, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.6011904761904762, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.623015873015873, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.6458333333333334, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.6696428571428571, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.6966765873015873, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.7266865079365079, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.7537202380952381, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.777281746031746, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.8127480158730159, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.8514384920634921, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.8883928571428571, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9077380952380952, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9174107142857143, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.923859126984127, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9290674603174603, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9325396825396826, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9342757936507936, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9372519841269841, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.939484126984127, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9432043650793651, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9456845238095238, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9464285714285714, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9481646825396826, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9494047619047619, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9508928571428571, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9536210317460317, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9548611111111112, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9563492063492064, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9573412698412699, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9590773809523809, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9605654761904762, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9615575396825397, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9620535714285714, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9632936507936508, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9650297619047619, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9652777777777778, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9670138888888888, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9675099206349206, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9675099206349206, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9672619047619048, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9675099206349206, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.96875, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9682539682539683, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.96875, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9680059523809523, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9680059523809523, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.35458620469171437, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.3762448653614505, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.39938632087068193, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.4227376598847701, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.44490933658230364, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.47071391508442706, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.4971871462801648, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.529688130346264, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.5660344056499143, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.606705550215971, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.6454386904010913, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.72127265737735, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.8044073924859356, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.8679447224454867, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.8982624083997811, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9120188138987502, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9193877256019606, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9248874717876848, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9285936538463582, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9304875749785543, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9331755462275118, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9357147545125335, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9387325650732989, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9407145676149508, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9416109988542019, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9433077799856097, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.944697829005818, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9465322029864849, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9489131564863881, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.94997734326958, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9517816851204547, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9521805582490673, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9537862156404417, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9550487735187184, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9563456080072564, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9565786422223569, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.957660513949205, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9593030942299704, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9597816609692702, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.96134060357294, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9615013061924862, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.961724786081946, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9613508053413689, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9622647792447095, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9629680686337633, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9624629563475994, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.962931716920591, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9622635157513715, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9620567731872004, "id_best": 44, "lr_best": 0.0078, "wd_best": 0.05, "train/loss_best": 0.058255200246348976, "validation/loss_best": 0.1132829487323761, "validation/acc_best": 0.96875, "validation/f1_best": 0.9629680686337633} +{"epoch": 15, "train/lr": 6.196799573888289e-05, "train/loss": 0.7853060030937195, "train/grad": 0.043914183601737024, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.662977294921875, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.6151123046875, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.537845458984375, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.4638153076171876, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.3927862548828127, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.2979559326171874, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.1958648681640627, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.0884573364257815, "train/loss_008_lr7.4e-02_wd1.0e+00": 1.9560687255859375, "train/loss_009_lr8.7e-02_wd1.0e+00": 1.8252783203125, "train/loss_010_lr1.0e-01_wd1.0e+00": 1.706110382080078, "train/loss_011_lr1.2e-01_wd1.0e+00": 1.5430469512939453, "train/loss_012_lr1.4e-01_wd1.0e+00": 1.401697311401367, "train/loss_013_lr1.7e-01_wd1.0e+00": 1.2242235565185546, "train/loss_014_lr2.0e-01_wd1.0e+00": 1.0808017921447755, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.9644796562194824, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.8417544078826904, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.7259705877304077, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.6248902797698974, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.5509622621536255, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.47932087182998656, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.4219546127319336, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.37208993613719943, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.33026579320430755, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.29583573758602144, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.2633756285905838, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.24002119094133378, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.22227475330233573, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.20216880835592746, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.18273581005632877, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.16844405002892018, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.1573362885415554, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.14436808981001378, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.13435800939798356, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.12395183123648167, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.11487840466201306, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.10620533706620336, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.09874898910522462, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.0914181435573846, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.08324025175534189, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.07752044992521405, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.07299245321191847, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.06764663087204098, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.0635323020350188, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.05932691531255841, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.055473651252686974, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.05266154914163053, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.04985667456872761, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.04789289186708629, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.013615783611312509, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.013351374347694218, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.01292505033314228, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.012511646123602987, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.012112132678739727, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.01158202880062163, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.01102711990941316, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.010471496828831733, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.009839858203195035, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.009274808685295283, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.008797535873018205, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.008173826062120497, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.007637090107891709, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.006948780852835626, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.006370568142738193, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.0058847994660027325, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.005352963691111654, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.004832436244469136, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.004363230146700516, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.004011784611502662, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.003665851627010852, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.003385851060738787, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0031403749831952154, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.002933434679871425, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0027619143965421245, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0025978575996123254, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0024772466585272924, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0023842922184849156, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0022763735795160757, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0021669923898298294, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0020843701815465463, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0020165552309481427, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0019350088288774714, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0018684223075979389, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.001794925045396667, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.001729346657230053, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0016605911444639786, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.001600042844656855, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0015356249239994212, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0014610382574028336, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0014042918101768009, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0013587946185725742, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0013020787830464542, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0012575315630238037, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0012092599015159067, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0011641085321025457, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.001131059034669306, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0010970057078520767, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0010746279418526682, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.6655380725860596, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.6177566051483154, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.540951728820801, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.467219114303589, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.396430015563965, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.3021976947784424, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.200810194015503, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.0941567420959473, "validation/loss_008_lr7.4e-02_wd1.0e+00": 1.9627798795700073, "validation/loss_009_lr8.7e-02_wd1.0e+00": 1.833161473274231, "validation/loss_010_lr1.0e-01_wd1.0e+00": 1.7150863409042358, "validation/loss_011_lr1.2e-01_wd1.0e+00": 1.5535675287246704, "validation/loss_012_lr1.4e-01_wd1.0e+00": 1.413314938545227, "validation/loss_013_lr1.7e-01_wd1.0e+00": 1.2371057271957397, "validation/loss_014_lr2.0e-01_wd1.0e+00": 1.0943514108657837, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.978586733341217, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.8559896945953369, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.7401921153068542, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.6386811137199402, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.5643767714500427, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.4922657907009125, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.4346317946910858, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.384498655796051, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.3425752520561218, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.3083195388317108, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.2762250304222107, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.2533508241176605, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.2362615168094635, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.217178612947464, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.19903957843780518, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.18617409467697144, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.17628911137580872, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.16524957120418549, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.15707869827747345, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.14887002110481262, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.14225997030735016, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.1361319124698639, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.13122643530368805, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.1268600970506668, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.12249071896076202, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.11973200738430023, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.11781083047389984, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.11576098203659058, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.11436433345079422, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.1132468581199646, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.11238432675600052, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.11179330945014954, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.11142980307340622, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.11132162064313889, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.5379464285714286, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.5575396825396826, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.5808531746031746, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.605406746031746, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.6267361111111112, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.6480654761904762, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.671875, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.699156746031746, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.7294146825396826, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.7579365079365079, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.7822420634920635, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.8199404761904762, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.8578869047619048, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.892609126984127, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9094742063492064, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.917906746031746, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9236111111111112, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9288194444444444, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9327876984126984, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9345238095238095, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9379960317460317, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9407242063492064, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9432043650793651, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9456845238095238, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9474206349206349, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9479166666666666, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9494047619047619, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.951140873015873, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9533730158730159, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.955109126984127, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9573412698412699, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9580853174603174, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9605654761904762, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9610615079365079, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9620535714285714, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9632936507936508, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9635416666666666, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9645337301587301, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9645337301587301, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9665178571428571, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9670138888888888, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9660218253968254, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.966765873015873, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9672619047619048, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9677579365079365, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9677579365079365, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9675099206349206, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9675099206349206, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.966765873015873, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.3567076677849269, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.37953194561211123, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.4015561333981764, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.42759413619120695, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.4487544325230346, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.4737938618667466, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.5014245937270009, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.5316071375330158, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.5678893023939672, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.6121467122543836, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.6559629691992745, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.7381657249992424, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.8175502527687232, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.8752465268034878, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9012930392910109, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9124490976323242, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9183484746082242, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9244507495589795, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9288310019535285, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9306761213974062, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9341398606366449, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9371274514140554, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9386594282467898, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9406789135670349, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9424676016443124, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9431602034687868, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9446347688944703, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9468077824217864, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9487902403862465, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9505791783291215, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9528408678353738, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9535033277524563, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9551612474673521, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9556586364662797, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9563975698959177, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9576565973839931, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9578825173221011, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9582632627389093, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.958625725521167, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9613255177949606, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9616646072378058, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.960680935916816, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9612082244628, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9615701204264743, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9622869406422603, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9622729194467671, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9618967358604752, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9618967358604752, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9612495941973493, "id_best": 44, "lr_best": 0.0078, "wd_best": 0.05, "train/loss_best": 0.05932691531255841, "validation/loss_best": 0.1132468581199646, "validation/acc_best": 0.9677579365079365, "validation/f1_best": 0.9622869406422603} +{"epoch": 16, "train/lr": 3.870405029380728e-05, "train/loss": 0.777254832983017, "train/grad": 0.04370213074609637, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.656343994140625, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.60779541015625, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.529366455078125, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.4543255615234374, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.3822406005859373, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.2862420654296876, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.1830313110351565, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.074509582519531, "train/loss_008_lr7.4e-02_wd1.0e+00": 1.9410679626464844, "train/loss_009_lr8.7e-02_wd1.0e+00": 1.809307861328125, "train/loss_010_lr1.0e-01_wd1.0e+00": 1.68940185546875, "train/loss_011_lr1.2e-01_wd1.0e+00": 1.525677947998047, "train/loss_012_lr1.4e-01_wd1.0e+00": 1.3839862060546875, "train/loss_013_lr1.7e-01_wd1.0e+00": 1.2065314483642577, "train/loss_014_lr2.0e-01_wd1.0e+00": 1.0635533905029297, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.9478086853027343, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.8258554363250732, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.711323504447937, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.6116056394577026, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.5388659620285035, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.46852932929992674, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.4122943663597107, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.3636098963022232, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.32282476663589477, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.289295334815979, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.2576637688279152, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.23488038629293442, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.21755610153079033, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.1979047181457281, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.17890490047633648, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.16489486202597617, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.1538559577614069, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.1410944090038538, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.13115203842520715, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.12083754822611809, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.11176319545134902, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.1030734509602189, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.09561096200719475, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.08828234493732452, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.08012696179561317, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.07447169645689428, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.07000273541547358, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.06471952452324331, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.06073774017393589, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.056639395840466025, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.052910211719572546, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.05016872982494533, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.047408689614385366, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.04543263784609735, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.013674926511012018, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.013404665105044842, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.012965011820197105, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.012539728921838104, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.012127437349408864, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.011581006515771151, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.011006322288885713, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.010432273079641164, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.009781520669348539, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.009199066725559533, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.008708160752430558, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.008068157457746566, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.007520720686297864, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.006822773588355631, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.006242503910325468, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.005757692353799939, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.0052302287286147475, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.004717484030406922, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.004257117386441678, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.0039129319484345615, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.003575540919555351, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.0033025028242263943, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0030638254643417895, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0028635653655510397, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0026976001443108546, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0025391776795731856, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.002422876940108836, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.002332929269759916, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0022284270339878276, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.002123241348308511, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.002042131808702834, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0019756048708222808, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0018962341465521603, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0018305152491666376, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0017584349733078852, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0016921857534907758, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0016248906968394294, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0015639127715257927, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0014997278765076772, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0014231333730276674, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0013661955375573597, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0013194766029482707, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0012607479724101721, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0012146132794441655, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0011650686615030281, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0011191131168743595, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0010845161826000549, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0010493364601279608, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0010247557508409955, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.661223888397217, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.612891435623169, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.5351223945617676, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.4607200622558594, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.3893330097198486, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.2941935062408447, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.191965103149414, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.084420680999756, "validation/loss_008_lr7.4e-02_wd1.0e+00": 1.9522149562835693, "validation/loss_009_lr8.7e-02_wd1.0e+00": 1.8217213153839111, "validation/loss_010_lr1.0e-01_wd1.0e+00": 1.7029343843460083, "validation/loss_011_lr1.2e-01_wd1.0e+00": 1.5407153367996216, "validation/loss_012_lr1.4e-01_wd1.0e+00": 1.4001648426055908, "validation/loss_013_lr1.7e-01_wd1.0e+00": 1.2238839864730835, "validation/loss_014_lr2.0e-01_wd1.0e+00": 1.081796407699585, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.966404378414154, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.8447610139846802, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.7300544381141663, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.6298342347145081, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.5565954446792603, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.48564133048057556, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.4287956953048706, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.3795101046562195, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.33842960000038147, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.3047367036342621, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.27325868606567383, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.250737726688385, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.2338651716709137, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.21514685451984406, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.19733448326587677, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.1846211552619934, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.17489750683307648, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.16402091085910797, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.1559617519378662, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.1478315144777298, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.141133651137352, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.1350395828485489, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.13037537038326263, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.12588679790496826, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.12156583368778229, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.11887025088071823, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.11687537282705307, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.11478694528341293, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.11354299634695053, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.11225030571222305, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.11126708984375, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.11061643064022064, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.11011836677789688, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.1097240000963211, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.5394345238095238, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.5595238095238095, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.5818452380952381, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.6068948412698413, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.626984126984127, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.6495535714285714, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.6743551587301587, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.7006448412698413, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.7313988095238095, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.7591765873015873, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.783234126984127, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.8211805555555556, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.861359126984127, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.8936011904761905, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9099702380952381, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9188988095238095, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9236111111111112, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9293154761904762, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9327876984126984, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9347718253968254, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9375, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9407242063492064, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9437003968253969, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9456845238095238, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9476686507936508, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9481646825396826, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9501488095238095, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9518849206349206, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9538690476190477, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9556051587301587, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.957093253968254, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9580853174603174, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9603174603174603, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9610615079365079, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9623015873015873, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9635416666666666, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9642857142857143, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9650297619047619, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9652777777777778, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9660218253968254, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9672619047619048, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.966765873015873, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9680059523809523, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9685019841269841, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9689980158730159, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9685019841269841, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9689980158730159, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9692460317460317, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9689980158730159, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.3583473361720974, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.3801855442349327, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.40314280547085907, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.4288110428058958, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.4494091126045559, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.4757947807036616, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.5041572195125065, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.5346180329578674, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.5700334379323339, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.614482379532794, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.6576824931637321, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.742675782889436, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.82543436972544, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.8763484033195601, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9017788351904091, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9129859630243673, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9181815002479574, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9250250080845736, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.92911304787094, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9308227447138903, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.933414201816493, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9369417072524937, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9392166013458514, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9407443209318804, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9428668957621971, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9434596966839496, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.945390959381282, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9473441680010305, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9491435701439547, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9511925557940236, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9525705601947942, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9534949217525691, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9549764778374219, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9556088847614097, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9569917375467989, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9578950647123771, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9582231311491554, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9590589446519457, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9597043258071972, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9609765720838135, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9616479846709415, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9611336101294615, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9624602359441119, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9627728497957591, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9631675990319363, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9627510386889665, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9633072222597473, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9634397574434674, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9632661973798529, "id_best": 47, "lr_best": 0.012899999999999998, "wd_best": 0.05, "train/loss_best": 0.047408689614385366, "validation/loss_best": 0.11011836677789688, "validation/acc_best": 0.9692460317460317, "validation/f1_best": 0.9634397574434674} +{"epoch": 17, "train/lr": 2.030750443206766e-05, "train/loss": 0.7744786751270294, "train/grad": 0.04348610740154982, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.6549737548828123, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.605955810546875, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.527030029296875, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.4514080810546877, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.378916015625, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.2822930908203123, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.17839599609375, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.069085998535156, "train/loss_008_lr7.4e-02_wd1.0e+00": 1.934775390625, "train/loss_009_lr8.7e-02_wd1.0e+00": 1.8023281860351563, "train/loss_010_lr1.0e-01_wd1.0e+00": 1.6817250061035156, "train/loss_011_lr1.2e-01_wd1.0e+00": 1.5174014282226562, "train/loss_012_lr1.4e-01_wd1.0e+00": 1.3752140045166015, "train/loss_013_lr1.7e-01_wd1.0e+00": 1.1976741790771483, "train/loss_014_lr2.0e-01_wd1.0e+00": 1.0552085304260255, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.9399695587158203, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.8189604377746582, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.7054721212387085, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.6068087291717529, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.534906063079834, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.46541940569877627, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.4098703396320343, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.3615979790687561, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.32115262389183047, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.2878757619857788, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.25632162362337113, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.23364225789904594, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.21631632700562478, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.19668483234941958, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.1776725158840418, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.16370265267789363, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.15269587561488152, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.13998620618134738, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.13015373840928077, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.1199009008705616, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.11096143361181021, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.10242541598156095, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.09514777461066842, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.0879300041217357, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.07993201395496725, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.07440907694399357, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.06999224699102342, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.0647603175137192, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.060750745069235564, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.05664285696111619, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.0528369271941483, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.05000680008903146, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.047103426586836576, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.04506130175665021, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.013560810363851488, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.013292945306748152, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.012859095088206231, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.012437714026309549, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.012032417780719697, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.01149647768586874, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.010937876123934985, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.010382003476843238, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.009753922442905604, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.009191291672177613, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.008713816502131521, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.008085724618285894, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.007542906089220196, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.0068468590476550165, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.006267120288684964, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.005782865472137928, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.005255210171453655, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.00474370380397886, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.004283765689469874, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.003940182022051886, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.0036022511508781462, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.0033270266710314898, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0030845010047778486, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.002879369738511741, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0027072715456597507, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0025403759500477463, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.002417497056303546, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.002322080223239027, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.002210403335047886, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0020980622817296534, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0020118958753300832, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.001941530323238112, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0018577076494693755, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0017895410349592566, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0017142300427076408, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0016455177907482722, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.001576325612841174, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.001514301074494142, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0014496695800335147, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0013725420681294054, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0013158324870164507, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0012695211681420914, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0012113913928624243, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0011658008527592756, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.001115910162916407, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0010696767762419768, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0010339575010584667, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.00099644592977711, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0009701042246888392, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.6589291095733643, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.6103789806365967, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.5322420597076416, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.457397937774658, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.3855795860290527, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.289980888366699, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.1872055530548096, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.0793094635009766, "validation/loss_008_lr7.4e-02_wd1.0e+00": 1.9465198516845703, "validation/loss_009_lr8.7e-02_wd1.0e+00": 1.8155930042266846, "validation/loss_010_lr1.0e-01_wd1.0e+00": 1.6964638233184814, "validation/loss_011_lr1.2e-01_wd1.0e+00": 1.533973217010498, "validation/loss_012_lr1.4e-01_wd1.0e+00": 1.3932464122772217, "validation/loss_013_lr1.7e-01_wd1.0e+00": 1.2169625759124756, "validation/loss_014_lr2.0e-01_wd1.0e+00": 1.0750315189361572, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.960006594657898, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.8387661576271057, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.7246285676956177, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.6251285076141357, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.5523816347122192, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.4820416271686554, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.4257090091705322, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.37692299485206604, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.3362724483013153, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.3028676509857178, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.2715964913368225, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.24934841692447662, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.2326670140028, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.21394923329353333, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.1963770091533661, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.18370193243026733, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.1740860790014267, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.16328981518745422, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.1552789807319641, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.1472560465335846, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.14067670702934265, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.13468582928180695, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.12992116808891296, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.12552930414676666, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.12110717594623566, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.11842404305934906, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.11650247126817703, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.11453371495008469, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.11314323544502258, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.1120312511920929, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.1110166385769844, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.11038859188556671, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.10982733219861984, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.10944946110248566, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.5394345238095238, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.5612599206349206, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.5833333333333334, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.609375, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.6272321428571429, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.6507936507936508, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.6765873015873016, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.7021329365079365, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.7313988095238095, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.761656746031746, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.7842261904761905, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.8239087301587301, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.863343253968254, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.8955853174603174, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.910218253968254, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9186507936507936, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9233630952380952, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9300595238095238, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9332837301587301, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9347718253968254, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9379960317460317, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9404761904761905, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9437003968253969, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9456845238095238, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9476686507936508, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9484126984126984, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9499007936507936, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9513888888888888, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9541170634920635, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9558531746031746, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9568452380952381, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9585813492063492, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9600694444444444, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9610615079365079, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9618055555555556, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9625496031746031, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9642857142857143, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9642857142857143, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9650297619047619, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9670138888888888, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9670138888888888, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9672619047619048, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9682539682539683, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9685019841269841, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9685019841269841, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.96875, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9682539682539683, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9685019841269841, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9685019841269841, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.3586757390780592, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.3815563725036847, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.40493344725408004, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.43053100620861046, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.44975179197681975, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.47682334758972555, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.5079695834027909, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.5369436243220576, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.5698922633819417, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.6186183497225717, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.6602473176439427, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.7491684778470347, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.8297937045418909, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.8798933140931107, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9022051051014777, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9128132605877158, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9179789571714406, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9254400538641318, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.929514193626512, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9308230847062127, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9340851558541795, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9366161607264393, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9389364263643964, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.940734762532662, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9428405312797311, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9434861791114875, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9452168495179583, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9467647908116336, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9495111634248691, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9513482235387588, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.952203532736691, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9538911466785842, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9548316717961088, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9556936111024059, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9563411707155457, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9572569075739701, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9582545585225116, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9583397798068036, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9590488046826297, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9615528104524402, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9613518616092327, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9615350485236838, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9627094955433032, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9628866334048154, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9627549829811751, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9627409100965326, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9622944526945496, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9626872176321516, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9626872176321516, "id_best": 45, "lr_best": 0.0093, "wd_best": 0.05, "train/loss_best": 0.0528369271941483, "validation/loss_best": 0.1110166385769844, "validation/acc_best": 0.96875, "validation/f1_best": 0.9627409100965326} +{"epoch": 18, "train/lr": 7.5829098008590064e-06, "train/loss": 0.7750509682297707, "train/grad": 0.043606182169169186, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.65477783203125, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.6058416748046875, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.5268524169921873, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.45133544921875, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.3788507080078123, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.28232421875, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.1785260009765626, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.069332275390625, "train/loss_008_lr7.4e-02_wd1.0e+00": 1.935245361328125, "train/loss_009_lr8.7e-02_wd1.0e+00": 1.802965087890625, "train/loss_010_lr1.0e-01_wd1.0e+00": 1.6826873779296876, "train/loss_011_lr1.2e-01_wd1.0e+00": 1.518554916381836, "train/loss_012_lr1.4e-01_wd1.0e+00": 1.3768515014648437, "train/loss_013_lr1.7e-01_wd1.0e+00": 1.1996958541870117, "train/loss_014_lr2.0e-01_wd1.0e+00": 1.0573938369750977, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.9424495887756348, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.8215964031219483, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.7082501316070556, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.6095862770080567, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.537688136100769, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.46808237075805664, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.4123583912849426, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.36388318657875063, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.32327379047870636, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.2896562170982361, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.25790776789188385, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.23503291577100754, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.21751489922404288, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.19765447020530702, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.1784294156730175, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.16422182869166135, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.1530587489902973, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.14016868613660335, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.13016082018613814, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.11975079424679279, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.11067363576963545, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.10196348315104842, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.09461856625974178, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.08736398695968091, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.07924799802713096, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.07363022189587355, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.06911822727881373, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.06378575474023819, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.05968395709991455, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.05549049727618694, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.05161134214140475, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.04875925206579268, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.0458444002084434, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.04374732661060989, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.013657638914883136, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.013386182631365954, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.012944990126416088, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.012517327722162009, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.012103987243026495, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.011558310557156802, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.010988566745072603, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.010422971467487514, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.0097834846470505, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.009211809705011547, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.00872826125472784, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.00809145737439394, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.007543156589381397, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.006839014298748225, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.006252722807694226, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.005761560755781829, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.005227275856304914, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.004708037571981549, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.00424301341874525, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.003895445930538699, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.003554711954202503, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.0032783118251245467, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.003036595720332116, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.002832692503579892, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0026622415881138294, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.002498774354462512, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.002379190679639578, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0022857254481641574, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.002176817957079038, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.002067859927774407, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.001984083691495471, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0019159598991973325, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0018340744712622835, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0017671654903097078, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0016936468353378586, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.001625619764381554, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0015570756801753306, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.001495948326191865, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0014318450991413557, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.001355676256644074, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0012997677925159223, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0012523376429453492, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0011935585481114685, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0011470178273157217, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0010964508033066522, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0010485708892520051, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.001011565506196348, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.000972845999931451, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0009447048950823956, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.658121347427368, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.609405755996704, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.5311121940612793, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.4560704231262207, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.384119749069214, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.288362741470337, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.1854665279388428, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.077336549758911, "validation/loss_008_lr7.4e-02_wd1.0e+00": 1.9443633556365967, "validation/loss_009_lr8.7e-02_wd1.0e+00": 1.8132448196411133, "validation/loss_010_lr1.0e-01_wd1.0e+00": 1.694140911102295, "validation/loss_011_lr1.2e-01_wd1.0e+00": 1.5314288139343262, "validation/loss_012_lr1.4e-01_wd1.0e+00": 1.3906272649765015, "validation/loss_013_lr1.7e-01_wd1.0e+00": 1.21439790725708, "validation/loss_014_lr2.0e-01_wd1.0e+00": 1.072421669960022, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.9575564861297607, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.836581826210022, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.7226569652557373, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.6232820153236389, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.5508396029472351, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.4806525409221649, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.4245266020298004, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.37593919038772583, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.3353016674518585, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.3021131157875061, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.27099764347076416, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.2488127052783966, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.23217491805553436, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.21357211470603943, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.19601644575595856, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.1834379881620407, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.17379851639270782, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.16301941871643066, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.15505464375019073, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.14708364009857178, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.14052775502204895, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.13450545072555542, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.1297929286956787, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.12539663910865784, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.1210511326789856, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.1183215081691742, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.11648942530155182, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.11440617591142654, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.11311233788728714, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.1119232177734375, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.11104503273963928, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.11045648157596588, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.10991450399160385, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.10946056991815567, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.5404265873015873, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.5607638888888888, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.5830853174603174, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.6103670634920635, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.6272321428571429, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.6515376984126984, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.6770833333333334, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.7018849206349206, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.7313988095238095, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.7614087301587301, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.7849702380952381, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.824156746031746, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.8645833333333334, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.8953373015873016, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9104662698412699, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9184027777777778, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9233630952380952, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9295634920634921, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9330357142857143, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9345238095238095, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9382440476190477, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9407242063492064, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9441964285714286, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9459325396825397, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9474206349206349, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9484126984126984, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9499007936507936, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.951140873015873, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9543650793650794, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9561011904761905, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9568452380952381, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9590773809523809, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9603174603174603, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9608134920634921, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9615575396825397, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9625496031746031, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9640376984126984, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9645337301587301, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9655257936507936, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9670138888888888, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9670138888888888, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9670138888888888, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9675099206349206, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9680059523809523, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9677579365079365, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9682539682539683, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9680059523809523, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9677579365079365, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9682539682539683, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.3592971232871888, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.3811446637397684, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.40415769665083384, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.4313400387231856, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.44978484503987287, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.477328362645578, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.5082895800762345, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.5368317988369197, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.5698306752535371, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.6184679301269526, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.6608387549040711, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.7492069250059299, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.8313593316715705, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.8799893365047099, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9026368798372735, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9124842991395615, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9179789571714406, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9250798000724861, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9289592591840632, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9305498561888528, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.934346391465915, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9369417072524937, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9394938102127062, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9409212708930021, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9426813643002303, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9436164214818038, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.945206144118792, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9465803458165228, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9495472886435983, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9517321813437666, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9521492479881284, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.95424325185434, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.955100725579854, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9555112431553907, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9561616833869748, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9570638649909714, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9580502314904843, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9586073456695888, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9596235865295937, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9615528104524402, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9613518616092327, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9613518616092327, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9621808309270928, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.962438136508637, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9622324558521675, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9625711293594854, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9623471281757057, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9620942286283063, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9622689879153382, "id_best": 45, "lr_best": 0.0093, "wd_best": 0.05, "train/loss_best": 0.05161134214140475, "validation/loss_best": 0.11104503273963928, "validation/acc_best": 0.9682539682539683, "validation/f1_best": 0.9625711293594854} +{"epoch": 19, "train/lr": 1.0867618231465446e-06, "train/loss": 0.7732510483264923, "train/grad": 0.043639747090637684, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.6521112060546876, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.6027313232421876, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.5232220458984376, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.4470849609375, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.374056396484375, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.2769775390625, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.172574157714844, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.0628680419921874, "train/loss_008_lr7.4e-02_wd1.0e+00": 1.928238525390625, "train/loss_009_lr8.7e-02_wd1.0e+00": 1.7955960083007811, "train/loss_010_lr1.0e-01_wd1.0e+00": 1.6751103210449219, "train/loss_011_lr1.2e-01_wd1.0e+00": 1.5108470916748047, "train/loss_012_lr1.4e-01_wd1.0e+00": 1.3691917419433595, "train/loss_013_lr1.7e-01_wd1.0e+00": 1.1923037719726564, "train/loss_014_lr2.0e-01_wd1.0e+00": 1.0502409934997559, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.9357294082641602, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.8153939151763916, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.7027478790283204, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.6047926187515259, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.5334654331207276, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.4645224964618683, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.409526629447937, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.36173457622528077, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.3217239445447922, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.28883222967386246, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.257660573720932, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.23525892153382302, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.2180713565647602, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.19864379562437534, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.1798559970408678, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.16598321601748467, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.15504902970045806, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.1424204709753394, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.13259880045428873, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.12231020575389266, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.11328767839819193, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.10461578071117401, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.09713915690779686, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.08970976339653135, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.08139161583967507, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.07559112658724189, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.07091109291650355, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.06539930502884089, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.061148731131106616, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.056808515349403024, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.052794795325025914, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.04976242961362004, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.046730013582855466, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.04453661361709237, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.013669085102155804, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.01339548395946622, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.012951798462308943, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.012520972755737603, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.012104392545297741, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.01155589271336794, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.010981349041685462, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.010412508393637837, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.009768119286745787, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.009194634216837584, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.008709828243590892, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.008073564611840993, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.007528073552530259, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.006830000129994005, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.006248171285260468, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.005763009171932936, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.005234564365819097, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.00472144968342036, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.004261233247816563, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.003917510336032137, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.003579304404556751, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.003304902237141505, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0030633269506506623, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0028595515375491234, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0026887415815144778, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0025242796778911724, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0024045587377622725, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.002309496357338503, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.002201073069591075, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0020911209261976183, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0020079863246064635, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0019400224596029148, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0018590285448590294, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0017930704515310937, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0017219434611615726, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.001656421602529008, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.001589790348079987, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0015294367144815624, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0014679147966671735, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0013929309224477038, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.001337981225224212, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.001291072054882534, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.001233203035662882, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0011859569454099983, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0011357873171800748, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0010861597913026345, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0010482884844532237, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.00100857629586244, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0009801159330527298, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.65798282623291, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.609269618988037, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.530954360961914, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.4558682441711426, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.3839476108551025, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.2881298065185547, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.1852290630340576, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.0770649909973145, "validation/loss_008_lr7.4e-02_wd1.0e+00": 1.944058895111084, "validation/loss_009_lr8.7e-02_wd1.0e+00": 1.8128761053085327, "validation/loss_010_lr1.0e-01_wd1.0e+00": 1.6937698125839233, "validation/loss_011_lr1.2e-01_wd1.0e+00": 1.5310240983963013, "validation/loss_012_lr1.4e-01_wd1.0e+00": 1.3902764320373535, "validation/loss_013_lr1.7e-01_wd1.0e+00": 1.2140107154846191, "validation/loss_014_lr2.0e-01_wd1.0e+00": 1.0720479488372803, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.9571999311447144, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.8361819386482239, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.7223573923110962, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.6229792833328247, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.5506033301353455, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.480446994304657, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.4243970811367035, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.3757939040660858, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.3351951241493225, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.30198752880096436, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.27088284492492676, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.24874284863471985, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.23211106657981873, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.21354787051677704, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.19598662853240967, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.18340964615345, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.17378972470760345, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.16300976276397705, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.15503591299057007, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.14702588319778442, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.14049124717712402, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.13449983298778534, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.1297609955072403, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.12536601722240448, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.12104766815900803, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.11836577206850052, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.11645644903182983, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.11443068832159042, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.11311419308185577, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.1119561567902565, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.1110968217253685, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.11042805761098862, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.1099230945110321, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.10950852185487747, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.5406746031746031, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.5610119047619048, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.5828373015873016, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.6101190476190477, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.626984126984127, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.6512896825396826, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.6770833333333334, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.7021329365079365, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.7313988095238095, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.7611607142857143, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.7849702380952381, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.824156746031746, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.8648313492063492, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.8958333333333334, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9109623015873016, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9186507936507936, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9233630952380952, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9295634920634921, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9330357142857143, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9345238095238095, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9382440476190477, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9407242063492064, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9441964285714286, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9456845238095238, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9474206349206349, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9484126984126984, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9501488095238095, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.951140873015873, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9543650793650794, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9561011904761905, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.957093253968254, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9590773809523809, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9603174603174603, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9608134920634921, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9615575396825397, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9625496031746031, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9640376984126984, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9645337301587301, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9655257936507936, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9670138888888888, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9670138888888888, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.966765873015873, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9675099206349206, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9682539682539683, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9675099206349206, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9677579365079365, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9680059523809523, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9680059523809523, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9680059523809523, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.3594731286384575, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.3812998767661656, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.4040558989414707, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.43126449772466635, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.4496834815205871, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.4771174617728567, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.5083971981095896, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.5370937761137645, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.569658608496933, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.6181811421539344, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.6610294242611336, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.7491817725838251, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.8321169400750515, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.8806621780486265, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9032346147570939, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9126568353572792, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9179789571714406, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9250798000724861, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9289962667252757, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9305498561888528, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.934346391465915, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9369417072524937, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9394938102127062, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.940720972709229, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9426813643002303, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9436164214818038, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9453758901236269, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9465803458165228, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9495472886435983, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9517321813437666, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9523268657687319, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.95424325185434, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.955100725579854, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9555112431553907, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9561616833869748, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9570638649909714, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9578573797110951, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9586073456695888, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9596235865295937, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9615528104524402, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9613518616092327, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9611700029364656, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9621808309270928, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9626198768348221, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9620978977313976, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9622324558521675, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9623471281757057, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9622759111306282, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9620461613804294, "id_best": 43, "lr_best": 0.006599999999999999, "wd_best": 0.05, "train/loss_best": 0.061148731131106616, "validation/loss_best": 0.11311419308185577, "validation/acc_best": 0.9682539682539683, "validation/f1_best": 0.9626198768348221} diff --git a/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__attn/config.yaml b/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__attn/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..508125a5aeac7f6148ffe3447ea514a565594ebb --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__attn/config.yaml @@ -0,0 +1,96 @@ +output_root: experiments/decoders/output +name_prefix: eval_probe +remote_root: null +notes: decoder ablations crossreg_reg4; eval v2 (nsd_cococlip patch attn) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +dataset_kwargs: {} +classifier_kwargs: + embed_dim: null + dropout: 0.0 + xavier_init: false + norm: false +lr_scale_grid: +- 0.02 +- 0.023 +- 0.028 +- 0.033 +- 0.038 +- 0.045 +- 0.053 +- 0.062 +- 0.074 +- 0.087 +- 0.1 +- 0.12 +- 0.14 +- 0.17 +- 0.2 +- 0.23 +- 0.27 +- 0.32 +- 0.38 +- 0.44 +- 0.52 +- 0.61 +- 0.72 +- 0.85 +- 1 +- 1.2 +- 1.4 +- 1.6 +- 1.9 +- 2.3 +- 2.7 +- 3.1 +- 3.7 +- 4.3 +- 5.1 +- 6 +- 7.1 +- 8.3 +- 9.8 +- 12 +- 14 +- 16 +- 19 +- 22 +- 26 +- 31 +- 36 +- 43 +- 50 +wd_scale_grid: +- 1.0 +num_workers: 8 +prefetch_factor: null +balanced_sampling: false +epochs: 20 +steps_per_epoch: 200 +batch_size: 64 +accum_iter: 2 +lr: 0.0003 +warmup_epochs: 5 +no_decay: false +weight_decay: 0.05 +clip_grad: 1.0 +metrics: +- acc +- f1 +cv_metric: acc +early_stopping: true +amp: true +device: cuda +seed: 4466 +debug: false +wandb: false +wandb_entity: null +wandb_project: fMRI-fm-eval +name: decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__attn +model: flat_mae +representation: patch +classifier: attn +dataset: nsd_cococlip +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__attn +remote_dir: null diff --git a/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__attn/eval_log.json b/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__attn/eval_log.json new file mode 100644 index 0000000000000000000000000000000000000000..085f0c12eafcf3f051d3c0199eaa16a87e922a33 --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__attn/eval_log.json @@ -0,0 +1 @@ +{"eval/epoch": 7, "eval/id_best": 24, "eval/lr_best": 0.0003, "eval/wd_best": 0.05, "eval/train/loss": 2.0318095684051514, "eval/train/acc": 0.3866744521958265, "eval/train/acc_std": 0.002387726062369834, "eval/train/f1": 0.3318689003317408, "eval/train/f1_std": 0.0024548955470957705, "eval/validation/loss": 2.3388521671295166, "eval/validation/acc": 0.29992617201919525, "eval/validation/acc_std": 0.005267338133834117, "eval/validation/f1": 0.23211007531295333, "eval/validation/f1_std": 0.00474455591644188, "eval/test/loss": 2.3151602745056152, "eval/test/acc": 0.3096474953617811, "eval/test/acc_std": 0.005315251640359488, "eval/test/f1": 0.2452521830180977, "eval/test/f1_std": 0.00516823939276546, "eval/testid/loss": 2.2194652557373047, "eval/testid/acc": 0.32716406400616926, "eval/testid/acc_std": 0.005763874544401807, "eval/testid/f1": 0.2692919280949952, "eval/testid/f1_std": 0.005573398022299934} diff --git a/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__attn/eval_log_best.json b/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__attn/eval_log_best.json new file mode 100644 index 0000000000000000000000000000000000000000..f4f7f0c6be61db57836fde1c5b20ec2a098cc471 --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__attn/eval_log_best.json @@ -0,0 +1 @@ +{"eval/best/epoch": 7, "eval/best/id_best": 24, "eval/best/lr_best": 0.0003, "eval/best/wd_best": 0.05, "eval/best/train/loss": 2.0318095684051514, "eval/best/train/acc": 0.3866744521958265, "eval/best/train/acc_std": 0.002387726062369834, "eval/best/train/f1": 0.3318689003317408, "eval/best/train/f1_std": 0.0024548955470957705, "eval/best/validation/loss": 2.3388521671295166, "eval/best/validation/acc": 0.29992617201919525, "eval/best/validation/acc_std": 0.005267338133834117, "eval/best/validation/f1": 0.23211007531295333, "eval/best/validation/f1_std": 0.00474455591644188, "eval/best/test/loss": 2.3151602745056152, "eval/best/test/acc": 0.3096474953617811, "eval/best/test/acc_std": 0.005315251640359488, "eval/best/test/f1": 0.2452521830180977, "eval/best/test/f1_std": 0.00516823939276546, "eval/best/testid/loss": 2.2194652557373047, "eval/best/testid/acc": 0.32716406400616926, "eval/best/testid/acc_std": 0.005763874544401807, "eval/best/testid/f1": 0.2692919280949952, "eval/best/testid/f1_std": 0.005573398022299934} diff --git a/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__attn/eval_log_last.json b/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__attn/eval_log_last.json new file mode 100644 index 0000000000000000000000000000000000000000..24323a1a7660b7776d739c51ddc6d65d611169a0 --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__attn/eval_log_last.json @@ -0,0 +1 @@ +{"eval/last/epoch": 19, "eval/last/id_best": 23, "eval/last/lr_best": 0.00025499999999999996, "eval/last/wd_best": 0.05, "eval/last/train/loss": 1.8189494609832764, "eval/last/train/acc": 0.4496450413350134, "eval/last/train/acc_std": 0.002566571503072833, "eval/last/train/f1": 0.40444405344243656, "eval/last/train/f1_std": 0.002820992747921801, "eval/last/validation/loss": 2.393655776977539, "eval/last/validation/acc": 0.29346622369878184, "eval/last/validation/acc_std": 0.0053255077306136964, "eval/last/validation/f1": 0.23157688718453528, "eval/last/validation/f1_std": 0.004943055637392579, "eval/last/test/loss": 2.348196268081665, "eval/last/test/acc": 0.30352504638218925, "eval/last/test/acc_std": 0.005247040047478861, "eval/last/test/f1": 0.24265926290852993, "eval/last/test/f1_std": 0.00521069896700571, "eval/last/testid/loss": 2.1374034881591797, "eval/last/testid/acc": 0.3514555619818778, "eval/last/testid/acc_std": 0.005938160318592481, "eval/last/testid/f1": 0.2999727946799193, "eval/last/testid/f1_std": 0.005947509461892579} diff --git a/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__attn/eval_table.csv b/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__attn/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..c1c76688b0a478b7e97043fafe4b2cb9241eaa7f --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__attn/eval_table.csv @@ -0,0 +1,5 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,patch,attn,nsd_cococlip,best,7,0.0003,0.05,24,"[1, 1.0]",train,2.0318095684051514,0.3866744521958265,0.002387726062369834,0.3318689003317408,0.0024548955470957705 +flat_mae,patch,attn,nsd_cococlip,best,7,0.0003,0.05,24,"[1, 1.0]",validation,2.3388521671295166,0.29992617201919525,0.005267338133834117,0.23211007531295333,0.00474455591644188 +flat_mae,patch,attn,nsd_cococlip,best,7,0.0003,0.05,24,"[1, 1.0]",test,2.3151602745056152,0.3096474953617811,0.005315251640359488,0.2452521830180977,0.00516823939276546 +flat_mae,patch,attn,nsd_cococlip,best,7,0.0003,0.05,24,"[1, 1.0]",testid,2.2194652557373047,0.32716406400616926,0.005763874544401807,0.2692919280949952,0.005573398022299934 diff --git a/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__attn/eval_table_best.csv b/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__attn/eval_table_best.csv new file mode 100644 index 0000000000000000000000000000000000000000..c1c76688b0a478b7e97043fafe4b2cb9241eaa7f --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__attn/eval_table_best.csv @@ -0,0 +1,5 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,patch,attn,nsd_cococlip,best,7,0.0003,0.05,24,"[1, 1.0]",train,2.0318095684051514,0.3866744521958265,0.002387726062369834,0.3318689003317408,0.0024548955470957705 +flat_mae,patch,attn,nsd_cococlip,best,7,0.0003,0.05,24,"[1, 1.0]",validation,2.3388521671295166,0.29992617201919525,0.005267338133834117,0.23211007531295333,0.00474455591644188 +flat_mae,patch,attn,nsd_cococlip,best,7,0.0003,0.05,24,"[1, 1.0]",test,2.3151602745056152,0.3096474953617811,0.005315251640359488,0.2452521830180977,0.00516823939276546 +flat_mae,patch,attn,nsd_cococlip,best,7,0.0003,0.05,24,"[1, 1.0]",testid,2.2194652557373047,0.32716406400616926,0.005763874544401807,0.2692919280949952,0.005573398022299934 diff --git a/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__attn/eval_table_last.csv b/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__attn/eval_table_last.csv new file mode 100644 index 0000000000000000000000000000000000000000..f040feed3217b63167376f83d77e83f6f979beac --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__attn/eval_table_last.csv @@ -0,0 +1,5 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,patch,attn,nsd_cococlip,last,19,0.00025499999999999996,0.05,23,"[0.85, 1.0]",train,1.8189494609832764,0.4496450413350134,0.002566571503072833,0.40444405344243656,0.002820992747921801 +flat_mae,patch,attn,nsd_cococlip,last,19,0.00025499999999999996,0.05,23,"[0.85, 1.0]",validation,2.393655776977539,0.29346622369878184,0.0053255077306136964,0.23157688718453528,0.004943055637392579 +flat_mae,patch,attn,nsd_cococlip,last,19,0.00025499999999999996,0.05,23,"[0.85, 1.0]",test,2.348196268081665,0.30352504638218925,0.005247040047478861,0.24265926290852993,0.00521069896700571 +flat_mae,patch,attn,nsd_cococlip,last,19,0.00025499999999999996,0.05,23,"[0.85, 1.0]",testid,2.1374034881591797,0.3514555619818778,0.005938160318592481,0.2999727946799193,0.005947509461892579 diff --git a/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__attn/log.txt b/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__attn/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..f492b00f1b5d242aec16dcf863312a547c53aca4 --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__attn/log.txt @@ -0,0 +1,1372 @@ +fMRI foundation model probe eval +version: 0.1.dev65+g4003a1397 +sha: 6c01b606db98add5848cecd23e5d599250c0bf86, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-02-24 22:25:30 +config: +output_root: experiments/decoders/output +name_prefix: eval_probe +remote_root: null +notes: decoder ablations crossreg_reg4; eval v2 (nsd_cococlip patch attn) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +dataset_kwargs: {} +classifier_kwargs: + embed_dim: null + dropout: 0.0 + xavier_init: false + norm: false +lr_scale_grid: +- 0.02 +- 0.023 +- 0.028 +- 0.033 +- 0.038 +- 0.045 +- 0.053 +- 0.062 +- 0.074 +- 0.087 +- 0.1 +- 0.12 +- 0.14 +- 0.17 +- 0.2 +- 0.23 +- 0.27 +- 0.32 +- 0.38 +- 0.44 +- 0.52 +- 0.61 +- 0.72 +- 0.85 +- 1 +- 1.2 +- 1.4 +- 1.6 +- 1.9 +- 2.3 +- 2.7 +- 3.1 +- 3.7 +- 4.3 +- 5.1 +- 6 +- 7.1 +- 8.3 +- 9.8 +- 12 +- 14 +- 16 +- 19 +- 22 +- 26 +- 31 +- 36 +- 43 +- 50 +wd_scale_grid: +- 1.0 +num_workers: 8 +prefetch_factor: null +balanced_sampling: false +epochs: 20 +steps_per_epoch: 200 +batch_size: 64 +accum_iter: 2 +lr: 0.0003 +warmup_epochs: 5 +no_decay: false +weight_decay: 0.05 +clip_grad: 1.0 +metrics: +- acc +- f1 +cv_metric: acc +early_stopping: true +amp: true +device: cuda +seed: 4466 +debug: false +wandb: false +wandb_entity: null +wandb_project: fMRI-fm-eval +name: decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__attn +model: flat_mae +representation: patch +classifier: attn +dataset: nsd_cococlip +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__attn +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=False, reg_tokens=4, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: nsd_cococlip (flat) +train (n=32539): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'run', 'trial_id', 'nsd_id', 'category_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 32539 +}), + labels=[ 3 4 5 6 10 11 17 18 19 20 22 23 25 30 31 33 36 37 38 53 55 59 61 74], + counts=[1286 1180 1639 1868 834 824 1026 1042 913 1853 1503 2092 1001 1410 + 794 1241 1904 1872 2267 1428 889 904 1447 1322] +) + +validation (n=5418): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'run', 'trial_id', 'nsd_id', 'category_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 5418 +}), + labels=[ 3 4 5 6 10 11 17 18 19 20 22 23 25 30 31 33 36 37 38 53 55 59 61 74], + counts=[197 161 276 345 126 142 143 185 112 295 285 387 169 250 159 193 316 334 + 343 215 172 141 226 246] +) + +test (n=5390): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'run', 'trial_id', 'nsd_id', 'category_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 5390 +}), + labels=[ 3 4 5 6 10 11 17 18 19 20 22 23 25 30 31 33 36 37 38 53 55 59 61 74], + counts=[202 172 274 298 144 180 134 182 186 293 218 343 165 185 140 177 346 333 + 345 271 165 140 251 246] +) + +testid (n=5187): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'run', 'trial_id', 'nsd_id', 'category_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 5187 +}), + labels=[ 3 4 5 6 10 11 17 18 19 20 22 23 25 30 31 33 36 37 38 53 55 59 61 74], + counts=[197 159 267 273 123 153 175 184 139 310 215 386 153 230 118 192 330 306 + 349 223 143 127 249 186] +) + +running backbone on example batch to get embedding dim +embedding feature dim (patch): 768 +initializing sweep of classifier heads +classifiers: +ModuleList( + (0-48): 49 x AttnPoolClassifier( + (kv): Linear(in_features=768, out_features=1536, bias=True) + (linear): Linear(in_features=768, out_features=24, bias=True) + ) +) +classifier params (train): 58.8M (58.8M) +setting up optimizer +total batch size: 128 = 64 bs per gpu x 2 accum +lr: 3.00e-04 +full schedule: epochs = 20 (steps = 4000) (decay = True) +warmup: epochs = 5 (steps = 1000) +start training for 20 epochs +train: [0] [ 0/400] eta: 0:22:52 lr: nan time: 3.4304 data: 2.9533 max mem: 21740 +train: [0] [ 20/400] eta: 0:03:51 lr: 0.000003 loss: 3.1754 (3.1731) grad: 0.0573 (0.0593) time: 0.4673 data: 0.0076 max mem: 22448 +train: [0] [ 40/400] eta: 0:03:11 lr: 0.000006 loss: 3.1715 (3.1703) grad: 0.0573 (0.0582) time: 0.4501 data: 0.0041 max mem: 22448 +train: [0] [ 60/400] eta: 0:02:52 lr: 0.000009 loss: 3.1652 (3.1680) grad: 0.0554 (0.0575) time: 0.4562 data: 0.0045 max mem: 22448 +train: [0] [ 80/400] eta: 0:02:38 lr: 0.000012 loss: 3.1628 (3.1665) grad: 0.0558 (0.0578) time: 0.4565 data: 0.0041 max mem: 22448 +train: [0] [100/400] eta: 0:02:26 lr: 0.000015 loss: 3.1564 (3.1654) grad: 0.0536 (0.0568) time: 0.4639 data: 0.0043 max mem: 22448 +train: [0] [120/400] eta: 0:02:15 lr: 0.000018 loss: 3.1564 (3.1642) grad: 0.0508 (0.0558) time: 0.4544 data: 0.0042 max mem: 22448 +train: [0] [140/400] eta: 0:02:04 lr: 0.000021 loss: 3.1585 (3.1630) grad: 0.0511 (0.0557) time: 0.4609 data: 0.0043 max mem: 22448 +train: [0] [160/400] eta: 0:01:54 lr: 0.000024 loss: 3.1509 (3.1617) grad: 0.0528 (0.0557) time: 0.4619 data: 0.0044 max mem: 22448 +train: [0] [180/400] eta: 0:01:44 lr: 0.000027 loss: 3.1500 (3.1614) grad: 0.0523 (0.0552) time: 0.4611 data: 0.0041 max mem: 22448 +train: [0] [200/400] eta: 0:01:34 lr: 0.000030 loss: 3.1522 (3.1605) grad: 0.0503 (0.0549) time: 0.4563 data: 0.0042 max mem: 22448 +train: [0] [220/400] eta: 0:01:24 lr: 0.000033 loss: 3.1444 (3.1588) grad: 0.0565 (0.0552) time: 0.4536 data: 0.0041 max mem: 22448 +train: [0] [240/400] eta: 0:01:15 lr: 0.000036 loss: 3.1322 (3.1579) grad: 0.0554 (0.0550) time: 0.4731 data: 0.0042 max mem: 22448 +train: [0] [260/400] eta: 0:01:05 lr: 0.000039 loss: 3.1506 (3.1567) grad: 0.0550 (0.0554) time: 0.4465 data: 0.0043 max mem: 22448 +train: [0] [280/400] eta: 0:00:56 lr: 0.000042 loss: 3.1263 (3.1544) grad: 0.0603 (0.0558) time: 0.4484 data: 0.0042 max mem: 22448 +train: [0] [300/400] eta: 0:00:46 lr: 0.000045 loss: 3.1182 (3.1519) grad: 0.0622 (0.0563) time: 0.4581 data: 0.0043 max mem: 22448 +train: [0] [320/400] eta: 0:00:37 lr: 0.000048 loss: 3.1020 (3.1488) grad: 0.0648 (0.0570) time: 0.4646 data: 0.0042 max mem: 22448 +train: [0] [340/400] eta: 0:00:28 lr: 0.000051 loss: 3.0922 (3.1451) grad: 0.0689 (0.0581) time: 0.4567 data: 0.0044 max mem: 22448 +train: [0] [360/400] eta: 0:00:18 lr: 0.000054 loss: 3.0933 (3.1428) grad: 0.0723 (0.0589) time: 0.4759 data: 0.0042 max mem: 22448 +train: [0] [380/400] eta: 0:00:09 lr: 0.000057 loss: 3.0915 (3.1394) grad: 0.0697 (0.0595) time: 0.4680 data: 0.0043 max mem: 22448 +train: [0] [399/400] eta: 0:00:00 lr: 0.000060 loss: 3.0687 (3.1353) grad: 0.0728 (0.0602) time: 0.4651 data: 0.0041 max mem: 22448 +train: [0] Total time: 0:03:07 (0.4676 s / it) +train: [0] Summary: lr: 0.000060 loss: 3.0687 (3.1353) grad: 0.0728 (0.0602) +eval (validation): [0] [ 0/85] eta: 0:04:50 time: 3.4181 data: 3.1779 max mem: 22448 +eval (validation): [0] [20/85] eta: 0:00:31 time: 0.3444 data: 0.0043 max mem: 22448 +eval (validation): [0] [40/85] eta: 0:00:18 time: 0.3417 data: 0.0033 max mem: 22448 +eval (validation): [0] [60/85] eta: 0:00:09 time: 0.3605 data: 0.0040 max mem: 22448 +eval (validation): [0] [80/85] eta: 0:00:01 time: 0.3476 data: 0.0044 max mem: 22448 +eval (validation): [0] [84/85] eta: 0:00:00 time: 0.3309 data: 0.0041 max mem: 22448 +eval (validation): [0] Total time: 0:00:32 (0.3874 s / it) +cv: [0] best hparam: (50, 1.0) (048) ('048_lr5.0e+01_wd1.0e+00') loss: 2.578 acc: 0.234 f1: 0.160 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__attn/checkpoint-best.pth +train: [1] [ 0/400] eta: 0:22:54 lr: nan time: 3.4361 data: 3.0421 max mem: 22448 +train: [1] [ 20/400] eta: 0:03:43 lr: 0.000063 loss: 3.0525 (3.0621) grad: 0.0752 (0.0766) time: 0.4455 data: 0.0037 max mem: 22448 +train: [1] [ 40/400] eta: 0:03:08 lr: 0.000066 loss: 3.0359 (3.0481) grad: 0.0757 (0.0766) time: 0.4545 data: 0.0040 max mem: 22448 +train: [1] [ 60/400] eta: 0:02:51 lr: 0.000069 loss: 3.0338 (3.0448) grad: 0.0825 (0.0793) time: 0.4632 data: 0.0042 max mem: 22448 +train: [1] [ 80/400] eta: 0:02:37 lr: 0.000072 loss: 3.0231 (3.0357) grad: 0.0844 (0.0812) time: 0.4604 data: 0.0041 max mem: 22448 +train: [1] [100/400] eta: 0:02:25 lr: 0.000075 loss: 3.0116 (3.0298) grad: 0.0848 (0.0818) time: 0.4538 data: 0.0040 max mem: 22448 +train: [1] [120/400] eta: 0:02:14 lr: 0.000078 loss: 3.0002 (3.0248) grad: 0.0851 (0.0829) time: 0.4638 data: 0.0041 max mem: 22448 +train: [1] [140/400] eta: 0:02:04 lr: 0.000081 loss: 2.9953 (3.0211) grad: 0.0851 (0.0834) time: 0.4588 data: 0.0042 max mem: 22448 +train: [1] [160/400] eta: 0:01:53 lr: 0.000084 loss: 2.9905 (3.0177) grad: 0.0900 (0.0847) time: 0.4497 data: 0.0043 max mem: 22448 +train: [1] [180/400] eta: 0:01:44 lr: 0.000087 loss: 2.9905 (3.0145) grad: 0.0928 (0.0863) time: 0.4574 data: 0.0044 max mem: 22448 +train: [1] [200/400] eta: 0:01:34 lr: 0.000090 loss: 2.9732 (3.0093) grad: 0.0912 (0.0869) time: 0.4552 data: 0.0043 max mem: 22448 +train: [1] [220/400] eta: 0:01:24 lr: 0.000093 loss: 2.9594 (3.0043) grad: 0.0939 (0.0876) time: 0.4480 data: 0.0041 max mem: 22448 +train: [1] [240/400] eta: 0:01:15 lr: 0.000096 loss: 2.9349 (2.9988) grad: 0.0955 (0.0884) time: 0.4679 data: 0.0043 max mem: 22448 +train: [1] [260/400] eta: 0:01:05 lr: 0.000099 loss: 2.9357 (2.9944) grad: 0.0976 (0.0894) time: 0.4573 data: 0.0042 max mem: 22448 +train: [1] [280/400] eta: 0:00:56 lr: 0.000102 loss: 2.9460 (2.9917) grad: 0.0968 (0.0897) time: 0.4499 data: 0.0043 max mem: 22448 +train: [1] [300/400] eta: 0:00:46 lr: 0.000105 loss: 2.9572 (2.9883) grad: 0.0903 (0.0899) time: 0.4562 data: 0.0043 max mem: 22448 +train: [1] [320/400] eta: 0:00:37 lr: 0.000108 loss: 2.9245 (2.9844) grad: 0.0928 (0.0906) time: 0.4644 data: 0.0043 max mem: 22448 +train: [1] [340/400] eta: 0:00:27 lr: 0.000111 loss: 2.9068 (2.9808) grad: 0.1035 (0.0915) time: 0.4597 data: 0.0042 max mem: 22448 +train: [1] [360/400] eta: 0:00:18 lr: 0.000114 loss: 2.9089 (2.9765) grad: 0.1082 (0.0927) time: 0.4671 data: 0.0042 max mem: 22448 +train: [1] [380/400] eta: 0:00:09 lr: 0.000117 loss: 2.9098 (2.9732) grad: 0.1031 (0.0930) time: 0.4718 data: 0.0041 max mem: 22448 +train: [1] [399/400] eta: 0:00:00 lr: 0.000120 loss: 2.9261 (2.9731) grad: 0.0985 (0.0934) time: 0.4746 data: 0.0042 max mem: 22448 +train: [1] Total time: 0:03:06 (0.4667 s / it) +train: [1] Summary: lr: 0.000120 loss: 2.9261 (2.9731) grad: 0.0985 (0.0934) +eval (validation): [1] [ 0/85] eta: 0:04:43 time: 3.3376 data: 3.1022 max mem: 22448 +eval (validation): [1] [20/85] eta: 0:00:32 time: 0.3501 data: 0.0048 max mem: 22448 +eval (validation): [1] [40/85] eta: 0:00:19 time: 0.3698 data: 0.0042 max mem: 22448 +eval (validation): [1] [60/85] eta: 0:00:10 time: 0.3429 data: 0.0041 max mem: 22448 +eval (validation): [1] [80/85] eta: 0:00:01 time: 0.3535 data: 0.0045 max mem: 22448 +eval (validation): [1] [84/85] eta: 0:00:00 time: 0.3409 data: 0.0042 max mem: 22448 +eval (validation): [1] Total time: 0:00:33 (0.3917 s / it) +cv: [1] best hparam: (16, 1.0) (041) ('041_lr1.6e+01_wd1.0e+00') loss: 2.458 acc: 0.265 f1: 0.192 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__attn/checkpoint-best.pth +train: [2] [ 0/400] eta: 0:22:39 lr: nan time: 3.3986 data: 3.0122 max mem: 22448 +train: [2] [ 20/400] eta: 0:03:54 lr: 0.000123 loss: 2.8391 (2.8562) grad: 0.1011 (0.1034) time: 0.4770 data: 0.0047 max mem: 22448 +train: [2] [ 40/400] eta: 0:03:14 lr: 0.000126 loss: 2.8605 (2.8725) grad: 0.1148 (0.1125) time: 0.4579 data: 0.0042 max mem: 22448 +train: [2] [ 60/400] eta: 0:02:54 lr: 0.000129 loss: 2.8819 (2.8770) grad: 0.1221 (0.1171) time: 0.4577 data: 0.0043 max mem: 22448 +train: [2] [ 80/400] eta: 0:02:39 lr: 0.000132 loss: 2.8625 (2.8732) grad: 0.1117 (0.1147) time: 0.4528 data: 0.0042 max mem: 22448 +train: [2] [100/400] eta: 0:02:26 lr: 0.000135 loss: 2.8725 (2.8732) grad: 0.1101 (0.1147) time: 0.4581 data: 0.0042 max mem: 22448 +train: [2] [120/400] eta: 0:02:15 lr: 0.000138 loss: 2.8512 (2.8667) grad: 0.1131 (0.1152) time: 0.4633 data: 0.0042 max mem: 22448 +train: [2] [140/400] eta: 0:02:05 lr: 0.000141 loss: 2.8570 (2.8707) grad: 0.1129 (0.1150) time: 0.4576 data: 0.0042 max mem: 22448 +train: [2] [160/400] eta: 0:01:54 lr: 0.000144 loss: 2.8768 (2.8706) grad: 0.1196 (0.1169) time: 0.4585 data: 0.0042 max mem: 22448 +train: [2] [180/400] eta: 0:01:44 lr: 0.000147 loss: 2.8755 (2.8731) grad: 0.1315 (0.1178) time: 0.4604 data: 0.0042 max mem: 22448 +train: [2] [200/400] eta: 0:01:34 lr: 0.000150 loss: 2.8755 (2.8713) grad: 0.1208 (0.1179) time: 0.4451 data: 0.0041 max mem: 22448 +train: [2] [220/400] eta: 0:01:25 lr: 0.000153 loss: 2.8280 (2.8655) grad: 0.1191 (0.1183) time: 0.4608 data: 0.0043 max mem: 22448 +train: [2] [240/400] eta: 0:01:15 lr: 0.000156 loss: 2.7943 (2.8611) grad: 0.1205 (0.1191) time: 0.4568 data: 0.0043 max mem: 22448 +train: [2] [260/400] eta: 0:01:05 lr: 0.000159 loss: 2.7929 (2.8581) grad: 0.1234 (0.1195) time: 0.4571 data: 0.0042 max mem: 22448 +train: [2] [280/400] eta: 0:00:56 lr: 0.000162 loss: 2.8126 (2.8561) grad: 0.1158 (0.1193) time: 0.4633 data: 0.0043 max mem: 22448 +train: [2] [300/400] eta: 0:00:46 lr: 0.000165 loss: 2.8126 (2.8533) grad: 0.1175 (0.1195) time: 0.4595 data: 0.0043 max mem: 22448 +train: [2] [320/400] eta: 0:00:37 lr: 0.000168 loss: 2.7777 (2.8486) grad: 0.1207 (0.1195) time: 0.4528 data: 0.0041 max mem: 22448 +train: [2] [340/400] eta: 0:00:28 lr: 0.000171 loss: 2.7988 (2.8470) grad: 0.1239 (0.1201) time: 0.4701 data: 0.0042 max mem: 22448 +train: [2] [360/400] eta: 0:00:18 lr: 0.000174 loss: 2.8329 (2.8458) grad: 0.1303 (0.1206) time: 0.4801 data: 0.0044 max mem: 22448 +train: [2] [380/400] eta: 0:00:09 lr: 0.000177 loss: 2.8027 (2.8425) grad: 0.1280 (0.1209) time: 0.4564 data: 0.0041 max mem: 22448 +train: [2] [399/400] eta: 0:00:00 lr: 0.000180 loss: 2.7895 (2.8404) grad: 0.1246 (0.1211) time: 0.4736 data: 0.0042 max mem: 22448 +train: [2] Total time: 0:03:07 (0.4686 s / it) +train: [2] Summary: lr: 0.000180 loss: 2.7895 (2.8404) grad: 0.1246 (0.1211) +eval (validation): [2] [ 0/85] eta: 0:04:37 time: 3.2656 data: 2.9785 max mem: 22448 +eval (validation): [2] [20/85] eta: 0:00:32 time: 0.3655 data: 0.0048 max mem: 22448 +eval (validation): [2] [40/85] eta: 0:00:19 time: 0.3616 data: 0.0039 max mem: 22448 +eval (validation): [2] [60/85] eta: 0:00:10 time: 0.3521 data: 0.0043 max mem: 22448 +eval (validation): [2] [80/85] eta: 0:00:01 time: 0.3353 data: 0.0040 max mem: 22448 +eval (validation): [2] [84/85] eta: 0:00:00 time: 0.3295 data: 0.0039 max mem: 22448 +eval (validation): [2] Total time: 0:00:33 (0.3903 s / it) +cv: [2] best hparam: (4.3, 1.0) (033) ('033_lr4.3e+00_wd1.0e+00') loss: 2.413 acc: 0.272 f1: 0.204 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__attn/checkpoint-best.pth +train: [3] [ 0/400] eta: 0:22:18 lr: nan time: 3.3451 data: 3.0034 max mem: 22448 +train: [3] [ 20/400] eta: 0:03:47 lr: 0.000183 loss: 2.7838 (2.7860) grad: 0.1333 (0.1354) time: 0.4602 data: 0.0037 max mem: 22448 +train: [3] [ 40/400] eta: 0:03:08 lr: 0.000186 loss: 2.7724 (2.7664) grad: 0.1333 (0.1344) time: 0.4486 data: 0.0041 max mem: 22448 +train: [3] [ 60/400] eta: 0:02:50 lr: 0.000189 loss: 2.7582 (2.7658) grad: 0.1321 (0.1334) time: 0.4556 data: 0.0043 max mem: 22448 +train: [3] [ 80/400] eta: 0:02:37 lr: 0.000192 loss: 2.7659 (2.7653) grad: 0.1334 (0.1347) time: 0.4601 data: 0.0043 max mem: 22448 +train: [3] [100/400] eta: 0:02:25 lr: 0.000195 loss: 2.7809 (2.7669) grad: 0.1454 (0.1387) time: 0.4625 data: 0.0042 max mem: 22448 +train: [3] [120/400] eta: 0:02:14 lr: 0.000198 loss: 2.7938 (2.7806) grad: 0.1662 (0.1747) time: 0.4600 data: 0.0042 max mem: 22448 +WARNING: classifier 48 (50, 1.0) diverged (loss=70.18 > 63.56) at step 667. Freezing. +train: [3] [140/400] eta: 0:02:04 lr: 0.000201 loss: 2.9428 (2.8554) grad: 0.3937 (0.2812) time: 0.4712 data: 0.0043 max mem: 22448 +train: [3] [160/400] eta: 0:01:54 lr: 0.000204 loss: 2.7453 (2.8369) grad: 0.1282 (0.2613) time: 0.4501 data: 0.0043 max mem: 22448 +train: [3] [180/400] eta: 0:01:44 lr: 0.000207 loss: 2.7172 (2.8254) grad: 0.1236 (0.2464) time: 0.4556 data: 0.0042 max mem: 22448 +train: [3] [200/400] eta: 0:01:34 lr: 0.000210 loss: 2.7209 (2.8167) grad: 0.1311 (0.2352) time: 0.4452 data: 0.0040 max mem: 22448 +train: [3] [220/400] eta: 0:01:24 lr: 0.000213 loss: 2.7296 (2.8121) grad: 0.1331 (0.2262) time: 0.4636 data: 0.0041 max mem: 22448 +train: [3] [240/400] eta: 0:01:15 lr: 0.000216 loss: 2.7296 (2.8065) grad: 0.1344 (0.2183) time: 0.4586 data: 0.0041 max mem: 22448 +train: [3] [260/400] eta: 0:01:05 lr: 0.000219 loss: 2.7468 (2.8044) grad: 0.1361 (0.2123) time: 0.4523 data: 0.0041 max mem: 22448 +train: [3] [280/400] eta: 0:00:56 lr: 0.000222 loss: 2.7806 (2.8040) grad: 0.1347 (0.2065) time: 0.4630 data: 0.0042 max mem: 22448 +train: [3] [300/400] eta: 0:00:46 lr: 0.000225 loss: 2.7758 (2.7989) grad: 0.1303 (0.2017) time: 0.4557 data: 0.0042 max mem: 22448 +train: [3] [320/400] eta: 0:00:37 lr: 0.000228 loss: 2.7307 (2.7975) grad: 0.1348 (0.1978) time: 0.4607 data: 0.0043 max mem: 22448 +train: [3] [340/400] eta: 0:00:28 lr: 0.000231 loss: 2.7290 (2.7943) grad: 0.1373 (0.1943) time: 0.4807 data: 0.0044 max mem: 22448 +train: [3] [360/400] eta: 0:00:18 lr: 0.000234 loss: 2.7239 (2.7907) grad: 0.1437 (0.1922) time: 0.4654 data: 0.0043 max mem: 22448 +train: [3] [380/400] eta: 0:00:09 lr: 0.000237 loss: 2.7570 (2.7897) grad: 0.1505 (0.1902) time: 0.4679 data: 0.0042 max mem: 22448 +train: [3] [399/400] eta: 0:00:00 lr: 0.000240 loss: 2.7470 (2.7874) grad: 0.1531 (0.1884) time: 0.4592 data: 0.0041 max mem: 22448 +train: [3] Total time: 0:03:06 (0.4672 s / it) +train: [3] Summary: lr: 0.000240 loss: 2.7470 (2.7874) grad: 0.1531 (0.1884) +eval (validation): [3] [ 0/85] eta: 0:04:41 time: 3.3096 data: 3.0669 max mem: 22448 +eval (validation): [3] [20/85] eta: 0:00:31 time: 0.3474 data: 0.0037 max mem: 22448 +eval (validation): [3] [40/85] eta: 0:00:18 time: 0.3448 data: 0.0042 max mem: 22448 +eval (validation): [3] [60/85] eta: 0:00:09 time: 0.3533 data: 0.0029 max mem: 22448 +eval (validation): [3] [80/85] eta: 0:00:01 time: 0.3394 data: 0.0040 max mem: 22448 +eval (validation): [3] [84/85] eta: 0:00:00 time: 0.3319 data: 0.0038 max mem: 22448 +eval (validation): [3] Total time: 0:00:32 (0.3836 s / it) +cv: [3] best hparam: (3.1, 1.0) (031) ('031_lr3.1e+00_wd1.0e+00') loss: 2.397 acc: 0.283 f1: 0.207 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__attn/checkpoint-best.pth +train: [4] [ 0/400] eta: 0:22:49 lr: nan time: 3.4234 data: 3.0307 max mem: 22448 +train: [4] [ 20/400] eta: 0:03:51 lr: 0.000243 loss: 2.7357 (2.7349) grad: 0.1606 (0.1585) time: 0.4682 data: 0.0034 max mem: 22448 +train: [4] [ 40/400] eta: 0:03:13 lr: 0.000246 loss: 2.7085 (2.7170) grad: 0.1631 (0.1678) time: 0.4598 data: 0.0044 max mem: 22448 +train: [4] [ 60/400] eta: 0:02:52 lr: 0.000249 loss: 2.7582 (2.7676) grad: 0.1901 (0.2364) time: 0.4447 data: 0.0042 max mem: 22448 +WARNING: classifier 47 (43, 1.0) diverged (loss=113.61 > 63.56) at step 837. Freezing. +train: [4] [ 80/400] eta: 0:02:38 lr: 0.000252 loss: 2.8761 (2.9402) grad: 0.3859 (0.4493) time: 0.4615 data: 0.0043 max mem: 22448 +train: [4] [100/400] eta: 0:02:26 lr: 0.000255 loss: 2.7536 (2.8992) grad: 0.1502 (0.3886) time: 0.4611 data: 0.0044 max mem: 22448 +train: [4] [120/400] eta: 0:02:15 lr: 0.000258 loss: 2.7264 (2.8680) grad: 0.1446 (0.3490) time: 0.4566 data: 0.0042 max mem: 22448 +train: [4] [140/400] eta: 0:02:04 lr: 0.000261 loss: 2.7269 (2.8521) grad: 0.1523 (0.3219) time: 0.4531 data: 0.0043 max mem: 22448 +train: [4] [160/400] eta: 0:01:53 lr: 0.000264 loss: 2.7338 (2.8375) grad: 0.1604 (0.3042) time: 0.4453 data: 0.0044 max mem: 22448 +train: [4] [180/400] eta: 0:01:43 lr: 0.000267 loss: 2.7903 (2.8542) grad: 0.2182 (0.3281) time: 0.4474 data: 0.0043 max mem: 22448 +WARNING: classifier 46 (36, 1.0) diverged (loss=77.06 > 63.56) at step 895. Freezing. +train: [4] [200/400] eta: 0:01:33 lr: 0.000270 loss: 2.8776 (2.8817) grad: 0.4440 (0.3500) time: 0.4537 data: 0.0045 max mem: 22448 +train: [4] [220/400] eta: 0:01:24 lr: 0.000273 loss: 2.7454 (2.8650) grad: 0.1485 (0.3308) time: 0.4480 data: 0.0044 max mem: 22448 +train: [4] [240/400] eta: 0:01:14 lr: 0.000276 loss: 2.6974 (2.8510) grad: 0.1353 (0.3146) time: 0.4447 data: 0.0044 max mem: 22448 +train: [4] [260/400] eta: 0:01:05 lr: 0.000279 loss: 2.6794 (2.8368) grad: 0.1335 (0.3005) time: 0.4637 data: 0.0043 max mem: 22448 +train: [4] [280/400] eta: 0:00:55 lr: 0.000282 loss: 2.6834 (2.8286) grad: 0.1331 (0.2887) time: 0.4455 data: 0.0043 max mem: 22448 +train: [4] [300/400] eta: 0:00:46 lr: 0.000285 loss: 2.6834 (2.8188) grad: 0.1344 (0.2786) time: 0.4452 data: 0.0043 max mem: 22448 +train: [4] [320/400] eta: 0:00:37 lr: 0.000288 loss: 2.6697 (2.8092) grad: 0.1380 (0.2699) time: 0.4576 data: 0.0044 max mem: 22448 +train: [4] [340/400] eta: 0:00:27 lr: 0.000291 loss: 2.6841 (2.8034) grad: 0.1383 (0.2620) time: 0.4791 data: 0.0045 max mem: 22448 +train: [4] [360/400] eta: 0:00:18 lr: 0.000294 loss: 2.6961 (2.7968) grad: 0.1338 (0.2548) time: 0.4545 data: 0.0042 max mem: 22448 +train: [4] [380/400] eta: 0:00:09 lr: 0.000297 loss: 2.6923 (2.7915) grad: 0.1324 (0.2486) time: 0.4744 data: 0.0044 max mem: 22448 +train: [4] [399/400] eta: 0:00:00 lr: 0.000300 loss: 2.6852 (2.7870) grad: 0.1392 (0.2433) time: 0.4553 data: 0.0042 max mem: 22448 +train: [4] Total time: 0:03:05 (0.4637 s / it) +train: [4] Summary: lr: 0.000300 loss: 2.6852 (2.7870) grad: 0.1392 (0.2433) +eval (validation): [4] [ 0/85] eta: 0:04:43 time: 3.3382 data: 3.1111 max mem: 22448 +eval (validation): [4] [20/85] eta: 0:00:31 time: 0.3394 data: 0.0041 max mem: 22448 +eval (validation): [4] [40/85] eta: 0:00:19 time: 0.3864 data: 0.0036 max mem: 22448 +eval (validation): [4] [60/85] eta: 0:00:10 time: 0.3491 data: 0.0044 max mem: 22448 +eval (validation): [4] [80/85] eta: 0:00:01 time: 0.3422 data: 0.0039 max mem: 22448 +eval (validation): [4] [84/85] eta: 0:00:00 time: 0.3333 data: 0.0037 max mem: 22448 +eval (validation): [4] Total time: 0:00:33 (0.3915 s / it) +cv: [4] best hparam: (1.9, 1.0) (028) ('028_lr1.9e+00_wd1.0e+00') loss: 2.429 acc: 0.276 f1: 0.196 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [5] [ 0/400] eta: 0:22:34 lr: nan time: 3.3854 data: 3.0585 max mem: 22448 +train: [5] [ 20/400] eta: 0:03:42 lr: 0.000300 loss: 2.6433 (2.6406) grad: 0.1465 (0.1483) time: 0.4465 data: 0.0039 max mem: 22448 +train: [5] [ 40/400] eta: 0:03:06 lr: 0.000300 loss: 2.6510 (2.6567) grad: 0.1468 (0.1492) time: 0.4455 data: 0.0037 max mem: 22448 +train: [5] [ 60/400] eta: 0:02:48 lr: 0.000300 loss: 2.6503 (2.6540) grad: 0.1482 (0.1489) time: 0.4494 data: 0.0042 max mem: 22448 +train: [5] [ 80/400] eta: 0:02:34 lr: 0.000300 loss: 2.6503 (2.6478) grad: 0.1443 (0.1481) time: 0.4506 data: 0.0043 max mem: 22448 +train: [5] [100/400] eta: 0:02:23 lr: 0.000300 loss: 2.6728 (2.6595) grad: 0.1519 (0.1490) time: 0.4524 data: 0.0043 max mem: 22448 +train: [5] [120/400] eta: 0:02:12 lr: 0.000300 loss: 2.6834 (2.6628) grad: 0.1556 (0.1500) time: 0.4547 data: 0.0044 max mem: 22448 +train: [5] [140/400] eta: 0:02:02 lr: 0.000300 loss: 2.6627 (2.6640) grad: 0.1530 (0.1515) time: 0.4553 data: 0.0043 max mem: 22448 +train: [5] [160/400] eta: 0:01:52 lr: 0.000299 loss: 2.6685 (2.6643) grad: 0.1524 (0.1514) time: 0.4537 data: 0.0044 max mem: 22448 +train: [5] [180/400] eta: 0:01:42 lr: 0.000299 loss: 2.6395 (2.6591) grad: 0.1473 (0.1507) time: 0.4491 data: 0.0044 max mem: 22448 +train: [5] [200/400] eta: 0:01:33 lr: 0.000299 loss: 2.6074 (2.6550) grad: 0.1437 (0.1500) time: 0.4528 data: 0.0043 max mem: 22448 +train: [5] [220/400] eta: 0:01:23 lr: 0.000299 loss: 2.6074 (2.6536) grad: 0.1456 (0.1504) time: 0.4559 data: 0.0042 max mem: 22448 +train: [5] [240/400] eta: 0:01:14 lr: 0.000299 loss: 2.6555 (2.6558) grad: 0.1456 (0.1501) time: 0.4489 data: 0.0041 max mem: 22448 +train: [5] [260/400] eta: 0:01:04 lr: 0.000299 loss: 2.6456 (2.6549) grad: 0.1437 (0.1500) time: 0.4626 data: 0.0041 max mem: 22448 +train: [5] [280/400] eta: 0:00:55 lr: 0.000298 loss: 2.6367 (2.6552) grad: 0.1400 (0.1492) time: 0.4468 data: 0.0042 max mem: 22448 +train: [5] [300/400] eta: 0:00:46 lr: 0.000298 loss: 2.6384 (2.6539) grad: 0.1375 (0.1487) time: 0.4402 data: 0.0041 max mem: 22448 +train: [5] [320/400] eta: 0:00:36 lr: 0.000298 loss: 2.6094 (2.6496) grad: 0.1408 (0.1486) time: 0.4596 data: 0.0042 max mem: 22448 +train: [5] [340/400] eta: 0:00:27 lr: 0.000298 loss: 2.5992 (2.6490) grad: 0.1436 (0.1485) time: 0.4660 data: 0.0043 max mem: 22448 +train: [5] [360/400] eta: 0:00:18 lr: 0.000297 loss: 2.6621 (2.6505) grad: 0.1411 (0.1480) time: 0.4466 data: 0.0041 max mem: 22448 +train: [5] [380/400] eta: 0:00:09 lr: 0.000297 loss: 2.6246 (2.6476) grad: 0.1415 (0.1478) time: 0.4557 data: 0.0041 max mem: 22448 +train: [5] [399/400] eta: 0:00:00 lr: 0.000297 loss: 2.6244 (2.6466) grad: 0.1493 (0.1482) time: 0.4507 data: 0.0043 max mem: 22448 +train: [5] Total time: 0:03:03 (0.4598 s / it) +train: [5] Summary: lr: 0.000297 loss: 2.6244 (2.6466) grad: 0.1493 (0.1482) +eval (validation): [5] [ 0/85] eta: 0:04:44 time: 3.3474 data: 3.1139 max mem: 22448 +eval (validation): [5] [20/85] eta: 0:00:32 time: 0.3531 data: 0.0036 max mem: 22448 +eval (validation): [5] [40/85] eta: 0:00:19 time: 0.3464 data: 0.0038 max mem: 22448 +eval (validation): [5] [60/85] eta: 0:00:09 time: 0.3476 data: 0.0043 max mem: 22448 +eval (validation): [5] [80/85] eta: 0:00:01 time: 0.3360 data: 0.0041 max mem: 22448 +eval (validation): [5] [84/85] eta: 0:00:00 time: 0.3228 data: 0.0039 max mem: 22448 +eval (validation): [5] Total time: 0:00:32 (0.3829 s / it) +cv: [5] best hparam: (0.85, 1.0) (023) ('023_lr8.5e-01_wd1.0e+00') loss: 2.359 acc: 0.285 f1: 0.212 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__attn/checkpoint-best.pth +train: [6] [ 0/400] eta: 0:22:50 lr: nan time: 3.4251 data: 3.0906 max mem: 22448 +train: [6] [ 20/400] eta: 0:03:46 lr: 0.000296 loss: 2.5721 (2.5686) grad: 0.1464 (0.1464) time: 0.4534 data: 0.0033 max mem: 22448 +train: [6] [ 40/400] eta: 0:03:07 lr: 0.000296 loss: 2.5721 (2.5652) grad: 0.1464 (0.1495) time: 0.4445 data: 0.0039 max mem: 22448 +train: [6] [ 60/400] eta: 0:02:49 lr: 0.000296 loss: 2.5738 (2.5681) grad: 0.1445 (0.1474) time: 0.4478 data: 0.0045 max mem: 22448 +train: [6] [ 80/400] eta: 0:02:35 lr: 0.000295 loss: 2.5749 (2.5796) grad: 0.1404 (0.1454) time: 0.4477 data: 0.0043 max mem: 22448 +train: [6] [100/400] eta: 0:02:23 lr: 0.000295 loss: 2.5827 (2.5793) grad: 0.1404 (0.1453) time: 0.4444 data: 0.0042 max mem: 22448 +train: [6] [120/400] eta: 0:02:11 lr: 0.000295 loss: 2.5456 (2.5741) grad: 0.1428 (0.1445) time: 0.4405 data: 0.0041 max mem: 22448 +train: [6] [140/400] eta: 0:02:02 lr: 0.000294 loss: 2.5456 (2.5726) grad: 0.1415 (0.1448) time: 0.4605 data: 0.0042 max mem: 22448 +train: [6] [160/400] eta: 0:01:52 lr: 0.000294 loss: 2.5642 (2.5751) grad: 0.1451 (0.1455) time: 0.4547 data: 0.0041 max mem: 22448 +train: [6] [180/400] eta: 0:01:42 lr: 0.000293 loss: 2.5642 (2.5724) grad: 0.1495 (0.1457) time: 0.4354 data: 0.0041 max mem: 22448 +train: [6] [200/400] eta: 0:01:33 lr: 0.000293 loss: 2.5659 (2.5725) grad: 0.1492 (0.1459) time: 0.4785 data: 0.0042 max mem: 22448 +train: [6] [220/400] eta: 0:01:23 lr: 0.000292 loss: 2.5702 (2.5718) grad: 0.1502 (0.1470) time: 0.4537 data: 0.0043 max mem: 22448 +train: [6] [240/400] eta: 0:01:14 lr: 0.000292 loss: 2.5628 (2.5699) grad: 0.1503 (0.1472) time: 0.4525 data: 0.0043 max mem: 22448 +train: [6] [260/400] eta: 0:01:04 lr: 0.000291 loss: 2.5192 (2.5658) grad: 0.1482 (0.1475) time: 0.4532 data: 0.0043 max mem: 22448 +train: [6] [280/400] eta: 0:00:55 lr: 0.000291 loss: 2.5204 (2.5643) grad: 0.1582 (0.1487) time: 0.4453 data: 0.0043 max mem: 22448 +train: [6] [300/400] eta: 0:00:46 lr: 0.000290 loss: 2.5616 (2.5658) grad: 0.1574 (0.1488) time: 0.4524 data: 0.0043 max mem: 22448 +train: [6] [320/400] eta: 0:00:36 lr: 0.000290 loss: 2.5714 (2.5644) grad: 0.1555 (0.1493) time: 0.4686 data: 0.0043 max mem: 22448 +train: [6] [340/400] eta: 0:00:27 lr: 0.000289 loss: 2.5301 (2.5629) grad: 0.1511 (0.1492) time: 0.4604 data: 0.0043 max mem: 22448 +train: [6] [360/400] eta: 0:00:18 lr: 0.000288 loss: 2.5489 (2.5617) grad: 0.1562 (0.1498) time: 0.4525 data: 0.0043 max mem: 22448 +train: [6] [380/400] eta: 0:00:09 lr: 0.000288 loss: 2.5489 (2.5604) grad: 0.1581 (0.1503) time: 0.4488 data: 0.0041 max mem: 22448 +train: [6] [399/400] eta: 0:00:00 lr: 0.000287 loss: 2.4988 (2.5592) grad: 0.1550 (0.1503) time: 0.4775 data: 0.0044 max mem: 22448 +train: [6] Total time: 0:03:04 (0.4613 s / it) +train: [6] Summary: lr: 0.000287 loss: 2.4988 (2.5592) grad: 0.1550 (0.1503) +eval (validation): [6] [ 0/85] eta: 0:04:41 time: 3.3140 data: 3.0420 max mem: 22448 +eval (validation): [6] [20/85] eta: 0:00:32 time: 0.3568 data: 0.0054 max mem: 22448 +eval (validation): [6] [40/85] eta: 0:00:19 time: 0.3673 data: 0.0042 max mem: 22448 +eval (validation): [6] [60/85] eta: 0:00:10 time: 0.3553 data: 0.0043 max mem: 22448 +eval (validation): [6] [80/85] eta: 0:00:01 time: 0.3307 data: 0.0042 max mem: 22448 +eval (validation): [6] [84/85] eta: 0:00:00 time: 0.3240 data: 0.0040 max mem: 22448 +eval (validation): [6] Total time: 0:00:33 (0.3892 s / it) +cv: [6] best hparam: (1.4, 1.0) (026) ('026_lr1.4e+00_wd1.0e+00') loss: 2.369 acc: 0.291 f1: 0.222 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__attn/checkpoint-best.pth +train: [7] [ 0/400] eta: 0:24:50 lr: nan time: 3.7258 data: 3.3332 max mem: 22448 +train: [7] [ 20/400] eta: 0:03:51 lr: 0.000286 loss: 2.5012 (2.4992) grad: 0.1459 (0.1501) time: 0.4533 data: 0.0026 max mem: 22448 +train: [7] [ 40/400] eta: 0:03:10 lr: 0.000286 loss: 2.5225 (2.5334) grad: 0.1483 (0.1501) time: 0.4441 data: 0.0044 max mem: 22448 +train: [7] [ 60/400] eta: 0:02:49 lr: 0.000285 loss: 2.5336 (2.5299) grad: 0.1467 (0.1499) time: 0.4344 data: 0.0042 max mem: 22448 +train: [7] [ 80/400] eta: 0:02:36 lr: 0.000284 loss: 2.5233 (2.5174) grad: 0.1513 (0.1522) time: 0.4575 data: 0.0042 max mem: 22448 +train: [7] [100/400] eta: 0:02:24 lr: 0.000284 loss: 2.4921 (2.5163) grad: 0.1557 (0.1538) time: 0.4563 data: 0.0043 max mem: 22448 +train: [7] [120/400] eta: 0:02:13 lr: 0.000283 loss: 2.4921 (2.5181) grad: 0.1607 (0.1551) time: 0.4472 data: 0.0042 max mem: 22448 +train: [7] [140/400] eta: 0:02:02 lr: 0.000282 loss: 2.5214 (2.5205) grad: 0.1595 (0.1555) time: 0.4545 data: 0.0042 max mem: 22448 +train: [7] [160/400] eta: 0:01:53 lr: 0.000282 loss: 2.5427 (2.5234) grad: 0.1595 (0.1559) time: 0.4571 data: 0.0042 max mem: 22448 +train: [7] [180/400] eta: 0:01:43 lr: 0.000281 loss: 2.5084 (2.5222) grad: 0.1585 (0.1560) time: 0.4475 data: 0.0043 max mem: 22448 +train: [7] [200/400] eta: 0:01:33 lr: 0.000280 loss: 2.5084 (2.5214) grad: 0.1580 (0.1561) time: 0.4479 data: 0.0041 max mem: 22448 +train: [7] [220/400] eta: 0:01:23 lr: 0.000279 loss: 2.5407 (2.5257) grad: 0.1577 (0.1562) time: 0.4599 data: 0.0042 max mem: 22448 +train: [7] [240/400] eta: 0:01:14 lr: 0.000278 loss: 2.5068 (2.5222) grad: 0.1542 (0.1559) time: 0.4585 data: 0.0042 max mem: 22448 +train: [7] [260/400] eta: 0:01:04 lr: 0.000278 loss: 2.4778 (2.5202) grad: 0.1552 (0.1562) time: 0.4493 data: 0.0041 max mem: 22448 +train: [7] [280/400] eta: 0:00:55 lr: 0.000277 loss: 2.4827 (2.5185) grad: 0.1583 (0.1566) time: 0.4534 data: 0.0042 max mem: 22448 +train: [7] [300/400] eta: 0:00:46 lr: 0.000276 loss: 2.5522 (2.5203) grad: 0.1648 (0.1575) time: 0.4561 data: 0.0044 max mem: 22448 +train: [7] [320/400] eta: 0:00:37 lr: 0.000275 loss: 2.5244 (2.5184) grad: 0.1642 (0.1577) time: 0.4739 data: 0.0043 max mem: 22448 +train: [7] [340/400] eta: 0:00:27 lr: 0.000274 loss: 2.5014 (2.5165) grad: 0.1616 (0.1581) time: 0.4689 data: 0.0041 max mem: 22448 +train: [7] [360/400] eta: 0:00:18 lr: 0.000273 loss: 2.5017 (2.5167) grad: 0.1611 (0.1581) time: 0.4526 data: 0.0040 max mem: 22448 +train: [7] [380/400] eta: 0:00:09 lr: 0.000272 loss: 2.4823 (2.5151) grad: 0.1562 (0.1578) time: 0.4756 data: 0.0043 max mem: 22448 +train: [7] [399/400] eta: 0:00:00 lr: 0.000271 loss: 2.4775 (2.5144) grad: 0.1533 (0.1578) time: 0.4549 data: 0.0042 max mem: 22448 +train: [7] Total time: 0:03:05 (0.4636 s / it) +train: [7] Summary: lr: 0.000271 loss: 2.4775 (2.5144) grad: 0.1533 (0.1578) +eval (validation): [7] [ 0/85] eta: 0:04:44 time: 3.3489 data: 3.0624 max mem: 22448 +eval (validation): [7] [20/85] eta: 0:00:33 time: 0.3729 data: 0.0041 max mem: 22448 +eval (validation): [7] [40/85] eta: 0:00:19 time: 0.3414 data: 0.0039 max mem: 22448 +eval (validation): [7] [60/85] eta: 0:00:10 time: 0.3480 data: 0.0045 max mem: 22448 +eval (validation): [7] [80/85] eta: 0:00:01 time: 0.3343 data: 0.0041 max mem: 22448 +eval (validation): [7] [84/85] eta: 0:00:00 time: 0.3217 data: 0.0037 max mem: 22448 +eval (validation): [7] Total time: 0:00:32 (0.3865 s / it) +cv: [7] best hparam: (1, 1.0) (024) ('024_lr1.0e+00_wd1.0e+00') loss: 2.339 acc: 0.300 f1: 0.232 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__attn/checkpoint-best.pth +train: [8] [ 0/400] eta: 0:22:28 lr: nan time: 3.3717 data: 3.0350 max mem: 22448 +train: [8] [ 20/400] eta: 0:03:39 lr: 0.000270 loss: 2.4320 (2.4419) grad: 0.1540 (0.1565) time: 0.4392 data: 0.0041 max mem: 22448 +train: [8] [ 40/400] eta: 0:03:05 lr: 0.000270 loss: 2.4322 (2.4262) grad: 0.1568 (0.1579) time: 0.4460 data: 0.0041 max mem: 22448 +train: [8] [ 60/400] eta: 0:02:46 lr: 0.000269 loss: 2.4322 (2.4276) grad: 0.1608 (0.1602) time: 0.4434 data: 0.0041 max mem: 22448 +train: [8] [ 80/400] eta: 0:02:34 lr: 0.000268 loss: 2.4681 (2.4458) grad: 0.1608 (0.1601) time: 0.4569 data: 0.0043 max mem: 22448 +train: [8] [100/400] eta: 0:02:22 lr: 0.000267 loss: 2.4703 (2.4448) grad: 0.1604 (0.1597) time: 0.4458 data: 0.0043 max mem: 22448 +train: [8] [120/400] eta: 0:02:11 lr: 0.000266 loss: 2.4657 (2.4454) grad: 0.1632 (0.1611) time: 0.4500 data: 0.0042 max mem: 22448 +train: [8] [140/400] eta: 0:02:01 lr: 0.000265 loss: 2.4106 (2.4395) grad: 0.1580 (0.1600) time: 0.4399 data: 0.0041 max mem: 22448 +train: [8] [160/400] eta: 0:01:51 lr: 0.000264 loss: 2.4106 (2.4442) grad: 0.1580 (0.1607) time: 0.4532 data: 0.0043 max mem: 22448 +train: [8] [180/400] eta: 0:01:42 lr: 0.000263 loss: 2.4810 (2.4468) grad: 0.1636 (0.1615) time: 0.4570 data: 0.0041 max mem: 22448 +train: [8] [200/400] eta: 0:01:32 lr: 0.000262 loss: 2.4810 (2.4546) grad: 0.1634 (0.1621) time: 0.4657 data: 0.0045 max mem: 22448 +train: [8] [220/400] eta: 0:01:23 lr: 0.000260 loss: 2.4524 (2.4532) grad: 0.1616 (0.1624) time: 0.4381 data: 0.0040 max mem: 22448 +train: [8] [240/400] eta: 0:01:13 lr: 0.000259 loss: 2.4249 (2.4542) grad: 0.1624 (0.1626) time: 0.4617 data: 0.0044 max mem: 22448 +train: [8] [260/400] eta: 0:01:04 lr: 0.000258 loss: 2.4246 (2.4532) grad: 0.1644 (0.1629) time: 0.4424 data: 0.0043 max mem: 22448 +train: [8] [280/400] eta: 0:00:55 lr: 0.000257 loss: 2.4283 (2.4543) grad: 0.1627 (0.1625) time: 0.4449 data: 0.0043 max mem: 22448 +train: [8] [300/400] eta: 0:00:45 lr: 0.000256 loss: 2.4351 (2.4545) grad: 0.1585 (0.1626) time: 0.4676 data: 0.0042 max mem: 22448 +train: [8] [320/400] eta: 0:00:36 lr: 0.000255 loss: 2.4246 (2.4542) grad: 0.1619 (0.1632) time: 0.4932 data: 0.0046 max mem: 22448 +train: [8] [340/400] eta: 0:00:27 lr: 0.000254 loss: 2.4514 (2.4558) grad: 0.1619 (0.1633) time: 0.4618 data: 0.0040 max mem: 22448 +train: [8] [360/400] eta: 0:00:18 lr: 0.000253 loss: 2.4661 (2.4579) grad: 0.1674 (0.1639) time: 0.4401 data: 0.0040 max mem: 22448 +train: [8] [380/400] eta: 0:00:09 lr: 0.000252 loss: 2.4941 (2.4598) grad: 0.1603 (0.1632) time: 0.4716 data: 0.0043 max mem: 22448 +train: [8] [399/400] eta: 0:00:00 lr: 0.000250 loss: 2.5069 (2.4612) grad: 0.1586 (0.1632) time: 0.4358 data: 0.0042 max mem: 22448 +train: [8] Total time: 0:03:04 (0.4603 s / it) +train: [8] Summary: lr: 0.000250 loss: 2.5069 (2.4612) grad: 0.1586 (0.1632) +eval (validation): [8] [ 0/85] eta: 0:04:37 time: 3.2668 data: 2.9879 max mem: 22448 +eval (validation): [8] [20/85] eta: 0:00:33 time: 0.3701 data: 0.0247 max mem: 22448 +eval (validation): [8] [40/85] eta: 0:00:19 time: 0.3400 data: 0.0035 max mem: 22448 +eval (validation): [8] [60/85] eta: 0:00:09 time: 0.3189 data: 0.0042 max mem: 22448 +eval (validation): [8] [80/85] eta: 0:00:01 time: 0.3229 data: 0.0041 max mem: 22448 +eval (validation): [8] [84/85] eta: 0:00:00 time: 0.3180 data: 0.0040 max mem: 22448 +eval (validation): [8] Total time: 0:00:31 (0.3742 s / it) +cv: [8] best hparam: (0.72, 1.0) (022) ('022_lr7.2e-01_wd1.0e+00') loss: 2.359 acc: 0.292 f1: 0.217 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [9] [ 0/400] eta: 0:22:57 lr: nan time: 3.4444 data: 3.0702 max mem: 22448 +train: [9] [ 20/400] eta: 0:03:36 lr: 0.000249 loss: 2.3838 (2.3997) grad: 0.1591 (0.1612) time: 0.4266 data: 0.0040 max mem: 22448 +train: [9] [ 40/400] eta: 0:03:01 lr: 0.000248 loss: 2.3838 (2.3743) grad: 0.1580 (0.1583) time: 0.4339 data: 0.0040 max mem: 22448 +train: [9] [ 60/400] eta: 0:02:43 lr: 0.000247 loss: 2.3433 (2.3638) grad: 0.1576 (0.1591) time: 0.4296 data: 0.0043 max mem: 22448 +train: [9] [ 80/400] eta: 0:02:30 lr: 0.000246 loss: 2.3568 (2.3712) grad: 0.1584 (0.1627) time: 0.4402 data: 0.0043 max mem: 22448 +train: [9] [100/400] eta: 0:02:18 lr: 0.000244 loss: 2.3670 (2.3742) grad: 0.1568 (0.1621) time: 0.4306 data: 0.0043 max mem: 22448 +train: [9] [120/400] eta: 0:02:08 lr: 0.000243 loss: 2.3670 (2.3806) grad: 0.1592 (0.1622) time: 0.4412 data: 0.0042 max mem: 22448 +train: [9] [140/400] eta: 0:01:58 lr: 0.000242 loss: 2.4182 (2.3969) grad: 0.1625 (0.1635) time: 0.4329 data: 0.0043 max mem: 22448 +train: [9] [160/400] eta: 0:01:48 lr: 0.000241 loss: 2.4490 (2.4068) grad: 0.1688 (0.1638) time: 0.4314 data: 0.0042 max mem: 22448 +train: [9] [180/400] eta: 0:01:38 lr: 0.000240 loss: 2.4170 (2.4065) grad: 0.1602 (0.1632) time: 0.4240 data: 0.0041 max mem: 22448 +train: [9] [200/400] eta: 0:01:29 lr: 0.000238 loss: 2.3962 (2.4065) grad: 0.1604 (0.1632) time: 0.4488 data: 0.0042 max mem: 22448 +train: [9] [220/400] eta: 0:01:20 lr: 0.000237 loss: 2.4522 (2.4133) grad: 0.1625 (0.1630) time: 0.4406 data: 0.0042 max mem: 22448 +train: [9] [240/400] eta: 0:01:11 lr: 0.000236 loss: 2.4532 (2.4154) grad: 0.1626 (0.1636) time: 0.4524 data: 0.0044 max mem: 22448 +train: [9] [260/400] eta: 0:01:02 lr: 0.000234 loss: 2.3728 (2.4102) grad: 0.1609 (0.1632) time: 0.4404 data: 0.0043 max mem: 22448 +train: [9] [280/400] eta: 0:00:53 lr: 0.000233 loss: 2.3607 (2.4118) grad: 0.1569 (0.1627) time: 0.4364 data: 0.0043 max mem: 22448 +train: [9] [300/400] eta: 0:00:44 lr: 0.000232 loss: 2.4060 (2.4099) grad: 0.1579 (0.1627) time: 0.4531 data: 0.0043 max mem: 22448 +train: [9] [320/400] eta: 0:00:35 lr: 0.000230 loss: 2.3751 (2.4101) grad: 0.1623 (0.1629) time: 0.4832 data: 0.0044 max mem: 22448 +train: [9] [340/400] eta: 0:00:27 lr: 0.000229 loss: 2.3835 (2.4095) grad: 0.1623 (0.1629) time: 0.4568 data: 0.0043 max mem: 22448 +train: [9] [360/400] eta: 0:00:17 lr: 0.000228 loss: 2.3835 (2.4099) grad: 0.1609 (0.1629) time: 0.4404 data: 0.0041 max mem: 22448 +train: [9] [380/400] eta: 0:00:08 lr: 0.000226 loss: 2.3808 (2.4068) grad: 0.1630 (0.1632) time: 0.4561 data: 0.0043 max mem: 22448 +train: [9] [399/400] eta: 0:00:00 lr: 0.000225 loss: 2.3973 (2.4077) grad: 0.1661 (0.1635) time: 0.4410 data: 0.0043 max mem: 22448 +train: [9] Total time: 0:02:59 (0.4499 s / it) +train: [9] Summary: lr: 0.000225 loss: 2.3973 (2.4077) grad: 0.1661 (0.1635) +eval (validation): [9] [ 0/85] eta: 0:04:39 time: 3.2892 data: 3.0476 max mem: 22448 +eval (validation): [9] [20/85] eta: 0:00:31 time: 0.3474 data: 0.0042 max mem: 22448 +eval (validation): [9] [40/85] eta: 0:00:18 time: 0.3429 data: 0.0039 max mem: 22448 +eval (validation): [9] [60/85] eta: 0:00:10 time: 0.3708 data: 0.0045 max mem: 22448 +eval (validation): [9] [80/85] eta: 0:00:01 time: 0.3200 data: 0.0039 max mem: 22448 +eval (validation): [9] [84/85] eta: 0:00:00 time: 0.3186 data: 0.0038 max mem: 22448 +eval (validation): [9] Total time: 0:00:32 (0.3815 s / it) +cv: [9] best hparam: (0.72, 1.0) (022) ('022_lr7.2e-01_wd1.0e+00') loss: 2.352 acc: 0.289 f1: 0.220 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [10] [ 0/400] eta: 0:23:07 lr: nan time: 3.4679 data: 3.0755 max mem: 22448 +train: [10] [ 20/400] eta: 0:03:38 lr: 0.000224 loss: 2.3342 (2.3404) grad: 0.1568 (0.1561) time: 0.4312 data: 0.0041 max mem: 22448 +train: [10] [ 40/400] eta: 0:03:02 lr: 0.000222 loss: 2.3497 (2.3546) grad: 0.1575 (0.1582) time: 0.4330 data: 0.0038 max mem: 22448 +train: [10] [ 60/400] eta: 0:02:44 lr: 0.000221 loss: 2.3528 (2.3625) grad: 0.1636 (0.1590) time: 0.4398 data: 0.0041 max mem: 22448 +train: [10] [ 80/400] eta: 0:02:31 lr: 0.000220 loss: 2.3818 (2.3822) grad: 0.1613 (0.1590) time: 0.4395 data: 0.0041 max mem: 22448 +train: [10] [100/400] eta: 0:02:19 lr: 0.000218 loss: 2.3818 (2.3775) grad: 0.1613 (0.1595) time: 0.4365 data: 0.0043 max mem: 22448 +train: [10] [120/400] eta: 0:02:09 lr: 0.000217 loss: 2.3404 (2.3700) grad: 0.1658 (0.1600) time: 0.4395 data: 0.0042 max mem: 22448 +train: [10] [140/400] eta: 0:01:59 lr: 0.000215 loss: 2.2949 (2.3655) grad: 0.1663 (0.1616) time: 0.4371 data: 0.0041 max mem: 22448 +train: [10] [160/400] eta: 0:01:49 lr: 0.000214 loss: 2.3569 (2.3641) grad: 0.1663 (0.1622) time: 0.4392 data: 0.0042 max mem: 22448 +train: [10] [180/400] eta: 0:01:39 lr: 0.000213 loss: 2.3916 (2.3707) grad: 0.1693 (0.1641) time: 0.4345 data: 0.0041 max mem: 22448 +train: [10] [200/400] eta: 0:01:30 lr: 0.000211 loss: 2.3962 (2.3728) grad: 0.1781 (0.1653) time: 0.4485 data: 0.0042 max mem: 22448 +train: [10] [220/400] eta: 0:01:21 lr: 0.000210 loss: 2.3595 (2.3726) grad: 0.1697 (0.1659) time: 0.4398 data: 0.0041 max mem: 22448 +train: [10] [240/400] eta: 0:01:12 lr: 0.000208 loss: 2.3771 (2.3765) grad: 0.1689 (0.1662) time: 0.4404 data: 0.0040 max mem: 22448 +train: [10] [260/400] eta: 0:01:03 lr: 0.000207 loss: 2.4207 (2.3812) grad: 0.1668 (0.1664) time: 0.4447 data: 0.0042 max mem: 22448 +train: [10] [280/400] eta: 0:00:53 lr: 0.000205 loss: 2.4012 (2.3805) grad: 0.1668 (0.1662) time: 0.4438 data: 0.0041 max mem: 22448 +train: [10] [300/400] eta: 0:00:44 lr: 0.000204 loss: 2.3722 (2.3816) grad: 0.1678 (0.1663) time: 0.4451 data: 0.0041 max mem: 22448 +train: [10] [320/400] eta: 0:00:36 lr: 0.000202 loss: 2.3294 (2.3772) grad: 0.1682 (0.1663) time: 0.4765 data: 0.0041 max mem: 22448 +train: [10] [340/400] eta: 0:00:27 lr: 0.000201 loss: 2.3294 (2.3752) grad: 0.1644 (0.1662) time: 0.4507 data: 0.0041 max mem: 22448 +train: [10] [360/400] eta: 0:00:18 lr: 0.000199 loss: 2.3321 (2.3739) grad: 0.1643 (0.1661) time: 0.4495 data: 0.0041 max mem: 22448 +train: [10] [380/400] eta: 0:00:09 lr: 0.000198 loss: 2.3372 (2.3728) grad: 0.1655 (0.1663) time: 0.4652 data: 0.0042 max mem: 22448 +train: [10] [399/400] eta: 0:00:00 lr: 0.000196 loss: 2.3372 (2.3723) grad: 0.1711 (0.1667) time: 0.4417 data: 0.0041 max mem: 22448 +train: [10] Total time: 0:03:00 (0.4517 s / it) +train: [10] Summary: lr: 0.000196 loss: 2.3372 (2.3723) grad: 0.1711 (0.1667) +eval (validation): [10] [ 0/85] eta: 0:04:36 time: 3.2538 data: 2.9714 max mem: 22448 +eval (validation): [10] [20/85] eta: 0:00:32 time: 0.3581 data: 0.0053 max mem: 22448 +eval (validation): [10] [40/85] eta: 0:00:19 time: 0.3451 data: 0.0038 max mem: 22448 +eval (validation): [10] [60/85] eta: 0:00:09 time: 0.3363 data: 0.0042 max mem: 22448 +eval (validation): [10] [80/85] eta: 0:00:01 time: 0.3212 data: 0.0040 max mem: 22448 +eval (validation): [10] [84/85] eta: 0:00:00 time: 0.3173 data: 0.0039 max mem: 22448 +eval (validation): [10] Total time: 0:00:31 (0.3761 s / it) +cv: [10] best hparam: (0.52, 1.0) (020) ('020_lr5.2e-01_wd1.0e+00') loss: 2.364 acc: 0.287 f1: 0.217 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [11] [ 0/400] eta: 0:22:26 lr: nan time: 3.3667 data: 3.0285 max mem: 22448 +train: [11] [ 20/400] eta: 0:03:46 lr: 0.000195 loss: 2.3115 (2.3237) grad: 0.1653 (0.1727) time: 0.4572 data: 0.0053 max mem: 22448 +train: [11] [ 40/400] eta: 0:03:06 lr: 0.000193 loss: 2.2673 (2.2945) grad: 0.1640 (0.1670) time: 0.4383 data: 0.0043 max mem: 22448 +train: [11] [ 60/400] eta: 0:02:47 lr: 0.000192 loss: 2.2491 (2.3188) grad: 0.1677 (0.1701) time: 0.4392 data: 0.0042 max mem: 22448 +train: [11] [ 80/400] eta: 0:02:33 lr: 0.000190 loss: 2.3931 (2.3285) grad: 0.1706 (0.1706) time: 0.4353 data: 0.0042 max mem: 22448 +train: [11] [100/400] eta: 0:02:21 lr: 0.000189 loss: 2.3510 (2.3393) grad: 0.1700 (0.1707) time: 0.4390 data: 0.0042 max mem: 22448 +train: [11] [120/400] eta: 0:02:10 lr: 0.000187 loss: 2.3469 (2.3373) grad: 0.1709 (0.1711) time: 0.4444 data: 0.0042 max mem: 22448 +train: [11] [140/400] eta: 0:01:59 lr: 0.000186 loss: 2.3351 (2.3350) grad: 0.1660 (0.1702) time: 0.4316 data: 0.0042 max mem: 22448 +train: [11] [160/400] eta: 0:01:50 lr: 0.000184 loss: 2.3351 (2.3356) grad: 0.1655 (0.1702) time: 0.4364 data: 0.0044 max mem: 22448 +train: [11] [180/400] eta: 0:01:40 lr: 0.000183 loss: 2.3587 (2.3400) grad: 0.1743 (0.1710) time: 0.4348 data: 0.0043 max mem: 22448 +train: [11] [200/400] eta: 0:01:31 lr: 0.000181 loss: 2.3587 (2.3417) grad: 0.1741 (0.1710) time: 0.4516 data: 0.0044 max mem: 22448 +train: [11] [220/400] eta: 0:01:21 lr: 0.000180 loss: 2.3457 (2.3424) grad: 0.1687 (0.1704) time: 0.4388 data: 0.0045 max mem: 22448 +train: [11] [240/400] eta: 0:01:12 lr: 0.000178 loss: 2.3249 (2.3404) grad: 0.1627 (0.1699) time: 0.4359 data: 0.0044 max mem: 22448 +train: [11] [260/400] eta: 0:01:03 lr: 0.000177 loss: 2.3402 (2.3410) grad: 0.1655 (0.1695) time: 0.4393 data: 0.0042 max mem: 22448 +train: [11] [280/400] eta: 0:00:54 lr: 0.000175 loss: 2.3160 (2.3386) grad: 0.1660 (0.1694) time: 0.4486 data: 0.0043 max mem: 22448 +train: [11] [300/400] eta: 0:00:45 lr: 0.000174 loss: 2.3160 (2.3394) grad: 0.1664 (0.1693) time: 0.4441 data: 0.0043 max mem: 22448 +train: [11] [320/400] eta: 0:00:36 lr: 0.000172 loss: 2.3237 (2.3367) grad: 0.1658 (0.1691) time: 0.4667 data: 0.0043 max mem: 22448 +train: [11] [340/400] eta: 0:00:27 lr: 0.000170 loss: 2.2802 (2.3336) grad: 0.1650 (0.1691) time: 0.4414 data: 0.0043 max mem: 22448 +train: [11] [360/400] eta: 0:00:18 lr: 0.000169 loss: 2.2805 (2.3310) grad: 0.1642 (0.1688) time: 0.4608 data: 0.0042 max mem: 22448 +train: [11] [380/400] eta: 0:00:09 lr: 0.000167 loss: 2.3044 (2.3321) grad: 0.1642 (0.1689) time: 0.4487 data: 0.0042 max mem: 22448 +train: [11] [399/400] eta: 0:00:00 lr: 0.000166 loss: 2.3303 (2.3312) grad: 0.1684 (0.1689) time: 0.4483 data: 0.0044 max mem: 22448 +train: [11] Total time: 0:03:00 (0.4516 s / it) +train: [11] Summary: lr: 0.000166 loss: 2.3303 (2.3312) grad: 0.1684 (0.1689) +eval (validation): [11] [ 0/85] eta: 0:04:31 time: 3.1996 data: 2.9098 max mem: 22448 +eval (validation): [11] [20/85] eta: 0:00:33 time: 0.3784 data: 0.0051 max mem: 22448 +eval (validation): [11] [40/85] eta: 0:00:19 time: 0.3350 data: 0.0036 max mem: 22448 +eval (validation): [11] [60/85] eta: 0:00:09 time: 0.3283 data: 0.0044 max mem: 22448 +eval (validation): [11] [80/85] eta: 0:00:01 time: 0.3182 data: 0.0039 max mem: 22448 +eval (validation): [11] [84/85] eta: 0:00:00 time: 0.3161 data: 0.0038 max mem: 22448 +eval (validation): [11] Total time: 0:00:31 (0.3760 s / it) +cv: [11] best hparam: (0.72, 1.0) (022) ('022_lr7.2e-01_wd1.0e+00') loss: 2.386 acc: 0.288 f1: 0.226 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [12] [ 0/400] eta: 0:23:15 lr: nan time: 3.4875 data: 3.1106 max mem: 22448 +train: [12] [ 20/400] eta: 0:03:43 lr: 0.000164 loss: 2.2850 (2.3004) grad: 0.1724 (0.1724) time: 0.4428 data: 0.0037 max mem: 22448 +train: [12] [ 40/400] eta: 0:03:06 lr: 0.000163 loss: 2.2710 (2.2604) grad: 0.1647 (0.1678) time: 0.4439 data: 0.0042 max mem: 22448 +train: [12] [ 60/400] eta: 0:02:46 lr: 0.000161 loss: 2.2339 (2.2622) grad: 0.1680 (0.1701) time: 0.4356 data: 0.0042 max mem: 22448 +train: [12] [ 80/400] eta: 0:02:32 lr: 0.000160 loss: 2.2871 (2.2788) grad: 0.1737 (0.1724) time: 0.4315 data: 0.0044 max mem: 22448 +train: [12] [100/400] eta: 0:02:20 lr: 0.000158 loss: 2.2871 (2.2783) grad: 0.1809 (0.1744) time: 0.4413 data: 0.0042 max mem: 22448 +train: [12] [120/400] eta: 0:02:09 lr: 0.000156 loss: 2.2649 (2.2757) grad: 0.1777 (0.1742) time: 0.4371 data: 0.0042 max mem: 22448 +train: [12] [140/400] eta: 0:01:59 lr: 0.000155 loss: 2.2744 (2.2797) grad: 0.1680 (0.1733) time: 0.4401 data: 0.0041 max mem: 22448 +train: [12] [160/400] eta: 0:01:50 lr: 0.000153 loss: 2.2867 (2.2765) grad: 0.1685 (0.1732) time: 0.4468 data: 0.0042 max mem: 22448 +train: [12] [180/400] eta: 0:01:40 lr: 0.000152 loss: 2.2946 (2.2798) grad: 0.1681 (0.1722) time: 0.4358 data: 0.0040 max mem: 22448 +train: [12] [200/400] eta: 0:01:31 lr: 0.000150 loss: 2.2748 (2.2761) grad: 0.1634 (0.1710) time: 0.4635 data: 0.0041 max mem: 22448 +train: [12] [220/400] eta: 0:01:21 lr: 0.000149 loss: 2.2460 (2.2765) grad: 0.1645 (0.1708) time: 0.4399 data: 0.0044 max mem: 22448 +train: [12] [240/400] eta: 0:01:12 lr: 0.000147 loss: 2.2476 (2.2760) grad: 0.1665 (0.1709) time: 0.4393 data: 0.0042 max mem: 22448 +train: [12] [260/400] eta: 0:01:03 lr: 0.000145 loss: 2.2916 (2.2819) grad: 0.1732 (0.1713) time: 0.4377 data: 0.0041 max mem: 22448 +train: [12] [280/400] eta: 0:00:54 lr: 0.000144 loss: 2.3191 (2.2814) grad: 0.1732 (0.1712) time: 0.4544 data: 0.0042 max mem: 22448 +train: [12] [300/400] eta: 0:00:45 lr: 0.000142 loss: 2.2900 (2.2835) grad: 0.1691 (0.1711) time: 0.4494 data: 0.0041 max mem: 22448 +train: [12] [320/400] eta: 0:00:36 lr: 0.000141 loss: 2.2900 (2.2852) grad: 0.1648 (0.1709) time: 0.4655 data: 0.0041 max mem: 22448 +train: [12] [340/400] eta: 0:00:27 lr: 0.000139 loss: 2.2857 (2.2852) grad: 0.1666 (0.1710) time: 0.4492 data: 0.0040 max mem: 22448 +train: [12] [360/400] eta: 0:00:18 lr: 0.000138 loss: 2.2705 (2.2834) grad: 0.1695 (0.1711) time: 0.4483 data: 0.0041 max mem: 22448 +train: [12] [380/400] eta: 0:00:09 lr: 0.000136 loss: 2.2619 (2.2832) grad: 0.1677 (0.1707) time: 0.4573 data: 0.0042 max mem: 22448 +train: [12] [399/400] eta: 0:00:00 lr: 0.000134 loss: 2.3260 (2.2867) grad: 0.1682 (0.1707) time: 0.4421 data: 0.0041 max mem: 22448 +train: [12] Total time: 0:03:01 (0.4529 s / it) +train: [12] Summary: lr: 0.000134 loss: 2.3260 (2.2867) grad: 0.1682 (0.1707) +eval (validation): [12] [ 0/85] eta: 0:04:39 time: 3.2924 data: 3.0596 max mem: 22448 +eval (validation): [12] [20/85] eta: 0:00:31 time: 0.3429 data: 0.0032 max mem: 22448 +eval (validation): [12] [40/85] eta: 0:00:18 time: 0.3447 data: 0.0040 max mem: 22448 +eval (validation): [12] [60/85] eta: 0:00:09 time: 0.3655 data: 0.0046 max mem: 22448 +eval (validation): [12] [80/85] eta: 0:00:01 time: 0.3204 data: 0.0037 max mem: 22448 +eval (validation): [12] [84/85] eta: 0:00:00 time: 0.3181 data: 0.0037 max mem: 22448 +eval (validation): [12] Total time: 0:00:32 (0.3807 s / it) +cv: [12] best hparam: (0.72, 1.0) (022) ('022_lr7.2e-01_wd1.0e+00') loss: 2.372 acc: 0.291 f1: 0.225 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [13] [ 0/400] eta: 0:22:58 lr: nan time: 3.4464 data: 3.0620 max mem: 22448 +train: [13] [ 20/400] eta: 0:03:45 lr: 0.000133 loss: 2.2670 (2.2825) grad: 0.1677 (0.1705) time: 0.4500 data: 0.0046 max mem: 22448 +train: [13] [ 40/400] eta: 0:03:05 lr: 0.000131 loss: 2.2346 (2.2618) grad: 0.1665 (0.1678) time: 0.4316 data: 0.0043 max mem: 22448 +train: [13] [ 60/400] eta: 0:02:47 lr: 0.000130 loss: 2.2449 (2.2611) grad: 0.1665 (0.1695) time: 0.4488 data: 0.0042 max mem: 22448 +train: [13] [ 80/400] eta: 0:02:34 lr: 0.000128 loss: 2.2371 (2.2507) grad: 0.1695 (0.1696) time: 0.4503 data: 0.0041 max mem: 22448 +train: [13] [100/400] eta: 0:02:22 lr: 0.000127 loss: 2.2085 (2.2431) grad: 0.1661 (0.1688) time: 0.4385 data: 0.0042 max mem: 22448 +train: [13] [120/400] eta: 0:02:11 lr: 0.000125 loss: 2.2121 (2.2416) grad: 0.1658 (0.1680) time: 0.4426 data: 0.0041 max mem: 22448 +train: [13] [140/400] eta: 0:02:00 lr: 0.000124 loss: 2.1959 (2.2356) grad: 0.1658 (0.1681) time: 0.4364 data: 0.0042 max mem: 22448 +train: [13] [160/400] eta: 0:01:50 lr: 0.000122 loss: 2.1959 (2.2330) grad: 0.1668 (0.1681) time: 0.4380 data: 0.0041 max mem: 22448 +train: [13] [180/400] eta: 0:01:40 lr: 0.000120 loss: 2.2306 (2.2377) grad: 0.1640 (0.1682) time: 0.4414 data: 0.0041 max mem: 22448 +train: [13] [200/400] eta: 0:01:31 lr: 0.000119 loss: 2.2645 (2.2366) grad: 0.1647 (0.1680) time: 0.4461 data: 0.0042 max mem: 22448 +train: [13] [220/400] eta: 0:01:22 lr: 0.000117 loss: 2.2387 (2.2384) grad: 0.1671 (0.1678) time: 0.4547 data: 0.0047 max mem: 22448 +train: [13] [240/400] eta: 0:01:12 lr: 0.000116 loss: 2.2635 (2.2413) grad: 0.1687 (0.1681) time: 0.4380 data: 0.0044 max mem: 22448 +train: [13] [260/400] eta: 0:01:03 lr: 0.000114 loss: 2.2544 (2.2410) grad: 0.1730 (0.1681) time: 0.4482 data: 0.0042 max mem: 22448 +train: [13] [280/400] eta: 0:00:54 lr: 0.000113 loss: 2.2532 (2.2443) grad: 0.1706 (0.1684) time: 0.4568 data: 0.0044 max mem: 22448 +train: [13] [300/400] eta: 0:00:45 lr: 0.000111 loss: 2.2698 (2.2462) grad: 0.1706 (0.1685) time: 0.4431 data: 0.0042 max mem: 22448 +train: [13] [320/400] eta: 0:00:36 lr: 0.000110 loss: 2.2338 (2.2444) grad: 0.1672 (0.1684) time: 0.4626 data: 0.0042 max mem: 22448 +train: [13] [340/400] eta: 0:00:27 lr: 0.000108 loss: 2.1813 (2.2431) grad: 0.1665 (0.1684) time: 0.4572 data: 0.0043 max mem: 22448 +train: [13] [360/400] eta: 0:00:18 lr: 0.000107 loss: 2.2578 (2.2433) grad: 0.1676 (0.1683) time: 0.4434 data: 0.0042 max mem: 22448 +train: [13] [380/400] eta: 0:00:09 lr: 0.000105 loss: 2.2760 (2.2441) grad: 0.1676 (0.1684) time: 0.4557 data: 0.0042 max mem: 22448 +train: [13] [399/400] eta: 0:00:00 lr: 0.000104 loss: 2.2644 (2.2458) grad: 0.1668 (0.1685) time: 0.4426 data: 0.0040 max mem: 22448 +train: [13] Total time: 0:03:01 (0.4541 s / it) +train: [13] Summary: lr: 0.000104 loss: 2.2644 (2.2458) grad: 0.1668 (0.1685) +eval (validation): [13] [ 0/85] eta: 0:04:39 time: 3.2877 data: 3.0001 max mem: 22448 +eval (validation): [13] [20/85] eta: 0:00:34 time: 0.3850 data: 0.0047 max mem: 22448 +eval (validation): [13] [40/85] eta: 0:00:19 time: 0.3491 data: 0.0039 max mem: 22448 +eval (validation): [13] [60/85] eta: 0:00:10 time: 0.3363 data: 0.0046 max mem: 22448 +eval (validation): [13] [80/85] eta: 0:00:01 time: 0.3218 data: 0.0037 max mem: 22448 +eval (validation): [13] [84/85] eta: 0:00:00 time: 0.3193 data: 0.0038 max mem: 22448 +eval (validation): [13] Total time: 0:00:32 (0.3849 s / it) +cv: [13] best hparam: (0.72, 1.0) (022) ('022_lr7.2e-01_wd1.0e+00') loss: 2.395 acc: 0.289 f1: 0.224 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [14] [ 0/400] eta: 0:22:47 lr: nan time: 3.4189 data: 3.0495 max mem: 22448 +train: [14] [ 20/400] eta: 0:03:41 lr: 0.000102 loss: 2.1622 (2.1791) grad: 0.1643 (0.1649) time: 0.4419 data: 0.0049 max mem: 22448 +train: [14] [ 40/400] eta: 0:03:04 lr: 0.000101 loss: 2.1904 (2.2029) grad: 0.1658 (0.1682) time: 0.4394 data: 0.0038 max mem: 22448 +train: [14] [ 60/400] eta: 0:02:46 lr: 0.000099 loss: 2.1904 (2.1942) grad: 0.1672 (0.1675) time: 0.4454 data: 0.0043 max mem: 22448 +train: [14] [ 80/400] eta: 0:02:33 lr: 0.000098 loss: 2.1695 (2.1956) grad: 0.1672 (0.1692) time: 0.4431 data: 0.0045 max mem: 22448 +train: [14] [100/400] eta: 0:02:21 lr: 0.000096 loss: 2.2275 (2.1959) grad: 0.1710 (0.1691) time: 0.4375 data: 0.0042 max mem: 22448 +train: [14] [120/400] eta: 0:02:10 lr: 0.000095 loss: 2.2328 (2.2031) grad: 0.1658 (0.1691) time: 0.4451 data: 0.0041 max mem: 22448 +train: [14] [140/400] eta: 0:02:00 lr: 0.000093 loss: 2.2207 (2.2062) grad: 0.1658 (0.1693) time: 0.4386 data: 0.0041 max mem: 22448 +train: [14] [160/400] eta: 0:01:50 lr: 0.000092 loss: 2.2404 (2.2161) grad: 0.1730 (0.1703) time: 0.4388 data: 0.0042 max mem: 22448 +train: [14] [180/400] eta: 0:01:40 lr: 0.000090 loss: 2.2489 (2.2222) grad: 0.1765 (0.1711) time: 0.4305 data: 0.0041 max mem: 22448 +train: [14] [200/400] eta: 0:01:31 lr: 0.000089 loss: 2.2224 (2.2213) grad: 0.1683 (0.1708) time: 0.4555 data: 0.0041 max mem: 22448 +train: [14] [220/400] eta: 0:01:21 lr: 0.000088 loss: 2.1691 (2.2181) grad: 0.1632 (0.1707) time: 0.4423 data: 0.0042 max mem: 22448 +train: [14] [240/400] eta: 0:01:12 lr: 0.000086 loss: 2.2291 (2.2210) grad: 0.1632 (0.1701) time: 0.4541 data: 0.0041 max mem: 22448 +train: [14] [260/400] eta: 0:01:03 lr: 0.000085 loss: 2.2291 (2.2177) grad: 0.1638 (0.1699) time: 0.4513 data: 0.0042 max mem: 22448 +train: [14] [280/400] eta: 0:00:54 lr: 0.000083 loss: 2.2028 (2.2160) grad: 0.1689 (0.1700) time: 0.4496 data: 0.0042 max mem: 22448 +train: [14] [300/400] eta: 0:00:45 lr: 0.000082 loss: 2.2040 (2.2151) grad: 0.1727 (0.1702) time: 0.4438 data: 0.0043 max mem: 22448 +train: [14] [320/400] eta: 0:00:36 lr: 0.000081 loss: 2.1882 (2.2152) grad: 0.1705 (0.1699) time: 0.4638 data: 0.0045 max mem: 22448 +train: [14] [340/400] eta: 0:00:27 lr: 0.000079 loss: 2.1939 (2.2162) grad: 0.1739 (0.1703) time: 0.4635 data: 0.0044 max mem: 22448 +train: [14] [360/400] eta: 0:00:18 lr: 0.000078 loss: 2.2238 (2.2193) grad: 0.1739 (0.1704) time: 0.4394 data: 0.0042 max mem: 22448 +train: [14] [380/400] eta: 0:00:09 lr: 0.000076 loss: 2.1878 (2.2163) grad: 0.1681 (0.1702) time: 0.4643 data: 0.0043 max mem: 22448 +train: [14] [399/400] eta: 0:00:00 lr: 0.000075 loss: 2.1873 (2.2166) grad: 0.1661 (0.1702) time: 0.4461 data: 0.0042 max mem: 22448 +train: [14] Total time: 0:03:01 (0.4543 s / it) +train: [14] Summary: lr: 0.000075 loss: 2.1873 (2.2166) grad: 0.1661 (0.1702) +eval (validation): [14] [ 0/85] eta: 0:04:38 time: 3.2806 data: 3.0060 max mem: 22448 +eval (validation): [14] [20/85] eta: 0:00:33 time: 0.3755 data: 0.0053 max mem: 22448 +eval (validation): [14] [40/85] eta: 0:00:19 time: 0.3613 data: 0.0037 max mem: 22448 +eval (validation): [14] [60/85] eta: 0:00:10 time: 0.3523 data: 0.0044 max mem: 22448 +eval (validation): [14] [80/85] eta: 0:00:01 time: 0.3216 data: 0.0039 max mem: 22448 +eval (validation): [14] [84/85] eta: 0:00:00 time: 0.3163 data: 0.0037 max mem: 22448 +eval (validation): [14] Total time: 0:00:33 (0.3889 s / it) +cv: [14] best hparam: (0.61, 1.0) (021) ('021_lr6.1e-01_wd1.0e+00') loss: 2.370 acc: 0.291 f1: 0.223 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [15] [ 0/400] eta: 0:22:31 lr: nan time: 3.3794 data: 3.0533 max mem: 22448 +train: [15] [ 20/400] eta: 0:03:37 lr: 0.000074 loss: 2.1877 (2.1917) grad: 0.1595 (0.1614) time: 0.4322 data: 0.0052 max mem: 22448 +train: [15] [ 40/400] eta: 0:03:02 lr: 0.000072 loss: 2.1358 (2.1485) grad: 0.1631 (0.1641) time: 0.4399 data: 0.0038 max mem: 22448 +train: [15] [ 60/400] eta: 0:02:45 lr: 0.000071 loss: 2.1344 (2.1643) grad: 0.1669 (0.1657) time: 0.4419 data: 0.0043 max mem: 22448 +train: [15] [ 80/400] eta: 0:02:32 lr: 0.000070 loss: 2.1574 (2.1542) grad: 0.1644 (0.1655) time: 0.4529 data: 0.0043 max mem: 22448 +train: [15] [100/400] eta: 0:02:21 lr: 0.000068 loss: 2.1762 (2.1671) grad: 0.1629 (0.1657) time: 0.4441 data: 0.0043 max mem: 22448 +train: [15] [120/400] eta: 0:02:10 lr: 0.000067 loss: 2.2033 (2.1665) grad: 0.1636 (0.1665) time: 0.4371 data: 0.0043 max mem: 22448 +train: [15] [140/400] eta: 0:02:00 lr: 0.000066 loss: 2.2069 (2.1825) grad: 0.1657 (0.1659) time: 0.4474 data: 0.0043 max mem: 22448 +train: [15] [160/400] eta: 0:01:50 lr: 0.000064 loss: 2.2380 (2.1861) grad: 0.1613 (0.1655) time: 0.4448 data: 0.0043 max mem: 22448 +train: [15] [180/400] eta: 0:01:40 lr: 0.000063 loss: 2.1689 (2.1823) grad: 0.1613 (0.1650) time: 0.4379 data: 0.0041 max mem: 22448 +train: [15] [200/400] eta: 0:01:31 lr: 0.000062 loss: 2.1689 (2.1812) grad: 0.1590 (0.1647) time: 0.4599 data: 0.0042 max mem: 22448 +train: [15] [220/400] eta: 0:01:22 lr: 0.000061 loss: 2.1690 (2.1806) grad: 0.1631 (0.1651) time: 0.4412 data: 0.0042 max mem: 22448 +train: [15] [240/400] eta: 0:01:12 lr: 0.000059 loss: 2.1684 (2.1824) grad: 0.1659 (0.1654) time: 0.4431 data: 0.0042 max mem: 22448 +train: [15] [260/400] eta: 0:01:03 lr: 0.000058 loss: 2.1797 (2.1831) grad: 0.1659 (0.1653) time: 0.4617 data: 0.0041 max mem: 22448 +train: [15] [280/400] eta: 0:00:54 lr: 0.000057 loss: 2.1850 (2.1811) grad: 0.1660 (0.1656) time: 0.4527 data: 0.0042 max mem: 22448 +train: [15] [300/400] eta: 0:00:45 lr: 0.000056 loss: 2.2157 (2.1827) grad: 0.1740 (0.1662) time: 0.4398 data: 0.0042 max mem: 22448 +train: [15] [320/400] eta: 0:00:36 lr: 0.000054 loss: 2.2300 (2.1857) grad: 0.1740 (0.1665) time: 0.4626 data: 0.0041 max mem: 22448 +train: [15] [340/400] eta: 0:00:27 lr: 0.000053 loss: 2.2134 (2.1865) grad: 0.1676 (0.1662) time: 0.4715 data: 0.0042 max mem: 22448 +train: [15] [360/400] eta: 0:00:18 lr: 0.000052 loss: 2.1961 (2.1853) grad: 0.1623 (0.1662) time: 0.4464 data: 0.0041 max mem: 22448 +train: [15] [380/400] eta: 0:00:09 lr: 0.000051 loss: 2.1977 (2.1871) grad: 0.1657 (0.1666) time: 0.4716 data: 0.0043 max mem: 22448 +train: [15] [399/400] eta: 0:00:00 lr: 0.000050 loss: 2.1902 (2.1855) grad: 0.1673 (0.1665) time: 0.4587 data: 0.0042 max mem: 22448 +train: [15] Total time: 0:03:02 (0.4567 s / it) +train: [15] Summary: lr: 0.000050 loss: 2.1902 (2.1855) grad: 0.1673 (0.1665) +eval (validation): [15] [ 0/85] eta: 0:04:43 time: 3.3335 data: 3.0355 max mem: 22448 +eval (validation): [15] [20/85] eta: 0:00:33 time: 0.3777 data: 0.0041 max mem: 22448 +eval (validation): [15] [40/85] eta: 0:00:19 time: 0.3480 data: 0.0043 max mem: 22448 +eval (validation): [15] [60/85] eta: 0:00:10 time: 0.3536 data: 0.0044 max mem: 22448 +eval (validation): [15] [80/85] eta: 0:00:01 time: 0.3434 data: 0.0042 max mem: 22448 +eval (validation): [15] [84/85] eta: 0:00:00 time: 0.3355 data: 0.0041 max mem: 22448 +eval (validation): [15] Total time: 0:00:33 (0.3931 s / it) +cv: [15] best hparam: (0.61, 1.0) (021) ('021_lr6.1e-01_wd1.0e+00') loss: 2.366 acc: 0.290 f1: 0.225 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [16] [ 0/400] eta: 0:23:01 lr: nan time: 3.4547 data: 3.0623 max mem: 22448 +train: [16] [ 20/400] eta: 0:03:50 lr: 0.000048 loss: 2.1837 (2.2103) grad: 0.1657 (0.1680) time: 0.4633 data: 0.0038 max mem: 22448 +train: [16] [ 40/400] eta: 0:03:09 lr: 0.000047 loss: 2.1454 (2.1645) grad: 0.1651 (0.1633) time: 0.4408 data: 0.0043 max mem: 22448 +train: [16] [ 60/400] eta: 0:02:49 lr: 0.000046 loss: 2.1278 (2.1571) grad: 0.1609 (0.1637) time: 0.4422 data: 0.0042 max mem: 22448 +train: [16] [ 80/400] eta: 0:02:35 lr: 0.000045 loss: 2.1573 (2.1601) grad: 0.1609 (0.1641) time: 0.4544 data: 0.0041 max mem: 22448 +train: [16] [100/400] eta: 0:02:23 lr: 0.000044 loss: 2.1512 (2.1577) grad: 0.1674 (0.1656) time: 0.4461 data: 0.0043 max mem: 22448 +train: [16] [120/400] eta: 0:02:12 lr: 0.000043 loss: 2.1504 (2.1643) grad: 0.1674 (0.1659) time: 0.4475 data: 0.0042 max mem: 22448 +train: [16] [140/400] eta: 0:02:02 lr: 0.000042 loss: 2.1881 (2.1686) grad: 0.1646 (0.1659) time: 0.4421 data: 0.0044 max mem: 22448 +train: [16] [160/400] eta: 0:01:51 lr: 0.000041 loss: 2.1881 (2.1686) grad: 0.1646 (0.1656) time: 0.4433 data: 0.0041 max mem: 22448 +train: [16] [180/400] eta: 0:01:41 lr: 0.000040 loss: 2.1598 (2.1653) grad: 0.1615 (0.1650) time: 0.4408 data: 0.0043 max mem: 22448 +train: [16] [200/400] eta: 0:01:32 lr: 0.000039 loss: 2.1332 (2.1609) grad: 0.1628 (0.1648) time: 0.4524 data: 0.0043 max mem: 22448 +train: [16] [220/400] eta: 0:01:22 lr: 0.000038 loss: 2.0837 (2.1580) grad: 0.1635 (0.1644) time: 0.4433 data: 0.0042 max mem: 22448 +train: [16] [240/400] eta: 0:01:13 lr: 0.000036 loss: 2.1515 (2.1607) grad: 0.1639 (0.1647) time: 0.4420 data: 0.0040 max mem: 22448 +train: [16] [260/400] eta: 0:01:04 lr: 0.000035 loss: 2.1734 (2.1617) grad: 0.1672 (0.1649) time: 0.4465 data: 0.0040 max mem: 22448 +train: [16] [280/400] eta: 0:00:54 lr: 0.000034 loss: 2.1481 (2.1596) grad: 0.1698 (0.1655) time: 0.4485 data: 0.0041 max mem: 22448 +train: [16] [300/400] eta: 0:00:45 lr: 0.000033 loss: 2.1481 (2.1603) grad: 0.1646 (0.1654) time: 0.4508 data: 0.0042 max mem: 22448 +train: [16] [320/400] eta: 0:00:36 lr: 0.000032 loss: 2.1440 (2.1579) grad: 0.1640 (0.1656) time: 0.4538 data: 0.0041 max mem: 22448 +train: [16] [340/400] eta: 0:00:27 lr: 0.000031 loss: 2.1250 (2.1560) grad: 0.1631 (0.1655) time: 0.4586 data: 0.0043 max mem: 22448 +train: [16] [360/400] eta: 0:00:18 lr: 0.000031 loss: 2.1376 (2.1564) grad: 0.1600 (0.1654) time: 0.4469 data: 0.0040 max mem: 22448 +train: [16] [380/400] eta: 0:00:09 lr: 0.000030 loss: 2.1376 (2.1540) grad: 0.1631 (0.1656) time: 0.4557 data: 0.0043 max mem: 22448 +train: [16] [399/400] eta: 0:00:00 lr: 0.000029 loss: 2.1566 (2.1562) grad: 0.1671 (0.1656) time: 0.4493 data: 0.0040 max mem: 22448 +train: [16] Total time: 0:03:02 (0.4563 s / it) +train: [16] Summary: lr: 0.000029 loss: 2.1566 (2.1562) grad: 0.1671 (0.1656) +eval (validation): [16] [ 0/85] eta: 0:04:43 time: 3.3402 data: 3.0884 max mem: 22448 +eval (validation): [16] [20/85] eta: 0:00:35 time: 0.4109 data: 0.0178 max mem: 22448 +eval (validation): [16] [40/85] eta: 0:00:20 time: 0.3718 data: 0.0050 max mem: 22448 +eval (validation): [16] [60/85] eta: 0:00:10 time: 0.3238 data: 0.0036 max mem: 22448 +eval (validation): [16] [80/85] eta: 0:00:01 time: 0.3379 data: 0.0041 max mem: 22448 +eval (validation): [16] [84/85] eta: 0:00:00 time: 0.3418 data: 0.0040 max mem: 22448 +eval (validation): [16] Total time: 0:00:33 (0.3989 s / it) +cv: [16] best hparam: (0.85, 1.0) (023) ('023_lr8.5e-01_wd1.0e+00') loss: 2.386 acc: 0.291 f1: 0.228 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [17] [ 0/400] eta: 0:23:07 lr: nan time: 3.4696 data: 3.1437 max mem: 22448 +train: [17] [ 20/400] eta: 0:03:39 lr: 0.000028 loss: 2.1085 (2.1324) grad: 0.1614 (0.1640) time: 0.4320 data: 0.0030 max mem: 22448 +train: [17] [ 40/400] eta: 0:03:03 lr: 0.000027 loss: 2.1525 (2.1420) grad: 0.1614 (0.1629) time: 0.4385 data: 0.0037 max mem: 22448 +train: [17] [ 60/400] eta: 0:02:47 lr: 0.000026 loss: 2.1065 (2.1179) grad: 0.1576 (0.1619) time: 0.4576 data: 0.0046 max mem: 22448 +train: [17] [ 80/400] eta: 0:02:33 lr: 0.000025 loss: 2.0754 (2.1114) grad: 0.1571 (0.1611) time: 0.4463 data: 0.0042 max mem: 22448 +train: [17] [100/400] eta: 0:02:21 lr: 0.000024 loss: 2.0818 (2.1167) grad: 0.1582 (0.1614) time: 0.4404 data: 0.0044 max mem: 22448 +train: [17] [120/400] eta: 0:02:11 lr: 0.000023 loss: 2.0818 (2.1177) grad: 0.1653 (0.1623) time: 0.4464 data: 0.0042 max mem: 22448 +train: [17] [140/400] eta: 0:02:01 lr: 0.000023 loss: 2.1050 (2.1276) grad: 0.1704 (0.1637) time: 0.4484 data: 0.0047 max mem: 22448 +train: [17] [160/400] eta: 0:01:51 lr: 0.000022 loss: 2.1140 (2.1265) grad: 0.1626 (0.1633) time: 0.4470 data: 0.0041 max mem: 22448 +train: [17] [180/400] eta: 0:01:41 lr: 0.000021 loss: 2.1555 (2.1286) grad: 0.1588 (0.1626) time: 0.4433 data: 0.0041 max mem: 22448 +train: [17] [200/400] eta: 0:01:32 lr: 0.000020 loss: 2.1555 (2.1255) grad: 0.1628 (0.1629) time: 0.4562 data: 0.0043 max mem: 22448 +train: [17] [220/400] eta: 0:01:22 lr: 0.000019 loss: 2.0883 (2.1241) grad: 0.1640 (0.1629) time: 0.4407 data: 0.0042 max mem: 22448 +train: [17] [240/400] eta: 0:01:13 lr: 0.000019 loss: 2.1254 (2.1282) grad: 0.1634 (0.1633) time: 0.4427 data: 0.0043 max mem: 22448 +fMRI foundation model probe eval +version: 0.1.dev65+g4003a1397 +sha: 6c01b606db98add5848cecd23e5d599250c0bf86, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-02-24 23:31:17 +config: +output_root: experiments/decoders/output +name_prefix: eval_probe +remote_root: null +notes: decoder ablations crossreg_reg4; eval v2 (nsd_cococlip patch attn) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +dataset_kwargs: {} +classifier_kwargs: + embed_dim: null + dropout: 0.0 + xavier_init: false + norm: false +lr_scale_grid: +- 0.02 +- 0.023 +- 0.028 +- 0.033 +- 0.038 +- 0.045 +- 0.053 +- 0.062 +- 0.074 +- 0.087 +- 0.1 +- 0.12 +- 0.14 +- 0.17 +- 0.2 +- 0.23 +- 0.27 +- 0.32 +- 0.38 +- 0.44 +- 0.52 +- 0.61 +- 0.72 +- 0.85 +- 1 +- 1.2 +- 1.4 +- 1.6 +- 1.9 +- 2.3 +- 2.7 +- 3.1 +- 3.7 +- 4.3 +- 5.1 +- 6 +- 7.1 +- 8.3 +- 9.8 +- 12 +- 14 +- 16 +- 19 +- 22 +- 26 +- 31 +- 36 +- 43 +- 50 +wd_scale_grid: +- 1.0 +num_workers: 8 +prefetch_factor: null +balanced_sampling: false +epochs: 20 +steps_per_epoch: 200 +batch_size: 64 +accum_iter: 2 +lr: 0.0003 +warmup_epochs: 5 +no_decay: false +weight_decay: 0.05 +clip_grad: 1.0 +metrics: +- acc +- f1 +cv_metric: acc +early_stopping: true +amp: true +device: cuda +seed: 4466 +debug: false +wandb: false +wandb_entity: null +wandb_project: fMRI-fm-eval +name: decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__attn +model: flat_mae +representation: patch +classifier: attn +dataset: nsd_cococlip +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__attn +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=False, reg_tokens=4, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: nsd_cococlip (flat) +train: [17] [260/400] eta: 0:01:03 lr: 0.000018 loss: 2.1251 (2.1256) grad: 0.1625 (0.1634) time: 0.4389 data: 0.0038 max mem: 22448 +train: [17] [280/400] eta: 0:00:54 lr: 0.000017 loss: 2.1167 (2.1258) grad: 0.1636 (0.1636) time: 0.4412 data: 0.0042 max mem: 22448 +train: [17] [300/400] eta: 0:00:45 lr: 0.000016 loss: 2.1165 (2.1272) grad: 0.1655 (0.1642) time: 0.4526 data: 0.0041 max mem: 22448 +train: [17] [320/400] eta: 0:00:36 lr: 0.000016 loss: 2.1144 (2.1252) grad: 0.1652 (0.1639) time: 0.4694 data: 0.0042 max mem: 22448 +train: [17] [340/400] eta: 0:00:27 lr: 0.000015 loss: 2.1362 (2.1276) grad: 0.1632 (0.1640) time: 0.4459 data: 0.0045 max mem: 22448 +train (n=32539): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'run', 'trial_id', 'nsd_id', 'category_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 32539 +}), + labels=[ 3 4 5 6 10 11 17 18 19 20 22 23 25 30 31 33 36 37 38 53 55 59 61 74], + counts=[1286 1180 1639 1868 834 824 1026 1042 913 1853 1503 2092 1001 1410 + 794 1241 1904 1872 2267 1428 889 904 1447 1322] +) + +validation (n=5418): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'run', 'trial_id', 'nsd_id', 'category_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 5418 +}), + labels=[ 3 4 5 6 10 11 17 18 19 20 22 23 25 30 31 33 36 37 38 53 55 59 61 74], + counts=[197 161 276 345 126 142 143 185 112 295 285 387 169 250 159 193 316 334 + 343 215 172 141 226 246] +) + +test (n=5390): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'run', 'trial_id', 'nsd_id', 'category_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 5390 +}), + labels=[ 3 4 5 6 10 11 17 18 19 20 22 23 25 30 31 33 36 37 38 53 55 59 61 74], + counts=[202 172 274 298 144 180 134 182 186 293 218 343 165 185 140 177 346 333 + 345 271 165 140 251 246] +) + +testid (n=5187): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'run', 'trial_id', 'nsd_id', 'category_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 5187 +}), + labels=[ 3 4 5 6 10 11 17 18 19 20 22 23 25 30 31 33 36 37 38 53 55 59 61 74], + counts=[197 159 267 273 123 153 175 184 139 310 215 386 153 230 118 192 330 306 + 349 223 143 127 249 186] +) + +running backbone on example batch to get embedding dim +embedding feature dim (patch): 768 +initializing sweep of classifier heads +classifiers: +ModuleList( + (0-48): 49 x AttnPoolClassifier( + (kv): Linear(in_features=768, out_features=1536, bias=True) + (linear): Linear(in_features=768, out_features=24, bias=True) + ) +) +classifier params (train): 58.8M (58.8M) +setting up optimizer +total batch size: 128 = 64 bs per gpu x 2 accum +lr: 3.00e-04 +full schedule: epochs = 20 (steps = 4000) (decay = True) +warmup: epochs = 5 (steps = 1000) +loaded model and optimizer state, resuming training from 17 +freezing diverged classifier 46 (36, 1.0) +freezing diverged classifier 47 (43, 1.0) +freezing diverged classifier 48 (50, 1.0) +start training for 20 epochs +train: [17] [ 0/400] eta: 0:23:36 lr: nan time: 3.5416 data: 3.0007 max mem: 21363 +train: [17] [360/400] eta: 0:00:18 lr: 0.000014 loss: 2.1475 (2.1272) grad: 0.1636 (0.1637) time: 0.4401 data: 0.0045 max mem: 22448 +train: [17] [ 20/400] eta: 0:03:48 lr: 0.000028 loss: 2.1459 (2.1348) grad: 0.1608 (0.1661) time: 0.4545 data: 0.0030 max mem: 21606 +train: [17] [380/400] eta: 0:00:09 lr: 0.000014 loss: 2.1230 (2.1274) grad: 0.1572 (0.1639) time: 0.4453 data: 0.0042 max mem: 22448 +train: [17] [ 40/400] eta: 0:03:14 lr: 0.000027 loss: 2.1588 (2.1678) grad: 0.1640 (0.1673) time: 0.4772 data: 0.0045 max mem: 21606 +train: [17] [399/400] eta: 0:00:00 lr: 0.000013 loss: 2.1298 (2.1270) grad: 0.1572 (0.1636) time: 0.4378 data: 0.0042 max mem: 22448 +train: [17] Total time: 0:03:01 (0.4534 s / it) +train: [17] Summary: lr: 0.000013 loss: 2.1298 (2.1270) grad: 0.1572 (0.1636) +eval (validation): [17] [ 0/85] eta: 0:04:42 time: 3.3246 data: 3.0630 max mem: 22448 +train: [17] [ 60/400] eta: 0:02:54 lr: 0.000026 loss: 2.1328 (2.1500) grad: 0.1627 (0.1649) time: 0.4557 data: 0.0042 max mem: 21606 +eval (validation): [17] [20/85] eta: 0:00:33 time: 0.3790 data: 0.0050 max mem: 22448 +train: [17] [ 80/400] eta: 0:02:39 lr: 0.000025 loss: 2.1014 (2.1424) grad: 0.1609 (0.1644) time: 0.4568 data: 0.0043 max mem: 21606 +eval (validation): [17] [40/85] eta: 0:00:19 time: 0.3473 data: 0.0037 max mem: 22448 +train: [17] [100/400] eta: 0:02:27 lr: 0.000024 loss: 2.1074 (2.1443) grad: 0.1646 (0.1644) time: 0.4596 data: 0.0042 max mem: 21606 +eval (validation): [17] [60/85] eta: 0:00:10 time: 0.3399 data: 0.0044 max mem: 22448 +eval (validation): [17] [80/85] eta: 0:00:01 time: 0.3285 data: 0.0039 max mem: 22448 +train: [17] [120/400] eta: 0:02:15 lr: 0.000023 loss: 2.0925 (2.1382) grad: 0.1597 (0.1633) time: 0.4505 data: 0.0040 max mem: 21606 +eval (validation): [17] [84/85] eta: 0:00:00 time: 0.3299 data: 0.0038 max mem: 22448 +eval (validation): [17] Total time: 0:00:32 (0.3864 s / it) +cv: [17] best hparam: (0.61, 1.0) (021) ('021_lr6.1e-01_wd1.0e+00') loss: 2.368 acc: 0.291 f1: 0.227 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [18] [ 0/400] eta: 0:23:19 lr: nan time: 3.4978 data: 3.1120 max mem: 22448 +train: [17] [140/400] eta: 0:02:04 lr: 0.000023 loss: 2.0798 (2.1319) grad: 0.1566 (0.1630) time: 0.4554 data: 0.0042 max mem: 21606 +train: [18] [ 20/400] eta: 0:03:42 lr: 0.000012 loss: 2.0949 (2.1026) grad: 0.1600 (0.1638) time: 0.4404 data: 0.0033 max mem: 22448 +train: [17] [160/400] eta: 0:01:54 lr: 0.000022 loss: 2.1051 (2.1303) grad: 0.1568 (0.1627) time: 0.4665 data: 0.0041 max mem: 21606 +train: [18] [ 40/400] eta: 0:03:07 lr: 0.000012 loss: 2.0949 (2.1116) grad: 0.1611 (0.1629) time: 0.4541 data: 0.0041 max mem: 22448 +train: [17] [180/400] eta: 0:01:45 lr: 0.000021 loss: 2.1517 (2.1339) grad: 0.1610 (0.1633) time: 0.4676 data: 0.0041 max mem: 21606 +train: [18] [ 60/400] eta: 0:02:47 lr: 0.000011 loss: 2.0860 (2.1045) grad: 0.1624 (0.1629) time: 0.4377 data: 0.0044 max mem: 22448 +train: [17] [200/400] eta: 0:01:35 lr: 0.000020 loss: 2.1512 (2.1367) grad: 0.1648 (0.1634) time: 0.4588 data: 0.0041 max mem: 21606 +train: [18] [ 80/400] eta: 0:02:34 lr: 0.000011 loss: 2.0985 (2.0976) grad: 0.1624 (0.1636) time: 0.4524 data: 0.0044 max mem: 22448 +train: [17] [220/400] eta: 0:01:25 lr: 0.000019 loss: 2.1402 (2.1361) grad: 0.1643 (0.1643) time: 0.4615 data: 0.0039 max mem: 21606 +train: [18] [100/400] eta: 0:02:23 lr: 0.000010 loss: 2.1038 (2.1065) grad: 0.1616 (0.1632) time: 0.4526 data: 0.0044 max mem: 22448 +train: [17] [240/400] eta: 0:01:15 lr: 0.000019 loss: 2.1505 (2.1389) grad: 0.1592 (0.1638) time: 0.4574 data: 0.0040 max mem: 21606 +train: [18] [120/400] eta: 0:02:11 lr: 0.000009 loss: 2.1359 (2.1138) grad: 0.1637 (0.1639) time: 0.4399 data: 0.0044 max mem: 22448 +train: [17] [260/400] eta: 0:01:05 lr: 0.000018 loss: 2.1212 (2.1348) grad: 0.1565 (0.1637) time: 0.4402 data: 0.0039 max mem: 21606 +train: [18] [140/400] eta: 0:02:01 lr: 0.000009 loss: 2.1342 (2.1175) grad: 0.1611 (0.1631) time: 0.4427 data: 0.0042 max mem: 22448 +train: [17] [280/400] eta: 0:00:56 lr: 0.000017 loss: 2.1100 (2.1347) grad: 0.1597 (0.1636) time: 0.4643 data: 0.0042 max mem: 21606 +train: [18] [160/400] eta: 0:01:51 lr: 0.000008 loss: 2.1534 (2.1210) grad: 0.1607 (0.1630) time: 0.4416 data: 0.0040 max mem: 22448 +train: [17] [300/400] eta: 0:00:46 lr: 0.000016 loss: 2.1248 (2.1354) grad: 0.1581 (0.1636) time: 0.4471 data: 0.0042 max mem: 21606 +train: [18] [180/400] eta: 0:01:41 lr: 0.000008 loss: 2.1534 (2.1242) grad: 0.1607 (0.1629) time: 0.4500 data: 0.0041 max mem: 22448 +train: [17] [320/400] eta: 0:00:37 lr: 0.000016 loss: 2.1588 (2.1357) grad: 0.1636 (0.1637) time: 0.4554 data: 0.0039 max mem: 21606 +train: [18] [200/400] eta: 0:01:32 lr: 0.000007 loss: 2.1283 (2.1229) grad: 0.1600 (0.1626) time: 0.4451 data: 0.0041 max mem: 22448 +train: [17] [340/400] eta: 0:00:28 lr: 0.000015 loss: 2.1532 (2.1353) grad: 0.1653 (0.1642) time: 0.4768 data: 0.0041 max mem: 21606 +train: [18] [220/400] eta: 0:01:22 lr: 0.000007 loss: 2.1246 (2.1227) grad: 0.1609 (0.1625) time: 0.4414 data: 0.0042 max mem: 22448 +train: [17] [360/400] eta: 0:00:18 lr: 0.000014 loss: 2.1454 (2.1370) grad: 0.1622 (0.1640) time: 0.4620 data: 0.0041 max mem: 21606 +train: [18] [240/400] eta: 0:01:13 lr: 0.000006 loss: 2.1246 (2.1219) grad: 0.1604 (0.1628) time: 0.4438 data: 0.0042 max mem: 22448 +train: [17] [380/400] eta: 0:00:09 lr: 0.000014 loss: 2.1210 (2.1370) grad: 0.1622 (0.1640) time: 0.4421 data: 0.0038 max mem: 21606 +train: [18] [260/400] eta: 0:01:03 lr: 0.000006 loss: 2.1138 (2.1217) grad: 0.1616 (0.1631) time: 0.4469 data: 0.0041 max mem: 22448 +train: [17] [399/400] eta: 0:00:00 lr: 0.000013 loss: 2.1190 (2.1352) grad: 0.1622 (0.1638) time: 0.4666 data: 0.0039 max mem: 21606 +train: [17] Total time: 0:03:06 (0.4668 s / it) +train: [17] Summary: lr: 0.000013 loss: 2.1190 (2.1352) grad: 0.1622 (0.1638) +train: [18] [280/400] eta: 0:00:54 lr: 0.000006 loss: 2.1182 (2.1227) grad: 0.1616 (0.1632) time: 0.4448 data: 0.0041 max mem: 22448 +eval (validation): [17] [ 0/85] eta: 0:04:47 time: 3.3768 data: 3.0946 max mem: 21606 +eval (validation): [17] [20/85] eta: 0:00:31 time: 0.3413 data: 0.0042 max mem: 21606 +train: [18] [300/400] eta: 0:00:45 lr: 0.000005 loss: 2.1319 (2.1271) grad: 0.1631 (0.1632) time: 0.4457 data: 0.0044 max mem: 22448 +eval (validation): [17] [40/85] eta: 0:00:18 time: 0.3536 data: 0.0036 max mem: 21606 +train: [18] [320/400] eta: 0:00:36 lr: 0.000005 loss: 2.0919 (2.1241) grad: 0.1631 (0.1631) time: 0.4575 data: 0.0043 max mem: 22448 +eval (validation): [17] [60/85] eta: 0:00:09 time: 0.3447 data: 0.0041 max mem: 21606 +train: [18] [340/400] eta: 0:00:27 lr: 0.000004 loss: 2.0883 (2.1238) grad: 0.1639 (0.1631) time: 0.4313 data: 0.0042 max mem: 22448 +eval (validation): [17] [80/85] eta: 0:00:01 time: 0.3447 data: 0.0039 max mem: 21606 +eval (validation): [17] [84/85] eta: 0:00:00 time: 0.3367 data: 0.0038 max mem: 21606 +eval (validation): [17] Total time: 0:00:32 (0.3838 s / it) +cv: [17] best hparam: (0.61, 1.0) (021) ('021_lr6.1e-01_wd1.0e+00') loss: 2.357 acc: 0.294 f1: 0.230 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [18] [360/400] eta: 0:00:18 lr: 0.000004 loss: 2.1025 (2.1232) grad: 0.1640 (0.1632) time: 0.4450 data: 0.0041 max mem: 22448 +train: [18] [ 0/400] eta: 0:22:37 lr: nan time: 3.3949 data: 3.0601 max mem: 21606 +train: [18] [380/400] eta: 0:00:09 lr: 0.000004 loss: 2.0811 (2.1216) grad: 0.1629 (0.1630) time: 0.4598 data: 0.0042 max mem: 22448 +train: [18] [ 20/400] eta: 0:03:44 lr: 0.000012 loss: 2.0809 (2.1290) grad: 0.1655 (0.1644) time: 0.4517 data: 0.0036 max mem: 21606 +train: [18] [399/400] eta: 0:00:00 lr: 0.000003 loss: 2.0811 (2.1206) grad: 0.1604 (0.1630) time: 0.4473 data: 0.0042 max mem: 22448 +train: [18] Total time: 0:03:01 (0.4539 s / it) +train: [18] Summary: lr: 0.000003 loss: 2.0811 (2.1206) grad: 0.1604 (0.1630) +train: [18] [ 40/400] eta: 0:03:08 lr: 0.000012 loss: 2.0839 (2.1130) grad: 0.1591 (0.1614) time: 0.4539 data: 0.0039 max mem: 21606 +eval (validation): [18] [ 0/85] eta: 0:04:49 time: 3.4080 data: 3.1156 max mem: 22448 +train: [18] [ 60/400] eta: 0:02:49 lr: 0.000011 loss: 2.0976 (2.1073) grad: 0.1571 (0.1612) time: 0.4485 data: 0.0042 max mem: 21606 +eval (validation): [18] [20/85] eta: 0:00:32 time: 0.3492 data: 0.0046 max mem: 22448 +eval (validation): [18] [40/85] eta: 0:00:18 time: 0.3314 data: 0.0040 max mem: 22448 +train: [18] [ 80/400] eta: 0:02:36 lr: 0.000011 loss: 2.0877 (2.0998) grad: 0.1659 (0.1628) time: 0.4552 data: 0.0041 max mem: 21606 +eval (validation): [18] [60/85] eta: 0:00:09 time: 0.3390 data: 0.0038 max mem: 22448 +train: [18] [100/400] eta: 0:02:24 lr: 0.000010 loss: 2.0823 (2.1001) grad: 0.1651 (0.1629) time: 0.4540 data: 0.0042 max mem: 21606 +eval (validation): [18] [80/85] eta: 0:00:01 time: 0.3342 data: 0.0040 max mem: 22448 +eval (validation): [18] [84/85] eta: 0:00:00 time: 0.3316 data: 0.0040 max mem: 22448 +eval (validation): [18] Total time: 0:00:32 (0.3777 s / it) +cv: [18] best hparam: (0.61, 1.0) (021) ('021_lr6.1e-01_wd1.0e+00') loss: 2.363 acc: 0.293 f1: 0.228 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [18] [120/400] eta: 0:02:14 lr: 0.000009 loss: 2.0951 (2.1048) grad: 0.1635 (0.1630) time: 0.4679 data: 0.0043 max mem: 21606 +train: [19] [ 0/400] eta: 0:22:31 lr: nan time: 3.3792 data: 3.0384 max mem: 22448 +train: [18] [140/400] eta: 0:02:03 lr: 0.000009 loss: 2.1136 (2.1020) grad: 0.1592 (0.1627) time: 0.4368 data: 0.0039 max mem: 21606 +train: [19] [ 20/400] eta: 0:03:41 lr: 0.000003 loss: 2.1064 (2.1316) grad: 0.1595 (0.1597) time: 0.4443 data: 0.0047 max mem: 22448 +train: [18] [160/400] eta: 0:01:53 lr: 0.000008 loss: 2.0710 (2.0986) grad: 0.1583 (0.1624) time: 0.4750 data: 0.0042 max mem: 21606 +train: [19] [ 40/400] eta: 0:03:04 lr: 0.000003 loss: 2.1023 (2.1021) grad: 0.1595 (0.1581) time: 0.4386 data: 0.0044 max mem: 22448 +train: [18] [180/400] eta: 0:01:43 lr: 0.000008 loss: 2.0812 (2.0966) grad: 0.1573 (0.1627) time: 0.4556 data: 0.0042 max mem: 21606 +train: [19] [ 60/400] eta: 0:02:46 lr: 0.000002 loss: 2.0746 (2.0871) grad: 0.1536 (0.1571) time: 0.4373 data: 0.0043 max mem: 22448 +train: [18] [200/400] eta: 0:01:33 lr: 0.000007 loss: 2.0906 (2.0981) grad: 0.1569 (0.1624) time: 0.4504 data: 0.0040 max mem: 21606 +train: [19] [ 80/400] eta: 0:02:32 lr: 0.000002 loss: 2.1054 (2.1025) grad: 0.1548 (0.1578) time: 0.4457 data: 0.0044 max mem: 22448 +train: [18] [220/400] eta: 0:01:24 lr: 0.000007 loss: 2.0993 (2.0979) grad: 0.1598 (0.1625) time: 0.4666 data: 0.0044 max mem: 21606 +train: [19] [100/400] eta: 0:02:21 lr: 0.000002 loss: 2.1137 (2.0970) grad: 0.1584 (0.1580) time: 0.4428 data: 0.0043 max mem: 22448 +train: [18] [240/400] eta: 0:01:14 lr: 0.000006 loss: 2.0558 (2.0968) grad: 0.1598 (0.1625) time: 0.4498 data: 0.0041 max mem: 21606 +train: [19] [120/400] eta: 0:02:10 lr: 0.000002 loss: 2.0934 (2.0946) grad: 0.1608 (0.1597) time: 0.4476 data: 0.0044 max mem: 22448 +train: [18] [260/400] eta: 0:01:05 lr: 0.000006 loss: 2.0569 (2.0965) grad: 0.1598 (0.1623) time: 0.4526 data: 0.0040 max mem: 21606 +train: [19] [140/400] eta: 0:02:00 lr: 0.000001 loss: 2.1002 (2.1002) grad: 0.1576 (0.1598) time: 0.4507 data: 0.0045 max mem: 22448 +train: [18] [280/400] eta: 0:00:55 lr: 0.000006 loss: 2.1176 (2.1006) grad: 0.1602 (0.1623) time: 0.4413 data: 0.0040 max mem: 21606 +train: [19] [160/400] eta: 0:01:50 lr: 0.000001 loss: 2.0963 (2.1034) grad: 0.1567 (0.1596) time: 0.4465 data: 0.0043 max mem: 22448 +train: [18] [300/400] eta: 0:00:46 lr: 0.000005 loss: 2.1618 (2.1024) grad: 0.1588 (0.1623) time: 0.4410 data: 0.0037 max mem: 21606 +train: [19] [180/400] eta: 0:01:41 lr: 0.000001 loss: 2.0703 (2.1000) grad: 0.1567 (0.1600) time: 0.4593 data: 0.0044 max mem: 22448 +train: [18] [320/400] eta: 0:00:37 lr: 0.000005 loss: 2.1850 (2.1058) grad: 0.1583 (0.1623) time: 0.4721 data: 0.0040 max mem: 21606 +train: [19] [200/400] eta: 0:01:32 lr: 0.000001 loss: 2.0703 (2.0941) grad: 0.1584 (0.1596) time: 0.4625 data: 0.0043 max mem: 22448 +train: [18] [340/400] eta: 0:00:27 lr: 0.000004 loss: 2.1518 (2.1085) grad: 0.1641 (0.1627) time: 0.4622 data: 0.0039 max mem: 21606 +train: [19] [220/400] eta: 0:01:23 lr: 0.000001 loss: 2.0572 (2.0953) grad: 0.1584 (0.1595) time: 0.4583 data: 0.0043 max mem: 22448 +train: [18] [360/400] eta: 0:00:18 lr: 0.000004 loss: 2.1242 (2.1053) grad: 0.1656 (0.1627) time: 0.4610 data: 0.0039 max mem: 21606 +train: [19] [240/400] eta: 0:01:13 lr: 0.000001 loss: 2.0922 (2.0962) grad: 0.1555 (0.1591) time: 0.4390 data: 0.0041 max mem: 22448 +train: [18] [380/400] eta: 0:00:09 lr: 0.000004 loss: 2.0655 (2.1047) grad: 0.1615 (0.1624) time: 0.4433 data: 0.0039 max mem: 21606 +train: [19] [260/400] eta: 0:01:04 lr: 0.000000 loss: 2.0672 (2.0940) grad: 0.1555 (0.1588) time: 0.4700 data: 0.0043 max mem: 22448 +train: [18] [399/400] eta: 0:00:00 lr: 0.000003 loss: 2.1262 (2.1087) grad: 0.1578 (0.1624) time: 0.4593 data: 0.0042 max mem: 21606 +train: [18] Total time: 0:03:05 (0.4625 s / it) +train: [18] Summary: lr: 0.000003 loss: 2.1262 (2.1087) grad: 0.1578 (0.1624) +train: [19] [280/400] eta: 0:00:55 lr: 0.000000 loss: 2.0655 (2.0936) grad: 0.1529 (0.1583) time: 0.4437 data: 0.0042 max mem: 22448 +eval (validation): [18] [ 0/85] eta: 0:04:35 time: 3.2371 data: 3.0050 max mem: 21606 +train: [19] [300/400] eta: 0:00:45 lr: 0.000000 loss: 2.0855 (2.0953) grad: 0.1553 (0.1582) time: 0.4459 data: 0.0041 max mem: 22448 +eval (validation): [18] [20/85] eta: 0:00:32 time: 0.3640 data: 0.0040 max mem: 21606 +train: [19] [320/400] eta: 0:00:36 lr: 0.000000 loss: 2.1015 (2.0973) grad: 0.1573 (0.1584) time: 0.4532 data: 0.0042 max mem: 22448 +eval (validation): [18] [40/85] eta: 0:00:19 time: 0.3717 data: 0.0032 max mem: 21606 +eval (validation): [18] [60/85] eta: 0:00:10 time: 0.3418 data: 0.0042 max mem: 21606 +train: [19] [340/400] eta: 0:00:27 lr: 0.000000 loss: 2.0914 (2.0966) grad: 0.1591 (0.1585) time: 0.4411 data: 0.0042 max mem: 22448 +eval (validation): [18] [80/85] eta: 0:00:01 time: 0.3224 data: 0.0039 max mem: 21606 +eval (validation): [18] [84/85] eta: 0:00:00 time: 0.3139 data: 0.0038 max mem: 21606 +eval (validation): [18] Total time: 0:00:32 (0.3849 s / it) +cv: [18] best hparam: (0.61, 1.0) (021) ('021_lr6.1e-01_wd1.0e+00') loss: 2.359 acc: 0.293 f1: 0.229 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [19] [360/400] eta: 0:00:18 lr: 0.000000 loss: 2.0680 (2.0951) grad: 0.1563 (0.1585) time: 0.4408 data: 0.0043 max mem: 22448 +train: [19] [ 0/400] eta: 0:21:59 lr: nan time: 3.2978 data: 2.9635 max mem: 21606 +train: [19] [380/400] eta: 0:00:09 lr: 0.000000 loss: 2.0738 (2.0939) grad: 0.1557 (0.1587) time: 0.4454 data: 0.0042 max mem: 22448 +train: [19] [ 20/400] eta: 0:03:41 lr: 0.000003 loss: 2.0834 (2.0845) grad: 0.1543 (0.1576) time: 0.4476 data: 0.0034 max mem: 21606 +train: [19] [399/400] eta: 0:00:00 lr: 0.000000 loss: 2.0860 (2.0941) grad: 0.1557 (0.1587) time: 0.4474 data: 0.0041 max mem: 22448 +train: [19] Total time: 0:03:02 (0.4556 s / it) +train: [19] Summary: lr: 0.000000 loss: 2.0860 (2.0941) grad: 0.1557 (0.1587) +train: [19] [ 40/400] eta: 0:03:05 lr: 0.000003 loss: 2.1091 (2.1146) grad: 0.1614 (0.1612) time: 0.4437 data: 0.0041 max mem: 21606 +eval (validation): [19] [ 0/85] eta: 0:04:45 time: 3.3641 data: 3.0776 max mem: 22448 +eval (validation): [19] [20/85] eta: 0:00:32 time: 0.3508 data: 0.0048 max mem: 22448 +train: [19] [ 60/400] eta: 0:02:48 lr: 0.000002 loss: 2.1403 (2.1115) grad: 0.1648 (0.1618) time: 0.4546 data: 0.0043 max mem: 21606 +eval (validation): [19] [40/85] eta: 0:00:18 time: 0.3438 data: 0.0034 max mem: 22448 +train: [19] [ 80/400] eta: 0:02:34 lr: 0.000002 loss: 2.1055 (2.1076) grad: 0.1563 (0.1598) time: 0.4472 data: 0.0041 max mem: 21606 +eval (validation): [19] [60/85] eta: 0:00:10 time: 0.3589 data: 0.0043 max mem: 22448 +train: [19] [100/400] eta: 0:02:23 lr: 0.000002 loss: 2.1055 (2.1149) grad: 0.1541 (0.1607) time: 0.4561 data: 0.0043 max mem: 21606 +eval (validation): [19] [80/85] eta: 0:00:01 time: 0.3274 data: 0.0039 max mem: 22448 +eval (validation): [19] [84/85] eta: 0:00:00 time: 0.3244 data: 0.0039 max mem: 22448 +eval (validation): [19] Total time: 0:00:32 (0.3821 s / it) +cv: [19] best hparam: (0.61, 1.0) (021) ('021_lr6.1e-01_wd1.0e+00') loss: 2.363 acc: 0.293 f1: 0.228 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +evaluating last checkpoint: experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +eval model info: +{"score": 0.2927279438907346, "hparam": [0.61, 1.0], "hparam_id": 21, "epoch": 19, "is_best": false, "best_score": 0.29992617201919525} +train: [19] [120/400] eta: 0:02:12 lr: 0.000002 loss: 2.1252 (2.1063) grad: 0.1553 (0.1601) time: 0.4503 data: 0.0042 max mem: 21606 +eval (train): [20] [ 0/509] eta: 0:24:49 time: 2.9262 data: 2.6656 max mem: 22448 +eval (train): [20] [ 20/509] eta: 0:04:20 time: 0.4131 data: 0.0057 max mem: 22448 +train: [19] [140/400] eta: 0:02:02 lr: 0.000001 loss: 2.1281 (2.1118) grad: 0.1559 (0.1599) time: 0.4538 data: 0.0042 max mem: 21606 +eval (train): [20] [ 40/509] eta: 0:03:31 time: 0.3631 data: 0.0047 max mem: 22448 +train: [19] [160/400] eta: 0:01:52 lr: 0.000001 loss: 2.1390 (2.1117) grad: 0.1618 (0.1605) time: 0.4458 data: 0.0043 max mem: 21606 +eval (train): [20] [ 60/509] eta: 0:03:05 time: 0.3402 data: 0.0043 max mem: 22448 +train: [19] [180/400] eta: 0:01:42 lr: 0.000001 loss: 2.1357 (2.1145) grad: 0.1632 (0.1604) time: 0.4493 data: 0.0040 max mem: 21606 +eval (train): [20] [ 80/509] eta: 0:02:49 time: 0.3368 data: 0.0041 max mem: 22448 +train: [19] [200/400] eta: 0:01:32 lr: 0.000001 loss: 2.1360 (2.1146) grad: 0.1618 (0.1606) time: 0.4491 data: 0.0041 max mem: 21606 +eval (train): [20] [100/509] eta: 0:02:39 time: 0.3712 data: 0.0043 max mem: 22448 +eval (train): [20] [120/509] eta: 0:02:28 time: 0.3466 data: 0.0042 max mem: 22448 +train: [19] [220/400] eta: 0:01:23 lr: 0.000001 loss: 2.0799 (2.1119) grad: 0.1595 (0.1601) time: 0.4485 data: 0.0043 max mem: 21606 +eval (train): [20] [140/509] eta: 0:02:19 time: 0.3494 data: 0.0043 max mem: 22448 +train: [19] [240/400] eta: 0:01:13 lr: 0.000001 loss: 2.0593 (2.1071) grad: 0.1632 (0.1610) time: 0.4528 data: 0.0042 max mem: 21606 +eval (train): [20] [160/509] eta: 0:02:10 time: 0.3470 data: 0.0043 max mem: 22448 +train: [19] [260/400] eta: 0:01:04 lr: 0.000000 loss: 2.0773 (2.1044) grad: 0.1644 (0.1609) time: 0.4443 data: 0.0041 max mem: 21606 +eval (train): [20] [180/509] eta: 0:02:02 time: 0.3452 data: 0.0041 max mem: 22448 +eval (train): [20] [200/509] eta: 0:01:53 time: 0.3335 data: 0.0041 max mem: 22448 +train: [19] [280/400] eta: 0:00:55 lr: 0.000000 loss: 2.0871 (2.1048) grad: 0.1607 (0.1611) time: 0.4409 data: 0.0041 max mem: 21606 +eval (train): [20] [220/509] eta: 0:01:45 time: 0.3396 data: 0.0042 max mem: 22448 +train: [19] [300/400] eta: 0:00:45 lr: 0.000000 loss: 2.0601 (2.1041) grad: 0.1599 (0.1609) time: 0.4427 data: 0.0039 max mem: 21606 +eval (train): [20] [240/509] eta: 0:01:37 time: 0.3496 data: 0.0043 max mem: 22448 +train: [19] [320/400] eta: 0:00:36 lr: 0.000000 loss: 2.0392 (2.1006) grad: 0.1579 (0.1607) time: 0.4692 data: 0.0041 max mem: 21606 +eval (train): [20] [260/509] eta: 0:01:30 time: 0.3576 data: 0.0047 max mem: 22448 +train: [19] [340/400] eta: 0:00:27 lr: 0.000000 loss: 2.0728 (2.1011) grad: 0.1647 (0.1613) time: 0.4563 data: 0.0042 max mem: 21606 +eval (train): [20] [280/509] eta: 0:01:22 time: 0.3419 data: 0.0041 max mem: 22448 +eval (train): [20] [300/509] eta: 0:01:15 time: 0.3362 data: 0.0041 max mem: 22448 +train: [19] [360/400] eta: 0:00:18 lr: 0.000000 loss: 2.1036 (2.1023) grad: 0.1658 (0.1613) time: 0.4669 data: 0.0041 max mem: 21606 +eval (train): [20] [320/509] eta: 0:01:07 time: 0.3439 data: 0.0041 max mem: 22448 +train: [19] [380/400] eta: 0:00:09 lr: 0.000000 loss: 2.0959 (2.1009) grad: 0.1629 (0.1613) time: 0.4544 data: 0.0043 max mem: 21606 +eval (train): [20] [340/509] eta: 0:01:00 time: 0.3441 data: 0.0044 max mem: 22448 +train: [19] [399/400] eta: 0:00:00 lr: 0.000000 loss: 2.0859 (2.1010) grad: 0.1603 (0.1611) time: 0.4512 data: 0.0044 max mem: 21606 +train: [19] Total time: 0:03:03 (0.4585 s / it) +train: [19] Summary: lr: 0.000000 loss: 2.0859 (2.1010) grad: 0.1603 (0.1611) +eval (train): [20] [360/509] eta: 0:00:53 time: 0.3364 data: 0.0043 max mem: 22448 +eval (validation): [19] [ 0/85] eta: 0:04:32 time: 3.2065 data: 2.9734 max mem: 21606 +eval (train): [20] [380/509] eta: 0:00:45 time: 0.3510 data: 0.0041 max mem: 22448 +eval (validation): [19] [20/85] eta: 0:00:31 time: 0.3534 data: 0.0044 max mem: 21606 +eval (train): [20] [400/509] eta: 0:00:38 time: 0.3496 data: 0.0043 max mem: 22448 +eval (validation): [19] [40/85] eta: 0:00:19 time: 0.3536 data: 0.0038 max mem: 21606 +eval (train): [20] [420/509] eta: 0:00:31 time: 0.3554 data: 0.0042 max mem: 22448 +eval (validation): [19] [60/85] eta: 0:00:09 time: 0.3482 data: 0.0041 max mem: 21606 +eval (train): [20] [440/509] eta: 0:00:24 time: 0.3651 data: 0.0045 max mem: 22448 +eval (validation): [19] [80/85] eta: 0:00:01 time: 0.3349 data: 0.0039 max mem: 21606 +eval (validation): [19] [84/85] eta: 0:00:00 time: 0.3294 data: 0.0037 max mem: 21606 +eval (validation): [19] Total time: 0:00:32 (0.3824 s / it) +cv: [19] best hparam: (0.85, 1.0) (023) ('023_lr8.5e-01_wd1.0e+00') loss: 2.394 acc: 0.293 f1: 0.232 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +eval (train): [20] [460/509] eta: 0:00:17 time: 0.3386 data: 0.0041 max mem: 22448 +evaluating last checkpoint: experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +eval model info: +{"score": 0.29346622369878184, "hparam": [0.85, 1.0], "hparam_id": 23, "epoch": 19, "is_best": false, "best_score": 0.29992617201919525} +eval (train): [20] [ 0/509] eta: 0:26:19 time: 3.1035 data: 2.8160 max mem: 21606 +eval (train): [20] [480/509] eta: 0:00:10 time: 0.3373 data: 0.0043 max mem: 22448 +eval (train): [20] [500/509] eta: 0:00:03 time: 0.3384 data: 0.0041 max mem: 22448 +eval (train): [20] [ 20/509] eta: 0:04:10 time: 0.3834 data: 0.0046 max mem: 21606 +eval (train): [20] [508/509] eta: 0:00:00 time: 0.3152 data: 0.0038 max mem: 22448 +eval (train): [20] Total time: 0:03:00 (0.3552 s / it) +eval (train): [20] [ 40/509] eta: 0:03:21 time: 0.3423 data: 0.0041 max mem: 21606 +eval (validation): [20] [ 0/85] eta: 0:04:25 time: 3.1186 data: 2.8785 max mem: 22448 +eval (train): [20] [ 60/509] eta: 0:03:00 time: 0.3442 data: 0.0044 max mem: 21606 +eval (validation): [20] [20/85] eta: 0:00:30 time: 0.3397 data: 0.0048 max mem: 22448 +eval (train): [20] [ 80/509] eta: 0:02:46 time: 0.3473 data: 0.0041 max mem: 21606 +eval (validation): [20] [40/85] eta: 0:00:18 time: 0.3662 data: 0.0046 max mem: 22448 +eval (train): [20] [100/509] eta: 0:02:35 time: 0.3448 data: 0.0044 max mem: 21606 +eval (train): [20] [120/509] eta: 0:02:25 time: 0.3421 data: 0.0043 max mem: 21606 +eval (validation): [20] [60/85] eta: 0:00:09 time: 0.3565 data: 0.0044 max mem: 22448 +eval (train): [20] [140/509] eta: 0:02:16 time: 0.3421 data: 0.0041 max mem: 21606 +eval (validation): [20] [80/85] eta: 0:00:01 time: 0.3419 data: 0.0041 max mem: 22448 +eval (validation): [20] [84/85] eta: 0:00:00 time: 0.3327 data: 0.0040 max mem: 22448 +eval (validation): [20] Total time: 0:00:32 (0.3850 s / it) +eval (test): [20] [ 0/85] eta: 0:04:14 time: 2.9969 data: 2.7332 max mem: 22448 +eval (train): [20] [160/509] eta: 0:02:07 time: 0.3385 data: 0.0041 max mem: 21606 +eval (train): [20] [180/509] eta: 0:01:59 time: 0.3444 data: 0.0042 max mem: 21606 +eval (test): [20] [20/85] eta: 0:00:33 time: 0.3936 data: 0.0064 max mem: 22448 +eval (train): [20] [200/509] eta: 0:01:51 time: 0.3380 data: 0.0041 max mem: 21606 +eval (test): [20] [40/85] eta: 0:00:19 time: 0.3624 data: 0.0041 max mem: 22448 +eval (train): [20] [220/509] eta: 0:01:43 time: 0.3426 data: 0.0041 max mem: 21606 +eval (test): [20] [60/85] eta: 0:00:10 time: 0.3412 data: 0.0043 max mem: 22448 +eval (train): [20] [240/509] eta: 0:01:36 time: 0.3435 data: 0.0043 max mem: 21606 +eval (test): [20] [80/85] eta: 0:00:01 time: 0.3232 data: 0.0043 max mem: 22448 +eval (test): [20] [84/85] eta: 0:00:00 time: 0.3184 data: 0.0040 max mem: 22448 +eval (test): [20] Total time: 0:00:32 (0.3870 s / it) +eval (train): [20] [260/509] eta: 0:01:28 time: 0.3481 data: 0.0044 max mem: 21606 +eval (testid): [20] [ 0/82] eta: 0:04:14 time: 3.1073 data: 2.8315 max mem: 22448 +eval (train): [20] [280/509] eta: 0:01:21 time: 0.3377 data: 0.0043 max mem: 21606 +eval (testid): [20] [20/82] eta: 0:00:30 time: 0.3579 data: 0.0053 max mem: 22448 +eval (train): [20] [300/509] eta: 0:01:14 time: 0.3412 data: 0.0044 max mem: 21606 +eval (testid): [20] [40/82] eta: 0:00:17 time: 0.3547 data: 0.0039 max mem: 22448 +eval (train): [20] [320/509] eta: 0:01:06 time: 0.3489 data: 0.0041 max mem: 21606 +eval (testid): [20] [60/82] eta: 0:00:08 time: 0.3411 data: 0.0044 max mem: 22448 +eval (train): [20] [340/509] eta: 0:00:59 time: 0.3475 data: 0.0042 max mem: 21606 +eval (testid): [20] [80/82] eta: 0:00:00 time: 0.3377 data: 0.0044 max mem: 22448 +eval (testid): [20] [81/82] eta: 0:00:00 time: 0.3258 data: 0.0044 max mem: 22448 +eval (testid): [20] Total time: 0:00:31 (0.3824 s / it) +evaluating best checkpoint: experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__attn/checkpoint-best.pth +eval model info: +{"score": 0.29992617201919525, "hparam": [1, 1.0], "hparam_id": 24, "epoch": 7, "is_best": true, "best_score": 0.29992617201919525} +eval (train): [20] [ 0/509] eta: 0:24:45 time: 2.9180 data: 2.6953 max mem: 22448 +eval (train): [20] [360/509] eta: 0:00:52 time: 0.3448 data: 0.0042 max mem: 21606 +eval (train): [20] [ 20/509] eta: 0:03:44 time: 0.3363 data: 0.0167 max mem: 22448 +eval (train): [20] [380/509] eta: 0:00:45 time: 0.3346 data: 0.0044 max mem: 21606 +eval (train): [20] [400/509] eta: 0:00:38 time: 0.3373 data: 0.0042 max mem: 21606 +eval (train): [20] [ 40/509] eta: 0:03:09 time: 0.3463 data: 0.0040 max mem: 22448 +eval (train): [20] [420/509] eta: 0:00:31 time: 0.3664 data: 0.0043 max mem: 21606 +eval (train): [20] [ 60/509] eta: 0:02:56 time: 0.3673 data: 0.0038 max mem: 22448 +eval (train): [20] [ 80/509] eta: 0:02:43 time: 0.3484 data: 0.0046 max mem: 22448 +eval (train): [20] [440/509] eta: 0:00:24 time: 0.3672 data: 0.0048 max mem: 21606 +eval (train): [20] [100/509] eta: 0:02:33 time: 0.3459 data: 0.0043 max mem: 22448 +eval (train): [20] [460/509] eta: 0:00:17 time: 0.3565 data: 0.0040 max mem: 21606 +eval (train): [20] [120/509] eta: 0:02:23 time: 0.3341 data: 0.0042 max mem: 22448 +eval (train): [20] [480/509] eta: 0:00:10 time: 0.3465 data: 0.0042 max mem: 21606 +eval (train): [20] [140/509] eta: 0:02:15 time: 0.3654 data: 0.0042 max mem: 22448 +eval (train): [20] [500/509] eta: 0:00:03 time: 0.3493 data: 0.0044 max mem: 21606 +eval (train): [20] [508/509] eta: 0:00:00 time: 0.3352 data: 0.0041 max mem: 21606 +eval (train): [20] Total time: 0:03:00 (0.3537 s / it) +eval (train): [20] [160/509] eta: 0:02:07 time: 0.3414 data: 0.0043 max mem: 22448 +eval (validation): [20] [ 0/85] eta: 0:04:07 time: 2.9117 data: 2.6795 max mem: 21606 +eval (train): [20] [180/509] eta: 0:01:59 time: 0.3577 data: 0.0043 max mem: 22448 +eval (validation): [20] [20/85] eta: 0:00:32 time: 0.3793 data: 0.0051 max mem: 21606 +eval (train): [20] [200/509] eta: 0:01:52 time: 0.3850 data: 0.0046 max mem: 22448 +eval (validation): [20] [40/85] eta: 0:00:19 time: 0.3611 data: 0.0036 max mem: 21606 +eval (train): [20] [220/509] eta: 0:01:45 time: 0.3489 data: 0.0043 max mem: 22448 +eval (validation): [20] [60/85] eta: 0:00:10 time: 0.3570 data: 0.0042 max mem: 21606 +eval (train): [20] [240/509] eta: 0:01:37 time: 0.3511 data: 0.0045 max mem: 22448 +eval (validation): [20] [80/85] eta: 0:00:01 time: 0.3274 data: 0.0041 max mem: 21606 +eval (validation): [20] [84/85] eta: 0:00:00 time: 0.3174 data: 0.0039 max mem: 21606 +eval (validation): [20] Total time: 0:00:32 (0.3863 s / it) +eval (train): [20] [260/509] eta: 0:01:30 time: 0.3536 data: 0.0047 max mem: 22448 +eval (test): [20] [ 0/85] eta: 0:04:24 time: 3.1103 data: 2.8160 max mem: 21606 +eval (train): [20] [280/509] eta: 0:01:22 time: 0.3409 data: 0.0041 max mem: 22448 +eval (test): [20] [20/85] eta: 0:00:31 time: 0.3525 data: 0.0039 max mem: 21606 +eval (train): [20] [300/509] eta: 0:01:15 time: 0.3416 data: 0.0043 max mem: 22448 +eval (test): [20] [40/85] eta: 0:00:18 time: 0.3319 data: 0.0039 max mem: 21606 +eval (train): [20] [320/509] eta: 0:01:08 time: 0.3723 data: 0.0045 max mem: 22448 +eval (test): [20] [60/85] eta: 0:00:09 time: 0.3566 data: 0.0040 max mem: 21606 +eval (train): [20] [340/509] eta: 0:01:01 time: 0.3748 data: 0.0047 max mem: 22448 +eval (test): [20] [80/85] eta: 0:00:01 time: 0.3317 data: 0.0041 max mem: 21606 +eval (test): [20] [84/85] eta: 0:00:00 time: 0.3214 data: 0.0039 max mem: 21606 +eval (test): [20] Total time: 0:00:31 (0.3760 s / it) +eval (train): [20] [360/509] eta: 0:00:53 time: 0.3803 data: 0.0043 max mem: 22448 +eval (testid): [20] [ 0/82] eta: 0:04:13 time: 3.0920 data: 2.8119 max mem: 21606 +eval (train): [20] [380/509] eta: 0:00:46 time: 0.3815 data: 0.0043 max mem: 22448 +eval (testid): [20] [20/82] eta: 0:00:31 time: 0.3794 data: 0.0040 max mem: 21606 +eval (train): [20] [400/509] eta: 0:00:39 time: 0.3357 data: 0.0040 max mem: 22448 +eval (testid): [20] [40/82] eta: 0:00:18 time: 0.3447 data: 0.0044 max mem: 21606 +eval (train): [20] [420/509] eta: 0:00:32 time: 0.3553 data: 0.0042 max mem: 22448 +eval (testid): [20] [60/82] eta: 0:00:09 time: 0.3694 data: 0.0042 max mem: 21606 +eval (train): [20] [440/509] eta: 0:00:24 time: 0.3398 data: 0.0043 max mem: 22448 +eval (testid): [20] [80/82] eta: 0:00:00 time: 0.3371 data: 0.0041 max mem: 21606 +eval (testid): [20] [81/82] eta: 0:00:00 time: 0.3255 data: 0.0039 max mem: 21606 +eval (testid): [20] Total time: 0:00:32 (0.3914 s / it) +evaluating best checkpoint: experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__attn/checkpoint-best.pth +eval model info: +{"score": 0.29992617201919525, "hparam": [1, 1.0], "hparam_id": 24, "epoch": 7, "is_best": true, "best_score": 0.29992617201919525} +eval (train): [20] [460/509] eta: 0:00:17 time: 0.3471 data: 0.0042 max mem: 22448 +eval (train): [20] [ 0/509] eta: 0:26:17 time: 3.0987 data: 2.8316 max mem: 21606 +eval (train): [20] [480/509] eta: 0:00:10 time: 0.3407 data: 0.0036 max mem: 22448 +eval (train): [20] [ 20/509] eta: 0:03:59 time: 0.3585 data: 0.0054 max mem: 21606 +eval (train): [20] [500/509] eta: 0:00:03 time: 0.3336 data: 0.0039 max mem: 22448 +eval (train): [20] [508/509] eta: 0:00:00 time: 0.3147 data: 0.0034 max mem: 22448 +eval (train): [20] [ 40/509] eta: 0:03:16 time: 0.3475 data: 0.0044 max mem: 21606 +eval (train): [20] Total time: 0:03:02 (0.3588 s / it) +eval (train): [20] [ 60/509] eta: 0:02:56 time: 0.3369 data: 0.0035 max mem: 21606 +eval (validation): [20] [ 0/85] eta: 0:04:10 time: 2.9434 data: 2.7172 max mem: 22448 +eval (train): [20] [ 80/509] eta: 0:02:45 time: 0.3615 data: 0.0042 max mem: 21606 +eval (validation): [20] [20/85] eta: 0:00:34 time: 0.4055 data: 0.0317 max mem: 22448 +eval (train): [20] [100/509] eta: 0:02:35 time: 0.3574 data: 0.0043 max mem: 21606 +eval (validation): [20] [40/85] eta: 0:00:19 time: 0.3581 data: 0.0035 max mem: 22448 +eval (train): [20] [120/509] eta: 0:02:25 time: 0.3494 data: 0.0044 max mem: 21606 +eval (validation): [20] [60/85] eta: 0:00:10 time: 0.3441 data: 0.0045 max mem: 22448 +eval (train): [20] [140/509] eta: 0:02:16 time: 0.3451 data: 0.0041 max mem: 21606 +eval (validation): [20] [80/85] eta: 0:00:01 time: 0.3259 data: 0.0043 max mem: 22448 +eval (validation): [20] [84/85] eta: 0:00:00 time: 0.3207 data: 0.0041 max mem: 22448 +eval (validation): [20] Total time: 0:00:33 (0.3899 s / it) +eval (train): [20] [160/509] eta: 0:02:08 time: 0.3466 data: 0.0043 max mem: 21606 +eval (test): [20] [ 0/85] eta: 0:04:19 time: 3.0550 data: 2.7837 max mem: 22448 +eval (train): [20] [180/509] eta: 0:01:59 time: 0.3357 data: 0.0042 max mem: 21606 +eval (test): [20] [20/85] eta: 0:00:31 time: 0.3587 data: 0.0054 max mem: 22448 +eval (train): [20] [200/509] eta: 0:01:51 time: 0.3459 data: 0.0039 max mem: 21606 +eval (test): [20] [40/85] eta: 0:00:19 time: 0.3566 data: 0.0039 max mem: 22448 +eval (train): [20] [220/509] eta: 0:01:45 time: 0.3788 data: 0.0042 max mem: 21606 +eval (test): [20] [60/85] eta: 0:00:09 time: 0.3417 data: 0.0043 max mem: 22448 +eval (train): [20] [240/509] eta: 0:01:37 time: 0.3552 data: 0.0043 max mem: 21606 +eval (test): [20] [80/85] eta: 0:00:01 time: 0.3310 data: 0.0041 max mem: 22448 +eval (test): [20] [84/85] eta: 0:00:00 time: 0.3176 data: 0.0040 max mem: 22448 +eval (test): [20] Total time: 0:00:32 (0.3799 s / it) +eval (train): [20] [260/509] eta: 0:01:30 time: 0.3812 data: 0.0042 max mem: 21606 +eval (testid): [20] [ 0/82] eta: 0:04:05 time: 2.9973 data: 2.7296 max mem: 22448 +eval (train): [20] [280/509] eta: 0:01:23 time: 0.3548 data: 0.0041 max mem: 21606 +eval (testid): [20] [20/82] eta: 0:00:29 time: 0.3445 data: 0.0048 max mem: 22448 +eval (train): [20] [300/509] eta: 0:01:16 time: 0.3810 data: 0.0042 max mem: 21606 +eval (testid): [20] [40/82] eta: 0:00:16 time: 0.3318 data: 0.0036 max mem: 22448 +eval (train): [20] [320/509] eta: 0:01:08 time: 0.3603 data: 0.0044 max mem: 21606 +eval (testid): [20] [60/82] eta: 0:00:08 time: 0.3218 data: 0.0037 max mem: 22448 +eval (train): [20] [340/509] eta: 0:01:01 time: 0.3328 data: 0.0042 max mem: 21606 +eval (testid): [20] [80/82] eta: 0:00:00 time: 0.3341 data: 0.0040 max mem: 22448 +eval (testid): [20] [81/82] eta: 0:00:00 time: 0.3241 data: 0.0038 max mem: 22448 +eval (testid): [20] Total time: 0:00:30 (0.3669 s / it) +eval results: + +| model | repr | clf | dataset | ckpt | epoch | lr | wd | hparam_id | hparam | split | loss | acc | acc_std | f1 | f1_std | +|:---------|:-------|:------|:-------------|:-------|--------:|-------:|-----:|------------:|:---------|:-----------|-------:|--------:|----------:|--------:|----------:| +| flat_mae | patch | attn | nsd_cococlip | best | 7 | 0.0003 | 0.05 | 24 | [1, 1.0] | train | 2.0318 | 0.38667 | 0.0023877 | 0.33187 | 0.0024549 | +| flat_mae | patch | attn | nsd_cococlip | best | 7 | 0.0003 | 0.05 | 24 | [1, 1.0] | validation | 2.3389 | 0.29993 | 0.0052673 | 0.23211 | 0.0047446 | +| flat_mae | patch | attn | nsd_cococlip | best | 7 | 0.0003 | 0.05 | 24 | [1, 1.0] | test | 2.3152 | 0.30965 | 0.0053153 | 0.24525 | 0.0051682 | +| flat_mae | patch | attn | nsd_cococlip | best | 7 | 0.0003 | 0.05 | 24 | [1, 1.0] | testid | 2.2195 | 0.32716 | 0.0057639 | 0.26929 | 0.0055734 | + + +done! total time: 1:23:55 +eval (train): [20] [360/509] eta: 0:00:54 time: 0.3648 data: 0.0042 max mem: 21606 +eval (train): [20] [380/509] eta: 0:00:46 time: 0.3637 data: 0.0043 max mem: 21606 +eval (train): [20] [400/509] eta: 0:00:39 time: 0.3562 data: 0.0043 max mem: 21606 +eval (train): [20] [420/509] eta: 0:00:32 time: 0.3337 data: 0.0039 max mem: 21606 +eval (train): [20] [440/509] eta: 0:00:24 time: 0.3424 data: 0.0041 max mem: 21606 +eval (train): [20] [460/509] eta: 0:00:17 time: 0.3472 data: 0.0042 max mem: 21606 +eval (train): [20] [480/509] eta: 0:00:10 time: 0.3367 data: 0.0040 max mem: 21606 +eval (train): [20] [500/509] eta: 0:00:03 time: 0.3377 data: 0.0040 max mem: 21606 +eval (train): [20] [508/509] eta: 0:00:00 time: 0.3190 data: 0.0038 max mem: 21606 +eval (train): [20] Total time: 0:03:02 (0.3584 s / it) +eval (validation): [20] [ 0/85] eta: 0:04:17 time: 3.0266 data: 2.7919 max mem: 21606 +eval (validation): [20] [20/85] eta: 0:00:31 time: 0.3520 data: 0.0049 max mem: 21606 +eval (validation): [20] [40/85] eta: 0:00:18 time: 0.3366 data: 0.0039 max mem: 21606 +eval (validation): [20] [60/85] eta: 0:00:09 time: 0.3356 data: 0.0044 max mem: 21606 +eval (validation): [20] [80/85] eta: 0:00:01 time: 0.3352 data: 0.0040 max mem: 21606 +eval (validation): [20] [84/85] eta: 0:00:00 time: 0.3257 data: 0.0038 max mem: 21606 +eval (validation): [20] Total time: 0:00:31 (0.3729 s / it) +eval (test): [20] [ 0/85] eta: 0:04:17 time: 3.0255 data: 2.7951 max mem: 21606 +eval (test): [20] [20/85] eta: 0:00:32 time: 0.3782 data: 0.0239 max mem: 21606 +eval (test): [20] [40/85] eta: 0:00:19 time: 0.3446 data: 0.0040 max mem: 21606 +eval (test): [20] [60/85] eta: 0:00:09 time: 0.3446 data: 0.0044 max mem: 21606 +eval (test): [20] [80/85] eta: 0:00:01 time: 0.3275 data: 0.0042 max mem: 21606 +eval (test): [20] [84/85] eta: 0:00:00 time: 0.3158 data: 0.0039 max mem: 21606 +eval (test): [20] Total time: 0:00:32 (0.3802 s / it) +eval (testid): [20] [ 0/82] eta: 0:04:07 time: 3.0197 data: 2.7865 max mem: 21606 +eval (testid): [20] [20/82] eta: 0:00:30 time: 0.3679 data: 0.0189 max mem: 21606 +eval (testid): [20] [40/82] eta: 0:00:17 time: 0.3497 data: 0.0042 max mem: 21606 +eval (testid): [20] [60/82] eta: 0:00:08 time: 0.3322 data: 0.0033 max mem: 21606 +eval (testid): [20] [80/82] eta: 0:00:00 time: 0.3263 data: 0.0044 max mem: 21606 +eval (testid): [20] [81/82] eta: 0:00:00 time: 0.3160 data: 0.0042 max mem: 21606 +eval (testid): [20] Total time: 0:00:30 (0.3768 s / it) +eval results: + +| model | repr | clf | dataset | ckpt | epoch | lr | wd | hparam_id | hparam | split | loss | acc | acc_std | f1 | f1_std | +|:---------|:-------|:------|:-------------|:-------|--------:|-------:|-----:|------------:|:---------|:-----------|-------:|--------:|----------:|--------:|----------:| +| flat_mae | patch | attn | nsd_cococlip | best | 7 | 0.0003 | 0.05 | 24 | [1, 1.0] | train | 2.0318 | 0.38667 | 0.0023877 | 0.33187 | 0.0024549 | +| flat_mae | patch | attn | nsd_cococlip | best | 7 | 0.0003 | 0.05 | 24 | [1, 1.0] | validation | 2.3389 | 0.29993 | 0.0052673 | 0.23211 | 0.0047446 | +| flat_mae | patch | attn | nsd_cococlip | best | 7 | 0.0003 | 0.05 | 24 | [1, 1.0] | test | 2.3152 | 0.30965 | 0.0053153 | 0.24525 | 0.0051682 | +| flat_mae | patch | attn | nsd_cococlip | best | 7 | 0.0003 | 0.05 | 24 | [1, 1.0] | testid | 2.2195 | 0.32716 | 0.0057639 | 0.26929 | 0.0055734 | + + +done! total time: 0:20:48 diff --git a/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__attn/train_log.json b/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__attn/train_log.json new file mode 100644 index 0000000000000000000000000000000000000000..f5c60b018beeebe917036478a83f11df2e350ddc --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__attn/train_log.json @@ -0,0 +1,23 @@ +{"epoch": 0, "train/lr": 2.987987987987988e-05, "train/loss": 3.1352599930763243, "train/grad": 0.06020126551389694, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.1750927734375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.1748291015625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.174390869140625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.174007568359375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.17359375, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.172991943359375, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.17236328125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.17155517578125, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.170626220703125, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.1697412109375, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.168790283203125, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.167447509765625, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.16610595703125, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.164384765625, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.162742919921875, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.161300048828125, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.159544677734375, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.1575927734375, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.15567626953125, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.15406494140625, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.152269287109375, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.1507080078125, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.149071044921875, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.147720947265625, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.14642333984375, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.145125732421875, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.144105224609375, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.14332275390625, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.14242431640625, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.14154296875, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.140902099609375, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.140467529296875, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.139908447265625, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.13949951171875, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.1390966796875, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.13874267578125, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.13852294921875, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.13830322265625, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.138294677734375, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.13732421875, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.13087158203125, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.1157530212402342, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.094736328125, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.077071533203125, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.0529112243652343, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.0213665771484375, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.005419921875, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.9771233940124513, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.951871185302734, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.00798930078977719, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.007982048925478012, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.007970163717400282, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.007958697436843068, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.007947252003941686, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.007932106838561595, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.00791469429153949, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.007895445702597498, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.007871123212389648, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.007846600464545191, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.007824114852119236, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.007792380445171148, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.007763665874954313, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.007725676929112524, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.007693152164574712, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.007665728207211941, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.007636041180230677, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.0076082315412349995, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.0075854247901588675, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.007571669460739941, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.007563523747958243, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.00756170335225761, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.007566572474315763, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.007575390888378024, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.00758559400215745, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.00759871618123725, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0076103292009793225, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.007620491462294012, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.007633032803423703, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.007645531299058348, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.007654408658854663, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.007659404948353768, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.007662190815899521, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.007661047843284905, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.007657512158621102, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.007651347273495048, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.007643639179877937, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0076399284042418004, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.007640768997371197, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.007672014196868986, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.00786423141369596, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.008362748303916305, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.009060674454085529, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.009783761801663786, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.010406749730464071, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.011350272179115564, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.012203288518358023, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.01343005575472489, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.014071502941660582, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1719861030578613, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1711699962615967, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1698520183563232, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1685571670532227, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1672773361206055, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1655642986297607, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1636641025543213, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.16161847114563, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.159055233001709, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1564366817474365, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1539700031280518, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.150503158569336, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.147390604019165, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1433069705963135, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.139857530593872, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.136986255645752, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.133878707885742, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.131012201309204, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1286520957946777, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.1271419525146484, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.1259443759918213, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.1252803802490234, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.1249754428863525, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.124929666519165, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.125098466873169, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.1255364418029785, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.125999689102173, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.1264631748199463, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.127119302749634, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.1279594898223877, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.128854274749756, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.1296682357788086, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.1308162212371826, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.131741762161255, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.132495880126953, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.132645845413208, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.1316847801208496, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.1289258003234863, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.121216058731079, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.0738778114318848, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.8982183933258057, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.8116745948791504, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.769488573074341, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.715364694595337, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.6269779205322266, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.6182374954223633, "validation/loss_046_lr3.6e+01_wd1.0e+00": 2.6159439086914062, "validation/loss_047_lr4.3e+01_wd1.0e+00": 2.583643913269043, "validation/loss_048_lr5.0e+01_wd1.0e+00": 2.5781476497650146, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.05444813584348468, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.05444813584348468, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.05444813584348468, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.05444813584348468, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.05444813584348468, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.05444813584348468, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.05444813584348468, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.05444813584348468, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.05444813584348468, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.05444813584348468, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.05444813584348468, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.05444813584348468, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.05352528608342562, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.062384643779992616, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.062200073827980804, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06404577334809892, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.06312292358803986, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.06589147286821706, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.059800664451827246, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.062384643779992616, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.06164636397194537, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.06164636397194537, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.06164636397194537, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.06164636397194537, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.06164636397194537, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.06164636397194537, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.062384643779992616, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.07678110003691399, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.09523809523809523, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.12901439645625692, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.14673311184939092, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.1539313399778516, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.16925064599483206, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.19564414913252123, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.20948689553340716, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.2146548541897379, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.22517534145441123, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.2336655592469546, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.004308330412431359, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.004308330412431359, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.004304558454444639, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.004303804855275443, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.004303051519925317, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.004303051519925317, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.004303051519925317, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.004303051519925317, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.004303051519925317, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.004303051519925317, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.004305312317571512, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.004534204780632819, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.00575553656626077, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.009442274836141342, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.0076454939831811656, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.0065717171383140845, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.005243293716424273, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.0049615228837586066, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.0049615228837586066, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.0049615228837586066, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.005565878721416677, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.009409073698577861, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.008689462908646346, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.006533284316243128, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.004838896615669912, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.004838896615669912, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.004838896615669912, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.004838896615669912, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.004838896615669912, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.004838896615669912, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.007094059338222397, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.01742075188409412, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.02419601573640905, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.04707485306180182, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.06111303091185824, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.06853946094614363, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.08165886398278016, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.10481021278769483, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.1236559418443955, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.14151562242410656, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.1530212975050381, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.15974680505575373, "id_best": 48, "lr_best": 0.015, "wd_best": 0.05, "train/loss_best": 2.951871185302734, "validation/loss_best": 2.5781476497650146, "validation/acc_best": 0.2336655592469546, "validation/f1_best": 0.15974680505575373} +{"epoch": 1, "train/lr": 8.993993993993998e-05, "train/loss": 2.973051301240921, "train/grad": 0.09337339717894792, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.165235595703125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.163787841796875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.161451416015625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.159205322265625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.15714111328125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.154539794921875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.15173583984375, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.148994140625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.145858154296875, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.143056640625, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.14083251953125, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.13794189453125, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.1359033203125, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.13375, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.132308349609375, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.131231689453125, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.130526123046875, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.1299072265625, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.129609375, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.12949462890625, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.12947021484375, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.12952880859375, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.129471435546875, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.129520263671875, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.12956787109375, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.129542236328125, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.1294091796875, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.129234619140625, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.12880859375, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.127769775390625, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.124560546875, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.1064488220214845, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.0582955932617186, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.007873840332031, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.947011260986328, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.876178436279297, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.8038268661499024, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.743343086242676, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.6760041999816893, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.6009145545959473, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.5584395027160642, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.5272254657745363, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.5040435218811035, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.4883684158325194, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.4824585914611816, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.4828693294525146, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.4925239849090577, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.50547194480896, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.5188249015808104, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.007801016794983298, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.007765217006672174, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.007711624943185598, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.007664287083316595, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.00762196856783703, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.007570375259965658, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.007523806617828086, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.007483423530356958, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.00744645775295794, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.007422131213825196, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.0074098074052017186, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.007412338547874242, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.0074292381887789815, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.0074681861593853685, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.007509032811503858, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.007546244179829955, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.00758946139132604, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.0076333595975302156, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.0076724019576795395, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.007699673802126199, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.007723713738378137, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.007739681925158948, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.007750167718622834, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.007754190843552351, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.007750799793284386, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.007738673437852412, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.00772029249696061, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.007697551376186312, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.007657396646682173, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.007608348252251745, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.007610760501120239, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.008061640735249967, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.009221634215209632, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.010483683808706701, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.011768367805052549, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.013377986734267324, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.015225660044234247, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.01659163191448897, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.018061174808535724, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.019678693350870163, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.020595464492216706, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.02142994853667915, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.022135735852643848, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.022753510670736433, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.022677685283124447, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.024093976467847823, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.024044185262173414, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.025323636196553707, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.026206932244822383, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1577885150909424, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1554388999938965, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1518425941467285, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.148594379425049, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1456985473632812, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1421267986297607, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.138714075088501, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1355576515197754, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.132330894470215, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.12984037399292, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1281254291534424, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.126436948776245, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1254384517669678, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1246724128723145, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1243503093719482, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1241846084594727, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1240720748901367, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.123971462249756, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1238226890563965, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.123629093170166, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.123325824737549, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.1229305267333984, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.122445583343506, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.1218373775482178, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.1211540699005127, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.1202199459075928, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.11919903755188, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.117983341217041, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.1151421070098877, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.105372190475464, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.0453226566314697, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.7931175231933594, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.6885697841644287, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.6284005641937256, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.5420567989349365, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.481114625930786, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.493004083633423, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.4657816886901855, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.4530811309814453, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.4792909622192383, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.471944570541382, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.4575040340423584, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.472010374069214, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.5157601833343506, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.5623929500579834, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.636817455291748, "validation/loss_046_lr3.6e+01_wd1.0e+00": 2.637070894241333, "validation/loss_047_lr4.3e+01_wd1.0e+00": 2.652061939239502, "validation/loss_048_lr5.0e+01_wd1.0e+00": 2.6538097858428955, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.05444813584348468, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.05444813584348468, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.05444813584348468, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.05389442598744924, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.05444813584348468, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06183093392395718, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06404577334809892, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.06312292358803986, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.06441491325212255, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.0664451827242525, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.06939830195644149, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.07235142118863049, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.07364341085271318, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.07142857142857142, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.06902916205241787, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.06570690291620525, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.08361018826135105, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.1688815060908084, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.18733850129198967, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.2102251753414544, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.23274270948689554, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.2441860465116279, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.24473975636766335, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.2532299741602067, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.25599852344038393, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.25064599483204136, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.24787744555186417, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.2648578811369509, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.2619047619047619, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.2558139534883721, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.24178663713547435, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.23883351790328536, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.23588039867109634, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.2412329272794389, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.22868217054263565, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.004303051519925317, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.004303804855275443, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.0043128654970760235, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.005157271241830065, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.007799159611331405, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.0089052594961466, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.007687064312157724, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.005908137891623485, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.00496410790783837, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.0049522154648132055, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.005374085754065246, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.005710212517285114, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.006782569905853075, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.007985402623122839, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.009372150528653067, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.010081392556053984, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.010355143175875435, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.009815031891442614, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.009088193035990571, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.007362326722440779, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.025620091098868147, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.06763005518624146, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.10249764988491446, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.12776511074934457, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.15776091819028895, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.17138388154434417, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.17237795821319493, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.1868229701784578, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.19059496477507176, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.17932822477470403, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.17910777635214203, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.19234309143546233, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.18313825194965863, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.18080074797999815, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.17452280918793825, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.17025157691171314, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.1608428924863751, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.1638659572512976, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.1581208876715888, "id_best": 41, "lr_best": 0.0048, "wd_best": 0.05, "train/loss_best": 2.5272254657745363, "validation/loss_best": 2.4575040340423584, "validation/acc_best": 0.2648578811369509, "validation/f1_best": 0.19234309143546233} +{"epoch": 2, "train/lr": 0.00014999999999999988, "train/loss": 2.840377478599548, "train/grad": 0.12109235301613808, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.150091552734375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.1475048828125, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.143756103515625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.1406005859375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.13813720703125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.135369873046875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.13310546875, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.13122802734375, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.1296630859375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.128717041015625, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.128033447265625, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.127435302734375, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.127254638671875, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.12698974609375, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.12674560546875, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.12667236328125, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.12649169921875, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.1262158203125, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.126051025390625, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.125712890625, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.125416259765625, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.125113525390625, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.124552001953125, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.123695068359375, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.121876220703125, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.108248291015625, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.0473486328125, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.979115753173828, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.884080810546875, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.762946090698242, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.6514279556274416, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.5722130584716796, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.498628787994385, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.446000909805298, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.398794164657593, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.3702428913116456, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.3445608711242674, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.328531627655029, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.3252353143692015, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.3250904846191407, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.3333029985427856, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.344274888038635, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.3557216691970826, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.3812007308006287, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.406252477169037, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.4354152488708496, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.4837862348556516, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.536564304828644, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.593086017370224, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.007523299204185605, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.007485868064686656, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.007442333337385207, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.007418084023520351, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.007407577876001596, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.0074135505361482504, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.007438516037072986, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.007478008856996894, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.007535790938418358, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.007593864935915917, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.007643155152909458, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.007697518256027252, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.007733251629397273, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.007765024059917778, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.007780648609623313, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.007788857647683472, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.007794497674331069, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.007795618483796716, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.007792519864160567, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.007786410404369235, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.007773382479790598, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.007754431315697729, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0077257274906151, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.00768580544507131, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.007642394220456481, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.007783367384690792, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.009213308105245233, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.01071849805302918, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.012852510518860072, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.015507375621236861, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.017897743557114154, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.019449211740866303, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.020787217137403786, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.021645880020223558, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.022451655715703966, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.022669008746743203, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.02315144019201398, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.023235110295936466, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.02398144794628024, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.024387807277962567, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.024733364544808865, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.025592185044661164, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.025894310511648654, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.02670914710499346, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.027188409129157664, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.028580738799646496, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0299183077737689, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.03249681550078094, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.035075193075463175, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1420774459838867, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1391549110412598, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.13519287109375, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1322529315948486, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.130079984664917, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1279728412628174, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1264708042144775, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1254653930664062, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.124753475189209, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1244113445281982, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1242926120758057, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1242475509643555, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1242923736572266, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.124389410018921, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.124432325363159, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1244571208953857, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1243796348571777, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1241819858551025, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1238627433776855, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.12349534034729, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.122903823852539, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.1220991611480713, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.1207001209259033, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.117676258087158, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.1070830821990967, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.9390153884887695, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.7398672103881836, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.6796422004699707, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.6039533615112305, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.52363657951355, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.5079245567321777, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.4965529441833496, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.443051338195801, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.412668228149414, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.438398599624634, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.461181879043579, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.4651172161102295, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.479581594467163, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.458387851715088, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.5141818523406982, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.604504108428955, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.6088294982910156, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.7355308532714844, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.7485427856445312, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.8532519340515137, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.023862838745117, "validation/loss_046_lr3.6e+01_wd1.0e+00": 2.8433923721313477, "validation/loss_047_lr4.3e+01_wd1.0e+00": 2.787492275238037, "validation/loss_048_lr5.0e+01_wd1.0e+00": 2.8839590549468994, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06312292358803986, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06607604282022887, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.06607604282022887, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.06386120339608711, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.06256921373200443, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.06183093392395718, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.07511997046880768, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.1404577334809893, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.17201919527500922, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.18586194167589518, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.21114802510151348, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.23846437799926173, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.24141749723145073, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.25046142488002954, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.2652270210409745, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.2724252491694352, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.2646733111849391, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.2606127722406792, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.25950535252860835, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.25692137320044295, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.2541528239202658, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.24363233665559247, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.2320044296788483, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.22849760059062385, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.20985603543743078, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.20911775562938353, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.19896640826873385, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.18309339239571798, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.2009966777408638, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.20764119601328904, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.19453672942045036, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.006608025226079883, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.005230492489576546, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.0051857910586100365, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.008674757583639862, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.010152891233990621, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.009484576226188335, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.007326788563182204, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.0064183496045881324, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.008396243839924383, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.022418027429813376, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.05514355760723222, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.085220717459442, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.10300115512416369, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.1284831542467779, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.1617050438157528, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.16699344973107877, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.18336796509838163, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.1958153837769577, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.20392521017147555, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.19806261735497374, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.1965214519044971, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.19549289667834588, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.1941566715438081, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.19587561194546277, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.19177596440043201, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.1743412787268465, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.16940023835140092, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.14212740894973083, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.13585786776594513, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.11249731472394835, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.09970253138726844, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.1192040017574225, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.12276054364904644, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.10408951215378687, "id_best": 33, "lr_best": 0.00129, "wd_best": 0.05, "train/loss_best": 2.446000909805298, "validation/loss_best": 2.412668228149414, "validation/acc_best": 0.2724252491694352, "validation/f1_best": 0.20392521017147555} +{"epoch": 3, "train/lr": 0.0002100600600600602, "train/loss": 2.7873893642425536, "train/grad": 0.18837240722030402, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.1366064453125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.134345703125, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.1315283203125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.12974365234375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.12864990234375, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.127601318359375, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.126981201171875, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.126834716796875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.126632080078125, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.126337890625, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.126212158203125, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.126123046875, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.125902099609375, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.125655517578125, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.125361328125, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.12508544921875, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.124669189453125, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.124024658203125, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.123367919921875, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.12249267578125, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.1207275390625, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.11499267578125, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.0607669067382814, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.9574021911621093, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.8318551635742186, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.6803015899658202, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.579268035888672, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.508946533203125, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.426205940246582, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.358098030090332, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.3152692794799803, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.28716609954834, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.2636816120147705, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.2478131437301636, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.234643256664276, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.235369396209717, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.230433669090271, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.2372297406196595, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.239165563583374, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.257335171699524, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.2633908915519716, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.2771576273441316, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.314987213611603, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.3422884356975557, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.3995099759101866, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.4751046097278593, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.4894113302230836, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.5884529900550843, "train/loss_048_lr5.0e+01_wd1.0e+00": 4.7009507381916045, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.007360813829582185, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.007358282520435751, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.00737917663063854, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.007417753804475069, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.007462020220700651, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.0075210385932587085, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.007576250052079558, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.007620792388916015, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.007658614595420658, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.007682377900928259, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.007695040090475232, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.0077034281333908435, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.007706463194917888, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.0077070665592327715, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.007704268402885645, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.007698558694683015, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.007687952651176602, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.007669103294610977, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.007640801835805178, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.007606740929186344, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.007562137476634234, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.007567344084382057, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.008675326923839748, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.011191492220386862, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.01417551354272291, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.01740723690483719, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.019332728036679327, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.02057992445770651, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.02174796739127487, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.022508678007870913, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.02308699524961412, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.02358098209835589, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.023959085624665023, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.02429779197089374, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.025121826259419323, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.025178426941856742, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.025510222567245364, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.025752192297950387, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.026447412893176078, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.026726894676685334, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.02631240370683372, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.026962958592921495, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.02807672376744449, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.028314962647855282, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.02954825428314507, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0341638055536896, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.03315955817699432, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.03739087187685072, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.07345061156898737, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1304094791412354, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1284048557281494, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1262147426605225, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.124899387359619, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.124124050140381, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1234896183013916, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.123079299926758, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.122748851776123, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1224491596221924, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.122183084487915, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1219751834869385, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1216886043548584, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.121433973312378, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1211280822753906, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.120901346206665, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.120664119720459, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.12030291557312, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1196300983428955, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1183669567108154, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.11623477935791, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.10968279838562, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.067047595977783, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.7641427516937256, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.6675703525543213, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.6130592823028564, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.4997053146362305, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.463916301727295, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.4399545192718506, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.416531562805176, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.4040722846984863, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.3923792839050293, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.3970656394958496, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.4383583068847656, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.4606356620788574, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.537036657333374, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.537436008453369, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.476855516433716, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.501405715942383, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.4956960678100586, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.5427463054656982, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.564892530441284, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.565845489501953, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.605593204498291, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.8908629417419434, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.7766077518463135, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.3163082599639893, "validation/loss_046_lr3.6e+01_wd1.0e+00": 2.8474209308624268, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.5319864749908447, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06459948320413436, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06699889258028793, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06939830195644149, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.07475083056478406, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.07659653008490218, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.07678110003691399, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.07751937984496124, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.07788851974898486, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.07825765965300849, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.07881136950904392, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.07973421926910298, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.08250276854928018, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.09874492432631968, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.17091177556293835, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.19269102990033224, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.2074566260612772, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.2441860465116279, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.2532299741602067, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.2617201919527501, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.26744186046511625, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.2733480989294943, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.27906976744186046, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.2827611664820967, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.2742709486895533, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.26947212993724623, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.2591362126245847, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.26098191214470284, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.26393503137689184, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.2589516426725729, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.25359911406423036, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.25064599483204136, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.2412329272794389, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.24197120708748615, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.22978959025470652, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.19416758951642674, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.21853082318198597, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.18383167220376523, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.23477297895902546, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.1819859726836471, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.004962384259259259, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.005170139449738868, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.006493348681870755, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.008332814700139253, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.00936857881671125, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.010630795102861539, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.0112331294055816, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.011425011516730083, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.011689368493242988, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.011815548270525842, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.011873217670354356, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.011927129469905358, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.012036734863733632, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.012556081270552516, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.025675529651351708, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.0676196230665332, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.09476295096023257, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.11333165979691424, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.15445852454997397, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.1672604748359854, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.1786634063918154, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.18808421173693926, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.1967729753979389, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.20320545137100876, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.20705601764568557, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.20480194059850154, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.20047758312782957, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.18826658371673785, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.1889477596245411, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.1943242356262629, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.19978693509494116, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.19153645338730574, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.1857644147417845, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.17463154124846528, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.1648137939180199, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.1703736372216136, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.14254359599639765, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.14533016814773345, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.11249907390328266, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.15449616524207185, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.09416680745530571, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 31, "lr_best": 0.0009299999999999999, "wd_best": 0.05, "train/loss_best": 2.28716609954834, "validation/loss_best": 2.3970656394958496, "validation/acc_best": 0.2827611664820967, "validation/f1_best": 0.20705601764568557} +{"epoch": 4, "train/lr": 0.0002701201201201201, "train/loss": 2.7870130610466, "train/grad": 0.24333604939281941, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.127735595703125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.1264404296875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.125233154296875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.1246044921875, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.124205322265625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.123985595703125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.123824462890625, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.123514404296875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.123197021484375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.122960205078125, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.122740478515625, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.122357177734375, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.12194580078125, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.12135986328125, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.12068359375, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.120015869140625, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.11878173828125, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.116630859375, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.11018798828125, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.0593682861328126, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.929975738525391, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.7839982604980467, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.6473003005981446, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.5358808517456053, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.4433422470092774, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.3621302890777587, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.3139906978607176, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.2825624465942385, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.2457260370254515, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.216337113380432, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.19430805683136, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.1785891675949096, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.167955102920532, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.1687755393981933, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.168979163169861, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.1770658540725707, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.184087144136429, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.1878632879257203, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.2009883332252502, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.223530683517456, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.263602991104126, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.2874407172203064, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.3377128684520723, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.4088495814800264, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.461498410701752, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.534827560186386, "train/loss_046_lr3.6e+01_wd1.0e+00": 4.6640964078903195, "train/loss_047_lr4.3e+01_wd1.0e+00": 5.440580644607544, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.007446459773927927, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.007498857716564089, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.007573959904257208, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.0076310854381881656, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.007672566510736942, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.00770919902715832, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.007733577650506049, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.007747627284843474, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.007756042657420039, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.007759320863988251, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.007759997469838709, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.007758460510522127, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.007754873125813902, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.007744638377334923, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.007727443154435605, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.007706433576531708, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.007675254927016794, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.007635970793198794, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.007644456892739982, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.008578537786379457, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.011563858231529594, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.015041193019133061, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.018137036329135298, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.019976509986445307, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.02145161000546068, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.022659083120524882, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.02328092047944665, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.023794640274718403, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0244433662109077, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0249928367882967, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.025590125769376755, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.025867155659943818, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.026387484092265368, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.026764489579945802, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.02720384563319385, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.02722146316431463, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.027774836849421263, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.027579758474603297, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.027720307931303978, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.028067848887294532, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.028779624719172715, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.02958905218169093, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.03084619790315628, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.033338864063844086, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.03475728453136981, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.036385636748746036, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.06805664363317192, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.07639115327969194, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1252169609069824, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1243326663970947, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1234798431396484, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.12300443649292, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1226871013641357, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1223676204681396, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1220715045928955, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.121781587600708, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.121436595916748, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1210548877716064, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.120685338973999, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1201038360595703, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.119497776031494, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1184682846069336, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1173696517944336, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.116074323654175, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1138155460357666, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1082799434661865, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.0731441974639893, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.7922468185424805, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.6705105304718018, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.613165855407715, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.502426862716675, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.4400975704193115, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.416940927505493, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.412362813949585, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.4126527309417725, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.415428400039673, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.4288086891174316, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.4302031993865967, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.4544336795806885, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.4901416301727295, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.5297672748565674, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.5174624919891357, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.4689571857452393, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.4556477069854736, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.4399735927581787, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.4280028343200684, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.530089855194092, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.5768260955810547, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.614173173904419, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.583570718765259, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.575554370880127, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.569793462753296, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.6126492023468018, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.5672428607940674, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06570690291620525, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.07069029162052418, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.07622739018087855, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.07604282022886674, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.07235142118863049, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.07179771133259505, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.07179771133259505, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.07161314138058324, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.0710594315245478, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.07308970099667775, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.07475083056478406, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.10889627168696936, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.16943521594684385, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.19804355850867478, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.20505721668512367, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.2440014765596161, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.25839793281653745, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.2652270210409745, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.26891842008121075, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.27408637873754155, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.2751937984496124, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.27611664820967147, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.2742709486895533, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.26947212993724623, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.2633813215208564, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.25802879291251385, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.26116648209671467, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.2681801402731635, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.26965669988925806, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.2705795496493171, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.27150239940937615, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.2499077150239941, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.22905131044665927, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.23994093761535623, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.24473975636766335, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.25064599483204136, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.2500922849760059, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.2571059431524548, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.2543373938722776, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.004964970181228649, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.0055661392870695195, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.00755518492384231, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.009711427443594335, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.011129267724088556, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.011498627917937208, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.010768317622438335, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.010297069399703375, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.009844211385617793, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.00981829886917624, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.009745995647206808, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.010894023837852505, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.012005847039971188, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.027472057679098466, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.07271476632786868, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.10107112830170552, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.11803489702009777, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.1614842056906051, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.18040795190886574, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.18747480167969655, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.19169106101678945, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.19613718057625773, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.19852970765607822, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.19601833730670815, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.19592141913157965, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.1957329431211852, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.19664997826570227, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.19188358918182394, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.19093666036331777, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.20436195663044834, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.2071781991650856, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.20996045840935604, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.21467902126139404, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.1936995210775594, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.18154097573702574, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.1797880344274366, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.18552386880373772, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.1992426271625066, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.19630590452066166, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.19316456374652183, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.17519372635608, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 28, "lr_best": 0.00057, "wd_best": 0.05, "train/loss_best": 2.2457260370254515, "validation/loss_best": 2.4288086891174316, "validation/acc_best": 0.27611664820967147, "validation/f1_best": 0.19601833730670815} +{"epoch": 5, "train/lr": 0.00029891323817685334, "train/loss": 2.6466176545619966, "train/grad": 0.14817066729068756, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.1291455078125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.128836669921875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.1286279296875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.1284521484375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.128326416015625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.1281103515625, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.1278173828125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.12749267578125, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.12712158203125, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.126671142578125, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.12620849609375, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.125557861328125, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.124794921875, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.123658447265625, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.1221240234375, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.119866943359375, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.1116259765625, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.018998107910156, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.84088134765625, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.7057510375976563, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.601577835083008, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.4890208435058594, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.393174285888672, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.3253401565551757, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.272901039123535, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.2296859645843505, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.200980987548828, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.1784876680374143, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.1562210392951964, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.1347468972206114, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.119271466732025, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.1130741107463837, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.1030218625068664, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.0997896885871885, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.1039909064769744, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.120037373304367, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.1307129740715025, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.1554217135906217, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.1767255914211274, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.215504616498947, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.2555478549003602, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.282515411376953, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.332470360994339, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.3738145172595977, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.430596237182617, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.4739421033859252, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.007539510864298791, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.0075850421492941675, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.007633084096014499, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.007659749356098473, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.007674569333903492, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.0076849255524575714, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.007689538784325123, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.007690591143909842, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.007688540904782712, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.007684196070767939, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.007678039951715618, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.007666108217090368, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.007650567286182195, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.007622578542213887, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.007591552620287985, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.007564326848369092, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.007600312267895788, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.009413290342781693, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.013922415480483324, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.01755283999722451, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.019578456776216627, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.02134480662178248, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.02275554968044162, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.02317696358077228, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.023636107323691247, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.02427128776907921, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.024890464106574653, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.02535126601345837, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.026023786682635545, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.02668078200891614, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.027305693347007037, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.027809015791863203, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.028223119983449577, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.028363936645910144, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.028541008178144693, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.028370340624824165, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.02848858836106956, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.028690594267100095, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.02901529151946306, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.02972730580717325, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.03049082074314356, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.031232374319806695, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.03181749467737973, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.032525899540632966, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.03369485167786479, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.034291448388248685, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.123486042022705, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1230900287628174, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.122685670852661, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1224236488342285, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1222105026245117, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.121950626373291, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.121673822402954, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.121371269226074, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1209664344787598, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1205151081085205, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.120046615600586, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.119269609451294, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.118387222290039, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1167216300964355, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1141107082366943, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.10871958732605, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.0741336345672607, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.765824794769287, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.656322717666626, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.586308717727661, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.4751012325286865, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.4160289764404297, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.3831756114959717, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.3586173057556152, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.35711932182312, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.3738973140716553, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.390454053878784, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.3979666233062744, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.4040913581848145, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.4462335109710693, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.4747838973999023, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.470609426498413, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.454622745513916, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.4211859703063965, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.434213399887085, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.4461746215820312, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.486673355102539, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.466156244277954, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.4454948902130127, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.404064655303955, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.4748172760009766, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.435429096221924, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.4716668128967285, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.4791624546051025, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.662456512451172, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.922384262084961, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06699889258028793, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06939830195644149, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.07198228128460686, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.0725359911406423, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.07272056109265411, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.07272056109265411, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.07401255075673681, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.07954964931709117, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.10465116279069768, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.1821705426356589, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.1998892580287929, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.22277593207825766, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.2543373938722776, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.2691029900332226, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.2766703580657069, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.28497600590623845, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.2836840162421558, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.28349944629014395, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.27888519748984864, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.27759320782576596, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.2796234772978959, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.2757475083056478, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.26854928017718716, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.2619047619047619, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.2681801402731635, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.27556293835363604, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.28294573643410853, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.2842377260981912, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.27150239940937615, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.2692875599852344, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.2681801402731635, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.2748246585455888, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.2596899224806202, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.26153562200073827, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.2543373938722776, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.2572905131044666, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.22240679217423404, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.20653377630121816, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.004962384259259259, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.004966695626991023, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.005159817900815974, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.006013226809793733, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.008103070752268298, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.009249002765166376, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.00983009673766141, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.010109586357286449, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.010138504786422933, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.011112392165704713, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.01346097143497702, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.01707452124873167, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.02424900256065789, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.0902826253785959, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.11179882466911573, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.13305738695618063, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.17291762036430722, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.19159661986413398, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.20200622796797515, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.2121454919913867, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.2127480212527498, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.2080057352674579, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.20167664075446665, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.1972982818383848, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.1993770399847914, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.2018094989140271, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.20078188617157658, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.19988031164180406, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.20873896084923663, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.21233777680258029, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.20822893091983583, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.20990438804029207, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.1992233287475056, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.1974945677957987, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.20862494758950567, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.21775708226788026, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.2003975643529082, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.20058801466522094, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.19745464683643335, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.20937669605825102, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.1728965424655553, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.1479512571555653, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 23, "lr_best": 0.00025499999999999996, "wd_best": 0.05, "train/loss_best": 2.3253401565551757, "validation/loss_best": 2.3586173057556152, "validation/acc_best": 0.28497600590623845, "validation/f1_best": 0.2121454919913867} +{"epoch": 6, "train/lr": 0.0002924170901991409, "train/loss": 2.5592440938949585, "train/grad": 0.15034604527056217, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.125938720703125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.12576171875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.125460205078125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.125079345703125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.12485107421875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.12453125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.12414794921875, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.123658447265625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.123153076171875, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.1224853515625, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.121884765625, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.120721435546875, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.11953857421875, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.11681640625, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.110677490234375, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.0721725463867187, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.8799057006835938, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.703967742919922, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.5985800933837893, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.495989189147949, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.38659366607666, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.310950126647949, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.2499588203430174, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.201937503814697, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.157755527496338, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.118261227607727, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.0880889463424683, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.0630563259124757, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.0345720934867857, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.0142732739448546, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.000741432905197, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.9974982345104217, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.9910554420948028, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.994561542868614, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.9988592940568923, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.013021189570427, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.0289537370204926, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.049165610074997, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.0775341403484346, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.1016823756694794, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.1343123829364776, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.153089429140091, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.202394108772278, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.2366405010223387, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.3166784501075743, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.3803816556930544, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.007484166629146785, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.007507321110460907, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.007527173757553101, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.0075352635351009665, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.007538337470032274, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.007538908463902772, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.007538495827466249, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.007536258692853153, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.00753103838302195, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.007522842439357191, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.007513552207965404, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.007494715205393731, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.0074730288982391355, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.007442441137973219, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.007450111007783562, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.007971169333904982, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.012539371189195663, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.017216378445737063, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.01969378048554063, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.021317765484564006, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.02312510311603546, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.023864537747576832, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.024322237726300953, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.024484954476356506, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.02481524046510458, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.025343921426683666, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.02579255579970777, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.026093896590173245, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.026491284193471073, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.02697284961119294, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.027575848149135707, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.028123997943475844, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.02862484099343419, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.028869291050359607, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0289924524538219, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.028933256519958376, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.02963719444349408, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.029400747902691364, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.02971226436085999, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.02888763220049441, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.028873871127143503, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.029038294050842524, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.029670410435646773, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.029933999245986342, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.031064297510311006, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.03272081742994487, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1235384941101074, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1233608722686768, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.123154640197754, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1229920387268066, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1228363513946533, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.122607469558716, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.122347831726074, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1220173835754395, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1215415000915527, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1209754943847656, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1203272342681885, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1192362308502197, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1177241802215576, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1134157180786133, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.0971126556396484, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.9208850860595703, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.700049638748169, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.6155807971954346, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.536529064178467, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.4478282928466797, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.4074995517730713, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.3881654739379883, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.3725359439849854, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.358210802078247, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.3558435440063477, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.3632192611694336, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.3687193393707275, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.3752036094665527, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.4117636680603027, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.44433331489563, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.4991345405578613, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.4873058795928955, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.472036123275757, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.489910364151001, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.486708164215088, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.4970362186431885, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.479771137237549, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.547612428665161, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.575014591217041, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.5284600257873535, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.6239912509918213, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.705676555633545, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.721208095550537, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.754364252090454, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.8562207221984863, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.7998104095458984, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.0636766334440753, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.0681063122923588, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.1539313399778516, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.18180140273163528, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.20653377630121816, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.22757475083056478, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.2589516426725729, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.2663344407530454, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.27759320782576596, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.2823920265780731, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.287375415282392, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.287375415282392, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.28959025470653377, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.29051310446659284, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.2836840162421558, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.27611664820967147, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.2702104097452935, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.2643041712809155, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.26301218161683276, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.2593207825765965, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.2576596530084902, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.2622739018087855, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.26208933185677374, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.26541159099298633, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.2563676633444075, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.25599852344038393, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.2622739018087855, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.24307862679955702, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.23052787006275377, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.23883351790328536, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.2349575489110373, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.20634920634920634, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.21982281284606867, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.004962384259259259, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.004964970181228649, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.005447870040144243, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.011129081554790176, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.06500534962903691, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.08993343230117971, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.11687392401806324, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.14438995683575181, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.17567549132862356, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.18329284532529644, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.19102701608800368, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.20136238331209402, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.2086750644168661, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.21115579767451195, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.21743733006867572, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.22214995169984242, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.21919693008127392, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.2211046271171038, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.21816948389511112, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.21399095550772548, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.21066355741854373, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.20949110465436083, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.20899529447393442, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.215845530294858, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.2159926729282334, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.2161896455606019, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.21114202774699511, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.1973704790756042, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.20587580966936234, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.19388771722283685, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.18306627819707788, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.18632835939664838, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.17714002924040714, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.15597423093362098, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.15594245890865185, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 26, "lr_best": 0.00041999999999999996, "wd_best": 0.05, "train/loss_best": 2.0880889463424683, "validation/loss_best": 2.3687193393707275, "validation/acc_best": 0.29051310446659284, "validation/f1_best": 0.22214995169984242} +{"epoch": 7, "train/lr": 0.00027969249556793234, "train/loss": 2.5144003307819367, "train/grad": 0.1577802489697933, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.128997802734375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.12873291015625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.128431396484375, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.128143310546875, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.12788330078125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.127532958984375, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.127015380859375, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.12648193359375, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.12575927734375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.12482666015625, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.123897705078125, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.1223193359375, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.11974365234375, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.1099951171875, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.0097079467773438, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.809178466796875, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.6813890075683595, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.5828614807128907, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.454788131713867, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.3641466522216796, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.293364238739014, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.2350781059265135, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.18465482711792, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.1417422771453856, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.1033675718307494, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.066692569255829, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.039494559764862, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.0162831282615663, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.9882839500904084, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.9657102692127228, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.946917588710785, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.9372189062833787, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.9274192827939987, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.9303840970993043, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.9317554277181626, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.9526415073871612, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.968015678524971, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.9928290450572967, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.02672678232193, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.0737299191951752, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.1192256557941436, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.1379463410377504, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.1925728690624235, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.2587346065044405, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.283766349554062, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.3236059379577636, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.007596024391241372, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.007610906001646072, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.007623119396157563, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.007628170049283654, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.0076303881057538095, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.007631130160298198, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.007630598121322691, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.0076268909126520155, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.007619150548707694, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.00760755619732663, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.007594396381173283, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.007571640708483755, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.007551458929665387, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.007591260187327861, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.009294794625602662, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.014417374087497593, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.01855989130679518, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.020867845974862576, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.02276651220396161, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.0242490213830024, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.024875769671052695, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.025085145737975836, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.02541978315450251, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.025498031908646225, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.02592676375992596, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.026609778217971326, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.02729249763302505, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.02782578531652689, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.028484186325222254, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.02887317298911512, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.028973810896277426, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.028940515015274285, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.029400571091100572, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.029499444710090757, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.02927422915585339, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.029516634475439788, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.02972113830037415, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.029695714488625527, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0299843227583915, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.03004399100318551, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.030198612436652183, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.030744500206783414, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.03102280605584383, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.03284608616493642, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.03136344972997904, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.03128829300403595, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.122931957244873, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1227097511291504, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1223533153533936, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1220309734344482, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.121690273284912, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1212267875671387, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1206741333007812, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.120055913925171, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1191792488098145, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.118143081665039, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1170177459716797, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.114664077758789, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.110602855682373, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.086129903793335, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.811537981033325, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.6773335933685303, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.6002402305603027, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.5178160667419434, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.4190173149108887, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.3817813396453857, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.350187301635742, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.3382599353790283, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.3324549198150635, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.333136558532715, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.3388521671295166, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.3530542850494385, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.3792824745178223, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.4002654552459717, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.400752067565918, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.386658191680908, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.4238665103912354, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.45886492729187, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.5166513919830322, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.513075351715088, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.528618335723877, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.511061906814575, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.491342067718506, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.4924442768096924, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.4984514713287354, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.4452922344207764, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.551123857498169, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.6248176097869873, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.619325637817383, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.677630662918091, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.6391146183013916, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.6224312782287598, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.0636766334440753, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.0636766334440753, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.07954964931709117, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.1744186046511628, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.1998892580287929, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.21779254337393872, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.24289405684754523, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.2691029900332226, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.2757475083056478, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.2868217054263566, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.29069767441860467, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.29346622369878184, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.29457364341085274, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.29992617201919525, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.2971576227390181, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.29069767441860467, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.2871908453303802, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.28922111480251017, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.2918050941306755, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.2866371354743448, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.2851605758582503, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.26891842008121075, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.271686969361388, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.27260981912144705, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.2751937984496124, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.27703949796973054, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.2733480989294943, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.2768549280177187, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.2702104097452935, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.25987449243263194, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.260797342192691, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.25839793281653745, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.2604282022886674, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.2576596530084902, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.24160206718346253, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.004962384259259259, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.005179064721841408, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.005183194838367252, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.005723381127919353, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.006297773571299801, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.016843922935172378, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.07671498370295007, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.10604552203989293, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.12958352698046707, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.1595087303150108, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.19333950337924774, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.20419702145694285, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.21630641222509817, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.2191543471936244, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.2255340617430465, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.2287925395669028, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.23211007531295333, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.22798959150171338, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.22091155828538186, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.21903165401666025, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.22254476356155914, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.22831753931981216, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.2240175398113876, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.21907673601961644, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.21231810607186966, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.21848351308786895, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.22108409920533126, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.21811813185746973, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.21955770251915332, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.21825283283046457, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.223039768435387, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.21927916609357337, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.2004508711671226, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.19840505505168982, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.1846839639181549, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.18123832492065875, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.18400486517491998, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.17636144155001607, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 24, "lr_best": 0.0003, "wd_best": 0.05, "train/loss_best": 2.1033675718307494, "validation/loss_best": 2.3388521671295166, "validation/acc_best": 0.29992617201919525, "validation/f1_best": 0.23211007531295333} +{"epoch": 8, "train/lr": 0.0002612959497061927, "train/loss": 2.461156233549118, "train/grad": 0.16323864728212356, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.12789306640625, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.127691650390625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.127291259765625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.126939697265625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.12662353515625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.126165771484375, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.125556640625, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.124842529296875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.123931884765625, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.122791748046875, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.12150146484375, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.11858642578125, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.11236083984375, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.0186175537109374, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.7851788330078127, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.6841590881347654, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.588684387207031, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.460546226501465, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.346867866516113, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.279475383758545, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.216012325286865, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.1633328866958617, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.1135890913009643, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.0738288593292236, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.036214039325714, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.9990443062782288, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.968505541086197, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.9443508422374725, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.9184203577041625, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.8944521832466126, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.8778979980945587, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.8683276635408401, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.8578323930501939, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.857803582549095, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.8676630920171737, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.8847517132759095, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.8986891055107116, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.9280050492286682, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.9674888724088668, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.0055549538135526, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.0432278728485107, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.0907430374622344, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.125637892484665, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.18035649895668, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.237970133423805, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.2856268858909607, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.007690371957141906, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.007697086418047548, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.007700502097140998, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.007700705374591052, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.007699680523946881, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.007697093333117664, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.007693970806431025, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.007688869836274534, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.0076801862497814, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.007668512971140445, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.007656707679852843, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.007642405845690519, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.007667080173268915, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.009186514033935965, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.01548082156572491, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.01863899843301624, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.021253863545134664, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.022952980501577257, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.02485341627150774, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.02549503437243402, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.025712262289598584, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.025720818769186735, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.025998669331893324, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.026063970010727643, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.02641822537407279, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.027101676370948555, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.02777235076762736, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.028390792151913046, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.029224347677081822, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.029862494934350253, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.030014557810500265, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.030445819552987814, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.030771058807149528, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.030743276765570045, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.030881649423390625, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.030966396890580655, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.031055605970323086, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.030967042231932283, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.03115251151844859, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.03084287884645164, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.030405980683863163, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.03108869232237339, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.03088124423287809, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0314532604534179, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.031248685969039798, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.03147276501171291, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1224851608276367, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.122206687927246, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.121748685836792, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1213037967681885, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1208367347717285, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.120205879211426, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1194934844970703, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.118635654449463, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1174330711364746, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1159791946411133, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1141910552978516, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.109790563583374, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.0974063873291016, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.8543314933776855, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.6854286193847656, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.618507146835327, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.5471339225769043, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.449526786804199, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.396876335144043, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.371400833129883, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.3517119884490967, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.3525328636169434, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.3594937324523926, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.379577159881592, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.3954076766967773, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.4145724773406982, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.432382583618164, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.4454421997070312, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.439241647720337, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.4556972980499268, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.5246291160583496, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.555821418762207, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.5628461837768555, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.5432965755462646, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.5303144454956055, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.493928909301758, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.4748950004577637, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.502910852432251, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.5473268032073975, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.5274832248687744, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.5276505947113037, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.457484483718872, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.5247151851654053, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.5461292266845703, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.5820040702819824, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.6648917198181152, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06478405315614617, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06902916205241787, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.07179771133259505, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.07401255075673681, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.0784422296050203, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.08342561830933924, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.08840900701365817, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.10022148394241417, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.16666666666666666, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.1982281284606866, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.21539313399778517, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.23034330011074197, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.2589516426725729, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.2702104097452935, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.2766703580657069, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.2866371354743448, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.2886674049464747, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.2916205241786637, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.29088224437061644, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.2851605758582503, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.2833148763381321, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.27759320782576596, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.27703949796973054, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.2766703580657069, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.268733850129199, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.2622739018087855, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.25489110372831303, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.2532299741602067, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.25396825396825395, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.2574750830564784, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.2643041712809155, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.26596530084902176, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.26411960132890366, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.25249169435215946, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.26559616094499816, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.26116648209671467, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.2703949796973053, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.24658545588778147, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.2467700258397933, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.24953857511997046, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.23108157991878922, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.004965832754227473, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.005169405160438159, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.005523264064300432, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.006981378360187839, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.009159320822133615, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.009821661655862393, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.010517769708908062, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.013087041026107846, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.01609838623984193, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.01928095558949011, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.022386592515641266, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.0658589385356729, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.11185557865665581, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.13218878029841383, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.14867321987276316, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.1776808730174859, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.1912894837114697, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.19958727138312615, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.2132931478694391, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.21579612184728406, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.21745446183281322, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.21557792179244895, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.2147777298895354, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.21503589233505424, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.2111703730752771, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.2118698618152485, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.21684092847998385, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.21713653665738206, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.20884183282784782, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.20316412945147996, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.20515140346853775, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.20959109583305516, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.2049635002271881, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.21016990664608085, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.21398621813098537, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.2164906954185137, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.20800594925002067, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.20948860489975427, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.21293778135305272, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.21764371759367687, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.19588817435495806, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.21811725931744716, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.2158010078277676, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.1870155100597641, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 22, "lr_best": 0.00021599999999999996, "wd_best": 0.05, "train/loss_best": 2.1135890913009643, "validation/loss_best": 2.3594937324523926, "validation/acc_best": 0.2916205241786637, "validation/f1_best": 0.21745446183281322} +{"epoch": 9, "train/lr": 0.00023803200426111704, "train/loss": 2.4076642751693726, "train/grad": 0.16346948340535164, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.130244140625, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.12994873046875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.129515380859375, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.129119873046875, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.12865966796875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.12802978515625, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.127239990234375, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.126343994140625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.125025634765625, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.12343505859375, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.12132568359375, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.115272216796875, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.0889996337890624, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.813309783935547, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.6846414184570313, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.6018292999267576, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.486394386291504, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.3704459190368654, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.2809403991699218, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.2208076095581055, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.1605706214904785, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.1094756507873536, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.0602211570739746, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.0187639379501343, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.978228921890259, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.9404131031036378, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.9070714545249938, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.8807398080825806, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.8475016576051713, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.8225469797849656, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.8025885450839996, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.7924423056840897, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.7820292407274245, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.7873363119363785, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.796699622273445, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.8083409309387206, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.8219381576776505, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.8435634583234788, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.8746675503253938, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.9361131876707076, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.9640823829174041, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.9873439437150955, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.0393021154403685, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.0870032894611357, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.1422174829244613, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.207196106910706, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.0076433293987065555, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.007645602542906999, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.007645011343993246, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.007642955235205591, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.007640860183164478, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.0076363848359324036, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.0076305832737125455, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.007622447658795863, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.0076083690766245125, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.007592388514894992, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.007577995131723583, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.007581349250394851, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.00785091130528599, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.014027201859280468, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.018310296284034848, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.020695263147354127, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.02279578389134258, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.024417365565896035, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.025838666297495365, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.026063249269500374, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.026385883260518314, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.026367973163723947, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.02664911463856697, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.02678047362715006, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.027067224234342574, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.027740161521360277, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.028342842580750583, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.02877737642265856, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.029254722222685815, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.029892728254199027, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.030310090584680437, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.030610162317752838, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.031239878768101335, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.03144454186782241, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.031648798417299985, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.031183383027091623, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.031132219629362225, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.03073885294608772, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.03014379699714482, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.030161056676879527, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.02945067882537842, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.02923379491083324, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.02892420530319214, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.028891878789290785, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.028584754075855017, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.029741015248000623, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1222710609436035, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1220040321350098, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1215667724609375, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1211369037628174, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1207196712493896, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1201212406158447, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1194369792938232, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1186201572418213, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1173837184906006, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1156978607177734, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1132054328918457, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.104138135910034, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.0439655780792236, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.726996421813965, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.6297049522399902, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.5728766918182373, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.474400043487549, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.4281296730041504, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.393240451812744, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.3710055351257324, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.3590307235717773, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.354887008666992, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.352017641067505, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.3573973178863525, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.3773274421691895, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.3980205059051514, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.4157729148864746, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.4130797386169434, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.4175078868865967, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.429715871810913, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.463656425476074, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.542080879211426, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.5827484130859375, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.56673002243042, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.586573362350464, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.5566561222076416, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.5181407928466797, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.5285582542419434, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.4970617294311523, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.50484561920166, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.4831337928771973, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.5213518142700195, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.492980480194092, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.5859639644622803, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.646554946899414, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.498821258544922, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06570690291620525, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.07918050941306755, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.11166482096714656, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.18549280177187155, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.20801033591731266, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.2222222222222222, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.2541528239202658, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.26375046142488, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.2705795496493171, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.27759320782576596, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.27906976744186046, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.2882982650424511, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.28903654485049834, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.28811369509043927, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.2853451458102621, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.2807308970099668, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.2794389073458841, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.28036175710594313, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.28183831672203763, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.2781469176818014, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.27851605758582504, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.2705795496493171, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.2602436323366556, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.26301218161683276, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.26448874123292726, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.26891842008121075, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.2707641196013289, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.2753783684016242, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.2809154669619786, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.2781469176818014, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.2742709486895533, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.27740863787375414, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.2862679955703212, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.2731635289774825, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.25544481358434845, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.28146917681801403, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.00496410790783837, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.004965832754227473, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.005164907540443035, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.0053733914822591934, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.005342590971857557, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.006321014975298785, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.00849759043717018, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.015903524687600527, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.02591856919230363, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.08739035722518418, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.11922862631161484, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.13842406304125857, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.17320331611931103, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.18679156981077127, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.19805477284126724, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.2061426561382663, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.20896734621389965, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.21893994920327145, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.22040162343979905, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.2242678766991603, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.22479883371593787, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.22277655095309257, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.2226709752732375, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.2246668908244772, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.22978973033574168, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.22717356008229342, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.21831278503762788, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.20891381507521165, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.19963829253382212, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.2026021560135555, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.2019402003474271, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.20191731297456983, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.20878239770013685, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.2134484055666982, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.21496691860638215, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.21106701533596575, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.19676907085656772, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.19667722286346848, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.21266112518699687, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.19651539610239968, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.19497676552139556, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.2073889219752315, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 22, "lr_best": 0.00021599999999999996, "wd_best": 0.05, "train/loss_best": 2.0602211570739746, "validation/loss_best": 2.352017641067505, "validation/acc_best": 0.28903654485049834, "validation/f1_best": 0.22040162343979905} +{"epoch": 10, "train/lr": 0.00021091808096876188, "train/loss": 2.3723053169250488, "train/grad": 0.16671138122677803, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.12848876953125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.12818603515625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.12769775390625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.127138671875, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.126578369140625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.12582763671875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.1249951171875, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.1239013671875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.122318115234375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.12017822265625, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.11697021484375, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.1035107421875, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.9693568420410155, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.733884124755859, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.629670639038086, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.5410070037841797, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.410188522338867, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.314673728942871, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.2375783348083496, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.182992944717407, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.126219940185547, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.077190055847168, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.0244782829284667, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.9848126149177552, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.9467895722389221, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.905435426235199, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.866785084605217, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.8387016052007674, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.8044974893331527, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.77385648727417, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.7486816900968551, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.7284956663846969, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.7210150736570358, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.727813459634781, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.73224810898304, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.75353830575943, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.769536799788475, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.7909542948007584, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.8383144050836564, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.8797267270088196, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.9349158531427384, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.9526045751571655, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.001742241382599, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.037220457792282, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.1043946570158005, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.1622252893447875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.0075432821712456645, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.007546700744424015, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.007549341723788529, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.007550358599983156, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.007550830070395023, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.007550670725759118, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.007548695232253521, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.007544860769994557, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.0075370037346147, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.007528699864633381, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.0075281346077099446, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.0076280380599200726, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.009730002572759987, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.016628373018465935, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.020073561295866967, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.022048268672078847, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.024262704038992524, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.025549254436045884, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.02648391243070364, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.02654545133933425, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.026843143301084636, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.026670353477820753, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.02687609345652163, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.026896726172417403, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.02711521458812058, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.02781554212793708, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0285250776167959, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.029010894717648627, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.029630829663947224, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.03020195197314024, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.03049776440486312, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.030846671778708697, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.03129255635663867, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.03169611574150622, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.03158967027440667, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.031775409439578656, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.032135358545929193, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.031437658835202456, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.03145448445342481, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.030486470414325596, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.03033839819021523, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.030104353465139864, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.030001644864678382, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.02977048653177917, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.029420115696266295, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.029420989006757735, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.122235059738159, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1219546794891357, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1215012073516846, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1210522651672363, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1206016540527344, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1199164390563965, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.119115114212036, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1181232929229736, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.116520643234253, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.11411714553833, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1099257469177246, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.0867831707000732, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.8535780906677246, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.670111894607544, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.5963757038116455, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.5216310024261475, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.446688413619995, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.4178466796875, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.390371322631836, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.3699440956115723, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.364132881164551, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.3743157386779785, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.3839142322540283, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.3974554538726807, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.421807289123535, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.447052478790283, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.466498851776123, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.4750914573669434, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.480404853820801, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.530402421951294, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.587921619415283, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.6132290363311768, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.676720142364502, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.7137577533721924, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.672248125076294, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.692375659942627, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.669895648956299, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.639181137084961, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.6328165531158447, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.614442825317383, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.5709245204925537, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.5102157592773438, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.6192467212677, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.6099796295166016, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.6371960639953613, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.5832948684692383, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06533776301218161, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.07013658176448874, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.0917312661498708, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.16777408637873753, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.19712070874861573, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.21650055370985605, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.23846437799926173, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.2589516426725729, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.26393503137689184, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.2705795496493171, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.2796234772978959, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.2871908453303802, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.28460686600221485, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.2833148763381321, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.2792543373938723, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.27611664820967147, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.2757475083056478, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.2709486895533407, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.27002583979328165, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.26965669988925806, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.2672572905131045, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.25802879291251385, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.2558139534883721, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.25341454411221853, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.24713916574381692, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.2511997046880768, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.24492432631967515, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.2517534145441122, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.25692137320044295, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.24880029531192321, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.24750830564784054, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.2543373938722776, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.262827611664821, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.25064599483204136, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.2589516426725729, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.24935400516795866, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.260797342192691, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.004962384259259259, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.00496410790783837, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.005179064721841408, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.005167617973985362, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.005357620930416619, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.005697083913360512, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.0058180295258270275, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.006058947935669297, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.007581727919621871, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.011913151350355117, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.02019331666869718, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.07096841935862756, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.10833632963361262, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.1303029556763152, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.1546807673739962, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.1788856188332164, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.18919294949859686, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.19491177032558346, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.2050913479319536, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.21651916620921352, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.21488571336149612, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.21616164538224347, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.21536550191432294, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.21226257538063176, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.21154737843108107, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.20656721481820783, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.21015993983644055, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.2137147276374287, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.21192568827699354, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.19677339301184885, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.19652230106010968, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.19900030049076825, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.19449166602436477, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.20151341625562078, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.19031093457302403, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.19662722487291817, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.20571414477662783, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.19770242053168477, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.19636289801519355, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.20292524195786546, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.20716832450417297, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.1873285801024762, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.18988482196398918, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.17660842296287102, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.18107366559685786, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 20, "lr_best": 0.000156, "wd_best": 0.05, "train/loss_best": 2.126219940185547, "validation/loss_best": 2.364132881164551, "validation/acc_best": 0.2871908453303802, "validation/f1_best": 0.21651916620921352} +{"epoch": 11, "train/lr": 0.00018113997589164516, "train/loss": 2.331234985589981, "train/grad": 0.16887239821255207, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.12831787109375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.12798095703125, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.127391357421875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.12678466796875, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.1261279296875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.1254248046875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.124384765625, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.12312744140625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.121270751953125, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.118468017578125, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.11332763671875, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.076932373046875, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.830782470703125, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.677200927734375, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.5810174560546875, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.4732035064697264, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.3618413734436037, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.275951805114746, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.2054236698150635, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.1513204765319824, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.095676236152649, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.045935697555542, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.9952856945991515, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.9518119120597839, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.9126365327835082, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.8685974967479706, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.8281509786844254, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.7974478161334992, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.7585631483793258, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.7226876783370972, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.6944329750537872, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.6701661711931228, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.6520283651351928, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.6506427544355393, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.6560778427124023, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.6726639515161514, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.695859454870224, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.7256638288497925, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.7561043363809585, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.801405005455017, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.840905773639679, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.8846502536535263, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.9380759346485137, "train/loss_043_lr2.2e+01_wd1.0e+00": 1.9746561300754548, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.0387808310985567, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.089704533815384, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.007656878256238997, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.007659550104290247, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.007661788493860513, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.007662216506432742, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.0076617841562256215, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.007660601485986263, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.007657884357031435, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.0076529303682036694, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.007645841161720454, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.0076419880823232235, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.007659537969157099, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.00804736408405006, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.013265990945510566, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.018715453250333667, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.021751538272947072, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.023565866332501174, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.025429070517420767, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.026552126724272967, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.02715409736149013, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.027254524705931545, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.027609250955283642, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.027468100832775236, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.027699934607371687, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.027743723802268506, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.02796907365322113, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.028669663406908512, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.029359775269404052, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.029866017550230026, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.03045785184018314, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.031060026427730918, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.031273960955441, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.03137505952268839, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.03136517870239913, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.03146445982158184, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.031622828720137476, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.03170607172884047, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.031948044588789345, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.031711130561307074, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.031000055437907577, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.03027488714084029, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.029409058513119816, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.029720312617719173, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.029344616355374456, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.02935789281502366, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.028526824014261366, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.028151519102975725, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1221532821655273, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1218655109405518, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.121377468109131, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.12088680267334, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.120366334915161, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1196110248565674, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1186885833740234, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1174840927124023, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.115501880645752, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1122097969055176, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.105400323867798, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.0415499210357666, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.7656326293945312, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.6359829902648926, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.569585084915161, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.479191541671753, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.429539442062378, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.4025611877441406, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.377727746963501, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.3592770099639893, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.3569765090942383, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.3702898025512695, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.3861911296844482, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.4084932804107666, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.434595823287964, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.4403767585754395, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.436851739883423, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.443542957305908, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.468736171722412, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.523646116256714, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.582732677459717, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.647976875305176, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.65231990814209, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.6530051231384277, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.6704888343811035, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.6679129600524902, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.661316394805908, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.7240653038024902, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.7268590927124023, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.695636510848999, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.670837879180908, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.624600648880005, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.651487112045288, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.6571552753448486, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.6294915676116943, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.638078451156616, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06404577334809892, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06976744186046512, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.11701734957548911, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.18309339239571798, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.2039497969730528, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.2233296419342931, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.2500922849760059, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.2619047619047619, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.2672572905131045, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.2757475083056478, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.2822074566260613, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.2833148763381321, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.2871908453303802, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.28811369509043927, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.2866371354743448, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.27722406792174237, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.2777777777777778, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.27593207825765964, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.27556293835363604, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.2731635289774825, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.26356589147286824, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.2572905131044666, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.25064599483204136, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.24916943521594684, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.25489110372831303, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.25230712440014763, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.25452196382428943, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.2596899224806202, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.25489110372831303, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.2602436323366556, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.24307862679955702, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.2574750830564784, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.2561830933923957, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.2543373938722776, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.25692137320044295, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.25249169435215946, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.25341454411221853, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.004962384259259259, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.004965832754227473, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.0051652360414530096, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.005359919676019152, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.006051934234449573, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.006806557075797974, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.012629781682201404, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.037857303285575294, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.08722670060645787, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.11717263375982144, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.14240591216430337, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.17294418071692394, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.19478189709386365, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.19944364118819666, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.20923407315032763, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.21669389204304754, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.2189584945300328, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.223695750391528, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.2256218095955881, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.22432320459849628, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.21762415781117952, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.2187358800123552, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.22069225316528315, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.2252389431976404, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.2297764657704692, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.22270385995349154, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.21405502087905523, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.21026721006098192, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.20600835605463638, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.21359388291021375, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.20757698483417308, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.20812469069876624, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.2042696856010834, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.19865545094149284, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.20061858419650566, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.18962556547283826, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.1947418582840679, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.19899753798349482, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.1875007480198625, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.18623764181750713, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.18523766804395192, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.18909453798445255, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 22, "lr_best": 0.00021599999999999996, "wd_best": 0.05, "train/loss_best": 1.9952856945991515, "validation/loss_best": 2.3861911296844482, "validation/acc_best": 0.28811369509043927, "validation/f1_best": 0.2256218095955881} +{"epoch": 12, "train/lr": 0.0001499999999999999, "train/loss": 2.2866510105133058, "train/grad": 0.17072421312332153, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.126492919921875, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.12617431640625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.12560302734375, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.124913330078125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.1242578125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.123375244140625, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.1222900390625, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.120863037109375, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.118563232421875, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.114873046875, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.10685791015625, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.01074951171875, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.7757528686523436, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.6380084228515623, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.537003631591797, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.4200022125244143, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.322723808288574, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.241482391357422, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.171849002838135, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.1153931713104246, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.0579104900360106, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.0073300552368165, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.951135926246643, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.9063259291648864, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.8659920072555543, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.818512989282608, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.77406045794487, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.738287314772606, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.6941127157211304, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.6566511046886445, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.6247866886854172, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.5983481323719024, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.5800869500637054, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.5749273788928986, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.5810361164808273, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.589985675215721, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.6131865590810777, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.6295467275381088, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.6701939845085143, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.7286281329393387, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.767245625257492, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.8041126346588134, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.8519599783420562, "train/loss_043_lr2.2e+01_wd1.0e+00": 1.8999653589725494, "train/loss_044_lr2.6e+01_wd1.0e+00": 1.9619161611795426, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.016802395582199, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.0076213878230191765, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.007621469242731109, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.007620570146245882, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.00761797257582657, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.007615264906780795, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.007609949235338718, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.007604330484755337, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.007596904438687488, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.007587458692723885, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.007586923144990578, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.007632508241804317, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.008864093695301563, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.015071077947504818, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.019753490071743728, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.022512173177674413, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.02441865835338831, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.026123512759804724, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.027122307447716595, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.027545043360441925, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.027631663847714663, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.027973161693662405, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.027683239690959455, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.02794602788053453, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.028005585726350545, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.02816716155037284, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.028773498088121414, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.029453828940168025, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.029795341547578572, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.03028335145674646, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.030980574041604994, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.03140663889236748, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.03163642097264528, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.03211252292618155, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.03236863262020052, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.03234505943953991, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.032165699293836954, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.03259719330817461, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.03180475456640124, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.031675837729126216, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.030562492487952113, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.02980846628546715, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0298151399102062, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.029358852943405508, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.029352121660485862, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.028266612496227025, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.02737091215327382, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.122053384780884, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.121737480163574, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1212167739868164, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.120648145675659, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.12005615234375, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1192097663879395, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1181211471557617, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1167187690734863, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.114290237426758, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.109860897064209, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.099013566970825, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.946991205215454, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.7215633392333984, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.6152071952819824, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.5410640239715576, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.4531354904174805, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.414276361465454, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.389500617980957, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.364762783050537, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.3478763103485107, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.3466172218322754, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.360914707183838, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.3718113899230957, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.3978452682495117, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.4293854236602783, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.463965654373169, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.5050339698791504, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.548403024673462, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.596768617630005, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.6688263416290283, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.7323431968688965, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.74149489402771, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.706354856491089, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.6704955101013184, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.6832165718078613, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.671097993850708, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.659264087677002, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.7164151668548584, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.7522430419921875, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.6074235439300537, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.6614437103271484, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.646164894104004, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.662249803543091, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.605717420578003, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.5804598331451416, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.539013385772705, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06404577334809892, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.07364341085271318, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.14857881136950904, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.1849390919158361, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.2115171650055371, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.23421926910299004, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.2589516426725729, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.2663344407530454, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.2702104097452935, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.28017718715393136, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.28811369509043927, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.28792912513842744, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.2888519748984865, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.29069767441860467, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.28497600590623845, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.2796234772978959, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.27445551864156514, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.2691029900332226, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.2652270210409745, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.2617201919527501, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.2497231450719823, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.24160206718346253, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.2482465854558878, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.2484311554078996, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.25083056478405313, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.2558139534883721, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.2543373938722776, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.2561830933923957, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.2558139534883721, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.2482465854558878, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.2543373938722776, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.2502768549280177, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.25507567368032485, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.2604282022886674, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.2567368032484312, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.25599852344038393, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.262827611664821, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.00496410790783837, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.005178739732164899, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.005169405160438159, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.005534167851338759, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.006451739881149938, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.014103310377809972, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.05852886978866461, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.09173249058357075, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.12507885820705142, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.15081769648334956, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.17926642443401244, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.19247488086019546, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.19648622500804466, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.20844627937526705, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.21670157574386964, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.2179368118172855, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.2214002793522142, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.22508285987218932, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.2213822150644745, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.21813832679413162, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.21316498056956631, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.2075315664802139, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.2087029666655769, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.2056346461572537, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.1950429208238981, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.18630951346909064, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.19450034671026298, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.19934365264803597, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.20342830648719404, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.2074029797800516, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.20757502173806064, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.20382858804277185, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.2031864585664739, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.19687229654028912, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.20279495039663809, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.20171435861510614, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.20720935178431601, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.2004066690374013, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.19852945894407434, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.19256482137840444, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.19141965916280754, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 22, "lr_best": 0.00021599999999999996, "wd_best": 0.05, "train/loss_best": 1.951135926246643, "validation/loss_best": 2.3718113899230957, "validation/acc_best": 0.29069767441860467, "validation/f1_best": 0.22508285987218932} +{"epoch": 13, "train/lr": 0.00011886002410835478, "train/loss": 2.245769600868225, "train/grad": 0.1684717258065939, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.123349609375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.122972412109375, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.1222705078125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.12156494140625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.12087158203125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.11988037109375, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.118524169921875, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.11695068359375, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.114412841796875, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.1097216796875, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.0977490234375, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.921611022949219, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.739682312011719, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.6124089050292967, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.504404754638672, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.3904794311523436, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.3013416290283204, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.2231718063354493, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.1554151821136474, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.0988802480697633, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.04062668800354, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.987346544265747, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.9309902858734131, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.885005202293396, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.8418144094944, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.7886941874027251, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.7419002091884612, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.7049991977214813, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.6568093079328536, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.60810359954834, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.5717073047161103, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.5391030758619308, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.5158079063892365, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.505379998087883, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.4978747546672821, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.5008859342336656, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.5173660624027252, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.5394145673513413, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.5756217956542968, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.6289343434572219, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.6699867075681687, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.6992002409696578, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.748208070397377, "train/loss_043_lr2.2e+01_wd1.0e+00": 1.7945800817012787, "train/loss_044_lr2.6e+01_wd1.0e+00": 1.8685235559940339, "train/loss_045_lr3.1e+01_wd1.0e+00": 1.932540811896324, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.007701930126640946, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.0077018885361030695, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.007700869194231927, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.007698566147591918, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.0076965350704267625, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.0076922741997987034, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.007686933446675539, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.00768067640485242, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.007673798846080899, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.007681266972795129, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.007771818526089191, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.010430653088260442, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.01623166313394904, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.020548504726029933, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.023059986140578984, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.0249158769287169, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.0264902011025697, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.027299924604594707, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.027644595773890616, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.027703023906797172, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.02798875767737627, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.027624241393059492, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.027937515135854483, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.02799432622268796, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.028140768138691784, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.02869599314406514, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.02908662337809801, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.029402125952765347, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.029874860448762773, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.03068662297911942, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.030960200233384968, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.03138269141316414, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.031961810709908604, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.032276890398934485, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.03202261976897716, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.03150062833912671, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.03146298296749592, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.03118605208583176, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.030779632553458215, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.029540610825642945, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.029120014971122144, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.028573151836171748, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.02783261033706367, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0279655434563756, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.026626550182700156, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.025794487595558167, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1217923164367676, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1214373111724854, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1208269596099854, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1201910972595215, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.119544267654419, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1185715198516846, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1173572540283203, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.115779399871826, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.112929344177246, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.107332468032837, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.0913968086242676, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.865525007247925, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.694888114929199, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.598034381866455, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.51357102394104, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.4400789737701416, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.410024404525757, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.3907229900360107, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.3704211711883545, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.3604166507720947, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.3655638694763184, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.3835723400115967, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.3950791358947754, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.4121475219726562, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.4331166744232178, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.438798427581787, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.441648244857788, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.4574854373931885, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.474719762802124, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.503356456756592, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.5619256496429443, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.559321165084839, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.573737382888794, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.5792453289031982, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.609661340713501, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.6558337211608887, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.6632354259490967, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.6488122940063477, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.7124507427215576, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.6067373752593994, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.5942623615264893, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.5797016620635986, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.545001745223999, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.5666399002075195, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.522824764251709, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.506071090698242, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06496862310815799, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06699889258028793, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06902916205241787, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.07235142118863049, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.08028792912513842, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.09634551495016612, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.16943521594684385, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.19195275009228496, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.21945367294204504, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.24086378737541528, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.26116648209671467, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.268733850129199, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.2724252491694352, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.28165374677002586, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.2866371354743448, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.2868217054263566, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.2858988556662975, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.28940568475452194, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.2862679955703212, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.2827611664820967, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.27740863787375414, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.2777777777777778, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.2781469176818014, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.2763012181616833, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.27150239940937615, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.2643041712809155, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.2643041712809155, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.27150239940937615, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.26541159099298633, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.26411960132890366, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.26596530084902176, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.26504245108896274, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.2753783684016242, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.26135105204872644, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.2648578811369509, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.26891842008121075, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.2702104097452935, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.27150239940937615, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.2678110003691399, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.268733850129199, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.26707272056109266, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.00496410790783837, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.005165567525875469, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.005357317780818393, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.005665016148512197, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.007110520415302579, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.00829068861942374, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.00903666521901778, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.010698456595798947, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.015946536092930758, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.021209232747458822, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.07044529128426678, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.09992764494515559, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.13229770524239212, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.15956648420503056, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.18476289306813576, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.19623563073535402, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.20123334982897767, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.20801740399007906, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.21614721351020846, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.21734951896193114, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.21872362779793444, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.22401127752561348, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.222226781741926, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.22028888033676272, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.21768232307365173, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.22080989601596604, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.2255613979142548, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.22378490042400226, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.22550366341584493, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.2201704704005615, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.22094454371378544, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.23201194002915423, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.22741825234607785, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.2274932843739544, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.2206288048511774, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.21614577052859016, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.22521663705342487, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.21334724970596072, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.21979921401599115, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.22070207910474546, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.21892347722540928, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.21854355712139584, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.2134380563500904, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.2165955526624788, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.21363378417847234, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 22, "lr_best": 0.00021599999999999996, "wd_best": 0.05, "train/loss_best": 1.9309902858734131, "validation/loss_best": 2.3950791358947754, "validation/acc_best": 0.28940568475452194, "validation/f1_best": 0.22401127752561348} +{"epoch": 14, "train/lr": 8.9081919031238e-05, "train/loss": 2.2166178488731383, "train/grad": 0.1702004338800907, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.123734130859375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.123294677734375, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.12265869140625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.121900634765625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.12112060546875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.12005859375, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.1187353515625, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.116978759765625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.1141015625, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.10831787109375, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.0915966796875, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.8686500549316407, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.7256446838378907, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.6023873901367187, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.484881591796875, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.3804460525512696, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.29455680847168, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.2162067604064943, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.1458372592926027, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.0891807651519776, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.0304643154144286, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.9764856433868407, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.9165187454223633, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.8677801728248595, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.8215226197242738, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.767342401742935, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.7174462956190109, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.6775616490840912, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.6233194422721864, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.573721046447754, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.5299594193696975, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.4970176994800568, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.461961988210678, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.4493026238679887, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.4414512825012207, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.4377876317501068, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.4501194232702255, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.4635397207736969, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.4942389106750489, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.5514056557416915, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.584581354856491, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.6188186818361283, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.6755802631378174, "train/loss_043_lr2.2e+01_wd1.0e+00": 1.7091520410776138, "train/loss_044_lr2.6e+01_wd1.0e+00": 1.8032774770259856, "train/loss_045_lr3.1e+01_wd1.0e+00": 1.8680065864324569, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.007736702763941139, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.007736679292283952, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.007736252245958895, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.007734514537733048, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.0077327718771994115, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.007729613680858165, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.00772562556900084, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.007720621200278401, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.007717687406111509, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.00773761970223859, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.007887378374580294, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.011783201713114977, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.017142465393990277, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.02131155487149954, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.023796379286795854, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.025565228844061493, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.027034042989835142, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.027727257208898664, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.028033442199230194, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.028084759823977946, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.028277937192469835, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.027859616028144955, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.028065178282558917, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.028053072253242134, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.028142812848091125, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.028689827648922802, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.029227971229702235, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.029553801100701094, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.03007455580867827, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0308046199940145, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.031071479823440315, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.031391080422326925, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.031790200909599664, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.03208403033204377, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.032180394576862455, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.031998154819011686, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.03203563402406871, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.03135920353233814, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.030873535610735418, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.03031195517629385, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0296784695610404, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.029450605036690832, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.028420516652986408, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.027961012683808805, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.026713620908558368, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.02576659608632326, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1216177940368652, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.121230363845825, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.120589017868042, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1199142932891846, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1192145347595215, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1182000637054443, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.116910934448242, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.115199089050293, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.112036943435669, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1053316593170166, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.08374285697937, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.823887825012207, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.6791293621063232, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.5892183780670166, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.498692750930786, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.4373555183410645, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.410879135131836, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.3917315006256104, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.3696393966674805, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.3566629886627197, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.358095407485962, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.3703348636627197, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.3775086402893066, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.400373935699463, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.4301912784576416, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.4499616622924805, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.4685463905334473, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.485883951187134, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.5100791454315186, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.5423336029052734, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.612842559814453, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.641885280609131, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.6665596961975098, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.6882078647613525, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.7478504180908203, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.7885704040527344, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.7669830322265625, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.763758897781372, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.795342206954956, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.738607406616211, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.7128448486328125, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.695496082305908, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.6122400760650635, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.631364107131958, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.6179635524749756, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.533653736114502, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06902916205241787, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.08637873754152824, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.17404946474713917, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.19619785898855666, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.22129937246216316, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.24658545588778147, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.2572905131044666, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.2672572905131045, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.2705795496493171, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.28165374677002586, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.2877445551864157, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.28183831672203763, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.29069767441860467, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.2877445551864157, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.2897748246585456, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.2781469176818014, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.27648578811369506, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.2751937984496124, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.27464008859357697, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.26947212993724623, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.2709486895533407, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.2582133628645257, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.25987449243263194, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.25452196382428943, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.25212255444813586, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.2484311554078996, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.23994093761535623, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.24529346622369877, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.2502768549280177, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.24640088593576967, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.24861572535991142, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.25655223329641935, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.25692137320044295, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.2633813215208564, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.2646733111849391, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.2561830933923957, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.26375046142488, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.00496410790783837, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.0049522154648132055, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.005167269003630184, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.005357501379024438, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.005714807852965748, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.005827726380712083, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.006397426898456277, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.011404821257405695, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.01850378281838473, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.07495629842721056, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.10386294617416682, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.13516814813846692, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.16509800604636996, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.18400686801386903, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.19704573269869022, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.20027254993638802, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.21273113930221077, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.2188806505113627, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.21562155722340626, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.22268654883468822, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.2236948684043809, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.22375993832337762, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.2161699067741629, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.21430116350511833, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.215534985656595, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.21919546484585137, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.21753897527254185, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.2215391892831348, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.21151598923660853, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.21672576393456144, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.2138269796031533, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.21277255390877992, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.21201603073819766, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.20489239745318835, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.21013960223250758, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.21526519300623695, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.2103321747492596, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.2113816596886751, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.2136463726904878, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.2103558208488058, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.21701932866613513, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.21374199900652033, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.21348355265230387, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.2185868446596252, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 21, "lr_best": 0.00018299999999999998, "wd_best": 0.05, "train/loss_best": 1.9764856433868407, "validation/loss_best": 2.3703348636627197, "validation/acc_best": 0.29069767441860467, "validation/f1_best": 0.22268654883468822} +{"epoch": 15, "train/lr": 6.196799573888289e-05, "train/loss": 2.185539370775223, "train/grad": 0.16646127395331858, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.126162109375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.1257666015625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.125040283203125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.12435791015625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.12352294921875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.122484130859375, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.121058349609375, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.119241943359375, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.11603515625, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.10953369140625, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.087879638671875, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.8446717834472657, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.713123016357422, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.591930389404297, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.4679501724243162, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.367984275817871, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.2841088485717775, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.205905294418335, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.133936605453491, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.0750722980499265, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.0173777198791503, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.9629603815078736, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.9012782716751098, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.8516909575462341, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.802929995059967, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.7458051192760466, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.6928925293684005, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.6494295173883438, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.5956870704889297, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.5416496419906616, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.4949915087223054, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.4535788506269456, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.4108632707595825, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.3907087922096253, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.3753259378671645, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.3652382570505142, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.37683140873909, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.3779819458723068, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.4020128601789474, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.458979042172432, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.4945513200759888, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.5250058484077453, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.5776299989223481, "train/loss_043_lr2.2e+01_wd1.0e+00": 1.6180119407176972, "train/loss_044_lr2.6e+01_wd1.0e+00": 1.714354109764099, "train/loss_045_lr3.1e+01_wd1.0e+00": 1.7922748392820358, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.007579407705925405, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.007579779427032918, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.007579592547845095, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.0075788291473872955, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.007577303440775722, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.007574617564678192, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.007572008878923953, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.007568312813527882, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.007567789885215461, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.007596420934423804, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.007797395668458194, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.012411987045779824, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.01729894316289574, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.021231532236561178, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.023578993417322634, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.025221408335492013, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.02661780742928386, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.027285636933520437, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.027570082442834973, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.027634153654798866, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.027879656059667468, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.027544438429176806, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.027722732005640863, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.027713207425549627, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.027831377098336815, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.028314431542530657, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.028717875173315408, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.02895459273830056, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.029475898770615457, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.030019547417759897, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.03024133582599461, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0304508007876575, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.030895881904289126, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.03090412954799831, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.03088452760130167, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.030758109819144012, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0307357045263052, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.030438930606469513, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0301380970235914, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.029572572810575366, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.029114029370248318, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.028916935678571464, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.02769642206840217, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.02759788908995688, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.025970536712557078, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.024847042616456746, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1215898990631104, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.121185779571533, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.120530605316162, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.119860887527466, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.119166851043701, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.118116855621338, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1168212890625, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.115046501159668, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1116366386413574, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.104055166244507, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.0773355960845947, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.8026134967803955, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.6702516078948975, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.582782030105591, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.4880423545837402, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.4309351444244385, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.404503345489502, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.3860256671905518, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.363619804382324, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.3514914512634277, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.3554494380950928, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.3661692142486572, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.37642502784729, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.3986778259277344, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.428501844406128, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.450338125228882, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.4809317588806152, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.5105624198913574, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.546137809753418, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.5821824073791504, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.6553661823272705, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.6819217205047607, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.704900026321411, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.722761869430542, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.785985231399536, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.820582151412964, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.826301097869873, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.8383641242980957, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.8446531295776367, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.7270917892456055, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.7108876705169678, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.676788568496704, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.642457962036133, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.692460775375366, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.6662724018096924, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.6467034816741943, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06976744186046512, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.0932078257659653, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.1758951642672573, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.20044296788482835, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.22129937246216316, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.24916943521594684, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.26135105204872644, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.26651901070505724, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.27002583979328165, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.28036175710594313, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.28645256552233295, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.284422296050203, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.2897748246585456, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.28552971576227393, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.28792912513842744, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.27611664820967147, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.2724252491694352, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.2718715393133998, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.2705795496493171, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.2643041712809155, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.26393503137689184, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.25341454411221853, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.25692137320044295, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.2541528239202658, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.2576596530084902, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.2511997046880768, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.25249169435215946, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.2530454042081949, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.25599852344038393, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.25359911406423036, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.2576596530084902, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.26596530084902176, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.2705795496493171, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.2724252491694352, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.26116648209671467, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.26245847176079734, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.2672572905131045, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.004962384259259259, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.004964970181228649, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.005164582043125153, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.005167969791408111, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.005357501379024438, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.005530916566468547, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.006309499469384974, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.011817330410939129, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.019479050491445177, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.07753602106600473, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.10823967307840954, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.13596156874100754, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.16986410173215352, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.18610963135917455, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.19511553660196704, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.20295855745044164, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.2110581901054163, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.21728679183278432, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.21796221063850227, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.22479620747709228, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.2223705205525551, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.22684742193214968, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.2164942083006157, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.21496340576292114, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.217893917723085, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.2204927234749092, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.2160381550466425, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.21973992106456786, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.20764146760578595, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.21190700810639418, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.21156157420382563, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.21832531993821988, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.20961374949829337, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.21192715341859802, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.20917786748326997, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.20909153908763697, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.21164887696914514, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.2164978045366137, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.21853822899326913, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.22200127180833373, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.21767422016840474, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.2041290275706682, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.20934755515004097, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.20736277598252664, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 21, "lr_best": 0.00018299999999999998, "wd_best": 0.05, "train/loss_best": 1.9629603815078736, "validation/loss_best": 2.3661692142486572, "validation/acc_best": 0.2897748246585456, "validation/f1_best": 0.22479620747709228} +{"epoch": 16, "train/lr": 3.870405029380728e-05, "train/loss": 2.1562468349933623, "train/grad": 0.16564900673925875, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.128212890625, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.127808837890625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.127142333984375, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.12638427734375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.12557861328125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.124415283203125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.12305908203125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.121304931640625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.11801513671875, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.110758056640625, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.08552734375, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.831157531738281, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.6977806091308594, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.575960998535156, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.451311149597168, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.3569903564453125, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.2749463653564455, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.1990038204193114, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.128491144180298, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.070510926246643, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.0117884159088133, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.9560195350646972, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.8958628487586975, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.844199035167694, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.7960115885734558, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.733978328704834, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.678662251830101, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.636098769903183, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.577658504843712, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.5204003363847733, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.4624284076690675, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.4138314753770829, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.3637173348665237, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.336558510661125, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.3139066523313523, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.3015691134333611, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.3020024800300598, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.3062538132071495, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.3273932725191115, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.360046562552452, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.3893774211406709, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.4181084531545638, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.4762579375505447, "train/loss_043_lr2.2e+01_wd1.0e+00": 1.502603207230568, "train/loss_044_lr2.6e+01_wd1.0e+00": 1.6190733802318573, "train/loss_045_lr3.1e+01_wd1.0e+00": 1.6923047119379044, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.00762143193744123, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.007622533091343939, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.007623361616861075, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.007623077454045415, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.007622275711037218, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.007620396427810192, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.007617931622080505, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.007614795672707259, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.007616404003929347, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.00765299717662856, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.007904654047451913, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.012971802768297493, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.017725913412868978, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.021683458988554775, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.024049410605803134, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.025633339481428267, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.027015462554991244, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.027669829232618213, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.027966369474306703, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.028024598844349383, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.028217593617737294, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.027807753942906858, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.027963215364143253, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.027886664746329188, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.027958163358271122, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.02845960925333202, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0289092377666384, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.029162609344348313, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.029537864103913306, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.03003751895390451, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.030211589643731714, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.030184017233550547, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.03030950440093875, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.030442533288151025, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.030277009550482036, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.030007465574890375, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.029758158382028343, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.02940978870727122, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.02924604246392846, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.02875970995053649, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.028250283943489194, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.02820022343657911, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.027133185258135198, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.027181932292878627, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.025937491627410054, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.024910004697740077, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.121490240097046, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1210973262786865, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1204233169555664, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1197195053100586, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.119004249572754, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.117933988571167, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1165621280670166, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1147096157073975, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1110963821411133, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.102823495864868, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.0723910331726074, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.790222406387329, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.6628971099853516, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.5757689476013184, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.4787497520446777, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.423892021179199, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.3980045318603516, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.379150867462158, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.3573713302612305, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.3456547260284424, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.347736358642578, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.3571839332580566, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.3646135330200195, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.3858048915863037, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.4112846851348877, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.4333455562591553, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.4617958068847656, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.490816116333008, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.531796932220459, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.577526330947876, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.6361546516418457, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.662395715713501, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.700725555419922, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.716400384902954, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.749359607696533, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.76813006401062, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.7990458011627197, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.8212523460388184, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.8556466102600098, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.749876022338867, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.753028154373169, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.6882169246673584, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.6511363983154297, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.6740753650665283, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.6305203437805176, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.577974796295166, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06552233296419344, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.07475083056478406, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.09929863418235511, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.17626430417128092, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.20136581764488742, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.22609819121447028, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.25230712440014763, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.26098191214470284, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.26947212993724623, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.2722406792174234, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.2840531561461794, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.2884828349944629, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.2833148763381321, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.29106681432262826, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.29051310446659284, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.2912513842746401, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.2836840162421558, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.2766703580657069, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.2777777777777778, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.2751937984496124, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.2663344407530454, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.2678110003691399, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.26005906238464377, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.260797342192691, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.2547065337763012, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.2541528239202658, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.2558139534883721, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.2526762643041713, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.2456626061277224, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.25249169435215946, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.2526762643041713, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.2541528239202658, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.2587670727205611, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.26153562200073827, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.2681801402731635, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.2646733111849391, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.26245847176079734, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.2709486895533407, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.004963245933900562, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.004965832754227473, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.005164907540443035, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.005358289953814911, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.005342581384978021, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.0058280298858399875, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.00825917728294718, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.014561199410124195, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.02070314531437296, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.07873417454001623, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.109036787898114, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.13967008259512162, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.17339518547698915, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.1871221533014217, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.1977829586581281, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.2029209862594584, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.21388437482966305, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.21787155173561257, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.21594922986798962, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.22386552382250033, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.22575920049510464, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.22812934304959312, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.22202711197875633, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.21848024932357782, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.22206123859662322, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.22307502485469097, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.21602464578314917, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.22188645736564683, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.21499023110383683, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.21929437952791267, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.21408126272230912, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.21519544257438025, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.21752070355468922, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.2144030207403562, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.2078161108409151, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.21311979844834192, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.21425996843113962, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.21677331000754166, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.21981136789179434, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.2223864525628412, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.22789693493557758, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.2200756574780356, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.2210318164742157, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.22687632681685366, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 23, "lr_best": 0.00025499999999999996, "wd_best": 0.05, "train/loss_best": 1.844199035167694, "validation/loss_best": 2.3858048915863037, "validation/acc_best": 0.2912513842746401, "validation/f1_best": 0.22812934304959312} +{"epoch": 17, "train/lr": 2.030750443206766e-05, "train/loss": 2.127020851969719, "train/grad": 0.16356484904885293, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.129197998046875, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.128768310546875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.128017578125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.127216796875, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.12651123046875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.125311279296875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.12380859375, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.121839599609375, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.118270263671875, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.110592041015625, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.082371826171875, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.8243467712402346, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.6967665100097657, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.5749431610107423, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.446588592529297, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.3499945831298827, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.2667434120178225, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.1882659244537352, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.117455186843872, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.058165555000305, "train/loss_020_lr5.2e-01_wd1.0e+00": 1.996798303127289, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.9410708165168762, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.8785237491130828, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.826310044527054, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.7774123752117157, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.714640076160431, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.6602737575769424, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.6137376016378402, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.550803365111351, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.487162337899208, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.4293187004327774, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.3749495834112166, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.3229286828637123, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.2924776020646096, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.2649883654713632, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.2500927209854127, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.2407004541158677, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.2374853467941285, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.2501078337430953, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.2800945001840591, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.2908761101961135, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.3232068273425102, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.3736377596855163, "train/loss_043_lr2.2e+01_wd1.0e+00": 1.3955695885419845, "train/loss_044_lr2.6e+01_wd1.0e+00": 1.5059127658605576, "train/loss_045_lr3.1e+01_wd1.0e+00": 1.5841438937187196, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.00762991547351703, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.007629683110862971, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.007628627915401012, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.00762668288545683, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.007623892854899168, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.0076196441962383685, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.007614136491902172, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.00760851422790438, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.007606990337371826, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.007645236921962351, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.007920786831527948, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.013181441067717969, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.01788369081914425, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.02181727104820311, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.024201493170112373, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.025789163568988444, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.027152241468429567, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.027753008389845492, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.027990825269371272, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.028022777158766984, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.02823794943280518, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.027811889722943305, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.027851846581324936, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.027751683155074716, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.027830631425604224, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.028228762513026594, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.028648379696533083, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.028831111323088406, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.029093129904940725, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.029516123132780195, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.029667470371350646, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.02968421349301934, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.029735479978844525, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.029651505136862398, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.02944572045467794, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.029167935783043504, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.029001606991514564, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.028649810357019304, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.028429929297417403, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.02795962552540004, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.027524292171001434, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.027451583947986365, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.026497934106737377, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.02668554020114243, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.025507490802556276, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.024689247654750942, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1214852333068848, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.121077537536621, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1204028129577637, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1197009086608887, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1189863681793213, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1178958415985107, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.11651349067688, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.114628314971924, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.110942840576172, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.102329969406128, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.069960594177246, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.785059690475464, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.6609013080596924, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.5756218433380127, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.4798145294189453, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.4282076358795166, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.4040918350219727, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.3857908248901367, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.3636388778686523, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.3522822856903076, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.3553073406219482, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.3678956031799316, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.376828908920288, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.4005844593048096, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.4273018836975098, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.451514959335327, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.4817957878112793, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.509458541870117, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.5489485263824463, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.5859200954437256, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.6512575149536133, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.68477201461792, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.7110188007354736, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.7257330417633057, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.765502691268921, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.781886100769043, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.8056013584136963, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.8401100635528564, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.8751070499420166, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.783843994140625, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.7943320274353027, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.7485511302948, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.7190282344818115, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.7527644634246826, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.659998655319214, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.619683265686035, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06626061277224068, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.07641196013289037, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.10040605389442599, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.17644887412329271, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.20155038759689922, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.22535991140642303, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.2515688445921004, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.26153562200073827, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.2678110003691399, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.2731635289774825, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.2822074566260613, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.2853451458102621, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.28313030638612036, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.29106681432262826, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.28922111480251017, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.2897748246585456, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.28036175710594313, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.2742709486895533, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.2724252491694352, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.27002583979328165, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.26541159099298633, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.2646733111849391, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.2572905131044666, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.2593207825765965, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.24473975636766335, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.25249169435215946, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.25046142488002954, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.2497231450719823, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.25046142488002954, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.2497231450719823, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.2502768549280177, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.24880029531192321, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.2528608342561831, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.2556293835363603, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.2571059431524548, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.2484311554078996, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.2558139534883721, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.26578073089701, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.00496410790783837, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.005178739732164899, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.005166579679888658, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.005357501379024438, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.005691939738207218, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.006047708774726789, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.009053949421404847, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.015251119589129905, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.02097792192885038, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.07945041348785792, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.10984094620528213, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.13907100238843687, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.1725443665898058, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.18778076759234455, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.19673138254442954, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.2032786410336838, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.21377538014346378, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.21656686966619687, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.2181643795740589, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.22708050570010338, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.22694899502136545, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.2291665233162359, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.2222016084969992, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.21875265386504983, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.21944641636025197, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.22076542537410834, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.21885709469777404, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.22297774102921009, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.21548291174145487, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.21867593124007967, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.2084995454454692, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.21671530722979945, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.21541328712705746, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.21584728200970202, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.2154766023165465, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.2125286498564195, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.21626498944720995, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.21586417333766242, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.21993409368981134, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.2221587865801209, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.2173243571538607, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.2167669919368442, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.22252351514304278, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.23053263979414362, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 21, "lr_best": 0.00018299999999999998, "wd_best": 0.05, "train/loss_best": 1.9410708165168762, "validation/loss_best": 2.3678956031799316, "validation/acc_best": 0.29106681432262826, "validation/f1_best": 0.22708050570010338} +{"epoch": 17, "train/lr": 2.030750443206766e-05, "train/loss": 2.135218620300293, "train/grad": 0.1637765435129404, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.126839599609375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.12643310546875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.125655517578125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.12495361328125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.124085693359375, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.1229638671875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.121357421875, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.1194384765625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.115928955078125, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.108125, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.0799169921875, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.8255323791503906, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.7022164916992186, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.582665481567383, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.456269607543945, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.3616039848327635, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.2800754356384276, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.202993268966675, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.1316107368469237, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.0737955522537233, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.014141855239868, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.9598461842536927, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.8960650253295899, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.842767686843872, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.7924688124656678, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.7284017622470855, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.6711570250988006, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.6245942217111589, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.5625783336162566, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.4973042339086533, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.4418547356128693, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.3888836079835891, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.3393266880512238, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.3062896770238877, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.2767091459035873, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.2586999604105948, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.2490313297510147, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.2439814281463624, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.251025723218918, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.2853198498487473, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.3059221836924553, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.3310148984193801, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.3977670788764953, "train/loss_043_lr2.2e+01_wd1.0e+00": 1.4082419931888581, "train/loss_044_lr2.6e+01_wd1.0e+00": 1.5268695145845412, "train/loss_045_lr3.1e+01_wd1.0e+00": 1.5973654156923294, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.007589323646388948, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.007589292749762535, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.007587790852412581, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.007585205088835209, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.0075827562808990475, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.007577880762983114, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.007572299675084651, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.0075656540994532406, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.007562319857534021, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.007596586069557816, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.007862212809268385, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.01309944734442979, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.017764112949371337, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.021709582512266935, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.024108227584511043, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.025717923864722252, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.027112624878063797, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.02770432036370039, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.027924954881891607, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.02800814324989915, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.028234126139432193, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.027831363826990127, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.027968446165323256, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.027885245075449348, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.027910813819617034, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.02833062189631164, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.028742272621020675, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.028862449852749706, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.029074582010507583, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.02952192407101393, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.029816718781366946, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.029821797208860516, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.03003896662965417, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.029933317275717856, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.029634067509323358, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.029377418188378215, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.029276320720091464, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.02874479121528566, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.028517649602144958, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.027852008109912275, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.027561291614547373, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.02731182347983122, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.02651224222034216, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.026468717055395247, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.025441226726397873, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.024740282138809563, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1215085983276367, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1211154460906982, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.120450019836426, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.119753122329712, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.119044065475464, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.117969036102295, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.116591215133667, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1147212982177734, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1110455989837646, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.102452516555786, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.0700736045837402, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.785409688949585, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.6611664295196533, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.575496196746826, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.479116439819336, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.4268534183502197, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.4016497135162354, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.3820557594299316, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.3583621978759766, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.345391035079956, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.3463432788848877, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.3571865558624268, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.3655428886413574, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.3876326084136963, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.411484718322754, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.435279130935669, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.4617555141448975, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.487856388092041, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.5290234088897705, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.5736773014068604, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.6367273330688477, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.671706199645996, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.6971969604492188, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.721522808074951, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.7640647888183594, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.8049707412719727, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.827925205230713, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.866905689239502, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.881920576095581, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.7830300331115723, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.7810914516448975, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.736788034439087, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.700347900390625, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.7349348068237305, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.6412227153778076, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.621485471725464, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06441491325212255, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.07419712070874862, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.09874492432631968, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.1788482834994463, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.1997046880767811, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.22572905131044665, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.25083056478405313, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.260797342192691, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.2676264304171281, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.2731635289774825, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.28552971576227393, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.28903654485049834, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.2866371354743448, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.2942045035068291, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.2918050941306755, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.29346622369878184, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.2827611664820967, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.2763012181616833, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.2763012181616833, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.27205610926541157, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.26744186046511625, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.26947212993724623, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.26098191214470284, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.2593207825765965, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.25212255444813586, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.2532299741602067, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.25396825396825395, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.24732373569582872, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.24935400516795866, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.25046142488002954, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.24916943521594684, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.2528608342561831, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.2576596530084902, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.26301218161683276, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.2631967515688446, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.2574750830564784, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.26688815060908083, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.2748246585455888, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.004962384259259259, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.004965832754227473, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.005178739732164899, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.00537351991755462, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.005342580457259356, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.005853856703079373, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.007095503325855831, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.014322609180956375, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.02052001147785436, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.08067535786131126, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.10908030114701082, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.13920363454015583, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.17103845666808795, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.18682894168100372, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.1959043930220281, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.2029076525797504, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.2165278967987473, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.2189326361982206, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.2205338411343034, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.22995049873987547, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.22823570670669777, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.23224587773064043, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.2243935836547245, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.22143627895841508, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.22404764765751262, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.22311261100816945, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.22079957777890802, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.2259131949531883, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.21906965002896397, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.21985641613319243, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.2138809454668121, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.21576525381966652, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.21649151914640116, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.21249929673336107, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.2126200984225154, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.21178670139193323, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.21273160896411625, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.21901220405110702, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.22045150904575825, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.2269078909014973, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.22268875446412448, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.21753859456057112, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.22586080850091447, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.23407791838671174, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 21, "lr_best": 0.00018299999999999998, "wd_best": 0.05, "train/loss_best": 1.9598461842536927, "validation/loss_best": 2.3571865558624268, "validation/acc_best": 0.2942045035068291, "validation/f1_best": 0.22995049873987547} +{"epoch": 18, "train/lr": 7.5829098008590064e-06, "train/loss": 2.1205772602558137, "train/grad": 0.16298397347331048, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.129027099609375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.128665771484375, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.1279443359375, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.1271435546875, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.126324462890625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.125068359375, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.123585205078125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.121658935546875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.117999267578125, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.11010009765625, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.08072021484375, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.8203564453125, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.6932374572753908, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.572151794433594, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.442434158325195, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.3471680068969727, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.2641257095336913, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.189017963409424, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.1195970439910887, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.062602205276489, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.0051495122909544, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.9490198731422423, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.8873744547367095, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.8358440923690795, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.7880267691612244, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.7251075959205628, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.666499959230423, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.6204211139678955, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.5596156096458436, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.494086481332779, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.4351469004154205, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.3858732908964158, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.3266264307498932, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.2926173478364944, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.2604201900959016, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.2383440107107162, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.2238331890106202, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.2159929859638214, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.2177039024233818, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.245253202021122, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.2641852566599845, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.2835984668135643, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.3314479410648346, "train/loss_043_lr2.2e+01_wd1.0e+00": 1.3360959637165069, "train/loss_044_lr2.6e+01_wd1.0e+00": 1.4514923417568206, "train/loss_045_lr3.1e+01_wd1.0e+00": 1.5239582055807113, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.007720177492592484, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.007719754702411592, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.00771788494894281, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.007715100152418017, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.007711985207861289, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.007706436836160719, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.007700725474860519, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.007694819517200813, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.0076933337899390605, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.007734674005769193, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.008028816597070545, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.01351686699781567, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.018225682699121535, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.022151506287045777, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.024522646465338766, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.02609170688316226, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.02745325507596135, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.027978242579847573, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.02814937327057123, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.02817865087650716, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.028341878084465862, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.027908001700416206, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.02800515295006335, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.027912118984386326, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.027945801746100188, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.028344875695183874, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.028725005341693758, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.02891445141285658, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.029155984884127975, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.029490790851414202, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.029570638248696924, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.02968393693678081, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.029639441492035984, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.02945922464132309, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.02913472866639495, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.028864817703142764, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.028834835477173328, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.028267076881602408, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.027948298109695315, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.02744890183210373, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0269814545661211, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.026724606063216926, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0257641068007797, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.025799597408622504, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.024772354792803528, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.02414666616357863, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1214942932128906, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.121086597442627, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.120391607284546, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1196963787078857, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.118995428085327, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.117875337600708, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1165082454681396, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.114621639251709, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1109049320220947, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.102184295654297, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.069060802459717, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.7832720279693604, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.6599366664886475, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.5746960639953613, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.478193759918213, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.4261698722839355, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.401379108428955, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.3825442790985107, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.359959363937378, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.3477649688720703, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.350351095199585, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.3628807067871094, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.372011184692383, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.3959736824035645, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.422799587249756, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.446706533432007, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.4746556282043457, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.499669075012207, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.5387351512908936, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.57939076423645, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.6427900791168213, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.673896312713623, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.70056414604187, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.7221436500549316, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.7654576301574707, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.790548324584961, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.815272092819214, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.8423120975494385, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.872929811477661, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.7868871688842773, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.7935404777526855, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.7575159072875977, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.7124617099761963, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.750486135482788, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.6679999828338623, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.6275060176849365, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06699889258028793, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.07641196013289037, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.10022148394241417, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.17811000369139904, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.20173495754891105, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.22462163159837578, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.25230712440014763, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.26135105204872644, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.268733850129199, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.27353266888150607, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.2836840162421558, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.2897748246585456, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.2851605758582503, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.29254337393872276, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.2901439645625692, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.29051310446659284, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.2796234772978959, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.2742709486895533, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.2753783684016242, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.2707641196013289, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.26504245108896274, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.2643041712809155, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.25858250276854927, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.2567368032484312, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.24935400516795866, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.2530454042081949, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.24916943521594684, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.24916943521594684, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.24750830564784054, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.2499077150239941, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.24750830564784054, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.2499077150239941, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.25599852344038393, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.25802879291251385, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.26301218161683276, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.2561830933923957, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.2574750830564784, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.26744186046511625, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.00496410790783837, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.005164582043125153, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.005374240418470817, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.005342625089492758, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.005684563288941517, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.006189339943224397, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.009530070442456259, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.015261572112359319, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.02132544509107859, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.08062450980978185, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.11087712421933289, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.13943354334383742, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.17210829351084111, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.18794583776719595, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.19810717663635757, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.20352236902674012, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.2146375178906129, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.2200473240082004, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.21896101002049492, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.22794874931011477, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.22724768689512742, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.22990154412458944, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.22040488238043418, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.21860977456908967, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.2223787145544942, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.2217988452979466, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.2195814447324326, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.22338718356110332, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.21867027815680107, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.22002265064617346, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.21390498131258695, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.21840774905271002, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.21632379468543847, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.21650378149810087, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.21252200597027648, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.21233338162345006, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.21304603515186996, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.21612310012583794, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.22129478938245625, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.22162896742702207, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.22355030819869307, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.2178201946638176, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.217369105277025, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.22774703331385845, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 21, "lr_best": 0.00018299999999999998, "wd_best": 0.05, "train/loss_best": 1.9490198731422423, "validation/loss_best": 2.3628807067871094, "validation/acc_best": 0.29254337393872276, "validation/f1_best": 0.22794874931011477} +{"epoch": 18, "train/lr": 7.5829098008590064e-06, "train/loss": 2.108655776977539, "train/grad": 0.16242321744561194, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.12588623046875, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.125413818359375, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.124698486328125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.123980712890625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.1231396484375, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.12198974609375, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.12046142578125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.1185546875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.114915771484375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.10701171875, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.0773785400390623, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.8155863952636717, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.690440216064453, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.569881591796875, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.4422232818603518, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.346206645965576, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.2623330307006837, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.1839315605163576, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.1126868820190428, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.056350574493408, "train/loss_020_lr5.2e-01_wd1.0e+00": 1.9954213976860047, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.9392965698242188, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.8755457246303557, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.8205274510383607, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.770333536863327, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.7084304332733153, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.652677253484726, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.604621649980545, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.5427567666769029, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.4785381656885148, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.4151569551229477, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.3662906605005265, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.3072759538888932, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.2697792756557464, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.2440370917320251, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.2229849362373353, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.2069667559862136, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.1961974167823792, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.1966094595193864, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.2227214142680167, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.2408168432116509, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.2537012127041818, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.3056218528747559, "train/loss_043_lr2.2e+01_wd1.0e+00": 1.3041372668743134, "train/loss_044_lr2.6e+01_wd1.0e+00": 1.4179600262641907, "train/loss_045_lr3.1e+01_wd1.0e+00": 1.487033554315567, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.0077160740434192125, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.007716104271821678, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.00771479340037331, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.007712043763604015, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.007709748540073633, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.007705530221574009, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.007700351655948907, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.007694134686607868, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.007692429521121084, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.0077316630654968325, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.008016122439876198, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.013368369447998702, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.01805830903351307, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.02202497563324869, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.0243868010584265, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.02595977204851806, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.027335684355348347, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.02789044258184731, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.028094488587230446, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.028122051982209087, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.02830736752599478, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.02789715473540127, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.027955999532714486, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.027849748032167554, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.027847577715292574, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.02826306805945933, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.028617313075810672, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.028733873572200537, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.02892937953583896, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.02925028887577355, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.029422306921333075, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.029425241900607944, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.029493248583748938, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.029308054512366653, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.029089976223185657, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.02871164015494287, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.028496346743777393, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.028159670708701016, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.027891872702166438, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.02741917527280748, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0268850667681545, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.02689627873711288, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.02587107026949525, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.025955417342483997, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.024932781094685198, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.02408682644367218, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1214795112609863, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1210825443267822, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.120398759841919, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1197187900543213, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.11898136138916, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1179168224334717, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1165151596069336, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1146326065063477, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.110908269882202, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1021857261657715, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.0690464973449707, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.7834644317626953, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.660050630569458, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.5744009017944336, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.4774348735809326, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.425483465194702, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.4003689289093018, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.3811395168304443, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.3578720092773438, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.345475673675537, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.3473663330078125, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.358771800994873, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.367558717727661, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.3915610313415527, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.4176478385925293, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.441804885864258, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.4700868129730225, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.4965574741363525, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.5366740226745605, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.5769989490509033, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.641899347305298, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.676251173019409, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.7027416229248047, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.7288269996643066, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.76825213432312, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.7951858043670654, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.8170204162597656, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.84127140045166, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.8756959438323975, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.781259775161743, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.7865524291992188, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.7552037239074707, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.7094552516937256, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.7515029907226562, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.661564588546753, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.632185459136963, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06533776301218161, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.0753045404208195, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.09948320413436693, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.17811000369139904, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.20155038759689922, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.2249907715023994, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.2513842746400886, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.26135105204872644, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.268733850129199, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.2724252491694352, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.2853451458102621, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.28959025470653377, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.2858988556662975, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.2929125138427464, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.29051310446659284, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.29106681432262826, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.28165374677002586, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.27556293835363604, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.2742709486895533, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.2727943890734588, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.2661498708010336, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.2663344407530454, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.2541528239202658, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.2561830933923957, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.2526762643041713, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.25249169435215946, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.25064599483204136, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.24861572535991142, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.24658545588778147, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.2528608342561831, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.24732373569582872, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.2499077150239941, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.2596899224806202, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.2619047619047619, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.26448874123292726, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.2574750830564784, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.25802879291251385, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.2663344407530454, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.004962384259259259, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.004964970181228649, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.005164582043125153, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.0053730368656557835, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.005342574268533927, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.005832976830756363, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.008120535217402325, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.014847505142896419, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.020562030037039464, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.0802424313891631, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.11073518858099861, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.1388820051566143, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.17155511987846203, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.1872662198765521, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.19747728494071368, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.20264879739758238, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.2160635400533039, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.21974200230714244, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.22026649154253686, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.22864495073619806, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.22738352768451153, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.2307989358850541, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.2237110314562645, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.22015148119651476, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.22142927623306652, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.22434019373911807, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.22168735146213248, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.22440636020701, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.21459584297350917, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.21869122286450557, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.21773781590311855, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.21713980444627104, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.2161149845207547, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.21464516920147134, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.21095247362864333, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.21442803488401116, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.21132125420148454, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.21550795706904954, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.223330679073196, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.22449972595943246, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.2231726179866794, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.21626736333585517, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.21961243440040168, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.22890210141446335, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 21, "lr_best": 0.00018299999999999998, "wd_best": 0.05, "train/loss_best": 1.9392965698242188, "validation/loss_best": 2.358771800994873, "validation/acc_best": 0.2929125138427464, "validation/f1_best": 0.22864495073619806} +{"epoch": 19, "train/lr": 1.0867618231465446e-06, "train/loss": 2.094141273498535, "train/grad": 0.1586763373762369, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.12447021484375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.124053955078125, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.12331787109375, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.1224609375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.12172607421875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.12053955078125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.1190478515625, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.117117919921875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.11343505859375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.105572509765625, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.07638427734375, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.8179640197753906, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.6883006286621094, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.563947906494141, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.4316566467285154, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.3326722717285158, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.247402744293213, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.168514986038208, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.096589345932007, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.0389488172531127, "train/loss_020_lr5.2e-01_wd1.0e+00": 1.9772327995300294, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.9191642546653747, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.8572150588035583, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.8019898855686187, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.7537979435920716, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.689483027458191, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.6329586982727051, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.585843595266342, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.5227058553695678, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.4594945085048676, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.3989613699913024, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.3486762565374375, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.2933958327770234, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.2598900228738785, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.227744408249855, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.1992324969172479, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.1890238520503045, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.1764324060082436, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.1770613810420036, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.1927619189023972, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.2078266319632531, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.220094425678253, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.2658488249778748, "train/loss_043_lr2.2e+01_wd1.0e+00": 1.2680764204263688, "train/loss_044_lr2.6e+01_wd1.0e+00": 1.3772017246484756, "train/loss_045_lr3.1e+01_wd1.0e+00": 1.4410626643896103, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.007435593632981181, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.007435143392067403, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.007433086771052331, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.0074304149835370484, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.007427362867165357, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.007422351806890219, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.007416739990003407, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.0074116989993490276, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.007411448834463954, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.00745388021459803, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.007748015983961523, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.013098968644626438, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.017659246199764313, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.021448866231366992, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.02375750879757106, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.025300061693415046, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.02662841967307031, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.027231795536354183, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.02749692913144827, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.027589536840096116, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.027798543926328422, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.02742893148213625, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.027554282499477268, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.027481659464538098, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.027475652573630212, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.027843634812161327, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0281840633880347, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.028314792970195412, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.028441158290952444, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.028754426203668117, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.02883520952425897, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.028726029749959706, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.02872466259635985, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.028620672393590212, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.02833345839753747, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.028047177623957396, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.027805123375728727, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.02745261904783547, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.02715070053935051, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.02661127470433712, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.02622603171505034, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0260435963049531, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.025027828570455313, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0250756483245641, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.02398605106398463, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.02332391167059541, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1214966773986816, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1210777759552, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1203980445861816, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.119692802429199, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1189990043640137, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1178719997406006, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1165082454681396, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.114611864089966, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1108999252319336, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1021511554718018, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.068931818008423, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.782963752746582, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.6598291397094727, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.574732542037964, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.4779694080352783, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.4262373447418213, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.401502847671509, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.3827414512634277, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.360065221786499, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.3478612899780273, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.350360155105591, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.3628089427948, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.3715951442718506, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.395162582397461, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.421477794647217, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.445061206817627, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.4727063179016113, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.497880458831787, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.53757381439209, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.578392505645752, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.6416451930999756, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.6755785942077637, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.7044472694396973, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.725738048553467, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.7695860862731934, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.7973506450653076, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.822150707244873, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.8509323596954346, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.8859853744506836, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.7954306602478027, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.805666923522949, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.7676196098327637, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.7260987758636475, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.7691233158111572, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.688103199005127, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.6451199054718018, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06699889258028793, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.07641196013289037, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.10040605389442599, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.17847914359542266, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.20173495754891105, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.22554448135843486, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.2528608342561831, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.26098191214470284, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.268733850129199, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.27353266888150607, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.284422296050203, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.29069767441860467, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.2857142857142857, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.2927279438907346, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.28940568475452194, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.290328534514581, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.2798080472499077, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.27500922849760057, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.2742709486895533, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.2724252491694352, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.2648578811369509, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.2646733111849391, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.26005906238464377, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.2572905131044666, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.24880029531192321, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.25083056478405313, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.25083056478405313, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.24916943521594684, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.24769287559985234, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.25064599483204136, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.2500922849760059, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.2517534145441122, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.2582133628645257, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.25599852344038393, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.260797342192691, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.25452196382428943, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.2552602436323367, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.2646733111849391, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.00496410790783837, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.005164582043125153, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.005374085754065246, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.005342648748585301, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.005684563288941517, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.006187759735361481, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.009460324120843739, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.015257197037602347, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.02137669053733185, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.0810346675611212, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.11091800491621372, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.13999160359935645, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.17280857078113943, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.1876076629582731, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.1981307599845864, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.2034966604308622, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.2149489704868809, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.22091233497432913, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.2195159865596478, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.22787845625681644, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.22639484354741327, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.22926509060595837, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.22017057223442704, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.2189741274923116, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.22153920955317763, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.222877299624908, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.2186564473423782, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.2225635754869236, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.2196870622890756, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.22027245375379703, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.2123244138136966, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.2158630121291031, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.21652145424913205, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.21489180518223958, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.21265477931768237, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.21256063104658063, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.2147382513708053, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.2170174909238959, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.22190389296073254, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.22034950895606806, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.2206258969657295, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.21665196316146543, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.21680982733752294, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.22614193012494765, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 21, "lr_best": 0.00018299999999999998, "wd_best": 0.05, "train/loss_best": 1.9191642546653747, "validation/loss_best": 2.3628089427948, "validation/acc_best": 0.2927279438907346, "validation/f1_best": 0.22787845625681644} +{"epoch": 19, "train/lr": 1.0867618231465446e-06, "train/loss": 2.101018395423889, "train/grad": 0.1611019141227007, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.12415283203125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.123704833984375, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.12291259765625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.122174072265625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.12124755859375, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.12002197265625, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.118448486328125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.116429443359375, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.112777099609375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.104560546875, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.074276123046875, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.8080818176269533, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.681357879638672, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.5609089660644533, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.4316870880126955, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.338236312866211, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.256482219696045, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.1805674266815185, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.1093758869171144, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.0517412757873537, "train/loss_020_lr5.2e-01_wd1.0e+00": 1.9931769227981568, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.9366612768173217, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.8748220133781432, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.8194699859619141, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.770958379507065, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.7063439989089966, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.6486791718006133, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.603264449238777, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.5400607246160507, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.4735061413049697, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.41419178545475, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.3604914909601211, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.3032799538969995, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.265057623386383, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.23170979231596, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.2097926607728005, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.1907670572400093, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.184627734720707, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.1843693035840988, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.2051783457398415, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.214005899131298, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.227890675663948, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.2797997975349427, "train/loss_043_lr2.2e+01_wd1.0e+00": 1.2745540967583657, "train/loss_044_lr2.6e+01_wd1.0e+00": 1.3836662757396698, "train/loss_045_lr3.1e+01_wd1.0e+00": 1.4588079923391342, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.007770624915137887, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.0077706408919766545, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.007769810857716948, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.00776729108998552, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.007764778765849769, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.0077606897964142265, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.007756331709679216, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.007751317955553532, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.007751948335207998, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.0077967531234025955, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.008096963700372726, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.0135611799871549, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.01824530663434416, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.022200444038026033, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.024516627555713058, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.026012182785198092, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.02732609865255654, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.027888297792524098, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.028042839765548708, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.028020930653437973, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.02820882948115468, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.027795022027567028, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.02786950534209609, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.027747848741710185, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.02776049418374896, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.028142219725996256, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.02849925742484629, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.028634562231600283, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.028839875683188437, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.029162837387993933, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.029197479002177715, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.02918934455141425, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.02922509714961052, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.029082116009667515, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.028783898865804076, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.028307392401620744, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.028135352395474912, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.027660407265648244, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.02735114749521017, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.026936506619676948, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.026398585317656396, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.026246225060895086, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.025234188297763468, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.025255616791546344, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.02422586228698492, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.023378573888912797, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.121480941772461, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.121082305908203, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.120387554168701, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1197164058685303, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.118978500366211, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.117910623550415, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.116501569747925, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1146230697631836, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.110891103744507, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1021573543548584, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.0689263343811035, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.783123016357422, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.660040855407715, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.5744478702545166, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.477509021759033, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.425490140914917, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.400552272796631, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.3814806938171387, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.3583004474639893, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.346139669418335, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.348407506942749, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.360429286956787, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.369384288787842, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.393655776977539, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.4196884632110596, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.4434902667999268, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.4714672565460205, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.4974186420440674, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.5367472171783447, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.576996326446533, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.6417081356048584, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.675051212310791, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.7019691467285156, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.727208375930786, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.767815589904785, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.7966573238372803, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.819873094558716, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.850409746170044, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.8879940509796143, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.796372175216675, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.7985739707946777, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.761443614959717, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.7191929817199707, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.765397071838379, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.6820180416107178, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.651597499847412, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06533776301218161, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.0753045404208195, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.09948320413436693, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.17847914359542266, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.20191952750092285, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.2248062015503876, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.2517534145441122, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.260797342192691, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.26854928017718716, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.27205610926541157, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.2853451458102621, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.28940568475452194, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.2877445551864157, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.29254337393872276, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.29198966408268734, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.29346622369878184, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.2807308970099668, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.2751937984496124, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.2742709486895533, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.2733480989294943, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.26596530084902176, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.2661498708010336, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.25858250276854927, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.2558139534883721, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.25064599483204136, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.2532299741602067, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.24898486526393504, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.25064599483204136, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.24713916574381692, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.25046142488002954, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.24713916574381692, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.2497231450719823, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.2571059431524548, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.26116648209671467, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.2643041712809155, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.2558139534883721, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.25655223329641935, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.26578073089701, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.004962384259259259, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.004965832754227473, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.005164582043125153, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.0053730368656557835, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.005342574268533927, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.005832134206297815, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.008120535217402325, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.014877051228329661, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.02058595871644046, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.0807661070888183, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.11102507018696567, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.13919107110032816, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.17104397878501332, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.18701528490018382, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.196945131406459, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.20252657258802284, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.21600182510796662, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.21953430151030973, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.22107161937609363, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.22744496608825782, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.22889892548872934, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.23157688718453528, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.2216738686160231, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.21962862562519447, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.22121781997972392, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.22361074492438557, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.22018666801610456, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.22397833070079423, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.21783546714430954, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.21785131126921617, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.21516886804074153, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.21740505947663155, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.21495925713676423, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.21667183071342647, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.212614995859141, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.21249895002296396, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.21153940118550915, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.21620667526250817, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.220844833752194, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.22666472573503327, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.225114617508936, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.21701537283633024, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.21821569657911621, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.22842473309400477, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 23, "lr_best": 0.00025499999999999996, "wd_best": 0.05, "train/loss_best": 1.8194699859619141, "validation/loss_best": 2.393655776977539, "validation/acc_best": 0.29346622369878184, "validation/f1_best": 0.23157688718453528} diff --git a/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__linear/config.yaml b/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__linear/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..027cdcbd23869c53edd689bc82d2b14bc67bd87f --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__linear/config.yaml @@ -0,0 +1,96 @@ +output_root: experiments/decoders/output +name_prefix: eval_probe +remote_root: null +notes: decoder ablations crossreg_reg4; eval v2 (nsd_cococlip patch linear) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +dataset_kwargs: {} +classifier_kwargs: + embed_dim: null + dropout: 0.0 + xavier_init: false + norm: false +lr_scale_grid: +- 0.02 +- 0.023 +- 0.028 +- 0.033 +- 0.038 +- 0.045 +- 0.053 +- 0.062 +- 0.074 +- 0.087 +- 0.1 +- 0.12 +- 0.14 +- 0.17 +- 0.2 +- 0.23 +- 0.27 +- 0.32 +- 0.38 +- 0.44 +- 0.52 +- 0.61 +- 0.72 +- 0.85 +- 1 +- 1.2 +- 1.4 +- 1.6 +- 1.9 +- 2.3 +- 2.7 +- 3.1 +- 3.7 +- 4.3 +- 5.1 +- 6 +- 7.1 +- 8.3 +- 9.8 +- 12 +- 14 +- 16 +- 19 +- 22 +- 26 +- 31 +- 36 +- 43 +- 50 +wd_scale_grid: +- 1.0 +num_workers: 8 +prefetch_factor: null +balanced_sampling: false +epochs: 20 +steps_per_epoch: 200 +batch_size: 64 +accum_iter: 2 +lr: 0.0003 +warmup_epochs: 5 +no_decay: false +weight_decay: 0.05 +clip_grad: 1.0 +metrics: +- acc +- f1 +cv_metric: acc +early_stopping: true +amp: true +device: cuda +seed: 4466 +debug: false +wandb: false +wandb_entity: null +wandb_project: fMRI-fm-eval +name: decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__linear +model: flat_mae +representation: patch +classifier: linear +dataset: nsd_cococlip +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__linear +remote_dir: null diff --git a/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__linear/eval_log.json b/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__linear/eval_log.json new file mode 100644 index 0000000000000000000000000000000000000000..1d39c065945eabd08f75c41bf861c633fb036df3 --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__linear/eval_log.json @@ -0,0 +1 @@ +{"eval/epoch": 19, "eval/id_best": 48, "eval/lr_best": 0.015, "eval/wd_best": 0.05, "eval/train/loss": 2.9368033409118652, "eval/train/acc": 0.1474538246411998, "eval/train/acc_std": 0.0016629482942817637, "eval/train/f1": 0.0835960790218555, "eval/train/f1_std": 0.001239356394606369, "eval/validation/loss": 2.9848053455352783, "eval/validation/acc": 0.13104466592838687, "eval/validation/acc_std": 0.003778276646400821, "eval/validation/f1": 0.06727705151638409, "eval/validation/f1_std": 0.002614965500049542, "eval/test/loss": 2.971991539001465, "eval/test/acc": 0.13376623376623376, "eval/test/acc_std": 0.003625051504902462, "eval/test/f1": 0.06209723653306998, "eval/test/f1_std": 0.002335943515625102, "eval/testid/loss": 2.9969723224639893, "eval/testid/acc": 0.12473491420859842, "eval/testid/acc_std": 0.004053599965125619, "eval/testid/f1": 0.06967685953978074, "eval/testid/f1_std": 0.0029145074722420217} diff --git a/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__linear/eval_log_best.json b/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__linear/eval_log_best.json new file mode 100644 index 0000000000000000000000000000000000000000..f24ab0113c9f83e16e7ce0d2bba76811d7c490c9 --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__linear/eval_log_best.json @@ -0,0 +1 @@ +{"eval/best/epoch": 19, "eval/best/id_best": 48, "eval/best/lr_best": 0.015, "eval/best/wd_best": 0.05, "eval/best/train/loss": 2.9368033409118652, "eval/best/train/acc": 0.1474538246411998, "eval/best/train/acc_std": 0.0016629482942817637, "eval/best/train/f1": 0.0835960790218555, "eval/best/train/f1_std": 0.001239356394606369, "eval/best/validation/loss": 2.9848053455352783, "eval/best/validation/acc": 0.13104466592838687, "eval/best/validation/acc_std": 0.003778276646400821, "eval/best/validation/f1": 0.06727705151638409, "eval/best/validation/f1_std": 0.002614965500049542, "eval/best/test/loss": 2.971991539001465, "eval/best/test/acc": 0.13376623376623376, "eval/best/test/acc_std": 0.003625051504902462, "eval/best/test/f1": 0.06209723653306998, "eval/best/test/f1_std": 0.002335943515625102, "eval/best/testid/loss": 2.9969723224639893, "eval/best/testid/acc": 0.12473491420859842, "eval/best/testid/acc_std": 0.004053599965125619, "eval/best/testid/f1": 0.06967685953978074, "eval/best/testid/f1_std": 0.0029145074722420217} diff --git a/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__linear/eval_log_last.json b/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__linear/eval_log_last.json new file mode 100644 index 0000000000000000000000000000000000000000..93f25766bd16b9d5ab19bc1f3ffc937c1f0c5af6 --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__linear/eval_log_last.json @@ -0,0 +1 @@ +{"eval/last/epoch": 19, "eval/last/id_best": 48, "eval/last/lr_best": 0.015, "eval/last/wd_best": 0.05, "eval/last/train/loss": 2.9368033409118652, "eval/last/train/acc": 0.1474538246411998, "eval/last/train/acc_std": 0.0016629482942817637, "eval/last/train/f1": 0.0835960790218555, "eval/last/train/f1_std": 0.001239356394606369, "eval/last/validation/loss": 2.9848053455352783, "eval/last/validation/acc": 0.13104466592838687, "eval/last/validation/acc_std": 0.003778276646400821, "eval/last/validation/f1": 0.06727705151638409, "eval/last/validation/f1_std": 0.002614965500049542, "eval/last/test/loss": 2.971991539001465, "eval/last/test/acc": 0.13376623376623376, "eval/last/test/acc_std": 0.003625051504902462, "eval/last/test/f1": 0.06209723653306998, "eval/last/test/f1_std": 0.002335943515625102, "eval/last/testid/loss": 2.9969723224639893, "eval/last/testid/acc": 0.12473491420859842, "eval/last/testid/acc_std": 0.004053599965125619, "eval/last/testid/f1": 0.06967685953978074, "eval/last/testid/f1_std": 0.0029145074722420217} diff --git a/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__linear/eval_table.csv b/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__linear/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..eef24e75c97cb8d9d9149dabc28299678c1970af --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__linear/eval_table.csv @@ -0,0 +1,5 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,patch,linear,nsd_cococlip,best,19,0.015,0.05,48,"[50, 1.0]",train,2.9368033409118652,0.1474538246411998,0.0016629482942817637,0.0835960790218555,0.001239356394606369 +flat_mae,patch,linear,nsd_cococlip,best,19,0.015,0.05,48,"[50, 1.0]",validation,2.9848053455352783,0.13104466592838687,0.003778276646400821,0.06727705151638409,0.002614965500049542 +flat_mae,patch,linear,nsd_cococlip,best,19,0.015,0.05,48,"[50, 1.0]",test,2.971991539001465,0.13376623376623376,0.003625051504902462,0.06209723653306998,0.002335943515625102 +flat_mae,patch,linear,nsd_cococlip,best,19,0.015,0.05,48,"[50, 1.0]",testid,2.9969723224639893,0.12473491420859842,0.004053599965125619,0.06967685953978074,0.0029145074722420217 diff --git a/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__linear/eval_table_best.csv b/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__linear/eval_table_best.csv new file mode 100644 index 0000000000000000000000000000000000000000..eef24e75c97cb8d9d9149dabc28299678c1970af --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__linear/eval_table_best.csv @@ -0,0 +1,5 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,patch,linear,nsd_cococlip,best,19,0.015,0.05,48,"[50, 1.0]",train,2.9368033409118652,0.1474538246411998,0.0016629482942817637,0.0835960790218555,0.001239356394606369 +flat_mae,patch,linear,nsd_cococlip,best,19,0.015,0.05,48,"[50, 1.0]",validation,2.9848053455352783,0.13104466592838687,0.003778276646400821,0.06727705151638409,0.002614965500049542 +flat_mae,patch,linear,nsd_cococlip,best,19,0.015,0.05,48,"[50, 1.0]",test,2.971991539001465,0.13376623376623376,0.003625051504902462,0.06209723653306998,0.002335943515625102 +flat_mae,patch,linear,nsd_cococlip,best,19,0.015,0.05,48,"[50, 1.0]",testid,2.9969723224639893,0.12473491420859842,0.004053599965125619,0.06967685953978074,0.0029145074722420217 diff --git a/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__linear/eval_table_last.csv b/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__linear/eval_table_last.csv new file mode 100644 index 0000000000000000000000000000000000000000..edecf70fa4e76cf9c03def6b8a9bf2782f344c5a --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__linear/eval_table_last.csv @@ -0,0 +1,5 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,patch,linear,nsd_cococlip,last,19,0.015,0.05,48,"[50, 1.0]",train,2.9368033409118652,0.1474538246411998,0.0016629482942817637,0.0835960790218555,0.001239356394606369 +flat_mae,patch,linear,nsd_cococlip,last,19,0.015,0.05,48,"[50, 1.0]",validation,2.9848053455352783,0.13104466592838687,0.003778276646400821,0.06727705151638409,0.002614965500049542 +flat_mae,patch,linear,nsd_cococlip,last,19,0.015,0.05,48,"[50, 1.0]",test,2.971991539001465,0.13376623376623376,0.003625051504902462,0.06209723653306998,0.002335943515625102 +flat_mae,patch,linear,nsd_cococlip,last,19,0.015,0.05,48,"[50, 1.0]",testid,2.9969723224639893,0.12473491420859842,0.004053599965125619,0.06967685953978074,0.0029145074722420217 diff --git a/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__linear/log.txt b/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__linear/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..ad719296020e2fbfe815d2e00c901a386743822b --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__linear/log.txt @@ -0,0 +1,959 @@ +fMRI foundation model probe eval +version: 0.1.dev66+g7ddd3aa04 +sha: aef99c83a386cf95c3d8ca503ecc968d8d5694af, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-03-07 23:05:01 +config: +output_root: experiments/decoders/output +name_prefix: eval_probe +remote_root: null +notes: decoder ablations crossreg_reg4; eval v2 (nsd_cococlip patch linear) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +dataset_kwargs: {} +classifier_kwargs: + embed_dim: null + dropout: 0.0 + xavier_init: false + norm: false +lr_scale_grid: +- 0.02 +- 0.023 +- 0.028 +- 0.033 +- 0.038 +- 0.045 +- 0.053 +- 0.062 +- 0.074 +- 0.087 +- 0.1 +- 0.12 +- 0.14 +- 0.17 +- 0.2 +- 0.23 +- 0.27 +- 0.32 +- 0.38 +- 0.44 +- 0.52 +- 0.61 +- 0.72 +- 0.85 +- 1 +- 1.2 +- 1.4 +- 1.6 +- 1.9 +- 2.3 +- 2.7 +- 3.1 +- 3.7 +- 4.3 +- 5.1 +- 6 +- 7.1 +- 8.3 +- 9.8 +- 12 +- 14 +- 16 +- 19 +- 22 +- 26 +- 31 +- 36 +- 43 +- 50 +wd_scale_grid: +- 1.0 +num_workers: 8 +prefetch_factor: null +balanced_sampling: false +epochs: 20 +steps_per_epoch: 200 +batch_size: 64 +accum_iter: 2 +lr: 0.0003 +warmup_epochs: 5 +no_decay: false +weight_decay: 0.05 +clip_grad: 1.0 +metrics: +- acc +- f1 +cv_metric: acc +early_stopping: true +amp: true +device: cuda +seed: 4466 +debug: false +wandb: false +wandb_entity: null +wandb_project: fMRI-fm-eval +name: decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__linear +model: flat_mae +representation: patch +classifier: linear +dataset: nsd_cococlip +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__linear +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=False, reg_tokens=4, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: nsd_cococlip (flat) +train (n=32539): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'run', 'trial_id', 'nsd_id', 'category_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 32539 +}), + labels=[ 3 4 5 6 10 11 17 18 19 20 22 23 25 30 31 33 36 37 38 53 55 59 61 74], + counts=[1286 1180 1639 1868 834 824 1026 1042 913 1853 1503 2092 1001 1410 + 794 1241 1904 1872 2267 1428 889 904 1447 1322] +) + +validation (n=5418): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'run', 'trial_id', 'nsd_id', 'category_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 5418 +}), + labels=[ 3 4 5 6 10 11 17 18 19 20 22 23 25 30 31 33 36 37 38 53 55 59 61 74], + counts=[197 161 276 345 126 142 143 185 112 295 285 387 169 250 159 193 316 334 + 343 215 172 141 226 246] +) + +test (n=5390): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'run', 'trial_id', 'nsd_id', 'category_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 5390 +}), + labels=[ 3 4 5 6 10 11 17 18 19 20 22 23 25 30 31 33 36 37 38 53 55 59 61 74], + counts=[202 172 274 298 144 180 134 182 186 293 218 343 165 185 140 177 346 333 + 345 271 165 140 251 246] +) + +testid (n=5187): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'run', 'trial_id', 'nsd_id', 'category_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 5187 +}), + labels=[ 3 4 5 6 10 11 17 18 19 20 22 23 25 30 31 33 36 37 38 53 55 59 61 74], + counts=[197 159 267 273 123 153 175 184 139 310 215 386 153 230 118 192 330 306 + 349 223 143 127 249 186] +) + +running backbone on example batch to get embedding dim +embedding feature dim (patch): 768 +initializing sweep of classifier heads +classifiers: +ModuleList( + (0-48): 49 x LinearClassifier( + (linear): Linear(in_features=768, out_features=24, bias=True) + ) +) +classifier params (train): 0.9M (0.9M) +setting up optimizer +total batch size: 128 = 64 bs per gpu x 2 accum +lr: 3.00e-04 +full schedule: epochs = 20 (steps = 4000) (decay = True) +warmup: epochs = 5 (steps = 1000) +start training for 20 epochs +train: [0] [ 0/400] eta: 0:23:16 lr: nan time: 3.4902 data: 3.1299 max mem: 3915 +train: [0] [ 20/400] eta: 0:03:20 lr: 0.000003 loss: 3.1729 (3.1787) grad: 0.0646 (0.0672) time: 0.3805 data: 0.0055 max mem: 3957 +train: [0] [ 40/400] eta: 0:02:35 lr: 0.000006 loss: 3.1729 (3.1782) grad: 0.0640 (0.0653) time: 0.3316 data: 0.0036 max mem: 3957 +train: [0] [ 60/400] eta: 0:02:22 lr: 0.000009 loss: 3.1732 (3.1760) grad: 0.0623 (0.0651) time: 0.3887 data: 0.0053 max mem: 3957 +train: [0] [ 80/400] eta: 0:02:06 lr: 0.000012 loss: 3.1740 (3.1746) grad: 0.0665 (0.0658) time: 0.3281 data: 0.0040 max mem: 3957 +train: [0] [100/400] eta: 0:01:54 lr: 0.000015 loss: 3.1692 (3.1738) grad: 0.0665 (0.0660) time: 0.3306 data: 0.0040 max mem: 3957 +train: [0] [120/400] eta: 0:01:45 lr: 0.000018 loss: 3.1685 (3.1732) grad: 0.0650 (0.0658) time: 0.3494 data: 0.0037 max mem: 3957 +train: [0] [140/400] eta: 0:01:36 lr: 0.000021 loss: 3.1629 (3.1720) grad: 0.0651 (0.0658) time: 0.3467 data: 0.0039 max mem: 3957 +train: [0] [160/400] eta: 0:01:28 lr: 0.000024 loss: 3.1592 (3.1705) grad: 0.0673 (0.0660) time: 0.3261 data: 0.0036 max mem: 3957 +train: [0] [180/400] eta: 0:01:19 lr: 0.000027 loss: 3.1589 (3.1685) grad: 0.0648 (0.0656) time: 0.3321 data: 0.0045 max mem: 3957 +train: [0] [200/400] eta: 0:01:12 lr: 0.000030 loss: 3.1561 (3.1671) grad: 0.0582 (0.0651) time: 0.3421 data: 0.0041 max mem: 3957 +train: [0] [220/400] eta: 0:01:04 lr: 0.000033 loss: 3.1485 (3.1650) grad: 0.0599 (0.0650) time: 0.3353 data: 0.0040 max mem: 3957 +train: [0] [240/400] eta: 0:00:57 lr: 0.000036 loss: 3.1419 (3.1635) grad: 0.0599 (0.0648) time: 0.3278 data: 0.0038 max mem: 3957 +train: [0] [260/400] eta: 0:00:49 lr: 0.000039 loss: 3.1478 (3.1624) grad: 0.0620 (0.0648) time: 0.3319 data: 0.0042 max mem: 3957 +train: [0] [280/400] eta: 0:00:42 lr: 0.000042 loss: 3.1478 (3.1614) grad: 0.0633 (0.0649) time: 0.3346 data: 0.0038 max mem: 3957 +train: [0] [300/400] eta: 0:00:35 lr: 0.000045 loss: 3.1432 (3.1603) grad: 0.0635 (0.0648) time: 0.3107 data: 0.0039 max mem: 3957 +train: [0] [320/400] eta: 0:00:28 lr: 0.000048 loss: 3.1357 (3.1593) grad: 0.0648 (0.0648) time: 0.3528 data: 0.0037 max mem: 3957 +train: [0] [340/400] eta: 0:00:21 lr: 0.000051 loss: 3.1417 (3.1589) grad: 0.0623 (0.0645) time: 0.3489 data: 0.0039 max mem: 3957 +train: [0] [360/400] eta: 0:00:13 lr: 0.000054 loss: 3.1482 (3.1585) grad: 0.0611 (0.0643) time: 0.3303 data: 0.0043 max mem: 3957 +train: [0] [380/400] eta: 0:00:06 lr: 0.000057 loss: 3.1565 (3.1586) grad: 0.0636 (0.0645) time: 0.3247 data: 0.0038 max mem: 3957 +train: [0] [399/400] eta: 0:00:00 lr: 0.000060 loss: 3.1507 (3.1581) grad: 0.0653 (0.0646) time: 0.3390 data: 0.0048 max mem: 3957 +train: [0] Total time: 0:02:19 (0.3477 s / it) +train: [0] Summary: lr: 0.000060 loss: 3.1507 (3.1581) grad: 0.0653 (0.0646) +eval (validation): [0] [ 0/85] eta: 0:04:43 time: 3.3359 data: 3.1267 max mem: 3957 +eval (validation): [0] [20/85] eta: 0:00:30 time: 0.3193 data: 0.0041 max mem: 3957 +eval (validation): [0] [40/85] eta: 0:00:19 time: 0.3831 data: 0.0047 max mem: 3957 +eval (validation): [0] [60/85] eta: 0:00:10 time: 0.3580 data: 0.0048 max mem: 3957 +eval (validation): [0] [80/85] eta: 0:00:01 time: 0.3196 data: 0.0042 max mem: 3957 +eval (validation): [0] [84/85] eta: 0:00:00 time: 0.3036 data: 0.0041 max mem: 3957 +eval (validation): [0] Total time: 0:00:32 (0.3820 s / it) +cv: [0] best hparam: (31, 1.0) (045) ('045_lr3.1e+01_wd1.0e+00') loss: 3.120 acc: 0.092 f1: 0.022 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__linear/checkpoint-best.pth +train: [1] [ 0/400] eta: 0:23:54 lr: nan time: 3.5857 data: 3.3350 max mem: 3957 +train: [1] [ 20/400] eta: 0:03:20 lr: 0.000063 loss: 3.1558 (3.1550) grad: 0.0582 (0.0604) time: 0.3737 data: 0.0217 max mem: 3957 +train: [1] [ 40/400] eta: 0:02:41 lr: 0.000066 loss: 3.1518 (3.1521) grad: 0.0584 (0.0597) time: 0.3692 data: 0.0065 max mem: 3957 +train: [1] [ 60/400] eta: 0:02:21 lr: 0.000069 loss: 3.1439 (3.1455) grad: 0.0597 (0.0605) time: 0.3498 data: 0.0043 max mem: 3957 +train: [1] [ 80/400] eta: 0:02:08 lr: 0.000072 loss: 3.1392 (3.1456) grad: 0.0584 (0.0600) time: 0.3541 data: 0.0040 max mem: 3957 +train: [1] [100/400] eta: 0:01:57 lr: 0.000075 loss: 3.1470 (3.1445) grad: 0.0559 (0.0599) time: 0.3547 data: 0.0045 max mem: 3957 +train: [1] [120/400] eta: 0:01:47 lr: 0.000078 loss: 3.1470 (3.1452) grad: 0.0586 (0.0603) time: 0.3507 data: 0.0038 max mem: 3957 +train: [1] [140/400] eta: 0:01:38 lr: 0.000081 loss: 3.1457 (3.1461) grad: 0.0586 (0.0606) time: 0.3511 data: 0.0045 max mem: 3957 +train: [1] [160/400] eta: 0:01:30 lr: 0.000084 loss: 3.1453 (3.1471) grad: 0.0611 (0.0609) time: 0.3461 data: 0.0039 max mem: 3957 +train: [1] [180/400] eta: 0:01:22 lr: 0.000087 loss: 3.1458 (3.1472) grad: 0.0644 (0.0613) time: 0.3530 data: 0.0042 max mem: 3957 +train: [1] [200/400] eta: 0:01:13 lr: 0.000090 loss: 3.1373 (3.1463) grad: 0.0647 (0.0613) time: 0.3368 data: 0.0042 max mem: 3957 +train: [1] [220/400] eta: 0:01:06 lr: 0.000093 loss: 3.1352 (3.1460) grad: 0.0626 (0.0615) time: 0.3485 data: 0.0043 max mem: 3957 +train: [1] [240/400] eta: 0:00:58 lr: 0.000096 loss: 3.1352 (3.1449) grad: 0.0636 (0.0617) time: 0.3448 data: 0.0042 max mem: 3957 +train: [1] [260/400] eta: 0:00:51 lr: 0.000099 loss: 3.1447 (3.1450) grad: 0.0621 (0.0617) time: 0.3680 data: 0.0045 max mem: 3957 +train: [1] [280/400] eta: 0:00:43 lr: 0.000102 loss: 3.1401 (3.1433) grad: 0.0608 (0.0618) time: 0.3406 data: 0.0039 max mem: 3957 +train: [1] [300/400] eta: 0:00:36 lr: 0.000105 loss: 3.1375 (3.1445) grad: 0.0608 (0.0618) time: 0.3288 data: 0.0038 max mem: 3957 +train: [1] [320/400] eta: 0:00:28 lr: 0.000108 loss: 3.1539 (3.1442) grad: 0.0589 (0.0618) time: 0.3683 data: 0.0042 max mem: 3957 +train: [1] [340/400] eta: 0:00:21 lr: 0.000111 loss: 3.1496 (3.1445) grad: 0.0589 (0.0616) time: 0.3478 data: 0.0041 max mem: 3957 +train: [1] [360/400] eta: 0:00:14 lr: 0.000114 loss: 3.1361 (3.1438) grad: 0.0613 (0.0617) time: 0.3493 data: 0.0038 max mem: 3957 +train: [1] [380/400] eta: 0:00:07 lr: 0.000117 loss: 3.1369 (3.1439) grad: 0.0608 (0.0615) time: 0.3418 data: 0.0043 max mem: 3957 +train: [1] [399/400] eta: 0:00:00 lr: 0.000120 loss: 3.1390 (3.1433) grad: 0.0573 (0.0612) time: 0.3380 data: 0.0045 max mem: 3957 +train: [1] Total time: 0:02:23 (0.3592 s / it) +train: [1] Summary: lr: 0.000120 loss: 3.1390 (3.1433) grad: 0.0573 (0.0612) +eval (validation): [1] [ 0/85] eta: 0:04:27 time: 3.1486 data: 2.8861 max mem: 3957 +eval (validation): [1] [20/85] eta: 0:00:34 time: 0.4025 data: 0.0178 max mem: 3957 +eval (validation): [1] [40/85] eta: 0:00:20 time: 0.3591 data: 0.0042 max mem: 3957 +eval (validation): [1] [60/85] eta: 0:00:10 time: 0.3326 data: 0.0049 max mem: 3957 +eval (validation): [1] [80/85] eta: 0:00:01 time: 0.3376 data: 0.0043 max mem: 3957 +eval (validation): [1] [84/85] eta: 0:00:00 time: 0.3271 data: 0.0044 max mem: 3957 +eval (validation): [1] Total time: 0:00:33 (0.3916 s / it) +cv: [1] best hparam: (31, 1.0) (045) ('045_lr3.1e+01_wd1.0e+00') loss: 3.101 acc: 0.083 f1: 0.023 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__linear/checkpoint-last.pth +train: [2] [ 0/400] eta: 0:23:51 lr: nan time: 3.5799 data: 3.3131 max mem: 3957 +train: [2] [ 20/400] eta: 0:03:17 lr: 0.000123 loss: 3.1129 (3.1191) grad: 0.0592 (0.0608) time: 0.3661 data: 0.0050 max mem: 3957 +train: [2] [ 40/400] eta: 0:02:36 lr: 0.000126 loss: 3.1354 (3.1304) grad: 0.0603 (0.0630) time: 0.3481 data: 0.0037 max mem: 3957 +train: [2] [ 60/400] eta: 0:02:18 lr: 0.000129 loss: 3.1449 (3.1349) grad: 0.0623 (0.0630) time: 0.3507 data: 0.0044 max mem: 3957 +train: [2] [ 80/400] eta: 0:02:05 lr: 0.000132 loss: 3.1388 (3.1366) grad: 0.0609 (0.0624) time: 0.3411 data: 0.0040 max mem: 3957 +train: [2] [100/400] eta: 0:01:54 lr: 0.000135 loss: 3.1385 (3.1370) grad: 0.0587 (0.0617) time: 0.3443 data: 0.0041 max mem: 3957 +train: [2] [120/400] eta: 0:01:44 lr: 0.000138 loss: 3.1343 (3.1346) grad: 0.0600 (0.0617) time: 0.3382 data: 0.0038 max mem: 3957 +train: [2] [140/400] eta: 0:01:36 lr: 0.000141 loss: 3.1222 (3.1335) grad: 0.0598 (0.0617) time: 0.3511 data: 0.0041 max mem: 3957 +train: [2] [160/400] eta: 0:01:28 lr: 0.000144 loss: 3.1231 (3.1341) grad: 0.0594 (0.0612) time: 0.3387 data: 0.0043 max mem: 3957 +train: [2] [180/400] eta: 0:01:20 lr: 0.000147 loss: 3.1258 (3.1350) grad: 0.0568 (0.0611) time: 0.3469 data: 0.0040 max mem: 3957 +train: [2] [200/400] eta: 0:01:12 lr: 0.000150 loss: 3.1456 (3.1357) grad: 0.0601 (0.0613) time: 0.3479 data: 0.0044 max mem: 3957 +train: [2] [220/400] eta: 0:01:05 lr: 0.000153 loss: 3.1455 (3.1350) grad: 0.0624 (0.0615) time: 0.3502 data: 0.0044 max mem: 3957 +train: [2] [240/400] eta: 0:00:57 lr: 0.000156 loss: 3.1382 (3.1348) grad: 0.0602 (0.0612) time: 0.3658 data: 0.0044 max mem: 3957 +train: [2] [260/400] eta: 0:00:50 lr: 0.000159 loss: 3.1382 (3.1358) grad: 0.0605 (0.0611) time: 0.3606 data: 0.0042 max mem: 3957 +train: [2] [280/400] eta: 0:00:43 lr: 0.000162 loss: 3.1267 (3.1347) grad: 0.0590 (0.0610) time: 0.3358 data: 0.0043 max mem: 3957 +train: [2] [300/400] eta: 0:00:35 lr: 0.000165 loss: 3.1278 (3.1352) grad: 0.0573 (0.0608) time: 0.3339 data: 0.0037 max mem: 3957 +train: [2] [320/400] eta: 0:00:28 lr: 0.000168 loss: 3.1342 (3.1348) grad: 0.0580 (0.0608) time: 0.3617 data: 0.0044 max mem: 3957 +train: [2] [340/400] eta: 0:00:21 lr: 0.000171 loss: 3.1142 (3.1338) grad: 0.0582 (0.0608) time: 0.3458 data: 0.0042 max mem: 3957 +train: [2] [360/400] eta: 0:00:14 lr: 0.000174 loss: 3.1142 (3.1327) grad: 0.0605 (0.0610) time: 0.3465 data: 0.0043 max mem: 3957 +train: [2] [380/400] eta: 0:00:07 lr: 0.000177 loss: 3.1182 (3.1328) grad: 0.0605 (0.0609) time: 0.3574 data: 0.0040 max mem: 3957 +train: [2] [399/400] eta: 0:00:00 lr: 0.000180 loss: 3.1329 (3.1328) grad: 0.0575 (0.0608) time: 0.3441 data: 0.0041 max mem: 3957 +train: [2] Total time: 0:02:22 (0.3571 s / it) +train: [2] Summary: lr: 0.000180 loss: 3.1329 (3.1328) grad: 0.0575 (0.0608) +eval (validation): [2] [ 0/85] eta: 0:04:39 time: 3.2904 data: 3.0599 max mem: 3957 +eval (validation): [2] [20/85] eta: 0:00:34 time: 0.3865 data: 0.0054 max mem: 3957 +eval (validation): [2] [40/85] eta: 0:00:19 time: 0.3548 data: 0.0045 max mem: 3957 +eval (validation): [2] [60/85] eta: 0:00:10 time: 0.3311 data: 0.0038 max mem: 3957 +eval (validation): [2] [80/85] eta: 0:00:01 time: 0.3318 data: 0.0045 max mem: 3957 +eval (validation): [2] [84/85] eta: 0:00:00 time: 0.3285 data: 0.0043 max mem: 3957 +eval (validation): [2] Total time: 0:00:32 (0.3870 s / it) +cv: [2] best hparam: (26, 1.0) (044) ('044_lr2.6e+01_wd1.0e+00') loss: 3.116 acc: 0.086 f1: 0.032 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__linear/checkpoint-last.pth +train: [3] [ 0/400] eta: 0:22:41 lr: nan time: 3.4032 data: 3.1672 max mem: 3957 +train: [3] [ 20/400] eta: 0:03:09 lr: 0.000183 loss: 3.1223 (3.1407) grad: 0.0598 (0.0625) time: 0.3536 data: 0.0050 max mem: 3957 +train: [3] [ 40/400] eta: 0:02:34 lr: 0.000186 loss: 3.1376 (3.1410) grad: 0.0605 (0.0626) time: 0.3547 data: 0.0036 max mem: 3957 +train: [3] [ 60/400] eta: 0:02:15 lr: 0.000189 loss: 3.1345 (3.1352) grad: 0.0583 (0.0612) time: 0.3379 data: 0.0043 max mem: 3957 +train: [3] [ 80/400] eta: 0:02:04 lr: 0.000192 loss: 3.1397 (3.1388) grad: 0.0583 (0.0611) time: 0.3537 data: 0.0043 max mem: 3957 +train: [3] [100/400] eta: 0:01:53 lr: 0.000195 loss: 3.1272 (3.1337) grad: 0.0601 (0.0615) time: 0.3464 data: 0.0040 max mem: 3957 +train: [3] [120/400] eta: 0:01:45 lr: 0.000198 loss: 3.1260 (3.1326) grad: 0.0598 (0.0615) time: 0.3554 data: 0.0038 max mem: 3957 +train: [3] [140/400] eta: 0:01:36 lr: 0.000201 loss: 3.1206 (3.1302) grad: 0.0582 (0.0609) time: 0.3577 data: 0.0040 max mem: 3957 +train: [3] [160/400] eta: 0:01:29 lr: 0.000204 loss: 3.1137 (3.1290) grad: 0.0579 (0.0611) time: 0.3615 data: 0.0039 max mem: 3957 +train: [3] [180/400] eta: 0:01:21 lr: 0.000207 loss: 3.1215 (3.1286) grad: 0.0578 (0.0607) time: 0.3534 data: 0.0042 max mem: 3957 +train: [3] [200/400] eta: 0:01:13 lr: 0.000210 loss: 3.1149 (3.1262) grad: 0.0578 (0.0607) time: 0.3436 data: 0.0039 max mem: 3957 +train: [3] [220/400] eta: 0:01:05 lr: 0.000213 loss: 3.1099 (3.1250) grad: 0.0586 (0.0605) time: 0.3526 data: 0.0039 max mem: 3957 +train: [3] [240/400] eta: 0:00:58 lr: 0.000216 loss: 3.1044 (3.1241) grad: 0.0575 (0.0606) time: 0.3573 data: 0.0042 max mem: 3957 +train: [3] [260/400] eta: 0:00:51 lr: 0.000219 loss: 3.0979 (3.1229) grad: 0.0598 (0.0604) time: 0.3563 data: 0.0045 max mem: 3957 +train: [3] [280/400] eta: 0:00:43 lr: 0.000222 loss: 3.1240 (3.1238) grad: 0.0598 (0.0606) time: 0.3311 data: 0.0037 max mem: 3957 +train: [3] [300/400] eta: 0:00:36 lr: 0.000225 loss: 3.1346 (3.1242) grad: 0.0623 (0.0606) time: 0.3336 data: 0.0038 max mem: 3957 +train: [3] [320/400] eta: 0:00:28 lr: 0.000228 loss: 3.1296 (3.1253) grad: 0.0615 (0.0607) time: 0.3718 data: 0.0043 max mem: 3957 +train: [3] [340/400] eta: 0:00:21 lr: 0.000231 loss: 3.1274 (3.1253) grad: 0.0603 (0.0606) time: 0.3612 data: 0.0044 max mem: 3957 +train: [3] [360/400] eta: 0:00:14 lr: 0.000234 loss: 3.1274 (3.1255) grad: 0.0593 (0.0606) time: 0.3551 data: 0.0040 max mem: 3957 +train: [3] [380/400] eta: 0:00:07 lr: 0.000237 loss: 3.1237 (3.1254) grad: 0.0620 (0.0606) time: 0.3456 data: 0.0040 max mem: 3957 +train: [3] [399/400] eta: 0:00:00 lr: 0.000240 loss: 3.1237 (3.1254) grad: 0.0621 (0.0608) time: 0.3479 data: 0.0035 max mem: 3957 +train: [3] Total time: 0:02:23 (0.3595 s / it) +train: [3] Summary: lr: 0.000240 loss: 3.1237 (3.1254) grad: 0.0621 (0.0608) +eval (validation): [3] [ 0/85] eta: 0:05:56 time: 4.1918 data: 3.9598 max mem: 3957 +eval (validation): [3] [20/85] eta: 0:00:34 time: 0.3544 data: 0.0133 max mem: 3957 +eval (validation): [3] [40/85] eta: 0:00:20 time: 0.3892 data: 0.0046 max mem: 3957 +eval (validation): [3] [60/85] eta: 0:00:10 time: 0.3321 data: 0.0039 max mem: 3957 +eval (validation): [3] [80/85] eta: 0:00:01 time: 0.3329 data: 0.0045 max mem: 3957 +eval (validation): [3] [84/85] eta: 0:00:00 time: 0.3206 data: 0.0044 max mem: 3957 +eval (validation): [3] Total time: 0:00:33 (0.3999 s / it) +cv: [3] best hparam: (26, 1.0) (044) ('044_lr2.6e+01_wd1.0e+00') loss: 3.074 acc: 0.090 f1: 0.037 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__linear/checkpoint-last.pth +train: [4] [ 0/400] eta: 0:23:41 lr: nan time: 3.5528 data: 3.2804 max mem: 3957 +train: [4] [ 20/400] eta: 0:03:11 lr: 0.000243 loss: 3.1282 (3.1254) grad: 0.0582 (0.0628) time: 0.3512 data: 0.0049 max mem: 3957 +train: [4] [ 40/400] eta: 0:02:34 lr: 0.000246 loss: 3.1261 (3.1245) grad: 0.0573 (0.0602) time: 0.3519 data: 0.0055 max mem: 3957 +train: [4] [ 60/400] eta: 0:02:17 lr: 0.000249 loss: 3.1133 (3.1191) grad: 0.0562 (0.0599) time: 0.3501 data: 0.0037 max mem: 3957 +train: [4] [ 80/400] eta: 0:02:06 lr: 0.000252 loss: 3.1097 (3.1203) grad: 0.0602 (0.0613) time: 0.3650 data: 0.0038 max mem: 3957 +train: [4] [100/400] eta: 0:01:56 lr: 0.000255 loss: 3.1268 (3.1234) grad: 0.0632 (0.0620) time: 0.3587 data: 0.0041 max mem: 3957 +train: [4] [120/400] eta: 0:01:46 lr: 0.000258 loss: 3.1419 (3.1252) grad: 0.0609 (0.0623) time: 0.3560 data: 0.0043 max mem: 3957 +train: [4] [140/400] eta: 0:01:38 lr: 0.000261 loss: 3.1218 (3.1254) grad: 0.0597 (0.0621) time: 0.3610 data: 0.0039 max mem: 3957 +train: [4] [160/400] eta: 0:01:30 lr: 0.000264 loss: 3.1205 (3.1265) grad: 0.0607 (0.0625) time: 0.3549 data: 0.0040 max mem: 3957 +train: [4] [180/400] eta: 0:01:22 lr: 0.000267 loss: 3.1071 (3.1251) grad: 0.0629 (0.0627) time: 0.3681 data: 0.0037 max mem: 3957 +train: [4] [200/400] eta: 0:01:14 lr: 0.000270 loss: 3.1129 (3.1247) grad: 0.0607 (0.0623) time: 0.3568 data: 0.0040 max mem: 3957 +train: [4] [220/400] eta: 0:01:06 lr: 0.000273 loss: 3.1131 (3.1241) grad: 0.0597 (0.0620) time: 0.3528 data: 0.0040 max mem: 3957 +train: [4] [240/400] eta: 0:00:59 lr: 0.000276 loss: 3.1131 (3.1251) grad: 0.0599 (0.0617) time: 0.3470 data: 0.0044 max mem: 3957 +train: [4] [260/400] eta: 0:00:51 lr: 0.000279 loss: 3.1425 (3.1258) grad: 0.0568 (0.0618) time: 0.3407 data: 0.0039 max mem: 3957 +train: [4] [280/400] eta: 0:00:43 lr: 0.000282 loss: 3.1191 (3.1249) grad: 0.0575 (0.0615) time: 0.3493 data: 0.0041 max mem: 3957 +train: [4] [300/400] eta: 0:00:36 lr: 0.000285 loss: 3.1047 (3.1240) grad: 0.0598 (0.0615) time: 0.3186 data: 0.0038 max mem: 3957 +train: [4] [320/400] eta: 0:00:28 lr: 0.000288 loss: 3.1051 (3.1232) grad: 0.0609 (0.0615) time: 0.3571 data: 0.0041 max mem: 3957 +train: [4] [340/400] eta: 0:00:21 lr: 0.000291 loss: 3.1159 (3.1225) grad: 0.0623 (0.0616) time: 0.3589 data: 0.0040 max mem: 3957 +train: [4] [360/400] eta: 0:00:14 lr: 0.000294 loss: 3.1158 (3.1220) grad: 0.0616 (0.0614) time: 0.3362 data: 0.0042 max mem: 3957 +train: [4] [380/400] eta: 0:00:07 lr: 0.000297 loss: 3.0995 (3.1208) grad: 0.0560 (0.0611) time: 0.3408 data: 0.0042 max mem: 3957 +train: [4] [399/400] eta: 0:00:00 lr: 0.000300 loss: 3.1074 (3.1209) grad: 0.0609 (0.0612) time: 0.3352 data: 0.0042 max mem: 3957 +train: [4] Total time: 0:02:23 (0.3588 s / it) +train: [4] Summary: lr: 0.000300 loss: 3.1074 (3.1209) grad: 0.0609 (0.0612) +eval (validation): [4] [ 0/85] eta: 0:04:40 time: 3.3048 data: 3.0852 max mem: 3957 +eval (validation): [4] [20/85] eta: 0:00:32 time: 0.3535 data: 0.0154 max mem: 3957 +eval (validation): [4] [40/85] eta: 0:00:18 time: 0.3443 data: 0.0047 max mem: 3957 +eval (validation): [4] [60/85] eta: 0:00:09 time: 0.3315 data: 0.0043 max mem: 3957 +eval (validation): [4] [80/85] eta: 0:00:01 time: 0.3131 data: 0.0042 max mem: 3957 +eval (validation): [4] [84/85] eta: 0:00:00 time: 0.3065 data: 0.0039 max mem: 3957 +eval (validation): [4] Total time: 0:00:31 (0.3726 s / it) +cv: [4] best hparam: (36, 1.0) (046) ('046_lr3.6e+01_wd1.0e+00') loss: 3.100 acc: 0.108 f1: 0.050 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__linear/checkpoint-best.pth +train: [5] [ 0/400] eta: 0:22:32 lr: nan time: 3.3825 data: 3.1051 max mem: 3957 +train: [5] [ 20/400] eta: 0:03:24 lr: 0.000300 loss: 3.1213 (3.1236) grad: 0.0598 (0.0609) time: 0.3948 data: 0.0038 max mem: 3957 +train: [5] [ 40/400] eta: 0:02:43 lr: 0.000300 loss: 3.1169 (3.1127) grad: 0.0590 (0.0609) time: 0.3657 data: 0.0045 max mem: 3957 +train: [5] [ 60/400] eta: 0:02:22 lr: 0.000300 loss: 3.1031 (3.1185) grad: 0.0572 (0.0590) time: 0.3527 data: 0.0045 max mem: 3957 +train: [5] [ 80/400] eta: 0:02:11 lr: 0.000300 loss: 3.1173 (3.1156) grad: 0.0564 (0.0593) time: 0.3789 data: 0.0042 max mem: 3957 +train: [5] [100/400] eta: 0:02:00 lr: 0.000300 loss: 3.1092 (3.1149) grad: 0.0619 (0.0605) time: 0.3733 data: 0.0044 max mem: 3957 +train: [5] [120/400] eta: 0:01:51 lr: 0.000300 loss: 3.0955 (3.1131) grad: 0.0640 (0.0611) time: 0.3673 data: 0.0043 max mem: 3957 +train: [5] [140/400] eta: 0:01:42 lr: 0.000300 loss: 3.1106 (3.1148) grad: 0.0637 (0.0612) time: 0.3727 data: 0.0045 max mem: 3957 +train: [5] [160/400] eta: 0:01:33 lr: 0.000299 loss: 3.1287 (3.1159) grad: 0.0630 (0.0610) time: 0.3677 data: 0.0044 max mem: 3957 +train: [5] [180/400] eta: 0:01:25 lr: 0.000299 loss: 3.1176 (3.1152) grad: 0.0594 (0.0613) time: 0.3749 data: 0.0046 max mem: 3957 +train: [5] [200/400] eta: 0:01:17 lr: 0.000299 loss: 3.0875 (3.1119) grad: 0.0603 (0.0610) time: 0.3610 data: 0.0046 max mem: 3957 +train: [5] [220/400] eta: 0:01:09 lr: 0.000299 loss: 3.0828 (3.1105) grad: 0.0594 (0.0608) time: 0.3741 data: 0.0044 max mem: 3957 +train: [5] [240/400] eta: 0:01:01 lr: 0.000299 loss: 3.1159 (3.1122) grad: 0.0572 (0.0603) time: 0.3791 data: 0.0044 max mem: 3957 +train: [5] [260/400] eta: 0:00:53 lr: 0.000299 loss: 3.1159 (3.1132) grad: 0.0589 (0.0603) time: 0.3541 data: 0.0043 max mem: 3957 +train: [5] [280/400] eta: 0:00:45 lr: 0.000298 loss: 3.1131 (3.1146) grad: 0.0586 (0.0601) time: 0.3555 data: 0.0044 max mem: 3957 +train: [5] [300/400] eta: 0:00:37 lr: 0.000298 loss: 3.1255 (3.1146) grad: 0.0585 (0.0603) time: 0.3383 data: 0.0040 max mem: 3957 +train: [5] [320/400] eta: 0:00:30 lr: 0.000298 loss: 3.1220 (3.1152) grad: 0.0583 (0.0601) time: 0.3894 data: 0.0044 max mem: 3957 +train: [5] [340/400] eta: 0:00:22 lr: 0.000298 loss: 3.1100 (3.1147) grad: 0.0554 (0.0600) time: 0.3665 data: 0.0044 max mem: 3957 +train: [5] [360/400] eta: 0:00:15 lr: 0.000297 loss: 3.1207 (3.1163) grad: 0.0579 (0.0599) time: 0.3582 data: 0.0041 max mem: 3957 +train: [5] [380/400] eta: 0:00:07 lr: 0.000297 loss: 3.1362 (3.1165) grad: 0.0595 (0.0600) time: 0.3547 data: 0.0045 max mem: 3957 +train: [5] [399/400] eta: 0:00:00 lr: 0.000297 loss: 3.1173 (3.1167) grad: 0.0597 (0.0600) time: 0.3433 data: 0.0039 max mem: 3957 +train: [5] Total time: 0:02:29 (0.3740 s / it) +train: [5] Summary: lr: 0.000297 loss: 3.1173 (3.1167) grad: 0.0597 (0.0600) +eval (validation): [5] [ 0/85] eta: 0:04:51 time: 3.4321 data: 3.2140 max mem: 3957 +eval (validation): [5] [20/85] eta: 0:00:33 time: 0.3731 data: 0.0186 max mem: 3957 +eval (validation): [5] [40/85] eta: 0:00:19 time: 0.3636 data: 0.0041 max mem: 3957 +eval (validation): [5] [60/85] eta: 0:00:10 time: 0.3499 data: 0.0043 max mem: 3957 +eval (validation): [5] [80/85] eta: 0:00:01 time: 0.3234 data: 0.0042 max mem: 3957 +eval (validation): [5] [84/85] eta: 0:00:00 time: 0.3163 data: 0.0042 max mem: 3957 +eval (validation): [5] Total time: 0:00:33 (0.3915 s / it) +cv: [5] best hparam: (19, 1.0) (042) ('042_lr1.9e+01_wd1.0e+00') loss: 3.080 acc: 0.107 f1: 0.046 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__linear/checkpoint-last.pth +train: [6] [ 0/400] eta: 0:23:01 lr: nan time: 3.4532 data: 3.2059 max mem: 3957 +train: [6] [ 20/400] eta: 0:03:27 lr: 0.000296 loss: 3.0903 (3.0971) grad: 0.0603 (0.0611) time: 0.4014 data: 0.0284 max mem: 3957 +train: [6] [ 40/400] eta: 0:02:44 lr: 0.000296 loss: 3.0959 (3.0967) grad: 0.0608 (0.0617) time: 0.3636 data: 0.0038 max mem: 3957 +train: [6] [ 60/400] eta: 0:02:22 lr: 0.000296 loss: 3.1045 (3.1001) grad: 0.0623 (0.0617) time: 0.3450 data: 0.0044 max mem: 3957 +train: [6] [ 80/400] eta: 0:02:10 lr: 0.000295 loss: 3.1045 (3.1015) grad: 0.0588 (0.0612) time: 0.3728 data: 0.0046 max mem: 3957 +train: [6] [100/400] eta: 0:02:01 lr: 0.000295 loss: 3.1087 (3.1031) grad: 0.0596 (0.0612) time: 0.3900 data: 0.0046 max mem: 3957 +train: [6] [120/400] eta: 0:01:51 lr: 0.000295 loss: 3.0999 (3.1017) grad: 0.0596 (0.0604) time: 0.3618 data: 0.0045 max mem: 3957 +train: [6] [140/400] eta: 0:01:41 lr: 0.000294 loss: 3.0832 (3.0997) grad: 0.0580 (0.0605) time: 0.3548 data: 0.0045 max mem: 3957 +train: [6] [160/400] eta: 0:01:33 lr: 0.000294 loss: 3.1029 (3.0997) grad: 0.0629 (0.0609) time: 0.3650 data: 0.0039 max mem: 3957 +train: [6] [180/400] eta: 0:01:24 lr: 0.000293 loss: 3.1032 (3.1000) grad: 0.0616 (0.0612) time: 0.3590 data: 0.0044 max mem: 3957 +train: [6] [200/400] eta: 0:01:16 lr: 0.000293 loss: 3.0908 (3.1015) grad: 0.0599 (0.0607) time: 0.3509 data: 0.0044 max mem: 3957 +train: [6] [220/400] eta: 0:01:08 lr: 0.000292 loss: 3.1046 (3.1030) grad: 0.0563 (0.0604) time: 0.3593 data: 0.0040 max mem: 3957 +train: [6] [240/400] eta: 0:01:00 lr: 0.000292 loss: 3.1130 (3.1031) grad: 0.0596 (0.0604) time: 0.3604 data: 0.0042 max mem: 3957 +train: [6] [260/400] eta: 0:00:52 lr: 0.000291 loss: 3.1109 (3.1033) grad: 0.0620 (0.0607) time: 0.3607 data: 0.0043 max mem: 3957 +train: [6] [280/400] eta: 0:00:44 lr: 0.000291 loss: 3.0984 (3.1041) grad: 0.0617 (0.0605) time: 0.3441 data: 0.0043 max mem: 3957 +train: [6] [300/400] eta: 0:00:37 lr: 0.000290 loss: 3.0984 (3.1036) grad: 0.0581 (0.0605) time: 0.3416 data: 0.0042 max mem: 3957 +train: [6] [320/400] eta: 0:00:29 lr: 0.000290 loss: 3.0893 (3.1026) grad: 0.0564 (0.0605) time: 0.3808 data: 0.0044 max mem: 3957 +train: [6] [340/400] eta: 0:00:22 lr: 0.000289 loss: 3.1034 (3.1043) grad: 0.0628 (0.0606) time: 0.3581 data: 0.0041 max mem: 3957 +train: [6] [360/400] eta: 0:00:14 lr: 0.000288 loss: 3.1144 (3.1037) grad: 0.0590 (0.0605) time: 0.3876 data: 0.0041 max mem: 3957 +train: [6] [380/400] eta: 0:00:07 lr: 0.000288 loss: 3.1030 (3.1045) grad: 0.0590 (0.0606) time: 0.3534 data: 0.0043 max mem: 3957 +train: [6] [399/400] eta: 0:00:00 lr: 0.000287 loss: 3.1048 (3.1042) grad: 0.0573 (0.0604) time: 0.3559 data: 0.0040 max mem: 3957 +train: [6] Total time: 0:02:28 (0.3714 s / it) +train: [6] Summary: lr: 0.000287 loss: 3.1048 (3.1042) grad: 0.0573 (0.0604) +eval (validation): [6] [ 0/85] eta: 0:04:48 time: 3.3960 data: 3.1078 max mem: 3957 +eval (validation): [6] [20/85] eta: 0:00:33 time: 0.3707 data: 0.0121 max mem: 3957 +eval (validation): [6] [40/85] eta: 0:00:19 time: 0.3607 data: 0.0128 max mem: 3957 +eval (validation): [6] [60/85] eta: 0:00:10 time: 0.3464 data: 0.0210 max mem: 3957 +eval (validation): [6] [80/85] eta: 0:00:01 time: 0.3462 data: 0.0035 max mem: 3957 +eval (validation): [6] [84/85] eta: 0:00:00 time: 0.3404 data: 0.0022 max mem: 3957 +eval (validation): [6] Total time: 0:00:33 (0.3940 s / it) +cv: [6] best hparam: (31, 1.0) (045) ('045_lr3.1e+01_wd1.0e+00') loss: 3.055 acc: 0.113 f1: 0.052 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__linear/checkpoint-best.pth +train: [7] [ 0/400] eta: 0:24:05 lr: nan time: 3.6149 data: 3.3080 max mem: 3957 +train: [7] [ 20/400] eta: 0:03:24 lr: 0.000286 loss: 3.0997 (3.0941) grad: 0.0504 (0.0542) time: 0.3846 data: 0.0053 max mem: 3957 +train: [7] [ 40/400] eta: 0:02:44 lr: 0.000286 loss: 3.1079 (3.0972) grad: 0.0560 (0.0575) time: 0.3696 data: 0.0043 max mem: 3957 +train: [7] [ 60/400] eta: 0:02:23 lr: 0.000285 loss: 3.0840 (3.0958) grad: 0.0596 (0.0582) time: 0.3490 data: 0.0040 max mem: 3957 +train: [7] [ 80/400] eta: 0:02:10 lr: 0.000284 loss: 3.0838 (3.0935) grad: 0.0592 (0.0583) time: 0.3698 data: 0.0042 max mem: 3957 +train: [7] [100/400] eta: 0:01:59 lr: 0.000284 loss: 3.0963 (3.0977) grad: 0.0561 (0.0581) time: 0.3656 data: 0.0043 max mem: 3957 +train: [7] [120/400] eta: 0:01:50 lr: 0.000283 loss: 3.0868 (3.0953) grad: 0.0588 (0.0591) time: 0.3593 data: 0.0043 max mem: 3957 +train: [7] [140/400] eta: 0:01:40 lr: 0.000282 loss: 3.0866 (3.0959) grad: 0.0606 (0.0593) time: 0.3507 data: 0.0039 max mem: 3957 +train: [7] [160/400] eta: 0:01:32 lr: 0.000282 loss: 3.0921 (3.0950) grad: 0.0620 (0.0596) time: 0.3579 data: 0.0042 max mem: 3957 +train: [7] [180/400] eta: 0:01:23 lr: 0.000281 loss: 3.0914 (3.0947) grad: 0.0627 (0.0598) time: 0.3628 data: 0.0043 max mem: 3957 +train: [7] [200/400] eta: 0:01:15 lr: 0.000280 loss: 3.1038 (3.0965) grad: 0.0594 (0.0599) time: 0.3606 data: 0.0038 max mem: 3957 +train: [7] [220/400] eta: 0:01:07 lr: 0.000279 loss: 3.1082 (3.0981) grad: 0.0598 (0.0599) time: 0.3605 data: 0.0039 max mem: 3957 +train: [7] [240/400] eta: 0:01:00 lr: 0.000278 loss: 3.1047 (3.0991) grad: 0.0598 (0.0599) time: 0.3705 data: 0.0044 max mem: 3957 +train: [7] [260/400] eta: 0:00:52 lr: 0.000278 loss: 3.1045 (3.0986) grad: 0.0590 (0.0598) time: 0.3770 data: 0.0041 max mem: 3957 +train: [7] [280/400] eta: 0:00:44 lr: 0.000277 loss: 3.0955 (3.0973) grad: 0.0580 (0.0599) time: 0.3472 data: 0.0041 max mem: 3957 +train: [7] [300/400] eta: 0:00:37 lr: 0.000276 loss: 3.0977 (3.0969) grad: 0.0574 (0.0601) time: 0.3589 data: 0.0042 max mem: 3957 +train: [7] [320/400] eta: 0:00:29 lr: 0.000275 loss: 3.1011 (3.0980) grad: 0.0616 (0.0601) time: 0.3718 data: 0.0042 max mem: 3957 +train: [7] [340/400] eta: 0:00:22 lr: 0.000274 loss: 3.1061 (3.0986) grad: 0.0605 (0.0600) time: 0.3717 data: 0.0042 max mem: 3957 +train: [7] [360/400] eta: 0:00:14 lr: 0.000273 loss: 3.1156 (3.1001) grad: 0.0583 (0.0602) time: 0.3698 data: 0.0042 max mem: 3957 +train: [7] [380/400] eta: 0:00:07 lr: 0.000272 loss: 3.1160 (3.1005) grad: 0.0598 (0.0603) time: 0.3630 data: 0.0043 max mem: 3957 +train: [7] [399/400] eta: 0:00:00 lr: 0.000271 loss: 3.1160 (3.1017) grad: 0.0631 (0.0604) time: 0.3651 data: 0.0042 max mem: 3957 +train: [7] Total time: 0:02:29 (0.3727 s / it) +train: [7] Summary: lr: 0.000271 loss: 3.1160 (3.1017) grad: 0.0631 (0.0604) +eval (validation): [7] [ 0/85] eta: 0:04:58 time: 3.5144 data: 3.2262 max mem: 3957 +eval (validation): [7] [20/85] eta: 0:00:33 time: 0.3669 data: 0.0139 max mem: 3957 +eval (validation): [7] [40/85] eta: 0:00:19 time: 0.3656 data: 0.0043 max mem: 3957 +eval (validation): [7] [60/85] eta: 0:00:10 time: 0.3337 data: 0.0036 max mem: 3957 +eval (validation): [7] [80/85] eta: 0:00:01 time: 0.3736 data: 0.0044 max mem: 3957 +eval (validation): [7] [84/85] eta: 0:00:00 time: 0.3725 data: 0.0043 max mem: 3957 +eval (validation): [7] Total time: 0:00:33 (0.3995 s / it) +cv: [7] best hparam: (26, 1.0) (044) ('044_lr2.6e+01_wd1.0e+00') loss: 3.086 acc: 0.106 f1: 0.046 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__linear/checkpoint-last.pth +train: [8] [ 0/400] eta: 0:24:26 lr: nan time: 3.6655 data: 3.3557 max mem: 3957 +train: [8] [ 20/400] eta: 0:03:20 lr: 0.000270 loss: 3.0702 (3.0859) grad: 0.0600 (0.0641) time: 0.3713 data: 0.0055 max mem: 3957 +train: [8] [ 40/400] eta: 0:02:43 lr: 0.000270 loss: 3.0702 (3.0799) grad: 0.0590 (0.0600) time: 0.3746 data: 0.0042 max mem: 3957 +train: [8] [ 60/400] eta: 0:02:22 lr: 0.000269 loss: 3.0833 (3.0896) grad: 0.0560 (0.0590) time: 0.3521 data: 0.0041 max mem: 3957 +train: [8] [ 80/400] eta: 0:02:11 lr: 0.000268 loss: 3.1035 (3.0931) grad: 0.0575 (0.0589) time: 0.3847 data: 0.0045 max mem: 3957 +train: [8] [100/400] eta: 0:02:01 lr: 0.000267 loss: 3.0943 (3.0948) grad: 0.0628 (0.0603) time: 0.3743 data: 0.0042 max mem: 3957 +train: [8] [120/400] eta: 0:01:51 lr: 0.000266 loss: 3.1033 (3.0955) grad: 0.0628 (0.0603) time: 0.3702 data: 0.0041 max mem: 3957 +train: [8] [140/400] eta: 0:01:42 lr: 0.000265 loss: 3.0874 (3.0940) grad: 0.0599 (0.0604) time: 0.3645 data: 0.0041 max mem: 3957 +train: [8] [160/400] eta: 0:01:33 lr: 0.000264 loss: 3.0810 (3.0945) grad: 0.0575 (0.0601) time: 0.3718 data: 0.0043 max mem: 3957 +train: [8] [180/400] eta: 0:01:25 lr: 0.000263 loss: 3.0765 (3.0931) grad: 0.0586 (0.0600) time: 0.3765 data: 0.0041 max mem: 3957 +train: [8] [200/400] eta: 0:01:17 lr: 0.000262 loss: 3.1053 (3.0953) grad: 0.0612 (0.0602) time: 0.3531 data: 0.0041 max mem: 3957 +train: [8] [220/400] eta: 0:01:09 lr: 0.000260 loss: 3.1108 (3.0948) grad: 0.0618 (0.0603) time: 0.3736 data: 0.0043 max mem: 3957 +train: [8] [240/400] eta: 0:01:01 lr: 0.000259 loss: 3.1068 (3.0953) grad: 0.0584 (0.0600) time: 0.3824 data: 0.0044 max mem: 3957 +train: [8] [260/400] eta: 0:00:53 lr: 0.000258 loss: 3.1068 (3.0960) grad: 0.0565 (0.0598) time: 0.3676 data: 0.0046 max mem: 3957 +train: [8] [280/400] eta: 0:00:45 lr: 0.000257 loss: 3.0950 (3.0956) grad: 0.0566 (0.0598) time: 0.3462 data: 0.0037 max mem: 3957 +train: [8] [300/400] eta: 0:00:37 lr: 0.000256 loss: 3.0889 (3.0948) grad: 0.0575 (0.0596) time: 0.3718 data: 0.0040 max mem: 3957 +train: [8] [320/400] eta: 0:00:30 lr: 0.000255 loss: 3.0891 (3.0950) grad: 0.0575 (0.0595) time: 0.3612 data: 0.0041 max mem: 3957 +train: [8] [340/400] eta: 0:00:22 lr: 0.000254 loss: 3.0924 (3.0946) grad: 0.0567 (0.0593) time: 0.3921 data: 0.0043 max mem: 3957 +train: [8] [360/400] eta: 0:00:15 lr: 0.000253 loss: 3.0942 (3.0950) grad: 0.0580 (0.0593) time: 0.3732 data: 0.0040 max mem: 3957 +train: [8] [380/400] eta: 0:00:07 lr: 0.000252 loss: 3.0996 (3.0950) grad: 0.0607 (0.0594) time: 0.3613 data: 0.0043 max mem: 3957 +train: [8] [399/400] eta: 0:00:00 lr: 0.000250 loss: 3.1055 (3.0959) grad: 0.0608 (0.0594) time: 0.3604 data: 0.0044 max mem: 3957 +train: [8] Total time: 0:02:31 (0.3777 s / it) +train: [8] Summary: lr: 0.000250 loss: 3.1055 (3.0959) grad: 0.0608 (0.0594) +eval (validation): [8] [ 0/85] eta: 0:04:55 time: 3.4809 data: 3.2053 max mem: 3957 +eval (validation): [8] [20/85] eta: 0:00:34 time: 0.3856 data: 0.0058 max mem: 3957 +eval (validation): [8] [40/85] eta: 0:00:20 time: 0.3663 data: 0.0043 max mem: 3957 +eval (validation): [8] [60/85] eta: 0:00:10 time: 0.3590 data: 0.0043 max mem: 3957 +eval (validation): [8] [80/85] eta: 0:00:02 time: 0.3603 data: 0.0045 max mem: 3957 +eval (validation): [8] [84/85] eta: 0:00:00 time: 0.3554 data: 0.0044 max mem: 3957 +eval (validation): [8] Total time: 0:00:34 (0.4068 s / it) +cv: [8] best hparam: (36, 1.0) (046) ('046_lr3.6e+01_wd1.0e+00') loss: 3.027 acc: 0.122 f1: 0.055 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__linear/checkpoint-best.pth +train: [9] [ 0/400] eta: 0:25:08 lr: nan time: 3.7713 data: 3.4532 max mem: 3957 +train: [9] [ 20/400] eta: 0:03:42 lr: 0.000249 loss: 3.0791 (3.0803) grad: 0.0552 (0.0558) time: 0.4274 data: 0.0225 max mem: 3957 +train: [9] [ 40/400] eta: 0:02:54 lr: 0.000248 loss: 3.0847 (3.0891) grad: 0.0552 (0.0584) time: 0.3776 data: 0.0044 max mem: 3957 +train: [9] [ 60/400] eta: 0:02:30 lr: 0.000247 loss: 3.1096 (3.0964) grad: 0.0569 (0.0586) time: 0.3535 data: 0.0043 max mem: 3957 +train: [9] [ 80/400] eta: 0:02:17 lr: 0.000246 loss: 3.1096 (3.0996) grad: 0.0579 (0.0583) time: 0.3872 data: 0.0043 max mem: 3957 +train: [9] [100/400] eta: 0:02:05 lr: 0.000244 loss: 3.1114 (3.1018) grad: 0.0601 (0.0586) time: 0.3778 data: 0.0042 max mem: 3957 +train: [9] [120/400] eta: 0:01:55 lr: 0.000243 loss: 3.0931 (3.0954) grad: 0.0581 (0.0589) time: 0.3759 data: 0.0043 max mem: 3957 +train: [9] [140/400] eta: 0:01:45 lr: 0.000242 loss: 3.0848 (3.0951) grad: 0.0583 (0.0590) time: 0.3730 data: 0.0045 max mem: 3957 +train: [9] [160/400] eta: 0:01:36 lr: 0.000241 loss: 3.1060 (3.0983) grad: 0.0587 (0.0590) time: 0.3699 data: 0.0044 max mem: 3957 +train: [9] [180/400] eta: 0:01:27 lr: 0.000240 loss: 3.0904 (3.0968) grad: 0.0606 (0.0592) time: 0.3770 data: 0.0041 max mem: 3957 +train: [9] [200/400] eta: 0:01:19 lr: 0.000238 loss: 3.0885 (3.0959) grad: 0.0588 (0.0594) time: 0.3779 data: 0.0043 max mem: 3957 +train: [9] [220/400] eta: 0:01:11 lr: 0.000237 loss: 3.0883 (3.0943) grad: 0.0565 (0.0594) time: 0.3730 data: 0.0041 max mem: 3957 +train: [9] [240/400] eta: 0:01:03 lr: 0.000236 loss: 3.0747 (3.0941) grad: 0.0613 (0.0596) time: 0.3968 data: 0.0045 max mem: 3957 +train: [9] [260/400] eta: 0:00:54 lr: 0.000234 loss: 3.0867 (3.0949) grad: 0.0613 (0.0597) time: 0.3632 data: 0.0044 max mem: 3957 +train: [9] [280/400] eta: 0:00:46 lr: 0.000233 loss: 3.0868 (3.0947) grad: 0.0592 (0.0599) time: 0.3813 data: 0.0046 max mem: 3957 +train: [9] [300/400] eta: 0:00:38 lr: 0.000232 loss: 3.1043 (3.0964) grad: 0.0592 (0.0600) time: 0.3692 data: 0.0039 max mem: 3957 +train: [9] [320/400] eta: 0:00:31 lr: 0.000230 loss: 3.0972 (3.0966) grad: 0.0605 (0.0601) time: 0.3710 data: 0.0042 max mem: 3957 +train: [9] [340/400] eta: 0:00:23 lr: 0.000229 loss: 3.0972 (3.0968) grad: 0.0587 (0.0600) time: 0.3762 data: 0.0045 max mem: 3957 +train: [9] [360/400] eta: 0:00:15 lr: 0.000228 loss: 3.0895 (3.0958) grad: 0.0622 (0.0604) time: 0.3641 data: 0.0043 max mem: 3957 +train: [9] [380/400] eta: 0:00:07 lr: 0.000226 loss: 3.0691 (3.0939) grad: 0.0616 (0.0602) time: 0.3510 data: 0.0041 max mem: 3957 +train: [9] [399/400] eta: 0:00:00 lr: 0.000225 loss: 3.0749 (3.0944) grad: 0.0574 (0.0603) time: 0.3546 data: 0.0040 max mem: 3957 +train: [9] Total time: 0:02:33 (0.3837 s / it) +train: [9] Summary: lr: 0.000225 loss: 3.0749 (3.0944) grad: 0.0574 (0.0603) +eval (validation): [9] [ 0/85] eta: 0:04:42 time: 3.3254 data: 3.0994 max mem: 3957 +eval (validation): [9] [20/85] eta: 0:00:34 time: 0.3898 data: 0.0139 max mem: 3957 +eval (validation): [9] [40/85] eta: 0:00:19 time: 0.3228 data: 0.0039 max mem: 3957 +eval (validation): [9] [60/85] eta: 0:00:09 time: 0.3392 data: 0.0042 max mem: 3957 +eval (validation): [9] [80/85] eta: 0:00:01 time: 0.3335 data: 0.0042 max mem: 3957 +eval (validation): [9] [84/85] eta: 0:00:00 time: 0.3270 data: 0.0041 max mem: 3957 +eval (validation): [9] Total time: 0:00:32 (0.3827 s / it) +cv: [9] best hparam: (26, 1.0) (044) ('044_lr2.6e+01_wd1.0e+00') loss: 3.032 acc: 0.120 f1: 0.065 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__linear/checkpoint-last.pth +train: [10] [ 0/400] eta: 0:21:54 lr: nan time: 3.2871 data: 3.0586 max mem: 3957 +train: [10] [ 20/400] eta: 0:03:03 lr: 0.000224 loss: 3.0682 (3.0815) grad: 0.0559 (0.0566) time: 0.3440 data: 0.0042 max mem: 3957 +train: [10] [ 40/400] eta: 0:02:28 lr: 0.000222 loss: 3.0904 (3.0816) grad: 0.0555 (0.0563) time: 0.3358 data: 0.0040 max mem: 3957 +train: [10] [ 60/400] eta: 0:02:12 lr: 0.000221 loss: 3.0904 (3.0882) grad: 0.0535 (0.0565) time: 0.3419 data: 0.0047 max mem: 3957 +train: [10] [ 80/400] eta: 0:02:01 lr: 0.000220 loss: 3.0720 (3.0836) grad: 0.0552 (0.0566) time: 0.3484 data: 0.0033 max mem: 3957 +train: [10] [100/400] eta: 0:01:52 lr: 0.000218 loss: 3.0813 (3.0879) grad: 0.0577 (0.0567) time: 0.3524 data: 0.0043 max mem: 3957 +train: [10] [120/400] eta: 0:01:43 lr: 0.000217 loss: 3.0899 (3.0874) grad: 0.0557 (0.0567) time: 0.3467 data: 0.0042 max mem: 3957 +train: [10] [140/400] eta: 0:01:35 lr: 0.000215 loss: 3.0809 (3.0854) grad: 0.0557 (0.0576) time: 0.3480 data: 0.0043 max mem: 3957 +train: [10] [160/400] eta: 0:01:27 lr: 0.000214 loss: 3.1027 (3.0877) grad: 0.0613 (0.0577) time: 0.3555 data: 0.0038 max mem: 3957 +train: [10] [180/400] eta: 0:01:20 lr: 0.000213 loss: 3.1053 (3.0889) grad: 0.0613 (0.0582) time: 0.3603 data: 0.0041 max mem: 3957 +train: [10] [200/400] eta: 0:01:12 lr: 0.000211 loss: 3.0912 (3.0889) grad: 0.0615 (0.0584) time: 0.3560 data: 0.0039 max mem: 3957 +train: [10] [220/400] eta: 0:01:05 lr: 0.000210 loss: 3.0910 (3.0897) grad: 0.0615 (0.0587) time: 0.3520 data: 0.0042 max mem: 3957 +train: [10] [240/400] eta: 0:00:58 lr: 0.000208 loss: 3.0910 (3.0891) grad: 0.0593 (0.0585) time: 0.3862 data: 0.0042 max mem: 3957 +train: [10] [260/400] eta: 0:00:51 lr: 0.000207 loss: 3.1023 (3.0908) grad: 0.0546 (0.0584) time: 0.3694 data: 0.0039 max mem: 3957 +train: [10] [280/400] eta: 0:00:44 lr: 0.000205 loss: 3.1072 (3.0912) grad: 0.0558 (0.0584) time: 0.3950 data: 0.0041 max mem: 3957 +train: [10] [300/400] eta: 0:00:36 lr: 0.000204 loss: 3.0845 (3.0901) grad: 0.0589 (0.0585) time: 0.3766 data: 0.0042 max mem: 3957 +train: [10] [320/400] eta: 0:00:29 lr: 0.000202 loss: 3.0911 (3.0910) grad: 0.0583 (0.0585) time: 0.3787 data: 0.0042 max mem: 3957 +train: [10] [340/400] eta: 0:00:22 lr: 0.000201 loss: 3.1095 (3.0913) grad: 0.0572 (0.0586) time: 0.3737 data: 0.0044 max mem: 3957 +train: [10] [360/400] eta: 0:00:14 lr: 0.000199 loss: 3.0838 (3.0919) grad: 0.0605 (0.0587) time: 0.3938 data: 0.0043 max mem: 3957 +train: [10] [380/400] eta: 0:00:07 lr: 0.000198 loss: 3.0636 (3.0910) grad: 0.0592 (0.0588) time: 0.3739 data: 0.0042 max mem: 3957 +train: [10] [399/400] eta: 0:00:00 lr: 0.000196 loss: 3.0916 (3.0910) grad: 0.0562 (0.0586) time: 0.3731 data: 0.0043 max mem: 3957 +train: [10] Total time: 0:02:28 (0.3707 s / it) +train: [10] Summary: lr: 0.000196 loss: 3.0916 (3.0910) grad: 0.0562 (0.0586) +eval (validation): [10] [ 0/85] eta: 0:05:03 time: 3.5718 data: 3.3236 max mem: 3957 +eval (validation): [10] [20/85] eta: 0:00:36 time: 0.4096 data: 0.0419 max mem: 3957 +eval (validation): [10] [40/85] eta: 0:00:20 time: 0.3466 data: 0.0046 max mem: 3957 +eval (validation): [10] [60/85] eta: 0:00:10 time: 0.3832 data: 0.0049 max mem: 3957 +eval (validation): [10] [80/85] eta: 0:00:02 time: 0.3635 data: 0.0045 max mem: 3957 +eval (validation): [10] [84/85] eta: 0:00:00 time: 0.3508 data: 0.0043 max mem: 3957 +eval (validation): [10] Total time: 0:00:35 (0.4139 s / it) +cv: [10] best hparam: (26, 1.0) (044) ('044_lr2.6e+01_wd1.0e+00') loss: 3.025 acc: 0.123 f1: 0.076 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__linear/checkpoint-best.pth +train: [11] [ 0/400] eta: 0:24:56 lr: nan time: 3.7423 data: 3.4345 max mem: 3957 +train: [11] [ 20/400] eta: 0:03:27 lr: 0.000195 loss: 3.0776 (3.0870) grad: 0.0595 (0.0586) time: 0.3876 data: 0.0040 max mem: 3957 +train: [11] [ 40/400] eta: 0:02:46 lr: 0.000193 loss: 3.0776 (3.0778) grad: 0.0600 (0.0604) time: 0.3726 data: 0.0040 max mem: 3957 +train: [11] [ 60/400] eta: 0:02:24 lr: 0.000192 loss: 3.0807 (3.0852) grad: 0.0608 (0.0605) time: 0.3514 data: 0.0043 max mem: 3957 +train: [11] [ 80/400] eta: 0:02:13 lr: 0.000190 loss: 3.0976 (3.0871) grad: 0.0608 (0.0606) time: 0.3875 data: 0.0044 max mem: 3957 +train: [11] [100/400] eta: 0:02:02 lr: 0.000189 loss: 3.0976 (3.0914) grad: 0.0599 (0.0603) time: 0.3834 data: 0.0044 max mem: 3957 +train: [11] [120/400] eta: 0:01:53 lr: 0.000187 loss: 3.0917 (3.0904) grad: 0.0596 (0.0600) time: 0.3781 data: 0.0045 max mem: 3957 +train: [11] [140/400] eta: 0:01:44 lr: 0.000186 loss: 3.0773 (3.0834) grad: 0.0578 (0.0599) time: 0.3828 data: 0.0039 max mem: 3957 +train: [11] [160/400] eta: 0:01:35 lr: 0.000184 loss: 3.0887 (3.0851) grad: 0.0657 (0.0605) time: 0.3834 data: 0.0044 max mem: 3957 +train: [11] [180/400] eta: 0:01:27 lr: 0.000183 loss: 3.0895 (3.0846) grad: 0.0631 (0.0603) time: 0.3814 data: 0.0046 max mem: 3957 +train: [11] [200/400] eta: 0:01:19 lr: 0.000181 loss: 3.0699 (3.0837) grad: 0.0603 (0.0602) time: 0.3799 data: 0.0042 max mem: 3957 +train: [11] [220/400] eta: 0:01:10 lr: 0.000180 loss: 3.0860 (3.0858) grad: 0.0613 (0.0605) time: 0.3769 data: 0.0042 max mem: 3957 +train: [11] [240/400] eta: 0:01:03 lr: 0.000178 loss: 3.1208 (3.0871) grad: 0.0577 (0.0602) time: 0.4036 data: 0.0045 max mem: 3957 +train: [11] [260/400] eta: 0:00:54 lr: 0.000177 loss: 3.0808 (3.0858) grad: 0.0576 (0.0599) time: 0.3609 data: 0.0041 max mem: 3957 +train: [11] [280/400] eta: 0:00:47 lr: 0.000175 loss: 3.0728 (3.0858) grad: 0.0558 (0.0597) time: 0.3998 data: 0.0048 max mem: 3957 +train: [11] [300/400] eta: 0:00:39 lr: 0.000174 loss: 3.0953 (3.0873) grad: 0.0558 (0.0595) time: 0.3633 data: 0.0042 max mem: 3957 +train: [11] [320/400] eta: 0:00:31 lr: 0.000172 loss: 3.0887 (3.0866) grad: 0.0577 (0.0596) time: 0.3501 data: 0.0043 max mem: 3957 +train: [11] [340/400] eta: 0:00:23 lr: 0.000170 loss: 3.0867 (3.0869) grad: 0.0583 (0.0595) time: 0.3829 data: 0.0038 max mem: 3957 +train: [11] [360/400] eta: 0:00:15 lr: 0.000169 loss: 3.0856 (3.0854) grad: 0.0583 (0.0594) time: 0.3785 data: 0.0039 max mem: 3957 +train: [11] [380/400] eta: 0:00:07 lr: 0.000167 loss: 3.0625 (3.0853) grad: 0.0596 (0.0596) time: 0.3632 data: 0.0040 max mem: 3957 +train: [11] [399/400] eta: 0:00:00 lr: 0.000166 loss: 3.1003 (3.0862) grad: 0.0576 (0.0594) time: 0.3941 data: 0.0044 max mem: 3957 +train: [11] Total time: 0:02:34 (0.3868 s / it) +train: [11] Summary: lr: 0.000166 loss: 3.1003 (3.0862) grad: 0.0576 (0.0594) +eval (validation): [11] [ 0/85] eta: 0:05:05 time: 3.5903 data: 3.3057 max mem: 3957 +eval (validation): [11] [20/85] eta: 0:00:35 time: 0.3988 data: 0.0048 max mem: 3957 +eval (validation): [11] [40/85] eta: 0:00:20 time: 0.3745 data: 0.0040 max mem: 3957 +eval (validation): [11] [60/85] eta: 0:00:11 time: 0.3899 data: 0.0045 max mem: 3957 +eval (validation): [11] [80/85] eta: 0:00:02 time: 0.3658 data: 0.0044 max mem: 3957 +eval (validation): [11] [84/85] eta: 0:00:00 time: 0.3598 data: 0.0044 max mem: 3957 +eval (validation): [11] Total time: 0:00:35 (0.4219 s / it) +cv: [11] best hparam: (26, 1.0) (044) ('044_lr2.6e+01_wd1.0e+00') loss: 3.019 acc: 0.121 f1: 0.057 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__linear/checkpoint-last.pth +train: [12] [ 0/400] eta: 0:23:44 lr: nan time: 3.5622 data: 3.3165 max mem: 3957 +train: [12] [ 20/400] eta: 0:03:20 lr: 0.000164 loss: 3.0701 (3.0795) grad: 0.0572 (0.0592) time: 0.3755 data: 0.0043 max mem: 3957 +train: [12] [ 40/400] eta: 0:02:45 lr: 0.000163 loss: 3.0757 (3.0839) grad: 0.0598 (0.0589) time: 0.3860 data: 0.0044 max mem: 3957 +train: [12] [ 60/400] eta: 0:02:24 lr: 0.000161 loss: 3.0980 (3.0890) grad: 0.0598 (0.0598) time: 0.3600 data: 0.0041 max mem: 3957 +train: [12] [ 80/400] eta: 0:02:13 lr: 0.000160 loss: 3.0957 (3.0863) grad: 0.0608 (0.0599) time: 0.3939 data: 0.0037 max mem: 3957 +train: [12] [100/400] eta: 0:02:03 lr: 0.000158 loss: 3.0903 (3.0890) grad: 0.0603 (0.0600) time: 0.3777 data: 0.0043 max mem: 3957 +train: [12] [120/400] eta: 0:01:53 lr: 0.000156 loss: 3.0879 (3.0857) grad: 0.0597 (0.0595) time: 0.3759 data: 0.0045 max mem: 3957 +train: [12] [140/400] eta: 0:01:45 lr: 0.000155 loss: 3.0656 (3.0832) grad: 0.0569 (0.0596) time: 0.4042 data: 0.0045 max mem: 3957 +train: [12] [160/400] eta: 0:01:36 lr: 0.000153 loss: 3.0598 (3.0798) grad: 0.0599 (0.0594) time: 0.3728 data: 0.0044 max mem: 3957 +train: [12] [180/400] eta: 0:01:27 lr: 0.000152 loss: 3.0509 (3.0771) grad: 0.0599 (0.0595) time: 0.3851 data: 0.0043 max mem: 3957 +train: [12] [200/400] eta: 0:01:19 lr: 0.000150 loss: 3.0640 (3.0772) grad: 0.0576 (0.0592) time: 0.3879 data: 0.0043 max mem: 3957 +train: [12] [220/400] eta: 0:01:11 lr: 0.000149 loss: 3.0836 (3.0778) grad: 0.0575 (0.0589) time: 0.3721 data: 0.0042 max mem: 3957 +train: [12] [240/400] eta: 0:01:02 lr: 0.000147 loss: 3.0835 (3.0764) grad: 0.0575 (0.0589) time: 0.3749 data: 0.0039 max mem: 3957 +train: [12] [260/400] eta: 0:00:55 lr: 0.000145 loss: 3.0704 (3.0766) grad: 0.0570 (0.0590) time: 0.3892 data: 0.0042 max mem: 3957 +train: [12] [280/400] eta: 0:00:47 lr: 0.000144 loss: 3.0809 (3.0775) grad: 0.0555 (0.0586) time: 0.3792 data: 0.0043 max mem: 3957 +train: [12] [300/400] eta: 0:00:39 lr: 0.000142 loss: 3.0791 (3.0771) grad: 0.0555 (0.0586) time: 0.3802 data: 0.0042 max mem: 3957 +train: [12] [320/400] eta: 0:00:31 lr: 0.000141 loss: 3.0715 (3.0776) grad: 0.0575 (0.0584) time: 0.3673 data: 0.0041 max mem: 3957 +train: [12] [340/400] eta: 0:00:23 lr: 0.000139 loss: 3.0786 (3.0785) grad: 0.0564 (0.0583) time: 0.4076 data: 0.0041 max mem: 3957 +train: [12] [360/400] eta: 0:00:15 lr: 0.000138 loss: 3.0826 (3.0778) grad: 0.0587 (0.0586) time: 0.3778 data: 0.0043 max mem: 3957 +train: [12] [380/400] eta: 0:00:07 lr: 0.000136 loss: 3.0816 (3.0783) grad: 0.0561 (0.0584) time: 0.3853 data: 0.0040 max mem: 3957 +train: [12] [399/400] eta: 0:00:00 lr: 0.000134 loss: 3.0843 (3.0791) grad: 0.0557 (0.0585) time: 0.3742 data: 0.0040 max mem: 3957 +train: [12] Total time: 0:02:35 (0.3895 s / it) +train: [12] Summary: lr: 0.000134 loss: 3.0843 (3.0791) grad: 0.0557 (0.0585) +eval (validation): [12] [ 0/85] eta: 0:05:05 time: 3.5930 data: 3.2736 max mem: 3957 +eval (validation): [12] [20/85] eta: 0:00:32 time: 0.3481 data: 0.0049 max mem: 3957 +eval (validation): [12] [40/85] eta: 0:00:19 time: 0.3831 data: 0.0045 max mem: 3957 +eval (validation): [12] [60/85] eta: 0:00:10 time: 0.3628 data: 0.0045 max mem: 3957 +eval (validation): [12] [80/85] eta: 0:00:02 time: 0.3625 data: 0.0042 max mem: 3957 +eval (validation): [12] [84/85] eta: 0:00:00 time: 0.3504 data: 0.0041 max mem: 3957 +eval (validation): [12] Total time: 0:00:34 (0.4054 s / it) +cv: [12] best hparam: (12, 1.0) (039) ('039_lr1.2e+01_wd1.0e+00') loss: 3.025 acc: 0.120 f1: 0.066 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__linear/checkpoint-last.pth +train: [13] [ 0/400] eta: 0:28:16 lr: nan time: 4.2401 data: 3.9998 max mem: 3957 +train: [13] [ 20/400] eta: 0:03:42 lr: 0.000133 loss: 3.0833 (3.0881) grad: 0.0613 (0.0619) time: 0.4024 data: 0.0201 max mem: 3957 +train: [13] [ 40/400] eta: 0:02:58 lr: 0.000131 loss: 3.0833 (3.0836) grad: 0.0595 (0.0598) time: 0.4018 data: 0.0036 max mem: 3957 +train: [13] [ 60/400] eta: 0:02:34 lr: 0.000130 loss: 3.0845 (3.0868) grad: 0.0586 (0.0599) time: 0.3679 data: 0.0041 max mem: 3957 +train: [13] [ 80/400] eta: 0:02:19 lr: 0.000128 loss: 3.0875 (3.0873) grad: 0.0606 (0.0595) time: 0.3776 data: 0.0044 max mem: 3957 +train: [13] [100/400] eta: 0:02:07 lr: 0.000127 loss: 3.0865 (3.0863) grad: 0.0632 (0.0595) time: 0.3783 data: 0.0042 max mem: 3957 +train: [13] [120/400] eta: 0:01:56 lr: 0.000125 loss: 3.0795 (3.0839) grad: 0.0580 (0.0596) time: 0.3730 data: 0.0043 max mem: 3957 +train: [13] [140/400] eta: 0:01:46 lr: 0.000124 loss: 3.0637 (3.0826) grad: 0.0592 (0.0598) time: 0.3725 data: 0.0042 max mem: 3957 +train: [13] [160/400] eta: 0:01:37 lr: 0.000122 loss: 3.0741 (3.0827) grad: 0.0603 (0.0595) time: 0.3735 data: 0.0041 max mem: 3957 +train: [13] [180/400] eta: 0:01:28 lr: 0.000120 loss: 3.0741 (3.0798) grad: 0.0567 (0.0591) time: 0.3764 data: 0.0043 max mem: 3957 +train: [13] [200/400] eta: 0:01:19 lr: 0.000119 loss: 3.0724 (3.0791) grad: 0.0559 (0.0588) time: 0.3834 data: 0.0041 max mem: 3957 +train: [13] [220/400] eta: 0:01:11 lr: 0.000117 loss: 3.0837 (3.0790) grad: 0.0535 (0.0586) time: 0.3611 data: 0.0041 max mem: 3957 +train: [13] [240/400] eta: 0:01:03 lr: 0.000116 loss: 3.0837 (3.0796) grad: 0.0567 (0.0588) time: 0.3794 data: 0.0041 max mem: 3957 +train: [13] [260/400] eta: 0:00:55 lr: 0.000114 loss: 3.0928 (3.0798) grad: 0.0587 (0.0585) time: 0.4026 data: 0.0046 max mem: 3957 +train: [13] [280/400] eta: 0:00:47 lr: 0.000113 loss: 3.0928 (3.0803) grad: 0.0587 (0.0585) time: 0.3663 data: 0.0042 max mem: 3957 +train: [13] [300/400] eta: 0:00:39 lr: 0.000111 loss: 3.0868 (3.0803) grad: 0.0580 (0.0585) time: 0.3820 data: 0.0042 max mem: 3957 +train: [13] [320/400] eta: 0:00:31 lr: 0.000110 loss: 3.0812 (3.0794) grad: 0.0579 (0.0585) time: 0.3841 data: 0.0040 max mem: 3957 +train: [13] [340/400] eta: 0:00:23 lr: 0.000108 loss: 3.0812 (3.0792) grad: 0.0565 (0.0583) time: 0.3934 data: 0.0043 max mem: 3957 +train: [13] [360/400] eta: 0:00:15 lr: 0.000107 loss: 3.0762 (3.0779) grad: 0.0565 (0.0582) time: 0.3689 data: 0.0041 max mem: 3957 +train: [13] [380/400] eta: 0:00:07 lr: 0.000105 loss: 3.0428 (3.0776) grad: 0.0574 (0.0583) time: 0.3899 data: 0.0042 max mem: 3957 +train: [13] [399/400] eta: 0:00:00 lr: 0.000104 loss: 3.0562 (3.0767) grad: 0.0574 (0.0584) time: 0.3602 data: 0.0043 max mem: 3957 +train: [13] Total time: 0:02:35 (0.3897 s / it) +train: [13] Summary: lr: 0.000104 loss: 3.0562 (3.0767) grad: 0.0574 (0.0584) +eval (validation): [13] [ 0/85] eta: 0:05:04 time: 3.5825 data: 3.3700 max mem: 3957 +eval (validation): [13] [20/85] eta: 0:00:34 time: 0.3713 data: 0.0050 max mem: 3957 +eval (validation): [13] [40/85] eta: 0:00:20 time: 0.3827 data: 0.0042 max mem: 3957 +eval (validation): [13] [60/85] eta: 0:00:10 time: 0.3807 data: 0.0050 max mem: 3957 +eval (validation): [13] [80/85] eta: 0:00:02 time: 0.3554 data: 0.0042 max mem: 3957 +eval (validation): [13] [84/85] eta: 0:00:00 time: 0.3543 data: 0.0041 max mem: 3957 +eval (validation): [13] Total time: 0:00:35 (0.4134 s / it) +cv: [13] best hparam: (16, 1.0) (041) ('041_lr1.6e+01_wd1.0e+00') loss: 3.039 acc: 0.109 f1: 0.046 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__linear/checkpoint-last.pth +train: [14] [ 0/400] eta: 0:24:05 lr: nan time: 3.6126 data: 3.3115 max mem: 3957 +train: [14] [ 20/400] eta: 0:03:28 lr: 0.000102 loss: 3.0793 (3.0854) grad: 0.0593 (0.0592) time: 0.3966 data: 0.0057 max mem: 3957 +train: [14] [ 40/400] eta: 0:02:48 lr: 0.000101 loss: 3.0793 (3.0788) grad: 0.0565 (0.0569) time: 0.3848 data: 0.0038 max mem: 3957 +train: [14] [ 60/400] eta: 0:02:29 lr: 0.000099 loss: 3.0933 (3.0864) grad: 0.0565 (0.0579) time: 0.3761 data: 0.0037 max mem: 3957 +train: [14] [ 80/400] eta: 0:02:16 lr: 0.000098 loss: 3.0732 (3.0797) grad: 0.0594 (0.0574) time: 0.3888 data: 0.0043 max mem: 3957 +train: [14] [100/400] eta: 0:02:05 lr: 0.000096 loss: 3.0600 (3.0778) grad: 0.0537 (0.0579) time: 0.3884 data: 0.0043 max mem: 3957 +train: [14] [120/400] eta: 0:01:55 lr: 0.000095 loss: 3.0666 (3.0769) grad: 0.0558 (0.0575) time: 0.3825 data: 0.0043 max mem: 3957 +train: [14] [140/400] eta: 0:01:46 lr: 0.000093 loss: 3.0666 (3.0737) grad: 0.0554 (0.0574) time: 0.3772 data: 0.0043 max mem: 3957 +train: [14] [160/400] eta: 0:01:37 lr: 0.000092 loss: 3.0661 (3.0737) grad: 0.0569 (0.0577) time: 0.3882 data: 0.0045 max mem: 3957 +train: [14] [180/400] eta: 0:01:28 lr: 0.000090 loss: 3.0832 (3.0752) grad: 0.0594 (0.0580) time: 0.3852 data: 0.0044 max mem: 3957 +train: [14] [200/400] eta: 0:01:20 lr: 0.000089 loss: 3.0832 (3.0759) grad: 0.0590 (0.0581) time: 0.3797 data: 0.0042 max mem: 3957 +train: [14] [220/400] eta: 0:01:11 lr: 0.000088 loss: 3.0807 (3.0760) grad: 0.0574 (0.0579) time: 0.3638 data: 0.0039 max mem: 3957 +train: [14] [240/400] eta: 0:01:03 lr: 0.000086 loss: 3.0633 (3.0747) grad: 0.0537 (0.0577) time: 0.3890 data: 0.0042 max mem: 3957 +train: [14] [260/400] eta: 0:00:55 lr: 0.000085 loss: 3.0602 (3.0726) grad: 0.0579 (0.0576) time: 0.3861 data: 0.0042 max mem: 3957 +train: [14] [280/400] eta: 0:00:47 lr: 0.000083 loss: 3.0647 (3.0726) grad: 0.0579 (0.0577) time: 0.3694 data: 0.0042 max mem: 3957 +train: [14] [300/400] eta: 0:00:39 lr: 0.000082 loss: 3.0647 (3.0721) grad: 0.0584 (0.0577) time: 0.3720 data: 0.0042 max mem: 3957 +train: [14] [320/400] eta: 0:00:31 lr: 0.000081 loss: 3.0734 (3.0722) grad: 0.0585 (0.0579) time: 0.3761 data: 0.0041 max mem: 3957 +train: [14] [340/400] eta: 0:00:23 lr: 0.000079 loss: 3.0788 (3.0722) grad: 0.0581 (0.0578) time: 0.3849 data: 0.0042 max mem: 3957 +train: [14] [360/400] eta: 0:00:15 lr: 0.000078 loss: 3.0788 (3.0726) grad: 0.0572 (0.0578) time: 0.3697 data: 0.0038 max mem: 3957 +train: [14] [380/400] eta: 0:00:07 lr: 0.000076 loss: 3.0734 (3.0722) grad: 0.0584 (0.0579) time: 0.3806 data: 0.0043 max mem: 3957 +train: [14] [399/400] eta: 0:00:00 lr: 0.000075 loss: 3.0816 (3.0731) grad: 0.0584 (0.0580) time: 0.3741 data: 0.0043 max mem: 3957 +train: [14] Total time: 0:02:35 (0.3890 s / it) +train: [14] Summary: lr: 0.000075 loss: 3.0816 (3.0731) grad: 0.0584 (0.0580) +eval (validation): [14] [ 0/85] eta: 0:04:57 time: 3.4968 data: 3.2298 max mem: 3957 +eval (validation): [14] [20/85] eta: 0:00:33 time: 0.3701 data: 0.0039 max mem: 3957 +eval (validation): [14] [40/85] eta: 0:00:20 time: 0.3931 data: 0.0050 max mem: 3957 +eval (validation): [14] [60/85] eta: 0:00:10 time: 0.3403 data: 0.0046 max mem: 3957 +eval (validation): [14] [80/85] eta: 0:00:01 time: 0.3324 data: 0.0042 max mem: 3957 +eval (validation): [14] [84/85] eta: 0:00:00 time: 0.3292 data: 0.0041 max mem: 3957 +eval (validation): [14] Total time: 0:00:33 (0.3976 s / it) +cv: [14] best hparam: (36, 1.0) (046) ('046_lr3.6e+01_wd1.0e+00') loss: 3.003 acc: 0.127 f1: 0.070 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__linear/checkpoint-best.pth +train: [15] [ 0/400] eta: 0:22:23 lr: nan time: 3.3580 data: 3.1220 max mem: 3957 +train: [15] [ 20/400] eta: 0:03:23 lr: 0.000074 loss: 3.0555 (3.0675) grad: 0.0572 (0.0597) time: 0.3939 data: 0.0261 max mem: 3957 +train: [15] [ 40/400] eta: 0:02:40 lr: 0.000072 loss: 3.0607 (3.0734) grad: 0.0572 (0.0600) time: 0.3497 data: 0.0035 max mem: 3957 +train: [15] [ 60/400] eta: 0:02:19 lr: 0.000071 loss: 3.0618 (3.0644) grad: 0.0572 (0.0593) time: 0.3361 data: 0.0038 max mem: 3957 +train: [15] [ 80/400] eta: 0:02:06 lr: 0.000070 loss: 3.0393 (3.0639) grad: 0.0554 (0.0577) time: 0.3573 data: 0.0042 max mem: 3957 +train: [15] [100/400] eta: 0:01:56 lr: 0.000068 loss: 3.0600 (3.0653) grad: 0.0542 (0.0582) time: 0.3539 data: 0.0042 max mem: 3957 +train: [15] [120/400] eta: 0:01:46 lr: 0.000067 loss: 3.0640 (3.0630) grad: 0.0547 (0.0579) time: 0.3506 data: 0.0040 max mem: 3957 +train: [15] [140/400] eta: 0:01:38 lr: 0.000066 loss: 3.0523 (3.0628) grad: 0.0585 (0.0585) time: 0.3507 data: 0.0041 max mem: 3957 +train: [15] [160/400] eta: 0:01:29 lr: 0.000064 loss: 3.0629 (3.0642) grad: 0.0585 (0.0585) time: 0.3527 data: 0.0039 max mem: 3957 +train: [15] [180/400] eta: 0:01:21 lr: 0.000063 loss: 3.0794 (3.0660) grad: 0.0560 (0.0584) time: 0.3431 data: 0.0044 max mem: 3957 +train: [15] [200/400] eta: 0:01:13 lr: 0.000062 loss: 3.0834 (3.0685) grad: 0.0545 (0.0583) time: 0.3493 data: 0.0041 max mem: 3957 +train: [15] [220/400] eta: 0:01:05 lr: 0.000061 loss: 3.0717 (3.0679) grad: 0.0533 (0.0578) time: 0.3388 data: 0.0036 max mem: 3957 +train: [15] [240/400] eta: 0:00:58 lr: 0.000059 loss: 3.0712 (3.0693) grad: 0.0554 (0.0580) time: 0.3624 data: 0.0041 max mem: 3957 +train: [15] [260/400] eta: 0:00:51 lr: 0.000058 loss: 3.0902 (3.0704) grad: 0.0571 (0.0579) time: 0.3509 data: 0.0039 max mem: 3957 +train: [15] [280/400] eta: 0:00:43 lr: 0.000057 loss: 3.0785 (3.0705) grad: 0.0571 (0.0581) time: 0.3533 data: 0.0042 max mem: 3957 +train: [15] [300/400] eta: 0:00:36 lr: 0.000056 loss: 3.0758 (3.0706) grad: 0.0543 (0.0580) time: 0.3450 data: 0.0035 max mem: 3957 +train: [15] [320/400] eta: 0:00:28 lr: 0.000054 loss: 3.0853 (3.0715) grad: 0.0569 (0.0581) time: 0.3334 data: 0.0038 max mem: 3957 +train: [15] [340/400] eta: 0:00:21 lr: 0.000053 loss: 3.0771 (3.0703) grad: 0.0616 (0.0582) time: 0.3524 data: 0.0040 max mem: 3957 +train: [15] [360/400] eta: 0:00:14 lr: 0.000052 loss: 3.0713 (3.0705) grad: 0.0585 (0.0582) time: 0.3539 data: 0.0040 max mem: 3957 +train: [15] [380/400] eta: 0:00:07 lr: 0.000051 loss: 3.0797 (3.0705) grad: 0.0544 (0.0579) time: 0.3593 data: 0.0040 max mem: 3957 +train: [15] [399/400] eta: 0:00:00 lr: 0.000050 loss: 3.0797 (3.0711) grad: 0.0544 (0.0580) time: 0.3447 data: 0.0043 max mem: 3957 +train: [15] Total time: 0:02:23 (0.3594 s / it) +train: [15] Summary: lr: 0.000050 loss: 3.0797 (3.0711) grad: 0.0544 (0.0580) +eval (validation): [15] [ 0/85] eta: 0:04:56 time: 3.4864 data: 3.1906 max mem: 3957 +eval (validation): [15] [20/85] eta: 0:00:35 time: 0.4005 data: 0.0043 max mem: 3957 +eval (validation): [15] [40/85] eta: 0:00:21 time: 0.3870 data: 0.0050 max mem: 3957 +eval (validation): [15] [60/85] eta: 0:00:10 time: 0.3743 data: 0.0047 max mem: 3957 +eval (validation): [15] [80/85] eta: 0:00:02 time: 0.3403 data: 0.0043 max mem: 3957 +eval (validation): [15] [84/85] eta: 0:00:00 time: 0.3339 data: 0.0043 max mem: 3957 +eval (validation): [15] Total time: 0:00:35 (0.4148 s / it) +cv: [15] best hparam: (36, 1.0) (046) ('046_lr3.6e+01_wd1.0e+00') loss: 2.994 acc: 0.122 f1: 0.062 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__linear/checkpoint-last.pth +train: [16] [ 0/400] eta: 0:24:13 lr: nan time: 3.6341 data: 3.3993 max mem: 3957 +train: [16] [ 20/400] eta: 0:03:21 lr: 0.000048 loss: 3.0813 (3.0848) grad: 0.0542 (0.0580) time: 0.3762 data: 0.0050 max mem: 3957 +train: [16] [ 40/400] eta: 0:02:45 lr: 0.000047 loss: 3.0815 (3.0818) grad: 0.0536 (0.0550) time: 0.3860 data: 0.0039 max mem: 3957 +train: [16] [ 60/400] eta: 0:02:27 lr: 0.000046 loss: 3.0666 (3.0699) grad: 0.0542 (0.0548) time: 0.3827 data: 0.0043 max mem: 3957 +train: [16] [ 80/400] eta: 0:02:13 lr: 0.000045 loss: 3.0678 (3.0702) grad: 0.0542 (0.0547) time: 0.3592 data: 0.0041 max mem: 3957 +train: [16] [100/400] eta: 0:02:03 lr: 0.000044 loss: 3.0792 (3.0730) grad: 0.0545 (0.0554) time: 0.3886 data: 0.0045 max mem: 3957 +train: [16] [120/400] eta: 0:01:53 lr: 0.000043 loss: 3.0730 (3.0693) grad: 0.0557 (0.0560) time: 0.3778 data: 0.0041 max mem: 3957 +train: [16] [140/400] eta: 0:01:44 lr: 0.000042 loss: 3.0436 (3.0676) grad: 0.0596 (0.0570) time: 0.3923 data: 0.0046 max mem: 3957 +train: [16] [160/400] eta: 0:01:36 lr: 0.000041 loss: 3.0641 (3.0687) grad: 0.0571 (0.0567) time: 0.3802 data: 0.0044 max mem: 3957 +train: [16] [180/400] eta: 0:01:27 lr: 0.000040 loss: 3.0671 (3.0680) grad: 0.0547 (0.0569) time: 0.3891 data: 0.0044 max mem: 3957 +train: [16] [200/400] eta: 0:01:19 lr: 0.000039 loss: 3.0831 (3.0704) grad: 0.0549 (0.0568) time: 0.3850 data: 0.0042 max mem: 3957 +train: [16] [220/400] eta: 0:01:11 lr: 0.000038 loss: 3.0942 (3.0711) grad: 0.0542 (0.0566) time: 0.3631 data: 0.0042 max mem: 3957 +train: [16] [240/400] eta: 0:01:02 lr: 0.000036 loss: 3.0683 (3.0705) grad: 0.0580 (0.0567) time: 0.3727 data: 0.0043 max mem: 3957 +train: [16] [260/400] eta: 0:00:55 lr: 0.000035 loss: 3.0683 (3.0713) grad: 0.0584 (0.0568) time: 0.4051 data: 0.0045 max mem: 3957 +train: [16] [280/400] eta: 0:00:47 lr: 0.000034 loss: 3.0719 (3.0709) grad: 0.0586 (0.0570) time: 0.3729 data: 0.0043 max mem: 3957 +train: [16] [300/400] eta: 0:00:39 lr: 0.000033 loss: 3.0618 (3.0698) grad: 0.0590 (0.0571) time: 0.3934 data: 0.0041 max mem: 3957 +train: [16] [320/400] eta: 0:00:31 lr: 0.000032 loss: 3.0596 (3.0692) grad: 0.0592 (0.0571) time: 0.3799 data: 0.0042 max mem: 3957 +train: [16] [340/400] eta: 0:00:23 lr: 0.000031 loss: 3.0629 (3.0698) grad: 0.0557 (0.0571) time: 0.3536 data: 0.0040 max mem: 3957 +train: [16] [360/400] eta: 0:00:15 lr: 0.000031 loss: 3.0787 (3.0707) grad: 0.0557 (0.0573) time: 0.4142 data: 0.0044 max mem: 3957 +train: [16] [380/400] eta: 0:00:07 lr: 0.000030 loss: 3.0771 (3.0702) grad: 0.0572 (0.0573) time: 0.4040 data: 0.0044 max mem: 3957 +train: [16] [399/400] eta: 0:00:00 lr: 0.000029 loss: 3.0660 (3.0704) grad: 0.0559 (0.0572) time: 0.3899 data: 0.0043 max mem: 3957 +train: [16] Total time: 0:02:36 (0.3915 s / it) +train: [16] Summary: lr: 0.000029 loss: 3.0660 (3.0704) grad: 0.0559 (0.0572) +eval (validation): [16] [ 0/85] eta: 0:05:15 time: 3.7065 data: 3.3898 max mem: 3957 +eval (validation): [16] [20/85] eta: 0:00:38 time: 0.4310 data: 0.0056 max mem: 3957 +eval (validation): [16] [40/85] eta: 0:00:22 time: 0.4022 data: 0.0047 max mem: 3957 +eval (validation): [16] [60/85] eta: 0:00:11 time: 0.3820 data: 0.0046 max mem: 3957 +eval (validation): [16] [80/85] eta: 0:00:02 time: 0.3450 data: 0.0046 max mem: 3957 +eval (validation): [16] [84/85] eta: 0:00:00 time: 0.3355 data: 0.0044 max mem: 3957 +eval (validation): [16] Total time: 0:00:36 (0.4301 s / it) +cv: [16] best hparam: (31, 1.0) (045) ('045_lr3.1e+01_wd1.0e+00') loss: 2.998 acc: 0.123 f1: 0.061 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__linear/checkpoint-last.pth +train: [17] [ 0/400] eta: 0:23:26 lr: nan time: 3.5163 data: 3.2791 max mem: 3957 +train: [17] [ 20/400] eta: 0:03:20 lr: 0.000028 loss: 3.0279 (3.0444) grad: 0.0557 (0.0542) time: 0.3795 data: 0.0042 max mem: 3957 +train: [17] [ 40/400] eta: 0:02:45 lr: 0.000027 loss: 3.0392 (3.0398) grad: 0.0560 (0.0577) time: 0.3893 data: 0.0038 max mem: 3957 +train: [17] [ 60/400] eta: 0:02:27 lr: 0.000026 loss: 3.0586 (3.0480) grad: 0.0579 (0.0572) time: 0.3769 data: 0.0043 max mem: 3957 +train: [17] [ 80/400] eta: 0:02:12 lr: 0.000025 loss: 3.0634 (3.0517) grad: 0.0557 (0.0565) time: 0.3579 data: 0.0045 max mem: 3957 +train: [17] [100/400] eta: 0:02:02 lr: 0.000024 loss: 3.0467 (3.0488) grad: 0.0557 (0.0563) time: 0.3844 data: 0.0044 max mem: 3957 +train: [17] [120/400] eta: 0:01:52 lr: 0.000023 loss: 3.0428 (3.0514) grad: 0.0570 (0.0567) time: 0.3763 data: 0.0044 max mem: 3957 +train: [17] [140/400] eta: 0:01:44 lr: 0.000023 loss: 3.0713 (3.0576) grad: 0.0579 (0.0564) time: 0.3904 data: 0.0043 max mem: 3957 +train: [17] [160/400] eta: 0:01:35 lr: 0.000022 loss: 3.0709 (3.0586) grad: 0.0544 (0.0563) time: 0.3848 data: 0.0040 max mem: 3957 +train: [17] [180/400] eta: 0:01:27 lr: 0.000021 loss: 3.0477 (3.0572) grad: 0.0561 (0.0562) time: 0.3766 data: 0.0048 max mem: 3957 +train: [17] [200/400] eta: 0:01:18 lr: 0.000020 loss: 3.0566 (3.0583) grad: 0.0563 (0.0561) time: 0.3707 data: 0.0043 max mem: 3957 +train: [17] [220/400] eta: 0:01:11 lr: 0.000019 loss: 3.0593 (3.0579) grad: 0.0561 (0.0562) time: 0.3982 data: 0.0043 max mem: 3957 +train: [17] [240/400] eta: 0:01:03 lr: 0.000019 loss: 3.0593 (3.0585) grad: 0.0516 (0.0560) time: 0.3983 data: 0.0045 max mem: 3957 +train: [17] [260/400] eta: 0:00:55 lr: 0.000018 loss: 3.0612 (3.0584) grad: 0.0556 (0.0561) time: 0.3722 data: 0.0041 max mem: 3957 +train: [17] [280/400] eta: 0:00:47 lr: 0.000017 loss: 3.0758 (3.0602) grad: 0.0551 (0.0558) time: 0.3842 data: 0.0043 max mem: 3957 +train: [17] [300/400] eta: 0:00:39 lr: 0.000016 loss: 3.0872 (3.0611) grad: 0.0540 (0.0557) time: 0.3829 data: 0.0042 max mem: 3957 +train: [17] [320/400] eta: 0:00:31 lr: 0.000016 loss: 3.0731 (3.0623) grad: 0.0551 (0.0557) time: 0.3694 data: 0.0044 max mem: 3957 +train: [17] [340/400] eta: 0:00:23 lr: 0.000015 loss: 3.0641 (3.0612) grad: 0.0562 (0.0557) time: 0.3478 data: 0.0042 max mem: 3957 +train: [17] [360/400] eta: 0:00:15 lr: 0.000014 loss: 3.0552 (3.0622) grad: 0.0565 (0.0558) time: 0.4068 data: 0.0041 max mem: 3957 +train: [17] [380/400] eta: 0:00:07 lr: 0.000014 loss: 3.0554 (3.0619) grad: 0.0555 (0.0556) time: 0.3946 data: 0.0045 max mem: 3957 +train: [17] [399/400] eta: 0:00:00 lr: 0.000013 loss: 3.0617 (3.0623) grad: 0.0545 (0.0556) time: 0.3711 data: 0.0042 max mem: 3957 +train: [17] Total time: 0:02:35 (0.3887 s / it) +train: [17] Summary: lr: 0.000013 loss: 3.0617 (3.0623) grad: 0.0545 (0.0556) +eval (validation): [17] [ 0/85] eta: 0:05:11 time: 3.6650 data: 3.3582 max mem: 3957 +eval (validation): [17] [20/85] eta: 0:00:35 time: 0.3887 data: 0.0055 max mem: 3957 +eval (validation): [17] [40/85] eta: 0:00:20 time: 0.3693 data: 0.0039 max mem: 3957 +eval (validation): [17] [60/85] eta: 0:00:10 time: 0.3489 data: 0.0046 max mem: 3957 +eval (validation): [17] [80/85] eta: 0:00:02 time: 0.3600 data: 0.0042 max mem: 3957 +eval (validation): [17] [84/85] eta: 0:00:00 time: 0.3491 data: 0.0042 max mem: 3957 +eval (validation): [17] Total time: 0:00:34 (0.4079 s / it) +cv: [17] best hparam: (43, 1.0) (047) ('047_lr4.3e+01_wd1.0e+00') loss: 2.989 acc: 0.128 f1: 0.070 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__linear/checkpoint-best.pth +train: [18] [ 0/400] eta: 0:24:02 lr: nan time: 3.6055 data: 3.2901 max mem: 3957 +train: [18] [ 20/400] eta: 0:03:23 lr: 0.000012 loss: 3.0739 (3.0883) grad: 0.0531 (0.0504) time: 0.3832 data: 0.0055 max mem: 3957 +train: [18] [ 40/400] eta: 0:02:47 lr: 0.000012 loss: 3.0903 (3.0906) grad: 0.0537 (0.0538) time: 0.3877 data: 0.0041 max mem: 3957 +train: [18] [ 60/400] eta: 0:02:28 lr: 0.000011 loss: 3.0818 (3.0814) grad: 0.0565 (0.0553) time: 0.3768 data: 0.0043 max mem: 3957 +train: [18] [ 80/400] eta: 0:02:13 lr: 0.000011 loss: 3.0385 (3.0737) grad: 0.0570 (0.0554) time: 0.3632 data: 0.0043 max mem: 3957 +train: [18] [100/400] eta: 0:02:03 lr: 0.000010 loss: 3.0743 (3.0758) grad: 0.0561 (0.0557) time: 0.3854 data: 0.0045 max mem: 3957 +train: [18] [120/400] eta: 0:01:53 lr: 0.000009 loss: 3.0818 (3.0737) grad: 0.0548 (0.0567) time: 0.3842 data: 0.0043 max mem: 3957 +train: [18] [140/400] eta: 0:01:45 lr: 0.000009 loss: 3.0622 (3.0710) grad: 0.0548 (0.0566) time: 0.3958 data: 0.0044 max mem: 3957 +train: [18] [160/400] eta: 0:01:36 lr: 0.000008 loss: 3.0712 (3.0742) grad: 0.0566 (0.0566) time: 0.3661 data: 0.0044 max mem: 3957 +train: [18] [180/400] eta: 0:01:27 lr: 0.000008 loss: 3.0712 (3.0732) grad: 0.0564 (0.0566) time: 0.3846 data: 0.0044 max mem: 3957 +train: [18] [200/400] eta: 0:01:19 lr: 0.000007 loss: 3.0611 (3.0721) grad: 0.0546 (0.0566) time: 0.3629 data: 0.0045 max mem: 3957 +train: [18] [220/400] eta: 0:01:11 lr: 0.000007 loss: 3.0659 (3.0723) grad: 0.0548 (0.0566) time: 0.4100 data: 0.0044 max mem: 3957 +train: [18] [240/400] eta: 0:01:03 lr: 0.000006 loss: 3.0659 (3.0719) grad: 0.0548 (0.0567) time: 0.3899 data: 0.0042 max mem: 3957 +train: [18] [260/400] eta: 0:00:55 lr: 0.000006 loss: 3.0767 (3.0734) grad: 0.0545 (0.0565) time: 0.3990 data: 0.0041 max mem: 3957 +train: [18] [280/400] eta: 0:00:47 lr: 0.000006 loss: 3.0734 (3.0720) grad: 0.0545 (0.0564) time: 0.3814 data: 0.0043 max mem: 3957 +train: [18] [300/400] eta: 0:00:39 lr: 0.000005 loss: 3.0448 (3.0692) grad: 0.0556 (0.0567) time: 0.3954 data: 0.0041 max mem: 3957 +train: [18] [320/400] eta: 0:00:31 lr: 0.000005 loss: 3.0448 (3.0696) grad: 0.0588 (0.0569) time: 0.3882 data: 0.0038 max mem: 3957 +train: [18] [340/400] eta: 0:00:23 lr: 0.000004 loss: 3.0772 (3.0692) grad: 0.0569 (0.0568) time: 0.3979 data: 0.0040 max mem: 3957 +train: [18] [360/400] eta: 0:00:15 lr: 0.000004 loss: 3.0453 (3.0682) grad: 0.0540 (0.0568) time: 0.4378 data: 0.0045 max mem: 3957 +train: [18] [380/400] eta: 0:00:07 lr: 0.000004 loss: 3.0543 (3.0684) grad: 0.0553 (0.0568) time: 0.3959 data: 0.0043 max mem: 3957 +train: [18] [399/400] eta: 0:00:00 lr: 0.000003 loss: 3.0544 (3.0673) grad: 0.0553 (0.0567) time: 0.3804 data: 0.0041 max mem: 3957 +train: [18] Total time: 0:02:38 (0.3966 s / it) +train: [18] Summary: lr: 0.000003 loss: 3.0544 (3.0673) grad: 0.0553 (0.0567) +eval (validation): [18] [ 0/85] eta: 0:05:15 time: 3.7152 data: 3.4132 max mem: 3957 +eval (validation): [18] [20/85] eta: 0:00:36 time: 0.3983 data: 0.0049 max mem: 3957 +eval (validation): [18] [40/85] eta: 0:00:21 time: 0.3733 data: 0.0046 max mem: 3957 +eval (validation): [18] [60/85] eta: 0:00:10 time: 0.3677 data: 0.0046 max mem: 3957 +eval (validation): [18] [80/85] eta: 0:00:02 time: 0.3703 data: 0.0048 max mem: 3957 +eval (validation): [18] [84/85] eta: 0:00:00 time: 0.3519 data: 0.0048 max mem: 3957 +eval (validation): [18] Total time: 0:00:35 (0.4189 s / it) +cv: [18] best hparam: (50, 1.0) (048) ('048_lr5.0e+01_wd1.0e+00') loss: 2.984 acc: 0.130 f1: 0.068 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__linear/checkpoint-best.pth +train: [19] [ 0/400] eta: 0:24:07 lr: nan time: 3.6188 data: 3.2835 max mem: 3957 +train: [19] [ 20/400] eta: 0:03:38 lr: 0.000003 loss: 3.0784 (3.0863) grad: 0.0488 (0.0508) time: 0.4235 data: 0.0046 max mem: 3957 +train: [19] [ 40/400] eta: 0:02:54 lr: 0.000003 loss: 3.0766 (3.0720) grad: 0.0548 (0.0537) time: 0.3903 data: 0.0044 max mem: 3957 +train: [19] [ 60/400] eta: 0:02:36 lr: 0.000002 loss: 3.0724 (3.0717) grad: 0.0565 (0.0547) time: 0.4069 data: 0.0043 max mem: 3957 +train: [19] [ 80/400] eta: 0:02:20 lr: 0.000002 loss: 3.0728 (3.0716) grad: 0.0582 (0.0557) time: 0.3705 data: 0.0043 max mem: 3957 +train: [19] [100/400] eta: 0:02:08 lr: 0.000002 loss: 3.0728 (3.0705) grad: 0.0606 (0.0563) time: 0.3972 data: 0.0043 max mem: 3957 +train: [19] [120/400] eta: 0:01:58 lr: 0.000002 loss: 3.0751 (3.0716) grad: 0.0558 (0.0556) time: 0.3938 data: 0.0044 max mem: 3957 +train: [19] [140/400] eta: 0:01:49 lr: 0.000001 loss: 3.0712 (3.0731) grad: 0.0527 (0.0554) time: 0.4181 data: 0.0039 max mem: 3957 +train: [19] [160/400] eta: 0:01:40 lr: 0.000001 loss: 3.0479 (3.0697) grad: 0.0515 (0.0554) time: 0.3906 data: 0.0043 max mem: 3957 +train: [19] [180/400] eta: 0:01:31 lr: 0.000001 loss: 3.0581 (3.0703) grad: 0.0515 (0.0551) time: 0.3940 data: 0.0040 max mem: 3957 +train: [19] [200/400] eta: 0:01:22 lr: 0.000001 loss: 3.0769 (3.0701) grad: 0.0534 (0.0558) time: 0.4003 data: 0.0040 max mem: 3957 +train: [19] [220/400] eta: 0:01:14 lr: 0.000001 loss: 3.0486 (3.0682) grad: 0.0573 (0.0556) time: 0.4170 data: 0.0046 max mem: 3957 +train: [19] [240/400] eta: 0:01:05 lr: 0.000001 loss: 3.0541 (3.0687) grad: 0.0534 (0.0558) time: 0.3860 data: 0.0041 max mem: 3957 +train: [19] [260/400] eta: 0:00:57 lr: 0.000000 loss: 3.0960 (3.0705) grad: 0.0568 (0.0557) time: 0.3674 data: 0.0042 max mem: 3957 +train: [19] [280/400] eta: 0:00:48 lr: 0.000000 loss: 3.0697 (3.0702) grad: 0.0568 (0.0560) time: 0.3839 data: 0.0043 max mem: 3957 +train: [19] [300/400] eta: 0:00:40 lr: 0.000000 loss: 3.0550 (3.0704) grad: 0.0559 (0.0559) time: 0.3834 data: 0.0045 max mem: 3957 +train: [19] [320/400] eta: 0:00:32 lr: 0.000000 loss: 3.0564 (3.0703) grad: 0.0537 (0.0560) time: 0.3940 data: 0.0041 max mem: 3957 +train: [19] [340/400] eta: 0:00:24 lr: 0.000000 loss: 3.0523 (3.0687) grad: 0.0557 (0.0561) time: 0.3752 data: 0.0040 max mem: 3957 +train: [19] [360/400] eta: 0:00:16 lr: 0.000000 loss: 3.0566 (3.0696) grad: 0.0547 (0.0561) time: 0.3818 data: 0.0041 max mem: 3957 +train: [19] [380/400] eta: 0:00:08 lr: 0.000000 loss: 3.0887 (3.0703) grad: 0.0550 (0.0561) time: 0.4066 data: 0.0046 max mem: 3957 +train: [19] [399/400] eta: 0:00:00 lr: 0.000000 loss: 3.0765 (3.0694) grad: 0.0583 (0.0563) time: 0.3797 data: 0.0044 max mem: 3957 +train: [19] Total time: 0:02:40 (0.4013 s / it) +train: [19] Summary: lr: 0.000000 loss: 3.0765 (3.0694) grad: 0.0583 (0.0563) +eval (validation): [19] [ 0/85] eta: 0:05:11 time: 3.6679 data: 3.3659 max mem: 3957 +eval (validation): [19] [20/85] eta: 0:00:34 time: 0.3713 data: 0.0035 max mem: 3957 +eval (validation): [19] [40/85] eta: 0:00:20 time: 0.3763 data: 0.0046 max mem: 3957 +eval (validation): [19] [60/85] eta: 0:00:10 time: 0.3614 data: 0.0044 max mem: 3957 +eval (validation): [19] [80/85] eta: 0:00:02 time: 0.3383 data: 0.0042 max mem: 3957 +eval (validation): [19] [84/85] eta: 0:00:00 time: 0.3263 data: 0.0040 max mem: 3957 +eval (validation): [19] Total time: 0:00:34 (0.4014 s / it) +cv: [19] best hparam: (50, 1.0) (048) ('048_lr5.0e+01_wd1.0e+00') loss: 2.985 acc: 0.131 f1: 0.067 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__linear/checkpoint-best.pth +evaluating last checkpoint: experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__linear/checkpoint-last.pth +eval model info: +{"score": 0.13104466592838687, "hparam": [50, 1.0], "hparam_id": 48, "epoch": 19, "is_best": true, "best_score": 0.13104466592838687} +eval (train): [20] [ 0/509] eta: 0:29:15 time: 3.4497 data: 3.1684 max mem: 3957 +eval (train): [20] [ 20/509] eta: 0:03:55 time: 0.3331 data: 0.0038 max mem: 3957 +eval (train): [20] [ 40/509] eta: 0:03:14 time: 0.3434 data: 0.0040 max mem: 3957 +eval (train): [20] [ 60/509] eta: 0:02:54 time: 0.3390 data: 0.0041 max mem: 3957 +eval (train): [20] [ 80/509] eta: 0:02:42 time: 0.3415 data: 0.0046 max mem: 3957 +eval (train): [20] [100/509] eta: 0:02:33 time: 0.3667 data: 0.0044 max mem: 3957 +eval (train): [20] [120/509] eta: 0:02:26 time: 0.3830 data: 0.0049 max mem: 3957 +eval (train): [20] [140/509] eta: 0:02:17 time: 0.3455 data: 0.0044 max mem: 3957 +eval (train): [20] [160/509] eta: 0:02:08 time: 0.3314 data: 0.0047 max mem: 3957 +eval (train): [20] [180/509] eta: 0:01:59 time: 0.3442 data: 0.0039 max mem: 3957 +eval (train): [20] [200/509] eta: 0:01:52 time: 0.3444 data: 0.0043 max mem: 3957 +eval (train): [20] [220/509] eta: 0:01:44 time: 0.3380 data: 0.0043 max mem: 3957 +eval (train): [20] [240/509] eta: 0:01:36 time: 0.3545 data: 0.0044 max mem: 3957 +eval (train): [20] [260/509] eta: 0:01:29 time: 0.3474 data: 0.0044 max mem: 3957 +eval (train): [20] [280/509] eta: 0:01:21 time: 0.3412 data: 0.0048 max mem: 3957 +eval (train): [20] [300/509] eta: 0:01:14 time: 0.3191 data: 0.0043 max mem: 3957 +eval (train): [20] [320/509] eta: 0:01:06 time: 0.3245 data: 0.0040 max mem: 3957 +eval (train): [20] [340/509] eta: 0:00:59 time: 0.3214 data: 0.0043 max mem: 3957 +eval (train): [20] [360/509] eta: 0:00:52 time: 0.3177 data: 0.0044 max mem: 3957 +eval (train): [20] [380/509] eta: 0:00:44 time: 0.3214 data: 0.0043 max mem: 3957 +eval (train): [20] [400/509] eta: 0:00:37 time: 0.3503 data: 0.0044 max mem: 3957 +eval (train): [20] [420/509] eta: 0:00:30 time: 0.3211 data: 0.0043 max mem: 3957 +eval (train): [20] [440/509] eta: 0:00:23 time: 0.3534 data: 0.0045 max mem: 3957 +eval (train): [20] [460/509] eta: 0:00:16 time: 0.3364 data: 0.0041 max mem: 3957 +eval (train): [20] [480/509] eta: 0:00:10 time: 0.3230 data: 0.0043 max mem: 3957 +eval (train): [20] [500/509] eta: 0:00:03 time: 0.3264 data: 0.0044 max mem: 3957 +eval (train): [20] [508/509] eta: 0:00:00 time: 0.3033 data: 0.0041 max mem: 3957 +eval (train): [20] Total time: 0:02:55 (0.3457 s / it) +eval (validation): [20] [ 0/85] eta: 0:04:41 time: 3.3141 data: 3.0927 max mem: 3957 +eval (validation): [20] [20/85] eta: 0:00:33 time: 0.3674 data: 0.0163 max mem: 3957 +eval (validation): [20] [40/85] eta: 0:00:19 time: 0.3366 data: 0.0037 max mem: 3957 +eval (validation): [20] [60/85] eta: 0:00:09 time: 0.3475 data: 0.0045 max mem: 3957 +eval (validation): [20] [80/85] eta: 0:00:01 time: 0.3331 data: 0.0044 max mem: 3957 +eval (validation): [20] [84/85] eta: 0:00:00 time: 0.3203 data: 0.0043 max mem: 3957 +eval (validation): [20] Total time: 0:00:32 (0.3825 s / it) +eval (test): [20] [ 0/85] eta: 0:04:56 time: 3.4842 data: 3.2101 max mem: 3957 +eval (test): [20] [20/85] eta: 0:00:33 time: 0.3683 data: 0.0040 max mem: 3957 +eval (test): [20] [40/85] eta: 0:00:19 time: 0.3378 data: 0.0036 max mem: 3957 +eval (test): [20] [60/85] eta: 0:00:10 time: 0.3472 data: 0.0049 max mem: 3957 +eval (test): [20] [80/85] eta: 0:00:01 time: 0.3405 data: 0.0043 max mem: 3957 +eval (test): [20] [84/85] eta: 0:00:00 time: 0.3190 data: 0.0037 max mem: 3957 +eval (test): [20] Total time: 0:00:32 (0.3860 s / it) +eval (testid): [20] [ 0/82] eta: 0:04:37 time: 3.3783 data: 3.1415 max mem: 3957 +eval (testid): [20] [20/82] eta: 0:00:29 time: 0.3326 data: 0.0051 max mem: 3957 +eval (testid): [20] [40/82] eta: 0:00:17 time: 0.3356 data: 0.0048 max mem: 3957 +eval (testid): [20] [60/82] eta: 0:00:08 time: 0.3312 data: 0.0039 max mem: 3957 +eval (testid): [20] [80/82] eta: 0:00:00 time: 0.3043 data: 0.0041 max mem: 3957 +eval (testid): [20] [81/82] eta: 0:00:00 time: 0.2945 data: 0.0039 max mem: 3957 +eval (testid): [20] Total time: 0:00:29 (0.3644 s / it) +evaluating best checkpoint: experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__linear/checkpoint-best.pth +eval model info: +{"score": 0.13104466592838687, "hparam": [50, 1.0], "hparam_id": 48, "epoch": 19, "is_best": true, "best_score": 0.13104466592838687} +eval (train): [20] [ 0/509] eta: 0:29:10 time: 3.4389 data: 3.1971 max mem: 3957 +eval (train): [20] [ 20/509] eta: 0:04:07 time: 0.3603 data: 0.0053 max mem: 3957 +eval (train): [20] [ 40/509] eta: 0:03:19 time: 0.3405 data: 0.0041 max mem: 3957 +eval (train): [20] [ 60/509] eta: 0:03:01 time: 0.3616 data: 0.0053 max mem: 3957 +eval (train): [20] [ 80/509] eta: 0:02:47 time: 0.3467 data: 0.0034 max mem: 3957 +eval (train): [20] [100/509] eta: 0:02:34 time: 0.3306 data: 0.0044 max mem: 3957 +eval (train): [20] [120/509] eta: 0:02:23 time: 0.3249 data: 0.0040 max mem: 3957 +eval (train): [20] [140/509] eta: 0:02:14 time: 0.3350 data: 0.0041 max mem: 3957 +eval (train): [20] [160/509] eta: 0:02:06 time: 0.3454 data: 0.0045 max mem: 3957 +eval (train): [20] [180/509] eta: 0:01:58 time: 0.3392 data: 0.0045 max mem: 3957 +eval (train): [20] [200/509] eta: 0:01:50 time: 0.3456 data: 0.0045 max mem: 3957 +eval (train): [20] [220/509] eta: 0:01:42 time: 0.3347 data: 0.0044 max mem: 3957 +eval (train): [20] [240/509] eta: 0:01:35 time: 0.3285 data: 0.0044 max mem: 3957 +eval (train): [20] [260/509] eta: 0:01:27 time: 0.3468 data: 0.0045 max mem: 3957 +eval (train): [20] [280/509] eta: 0:01:20 time: 0.3534 data: 0.0051 max mem: 3957 +eval (train): [20] [300/509] eta: 0:01:14 time: 0.3713 data: 0.0045 max mem: 3957 +eval (train): [20] [320/509] eta: 0:01:06 time: 0.3212 data: 0.0043 max mem: 3957 +eval (train): [20] [340/509] eta: 0:00:59 time: 0.3529 data: 0.0044 max mem: 3957 +eval (train): [20] [360/509] eta: 0:00:52 time: 0.3284 data: 0.0045 max mem: 3957 +eval (train): [20] [380/509] eta: 0:00:45 time: 0.3392 data: 0.0044 max mem: 3957 +eval (train): [20] [400/509] eta: 0:00:38 time: 0.3482 data: 0.0043 max mem: 3957 +eval (train): [20] [420/509] eta: 0:00:31 time: 0.3410 data: 0.0044 max mem: 3957 +eval (train): [20] [440/509] eta: 0:00:24 time: 0.3363 data: 0.0044 max mem: 3957 +eval (train): [20] [460/509] eta: 0:00:17 time: 0.3798 data: 0.0044 max mem: 3957 +eval (train): [20] [480/509] eta: 0:00:10 time: 0.3260 data: 0.0043 max mem: 3957 +eval (train): [20] [500/509] eta: 0:00:03 time: 0.3345 data: 0.0044 max mem: 3957 +eval (train): [20] [508/509] eta: 0:00:00 time: 0.3304 data: 0.0043 max mem: 3957 +eval (train): [20] Total time: 0:02:58 (0.3500 s / it) +eval (validation): [20] [ 0/85] eta: 0:04:32 time: 3.2104 data: 2.9554 max mem: 3957 +eval (validation): [20] [20/85] eta: 0:00:33 time: 0.3756 data: 0.0046 max mem: 3957 +eval (validation): [20] [40/85] eta: 0:00:18 time: 0.3144 data: 0.0038 max mem: 3957 +eval (validation): [20] [60/85] eta: 0:00:09 time: 0.3686 data: 0.0045 max mem: 3957 +eval (validation): [20] [80/85] eta: 0:00:01 time: 0.3632 data: 0.0043 max mem: 3957 +eval (validation): [20] [84/85] eta: 0:00:00 time: 0.3519 data: 0.0041 max mem: 3957 +eval (validation): [20] Total time: 0:00:33 (0.3907 s / it) +eval (test): [20] [ 0/85] eta: 0:04:37 time: 3.2689 data: 3.0049 max mem: 3957 +eval (test): [20] [20/85] eta: 0:00:31 time: 0.3525 data: 0.0347 max mem: 3957 +eval (test): [20] [40/85] eta: 0:00:18 time: 0.3386 data: 0.0037 max mem: 3957 +eval (test): [20] [60/85] eta: 0:00:09 time: 0.3231 data: 0.0037 max mem: 3957 +eval (test): [20] [80/85] eta: 0:00:01 time: 0.3282 data: 0.0041 max mem: 3957 +eval (test): [20] [84/85] eta: 0:00:00 time: 0.3143 data: 0.0039 max mem: 3957 +eval (test): [20] Total time: 0:00:31 (0.3703 s / it) +eval (testid): [20] [ 0/82] eta: 0:04:11 time: 3.0611 data: 2.8193 max mem: 3957 +eval (testid): [20] [20/82] eta: 0:00:27 time: 0.3165 data: 0.0112 max mem: 3957 +eval (testid): [20] [40/82] eta: 0:00:15 time: 0.3058 data: 0.0035 max mem: 3957 +eval (testid): [20] [60/82] eta: 0:00:07 time: 0.3078 data: 0.0034 max mem: 3957 +eval (testid): [20] [80/82] eta: 0:00:00 time: 0.3003 data: 0.0039 max mem: 3957 +eval (testid): [20] [81/82] eta: 0:00:00 time: 0.2905 data: 0.0038 max mem: 3957 +eval (testid): [20] Total time: 0:00:28 (0.3430 s / it) +eval results: + +| model | repr | clf | dataset | ckpt | epoch | lr | wd | hparam_id | hparam | split | loss | acc | acc_std | f1 | f1_std | +|:---------|:-------|:-------|:-------------|:-------|--------:|------:|-----:|------------:|:----------|:-----------|-------:|--------:|----------:|---------:|----------:| +| flat_mae | patch | linear | nsd_cococlip | best | 19 | 0.015 | 0.05 | 48 | [50, 1.0] | train | 2.9368 | 0.14745 | 0.0016629 | 0.083596 | 0.0012394 | +| flat_mae | patch | linear | nsd_cococlip | best | 19 | 0.015 | 0.05 | 48 | [50, 1.0] | validation | 2.9848 | 0.13104 | 0.0037783 | 0.067277 | 0.002615 | +| flat_mae | patch | linear | nsd_cococlip | best | 19 | 0.015 | 0.05 | 48 | [50, 1.0] | test | 2.972 | 0.13377 | 0.0036251 | 0.062097 | 0.0023359 | +| flat_mae | patch | linear | nsd_cococlip | best | 19 | 0.015 | 0.05 | 48 | [50, 1.0] | testid | 2.997 | 0.12473 | 0.0040536 | 0.069677 | 0.0029145 | + + +done! total time: 1:12:11 diff --git a/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__linear/train_log.json b/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__linear/train_log.json new file mode 100644 index 0000000000000000000000000000000000000000..df01e1306b88ad9ca14ebe0648e49cb423f27392 --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/nsd_cococlip__patch__linear/train_log.json @@ -0,0 +1,20 @@ +{"epoch": 0, "train/lr": 2.987987987987988e-05, "train/loss": 3.158127340078354, "train/grad": 0.06456890976056456, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.178284912109375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.178197021484375, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.178072509765625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.177939453125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.177796630859375, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.177601318359375, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.17738525390625, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.177142333984375, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.17685546875, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.17649658203125, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.176148681640625, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.17568603515625, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.175216064453125, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.1744775390625, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.173756103515625, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.17302978515625, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.172109375, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.1710791015625, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.16984375, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.1686767578125, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.16720947265625, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.165614013671875, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.163970947265625, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.1620556640625, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.160191650390625, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.1579052734375, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.1559521484375, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.154290771484375, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.152232666015625, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.150010986328125, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.148233642578125, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.14673095703125, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.145020751953125, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.14369140625, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.142242431640625, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.141038818359375, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.1398681640625, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.138948974609375, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.138057861328125, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.13716552734375, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.136561279296875, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.1362255859375, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.136014404296875, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.135958251953125, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.136171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.1365625, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.137235107421875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.1380908203125, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.1391961669921873, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.009883674923330546, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.009880914215464144, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.009876600904390216, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.00987217852845788, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.009867731733247637, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.009861635356210173, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.00985456296009943, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.009846677512396127, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.009836549782194197, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.009825458510313183, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.009814545097760856, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.009797716753091663, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.00978074643528089, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.009756152185145766, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.009731916461605579, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.009708017059601844, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.009677510692272335, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.009640123122371733, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.009596812520176173, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.009555271898861975, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.009502482085954398, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.009447094118222595, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.00938468443462625, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.009316946840845048, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.009245777023024856, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.009163052041549236, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.009092298925388605, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.00903128007426858, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.008954032310284674, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.00887168726650998, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.008806010782718659, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.008754220476839691, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.008692731051705777, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.008645461909472942, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.008598051713779569, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.008557961748447269, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.00852301383158192, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.008496133813168853, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.008473627760540694, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.008456123168580234, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.008449906385503709, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.008450791351497173, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.008459012578241528, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.008474356371443718, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.008502022589091211, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.008541430430486798, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.008582774577662348, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.008638544688001275, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.008692182525992393, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1782498359680176, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.177994728088379, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.177565336227417, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1771388053894043, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.176736831665039, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1761579513549805, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.175485610961914, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1747708320617676, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1738128662109375, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1727633476257324, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.171795606613159, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.170285224914551, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1688220500946045, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1667251586914062, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1646828651428223, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1627464294433594, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.160280704498291, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.157418966293335, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1542608737945557, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.1513495445251465, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.147907257080078, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.144508123397827, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.1409645080566406, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.137510061264038, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.1343374252319336, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.1312084197998047, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.129007577896118, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.1274805068969727, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.1260204315185547, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.1250669956207275, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.124736785888672, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.1246845722198486, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.124873161315918, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.125199317932129, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.1256511211395264, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.126134157180786, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.126589059829712, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.1269261837005615, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.127174139022827, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.1271910667419434, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.1268811225891113, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.1263668537139893, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.1253907680511475, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1243557929992676, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.122767210006714, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1201250553131104, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1166462898254395, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1120364665985107, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1094818115234375, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.052233296419342934, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.05149501661129568, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.0518641565153193, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.05094130675526024, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.0518641565153193, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.05370985603543743, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.05352528608342562, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.055001845699520116, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.055740125507567365, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.055740125507567365, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.056847545219638244, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.05813953488372093, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.05998523440383906, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06312292358803986, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06496862310815799, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.0651531930601698, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06736803248431156, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06847545219638243, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.07013658176448874, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.07124400147655961, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.07198228128460686, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.07290513104466592, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.07290513104466592, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.07419712070874862, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.07087486157253599, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.06866002214839424, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.06847545219638243, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.06847545219638243, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.06459948320413436, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.0636766334440753, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.06349206349206349, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.0636766334440753, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.06386120339608711, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.0636766334440753, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.0636766334440753, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.06349206349206349, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.06349206349206349, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.06349206349206349, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.06349206349206349, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.06349206349206349, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.0636766334440753, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.06330749354005168, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.0636766334440753, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.06533776301218161, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.06866002214839424, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.09210040605389443, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.08637873754152824, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.07936507936507936, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.07936507936507936, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.008046717309823958, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.007962687191897822, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.008775338477594057, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.008689957869827288, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.009394524359012968, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.010512659065590568, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.010501398766662557, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.011340459003109994, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.011919314611650121, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.012166257938362299, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.01235854637236277, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.012566538885870593, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.012584891783653898, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.012334926169991064, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.012366492540320054, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.011322166936375203, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.010460279600402834, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.009614655648038995, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.00960924802198259, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.009938366022472606, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.010191928110303108, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.010337852257926713, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.009780204167264191, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.01073891106915278, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.010326951986559925, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.01008197693128504, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.009996292973759495, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.009508516109650096, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.007904899844981729, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.006430932403472449, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.005900064924822239, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.005576643514779519, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.005595688270665109, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.005389410809556947, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.005389774961765348, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.00517939273657259, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.005179064721841408, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.005177783121513583, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.00517809891098142, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.005178739732164899, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.005388040449586914, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.005707628645335204, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.006619853313108753, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.007944654353081197, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.011059749760528342, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.02167053525395138, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.02131610339204568, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.014192835950334971, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.012293420299165773, "id_best": 45, "lr_best": 0.0093, "wd_best": 0.05, "train/loss_best": 3.1365625, "validation/loss_best": 3.1201250553131104, "validation/acc_best": 0.09210040605389443, "validation/f1_best": 0.02167053525395138} +{"epoch": 1, "train/lr": 8.993993993993998e-05, "train/loss": 3.143274347782135, "train/grad": 0.06123608488589525, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.17474609375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.174288330078125, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.173519287109375, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.17263671875, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.17184814453125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.1706982421875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.169425048828125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.168118896484375, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.1663427734375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.164544677734375, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.16286376953125, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.160379638671875, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.158260498046875, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.15518310546875, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.15239013671875, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.15010009765625, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.147266845703125, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.144365234375, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.14151611328125, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.139271240234375, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.136895751953125, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.1351904296875, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.13357177734375, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.1323291015625, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.131402587890625, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.130726318359375, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.130423583984375, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.13012939453125, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.13009521484375, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.12993408203125, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.129952392578125, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.129931640625, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.1298974609375, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.1300341796875, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.12998291015625, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.13012939453125, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.130283203125, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.1303564453125, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.130478515625, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.13023681640625, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.130152587890625, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.129892578125, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.129627685546875, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.129512939453125, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.1296533203125, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.1302996826171876, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.1315692138671873, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.13397216796875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.1360198974609377, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.009784668684005737, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.009766696703154594, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.00973674225853756, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.009707752261310815, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.009678952696267515, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.009639384362380952, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.009595117545686663, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.00954593151109293, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.00948359799804166, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.009417922184802592, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.009355133685749023, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.009263109064195306, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.009177478570491076, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.009060117579065264, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.008954742634668946, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.00885905315168202, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.008746675695292652, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.008627666237298399, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.008509673199150712, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.008415603206958621, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.00831878098193556, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.00823707235045731, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.008166526257991791, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.008111289362423122, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.008072190817911178, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.00804387774085626, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.008030868950299919, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.008027104039210826, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.008028560630045832, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.008036567952949554, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.008048043842427433, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.008059869694989175, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.00807767682010308, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.008095314605161547, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.008117660817224532, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.008143174091819673, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.008172664935700595, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.008202564956154674, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.008239396554417909, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.008291525843087583, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.008340285022277384, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.008391026149038226, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.008471018187701702, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.008560280895326287, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.008685762295499444, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.008846390771213918, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.008999709805939346, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.009197451898362487, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.00936020295135677, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.173346519470215, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.172415256500244, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.170893669128418, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.169419765472412, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.167987823486328, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1660521030426025, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1639211177825928, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1616671085357666, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1588351726531982, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1559579372406006, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1533379554748535, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.149661064147949, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.146415948867798, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.14225697517395, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.138795852661133, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1359715461730957, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1329660415649414, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1301488876342773, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.12782883644104, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.12629771232605, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.1250269412994385, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.124260187149048, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.1237692832946777, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.1235270500183105, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.1233789920806885, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.1232869625091553, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.123197555541992, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.123114585876465, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.1229748725891113, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.122821092605591, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.1226792335510254, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.1226344108581543, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.1225898265838623, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.1226344108581543, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.1227095127105713, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.1226038932800293, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.1221089363098145, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.121190071105957, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.1196446418762207, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.116881847381592, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.1141810417175293, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.111668109893799, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.1086912155151367, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1060853004455566, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1030776500701904, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.101362705230713, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1033661365509033, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.110494613647461, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1187937259674072, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.055924695459579184, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.05555555555555555, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.05740125507567368, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.05813953488372093, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.060538944259874494, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06293835363602805, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06459948320413436, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06589147286821706, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06773717238833518, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06939830195644149, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.07069029162052418, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.07198228128460686, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.07290513104466592, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.0725359911406423, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.073827980804725, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.07364341085271318, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06847545219638243, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.0681063122923588, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.0681063122923588, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.06699889258028793, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.06441491325212255, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.06386120339608711, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.06312292358803986, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.06293835363602805, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.06293835363602805, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.06293835363602805, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.06293835363602805, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.06312292358803986, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.06312292358803986, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.06312292358803986, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.06349206349206349, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.06349206349206349, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.06349206349206349, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.06423034330011074, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.0664451827242525, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.07308970099667775, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.07715023994093761, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.07973421926910298, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.0799187892211148, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.08102620893318568, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.0799187892211148, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.0812107788851975, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.08342561830933924, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.0799187892211148, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.07050572166851236, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.06773717238833518, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.011925755964923575, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.011997618365150084, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.012406268211250128, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.0125304941142962, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.01263784213227838, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.012706125174231064, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.012211368948495826, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.01158526947383068, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.010403543655929043, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.01011630938700838, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.01009475221551148, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.010475000937282437, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.010824827717428183, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.009917567046404488, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.010711175616835994, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.010736616233120338, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.009984062033281582, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.010010298848800897, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.009913268270716783, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.009032755874153723, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.007771344854338182, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.00679505561348627, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.006142257768599029, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.00583993083993084, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.005675027977649534, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.005672556609565574, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.005674196286047619, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.005858176561773835, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.005688805916716155, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.005693031809929121, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.005724843454201252, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.005536996663067655, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.005539018682783266, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.005731246857317848, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.005898754354959523, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.006031833125130846, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.0077360044412336975, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.01032481928481155, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.014266960383602525, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.01605609714020322, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.018689226313171037, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.01998844785542781, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.019945954545393458, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.01870444749506402, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.02253345965645955, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.023365942580827238, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.018767177775863193, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.014907890898474538, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.01420143121499882, "id_best": 45, "lr_best": 0.0093, "wd_best": 0.05, "train/loss_best": 3.1302996826171876, "validation/loss_best": 3.101362705230713, "validation/acc_best": 0.08342561830933924, "validation/f1_best": 0.023365942580827238} +{"epoch": 2, "train/lr": 0.00014999999999999988, "train/loss": 3.1327569484710693, "train/grad": 0.06079714616760611, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.16983154296875, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.1686181640625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.166600341796875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.164710693359375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.162838134765625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.160347900390625, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.15787841796875, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.155179443359375, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.15194580078125, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.148883056640625, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.146248779296875, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.142783203125, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.1399609375, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.136798095703125, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.1344189453125, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.132679443359375, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.131114501953125, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.129749755859375, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.12883056640625, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.128260498046875, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.127864990234375, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.127705078125, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.127410888671875, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.1273193359375, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.127110595703125, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.126822509765625, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.126624755859375, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.126453857421875, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.126160888671875, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.12578369140625, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.125333251953125, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.124942626953125, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.124439697265625, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.123876953125, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.12346923828125, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.122803955078125, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.122181396484375, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.1214697265625, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.12045654296875, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.1190789794921874, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.1176934814453126, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.116358642578125, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.114906005859375, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.11391357421875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.1132965087890625, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.113662109375, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.1154693603515624, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.1197991943359376, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.12500732421875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.00962627750588581, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.009581641454715281, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.009509405712597072, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.009440177073702215, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.009373582613188774, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.009284816021099686, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.009189119599759578, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.009089195686392486, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.008968975502066314, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.00885242538060993, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.008749052886851133, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.00861360585782677, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.008502490038517862, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.008369926537852734, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.008274540933780373, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.00820458818692714, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.008140675541944802, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.008091205949895083, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.008059264754410832, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.008043574593029916, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.008035374791361391, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.008035049261525273, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.008039414898958057, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.008046365433838219, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.008054983057081699, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.008066858821548522, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.008078140651341527, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.00808931384468451, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.008105527425650507, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.008127704442013056, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.008149312420282512, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.008170246325898916, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.00820131299784407, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.008233578000217677, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.00827687197132036, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.008326054934877902, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.008382345258723944, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.00843892783857882, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.008503822193015367, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.008600419070571661, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.008692596354521812, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.008784621264785528, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.008918019731063397, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.009039696112740785, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.009184360650833697, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.009362368111032993, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.009572162814438344, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.00990784463705495, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.010233760830014944, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.166200876235962, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1643927097320557, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1616082191467285, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.158973455429077, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.156508445739746, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.153332471847534, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1500794887542725, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1468145847320557, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.143054246902466, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1396217346191406, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1367857456207275, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1333351135253906, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1307601928710938, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1280767917633057, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1263513565063477, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.125209093093872, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.124281883239746, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.123640298843384, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1232004165649414, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.1229379177093506, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.122657537460327, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.122408866882324, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.122135639190674, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.1218647956848145, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.1215505599975586, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.1212055683135986, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.1208510398864746, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.1205105781555176, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.1200222969055176, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.1193013191223145, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.1184887886047363, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.1176156997680664, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.116187572479248, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.1147642135620117, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.113112449645996, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.1118667125701904, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.1111514568328857, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.111067771911621, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.110971689224243, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.110032081604004, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.1088504791259766, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.108055353164673, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.107980728149414, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.11021089553833, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1156625747680664, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.121121883392334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.12204909324646, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1201276779174805, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1184639930725098, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06127722406792174, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.062200073827980804, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.0651531930601698, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06718346253229975, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.07050572166851236, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.07013658176448874, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.07179771133259505, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.07438169066076043, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.07272056109265411, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06866002214839424, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06829088224437062, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06681432262827612, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06570690291620525, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06312292358803986, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.06275378368401624, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.06293835363602805, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.06293835363602805, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.06312292358803986, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.06312292358803986, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.06312292358803986, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.06312292358803986, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.06312292358803986, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.0636766334440753, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.067921742340347, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.0725359911406423, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.07862679955703211, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.07161314138058324, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.07364341085271318, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.073827980804725, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.07401255075673681, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.07585825027685493, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.07807308970099668, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.08139534883720931, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.08619416758951642, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.08324104835732743, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.08361018826135105, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.07954964931709117, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.07069029162052418, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.013052189854480596, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.012680811730417752, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.011890479740521131, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.01147212987839505, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.01143038929461193, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.012689440827125253, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.011894158014520739, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.011827800948308896, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.012697656405611636, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.01174645641054678, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.010535804331888431, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.010032590322262865, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.009572969252356915, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.008458003858082432, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.0070250434476904, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.006258708993825743, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.005852189395445958, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.005540070405814158, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.0055445574378448735, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.005543392889945591, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.005540606606377937, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.00587900910316943, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.005814901235716777, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.005959337609912592, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.006241235785757848, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.006549009976055851, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.006406908416639226, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.006145627200114945, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.005704242117293122, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.005343287221778841, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.005343370891553296, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.005540606606377937, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.005680197196093911, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.006580160386844479, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.009221443880280055, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.010533694359604459, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.012318700870628375, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.010896828201785863, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.011107486671647992, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.010765749746846158, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.01165382280974788, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.014175021312345583, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.019413998214470762, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.028540515851413695, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.032036748666402944, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.026705940173847326, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.029042866415082535, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.030428534010849686, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.027764633017784025, "id_best": 44, "lr_best": 0.0078, "wd_best": 0.05, "train/loss_best": 3.1132965087890625, "validation/loss_best": 3.1156625747680664, "validation/acc_best": 0.08619416758951642, "validation/f1_best": 0.032036748666402944} +{"epoch": 3, "train/lr": 0.0002100600600600602, "train/loss": 3.125407291650772, "train/grad": 0.060766175668686626, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.16091552734375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.15890380859375, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.15569091796875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.152969970703125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.1503125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.14710205078125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.14395263671875, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.14104736328125, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.13781005859375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.135137939453125, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.132991943359375, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.130841064453125, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.129339599609375, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.127977294921875, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.12714599609375, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.126689453125, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.126434326171875, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.12619873046875, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.125946044921875, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.125772705078125, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.125517578125, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.1252197265625, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.125078125, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.124615478515625, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.124219970703125, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.12372314453125, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.12308349609375, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.122664794921875, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.12192138671875, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.120965576171875, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.1201220703125, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.119298095703125, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.118182373046875, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.116971435546875, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.11563232421875, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.11400634765625, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.112354736328125, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.11088623046875, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.1093804931640623, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.1080914306640626, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.1075238037109374, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.10728271484375, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.106832275390625, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.1069818115234376, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.107559814453125, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.1099078369140627, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.112845458984375, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.1174945068359374, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.1234173583984375, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.009293253892101347, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.009220963942352682, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.009106896615121514, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.009001329024322331, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.008904982663225383, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008785682693123818, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.008666302734054625, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.008550536565016954, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.008424877673387527, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.008318599464837461, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.00823735662503168, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.008149228398688138, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.008091445167083293, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.008042815404478461, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.00801894414005801, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.008008373563643544, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.008003870027605444, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.008005113657563925, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.00800991640193388, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.008015015388373285, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.008022243559826165, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.008030265765264631, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.008039736188948154, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.008050865589175372, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.008062920288648457, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.008079069850500673, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.008094669398851694, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.008111249404028058, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.00813513572094962, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.008165063911583274, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.00819526392966509, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.008224904248490929, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.008267939565703273, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.008309435553383083, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.00836123644374311, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.008418421607930214, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.008487655967473983, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.008565193170215934, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.008661597184836865, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.008800700544379652, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.008926911409944296, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.00905919991666451, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.009270712749566883, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.009491813567001373, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.009777434389106929, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.010100754180457442, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.010368148975539953, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.010726501180324704, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.011092999815009535, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1578259468078613, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1553351879119873, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1515398025512695, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.14817214012146, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1452083587646484, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.14159893989563, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.138211965560913, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1351146697998047, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1319568157196045, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.12947154045105, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.127692461013794, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.125844717025757, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1247079372406006, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.123739719390869, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.123190402984619, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1228396892547607, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1225345134735107, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1222567558288574, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1220173835754395, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.121809959411621, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.1215929985046387, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.1213815212249756, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.1211607456207275, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.120882511138916, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.120542287826538, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.1200172901153564, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.11942458152771, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.11873459815979, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.1176373958587646, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.1160495281219482, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.114438533782959, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.1128313541412354, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.1105854511260986, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.1085004806518555, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.105820894241333, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.1026923656463623, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.0989153385162354, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.0958240032196045, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.094421148300171, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.094522476196289, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.092641830444336, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.0889627933502197, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.083017587661743, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.0778114795684814, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.0737202167510986, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.0801198482513428, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1073782444000244, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.119391441345215, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.10052490234375, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06662975267626431, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06884459210040605, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.07069029162052418, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.07124400147655961, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.07345884090070137, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.07401255075673681, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.07179771133259505, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06829088224437062, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06902916205241787, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06681432262827612, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06681432262827612, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06423034330011074, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06386120339608711, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06312292358803986, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06312292358803986, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.0636766334440753, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06404577334809892, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.06478405315614617, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.06423034330011074, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.06496862310815799, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.06607604282022887, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.06718346253229975, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.0681063122923588, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.0681063122923588, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.067921742340347, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.06829088224437062, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.06773717238833518, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.0681063122923588, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.06847545219638243, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.06939830195644149, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.07198228128460686, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.07511997046880768, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.07751937984496124, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.07936507936507936, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.08176448874123293, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.0828719084533038, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.08342561830933924, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.08194905869324474, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.08342561830933924, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.08416389811738649, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.08508674787744555, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.08933185677371724, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.08970099667774087, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.0710594315245478, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.061461794019933555, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.06884459210040605, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.08970099667774087, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.010903539221431524, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.011922050578873557, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.012374182903984227, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.011430639639365928, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.012332638162083603, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.012108681473063057, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.010950441861135786, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.01001533708955442, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.010140036525192856, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.009412176258691233, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.00882106147881268, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.007665895167384751, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.006865811776678432, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.006127628453918785, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.0061724485946754795, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.006174226595495844, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.006135649445062699, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.00657858702426644, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.007093764758218701, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.0074512483790169295, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.007532054815497184, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.007982120051085569, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.008399295838115469, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.008859990094187314, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.009079848343428554, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.009077660917721416, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.009032172963571831, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.009157086634918163, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.00900117378356636, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.009355598978941686, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.011452384041019717, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.013330408516470979, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.01567649597695539, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.018316015189219458, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.019050149856744168, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.01996335517596187, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.021260567350944202, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.021044050299992314, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.02172224597074296, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.02455325805782362, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.027059119254096903, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.02771480299286086, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.028279238624023612, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.03278803720113183, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.03686821592309747, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.02855360845969344, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.017695719601893464, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.023192021255485366, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.03020661201157379, "id_best": 44, "lr_best": 0.0078, "wd_best": 0.05, "train/loss_best": 3.107559814453125, "validation/loss_best": 3.0737202167510986, "validation/acc_best": 0.08970099667774087, "validation/f1_best": 0.03686821592309747} +{"epoch": 4, "train/lr": 0.0002701201201201201, "train/loss": 3.1209481239318846, "train/grad": 0.0612403004989028, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.154840087890625, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.1523486328125, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.1486767578125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.1455224609375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.14283447265625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.1397998046875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.13710693359375, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.1348681640625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.1326025390625, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.13117919921875, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.130277099609375, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.129447021484375, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.129049072265625, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.128648681640625, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.128389892578125, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.128297119140625, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.12811767578125, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.127816162109375, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.127529296875, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.127200927734375, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.1268212890625, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.1264208984375, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.12587158203125, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.12514892578125, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.124449462890625, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.1235009765625, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.12250732421875, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.12161865234375, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.12028076171875, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.118599853515625, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.117047119140625, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.11554931640625, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.113638916015625, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.1118701171875, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.109610595703125, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.107313232421875, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.1049505615234376, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.102786865234375, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.1008465576171873, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.0988763427734374, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.097852783203125, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.09715087890625, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.0964739990234373, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.0963153076171874, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.0976953125, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.1006768798828124, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.1031787109375, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.1060479736328124, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.1088076782226564, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.009109151794109493, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.009010913155507297, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.008867790214717388, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.008744434511754662, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.008636973863467574, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008510836933273822, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.008398058395832776, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.008302763167303056, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.008214009113144129, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.008151958470698446, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.008112367843277752, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.008078702110797167, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.008062515046913177, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.008054441947024316, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.008053260513115675, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.008055032177362592, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.008058800648432224, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.00806456862948835, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.008071440132334828, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.008078821925446391, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.008087493686471135, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.008097466959152371, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.008108970965258777, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.008121597599238157, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.008135426191147417, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.008152376189827918, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.00816912305308506, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.008185746062081308, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0082099918439053, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.008243456908967346, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.008277469780296087, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.008312568734399974, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.008364193635061383, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.008415002161636948, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.008481528609991074, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.008557298006489873, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.008651428814046085, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.008758028361480683, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.008887647623196245, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.009061417717020959, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.009210426206700505, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.00935352752916515, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.009555063911247998, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.009759946258272976, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.010065060905180872, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.010423856854904443, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.010708343132864683, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.011088235529605299, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.011461479258723557, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.149233102798462, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1463096141815186, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.142118215560913, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1386775970458984, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1358540058135986, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.132723808288574, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1301069259643555, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1280055046081543, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1261589527130127, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.124925374984741, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1241824626922607, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.123530626296997, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.123189926147461, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1228997707366943, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.12269926071167, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.122528553009033, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1223604679107666, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.122117280960083, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.121856451034546, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.121595621109009, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.1212899684906006, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.1209592819213867, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.1206374168395996, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.1202917098999023, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.1199495792388916, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.1195638179779053, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.1191654205322266, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.118687152862549, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.117788314819336, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.1162607669830322, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.1144206523895264, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.112318992614746, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.1086912155151367, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.1048123836517334, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.1000773906707764, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.096144437789917, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.093649387359619, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.093214273452759, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.0943708419799805, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.0986692905426025, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.1054580211639404, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.1120638847351074, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.11629056930542, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1176671981811523, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1175854206085205, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1115219593048096, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.099888324737549, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.0868427753448486, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.087099075317383, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.07050572166851236, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.07216685123661867, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.073827980804725, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.07124400147655961, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06884459210040605, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06829088224437062, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06718346253229975, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06496862310815799, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06386120339608711, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06386120339608711, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.0636766334440753, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.06312292358803986, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.0636766334440753, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.06718346253229975, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.07327427094868956, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.07862679955703211, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.0812107788851975, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.08250276854928018, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.08397932816537468, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.08361018826135105, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.08324104835732743, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.08508674787744555, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.08803986710963455, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.09302325581395349, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.09560723514211886, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.09283868586194167, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.09062384643779993, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.09043927648578812, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.09413067552602436, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.09616094499815431, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.09431524547803617, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.09948320413436693, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.09449981543004798, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.08896271686969362, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.0946843853820598, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.10834256183093392, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.10575858250276855, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.09542266519010704, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.011645338624306107, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.012078217166245334, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.012410423594650914, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.010858687691986307, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.01060021892308479, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.009995426817568584, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.009295394221369995, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.008207678791381354, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.006897800684020521, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.006012624894667148, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.005540070405814158, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.005595688270665109, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.005600599176746604, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.005391002822254683, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.005178417788241079, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.00517809891098142, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.00517809891098142, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.005178739732164899, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.005179064721841408, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.005165901973636297, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.005153461899114703, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.005358395580336406, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.005965427216985395, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.006721646584475928, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.011215558180860924, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.01570357360023889, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.018482780444239663, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.020883285058969938, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.023197954578297514, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.026715680374376646, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.02894040804724081, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.030761277526561936, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.03378197570162019, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.03763066518553562, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.04261947954000844, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.04348152640092263, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.037829087088957554, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.031829810502061316, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.03123605315607487, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.03568431972263351, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.04015751398572912, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.040375063972731544, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.03975758917331646, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.040042085352862494, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.04524407951499976, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.04561073365993871, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0503853825718687, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.05197234461385317, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.040891011957008026, "id_best": 46, "lr_best": 0.010799999999999999, "wd_best": 0.05, "train/loss_best": 3.1031787109375, "validation/loss_best": 3.099888324737549, "validation/acc_best": 0.10834256183093392, "validation/f1_best": 0.0503853825718687} +{"epoch": 5, "train/lr": 0.00029891323817685334, "train/loss": 3.116684274673462, "train/grad": 0.05999583533033728, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.148375244140625, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.14593994140625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.142413330078125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.139749755859375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.13767822265625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.1355517578125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.134007568359375, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.132894287109375, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.13201171875, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.131513671875, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.131331787109375, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.131070556640625, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.13090576171875, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.13074462890625, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.130504150390625, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.130311279296875, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.129979248046875, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.129630126953125, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.1290966796875, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.1286376953125, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.12800537109375, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.12726318359375, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.126419677734375, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.12541015625, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.124320068359375, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.122958984375, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.121585693359375, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.120137939453125, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.118270263671875, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.11598388671875, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.113763427734375, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.1116845703125, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.10877685546875, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.10599853515625, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.102843017578125, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.099844970703125, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.0968206787109374, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.093934326171875, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.0906109619140625, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.08679931640625, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.0848004150390627, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.0834295654296877, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.0821151733398438, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.0822378540039064, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.083920593261719, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.087204895019531, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.091333312988281, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.096307678222656, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.1024038696289065, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.008662038731854409, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.008555249441415072, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.008403262950014322, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.0082835923274979, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.008190763618331402, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008093866552226246, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.008019511920865625, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.00796766585437581, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.007927972683683037, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.007907229901757091, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.007898492554668337, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.007894377559423446, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.007895354623906314, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.00789950623176992, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.007904086918570101, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.007908779922872781, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.007914309976622463, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.007921056980267167, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.00792865441646427, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.007935896986164153, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.007944634156301618, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.007955238316208124, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.007967690138611943, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.007982788067311048, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.007999699278734625, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.008022045283578336, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.008043596688657999, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.008063929316122084, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.008093113389331847, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.008129089220892638, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.008162973620928824, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.008196087928954512, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.008247417835518718, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.008297974590677768, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.008368500543292611, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.008454237403348087, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.008564364113844931, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.008677570265717804, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.008803165203426033, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.008972170627675951, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0091367715341039, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.009297209242358804, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.009521414954215289, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.009739476735703648, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.009993269329424948, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.010278153026010841, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.010590539649128913, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.010923751851078124, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.011217121086083352, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.142096757888794, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1391515731811523, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1352078914642334, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1322381496429443, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1299962997436523, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1277408599853516, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.126046895980835, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.124835729598999, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1239004135131836, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.123293876647949, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.12294602394104, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1225781440734863, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1222877502441406, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1219451427459717, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.121609687805176, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1213090419769287, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1209185123443604, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.120469331741333, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1199567317962646, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.1194608211517334, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.118859052658081, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.118218421936035, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.117551565170288, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.116831064224243, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.1161088943481445, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.115262508392334, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.114504337310791, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.1137757301330566, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.1126561164855957, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.110990047454834, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.1089489459991455, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.1064767837524414, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.1022231578826904, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.097766637802124, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.0923995971679688, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.0878052711486816, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.084282159805298, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.082270860671997, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.080672264099121, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.07846999168396, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.0772995948791504, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.0775396823883057, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.079747438430786, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.086796998977661, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.094712495803833, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.0902533531188965, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.0781912803649902, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.0728189945220947, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.0751712322235107, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.07364341085271318, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.07290513104466592, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06995201181247693, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06755260243632337, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06902916205241787, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06718346253229975, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06681432262827612, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06423034330011074, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06404577334809892, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06386120339608711, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06386120339608711, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06423034330011074, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06404577334809892, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06441491325212255, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06478405315614617, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06589147286821706, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06681432262827612, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06847545219638243, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.0681063122923588, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.07013658176448874, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.07142857142857142, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.07069029162052418, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.07456626061277224, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.07678110003691399, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.07825765965300849, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.08139534883720931, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.08361018826135105, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.08490217792543374, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.08600959763750461, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.08508674787744555, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.0843484680693983, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.08822443706164636, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.09007013658176449, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.0932078257659653, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.09339239571797711, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.09339239571797711, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.0946843853820598, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.09726836471022518, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.10409745293466224, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.10243632336655592, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.10299003322259136, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.10686600221483943, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.10612772240679218, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.10409745293466224, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.10409745293466224, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.09874492432631968, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.10262089331856773, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.10686600221483943, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.012361243381883722, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.01149584209092771, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.010469834102855466, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.009923573073500133, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.010114695969684236, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.009505582176282222, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.008842393152165449, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.007881546581624455, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.007125096284433377, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.006773570972670127, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.006693974073360039, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.00667780037670265, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.007156171823136039, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.007023304838160331, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.0075014167776316755, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.007838338174836331, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.008349521178810845, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.008837962632517694, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.009459053682503672, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.009528555710254195, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.009932597313359192, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.011137396591986476, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.012816938215099646, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.01711110588051325, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.017406612450052577, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.016726567605531203, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.017292727821418715, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.01809868371293824, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.019571100738794752, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.02261889550984032, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.02286972833054648, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.022131408130380333, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.023644278974231072, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.024466070583231053, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.025080904275841084, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.023471060960525248, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.0212281307099489, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.023662122547396146, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.029238597725907017, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.034840769391215005, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.03416092861295818, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.03762563213516567, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.04585141376778576, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.04731380343589992, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.048654186500452466, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0505226265645382, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.050493263758482364, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.05995518771177683, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0637525002802568, "id_best": 42, "lr_best": 0.005699999999999999, "wd_best": 0.05, "train/loss_best": 3.0821151733398438, "validation/loss_best": 3.079747438430786, "validation/acc_best": 0.10686600221483943, "validation/f1_best": 0.04585141376778576} +{"epoch": 6, "train/lr": 0.0002924170901991409, "train/loss": 3.104191474914551, "train/grad": 0.06042481718584895, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.140841064453125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.138282470703125, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.134892578125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.1324267578125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.130673828125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.12902099609375, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.1278857421875, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.12706787109375, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.126566162109375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.126070556640625, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.125841064453125, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.125509033203125, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.125177001953125, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.12474609375, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.124383544921875, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.124013671875, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.123399658203125, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.122696533203125, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.12197998046875, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.121248779296875, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.120159912109375, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.1189599609375, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.117628173828125, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.1160888671875, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.114464111328125, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.11229248046875, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.11044189453125, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.10851318359375, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.105972900390625, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.102705078125, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.099627685546875, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.09693603515625, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.09312255859375, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.0896527099609377, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.0853961181640623, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.0809552001953127, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.076160888671875, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.071561279296875, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.067052001953125, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.0625091552734376, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.0603594970703125, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.0595196533203124, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.05986572265625, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.0606317138671875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.062066650390625, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.0655587768554686, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.0708587646484373, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.078197021484375, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.085404052734375, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.008514496597927064, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.008409432279877364, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.008275601339992136, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.008178252638317644, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.008110925296787173, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008048561217729002, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.008006117474287748, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.007980571282096206, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.007966006291098893, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.007960101759526878, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.00795863283565268, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.007959995742421597, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.00796217859024182, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.007966276167426258, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.007970129388850182, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.007973597394302487, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.00797783541958779, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.00798278326401487, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.007987642718944699, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.007992279671598226, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.00799807915231213, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.008004710145760327, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.008012855448760093, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.008022807030938566, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.008034984723199159, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.008053558832034468, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.008073553259018809, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.008094981363974511, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.008128549086395652, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.00817461100174114, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.008221012393478304, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.008266702499240637, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.008333724229596556, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.008396296496503055, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.00847252859501168, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.008549023277591914, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.008635925250127912, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.008726930981501936, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.008841781497467309, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.009024900039657951, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.00919777114642784, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.009370570131577551, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.009619478969834745, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.00985409935703501, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.010163718280382454, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.01054942335234955, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.010885285299737006, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.011190010998398066, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.011445382714737207, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.136908769607544, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.134209394454956, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.130794048309326, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1284360885620117, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.126774311065674, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1252329349517822, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1241719722747803, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.123469829559326, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.122912883758545, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.122542142868042, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.122288465499878, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1219351291656494, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.121642827987671, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1212422847747803, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.120851755142212, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.12048602104187, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1200332641601562, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1195011138916016, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1188900470733643, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.118319511413574, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.1176016330718994, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.1168363094329834, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.115899085998535, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.1148180961608887, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.1135239601135254, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.1117231845855713, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.1098289489746094, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.1078732013702393, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.1049132347106934, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.1010520458221436, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.0974435806274414, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.0941429138183594, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.0898895263671875, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.086303472518921, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.082465887069702, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.079486846923828, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.0780904293060303, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.0786805152893066, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.0795540809631348, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.0783350467681885, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.0767955780029297, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.0759167671203613, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.07578182220459, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.0734457969665527, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.064077138900757, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.0552585124969482, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.051412582397461, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.045872926712036, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.0440430641174316, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.07142857142857142, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06902916205241787, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06847545219638243, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06755260243632337, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06626061277224068, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06533776301218161, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06404577334809892, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06496862310815799, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06496862310815799, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06441491325212255, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06496862310815799, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06589147286821706, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.06626061277224068, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.06681432262827612, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.06773717238833518, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.06847545219638243, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.06902916205241787, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.06939830195644149, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.07032115171650055, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.07069029162052418, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.07161314138058324, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.07345884090070137, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.07807308970099668, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.08139534883720931, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.08564045773348099, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.08877814691768181, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.08822443706164636, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.08951642672572906, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.09043927648578812, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.09246954595791805, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.09505352528608342, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.09745293466223699, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.09837578442229605, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.10022148394241417, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.10188261351052048, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.1020671834625323, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.10483573274270949, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.11258767072720562, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.11332595053525286, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.11092654115909929, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.1124031007751938, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.1111111111111111, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.010891901416233639, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.010623588817910942, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.010053087863331455, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.009635619825692754, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.008869547024598348, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.008287119682908801, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.007053934191500352, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.006656185452329016, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.006277882962478921, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.006290774983421687, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.006283340562670746, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.006265532036920536, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.006657275916555527, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.007016312835896768, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.007542223526275719, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.007626668740175246, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.007423645863076006, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.00782234331329666, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.0082374985373855, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.008288164323258242, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.008960407022827164, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.00950555188939533, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.010091880152308856, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.009989020576625682, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.010055564700264426, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.010811019563249716, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.012096188022064117, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.013162830991166434, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.015617109319035602, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.022577627480495726, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.027817964762232802, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.031041935819397876, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.03377442010520488, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.03407573840818018, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.034645306281379906, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.032143247444113406, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.03265894873346197, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.03481023526287517, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.03779919038324611, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.03893742407536347, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.041391956802109296, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.044255242870927684, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.0464269893899805, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.05160854477640669, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.05991366582507868, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0522934007742742, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.04387404431556507, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0497459484246664, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.05648732498188604, "id_best": 45, "lr_best": 0.0093, "wd_best": 0.05, "train/loss_best": 3.0655587768554686, "validation/loss_best": 3.0552585124969482, "validation/acc_best": 0.11332595053525286, "validation/f1_best": 0.0522934007742742} +{"epoch": 7, "train/lr": 0.00027969249556793234, "train/loss": 3.1017267286777495, "train/grad": 0.06042140604928136, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.138045654296875, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.135882568359375, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.13330810546875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.1316748046875, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.13067626953125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.1297021484375, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.129197998046875, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.1288623046875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.1285498046875, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.128282470703125, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.12801513671875, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.127686767578125, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.1273779296875, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.126781005859375, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.126300048828125, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.125709228515625, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.12509033203125, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.12408203125, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.123076171875, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.122125244140625, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.12082763671875, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.1193212890625, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.11772216796875, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.115928955078125, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.113809814453125, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.111162109375, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.10852783203125, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.10618408203125, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.102808837890625, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.09866943359375, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.09487548828125, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.0914703369140626, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.0869512939453125, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.082872314453125, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.078099365234375, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.0734478759765627, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.0687640380859373, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.064725341796875, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.0608880615234373, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.0569549560546876, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.054871826171875, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.05402099609375, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.0543670654296875, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.0557928466796875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.0583880615234373, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.061260986328125, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.0635986328125, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.066568603515625, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.0713067626953126, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.00840866811806336, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.008321285736747086, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.008215339756570756, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.008149350031744688, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.008106916134711355, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008072683059144764, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.008054900583811104, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.008045615560840816, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.008042034488171338, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.008042356551159173, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.008044119116384536, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.008047017576172948, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.008049727028701454, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.008053300553001463, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.00805666076252237, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.008060155017301441, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.008064202815294266, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.008068929344881326, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.008073983222711831, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.008079037072602659, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.00808552437927574, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.008092595704365522, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.00810127479955554, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.008110628579743207, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.008121421898249537, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.008135500291828066, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.008150031561963261, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.008164957172702998, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.008187207011505961, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.008219077587127685, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0082518768357113, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.008285061412025244, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.008335556949023158, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.008385267369449138, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.008450655492488295, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.008520767032168806, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.008606843499001116, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.008706246397923677, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.00883629395160824, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.009023420882876963, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.00917984354076907, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.009330804741475731, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.00955602788599208, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.00978784183273092, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.01007604515645653, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.01037299538264051, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.010617134405765682, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.01095828031655401, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.011292857234366238, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.13336443901062, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1310112476348877, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1282153129577637, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.126392126083374, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1252050399780273, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1241888999938965, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.123516321182251, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1230621337890625, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.122675657272339, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.122403144836426, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.122152090072632, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.121812105178833, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.121461868286133, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1210036277770996, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1205551624298096, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.12011456489563, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.119553327560425, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1188838481903076, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.118138551712036, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.117422103881836, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.116558790206909, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.1156270503997803, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.1145617961883545, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.1133968830108643, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.1120266914367676, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.1101813316345215, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.1082704067230225, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.1062135696411133, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.10294246673584, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.0984034538269043, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.094069480895996, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.0901284217834473, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.0853283405303955, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.0814645290374756, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.077303409576416, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.0739898681640625, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.072007417678833, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.0721142292022705, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.074047565460205, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.0745315551757812, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.071425437927246, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.0685839653015137, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.0692336559295654, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.076237440109253, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.0863091945648193, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.0969576835632324, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1065213680267334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1209797859191895, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1431210041046143, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06773717238833518, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06884459210040605, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06626061277224068, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06552233296419344, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06312292358803986, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06312292358803986, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06293835363602805, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06404577334809892, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06459948320413436, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06496862310815799, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06533776301218161, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06570690291620525, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06866002214839424, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.0695828719084533, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.07013658176448874, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.07179771133259505, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.0710594315245478, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.07198228128460686, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.07290513104466592, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.07438169066076043, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.07622739018087855, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.07733480989294943, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.07936507936507936, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.08490217792543374, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.08637873754152824, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.08767072720561092, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.09007013658176449, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.08767072720561092, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.08933185677371724, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.09154669619785899, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.09154669619785899, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.09449981543004798, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.09708379475821337, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.09505352528608342, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.09874492432631968, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.09745293466223699, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.09800664451827243, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.10114433370247324, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.10594315245478036, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.10003691399040236, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.09394610557401255, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.09819121447028424, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.10465116279069768, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.009950125322849472, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.010083839573775849, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.008999787895532968, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.008361246542900916, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.007183603527227009, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.006562881562881563, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.006167183566015653, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.005856960108604845, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.005707628645335204, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.0058752506237271795, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.006017221843675383, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.006156003022339307, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.006105129938801339, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.007096427971616912, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.007313232103401085, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.007672423613119178, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.008022483490113084, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.008407597615883557, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.009326063545092758, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.009700357236620036, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.010218382410076767, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.011192941899092883, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.011628292158146378, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.013072650905566148, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.014884861535289298, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.01632309535875883, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.018453484737516984, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.01949985915430418, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.023207296967253793, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.028617188791982922, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.030918823721670624, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.03392565440750855, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.03615919549191173, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.036715581236685724, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.038838160676526734, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.04006089203457846, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.03840076833191077, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.03798406628463653, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.0367258435168663, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.036220071783087844, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.04005474224156939, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.041040075743571595, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.044962749294701454, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0459442200226299, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.04577687983937901, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.04151821126124828, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0406936474754454, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.040844950073275814, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.04327071904028406, "id_best": 44, "lr_best": 0.0078, "wd_best": 0.05, "train/loss_best": 3.0583880615234373, "validation/loss_best": 3.0863091945648193, "validation/acc_best": 0.10594315245478036, "validation/f1_best": 0.04577687983937901} +{"epoch": 8, "train/lr": 0.0002612959497061927, "train/loss": 3.095928740501404, "train/grad": 0.05942119343206286, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.137095947265625, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.135283203125, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.13333740234375, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.13212890625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.131409912109375, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.1308447265625, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.13051513671875, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.13020263671875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.1299365234375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.129644775390625, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.129429931640625, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.1290283203125, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.1286328125, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.12802978515625, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.127420654296875, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.126876220703125, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.12610107421875, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.125087890625, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.12389892578125, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.122734375, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.121182861328125, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.1195458984375, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.11753662109375, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.11534912109375, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.112845458984375, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.109749755859375, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.106884765625, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.104176025390625, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.100390625, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.09569580078125, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.09157958984375, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.0876220703125, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.0821246337890624, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.0772540283203127, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.0714111328125, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.0656640625, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.059500732421875, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.05356201171875, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.04748291015625, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.0409527587890626, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.03690673828125, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.0339892578125, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.031986083984375, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.032126159667969, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.0334793090820313, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.0355255126953127, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.0387234497070312, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.04283203125, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.0467926025390626, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.008235659184865653, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.008155677700415254, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.008070996780879795, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.00801855450263247, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.007987170345149935, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.007965616730507464, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.00795432409271598, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.007949256950523705, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.00794870866695419, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.007950336798094213, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.007952261562459172, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.00795539177954197, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.007958504010457546, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.007963127112016083, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.007968015628866851, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.007971651738043874, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.007976446531247348, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.007981926640495659, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.0079880211642012, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.007993708665017038, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.008000363511964679, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.008006960169877857, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.008014659164473414, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.008024125068914145, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.008034667081665248, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.008049546570982785, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.00806554232025519, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.00808155772741884, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.008106863077264279, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.008141104083042592, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.008175493401940912, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.008209448030684144, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.008260918741580098, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.008311288820113987, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.008374711603391916, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.008439728752709924, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.008511079184245318, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.008583210960496216, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.008678969459142536, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.008832502232398837, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.008970208743121474, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.009099265153054148, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.009289345196448267, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.009478847426362336, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.009714864711277187, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.010010270783677697, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.010328548068646342, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.010656493711285292, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.010902138515375555, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1308810710906982, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1288607120513916, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1265854835510254, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.125211000442505, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1243677139282227, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.123674154281616, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1232025623321533, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.122887134552002, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1225745677948, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1223385334014893, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.122114896774292, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1217851638793945, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.121452808380127, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.120979070663452, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.120516538619995, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1200685501098633, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.119475841522217, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.118743419647217, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.117872476577759, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.117030382156372, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.115889072418213, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.1145718097686768, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.112938165664673, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.1109347343444824, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.1086363792419434, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.105576276779175, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.102621555328369, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.0998058319091797, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.0957186222076416, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.0907745361328125, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.0862979888916016, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.0823168754577637, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.077199697494507, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.072995185852051, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.0686042308807373, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.065192937850952, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.06242036819458, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.0604777336120605, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.0582327842712402, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.05374813079834, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.0486605167388916, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.042537212371826, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.0353920459747314, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.0324273109436035, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.0305733680725098, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.0257813930511475, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.0268306732177734, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.0442862510681152, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.0594985485076904, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06829088224437062, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06736803248431156, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06626061277224068, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06312292358803986, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06293835363602805, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06404577334809892, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06404577334809892, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06386120339608711, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06404577334809892, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.06423034330011074, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.06459948320413436, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.0651531930601698, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.06681432262827612, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.06921373200442968, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.07364341085271318, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.07862679955703211, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.08379475821336287, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.08914728682170543, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.09080841638981174, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.09302325581395349, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.09283868586194167, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.0946843853820598, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.09819121447028424, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.10077519379844961, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.10612772240679218, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.10926541159099298, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.10815799187892211, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.11092654115909929, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.10981912144702842, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.11074197120708748, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.11037283130306386, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.10815799187892211, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.10668143226282761, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.10594315245478036, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.11148025101513473, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.12163159837578442, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.12218530823181986, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.11277224067921743, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.11738648947951273, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.009973369731936245, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.009456528473198797, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.008724866605828219, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.007369982881101589, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.0067620542629238745, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.006129211709595814, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.006170682136895116, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.00618887490732819, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.006185141072619204, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.006156003022339307, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.006304230815209113, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.006121398289654749, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.006232548723962696, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.0066786781424956, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.0066435637787067734, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.00708131808167236, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.007049331901694107, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.0068754861936723005, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.007006770097619363, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.007363633527122598, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.007564219741069252, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.008628544279520157, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.010535610756286297, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.012465227524883599, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.01644786455121317, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.02093921956830212, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.023454616716840616, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.025327150604456544, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.026480434929779247, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.02773899148945326, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.029139867067758615, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.03145142132273995, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.035838665927218585, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.04092590611488969, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.04641662614723057, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.05067818197348547, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.054769660182642045, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.06071913931910614, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.06040724457274337, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.05537382936501617, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.053886704104408885, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.05287052759343692, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.05108985505903588, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.04890104460946298, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.05341413354227844, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.05746522022701847, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.05541045118241144, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.045038784399011426, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.047358265623473395, "id_best": 46, "lr_best": 0.010799999999999999, "wd_best": 0.05, "train/loss_best": 3.0387234497070312, "validation/loss_best": 3.0268306732177734, "validation/acc_best": 0.12218530823181986, "validation/f1_best": 0.05541045118241144} +{"epoch": 9, "train/lr": 0.00023803200426111704, "train/loss": 3.0943587136268618, "train/grad": 0.06034995697438717, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.13521728515625, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.133656005859375, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.13213623046875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.131251220703125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.13074951171875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.130283203125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.129893798828125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.1297412109375, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.1293896484375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.12910400390625, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.12883056640625, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.128316650390625, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.127913818359375, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.12718505859375, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.126553955078125, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.125887451171875, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.1251318359375, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.123978271484375, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.1228564453125, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.121622314453125, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.1200390625, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.1183935546875, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.11643798828125, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.11416748046875, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.111513671875, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.10828857421875, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.10518310546875, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.102215576171875, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.0979541015625, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.09274169921875, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.088001708984375, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.0836920166015624, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.0778131103515625, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.072532958984375, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.0662921142578123, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.060252685546875, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.0542938232421877, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.049051513671875, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.044002685546875, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.038271484375, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.03449951171875, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.03192626953125, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.029871826171875, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.0300250244140625, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.0322140502929686, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.03587890625, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.040006103515625, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.0463931274414064, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.0519277954101565, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.008310571361798793, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.008245537616312503, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.008176437860820443, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.008137062068562954, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.008116770780179649, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008101904273498804, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.008094880597200245, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.008092706103343516, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.008092616794165224, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.00809350288938731, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.00809460346121341, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.008096512726042419, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.008098588869906963, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.00810122373048216, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.008104052159469575, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.008106790874153376, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.008110176492482423, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.008114358009770513, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.008119291521143168, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.008124482589773835, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.008131100195460022, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.00813909351825714, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.008147932279389352, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.008159262621775269, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.00817140078637749, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.008187870231922715, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.00820380896795541, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.008219116476830095, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.008242306550964713, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.00827260008547455, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.008302865731529892, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.008332778254989535, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.008375908641610294, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.008416810629423708, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.008471487648785114, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.008533013337291777, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.008607482712250203, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.008686346940230578, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.008784100303892046, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.008932322086766363, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.009071728705894202, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.00921056779101491, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.009424552246928215, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.00964698488591239, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.009943528594449162, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.01026022362522781, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.010516307496000082, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0108163828169927, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.011049222212750464, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.12905216217041, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1273295879364014, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1254563331604004, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1243865489959717, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.123745918273926, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1232104301452637, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.122853994369507, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1225688457489014, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.122262477874756, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1219589710235596, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.121695041656494, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1213021278381348, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.120917558670044, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1203649044036865, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1198110580444336, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1192877292633057, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1186330318450928, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1178858280181885, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1170120239257812, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.116227865219116, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.115199089050293, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.1140973567962646, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.1128346920013428, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.1113829612731934, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.109776258468628, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.10766339302063, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.1056346893310547, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.1036219596862793, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.1006240844726562, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.0966219902038574, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.0927135944366455, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.0890862941741943, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.0842702388763428, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.0802605152130127, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.0757501125335693, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.071187734603882, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.065554141998291, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.059417724609375, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.0527408123016357, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.0464603900909424, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.042870044708252, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.0393307209014893, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.03486704826355, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.032715082168579, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.0324175357818604, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.037996530532837, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.052694797515869, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.0791099071502686, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.08681058883667, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06718346253229975, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06699889258028793, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06441491325212255, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06312292358803986, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06404577334809892, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06478405315614617, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06533776301218161, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06478405315614617, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.0651531930601698, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.0664451827242525, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06699889258028793, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.067921742340347, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.06847545219638243, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.07050572166851236, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.0695828719084533, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.07050572166851236, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.07142857142857142, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.07216685123661867, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.07567368032484312, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.07954964931709117, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.08490217792543374, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.08896271686969362, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.09413067552602436, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.0976375046142488, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.09523809523809523, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.09689922480620156, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.09671465485418974, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.09579180509413067, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.10003691399040236, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.1050203026947213, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.10834256183093392, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.10908084163898117, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.11258767072720562, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.11480251015134736, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.11812476928755998, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.1168327796234773, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.11997046880767812, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.11480251015134736, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.11018826135105204, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.11074197120708748, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.11221853082318199, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.009525929964984711, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.008954122877930477, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.00789171888594715, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.006674707182395811, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.006265532036920536, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.006143936990055074, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.006179630578001762, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.00618700192214086, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.006143936990055074, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.006296471359723663, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.006259542776203098, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.0066786781424956, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.007032584966232113, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.007448294231980231, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.007764992641474437, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.007549542589811515, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.00800162056408534, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.008443463878959443, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.00886524632694889, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.009655991382558833, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.010883675629696778, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.013167453423231923, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.013330880886412851, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.015581694734375928, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.017360894157556633, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.018274982241912142, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.02302220674952218, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.02624404804094783, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.029369157402649115, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.032522203971550104, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.03535587483986693, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.0367431164009211, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.03614392910304798, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.03729075660825941, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.03818486349575883, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.03837621819265599, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.041425208052431516, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.044840482173903816, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.0482683923659615, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.04914711053248111, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.05382857639044619, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.05705099048238268, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.059983455368984286, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.058773327226684435, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0651372573842774, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.06454606218469609, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.06210209543398135, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.057414443813549626, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.05592883688280061, "id_best": 44, "lr_best": 0.0078, "wd_best": 0.05, "train/loss_best": 3.0322140502929686, "validation/loss_best": 3.0324175357818604, "validation/acc_best": 0.11997046880767812, "validation/f1_best": 0.0651372573842774} +{"epoch": 10, "train/lr": 0.00021091808096876188, "train/loss": 3.091030293703079, "train/grad": 0.058602627050131556, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.1329150390625, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.131737060546875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.13057373046875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.129971923828125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.129698486328125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.12941650390625, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.129134521484375, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.1289501953125, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.12861083984375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.1283251953125, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.127955322265625, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.1274609375, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.126888427734375, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.126151123046875, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.125369873046875, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.124696044921875, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.123658447265625, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.1223681640625, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.121024169921875, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.119716796875, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.117911376953125, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.116060791015625, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.11375, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.11126953125, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.108507080078125, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.105008544921875, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.101678466796875, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.098597412109375, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.094239501953125, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.0890087890625, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.0842877197265626, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.080023193359375, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.0742303466796876, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.0691400146484376, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.0632086181640625, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.0573553466796874, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.0513397216796876, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.0458001708984375, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.0401800537109374, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.03392822265625, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.0298699951171875, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.0272418212890626, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.0252069091796874, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.0247979736328126, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.025240478515625, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.026813659667969, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.0292828369140623, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.033541259765625, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.0383450317382814, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.008047359753400088, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.00799378449562937, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.007937953090295196, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.00791192535078153, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.007899101932998746, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.007891281745396555, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.007889211846049874, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.007889498195145278, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.00789101698435843, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.007893039060290903, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.007894692195113748, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.00789707388030365, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.007899151793681084, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.007902711529750377, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.007906413620803505, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.007910035194363445, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.007913949822541327, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.00791974418098107, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.007925777132622897, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.007931179646402598, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.007938055724371224, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.007945666403975338, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.007954148137941956, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.00796416834462434, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.007976373869460075, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.007993231201544404, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.008009670150931925, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.008026257855817676, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.008050523775164038, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.008083351778332144, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.00811604991555214, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.008148153065703809, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.008194308246020228, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.00823820123448968, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.008291190878953785, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.008345676211174578, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.008410275967326014, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.008481256682425737, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.00857989797834307, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.008730847360566259, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.008855888203252107, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.008969074687920511, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.009134334409609438, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.009302865120116622, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.009526192890480161, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.00977609518216923, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.009991424777545034, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.010231959740631283, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.010438008473720402, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1277778148651123, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.126291513442993, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1247594356536865, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.123898983001709, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.123389959335327, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.122951030731201, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1226301193237305, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.122342586517334, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.121999740600586, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1216495037078857, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1213343143463135, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.120821237564087, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1203465461730957, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1196179389953613, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.118892192840576, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.118178129196167, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1172451972961426, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1161088943481445, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1147921085357666, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.1134722232818604, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.111774444580078, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.1098947525024414, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.1076719760894775, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.1050872802734375, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.1022255420684814, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.098585605621338, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.095229387283325, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.0921127796173096, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.087825059890747, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.0828211307525635, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.078437089920044, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.0746335983276367, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.0697872638702393, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.0657660961151123, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.061310291290283, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.057529926300049, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.054286003112793, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.052121877670288, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.049898147583008, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.045269727706909, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.0394046306610107, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.033978223800659, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.0281877517700195, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.02542781829834, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.025221109390259, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.0289454460144043, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.0356922149658203, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.046328544616699, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.0537896156311035, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06626061277224068, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.0651531930601698, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06293835363602805, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06312292358803986, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06293835363602805, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06312292358803986, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.0636766334440753, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.0636766334440753, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.06404577334809892, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.06404577334809892, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.06496862310815799, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.06607604282022887, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.06976744186046512, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.0725359911406423, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.07511997046880768, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.07770394979697305, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.08250276854928018, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.08674787744555186, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.09007013658176449, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.09283868586194167, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.09653008490217793, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.09966777408637874, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.0976375046142488, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.09948320413436693, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.09985234403839055, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.0991140642303433, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.0991140642303433, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.09985234403839055, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.10095976375046142, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.10317460317460317, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.10520487264673312, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.11184939091915837, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.11590992986341823, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.12292358803986711, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.11867847914359542, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.11258767072720562, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.10815799187892211, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.10557401255075674, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.008924343854338013, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.00832678075976438, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.0069595082369274695, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.006258708993825743, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.006160321845386208, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.006196489754831902, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.006038142505988227, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.006036555177156872, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.0060156760488713, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.00600662674176568, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.005977691777849445, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.006142257768599029, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.006116087370911605, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.00642186322854599, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.006440633873036643, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.006570725724368026, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.00657858702426644, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.006636040854411489, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.0068490820541642385, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.007221037946736964, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.007378343065625361, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.007959483242562583, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.009064326112414707, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.012828036606753595, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.015203162681095062, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.016856599350483743, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.01881322180663054, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.023274314538868534, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.028957196763815096, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.03318128096064068, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.036743431149965616, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.04003625565779139, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.04248527722802702, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.042241484022079355, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.04358633768360942, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.04328307492399718, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.04150499460336312, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.040247265978553555, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.04086815410826324, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.04403444141951542, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.0471167043635132, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.05075021065829342, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.05776538407961377, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.06665393238214314, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.07579394951664192, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.07172652053520095, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0648213842725562, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.05950253991740693, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.05905969317084467, "id_best": 44, "lr_best": 0.0078, "wd_best": 0.05, "train/loss_best": 3.025240478515625, "validation/loss_best": 3.025221109390259, "validation/acc_best": 0.12292358803986711, "validation/f1_best": 0.07579394951664192} +{"epoch": 11, "train/lr": 0.00018113997589164516, "train/loss": 3.086232112646103, "train/grad": 0.059351645894348624, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.13309326171875, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.132108154296875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.131259765625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.130802001953125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.130611572265625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.130274658203125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.13004150390625, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.12984619140625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.129473876953125, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.129051513671875, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.128656005859375, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.1279833984375, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.127349853515625, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.1264892578125, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.1256689453125, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.12484130859375, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.123663330078125, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.1223583984375, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.12086181640625, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.11932373046875, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.117393798828125, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.11515869140625, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.112818603515625, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.11003173828125, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.106983642578125, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.103289794921875, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.09959716796875, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.09628662109375, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.09150390625, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.0855474853515625, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.080140380859375, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.0751885986328125, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.068560791015625, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.0626416015625, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.05586181640625, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.049188232421875, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.042454833984375, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.0363018798828123, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.030037841796875, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.0230047607421877, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.018309326171875, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.014622802734375, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.010598449707031, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.0076754760742186, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.005793151855469, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.00593994140625, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.008406982421875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.014779052734375, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.0235003662109374, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.008237801417708397, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.008194555910304189, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.008154334821738303, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.008136888085864484, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.008128876395057888, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008124624972697347, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.008123967433348298, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.0081244176463224, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.008125443225726486, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.00812697967281565, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.008128360165283083, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.008129701782017947, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.008131822953000665, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.008133674608543515, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.008135887030512094, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.008137780416291207, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.008139916993677616, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.008142392649315298, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.00814619699958712, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.008149764074478299, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.008154390559066088, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.008159839289728552, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.00816654367838055, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.008174841208383441, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.008184117688797414, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.008197249548975378, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.008209782352205366, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.008222323686350137, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.008239754412788897, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.008261486473493278, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.008282991170417517, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.008303355225361884, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.008333105677738786, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.008363444050773978, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.00840266285231337, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.008445250513032078, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.008497475823387503, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.008554958878085018, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.008629160267300904, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.008740736427716911, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.008838189851958304, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.008926549998577685, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.009041799379047007, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0091479336284101, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.009283508346416057, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.009463424673303961, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.009672164551448077, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.01000380759127438, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.010345352331642061, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.126955986022949, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1256415843963623, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.124356508255005, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1236355304718018, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.123203992843628, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1228299140930176, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1225273609161377, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.122234582901001, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.121885299682617, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.121541738510132, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1212098598480225, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.120673418045044, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1201765537261963, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1193833351135254, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.118637800216675, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1178781986236572, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1169049739837646, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.115680694580078, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.114288568496704, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.112884759902954, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.1110780239105225, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.1090848445892334, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.1066734790802, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.1038894653320312, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.1007773876190186, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.0968353748321533, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.0931239128112793, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.08963680267334, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.0848538875579834, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.0791375637054443, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.0740528106689453, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.0695741176605225, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.0636277198791504, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.0584042072296143, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.0524027347564697, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.0466537475585938, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.0409700870513916, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.036187171936035, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.032001256942749, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.0292420387268066, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.029506206512451, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.0304811000823975, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.0301353931427, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.025998830795288, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.0192856788635254, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.015242576599121, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.017930746078491, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.027390718460083, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.0384607315063477, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.0664451827242525, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06441491325212255, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06293835363602805, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06404577334809892, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06459948320413436, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06533776301218161, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.0651531930601698, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.0664451827242525, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06718346253229975, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06976744186046512, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.07216685123661867, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.07419712070874862, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.07622739018087855, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.08139534883720931, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.08545588778146918, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.08637873754152824, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.09007013658176449, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.0902547065337763, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.0917312661498708, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.09597637504614248, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.09671465485418974, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.09892949427833149, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.09929863418235511, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.10077519379844961, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.10077519379844961, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.10299003322259136, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.10243632336655592, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.10409745293466224, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.10631229235880399, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.10778885197489849, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.10981912144702842, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.11018826135105204, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.11424880029531193, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.11609449981543005, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.11664820967146548, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.12070874861572536, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.12033960871170174, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.11794019933554817, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.11037283130306386, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.10871170173495755, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.008779921951174956, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.007923091800376396, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.006785385005853042, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.006147124913452186, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.006185141072619204, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.006039741039741039, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.006018778558154577, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.0061984245868829954, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.006003694581280788, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.006306200487151951, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.006108209511829272, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.006546723685682675, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.007057888088715717, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.007321730791039265, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.007740771471696567, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.00787269974026495, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.008443463878959443, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.008774152532995865, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.009826216155795047, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.010931607496848324, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.013317360720051076, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.01610865800553824, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.020951254530674156, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.024777929972532402, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.0261731692713105, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.028725587116207593, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.029545017723610956, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.03247013042862854, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.037084932325588744, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.038211824916649824, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.0394089083331165, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.03965002771655305, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.04041896552293275, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.04012546133714482, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.04124039020581129, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.0419120252358264, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.04333737868848039, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.04660761268771984, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.04765599791626659, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.04823983322752889, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.04801131209909345, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.05058974460130795, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.0526100678459158, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.05209096409479567, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.05719665273543644, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.06128521519968041, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.06087448159004927, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.05635717023302977, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.056221368742759466, "id_best": 44, "lr_best": 0.0078, "wd_best": 0.05, "train/loss_best": 3.005793151855469, "validation/loss_best": 3.0192856788635254, "validation/acc_best": 0.12070874861572536, "validation/f1_best": 0.05719665273543644} +{"epoch": 12, "train/lr": 0.0001499999999999999, "train/loss": 3.0790608644485475, "train/grad": 0.058484560772776605, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.130399169921875, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.129320068359375, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.128311767578125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.127857666015625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.127479248046875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.1272021484375, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.126878662109375, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.126583251953125, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.12619384765625, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.12573974609375, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.125330810546875, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.124710693359375, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.1240087890625, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.1231396484375, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.12218017578125, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.121246337890625, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.120179443359375, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.118671875, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.117005615234375, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.115345458984375, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.113155517578125, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.1108203125, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.10802978515625, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.105042724609375, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.101544189453125, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.097342529296875, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.093358154296875, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.089591064453125, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.084410400390625, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.07818603515625, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.07246826171875, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.0673712158203124, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.060440673828125, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.054522705078125, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.047567138671875, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.04072021484375, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.033759765625, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.0273077392578127, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.020675048828125, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.0129180908203126, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.007298583984375, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.0027667236328126, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.9975537109375, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.99412841796875, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.99134765625, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.990284118652344, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.990811767578125, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.9937164306640627, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.999062194824219, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.008155807182192802, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.00811427184380591, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.008078128166962415, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.008062306467909366, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.008054486280307173, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008050820215139538, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.008049869209062309, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.008049927698448301, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.008050761583726853, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.008051925981417298, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.00805313347838819, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.00805474505526945, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.008056140274275094, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.008058806008193642, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.008060927297919988, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.00806329388404265, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.008066470101475716, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.008069668805692345, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.00807369987014681, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.008077453759033232, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.008081482334528118, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.008086100448854267, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.008091364486608655, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.008097343889530748, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.008103558113798499, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.008111875797621905, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.008120916280895472, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.008129527654964476, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.008143301901873201, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.00816023545106873, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.008178290526848287, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.008197596524842083, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.008226056185085326, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.00825462801149115, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.00829169449629262, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.008330697156488896, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.008374903684016317, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.008422076033893973, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.00848270678659901, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.008572189933620394, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.008649894557893277, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.00872615449829027, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.008837862676009535, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.008948009726591408, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.009086747143883259, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.009256148333661259, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.009423667923547327, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0096599222230725, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.00990159971639514, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1263108253479004, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.125143051147461, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1240108013153076, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1233906745910645, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1230061054229736, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.122637987136841, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1223223209381104, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1220216751098633, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.121643543243408, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1212732791900635, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1208739280700684, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1202826499938965, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.119703769683838, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.118835210800171, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.117981195449829, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1171374320983887, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.116044759750366, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1146976947784424, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1131269931793213, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.111602783203125, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.109647512435913, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.107532501220703, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.1050939559936523, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.102346658706665, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.0993425846099854, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.0956149101257324, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.0921249389648438, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.0888776779174805, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.0843214988708496, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.078845262527466, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.0739455223083496, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.0694921016693115, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.0636026859283447, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.0584278106689453, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.0525569915771484, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.0470001697540283, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.041388988494873, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.0362911224365234, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.031005859375, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.0253615379333496, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.021693706512451, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.0186734199523926, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.0151491165161133, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.013174057006836, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.013054370880127, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.0136892795562744, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.0135128498077393, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.0142979621887207, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.0199592113494873, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06404577334809892, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.0636766334440753, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.0636766334440753, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.0636766334440753, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06404577334809892, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06459948320413436, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.06773717238833518, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.07290513104466592, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.07770394979697305, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.08231819859726837, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.08545588778146918, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.08933185677371724, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.0917312661498708, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.09505352528608342, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.09653008490217793, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.09874492432631968, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.10095976375046142, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.10040605389442599, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.1005906238464378, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.10169804355850867, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.10225175341454411, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.10631229235880399, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.10852713178294573, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.11314138058324105, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.11351052048726468, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.11720191952750092, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.1197858988556663, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.11646363971945367, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.11517165005537099, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.11443337024732374, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.11351052048726468, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.11517165005537099, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.11424880029531193, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.11757105943152454, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.1138796603912883, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.11184939091915837, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.007761011756913396, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.006935323552494179, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.006165451312201088, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.0058961638104945745, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.005539541113440485, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.005543392889945591, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.005542821435629372, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.005557933691434568, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.005557364774780041, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.005527151503059324, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.005719557548795824, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.005712955049210072, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.005706769871100636, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.005882623094506114, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.006366583553943111, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.006483881712332735, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.006660613764629897, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.0071827328941067225, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.007821802135315359, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.01070250203994657, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.014526372452779608, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.017018069794943396, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.019354692506178325, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.02097557404588257, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.02276635204517642, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.02490140393190403, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.028270287742890542, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.03147292116743324, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.03483035815143268, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.03938028044519153, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.04139805122340109, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.04289860884910778, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.04479265288774917, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.0456452655489251, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.048945879164818955, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.05199841850057508, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.05733349892038735, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.06019436017665893, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.06409534702975113, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.06603851059738813, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.06419307463430997, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.06396520137483618, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.06414225680159537, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.06262355278208602, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.06073597203841393, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0576815934213307, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.05922711586925681, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.05651104677168184, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.056639018759741006, "id_best": 39, "lr_best": 0.0036, "wd_best": 0.05, "train/loss_best": 3.0129180908203126, "validation/loss_best": 3.0253615379333496, "validation/acc_best": 0.1197858988556663, "validation/f1_best": 0.06603851059738813} +{"epoch": 13, "train/lr": 0.00011886002410835478, "train/loss": 3.076710002422333, "train/grad": 0.05839082255959511, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.13035888671875, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.12946044921875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.128702392578125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.128223876953125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.127872314453125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.127589111328125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.12727783203125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.12691650390625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.1266015625, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.12618896484375, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.12567138671875, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.1249560546875, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.12436767578125, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.123343505859375, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.12242431640625, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.121385498046875, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.120106201171875, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.118570556640625, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.1168115234375, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.115008544921875, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.112724609375, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.110191650390625, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.107291259765625, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.1041015625, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.10044921875, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.09596435546875, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.091719970703125, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.087862548828125, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.0823834228515623, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.07583740234375, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.069954833984375, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.064635009765625, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.057459716796875, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.051163330078125, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.0438873291015627, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.03671875, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.0294281005859376, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.0224945068359377, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.015596923828125, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.00751220703125, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.0017974853515623, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.9972103881835936, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.9919219970703126, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.988170166015625, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.9849468994140627, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.982838439941406, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.9824566650390625, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.9836196899414062, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.986617431640625, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.008184245291631668, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.008147362442687154, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.008117563487030566, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.008104509026743471, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.008098923296201974, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.00809567045653239, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.008094760372769088, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.008094849456101656, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.008095394691918046, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.008096569408662617, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.008097408225294202, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.008098473744466901, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.008099925729911774, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.008101717405952513, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.00810404324438423, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.008105585926678031, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.008107736250385642, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.008110681371763349, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.0081137259863317, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.008116612867452204, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.008120042444206775, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.008124401862733065, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.008129428129177541, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.00813493664842099, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.00814206368289888, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.008150930004194378, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.008159723959397524, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.008168918748851865, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.008182192652020604, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.008199450247921049, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.008215918417554348, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.00823203317122534, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.00825504511827603, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.008277415924239903, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.008304514558985829, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.008332029855810106, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.008364164442755282, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.008399233787786215, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.008444712716154754, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.008509754207916559, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.008566098583396525, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.008621817692182959, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.00870253200409934, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.008781069361139088, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.008888711768668145, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.009041105275973677, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.009204501579515635, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.009421172782313079, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.00962481034686789, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.125849723815918, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.124772787094116, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1237401962280273, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1231679916381836, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1228039264678955, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1224288940429688, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1221306324005127, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1217870712280273, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.121398687362671, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.120974063873291, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.120537042617798, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1198925971984863, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.119272470474243, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.118359088897705, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.117443084716797, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.116565227508545, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1154305934906006, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.114043712615967, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.112438440322876, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.110894203186035, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.1089231967926025, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.106776714324951, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.1043219566345215, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.1015584468841553, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.0985400676727295, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.094816207885742, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.0913703441619873, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.088134288787842, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.0836822986602783, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.0783398151397705, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.0734856128692627, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.069179058074951, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.063460350036621, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.058647871017456, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.053370714187622, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.048823833465576, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.0447921752929688, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.0420219898223877, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.0401737689971924, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.039268732070923, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.039130210876465, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.0389716625213623, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.038860321044922, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.039644956588745, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.041433334350586, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.043323516845703, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.0427167415618896, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.039858341217041, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.0396502017974854, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06423034330011074, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06293835363602805, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06386120339608711, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06404577334809892, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06441491325212255, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06533776301218161, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06699889258028793, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06847545219638243, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.06995201181247693, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.0725359911406423, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.07419712070874862, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.07715023994093761, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.08010335917312661, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.08231819859726837, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.08619416758951642, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.08988556662975268, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.09246954595791805, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.09523809523809523, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.09966777408637874, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.10151347360649686, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.1035437430786268, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.10557401255075674, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.10575858250276855, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.10557401255075674, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.10705057216685124, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.10815799187892211, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.1079734219269103, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.10834256183093392, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.10871170173495755, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.10815799187892211, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.10889627168696936, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.10520487264673312, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.1050203026947213, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.10428202288667406, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.09966777408637874, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.10040605389442599, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.10280546327057954, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.1035437430786268, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.007700784956093554, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.006695093211216421, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.006162020520478995, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.005874017403486254, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.005900064924822239, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.005712955049210072, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.005712046355005922, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.005691317276087859, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.00587900910316943, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.006030316479885588, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.006167183566015653, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.006109764513794206, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.006546723685682675, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.006897962877705769, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.007028041251895778, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.00742681716695609, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.008099602897679074, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.009041560528133418, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.009892339005748025, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.011084205479463176, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.013387502674730168, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.015389371074168481, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.01795524768348714, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.019850706278754175, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.022164152325899345, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.027248300094123597, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.031273720063819274, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.033943415768608, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.03705446226919196, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.03958308576854477, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.041153229646125805, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.04281018337278688, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.043380948812826635, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.04381780142766815, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.043951938691652113, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.04471620287544456, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.045875516024590585, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.04679936956760827, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.04651272493903208, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.046824329132458174, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.045926135747939766, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.04599685483755536, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.04307226786453566, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.04092721216339288, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.038522604439661566, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.03569016750444589, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.03623679417400628, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.03936445459689853, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.04102688603120265, "id_best": 41, "lr_best": 0.0048, "wd_best": 0.05, "train/loss_best": 2.9972103881835936, "validation/loss_best": 3.0389716625213623, "validation/acc_best": 0.10889627168696936, "validation/f1_best": 0.04599685483755536} +{"epoch": 14, "train/lr": 8.9081919031238e-05, "train/loss": 3.0731424355506896, "train/grad": 0.05795138215646148, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.128360595703125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.12752685546875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.126658935546875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.126220703125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.125836181640625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.125572509765625, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.125194091796875, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.12494384765625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.124482421875, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.124046630859375, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.1235595703125, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.122847900390625, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.1221142578125, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.121109619140625, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.12007568359375, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.11916015625, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.11784423828125, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.11621337890625, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.11437255859375, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.112606201171875, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.11029052734375, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.107786865234375, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.104913330078125, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.101634521484375, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.098018798828125, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.093612060546875, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.089339599609375, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.085406494140625, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.0800250244140623, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.0734124755859376, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.067421875, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.0619482421875, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.0547119140625, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.0482293701171876, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.0406878662109373, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.0332623291015626, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.0256640625, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.018477783203125, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.01112548828125, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.0025115966796876, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.99639892578125, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.99140869140625, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.9857598876953126, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.9816162109375, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.977702331542969, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.9746624755859377, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.972935791015625, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.9724160766601564, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.973855285644531, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.008165717287920416, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.008133950943592936, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.00811004085931927, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.008099390307907016, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.00809458942618221, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008092679267283529, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.00809199212351814, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.008092083060182631, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.008092359900474548, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.00809280788525939, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.008093120572157204, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.008094177420716733, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.008094781490508468, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.008095947855617852, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.008097112490795554, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.008097783986013383, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.008099958100356162, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.008101896778680385, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.008104491329286248, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.008106616761069744, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.00810977841494605, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.008113381660077721, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0081174295139499, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.00812219585524872, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.008127364667598159, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.008134089861996471, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.008140428189653904, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.008146816897206009, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.008155331260059028, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.008166245971806348, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0081777114700526, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.008187954993918539, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.008203276607673615, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.008219218642916531, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.008238483583554626, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.008259450874757022, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.008285933814477175, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.008315474388655274, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.008352827499620616, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.008410020032897592, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.008463306117337198, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.008513894209172576, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.008587412887718528, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.00865986786549911, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.008750485859345646, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.008850915788207203, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.008942370428703725, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.009073755301069469, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.009215712524019181, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.125591993331909, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.124602794647217, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1236531734466553, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1231255531311035, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.122784376144409, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1224429607391357, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1221413612365723, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1218268871307373, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1214499473571777, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1210317611694336, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1206326484680176, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.120008945465088, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.11942458152771, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1185343265533447, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1176676750183105, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.116825580596924, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.115722894668579, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1144001483917236, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1128270626068115, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.1113033294677734, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.109325647354126, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.1071791648864746, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.1046204566955566, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.101743221282959, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.098555326461792, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.0945510864257812, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.090759038925171, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.08719801902771, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.082233428955078, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.0762505531311035, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.0708749294281006, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.066115379333496, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.0598223209381104, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.0544071197509766, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.0483710765838623, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.042839288711548, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.03735089302063, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.0324478149414062, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.0273380279541016, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.021531820297241, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.017575263977051, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.014477252960205, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.011060953140259, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.0085854530334473, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.0057828426361084, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.003573417663574, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.0032620429992676, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.0053181648254395, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.008777141571045, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06312292358803986, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06293835363602805, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06386120339608711, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06404577334809892, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06441491325212255, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06478405315614617, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.0651531930601698, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06607604282022887, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.06681432262827612, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.06939830195644149, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.07364341085271318, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.0754891103728313, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.07751937984496124, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.08176448874123293, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.08564045773348099, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.08748615725359911, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.08970099667774087, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.09154669619785899, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.09671465485418974, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.09819121447028424, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.09948320413436693, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.10132890365448505, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.10262089331856773, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.10446659283868587, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.10280546327057954, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.10409745293466224, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.10852713178294573, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.11148025101513473, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.11424880029531193, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.11424880029531193, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.11627906976744186, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.11867847914359542, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.1184939091915836, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.12144702842377261, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.12440014765596161, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.1273532668881506, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.12403100775193798, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.1197858988556663, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.007367311338882847, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.0066132107433734474, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.006165451312201088, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.005874017403486254, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.005894883701587249, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.005710254285200319, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.005880281750766619, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.0058752506237271795, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.00603185970303483, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.006002244006364957, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.006145627200114945, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.006106664673435984, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.006531068046495958, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.006932242787626, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.0070857718949184564, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.007265237696475239, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.007497327507658753, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.008174805984285502, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.008762825972801858, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.00914594421648802, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.011536633506590734, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.01564814987393469, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.017796962599322976, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.01931985600784539, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.023948062335055656, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.027813201017377383, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.03063404158170333, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.03269498500088101, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.03548132928503542, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.03920505948030133, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.04079961001120829, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.04236037780061321, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.04474544369329609, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.04716046402997386, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.048436320472334295, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.04786996283807047, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.0486383999955316, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.05258299205645054, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.05468632092550305, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.056449123021777126, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.05668675569740265, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.05776493264666769, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.05837250634196354, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.056500155929141864, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.06017956410129464, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.06383057548701178, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.06997163178198702, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.06997055805843427, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0661723576317231, "id_best": 46, "lr_best": 0.010799999999999999, "wd_best": 0.05, "train/loss_best": 2.972935791015625, "validation/loss_best": 3.0032620429992676, "validation/acc_best": 0.1273532668881506, "validation/f1_best": 0.06997163178198702} +{"epoch": 15, "train/lr": 6.196799573888289e-05, "train/loss": 3.071094619035721, "train/grad": 0.05797908492386341, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.12977783203125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.12890869140625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.128189697265625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.1277587890625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.127412109375, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.127073974609375, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.12674072265625, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.126339111328125, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.125902099609375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.125335693359375, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.124884033203125, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.124058837890625, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.12333984375, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.1222021484375, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.12119873046875, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.1201611328125, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.118760986328125, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.11708740234375, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.115101318359375, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.113251953125, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.110860595703125, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.108182373046875, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.10510498046875, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.1016455078125, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.0978466796875, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.093128662109375, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.088819580078125, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.0846630859375, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.0788653564453123, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.071922607421875, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.0656707763671873, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.06001708984375, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.052347412109375, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.045587158203125, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.0377716064453124, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.0300750732421875, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.0219952392578127, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.0145428466796873, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.006444091796875, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.9970294189453126, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.99015625, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.984525146484375, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.9779852294921874, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.973035888671875, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.968236083984375, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.9639154052734376, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.9613006591796873, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.959329833984375, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.9591497802734374, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.008244306803680957, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.00821378419175744, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.008188788944389671, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.008176597103010863, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.00817106466041878, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008167865541763604, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.008166656533721834, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.008166345197241753, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.00816636719275266, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.008166392871644348, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.00816663671284914, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.00816689144121483, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.008167333228047937, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.008167963707819581, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.008168630430009215, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.008169425872620196, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.008170521573629231, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.008171413671225309, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.008172663636505604, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.008173819594085217, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.008175536361522972, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.008177222136873752, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.008179397508502006, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.00818171160062775, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.008184525114484132, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.008188497354276479, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.008191478457301855, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.008194144505541772, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.008199554781895131, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0082054046029225, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.008212389829568565, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.008218341760803015, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.008227302040904761, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.008236435980070383, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.008249303121119737, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.008263118593022227, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.008280739332549273, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.008298600588459522, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.00832134098978713, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.008352744937874378, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.008378785341046751, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.008406608931254595, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.008449036185629666, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.008495729400310665, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.008560093403793871, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.008643741097766906, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0087250159191899, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.008836178779602051, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.008948280182667077, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1254019737243652, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.124460458755493, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1235501766204834, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1230547428131104, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.122728109359741, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1223936080932617, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1221132278442383, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1217899322509766, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.121407985687256, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1209895610809326, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.120576858520508, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.119948387145996, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1193344593048096, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.118433952331543, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1175284385681152, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1166582107543945, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1155264377593994, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1141135692596436, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1124651432037354, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.1108500957489014, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.108750343322754, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.1064486503601074, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.103781223297119, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.1007325649261475, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.097407817840576, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.0932297706604004, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.0893332958221436, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.0856919288635254, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.080566644668579, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.0744426250457764, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.068955659866333, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.0639593601226807, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.057375907897949, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.051623821258545, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.0450832843780518, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.0388588905334473, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.032532215118408, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.0268256664276123, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.0209686756134033, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.0141923427581787, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.0094892978668213, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.005770683288574, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.001584529876709, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.9986586570739746, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.996119260787964, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.9942517280578613, "validation/loss_046_lr3.6e+01_wd1.0e+00": 2.993558645248413, "validation/loss_047_lr4.3e+01_wd1.0e+00": 2.993685245513916, "validation/loss_048_lr5.0e+01_wd1.0e+00": 2.9946253299713135, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06293835363602805, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06312292358803986, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06386120339608711, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06404577334809892, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06423034330011074, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.0651531930601698, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06589147286821706, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.06736803248431156, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.07069029162052418, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.07438169066076043, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.07715023994093761, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.07899593946105574, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.08324104835732743, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.08767072720561092, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.08970099667774087, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.09191583610188261, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.09394610557401255, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.09634551495016612, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.09856035437430787, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.10317460317460317, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.10520487264673312, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.1094499815430048, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.11258767072720562, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.11498708010335917, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.11664820967146548, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.11941675895164268, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.11886304909560723, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.11941675895164268, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.11941675895164268, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.12015503875968993, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.12181616832779624, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.1212624584717608, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.1212624584717608, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.12144702842377261, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.12200073827980805, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.12089331856773718, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.11941675895164268, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.007304583381291643, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.006526640560104426, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.006179630578001762, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.0058752506237271795, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.005711146118987883, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.005710254285200319, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.005697462292469462, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.005877746409397588, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.006059221919149943, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.0060349789812139155, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.006177817514358756, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.006122577759941492, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.006411119676708209, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.00654807464508957, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.0069187969754705425, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.006965321152686163, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.007115243344014924, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.008086810534343165, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.008690951877215131, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.010242896140624687, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.013207807494503941, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.0166766862148019, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.019514025806682867, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.020470669258340724, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.02476990376297862, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.02930441062002838, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.03264662860571324, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.03515013935377615, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.037014913392462566, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.03919117883367167, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.042085068170239874, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.045957172638203016, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.04790066017731106, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.051362058291881, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.05274099797381273, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.05522667490345018, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.05638457365120966, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.05806637806302931, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.0586492156443558, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.05923604454007144, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.059046214526339846, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.06064527067257162, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.06250727065017819, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.06247852399899542, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.06258231946769299, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.06298636203898846, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.062394347762372605, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.06206535632625811, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.061858921888986416, "id_best": 46, "lr_best": 0.010799999999999999, "wd_best": 0.05, "train/loss_best": 2.9613006591796873, "validation/loss_best": 2.993558645248413, "validation/acc_best": 0.12200073827980805, "validation/f1_best": 0.062394347762372605} +{"epoch": 16, "train/lr": 3.870405029380728e-05, "train/loss": 3.070417070388794, "train/grad": 0.057190684620291, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.127781982421875, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.127073974609375, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.12631103515625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.126029052734375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.125689697265625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.125418701171875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.125179443359375, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.124808349609375, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.124383544921875, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.12385986328125, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.123321533203125, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.122655029296875, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.121917724609375, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.120869140625, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.11982421875, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.118721923828125, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.1173974609375, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.11573974609375, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.11384521484375, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.11199951171875, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.10958251953125, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.107061767578125, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.10396484375, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.100616455078125, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.096884765625, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.092298583984375, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.0880078125, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.0839501953125, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.078277587890625, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.0715093994140625, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.0653143310546875, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.0596783447265623, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.052237548828125, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.0455517578125, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.0377825927734374, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.0300732421875, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.0221490478515625, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.0147528076171874, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.007015380859375, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.9978265380859375, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.9911700439453126, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.98577880859375, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.97928955078125, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.9742657470703127, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.969127197265625, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.9648101806640623, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.9617074584960936, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.959048156738281, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.957879943847656, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.008158091639634222, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.008130723473150282, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.00811002051224932, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.00810119257075712, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.008097978273872286, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008096966911107301, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.008096812390722335, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.008096898400690406, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.008097107827197761, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.00809763859724626, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.008097662415821105, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.008098252341151238, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.008098326551262289, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.008098681021947414, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.008099133197683841, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.008099385388195515, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.008099629711359739, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.008099584626033902, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.008100021225400269, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.00810046975268051, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.00810090838931501, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.008101207960862666, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.008101347712799906, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.008102342763449996, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.008103382410481572, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.008104558973573149, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.008105267034843565, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.008106439611874522, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.008108840056229383, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.00811174460919574, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.008114728168584407, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.008119213033933193, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.008126022801734507, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.008132950991857797, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.008143180534243583, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.008154757018201054, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.008169658237602562, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.008185945299919695, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.008204266880638897, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.008229786234442144, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.00825134854298085, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.00827210643561557, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.008301288166549056, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.008328007506206632, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.008362866786774248, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.008405655212700367, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.008447348724585026, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.00850346167339012, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.00856207120930776, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.12528920173645, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1243886947631836, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1235053539276123, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1230251789093018, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.122716188430786, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1223647594451904, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.122068405151367, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.121753454208374, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1213526725769043, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.120938777923584, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1205101013183594, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1198790073394775, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1192376613616943, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.118321657180786, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.117403030395508, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.116504669189453, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1153461933135986, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1139044761657715, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.112213373184204, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.1105797290802, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.1084399223327637, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.106126546859741, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.1034059524536133, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.10038161277771, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.097036600112915, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.0929222106933594, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.08907413482666, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.085484743118286, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.080545663833618, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.074678659439087, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.06946063041687, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.06479811668396, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.058692455291748, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.0534098148345947, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.047407865524292, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.0417797565460205, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.0360496044158936, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.030816078186035, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.0256075859069824, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.0195441246032715, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.0152535438537598, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.0117616653442383, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.007578134536743, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.004253387451172, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.0008137226104736, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.9979665279388428, "validation/loss_046_lr3.6e+01_wd1.0e+00": 2.996188163757324, "validation/loss_047_lr4.3e+01_wd1.0e+00": 2.994703769683838, "validation/loss_048_lr5.0e+01_wd1.0e+00": 2.9938676357269287, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06312292358803986, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06404577334809892, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06404577334809892, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06404577334809892, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06533776301218161, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06607604282022887, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.06829088224437062, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.07179771133259505, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.07567368032484312, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.07936507936507936, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.082687338501292, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.0858250276854928, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.08933185677371724, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.09154669619785899, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.09431524547803617, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.0976375046142488, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.09708379475821337, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.09929863418235511, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.10299003322259136, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.10520487264673312, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.10926541159099298, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.11018826135105204, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.11221853082318199, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.11406423034330011, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.11498708010335917, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.11443337024732374, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.11609449981543005, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.11830933923957179, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.12015503875968993, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.12089331856773718, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.12163159837578442, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.12218530823181986, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.12255444813584349, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.12218530823181986, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.1212624584717608, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.12033960871170174, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.00699700710811822, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.0063969973797889665, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.006203528210182653, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.005880281750766619, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.005713872258075664, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.005712955049210072, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.005697462292469462, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.00569217047843537, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.0058752506237271795, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.006052770087756409, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.006190760105179477, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.006149040855267023, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.006449900568215975, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.0065592437537235785, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.0069581120278232635, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.006986032551996763, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.007098834172399767, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.00831036782111166, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.008833925260934815, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.010895313295980714, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.013996961270198815, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.01748615315086189, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.02028231107514573, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.02289161205051245, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.025315025645844227, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.0284165429039895, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.03250543615590431, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.03636163348718897, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.03957991852021794, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.04027542566753644, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.04274420130715295, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.045438471830098755, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.04728618127066523, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.05026603466712514, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.05071594571525281, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.05200400483141499, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.053682566813741193, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.05438908115235999, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.054130540295868695, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.05481984524259384, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.0564934167686058, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.05850317395309556, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.059283621901186107, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.060082732377137536, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.06047499324635431, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.06056639829309205, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0606708768371928, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0603250215186859, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.05942954954516041, "id_best": 45, "lr_best": 0.0093, "wd_best": 0.05, "train/loss_best": 2.9648101806640623, "validation/loss_best": 2.9979665279388428, "validation/acc_best": 0.12255444813584349, "validation/f1_best": 0.06056639829309205} +{"epoch": 17, "train/lr": 2.030750443206766e-05, "train/loss": 3.062280766963959, "train/grad": 0.05562557952478528, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.1239306640625, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.12294677734375, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.121903076171875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.12134765625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.1209521484375, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.120513916015625, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.120216064453125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.119827880859375, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.119293212890625, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.1187890625, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.118258056640625, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.11743408203125, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.1167822265625, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.115616455078125, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.114495849609375, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.113416748046875, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.111953125, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.11019775390625, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.10822021484375, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.10631103515625, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.103817138671875, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.101123046875, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.097928466796875, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.094432373046875, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.090557861328125, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.085672607421875, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.0812060546875, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.0769189453125, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.0709320068359376, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.063795166015625, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.0572723388671874, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.05138916015625, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.0433453369140624, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.0364581298828126, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.0281939697265625, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.02013671875, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.01163818359375, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.0038531494140623, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.9956756591796876, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.985804443359375, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.9786590576171874, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.9727581787109374, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.9655267333984376, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.960057373046875, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.9544219970703125, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.949307861328125, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.945672607421875, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.94236572265625, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.9404342651367186, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.00798379794927314, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.007956289621070027, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.007934597360435874, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.007924637130927295, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.007921075243502855, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.007919413754716515, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.007918646277394146, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.007918415120802819, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.007918426054529845, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.00791827864246443, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.007918225368484855, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.007917952651623636, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.007918071569874882, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.007918036375194788, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.007918185219168664, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.007918060922529549, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.007918083583936095, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.007917565759271383, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.007917457642033696, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.007917666567955166, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.007917349350173027, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.007917437222786247, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.007917565098032354, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.007917201037053019, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.007917212808970363, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.007917286045849323, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.007917885282076896, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.007917894339188934, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.00791857551317662, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.007919008003082127, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.007920032544061541, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.007920813709497453, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.007922353541944175, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.007923659346997737, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.007925168983638287, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.007927456055767834, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.007931284457445145, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.007935678493231535, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.007941878563724459, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.007951203719712793, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.007960909672547131, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.007971421866677701, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.007987745807040482, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.008003561380319298, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.008024429876822978, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.00804899366106838, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.008072132486850023, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.00810572545742616, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.00813864519353956, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.125235080718994, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1243464946746826, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.123488187789917, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1230082511901855, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1226892471313477, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1223647594451904, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1220526695251465, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.121744155883789, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.121359348297119, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1209192276000977, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.120502471923828, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1198554039001465, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.119230270385742, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1183011531829834, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.11739444732666, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1165058612823486, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1153180599212646, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1138718128204346, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1121954917907715, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.110553503036499, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.1084349155426025, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.106112480163574, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.103415012359619, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.100353479385376, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.0970396995544434, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.0928690433502197, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.088967800140381, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.0853235721588135, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.080265998840332, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.074172258377075, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.068753719329834, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.0638234615325928, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.057337522506714, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.0517001152038574, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.045199394226074, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.039008378982544, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.0326974391937256, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.0269837379455566, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.021096706390381, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.014293670654297, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.0094449520111084, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.0054779052734375, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.000875234603882, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.99737548828125, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.9939873218536377, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.991182565689087, "validation/loss_046_lr3.6e+01_wd1.0e+00": 2.9896225929260254, "validation/loss_047_lr4.3e+01_wd1.0e+00": 2.988551616668701, "validation/loss_048_lr5.0e+01_wd1.0e+00": 2.9884603023529053, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.0636766334440753, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.0636766334440753, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.0636766334440753, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06404577334809892, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06459948320413436, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06496862310815799, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.06736803248431156, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.07013658176448874, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.073827980804725, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.0769656699889258, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.07899593946105574, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.08194905869324474, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.08767072720561092, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.09062384643779993, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.09191583610188261, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.09616094499815431, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.0976375046142488, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.10040605389442599, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.10280546327057954, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.10520487264673312, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.10926541159099298, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.1111111111111111, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.11055740125507567, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.11277224067921743, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.11590992986341823, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.1168327796234773, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.1184939091915836, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.11923218899963087, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.1197858988556663, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.12163159837578442, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.12200073827980805, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.1256921373200443, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.1256921373200443, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.12550756736803248, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.12753783684016243, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.12643041712809155, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.006981481739356469, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.006260399061499035, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.006036555177156872, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.0057093707982013376, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.0055234280048811505, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.0057205359865420925, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.0055234280048811505, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.005697462292469462, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.005881564417829309, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.006060863442350232, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.006070595747857143, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.0062163136820189225, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.006339168916474157, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.006453532315906276, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.006590183540887177, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.006525443848890177, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.00699162364650031, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.00759410509725635, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.008077023500551296, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.010226710768323504, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.01283394222897818, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.016532982321218064, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.018959864675836723, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.02033784643438918, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.02308431685291251, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.028209989628188187, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.03247639869616483, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.034700760906010854, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.038641192935970035, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.040276555126583985, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.04248455993817218, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.04502777314570292, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.04698609029057368, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.04983609755795044, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.051541172915754524, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.05273951158127369, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.05425828488802905, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.056086468678003855, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.058069477681493675, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.05989935259738607, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.061815529555406756, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.06229828303639112, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.06339845448267785, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.06423964122033696, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.06752635766266661, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.06804538994545967, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.06874000611949785, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.07046420411465402, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.06955220925786451, "id_best": 47, "lr_best": 0.012899999999999998, "wd_best": 0.05, "train/loss_best": 2.94236572265625, "validation/loss_best": 2.988551616668701, "validation/acc_best": 0.12753783684016243, "validation/f1_best": 0.07046420411465402} +{"epoch": 18, "train/lr": 7.5829098008590064e-06, "train/loss": 3.0672706460952757, "train/grad": 0.056719390023499724, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.130048828125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.12940673828125, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.128778076171875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.1284228515625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.128221435546875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.127935791015625, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.127659912109375, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.127313232421875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.126748046875, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.126240234375, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.12570068359375, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.12489990234375, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.1242138671875, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.12300537109375, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.12184814453125, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.12066162109375, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.119212646484375, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.117442626953125, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.115367431640625, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.113292236328125, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.110699462890625, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.107855224609375, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.104610595703125, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.1008984375, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.09693359375, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.091864013671875, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.087181396484375, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.082689208984375, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.0766217041015627, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.0691876220703125, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.06252197265625, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.05638916015625, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.0482427978515627, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.04100341796875, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.032464599609375, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.024151611328125, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.0153857421875, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.0073089599609375, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.9987640380859375, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.988372802734375, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.9808245849609376, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.97446044921875, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.966661376953125, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.9605718994140626, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.954251708984375, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.9483966064453124, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.9441519165039063, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.939974670410156, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.9374053955078123, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.008152363442350178, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.008129430529661476, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.008112591521348805, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.008106182513292879, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.008104252726770938, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008103929252829403, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.008103927250485867, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.008104289581533522, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.008104510330595076, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.008104631113819778, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.00810425820061937, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.008104223180562259, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.008104097836185247, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.00810408006189391, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.008103790876921266, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.008103285704273731, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.008102809463161975, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.008102177111431956, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.008101345144677908, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.008100991626270116, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.008100261439103633, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.008099367232061923, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.008097684599924833, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.00809692457318306, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.008095316027756781, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.008093947842717171, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.008092023998033255, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.008091127348598093, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.008088830180931837, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.008087113483343273, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.008085399619303643, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.008083242690190673, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.008082701934035867, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.008081815601326526, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.008081593287643045, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.008081110520288348, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.008081620757002384, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.008082442658487708, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.008083482030779124, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.008086487972177566, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.008089073738083243, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.008091760633978992, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.008097636846359819, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.008103429961483926, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.00811221033334732, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.00812342933146283, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.008133603844325989, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.008148202386219055, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.00816332631278783, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1252145767211914, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.124336004257202, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1234827041625977, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1230108737945557, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.122694253921509, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.122366189956665, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.122044086456299, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.121750593185425, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.121340274810791, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1209185123443604, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1204960346221924, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1198530197143555, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.119237184524536, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1183035373687744, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.117396116256714, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.116506576538086, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1153101921081543, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.113874912261963, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.112165927886963, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.110529661178589, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.108397960662842, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.1060805320739746, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.1033689975738525, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.100321054458618, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.0969431400299072, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.09279465675354, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.0888426303863525, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.0851776599884033, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.080080270767212, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.073951244354248, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.068479061126709, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.0635476112365723, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.057016372680664, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.0513219833374023, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.0448410511016846, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.038620948791504, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.032301187515259, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.0264968872070312, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.0205914974212646, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.013730525970459, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.008845567703247, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.004887580871582, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.0001380443573, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.996548652648926, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.9929349422454834, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.989701509475708, "validation/loss_046_lr3.6e+01_wd1.0e+00": 2.987494707107544, "validation/loss_047_lr4.3e+01_wd1.0e+00": 2.9853627681732178, "validation/loss_048_lr5.0e+01_wd1.0e+00": 2.984099864959717, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06293835363602805, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.0636766334440753, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.0636766334440753, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.0636766334440753, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06386120339608711, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06478405315614617, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06552233296419344, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.06773717238833518, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.07069029162052418, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.07401255075673681, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.07881136950904392, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.07954964931709117, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.08416389811738649, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.08748615725359911, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.08933185677371724, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.09228497600590624, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.09616094499815431, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.09837578442229605, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.1005906238464378, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.10335917312661498, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.10575858250276855, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.10889627168696936, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.11148025101513473, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.11351052048726468, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.11498708010335917, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.1168327796234773, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.11738648947951273, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.11886304909560723, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.12015503875968993, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.12181616832779624, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.12292358803986711, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.12403100775193798, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.12458471760797342, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.12679955703211518, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.12827611664820968, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.12846068660022147, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.12956810631229235, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.007105026308501801, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.0062570292891725885, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.006036555177156872, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.005710254285200319, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.005716675545316917, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.0057205359865420925, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.0055234280048811505, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.0055059178033846625, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.005880281750766619, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.006059221919149943, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.006067397669524591, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.006196119092533412, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.006335024850277891, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.006447027046238049, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.006571781587679117, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.006786858974358974, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.006945039269600301, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.007898237499489808, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.008467656738373837, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.010405084587181174, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.013479717498759113, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.016357696560894187, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.020034319666092874, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.020576041777300397, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.024063505746398234, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.027774169286227265, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.03170426968334145, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.03489754297770723, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.03822474984517138, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.04058836652813896, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.042738310277922444, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.045180918923280765, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.04793561757282772, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.049929063184678706, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.05149541018402012, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.053376158193498745, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.05445835026795686, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.05549779403405417, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.05707215837444244, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.05803131416687027, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.059579659361044764, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.060980457513263205, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.06176128549203369, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.06269937117623212, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.06329940977060107, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.06604727353974697, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.06769839397219572, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.06749008335478891, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.068315075836416, "id_best": 48, "lr_best": 0.015, "wd_best": 0.05, "train/loss_best": 2.9374053955078123, "validation/loss_best": 2.984099864959717, "validation/acc_best": 0.12956810631229235, "validation/f1_best": 0.068315075836416} +{"epoch": 19, "train/lr": 1.0867618231465446e-06, "train/loss": 3.0694238924980164, "train/grad": 0.05629183480516076, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.131534423828125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.130950927734375, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.13026611328125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.129954833984375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.129658203125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.1293701171875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.129102783203125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.12875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.128271484375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.127755126953125, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.12724609375, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.1264453125, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.1257177734375, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.124561767578125, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.123568115234375, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.12235107421875, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.12092041015625, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.11916748046875, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.11716552734375, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.11517822265625, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.112601318359375, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.10986328125, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.1066943359375, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.103057861328125, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.099183349609375, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.094156494140625, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.089473876953125, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.085115966796875, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.0790472412109375, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.071680908203125, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.065010986328125, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.0590167236328125, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.0508587646484373, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.043568115234375, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.0352734375, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.026884765625, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.018321533203125, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.010123291015625, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.001474609375, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.991275634765625, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.9836663818359375, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.977344970703125, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.9695574951171877, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.9633697509765624, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.9570806884765624, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.95114013671875, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.9468316650390625, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.94247802734375, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.939686584472656, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.008111427484545857, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.008088021480944008, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.008070795920211822, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.008063140963204206, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.00806036347290501, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008059671132359654, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.008059418397024273, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.00805921470746398, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.008059630270581692, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.008059514537453651, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.008059373470023274, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.008058851030655205, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.00805862388573587, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.008058570316061378, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.008057787255384028, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.008057290152646602, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.008056794949807227, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.008056166910100727, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.008055188560392708, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.008054438300896437, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.00805310623254627, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.008051626994274556, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.008050277738366276, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.00804861746262759, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.008046750577632338, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.008044409635476767, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.00804210344562307, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.008040734063833953, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.008038318902254104, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.008035331321880222, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.008032833577599376, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.008030658492352814, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.008027295377105474, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.008024481576867401, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.00802153178025037, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.008019418099429458, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.00801686873426661, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.008015016743447631, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.008012877127621323, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.008011076333932578, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.008009903465863317, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.008009398891590535, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.008008334182668476, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.008008658858016134, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.008008422954007983, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.008008929591160268, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.008010301957838237, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.008012336436659098, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.008014340787194669, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.125213146209717, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.124333143234253, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.123481512069702, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1230080127716064, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.122697114944458, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.122368335723877, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1220450401306152, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.12174916267395, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.121340274810791, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1209163665771484, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1204967498779297, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.119854688644409, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.119235038757324, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.118299961090088, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.117391586303711, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1164917945861816, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.115307092666626, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.113882064819336, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1121771335601807, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.1105234622955322, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.1083943843841553, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.106081247329712, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.103362798690796, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.100306510925293, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.0969479084014893, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.092750072479248, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.088829278945923, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.085174083709717, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.0800600051879883, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.073944330215454, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.068455934524536, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.0635414123535156, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.057013988494873, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.0513415336608887, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.0448923110961914, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.0387163162231445, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.0324349403381348, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.026707172393799, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.0208687782287598, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.0141122341156006, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.009352207183838, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.0054402351379395, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.0008766651153564, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.9974210262298584, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.9939091205596924, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.990724563598633, "validation/loss_046_lr3.6e+01_wd1.0e+00": 2.9884591102600098, "validation/loss_047_lr4.3e+01_wd1.0e+00": 2.9862351417541504, "validation/loss_048_lr5.0e+01_wd1.0e+00": 2.9848053455352783, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06293835363602805, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.0636766334440753, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.0636766334440753, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.0636766334440753, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06386120339608711, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06459948320413436, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06570690291620525, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.06773717238833518, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.07087486157253599, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.07419712070874862, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.07899593946105574, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.07973421926910298, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.08416389811738649, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.08803986710963455, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.08951642672572906, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.09210040605389443, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.09653008490217793, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.09874492432631968, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.10169804355850867, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.10391288298265043, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.10686600221483943, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.10871170173495755, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.11129568106312292, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.11295681063122924, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.11517165005537099, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.11609449981543005, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.1168327796234773, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.11775562938353636, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.1197858988556663, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.12181616832779624, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.12200073827980805, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.12347729789590255, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.12679955703211518, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.12809154669619785, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.12790697674418605, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.12975267626430417, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.13104466592838687, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.007105026308501801, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.0062570292891725885, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.006036555177156872, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.0057093707982013376, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.005716675545316917, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.005524982529699511, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.0055229233383439, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.005504988622440049, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.005881564417829309, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.006059221919149943, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.006051185326969607, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.006177817514358756, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.006335024850277891, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.006609419263456091, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.006571781587679117, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.0067843957510041126, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.006938955399172715, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.007872770202572236, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.008577720519292778, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.010373913210082287, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.013563467366182523, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.01642609244972928, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.020120233156509355, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.020577457726090743, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.024223717177602227, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.028554753301333016, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.03232434513892798, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.03479019499589859, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.038628812884160875, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.04097741501039923, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.04421743829448549, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.045769396785986016, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.048345222226213395, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.049552357069351925, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.051313954346177415, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.05303236289530724, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.054706282690286594, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.05522044047637403, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.05618554432236336, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.05767811016694933, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.0594093473887336, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.06087223349322116, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.06083293232525624, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.06187472198290187, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.06513090358945785, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.06557486721260393, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.06571344275421981, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.06684129549677767, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.06727705151638409, "id_best": 48, "lr_best": 0.015, "wd_best": 0.05, "train/loss_best": 2.939686584472656, "validation/loss_best": 2.9848053455352783, "validation/acc_best": 0.13104466592838687, "validation/f1_best": 0.06727705151638409} diff --git a/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__attn/config.yaml b/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__attn/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..ac78b40f74ef463fbcf305d2fcb34fe56c2c9c47 --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__attn/config.yaml @@ -0,0 +1,96 @@ +output_root: experiments/decoders/output +name_prefix: eval_probe +remote_root: null +notes: decoder ablations crossreg_reg4; eval v2 (nsd_cococlip reg attn) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +dataset_kwargs: {} +classifier_kwargs: + embed_dim: null + dropout: 0.0 + xavier_init: false + norm: false +lr_scale_grid: +- 0.02 +- 0.023 +- 0.028 +- 0.033 +- 0.038 +- 0.045 +- 0.053 +- 0.062 +- 0.074 +- 0.087 +- 0.1 +- 0.12 +- 0.14 +- 0.17 +- 0.2 +- 0.23 +- 0.27 +- 0.32 +- 0.38 +- 0.44 +- 0.52 +- 0.61 +- 0.72 +- 0.85 +- 1 +- 1.2 +- 1.4 +- 1.6 +- 1.9 +- 2.3 +- 2.7 +- 3.1 +- 3.7 +- 4.3 +- 5.1 +- 6 +- 7.1 +- 8.3 +- 9.8 +- 12 +- 14 +- 16 +- 19 +- 22 +- 26 +- 31 +- 36 +- 43 +- 50 +wd_scale_grid: +- 1.0 +num_workers: 8 +prefetch_factor: null +balanced_sampling: false +epochs: 20 +steps_per_epoch: 200 +batch_size: 64 +accum_iter: 2 +lr: 0.0003 +warmup_epochs: 5 +no_decay: false +weight_decay: 0.05 +clip_grad: 1.0 +metrics: +- acc +- f1 +cv_metric: acc +early_stopping: true +amp: true +device: cuda +seed: 4466 +debug: false +wandb: false +wandb_entity: null +wandb_project: fMRI-fm-eval +name: decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__attn +model: flat_mae +representation: reg +classifier: attn +dataset: nsd_cococlip +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__attn +remote_dir: null diff --git a/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__attn/eval_log.json b/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__attn/eval_log.json new file mode 100644 index 0000000000000000000000000000000000000000..83b665872ddc67855b99bfa227971fe91dfbc484 --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__attn/eval_log.json @@ -0,0 +1 @@ +{"eval/epoch": 19, "eval/id_best": 35, "eval/lr_best": 0.0018, "eval/wd_best": 0.05, "eval/train/loss": 2.1274821758270264, "eval/train/acc": 0.3640247088109653, "eval/train/acc_std": 0.0025284851858652082, "eval/train/f1": 0.31873222709541577, "eval/train/f1_std": 0.0027627875641306437, "eval/validation/loss": 2.5683116912841797, "eval/validation/acc": 0.24363233665559247, "eval/validation/acc_std": 0.004981124938708288, "eval/validation/f1": 0.18654225620531506, "eval/validation/f1_std": 0.004580960859529901, "eval/test/loss": 2.537184953689575, "eval/test/acc": 0.26419294990723563, "eval/test/acc_std": 0.005167695749309386, "eval/test/f1": 0.199127492909933, "eval/test/f1_std": 0.005029126758782687, "eval/testid/loss": 2.5783143043518066, "eval/testid/acc": 0.23809523809523808, "eval/testid/acc_std": 0.0053545746535052985, "eval/testid/f1": 0.19291439674754884, "eval/testid/f1_std": 0.005023209162255894} diff --git a/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__attn/eval_log_best.json b/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__attn/eval_log_best.json new file mode 100644 index 0000000000000000000000000000000000000000..9a6c4437fb0931ae539ed63903603f4c311c4206 --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__attn/eval_log_best.json @@ -0,0 +1 @@ +{"eval/best/epoch": 19, "eval/best/id_best": 35, "eval/best/lr_best": 0.0018, "eval/best/wd_best": 0.05, "eval/best/train/loss": 2.1274821758270264, "eval/best/train/acc": 0.3640247088109653, "eval/best/train/acc_std": 0.0025284851858652082, "eval/best/train/f1": 0.31873222709541577, "eval/best/train/f1_std": 0.0027627875641306437, "eval/best/validation/loss": 2.5683116912841797, "eval/best/validation/acc": 0.24363233665559247, "eval/best/validation/acc_std": 0.004981124938708288, "eval/best/validation/f1": 0.18654225620531506, "eval/best/validation/f1_std": 0.004580960859529901, "eval/best/test/loss": 2.537184953689575, "eval/best/test/acc": 0.26419294990723563, "eval/best/test/acc_std": 0.005167695749309386, "eval/best/test/f1": 0.199127492909933, "eval/best/test/f1_std": 0.005029126758782687, "eval/best/testid/loss": 2.5783143043518066, "eval/best/testid/acc": 0.23809523809523808, "eval/best/testid/acc_std": 0.0053545746535052985, "eval/best/testid/f1": 0.19291439674754884, "eval/best/testid/f1_std": 0.005023209162255894} diff --git a/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__attn/eval_log_last.json b/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__attn/eval_log_last.json new file mode 100644 index 0000000000000000000000000000000000000000..26798b104dbdfd6f2c723cff8e6d73d075cb6dd9 --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__attn/eval_log_last.json @@ -0,0 +1 @@ +{"eval/last/epoch": 19, "eval/last/id_best": 35, "eval/last/lr_best": 0.0018, "eval/last/wd_best": 0.05, "eval/last/train/loss": 2.1274821758270264, "eval/last/train/acc": 0.3640247088109653, "eval/last/train/acc_std": 0.0025284851858652082, "eval/last/train/f1": 0.31873222709541577, "eval/last/train/f1_std": 0.0027627875641306437, "eval/last/validation/loss": 2.5683116912841797, "eval/last/validation/acc": 0.24363233665559247, "eval/last/validation/acc_std": 0.004981124938708288, "eval/last/validation/f1": 0.18654225620531506, "eval/last/validation/f1_std": 0.004580960859529901, "eval/last/test/loss": 2.537184953689575, "eval/last/test/acc": 0.26419294990723563, "eval/last/test/acc_std": 0.005167695749309386, "eval/last/test/f1": 0.199127492909933, "eval/last/test/f1_std": 0.005029126758782687, "eval/last/testid/loss": 2.5783143043518066, "eval/last/testid/acc": 0.23809523809523808, "eval/last/testid/acc_std": 0.0053545746535052985, "eval/last/testid/f1": 0.19291439674754884, "eval/last/testid/f1_std": 0.005023209162255894} diff --git a/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__attn/eval_table.csv b/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__attn/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..44608cc1ff22fd25bd89c4b043fdb166187b8593 --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__attn/eval_table.csv @@ -0,0 +1,5 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,reg,attn,nsd_cococlip,best,19,0.0018,0.05,35,"[6, 1.0]",train,2.1274821758270264,0.3640247088109653,0.0025284851858652082,0.31873222709541577,0.0027627875641306437 +flat_mae,reg,attn,nsd_cococlip,best,19,0.0018,0.05,35,"[6, 1.0]",validation,2.5683116912841797,0.24363233665559247,0.004981124938708288,0.18654225620531506,0.004580960859529901 +flat_mae,reg,attn,nsd_cococlip,best,19,0.0018,0.05,35,"[6, 1.0]",test,2.537184953689575,0.26419294990723563,0.005167695749309386,0.199127492909933,0.005029126758782687 +flat_mae,reg,attn,nsd_cococlip,best,19,0.0018,0.05,35,"[6, 1.0]",testid,2.5783143043518066,0.23809523809523808,0.0053545746535052985,0.19291439674754884,0.005023209162255894 diff --git a/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__attn/eval_table_best.csv b/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__attn/eval_table_best.csv new file mode 100644 index 0000000000000000000000000000000000000000..44608cc1ff22fd25bd89c4b043fdb166187b8593 --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__attn/eval_table_best.csv @@ -0,0 +1,5 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,reg,attn,nsd_cococlip,best,19,0.0018,0.05,35,"[6, 1.0]",train,2.1274821758270264,0.3640247088109653,0.0025284851858652082,0.31873222709541577,0.0027627875641306437 +flat_mae,reg,attn,nsd_cococlip,best,19,0.0018,0.05,35,"[6, 1.0]",validation,2.5683116912841797,0.24363233665559247,0.004981124938708288,0.18654225620531506,0.004580960859529901 +flat_mae,reg,attn,nsd_cococlip,best,19,0.0018,0.05,35,"[6, 1.0]",test,2.537184953689575,0.26419294990723563,0.005167695749309386,0.199127492909933,0.005029126758782687 +flat_mae,reg,attn,nsd_cococlip,best,19,0.0018,0.05,35,"[6, 1.0]",testid,2.5783143043518066,0.23809523809523808,0.0053545746535052985,0.19291439674754884,0.005023209162255894 diff --git a/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__attn/eval_table_last.csv b/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__attn/eval_table_last.csv new file mode 100644 index 0000000000000000000000000000000000000000..2a130e4937a26b3a24ddbbe4ffa503ea7694b42b --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__attn/eval_table_last.csv @@ -0,0 +1,5 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,reg,attn,nsd_cococlip,last,19,0.0018,0.05,35,"[6, 1.0]",train,2.1274821758270264,0.3640247088109653,0.0025284851858652082,0.31873222709541577,0.0027627875641306437 +flat_mae,reg,attn,nsd_cococlip,last,19,0.0018,0.05,35,"[6, 1.0]",validation,2.5683116912841797,0.24363233665559247,0.004981124938708288,0.18654225620531506,0.004580960859529901 +flat_mae,reg,attn,nsd_cococlip,last,19,0.0018,0.05,35,"[6, 1.0]",test,2.537184953689575,0.26419294990723563,0.005167695749309386,0.199127492909933,0.005029126758782687 +flat_mae,reg,attn,nsd_cococlip,last,19,0.0018,0.05,35,"[6, 1.0]",testid,2.5783143043518066,0.23809523809523808,0.0053545746535052985,0.19291439674754884,0.005023209162255894 diff --git a/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__attn/log.txt b/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__attn/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..780191cd3cff76c9482d2e6cec92f62a31bb1f64 --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__attn/log.txt @@ -0,0 +1,965 @@ +fMRI foundation model probe eval +version: 0.1.dev65+g4003a1397 +sha: 6c01b606db98add5848cecd23e5d599250c0bf86, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-02-24 23:41:52 +config: +output_root: experiments/decoders/output +name_prefix: eval_probe +remote_root: null +notes: decoder ablations crossreg_reg4; eval v2 (nsd_cococlip reg attn) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +dataset_kwargs: {} +classifier_kwargs: + embed_dim: null + dropout: 0.0 + xavier_init: false + norm: false +lr_scale_grid: +- 0.02 +- 0.023 +- 0.028 +- 0.033 +- 0.038 +- 0.045 +- 0.053 +- 0.062 +- 0.074 +- 0.087 +- 0.1 +- 0.12 +- 0.14 +- 0.17 +- 0.2 +- 0.23 +- 0.27 +- 0.32 +- 0.38 +- 0.44 +- 0.52 +- 0.61 +- 0.72 +- 0.85 +- 1 +- 1.2 +- 1.4 +- 1.6 +- 1.9 +- 2.3 +- 2.7 +- 3.1 +- 3.7 +- 4.3 +- 5.1 +- 6 +- 7.1 +- 8.3 +- 9.8 +- 12 +- 14 +- 16 +- 19 +- 22 +- 26 +- 31 +- 36 +- 43 +- 50 +wd_scale_grid: +- 1.0 +num_workers: 8 +prefetch_factor: null +balanced_sampling: false +epochs: 20 +steps_per_epoch: 200 +batch_size: 64 +accum_iter: 2 +lr: 0.0003 +warmup_epochs: 5 +no_decay: false +weight_decay: 0.05 +clip_grad: 1.0 +metrics: +- acc +- f1 +cv_metric: acc +early_stopping: true +amp: true +device: cuda +seed: 4466 +debug: false +wandb: false +wandb_entity: null +wandb_project: fMRI-fm-eval +name: decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__attn +model: flat_mae +representation: reg +classifier: attn +dataset: nsd_cococlip +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__attn +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=False, reg_tokens=4, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: nsd_cococlip (flat) +train (n=32539): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'run', 'trial_id', 'nsd_id', 'category_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 32539 +}), + labels=[ 3 4 5 6 10 11 17 18 19 20 22 23 25 30 31 33 36 37 38 53 55 59 61 74], + counts=[1286 1180 1639 1868 834 824 1026 1042 913 1853 1503 2092 1001 1410 + 794 1241 1904 1872 2267 1428 889 904 1447 1322] +) + +validation (n=5418): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'run', 'trial_id', 'nsd_id', 'category_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 5418 +}), + labels=[ 3 4 5 6 10 11 17 18 19 20 22 23 25 30 31 33 36 37 38 53 55 59 61 74], + counts=[197 161 276 345 126 142 143 185 112 295 285 387 169 250 159 193 316 334 + 343 215 172 141 226 246] +) + +test (n=5390): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'run', 'trial_id', 'nsd_id', 'category_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 5390 +}), + labels=[ 3 4 5 6 10 11 17 18 19 20 22 23 25 30 31 33 36 37 38 53 55 59 61 74], + counts=[202 172 274 298 144 180 134 182 186 293 218 343 165 185 140 177 346 333 + 345 271 165 140 251 246] +) + +testid (n=5187): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'run', 'trial_id', 'nsd_id', 'category_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 5187 +}), + labels=[ 3 4 5 6 10 11 17 18 19 20 22 23 25 30 31 33 36 37 38 53 55 59 61 74], + counts=[197 159 267 273 123 153 175 184 139 310 215 386 153 230 118 192 330 306 + 349 223 143 127 249 186] +) + +running backbone on example batch to get embedding dim +embedding feature dim (reg): 768 +initializing sweep of classifier heads +classifiers: +ModuleList( + (0-48): 49 x AttnPoolClassifier( + (kv): Linear(in_features=768, out_features=1536, bias=True) + (linear): Linear(in_features=768, out_features=24, bias=True) + ) +) +classifier params (train): 58.8M (58.8M) +setting up optimizer +total batch size: 128 = 64 bs per gpu x 2 accum +lr: 3.00e-04 +full schedule: epochs = 20 (steps = 4000) (decay = True) +warmup: epochs = 5 (steps = 1000) +start training for 20 epochs +train: [0] [ 0/400] eta: 0:22:34 lr: nan time: 3.3870 data: 2.9192 max mem: 4136 +train: [0] [ 20/400] eta: 0:03:16 lr: 0.000003 loss: 3.1781 (3.1789) grad: 0.0684 (0.0709) time: 0.3749 data: 0.0046 max mem: 4841 +train: [0] [ 40/400] eta: 0:02:36 lr: 0.000006 loss: 3.1771 (3.1757) grad: 0.0681 (0.0698) time: 0.3482 data: 0.0041 max mem: 4841 +train: [0] [ 60/400] eta: 0:02:16 lr: 0.000009 loss: 3.1718 (3.1737) grad: 0.0655 (0.0690) time: 0.3352 data: 0.0037 max mem: 4841 +train: [0] [ 80/400] eta: 0:02:04 lr: 0.000012 loss: 3.1675 (3.1720) grad: 0.0668 (0.0692) time: 0.3425 data: 0.0041 max mem: 4841 +train: [0] [100/400] eta: 0:01:53 lr: 0.000015 loss: 3.1634 (3.1706) grad: 0.0652 (0.0682) time: 0.3339 data: 0.0041 max mem: 4841 +train: [0] [120/400] eta: 0:01:43 lr: 0.000018 loss: 3.1634 (3.1686) grad: 0.0620 (0.0671) time: 0.3405 data: 0.0042 max mem: 4841 +train: [0] [140/400] eta: 0:01:34 lr: 0.000021 loss: 3.1602 (3.1670) grad: 0.0620 (0.0669) time: 0.3293 data: 0.0041 max mem: 4841 +train: [0] [160/400] eta: 0:01:26 lr: 0.000024 loss: 3.1532 (3.1650) grad: 0.0659 (0.0669) time: 0.3300 data: 0.0039 max mem: 4841 +train: [0] [180/400] eta: 0:01:18 lr: 0.000027 loss: 3.1532 (3.1643) grad: 0.0636 (0.0663) time: 0.3324 data: 0.0038 max mem: 4841 +train: [0] [200/400] eta: 0:01:11 lr: 0.000030 loss: 3.1520 (3.1632) grad: 0.0598 (0.0660) time: 0.3614 data: 0.0041 max mem: 4841 +train: [0] [220/400] eta: 0:01:04 lr: 0.000033 loss: 3.1427 (3.1612) grad: 0.0677 (0.0663) time: 0.3571 data: 0.0041 max mem: 4841 +train: [0] [240/400] eta: 0:00:57 lr: 0.000036 loss: 3.1348 (3.1596) grad: 0.0677 (0.0661) time: 0.3426 data: 0.0038 max mem: 4841 +train: [0] [260/400] eta: 0:00:49 lr: 0.000039 loss: 3.1433 (3.1584) grad: 0.0657 (0.0663) time: 0.3376 data: 0.0041 max mem: 4841 +train: [0] [280/400] eta: 0:00:42 lr: 0.000042 loss: 3.1348 (3.1566) grad: 0.0680 (0.0664) time: 0.3376 data: 0.0040 max mem: 4841 +train: [0] [300/400] eta: 0:00:35 lr: 0.000045 loss: 3.1339 (3.1546) grad: 0.0687 (0.0667) time: 0.3586 data: 0.0040 max mem: 4841 +train: [0] [320/400] eta: 0:00:28 lr: 0.000048 loss: 3.1182 (3.1525) grad: 0.0700 (0.0670) time: 0.3554 data: 0.0042 max mem: 4841 +train: [0] [340/400] eta: 0:00:21 lr: 0.000051 loss: 3.1080 (3.1499) grad: 0.0741 (0.0675) time: 0.3491 data: 0.0041 max mem: 4841 +train: [0] [360/400] eta: 0:00:14 lr: 0.000054 loss: 3.1154 (3.1488) grad: 0.0705 (0.0678) time: 0.3384 data: 0.0039 max mem: 4841 +train: [0] [380/400] eta: 0:00:07 lr: 0.000057 loss: 3.1197 (3.1464) grad: 0.0702 (0.0679) time: 0.3465 data: 0.0039 max mem: 4841 +train: [0] [399/400] eta: 0:00:00 lr: 0.000060 loss: 3.0974 (3.1439) grad: 0.0712 (0.0681) time: 0.3608 data: 0.0041 max mem: 4841 +train: [0] Total time: 0:02:21 (0.3534 s / it) +train: [0] Summary: lr: 0.000060 loss: 3.0974 (3.1439) grad: 0.0712 (0.0681) +eval (validation): [0] [ 0/85] eta: 0:04:36 time: 3.2559 data: 3.0558 max mem: 4841 +eval (validation): [0] [20/85] eta: 0:00:29 time: 0.3131 data: 0.0057 max mem: 4841 +eval (validation): [0] [40/85] eta: 0:00:17 time: 0.3285 data: 0.0054 max mem: 4841 +eval (validation): [0] [60/85] eta: 0:00:09 time: 0.2952 data: 0.0034 max mem: 4841 +eval (validation): [0] [80/85] eta: 0:00:01 time: 0.2981 data: 0.0039 max mem: 4841 +eval (validation): [0] [84/85] eta: 0:00:00 time: 0.2972 data: 0.0038 max mem: 4841 +eval (validation): [0] Total time: 0:00:29 (0.3459 s / it) +cv: [0] best hparam: (50, 1.0) (048) ('048_lr5.0e+01_wd1.0e+00') loss: 2.838 acc: 0.164 f1: 0.082 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__attn/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__attn/checkpoint-best.pth +train: [1] [ 0/400] eta: 0:21:50 lr: nan time: 3.2771 data: 3.0502 max mem: 4841 +train: [1] [ 20/400] eta: 0:03:05 lr: 0.000063 loss: 3.0790 (3.0921) grad: 0.0783 (0.0792) time: 0.3500 data: 0.0045 max mem: 4841 +train: [1] [ 40/400] eta: 0:02:32 lr: 0.000066 loss: 3.0756 (3.0830) grad: 0.0773 (0.0778) time: 0.3561 data: 0.0042 max mem: 4841 +train: [1] [ 60/400] eta: 0:02:14 lr: 0.000069 loss: 3.0680 (3.0812) grad: 0.0786 (0.0788) time: 0.3404 data: 0.0044 max mem: 4841 +train: [1] [ 80/400] eta: 0:02:01 lr: 0.000072 loss: 3.0543 (3.0777) grad: 0.0821 (0.0805) time: 0.3297 data: 0.0041 max mem: 4841 +train: [1] [100/400] eta: 0:01:52 lr: 0.000075 loss: 3.0601 (3.0757) grad: 0.0848 (0.0812) time: 0.3536 data: 0.0040 max mem: 4841 +train: [1] [120/400] eta: 0:01:43 lr: 0.000078 loss: 3.0684 (3.0735) grad: 0.0861 (0.0820) time: 0.3495 data: 0.0043 max mem: 4841 +train: [1] [140/400] eta: 0:01:35 lr: 0.000081 loss: 3.0637 (3.0725) grad: 0.0824 (0.0818) time: 0.3330 data: 0.0043 max mem: 4841 +train: [1] [160/400] eta: 0:01:27 lr: 0.000084 loss: 3.0557 (3.0716) grad: 0.0821 (0.0824) time: 0.3591 data: 0.0045 max mem: 4841 +train: [1] [180/400] eta: 0:01:19 lr: 0.000087 loss: 3.0619 (3.0697) grad: 0.0848 (0.0832) time: 0.3464 data: 0.0039 max mem: 4841 +train: [1] [200/400] eta: 0:01:12 lr: 0.000090 loss: 3.0506 (3.0668) grad: 0.0867 (0.0834) time: 0.3736 data: 0.0045 max mem: 4841 +train: [1] [220/400] eta: 0:01:04 lr: 0.000093 loss: 3.0407 (3.0644) grad: 0.0886 (0.0841) time: 0.3335 data: 0.0044 max mem: 4841 +train: [1] [240/400] eta: 0:00:57 lr: 0.000096 loss: 3.0308 (3.0615) grad: 0.0910 (0.0849) time: 0.3430 data: 0.0041 max mem: 4841 +train: [1] [260/400] eta: 0:00:50 lr: 0.000099 loss: 3.0316 (3.0599) grad: 0.0947 (0.0862) time: 0.3461 data: 0.0042 max mem: 4841 +train: [1] [280/400] eta: 0:00:42 lr: 0.000102 loss: 3.0494 (3.0597) grad: 0.0905 (0.0863) time: 0.3461 data: 0.0046 max mem: 4841 +train: [1] [300/400] eta: 0:00:35 lr: 0.000105 loss: 3.0432 (3.0576) grad: 0.0860 (0.0862) time: 0.3402 data: 0.0038 max mem: 4841 +train: [1] [320/400] eta: 0:00:28 lr: 0.000108 loss: 3.0128 (3.0561) grad: 0.0863 (0.0867) time: 0.3600 data: 0.0042 max mem: 4841 +train: [1] [340/400] eta: 0:00:21 lr: 0.000111 loss: 3.0122 (3.0543) grad: 0.0965 (0.0874) time: 0.3538 data: 0.0040 max mem: 4841 +train: [1] [360/400] eta: 0:00:14 lr: 0.000114 loss: 3.0217 (3.0525) grad: 0.0979 (0.0880) time: 0.3357 data: 0.0039 max mem: 4841 +train: [1] [380/400] eta: 0:00:07 lr: 0.000117 loss: 3.0217 (3.0500) grad: 0.0898 (0.0878) time: 0.3472 data: 0.0040 max mem: 4841 +train: [1] [399/400] eta: 0:00:00 lr: 0.000120 loss: 3.0296 (3.0514) grad: 0.0863 (0.0881) time: 0.3622 data: 0.0042 max mem: 4841 +train: [1] Total time: 0:02:22 (0.3555 s / it) +train: [1] Summary: lr: 0.000120 loss: 3.0296 (3.0514) grad: 0.0863 (0.0881) +eval (validation): [1] [ 0/85] eta: 0:04:40 time: 3.2945 data: 3.0947 max mem: 4841 +eval (validation): [1] [20/85] eta: 0:00:30 time: 0.3304 data: 0.0265 max mem: 4841 +eval (validation): [1] [40/85] eta: 0:00:18 time: 0.3355 data: 0.0225 max mem: 4841 +eval (validation): [1] [60/85] eta: 0:00:09 time: 0.3449 data: 0.0054 max mem: 4841 +eval (validation): [1] [80/85] eta: 0:00:01 time: 0.3007 data: 0.0031 max mem: 4841 +eval (validation): [1] [84/85] eta: 0:00:00 time: 0.3031 data: 0.0037 max mem: 4841 +eval (validation): [1] Total time: 0:00:31 (0.3655 s / it) +cv: [1] best hparam: (7.1, 1.0) (036) ('036_lr7.1e+00_wd1.0e+00') loss: 2.740 acc: 0.187 f1: 0.115 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__attn/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__attn/checkpoint-best.pth +train: [2] [ 0/400] eta: 0:22:13 lr: nan time: 3.3346 data: 3.0584 max mem: 4841 +train: [2] [ 20/400] eta: 0:03:01 lr: 0.000123 loss: 2.9584 (2.9652) grad: 0.0939 (0.0959) time: 0.3347 data: 0.0121 max mem: 4841 +train: [2] [ 40/400] eta: 0:02:26 lr: 0.000126 loss: 2.9761 (2.9831) grad: 0.1023 (0.1016) time: 0.3317 data: 0.0042 max mem: 4841 +train: [2] [ 60/400] eta: 0:02:10 lr: 0.000129 loss: 2.9880 (2.9880) grad: 0.1051 (0.1044) time: 0.3380 data: 0.0037 max mem: 4841 +train: [2] [ 80/400] eta: 0:01:57 lr: 0.000132 loss: 2.9904 (2.9878) grad: 0.1038 (0.1043) time: 0.3215 data: 0.0043 max mem: 4841 +train: [2] [100/400] eta: 0:01:49 lr: 0.000135 loss: 2.9947 (2.9920) grad: 0.1038 (0.1042) time: 0.3442 data: 0.0040 max mem: 4841 +train: [2] [120/400] eta: 0:01:42 lr: 0.000138 loss: 2.9841 (2.9876) grad: 0.0985 (0.1033) time: 0.3806 data: 0.0049 max mem: 4841 +train: [2] [140/400] eta: 0:01:34 lr: 0.000141 loss: 2.9801 (2.9914) grad: 0.0974 (0.1028) time: 0.3549 data: 0.0042 max mem: 4841 +train: [2] [160/400] eta: 0:01:27 lr: 0.000144 loss: 2.9989 (2.9915) grad: 0.1006 (0.1041) time: 0.3540 data: 0.0042 max mem: 4841 +train: [2] [180/400] eta: 0:01:19 lr: 0.000147 loss: 2.9989 (2.9940) grad: 0.1109 (0.1053) time: 0.3447 data: 0.0043 max mem: 4841 +train: [2] [200/400] eta: 0:01:11 lr: 0.000150 loss: 3.0024 (2.9956) grad: 0.1092 (0.1059) time: 0.3306 data: 0.0042 max mem: 4841 +train: [2] [220/400] eta: 0:01:04 lr: 0.000153 loss: 2.9572 (2.9898) grad: 0.1058 (0.1060) time: 0.3627 data: 0.0043 max mem: 4841 +train: [2] [240/400] eta: 0:00:57 lr: 0.000156 loss: 2.9436 (2.9875) grad: 0.1077 (0.1068) time: 0.3391 data: 0.0043 max mem: 4841 +train: [2] [260/400] eta: 0:00:49 lr: 0.000159 loss: 2.9623 (2.9866) grad: 0.1108 (0.1074) time: 0.3208 data: 0.0036 max mem: 4841 +train: [2] [280/400] eta: 0:00:42 lr: 0.000162 loss: 2.9699 (2.9862) grad: 0.1059 (0.1070) time: 0.3416 data: 0.0039 max mem: 4841 +train: [2] [300/400] eta: 0:00:35 lr: 0.000165 loss: 2.9613 (2.9838) grad: 0.1020 (0.1068) time: 0.3371 data: 0.0042 max mem: 4841 +train: [2] [320/400] eta: 0:00:28 lr: 0.000168 loss: 2.9544 (2.9818) grad: 0.1046 (0.1069) time: 0.3353 data: 0.0041 max mem: 4841 +train: [2] [340/400] eta: 0:00:21 lr: 0.000171 loss: 2.9544 (2.9807) grad: 0.1074 (0.1072) time: 0.3339 data: 0.0039 max mem: 4841 +train: [2] [360/400] eta: 0:00:13 lr: 0.000174 loss: 2.9541 (2.9802) grad: 0.1098 (0.1073) time: 0.3360 data: 0.0041 max mem: 4841 +train: [2] [380/400] eta: 0:00:06 lr: 0.000177 loss: 2.9541 (2.9792) grad: 0.1120 (0.1076) time: 0.3266 data: 0.0040 max mem: 4841 +train: [2] [399/400] eta: 0:00:00 lr: 0.000180 loss: 2.9520 (2.9782) grad: 0.1107 (0.1077) time: 0.3344 data: 0.0041 max mem: 4841 +train: [2] Total time: 0:02:19 (0.3478 s / it) +train: [2] Summary: lr: 0.000180 loss: 2.9520 (2.9782) grad: 0.1107 (0.1077) +eval (validation): [2] [ 0/85] eta: 0:04:30 time: 3.1853 data: 2.9285 max mem: 4841 +eval (validation): [2] [20/85] eta: 0:00:28 time: 0.3050 data: 0.0040 max mem: 4841 +eval (validation): [2] [40/85] eta: 0:00:18 time: 0.3602 data: 0.0045 max mem: 4841 +eval (validation): [2] [60/85] eta: 0:00:09 time: 0.3110 data: 0.0042 max mem: 4841 +eval (validation): [2] [80/85] eta: 0:00:01 time: 0.2961 data: 0.0042 max mem: 4841 +eval (validation): [2] [84/85] eta: 0:00:00 time: 0.2898 data: 0.0041 max mem: 4841 +eval (validation): [2] Total time: 0:00:30 (0.3533 s / it) +cv: [2] best hparam: (9.8, 1.0) (038) ('038_lr9.8e+00_wd1.0e+00') loss: 2.678 acc: 0.203 f1: 0.138 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__attn/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__attn/checkpoint-best.pth +train: [3] [ 0/400] eta: 0:22:08 lr: nan time: 3.3218 data: 3.1026 max mem: 4841 +train: [3] [ 20/400] eta: 0:02:55 lr: 0.000183 loss: 2.9357 (2.9245) grad: 0.1082 (0.1103) time: 0.3192 data: 0.0041 max mem: 4841 +train: [3] [ 40/400] eta: 0:02:22 lr: 0.000186 loss: 2.9253 (2.9196) grad: 0.1150 (0.1140) time: 0.3247 data: 0.0036 max mem: 4841 +train: [3] [ 60/400] eta: 0:02:07 lr: 0.000189 loss: 2.9393 (2.9275) grad: 0.1173 (0.1150) time: 0.3322 data: 0.0038 max mem: 4841 +train: [3] [ 80/400] eta: 0:01:55 lr: 0.000192 loss: 2.9408 (2.9316) grad: 0.1191 (0.1165) time: 0.3254 data: 0.0042 max mem: 4841 +train: [3] [100/400] eta: 0:01:46 lr: 0.000195 loss: 2.9408 (2.9415) grad: 0.1291 (0.1361) time: 0.3278 data: 0.0040 max mem: 4841 +train: [3] [120/400] eta: 0:01:38 lr: 0.000198 loss: 3.0272 (3.0186) grad: 0.3390 (0.2442) time: 0.3408 data: 0.0041 max mem: 4841 +WARNING: classifier 48 (50, 1.0) diverged (loss=94.82 > 63.56) at step 665. Freezing. +train: [3] [140/400] eta: 0:01:31 lr: 0.000201 loss: 3.2696 (3.0861) grad: 0.7556 (0.3032) time: 0.3392 data: 0.0042 max mem: 4841 +train: [3] [160/400] eta: 0:01:23 lr: 0.000204 loss: 2.9373 (3.0643) grad: 0.1091 (0.2790) time: 0.3325 data: 0.0045 max mem: 4841 +train: [3] [180/400] eta: 0:01:16 lr: 0.000207 loss: 2.9091 (3.0487) grad: 0.1054 (0.2597) time: 0.3344 data: 0.0042 max mem: 4841 +train: [3] [200/400] eta: 0:01:09 lr: 0.000210 loss: 2.9288 (3.0360) grad: 0.1092 (0.2450) time: 0.3353 data: 0.0043 max mem: 4841 +train: [3] [220/400] eta: 0:01:02 lr: 0.000213 loss: 2.9386 (3.0274) grad: 0.1174 (0.2336) time: 0.3363 data: 0.0042 max mem: 4841 +train: [3] [240/400] eta: 0:00:55 lr: 0.000216 loss: 2.9386 (3.0183) grad: 0.1160 (0.2235) time: 0.3372 data: 0.0042 max mem: 4841 +train: [3] [260/400] eta: 0:00:48 lr: 0.000219 loss: 2.9370 (3.0140) grad: 0.1131 (0.2154) time: 0.3453 data: 0.0043 max mem: 4841 +train: [3] [280/400] eta: 0:00:41 lr: 0.000222 loss: 2.9430 (3.0099) grad: 0.1108 (0.2079) time: 0.3539 data: 0.0045 max mem: 4841 +train: [3] [300/400] eta: 0:00:34 lr: 0.000225 loss: 2.9527 (3.0045) grad: 0.1108 (0.2018) time: 0.3453 data: 0.0042 max mem: 4841 +train: [3] [320/400] eta: 0:00:27 lr: 0.000228 loss: 2.9499 (3.0015) grad: 0.1196 (0.1969) time: 0.3188 data: 0.0040 max mem: 4841 +train: [3] [340/400] eta: 0:00:20 lr: 0.000231 loss: 2.9487 (2.9987) grad: 0.1243 (0.1929) time: 0.3552 data: 0.0043 max mem: 4841 +train: [3] [360/400] eta: 0:00:13 lr: 0.000234 loss: 2.9597 (2.9975) grad: 0.1469 (0.1969) time: 0.3248 data: 0.0042 max mem: 4841 +WARNING: classifier 47 (43, 1.0) diverged (loss=64.34 > 63.56) at step 786. Freezing. +train: [3] [380/400] eta: 0:00:06 lr: 0.000237 loss: 3.0442 (3.0133) grad: 0.2447 (0.2139) time: 0.3151 data: 0.0037 max mem: 4841 +train: [3] [399/400] eta: 0:00:00 lr: 0.000240 loss: 2.9892 (3.0093) grad: 0.1322 (0.2095) time: 0.3285 data: 0.0044 max mem: 4841 +train: [3] Total time: 0:02:16 (0.3414 s / it) +train: [3] Summary: lr: 0.000240 loss: 2.9892 (3.0093) grad: 0.1322 (0.2095) +eval (validation): [3] [ 0/85] eta: 0:04:36 time: 3.2480 data: 3.0436 max mem: 4841 +eval (validation): [3] [20/85] eta: 0:00:31 time: 0.3453 data: 0.0059 max mem: 4841 +eval (validation): [3] [40/85] eta: 0:00:17 time: 0.3075 data: 0.0044 max mem: 4841 +eval (validation): [3] [60/85] eta: 0:00:09 time: 0.3061 data: 0.0043 max mem: 4841 +eval (validation): [3] [80/85] eta: 0:00:01 time: 0.3042 data: 0.0041 max mem: 4841 +eval (validation): [3] [84/85] eta: 0:00:00 time: 0.3015 data: 0.0040 max mem: 4841 +eval (validation): [3] Total time: 0:00:30 (0.3530 s / it) +cv: [3] best hparam: (4.3, 1.0) (033) ('033_lr4.3e+00_wd1.0e+00') loss: 2.672 acc: 0.202 f1: 0.123 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__attn/checkpoint-last.pth +train: [4] [ 0/400] eta: 0:21:53 lr: nan time: 3.2831 data: 3.0570 max mem: 4841 +train: [4] [ 20/400] eta: 0:03:09 lr: 0.000243 loss: 2.9122 (2.9255) grad: 0.1224 (0.1215) time: 0.3592 data: 0.0170 max mem: 4841 +train: [4] [ 40/400] eta: 0:02:30 lr: 0.000246 loss: 2.8963 (2.9017) grad: 0.1224 (0.1226) time: 0.3326 data: 0.0036 max mem: 4841 +train: [4] [ 60/400] eta: 0:02:13 lr: 0.000249 loss: 2.8794 (2.8998) grad: 0.1213 (0.1223) time: 0.3447 data: 0.0043 max mem: 4841 +train: [4] [ 80/400] eta: 0:02:01 lr: 0.000252 loss: 2.9063 (2.9063) grad: 0.1235 (0.1228) time: 0.3407 data: 0.0041 max mem: 4841 +train: [4] [100/400] eta: 0:01:50 lr: 0.000255 loss: 2.9333 (2.9129) grad: 0.1255 (0.1239) time: 0.3223 data: 0.0044 max mem: 4841 +train: [4] [120/400] eta: 0:01:42 lr: 0.000258 loss: 2.9380 (2.9152) grad: 0.1340 (0.1333) time: 0.3495 data: 0.0043 max mem: 4841 +train: [4] [140/400] eta: 0:01:34 lr: 0.000261 loss: 3.0112 (2.9437) grad: 0.2620 (0.1733) time: 0.3399 data: 0.0044 max mem: 4841 +WARNING: classifier 46 (36, 1.0) diverged (loss=90.75 > 63.56) at step 878. Freezing. +train: [4] [160/400] eta: 0:01:26 lr: 0.000264 loss: 3.1613 (3.0361) grad: 0.3723 (0.2687) time: 0.3406 data: 0.0041 max mem: 4841 +train: [4] [180/400] eta: 0:01:18 lr: 0.000267 loss: 2.9261 (3.0209) grad: 0.1286 (0.2522) time: 0.3399 data: 0.0043 max mem: 4841 +train: [4] [200/400] eta: 0:01:10 lr: 0.000270 loss: 2.9079 (3.0116) grad: 0.1160 (0.2394) time: 0.3293 data: 0.0042 max mem: 4841 +train: [4] [220/400] eta: 0:01:03 lr: 0.000273 loss: 2.9232 (3.0026) grad: 0.1194 (0.2283) time: 0.3282 data: 0.0040 max mem: 4841 +train: [4] [240/400] eta: 0:00:56 lr: 0.000276 loss: 2.9009 (2.9948) grad: 0.1111 (0.2186) time: 0.3511 data: 0.0042 max mem: 4841 +train: [4] [260/400] eta: 0:00:49 lr: 0.000279 loss: 2.8925 (2.9838) grad: 0.1091 (0.2102) time: 0.3397 data: 0.0043 max mem: 4841 +train: [4] [280/400] eta: 0:00:42 lr: 0.000282 loss: 2.8748 (2.9777) grad: 0.1125 (0.2038) time: 0.3363 data: 0.0041 max mem: 4841 +train: [4] [300/400] eta: 0:00:34 lr: 0.000285 loss: 2.8861 (2.9729) grad: 0.1159 (0.1983) time: 0.3320 data: 0.0040 max mem: 4841 +train: [4] [320/400] eta: 0:00:27 lr: 0.000288 loss: 2.9085 (2.9697) grad: 0.1306 (0.1950) time: 0.3316 data: 0.0041 max mem: 4841 +train: [4] [340/400] eta: 0:00:20 lr: 0.000291 loss: 2.9257 (2.9743) grad: 0.1668 (0.1998) time: 0.3269 data: 0.0041 max mem: 4841 +WARNING: classifier 45 (31, 1.0) diverged (loss=71.62 > 63.56) at step 980. Freezing. +train: [4] [360/400] eta: 0:00:13 lr: 0.000294 loss: 3.1907 (3.0113) grad: 0.5640 (0.2442) time: 0.3332 data: 0.0044 max mem: 4841 +train: [4] [380/400] eta: 0:00:06 lr: 0.000297 loss: 2.9987 (3.0057) grad: 0.1205 (0.2372) time: 0.3397 data: 0.0042 max mem: 4841 +train: [4] [399/400] eta: 0:00:00 lr: 0.000300 loss: 2.9111 (3.0015) grad: 0.1129 (0.2313) time: 0.3627 data: 0.0042 max mem: 4841 +train: [4] Total time: 0:02:18 (0.3466 s / it) +train: [4] Summary: lr: 0.000300 loss: 2.9111 (3.0015) grad: 0.1129 (0.2313) +eval (validation): [4] [ 0/85] eta: 0:04:33 time: 3.2232 data: 3.0221 max mem: 4841 +eval (validation): [4] [20/85] eta: 0:00:29 time: 0.3094 data: 0.0220 max mem: 4841 +eval (validation): [4] [40/85] eta: 0:00:17 time: 0.3221 data: 0.0038 max mem: 4841 +eval (validation): [4] [60/85] eta: 0:00:09 time: 0.3350 data: 0.0040 max mem: 4841 +eval (validation): [4] [80/85] eta: 0:00:01 time: 0.3179 data: 0.0041 max mem: 4841 +eval (validation): [4] [84/85] eta: 0:00:00 time: 0.3052 data: 0.0040 max mem: 4841 +eval (validation): [4] Total time: 0:00:30 (0.3572 s / it) +cv: [4] best hparam: (2.3, 1.0) (029) ('029_lr2.3e+00_wd1.0e+00') loss: 2.666 acc: 0.203 f1: 0.127 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__attn/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__attn/checkpoint-best.pth +train: [5] [ 0/400] eta: 0:21:46 lr: nan time: 3.2663 data: 3.0337 max mem: 4841 +train: [5] [ 20/400] eta: 0:03:07 lr: 0.000300 loss: 2.8610 (2.8754) grad: 0.1137 (0.1180) time: 0.3549 data: 0.0109 max mem: 4841 +train: [5] [ 40/400] eta: 0:02:29 lr: 0.000300 loss: 2.8751 (2.8836) grad: 0.1159 (0.1179) time: 0.3358 data: 0.0039 max mem: 4841 +train: [5] [ 60/400] eta: 0:02:12 lr: 0.000300 loss: 2.8751 (2.8792) grad: 0.1161 (0.1172) time: 0.3365 data: 0.0042 max mem: 4841 +train: [5] [ 80/400] eta: 0:02:00 lr: 0.000300 loss: 2.8627 (2.8732) grad: 0.1122 (0.1161) time: 0.3406 data: 0.0040 max mem: 4841 +train: [5] [100/400] eta: 0:01:51 lr: 0.000300 loss: 2.8789 (2.8834) grad: 0.1136 (0.1169) time: 0.3413 data: 0.0044 max mem: 4841 +train: [5] [120/400] eta: 0:01:43 lr: 0.000300 loss: 2.8974 (2.8847) grad: 0.1196 (0.1178) time: 0.3570 data: 0.0042 max mem: 4841 +train: [5] [140/400] eta: 0:01:35 lr: 0.000300 loss: 2.8974 (2.8869) grad: 0.1196 (0.1185) time: 0.3509 data: 0.0046 max mem: 4841 +train: [5] [160/400] eta: 0:01:27 lr: 0.000299 loss: 2.9052 (2.8886) grad: 0.1221 (0.1192) time: 0.3445 data: 0.0040 max mem: 4841 +train: [5] [180/400] eta: 0:01:19 lr: 0.000299 loss: 2.8749 (2.8882) grad: 0.1212 (0.1192) time: 0.3451 data: 0.0040 max mem: 4841 +train: [5] [200/400] eta: 0:01:12 lr: 0.000299 loss: 2.8618 (2.8855) grad: 0.1118 (0.1181) time: 0.3625 data: 0.0042 max mem: 4841 +train: [5] [220/400] eta: 0:01:04 lr: 0.000299 loss: 2.8618 (2.8852) grad: 0.1063 (0.1173) time: 0.3390 data: 0.0039 max mem: 4841 +train: [5] [240/400] eta: 0:00:57 lr: 0.000299 loss: 2.9009 (2.8851) grad: 0.1041 (0.1162) time: 0.3515 data: 0.0041 max mem: 4841 +train: [5] [260/400] eta: 0:00:50 lr: 0.000299 loss: 2.8870 (2.8852) grad: 0.0995 (0.1156) time: 0.3420 data: 0.0041 max mem: 4841 +train: [5] [280/400] eta: 0:00:42 lr: 0.000298 loss: 2.8856 (2.8865) grad: 0.1068 (0.1150) time: 0.3414 data: 0.0042 max mem: 4841 +train: [5] [300/400] eta: 0:00:35 lr: 0.000298 loss: 2.8696 (2.8857) grad: 0.1032 (0.1142) time: 0.3457 data: 0.0043 max mem: 4841 +train: [5] [320/400] eta: 0:00:28 lr: 0.000298 loss: 2.8588 (2.8839) grad: 0.1098 (0.1145) time: 0.3568 data: 0.0043 max mem: 4841 +train: [5] [340/400] eta: 0:00:21 lr: 0.000298 loss: 2.8783 (2.8848) grad: 0.1130 (0.1144) time: 0.3378 data: 0.0042 max mem: 4841 +train: [5] [360/400] eta: 0:00:14 lr: 0.000297 loss: 2.9092 (2.8856) grad: 0.1057 (0.1137) time: 0.3418 data: 0.0044 max mem: 4841 +train: [5] [380/400] eta: 0:00:07 lr: 0.000297 loss: 2.8930 (2.8848) grad: 0.1044 (0.1136) time: 0.3470 data: 0.0046 max mem: 4841 +train: [5] [399/400] eta: 0:00:00 lr: 0.000297 loss: 2.8682 (2.8833) grad: 0.1179 (0.1139) time: 0.3425 data: 0.0042 max mem: 4841 +train: [5] Total time: 0:02:21 (0.3534 s / it) +train: [5] Summary: lr: 0.000297 loss: 2.8682 (2.8833) grad: 0.1179 (0.1139) +eval (validation): [5] [ 0/85] eta: 0:04:32 time: 3.2102 data: 2.9763 max mem: 4841 +eval (validation): [5] [20/85] eta: 0:00:31 time: 0.3454 data: 0.0050 max mem: 4841 +eval (validation): [5] [40/85] eta: 0:00:19 time: 0.3695 data: 0.0047 max mem: 4841 +eval (validation): [5] [60/85] eta: 0:00:09 time: 0.3133 data: 0.0047 max mem: 4841 +eval (validation): [5] [80/85] eta: 0:00:01 time: 0.3164 data: 0.0042 max mem: 4841 +eval (validation): [5] [84/85] eta: 0:00:00 time: 0.3064 data: 0.0040 max mem: 4841 +eval (validation): [5] Total time: 0:00:31 (0.3717 s / it) +cv: [5] best hparam: (3.7, 1.0) (032) ('032_lr3.7e+00_wd1.0e+00') loss: 2.581 acc: 0.228 f1: 0.156 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__attn/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__attn/checkpoint-best.pth +train: [6] [ 0/400] eta: 0:22:18 lr: nan time: 3.3475 data: 3.0678 max mem: 4841 +train: [6] [ 20/400] eta: 0:03:10 lr: 0.000296 loss: 2.8667 (2.8465) grad: 0.1091 (0.1112) time: 0.3599 data: 0.0047 max mem: 4841 +train: [6] [ 40/400] eta: 0:02:32 lr: 0.000296 loss: 2.8306 (2.8264) grad: 0.1091 (0.1107) time: 0.3392 data: 0.0041 max mem: 4841 +train: [6] [ 60/400] eta: 0:02:13 lr: 0.000296 loss: 2.8207 (2.8269) grad: 0.1056 (0.1091) time: 0.3270 data: 0.0040 max mem: 4841 +train: [6] [ 80/400] eta: 0:02:02 lr: 0.000295 loss: 2.8246 (2.8306) grad: 0.1056 (0.1079) time: 0.3562 data: 0.0043 max mem: 4841 +train: [6] [100/400] eta: 0:01:52 lr: 0.000295 loss: 2.8372 (2.8344) grad: 0.1050 (0.1077) time: 0.3394 data: 0.0040 max mem: 4841 +train: [6] [120/400] eta: 0:01:43 lr: 0.000295 loss: 2.8181 (2.8302) grad: 0.1034 (0.1075) time: 0.3500 data: 0.0042 max mem: 4841 +train: [6] [140/400] eta: 0:01:35 lr: 0.000294 loss: 2.8159 (2.8303) grad: 0.1035 (0.1073) time: 0.3428 data: 0.0042 max mem: 4841 +train: [6] [160/400] eta: 0:01:27 lr: 0.000294 loss: 2.8221 (2.8343) grad: 0.1056 (0.1078) time: 0.3398 data: 0.0042 max mem: 4841 +train: [6] [180/400] eta: 0:01:19 lr: 0.000293 loss: 2.8549 (2.8357) grad: 0.1094 (0.1080) time: 0.3393 data: 0.0043 max mem: 4841 +train: [6] [200/400] eta: 0:01:11 lr: 0.000293 loss: 2.8350 (2.8342) grad: 0.1091 (0.1080) time: 0.3520 data: 0.0044 max mem: 4841 +train: [6] [220/400] eta: 0:01:04 lr: 0.000292 loss: 2.8350 (2.8298) grad: 0.1109 (0.1083) time: 0.3359 data: 0.0040 max mem: 4841 +train: [6] [240/400] eta: 0:00:57 lr: 0.000292 loss: 2.8561 (2.8327) grad: 0.1133 (0.1089) time: 0.3678 data: 0.0042 max mem: 4841 +train: [6] [260/400] eta: 0:00:50 lr: 0.000291 loss: 2.8303 (2.8318) grad: 0.1161 (0.1095) time: 0.3613 data: 0.0039 max mem: 4841 +train: [6] [280/400] eta: 0:00:43 lr: 0.000291 loss: 2.8205 (2.8325) grad: 0.1178 (0.1102) time: 0.3597 data: 0.0043 max mem: 4841 +train: [6] [300/400] eta: 0:00:35 lr: 0.000290 loss: 2.8410 (2.8351) grad: 0.1159 (0.1105) time: 0.3393 data: 0.0039 max mem: 4841 +train: [6] [320/400] eta: 0:00:28 lr: 0.000290 loss: 2.8494 (2.8350) grad: 0.1142 (0.1108) time: 0.3608 data: 0.0043 max mem: 4841 +train: [6] [340/400] eta: 0:00:21 lr: 0.000289 loss: 2.8078 (2.8331) grad: 0.1132 (0.1108) time: 0.3464 data: 0.0039 max mem: 4841 +train: [6] [360/400] eta: 0:00:14 lr: 0.000288 loss: 2.8058 (2.8325) grad: 0.1157 (0.1112) time: 0.3523 data: 0.0043 max mem: 4841 +train: [6] [380/400] eta: 0:00:07 lr: 0.000288 loss: 2.8134 (2.8327) grad: 0.1175 (0.1118) time: 0.3383 data: 0.0042 max mem: 4841 +train: [6] [399/400] eta: 0:00:00 lr: 0.000287 loss: 2.8169 (2.8323) grad: 0.1155 (0.1118) time: 0.3279 data: 0.0038 max mem: 4841 +train: [6] Total time: 0:02:21 (0.3546 s / it) +train: [6] Summary: lr: 0.000287 loss: 2.8169 (2.8323) grad: 0.1155 (0.1118) +eval (validation): [6] [ 0/85] eta: 0:04:37 time: 3.2667 data: 3.0206 max mem: 4841 +eval (validation): [6] [20/85] eta: 0:00:30 time: 0.3297 data: 0.0046 max mem: 4841 +eval (validation): [6] [40/85] eta: 0:00:17 time: 0.2944 data: 0.0037 max mem: 4841 +eval (validation): [6] [60/85] eta: 0:00:08 time: 0.2920 data: 0.0042 max mem: 4841 +eval (validation): [6] [80/85] eta: 0:00:01 time: 0.2896 data: 0.0041 max mem: 4841 +eval (validation): [6] [84/85] eta: 0:00:00 time: 0.2857 data: 0.0040 max mem: 4841 +eval (validation): [6] Total time: 0:00:28 (0.3386 s / it) +cv: [6] best hparam: (4.3, 1.0) (033) ('033_lr4.3e+00_wd1.0e+00') loss: 2.582 acc: 0.222 f1: 0.161 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__attn/checkpoint-last.pth +train: [7] [ 0/400] eta: 0:20:45 lr: nan time: 3.1133 data: 2.8996 max mem: 4841 +train: [7] [ 20/400] eta: 0:02:58 lr: 0.000286 loss: 2.7630 (2.7679) grad: 0.1042 (0.1075) time: 0.3381 data: 0.0047 max mem: 4841 +train: [7] [ 40/400] eta: 0:02:24 lr: 0.000286 loss: 2.7829 (2.8124) grad: 0.1089 (0.1115) time: 0.3305 data: 0.0036 max mem: 4841 +train: [7] [ 60/400] eta: 0:02:08 lr: 0.000285 loss: 2.8421 (2.8148) grad: 0.1150 (0.1130) time: 0.3313 data: 0.0040 max mem: 4841 +train: [7] [ 80/400] eta: 0:01:59 lr: 0.000284 loss: 2.8016 (2.8067) grad: 0.1136 (0.1129) time: 0.3564 data: 0.0045 max mem: 4841 +train: [7] [100/400] eta: 0:01:50 lr: 0.000284 loss: 2.7958 (2.8087) grad: 0.1163 (0.1148) time: 0.3484 data: 0.0043 max mem: 4841 +train: [7] [120/400] eta: 0:01:41 lr: 0.000283 loss: 2.7941 (2.8114) grad: 0.1197 (0.1156) time: 0.3436 data: 0.0042 max mem: 4841 +train: [7] [140/400] eta: 0:01:33 lr: 0.000282 loss: 2.8185 (2.8157) grad: 0.1188 (0.1161) time: 0.3401 data: 0.0042 max mem: 4841 +train: [7] [160/400] eta: 0:01:25 lr: 0.000282 loss: 2.8467 (2.8179) grad: 0.1172 (0.1162) time: 0.3390 data: 0.0040 max mem: 4841 +train: [7] [180/400] eta: 0:01:18 lr: 0.000281 loss: 2.8170 (2.8158) grad: 0.1139 (0.1161) time: 0.3418 data: 0.0043 max mem: 4841 +train: [7] [200/400] eta: 0:01:10 lr: 0.000280 loss: 2.7910 (2.8136) grad: 0.1189 (0.1171) time: 0.3255 data: 0.0041 max mem: 4841 +train: [7] [220/400] eta: 0:01:03 lr: 0.000279 loss: 2.8065 (2.8162) grad: 0.1216 (0.1171) time: 0.3603 data: 0.0043 max mem: 4841 +train: [7] [240/400] eta: 0:00:56 lr: 0.000278 loss: 2.8160 (2.8159) grad: 0.1156 (0.1166) time: 0.3442 data: 0.0043 max mem: 4841 +train: [7] [260/400] eta: 0:00:49 lr: 0.000278 loss: 2.8025 (2.8155) grad: 0.1165 (0.1168) time: 0.3418 data: 0.0043 max mem: 4841 +train: [7] [280/400] eta: 0:00:42 lr: 0.000277 loss: 2.8008 (2.8148) grad: 0.1196 (0.1171) time: 0.3420 data: 0.0041 max mem: 4841 +train: [7] [300/400] eta: 0:00:35 lr: 0.000276 loss: 2.8375 (2.8157) grad: 0.1189 (0.1172) time: 0.3357 data: 0.0042 max mem: 4841 +train: [7] [320/400] eta: 0:00:27 lr: 0.000275 loss: 2.8163 (2.8139) grad: 0.1123 (0.1168) time: 0.3404 data: 0.0042 max mem: 4841 +train: [7] [340/400] eta: 0:00:20 lr: 0.000274 loss: 2.7915 (2.8116) grad: 0.1126 (0.1167) time: 0.3366 data: 0.0042 max mem: 4841 +train: [7] [360/400] eta: 0:00:13 lr: 0.000273 loss: 2.7915 (2.8116) grad: 0.1160 (0.1166) time: 0.3377 data: 0.0042 max mem: 4841 +train: [7] [380/400] eta: 0:00:06 lr: 0.000272 loss: 2.7923 (2.8112) grad: 0.1106 (0.1164) time: 0.3717 data: 0.0042 max mem: 4841 +train: [7] [399/400] eta: 0:00:00 lr: 0.000271 loss: 2.8033 (2.8123) grad: 0.1140 (0.1164) time: 0.3741 data: 0.0042 max mem: 4841 +train: [7] Total time: 0:02:20 (0.3511 s / it) +train: [7] Summary: lr: 0.000271 loss: 2.8033 (2.8123) grad: 0.1140 (0.1164) +eval (validation): [7] [ 0/85] eta: 0:04:43 time: 3.3302 data: 3.1228 max mem: 4841 +eval (validation): [7] [20/85] eta: 0:00:31 time: 0.3347 data: 0.0245 max mem: 4841 +eval (validation): [7] [40/85] eta: 0:00:18 time: 0.3325 data: 0.0038 max mem: 4841 +eval (validation): [7] [60/85] eta: 0:00:09 time: 0.3169 data: 0.0043 max mem: 4841 +eval (validation): [7] [80/85] eta: 0:00:01 time: 0.3196 data: 0.0041 max mem: 4841 +eval (validation): [7] [84/85] eta: 0:00:00 time: 0.2993 data: 0.0040 max mem: 4841 +eval (validation): [7] Total time: 0:00:30 (0.3637 s / it) +cv: [7] best hparam: (2.7, 1.0) (030) ('030_lr2.7e+00_wd1.0e+00') loss: 2.560 acc: 0.239 f1: 0.166 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__attn/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__attn/checkpoint-best.pth +train: [8] [ 0/400] eta: 0:22:35 lr: nan time: 3.3892 data: 3.1161 max mem: 4841 +train: [8] [ 20/400] eta: 0:03:11 lr: 0.000270 loss: 2.7670 (2.7671) grad: 0.1117 (0.1148) time: 0.3605 data: 0.0035 max mem: 4841 +train: [8] [ 40/400] eta: 0:02:30 lr: 0.000270 loss: 2.7539 (2.7588) grad: 0.1153 (0.1158) time: 0.3293 data: 0.0042 max mem: 4841 +train: [8] [ 60/400] eta: 0:02:14 lr: 0.000269 loss: 2.7509 (2.7620) grad: 0.1157 (0.1159) time: 0.3472 data: 0.0042 max mem: 4841 +train: [8] [ 80/400] eta: 0:02:02 lr: 0.000268 loss: 2.8088 (2.7742) grad: 0.1140 (0.1157) time: 0.3394 data: 0.0045 max mem: 4841 +train: [8] [100/400] eta: 0:01:52 lr: 0.000267 loss: 2.8032 (2.7745) grad: 0.1140 (0.1156) time: 0.3462 data: 0.0038 max mem: 4841 +train: [8] [120/400] eta: 0:01:43 lr: 0.000266 loss: 2.7567 (2.7739) grad: 0.1170 (0.1170) time: 0.3361 data: 0.0045 max mem: 4841 +train: [8] [140/400] eta: 0:01:34 lr: 0.000265 loss: 2.7687 (2.7717) grad: 0.1180 (0.1171) time: 0.3444 data: 0.0040 max mem: 4841 +train: [8] [160/400] eta: 0:01:26 lr: 0.000264 loss: 2.7678 (2.7716) grad: 0.1160 (0.1168) time: 0.3339 data: 0.0044 max mem: 4841 +train: [8] [180/400] eta: 0:01:18 lr: 0.000263 loss: 2.7801 (2.7732) grad: 0.1156 (0.1172) time: 0.3409 data: 0.0043 max mem: 4841 +train: [8] [200/400] eta: 0:01:11 lr: 0.000262 loss: 2.7887 (2.7783) grad: 0.1183 (0.1174) time: 0.3379 data: 0.0043 max mem: 4841 +train: [8] [220/400] eta: 0:01:03 lr: 0.000260 loss: 2.7693 (2.7766) grad: 0.1127 (0.1173) time: 0.3407 data: 0.0040 max mem: 4841 +train: [8] [240/400] eta: 0:00:56 lr: 0.000259 loss: 2.7666 (2.7775) grad: 0.1124 (0.1171) time: 0.3425 data: 0.0045 max mem: 4841 +train: [8] [260/400] eta: 0:00:49 lr: 0.000258 loss: 2.7537 (2.7764) grad: 0.1185 (0.1172) time: 0.3402 data: 0.0041 max mem: 4841 +train: [8] [280/400] eta: 0:00:42 lr: 0.000257 loss: 2.7537 (2.7778) grad: 0.1179 (0.1172) time: 0.3445 data: 0.0043 max mem: 4841 +train: [8] [300/400] eta: 0:00:35 lr: 0.000256 loss: 2.8078 (2.7797) grad: 0.1183 (0.1174) time: 0.3440 data: 0.0039 max mem: 4841 +train: [8] [320/400] eta: 0:00:28 lr: 0.000255 loss: 2.7876 (2.7796) grad: 0.1183 (0.1175) time: 0.3374 data: 0.0043 max mem: 4841 +train: [8] [340/400] eta: 0:00:21 lr: 0.000254 loss: 2.7981 (2.7815) grad: 0.1132 (0.1175) time: 0.3403 data: 0.0039 max mem: 4841 +train: [8] [360/400] eta: 0:00:13 lr: 0.000253 loss: 2.8070 (2.7829) grad: 0.1124 (0.1175) time: 0.3387 data: 0.0040 max mem: 4841 +train: [8] [380/400] eta: 0:00:07 lr: 0.000252 loss: 2.8090 (2.7842) grad: 0.1110 (0.1172) time: 0.3779 data: 0.0044 max mem: 4841 +train: [8] [399/400] eta: 0:00:00 lr: 0.000250 loss: 2.8305 (2.7859) grad: 0.1136 (0.1174) time: 0.3492 data: 0.0042 max mem: 4841 +train: [8] Total time: 0:02:20 (0.3512 s / it) +train: [8] Summary: lr: 0.000250 loss: 2.8305 (2.7859) grad: 0.1136 (0.1174) +eval (validation): [8] [ 0/85] eta: 0:04:36 time: 3.2546 data: 3.0452 max mem: 4841 +eval (validation): [8] [20/85] eta: 0:00:29 time: 0.3217 data: 0.0123 max mem: 4841 +eval (validation): [8] [40/85] eta: 0:00:17 time: 0.3354 data: 0.0043 max mem: 4841 +eval (validation): [8] [60/85] eta: 0:00:09 time: 0.3558 data: 0.0043 max mem: 4841 +eval (validation): [8] [80/85] eta: 0:00:01 time: 0.3232 data: 0.0041 max mem: 4841 +eval (validation): [8] [84/85] eta: 0:00:00 time: 0.3122 data: 0.0041 max mem: 4841 +eval (validation): [8] Total time: 0:00:31 (0.3700 s / it) +cv: [8] best hparam: (8.3, 1.0) (037) ('037_lr8.3e+00_wd1.0e+00') loss: 2.638 acc: 0.227 f1: 0.161 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__attn/checkpoint-last.pth +train: [9] [ 0/400] eta: 0:22:06 lr: nan time: 3.3161 data: 3.0535 max mem: 4841 +train: [9] [ 20/400] eta: 0:03:06 lr: 0.000249 loss: 2.7382 (2.7683) grad: 0.1201 (0.1193) time: 0.3495 data: 0.0050 max mem: 4841 +train: [9] [ 40/400] eta: 0:02:30 lr: 0.000248 loss: 2.7382 (2.7496) grad: 0.1189 (0.1193) time: 0.3400 data: 0.0038 max mem: 4841 +train: [9] [ 60/400] eta: 0:02:14 lr: 0.000247 loss: 2.7242 (2.7336) grad: 0.1149 (0.1180) time: 0.3536 data: 0.0034 max mem: 4841 +train: [9] [ 80/400] eta: 0:02:02 lr: 0.000246 loss: 2.6973 (2.7320) grad: 0.1136 (0.1190) time: 0.3454 data: 0.0043 max mem: 4841 +train: [9] [100/400] eta: 0:01:53 lr: 0.000244 loss: 2.7204 (2.7342) grad: 0.1140 (0.1180) time: 0.3519 data: 0.0044 max mem: 4841 +train: [9] [120/400] eta: 0:01:43 lr: 0.000243 loss: 2.7495 (2.7411) grad: 0.1144 (0.1175) time: 0.3303 data: 0.0044 max mem: 4841 +train: [9] [140/400] eta: 0:01:35 lr: 0.000242 loss: 2.7823 (2.7490) grad: 0.1147 (0.1171) time: 0.3395 data: 0.0043 max mem: 4841 +train: [9] [160/400] eta: 0:01:27 lr: 0.000241 loss: 2.7920 (2.7578) grad: 0.1161 (0.1170) time: 0.3512 data: 0.0045 max mem: 4841 +train: [9] [180/400] eta: 0:01:19 lr: 0.000240 loss: 2.7615 (2.7594) grad: 0.1161 (0.1167) time: 0.3390 data: 0.0042 max mem: 4841 +train: [9] [200/400] eta: 0:01:12 lr: 0.000238 loss: 2.7441 (2.7586) grad: 0.1111 (0.1165) time: 0.3529 data: 0.0044 max mem: 4841 +train: [9] [220/400] eta: 0:01:04 lr: 0.000237 loss: 2.7661 (2.7635) grad: 0.1172 (0.1168) time: 0.3416 data: 0.0043 max mem: 4841 +train: [9] [240/400] eta: 0:00:57 lr: 0.000236 loss: 2.7918 (2.7648) grad: 0.1206 (0.1173) time: 0.3421 data: 0.0044 max mem: 4841 +train: [9] [260/400] eta: 0:00:49 lr: 0.000234 loss: 2.7355 (2.7608) grad: 0.1168 (0.1168) time: 0.3253 data: 0.0040 max mem: 4841 +train: [9] [280/400] eta: 0:00:42 lr: 0.000233 loss: 2.7250 (2.7619) grad: 0.1118 (0.1167) time: 0.3455 data: 0.0044 max mem: 4841 +train: [9] [300/400] eta: 0:00:35 lr: 0.000232 loss: 2.7619 (2.7606) grad: 0.1147 (0.1165) time: 0.3402 data: 0.0043 max mem: 4841 +train: [9] [320/400] eta: 0:00:28 lr: 0.000230 loss: 2.7619 (2.7609) grad: 0.1147 (0.1164) time: 0.3446 data: 0.0044 max mem: 4841 +train: [9] [340/400] eta: 0:00:21 lr: 0.000229 loss: 2.7488 (2.7604) grad: 0.1124 (0.1162) time: 0.3358 data: 0.0044 max mem: 4841 +train: [9] [360/400] eta: 0:00:14 lr: 0.000228 loss: 2.7488 (2.7596) grad: 0.1107 (0.1159) time: 0.3290 data: 0.0044 max mem: 4841 +train: [9] [380/400] eta: 0:00:06 lr: 0.000226 loss: 2.7144 (2.7561) grad: 0.1150 (0.1161) time: 0.3326 data: 0.0044 max mem: 4841 +train: [9] [399/400] eta: 0:00:00 lr: 0.000225 loss: 2.7227 (2.7572) grad: 0.1218 (0.1164) time: 0.3389 data: 0.0044 max mem: 4841 +train: [9] Total time: 0:02:19 (0.3492 s / it) +train: [9] Summary: lr: 0.000225 loss: 2.7227 (2.7572) grad: 0.1218 (0.1164) +eval (validation): [9] [ 0/85] eta: 0:04:37 time: 3.2638 data: 3.0672 max mem: 4841 +eval (validation): [9] [20/85] eta: 0:00:30 time: 0.3250 data: 0.0046 max mem: 4841 +eval (validation): [9] [40/85] eta: 0:00:17 time: 0.3054 data: 0.0036 max mem: 4841 +eval (validation): [9] [60/85] eta: 0:00:09 time: 0.3584 data: 0.0045 max mem: 4841 +eval (validation): [9] [80/85] eta: 0:00:01 time: 0.3074 data: 0.0038 max mem: 4841 +eval (validation): [9] [84/85] eta: 0:00:00 time: 0.3044 data: 0.0041 max mem: 4841 +eval (validation): [9] Total time: 0:00:30 (0.3610 s / it) +cv: [9] best hparam: (3.1, 1.0) (031) ('031_lr3.1e+00_wd1.0e+00') loss: 2.549 acc: 0.239 f1: 0.177 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__attn/checkpoint-last.pth +train: [10] [ 0/400] eta: 0:21:28 lr: nan time: 3.2210 data: 2.9645 max mem: 4841 +train: [10] [ 20/400] eta: 0:03:05 lr: 0.000224 loss: 2.7184 (2.7028) grad: 0.1097 (0.1084) time: 0.3508 data: 0.0046 max mem: 4841 +train: [10] [ 40/400] eta: 0:02:30 lr: 0.000222 loss: 2.7184 (2.7127) grad: 0.1062 (0.1083) time: 0.3459 data: 0.0033 max mem: 4841 +train: [10] [ 60/400] eta: 0:02:13 lr: 0.000221 loss: 2.7233 (2.7245) grad: 0.1061 (0.1091) time: 0.3394 data: 0.0041 max mem: 4841 +train: [10] [ 80/400] eta: 0:02:01 lr: 0.000220 loss: 2.7378 (2.7363) grad: 0.1056 (0.1091) time: 0.3365 data: 0.0039 max mem: 4841 +train: [10] [100/400] eta: 0:01:51 lr: 0.000218 loss: 2.7378 (2.7325) grad: 0.1056 (0.1099) time: 0.3360 data: 0.0041 max mem: 4841 +train: [10] [120/400] eta: 0:01:43 lr: 0.000217 loss: 2.6938 (2.7274) grad: 0.1164 (0.1113) time: 0.3588 data: 0.0044 max mem: 4841 +train: [10] [140/400] eta: 0:01:35 lr: 0.000215 loss: 2.6927 (2.7254) grad: 0.1196 (0.1122) time: 0.3561 data: 0.0043 max mem: 4841 +train: [10] [160/400] eta: 0:01:27 lr: 0.000214 loss: 2.7004 (2.7222) grad: 0.1186 (0.1124) time: 0.3498 data: 0.0043 max mem: 4841 +train: [10] [180/400] eta: 0:01:19 lr: 0.000213 loss: 2.7310 (2.7262) grad: 0.1207 (0.1142) time: 0.3304 data: 0.0041 max mem: 4841 +train: [10] [200/400] eta: 0:01:11 lr: 0.000211 loss: 2.7688 (2.7292) grad: 0.1220 (0.1148) time: 0.3472 data: 0.0037 max mem: 4841 +train: [10] [220/400] eta: 0:01:04 lr: 0.000210 loss: 2.7304 (2.7277) grad: 0.1173 (0.1149) time: 0.3583 data: 0.0041 max mem: 4841 +train: [10] [240/400] eta: 0:00:57 lr: 0.000208 loss: 2.7467 (2.7310) grad: 0.1149 (0.1148) time: 0.3651 data: 0.0044 max mem: 4841 +train: [10] [260/400] eta: 0:00:50 lr: 0.000207 loss: 2.7471 (2.7338) grad: 0.1169 (0.1150) time: 0.3569 data: 0.0044 max mem: 4841 +train: [10] [280/400] eta: 0:00:43 lr: 0.000205 loss: 2.7341 (2.7334) grad: 0.1169 (0.1148) time: 0.3538 data: 0.0043 max mem: 4841 +train: [10] [300/400] eta: 0:00:35 lr: 0.000204 loss: 2.7354 (2.7353) grad: 0.1133 (0.1148) time: 0.3488 data: 0.0045 max mem: 4841 +train: [10] [320/400] eta: 0:00:28 lr: 0.000202 loss: 2.7354 (2.7336) grad: 0.1147 (0.1149) time: 0.3761 data: 0.0045 max mem: 4841 +train: [10] [340/400] eta: 0:00:21 lr: 0.000201 loss: 2.7064 (2.7327) grad: 0.1132 (0.1147) time: 0.3475 data: 0.0044 max mem: 4841 +train: [10] [360/400] eta: 0:00:14 lr: 0.000199 loss: 2.7136 (2.7311) grad: 0.1123 (0.1147) time: 0.3434 data: 0.0045 max mem: 4841 +train: [10] [380/400] eta: 0:00:07 lr: 0.000198 loss: 2.7070 (2.7298) grad: 0.1133 (0.1148) time: 0.3447 data: 0.0046 max mem: 4841 +train: [10] [399/400] eta: 0:00:00 lr: 0.000196 loss: 2.6946 (2.7291) grad: 0.1144 (0.1150) time: 0.3378 data: 0.0044 max mem: 4841 +train: [10] Total time: 0:02:22 (0.3566 s / it) +train: [10] Summary: lr: 0.000196 loss: 2.6946 (2.7291) grad: 0.1144 (0.1150) +eval (validation): [10] [ 0/85] eta: 0:04:53 time: 3.4512 data: 3.1858 max mem: 4841 +eval (validation): [10] [20/85] eta: 0:00:32 time: 0.3535 data: 0.0279 max mem: 4841 +eval (validation): [10] [40/85] eta: 0:00:18 time: 0.3335 data: 0.0241 max mem: 4841 +eval (validation): [10] [60/85] eta: 0:00:09 time: 0.3154 data: 0.0024 max mem: 4841 +eval (validation): [10] [80/85] eta: 0:00:01 time: 0.3001 data: 0.0037 max mem: 4841 +eval (validation): [10] [84/85] eta: 0:00:00 time: 0.2898 data: 0.0030 max mem: 4841 +eval (validation): [10] Total time: 0:00:30 (0.3627 s / it) +cv: [10] best hparam: (4.3, 1.0) (033) ('033_lr4.3e+00_wd1.0e+00') loss: 2.570 acc: 0.238 f1: 0.164 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__attn/checkpoint-last.pth +train: [11] [ 0/400] eta: 0:21:22 lr: nan time: 3.2050 data: 2.9918 max mem: 4841 +train: [11] [ 20/400] eta: 0:03:00 lr: 0.000195 loss: 2.6654 (2.6791) grad: 0.1143 (0.1161) time: 0.3391 data: 0.0044 max mem: 4841 +train: [11] [ 40/400] eta: 0:02:30 lr: 0.000193 loss: 2.6641 (2.6565) grad: 0.1133 (0.1145) time: 0.3558 data: 0.0038 max mem: 4841 +train: [11] [ 60/400] eta: 0:02:13 lr: 0.000192 loss: 2.6693 (2.6812) grad: 0.1170 (0.1158) time: 0.3431 data: 0.0041 max mem: 4841 +train: [11] [ 80/400] eta: 0:02:01 lr: 0.000190 loss: 2.7451 (2.6961) grad: 0.1173 (0.1178) time: 0.3368 data: 0.0040 max mem: 4841 +train: [11] [100/400] eta: 0:01:51 lr: 0.000189 loss: 2.7397 (2.7042) grad: 0.1212 (0.1186) time: 0.3455 data: 0.0041 max mem: 4841 +train: [11] [120/400] eta: 0:01:43 lr: 0.000187 loss: 2.7070 (2.7021) grad: 0.1187 (0.1185) time: 0.3553 data: 0.0042 max mem: 4841 +train: [11] [140/400] eta: 0:01:35 lr: 0.000186 loss: 2.6939 (2.7027) grad: 0.1166 (0.1186) time: 0.3467 data: 0.0042 max mem: 4841 +train: [11] [160/400] eta: 0:01:27 lr: 0.000184 loss: 2.6939 (2.7037) grad: 0.1166 (0.1187) time: 0.3475 data: 0.0039 max mem: 4841 +train: [11] [180/400] eta: 0:01:19 lr: 0.000183 loss: 2.7495 (2.7095) grad: 0.1160 (0.1187) time: 0.3411 data: 0.0041 max mem: 4841 +train: [11] [200/400] eta: 0:01:11 lr: 0.000181 loss: 2.7499 (2.7133) grad: 0.1158 (0.1188) time: 0.3387 data: 0.0042 max mem: 4841 +train: [11] [220/400] eta: 0:01:04 lr: 0.000180 loss: 2.7206 (2.7145) grad: 0.1182 (0.1190) time: 0.3599 data: 0.0041 max mem: 4841 +train: [11] [240/400] eta: 0:00:57 lr: 0.000178 loss: 2.7011 (2.7129) grad: 0.1178 (0.1186) time: 0.3427 data: 0.0038 max mem: 4841 +train: [11] [260/400] eta: 0:00:50 lr: 0.000177 loss: 2.7011 (2.7144) grad: 0.1152 (0.1183) time: 0.3630 data: 0.0043 max mem: 4841 +train: [11] [280/400] eta: 0:00:43 lr: 0.000175 loss: 2.6922 (2.7128) grad: 0.1121 (0.1179) time: 0.3699 data: 0.0045 max mem: 4841 +train: [11] [300/400] eta: 0:00:35 lr: 0.000174 loss: 2.7007 (2.7136) grad: 0.1121 (0.1177) time: 0.3663 data: 0.0044 max mem: 4841 +train: [11] [320/400] eta: 0:00:28 lr: 0.000172 loss: 2.7075 (2.7133) grad: 0.1136 (0.1177) time: 0.3356 data: 0.0038 max mem: 4841 +train: [11] [340/400] eta: 0:00:21 lr: 0.000170 loss: 2.6626 (2.7103) grad: 0.1166 (0.1178) time: 0.3554 data: 0.0043 max mem: 4841 +train: [11] [360/400] eta: 0:00:14 lr: 0.000169 loss: 2.6535 (2.7093) grad: 0.1161 (0.1177) time: 0.3448 data: 0.0041 max mem: 4841 +train: [11] [380/400] eta: 0:00:07 lr: 0.000167 loss: 2.7099 (2.7109) grad: 0.1178 (0.1178) time: 0.3454 data: 0.0040 max mem: 4841 +train: [11] [399/400] eta: 0:00:00 lr: 0.000166 loss: 2.7099 (2.7105) grad: 0.1178 (0.1177) time: 0.3439 data: 0.0041 max mem: 4841 +train: [11] Total time: 0:02:22 (0.3563 s / it) +train: [11] Summary: lr: 0.000166 loss: 2.7099 (2.7105) grad: 0.1178 (0.1177) +eval (validation): [11] [ 0/85] eta: 0:04:44 time: 3.3529 data: 3.0956 max mem: 4841 +eval (validation): [11] [20/85] eta: 0:00:31 time: 0.3382 data: 0.0052 max mem: 4841 +eval (validation): [11] [40/85] eta: 0:00:19 time: 0.3865 data: 0.0046 max mem: 4841 +eval (validation): [11] [60/85] eta: 0:00:09 time: 0.3159 data: 0.0042 max mem: 4841 +eval (validation): [11] [80/85] eta: 0:00:01 time: 0.3395 data: 0.0042 max mem: 4841 +eval (validation): [11] [84/85] eta: 0:00:00 time: 0.3254 data: 0.0042 max mem: 4841 +eval (validation): [11] Total time: 0:00:32 (0.3818 s / it) +cv: [11] best hparam: (26, 1.0) (044) ('044_lr2.6e+01_wd1.0e+00') loss: 2.634 acc: 0.225 f1: 0.158 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__attn/checkpoint-last.pth +train: [12] [ 0/400] eta: 0:21:18 lr: nan time: 3.1950 data: 2.9775 max mem: 4841 +train: [12] [ 20/400] eta: 0:03:02 lr: 0.000164 loss: 2.6617 (2.7075) grad: 0.1232 (0.1211) time: 0.3450 data: 0.0047 max mem: 4841 +train: [12] [ 40/400] eta: 0:02:31 lr: 0.000163 loss: 2.6591 (2.6813) grad: 0.1159 (0.1169) time: 0.3575 data: 0.0039 max mem: 4841 +train: [12] [ 60/400] eta: 0:02:17 lr: 0.000161 loss: 2.6568 (2.6770) grad: 0.1137 (0.1180) time: 0.3673 data: 0.0044 max mem: 4841 +train: [12] [ 80/400] eta: 0:02:03 lr: 0.000160 loss: 2.7160 (2.6843) grad: 0.1217 (0.1203) time: 0.3396 data: 0.0041 max mem: 4841 +train: [12] [100/400] eta: 0:01:54 lr: 0.000158 loss: 2.6783 (2.6826) grad: 0.1246 (0.1211) time: 0.3510 data: 0.0041 max mem: 4841 +train: [12] [120/400] eta: 0:01:46 lr: 0.000156 loss: 2.6664 (2.6761) grad: 0.1227 (0.1210) time: 0.3877 data: 0.0045 max mem: 4841 +train: [12] [140/400] eta: 0:01:38 lr: 0.000155 loss: 2.6881 (2.6855) grad: 0.1158 (0.1202) time: 0.3497 data: 0.0042 max mem: 4841 +train: [12] [160/400] eta: 0:01:29 lr: 0.000153 loss: 2.7320 (2.6859) grad: 0.1158 (0.1199) time: 0.3451 data: 0.0041 max mem: 4841 +train: [12] [180/400] eta: 0:01:20 lr: 0.000152 loss: 2.7302 (2.6918) grad: 0.1191 (0.1195) time: 0.3284 data: 0.0040 max mem: 4841 +train: [12] [200/400] eta: 0:01:12 lr: 0.000150 loss: 2.7036 (2.6916) grad: 0.1117 (0.1185) time: 0.3331 data: 0.0040 max mem: 4841 +train: [12] [220/400] eta: 0:01:05 lr: 0.000149 loss: 2.6733 (2.6880) grad: 0.1092 (0.1179) time: 0.3462 data: 0.0040 max mem: 4841 +train: [12] [240/400] eta: 0:00:57 lr: 0.000147 loss: 2.6504 (2.6879) grad: 0.1092 (0.1173) time: 0.3549 data: 0.0040 max mem: 4841 +train: [12] [260/400] eta: 0:00:50 lr: 0.000145 loss: 2.7148 (2.6908) grad: 0.1151 (0.1177) time: 0.3358 data: 0.0038 max mem: 4841 +train: [12] [280/400] eta: 0:00:43 lr: 0.000144 loss: 2.7148 (2.6918) grad: 0.1182 (0.1176) time: 0.3355 data: 0.0039 max mem: 4841 +train: [12] [300/400] eta: 0:00:35 lr: 0.000142 loss: 2.6725 (2.6919) grad: 0.1132 (0.1176) time: 0.3388 data: 0.0039 max mem: 4841 +train: [12] [320/400] eta: 0:00:28 lr: 0.000141 loss: 2.6748 (2.6936) grad: 0.1132 (0.1174) time: 0.3349 data: 0.0039 max mem: 4841 +train: [12] [340/400] eta: 0:00:21 lr: 0.000139 loss: 2.6745 (2.6933) grad: 0.1148 (0.1173) time: 0.3408 data: 0.0039 max mem: 4841 +train: [12] [360/400] eta: 0:00:14 lr: 0.000138 loss: 2.6745 (2.6922) grad: 0.1162 (0.1175) time: 0.3437 data: 0.0041 max mem: 4841 +train: [12] [380/400] eta: 0:00:07 lr: 0.000136 loss: 2.6915 (2.6918) grad: 0.1130 (0.1171) time: 0.3620 data: 0.0039 max mem: 4841 +train: [12] [399/400] eta: 0:00:00 lr: 0.000134 loss: 2.7055 (2.6934) grad: 0.1109 (0.1171) time: 0.3575 data: 0.0040 max mem: 4841 +train: [12] Total time: 0:02:22 (0.3552 s / it) +train: [12] Summary: lr: 0.000134 loss: 2.7055 (2.6934) grad: 0.1109 (0.1171) +eval (validation): [12] [ 0/85] eta: 0:04:40 time: 3.3037 data: 3.1020 max mem: 4841 +eval (validation): [12] [20/85] eta: 0:00:29 time: 0.3086 data: 0.0164 max mem: 4841 +eval (validation): [12] [40/85] eta: 0:00:17 time: 0.3059 data: 0.0037 max mem: 4841 +eval (validation): [12] [60/85] eta: 0:00:09 time: 0.3448 data: 0.0045 max mem: 4841 +eval (validation): [12] [80/85] eta: 0:00:01 time: 0.3397 data: 0.0046 max mem: 4841 +eval (validation): [12] [84/85] eta: 0:00:00 time: 0.3087 data: 0.0042 max mem: 4841 +eval (validation): [12] Total time: 0:00:30 (0.3612 s / it) +cv: [12] best hparam: (14, 1.0) (040) ('040_lr1.4e+01_wd1.0e+00') loss: 2.602 acc: 0.234 f1: 0.178 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__attn/checkpoint-last.pth +train: [13] [ 0/400] eta: 0:21:51 lr: nan time: 3.2780 data: 3.0137 max mem: 4841 +train: [13] [ 20/400] eta: 0:03:06 lr: 0.000133 loss: 2.6547 (2.6752) grad: 0.1215 (0.1218) time: 0.3502 data: 0.0056 max mem: 4841 +train: [13] [ 40/400] eta: 0:02:30 lr: 0.000131 loss: 2.6547 (2.6670) grad: 0.1158 (0.1187) time: 0.3416 data: 0.0037 max mem: 4841 +train: [13] [ 60/400] eta: 0:02:12 lr: 0.000130 loss: 2.6734 (2.6724) grad: 0.1154 (0.1203) time: 0.3368 data: 0.0043 max mem: 4841 +train: [13] [ 80/400] eta: 0:02:00 lr: 0.000128 loss: 2.6801 (2.6654) grad: 0.1193 (0.1200) time: 0.3384 data: 0.0044 max mem: 4841 +train: [13] [100/400] eta: 0:01:51 lr: 0.000127 loss: 2.6437 (2.6575) grad: 0.1168 (0.1187) time: 0.3408 data: 0.0042 max mem: 4841 +train: [13] [120/400] eta: 0:01:42 lr: 0.000125 loss: 2.6299 (2.6542) grad: 0.1139 (0.1182) time: 0.3490 data: 0.0043 max mem: 4841 +train: [13] [140/400] eta: 0:01:34 lr: 0.000124 loss: 2.6343 (2.6553) grad: 0.1139 (0.1181) time: 0.3490 data: 0.0043 max mem: 4841 +train: [13] [160/400] eta: 0:01:26 lr: 0.000122 loss: 2.6352 (2.6532) grad: 0.1137 (0.1178) time: 0.3260 data: 0.0040 max mem: 4841 +train: [13] [180/400] eta: 0:01:18 lr: 0.000120 loss: 2.6722 (2.6555) grad: 0.1188 (0.1181) time: 0.3455 data: 0.0042 max mem: 4841 +train: [13] [200/400] eta: 0:01:11 lr: 0.000119 loss: 2.6722 (2.6564) grad: 0.1190 (0.1178) time: 0.3364 data: 0.0042 max mem: 4841 +train: [13] [220/400] eta: 0:01:03 lr: 0.000117 loss: 2.6548 (2.6563) grad: 0.1105 (0.1172) time: 0.3436 data: 0.0040 max mem: 4841 +train: [13] [240/400] eta: 0:00:56 lr: 0.000116 loss: 2.6950 (2.6600) grad: 0.1099 (0.1169) time: 0.3354 data: 0.0042 max mem: 4841 +train: [13] [260/400] eta: 0:00:49 lr: 0.000114 loss: 2.6517 (2.6594) grad: 0.1117 (0.1165) time: 0.3454 data: 0.0037 max mem: 4841 +train: [13] [280/400] eta: 0:00:42 lr: 0.000113 loss: 2.6841 (2.6626) grad: 0.1117 (0.1167) time: 0.3309 data: 0.0040 max mem: 4841 +train: [13] [300/400] eta: 0:00:35 lr: 0.000111 loss: 2.6904 (2.6635) grad: 0.1150 (0.1166) time: 0.3398 data: 0.0040 max mem: 4841 +train: [13] [320/400] eta: 0:00:27 lr: 0.000110 loss: 2.6713 (2.6636) grad: 0.1158 (0.1165) time: 0.3302 data: 0.0042 max mem: 4841 +train: [13] [340/400] eta: 0:00:20 lr: 0.000108 loss: 2.6654 (2.6632) grad: 0.1159 (0.1166) time: 0.3340 data: 0.0042 max mem: 4841 +train: [13] [360/400] eta: 0:00:13 lr: 0.000107 loss: 2.6687 (2.6639) grad: 0.1185 (0.1166) time: 0.3523 data: 0.0042 max mem: 4841 +train: [13] [380/400] eta: 0:00:06 lr: 0.000105 loss: 2.6687 (2.6633) grad: 0.1182 (0.1164) time: 0.3561 data: 0.0044 max mem: 4841 +train: [13] [399/400] eta: 0:00:00 lr: 0.000104 loss: 2.6687 (2.6654) grad: 0.1135 (0.1164) time: 0.3406 data: 0.0041 max mem: 4841 +train: [13] Total time: 0:02:19 (0.3487 s / it) +train: [13] Summary: lr: 0.000104 loss: 2.6687 (2.6654) grad: 0.1135 (0.1164) +eval (validation): [13] [ 0/85] eta: 0:04:28 time: 3.1545 data: 2.9610 max mem: 4841 +eval (validation): [13] [20/85] eta: 0:00:30 time: 0.3394 data: 0.0064 max mem: 4841 +eval (validation): [13] [40/85] eta: 0:00:18 time: 0.3298 data: 0.0039 max mem: 4841 +eval (validation): [13] [60/85] eta: 0:00:09 time: 0.3181 data: 0.0043 max mem: 4841 +eval (validation): [13] [80/85] eta: 0:00:01 time: 0.3023 data: 0.0041 max mem: 4841 +eval (validation): [13] [84/85] eta: 0:00:00 time: 0.3051 data: 0.0040 max mem: 4841 +eval (validation): [13] Total time: 0:00:30 (0.3585 s / it) +cv: [13] best hparam: (6, 1.0) (035) ('035_lr6.0e+00_wd1.0e+00') loss: 2.571 acc: 0.241 f1: 0.176 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__attn/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__attn/checkpoint-best.pth +train: [14] [ 0/400] eta: 0:22:36 lr: nan time: 3.3917 data: 3.1144 max mem: 4841 +train: [14] [ 20/400] eta: 0:03:13 lr: 0.000102 loss: 2.6106 (2.6284) grad: 0.1195 (0.1182) time: 0.3640 data: 0.0051 max mem: 4841 +train: [14] [ 40/400] eta: 0:02:31 lr: 0.000101 loss: 2.6309 (2.6343) grad: 0.1207 (0.1196) time: 0.3318 data: 0.0033 max mem: 4841 +train: [14] [ 60/400] eta: 0:02:11 lr: 0.000099 loss: 2.6283 (2.6223) grad: 0.1188 (0.1180) time: 0.3136 data: 0.0038 max mem: 4841 +train: [14] [ 80/400] eta: 0:02:00 lr: 0.000098 loss: 2.5881 (2.6279) grad: 0.1142 (0.1182) time: 0.3427 data: 0.0041 max mem: 4841 +train: [14] [100/400] eta: 0:01:50 lr: 0.000096 loss: 2.6426 (2.6304) grad: 0.1144 (0.1176) time: 0.3374 data: 0.0042 max mem: 4841 +train: [14] [120/400] eta: 0:01:41 lr: 0.000095 loss: 2.6674 (2.6419) grad: 0.1154 (0.1176) time: 0.3290 data: 0.0041 max mem: 4841 +train: [14] [140/400] eta: 0:01:32 lr: 0.000093 loss: 2.6557 (2.6431) grad: 0.1171 (0.1177) time: 0.3290 data: 0.0039 max mem: 4841 +train: [14] [160/400] eta: 0:01:25 lr: 0.000092 loss: 2.6871 (2.6525) grad: 0.1147 (0.1176) time: 0.3408 data: 0.0040 max mem: 4841 +train: [14] [180/400] eta: 0:01:17 lr: 0.000090 loss: 2.6890 (2.6570) grad: 0.1143 (0.1175) time: 0.3281 data: 0.0042 max mem: 4841 +train: [14] [200/400] eta: 0:01:09 lr: 0.000089 loss: 2.6639 (2.6589) grad: 0.1143 (0.1174) time: 0.3298 data: 0.0042 max mem: 4841 +train: [14] [220/400] eta: 0:01:02 lr: 0.000088 loss: 2.6631 (2.6560) grad: 0.1132 (0.1172) time: 0.3312 data: 0.0041 max mem: 4841 +train: [14] [240/400] eta: 0:00:55 lr: 0.000086 loss: 2.6648 (2.6595) grad: 0.1116 (0.1166) time: 0.3347 data: 0.0041 max mem: 4841 +train: [14] [260/400] eta: 0:00:48 lr: 0.000085 loss: 2.6538 (2.6579) grad: 0.1130 (0.1167) time: 0.3282 data: 0.0041 max mem: 4841 +train: [14] [280/400] eta: 0:00:41 lr: 0.000083 loss: 2.6515 (2.6574) grad: 0.1208 (0.1172) time: 0.3275 data: 0.0041 max mem: 4841 +train: [14] [300/400] eta: 0:00:34 lr: 0.000082 loss: 2.6405 (2.6570) grad: 0.1212 (0.1174) time: 0.3302 data: 0.0041 max mem: 4841 +train: [14] [320/400] eta: 0:00:27 lr: 0.000081 loss: 2.6314 (2.6560) grad: 0.1156 (0.1171) time: 0.3286 data: 0.0043 max mem: 4841 +train: [14] [340/400] eta: 0:00:20 lr: 0.000079 loss: 2.6448 (2.6579) grad: 0.1173 (0.1175) time: 0.3428 data: 0.0041 max mem: 4841 +train: [14] [360/400] eta: 0:00:13 lr: 0.000078 loss: 2.7382 (2.6623) grad: 0.1196 (0.1175) time: 0.3453 data: 0.0040 max mem: 4841 +train: [14] [380/400] eta: 0:00:06 lr: 0.000076 loss: 2.6708 (2.6599) grad: 0.1180 (0.1175) time: 0.3429 data: 0.0040 max mem: 4841 +train: [14] [399/400] eta: 0:00:00 lr: 0.000075 loss: 2.6302 (2.6591) grad: 0.1180 (0.1175) time: 0.3331 data: 0.0042 max mem: 4841 +train: [14] Total time: 0:02:16 (0.3424 s / it) +train: [14] Summary: lr: 0.000075 loss: 2.6302 (2.6591) grad: 0.1180 (0.1175) +eval (validation): [14] [ 0/85] eta: 0:04:42 time: 3.3217 data: 3.0778 max mem: 4841 +eval (validation): [14] [20/85] eta: 0:00:31 time: 0.3471 data: 0.0057 max mem: 4841 +eval (validation): [14] [40/85] eta: 0:00:18 time: 0.3347 data: 0.0037 max mem: 4841 +eval (validation): [14] [60/85] eta: 0:00:09 time: 0.3338 data: 0.0041 max mem: 4841 +eval (validation): [14] [80/85] eta: 0:00:01 time: 0.3113 data: 0.0044 max mem: 4841 +eval (validation): [14] [84/85] eta: 0:00:00 time: 0.3021 data: 0.0041 max mem: 4841 +eval (validation): [14] Total time: 0:00:31 (0.3683 s / it) +cv: [14] best hparam: (2.7, 1.0) (030) ('030_lr2.7e+00_wd1.0e+00') loss: 2.561 acc: 0.237 f1: 0.165 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__attn/checkpoint-last.pth +train: [15] [ 0/400] eta: 0:21:57 lr: nan time: 3.2928 data: 3.0770 max mem: 4841 +train: [15] [ 20/400] eta: 0:03:03 lr: 0.000074 loss: 2.6888 (2.6632) grad: 0.1095 (0.1117) time: 0.3416 data: 0.0048 max mem: 4841 +train: [15] [ 40/400] eta: 0:02:32 lr: 0.000072 loss: 2.6058 (2.6213) grad: 0.1126 (0.1125) time: 0.3607 data: 0.0038 max mem: 4841 +train: [15] [ 60/400] eta: 0:02:15 lr: 0.000071 loss: 2.6025 (2.6310) grad: 0.1115 (0.1127) time: 0.3452 data: 0.0044 max mem: 4841 +train: [15] [ 80/400] eta: 0:02:03 lr: 0.000070 loss: 2.5990 (2.6230) grad: 0.1096 (0.1129) time: 0.3478 data: 0.0042 max mem: 4841 +train: [15] [100/400] eta: 0:01:52 lr: 0.000068 loss: 2.6298 (2.6338) grad: 0.1130 (0.1133) time: 0.3402 data: 0.0043 max mem: 4841 +train: [15] [120/400] eta: 0:01:44 lr: 0.000067 loss: 2.6300 (2.6321) grad: 0.1150 (0.1146) time: 0.3483 data: 0.0041 max mem: 4841 +train: [15] [140/400] eta: 0:01:36 lr: 0.000066 loss: 2.6394 (2.6414) grad: 0.1148 (0.1141) time: 0.3669 data: 0.0042 max mem: 4841 +train: [15] [160/400] eta: 0:01:28 lr: 0.000064 loss: 2.6620 (2.6418) grad: 0.1114 (0.1138) time: 0.3444 data: 0.0044 max mem: 4841 +train: [15] [180/400] eta: 0:01:20 lr: 0.000063 loss: 2.6477 (2.6413) grad: 0.1124 (0.1138) time: 0.3332 data: 0.0043 max mem: 4841 +train: [15] [200/400] eta: 0:01:12 lr: 0.000062 loss: 2.6116 (2.6388) grad: 0.1125 (0.1136) time: 0.3275 data: 0.0040 max mem: 4841 +train: [15] [220/400] eta: 0:01:04 lr: 0.000061 loss: 2.6116 (2.6375) grad: 0.1130 (0.1140) time: 0.3516 data: 0.0043 max mem: 4841 +train: [15] [240/400] eta: 0:00:57 lr: 0.000059 loss: 2.6130 (2.6379) grad: 0.1130 (0.1139) time: 0.3354 data: 0.0042 max mem: 4841 +train: [15] [260/400] eta: 0:00:49 lr: 0.000058 loss: 2.6367 (2.6391) grad: 0.1100 (0.1138) time: 0.3330 data: 0.0039 max mem: 4841 +train: [15] [280/400] eta: 0:00:42 lr: 0.000057 loss: 2.6504 (2.6380) grad: 0.1120 (0.1139) time: 0.3331 data: 0.0042 max mem: 4841 +train: [15] [300/400] eta: 0:00:35 lr: 0.000056 loss: 2.6602 (2.6396) grad: 0.1192 (0.1144) time: 0.3419 data: 0.0040 max mem: 4841 +train: [15] [320/400] eta: 0:00:28 lr: 0.000054 loss: 2.6369 (2.6404) grad: 0.1192 (0.1146) time: 0.3360 data: 0.0039 max mem: 4841 +train: [15] [340/400] eta: 0:00:21 lr: 0.000053 loss: 2.6380 (2.6405) grad: 0.1142 (0.1146) time: 0.3374 data: 0.0041 max mem: 4841 +train: [15] [360/400] eta: 0:00:14 lr: 0.000052 loss: 2.6365 (2.6389) grad: 0.1134 (0.1145) time: 0.3410 data: 0.0042 max mem: 4841 +train: [15] [380/400] eta: 0:00:06 lr: 0.000051 loss: 2.6425 (2.6408) grad: 0.1156 (0.1149) time: 0.3290 data: 0.0041 max mem: 4841 +train: [15] [399/400] eta: 0:00:00 lr: 0.000050 loss: 2.6274 (2.6385) grad: 0.1140 (0.1148) time: 0.3504 data: 0.0042 max mem: 4841 +train: [15] Total time: 0:02:19 (0.3499 s / it) +train: [15] Summary: lr: 0.000050 loss: 2.6274 (2.6385) grad: 0.1140 (0.1148) +eval (validation): [15] [ 0/85] eta: 0:04:37 time: 3.2634 data: 3.0647 max mem: 4841 +eval (validation): [15] [20/85] eta: 0:00:29 time: 0.3184 data: 0.0301 max mem: 4841 +eval (validation): [15] [40/85] eta: 0:00:17 time: 0.3032 data: 0.0046 max mem: 4841 +eval (validation): [15] [60/85] eta: 0:00:09 time: 0.3334 data: 0.0037 max mem: 4841 +eval (validation): [15] [80/85] eta: 0:00:01 time: 0.2991 data: 0.0042 max mem: 4841 +eval (validation): [15] [84/85] eta: 0:00:00 time: 0.2946 data: 0.0040 max mem: 4841 +eval (validation): [15] Total time: 0:00:29 (0.3502 s / it) +cv: [15] best hparam: (4.3, 1.0) (033) ('033_lr4.3e+00_wd1.0e+00') loss: 2.560 acc: 0.240 f1: 0.177 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__attn/checkpoint-last.pth +train: [16] [ 0/400] eta: 0:21:34 lr: nan time: 3.2361 data: 3.0187 max mem: 4841 +train: [16] [ 20/400] eta: 0:02:57 lr: 0.000048 loss: 2.6153 (2.6543) grad: 0.1172 (0.1177) time: 0.3287 data: 0.0047 max mem: 4841 +train: [16] [ 40/400] eta: 0:02:25 lr: 0.000047 loss: 2.6034 (2.6085) grad: 0.1107 (0.1133) time: 0.3378 data: 0.0037 max mem: 4841 +train: [16] [ 60/400] eta: 0:02:10 lr: 0.000046 loss: 2.5810 (2.6100) grad: 0.1082 (0.1127) time: 0.3405 data: 0.0042 max mem: 4841 +train: [16] [ 80/400] eta: 0:01:59 lr: 0.000045 loss: 2.6134 (2.6055) grad: 0.1097 (0.1125) time: 0.3437 data: 0.0042 max mem: 4841 +train: [16] [100/400] eta: 0:01:49 lr: 0.000044 loss: 2.5817 (2.6059) grad: 0.1145 (0.1137) time: 0.3315 data: 0.0041 max mem: 4841 +train: [16] [120/400] eta: 0:01:41 lr: 0.000043 loss: 2.6248 (2.6137) grad: 0.1145 (0.1134) time: 0.3555 data: 0.0044 max mem: 4841 +train: [16] [140/400] eta: 0:01:33 lr: 0.000042 loss: 2.6554 (2.6211) grad: 0.1109 (0.1136) time: 0.3453 data: 0.0042 max mem: 4841 +train: [16] [160/400] eta: 0:01:26 lr: 0.000041 loss: 2.6466 (2.6227) grad: 0.1132 (0.1134) time: 0.3410 data: 0.0040 max mem: 4841 +train: [16] [180/400] eta: 0:01:18 lr: 0.000040 loss: 2.6105 (2.6217) grad: 0.1115 (0.1135) time: 0.3514 data: 0.0042 max mem: 4841 +train: [16] [200/400] eta: 0:01:11 lr: 0.000039 loss: 2.6177 (2.6205) grad: 0.1119 (0.1136) time: 0.3554 data: 0.0043 max mem: 4841 +train: [16] [220/400] eta: 0:01:04 lr: 0.000038 loss: 2.6299 (2.6213) grad: 0.1110 (0.1134) time: 0.3528 data: 0.0042 max mem: 4841 +train: [16] [240/400] eta: 0:00:56 lr: 0.000036 loss: 2.6338 (2.6229) grad: 0.1106 (0.1136) time: 0.3452 data: 0.0041 max mem: 4841 +train: [16] [260/400] eta: 0:00:49 lr: 0.000035 loss: 2.6338 (2.6257) grad: 0.1157 (0.1138) time: 0.3397 data: 0.0042 max mem: 4841 +train: [16] [280/400] eta: 0:00:42 lr: 0.000034 loss: 2.6456 (2.6267) grad: 0.1162 (0.1143) time: 0.3722 data: 0.0043 max mem: 4841 +train: [16] [300/400] eta: 0:00:35 lr: 0.000033 loss: 2.6313 (2.6269) grad: 0.1162 (0.1141) time: 0.3471 data: 0.0044 max mem: 4841 +train: [16] [320/400] eta: 0:00:28 lr: 0.000032 loss: 2.6168 (2.6270) grad: 0.1117 (0.1141) time: 0.3287 data: 0.0041 max mem: 4841 +train: [16] [340/400] eta: 0:00:21 lr: 0.000031 loss: 2.6196 (2.6279) grad: 0.1080 (0.1140) time: 0.3401 data: 0.0040 max mem: 4841 +train: [16] [360/400] eta: 0:00:14 lr: 0.000031 loss: 2.6196 (2.6269) grad: 0.1124 (0.1140) time: 0.3334 data: 0.0040 max mem: 4841 +train: [16] [380/400] eta: 0:00:07 lr: 0.000030 loss: 2.5917 (2.6242) grad: 0.1144 (0.1139) time: 0.3552 data: 0.0042 max mem: 4841 +train: [16] [399/400] eta: 0:00:00 lr: 0.000029 loss: 2.5989 (2.6240) grad: 0.1128 (0.1139) time: 0.3322 data: 0.0041 max mem: 4841 +train: [16] Total time: 0:02:20 (0.3514 s / it) +train: [16] Summary: lr: 0.000029 loss: 2.5989 (2.6240) grad: 0.1128 (0.1139) +eval (validation): [16] [ 0/85] eta: 0:04:35 time: 3.2454 data: 3.0380 max mem: 4841 +eval (validation): [16] [20/85] eta: 0:00:29 time: 0.3086 data: 0.0041 max mem: 4841 +eval (validation): [16] [40/85] eta: 0:00:17 time: 0.3367 data: 0.0051 max mem: 4841 +eval (validation): [16] [60/85] eta: 0:00:09 time: 0.3154 data: 0.0040 max mem: 4841 +eval (validation): [16] [80/85] eta: 0:00:01 time: 0.2964 data: 0.0041 max mem: 4841 +eval (validation): [16] [84/85] eta: 0:00:00 time: 0.2915 data: 0.0040 max mem: 4841 +eval (validation): [16] Total time: 0:00:29 (0.3506 s / it) +cv: [16] best hparam: (1.6, 1.0) (027) ('027_lr1.6e+00_wd1.0e+00') loss: 2.530 acc: 0.243 f1: 0.175 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__attn/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__attn/checkpoint-best.pth +train: [17] [ 0/400] eta: 0:21:56 lr: nan time: 3.2914 data: 3.0318 max mem: 4841 +train: [17] [ 20/400] eta: 0:03:06 lr: 0.000028 loss: 2.5786 (2.5948) grad: 0.1115 (0.1122) time: 0.3517 data: 0.0049 max mem: 4841 +train: [17] [ 40/400] eta: 0:02:29 lr: 0.000027 loss: 2.6229 (2.6149) grad: 0.1122 (0.1135) time: 0.3335 data: 0.0042 max mem: 4841 +train: [17] [ 60/400] eta: 0:02:11 lr: 0.000026 loss: 2.6069 (2.6009) grad: 0.1105 (0.1130) time: 0.3326 data: 0.0044 max mem: 4841 +train: [17] [ 80/400] eta: 0:01:59 lr: 0.000025 loss: 2.5892 (2.6011) grad: 0.1105 (0.1134) time: 0.3279 data: 0.0043 max mem: 4841 +train: [17] [100/400] eta: 0:01:49 lr: 0.000024 loss: 2.6007 (2.6027) grad: 0.1146 (0.1136) time: 0.3278 data: 0.0041 max mem: 4841 +train: [17] [120/400] eta: 0:01:40 lr: 0.000023 loss: 2.5620 (2.6031) grad: 0.1151 (0.1146) time: 0.3305 data: 0.0044 max mem: 4841 +train: [17] [140/400] eta: 0:01:32 lr: 0.000023 loss: 2.5940 (2.6103) grad: 0.1160 (0.1149) time: 0.3277 data: 0.0038 max mem: 4841 +train: [17] [160/400] eta: 0:01:24 lr: 0.000022 loss: 2.5966 (2.6056) grad: 0.1128 (0.1144) time: 0.3246 data: 0.0036 max mem: 4841 +train: [17] [180/400] eta: 0:01:16 lr: 0.000021 loss: 2.5966 (2.6065) grad: 0.1087 (0.1141) time: 0.3317 data: 0.0037 max mem: 4841 +train: [17] [200/400] eta: 0:01:09 lr: 0.000020 loss: 2.5565 (2.6043) grad: 0.1119 (0.1142) time: 0.3272 data: 0.0038 max mem: 4841 +train: [17] [220/400] eta: 0:01:02 lr: 0.000019 loss: 2.5834 (2.6043) grad: 0.1159 (0.1142) time: 0.3295 data: 0.0040 max mem: 4841 +train: [17] [240/400] eta: 0:00:54 lr: 0.000019 loss: 2.6056 (2.6070) grad: 0.1169 (0.1142) time: 0.3247 data: 0.0041 max mem: 4841 +train: [17] [260/400] eta: 0:00:48 lr: 0.000018 loss: 2.5959 (2.6055) grad: 0.1110 (0.1142) time: 0.3582 data: 0.0042 max mem: 4841 +train: [17] [280/400] eta: 0:00:41 lr: 0.000017 loss: 2.5959 (2.6073) grad: 0.1109 (0.1141) time: 0.3347 data: 0.0042 max mem: 4841 +train: [17] [300/400] eta: 0:00:34 lr: 0.000016 loss: 2.6252 (2.6089) grad: 0.1129 (0.1144) time: 0.3246 data: 0.0042 max mem: 4841 +train: [17] [320/400] eta: 0:00:27 lr: 0.000016 loss: 2.6196 (2.6079) grad: 0.1100 (0.1140) time: 0.3390 data: 0.0038 max mem: 4841 +train: [17] [340/400] eta: 0:00:20 lr: 0.000015 loss: 2.6486 (2.6095) grad: 0.1089 (0.1140) time: 0.3462 data: 0.0040 max mem: 4841 +train: [17] [360/400] eta: 0:00:13 lr: 0.000014 loss: 2.6353 (2.6097) grad: 0.1101 (0.1137) time: 0.3551 data: 0.0043 max mem: 4841 +train: [17] [380/400] eta: 0:00:06 lr: 0.000014 loss: 2.5882 (2.6087) grad: 0.1120 (0.1139) time: 0.3472 data: 0.0040 max mem: 4841 +train: [17] [399/400] eta: 0:00:00 lr: 0.000013 loss: 2.5882 (2.6083) grad: 0.1084 (0.1136) time: 0.3394 data: 0.0041 max mem: 4841 +train: [17] Total time: 0:02:17 (0.3433 s / it) +train: [17] Summary: lr: 0.000013 loss: 2.5882 (2.6083) grad: 0.1084 (0.1136) +eval (validation): [17] [ 0/85] eta: 0:04:50 time: 3.4126 data: 3.1958 max mem: 4841 +eval (validation): [17] [20/85] eta: 0:00:32 time: 0.3544 data: 0.0057 max mem: 4841 +eval (validation): [17] [40/85] eta: 0:00:18 time: 0.3066 data: 0.0038 max mem: 4841 +eval (validation): [17] [60/85] eta: 0:00:09 time: 0.3243 data: 0.0043 max mem: 4841 +eval (validation): [17] [80/85] eta: 0:00:01 time: 0.3223 data: 0.0044 max mem: 4841 +eval (validation): [17] [84/85] eta: 0:00:00 time: 0.3023 data: 0.0043 max mem: 4841 +eval (validation): [17] Total time: 0:00:31 (0.3651 s / it) +cv: [17] best hparam: (8.3, 1.0) (037) ('037_lr8.3e+00_wd1.0e+00') loss: 2.605 acc: 0.239 f1: 0.186 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__attn/checkpoint-last.pth +train: [18] [ 0/400] eta: 0:21:55 lr: nan time: 3.2880 data: 3.0663 max mem: 4841 +train: [18] [ 20/400] eta: 0:02:59 lr: 0.000012 loss: 2.5262 (2.5562) grad: 0.1091 (0.1164) time: 0.3303 data: 0.0040 max mem: 4841 +train: [18] [ 40/400] eta: 0:02:26 lr: 0.000012 loss: 2.5579 (2.5697) grad: 0.1160 (0.1150) time: 0.3422 data: 0.0038 max mem: 4841 +train: [18] [ 60/400] eta: 0:02:10 lr: 0.000011 loss: 2.6217 (2.5897) grad: 0.1164 (0.1153) time: 0.3358 data: 0.0046 max mem: 4841 +train: [18] [ 80/400] eta: 0:01:58 lr: 0.000011 loss: 2.6028 (2.5856) grad: 0.1138 (0.1160) time: 0.3258 data: 0.0035 max mem: 4841 +train: [18] [100/400] eta: 0:01:50 lr: 0.000010 loss: 2.6181 (2.5951) grad: 0.1111 (0.1148) time: 0.3635 data: 0.0047 max mem: 4841 +train: [18] [120/400] eta: 0:01:43 lr: 0.000009 loss: 2.6232 (2.5959) grad: 0.1123 (0.1150) time: 0.3643 data: 0.0044 max mem: 4841 +train: [18] [140/400] eta: 0:01:34 lr: 0.000009 loss: 2.6234 (2.6009) grad: 0.1148 (0.1145) time: 0.3457 data: 0.0044 max mem: 4841 +train: [18] [160/400] eta: 0:01:26 lr: 0.000008 loss: 2.6607 (2.6058) grad: 0.1163 (0.1149) time: 0.3413 data: 0.0041 max mem: 4841 +train: [18] [180/400] eta: 0:01:18 lr: 0.000008 loss: 2.6456 (2.6083) grad: 0.1108 (0.1144) time: 0.3333 data: 0.0043 max mem: 4841 +train: [18] [200/400] eta: 0:01:11 lr: 0.000007 loss: 2.6011 (2.6067) grad: 0.1101 (0.1141) time: 0.3363 data: 0.0043 max mem: 4841 +train: [18] [220/400] eta: 0:01:03 lr: 0.000007 loss: 2.6142 (2.6097) grad: 0.1104 (0.1139) time: 0.3345 data: 0.0040 max mem: 4841 +train: [18] [240/400] eta: 0:00:56 lr: 0.000006 loss: 2.6080 (2.6083) grad: 0.1108 (0.1141) time: 0.3453 data: 0.0046 max mem: 4841 +train: [18] [260/400] eta: 0:00:49 lr: 0.000006 loss: 2.5821 (2.6073) grad: 0.1132 (0.1143) time: 0.3371 data: 0.0038 max mem: 4841 +train: [18] [280/400] eta: 0:00:42 lr: 0.000006 loss: 2.6121 (2.6087) grad: 0.1090 (0.1143) time: 0.3366 data: 0.0044 max mem: 4841 +train: [18] [300/400] eta: 0:00:34 lr: 0.000005 loss: 2.6503 (2.6131) grad: 0.1096 (0.1144) time: 0.3237 data: 0.0037 max mem: 4841 +train: [18] [320/400] eta: 0:00:27 lr: 0.000005 loss: 2.6367 (2.6099) grad: 0.1141 (0.1143) time: 0.3510 data: 0.0043 max mem: 4841 +train: [18] [340/400] eta: 0:00:20 lr: 0.000004 loss: 2.5369 (2.6081) grad: 0.1124 (0.1141) time: 0.3481 data: 0.0042 max mem: 4841 +train: [18] [360/400] eta: 0:00:13 lr: 0.000004 loss: 2.5582 (2.6056) grad: 0.1144 (0.1142) time: 0.3330 data: 0.0042 max mem: 4841 +train: [18] [380/400] eta: 0:00:06 lr: 0.000004 loss: 2.5604 (2.6039) grad: 0.1113 (0.1140) time: 0.3545 data: 0.0042 max mem: 4841 +train: [18] [399/400] eta: 0:00:00 lr: 0.000003 loss: 2.5784 (2.6035) grad: 0.1105 (0.1139) time: 0.3420 data: 0.0043 max mem: 4841 +train: [18] Total time: 0:02:19 (0.3489 s / it) +train: [18] Summary: lr: 0.000003 loss: 2.5784 (2.6035) grad: 0.1105 (0.1139) +eval (validation): [18] [ 0/85] eta: 0:04:41 time: 3.3142 data: 3.0565 max mem: 4841 +eval (validation): [18] [20/85] eta: 0:00:32 time: 0.3538 data: 0.0045 max mem: 4841 +eval (validation): [18] [40/85] eta: 0:00:18 time: 0.3349 data: 0.0040 max mem: 4841 +eval (validation): [18] [60/85] eta: 0:00:09 time: 0.3243 data: 0.0045 max mem: 4841 +eval (validation): [18] [80/85] eta: 0:00:01 time: 0.3353 data: 0.0047 max mem: 4841 +eval (validation): [18] [84/85] eta: 0:00:00 time: 0.3167 data: 0.0045 max mem: 4841 +eval (validation): [18] Total time: 0:00:31 (0.3730 s / it) +cv: [18] best hparam: (6, 1.0) (035) ('035_lr6.0e+00_wd1.0e+00') loss: 2.568 acc: 0.243 f1: 0.188 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__attn/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__attn/checkpoint-best.pth +train: [19] [ 0/400] eta: 0:22:05 lr: nan time: 3.3145 data: 3.0268 max mem: 4841 +train: [19] [ 20/400] eta: 0:03:23 lr: 0.000003 loss: 2.5675 (2.6141) grad: 0.1082 (0.1122) time: 0.3955 data: 0.0333 max mem: 4841 +train: [19] [ 40/400] eta: 0:02:36 lr: 0.000003 loss: 2.5669 (2.5915) grad: 0.1089 (0.1111) time: 0.3310 data: 0.0040 max mem: 4841 +train: [19] [ 60/400] eta: 0:02:14 lr: 0.000002 loss: 2.5464 (2.5821) grad: 0.1090 (0.1107) time: 0.3116 data: 0.0040 max mem: 4841 +train: [19] [ 80/400] eta: 0:02:01 lr: 0.000002 loss: 2.6142 (2.5988) grad: 0.1103 (0.1108) time: 0.3312 data: 0.0036 max mem: 4841 +train: [19] [100/400] eta: 0:01:51 lr: 0.000002 loss: 2.5943 (2.5954) grad: 0.1103 (0.1114) time: 0.3476 data: 0.0042 max mem: 4841 +train: [19] [120/400] eta: 0:01:42 lr: 0.000002 loss: 2.5512 (2.5887) grad: 0.1122 (0.1121) time: 0.3264 data: 0.0043 max mem: 4841 +train: [19] [140/400] eta: 0:01:33 lr: 0.000001 loss: 2.6063 (2.5984) grad: 0.1102 (0.1120) time: 0.3341 data: 0.0043 max mem: 4841 +train: [19] [160/400] eta: 0:01:25 lr: 0.000001 loss: 2.6063 (2.5984) grad: 0.1084 (0.1115) time: 0.3307 data: 0.0042 max mem: 4841 +train: [19] [180/400] eta: 0:01:17 lr: 0.000001 loss: 2.5568 (2.5915) grad: 0.1078 (0.1116) time: 0.3276 data: 0.0040 max mem: 4841 +train: [19] [200/400] eta: 0:01:10 lr: 0.000001 loss: 2.5445 (2.5872) grad: 0.1079 (0.1115) time: 0.3379 data: 0.0043 max mem: 4841 +train: [19] [220/400] eta: 0:01:03 lr: 0.000001 loss: 2.5281 (2.5853) grad: 0.1067 (0.1111) time: 0.3355 data: 0.0041 max mem: 4841 +train: [19] [240/400] eta: 0:00:55 lr: 0.000001 loss: 2.5840 (2.5858) grad: 0.1061 (0.1107) time: 0.3322 data: 0.0041 max mem: 4841 +train: [19] [260/400] eta: 0:00:48 lr: 0.000000 loss: 2.5962 (2.5850) grad: 0.1080 (0.1108) time: 0.3285 data: 0.0040 max mem: 4841 +train: [19] [280/400] eta: 0:00:41 lr: 0.000000 loss: 2.5552 (2.5861) grad: 0.1073 (0.1105) time: 0.3426 data: 0.0042 max mem: 4841 +train: [19] [300/400] eta: 0:00:34 lr: 0.000000 loss: 2.5920 (2.5881) grad: 0.1071 (0.1105) time: 0.3409 data: 0.0044 max mem: 4841 +train: [19] [320/400] eta: 0:00:27 lr: 0.000000 loss: 2.5966 (2.5903) grad: 0.1083 (0.1105) time: 0.3454 data: 0.0042 max mem: 4841 +train: [19] [340/400] eta: 0:00:20 lr: 0.000000 loss: 2.5880 (2.5890) grad: 0.1092 (0.1106) time: 0.3416 data: 0.0041 max mem: 4841 +train: [19] [360/400] eta: 0:00:13 lr: 0.000000 loss: 2.6045 (2.5897) grad: 0.1092 (0.1106) time: 0.3352 data: 0.0040 max mem: 4841 +train: [19] [380/400] eta: 0:00:06 lr: 0.000000 loss: 2.6175 (2.5897) grad: 0.1103 (0.1108) time: 0.3384 data: 0.0042 max mem: 4841 +train: [19] [399/400] eta: 0:00:00 lr: 0.000000 loss: 2.6143 (2.5906) grad: 0.1097 (0.1108) time: 0.3401 data: 0.0042 max mem: 4841 +train: [19] Total time: 0:02:18 (0.3454 s / it) +train: [19] Summary: lr: 0.000000 loss: 2.6143 (2.5906) grad: 0.1097 (0.1108) +eval (validation): [19] [ 0/85] eta: 0:04:42 time: 3.3180 data: 3.1137 max mem: 4841 +eval (validation): [19] [20/85] eta: 0:00:29 time: 0.3159 data: 0.0038 max mem: 4841 +eval (validation): [19] [40/85] eta: 0:00:18 time: 0.3499 data: 0.0049 max mem: 4841 +eval (validation): [19] [60/85] eta: 0:00:09 time: 0.3134 data: 0.0041 max mem: 4841 +eval (validation): [19] [80/85] eta: 0:00:01 time: 0.3020 data: 0.0043 max mem: 4841 +eval (validation): [19] [84/85] eta: 0:00:00 time: 0.2837 data: 0.0040 max mem: 4841 +eval (validation): [19] Total time: 0:00:30 (0.3571 s / it) +cv: [19] best hparam: (6, 1.0) (035) ('035_lr6.0e+00_wd1.0e+00') loss: 2.568 acc: 0.244 f1: 0.187 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__attn/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__attn/checkpoint-best.pth +evaluating last checkpoint: experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__attn/checkpoint-last.pth +eval model info: +{"score": 0.24363233665559247, "hparam": [6, 1.0], "hparam_id": 35, "epoch": 19, "is_best": true, "best_score": 0.24363233665559247} +eval (train): [20] [ 0/509] eta: 0:25:41 time: 3.0291 data: 2.7816 max mem: 4841 +eval (train): [20] [ 20/509] eta: 0:03:47 time: 0.3372 data: 0.0055 max mem: 4841 +eval (train): [20] [ 40/509] eta: 0:03:06 time: 0.3248 data: 0.0036 max mem: 4841 +eval (train): [20] [ 60/509] eta: 0:02:44 time: 0.3028 data: 0.0044 max mem: 4841 +eval (train): [20] [ 80/509] eta: 0:02:33 time: 0.3365 data: 0.0041 max mem: 4841 +eval (train): [20] [100/509] eta: 0:02:23 time: 0.3247 data: 0.0043 max mem: 4841 +eval (train): [20] [120/509] eta: 0:02:15 time: 0.3376 data: 0.0045 max mem: 4841 +eval (train): [20] [140/509] eta: 0:02:09 time: 0.3638 data: 0.0045 max mem: 4841 +eval (train): [20] [160/509] eta: 0:02:03 time: 0.3714 data: 0.0047 max mem: 4841 +eval (train): [20] [180/509] eta: 0:01:55 time: 0.3267 data: 0.0045 max mem: 4841 +eval (train): [20] [200/509] eta: 0:01:46 time: 0.2983 data: 0.0039 max mem: 4841 +eval (train): [20] [220/509] eta: 0:01:40 time: 0.3554 data: 0.0048 max mem: 4841 +eval (train): [20] [240/509] eta: 0:01:32 time: 0.3205 data: 0.0044 max mem: 4841 +eval (train): [20] [260/509] eta: 0:01:24 time: 0.3034 data: 0.0039 max mem: 4841 +eval (train): [20] [280/509] eta: 0:01:17 time: 0.3033 data: 0.0041 max mem: 4841 +eval (train): [20] [300/509] eta: 0:01:10 time: 0.3304 data: 0.0048 max mem: 4841 +eval (train): [20] [320/509] eta: 0:01:04 time: 0.3780 data: 0.0042 max mem: 4841 +eval (train): [20] [340/509] eta: 0:00:57 time: 0.3057 data: 0.0037 max mem: 4841 +eval (train): [20] [360/509] eta: 0:00:50 time: 0.3082 data: 0.0039 max mem: 4841 +eval (train): [20] [380/509] eta: 0:00:43 time: 0.3251 data: 0.0050 max mem: 4841 +eval (train): [20] [400/509] eta: 0:00:36 time: 0.3208 data: 0.0036 max mem: 4841 +eval (train): [20] [420/509] eta: 0:00:29 time: 0.3118 data: 0.0041 max mem: 4841 +eval (train): [20] [440/509] eta: 0:00:22 time: 0.3108 data: 0.0041 max mem: 4841 +eval (train): [20] [460/509] eta: 0:00:16 time: 0.3248 data: 0.0042 max mem: 4841 +eval (train): [20] [480/509] eta: 0:00:09 time: 0.3265 data: 0.0045 max mem: 4841 +eval (train): [20] [500/509] eta: 0:00:02 time: 0.3187 data: 0.0045 max mem: 4841 +eval (train): [20] [508/509] eta: 0:00:00 time: 0.2974 data: 0.0040 max mem: 4841 +eval (train): [20] Total time: 0:02:49 (0.3326 s / it) +eval (validation): [20] [ 0/85] eta: 0:04:15 time: 3.0096 data: 2.7598 max mem: 4841 +eval (validation): [20] [20/85] eta: 0:00:31 time: 0.3578 data: 0.0050 max mem: 4841 +eval (validation): [20] [40/85] eta: 0:00:18 time: 0.3287 data: 0.0043 max mem: 4841 +eval (validation): [20] [60/85] eta: 0:00:09 time: 0.3492 data: 0.0045 max mem: 4841 +eval (validation): [20] [80/85] eta: 0:00:01 time: 0.3023 data: 0.0042 max mem: 4841 +eval (validation): [20] [84/85] eta: 0:00:00 time: 0.2916 data: 0.0040 max mem: 4841 +eval (validation): [20] Total time: 0:00:31 (0.3661 s / it) +eval (test): [20] [ 0/85] eta: 0:04:09 time: 2.9303 data: 2.6939 max mem: 4841 +eval (test): [20] [20/85] eta: 0:00:31 time: 0.3548 data: 0.0054 max mem: 4841 +eval (test): [20] [40/85] eta: 0:00:18 time: 0.3261 data: 0.0041 max mem: 4841 +eval (test): [20] [60/85] eta: 0:00:09 time: 0.3179 data: 0.0042 max mem: 4841 +eval (test): [20] [80/85] eta: 0:00:01 time: 0.3234 data: 0.0046 max mem: 4841 +eval (test): [20] [84/85] eta: 0:00:00 time: 0.3025 data: 0.0035 max mem: 4841 +eval (test): [20] Total time: 0:00:30 (0.3616 s / it) +eval (testid): [20] [ 0/82] eta: 0:04:05 time: 2.9984 data: 2.7477 max mem: 4841 +eval (testid): [20] [20/82] eta: 0:00:29 time: 0.3437 data: 0.0058 max mem: 4841 +eval (testid): [20] [40/82] eta: 0:00:16 time: 0.3156 data: 0.0042 max mem: 4841 +eval (testid): [20] [60/82] eta: 0:00:08 time: 0.3115 data: 0.0043 max mem: 4841 +eval (testid): [20] [80/82] eta: 0:00:00 time: 0.3195 data: 0.0039 max mem: 4841 +eval (testid): [20] [81/82] eta: 0:00:00 time: 0.3115 data: 0.0036 max mem: 4841 +eval (testid): [20] Total time: 0:00:29 (0.3573 s / it) +evaluating best checkpoint: experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__attn/checkpoint-best.pth +eval model info: +{"score": 0.24363233665559247, "hparam": [6, 1.0], "hparam_id": 35, "epoch": 19, "is_best": true, "best_score": 0.24363233665559247} +eval (train): [20] [ 0/509] eta: 0:26:50 time: 3.1638 data: 2.8973 max mem: 4841 +eval (train): [20] [ 20/509] eta: 0:03:53 time: 0.3430 data: 0.0400 max mem: 4841 +eval (train): [20] [ 40/509] eta: 0:03:10 time: 0.3316 data: 0.0372 max mem: 4841 +eval (train): [20] [ 60/509] eta: 0:02:48 time: 0.3091 data: 0.0042 max mem: 4841 +eval (train): [20] [ 80/509] eta: 0:02:36 time: 0.3389 data: 0.0041 max mem: 4841 +eval (train): [20] [100/509] eta: 0:02:25 time: 0.3196 data: 0.0044 max mem: 4841 +eval (train): [20] [120/509] eta: 0:02:17 time: 0.3375 data: 0.0041 max mem: 4841 +eval (train): [20] [140/509] eta: 0:02:08 time: 0.3227 data: 0.0053 max mem: 4841 +eval (train): [20] [160/509] eta: 0:01:59 time: 0.3055 data: 0.0033 max mem: 4841 +eval (train): [20] [180/509] eta: 0:01:51 time: 0.3093 data: 0.0084 max mem: 4841 +eval (train): [20] [200/509] eta: 0:01:45 time: 0.3445 data: 0.0044 max mem: 4841 +eval (train): [20] [220/509] eta: 0:01:37 time: 0.3053 data: 0.0039 max mem: 4841 +eval (train): [20] [240/509] eta: 0:01:30 time: 0.3297 data: 0.0048 max mem: 4841 +eval (train): [20] [260/509] eta: 0:01:23 time: 0.3204 data: 0.0043 max mem: 4841 +eval (train): [20] [280/509] eta: 0:01:16 time: 0.3097 data: 0.0041 max mem: 4841 +eval (train): [20] [300/509] eta: 0:01:09 time: 0.3557 data: 0.0047 max mem: 4841 +eval (train): [20] [320/509] eta: 0:01:03 time: 0.3596 data: 0.0047 max mem: 4841 +eval (train): [20] [340/509] eta: 0:00:56 time: 0.3198 data: 0.0044 max mem: 4841 +eval (train): [20] [360/509] eta: 0:00:49 time: 0.3264 data: 0.0045 max mem: 4841 +eval (train): [20] [380/509] eta: 0:00:43 time: 0.3433 data: 0.0049 max mem: 4841 +eval (train): [20] [400/509] eta: 0:00:36 time: 0.3304 data: 0.0042 max mem: 4841 +eval (train): [20] [420/509] eta: 0:00:29 time: 0.3092 data: 0.0043 max mem: 4841 +eval (train): [20] [440/509] eta: 0:00:23 time: 0.3226 data: 0.0046 max mem: 4841 +eval (train): [20] [460/509] eta: 0:00:16 time: 0.3014 data: 0.0043 max mem: 4841 +eval (train): [20] [480/509] eta: 0:00:09 time: 0.3377 data: 0.0046 max mem: 4841 +eval (train): [20] [500/509] eta: 0:00:02 time: 0.3317 data: 0.0044 max mem: 4841 +eval (train): [20] [508/509] eta: 0:00:00 time: 0.3017 data: 0.0040 max mem: 4841 +eval (train): [20] Total time: 0:02:49 (0.3331 s / it) +eval (validation): [20] [ 0/85] eta: 0:04:23 time: 3.0969 data: 2.8779 max mem: 4841 +eval (validation): [20] [20/85] eta: 0:00:33 time: 0.3855 data: 0.0275 max mem: 4841 +eval (validation): [20] [40/85] eta: 0:00:18 time: 0.3215 data: 0.0035 max mem: 4841 +eval (validation): [20] [60/85] eta: 0:00:09 time: 0.3215 data: 0.0042 max mem: 4841 +eval (validation): [20] [80/85] eta: 0:00:01 time: 0.2943 data: 0.0040 max mem: 4841 +eval (validation): [20] [84/85] eta: 0:00:00 time: 0.2821 data: 0.0038 max mem: 4841 +eval (validation): [20] Total time: 0:00:30 (0.3631 s / it) +eval (test): [20] [ 0/85] eta: 0:04:17 time: 3.0336 data: 2.8195 max mem: 4841 +eval (test): [20] [20/85] eta: 0:00:31 time: 0.3604 data: 0.0128 max mem: 4841 +eval (test): [20] [40/85] eta: 0:00:18 time: 0.3129 data: 0.0037 max mem: 4841 +eval (test): [20] [60/85] eta: 0:00:09 time: 0.3125 data: 0.0045 max mem: 4841 +eval (test): [20] [80/85] eta: 0:00:01 time: 0.2971 data: 0.0038 max mem: 4841 +eval (test): [20] [84/85] eta: 0:00:00 time: 0.2793 data: 0.0031 max mem: 4841 +eval (test): [20] Total time: 0:00:29 (0.3523 s / it) +eval (testid): [20] [ 0/82] eta: 0:04:00 time: 2.9344 data: 2.7294 max mem: 4841 +eval (testid): [20] [20/82] eta: 0:00:28 time: 0.3332 data: 0.0268 max mem: 4841 +eval (testid): [20] [40/82] eta: 0:00:16 time: 0.3265 data: 0.0048 max mem: 4841 +eval (testid): [20] [60/82] eta: 0:00:08 time: 0.3079 data: 0.0045 max mem: 4841 +eval (testid): [20] [80/82] eta: 0:00:00 time: 0.3047 data: 0.0041 max mem: 4841 +eval (testid): [20] [81/82] eta: 0:00:00 time: 0.2946 data: 0.0040 max mem: 4841 +eval (testid): [20] Total time: 0:00:28 (0.3508 s / it) +eval results: + +| model | repr | clf | dataset | ckpt | epoch | lr | wd | hparam_id | hparam | split | loss | acc | acc_std | f1 | f1_std | +|:---------|:-------|:------|:-------------|:-------|--------:|-------:|-----:|------------:|:---------|:-----------|-------:|--------:|----------:|--------:|----------:| +| flat_mae | reg | attn | nsd_cococlip | best | 19 | 0.0018 | 0.05 | 35 | [6, 1.0] | train | 2.1275 | 0.36402 | 0.0025285 | 0.31873 | 0.0027628 | +| flat_mae | reg | attn | nsd_cococlip | best | 19 | 0.0018 | 0.05 | 35 | [6, 1.0] | validation | 2.5683 | 0.24363 | 0.0049811 | 0.18654 | 0.004581 | +| flat_mae | reg | attn | nsd_cococlip | best | 19 | 0.0018 | 0.05 | 35 | [6, 1.0] | test | 2.5372 | 0.26419 | 0.0051677 | 0.19913 | 0.0050291 | +| flat_mae | reg | attn | nsd_cococlip | best | 19 | 0.0018 | 0.05 | 35 | [6, 1.0] | testid | 2.5783 | 0.2381 | 0.0053546 | 0.19291 | 0.0050232 | + + +done! total time: 1:08:18 diff --git a/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__attn/train_log.json b/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__attn/train_log.json new file mode 100644 index 0000000000000000000000000000000000000000..f3c4772a120b236f61011357e7a119e798613b75 --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__attn/train_log.json @@ -0,0 +1,20 @@ +{"epoch": 0, "train/lr": 2.987987987987988e-05, "train/loss": 3.1438705348968505, "train/grad": 0.06812858572229744, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.18029052734375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.179952392578125, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.179425048828125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.178878173828125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.178358154296875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.17759033203125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.176827392578125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.176011962890625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.17485595703125, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.173729248046875, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.17261474609375, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.171036376953125, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.169600830078125, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.16750244140625, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.16564208984375, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.1639208984375, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.161959228515625, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.159879150390625, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.157723388671875, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.155994873046875, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.15408935546875, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.15232177734375, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.1507275390625, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.14910888671875, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.147708740234375, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.146322021484375, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.145067138671875, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.144228515625, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.14306396484375, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.142008056640625, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.141220703125, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.140450439453125, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.139599609375, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.138941650390625, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.138189697265625, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.1373486328125, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.13623291015625, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.134794921875, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.131988525390625, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.1262939453125, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.119671630859375, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.1135104370117186, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.104332275390625, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.0961842346191406, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.0877825927734377, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.0778619384765626, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.070474853515625, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.0630307006835937, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.0553103637695314, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.009639389337971807, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.009629299123771489, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.009612932279706, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.009597074242774397, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.00958167843753472, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.009560632805805653, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.009537721523083747, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.009512903003487736, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.009481644746847451, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.009449694675859065, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.009420161440502853, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.009378522564657033, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.00934045716188848, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.009290725183673203, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.00924862022511661, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.009212738848291338, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.009173559541814029, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.009136503115296363, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.009104515430517495, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.009084075707942247, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.00906748547917232, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.009058266174979507, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.009054357949644327, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.009055129375774414, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.009057863224297762, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.009063407906796783, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.009069280629046262, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.009075521738268436, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.009083636205177754, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.009092298788018524, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.009098251683171838, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.009101929436437785, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.009103533995803445, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.009103672171477228, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.009100833856500685, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.009098827273119241, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.009104988046456128, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.009132538009434938, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.009230259631294757, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.009481348034460097, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.00968676470918581, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.009900356691796333, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.010215302323922515, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.01050105324946344, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.010957574467174708, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.011414007102139294, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.012037703038658946, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.012737752667162568, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.01336808304535225, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1748640537261963, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1737985610961914, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1720638275146484, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1703920364379883, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.168755292892456, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.16656494140625, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.164154052734375, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.161591053009033, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1584291458129883, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1552207469940186, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1522810459136963, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1482431888580322, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.144702196121216, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.140244245529175, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.136640787124634, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1337757110595703, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1308767795562744, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1283719539642334, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1264843940734863, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.1253604888916016, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.1245980262756348, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.124208450317383, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.124074935913086, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.124160051345825, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.124394416809082, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.1248269081115723, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.125309944152832, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.125826120376587, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.126596689224243, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.1276979446411133, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.128770589828491, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.129784345626831, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.1310555934906006, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.1318724155426025, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.131596565246582, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.1285667419433594, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.1186070442199707, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.095424175262451, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.0525662899017334, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.0297930240631104, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.994590997695923, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.965325355529785, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.9204189777374268, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.8866281509399414, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.8768489360809326, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.84116530418396, "validation/loss_046_lr3.6e+01_wd1.0e+00": 2.825308084487915, "validation/loss_047_lr4.3e+01_wd1.0e+00": 2.8585445880889893, "validation/loss_048_lr5.0e+01_wd1.0e+00": 2.838378667831421, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.056109265411590996, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.05998523440383906, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06459948320413436, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06570690291620525, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06589147286821706, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06607604282022887, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06626061277224068, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06570690291620525, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06496862310815799, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06441491325212255, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06423034330011074, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06607604282022887, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06736803248431156, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.0681063122923588, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.0664451827242525, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06533776301218161, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06478405315614617, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06423034330011074, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.06293835363602805, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.0636766334440753, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.06386120339608711, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.06349206349206349, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.0636766334440753, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.06404577334809892, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.06570690291620525, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.06570690291620525, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.06478405315614617, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.06312292358803986, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.06275378368401624, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.06533776301218161, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.07235142118863049, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.09043927648578812, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.10391288298265043, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.10114433370247324, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.11000369139904023, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.1168327796234773, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.12827611664820968, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.14174972314507198, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.13971945367294206, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.15503875968992248, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.15706902916205243, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.15430047988187523, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.1638981173864895, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.011683771791384022, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.010936057251753799, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.011130093079117243, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.010312740818413619, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.010775613883282019, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.011129937862291642, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.011276112759199153, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.011374754507955212, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.011449811914104456, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.011721188537556519, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.0121787186942068, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.012652231834834113, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.01378343336371741, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.0142013062109584, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.014178919698740381, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.012799367784845125, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.011061713365898696, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.00901736328711601, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.007456897900364273, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.006181466990506861, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.005457242101565844, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.005459203781416718, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.005450820281910238, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.005794344249786307, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.006901432475180653, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.007988401706231918, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.008422624369166415, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.009196579298381443, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.009739037175476304, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.009860964249560539, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.010054780692019054, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.009114728059856416, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.0069947860825637295, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.00644034722661814, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.007501416837277327, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.010722028141317242, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.01936249667549735, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.028514426505815538, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.03776334082686574, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.03675901512341063, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.04193120783978604, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.04818174378003879, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.055128994436025223, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.06504550175488494, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0673083195805834, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0780338999980208, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.07455577421488598, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.07109346525359224, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.08218823758291893, "id_best": 48, "lr_best": 0.015, "wd_best": 0.05, "train/loss_best": 3.0553103637695314, "validation/loss_best": 2.838378667831421, "validation/acc_best": 0.1638981173864895, "validation/f1_best": 0.08218823758291893} +{"epoch": 1, "train/lr": 8.993993993993998e-05, "train/loss": 3.0514038050174714, "train/grad": 0.0880965531244874, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.168515625, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.1666748046875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.163916015625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.16138916015625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.158984375, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.156058349609375, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.152952880859375, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.15000244140625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.146646728515625, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.143779296875, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.14130859375, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.13853271484375, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.13635986328125, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.134173583984375, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.1327099609375, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.131611328125, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.130782470703125, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.130076904296875, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.12952880859375, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.129183349609375, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.12886962890625, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.128465576171875, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.128106689453125, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.127679443359375, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.1269921875, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.125966796875, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.124842529296875, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.123270263671875, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.119404296875, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.1105938720703126, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.09740966796875, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.0818307495117185, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.058172302246094, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.0357846069335936, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.008222961425781, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.9804536437988283, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.9451881408691407, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.915523910522461, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.8901600646972656, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.8648236846923827, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.8472743225097656, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.8268660354614257, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.8178141021728518, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.819664936065674, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.8167348861694337, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.815946979522705, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.8300216674804686, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.8520562744140623, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.867462158203125, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.00938730320893228, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.009341685087420046, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.009272376550361514, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.009211093874182553, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.009156708749942481, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.009092289814725518, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.00903247914975509, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.008980387763585895, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.008930762293748557, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.008897176238242537, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.00887995704310015, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.008875029957853258, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.008886342411860823, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.00891604927368462, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.008950720396824182, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.00898440217366442, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.009023184753023088, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.009062712099403143, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.009098236442077905, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.009123972677625715, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.0091461686254479, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.009162235751282423, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.00917387823574245, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.009180350117385388, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.009181668953970075, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.009177988166920842, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.009171368377283216, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.009172658591996879, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.009223983872216195, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.009480089521966875, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.009863995194900782, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.010212964876554907, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.01069680594606325, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.011223451509140432, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.011958654657937585, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.012803450166247786, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.013304781126789749, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.014118668101727962, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.015203629219904542, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.015930699189193546, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.01659144539386034, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.01706650185864419, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.018001764020882546, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.018847655281424524, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.019229416553862393, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.01994056096766144, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.020972088370472194, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.02244918962009251, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.02351362755987793, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.15685772895813, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.154020071029663, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1497561931610107, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.146038055419922, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1428163051605225, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.138983726501465, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1354479789733887, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.132356882095337, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.129356861114502, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1272494792938232, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.125819683074951, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.124537944793701, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1238579750061035, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1233301162719727, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.123094081878662, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1229588985443115, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.122802734375, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.122605562210083, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1223230361938477, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.1219732761383057, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.1214041709899902, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.120713710784912, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.1196956634521484, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.1183977127075195, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.1166257858276367, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.1133973598480225, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.108107089996338, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.098752021789551, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.0718257427215576, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.021245241165161, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.9797935485839844, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.9353883266448975, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.889232635498047, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.8429157733917236, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.8109705448150635, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.7938663959503174, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.740415096282959, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.746631145477295, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.7482848167419434, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.7684690952301025, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.7683539390563965, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.750614881515503, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.7871460914611816, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.7903993129730225, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.7774062156677246, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.8139822483062744, "validation/loss_046_lr3.6e+01_wd1.0e+00": 2.827160120010376, "validation/loss_047_lr4.3e+01_wd1.0e+00": 2.8610501289367676, "validation/loss_048_lr5.0e+01_wd1.0e+00": 2.875889778137207, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06552233296419344, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06533776301218161, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06496862310815799, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06626061277224068, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06533776301218161, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06736803248431156, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06533776301218161, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06773717238833518, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06570690291620525, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06404577334809892, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.0636766334440753, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.0636766334440753, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.06441491325212255, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.06496862310815799, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.06699889258028793, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.06884459210040605, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.06884459210040605, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.07179771133259505, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.07087486157253599, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.07345884090070137, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.08490217792543374, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.09985234403839055, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.11203396087117018, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.1288298265042451, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.13953488372093023, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.1598375784422296, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.16168327796234774, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.16943521594684385, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.18715393133997785, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.18327796234772978, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.18161683277962348, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.17847914359542266, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.1746031746031746, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.18032484311554078, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.17681801402731634, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.17404946474713917, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.1834625322997416, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.17811000369139904, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.17257290513104467, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.1552233296419343, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.1699889258028793, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.011557758173507474, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.01205771688556534, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.012749668092110896, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.013415674449696902, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.01340085552261949, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.013865680376962957, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.01295704014976187, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.012492358959779884, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.010518209297298922, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.007704380221152499, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.0070215246914224405, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.005827285467026297, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.005364401631662178, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.005375861036238394, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.005375496537579212, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.0051823970328872294, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.0051845677371140314, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.005360182565327904, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.005537648694339506, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.006109603376968672, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.0068299396580322955, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.007286731212651981, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.008566545851891113, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.009467438175617198, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.009543388025654895, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.01006698216706328, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.010607854931530982, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.014942975685651195, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.03064844878261173, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.04272742824811135, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.04994960161132763, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.057854839141694925, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.07096470085145769, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.08822583091750058, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.09325966574395689, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.10377447160400721, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.11475273913521185, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.11348978937805636, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.111699210260229, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.11049068739940526, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.10653915984449358, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.11062963124742385, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.10672234245943336, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.1046435405243208, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.108312443662976, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0974601749532497, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.09643201707511151, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.09346950203494386, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.10094396278143669, "id_best": 36, "lr_best": 0.0021299999999999995, "wd_best": 0.05, "train/loss_best": 2.9451881408691407, "validation/loss_best": 2.740415096282959, "validation/acc_best": 0.18715393133997785, "validation/f1_best": 0.11475273913521185} +{"epoch": 2, "train/lr": 0.00014999999999999988, "train/loss": 2.9782204389572144, "train/grad": 0.10767352860420942, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.150938720703125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.148126220703125, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.143988037109375, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.140794677734375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.1380908203125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.13531494140625, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.1329931640625, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.131036376953125, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.12946044921875, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.1283154296875, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.127568359375, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.1268359375, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.1263916015625, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.125673828125, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.1250341796875, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.12451416015625, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.12384521484375, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.122939453125, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.12205078125, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.121064453125, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.11959716796875, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.11762451171875, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.114078369140625, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.106263427734375, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.0911065673828126, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.063901062011719, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.0334036254882815, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.002969970703125, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.9623460388183593, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.9157170104980468, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.8797698974609376, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.851512603759766, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.8144776153564455, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.7874519348144533, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.7565091323852537, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.7354161071777345, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.7142908477783205, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.7023334884643555, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.6966695404052734, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.6970269775390623, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.7010858917236327, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.705836868286133, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.716306266784668, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.7314269447326662, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.764071054458618, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.8045748138427733, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.8408208465576172, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.891464352607727, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.9897743558883665, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.009001840427517891, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.008952679762151092, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.0088941200543195, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.0088609340460971, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.008845534953288735, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008845729483291508, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.008864726775791497, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.008899275939911603, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.008950316596310586, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.009002068319823593, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.009044968173839152, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.009093285845592618, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.009125717713031918, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.009154069942887873, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.00916963943745941, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.009178530734498053, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.009185061156749726, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.009189526187255978, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.009191269301809371, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.009191273376345635, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.00918944419361651, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.009190340903587639, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.009215437672100962, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.00935084467753768, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.009733843796420843, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.010430867585819214, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.011109027245547623, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.01169697667239234, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.012447785716503859, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.01321327755227685, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.013986411378718913, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.014742934443056584, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.01559844333678484, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.016436423761770128, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.016982201072387397, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.01777130169328302, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.018452852494083346, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.018653688663616778, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.018761741654016076, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.019341206746175885, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.019718037652783096, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.020209016869775952, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.020922016869299113, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.021599446241743862, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.02293180410284549, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.02457669856958091, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.026954474719241263, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.029426039634272455, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.03440388479270041, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.138831853866577, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1358015537261963, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1319093704223633, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.129169464111328, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.127265691757202, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1255486011505127, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1243834495544434, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1236515045166016, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1231391429901123, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.122833013534546, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1226651668548584, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1225242614746094, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.122398614883423, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.122222900390625, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.122041940689087, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1218085289001465, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.12135648727417, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1206729412078857, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1196413040161133, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.1182825565338135, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.115597724914551, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.1103501319885254, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.0971267223358154, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.0655453205108643, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.0162086486816406, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.9534127712249756, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.9053070545196533, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.8686349391937256, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.828429937362671, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.7810564041137695, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.748056173324585, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.7295000553131104, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.737093448638916, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.718688726425171, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.705383062362671, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.704674243927002, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.7198538780212402, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.691744804382324, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.677743911743164, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.723313331604004, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.7719907760620117, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.788341760635376, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.766272783279419, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.8290936946868896, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.811626434326172, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.8430635929107666, "validation/loss_046_lr3.6e+01_wd1.0e+00": 2.98779559135437, "validation/loss_047_lr4.3e+01_wd1.0e+00": 2.9671642780303955, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.010103225708008, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06939830195644149, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06496862310815799, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06718346253229975, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06459948320413436, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06312292358803986, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06275378368401624, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06312292358803986, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06552233296419344, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06773717238833518, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.07032115171650055, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.06829088224437062, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.07345884090070137, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.08527131782945736, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.11406423034330011, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.1212624584717608, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.13215208564045774, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.14304171280915468, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.15023994093761536, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.1598375784422296, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.17423403469915097, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.18143226282761166, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.18235511258767073, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.18143226282761166, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.19139904023624954, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.19232188999630861, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.18899963086009597, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.18807678110003692, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.1998892580287929, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.20284237726098192, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.1862310815799188, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.1777408637873754, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.1773717238833518, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.17238833517903285, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.17220376522702105, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.17220376522702105, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.16629752676264303, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.16279069767441862, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.15134736064968624, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.17220376522702105, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.013629341650559365, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.011619490421629934, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.010711031606534763, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.007977285316815854, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.006227901843180425, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.005358037406773615, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.005182123340971147, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.005180057759458035, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.004964970181228649, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.004964970181228649, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.004962384259259259, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.004962384259259259, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.004964970181228649, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.004959109100400209, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.00536560867818401, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.006914244561303385, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.008588279434999792, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.01074937216578426, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.012479308238303647, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.013802660412403961, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.015029584227820943, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.020252724657186978, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.033991484653565135, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.056793954472771135, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.059565808423608535, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.0655071002820862, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.0753767256960564, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.07960824389350707, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.0857818219859879, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.09650212008860344, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.10488155728340043, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.1147088828950165, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.12371786155347946, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.13790141037299775, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.14129198461309503, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.13666820129911025, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.13484966043612376, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.14210806230496675, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.1380075190662993, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.11601821036747346, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.1047991587035975, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.10486334260499763, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.1140140785751909, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.10595295613765465, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.11047379671338324, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.09693124361153849, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.09841444239946902, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.08997648948962521, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.08864032025857564, "id_best": 38, "lr_best": 0.00294, "wd_best": 0.05, "train/loss_best": 2.6966695404052734, "validation/loss_best": 2.677743911743164, "validation/acc_best": 0.20284237726098192, "validation/f1_best": 0.1380075190662993} +{"epoch": 3, "train/lr": 0.0002100600600600602, "train/loss": 3.0093180918693543, "train/grad": 0.20952002458274366, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.136910400390625, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.134605712890625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.131685791015625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.12983642578125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.128717041015625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.127591552734375, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.126839599609375, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.126226806640625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.125537109375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.12510009765625, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.12458984375, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.123897705078125, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.123134765625, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.1220166015625, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.121099853515625, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.11994384765625, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.118504638671875, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.116112060546875, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.112286376953125, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.10557373046875, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.0897369384765625, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.063043212890625, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.024998779296875, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.9799737548828125, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.93441162109375, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.8876103210449218, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.851246185302734, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.821790924072266, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.7844247436523437, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.7428987884521483, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.712918701171875, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.6939291763305664, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.6677791595458986, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.656136360168457, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.6476921463012695, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.644713325500488, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.6412448120117187, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.641523208618164, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.6497946548461915, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.665796298980713, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.6799575233459474, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.697264804840088, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.7174033737182617, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.741853036880493, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.787905426025391, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.8278542518615724, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.9449622726440428, "train/loss_047_lr4.3e+01_wd1.0e+00": 4.013769772052765, "train/loss_048_lr5.0e+01_wd1.0e+00": 5.7637456917762755, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.008785272487439216, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.008778767317999155, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.008794987187720836, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.008828549955505877, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.008867548031266778, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008918866231106222, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.008966862098313868, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.009005884137004615, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.009038764068391174, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.009059723892714828, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.009072266863659023, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.00908247050596401, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.009087957225274295, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.009092138800770044, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.009094666813034565, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.009095163005404173, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.00909589001443237, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.009098929741885513, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.009123787675052881, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.009226737776771188, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.00961378776933998, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.010317651422228664, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.011199985034763812, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.011988900364376604, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.012553980532102287, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.013048590002581477, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.013502780459821223, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.014005425535142422, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.014726038565859198, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.015793722942471503, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.01655363296158612, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.01713898723013699, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.017519453917630018, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0180125536583364, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.01857118770480156, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.018869841787964105, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.01897302010562271, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.019231722853146494, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.019852753221057354, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.02059278202243149, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.021375746834091842, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.022319954773411154, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.02331593439448625, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0242955082654953, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.02672167236916721, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.02861284838989377, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.03477033787406981, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.06609522887505591, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0861229948233813, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1274678707122803, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.125788450241089, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1240642070770264, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.12310791015625, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1225249767303467, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1220078468322754, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1215462684631348, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1211395263671875, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1206531524658203, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1201529502868652, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1197073459625244, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.119072437286377, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.118485689163208, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1176533699035645, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.116760015487671, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1157138347625732, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1137020587921143, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.109415292739868, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.0988974571228027, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.077075719833374, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.028857707977295, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.9735231399536133, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.9198789596557617, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.87226939201355, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.8302958011627197, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.792121410369873, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.771228313446045, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.757816791534424, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.731464147567749, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.6969716548919678, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.688699245452881, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.6868045330047607, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.674874782562256, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.6717629432678223, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.701237201690674, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.7218096256256104, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.7363131046295166, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.731353282928467, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.7000131607055664, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.7616770267486572, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.794569253921509, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.904003381729126, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.8908283710479736, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1019229888916016, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.9140214920043945, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.106919050216675, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.3372676372528076, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06478405315614617, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06626061277224068, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06699889258028793, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06866002214839424, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.07179771133259505, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.07456626061277224, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.07364341085271318, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.07641196013289037, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.07751937984496124, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.07807308970099668, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.07954964931709117, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.08157991878922112, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.08970099667774087, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.11074197120708748, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.12495385751199704, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.13732004429678848, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.15042451088962716, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.16020671834625322, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.16777408637873753, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.16777408637873753, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.17220376522702105, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.1806939830195644, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.18604651162790697, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.1893687707641196, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.1925064599483204, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.1997046880767811, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.20155038759689922, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.19269102990033224, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.18955334071613142, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.18549280177187155, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.18733850129198967, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.19176818014027316, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.18106312292358803, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.17940199335548174, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.1686969361387966, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.16463639719453674, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.14525655223329642, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.16168327796234774, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.15411590992986343, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.14230343300110743, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.007592482939957991, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.0065629988828480494, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.006036506394689979, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.005736031870942356, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.0059104273814425306, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.006015425251611813, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.006498832532297098, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.0075477239353891334, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.008229726043266555, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.008975243875525596, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.00955158042355146, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.010255924131899888, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.010840439611398864, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.010803341144531664, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.01124616730396385, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.011450820019757203, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.011583127583050455, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.011817336848740848, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.01391643674481167, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.025649623405721914, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.04145549220979603, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.05062001767031199, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.06246546237876213, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.07525112850901734, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.08281263449269204, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.09031573551526502, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.09219158919264857, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.09688235057031062, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.10444467131602568, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.10947449387783252, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.11003732430993285, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.1148685817540126, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.11764114131257003, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.1233091841979762, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.12071560410888264, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.11990730867802996, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.11625969315876593, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.1216040333724205, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.1251638031780075, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.11770954458055292, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.12389075143049305, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.11140518719121313, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.11360737498707657, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.09167040395769926, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.11340307824167974, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.090077575971985, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.09083006726839112, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 33, "lr_best": 0.00129, "wd_best": 0.05, "train/loss_best": 2.656136360168457, "validation/loss_best": 2.6717629432678223, "validation/acc_best": 0.20155038759689922, "validation/f1_best": 0.1233091841979762} +{"epoch": 4, "train/lr": 0.0002701201201201201, "train/loss": 3.0014657485485077, "train/grad": 0.23125618226826192, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.127696533203125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.12646484375, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.1251220703125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.124410400390625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.123792724609375, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.123150634765625, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.12257080078125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.12198486328125, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.121168212890625, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.120281982421875, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.11957275390625, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.118348388671875, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.117115478515625, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.1150390625, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.112608642578125, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.109219970703125, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.101964111328125, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.08486572265625, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.052184753417969, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.0136785888671875, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.9640301513671874, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.91693603515625, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.8717829895019533, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.8290789794921873, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.791088104248047, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.754038543701172, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.7229541015625, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.696769104003906, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.666262969970703, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.641517162322998, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.6305340003967284, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.6229147911071777, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.611945323944092, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.6081880569458007, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.6047059440612794, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.6039926528930666, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.612102565765381, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.624665603637695, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.6363755226135255, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.6651930904388426, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.6819461822509765, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.7154057788848878, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.7544864559173585, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.767720820903778, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.845063052177429, "train/loss_045_lr3.1e+01_wd1.0e+00": 5.07136860370636, "train/loss_046_lr3.6e+01_wd1.0e+00": 5.635767970085144, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.008867832897230983, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.008912124580238014, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.008980156667530537, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.009031918302644043, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.009068968701176345, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.009102267865091562, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.009123457954265177, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.009136413526721298, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.009145957157015801, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.009151394809596241, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.00915510206250474, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.00915897668339312, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.009161232439801097, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.009162775478325785, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.009167871996760368, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.009188162244390697, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.009291667025536299, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.009705535855609924, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.010596580421552062, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.011505544709507376, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.012371444161981344, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.012893944242969156, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.013317607217468322, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0138163868105039, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.01441918351687491, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.015372708640061319, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.016477428120560945, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.01747394012287259, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.018238600101321934, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.01871546829584986, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0191815625783056, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.019456388745456934, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.01960808037314564, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.019625903679989277, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.019808121705427766, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0199134959327057, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.020385103975422682, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.020877978960052133, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.02167667431756854, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.022956524733453988, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.023508429592475295, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.02513264556415379, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.026627403432503343, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.027503910176455974, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.031546811629086735, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.09367204572074116, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.08417374026961624, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.123317241668701, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1226401329040527, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.121946334838867, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1214613914489746, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.121072769165039, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1205904483795166, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1201138496398926, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.119570255279541, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.118861675262451, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1181185245513916, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1173579692840576, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.116074562072754, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.114607810974121, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.111776828765869, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.107414960861206, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.0999035835266113, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.0798964500427246, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.033951759338379, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.9719648361206055, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.9211552143096924, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.8699381351470947, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.826411008834839, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.7892582416534424, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.76069712638855, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.7382688522338867, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.719181776046753, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.7112386226654053, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.698249578475952, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.672783136367798, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.666341543197632, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.6750783920288086, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.687638759613037, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.7040762901306152, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.7074811458587646, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.695333957672119, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.6792044639587402, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.6899545192718506, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.715301990509033, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.7577271461486816, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.841742753982544, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.8610823154449463, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.9087657928466797, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.8344078063964844, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.8798396587371826, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.978628158569336, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06404577334809892, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06607604282022887, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06755260243632337, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.07013658176448874, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.07272056109265411, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.0753045404208195, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.07567368032484312, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.07401255075673681, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.073827980804725, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.07401255075673681, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.0754891103728313, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.08065706902916205, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.09246954595791805, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.12107788851974899, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.1330749354005168, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.14691768180140274, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.1596530084902178, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.17423403469915097, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.1849390919158361, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.18899963086009597, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.18752307124400147, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.1877076411960133, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.18456995201181248, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.19102990033222592, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.19952011812476927, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.20321151716500555, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.20228866740494647, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.1998892580287929, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.19361387966039129, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.18863049095607234, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.18715393133997785, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.1967515688445921, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.1997046880767811, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.19804355850867478, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.18383167220376523, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.1760797342192691, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.16980435585086748, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.17275747508305647, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.18383167220376523, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.16685123661867848, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.1642672572905131, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.005546996955479187, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.005737684161142165, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.005886831428005358, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.006117349147175692, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.006709695655890669, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.008179207141942446, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.00908016244877633, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.00995287691137881, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.01068551063987522, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.01153612076614518, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.011689565761717364, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.01138917036131139, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.011296762313950525, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.01163963121045839, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.013028507619267148, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.016119428991729808, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.03131812877540653, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.05958504482383708, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.06854440541129685, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.07811182442854957, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.0886271329511229, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.09974804975617217, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.10739664221140861, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.11150548130315852, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.11412650564705969, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.11895407787703005, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.11683301105453041, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.12162883894425773, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.1258205065968195, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.12723771089159214, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.12844767951059327, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.13139029695717838, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.1340460637514134, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.13308152956269384, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.13086197322121285, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.13136119740993024, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.13443808348372918, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.1344489094207085, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.12708638883011214, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.11917545120347041, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.12542624117338036, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.12058762501712572, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.1292586917925382, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.11972197615663867, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.12003722026802732, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 29, "lr_best": 0.0006899999999999999, "wd_best": 0.05, "train/loss_best": 2.641517162322998, "validation/loss_best": 2.666341543197632, "validation/acc_best": 0.20321151716500555, "validation/f1_best": 0.12723771089159214} +{"epoch": 5, "train/lr": 0.00029891323817685334, "train/loss": 2.8832516038417815, "train/grad": 0.11385810397565364, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.128697509765625, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.12821533203125, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.12760498046875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.1269384765625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.126571044921875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.125772705078125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.125018310546875, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.1241259765625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.122879638671875, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.121781005859375, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.1204443359375, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.1181640625, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.115552978515625, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.10957763671875, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.098560791015625, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.0786761474609374, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.0403314208984376, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.9890060424804688, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.936041259765625, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.8942329406738283, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.8497959899902345, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.81035400390625, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.773385009765625, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.7394974517822264, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.7063107299804687, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.6671701431274415, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.6423848724365233, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.627383098602295, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.6112314796447755, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.5982147216796876, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.591812725067139, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.5897816467285155, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.5887228775024416, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.590661678314209, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.590582218170166, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.597905979156494, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.6079595947265624, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.6166857719421386, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.6336413192749024, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.663956642150879, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.6836995029449464, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.7015731716156006, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.7292960023880006, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.7771594429016115, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.844473066329956, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.008961906873155385, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.00900343005778268, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.009048069883137942, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.009072242262773216, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.009085540233645589, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.009095306191593409, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.009100356404669583, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.009103261260315776, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.009104378127958626, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.009105143069755286, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.009105696096085011, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.009107436509802938, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.00911409815773368, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.009163470400962978, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.009365559390280396, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.009884516671299935, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.010941438998561353, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.012062108335085213, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.01271629090886563, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.013082886971533298, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.013507911176420749, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.014017541673965753, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.014643238373100758, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.015473404191434384, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.01659925070591271, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.017591568068601193, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.018177408040501178, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.01860253056511283, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0189377364423126, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.019395071640610696, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.019649739316664635, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.019864958003163336, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.02011606835760176, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.02002652396913618, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.020000385697931052, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0201837465679273, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.020714357211254537, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.02107020593248308, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.02176960162818432, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.022873649494722485, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.023920293729752302, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.02525735318660736, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.026045712837949396, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.028208074197173118, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.03164450825192034, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1217901706695557, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1213858127593994, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1208760738372803, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1204404830932617, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1200404167175293, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1195144653320312, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1189229488372803, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.118286609649658, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1173651218414307, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1163249015808105, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.115090847015381, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1126928329467773, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1090030670166016, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.098001480102539, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.073190927505493, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.0321125984191895, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.974313974380493, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.9172215461730957, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.8671066761016846, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.8301806449890137, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.7935519218444824, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.7626800537109375, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.728653907775879, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.697253465652466, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.674290895462036, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.6426944732666016, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.6249561309814453, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.622749090194702, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.6283795833587646, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.6295218467712402, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.6113064289093018, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.5930514335632324, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.5814056396484375, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.5839548110961914, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.588481903076172, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.6078457832336426, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.6171672344207764, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.6254754066467285, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.6630401611328125, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.7099714279174805, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.7517666816711426, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.7315032482147217, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.760748863220215, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.8815760612487793, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.8872814178466797, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06404577334809892, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06404577334809892, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06459948320413436, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06459948320413436, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06552233296419344, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06829088224437062, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.07142857142857142, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.073827980804725, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.07456626061277224, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.07751937984496124, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.07899593946105574, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.08342561830933924, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.0946843853820598, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.1111111111111111, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.12218530823181986, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.13547434477667036, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.14747139165743817, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.15466961978589885, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.16002214839424142, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.17035806570690293, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.17995570321151716, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.18807678110003692, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.1906607604282023, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.19730527870062753, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.20136581764488742, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.20468807678110004, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.20653377630121816, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.20616463639719454, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.20505721668512367, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.21336286452565523, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.22056109265411591, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.22849760059062385, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.22849760059062385, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.22739018087855298, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.21908453303802142, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.21483942414174972, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.20616463639719454, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.1998892580287929, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.18863049095607234, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.18604651162790697, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.18604651162790697, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.1878922111480251, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.18124769287559986, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.17238833517903285, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.0057042307282212795, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.006212589180361176, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.006434094695267257, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.007090113657281624, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.007326051619173514, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.008412656639174728, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.0094780413603567, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.01081748452404938, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.011988012827978484, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.013465959436256385, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.015350281217617194, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.016871976551453626, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.021912574875806726, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.036499685967994806, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.0517202739561744, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.0550054851185059, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.06351517049727014, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.07174275630165804, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.07745092293636038, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.08328594613508036, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.09231552518850113, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.10267940689678008, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.11012016171697776, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.11432700950956921, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.1231203040898577, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.13123301006357682, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.13445182681681186, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.13516809523413872, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.13269621120288475, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.13068594275033277, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.13755819749000706, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.14438910746100686, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.15623649545256618, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.15997958852232133, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.15537269192047995, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.1478981390619158, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.1529698698730428, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.14859208172768482, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.13900077354269305, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.13577823295721547, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.13405257291875305, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.138606542858385, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.13554636656803742, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.13229824998017747, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.1158621965623835, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 32, "lr_best": 0.0011099999999999999, "wd_best": 0.05, "train/loss_best": 2.5887228775024416, "validation/loss_best": 2.5814056396484375, "validation/acc_best": 0.22849760059062385, "validation/f1_best": 0.15623649545256618} +{"epoch": 6, "train/lr": 0.0002924170901991409, "train/loss": 2.8323271429538726, "train/grad": 0.1117775421589613, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.12472412109375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.1242138671875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.123363037109375, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.122520751953125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.12183837890625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.120943603515625, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.119683837890625, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.118499755859375, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.116707763671875, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.11477294921875, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.11263671875, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.108126220703125, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.100709228515625, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.078203125, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.03851806640625, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.9934646606445314, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.940926208496094, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.8896112060546875, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.8412548828125, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.8024916076660156, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.761720199584961, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.726651840209961, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.693360061645508, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.654291229248047, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.6193084716796875, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.5902878570556642, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.5713645935058596, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.5577586936950683, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.5440546035766602, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.5323077201843263, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.524792442321777, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.5214363956451415, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.520830612182617, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.520714282989502, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.517186679840088, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.521704578399658, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.529535007476807, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.5464302825927736, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.5673336124420167, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.5913505506515504, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.6064613389968874, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.6315626382827757, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.670475034713745, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.711281714439392, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.7511226892471314, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.008872651765123009, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.008894320321269333, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.008912856723181904, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.008920621378347277, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.00892439518822357, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008926766312215477, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.008928497156593948, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.00892972896574065, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.008931309266481549, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.008934348502662033, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.008940323255956173, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.008966816950123756, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.009059818841051311, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.009570448873564601, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.010634757848456501, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.01163764862343669, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.012340357974171639, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.012729162387549876, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.013065520212985576, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.013364155571907758, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.013773115486837923, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.014296786705963314, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.014948799875564873, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.015922184912487865, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.016778204147703944, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.017758059967309236, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.018274705074727535, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.018510806453414262, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.018772997572086753, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.018978804131038488, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.019137820014730095, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.019147151340730487, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.019084285995922982, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.01896976582240313, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.019089285782538355, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.019380090688355268, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.019834613692946732, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.020639215181581676, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.02178410494700074, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.022739870036020876, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.02327522403560579, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.024318498168140648, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.025730521120131016, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.027598784007132053, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.029385739462450145, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1220202445983887, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1217682361602783, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.121371269226074, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.121000051498413, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.120614767074585, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.12005877494812, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1193673610687256, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1185250282287598, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.11724853515625, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1155097484588623, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1132149696350098, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.107196569442749, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.0949172973632812, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.0539255142211914, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.9960315227508545, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.945647716522217, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.893545389175415, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.8451147079467773, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.8009612560272217, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.7669739723205566, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.734459161758423, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.7076520919799805, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.6811985969543457, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.6524951457977295, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.6343371868133545, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.617955446243286, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.611821174621582, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.6146280765533447, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.6156625747680664, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.6102335453033447, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.6155405044555664, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.6126692295074463, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.588442802429199, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.581714630126953, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.5850536823272705, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.5908663272857666, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.6465518474578857, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.712493896484375, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.754009246826172, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.7577359676361084, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.8086421489715576, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.8284547328948975, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.8784637451171875, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.8653206825256348, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.8084332942962646, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06386120339608711, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06459948320413436, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.07954964931709117, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.11461794019933555, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.13067552602436322, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.14248800295311922, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.15079365079365079, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.15873015873015872, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.16851236618678478, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.17368032484311555, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.18235511258767073, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.19029162052417867, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.19490586932447398, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.2026578073089701, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.20358065706902917, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.20948689553340716, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.21133259505352528, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.21096345514950166, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.21244001476559615, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.21539313399778517, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.2144702842377261, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.21262458471760798, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.21797711332595054, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.2216685123661868, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.22148394241417496, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.22129937246216316, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.21225544481358435, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.19804355850867478, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.20044296788482835, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.19933554817275748, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.18032484311554078, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.18124769287559986, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.17995570321151716, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.1788482834994463, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.18549280177187155, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.004964970181228649, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.004964970181228649, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.004963245933900562, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.004962384259259259, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.004963245933900562, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.00496410790783837, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.00496410790783837, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.00495565988523735, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.0051648944998569715, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.005633575871013416, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.006823207009840497, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.007752687770287839, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.02561856485879505, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.05197909843214674, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.06052809540351895, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.06879851283849456, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.07662075112952232, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.08314956140539213, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.09293018738334424, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.09792867051936525, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.10828689330842857, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.11647351492962972, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.12117844508189697, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.12731820351944176, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.12914501120134092, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.13276000133755936, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.13455436493529507, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.13535529131811652, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.13977141135542967, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.14348382706427218, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.14539435694747674, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.146071698406215, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.15260584400575147, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.1609061265690219, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.1652700765319782, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.16450292995215005, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.15453013091016377, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.13927702862425348, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.14626880777193857, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.1426439128096109, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.13360988189501016, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.12680389830876146, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.1321784822474185, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.12609376478421364, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.13415967426164346, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 33, "lr_best": 0.00129, "wd_best": 0.05, "train/loss_best": 2.520714282989502, "validation/loss_best": 2.581714630126953, "validation/acc_best": 0.2216685123661868, "validation/f1_best": 0.1609061265690219} +{"epoch": 7, "train/lr": 0.00027969249556793234, "train/loss": 2.8123366332054136, "train/grad": 0.11640940055251121, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.1274267578125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.126824951171875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.125904541015625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.125018310546875, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.124129638671875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.123013916015625, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.121727294921875, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.119925537109375, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.1176806640625, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.114630126953125, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.110726318359375, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.10025634765625, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.0795233154296877, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.02730224609375, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.9735641479492188, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.930020599365234, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.8835855102539063, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.837220458984375, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.791868896484375, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.7550617980957033, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.7172100067138674, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.6852242660522463, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.6478989028930666, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.611731472015381, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.588348789215088, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.5662960529327394, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.547993927001953, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.534540100097656, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.51980393409729, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.508459405899048, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.500817070007324, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.496740388870239, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.4954006099700927, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.496396713256836, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.496532135009766, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.505440559387207, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.51876296043396, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.5358155250549315, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.553465461730957, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.5832532596588136, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.6068482780456543, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.627239818572998, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.6553596210479737, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.695486149787903, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.7065209484100343, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.009000723930075765, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.00901386962737888, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.009024966366123408, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.009030555647332222, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.009033756016287952, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.009036609379108995, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.009039250377099961, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.009042625497095287, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.009048142484389246, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.00905980504117906, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.009090449917130173, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.009243065267801285, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.00972725399537012, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.011112896094564348, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.01219711077399552, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.012741055521182716, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.013143190862610937, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.013531974996440113, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.013958847974427044, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.01431116127409041, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.01484692693222314, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.01548298885114491, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.016565981544554232, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.017937445468269288, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.01885201229248196, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.019348492715507745, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.019531973311677574, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.019576050569303335, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.01949393933173269, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.019421344539150596, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.019370128191076218, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.01930608309805393, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.01934833046980202, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.019375442662276327, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.019521254431456327, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.019932435913942753, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.020688753607682884, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.021503478083759547, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.022202372401952743, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.023397265076637266, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.024341804636642338, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.025197012489661573, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.026624529100954534, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.028319002734497188, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.029116867808625102, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.121203660964966, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1208090782165527, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.120191812515259, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1195483207702637, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1189422607421875, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.118032217025757, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1169307231903076, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.115596294403076, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.113386869430542, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.110050916671753, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1046738624572754, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.087848424911499, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.052882432937622, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.9815521240234375, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.9224612712860107, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.8779261112213135, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.8323614597320557, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.7895843982696533, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.7515692710876465, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.7232816219329834, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.6962666511535645, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.6702990531921387, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.640754461288452, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.6185050010681152, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.6061997413635254, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.593829393386841, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.5812408924102783, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.5670366287231445, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.564209461212158, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.5642316341400146, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.5602574348449707, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.5581281185150146, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.5609898567199707, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.5721964836120605, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.5844626426696777, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.597648859024048, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.6088998317718506, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.618661403656006, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.6216413974761963, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.6737282276153564, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.702005386352539, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.7311036586761475, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.7440133094787598, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.782453775405884, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.8325867652893066, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.0651531930601698, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06755260243632337, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.08084163898117387, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.11277224067921743, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.13547434477667036, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.14839424141749724, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.15651531930601698, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.17072720561092655, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.1819859726836471, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.19139904023624954, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.19564414913252123, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.1982281284606866, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.20210409745293467, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.21114802510151348, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.2146548541897379, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.21520856404577335, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.2201919527500923, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.22388335179032853, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.23145071982281284, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.23255813953488372, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.2351421188630491, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.23883351790328536, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.23791066814322628, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.23809523809523808, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.23661867847914358, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.2334809892949428, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.2277593207825766, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.2294204503506829, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.22296050203026946, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.2249907715023994, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.21207087486157253, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.21244001476559615, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.21188630490956073, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.20468807678110004, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.19896640826873385, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.18383167220376523, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.004977073538800859, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.004966887417218543, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.00497208653175157, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.005421081631346949, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.0056253316068478575, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.005821475396763994, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.005803553494359501, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.006260343375293003, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.006861700631870429, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.008565141070445058, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.012294054144458418, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.028042363211335134, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.052263800589638386, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.06576634847641233, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.07598544395325844, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.08394882981052755, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.09691749647108594, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.10704592292901986, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.1161135973603563, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.1219907534534674, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.12662839965029252, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.13335371019330874, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.13951924904624805, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.14151219856750152, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.14344415052774995, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.1479427233043942, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.1528800788838659, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.16120986221947745, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.1624514965720248, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.16305689975549947, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.16602987171768277, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.16419522208267304, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.16248701342902677, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.1597798260641419, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.15546576885460903, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.14980343722013104, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.1573064460482623, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.15320767259232648, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.15801115343433725, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.14775331000231187, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.14890096998659563, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.14445492927623313, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.144446063249588, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.13942713891498018, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.12847485961004212, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 30, "lr_best": 0.00081, "wd_best": 0.05, "train/loss_best": 2.500817070007324, "validation/loss_best": 2.5602574348449707, "validation/acc_best": 0.23883351790328536, "validation/f1_best": 0.16602987171768277} +{"epoch": 8, "train/lr": 0.0002612959497061927, "train/loss": 2.785860184431076, "train/grad": 0.11738875262439251, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.126429443359375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.12577880859375, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.124754638671875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.12365478515625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.122691650390625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.1212158203125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.119552001953125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.1175, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.11432861328125, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.109447021484375, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.10205078125, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.0793560791015624, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.0403509521484375, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.9772793579101564, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.9269204711914063, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.88658447265625, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.842470855712891, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.797591323852539, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.7545225524902346, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.7208170318603515, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.68644718170166, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.651861209869385, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.609575424194336, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.577574634552002, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.555154552459717, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.5349996757507323, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.516452045440674, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.502130002975464, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.4900772380828857, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.4810487461090087, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.4749005889892577, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.4726260614395144, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.4718251752853395, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.4714846420288086, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.4706596088409425, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.4743878078460693, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.48144588470459, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.4950484466552734, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.511029100418091, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.5275188636779786, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.549667253494263, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.5634780883789063, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.6054970598220826, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.643114924430847, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.6683511924743653, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.009069862416945398, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.009075988279655577, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.009080924913287164, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.009083258595783263, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.009084595125168562, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.00908829189138487, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.009092853283509611, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.00909974448615685, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.009116370948031544, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.00915764146251604, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.009269742520991713, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.009805524710100145, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.010904513681307435, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.012289155442267656, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.012909431466832757, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.013245924026705325, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.01356408502906561, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.013902796730399132, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.014331103451550007, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.01480989195406437, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.015434517180547119, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.016089021181687712, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.017273459169082343, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.01812766583170742, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.018789836494252084, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.019283028873614966, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.019563853363506495, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.01961407054681331, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.019742638012394308, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.01988905530422926, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.019945238954387604, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.019903415800072252, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.01991865617223084, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.019993949732743203, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0201606953330338, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.020473584411665798, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.020975519828498365, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.021584284603595735, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.022159444503486156, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.022953465338796376, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.023825296415016056, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.02423785553313792, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.026175885098055005, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.028136876365169882, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.028714374266564847, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.120426893234253, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1199262142181396, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.119084119796753, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1182541847229004, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1173980236053467, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.11614990234375, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1146209239959717, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.112593173980713, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1090095043182373, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1027510166168213, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.091412305831909, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.0555522441864014, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.001566171646118, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.9300498962402344, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.878359079360962, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.839305877685547, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.7980570793151855, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.757733106613159, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.721665620803833, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.6950507164001465, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.6732094287872314, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.6527533531188965, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.6338672637939453, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.619652271270752, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.6146914958953857, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.618617296218872, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.616161823272705, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.608128547668457, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.5981504917144775, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.592148780822754, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.593963146209717, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.599017381668091, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.6102702617645264, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.6053340435028076, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.5896220207214355, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.6030569076538086, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.630828619003296, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.63757586479187, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.6535532474517822, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.6617496013641357, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.7070326805114746, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.7303707599639893, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.7823235988616943, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.809732437133789, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.844747543334961, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06404577334809892, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06404577334809892, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.0651531930601698, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06755260243632337, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.07179771133259505, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.07567368032484312, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.07936507936507936, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.0843484680693983, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.09191583610188261, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.09579180509413067, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.11812476928755998, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.13344407530454042, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.15190107050572166, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.16611295681063123, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.17331118493909192, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.1786637135474345, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.18844592100406055, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.19804355850867478, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.20302694721299372, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.2039497969730528, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.20985603543743078, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.2146548541897379, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.2172388335179033, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.21945367294204504, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.21834625322997417, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.21834625322997417, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.21760797342192692, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.2222222222222222, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.22111480251015134, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.22129937246216316, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.2188999630860096, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.21779254337393872, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.21797711332595054, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.21926910299003322, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.22554448135843486, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.22093023255813954, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.22720561092654115, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.2235142118863049, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.2222222222222222, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.2174234034699151, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.20764119601328904, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.20210409745293467, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.18586194167589518, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.18087855297157623, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.006195319890340467, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.00628122759952023, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.006701554495672143, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.00795580531019452, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.009167704441961607, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.0113532179867312, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.013081485147230084, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.015996669509694326, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.019033812269054363, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.023821211434201035, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.027512265031821564, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.05239380719647705, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.06493989311832843, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.08013913459208769, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.09343238576022006, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.09939933155903365, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.10546963082282396, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.11358456547154112, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.12155059376338323, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.12810324575727927, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.13134406408498597, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.1356845625831877, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.13952547418111083, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.1403358281924984, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.14371934497957464, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.14578375740434318, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.14684152868353315, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.1492155883456658, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.15416398070069245, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.1558344506233413, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.1592940738564421, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.1581466509538272, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.15739148057088168, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.15585530874514655, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.15890926204796169, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.16024759130534283, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.15483240137029922, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.1606367876320947, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.16421674730579863, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.1639218596253223, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.16591420983487545, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.15552642931481073, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.14733240385232835, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.13274106837036656, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.13288111426552215, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 37, "lr_best": 0.00249, "wd_best": 0.05, "train/loss_best": 2.4950484466552734, "validation/loss_best": 2.63757586479187, "validation/acc_best": 0.22720561092654115, "validation/f1_best": 0.1606367876320947} +{"epoch": 9, "train/lr": 0.00023803200426111704, "train/loss": 2.7572328460216524, "train/grad": 0.11638154655694961, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.1279296875, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.127119140625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.12587158203125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.12471435546875, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.1233642578125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.121629638671875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.119521484375, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.11668701171875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.1117529296875, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.103404541015625, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.088656005859375, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.046690673828125, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.994659423828125, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.9305984497070314, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.8819454956054686, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.842182464599609, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.797984924316406, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.753377685546875, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.711047897338867, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.6785789489746095, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.645017547607422, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.6053760147094724, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.5664249801635743, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.5391837120056153, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.519162502288818, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.5001855278015137, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.484067687988281, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.472473258972168, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.4610502243041994, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.4513037490844725, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.443919849395752, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.4419354152679444, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.4431191539764403, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.4436266803741455, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.443541965484619, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.44605122089386, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.4514454650878905, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.4555083656311036, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.4671952629089358, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.4809036540985105, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.497236566543579, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.5211304664611816, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.539887299537659, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.5668505144119265, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.602598264217377, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.009035072452388705, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.009038564178626984, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.009041248478461057, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.009042341460008175, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.009043889532331378, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.009047275895718486, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.009052736344747245, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.009062570533715189, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.009094705786556006, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.009195118371862918, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.00948266969062388, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.01054850413929671, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.01176466136239469, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.012732995240949094, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.013183149322867394, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.013482271768152714, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.013824234609492123, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.01421753448434174, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.014670423017814755, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.01515997995622456, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.015793554158881305, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.0167859971197322, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.017779243807308377, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.018540649972856045, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.01911659060511738, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.019568505859933794, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.01990780078805983, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.020048007322475313, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.02024204669520259, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.020450712954625486, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.020536431581713258, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.020454286951571702, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.02065291007515043, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.020680459733121097, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.020595825128257274, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.020846634805202484, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.02123183639720082, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.021520402329042555, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.02170371662825346, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.022190419966354968, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.022353936871513724, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.02294398213736713, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.023702307641506194, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.024474404565989972, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.02631337587721646, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1200578212738037, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1195638179779053, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.118716239929199, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.117879629135132, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1170239448547363, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1157145500183105, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1139914989471436, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1114792823791504, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1063296794891357, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.0958333015441895, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.0751898288726807, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.0199437141418457, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.961674928665161, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.897235631942749, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.850971221923828, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.814380407333374, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.7752532958984375, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.7384495735168457, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.70625376701355, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.6847362518310547, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.6671197414398193, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.65085768699646, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.628756523132324, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.609686851501465, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.5953145027160645, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.5764639377593994, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.5624802112579346, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.557779312133789, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.5538511276245117, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.55059814453125, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.550008535385132, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.548631429672241, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.555233955383301, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.563537120819092, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.580777168273926, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.6083028316497803, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.6136999130249023, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.6306471824645996, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.641014814376831, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.695352554321289, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.7222161293029785, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.7360057830810547, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.7531650066375732, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.7545371055603027, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.757225275039673, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06552233296419344, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.07013658176448874, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.08416389811738649, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.10409745293466224, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.12476928755998523, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.14027316352897748, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.1496862310815799, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.16057585825027684, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.16223698781838317, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.1773717238833518, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.18586194167589518, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.19453672942045036, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.19933554817275748, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.2024732373569583, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.20801033591731266, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.21188630490956073, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.21760797342192692, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.22000738279808046, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.2222222222222222, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.22757475083056478, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.23034330011074197, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.23311184939091917, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.23458840900701367, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.23588039867109634, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.23883351790328536, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.23569582871908454, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.2320044296788483, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.23145071982281284, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.22757475083056478, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.22296050203026946, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.22849760059062385, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.22296050203026946, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.21760797342192692, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.2131782945736434, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.20450350682908822, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.2087486157253599, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.21114802510151348, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.21797711332595054, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.005185412745483022, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.005186945309284807, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.005374504587240766, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.005377203313683008, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.0055496667540695524, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.005367102720489451, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.006548876538389113, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.008995642227838252, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.01496183149455643, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.028581072279961987, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.044802153315664305, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.053368452308462065, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.06214755361088012, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.07117896918095122, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.0825505568163728, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.08581562557084742, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.10093468146356772, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.10949084215048709, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.1189532166088285, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.12299755502495154, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.12532007453984065, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.13174138205886843, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.13718228255076337, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.14396012690383161, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.14781301857280024, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.15322793718788527, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.1624772678090913, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.16588259475980435, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.17009230041753506, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.1730542438025028, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.17657868812338806, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.1769091900194523, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.17424322860825614, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.1718636715126474, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.17132037287633975, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.16812302658905187, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.16116377639579677, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.167386563975117, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.1547316862384072, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.13983302504354742, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.13362259397321843, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.13355884548481606, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.13298813282617197, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.1322804454976538, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.13847908470561074, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 31, "lr_best": 0.0009299999999999999, "wd_best": 0.05, "train/loss_best": 2.4419354152679444, "validation/loss_best": 2.548631429672241, "validation/acc_best": 0.23883351790328536, "validation/f1_best": 0.1769091900194523} +{"epoch": 10, "train/lr": 0.00021091808096876188, "train/loss": 2.7291479563713072, "train/grad": 0.114956069663167, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.12557861328125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.124722900390625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.123336181640625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.1218896484375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.120506591796875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.11845947265625, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.11571044921875, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.112205810546875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.1051513671875, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.091497802734375, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.0663739013671876, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.008668212890625, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.9542306518554686, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.8927183532714844, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.8455857849121093, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.8066500854492187, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.76383415222168, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.7210713958740236, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.681125831604004, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.6503594589233397, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.6156327819824217, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.5729460525512695, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.5382400131225586, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.5118275833129884, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.4909898376464845, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.470511589050293, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.451807074546814, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.439381732940674, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.4262558460235595, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.41385009765625, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.403202118873596, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.3985989332199096, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.3964517974853514, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.396626470088959, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.394053168296814, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.399312665462494, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.4061551475524903, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.414436037540436, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.4327783036231994, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.4451846623420717, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.4568913698196413, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.4749287497997283, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.490635062456131, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.509210950136185, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.5411672627925874, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.008941448233090342, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.00894593976670876, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.008950827149674297, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.008955784237477928, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.00896139551885426, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008970536766573787, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.00898331563686952, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.009006673046387732, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.009078633023891598, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.009303828484844416, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.009878348216880113, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.011275622816756368, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.012256362219341099, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.012940918751992285, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.013316911486908794, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.013605048968456686, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.013942626821808517, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.01435152637772262, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.014879240957088768, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.015396320139989256, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.016002474753186106, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.017049730019643904, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.017909694616682827, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.018485812311992048, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.018886393448337913, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.01918784382753074, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.01948013860732317, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.01967650219798088, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.019852850195020436, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.019807451437227428, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.01969197972211987, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.01948305517900735, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.01948633692692965, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.019572284459136426, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.019781592930667103, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.02013564102817327, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.020768190426751973, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.021377268265932798, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.021859112791717053, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.022582094352692365, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.022719996450468898, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.023188655227422715, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.023767071263864636, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.024302070923149587, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.025177918085828425, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1199207305908203, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1193766593933105, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.11849308013916, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1175479888916016, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1165637969970703, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.114995002746582, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1127822399139404, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1093385219573975, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1015124320983887, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.084259510040283, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.0518691539764404, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.9854273796081543, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.9300522804260254, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.8708314895629883, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.826730728149414, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.791588544845581, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.7543280124664307, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.7190263271331787, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.6889781951904297, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.6690142154693604, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.649406671524048, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.629621982574463, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.6105587482452393, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.5957798957824707, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.586745262145996, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.583371877670288, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.5796566009521484, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.573702812194824, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.560770034790039, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.553788661956787, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.5520401000976562, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.552906036376953, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.5618176460266113, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.5703964233398438, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.5955216884613037, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.6130363941192627, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.6383183002471924, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.6623055934906006, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.710324287414551, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.734959363937378, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.7475783824920654, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.7554638385772705, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.7306792736053467, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.768866777420044, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.778503179550171, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06423034330011074, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06441491325212255, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06459948320413436, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.0651531930601698, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.067921742340347, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.07788851974898486, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.09800664451827243, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.11554078995939461, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.13528977482465854, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.1463639719453673, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.15780730897009967, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.16629752676264303, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.17386489479512734, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.18272425249169436, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.18696936138796605, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.19619785898855666, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.19933554817275748, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.2056109265411591, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.21207087486157253, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.21391657438169065, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.21760797342192692, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.22148394241417496, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.22185308231819859, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.2279438907345884, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.22831303063861202, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.23458840900701367, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.2334809892949428, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.23477297895902546, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.23717238833517904, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.2355112587670727, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.23809523809523808, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.23181985972683647, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.23255813953488372, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.22720561092654115, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.22517534145441123, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.2188999630860096, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.22517534145441123, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.2201919527500923, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.2277593207825766, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.23052787006275377, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.22702104097452935, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.22462163159837578, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.005377392458725879, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.005354844120939833, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.006016177256109828, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.006422254241317246, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.006960930786683219, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.00784436572329418, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.009349883330652533, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.012419657661438627, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.0227016937570484, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.039700909433761436, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.05174155225537976, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.06420771826379816, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.07207751331917912, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.08294649260868593, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.09176485235125165, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.09915982877956085, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.10966544159166026, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.11307357757106166, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.12300256087041166, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.1260114511735435, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.1305751780430174, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.13616066938936186, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.13844074949600163, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.14348883471789703, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.14861965781455566, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.15118439775101775, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.15748466429110086, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.15864940121666102, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.1656395318652614, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.1646363358455565, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.1635955970566819, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.16598883739715478, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.16261754429849665, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.16400862363195878, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.16045770763879472, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.16339679697491535, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.1570248678885077, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.15653401034874104, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.1486158294842897, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.1558658048858182, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.1530476746455758, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.16059267577683253, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.17092698690377003, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.16286568451472438, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.15689288727165682, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 33, "lr_best": 0.00129, "wd_best": 0.05, "train/loss_best": 2.396626470088959, "validation/loss_best": 2.5703964233398438, "validation/acc_best": 0.23809523809523808, "validation/f1_best": 0.16400862363195878} +{"epoch": 11, "train/lr": 0.00018113997589164516, "train/loss": 2.710497558116913, "train/grad": 0.11770975984632968, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.124935302734375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.12408447265625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.12254150390625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.121102294921875, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.1194921875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.11720458984375, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.114150390625, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.109683837890625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.100009765625, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.0798846435546876, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.0450628662109374, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.9810858154296875, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.9285369873046876, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.8690887451171876, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.8224723815917967, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.7843113708496094, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.743006820678711, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.702598876953125, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.665246887207031, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.6365494918823242, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.5986097717285155, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.5566709899902342, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.5238846588134765, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.4977002334594727, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.4762718200683596, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.4541815185546874, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.433215675354004, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.418957872390747, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.40570348739624, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.394961109161377, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.3845816802978517, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.3790762186050416, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.3735738372802735, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.368862690925598, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.3612496519088744, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.360151586532593, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.3629562711715697, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.3665200233459474, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.3846947145462036, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.3996288442611693, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.4223532485961914, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.443873333930969, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.462765026092529, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.480420165061951, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.5049693298339846, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.00905592917231843, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.00905971580883488, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.009065643914509565, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.00907163759926334, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.009077858568634838, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.009088589609600604, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.009106403507757932, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.009142973388079553, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.009268015639390796, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.009667001133784651, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.010524628758430481, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.01197182469535619, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.012772354930639267, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.013361065359786152, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.013739350088872015, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.014077140460722148, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.014506589248776436, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.015026955385692417, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.015636471030302346, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.01621600926388055, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.016934861093759537, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.017990575484000147, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.01884369446430355, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.01945441816933453, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.019858119506388903, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.02017317734658718, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.020366275659762324, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0204711750568822, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.020636291545815765, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.02079206021036953, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.020748125645332037, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.020538802752271296, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.02045521707739681, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.02035686092451215, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.020266268104314804, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.02041020714212209, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.02075413222424686, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.021211011363193394, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.021455259546637535, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.022135932352393865, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.022721592132002116, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.023177153132855892, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.02353378478437662, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.023962865080684424, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.024507094230502843, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.119706869125366, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.119157314300537, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1181442737579346, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.117136001586914, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1159913539886475, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.114161491394043, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.111438751220703, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1069161891937256, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.0959067344665527, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.0709030628204346, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.028687000274658, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.958953857421875, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.9064223766326904, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.8497819900512695, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.8076701164245605, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.774688482284546, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.73994779586792, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.70652174949646, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.677973985671997, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.658148765563965, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.6353769302368164, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.6135752201080322, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.596970796585083, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.58450984954834, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.574504852294922, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.5678908824920654, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.5669476985931396, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.5754897594451904, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.5874481201171875, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.598628044128418, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.6078548431396484, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.606096029281616, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.6151106357574463, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.624197006225586, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.625856637954712, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.6328330039978027, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.642251491546631, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.656128406524658, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.6658735275268555, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.660773754119873, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.6432125568389893, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.678473711013794, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.668910503387451, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.649871826171875, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.634275436401367, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06404577334809892, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06496862310815799, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06589147286821706, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.07069029162052418, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.08213362864525656, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.10428202288667406, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.12532299741602068, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.14082687338501293, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.15485418973791068, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.16205241786637137, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.16795865633074936, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.17331118493909192, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.18383167220376523, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.19435215946843853, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.20062753783684018, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.20524178663713546, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.2059800664451827, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.21133259505352528, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.21373200442967885, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.21631598375784422, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.22129937246216316, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.22148394241417496, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.2233296419342931, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.2222222222222222, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.21926910299003322, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.21686969361387967, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.21760797342192692, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.21816168327796234, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.2188999630860096, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.21779254337393872, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.21410114433370248, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.21483942414174972, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.2159468438538206, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.21520856404577335, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.21225544481358435, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.21613141380583242, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.22296050203026946, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.21963824289405684, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.22148394241417496, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.22314507198228128, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.22535991140642303, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.005175324069493736, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.005624645207466454, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.005845769820774671, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.006840293522690363, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.007496546413167648, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.00827822463807433, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.009927790987551607, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.015223462297558993, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.026627684557531575, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.045798770540458916, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.05882472883126481, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.06800922059179935, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.07896613983860243, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.08762909829568573, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.09412008952050548, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.10006764337511748, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.11249187786217234, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.12328242535845473, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.1309033391224735, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.13703740378624465, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.1375260585760698, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.14261549463895518, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.1469457703932098, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.15198262146286012, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.15846455931894038, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.15879124258584315, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.16169954903258155, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.16155418851094228, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.1601615571431916, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.1594531138375828, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.16111567161991083, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.1621010382967986, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.16237197949885154, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.15967093112534103, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.158261823142918, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.15856307115120327, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.16063584215802237, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.1602926185526136, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.15872178352776048, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.15798230999079815, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.15945941855502463, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.1513319311993081, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.15341670954159084, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.1491173654322333, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.157983111881025, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 44, "lr_best": 0.0078, "wd_best": 0.05, "train/loss_best": 2.5049693298339846, "validation/loss_best": 2.634275436401367, "validation/acc_best": 0.22535991140642303, "validation/f1_best": 0.157983111881025} +{"epoch": 12, "train/lr": 0.0001499999999999999, "train/loss": 2.693382966518402, "train/grad": 0.1170564016327262, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.12315185546875, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.122139892578125, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.120457763671875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.1187451171875, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.116944580078125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.114197998046875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.110537109375, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.104798583984375, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.09200439453125, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.064622802734375, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.0220452880859376, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.956558837890625, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.9066944885253907, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.8495051574707033, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.804093780517578, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.7664418029785156, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.725423583984375, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.685130958557129, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.6479835891723633, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.6199636268615722, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.5788536643981934, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.538115768432617, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.5060679435729982, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.4806528091430664, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.460345115661621, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.4379674339294435, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.4159312629699707, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.4005165672302247, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.3850274801254274, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.3730021381378172, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.361114206314087, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.357262885570526, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.353850917816162, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.3500412797927854, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.3437345314025877, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.344319689273834, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.3477360367774964, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.348410828113556, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.362018928527832, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.367407956123352, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.3893241930007934, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.40373366355896, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.420960555076599, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.4345628786087037, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.455868196487427, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.009005270735360681, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.009006927255541086, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.009009378633927555, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.009013007779140025, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.009017700625117869, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.009028299907222391, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.009048528510611505, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.009097264532465487, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.009282784850802273, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.009863226495217531, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.010887380710337312, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.012201100592501462, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.012856500064954162, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.013370853955857456, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.013726516915485263, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.014041325743310153, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.0144413596438244, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.014943747767247259, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.01556378132198006, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.016176766552962362, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.017041346821933985, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.01796522317454219, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.018639346873387693, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.019175910940393805, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.019614928090013563, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.019966132752597333, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.020153168789111078, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.020212390921078623, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.02028972185216844, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.020385059383697807, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.020429940521717073, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.020288786543533208, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.020431233900599182, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.020511095011606813, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.020678104469552636, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.021023607077077032, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.021291705686599015, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.021626841416582464, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.02173126757144928, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.02244214529171586, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.022592581836506725, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.02270750845782459, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.023063923241570593, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0232206164021045, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.023447168301790954, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1195132732391357, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.118896484375, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.117830514907837, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1166627407073975, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1153836250305176, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1132524013519287, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1099355220794678, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1042139530181885, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.089550256729126, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.0567538738250732, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.0078985691070557, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.938602924346924, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.8883731365203857, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.832899332046509, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.790562391281128, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.7569034099578857, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.7218403816223145, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.6890554428100586, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.6605000495910645, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.6399006843566895, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.613409996032715, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.5918686389923096, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.5793213844299316, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.5760622024536133, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.5801570415496826, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.5882151126861572, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.590871810913086, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.5942089557647705, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.594677448272705, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.601386547088623, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.6097450256347656, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.6112825870513916, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.6189916133880615, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.618858814239502, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.6317994594573975, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.628797769546509, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.627758026123047, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.629042863845825, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.620102643966675, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.6006476879119873, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.602296829223633, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.607982873916626, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.6057369709014893, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.6327695846557617, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.623581647872925, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06441491325212255, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06829088224437062, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.08545588778146918, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.10834256183093392, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.12753783684016243, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.1435954226651901, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.15503875968992248, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.16500553709856036, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.17534145441122184, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.18456995201181248, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.18973791066814322, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.19878183831672203, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.20431893687707642, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.20967146548541898, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.21391657438169065, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.2172388335179033, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.2220376522702104, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.22277593207825766, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.22148394241417496, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.2157622739018088, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.22111480251015134, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.22425249169435216, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.2249907715023994, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.22609819121447028, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.22535991140642303, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.22554448135843486, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.22757475083056478, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.23034330011074197, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.2279438907345884, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.2294204503506829, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.23089700996677742, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.23311184939091917, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.23052787006275377, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.23089700996677742, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.23403469915097821, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.23181985972683647, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.22849760059062385, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.22572905131044665, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.22720561092654115, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.005180256509568494, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.005168153987193443, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.005377723321974194, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.00538101488095609, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.005357434919273253, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.005859867155323326, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.00732104535402403, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.013791355596316925, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.03198847128168696, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.049050554646882814, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.05924318201639297, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.07101949298918574, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.08118246029584276, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.09166388384789854, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.10080915429928557, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.1085134910505441, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.1146284577779304, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.1235959037515502, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.12932816803458894, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.13624574716301324, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.1410728236835218, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.1459482345567349, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.14995691853217308, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.15239683145341792, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.15390650243240797, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.15122546076504714, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.1564966080321424, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.16197799773088498, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.1622843752497668, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.16404430181465376, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.1616787516018698, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.1630546800610299, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.16639107819821494, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.1673881195024168, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.16528307737626263, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.16664150366751543, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.16569626868086454, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.1694462887992875, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.16688950499898936, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.17110284807848278, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.17762749247564624, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.17309727507803482, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.16959086960766612, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.16203541645533445, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.16731003419195487, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 40, "lr_best": 0.0042, "wd_best": 0.05, "train/loss_best": 2.3893241930007934, "validation/loss_best": 2.602296829223633, "validation/acc_best": 0.23403469915097821, "validation/f1_best": 0.17762749247564624} +{"epoch": 13, "train/lr": 0.00011886002410835478, "train/loss": 2.6653527760505678, "train/grad": 0.11639218855649233, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.119610595703125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.118551025390625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.1168798828125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.11506591796875, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.1131591796875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.11024169921875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.106204833984375, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.099659423828125, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.083994140625, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.0512469482421873, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.005308837890625, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.9410052490234375, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.892194366455078, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.8347398376464845, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.7886088562011717, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.7504766845703124, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.7090214538574218, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.6686331176757814, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.631490478515625, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.60322940826416, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.5597328186035155, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.52047155380249, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.4893351936340333, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.463705759048462, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.442327537536621, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.419174633026123, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.396197347640991, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.3788391399383544, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.3604602003097535, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.344231548309326, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.3296411776542665, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.321930401325226, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.3125758957862854, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.30357501745224, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.289955248832703, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.280040855407715, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.275616958141327, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.2743769001960756, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.2874732923507692, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.2958125686645507, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.312105445861816, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.324789590835571, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.340409746170044, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.3573542261123657, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.3753340005874635, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.009075928847305476, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.009078360779676586, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.009083308619447053, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.00908879837486893, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.009095645763445646, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.009108836757950484, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.009136038308497518, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.009203591551631689, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.009463208883535117, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.01022275453666225, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.011346833612769842, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.01256831010337919, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.01315637595951557, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.013634212287142873, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.013971736836247146, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.014272020384669303, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.014658444514498114, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.01514648064505309, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.015760045829229057, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.016333433724939825, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.017219089358113705, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.01819066050928086, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.018935504788532852, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.019518816345371306, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.019963096366263925, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.020316992648877204, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.020505595370195806, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.020506051257252692, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.020545163764618336, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.02062456392683089, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.020642967028543353, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0204368881508708, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.02039013771805912, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.02032884897198528, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.02044027272146195, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.02072111295070499, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.02092001617886126, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.021298888428136705, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.021219370914623142, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.02200698903761804, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.022042430499568583, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.021951993480324745, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.02194145869463682, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.021880243541672825, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.021564058512449264, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.119192123413086, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.118483543395996, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1173014640808105, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1160237789154053, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1145718097686768, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1121175289154053, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.108306407928467, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.101412057876587, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.08337664604187, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.044264793395996, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.992002487182617, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.924257755279541, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.875887632369995, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.8221285343170166, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.781233310699463, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.7487969398498535, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.715043783187866, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.6837499141693115, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.6571078300476074, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.6384477615356445, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.6106626987457275, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.588921546936035, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.5734379291534424, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.563732624053955, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.5591537952423096, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.5558712482452393, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.549318313598633, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.54451584815979, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.5380303859710693, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.5370285511016846, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.5415005683898926, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.5466601848602295, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.5535435676574707, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.555690050125122, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.5661184787750244, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.571129083633423, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.5870368480682373, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.597270965576172, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.6160354614257812, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.632056474685669, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.634488344192505, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.6248362064361572, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.6153650283813477, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.6287505626678467, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.616262197494507, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06423034330011074, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.0651531930601698, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.0695828719084533, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.07345884090070137, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.08028792912513842, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.10151347360649686, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.12532299741602068, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.1345514950166113, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.14802510151347362, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.15596160944998155, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.1672203765227021, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.17792543373938724, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.1877076411960133, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.1934293097083795, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.1998892580287929, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.20302694721299372, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.2070874861572536, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.2131782945736434, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.2207456626061277, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.2248062015503876, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.22702104097452935, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.2277593207825766, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.2336655592469546, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.2355112587670727, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.2368032484311554, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.23901808785529716, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.2369878183831672, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.23754152823920266, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.23477297895902546, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.2369878183831672, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.23735695828719083, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.23588039867109634, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.24067921742340348, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.2349575489110373, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.2334809892949428, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.2277593207825766, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.23181985972683647, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.22831303063861202, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.23052787006275377, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.23089700996677742, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.22314507198228128, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.2248062015503876, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.005362466000718931, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.00586602914697435, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.0063472046295027645, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.007174290090927438, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.007977525215253462, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.01079675028881244, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.013945900061557742, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.020256789386749064, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.04190604010846009, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.058010711222940665, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.06349643340064576, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.07349605515654284, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.0808756115523264, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.09166688348847966, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.10208900130131908, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.11128170388398706, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.11678746762723409, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.12487798736046418, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.13032501084072481, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.13495904723556343, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.14149303195348048, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.14915766165245561, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.15507669915879832, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.15688472431545483, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.1582531678996426, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.16393336805083822, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.16641220860959957, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.16754763387084573, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.17156431912519643, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.1718839652963676, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.1743988203979686, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.1704058324140054, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.173117963300312, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.17119985379076472, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.17486871550901964, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.1764861632258313, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.1680867998808341, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.16478682085694069, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.15825785046974486, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.16185407518534076, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.15794019553366773, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.16087649950407054, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.16322709940405203, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.15704661753055213, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.15853512875620915, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 35, "lr_best": 0.0018, "wd_best": 0.05, "train/loss_best": 2.280040855407715, "validation/loss_best": 2.571129083633423, "validation/acc_best": 0.24067921742340348, "validation/f1_best": 0.1764861632258313} +{"epoch": 14, "train/lr": 8.9081919031238e-05, "train/loss": 2.6590712738037108, "train/grad": 0.11753673382103443, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.119676513671875, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.118544921875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.116671142578125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.11478271484375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.112838134765625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.109744873046875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.10515869140625, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.09765869140625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.079189453125, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.0413531494140624, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.993299865722656, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.931161193847656, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.8845620727539063, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.8293255615234374, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.7847866821289062, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.7478033447265626, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.707815704345703, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.66882438659668, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.6331936645507814, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.605582580566406, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.560421142578125, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.5223279762268067, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.4914959716796874, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.4653753089904784, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.443163366317749, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.4179525566101074, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.394032382965088, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.376603298187256, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.3586212825775146, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.342359809875488, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.3265777349472048, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.317146592140198, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.3064917516708374, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.296101441383362, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.2797340106964112, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.265349795818329, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.260030596256256, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.255833373069763, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.2674481964111326, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.2661499691009523, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.2869174551963805, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.3023531007766724, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.3124077892303467, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.330992479324341, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.359134323596954, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.009146215450018645, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.009148229707498103, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.009152453369461, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.009158389535732567, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.00916534909280017, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.009180841005872934, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.009213827135972678, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.009298930238001048, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.009625097890384494, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.010512003977783024, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.011659267381764949, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.012789384704083204, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.013339400351978838, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.013817673861049116, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.014175123935565352, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.014498462826013565, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.014917952949181199, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.01544356637634337, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.01608936474658549, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.01666776870843023, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.017643816340714692, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.018582320753484965, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.019302669246681035, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.019819596116431058, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.020162902306765318, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.020404118560254574, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.02055169656407088, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.020607628687284888, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.020666993325576186, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.020705138491466643, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.020684860139153896, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.02046515797264874, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.020407366775907577, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.020355901587754487, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.020633036615327, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.020871306108310818, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.021098395949229597, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.02147609678097069, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.021526176007464527, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.022211171267554165, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.022241081725805998, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.02219681130722165, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.022078327629715205, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.02207675966434181, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.02190062252804637, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.118906259536743, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.118177652359009, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1169028282165527, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1155292987823486, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1139988899230957, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1113569736480713, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1071157455444336, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.0993282794952393, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.0785367488861084, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.0349771976470947, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.9812166690826416, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.915118932723999, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.868072032928467, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.8155953884124756, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.7759811878204346, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.744898796081543, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.712998390197754, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.68346905708313, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.6581413745880127, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.6403403282165527, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.6136538982391357, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.592315196990967, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.5762908458709717, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.5656936168670654, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.5595896244049072, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.5560171604156494, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.5537350177764893, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.5551247596740723, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.5555479526519775, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.5573551654815674, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.5612828731536865, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.5628175735473633, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.5703017711639404, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.574213981628418, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.5922138690948486, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.60491943359375, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.6171109676361084, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.6210434436798096, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.6210274696350098, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.612295627593994, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.602684497833252, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.5913898944854736, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.582085371017456, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.5825064182281494, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.5901758670806885, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06404577334809892, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.0651531930601698, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06718346253229975, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.07364341085271318, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.09357696566998892, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.11646363971945367, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.13362864525655224, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.14747139165743817, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.15780730897009967, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.1640826873385013, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.1731266149870801, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.18512366186784793, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.1921373200442968, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.19619785898855666, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.20358065706902917, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.20634920634920634, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.21225544481358435, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.21502399409376152, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.2207456626061277, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.2248062015503876, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.22812846068660023, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.23126614987080105, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.23588039867109634, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.23661867847914358, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.2368032484311554, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.23588039867109634, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.23735695828719083, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.23717238833517904, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.2334809892949428, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.23717238833517904, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.23403469915097821, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.2369878183831672, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.2292358803986711, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.23237356958287192, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.22757475083056478, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.23126614987080105, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.23237356958287192, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.23126614987080105, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.23421926910299004, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.23126614987080105, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.23034330011074197, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.005389906657845656, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.005377100070755487, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.005529780209301772, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.006014832683949194, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.0065104756658553265, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.00854833880307594, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.01130082126360757, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.01757486372776581, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.03849120759297205, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.053670864902539896, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.06254599586788134, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.07298086832646622, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.08249555821508271, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.09047883767514597, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.09823470153239332, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.11004910783933684, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.11780529938138755, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.12347899061391432, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.13039967830341734, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.1337093435636272, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.14111545282836108, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.14446796526311823, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.1511246914363274, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.15499817623247739, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.1594429070433469, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.16129028791394395, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.1666329885358714, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.16702276508292047, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.164617861814059, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.1643638669809165, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.1649587107535844, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.1656777103448748, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.16295248141981614, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.16723157209964146, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.1654941422710481, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.17130193007558767, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.16455193896796597, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.16897235277195724, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.16693600812757112, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.17390407195138366, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.17269932511793748, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.1724448196331505, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.17913040760941254, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.17440119798388873, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.17015980932353322, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 30, "lr_best": 0.00081, "wd_best": 0.05, "train/loss_best": 2.3265777349472048, "validation/loss_best": 2.5612828731536865, "validation/acc_best": 0.23735695828719083, "validation/f1_best": 0.1649587107535844} +{"epoch": 15, "train/lr": 6.196799573888289e-05, "train/loss": 2.638514312505722, "train/grad": 0.11475444976240397, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.12189208984375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.120731201171875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.118880615234375, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.11691162109375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.114879150390625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.111510009765625, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.106680908203125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.098336181640625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.0776153564453126, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.03593017578125, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.985625915527344, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.922288818359375, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.8747076416015624, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.818403472900391, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.773129577636719, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.735947570800781, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.696134719848633, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.6573596954345704, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.621779327392578, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.594284019470215, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.5480590629577637, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.51116491317749, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.4802912616729738, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.4535437202453614, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.430364646911621, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.4044707918167116, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.3792418813705445, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.3604048204422, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.340541081428528, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.3216902875900267, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.302709176540375, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.2914639842510223, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.2763403284549715, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.2620104718208314, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.24027642250061, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.223184220790863, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.2096996891498564, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.199171543121338, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.2078661131858826, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.202639706134796, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.2192069411277773, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.232538239955902, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.244486999511719, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.26228057384491, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.2930287671089173, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.008955603421200067, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.00895920328097418, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.008965869720559566, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.008973130893427878, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.008981831166893243, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.009001114449929445, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.00903970655053854, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.009139378112740815, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.009517678131815047, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.010485449463594705, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.011624883031472563, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.012680185129866003, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.013191489288583397, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.013635869501158596, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.013968929736874998, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.014266379363834857, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.014652447160333395, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.015145046841353179, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.015750038726255296, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.01626543666701764, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.017144998470321297, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.01796412403229624, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.01862052467651665, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.01911427970044315, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.019467913657426835, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.01972908389288932, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.019917400465346874, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.01995924972463399, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.020072462214156987, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.020154571104794742, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.020171433463692667, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.020020092399790884, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.02005543346516788, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.02013503830879927, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.020493465857580304, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.020902286227792503, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.02107143954373896, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.021297974865883588, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.02113673083484173, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.021797391455620527, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.021715031871572137, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.021553907990455628, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0213363307248801, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.02102861081250012, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.020482644913718106, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1188271045684814, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1181225776672363, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1168432235717773, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1154017448425293, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.113818645477295, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.11106276512146, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.106555938720703, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.0980701446533203, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.0752220153808594, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.0286295413970947, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.974165678024292, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.9091084003448486, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.8626294136047363, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.810397148132324, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.770582437515259, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.7394089698791504, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.7071526050567627, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.6772751808166504, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.6518936157226562, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.633695602416992, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.6061482429504395, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.585688352584839, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.5700573921203613, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.558648109436035, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.5512993335723877, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.5453107357025146, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.540125846862793, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.538118362426758, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.5343873500823975, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.5339083671569824, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.5370399951934814, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.540891170501709, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.5519473552703857, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.560029983520508, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.5838756561279297, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.5970277786254883, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.6126115322113037, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.617971897125244, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.625643730163574, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.6390349864959717, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.631598472595215, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.6258366107940674, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.6154046058654785, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.6070804595947266, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.6063404083251953, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.0651531930601698, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06662975267626431, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.07345884090070137, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.09634551495016612, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.12089331856773718, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.13750461424880028, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.14839424141749724, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.15854558877814692, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.16832779623477298, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.17829457364341086, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.18272425249169436, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.19287559985234404, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.19896640826873385, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.20524178663713546, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.20782576596530086, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.21539313399778517, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.22277593207825766, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.2294204503506829, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.2336655592469546, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.23477297895902546, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.2355112587670727, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.2369878183831672, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.23901808785529716, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.24012550756736803, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.23938722775932078, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.23772609819121446, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.23994093761535623, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.23994093761535623, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.24049464747139165, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.23920265780730898, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.23809523809523808, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.23661867847914358, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.23569582871908454, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.22886674049464747, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.22868217054263565, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.22665190107050573, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.22978959025470652, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.2294204503506829, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.2294204503506829, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.23145071982281284, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.00537673104071846, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.005377157487157847, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.005367833846913659, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.005366514178879665, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.006102305489004048, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.008247078241937685, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.01092617388389252, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.017394191868215215, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.04074934586367467, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.05574839893686209, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.06468550318646346, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.0752504761228613, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.0830930701046136, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.09357163179088679, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.10548892206419426, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.10991802822338399, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.11953760092880289, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.12630805397520725, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.13332746480060265, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.13633565278567558, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.14393702110831283, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.15130748344714748, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.1575586650840013, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.16359613343236049, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.16620557299292124, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.16876561524147707, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.1709061442594134, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.17317184720570752, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.17572262962855825, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.17553151097234854, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.1751071188945419, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.17572135083818366, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.17726396775493636, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.17732411586935415, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.1761908416093866, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.17450294961293353, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.1720440317035338, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.17465717503395276, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.1703590337725193, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.1688132261563197, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.16384553312631941, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.16640146572146206, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.167556095232404, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.165092438456425, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.1630612349327135, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 33, "lr_best": 0.00129, "wd_best": 0.05, "train/loss_best": 2.2620104718208314, "validation/loss_best": 2.560029983520508, "validation/acc_best": 0.24049464747139165, "validation/f1_best": 0.17732411586935415} +{"epoch": 16, "train/lr": 3.870405029380728e-05, "train/loss": 2.6239572489261627, "train/grad": 0.11390130672603846, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.124581298828125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.12340087890625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.1214501953125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.119569091796875, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.1175, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.114149169921875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.1090625, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.100408935546875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.078443603515625, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.0352886962890624, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.98527099609375, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.9234182739257815, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.876188201904297, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.819593963623047, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.7738795471191406, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.73626823425293, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.695622329711914, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.6560659790039063, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.6198250961303713, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.591652374267578, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.5428904151916503, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.505537176132202, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.4741251182556154, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.446431140899658, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.422497243881226, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.3951560115814208, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.3689449787139893, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.3496081399917603, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.327062544822693, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.3058920192718504, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.2847964334487916, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.2710192441940307, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.2530240058898925, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.2352069759368898, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.2096876811981203, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.184373278617859, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.169512987136841, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.1539930534362792, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.1578149247169494, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.1414092898368837, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.158221409320831, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.1725597262382506, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.1869917845726015, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.2072385537624357, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.2407745003700255, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.009013810437172651, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.009017373216338456, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.009024247012566775, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.009032299455720932, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.009042046561371536, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.009061743228230626, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.009103317584376783, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.009212369546294213, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.009625777639448642, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.010646939391735942, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.011788828331045807, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.012815196514129639, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.013321054023690522, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.013776588523760437, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.014126577256247401, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.014441381976939737, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.014852685956284403, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.015372629221528768, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.01599879707209766, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.016518820440396667, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.01742673742584884, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.018200369607657193, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.01882084534969181, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.01930190689396113, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.019636441920883953, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.019894899004139006, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.02004370083566755, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.020107480981387198, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.020175386392511426, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.020192129649221898, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.020140196438878776, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.019903194946236907, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.019800557168200613, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.019723107288591564, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.019941399870440364, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.020239813039079308, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.020342031959444284, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.020576748065650463, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.02048174207098782, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.021117620253935456, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.021004523243755104, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.020988047234714032, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.020866555105894805, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.020575897386297583, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.02006930316798389, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.118730068206787, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1179561614990234, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1166441440582275, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1152007579803467, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1135306358337402, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.110649585723877, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1059179306030273, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.0969457626342773, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.072688102722168, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.0241425037384033, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.969174385070801, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.9044137001037598, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.8580026626586914, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.805684804916382, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.765761375427246, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.7344071865081787, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.7021639347076416, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.672484874725342, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.6470232009887695, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.628624200820923, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.5995612144470215, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.578272581100464, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.562211513519287, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.550692081451416, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.5430970191955566, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.536860466003418, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.531989812850952, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.5304408073425293, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.5302066802978516, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.534322500228882, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.5403542518615723, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.543721914291382, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.5518863201141357, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.5532238483428955, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.5624923706054688, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.5727386474609375, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.5831336975097656, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.5863378047943115, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.585319757461548, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.5889577865600586, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.5833852291107178, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.5792267322540283, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.566807746887207, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.5665814876556396, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.557758331298828, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06404577334809892, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06607604282022887, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06921373200442968, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.07807308970099668, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.10280546327057954, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.12643041712809155, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.14248800295311922, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.15337763012181616, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.16297526762643041, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.17349575489110372, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.18124769287559986, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.19010705057216684, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.19730527870062753, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.20284237726098192, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.2074566260612772, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.2115171650055371, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.21483942414174972, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.22388335179032853, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.22905131044665927, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.23255813953488372, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.2349575489110373, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.2364341085271318, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.24086378737541528, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.2427094868955334, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.2425249169435216, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.24067921742340348, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.2397563676633444, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.24160206718346253, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.23994093761535623, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.24012550756736803, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.2425249169435216, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.24086378737541528, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.23846437799926173, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.2353266888150609, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.2364341085271318, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.2353266888150609, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.24012550756736803, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.24031007751937986, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.23772609819121446, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.23717238833517904, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.2364341085271318, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.005376591273026705, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.005364162444146162, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.0053600804111523246, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.00561835475740529, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.0069157473885946, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.009872298895674973, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.013200807259343467, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.021018203216008922, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.04477721794323635, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.05827837833505315, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.06771730948028128, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.07842128134686278, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.08694918444807558, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.09671222574568779, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.10514509592803412, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.11453099168593994, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.12320066368911536, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.13034295015193506, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.13465869947834022, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.13885565381670387, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.14294131587846629, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.15242360781553946, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.157665945349851, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.16254099412943226, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.16534098535411873, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.1670943354310893, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.172658587118549, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.17531293933172978, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.1759726725049947, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.1741704215192764, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.17627604683112733, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.17867988598081228, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.17927436550600903, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.1813582223760668, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.18628945273499795, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.1867235835913703, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.1847633253899157, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.1839481650525984, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.18631354035622819, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.18750864516922994, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.19257318322001646, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.1936112686029983, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.18969304106608534, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.1874894290423232, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.1872354272001876, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 27, "lr_best": 0.00047999999999999996, "wd_best": 0.05, "train/loss_best": 2.3496081399917603, "validation/loss_best": 2.5304408073425293, "validation/acc_best": 0.2427094868955334, "validation/f1_best": 0.17531293933172978} +{"epoch": 17, "train/lr": 2.030750443206766e-05, "train/loss": 2.6082524883747102, "train/grad": 0.11363770663738251, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.125382080078125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.124268798828125, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.122425537109375, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.12033203125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.11826171875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.114622802734375, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.109404296875, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.100177001953125, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.07703857421875, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.0321099853515623, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.9816180419921876, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.9198782348632815, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.8727259826660156, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.8160694885253905, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.770115966796875, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.7319495391845705, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.690552978515625, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.6500052642822265, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.6128459548950196, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.5837403106689454, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.533133544921875, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.4945923614501955, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.462305088043213, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.434270324707031, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.4098386859893797, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.38116774559021, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.3551123046875, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.334719944000244, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.31082426071167, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.287522888183594, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.2662871217727663, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.252562484741211, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.234504179954529, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.213668031692505, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.186888625621796, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.1580114006996154, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.141472866535187, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.120355987548828, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.121649978160858, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.0919767487049103, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.1021016454696655, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.1100000166893005, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.1226934933662416, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.140212950706482, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.1774771428108215, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.009003884010016918, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.009006731377448887, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.009012329757679254, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.009018992695491761, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.009027615927625448, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.009046116401441396, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.009087793331127613, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.0092003960814327, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.009634390270803124, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.010687807365320623, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.011833660160191358, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.01284737592563033, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.013348222449421883, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.013804138326086103, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.014153576861135662, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.01446711253374815, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.014866770720109343, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.015368188093416392, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.015972600914537907, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.016468234341591597, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.017364068976603447, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.01817556058987975, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.018808505083434283, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.01927636326290667, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.019585575554519893, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.019807734256610275, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.019903847286477684, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.01992733784019947, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.01998337154276669, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.02000193713698536, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.019963057776913047, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.01971224825363606, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.019643932608887554, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.01961462183855474, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.01987376467324793, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.020212358571588995, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.020352391554042698, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.02064134337939322, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.020537347877398134, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.021169004859402776, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.021082165408879517, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.021034467872232197, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.02091753893531859, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.020613326793536543, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.020052950493991376, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1186885833740234, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.117910385131836, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1165666580200195, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1151070594787598, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1134417057037354, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1105000972747803, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1056699752807617, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.096471071243286, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.071530342102051, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.02215838432312, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.967100143432617, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.9027726650238037, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.8566834926605225, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.804729700088501, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.765303373336792, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.734490156173706, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.7028141021728516, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.673924446105957, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.649334669113159, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.6317203044891357, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.6036596298217773, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.5831189155578613, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.5677151679992676, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.5566203594207764, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.5497055053710938, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.5447871685028076, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.540328025817871, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.53951358795166, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.539254903793335, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.5433430671691895, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.548816680908203, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.552659034729004, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.5603880882263184, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.562288999557495, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.576693058013916, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.584416151046753, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.597463846206665, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.604682445526123, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.6084587574005127, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.620224714279175, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.614598512649536, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.610003709793091, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.598083972930908, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.584231376647949, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.5724847316741943, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06423034330011074, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06589147286821706, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06939830195644149, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.07899593946105574, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.10428202288667406, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.12772240679217423, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.14101144333702473, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.15282392026578073, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.16057585825027684, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.17054263565891473, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.1792174234034699, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.18826135105204872, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.19509043927648578, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.1997046880767811, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.20339608711701734, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.2070874861572536, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.21373200442967885, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.2172388335179033, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.2248062015503876, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.23015873015873015, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.23237356958287192, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.23477297895902546, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.23717238833517904, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.23809523809523808, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.23661867847914358, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.2353266888150609, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.2364341085271318, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.23772609819121446, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.23809523809523808, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.23403469915097821, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.23754152823920266, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.2382798080472499, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.2368032484311554, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.23920265780730898, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.2353266888150609, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.2334809892949428, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.23569582871908454, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.23624953857511996, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.23606496862310816, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.2369878183831672, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.23403469915097821, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.005376368368999687, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.005363309066316585, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.005535790567637702, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.005851943055361242, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.006965065216611491, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.009425116245724662, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.013569502010090115, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.02244640787368926, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.04649754575050857, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.058884670409687916, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.06693568776731096, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.07825638118908214, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.08521343177831979, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.0952887968463415, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.10403404881114198, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.11340133582265323, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.12215076761480348, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.1271593875877942, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.13131215807182248, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.1349460564742764, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.14284446375821178, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.14753234729210682, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.1548912413961891, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.1613280950734997, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.1657414539886302, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.16904849285505733, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.1723411093224366, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.17524209054009413, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.1736692565135722, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.1744703454641486, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.17814871272282962, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.17880701739691132, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.18064178098110664, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.17712723463186864, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.1796968188963263, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.18229307415876828, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.18144414334386086, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.18619074120579146, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.17983417815395616, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.18252668625468704, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.18527129289165947, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.18635143087891426, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.18666713462090256, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.18713663134164005, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.18328262142765595, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 37, "lr_best": 0.00249, "wd_best": 0.05, "train/loss_best": 2.120355987548828, "validation/loss_best": 2.604682445526123, "validation/acc_best": 0.23920265780730898, "validation/f1_best": 0.18619074120579146} +{"epoch": 18, "train/lr": 7.5829098008590064e-06, "train/loss": 2.6035008931159975, "train/grad": 0.11394344441592694, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.12492919921875, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.123773193359375, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.121812744140625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.11974609375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.117576904296875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.114088134765625, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.108697509765625, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.099501953125, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.07609130859375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.03116943359375, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.980613098144531, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.919025573730469, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.8722760009765627, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.816328582763672, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.771278076171875, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.733850326538086, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.6934674072265623, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.653943634033203, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.6172798919677733, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.5881563568115236, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.536925277709961, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.497144355773926, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.4643187713623047, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.4361721801757814, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.4113852882385256, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.3830655002593994, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.3559889602661133, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.3350054168701173, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.3116076469421385, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.289035234451294, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.2665875911712647, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.2518590450286866, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.231865477561951, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.212121968269348, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.1791732835769655, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.148600654602051, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.123370862007141, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.1036358451843262, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.099925630092621, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.0712216210365297, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.07637930393219, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.0826737940311433, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.0863105773925783, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.104192259311676, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.1418750262260438, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.009107863320969046, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.009110827096737922, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.009115190638694912, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.009121499583125114, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.009129376525525004, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.009148055224213749, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.009190740096382797, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.009306620126590132, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.00975357161834836, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.010826793254818768, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.011977840822655707, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.012986795692704618, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.013482018210925161, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.01393737410660833, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.014293597904033959, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.01461692875251174, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.015035633738152683, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.015565908588469029, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.01619726142846048, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.016712832134217023, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.017648891136050223, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.018447833769023418, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.01906465906184167, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.019521817467175424, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.01981269020587206, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.02001057019457221, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.020072339549660683, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.020076998830772935, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.020096683562733232, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.020069208946079015, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.020011061551049352, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.019776579411700367, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.01966709743719548, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.019612931278534234, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.019814347270876168, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.020133869275450706, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.02027772302739322, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.020562712624669074, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.02036477850750089, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.02098189509473741, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.020867429850623013, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.020780270146206023, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.02066830487921834, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.02032840294763446, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.01980405770242214, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1186747550964355, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1179022789001465, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1165566444396973, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.115098714828491, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.113408088684082, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.110471487045288, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1055989265441895, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.096313714981079, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.071141004562378, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.0214595794677734, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.966341257095337, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.9021217823028564, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.8560941219329834, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.8041493892669678, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.7645792961120605, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.7335331439971924, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.7014946937561035, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.6718485355377197, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.646314859390259, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.6276662349700928, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.5983822345733643, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.5770180225372314, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.561062812805176, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.5498392581939697, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.542701244354248, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.537184715270996, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.5324182510375977, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.53139591217041, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.5304503440856934, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.533250093460083, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.537252187728882, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.5399680137634277, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.5460309982299805, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.5483169555664062, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.558950662612915, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.567744493484497, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.580171585083008, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.587008237838745, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.590233325958252, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.6001925468444824, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.5941085815429688, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.591745376586914, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.5857975482940674, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.579702377319336, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.5685105323791504, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06441491325212255, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06626061277224068, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06976744186046512, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.08047249907715023, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.1050203026947213, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.12809154669619785, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.14248800295311922, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.15356220007382798, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.16205241786637137, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.17035806570690293, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.18087855297157623, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.18973791066814322, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.19619785898855666, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.2009966777408638, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.20524178663713546, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.21188630490956073, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.21483942414174972, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.22296050203026946, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.23015873015873015, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.23385012919896642, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.2368032484311554, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.2412329272794389, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.23901808785529716, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.24160206718346253, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.23994093761535623, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.23772609819121446, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.24086378737541528, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.24197120708748615, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.24049464747139165, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.23883351790328536, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.2397563676633444, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.24307862679955702, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.24178663713547435, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.24086378737541528, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.23791066814322628, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.23754152823920266, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.23994093761535623, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.23920265780730898, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.23624953857511996, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.23864894795127353, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.2364341085271318, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.005376219339273816, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.005364325493018902, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.005523012552301255, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.006320927775486839, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.007505973436764621, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.009994847311318545, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.0137933049949699, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.023893798175121727, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.047087842481048775, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.05949486856182682, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.06824453912090221, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.07873230503749487, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.08662963042433636, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.09516700649755984, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.10531114581350347, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.11430957845349717, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.12240323555230864, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.12864394897953732, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.1332632240379351, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.13922314275484332, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.14388806184254685, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.15269295556206272, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.16065018654213947, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.16553240130166666, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.16895057259851232, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.1740126354186863, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.17477348531103876, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.17761147005291647, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.17739485002570463, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.1762674781442666, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.18192629936230595, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.18405457556277108, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.18406350304257468, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.18266704551475954, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.18421064139519983, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.18831923253416405, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.1885178283379989, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.18924483868117944, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.18719551395951473, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.18667732577267696, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.1897388538920659, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.190569538541155, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.185357678450216, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.18471894037579753, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.18311632868228048, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 35, "lr_best": 0.0018, "wd_best": 0.05, "train/loss_best": 2.148600654602051, "validation/loss_best": 2.567744493484497, "validation/acc_best": 0.24307862679955702, "validation/f1_best": 0.18831923253416405} +{"epoch": 19, "train/lr": 1.0867618231465446e-06, "train/loss": 2.590551141500473, "train/grad": 0.11076092381030321, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.120076904296875, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.118875732421875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.116856689453125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.11471923828125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.112642822265625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.10889404296875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.1034716796875, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.09412353515625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.0702142333984375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.0245953369140626, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.9737228393554687, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.9116436767578127, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.864182434082031, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.8069586181640624, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.760606536865234, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.722419204711914, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.6812001037597657, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.6408517456054685, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.603886833190918, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.5747929573059083, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.523933162689209, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.4855706214904787, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.4533141613006593, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.425194053649902, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.4004189777374267, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.3722661113739014, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.3451314306259157, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.322683172225952, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.2987813329696656, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.2750708150863646, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.2511224031448362, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.235469741821289, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.213633944988251, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.1927283072471617, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.1617255640029907, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.1286615753173828, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.105302882194519, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.081335353851318, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.0785424637794496, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.044799072742462, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.048434839248657, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.051517460346222, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.053251316547394, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.069289605617523, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.106595494747162, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.008814357570372522, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.008817308654543013, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.008821860512252897, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.008828863461967557, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.00883746170438826, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008856586455367505, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.00889957818435505, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.009016536341514439, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.009464411926455796, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.010529871741309762, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.011664660186506809, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.012658313876017927, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.013150082253850996, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.013600390804931521, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.013949641273356975, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.014264105041511356, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.014669562904164195, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.01517851899843663, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.015784685271792113, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.016275609084405004, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.017163948444649576, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.0179388814419508, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.018540214146487415, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.01897828446701169, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.019259875039570034, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.01945464627351612, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.019532650876790285, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.019520188416354358, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.019533824040554464, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.019468558966182173, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0194127562828362, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.01917305606417358, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.019059942085295916, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.018981406590901317, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.01924611528404057, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.019571101116016506, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.01971633263863623, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.019995869528502228, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.019835839523002507, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.020459946785122154, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.020358474040403963, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.02025751323439181, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.020115203950554134, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.019762081541121006, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0192179108876735, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1186788082122803, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.117913246154785, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1165614128112793, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.115098476409912, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.113416910171509, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.110469341278076, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1055917739868164, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.0962884426116943, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.0710742473602295, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.021348714828491, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.9662423133850098, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.902053117752075, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.8560569286346436, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.8041679859161377, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.7646422386169434, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.733583688735962, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.701625108718872, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.672119379043579, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.646615982055664, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.628059148788452, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.598918914794922, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.5775957107543945, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.5616369247436523, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.550309419631958, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.5432040691375732, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.537581205368042, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.532792329788208, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.5315301418304443, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.5302953720092773, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.5328407287597656, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.5369181632995605, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.539389133453369, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.5452520847320557, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.547653913497925, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.559419870376587, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.5683116912841797, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.581709861755371, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.58896803855896, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.5934207439422607, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.603109359741211, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.5977346897125244, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.5950496196746826, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.5891458988189697, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.580747365951538, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.572373867034912, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06441491325212255, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06607604282022887, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06995201181247693, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.08010335917312661, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.10465116279069768, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.12809154669619785, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.14230343300110743, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.15356220007382798, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.16168327796234774, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.17035806570690293, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.18087855297157623, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.18899963086009597, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.1967515688445921, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.2009966777408638, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.2059800664451827, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.2117017349575489, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.2146548541897379, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.2220376522702104, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.22849760059062385, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.23421926910299004, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.23661867847914358, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.2412329272794389, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.23938722775932078, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.2427094868955334, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.2410483573274271, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.23791066814322628, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.2410483573274271, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.24178663713547435, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.24049464747139165, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.24067921742340348, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.24197120708748615, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.24363233665559247, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.24178663713547435, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.2427094868955334, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.23846437799926173, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.23920265780730898, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.23901808785529716, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.23901808785529716, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.23735695828719083, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.2427094868955334, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.2412329272794389, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.0053761934007941934, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.00553615629854317, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.00552322421552446, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.006318939977993837, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.007505191125707456, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.009978075453630447, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.013820437543119722, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.02344954682342952, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.04690510491759761, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.059712891094816, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.06806560477600952, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.07867345671593938, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.08653589263951628, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.09516998806566135, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.10510347846128366, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.11421744514789295, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.1229898070404397, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.12888417491159943, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.13384088252126203, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.13908952992277776, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.14386291597374734, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.15212317268647702, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.1592145283247246, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.1648457264984022, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.16822404708111705, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.1735679670561604, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.17453531186364532, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.17864797011712752, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.17859142263984737, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.17652914471420958, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.18150535663296066, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.1831306696353369, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.18482704009201353, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.18475655517988612, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.18495901518057525, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.18654225620531506, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.18660956734479195, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.1907352983071422, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.18586534918021427, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.18598246915145075, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.18555646235529685, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.18738335014511612, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.18461083095815223, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.18819294509763992, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.18634508776723446, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 35, "lr_best": 0.0018, "wd_best": 0.05, "train/loss_best": 2.1286615753173828, "validation/loss_best": 2.5683116912841797, "validation/acc_best": 0.24363233665559247, "validation/f1_best": 0.18654225620531506} diff --git a/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__linear/config.yaml b/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__linear/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..d136767e587181197e4aea76570e539caca82b44 --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__linear/config.yaml @@ -0,0 +1,96 @@ +output_root: experiments/decoders/output +name_prefix: eval_probe +remote_root: null +notes: decoder ablations crossreg_reg4; eval v2 (nsd_cococlip reg linear) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +dataset_kwargs: {} +classifier_kwargs: + embed_dim: null + dropout: 0.0 + xavier_init: false + norm: false +lr_scale_grid: +- 0.02 +- 0.023 +- 0.028 +- 0.033 +- 0.038 +- 0.045 +- 0.053 +- 0.062 +- 0.074 +- 0.087 +- 0.1 +- 0.12 +- 0.14 +- 0.17 +- 0.2 +- 0.23 +- 0.27 +- 0.32 +- 0.38 +- 0.44 +- 0.52 +- 0.61 +- 0.72 +- 0.85 +- 1 +- 1.2 +- 1.4 +- 1.6 +- 1.9 +- 2.3 +- 2.7 +- 3.1 +- 3.7 +- 4.3 +- 5.1 +- 6 +- 7.1 +- 8.3 +- 9.8 +- 12 +- 14 +- 16 +- 19 +- 22 +- 26 +- 31 +- 36 +- 43 +- 50 +wd_scale_grid: +- 1.0 +num_workers: 8 +prefetch_factor: null +balanced_sampling: false +epochs: 20 +steps_per_epoch: 200 +batch_size: 64 +accum_iter: 2 +lr: 0.0003 +warmup_epochs: 5 +no_decay: false +weight_decay: 0.05 +clip_grad: 1.0 +metrics: +- acc +- f1 +cv_metric: acc +early_stopping: true +amp: true +device: cuda +seed: 4466 +debug: false +wandb: false +wandb_entity: null +wandb_project: fMRI-fm-eval +name: decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__linear +model: flat_mae +representation: reg +classifier: linear +dataset: nsd_cococlip +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__linear +remote_dir: null diff --git a/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__linear/eval_log.json b/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__linear/eval_log.json new file mode 100644 index 0000000000000000000000000000000000000000..97b37125a862d311bd7fcfa4a9eddf2aa225d924 --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__linear/eval_log.json @@ -0,0 +1 @@ +{"eval/epoch": 17, "eval/id_best": 46, "eval/lr_best": 0.010799999999999999, "eval/wd_best": 0.05, "eval/train/loss": 2.884960651397705, "eval/train/acc": 0.1619902271120809, "eval/train/acc_std": 0.0018654117186175058, "eval/train/f1": 0.11140099438325955, "eval/train/f1_std": 0.0016810265672069203, "eval/validation/loss": 3.0113778114318848, "eval/validation/acc": 0.11720191952750092, "eval/validation/acc_std": 0.003972473586468523, "eval/validation/f1": 0.07053102428076782, "eval/validation/f1_std": 0.003003913278708565, "eval/test/loss": 2.984748363494873, "eval/test/acc": 0.12857142857142856, "eval/test/acc_std": 0.003846686851689246, "eval/test/f1": 0.07192350773342551, "eval/test/f1_std": 0.002728447204730143, "eval/testid/loss": 3.0147416591644287, "eval/testid/acc": 0.11123963755542703, "eval/testid/acc_std": 0.004168915059094805, "eval/testid/f1": 0.07332820826621526, "eval/testid/f1_std": 0.0033676209932556136} diff --git a/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__linear/eval_log_best.json b/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__linear/eval_log_best.json new file mode 100644 index 0000000000000000000000000000000000000000..f52354445beaa8f94535f382b67ffd942ab179e5 --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__linear/eval_log_best.json @@ -0,0 +1 @@ +{"eval/best/epoch": 17, "eval/best/id_best": 46, "eval/best/lr_best": 0.010799999999999999, "eval/best/wd_best": 0.05, "eval/best/train/loss": 2.884960651397705, "eval/best/train/acc": 0.1619902271120809, "eval/best/train/acc_std": 0.0018654117186175058, "eval/best/train/f1": 0.11140099438325955, "eval/best/train/f1_std": 0.0016810265672069203, "eval/best/validation/loss": 3.0113778114318848, "eval/best/validation/acc": 0.11720191952750092, "eval/best/validation/acc_std": 0.003972473586468523, "eval/best/validation/f1": 0.07053102428076782, "eval/best/validation/f1_std": 0.003003913278708565, "eval/best/test/loss": 2.984748363494873, "eval/best/test/acc": 0.12857142857142856, "eval/best/test/acc_std": 0.003846686851689246, "eval/best/test/f1": 0.07192350773342551, "eval/best/test/f1_std": 0.002728447204730143, "eval/best/testid/loss": 3.0147416591644287, "eval/best/testid/acc": 0.11123963755542703, "eval/best/testid/acc_std": 0.004168915059094805, "eval/best/testid/f1": 0.07332820826621526, "eval/best/testid/f1_std": 0.0033676209932556136} diff --git a/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__linear/eval_log_last.json b/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__linear/eval_log_last.json new file mode 100644 index 0000000000000000000000000000000000000000..2f006202828c7137acf8b1df1f9519e0aa73b835 --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__linear/eval_log_last.json @@ -0,0 +1 @@ +{"eval/last/epoch": 19, "eval/last/id_best": 46, "eval/last/lr_best": 0.010799999999999999, "eval/last/wd_best": 0.05, "eval/last/train/loss": 2.881417751312256, "eval/last/train/acc": 0.16383416822889454, "eval/last/train/acc_std": 0.0018108540534624653, "eval/last/train/f1": 0.11114459026861535, "eval/last/train/f1_std": 0.0016137216074583165, "eval/last/validation/loss": 3.008491039276123, "eval/last/validation/acc": 0.11332595053525286, "eval/last/validation/acc_std": 0.0038385018910410073, "eval/last/validation/f1": 0.06515514316617416, "eval/last/validation/f1_std": 0.0028531902047225313, "eval/last/test/loss": 2.9828546047210693, "eval/last/test/acc": 0.12634508348794063, "eval/last/test/acc_std": 0.0037033371149801124, "eval/last/test/f1": 0.0667541335491005, "eval/last/test/f1_std": 0.0024866492211625246, "eval/last/testid/loss": 3.0120861530303955, "eval/last/testid/acc": 0.11008289955658376, "eval/last/testid/acc_std": 0.004107666883728585, "eval/last/testid/f1": 0.0694078910053913, "eval/last/testid/f1_std": 0.003269541864513907} diff --git a/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__linear/eval_table.csv b/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__linear/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..b1597977e72d7b20bc28fb096344e7edd496b562 --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__linear/eval_table.csv @@ -0,0 +1,5 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,reg,linear,nsd_cococlip,best,17,0.010799999999999999,0.05,46,"[36, 1.0]",train,2.884960651397705,0.1619902271120809,0.0018654117186175058,0.11140099438325955,0.0016810265672069203 +flat_mae,reg,linear,nsd_cococlip,best,17,0.010799999999999999,0.05,46,"[36, 1.0]",validation,3.0113778114318848,0.11720191952750092,0.003972473586468523,0.07053102428076782,0.003003913278708565 +flat_mae,reg,linear,nsd_cococlip,best,17,0.010799999999999999,0.05,46,"[36, 1.0]",test,2.984748363494873,0.12857142857142856,0.003846686851689246,0.07192350773342551,0.002728447204730143 +flat_mae,reg,linear,nsd_cococlip,best,17,0.010799999999999999,0.05,46,"[36, 1.0]",testid,3.0147416591644287,0.11123963755542703,0.004168915059094805,0.07332820826621526,0.0033676209932556136 diff --git a/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__linear/eval_table_best.csv b/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__linear/eval_table_best.csv new file mode 100644 index 0000000000000000000000000000000000000000..b1597977e72d7b20bc28fb096344e7edd496b562 --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__linear/eval_table_best.csv @@ -0,0 +1,5 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,reg,linear,nsd_cococlip,best,17,0.010799999999999999,0.05,46,"[36, 1.0]",train,2.884960651397705,0.1619902271120809,0.0018654117186175058,0.11140099438325955,0.0016810265672069203 +flat_mae,reg,linear,nsd_cococlip,best,17,0.010799999999999999,0.05,46,"[36, 1.0]",validation,3.0113778114318848,0.11720191952750092,0.003972473586468523,0.07053102428076782,0.003003913278708565 +flat_mae,reg,linear,nsd_cococlip,best,17,0.010799999999999999,0.05,46,"[36, 1.0]",test,2.984748363494873,0.12857142857142856,0.003846686851689246,0.07192350773342551,0.002728447204730143 +flat_mae,reg,linear,nsd_cococlip,best,17,0.010799999999999999,0.05,46,"[36, 1.0]",testid,3.0147416591644287,0.11123963755542703,0.004168915059094805,0.07332820826621526,0.0033676209932556136 diff --git a/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__linear/eval_table_last.csv b/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__linear/eval_table_last.csv new file mode 100644 index 0000000000000000000000000000000000000000..21c54917edc1202ee9462ba3a161e79b67e575b3 --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__linear/eval_table_last.csv @@ -0,0 +1,5 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,reg,linear,nsd_cococlip,last,19,0.010799999999999999,0.05,46,"[36, 1.0]",train,2.881417751312256,0.16383416822889454,0.0018108540534624653,0.11114459026861535,0.0016137216074583165 +flat_mae,reg,linear,nsd_cococlip,last,19,0.010799999999999999,0.05,46,"[36, 1.0]",validation,3.008491039276123,0.11332595053525286,0.0038385018910410073,0.06515514316617416,0.0028531902047225313 +flat_mae,reg,linear,nsd_cococlip,last,19,0.010799999999999999,0.05,46,"[36, 1.0]",test,2.9828546047210693,0.12634508348794063,0.0037033371149801124,0.0667541335491005,0.0024866492211625246 +flat_mae,reg,linear,nsd_cococlip,last,19,0.010799999999999999,0.05,46,"[36, 1.0]",testid,3.0120861530303955,0.11008289955658376,0.004107666883728585,0.0694078910053913,0.003269541864513907 diff --git a/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__linear/log.txt b/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__linear/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..45437d66be189215bb58ab03af7e93fc0924f653 --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__linear/log.txt @@ -0,0 +1,956 @@ +fMRI foundation model probe eval +version: 0.1.dev65+g4003a1397 +sha: 6c01b606db98add5848cecd23e5d599250c0bf86, status: clean, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-02-24 21:17:35 +config: +output_root: experiments/decoders/output +name_prefix: eval_probe +remote_root: null +notes: decoder ablations crossreg_reg4; eval v2 (nsd_cococlip reg linear) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +dataset_kwargs: {} +classifier_kwargs: + embed_dim: null + dropout: 0.0 + xavier_init: false + norm: false +lr_scale_grid: +- 0.02 +- 0.023 +- 0.028 +- 0.033 +- 0.038 +- 0.045 +- 0.053 +- 0.062 +- 0.074 +- 0.087 +- 0.1 +- 0.12 +- 0.14 +- 0.17 +- 0.2 +- 0.23 +- 0.27 +- 0.32 +- 0.38 +- 0.44 +- 0.52 +- 0.61 +- 0.72 +- 0.85 +- 1 +- 1.2 +- 1.4 +- 1.6 +- 1.9 +- 2.3 +- 2.7 +- 3.1 +- 3.7 +- 4.3 +- 5.1 +- 6 +- 7.1 +- 8.3 +- 9.8 +- 12 +- 14 +- 16 +- 19 +- 22 +- 26 +- 31 +- 36 +- 43 +- 50 +wd_scale_grid: +- 1.0 +num_workers: 8 +prefetch_factor: null +balanced_sampling: false +epochs: 20 +steps_per_epoch: 200 +batch_size: 64 +accum_iter: 2 +lr: 0.0003 +warmup_epochs: 5 +no_decay: false +weight_decay: 0.05 +clip_grad: 1.0 +metrics: +- acc +- f1 +cv_metric: acc +early_stopping: true +amp: true +device: cuda +seed: 4466 +debug: false +wandb: false +wandb_entity: null +wandb_project: fMRI-fm-eval +name: decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__linear +model: flat_mae +representation: reg +classifier: linear +dataset: nsd_cococlip +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__linear +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=False, reg_tokens=4, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: nsd_cococlip (flat) +train (n=32539): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'run', 'trial_id', 'nsd_id', 'category_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 32539 +}), + labels=[ 3 4 5 6 10 11 17 18 19 20 22 23 25 30 31 33 36 37 38 53 55 59 61 74], + counts=[1286 1180 1639 1868 834 824 1026 1042 913 1853 1503 2092 1001 1410 + 794 1241 1904 1872 2267 1428 889 904 1447 1322] +) + +validation (n=5418): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'run', 'trial_id', 'nsd_id', 'category_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 5418 +}), + labels=[ 3 4 5 6 10 11 17 18 19 20 22 23 25 30 31 33 36 37 38 53 55 59 61 74], + counts=[197 161 276 345 126 142 143 185 112 295 285 387 169 250 159 193 316 334 + 343 215 172 141 226 246] +) + +test (n=5390): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'run', 'trial_id', 'nsd_id', 'category_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 5390 +}), + labels=[ 3 4 5 6 10 11 17 18 19 20 22 23 25 30 31 33 36 37 38 53 55 59 61 74], + counts=[202 172 274 298 144 180 134 182 186 293 218 343 165 185 140 177 346 333 + 345 271 165 140 251 246] +) + +testid (n=5187): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'run', 'trial_id', 'nsd_id', 'category_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 5187 +}), + labels=[ 3 4 5 6 10 11 17 18 19 20 22 23 25 30 31 33 36 37 38 53 55 59 61 74], + counts=[197 159 267 273 123 153 175 184 139 310 215 386 153 230 118 192 330 306 + 349 223 143 127 249 186] +) + +running backbone on example batch to get embedding dim +embedding feature dim (reg): 768 +initializing sweep of classifier heads +classifiers: +ModuleList( + (0-48): 49 x LinearClassifier( + (linear): Linear(in_features=768, out_features=24, bias=True) + ) +) +classifier params (train): 0.9M (0.9M) +setting up optimizer +total batch size: 128 = 64 bs per gpu x 2 accum +lr: 3.00e-04 +full schedule: epochs = 20 (steps = 4000) (decay = True) +warmup: epochs = 5 (steps = 1000) +start training for 20 epochs +train: [0] [ 0/400] eta: 0:22:45 lr: nan time: 3.4125 data: 2.9879 max mem: 3915 +train: [0] [ 20/400] eta: 0:03:05 lr: 0.000003 loss: 3.1904 (3.1895) grad: 0.0837 (0.0850) time: 0.3433 data: 0.0054 max mem: 3957 +train: [0] [ 40/400] eta: 0:02:25 lr: 0.000006 loss: 3.1832 (3.1832) grad: 0.0809 (0.0810) time: 0.3155 data: 0.0039 max mem: 3957 +train: [0] [ 60/400] eta: 0:02:10 lr: 0.000009 loss: 3.1802 (3.1831) grad: 0.0782 (0.0811) time: 0.3453 data: 0.0036 max mem: 3957 +train: [0] [ 80/400] eta: 0:01:58 lr: 0.000012 loss: 3.1735 (3.1805) grad: 0.0829 (0.0817) time: 0.3275 data: 0.0043 max mem: 3957 +train: [0] [100/400] eta: 0:01:48 lr: 0.000015 loss: 3.1702 (3.1798) grad: 0.0829 (0.0821) time: 0.3214 data: 0.0046 max mem: 3957 +train: [0] [120/400] eta: 0:01:39 lr: 0.000018 loss: 3.1698 (3.1784) grad: 0.0804 (0.0818) time: 0.3266 data: 0.0042 max mem: 3957 +train: [0] [140/400] eta: 0:01:31 lr: 0.000021 loss: 3.1646 (3.1768) grad: 0.0807 (0.0818) time: 0.3360 data: 0.0038 max mem: 3957 +train: [0] [160/400] eta: 0:01:24 lr: 0.000024 loss: 3.1644 (3.1748) grad: 0.0812 (0.0819) time: 0.3316 data: 0.0041 max mem: 3957 +train: [0] [180/400] eta: 0:01:16 lr: 0.000027 loss: 3.1640 (3.1725) grad: 0.0825 (0.0815) time: 0.3317 data: 0.0042 max mem: 3957 +train: [0] [200/400] eta: 0:01:09 lr: 0.000030 loss: 3.1586 (3.1713) grad: 0.0770 (0.0812) time: 0.3213 data: 0.0040 max mem: 3957 +train: [0] [220/400] eta: 0:01:02 lr: 0.000033 loss: 3.1567 (3.1696) grad: 0.0759 (0.0810) time: 0.3437 data: 0.0042 max mem: 3957 +train: [0] [240/400] eta: 0:00:55 lr: 0.000036 loss: 3.1502 (3.1681) grad: 0.0759 (0.0808) time: 0.3470 data: 0.0041 max mem: 3957 +train: [0] [260/400] eta: 0:00:48 lr: 0.000039 loss: 3.1492 (3.1670) grad: 0.0763 (0.0808) time: 0.3385 data: 0.0040 max mem: 3957 +train: [0] [280/400] eta: 0:00:41 lr: 0.000042 loss: 3.1482 (3.1662) grad: 0.0794 (0.0808) time: 0.3214 data: 0.0040 max mem: 3957 +train: [0] [300/400] eta: 0:00:34 lr: 0.000045 loss: 3.1455 (3.1649) grad: 0.0793 (0.0807) time: 0.3387 data: 0.0041 max mem: 3957 +train: [0] [320/400] eta: 0:00:27 lr: 0.000048 loss: 3.1442 (3.1639) grad: 0.0799 (0.0807) time: 0.3575 data: 0.0044 max mem: 3957 +train: [0] [340/400] eta: 0:00:20 lr: 0.000051 loss: 3.1480 (3.1631) grad: 0.0796 (0.0804) time: 0.3207 data: 0.0042 max mem: 3957 +train: [0] [360/400] eta: 0:00:13 lr: 0.000054 loss: 3.1480 (3.1622) grad: 0.0753 (0.0802) time: 0.3201 data: 0.0044 max mem: 3957 +train: [0] [380/400] eta: 0:00:06 lr: 0.000057 loss: 3.1526 (3.1623) grad: 0.0806 (0.0804) time: 0.3244 data: 0.0042 max mem: 3957 +train: [0] [399/400] eta: 0:00:00 lr: 0.000060 loss: 3.1563 (3.1618) grad: 0.0807 (0.0804) time: 0.3222 data: 0.0041 max mem: 3957 +train: [0] Total time: 0:02:15 (0.3397 s / it) +train: [0] Summary: lr: 0.000060 loss: 3.1563 (3.1618) grad: 0.0807 (0.0804) +eval (validation): [0] [ 0/85] eta: 0:04:32 time: 3.2054 data: 3.0103 max mem: 3957 +eval (validation): [0] [20/85] eta: 0:00:28 time: 0.3058 data: 0.0039 max mem: 3957 +eval (validation): [0] [40/85] eta: 0:00:17 time: 0.3170 data: 0.0040 max mem: 3957 +eval (validation): [0] [60/85] eta: 0:00:09 time: 0.3370 data: 0.0047 max mem: 3957 +eval (validation): [0] [80/85] eta: 0:00:01 time: 0.3235 data: 0.0038 max mem: 3957 +eval (validation): [0] [84/85] eta: 0:00:00 time: 0.3100 data: 0.0040 max mem: 3957 +eval (validation): [0] Total time: 0:00:30 (0.3581 s / it) +cv: [0] best hparam: (31, 1.0) (045) ('045_lr3.1e+01_wd1.0e+00') loss: 3.117 acc: 0.087 f1: 0.025 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__linear/checkpoint-best.pth +train: [1] [ 0/400] eta: 0:21:17 lr: nan time: 3.1950 data: 2.9825 max mem: 3957 +train: [1] [ 20/400] eta: 0:02:59 lr: 0.000063 loss: 3.1503 (3.1572) grad: 0.0742 (0.0757) time: 0.3356 data: 0.0049 max mem: 3957 +train: [1] [ 40/400] eta: 0:02:24 lr: 0.000066 loss: 3.1476 (3.1517) grad: 0.0734 (0.0746) time: 0.3280 data: 0.0036 max mem: 3957 +train: [1] [ 60/400] eta: 0:02:08 lr: 0.000069 loss: 3.1426 (3.1456) grad: 0.0731 (0.0757) time: 0.3315 data: 0.0040 max mem: 3957 +train: [1] [ 80/400] eta: 0:01:58 lr: 0.000072 loss: 3.1438 (3.1460) grad: 0.0734 (0.0752) time: 0.3389 data: 0.0045 max mem: 3957 +train: [1] [100/400] eta: 0:01:48 lr: 0.000075 loss: 3.1442 (3.1439) grad: 0.0716 (0.0751) time: 0.3317 data: 0.0045 max mem: 3957 +train: [1] [120/400] eta: 0:01:39 lr: 0.000078 loss: 3.1468 (3.1445) grad: 0.0740 (0.0754) time: 0.3231 data: 0.0041 max mem: 3957 +train: [1] [140/400] eta: 0:01:31 lr: 0.000081 loss: 3.1477 (3.1450) grad: 0.0744 (0.0756) time: 0.3311 data: 0.0041 max mem: 3957 +train: [1] [160/400] eta: 0:01:24 lr: 0.000084 loss: 3.1473 (3.1461) grad: 0.0753 (0.0760) time: 0.3401 data: 0.0042 max mem: 3957 +train: [1] [180/400] eta: 0:01:16 lr: 0.000087 loss: 3.1447 (3.1462) grad: 0.0792 (0.0764) time: 0.3272 data: 0.0041 max mem: 3957 +train: [1] [200/400] eta: 0:01:09 lr: 0.000090 loss: 3.1328 (3.1454) grad: 0.0805 (0.0765) time: 0.3232 data: 0.0040 max mem: 3957 +train: [1] [220/400] eta: 0:01:01 lr: 0.000093 loss: 3.1306 (3.1454) grad: 0.0767 (0.0768) time: 0.3324 data: 0.0039 max mem: 3957 +train: [1] [240/400] eta: 0:00:54 lr: 0.000096 loss: 3.1417 (3.1441) grad: 0.0789 (0.0770) time: 0.3358 data: 0.0040 max mem: 3957 +train: [1] [260/400] eta: 0:00:47 lr: 0.000099 loss: 3.1389 (3.1439) grad: 0.0781 (0.0769) time: 0.3241 data: 0.0041 max mem: 3957 +train: [1] [280/400] eta: 0:00:40 lr: 0.000102 loss: 3.1342 (3.1422) grad: 0.0763 (0.0770) time: 0.3184 data: 0.0039 max mem: 3957 +train: [1] [300/400] eta: 0:00:33 lr: 0.000105 loss: 3.1365 (3.1434) grad: 0.0769 (0.0771) time: 0.3329 data: 0.0042 max mem: 3957 +train: [1] [320/400] eta: 0:00:27 lr: 0.000108 loss: 3.1535 (3.1431) grad: 0.0753 (0.0771) time: 0.3312 data: 0.0041 max mem: 3957 +train: [1] [340/400] eta: 0:00:20 lr: 0.000111 loss: 3.1435 (3.1433) grad: 0.0738 (0.0768) time: 0.3264 data: 0.0040 max mem: 3957 +train: [1] [360/400] eta: 0:00:13 lr: 0.000114 loss: 3.1333 (3.1425) grad: 0.0756 (0.0769) time: 0.3277 data: 0.0040 max mem: 3957 +train: [1] [380/400] eta: 0:00:06 lr: 0.000117 loss: 3.1273 (3.1425) grad: 0.0760 (0.0767) time: 0.3337 data: 0.0041 max mem: 3957 +train: [1] [399/400] eta: 0:00:00 lr: 0.000120 loss: 3.1273 (3.1418) grad: 0.0704 (0.0764) time: 0.3421 data: 0.0041 max mem: 3957 +train: [1] Total time: 0:02:15 (0.3382 s / it) +train: [1] Summary: lr: 0.000120 loss: 3.1273 (3.1418) grad: 0.0704 (0.0764) +eval (validation): [1] [ 0/85] eta: 0:04:40 time: 3.3019 data: 3.0932 max mem: 3957 +eval (validation): [1] [20/85] eta: 0:00:30 time: 0.3310 data: 0.0306 max mem: 3957 +eval (validation): [1] [40/85] eta: 0:00:18 time: 0.3299 data: 0.0047 max mem: 3957 +eval (validation): [1] [60/85] eta: 0:00:09 time: 0.3816 data: 0.0040 max mem: 3957 +eval (validation): [1] [80/85] eta: 0:00:01 time: 0.3054 data: 0.0041 max mem: 3957 +eval (validation): [1] [84/85] eta: 0:00:00 time: 0.2922 data: 0.0039 max mem: 3957 +eval (validation): [1] Total time: 0:00:31 (0.3722 s / it) +cv: [1] best hparam: (31, 1.0) (045) ('045_lr3.1e+01_wd1.0e+00') loss: 3.097 acc: 0.086 f1: 0.036 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__linear/checkpoint-last.pth +train: [2] [ 0/400] eta: 0:22:00 lr: nan time: 3.3014 data: 3.0980 max mem: 3957 +train: [2] [ 20/400] eta: 0:02:57 lr: 0.000123 loss: 3.1006 (3.1132) grad: 0.0768 (0.0767) time: 0.3245 data: 0.0041 max mem: 3957 +train: [2] [ 40/400] eta: 0:02:25 lr: 0.000126 loss: 3.1244 (3.1237) grad: 0.0749 (0.0781) time: 0.3375 data: 0.0042 max mem: 3957 +train: [2] [ 60/400] eta: 0:02:07 lr: 0.000129 loss: 3.1330 (3.1284) grad: 0.0791 (0.0781) time: 0.3180 data: 0.0041 max mem: 3957 +train: [2] [ 80/400] eta: 0:01:58 lr: 0.000132 loss: 3.1349 (3.1311) grad: 0.0776 (0.0776) time: 0.3558 data: 0.0044 max mem: 3957 +train: [2] [100/400] eta: 0:01:48 lr: 0.000135 loss: 3.1370 (3.1321) grad: 0.0762 (0.0769) time: 0.3227 data: 0.0041 max mem: 3957 +train: [2] [120/400] eta: 0:01:39 lr: 0.000138 loss: 3.1296 (3.1295) grad: 0.0752 (0.0769) time: 0.3268 data: 0.0042 max mem: 3957 +train: [2] [140/400] eta: 0:01:31 lr: 0.000141 loss: 3.1171 (3.1284) grad: 0.0751 (0.0768) time: 0.3435 data: 0.0040 max mem: 3957 +train: [2] [160/400] eta: 0:01:24 lr: 0.000144 loss: 3.1154 (3.1289) grad: 0.0739 (0.0762) time: 0.3436 data: 0.0041 max mem: 3957 +train: [2] [180/400] eta: 0:01:17 lr: 0.000147 loss: 3.1240 (3.1296) grad: 0.0706 (0.0761) time: 0.3316 data: 0.0040 max mem: 3957 +train: [2] [200/400] eta: 0:01:09 lr: 0.000150 loss: 3.1409 (3.1306) grad: 0.0761 (0.0762) time: 0.3339 data: 0.0039 max mem: 3957 +train: [2] [220/400] eta: 0:01:02 lr: 0.000153 loss: 3.1350 (3.1301) grad: 0.0782 (0.0765) time: 0.3205 data: 0.0037 max mem: 3957 +train: [2] [240/400] eta: 0:00:55 lr: 0.000156 loss: 3.1286 (3.1299) grad: 0.0755 (0.0762) time: 0.3507 data: 0.0041 max mem: 3957 +train: [2] [260/400] eta: 0:00:48 lr: 0.000159 loss: 3.1368 (3.1308) grad: 0.0757 (0.0761) time: 0.3360 data: 0.0041 max mem: 3957 +train: [2] [280/400] eta: 0:00:41 lr: 0.000162 loss: 3.1207 (3.1295) grad: 0.0737 (0.0760) time: 0.3246 data: 0.0042 max mem: 3957 +train: [2] [300/400] eta: 0:00:34 lr: 0.000165 loss: 3.1207 (3.1300) grad: 0.0716 (0.0758) time: 0.3225 data: 0.0041 max mem: 3957 +train: [2] [320/400] eta: 0:00:27 lr: 0.000168 loss: 3.1300 (3.1297) grad: 0.0722 (0.0759) time: 0.3207 data: 0.0042 max mem: 3957 +train: [2] [340/400] eta: 0:00:20 lr: 0.000171 loss: 3.1049 (3.1288) grad: 0.0728 (0.0758) time: 0.3317 data: 0.0042 max mem: 3957 +train: [2] [360/400] eta: 0:00:13 lr: 0.000174 loss: 3.1038 (3.1277) grad: 0.0756 (0.0759) time: 0.3130 data: 0.0041 max mem: 3957 +train: [2] [380/400] eta: 0:00:06 lr: 0.000177 loss: 3.1096 (3.1280) grad: 0.0765 (0.0758) time: 0.3889 data: 0.0046 max mem: 3957 +train: [2] [399/400] eta: 0:00:00 lr: 0.000180 loss: 3.1237 (3.1277) grad: 0.0749 (0.0758) time: 0.3410 data: 0.0044 max mem: 3957 +train: [2] Total time: 0:02:16 (0.3419 s / it) +train: [2] Summary: lr: 0.000180 loss: 3.1237 (3.1277) grad: 0.0749 (0.0758) +eval (validation): [2] [ 0/85] eta: 0:04:34 time: 3.2346 data: 3.0290 max mem: 3957 +eval (validation): [2] [20/85] eta: 0:00:30 time: 0.3325 data: 0.0132 max mem: 3957 +eval (validation): [2] [40/85] eta: 0:00:17 time: 0.3152 data: 0.0046 max mem: 3957 +eval (validation): [2] [60/85] eta: 0:00:09 time: 0.3061 data: 0.0046 max mem: 3957 +eval (validation): [2] [80/85] eta: 0:00:01 time: 0.3088 data: 0.0040 max mem: 3957 +eval (validation): [2] [84/85] eta: 0:00:00 time: 0.3019 data: 0.0040 max mem: 3957 +eval (validation): [2] Total time: 0:00:29 (0.3522 s / it) +cv: [2] best hparam: (19, 1.0) (042) ('042_lr1.9e+01_wd1.0e+00') loss: 3.107 acc: 0.084 f1: 0.035 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__linear/checkpoint-last.pth +train: [3] [ 0/400] eta: 0:22:20 lr: nan time: 3.3515 data: 3.0990 max mem: 3957 +train: [3] [ 20/400] eta: 0:03:04 lr: 0.000183 loss: 3.1163 (3.1304) grad: 0.0736 (0.0776) time: 0.3414 data: 0.0124 max mem: 3957 +train: [3] [ 40/400] eta: 0:02:31 lr: 0.000186 loss: 3.1163 (3.1287) grad: 0.0759 (0.0774) time: 0.3535 data: 0.0042 max mem: 3957 +train: [3] [ 60/400] eta: 0:02:12 lr: 0.000189 loss: 3.1154 (3.1232) grad: 0.0746 (0.0760) time: 0.3303 data: 0.0042 max mem: 3957 +train: [3] [ 80/400] eta: 0:02:00 lr: 0.000192 loss: 3.1278 (3.1276) grad: 0.0741 (0.0760) time: 0.3302 data: 0.0045 max mem: 3957 +train: [3] [100/400] eta: 0:01:50 lr: 0.000195 loss: 3.1169 (3.1217) grad: 0.0751 (0.0765) time: 0.3320 data: 0.0039 max mem: 3957 +train: [3] [120/400] eta: 0:01:42 lr: 0.000198 loss: 3.1165 (3.1218) grad: 0.0741 (0.0765) time: 0.3545 data: 0.0040 max mem: 3957 +train: [3] [140/400] eta: 0:01:33 lr: 0.000201 loss: 3.1205 (3.1200) grad: 0.0716 (0.0759) time: 0.3317 data: 0.0040 max mem: 3957 +train: [3] [160/400] eta: 0:01:26 lr: 0.000204 loss: 3.1104 (3.1192) grad: 0.0719 (0.0761) time: 0.3654 data: 0.0048 max mem: 3957 +train: [3] [180/400] eta: 0:01:18 lr: 0.000207 loss: 3.1145 (3.1199) grad: 0.0719 (0.0757) time: 0.3285 data: 0.0039 max mem: 3957 +train: [3] [200/400] eta: 0:01:10 lr: 0.000210 loss: 3.1064 (3.1176) grad: 0.0739 (0.0758) time: 0.3196 data: 0.0041 max mem: 3957 +train: [3] [220/400] eta: 0:01:03 lr: 0.000213 loss: 3.1032 (3.1168) grad: 0.0745 (0.0757) time: 0.3225 data: 0.0036 max mem: 3957 +train: [3] [240/400] eta: 0:00:56 lr: 0.000216 loss: 3.0942 (3.1157) grad: 0.0744 (0.0757) time: 0.3458 data: 0.0041 max mem: 3957 +train: [3] [260/400] eta: 0:00:48 lr: 0.000219 loss: 3.0978 (3.1150) grad: 0.0742 (0.0755) time: 0.3398 data: 0.0040 max mem: 3957 +train: [3] [280/400] eta: 0:00:41 lr: 0.000222 loss: 3.1154 (3.1157) grad: 0.0753 (0.0757) time: 0.3464 data: 0.0040 max mem: 3957 +train: [3] [300/400] eta: 0:00:34 lr: 0.000225 loss: 3.1237 (3.1163) grad: 0.0772 (0.0757) time: 0.3374 data: 0.0040 max mem: 3957 +train: [3] [320/400] eta: 0:00:27 lr: 0.000228 loss: 3.1271 (3.1173) grad: 0.0772 (0.0759) time: 0.3371 data: 0.0042 max mem: 3957 +train: [3] [340/400] eta: 0:00:20 lr: 0.000231 loss: 3.1222 (3.1176) grad: 0.0755 (0.0757) time: 0.3354 data: 0.0041 max mem: 3957 +train: [3] [360/400] eta: 0:00:13 lr: 0.000234 loss: 3.1186 (3.1179) grad: 0.0755 (0.0757) time: 0.3294 data: 0.0041 max mem: 3957 +train: [3] [380/400] eta: 0:00:06 lr: 0.000237 loss: 3.1186 (3.1177) grad: 0.0785 (0.0758) time: 0.3254 data: 0.0036 max mem: 3957 +train: [3] [399/400] eta: 0:00:00 lr: 0.000240 loss: 3.1193 (3.1177) grad: 0.0782 (0.0759) time: 0.3442 data: 0.0039 max mem: 3957 +train: [3] Total time: 0:02:18 (0.3453 s / it) +train: [3] Summary: lr: 0.000240 loss: 3.1193 (3.1177) grad: 0.0782 (0.0759) +eval (validation): [3] [ 0/85] eta: 0:04:41 time: 3.3163 data: 3.0629 max mem: 3957 +eval (validation): [3] [20/85] eta: 0:00:31 time: 0.3400 data: 0.0220 max mem: 3957 +eval (validation): [3] [40/85] eta: 0:00:19 time: 0.3642 data: 0.0041 max mem: 3957 +eval (validation): [3] [60/85] eta: 0:00:09 time: 0.3304 data: 0.0047 max mem: 3957 +eval (validation): [3] [80/85] eta: 0:00:01 time: 0.3061 data: 0.0040 max mem: 3957 +eval (validation): [3] [84/85] eta: 0:00:00 time: 0.2970 data: 0.0038 max mem: 3957 +eval (validation): [3] Total time: 0:00:31 (0.3707 s / it) +cv: [3] best hparam: (50, 1.0) (048) ('048_lr5.0e+01_wd1.0e+00') loss: 3.133 acc: 0.096 f1: 0.045 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__linear/checkpoint-best.pth +train: [4] [ 0/400] eta: 0:22:09 lr: nan time: 3.3248 data: 3.0703 max mem: 3957 +train: [4] [ 20/400] eta: 0:03:10 lr: 0.000243 loss: 3.1093 (3.1143) grad: 0.0731 (0.0779) time: 0.3610 data: 0.0033 max mem: 3957 +train: [4] [ 40/400] eta: 0:02:30 lr: 0.000246 loss: 3.1093 (3.1121) grad: 0.0728 (0.0754) time: 0.3297 data: 0.0041 max mem: 3957 +train: [4] [ 60/400] eta: 0:02:12 lr: 0.000249 loss: 3.0982 (3.1092) grad: 0.0708 (0.0747) time: 0.3327 data: 0.0043 max mem: 3957 +train: [4] [ 80/400] eta: 0:01:59 lr: 0.000252 loss: 3.0982 (3.1092) grad: 0.0756 (0.0761) time: 0.3268 data: 0.0041 max mem: 3957 +train: [4] [100/400] eta: 0:01:48 lr: 0.000255 loss: 3.1071 (3.1117) grad: 0.0772 (0.0768) time: 0.3184 data: 0.0042 max mem: 3957 +train: [4] [120/400] eta: 0:01:39 lr: 0.000258 loss: 3.1229 (3.1136) grad: 0.0750 (0.0772) time: 0.3228 data: 0.0041 max mem: 3957 +train: [4] [140/400] eta: 0:01:31 lr: 0.000261 loss: 3.1136 (3.1144) grad: 0.0735 (0.0770) time: 0.3208 data: 0.0039 max mem: 3957 +train: [4] [160/400] eta: 0:01:23 lr: 0.000264 loss: 3.1183 (3.1153) grad: 0.0758 (0.0773) time: 0.3373 data: 0.0041 max mem: 3957 +train: [4] [180/400] eta: 0:01:16 lr: 0.000267 loss: 3.0951 (3.1139) grad: 0.0787 (0.0776) time: 0.3384 data: 0.0041 max mem: 3957 +train: [4] [200/400] eta: 0:01:09 lr: 0.000270 loss: 3.0896 (3.1137) grad: 0.0749 (0.0772) time: 0.3423 data: 0.0038 max mem: 3957 +train: [4] [220/400] eta: 0:01:02 lr: 0.000273 loss: 3.1092 (3.1133) grad: 0.0741 (0.0768) time: 0.3230 data: 0.0041 max mem: 3957 +train: [4] [240/400] eta: 0:00:55 lr: 0.000276 loss: 3.1092 (3.1143) grad: 0.0739 (0.0766) time: 0.3288 data: 0.0035 max mem: 3957 +train: [4] [260/400] eta: 0:00:48 lr: 0.000279 loss: 3.1303 (3.1151) grad: 0.0735 (0.0766) time: 0.3416 data: 0.0043 max mem: 3957 +train: [4] [280/400] eta: 0:00:41 lr: 0.000282 loss: 3.1222 (3.1145) grad: 0.0727 (0.0763) time: 0.3474 data: 0.0037 max mem: 3957 +train: [4] [300/400] eta: 0:00:34 lr: 0.000285 loss: 3.0901 (3.1134) grad: 0.0742 (0.0763) time: 0.3342 data: 0.0040 max mem: 3957 +train: [4] [320/400] eta: 0:00:27 lr: 0.000288 loss: 3.0901 (3.1128) grad: 0.0745 (0.0763) time: 0.3268 data: 0.0040 max mem: 3957 +train: [4] [340/400] eta: 0:00:20 lr: 0.000291 loss: 3.1050 (3.1122) grad: 0.0766 (0.0764) time: 0.3196 data: 0.0040 max mem: 3957 +train: [4] [360/400] eta: 0:00:13 lr: 0.000294 loss: 3.1000 (3.1114) grad: 0.0744 (0.0762) time: 0.3268 data: 0.0041 max mem: 3957 +train: [4] [380/400] eta: 0:00:06 lr: 0.000297 loss: 3.0860 (3.1103) grad: 0.0703 (0.0760) time: 0.3280 data: 0.0041 max mem: 3957 +train: [4] [399/400] eta: 0:00:00 lr: 0.000300 loss: 3.0867 (3.1107) grad: 0.0744 (0.0762) time: 0.3308 data: 0.0041 max mem: 3957 +train: [4] Total time: 0:02:15 (0.3396 s / it) +train: [4] Summary: lr: 0.000300 loss: 3.0867 (3.1107) grad: 0.0744 (0.0762) +eval (validation): [4] [ 0/85] eta: 0:04:32 time: 3.2045 data: 3.0024 max mem: 3957 +eval (validation): [4] [20/85] eta: 0:00:32 time: 0.3592 data: 0.0056 max mem: 3957 +eval (validation): [4] [40/85] eta: 0:00:19 time: 0.3791 data: 0.0042 max mem: 3957 +eval (validation): [4] [60/85] eta: 0:00:10 time: 0.3512 data: 0.0046 max mem: 3957 +eval (validation): [4] [80/85] eta: 0:00:01 time: 0.3215 data: 0.0043 max mem: 3957 +eval (validation): [4] [84/85] eta: 0:00:00 time: 0.3090 data: 0.0040 max mem: 3957 +eval (validation): [4] Total time: 0:00:32 (0.3871 s / it) +cv: [4] best hparam: (36, 1.0) (046) ('046_lr3.6e+01_wd1.0e+00') loss: 3.133 acc: 0.099 f1: 0.055 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__linear/checkpoint-best.pth +train: [5] [ 0/400] eta: 0:21:58 lr: nan time: 3.2957 data: 3.0487 max mem: 3957 +train: [5] [ 20/400] eta: 0:03:14 lr: 0.000300 loss: 3.1130 (3.1145) grad: 0.0753 (0.0748) time: 0.3718 data: 0.0049 max mem: 3957 +train: [5] [ 40/400] eta: 0:02:34 lr: 0.000300 loss: 3.0999 (3.1007) grad: 0.0753 (0.0750) time: 0.3413 data: 0.0041 max mem: 3957 +train: [5] [ 60/400] eta: 0:02:13 lr: 0.000300 loss: 3.0854 (3.1044) grad: 0.0724 (0.0737) time: 0.3161 data: 0.0045 max mem: 3957 +train: [5] [ 80/400] eta: 0:01:59 lr: 0.000300 loss: 3.1004 (3.1010) grad: 0.0714 (0.0739) time: 0.3232 data: 0.0045 max mem: 3957 +train: [5] [100/400] eta: 0:01:49 lr: 0.000300 loss: 3.0990 (3.1016) grad: 0.0779 (0.0752) time: 0.3254 data: 0.0041 max mem: 3957 +train: [5] [120/400] eta: 0:01:41 lr: 0.000300 loss: 3.0959 (3.1006) grad: 0.0796 (0.0759) time: 0.3495 data: 0.0052 max mem: 3957 +train: [5] [140/400] eta: 0:01:32 lr: 0.000300 loss: 3.0997 (3.1029) grad: 0.0788 (0.0761) time: 0.3289 data: 0.0039 max mem: 3957 +train: [5] [160/400] eta: 0:01:25 lr: 0.000299 loss: 3.1125 (3.1050) grad: 0.0768 (0.0759) time: 0.3384 data: 0.0041 max mem: 3957 +train: [5] [180/400] eta: 0:01:17 lr: 0.000299 loss: 3.1068 (3.1042) grad: 0.0741 (0.0762) time: 0.3413 data: 0.0042 max mem: 3957 +train: [5] [200/400] eta: 0:01:10 lr: 0.000299 loss: 3.0853 (3.1006) grad: 0.0741 (0.0758) time: 0.3382 data: 0.0040 max mem: 3957 +train: [5] [220/400] eta: 0:01:02 lr: 0.000299 loss: 3.0761 (3.0997) grad: 0.0737 (0.0757) time: 0.3195 data: 0.0039 max mem: 3957 +train: [5] [240/400] eta: 0:00:55 lr: 0.000299 loss: 3.1012 (3.1015) grad: 0.0713 (0.0752) time: 0.3346 data: 0.0045 max mem: 3957 +train: [5] [260/400] eta: 0:00:48 lr: 0.000299 loss: 3.1122 (3.1022) grad: 0.0732 (0.0752) time: 0.3360 data: 0.0040 max mem: 3957 +train: [5] [280/400] eta: 0:00:41 lr: 0.000298 loss: 3.1122 (3.1039) grad: 0.0731 (0.0751) time: 0.3565 data: 0.0045 max mem: 3957 +train: [5] [300/400] eta: 0:00:34 lr: 0.000298 loss: 3.1252 (3.1044) grad: 0.0732 (0.0753) time: 0.3275 data: 0.0039 max mem: 3957 +train: [5] [320/400] eta: 0:00:27 lr: 0.000298 loss: 3.1214 (3.1051) grad: 0.0732 (0.0751) time: 0.3252 data: 0.0040 max mem: 3957 +train: [5] [340/400] eta: 0:00:20 lr: 0.000298 loss: 3.1045 (3.1046) grad: 0.0705 (0.0750) time: 0.3408 data: 0.0040 max mem: 3957 +train: [5] [360/400] eta: 0:00:13 lr: 0.000297 loss: 3.1155 (3.1063) grad: 0.0715 (0.0749) time: 0.3384 data: 0.0040 max mem: 3957 +train: [5] [380/400] eta: 0:00:06 lr: 0.000297 loss: 3.1225 (3.1063) grad: 0.0743 (0.0750) time: 0.3291 data: 0.0040 max mem: 3957 +train: [5] [399/400] eta: 0:00:00 lr: 0.000297 loss: 3.0983 (3.1062) grad: 0.0743 (0.0750) time: 0.3302 data: 0.0039 max mem: 3957 +train: [5] Total time: 0:02:17 (0.3433 s / it) +train: [5] Summary: lr: 0.000297 loss: 3.0983 (3.1062) grad: 0.0743 (0.0750) +eval (validation): [5] [ 0/85] eta: 0:04:35 time: 3.2365 data: 3.0211 max mem: 3957 +eval (validation): [5] [20/85] eta: 0:00:30 time: 0.3230 data: 0.0060 max mem: 3957 +eval (validation): [5] [40/85] eta: 0:00:17 time: 0.3262 data: 0.0039 max mem: 3957 +eval (validation): [5] [60/85] eta: 0:00:09 time: 0.3269 data: 0.0044 max mem: 3957 +eval (validation): [5] [80/85] eta: 0:00:01 time: 0.3018 data: 0.0042 max mem: 3957 +eval (validation): [5] [84/85] eta: 0:00:00 time: 0.2950 data: 0.0042 max mem: 3957 +eval (validation): [5] Total time: 0:00:30 (0.3560 s / it) +cv: [5] best hparam: (9.8, 1.0) (038) ('038_lr9.8e+00_wd1.0e+00') loss: 3.084 acc: 0.098 f1: 0.040 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__linear/checkpoint-last.pth +train: [6] [ 0/400] eta: 0:22:07 lr: nan time: 3.3195 data: 3.0588 max mem: 3957 +train: [6] [ 20/400] eta: 0:03:15 lr: 0.000296 loss: 3.0705 (3.0800) grad: 0.0733 (0.0760) time: 0.3749 data: 0.0049 max mem: 3957 +train: [6] [ 40/400] eta: 0:02:31 lr: 0.000296 loss: 3.0721 (3.0799) grad: 0.0744 (0.0764) time: 0.3194 data: 0.0037 max mem: 3957 +train: [6] [ 60/400] eta: 0:02:11 lr: 0.000296 loss: 3.0829 (3.0827) grad: 0.0767 (0.0768) time: 0.3233 data: 0.0042 max mem: 3957 +train: [6] [ 80/400] eta: 0:01:59 lr: 0.000295 loss: 3.0894 (3.0851) grad: 0.0750 (0.0761) time: 0.3278 data: 0.0042 max mem: 3957 +train: [6] [100/400] eta: 0:01:50 lr: 0.000295 loss: 3.0911 (3.0849) grad: 0.0740 (0.0760) time: 0.3472 data: 0.0045 max mem: 3957 +train: [6] [120/400] eta: 0:01:42 lr: 0.000295 loss: 3.0743 (3.0834) grad: 0.0742 (0.0753) time: 0.3485 data: 0.0042 max mem: 3957 +train: [6] [140/400] eta: 0:01:33 lr: 0.000294 loss: 3.0703 (3.0825) grad: 0.0742 (0.0753) time: 0.3330 data: 0.0037 max mem: 3957 +train: [6] [160/400] eta: 0:01:25 lr: 0.000294 loss: 3.0820 (3.0835) grad: 0.0781 (0.0758) time: 0.3414 data: 0.0044 max mem: 3957 +train: [6] [180/400] eta: 0:01:17 lr: 0.000293 loss: 3.0855 (3.0834) grad: 0.0767 (0.0759) time: 0.3261 data: 0.0038 max mem: 3957 +train: [6] [200/400] eta: 0:01:10 lr: 0.000293 loss: 3.0829 (3.0848) grad: 0.0734 (0.0755) time: 0.3401 data: 0.0041 max mem: 3957 +train: [6] [220/400] eta: 0:01:03 lr: 0.000292 loss: 3.0833 (3.0864) grad: 0.0730 (0.0752) time: 0.3254 data: 0.0039 max mem: 3957 +train: [6] [240/400] eta: 0:00:55 lr: 0.000292 loss: 3.1052 (3.0870) grad: 0.0746 (0.0753) time: 0.3380 data: 0.0041 max mem: 3957 +train: [6] [260/400] eta: 0:00:48 lr: 0.000291 loss: 3.0971 (3.0878) grad: 0.0784 (0.0755) time: 0.3391 data: 0.0041 max mem: 3957 +train: [6] [280/400] eta: 0:00:41 lr: 0.000291 loss: 3.0860 (3.0888) grad: 0.0774 (0.0755) time: 0.3343 data: 0.0042 max mem: 3957 +train: [6] [300/400] eta: 0:00:34 lr: 0.000290 loss: 3.0834 (3.0888) grad: 0.0725 (0.0755) time: 0.3329 data: 0.0037 max mem: 3957 +train: [6] [320/400] eta: 0:00:27 lr: 0.000290 loss: 3.0696 (3.0875) grad: 0.0725 (0.0756) time: 0.3216 data: 0.0040 max mem: 3957 +train: [6] [340/400] eta: 0:00:20 lr: 0.000289 loss: 3.0913 (3.0897) grad: 0.0780 (0.0756) time: 0.3468 data: 0.0042 max mem: 3957 +train: [6] [360/400] eta: 0:00:13 lr: 0.000288 loss: 3.0962 (3.0893) grad: 0.0755 (0.0756) time: 0.3322 data: 0.0042 max mem: 3957 +train: [6] [380/400] eta: 0:00:06 lr: 0.000288 loss: 3.0962 (3.0904) grad: 0.0742 (0.0757) time: 0.3243 data: 0.0037 max mem: 3957 +train: [6] [399/400] eta: 0:00:00 lr: 0.000287 loss: 3.1041 (3.0903) grad: 0.0699 (0.0755) time: 0.3253 data: 0.0040 max mem: 3957 +train: [6] Total time: 0:02:17 (0.3429 s / it) +train: [6] Summary: lr: 0.000287 loss: 3.1041 (3.0903) grad: 0.0699 (0.0755) +eval (validation): [6] [ 0/85] eta: 0:04:39 time: 3.2885 data: 3.0521 max mem: 3957 +eval (validation): [6] [20/85] eta: 0:00:32 time: 0.3575 data: 0.0050 max mem: 3957 +eval (validation): [6] [40/85] eta: 0:00:18 time: 0.3253 data: 0.0043 max mem: 3957 +eval (validation): [6] [60/85] eta: 0:00:09 time: 0.3294 data: 0.0046 max mem: 3957 +eval (validation): [6] [80/85] eta: 0:00:01 time: 0.3029 data: 0.0040 max mem: 3957 +eval (validation): [6] [84/85] eta: 0:00:00 time: 0.2964 data: 0.0040 max mem: 3957 +eval (validation): [6] Total time: 0:00:31 (0.3665 s / it) +cv: [6] best hparam: (36, 1.0) (046) ('046_lr3.6e+01_wd1.0e+00') loss: 3.096 acc: 0.101 f1: 0.057 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__linear/checkpoint-best.pth +train: [7] [ 0/400] eta: 0:22:33 lr: nan time: 3.3831 data: 3.1176 max mem: 3957 +train: [7] [ 20/400] eta: 0:03:14 lr: 0.000286 loss: 3.0616 (3.0765) grad: 0.0668 (0.0692) time: 0.3687 data: 0.0046 max mem: 3957 +train: [7] [ 40/400] eta: 0:02:33 lr: 0.000286 loss: 3.0991 (3.0835) grad: 0.0704 (0.0728) time: 0.3342 data: 0.0041 max mem: 3957 +train: [7] [ 60/400] eta: 0:02:13 lr: 0.000285 loss: 3.0727 (3.0803) grad: 0.0748 (0.0735) time: 0.3224 data: 0.0042 max mem: 3957 +train: [7] [ 80/400] eta: 0:02:00 lr: 0.000284 loss: 3.0693 (3.0766) grad: 0.0721 (0.0736) time: 0.3352 data: 0.0040 max mem: 3957 +train: [7] [100/400] eta: 0:01:50 lr: 0.000284 loss: 3.0714 (3.0804) grad: 0.0706 (0.0735) time: 0.3342 data: 0.0041 max mem: 3957 +train: [7] [120/400] eta: 0:01:41 lr: 0.000283 loss: 3.0714 (3.0768) grad: 0.0722 (0.0743) time: 0.3247 data: 0.0042 max mem: 3957 +train: [7] [140/400] eta: 0:01:33 lr: 0.000282 loss: 3.0715 (3.0782) grad: 0.0738 (0.0745) time: 0.3556 data: 0.0044 max mem: 3957 +train: [7] [160/400] eta: 0:01:25 lr: 0.000282 loss: 3.0853 (3.0774) grad: 0.0763 (0.0748) time: 0.3340 data: 0.0041 max mem: 3957 +train: [7] [180/400] eta: 0:01:18 lr: 0.000281 loss: 3.0756 (3.0775) grad: 0.0763 (0.0750) time: 0.3319 data: 0.0041 max mem: 3957 +train: [7] [200/400] eta: 0:01:10 lr: 0.000280 loss: 3.0756 (3.0795) grad: 0.0739 (0.0751) time: 0.3222 data: 0.0041 max mem: 3957 +train: [7] [220/400] eta: 0:01:02 lr: 0.000279 loss: 3.0812 (3.0811) grad: 0.0755 (0.0751) time: 0.3179 data: 0.0040 max mem: 3957 +train: [7] [240/400] eta: 0:00:55 lr: 0.000278 loss: 3.0811 (3.0822) grad: 0.0755 (0.0750) time: 0.3501 data: 0.0043 max mem: 3957 +train: [7] [260/400] eta: 0:00:48 lr: 0.000278 loss: 3.0780 (3.0811) grad: 0.0733 (0.0748) time: 0.3401 data: 0.0041 max mem: 3957 +train: [7] [280/400] eta: 0:00:41 lr: 0.000277 loss: 3.0721 (3.0797) grad: 0.0702 (0.0748) time: 0.3428 data: 0.0042 max mem: 3957 +train: [7] [300/400] eta: 0:00:34 lr: 0.000276 loss: 3.0721 (3.0796) grad: 0.0731 (0.0751) time: 0.3592 data: 0.0040 max mem: 3957 +train: [7] [320/400] eta: 0:00:27 lr: 0.000275 loss: 3.0801 (3.0812) grad: 0.0751 (0.0751) time: 0.3230 data: 0.0041 max mem: 3957 +train: [7] [340/400] eta: 0:00:20 lr: 0.000274 loss: 3.0987 (3.0819) grad: 0.0748 (0.0750) time: 0.3220 data: 0.0042 max mem: 3957 +train: [7] [360/400] eta: 0:00:13 lr: 0.000273 loss: 3.0987 (3.0836) grad: 0.0719 (0.0752) time: 0.3472 data: 0.0042 max mem: 3957 +train: [7] [380/400] eta: 0:00:06 lr: 0.000272 loss: 3.0973 (3.0840) grad: 0.0781 (0.0753) time: 0.3256 data: 0.0043 max mem: 3957 +train: [7] [399/400] eta: 0:00:00 lr: 0.000271 loss: 3.0980 (3.0853) grad: 0.0781 (0.0754) time: 0.3510 data: 0.0044 max mem: 3957 +train: [7] Total time: 0:02:18 (0.3450 s / it) +train: [7] Summary: lr: 0.000271 loss: 3.0980 (3.0853) grad: 0.0781 (0.0754) +eval (validation): [7] [ 0/85] eta: 0:04:38 time: 3.2730 data: 3.0661 max mem: 3957 +eval (validation): [7] [20/85] eta: 0:00:30 time: 0.3367 data: 0.0050 max mem: 3957 +eval (validation): [7] [40/85] eta: 0:00:18 time: 0.3297 data: 0.0046 max mem: 3957 +eval (validation): [7] [60/85] eta: 0:00:09 time: 0.3189 data: 0.0039 max mem: 3957 +eval (validation): [7] [80/85] eta: 0:00:01 time: 0.3132 data: 0.0041 max mem: 3957 +eval (validation): [7] [84/85] eta: 0:00:00 time: 0.3094 data: 0.0039 max mem: 3957 +eval (validation): [7] Total time: 0:00:30 (0.3626 s / it) +cv: [7] best hparam: (22, 1.0) (043) ('043_lr2.2e+01_wd1.0e+00') loss: 3.122 acc: 0.100 f1: 0.055 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__linear/checkpoint-last.pth +train: [8] [ 0/400] eta: 0:22:23 lr: nan time: 3.3599 data: 3.1450 max mem: 3957 +train: [8] [ 20/400] eta: 0:03:00 lr: 0.000270 loss: 3.0588 (3.0642) grad: 0.0764 (0.0799) time: 0.3311 data: 0.0043 max mem: 3957 +train: [8] [ 40/400] eta: 0:02:24 lr: 0.000270 loss: 3.0558 (3.0583) grad: 0.0718 (0.0748) time: 0.3212 data: 0.0036 max mem: 3957 +train: [8] [ 60/400] eta: 0:02:09 lr: 0.000269 loss: 3.0618 (3.0677) grad: 0.0689 (0.0735) time: 0.3411 data: 0.0039 max mem: 3957 +train: [8] [ 80/400] eta: 0:01:57 lr: 0.000268 loss: 3.0860 (3.0736) grad: 0.0725 (0.0736) time: 0.3242 data: 0.0042 max mem: 3957 +train: [8] [100/400] eta: 0:01:47 lr: 0.000267 loss: 3.0867 (3.0765) grad: 0.0779 (0.0752) time: 0.3278 data: 0.0043 max mem: 3957 +train: [8] [120/400] eta: 0:01:38 lr: 0.000266 loss: 3.0869 (3.0766) grad: 0.0782 (0.0752) time: 0.3235 data: 0.0042 max mem: 3957 +train: [8] [140/400] eta: 0:01:30 lr: 0.000265 loss: 3.0797 (3.0763) grad: 0.0730 (0.0754) time: 0.3285 data: 0.0043 max mem: 3957 +train: [8] [160/400] eta: 0:01:23 lr: 0.000264 loss: 3.0749 (3.0759) grad: 0.0748 (0.0754) time: 0.3484 data: 0.0041 max mem: 3957 +train: [8] [180/400] eta: 0:01:17 lr: 0.000263 loss: 3.0470 (3.0737) grad: 0.0758 (0.0752) time: 0.3766 data: 0.0047 max mem: 3957 +train: [8] [200/400] eta: 0:01:10 lr: 0.000262 loss: 3.0771 (3.0761) grad: 0.0754 (0.0753) time: 0.3473 data: 0.0043 max mem: 3957 +train: [8] [220/400] eta: 0:01:02 lr: 0.000260 loss: 3.0872 (3.0756) grad: 0.0752 (0.0752) time: 0.3207 data: 0.0039 max mem: 3957 +train: [8] [240/400] eta: 0:00:55 lr: 0.000259 loss: 3.0801 (3.0757) grad: 0.0733 (0.0749) time: 0.3470 data: 0.0039 max mem: 3957 +train: [8] [260/400] eta: 0:00:48 lr: 0.000258 loss: 3.0854 (3.0769) grad: 0.0707 (0.0747) time: 0.3420 data: 0.0039 max mem: 3957 +train: [8] [280/400] eta: 0:00:41 lr: 0.000257 loss: 3.0685 (3.0764) grad: 0.0707 (0.0746) time: 0.3354 data: 0.0041 max mem: 3957 +train: [8] [300/400] eta: 0:00:34 lr: 0.000256 loss: 3.0645 (3.0757) grad: 0.0708 (0.0744) time: 0.3302 data: 0.0039 max mem: 3957 +train: [8] [320/400] eta: 0:00:27 lr: 0.000255 loss: 3.0584 (3.0761) grad: 0.0717 (0.0743) time: 0.3314 data: 0.0041 max mem: 3957 +train: [8] [340/400] eta: 0:00:20 lr: 0.000254 loss: 3.0721 (3.0759) grad: 0.0717 (0.0742) time: 0.3279 data: 0.0044 max mem: 3957 +train: [8] [360/400] eta: 0:00:13 lr: 0.000253 loss: 3.0738 (3.0764) grad: 0.0742 (0.0742) time: 0.3282 data: 0.0040 max mem: 3957 +train: [8] [380/400] eta: 0:00:06 lr: 0.000252 loss: 3.0774 (3.0766) grad: 0.0758 (0.0743) time: 0.3294 data: 0.0040 max mem: 3957 +train: [8] [399/400] eta: 0:00:00 lr: 0.000250 loss: 3.0895 (3.0774) grad: 0.0758 (0.0743) time: 0.3293 data: 0.0035 max mem: 3957 +train: [8] Total time: 0:02:16 (0.3424 s / it) +train: [8] Summary: lr: 0.000250 loss: 3.0895 (3.0774) grad: 0.0758 (0.0743) +eval (validation): [8] [ 0/85] eta: 0:04:47 time: 3.3767 data: 3.1204 max mem: 3957 +eval (validation): [8] [20/85] eta: 0:00:31 time: 0.3458 data: 0.0051 max mem: 3957 +eval (validation): [8] [40/85] eta: 0:00:18 time: 0.3350 data: 0.0041 max mem: 3957 +eval (validation): [8] [60/85] eta: 0:00:09 time: 0.3357 data: 0.0042 max mem: 3957 +eval (validation): [8] [80/85] eta: 0:00:01 time: 0.3171 data: 0.0042 max mem: 3957 +eval (validation): [8] [84/85] eta: 0:00:00 time: 0.3110 data: 0.0039 max mem: 3957 +eval (validation): [8] Total time: 0:00:31 (0.3708 s / it) +cv: [8] best hparam: (22, 1.0) (043) ('043_lr2.2e+01_wd1.0e+00') loss: 3.071 acc: 0.114 f1: 0.064 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__linear/checkpoint-best.pth +train: [9] [ 0/400] eta: 0:22:14 lr: nan time: 3.3372 data: 3.1163 max mem: 3957 +train: [9] [ 20/400] eta: 0:03:02 lr: 0.000249 loss: 3.0609 (3.0623) grad: 0.0684 (0.0699) time: 0.3375 data: 0.0037 max mem: 3957 +train: [9] [ 40/400] eta: 0:02:26 lr: 0.000248 loss: 3.0688 (3.0691) grad: 0.0684 (0.0729) time: 0.3312 data: 0.0037 max mem: 3957 +train: [9] [ 60/400] eta: 0:02:10 lr: 0.000247 loss: 3.0822 (3.0771) grad: 0.0733 (0.0731) time: 0.3311 data: 0.0039 max mem: 3957 +train: [9] [ 80/400] eta: 0:01:58 lr: 0.000246 loss: 3.0841 (3.0804) grad: 0.0738 (0.0729) time: 0.3275 data: 0.0044 max mem: 3957 +train: [9] [100/400] eta: 0:01:48 lr: 0.000244 loss: 3.0880 (3.0823) grad: 0.0736 (0.0732) time: 0.3343 data: 0.0042 max mem: 3957 +train: [9] [120/400] eta: 0:01:39 lr: 0.000243 loss: 3.0659 (3.0757) grad: 0.0723 (0.0735) time: 0.3277 data: 0.0046 max mem: 3957 +train: [9] [140/400] eta: 0:01:31 lr: 0.000242 loss: 3.0638 (3.0766) grad: 0.0723 (0.0736) time: 0.3366 data: 0.0041 max mem: 3957 +train: [9] [160/400] eta: 0:01:24 lr: 0.000241 loss: 3.0942 (3.0794) grad: 0.0728 (0.0735) time: 0.3412 data: 0.0042 max mem: 3957 +train: [9] [180/400] eta: 0:01:17 lr: 0.000240 loss: 3.0768 (3.0779) grad: 0.0745 (0.0738) time: 0.3500 data: 0.0041 max mem: 3957 +train: [9] [200/400] eta: 0:01:10 lr: 0.000238 loss: 3.0648 (3.0770) grad: 0.0745 (0.0740) time: 0.3367 data: 0.0046 max mem: 3957 +train: [9] [220/400] eta: 0:01:02 lr: 0.000237 loss: 3.0648 (3.0756) grad: 0.0715 (0.0741) time: 0.3248 data: 0.0036 max mem: 3957 +train: [9] [240/400] eta: 0:00:55 lr: 0.000236 loss: 3.0707 (3.0756) grad: 0.0752 (0.0743) time: 0.3408 data: 0.0041 max mem: 3957 +train: [9] [260/400] eta: 0:00:48 lr: 0.000234 loss: 3.0724 (3.0760) grad: 0.0747 (0.0743) time: 0.3363 data: 0.0043 max mem: 3957 +train: [9] [280/400] eta: 0:00:41 lr: 0.000233 loss: 3.0807 (3.0760) grad: 0.0728 (0.0745) time: 0.3381 data: 0.0040 max mem: 3957 +train: [9] [300/400] eta: 0:00:34 lr: 0.000232 loss: 3.0893 (3.0778) grad: 0.0759 (0.0747) time: 0.3338 data: 0.0041 max mem: 3957 +train: [9] [320/400] eta: 0:00:27 lr: 0.000230 loss: 3.0765 (3.0782) grad: 0.0759 (0.0748) time: 0.3427 data: 0.0041 max mem: 3957 +train: [9] [340/400] eta: 0:00:20 lr: 0.000229 loss: 3.0765 (3.0786) grad: 0.0743 (0.0748) time: 0.3422 data: 0.0041 max mem: 3957 +train: [9] [360/400] eta: 0:00:13 lr: 0.000228 loss: 3.0752 (3.0774) grad: 0.0767 (0.0752) time: 0.3392 data: 0.0040 max mem: 3957 +train: [9] [380/400] eta: 0:00:06 lr: 0.000226 loss: 3.0400 (3.0754) grad: 0.0761 (0.0749) time: 0.3243 data: 0.0039 max mem: 3957 +train: [9] [399/400] eta: 0:00:00 lr: 0.000225 loss: 3.0536 (3.0757) grad: 0.0721 (0.0751) time: 0.3395 data: 0.0042 max mem: 3957 +train: [9] Total time: 0:02:17 (0.3435 s / it) +train: [9] Summary: lr: 0.000225 loss: 3.0536 (3.0757) grad: 0.0721 (0.0751) +eval (validation): [9] [ 0/85] eta: 0:04:50 time: 3.4139 data: 3.1661 max mem: 3957 +eval (validation): [9] [20/85] eta: 0:00:31 time: 0.3344 data: 0.0050 max mem: 3957 +eval (validation): [9] [40/85] eta: 0:00:18 time: 0.3411 data: 0.0040 max mem: 3957 +eval (validation): [9] [60/85] eta: 0:00:09 time: 0.3278 data: 0.0046 max mem: 3957 +eval (validation): [9] [80/85] eta: 0:00:01 time: 0.3021 data: 0.0040 max mem: 3957 +eval (validation): [9] [84/85] eta: 0:00:00 time: 0.2974 data: 0.0039 max mem: 3957 +eval (validation): [9] Total time: 0:00:31 (0.3650 s / it) +cv: [9] best hparam: (16, 1.0) (041) ('041_lr1.6e+01_wd1.0e+00') loss: 3.050 acc: 0.108 f1: 0.064 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__linear/checkpoint-last.pth +train: [10] [ 0/400] eta: 0:22:10 lr: nan time: 3.3268 data: 3.1106 max mem: 3957 +train: [10] [ 20/400] eta: 0:03:01 lr: 0.000224 loss: 3.0474 (3.0597) grad: 0.0699 (0.0713) time: 0.3338 data: 0.0049 max mem: 3957 +train: [10] [ 40/400] eta: 0:02:27 lr: 0.000222 loss: 3.0642 (3.0602) grad: 0.0699 (0.0710) time: 0.3381 data: 0.0042 max mem: 3957 +train: [10] [ 60/400] eta: 0:02:11 lr: 0.000221 loss: 3.0642 (3.0665) grad: 0.0673 (0.0712) time: 0.3389 data: 0.0037 max mem: 3957 +train: [10] [ 80/400] eta: 0:02:00 lr: 0.000220 loss: 3.0427 (3.0626) grad: 0.0695 (0.0714) time: 0.3481 data: 0.0042 max mem: 3957 +train: [10] [100/400] eta: 0:01:50 lr: 0.000218 loss: 3.0641 (3.0668) grad: 0.0722 (0.0715) time: 0.3359 data: 0.0041 max mem: 3957 +train: [10] [120/400] eta: 0:01:41 lr: 0.000217 loss: 3.0708 (3.0661) grad: 0.0716 (0.0716) time: 0.3398 data: 0.0039 max mem: 3957 +train: [10] [140/400] eta: 0:01:33 lr: 0.000215 loss: 3.0659 (3.0647) grad: 0.0713 (0.0726) time: 0.3228 data: 0.0038 max mem: 3957 +train: [10] [160/400] eta: 0:01:25 lr: 0.000214 loss: 3.0858 (3.0671) grad: 0.0763 (0.0727) time: 0.3409 data: 0.0040 max mem: 3957 +train: [10] [180/400] eta: 0:01:18 lr: 0.000213 loss: 3.0840 (3.0682) grad: 0.0773 (0.0733) time: 0.3475 data: 0.0042 max mem: 3957 +train: [10] [200/400] eta: 0:01:10 lr: 0.000211 loss: 3.0729 (3.0681) grad: 0.0763 (0.0734) time: 0.3292 data: 0.0040 max mem: 3957 +train: [10] [220/400] eta: 0:01:03 lr: 0.000210 loss: 3.0720 (3.0692) grad: 0.0763 (0.0735) time: 0.3421 data: 0.0044 max mem: 3957 +train: [10] [240/400] eta: 0:00:55 lr: 0.000208 loss: 3.0740 (3.0684) grad: 0.0722 (0.0734) time: 0.3251 data: 0.0035 max mem: 3957 +train: [10] [260/400] eta: 0:00:48 lr: 0.000207 loss: 3.0863 (3.0704) grad: 0.0698 (0.0731) time: 0.3557 data: 0.0041 max mem: 3957 +train: [10] [280/400] eta: 0:00:41 lr: 0.000205 loss: 3.0951 (3.0704) grad: 0.0698 (0.0731) time: 0.3462 data: 0.0040 max mem: 3957 +train: [10] [300/400] eta: 0:00:34 lr: 0.000204 loss: 3.0548 (3.0689) grad: 0.0728 (0.0733) time: 0.3337 data: 0.0038 max mem: 3957 +train: [10] [320/400] eta: 0:00:27 lr: 0.000202 loss: 3.0642 (3.0695) grad: 0.0728 (0.0733) time: 0.3208 data: 0.0038 max mem: 3957 +train: [10] [340/400] eta: 0:00:20 lr: 0.000201 loss: 3.0886 (3.0700) grad: 0.0713 (0.0734) time: 0.3452 data: 0.0041 max mem: 3957 +train: [10] [360/400] eta: 0:00:13 lr: 0.000199 loss: 3.0886 (3.0708) grad: 0.0732 (0.0734) time: 0.3362 data: 0.0039 max mem: 3957 +train: [10] [380/400] eta: 0:00:06 lr: 0.000198 loss: 3.0610 (3.0702) grad: 0.0723 (0.0735) time: 0.3341 data: 0.0039 max mem: 3957 +train: [10] [399/400] eta: 0:00:00 lr: 0.000196 loss: 3.0737 (3.0705) grad: 0.0715 (0.0734) time: 0.3301 data: 0.0035 max mem: 3957 +train: [10] Total time: 0:02:17 (0.3450 s / it) +train: [10] Summary: lr: 0.000196 loss: 3.0737 (3.0705) grad: 0.0715 (0.0734) +eval (validation): [10] [ 0/85] eta: 0:04:33 time: 3.2150 data: 3.0126 max mem: 3957 +eval (validation): [10] [20/85] eta: 0:00:30 time: 0.3289 data: 0.0041 max mem: 3957 +eval (validation): [10] [40/85] eta: 0:00:17 time: 0.3136 data: 0.0045 max mem: 3957 +eval (validation): [10] [60/85] eta: 0:00:09 time: 0.3261 data: 0.0042 max mem: 3957 +eval (validation): [10] [80/85] eta: 0:00:01 time: 0.3063 data: 0.0038 max mem: 3957 +eval (validation): [10] [84/85] eta: 0:00:00 time: 0.2988 data: 0.0038 max mem: 3957 +eval (validation): [10] Total time: 0:00:30 (0.3556 s / it) +cv: [10] best hparam: (19, 1.0) (042) ('042_lr1.9e+01_wd1.0e+00') loss: 3.059 acc: 0.106 f1: 0.072 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__linear/checkpoint-last.pth +train: [11] [ 0/400] eta: 0:22:04 lr: nan time: 3.3106 data: 3.0903 max mem: 3957 +train: [11] [ 20/400] eta: 0:03:06 lr: 0.000195 loss: 3.0490 (3.0613) grad: 0.0729 (0.0725) time: 0.3509 data: 0.0297 max mem: 3957 +train: [11] [ 40/400] eta: 0:02:28 lr: 0.000193 loss: 3.0490 (3.0528) grad: 0.0738 (0.0746) time: 0.3313 data: 0.0034 max mem: 3957 +train: [11] [ 60/400] eta: 0:02:12 lr: 0.000192 loss: 3.0584 (3.0614) grad: 0.0753 (0.0751) time: 0.3375 data: 0.0037 max mem: 3957 +train: [11] [ 80/400] eta: 0:01:59 lr: 0.000190 loss: 3.0667 (3.0633) grad: 0.0750 (0.0753) time: 0.3297 data: 0.0041 max mem: 3957 +train: [11] [100/400] eta: 0:01:49 lr: 0.000189 loss: 3.0680 (3.0688) grad: 0.0733 (0.0749) time: 0.3303 data: 0.0040 max mem: 3957 +train: [11] [120/400] eta: 0:01:40 lr: 0.000187 loss: 3.0804 (3.0676) grad: 0.0733 (0.0746) time: 0.3364 data: 0.0042 max mem: 3957 +train: [11] [140/400] eta: 0:01:32 lr: 0.000186 loss: 3.0553 (3.0598) grad: 0.0740 (0.0746) time: 0.3387 data: 0.0041 max mem: 3957 +train: [11] [160/400] eta: 0:01:25 lr: 0.000184 loss: 3.0642 (3.0621) grad: 0.0794 (0.0751) time: 0.3380 data: 0.0039 max mem: 3957 +train: [11] [180/400] eta: 0:01:18 lr: 0.000183 loss: 3.0642 (3.0610) grad: 0.0778 (0.0749) time: 0.3530 data: 0.0043 max mem: 3957 +train: [11] [200/400] eta: 0:01:10 lr: 0.000181 loss: 3.0433 (3.0601) grad: 0.0739 (0.0749) time: 0.3368 data: 0.0040 max mem: 3957 +train: [11] [220/400] eta: 0:01:03 lr: 0.000180 loss: 3.0750 (3.0630) grad: 0.0747 (0.0751) time: 0.3404 data: 0.0041 max mem: 3957 +train: [11] [240/400] eta: 0:00:56 lr: 0.000178 loss: 3.0804 (3.0635) grad: 0.0722 (0.0747) time: 0.3495 data: 0.0039 max mem: 3957 +train: [11] [260/400] eta: 0:00:49 lr: 0.000177 loss: 3.0438 (3.0621) grad: 0.0712 (0.0744) time: 0.3355 data: 0.0040 max mem: 3957 +train: [11] [280/400] eta: 0:00:42 lr: 0.000175 loss: 3.0414 (3.0622) grad: 0.0705 (0.0743) time: 0.3442 data: 0.0039 max mem: 3957 +train: [11] [300/400] eta: 0:00:34 lr: 0.000174 loss: 3.0648 (3.0637) grad: 0.0705 (0.0741) time: 0.3403 data: 0.0040 max mem: 3957 +train: [11] [320/400] eta: 0:00:27 lr: 0.000172 loss: 3.0641 (3.0629) grad: 0.0736 (0.0742) time: 0.3305 data: 0.0037 max mem: 3957 +train: [11] [340/400] eta: 0:00:20 lr: 0.000170 loss: 3.0557 (3.0631) grad: 0.0741 (0.0741) time: 0.3467 data: 0.0043 max mem: 3957 +train: [11] [360/400] eta: 0:00:13 lr: 0.000169 loss: 3.0472 (3.0616) grad: 0.0720 (0.0740) time: 0.3368 data: 0.0038 max mem: 3957 +train: [11] [380/400] eta: 0:00:06 lr: 0.000167 loss: 3.0350 (3.0614) grad: 0.0732 (0.0742) time: 0.3366 data: 0.0043 max mem: 3957 +train: [11] [399/400] eta: 0:00:00 lr: 0.000166 loss: 3.0829 (3.0627) grad: 0.0732 (0.0740) time: 0.3237 data: 0.0040 max mem: 3957 +train: [11] Total time: 0:02:18 (0.3460 s / it) +train: [11] Summary: lr: 0.000166 loss: 3.0829 (3.0627) grad: 0.0732 (0.0740) +eval (validation): [11] [ 0/85] eta: 0:04:43 time: 3.3308 data: 3.0888 max mem: 3957 +eval (validation): [11] [20/85] eta: 0:00:31 time: 0.3413 data: 0.0060 max mem: 3957 +eval (validation): [11] [40/85] eta: 0:00:18 time: 0.3142 data: 0.0039 max mem: 3957 +eval (validation): [11] [60/85] eta: 0:00:09 time: 0.3150 data: 0.0035 max mem: 3957 +eval (validation): [11] [80/85] eta: 0:00:01 time: 0.3029 data: 0.0043 max mem: 3957 +eval (validation): [11] [84/85] eta: 0:00:00 time: 0.2966 data: 0.0041 max mem: 3957 +eval (validation): [11] Total time: 0:00:30 (0.3564 s / it) +cv: [11] best hparam: (19, 1.0) (042) ('042_lr1.9e+01_wd1.0e+00') loss: 3.045 acc: 0.113 f1: 0.065 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__linear/checkpoint-last.pth +train: [12] [ 0/400] eta: 0:21:20 lr: nan time: 3.2017 data: 2.9928 max mem: 3957 +train: [12] [ 20/400] eta: 0:02:57 lr: 0.000164 loss: 3.0450 (3.0511) grad: 0.0723 (0.0740) time: 0.3310 data: 0.0044 max mem: 3957 +train: [12] [ 40/400] eta: 0:02:24 lr: 0.000163 loss: 3.0559 (3.0585) grad: 0.0744 (0.0732) time: 0.3345 data: 0.0038 max mem: 3957 +train: [12] [ 60/400] eta: 0:02:08 lr: 0.000161 loss: 3.0625 (3.0656) grad: 0.0744 (0.0744) time: 0.3275 data: 0.0043 max mem: 3957 +train: [12] [ 80/400] eta: 0:01:57 lr: 0.000160 loss: 3.0694 (3.0627) grad: 0.0745 (0.0745) time: 0.3352 data: 0.0044 max mem: 3957 +train: [12] [100/400] eta: 0:01:48 lr: 0.000158 loss: 3.0652 (3.0641) grad: 0.0745 (0.0744) time: 0.3338 data: 0.0043 max mem: 3957 +train: [12] [120/400] eta: 0:01:39 lr: 0.000156 loss: 3.0536 (3.0611) grad: 0.0723 (0.0739) time: 0.3280 data: 0.0042 max mem: 3957 +train: [12] [140/400] eta: 0:01:31 lr: 0.000155 loss: 3.0468 (3.0586) grad: 0.0723 (0.0741) time: 0.3311 data: 0.0042 max mem: 3957 +train: [12] [160/400] eta: 0:01:24 lr: 0.000153 loss: 3.0468 (3.0556) grad: 0.0754 (0.0740) time: 0.3377 data: 0.0042 max mem: 3957 +train: [12] [180/400] eta: 0:01:16 lr: 0.000152 loss: 3.0340 (3.0532) grad: 0.0730 (0.0741) time: 0.3429 data: 0.0044 max mem: 3957 +train: [12] [200/400] eta: 0:01:09 lr: 0.000150 loss: 3.0340 (3.0530) grad: 0.0713 (0.0737) time: 0.3356 data: 0.0041 max mem: 3957 +train: [12] [220/400] eta: 0:01:02 lr: 0.000149 loss: 3.0563 (3.0533) grad: 0.0709 (0.0735) time: 0.3326 data: 0.0039 max mem: 3957 +train: [12] [240/400] eta: 0:00:55 lr: 0.000147 loss: 3.0436 (3.0513) grad: 0.0709 (0.0735) time: 0.3457 data: 0.0043 max mem: 3957 +train: [12] [260/400] eta: 0:00:48 lr: 0.000145 loss: 3.0436 (3.0515) grad: 0.0717 (0.0735) time: 0.3397 data: 0.0040 max mem: 3957 +train: [12] [280/400] eta: 0:00:41 lr: 0.000144 loss: 3.0584 (3.0524) grad: 0.0687 (0.0732) time: 0.3642 data: 0.0046 max mem: 3957 +train: [12] [300/400] eta: 0:00:34 lr: 0.000142 loss: 3.0582 (3.0519) grad: 0.0682 (0.0731) time: 0.3358 data: 0.0041 max mem: 3957 +train: [12] [320/400] eta: 0:00:27 lr: 0.000141 loss: 3.0582 (3.0525) grad: 0.0721 (0.0729) time: 0.3375 data: 0.0035 max mem: 3957 +train: [12] [340/400] eta: 0:00:20 lr: 0.000139 loss: 3.0610 (3.0541) grad: 0.0711 (0.0728) time: 0.3345 data: 0.0038 max mem: 3957 +train: [12] [360/400] eta: 0:00:13 lr: 0.000138 loss: 3.0609 (3.0536) grad: 0.0726 (0.0730) time: 0.3412 data: 0.0035 max mem: 3957 +train: [12] [380/400] eta: 0:00:06 lr: 0.000136 loss: 3.0607 (3.0544) grad: 0.0711 (0.0730) time: 0.3346 data: 0.0038 max mem: 3957 +train: [12] [399/400] eta: 0:00:00 lr: 0.000134 loss: 3.0672 (3.0553) grad: 0.0702 (0.0730) time: 0.3543 data: 0.0036 max mem: 3957 +train: [12] Total time: 0:02:18 (0.3453 s / it) +train: [12] Summary: lr: 0.000134 loss: 3.0672 (3.0553) grad: 0.0702 (0.0730) +eval (validation): [12] [ 0/85] eta: 0:04:47 time: 3.3882 data: 3.1496 max mem: 3957 +eval (validation): [12] [20/85] eta: 0:00:37 time: 0.4335 data: 0.0231 max mem: 3957 +eval (validation): [12] [40/85] eta: 0:00:20 time: 0.3343 data: 0.0043 max mem: 3957 +eval (validation): [12] [60/85] eta: 0:00:10 time: 0.3061 data: 0.0039 max mem: 3957 +eval (validation): [12] [80/85] eta: 0:00:01 time: 0.3224 data: 0.0036 max mem: 3957 +eval (validation): [12] [84/85] eta: 0:00:00 time: 0.3115 data: 0.0036 max mem: 3957 +eval (validation): [12] Total time: 0:00:32 (0.3867 s / it) +cv: [12] best hparam: (8.3, 1.0) (037) ('037_lr8.3e+00_wd1.0e+00') loss: 3.038 acc: 0.109 f1: 0.066 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__linear/checkpoint-last.pth +train: [13] [ 0/400] eta: 0:22:30 lr: nan time: 3.3757 data: 3.1204 max mem: 3957 +train: [13] [ 20/400] eta: 0:03:00 lr: 0.000133 loss: 3.0470 (3.0577) grad: 0.0770 (0.0774) time: 0.3288 data: 0.0043 max mem: 3957 +train: [13] [ 40/400] eta: 0:02:26 lr: 0.000131 loss: 3.0492 (3.0527) grad: 0.0753 (0.0749) time: 0.3368 data: 0.0040 max mem: 3957 +train: [13] [ 60/400] eta: 0:02:11 lr: 0.000130 loss: 3.0564 (3.0600) grad: 0.0753 (0.0752) time: 0.3495 data: 0.0048 max mem: 3957 +train: [13] [ 80/400] eta: 0:02:00 lr: 0.000128 loss: 3.0564 (3.0589) grad: 0.0765 (0.0747) time: 0.3371 data: 0.0032 max mem: 3957 +train: [13] [100/400] eta: 0:01:50 lr: 0.000127 loss: 3.0520 (3.0581) grad: 0.0779 (0.0747) time: 0.3433 data: 0.0039 max mem: 3957 +train: [13] [120/400] eta: 0:01:41 lr: 0.000125 loss: 3.0470 (3.0549) grad: 0.0735 (0.0746) time: 0.3359 data: 0.0040 max mem: 3957 +train: [13] [140/400] eta: 0:01:33 lr: 0.000124 loss: 3.0533 (3.0543) grad: 0.0736 (0.0747) time: 0.3376 data: 0.0041 max mem: 3957 +train: [13] [160/400] eta: 0:01:25 lr: 0.000122 loss: 3.0533 (3.0544) grad: 0.0751 (0.0744) time: 0.3335 data: 0.0043 max mem: 3957 +train: [13] [180/400] eta: 0:01:17 lr: 0.000120 loss: 3.0492 (3.0520) grad: 0.0707 (0.0739) time: 0.3287 data: 0.0037 max mem: 3957 +train: [13] [200/400] eta: 0:01:10 lr: 0.000119 loss: 3.0478 (3.0509) grad: 0.0683 (0.0734) time: 0.3370 data: 0.0043 max mem: 3957 +train: [13] [220/400] eta: 0:01:02 lr: 0.000117 loss: 3.0530 (3.0499) grad: 0.0683 (0.0732) time: 0.3256 data: 0.0037 max mem: 3957 +train: [13] [240/400] eta: 0:00:56 lr: 0.000116 loss: 3.0616 (3.0511) grad: 0.0721 (0.0734) time: 0.3654 data: 0.0041 max mem: 3957 +train: [13] [260/400] eta: 0:00:48 lr: 0.000114 loss: 3.0682 (3.0516) grad: 0.0724 (0.0732) time: 0.3201 data: 0.0037 max mem: 3957 +train: [13] [280/400] eta: 0:00:41 lr: 0.000113 loss: 3.0682 (3.0522) grad: 0.0724 (0.0733) time: 0.3501 data: 0.0043 max mem: 3957 +train: [13] [300/400] eta: 0:00:34 lr: 0.000111 loss: 3.0493 (3.0518) grad: 0.0732 (0.0733) time: 0.3355 data: 0.0042 max mem: 3957 +train: [13] [320/400] eta: 0:00:27 lr: 0.000110 loss: 3.0421 (3.0508) grad: 0.0727 (0.0732) time: 0.3352 data: 0.0041 max mem: 3957 +train: [13] [340/400] eta: 0:00:20 lr: 0.000108 loss: 3.0471 (3.0507) grad: 0.0700 (0.0730) time: 0.3288 data: 0.0040 max mem: 3957 +train: [13] [360/400] eta: 0:00:13 lr: 0.000107 loss: 3.0434 (3.0498) grad: 0.0725 (0.0730) time: 0.3323 data: 0.0038 max mem: 3957 +train: [13] [380/400] eta: 0:00:06 lr: 0.000105 loss: 3.0203 (3.0497) grad: 0.0727 (0.0731) time: 0.3346 data: 0.0038 max mem: 3957 +train: [13] [399/400] eta: 0:00:00 lr: 0.000104 loss: 3.0203 (3.0490) grad: 0.0733 (0.0731) time: 0.3329 data: 0.0034 max mem: 3957 +train: [13] Total time: 0:02:17 (0.3443 s / it) +train: [13] Summary: lr: 0.000104 loss: 3.0203 (3.0490) grad: 0.0733 (0.0731) +eval (validation): [13] [ 0/85] eta: 0:04:46 time: 3.3678 data: 3.1596 max mem: 3957 +eval (validation): [13] [20/85] eta: 0:00:34 time: 0.3814 data: 0.0170 max mem: 3957 +eval (validation): [13] [40/85] eta: 0:00:18 time: 0.3114 data: 0.0042 max mem: 3957 +eval (validation): [13] [60/85] eta: 0:00:09 time: 0.3284 data: 0.0045 max mem: 3957 +eval (validation): [13] [80/85] eta: 0:00:01 time: 0.3116 data: 0.0042 max mem: 3957 +eval (validation): [13] [84/85] eta: 0:00:00 time: 0.3016 data: 0.0040 max mem: 3957 +eval (validation): [13] Total time: 0:00:31 (0.3706 s / it) +cv: [13] best hparam: (9.8, 1.0) (038) ('038_lr9.8e+00_wd1.0e+00') loss: 3.047 acc: 0.110 f1: 0.057 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__linear/checkpoint-last.pth +train: [14] [ 0/400] eta: 0:22:21 lr: nan time: 3.3527 data: 3.1398 max mem: 3957 +train: [14] [ 20/400] eta: 0:03:01 lr: 0.000102 loss: 3.0525 (3.0569) grad: 0.0747 (0.0737) time: 0.3344 data: 0.0044 max mem: 3957 +train: [14] [ 40/400] eta: 0:02:27 lr: 0.000101 loss: 3.0525 (3.0554) grad: 0.0716 (0.0712) time: 0.3367 data: 0.0043 max mem: 3957 +train: [14] [ 60/400] eta: 0:02:13 lr: 0.000099 loss: 3.0676 (3.0630) grad: 0.0702 (0.0725) time: 0.3584 data: 0.0039 max mem: 3957 +train: [14] [ 80/400] eta: 0:02:01 lr: 0.000098 loss: 3.0518 (3.0526) grad: 0.0702 (0.0720) time: 0.3422 data: 0.0039 max mem: 3957 +train: [14] [100/400] eta: 0:01:51 lr: 0.000096 loss: 3.0209 (3.0491) grad: 0.0696 (0.0724) time: 0.3433 data: 0.0044 max mem: 3957 +train: [14] [120/400] eta: 0:01:42 lr: 0.000095 loss: 3.0286 (3.0483) grad: 0.0719 (0.0721) time: 0.3298 data: 0.0043 max mem: 3957 +train: [14] [140/400] eta: 0:01:33 lr: 0.000093 loss: 3.0341 (3.0445) grad: 0.0689 (0.0720) time: 0.3301 data: 0.0040 max mem: 3957 +train: [14] [160/400] eta: 0:01:26 lr: 0.000092 loss: 3.0272 (3.0447) grad: 0.0730 (0.0724) time: 0.3600 data: 0.0040 max mem: 3957 +train: [14] [180/400] eta: 0:01:19 lr: 0.000090 loss: 3.0627 (3.0467) grad: 0.0742 (0.0727) time: 0.3477 data: 0.0042 max mem: 3957 +train: [14] [200/400] eta: 0:01:11 lr: 0.000089 loss: 3.0556 (3.0478) grad: 0.0742 (0.0728) time: 0.3550 data: 0.0041 max mem: 3957 +train: [14] [220/400] eta: 0:01:04 lr: 0.000088 loss: 3.0481 (3.0481) grad: 0.0717 (0.0725) time: 0.3550 data: 0.0045 max mem: 3957 +train: [14] [240/400] eta: 0:00:57 lr: 0.000086 loss: 3.0332 (3.0463) grad: 0.0684 (0.0725) time: 0.3523 data: 0.0041 max mem: 3957 +train: [14] [260/400] eta: 0:00:49 lr: 0.000085 loss: 3.0245 (3.0447) grad: 0.0722 (0.0724) time: 0.3352 data: 0.0042 max mem: 3957 +train: [14] [280/400] eta: 0:00:42 lr: 0.000083 loss: 3.0474 (3.0450) grad: 0.0720 (0.0724) time: 0.3542 data: 0.0044 max mem: 3957 +train: [14] [300/400] eta: 0:00:35 lr: 0.000082 loss: 3.0474 (3.0451) grad: 0.0720 (0.0724) time: 0.3549 data: 0.0043 max mem: 3957 +train: [14] [320/400] eta: 0:00:28 lr: 0.000081 loss: 3.0453 (3.0447) grad: 0.0733 (0.0726) time: 0.3473 data: 0.0041 max mem: 3957 +train: [14] [340/400] eta: 0:00:21 lr: 0.000079 loss: 3.0523 (3.0449) grad: 0.0733 (0.0725) time: 0.3402 data: 0.0041 max mem: 3957 +train: [14] [360/400] eta: 0:00:14 lr: 0.000078 loss: 3.0488 (3.0449) grad: 0.0737 (0.0725) time: 0.3352 data: 0.0043 max mem: 3957 +train: [14] [380/400] eta: 0:00:07 lr: 0.000076 loss: 3.0409 (3.0448) grad: 0.0743 (0.0726) time: 0.3384 data: 0.0041 max mem: 3957 +train: [14] [399/400] eta: 0:00:00 lr: 0.000075 loss: 3.0503 (3.0462) grad: 0.0734 (0.0726) time: 0.3409 data: 0.0043 max mem: 3957 +train: [14] Total time: 0:02:20 (0.3524 s / it) +train: [14] Summary: lr: 0.000075 loss: 3.0503 (3.0462) grad: 0.0734 (0.0726) +eval (validation): [14] [ 0/85] eta: 0:04:46 time: 3.3703 data: 3.1593 max mem: 3957 +eval (validation): [14] [20/85] eta: 0:00:31 time: 0.3396 data: 0.0048 max mem: 3957 +eval (validation): [14] [40/85] eta: 0:00:19 time: 0.3659 data: 0.0050 max mem: 3957 +eval (validation): [14] [60/85] eta: 0:00:09 time: 0.3402 data: 0.0048 max mem: 3957 +eval (validation): [14] [80/85] eta: 0:00:01 time: 0.3111 data: 0.0046 max mem: 3957 +eval (validation): [14] [84/85] eta: 0:00:00 time: 0.3039 data: 0.0040 max mem: 3957 +eval (validation): [14] Total time: 0:00:31 (0.3764 s / it) +cv: [14] best hparam: (50, 1.0) (048) ('048_lr5.0e+01_wd1.0e+00') loss: 3.046 acc: 0.110 f1: 0.068 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__linear/checkpoint-last.pth +train: [15] [ 0/400] eta: 0:22:38 lr: nan time: 3.3955 data: 3.1862 max mem: 3957 +train: [15] [ 20/400] eta: 0:03:07 lr: 0.000074 loss: 3.0197 (3.0333) grad: 0.0713 (0.0744) time: 0.3481 data: 0.0053 max mem: 3957 +train: [15] [ 40/400] eta: 0:02:33 lr: 0.000072 loss: 3.0300 (3.0367) grad: 0.0733 (0.0747) time: 0.3561 data: 0.0046 max mem: 3957 +train: [15] [ 60/400] eta: 0:02:17 lr: 0.000071 loss: 3.0263 (3.0316) grad: 0.0733 (0.0740) time: 0.3553 data: 0.0037 max mem: 3957 +train: [15] [ 80/400] eta: 0:02:06 lr: 0.000070 loss: 3.0252 (3.0328) grad: 0.0682 (0.0725) time: 0.3718 data: 0.0045 max mem: 3957 +train: [15] [100/400] eta: 0:01:54 lr: 0.000068 loss: 3.0283 (3.0352) grad: 0.0677 (0.0730) time: 0.3340 data: 0.0043 max mem: 3957 +train: [15] [120/400] eta: 0:01:45 lr: 0.000067 loss: 3.0412 (3.0343) grad: 0.0704 (0.0726) time: 0.3346 data: 0.0043 max mem: 3957 +train: [15] [140/400] eta: 0:01:36 lr: 0.000066 loss: 3.0255 (3.0335) grad: 0.0731 (0.0731) time: 0.3449 data: 0.0040 max mem: 3957 +train: [15] [160/400] eta: 0:01:28 lr: 0.000064 loss: 3.0297 (3.0349) grad: 0.0731 (0.0729) time: 0.3443 data: 0.0042 max mem: 3957 +train: [15] [180/400] eta: 0:01:19 lr: 0.000063 loss: 3.0565 (3.0372) grad: 0.0694 (0.0729) time: 0.3278 data: 0.0040 max mem: 3957 +train: [15] [200/400] eta: 0:01:12 lr: 0.000062 loss: 3.0596 (3.0401) grad: 0.0702 (0.0727) time: 0.3499 data: 0.0041 max mem: 3957 +train: [15] [220/400] eta: 0:01:05 lr: 0.000061 loss: 3.0572 (3.0384) grad: 0.0671 (0.0721) time: 0.3541 data: 0.0044 max mem: 3957 +train: [15] [240/400] eta: 0:00:57 lr: 0.000059 loss: 3.0426 (3.0401) grad: 0.0696 (0.0724) time: 0.3570 data: 0.0042 max mem: 3957 +train: [15] [260/400] eta: 0:00:50 lr: 0.000058 loss: 3.0618 (3.0407) grad: 0.0717 (0.0723) time: 0.3502 data: 0.0041 max mem: 3957 +train: [15] [280/400] eta: 0:00:43 lr: 0.000057 loss: 3.0444 (3.0407) grad: 0.0711 (0.0725) time: 0.3428 data: 0.0041 max mem: 3957 +train: [15] [300/400] eta: 0:00:35 lr: 0.000056 loss: 3.0426 (3.0409) grad: 0.0696 (0.0723) time: 0.3375 data: 0.0039 max mem: 3957 +train: [15] [320/400] eta: 0:00:28 lr: 0.000054 loss: 3.0524 (3.0422) grad: 0.0711 (0.0724) time: 0.3391 data: 0.0039 max mem: 3957 +train: [15] [340/400] eta: 0:00:21 lr: 0.000053 loss: 3.0551 (3.0409) grad: 0.0745 (0.0725) time: 0.3397 data: 0.0040 max mem: 3957 +train: [15] [360/400] eta: 0:00:14 lr: 0.000052 loss: 3.0416 (3.0414) grad: 0.0720 (0.0726) time: 0.3564 data: 0.0044 max mem: 3957 +train: [15] [380/400] eta: 0:00:07 lr: 0.000051 loss: 3.0554 (3.0422) grad: 0.0696 (0.0723) time: 0.3460 data: 0.0037 max mem: 3957 +train: [15] [399/400] eta: 0:00:00 lr: 0.000050 loss: 3.0527 (3.0425) grad: 0.0697 (0.0723) time: 0.3351 data: 0.0042 max mem: 3957 +train: [15] Total time: 0:02:21 (0.3541 s / it) +train: [15] Summary: lr: 0.000050 loss: 3.0527 (3.0425) grad: 0.0697 (0.0723) +eval (validation): [15] [ 0/85] eta: 0:04:39 time: 3.2862 data: 3.0187 max mem: 3957 +eval (validation): [15] [20/85] eta: 0:00:33 time: 0.3844 data: 0.0045 max mem: 3957 +eval (validation): [15] [40/85] eta: 0:00:19 time: 0.3303 data: 0.0047 max mem: 3957 +eval (validation): [15] [60/85] eta: 0:00:10 time: 0.3479 data: 0.0046 max mem: 3957 +eval (validation): [15] [80/85] eta: 0:00:01 time: 0.3437 data: 0.0044 max mem: 3957 +eval (validation): [15] [84/85] eta: 0:00:00 time: 0.3266 data: 0.0042 max mem: 3957 +eval (validation): [15] Total time: 0:00:32 (0.3867 s / it) +cv: [15] best hparam: (22, 1.0) (043) ('043_lr2.2e+01_wd1.0e+00') loss: 3.017 acc: 0.114 f1: 0.067 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__linear/checkpoint-last.pth +train: [16] [ 0/400] eta: 0:21:31 lr: nan time: 3.2277 data: 3.0216 max mem: 3957 +train: [16] [ 20/400] eta: 0:03:11 lr: 0.000048 loss: 3.0464 (3.0584) grad: 0.0684 (0.0721) time: 0.3686 data: 0.0050 max mem: 3957 +train: [16] [ 40/400] eta: 0:02:34 lr: 0.000047 loss: 3.0551 (3.0540) grad: 0.0672 (0.0692) time: 0.3489 data: 0.0037 max mem: 3957 +train: [16] [ 60/400] eta: 0:02:16 lr: 0.000046 loss: 3.0233 (3.0398) grad: 0.0684 (0.0691) time: 0.3427 data: 0.0039 max mem: 3957 +train: [16] [ 80/400] eta: 0:02:03 lr: 0.000045 loss: 3.0330 (3.0404) grad: 0.0685 (0.0687) time: 0.3427 data: 0.0040 max mem: 3957 +train: [16] [100/400] eta: 0:01:52 lr: 0.000044 loss: 3.0613 (3.0440) grad: 0.0685 (0.0695) time: 0.3334 data: 0.0039 max mem: 3957 +train: [16] [120/400] eta: 0:01:43 lr: 0.000043 loss: 3.0411 (3.0410) grad: 0.0710 (0.0700) time: 0.3341 data: 0.0041 max mem: 3957 +train: [16] [140/400] eta: 0:01:35 lr: 0.000042 loss: 3.0132 (3.0390) grad: 0.0734 (0.0713) time: 0.3497 data: 0.0041 max mem: 3957 +train: [16] [160/400] eta: 0:01:27 lr: 0.000041 loss: 3.0239 (3.0392) grad: 0.0746 (0.0711) time: 0.3405 data: 0.0040 max mem: 3957 +train: [16] [180/400] eta: 0:01:19 lr: 0.000040 loss: 3.0306 (3.0384) grad: 0.0691 (0.0712) time: 0.3354 data: 0.0040 max mem: 3957 +train: [16] [200/400] eta: 0:01:11 lr: 0.000039 loss: 3.0445 (3.0411) grad: 0.0698 (0.0711) time: 0.3380 data: 0.0040 max mem: 3957 +train: [16] [220/400] eta: 0:01:04 lr: 0.000038 loss: 3.0519 (3.0418) grad: 0.0686 (0.0709) time: 0.3431 data: 0.0038 max mem: 3957 +train: [16] [240/400] eta: 0:00:56 lr: 0.000036 loss: 3.0397 (3.0411) grad: 0.0698 (0.0712) time: 0.3426 data: 0.0040 max mem: 3957 +train: [16] [260/400] eta: 0:00:49 lr: 0.000035 loss: 3.0379 (3.0418) grad: 0.0719 (0.0713) time: 0.3346 data: 0.0041 max mem: 3957 +train: [16] [280/400] eta: 0:00:42 lr: 0.000034 loss: 3.0406 (3.0414) grad: 0.0719 (0.0714) time: 0.3503 data: 0.0041 max mem: 3957 +train: [16] [300/400] eta: 0:00:35 lr: 0.000033 loss: 3.0320 (3.0404) grad: 0.0723 (0.0716) time: 0.3387 data: 0.0043 max mem: 3957 +train: [16] [320/400] eta: 0:00:28 lr: 0.000032 loss: 3.0223 (3.0398) grad: 0.0721 (0.0715) time: 0.3316 data: 0.0038 max mem: 3957 +train: [16] [340/400] eta: 0:00:21 lr: 0.000031 loss: 3.0397 (3.0408) grad: 0.0696 (0.0715) time: 0.3347 data: 0.0039 max mem: 3957 +train: [16] [360/400] eta: 0:00:13 lr: 0.000031 loss: 3.0564 (3.0421) grad: 0.0696 (0.0717) time: 0.3368 data: 0.0043 max mem: 3957 +train: [16] [380/400] eta: 0:00:06 lr: 0.000030 loss: 3.0564 (3.0418) grad: 0.0727 (0.0717) time: 0.3311 data: 0.0040 max mem: 3957 +train: [16] [399/400] eta: 0:00:00 lr: 0.000029 loss: 3.0461 (3.0419) grad: 0.0704 (0.0716) time: 0.3420 data: 0.0037 max mem: 3957 +train: [16] Total time: 0:02:19 (0.3484 s / it) +train: [16] Summary: lr: 0.000029 loss: 3.0461 (3.0419) grad: 0.0704 (0.0716) +eval (validation): [16] [ 0/85] eta: 0:04:54 time: 3.4599 data: 3.2004 max mem: 3957 +eval (validation): [16] [20/85] eta: 0:00:32 time: 0.3507 data: 0.0231 max mem: 3957 +eval (validation): [16] [40/85] eta: 0:00:19 time: 0.3533 data: 0.0054 max mem: 3957 +eval (validation): [16] [60/85] eta: 0:00:10 time: 0.3453 data: 0.0038 max mem: 3957 +eval (validation): [16] [80/85] eta: 0:00:01 time: 0.3189 data: 0.0042 max mem: 3957 +eval (validation): [16] [84/85] eta: 0:00:00 time: 0.3113 data: 0.0041 max mem: 3957 +eval (validation): [16] Total time: 0:00:32 (0.3805 s / it) +cv: [16] best hparam: (26, 1.0) (044) ('044_lr2.6e+01_wd1.0e+00') loss: 3.019 acc: 0.114 f1: 0.063 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__linear/checkpoint-last.pth +train: [17] [ 0/400] eta: 0:22:49 lr: nan time: 3.4235 data: 3.1587 max mem: 3957 +train: [17] [ 20/400] eta: 0:03:26 lr: 0.000028 loss: 2.9945 (3.0140) grad: 0.0696 (0.0691) time: 0.4003 data: 0.0054 max mem: 3957 +train: [17] [ 40/400] eta: 0:02:40 lr: 0.000027 loss: 3.0078 (3.0101) grad: 0.0712 (0.0723) time: 0.3447 data: 0.0041 max mem: 3957 +train: [17] [ 60/400] eta: 0:02:19 lr: 0.000026 loss: 3.0223 (3.0187) grad: 0.0717 (0.0718) time: 0.3352 data: 0.0040 max mem: 3957 +train: [17] [ 80/400] eta: 0:02:05 lr: 0.000025 loss: 3.0336 (3.0225) grad: 0.0711 (0.0712) time: 0.3339 data: 0.0038 max mem: 3957 +train: [17] [100/400] eta: 0:01:54 lr: 0.000024 loss: 3.0285 (3.0199) grad: 0.0707 (0.0708) time: 0.3474 data: 0.0041 max mem: 3957 +train: [17] [120/400] eta: 0:01:45 lr: 0.000023 loss: 3.0285 (3.0225) grad: 0.0715 (0.0712) time: 0.3372 data: 0.0040 max mem: 3957 +train: [17] [140/400] eta: 0:01:36 lr: 0.000023 loss: 3.0479 (3.0281) grad: 0.0713 (0.0708) time: 0.3489 data: 0.0039 max mem: 3957 +train: [17] [160/400] eta: 0:01:28 lr: 0.000022 loss: 3.0452 (3.0285) grad: 0.0694 (0.0706) time: 0.3466 data: 0.0043 max mem: 3957 +train: [17] [180/400] eta: 0:01:20 lr: 0.000021 loss: 3.0292 (3.0277) grad: 0.0696 (0.0705) time: 0.3308 data: 0.0038 max mem: 3957 +train: [17] [200/400] eta: 0:01:12 lr: 0.000020 loss: 3.0350 (3.0293) grad: 0.0696 (0.0704) time: 0.3463 data: 0.0041 max mem: 3957 +train: [17] [220/400] eta: 0:01:05 lr: 0.000019 loss: 3.0350 (3.0300) grad: 0.0692 (0.0705) time: 0.3529 data: 0.0040 max mem: 3957 +train: [17] [240/400] eta: 0:00:57 lr: 0.000019 loss: 3.0265 (3.0304) grad: 0.0654 (0.0703) time: 0.3430 data: 0.0044 max mem: 3957 +train: [17] [260/400] eta: 0:00:50 lr: 0.000018 loss: 3.0255 (3.0298) grad: 0.0695 (0.0704) time: 0.3232 data: 0.0038 max mem: 3957 +train: [17] [280/400] eta: 0:00:42 lr: 0.000017 loss: 3.0292 (3.0316) grad: 0.0693 (0.0701) time: 0.3428 data: 0.0042 max mem: 3957 +train: [17] [300/400] eta: 0:00:35 lr: 0.000016 loss: 3.0541 (3.0328) grad: 0.0674 (0.0700) time: 0.3402 data: 0.0040 max mem: 3957 +train: [17] [320/400] eta: 0:00:28 lr: 0.000016 loss: 3.0467 (3.0333) grad: 0.0703 (0.0700) time: 0.3606 data: 0.0042 max mem: 3957 +train: [17] [340/400] eta: 0:00:21 lr: 0.000015 loss: 3.0194 (3.0317) grad: 0.0709 (0.0700) time: 0.3424 data: 0.0039 max mem: 3957 +train: [17] [360/400] eta: 0:00:14 lr: 0.000014 loss: 3.0180 (3.0324) grad: 0.0710 (0.0701) time: 0.3421 data: 0.0044 max mem: 3957 +train: [17] [380/400] eta: 0:00:07 lr: 0.000014 loss: 3.0437 (3.0325) grad: 0.0703 (0.0700) time: 0.3503 data: 0.0036 max mem: 3957 +train: [17] [399/400] eta: 0:00:00 lr: 0.000013 loss: 3.0296 (3.0329) grad: 0.0692 (0.0700) time: 0.3314 data: 0.0041 max mem: 3957 +train: [17] Total time: 0:02:21 (0.3530 s / it) +train: [17] Summary: lr: 0.000013 loss: 3.0296 (3.0329) grad: 0.0692 (0.0700) +eval (validation): [17] [ 0/85] eta: 0:04:41 time: 3.3174 data: 3.0720 max mem: 3957 +eval (validation): [17] [20/85] eta: 0:00:31 time: 0.3450 data: 0.0050 max mem: 3957 +eval (validation): [17] [40/85] eta: 0:00:18 time: 0.3315 data: 0.0040 max mem: 3957 +eval (validation): [17] [60/85] eta: 0:00:09 time: 0.3204 data: 0.0044 max mem: 3957 +eval (validation): [17] [80/85] eta: 0:00:01 time: 0.3126 data: 0.0042 max mem: 3957 +eval (validation): [17] [84/85] eta: 0:00:00 time: 0.3038 data: 0.0042 max mem: 3957 +eval (validation): [17] Total time: 0:00:30 (0.3645 s / it) +cv: [17] best hparam: (36, 1.0) (046) ('046_lr3.6e+01_wd1.0e+00') loss: 3.011 acc: 0.117 f1: 0.071 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__linear/checkpoint-best.pth +train: [18] [ 0/400] eta: 0:21:58 lr: nan time: 3.2963 data: 3.0352 max mem: 3957 +train: [18] [ 20/400] eta: 0:03:24 lr: 0.000012 loss: 3.0391 (3.0582) grad: 0.0650 (0.0639) time: 0.4005 data: 0.0048 max mem: 3957 +train: [18] [ 40/400] eta: 0:02:36 lr: 0.000012 loss: 3.0572 (3.0620) grad: 0.0689 (0.0676) time: 0.3261 data: 0.0040 max mem: 3957 +train: [18] [ 60/400] eta: 0:02:16 lr: 0.000011 loss: 3.0572 (3.0531) grad: 0.0702 (0.0693) time: 0.3362 data: 0.0040 max mem: 3957 +train: [18] [ 80/400] eta: 0:02:04 lr: 0.000011 loss: 3.0054 (3.0438) grad: 0.0707 (0.0694) time: 0.3463 data: 0.0039 max mem: 3957 +train: [18] [100/400] eta: 0:01:54 lr: 0.000010 loss: 3.0480 (3.0455) grad: 0.0707 (0.0698) time: 0.3482 data: 0.0043 max mem: 3957 +train: [18] [120/400] eta: 0:01:44 lr: 0.000009 loss: 3.0508 (3.0435) grad: 0.0713 (0.0710) time: 0.3358 data: 0.0043 max mem: 3957 +train: [18] [140/400] eta: 0:01:35 lr: 0.000009 loss: 3.0262 (3.0407) grad: 0.0719 (0.0708) time: 0.3379 data: 0.0035 max mem: 3957 +train: [18] [160/400] eta: 0:01:27 lr: 0.000008 loss: 3.0444 (3.0431) grad: 0.0704 (0.0709) time: 0.3369 data: 0.0041 max mem: 3957 +train: [18] [180/400] eta: 0:01:19 lr: 0.000008 loss: 3.0388 (3.0416) grad: 0.0697 (0.0709) time: 0.3429 data: 0.0034 max mem: 3957 +train: [18] [200/400] eta: 0:01:11 lr: 0.000007 loss: 3.0232 (3.0414) grad: 0.0683 (0.0709) time: 0.3392 data: 0.0045 max mem: 3957 +train: [18] [220/400] eta: 0:01:04 lr: 0.000007 loss: 3.0385 (3.0411) grad: 0.0683 (0.0709) time: 0.3349 data: 0.0038 max mem: 3957 +train: [18] [240/400] eta: 0:00:56 lr: 0.000006 loss: 3.0314 (3.0405) grad: 0.0713 (0.0711) time: 0.3329 data: 0.0042 max mem: 3957 +train: [18] [260/400] eta: 0:00:49 lr: 0.000006 loss: 3.0436 (3.0420) grad: 0.0693 (0.0709) time: 0.3260 data: 0.0035 max mem: 3957 +train: [18] [280/400] eta: 0:00:42 lr: 0.000006 loss: 3.0361 (3.0408) grad: 0.0664 (0.0707) time: 0.3543 data: 0.0040 max mem: 3957 +train: [18] [300/400] eta: 0:00:35 lr: 0.000005 loss: 3.0201 (3.0376) grad: 0.0680 (0.0711) time: 0.3513 data: 0.0041 max mem: 3957 +train: [18] [320/400] eta: 0:00:28 lr: 0.000005 loss: 3.0125 (3.0381) grad: 0.0732 (0.0713) time: 0.3348 data: 0.0040 max mem: 3957 +train: [18] [340/400] eta: 0:00:21 lr: 0.000004 loss: 3.0323 (3.0377) grad: 0.0714 (0.0712) time: 0.3466 data: 0.0041 max mem: 3957 +train: [18] [360/400] eta: 0:00:14 lr: 0.000004 loss: 3.0310 (3.0364) grad: 0.0684 (0.0712) time: 0.3401 data: 0.0045 max mem: 3957 +train: [18] [380/400] eta: 0:00:06 lr: 0.000004 loss: 3.0379 (3.0373) grad: 0.0699 (0.0712) time: 0.3309 data: 0.0043 max mem: 3957 +train: [18] [399/400] eta: 0:00:00 lr: 0.000003 loss: 3.0432 (3.0364) grad: 0.0694 (0.0711) time: 0.3353 data: 0.0042 max mem: 3957 +train: [18] Total time: 0:02:19 (0.3495 s / it) +train: [18] Summary: lr: 0.000003 loss: 3.0432 (3.0364) grad: 0.0694 (0.0711) +eval (validation): [18] [ 0/85] eta: 0:04:44 time: 3.3460 data: 3.1351 max mem: 3957 +eval (validation): [18] [20/85] eta: 0:00:31 time: 0.3441 data: 0.0058 max mem: 3957 +eval (validation): [18] [40/85] eta: 0:00:19 time: 0.3618 data: 0.0040 max mem: 3957 +eval (validation): [18] [60/85] eta: 0:00:09 time: 0.3292 data: 0.0045 max mem: 3957 +eval (validation): [18] [80/85] eta: 0:00:01 time: 0.3183 data: 0.0043 max mem: 3957 +eval (validation): [18] [84/85] eta: 0:00:00 time: 0.3133 data: 0.0043 max mem: 3957 +eval (validation): [18] Total time: 0:00:31 (0.3758 s / it) +cv: [18] best hparam: (50, 1.0) (048) ('048_lr5.0e+01_wd1.0e+00') loss: 3.006 acc: 0.116 f1: 0.068 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__linear/checkpoint-last.pth +train: [19] [ 0/400] eta: 0:21:51 lr: nan time: 3.2778 data: 3.0630 max mem: 3957 +train: [19] [ 20/400] eta: 0:03:03 lr: 0.000003 loss: 3.0512 (3.0618) grad: 0.0632 (0.0662) time: 0.3420 data: 0.0058 max mem: 3957 +train: [19] [ 40/400] eta: 0:02:27 lr: 0.000003 loss: 3.0366 (3.0435) grad: 0.0691 (0.0685) time: 0.3325 data: 0.0035 max mem: 3957 +train: [19] [ 60/400] eta: 0:02:12 lr: 0.000002 loss: 3.0436 (3.0438) grad: 0.0708 (0.0692) time: 0.3508 data: 0.0032 max mem: 3957 +train: [19] [ 80/400] eta: 0:02:00 lr: 0.000002 loss: 3.0447 (3.0426) grad: 0.0728 (0.0701) time: 0.3343 data: 0.0037 max mem: 3957 +train: [19] [100/400] eta: 0:01:51 lr: 0.000002 loss: 3.0371 (3.0422) grad: 0.0747 (0.0706) time: 0.3492 data: 0.0039 max mem: 3957 +train: [19] [120/400] eta: 0:01:41 lr: 0.000002 loss: 3.0363 (3.0426) grad: 0.0691 (0.0698) time: 0.3190 data: 0.0037 max mem: 3957 +train: [19] [140/400] eta: 0:01:33 lr: 0.000001 loss: 3.0363 (3.0430) grad: 0.0674 (0.0698) time: 0.3420 data: 0.0042 max mem: 3957 +train: [19] [160/400] eta: 0:01:25 lr: 0.000001 loss: 3.0216 (3.0392) grad: 0.0670 (0.0698) time: 0.3437 data: 0.0039 max mem: 3957 +train: [19] [180/400] eta: 0:01:18 lr: 0.000001 loss: 3.0252 (3.0397) grad: 0.0666 (0.0696) time: 0.3335 data: 0.0044 max mem: 3957 +train: [19] [200/400] eta: 0:01:10 lr: 0.000001 loss: 3.0401 (3.0395) grad: 0.0693 (0.0703) time: 0.3268 data: 0.0036 max mem: 3957 +train: [19] [220/400] eta: 0:01:03 lr: 0.000001 loss: 3.0149 (3.0376) grad: 0.0707 (0.0701) time: 0.3309 data: 0.0041 max mem: 3957 +train: [19] [240/400] eta: 0:00:55 lr: 0.000001 loss: 3.0154 (3.0372) grad: 0.0674 (0.0704) time: 0.3138 data: 0.0038 max mem: 3957 +train: [19] [260/400] eta: 0:00:48 lr: 0.000000 loss: 3.0514 (3.0391) grad: 0.0710 (0.0703) time: 0.3290 data: 0.0042 max mem: 3957 +train: [19] [280/400] eta: 0:00:41 lr: 0.000000 loss: 3.0389 (3.0388) grad: 0.0728 (0.0705) time: 0.3285 data: 0.0040 max mem: 3957 +train: [19] [300/400] eta: 0:00:34 lr: 0.000000 loss: 3.0376 (3.0396) grad: 0.0728 (0.0705) time: 0.3408 data: 0.0040 max mem: 3957 +train: [19] [320/400] eta: 0:00:27 lr: 0.000000 loss: 3.0372 (3.0388) grad: 0.0688 (0.0706) time: 0.3471 data: 0.0042 max mem: 3957 +train: [19] [340/400] eta: 0:00:20 lr: 0.000000 loss: 3.0075 (3.0372) grad: 0.0688 (0.0706) time: 0.3286 data: 0.0044 max mem: 3957 +train: [19] [360/400] eta: 0:00:13 lr: 0.000000 loss: 3.0420 (3.0384) grad: 0.0685 (0.0706) time: 0.3272 data: 0.0043 max mem: 3957 +train: [19] [380/400] eta: 0:00:06 lr: 0.000000 loss: 3.0573 (3.0390) grad: 0.0706 (0.0706) time: 0.3324 data: 0.0041 max mem: 3957 +train: [19] [399/400] eta: 0:00:00 lr: 0.000000 loss: 3.0488 (3.0387) grad: 0.0731 (0.0708) time: 0.3441 data: 0.0038 max mem: 3957 +train: [19] Total time: 0:02:16 (0.3423 s / it) +train: [19] Summary: lr: 0.000000 loss: 3.0488 (3.0387) grad: 0.0731 (0.0708) +eval (validation): [19] [ 0/85] eta: 0:05:58 time: 4.2192 data: 3.9396 max mem: 3957 +eval (validation): [19] [20/85] eta: 0:00:34 time: 0.3443 data: 0.0031 max mem: 3957 +eval (validation): [19] [40/85] eta: 0:00:20 time: 0.3583 data: 0.0046 max mem: 3957 +eval (validation): [19] [60/85] eta: 0:00:10 time: 0.3110 data: 0.0043 max mem: 3957 +eval (validation): [19] [80/85] eta: 0:00:01 time: 0.3099 data: 0.0046 max mem: 3957 +eval (validation): [19] [84/85] eta: 0:00:00 time: 0.3003 data: 0.0043 max mem: 3957 +eval (validation): [19] Total time: 0:00:32 (0.3782 s / it) +cv: [19] best hparam: (36, 1.0) (046) ('046_lr3.6e+01_wd1.0e+00') loss: 3.008 acc: 0.113 f1: 0.065 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__linear/checkpoint-last.pth +evaluating last checkpoint: experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__linear/checkpoint-last.pth +eval model info: +{"score": 0.11332595053525286, "hparam": [36, 1.0], "hparam_id": 46, "epoch": 19, "is_best": false, "best_score": 0.11720191952750092} +eval (train): [20] [ 0/509] eta: 0:28:28 time: 3.3561 data: 3.1474 max mem: 3957 +eval (train): [20] [ 20/509] eta: 0:03:52 time: 0.3323 data: 0.0044 max mem: 3957 +eval (train): [20] [ 40/509] eta: 0:03:12 time: 0.3416 data: 0.0046 max mem: 3957 +eval (train): [20] [ 60/509] eta: 0:02:51 time: 0.3220 data: 0.0044 max mem: 3957 +eval (train): [20] [ 80/509] eta: 0:02:39 time: 0.3411 data: 0.0045 max mem: 3957 +eval (train): [20] [100/509] eta: 0:02:28 time: 0.3240 data: 0.0045 max mem: 3957 +eval (train): [20] [120/509] eta: 0:02:18 time: 0.3239 data: 0.0040 max mem: 3957 +eval (train): [20] [140/509] eta: 0:02:09 time: 0.3198 data: 0.0044 max mem: 3957 +eval (train): [20] [160/509] eta: 0:02:01 time: 0.3329 data: 0.0043 max mem: 3957 +eval (train): [20] [180/509] eta: 0:01:53 time: 0.3207 data: 0.0042 max mem: 3957 +eval (train): [20] [200/509] eta: 0:01:46 time: 0.3294 data: 0.0045 max mem: 3957 +eval (train): [20] [220/509] eta: 0:01:39 time: 0.3304 data: 0.0040 max mem: 3957 +eval (train): [20] [240/509] eta: 0:01:32 time: 0.3395 data: 0.0042 max mem: 3957 +eval (train): [20] [260/509] eta: 0:01:25 time: 0.3365 data: 0.0043 max mem: 3957 +eval (train): [20] [280/509] eta: 0:01:18 time: 0.3264 data: 0.0047 max mem: 3957 +eval (train): [20] [300/509] eta: 0:01:11 time: 0.3719 data: 0.0048 max mem: 3957 +eval (train): [20] [320/509] eta: 0:01:04 time: 0.3388 data: 0.0045 max mem: 3957 +eval (train): [20] [340/509] eta: 0:00:57 time: 0.3427 data: 0.0048 max mem: 3957 +eval (train): [20] [360/509] eta: 0:00:51 time: 0.3592 data: 0.0047 max mem: 3957 +eval (train): [20] [380/509] eta: 0:00:44 time: 0.3374 data: 0.0043 max mem: 3957 +eval (train): [20] [400/509] eta: 0:00:37 time: 0.3433 data: 0.0049 max mem: 3957 +eval (train): [20] [420/509] eta: 0:00:30 time: 0.3128 data: 0.0045 max mem: 3957 +eval (train): [20] [440/509] eta: 0:00:23 time: 0.3252 data: 0.0042 max mem: 3957 +eval (train): [20] [460/509] eta: 0:00:16 time: 0.3433 data: 0.0044 max mem: 3957 +eval (train): [20] [480/509] eta: 0:00:09 time: 0.3405 data: 0.0048 max mem: 3957 +eval (train): [20] [500/509] eta: 0:00:03 time: 0.3416 data: 0.0048 max mem: 3957 +eval (train): [20] [508/509] eta: 0:00:00 time: 0.3018 data: 0.0043 max mem: 3957 +eval (train): [20] Total time: 0:02:54 (0.3419 s / it) +eval (validation): [20] [ 0/85] eta: 0:04:53 time: 3.4531 data: 3.1901 max mem: 3957 +eval (validation): [20] [20/85] eta: 0:00:31 time: 0.3346 data: 0.0274 max mem: 3957 +eval (validation): [20] [40/85] eta: 0:00:18 time: 0.3563 data: 0.0048 max mem: 3957 +eval (validation): [20] [60/85] eta: 0:00:09 time: 0.3288 data: 0.0034 max mem: 3957 +eval (validation): [20] [80/85] eta: 0:00:01 time: 0.3163 data: 0.0041 max mem: 3957 +eval (validation): [20] [84/85] eta: 0:00:00 time: 0.3123 data: 0.0040 max mem: 3957 +eval (validation): [20] Total time: 0:00:31 (0.3724 s / it) +eval (test): [20] [ 0/85] eta: 0:04:42 time: 3.3236 data: 3.1267 max mem: 3957 +eval (test): [20] [20/85] eta: 0:00:32 time: 0.3664 data: 0.0339 max mem: 3957 +eval (test): [20] [40/85] eta: 0:00:19 time: 0.3607 data: 0.0046 max mem: 3957 +eval (test): [20] [60/85] eta: 0:00:10 time: 0.3277 data: 0.0045 max mem: 3957 +eval (test): [20] [80/85] eta: 0:00:01 time: 0.3138 data: 0.0045 max mem: 3957 +eval (test): [20] [84/85] eta: 0:00:00 time: 0.3022 data: 0.0041 max mem: 3957 +eval (test): [20] Total time: 0:00:32 (0.3774 s / it) +eval (testid): [20] [ 0/82] eta: 0:04:36 time: 3.3723 data: 3.1168 max mem: 3957 +eval (testid): [20] [20/82] eta: 0:00:29 time: 0.3367 data: 0.0054 max mem: 3957 +eval (testid): [20] [40/82] eta: 0:00:16 time: 0.3096 data: 0.0044 max mem: 3957 +eval (testid): [20] [60/82] eta: 0:00:08 time: 0.3032 data: 0.0039 max mem: 3957 +eval (testid): [20] [80/82] eta: 0:00:00 time: 0.3294 data: 0.0038 max mem: 3957 +eval (testid): [20] [81/82] eta: 0:00:00 time: 0.3201 data: 0.0038 max mem: 3957 +eval (testid): [20] Total time: 0:00:29 (0.3587 s / it) +evaluating best checkpoint: experiments/decoders/output/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__linear/checkpoint-best.pth +eval model info: +{"score": 0.11720191952750092, "hparam": [36, 1.0], "hparam_id": 46, "epoch": 17, "is_best": true, "best_score": 0.11720191952750092} +eval (train): [20] [ 0/509] eta: 0:28:49 time: 3.3980 data: 3.1491 max mem: 3957 +eval (train): [20] [ 20/509] eta: 0:04:10 time: 0.3683 data: 0.0253 max mem: 3957 +eval (train): [20] [ 40/509] eta: 0:03:19 time: 0.3325 data: 0.0037 max mem: 3957 +eval (train): [20] [ 60/509] eta: 0:02:53 time: 0.3110 data: 0.0041 max mem: 3957 +eval (train): [20] [ 80/509] eta: 0:02:37 time: 0.3051 data: 0.0043 max mem: 3957 +eval (train): [20] [100/509] eta: 0:02:26 time: 0.3281 data: 0.0043 max mem: 3957 +eval (train): [20] [120/509] eta: 0:02:18 time: 0.3446 data: 0.0046 max mem: 3957 +eval (train): [20] [140/509] eta: 0:02:09 time: 0.3152 data: 0.0042 max mem: 3957 +eval (train): [20] [160/509] eta: 0:02:00 time: 0.3117 data: 0.0042 max mem: 3957 +eval (train): [20] [180/509] eta: 0:01:52 time: 0.3105 data: 0.0042 max mem: 3957 +eval (train): [20] [200/509] eta: 0:01:45 time: 0.3324 data: 0.0042 max mem: 3957 +eval (train): [20] [220/509] eta: 0:01:39 time: 0.3587 data: 0.0044 max mem: 3957 +eval (train): [20] [240/509] eta: 0:01:32 time: 0.3478 data: 0.0043 max mem: 3957 +eval (train): [20] [260/509] eta: 0:01:25 time: 0.3579 data: 0.0045 max mem: 3957 +eval (train): [20] [280/509] eta: 0:01:18 time: 0.3028 data: 0.0044 max mem: 3957 +eval (train): [20] [300/509] eta: 0:01:11 time: 0.3215 data: 0.0044 max mem: 3957 +eval (train): [20] [320/509] eta: 0:01:04 time: 0.3260 data: 0.0045 max mem: 3957 +eval (train): [20] [340/509] eta: 0:00:57 time: 0.3333 data: 0.0041 max mem: 3957 +eval (train): [20] [360/509] eta: 0:00:50 time: 0.3171 data: 0.0043 max mem: 3957 +eval (train): [20] [380/509] eta: 0:00:43 time: 0.3209 data: 0.0047 max mem: 3957 +eval (train): [20] [400/509] eta: 0:00:36 time: 0.3277 data: 0.0044 max mem: 3957 +eval (train): [20] [420/509] eta: 0:00:29 time: 0.3164 data: 0.0043 max mem: 3957 +eval (train): [20] [440/509] eta: 0:00:23 time: 0.3218 data: 0.0046 max mem: 3957 +eval (train): [20] [460/509] eta: 0:00:16 time: 0.3132 data: 0.0047 max mem: 3957 +eval (train): [20] [480/509] eta: 0:00:09 time: 0.3094 data: 0.0039 max mem: 3957 +eval (train): [20] [500/509] eta: 0:00:02 time: 0.3083 data: 0.0039 max mem: 3957 +eval (train): [20] [508/509] eta: 0:00:00 time: 0.2983 data: 0.0038 max mem: 3957 +eval (train): [20] Total time: 0:02:49 (0.3327 s / it) +eval (validation): [20] [ 0/85] eta: 0:04:36 time: 3.2486 data: 2.9972 max mem: 3957 +eval (validation): [20] [20/85] eta: 0:00:32 time: 0.3672 data: 0.0053 max mem: 3957 +eval (validation): [20] [40/85] eta: 0:00:18 time: 0.3319 data: 0.0046 max mem: 3957 +eval (validation): [20] [60/85] eta: 0:00:09 time: 0.3284 data: 0.0045 max mem: 3957 +eval (validation): [20] [80/85] eta: 0:00:01 time: 0.2973 data: 0.0038 max mem: 3957 +eval (validation): [20] [84/85] eta: 0:00:00 time: 0.2875 data: 0.0038 max mem: 3957 +eval (validation): [20] Total time: 0:00:31 (0.3673 s / it) +eval (test): [20] [ 0/85] eta: 0:04:34 time: 3.2261 data: 2.9717 max mem: 3957 +eval (test): [20] [20/85] eta: 0:00:29 time: 0.3221 data: 0.0046 max mem: 3957 +eval (test): [20] [40/85] eta: 0:00:18 time: 0.3375 data: 0.0037 max mem: 3957 +eval (test): [20] [60/85] eta: 0:00:09 time: 0.3361 data: 0.0044 max mem: 3957 +eval (test): [20] [80/85] eta: 0:00:01 time: 0.3053 data: 0.0044 max mem: 3957 +eval (test): [20] [84/85] eta: 0:00:00 time: 0.2883 data: 0.0039 max mem: 3957 +eval (test): [20] Total time: 0:00:30 (0.3602 s / it) +eval (testid): [20] [ 0/82] eta: 0:04:18 time: 3.1538 data: 2.9547 max mem: 3957 +eval (testid): [20] [20/82] eta: 0:00:27 time: 0.3149 data: 0.0121 max mem: 3957 +eval (testid): [20] [40/82] eta: 0:00:16 time: 0.3090 data: 0.0044 max mem: 3957 +eval (testid): [20] [60/82] eta: 0:00:07 time: 0.3110 data: 0.0039 max mem: 3957 +eval (testid): [20] [80/82] eta: 0:00:00 time: 0.2962 data: 0.0040 max mem: 3957 +eval (testid): [20] [81/82] eta: 0:00:00 time: 0.2854 data: 0.0038 max mem: 3957 +eval (testid): [20] Total time: 0:00:28 (0.3441 s / it) +eval results: + +| model | repr | clf | dataset | ckpt | epoch | lr | wd | hparam_id | hparam | split | loss | acc | acc_std | f1 | f1_std | +|:---------|:-------|:-------|:-------------|:-------|--------:|-------:|-----:|------------:|:----------|:-----------|-------:|--------:|----------:|---------:|----------:| +| flat_mae | reg | linear | nsd_cococlip | best | 17 | 0.0108 | 0.05 | 46 | [36, 1.0] | train | 2.885 | 0.16199 | 0.0018654 | 0.1114 | 0.001681 | +| flat_mae | reg | linear | nsd_cococlip | best | 17 | 0.0108 | 0.05 | 46 | [36, 1.0] | validation | 3.0114 | 0.1172 | 0.0039725 | 0.070531 | 0.0030039 | +| flat_mae | reg | linear | nsd_cococlip | best | 17 | 0.0108 | 0.05 | 46 | [36, 1.0] | test | 2.9847 | 0.12857 | 0.0038467 | 0.071924 | 0.0027284 | +| flat_mae | reg | linear | nsd_cococlip | best | 17 | 0.0108 | 0.05 | 46 | [36, 1.0] | testid | 3.0147 | 0.11124 | 0.0041689 | 0.073328 | 0.0033676 | + + +done! total time: 1:06:50 diff --git a/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__linear/train_log.json b/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__linear/train_log.json new file mode 100644 index 0000000000000000000000000000000000000000..c2d381d1b45a53d35d8f45bb288058bf361ad07b --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/nsd_cococlip__reg__linear/train_log.json @@ -0,0 +1,20 @@ +{"epoch": 0, "train/lr": 2.987987987987988e-05, "train/loss": 3.161760421991348, "train/grad": 0.0803881687670946, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.18648193359375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.18640380859375, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.186212158203125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.1860400390625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.18587890625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.185687255859375, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.185340576171875, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.184989013671875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.184591064453125, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.184111328125, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.1836865234375, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.18302001953125, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.182353515625, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.1814013671875, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.1804541015625, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.17956787109375, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.17833984375, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.176954345703125, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.17535888671875, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.173900146484375, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.172017822265625, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.170006103515625, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.167799072265625, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.16554931640625, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.163289794921875, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.1606591796875, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.158397216796875, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.156485595703125, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.154093017578125, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.15157470703125, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.149554443359375, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.14793701171875, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.145970458984375, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.14438720703125, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.142786865234375, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.141405029296875, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.140068359375, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.138944091796875, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.137999267578125, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.1369189453125, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.136324462890625, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.13592041015625, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.1356884765625, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.135748291015625, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.1358740234375, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.136436767578125, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.1369708251953123, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.137877197265625, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.138807373046875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.012314453120343388, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.012310608187690378, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.012304217368364335, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.012297949101775885, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.01229153785854578, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.012282537813298404, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.01227240236941725, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.012260787482373416, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.012246291916817427, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.012230183170177043, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.012214531456120312, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.01219082769472152, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.012166956746950746, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.01213238918222487, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.012099077170714735, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.012065959894098342, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.012023361870087684, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.011972049018368125, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.011913474430330098, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.01185738037340343, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.011787120755761861, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.011714333323761822, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.011632476337254047, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.011545822182670236, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.01145799127407372, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.011357034062966705, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.011272926381789148, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.011201425525359809, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.011113864444196224, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.011022099647670985, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.01095174897927791, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.010895129344426095, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.01082953876350075, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.010779615743085742, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.01072953935712576, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.01068791901692748, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.010651855822652578, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.010624407008290291, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.010601922059431673, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.010584840243682265, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.01058047333266586, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.010582960313186049, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.010597008857876062, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.010618025697767734, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.01065272900974378, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.010701112714596093, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.010747619946487248, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.010807169997133315, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.010864488063380123, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.189805746078491, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.18941068649292, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1888012886047363, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.188171863555908, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1875576972961426, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1866848468780518, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1857194900512695, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1846675872802734, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.183255672454834, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1817898750305176, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1803176403045654, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1781527996063232, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.176044464111328, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.173044443130493, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1701972484588623, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.167495012283325, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1641345024108887, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.160273313522339, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.156066417694092, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.1523470878601074, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.147988796234131, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.1438791751861572, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.139763116836548, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.1360085010528564, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.132803201675415, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.1299221515655518, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.1280977725982666, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.127012252807617, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.126145362854004, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.1257638931274414, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.1257214546203613, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.1258904933929443, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.1262223720550537, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.1266207695007324, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.127058506011963, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.127546787261963, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.1279401779174805, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.128288984298706, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.1284499168395996, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.1282825469970703, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.12772536277771, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.1269283294677734, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.1256141662597656, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1241261959075928, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.121490716934204, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.11698317527771, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1118381023406982, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.106654644012451, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1054160594940186, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.04078995939461056, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.04171280915466962, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.04226651901070506, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.043004798818752306, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.043004798818752306, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.043004798818752306, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.04466592838685862, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.04466592838685862, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.04595791805094131, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.04614248800295312, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.04798818752307124, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.05057216685123662, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.0518641565153193, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.05518641565153193, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.055924695459579184, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.05758582502768549, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.060723514211886306, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06312292358803986, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06441491325212255, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.06256921373200443, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.06386120339608711, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.06404577334809892, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.06423034330011074, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.06459948320413436, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.06441491325212255, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.0636766334440753, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.06423034330011074, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.06404577334809892, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.0636766334440753, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.0636766334440753, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.06256921373200443, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.062200073827980804, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.06256921373200443, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.062384643779992616, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.062384643779992616, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.062384643779992616, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.06256921373200443, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.06404577334809892, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.06662975267626431, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.07308970099667775, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.07825765965300849, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.08416389811738649, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.08656330749354005, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.08157991878922112, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.08084163898117387, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.08139534883720931, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.012115624423276669, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.012659107264798486, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.01274492335022472, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.01284104325966682, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.012686162102808032, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.012051506574530612, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.01259165204461611, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.012329516280002778, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.012511681370855935, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.012321522773097815, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.012759761526450033, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.014103317921406908, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.015352977675938217, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.015987732715387528, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.015438645667065092, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.013784426431321675, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.013454174151962553, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.014297063008792193, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.012700273485807123, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.010270960868259857, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.009027486724839497, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.008504564176907212, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.008431316955694984, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.008457970143195022, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.00811254065825312, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.007985700773682287, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.008439040177178864, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.008286775802251322, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.008214328103818431, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.008029257880747235, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.00789218162099518, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.007720179132631742, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.007078570175858165, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.0067108782703660915, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.006944300918777863, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.006731468077570892, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.006492183081622736, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.006394066650476906, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.007352225796448994, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.008609949401073937, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.009809177216667055, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.011817190047456799, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.016363303028555178, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.01941996631235554, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.02332460674850496, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.024848938721488145, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.02134952641730709, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.019970866424674816, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.024142800537405654, "id_best": 45, "lr_best": 0.0093, "wd_best": 0.05, "train/loss_best": 3.136436767578125, "validation/loss_best": 3.11698317527771, "validation/acc_best": 0.08656330749354005, "validation/f1_best": 0.024848938721488145} +{"epoch": 1, "train/lr": 8.993993993993998e-05, "train/loss": 3.141785227060318, "train/grad": 0.07638069020584226, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.182271728515625, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.18154296875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.180423583984375, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.1792919921875, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.178245849609375, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.17672607421875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.17503662109375, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.1733154296875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.1708984375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.168673095703125, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.166541748046875, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.1633740234375, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.16058349609375, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.15672607421875, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.153470458984375, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.15057861328125, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.14741943359375, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.144146728515625, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.140968017578125, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.1385498046875, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.136185302734375, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.1342138671875, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.132677001953125, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.13143310546875, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.130423583984375, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.129635009765625, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.12917236328125, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.12877197265625, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.128331298828125, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.127896728515625, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.127462158203125, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.127093505859375, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.126715087890625, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.126329345703125, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.125916748046875, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.12548095703125, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.1249609375, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.1244775390625, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.123798828125, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.1227032470703127, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.1217755126953124, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.1208917236328126, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.120096435546875, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.1194757080078124, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.11927490234375, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.1200732421875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.1218060302734374, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.124698486328125, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.1269244384765624, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.012169484202750026, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.012143908003345132, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.0121018159808591, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.012060544937849044, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.01202025736682117, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.011964767850004136, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.011903516398742795, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.011836041286587716, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.011750064208172262, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.011660865168087184, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.011577097699046135, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.011456362786702812, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.011344465594738722, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.011192982355132698, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.011059724888764322, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.010943016824312509, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.010809988128021359, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.010673213514965028, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.010544115153606981, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.01044477742863819, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.010347625196445734, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.010271593742072583, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.010209549681749195, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.010164935467764735, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.010136459188070148, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.010119815452490001, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.010115592621732504, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.010116752267349512, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.010124171406496317, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.010136586246080697, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.010149943421129137, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.01016435214318335, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.01018511481815949, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.010204895688220859, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.010230551571585238, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.010258865447249264, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.010291260664816946, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.010324810903985054, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.010366172743961215, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.010426772406790406, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.01048268864164129, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0105430574179627, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.010642357806209474, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.010749615549575537, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.010898002996109426, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.011083355522714555, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.011258300067856908, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.011468724785372615, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.011623274348676205, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.182619333267212, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.181272268295288, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1790688037872314, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.176954746246338, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1749327182769775, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.172210693359375, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1692585945129395, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1661245822906494, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1622629165649414, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1584575176239014, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1550066471099854, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.150338649749756, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1463584899902344, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.141401529312134, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1375529766082764, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.134538412094116, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1315627098083496, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1290338039398193, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1271557807922363, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.1260411739349365, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.1252527236938477, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.124778985977173, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.1245429515838623, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.124337673187256, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.1241614818573, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.1238958835601807, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.1236300468444824, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.1233763694763184, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.123032808303833, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.122666120529175, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.1223788261413574, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.122184991836548, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.1220011711120605, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.121809720993042, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.1213316917419434, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.12041974067688, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.118716239929199, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.1165313720703125, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.113649606704712, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.1093544960021973, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.105774402618408, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.102989673614502, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.0996925830841064, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.0967226028442383, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.0943665504455566, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.096914052963257, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.10493803024292, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1194355487823486, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.135740280151367, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.04558877814691768, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.046696197858988556, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.04928017718715393, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.05094130675526024, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.05149501661129568, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.055740125507567365, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.056109265411590996, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.057770394979697305, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06016980435585087, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06386120339608711, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06293835363602805, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06496862310815799, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06478405315614617, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06459948320413436, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06478405315614617, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06386120339608711, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06404577334809892, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06404577334809892, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.06404577334809892, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.0636766334440753, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.0636766334440753, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.06386120339608711, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.06349206349206349, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.06478405315614617, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.06459948320413436, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.06478405315614617, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.06496862310815799, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.06533776301218161, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.06441491325212255, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.06423034330011074, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.06589147286821706, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.06718346253229975, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.0681063122923588, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.07290513104466592, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.07475083056478406, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.07973421926910298, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.07825765965300849, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.07899593946105574, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.08028792912513842, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.08028792912513842, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.08361018826135105, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.08453303802141011, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.08619416758951642, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.08471760797342193, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.07825765965300849, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.07364341085271318, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.012019030786775659, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.012386885136137659, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.013786773310162405, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.01481561344009557, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.015245393917470004, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.01616685773597847, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.01528977281792169, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.013774559885681228, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.013499934111805152, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.013099858882942064, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.012882149327712457, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.010720753240396735, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.010456399357403508, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.009936150842467304, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.009354306339994298, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.009205185221752598, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.008641603104703093, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.008611789055595764, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.008735653181121126, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.008834239660964463, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.00891003885551514, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.009172104902588131, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.009514193108333234, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.01034385021124498, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.010787204592750094, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.010651699630046965, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.011436313732935485, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.01156515350965008, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.01122189536930141, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.010277643022772669, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.0105115873899556, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.009695750938033059, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.00929743950287957, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.011316351413888195, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.013231859662320116, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.013729507777171126, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.017429222584103243, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.021306383885241264, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.025661071396876182, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.027325395618947285, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.02789614138474143, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.02636430556003049, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.02610711847256718, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.030383775366102886, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0360728243473771, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.036026590871125704, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.03564217336427123, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.03018132800534178, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0242355530640118, "id_best": 45, "lr_best": 0.0093, "wd_best": 0.05, "train/loss_best": 3.1200732421875, "validation/loss_best": 3.096914052963257, "validation/acc_best": 0.08619416758951642, "validation/f1_best": 0.036026590871125704} +{"epoch": 2, "train/lr": 0.00014999999999999988, "train/loss": 3.1277075064182283, "train/grad": 0.07575502065941692, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.174515380859375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.17283203125, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.170238037109375, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.167738037109375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.16539794921875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.162301025390625, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.1591943359375, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.155999755859375, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.152266845703125, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.1486279296875, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.145650634765625, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.141900634765625, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.138951416015625, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.135595703125, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.13340576171875, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.13177490234375, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.130281982421875, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.1290966796875, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.1281884765625, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.127626953125, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.126953125, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.1265283203125, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.1259521484375, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.125411376953125, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.12466796875, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.1238623046875, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.123070068359375, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.122344970703125, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.1212646484375, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.1199658203125, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.11878173828125, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.117689208984375, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.116063232421875, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.114674072265625, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.113204345703125, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.11167236328125, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.1099139404296876, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.1082940673828126, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.106365966796875, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.1038299560546876, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.1017376708984377, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.100107421875, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.0982769775390624, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.0973297119140626, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.0972906494140626, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.0991802978515626, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.1030517578125, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.1102529907226564, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.1183489990234374, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.011911086244508625, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.011849899380467831, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.01175129545852542, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.011657826919108629, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.011568337716162204, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.011450682645663618, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.011326929610222579, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.01119984800927341, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.011049639456905425, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.010907869734801352, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.0107870485750027, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.010633976275566965, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.010513880958314984, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.01038180606905371, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.010292867121752352, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.010232417504303157, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.010181732000783086, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.010147576024755835, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.010128297291230411, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.010121042646933347, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.01011986704543233, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.01012275778921321, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.010129088384564966, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.010137246914673596, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.010146482537966222, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.010158690188545734, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.010171136395074427, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.01018364334711805, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.010202069075312466, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.010225792152341455, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.01024908217601478, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.01027303458424285, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.010308210398070514, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.010345054059289396, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.010395279687363654, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.010449605067260564, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.010512596738990396, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.010575366297271103, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.010654404175002128, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.01077400584705174, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.010883901324123145, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.010987684684805573, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.011127970633096992, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.011252065626904369, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.01140939029864967, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.011635229280218483, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.011905510309152306, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.012300582737661898, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.012666548532433809, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1724207401275635, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1699492931365967, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.166105031967163, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.162550687789917, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1592648029327393, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1551785469055176, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.151003122329712, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1469919681549072, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1425554752349854, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1387057304382324, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1356751918792725, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1322219371795654, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.129835605621338, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1275651454925537, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.12623929977417, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.125425338745117, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1247522830963135, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1242668628692627, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1237800121307373, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.1234278678894043, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.1229186058044434, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.122422933578491, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.1218624114990234, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.121215581893921, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.1205790042877197, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.119809627532959, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.1190950870513916, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.118415355682373, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.1174044609069824, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.116086483001709, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.1146655082702637, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.113192319869995, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.1109871864318848, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.1090354919433594, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.107067823410034, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.1059460639953613, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.105639696121216, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.1058108806610107, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.1056151390075684, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.104485034942627, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.103999376296997, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.1041767597198486, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.1073150634765625, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1136324405670166, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1225898265838623, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.130380392074585, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.134485960006714, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1357407569885254, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1389620304107666, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.055740125507567365, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.05647840531561462, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.0592469545957918, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06183093392395718, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.062200073827980804, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06201550387596899, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.0636766334440753, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06312292358803986, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.0636766334440753, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.0636766334440753, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.0636766334440753, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.06312292358803986, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.06256921373200443, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.06275378368401624, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.061461794019933555, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.06164636397194537, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.06275378368401624, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.062384643779992616, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.06423034330011074, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.06423034330011074, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.06386120339608711, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.06293835363602805, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.06441491325212255, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.06496862310815799, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.06718346253229975, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.07198228128460686, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.07585825027685493, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.0828719084533038, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.08305647840531562, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.07899593946105574, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.08010335917312661, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.08047249907715023, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.08047249907715023, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.08065706902916205, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.08379475821336287, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.08213362864525656, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.08102620893318568, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.08194905869324474, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.08324104835732743, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.07770394979697305, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.0710594315245478, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.016246712590103966, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.015225026461585883, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.014239841764640325, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.014458532341168256, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.012335617075496361, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.012452005668382721, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.01022086738719683, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.00934945723097616, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.008730223100083397, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.008255078972798464, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.00851460609721818, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.0077395834386923094, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.0077478266705506725, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.007667854972954194, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.007808925676625499, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.007627969750069476, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.007438872066417479, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.007655617540487808, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.008080855384060065, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.008104692796612474, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.007697353713458849, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.007954486563624517, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.00764839256293356, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.008529879241648233, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.009573703515358988, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.009263584148418555, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.009921899912137473, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.00982686865650824, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.008402435191118154, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.006986436414337233, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.008249807801724317, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.00903327761768364, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.011729208318135016, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.01796034327974939, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.022570260452908154, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.0269127018248914, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.030047349044091152, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.02771149348261695, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.02882766062408106, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.029429069503043016, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.028917482147242966, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.030711662420325966, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.03459905601711833, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.03489851537749825, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.03406384173838523, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.03715243516595395, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.04243721097148965, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.03945599302100244, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.03290456300764655, "id_best": 42, "lr_best": 0.005699999999999999, "wd_best": 0.05, "train/loss_best": 3.0982769775390624, "validation/loss_best": 3.1073150634765625, "validation/acc_best": 0.08379475821336287, "validation/f1_best": 0.03459905601711833} +{"epoch": 3, "train/lr": 0.0002100600600600602, "train/loss": 3.1177438640594484, "train/grad": 0.0759071035310626, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.164149169921875, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.16152587890625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.157706298828125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.15434814453125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.151199951171875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.14756103515625, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.143856201171875, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.140576171875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.13715576171875, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.134371337890625, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.132177734375, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.130167236328125, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.128614501953125, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.12732177734375, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.126524658203125, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.12590087890625, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.125216064453125, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.124727783203125, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.1239990234375, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.123463134765625, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.122672119140625, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.121846923828125, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.12091796875, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.119925537109375, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.11878173828125, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.11729248046875, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.115904541015625, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.114652099609375, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.112874755859375, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.110599365234375, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.108524169921875, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.106707763671875, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.10404052734375, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.101690673828125, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.0987408447265623, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.095968017578125, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.0932440185546874, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.090919189453125, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.0889947509765623, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.087103271484375, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.0863018798828126, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.08594482421875, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.0860675048828123, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.0869915771484373, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.089703369140625, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.094410400390625, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.099661865234375, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.1090383911132813, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.119368896484375, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.011503351577557623, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.011406666329130531, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.011259109061211348, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.011126034972257913, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.011006745314225554, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.010861127339303493, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.010720505903009325, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.010590610499493778, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.010456886612810195, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.010350887088570744, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.010275380772072821, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.010199803623836488, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.010155268835369498, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.010121423900127411, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.010108049258124084, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.010103505635634065, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.010102860708720983, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.010105762502644212, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.010110337873920799, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.01011532325996086, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.010122521945741028, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.010130693463142961, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.010140007697045803, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.010151609445456415, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.01016461278544739, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.010182521918322892, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.010200294747482986, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.01021831821417436, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.010244914183858781, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.010278916244860738, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.010313245623838157, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.010345823159441351, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.010393096189945937, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.010437799654901027, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.010495362002402545, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.010561691615730524, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.010645620403811335, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.010737731652334333, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.010850983238779009, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.011012909258715809, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.011166646564379334, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.011332956459373236, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.011596109652891755, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.011854802179150283, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.012175144152715802, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.01252162452088669, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.012834785962477327, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.01327429283875972, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.013670648480765522, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1609926223754883, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1576688289642334, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.152787923812866, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1485958099365234, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1449811458587646, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1408395767211914, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1370856761932373, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1338772773742676, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.130807399749756, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1285746097564697, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.127063512802124, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.125645160675049, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1247851848602295, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.124037504196167, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1235544681549072, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1231770515441895, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.122760534286499, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.122326612472534, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1219229698181152, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.1215522289276123, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.1211156845092773, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.1207101345062256, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.1202101707458496, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.1196041107177734, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.1188645362854004, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.117762804031372, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.1165685653686523, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.1153323650360107, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.1134390830993652, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.110933780670166, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.108611583709717, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.106492519378662, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.1037113666534424, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.1011617183685303, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.097867488861084, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.0943822860717773, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.0914604663848877, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.0909969806671143, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.092874050140381, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.0931475162506104, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.0891451835632324, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.0846850872039795, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.079747200012207, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.0770468711853027, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.0795438289642334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.112215757369995, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1440107822418213, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.140106201171875, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1331982612609863, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06183093392395718, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06256921373200443, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.062384643779992616, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06404577334809892, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06404577334809892, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06404577334809892, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06441491325212255, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06404577334809892, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06275378368401624, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06256921373200443, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06201550387596899, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06183093392395718, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06256921373200443, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.06386120339608711, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.06423034330011074, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.06478405315614617, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.06607604282022887, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.06662975267626431, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.06902916205241787, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.0695828719084533, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.07272056109265411, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.07272056109265411, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.07419712070874862, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.07567368032484312, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.0769656699889258, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.07973421926910298, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.08102620893318568, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.0828719084533038, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.08361018826135105, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.08600959763750461, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.08767072720561092, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.08656330749354005, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.08748615725359911, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.08785529715762273, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.08914728682170543, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.09228497600590624, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.0946843853820598, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.08767072720561092, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.07456626061277224, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.07235142118863049, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.09099298634182355, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.09597637504614248, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.0138795779245578, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.012427102692279242, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.010877945537136209, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.009750071894454778, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.009269164431934453, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.009027132480083104, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.008781725570239172, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.007811337173304252, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.008082766208819552, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.008124123747192928, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.008056610331657098, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.008369564137608075, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.00853478736828777, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.008621067160727977, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.008560423853002814, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.008769526013195974, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.008936214892959761, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.00903395683395137, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.009819357599925645, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.010188386292545763, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.010390719128456322, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.010492528464674711, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.010649527943379538, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.011622590294628005, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.012093103462277384, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.013894034689707874, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.015968814459731067, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.020220071565461403, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.022314804927416474, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.02572332466397335, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.02814864042052337, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.028853640866316494, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.03071697059875865, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.031735608625412075, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.0326743892197048, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.03401462694587363, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.03813718645044533, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.0417045195004155, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.04271443722647389, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.043498932670661246, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.04263773460214771, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.041405687264613016, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.04189588730519309, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0453332171718541, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.045975371578055084, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.03612816522705222, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.030487625288540644, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.03995155869160152, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0446948880833108, "id_best": 48, "lr_best": 0.015, "wd_best": 0.05, "train/loss_best": 3.119368896484375, "validation/loss_best": 3.1331982612609863, "validation/acc_best": 0.09597637504614248, "validation/f1_best": 0.0446948880833108} +{"epoch": 4, "train/lr": 0.0002701201201201201, "train/loss": 3.110689661502838, "train/grad": 0.07615299765020608, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.1552734375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.15220703125, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.147913818359375, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.144327392578125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.1414697265625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.138236083984375, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.1355322265625, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.13338134765625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.131319580078125, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.12993896484375, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.12907958984375, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.12822265625, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.12765625, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.127049560546875, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.12652099609375, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.125968017578125, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.125272216796875, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.124542236328125, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.123662109375, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.12287109375, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.121688232421875, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.120550537109375, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.11911376953125, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.117388916015625, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.11571044921875, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.113411865234375, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.11123291015625, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.109180908203125, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.106385498046875, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.1028125, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.09972900390625, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.096932373046875, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.093165283203125, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.089891357421875, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.085968017578125, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.0824395751953126, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.07905029296875, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.07631103515625, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.073917236328125, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.07225341796875, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.0717156982421874, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.0717669677734376, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.0727264404296877, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.075356140136719, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.0803286743164064, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.0864749145507813, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.0914361572265623, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.100733642578125, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.1156802368164063, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.011207072888500988, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.011084582153707744, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.010907633444294334, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.010761230294592678, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.010640183810610325, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.010505930706858634, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.01039285974111408, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.010302971666678786, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.01022597007220611, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.01017704593250528, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.010149418241344393, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.010127879476640374, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.010118576537352056, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.010115224740002305, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.010116322934627532, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.010118575007654727, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.010123043581843376, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.010128852645866573, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.010136386982630939, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.010143355031032116, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.01015223417431116, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.010162454312667251, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.010173881882801652, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.010186775845941156, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.010200907799880952, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.01021872550714761, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.010236055804416538, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.010253810521680862, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.010279742861166596, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.01031733226729557, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.010355545822530985, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.010394388814456762, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.010452297893352806, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.010509420691523701, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.010585605015512556, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.010673951022326947, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.010785677882377059, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.010905543372500688, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0110520714125596, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.011260328323114664, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.011440341211855411, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.011601631187368185, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.011837461355607957, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.012111378042027355, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.012475754185579717, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.012835622602142393, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.013147544697858393, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.013628370906226338, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.014154289914295078, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.149857759475708, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.146292209625244, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1413986682891846, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1375620365142822, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.134594440460205, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.131521224975586, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1291160583496094, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.127361297607422, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1259069442749023, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1250479221343994, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.124509334564209, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1239826679229736, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1236624717712402, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1232476234436035, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1228721141815186, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1224935054779053, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.122042655944824, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.121497392654419, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.120879650115967, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.120270013809204, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.1195573806762695, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.1188411712646484, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.118072032928467, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.117302179336548, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.116529703140259, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.1156373023986816, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.114745616912842, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.113820791244507, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.112139940261841, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.1096601486206055, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.1069066524505615, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.103931188583374, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.0994021892547607, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.0954651832580566, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.0919418334960938, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.090456247329712, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.091223955154419, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.0938775539398193, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.0992066860198975, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.110698699951172, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.121142864227295, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.1278724670410156, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.1365067958831787, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.148564338684082, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1563119888305664, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.145695686340332, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1328349113464355, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.144429922103882, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1656479835510254, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06293835363602805, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06293835363602805, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06293835363602805, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06293835363602805, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06293835363602805, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06441491325212255, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.0636766334440753, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06293835363602805, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.0636766334440753, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06459948320413436, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06459948320413436, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.06570690291620525, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.06496862310815799, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.06552233296419344, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.06976744186046512, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.07419712070874862, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.07936507936507936, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.08213362864525656, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.08342561830933924, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.08342561830933924, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.08324104835732743, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.08453303802141011, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.08803986710963455, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.08951642672572906, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.09210040605389443, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.09449981543004798, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.09413067552602436, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.09653008490217793, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.09671465485418974, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.09210040605389443, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.09062384643779993, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.08656330749354005, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.08711701734957548, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.08416389811738649, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.07641196013289037, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.0753045404208195, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.0843484680693983, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.09394610557401255, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.09948320413436693, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.09413067552602436, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.09708379475821337, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.010015470267091466, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.00900387363123381, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.008102004240272877, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.007851120412366113, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.007581094167423995, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.008073980262861755, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.008052033832697605, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.007819527857382297, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.0077211931664216416, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.00755626469676645, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.008204120528475774, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.00790237979407019, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.008084297261489173, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.00783643105880954, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.00815704595225655, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.008891683104349716, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.009092021602293976, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.010239529470335846, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.010740888002679645, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.012308749832402988, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.01323799944916614, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.01592296750476059, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.01953474650592971, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.022923307130555317, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.025659114842306447, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.027862505338315174, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.02984080308524385, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.030631353566437525, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.03083363937976, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.03425232719700385, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.03858133833065638, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.040151342867594274, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.04219605419576989, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.0460308808109167, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.04790673174653227, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.051497870842679955, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.052623028950252004, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.04910602683276751, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.04834853775364317, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.046597769794390585, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.04756458210837944, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.04446106865335348, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.04021043228164606, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.044410740333029275, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.047801461285009124, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.04971613381804191, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.05506284427834742, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.049794095252533394, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.04943801878588091, "id_best": 46, "lr_best": 0.010799999999999999, "wd_best": 0.05, "train/loss_best": 3.0914361572265623, "validation/loss_best": 3.1328349113464355, "validation/acc_best": 0.09948320413436693, "validation/f1_best": 0.05506284427834742} +{"epoch": 5, "train/lr": 0.00029891323817685334, "train/loss": 3.106175991296768, "train/grad": 0.07495394935831427, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.14941162109375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.14662109375, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.14289794921875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.140140380859375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.13810791015625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.13611083984375, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.134698486328125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.1336279296875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.132747802734375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.13218017578125, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.131669921875, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.131177978515625, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.130689697265625, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.129739990234375, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.128936767578125, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.12828857421875, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.127322998046875, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.12608154296875, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.12484375, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.123629150390625, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.121895751953125, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.120146484375, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.1181005859375, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.115743408203125, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.11334228515625, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.110172119140625, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.10728515625, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.1045233154296876, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.1007550048828123, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.096300048828125, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.09228759765625, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.088616943359375, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.08378662109375, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.0794989013671876, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.074859619140625, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.0707476806640623, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.06687255859375, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.0632229614257813, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.0598223876953123, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.057109680175781, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.0561312866210937, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.0560757446289064, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.0580914306640623, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.06196533203125, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.06875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.0778070068359376, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.0872428894042967, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.1027410888671874, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.1198078918457033, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.010694143495056778, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.010569554378744215, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.010404686518013477, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.010282098394818605, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.010191799479071052, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.010105624108109622, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.010045478390529751, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.010006849805358797, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.009981760731898248, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.009970640526153146, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.009966818017419428, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.009966713378671556, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.00996880061691627, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.009973030011169613, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.009977213994134218, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.009981505463365466, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.009987004797440023, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.009993415551725775, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.010001534051261841, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.010008701863698661, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.01001902864780277, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.010031093589495867, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.01004463668446988, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.010061208684928715, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.010080280594993383, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.010105234845541418, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.010128826727159321, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.010151387199293822, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.01018190750386566, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.010220969803631305, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.010258122568484396, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.01029584713280201, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.010351889072917403, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.010409289493691177, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.010491892877034843, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.010592633597552777, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.010716807099524885, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.010837721549905836, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.01097227358724922, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.01117717199260369, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.011361386438366025, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.011533937202766537, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.011801591268740594, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.012058400409296155, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.012361250398680568, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.012732550809159875, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.013039296884089708, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.013445402821525931, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.013889611549675464, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.141369104385376, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1380832195281982, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1339378356933594, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1310296058654785, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1289916038513184, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.127073049545288, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.125736951828003, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1248459815979004, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1241226196289062, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1236164569854736, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.123230457305908, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1227242946624756, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1222848892211914, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.121645927429199, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1210479736328125, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.120488405227661, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.11978816986084, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1189680099487305, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1180765628814697, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.117267608642578, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.1162571907043457, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.1152491569519043, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.114177703857422, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.113109588623047, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.1120502948760986, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.1108224391937256, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.1096694469451904, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.1085193157196045, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.1067001819610596, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.104020357131958, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.100966215133667, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.097668170928955, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.0926032066345215, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.088101863861084, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.0835416316986084, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.0805625915527344, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.0794126987457275, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.0804507732391357, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.0836181640625, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.0901129245758057, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.0969245433807373, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.1029412746429443, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.1136608123779297, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1255478858947754, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1312992572784424, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1265878677368164, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.127674102783203, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.128399133682251, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1494998931884766, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06423034330011074, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06441491325212255, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06423034330011074, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06478405315614617, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06275378368401624, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.062200073827980804, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06275378368401624, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06256921373200443, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06275378368401624, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06312292358803986, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06423034330011074, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06478405315614617, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06699889258028793, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.0681063122923588, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.07013658176448874, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.0725359911406423, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.07272056109265411, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.07419712070874862, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.0754891103728313, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.07770394979697305, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.07807308970099668, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.07973421926910298, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.0843484680693983, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.08361018826135105, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.08527131782945736, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.08674787744555186, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.08748615725359911, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.08822443706164636, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.08970099667774087, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.09191583610188261, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.09154669619785899, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.09597637504614248, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.09616094499815431, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.09745293466223699, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.0976375046142488, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.09376153562200074, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.09246954595791805, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.09265411590992986, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.0902547065337763, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.08914728682170543, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.09099298634182355, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.08471760797342193, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.07881136950904392, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.07862679955703211, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.08342561830933924, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.009092858752075786, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.008821393664333398, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.008073710154256968, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.00847459567201409, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.00856483015915397, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.008795869397924297, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.008716536920699602, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.008488891368517331, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.008438528050597015, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.00877723460781072, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.008956058773955439, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.009104921523526783, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.009346055725037343, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.00997704380998562, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.010668157622039346, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.01100035810196883, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.012713123504423357, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.014610686368522535, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.01653855467673561, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.01834630250547187, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.020431029125351163, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.02177729048381623, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.02172916704122341, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.021665568974084018, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.02211519247884311, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.022800614932213217, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.028138998721176384, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.029282993622624376, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.03339733884869516, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.03535626946400584, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.03721971396579781, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.03775295608204158, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.038335201297413794, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.039165408224446564, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.038093832033716864, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.04023843753964764, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.03974494583282794, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.04007299540625637, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.03986487020027244, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.038105152478891624, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.04081300693219273, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.04734853991065125, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.05144032824168071, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.052430487862286546, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.055343439038209596, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.05799988400147136, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.057463620336633825, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.056762369337877594, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.05975611460773611, "id_best": 38, "lr_best": 0.00294, "wd_best": 0.05, "train/loss_best": 3.0598223876953123, "validation/loss_best": 3.0836181640625, "validation/acc_best": 0.0976375046142488, "validation/f1_best": 0.03986487020027244} +{"epoch": 6, "train/lr": 0.0002924170901991409, "train/loss": 3.090279780626297, "train/grad": 0.07548659538850189, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.13992431640625, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.137158203125, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.133779296875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.1315380859375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.12989990234375, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.128253173828125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.1272021484375, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.12634765625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.125545654296875, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.124739990234375, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.124146728515625, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.123294677734375, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.122406005859375, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.121383056640625, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.120281982421875, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.119141845703125, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.11779052734375, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.116175537109375, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.114287109375, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.11254150390625, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.110185546875, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.10776123046875, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.105042724609375, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.1019287109375, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.0986669921875, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.094652099609375, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.091087646484375, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.087755126953125, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.083157958984375, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.077646484375, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.0729364013671874, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.0685894775390623, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.0629962158203123, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.058023681640625, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.0522869873046874, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.0467919921875, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.0414532470703124, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.0370318603515627, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.0332037353515626, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.03070556640625, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.030827941894531, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.032257385253906, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.035364685058594, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.0386981201171874, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.044469299316406, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.0543038940429685, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.064183654785156, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.0771966552734376, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.0886695861816404, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.01051160530652851, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.010402496494352818, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.010269990512169898, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.010183363305404782, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.01012693180469796, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.01008068499621004, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.010053839690517635, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.010039480184204877, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.010032840967178346, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.010030535634141415, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.010031313782092184, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.01003328202990815, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.010035625512246042, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.010038751752581447, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.01004168213577941, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.010044244320597499, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.010048119199927897, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.010052482814062387, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.01005761155160144, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.010062137001659721, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.010068663582205772, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.010075301236938686, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.010084405972156674, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.010095494668930768, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.010110222038347274, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.010132370905485005, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.010156493887770922, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.010182253292296082, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.010221450987737626, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.010274290016386658, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.010326747018843889, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.01037742480635643, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.010449963377323002, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.010517482054419816, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.010600721407681703, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.010686167241074145, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.010785186579450965, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.010896162702701986, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.011045821630395948, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.011276355129666626, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.011486701243557036, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.011691639199852943, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.011988208969123662, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.012276483452878892, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.01265593518037349, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.013082377235405148, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.013378636208362877, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.01368665864225477, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.013987972205504774, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.135727882385254, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1329760551452637, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.129725694656372, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.127671957015991, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1263210773468018, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1251413822174072, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.124370574951172, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1237852573394775, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1232750415802, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.122819423675537, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1224334239959717, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.121851921081543, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.12129807472229, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1205389499664307, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1197988986968994, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.119180202484131, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.118324041366577, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1173179149627686, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1162407398223877, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.1152138710021973, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.113907814025879, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.1125292778015137, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.110940933227539, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.1090574264526367, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.1069133281707764, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.104017496109009, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.101170301437378, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.0983850955963135, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.0943562984466553, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.089550018310547, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.085432529449463, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.082019805908203, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.0779902935028076, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.0749688148498535, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.0724403858184814, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.072110652923584, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.075070858001709, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.079514265060425, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.0829994678497314, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.083693027496338, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.0826022624969482, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.0830907821655273, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.0883073806762695, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.089780330657959, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.0891501903533936, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.0946195125579834, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.095548152923584, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.102099657058716, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.148545980453491, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06441491325212255, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06404577334809892, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06459948320413436, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06256921373200443, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06256921373200443, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06256921373200443, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.062200073827980804, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06256921373200443, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06478405315614617, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06589147286821706, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06552233296419344, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06736803248431156, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.0695828719084533, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.07069029162052418, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.07142857142857142, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.07198228128460686, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.07290513104466592, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.073827980804725, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.07364341085271318, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.0769656699889258, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.07770394979697305, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.08047249907715023, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.08250276854928018, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.08416389811738649, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.08693244739756367, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.08767072720561092, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.09210040605389443, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.09265411590992986, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.09154669619785899, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.09394610557401255, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.0932078257659653, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.09357696566998892, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.09376153562200074, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.09302325581395349, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.09265411590992986, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.09394610557401255, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.09449981543004798, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.09745293466223699, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.09449981543004798, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.09523809523809523, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.09837578442229605, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.09948320413436693, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.10077519379844961, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.09874492432631968, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.09357696566998892, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.008943909213389277, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.007952560749309672, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.008431860830226852, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.008861984879513752, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.008653458354785308, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.00851403504830995, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.008443880315281182, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.00904096524418735, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.009343441779722675, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.009576160257009627, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.010534839987364654, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.010864329402856296, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.01248217831679919, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.013097791568987016, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.013084903516308371, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.014058331297891332, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.014899222870228969, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.01574556539709881, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.016435009961234655, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.01669938513748959, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.016992021185371523, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.017765109069721008, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.01937228371551115, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.022219923397661347, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.023922528021842138, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.027490120690807158, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.0310181430155595, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.03420425422777058, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.036935949261748084, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.0400868247129924, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.044144943809294075, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.04612795565626656, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.045868455319330065, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.04756263688044552, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.047313093956453035, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.046931060582684626, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.04487654003598677, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.04300675472013807, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.04241368671776241, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.04434989965625332, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.04443081183034784, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.04814493779885918, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.04872500708022768, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.05126757379888056, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.054735586182939354, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.05431812788463303, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.057096061388002994, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.05891887328444214, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.053890500174718914, "id_best": 46, "lr_best": 0.010799999999999999, "wd_best": 0.05, "train/loss_best": 3.064183654785156, "validation/loss_best": 3.095548152923584, "validation/acc_best": 0.10077519379844961, "validation/f1_best": 0.057096061388002994} +{"epoch": 7, "train/lr": 0.00027969249556793234, "train/loss": 3.085267721414566, "train/grad": 0.0754235447384417, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.136412353515625, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.134359130859375, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.131943359375, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.130491943359375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.12958984375, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.12855224609375, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.127921142578125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.127318115234375, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.1266162109375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.12594482421875, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.125166015625, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.124266357421875, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.123289794921875, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.1218408203125, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.120484619140625, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.11915283203125, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.1175830078125, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.115550537109375, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.11329833984375, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.111170654296875, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.108421630859375, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.105535888671875, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.1022412109375, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.0984326171875, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.094501953125, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.08963134765625, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.085316162109375, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.0810699462890625, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.07565185546875, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.069110107421875, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.063516845703125, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.0585784912109375, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.0522357177734376, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.0469482421875, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.0410284423828124, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.035615234375, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.0306396484375, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.02676513671875, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.023580322265625, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.0215859985351563, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.0214752197265624, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.0227236938476563, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.0264288330078126, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.031104736328125, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.0374560546875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.044119873046875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.0511106872558593, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.0630728149414064, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.079270324707031, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.010414539212360978, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.010330561602022498, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.01023869990138337, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.010186435487121344, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.01015618146630004, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.010135258301161229, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.010125696728937327, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.010122301138471812, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.010122164231725038, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.01012330231955275, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.010124744391068816, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.010127398879267275, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.01012961484491825, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.010132544438820333, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.010135883083567023, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.010138682501856238, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.010142834389116616, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.010147369008045644, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.010152314556762576, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.010157183911651373, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.010163317574188114, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.010170149379409849, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.010178650382440537, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.010188726321794093, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.010199119681492447, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.01021398684475571, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.01022922394797206, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.010243839763570578, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.010268185720779002, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.010302242829930038, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.010337700380478054, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.010374144446104764, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.010429530460387469, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.01048421751242131, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.010554799740202726, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.010633867990691215, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.010734043531119824, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.010854648586828261, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.011009694423992187, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.011217931739520282, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.011395885283127427, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.011576428418047726, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.011863175029866398, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.012135609122924506, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.012445693924091757, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.012759663732722401, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.013073508492670954, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.013519462356343865, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.014000825597904623, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1321964263916016, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.129948139190674, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.127534866333008, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1260862350463867, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.125190019607544, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.124412775039673, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.123854398727417, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1233959197998047, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1229186058044434, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.12246036529541, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1219990253448486, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1213529109954834, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1207354068756104, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.119842052459717, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1189517974853516, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1181492805480957, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1170732975006104, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.11580753326416, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.114417552947998, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.1131014823913574, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.111506938934326, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.1098368167877197, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.1080379486083984, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.106013774871826, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.103821039199829, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.100963830947876, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.0980913639068604, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.095144271850586, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.0907866954803467, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.08543062210083, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.0808982849121094, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.077361822128296, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.073408365249634, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.0704426765441895, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.06801176071167, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.0674991607666016, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.0700905323028564, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.0751988887786865, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.0809526443481445, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.082381010055542, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.0826938152313232, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.0875935554504395, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.104504346847534, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.12158465385437, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1388463973999023, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.155463457107544, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1729178428649902, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.206587791442871, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.2234299182891846, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06404577334809892, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06423034330011074, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06423034330011074, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06404577334809892, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06293835363602805, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06293835363602805, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06312292358803986, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.0636766334440753, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06589147286821706, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.0664451827242525, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06884459210040605, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06995201181247693, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.07272056109265411, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.07585825027685493, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.07678110003691399, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.07715023994093761, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.07659653008490218, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.0784422296050203, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.07899593946105574, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.07936507936507936, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.07936507936507936, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.0812107788851975, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.08397932816537468, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.08711701734957548, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.08656330749354005, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.08970099667774087, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.08970099667774087, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.09431524547803617, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.09357696566998892, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.09376153562200074, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.09505352528608342, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.09376153562200074, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.09653008490217793, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.09726836471022518, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.09929863418235511, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.09929863418235511, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.09597637504614248, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.09542266519010704, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.10003691399040236, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.09283868586194167, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.08877814691768181, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.09117755629383537, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.0917312661498708, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.09726836471022518, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.007870776183824417, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.00809611231377618, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.008335637750225028, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.008443658445347122, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.0083241609189909, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.008529761883178423, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.008802950756202856, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.008984265048199687, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.008902050460916126, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.008657690291215934, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.009272353162249487, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.010310825906474247, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.010996593764747662, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.012422065786475233, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.013105289072268838, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.0144826334942655, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.015143477882004987, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.016728832057493828, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.01895050263566016, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.020140282025190206, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.021072677240964535, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.021754344054933192, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.023673536947210024, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.02585454838600965, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.02727556264932966, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.029416140883730745, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.03080431873710988, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.03410619037161574, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.03606881170209384, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.038069775615725436, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.04096110054666296, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.041423890996602215, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.04624368756458511, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.04681080563575654, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.04662570166677649, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.046524337280529106, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.04550854188464173, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.04601793163416304, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.04653884731744686, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.04819841053327831, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.05098034100703391, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.051729857234153014, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.05321301026535749, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.054600921797417906, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.04603808071155204, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.041366966215410354, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.04117798410057139, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.04112218316210062, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.049961875428798395, "id_best": 43, "lr_best": 0.006599999999999999, "wd_best": 0.05, "train/loss_best": 3.031104736328125, "validation/loss_best": 3.12158465385437, "validation/acc_best": 0.10003691399040236, "validation/f1_best": 0.054600921797417906} +{"epoch": 8, "train/lr": 0.0002612959497061927, "train/loss": 3.0774211728572847, "train/grad": 0.07426983522251249, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.136282958984375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.134713134765625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.132830810546875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.13173095703125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.13100830078125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.130294189453125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.129580078125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.128983154296875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.1281494140625, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.1273193359375, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.126494140625, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.1253759765625, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.124244384765625, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.1227001953125, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.121246337890625, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.11970458984375, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.117752685546875, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.11559326171875, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.1129052734375, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.110478515625, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.107255859375, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.104027099609375, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.10014892578125, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.0958642578125, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.091409912109375, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.0858880615234376, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.080966796875, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.076519775390625, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.070467529296875, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.0632891845703125, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.0570135498046875, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.0514276123046873, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.044197998046875, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.0379180908203125, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.0308447265625, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.024246826171875, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.0175994873046874, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.0116836547851564, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.006344909667969, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.0015313720703123, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.999276428222656, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.9986346435546873, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.0001766967773436, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.0030780029296875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.0075830078125, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.014998474121094, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.02279296875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.0331890869140623, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.0478778076171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.01022651496808976, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.010156962142791598, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.010086378594860435, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.010049988706596196, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.01003068389138207, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.010017736398149282, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.010012412823271007, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.010010754151735454, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.010011157458648086, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.010012322578113526, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.010013970332220196, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.010016229103785008, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.010018999150488525, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.010023204663302749, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.010027061824221164, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.010030823769047856, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.01003525489475578, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.010040420033037662, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.010046115585137159, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.010051684870850295, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.010057980036363006, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.010064755640923977, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.010072892534080892, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.01008300885092467, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.010094957342371345, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.010110856385435909, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.010128427913878113, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.010145879660267382, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.01017334957839921, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.010210138240363448, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.010246540040243416, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.01028348839143291, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.01033717127982527, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.010390164873097091, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.01045720248715952, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.010524666381534188, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.010601718933321536, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.010690952979493885, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.010814126392360776, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.011000923512037844, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.011158357844687999, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.011309278884436936, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.011535035739652812, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.011758965328335763, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.01205521557945758, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.012463985164649784, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.012798547241836787, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.013142836592160166, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.013508180258795618, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1298320293426514, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1280903816223145, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.126253843307495, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.125202178955078, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.12457275390625, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.12399959564209, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.123560905456543, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.123150587081909, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1226658821105957, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.122183084487915, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1217331886291504, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1210594177246094, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1204240322113037, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1195075511932373, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1186118125915527, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1177499294281006, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1166417598724365, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1152894496917725, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.113713026046753, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.1122047901153564, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.1102163791656494, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.108031749725342, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.105353355407715, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.102311611175537, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.09898042678833, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.0948257446289062, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.0910327434539795, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.087561845779419, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.0829086303710938, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.077670097351074, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.0734591484069824, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.0700645446777344, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.066230297088623, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.0638060569763184, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.062208414077759, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.0621232986450195, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.06347393989563, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.0651655197143555, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.0657191276550293, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.064115047454834, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.061922550201416, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.0617728233337402, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.06640625, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.0708250999450684, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.072730541229248, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.080859661102295, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.103872537612915, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.134350299835205, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1572911739349365, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06423034330011074, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06459948320413436, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06404577334809892, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06275378368401624, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06275378368401624, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06201550387596899, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.062384643779992616, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06275378368401624, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06441491325212255, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06478405315614617, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06496862310815799, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06570690291620525, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06662975267626431, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06699889258028793, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06829088224437062, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06884459210040605, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.06902916205241787, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.07216685123661867, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.07364341085271318, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.07622739018087855, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.08010335917312661, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.08342561830933924, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.09062384643779993, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.09265411590992986, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.09449981543004798, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.09616094499815431, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.09579180509413067, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.09634551495016612, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.09708379475821337, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.09874492432631968, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.10040605389442599, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.10575858250276855, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.1064968623108158, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.10575858250276855, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.10483573274270949, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.10668143226282761, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.10446659283868587, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.10723514211886305, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.1064968623108158, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.1111111111111111, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.1138796603912883, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.11314138058324105, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.10871170173495755, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.1064968623108158, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.10778885197489849, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.11074197120708748, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.008375463088930288, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.008722540676520028, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.0086025252942264, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.009024638690628119, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.008983225587550221, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.009355229026798709, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.009321092224250297, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.009326796509692958, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.010304390568298587, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.01048394731037912, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.01125357915104499, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.011962682103166518, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.012210965568435256, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.012595190465501553, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.012676206041127298, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.013218050775521078, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.0136594972210552, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.014697918316911347, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.015834006646253385, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.017425939866085743, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.02098166416845497, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.023319817359931005, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.02676664123206678, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.030302517215502343, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.031647576894556835, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.036707470727138196, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.037714412367658455, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.03929471922676268, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.04255373239947271, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.04378293472598149, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.04584006848467559, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.047689908957385584, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.05153581142087683, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.055341886643032, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.061711299907659806, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.06348563254769014, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.06483362126112352, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.0633799359328618, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.06387454292960226, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.05915813783795449, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.0614405428908574, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.05981051190120362, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.060147263358740995, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.06382524822590735, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.06357744272073536, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.058022144679566706, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.05117292438991977, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.04965074298291349, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.04979167503883428, "id_best": 43, "lr_best": 0.006599999999999999, "wd_best": 0.05, "train/loss_best": 3.0030780029296875, "validation/loss_best": 3.0708250999450684, "validation/acc_best": 0.1138796603912883, "validation/f1_best": 0.06382524822590735} +{"epoch": 9, "train/lr": 0.00023803200426111704, "train/loss": 3.0756648421287536, "train/grad": 0.07508523950353264, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.134378662109375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.133045654296875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.13159423828125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.130804443359375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.130189208984375, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.129466552734375, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.1289111328125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.1283740234375, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.1275341796875, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.12667236328125, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.12582763671875, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.1247021484375, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.12345947265625, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.121827392578125, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.120186767578125, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.118590087890625, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.116640625, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.11425537109375, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.111561279296875, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.1089404296875, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.105697021484375, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.10218994140625, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.0982763671875, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.09392578125, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.0892578125, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.08357421875, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.0783953857421875, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.0736236572265625, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.0669097900390625, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.0593212890625, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.0527099609375, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.04681396484375, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.0393280029296874, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.032811279296875, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.0256463623046876, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.0192059326171874, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.0132412719726562, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.008372802734375, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.0041348266601564, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.99991455078125, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.997908630371094, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.997436218261719, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.9991058349609374, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.002982482910156, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.0087680053710937, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.016501159667969, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.024561004638672, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.0348635864257814, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.0451416015625, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.01029693408170715, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.010242755978833885, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.010193107598461211, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.010169056546874344, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.010157799185253679, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.010150621044449509, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.010148279224522412, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.010147506219800562, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.010147721089888364, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.010148661856073887, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.010149516931269318, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.010151202010456472, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.010152481824625283, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.010155007494613528, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.010157331540249288, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.01015917313285172, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.01016200787620619, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.010165308015421032, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.010169474764261395, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.010173945664428174, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.010179692949168383, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.01018696733051911, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.01019547892268747, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.010205929318908602, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.010217943959869445, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.010233821850270032, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.010249329737853259, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.010264843013137579, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.010287894466891885, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.010319423880428075, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.010352121209725737, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.010383967675734311, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.01043132257880643, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.010477998787537217, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.010541937772650271, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.010613934248685836, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.010701385689899326, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.010794533221051096, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.010911341249011457, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.01109010687796399, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.011259584766812623, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.011438067723065614, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.011721322615630924, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.011999888867139817, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.012320596552453935, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.012640000828541815, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.012894419608637691, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.013170109977945686, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.013449441012926399, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.128255844116211, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1268227100372314, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1253902912139893, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.12459659576416, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.124068021774292, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1235673427581787, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1231369972229004, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.122718572616577, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.122177839279175, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1216063499450684, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.121110677719116, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.120323419570923, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1195991039276123, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1185519695281982, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.117579460144043, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.116619825363159, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.115460157394409, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.114100933074951, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.112595319747925, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.1111786365509033, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.109473705291748, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.1077029705047607, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.1057045459747314, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.103532314300537, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.1012957096099854, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.0985848903656006, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.0960543155670166, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.0936970710754395, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.0902962684631348, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.086059808731079, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.0822126865386963, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.0789361000061035, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.07495379447937, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.0718820095062256, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.0682194232940674, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.0641040802001953, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.0592238903045654, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.0549755096435547, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.0520541667938232, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.0514156818389893, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.050758123397827, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.050474166870117, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.0522751808166504, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.0558950901031494, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.0657260417938232, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.0924038887023926, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1266136169433594, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1479709148406982, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.140979766845703, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06423034330011074, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06404577334809892, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06293835363602805, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.062384643779992616, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06293835363602805, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06293835363602805, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06478405315614617, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06386120339608711, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06607604282022887, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06589147286821706, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06755260243632337, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06902916205241787, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06995201181247693, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06847545219638243, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.07013658176448874, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.07290513104466592, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.07198228128460686, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.07493540051679587, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.07807308970099668, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.08028792912513842, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.08139534883720931, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.08453303802141011, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.08674787744555186, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.08711701734957548, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.08859357696567, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.09117755629383537, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.0932078257659653, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.09413067552602436, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.09339239571797711, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.09560723514211886, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.09560723514211886, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.09874492432631968, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.10243632336655592, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.10557401255075674, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.10686600221483943, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.10409745293466224, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.10483573274270949, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.10815799187892211, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.10594315245478036, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.10778885197489849, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.10409745293466224, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.1037283130306386, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.10040605389442599, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.10169804355850867, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.10686600221483943, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.008510051926849345, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.008378132804126156, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.008842413806791186, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.009042574504363438, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.009368250999161746, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.009350556865380456, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.009035342593393367, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.009999338468532354, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.010355248530864952, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.010316023012558705, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.01173783669500478, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.011657273430473314, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.012860062234926563, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.013032726187463638, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.014106977059656892, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.015038551920063273, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.016220572790816772, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.01650344864460203, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.01902324347130145, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.02229188371345783, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.023940102447255415, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.02852070040908672, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.03157364342659602, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.03257934279571938, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.033740017896286965, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.035582581686408564, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.037274651741170776, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.03730581673513006, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.037648003239836324, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.039934090861426554, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.04163152287722228, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.04201976189563376, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.04062442854619046, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.04129238447173877, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.04200454152894776, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.045102873738847325, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.04823496013190684, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.050759966323853566, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.05296834279716386, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.05366822656681389, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.058309703036032993, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.06370205923102643, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.06303339837790829, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.06696696174696401, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.06284764088049659, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.062483213125010595, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.059089435982702, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.05867142777593046, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.058210132642965935, "id_best": 41, "lr_best": 0.0048, "wd_best": 0.05, "train/loss_best": 2.997436218261719, "validation/loss_best": 3.050474166870117, "validation/acc_best": 0.10815799187892211, "validation/f1_best": 0.06370205923102643} +{"epoch": 10, "train/lr": 0.00021091808096876188, "train/loss": 3.0704534316062926, "train/grad": 0.07335644597187638, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.1323046875, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.13114990234375, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.130025634765625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.12922119140625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.128680419921875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.128031005859375, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.127301025390625, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.12668212890625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.12570556640625, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.124764404296875, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.123851318359375, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.12259765625, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.121304931640625, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.119388427734375, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.1175830078125, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.115819091796875, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.11364013671875, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.111002197265625, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.108160400390625, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.105311279296875, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.1018505859375, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.098258056640625, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.093974609375, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.0895953369140625, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.0847344970703126, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.078790283203125, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.0736083984375, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.068885498046875, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.062366943359375, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.054827880859375, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.048526611328125, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.042796630859375, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.0355572509765625, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.0294134521484377, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.022627868652344, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.01632080078125, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.0101077270507814, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.0047027587890627, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.999636535644531, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.9946124267578127, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.9920556640625, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.9907774353027343, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.990786285400391, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.991874084472656, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.994630889892578, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.999034423828125, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.004070129394531, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.011923522949219, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.0233505249023436, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.0100724300253205, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.01002934000454843, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.009991462058387697, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.009974979686085135, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.009967160641681403, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.009963121779728681, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.009961778055876494, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.009961946182884276, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.00996299638878554, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.00996387489605695, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.009965409664437175, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.009967351283412427, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.009969347058795392, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.009972129222005606, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.009974848690908401, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.009977273200638593, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.00998032837640494, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.009984385585412384, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.009988905992358924, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.009993455093353986, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.009999207493383438, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.010005514728836715, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.010013672190252692, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.010023946459405124, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.01003599446732551, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.010053257492836564, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.01006972168572247, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.01008782970253378, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.010114496941678226, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.01014993418706581, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.010185604351572692, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.010220772016327827, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.010270318794064225, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.010315110636875034, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.010371063167694957, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.010431998516432941, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0105092268390581, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.010602456773631275, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.010729321616236121, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.01090569918276742, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.011042947594542057, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0111702397512272, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.011362979987170547, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.011561748157255351, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.011818830696865916, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.012085568010807037, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.012283320724964141, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.012518274164758623, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.012834562351927162, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1271708011627197, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.125997543334961, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1248302459716797, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.124174118041992, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.123708724975586, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.123241424560547, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1227612495422363, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.122263193130493, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.121666193008423, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1210238933563232, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1203882694244385, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.119433641433716, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.118494749069214, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1171398162841797, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.115835189819336, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.114556312561035, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.112924337387085, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.110926628112793, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.108647584915161, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.10648250579834, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.1036882400512695, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.1007273197174072, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.0973093509674072, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.0935235023498535, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.0895464420318604, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.0847995281219482, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.080629348754883, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.077009916305542, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.072355031967163, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.067413806915283, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.0634820461273193, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.060304880142212, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.0566442012786865, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.053945302963257, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.051619052886963, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.0506136417388916, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.0509438514709473, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.0522406101226807, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.0532307624816895, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.0528624057769775, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.0521183013916016, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.0534424781799316, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.0588111877441406, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.067493438720703, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.0799667835235596, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.0956194400787354, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.108808755874634, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.118445634841919, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.11114239692688, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06441491325212255, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06441491325212255, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.062384643779992616, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06293835363602805, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06293835363602805, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06312292358803986, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06496862310815799, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06681432262827612, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06829088224437062, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06995201181247693, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.07161314138058324, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.07198228128460686, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.07419712070874862, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.0754891103728313, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.07918050941306755, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.0828719084533038, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.08600959763750461, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.08859357696567, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.0917312661498708, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.09191583610188261, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.09431524547803617, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.09579180509413067, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.09597637504614248, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.09689922480620156, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.09689922480620156, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.09616094499815431, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.09597637504614248, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.09357696566998892, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.09579180509413067, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.09653008490217793, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.09449981543004798, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.09634551495016612, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.09874492432631968, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.10538944259874493, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.1064968623108158, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.10299003322259136, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.09874492432631968, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.09653008490217793, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.0946843853820598, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.09357696566998892, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.09800664451827243, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.008482850871623973, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.008476989212345657, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.008456409059973054, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.00888784314766219, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.009262687448661395, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.008771691529396655, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.008826259545841654, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.008701321809480264, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.009058125662228932, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.009737987836342237, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.009519842879890888, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.009911873974169377, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.00990126734064683, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.010480432772392302, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.01196303963186659, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.013573057820039253, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.014328032628894484, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.015640248632241643, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.017152351998948993, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.018328397486567432, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.02102223465530721, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.022407751683609922, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.025622492751340004, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.02992810074014965, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.03375265813981373, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.0367317421280938, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.04075982807173644, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.041336010723598604, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.04368483573038447, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.044799831108928566, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.046880818227930304, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.04820025834153396, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.04891249631627875, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.04904159155774664, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.04880609448309098, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.0471976693933558, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.048552773736619266, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.04980361731738922, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.04860787680189379, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.054339252627388, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.05955636766851918, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.06610031951943196, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.07154214079538483, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.07102047476746011, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.06904609175845859, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.06813438619093089, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.06461377521532402, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.06499453882653833, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.06836309702856898, "id_best": 42, "lr_best": 0.005699999999999999, "wd_best": 0.05, "train/loss_best": 2.990786285400391, "validation/loss_best": 3.0588111877441406, "validation/acc_best": 0.1064968623108158, "validation/f1_best": 0.07154214079538483} +{"epoch": 11, "train/lr": 0.00018113997589164516, "train/loss": 3.0626878559589388, "train/grad": 0.07398188173770905, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.13288818359375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.131949462890625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.130784912109375, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.130238037109375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.129708251953125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.12901123046875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.1283203125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.127506103515625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.1265087890625, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.12547607421875, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.1244775390625, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.122955322265625, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.1215380859375, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.1193798828125, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.117406005859375, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.115516357421875, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.1130908203125, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.110311279296875, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.10701171875, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.103941650390625, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.100111083984375, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.09603271484375, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.091507568359375, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.086431884765625, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.0810791015625, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.07459716796875, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.0686663818359374, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.0633349609375, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.0560595703125, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.0474688720703127, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.039976806640625, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.033555908203125, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.0249700927734375, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.0178533935546876, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.0098507690429686, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.002433166503906, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.9950836181640623, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.988712158203125, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.982643737792969, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.9765411376953126, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.972720489501953, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.970033721923828, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.967443542480469, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.966219177246094, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.966999816894531, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.9711930084228517, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.978055648803711, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.9906720733642578, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.0034400177001954, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.010258363937027752, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.010227252331096679, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.01020111374091357, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.010190066883806139, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.01018542556092143, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.010183001218829304, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.010182394315488636, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.01018220408121124, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.010181942672934383, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.010182296172715724, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.010182617311365903, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.010183401526883245, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.010184189442079515, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.010185166562441736, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.010185848092660307, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.010186950892675668, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.010188345720525831, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.010190264615230262, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.010193086254876107, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.010195584534667432, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.0101991774328053, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.010203689413610845, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.01020998612511903, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.010217291822191327, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.010226137449499219, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.010238397314678878, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.010250633205287159, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.010261881547048688, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.010279035659041256, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.010301350706722587, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.010322886866051704, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.010345277497544885, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.010377568125259131, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.01040982339065522, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.010452618270646781, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.010501044224947692, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.010560996022541076, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.010631158598698676, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.01072403488215059, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.010863932790234685, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.010975944637320935, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.011070933043956756, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.011193048097193242, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.011307097226381301, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.011472738133743405, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.011728101465851069, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.012026717704720795, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.01244437085930258, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.012797833904623985, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.126523494720459, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1255033016204834, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.124530553817749, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.123924732208252, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.123537540435791, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1230554580688477, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1225898265838623, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.122096538543701, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1214382648468018, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.12076997756958, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.120115280151367, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1191442012786865, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.118190288543701, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1168172359466553, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.115473747253418, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1141910552978516, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1125307083129883, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.110535144805908, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1082913875579834, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.106109380722046, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.1033480167388916, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.1003527641296387, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.096916437149048, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.093066930770874, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.088953971862793, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.083951234817505, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.0794808864593506, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.075505256652832, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.0703272819519043, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.064589500427246, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.0599420070648193, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.056104898452759, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.0513408184051514, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.047339916229248, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.043107271194458, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.039431571960449, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.0362284183502197, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.034322738647461, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.0347607135772705, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.039199113845825, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.0440220832824707, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.0463531017303467, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.0447840690612793, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.040602207183838, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.0395865440368652, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.0494954586029053, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.0634195804595947, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.0802316665649414, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.0907161235809326, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06423034330011074, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06404577334809892, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.062200073827980804, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.062384643779992616, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06423034330011074, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06533776301218161, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06662975267626431, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.0681063122923588, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06939830195644149, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.07161314138058324, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.07567368032484312, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.07585825027685493, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.0784422296050203, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.08102620893318568, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.08379475821336287, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.0858250276854928, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.08785529715762273, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.08674787744555186, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.09043927648578812, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.09265411590992986, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.0932078257659653, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.09523809523809523, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.09929863418235511, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.09892949427833149, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.09985234403839055, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.10003691399040236, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.10114433370247324, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.10575858250276855, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.1064968623108158, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.10520487264673312, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.10465116279069768, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.1050203026947213, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.11018826135105204, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.11018826135105204, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.11203396087117018, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.11314138058324105, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.1094499815430048, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.10889627168696936, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.10520487264673312, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.1020671834625323, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.09892949427833149, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.10022148394241417, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.008201550083344266, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.00824673465949337, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.008445319944802299, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.009074711820385035, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.008920771796690147, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.00883823440571445, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.00884375805007231, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.008297333556859503, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.00908132370961183, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.009913713844813325, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.010253638527425805, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.010760353755579826, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.011656115508855236, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.01338392876489075, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.014065953756891762, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.015412725059782764, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.01766413475121107, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.021627026588614363, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.022570165833492088, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.025372871597568677, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.027443516140253296, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.029734442716874174, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.032426730181684925, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.035139024624836, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.036553891880123805, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.03926508310902085, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.04126925466652288, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.042350384350354486, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.043873588172829124, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.04684512990879022, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.04684913320042249, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.04766885998393843, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.048104693801498344, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.049436320805728094, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.053415340657977727, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.05485898275590032, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.055032513083441814, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.05511597104173983, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.05387183026051179, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.057449914058484756, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.05690338177268608, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.059302086376060846, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.0646664054449181, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0655171058683021, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.06923952332083481, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.06330603796496886, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.062149029010062785, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.061284020096720404, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0615139927252329, "id_best": 42, "lr_best": 0.005699999999999999, "wd_best": 0.05, "train/loss_best": 2.967443542480469, "validation/loss_best": 3.0447840690612793, "validation/acc_best": 0.11314138058324105, "validation/f1_best": 0.0646664054449181} +{"epoch": 12, "train/lr": 0.0001499999999999999, "train/loss": 3.055309854745865, "train/grad": 0.07304419141262769, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.129395751953125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.128494873046875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.127337646484375, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.126767578125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.126129150390625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.125404052734375, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.124637451171875, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.123773193359375, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.122716064453125, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.121676025390625, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.120609130859375, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.119007568359375, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.117601318359375, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.1154296875, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.11341796875, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.111396484375, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.108927001953125, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.1059423828125, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.102484130859375, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.099212646484375, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.095181884765625, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.090850830078125, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.08593017578125, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.0805322265625, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.0748248291015625, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.0679437255859376, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.06171875, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.05614013671875, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.048603515625, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.03985107421875, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.03227783203125, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.0258673095703124, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.0174850463867187, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.01046875, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.0027127075195312, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.9954473876953127, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.988192138671875, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.981744689941406, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.975274963378906, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.9677584838867186, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.962750244140625, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.95916015625, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.9555313110351564, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.9535751342773438, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.9532427978515625, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.954881591796875, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.9586187744140626, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.966805725097656, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.9764535522460935, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.01017130215652287, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.010142999331001191, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.01012016748310998, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.01011040796060115, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.010106520194094628, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.01010419246274978, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.010103296576999128, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.010103212539106607, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.010103504820726812, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.010103810436557979, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.010104318941012025, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.01010523442644626, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.01010646991431713, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.010107824990991504, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.010109338436741382, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.010111184120178222, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.01011333890259266, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.010115719027817249, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.010118670263327658, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.010121122244745493, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.010124299507588148, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.010127324603963643, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.010131002617999912, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.010134717337787152, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.010139451373834162, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.010146904024295508, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.010154147609136998, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.010161733517888934, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.010173852110747249, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.010191279964055866, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.010210583780426531, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.01023008787073195, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.010261843234766276, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.01029285777360201, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.010333556614350528, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.010377358130645007, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.010429512085393071, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.01048804642399773, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.010562720135785639, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.010668929181993008, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.010763284296263009, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.010858277725055814, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.010993540994822979, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.01112032904755324, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.011286933259107172, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.011495636757463217, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.011708066933788359, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.012015170031227172, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.012292686915025115, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.125994920730591, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.125131845474243, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1242380142211914, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1237215995788574, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.123307943344116, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1228139400482178, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.122326374053955, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1217825412750244, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.121084690093994, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1203391551971436, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1196250915527344, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.118558168411255, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.117494583129883, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.115959644317627, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.114475965499878, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1130082607269287, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1111485958099365, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1089158058166504, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1063454151153564, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.1039485931396484, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.100938081741333, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.097836494445801, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.094290018081665, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.090550422668457, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.086616277694702, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.0820131301879883, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.0779361724853516, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.074298858642578, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.0696184635162354, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.0643200874328613, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.059938430786133, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.0562658309936523, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.051760673522949, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.0482444763183594, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.044788122177124, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.0420076847076416, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.039700984954834, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.0381195545196533, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.0370748043060303, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.0368947982788086, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.0369925498962402, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.0371525287628174, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.038984537124634, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.0429365634918213, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.048767566680908, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.0529186725616455, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.054348945617676, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.0606167316436768, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.073605537414551, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06423034330011074, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06423034330011074, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06404577334809892, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06404577334809892, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.062384643779992616, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.0636766334440753, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06496862310815799, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06626061277224068, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.0681063122923588, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06939830195644149, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.07161314138058324, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.07419712070874862, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.07733480989294943, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.08379475821336287, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.08564045773348099, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.08933185677371724, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.09283868586194167, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.09394610557401255, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.09856035437430787, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.09745293466223699, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.09653008490217793, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.09782207456626062, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.0976375046142488, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.09800664451827243, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.10040605389442599, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.10132890365448505, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.1037283130306386, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.10446659283868587, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.10631229235880399, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.10723514211886305, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.10852713178294573, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.10705057216685124, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.10760428202288667, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.10538944259874493, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.10280546327057954, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.10335917312661498, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.10022148394241417, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.10225175341454411, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.10428202288667406, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.1050203026947213, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.10465116279069768, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.10262089331856773, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.00810524088910531, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.008159069821780456, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.008159158026874782, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.008638892446868565, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.008696830772100936, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.008486374994895322, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.008278896950667242, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.008300964082252733, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.008084461674643653, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.007610852877525084, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.008260892719710469, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.008714094270980187, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.00874620743510348, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.010749381866314614, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.012888989927722902, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.01441789494269319, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.015973623466856948, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.018455647219404295, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.021448805709919794, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.02411211922440176, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.02884834415939058, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.03292935733089177, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.0366858650833761, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.04051019484007597, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.04218640999726944, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.04504788363491672, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.04452257330307976, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.043827377962970045, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.04486769149232506, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.04531404223460082, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.045977668789888904, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.047663650389749825, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.05027334277087026, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.053113753875065776, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.05712964929225258, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.061032395707803576, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.06450134715033505, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.06596694628873627, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.06581647284807349, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.06809450454773948, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.06727266394694999, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.06492018385243654, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.06451290142824113, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.062019086498516514, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.06268824538004436, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.06283304116165295, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.06253317081292703, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.060781493545040845, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.05793033446789043, "id_best": 37, "lr_best": 0.00249, "wd_best": 0.05, "train/loss_best": 2.981744689941406, "validation/loss_best": 3.0381195545196533, "validation/acc_best": 0.10852713178294573, "validation/f1_best": 0.06596694628873627} +{"epoch": 13, "train/lr": 0.00011886002410835478, "train/loss": 3.0489514553546906, "train/grad": 0.07311372023075818, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.1297998046875, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.128914794921875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.127884521484375, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.127154541015625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.126402587890625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.125709228515625, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.12486328125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.12396728515625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.12283935546875, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.1215869140625, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.1204296875, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.11876953125, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.117103271484375, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.11466064453125, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.112354736328125, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.110264892578125, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.10744384765625, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.10414306640625, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.100341796875, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.096885986328125, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.09232666015625, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.087652587890625, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.082432861328125, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.076658935546875, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.0704833984375, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.0631475830078125, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.056593017578125, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.0506756591796873, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.0426678466796875, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.0334393310546877, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.025478515625, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.0184918212890626, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.009576416015625, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.0019244384765624, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.993399963378906, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.9854000854492186, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.977269592285156, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.9702294921875, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.9631402587890623, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.9551626586914064, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.949735107421875, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.9454574584960938, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.9411087036132812, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.9383364868164064, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.9366116333007812, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.9369242858886717, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.9387327575683595, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.943504180908203, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.950542755126953, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.010235727936960757, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.010211368256714195, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.010191467844415457, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.010183220682665705, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.010179881912190467, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.01017785020172596, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.010177039466798305, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.010176730437669902, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.010177016898524016, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.010177183062769473, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.010177624272182583, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.010178106080275029, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.010178504562936723, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.010179667316842824, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.010181244448758661, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.010181921403855085, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.010183558533899486, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.010185658265836537, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.010187768682371826, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.01019032347248867, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.010194025586824864, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.010197606284637005, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.010202461332082748, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.010207727851811796, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.010214646072126925, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.010223469214979559, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.010232625980861484, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.010241501182317734, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.010255972573067993, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.010274212162476032, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.010292350417003035, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.010309289628639817, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.010334086481016129, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.010356073349248618, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.010383685079868882, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.010412865651305765, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.010448514521121978, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.01048945809714496, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.010540533906314521, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.010613565612584353, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.010678923451341688, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.010744853890500963, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.010842712027952076, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.010942174950614572, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.011086703934706748, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.011285181627608836, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.011477592696901412, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.011737607228569686, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.012007022532634437, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.125614881515503, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1248226165771484, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.123995304107666, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1234912872314453, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1230666637420654, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.122544765472412, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1220240592956543, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.121428966522217, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1207008361816406, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.119906187057495, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1191558837890625, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1180083751678467, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.116896152496338, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.115302562713623, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1137633323669434, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.112281322479248, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1104071140289307, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1081597805023193, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.105640411376953, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.1033003330230713, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.1003661155700684, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.0972936153411865, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.0938382148742676, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.0901386737823486, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.0863029956817627, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.0817177295684814, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.077705144882202, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.074148178100586, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.069511890411377, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.0643391609191895, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.060149669647217, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.056680679321289, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.052626848220825, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.0497171878814697, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.0471606254577637, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.0456767082214355, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.0451507568359375, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.0457372665405273, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.0471596717834473, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.04937744140625, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.050865650177002, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.052231550216675, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.0559113025665283, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.0610342025756836, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.066760540008545, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.0691049098968506, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.068140983581543, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.0693931579589844, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.0766420364379883, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06404577334809892, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06459948320413436, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06404577334809892, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06404577334809892, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06404577334809892, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06570690291620525, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06570690291620525, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.067921742340347, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06829088224437062, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.07050572166851236, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.07142857142857142, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.07567368032484312, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.07899593946105574, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.08010335917312661, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.0843484680693983, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.08545588778146918, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.08933185677371724, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.09339239571797711, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.09449981543004798, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.0946843853820598, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.09653008490217793, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.09800664451827243, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.0976375046142488, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.09819121447028424, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.10132890365448505, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.10225175341454411, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.10391288298265043, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.10409745293466224, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.10594315245478036, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.10723514211886305, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.1079734219269103, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.10926541159099298, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.11000369139904023, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.10686600221483943, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.1064968623108158, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.10538944259874493, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.10391288298265043, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.10428202288667406, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.10225175341454411, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.10243632336655592, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.10299003322259136, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.10391288298265043, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.10169804355850867, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.008213682645294621, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.008294725905824115, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.008512072868469054, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.008733870182996553, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.008942797781453675, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.008846398833044994, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.008756403016450667, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.008656031498821867, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.00955068696465515, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.009927342558810547, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.010700737053482873, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.012269938336186344, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.012627887735674014, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.015104474251246251, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.015970857362846504, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.018195117903524193, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.019353922973228247, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.022762069917954847, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.026558137358852863, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.02845033162037371, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.032804922259039734, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.03467753219898004, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.03843536892447421, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.04200147061988687, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.04270796522409004, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.04332424843499428, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.044018442333681324, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.04504044877366534, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.0451599898837633, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.044831779894272145, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.046593227538618685, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.04685656470089692, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.04903208795042319, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.04986648724825742, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.051988573276508764, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.05320477231488768, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.053759267056907846, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.05577701163174823, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.05654198173070549, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.054024111303338694, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.052989346364352485, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.05194798530443048, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.04963358964115999, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.049225338095252334, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.04774754042072383, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.04866397452854928, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.04907858758786316, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.04964062896483069, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.04814558372206665, "id_best": 38, "lr_best": 0.00294, "wd_best": 0.05, "train/loss_best": 2.9631402587890623, "validation/loss_best": 3.0471596717834473, "validation/acc_best": 0.11000369139904023, "validation/f1_best": 0.05654198173070549} +{"epoch": 14, "train/lr": 8.9081919031238e-05, "train/loss": 3.0461887240409853, "train/grad": 0.07263282746076584, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.1272998046875, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.1263818359375, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.12549072265625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.124697265625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.124053955078125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.123253173828125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.1223779296875, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.121444091796875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.12028076171875, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.119078369140625, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.11789794921875, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.116300048828125, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.114578857421875, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.11223876953125, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.110010986328125, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.1079443359375, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.10513916015625, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.101925048828125, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.09831787109375, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.094805908203125, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.0905078125, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.085845947265625, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.080703125, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.0751043701171876, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.06916015625, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.0620147705078127, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.0555865478515627, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.0497576904296877, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.041883544921875, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.0328106689453125, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.0249493408203123, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.017940673828125, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.0090432739257813, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.001414794921875, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.99266845703125, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.9845220947265627, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.9761666870117187, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.9684661865234374, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.9609005737304686, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.952383728027344, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.946462860107422, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.9419680786132814, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.936961975097656, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.93351318359375, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.9307366943359376, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.92921875, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.929509582519531, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.9323880004882814, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.937144012451172, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.01023124449653551, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.010210882741957902, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.010195076712407172, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.010188881622161717, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.010186082287691533, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.010184339107945561, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.010183520561549813, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.010182849543634803, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.010182869292329998, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.010182644599117338, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.010182076103519648, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.010181870732922108, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.010182045600377023, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.010181878069415689, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.010182048736605793, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.01018249086337164, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.0101828606845811, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.010183254291769117, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.010184803118463606, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.010186364785768091, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.010187880429439246, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.010190446684136987, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.01019341593142599, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.010197112311143428, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.010201397112105041, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.01020688729826361, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.010212408085353673, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.010217963729519396, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0102260467922315, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.010236282744444906, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.010246669563930482, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0102569689322263, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.01027264433214441, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.010288915163837373, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.010309566827490926, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.01033261934062466, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.010363559254910797, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.010397888619918376, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.010443341198842972, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.010511732874438167, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.010573054342530667, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.010632793332915754, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.010719629114028066, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.01079964564414695, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.010898131858557463, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.01101370616350323, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.011136885499581695, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.01132745795417577, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.011524238269776105, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.125455617904663, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1247029304504395, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1239492893218994, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1234498023986816, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1230525970458984, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.122573137283325, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.122032403945923, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1214663982391357, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1207354068756104, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1199522018432617, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.119209051132202, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.118107557296753, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1170380115509033, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1154773235321045, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.113986015319824, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.112555503845215, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.110726833343506, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1085519790649414, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1060636043548584, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.103724241256714, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.100742816925049, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.097620964050293, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.094083547592163, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.0902352333068848, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.086191177368164, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.081322431564331, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.0769927501678467, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.073086738586426, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.0679447650909424, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.0621893405914307, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.0573537349700928, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.0533320903778076, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.048433303833008, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.0446479320526123, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.0408527851104736, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.037728786468506, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.0348422527313232, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.03257417678833, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.0301713943481445, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.0276596546173096, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.02652907371521, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.025963544845581, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.026315689086914, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.027400016784668, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.0293869972229004, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.032038688659668, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.036041498184204, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.041740894317627, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.046020746231079, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06404577334809892, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06423034330011074, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06404577334809892, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06496862310815799, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.0651531930601698, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06662975267626431, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.0681063122923588, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.0695828719084533, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06976744186046512, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.07198228128460686, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.07345884090070137, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.0753045404208195, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.07862679955703211, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.08102620893318568, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.08490217792543374, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.0902547065337763, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.09210040605389443, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.0932078257659653, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.09357696566998892, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.09579180509413067, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.09689922480620156, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.09800664451827243, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.09948320413436693, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.10169804355850867, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.1005906238464378, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.10262089331856773, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.1020671834625323, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.1035437430786268, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.10317460317460317, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.10520487264673312, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.10612772240679218, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.10852713178294573, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.10834256183093392, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.10686600221483943, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.10760428202288667, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.10575858250276855, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.10446659283868587, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.10612772240679218, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.10594315245478036, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.1079734219269103, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.10981912144702842, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.008167998509364355, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.00822705469417359, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.008539897960600335, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.008698588926999607, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.008899274443621897, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.008876727062528714, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.008482566260381555, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.008597710104021583, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.009245341160418684, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.00984959036657053, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.00997226923546012, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.011723101850587484, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.01208571176841349, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.013775364211222293, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.01520756952828906, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.016411659350235825, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.017255295580058127, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.01971864265659768, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.02309875623826339, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.025877350536770528, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.029265894575418238, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.03184369450262684, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.03580811866478043, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.03998614378341018, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.040928869167974606, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.04168061418965846, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.041908531397088666, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.0436784211797489, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.044583487360893764, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.04670534275009671, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.049004845053110015, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.051138314720223864, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.05103999830797735, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.053585085312951974, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.054854046366575974, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.056865463504060854, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.05803619120965355, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.060339001392645863, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.061222811344934645, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.06443195784472229, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.06394580966495421, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.06338808370439752, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.06493493763047442, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.06483863043177869, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.065290093130055, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.06792226453012977, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.06745674267117358, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.06816021442811367, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.06828393716016755, "id_best": 48, "lr_best": 0.015, "wd_best": 0.05, "train/loss_best": 2.937144012451172, "validation/loss_best": 3.046020746231079, "validation/acc_best": 0.10981912144702842, "validation/f1_best": 0.06828393716016755} +{"epoch": 15, "train/lr": 6.196799573888289e-05, "train/loss": 3.042474329471588, "train/grad": 0.07233001900836826, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.12936767578125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.128603515625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.12755615234375, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.126866455078125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.1262060546875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.12532958984375, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.124464111328125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.123548583984375, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.1223779296875, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.121046142578125, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.119786376953125, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.1179296875, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.116318359375, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.11382080078125, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.111502685546875, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.1092431640625, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.10640625, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.102998046875, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.09916259765625, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.095576171875, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.091055908203125, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.0863330078125, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.08082763671875, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.0749591064453123, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.068651123046875, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.0611981201171874, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.0543701171875, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.0482293701171876, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.0398956298828126, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.0303314208984373, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.022039794921875, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.01460205078125, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.0051715087890627, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.997008056640625, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.9877325439453126, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.9789630126953126, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.969786376953125, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.9614334106445312, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.95270263671875, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.9428091430664063, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.935663757324219, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.929950866699219, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.9236441040039063, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.918887939453125, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.9145242309570314, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.9112008666992186, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.9095440673828126, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.90982177734375, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.9117974853515625, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.010270657120272517, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.010251687269192188, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.010236656598281116, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.010230445438064634, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.010227496484294534, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.010225133241619914, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.010224166065454484, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.010223378259688616, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.01022240987047553, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.010221751020289958, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.010221484589856118, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.010220254037994892, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.010219617947004735, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.010219048233702779, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.010218534674495459, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.010218048300594092, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.010217465055175125, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.01021696678129956, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.01021671524271369, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.010216586468741297, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.010216797078028321, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.01021721210796386, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.010217798592057079, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.010219148190226407, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.010220593058038503, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.010222795708104969, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.010224597083870322, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.010226212367415428, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.010229853559285402, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.010235174333211035, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.010241132827941328, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.010246342471800745, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.010255422834306955, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.010265187937766313, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.01027876602485776, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.010293443079572171, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.01031195042654872, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.010333656626753509, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.010358048379421234, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.01039259259123355, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.010423972907010465, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.010456322678364813, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0105095105455257, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.01056569357868284, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.010644237259402872, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.010741508489008993, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.010836176571901888, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.010973313483409583, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.011108343959785999, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1253089904785156, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1246087551116943, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1238741874694824, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.123394012451172, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1230010986328125, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.122511148452759, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1219730377197266, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1214005947113037, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.120656728744507, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.119880437850952, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.119135856628418, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1180083751678467, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.116914987564087, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.115344762802124, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1138112545013428, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1123368740081787, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1104235649108887, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1081268787384033, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.105530023574829, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.103069305419922, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.099929094314575, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.0966079235076904, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.0928711891174316, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.0887973308563232, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.084530830383301, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.0794126987457275, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.0748939514160156, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.0708329677581787, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.0655136108398438, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.059516191482544, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.054489850997925, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.0502490997314453, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.0449838638305664, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.0407521724700928, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.0362813472747803, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.032346248626709, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.028738021850586, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.0256664752960205, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.022843837738037, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.0199711322784424, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.0183186531066895, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.0174779891967773, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.0168116092681885, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.016961097717285, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.017815589904785, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.0194222927093506, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.0212552547454834, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.0231423377990723, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.0247068405151367, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06423034330011074, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06404577334809892, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06404577334809892, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.0636766334440753, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.0651531930601698, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06496862310815799, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06718346253229975, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06847545219638243, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06902916205241787, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06976744186046512, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.07050572166851236, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.07475083056478406, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.07733480989294943, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.08139534883720931, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.08342561830933924, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.08674787744555186, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.08988556662975268, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.09136212624584718, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.09357696566998892, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.09431524547803617, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.09449981543004798, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.09653008490217793, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.09966777408637874, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.10188261351052048, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.10225175341454411, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.10557401255075674, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.10483573274270949, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.10686600221483943, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.10723514211886305, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.10834256183093392, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.10981912144702842, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.11074197120708748, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.11037283130306386, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.11166482096714656, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.11203396087117018, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.11166482096714656, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.11369509043927649, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.11258767072720562, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.1111111111111111, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.11129568106312292, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.11148025101513473, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.10852713178294573, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.008091522070605803, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.008206483593944268, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.008557186555227962, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.008715633574967923, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.00891124388249021, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.008588567222512116, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.008731775776881666, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.008801275960005977, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.009483666730230886, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.009631240878098487, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.010250366477153966, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.011660919447956034, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.011840918319240418, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.01384964134760853, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.015339523715859211, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.01607092623333264, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.017432074793520172, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.019450351973386657, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.0243222924333162, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.027784111099243464, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.0316994340893328, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.0342094628754292, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.03834797558958121, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.040473446047711456, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.041772547013306925, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.04322638867025572, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.043763816173766956, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.04450949638463029, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.04596744843736061, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.049443414474966176, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.05124617168303048, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.05228168834779279, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.05476199998471095, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.055257363587056414, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.05749083492576853, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.058088165247251855, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.060508712599369095, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.061632671478857565, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.06256113737052414, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.06292055423193317, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.06402415570290895, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.06454469072464206, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.06547891366835568, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.06670549588385143, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.06537092149537012, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.06443158590761744, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0647494713588088, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.06305603849022341, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.062194665890595774, "id_best": 43, "lr_best": 0.006599999999999999, "wd_best": 0.05, "train/loss_best": 2.918887939453125, "validation/loss_best": 3.016961097717285, "validation/acc_best": 0.11369509043927649, "validation/f1_best": 0.06670549588385143} +{"epoch": 16, "train/lr": 3.870405029380728e-05, "train/loss": 3.041915317773819, "train/grad": 0.07159983936697245, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.1267919921875, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.126024169921875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.125140380859375, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.124461669921875, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.123843994140625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.123126220703125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.1223046875, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.1213720703125, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.120340576171875, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.119097900390625, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.117958984375, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.116229248046875, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.114541015625, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.112152099609375, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.109959716796875, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.1077880859375, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.104971923828125, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.10168212890625, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.097918701171875, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.094385986328125, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.090008544921875, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.085367431640625, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.0800714111328125, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.0744451904296874, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.0683392333984374, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.0611090087890624, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.054503173828125, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.04852783203125, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.0405426025390625, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.0312493896484374, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.0231634521484376, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.0159918212890626, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.0067755126953126, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.998807373046875, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.9895700073242186, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.980837707519531, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.971826477050781, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.963609313964844, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.9550579833984374, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.9451593017578124, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.937886199951172, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.932079162597656, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.9250418090820314, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.9197265625, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.9146417236328124, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.9103759765625, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.90754150390625, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.9058099365234376, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.9056964111328125, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.010200338433496653, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.010183714525774122, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.01017215544823557, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.010167694021947681, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.01016646919073537, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.010165626669768245, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.010165334895718843, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.0101654624636285, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.010164863038808107, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.010164559704717248, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.01016446320572868, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.010164168351329862, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.01016385096590966, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.010163153233006596, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.010162553850095719, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.010162457642145455, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.0101616300502792, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.010161257500294596, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.01016045713564381, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.010159550260286778, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.010158112111967058, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.010157618685625494, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.010157367622014135, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.010156224223319441, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.010156016133259982, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.010155552614014596, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.01015531102893874, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.010155611734371633, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.010156712047755718, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.010159180008340627, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.010161932855844498, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.01016620511887595, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.010173167556058616, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.010181148014962673, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.010192435148637742, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.010205826163291931, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.01022158346604556, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.010237922980450094, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.010258386668283492, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.010284412121400237, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.01030604493804276, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.010326187685132026, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.01035429368261248, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.010381420962512494, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.010420751394703984, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.010468516452237963, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.010517734633758664, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.010587874157354236, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.010659286994487047, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1252479553222656, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.124528169631958, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.123835563659668, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.123335361480713, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.122948169708252, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1224584579467773, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1219184398651123, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.12133526802063, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1205666065216064, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1197850704193115, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1190097332000732, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.117852210998535, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.116713523864746, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1151061058044434, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1135263442993164, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.112013339996338, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1100497245788574, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1076998710632324, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1050260066986084, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.1024906635284424, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.0993247032165527, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.0959436893463135, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.092170000076294, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.0880727767944336, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.083796262741089, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.0787391662597656, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.0742883682250977, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.0703985691070557, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.065277099609375, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.059596300125122, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.0549333095550537, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.0510361194610596, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.046196460723877, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.042360544204712, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.038226842880249, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.034574508666992, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.031175374984741, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.028334379196167, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.0256552696228027, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.02307391166687, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.021517515182495, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.0205798149108887, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.019742727279663, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.019153356552124, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.0188276767730713, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.0193543434143066, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.020259380340576, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.021717071533203, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.0227627754211426, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06404577334809892, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06404577334809892, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06404577334809892, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06404577334809892, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06386120339608711, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06496862310815799, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.0651531930601698, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06699889258028793, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06773717238833518, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.0695828719084533, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06976744186046512, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.07216685123661867, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.07401255075673681, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.07881136950904392, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.08176448874123293, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.08471760797342193, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.08748615725359911, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.09117755629383537, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.09394610557401255, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.09431524547803617, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.09505352528608342, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.09597637504614248, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.0991140642303433, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.10022148394241417, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.1005906238464378, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.10040605389442599, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.10151347360649686, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.1037283130306386, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.10538944259874493, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.10686600221483943, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.10778885197489849, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.1079734219269103, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.10981912144702842, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.11166482096714656, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.11148025101513473, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.11258767072720562, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.11258767072720562, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.11277224067921743, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.1138796603912883, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.11277224067921743, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.11092654115909929, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.11258767072720562, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.11295681063122924, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.008047748389114236, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.008309954658981841, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.00873295175239773, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.008742779413532078, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.008944259453070837, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.008626911579912426, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.008774322645620626, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.009014993062840398, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.009162846553966703, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.009723598119499936, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.01031953135731934, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.011210031046396137, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.011937074017983757, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.01393154328797343, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.014727064379471758, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.016554825913798674, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.017324597591569766, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.02016241121352397, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.02275212820968703, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.02717073821186472, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.030520625431769467, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.03359710434427466, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.03806628756598739, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.041942607626176215, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.044286507251807494, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.0443679949880815, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.045595597484539285, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.046500670310840764, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.048634693558150865, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.0503388530025047, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.051132988353266934, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.05147627514152623, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.052103936516374454, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.053893306204891384, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.05546378616538041, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.057389232675884826, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.05878153199697022, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.05883605675342685, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.06015255687095348, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.06127804144712878, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.0612778915324953, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.06277582936255223, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.06222066868409603, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.06166823782522025, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0627485575670481, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.061649798599358964, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.06067839420223442, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.06226035569797, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.06314850068059219, "id_best": 44, "lr_best": 0.0078, "wd_best": 0.05, "train/loss_best": 2.9146417236328124, "validation/loss_best": 3.0188276767730713, "validation/acc_best": 0.1138796603912883, "validation/f1_best": 0.0627485575670481} +{"epoch": 17, "train/lr": 2.030750443206766e-05, "train/loss": 3.0329271817207335, "train/grad": 0.06999546580016613, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.122685546875, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.121636962890625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.12057373046875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.119813232421875, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.119102783203125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.118289794921875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.117362060546875, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.116539306640625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.115252685546875, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.11400390625, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.112764892578125, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.11097900390625, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.109244384765625, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.106627197265625, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.10429443359375, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.10200439453125, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.099132080078125, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.09557373046875, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.091636962890625, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.08800537109375, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.0833203125, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.0784588623046876, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.0729595947265627, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.066962890625, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.0606640625, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.05294677734375, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.046044921875, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.039873046875, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.0315350341796874, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.0218316650390626, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.0133447265625, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.006081848144531, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.9963534545898436, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.98798583984375, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.9784722900390626, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.96942626953125, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.9600765991210936, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.95145751953125, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.942564697265625, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.932048797607422, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.924482421875, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.918143768310547, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.9106492614746093, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.9048455810546874, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.8990411376953125, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.8940965270996095, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.890438232421875, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.887512512207031, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.8862937927246093, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.010030087435152381, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.010013120120856912, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.010000332170166075, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.009995487742125988, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.00999318615766242, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.009991604338865727, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.009990490034688264, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.009989590956829488, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.009988508634269238, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.00998722508084029, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.009986440490465612, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.009985424731858074, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.00998432083055377, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.009982970694545656, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.009982026333454996, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.009980846422258764, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.00997946044895798, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.009978363355621696, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.009976574743632227, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.009974734981078655, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.009973646919243039, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.009971842290833593, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.009970254534855484, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.009969001512508839, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.009967599296942353, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.009966125884093345, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.009965003249235452, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.009964030224364252, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.009963233666494488, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.00996163099538535, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.009961629207246005, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.009961708798073232, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.009961021854542196, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.009962052584160119, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.009963246220722794, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.009965350504498928, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.009968231660313904, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.009972259770147502, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.009979659470263868, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.009990657023154199, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.01000074737239629, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.010012314296327532, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.010029461628291755, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.010046724982094019, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.010068080462515354, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.01009464104892686, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.010121203435119241, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.010158348164986819, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0101962721766904, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.125188112258911, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.124514102935791, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1238179206848145, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.123328447341919, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.12294340133667, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1224398612976074, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.12190842628479, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.12131404876709, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.120562791824341, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1197614669799805, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.118985652923584, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.117833375930786, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1167209148406982, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.115097761154175, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1134932041168213, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1119771003723145, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.110008478164673, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.107654094696045, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.10497784614563, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.1024630069732666, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.099260091781616, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.0959482192993164, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.0921385288238525, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.088048219680786, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.0837817192077637, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.0787127017974854, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.074200391769409, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.070208787918091, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.0649123191833496, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.0589711666107178, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.0540378093719482, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.0498461723327637, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.0446643829345703, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.0404508113861084, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.0359079837799072, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.0319323539733887, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.0281527042388916, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.025071859359741, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.0220720767974854, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.018941879272461, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.016869306564331, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.0154006481170654, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.013742446899414, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.0126113891601562, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.0116610527038574, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.0111637115478516, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.0113778114318848, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.012346029281616, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.013791799545288, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06423034330011074, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06423034330011074, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06423034330011074, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06423034330011074, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06441491325212255, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06570690291620525, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.0664451827242525, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.067921742340347, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06921373200442968, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06921373200442968, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.07124400147655961, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.07345884090070137, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.07641196013289037, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.08102620893318568, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.08508674787744555, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.08840900701365817, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.09099298634182355, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.09191583610188261, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.09302325581395349, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.09449981543004798, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.09413067552602436, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.09579180509413067, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.09671465485418974, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.09929863418235511, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.10114433370247324, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.10428202288667406, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.10557401255075674, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.10594315245478036, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.10723514211886305, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.1079734219269103, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.10908084163898117, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.11184939091915837, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.11406423034330011, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.11314138058324105, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.11351052048726468, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.11332595053525286, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.11406423034330011, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.11424880029531193, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.11498708010335917, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.11720191952750092, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.11701734957548911, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.11554078995939461, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.00821451852810497, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.008174703455832221, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.008687729150796844, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.009037903840264289, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.008905591584208587, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.008737554852995653, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.00873027593362596, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.008528012683047455, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.00911787974982285, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.009658877231756367, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.009915351044871174, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.01096795102247263, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.011544995702278418, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.013236138047610745, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.014582958707545182, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.01586145097921981, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.01657765686470753, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.019179156460756932, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.022323651710362335, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.025827179740617934, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.029825979713563707, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.034597995415984344, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.03824861297858324, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.04137744091466673, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.04236691819252724, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.04299665633217706, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.04409370191730317, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.04422508448208053, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.04566807150077068, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.046957486423941465, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.04913949972513787, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.05130260732523361, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.05359216480652404, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.05517061351284681, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.05631802077485978, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.057644553103628184, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.05849754918785458, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.059627937382701786, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.062080656367114295, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.06449802839731554, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.06476330124069488, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.06586083275474819, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.06667524449084372, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.06795543760188766, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.06830794945223934, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.06924836545059825, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.07053102428076782, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.07005787725430372, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.06874272131775909, "id_best": 46, "lr_best": 0.010799999999999999, "wd_best": 0.05, "train/loss_best": 2.890438232421875, "validation/loss_best": 3.0113778114318848, "validation/acc_best": 0.11720191952750092, "validation/f1_best": 0.07053102428076782} +{"epoch": 18, "train/lr": 7.5829098008590064e-06, "train/loss": 3.036401994228363, "train/grad": 0.07110020907595754, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.129639892578125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.128944091796875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.127987060546875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.127393798828125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.126778564453125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.125941162109375, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.125042724609375, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.124085693359375, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.12279541015625, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.121610107421875, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.120211181640625, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.118419189453125, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.11656494140625, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.114029541015625, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.111580810546875, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.1091943359375, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.106148681640625, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.1026513671875, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.0985400390625, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.094703369140625, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.08987548828125, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.084849853515625, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.079117431640625, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.07296875, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.066356201171875, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.058402099609375, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.0512127685546875, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.044754638671875, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.0359521484375, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.0257794189453127, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.01700439453125, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.009202880859375, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.9990411376953126, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.9901776123046875, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.9803121948242186, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.970634765625, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.960782775878906, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.951690673828125, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.9420651245117186, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.9308267211914063, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.9224822998046873, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.915648956298828, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.9074079895019533, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.9010270690917968, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.8942063903808593, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.8882044982910156, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.8838323974609374, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.8798703002929686, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.877752227783203, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.010216949169989675, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.010201789315324276, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.010190501105971634, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.010186793478205801, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.010184862245805561, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.010183985468465835, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.010183370655868202, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.010182832418940961, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.0101821855828166, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.01018122114939615, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.010180067440960556, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.010179382655769587, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.010178246123250573, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.010177029257174581, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.01017548507777974, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.010174122415482998, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.010172316718380899, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.01017029715469107, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.010167971435002983, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.010165318408980965, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.010162898250855505, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.01016040119342506, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.010158251039683819, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.010155041445977986, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.01015114550013095, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.010147624283563346, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.010144544683862477, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.010141115209553391, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.01013679148396477, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.010132653082255274, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.010129133467562496, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.010125713536981494, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.01012204702012241, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.010120109668932856, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.010118811272550375, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.010117738686967642, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.010117014837451279, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.010115860933437944, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.01011594496667385, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.010117411150131374, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.010119533818215131, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.010121555656660348, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.01012698215432465, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.01013300150167197, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.010141473652329296, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.010153161261696369, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.01016345840645954, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.010179239453282207, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.010195120538119226, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.125182867050171, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1245169639587402, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.123821973800659, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.123335599899292, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.122938632965088, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1224377155303955, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1218979358673096, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1213128566741943, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1205461025238037, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1197433471679688, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1189746856689453, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1178231239318848, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.116710901260376, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.115070343017578, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.113474130630493, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1119399070739746, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1099774837493896, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.107638120651245, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.104954719543457, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.1024065017700195, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.099231243133545, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.0958869457244873, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.092092514038086, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.087996244430542, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.083691358566284, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.078592300415039, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.0740745067596436, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.07000470161438, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.0646989345550537, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.0586998462677, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.0537285804748535, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.0494585037231445, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.0442440509796143, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.0399367809295654, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.0353405475616455, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.0312280654907227, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.0272982120513916, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.0239903926849365, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.0207138061523438, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.0172698497772217, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.014986038208008, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.013212203979492, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.0112216472625732, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.0098536014556885, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.0086166858673096, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.0075507164001465, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.0069117546081543, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.0064423084259033, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.0062649250030518, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06423034330011074, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06441491325212255, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06423034330011074, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06423034330011074, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06423034330011074, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.0636766334440753, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06496862310815799, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06533776301218161, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06626061277224068, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.067921742340347, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06884459210040605, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06921373200442968, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.07124400147655961, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.07401255075673681, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.07825765965300849, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.08139534883720931, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.08342561830933924, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.0873015873015873, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.09062384643779993, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.09357696566998892, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.09394610557401255, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.0946843853820598, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.09486895533407161, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.09782207456626062, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.10022148394241417, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.10151347360649686, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.10188261351052048, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.10428202288667406, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.10538944259874493, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.10686600221483943, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.10815799187892211, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.11018826135105204, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.11000369139904023, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.10981912144702842, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.1111111111111111, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.11184939091915837, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.11221853082318199, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.11314138058324105, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.1138796603912883, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.11406423034330011, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.11517165005537099, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.11480251015134736, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.11517165005537099, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.11590992986341823, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.008193467604433078, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.008276782261851849, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.00867848586434292, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.009020333747835804, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.00889875690187414, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.008729050393835583, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.008718944371037611, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.00880149633477733, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.009456365852788761, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.010101974305115308, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.01013436924854758, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.011321873041253967, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.011484830287739412, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.013383591307857835, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.014809029661621939, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.015719592706123157, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.01677978640699705, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.01979324235998309, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.022952457378519604, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.02719253129699016, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.030258140963508456, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.03392213223163789, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.03828938394679003, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.04108983593164562, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.043458707161408004, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.04387985208291234, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.04465137238612787, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.044763867770394504, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.046980178253703576, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.04923076168535351, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.05030969540161745, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.05140429295897187, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.05276860039990613, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.054890146428062704, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.056860803454282564, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.05830277914388507, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.060657044148859335, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.06089654238175921, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.06063006017779617, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.061841929152762126, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.06291264372671872, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.06337743719730599, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.06413664885499976, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.06467252420392026, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.06507309886837191, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.06574280571585384, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.06608533073546709, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.06672686900386891, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.06755366073545993, "id_best": 48, "lr_best": 0.015, "wd_best": 0.05, "train/loss_best": 2.877752227783203, "validation/loss_best": 3.0062649250030518, "validation/acc_best": 0.11590992986341823, "validation/f1_best": 0.06755366073545993} +{"epoch": 19, "train/lr": 1.0867618231465446e-06, "train/loss": 3.038657876253128, "train/grad": 0.07080220783129335, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.13111572265625, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.130401611328125, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.129610595703125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.129041748046875, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.1284033203125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.127657470703125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.126732177734375, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.12585205078125, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.1245703125, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.1233203125, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.12209228515625, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.12026611328125, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.11842041015625, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.11584716796875, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.113502197265625, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.1111083984375, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.1081640625, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.1046435546875, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.100556640625, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.09671875, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.092010498046875, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.0869036865234376, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.0813861083984375, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.0750421142578124, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.068564453125, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.06067626953125, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.053543701171875, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.0472113037109376, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.038570556640625, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.028602294921875, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.0199847412109375, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.0122113037109375, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.0022796630859374, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.993652038574219, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.983770446777344, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.974271240234375, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.96443359375, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.955364990234375, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.945770568847656, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.934446105957031, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.9259381103515625, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.9188726806640624, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.9102189636230467, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.903520202636719, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.8963796997070315, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.8897470092773436, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.8850027465820314, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.880346221923828, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.87749267578125, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.0101843081577681, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.01017085979692638, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.010161537947133183, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.01015896724537015, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.010158236336428672, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.010157714341767132, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.010157457878813147, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.010156611171551049, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.010156201550271362, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.010155719264876097, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.01015495078638196, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.010153474383987487, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.010152600163128227, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.01015077390242368, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.010148930181749165, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.010147826340980827, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.010145856556482613, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.010143792177550494, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.010141466800123454, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.010139471178408712, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.010136699434369803, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.01013379093259573, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.010130849143024534, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.010127043558750302, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.010124033882748336, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.010119379956740886, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.010115983088035137, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.010112264996860177, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.010108262719586491, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.010103664661291986, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.010099463560618461, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0100953983142972, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.010090341523755342, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.010086985097732395, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.010081921704113483, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.010077480354811996, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.010073099136352539, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.010069229046348483, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.010065400865860283, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.010061417492106556, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.010058891547378152, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.010056087132543325, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.010054167576599866, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.010052146967500447, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.010050313065294176, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.010049499329179526, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.01005055810790509, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.010052039655856788, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.010054585349280387, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1251795291900635, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1245205402374268, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1238229274749756, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.123333215713501, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1229441165924072, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.122431993484497, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1218948364257812, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.121314287185669, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.120551109313965, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.119745969772339, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1189823150634766, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1178202629089355, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1167044639587402, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.115058183670044, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1134676933288574, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1119422912597656, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.109971284866333, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.107630968093872, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.104951858520508, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.1024067401885986, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.0992205142974854, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.0958733558654785, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.0921010971069336, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.0879862308502197, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.0836985111236572, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.078601598739624, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.0740506649017334, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.070021629333496, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.064696788787842, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.0587263107299805, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.0537571907043457, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.0495307445526123, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.0443053245544434, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.0400571823120117, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.035532236099243, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.0315163135528564, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.0277063846588135, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.0244345664978027, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.021399736404419, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.018148422241211, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.0160434246063232, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.014458417892456, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.0126707553863525, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.0113720893859863, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.010237216949463, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.0092201232910156, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.008491039276123, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.0078675746917725, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.007640838623047, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06423034330011074, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06441491325212255, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06423034330011074, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06423034330011074, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06423034330011074, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.0636766334440753, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06496862310815799, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.0651531930601698, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.0664451827242525, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06829088224437062, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06884459210040605, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06921373200442968, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.07124400147655961, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.073827980804725, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.0784422296050203, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.08139534883720931, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.08342561830933924, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.08785529715762273, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.0902547065337763, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.09357696566998892, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.09431524547803617, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.09413067552602436, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.09394610557401255, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.09671465485418974, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.1005906238464378, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.10151347360649686, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.10317460317460317, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.10428202288667406, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.10631229235880399, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.10705057216685124, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.10760428202288667, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.10889627168696936, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.10981912144702842, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.10981912144702842, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.11037283130306386, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.1111111111111111, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.11092654115909929, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.11277224067921743, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.11295681063122924, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.11277224067921743, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.11277224067921743, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.11332595053525286, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.11277224067921743, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.11332595053525286, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.008190004999921315, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.008273290625304812, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.008681145371722184, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.009023822369269642, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.008895358327996672, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.008729050393835583, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.008712791164454127, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.008822628659212134, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.009453592623690792, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.010099713976200892, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.010132075298269374, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.011320988015078193, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.01145921583357082, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.013528100277150167, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.01501993934403536, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.015718323175232665, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.017122502404380673, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.019765555058917274, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.023197782908282994, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.02727284432798062, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.030225651887289567, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.033976888898267395, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.038706872328820106, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.04088169692291029, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.04339604371469127, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.04419881835870714, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.04412873170999928, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.044495142570114464, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.04634879356529678, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.04940032610783742, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.05032062192644029, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.05212802991236274, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.05303954061882285, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.05506082185924968, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.05668627037990215, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.05794881943184744, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.05937152905301629, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.05996281757953934, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.060337277794887366, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.06061291174957557, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.06194176391295592, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.062044253258444565, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.06345095977747271, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.06396411403584173, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.06398684111363524, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.06450680136474138, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.06515514316617416, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.06484092407494052, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.06515605508971356, "id_best": 46, "lr_best": 0.010799999999999999, "wd_best": 0.05, "train/loss_best": 2.8850027465820314, "validation/loss_best": 3.008491039276123, "validation/acc_best": 0.11332595053525286, "validation/f1_best": 0.06515514316617416} diff --git a/decoders/crossreg_reg4/eval_v2/ppmi_dx__patch__logistic/config.yaml b/decoders/crossreg_reg4/eval_v2/ppmi_dx__patch__logistic/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..374eb984f2e862f97f0f56c5cad5e73ad7f85c33 --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/ppmi_dx__patch__logistic/config.yaml @@ -0,0 +1,30 @@ +output_root: experiments/decoders/output +name_prefix: eval_logistic +remote_root: null +notes: decoder ablations crossreg_reg4; eval v2 (ppmi_dx patch logistic) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: decoders/crossreg_reg4/eval_v2/ppmi_dx__patch__logistic +model: flat_mae +representation: patch +dataset: ppmi_dx +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg4/eval_v2/ppmi_dx__patch__logistic +remote_dir: null diff --git a/decoders/crossreg_reg4/eval_v2/ppmi_dx__patch__logistic/eval_table.csv b/decoders/crossreg_reg4/eval_v2/ppmi_dx__patch__logistic/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..e4721e1988f2cd5c5ec3f3259f6fcdc7b08e1a95 --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/ppmi_dx__patch__logistic/eval_table.csv @@ -0,0 +1,203 @@ +model,repr,clf,dataset,trial,C,split,acc,acc_std,f1,f1_std,bacc,bacc_std +flat_mae,patch,logistic,ppmi_dx,,0.3593813663804626,train,0.9163701067615658,0.011706690079679822,0.9107523575582083,0.012620931401142621,0.9062378948774461,0.013176425268692307 +flat_mae,patch,logistic,ppmi_dx,,0.3593813663804626,test,0.64,0.04450195051905029,0.609375,0.0483200918126307,0.6083226083226083,0.047601825500014086 +flat_mae,patch,logistic,ppmi_dx,1,0.005994842503189409,train,0.7117437722419929,0.015384295125810212,0.6561366932559827,0.020460498244242103,0.6537010276172126,0.01769438233279804 +flat_mae,patch,logistic,ppmi_dx,1,0.005994842503189409,test,0.69,0.037193391886193965,0.6196785670469881,0.05143288549270446,0.6226655348047538,0.04249458525066637 +flat_mae,patch,logistic,ppmi_dx,2,0.046415888336127774,train,0.7758007117437722,0.0157604067392748,0.7475508021390374,0.01888731954092731,0.7379040890601585,0.018136489993756104 +flat_mae,patch,logistic,ppmi_dx,2,0.046415888336127774,test,0.71,0.04363255665211471,0.6833715471121302,0.04833159118624529,0.6795415959252971,0.0470824433207542 +flat_mae,patch,logistic,ppmi_dx,3,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,3,2.782559402207126,test,0.63,0.047144284913444176,0.6129302228266555,0.04881074815562475,0.615025466893039,0.04956718039740403 +flat_mae,patch,logistic,ppmi_dx,4,0.046415888336127774,train,0.7775800711743772,0.01739317244756348,0.7492173081110798,0.020710892865811154,0.7393491757653607,0.01986965621318437 +flat_mae,patch,logistic,ppmi_dx,4,0.046415888336127774,test,0.69,0.042182157365407466,0.6467236467236468,0.04970418204741729,0.6430390492359932,0.0461336006381166 +flat_mae,patch,logistic,ppmi_dx,5,0.3593813663804626,train,0.9199288256227758,0.011489570063118374,0.9140482947304025,0.01255161468265622,0.9080095268679084,0.013325352399215975 +flat_mae,patch,logistic,ppmi_dx,5,0.3593813663804626,test,0.59,0.05023733671284735,0.5577607593571352,0.053850778638830005,0.5573005093378608,0.0528237028136196 +flat_mae,patch,logistic,ppmi_dx,6,0.046415888336127774,train,0.798932384341637,0.015223779606532963,0.7762321046641508,0.017749243923480172,0.766257225433526,0.01744495945704889 +flat_mae,patch,logistic,ppmi_dx,6,0.046415888336127774,test,0.61,0.049025589236642526,0.5741893219783819,0.05351322850018915,0.5734295415959253,0.05181207979461741 +flat_mae,patch,logistic,ppmi_dx,7,0.046415888336127774,train,0.7864768683274022,0.01661608900126325,0.7614601018675722,0.019291893711560208,0.7517929779490473,0.018729993595998407 +flat_mae,patch,logistic,ppmi_dx,7,0.046415888336127774,test,0.62,0.04676020102608627,0.5924495924495925,0.0505749568865701,0.5916808149405772,0.05008205116269654 +flat_mae,patch,logistic,ppmi_dx,8,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,8,21.54434690031882,test,0.55,0.049094504784140555,0.5248653785239151,0.05099104168641188,0.5250424448217317,0.051349640527547646 +flat_mae,patch,logistic,ppmi_dx,9,0.3593813663804626,train,0.9074733096085409,0.012181770165817103,0.9003763499509109,0.013381478353883905,0.8935452793834298,0.01416928746263555 +flat_mae,patch,logistic,ppmi_dx,9,0.3593813663804626,test,0.62,0.046072534117411,0.5967741935483871,0.048829889268775684,0.5967741935483871,0.04851699556668779 +flat_mae,patch,logistic,ppmi_dx,10,0.005994842503189409,train,0.7135231316725978,0.015816455239056375,0.655284342224068,0.021684247462855945,0.6534066581031899,0.01851674667260725 +flat_mae,patch,logistic,ppmi_dx,10,0.005994842503189409,test,0.63,0.03838463755202074,0.5552350042072365,0.049175198696911185,0.5640916808149405,0.041777185287987614 +flat_mae,patch,logistic,ppmi_dx,11,0.046415888336127774,train,0.7829181494661922,0.016601222855451004,0.7568549016270196,0.019683166012568677,0.7471633483194177,0.019086355318877684 +flat_mae,patch,logistic,ppmi_dx,11,0.046415888336127774,test,0.68,0.04391992714019456,0.6381727725011307,0.0523755861383105,0.634974533106961,0.048972621625394876 +flat_mae,patch,logistic,ppmi_dx,12,0.046415888336127774,train,0.7846975088967971,0.016909367541532327,0.7597807003599651,0.019801070552627118,0.750347891243845,0.019314752170060706 +flat_mae,patch,logistic,ppmi_dx,12,0.046415888336127774,test,0.63,0.04240552322516491,0.5552350042072365,0.05241277695149047,0.5640916808149405,0.045434250565029075 +flat_mae,patch,logistic,ppmi_dx,13,0.046415888336127774,train,0.7953736654804271,0.01553364110251192,0.7711037523684723,0.0183733973463661,0.7607578676942839,0.01798584255230683 +flat_mae,patch,logistic,ppmi_dx,13,0.046415888336127774,test,0.61,0.040418703591283085,0.5555555555555556,0.04805435854636089,0.5581494057724957,0.043853063633789706 +flat_mae,patch,logistic,ppmi_dx,14,0.046415888336127774,train,0.7900355871886121,0.016423374189450852,0.764826872065478,0.019387689936877336,0.754683151359452,0.01893445756863958 +flat_mae,patch,logistic,ppmi_dx,14,0.046415888336127774,test,0.58,0.042118423522254485,0.5091164095371669,0.04973581474771774,0.5186757215619694,0.044057369237435896 +flat_mae,patch,logistic,ppmi_dx,15,0.046415888336127774,train,0.7882562277580071,0.01610988595320308,0.7618940809968847,0.019234505724852184,0.7514986084350246,0.01862815505804065 +flat_mae,patch,logistic,ppmi_dx,15,0.046415888336127774,test,0.63,0.047278659033437066,0.6053333333333333,0.05000037379260817,0.6048387096774194,0.049604437323765904 +flat_mae,patch,logistic,ppmi_dx,16,0.046415888336127774,train,0.7935943060498221,0.015150448841537646,0.7675864527629234,0.018164458828965946,0.756703596660244,0.01771726631654102 +flat_mae,patch,logistic,ppmi_dx,16,0.046415888336127774,test,0.62,0.04619338047815943,0.5924495924495925,0.04875801163597031,0.5916808149405772,0.048189113464747864 +flat_mae,patch,logistic,ppmi_dx,17,0.046415888336127774,train,0.7829181494661922,0.015910154462881174,0.7555650623885919,0.019010694348775142,0.7454238921001928,0.018347727390133392 +flat_mae,patch,logistic,ppmi_dx,17,0.046415888336127774,test,0.59,0.04643830746269721,0.5523528769516323,0.04992393917256893,0.5522071307300509,0.04834835176959865 +flat_mae,patch,logistic,ppmi_dx,18,0.005994842503189409,train,0.7135231316725978,0.015871972296017438,0.6622331390943061,0.020395146963554878,0.6586250267608649,0.017998611443857032 +flat_mae,patch,logistic,ppmi_dx,18,0.005994842503189409,test,0.6,0.03981515289434413,0.503968253968254,0.04975757739910872,0.5246179966044142,0.04155150460677975 +flat_mae,patch,logistic,ppmi_dx,19,0.046415888336127774,train,0.7953736654804271,0.015528596876598832,0.7711037523684723,0.01823339866973452,0.7607578676942839,0.01783929215592276 +flat_mae,patch,logistic,ppmi_dx,19,0.046415888336127774,test,0.62,0.04592395453355471,0.5967741935483871,0.048101012008295,0.5967741935483871,0.04810968866663364 +flat_mae,patch,logistic,ppmi_dx,20,0.005994842503189409,train,0.7153024911032029,0.0171539477904743,0.6626650660264106,0.022222065366216254,0.6592003853564548,0.01952708045049122 +flat_mae,patch,logistic,ppmi_dx,20,0.005994842503189409,test,0.59,0.0424183733775825,0.5327635327635327,0.04878439513511393,0.5369269949066213,0.04471737562254186 +flat_mae,patch,logistic,ppmi_dx,21,0.005994842503189409,train,0.702846975088968,0.015960242711166677,0.6461264087414551,0.02087470919698404,0.644736137871976,0.01810020619671872 +flat_mae,patch,logistic,ppmi_dx,21,0.005994842503189409,test,0.65,0.036134609448560534,0.5706048337627285,0.05000888475712918,0.580220713073005,0.040653154270296754 +flat_mae,patch,logistic,ppmi_dx,22,0.046415888336127774,train,0.7829181494661922,0.016440589407888426,0.7568549016270196,0.019496622314428037,0.7471633483194177,0.018947389106701157 +flat_mae,patch,logistic,ppmi_dx,22,0.046415888336127774,test,0.61,0.04382610637508196,0.5623386825272135,0.05011234368054188,0.5632427843803056,0.04701199837227422 +flat_mae,patch,logistic,ppmi_dx,23,2.782559402207126,train,0.998220640569395,0.0016728401429737646,0.9981184064710746,0.0017716677827968323,0.9976851851851851,0.002176241111924203 +flat_mae,patch,logistic,ppmi_dx,23,2.782559402207126,test,0.56,0.047949973931171216,0.5280995280995281,0.050581385175900974,0.5280135823429541,0.0498075459989968 +flat_mae,patch,logistic,ppmi_dx,24,0.046415888336127774,train,0.797153024911032,0.015534014094907555,0.7715935828877005,0.018550090712491273,0.7604634981802612,0.018000509774299726 +flat_mae,patch,logistic,ppmi_dx,24,0.046415888336127774,test,0.63,0.04310438956765309,0.5783475783475784,0.05156997838681207,0.5793718166383701,0.0472088107167295 +flat_mae,patch,logistic,ppmi_dx,25,0.046415888336127774,train,0.791814946619217,0.016564832870367314,0.7658958611481976,0.019565312923586143,0.7552585099550417,0.018937913466389785 +flat_mae,patch,logistic,ppmi_dx,25,0.046415888336127774,test,0.65,0.03781222553619398,0.5792763553311696,0.04925129054849584,0.5853140916808149,0.04195847801194228 +flat_mae,patch,logistic,ppmi_dx,26,0.046415888336127774,train,0.791814946619217,0.01588795605416835,0.7665143331948484,0.01886412508714612,0.7561282380646542,0.018374653808514375 +flat_mae,patch,logistic,ppmi_dx,26,0.046415888336127774,test,0.62,0.046266290104135216,0.5876736111111112,0.05071411252272973,0.5865874363327674,0.04948078355165446 +flat_mae,patch,logistic,ppmi_dx,27,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,27,2.782559402207126,test,0.52,0.04744183386000166,0.4851994851994852,0.04903891521958805,0.48556876061120546,0.04845482005232822 +flat_mae,patch,logistic,ppmi_dx,28,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,28,166.81005372000556,test,0.51,0.04745296197288427,0.47733333333333333,0.04947548067764703,0.4775042444821732,0.04897831708452532 +flat_mae,patch,logistic,ppmi_dx,29,0.046415888336127774,train,0.7935943060498221,0.016265484958560922,0.770579954954955,0.019068278084215018,0.7610522372083066,0.01874167778403859 +flat_mae,patch,logistic,ppmi_dx,29,0.046415888336127774,test,0.63,0.043927594971725915,0.5783475783475784,0.05158268927883656,0.5793718166383701,0.047413641722442286 +flat_mae,patch,logistic,ppmi_dx,30,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,30,2.782559402207126,test,0.65,0.04639297791692186,0.6266666666666667,0.04969893156841365,0.6260611205432938,0.049709614032592546 +flat_mae,patch,logistic,ppmi_dx,31,0.046415888336127774,train,0.7953736654804271,0.01613808141514998,0.7716924011685619,0.018912363485367185,0.7616275958038964,0.01845925400490711 +flat_mae,patch,logistic,ppmi_dx,31,0.046415888336127774,test,0.67,0.046788592626835865,0.6396986570586308,0.05152284443045045,0.6370967741935484,0.05006119276968571 +flat_mae,patch,logistic,ppmi_dx,32,0.046415888336127774,train,0.797153024911032,0.015643763818580222,0.7709763212079617,0.018898443184965953,0.7595937700706487,0.01832843632040715 +flat_mae,patch,logistic,ppmi_dx,32,0.046415888336127774,test,0.65,0.04433001240694616,0.6178622120318812,0.04947280621863624,0.615874363327674,0.048069732548444134 +flat_mae,patch,logistic,ppmi_dx,33,0.046415888336127774,train,0.7811387900355872,0.015957814411195485,0.7518763796909492,0.0194003570257419,0.7413696210661529,0.01857613035688093 +flat_mae,patch,logistic,ppmi_dx,33,0.046415888336127774,test,0.7,0.0428000186915847,0.6744791666666667,0.04694778153520295,0.6714770797962648,0.04620378084258026 +flat_mae,patch,logistic,ppmi_dx,34,0.046415888336127774,train,0.7793594306049823,0.017401180027492684,0.7502043157215571,0.020816736140168792,0.7399245343609505,0.01988329817096448 +flat_mae,patch,logistic,ppmi_dx,34,0.046415888336127774,test,0.69,0.0440477014156244,0.6570417081535569,0.049461006342273406,0.6532258064516129,0.04773720657653101 +flat_mae,patch,logistic,ppmi_dx,35,0.005994842503189409,train,0.7170818505338078,0.015735373548939394,0.6619261108904149,0.021093475891493425,0.658906015842432,0.018257051715505755 +flat_mae,patch,logistic,ppmi_dx,35,0.005994842503189409,test,0.63,0.04692043904312917,0.6053333333333333,0.04975282820326576,0.6048387096774194,0.049029207431765795 +flat_mae,patch,logistic,ppmi_dx,36,0.3593813663804626,train,0.900355871886121,0.01213031699368968,0.8933542974097619,0.01313721260148069,0.8886346606722328,0.013744888359320962 +flat_mae,patch,logistic,ppmi_dx,36,0.3593813663804626,test,0.62,0.04369431999699732,0.5703301673450927,0.049390434740036716,0.5713073005093379,0.04586387973542212 +flat_mae,patch,logistic,ppmi_dx,37,0.046415888336127774,train,0.7740213523131673,0.015653254990204153,0.7458869603916333,0.018593804175555246,0.7364590023549561,0.017835312331536443 +flat_mae,patch,logistic,ppmi_dx,37,0.046415888336127774,test,0.68,0.04297483449648177,0.6381727725011307,0.05080262872779873,0.634974533106961,0.04731635340359598 +flat_mae,patch,logistic,ppmi_dx,38,0.3593813663804626,train,0.9145907473309609,0.011121572084745937,0.9078499692559951,0.012268011517935785,0.9001953543138514,0.013192189018905185 +flat_mae,patch,logistic,ppmi_dx,38,0.3593813663804626,test,0.65,0.04766372205357026,0.6266666666666667,0.05046141299982007,0.6260611205432938,0.050184114711797685 +flat_mae,patch,logistic,ppmi_dx,39,0.005994842503189409,train,0.693950177935943,0.016132536935941407,0.6297646770437553,0.02215703463220019,0.631422607578677,0.018634150110563494 +flat_mae,patch,logistic,ppmi_dx,39,0.005994842503189409,test,0.69,0.038497189507806916,0.627359057579036,0.05071069920724843,0.6277589134125636,0.0433741512899555 +flat_mae,patch,logistic,ppmi_dx,40,0.005994842503189409,train,0.701067615658363,0.015645932869582473,0.6383748008334355,0.02136213855309582,0.6389424106187112,0.01803525481239471 +flat_mae,patch,logistic,ppmi_dx,40,0.005994842503189409,test,0.7,0.03810710694870446,0.6357455075279261,0.052275779735190014,0.6358234295415959,0.04425024011612922 +flat_mae,patch,logistic,ppmi_dx,41,0.046415888336127774,train,0.7864768683274022,0.015659282972003367,0.7608408868462488,0.018171580559528777,0.7509232498394348,0.017502557618710928 +flat_mae,patch,logistic,ppmi_dx,41,0.046415888336127774,test,0.67,0.04394212557444166,0.6440513428972063,0.04770651754276264,0.6421901528013583,0.04708817045128571 +flat_mae,patch,logistic,ppmi_dx,42,10000.0,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,42,10000.0,test,0.6,0.04450231005240065,0.5324918186068257,0.05303658568642919,0.5398981324278438,0.04730355755025885 +flat_mae,patch,logistic,ppmi_dx,43,0.005994842503189409,train,0.7046263345195729,0.016176188193603194,0.6488399054458949,0.021632343272587833,0.6470509526867909,0.018765373078451015 +flat_mae,patch,logistic,ppmi_dx,43,0.005994842503189409,test,0.66,0.04081099851755651,0.587178241864983,0.053270981260931695,0.5933786078098472,0.04524859277435758 +flat_mae,patch,logistic,ppmi_dx,44,0.005994842503189409,train,0.702846975088968,0.016226128406658297,0.648490840926881,0.021197379451692113,0.646475594091201,0.0185293007872889 +flat_mae,patch,logistic,ppmi_dx,44,0.005994842503189409,test,0.66,0.03682548574017727,0.5783730158730158,0.052844326132826615,0.5882852292020373,0.04246461965268768 +flat_mae,patch,logistic,ppmi_dx,45,0.005994842503189409,train,0.7064056939501779,0.016050544444056927,0.6503644158223958,0.02143363929706267,0.6484960393919932,0.01851717583739927 +flat_mae,patch,logistic,ppmi_dx,45,0.005994842503189409,test,0.69,0.03816831670377932,0.6196785670469881,0.05246264235207439,0.6226655348047538,0.04375840088183484 +flat_mae,patch,logistic,ppmi_dx,46,0.046415888336127774,train,0.791814946619217,0.015906065682464176,0.7658958611481976,0.018891678952493787,0.7552585099550417,0.018344449619671292 +flat_mae,patch,logistic,ppmi_dx,46,0.046415888336127774,test,0.54,0.04589586473746845,0.4945054945054945,0.049851715050077634,0.49660441426146007,0.04746562854363071 +flat_mae,patch,logistic,ppmi_dx,47,0.3593813663804626,train,0.905693950177936,0.011976505497538682,0.8977111557547348,0.013337491911751358,0.8886212802397773,0.01416474128768666 +flat_mae,patch,logistic,ppmi_dx,47,0.3593813663804626,test,0.74,0.041766067566865815,0.7241086587436333,0.044622807805426296,0.7241086587436333,0.04502236424092212 +flat_mae,patch,logistic,ppmi_dx,48,0.005994842503189409,train,0.7064056939501779,0.01668135905045708,0.6415857886620053,0.02311423837296759,0.6424079426247057,0.019291048630373904 +flat_mae,patch,logistic,ppmi_dx,48,0.005994842503189409,test,0.68,0.04473135812827506,0.64349376114082,0.052129289125197514,0.6400679117147707,0.049227455936849684 +flat_mae,patch,logistic,ppmi_dx,49,0.046415888336127774,train,0.7882562277580071,0.016991118389539695,0.7592749236013376,0.020611827724808986,0.7480196959965746,0.019703566684493568 +flat_mae,patch,logistic,ppmi_dx,49,0.046415888336127774,test,0.66,0.039134123217468404,0.5952380952380952,0.05037276854222254,0.5984719864176571,0.04331711704145282 +flat_mae,patch,logistic,ppmi_dx,50,0.005994842503189409,train,0.697508896797153,0.015455618850461277,0.639155789219241,0.020011248794308618,0.6386614215371441,0.017373125310600205 +flat_mae,patch,logistic,ppmi_dx,50,0.005994842503189409,test,0.69,0.03838697695833835,0.6196785670469881,0.05240579979108466,0.6226655348047538,0.043570607588362044 +flat_mae,patch,logistic,ppmi_dx,51,0.3593813663804626,train,0.9128113879003559,0.011351322483798032,0.9065935370515469,0.012332637629428952,0.9013594519374866,0.012996790925483573 +flat_mae,patch,logistic,ppmi_dx,51,0.3593813663804626,test,0.57,0.0476952156929812,0.5305164319248826,0.05086739799942668,0.5309847198641766,0.04924260768754011 +flat_mae,patch,logistic,ppmi_dx,52,2.782559402207126,train,0.998220640569395,0.0017397149399655996,0.9981216765874674,0.0018333758649182613,0.9985549132947977,0.0014128898789894102 +flat_mae,patch,logistic,ppmi_dx,52,2.782559402207126,test,0.59,0.048330925917056455,0.5670995670995671,0.0495393978808992,0.5674872665534805,0.04966215010192966 +flat_mae,patch,logistic,ppmi_dx,53,0.3593813663804626,train,0.9110320284697508,0.011819367928907086,0.9053234501347709,0.012721317243799312,0.9025235495611218,0.013426211061833995 +flat_mae,patch,logistic,ppmi_dx,53,0.3593813663804626,test,0.62,0.045912346923240595,0.5824175824175825,0.05056920295569798,0.5814940577249575,0.04876007487107554 +flat_mae,patch,logistic,ppmi_dx,54,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,54,21.54434690031882,test,0.54,0.046294617397706184,0.5008680555555556,0.048581951636397266,0.50169779286927,0.047545969009596845 +flat_mae,patch,logistic,ppmi_dx,55,0.005994842503189409,train,0.7188612099644128,0.01541495501567494,0.6623007180236096,0.020591154015345257,0.6594813744380219,0.017734922871975357 +flat_mae,patch,logistic,ppmi_dx,55,0.005994842503189409,test,0.65,0.04582001309471659,0.6072270227808326,0.05255040260592497,0.6056876061120543,0.04909613280550803 +flat_mae,patch,logistic,ppmi_dx,56,0.005994842503189409,train,0.7259786476868327,0.01536815506885874,0.6753151260504202,0.020500931805472147,0.6704800899165061,0.018050328965201947 +flat_mae,patch,logistic,ppmi_dx,56,0.005994842503189409,test,0.59,0.041520481692774225,0.5071523019593701,0.050603928142715686,0.5216468590831919,0.043540979754395505 +flat_mae,patch,logistic,ppmi_dx,57,0.046415888336127774,train,0.7811387900355872,0.01560170069824117,0.753890520694259,0.01853409074673253,0.7439788053949904,0.0179290374046401 +flat_mae,patch,logistic,ppmi_dx,57,0.046415888336127774,test,0.68,0.044190388095150274,0.6381727725011307,0.05226391369227922,0.634974533106961,0.0488612132035058 +flat_mae,patch,logistic,ppmi_dx,58,0.046415888336127774,train,0.7829181494661922,0.01555892886653243,0.7514392192688621,0.01938460451308252,0.7402055234425177,0.01834716952000842 +flat_mae,patch,logistic,ppmi_dx,58,0.046415888336127774,test,0.63,0.0442220714123615,0.5783475783475784,0.051402457675031384,0.5793718166383701,0.047487356837794696 +flat_mae,patch,logistic,ppmi_dx,59,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,59,2.782559402207126,test,0.64,0.049953974816825134,0.6216897856242118,0.05224459760723616,0.6230899830220713,0.05254424356813113 +flat_mae,patch,logistic,ppmi_dx,60,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,60,21.54434690031882,test,0.57,0.04672014982852687,0.5361881134721174,0.05040341367348005,0.5360780984719864,0.04915461024024188 +flat_mae,patch,logistic,ppmi_dx,61,0.046415888336127774,train,0.7882562277580071,0.016628109214015634,0.761254877321748,0.019874052768882072,0.7506288803254121,0.019207295899749715 +flat_mae,patch,logistic,ppmi_dx,61,0.046415888336127774,test,0.63,0.04598387108541429,0.5847828526540231,0.051532753348824054,0.5844651952461799,0.04839877495121012 +flat_mae,patch,logistic,ppmi_dx,62,0.046415888336127774,train,0.7793594306049823,0.015821807516534253,0.750886524822695,0.019087617592238513,0.740794262470563,0.018318920226372434 +flat_mae,patch,logistic,ppmi_dx,62,0.046415888336127774,test,0.66,0.040345507804463186,0.6026180458158018,0.04859820807745741,0.6035653650254669,0.043412973140805014 +flat_mae,patch,logistic,ppmi_dx,63,0.005994842503189409,train,0.7099644128113879,0.01550980972294225,0.6557653645980122,0.02045930717374448,0.6531256690216227,0.01783194211251537 +flat_mae,patch,logistic,ppmi_dx,63,0.005994842503189409,test,0.68,0.03849843633188235,0.6259934548854604,0.04852255737004102,0.6247877758913413,0.043234421891842324 +flat_mae,patch,logistic,ppmi_dx,64,0.046415888336127774,train,0.7811387900355872,0.01539151626097619,0.7518763796909492,0.018587875358499442,0.7413696210661529,0.01777458929707936 +flat_mae,patch,logistic,ppmi_dx,64,0.046415888336127774,test,0.61,0.04371853153984018,0.5623386825272135,0.04918695961092104,0.5632427843803056,0.046196058527306925 +flat_mae,patch,logistic,ppmi_dx,65,2.782559402207126,train,0.994661921708185,0.002826832660467817,0.9943552194132241,0.0029920108137251166,0.993925283665168,0.0032744572023514014 +flat_mae,patch,logistic,ppmi_dx,65,2.782559402207126,test,0.58,0.046373695129890175,0.5495495495495495,0.048786792535352494,0.5492359932088284,0.04827332177476584 +flat_mae,patch,logistic,ppmi_dx,66,0.046415888336127774,train,0.7846975088967971,0.016340882160452385,0.7597807003599651,0.019213603655051276,0.750347891243845,0.018718925289376288 +flat_mae,patch,logistic,ppmi_dx,66,0.046415888336127774,test,0.61,0.04710870832447011,0.568536342515765,0.05056153264291907,0.5683361629881154,0.04833143896318253 +flat_mae,patch,logistic,ppmi_dx,67,0.046415888336127774,train,0.8042704626334519,0.015335966034342506,0.7777921555095468,0.018736969329358224,0.7653741168914578,0.01814059293566924 +flat_mae,patch,logistic,ppmi_dx,67,0.046415888336127774,test,0.61,0.0468318652201682,0.5741893219783819,0.049848416522197854,0.5734295415959253,0.04827596133496994 +flat_mae,patch,logistic,ppmi_dx,68,0.046415888336127774,train,0.7722419928825622,0.016000745603883402,0.7421463904222525,0.01937458984486119,0.7324047313209163,0.018524032973959617 +flat_mae,patch,logistic,ppmi_dx,68,0.046415888336127774,test,0.68,0.04495786471797787,0.64349376114082,0.05264457753462106,0.6400679117147707,0.049979469382673045 +flat_mae,patch,logistic,ppmi_dx,69,0.046415888336127774,train,0.7758007117437722,0.015394813367448095,0.7475508021390374,0.018173469973921618,0.7379040890601585,0.017466519433790732 +flat_mae,patch,logistic,ppmi_dx,69,0.046415888336127774,test,0.69,0.044904035453397724,0.6570417081535569,0.050578709687624984,0.6532258064516129,0.048636340605680235 +flat_mae,patch,logistic,ppmi_dx,70,0.005994842503189409,train,0.7224199288256228,0.01617627587915007,0.6688723712835387,0.02158771927949934,0.664980732177264,0.018769194175078868 +flat_mae,patch,logistic,ppmi_dx,70,0.005994842503189409,test,0.61,0.044933479722808034,0.5623386825272135,0.050973428844251295,0.5632427843803056,0.04765913534395077 +flat_mae,patch,logistic,ppmi_dx,71,0.3593813663804626,train,0.9074733096085409,0.012017649748279478,0.9005783493229911,0.0131497370604217,0.8944150074930421,0.01391964173201573 +flat_mae,patch,logistic,ppmi_dx,71,0.3593813663804626,test,0.53,0.04697878670208502,0.4725620020199753,0.05068625359548202,0.47835314091680814,0.04790449863776276 +flat_mae,patch,logistic,ppmi_dx,72,0.005994842503189409,train,0.7153024911032029,0.016613301087598172,0.6592132191313576,0.02213211491174276,0.6565912010276171,0.019145735944406748 +flat_mae,patch,logistic,ppmi_dx,72,0.005994842503189409,test,0.65,0.041582356835561884,0.5944849959448499,0.04923322741429728,0.5955008488964346,0.04438609287884119 +flat_mae,patch,logistic,ppmi_dx,73,0.3593813663804626,train,0.9128113879003559,0.01134779414512272,0.9065935370515469,0.012297818156065171,0.9013594519374866,0.012867929599689958 +flat_mae,patch,logistic,ppmi_dx,73,0.3593813663804626,test,0.58,0.048456479442898034,0.5384615384615385,0.05309863236862555,0.5390492359932089,0.051172310506798165 +flat_mae,patch,logistic,ppmi_dx,74,0.005994842503189409,train,0.7224199288256228,0.01689745184567525,0.6732558139534883,0.02156664267383929,0.6684596446157139,0.01926187540863288 +flat_mae,patch,logistic,ppmi_dx,74,0.005994842503189409,test,0.61,0.04093251030660104,0.5481404240528328,0.048924741966056264,0.5530560271646858,0.04384350881433403 +flat_mae,patch,logistic,ppmi_dx,75,0.005994842503189409,train,0.7206405693950177,0.01567310653351746,0.6673164441461585,0.02048215344839221,0.6635356454720617,0.01788230782661048 +flat_mae,patch,logistic,ppmi_dx,75,0.005994842503189409,test,0.66,0.039296183020746424,0.5952380952380952,0.05050308326818071,0.5984719864176571,0.043840126676396134 +flat_mae,patch,logistic,ppmi_dx,76,0.005994842503189409,train,0.7099644128113879,0.016094854405810755,0.6569102219825245,0.021059389329541767,0.6539953971312353,0.018500080382351212 +flat_mae,patch,logistic,ppmi_dx,76,0.005994842503189409,test,0.69,0.0397232627058755,0.6343908479773559,0.05081390944394968,0.6328522920203735,0.04467173011225954 +flat_mae,patch,logistic,ppmi_dx,77,2.782559402207126,train,0.99644128113879,0.002544172889923855,0.9962400984799828,0.0026877662905857745,0.9962400984799828,0.00276718534832683 +flat_mae,patch,logistic,ppmi_dx,77,2.782559402207126,test,0.63,0.047779070731859156,0.5960257670051315,0.053321949944784064,0.5946519524617997,0.05153291660704739 +flat_mae,patch,logistic,ppmi_dx,78,0.046415888336127774,train,0.7686832740213523,0.015421914205044355,0.7388326469915352,0.0183566594583746,0.7295145579105117,0.01754045646341135 +flat_mae,patch,logistic,ppmi_dx,78,0.046415888336127774,test,0.62,0.04177434140713651,0.5476190476190476,0.0514994087898092,0.5560271646859083,0.04460467891880801 +flat_mae,patch,logistic,ppmi_dx,79,0.005994842503189409,train,0.7241992882562278,0.01600334742595293,0.6669534132400452,0.02169247643827032,0.6638166345536287,0.01859127897036617 +flat_mae,patch,logistic,ppmi_dx,79,0.005994842503189409,test,0.64,0.04181578649266328,0.5714285714285714,0.05121681448970941,0.5772495755517827,0.04466626798350094 +flat_mae,patch,logistic,ppmi_dx,80,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,80,2.782559402207126,test,0.58,0.04862096667076869,0.565936337329475,0.049522237213048194,0.5696095076400679,0.051080166876243664 +flat_mae,patch,logistic,ppmi_dx,81,2.782559402207126,train,0.998220640569395,0.0019725577701896605,0.9981184064710746,0.0020907813199238573,0.9976851851851851,0.0025661515436263636 +flat_mae,patch,logistic,ppmi_dx,81,2.782559402207126,test,0.62,0.04427753832362409,0.5876736111111112,0.04734361286006519,0.5865874363327674,0.04600365871123828 +flat_mae,patch,logistic,ppmi_dx,82,0.005994842503189409,train,0.7064056939501779,0.015686084729406472,0.6441932476143336,0.021149806349141168,0.6441473988439306,0.017902482454684402 +flat_mae,patch,logistic,ppmi_dx,82,0.005994842503189409,test,0.66,0.03995506976592582,0.6026180458158018,0.05006821639609031,0.6035653650254669,0.044558506568101404 +flat_mae,patch,logistic,ppmi_dx,83,0.3593813663804626,train,0.9306049822064056,0.010687410438700034,0.9255085220996822,0.011670737437673015,0.9192892314279597,0.012551916831504077 +flat_mae,patch,logistic,ppmi_dx,83,0.3593813663804626,test,0.53,0.053918379055754265,0.5160127690248172,0.05483389719935392,0.519100169779287,0.05645389848826786 +flat_mae,patch,logistic,ppmi_dx,84,0.046415888336127774,train,0.8113879003558719,0.01424670149327227,0.7887427833808531,0.01689517780946322,0.7772425604795548,0.016674013570634798 +flat_mae,patch,logistic,ppmi_dx,84,0.046415888336127774,test,0.56,0.04595762831130431,0.5098039215686274,0.050177165651171994,0.5127334465195246,0.04768739759733163 +flat_mae,patch,logistic,ppmi_dx,85,0.005994842503189409,train,0.7099644128113879,0.015577116946293563,0.6534211073908026,0.020351401684504684,0.6513862128023977,0.01762956784421922 +flat_mae,patch,logistic,ppmi_dx,85,0.005994842503189409,test,0.66,0.03719395112111645,0.587178241864983,0.048957471506141215,0.5933786078098472,0.041433537316555455 +flat_mae,patch,logistic,ppmi_dx,86,0.046415888336127774,train,0.7864768683274022,0.01623467535342972,0.7614601018675722,0.018966372578257975,0.7517929779490473,0.01839757155752034 +flat_mae,patch,logistic,ppmi_dx,86,0.046415888336127774,test,0.53,0.04407186857849347,0.4725620020199753,0.04955018352380528,0.47835314091680814,0.0459269874692449 +flat_mae,patch,logistic,ppmi_dx,87,0.005994842503189409,train,0.7241992882562278,0.01653535502585999,0.6692900232723242,0.02197568559234007,0.6655560907728538,0.019031858927694403 +flat_mae,patch,logistic,ppmi_dx,87,0.005994842503189409,test,0.69,0.04142008691444284,0.6343908479773559,0.053297488747498754,0.6328522920203735,0.046696792261035326 +flat_mae,patch,logistic,ppmi_dx,88,0.046415888336127774,train,0.7900355871886121,0.016299998411112716,0.765435766836446,0.019272760093175828,0.7555528794690645,0.01879052883503844 +flat_mae,patch,logistic,ppmi_dx,88,0.046415888336127774,test,0.67,0.04184227049288793,0.6296711929076422,0.048577929882950135,0.6269100169779287,0.045523729288592295 +flat_mae,patch,logistic,ppmi_dx,89,0.3593813663804626,train,0.9128113879003559,0.011287511250677283,0.9064081431508828,0.012338885987800991,0.9004897238278742,0.013163748815569355 +flat_mae,patch,logistic,ppmi_dx,89,0.3593813663804626,test,0.63,0.047843657886913284,0.6129302228266555,0.049594216369003574,0.615025466893039,0.050180775492073164 +flat_mae,patch,logistic,ppmi_dx,90,0.046415888336127774,train,0.7775800711743772,0.017023704044980978,0.751199730835296,0.01963076723068597,0.7419583600941982,0.01888917393074441 +flat_mae,patch,logistic,ppmi_dx,90,0.046415888336127774,test,0.6,0.047486499133964376,0.5659722222222222,0.050098551135983826,0.565365025466893,0.04870821166028809 +flat_mae,patch,logistic,ppmi_dx,91,0.3593813663804626,train,0.9110320284697508,0.012070635101765887,0.9047806226872874,0.013138316609462642,0.8999143652322843,0.013866435111695649 +flat_mae,patch,logistic,ppmi_dx,91,0.3593813663804626,test,0.64,0.046571557843817085,0.6179966044142615,0.04907450716779282,0.6179966044142615,0.04902615558762517 +flat_mae,patch,logistic,ppmi_dx,92,0.046415888336127774,train,0.802491103202847,0.01509596418413712,0.7796335350409598,0.0175949269708031,0.7691473988439306,0.01726850671999589 +flat_mae,patch,logistic,ppmi_dx,92,0.046415888336127774,test,0.69,0.04452808102759426,0.6615351020853806,0.04888095629317455,0.6583191850594228,0.04764569258496765 +flat_mae,patch,logistic,ppmi_dx,93,0.005994842503189409,train,0.7046263345195729,0.015592036815684177,0.6500150060024009,0.019955412158144892,0.6479206807964033,0.017496259981641775 +flat_mae,patch,logistic,ppmi_dx,93,0.005994842503189409,test,0.64,0.0413533988929568,0.5792426367461431,0.05108677219284305,0.5823429541595926,0.04529992230158811 +flat_mae,patch,logistic,ppmi_dx,94,0.005994842503189409,train,0.7099644128113879,0.01619623741512085,0.6569102219825245,0.021008112786258963,0.6539953971312353,0.018438939973551415 +flat_mae,patch,logistic,ppmi_dx,94,0.005994842503189409,test,0.68,0.041493498285876056,0.6381727725011307,0.04909775234706154,0.634974533106961,0.04571194693049735 +flat_mae,patch,logistic,ppmi_dx,95,0.046415888336127774,train,0.7811387900355872,0.015711006620544317,0.7545407092561226,0.01871166726269543,0.7448485335046029,0.01820819264587345 +flat_mae,patch,logistic,ppmi_dx,95,0.046415888336127774,test,0.67,0.04168556584718504,0.6176572818908586,0.05112356339378729,0.616723259762309,0.04601792998325598 +flat_mae,patch,logistic,ppmi_dx,96,0.046415888336127774,train,0.800711743772242,0.015764063732052403,0.7767848277231655,0.01892146868267441,0.7659628559195033,0.018614399173157457 +flat_mae,patch,logistic,ppmi_dx,96,0.046415888336127774,test,0.56,0.044316841042655555,0.5164835164835164,0.04854145307978827,0.5178268251273345,0.04662997833009024 +flat_mae,patch,logistic,ppmi_dx,97,0.3593813663804626,train,0.9039145907473309,0.012443041541781554,0.8963312154129945,0.01368114218076255,0.8889156497538,0.014316155758021686 +flat_mae,patch,logistic,ppmi_dx,97,0.3593813663804626,test,0.65,0.04918050020079096,0.6419437340153453,0.049281015374855706,0.6515280135823429,0.050045733622134686 +flat_mae,patch,logistic,ppmi_dx,98,0.046415888336127774,train,0.7740213523131673,0.016138024912513264,0.7472189265286607,0.01911241977205856,0.7381984585741812,0.01848372897714573 +flat_mae,patch,logistic,ppmi_dx,98,0.046415888336127774,test,0.67,0.038851198179721554,0.5951417004048583,0.05379406654221914,0.6014431239388794,0.04443331739293623 +flat_mae,patch,logistic,ppmi_dx,99,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,99,1291.5496650148827,test,0.64,0.04829287318021159,0.6305418719211823,0.0493410019463765,0.6383701188455009,0.050909061514595115 +flat_mae,patch,logistic,ppmi_dx,100,0.046415888336127774,train,0.7864768683274022,0.015416802207382091,0.7589224433768016,0.01840239868154613,0.7483140655105973,0.017732816912186502 +flat_mae,patch,logistic,ppmi_dx,100,0.046415888336127774,test,0.64,0.041494457461208,0.5792426367461431,0.05141472606074827,0.5823429541595926,0.04538048833787405 diff --git a/decoders/crossreg_reg4/eval_v2/ppmi_dx__patch__logistic/log.txt b/decoders/crossreg_reg4/eval_v2/ppmi_dx__patch__logistic/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..626b0d02430a6ae79b1e13ba699db24b4caf3522 --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/ppmi_dx__patch__logistic/log.txt @@ -0,0 +1,247 @@ +fMRI foundation model logistic probe eval +version: 0.1.dev66+g7ddd3aa04 +sha: aef99c83a386cf95c3d8ca503ecc968d8d5694af, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-03-07 21:48:00 +config: +output_root: experiments/decoders/output +name_prefix: eval_logistic +remote_root: null +notes: decoder ablations crossreg_reg4; eval v2 (ppmi_dx patch logistic) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: decoders/crossreg_reg4/eval_v2/ppmi_dx__patch__logistic +model: flat_mae +representation: patch +dataset: ppmi_dx +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg4/eval_v2/ppmi_dx__patch__logistic +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=False, reg_tokens=4, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: ppmi_dx (flat) +train (n=463): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'dir', 'sex', 'age', 'age_bin', 'dx', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 463 +}), + labels=['PD' 'Prodromal'], + counts=[178 285] +) + +validation (n=99): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'dir', 'sex', 'age', 'age_bin', 'dx', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 99 +}), + labels=['PD' 'Prodromal'], + counts=[39 60] +) + +test (n=100): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'dir', 'sex', 'age', 'age_bin', 'dx', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 100 +}), + labels=['PD' 'Prodromal'], + counts=[37 63] +) + +extracting features for all splits +extract (train) [ 0/232] eta: 0:17:41 time: 4.5756 data: 3.5500 max mem: 2698 +extract (train) [ 20/232] eta: 0:01:19 time: 0.1656 data: 0.0481 max mem: 2852 +extract (train) [ 40/232] eta: 0:00:51 time: 0.1518 data: 0.0429 max mem: 2852 +extract (train) [ 60/232] eta: 0:00:40 time: 0.1660 data: 0.0514 max mem: 2852 +extract (train) [ 80/232] eta: 0:00:33 time: 0.1689 data: 0.0546 max mem: 2852 +extract (train) [100/232] eta: 0:00:27 time: 0.1650 data: 0.0507 max mem: 2852 +extract (train) [120/232] eta: 0:00:22 time: 0.1648 data: 0.0525 max mem: 2852 +extract (train) [140/232] eta: 0:00:17 time: 0.1506 data: 0.0439 max mem: 2852 +extract (train) [160/232] eta: 0:00:13 time: 0.1585 data: 0.0487 max mem: 2852 +extract (train) [180/232] eta: 0:00:09 time: 0.1685 data: 0.0529 max mem: 2852 +extract (train) [200/232] eta: 0:00:05 time: 0.1490 data: 0.0427 max mem: 2852 +extract (train) [220/232] eta: 0:00:02 time: 0.1426 data: 0.0404 max mem: 2852 +extract (train) [231/232] eta: 0:00:00 time: 0.1407 data: 0.0409 max mem: 2852 +extract (train) Total time: 0:00:41 (0.1790 s / it) +extract (validation) [ 0/50] eta: 0:02:51 time: 3.4361 data: 3.2976 max mem: 2852 +extract (validation) [20/50] eta: 0:00:10 time: 0.1970 data: 0.0634 max mem: 2852 +extract (validation) [40/50] eta: 0:00:02 time: 0.1329 data: 0.0323 max mem: 2852 +extract (validation) [49/50] eta: 0:00:00 time: 0.1332 data: 0.0352 max mem: 2852 +extract (validation) Total time: 0:00:11 (0.2303 s / it) +extract (test) [ 0/50] eta: 0:02:34 time: 3.0982 data: 2.9439 max mem: 2852 +extract (test) [20/50] eta: 0:00:10 time: 0.2061 data: 0.0714 max mem: 2852 +extract (test) [40/50] eta: 0:00:02 time: 0.1517 data: 0.0452 max mem: 2852 +extract (test) [49/50] eta: 0:00:00 time: 0.1570 data: 0.0476 max mem: 2852 +extract (test) Total time: 0:00:12 (0.2429 s / it) +feature extraction time: 0:01:05 +train features: (463, 768) +validation features: (99, 768) +test features: (100, 768) +evaluating fixed splits +eval results (fixed splits): + +| model | repr | clf | dataset | trial | C | split | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|--------:|:--------|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | ppmi_dx | | 0.35938 | train | 0.91637 | 0.011707 | 0.91075 | 0.012621 | 0.90624 | 0.013176 | +| flat_mae | patch | logistic | ppmi_dx | | 0.35938 | test | 0.64 | 0.044502 | 0.60938 | 0.04832 | 0.60832 | 0.047602 | + + +evaluating random splits (n=100) +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 1, "C": 0.005994842503189409, "split": "test", "acc": 0.69, "acc_std": 0.037193391886193965, "f1": 0.6196785670469881, "f1_std": 0.05143288549270446, "bacc": 0.6226655348047538, "bacc_std": 0.04249458525066637} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 2, "C": 0.046415888336127774, "split": "test", "acc": 0.71, "acc_std": 0.04363255665211471, "f1": 0.6833715471121302, "f1_std": 0.04833159118624529, "bacc": 0.6795415959252971, "bacc_std": 0.0470824433207542} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 3, "C": 2.782559402207126, "split": "test", "acc": 0.63, "acc_std": 0.047144284913444176, "f1": 0.6129302228266555, "f1_std": 0.04881074815562475, "bacc": 0.615025466893039, "bacc_std": 0.04956718039740403} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 4, "C": 0.046415888336127774, "split": "test", "acc": 0.69, "acc_std": 0.042182157365407466, "f1": 0.6467236467236468, "f1_std": 0.04970418204741729, "bacc": 0.6430390492359932, "bacc_std": 0.0461336006381166} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 5, "C": 0.3593813663804626, "split": "test", "acc": 0.59, "acc_std": 0.05023733671284735, "f1": 0.5577607593571352, "f1_std": 0.053850778638830005, "bacc": 0.5573005093378608, "bacc_std": 0.0528237028136196} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 6, "C": 0.046415888336127774, "split": "test", "acc": 0.61, "acc_std": 0.049025589236642526, "f1": 0.5741893219783819, "f1_std": 0.05351322850018915, "bacc": 0.5734295415959253, "bacc_std": 0.05181207979461741} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 7, "C": 0.046415888336127774, "split": "test", "acc": 0.62, "acc_std": 0.04676020102608627, "f1": 0.5924495924495925, "f1_std": 0.0505749568865701, "bacc": 0.5916808149405772, "bacc_std": 0.05008205116269654} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 8, "C": 21.54434690031882, "split": "test", "acc": 0.55, "acc_std": 0.049094504784140555, "f1": 0.5248653785239151, "f1_std": 0.05099104168641188, "bacc": 0.5250424448217317, "bacc_std": 0.051349640527547646} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 9, "C": 0.3593813663804626, "split": "test", "acc": 0.62, "acc_std": 0.046072534117411, "f1": 0.5967741935483871, "f1_std": 0.048829889268775684, "bacc": 0.5967741935483871, "bacc_std": 0.04851699556668779} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 10, "C": 0.005994842503189409, "split": "test", "acc": 0.63, "acc_std": 0.03838463755202074, "f1": 0.5552350042072365, "f1_std": 0.049175198696911185, "bacc": 0.5640916808149405, "bacc_std": 0.041777185287987614} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 11, "C": 0.046415888336127774, "split": "test", "acc": 0.68, "acc_std": 0.04391992714019456, "f1": 0.6381727725011307, "f1_std": 0.0523755861383105, "bacc": 0.634974533106961, "bacc_std": 0.048972621625394876} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 12, "C": 0.046415888336127774, "split": "test", "acc": 0.63, "acc_std": 0.04240552322516491, "f1": 0.5552350042072365, "f1_std": 0.05241277695149047, "bacc": 0.5640916808149405, "bacc_std": 0.045434250565029075} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 13, "C": 0.046415888336127774, "split": "test", "acc": 0.61, "acc_std": 0.040418703591283085, "f1": 0.5555555555555556, "f1_std": 0.04805435854636089, "bacc": 0.5581494057724957, "bacc_std": 0.043853063633789706} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 14, "C": 0.046415888336127774, "split": "test", "acc": 0.58, "acc_std": 0.042118423522254485, "f1": 0.5091164095371669, "f1_std": 0.04973581474771774, "bacc": 0.5186757215619694, "bacc_std": 0.044057369237435896} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 15, "C": 0.046415888336127774, "split": "test", "acc": 0.63, "acc_std": 0.047278659033437066, "f1": 0.6053333333333333, "f1_std": 0.05000037379260817, "bacc": 0.6048387096774194, "bacc_std": 0.049604437323765904} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 16, "C": 0.046415888336127774, "split": "test", "acc": 0.62, "acc_std": 0.04619338047815943, "f1": 0.5924495924495925, "f1_std": 0.04875801163597031, "bacc": 0.5916808149405772, "bacc_std": 0.048189113464747864} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 17, "C": 0.046415888336127774, "split": "test", "acc": 0.59, "acc_std": 0.04643830746269721, "f1": 0.5523528769516323, "f1_std": 0.04992393917256893, "bacc": 0.5522071307300509, "bacc_std": 0.04834835176959865} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 18, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.03981515289434413, "f1": 0.503968253968254, "f1_std": 0.04975757739910872, "bacc": 0.5246179966044142, "bacc_std": 0.04155150460677975} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 19, "C": 0.046415888336127774, "split": "test", "acc": 0.62, "acc_std": 0.04592395453355471, "f1": 0.5967741935483871, "f1_std": 0.048101012008295, "bacc": 0.5967741935483871, "bacc_std": 0.04810968866663364} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 20, "C": 0.005994842503189409, "split": "test", "acc": 0.59, "acc_std": 0.0424183733775825, "f1": 0.5327635327635327, "f1_std": 0.04878439513511393, "bacc": 0.5369269949066213, "bacc_std": 0.04471737562254186} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 21, "C": 0.005994842503189409, "split": "test", "acc": 0.65, "acc_std": 0.036134609448560534, "f1": 0.5706048337627285, "f1_std": 0.05000888475712918, "bacc": 0.580220713073005, "bacc_std": 0.040653154270296754} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 22, "C": 0.046415888336127774, "split": "test", "acc": 0.61, "acc_std": 0.04382610637508196, "f1": 0.5623386825272135, "f1_std": 0.05011234368054188, "bacc": 0.5632427843803056, "bacc_std": 0.04701199837227422} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 23, "C": 2.782559402207126, "split": "test", "acc": 0.56, "acc_std": 0.047949973931171216, "f1": 0.5280995280995281, "f1_std": 0.050581385175900974, "bacc": 0.5280135823429541, "bacc_std": 0.0498075459989968} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 24, "C": 0.046415888336127774, "split": "test", "acc": 0.63, "acc_std": 0.04310438956765309, "f1": 0.5783475783475784, "f1_std": 0.05156997838681207, "bacc": 0.5793718166383701, "bacc_std": 0.0472088107167295} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 25, "C": 0.046415888336127774, "split": "test", "acc": 0.65, "acc_std": 0.03781222553619398, "f1": 0.5792763553311696, "f1_std": 0.04925129054849584, "bacc": 0.5853140916808149, "bacc_std": 0.04195847801194228} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 26, "C": 0.046415888336127774, "split": "test", "acc": 0.62, "acc_std": 0.046266290104135216, "f1": 0.5876736111111112, "f1_std": 0.05071411252272973, "bacc": 0.5865874363327674, "bacc_std": 0.04948078355165446} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 27, "C": 2.782559402207126, "split": "test", "acc": 0.52, "acc_std": 0.04744183386000166, "f1": 0.4851994851994852, "f1_std": 0.04903891521958805, "bacc": 0.48556876061120546, "bacc_std": 0.04845482005232822} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 28, "C": 166.81005372000556, "split": "test", "acc": 0.51, "acc_std": 0.04745296197288427, "f1": 0.47733333333333333, "f1_std": 0.04947548067764703, "bacc": 0.4775042444821732, "bacc_std": 0.04897831708452532} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 29, "C": 0.046415888336127774, "split": "test", "acc": 0.63, "acc_std": 0.043927594971725915, "f1": 0.5783475783475784, "f1_std": 0.05158268927883656, "bacc": 0.5793718166383701, "bacc_std": 0.047413641722442286} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 30, "C": 2.782559402207126, "split": "test", "acc": 0.65, "acc_std": 0.04639297791692186, "f1": 0.6266666666666667, "f1_std": 0.04969893156841365, "bacc": 0.6260611205432938, "bacc_std": 0.049709614032592546} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 31, "C": 0.046415888336127774, "split": "test", "acc": 0.67, "acc_std": 0.046788592626835865, "f1": 0.6396986570586308, "f1_std": 0.05152284443045045, "bacc": 0.6370967741935484, "bacc_std": 0.05006119276968571} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 32, "C": 0.046415888336127774, "split": "test", "acc": 0.65, "acc_std": 0.04433001240694616, "f1": 0.6178622120318812, "f1_std": 0.04947280621863624, "bacc": 0.615874363327674, "bacc_std": 0.048069732548444134} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 33, "C": 0.046415888336127774, "split": "test", "acc": 0.7, "acc_std": 0.0428000186915847, "f1": 0.6744791666666667, "f1_std": 0.04694778153520295, "bacc": 0.6714770797962648, "bacc_std": 0.04620378084258026} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 34, "C": 0.046415888336127774, "split": "test", "acc": 0.69, "acc_std": 0.0440477014156244, "f1": 0.6570417081535569, "f1_std": 0.049461006342273406, "bacc": 0.6532258064516129, "bacc_std": 0.04773720657653101} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 35, "C": 0.005994842503189409, "split": "test", "acc": 0.63, "acc_std": 0.04692043904312917, "f1": 0.6053333333333333, "f1_std": 0.04975282820326576, "bacc": 0.6048387096774194, "bacc_std": 0.049029207431765795} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 36, "C": 0.3593813663804626, "split": "test", "acc": 0.62, "acc_std": 0.04369431999699732, "f1": 0.5703301673450927, "f1_std": 0.049390434740036716, "bacc": 0.5713073005093379, "bacc_std": 0.04586387973542212} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 37, "C": 0.046415888336127774, "split": "test", "acc": 0.68, "acc_std": 0.04297483449648177, "f1": 0.6381727725011307, "f1_std": 0.05080262872779873, "bacc": 0.634974533106961, "bacc_std": 0.04731635340359598} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 38, "C": 0.3593813663804626, "split": "test", "acc": 0.65, "acc_std": 0.04766372205357026, "f1": 0.6266666666666667, "f1_std": 0.05046141299982007, "bacc": 0.6260611205432938, "bacc_std": 0.050184114711797685} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 39, "C": 0.005994842503189409, "split": "test", "acc": 0.69, "acc_std": 0.038497189507806916, "f1": 0.627359057579036, "f1_std": 0.05071069920724843, "bacc": 0.6277589134125636, "bacc_std": 0.0433741512899555} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 40, "C": 0.005994842503189409, "split": "test", "acc": 0.7, "acc_std": 0.03810710694870446, "f1": 0.6357455075279261, "f1_std": 0.052275779735190014, "bacc": 0.6358234295415959, "bacc_std": 0.04425024011612922} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 41, "C": 0.046415888336127774, "split": "test", "acc": 0.67, "acc_std": 0.04394212557444166, "f1": 0.6440513428972063, "f1_std": 0.04770651754276264, "bacc": 0.6421901528013583, "bacc_std": 0.04708817045128571} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 42, "C": 10000.0, "split": "test", "acc": 0.6, "acc_std": 0.04450231005240065, "f1": 0.5324918186068257, "f1_std": 0.05303658568642919, "bacc": 0.5398981324278438, "bacc_std": 0.04730355755025885} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 43, "C": 0.005994842503189409, "split": "test", "acc": 0.66, "acc_std": 0.04081099851755651, "f1": 0.587178241864983, "f1_std": 0.053270981260931695, "bacc": 0.5933786078098472, "bacc_std": 0.04524859277435758} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 44, "C": 0.005994842503189409, "split": "test", "acc": 0.66, "acc_std": 0.03682548574017727, "f1": 0.5783730158730158, "f1_std": 0.052844326132826615, "bacc": 0.5882852292020373, "bacc_std": 0.04246461965268768} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 45, "C": 0.005994842503189409, "split": "test", "acc": 0.69, "acc_std": 0.03816831670377932, "f1": 0.6196785670469881, "f1_std": 0.05246264235207439, "bacc": 0.6226655348047538, "bacc_std": 0.04375840088183484} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 46, "C": 0.046415888336127774, "split": "test", "acc": 0.54, "acc_std": 0.04589586473746845, "f1": 0.4945054945054945, "f1_std": 0.049851715050077634, "bacc": 0.49660441426146007, "bacc_std": 0.04746562854363071} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 47, "C": 0.3593813663804626, "split": "test", "acc": 0.74, "acc_std": 0.041766067566865815, "f1": 0.7241086587436333, "f1_std": 0.044622807805426296, "bacc": 0.7241086587436333, "bacc_std": 0.04502236424092212} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 48, "C": 0.005994842503189409, "split": "test", "acc": 0.68, "acc_std": 0.04473135812827506, "f1": 0.64349376114082, "f1_std": 0.052129289125197514, "bacc": 0.6400679117147707, "bacc_std": 0.049227455936849684} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 49, "C": 0.046415888336127774, "split": "test", "acc": 0.66, "acc_std": 0.039134123217468404, "f1": 0.5952380952380952, "f1_std": 0.05037276854222254, "bacc": 0.5984719864176571, "bacc_std": 0.04331711704145282} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 50, "C": 0.005994842503189409, "split": "test", "acc": 0.69, "acc_std": 0.03838697695833835, "f1": 0.6196785670469881, "f1_std": 0.05240579979108466, "bacc": 0.6226655348047538, "bacc_std": 0.043570607588362044} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 51, "C": 0.3593813663804626, "split": "test", "acc": 0.57, "acc_std": 0.0476952156929812, "f1": 0.5305164319248826, "f1_std": 0.05086739799942668, "bacc": 0.5309847198641766, "bacc_std": 0.04924260768754011} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 52, "C": 2.782559402207126, "split": "test", "acc": 0.59, "acc_std": 0.048330925917056455, "f1": 0.5670995670995671, "f1_std": 0.0495393978808992, "bacc": 0.5674872665534805, "bacc_std": 0.04966215010192966} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 53, "C": 0.3593813663804626, "split": "test", "acc": 0.62, "acc_std": 0.045912346923240595, "f1": 0.5824175824175825, "f1_std": 0.05056920295569798, "bacc": 0.5814940577249575, "bacc_std": 0.04876007487107554} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 54, "C": 21.54434690031882, "split": "test", "acc": 0.54, "acc_std": 0.046294617397706184, "f1": 0.5008680555555556, "f1_std": 0.048581951636397266, "bacc": 0.50169779286927, "bacc_std": 0.047545969009596845} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 55, "C": 0.005994842503189409, "split": "test", "acc": 0.65, "acc_std": 0.04582001309471659, "f1": 0.6072270227808326, "f1_std": 0.05255040260592497, "bacc": 0.6056876061120543, "bacc_std": 0.04909613280550803} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 56, "C": 0.005994842503189409, "split": "test", "acc": 0.59, "acc_std": 0.041520481692774225, "f1": 0.5071523019593701, "f1_std": 0.050603928142715686, "bacc": 0.5216468590831919, "bacc_std": 0.043540979754395505} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 57, "C": 0.046415888336127774, "split": "test", "acc": 0.68, "acc_std": 0.044190388095150274, "f1": 0.6381727725011307, "f1_std": 0.05226391369227922, "bacc": 0.634974533106961, "bacc_std": 0.0488612132035058} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 58, "C": 0.046415888336127774, "split": "test", "acc": 0.63, "acc_std": 0.0442220714123615, "f1": 0.5783475783475784, "f1_std": 0.051402457675031384, "bacc": 0.5793718166383701, "bacc_std": 0.047487356837794696} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 59, "C": 2.782559402207126, "split": "test", "acc": 0.64, "acc_std": 0.049953974816825134, "f1": 0.6216897856242118, "f1_std": 0.05224459760723616, "bacc": 0.6230899830220713, "bacc_std": 0.05254424356813113} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 60, "C": 21.54434690031882, "split": "test", "acc": 0.57, "acc_std": 0.04672014982852687, "f1": 0.5361881134721174, "f1_std": 0.05040341367348005, "bacc": 0.5360780984719864, "bacc_std": 0.04915461024024188} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 61, "C": 0.046415888336127774, "split": "test", "acc": 0.63, "acc_std": 0.04598387108541429, "f1": 0.5847828526540231, "f1_std": 0.051532753348824054, "bacc": 0.5844651952461799, "bacc_std": 0.04839877495121012} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 62, "C": 0.046415888336127774, "split": "test", "acc": 0.66, "acc_std": 0.040345507804463186, "f1": 0.6026180458158018, "f1_std": 0.04859820807745741, "bacc": 0.6035653650254669, "bacc_std": 0.043412973140805014} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 63, "C": 0.005994842503189409, "split": "test", "acc": 0.68, "acc_std": 0.03849843633188235, "f1": 0.6259934548854604, "f1_std": 0.04852255737004102, "bacc": 0.6247877758913413, "bacc_std": 0.043234421891842324} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 64, "C": 0.046415888336127774, "split": "test", "acc": 0.61, "acc_std": 0.04371853153984018, "f1": 0.5623386825272135, "f1_std": 0.04918695961092104, "bacc": 0.5632427843803056, "bacc_std": 0.046196058527306925} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 65, "C": 2.782559402207126, "split": "test", "acc": 0.58, "acc_std": 0.046373695129890175, "f1": 0.5495495495495495, "f1_std": 0.048786792535352494, "bacc": 0.5492359932088284, "bacc_std": 0.04827332177476584} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 66, "C": 0.046415888336127774, "split": "test", "acc": 0.61, "acc_std": 0.04710870832447011, "f1": 0.568536342515765, "f1_std": 0.05056153264291907, "bacc": 0.5683361629881154, "bacc_std": 0.04833143896318253} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 67, "C": 0.046415888336127774, "split": "test", "acc": 0.61, "acc_std": 0.0468318652201682, "f1": 0.5741893219783819, "f1_std": 0.049848416522197854, "bacc": 0.5734295415959253, "bacc_std": 0.04827596133496994} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 68, "C": 0.046415888336127774, "split": "test", "acc": 0.68, "acc_std": 0.04495786471797787, "f1": 0.64349376114082, "f1_std": 0.05264457753462106, "bacc": 0.6400679117147707, "bacc_std": 0.049979469382673045} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 69, "C": 0.046415888336127774, "split": "test", "acc": 0.69, "acc_std": 0.044904035453397724, "f1": 0.6570417081535569, "f1_std": 0.050578709687624984, "bacc": 0.6532258064516129, "bacc_std": 0.048636340605680235} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 70, "C": 0.005994842503189409, "split": "test", "acc": 0.61, "acc_std": 0.044933479722808034, "f1": 0.5623386825272135, "f1_std": 0.050973428844251295, "bacc": 0.5632427843803056, "bacc_std": 0.04765913534395077} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 71, "C": 0.3593813663804626, "split": "test", "acc": 0.53, "acc_std": 0.04697878670208502, "f1": 0.4725620020199753, "f1_std": 0.05068625359548202, "bacc": 0.47835314091680814, "bacc_std": 0.04790449863776276} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 72, "C": 0.005994842503189409, "split": "test", "acc": 0.65, "acc_std": 0.041582356835561884, "f1": 0.5944849959448499, "f1_std": 0.04923322741429728, "bacc": 0.5955008488964346, "bacc_std": 0.04438609287884119} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 73, "C": 0.3593813663804626, "split": "test", "acc": 0.58, "acc_std": 0.048456479442898034, "f1": 0.5384615384615385, "f1_std": 0.05309863236862555, "bacc": 0.5390492359932089, "bacc_std": 0.051172310506798165} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 74, "C": 0.005994842503189409, "split": "test", "acc": 0.61, "acc_std": 0.04093251030660104, "f1": 0.5481404240528328, "f1_std": 0.048924741966056264, "bacc": 0.5530560271646858, "bacc_std": 0.04384350881433403} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 75, "C": 0.005994842503189409, "split": "test", "acc": 0.66, "acc_std": 0.039296183020746424, "f1": 0.5952380952380952, "f1_std": 0.05050308326818071, "bacc": 0.5984719864176571, "bacc_std": 0.043840126676396134} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 76, "C": 0.005994842503189409, "split": "test", "acc": 0.69, "acc_std": 0.0397232627058755, "f1": 0.6343908479773559, "f1_std": 0.05081390944394968, "bacc": 0.6328522920203735, "bacc_std": 0.04467173011225954} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 77, "C": 2.782559402207126, "split": "test", "acc": 0.63, "acc_std": 0.047779070731859156, "f1": 0.5960257670051315, "f1_std": 0.053321949944784064, "bacc": 0.5946519524617997, "bacc_std": 0.05153291660704739} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 78, "C": 0.046415888336127774, "split": "test", "acc": 0.62, "acc_std": 0.04177434140713651, "f1": 0.5476190476190476, "f1_std": 0.0514994087898092, "bacc": 0.5560271646859083, "bacc_std": 0.04460467891880801} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 79, "C": 0.005994842503189409, "split": "test", "acc": 0.64, "acc_std": 0.04181578649266328, "f1": 0.5714285714285714, "f1_std": 0.05121681448970941, "bacc": 0.5772495755517827, "bacc_std": 0.04466626798350094} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 80, "C": 2.782559402207126, "split": "test", "acc": 0.58, "acc_std": 0.04862096667076869, "f1": 0.565936337329475, "f1_std": 0.049522237213048194, "bacc": 0.5696095076400679, "bacc_std": 0.051080166876243664} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 81, "C": 2.782559402207126, "split": "test", "acc": 0.62, "acc_std": 0.04427753832362409, "f1": 0.5876736111111112, "f1_std": 0.04734361286006519, "bacc": 0.5865874363327674, "bacc_std": 0.04600365871123828} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 82, "C": 0.005994842503189409, "split": "test", "acc": 0.66, "acc_std": 0.03995506976592582, "f1": 0.6026180458158018, "f1_std": 0.05006821639609031, "bacc": 0.6035653650254669, "bacc_std": 0.044558506568101404} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 83, "C": 0.3593813663804626, "split": "test", "acc": 0.53, "acc_std": 0.053918379055754265, "f1": 0.5160127690248172, "f1_std": 0.05483389719935392, "bacc": 0.519100169779287, "bacc_std": 0.05645389848826786} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 84, "C": 0.046415888336127774, "split": "test", "acc": 0.56, "acc_std": 0.04595762831130431, "f1": 0.5098039215686274, "f1_std": 0.050177165651171994, "bacc": 0.5127334465195246, "bacc_std": 0.04768739759733163} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 85, "C": 0.005994842503189409, "split": "test", "acc": 0.66, "acc_std": 0.03719395112111645, "f1": 0.587178241864983, "f1_std": 0.048957471506141215, "bacc": 0.5933786078098472, "bacc_std": 0.041433537316555455} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 86, "C": 0.046415888336127774, "split": "test", "acc": 0.53, "acc_std": 0.04407186857849347, "f1": 0.4725620020199753, "f1_std": 0.04955018352380528, "bacc": 0.47835314091680814, "bacc_std": 0.0459269874692449} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 87, "C": 0.005994842503189409, "split": "test", "acc": 0.69, "acc_std": 0.04142008691444284, "f1": 0.6343908479773559, "f1_std": 0.053297488747498754, "bacc": 0.6328522920203735, "bacc_std": 0.046696792261035326} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 88, "C": 0.046415888336127774, "split": "test", "acc": 0.67, "acc_std": 0.04184227049288793, "f1": 0.6296711929076422, "f1_std": 0.048577929882950135, "bacc": 0.6269100169779287, "bacc_std": 0.045523729288592295} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 89, "C": 0.3593813663804626, "split": "test", "acc": 0.63, "acc_std": 0.047843657886913284, "f1": 0.6129302228266555, "f1_std": 0.049594216369003574, "bacc": 0.615025466893039, "bacc_std": 0.050180775492073164} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 90, "C": 0.046415888336127774, "split": "test", "acc": 0.6, "acc_std": 0.047486499133964376, "f1": 0.5659722222222222, "f1_std": 0.050098551135983826, "bacc": 0.565365025466893, "bacc_std": 0.04870821166028809} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 91, "C": 0.3593813663804626, "split": "test", "acc": 0.64, "acc_std": 0.046571557843817085, "f1": 0.6179966044142615, "f1_std": 0.04907450716779282, "bacc": 0.6179966044142615, "bacc_std": 0.04902615558762517} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 92, "C": 0.046415888336127774, "split": "test", "acc": 0.69, "acc_std": 0.04452808102759426, "f1": 0.6615351020853806, "f1_std": 0.04888095629317455, "bacc": 0.6583191850594228, "bacc_std": 0.04764569258496765} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 93, "C": 0.005994842503189409, "split": "test", "acc": 0.64, "acc_std": 0.0413533988929568, "f1": 0.5792426367461431, "f1_std": 0.05108677219284305, "bacc": 0.5823429541595926, "bacc_std": 0.04529992230158811} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 94, "C": 0.005994842503189409, "split": "test", "acc": 0.68, "acc_std": 0.041493498285876056, "f1": 0.6381727725011307, "f1_std": 0.04909775234706154, "bacc": 0.634974533106961, "bacc_std": 0.04571194693049735} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 95, "C": 0.046415888336127774, "split": "test", "acc": 0.67, "acc_std": 0.04168556584718504, "f1": 0.6176572818908586, "f1_std": 0.05112356339378729, "bacc": 0.616723259762309, "bacc_std": 0.04601792998325598} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 96, "C": 0.046415888336127774, "split": "test", "acc": 0.56, "acc_std": 0.044316841042655555, "f1": 0.5164835164835164, "f1_std": 0.04854145307978827, "bacc": 0.5178268251273345, "bacc_std": 0.04662997833009024} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 97, "C": 0.3593813663804626, "split": "test", "acc": 0.65, "acc_std": 0.04918050020079096, "f1": 0.6419437340153453, "f1_std": 0.049281015374855706, "bacc": 0.6515280135823429, "bacc_std": 0.050045733622134686} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 98, "C": 0.046415888336127774, "split": "test", "acc": 0.67, "acc_std": 0.038851198179721554, "f1": 0.5951417004048583, "f1_std": 0.05379406654221914, "bacc": 0.6014431239388794, "bacc_std": 0.04443331739293623} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 99, "C": 1291.5496650148827, "split": "test", "acc": 0.64, "acc_std": 0.04829287318021159, "f1": 0.6305418719211823, "f1_std": 0.0493410019463765, "bacc": 0.6383701188455009, "bacc_std": 0.050909061514595115} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 100, "C": 0.046415888336127774, "split": "test", "acc": 0.64, "acc_std": 0.041494457461208, "f1": 0.5792426367461431, "f1_std": 0.05141472606074827, "bacc": 0.5823429541595926, "bacc_std": 0.04538048833787405} +eval results (random splits): + +| model | repr | clf | dataset | split | n_trials | C | C_std | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|-----------:|-------:|--------:|-------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | ppmi_dx | train | 100 | 115.58 | 1006.9 | 0.8168 | 0.10015 | 0.78922 | 0.11918 | 0.78332 | 0.1202 | +| flat_mae | patch | logistic | ppmi_dx | test | 100 | 115.58 | 1006.9 | 0.6305 | 0.047745 | 0.58573 | 0.049634 | 0.58726 | 0.047747 | + + +done! total time: 0:05:20 diff --git a/decoders/crossreg_reg4/eval_v2/ppmi_dx__reg__logistic/config.yaml b/decoders/crossreg_reg4/eval_v2/ppmi_dx__reg__logistic/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..8dccb3779359e94df1f51d1ae7390962097133a7 --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/ppmi_dx__reg__logistic/config.yaml @@ -0,0 +1,30 @@ +output_root: experiments/decoders/output +name_prefix: eval_logistic +remote_root: null +notes: decoder ablations crossreg_reg4; eval v2 (ppmi_dx reg logistic) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: decoders/crossreg_reg4/eval_v2/ppmi_dx__reg__logistic +model: flat_mae +representation: reg +dataset: ppmi_dx +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg4/eval_v2/ppmi_dx__reg__logistic +remote_dir: null diff --git a/decoders/crossreg_reg4/eval_v2/ppmi_dx__reg__logistic/eval_table.csv b/decoders/crossreg_reg4/eval_v2/ppmi_dx__reg__logistic/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..392a94d5f37e5dc959386aee5ceb6bc6ac4e851e --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/ppmi_dx__reg__logistic/eval_table.csv @@ -0,0 +1,203 @@ +model,repr,clf,dataset,trial,C,split,acc,acc_std,f1,f1_std,bacc,bacc_std +flat_mae,reg,logistic,ppmi_dx,,0.046415888336127774,train,0.8451957295373665,0.015013787392986993,0.8302026358285148,0.01709556192713171,0.8200561009817672,0.01734989772837028 +flat_mae,reg,logistic,ppmi_dx,,0.046415888336127774,test,0.6,0.0449868380751526,0.5477159656264134,0.04974110012164312,0.5486915486915487,0.046976336946749415 +flat_mae,reg,logistic,ppmi_dx,1,0.046415888336127774,train,0.8416370106761566,0.015279133046002773,0.8278583302072184,0.016996134253841545,0.8200733247698566,0.017208917876664176 +flat_mae,reg,logistic,ppmi_dx,1,0.046415888336127774,test,0.71,0.04159824996318955,0.6745595331612613,0.04870012161359999,0.6693548387096775,0.04601927064989391 +flat_mae,reg,logistic,ppmi_dx,2,0.000774263682681127,train,0.693950177935943,0.014067402745795371,0.612227214377407,0.02129345245132078,0.6209858702633269,0.01658130318994496 +flat_mae,reg,logistic,ppmi_dx,2,0.000774263682681127,test,0.65,0.032287576558174824,0.539413080668509,0.04892759365300171,0.5649405772495755,0.03642134011041704 +flat_mae,reg,logistic,ppmi_dx,3,0.005994842503189409,train,0.7384341637010676,0.016710432693634848,0.6991861925828827,0.02084434188512563,0.6919021622778848,0.01922773535323934 +flat_mae,reg,logistic,ppmi_dx,3,0.005994842503189409,test,0.67,0.042435362611859456,0.6176572818908586,0.05143445658117249,0.616723259762309,0.04641926150689125 +flat_mae,reg,logistic,ppmi_dx,4,0.3593813663804626,train,0.9412811387900356,0.00953940794533489,0.9375713203736431,0.010224215522964044,0.9349175765360737,0.010872442554285638 +flat_mae,reg,logistic,ppmi_dx,4,0.3593813663804626,test,0.66,0.047717434968782634,0.6310763888888888,0.052286820138305636,0.6290322580645161,0.051283235309100034 +flat_mae,reg,logistic,ppmi_dx,5,0.3593813663804626,train,0.9537366548042705,0.008771802375419375,0.9504859237973895,0.009534991524508186,0.9450331834724899,0.010621739903830729 +flat_mae,reg,logistic,ppmi_dx,5,0.3593813663804626,test,0.67,0.04906101914962631,0.6440513428972063,0.05272953262069764,0.6421901528013583,0.05196299211804547 +flat_mae,reg,logistic,ppmi_dx,6,0.046415888336127774,train,0.8291814946619217,0.015066415362436298,0.8110712684894665,0.01755443587966885,0.8003907086277029,0.017705134719214317 +flat_mae,reg,logistic,ppmi_dx,6,0.046415888336127774,test,0.64,0.04630740329580142,0.5989304812834224,0.053227809144682524,0.597623089983022,0.05025862367859359 +flat_mae,reg,logistic,ppmi_dx,7,0.046415888336127774,train,0.8309608540925267,0.01571737666182147,0.8154351395730706,0.01762510329003973,0.8070541639905802,0.01780477091785505 +flat_mae,reg,logistic,ppmi_dx,7,0.046415888336127774,test,0.67,0.046668237592606805,0.6396986570586308,0.05219317764316586,0.6370967741935484,0.05106902065995231 +flat_mae,reg,logistic,ppmi_dx,8,0.3593813663804626,train,0.9483985765124555,0.009232139831656199,0.9444972296291756,0.010150689591089975,0.9372190109184328,0.011436972079153979 +flat_mae,reg,logistic,ppmi_dx,8,0.3593813663804626,test,0.56,0.04475544212718716,0.5024875621890548,0.04890032673829789,0.5076400679117148,0.04594226092553963 +flat_mae,reg,logistic,ppmi_dx,9,0.005994842503189409,train,0.7384341637010676,0.01588100331794786,0.6935898434457513,0.02020955200430675,0.6866837936202098,0.0182147915423355 +flat_mae,reg,logistic,ppmi_dx,9,0.005994842503189409,test,0.73,0.039850902122787635,0.6871741397288842,0.04971662395826252,0.6803904923599321,0.0457184732753773 +flat_mae,reg,logistic,ppmi_dx,10,0.046415888336127774,train,0.8345195729537367,0.01425825970740703,0.8171974188132837,0.01648836627053478,0.8064654249625348,0.016707454900110764 +flat_mae,reg,logistic,ppmi_dx,10,0.046415888336127774,test,0.6,0.044379900856130805,0.554367201426025,0.05047045108947397,0.5551782682512734,0.047237302714573756 +flat_mae,reg,logistic,ppmi_dx,11,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,ppmi_dx,11,166.81005372000556,test,0.6,0.04690671593705959,0.5755517826825127,0.04926949517940075,0.5755517826825127,0.04910779792428837 +flat_mae,reg,logistic,ppmi_dx,12,0.046415888336127774,train,0.8256227758007118,0.014880638981466876,0.8085112300952646,0.017001087168698956,0.7992399914365232,0.017170164571866202 +flat_mae,reg,logistic,ppmi_dx,12,0.046415888336127774,test,0.68,0.044957201870223194,0.6381727725011307,0.05158916878500798,0.634974533106961,0.048526839842531075 +flat_mae,reg,logistic,ppmi_dx,13,0.046415888336127774,train,0.8309608540925267,0.015206956190226628,0.8137144412305524,0.017494107336497738,0.8035752515521302,0.017660084684796348 +flat_mae,reg,logistic,ppmi_dx,13,0.046415888336127774,test,0.62,0.042269965696697706,0.5824175824175825,0.04778227575881548,0.5814940577249575,0.04559836377826753 +flat_mae,reg,logistic,ppmi_dx,14,0.005994842503189409,train,0.7544483985765125,0.016322465101355474,0.7109570661896243,0.021242669644858082,0.7022987582958682,0.01922098321790879 +flat_mae,reg,logistic,ppmi_dx,14,0.005994842503189409,test,0.62,0.040836748156531766,0.5476190476190476,0.05050960736645063,0.5560271646859083,0.04365102302735377 +flat_mae,reg,logistic,ppmi_dx,15,0.005994842503189409,train,0.7295373665480427,0.015643593811204243,0.683671051072402,0.020216201061561093,0.6777189038749732,0.018176521862810425 +flat_mae,reg,logistic,ppmi_dx,15,0.005994842503189409,test,0.66,0.04485905036890549,0.6155585707824514,0.05163996984990924,0.6137521222410866,0.048309903606239754 +flat_mae,reg,logistic,ppmi_dx,16,0.046415888336127774,train,0.8345195729537367,0.014407914461809366,0.8158370418917348,0.01678798305281218,0.8038562406336973,0.016788532834137934 +flat_mae,reg,logistic,ppmi_dx,16,0.046415888336127774,test,0.59,0.049394671777429594,0.5670995670995671,0.05118656391982971,0.5674872665534805,0.05121563500300935 +flat_mae,reg,logistic,ppmi_dx,17,0.005994842503189409,train,0.7473309608540926,0.017096680987963554,0.706326542628356,0.021739360153178802,0.6982578676942839,0.019874672324355427 +flat_mae,reg,logistic,ppmi_dx,17,0.005994842503189409,test,0.68,0.04314535432697244,0.6323529411764706,0.05202111032116515,0.6298811544991512,0.04757746532071468 +flat_mae,reg,logistic,ppmi_dx,18,0.005994842503189409,train,0.7366548042704626,0.015225253640750024,0.6929641934293097,0.019378047427162457,0.68610843502462,0.01751851383103742 +flat_mae,reg,logistic,ppmi_dx,18,0.005994842503189409,test,0.63,0.04376563035076726,0.5783475783475784,0.05128553556008317,0.5793718166383701,0.04701984860262091 +flat_mae,reg,logistic,ppmi_dx,19,0.046415888336127774,train,0.8398576512455516,0.01519299399481594,0.8253453038674033,0.01711741470622198,0.8168887818454292,0.017495894248863452 +flat_mae,reg,logistic,ppmi_dx,19,0.046415888336127774,test,0.62,0.049210450109707385,0.6041666666666667,0.04992996905872085,0.6069609507640068,0.05035624979883742 +flat_mae,reg,logistic,ppmi_dx,20,0.046415888336127774,train,0.8309608540925267,0.015450117585560044,0.8141553798867319,0.017712184603870924,0.8044449796617427,0.017868718185382226 +flat_mae,reg,logistic,ppmi_dx,20,0.046415888336127774,test,0.67,0.04456052064327794,0.6349153667441089,0.049917329834335986,0.6320033955857385,0.04781851869119677 +flat_mae,reg,logistic,ppmi_dx,21,0.046415888336127774,train,0.8291814946619217,0.015831274343840976,0.8106070179872783,0.01841280481133683,0.7995209805180903,0.018403812767108244 +flat_mae,reg,logistic,ppmi_dx,21,0.046415888336127774,test,0.7,0.04095607403060014,0.6553308823529411,0.05006881710260014,0.6511035653650254,0.04586094336588796 +flat_mae,reg,logistic,ppmi_dx,22,0.046415888336127774,train,0.8256227758007118,0.01588988454953594,0.8085112300952646,0.018151518604369445,0.7992399914365232,0.018350607789414247 +flat_mae,reg,logistic,ppmi_dx,22,0.046415888336127774,test,0.6,0.04470792323514927,0.5604395604395604,0.04892182934534887,0.5602716468590832,0.047137649180441304 +flat_mae,reg,logistic,ppmi_dx,23,0.3593813663804626,train,0.9412811387900356,0.009811624758182773,0.937216269740517,0.010607006188258761,0.9323083922072362,0.011337358255364279 +flat_mae,reg,logistic,ppmi_dx,23,0.3593813663804626,test,0.64,0.04743063988604834,0.609375,0.05228316521455914,0.6078098471986417,0.05103345158346991 +flat_mae,reg,logistic,ppmi_dx,24,0.005994842503189409,train,0.7419928825622776,0.016251578867333447,0.6996568665391434,0.02070842321742073,0.692183151359452,0.01882216464446769 +flat_mae,reg,logistic,ppmi_dx,24,0.005994842503189409,test,0.63,0.04166341320631328,0.5636277862955537,0.052336047263510536,0.5691850594227504,0.04560816715778895 +flat_mae,reg,logistic,ppmi_dx,25,0.3593813663804626,train,0.9395017793594306,0.009983927890585744,0.9358550864754539,0.01064295563719047,0.9343422179404839,0.011153189331632162 +flat_mae,reg,logistic,ppmi_dx,25,0.3593813663804626,test,0.65,0.04206495453462419,0.6011396011396011,0.049552923841993265,0.6005942275042444,0.045688004304576646 +flat_mae,reg,logistic,ppmi_dx,26,0.3593813663804626,train,0.9501779359430605,0.008677043298657853,0.9468816246067431,0.009349623414236487,0.9430127381716977,0.01016666874419988 +flat_mae,reg,logistic,ppmi_dx,26,0.3593813663804626,test,0.62,0.04872424858322599,0.5924495924495925,0.05112232957827361,0.5916808149405772,0.05055497556556213 +flat_mae,reg,logistic,ppmi_dx,27,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,ppmi_dx,27,2.782559402207126,test,0.56,0.04578006553075257,0.5164835164835164,0.04917534682998962,0.5178268251273345,0.047289922725388886 +flat_mae,reg,logistic,ppmi_dx,28,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,ppmi_dx,28,21.54434690031882,test,0.6,0.04681163957820747,0.5659722222222222,0.051075859684550785,0.565365025466893,0.04959095107599852 +flat_mae,reg,logistic,ppmi_dx,29,0.046415888336127774,train,0.8345195729537367,0.014839104924712583,0.8162979104792366,0.01759671717095099,0.8047259687433097,0.017842372688641858 +flat_mae,reg,logistic,ppmi_dx,29,0.046415888336127774,test,0.67,0.041256364357514584,0.6176572818908586,0.04996984157089326,0.616723259762309,0.045054188803215184 +flat_mae,reg,logistic,ppmi_dx,30,0.046415888336127774,train,0.8327402135231317,0.01487467177749106,0.8150072837292694,0.017149641110265082,0.80415061014772,0.017299473062552955 +flat_mae,reg,logistic,ppmi_dx,30,0.046415888336127774,test,0.66,0.04184770483551039,0.5952380952380952,0.05297335906622304,0.5984719864176571,0.046072688206823156 +flat_mae,reg,logistic,ppmi_dx,31,0.046415888336127774,train,0.8327402135231317,0.015242861142027747,0.8171712557276742,0.017182745742754052,0.8084992506957824,0.017378501114209896 +flat_mae,reg,logistic,ppmi_dx,31,0.046415888336127774,test,0.67,0.04531812440955605,0.648,0.04779128475894487,0.6472835314091681,0.04743426725927141 +flat_mae,reg,logistic,ppmi_dx,32,0.005994842503189409,train,0.7330960854092526,0.016902013004111077,0.6907329958177416,0.021404960421159535,0.6840879897238279,0.019549868777907077 +flat_mae,reg,logistic,ppmi_dx,32,0.005994842503189409,test,0.7,0.044219163266620044,0.66078697421981,0.05207296789997159,0.6561969439728353,0.04868046046514683 +flat_mae,reg,logistic,ppmi_dx,33,0.046415888336127774,train,0.8487544483985765,0.014684394811141041,0.8333234474168101,0.01692002931604079,0.8223747591522158,0.017310801640719863 +flat_mae,reg,logistic,ppmi_dx,33,0.046415888336127774,test,0.65,0.04411825472522684,0.612789025334661,0.04922917888563236,0.6107809847198642,0.04698983918323897 +flat_mae,reg,logistic,ppmi_dx,34,0.005994842503189409,train,0.7241992882562278,0.01676771653135318,0.6789435469901188,0.020859484178062264,0.6733836437593663,0.018896359615221223 +flat_mae,reg,logistic,ppmi_dx,34,0.005994842503189409,test,0.68,0.040792406156048205,0.6114618746964546,0.05363900507034931,0.6146010186757216,0.045541210994518896 +flat_mae,reg,logistic,ppmi_dx,35,0.046415888336127774,train,0.8434163701067615,0.014608790163499495,0.828050900493707,0.016664344080267183,0.8180394990366089,0.016943710634358764 +flat_mae,reg,logistic,ppmi_dx,35,0.046415888336127774,test,0.62,0.04719133818827349,0.5967741935483871,0.05002965481057404,0.5967741935483871,0.049866550909340585 +flat_mae,reg,logistic,ppmi_dx,36,0.3593813663804626,train,0.9412811387900356,0.00971477844584064,0.9370936065857357,0.010536060056025804,0.9314386640976235,0.011319434843054418 +flat_mae,reg,logistic,ppmi_dx,36,0.3593813663804626,test,0.63,0.04455380567358977,0.5783475783475784,0.052508599976154105,0.5793718166383701,0.04810090957286263 +flat_mae,reg,logistic,ppmi_dx,37,0.000774263682681127,train,0.6921708185053381,0.014175110749830126,0.6107768370063452,0.021110883002464415,0.6195407835581246,0.016539610867932816 +flat_mae,reg,logistic,ppmi_dx,37,0.000774263682681127,test,0.63,0.03198631582411455,0.49993242330044596,0.04883746360461434,0.5386247877758913,0.03520573419055316 +flat_mae,reg,logistic,ppmi_dx,38,0.005994842503189409,train,0.7473309608540926,0.01574370909552117,0.7054115909929863,0.0199601869596459,0.6973881395846714,0.01814385713218651 +flat_mae,reg,logistic,ppmi_dx,38,0.005994842503189409,test,0.63,0.044132577536327974,0.5847828526540231,0.05131969694616519,0.5844651952461799,0.04804521447013634 +flat_mae,reg,logistic,ppmi_dx,39,0.3593813663804626,train,0.9483985765124555,0.008497752688940865,0.9448264188628785,0.009202795253209963,0.9398281952472705,0.010039666015923971 +flat_mae,reg,logistic,ppmi_dx,39,0.3593813663804626,test,0.7,0.0442723570639739,0.6782496782496783,0.048028562923675924,0.6765704584040747,0.04788484920226372 +flat_mae,reg,logistic,ppmi_dx,40,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,ppmi_dx,40,2.782559402207126,test,0.56,0.049672732962864036,0.548440065681445,0.05013220599123644,0.5534804753820034,0.051518004939483796 +flat_mae,reg,logistic,ppmi_dx,41,0.046415888336127774,train,0.8220640569395018,0.01511413122052117,0.8017245029000437,0.017730033129836988,0.7902617212588311,0.017588134459466387 +flat_mae,reg,logistic,ppmi_dx,41,0.046415888336127774,test,0.7,0.04288206618156359,0.6782496782496783,0.04641082883250137,0.6765704584040747,0.04644011118979614 +flat_mae,reg,logistic,ppmi_dx,42,0.3593813663804626,train,0.9412811387900356,0.009449250351992884,0.9369687494689618,0.010300056678142605,0.9305689359880112,0.01114137408778536 +flat_mae,reg,logistic,ppmi_dx,42,0.3593813663804626,test,0.68,0.043621627663350655,0.6381727725011307,0.05130453274173231,0.634974533106961,0.04822914675311503 +flat_mae,reg,logistic,ppmi_dx,43,0.005994842503189409,train,0.7348754448398577,0.016437233175480466,0.6913715387195336,0.020907271390304856,0.6846633483194177,0.018983585295641387 +flat_mae,reg,logistic,ppmi_dx,43,0.005994842503189409,test,0.66,0.0419107384807283,0.6026180458158018,0.05126465332142897,0.6035653650254669,0.04574547532727064 +flat_mae,reg,logistic,ppmi_dx,44,0.005994842503189409,train,0.7348754448398577,0.015522857138098513,0.6884225409759819,0.020289077639816567,0.6820541639905802,0.018127639641770835 +flat_mae,reg,logistic,ppmi_dx,44,0.005994842503189409,test,0.67,0.0396640895521377,0.6108031607500884,0.049926648867611466,0.6116298811544991,0.044279798945567495 +flat_mae,reg,logistic,ppmi_dx,45,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,ppmi_dx,45,2.782559402207126,test,0.58,0.04920250400132091,0.5625,0.050084628877029184,0.564516129032258,0.05093229296057087 +flat_mae,reg,logistic,ppmi_dx,46,0.3593813663804626,train,0.9483985765124555,0.009211704417965387,0.9448264188628785,0.009944823749706642,0.9398281952472705,0.010704426744336335 +flat_mae,reg,logistic,ppmi_dx,46,0.3593813663804626,test,0.66,0.04758068515689953,0.6263736263736264,0.05359237837364836,0.6239388794567062,0.05147814793320015 +flat_mae,reg,logistic,ppmi_dx,47,10000.0,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,ppmi_dx,47,10000.0,test,0.62,0.046013754465376984,0.5967741935483871,0.048666342129931026,0.5967741935483871,0.048549322640207754 +flat_mae,reg,logistic,ppmi_dx,48,0.046415888336127774,train,0.8309608540925267,0.01517503612371689,0.8128105070139087,0.01773225700041123,0.8018357953329052,0.017957268971453028 +flat_mae,reg,logistic,ppmi_dx,48,0.046415888336127774,test,0.69,0.04463370475324673,0.6693333333333333,0.048192226635651515,0.6685059422750425,0.04803598596327075 +flat_mae,reg,logistic,ppmi_dx,49,0.046415888336127774,train,0.8291814946619217,0.015895501318649828,0.81197724991636,0.018003644026301332,0.8021301648469279,0.017962796692000918 +flat_mae,reg,logistic,ppmi_dx,49,0.046415888336127774,test,0.68,0.043547762284645575,0.6381727725011307,0.051453192290975336,0.634974533106961,0.04786044741001962 +flat_mae,reg,logistic,ppmi_dx,50,0.005994842503189409,train,0.7330960854092526,0.015279501061737404,0.6878332740846071,0.01911922792941111,0.6814788053949904,0.01724694430428806 +flat_mae,reg,logistic,ppmi_dx,50,0.005994842503189409,test,0.7,0.038225703394443894,0.6357455075279261,0.05098134765230018,0.6358234295415959,0.04325657765575057 +flat_mae,reg,logistic,ppmi_dx,51,0.3593813663804626,train,0.9483985765124555,0.009492001846900477,0.944932305727405,0.010233189230316258,0.9406979233568828,0.01096505311816709 +flat_mae,reg,logistic,ppmi_dx,51,0.3593813663804626,test,0.55,0.04874857536379909,0.5331465919701214,0.0495848283351288,0.5352292020373515,0.050520954642768436 +flat_mae,reg,logistic,ppmi_dx,52,0.005994842503189409,train,0.7348754448398577,0.016926330520381446,0.6874083088512521,0.021650283830074713,0.6811844358809677,0.019290344628438018 +flat_mae,reg,logistic,ppmi_dx,52,0.005994842503189409,test,0.64,0.04330769446645712,0.592944369063772,0.049985852649667324,0.5925297113752122,0.04669699497542007 +flat_mae,reg,logistic,ppmi_dx,53,0.046415888336127774,train,0.8238434163701067,0.015616248768266373,0.8054037038980117,0.01800963593161676,0.7951857204024835,0.018049448093432716 +flat_mae,reg,logistic,ppmi_dx,53,0.046415888336127774,test,0.68,0.04563235255824533,0.6483516483516483,0.05112242789754754,0.6451612903225806,0.0494988903267271 +flat_mae,reg,logistic,ppmi_dx,54,0.3593813663804626,train,0.9483985765124555,0.008413138801728929,0.9450363040978271,0.009020381149394414,0.9415676514664955,0.009588572396126354 +flat_mae,reg,logistic,ppmi_dx,54,0.3593813663804626,test,0.54,0.04738379047733517,0.5008680555555556,0.049410328417599056,0.50169779286927,0.048096639160722356 +flat_mae,reg,logistic,ppmi_dx,55,0.3593813663804626,train,0.9448398576512456,0.0090665764752551,0.9410213443016977,0.009804854655505594,0.9360682937272533,0.010535680540444068 +flat_mae,reg,logistic,ppmi_dx,55,0.3593813663804626,test,0.63,0.04844633732285652,0.6129302228266555,0.05060108432219476,0.615025466893039,0.05136884131160359 +flat_mae,reg,logistic,ppmi_dx,56,0.005994842503189409,train,0.7366548042704626,0.01609573999816645,0.6975858057009889,0.019756691260435395,0.6904570755726825,0.018272068205693857 +flat_mae,reg,logistic,ppmi_dx,56,0.005994842503189409,test,0.58,0.0471736197466338,0.5384615384615385,0.051685729910777516,0.5390492359932089,0.04953349799005633 +flat_mae,reg,logistic,ppmi_dx,57,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,ppmi_dx,57,2.782559402207126,test,0.6,0.0450353816459903,0.5659722222222222,0.049207824708110824,0.565365025466893,0.047964563388613865 +flat_mae,reg,logistic,ppmi_dx,58,0.005994842503189409,train,0.7366548042704626,0.01582063242026614,0.6900119260584376,0.020643301424090186,0.6834992506957824,0.01841235974969284 +flat_mae,reg,logistic,ppmi_dx,58,0.005994842503189409,test,0.72,0.03544471187638574,0.6527777777777778,0.050855636322051936,0.6519524617996604,0.042044466511358056 +flat_mae,reg,logistic,ppmi_dx,59,0.3593813663804626,train,0.9501779359430605,0.008917893848245099,0.946780303030303,0.009633620178612311,0.9421430100620852,0.010513086124589505 +flat_mae,reg,logistic,ppmi_dx,59,0.3593813663804626,test,0.56,0.050171529775361635,0.5416666666666666,0.051742988449116116,0.5432937181663837,0.052568777225588996 +flat_mae,reg,logistic,ppmi_dx,60,0.046415888336127774,train,0.8380782918149466,0.014931635855434064,0.8228044584729349,0.01687739768822031,0.813704238921002,0.01708642646676332 +flat_mae,reg,logistic,ppmi_dx,60,0.046415888336127774,test,0.63,0.047221842403701274,0.6009060511271707,0.051504515947467765,0.5997453310696095,0.05067938734347097 +flat_mae,reg,logistic,ppmi_dx,61,0.3593813663804626,train,0.9430604982206405,0.010056901723376544,0.9392932852648492,0.010841940882068888,0.9354929351316634,0.011596925414178668 +flat_mae,reg,logistic,ppmi_dx,61,0.3593813663804626,test,0.59,0.046146913222879817,0.539894512400404,0.051529419264863145,0.5420203735144312,0.0483053454391788 +flat_mae,reg,logistic,ppmi_dx,62,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,ppmi_dx,62,21.54434690031882,test,0.66,0.04768957538078945,0.6353496353496353,0.05082552101623715,0.634125636672326,0.05006302860218918 +flat_mae,reg,logistic,ppmi_dx,63,0.046415888336127774,train,0.8505338078291815,0.014538096132439043,0.835866768653084,0.016490205492022385,0.8255593020766431,0.01670310929781732 +flat_mae,reg,logistic,ppmi_dx,63,0.046415888336127774,test,0.6,0.04485369995886627,0.554367201426025,0.05138309676203943,0.5551782682512734,0.04838186731935433 +flat_mae,reg,logistic,ppmi_dx,64,0.046415888336127774,train,0.8434163701067615,0.014171835501005507,0.8272339830922937,0.016359505780519538,0.8163000428173839,0.016591119037248976 +flat_mae,reg,logistic,ppmi_dx,64,0.046415888336127774,test,0.59,0.043308770474350805,0.5327635327635327,0.04925390730736869,0.5369269949066213,0.04540459502710658 +flat_mae,reg,logistic,ppmi_dx,65,0.046415888336127774,train,0.8345195729537367,0.015320300817132886,0.8184924727822056,0.01752588103637528,0.8090746092913723,0.017842763805002722 +flat_mae,reg,logistic,ppmi_dx,65,0.046415888336127774,test,0.56,0.046181814602719966,0.5098039215686274,0.04967947477132548,0.5127334465195246,0.047120559045739155 +flat_mae,reg,logistic,ppmi_dx,66,0.005994842503189409,train,0.7437722419928826,0.015703116245813636,0.7048879034963607,0.019544618036337585,0.6971071505031042,0.018026162992551054 +flat_mae,reg,logistic,ppmi_dx,66,0.005994842503189409,test,0.62,0.04501384675852532,0.5703301673450927,0.05130678892130859,0.5713073005093379,0.04761056594865896 +flat_mae,reg,logistic,ppmi_dx,67,0.046415888336127774,train,0.8327402135231317,0.015024998271804127,0.8158943905431024,0.017116538016026084,0.8058900663669449,0.01719893746920431 +flat_mae,reg,logistic,ppmi_dx,67,0.046415888336127774,test,0.68,0.044492444302375644,0.6527777777777778,0.048629040672170165,0.6502546689303905,0.0477895014298583 +flat_mae,reg,logistic,ppmi_dx,68,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,ppmi_dx,68,21.54434690031882,test,0.56,0.04764829482783198,0.5416666666666666,0.04870792833358372,0.5432937181663837,0.04940304402059872 +flat_mae,reg,logistic,ppmi_dx,69,0.005994842503189409,train,0.7206405693950177,0.016731869939984448,0.6758045729948596,0.020810783251310843,0.6704934703489617,0.018854714555022453 +flat_mae,reg,logistic,ppmi_dx,69,0.005994842503189409,test,0.66,0.04404668432470257,0.6155585707824514,0.05095173425093403,0.6137521222410866,0.04763415882067036 +flat_mae,reg,logistic,ppmi_dx,70,0.046415888336127774,train,0.8202846975088968,0.014897340812648596,0.8009880127200502,0.017222811103673068,0.7905560907728538,0.017189285972546372 +flat_mae,reg,logistic,ppmi_dx,70,0.046415888336127774,test,0.6,0.04647354085928895,0.5604395604395604,0.05028419976048793,0.5602716468590832,0.0484560534695048 +flat_mae,reg,logistic,ppmi_dx,71,0.046415888336127774,train,0.8274021352313167,0.015112522322504261,0.8093349422031023,0.017453995263042373,0.7989456219225005,0.017538434477918696 +flat_mae,reg,logistic,ppmi_dx,71,0.046415888336127774,test,0.61,0.04429860494417404,0.5555555555555556,0.05061507765622923,0.5581494057724957,0.0464814876467233 +flat_mae,reg,logistic,ppmi_dx,72,0.046415888336127774,train,0.8291814946619217,0.01468506793387901,0.809655522784042,0.017244013388407517,0.7977815242988653,0.017228343994379443 +flat_mae,reg,logistic,ppmi_dx,72,0.046415888336127774,test,0.61,0.048655523838511905,0.5920075321686369,0.04998568190644371,0.5938030560271647,0.05057563314148516 +flat_mae,reg,logistic,ppmi_dx,73,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,ppmi_dx,73,166.81005372000556,test,0.54,0.050293295775878516,0.5308037535699714,0.05019313516772131,0.5373514431239388,0.05170091550810333 +flat_mae,reg,logistic,ppmi_dx,74,0.005994842503189409,train,0.7348754448398577,0.016644512362816458,0.6913715387195336,0.021000575995461988,0.6846633483194177,0.019109576708812758 +flat_mae,reg,logistic,ppmi_dx,74,0.005994842503189409,test,0.57,0.041399995169081834,0.50997150997151,0.047403853839706134,0.515704584040747,0.04336731394880627 +flat_mae,reg,logistic,ppmi_dx,75,0.000774263682681127,train,0.6886120996441281,0.014441961646619515,0.6012972534711665,0.021695061081215227,0.6131716977092699,0.016730924950142084 +flat_mae,reg,logistic,ppmi_dx,75,0.000774263682681127,test,0.7,0.03503421755940896,0.6194824961948249,0.052541815861741795,0.6256366723259762,0.041453863738906645 +flat_mae,reg,logistic,ppmi_dx,76,10000.0,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,ppmi_dx,76,10000.0,test,0.59,0.04941585170772633,0.5670995670995671,0.05170009266778246,0.5674872665534805,0.051699684214958935 +flat_mae,reg,logistic,ppmi_dx,77,0.046415888336127774,train,0.8451957295373665,0.014819607354731179,0.8305932734851136,0.016798231129504376,0.8212240419610362,0.017139971971012902 +flat_mae,reg,logistic,ppmi_dx,77,0.046415888336127774,test,0.63,0.04174254424445161,0.5960257670051315,0.04616666354345034,0.5946519524617997,0.04480035069729405 +flat_mae,reg,logistic,ppmi_dx,78,0.046415888336127774,train,0.8309608540925267,0.014654326799796835,0.8141553798867319,0.016693872360371027,0.8044449796617427,0.01684354069608783 +flat_mae,reg,logistic,ppmi_dx,78,0.046415888336127774,test,0.66,0.042091785421861115,0.6026180458158018,0.05214492978441291,0.6035653650254669,0.04651454052340558 +flat_mae,reg,logistic,ppmi_dx,79,0.3593813663804626,train,0.9430604982206405,0.008988629965076989,0.9391774891774892,0.009709685775599471,0.9346232070220509,0.010451723005680525 +flat_mae,reg,logistic,ppmi_dx,79,0.3593813663804626,test,0.64,0.044684243307904416,0.609375,0.048755038984962744,0.6078098471986417,0.047461823619630056 +flat_mae,reg,logistic,ppmi_dx,80,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,ppmi_dx,80,2.782559402207126,test,0.62,0.047434063709532626,0.5924495924495925,0.05092819443634123,0.5916808149405772,0.05040094562977497 +flat_mae,reg,logistic,ppmi_dx,81,0.3593813663804626,train,0.9448398576512456,0.009112974340940262,0.9413548767146342,0.009757220936601255,0.9386774780560908,0.010345429187925475 +flat_mae,reg,logistic,ppmi_dx,81,0.3593813663804626,test,0.65,0.04385785676478047,0.6266666666666667,0.04709054730112285,0.6260611205432938,0.04707232773338551 +flat_mae,reg,logistic,ppmi_dx,82,0.3593813663804626,train,0.9323843416370107,0.010324434065841284,0.9274907648848327,0.011226178479927098,0.9216040462427746,0.01201794902334754 +flat_mae,reg,logistic,ppmi_dx,82,0.3593813663804626,test,0.69,0.04308582597560361,0.6615351020853806,0.048007796001166815,0.6583191850594228,0.04680356953632647 +flat_mae,reg,logistic,ppmi_dx,83,0.3593813663804626,train,0.9537366548042705,0.00848717069836531,0.9509480073047589,0.00902947606110063,0.9493818240205524,0.009441144571903159 +flat_mae,reg,logistic,ppmi_dx,83,0.3593813663804626,test,0.62,0.047337089052876924,0.614448051948052,0.04719755900155717,0.6273344651952462,0.04847590468197732 +flat_mae,reg,logistic,ppmi_dx,84,0.046415888336127774,train,0.8345195729537367,0.014678305119368861,0.8189100509668455,0.016724492003655788,0.8099443374009848,0.017049591149782252 +flat_mae,reg,logistic,ppmi_dx,84,0.046415888336127774,test,0.6,0.048346462124958016,0.5659722222222222,0.0527037543585211,0.565365025466893,0.051624653093286454 +flat_mae,reg,logistic,ppmi_dx,85,0.046415888336127774,train,0.8327402135231317,0.014690889309200402,0.8150072837292694,0.017049175482892448,0.80415061014772,0.01716409380160775 +flat_mae,reg,logistic,ppmi_dx,85,0.046415888336127774,test,0.65,0.043023416879648224,0.6178622120318812,0.04709803004998445,0.615874363327674,0.04583444669790659 +flat_mae,reg,logistic,ppmi_dx,86,0.005994842503189409,train,0.7455516014234875,0.015191411372752928,0.7037995304489483,0.019196320482305993,0.695943052879469,0.017471370136558747 +flat_mae,reg,logistic,ppmi_dx,86,0.005994842503189409,test,0.6,0.03989636073628771,0.5143273433705683,0.05040481614540427,0.5297113752122241,0.04239791583929846 +flat_mae,reg,logistic,ppmi_dx,87,0.3593813663804626,train,0.9501779359430605,0.008657475092442028,0.946780303030303,0.009357135974864978,0.9421430100620852,0.010234961681374524 +flat_mae,reg,logistic,ppmi_dx,87,0.3593813663804626,test,0.6,0.04523483171185674,0.570999570999571,0.048289188097424864,0.5704584040747029,0.047542607567654764 +flat_mae,reg,logistic,ppmi_dx,88,0.3593813663804626,train,0.9359430604982206,0.010288400865090051,0.9313070404172099,0.011209042888631953,0.9253639477627917,0.012141911555561456 +flat_mae,reg,logistic,ppmi_dx,88,0.3593813663804626,test,0.66,0.04474948491323671,0.6263736263736264,0.050193967288065466,0.6239388794567062,0.048406001214312606 +flat_mae,reg,logistic,ppmi_dx,89,0.3593813663804626,train,0.9341637010676157,0.01065700298478054,0.9297412176522065,0.011502683052967587,0.9256583172768144,0.01227382322446705 +flat_mae,reg,logistic,ppmi_dx,89,0.3593813663804626,test,0.68,0.04444693015271133,0.6567996567996568,0.048248148096335215,0.6553480475382003,0.04781878250591834 +flat_mae,reg,logistic,ppmi_dx,90,0.046415888336127774,train,0.8256227758007118,0.016038243766216133,0.8093913091628944,0.018083464213245155,0.8009794476557482,0.018199686351559385 +flat_mae,reg,logistic,ppmi_dx,90,0.046415888336127774,test,0.66,0.04514660120097636,0.6263736263736264,0.04935998434051278,0.6239388794567062,0.04756142164928627 +flat_mae,reg,logistic,ppmi_dx,91,0.046415888336127774,train,0.8256227758007118,0.01594506652033994,0.8076014811709635,0.018473088783708812,0.7975005352172982,0.01861333307721747 +flat_mae,reg,logistic,ppmi_dx,91,0.046415888336127774,test,0.69,0.042398957534354534,0.6615351020853806,0.04812366902549615,0.6583191850594228,0.04675017062792594 +flat_mae,reg,logistic,ppmi_dx,92,0.046415888336127774,train,0.8185053380782918,0.014903433204215963,0.7987699566114832,0.01741587738695899,0.7882412759580391,0.017446641467507816 +flat_mae,reg,logistic,ppmi_dx,92,0.046415888336127774,test,0.68,0.04489810686432112,0.6527777777777778,0.04897361573235102,0.6502546689303905,0.0481765716550441 +flat_mae,reg,logistic,ppmi_dx,93,0.046415888336127774,train,0.8345195729537367,0.01417522153481113,0.8205120280224592,0.015656616485392696,0.8134232498394348,0.01583478117339795 +flat_mae,reg,logistic,ppmi_dx,93,0.046415888336127774,test,0.63,0.0457630899306417,0.6053333333333333,0.04887603078735123,0.6048387096774194,0.048607985163417376 +flat_mae,reg,logistic,ppmi_dx,94,0.046415888336127774,train,0.8327402135231317,0.014972176083017569,0.8154544819394955,0.01711514301792971,0.8050203382573324,0.01712199380558655 +flat_mae,reg,logistic,ppmi_dx,94,0.046415888336127774,test,0.7,0.040189929086774955,0.66078697421981,0.04690090000471416,0.6561969439728353,0.04382688836537066 +flat_mae,reg,logistic,ppmi_dx,95,0.046415888336127774,train,0.8345195729537367,0.0159592269966537,0.8184924727822056,0.0179804304938449,0.8090746092913723,0.018060866314198138 +flat_mae,reg,logistic,ppmi_dx,95,0.046415888336127774,test,0.65,0.04068148964824174,0.5872154735228211,0.04970613482379556,0.5904074702886248,0.04390800770802501 +flat_mae,reg,logistic,ppmi_dx,96,0.046415888336127774,train,0.8238434163701067,0.015630604236789202,0.8063303432503838,0.017969754852509824,0.7969251766217085,0.018076135036549885 +flat_mae,reg,logistic,ppmi_dx,96,0.046415888336127774,test,0.66,0.040979194721224084,0.6155585707824514,0.04809732388079008,0.6137521222410866,0.04453812079893039 +flat_mae,reg,logistic,ppmi_dx,97,0.046415888336127774,train,0.8167259786476868,0.015416473204112371,0.7970471812887641,0.01787836226959118,0.7867961892528367,0.017872805465510372 +flat_mae,reg,logistic,ppmi_dx,97,0.046415888336127774,test,0.72,0.04177985639037071,0.6923076923076923,0.04668133518949705,0.6876061120543294,0.045410690227966385 +flat_mae,reg,logistic,ppmi_dx,98,0.3593813663804626,train,0.9519572953736655,0.008425563583859076,0.9485311326610564,0.00916631839969759,0.942718368657675,0.010175267489692821 +flat_mae,reg,logistic,ppmi_dx,98,0.3593813663804626,test,0.61,0.04667787055982739,0.584,0.050187863910995625,0.583616298811545,0.049821973117357414 +flat_mae,reg,logistic,ppmi_dx,99,0.3593813663804626,train,0.9412811387900356,0.009402328520835041,0.9374551046630447,0.010114508613548094,0.9340478484264612,0.010837123260250676 +flat_mae,reg,logistic,ppmi_dx,99,0.3593813663804626,test,0.65,0.04616081021819266,0.6224786970121885,0.04959577241763764,0.6209677419354839,0.04865190010930696 +flat_mae,reg,logistic,ppmi_dx,100,0.046415888336127774,train,0.8202846975088968,0.015089061975131875,0.8028789220537931,0.017141816794318677,0.7940350032113038,0.017265901350210597 +flat_mae,reg,logistic,ppmi_dx,100,0.046415888336127774,test,0.65,0.04267519654319122,0.6072270227808326,0.05037030706169902,0.6056876061120543,0.04713903996398583 diff --git a/decoders/crossreg_reg4/eval_v2/ppmi_dx__reg__logistic/log.txt b/decoders/crossreg_reg4/eval_v2/ppmi_dx__reg__logistic/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..38c7ec6906d907164bf06651a4af62241f22fde0 --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/ppmi_dx__reg__logistic/log.txt @@ -0,0 +1,247 @@ +fMRI foundation model logistic probe eval +version: 0.1.dev66+g7ddd3aa04 +sha: aef99c83a386cf95c3d8ca503ecc968d8d5694af, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-03-07 21:19:47 +config: +output_root: experiments/decoders/output +name_prefix: eval_logistic +remote_root: null +notes: decoder ablations crossreg_reg4; eval v2 (ppmi_dx reg logistic) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: decoders/crossreg_reg4/eval_v2/ppmi_dx__reg__logistic +model: flat_mae +representation: reg +dataset: ppmi_dx +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg4/eval_v2/ppmi_dx__reg__logistic +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=False, reg_tokens=4, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: ppmi_dx (flat) +train (n=463): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'dir', 'sex', 'age', 'age_bin', 'dx', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 463 +}), + labels=['PD' 'Prodromal'], + counts=[178 285] +) + +validation (n=99): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'dir', 'sex', 'age', 'age_bin', 'dx', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 99 +}), + labels=['PD' 'Prodromal'], + counts=[39 60] +) + +test (n=100): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'dir', 'sex', 'age', 'age_bin', 'dx', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 100 +}), + labels=['PD' 'Prodromal'], + counts=[37 63] +) + +extracting features for all splits +extract (train) [ 0/232] eta: 0:18:04 time: 4.6753 data: 3.8785 max mem: 2698 +extract (train) [ 20/232] eta: 0:01:29 time: 0.2098 data: 0.0777 max mem: 2852 +extract (train) [ 40/232] eta: 0:00:59 time: 0.1902 data: 0.0696 max mem: 2852 +extract (train) [ 60/232] eta: 0:00:45 time: 0.1813 data: 0.0588 max mem: 2852 +extract (train) [ 80/232] eta: 0:00:37 time: 0.1716 data: 0.0564 max mem: 2852 +extract (train) [100/232] eta: 0:00:30 time: 0.1661 data: 0.0521 max mem: 2852 +extract (train) [120/232] eta: 0:00:24 time: 0.1721 data: 0.0553 max mem: 2852 +extract (train) [140/232] eta: 0:00:19 time: 0.1913 data: 0.0637 max mem: 2852 +extract (train) [160/232] eta: 0:00:15 time: 0.2049 data: 0.0764 max mem: 2852 +extract (train) [180/232] eta: 0:00:11 time: 0.1954 data: 0.0668 max mem: 2852 +extract (train) [200/232] eta: 0:00:06 time: 0.1613 data: 0.0497 max mem: 2852 +extract (train) [220/232] eta: 0:00:02 time: 0.1630 data: 0.0526 max mem: 2852 +extract (train) [231/232] eta: 0:00:00 time: 0.1604 data: 0.0500 max mem: 2852 +extract (train) Total time: 0:00:47 (0.2026 s / it) +extract (validation) [ 0/50] eta: 0:02:59 time: 3.5806 data: 3.4286 max mem: 2852 +extract (validation) [20/50] eta: 0:00:11 time: 0.2180 data: 0.0812 max mem: 2852 +extract (validation) [40/50] eta: 0:00:02 time: 0.1548 data: 0.0458 max mem: 2852 +extract (validation) [49/50] eta: 0:00:00 time: 0.1582 data: 0.0500 max mem: 2852 +extract (validation) Total time: 0:00:12 (0.2559 s / it) +extract (test) [ 0/50] eta: 0:03:01 time: 3.6263 data: 3.4029 max mem: 2852 +extract (test) [20/50] eta: 0:00:11 time: 0.2142 data: 0.0782 max mem: 2852 +extract (test) [40/50] eta: 0:00:02 time: 0.1561 data: 0.0483 max mem: 2852 +extract (test) [49/50] eta: 0:00:00 time: 0.1585 data: 0.0506 max mem: 2852 +extract (test) Total time: 0:00:12 (0.2561 s / it) +feature extraction time: 0:01:12 +train features: (463, 768) +validation features: (99, 768) +test features: (100, 768) +evaluating fixed splits +eval results (fixed splits): + +| model | repr | clf | dataset | trial | C | split | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|---------:|:--------|-------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | reg | logistic | ppmi_dx | | 0.046416 | train | 0.8452 | 0.015014 | 0.8302 | 0.017096 | 0.82006 | 0.01735 | +| flat_mae | reg | logistic | ppmi_dx | | 0.046416 | test | 0.6 | 0.044987 | 0.54772 | 0.049741 | 0.54869 | 0.046976 | + + +evaluating random splits (n=100) +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 1, "C": 0.046415888336127774, "split": "test", "acc": 0.71, "acc_std": 0.04159824996318955, "f1": 0.6745595331612613, "f1_std": 0.04870012161359999, "bacc": 0.6693548387096775, "bacc_std": 0.04601927064989391} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 2, "C": 0.000774263682681127, "split": "test", "acc": 0.65, "acc_std": 0.032287576558174824, "f1": 0.539413080668509, "f1_std": 0.04892759365300171, "bacc": 0.5649405772495755, "bacc_std": 0.03642134011041704} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 3, "C": 0.005994842503189409, "split": "test", "acc": 0.67, "acc_std": 0.042435362611859456, "f1": 0.6176572818908586, "f1_std": 0.05143445658117249, "bacc": 0.616723259762309, "bacc_std": 0.04641926150689125} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 4, "C": 0.3593813663804626, "split": "test", "acc": 0.66, "acc_std": 0.047717434968782634, "f1": 0.6310763888888888, "f1_std": 0.052286820138305636, "bacc": 0.6290322580645161, "bacc_std": 0.051283235309100034} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 5, "C": 0.3593813663804626, "split": "test", "acc": 0.67, "acc_std": 0.04906101914962631, "f1": 0.6440513428972063, "f1_std": 0.05272953262069764, "bacc": 0.6421901528013583, "bacc_std": 0.05196299211804547} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 6, "C": 0.046415888336127774, "split": "test", "acc": 0.64, "acc_std": 0.04630740329580142, "f1": 0.5989304812834224, "f1_std": 0.053227809144682524, "bacc": 0.597623089983022, "bacc_std": 0.05025862367859359} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 7, "C": 0.046415888336127774, "split": "test", "acc": 0.67, "acc_std": 0.046668237592606805, "f1": 0.6396986570586308, "f1_std": 0.05219317764316586, "bacc": 0.6370967741935484, "bacc_std": 0.05106902065995231} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 8, "C": 0.3593813663804626, "split": "test", "acc": 0.56, "acc_std": 0.04475544212718716, "f1": 0.5024875621890548, "f1_std": 0.04890032673829789, "bacc": 0.5076400679117148, "bacc_std": 0.04594226092553963} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 9, "C": 0.005994842503189409, "split": "test", "acc": 0.73, "acc_std": 0.039850902122787635, "f1": 0.6871741397288842, "f1_std": 0.04971662395826252, "bacc": 0.6803904923599321, "bacc_std": 0.0457184732753773} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 10, "C": 0.046415888336127774, "split": "test", "acc": 0.6, "acc_std": 0.044379900856130805, "f1": 0.554367201426025, "f1_std": 0.05047045108947397, "bacc": 0.5551782682512734, "bacc_std": 0.047237302714573756} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 11, "C": 166.81005372000556, "split": "test", "acc": 0.6, "acc_std": 0.04690671593705959, "f1": 0.5755517826825127, "f1_std": 0.04926949517940075, "bacc": 0.5755517826825127, "bacc_std": 0.04910779792428837} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 12, "C": 0.046415888336127774, "split": "test", "acc": 0.68, "acc_std": 0.044957201870223194, "f1": 0.6381727725011307, "f1_std": 0.05158916878500798, "bacc": 0.634974533106961, "bacc_std": 0.048526839842531075} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 13, "C": 0.046415888336127774, "split": "test", "acc": 0.62, "acc_std": 0.042269965696697706, "f1": 0.5824175824175825, "f1_std": 0.04778227575881548, "bacc": 0.5814940577249575, "bacc_std": 0.04559836377826753} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 14, "C": 0.005994842503189409, "split": "test", "acc": 0.62, "acc_std": 0.040836748156531766, "f1": 0.5476190476190476, "f1_std": 0.05050960736645063, "bacc": 0.5560271646859083, "bacc_std": 0.04365102302735377} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 15, "C": 0.005994842503189409, "split": "test", "acc": 0.66, "acc_std": 0.04485905036890549, "f1": 0.6155585707824514, "f1_std": 0.05163996984990924, "bacc": 0.6137521222410866, "bacc_std": 0.048309903606239754} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 16, "C": 0.046415888336127774, "split": "test", "acc": 0.59, "acc_std": 0.049394671777429594, "f1": 0.5670995670995671, "f1_std": 0.05118656391982971, "bacc": 0.5674872665534805, "bacc_std": 0.05121563500300935} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 17, "C": 0.005994842503189409, "split": "test", "acc": 0.68, "acc_std": 0.04314535432697244, "f1": 0.6323529411764706, "f1_std": 0.05202111032116515, "bacc": 0.6298811544991512, "bacc_std": 0.04757746532071468} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 18, "C": 0.005994842503189409, "split": "test", "acc": 0.63, "acc_std": 0.04376563035076726, "f1": 0.5783475783475784, "f1_std": 0.05128553556008317, "bacc": 0.5793718166383701, "bacc_std": 0.04701984860262091} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 19, "C": 0.046415888336127774, "split": "test", "acc": 0.62, "acc_std": 0.049210450109707385, "f1": 0.6041666666666667, "f1_std": 0.04992996905872085, "bacc": 0.6069609507640068, "bacc_std": 0.05035624979883742} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 20, "C": 0.046415888336127774, "split": "test", "acc": 0.67, "acc_std": 0.04456052064327794, "f1": 0.6349153667441089, "f1_std": 0.049917329834335986, "bacc": 0.6320033955857385, "bacc_std": 0.04781851869119677} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 21, "C": 0.046415888336127774, "split": "test", "acc": 0.7, "acc_std": 0.04095607403060014, "f1": 0.6553308823529411, "f1_std": 0.05006881710260014, "bacc": 0.6511035653650254, "bacc_std": 0.04586094336588796} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 22, "C": 0.046415888336127774, "split": "test", "acc": 0.6, "acc_std": 0.04470792323514927, "f1": 0.5604395604395604, "f1_std": 0.04892182934534887, "bacc": 0.5602716468590832, "bacc_std": 0.047137649180441304} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 23, "C": 0.3593813663804626, "split": "test", "acc": 0.64, "acc_std": 0.04743063988604834, "f1": 0.609375, "f1_std": 0.05228316521455914, "bacc": 0.6078098471986417, "bacc_std": 0.05103345158346991} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 24, "C": 0.005994842503189409, "split": "test", "acc": 0.63, "acc_std": 0.04166341320631328, "f1": 0.5636277862955537, "f1_std": 0.052336047263510536, "bacc": 0.5691850594227504, "bacc_std": 0.04560816715778895} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 25, "C": 0.3593813663804626, "split": "test", "acc": 0.65, "acc_std": 0.04206495453462419, "f1": 0.6011396011396011, "f1_std": 0.049552923841993265, "bacc": 0.6005942275042444, "bacc_std": 0.045688004304576646} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 26, "C": 0.3593813663804626, "split": "test", "acc": 0.62, "acc_std": 0.04872424858322599, "f1": 0.5924495924495925, "f1_std": 0.05112232957827361, "bacc": 0.5916808149405772, "bacc_std": 0.05055497556556213} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 27, "C": 2.782559402207126, "split": "test", "acc": 0.56, "acc_std": 0.04578006553075257, "f1": 0.5164835164835164, "f1_std": 0.04917534682998962, "bacc": 0.5178268251273345, "bacc_std": 0.047289922725388886} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 28, "C": 21.54434690031882, "split": "test", "acc": 0.6, "acc_std": 0.04681163957820747, "f1": 0.5659722222222222, "f1_std": 0.051075859684550785, "bacc": 0.565365025466893, "bacc_std": 0.04959095107599852} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 29, "C": 0.046415888336127774, "split": "test", "acc": 0.67, "acc_std": 0.041256364357514584, "f1": 0.6176572818908586, "f1_std": 0.04996984157089326, "bacc": 0.616723259762309, "bacc_std": 0.045054188803215184} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 30, "C": 0.046415888336127774, "split": "test", "acc": 0.66, "acc_std": 0.04184770483551039, "f1": 0.5952380952380952, "f1_std": 0.05297335906622304, "bacc": 0.5984719864176571, "bacc_std": 0.046072688206823156} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 31, "C": 0.046415888336127774, "split": "test", "acc": 0.67, "acc_std": 0.04531812440955605, "f1": 0.648, "f1_std": 0.04779128475894487, "bacc": 0.6472835314091681, "bacc_std": 0.04743426725927141} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 32, "C": 0.005994842503189409, "split": "test", "acc": 0.7, "acc_std": 0.044219163266620044, "f1": 0.66078697421981, "f1_std": 0.05207296789997159, "bacc": 0.6561969439728353, "bacc_std": 0.04868046046514683} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 33, "C": 0.046415888336127774, "split": "test", "acc": 0.65, "acc_std": 0.04411825472522684, "f1": 0.612789025334661, "f1_std": 0.04922917888563236, "bacc": 0.6107809847198642, "bacc_std": 0.04698983918323897} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 34, "C": 0.005994842503189409, "split": "test", "acc": 0.68, "acc_std": 0.040792406156048205, "f1": 0.6114618746964546, "f1_std": 0.05363900507034931, "bacc": 0.6146010186757216, "bacc_std": 0.045541210994518896} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 35, "C": 0.046415888336127774, "split": "test", "acc": 0.62, "acc_std": 0.04719133818827349, "f1": 0.5967741935483871, "f1_std": 0.05002965481057404, "bacc": 0.5967741935483871, "bacc_std": 0.049866550909340585} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 36, "C": 0.3593813663804626, "split": "test", "acc": 0.63, "acc_std": 0.04455380567358977, "f1": 0.5783475783475784, "f1_std": 0.052508599976154105, "bacc": 0.5793718166383701, "bacc_std": 0.04810090957286263} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 37, "C": 0.000774263682681127, "split": "test", "acc": 0.63, "acc_std": 0.03198631582411455, "f1": 0.49993242330044596, "f1_std": 0.04883746360461434, "bacc": 0.5386247877758913, "bacc_std": 0.03520573419055316} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 38, "C": 0.005994842503189409, "split": "test", "acc": 0.63, "acc_std": 0.044132577536327974, "f1": 0.5847828526540231, "f1_std": 0.05131969694616519, "bacc": 0.5844651952461799, "bacc_std": 0.04804521447013634} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 39, "C": 0.3593813663804626, "split": "test", "acc": 0.7, "acc_std": 0.0442723570639739, "f1": 0.6782496782496783, "f1_std": 0.048028562923675924, "bacc": 0.6765704584040747, "bacc_std": 0.04788484920226372} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 40, "C": 2.782559402207126, "split": "test", "acc": 0.56, "acc_std": 0.049672732962864036, "f1": 0.548440065681445, "f1_std": 0.05013220599123644, "bacc": 0.5534804753820034, "bacc_std": 0.051518004939483796} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 41, "C": 0.046415888336127774, "split": "test", "acc": 0.7, "acc_std": 0.04288206618156359, "f1": 0.6782496782496783, "f1_std": 0.04641082883250137, "bacc": 0.6765704584040747, "bacc_std": 0.04644011118979614} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 42, "C": 0.3593813663804626, "split": "test", "acc": 0.68, "acc_std": 0.043621627663350655, "f1": 0.6381727725011307, "f1_std": 0.05130453274173231, "bacc": 0.634974533106961, "bacc_std": 0.04822914675311503} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 43, "C": 0.005994842503189409, "split": "test", "acc": 0.66, "acc_std": 0.0419107384807283, "f1": 0.6026180458158018, "f1_std": 0.05126465332142897, "bacc": 0.6035653650254669, "bacc_std": 0.04574547532727064} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 44, "C": 0.005994842503189409, "split": "test", "acc": 0.67, "acc_std": 0.0396640895521377, "f1": 0.6108031607500884, "f1_std": 0.049926648867611466, "bacc": 0.6116298811544991, "bacc_std": 0.044279798945567495} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 45, "C": 2.782559402207126, "split": "test", "acc": 0.58, "acc_std": 0.04920250400132091, "f1": 0.5625, "f1_std": 0.050084628877029184, "bacc": 0.564516129032258, "bacc_std": 0.05093229296057087} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 46, "C": 0.3593813663804626, "split": "test", "acc": 0.66, "acc_std": 0.04758068515689953, "f1": 0.6263736263736264, "f1_std": 0.05359237837364836, "bacc": 0.6239388794567062, "bacc_std": 0.05147814793320015} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 47, "C": 10000.0, "split": "test", "acc": 0.62, "acc_std": 0.046013754465376984, "f1": 0.5967741935483871, "f1_std": 0.048666342129931026, "bacc": 0.5967741935483871, "bacc_std": 0.048549322640207754} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 48, "C": 0.046415888336127774, "split": "test", "acc": 0.69, "acc_std": 0.04463370475324673, "f1": 0.6693333333333333, "f1_std": 0.048192226635651515, "bacc": 0.6685059422750425, "bacc_std": 0.04803598596327075} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 49, "C": 0.046415888336127774, "split": "test", "acc": 0.68, "acc_std": 0.043547762284645575, "f1": 0.6381727725011307, "f1_std": 0.051453192290975336, "bacc": 0.634974533106961, "bacc_std": 0.04786044741001962} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 50, "C": 0.005994842503189409, "split": "test", "acc": 0.7, "acc_std": 0.038225703394443894, "f1": 0.6357455075279261, "f1_std": 0.05098134765230018, "bacc": 0.6358234295415959, "bacc_std": 0.04325657765575057} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 51, "C": 0.3593813663804626, "split": "test", "acc": 0.55, "acc_std": 0.04874857536379909, "f1": 0.5331465919701214, "f1_std": 0.0495848283351288, "bacc": 0.5352292020373515, "bacc_std": 0.050520954642768436} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 52, "C": 0.005994842503189409, "split": "test", "acc": 0.64, "acc_std": 0.04330769446645712, "f1": 0.592944369063772, "f1_std": 0.049985852649667324, "bacc": 0.5925297113752122, "bacc_std": 0.04669699497542007} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 53, "C": 0.046415888336127774, "split": "test", "acc": 0.68, "acc_std": 0.04563235255824533, "f1": 0.6483516483516483, "f1_std": 0.05112242789754754, "bacc": 0.6451612903225806, "bacc_std": 0.0494988903267271} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 54, "C": 0.3593813663804626, "split": "test", "acc": 0.54, "acc_std": 0.04738379047733517, "f1": 0.5008680555555556, "f1_std": 0.049410328417599056, "bacc": 0.50169779286927, "bacc_std": 0.048096639160722356} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 55, "C": 0.3593813663804626, "split": "test", "acc": 0.63, "acc_std": 0.04844633732285652, "f1": 0.6129302228266555, "f1_std": 0.05060108432219476, "bacc": 0.615025466893039, "bacc_std": 0.05136884131160359} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 56, "C": 0.005994842503189409, "split": "test", "acc": 0.58, "acc_std": 0.0471736197466338, "f1": 0.5384615384615385, "f1_std": 0.051685729910777516, "bacc": 0.5390492359932089, "bacc_std": 0.04953349799005633} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 57, "C": 2.782559402207126, "split": "test", "acc": 0.6, "acc_std": 0.0450353816459903, "f1": 0.5659722222222222, "f1_std": 0.049207824708110824, "bacc": 0.565365025466893, "bacc_std": 0.047964563388613865} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 58, "C": 0.005994842503189409, "split": "test", "acc": 0.72, "acc_std": 0.03544471187638574, "f1": 0.6527777777777778, "f1_std": 0.050855636322051936, "bacc": 0.6519524617996604, "bacc_std": 0.042044466511358056} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 59, "C": 0.3593813663804626, "split": "test", "acc": 0.56, "acc_std": 0.050171529775361635, "f1": 0.5416666666666666, "f1_std": 0.051742988449116116, "bacc": 0.5432937181663837, "bacc_std": 0.052568777225588996} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 60, "C": 0.046415888336127774, "split": "test", "acc": 0.63, "acc_std": 0.047221842403701274, "f1": 0.6009060511271707, "f1_std": 0.051504515947467765, "bacc": 0.5997453310696095, "bacc_std": 0.05067938734347097} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 61, "C": 0.3593813663804626, "split": "test", "acc": 0.59, "acc_std": 0.046146913222879817, "f1": 0.539894512400404, "f1_std": 0.051529419264863145, "bacc": 0.5420203735144312, "bacc_std": 0.0483053454391788} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 62, "C": 21.54434690031882, "split": "test", "acc": 0.66, "acc_std": 0.04768957538078945, "f1": 0.6353496353496353, "f1_std": 0.05082552101623715, "bacc": 0.634125636672326, "bacc_std": 0.05006302860218918} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 63, "C": 0.046415888336127774, "split": "test", "acc": 0.6, "acc_std": 0.04485369995886627, "f1": 0.554367201426025, "f1_std": 0.05138309676203943, "bacc": 0.5551782682512734, "bacc_std": 0.04838186731935433} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 64, "C": 0.046415888336127774, "split": "test", "acc": 0.59, "acc_std": 0.043308770474350805, "f1": 0.5327635327635327, "f1_std": 0.04925390730736869, "bacc": 0.5369269949066213, "bacc_std": 0.04540459502710658} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 65, "C": 0.046415888336127774, "split": "test", "acc": 0.56, "acc_std": 0.046181814602719966, "f1": 0.5098039215686274, "f1_std": 0.04967947477132548, "bacc": 0.5127334465195246, "bacc_std": 0.047120559045739155} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 66, "C": 0.005994842503189409, "split": "test", "acc": 0.62, "acc_std": 0.04501384675852532, "f1": 0.5703301673450927, "f1_std": 0.05130678892130859, "bacc": 0.5713073005093379, "bacc_std": 0.04761056594865896} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 67, "C": 0.046415888336127774, "split": "test", "acc": 0.68, "acc_std": 0.044492444302375644, "f1": 0.6527777777777778, "f1_std": 0.048629040672170165, "bacc": 0.6502546689303905, "bacc_std": 0.0477895014298583} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 68, "C": 21.54434690031882, "split": "test", "acc": 0.56, "acc_std": 0.04764829482783198, "f1": 0.5416666666666666, "f1_std": 0.04870792833358372, "bacc": 0.5432937181663837, "bacc_std": 0.04940304402059872} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 69, "C": 0.005994842503189409, "split": "test", "acc": 0.66, "acc_std": 0.04404668432470257, "f1": 0.6155585707824514, "f1_std": 0.05095173425093403, "bacc": 0.6137521222410866, "bacc_std": 0.04763415882067036} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 70, "C": 0.046415888336127774, "split": "test", "acc": 0.6, "acc_std": 0.04647354085928895, "f1": 0.5604395604395604, "f1_std": 0.05028419976048793, "bacc": 0.5602716468590832, "bacc_std": 0.0484560534695048} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 71, "C": 0.046415888336127774, "split": "test", "acc": 0.61, "acc_std": 0.04429860494417404, "f1": 0.5555555555555556, "f1_std": 0.05061507765622923, "bacc": 0.5581494057724957, "bacc_std": 0.0464814876467233} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 72, "C": 0.046415888336127774, "split": "test", "acc": 0.61, "acc_std": 0.048655523838511905, "f1": 0.5920075321686369, "f1_std": 0.04998568190644371, "bacc": 0.5938030560271647, "bacc_std": 0.05057563314148516} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 73, "C": 166.81005372000556, "split": "test", "acc": 0.54, "acc_std": 0.050293295775878516, "f1": 0.5308037535699714, "f1_std": 0.05019313516772131, "bacc": 0.5373514431239388, "bacc_std": 0.05170091550810333} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 74, "C": 0.005994842503189409, "split": "test", "acc": 0.57, "acc_std": 0.041399995169081834, "f1": 0.50997150997151, "f1_std": 0.047403853839706134, "bacc": 0.515704584040747, "bacc_std": 0.04336731394880627} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 75, "C": 0.000774263682681127, "split": "test", "acc": 0.7, "acc_std": 0.03503421755940896, "f1": 0.6194824961948249, "f1_std": 0.052541815861741795, "bacc": 0.6256366723259762, "bacc_std": 0.041453863738906645} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 76, "C": 10000.0, "split": "test", "acc": 0.59, "acc_std": 0.04941585170772633, "f1": 0.5670995670995671, "f1_std": 0.05170009266778246, "bacc": 0.5674872665534805, "bacc_std": 0.051699684214958935} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 77, "C": 0.046415888336127774, "split": "test", "acc": 0.63, "acc_std": 0.04174254424445161, "f1": 0.5960257670051315, "f1_std": 0.04616666354345034, "bacc": 0.5946519524617997, "bacc_std": 0.04480035069729405} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 78, "C": 0.046415888336127774, "split": "test", "acc": 0.66, "acc_std": 0.042091785421861115, "f1": 0.6026180458158018, "f1_std": 0.05214492978441291, "bacc": 0.6035653650254669, "bacc_std": 0.04651454052340558} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 79, "C": 0.3593813663804626, "split": "test", "acc": 0.64, "acc_std": 0.044684243307904416, "f1": 0.609375, "f1_std": 0.048755038984962744, "bacc": 0.6078098471986417, "bacc_std": 0.047461823619630056} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 80, "C": 2.782559402207126, "split": "test", "acc": 0.62, "acc_std": 0.047434063709532626, "f1": 0.5924495924495925, "f1_std": 0.05092819443634123, "bacc": 0.5916808149405772, "bacc_std": 0.05040094562977497} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 81, "C": 0.3593813663804626, "split": "test", "acc": 0.65, "acc_std": 0.04385785676478047, "f1": 0.6266666666666667, "f1_std": 0.04709054730112285, "bacc": 0.6260611205432938, "bacc_std": 0.04707232773338551} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 82, "C": 0.3593813663804626, "split": "test", "acc": 0.69, "acc_std": 0.04308582597560361, "f1": 0.6615351020853806, "f1_std": 0.048007796001166815, "bacc": 0.6583191850594228, "bacc_std": 0.04680356953632647} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 83, "C": 0.3593813663804626, "split": "test", "acc": 0.62, "acc_std": 0.047337089052876924, "f1": 0.614448051948052, "f1_std": 0.04719755900155717, "bacc": 0.6273344651952462, "bacc_std": 0.04847590468197732} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 84, "C": 0.046415888336127774, "split": "test", "acc": 0.6, "acc_std": 0.048346462124958016, "f1": 0.5659722222222222, "f1_std": 0.0527037543585211, "bacc": 0.565365025466893, "bacc_std": 0.051624653093286454} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 85, "C": 0.046415888336127774, "split": "test", "acc": 0.65, "acc_std": 0.043023416879648224, "f1": 0.6178622120318812, "f1_std": 0.04709803004998445, "bacc": 0.615874363327674, "bacc_std": 0.04583444669790659} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 86, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.03989636073628771, "f1": 0.5143273433705683, "f1_std": 0.05040481614540427, "bacc": 0.5297113752122241, "bacc_std": 0.04239791583929846} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 87, "C": 0.3593813663804626, "split": "test", "acc": 0.6, "acc_std": 0.04523483171185674, "f1": 0.570999570999571, "f1_std": 0.048289188097424864, "bacc": 0.5704584040747029, "bacc_std": 0.047542607567654764} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 88, "C": 0.3593813663804626, "split": "test", "acc": 0.66, "acc_std": 0.04474948491323671, "f1": 0.6263736263736264, "f1_std": 0.050193967288065466, "bacc": 0.6239388794567062, "bacc_std": 0.048406001214312606} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 89, "C": 0.3593813663804626, "split": "test", "acc": 0.68, "acc_std": 0.04444693015271133, "f1": 0.6567996567996568, "f1_std": 0.048248148096335215, "bacc": 0.6553480475382003, "bacc_std": 0.04781878250591834} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 90, "C": 0.046415888336127774, "split": "test", "acc": 0.66, "acc_std": 0.04514660120097636, "f1": 0.6263736263736264, "f1_std": 0.04935998434051278, "bacc": 0.6239388794567062, "bacc_std": 0.04756142164928627} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 91, "C": 0.046415888336127774, "split": "test", "acc": 0.69, "acc_std": 0.042398957534354534, "f1": 0.6615351020853806, "f1_std": 0.04812366902549615, "bacc": 0.6583191850594228, "bacc_std": 0.04675017062792594} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 92, "C": 0.046415888336127774, "split": "test", "acc": 0.68, "acc_std": 0.04489810686432112, "f1": 0.6527777777777778, "f1_std": 0.04897361573235102, "bacc": 0.6502546689303905, "bacc_std": 0.0481765716550441} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 93, "C": 0.046415888336127774, "split": "test", "acc": 0.63, "acc_std": 0.0457630899306417, "f1": 0.6053333333333333, "f1_std": 0.04887603078735123, "bacc": 0.6048387096774194, "bacc_std": 0.048607985163417376} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 94, "C": 0.046415888336127774, "split": "test", "acc": 0.7, "acc_std": 0.040189929086774955, "f1": 0.66078697421981, "f1_std": 0.04690090000471416, "bacc": 0.6561969439728353, "bacc_std": 0.04382688836537066} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 95, "C": 0.046415888336127774, "split": "test", "acc": 0.65, "acc_std": 0.04068148964824174, "f1": 0.5872154735228211, "f1_std": 0.04970613482379556, "bacc": 0.5904074702886248, "bacc_std": 0.04390800770802501} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 96, "C": 0.046415888336127774, "split": "test", "acc": 0.66, "acc_std": 0.040979194721224084, "f1": 0.6155585707824514, "f1_std": 0.04809732388079008, "bacc": 0.6137521222410866, "bacc_std": 0.04453812079893039} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 97, "C": 0.046415888336127774, "split": "test", "acc": 0.72, "acc_std": 0.04177985639037071, "f1": 0.6923076923076923, "f1_std": 0.04668133518949705, "bacc": 0.6876061120543294, "bacc_std": 0.045410690227966385} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 98, "C": 0.3593813663804626, "split": "test", "acc": 0.61, "acc_std": 0.04667787055982739, "f1": 0.584, "f1_std": 0.050187863910995625, "bacc": 0.583616298811545, "bacc_std": 0.049821973117357414} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 99, "C": 0.3593813663804626, "split": "test", "acc": 0.65, "acc_std": 0.04616081021819266, "f1": 0.6224786970121885, "f1_std": 0.04959577241763764, "bacc": 0.6209677419354839, "bacc_std": 0.04865190010930696} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 100, "C": 0.046415888336127774, "split": "test", "acc": 0.65, "acc_std": 0.04267519654319122, "f1": 0.6072270227808326, "f1_std": 0.05037030706169902, "bacc": 0.6056876061120543, "bacc_std": 0.04713903996398583} +eval results (random splits): + +| model | repr | clf | dataset | split | n_trials | C | C_std | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|-----------:|-------:|--------:|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | reg | logistic | ppmi_dx | train | 100 | 204.23 | 1406.6 | 0.85601 | 0.091526 | 0.83696 | 0.10877 | 0.83071 | 0.10986 | +| flat_mae | reg | logistic | ppmi_dx | test | 100 | 204.23 | 1406.6 | 0.6384 | 0.044489 | 0.59869 | 0.046274 | 0.59939 | 0.043261 | + + +done! total time: 0:05:28 diff --git a/decoders/crossreg_reg4/pretrain/config.yaml b/decoders/crossreg_reg4/pretrain/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..51196583c6b0500ab6b6810d4a8c308de131b2c4 --- /dev/null +++ b/decoders/crossreg_reg4/pretrain/config.yaml @@ -0,0 +1,99 @@ +name: decoders/crossreg_reg4/pretrain +notes: decoder ablations crossreg_reg4 (model_kwargs.decoding=crossreg model_kwargs.reg_tokens=4) +output_dir: experiments/decoders/output/decoders/crossreg_reg4/pretrain +input_space: flat +patch_size: 16 +num_frames: 16 +t_patch_size: 4 +mask_ratio: 0.9 +pred_mask_ratio: null +masking: tube +masking_kwargs: {} +mask_patch_size: null +model: mae_vit_base +model_kwargs: + decoding: crossreg + pos_embed: sep + target_norm: null + t_pred_stride: 2 + no_decode_pos: true + mask_drop_scale: false + pred_edge_pad: 0 + class_token: false + reg_tokens: 4 + no_embed_class: true + head_init_scale: 0.0 + decoder_depth: 4 + drop_path_rate: 0.0 +datasets: + hcp-train: + type: wds + url: /data/fmri-datasets/pretrain/hcpya-all.${input_space}.wds/hcpya-all-${input_space}-{00000..01799}.tar + clipping: random + clipping_kwargs: + oversample: 4.0 + shuffle: true + buffer_size: 2000 + samples_per_epoch: 200000 + hcp-train-subset: + type: arrow + root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/validation + split_range: + - 0 + - 2000 + shuffle: false + hcp-val: + type: arrow + root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/test + split_range: + - 0 + - 2000 + shuffle: false +train_dataset: hcp-train +eval_datasets: +- hcp-train-subset +- hcp-val +clip_vmax: 3.0 +normalize: frame +tr_scale: null +crop_scale: null +crop_aspect: null +gray_jitter: null +gauss_sigma: null +num_workers: 16 +epochs: 100 +batch_size: 32 +accum_iter: 1 +base_lr: 0.001 +min_lr: 0.0 +warmup_epochs: 5 +weight_decay: 0.05 +betas: +- 0.9 +- 0.95 +clip_grad: 1.0 +amp: true +amp_dtype: float16 +ckpt: null +resume: true +auto_resume: true +start_epoch: 0 +max_checkpoints: 5 +checkpoint_period: 20 +plot_period: 5 +device: cuda +presend_cuda: false +seed: 7338 +debug: false +wandb: true +wandb_entity: null +wandb_project: fMRI-foundation-model +rank: 0 +world_size: 1 +gpu: 0 +distributed: true +dist_backend: nccl +in_chans: 1 +img_size: +- 224 +- 560 diff --git a/decoders/crossreg_reg4/pretrain/log.json b/decoders/crossreg_reg4/pretrain/log.json new file mode 100644 index 0000000000000000000000000000000000000000..e6a03295eaa360d3944d41240e316c9ac5d65052 --- /dev/null +++ b/decoders/crossreg_reg4/pretrain/log.json @@ -0,0 +1,100 @@ +{"epoch": 0, "train/lr": 1.2502400076802458e-05, "train/grad": 0.05388966559752822, "train/loss": 0.9935757109260559, "eval/hcp-train-subset/loss": 0.9918823097982714, "eval/hcp-val/loss": 0.9912039906747879} +{"epoch": 1, "train/lr": 3.750320010240327e-05, "train/grad": 0.18776392278313636, "train/loss": 0.9861712121772767, "eval/hcp-train-subset/loss": 0.9834637343883514, "eval/hcp-val/loss": 0.9798440990909454} +{"epoch": 2, "train/lr": 6.250400012800409e-05, "train/grad": 0.30221413145575576, "train/loss": 0.9741246353530884, "eval/hcp-train-subset/loss": 0.9695539580237481, "eval/hcp-val/loss": 0.9667147234562905} +{"epoch": 3, "train/lr": 8.75048001536049e-05, "train/grad": 0.2671103078988828, "train/loss": 0.9514333650779724, "eval/hcp-train-subset/loss": 0.9413565926013454, "eval/hcp-val/loss": 0.9367591392609381} +{"epoch": 4, "train/lr": 0.00011250559953918529, "train/grad": 0.15635117827276682, "train/loss": 0.9312010354042053, "eval/hcp-train-subset/loss": 0.926502654629369, "eval/hcp-val/loss": 0.921858633718183} +{"epoch": 5, "train/lr": 0.00012498860637884563, "train/grad": 0.11855490339318524, "train/loss": 0.915841375246048, "eval/hcp-train-subset/loss": 0.9154152370268299, "eval/hcp-val/loss": 0.9097616095696727} +{"epoch": 6, "train/lr": 0.0001249202705377922, "train/grad": 0.09847153393997693, "train/loss": 0.9057537861156464, "eval/hcp-train-subset/loss": 0.908178364076922, "eval/hcp-val/loss": 0.9030082975664446} +{"epoch": 7, "train/lr": 0.0001247836790473516, "train/grad": 0.0888078669262045, "train/loss": 0.8983097255802155, "eval/hcp-train-subset/loss": 0.9033375968856197, "eval/hcp-val/loss": 0.8993849687037929} +{"epoch": 8, "train/lr": 0.000124578981268311, "train/grad": 0.08163109598514384, "train/loss": 0.8955383694934845, "eval/hcp-train-subset/loss": 0.8997713135134789, "eval/hcp-val/loss": 0.8952526930839785} +{"epoch": 9, "train/lr": 0.00012430640103468907, "train/grad": 0.08338460912662575, "train/loss": 0.8898023924350739, "eval/hcp-train-subset/loss": 0.8990415671179371, "eval/hcp-val/loss": 0.8942973902148585} +{"epoch": 10, "train/lr": 0.00012396623640896796, "train/grad": 0.08031214027762146, "train/loss": 0.8877510054588318, "eval/hcp-train-subset/loss": 0.896944785310376, "eval/hcp-val/loss": 0.8924067520326183} +{"epoch": 11, "train/lr": 0.0001235588593561712, "train/grad": 0.07855777809438427, "train/loss": 0.8855886218070984, "eval/hcp-train-subset/loss": 0.8944891556616752, "eval/hcp-val/loss": 0.8905386703629647} +{"epoch": 12, "train/lr": 0.00012308471533712604, "train/grad": 0.07874574102687908, "train/loss": 0.8832494357013703, "eval/hcp-train-subset/loss": 0.893598884344101, "eval/hcp-val/loss": 0.8898018588942866} +{"epoch": 13, "train/lr": 0.00012254432282135565, "train/grad": 0.07641141902161679, "train/loss": 0.8819301776599884, "eval/hcp-train-subset/loss": 0.8926923428812334, "eval/hcp-val/loss": 0.8890491387536449} +{"epoch": 14, "train/lr": 0.00012193827272014171, "train/grad": 0.07884119403220108, "train/loss": 0.8793929813861847, "eval/hcp-train-subset/loss": 0.8911963249406507, "eval/hcp-val/loss": 0.8886694542823299} +{"epoch": 15, "train/lr": 0.00012126722774037197, "train/grad": 0.07931469725778806, "train/loss": 0.8776839946269989, "eval/hcp-train-subset/loss": 0.890329570539536, "eval/hcp-val/loss": 0.8879599628909942} +{"epoch": 16, "train/lr": 0.00012053192165988122, "train/grad": 0.07904943412344838, "train/loss": 0.8733891074085236, "eval/hcp-train-subset/loss": 0.8901596242381681, "eval/hcp-val/loss": 0.8868348127411257} +{"epoch": 17, "train/lr": 0.00011973315852507104, "train/grad": 0.0787380174528709, "train/loss": 0.8747914549541473, "eval/hcp-train-subset/loss": 0.889167804871836, "eval/hcp-val/loss": 0.885674762149011} +{"epoch": 18, "train/lr": 0.00011887181177170142, "train/grad": 0.0797597756150218, "train/loss": 0.8714536661434173, "eval/hcp-train-subset/loss": 0.8884700142568157, "eval/hcp-val/loss": 0.8856229147603435} +{"epoch": 19, "train/lr": 0.00011794882326980209, "train/grad": 0.08024585480086609, "train/loss": 0.8703926407241821, "eval/hcp-train-subset/loss": 0.8880525856248794, "eval/hcp-val/loss": 0.8854351207133262} +{"epoch": 20, "train/lr": 0.00011696520229374954, "train/grad": 0.08049558823637273, "train/loss": 0.8704579412555694, "eval/hcp-train-subset/loss": 0.8856064340760631, "eval/hcp-val/loss": 0.8852012445849757} +{"epoch": 21, "train/lr": 0.00011592202441863837, "train/grad": 0.08130936608331497, "train/loss": 0.8689427574825287, "eval/hcp-train-subset/loss": 0.8884705430076968, "eval/hcp-val/loss": 0.8851124509688346} +{"epoch": 22, "train/lr": 0.00011482043034415979, "train/grad": 0.08070971154345381, "train/loss": 0.8688149710845947, "eval/hcp-train-subset/loss": 0.8867073568605608, "eval/hcp-val/loss": 0.88424791539869} +{"epoch": 23, "train/lr": 0.00011366162464726024, "train/grad": 0.07992029491975412, "train/loss": 0.8673477858924866, "eval/hcp-train-subset/loss": 0.8871473900733455, "eval/hcp-val/loss": 0.8842398524284363} +{"epoch": 24, "train/lr": 0.0001124468744649569, "train/grad": 0.08049050134352663, "train/loss": 0.8646563814353943, "eval/hcp-train-subset/loss": 0.8867147420683215, "eval/hcp-val/loss": 0.8838533124616069} +{"epoch": 25, "train/lr": 0.0001111775081087387, "train/grad": 0.08275181970022212, "train/loss": 0.8642619590473175, "eval/hcp-train-subset/loss": 0.8843738350176042, "eval/hcp-val/loss": 0.8837287762472706} +{"epoch": 26, "train/lr": 0.0001098549136120796, "train/grad": 0.08121638548847827, "train/loss": 0.8627014552402497, "eval/hcp-train-subset/loss": 0.8830372835359266, "eval/hcp-val/loss": 0.8833793882400759} +{"epoch": 27, "train/lr": 0.00010848053721264312, "train/grad": 0.0831994849940459, "train/loss": 0.86147729678154, "eval/hcp-train-subset/loss": 0.8839605537153059, "eval/hcp-val/loss": 0.8840169118296716} +{"epoch": 28, "train/lr": 0.00010705588177084458, "train/grad": 0.08393993143338728, "train/loss": 0.8611019814491272, "eval/hcp-train-subset/loss": 0.8822055036021818, "eval/hcp-val/loss": 0.8832958975145894} +{"epoch": 29, "train/lr": 0.00010558250512649171, "train/grad": 0.0839181463800552, "train/loss": 0.8605893201637268, "eval/hcp-train-subset/loss": 0.8847854877671888, "eval/hcp-val/loss": 0.8832285990638118} +{"epoch": 30, "train/lr": 0.00010406201839531515, "train/grad": 0.083762054759699, "train/loss": 0.8601829997062683, "eval/hcp-train-subset/loss": 0.8813608577174525, "eval/hcp-val/loss": 0.8819547718571078} +{"epoch": 31, "train/lr": 0.00010249608420723018, "train/grad": 0.08220032042383708, "train/loss": 0.8597023143577576, "eval/hcp-train-subset/loss": 0.88273855563133, "eval/hcp-val/loss": 0.8823987303241607} +{"epoch": 32, "train/lr": 0.00010088641488828097, "train/grad": 0.08364820709159532, "train/loss": 0.859173323469162, "eval/hcp-train-subset/loss": 0.8775832691500264, "eval/hcp-val/loss": 0.8819949501945127} +{"epoch": 33, "train/lr": 9.923477058823526e-05, "train/grad": 0.08415693314579076, "train/loss": 0.8595771013355256, "eval/hcp-train-subset/loss": 0.8820955416848583, "eval/hcp-val/loss": 0.8825623248853991} +{"epoch": 34, "train/lr": 9.754295735588547e-05, "train/grad": 0.08501635064405512, "train/loss": 0.8572864503288269, "eval/hcp-train-subset/loss": 0.8829003630145904, "eval/hcp-val/loss": 0.8816867355377443} +{"epoch": 35, "train/lr": 9.581282516416285e-05, "train/grad": 0.08461375571328181, "train/loss": 0.8564209907150269, "eval/hcp-train-subset/loss": 0.8825957207910476, "eval/hcp-val/loss": 0.8820285479868611} +{"epoch": 36, "train/lr": 9.404626588721676e-05, "train/grad": 0.08607668014340715, "train/loss": 0.8553887875175477, "eval/hcp-train-subset/loss": 0.8803940050063594, "eval/hcp-val/loss": 0.8815261173632837} +{"epoch": 37, "train/lr": 9.224521123168153e-05, "train/grad": 0.08695210331768556, "train/loss": 0.8553948613929748, "eval/hcp-train-subset/loss": 0.8822617444299883, "eval/hcp-val/loss": 0.8821120290986953} +{"epoch": 38, "train/lr": 9.041163062437843e-05, "train/grad": 0.08765241784781752, "train/loss": 0.8543372651004791, "eval/hcp-train-subset/loss": 0.8791035913651989, "eval/hcp-val/loss": 0.8818459597326094} +{"epoch": 39, "train/lr": 8.85475290587822e-05, "train/grad": 0.08831381871843193, "train/loss": 0.8531440421581268, "eval/hcp-train-subset/loss": 0.8785338622908438, "eval/hcp-val/loss": 0.8811222228311724} +{"epoch": 40, "train/lr": 8.665494490258622e-05, "train/grad": 0.089874123234009, "train/loss": 0.8522351208209992, "eval/hcp-train-subset/loss": 0.8781626734041399, "eval/hcp-val/loss": 0.880158495518469} +{"epoch": 41, "train/lr": 8.473594766877838e-05, "train/grad": 0.08891261078648716, "train/loss": 0.8538391574287415, "eval/hcp-train-subset/loss": 0.8786630668947774, "eval/hcp-val/loss": 0.8796040252331765} +{"epoch": 42, "train/lr": 8.279263575265999e-05, "train/grad": 0.08969190610408782, "train/loss": 0.8530588736248016, "eval/hcp-train-subset/loss": 0.8798121031253568, "eval/hcp-val/loss": 0.8800749048109977} +{"epoch": 43, "train/lr": 8.082713413727944e-05, "train/grad": 0.08938937219659175, "train/loss": 0.8506306709384919, "eval/hcp-train-subset/loss": 0.8790678603033866, "eval/hcp-val/loss": 0.8803336918354034} +{"epoch": 44, "train/lr": 7.884159206979602e-05, "train/grad": 0.0918543223391223, "train/loss": 0.8513057193088531, "eval/hcp-train-subset/loss": 0.8777537643909454, "eval/hcp-val/loss": 0.880049838173774} +{"epoch": 45, "train/lr": 7.683818071130916e-05, "train/grad": 0.09307660117015605, "train/loss": 0.8492150576114654, "eval/hcp-train-subset/loss": 0.8768874156859613, "eval/hcp-val/loss": 0.8792254472932508} +{"epoch": 46, "train/lr": 7.481909076272522e-05, "train/grad": 0.0933197910046318, "train/loss": 0.8485946421623229, "eval/hcp-train-subset/loss": 0.877492997915514, "eval/hcp-val/loss": 0.8789699827471087} +{"epoch": 47, "train/lr": 7.278653006925963e-05, "train/grad": 0.09522632346458723, "train/loss": 0.8475550421333313, "eval/hcp-train-subset/loss": 0.8761326834078758, "eval/hcp-val/loss": 0.8791476170862874} +{"epoch": 48, "train/lr": 7.074272120618864e-05, "train/grad": 0.09651413129132226, "train/loss": 0.8489421479415894, "eval/hcp-train-subset/loss": 0.8773502947822693, "eval/hcp-val/loss": 0.8785673841353385} +{"epoch": 49, "train/lr": 6.868989904849677e-05, "train/grad": 0.09537665261430074, "train/loss": 0.8488782702445984, "eval/hcp-train-subset/loss": 0.8756491839885712, "eval/hcp-val/loss": 0.8793134189421131} +{"epoch": 50, "train/lr": 6.6630308327075e-05, "train/grad": 0.09510579861094758, "train/loss": 0.8505133409023284, "eval/hcp-train-subset/loss": 0.8741240126471366, "eval/hcp-val/loss": 0.8788717581379798} +{"epoch": 51, "train/lr": 6.456620117413798e-05, "train/grad": 0.0959533433612822, "train/loss": 0.8496167596912384, "eval/hcp-train-subset/loss": 0.8742856133368707, "eval/hcp-val/loss": 0.8803299713519311} +{"epoch": 52, "train/lr": 6.249983466055255e-05, "train/grad": 0.1005881389551436, "train/loss": 0.844548471250534, "eval/hcp-train-subset/loss": 0.8736840621117623, "eval/hcp-val/loss": 0.8778163511906901} +{"epoch": 53, "train/lr": 6.0433468327763305e-05, "train/grad": 0.09909832357427775, "train/loss": 0.8468215661430359, "eval/hcp-train-subset/loss": 0.8722073022396334, "eval/hcp-val/loss": 0.8783723269739458} +{"epoch": 54, "train/lr": 5.83693617170174e-05, "train/grad": 0.10095817572944028, "train/loss": 0.844535175743103, "eval/hcp-train-subset/loss": 0.8714097421015462, "eval/hcp-val/loss": 0.8781340641360129} +{"epoch": 55, "train/lr": 5.6309771898588165e-05, "train/grad": 0.101471410128323, "train/loss": 0.8449193961906433, "eval/hcp-train-subset/loss": 0.8740726363274359, "eval/hcp-val/loss": 0.8774754731885849} +{"epoch": 56, "train/lr": 5.4256951003704155e-05, "train/grad": 0.10451817848074528, "train/loss": 0.8427514645767212, "eval/hcp-train-subset/loss": 0.873344704989464, "eval/hcp-val/loss": 0.8788409444593615} +{"epoch": 57, "train/lr": 5.221314376187425e-05, "train/grad": 0.10348427424194509, "train/loss": 0.8461873410987854, "eval/hcp-train-subset/loss": 0.8706657530799988, "eval/hcp-val/loss": 0.8776342666918232} +{"epoch": 58, "train/lr": 5.018058504631059e-05, "train/grad": 0.10403339691202558, "train/loss": 0.8447160700511932, "eval/hcp-train-subset/loss": 0.873078606782421, "eval/hcp-val/loss": 0.8777099444020179} +{"epoch": 59, "train/lr": 4.816149743012713e-05, "train/grad": 0.1078550030027263, "train/loss": 0.8404567497062683, "eval/hcp-train-subset/loss": 0.8705499133756084, "eval/hcp-val/loss": 0.8777385286746486} +{"epoch": 60, "train/lr": 4.615808875598772e-05, "train/grad": 0.10893356800317879, "train/loss": 0.842001282196045, "eval/hcp-train-subset/loss": 0.8711612080374072, "eval/hcp-val/loss": 0.8773504034165414} +{"epoch": 61, "train/lr": 4.417254972186445e-05, "train/grad": 0.11203382954790844, "train/loss": 0.8374168596744538, "eval/hcp-train-subset/loss": 0.8695857726758526, "eval/hcp-val/loss": 0.8772082011545858} +{"epoch": 62, "train/lr": 4.220705148553925e-05, "train/grad": 0.11306201513241333, "train/loss": 0.8405242894172669, "eval/hcp-train-subset/loss": 0.8664985183746584, "eval/hcp-val/loss": 0.8768278658390045} +{"epoch": 63, "train/lr": 4.026374329047657e-05, "train/grad": 0.11340276214142692, "train/loss": 0.8418943878555298, "eval/hcp-train-subset/loss": 0.8684340446226059, "eval/hcp-val/loss": 0.8767359487472042} +{"epoch": 64, "train/lr": 3.834475011565652e-05, "train/grad": 0.112875842411928, "train/loss": 0.8403336109542847, "eval/hcp-train-subset/loss": 0.8672988626264757, "eval/hcp-val/loss": 0.8761636710936024} +{"epoch": 65, "train/lr": 3.6452170351940815e-05, "train/grad": 0.11204279001704423, "train/loss": 0.8449230549049378, "eval/hcp-train-subset/loss": 0.8682536809675155, "eval/hcp-val/loss": 0.8767260370715972} +{"epoch": 66, "train/lr": 3.458807350751516e-05, "train/grad": 0.11533431085446676, "train/loss": 0.840039342212677, "eval/hcp-train-subset/loss": 0.864080507909098, "eval/hcp-val/loss": 0.8759072038435167} +{"epoch": 67, "train/lr": 3.2754497944910164e-05, "train/grad": 0.1175480386806103, "train/loss": 0.839600899553299, "eval/hcp-train-subset/loss": 0.8650067390934113, "eval/hcp-val/loss": 0.8756496646711903} +{"epoch": 68, "train/lr": 3.0953448652083367e-05, "train/grad": 0.11945425089653232, "train/loss": 0.840064877576828, "eval/hcp-train-subset/loss": 0.8638346512471476, "eval/hcp-val/loss": 0.8755420167599955} +{"epoch": 69, "train/lr": 2.9186895049993948e-05, "train/grad": 0.11852931799235898, "train/loss": 0.8429887503910065, "eval/hcp-train-subset/loss": 0.8644648674995669, "eval/hcp-val/loss": 0.8757634105220917} +{"epoch": 70, "train/lr": 2.7456768839068717e-05, "train/grad": 0.12320731884387086, "train/loss": 0.8375632058238983, "eval/hcp-train-subset/loss": 0.8620265145455638, "eval/hcp-val/loss": 0.874571681022644} +{"epoch": 71, "train/lr": 2.5764961886919063e-05, "train/grad": 0.12245688379068498, "train/loss": 0.8416714514446259, "eval/hcp-train-subset/loss": 0.8615484170375332, "eval/hcp-val/loss": 0.8756860831091481} +{"epoch": 72, "train/lr": 2.411332415960724e-05, "train/grad": 0.1255601192752994, "train/loss": 0.8393576233196258, "eval/hcp-train-subset/loss": 0.8606117338903488, "eval/hcp-val/loss": 0.8748754416742632} +{"epoch": 73, "train/lr": 2.2503661698739544e-05, "train/grad": 0.12773055205462683, "train/loss": 0.8366428199005127, "eval/hcp-train-subset/loss": 0.8595591149022502, "eval/hcp-val/loss": 0.8745551061245703} +{"epoch": 74, "train/lr": 2.0937734646583902e-05, "train/grad": 0.12705932264902772, "train/loss": 0.8410284567260742, "eval/hcp-train-subset/loss": 0.8583232904634168, "eval/hcp-val/loss": 0.8742073437859935} +{"epoch": 75, "train/lr": 1.9417255321381202e-05, "train/grad": 0.1305888697180644, "train/loss": 0.8385935655593872, "eval/hcp-train-subset/loss": 0.8586738292248018, "eval/hcp-val/loss": 0.8749308951439396} +{"epoch": 76, "train/lr": 1.7943886344950134e-05, "train/grad": 0.12805539812706648, "train/loss": 0.8433659674263001, "eval/hcp-train-subset/loss": 0.8568202555179596, "eval/hcp-val/loss": 0.8742495140721721} +{"epoch": 77, "train/lr": 1.651923882463461e-05, "train/grad": 0.13255620315174899, "train/loss": 0.8395819239139557, "eval/hcp-train-subset/loss": 0.8580428342665395, "eval/hcp-val/loss": 0.8730256413259814} +{"epoch": 78, "train/lr": 1.5144870591581508e-05, "train/grad": 0.13418847582661922, "train/loss": 0.837537213087082, "eval/hcp-train-subset/loss": 0.8564821106772269, "eval/hcp-val/loss": 0.872887029763191} +{"epoch": 79, "train/lr": 1.3822284497275662e-05, "train/grad": 0.13582006290409496, "train/loss": 0.8368572948741912, "eval/hcp-train-subset/loss": 0.8558109268065421, "eval/hcp-val/loss": 0.8733975300865788} +{"epoch": 80, "train/lr": 1.2552926770192975e-05, "train/grad": 0.13376917493041895, "train/loss": 0.8413552492809295, "eval/hcp-train-subset/loss": 0.8543238659058848, "eval/hcp-val/loss": 0.8728770036851207} +{"epoch": 81, "train/lr": 1.1338185434371453e-05, "train/grad": 0.1378548362478554, "train/loss": 0.8394292843437194, "eval/hcp-train-subset/loss": 0.8532891994522463, "eval/hcp-val/loss": 0.8731448544609931} +{"epoch": 82, "train/lr": 1.0179388791627326e-05, "train/grad": 0.13984951945100763, "train/loss": 0.8377185324573517, "eval/hcp-train-subset/loss": 0.8522931039333344, "eval/hcp-val/loss": 0.8727977554644307} +{"epoch": 83, "train/lr": 9.07780396907607e-06, "train/grad": 0.14317589766510358, "train/loss": 0.8397254557228089, "eval/hcp-train-subset/loss": 0.852076385290392, "eval/hcp-val/loss": 0.8733980607601904} +{"epoch": 84, "train/lr": 8.034635533547902e-06, "train/grad": 0.14355633266403717, "train/loss": 0.8395180079650879, "eval/hcp-train-subset/loss": 0.851054641508287, "eval/hcp-val/loss": 0.8729187509705943} +{"epoch": 85, "train/lr": 7.051024174411275e-06, "train/grad": 0.1466684254065867, "train/loss": 0.8378952024841309, "eval/hcp-train-subset/loss": 0.8510541185255973, "eval/hcp-val/loss": 0.8725367486476898} +{"epoch": 86, "train/lr": 6.1280454562463606e-06, "train/grad": 0.1461602923457175, "train/loss": 0.8386540668582916, "eval/hcp-train-subset/loss": 0.849699116522266, "eval/hcp-val/loss": 0.8717685957108775} +{"epoch": 87, "train/lr": 5.266708642730326e-06, "train/grad": 0.14913765709219273, "train/loss": 0.836748091211319, "eval/hcp-train-subset/loss": 0.8486024766199051, "eval/hcp-val/loss": 0.8721940152106746} +{"epoch": 88, "train/lr": 4.467955593022733e-06, "train/grad": 0.14643663526473188, "train/loss": 0.8435041956424714, "eval/hcp-train-subset/loss": 0.8476996431427617, "eval/hcp-val/loss": 0.8716011451136682} +{"epoch": 89, "train/lr": 3.732659731856291e-06, "train/grad": 0.147415390033591, "train/loss": 0.8429521555519104, "eval/hcp-train-subset/loss": 0.8468830287456512, "eval/hcp-val/loss": 0.8715177630224535} +{"epoch": 90, "train/lr": 3.0616250944596583e-06, "train/grad": 0.1527493357262548, "train/loss": 0.8416925902271271, "eval/hcp-train-subset/loss": 0.8465732739817712, "eval/hcp-val/loss": 0.8711044951792686} +{"epoch": 91, "train/lr": 2.4555854473568305e-06, "train/grad": 0.15774631219371446, "train/loss": 0.840288868150711, "eval/hcp-train-subset/loss": 0.8445955870612976, "eval/hcp-val/loss": 0.8711625433737232} +{"epoch": 92, "train/lr": 1.915203486004091e-06, "train/grad": 0.15254576235446748, "train/loss": 0.8412628438663483, "eval/hcp-train-subset/loss": 0.8438848699292829, "eval/hcp-val/loss": 0.8716199023108329} +{"epoch": 93, "train/lr": 1.4410701101423926e-06, "train/grad": 0.15574044202992193, "train/loss": 0.8412127357769013, "eval/hcp-train-subset/loss": 0.8429902349748919, "eval/hcp-val/loss": 0.8713194612533816} +{"epoch": 94, "train/lr": 1.0337037776570775e-06, "train/grad": 0.1580589461468765, "train/loss": 0.8437691001605988, "eval/hcp-train-subset/loss": 0.8431036183910985, "eval/hcp-val/loss": 0.8707708014595893} +{"epoch": 95, "train/lr": 6.935499376518293e-07, "train/grad": 0.16365880801291152, "train/loss": 0.8401867779636383, "eval/hcp-train-subset/loss": 0.8428012180712915, "eval/hcp-val/loss": 0.8712327461088857} +{"epoch": 96, "train/lr": 4.209805433566085e-07, "train/grad": 0.162210466366721, "train/loss": 0.8421917659950257, "eval/hcp-train-subset/loss": 0.8427043634076272, "eval/hcp-val/loss": 0.8708486066710565} +{"epoch": 97, "train/lr": 2.1629364540224422e-07, "train/grad": 0.1631682006327409, "train/loss": 0.8435694891548157, "eval/hcp-train-subset/loss": 0.842402268801966, "eval/hcp-val/loss": 0.8701124297034356} +{"epoch": 98, "train/lr": 7.971306590647406e-08, "train/grad": 0.16400829010861287, "train/loss": 0.8443479567623139, "eval/hcp-train-subset/loss": 0.8422047101682232, "eval/hcp-val/loss": 0.8701451930307573} +{"epoch": 99, "train/lr": 1.1388153727718725e-08, "train/grad": 0.16493449564555063, "train/loss": 0.8441613182353973, "eval/hcp-train-subset/loss": 0.8424081936959298, "eval/hcp-val/loss": 0.870439624594104} diff --git a/decoders/crossreg_reg4/pretrain/log.txt b/decoders/crossreg_reg4/pretrain/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..2041827f5d37b1cf71a4458bf60f012f6bbfd68a --- /dev/null +++ b/decoders/crossreg_reg4/pretrain/log.txt @@ -0,0 +1,7774 @@ +pretraining fmri mae +start: 2026-01-16 00:34:19 +cwd: /admin/home/connor/fmri-fm +sha: f9ef1eebbc1a5292e462bf6c7741545659511885, status: has uncommitted changes, branch: dev/clane9 +config: +name: decoders/crossreg_reg4/pretrain +notes: decoder ablations crossreg_reg4 (model_kwargs.decoding=crossreg model_kwargs.reg_tokens=4) +output_dir: experiments/decoders/output/decoders/crossreg_reg4/pretrain +input_space: flat +patch_size: 16 +num_frames: 16 +t_patch_size: 4 +mask_ratio: 0.9 +pred_mask_ratio: null +masking: tube +masking_kwargs: {} +mask_patch_size: null +model: mae_vit_base +model_kwargs: + decoding: crossreg + pos_embed: sep + target_norm: null + t_pred_stride: 2 + no_decode_pos: true + mask_drop_scale: false + pred_edge_pad: 0 + class_token: false + reg_tokens: 4 + no_embed_class: true + head_init_scale: 0.0 + decoder_depth: 4 + drop_path_rate: 0.0 +datasets: + hcp-train: + type: wds + url: /data/fmri-datasets/pretrain/hcpya-all.${input_space}.wds/hcpya-all-${input_space}-{00000..01799}.tar + clipping: random + clipping_kwargs: + oversample: 4.0 + shuffle: true + buffer_size: 2000 + samples_per_epoch: 200000 + hcp-train-subset: + type: arrow + root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/validation + split_range: + - 0 + - 2000 + shuffle: false + hcp-val: + type: arrow + root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/test + split_range: + - 0 + - 2000 + shuffle: false +train_dataset: hcp-train +eval_datasets: +- hcp-train-subset +- hcp-val +clip_vmax: 3.0 +normalize: frame +tr_scale: null +crop_scale: null +crop_aspect: null +gray_jitter: null +gauss_sigma: null +num_workers: 16 +epochs: 100 +batch_size: 32 +accum_iter: 1 +base_lr: 0.001 +min_lr: 0.0 +warmup_epochs: 5 +weight_decay: 0.05 +betas: +- 0.9 +- 0.95 +clip_grad: 1.0 +amp: true +amp_dtype: float16 +ckpt: null +resume: true +auto_resume: true +start_epoch: 0 +max_checkpoints: 5 +checkpoint_period: 20 +plot_period: 5 +device: cuda +presend_cuda: false +seed: 7338 +debug: false +wandb: true +wandb_entity: null +wandb_project: fMRI-foundation-model +rank: 0 +world_size: 1 +gpu: 0 +distributed: true +dist_backend: nccl +in_chans: 1 +img_size: +- 224 +- 560 + +train transform: +Transform( +transform=Compose( + ToTensor() + TemporalCenterCrop(num_frames=16) + Normalize(mode='frame') + Clip(vmax=3.0) + FlatUnmask((224, 560)) +), +noise_transform=None +) +val transform: +Transform( +transform=Compose( + ToTensor() + TemporalCenterCrop(num_frames=16) + Normalize(mode='frame') + Clip(vmax=3.0) + FlatUnmask((224, 560)) +), +noise_transform=None +) +mask generator: +TubeMasking( + mask_ratio=0.9 + (patchify): Patchify2D((224, 560), (16, 16), in_chans=1) +) +loading dataset: hcp-train + +type: wds +url: /data/fmri-datasets/pretrain/hcpya-all.${input_space}.wds/hcpya-all-${input_space}-{00000..01799}.tar +clipping: random +clipping_kwargs: + oversample: 4.0 +shuffle: true +buffer_size: 2000 +samples_per_epoch: 200000 + +loading dataset: hcp-train-subset + +type: arrow +root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/validation +split_range: +- 0 +- 2000 +shuffle: false + +split indices: [899, 472, 767, 116, 1265, 1852, 300, 1335, 361, 1560] +loading dataset: hcp-val + +type: arrow +root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/test +split_range: +- 0 +- 2000 +shuffle: false + +split indices: [1075, 1189, 738, 1350, 965, 1964, 1367, 1183, 1619, 1407] +model: +MaskedAutoencoderViT( + decoding=crossreg, t_pred_stride=2, pred_edge_pad=0, no_decode_pos=True + (encoder): MaskedEncoder( + class_token=False, reg_tokens=4, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) + (pred_patchify): StridedPatchify3D((16, 224, 560), (2, 16, 16), in_chans=1, t_stride=2) + (decoder): MaskedDecoder( + cross_decode=True, class_token=False, no_embed_class=True + (pos_embed): SeparablePosEmbed(512, (4, 14, 35)) + (proj): Identity() + (blocks): ModuleList( + (0-3): 4 x Block( + (norm1): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=16 + (q): Linear(in_features=512, out_features=512, bias=True) + (k): Linear(in_features=768, out_features=512, bias=True) + (v): Linear(in_features=768, out_features=512, bias=True) + (proj): Linear(in_features=512, out_features=512, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=512, out_features=2048, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=2048, out_features=512, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (head): Linear(in_features=512, out_features=512, bias=True) + ) +) +num params: 100.4M +total batch size: 32 = 32 bs per gpu x 1 accum x 1 gpus +lr: 1.25e-04 = 1.00e-03 x 32 / 256 +full schedule: epochs = 100 (steps = 625000) +warmup: epochs = 5 (steps = 31250) +start training for 100 epochs +Train: [0] [ 0/6250] eta: 10:17:39 lr: 0.000000 grad: 0.0162 (0.0162) loss: 0.9960 (0.9960) time: 5.9295 data: 4.8241 max mem: 7455 +Train: [0] [ 100/6250] eta: 0:22:53 lr: 0.000000 grad: 0.0145 (0.0158) loss: 0.9962 (0.9960) time: 0.1685 data: 0.0772 max mem: 8255 +Train: [0] [ 200/6250] eta: 0:21:11 lr: 0.000001 grad: 0.0131 (0.0149) loss: 0.9962 (0.9959) time: 0.1938 data: 0.1087 max mem: 8255 +Train: [0] [ 300/6250] eta: 0:19:30 lr: 0.000001 grad: 0.0128 (0.0143) loss: 0.9961 (0.9959) time: 0.1410 data: 0.0358 max mem: 8255 +Train: [0] [ 400/6250] eta: 0:19:10 lr: 0.000002 grad: 0.0127 (0.0140) loss: 0.9958 (0.9959) time: 0.2012 data: 0.1181 max mem: 8255 +Train: [0] [ 500/6250] eta: 0:18:20 lr: 0.000002 grad: 0.0127 (0.0137) loss: 0.9957 (0.9959) time: 0.1551 data: 0.0668 max mem: 8255 +Train: [0] [ 600/6250] eta: 0:17:55 lr: 0.000002 grad: 0.0126 (0.0136) loss: 0.9956 (0.9959) time: 0.1870 data: 0.1024 max mem: 8255 +Train: [0] [ 700/6250] eta: 0:17:20 lr: 0.000003 grad: 0.0126 (0.0134) loss: 0.9954 (0.9958) time: 0.1653 data: 0.0687 max mem: 8255 +Train: [0] [ 800/6250] eta: 0:16:51 lr: 0.000003 grad: 0.0124 (0.0134) loss: 0.9955 (0.9958) time: 0.1475 data: 0.0594 max mem: 8255 +Train: [0] [ 900/6250] eta: 0:16:41 lr: 0.000004 grad: 0.0128 (0.0133) loss: 0.9953 (0.9958) time: 0.1671 data: 0.0789 max mem: 8255 +Train: [0] [1000/6250] eta: 0:16:17 lr: 0.000004 grad: 0.0126 (0.0132) loss: 0.9958 (0.9958) time: 0.1586 data: 0.0640 max mem: 8255 +Train: [0] [1100/6250] eta: 0:15:50 lr: 0.000004 grad: 0.0127 (0.0132) loss: 0.9962 (0.9958) time: 0.1789 data: 0.1091 max mem: 8255 +Train: [0] [1200/6250] eta: 0:15:19 lr: 0.000005 grad: 0.0128 (0.0132) loss: 0.9959 (0.9958) time: 0.1512 data: 0.0794 max mem: 8255 +Train: [0] [1300/6250] eta: 0:14:54 lr: 0.000005 grad: 0.0129 (0.0131) loss: 0.9957 (0.9958) time: 0.1690 data: 0.0943 max mem: 8255 +Train: [0] [1400/6250] eta: 0:14:29 lr: 0.000006 grad: 0.0129 (0.0131) loss: 0.9957 (0.9958) time: 0.1494 data: 0.0668 max mem: 8255 +Train: [0] [1500/6250] eta: 0:14:05 lr: 0.000006 grad: 0.0133 (0.0131) loss: 0.9958 (0.9958) time: 0.1481 data: 0.0748 max mem: 8255 +Train: [0] [1600/6250] eta: 0:13:42 lr: 0.000006 grad: 0.0142 (0.0132) loss: 0.9962 (0.9958) time: 0.1844 data: 0.1073 max mem: 8255 +Train: [0] [1700/6250] eta: 0:13:16 lr: 0.000007 grad: 0.0175 (0.0133) loss: 0.9956 (0.9958) time: 0.1582 data: 0.0862 max mem: 8255 +Train: [0] [1800/6250] eta: 0:12:53 lr: 0.000007 grad: 0.0195 (0.0136) loss: 0.9956 (0.9958) time: 0.1325 data: 0.0504 max mem: 8255 +Train: [0] [1900/6250] eta: 0:12:32 lr: 0.000008 grad: 0.0226 (0.0140) loss: 0.9955 (0.9958) time: 0.1709 data: 0.0902 max mem: 8255 +Train: [0] [2000/6250] eta: 0:12:10 lr: 0.000008 grad: 0.0223 (0.0144) loss: 0.9957 (0.9958) time: 0.1488 data: 0.0779 max mem: 8255 +Train: [0] [2100/6250] eta: 0:11:48 lr: 0.000008 grad: 0.0272 (0.0151) loss: 0.9952 (0.9958) time: 0.1345 data: 0.0563 max mem: 8255 +Train: [0] [2200/6250] eta: 0:11:30 lr: 0.000009 grad: 0.0287 (0.0159) loss: 0.9953 (0.9957) time: 0.1713 data: 0.0882 max mem: 8255 +Train: [0] [2300/6250] eta: 0:11:11 lr: 0.000009 grad: 0.0409 (0.0169) loss: 0.9943 (0.9957) time: 0.1636 data: 0.0804 max mem: 8255 +Train: [0] [2400/6250] eta: 0:10:50 lr: 0.000010 grad: 0.0403 (0.0179) loss: 0.9946 (0.9957) time: 0.1200 data: 0.0449 max mem: 8255 +Train: [0] [2500/6250] eta: 0:10:32 lr: 0.000010 grad: 0.0398 (0.0189) loss: 0.9945 (0.9956) time: 0.1705 data: 0.0687 max mem: 8255 +Train: [0] [2600/6250] eta: 0:10:13 lr: 0.000010 grad: 0.0423 (0.0198) loss: 0.9944 (0.9956) time: 0.1585 data: 0.0672 max mem: 8255 +Train: [0] [2700/6250] eta: 0:09:55 lr: 0.000011 grad: 0.0473 (0.0207) loss: 0.9946 (0.9955) time: 0.1459 data: 0.0795 max mem: 8255 +Train: [0] [2800/6250] eta: 0:09:36 lr: 0.000011 grad: 0.0305 (0.0214) loss: 0.9947 (0.9955) time: 0.1373 data: 0.0604 max mem: 8255 +Train: [0] [2900/6250] eta: 0:09:18 lr: 0.000012 grad: 0.0375 (0.0221) loss: 0.9944 (0.9955) time: 0.1820 data: 0.0914 max mem: 8255 +Train: [0] [3000/6250] eta: 0:09:00 lr: 0.000012 grad: 0.0441 (0.0230) loss: 0.9937 (0.9954) time: 0.1344 data: 0.0588 max mem: 8255 +Train: [0] [3100/6250] eta: 0:08:41 lr: 0.000012 grad: 0.0685 (0.0242) loss: 0.9937 (0.9954) time: 0.1278 data: 0.0562 max mem: 8255 +Train: [0] [3200/6250] eta: 0:08:24 lr: 0.000013 grad: 0.0525 (0.0253) loss: 0.9933 (0.9953) time: 0.1605 data: 0.0795 max mem: 8255 +Train: [0] [3300/6250] eta: 0:08:07 lr: 0.000013 grad: 0.0490 (0.0263) loss: 0.9936 (0.9953) time: 0.1301 data: 0.0525 max mem: 8255 +Train: [0] [3400/6250] eta: 0:07:50 lr: 0.000014 grad: 0.0763 (0.0277) loss: 0.9936 (0.9952) time: 0.1800 data: 0.0988 max mem: 8255 +Train: [0] [3500/6250] eta: 0:07:32 lr: 0.000014 grad: 0.0733 (0.0291) loss: 0.9931 (0.9952) time: 0.1736 data: 0.0910 max mem: 8255 +Train: [0] [3600/6250] eta: 0:07:14 lr: 0.000014 grad: 0.0502 (0.0304) loss: 0.9936 (0.9951) time: 0.1565 data: 0.0852 max mem: 8255 +Train: [0] [3700/6250] eta: 0:06:56 lr: 0.000015 grad: 0.0661 (0.0317) loss: 0.9930 (0.9951) time: 0.1670 data: 0.1010 max mem: 8255 +Train: [0] [3800/6250] eta: 0:06:39 lr: 0.000015 grad: 0.0940 (0.0328) loss: 0.9931 (0.9950) time: 0.1108 data: 0.0218 max mem: 8255 +Train: [0] [3900/6250] eta: 0:06:22 lr: 0.000016 grad: 0.0657 (0.0339) loss: 0.9922 (0.9949) time: 0.1375 data: 0.0633 max mem: 8255 +Train: [0] [4000/6250] eta: 0:06:06 lr: 0.000016 grad: 0.0861 (0.0351) loss: 0.9920 (0.9949) time: 0.1474 data: 0.0827 max mem: 8255 +Train: [0] [4100/6250] eta: 0:05:49 lr: 0.000016 grad: 0.0701 (0.0361) loss: 0.9922 (0.9948) time: 0.2152 data: 0.1458 max mem: 8255 +Train: [0] [4200/6250] eta: 0:05:32 lr: 0.000017 grad: 0.0712 (0.0372) loss: 0.9930 (0.9948) time: 0.1734 data: 0.0929 max mem: 8255 +Train: [0] [4300/6250] eta: 0:05:15 lr: 0.000017 grad: 0.0549 (0.0381) loss: 0.9925 (0.9947) time: 0.1628 data: 0.0899 max mem: 8255 +Train: [0] [4400/6250] eta: 0:04:58 lr: 0.000018 grad: 0.0581 (0.0390) loss: 0.9927 (0.9947) time: 0.1274 data: 0.0421 max mem: 8255 +Train: [0] [4500/6250] eta: 0:04:42 lr: 0.000018 grad: 0.0621 (0.0398) loss: 0.9924 (0.9946) time: 0.1877 data: 0.1142 max mem: 8255 +Train: [0] [4600/6250] eta: 0:04:25 lr: 0.000018 grad: 0.0780 (0.0408) loss: 0.9917 (0.9946) time: 0.1766 data: 0.0846 max mem: 8255 +Train: [0] [4700/6250] eta: 0:04:09 lr: 0.000019 grad: 0.0651 (0.0416) loss: 0.9920 (0.9945) time: 0.1721 data: 0.0993 max mem: 8255 +Train: [0] [4800/6250] eta: 0:03:52 lr: 0.000019 grad: 0.0706 (0.0424) loss: 0.9915 (0.9945) time: 0.1602 data: 0.0832 max mem: 8255 +Train: [0] [4900/6250] eta: 0:03:36 lr: 0.000020 grad: 0.0703 (0.0431) loss: 0.9921 (0.9944) time: 0.1337 data: 0.0695 max mem: 8255 +Train: [0] [5000/6250] eta: 0:03:20 lr: 0.000020 grad: 0.0782 (0.0439) loss: 0.9908 (0.9943) time: 0.1542 data: 0.0710 max mem: 8255 +Train: [0] [5100/6250] eta: 0:03:04 lr: 0.000020 grad: 0.0676 (0.0447) loss: 0.9921 (0.9943) time: 0.1258 data: 0.0516 max mem: 8255 +Train: [0] [5200/6250] eta: 0:02:48 lr: 0.000021 grad: 0.0716 (0.0456) loss: 0.9914 (0.9942) time: 0.1405 data: 0.0656 max mem: 8255 +Train: [0] [5300/6250] eta: 0:02:32 lr: 0.000021 grad: 0.0755 (0.0464) loss: 0.9923 (0.9942) time: 0.1399 data: 0.0706 max mem: 8255 +Train: [0] [5400/6250] eta: 0:02:15 lr: 0.000022 grad: 0.1044 (0.0473) loss: 0.9907 (0.9941) time: 0.1555 data: 0.0795 max mem: 8255 +Train: [0] [5500/6250] eta: 0:01:59 lr: 0.000022 grad: 0.0772 (0.0480) loss: 0.9915 (0.9941) time: 0.1519 data: 0.0780 max mem: 8255 +Train: [0] [5600/6250] eta: 0:01:43 lr: 0.000022 grad: 0.0829 (0.0488) loss: 0.9922 (0.9940) time: 0.1420 data: 0.0703 max mem: 8255 +Train: [0] [5700/6250] eta: 0:01:27 lr: 0.000023 grad: 0.0906 (0.0497) loss: 0.9903 (0.9939) time: 0.1367 data: 0.0653 max mem: 8255 +Train: [0] [5800/6250] eta: 0:01:11 lr: 0.000023 grad: 0.0970 (0.0504) loss: 0.9910 (0.9939) time: 0.1534 data: 0.0707 max mem: 8255 +Train: [0] [5900/6250] eta: 0:00:55 lr: 0.000024 grad: 0.0841 (0.0512) loss: 0.9913 (0.9938) time: 0.1454 data: 0.0660 max mem: 8255 +Train: [0] [6000/6250] eta: 0:00:39 lr: 0.000024 grad: 0.1041 (0.0519) loss: 0.9904 (0.9937) time: 0.1252 data: 0.0522 max mem: 8255 +Train: [0] [6100/6250] eta: 0:00:23 lr: 0.000024 grad: 0.0666 (0.0527) loss: 0.9899 (0.9937) time: 0.1474 data: 0.0608 max mem: 8255 +Train: [0] [6200/6250] eta: 0:00:07 lr: 0.000025 grad: 0.0879 (0.0534) loss: 0.9882 (0.9936) time: 0.1322 data: 0.0419 max mem: 8255 +Train: [0] [6249/6250] eta: 0:00:00 lr: 0.000025 grad: 0.1046 (0.0539) loss: 0.9896 (0.9936) time: 0.1457 data: 0.0719 max mem: 8255 +Train: [0] Total time: 0:16:34 (0.1591 s / it) +Averaged stats: lr: 0.000025 grad: 0.1046 (0.0539) loss: 0.9896 (0.9936) +Eval (hcp-train-subset): [0] [ 0/62] eta: 0:05:57 loss: 0.9927 (0.9927) time: 5.7717 data: 5.6792 max mem: 8255 +Eval (hcp-train-subset): [0] [61/62] eta: 0:00:00 loss: 0.9920 (0.9919) time: 0.0975 data: 0.0756 max mem: 8255 +Eval (hcp-train-subset): [0] Total time: 0:00:14 (0.2344 s / it) +Averaged stats (hcp-train-subset): loss: 0.9920 (0.9919) +Eval (hcp-val): [0] [ 0/62] eta: 0:04:12 loss: 0.9891 (0.9891) time: 4.0668 data: 3.9995 max mem: 8255 +Eval (hcp-val): [0] [61/62] eta: 0:00:00 loss: 0.9907 (0.9912) time: 0.1162 data: 0.0941 max mem: 8255 +Eval (hcp-val): [0] Total time: 0:00:13 (0.2132 s / it) +Averaged stats (hcp-val): loss: 0.9907 (0.9912) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +Train: [1] [ 0/6250] eta: 8:06:33 lr: 0.000025 grad: 0.0674 (0.0674) loss: 0.9915 (0.9915) time: 4.6710 data: 4.5091 max mem: 8255 +Train: [1] [ 100/6250] eta: 0:24:35 lr: 0.000025 grad: 0.0819 (0.1088) loss: 0.9919 (0.9904) time: 0.1369 data: 0.0607 max mem: 8255 +Train: [1] [ 200/6250] eta: 0:20:34 lr: 0.000026 grad: 0.1155 (0.1093) loss: 0.9884 (0.9899) time: 0.1656 data: 0.0944 max mem: 8255 +Train: [1] [ 300/6250] eta: 0:18:43 lr: 0.000026 grad: 0.0740 (0.1084) loss: 0.9899 (0.9894) time: 0.1250 data: 0.0478 max mem: 8255 +Train: [1] [ 400/6250] eta: 0:17:39 lr: 0.000027 grad: 0.0888 (0.1073) loss: 0.9892 (0.9895) time: 0.1681 data: 0.0755 max mem: 8255 +Train: [1] [ 500/6250] eta: 0:16:59 lr: 0.000027 grad: 0.1025 (0.1072) loss: 0.9879 (0.9894) time: 0.1547 data: 0.0665 max mem: 8255 +Train: [1] [ 600/6250] eta: 0:16:36 lr: 0.000027 grad: 0.0860 (0.1064) loss: 0.9897 (0.9895) time: 0.1836 data: 0.0932 max mem: 8255 +Train: [1] [ 700/6250] eta: 0:16:11 lr: 0.000028 grad: 0.0927 (0.1053) loss: 0.9895 (0.9895) time: 0.1712 data: 0.0831 max mem: 8255 +Train: [1] [ 800/6250] eta: 0:15:52 lr: 0.000028 grad: 0.0938 (0.1038) loss: 0.9894 (0.9896) time: 0.1978 data: 0.0942 max mem: 8255 +Train: [1] [ 900/6250] eta: 0:15:52 lr: 0.000029 grad: 0.0834 (0.1024) loss: 0.9904 (0.9897) time: 0.1716 data: 0.0878 max mem: 8255 +Train: [1] [1000/6250] eta: 0:15:28 lr: 0.000029 grad: 0.1011 (0.1020) loss: 0.9901 (0.9897) time: 0.1729 data: 0.1091 max mem: 8255 +Train: [1] [1100/6250] eta: 0:15:10 lr: 0.000029 grad: 0.0879 (0.1020) loss: 0.9908 (0.9897) time: 0.2314 data: 0.1464 max mem: 8255 +Train: [1] [1200/6250] eta: 0:14:47 lr: 0.000030 grad: 0.0813 (0.1013) loss: 0.9909 (0.9897) time: 0.2085 data: 0.1244 max mem: 8255 +Train: [1] [1300/6250] eta: 0:14:24 lr: 0.000030 grad: 0.0860 (0.1010) loss: 0.9890 (0.9897) time: 0.1790 data: 0.0896 max mem: 8255 +Train: [1] [1400/6250] eta: 0:14:03 lr: 0.000031 grad: 0.0804 (0.1006) loss: 0.9914 (0.9897) time: 0.1661 data: 0.0936 max mem: 8255 +Train: [1] [1500/6250] eta: 0:13:41 lr: 0.000031 grad: 0.0905 (0.1011) loss: 0.9889 (0.9897) time: 0.1431 data: 0.0608 max mem: 8255 +Train: [1] [1600/6250] eta: 0:13:21 lr: 0.000031 grad: 0.0874 (0.1013) loss: 0.9895 (0.9896) time: 0.1755 data: 0.0999 max mem: 8255 +Train: [1] [1700/6250] eta: 0:13:03 lr: 0.000032 grad: 0.1105 (0.1014) loss: 0.9862 (0.9896) time: 0.1423 data: 0.0575 max mem: 8255 +Train: [1] [1800/6250] eta: 0:12:42 lr: 0.000032 grad: 0.0842 (0.1015) loss: 0.9894 (0.9895) time: 0.1544 data: 0.0798 max mem: 8255 +Train: [1] [1900/6250] eta: 0:12:23 lr: 0.000033 grad: 0.0897 (0.1019) loss: 0.9889 (0.9895) time: 0.1374 data: 0.0596 max mem: 8255 +Train: [1] [2000/6250] eta: 0:12:04 lr: 0.000033 grad: 0.0916 (0.1022) loss: 0.9883 (0.9895) time: 0.2067 data: 0.1342 max mem: 8255 +Train: [1] [2100/6250] eta: 0:11:42 lr: 0.000033 grad: 0.0985 (0.1026) loss: 0.9901 (0.9895) time: 0.1625 data: 0.0711 max mem: 8255 +Train: [1] [2200/6250] eta: 0:11:23 lr: 0.000034 grad: 0.1204 (0.1034) loss: 0.9865 (0.9894) time: 0.1385 data: 0.0528 max mem: 8255 +Train: [1] [2300/6250] eta: 0:11:04 lr: 0.000034 grad: 0.1010 (0.1042) loss: 0.9873 (0.9893) time: 0.1206 data: 0.0480 max mem: 8255 +Train: [1] [2400/6250] eta: 0:10:44 lr: 0.000035 grad: 0.1129 (0.1054) loss: 0.9887 (0.9893) time: 0.1490 data: 0.0736 max mem: 8255 +Train: [1] [2500/6250] eta: 0:10:26 lr: 0.000035 grad: 0.1175 (0.1067) loss: 0.9878 (0.9892) time: 0.1246 data: 0.0363 max mem: 8255 +Train: [1] [2600/6250] eta: 0:10:06 lr: 0.000035 grad: 0.0899 (0.1081) loss: 0.9890 (0.9892) time: 0.1555 data: 0.0657 max mem: 8255 +Train: [1] [2700/6250] eta: 0:09:50 lr: 0.000036 grad: 0.1406 (0.1095) loss: 0.9888 (0.9891) time: 0.1600 data: 0.0863 max mem: 8255 +Train: [1] [2800/6250] eta: 0:09:35 lr: 0.000036 grad: 0.1151 (0.1103) loss: 0.9868 (0.9891) time: 0.1610 data: 0.0796 max mem: 8255 +Train: [1] [2900/6250] eta: 0:09:18 lr: 0.000037 grad: 0.1101 (0.1117) loss: 0.9882 (0.9890) time: 0.1525 data: 0.0714 max mem: 8255 +Train: [1] [3000/6250] eta: 0:09:00 lr: 0.000037 grad: 0.1982 (0.1146) loss: 0.9860 (0.9890) time: 0.1355 data: 0.0456 max mem: 8255 +Train: [1] [3100/6250] eta: 0:08:43 lr: 0.000037 grad: 0.1794 (0.1171) loss: 0.9872 (0.9889) time: 0.1737 data: 0.0879 max mem: 8255 +Train: [1] [3200/6250] eta: 0:08:26 lr: 0.000038 grad: 0.1992 (0.1196) loss: 0.9864 (0.9888) time: 0.1696 data: 0.0897 max mem: 8255 +Train: [1] [3300/6250] eta: 0:08:09 lr: 0.000038 grad: 0.2055 (0.1227) loss: 0.9855 (0.9887) time: 0.2071 data: 0.1371 max mem: 8255 +Train: [1] [3400/6250] eta: 0:07:53 lr: 0.000039 grad: 0.1573 (0.1256) loss: 0.9866 (0.9886) time: 0.2285 data: 0.1444 max mem: 8255 +Train: [1] [3500/6250] eta: 0:07:36 lr: 0.000039 grad: 0.1571 (0.1291) loss: 0.9840 (0.9885) time: 0.1824 data: 0.1023 max mem: 8255 +Train: [1] [3600/6250] eta: 0:07:19 lr: 0.000039 grad: 0.2336 (0.1322) loss: 0.9841 (0.9884) time: 0.1007 data: 0.0002 max mem: 8255 +Train: [1] [3700/6250] eta: 0:07:03 lr: 0.000040 grad: 0.3236 (0.1370) loss: 0.9856 (0.9883) time: 0.2086 data: 0.1361 max mem: 8255 +Train: [1] [3800/6250] eta: 0:06:45 lr: 0.000040 grad: 0.3423 (0.1399) loss: 0.9859 (0.9882) time: 0.1561 data: 0.0732 max mem: 8255 +Train: [1] [3900/6250] eta: 0:06:28 lr: 0.000041 grad: 0.2784 (0.1422) loss: 0.9865 (0.9881) time: 0.1595 data: 0.0912 max mem: 8255 +Train: [1] [4000/6250] eta: 0:06:11 lr: 0.000041 grad: 0.2041 (0.1450) loss: 0.9820 (0.9880) time: 0.1365 data: 0.0626 max mem: 8255 +Train: [1] [4100/6250] eta: 0:05:54 lr: 0.000041 grad: 0.1712 (0.1475) loss: 0.9849 (0.9880) time: 0.1557 data: 0.0713 max mem: 8255 +Train: [1] [4200/6250] eta: 0:05:38 lr: 0.000042 grad: 0.2157 (0.1509) loss: 0.9839 (0.9879) time: 0.2053 data: 0.1256 max mem: 8255 +Train: [1] [4300/6250] eta: 0:05:23 lr: 0.000042 grad: 0.2105 (0.1534) loss: 0.9861 (0.9878) time: 0.1940 data: 0.1139 max mem: 8255 +Train: [1] [4400/6250] eta: 0:05:07 lr: 0.000043 grad: 0.1565 (0.1557) loss: 0.9858 (0.9877) time: 0.1480 data: 0.0475 max mem: 8255 +Train: [1] [4500/6250] eta: 0:04:50 lr: 0.000043 grad: 0.1738 (0.1575) loss: 0.9840 (0.9876) time: 0.2003 data: 0.1210 max mem: 8255 +Train: [1] [4600/6250] eta: 0:04:34 lr: 0.000043 grad: 0.1670 (0.1596) loss: 0.9844 (0.9875) time: 0.1431 data: 0.0598 max mem: 8255 +Train: [1] [4700/6250] eta: 0:04:17 lr: 0.000044 grad: 0.2299 (0.1620) loss: 0.9822 (0.9874) time: 0.2160 data: 0.1308 max mem: 8255 +Train: [1] [4800/6250] eta: 0:04:01 lr: 0.000044 grad: 0.2605 (0.1644) loss: 0.9845 (0.9873) time: 0.1670 data: 0.0802 max mem: 8255 +Train: [1] [4900/6250] eta: 0:03:44 lr: 0.000045 grad: 0.2608 (0.1674) loss: 0.9848 (0.9873) time: 0.1899 data: 0.1171 max mem: 8255 +Train: [1] [5000/6250] eta: 0:03:27 lr: 0.000045 grad: 0.2949 (0.1698) loss: 0.9827 (0.9872) time: 0.2543 data: 0.1700 max mem: 8255 +Train: [1] [5100/6250] eta: 0:03:11 lr: 0.000045 grad: 0.2191 (0.1721) loss: 0.9826 (0.9871) time: 0.1858 data: 0.1135 max mem: 8255 +Train: [1] [5200/6250] eta: 0:02:54 lr: 0.000046 grad: 0.2705 (0.1745) loss: 0.9828 (0.9870) time: 0.1854 data: 0.1128 max mem: 8255 +Train: [1] [5300/6250] eta: 0:02:38 lr: 0.000046 grad: 0.2413 (0.1761) loss: 0.9843 (0.9869) time: 0.1788 data: 0.0999 max mem: 8255 +Train: [1] [5400/6250] eta: 0:02:21 lr: 0.000047 grad: 0.1699 (0.1774) loss: 0.9814 (0.9868) time: 0.1730 data: 0.0781 max mem: 8255 +Train: [1] [5500/6250] eta: 0:02:05 lr: 0.000047 grad: 0.1760 (0.1787) loss: 0.9828 (0.9867) time: 0.1190 data: 0.0382 max mem: 8255 +Train: [1] [5600/6250] eta: 0:01:48 lr: 0.000047 grad: 0.1934 (0.1800) loss: 0.9816 (0.9867) time: 0.1255 data: 0.0358 max mem: 8255 +Train: [1] [5700/6250] eta: 0:01:31 lr: 0.000048 grad: 0.2239 (0.1806) loss: 0.9814 (0.9866) time: 0.1659 data: 0.0773 max mem: 8255 +Train: [1] [5800/6250] eta: 0:01:15 lr: 0.000048 grad: 0.2985 (0.1822) loss: 0.9833 (0.9865) time: 0.1600 data: 0.0676 max mem: 8255 +Train: [1] [5900/6250] eta: 0:00:58 lr: 0.000049 grad: 0.2198 (0.1834) loss: 0.9815 (0.9864) time: 0.1804 data: 0.0955 max mem: 8255 +Train: [1] [6000/6250] eta: 0:00:41 lr: 0.000049 grad: 0.2433 (0.1850) loss: 0.9828 (0.9864) time: 0.1752 data: 0.0958 max mem: 8255 +Train: [1] [6100/6250] eta: 0:00:25 lr: 0.000049 grad: 0.2255 (0.1862) loss: 0.9811 (0.9863) time: 0.1838 data: 0.1015 max mem: 8255 +Train: [1] [6200/6250] eta: 0:00:08 lr: 0.000050 grad: 0.2210 (0.1870) loss: 0.9790 (0.9862) time: 0.1381 data: 0.0492 max mem: 8255 +Train: [1] [6249/6250] eta: 0:00:00 lr: 0.000050 grad: 0.2909 (0.1878) loss: 0.9799 (0.9862) time: 0.1897 data: 0.1053 max mem: 8255 +Train: [1] Total time: 0:17:30 (0.1681 s / it) +Averaged stats: lr: 0.000050 grad: 0.2909 (0.1878) loss: 0.9799 (0.9862) +Eval (hcp-train-subset): [1] [ 0/62] eta: 0:03:09 loss: 0.9830 (0.9830) time: 3.0609 data: 2.9979 max mem: 8255 +Eval (hcp-train-subset): [1] [61/62] eta: 0:00:00 loss: 0.9835 (0.9835) time: 0.1441 data: 0.1224 max mem: 8255 +Eval (hcp-train-subset): [1] Total time: 0:00:13 (0.2135 s / it) +Averaged stats (hcp-train-subset): loss: 0.9835 (0.9835) +Eval (hcp-val): [1] [ 0/62] eta: 0:03:12 loss: 0.9750 (0.9750) time: 3.1040 data: 3.0388 max mem: 8255 +Eval (hcp-val): [1] [61/62] eta: 0:00:00 loss: 0.9805 (0.9798) time: 0.1312 data: 0.1086 max mem: 8255 +Eval (hcp-val): [1] Total time: 0:00:14 (0.2329 s / it) +Averaged stats (hcp-val): loss: 0.9805 (0.9798) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +Train: [2] [ 0/6250] eta: 7:47:51 lr: 0.000050 grad: 0.2756 (0.2756) loss: 0.9839 (0.9839) time: 4.4915 data: 4.2033 max mem: 8255 +Train: [2] [ 100/6250] eta: 0:23:12 lr: 0.000050 grad: 0.1747 (0.3145) loss: 0.9809 (0.9819) time: 0.2054 data: 0.1193 max mem: 8255 +Train: [2] [ 200/6250] eta: 0:21:16 lr: 0.000051 grad: 0.2013 (0.3059) loss: 0.9800 (0.9815) time: 0.2139 data: 0.1518 max mem: 8255 +Train: [2] [ 300/6250] eta: 0:19:36 lr: 0.000051 grad: 0.2533 (0.2924) loss: 0.9826 (0.9813) time: 0.1640 data: 0.0889 max mem: 8255 +Train: [2] [ 400/6250] eta: 0:18:20 lr: 0.000052 grad: 0.1906 (0.2814) loss: 0.9828 (0.9811) time: 0.1420 data: 0.0718 max mem: 8255 +Train: [2] [ 500/6250] eta: 0:17:54 lr: 0.000052 grad: 0.2218 (0.2746) loss: 0.9800 (0.9808) time: 0.1883 data: 0.1158 max mem: 8255 +Train: [2] [ 600/6250] eta: 0:17:10 lr: 0.000052 grad: 0.2980 (0.2774) loss: 0.9801 (0.9807) time: 0.1515 data: 0.0578 max mem: 8255 +Train: [2] [ 700/6250] eta: 0:16:40 lr: 0.000053 grad: 0.2416 (0.2755) loss: 0.9781 (0.9805) time: 0.1480 data: 0.0595 max mem: 8255 +Train: [2] [ 800/6250] eta: 0:16:43 lr: 0.000053 grad: 0.2165 (0.2736) loss: 0.9788 (0.9804) time: 0.2196 data: 0.1020 max mem: 8255 +Train: [2] [ 900/6250] eta: 0:16:27 lr: 0.000054 grad: 0.2499 (0.2754) loss: 0.9808 (0.9802) time: 0.1434 data: 0.0605 max mem: 8255 +Train: [2] [1000/6250] eta: 0:15:59 lr: 0.000054 grad: 0.2624 (0.2754) loss: 0.9816 (0.9802) time: 0.1563 data: 0.0862 max mem: 8255 +Train: [2] [1100/6250] eta: 0:15:36 lr: 0.000054 grad: 0.2790 (0.2768) loss: 0.9790 (0.9801) time: 0.1807 data: 0.1000 max mem: 8255 +Train: [2] [1200/6250] eta: 0:15:20 lr: 0.000055 grad: 0.2581 (0.2767) loss: 0.9815 (0.9800) time: 0.1920 data: 0.0888 max mem: 8255 +Train: [2] [1300/6250] eta: 0:14:59 lr: 0.000055 grad: 0.2701 (0.2766) loss: 0.9797 (0.9799) time: 0.2124 data: 0.1441 max mem: 8255 +Train: [2] [1400/6250] eta: 0:14:33 lr: 0.000056 grad: 0.2575 (0.2776) loss: 0.9741 (0.9798) time: 0.1616 data: 0.0733 max mem: 8255 +Train: [2] [1500/6250] eta: 0:14:10 lr: 0.000056 grad: 0.2664 (0.2766) loss: 0.9781 (0.9796) time: 0.1468 data: 0.0651 max mem: 8255 +Train: [2] [1600/6250] eta: 0:13:47 lr: 0.000056 grad: 0.2170 (0.2773) loss: 0.9760 (0.9794) time: 0.1721 data: 0.1017 max mem: 8255 +Train: [2] [1700/6250] eta: 0:13:25 lr: 0.000057 grad: 0.2556 (0.2777) loss: 0.9804 (0.9793) time: 0.1624 data: 0.0817 max mem: 8255 +Train: [2] [1800/6250] eta: 0:13:06 lr: 0.000057 grad: 0.2508 (0.2769) loss: 0.9786 (0.9792) time: 0.1707 data: 0.0857 max mem: 8255 +Train: [2] [1900/6250] eta: 0:12:45 lr: 0.000058 grad: 0.2307 (0.2764) loss: 0.9736 (0.9791) time: 0.1443 data: 0.0600 max mem: 8255 +Train: [2] [2000/6250] eta: 0:12:27 lr: 0.000058 grad: 0.2343 (0.2760) loss: 0.9773 (0.9790) time: 0.1601 data: 0.0836 max mem: 8255 +Train: [2] [2100/6250] eta: 0:12:08 lr: 0.000058 grad: 0.1633 (0.2748) loss: 0.9768 (0.9789) time: 0.2094 data: 0.1318 max mem: 8255 +Train: [2] [2200/6250] eta: 0:11:50 lr: 0.000059 grad: 0.2479 (0.2745) loss: 0.9756 (0.9788) time: 0.2005 data: 0.1149 max mem: 8255 +Train: [2] [2300/6250] eta: 0:11:30 lr: 0.000059 grad: 0.2330 (0.2745) loss: 0.9774 (0.9787) time: 0.1559 data: 0.0774 max mem: 8255 +Train: [2] [2400/6250] eta: 0:11:14 lr: 0.000060 grad: 0.2505 (0.2748) loss: 0.9777 (0.9786) time: 0.2533 data: 0.1582 max mem: 8255 +Train: [2] [2500/6250] eta: 0:10:55 lr: 0.000060 grad: 0.2646 (0.2747) loss: 0.9766 (0.9786) time: 0.1397 data: 0.0591 max mem: 8255 +Train: [2] [2600/6250] eta: 0:10:37 lr: 0.000060 grad: 0.1977 (0.2737) loss: 0.9741 (0.9785) time: 0.2049 data: 0.1179 max mem: 8255 +Train: [2] [2700/6250] eta: 0:10:20 lr: 0.000061 grad: 0.2479 (0.2737) loss: 0.9756 (0.9784) time: 0.1538 data: 0.0706 max mem: 8255 +Train: [2] [2800/6250] eta: 0:10:04 lr: 0.000061 grad: 0.2604 (0.2740) loss: 0.9735 (0.9782) time: 0.2380 data: 0.1530 max mem: 8255 +Train: [2] [2900/6250] eta: 0:09:46 lr: 0.000062 grad: 0.2276 (0.2739) loss: 0.9727 (0.9780) time: 0.1772 data: 0.0921 max mem: 8255 +Train: [2] [3000/6250] eta: 0:09:29 lr: 0.000062 grad: 0.2961 (0.2744) loss: 0.9744 (0.9779) time: 0.1594 data: 0.0695 max mem: 8255 +Train: [2] [3100/6250] eta: 0:09:11 lr: 0.000062 grad: 0.2523 (0.2754) loss: 0.9762 (0.9778) time: 0.1721 data: 0.0926 max mem: 8255 +Train: [2] [3200/6250] eta: 0:08:53 lr: 0.000063 grad: 0.2302 (0.2760) loss: 0.9748 (0.9777) time: 0.1557 data: 0.0719 max mem: 8255 +Train: [2] [3300/6250] eta: 0:08:36 lr: 0.000063 grad: 0.2241 (0.2768) loss: 0.9722 (0.9776) time: 0.1780 data: 0.0927 max mem: 8255 +Train: [2] [3400/6250] eta: 0:08:18 lr: 0.000064 grad: 0.2410 (0.2775) loss: 0.9751 (0.9775) time: 0.1830 data: 0.1085 max mem: 8255 +Train: [2] [3500/6250] eta: 0:08:01 lr: 0.000064 grad: 0.2800 (0.2780) loss: 0.9734 (0.9774) time: 0.1737 data: 0.0934 max mem: 8255 +Train: [2] [3600/6250] eta: 0:07:44 lr: 0.000064 grad: 0.2356 (0.2784) loss: 0.9724 (0.9773) time: 0.1299 data: 0.0373 max mem: 8255 +Train: [2] [3700/6250] eta: 0:07:26 lr: 0.000065 grad: 0.2822 (0.2787) loss: 0.9726 (0.9772) time: 0.1470 data: 0.0662 max mem: 8255 +Train: [2] [3800/6250] eta: 0:07:09 lr: 0.000065 grad: 0.2356 (0.2791) loss: 0.9714 (0.9771) time: 0.2220 data: 0.1584 max mem: 8255 +Train: [2] [3900/6250] eta: 0:06:51 lr: 0.000066 grad: 0.3401 (0.2811) loss: 0.9746 (0.9770) time: 0.1827 data: 0.0926 max mem: 8255 +Train: [2] [4000/6250] eta: 0:06:34 lr: 0.000066 grad: 0.2865 (0.2822) loss: 0.9722 (0.9769) time: 0.1139 data: 0.0006 max mem: 8255 +Train: [2] [4100/6250] eta: 0:06:16 lr: 0.000066 grad: 0.3578 (0.2830) loss: 0.9716 (0.9768) time: 0.1637 data: 0.0646 max mem: 8255 +Train: [2] [4200/6250] eta: 0:05:59 lr: 0.000067 grad: 0.3356 (0.2843) loss: 0.9712 (0.9766) time: 0.2300 data: 0.1521 max mem: 8255 +Train: [2] [4300/6250] eta: 0:05:41 lr: 0.000067 grad: 0.3350 (0.2857) loss: 0.9724 (0.9765) time: 0.1598 data: 0.0849 max mem: 8255 +Train: [2] [4400/6250] eta: 0:05:23 lr: 0.000068 grad: 0.3195 (0.2865) loss: 0.9709 (0.9764) time: 0.1540 data: 0.0766 max mem: 8255 +Train: [2] [4500/6250] eta: 0:05:06 lr: 0.000068 grad: 0.3160 (0.2875) loss: 0.9732 (0.9763) time: 0.1626 data: 0.0716 max mem: 8255 +Train: [2] [4600/6250] eta: 0:04:48 lr: 0.000068 grad: 0.2999 (0.2884) loss: 0.9688 (0.9762) time: 0.1515 data: 0.0782 max mem: 8255 +Train: [2] [4700/6250] eta: 0:04:30 lr: 0.000069 grad: 0.2918 (0.2893) loss: 0.9696 (0.9761) time: 0.1486 data: 0.0736 max mem: 8255 +Train: [2] [4800/6250] eta: 0:04:13 lr: 0.000069 grad: 0.3486 (0.2907) loss: 0.9684 (0.9759) time: 0.1597 data: 0.0806 max mem: 8255 +Train: [2] [4900/6250] eta: 0:03:55 lr: 0.000070 grad: 0.3828 (0.2921) loss: 0.9705 (0.9758) time: 0.1664 data: 0.0861 max mem: 8255 +Train: [2] [5000/6250] eta: 0:03:37 lr: 0.000070 grad: 0.3149 (0.2932) loss: 0.9685 (0.9757) time: 0.1443 data: 0.0664 max mem: 8255 +Train: [2] [5100/6250] eta: 0:03:20 lr: 0.000070 grad: 0.3563 (0.2942) loss: 0.9704 (0.9756) time: 0.1627 data: 0.0802 max mem: 8255 +Train: [2] [5200/6250] eta: 0:03:02 lr: 0.000071 grad: 0.3409 (0.2953) loss: 0.9671 (0.9755) time: 0.1569 data: 0.0791 max mem: 8255 +Train: [2] [5300/6250] eta: 0:02:46 lr: 0.000071 grad: 0.3081 (0.2964) loss: 0.9700 (0.9754) time: 0.2741 data: 0.1979 max mem: 8255 +Train: [2] [5400/6250] eta: 0:02:28 lr: 0.000072 grad: 0.3539 (0.2972) loss: 0.9695 (0.9753) time: 0.1430 data: 0.0449 max mem: 8255 +Train: [2] [5500/6250] eta: 0:02:10 lr: 0.000072 grad: 0.3247 (0.2980) loss: 0.9680 (0.9752) time: 0.1716 data: 0.0845 max mem: 8255 +Train: [2] [5600/6250] eta: 0:01:53 lr: 0.000072 grad: 0.2843 (0.2985) loss: 0.9696 (0.9750) time: 0.2098 data: 0.1286 max mem: 8255 +Train: [2] [5700/6250] eta: 0:01:36 lr: 0.000073 grad: 0.3122 (0.2991) loss: 0.9632 (0.9749) time: 0.1725 data: 0.0739 max mem: 8255 +Train: [2] [5800/6250] eta: 0:01:18 lr: 0.000073 grad: 0.3096 (0.2997) loss: 0.9677 (0.9748) time: 0.2028 data: 0.1343 max mem: 8255 +Train: [2] [5900/6250] eta: 0:01:01 lr: 0.000074 grad: 0.3325 (0.3005) loss: 0.9664 (0.9746) time: 0.1479 data: 0.0694 max mem: 8255 +Train: [2] [6000/6250] eta: 0:00:43 lr: 0.000074 grad: 0.2985 (0.3011) loss: 0.9696 (0.9745) time: 0.1604 data: 0.0737 max mem: 8255 +Train: [2] [6100/6250] eta: 0:00:26 lr: 0.000074 grad: 0.3190 (0.3016) loss: 0.9667 (0.9743) time: 0.1757 data: 0.0859 max mem: 8255 +Train: [2] [6200/6250] eta: 0:00:08 lr: 0.000075 grad: 0.2985 (0.3021) loss: 0.9663 (0.9742) time: 0.1864 data: 0.1198 max mem: 8255 +Train: [2] [6249/6250] eta: 0:00:00 lr: 0.000075 grad: 0.3068 (0.3022) loss: 0.9641 (0.9741) time: 0.1616 data: 0.0802 max mem: 8255 +Train: [2] Total time: 0:18:15 (0.1753 s / it) +Averaged stats: lr: 0.000075 grad: 0.3068 (0.3022) loss: 0.9641 (0.9741) +Eval (hcp-train-subset): [2] [ 0/62] eta: 0:04:15 loss: 0.9700 (0.9700) time: 4.1166 data: 4.0907 max mem: 8255 +Eval (hcp-train-subset): [2] [61/62] eta: 0:00:00 loss: 0.9708 (0.9696) time: 0.1511 data: 0.1287 max mem: 8255 +Eval (hcp-train-subset): [2] Total time: 0:00:13 (0.2208 s / it) +Averaged stats (hcp-train-subset): loss: 0.9708 (0.9696) +Eval (hcp-val): [2] [ 0/62] eta: 0:05:10 loss: 0.9648 (0.9648) time: 5.0039 data: 4.9786 max mem: 8255 +Eval (hcp-val): [2] [61/62] eta: 0:00:00 loss: 0.9674 (0.9667) time: 0.1312 data: 0.1100 max mem: 8255 +Eval (hcp-val): [2] Total time: 0:00:14 (0.2335 s / it) +Averaged stats (hcp-val): loss: 0.9674 (0.9667) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +Train: [3] [ 0/6250] eta: 8:51:51 lr: 0.000075 grad: 0.2508 (0.2508) loss: 0.9825 (0.9825) time: 5.1058 data: 4.8362 max mem: 8255 +Train: [3] [ 100/6250] eta: 0:23:02 lr: 0.000075 grad: 0.3267 (0.3242) loss: 0.9711 (0.9698) time: 0.1761 data: 0.0960 max mem: 8255 +Train: [3] [ 200/6250] eta: 0:20:09 lr: 0.000076 grad: 0.2885 (0.3350) loss: 0.9656 (0.9663) time: 0.1753 data: 0.0877 max mem: 8255 +Train: [3] [ 300/6250] eta: 0:18:50 lr: 0.000076 grad: 0.2985 (0.3375) loss: 0.9605 (0.9653) time: 0.1692 data: 0.0830 max mem: 8255 +Train: [3] [ 400/6250] eta: 0:18:14 lr: 0.000077 grad: 0.3166 (0.3394) loss: 0.9637 (0.9645) time: 0.1785 data: 0.0905 max mem: 8255 +Train: [3] [ 500/6250] eta: 0:17:52 lr: 0.000077 grad: 0.2537 (0.3395) loss: 0.9602 (0.9641) time: 0.2147 data: 0.1166 max mem: 8255 +Train: [3] [ 600/6250] eta: 0:18:09 lr: 0.000077 grad: 0.2828 (0.3399) loss: 0.9640 (0.9639) time: 0.2614 data: 0.1562 max mem: 8255 +Train: [3] [ 700/6250] eta: 0:17:58 lr: 0.000078 grad: 0.3158 (0.3408) loss: 0.9577 (0.9634) time: 0.2051 data: 0.1041 max mem: 8255 +Train: [3] [ 800/6250] eta: 0:17:38 lr: 0.000078 grad: 0.2673 (0.3382) loss: 0.9586 (0.9630) time: 0.2346 data: 0.1414 max mem: 8255 +Train: [3] [ 900/6250] eta: 0:17:13 lr: 0.000079 grad: 0.2800 (0.3372) loss: 0.9593 (0.9625) time: 0.2065 data: 0.1004 max mem: 8255 +Train: [3] [1000/6250] eta: 0:16:42 lr: 0.000079 grad: 0.2855 (0.3350) loss: 0.9615 (0.9622) time: 0.1735 data: 0.0772 max mem: 8255 +Train: [3] [1100/6250] eta: 0:16:24 lr: 0.000079 grad: 0.2853 (0.3328) loss: 0.9560 (0.9619) time: 0.2202 data: 0.1396 max mem: 8255 +Train: [3] [1200/6250] eta: 0:16:04 lr: 0.000080 grad: 0.2821 (0.3315) loss: 0.9590 (0.9617) time: 0.1642 data: 0.0865 max mem: 8255 +Train: [3] [1300/6250] eta: 0:15:38 lr: 0.000080 grad: 0.4132 (0.3310) loss: 0.9608 (0.9615) time: 0.1760 data: 0.0924 max mem: 8255 +Train: [3] [1400/6250] eta: 0:15:34 lr: 0.000081 grad: 0.2559 (0.3272) loss: 0.9577 (0.9613) time: 0.2518 data: 0.1271 max mem: 8255 +Train: [3] [1500/6250] eta: 0:15:05 lr: 0.000081 grad: 0.2265 (0.3246) loss: 0.9558 (0.9611) time: 0.1809 data: 0.1008 max mem: 8255 +Train: [3] [1600/6250] eta: 0:14:42 lr: 0.000081 grad: 0.2224 (0.3229) loss: 0.9584 (0.9610) time: 0.1418 data: 0.0340 max mem: 8255 +Train: [3] [1700/6250] eta: 0:14:21 lr: 0.000082 grad: 0.2714 (0.3229) loss: 0.9549 (0.9607) time: 0.1516 data: 0.0663 max mem: 8255 +Train: [3] [1800/6250] eta: 0:13:59 lr: 0.000082 grad: 0.3015 (0.3215) loss: 0.9575 (0.9605) time: 0.1926 data: 0.0426 max mem: 8255 +Train: [3] [1900/6250] eta: 0:13:40 lr: 0.000083 grad: 0.3081 (0.3206) loss: 0.9558 (0.9603) time: 0.1838 data: 0.1022 max mem: 8255 +Train: [3] [2000/6250] eta: 0:13:23 lr: 0.000083 grad: 0.2710 (0.3197) loss: 0.9556 (0.9601) time: 0.2609 data: 0.1873 max mem: 8255 +Train: [3] [2100/6250] eta: 0:13:01 lr: 0.000083 grad: 0.2870 (0.3182) loss: 0.9579 (0.9599) time: 0.1771 data: 0.0992 max mem: 8255 +Train: [3] [2200/6250] eta: 0:12:37 lr: 0.000084 grad: 0.2350 (0.3167) loss: 0.9546 (0.9598) time: 0.1923 data: 0.0981 max mem: 8255 +Train: [3] [2300/6250] eta: 0:12:17 lr: 0.000084 grad: 0.2567 (0.3153) loss: 0.9559 (0.9595) time: 0.2186 data: 0.1454 max mem: 8255 +Train: [3] [2400/6250] eta: 0:11:57 lr: 0.000085 grad: 0.2730 (0.3140) loss: 0.9547 (0.9593) time: 0.1805 data: 0.1034 max mem: 8255 +Train: [3] [2500/6250] eta: 0:11:41 lr: 0.000085 grad: 0.2629 (0.3125) loss: 0.9569 (0.9592) time: 0.2866 data: 0.1975 max mem: 8255 +Train: [3] [2600/6250] eta: 0:11:23 lr: 0.000085 grad: 0.2531 (0.3114) loss: 0.9547 (0.9590) time: 0.2380 data: 0.1427 max mem: 8255 +Train: [3] [2700/6250] eta: 0:11:01 lr: 0.000086 grad: 0.2530 (0.3104) loss: 0.9524 (0.9588) time: 0.1677 data: 0.0842 max mem: 8255 +Train: [3] [2800/6250] eta: 0:10:40 lr: 0.000086 grad: 0.2847 (0.3098) loss: 0.9512 (0.9586) time: 0.1549 data: 0.0807 max mem: 8255 +Train: [3] [2900/6250] eta: 0:10:23 lr: 0.000087 grad: 0.2162 (0.3081) loss: 0.9539 (0.9584) time: 0.2045 data: 0.1228 max mem: 8255 +Train: [3] [3000/6250] eta: 0:10:03 lr: 0.000087 grad: 0.2073 (0.3069) loss: 0.9531 (0.9582) time: 0.2024 data: 0.1104 max mem: 8255 +Train: [3] [3100/6250] eta: 0:09:43 lr: 0.000087 grad: 0.2209 (0.3056) loss: 0.9532 (0.9580) time: 0.1583 data: 0.0670 max mem: 8255 +Train: [3] [3200/6250] eta: 0:09:23 lr: 0.000088 grad: 0.2330 (0.3050) loss: 0.9485 (0.9578) time: 0.1480 data: 0.0511 max mem: 8255 +Train: [3] [3300/6250] eta: 0:09:02 lr: 0.000088 grad: 0.2260 (0.3034) loss: 0.9526 (0.9576) time: 0.1506 data: 0.0619 max mem: 8255 +Train: [3] [3400/6250] eta: 0:08:43 lr: 0.000089 grad: 0.2396 (0.3025) loss: 0.9477 (0.9574) time: 0.1628 data: 0.0618 max mem: 8255 +Train: [3] [3500/6250] eta: 0:08:26 lr: 0.000089 grad: 0.2917 (0.3016) loss: 0.9491 (0.9572) time: 0.1782 data: 0.0985 max mem: 8255 +Train: [3] [3600/6250] eta: 0:08:06 lr: 0.000089 grad: 0.2126 (0.3000) loss: 0.9478 (0.9570) time: 0.1579 data: 0.0775 max mem: 8255 +Train: [3] [3700/6250] eta: 0:07:47 lr: 0.000090 grad: 0.2007 (0.2985) loss: 0.9510 (0.9568) time: 0.1732 data: 0.1073 max mem: 8255 +Train: [3] [3800/6250] eta: 0:07:28 lr: 0.000090 grad: 0.2104 (0.2972) loss: 0.9492 (0.9566) time: 0.1472 data: 0.0531 max mem: 8255 +Train: [3] [3900/6250] eta: 0:07:09 lr: 0.000091 grad: 0.2040 (0.2956) loss: 0.9506 (0.9564) time: 0.1843 data: 0.0982 max mem: 8255 +Train: [3] [4000/6250] eta: 0:06:50 lr: 0.000091 grad: 0.2010 (0.2944) loss: 0.9502 (0.9563) time: 0.1723 data: 0.0729 max mem: 8255 +Train: [3] [4100/6250] eta: 0:06:31 lr: 0.000091 grad: 0.1887 (0.2932) loss: 0.9479 (0.9561) time: 0.1515 data: 0.0582 max mem: 8255 +Train: [3] [4200/6250] eta: 0:06:13 lr: 0.000092 grad: 0.2420 (0.2920) loss: 0.9479 (0.9559) time: 0.1669 data: 0.0546 max mem: 8255 +Train: [3] [4300/6250] eta: 0:05:56 lr: 0.000092 grad: 0.1887 (0.2905) loss: 0.9461 (0.9557) time: 0.1895 data: 0.0822 max mem: 8255 +Train: [3] [4400/6250] eta: 0:05:36 lr: 0.000093 grad: 0.2550 (0.2895) loss: 0.9490 (0.9555) time: 0.1433 data: 0.0627 max mem: 8255 +Train: [3] [4500/6250] eta: 0:05:17 lr: 0.000093 grad: 0.2129 (0.2880) loss: 0.9444 (0.9553) time: 0.1293 data: 0.0373 max mem: 8255 +Train: [3] [4600/6250] eta: 0:04:59 lr: 0.000093 grad: 0.2955 (0.2870) loss: 0.9472 (0.9551) time: 0.1542 data: 0.0756 max mem: 8255 +Train: [3] [4700/6250] eta: 0:04:40 lr: 0.000094 grad: 0.2010 (0.2855) loss: 0.9414 (0.9549) time: 0.1402 data: 0.0660 max mem: 8255 +Train: [3] [4800/6250] eta: 0:04:22 lr: 0.000094 grad: 0.1929 (0.2842) loss: 0.9474 (0.9547) time: 0.1244 data: 0.0353 max mem: 8255 +Train: [3] [4900/6250] eta: 0:04:05 lr: 0.000095 grad: 0.2109 (0.2830) loss: 0.9443 (0.9545) time: 0.2617 data: 0.1863 max mem: 8255 +Train: [3] [5000/6250] eta: 0:03:46 lr: 0.000095 grad: 0.1695 (0.2815) loss: 0.9439 (0.9542) time: 0.1529 data: 0.0741 max mem: 8255 +Train: [3] [5100/6250] eta: 0:03:27 lr: 0.000095 grad: 0.2113 (0.2804) loss: 0.9422 (0.9540) time: 0.1708 data: 0.1011 max mem: 8255 +Train: [3] [5200/6250] eta: 0:03:09 lr: 0.000096 grad: 0.1976 (0.2794) loss: 0.9416 (0.9538) time: 0.1675 data: 0.0807 max mem: 8255 +Train: [3] [5300/6250] eta: 0:02:51 lr: 0.000096 grad: 0.1974 (0.2779) loss: 0.9406 (0.9536) time: 0.2417 data: 0.1574 max mem: 8255 +Train: [3] [5400/6250] eta: 0:02:33 lr: 0.000097 grad: 0.1998 (0.2766) loss: 0.9418 (0.9534) time: 0.1322 data: 0.0376 max mem: 8255 +Train: [3] [5500/6250] eta: 0:02:14 lr: 0.000097 grad: 0.1712 (0.2755) loss: 0.9396 (0.9532) time: 0.1572 data: 0.0832 max mem: 8255 +Train: [3] [5600/6250] eta: 0:01:56 lr: 0.000097 grad: 0.2081 (0.2742) loss: 0.9401 (0.9529) time: 0.1647 data: 0.0953 max mem: 8255 +Train: [3] [5700/6250] eta: 0:01:38 lr: 0.000098 grad: 0.1942 (0.2732) loss: 0.9367 (0.9527) time: 0.1855 data: 0.0958 max mem: 8255 +Train: [3] [5800/6250] eta: 0:01:20 lr: 0.000098 grad: 0.1956 (0.2720) loss: 0.9374 (0.9525) time: 0.1726 data: 0.0967 max mem: 8255 +Train: [3] [5900/6250] eta: 0:01:02 lr: 0.000099 grad: 0.2057 (0.2710) loss: 0.9390 (0.9522) time: 0.1770 data: 0.1041 max mem: 8255 +Train: [3] [6000/6250] eta: 0:00:44 lr: 0.000099 grad: 0.1956 (0.2699) loss: 0.9374 (0.9520) time: 0.1616 data: 0.0970 max mem: 8255 +Train: [3] [6100/6250] eta: 0:00:26 lr: 0.000099 grad: 0.1901 (0.2687) loss: 0.9379 (0.9518) time: 0.1630 data: 0.0948 max mem: 8255 +Train: [3] [6200/6250] eta: 0:00:08 lr: 0.000100 grad: 0.1913 (0.2679) loss: 0.9373 (0.9515) time: 0.1769 data: 0.0895 max mem: 8255 +Train: [3] [6249/6250] eta: 0:00:00 lr: 0.000100 grad: 0.1607 (0.2671) loss: 0.9385 (0.9514) time: 0.1374 data: 0.0673 max mem: 8255 +Train: [3] Total time: 0:18:45 (0.1801 s / it) +Averaged stats: lr: 0.000100 grad: 0.1607 (0.2671) loss: 0.9385 (0.9514) +Eval (hcp-train-subset): [3] [ 0/62] eta: 0:03:02 loss: 0.9442 (0.9442) time: 2.9469 data: 2.8746 max mem: 8255 +Eval (hcp-train-subset): [3] [61/62] eta: 0:00:00 loss: 0.9440 (0.9414) time: 0.1417 data: 0.1208 max mem: 8255 +Eval (hcp-train-subset): [3] Total time: 0:00:13 (0.2155 s / it) +Averaged stats (hcp-train-subset): loss: 0.9440 (0.9414) +Eval (hcp-val): [3] [ 0/62] eta: 0:03:18 loss: 0.9389 (0.9389) time: 3.2046 data: 3.1325 max mem: 8255 +Eval (hcp-val): [3] [61/62] eta: 0:00:00 loss: 0.9378 (0.9368) time: 0.1456 data: 0.1230 max mem: 8255 +Eval (hcp-val): [3] Total time: 0:00:14 (0.2323 s / it) +Averaged stats (hcp-val): loss: 0.9378 (0.9368) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +Train: [4] [ 0/6250] eta: 9:50:08 lr: 0.000100 grad: 0.2634 (0.2634) loss: 0.9306 (0.9306) time: 5.6653 data: 5.3930 max mem: 8255 +Train: [4] [ 100/6250] eta: 0:29:41 lr: 0.000100 grad: 0.1720 (0.2061) loss: 0.9429 (0.9440) time: 0.2477 data: 0.1320 max mem: 8255 +Train: [4] [ 200/6250] eta: 0:27:12 lr: 0.000101 grad: 0.1725 (0.1956) loss: 0.9362 (0.9428) time: 0.1981 data: 0.0853 max mem: 8255 +Train: [4] [ 300/6250] eta: 0:25:12 lr: 0.000101 grad: 0.1547 (0.1884) loss: 0.9393 (0.9418) time: 0.1330 data: 0.0160 max mem: 8255 +Train: [4] [ 400/6250] eta: 0:23:33 lr: 0.000102 grad: 0.1718 (0.1871) loss: 0.9364 (0.9408) time: 0.1768 data: 0.0830 max mem: 8255 +Train: [4] [ 500/6250] eta: 0:22:22 lr: 0.000102 grad: 0.1709 (0.1832) loss: 0.9404 (0.9405) time: 0.1894 data: 0.1054 max mem: 8255 +Train: [4] [ 600/6250] eta: 0:21:18 lr: 0.000102 grad: 0.1607 (0.1819) loss: 0.9396 (0.9402) time: 0.1881 data: 0.1062 max mem: 8255 +Train: [4] [ 700/6250] eta: 0:20:31 lr: 0.000103 grad: 0.1487 (0.1818) loss: 0.9361 (0.9397) time: 0.1942 data: 0.1173 max mem: 8255 +Train: [4] [ 800/6250] eta: 0:19:57 lr: 0.000103 grad: 0.1679 (0.1810) loss: 0.9373 (0.9393) time: 0.1976 data: 0.0944 max mem: 8255 +Train: [4] [ 900/6250] eta: 0:19:17 lr: 0.000104 grad: 0.1688 (0.1802) loss: 0.9365 (0.9390) time: 0.1621 data: 0.0695 max mem: 8255 +Train: [4] [1000/6250] eta: 0:18:48 lr: 0.000104 grad: 0.1804 (0.1809) loss: 0.9367 (0.9388) time: 0.1889 data: 0.1050 max mem: 8255 +Train: [4] [1100/6250] eta: 0:18:18 lr: 0.000104 grad: 0.1621 (0.1807) loss: 0.9375 (0.9384) time: 0.1830 data: 0.0489 max mem: 8255 +Train: [4] [1200/6250] eta: 0:17:52 lr: 0.000105 grad: 0.1793 (0.1804) loss: 0.9339 (0.9381) time: 0.1331 data: 0.0342 max mem: 8255 +Train: [4] [1300/6250] eta: 0:17:15 lr: 0.000105 grad: 0.1470 (0.1792) loss: 0.9341 (0.9379) time: 0.1845 data: 0.0937 max mem: 8255 +Train: [4] [1400/6250] eta: 0:16:46 lr: 0.000106 grad: 0.1718 (0.1796) loss: 0.9336 (0.9377) time: 0.2735 data: 0.1689 max mem: 8255 +Train: [4] [1500/6250] eta: 0:16:14 lr: 0.000106 grad: 0.1606 (0.1795) loss: 0.9352 (0.9376) time: 0.1463 data: 0.0641 max mem: 8255 +Train: [4] [1600/6250] eta: 0:15:50 lr: 0.000106 grad: 0.1510 (0.1785) loss: 0.9363 (0.9374) time: 0.2443 data: 0.1299 max mem: 8255 +Train: [4] [1700/6250] eta: 0:15:26 lr: 0.000107 grad: 0.1855 (0.1782) loss: 0.9347 (0.9373) time: 0.1563 data: 0.0729 max mem: 8255 +Train: [4] [1800/6250] eta: 0:14:58 lr: 0.000107 grad: 0.1621 (0.1770) loss: 0.9351 (0.9371) time: 0.1987 data: 0.1207 max mem: 8255 +Train: [4] [1900/6250] eta: 0:14:29 lr: 0.000108 grad: 0.1530 (0.1770) loss: 0.9312 (0.9369) time: 0.1772 data: 0.1009 max mem: 8255 +Train: [4] [2000/6250] eta: 0:14:00 lr: 0.000108 grad: 0.1468 (0.1761) loss: 0.9315 (0.9368) time: 0.1655 data: 0.0899 max mem: 8255 +Train: [4] [2100/6250] eta: 0:13:34 lr: 0.000108 grad: 0.1652 (0.1754) loss: 0.9293 (0.9366) time: 0.1979 data: 0.1153 max mem: 8255 +Train: [4] [2200/6250] eta: 0:13:14 lr: 0.000109 grad: 0.1707 (0.1751) loss: 0.9306 (0.9364) time: 0.0959 data: 0.0002 max mem: 8255 +Train: [4] [2300/6250] eta: 0:12:51 lr: 0.000109 grad: 0.1645 (0.1748) loss: 0.9308 (0.9362) time: 0.1526 data: 0.0820 max mem: 8255 +Train: [4] [2400/6250] eta: 0:12:29 lr: 0.000110 grad: 0.1496 (0.1738) loss: 0.9332 (0.9360) time: 0.1663 data: 0.0846 max mem: 8255 +Train: [4] [2500/6250] eta: 0:12:08 lr: 0.000110 grad: 0.1640 (0.1733) loss: 0.9323 (0.9359) time: 0.0876 data: 0.0004 max mem: 8255 +Train: [4] [2600/6250] eta: 0:11:45 lr: 0.000110 grad: 0.1574 (0.1730) loss: 0.9338 (0.9358) time: 0.1685 data: 0.0834 max mem: 8255 +Train: [4] [2700/6250] eta: 0:11:23 lr: 0.000111 grad: 0.1467 (0.1725) loss: 0.9314 (0.9356) time: 0.1686 data: 0.0775 max mem: 8255 +Train: [4] [2800/6250] eta: 0:11:01 lr: 0.000111 grad: 0.1445 (0.1718) loss: 0.9342 (0.9355) time: 0.1877 data: 0.1044 max mem: 8255 +Train: [4] [2900/6250] eta: 0:10:41 lr: 0.000112 grad: 0.1495 (0.1711) loss: 0.9304 (0.9353) time: 0.1563 data: 0.0677 max mem: 8255 +Train: [4] [3000/6250] eta: 0:10:22 lr: 0.000112 grad: 0.1407 (0.1707) loss: 0.9306 (0.9352) time: 0.1147 data: 0.0003 max mem: 8255 +Train: [4] [3100/6250] eta: 0:10:01 lr: 0.000112 grad: 0.1320 (0.1701) loss: 0.9310 (0.9350) time: 0.1627 data: 0.0755 max mem: 8255 +Train: [4] [3200/6250] eta: 0:09:40 lr: 0.000113 grad: 0.1637 (0.1696) loss: 0.9285 (0.9348) time: 0.1534 data: 0.0827 max mem: 8255 +Train: [4] [3300/6250] eta: 0:09:19 lr: 0.000113 grad: 0.1245 (0.1689) loss: 0.9295 (0.9347) time: 0.1839 data: 0.1003 max mem: 8255 +Train: [4] [3400/6250] eta: 0:09:00 lr: 0.000114 grad: 0.1597 (0.1685) loss: 0.9304 (0.9346) time: 0.1625 data: 0.0690 max mem: 8255 +Train: [4] [3500/6250] eta: 0:08:40 lr: 0.000114 grad: 0.1508 (0.1682) loss: 0.9297 (0.9345) time: 0.1911 data: 0.1029 max mem: 8255 +Train: [4] [3600/6250] eta: 0:08:22 lr: 0.000114 grad: 0.1485 (0.1675) loss: 0.9313 (0.9343) time: 0.1281 data: 0.0002 max mem: 8255 +Train: [4] [3700/6250] eta: 0:08:03 lr: 0.000115 grad: 0.1271 (0.1671) loss: 0.9308 (0.9342) time: 0.2025 data: 0.0901 max mem: 8255 +Train: [4] [3800/6250] eta: 0:07:43 lr: 0.000115 grad: 0.1349 (0.1665) loss: 0.9281 (0.9341) time: 0.1798 data: 0.0926 max mem: 8255 +Train: [4] [3900/6250] eta: 0:07:24 lr: 0.000116 grad: 0.1571 (0.1662) loss: 0.9310 (0.9340) time: 0.1771 data: 0.0848 max mem: 8255 +Train: [4] [4000/6250] eta: 0:07:05 lr: 0.000116 grad: 0.1402 (0.1656) loss: 0.9328 (0.9339) time: 0.1055 data: 0.0014 max mem: 8255 +Train: [4] [4100/6250] eta: 0:06:45 lr: 0.000116 grad: 0.1348 (0.1650) loss: 0.9287 (0.9338) time: 0.1619 data: 0.0815 max mem: 8255 +Train: [4] [4200/6250] eta: 0:06:26 lr: 0.000117 grad: 0.1393 (0.1648) loss: 0.9263 (0.9337) time: 0.1359 data: 0.0449 max mem: 8255 +Train: [4] [4300/6250] eta: 0:06:06 lr: 0.000117 grad: 0.1255 (0.1641) loss: 0.9279 (0.9336) time: 0.1766 data: 0.0926 max mem: 8255 +Train: [4] [4400/6250] eta: 0:05:47 lr: 0.000118 grad: 0.1410 (0.1638) loss: 0.9307 (0.9334) time: 0.1733 data: 0.1023 max mem: 8255 +Train: [4] [4500/6250] eta: 0:05:28 lr: 0.000118 grad: 0.1342 (0.1632) loss: 0.9342 (0.9333) time: 0.1729 data: 0.0783 max mem: 8255 +Train: [4] [4600/6250] eta: 0:05:09 lr: 0.000118 grad: 0.1229 (0.1628) loss: 0.9242 (0.9332) time: 0.1315 data: 0.0443 max mem: 8255 +Train: [4] [4700/6250] eta: 0:04:50 lr: 0.000119 grad: 0.1274 (0.1625) loss: 0.9285 (0.9331) time: 0.2381 data: 0.1638 max mem: 8255 +Train: [4] [4800/6250] eta: 0:04:30 lr: 0.000119 grad: 0.1341 (0.1620) loss: 0.9266 (0.9330) time: 0.1583 data: 0.0660 max mem: 8255 +Train: [4] [4900/6250] eta: 0:04:11 lr: 0.000120 grad: 0.1225 (0.1616) loss: 0.9290 (0.9329) time: 0.1289 data: 0.0257 max mem: 8255 +Train: [4] [5000/6250] eta: 0:03:52 lr: 0.000120 grad: 0.1350 (0.1612) loss: 0.9250 (0.9328) time: 0.1786 data: 0.1040 max mem: 8255 +Train: [4] [5100/6250] eta: 0:03:33 lr: 0.000120 grad: 0.1293 (0.1608) loss: 0.9249 (0.9326) time: 0.2048 data: 0.1358 max mem: 8255 +Train: [4] [5200/6250] eta: 0:03:14 lr: 0.000121 grad: 0.1337 (0.1603) loss: 0.9251 (0.9325) time: 0.1208 data: 0.0473 max mem: 8255 +Train: [4] [5300/6250] eta: 0:02:56 lr: 0.000121 grad: 0.1202 (0.1599) loss: 0.9240 (0.9324) time: 0.1776 data: 0.1068 max mem: 8255 +Train: [4] [5400/6250] eta: 0:02:37 lr: 0.000122 grad: 0.1189 (0.1594) loss: 0.9251 (0.9323) time: 0.1536 data: 0.0738 max mem: 8255 +Train: [4] [5500/6250] eta: 0:02:18 lr: 0.000122 grad: 0.1315 (0.1591) loss: 0.9239 (0.9321) time: 0.1825 data: 0.1007 max mem: 8255 +Train: [4] [5600/6250] eta: 0:01:59 lr: 0.000122 grad: 0.1240 (0.1587) loss: 0.9279 (0.9320) time: 0.1579 data: 0.0756 max mem: 8255 +Train: [4] [5700/6250] eta: 0:01:41 lr: 0.000123 grad: 0.1288 (0.1583) loss: 0.9268 (0.9318) time: 0.1607 data: 0.0790 max mem: 8255 +Train: [4] [5800/6250] eta: 0:01:22 lr: 0.000123 grad: 0.1291 (0.1579) loss: 0.9240 (0.9317) time: 0.1606 data: 0.0769 max mem: 8255 +Train: [4] [5900/6250] eta: 0:01:04 lr: 0.000124 grad: 0.1308 (0.1576) loss: 0.9264 (0.9316) time: 0.1606 data: 0.0802 max mem: 8255 +Train: [4] [6000/6250] eta: 0:00:45 lr: 0.000124 grad: 0.1209 (0.1573) loss: 0.9276 (0.9315) time: 0.1509 data: 0.0611 max mem: 8255 +Train: [4] [6100/6250] eta: 0:00:27 lr: 0.000124 grad: 0.1487 (0.1569) loss: 0.9191 (0.9314) time: 0.1712 data: 0.0968 max mem: 8255 +Train: [4] [6200/6250] eta: 0:00:09 lr: 0.000125 grad: 0.1368 (0.1565) loss: 0.9251 (0.9312) time: 0.1653 data: 0.0895 max mem: 8255 +Train: [4] [6249/6250] eta: 0:00:00 lr: 0.000125 grad: 0.1369 (0.1564) loss: 0.9280 (0.9312) time: 0.1579 data: 0.0770 max mem: 8255 +Train: [4] Total time: 0:19:06 (0.1834 s / it) +Averaged stats: lr: 0.000125 grad: 0.1369 (0.1564) loss: 0.9280 (0.9312) +Eval (hcp-train-subset): [4] [ 0/62] eta: 0:06:31 loss: 0.9345 (0.9345) time: 6.3120 data: 6.2858 max mem: 8255 +Eval (hcp-train-subset): [4] [61/62] eta: 0:00:00 loss: 0.9283 (0.9265) time: 0.1926 data: 0.1711 max mem: 8255 +Eval (hcp-train-subset): [4] Total time: 0:00:16 (0.2646 s / it) +Averaged stats (hcp-train-subset): loss: 0.9283 (0.9265) +Making plots (hcp-train-subset): example=39 +Eval (hcp-val): [4] [ 0/62] eta: 0:05:20 loss: 0.9172 (0.9172) time: 5.1763 data: 5.1485 max mem: 8255 +Eval (hcp-val): [4] [61/62] eta: 0:00:00 loss: 0.9222 (0.9219) time: 0.1428 data: 0.1219 max mem: 8255 +Eval (hcp-val): [4] Total time: 0:00:16 (0.2602 s / it) +Averaged stats (hcp-val): loss: 0.9222 (0.9219) +Making plots (hcp-val): example=10 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +Train: [5] [ 0/6250] eta: 9:17:05 lr: 0.000125 grad: 0.1234 (0.1234) loss: 0.9387 (0.9387) time: 5.3480 data: 4.9661 max mem: 8255 +Train: [5] [ 100/6250] eta: 0:27:10 lr: 0.000125 grad: 0.1418 (0.1551) loss: 0.9290 (0.9271) time: 0.2113 data: 0.1199 max mem: 8255 +Train: [5] [ 200/6250] eta: 0:23:55 lr: 0.000125 grad: 0.1236 (0.1508) loss: 0.9227 (0.9240) time: 0.1684 data: 0.0858 max mem: 8255 +Train: [5] [ 300/6250] eta: 0:22:03 lr: 0.000125 grad: 0.1105 (0.1454) loss: 0.9146 (0.9225) time: 0.2019 data: 0.1183 max mem: 8255 +Train: [5] [ 400/6250] eta: 0:21:40 lr: 0.000125 grad: 0.1273 (0.1425) loss: 0.9190 (0.9220) time: 0.1915 data: 0.0727 max mem: 8255 +Train: [5] [ 500/6250] eta: 0:20:30 lr: 0.000125 grad: 0.1222 (0.1408) loss: 0.9217 (0.9218) time: 0.2137 data: 0.1109 max mem: 8255 +Train: [5] [ 600/6250] eta: 0:19:58 lr: 0.000125 grad: 0.1229 (0.1393) loss: 0.9129 (0.9213) time: 0.2040 data: 0.1173 max mem: 8255 +Train: [5] [ 700/6250] eta: 0:19:16 lr: 0.000125 grad: 0.1261 (0.1393) loss: 0.9160 (0.9212) time: 0.1898 data: 0.1099 max mem: 8255 +Train: [5] [ 800/6250] eta: 0:18:30 lr: 0.000125 grad: 0.1216 (0.1379) loss: 0.9179 (0.9212) time: 0.1877 data: 0.1048 max mem: 8255 +Train: [5] [ 900/6250] eta: 0:17:59 lr: 0.000125 grad: 0.1226 (0.1362) loss: 0.9185 (0.9210) time: 0.1772 data: 0.1017 max mem: 8255 +Train: [5] [1000/6250] eta: 0:17:33 lr: 0.000125 grad: 0.1234 (0.1358) loss: 0.9183 (0.9209) time: 0.1670 data: 0.0972 max mem: 8255 +Train: [5] [1100/6250] eta: 0:17:08 lr: 0.000125 grad: 0.1241 (0.1347) loss: 0.9188 (0.9208) time: 0.1974 data: 0.1079 max mem: 8255 +Train: [5] [1200/6250] eta: 0:16:37 lr: 0.000125 grad: 0.1106 (0.1337) loss: 0.9209 (0.9207) time: 0.2050 data: 0.1193 max mem: 8255 +Train: [5] [1300/6250] eta: 0:16:10 lr: 0.000125 grad: 0.1210 (0.1333) loss: 0.9186 (0.9206) time: 0.2081 data: 0.0965 max mem: 8255 +Train: [5] [1400/6250] eta: 0:15:42 lr: 0.000125 grad: 0.1160 (0.1321) loss: 0.9206 (0.9205) time: 0.1511 data: 0.0347 max mem: 8255 +Train: [5] [1500/6250] eta: 0:15:17 lr: 0.000125 grad: 0.1303 (0.1318) loss: 0.9206 (0.9204) time: 0.1143 data: 0.0190 max mem: 8255 +Train: [5] [1600/6250] eta: 0:14:57 lr: 0.000125 grad: 0.1290 (0.1313) loss: 0.9226 (0.9204) time: 0.2089 data: 0.1317 max mem: 8255 +Train: [5] [1700/6250] eta: 0:14:28 lr: 0.000125 grad: 0.1084 (0.1305) loss: 0.9211 (0.9205) time: 0.2069 data: 0.1231 max mem: 8255 +Train: [5] [1800/6250] eta: 0:13:59 lr: 0.000125 grad: 0.1167 (0.1300) loss: 0.9212 (0.9205) time: 0.1613 data: 0.0809 max mem: 8255 +Train: [5] [1900/6250] eta: 0:13:34 lr: 0.000125 grad: 0.1223 (0.1298) loss: 0.9237 (0.9206) time: 0.1730 data: 0.1023 max mem: 8255 +Train: [5] [2000/6250] eta: 0:13:16 lr: 0.000125 grad: 0.1105 (0.1291) loss: 0.9163 (0.9206) time: 0.1556 data: 0.0863 max mem: 8255 +Train: [5] [2100/6250] eta: 0:12:51 lr: 0.000125 grad: 0.1213 (0.1287) loss: 0.9179 (0.9204) time: 0.1587 data: 0.0785 max mem: 8255 +Train: [5] [2200/6250] eta: 0:12:29 lr: 0.000125 grad: 0.1206 (0.1283) loss: 0.9195 (0.9203) time: 0.1637 data: 0.0990 max mem: 8255 +Train: [5] [2300/6250] eta: 0:12:11 lr: 0.000125 grad: 0.1155 (0.1280) loss: 0.9181 (0.9202) time: 0.2598 data: 0.1805 max mem: 8255 +Train: [5] [2400/6250] eta: 0:11:47 lr: 0.000125 grad: 0.1235 (0.1277) loss: 0.9163 (0.9201) time: 0.1716 data: 0.1058 max mem: 8255 +Train: [5] [2500/6250] eta: 0:11:26 lr: 0.000125 grad: 0.1049 (0.1274) loss: 0.9214 (0.9200) time: 0.1814 data: 0.1143 max mem: 8255 +Train: [5] [2600/6250] eta: 0:11:04 lr: 0.000125 grad: 0.1223 (0.1273) loss: 0.9220 (0.9200) time: 0.1395 data: 0.0641 max mem: 8255 +Train: [5] [2700/6250] eta: 0:10:45 lr: 0.000125 grad: 0.1006 (0.1270) loss: 0.9194 (0.9198) time: 0.1127 data: 0.0352 max mem: 8255 +Train: [5] [2800/6250] eta: 0:10:25 lr: 0.000125 grad: 0.1190 (0.1266) loss: 0.9127 (0.9197) time: 0.2188 data: 0.1420 max mem: 8255 +Train: [5] [2900/6250] eta: 0:10:06 lr: 0.000125 grad: 0.1095 (0.1262) loss: 0.9167 (0.9196) time: 0.1520 data: 0.0687 max mem: 8255 +Train: [5] [3000/6250] eta: 0:09:47 lr: 0.000125 grad: 0.1171 (0.1259) loss: 0.9188 (0.9195) time: 0.1815 data: 0.1077 max mem: 8255 +Train: [5] [3100/6250] eta: 0:09:30 lr: 0.000125 grad: 0.1107 (0.1256) loss: 0.9187 (0.9194) time: 0.1164 data: 0.0003 max mem: 8255 +Train: [5] [3200/6250] eta: 0:09:10 lr: 0.000125 grad: 0.1097 (0.1253) loss: 0.9201 (0.9194) time: 0.1792 data: 0.0982 max mem: 8255 +Train: [5] [3300/6250] eta: 0:08:51 lr: 0.000125 grad: 0.1034 (0.1248) loss: 0.9151 (0.9193) time: 0.1998 data: 0.1051 max mem: 8255 +Train: [5] [3400/6250] eta: 0:08:31 lr: 0.000125 grad: 0.1142 (0.1246) loss: 0.9168 (0.9192) time: 0.1572 data: 0.0781 max mem: 8255 +Train: [5] [3500/6250] eta: 0:08:14 lr: 0.000125 grad: 0.1073 (0.1243) loss: 0.9181 (0.9191) time: 0.2072 data: 0.1294 max mem: 8255 +Train: [5] [3600/6250] eta: 0:07:56 lr: 0.000125 grad: 0.1034 (0.1240) loss: 0.9133 (0.9189) time: 0.1652 data: 0.0709 max mem: 8255 +Train: [5] [3700/6250] eta: 0:07:37 lr: 0.000125 grad: 0.1099 (0.1237) loss: 0.9190 (0.9188) time: 0.1271 data: 0.0581 max mem: 8255 +Train: [5] [3800/6250] eta: 0:07:19 lr: 0.000125 grad: 0.1081 (0.1235) loss: 0.9124 (0.9187) time: 0.2129 data: 0.1274 max mem: 8255 +Train: [5] [3900/6250] eta: 0:07:01 lr: 0.000125 grad: 0.1174 (0.1232) loss: 0.9163 (0.9186) time: 0.1429 data: 0.0647 max mem: 8255 +Train: [5] [4000/6250] eta: 0:06:42 lr: 0.000125 grad: 0.1142 (0.1230) loss: 0.9145 (0.9185) time: 0.1647 data: 0.0911 max mem: 8255 +Train: [5] [4100/6250] eta: 0:06:24 lr: 0.000125 grad: 0.1112 (0.1227) loss: 0.9131 (0.9184) time: 0.2090 data: 0.1401 max mem: 8255 +Train: [5] [4200/6250] eta: 0:06:07 lr: 0.000125 grad: 0.1228 (0.1225) loss: 0.9132 (0.9183) time: 0.2678 data: 0.1748 max mem: 8255 +Train: [5] [4300/6250] eta: 0:05:47 lr: 0.000125 grad: 0.1148 (0.1225) loss: 0.9148 (0.9182) time: 0.1656 data: 0.0816 max mem: 8255 +Train: [5] [4400/6250] eta: 0:05:29 lr: 0.000125 grad: 0.1128 (0.1222) loss: 0.9157 (0.9181) time: 0.1247 data: 0.0487 max mem: 8255 +Train: [5] [4500/6250] eta: 0:05:11 lr: 0.000125 grad: 0.1028 (0.1220) loss: 0.9115 (0.9180) time: 0.1313 data: 0.0577 max mem: 8255 +Train: [5] [4600/6250] eta: 0:04:52 lr: 0.000125 grad: 0.1050 (0.1218) loss: 0.9116 (0.9179) time: 0.1591 data: 0.0698 max mem: 8255 +Train: [5] [4700/6250] eta: 0:04:35 lr: 0.000125 grad: 0.1029 (0.1216) loss: 0.9089 (0.9178) time: 0.1670 data: 0.1026 max mem: 8255 +Train: [5] [4800/6250] eta: 0:04:17 lr: 0.000125 grad: 0.1158 (0.1214) loss: 0.9091 (0.9176) time: 0.1678 data: 0.0985 max mem: 8255 +Train: [5] [4900/6250] eta: 0:03:59 lr: 0.000125 grad: 0.1125 (0.1212) loss: 0.9104 (0.9175) time: 0.1598 data: 0.0804 max mem: 8255 +Train: [5] [5000/6250] eta: 0:03:40 lr: 0.000125 grad: 0.1044 (0.1210) loss: 0.9110 (0.9174) time: 0.1501 data: 0.0789 max mem: 8255 +Train: [5] [5100/6250] eta: 0:03:22 lr: 0.000125 grad: 0.1036 (0.1208) loss: 0.9114 (0.9172) time: 0.1491 data: 0.0761 max mem: 8255 +Train: [5] [5200/6250] eta: 0:03:04 lr: 0.000125 grad: 0.1040 (0.1206) loss: 0.9112 (0.9171) time: 0.1587 data: 0.0837 max mem: 8255 +Train: [5] [5300/6250] eta: 0:02:46 lr: 0.000125 grad: 0.1037 (0.1203) loss: 0.9109 (0.9169) time: 0.1553 data: 0.0864 max mem: 8255 +Train: [5] [5400/6250] eta: 0:02:28 lr: 0.000125 grad: 0.0961 (0.1200) loss: 0.9115 (0.9168) time: 0.1382 data: 0.0676 max mem: 8255 +Train: [5] [5500/6250] eta: 0:02:11 lr: 0.000125 grad: 0.1170 (0.1199) loss: 0.9112 (0.9167) time: 0.1384 data: 0.0551 max mem: 8255 +Train: [5] [5600/6250] eta: 0:01:54 lr: 0.000125 grad: 0.1168 (0.1197) loss: 0.9090 (0.9166) time: 0.2360 data: 0.1244 max mem: 8255 +Train: [5] [5700/6250] eta: 0:01:37 lr: 0.000125 grad: 0.0973 (0.1195) loss: 0.9128 (0.9165) time: 0.2156 data: 0.1326 max mem: 8255 +Train: [5] [5800/6250] eta: 0:01:19 lr: 0.000125 grad: 0.1035 (0.1193) loss: 0.9127 (0.9164) time: 0.2206 data: 0.1311 max mem: 8255 +Train: [5] [5900/6250] eta: 0:01:01 lr: 0.000125 grad: 0.0999 (0.1191) loss: 0.9093 (0.9163) time: 0.1879 data: 0.0898 max mem: 8255 +Train: [5] [6000/6250] eta: 0:00:44 lr: 0.000125 grad: 0.1120 (0.1190) loss: 0.9121 (0.9161) time: 0.1698 data: 0.0777 max mem: 8255 +Train: [5] [6100/6250] eta: 0:00:26 lr: 0.000125 grad: 0.1027 (0.1188) loss: 0.9100 (0.9160) time: 0.1510 data: 0.0388 max mem: 8255 +Train: [5] [6200/6250] eta: 0:00:08 lr: 0.000125 grad: 0.1036 (0.1187) loss: 0.9087 (0.9159) time: 0.1525 data: 0.0720 max mem: 8255 +Train: [5] [6249/6250] eta: 0:00:00 lr: 0.000125 grad: 0.0992 (0.1186) loss: 0.9040 (0.9158) time: 0.2237 data: 0.1249 max mem: 8255 +Train: [5] Total time: 0:18:37 (0.1787 s / it) +Averaged stats: lr: 0.000125 grad: 0.0992 (0.1186) loss: 0.9040 (0.9158) +Eval (hcp-train-subset): [5] [ 0/62] eta: 0:06:18 loss: 0.9255 (0.9255) time: 6.1068 data: 6.0780 max mem: 8255 +Eval (hcp-train-subset): [5] [61/62] eta: 0:00:00 loss: 0.9163 (0.9154) time: 0.1780 data: 0.1554 max mem: 8255 +Eval (hcp-train-subset): [5] Total time: 0:00:16 (0.2671 s / it) +Averaged stats (hcp-train-subset): loss: 0.9163 (0.9154) +Eval (hcp-val): [5] [ 0/62] eta: 0:05:48 loss: 0.9034 (0.9034) time: 5.6129 data: 5.5846 max mem: 8255 +Eval (hcp-val): [5] [61/62] eta: 0:00:00 loss: 0.9098 (0.9098) time: 0.1664 data: 0.1452 max mem: 8255 +Eval (hcp-val): [5] Total time: 0:00:17 (0.2775 s / it) +Averaged stats (hcp-val): loss: 0.9098 (0.9098) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +Train: [6] [ 0/6250] eta: 12:24:39 lr: 0.000125 grad: 0.0983 (0.0983) loss: 0.9102 (0.9102) time: 7.1488 data: 7.0354 max mem: 8255 +Train: [6] [ 100/6250] eta: 0:24:58 lr: 0.000125 grad: 0.1243 (0.1304) loss: 0.9060 (0.9096) time: 0.1756 data: 0.0948 max mem: 8255 +Train: [6] [ 200/6250] eta: 0:22:50 lr: 0.000125 grad: 0.1101 (0.1275) loss: 0.9064 (0.9074) time: 0.1691 data: 0.0735 max mem: 8255 +Train: [6] [ 300/6250] eta: 0:21:45 lr: 0.000125 grad: 0.1037 (0.1220) loss: 0.9099 (0.9080) time: 0.2002 data: 0.1197 max mem: 8255 +Train: [6] [ 400/6250] eta: 0:20:32 lr: 0.000125 grad: 0.1014 (0.1180) loss: 0.9093 (0.9086) time: 0.1790 data: 0.0885 max mem: 8255 +Train: [6] [ 500/6250] eta: 0:19:39 lr: 0.000125 grad: 0.1106 (0.1159) loss: 0.9123 (0.9094) time: 0.1783 data: 0.0836 max mem: 8255 +Train: [6] [ 600/6250] eta: 0:18:51 lr: 0.000125 grad: 0.1000 (0.1145) loss: 0.9104 (0.9099) time: 0.1928 data: 0.0991 max mem: 8255 +Train: [6] [ 700/6250] eta: 0:18:46 lr: 0.000125 grad: 0.1091 (0.1129) loss: 0.9113 (0.9101) time: 0.2143 data: 0.1296 max mem: 8255 +Train: [6] [ 800/6250] eta: 0:18:11 lr: 0.000125 grad: 0.1020 (0.1117) loss: 0.9104 (0.9103) time: 0.1473 data: 0.0581 max mem: 8255 +Train: [6] [ 900/6250] eta: 0:17:40 lr: 0.000125 grad: 0.0962 (0.1105) loss: 0.9142 (0.9104) time: 0.1564 data: 0.0874 max mem: 8255 +Train: [6] [1000/6250] eta: 0:17:17 lr: 0.000125 grad: 0.0947 (0.1094) loss: 0.9099 (0.9102) time: 0.1706 data: 0.0917 max mem: 8255 +Train: [6] [1100/6250] eta: 0:16:53 lr: 0.000125 grad: 0.1039 (0.1090) loss: 0.9063 (0.9100) time: 0.1487 data: 0.0639 max mem: 8255 +Train: [6] [1200/6250] eta: 0:16:32 lr: 0.000125 grad: 0.0946 (0.1081) loss: 0.9123 (0.9099) time: 0.2212 data: 0.1146 max mem: 8255 +Train: [6] [1300/6250] eta: 0:16:08 lr: 0.000125 grad: 0.0981 (0.1076) loss: 0.9092 (0.9097) time: 0.1625 data: 0.0816 max mem: 8255 +Train: [6] [1400/6250] eta: 0:15:51 lr: 0.000125 grad: 0.1002 (0.1070) loss: 0.9093 (0.9096) time: 0.2376 data: 0.1509 max mem: 8255 +Train: [6] [1500/6250] eta: 0:15:24 lr: 0.000125 grad: 0.1017 (0.1069) loss: 0.9086 (0.9095) time: 0.1710 data: 0.0874 max mem: 8255 +Train: [6] [1600/6250] eta: 0:15:00 lr: 0.000125 grad: 0.0910 (0.1064) loss: 0.9082 (0.9094) time: 0.1989 data: 0.1042 max mem: 8255 +Train: [6] [1700/6250] eta: 0:14:34 lr: 0.000125 grad: 0.1010 (0.1061) loss: 0.9075 (0.9093) time: 0.1839 data: 0.1111 max mem: 8255 +Train: [6] [1800/6250] eta: 0:14:10 lr: 0.000125 grad: 0.1062 (0.1057) loss: 0.9082 (0.9093) time: 0.1958 data: 0.1193 max mem: 8255 +Train: [6] [1900/6250] eta: 0:13:46 lr: 0.000125 grad: 0.0996 (0.1054) loss: 0.9101 (0.9092) time: 0.1679 data: 0.0899 max mem: 8255 +Train: [6] [2000/6250] eta: 0:13:19 lr: 0.000125 grad: 0.0900 (0.1051) loss: 0.9087 (0.9091) time: 0.1581 data: 0.0781 max mem: 8255 +Train: [6] [2100/6250] eta: 0:12:59 lr: 0.000125 grad: 0.0993 (0.1049) loss: 0.9063 (0.9090) time: 0.0977 data: 0.0063 max mem: 8255 +Train: [6] [2200/6250] eta: 0:12:42 lr: 0.000125 grad: 0.0935 (0.1047) loss: 0.9082 (0.9089) time: 0.2264 data: 0.1421 max mem: 8255 +Train: [6] [2300/6250] eta: 0:12:18 lr: 0.000125 grad: 0.0926 (0.1044) loss: 0.9050 (0.9088) time: 0.1439 data: 0.0657 max mem: 8255 +Train: [6] [2400/6250] eta: 0:11:58 lr: 0.000125 grad: 0.0894 (0.1043) loss: 0.9018 (0.9086) time: 0.1874 data: 0.0907 max mem: 8255 +Train: [6] [2500/6250] eta: 0:11:39 lr: 0.000125 grad: 0.0968 (0.1041) loss: 0.9043 (0.9085) time: 0.1256 data: 0.0003 max mem: 8255 +Train: [6] [2600/6250] eta: 0:11:20 lr: 0.000125 grad: 0.0988 (0.1038) loss: 0.9045 (0.9083) time: 0.1648 data: 0.0825 max mem: 8255 +Train: [6] [2700/6250] eta: 0:11:00 lr: 0.000125 grad: 0.1015 (0.1037) loss: 0.9022 (0.9082) time: 0.2086 data: 0.1271 max mem: 8255 +Train: [6] [2800/6250] eta: 0:10:41 lr: 0.000125 grad: 0.0975 (0.1035) loss: 0.9070 (0.9081) time: 0.0885 data: 0.0002 max mem: 8255 +Train: [6] [2900/6250] eta: 0:10:19 lr: 0.000125 grad: 0.0928 (0.1033) loss: 0.9077 (0.9080) time: 0.1760 data: 0.1031 max mem: 8255 +Train: [6] [3000/6250] eta: 0:09:58 lr: 0.000125 grad: 0.1000 (0.1032) loss: 0.9033 (0.9079) time: 0.2130 data: 0.1277 max mem: 8255 +Train: [6] [3100/6250] eta: 0:09:43 lr: 0.000125 grad: 0.0996 (0.1031) loss: 0.9066 (0.9078) time: 0.2041 data: 0.1182 max mem: 8255 +Train: [6] [3200/6250] eta: 0:09:20 lr: 0.000125 grad: 0.0882 (0.1028) loss: 0.9083 (0.9077) time: 0.1743 data: 0.0773 max mem: 8255 +Train: [6] [3300/6250] eta: 0:09:03 lr: 0.000125 grad: 0.0903 (0.1026) loss: 0.9057 (0.9076) time: 0.1865 data: 0.0958 max mem: 8255 +Train: [6] [3400/6250] eta: 0:08:43 lr: 0.000125 grad: 0.0902 (0.1023) loss: 0.9055 (0.9075) time: 0.1650 data: 0.0973 max mem: 8255 +Train: [6] [3500/6250] eta: 0:08:25 lr: 0.000125 grad: 0.0911 (0.1022) loss: 0.9076 (0.9074) time: 0.1141 data: 0.0003 max mem: 8255 +Train: [6] [3600/6250] eta: 0:08:05 lr: 0.000125 grad: 0.0905 (0.1020) loss: 0.9069 (0.9074) time: 0.1262 data: 0.0282 max mem: 8255 +Train: [6] [3700/6250] eta: 0:07:48 lr: 0.000125 grad: 0.0866 (0.1019) loss: 0.9046 (0.9073) time: 0.1296 data: 0.0218 max mem: 8255 +Train: [6] [3800/6250] eta: 0:07:27 lr: 0.000125 grad: 0.0940 (0.1017) loss: 0.9058 (0.9073) time: 0.1255 data: 0.0541 max mem: 8255 +Train: [6] [3900/6250] eta: 0:07:08 lr: 0.000125 grad: 0.0906 (0.1015) loss: 0.9031 (0.9072) time: 0.1704 data: 0.0886 max mem: 8255 +Train: [6] [4000/6250] eta: 0:06:51 lr: 0.000125 grad: 0.0954 (0.1014) loss: 0.9058 (0.9071) time: 0.2139 data: 0.1320 max mem: 8255 +Train: [6] [4100/6250] eta: 0:06:32 lr: 0.000125 grad: 0.0869 (0.1012) loss: 0.9049 (0.9071) time: 0.1599 data: 0.0880 max mem: 8255 +Train: [6] [4200/6250] eta: 0:06:13 lr: 0.000125 grad: 0.0853 (0.1010) loss: 0.9052 (0.9070) time: 0.0963 data: 0.0002 max mem: 8255 +Train: [6] [4300/6250] eta: 0:05:54 lr: 0.000125 grad: 0.0953 (0.1008) loss: 0.8999 (0.9070) time: 0.1918 data: 0.0994 max mem: 8255 +Train: [6] [4400/6250] eta: 0:05:36 lr: 0.000125 grad: 0.0931 (0.1007) loss: 0.9010 (0.9069) time: 0.3362 data: 0.2534 max mem: 8255 +Train: [6] [4500/6250] eta: 0:05:17 lr: 0.000125 grad: 0.0871 (0.1006) loss: 0.9022 (0.9068) time: 0.1365 data: 0.0593 max mem: 8255 +Train: [6] [4600/6250] eta: 0:04:58 lr: 0.000125 grad: 0.0992 (0.1006) loss: 0.9016 (0.9067) time: 0.2297 data: 0.1563 max mem: 8255 +Train: [6] [4700/6250] eta: 0:04:39 lr: 0.000125 grad: 0.0949 (0.1006) loss: 0.9047 (0.9066) time: 0.2331 data: 0.1536 max mem: 8255 +Train: [6] [4800/6250] eta: 0:04:20 lr: 0.000125 grad: 0.0887 (0.1005) loss: 0.9025 (0.9065) time: 0.1669 data: 0.0820 max mem: 8255 +Train: [6] [4900/6250] eta: 0:04:02 lr: 0.000125 grad: 0.0896 (0.1003) loss: 0.9039 (0.9065) time: 0.1449 data: 0.0606 max mem: 8255 +Train: [6] [5000/6250] eta: 0:03:43 lr: 0.000125 grad: 0.0906 (0.1001) loss: 0.9016 (0.9064) time: 0.1616 data: 0.0858 max mem: 8255 +Train: [6] [5100/6250] eta: 0:03:25 lr: 0.000125 grad: 0.0906 (0.1000) loss: 0.9052 (0.9063) time: 0.1578 data: 0.0762 max mem: 8255 +Train: [6] [5200/6250] eta: 0:03:07 lr: 0.000125 grad: 0.0866 (0.0999) loss: 0.9034 (0.9063) time: 0.1525 data: 0.0720 max mem: 8255 +Train: [6] [5300/6250] eta: 0:02:49 lr: 0.000125 grad: 0.0943 (0.0998) loss: 0.9049 (0.9063) time: 0.1657 data: 0.0892 max mem: 8255 +Train: [6] [5400/6250] eta: 0:02:31 lr: 0.000125 grad: 0.0929 (0.0997) loss: 0.8992 (0.9062) time: 0.1824 data: 0.0971 max mem: 8255 +Train: [6] [5500/6250] eta: 0:02:13 lr: 0.000125 grad: 0.0867 (0.0995) loss: 0.9034 (0.9062) time: 0.2536 data: 0.1764 max mem: 8255 +Train: [6] [5600/6250] eta: 0:01:56 lr: 0.000125 grad: 0.0875 (0.0994) loss: 0.8995 (0.9061) time: 0.2234 data: 0.1350 max mem: 8255 +Train: [6] [5700/6250] eta: 0:01:38 lr: 0.000125 grad: 0.0810 (0.0992) loss: 0.9023 (0.9061) time: 0.1784 data: 0.0986 max mem: 8255 +Train: [6] [5800/6250] eta: 0:01:20 lr: 0.000125 grad: 0.0874 (0.0991) loss: 0.9026 (0.9060) time: 0.2271 data: 0.1345 max mem: 8255 +Train: [6] [5900/6250] eta: 0:01:02 lr: 0.000125 grad: 0.0896 (0.0989) loss: 0.9002 (0.9060) time: 0.3612 data: 0.2419 max mem: 8255 +Train: [6] [6000/6250] eta: 0:00:44 lr: 0.000125 grad: 0.0910 (0.0988) loss: 0.9015 (0.9059) time: 0.1681 data: 0.0881 max mem: 8255 +Train: [6] [6100/6250] eta: 0:00:26 lr: 0.000125 grad: 0.0857 (0.0986) loss: 0.9033 (0.9059) time: 0.1777 data: 0.0955 max mem: 8255 +Train: [6] [6200/6250] eta: 0:00:08 lr: 0.000125 grad: 0.0956 (0.0985) loss: 0.8994 (0.9058) time: 0.2703 data: 0.1993 max mem: 8255 +Train: [6] [6249/6250] eta: 0:00:00 lr: 0.000125 grad: 0.0946 (0.0985) loss: 0.9003 (0.9058) time: 0.2422 data: 0.1699 max mem: 8255 +Train: [6] Total time: 0:18:50 (0.1809 s / it) +Averaged stats: lr: 0.000125 grad: 0.0946 (0.0985) loss: 0.9003 (0.9058) +Eval (hcp-train-subset): [6] [ 0/62] eta: 0:03:37 loss: 0.9146 (0.9146) time: 3.5110 data: 3.4536 max mem: 8255 +Eval (hcp-train-subset): [6] [61/62] eta: 0:00:00 loss: 0.9093 (0.9082) time: 0.1575 data: 0.1370 max mem: 8255 +Eval (hcp-train-subset): [6] Total time: 0:00:14 (0.2332 s / it) +Averaged stats (hcp-train-subset): loss: 0.9093 (0.9082) +Eval (hcp-val): [6] [ 0/62] eta: 0:05:22 loss: 0.8992 (0.8992) time: 5.2013 data: 5.1747 max mem: 8255 +Eval (hcp-val): [6] [61/62] eta: 0:00:00 loss: 0.9020 (0.9030) time: 0.1431 data: 0.1212 max mem: 8255 +Eval (hcp-val): [6] Total time: 0:00:14 (0.2399 s / it) +Averaged stats (hcp-val): loss: 0.9020 (0.9030) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +Train: [7] [ 0/6250] eta: 9:43:13 lr: 0.000125 grad: 0.1027 (0.1027) loss: 0.8945 (0.8945) time: 5.5989 data: 5.4229 max mem: 8255 +Train: [7] [ 100/6250] eta: 0:23:16 lr: 0.000125 grad: 0.1072 (0.1220) loss: 0.8905 (0.8943) time: 0.2124 data: 0.0862 max mem: 8255 +Train: [7] [ 200/6250] eta: 0:20:51 lr: 0.000125 grad: 0.0791 (0.1129) loss: 0.9042 (0.8959) time: 0.1642 data: 0.0799 max mem: 8255 +Train: [7] [ 300/6250] eta: 0:20:26 lr: 0.000125 grad: 0.0871 (0.1059) loss: 0.9094 (0.8978) time: 0.2689 data: 0.1701 max mem: 8255 +Train: [7] [ 400/6250] eta: 0:19:06 lr: 0.000125 grad: 0.0878 (0.1015) loss: 0.9020 (0.8991) time: 0.1648 data: 0.0779 max mem: 8255 +Train: [7] [ 500/6250] eta: 0:18:00 lr: 0.000125 grad: 0.0917 (0.1001) loss: 0.9012 (0.8988) time: 0.1506 data: 0.0617 max mem: 8255 +Train: [7] [ 600/6250] eta: 0:17:29 lr: 0.000125 grad: 0.0877 (0.0983) loss: 0.8962 (0.8986) time: 0.1924 data: 0.1099 max mem: 8255 +Train: [7] [ 700/6250] eta: 0:17:00 lr: 0.000125 grad: 0.0863 (0.0973) loss: 0.9033 (0.8990) time: 0.1632 data: 0.0757 max mem: 8255 +Train: [7] [ 800/6250] eta: 0:16:51 lr: 0.000125 grad: 0.0924 (0.0966) loss: 0.8996 (0.8988) time: 0.2421 data: 0.1670 max mem: 8255 +Train: [7] [ 900/6250] eta: 0:16:22 lr: 0.000125 grad: 0.0908 (0.0960) loss: 0.8949 (0.8987) time: 0.1848 data: 0.0926 max mem: 8255 +Train: [7] [1000/6250] eta: 0:15:55 lr: 0.000125 grad: 0.0953 (0.0956) loss: 0.9013 (0.8986) time: 0.1485 data: 0.0768 max mem: 8255 +Train: [7] [1100/6250] eta: 0:15:42 lr: 0.000125 grad: 0.0866 (0.0949) loss: 0.9016 (0.8988) time: 0.2228 data: 0.1488 max mem: 8255 +Train: [7] [1200/6250] eta: 0:15:26 lr: 0.000125 grad: 0.0784 (0.0942) loss: 0.9046 (0.8990) time: 0.1695 data: 0.0801 max mem: 8255 +Train: [7] [1300/6250] eta: 0:15:08 lr: 0.000125 grad: 0.0857 (0.0940) loss: 0.9000 (0.8990) time: 0.2441 data: 0.1533 max mem: 8255 +Train: [7] [1400/6250] eta: 0:14:53 lr: 0.000125 grad: 0.0866 (0.0936) loss: 0.8966 (0.8990) time: 0.2316 data: 0.1429 max mem: 8255 +Train: [7] [1500/6250] eta: 0:14:33 lr: 0.000125 grad: 0.0942 (0.0934) loss: 0.8970 (0.8991) time: 0.1254 data: 0.0013 max mem: 8255 +Train: [7] [1600/6250] eta: 0:14:11 lr: 0.000125 grad: 0.0926 (0.0931) loss: 0.8940 (0.8991) time: 0.1732 data: 0.0757 max mem: 8255 +Train: [7] [1700/6250] eta: 0:13:56 lr: 0.000125 grad: 0.0929 (0.0928) loss: 0.8986 (0.8990) time: 0.1692 data: 0.0993 max mem: 8255 +Train: [7] [1800/6250] eta: 0:13:30 lr: 0.000125 grad: 0.0837 (0.0928) loss: 0.8984 (0.8990) time: 0.1657 data: 0.0824 max mem: 8255 +Train: [7] [1900/6250] eta: 0:13:11 lr: 0.000125 grad: 0.0824 (0.0927) loss: 0.8967 (0.8989) time: 0.1293 data: 0.0566 max mem: 8255 +Train: [7] [2000/6250] eta: 0:12:58 lr: 0.000125 grad: 0.0897 (0.0926) loss: 0.9000 (0.8988) time: 0.1578 data: 0.0656 max mem: 8255 +Train: [7] [2100/6250] eta: 0:12:38 lr: 0.000125 grad: 0.0856 (0.0923) loss: 0.8976 (0.8987) time: 0.1820 data: 0.1014 max mem: 8255 +Train: [7] [2200/6250] eta: 0:12:21 lr: 0.000125 grad: 0.0853 (0.0921) loss: 0.8981 (0.8987) time: 0.1252 data: 0.0003 max mem: 8255 +Train: [7] [2300/6250] eta: 0:11:58 lr: 0.000125 grad: 0.0854 (0.0920) loss: 0.8980 (0.8987) time: 0.1542 data: 0.0754 max mem: 8255 +Train: [7] [2400/6250] eta: 0:11:41 lr: 0.000125 grad: 0.0825 (0.0918) loss: 0.8961 (0.8987) time: 0.2306 data: 0.1506 max mem: 8255 +Train: [7] [2500/6250] eta: 0:11:26 lr: 0.000125 grad: 0.0826 (0.0916) loss: 0.9015 (0.8988) time: 0.1350 data: 0.0550 max mem: 8255 +Train: [7] [2600/6250] eta: 0:11:04 lr: 0.000125 grad: 0.0860 (0.0914) loss: 0.9005 (0.8988) time: 0.1652 data: 0.0678 max mem: 8255 +Train: [7] [2700/6250] eta: 0:10:46 lr: 0.000125 grad: 0.0822 (0.0912) loss: 0.8982 (0.8988) time: 0.2301 data: 0.1168 max mem: 8255 +Train: [7] [2800/6250] eta: 0:10:29 lr: 0.000125 grad: 0.0960 (0.0911) loss: 0.8921 (0.8988) time: 0.1168 data: 0.0003 max mem: 8255 +Train: [7] [2900/6250] eta: 0:10:08 lr: 0.000125 grad: 0.0826 (0.0910) loss: 0.9028 (0.8988) time: 0.1661 data: 0.0813 max mem: 8255 +Train: [7] [3000/6250] eta: 0:09:49 lr: 0.000125 grad: 0.0880 (0.0908) loss: 0.9012 (0.8988) time: 0.1447 data: 0.0646 max mem: 8255 +Train: [7] [3100/6250] eta: 0:09:31 lr: 0.000125 grad: 0.0847 (0.0908) loss: 0.8975 (0.8989) time: 0.2439 data: 0.1449 max mem: 8255 +Train: [7] [3200/6250] eta: 0:09:13 lr: 0.000125 grad: 0.0797 (0.0906) loss: 0.9018 (0.8989) time: 0.2098 data: 0.1282 max mem: 8255 +Train: [7] [3300/6250] eta: 0:08:53 lr: 0.000125 grad: 0.0876 (0.0904) loss: 0.9024 (0.8990) time: 0.1724 data: 0.0952 max mem: 8255 +Train: [7] [3400/6250] eta: 0:08:34 lr: 0.000125 grad: 0.0819 (0.0903) loss: 0.9011 (0.8990) time: 0.1957 data: 0.1212 max mem: 8255 +Train: [7] [3500/6250] eta: 0:08:17 lr: 0.000125 grad: 0.0831 (0.0901) loss: 0.9051 (0.8991) time: 0.2229 data: 0.1240 max mem: 8255 +Train: [7] [3600/6250] eta: 0:08:02 lr: 0.000125 grad: 0.0918 (0.0900) loss: 0.9004 (0.8992) time: 0.2846 data: 0.1943 max mem: 8255 +Train: [7] [3700/6250] eta: 0:07:41 lr: 0.000125 grad: 0.0791 (0.0898) loss: 0.8975 (0.8993) time: 0.1628 data: 0.0743 max mem: 8255 +Train: [7] [3800/6250] eta: 0:07:23 lr: 0.000125 grad: 0.0835 (0.0898) loss: 0.9016 (0.8993) time: 0.2059 data: 0.1302 max mem: 8255 +Train: [7] [3900/6250] eta: 0:07:03 lr: 0.000125 grad: 0.0786 (0.0896) loss: 0.9026 (0.8994) time: 0.1720 data: 0.0997 max mem: 8255 +Train: [7] [4000/6250] eta: 0:06:43 lr: 0.000125 grad: 0.0832 (0.0895) loss: 0.9012 (0.8994) time: 0.1551 data: 0.0835 max mem: 8255 +Train: [7] [4100/6250] eta: 0:06:27 lr: 0.000125 grad: 0.0857 (0.0895) loss: 0.8994 (0.8995) time: 0.3701 data: 0.3008 max mem: 8255 +Train: [7] [4200/6250] eta: 0:06:06 lr: 0.000125 grad: 0.0810 (0.0895) loss: 0.8998 (0.8994) time: 0.1582 data: 0.0818 max mem: 8255 +Train: [7] [4300/6250] eta: 0:05:50 lr: 0.000125 grad: 0.0836 (0.0894) loss: 0.8927 (0.8994) time: 0.2435 data: 0.1683 max mem: 8255 +Train: [7] [4400/6250] eta: 0:05:30 lr: 0.000125 grad: 0.0844 (0.0893) loss: 0.8995 (0.8994) time: 0.1770 data: 0.1047 max mem: 8255 +Train: [7] [4500/6250] eta: 0:05:11 lr: 0.000125 grad: 0.0863 (0.0891) loss: 0.9011 (0.8994) time: 0.1461 data: 0.0664 max mem: 8255 +Train: [7] [4600/6250] eta: 0:04:53 lr: 0.000125 grad: 0.0801 (0.0891) loss: 0.9009 (0.8993) time: 0.1559 data: 0.0811 max mem: 8255 +Train: [7] [4700/6250] eta: 0:04:34 lr: 0.000125 grad: 0.0793 (0.0890) loss: 0.9018 (0.8993) time: 0.1243 data: 0.0315 max mem: 8255 +Train: [7] [4800/6250] eta: 0:04:16 lr: 0.000125 grad: 0.0836 (0.0889) loss: 0.8988 (0.8993) time: 0.1382 data: 0.0404 max mem: 8255 +Train: [7] [4900/6250] eta: 0:03:57 lr: 0.000125 grad: 0.0859 (0.0889) loss: 0.8923 (0.8992) time: 0.1707 data: 0.0808 max mem: 8255 +Train: [7] [5000/6250] eta: 0:03:40 lr: 0.000125 grad: 0.0879 (0.0890) loss: 0.8982 (0.8991) time: 0.1660 data: 0.0817 max mem: 8255 +Train: [7] [5100/6250] eta: 0:03:22 lr: 0.000125 grad: 0.0878 (0.0889) loss: 0.8915 (0.8991) time: 0.2220 data: 0.1425 max mem: 8255 +Train: [7] [5200/6250] eta: 0:03:05 lr: 0.000125 grad: 0.0828 (0.0889) loss: 0.8963 (0.8990) time: 0.1787 data: 0.0782 max mem: 8255 +Train: [7] [5300/6250] eta: 0:02:48 lr: 0.000125 grad: 0.0836 (0.0889) loss: 0.8971 (0.8990) time: 0.1211 data: 0.0224 max mem: 8255 +Train: [7] [5400/6250] eta: 0:02:30 lr: 0.000125 grad: 0.0773 (0.0889) loss: 0.8941 (0.8989) time: 0.2437 data: 0.1400 max mem: 8255 +Train: [7] [5500/6250] eta: 0:02:13 lr: 0.000125 grad: 0.0825 (0.0889) loss: 0.8950 (0.8989) time: 0.1121 data: 0.0036 max mem: 8255 +Train: [7] [5600/6250] eta: 0:01:56 lr: 0.000125 grad: 0.0832 (0.0889) loss: 0.8930 (0.8988) time: 0.1963 data: 0.0999 max mem: 8255 +Train: [7] [5700/6250] eta: 0:01:38 lr: 0.000125 grad: 0.0883 (0.0890) loss: 0.8943 (0.8987) time: 0.1545 data: 0.0794 max mem: 8255 +Train: [7] [5800/6250] eta: 0:01:20 lr: 0.000125 grad: 0.0888 (0.0890) loss: 0.8953 (0.8986) time: 0.1277 data: 0.0399 max mem: 8255 +Train: [7] [5900/6250] eta: 0:01:02 lr: 0.000125 grad: 0.0839 (0.0889) loss: 0.8927 (0.8985) time: 0.1226 data: 0.0125 max mem: 8255 +Train: [7] [6000/6250] eta: 0:00:44 lr: 0.000125 grad: 0.0871 (0.0889) loss: 0.8988 (0.8985) time: 0.1537 data: 0.0686 max mem: 8255 +Train: [7] [6100/6250] eta: 0:00:26 lr: 0.000125 grad: 0.0848 (0.0889) loss: 0.8950 (0.8984) time: 0.1425 data: 0.0507 max mem: 8255 +Train: [7] [6200/6250] eta: 0:00:08 lr: 0.000125 grad: 0.0829 (0.0888) loss: 0.8936 (0.8983) time: 0.1568 data: 0.0719 max mem: 8255 +Train: [7] [6249/6250] eta: 0:00:00 lr: 0.000125 grad: 0.0857 (0.0888) loss: 0.8960 (0.8983) time: 0.3264 data: 0.2292 max mem: 8255 +Train: [7] Total time: 0:18:52 (0.1812 s / it) +Averaged stats: lr: 0.000125 grad: 0.0857 (0.0888) loss: 0.8960 (0.8983) +Eval (hcp-train-subset): [7] [ 0/62] eta: 0:04:06 loss: 0.9103 (0.9103) time: 3.9772 data: 3.9151 max mem: 8255 +Eval (hcp-train-subset): [7] [61/62] eta: 0:00:00 loss: 0.9021 (0.9033) time: 0.1326 data: 0.1115 max mem: 8255 +Eval (hcp-train-subset): [7] Total time: 0:00:16 (0.2616 s / it) +Averaged stats (hcp-train-subset): loss: 0.9021 (0.9033) +Eval (hcp-val): [7] [ 0/62] eta: 0:03:57 loss: 0.8946 (0.8946) time: 3.8278 data: 3.7406 max mem: 8255 +Eval (hcp-val): [7] [61/62] eta: 0:00:00 loss: 0.8993 (0.8994) time: 0.1643 data: 0.1431 max mem: 8255 +Eval (hcp-val): [7] Total time: 0:00:16 (0.2680 s / it) +Averaged stats (hcp-val): loss: 0.8993 (0.8994) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +Train: [8] [ 0/6250] eta: 10:54:25 lr: 0.000125 grad: 0.0635 (0.0635) loss: 0.9289 (0.9289) time: 6.2825 data: 6.1396 max mem: 8255 +Train: [8] [ 100/6250] eta: 0:24:24 lr: 0.000125 grad: 0.0958 (0.1022) loss: 0.8986 (0.9006) time: 0.1863 data: 0.1024 max mem: 8255 +Train: [8] [ 200/6250] eta: 0:22:41 lr: 0.000125 grad: 0.0959 (0.0969) loss: 0.8939 (0.8980) time: 0.2976 data: 0.2077 max mem: 8255 +Train: [8] [ 300/6250] eta: 0:20:20 lr: 0.000125 grad: 0.0857 (0.0953) loss: 0.9026 (0.8976) time: 0.1538 data: 0.0496 max mem: 8255 +Train: [8] [ 400/6250] eta: 0:20:03 lr: 0.000125 grad: 0.0861 (0.0946) loss: 0.8931 (0.8977) time: 0.2198 data: 0.1251 max mem: 8255 +Train: [8] [ 500/6250] eta: 0:19:14 lr: 0.000125 grad: 0.0791 (0.0930) loss: 0.8964 (0.8977) time: 0.2025 data: 0.1237 max mem: 8255 +Train: [8] [ 600/6250] eta: 0:18:58 lr: 0.000125 grad: 0.0826 (0.0922) loss: 0.8990 (0.8977) time: 0.2481 data: 0.1667 max mem: 8255 +Train: [8] [ 700/6250] eta: 0:18:29 lr: 0.000125 grad: 0.0809 (0.0908) loss: 0.8987 (0.8977) time: 0.1671 data: 0.0847 max mem: 8255 +Train: [8] [ 800/6250] eta: 0:17:58 lr: 0.000125 grad: 0.0793 (0.0900) loss: 0.9001 (0.8978) time: 0.1705 data: 0.0897 max mem: 8255 +Train: [8] [ 900/6250] eta: 0:17:58 lr: 0.000125 grad: 0.0744 (0.0890) loss: 0.9013 (0.8980) time: 0.2746 data: 0.2067 max mem: 8255 +Train: [8] [1000/6250] eta: 0:17:31 lr: 0.000125 grad: 0.0755 (0.0882) loss: 0.8966 (0.8978) time: 0.1909 data: 0.1201 max mem: 8255 +Train: [8] [1100/6250] eta: 0:17:05 lr: 0.000125 grad: 0.0790 (0.0875) loss: 0.8993 (0.8977) time: 0.2037 data: 0.1287 max mem: 8255 +Train: [8] [1200/6250] eta: 0:16:44 lr: 0.000125 grad: 0.0790 (0.0869) loss: 0.8965 (0.8977) time: 0.2325 data: 0.1648 max mem: 8255 +Train: [8] [1300/6250] eta: 0:16:21 lr: 0.000125 grad: 0.0786 (0.0866) loss: 0.8956 (0.8976) time: 0.2241 data: 0.1444 max mem: 8255 +Train: [8] [1400/6250] eta: 0:15:58 lr: 0.000125 grad: 0.0803 (0.0863) loss: 0.8975 (0.8974) time: 0.2071 data: 0.1261 max mem: 8255 +Train: [8] [1500/6250] eta: 0:15:30 lr: 0.000125 grad: 0.0756 (0.0858) loss: 0.8982 (0.8974) time: 0.1212 data: 0.0185 max mem: 8255 +Train: [8] [1600/6250] eta: 0:15:12 lr: 0.000125 grad: 0.0797 (0.0856) loss: 0.8940 (0.8973) time: 0.1820 data: 0.0844 max mem: 8255 +Train: [8] [1700/6250] eta: 0:14:44 lr: 0.000125 grad: 0.0775 (0.0853) loss: 0.8976 (0.8971) time: 0.1528 data: 0.0875 max mem: 8255 +Train: [8] [1800/6250] eta: 0:14:32 lr: 0.000125 grad: 0.0826 (0.0851) loss: 0.8962 (0.8971) time: 0.0967 data: 0.0003 max mem: 8255 +Train: [8] [1900/6250] eta: 0:14:03 lr: 0.000125 grad: 0.0784 (0.0848) loss: 0.8985 (0.8971) time: 0.1648 data: 0.0875 max mem: 8255 +Train: [8] [2000/6250] eta: 0:13:42 lr: 0.000125 grad: 0.0755 (0.0846) loss: 0.8971 (0.8970) time: 0.2465 data: 0.1732 max mem: 8255 +Train: [8] [2100/6250] eta: 0:13:15 lr: 0.000125 grad: 0.0778 (0.0843) loss: 0.8991 (0.8969) time: 0.1867 data: 0.1149 max mem: 8255 +Train: [8] [2200/6250] eta: 0:12:55 lr: 0.000125 grad: 0.0759 (0.0842) loss: 0.8960 (0.8968) time: 0.1318 data: 0.0365 max mem: 8255 +Train: [8] [2300/6250] eta: 0:12:32 lr: 0.000125 grad: 0.0755 (0.0840) loss: 0.8969 (0.8969) time: 0.1817 data: 0.1040 max mem: 8255 +Train: [8] [2400/6250] eta: 0:12:10 lr: 0.000125 grad: 0.0771 (0.0838) loss: 0.8972 (0.8969) time: 0.1543 data: 0.0734 max mem: 8255 +Train: [8] [2500/6250] eta: 0:11:51 lr: 0.000125 grad: 0.0744 (0.0836) loss: 0.8980 (0.8968) time: 0.0941 data: 0.0002 max mem: 8255 +Train: [8] [2600/6250] eta: 0:11:29 lr: 0.000125 grad: 0.0795 (0.0834) loss: 0.8960 (0.8968) time: 0.1570 data: 0.0761 max mem: 8255 +Train: [8] [2700/6250] eta: 0:11:07 lr: 0.000125 grad: 0.0784 (0.0833) loss: 0.8990 (0.8969) time: 0.1308 data: 0.0525 max mem: 8255 +Train: [8] [2800/6250] eta: 0:10:45 lr: 0.000125 grad: 0.0822 (0.0832) loss: 0.8967 (0.8969) time: 0.1947 data: 0.1157 max mem: 8255 +Train: [8] [2900/6250] eta: 0:10:29 lr: 0.000125 grad: 0.0768 (0.0831) loss: 0.8974 (0.8969) time: 0.2969 data: 0.2059 max mem: 8255 +Train: [8] [3000/6250] eta: 0:10:05 lr: 0.000125 grad: 0.0762 (0.0829) loss: 0.8946 (0.8968) time: 0.1571 data: 0.0711 max mem: 8255 +Train: [8] [3100/6250] eta: 0:09:47 lr: 0.000125 grad: 0.0781 (0.0828) loss: 0.8989 (0.8969) time: 0.2689 data: 0.1769 max mem: 8255 +Train: [8] [3200/6250] eta: 0:09:26 lr: 0.000125 grad: 0.0803 (0.0827) loss: 0.8952 (0.8969) time: 0.1844 data: 0.0978 max mem: 8255 +Train: [8] [3300/6250] eta: 0:09:09 lr: 0.000125 grad: 0.0695 (0.0825) loss: 0.8966 (0.8969) time: 0.2937 data: 0.2221 max mem: 8255 +Train: [8] [3400/6250] eta: 0:08:47 lr: 0.000125 grad: 0.0818 (0.0825) loss: 0.8903 (0.8968) time: 0.1865 data: 0.0953 max mem: 8255 +Train: [8] [3500/6250] eta: 0:08:26 lr: 0.000125 grad: 0.0805 (0.0824) loss: 0.8936 (0.8968) time: 0.1805 data: 0.0956 max mem: 8255 +Train: [8] [3600/6250] eta: 0:08:06 lr: 0.000125 grad: 0.0818 (0.0824) loss: 0.8918 (0.8967) time: 0.1754 data: 0.0819 max mem: 8255 +Train: [8] [3700/6250] eta: 0:07:47 lr: 0.000125 grad: 0.0765 (0.0825) loss: 0.8965 (0.8966) time: 0.1833 data: 0.1028 max mem: 8255 +Train: [8] [3800/6250] eta: 0:07:28 lr: 0.000125 grad: 0.0804 (0.0825) loss: 0.8927 (0.8966) time: 0.0980 data: 0.0068 max mem: 8255 +Train: [8] [3900/6250] eta: 0:07:08 lr: 0.000125 grad: 0.0737 (0.0824) loss: 0.8951 (0.8965) time: 0.1173 data: 0.0367 max mem: 8255 +Train: [8] [4000/6250] eta: 0:06:50 lr: 0.000125 grad: 0.0779 (0.0823) loss: 0.8936 (0.8965) time: 0.1770 data: 0.1145 max mem: 8255 +Train: [8] [4100/6250] eta: 0:06:30 lr: 0.000125 grad: 0.0802 (0.0823) loss: 0.8898 (0.8964) time: 0.1089 data: 0.0134 max mem: 8255 +Train: [8] [4200/6250] eta: 0:06:11 lr: 0.000125 grad: 0.0862 (0.0823) loss: 0.8935 (0.8963) time: 0.1232 data: 0.0437 max mem: 8255 +Train: [8] [4300/6250] eta: 0:05:52 lr: 0.000125 grad: 0.0725 (0.0824) loss: 0.8956 (0.8962) time: 0.1475 data: 0.0687 max mem: 8255 +Train: [8] [4400/6250] eta: 0:05:33 lr: 0.000125 grad: 0.0762 (0.0823) loss: 0.8923 (0.8962) time: 0.1938 data: 0.1222 max mem: 8255 +Train: [8] [4500/6250] eta: 0:05:14 lr: 0.000125 grad: 0.0743 (0.0822) loss: 0.8934 (0.8961) time: 0.1572 data: 0.0701 max mem: 8255 +Train: [8] [4600/6250] eta: 0:04:56 lr: 0.000125 grad: 0.0782 (0.0821) loss: 0.8923 (0.8961) time: 0.1496 data: 0.0678 max mem: 8255 +Train: [8] [4700/6250] eta: 0:04:37 lr: 0.000125 grad: 0.0809 (0.0821) loss: 0.8924 (0.8961) time: 0.1497 data: 0.0840 max mem: 8255 +Train: [8] [4800/6250] eta: 0:04:19 lr: 0.000125 grad: 0.0802 (0.0821) loss: 0.8979 (0.8960) time: 0.2175 data: 0.1353 max mem: 8255 +Train: [8] [4900/6250] eta: 0:04:02 lr: 0.000125 grad: 0.0808 (0.0821) loss: 0.8934 (0.8960) time: 0.1870 data: 0.0952 max mem: 8255 +Train: [8] [5000/6250] eta: 0:03:45 lr: 0.000125 grad: 0.0764 (0.0821) loss: 0.8953 (0.8959) time: 0.1387 data: 0.0437 max mem: 8255 +Train: [8] [5100/6250] eta: 0:03:27 lr: 0.000125 grad: 0.0796 (0.0821) loss: 0.8974 (0.8958) time: 0.2041 data: 0.1261 max mem: 8255 +Train: [8] [5200/6250] eta: 0:03:09 lr: 0.000124 grad: 0.0784 (0.0820) loss: 0.8931 (0.8958) time: 0.1602 data: 0.0766 max mem: 8255 +Train: [8] [5300/6250] eta: 0:02:51 lr: 0.000124 grad: 0.0786 (0.0820) loss: 0.8945 (0.8958) time: 0.3551 data: 0.2409 max mem: 8255 +Train: [8] [5400/6250] eta: 0:02:33 lr: 0.000124 grad: 0.0807 (0.0819) loss: 0.8925 (0.8957) time: 0.1932 data: 0.1013 max mem: 8255 +Train: [8] [5500/6250] eta: 0:02:15 lr: 0.000124 grad: 0.0769 (0.0819) loss: 0.8969 (0.8957) time: 0.1774 data: 0.0524 max mem: 8255 +Train: [8] [5600/6250] eta: 0:01:57 lr: 0.000124 grad: 0.0735 (0.0818) loss: 0.8997 (0.8957) time: 0.1227 data: 0.0383 max mem: 8255 +Train: [8] [5700/6250] eta: 0:01:39 lr: 0.000124 grad: 0.0802 (0.0818) loss: 0.8926 (0.8957) time: 0.1972 data: 0.1121 max mem: 8255 +Train: [8] [5800/6250] eta: 0:01:21 lr: 0.000124 grad: 0.0754 (0.0818) loss: 0.8932 (0.8956) time: 0.1325 data: 0.0458 max mem: 8255 +Train: [8] [5900/6250] eta: 0:01:03 lr: 0.000124 grad: 0.0812 (0.0817) loss: 0.8983 (0.8956) time: 0.1922 data: 0.1039 max mem: 8255 +Train: [8] [6000/6250] eta: 0:00:45 lr: 0.000124 grad: 0.0777 (0.0817) loss: 0.8938 (0.8956) time: 0.1855 data: 0.1099 max mem: 8255 +Train: [8] [6100/6250] eta: 0:00:27 lr: 0.000124 grad: 0.0773 (0.0817) loss: 0.8952 (0.8956) time: 0.1411 data: 0.0504 max mem: 8255 +Train: [8] [6200/6250] eta: 0:00:09 lr: 0.000124 grad: 0.0806 (0.0817) loss: 0.8942 (0.8955) time: 0.1822 data: 0.0927 max mem: 8255 +Train: [8] [6249/6250] eta: 0:00:00 lr: 0.000124 grad: 0.0752 (0.0816) loss: 0.8937 (0.8955) time: 0.1867 data: 0.0916 max mem: 8255 +Train: [8] Total time: 0:18:55 (0.1817 s / it) +Averaged stats: lr: 0.000124 grad: 0.0752 (0.0816) loss: 0.8937 (0.8955) +Eval (hcp-train-subset): [8] [ 0/62] eta: 0:04:37 loss: 0.9081 (0.9081) time: 4.4790 data: 4.4392 max mem: 8255 +Eval (hcp-train-subset): [8] [61/62] eta: 0:00:00 loss: 0.9008 (0.8998) time: 0.1360 data: 0.1150 max mem: 8255 +Eval (hcp-train-subset): [8] Total time: 0:00:14 (0.2405 s / it) +Averaged stats (hcp-train-subset): loss: 0.9008 (0.8998) +Eval (hcp-val): [8] [ 0/62] eta: 0:03:46 loss: 0.8873 (0.8873) time: 3.6529 data: 3.6039 max mem: 8255 +Eval (hcp-val): [8] [61/62] eta: 0:00:00 loss: 0.8939 (0.8953) time: 0.1836 data: 0.1620 max mem: 8255 +Eval (hcp-val): [8] Total time: 0:00:15 (0.2452 s / it) +Averaged stats (hcp-val): loss: 0.8939 (0.8953) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +Train: [9] [ 0/6250] eta: 10:16:01 lr: 0.000124 grad: 0.0645 (0.0645) loss: 0.9163 (0.9163) time: 5.9139 data: 5.6914 max mem: 8255 +Train: [9] [ 100/6250] eta: 0:28:34 lr: 0.000124 grad: 0.0991 (0.0978) loss: 0.8870 (0.8951) time: 0.3189 data: 0.2243 max mem: 8255 +Train: [9] [ 200/6250] eta: 0:22:41 lr: 0.000124 grad: 0.0887 (0.0988) loss: 0.8935 (0.8922) time: 0.1555 data: 0.0588 max mem: 8255 +Train: [9] [ 300/6250] eta: 0:21:52 lr: 0.000124 grad: 0.0843 (0.0937) loss: 0.8961 (0.8930) time: 0.1095 data: 0.0002 max mem: 8255 +Train: [9] [ 400/6250] eta: 0:20:16 lr: 0.000124 grad: 0.0786 (0.0910) loss: 0.8925 (0.8930) time: 0.1869 data: 0.1094 max mem: 8255 +Train: [9] [ 500/6250] eta: 0:19:32 lr: 0.000124 grad: 0.0748 (0.0891) loss: 0.8918 (0.8931) time: 0.1840 data: 0.0997 max mem: 8255 +Train: [9] [ 600/6250] eta: 0:18:45 lr: 0.000124 grad: 0.0856 (0.0881) loss: 0.8914 (0.8930) time: 0.1956 data: 0.1193 max mem: 8255 +Train: [9] [ 700/6250] eta: 0:18:48 lr: 0.000124 grad: 0.0791 (0.0870) loss: 0.8935 (0.8932) time: 0.1666 data: 0.0854 max mem: 8255 +Train: [9] [ 800/6250] eta: 0:18:14 lr: 0.000124 grad: 0.0851 (0.0868) loss: 0.8953 (0.8930) time: 0.2190 data: 0.1422 max mem: 8255 +Train: [9] [ 900/6250] eta: 0:18:19 lr: 0.000124 grad: 0.0886 (0.0874) loss: 0.8915 (0.8926) time: 0.1574 data: 0.0523 max mem: 8255 +Train: [9] [1000/6250] eta: 0:17:32 lr: 0.000124 grad: 0.0788 (0.0868) loss: 0.8912 (0.8923) time: 0.1497 data: 0.0724 max mem: 8255 +Train: [9] [1100/6250] eta: 0:16:58 lr: 0.000124 grad: 0.0776 (0.0862) loss: 0.8894 (0.8919) time: 0.1756 data: 0.0930 max mem: 8255 +Train: [9] [1200/6250] eta: 0:16:28 lr: 0.000124 grad: 0.0796 (0.0859) loss: 0.8873 (0.8916) time: 0.1807 data: 0.1077 max mem: 8255 +Train: [9] [1300/6250] eta: 0:15:57 lr: 0.000124 grad: 0.0773 (0.0856) loss: 0.8927 (0.8914) time: 0.1645 data: 0.0815 max mem: 8255 +Train: [9] [1400/6250] eta: 0:15:42 lr: 0.000124 grad: 0.0827 (0.0854) loss: 0.8866 (0.8912) time: 0.1973 data: 0.1292 max mem: 8255 +Train: [9] [1500/6250] eta: 0:15:15 lr: 0.000124 grad: 0.0869 (0.0853) loss: 0.8877 (0.8910) time: 0.1640 data: 0.0852 max mem: 8255 +Train: [9] [1600/6250] eta: 0:14:48 lr: 0.000124 grad: 0.0787 (0.0851) loss: 0.8885 (0.8908) time: 0.1576 data: 0.0888 max mem: 8255 +Train: [9] [1700/6250] eta: 0:14:21 lr: 0.000124 grad: 0.0824 (0.0852) loss: 0.8856 (0.8906) time: 0.1714 data: 0.0897 max mem: 8255 +Train: [9] [1800/6250] eta: 0:14:01 lr: 0.000124 grad: 0.0804 (0.0850) loss: 0.8902 (0.8904) time: 0.1792 data: 0.0919 max mem: 8255 +Train: [9] [1900/6250] eta: 0:13:38 lr: 0.000124 grad: 0.0733 (0.0848) loss: 0.8915 (0.8903) time: 0.1053 data: 0.0177 max mem: 8255 +Train: [9] [2000/6250] eta: 0:13:19 lr: 0.000124 grad: 0.0782 (0.0846) loss: 0.8878 (0.8902) time: 0.1978 data: 0.1013 max mem: 8255 +Train: [9] [2100/6250] eta: 0:13:06 lr: 0.000124 grad: 0.0737 (0.0844) loss: 0.8866 (0.8902) time: 0.1108 data: 0.0004 max mem: 8255 +Train: [9] [2200/6250] eta: 0:12:46 lr: 0.000124 grad: 0.0794 (0.0843) loss: 0.8933 (0.8902) time: 0.1574 data: 0.0753 max mem: 8255 +Train: [9] [2300/6250] eta: 0:12:26 lr: 0.000124 grad: 0.0772 (0.0841) loss: 0.8918 (0.8901) time: 0.1201 data: 0.0314 max mem: 8255 +Train: [9] [2400/6250] eta: 0:12:02 lr: 0.000124 grad: 0.0802 (0.0842) loss: 0.8890 (0.8901) time: 0.1041 data: 0.0144 max mem: 8255 +Train: [9] [2500/6250] eta: 0:11:41 lr: 0.000124 grad: 0.0781 (0.0841) loss: 0.8874 (0.8900) time: 0.1955 data: 0.1316 max mem: 8255 +Train: [9] [2600/6250] eta: 0:11:18 lr: 0.000124 grad: 0.0750 (0.0839) loss: 0.8896 (0.8899) time: 0.1612 data: 0.0779 max mem: 8255 +Train: [9] [2700/6250] eta: 0:11:02 lr: 0.000124 grad: 0.0790 (0.0838) loss: 0.8874 (0.8898) time: 0.1305 data: 0.0401 max mem: 8255 +Train: [9] [2800/6250] eta: 0:10:42 lr: 0.000124 grad: 0.0803 (0.0836) loss: 0.8889 (0.8898) time: 0.2195 data: 0.1286 max mem: 8255 +Train: [9] [2900/6250] eta: 0:10:22 lr: 0.000124 grad: 0.0761 (0.0835) loss: 0.8880 (0.8898) time: 0.1437 data: 0.0459 max mem: 8255 +Train: [9] [3000/6250] eta: 0:10:01 lr: 0.000124 grad: 0.0788 (0.0835) loss: 0.8904 (0.8898) time: 0.1648 data: 0.0945 max mem: 8255 +Train: [9] [3100/6250] eta: 0:09:39 lr: 0.000124 grad: 0.0730 (0.0835) loss: 0.8952 (0.8898) time: 0.1268 data: 0.0454 max mem: 8255 +Train: [9] [3200/6250] eta: 0:09:19 lr: 0.000124 grad: 0.0782 (0.0836) loss: 0.8902 (0.8898) time: 0.1983 data: 0.1259 max mem: 8255 +Train: [9] [3300/6250] eta: 0:08:58 lr: 0.000124 grad: 0.0732 (0.0835) loss: 0.8931 (0.8898) time: 0.1605 data: 0.0890 max mem: 8255 +Train: [9] [3400/6250] eta: 0:08:38 lr: 0.000124 grad: 0.0818 (0.0835) loss: 0.8906 (0.8898) time: 0.1557 data: 0.0848 max mem: 8255 +Train: [9] [3500/6250] eta: 0:08:19 lr: 0.000124 grad: 0.0779 (0.0834) loss: 0.8882 (0.8899) time: 0.1681 data: 0.0874 max mem: 8255 +Train: [9] [3600/6250] eta: 0:08:00 lr: 0.000124 grad: 0.0831 (0.0834) loss: 0.8920 (0.8899) time: 0.1985 data: 0.1224 max mem: 8255 +Train: [9] [3700/6250] eta: 0:07:40 lr: 0.000124 grad: 0.0782 (0.0833) loss: 0.8895 (0.8899) time: 0.1772 data: 0.1071 max mem: 8255 +Train: [9] [3800/6250] eta: 0:07:21 lr: 0.000124 grad: 0.0842 (0.0834) loss: 0.8927 (0.8899) time: 0.1720 data: 0.0914 max mem: 8255 +Train: [9] [3900/6250] eta: 0:07:02 lr: 0.000124 grad: 0.0855 (0.0834) loss: 0.8822 (0.8898) time: 0.1554 data: 0.0938 max mem: 8255 +Train: [9] [4000/6250] eta: 0:06:43 lr: 0.000124 grad: 0.0864 (0.0835) loss: 0.8903 (0.8898) time: 0.1457 data: 0.0810 max mem: 8255 +Train: [9] [4100/6250] eta: 0:06:24 lr: 0.000124 grad: 0.0782 (0.0835) loss: 0.8892 (0.8897) time: 0.1522 data: 0.0675 max mem: 8255 +Train: [9] [4200/6250] eta: 0:06:05 lr: 0.000124 grad: 0.0863 (0.0836) loss: 0.8870 (0.8897) time: 0.1575 data: 0.0814 max mem: 8255 +Train: [9] [4300/6250] eta: 0:05:46 lr: 0.000124 grad: 0.0840 (0.0837) loss: 0.8906 (0.8896) time: 0.1544 data: 0.0852 max mem: 8255 +Train: [9] [4400/6250] eta: 0:05:28 lr: 0.000124 grad: 0.0761 (0.0837) loss: 0.8909 (0.8896) time: 0.1639 data: 0.0814 max mem: 8255 +Train: [9] [4500/6250] eta: 0:05:09 lr: 0.000124 grad: 0.0816 (0.0836) loss: 0.8908 (0.8896) time: 0.1635 data: 0.0896 max mem: 8255 +Train: [9] [4600/6250] eta: 0:04:51 lr: 0.000124 grad: 0.0814 (0.0837) loss: 0.8819 (0.8896) time: 0.2249 data: 0.1506 max mem: 8255 +Train: [9] [4700/6250] eta: 0:04:32 lr: 0.000124 grad: 0.0876 (0.0837) loss: 0.8868 (0.8896) time: 0.1351 data: 0.0644 max mem: 8255 +Train: [9] [4800/6250] eta: 0:04:14 lr: 0.000124 grad: 0.0733 (0.0837) loss: 0.8904 (0.8896) time: 0.1470 data: 0.0634 max mem: 8255 +Train: [9] [4900/6250] eta: 0:03:57 lr: 0.000124 grad: 0.0837 (0.0837) loss: 0.8938 (0.8896) time: 0.2020 data: 0.1260 max mem: 8255 +Train: [9] [5000/6250] eta: 0:03:39 lr: 0.000124 grad: 0.0760 (0.0837) loss: 0.8915 (0.8897) time: 0.1926 data: 0.1059 max mem: 8255 +Train: [9] [5100/6250] eta: 0:03:22 lr: 0.000124 grad: 0.0799 (0.0836) loss: 0.8895 (0.8897) time: 0.2302 data: 0.1528 max mem: 8255 +Train: [9] [5200/6250] eta: 0:03:04 lr: 0.000124 grad: 0.0854 (0.0836) loss: 0.8959 (0.8898) time: 0.2235 data: 0.1495 max mem: 8255 +Train: [9] [5300/6250] eta: 0:02:47 lr: 0.000124 grad: 0.0783 (0.0835) loss: 0.8916 (0.8898) time: 0.1960 data: 0.1130 max mem: 8255 +Train: [9] [5400/6250] eta: 0:02:29 lr: 0.000124 grad: 0.0688 (0.0834) loss: 0.8957 (0.8898) time: 0.1627 data: 0.0797 max mem: 8255 +Train: [9] [5500/6250] eta: 0:02:11 lr: 0.000124 grad: 0.0785 (0.0834) loss: 0.8938 (0.8898) time: 0.1927 data: 0.1106 max mem: 8255 +Train: [9] [5600/6250] eta: 0:01:54 lr: 0.000124 grad: 0.0741 (0.0833) loss: 0.8933 (0.8899) time: 0.0935 data: 0.0003 max mem: 8255 +Train: [9] [5700/6250] eta: 0:01:36 lr: 0.000124 grad: 0.0740 (0.0833) loss: 0.8923 (0.8899) time: 0.1451 data: 0.0757 max mem: 8255 +Train: [9] [5800/6250] eta: 0:01:19 lr: 0.000124 grad: 0.0794 (0.0833) loss: 0.8912 (0.8899) time: 0.1904 data: 0.1141 max mem: 8255 +Train: [9] [5900/6250] eta: 0:01:01 lr: 0.000124 grad: 0.0788 (0.0833) loss: 0.8906 (0.8899) time: 0.1723 data: 0.0923 max mem: 8255 +Train: [9] [6000/6250] eta: 0:00:43 lr: 0.000124 grad: 0.0761 (0.0833) loss: 0.8885 (0.8899) time: 0.1730 data: 0.0983 max mem: 8255 +Train: [9] [6100/6250] eta: 0:00:26 lr: 0.000124 grad: 0.0778 (0.0834) loss: 0.8929 (0.8898) time: 0.1739 data: 0.0786 max mem: 8255 +Train: [9] [6200/6250] eta: 0:00:08 lr: 0.000124 grad: 0.0742 (0.0834) loss: 0.8842 (0.8898) time: 0.1555 data: 0.0684 max mem: 8255 +Train: [9] [6249/6250] eta: 0:00:00 lr: 0.000124 grad: 0.0758 (0.0834) loss: 0.8908 (0.8898) time: 0.1891 data: 0.1127 max mem: 8255 +Train: [9] Total time: 0:18:27 (0.1773 s / it) +Averaged stats: lr: 0.000124 grad: 0.0758 (0.0834) loss: 0.8908 (0.8898) +Eval (hcp-train-subset): [9] [ 0/62] eta: 0:08:44 loss: 0.9095 (0.9095) time: 8.4585 data: 8.4326 max mem: 8255 +Eval (hcp-train-subset): [9] [61/62] eta: 0:00:00 loss: 0.9008 (0.8990) time: 0.1679 data: 0.1457 max mem: 8255 +Eval (hcp-train-subset): [9] Total time: 0:00:16 (0.2608 s / it) +Averaged stats (hcp-train-subset): loss: 0.9008 (0.8990) +Making plots (hcp-train-subset): example=54 +Eval (hcp-val): [9] [ 0/62] eta: 0:04:34 loss: 0.8912 (0.8912) time: 4.4293 data: 4.3553 max mem: 8255 +Eval (hcp-val): [9] [61/62] eta: 0:00:00 loss: 0.8943 (0.8943) time: 0.1411 data: 0.1200 max mem: 8255 +Eval (hcp-val): [9] Total time: 0:00:16 (0.2664 s / it) +Averaged stats (hcp-val): loss: 0.8943 (0.8943) +Making plots (hcp-val): example=9 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +Train: [10] [ 0/6250] eta: 11:16:19 lr: 0.000124 grad: 0.0702 (0.0702) loss: 0.9078 (0.9078) time: 6.4927 data: 6.3805 max mem: 8255 +Train: [10] [ 100/6250] eta: 0:25:55 lr: 0.000124 grad: 0.0825 (0.0871) loss: 0.8891 (0.8977) time: 0.2349 data: 0.1316 max mem: 8255 +Train: [10] [ 200/6250] eta: 0:22:07 lr: 0.000124 grad: 0.0996 (0.0941) loss: 0.8738 (0.8871) time: 0.1873 data: 0.1088 max mem: 8255 +Train: [10] [ 300/6250] eta: 0:21:27 lr: 0.000124 grad: 0.0788 (0.0924) loss: 0.8820 (0.8849) time: 0.2290 data: 0.1383 max mem: 8255 +Train: [10] [ 400/6250] eta: 0:20:09 lr: 0.000124 grad: 0.0803 (0.0912) loss: 0.8850 (0.8849) time: 0.1636 data: 0.0704 max mem: 8255 +Train: [10] [ 500/6250] eta: 0:19:11 lr: 0.000124 grad: 0.0786 (0.0905) loss: 0.8898 (0.8857) time: 0.1785 data: 0.0997 max mem: 8255 +Train: [10] [ 600/6250] eta: 0:19:12 lr: 0.000124 grad: 0.0767 (0.0899) loss: 0.8856 (0.8858) time: 0.3574 data: 0.1770 max mem: 8255 +Train: [10] [ 700/6250] eta: 0:18:23 lr: 0.000124 grad: 0.0785 (0.0891) loss: 0.8890 (0.8858) time: 0.1236 data: 0.0296 max mem: 8255 +Train: [10] [ 800/6250] eta: 0:17:52 lr: 0.000124 grad: 0.0885 (0.0885) loss: 0.8797 (0.8856) time: 0.1499 data: 0.0597 max mem: 8255 +Train: [10] [ 900/6250] eta: 0:17:22 lr: 0.000124 grad: 0.0817 (0.0883) loss: 0.8826 (0.8853) time: 0.1835 data: 0.0896 max mem: 8255 +Train: [10] [1000/6250] eta: 0:16:51 lr: 0.000124 grad: 0.0749 (0.0877) loss: 0.8805 (0.8852) time: 0.1677 data: 0.0783 max mem: 8255 +Train: [10] [1100/6250] eta: 0:16:20 lr: 0.000124 grad: 0.0826 (0.0874) loss: 0.8862 (0.8853) time: 0.1731 data: 0.0918 max mem: 8255 +Train: [10] [1200/6250] eta: 0:15:55 lr: 0.000124 grad: 0.0815 (0.0873) loss: 0.8841 (0.8852) time: 0.2430 data: 0.1792 max mem: 8255 +Train: [10] [1300/6250] eta: 0:15:27 lr: 0.000124 grad: 0.0788 (0.0873) loss: 0.8859 (0.8849) time: 0.1449 data: 0.0690 max mem: 8255 +Train: [10] [1400/6250] eta: 0:15:00 lr: 0.000124 grad: 0.0841 (0.0871) loss: 0.8810 (0.8848) time: 0.1432 data: 0.0603 max mem: 8255 +Train: [10] [1500/6250] eta: 0:14:36 lr: 0.000124 grad: 0.0780 (0.0869) loss: 0.8819 (0.8847) time: 0.1837 data: 0.1143 max mem: 8255 +Train: [10] [1600/6250] eta: 0:14:17 lr: 0.000124 grad: 0.0836 (0.0868) loss: 0.8858 (0.8846) time: 0.1500 data: 0.0573 max mem: 8255 +Train: [10] [1700/6250] eta: 0:14:01 lr: 0.000124 grad: 0.0853 (0.0866) loss: 0.8856 (0.8847) time: 0.2099 data: 0.1322 max mem: 8255 +Train: [10] [1800/6250] eta: 0:13:40 lr: 0.000124 grad: 0.0776 (0.0862) loss: 0.8839 (0.8847) time: 0.1591 data: 0.0819 max mem: 8255 +Train: [10] [1900/6250] eta: 0:13:20 lr: 0.000124 grad: 0.0786 (0.0862) loss: 0.8899 (0.8846) time: 0.2144 data: 0.1377 max mem: 8255 +Train: [10] [2000/6250] eta: 0:13:01 lr: 0.000124 grad: 0.0785 (0.0861) loss: 0.8888 (0.8847) time: 0.1661 data: 0.0872 max mem: 8255 +Train: [10] [2100/6250] eta: 0:12:43 lr: 0.000124 grad: 0.0745 (0.0858) loss: 0.8870 (0.8847) time: 0.2049 data: 0.1109 max mem: 8255 +Train: [10] [2200/6250] eta: 0:12:20 lr: 0.000124 grad: 0.0781 (0.0855) loss: 0.8877 (0.8847) time: 0.1374 data: 0.0558 max mem: 8255 +Train: [10] [2300/6250] eta: 0:12:01 lr: 0.000124 grad: 0.0771 (0.0855) loss: 0.8883 (0.8847) time: 0.1169 data: 0.0100 max mem: 8255 +Train: [10] [2400/6250] eta: 0:11:46 lr: 0.000124 grad: 0.0775 (0.0854) loss: 0.8840 (0.8847) time: 0.1323 data: 0.0565 max mem: 8255 +Train: [10] [2500/6250] eta: 0:11:24 lr: 0.000124 grad: 0.0863 (0.0853) loss: 0.8815 (0.8848) time: 0.1523 data: 0.0750 max mem: 8255 +Train: [10] [2600/6250] eta: 0:11:02 lr: 0.000124 grad: 0.0773 (0.0852) loss: 0.8872 (0.8848) time: 0.1519 data: 0.0830 max mem: 8255 +Train: [10] [2700/6250] eta: 0:10:41 lr: 0.000124 grad: 0.0778 (0.0851) loss: 0.8864 (0.8849) time: 0.1722 data: 0.0959 max mem: 8255 +Train: [10] [2800/6250] eta: 0:10:20 lr: 0.000124 grad: 0.0853 (0.0850) loss: 0.8851 (0.8850) time: 0.1524 data: 0.0701 max mem: 8255 +Train: [10] [2900/6250] eta: 0:10:00 lr: 0.000124 grad: 0.0753 (0.0849) loss: 0.8876 (0.8851) time: 0.1517 data: 0.0661 max mem: 8255 +Train: [10] [3000/6250] eta: 0:09:40 lr: 0.000124 grad: 0.0739 (0.0847) loss: 0.8840 (0.8852) time: 0.1694 data: 0.0876 max mem: 8255 +Train: [10] [3100/6250] eta: 0:09:20 lr: 0.000124 grad: 0.0740 (0.0845) loss: 0.8890 (0.8854) time: 0.1566 data: 0.0789 max mem: 8255 +Train: [10] [3200/6250] eta: 0:08:59 lr: 0.000124 grad: 0.0736 (0.0844) loss: 0.8854 (0.8855) time: 0.1437 data: 0.0644 max mem: 8255 +Train: [10] [3300/6250] eta: 0:08:40 lr: 0.000124 grad: 0.0749 (0.0841) loss: 0.8919 (0.8856) time: 0.1337 data: 0.0549 max mem: 8255 +Train: [10] [3400/6250] eta: 0:08:20 lr: 0.000124 grad: 0.0752 (0.0839) loss: 0.8925 (0.8857) time: 0.1373 data: 0.0541 max mem: 8255 +Train: [10] [3500/6250] eta: 0:08:01 lr: 0.000124 grad: 0.0790 (0.0837) loss: 0.8912 (0.8858) time: 0.1734 data: 0.1116 max mem: 8255 +Train: [10] [3600/6250] eta: 0:07:43 lr: 0.000124 grad: 0.0717 (0.0835) loss: 0.8903 (0.8860) time: 0.1704 data: 0.0851 max mem: 8255 +Train: [10] [3700/6250] eta: 0:07:25 lr: 0.000124 grad: 0.0681 (0.0833) loss: 0.8951 (0.8861) time: 0.1645 data: 0.0849 max mem: 8255 +Train: [10] [3800/6250] eta: 0:07:07 lr: 0.000124 grad: 0.0722 (0.0831) loss: 0.8917 (0.8863) time: 0.1920 data: 0.1184 max mem: 8255 +Train: [10] [3900/6250] eta: 0:06:48 lr: 0.000124 grad: 0.0711 (0.0830) loss: 0.8923 (0.8863) time: 0.1592 data: 0.0843 max mem: 8255 +Train: [10] [4000/6250] eta: 0:06:30 lr: 0.000124 grad: 0.0747 (0.0828) loss: 0.8918 (0.8864) time: 0.1482 data: 0.0585 max mem: 8255 +Train: [10] [4100/6250] eta: 0:06:12 lr: 0.000124 grad: 0.0716 (0.0827) loss: 0.8895 (0.8865) time: 0.1852 data: 0.1055 max mem: 8255 +Train: [10] [4200/6250] eta: 0:05:55 lr: 0.000124 grad: 0.0698 (0.0825) loss: 0.8918 (0.8866) time: 0.1937 data: 0.1272 max mem: 8255 +Train: [10] [4300/6250] eta: 0:05:39 lr: 0.000124 grad: 0.0759 (0.0824) loss: 0.8907 (0.8867) time: 0.1185 data: 0.0003 max mem: 8255 +Train: [10] [4400/6250] eta: 0:05:23 lr: 0.000124 grad: 0.0782 (0.0822) loss: 0.8923 (0.8868) time: 0.1794 data: 0.1000 max mem: 8255 +Train: [10] [4500/6250] eta: 0:05:07 lr: 0.000124 grad: 0.0730 (0.0821) loss: 0.8912 (0.8869) time: 0.2153 data: 0.1495 max mem: 8255 +Train: [10] [4600/6250] eta: 0:04:51 lr: 0.000124 grad: 0.0739 (0.0819) loss: 0.8939 (0.8870) time: 0.1725 data: 0.0895 max mem: 8255 +Train: [10] [4700/6250] eta: 0:04:34 lr: 0.000124 grad: 0.0725 (0.0818) loss: 0.8929 (0.8871) time: 0.1040 data: 0.0056 max mem: 8255 +Train: [10] [4800/6250] eta: 0:04:16 lr: 0.000124 grad: 0.0704 (0.0817) loss: 0.8882 (0.8872) time: 0.2025 data: 0.1333 max mem: 8255 +Train: [10] [4900/6250] eta: 0:03:58 lr: 0.000124 grad: 0.0710 (0.0815) loss: 0.8885 (0.8872) time: 0.1758 data: 0.0854 max mem: 8255 +Train: [10] [5000/6250] eta: 0:03:41 lr: 0.000124 grad: 0.0712 (0.0814) loss: 0.8863 (0.8873) time: 0.1861 data: 0.0948 max mem: 8255 +Train: [10] [5100/6250] eta: 0:03:24 lr: 0.000124 grad: 0.0689 (0.0813) loss: 0.8974 (0.8874) time: 0.2830 data: 0.1792 max mem: 8255 +Train: [10] [5200/6250] eta: 0:03:06 lr: 0.000124 grad: 0.0712 (0.0812) loss: 0.8929 (0.8875) time: 0.1720 data: 0.0977 max mem: 8255 +Train: [10] [5300/6250] eta: 0:02:48 lr: 0.000124 grad: 0.0819 (0.0811) loss: 0.8893 (0.8875) time: 0.2390 data: 0.1526 max mem: 8255 +Train: [10] [5400/6250] eta: 0:02:31 lr: 0.000124 grad: 0.0742 (0.0810) loss: 0.8896 (0.8875) time: 0.1459 data: 0.0597 max mem: 8255 +Train: [10] [5500/6250] eta: 0:02:13 lr: 0.000124 grad: 0.0752 (0.0809) loss: 0.8910 (0.8876) time: 0.1692 data: 0.0950 max mem: 8255 +Train: [10] [5600/6250] eta: 0:01:55 lr: 0.000124 grad: 0.0728 (0.0808) loss: 0.8873 (0.8876) time: 0.2901 data: 0.2044 max mem: 8255 +Train: [10] [5700/6250] eta: 0:01:38 lr: 0.000124 grad: 0.0699 (0.0807) loss: 0.8886 (0.8877) time: 0.1474 data: 0.0726 max mem: 8255 +Train: [10] [5800/6250] eta: 0:01:20 lr: 0.000124 grad: 0.0737 (0.0807) loss: 0.8877 (0.8877) time: 0.1629 data: 0.0823 max mem: 8255 +Train: [10] [5900/6250] eta: 0:01:02 lr: 0.000124 grad: 0.0686 (0.0806) loss: 0.8938 (0.8878) time: 0.1679 data: 0.0869 max mem: 8255 +Train: [10] [6000/6250] eta: 0:00:44 lr: 0.000124 grad: 0.0743 (0.0805) loss: 0.8887 (0.8877) time: 0.1576 data: 0.0709 max mem: 8255 +Train: [10] [6100/6250] eta: 0:00:26 lr: 0.000124 grad: 0.0723 (0.0804) loss: 0.8863 (0.8877) time: 0.1369 data: 0.0593 max mem: 8255 +Train: [10] [6200/6250] eta: 0:00:08 lr: 0.000124 grad: 0.0690 (0.0804) loss: 0.8880 (0.8878) time: 0.2777 data: 0.1760 max mem: 8255 +Train: [10] [6249/6250] eta: 0:00:00 lr: 0.000124 grad: 0.0763 (0.0803) loss: 0.8879 (0.8878) time: 0.1970 data: 0.1145 max mem: 8255 +Train: [10] Total time: 0:18:42 (0.1796 s / it) +Averaged stats: lr: 0.000124 grad: 0.0763 (0.0803) loss: 0.8879 (0.8878) +Eval (hcp-train-subset): [10] [ 0/62] eta: 0:08:36 loss: 0.9068 (0.9068) time: 8.3271 data: 8.3002 max mem: 8255 +Eval (hcp-train-subset): [10] [61/62] eta: 0:00:00 loss: 0.8972 (0.8969) time: 0.1323 data: 0.1099 max mem: 8255 +Eval (hcp-train-subset): [10] Total time: 0:00:16 (0.2621 s / it) +Averaged stats (hcp-train-subset): loss: 0.8972 (0.8969) +Eval (hcp-val): [10] [ 0/62] eta: 0:06:31 loss: 0.8870 (0.8870) time: 6.3098 data: 6.2754 max mem: 8255 +Eval (hcp-val): [10] [61/62] eta: 0:00:00 loss: 0.8901 (0.8924) time: 0.1321 data: 0.1113 max mem: 8255 +Eval (hcp-val): [10] Total time: 0:00:15 (0.2551 s / it) +Averaged stats (hcp-val): loss: 0.8901 (0.8924) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +Train: [11] [ 0/6250] eta: 8:31:27 lr: 0.000124 grad: 0.0545 (0.0545) loss: 0.9357 (0.9357) time: 4.9101 data: 4.7248 max mem: 8255 +Train: [11] [ 100/6250] eta: 0:36:05 lr: 0.000124 grad: 0.0819 (0.0953) loss: 0.8931 (0.8893) time: 0.6004 data: 0.5006 max mem: 8255 +Train: [11] [ 200/6250] eta: 0:27:03 lr: 0.000124 grad: 0.0903 (0.0884) loss: 0.8906 (0.8904) time: 0.1738 data: 0.0820 max mem: 8255 +Train: [11] [ 300/6250] eta: 0:24:41 lr: 0.000124 grad: 0.0730 (0.0857) loss: 0.8892 (0.8893) time: 0.1146 data: 0.0047 max mem: 8255 +Train: [11] [ 400/6250] eta: 0:22:55 lr: 0.000124 grad: 0.0680 (0.0837) loss: 0.8949 (0.8891) time: 0.1915 data: 0.1068 max mem: 8255 +Train: [11] [ 500/6250] eta: 0:21:28 lr: 0.000124 grad: 0.0823 (0.0832) loss: 0.8934 (0.8889) time: 0.1803 data: 0.1075 max mem: 8255 +Train: [11] [ 600/6250] eta: 0:20:23 lr: 0.000124 grad: 0.0755 (0.0822) loss: 0.8865 (0.8884) time: 0.1889 data: 0.1075 max mem: 8255 +Train: [11] [ 700/6250] eta: 0:19:52 lr: 0.000124 grad: 0.0824 (0.0819) loss: 0.8858 (0.8876) time: 0.2905 data: 0.1793 max mem: 8255 +Train: [11] [ 800/6250] eta: 0:19:24 lr: 0.000124 grad: 0.0815 (0.0815) loss: 0.8823 (0.8873) time: 0.1841 data: 0.1094 max mem: 8255 +Train: [11] [ 900/6250] eta: 0:18:34 lr: 0.000124 grad: 0.0761 (0.0814) loss: 0.8898 (0.8872) time: 0.1751 data: 0.0782 max mem: 8255 +Train: [11] [1000/6250] eta: 0:17:59 lr: 0.000124 grad: 0.0729 (0.0809) loss: 0.8851 (0.8872) time: 0.1635 data: 0.0670 max mem: 8255 +Train: [11] [1100/6250] eta: 0:17:20 lr: 0.000124 grad: 0.0833 (0.0807) loss: 0.8880 (0.8872) time: 0.1117 data: 0.0431 max mem: 8255 +Train: [11] [1200/6250] eta: 0:17:07 lr: 0.000124 grad: 0.0803 (0.0806) loss: 0.8856 (0.8870) time: 0.1353 data: 0.0370 max mem: 8255 +Train: [11] [1300/6250] eta: 0:16:29 lr: 0.000124 grad: 0.0769 (0.0807) loss: 0.8830 (0.8869) time: 0.1633 data: 0.0912 max mem: 8255 +Train: [11] [1400/6250] eta: 0:16:00 lr: 0.000124 grad: 0.0758 (0.0806) loss: 0.8856 (0.8868) time: 0.2008 data: 0.1247 max mem: 8255 +Train: [11] [1500/6250] eta: 0:15:32 lr: 0.000124 grad: 0.0749 (0.0805) loss: 0.8873 (0.8866) time: 0.1637 data: 0.0851 max mem: 8255 +Train: [11] [1600/6250] eta: 0:15:09 lr: 0.000124 grad: 0.0750 (0.0804) loss: 0.8878 (0.8865) time: 0.1856 data: 0.1057 max mem: 8255 +Train: [11] [1700/6250] eta: 0:14:48 lr: 0.000124 grad: 0.0776 (0.0802) loss: 0.8865 (0.8865) time: 0.2074 data: 0.1378 max mem: 8255 +Train: [11] [1800/6250] eta: 0:14:27 lr: 0.000124 grad: 0.0737 (0.0799) loss: 0.8883 (0.8865) time: 0.1953 data: 0.1140 max mem: 8255 +Train: [11] [1900/6250] eta: 0:14:04 lr: 0.000124 grad: 0.0798 (0.0800) loss: 0.8837 (0.8864) time: 0.1880 data: 0.1043 max mem: 8255 +Train: [11] [2000/6250] eta: 0:13:44 lr: 0.000124 grad: 0.0720 (0.0797) loss: 0.8913 (0.8864) time: 0.2860 data: 0.1862 max mem: 8255 +Train: [11] [2100/6250] eta: 0:13:25 lr: 0.000124 grad: 0.0727 (0.0799) loss: 0.8881 (0.8863) time: 0.1547 data: 0.0620 max mem: 8255 +Train: [11] [2200/6250] eta: 0:13:06 lr: 0.000124 grad: 0.0709 (0.0797) loss: 0.8870 (0.8863) time: 0.1357 data: 0.0576 max mem: 8255 +Train: [11] [2300/6250] eta: 0:12:37 lr: 0.000124 grad: 0.0725 (0.0796) loss: 0.8855 (0.8863) time: 0.1544 data: 0.0744 max mem: 8255 +Train: [11] [2400/6250] eta: 0:12:22 lr: 0.000124 grad: 0.0774 (0.0795) loss: 0.8843 (0.8863) time: 0.1630 data: 0.0877 max mem: 8255 +Train: [11] [2500/6250] eta: 0:12:01 lr: 0.000124 grad: 0.0695 (0.0794) loss: 0.8882 (0.8863) time: 0.1095 data: 0.0296 max mem: 8255 +Train: [11] [2600/6250] eta: 0:11:37 lr: 0.000124 grad: 0.0742 (0.0794) loss: 0.8856 (0.8862) time: 0.1841 data: 0.1108 max mem: 8255 +Train: [11] [2700/6250] eta: 0:11:17 lr: 0.000124 grad: 0.0773 (0.0793) loss: 0.8836 (0.8863) time: 0.1169 data: 0.0513 max mem: 8255 +Train: [11] [2800/6250] eta: 0:10:59 lr: 0.000124 grad: 0.0764 (0.0792) loss: 0.8850 (0.8863) time: 0.2696 data: 0.2017 max mem: 8255 +Train: [11] [2900/6250] eta: 0:10:36 lr: 0.000124 grad: 0.0723 (0.0791) loss: 0.8883 (0.8863) time: 0.1583 data: 0.0942 max mem: 8255 +Train: [11] [3000/6250] eta: 0:10:17 lr: 0.000124 grad: 0.0693 (0.0790) loss: 0.8864 (0.8863) time: 0.1010 data: 0.0002 max mem: 8255 +Train: [11] [3100/6250] eta: 0:09:55 lr: 0.000124 grad: 0.0715 (0.0789) loss: 0.8868 (0.8863) time: 0.1904 data: 0.1186 max mem: 8255 +Train: [11] [3200/6250] eta: 0:09:35 lr: 0.000124 grad: 0.0733 (0.0788) loss: 0.8885 (0.8864) time: 0.1361 data: 0.0563 max mem: 8255 +Train: [11] [3300/6250] eta: 0:09:14 lr: 0.000124 grad: 0.0768 (0.0788) loss: 0.8872 (0.8864) time: 0.1840 data: 0.1089 max mem: 8255 +Train: [11] [3400/6250] eta: 0:08:52 lr: 0.000124 grad: 0.0737 (0.0788) loss: 0.8848 (0.8865) time: 0.1416 data: 0.0801 max mem: 8255 +Train: [11] [3500/6250] eta: 0:08:31 lr: 0.000124 grad: 0.0712 (0.0788) loss: 0.8860 (0.8864) time: 0.1491 data: 0.0649 max mem: 8255 +Train: [11] [3600/6250] eta: 0:08:10 lr: 0.000124 grad: 0.0743 (0.0788) loss: 0.8891 (0.8864) time: 0.1649 data: 0.0896 max mem: 8255 +Train: [11] [3700/6250] eta: 0:07:51 lr: 0.000124 grad: 0.0766 (0.0788) loss: 0.8889 (0.8864) time: 0.1258 data: 0.0532 max mem: 8255 +Train: [11] [3800/6250] eta: 0:07:31 lr: 0.000124 grad: 0.0775 (0.0788) loss: 0.8799 (0.8864) time: 0.1796 data: 0.0980 max mem: 8255 +Train: [11] [3900/6250] eta: 0:07:11 lr: 0.000124 grad: 0.0713 (0.0788) loss: 0.8850 (0.8863) time: 0.1089 data: 0.0253 max mem: 8255 +Train: [11] [4000/6250] eta: 0:06:53 lr: 0.000123 grad: 0.0729 (0.0788) loss: 0.8834 (0.8863) time: 0.2672 data: 0.0925 max mem: 8255 +Train: [11] [4100/6250] eta: 0:06:35 lr: 0.000123 grad: 0.0744 (0.0787) loss: 0.8920 (0.8863) time: 0.1740 data: 0.0564 max mem: 8255 +Train: [11] [4200/6250] eta: 0:06:18 lr: 0.000123 grad: 0.0727 (0.0787) loss: 0.8884 (0.8863) time: 0.1015 data: 0.0002 max mem: 8255 +Train: [11] [4300/6250] eta: 0:06:02 lr: 0.000123 grad: 0.0749 (0.0786) loss: 0.8816 (0.8862) time: 0.3825 data: 0.2951 max mem: 8255 +Train: [11] [4400/6250] eta: 0:05:43 lr: 0.000123 grad: 0.0722 (0.0786) loss: 0.8809 (0.8862) time: 0.1923 data: 0.1037 max mem: 8255 +Train: [11] [4500/6250] eta: 0:05:25 lr: 0.000123 grad: 0.0719 (0.0786) loss: 0.8877 (0.8862) time: 0.1280 data: 0.0108 max mem: 8255 +Train: [11] [4600/6250] eta: 0:05:06 lr: 0.000123 grad: 0.0741 (0.0785) loss: 0.8828 (0.8862) time: 0.1808 data: 0.0981 max mem: 8255 +Train: [11] [4700/6250] eta: 0:04:47 lr: 0.000123 grad: 0.0752 (0.0786) loss: 0.8887 (0.8861) time: 0.1833 data: 0.1044 max mem: 8255 +Train: [11] [4800/6250] eta: 0:04:29 lr: 0.000123 grad: 0.0789 (0.0786) loss: 0.8806 (0.8861) time: 0.2483 data: 0.1516 max mem: 8255 +Train: [11] [4900/6250] eta: 0:04:11 lr: 0.000123 grad: 0.0809 (0.0786) loss: 0.8800 (0.8861) time: 0.1741 data: 0.0814 max mem: 8255 +Train: [11] [5000/6250] eta: 0:03:52 lr: 0.000123 grad: 0.0796 (0.0787) loss: 0.8791 (0.8860) time: 0.1652 data: 0.0714 max mem: 8255 +Train: [11] [5100/6250] eta: 0:03:33 lr: 0.000123 grad: 0.0768 (0.0787) loss: 0.8816 (0.8859) time: 0.1092 data: 0.0033 max mem: 8255 +Train: [11] [5200/6250] eta: 0:03:15 lr: 0.000123 grad: 0.0776 (0.0787) loss: 0.8838 (0.8859) time: 0.1098 data: 0.0002 max mem: 8255 +Train: [11] [5300/6250] eta: 0:02:56 lr: 0.000123 grad: 0.0752 (0.0787) loss: 0.8801 (0.8858) time: 0.2322 data: 0.1546 max mem: 8255 +Train: [11] [5400/6250] eta: 0:02:37 lr: 0.000123 grad: 0.0750 (0.0787) loss: 0.8888 (0.8858) time: 0.1426 data: 0.0495 max mem: 8255 +Train: [11] [5500/6250] eta: 0:02:19 lr: 0.000123 grad: 0.0746 (0.0786) loss: 0.8837 (0.8858) time: 0.1389 data: 0.0306 max mem: 8255 +Train: [11] [5600/6250] eta: 0:02:00 lr: 0.000123 grad: 0.0782 (0.0786) loss: 0.8860 (0.8857) time: 0.1783 data: 0.0974 max mem: 8255 +Train: [11] [5700/6250] eta: 0:01:41 lr: 0.000123 grad: 0.0720 (0.0786) loss: 0.8856 (0.8857) time: 0.2637 data: 0.1856 max mem: 8255 +Train: [11] [5800/6250] eta: 0:01:23 lr: 0.000123 grad: 0.0727 (0.0787) loss: 0.8837 (0.8857) time: 0.1859 data: 0.0985 max mem: 8255 +Train: [11] [5900/6250] eta: 0:01:04 lr: 0.000123 grad: 0.0759 (0.0786) loss: 0.8836 (0.8857) time: 0.1530 data: 0.0673 max mem: 8255 +Train: [11] [6000/6250] eta: 0:00:46 lr: 0.000123 grad: 0.0748 (0.0786) loss: 0.8821 (0.8856) time: 0.1630 data: 0.0734 max mem: 8255 +Train: [11] [6100/6250] eta: 0:00:27 lr: 0.000123 grad: 0.0752 (0.0786) loss: 0.8882 (0.8856) time: 0.1866 data: 0.1044 max mem: 8255 +Train: [11] [6200/6250] eta: 0:00:09 lr: 0.000123 grad: 0.0818 (0.0786) loss: 0.8894 (0.8856) time: 0.2083 data: 0.1225 max mem: 8255 +Train: [11] [6249/6250] eta: 0:00:00 lr: 0.000123 grad: 0.0713 (0.0786) loss: 0.8885 (0.8856) time: 0.2697 data: 0.1652 max mem: 8255 +Train: [11] Total time: 0:19:24 (0.1863 s / it) +Averaged stats: lr: 0.000123 grad: 0.0713 (0.0786) loss: 0.8885 (0.8856) +Eval (hcp-train-subset): [11] [ 0/62] eta: 0:03:22 loss: 0.9038 (0.9038) time: 3.2717 data: 3.1660 max mem: 8255 +Eval (hcp-train-subset): [11] [61/62] eta: 0:00:00 loss: 0.8946 (0.8945) time: 0.1737 data: 0.1514 max mem: 8255 +Eval (hcp-train-subset): [11] Total time: 0:00:16 (0.2586 s / it) +Averaged stats (hcp-train-subset): loss: 0.8946 (0.8945) +Eval (hcp-val): [11] [ 0/62] eta: 0:04:57 loss: 0.8866 (0.8866) time: 4.7951 data: 4.7671 max mem: 8255 +Eval (hcp-val): [11] [61/62] eta: 0:00:00 loss: 0.8880 (0.8905) time: 0.1553 data: 0.1336 max mem: 8255 +Eval (hcp-val): [11] Total time: 0:00:15 (0.2490 s / it) +Averaged stats (hcp-val): loss: 0.8880 (0.8905) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +Train: [12] [ 0/6250] eta: 9:47:18 lr: 0.000123 grad: 0.0994 (0.0994) loss: 0.9122 (0.9122) time: 5.6381 data: 5.4713 max mem: 8255 +Train: [12] [ 100/6250] eta: 0:24:59 lr: 0.000123 grad: 0.0902 (0.1042) loss: 0.8775 (0.8845) time: 0.2217 data: 0.1336 max mem: 8255 +Train: [12] [ 200/6250] eta: 0:23:36 lr: 0.000123 grad: 0.0820 (0.1010) loss: 0.8868 (0.8836) time: 0.1769 data: 0.1038 max mem: 8255 +Train: [12] [ 300/6250] eta: 0:21:09 lr: 0.000123 grad: 0.0827 (0.1048) loss: 0.8715 (0.8809) time: 0.1937 data: 0.1046 max mem: 8255 +Train: [12] [ 400/6250] eta: 0:20:06 lr: 0.000123 grad: 0.0750 (0.1017) loss: 0.8787 (0.8798) time: 0.2323 data: 0.1450 max mem: 8255 +Train: [12] [ 500/6250] eta: 0:20:09 lr: 0.000123 grad: 0.0741 (0.0976) loss: 0.8769 (0.8795) time: 0.2028 data: 0.0799 max mem: 8255 +Train: [12] [ 600/6250] eta: 0:19:22 lr: 0.000123 grad: 0.0732 (0.0944) loss: 0.8827 (0.8794) time: 0.1426 data: 0.0370 max mem: 8255 +Train: [12] [ 700/6250] eta: 0:18:58 lr: 0.000123 grad: 0.0776 (0.0931) loss: 0.8890 (0.8797) time: 0.1497 data: 0.0351 max mem: 8255 +Train: [12] [ 800/6250] eta: 0:19:00 lr: 0.000123 grad: 0.0814 (0.0913) loss: 0.8862 (0.8800) time: 0.1491 data: 0.0712 max mem: 8255 +Train: [12] [ 900/6250] eta: 0:18:50 lr: 0.000123 grad: 0.0734 (0.0898) loss: 0.8812 (0.8803) time: 0.2273 data: 0.1231 max mem: 8255 +Train: [12] [1000/6250] eta: 0:18:21 lr: 0.000123 grad: 0.0774 (0.0888) loss: 0.8778 (0.8803) time: 0.0969 data: 0.0046 max mem: 8255 +Train: [12] [1100/6250] eta: 0:17:53 lr: 0.000123 grad: 0.0693 (0.0876) loss: 0.8805 (0.8804) time: 0.1222 data: 0.0114 max mem: 8255 +Train: [12] [1200/6250] eta: 0:17:13 lr: 0.000123 grad: 0.0747 (0.0865) loss: 0.8835 (0.8803) time: 0.1862 data: 0.0722 max mem: 8255 +Train: [12] [1300/6250] eta: 0:16:39 lr: 0.000123 grad: 0.0776 (0.0857) loss: 0.8742 (0.8802) time: 0.2179 data: 0.1381 max mem: 8255 +Train: [12] [1400/6250] eta: 0:16:07 lr: 0.000123 grad: 0.0764 (0.0850) loss: 0.8793 (0.8803) time: 0.1843 data: 0.1089 max mem: 8255 +Train: [12] [1500/6250] eta: 0:15:43 lr: 0.000123 grad: 0.0771 (0.0847) loss: 0.8802 (0.8802) time: 0.1765 data: 0.0971 max mem: 8255 +Train: [12] [1600/6250] eta: 0:15:13 lr: 0.000123 grad: 0.0708 (0.0842) loss: 0.8809 (0.8802) time: 0.1989 data: 0.1099 max mem: 8255 +Train: [12] [1700/6250] eta: 0:14:48 lr: 0.000123 grad: 0.0734 (0.0838) loss: 0.8850 (0.8801) time: 0.2122 data: 0.1291 max mem: 8255 +Train: [12] [1800/6250] eta: 0:14:28 lr: 0.000123 grad: 0.0697 (0.0836) loss: 0.8849 (0.8801) time: 0.1978 data: 0.1187 max mem: 8255 +Train: [12] [1900/6250] eta: 0:14:00 lr: 0.000123 grad: 0.0723 (0.0834) loss: 0.8785 (0.8801) time: 0.1721 data: 0.0836 max mem: 8255 +Train: [12] [2000/6250] eta: 0:13:33 lr: 0.000123 grad: 0.0771 (0.0831) loss: 0.8823 (0.8801) time: 0.1664 data: 0.0760 max mem: 8255 +Train: [12] [2100/6250] eta: 0:13:06 lr: 0.000123 grad: 0.0786 (0.0829) loss: 0.8814 (0.8801) time: 0.1296 data: 0.0422 max mem: 8255 +Train: [12] [2200/6250] eta: 0:12:41 lr: 0.000123 grad: 0.0801 (0.0827) loss: 0.8762 (0.8801) time: 0.1169 data: 0.0327 max mem: 8255 +Train: [12] [2300/6250] eta: 0:12:15 lr: 0.000123 grad: 0.0812 (0.0826) loss: 0.8831 (0.8801) time: 0.1689 data: 0.0800 max mem: 8255 +Train: [12] [2400/6250] eta: 0:11:53 lr: 0.000123 grad: 0.0801 (0.0825) loss: 0.8809 (0.8800) time: 0.2651 data: 0.1905 max mem: 8255 +Train: [12] [2500/6250] eta: 0:11:28 lr: 0.000123 grad: 0.0723 (0.0823) loss: 0.8793 (0.8801) time: 0.1447 data: 0.0737 max mem: 8255 +Train: [12] [2600/6250] eta: 0:11:11 lr: 0.000123 grad: 0.0714 (0.0821) loss: 0.8802 (0.8801) time: 0.2191 data: 0.1543 max mem: 8255 +Train: [12] [2700/6250] eta: 0:10:49 lr: 0.000123 grad: 0.0755 (0.0820) loss: 0.8834 (0.8801) time: 0.1597 data: 0.0792 max mem: 8255 +Train: [12] [2800/6250] eta: 0:10:29 lr: 0.000123 grad: 0.0744 (0.0819) loss: 0.8801 (0.8802) time: 0.1984 data: 0.1247 max mem: 8255 +Train: [12] [2900/6250] eta: 0:10:14 lr: 0.000123 grad: 0.0749 (0.0816) loss: 0.8871 (0.8804) time: 0.3138 data: 0.2314 max mem: 8255 +Train: [12] [3000/6250] eta: 0:09:52 lr: 0.000123 grad: 0.0758 (0.0814) loss: 0.8806 (0.8805) time: 0.1837 data: 0.0869 max mem: 8255 +Train: [12] [3100/6250] eta: 0:09:31 lr: 0.000123 grad: 0.0766 (0.0813) loss: 0.8801 (0.8806) time: 0.1653 data: 0.0947 max mem: 8255 +Train: [12] [3200/6250] eta: 0:09:12 lr: 0.000123 grad: 0.0717 (0.0812) loss: 0.8828 (0.8808) time: 0.1626 data: 0.0721 max mem: 8255 +Train: [12] [3300/6250] eta: 0:08:53 lr: 0.000123 grad: 0.0741 (0.0811) loss: 0.8848 (0.8809) time: 0.2114 data: 0.1283 max mem: 8255 +Train: [12] [3400/6250] eta: 0:08:32 lr: 0.000123 grad: 0.0776 (0.0809) loss: 0.8822 (0.8810) time: 0.1633 data: 0.0748 max mem: 8255 +Train: [12] [3500/6250] eta: 0:08:13 lr: 0.000123 grad: 0.0727 (0.0808) loss: 0.8818 (0.8810) time: 0.1452 data: 0.0534 max mem: 8255 +Train: [12] [3600/6250] eta: 0:07:54 lr: 0.000123 grad: 0.0723 (0.0807) loss: 0.8778 (0.8811) time: 0.1754 data: 0.0923 max mem: 8255 +Train: [12] [3700/6250] eta: 0:07:34 lr: 0.000123 grad: 0.0683 (0.0806) loss: 0.8855 (0.8813) time: 0.1551 data: 0.0792 max mem: 8255 +Train: [12] [3800/6250] eta: 0:07:16 lr: 0.000123 grad: 0.0703 (0.0805) loss: 0.8869 (0.8814) time: 0.2237 data: 0.1501 max mem: 8255 +Train: [12] [3900/6250] eta: 0:06:59 lr: 0.000123 grad: 0.0773 (0.0804) loss: 0.8887 (0.8815) time: 0.1839 data: 0.1171 max mem: 8255 +Train: [12] [4000/6250] eta: 0:06:44 lr: 0.000123 grad: 0.0770 (0.0803) loss: 0.8866 (0.8816) time: 0.3612 data: 0.2614 max mem: 8255 +Train: [12] [4100/6250] eta: 0:06:29 lr: 0.000123 grad: 0.0741 (0.0802) loss: 0.8848 (0.8818) time: 0.1719 data: 0.0375 max mem: 8255 +Train: [12] [4200/6250] eta: 0:06:13 lr: 0.000123 grad: 0.0720 (0.0801) loss: 0.8860 (0.8819) time: 0.2241 data: 0.1098 max mem: 8255 +Train: [12] [4300/6250] eta: 0:05:56 lr: 0.000123 grad: 0.0694 (0.0800) loss: 0.8858 (0.8820) time: 0.1094 data: 0.0049 max mem: 8255 +Train: [12] [4400/6250] eta: 0:05:38 lr: 0.000123 grad: 0.0748 (0.0799) loss: 0.8890 (0.8822) time: 0.2179 data: 0.1360 max mem: 8255 +Train: [12] [4500/6250] eta: 0:05:19 lr: 0.000123 grad: 0.0747 (0.0798) loss: 0.8841 (0.8823) time: 0.1655 data: 0.0945 max mem: 8255 +Train: [12] [4600/6250] eta: 0:05:00 lr: 0.000123 grad: 0.0794 (0.0798) loss: 0.8888 (0.8824) time: 0.1601 data: 0.0842 max mem: 8255 +Train: [12] [4700/6250] eta: 0:04:42 lr: 0.000123 grad: 0.0778 (0.0797) loss: 0.8877 (0.8825) time: 0.1856 data: 0.1000 max mem: 8255 +Train: [12] [4800/6250] eta: 0:04:24 lr: 0.000123 grad: 0.0722 (0.0796) loss: 0.8864 (0.8826) time: 0.1474 data: 0.0754 max mem: 8255 +Train: [12] [4900/6250] eta: 0:04:06 lr: 0.000123 grad: 0.0760 (0.0796) loss: 0.8886 (0.8827) time: 0.1737 data: 0.0978 max mem: 8255 +Train: [12] [5000/6250] eta: 0:03:48 lr: 0.000123 grad: 0.0713 (0.0795) loss: 0.8859 (0.8828) time: 0.2002 data: 0.1098 max mem: 8255 +Train: [12] [5100/6250] eta: 0:03:31 lr: 0.000123 grad: 0.0753 (0.0795) loss: 0.8850 (0.8828) time: 0.1553 data: 0.0667 max mem: 8255 +Train: [12] [5200/6250] eta: 0:03:12 lr: 0.000123 grad: 0.0710 (0.0794) loss: 0.8850 (0.8829) time: 0.1962 data: 0.1145 max mem: 8255 +Train: [12] [5300/6250] eta: 0:02:54 lr: 0.000123 grad: 0.0706 (0.0793) loss: 0.8856 (0.8829) time: 0.1595 data: 0.0573 max mem: 8255 +Train: [12] [5400/6250] eta: 0:02:35 lr: 0.000123 grad: 0.0774 (0.0792) loss: 0.8810 (0.8830) time: 0.1475 data: 0.0487 max mem: 8255 +Train: [12] [5500/6250] eta: 0:02:17 lr: 0.000123 grad: 0.0717 (0.0791) loss: 0.8861 (0.8831) time: 0.1812 data: 0.0997 max mem: 8255 +Train: [12] [5600/6250] eta: 0:01:59 lr: 0.000123 grad: 0.0736 (0.0791) loss: 0.8836 (0.8831) time: 0.2502 data: 0.1636 max mem: 8255 +Train: [12] [5700/6250] eta: 0:01:40 lr: 0.000123 grad: 0.0731 (0.0790) loss: 0.8863 (0.8831) time: 0.1392 data: 0.0640 max mem: 8255 +Train: [12] [5800/6250] eta: 0:01:22 lr: 0.000123 grad: 0.0767 (0.0790) loss: 0.8835 (0.8832) time: 0.2350 data: 0.1304 max mem: 8255 +Train: [12] [5900/6250] eta: 0:01:04 lr: 0.000123 grad: 0.0719 (0.0789) loss: 0.8829 (0.8832) time: 0.1728 data: 0.0828 max mem: 8255 +Train: [12] [6000/6250] eta: 0:00:45 lr: 0.000123 grad: 0.0698 (0.0789) loss: 0.8857 (0.8832) time: 0.1669 data: 0.0883 max mem: 8255 +Train: [12] [6100/6250] eta: 0:00:27 lr: 0.000123 grad: 0.0752 (0.0788) loss: 0.8794 (0.8832) time: 0.1422 data: 0.0452 max mem: 8255 +Train: [12] [6200/6250] eta: 0:00:09 lr: 0.000123 grad: 0.0709 (0.0788) loss: 0.8848 (0.8832) time: 0.0998 data: 0.0034 max mem: 8255 +Train: [12] [6249/6250] eta: 0:00:00 lr: 0.000123 grad: 0.0710 (0.0787) loss: 0.8829 (0.8832) time: 0.1618 data: 0.0120 max mem: 8255 +Train: [12] Total time: 0:19:19 (0.1854 s / it) +Averaged stats: lr: 0.000123 grad: 0.0710 (0.0787) loss: 0.8829 (0.8832) +Eval (hcp-train-subset): [12] [ 0/62] eta: 0:06:06 loss: 0.9076 (0.9076) time: 5.9109 data: 5.8846 max mem: 8255 +Eval (hcp-train-subset): [12] [61/62] eta: 0:00:00 loss: 0.8924 (0.8936) time: 0.1236 data: 0.1028 max mem: 8255 +Eval (hcp-train-subset): [12] Total time: 0:00:14 (0.2330 s / it) +Averaged stats (hcp-train-subset): loss: 0.8924 (0.8936) +Eval (hcp-val): [12] [ 0/62] eta: 0:06:00 loss: 0.8874 (0.8874) time: 5.8079 data: 5.7788 max mem: 8255 +Eval (hcp-val): [12] [61/62] eta: 0:00:00 loss: 0.8891 (0.8898) time: 0.1188 data: 0.0980 max mem: 8255 +Eval (hcp-val): [12] Total time: 0:00:14 (0.2357 s / it) +Averaged stats (hcp-val): loss: 0.8891 (0.8898) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +Train: [13] [ 0/6250] eta: 7:40:18 lr: 0.000123 grad: 0.1134 (0.1134) loss: 0.9002 (0.9002) time: 4.4190 data: 4.2306 max mem: 8255 +Train: [13] [ 100/6250] eta: 0:24:25 lr: 0.000123 grad: 0.0851 (0.0858) loss: 0.8877 (0.8906) time: 0.1874 data: 0.0991 max mem: 8255 +Train: [13] [ 200/6250] eta: 0:21:15 lr: 0.000123 grad: 0.0714 (0.0828) loss: 0.8885 (0.8878) time: 0.1696 data: 0.0871 max mem: 8255 +Train: [13] [ 300/6250] eta: 0:20:05 lr: 0.000123 grad: 0.0718 (0.0797) loss: 0.8777 (0.8865) time: 0.1849 data: 0.0891 max mem: 8255 +Train: [13] [ 400/6250] eta: 0:19:01 lr: 0.000123 grad: 0.0716 (0.0790) loss: 0.8803 (0.8853) time: 0.1669 data: 0.0848 max mem: 8255 +Train: [13] [ 500/6250] eta: 0:19:19 lr: 0.000123 grad: 0.0727 (0.0779) loss: 0.8792 (0.8850) time: 0.1366 data: 0.0004 max mem: 8255 +Train: [13] [ 600/6250] eta: 0:18:33 lr: 0.000123 grad: 0.0741 (0.0772) loss: 0.8854 (0.8850) time: 0.1577 data: 0.0730 max mem: 8255 +Train: [13] [ 700/6250] eta: 0:18:20 lr: 0.000123 grad: 0.0765 (0.0766) loss: 0.8784 (0.8849) time: 0.1723 data: 0.0415 max mem: 8255 +Train: [13] [ 800/6250] eta: 0:17:46 lr: 0.000123 grad: 0.0774 (0.0774) loss: 0.8771 (0.8845) time: 0.1831 data: 0.0888 max mem: 8255 +Train: [13] [ 900/6250] eta: 0:17:20 lr: 0.000123 grad: 0.0712 (0.0774) loss: 0.8817 (0.8844) time: 0.1605 data: 0.0550 max mem: 8255 +Train: [13] [1000/6250] eta: 0:16:57 lr: 0.000123 grad: 0.0685 (0.0770) loss: 0.8853 (0.8843) time: 0.1184 data: 0.0007 max mem: 8255 +Train: [13] [1100/6250] eta: 0:16:25 lr: 0.000123 grad: 0.0694 (0.0769) loss: 0.8812 (0.8841) time: 0.1426 data: 0.0657 max mem: 8255 +Train: [13] [1200/6250] eta: 0:16:21 lr: 0.000123 grad: 0.0695 (0.0766) loss: 0.8834 (0.8840) time: 0.2015 data: 0.1184 max mem: 8255 +Train: [13] [1300/6250] eta: 0:15:46 lr: 0.000123 grad: 0.0741 (0.0765) loss: 0.8794 (0.8839) time: 0.1428 data: 0.0604 max mem: 8255 +Train: [13] [1400/6250] eta: 0:15:30 lr: 0.000123 grad: 0.0715 (0.0764) loss: 0.8853 (0.8837) time: 0.1578 data: 0.0718 max mem: 8255 +Train: [13] [1500/6250] eta: 0:15:01 lr: 0.000123 grad: 0.0720 (0.0763) loss: 0.8744 (0.8834) time: 0.1567 data: 0.0738 max mem: 8255 +Train: [13] [1600/6250] eta: 0:14:37 lr: 0.000123 grad: 0.0745 (0.0761) loss: 0.8824 (0.8832) time: 0.1297 data: 0.0382 max mem: 8255 +Train: [13] [1700/6250] eta: 0:14:15 lr: 0.000123 grad: 0.0689 (0.0760) loss: 0.8854 (0.8830) time: 0.1567 data: 0.0652 max mem: 8255 +Train: [13] [1800/6250] eta: 0:13:49 lr: 0.000123 grad: 0.0699 (0.0759) loss: 0.8810 (0.8830) time: 0.1469 data: 0.0693 max mem: 8255 +Train: [13] [1900/6250] eta: 0:13:32 lr: 0.000123 grad: 0.0753 (0.0758) loss: 0.8806 (0.8830) time: 0.2272 data: 0.1497 max mem: 8255 +Train: [13] [2000/6250] eta: 0:13:08 lr: 0.000123 grad: 0.0670 (0.0756) loss: 0.8877 (0.8831) time: 0.1732 data: 0.0933 max mem: 8255 +Train: [13] [2100/6250] eta: 0:12:47 lr: 0.000123 grad: 0.0765 (0.0756) loss: 0.8849 (0.8831) time: 0.1869 data: 0.1041 max mem: 8255 +Train: [13] [2200/6250] eta: 0:12:23 lr: 0.000123 grad: 0.0716 (0.0756) loss: 0.8787 (0.8831) time: 0.1427 data: 0.0616 max mem: 8255 +Train: [13] [2300/6250] eta: 0:12:03 lr: 0.000123 grad: 0.0747 (0.0755) loss: 0.8835 (0.8830) time: 0.1829 data: 0.0941 max mem: 8255 +Train: [13] [2400/6250] eta: 0:11:38 lr: 0.000123 grad: 0.0736 (0.0756) loss: 0.8871 (0.8830) time: 0.1414 data: 0.0693 max mem: 8255 +Train: [13] [2500/6250] eta: 0:11:18 lr: 0.000123 grad: 0.0734 (0.0757) loss: 0.8815 (0.8828) time: 0.1570 data: 0.0772 max mem: 8255 +Train: [13] [2600/6250] eta: 0:10:58 lr: 0.000123 grad: 0.0740 (0.0758) loss: 0.8838 (0.8828) time: 0.1643 data: 0.0886 max mem: 8255 +Train: [13] [2700/6250] eta: 0:10:37 lr: 0.000123 grad: 0.0691 (0.0758) loss: 0.8861 (0.8828) time: 0.1841 data: 0.1069 max mem: 8255 +Train: [13] [2800/6250] eta: 0:10:17 lr: 0.000123 grad: 0.0734 (0.0759) loss: 0.8851 (0.8827) time: 0.1566 data: 0.0763 max mem: 8255 +Train: [13] [2900/6250] eta: 0:09:55 lr: 0.000123 grad: 0.0714 (0.0760) loss: 0.8781 (0.8826) time: 0.1199 data: 0.0315 max mem: 8255 +Train: [13] [3000/6250] eta: 0:09:35 lr: 0.000123 grad: 0.0742 (0.0760) loss: 0.8805 (0.8826) time: 0.1727 data: 0.0832 max mem: 8255 +Train: [13] [3100/6250] eta: 0:09:15 lr: 0.000123 grad: 0.0744 (0.0761) loss: 0.8778 (0.8825) time: 0.1629 data: 0.0945 max mem: 8255 +Train: [13] [3200/6250] eta: 0:08:58 lr: 0.000123 grad: 0.0726 (0.0762) loss: 0.8825 (0.8825) time: 0.2260 data: 0.1584 max mem: 8255 +Train: [13] [3300/6250] eta: 0:08:37 lr: 0.000123 grad: 0.0685 (0.0761) loss: 0.8797 (0.8825) time: 0.1425 data: 0.0649 max mem: 8255 +Train: [13] [3400/6250] eta: 0:08:20 lr: 0.000123 grad: 0.0786 (0.0761) loss: 0.8758 (0.8824) time: 0.2243 data: 0.1470 max mem: 8255 +Train: [13] [3500/6250] eta: 0:08:02 lr: 0.000123 grad: 0.0773 (0.0762) loss: 0.8776 (0.8823) time: 0.1524 data: 0.0686 max mem: 8255 +Train: [13] [3600/6250] eta: 0:07:46 lr: 0.000123 grad: 0.0697 (0.0763) loss: 0.8791 (0.8823) time: 0.0977 data: 0.0038 max mem: 8255 +Train: [13] [3700/6250] eta: 0:07:33 lr: 0.000122 grad: 0.0691 (0.0764) loss: 0.8847 (0.8822) time: 0.1140 data: 0.0004 max mem: 8255 +Train: [13] [3800/6250] eta: 0:07:16 lr: 0.000122 grad: 0.0750 (0.0764) loss: 0.8832 (0.8822) time: 0.1901 data: 0.0953 max mem: 8255 +Train: [13] [3900/6250] eta: 0:06:59 lr: 0.000122 grad: 0.0807 (0.0765) loss: 0.8773 (0.8822) time: 0.2470 data: 0.1545 max mem: 8255 +Train: [13] [4000/6250] eta: 0:06:42 lr: 0.000122 grad: 0.0719 (0.0765) loss: 0.8769 (0.8821) time: 0.2521 data: 0.1738 max mem: 8255 +Train: [13] [4100/6250] eta: 0:06:26 lr: 0.000122 grad: 0.0728 (0.0765) loss: 0.8780 (0.8821) time: 0.1551 data: 0.0760 max mem: 8255 +Train: [13] [4200/6250] eta: 0:06:07 lr: 0.000122 grad: 0.0731 (0.0765) loss: 0.8782 (0.8820) time: 0.1786 data: 0.0933 max mem: 8255 +Train: [13] [4300/6250] eta: 0:05:50 lr: 0.000122 grad: 0.0735 (0.0765) loss: 0.8814 (0.8820) time: 0.1355 data: 0.0368 max mem: 8255 +Train: [13] [4400/6250] eta: 0:05:32 lr: 0.000122 grad: 0.0746 (0.0766) loss: 0.8808 (0.8820) time: 0.1472 data: 0.0690 max mem: 8255 +Train: [13] [4500/6250] eta: 0:05:14 lr: 0.000122 grad: 0.0745 (0.0766) loss: 0.8769 (0.8819) time: 0.1618 data: 0.0784 max mem: 8255 +Train: [13] [4600/6250] eta: 0:04:56 lr: 0.000122 grad: 0.0726 (0.0766) loss: 0.8813 (0.8819) time: 0.1777 data: 0.0877 max mem: 8255 +Train: [13] [4700/6250] eta: 0:04:38 lr: 0.000122 grad: 0.0663 (0.0766) loss: 0.8862 (0.8819) time: 0.1816 data: 0.1112 max mem: 8255 +Train: [13] [4800/6250] eta: 0:04:20 lr: 0.000122 grad: 0.0733 (0.0766) loss: 0.8824 (0.8818) time: 0.1688 data: 0.0750 max mem: 8255 +Train: [13] [4900/6250] eta: 0:04:01 lr: 0.000122 grad: 0.0731 (0.0766) loss: 0.8810 (0.8818) time: 0.1480 data: 0.0685 max mem: 8255 +Train: [13] [5000/6250] eta: 0:03:44 lr: 0.000122 grad: 0.0755 (0.0766) loss: 0.8826 (0.8819) time: 0.1899 data: 0.1053 max mem: 8255 +Train: [13] [5100/6250] eta: 0:03:26 lr: 0.000122 grad: 0.0721 (0.0766) loss: 0.8814 (0.8819) time: 0.1083 data: 0.0068 max mem: 8255 +Train: [13] [5200/6250] eta: 0:03:08 lr: 0.000122 grad: 0.0744 (0.0766) loss: 0.8800 (0.8820) time: 0.1380 data: 0.0407 max mem: 8255 +Train: [13] [5300/6250] eta: 0:02:50 lr: 0.000122 grad: 0.0709 (0.0766) loss: 0.8819 (0.8820) time: 0.2203 data: 0.1229 max mem: 8255 +Train: [13] [5400/6250] eta: 0:02:32 lr: 0.000122 grad: 0.0716 (0.0765) loss: 0.8800 (0.8820) time: 0.1759 data: 0.0884 max mem: 8255 +Train: [13] [5500/6250] eta: 0:02:14 lr: 0.000122 grad: 0.0768 (0.0766) loss: 0.8833 (0.8820) time: 0.2089 data: 0.1234 max mem: 8255 +Train: [13] [5600/6250] eta: 0:01:56 lr: 0.000122 grad: 0.0775 (0.0766) loss: 0.8817 (0.8820) time: 0.1600 data: 0.0788 max mem: 8255 +Train: [13] [5700/6250] eta: 0:01:38 lr: 0.000122 grad: 0.0734 (0.0766) loss: 0.8813 (0.8820) time: 0.1351 data: 0.0532 max mem: 8255 +Train: [13] [5800/6250] eta: 0:01:21 lr: 0.000122 grad: 0.0743 (0.0765) loss: 0.8833 (0.8820) time: 0.1978 data: 0.1232 max mem: 8255 +Train: [13] [5900/6250] eta: 0:01:03 lr: 0.000122 grad: 0.0748 (0.0765) loss: 0.8818 (0.8820) time: 0.2915 data: 0.2168 max mem: 8255 +Train: [13] [6000/6250] eta: 0:00:45 lr: 0.000122 grad: 0.0760 (0.0765) loss: 0.8829 (0.8820) time: 0.3737 data: 0.2791 max mem: 8255 +Train: [13] [6100/6250] eta: 0:00:27 lr: 0.000122 grad: 0.0725 (0.0765) loss: 0.8821 (0.8820) time: 0.3576 data: 0.2200 max mem: 8255 +Train: [13] [6200/6250] eta: 0:00:09 lr: 0.000122 grad: 0.0706 (0.0764) loss: 0.8774 (0.8820) time: 0.1504 data: 0.0721 max mem: 8255 +Train: [13] [6249/6250] eta: 0:00:00 lr: 0.000122 grad: 0.0703 (0.0764) loss: 0.8766 (0.8819) time: 0.1713 data: 0.0332 max mem: 8255 +Train: [13] Total time: 0:19:02 (0.1827 s / it) +Averaged stats: lr: 0.000122 grad: 0.0703 (0.0764) loss: 0.8766 (0.8819) +Eval (hcp-train-subset): [13] [ 0/62] eta: 0:06:32 loss: 0.9047 (0.9047) time: 6.3262 data: 6.2962 max mem: 8255 +Eval (hcp-train-subset): [13] [61/62] eta: 0:00:00 loss: 0.8947 (0.8927) time: 0.1261 data: 0.1037 max mem: 8255 +Eval (hcp-train-subset): [13] Total time: 0:00:14 (0.2407 s / it) +Averaged stats (hcp-train-subset): loss: 0.8947 (0.8927) +Eval (hcp-val): [13] [ 0/62] eta: 0:04:44 loss: 0.8862 (0.8862) time: 4.5924 data: 4.5432 max mem: 8255 +Eval (hcp-val): [13] [61/62] eta: 0:00:00 loss: 0.8884 (0.8890) time: 0.1658 data: 0.1450 max mem: 8255 +Eval (hcp-val): [13] Total time: 0:00:14 (0.2294 s / it) +Averaged stats (hcp-val): loss: 0.8884 (0.8890) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +Train: [14] [ 0/6250] eta: 13:59:46 lr: 0.000122 grad: 0.0642 (0.0642) loss: 0.9125 (0.9125) time: 8.0618 data: 7.9649 max mem: 8255 +Train: [14] [ 100/6250] eta: 0:25:46 lr: 0.000122 grad: 0.0796 (0.0840) loss: 0.8874 (0.8934) time: 0.2459 data: 0.1253 max mem: 8255 +Train: [14] [ 200/6250] eta: 0:23:13 lr: 0.000122 grad: 0.0735 (0.0846) loss: 0.8887 (0.8888) time: 0.3175 data: 0.2264 max mem: 8255 +Train: [14] [ 300/6250] eta: 0:21:37 lr: 0.000122 grad: 0.0828 (0.0833) loss: 0.8782 (0.8869) time: 0.1889 data: 0.1069 max mem: 8255 +Train: [14] [ 400/6250] eta: 0:20:15 lr: 0.000122 grad: 0.0771 (0.0826) loss: 0.8783 (0.8849) time: 0.1619 data: 0.0760 max mem: 8255 +Train: [14] [ 500/6250] eta: 0:19:09 lr: 0.000122 grad: 0.0764 (0.0820) loss: 0.8800 (0.8837) time: 0.1611 data: 0.0804 max mem: 8255 +Train: [14] [ 600/6250] eta: 0:18:25 lr: 0.000122 grad: 0.0752 (0.0816) loss: 0.8756 (0.8826) time: 0.1777 data: 0.0994 max mem: 8255 +Train: [14] [ 700/6250] eta: 0:18:00 lr: 0.000122 grad: 0.0770 (0.0808) loss: 0.8816 (0.8823) time: 0.1319 data: 0.0295 max mem: 8255 +Train: [14] [ 800/6250] eta: 0:17:34 lr: 0.000122 grad: 0.0756 (0.0806) loss: 0.8842 (0.8823) time: 0.1966 data: 0.1038 max mem: 8255 +Train: [14] [ 900/6250] eta: 0:17:08 lr: 0.000122 grad: 0.0710 (0.0805) loss: 0.8832 (0.8823) time: 0.1491 data: 0.0405 max mem: 8255 +Train: [14] [1000/6250] eta: 0:16:38 lr: 0.000122 grad: 0.0710 (0.0799) loss: 0.8791 (0.8824) time: 0.1802 data: 0.0887 max mem: 8255 +Train: [14] [1100/6250] eta: 0:16:21 lr: 0.000122 grad: 0.0685 (0.0794) loss: 0.8851 (0.8826) time: 0.2162 data: 0.1124 max mem: 8255 +Train: [14] [1200/6250] eta: 0:15:43 lr: 0.000122 grad: 0.0692 (0.0789) loss: 0.8880 (0.8825) time: 0.1786 data: 0.1079 max mem: 8255 +Train: [14] [1300/6250] eta: 0:15:19 lr: 0.000122 grad: 0.0682 (0.0786) loss: 0.8861 (0.8825) time: 0.1981 data: 0.1145 max mem: 8255 +Train: [14] [1400/6250] eta: 0:14:50 lr: 0.000122 grad: 0.0739 (0.0784) loss: 0.8770 (0.8825) time: 0.1280 data: 0.0502 max mem: 8255 +Train: [14] [1500/6250] eta: 0:14:23 lr: 0.000122 grad: 0.0728 (0.0784) loss: 0.8829 (0.8824) time: 0.1531 data: 0.0784 max mem: 8255 +Train: [14] [1600/6250] eta: 0:13:58 lr: 0.000122 grad: 0.0704 (0.0782) loss: 0.8835 (0.8823) time: 0.1659 data: 0.0792 max mem: 8255 +Train: [14] [1700/6250] eta: 0:13:38 lr: 0.000122 grad: 0.0712 (0.0780) loss: 0.8807 (0.8823) time: 0.1499 data: 0.0768 max mem: 8255 +Train: [14] [1800/6250] eta: 0:13:15 lr: 0.000122 grad: 0.0767 (0.0780) loss: 0.8790 (0.8822) time: 0.1632 data: 0.0864 max mem: 8255 +Train: [14] [1900/6250] eta: 0:12:57 lr: 0.000122 grad: 0.0707 (0.0780) loss: 0.8835 (0.8822) time: 0.1755 data: 0.0948 max mem: 8255 +Train: [14] [2000/6250] eta: 0:12:38 lr: 0.000122 grad: 0.0671 (0.0779) loss: 0.8880 (0.8823) time: 0.1477 data: 0.0739 max mem: 8255 +Train: [14] [2100/6250] eta: 0:12:17 lr: 0.000122 grad: 0.0776 (0.0779) loss: 0.8824 (0.8823) time: 0.1669 data: 0.0954 max mem: 8255 +Train: [14] [2200/6250] eta: 0:11:55 lr: 0.000122 grad: 0.0739 (0.0779) loss: 0.8738 (0.8822) time: 0.1482 data: 0.0689 max mem: 8255 +Train: [14] [2300/6250] eta: 0:11:34 lr: 0.000122 grad: 0.0708 (0.0778) loss: 0.8803 (0.8822) time: 0.1539 data: 0.0887 max mem: 8255 +Train: [14] [2400/6250] eta: 0:11:14 lr: 0.000122 grad: 0.0775 (0.0777) loss: 0.8754 (0.8821) time: 0.1898 data: 0.1070 max mem: 8255 +Train: [14] [2500/6250] eta: 0:10:52 lr: 0.000122 grad: 0.0708 (0.0776) loss: 0.8796 (0.8821) time: 0.1266 data: 0.0456 max mem: 8255 +Train: [14] [2600/6250] eta: 0:10:31 lr: 0.000122 grad: 0.0735 (0.0775) loss: 0.8796 (0.8821) time: 0.1551 data: 0.0839 max mem: 8255 +Train: [14] [2700/6250] eta: 0:10:12 lr: 0.000122 grad: 0.0745 (0.0776) loss: 0.8756 (0.8821) time: 0.1662 data: 0.0822 max mem: 8255 +Train: [14] [2800/6250] eta: 0:09:55 lr: 0.000122 grad: 0.0803 (0.0775) loss: 0.8789 (0.8820) time: 0.1792 data: 0.1035 max mem: 8255 +Train: [14] [2900/6250] eta: 0:09:38 lr: 0.000122 grad: 0.0742 (0.0775) loss: 0.8798 (0.8820) time: 0.1549 data: 0.0802 max mem: 8255 +Train: [14] [3000/6250] eta: 0:09:20 lr: 0.000122 grad: 0.0701 (0.0774) loss: 0.8834 (0.8819) time: 0.1661 data: 0.0839 max mem: 8255 +Train: [14] [3100/6250] eta: 0:09:02 lr: 0.000122 grad: 0.0716 (0.0774) loss: 0.8782 (0.8818) time: 0.1410 data: 0.0662 max mem: 8255 +Train: [14] [3200/6250] eta: 0:08:43 lr: 0.000122 grad: 0.0686 (0.0772) loss: 0.8884 (0.8818) time: 0.1438 data: 0.0684 max mem: 8255 +Train: [14] [3300/6250] eta: 0:08:26 lr: 0.000122 grad: 0.0753 (0.0773) loss: 0.8773 (0.8818) time: 0.1924 data: 0.1140 max mem: 8255 +Train: [14] [3400/6250] eta: 0:08:10 lr: 0.000122 grad: 0.0688 (0.0772) loss: 0.8862 (0.8818) time: 0.1345 data: 0.0543 max mem: 8255 +Train: [14] [3500/6250] eta: 0:07:55 lr: 0.000122 grad: 0.0758 (0.0772) loss: 0.8827 (0.8818) time: 0.2583 data: 0.1594 max mem: 8255 +Train: [14] [3600/6250] eta: 0:07:38 lr: 0.000122 grad: 0.0776 (0.0772) loss: 0.8806 (0.8818) time: 0.2261 data: 0.1433 max mem: 8255 +Train: [14] [3700/6250] eta: 0:07:21 lr: 0.000122 grad: 0.0770 (0.0772) loss: 0.8813 (0.8817) time: 0.2027 data: 0.1171 max mem: 8255 +Train: [14] [3800/6250] eta: 0:07:05 lr: 0.000122 grad: 0.0737 (0.0771) loss: 0.8779 (0.8817) time: 0.2001 data: 0.1227 max mem: 8255 +Train: [14] [3900/6250] eta: 0:06:49 lr: 0.000122 grad: 0.0735 (0.0772) loss: 0.8807 (0.8816) time: 0.2617 data: 0.1931 max mem: 8255 +Train: [14] [4000/6250] eta: 0:06:32 lr: 0.000122 grad: 0.0772 (0.0772) loss: 0.8804 (0.8815) time: 0.2319 data: 0.1409 max mem: 8255 +Train: [14] [4100/6250] eta: 0:06:16 lr: 0.000122 grad: 0.0742 (0.0773) loss: 0.8790 (0.8815) time: 0.1704 data: 0.0845 max mem: 8255 +Train: [14] [4200/6250] eta: 0:05:59 lr: 0.000122 grad: 0.0806 (0.0773) loss: 0.8728 (0.8814) time: 0.1143 data: 0.0371 max mem: 8255 +Train: [14] [4300/6250] eta: 0:05:43 lr: 0.000122 grad: 0.0819 (0.0774) loss: 0.8766 (0.8814) time: 0.3864 data: 0.2730 max mem: 8255 +Train: [14] [4400/6250] eta: 0:05:25 lr: 0.000122 grad: 0.0750 (0.0775) loss: 0.8819 (0.8812) time: 0.1967 data: 0.1231 max mem: 8255 +Train: [14] [4500/6250] eta: 0:05:07 lr: 0.000122 grad: 0.0737 (0.0776) loss: 0.8791 (0.8812) time: 0.1624 data: 0.0864 max mem: 8255 +Train: [14] [4600/6250] eta: 0:04:50 lr: 0.000122 grad: 0.0750 (0.0776) loss: 0.8740 (0.8811) time: 0.1135 data: 0.0003 max mem: 8255 +Train: [14] [4700/6250] eta: 0:04:32 lr: 0.000122 grad: 0.0789 (0.0777) loss: 0.8769 (0.8810) time: 0.1640 data: 0.0796 max mem: 8255 +Train: [14] [4800/6250] eta: 0:04:14 lr: 0.000122 grad: 0.0759 (0.0778) loss: 0.8712 (0.8809) time: 0.1436 data: 0.0665 max mem: 8255 +Train: [14] [4900/6250] eta: 0:03:56 lr: 0.000122 grad: 0.0825 (0.0779) loss: 0.8768 (0.8808) time: 0.1471 data: 0.0661 max mem: 8255 +Train: [14] [5000/6250] eta: 0:03:39 lr: 0.000122 grad: 0.0836 (0.0780) loss: 0.8699 (0.8807) time: 0.1016 data: 0.0222 max mem: 8255 +Train: [14] [5100/6250] eta: 0:03:21 lr: 0.000122 grad: 0.0746 (0.0781) loss: 0.8745 (0.8806) time: 0.1607 data: 0.0767 max mem: 8255 +Train: [14] [5200/6250] eta: 0:03:04 lr: 0.000122 grad: 0.0761 (0.0781) loss: 0.8782 (0.8805) time: 0.1711 data: 0.0891 max mem: 8255 +Train: [14] [5300/6250] eta: 0:02:47 lr: 0.000122 grad: 0.0802 (0.0782) loss: 0.8717 (0.8804) time: 0.1997 data: 0.1010 max mem: 8255 +Train: [14] [5400/6250] eta: 0:02:29 lr: 0.000122 grad: 0.0851 (0.0783) loss: 0.8651 (0.8803) time: 0.1324 data: 0.0496 max mem: 8255 +Train: [14] [5500/6250] eta: 0:02:12 lr: 0.000122 grad: 0.0828 (0.0784) loss: 0.8722 (0.8802) time: 0.1698 data: 0.0789 max mem: 8255 +Train: [14] [5600/6250] eta: 0:01:54 lr: 0.000122 grad: 0.0862 (0.0785) loss: 0.8700 (0.8801) time: 0.1474 data: 0.0674 max mem: 8255 +Train: [14] [5700/6250] eta: 0:01:37 lr: 0.000122 grad: 0.0755 (0.0785) loss: 0.8778 (0.8800) time: 0.1549 data: 0.0711 max mem: 8255 +Train: [14] [5800/6250] eta: 0:01:19 lr: 0.000122 grad: 0.0748 (0.0786) loss: 0.8670 (0.8799) time: 0.1943 data: 0.1143 max mem: 8255 +Train: [14] [5900/6250] eta: 0:01:01 lr: 0.000122 grad: 0.0777 (0.0786) loss: 0.8737 (0.8798) time: 0.1765 data: 0.1008 max mem: 8255 +Train: [14] [6000/6250] eta: 0:00:44 lr: 0.000122 grad: 0.0801 (0.0787) loss: 0.8687 (0.8796) time: 0.1612 data: 0.0867 max mem: 8255 +Train: [14] [6100/6250] eta: 0:00:26 lr: 0.000122 grad: 0.0804 (0.0788) loss: 0.8806 (0.8795) time: 0.2028 data: 0.1284 max mem: 8255 +Train: [14] [6200/6250] eta: 0:00:08 lr: 0.000122 grad: 0.0822 (0.0788) loss: 0.8761 (0.8795) time: 0.1306 data: 0.0429 max mem: 8255 +Train: [14] [6249/6250] eta: 0:00:00 lr: 0.000122 grad: 0.0796 (0.0788) loss: 0.8664 (0.8794) time: 0.1783 data: 0.1084 max mem: 8255 +Train: [14] Total time: 0:18:27 (0.1772 s / it) +Averaged stats: lr: 0.000122 grad: 0.0796 (0.0788) loss: 0.8664 (0.8794) +Eval (hcp-train-subset): [14] [ 0/62] eta: 0:04:36 loss: 0.9017 (0.9017) time: 4.4660 data: 4.4264 max mem: 8255 +Eval (hcp-train-subset): [14] [61/62] eta: 0:00:00 loss: 0.8921 (0.8912) time: 0.1727 data: 0.1498 max mem: 8255 +Eval (hcp-train-subset): [14] Total time: 0:00:15 (0.2468 s / it) +Averaged stats (hcp-train-subset): loss: 0.8921 (0.8912) +Making plots (hcp-train-subset): example=46 +Eval (hcp-val): [14] [ 0/62] eta: 0:06:09 loss: 0.8846 (0.8846) time: 5.9591 data: 5.9293 max mem: 8255 +Eval (hcp-val): [14] [61/62] eta: 0:00:00 loss: 0.8884 (0.8887) time: 0.1415 data: 0.1193 max mem: 8255 +Eval (hcp-val): [14] Total time: 0:00:15 (0.2548 s / it) +Averaged stats (hcp-val): loss: 0.8884 (0.8887) +Making plots (hcp-val): example=55 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +Train: [15] [ 0/6250] eta: 12:11:48 lr: 0.000122 grad: 0.1107 (0.1107) loss: 0.8438 (0.8438) time: 7.0254 data: 6.9340 max mem: 8255 +Train: [15] [ 100/6250] eta: 0:24:26 lr: 0.000122 grad: 0.0887 (0.0976) loss: 0.8918 (0.8894) time: 0.1852 data: 0.0952 max mem: 8255 +Train: [15] [ 200/6250] eta: 0:21:08 lr: 0.000122 grad: 0.0840 (0.0956) loss: 0.8823 (0.8847) time: 0.1598 data: 0.0813 max mem: 8255 +Train: [15] [ 300/6250] eta: 0:19:55 lr: 0.000122 grad: 0.0825 (0.0927) loss: 0.8893 (0.8836) time: 0.1990 data: 0.1217 max mem: 8255 +Train: [15] [ 400/6250] eta: 0:19:20 lr: 0.000122 grad: 0.0719 (0.0897) loss: 0.8780 (0.8830) time: 0.2069 data: 0.1243 max mem: 8255 +Train: [15] [ 500/6250] eta: 0:18:52 lr: 0.000122 grad: 0.0711 (0.0874) loss: 0.8778 (0.8823) time: 0.1981 data: 0.1128 max mem: 8255 +Train: [15] [ 600/6250] eta: 0:18:20 lr: 0.000122 grad: 0.0739 (0.0860) loss: 0.8753 (0.8816) time: 0.1696 data: 0.0917 max mem: 8255 +Train: [15] [ 700/6250] eta: 0:18:22 lr: 0.000122 grad: 0.0723 (0.0846) loss: 0.8769 (0.8814) time: 0.2724 data: 0.1812 max mem: 8255 +Train: [15] [ 800/6250] eta: 0:18:15 lr: 0.000122 grad: 0.0701 (0.0835) loss: 0.8851 (0.8812) time: 0.1723 data: 0.0283 max mem: 8255 +Train: [15] [ 900/6250] eta: 0:17:41 lr: 0.000122 grad: 0.0765 (0.0829) loss: 0.8771 (0.8809) time: 0.2165 data: 0.1409 max mem: 8255 +Train: [15] [1000/6250] eta: 0:17:26 lr: 0.000122 grad: 0.0755 (0.0823) loss: 0.8789 (0.8806) time: 0.3044 data: 0.2006 max mem: 8255 +Train: [15] [1100/6250] eta: 0:16:46 lr: 0.000121 grad: 0.0752 (0.0817) loss: 0.8800 (0.8802) time: 0.1486 data: 0.0629 max mem: 8255 +Train: [15] [1200/6250] eta: 0:16:12 lr: 0.000121 grad: 0.0676 (0.0813) loss: 0.8772 (0.8801) time: 0.2052 data: 0.1328 max mem: 8255 +Train: [15] [1300/6250] eta: 0:15:35 lr: 0.000121 grad: 0.0735 (0.0810) loss: 0.8798 (0.8799) time: 0.1311 data: 0.0514 max mem: 8255 +Train: [15] [1400/6250] eta: 0:15:08 lr: 0.000121 grad: 0.0813 (0.0807) loss: 0.8818 (0.8797) time: 0.1738 data: 0.0893 max mem: 8255 +Train: [15] [1500/6250] eta: 0:14:42 lr: 0.000121 grad: 0.0690 (0.0805) loss: 0.8759 (0.8796) time: 0.2063 data: 0.1343 max mem: 8255 +Train: [15] [1600/6250] eta: 0:14:12 lr: 0.000121 grad: 0.0778 (0.0804) loss: 0.8776 (0.8794) time: 0.1671 data: 0.0874 max mem: 8255 +Train: [15] [1700/6250] eta: 0:13:46 lr: 0.000121 grad: 0.0720 (0.0802) loss: 0.8779 (0.8793) time: 0.1495 data: 0.0708 max mem: 8255 +Train: [15] [1800/6250] eta: 0:13:26 lr: 0.000121 grad: 0.0694 (0.0804) loss: 0.8762 (0.8792) time: 0.2588 data: 0.1864 max mem: 8255 +Train: [15] [1900/6250] eta: 0:13:04 lr: 0.000121 grad: 0.0766 (0.0805) loss: 0.8762 (0.8791) time: 0.1758 data: 0.0991 max mem: 8255 +Train: [15] [2000/6250] eta: 0:12:43 lr: 0.000121 grad: 0.0697 (0.0802) loss: 0.8837 (0.8792) time: 0.1841 data: 0.1111 max mem: 8255 +Train: [15] [2100/6250] eta: 0:12:25 lr: 0.000121 grad: 0.0733 (0.0800) loss: 0.8774 (0.8791) time: 0.1870 data: 0.1236 max mem: 8255 +Train: [15] [2200/6250] eta: 0:12:13 lr: 0.000121 grad: 0.0735 (0.0799) loss: 0.8766 (0.8791) time: 0.1710 data: 0.0727 max mem: 8255 +Train: [15] [2300/6250] eta: 0:11:54 lr: 0.000121 grad: 0.0756 (0.0800) loss: 0.8792 (0.8791) time: 0.1834 data: 0.1001 max mem: 8255 +Train: [15] [2400/6250] eta: 0:11:35 lr: 0.000121 grad: 0.0782 (0.0800) loss: 0.8726 (0.8791) time: 0.1697 data: 0.0831 max mem: 8255 +Train: [15] [2500/6250] eta: 0:11:19 lr: 0.000121 grad: 0.0740 (0.0799) loss: 0.8843 (0.8791) time: 0.0808 data: 0.0002 max mem: 8255 +Train: [15] [2600/6250] eta: 0:10:59 lr: 0.000121 grad: 0.0749 (0.0797) loss: 0.8812 (0.8791) time: 0.2882 data: 0.2009 max mem: 8255 +Train: [15] [2700/6250] eta: 0:10:36 lr: 0.000121 grad: 0.0706 (0.0797) loss: 0.8779 (0.8790) time: 0.1509 data: 0.0672 max mem: 8255 +Train: [15] [2800/6250] eta: 0:10:16 lr: 0.000121 grad: 0.0764 (0.0797) loss: 0.8749 (0.8789) time: 0.1727 data: 0.1024 max mem: 8255 +Train: [15] [2900/6250] eta: 0:09:56 lr: 0.000121 grad: 0.0712 (0.0797) loss: 0.8779 (0.8788) time: 0.1411 data: 0.0640 max mem: 8255 +Train: [15] [3000/6250] eta: 0:09:37 lr: 0.000121 grad: 0.0766 (0.0797) loss: 0.8808 (0.8788) time: 0.1477 data: 0.0623 max mem: 8255 +Train: [15] [3100/6250] eta: 0:09:19 lr: 0.000121 grad: 0.0709 (0.0797) loss: 0.8820 (0.8788) time: 0.1592 data: 0.0564 max mem: 8255 +Train: [15] [3200/6250] eta: 0:09:05 lr: 0.000121 grad: 0.0798 (0.0797) loss: 0.8709 (0.8787) time: 0.2746 data: 0.1915 max mem: 8255 +Train: [15] [3300/6250] eta: 0:08:49 lr: 0.000121 grad: 0.0730 (0.0796) loss: 0.8811 (0.8787) time: 0.1291 data: 0.0441 max mem: 8255 +Train: [15] [3400/6250] eta: 0:08:35 lr: 0.000121 grad: 0.0815 (0.0796) loss: 0.8763 (0.8787) time: 0.2236 data: 0.0735 max mem: 8255 +Train: [15] [3500/6250] eta: 0:08:17 lr: 0.000121 grad: 0.0796 (0.0797) loss: 0.8745 (0.8786) time: 0.1843 data: 0.1014 max mem: 8255 +Train: [15] [3600/6250] eta: 0:08:02 lr: 0.000121 grad: 0.0706 (0.0797) loss: 0.8777 (0.8786) time: 0.1782 data: 0.0739 max mem: 8255 +Train: [15] [3700/6250] eta: 0:07:43 lr: 0.000121 grad: 0.0748 (0.0797) loss: 0.8801 (0.8785) time: 0.2024 data: 0.1304 max mem: 8255 +Train: [15] [3800/6250] eta: 0:07:27 lr: 0.000121 grad: 0.0759 (0.0798) loss: 0.8746 (0.8784) time: 0.1957 data: 0.1077 max mem: 8255 +Train: [15] [3900/6250] eta: 0:07:09 lr: 0.000121 grad: 0.0814 (0.0799) loss: 0.8723 (0.8784) time: 0.1295 data: 0.0402 max mem: 8255 +Train: [15] [4000/6250] eta: 0:06:50 lr: 0.000121 grad: 0.0831 (0.0799) loss: 0.8716 (0.8783) time: 0.1873 data: 0.1067 max mem: 8255 +Train: [15] [4100/6250] eta: 0:06:32 lr: 0.000121 grad: 0.0773 (0.0799) loss: 0.8776 (0.8783) time: 0.1613 data: 0.0842 max mem: 8255 +Train: [15] [4200/6250] eta: 0:06:14 lr: 0.000121 grad: 0.0769 (0.0798) loss: 0.8788 (0.8783) time: 0.2230 data: 0.1254 max mem: 8255 +Train: [15] [4300/6250] eta: 0:05:56 lr: 0.000121 grad: 0.0727 (0.0797) loss: 0.8761 (0.8783) time: 0.1863 data: 0.1144 max mem: 8255 +Train: [15] [4400/6250] eta: 0:05:38 lr: 0.000121 grad: 0.0754 (0.0797) loss: 0.8743 (0.8782) time: 0.1199 data: 0.0378 max mem: 8255 +Train: [15] [4500/6250] eta: 0:05:19 lr: 0.000121 grad: 0.0779 (0.0798) loss: 0.8774 (0.8782) time: 0.1740 data: 0.0897 max mem: 8255 +Train: [15] [4600/6250] eta: 0:05:01 lr: 0.000121 grad: 0.0758 (0.0797) loss: 0.8764 (0.8782) time: 0.1431 data: 0.0267 max mem: 8255 +Train: [15] [4700/6250] eta: 0:04:42 lr: 0.000121 grad: 0.0743 (0.0797) loss: 0.8783 (0.8781) time: 0.1911 data: 0.1067 max mem: 8255 +Train: [15] [4800/6250] eta: 0:04:24 lr: 0.000121 grad: 0.0765 (0.0797) loss: 0.8732 (0.8781) time: 0.1936 data: 0.1126 max mem: 8255 +Train: [15] [4900/6250] eta: 0:04:05 lr: 0.000121 grad: 0.0755 (0.0797) loss: 0.8781 (0.8781) time: 0.1626 data: 0.0918 max mem: 8255 +Train: [15] [5000/6250] eta: 0:03:47 lr: 0.000121 grad: 0.0789 (0.0796) loss: 0.8728 (0.8780) time: 0.1566 data: 0.0742 max mem: 8255 +Train: [15] [5100/6250] eta: 0:03:28 lr: 0.000121 grad: 0.0734 (0.0796) loss: 0.8793 (0.8780) time: 0.2085 data: 0.1132 max mem: 8255 +Train: [15] [5200/6250] eta: 0:03:11 lr: 0.000121 grad: 0.0697 (0.0795) loss: 0.8819 (0.8780) time: 0.1617 data: 0.0841 max mem: 8255 +Train: [15] [5300/6250] eta: 0:02:52 lr: 0.000121 grad: 0.0699 (0.0795) loss: 0.8783 (0.8780) time: 0.1756 data: 0.0916 max mem: 8255 +Train: [15] [5400/6250] eta: 0:02:35 lr: 0.000121 grad: 0.0769 (0.0795) loss: 0.8753 (0.8779) time: 0.1267 data: 0.0007 max mem: 8255 +Train: [15] [5500/6250] eta: 0:02:16 lr: 0.000121 grad: 0.0716 (0.0795) loss: 0.8786 (0.8779) time: 0.1734 data: 0.1039 max mem: 8255 +Train: [15] [5600/6250] eta: 0:01:58 lr: 0.000121 grad: 0.0745 (0.0795) loss: 0.8768 (0.8778) time: 0.1911 data: 0.1174 max mem: 8255 +Train: [15] [5700/6250] eta: 0:01:40 lr: 0.000121 grad: 0.0712 (0.0795) loss: 0.8769 (0.8778) time: 0.1164 data: 0.0059 max mem: 8255 +Train: [15] [5800/6250] eta: 0:01:22 lr: 0.000121 grad: 0.0801 (0.0795) loss: 0.8725 (0.8777) time: 0.1807 data: 0.1025 max mem: 8255 +Train: [15] [5900/6250] eta: 0:01:04 lr: 0.000121 grad: 0.0745 (0.0794) loss: 0.8740 (0.8777) time: 0.2121 data: 0.1392 max mem: 8255 +Train: [15] [6000/6250] eta: 0:00:45 lr: 0.000121 grad: 0.0769 (0.0794) loss: 0.8800 (0.8777) time: 0.1175 data: 0.0003 max mem: 8255 +Train: [15] [6100/6250] eta: 0:00:27 lr: 0.000121 grad: 0.0784 (0.0794) loss: 0.8716 (0.8777) time: 0.1625 data: 0.0766 max mem: 8255 +Train: [15] [6200/6250] eta: 0:00:09 lr: 0.000121 grad: 0.0740 (0.0793) loss: 0.8799 (0.8777) time: 0.1439 data: 0.0408 max mem: 8255 +Train: [15] [6249/6250] eta: 0:00:00 lr: 0.000121 grad: 0.0744 (0.0793) loss: 0.8760 (0.8777) time: 0.1645 data: 0.0770 max mem: 8255 +Train: [15] Total time: 0:19:12 (0.1844 s / it) +Averaged stats: lr: 0.000121 grad: 0.0744 (0.0793) loss: 0.8760 (0.8777) +Eval (hcp-train-subset): [15] [ 0/62] eta: 0:06:18 loss: 0.9015 (0.9015) time: 6.1040 data: 6.0716 max mem: 8255 +Eval (hcp-train-subset): [15] [61/62] eta: 0:00:00 loss: 0.8895 (0.8903) time: 0.1436 data: 0.1222 max mem: 8255 +Eval (hcp-train-subset): [15] Total time: 0:00:15 (0.2443 s / it) +Averaged stats (hcp-train-subset): loss: 0.8895 (0.8903) +Eval (hcp-val): [15] [ 0/62] eta: 0:05:29 loss: 0.8841 (0.8841) time: 5.3188 data: 5.2886 max mem: 8255 +Eval (hcp-val): [15] [61/62] eta: 0:00:00 loss: 0.8871 (0.8880) time: 0.1621 data: 0.1397 max mem: 8255 +Eval (hcp-val): [15] Total time: 0:00:15 (0.2434 s / it) +Averaged stats (hcp-val): loss: 0.8871 (0.8880) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +Train: [16] [ 0/6250] eta: 8:48:47 lr: 0.000121 grad: 0.0730 (0.0730) loss: 0.9056 (0.9056) time: 5.0765 data: 4.7906 max mem: 8255 +Train: [16] [ 100/6250] eta: 0:23:42 lr: 0.000121 grad: 0.1074 (0.0942) loss: 0.8693 (0.8826) time: 0.1473 data: 0.0674 max mem: 8255 +Train: [16] [ 200/6250] eta: 0:21:05 lr: 0.000121 grad: 0.0849 (0.0945) loss: 0.8677 (0.8778) time: 0.1730 data: 0.0882 max mem: 8255 +Train: [16] [ 300/6250] eta: 0:19:25 lr: 0.000121 grad: 0.0763 (0.0908) loss: 0.8756 (0.8757) time: 0.1587 data: 0.0729 max mem: 8255 +Train: [16] [ 400/6250] eta: 0:18:30 lr: 0.000121 grad: 0.0725 (0.0879) loss: 0.8675 (0.8747) time: 0.1362 data: 0.0673 max mem: 8255 +Train: [16] [ 500/6250] eta: 0:17:48 lr: 0.000121 grad: 0.0790 (0.0857) loss: 0.8742 (0.8745) time: 0.1472 data: 0.0625 max mem: 8255 +Train: [16] [ 600/6250] eta: 0:17:43 lr: 0.000121 grad: 0.0666 (0.0837) loss: 0.8793 (0.8753) time: 0.1913 data: 0.0983 max mem: 8255 +Train: [16] [ 700/6250] eta: 0:17:14 lr: 0.000121 grad: 0.0708 (0.0823) loss: 0.8819 (0.8758) time: 0.1455 data: 0.0470 max mem: 8255 +Train: [16] [ 800/6250] eta: 0:16:50 lr: 0.000121 grad: 0.0678 (0.0813) loss: 0.8741 (0.8757) time: 0.2118 data: 0.1088 max mem: 8255 +Train: [16] [ 900/6250] eta: 0:16:27 lr: 0.000121 grad: 0.0695 (0.0807) loss: 0.8768 (0.8758) time: 0.1424 data: 0.0449 max mem: 8255 +Train: [16] [1000/6250] eta: 0:15:57 lr: 0.000121 grad: 0.0701 (0.0801) loss: 0.8720 (0.8756) time: 0.1572 data: 0.0819 max mem: 8255 +Train: [16] [1100/6250] eta: 0:15:30 lr: 0.000121 grad: 0.0744 (0.0799) loss: 0.8781 (0.8756) time: 0.1696 data: 0.0948 max mem: 8255 +Train: [16] [1200/6250] eta: 0:15:01 lr: 0.000121 grad: 0.0718 (0.0796) loss: 0.8767 (0.8755) time: 0.1589 data: 0.0881 max mem: 8255 +Train: [16] [1300/6250] eta: 0:14:40 lr: 0.000121 grad: 0.0668 (0.0791) loss: 0.8714 (0.8755) time: 0.1699 data: 0.0844 max mem: 8255 +Train: [16] [1400/6250] eta: 0:14:20 lr: 0.000121 grad: 0.0690 (0.0789) loss: 0.8773 (0.8755) time: 0.1426 data: 0.0676 max mem: 8255 +Train: [16] [1500/6250] eta: 0:13:56 lr: 0.000121 grad: 0.0722 (0.0786) loss: 0.8766 (0.8755) time: 0.1495 data: 0.0554 max mem: 8255 +Train: [16] [1600/6250] eta: 0:13:33 lr: 0.000121 grad: 0.0740 (0.0785) loss: 0.8740 (0.8754) time: 0.1652 data: 0.0890 max mem: 8255 +Train: [16] [1700/6250] eta: 0:13:14 lr: 0.000121 grad: 0.0687 (0.0785) loss: 0.8777 (0.8752) time: 0.1813 data: 0.0908 max mem: 8255 +Train: [16] [1800/6250] eta: 0:12:59 lr: 0.000121 grad: 0.0773 (0.0786) loss: 0.8709 (0.8750) time: 0.1960 data: 0.1131 max mem: 8255 +Train: [16] [1900/6250] eta: 0:12:46 lr: 0.000121 grad: 0.0734 (0.0788) loss: 0.8683 (0.8746) time: 0.1355 data: 0.0495 max mem: 8255 +Train: [16] [2000/6250] eta: 0:12:30 lr: 0.000121 grad: 0.0758 (0.0789) loss: 0.8745 (0.8744) time: 0.1756 data: 0.0831 max mem: 8255 +Train: [16] [2100/6250] eta: 0:12:11 lr: 0.000121 grad: 0.0743 (0.0789) loss: 0.8679 (0.8742) time: 0.1782 data: 0.0997 max mem: 8255 +Train: [16] [2200/6250] eta: 0:11:51 lr: 0.000121 grad: 0.0669 (0.0788) loss: 0.8793 (0.8742) time: 0.1452 data: 0.0641 max mem: 8255 +Train: [16] [2300/6250] eta: 0:11:30 lr: 0.000121 grad: 0.0766 (0.0787) loss: 0.8708 (0.8741) time: 0.1584 data: 0.0799 max mem: 8255 +Train: [16] [2400/6250] eta: 0:11:13 lr: 0.000121 grad: 0.0738 (0.0786) loss: 0.8671 (0.8739) time: 0.1577 data: 0.0703 max mem: 8255 +Train: [16] [2500/6250] eta: 0:10:55 lr: 0.000121 grad: 0.0776 (0.0786) loss: 0.8698 (0.8739) time: 0.1651 data: 0.0835 max mem: 8255 +Train: [16] [2600/6250] eta: 0:10:37 lr: 0.000121 grad: 0.0732 (0.0785) loss: 0.8688 (0.8738) time: 0.1395 data: 0.0613 max mem: 8255 +Train: [16] [2700/6250] eta: 0:10:18 lr: 0.000121 grad: 0.0662 (0.0784) loss: 0.8739 (0.8737) time: 0.1580 data: 0.0814 max mem: 8255 +Train: [16] [2800/6250] eta: 0:09:58 lr: 0.000121 grad: 0.0787 (0.0784) loss: 0.8718 (0.8737) time: 0.1519 data: 0.0604 max mem: 8255 +Train: [16] [2900/6250] eta: 0:09:38 lr: 0.000121 grad: 0.0694 (0.0783) loss: 0.8722 (0.8737) time: 0.1832 data: 0.1027 max mem: 8255 +Train: [16] [3000/6250] eta: 0:09:24 lr: 0.000121 grad: 0.0695 (0.0782) loss: 0.8760 (0.8737) time: 0.3059 data: 0.2299 max mem: 8255 +Train: [16] [3100/6250] eta: 0:09:07 lr: 0.000121 grad: 0.0721 (0.0782) loss: 0.8769 (0.8736) time: 0.2103 data: 0.1395 max mem: 8255 +Train: [16] [3200/6250] eta: 0:08:49 lr: 0.000121 grad: 0.0748 (0.0782) loss: 0.8716 (0.8735) time: 0.1311 data: 0.0003 max mem: 8255 +Train: [16] [3300/6250] eta: 0:08:33 lr: 0.000121 grad: 0.0667 (0.0781) loss: 0.8770 (0.8735) time: 0.1524 data: 0.0719 max mem: 8255 +Train: [16] [3400/6250] eta: 0:08:22 lr: 0.000121 grad: 0.0719 (0.0781) loss: 0.8809 (0.8736) time: 0.1744 data: 0.0734 max mem: 8255 +Train: [16] [3500/6250] eta: 0:08:06 lr: 0.000120 grad: 0.0700 (0.0781) loss: 0.8741 (0.8735) time: 0.3377 data: 0.1656 max mem: 8255 +Train: [16] [3600/6250] eta: 0:07:46 lr: 0.000120 grad: 0.0742 (0.0781) loss: 0.8697 (0.8735) time: 0.1667 data: 0.1012 max mem: 8255 +Train: [16] [3700/6250] eta: 0:07:28 lr: 0.000120 grad: 0.0779 (0.0781) loss: 0.8686 (0.8735) time: 0.2068 data: 0.1209 max mem: 8255 +Train: [16] [3800/6250] eta: 0:07:11 lr: 0.000120 grad: 0.0714 (0.0780) loss: 0.8792 (0.8735) time: 0.1563 data: 0.0780 max mem: 8255 +Train: [16] [3900/6250] eta: 0:06:53 lr: 0.000120 grad: 0.0738 (0.0780) loss: 0.8747 (0.8735) time: 0.1997 data: 0.0742 max mem: 8255 +Train: [16] [4000/6250] eta: 0:06:36 lr: 0.000120 grad: 0.0756 (0.0780) loss: 0.8787 (0.8736) time: 0.1926 data: 0.1162 max mem: 8255 +Train: [16] [4100/6250] eta: 0:06:18 lr: 0.000120 grad: 0.0779 (0.0780) loss: 0.8754 (0.8736) time: 0.2014 data: 0.1148 max mem: 8255 +Train: [16] [4200/6250] eta: 0:06:01 lr: 0.000120 grad: 0.0738 (0.0781) loss: 0.8755 (0.8737) time: 0.1710 data: 0.0708 max mem: 8255 +Train: [16] [4300/6250] eta: 0:05:44 lr: 0.000120 grad: 0.0693 (0.0781) loss: 0.8788 (0.8737) time: 0.1967 data: 0.1126 max mem: 8255 +Train: [16] [4400/6250] eta: 0:05:26 lr: 0.000120 grad: 0.0757 (0.0782) loss: 0.8725 (0.8736) time: 0.2174 data: 0.1476 max mem: 8255 +Train: [16] [4500/6250] eta: 0:05:08 lr: 0.000120 grad: 0.0763 (0.0783) loss: 0.8726 (0.8736) time: 0.1850 data: 0.0988 max mem: 8255 +Train: [16] [4600/6250] eta: 0:04:51 lr: 0.000120 grad: 0.0781 (0.0784) loss: 0.8743 (0.8735) time: 0.1296 data: 0.0452 max mem: 8255 +Train: [16] [4700/6250] eta: 0:04:33 lr: 0.000120 grad: 0.0752 (0.0785) loss: 0.8723 (0.8735) time: 0.1711 data: 0.1001 max mem: 8255 +Train: [16] [4800/6250] eta: 0:04:16 lr: 0.000120 grad: 0.0824 (0.0786) loss: 0.8722 (0.8734) time: 0.2925 data: 0.2067 max mem: 8255 +Train: [16] [4900/6250] eta: 0:03:58 lr: 0.000120 grad: 0.0785 (0.0787) loss: 0.8648 (0.8734) time: 0.1717 data: 0.0818 max mem: 8255 +Train: [16] [5000/6250] eta: 0:03:41 lr: 0.000120 grad: 0.0776 (0.0787) loss: 0.8746 (0.8733) time: 0.1473 data: 0.0632 max mem: 8255 +Train: [16] [5100/6250] eta: 0:03:25 lr: 0.000120 grad: 0.0720 (0.0787) loss: 0.8750 (0.8734) time: 0.1703 data: 0.0517 max mem: 8255 +Train: [16] [5200/6250] eta: 0:03:06 lr: 0.000120 grad: 0.0725 (0.0787) loss: 0.8772 (0.8734) time: 0.1808 data: 0.0890 max mem: 8255 +Train: [16] [5300/6250] eta: 0:02:49 lr: 0.000120 grad: 0.0771 (0.0788) loss: 0.8755 (0.8734) time: 0.1485 data: 0.0303 max mem: 8255 +Train: [16] [5400/6250] eta: 0:02:32 lr: 0.000120 grad: 0.0742 (0.0788) loss: 0.8777 (0.8734) time: 0.2067 data: 0.0675 max mem: 8255 +Train: [16] [5500/6250] eta: 0:02:14 lr: 0.000120 grad: 0.0769 (0.0788) loss: 0.8786 (0.8734) time: 0.1520 data: 0.0628 max mem: 8255 +Train: [16] [5600/6250] eta: 0:01:56 lr: 0.000120 grad: 0.0781 (0.0788) loss: 0.8800 (0.8735) time: 0.2298 data: 0.1423 max mem: 8255 +Train: [16] [5700/6250] eta: 0:01:38 lr: 0.000120 grad: 0.0790 (0.0789) loss: 0.8691 (0.8734) time: 0.1227 data: 0.0409 max mem: 8255 +Train: [16] [5800/6250] eta: 0:01:21 lr: 0.000120 grad: 0.0803 (0.0789) loss: 0.8744 (0.8734) time: 0.4270 data: 0.3068 max mem: 8255 +Train: [16] [5900/6250] eta: 0:01:02 lr: 0.000120 grad: 0.0796 (0.0790) loss: 0.8677 (0.8734) time: 0.2084 data: 0.1348 max mem: 8255 +Train: [16] [6000/6250] eta: 0:00:44 lr: 0.000120 grad: 0.0782 (0.0790) loss: 0.8746 (0.8734) time: 0.1549 data: 0.0801 max mem: 8255 +Train: [16] [6100/6250] eta: 0:00:26 lr: 0.000120 grad: 0.0796 (0.0790) loss: 0.8691 (0.8734) time: 0.1545 data: 0.0727 max mem: 8255 +Train: [16] [6200/6250] eta: 0:00:08 lr: 0.000120 grad: 0.0800 (0.0790) loss: 0.8693 (0.8734) time: 0.1320 data: 0.0548 max mem: 8255 +Train: [16] [6249/6250] eta: 0:00:00 lr: 0.000120 grad: 0.0812 (0.0790) loss: 0.8722 (0.8734) time: 0.1784 data: 0.1037 max mem: 8255 +Train: [16] Total time: 0:18:50 (0.1808 s / it) +Averaged stats: lr: 0.000120 grad: 0.0812 (0.0790) loss: 0.8722 (0.8734) +Eval (hcp-train-subset): [16] [ 0/62] eta: 0:04:25 loss: 0.8946 (0.8946) time: 4.2822 data: 4.2153 max mem: 8255 +Eval (hcp-train-subset): [16] [61/62] eta: 0:00:00 loss: 0.8907 (0.8902) time: 0.1478 data: 0.1271 max mem: 8255 +Eval (hcp-train-subset): [16] Total time: 0:00:15 (0.2442 s / it) +Averaged stats (hcp-train-subset): loss: 0.8907 (0.8902) +Eval (hcp-val): [16] [ 0/62] eta: 0:03:25 loss: 0.8848 (0.8848) time: 3.3174 data: 3.2438 max mem: 8255 +Eval (hcp-val): [16] [61/62] eta: 0:00:00 loss: 0.8861 (0.8868) time: 0.1207 data: 0.0997 max mem: 8255 +Eval (hcp-val): [16] Total time: 0:00:15 (0.2485 s / it) +Averaged stats (hcp-val): loss: 0.8861 (0.8868) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +Train: [17] [ 0/6250] eta: 15:12:04 lr: 0.000120 grad: 0.1428 (0.1428) loss: 0.8997 (0.8997) time: 8.7558 data: 8.6633 max mem: 8255 +Train: [17] [ 100/6250] eta: 0:24:00 lr: 0.000120 grad: 0.0806 (0.1078) loss: 0.8836 (0.8808) time: 0.1644 data: 0.0659 max mem: 8255 +Train: [17] [ 200/6250] eta: 0:20:35 lr: 0.000120 grad: 0.0755 (0.0932) loss: 0.8807 (0.8802) time: 0.1596 data: 0.0816 max mem: 8255 +Train: [17] [ 300/6250] eta: 0:19:00 lr: 0.000120 grad: 0.0809 (0.0925) loss: 0.8779 (0.8799) time: 0.1628 data: 0.0623 max mem: 8255 +Train: [17] [ 400/6250] eta: 0:17:58 lr: 0.000120 grad: 0.0782 (0.0906) loss: 0.8734 (0.8784) time: 0.1620 data: 0.0756 max mem: 8255 +Train: [17] [ 500/6250] eta: 0:17:05 lr: 0.000120 grad: 0.0826 (0.0888) loss: 0.8663 (0.8769) time: 0.1502 data: 0.0577 max mem: 8255 +Train: [17] [ 600/6250] eta: 0:16:30 lr: 0.000120 grad: 0.0740 (0.0872) loss: 0.8759 (0.8762) time: 0.1741 data: 0.0874 max mem: 8255 +Train: [17] [ 700/6250] eta: 0:16:13 lr: 0.000120 grad: 0.0760 (0.0857) loss: 0.8748 (0.8765) time: 0.1724 data: 0.0890 max mem: 8255 +Train: [17] [ 800/6250] eta: 0:16:14 lr: 0.000120 grad: 0.0748 (0.0847) loss: 0.8816 (0.8766) time: 0.2485 data: 0.1722 max mem: 8255 +Train: [17] [ 900/6250] eta: 0:15:51 lr: 0.000120 grad: 0.0730 (0.0839) loss: 0.8831 (0.8770) time: 0.1373 data: 0.0257 max mem: 8255 +Train: [17] [1000/6250] eta: 0:15:34 lr: 0.000120 grad: 0.0684 (0.0828) loss: 0.8797 (0.8772) time: 0.1871 data: 0.0979 max mem: 8255 +Train: [17] [1100/6250] eta: 0:15:12 lr: 0.000120 grad: 0.0720 (0.0819) loss: 0.8827 (0.8775) time: 0.1779 data: 0.1006 max mem: 8255 +Train: [17] [1200/6250] eta: 0:14:51 lr: 0.000120 grad: 0.0699 (0.0811) loss: 0.8797 (0.8776) time: 0.1725 data: 0.0930 max mem: 8255 +Train: [17] [1300/6250] eta: 0:14:50 lr: 0.000120 grad: 0.0672 (0.0806) loss: 0.8821 (0.8777) time: 0.1119 data: 0.0003 max mem: 8255 +Train: [17] [1400/6250] eta: 0:14:42 lr: 0.000120 grad: 0.0694 (0.0801) loss: 0.8771 (0.8777) time: 0.1266 data: 0.0008 max mem: 8255 +Train: [17] [1500/6250] eta: 0:14:30 lr: 0.000120 grad: 0.0704 (0.0798) loss: 0.8832 (0.8777) time: 0.2486 data: 0.1704 max mem: 8255 +Train: [17] [1600/6250] eta: 0:14:07 lr: 0.000120 grad: 0.0744 (0.0794) loss: 0.8799 (0.8777) time: 0.1921 data: 0.1106 max mem: 8255 +Train: [17] [1700/6250] eta: 0:13:52 lr: 0.000120 grad: 0.0707 (0.0791) loss: 0.8756 (0.8777) time: 0.1499 data: 0.0416 max mem: 8255 +Train: [17] [1800/6250] eta: 0:13:29 lr: 0.000120 grad: 0.0681 (0.0789) loss: 0.8815 (0.8777) time: 0.1749 data: 0.1083 max mem: 8255 +Train: [17] [1900/6250] eta: 0:13:09 lr: 0.000120 grad: 0.0747 (0.0788) loss: 0.8793 (0.8776) time: 0.1856 data: 0.1187 max mem: 8255 +Train: [17] [2000/6250] eta: 0:12:47 lr: 0.000120 grad: 0.0809 (0.0789) loss: 0.8800 (0.8775) time: 0.1631 data: 0.0870 max mem: 8255 +Train: [17] [2100/6250] eta: 0:12:29 lr: 0.000120 grad: 0.0757 (0.0789) loss: 0.8835 (0.8774) time: 0.1648 data: 0.0856 max mem: 8255 +Train: [17] [2200/6250] eta: 0:12:08 lr: 0.000120 grad: 0.0707 (0.0789) loss: 0.8760 (0.8772) time: 0.1644 data: 0.1015 max mem: 8255 +Train: [17] [2300/6250] eta: 0:11:47 lr: 0.000120 grad: 0.0848 (0.0790) loss: 0.8758 (0.8771) time: 0.1614 data: 0.0671 max mem: 8255 +Train: [17] [2400/6250] eta: 0:11:27 lr: 0.000120 grad: 0.0735 (0.0790) loss: 0.8735 (0.8770) time: 0.1542 data: 0.0646 max mem: 8255 +Train: [17] [2500/6250] eta: 0:11:08 lr: 0.000120 grad: 0.0766 (0.0790) loss: 0.8758 (0.8768) time: 0.2029 data: 0.1260 max mem: 8255 +Train: [17] [2600/6250] eta: 0:10:46 lr: 0.000120 grad: 0.0803 (0.0790) loss: 0.8730 (0.8768) time: 0.1373 data: 0.0645 max mem: 8255 +Train: [17] [2700/6250] eta: 0:10:25 lr: 0.000120 grad: 0.0756 (0.0790) loss: 0.8792 (0.8767) time: 0.1465 data: 0.0640 max mem: 8255 +Train: [17] [2800/6250] eta: 0:10:04 lr: 0.000120 grad: 0.0765 (0.0790) loss: 0.8797 (0.8767) time: 0.1618 data: 0.0644 max mem: 8255 +Train: [17] [2900/6250] eta: 0:09:47 lr: 0.000120 grad: 0.0753 (0.0789) loss: 0.8725 (0.8766) time: 0.2012 data: 0.0848 max mem: 8255 +Train: [17] [3000/6250] eta: 0:09:31 lr: 0.000120 grad: 0.0784 (0.0789) loss: 0.8772 (0.8765) time: 0.1653 data: 0.0825 max mem: 8255 +Train: [17] [3100/6250] eta: 0:09:15 lr: 0.000120 grad: 0.0751 (0.0790) loss: 0.8723 (0.8764) time: 0.1422 data: 0.0422 max mem: 8255 +Train: [17] [3200/6250] eta: 0:08:59 lr: 0.000120 grad: 0.0743 (0.0790) loss: 0.8703 (0.8763) time: 0.1873 data: 0.1085 max mem: 8255 +Train: [17] [3300/6250] eta: 0:08:42 lr: 0.000120 grad: 0.0741 (0.0789) loss: 0.8734 (0.8763) time: 0.1933 data: 0.1171 max mem: 8255 +Train: [17] [3400/6250] eta: 0:08:25 lr: 0.000120 grad: 0.0755 (0.0789) loss: 0.8758 (0.8762) time: 0.1927 data: 0.0997 max mem: 8255 +Train: [17] [3500/6250] eta: 0:08:07 lr: 0.000120 grad: 0.0776 (0.0790) loss: 0.8769 (0.8761) time: 0.1405 data: 0.0571 max mem: 8255 +Train: [17] [3600/6250] eta: 0:07:48 lr: 0.000120 grad: 0.0749 (0.0790) loss: 0.8736 (0.8761) time: 0.1789 data: 0.1057 max mem: 8255 +Train: [17] [3700/6250] eta: 0:07:29 lr: 0.000120 grad: 0.0772 (0.0791) loss: 0.8721 (0.8759) time: 0.1580 data: 0.0883 max mem: 8255 +Train: [17] [3800/6250] eta: 0:07:13 lr: 0.000120 grad: 0.0767 (0.0791) loss: 0.8719 (0.8758) time: 0.1363 data: 0.0572 max mem: 8255 +Train: [17] [3900/6250] eta: 0:06:54 lr: 0.000120 grad: 0.0755 (0.0791) loss: 0.8725 (0.8757) time: 0.1974 data: 0.1113 max mem: 8255 +Train: [17] [4000/6250] eta: 0:06:39 lr: 0.000120 grad: 0.0753 (0.0792) loss: 0.8774 (0.8756) time: 0.2638 data: 0.1528 max mem: 8255 +Train: [17] [4100/6250] eta: 0:06:21 lr: 0.000120 grad: 0.0811 (0.0793) loss: 0.8688 (0.8754) time: 0.2086 data: 0.1213 max mem: 8255 +Train: [17] [4200/6250] eta: 0:06:02 lr: 0.000120 grad: 0.0863 (0.0793) loss: 0.8722 (0.8753) time: 0.1445 data: 0.0583 max mem: 8255 +Train: [17] [4300/6250] eta: 0:05:44 lr: 0.000120 grad: 0.0777 (0.0793) loss: 0.8698 (0.8752) time: 0.1604 data: 0.0813 max mem: 8255 +Train: [17] [4400/6250] eta: 0:05:26 lr: 0.000120 grad: 0.0774 (0.0793) loss: 0.8731 (0.8751) time: 0.2236 data: 0.1463 max mem: 8255 +Train: [17] [4500/6250] eta: 0:05:08 lr: 0.000120 grad: 0.0743 (0.0793) loss: 0.8701 (0.8750) time: 0.1540 data: 0.0818 max mem: 8255 +Train: [17] [4600/6250] eta: 0:04:50 lr: 0.000120 grad: 0.0781 (0.0792) loss: 0.8713 (0.8750) time: 0.1826 data: 0.0766 max mem: 8255 +Train: [17] [4700/6250] eta: 0:04:33 lr: 0.000120 grad: 0.0767 (0.0792) loss: 0.8735 (0.8749) time: 0.1543 data: 0.0767 max mem: 8255 +Train: [17] [4800/6250] eta: 0:04:15 lr: 0.000120 grad: 0.0724 (0.0791) loss: 0.8783 (0.8749) time: 0.1587 data: 0.0679 max mem: 8255 +Train: [17] [4900/6250] eta: 0:03:57 lr: 0.000119 grad: 0.0744 (0.0790) loss: 0.8725 (0.8748) time: 0.1584 data: 0.0876 max mem: 8255 +Train: [17] [5000/6250] eta: 0:03:39 lr: 0.000119 grad: 0.0693 (0.0789) loss: 0.8762 (0.8748) time: 0.1308 data: 0.0586 max mem: 8255 +Train: [17] [5100/6250] eta: 0:03:21 lr: 0.000119 grad: 0.0733 (0.0789) loss: 0.8759 (0.8748) time: 0.1729 data: 0.0897 max mem: 8255 +Train: [17] [5200/6250] eta: 0:03:04 lr: 0.000119 grad: 0.0767 (0.0789) loss: 0.8760 (0.8748) time: 0.1460 data: 0.0587 max mem: 8255 +Train: [17] [5300/6250] eta: 0:02:46 lr: 0.000119 grad: 0.0764 (0.0789) loss: 0.8738 (0.8748) time: 0.1895 data: 0.1180 max mem: 8255 +Train: [17] [5400/6250] eta: 0:02:28 lr: 0.000119 grad: 0.0748 (0.0789) loss: 0.8763 (0.8749) time: 0.1607 data: 0.0913 max mem: 8255 +Train: [17] [5500/6250] eta: 0:02:11 lr: 0.000119 grad: 0.0749 (0.0789) loss: 0.8762 (0.8749) time: 0.2733 data: 0.2038 max mem: 8255 +Train: [17] [5600/6250] eta: 0:01:54 lr: 0.000119 grad: 0.0719 (0.0789) loss: 0.8780 (0.8748) time: 0.1187 data: 0.0003 max mem: 8255 +Train: [17] [5700/6250] eta: 0:01:36 lr: 0.000119 grad: 0.0716 (0.0789) loss: 0.8761 (0.8748) time: 0.1312 data: 0.0464 max mem: 8255 +Train: [17] [5800/6250] eta: 0:01:19 lr: 0.000119 grad: 0.0772 (0.0789) loss: 0.8730 (0.8748) time: 0.1922 data: 0.1069 max mem: 8255 +Train: [17] [5900/6250] eta: 0:01:01 lr: 0.000119 grad: 0.0744 (0.0788) loss: 0.8801 (0.8748) time: 0.1627 data: 0.0770 max mem: 8255 +Train: [17] [6000/6250] eta: 0:00:43 lr: 0.000119 grad: 0.0742 (0.0788) loss: 0.8778 (0.8748) time: 0.1442 data: 0.0543 max mem: 8255 +Train: [17] [6100/6250] eta: 0:00:26 lr: 0.000119 grad: 0.0735 (0.0788) loss: 0.8718 (0.8748) time: 0.1682 data: 0.0927 max mem: 8255 +Train: [17] [6200/6250] eta: 0:00:08 lr: 0.000119 grad: 0.0784 (0.0788) loss: 0.8759 (0.8748) time: 0.1542 data: 0.0689 max mem: 8255 +Train: [17] [6249/6250] eta: 0:00:00 lr: 0.000119 grad: 0.0745 (0.0787) loss: 0.8694 (0.8748) time: 0.2911 data: 0.1920 max mem: 8255 +Train: [17] Total time: 0:18:29 (0.1775 s / it) +Averaged stats: lr: 0.000119 grad: 0.0745 (0.0787) loss: 0.8694 (0.8748) +Eval (hcp-train-subset): [17] [ 0/62] eta: 0:04:17 loss: 0.8978 (0.8978) time: 4.1525 data: 4.0046 max mem: 8255 +Eval (hcp-train-subset): [17] [61/62] eta: 0:00:00 loss: 0.8921 (0.8892) time: 0.1448 data: 0.1240 max mem: 8255 +Eval (hcp-train-subset): [17] Total time: 0:00:14 (0.2342 s / it) +Averaged stats (hcp-train-subset): loss: 0.8921 (0.8892) +Eval (hcp-val): [17] [ 0/62] eta: 0:03:54 loss: 0.8824 (0.8824) time: 3.7808 data: 3.7105 max mem: 8255 +Eval (hcp-val): [17] [61/62] eta: 0:00:00 loss: 0.8848 (0.8857) time: 0.1513 data: 0.1303 max mem: 8255 +Eval (hcp-val): [17] Total time: 0:00:13 (0.2222 s / it) +Averaged stats (hcp-val): loss: 0.8848 (0.8857) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +Train: [18] [ 0/6250] eta: 8:09:20 lr: 0.000119 grad: 0.0554 (0.0554) loss: 0.9115 (0.9115) time: 4.6976 data: 4.4060 max mem: 8255 +Train: [18] [ 100/6250] eta: 0:24:38 lr: 0.000119 grad: 0.1004 (0.0885) loss: 0.8644 (0.8812) time: 0.2242 data: 0.1467 max mem: 8255 +Train: [18] [ 200/6250] eta: 0:20:53 lr: 0.000119 grad: 0.0743 (0.0887) loss: 0.8699 (0.8782) time: 0.1519 data: 0.0639 max mem: 8255 +Train: [18] [ 300/6250] eta: 0:19:09 lr: 0.000119 grad: 0.0800 (0.0856) loss: 0.8754 (0.8770) time: 0.1626 data: 0.0774 max mem: 8255 +Train: [18] [ 400/6250] eta: 0:18:31 lr: 0.000119 grad: 0.0747 (0.0833) loss: 0.8802 (0.8771) time: 0.2399 data: 0.1526 max mem: 8255 +Train: [18] [ 500/6250] eta: 0:17:26 lr: 0.000119 grad: 0.0722 (0.0813) loss: 0.8778 (0.8775) time: 0.1801 data: 0.0838 max mem: 8255 +Train: [18] [ 600/6250] eta: 0:17:11 lr: 0.000119 grad: 0.0767 (0.0801) loss: 0.8820 (0.8777) time: 0.1594 data: 0.0842 max mem: 8255 +Train: [18] [ 700/6250] eta: 0:16:48 lr: 0.000119 grad: 0.0751 (0.0798) loss: 0.8766 (0.8775) time: 0.1907 data: 0.1083 max mem: 8255 +Train: [18] [ 800/6250] eta: 0:16:16 lr: 0.000119 grad: 0.0763 (0.0796) loss: 0.8735 (0.8772) time: 0.1485 data: 0.0741 max mem: 8255 +Train: [18] [ 900/6250] eta: 0:15:53 lr: 0.000119 grad: 0.0740 (0.0791) loss: 0.8800 (0.8771) time: 0.1991 data: 0.1108 max mem: 8255 +Train: [18] [1000/6250] eta: 0:15:25 lr: 0.000119 grad: 0.0713 (0.0786) loss: 0.8791 (0.8771) time: 0.1428 data: 0.0551 max mem: 8255 +Train: [18] [1100/6250] eta: 0:15:03 lr: 0.000119 grad: 0.0744 (0.0786) loss: 0.8753 (0.8769) time: 0.1599 data: 0.0740 max mem: 8255 +Train: [18] [1200/6250] eta: 0:14:42 lr: 0.000119 grad: 0.0736 (0.0783) loss: 0.8726 (0.8766) time: 0.1789 data: 0.1058 max mem: 8255 +Train: [18] [1300/6250] eta: 0:14:27 lr: 0.000119 grad: 0.0787 (0.0779) loss: 0.8704 (0.8762) time: 0.1989 data: 0.1066 max mem: 8255 +Train: [18] [1400/6250] eta: 0:14:20 lr: 0.000119 grad: 0.0723 (0.0777) loss: 0.8739 (0.8760) time: 0.1257 data: 0.0018 max mem: 8255 +Train: [18] [1500/6250] eta: 0:14:14 lr: 0.000119 grad: 0.0790 (0.0778) loss: 0.8686 (0.8757) time: 0.0976 data: 0.0002 max mem: 8255 +Train: [18] [1600/6250] eta: 0:13:49 lr: 0.000119 grad: 0.0754 (0.0779) loss: 0.8718 (0.8754) time: 0.1217 data: 0.0338 max mem: 8255 +Train: [18] [1700/6250] eta: 0:13:31 lr: 0.000119 grad: 0.0738 (0.0779) loss: 0.8692 (0.8750) time: 0.1521 data: 0.0648 max mem: 8255 +Train: [18] [1800/6250] eta: 0:13:06 lr: 0.000119 grad: 0.0789 (0.0781) loss: 0.8638 (0.8743) time: 0.1607 data: 0.0816 max mem: 8255 +Train: [18] [1900/6250] eta: 0:12:48 lr: 0.000119 grad: 0.0788 (0.0782) loss: 0.8718 (0.8741) time: 0.1123 data: 0.0002 max mem: 8255 +Train: [18] [2000/6250] eta: 0:12:25 lr: 0.000119 grad: 0.0822 (0.0784) loss: 0.8661 (0.8737) time: 0.1627 data: 0.0845 max mem: 8255 +Train: [18] [2100/6250] eta: 0:12:07 lr: 0.000119 grad: 0.0768 (0.0784) loss: 0.8722 (0.8735) time: 0.2112 data: 0.1484 max mem: 8255 +Train: [18] [2200/6250] eta: 0:11:50 lr: 0.000119 grad: 0.0794 (0.0785) loss: 0.8607 (0.8733) time: 0.1938 data: 0.1136 max mem: 8255 +Train: [18] [2300/6250] eta: 0:11:30 lr: 0.000119 grad: 0.0815 (0.0786) loss: 0.8721 (0.8731) time: 0.1522 data: 0.0798 max mem: 8255 +Train: [18] [2400/6250] eta: 0:11:12 lr: 0.000119 grad: 0.0866 (0.0788) loss: 0.8653 (0.8729) time: 0.1818 data: 0.1021 max mem: 8255 +Train: [18] [2500/6250] eta: 0:10:54 lr: 0.000119 grad: 0.0742 (0.0788) loss: 0.8715 (0.8726) time: 0.2079 data: 0.1385 max mem: 8255 +Train: [18] [2600/6250] eta: 0:10:33 lr: 0.000119 grad: 0.0854 (0.0790) loss: 0.8682 (0.8724) time: 0.1683 data: 0.0840 max mem: 8255 +Train: [18] [2700/6250] eta: 0:10:14 lr: 0.000119 grad: 0.0765 (0.0792) loss: 0.8693 (0.8721) time: 0.1625 data: 0.0862 max mem: 8255 +Train: [18] [2800/6250] eta: 0:09:58 lr: 0.000119 grad: 0.0734 (0.0793) loss: 0.8754 (0.8721) time: 0.1566 data: 0.0766 max mem: 8255 +Train: [18] [2900/6250] eta: 0:09:43 lr: 0.000119 grad: 0.0769 (0.0794) loss: 0.8700 (0.8720) time: 0.1550 data: 0.0710 max mem: 8255 +Train: [18] [3000/6250] eta: 0:09:27 lr: 0.000119 grad: 0.0864 (0.0795) loss: 0.8691 (0.8719) time: 0.2029 data: 0.1076 max mem: 8255 +Train: [18] [3100/6250] eta: 0:09:11 lr: 0.000119 grad: 0.0782 (0.0796) loss: 0.8734 (0.8718) time: 0.1814 data: 0.0855 max mem: 8255 +Train: [18] [3200/6250] eta: 0:08:58 lr: 0.000119 grad: 0.0807 (0.0798) loss: 0.8658 (0.8717) time: 0.2439 data: 0.1514 max mem: 8255 +Train: [18] [3300/6250] eta: 0:08:40 lr: 0.000119 grad: 0.0759 (0.0799) loss: 0.8743 (0.8716) time: 0.1953 data: 0.1129 max mem: 8255 +Train: [18] [3400/6250] eta: 0:08:24 lr: 0.000119 grad: 0.0774 (0.0799) loss: 0.8725 (0.8715) time: 0.2838 data: 0.1743 max mem: 8255 +Train: [18] [3500/6250] eta: 0:08:07 lr: 0.000119 grad: 0.0818 (0.0800) loss: 0.8675 (0.8713) time: 0.1108 data: 0.0059 max mem: 8255 +Train: [18] [3600/6250] eta: 0:07:55 lr: 0.000119 grad: 0.0728 (0.0800) loss: 0.8706 (0.8712) time: 0.2648 data: 0.1556 max mem: 8255 +Train: [18] [3700/6250] eta: 0:07:35 lr: 0.000119 grad: 0.0743 (0.0801) loss: 0.8700 (0.8711) time: 0.1540 data: 0.0596 max mem: 8255 +Train: [18] [3800/6250] eta: 0:07:16 lr: 0.000119 grad: 0.0783 (0.0801) loss: 0.8669 (0.8710) time: 0.1301 data: 0.0573 max mem: 8255 +Train: [18] [3900/6250] eta: 0:07:01 lr: 0.000119 grad: 0.0817 (0.0802) loss: 0.8700 (0.8710) time: 0.1305 data: 0.0313 max mem: 8255 +Train: [18] [4000/6250] eta: 0:06:41 lr: 0.000119 grad: 0.0754 (0.0802) loss: 0.8795 (0.8709) time: 0.1594 data: 0.0769 max mem: 8255 +Train: [18] [4100/6250] eta: 0:06:24 lr: 0.000119 grad: 0.0791 (0.0802) loss: 0.8703 (0.8709) time: 0.2332 data: 0.1518 max mem: 8255 +Train: [18] [4200/6250] eta: 0:06:05 lr: 0.000119 grad: 0.0782 (0.0802) loss: 0.8712 (0.8709) time: 0.2135 data: 0.1410 max mem: 8255 +Train: [18] [4300/6250] eta: 0:05:48 lr: 0.000119 grad: 0.0789 (0.0802) loss: 0.8737 (0.8709) time: 0.1601 data: 0.0722 max mem: 8255 +Train: [18] [4400/6250] eta: 0:05:29 lr: 0.000119 grad: 0.0760 (0.0802) loss: 0.8683 (0.8709) time: 0.1734 data: 0.1019 max mem: 8255 +Train: [18] [4500/6250] eta: 0:05:13 lr: 0.000119 grad: 0.0767 (0.0802) loss: 0.8773 (0.8709) time: 0.2440 data: 0.1655 max mem: 8255 +Train: [18] [4600/6250] eta: 0:04:54 lr: 0.000119 grad: 0.0744 (0.0801) loss: 0.8758 (0.8710) time: 0.1770 data: 0.0757 max mem: 8255 +Train: [18] [4700/6250] eta: 0:04:38 lr: 0.000119 grad: 0.0750 (0.0801) loss: 0.8694 (0.8710) time: 0.1575 data: 0.0754 max mem: 8255 +Train: [18] [4800/6250] eta: 0:04:19 lr: 0.000119 grad: 0.0738 (0.0800) loss: 0.8732 (0.8711) time: 0.1587 data: 0.0805 max mem: 8255 +Train: [18] [4900/6250] eta: 0:04:01 lr: 0.000119 grad: 0.0762 (0.0800) loss: 0.8711 (0.8711) time: 0.1538 data: 0.0666 max mem: 8255 +Train: [18] [5000/6250] eta: 0:03:43 lr: 0.000119 grad: 0.0752 (0.0800) loss: 0.8701 (0.8711) time: 0.1748 data: 0.0615 max mem: 8255 +Train: [18] [5100/6250] eta: 0:03:26 lr: 0.000119 grad: 0.0751 (0.0800) loss: 0.8667 (0.8710) time: 0.2459 data: 0.1573 max mem: 8255 +Train: [18] [5200/6250] eta: 0:03:08 lr: 0.000119 grad: 0.0760 (0.0800) loss: 0.8721 (0.8711) time: 0.2096 data: 0.1215 max mem: 8255 +Train: [18] [5300/6250] eta: 0:02:49 lr: 0.000119 grad: 0.0794 (0.0799) loss: 0.8709 (0.8711) time: 0.1518 data: 0.0612 max mem: 8255 +Train: [18] [5400/6250] eta: 0:02:31 lr: 0.000119 grad: 0.0791 (0.0799) loss: 0.8724 (0.8711) time: 0.1532 data: 0.0709 max mem: 8255 +Train: [18] [5500/6250] eta: 0:02:13 lr: 0.000119 grad: 0.0761 (0.0799) loss: 0.8782 (0.8711) time: 0.2096 data: 0.1324 max mem: 8255 +Train: [18] [5600/6250] eta: 0:01:56 lr: 0.000119 grad: 0.0768 (0.0799) loss: 0.8693 (0.8712) time: 0.1826 data: 0.1066 max mem: 8255 +Train: [18] [5700/6250] eta: 0:01:38 lr: 0.000119 grad: 0.0761 (0.0798) loss: 0.8690 (0.8712) time: 0.1508 data: 0.0700 max mem: 8255 +Train: [18] [5800/6250] eta: 0:01:20 lr: 0.000118 grad: 0.0716 (0.0798) loss: 0.8721 (0.8712) time: 0.1589 data: 0.0824 max mem: 8255 +Train: [18] [5900/6250] eta: 0:01:02 lr: 0.000118 grad: 0.0803 (0.0798) loss: 0.8766 (0.8712) time: 0.1908 data: 0.1015 max mem: 8255 +Train: [18] [6000/6250] eta: 0:00:44 lr: 0.000118 grad: 0.0790 (0.0799) loss: 0.8763 (0.8713) time: 0.1598 data: 0.0870 max mem: 8255 +Train: [18] [6100/6250] eta: 0:00:26 lr: 0.000118 grad: 0.0752 (0.0798) loss: 0.8744 (0.8714) time: 0.1452 data: 0.0648 max mem: 8255 +Train: [18] [6200/6250] eta: 0:00:08 lr: 0.000118 grad: 0.0713 (0.0798) loss: 0.8790 (0.8714) time: 0.1770 data: 0.0999 max mem: 8255 +Train: [18] [6249/6250] eta: 0:00:00 lr: 0.000118 grad: 0.0691 (0.0798) loss: 0.8751 (0.8715) time: 0.1262 data: 0.0584 max mem: 8255 +Train: [18] Total time: 0:18:42 (0.1795 s / it) +Averaged stats: lr: 0.000118 grad: 0.0691 (0.0798) loss: 0.8751 (0.8715) +Eval (hcp-train-subset): [18] [ 0/62] eta: 0:06:06 loss: 0.8964 (0.8964) time: 5.9073 data: 5.8520 max mem: 8255 +Eval (hcp-train-subset): [18] [61/62] eta: 0:00:00 loss: 0.8878 (0.8885) time: 0.1396 data: 0.1181 max mem: 8255 +Eval (hcp-train-subset): [18] Total time: 0:00:14 (0.2285 s / it) +Averaged stats (hcp-train-subset): loss: 0.8878 (0.8885) +Eval (hcp-val): [18] [ 0/62] eta: 0:04:46 loss: 0.8818 (0.8818) time: 4.6267 data: 4.6006 max mem: 8255 +Eval (hcp-val): [18] [61/62] eta: 0:00:00 loss: 0.8847 (0.8856) time: 0.1344 data: 0.1133 max mem: 8255 +Eval (hcp-val): [18] Total time: 0:00:14 (0.2289 s / it) +Averaged stats (hcp-val): loss: 0.8847 (0.8856) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +Train: [19] [ 0/6250] eta: 11:05:19 lr: 0.000118 grad: 0.2351 (0.2351) loss: 0.8382 (0.8382) time: 6.3871 data: 6.2927 max mem: 8255 +Train: [19] [ 100/6250] eta: 0:22:02 lr: 0.000118 grad: 0.0825 (0.0872) loss: 0.8806 (0.8838) time: 0.1451 data: 0.0646 max mem: 8255 +Train: [19] [ 200/6250] eta: 0:19:25 lr: 0.000118 grad: 0.0814 (0.0855) loss: 0.8796 (0.8823) time: 0.1553 data: 0.0574 max mem: 8255 +Train: [19] [ 300/6250] eta: 0:18:21 lr: 0.000118 grad: 0.0710 (0.0838) loss: 0.8853 (0.8823) time: 0.1721 data: 0.1005 max mem: 8255 +Train: [19] [ 400/6250] eta: 0:17:34 lr: 0.000118 grad: 0.0743 (0.0820) loss: 0.8776 (0.8812) time: 0.1702 data: 0.0876 max mem: 8255 +Train: [19] [ 500/6250] eta: 0:17:07 lr: 0.000118 grad: 0.0759 (0.0811) loss: 0.8652 (0.8797) time: 0.2114 data: 0.1095 max mem: 8255 +Train: [19] [ 600/6250] eta: 0:16:22 lr: 0.000118 grad: 0.0729 (0.0803) loss: 0.8752 (0.8787) time: 0.1068 data: 0.0002 max mem: 8255 +Train: [19] [ 700/6250] eta: 0:16:01 lr: 0.000118 grad: 0.0712 (0.0796) loss: 0.8731 (0.8780) time: 0.1806 data: 0.0935 max mem: 8255 +Train: [19] [ 800/6250] eta: 0:15:29 lr: 0.000118 grad: 0.0753 (0.0789) loss: 0.8703 (0.8774) time: 0.1207 data: 0.0100 max mem: 8255 +Train: [19] [ 900/6250] eta: 0:15:09 lr: 0.000118 grad: 0.0748 (0.0787) loss: 0.8681 (0.8766) time: 0.1665 data: 0.0752 max mem: 8255 +Train: [19] [1000/6250] eta: 0:14:51 lr: 0.000118 grad: 0.0748 (0.0784) loss: 0.8748 (0.8762) time: 0.1699 data: 0.0943 max mem: 8255 +Train: [19] [1100/6250] eta: 0:14:45 lr: 0.000118 grad: 0.0690 (0.0780) loss: 0.8729 (0.8759) time: 0.2914 data: 0.1927 max mem: 8255 +Train: [19] [1200/6250] eta: 0:14:32 lr: 0.000118 grad: 0.0746 (0.0781) loss: 0.8744 (0.8757) time: 0.1428 data: 0.0577 max mem: 8255 +Train: [19] [1300/6250] eta: 0:14:13 lr: 0.000118 grad: 0.0749 (0.0780) loss: 0.8726 (0.8754) time: 0.1763 data: 0.0882 max mem: 8255 +Train: [19] [1400/6250] eta: 0:13:54 lr: 0.000118 grad: 0.0742 (0.0782) loss: 0.8720 (0.8751) time: 0.1925 data: 0.1199 max mem: 8255 +Train: [19] [1500/6250] eta: 0:13:30 lr: 0.000118 grad: 0.0741 (0.0781) loss: 0.8734 (0.8750) time: 0.1547 data: 0.0759 max mem: 8255 +Train: [19] [1600/6250] eta: 0:13:09 lr: 0.000118 grad: 0.0766 (0.0779) loss: 0.8729 (0.8750) time: 0.1388 data: 0.0556 max mem: 8255 +Train: [19] [1700/6250] eta: 0:12:51 lr: 0.000118 grad: 0.0716 (0.0778) loss: 0.8788 (0.8748) time: 0.1750 data: 0.0877 max mem: 8255 +Train: [19] [1800/6250] eta: 0:12:32 lr: 0.000118 grad: 0.0718 (0.0780) loss: 0.8738 (0.8746) time: 0.1484 data: 0.0737 max mem: 8255 +Train: [19] [1900/6250] eta: 0:12:15 lr: 0.000118 grad: 0.0733 (0.0778) loss: 0.8763 (0.8745) time: 0.1493 data: 0.0651 max mem: 8255 +Train: [19] [2000/6250] eta: 0:11:55 lr: 0.000118 grad: 0.0790 (0.0778) loss: 0.8726 (0.8744) time: 0.1511 data: 0.0714 max mem: 8255 +Train: [19] [2100/6250] eta: 0:11:38 lr: 0.000118 grad: 0.0760 (0.0776) loss: 0.8726 (0.8743) time: 0.1524 data: 0.0595 max mem: 8255 +Train: [19] [2200/6250] eta: 0:11:22 lr: 0.000118 grad: 0.0735 (0.0776) loss: 0.8738 (0.8743) time: 0.1818 data: 0.1046 max mem: 8255 +Train: [19] [2300/6250] eta: 0:11:06 lr: 0.000118 grad: 0.0708 (0.0774) loss: 0.8765 (0.8744) time: 0.1562 data: 0.0717 max mem: 8255 +Train: [19] [2400/6250] eta: 0:10:50 lr: 0.000118 grad: 0.0753 (0.0775) loss: 0.8733 (0.8743) time: 0.1982 data: 0.1235 max mem: 8255 +Train: [19] [2500/6250] eta: 0:10:30 lr: 0.000118 grad: 0.0785 (0.0776) loss: 0.8721 (0.8741) time: 0.1607 data: 0.0764 max mem: 8255 +Train: [19] [2600/6250] eta: 0:10:12 lr: 0.000118 grad: 0.0771 (0.0777) loss: 0.8760 (0.8741) time: 0.1567 data: 0.0767 max mem: 8255 +Train: [19] [2700/6250] eta: 0:09:55 lr: 0.000118 grad: 0.0710 (0.0778) loss: 0.8738 (0.8740) time: 0.1832 data: 0.1030 max mem: 8255 +Train: [19] [2800/6250] eta: 0:09:37 lr: 0.000118 grad: 0.0779 (0.0778) loss: 0.8757 (0.8740) time: 0.1195 data: 0.0372 max mem: 8255 +Train: [19] [2900/6250] eta: 0:09:20 lr: 0.000118 grad: 0.0782 (0.0778) loss: 0.8699 (0.8739) time: 0.1704 data: 0.0900 max mem: 8255 +Train: [19] [3000/6250] eta: 0:09:04 lr: 0.000118 grad: 0.0807 (0.0779) loss: 0.8689 (0.8737) time: 0.1924 data: 0.1079 max mem: 8255 +Train: [19] [3100/6250] eta: 0:08:48 lr: 0.000118 grad: 0.0695 (0.0779) loss: 0.8720 (0.8736) time: 0.1645 data: 0.0921 max mem: 8255 +Train: [19] [3200/6250] eta: 0:08:33 lr: 0.000118 grad: 0.0737 (0.0780) loss: 0.8701 (0.8735) time: 0.2651 data: 0.1455 max mem: 8255 +Train: [19] [3300/6250] eta: 0:08:18 lr: 0.000118 grad: 0.0775 (0.0781) loss: 0.8676 (0.8734) time: 0.2546 data: 0.1724 max mem: 8255 +Train: [19] [3400/6250] eta: 0:08:04 lr: 0.000118 grad: 0.0763 (0.0782) loss: 0.8720 (0.8732) time: 0.3132 data: 0.2061 max mem: 8255 +Train: [19] [3500/6250] eta: 0:07:46 lr: 0.000118 grad: 0.0792 (0.0784) loss: 0.8709 (0.8730) time: 0.2561 data: 0.1632 max mem: 8255 +Train: [19] [3600/6250] eta: 0:07:28 lr: 0.000118 grad: 0.0819 (0.0785) loss: 0.8715 (0.8729) time: 0.1792 data: 0.1054 max mem: 8255 +Train: [19] [3700/6250] eta: 0:07:11 lr: 0.000118 grad: 0.0789 (0.0787) loss: 0.8672 (0.8728) time: 0.1706 data: 0.0973 max mem: 8255 +Train: [19] [3800/6250] eta: 0:06:53 lr: 0.000118 grad: 0.0747 (0.0788) loss: 0.8732 (0.8727) time: 0.1595 data: 0.0727 max mem: 8255 +Train: [19] [3900/6250] eta: 0:06:36 lr: 0.000118 grad: 0.0816 (0.0789) loss: 0.8713 (0.8725) time: 0.1463 data: 0.0707 max mem: 8255 +Train: [19] [4000/6250] eta: 0:06:20 lr: 0.000118 grad: 0.0816 (0.0790) loss: 0.8671 (0.8723) time: 0.2145 data: 0.1331 max mem: 8255 +Train: [19] [4100/6250] eta: 0:06:04 lr: 0.000118 grad: 0.0813 (0.0791) loss: 0.8689 (0.8722) time: 0.2004 data: 0.1280 max mem: 8255 +Train: [19] [4200/6250] eta: 0:05:49 lr: 0.000118 grad: 0.0800 (0.0792) loss: 0.8626 (0.8721) time: 0.2678 data: 0.1656 max mem: 8255 +Train: [19] [4300/6250] eta: 0:05:33 lr: 0.000118 grad: 0.0852 (0.0794) loss: 0.8656 (0.8719) time: 0.1697 data: 0.0650 max mem: 8255 +Train: [19] [4400/6250] eta: 0:05:18 lr: 0.000118 grad: 0.0794 (0.0795) loss: 0.8653 (0.8717) time: 0.1450 data: 0.0584 max mem: 8255 +Train: [19] [4500/6250] eta: 0:05:03 lr: 0.000118 grad: 0.0834 (0.0795) loss: 0.8646 (0.8716) time: 0.4225 data: 0.3264 max mem: 8255 +Train: [19] [4600/6250] eta: 0:04:45 lr: 0.000118 grad: 0.0783 (0.0796) loss: 0.8688 (0.8716) time: 0.1819 data: 0.0862 max mem: 8255 +Train: [19] [4700/6250] eta: 0:04:29 lr: 0.000118 grad: 0.0768 (0.0797) loss: 0.8703 (0.8714) time: 0.3639 data: 0.2387 max mem: 8255 +Train: [19] [4800/6250] eta: 0:04:11 lr: 0.000118 grad: 0.0783 (0.0798) loss: 0.8649 (0.8713) time: 0.1204 data: 0.0107 max mem: 8255 +Train: [19] [4900/6250] eta: 0:03:53 lr: 0.000118 grad: 0.0733 (0.0798) loss: 0.8741 (0.8713) time: 0.1572 data: 0.0722 max mem: 8255 +Train: [19] [5000/6250] eta: 0:03:35 lr: 0.000118 grad: 0.0797 (0.0798) loss: 0.8653 (0.8712) time: 0.1260 data: 0.0300 max mem: 8255 +Train: [19] [5100/6250] eta: 0:03:18 lr: 0.000118 grad: 0.0794 (0.0798) loss: 0.8677 (0.8711) time: 0.1882 data: 0.1126 max mem: 8255 +Train: [19] [5200/6250] eta: 0:03:00 lr: 0.000118 grad: 0.0754 (0.0799) loss: 0.8644 (0.8710) time: 0.1471 data: 0.0634 max mem: 8255 +Train: [19] [5300/6250] eta: 0:02:43 lr: 0.000118 grad: 0.0775 (0.0799) loss: 0.8719 (0.8709) time: 0.1245 data: 0.0410 max mem: 8255 +Train: [19] [5400/6250] eta: 0:02:26 lr: 0.000118 grad: 0.0767 (0.0800) loss: 0.8657 (0.8708) time: 0.1732 data: 0.1031 max mem: 8255 +Train: [19] [5500/6250] eta: 0:02:09 lr: 0.000118 grad: 0.0827 (0.0800) loss: 0.8664 (0.8708) time: 0.1794 data: 0.1015 max mem: 8255 +Train: [19] [5600/6250] eta: 0:01:51 lr: 0.000118 grad: 0.0818 (0.0800) loss: 0.8631 (0.8707) time: 0.1753 data: 0.0966 max mem: 8255 +Train: [19] [5700/6250] eta: 0:01:34 lr: 0.000118 grad: 0.0838 (0.0800) loss: 0.8698 (0.8706) time: 0.1095 data: 0.0005 max mem: 8255 +Train: [19] [5800/6250] eta: 0:01:17 lr: 0.000118 grad: 0.0844 (0.0801) loss: 0.8719 (0.8705) time: 0.1486 data: 0.0446 max mem: 8255 +Train: [19] [5900/6250] eta: 0:01:00 lr: 0.000118 grad: 0.0766 (0.0801) loss: 0.8715 (0.8705) time: 0.2356 data: 0.1340 max mem: 8255 +Train: [19] [6000/6250] eta: 0:00:43 lr: 0.000118 grad: 0.0795 (0.0801) loss: 0.8671 (0.8705) time: 0.1717 data: 0.0862 max mem: 8255 +Train: [19] [6100/6250] eta: 0:00:25 lr: 0.000117 grad: 0.0773 (0.0802) loss: 0.8766 (0.8705) time: 0.1735 data: 0.1022 max mem: 8255 +Train: [19] [6200/6250] eta: 0:00:08 lr: 0.000117 grad: 0.0856 (0.0802) loss: 0.8678 (0.8704) time: 0.1514 data: 0.0615 max mem: 8255 +Train: [19] [6249/6250] eta: 0:00:00 lr: 0.000117 grad: 0.0843 (0.0802) loss: 0.8629 (0.8704) time: 0.3096 data: 0.2307 max mem: 8255 +Train: [19] Total time: 0:18:12 (0.1749 s / it) +Averaged stats: lr: 0.000117 grad: 0.0843 (0.0802) loss: 0.8629 (0.8704) +Eval (hcp-train-subset): [19] [ 0/62] eta: 0:06:33 loss: 0.8998 (0.8998) time: 6.3456 data: 6.3188 max mem: 8255 +Eval (hcp-train-subset): [19] [61/62] eta: 0:00:00 loss: 0.8884 (0.8881) time: 0.1448 data: 0.1232 max mem: 8255 +Eval (hcp-train-subset): [19] Total time: 0:00:15 (0.2439 s / it) +Averaged stats (hcp-train-subset): loss: 0.8884 (0.8881) +Making plots (hcp-train-subset): example=6 +Eval (hcp-val): [19] [ 0/62] eta: 0:05:34 loss: 0.8823 (0.8823) time: 5.3975 data: 5.3700 max mem: 8255 +Eval (hcp-val): [19] [61/62] eta: 0:00:00 loss: 0.8845 (0.8854) time: 0.1338 data: 0.1112 max mem: 8255 +Eval (hcp-val): [19] Total time: 0:00:14 (0.2327 s / it) +Averaged stats (hcp-val): loss: 0.8845 (0.8854) +Making plots (hcp-val): example=51 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-00019.pth +Train: [20] [ 0/6250] eta: 7:23:27 lr: 0.000117 grad: 0.0601 (0.0601) loss: 0.8875 (0.8875) time: 4.2571 data: 4.0522 max mem: 8255 +Train: [20] [ 100/6250] eta: 0:21:52 lr: 0.000117 grad: 0.0802 (0.0937) loss: 0.8747 (0.8813) time: 0.1447 data: 0.0507 max mem: 8255 +Train: [20] [ 200/6250] eta: 0:19:17 lr: 0.000117 grad: 0.0777 (0.0897) loss: 0.8754 (0.8767) time: 0.1402 data: 0.0531 max mem: 8255 +Train: [20] [ 300/6250] eta: 0:18:07 lr: 0.000117 grad: 0.0792 (0.0870) loss: 0.8729 (0.8753) time: 0.1620 data: 0.0714 max mem: 8255 +Train: [20] [ 400/6250] eta: 0:17:13 lr: 0.000117 grad: 0.0786 (0.0847) loss: 0.8815 (0.8751) time: 0.1767 data: 0.0912 max mem: 8255 +Train: [20] [ 500/6250] eta: 0:17:01 lr: 0.000117 grad: 0.0700 (0.0842) loss: 0.8757 (0.8745) time: 0.1868 data: 0.0968 max mem: 8255 +Train: [20] [ 600/6250] eta: 0:16:42 lr: 0.000117 grad: 0.0709 (0.0829) loss: 0.8747 (0.8742) time: 0.1600 data: 0.0754 max mem: 8255 +Train: [20] [ 700/6250] eta: 0:16:35 lr: 0.000117 grad: 0.0753 (0.0817) loss: 0.8734 (0.8742) time: 0.1284 data: 0.0300 max mem: 8255 +Train: [20] [ 800/6250] eta: 0:16:24 lr: 0.000117 grad: 0.0711 (0.0813) loss: 0.8800 (0.8742) time: 0.1780 data: 0.0972 max mem: 8255 +Train: [20] [ 900/6250] eta: 0:16:23 lr: 0.000117 grad: 0.0781 (0.0806) loss: 0.8658 (0.8741) time: 0.1261 data: 0.0147 max mem: 8255 +Train: [20] [1000/6250] eta: 0:15:56 lr: 0.000117 grad: 0.0714 (0.0805) loss: 0.8738 (0.8739) time: 0.1641 data: 0.0810 max mem: 8255 +Train: [20] [1100/6250] eta: 0:15:27 lr: 0.000117 grad: 0.0783 (0.0807) loss: 0.8624 (0.8735) time: 0.1598 data: 0.0728 max mem: 8255 +Train: [20] [1200/6250] eta: 0:15:02 lr: 0.000117 grad: 0.0762 (0.0808) loss: 0.8697 (0.8730) time: 0.1895 data: 0.1055 max mem: 8255 +Train: [20] [1300/6250] eta: 0:14:36 lr: 0.000117 grad: 0.0777 (0.0810) loss: 0.8658 (0.8725) time: 0.1456 data: 0.0567 max mem: 8255 +Train: [20] [1400/6250] eta: 0:14:12 lr: 0.000117 grad: 0.0789 (0.0810) loss: 0.8650 (0.8721) time: 0.1544 data: 0.0842 max mem: 8255 +Train: [20] [1500/6250] eta: 0:13:51 lr: 0.000117 grad: 0.0798 (0.0812) loss: 0.8675 (0.8718) time: 0.1871 data: 0.1047 max mem: 8255 +Train: [20] [1600/6250] eta: 0:13:31 lr: 0.000117 grad: 0.0746 (0.0812) loss: 0.8600 (0.8713) time: 0.1668 data: 0.0844 max mem: 8255 +Train: [20] [1700/6250] eta: 0:13:07 lr: 0.000117 grad: 0.0897 (0.0815) loss: 0.8595 (0.8709) time: 0.1609 data: 0.0799 max mem: 8255 +Train: [20] [1800/6250] eta: 0:12:45 lr: 0.000117 grad: 0.0760 (0.0814) loss: 0.8660 (0.8708) time: 0.1529 data: 0.0808 max mem: 8255 +Train: [20] [1900/6250] eta: 0:12:27 lr: 0.000117 grad: 0.0794 (0.0814) loss: 0.8693 (0.8706) time: 0.1533 data: 0.0677 max mem: 8255 +Train: [20] [2000/6250] eta: 0:12:08 lr: 0.000117 grad: 0.0742 (0.0815) loss: 0.8705 (0.8703) time: 0.1581 data: 0.0782 max mem: 8255 +Train: [20] [2100/6250] eta: 0:11:48 lr: 0.000117 grad: 0.0831 (0.0815) loss: 0.8663 (0.8702) time: 0.1397 data: 0.0585 max mem: 8255 +Train: [20] [2200/6250] eta: 0:11:29 lr: 0.000117 grad: 0.0790 (0.0816) loss: 0.8676 (0.8700) time: 0.1509 data: 0.0674 max mem: 8255 +Train: [20] [2300/6250] eta: 0:11:12 lr: 0.000117 grad: 0.0774 (0.0816) loss: 0.8687 (0.8700) time: 0.1730 data: 0.0850 max mem: 8255 +Train: [20] [2400/6250] eta: 0:10:56 lr: 0.000117 grad: 0.0765 (0.0815) loss: 0.8691 (0.8699) time: 0.2720 data: 0.2066 max mem: 8255 +Train: [20] [2500/6250] eta: 0:10:42 lr: 0.000117 grad: 0.0769 (0.0816) loss: 0.8654 (0.8698) time: 0.1637 data: 0.0905 max mem: 8255 +Train: [20] [2600/6250] eta: 0:10:28 lr: 0.000117 grad: 0.0804 (0.0816) loss: 0.8707 (0.8697) time: 0.1868 data: 0.1064 max mem: 8255 +Train: [20] [2700/6250] eta: 0:10:13 lr: 0.000117 grad: 0.0819 (0.0815) loss: 0.8685 (0.8697) time: 0.2033 data: 0.1368 max mem: 8255 +Train: [20] [2800/6250] eta: 0:10:02 lr: 0.000117 grad: 0.0733 (0.0815) loss: 0.8749 (0.8698) time: 0.2205 data: 0.1550 max mem: 8255 +Train: [20] [2900/6250] eta: 0:09:48 lr: 0.000117 grad: 0.0786 (0.0814) loss: 0.8657 (0.8699) time: 0.1777 data: 0.1006 max mem: 8255 +Train: [20] [3000/6250] eta: 0:09:33 lr: 0.000117 grad: 0.0735 (0.0814) loss: 0.8751 (0.8699) time: 0.1917 data: 0.1089 max mem: 8255 +Train: [20] [3100/6250] eta: 0:09:17 lr: 0.000117 grad: 0.0774 (0.0813) loss: 0.8743 (0.8700) time: 0.1741 data: 0.0880 max mem: 8255 +Train: [20] [3200/6250] eta: 0:09:01 lr: 0.000117 grad: 0.0752 (0.0813) loss: 0.8717 (0.8700) time: 0.2074 data: 0.1273 max mem: 8255 +Train: [20] [3300/6250] eta: 0:08:50 lr: 0.000117 grad: 0.0766 (0.0813) loss: 0.8723 (0.8701) time: 0.1823 data: 0.0940 max mem: 8255 +Train: [20] [3400/6250] eta: 0:08:32 lr: 0.000117 grad: 0.0745 (0.0812) loss: 0.8727 (0.8701) time: 0.1649 data: 0.0928 max mem: 8255 +Train: [20] [3500/6250] eta: 0:08:16 lr: 0.000117 grad: 0.0747 (0.0812) loss: 0.8695 (0.8701) time: 0.1643 data: 0.0455 max mem: 8255 +Train: [20] [3600/6250] eta: 0:07:59 lr: 0.000117 grad: 0.0722 (0.0811) loss: 0.8712 (0.8701) time: 0.2197 data: 0.1561 max mem: 8255 +Train: [20] [3700/6250] eta: 0:07:41 lr: 0.000117 grad: 0.0824 (0.0810) loss: 0.8715 (0.8701) time: 0.2385 data: 0.1327 max mem: 8255 +Train: [20] [3800/6250] eta: 0:07:24 lr: 0.000117 grad: 0.0806 (0.0810) loss: 0.8645 (0.8700) time: 0.1197 data: 0.0122 max mem: 8255 +Train: [20] [3900/6250] eta: 0:07:06 lr: 0.000117 grad: 0.0792 (0.0810) loss: 0.8696 (0.8700) time: 0.1087 data: 0.0285 max mem: 8255 +Train: [20] [4000/6250] eta: 0:06:48 lr: 0.000117 grad: 0.0778 (0.0809) loss: 0.8700 (0.8700) time: 0.1878 data: 0.1013 max mem: 8255 +Train: [20] [4100/6250] eta: 0:06:30 lr: 0.000117 grad: 0.0767 (0.0809) loss: 0.8707 (0.8700) time: 0.1474 data: 0.0588 max mem: 8255 +Train: [20] [4200/6250] eta: 0:06:14 lr: 0.000117 grad: 0.0725 (0.0808) loss: 0.8709 (0.8700) time: 0.1712 data: 0.0864 max mem: 8255 +Train: [20] [4300/6250] eta: 0:05:54 lr: 0.000117 grad: 0.0743 (0.0807) loss: 0.8718 (0.8701) time: 0.1356 data: 0.0558 max mem: 8255 +Train: [20] [4400/6250] eta: 0:05:37 lr: 0.000117 grad: 0.0770 (0.0807) loss: 0.8682 (0.8701) time: 0.1582 data: 0.0756 max mem: 8255 +Train: [20] [4500/6250] eta: 0:05:19 lr: 0.000117 grad: 0.0736 (0.0807) loss: 0.8692 (0.8701) time: 0.2369 data: 0.1276 max mem: 8255 +Train: [20] [4600/6250] eta: 0:05:01 lr: 0.000117 grad: 0.0770 (0.0807) loss: 0.8717 (0.8701) time: 0.1293 data: 0.0431 max mem: 8255 +Train: [20] [4700/6250] eta: 0:04:43 lr: 0.000117 grad: 0.0746 (0.0807) loss: 0.8674 (0.8700) time: 0.1168 data: 0.0005 max mem: 8255 +Train: [20] [4800/6250] eta: 0:04:25 lr: 0.000117 grad: 0.0764 (0.0806) loss: 0.8758 (0.8701) time: 0.1877 data: 0.1046 max mem: 8255 +Train: [20] [4900/6250] eta: 0:04:06 lr: 0.000117 grad: 0.0767 (0.0806) loss: 0.8763 (0.8701) time: 0.1676 data: 0.0900 max mem: 8255 +Train: [20] [5000/6250] eta: 0:03:48 lr: 0.000117 grad: 0.0745 (0.0805) loss: 0.8720 (0.8702) time: 0.1697 data: 0.1022 max mem: 8255 +Train: [20] [5100/6250] eta: 0:03:30 lr: 0.000117 grad: 0.0690 (0.0805) loss: 0.8756 (0.8702) time: 0.1818 data: 0.1030 max mem: 8255 +Train: [20] [5200/6250] eta: 0:03:12 lr: 0.000117 grad: 0.0763 (0.0805) loss: 0.8744 (0.8703) time: 0.1903 data: 0.1157 max mem: 8255 +Train: [20] [5300/6250] eta: 0:02:54 lr: 0.000117 grad: 0.0779 (0.0805) loss: 0.8689 (0.8703) time: 0.1293 data: 0.0484 max mem: 8255 +Train: [20] [5400/6250] eta: 0:02:36 lr: 0.000117 grad: 0.0827 (0.0805) loss: 0.8688 (0.8703) time: 0.2228 data: 0.1473 max mem: 8255 +Train: [20] [5500/6250] eta: 0:02:18 lr: 0.000117 grad: 0.0709 (0.0805) loss: 0.8692 (0.8703) time: 0.2106 data: 0.1371 max mem: 8255 +Train: [20] [5600/6250] eta: 0:01:59 lr: 0.000117 grad: 0.0757 (0.0805) loss: 0.8705 (0.8703) time: 0.2004 data: 0.1140 max mem: 8255 +Train: [20] [5700/6250] eta: 0:01:41 lr: 0.000117 grad: 0.0817 (0.0805) loss: 0.8713 (0.8704) time: 0.1323 data: 0.0547 max mem: 8255 +Train: [20] [5800/6250] eta: 0:01:22 lr: 0.000117 grad: 0.0774 (0.0805) loss: 0.8711 (0.8704) time: 0.2317 data: 0.1442 max mem: 8255 +Train: [20] [5900/6250] eta: 0:01:04 lr: 0.000117 grad: 0.0719 (0.0804) loss: 0.8784 (0.8704) time: 0.1810 data: 0.0936 max mem: 8255 +Train: [20] [6000/6250] eta: 0:00:45 lr: 0.000116 grad: 0.0799 (0.0805) loss: 0.8652 (0.8704) time: 0.1725 data: 0.0930 max mem: 8255 +Train: [20] [6100/6250] eta: 0:00:27 lr: 0.000116 grad: 0.0788 (0.0805) loss: 0.8619 (0.8704) time: 0.2184 data: 0.1392 max mem: 8255 +Train: [20] [6200/6250] eta: 0:00:09 lr: 0.000116 grad: 0.0774 (0.0805) loss: 0.8642 (0.8705) time: 0.1629 data: 0.0863 max mem: 8255 +Train: [20] [6249/6250] eta: 0:00:00 lr: 0.000116 grad: 0.0782 (0.0805) loss: 0.8679 (0.8705) time: 0.1188 data: 0.0420 max mem: 8255 +Train: [20] Total time: 0:19:07 (0.1835 s / it) +Averaged stats: lr: 0.000116 grad: 0.0782 (0.0805) loss: 0.8679 (0.8705) +Eval (hcp-train-subset): [20] [ 0/62] eta: 0:04:53 loss: 0.8938 (0.8938) time: 4.7378 data: 4.7097 max mem: 8255 +Eval (hcp-train-subset): [20] [61/62] eta: 0:00:00 loss: 0.8852 (0.8856) time: 0.1484 data: 0.1274 max mem: 8255 +Eval (hcp-train-subset): [20] Total time: 0:00:14 (0.2299 s / it) +Averaged stats (hcp-train-subset): loss: 0.8852 (0.8856) +Eval (hcp-val): [20] [ 0/62] eta: 0:05:17 loss: 0.8820 (0.8820) time: 5.1220 data: 5.0912 max mem: 8255 +Eval (hcp-val): [20] [61/62] eta: 0:00:00 loss: 0.8840 (0.8852) time: 0.1254 data: 0.1044 max mem: 8255 +Eval (hcp-val): [20] Total time: 0:00:14 (0.2368 s / it) +Averaged stats (hcp-val): loss: 0.8840 (0.8852) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +Train: [21] [ 0/6250] eta: 7:10:24 lr: 0.000116 grad: 0.0607 (0.0607) loss: 0.9035 (0.9035) time: 4.1320 data: 3.8902 max mem: 8255 +Train: [21] [ 100/6250] eta: 0:23:23 lr: 0.000116 grad: 0.1046 (0.1087) loss: 0.8785 (0.8791) time: 0.1886 data: 0.1042 max mem: 8255 +Train: [21] [ 200/6250] eta: 0:20:32 lr: 0.000116 grad: 0.0883 (0.1044) loss: 0.8705 (0.8760) time: 0.1811 data: 0.0949 max mem: 8255 +Train: [21] [ 300/6250] eta: 0:20:13 lr: 0.000116 grad: 0.0890 (0.0992) loss: 0.8691 (0.8739) time: 0.1883 data: 0.0745 max mem: 8255 +Train: [21] [ 400/6250] eta: 0:21:12 lr: 0.000116 grad: 0.0793 (0.0954) loss: 0.8669 (0.8722) time: 0.3768 data: 0.2337 max mem: 8255 +Train: [21] [ 500/6250] eta: 0:20:37 lr: 0.000116 grad: 0.0793 (0.0926) loss: 0.8710 (0.8709) time: 0.3048 data: 0.2146 max mem: 8255 +Train: [21] [ 600/6250] eta: 0:19:47 lr: 0.000116 grad: 0.0812 (0.0907) loss: 0.8649 (0.8700) time: 0.1667 data: 0.0885 max mem: 8255 +Train: [21] [ 700/6250] eta: 0:19:02 lr: 0.000116 grad: 0.0798 (0.0895) loss: 0.8647 (0.8694) time: 0.1949 data: 0.1014 max mem: 8255 +Train: [21] [ 800/6250] eta: 0:18:35 lr: 0.000116 grad: 0.0742 (0.0881) loss: 0.8697 (0.8695) time: 0.2223 data: 0.1402 max mem: 8255 +Train: [21] [ 900/6250] eta: 0:17:53 lr: 0.000116 grad: 0.0769 (0.0869) loss: 0.8714 (0.8695) time: 0.1457 data: 0.0731 max mem: 8255 +Train: [21] [1000/6250] eta: 0:17:20 lr: 0.000116 grad: 0.0796 (0.0862) loss: 0.8681 (0.8693) time: 0.1752 data: 0.0942 max mem: 8255 +Train: [21] [1100/6250] eta: 0:16:52 lr: 0.000116 grad: 0.0772 (0.0855) loss: 0.8658 (0.8692) time: 0.1208 data: 0.0161 max mem: 8255 +Train: [21] [1200/6250] eta: 0:16:24 lr: 0.000116 grad: 0.0813 (0.0850) loss: 0.8647 (0.8690) time: 0.1764 data: 0.0900 max mem: 8255 +Train: [21] [1300/6250] eta: 0:15:53 lr: 0.000116 grad: 0.0779 (0.0845) loss: 0.8694 (0.8690) time: 0.1700 data: 0.0886 max mem: 8255 +Train: [21] [1400/6250] eta: 0:15:25 lr: 0.000116 grad: 0.0761 (0.0842) loss: 0.8670 (0.8689) time: 0.1699 data: 0.0840 max mem: 8255 +Train: [21] [1500/6250] eta: 0:14:59 lr: 0.000116 grad: 0.0812 (0.0842) loss: 0.8635 (0.8687) time: 0.1774 data: 0.1037 max mem: 8255 +Train: [21] [1600/6250] eta: 0:14:47 lr: 0.000116 grad: 0.0767 (0.0840) loss: 0.8654 (0.8685) time: 0.1487 data: 0.0757 max mem: 8255 +Train: [21] [1700/6250] eta: 0:14:24 lr: 0.000116 grad: 0.0774 (0.0840) loss: 0.8593 (0.8682) time: 0.2160 data: 0.1340 max mem: 8255 +Train: [21] [1800/6250] eta: 0:13:56 lr: 0.000116 grad: 0.0796 (0.0839) loss: 0.8677 (0.8681) time: 0.1120 data: 0.0379 max mem: 8255 +Train: [21] [1900/6250] eta: 0:13:34 lr: 0.000116 grad: 0.0800 (0.0837) loss: 0.8676 (0.8680) time: 0.1458 data: 0.0572 max mem: 8255 +Train: [21] [2000/6250] eta: 0:13:13 lr: 0.000116 grad: 0.0763 (0.0838) loss: 0.8671 (0.8679) time: 0.1668 data: 0.0785 max mem: 8255 +Train: [21] [2100/6250] eta: 0:12:51 lr: 0.000116 grad: 0.0796 (0.0836) loss: 0.8702 (0.8680) time: 0.1562 data: 0.0740 max mem: 8255 +Train: [21] [2200/6250] eta: 0:12:27 lr: 0.000116 grad: 0.0756 (0.0835) loss: 0.8690 (0.8680) time: 0.1812 data: 0.1114 max mem: 8255 +Train: [21] [2300/6250] eta: 0:12:14 lr: 0.000116 grad: 0.0803 (0.0832) loss: 0.8668 (0.8680) time: 0.3176 data: 0.2262 max mem: 8255 +Train: [21] [2400/6250] eta: 0:11:59 lr: 0.000116 grad: 0.0738 (0.0830) loss: 0.8734 (0.8681) time: 0.3243 data: 0.1425 max mem: 8255 +Train: [21] [2500/6250] eta: 0:11:40 lr: 0.000116 grad: 0.0739 (0.0829) loss: 0.8652 (0.8681) time: 0.2112 data: 0.1309 max mem: 8255 +Train: [21] [2600/6250] eta: 0:11:21 lr: 0.000116 grad: 0.0770 (0.0828) loss: 0.8669 (0.8681) time: 0.1936 data: 0.1275 max mem: 8255 +Train: [21] [2700/6250] eta: 0:11:02 lr: 0.000116 grad: 0.0747 (0.0829) loss: 0.8712 (0.8681) time: 0.1845 data: 0.1046 max mem: 8255 +Train: [21] [2800/6250] eta: 0:10:44 lr: 0.000116 grad: 0.0735 (0.0828) loss: 0.8705 (0.8681) time: 0.1787 data: 0.1013 max mem: 8255 +Train: [21] [2900/6250] eta: 0:10:29 lr: 0.000116 grad: 0.0734 (0.0827) loss: 0.8738 (0.8681) time: 0.1632 data: 0.0835 max mem: 8255 +Train: [21] [3000/6250] eta: 0:10:14 lr: 0.000116 grad: 0.0726 (0.0826) loss: 0.8732 (0.8682) time: 0.1982 data: 0.0858 max mem: 8255 +Train: [21] [3100/6250] eta: 0:10:00 lr: 0.000116 grad: 0.0767 (0.0824) loss: 0.8740 (0.8683) time: 0.2539 data: 0.1732 max mem: 8255 +Train: [21] [3200/6250] eta: 0:09:42 lr: 0.000116 grad: 0.0755 (0.0822) loss: 0.8793 (0.8683) time: 0.2996 data: 0.2192 max mem: 8255 +Train: [21] [3300/6250] eta: 0:09:22 lr: 0.000116 grad: 0.0722 (0.0821) loss: 0.8688 (0.8684) time: 0.1945 data: 0.1031 max mem: 8255 +Train: [21] [3400/6250] eta: 0:09:02 lr: 0.000116 grad: 0.0725 (0.0819) loss: 0.8734 (0.8685) time: 0.1557 data: 0.0804 max mem: 8255 +Train: [21] [3500/6250] eta: 0:08:45 lr: 0.000116 grad: 0.0804 (0.0818) loss: 0.8675 (0.8685) time: 0.1196 data: 0.0003 max mem: 8255 +Train: [21] [3600/6250] eta: 0:08:26 lr: 0.000116 grad: 0.0734 (0.0817) loss: 0.8769 (0.8687) time: 0.2301 data: 0.1028 max mem: 8255 +Train: [21] [3700/6250] eta: 0:08:07 lr: 0.000116 grad: 0.0774 (0.0816) loss: 0.8706 (0.8688) time: 0.1512 data: 0.0655 max mem: 8255 +Train: [21] [3800/6250] eta: 0:07:48 lr: 0.000116 grad: 0.0804 (0.0816) loss: 0.8673 (0.8688) time: 0.2301 data: 0.1246 max mem: 8255 +Train: [21] [3900/6250] eta: 0:07:30 lr: 0.000116 grad: 0.0795 (0.0816) loss: 0.8695 (0.8689) time: 0.2126 data: 0.1075 max mem: 8255 +Train: [21] [4000/6250] eta: 0:07:10 lr: 0.000116 grad: 0.0785 (0.0816) loss: 0.8725 (0.8689) time: 0.2978 data: 0.1495 max mem: 8255 +Train: [21] [4100/6250] eta: 0:06:50 lr: 0.000116 grad: 0.0787 (0.0815) loss: 0.8718 (0.8690) time: 0.1632 data: 0.0803 max mem: 8255 +Train: [21] [4200/6250] eta: 0:06:30 lr: 0.000116 grad: 0.0785 (0.0815) loss: 0.8771 (0.8690) time: 0.1671 data: 0.0873 max mem: 8255 +Train: [21] [4300/6250] eta: 0:06:10 lr: 0.000116 grad: 0.0791 (0.0815) loss: 0.8707 (0.8690) time: 0.1356 data: 0.0579 max mem: 8255 +Train: [21] [4400/6250] eta: 0:05:50 lr: 0.000116 grad: 0.0754 (0.0814) loss: 0.8739 (0.8691) time: 0.1979 data: 0.1178 max mem: 8255 +Train: [21] [4500/6250] eta: 0:05:32 lr: 0.000116 grad: 0.0761 (0.0814) loss: 0.8697 (0.8690) time: 0.1026 data: 0.0291 max mem: 8255 +Train: [21] [4600/6250] eta: 0:05:12 lr: 0.000116 grad: 0.0717 (0.0813) loss: 0.8727 (0.8691) time: 0.1652 data: 0.0714 max mem: 8255 +Train: [21] [4700/6250] eta: 0:04:53 lr: 0.000116 grad: 0.0756 (0.0812) loss: 0.8682 (0.8691) time: 0.1780 data: 0.0884 max mem: 8255 +Train: [21] [4800/6250] eta: 0:04:35 lr: 0.000116 grad: 0.0785 (0.0812) loss: 0.8698 (0.8691) time: 0.1878 data: 0.1047 max mem: 8255 +Train: [21] [4900/6250] eta: 0:04:16 lr: 0.000116 grad: 0.0744 (0.0811) loss: 0.8689 (0.8690) time: 0.1453 data: 0.0426 max mem: 8255 +Train: [21] [5000/6250] eta: 0:03:57 lr: 0.000116 grad: 0.0787 (0.0811) loss: 0.8668 (0.8690) time: 0.0936 data: 0.0002 max mem: 8255 +Train: [21] [5100/6250] eta: 0:03:37 lr: 0.000116 grad: 0.0750 (0.0811) loss: 0.8689 (0.8690) time: 0.1911 data: 0.1187 max mem: 8255 +Train: [21] [5200/6250] eta: 0:03:18 lr: 0.000116 grad: 0.0824 (0.0811) loss: 0.8761 (0.8690) time: 0.1262 data: 0.0004 max mem: 8255 +Train: [21] [5300/6250] eta: 0:03:00 lr: 0.000116 grad: 0.0769 (0.0811) loss: 0.8709 (0.8690) time: 0.1173 data: 0.0301 max mem: 8255 +Train: [21] [5400/6250] eta: 0:02:40 lr: 0.000116 grad: 0.0839 (0.0811) loss: 0.8712 (0.8690) time: 0.1516 data: 0.0791 max mem: 8255 +Train: [21] [5500/6250] eta: 0:02:21 lr: 0.000116 grad: 0.0770 (0.0813) loss: 0.8705 (0.8689) time: 0.1784 data: 0.1028 max mem: 8255 +Train: [21] [5600/6250] eta: 0:02:02 lr: 0.000115 grad: 0.0799 (0.0814) loss: 0.8706 (0.8689) time: 0.1049 data: 0.0110 max mem: 8255 +Train: [21] [5700/6250] eta: 0:01:43 lr: 0.000115 grad: 0.0771 (0.0813) loss: 0.8708 (0.8689) time: 0.1620 data: 0.0836 max mem: 8255 +Train: [21] [5800/6250] eta: 0:01:24 lr: 0.000115 grad: 0.0783 (0.0813) loss: 0.8669 (0.8689) time: 0.1486 data: 0.0589 max mem: 8255 +Train: [21] [5900/6250] eta: 0:01:05 lr: 0.000115 grad: 0.0743 (0.0813) loss: 0.8687 (0.8690) time: 0.1712 data: 0.0794 max mem: 8255 +Train: [21] [6000/6250] eta: 0:00:46 lr: 0.000115 grad: 0.0829 (0.0814) loss: 0.8674 (0.8689) time: 0.1510 data: 0.0808 max mem: 8255 +Train: [21] [6100/6250] eta: 0:00:27 lr: 0.000115 grad: 0.0771 (0.0814) loss: 0.8688 (0.8690) time: 0.1510 data: 0.0622 max mem: 8255 +Train: [21] [6200/6250] eta: 0:00:09 lr: 0.000115 grad: 0.0760 (0.0813) loss: 0.8636 (0.8690) time: 0.1811 data: 0.0964 max mem: 8255 +Train: [21] [6249/6250] eta: 0:00:00 lr: 0.000115 grad: 0.0750 (0.0813) loss: 0.8671 (0.8689) time: 0.1508 data: 0.0627 max mem: 8255 +Train: [21] Total time: 0:19:29 (0.1871 s / it) +Averaged stats: lr: 0.000115 grad: 0.0750 (0.0813) loss: 0.8671 (0.8689) +Eval (hcp-train-subset): [21] [ 0/62] eta: 0:05:39 loss: 0.8982 (0.8982) time: 5.4777 data: 5.4513 max mem: 8255 +Eval (hcp-train-subset): [21] [61/62] eta: 0:00:00 loss: 0.8871 (0.8885) time: 0.1296 data: 0.1081 max mem: 8255 +Eval (hcp-train-subset): [21] Total time: 0:00:14 (0.2307 s / it) +Averaged stats (hcp-train-subset): loss: 0.8871 (0.8885) +Eval (hcp-val): [21] [ 0/62] eta: 0:05:13 loss: 0.8824 (0.8824) time: 5.0607 data: 5.0353 max mem: 8255 +Eval (hcp-val): [21] [61/62] eta: 0:00:00 loss: 0.8849 (0.8851) time: 0.1776 data: 0.1564 max mem: 8255 +Eval (hcp-val): [21] Total time: 0:00:16 (0.2682 s / it) +Averaged stats (hcp-val): loss: 0.8849 (0.8851) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +Train: [22] [ 0/6250] eta: 11:37:28 lr: 0.000115 grad: 0.0694 (0.0694) loss: 0.8960 (0.8960) time: 6.6958 data: 6.4862 max mem: 8255 +Train: [22] [ 100/6250] eta: 0:29:11 lr: 0.000115 grad: 0.1017 (0.0928) loss: 0.8760 (0.8826) time: 0.2765 data: 0.1739 max mem: 8255 +Train: [22] [ 200/6250] eta: 0:26:30 lr: 0.000115 grad: 0.0753 (0.0877) loss: 0.8782 (0.8790) time: 0.1933 data: 0.0680 max mem: 8255 +Train: [22] [ 300/6250] eta: 0:23:30 lr: 0.000115 grad: 0.0757 (0.0841) loss: 0.8733 (0.8777) time: 0.1802 data: 0.0991 max mem: 8255 +Train: [22] [ 400/6250] eta: 0:22:52 lr: 0.000115 grad: 0.0710 (0.0824) loss: 0.8760 (0.8767) time: 0.2253 data: 0.1277 max mem: 8255 +Train: [22] [ 500/6250] eta: 0:21:28 lr: 0.000115 grad: 0.0756 (0.0812) loss: 0.8764 (0.8759) time: 0.1497 data: 0.0554 max mem: 8255 +Train: [22] [ 600/6250] eta: 0:20:44 lr: 0.000115 grad: 0.0770 (0.0801) loss: 0.8705 (0.8756) time: 0.1786 data: 0.0737 max mem: 8255 +Train: [22] [ 700/6250] eta: 0:20:10 lr: 0.000115 grad: 0.0765 (0.0796) loss: 0.8798 (0.8753) time: 0.2460 data: 0.1524 max mem: 8255 +Train: [22] [ 800/6250] eta: 0:19:45 lr: 0.000115 grad: 0.0788 (0.0793) loss: 0.8717 (0.8749) time: 0.1173 data: 0.0004 max mem: 8255 +Train: [22] [ 900/6250] eta: 0:19:17 lr: 0.000115 grad: 0.0740 (0.0790) loss: 0.8704 (0.8745) time: 0.1876 data: 0.1036 max mem: 8255 +Train: [22] [1000/6250] eta: 0:18:33 lr: 0.000115 grad: 0.0693 (0.0787) loss: 0.8736 (0.8741) time: 0.1889 data: 0.1059 max mem: 8255 +Train: [22] [1100/6250] eta: 0:18:32 lr: 0.000115 grad: 0.0743 (0.0787) loss: 0.8663 (0.8738) time: 0.4421 data: 0.3601 max mem: 8255 +Train: [22] [1200/6250] eta: 0:17:57 lr: 0.000115 grad: 0.0718 (0.0787) loss: 0.8678 (0.8733) time: 0.2813 data: 0.1838 max mem: 8255 +Train: [22] [1300/6250] eta: 0:17:28 lr: 0.000115 grad: 0.0748 (0.0786) loss: 0.8696 (0.8731) time: 0.1307 data: 0.0320 max mem: 8255 +Train: [22] [1400/6250] eta: 0:16:52 lr: 0.000115 grad: 0.0757 (0.0785) loss: 0.8705 (0.8728) time: 0.1708 data: 0.0944 max mem: 8255 +Train: [22] [1500/6250] eta: 0:16:16 lr: 0.000115 grad: 0.0769 (0.0786) loss: 0.8718 (0.8724) time: 0.1441 data: 0.0595 max mem: 8255 +Train: [22] [1600/6250] eta: 0:15:48 lr: 0.000115 grad: 0.0744 (0.0788) loss: 0.8609 (0.8719) time: 0.1986 data: 0.1105 max mem: 8255 +Train: [22] [1700/6250] eta: 0:15:19 lr: 0.000115 grad: 0.0727 (0.0788) loss: 0.8697 (0.8716) time: 0.2431 data: 0.1586 max mem: 8255 +Train: [22] [1800/6250] eta: 0:14:46 lr: 0.000115 grad: 0.0767 (0.0788) loss: 0.8700 (0.8715) time: 0.1979 data: 0.1205 max mem: 8255 +Train: [22] [1900/6250] eta: 0:14:23 lr: 0.000115 grad: 0.0819 (0.0788) loss: 0.8715 (0.8715) time: 0.2131 data: 0.1415 max mem: 8255 +Train: [22] [2000/6250] eta: 0:14:04 lr: 0.000115 grad: 0.0772 (0.0791) loss: 0.8718 (0.8714) time: 0.1851 data: 0.1001 max mem: 8255 +Train: [22] [2100/6250] eta: 0:13:42 lr: 0.000115 grad: 0.0746 (0.0790) loss: 0.8670 (0.8713) time: 0.2344 data: 0.1604 max mem: 8255 +Train: [22] [2200/6250] eta: 0:13:24 lr: 0.000115 grad: 0.0800 (0.0791) loss: 0.8710 (0.8712) time: 0.1279 data: 0.0438 max mem: 8255 +Train: [22] [2300/6250] eta: 0:13:07 lr: 0.000115 grad: 0.0736 (0.0792) loss: 0.8703 (0.8711) time: 0.2714 data: 0.1789 max mem: 8255 +Train: [22] [2400/6250] eta: 0:12:43 lr: 0.000115 grad: 0.0823 (0.0794) loss: 0.8678 (0.8710) time: 0.1138 data: 0.0003 max mem: 8255 +Train: [22] [2500/6250] eta: 0:12:21 lr: 0.000115 grad: 0.0718 (0.0795) loss: 0.8720 (0.8709) time: 0.1864 data: 0.1021 max mem: 8255 +Train: [22] [2600/6250] eta: 0:12:00 lr: 0.000115 grad: 0.0850 (0.0796) loss: 0.8669 (0.8707) time: 0.1732 data: 0.0930 max mem: 8255 +Train: [22] [2700/6250] eta: 0:11:40 lr: 0.000115 grad: 0.0772 (0.0796) loss: 0.8636 (0.8705) time: 0.0942 data: 0.0002 max mem: 8255 +Train: [22] [2800/6250] eta: 0:11:18 lr: 0.000115 grad: 0.0747 (0.0797) loss: 0.8714 (0.8703) time: 0.2028 data: 0.1155 max mem: 8255 +Train: [22] [2900/6250] eta: 0:10:54 lr: 0.000115 grad: 0.0787 (0.0799) loss: 0.8707 (0.8703) time: 0.1498 data: 0.0768 max mem: 8255 +Train: [22] [3000/6250] eta: 0:10:35 lr: 0.000115 grad: 0.0830 (0.0801) loss: 0.8649 (0.8702) time: 0.2086 data: 0.1295 max mem: 8255 +Train: [22] [3100/6250] eta: 0:10:15 lr: 0.000115 grad: 0.0785 (0.0802) loss: 0.8683 (0.8700) time: 0.1608 data: 0.0799 max mem: 8255 +Train: [22] [3200/6250] eta: 0:09:55 lr: 0.000115 grad: 0.0828 (0.0803) loss: 0.8655 (0.8698) time: 0.1871 data: 0.1180 max mem: 8255 +Train: [22] [3300/6250] eta: 0:09:38 lr: 0.000115 grad: 0.0878 (0.0805) loss: 0.8646 (0.8697) time: 0.3999 data: 0.2832 max mem: 8255 +Train: [22] [3400/6250] eta: 0:09:15 lr: 0.000115 grad: 0.0795 (0.0806) loss: 0.8691 (0.8696) time: 0.1719 data: 0.0854 max mem: 8255 +Train: [22] [3500/6250] eta: 0:08:55 lr: 0.000115 grad: 0.0825 (0.0807) loss: 0.8640 (0.8695) time: 0.2192 data: 0.1266 max mem: 8255 +Train: [22] [3600/6250] eta: 0:08:35 lr: 0.000115 grad: 0.0836 (0.0807) loss: 0.8657 (0.8694) time: 0.1328 data: 0.0039 max mem: 8255 +Train: [22] [3700/6250] eta: 0:08:18 lr: 0.000115 grad: 0.0836 (0.0808) loss: 0.8689 (0.8693) time: 0.1821 data: 0.0796 max mem: 8255 +Train: [22] [3800/6250] eta: 0:07:59 lr: 0.000115 grad: 0.0837 (0.0810) loss: 0.8594 (0.8691) time: 0.2404 data: 0.1504 max mem: 8255 +Train: [22] [3900/6250] eta: 0:07:39 lr: 0.000115 grad: 0.0759 (0.0810) loss: 0.8737 (0.8691) time: 0.0982 data: 0.0083 max mem: 8255 +Train: [22] [4000/6250] eta: 0:07:18 lr: 0.000115 grad: 0.0791 (0.0811) loss: 0.8665 (0.8691) time: 0.1974 data: 0.1112 max mem: 8255 +Train: [22] [4100/6250] eta: 0:07:00 lr: 0.000115 grad: 0.0754 (0.0811) loss: 0.8739 (0.8691) time: 0.3976 data: 0.3209 max mem: 8255 +Train: [22] [4200/6250] eta: 0:06:38 lr: 0.000115 grad: 0.0750 (0.0812) loss: 0.8662 (0.8691) time: 0.2269 data: 0.1495 max mem: 8255 +Train: [22] [4300/6250] eta: 0:06:20 lr: 0.000115 grad: 0.0772 (0.0812) loss: 0.8728 (0.8691) time: 0.2037 data: 0.0927 max mem: 8255 +Train: [22] [4400/6250] eta: 0:06:02 lr: 0.000115 grad: 0.0790 (0.0811) loss: 0.8729 (0.8691) time: 0.4744 data: 0.3542 max mem: 8255 +Train: [22] [4500/6250] eta: 0:05:40 lr: 0.000115 grad: 0.0751 (0.0811) loss: 0.8724 (0.8691) time: 0.1773 data: 0.0896 max mem: 8255 +Train: [22] [4600/6250] eta: 0:05:19 lr: 0.000115 grad: 0.0778 (0.0811) loss: 0.8695 (0.8691) time: 0.1410 data: 0.0536 max mem: 8255 +Train: [22] [4700/6250] eta: 0:04:59 lr: 0.000115 grad: 0.0780 (0.0811) loss: 0.8722 (0.8691) time: 0.1527 data: 0.0248 max mem: 8255 +Train: [22] [4800/6250] eta: 0:04:40 lr: 0.000115 grad: 0.0797 (0.0812) loss: 0.8705 (0.8691) time: 0.1151 data: 0.0271 max mem: 8255 +Train: [22] [4900/6250] eta: 0:04:20 lr: 0.000114 grad: 0.0717 (0.0812) loss: 0.8765 (0.8691) time: 0.1554 data: 0.0778 max mem: 8255 +Train: [22] [5000/6250] eta: 0:04:00 lr: 0.000114 grad: 0.0751 (0.0811) loss: 0.8704 (0.8691) time: 0.1707 data: 0.0898 max mem: 8255 +Train: [22] [5100/6250] eta: 0:03:39 lr: 0.000114 grad: 0.0766 (0.0811) loss: 0.8731 (0.8691) time: 0.0872 data: 0.0002 max mem: 8255 +Train: [22] [5200/6250] eta: 0:03:20 lr: 0.000114 grad: 0.0791 (0.0810) loss: 0.8617 (0.8691) time: 0.1627 data: 0.0887 max mem: 8255 +Train: [22] [5300/6250] eta: 0:03:00 lr: 0.000114 grad: 0.0766 (0.0810) loss: 0.8693 (0.8691) time: 0.1585 data: 0.0730 max mem: 8255 +Train: [22] [5400/6250] eta: 0:02:41 lr: 0.000114 grad: 0.0784 (0.0810) loss: 0.8674 (0.8691) time: 0.1251 data: 0.0437 max mem: 8255 +Train: [22] [5500/6250] eta: 0:02:22 lr: 0.000114 grad: 0.0772 (0.0810) loss: 0.8668 (0.8691) time: 0.1530 data: 0.0823 max mem: 8255 +Train: [22] [5600/6250] eta: 0:02:02 lr: 0.000114 grad: 0.0753 (0.0809) loss: 0.8698 (0.8691) time: 0.1288 data: 0.0630 max mem: 8255 +Train: [22] [5700/6250] eta: 0:01:43 lr: 0.000114 grad: 0.0766 (0.0809) loss: 0.8703 (0.8690) time: 0.1205 data: 0.0385 max mem: 8255 +Train: [22] [5800/6250] eta: 0:01:24 lr: 0.000114 grad: 0.0790 (0.0808) loss: 0.8716 (0.8690) time: 0.1727 data: 0.0940 max mem: 8255 +Train: [22] [5900/6250] eta: 0:01:05 lr: 0.000114 grad: 0.0772 (0.0808) loss: 0.8672 (0.8690) time: 0.1869 data: 0.1061 max mem: 8255 +Train: [22] [6000/6250] eta: 0:00:46 lr: 0.000114 grad: 0.0747 (0.0808) loss: 0.8694 (0.8689) time: 0.1808 data: 0.0956 max mem: 8255 +Train: [22] [6100/6250] eta: 0:00:28 lr: 0.000114 grad: 0.0749 (0.0807) loss: 0.8681 (0.8689) time: 0.2245 data: 0.0830 max mem: 8255 +Train: [22] [6200/6250] eta: 0:00:09 lr: 0.000114 grad: 0.0817 (0.0807) loss: 0.8671 (0.8688) time: 0.1874 data: 0.1087 max mem: 8255 +Train: [22] [6249/6250] eta: 0:00:00 lr: 0.000114 grad: 0.0804 (0.0807) loss: 0.8667 (0.8688) time: 0.4142 data: 0.3075 max mem: 8255 +Train: [22] Total time: 0:19:47 (0.1900 s / it) +Averaged stats: lr: 0.000114 grad: 0.0804 (0.0807) loss: 0.8667 (0.8688) +Eval (hcp-train-subset): [22] [ 0/62] eta: 0:03:46 loss: 0.9015 (0.9015) time: 3.6492 data: 3.5864 max mem: 8255 +Eval (hcp-train-subset): [22] [61/62] eta: 0:00:00 loss: 0.8881 (0.8867) time: 0.1415 data: 0.1203 max mem: 8255 +Eval (hcp-train-subset): [22] Total time: 0:00:15 (0.2453 s / it) +Averaged stats (hcp-train-subset): loss: 0.8881 (0.8867) +Eval (hcp-val): [22] [ 0/62] eta: 0:04:33 loss: 0.8799 (0.8799) time: 4.4114 data: 4.3450 max mem: 8255 +Eval (hcp-val): [22] [61/62] eta: 0:00:00 loss: 0.8830 (0.8842) time: 0.1403 data: 0.1195 max mem: 8255 +Eval (hcp-val): [22] Total time: 0:00:15 (0.2425 s / it) +Averaged stats (hcp-val): loss: 0.8830 (0.8842) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +Train: [23] [ 0/6250] eta: 18:33:15 lr: 0.000114 grad: nan (nan) loss: 0.8783 (0.8783) time: 10.6873 data: 10.5137 max mem: 8255 +Train: [23] [ 100/6250] eta: 0:28:53 lr: 0.000114 grad: 0.0972 (0.0903) loss: 0.8698 (0.8816) time: 0.1423 data: 0.0005 max mem: 8255 +Train: [23] [ 200/6250] eta: 0:23:04 lr: 0.000114 grad: 0.0766 (0.0964) loss: 0.8686 (0.8748) time: 0.1519 data: 0.0781 max mem: 8255 +Train: [23] [ 300/6250] eta: 0:20:47 lr: 0.000114 grad: 0.0721 (0.0901) loss: 0.8710 (0.8728) time: 0.1287 data: 0.0222 max mem: 8255 +Train: [23] [ 400/6250] eta: 0:19:40 lr: 0.000114 grad: 0.0771 (0.0874) loss: 0.8746 (0.8728) time: 0.1539 data: 0.0593 max mem: 8255 +Train: [23] [ 500/6250] eta: 0:18:39 lr: 0.000114 grad: 0.0771 (0.0865) loss: 0.8705 (0.8720) time: 0.1562 data: 0.0720 max mem: 8255 +Train: [23] [ 600/6250] eta: 0:17:54 lr: 0.000114 grad: 0.0747 (0.0852) loss: 0.8696 (0.8712) time: 0.1528 data: 0.0735 max mem: 8255 +Train: [23] [ 700/6250] eta: 0:17:05 lr: 0.000114 grad: 0.0779 (0.0840) loss: 0.8718 (0.8711) time: 0.1596 data: 0.0734 max mem: 8255 +Train: [23] [ 800/6250] eta: 0:16:50 lr: 0.000114 grad: 0.0716 (0.0828) loss: 0.8721 (0.8714) time: 0.2259 data: 0.1545 max mem: 8255 +Train: [23] [ 900/6250] eta: 0:16:47 lr: 0.000114 grad: 0.0710 (0.0819) loss: 0.8734 (0.8716) time: 0.0927 data: 0.0041 max mem: 8255 +Train: [23] [1000/6250] eta: 0:16:27 lr: 0.000114 grad: 0.0721 (0.0813) loss: 0.8718 (0.8716) time: 0.2267 data: 0.1456 max mem: 8255 +Train: [23] [1100/6250] eta: 0:15:51 lr: 0.000114 grad: 0.0758 (0.0809) loss: 0.8708 (0.8713) time: 0.1098 data: 0.0289 max mem: 8255 +Train: [23] [1200/6250] eta: 0:15:30 lr: 0.000114 grad: 0.0802 (0.0808) loss: 0.8718 (0.8711) time: 0.2446 data: 0.1704 max mem: 8255 +Train: [23] [1300/6250] eta: 0:14:59 lr: 0.000114 grad: 0.0700 (0.0803) loss: 0.8690 (0.8709) time: 0.1754 data: 0.0920 max mem: 8255 +Train: [23] [1400/6250] eta: 0:14:35 lr: 0.000114 grad: 0.0709 (0.0801) loss: 0.8669 (0.8706) time: 0.2141 data: 0.1356 max mem: 8255 +Train: [23] [1500/6250] eta: 0:14:10 lr: 0.000114 grad: 0.0750 (0.0797) loss: 0.8676 (0.8704) time: 0.1919 data: 0.1229 max mem: 8255 +Train: [23] [1600/6250] eta: 0:13:47 lr: 0.000114 grad: 0.0731 (0.0796) loss: 0.8705 (0.8702) time: 0.1207 data: 0.0288 max mem: 8255 +Train: [23] [1700/6250] eta: 0:13:22 lr: 0.000114 grad: 0.0755 (0.0796) loss: 0.8653 (0.8698) time: 0.1209 data: 0.0410 max mem: 8255 +Train: [23] [1800/6250] eta: 0:13:03 lr: 0.000114 grad: 0.0773 (0.0794) loss: 0.8633 (0.8696) time: 0.1831 data: 0.1051 max mem: 8255 +Train: [23] [1900/6250] eta: 0:12:48 lr: 0.000114 grad: 0.0747 (0.0794) loss: 0.8683 (0.8693) time: 0.2263 data: 0.1198 max mem: 8255 +Train: [23] [2000/6250] eta: 0:12:36 lr: 0.000114 grad: 0.0729 (0.0793) loss: 0.8714 (0.8691) time: 0.2091 data: 0.1196 max mem: 8255 +Train: [23] [2100/6250] eta: 0:12:21 lr: 0.000114 grad: 0.0803 (0.0792) loss: 0.8741 (0.8690) time: 0.1848 data: 0.1099 max mem: 8255 +Train: [23] [2200/6250] eta: 0:12:14 lr: 0.000114 grad: 0.0754 (0.0792) loss: 0.8663 (0.8689) time: 0.2429 data: 0.1405 max mem: 8255 +Train: [23] [2300/6250] eta: 0:11:58 lr: 0.000114 grad: 0.0815 (0.0793) loss: 0.8693 (0.8688) time: 0.1088 data: 0.0003 max mem: 8255 +Train: [23] [2400/6250] eta: 0:11:40 lr: 0.000114 grad: 0.0821 (0.0794) loss: 0.8632 (0.8687) time: 0.1952 data: 0.1046 max mem: 8255 +Train: [23] [2500/6250] eta: 0:11:23 lr: 0.000114 grad: 0.0777 (0.0794) loss: 0.8645 (0.8686) time: 0.2892 data: 0.1324 max mem: 8255 +Train: [23] [2600/6250] eta: 0:11:04 lr: 0.000114 grad: 0.0692 (0.0794) loss: 0.8694 (0.8685) time: 0.1789 data: 0.1004 max mem: 8255 +Train: [23] [2700/6250] eta: 0:10:42 lr: 0.000114 grad: 0.0730 (0.0794) loss: 0.8722 (0.8685) time: 0.1620 data: 0.0852 max mem: 8255 +Train: [23] [2800/6250] eta: 0:10:25 lr: 0.000114 grad: 0.0770 (0.0794) loss: 0.8711 (0.8684) time: 0.1767 data: 0.1130 max mem: 8255 +Train: [23] [2900/6250] eta: 0:10:05 lr: 0.000114 grad: 0.0759 (0.0795) loss: 0.8677 (0.8684) time: 0.1795 data: 0.1060 max mem: 8255 +Train: [23] [3000/6250] eta: 0:09:48 lr: 0.000114 grad: 0.0793 (0.0796) loss: 0.8665 (0.8682) time: 0.1797 data: 0.0975 max mem: 8255 +Train: [23] [3100/6250] eta: 0:09:31 lr: 0.000114 grad: 0.0785 (0.0797) loss: 0.8710 (0.8683) time: 0.1992 data: 0.1196 max mem: 8255 +Train: [23] [3200/6250] eta: 0:09:15 lr: 0.000114 grad: 0.0787 (0.0797) loss: 0.8701 (0.8682) time: 0.2021 data: 0.1228 max mem: 8255 +Train: [23] [3300/6250] eta: 0:08:59 lr: 0.000114 grad: 0.0762 (0.0798) loss: 0.8640 (0.8681) time: 0.1680 data: 0.0849 max mem: 8255 +Train: [23] [3400/6250] eta: 0:08:40 lr: 0.000114 grad: 0.0746 (0.0797) loss: 0.8682 (0.8681) time: 0.1552 data: 0.0595 max mem: 8255 +Train: [23] [3500/6250] eta: 0:08:21 lr: 0.000114 grad: 0.0722 (0.0797) loss: 0.8684 (0.8682) time: 0.1794 data: 0.0924 max mem: 8255 +Train: [23] [3600/6250] eta: 0:08:03 lr: 0.000114 grad: 0.0779 (0.0797) loss: 0.8725 (0.8681) time: 0.1804 data: 0.0934 max mem: 8255 +Train: [23] [3700/6250] eta: 0:07:46 lr: 0.000114 grad: 0.0757 (0.0796) loss: 0.8724 (0.8682) time: 0.1701 data: 0.0539 max mem: 8255 +Train: [23] [3800/6250] eta: 0:07:27 lr: 0.000114 grad: 0.0756 (0.0795) loss: 0.8676 (0.8682) time: 0.1325 data: 0.0518 max mem: 8255 +Train: [23] [3900/6250] eta: 0:07:08 lr: 0.000114 grad: 0.0756 (0.0796) loss: 0.8622 (0.8681) time: 0.1626 data: 0.0842 max mem: 8255 +Train: [23] [4000/6250] eta: 0:06:49 lr: 0.000113 grad: 0.0807 (0.0795) loss: 0.8687 (0.8682) time: 0.2179 data: 0.1343 max mem: 8255 +Train: [23] [4100/6250] eta: 0:06:32 lr: 0.000113 grad: 0.0735 (0.0794) loss: 0.8690 (0.8682) time: 0.1670 data: 0.0771 max mem: 8255 +Train: [23] [4200/6250] eta: 0:06:13 lr: 0.000113 grad: 0.0763 (0.0794) loss: 0.8706 (0.8683) time: 0.2087 data: 0.1312 max mem: 8255 +Train: [23] [4300/6250] eta: 0:05:54 lr: 0.000113 grad: 0.0737 (0.0794) loss: 0.8666 (0.8683) time: 0.1732 data: 0.0661 max mem: 8255 +Train: [23] [4400/6250] eta: 0:05:36 lr: 0.000113 grad: 0.0771 (0.0793) loss: 0.8741 (0.8683) time: 0.1777 data: 0.0986 max mem: 8255 +Train: [23] [4500/6250] eta: 0:05:17 lr: 0.000113 grad: 0.0780 (0.0794) loss: 0.8719 (0.8683) time: 0.1502 data: 0.0657 max mem: 8255 +Train: [23] [4600/6250] eta: 0:04:59 lr: 0.000113 grad: 0.0785 (0.0794) loss: 0.8619 (0.8683) time: 0.1284 data: 0.0254 max mem: 8255 +Train: [23] [4700/6250] eta: 0:04:40 lr: 0.000113 grad: 0.0807 (0.0794) loss: 0.8649 (0.8683) time: 0.1531 data: 0.0599 max mem: 8255 +Train: [23] [4800/6250] eta: 0:04:21 lr: 0.000113 grad: 0.0719 (0.0794) loss: 0.8649 (0.8683) time: 0.1535 data: 0.0705 max mem: 8255 +Train: [23] [4900/6250] eta: 0:04:04 lr: 0.000113 grad: 0.0838 (0.0794) loss: 0.8670 (0.8682) time: 0.2017 data: 0.1004 max mem: 8255 +Train: [23] [5000/6250] eta: 0:03:45 lr: 0.000113 grad: 0.0754 (0.0794) loss: 0.8698 (0.8682) time: 0.2120 data: 0.1365 max mem: 8255 +Train: [23] [5100/6250] eta: 0:03:26 lr: 0.000113 grad: 0.0754 (0.0794) loss: 0.8653 (0.8681) time: 0.1510 data: 0.0729 max mem: 8255 +Train: [23] [5200/6250] eta: 0:03:08 lr: 0.000113 grad: 0.0756 (0.0794) loss: 0.8678 (0.8680) time: 0.2381 data: 0.1560 max mem: 8255 +Train: [23] [5300/6250] eta: 0:02:49 lr: 0.000113 grad: 0.0772 (0.0794) loss: 0.8628 (0.8679) time: 0.1540 data: 0.0797 max mem: 8255 +Train: [23] [5400/6250] eta: 0:02:31 lr: 0.000113 grad: 0.0779 (0.0795) loss: 0.8630 (0.8679) time: 0.1515 data: 0.0761 max mem: 8255 +Train: [23] [5500/6250] eta: 0:02:13 lr: 0.000113 grad: 0.0792 (0.0796) loss: 0.8678 (0.8678) time: 0.1196 data: 0.0317 max mem: 8255 +Train: [23] [5600/6250] eta: 0:01:55 lr: 0.000113 grad: 0.0771 (0.0797) loss: 0.8692 (0.8677) time: 0.1634 data: 0.0827 max mem: 8255 +Train: [23] [5700/6250] eta: 0:01:37 lr: 0.000113 grad: 0.0766 (0.0797) loss: 0.8623 (0.8677) time: 0.1391 data: 0.0537 max mem: 8255 +Train: [23] [5800/6250] eta: 0:01:19 lr: 0.000113 grad: 0.0833 (0.0797) loss: 0.8605 (0.8676) time: 0.1632 data: 0.0826 max mem: 8255 +Train: [23] [5900/6250] eta: 0:01:01 lr: 0.000113 grad: 0.0804 (0.0797) loss: 0.8652 (0.8676) time: 0.1586 data: 0.0749 max mem: 8255 +Train: [23] [6000/6250] eta: 0:00:44 lr: 0.000113 grad: 0.0801 (0.0798) loss: 0.8641 (0.8675) time: 0.1809 data: 0.1074 max mem: 8255 +Train: [23] [6100/6250] eta: 0:00:26 lr: 0.000113 grad: 0.0840 (0.0798) loss: 0.8597 (0.8675) time: 0.2301 data: 0.1575 max mem: 8255 +Train: [23] [6200/6250] eta: 0:00:08 lr: 0.000113 grad: 0.0823 (0.0799) loss: 0.8616 (0.8674) time: 0.1347 data: 0.0503 max mem: 8255 +Train: [23] [6249/6250] eta: 0:00:00 lr: 0.000113 grad: 0.0803 (0.0799) loss: 0.8666 (0.8673) time: 0.1717 data: 0.0883 max mem: 8255 +Train: [23] Total time: 0:18:34 (0.1783 s / it) +Averaged stats: lr: 0.000113 grad: 0.0803 (0.0799) loss: 0.8666 (0.8673) +Eval (hcp-train-subset): [23] [ 0/62] eta: 0:04:42 loss: 0.8973 (0.8973) time: 4.5488 data: 4.5144 max mem: 8255 +Eval (hcp-train-subset): [23] [61/62] eta: 0:00:00 loss: 0.8865 (0.8871) time: 0.1154 data: 0.0943 max mem: 8255 +Eval (hcp-train-subset): [23] Total time: 0:00:14 (0.2336 s / it) +Averaged stats (hcp-train-subset): loss: 0.8865 (0.8871) +Eval (hcp-val): [23] [ 0/62] eta: 0:05:26 loss: 0.8808 (0.8808) time: 5.2603 data: 5.2345 max mem: 8255 +Eval (hcp-val): [23] [61/62] eta: 0:00:00 loss: 0.8829 (0.8842) time: 0.1564 data: 0.1354 max mem: 8255 +Eval (hcp-val): [23] Total time: 0:00:14 (0.2300 s / it) +Averaged stats (hcp-val): loss: 0.8829 (0.8842) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +Train: [24] [ 0/6250] eta: 7:36:28 lr: 0.000113 grad: 0.1386 (0.1386) loss: 0.8621 (0.8621) time: 4.3822 data: 4.1595 max mem: 8255 +Train: [24] [ 100/6250] eta: 0:22:32 lr: 0.000113 grad: 0.0881 (0.1006) loss: 0.8690 (0.8695) time: 0.1502 data: 0.0561 max mem: 8255 +Train: [24] [ 200/6250] eta: 0:19:35 lr: 0.000113 grad: 0.0784 (0.0988) loss: 0.8545 (0.8655) time: 0.1709 data: 0.0887 max mem: 8255 +Train: [24] [ 300/6250] eta: 0:18:19 lr: 0.000113 grad: 0.0792 (0.0935) loss: 0.8677 (0.8644) time: 0.1537 data: 0.0766 max mem: 8255 +Train: [24] [ 400/6250] eta: 0:17:01 lr: 0.000113 grad: 0.0726 (0.0897) loss: 0.8677 (0.8649) time: 0.1498 data: 0.0704 max mem: 8255 +Train: [24] [ 500/6250] eta: 0:16:43 lr: 0.000113 grad: 0.0731 (0.0871) loss: 0.8644 (0.8651) time: 0.1721 data: 0.0890 max mem: 8255 +Train: [24] [ 600/6250] eta: 0:16:25 lr: 0.000113 grad: 0.0742 (0.0852) loss: 0.8682 (0.8654) time: 0.1805 data: 0.0921 max mem: 8255 +Train: [24] [ 700/6250] eta: 0:16:11 lr: 0.000113 grad: 0.0699 (0.0840) loss: 0.8652 (0.8657) time: 0.2201 data: 0.1335 max mem: 8255 +Train: [24] [ 800/6250] eta: 0:15:40 lr: 0.000113 grad: 0.0719 (0.0831) loss: 0.8684 (0.8658) time: 0.1654 data: 0.0619 max mem: 8255 +Train: [24] [ 900/6250] eta: 0:15:15 lr: 0.000113 grad: 0.0745 (0.0826) loss: 0.8671 (0.8658) time: 0.1846 data: 0.1063 max mem: 8255 +Train: [24] [1000/6250] eta: 0:14:58 lr: 0.000113 grad: 0.0770 (0.0822) loss: 0.8672 (0.8660) time: 0.1409 data: 0.0492 max mem: 8255 +Train: [24] [1100/6250] eta: 0:14:34 lr: 0.000113 grad: 0.0768 (0.0819) loss: 0.8599 (0.8660) time: 0.1033 data: 0.0078 max mem: 8255 +Train: [24] [1200/6250] eta: 0:14:15 lr: 0.000113 grad: 0.0748 (0.0815) loss: 0.8678 (0.8660) time: 0.1288 data: 0.0555 max mem: 8255 +Train: [24] [1300/6250] eta: 0:13:56 lr: 0.000113 grad: 0.0817 (0.0813) loss: 0.8595 (0.8659) time: 0.1637 data: 0.0852 max mem: 8255 +Train: [24] [1400/6250] eta: 0:13:34 lr: 0.000113 grad: 0.0797 (0.0811) loss: 0.8672 (0.8658) time: 0.1700 data: 0.0874 max mem: 8255 +Train: [24] [1500/6250] eta: 0:13:18 lr: 0.000113 grad: 0.0775 (0.0809) loss: 0.8666 (0.8657) time: 0.1521 data: 0.0656 max mem: 8255 +Train: [24] [1600/6250] eta: 0:12:57 lr: 0.000113 grad: 0.0855 (0.0810) loss: 0.8639 (0.8656) time: 0.1564 data: 0.0699 max mem: 8255 +Train: [24] [1700/6250] eta: 0:12:40 lr: 0.000113 grad: 0.0762 (0.0809) loss: 0.8601 (0.8654) time: 0.1859 data: 0.0813 max mem: 8255 +Train: [24] [1800/6250] eta: 0:12:21 lr: 0.000113 grad: 0.0727 (0.0808) loss: 0.8625 (0.8653) time: 0.1475 data: 0.0613 max mem: 8255 +Train: [24] [1900/6250] eta: 0:12:08 lr: 0.000113 grad: 0.0745 (0.0807) loss: 0.8630 (0.8653) time: 0.2861 data: 0.2114 max mem: 8255 +Train: [24] [2000/6250] eta: 0:11:50 lr: 0.000113 grad: 0.0749 (0.0807) loss: 0.8654 (0.8652) time: 0.2358 data: 0.1579 max mem: 8255 +Train: [24] [2100/6250] eta: 0:11:48 lr: 0.000113 grad: 0.0789 (0.0807) loss: 0.8676 (0.8652) time: 0.3859 data: 0.2771 max mem: 8255 +Train: [24] [2200/6250] eta: 0:11:29 lr: 0.000113 grad: 0.0769 (0.0806) loss: 0.8608 (0.8651) time: 0.2042 data: 0.0813 max mem: 8255 +Train: [24] [2300/6250] eta: 0:11:10 lr: 0.000113 grad: 0.0795 (0.0805) loss: 0.8625 (0.8649) time: 0.1136 data: 0.0255 max mem: 8255 +Train: [24] [2400/6250] eta: 0:10:56 lr: 0.000113 grad: 0.0784 (0.0804) loss: 0.8603 (0.8649) time: 0.2198 data: 0.0893 max mem: 8255 +Train: [24] [2500/6250] eta: 0:10:42 lr: 0.000113 grad: 0.0813 (0.0803) loss: 0.8579 (0.8649) time: 0.1064 data: 0.0133 max mem: 8255 +Train: [24] [2600/6250] eta: 0:10:35 lr: 0.000113 grad: 0.0820 (0.0804) loss: 0.8597 (0.8648) time: 0.3620 data: 0.2030 max mem: 8255 +Train: [24] [2700/6250] eta: 0:10:13 lr: 0.000113 grad: 0.0782 (0.0804) loss: 0.8660 (0.8648) time: 0.1743 data: 0.0920 max mem: 8255 +Train: [24] [2800/6250] eta: 0:10:03 lr: 0.000113 grad: 0.0788 (0.0804) loss: 0.8587 (0.8648) time: 0.4360 data: 0.3417 max mem: 8255 +Train: [24] [2900/6250] eta: 0:09:43 lr: 0.000112 grad: 0.0812 (0.0803) loss: 0.8705 (0.8648) time: 0.2076 data: 0.1280 max mem: 8255 +Train: [24] [3000/6250] eta: 0:09:28 lr: 0.000112 grad: 0.0744 (0.0803) loss: 0.8624 (0.8648) time: 0.1448 data: 0.0653 max mem: 8255 +Train: [24] [3100/6250] eta: 0:09:10 lr: 0.000112 grad: 0.0780 (0.0802) loss: 0.8623 (0.8648) time: 0.2092 data: 0.1334 max mem: 8255 +Train: [24] [3200/6250] eta: 0:08:53 lr: 0.000112 grad: 0.0785 (0.0801) loss: 0.8681 (0.8649) time: 0.1742 data: 0.0949 max mem: 8255 +Train: [24] [3300/6250] eta: 0:08:37 lr: 0.000112 grad: 0.0800 (0.0801) loss: 0.8670 (0.8649) time: 0.1617 data: 0.0866 max mem: 8255 +Train: [24] [3400/6250] eta: 0:08:20 lr: 0.000112 grad: 0.0742 (0.0799) loss: 0.8665 (0.8650) time: 0.1973 data: 0.1164 max mem: 8255 +Train: [24] [3500/6250] eta: 0:08:03 lr: 0.000112 grad: 0.0750 (0.0799) loss: 0.8619 (0.8651) time: 0.1793 data: 0.0940 max mem: 8255 +Train: [24] [3600/6250] eta: 0:07:46 lr: 0.000112 grad: 0.0742 (0.0798) loss: 0.8713 (0.8652) time: 0.1743 data: 0.0903 max mem: 8255 +Train: [24] [3700/6250] eta: 0:07:30 lr: 0.000112 grad: 0.0752 (0.0797) loss: 0.8742 (0.8653) time: 0.1953 data: 0.1085 max mem: 8255 +Train: [24] [3800/6250] eta: 0:07:12 lr: 0.000112 grad: 0.0745 (0.0797) loss: 0.8611 (0.8653) time: 0.1657 data: 0.0825 max mem: 8255 +Train: [24] [3900/6250] eta: 0:06:55 lr: 0.000112 grad: 0.0807 (0.0797) loss: 0.8666 (0.8654) time: 0.1116 data: 0.0050 max mem: 8255 +Train: [24] [4000/6250] eta: 0:06:38 lr: 0.000112 grad: 0.0788 (0.0797) loss: 0.8618 (0.8654) time: 0.2305 data: 0.1360 max mem: 8255 +Train: [24] [4100/6250] eta: 0:06:21 lr: 0.000112 grad: 0.0785 (0.0796) loss: 0.8660 (0.8655) time: 0.1576 data: 0.0737 max mem: 8255 +Train: [24] [4200/6250] eta: 0:06:04 lr: 0.000112 grad: 0.0794 (0.0796) loss: 0.8719 (0.8656) time: 0.2994 data: 0.2062 max mem: 8255 +Train: [24] [4300/6250] eta: 0:05:46 lr: 0.000112 grad: 0.0746 (0.0796) loss: 0.8705 (0.8657) time: 0.1871 data: 0.1143 max mem: 8255 +Train: [24] [4400/6250] eta: 0:05:27 lr: 0.000112 grad: 0.0719 (0.0797) loss: 0.8686 (0.8657) time: 0.1676 data: 0.0896 max mem: 8255 +Train: [24] [4500/6250] eta: 0:05:09 lr: 0.000112 grad: 0.0710 (0.0796) loss: 0.8758 (0.8658) time: 0.1504 data: 0.0740 max mem: 8255 +Train: [24] [4600/6250] eta: 0:04:50 lr: 0.000112 grad: 0.0766 (0.0796) loss: 0.8720 (0.8658) time: 0.1365 data: 0.0513 max mem: 8255 +Train: [24] [4700/6250] eta: 0:04:32 lr: 0.000112 grad: 0.0773 (0.0796) loss: 0.8666 (0.8659) time: 0.1687 data: 0.0958 max mem: 8255 +Train: [24] [4800/6250] eta: 0:04:14 lr: 0.000112 grad: 0.0769 (0.0796) loss: 0.8664 (0.8659) time: 0.1612 data: 0.0866 max mem: 8255 +Train: [24] [4900/6250] eta: 0:03:56 lr: 0.000112 grad: 0.0745 (0.0796) loss: 0.8647 (0.8659) time: 0.1494 data: 0.0722 max mem: 8255 +Train: [24] [5000/6250] eta: 0:03:38 lr: 0.000112 grad: 0.0845 (0.0796) loss: 0.8654 (0.8659) time: 0.1386 data: 0.0534 max mem: 8255 +Train: [24] [5100/6250] eta: 0:03:20 lr: 0.000112 grad: 0.0818 (0.0796) loss: 0.8673 (0.8659) time: 0.1476 data: 0.0608 max mem: 8255 +Train: [24] [5200/6250] eta: 0:03:03 lr: 0.000112 grad: 0.0724 (0.0796) loss: 0.8641 (0.8658) time: 0.1621 data: 0.0837 max mem: 8255 +Train: [24] [5300/6250] eta: 0:02:45 lr: 0.000112 grad: 0.0778 (0.0797) loss: 0.8573 (0.8657) time: 0.1776 data: 0.0917 max mem: 8255 +Train: [24] [5400/6250] eta: 0:02:27 lr: 0.000112 grad: 0.0852 (0.0797) loss: 0.8591 (0.8656) time: 0.1648 data: 0.0934 max mem: 8255 +Train: [24] [5500/6250] eta: 0:02:10 lr: 0.000112 grad: 0.0791 (0.0798) loss: 0.8600 (0.8656) time: 0.1599 data: 0.0527 max mem: 8255 +Train: [24] [5600/6250] eta: 0:01:54 lr: 0.000112 grad: 0.0843 (0.0799) loss: 0.8620 (0.8654) time: 0.1835 data: 0.0875 max mem: 8255 +Train: [24] [5700/6250] eta: 0:01:37 lr: 0.000112 grad: 0.0767 (0.0801) loss: 0.8616 (0.8653) time: 0.4808 data: 0.3430 max mem: 8255 +Train: [24] [5800/6250] eta: 0:01:19 lr: 0.000112 grad: 0.0778 (0.0802) loss: 0.8617 (0.8652) time: 0.1930 data: 0.1220 max mem: 8255 +Train: [24] [5900/6250] eta: 0:01:01 lr: 0.000112 grad: 0.0874 (0.0803) loss: 0.8566 (0.8650) time: 0.2076 data: 0.1144 max mem: 8255 +Train: [24] [6000/6250] eta: 0:00:44 lr: 0.000112 grad: 0.0756 (0.0804) loss: 0.8563 (0.8649) time: 0.1418 data: 0.0585 max mem: 8255 +Train: [24] [6100/6250] eta: 0:00:26 lr: 0.000112 grad: 0.0752 (0.0804) loss: 0.8596 (0.8648) time: 0.2359 data: 0.1225 max mem: 8255 +Train: [24] [6200/6250] eta: 0:00:08 lr: 0.000112 grad: 0.0764 (0.0805) loss: 0.8543 (0.8647) time: 0.1806 data: 0.0902 max mem: 8255 +Train: [24] [6249/6250] eta: 0:00:00 lr: 0.000112 grad: 0.0842 (0.0805) loss: 0.8603 (0.8647) time: 0.2452 data: 0.1639 max mem: 8255 +Train: [24] Total time: 0:18:38 (0.1790 s / it) +Averaged stats: lr: 0.000112 grad: 0.0842 (0.0805) loss: 0.8603 (0.8647) +Eval (hcp-train-subset): [24] [ 0/62] eta: 0:03:24 loss: 0.8989 (0.8989) time: 3.3022 data: 3.2114 max mem: 8255 +Eval (hcp-train-subset): [24] [61/62] eta: 0:00:00 loss: 0.8865 (0.8867) time: 0.1354 data: 0.1145 max mem: 8255 +Eval (hcp-train-subset): [24] Total time: 0:00:15 (0.2544 s / it) +Averaged stats (hcp-train-subset): loss: 0.8865 (0.8867) +Making plots (hcp-train-subset): example=34 +Eval (hcp-val): [24] [ 0/62] eta: 0:06:20 loss: 0.8784 (0.8784) time: 6.1404 data: 6.1104 max mem: 8255 +Eval (hcp-val): [24] [61/62] eta: 0:00:00 loss: 0.8822 (0.8839) time: 0.1417 data: 0.1212 max mem: 8255 +Eval (hcp-val): [24] Total time: 0:00:14 (0.2280 s / it) +Averaged stats (hcp-val): loss: 0.8822 (0.8839) +Making plots (hcp-val): example=15 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +Train: [25] [ 0/6250] eta: 8:20:51 lr: 0.000112 grad: 0.0564 (0.0564) loss: 0.9314 (0.9314) time: 4.8082 data: 4.5862 max mem: 8255 +Train: [25] [ 100/6250] eta: 0:22:39 lr: 0.000112 grad: 0.0875 (0.0912) loss: 0.8891 (0.8877) time: 0.1595 data: 0.0781 max mem: 8255 +Train: [25] [ 200/6250] eta: 0:20:12 lr: 0.000112 grad: 0.0828 (0.0895) loss: 0.8789 (0.8833) time: 0.1738 data: 0.0828 max mem: 8255 +Train: [25] [ 300/6250] eta: 0:19:06 lr: 0.000112 grad: 0.0793 (0.0888) loss: 0.8685 (0.8793) time: 0.1360 data: 0.0503 max mem: 8255 +Train: [25] [ 400/6250] eta: 0:18:14 lr: 0.000112 grad: 0.0735 (0.0856) loss: 0.8757 (0.8776) time: 0.1695 data: 0.0896 max mem: 8255 +Train: [25] [ 500/6250] eta: 0:17:45 lr: 0.000112 grad: 0.0803 (0.0843) loss: 0.8659 (0.8764) time: 0.1610 data: 0.0739 max mem: 8255 +Train: [25] [ 600/6250] eta: 0:17:50 lr: 0.000112 grad: 0.0756 (0.0839) loss: 0.8684 (0.8750) time: 0.2644 data: 0.1718 max mem: 8255 +Train: [25] [ 700/6250] eta: 0:18:26 lr: 0.000112 grad: 0.0816 (0.0835) loss: 0.8689 (0.8738) time: 0.2333 data: 0.1394 max mem: 8255 +Train: [25] [ 800/6250] eta: 0:17:46 lr: 0.000112 grad: 0.0739 (0.0828) loss: 0.8669 (0.8731) time: 0.1408 data: 0.0482 max mem: 8255 +Train: [25] [ 900/6250] eta: 0:17:11 lr: 0.000112 grad: 0.0717 (0.0821) loss: 0.8652 (0.8725) time: 0.1537 data: 0.0718 max mem: 8255 +Train: [25] [1000/6250] eta: 0:16:37 lr: 0.000112 grad: 0.0789 (0.0818) loss: 0.8619 (0.8719) time: 0.1783 data: 0.1058 max mem: 8255 +Train: [25] [1100/6250] eta: 0:15:56 lr: 0.000112 grad: 0.0782 (0.0816) loss: 0.8644 (0.8711) time: 0.1350 data: 0.0521 max mem: 8255 +Train: [25] [1200/6250] eta: 0:15:30 lr: 0.000112 grad: 0.0778 (0.0815) loss: 0.8671 (0.8705) time: 0.1706 data: 0.0879 max mem: 8255 +Train: [25] [1300/6250] eta: 0:15:03 lr: 0.000112 grad: 0.0784 (0.0815) loss: 0.8633 (0.8699) time: 0.1949 data: 0.1071 max mem: 8255 +Train: [25] [1400/6250] eta: 0:14:40 lr: 0.000112 grad: 0.0804 (0.0815) loss: 0.8625 (0.8692) time: 0.1737 data: 0.0938 max mem: 8255 +Train: [25] [1500/6250] eta: 0:14:16 lr: 0.000112 grad: 0.0807 (0.0813) loss: 0.8629 (0.8687) time: 0.1469 data: 0.0690 max mem: 8255 +Train: [25] [1600/6250] eta: 0:13:59 lr: 0.000111 grad: 0.0775 (0.0814) loss: 0.8646 (0.8682) time: 0.2210 data: 0.1442 max mem: 8255 +Train: [25] [1700/6250] eta: 0:13:49 lr: 0.000111 grad: 0.0775 (0.0811) loss: 0.8613 (0.8681) time: 0.2055 data: 0.1233 max mem: 8255 +Train: [25] [1800/6250] eta: 0:13:43 lr: 0.000111 grad: 0.0879 (0.0813) loss: 0.8596 (0.8677) time: 0.1927 data: 0.0844 max mem: 8255 +Train: [25] [1900/6250] eta: 0:13:28 lr: 0.000111 grad: 0.0774 (0.0814) loss: 0.8606 (0.8675) time: 0.2248 data: 0.0686 max mem: 8255 +Train: [25] [2000/6250] eta: 0:13:11 lr: 0.000111 grad: 0.0825 (0.0815) loss: 0.8623 (0.8672) time: 0.1860 data: 0.1132 max mem: 8255 +Train: [25] [2100/6250] eta: 0:12:50 lr: 0.000111 grad: 0.0784 (0.0815) loss: 0.8663 (0.8671) time: 0.1477 data: 0.0695 max mem: 8255 +Train: [25] [2200/6250] eta: 0:12:29 lr: 0.000111 grad: 0.0778 (0.0815) loss: 0.8611 (0.8669) time: 0.1832 data: 0.1198 max mem: 8255 +Train: [25] [2300/6250] eta: 0:12:12 lr: 0.000111 grad: 0.0807 (0.0815) loss: 0.8634 (0.8667) time: 0.1934 data: 0.0992 max mem: 8255 +Train: [25] [2400/6250] eta: 0:11:59 lr: 0.000111 grad: 0.0843 (0.0816) loss: 0.8615 (0.8665) time: 0.1705 data: 0.0701 max mem: 8255 +Train: [25] [2500/6250] eta: 0:11:36 lr: 0.000111 grad: 0.0849 (0.0817) loss: 0.8620 (0.8663) time: 0.1159 data: 0.0287 max mem: 8255 +Train: [25] [2600/6250] eta: 0:11:13 lr: 0.000111 grad: 0.0847 (0.0817) loss: 0.8593 (0.8662) time: 0.1375 data: 0.0584 max mem: 8255 +Train: [25] [2700/6250] eta: 0:10:51 lr: 0.000111 grad: 0.0791 (0.0818) loss: 0.8609 (0.8660) time: 0.1498 data: 0.0731 max mem: 8255 +Train: [25] [2800/6250] eta: 0:10:30 lr: 0.000111 grad: 0.0806 (0.0819) loss: 0.8639 (0.8660) time: 0.1610 data: 0.0931 max mem: 8255 +Train: [25] [2900/6250] eta: 0:10:10 lr: 0.000111 grad: 0.0725 (0.0819) loss: 0.8624 (0.8659) time: 0.1995 data: 0.1064 max mem: 8255 +Train: [25] [3000/6250] eta: 0:09:58 lr: 0.000111 grad: 0.0844 (0.0820) loss: 0.8617 (0.8659) time: 0.1892 data: 0.0951 max mem: 8255 +Train: [25] [3100/6250] eta: 0:09:37 lr: 0.000111 grad: 0.0797 (0.0821) loss: 0.8663 (0.8657) time: 0.1557 data: 0.0714 max mem: 8255 +Train: [25] [3200/6250] eta: 0:09:19 lr: 0.000111 grad: 0.0785 (0.0821) loss: 0.8652 (0.8657) time: 0.2105 data: 0.1233 max mem: 8255 +Train: [25] [3300/6250] eta: 0:08:58 lr: 0.000111 grad: 0.0805 (0.0822) loss: 0.8667 (0.8656) time: 0.1633 data: 0.0928 max mem: 8255 +Train: [25] [3400/6250] eta: 0:08:41 lr: 0.000111 grad: 0.0770 (0.0821) loss: 0.8623 (0.8655) time: 0.2142 data: 0.1273 max mem: 8255 +Train: [25] [3500/6250] eta: 0:08:23 lr: 0.000111 grad: 0.0833 (0.0821) loss: 0.8588 (0.8654) time: 0.1836 data: 0.1084 max mem: 8255 +Train: [25] [3600/6250] eta: 0:08:06 lr: 0.000111 grad: 0.0744 (0.0821) loss: 0.8598 (0.8653) time: 0.3083 data: 0.2324 max mem: 8255 +Train: [25] [3700/6250] eta: 0:07:47 lr: 0.000111 grad: 0.0797 (0.0822) loss: 0.8560 (0.8651) time: 0.2290 data: 0.1573 max mem: 8255 +Train: [25] [3800/6250] eta: 0:07:28 lr: 0.000111 grad: 0.0766 (0.0822) loss: 0.8682 (0.8650) time: 0.1929 data: 0.1032 max mem: 8255 +Train: [25] [3900/6250] eta: 0:07:10 lr: 0.000111 grad: 0.0763 (0.0822) loss: 0.8667 (0.8649) time: 0.1971 data: 0.0760 max mem: 8255 +Train: [25] [4000/6250] eta: 0:06:51 lr: 0.000111 grad: 0.0818 (0.0823) loss: 0.8688 (0.8648) time: 0.1406 data: 0.0642 max mem: 8255 +Train: [25] [4100/6250] eta: 0:06:32 lr: 0.000111 grad: 0.0798 (0.0823) loss: 0.8583 (0.8648) time: 0.1615 data: 0.0670 max mem: 8255 +Train: [25] [4200/6250] eta: 0:06:12 lr: 0.000111 grad: 0.0757 (0.0824) loss: 0.8677 (0.8648) time: 0.1498 data: 0.0722 max mem: 8255 +Train: [25] [4300/6250] eta: 0:05:54 lr: 0.000111 grad: 0.0812 (0.0824) loss: 0.8674 (0.8648) time: 0.1960 data: 0.1301 max mem: 8255 +Train: [25] [4400/6250] eta: 0:05:35 lr: 0.000111 grad: 0.0864 (0.0824) loss: 0.8653 (0.8648) time: 0.1671 data: 0.0914 max mem: 8255 +Train: [25] [4500/6250] eta: 0:05:16 lr: 0.000111 grad: 0.0801 (0.0824) loss: 0.8694 (0.8648) time: 0.1539 data: 0.0779 max mem: 8255 +Train: [25] [4600/6250] eta: 0:04:57 lr: 0.000111 grad: 0.0800 (0.0825) loss: 0.8653 (0.8647) time: 0.1598 data: 0.0869 max mem: 8255 +Train: [25] [4700/6250] eta: 0:04:39 lr: 0.000111 grad: 0.0772 (0.0825) loss: 0.8629 (0.8647) time: 0.2103 data: 0.1309 max mem: 8255 +Train: [25] [4800/6250] eta: 0:04:20 lr: 0.000111 grad: 0.0818 (0.0825) loss: 0.8653 (0.8647) time: 0.1575 data: 0.0797 max mem: 8255 +Train: [25] [4900/6250] eta: 0:04:02 lr: 0.000111 grad: 0.0814 (0.0826) loss: 0.8615 (0.8646) time: 0.1705 data: 0.0892 max mem: 8255 +Train: [25] [5000/6250] eta: 0:03:44 lr: 0.000111 grad: 0.0818 (0.0826) loss: 0.8600 (0.8645) time: 0.1549 data: 0.0915 max mem: 8255 +Train: [25] [5100/6250] eta: 0:03:26 lr: 0.000111 grad: 0.0799 (0.0826) loss: 0.8615 (0.8645) time: 0.1790 data: 0.1045 max mem: 8255 +Train: [25] [5200/6250] eta: 0:03:07 lr: 0.000111 grad: 0.0787 (0.0826) loss: 0.8574 (0.8645) time: 0.1621 data: 0.0876 max mem: 8255 +Train: [25] [5300/6250] eta: 0:02:50 lr: 0.000111 grad: 0.0759 (0.0826) loss: 0.8634 (0.8645) time: 0.2542 data: 0.1711 max mem: 8255 +Train: [25] [5400/6250] eta: 0:02:32 lr: 0.000111 grad: 0.0816 (0.0826) loss: 0.8676 (0.8645) time: 0.1826 data: 0.0985 max mem: 8255 +Train: [25] [5500/6250] eta: 0:02:14 lr: 0.000111 grad: 0.0798 (0.0826) loss: 0.8629 (0.8645) time: 0.1756 data: 0.0894 max mem: 8255 +Train: [25] [5600/6250] eta: 0:01:57 lr: 0.000111 grad: 0.0772 (0.0826) loss: 0.8638 (0.8645) time: 0.2520 data: 0.1310 max mem: 8255 +Train: [25] [5700/6250] eta: 0:01:39 lr: 0.000111 grad: 0.0780 (0.0826) loss: 0.8616 (0.8645) time: 0.2650 data: 0.1690 max mem: 8255 +Train: [25] [5800/6250] eta: 0:01:21 lr: 0.000111 grad: 0.0813 (0.0827) loss: 0.8631 (0.8645) time: 0.1125 data: 0.0233 max mem: 8255 +Train: [25] [5900/6250] eta: 0:01:03 lr: 0.000111 grad: 0.0839 (0.0827) loss: 0.8595 (0.8644) time: 0.1344 data: 0.0295 max mem: 8255 +Train: [25] [6000/6250] eta: 0:00:45 lr: 0.000111 grad: 0.0777 (0.0827) loss: 0.8557 (0.8644) time: 0.3298 data: 0.2430 max mem: 8255 +Train: [25] [6100/6250] eta: 0:00:27 lr: 0.000111 grad: 0.0845 (0.0827) loss: 0.8563 (0.8643) time: 0.1559 data: 0.0768 max mem: 8255 +Train: [25] [6200/6250] eta: 0:00:09 lr: 0.000111 grad: 0.0815 (0.0827) loss: 0.8682 (0.8643) time: 0.3420 data: 0.2311 max mem: 8255 +Train: [25] [6249/6250] eta: 0:00:00 lr: 0.000111 grad: 0.0809 (0.0828) loss: 0.8603 (0.8643) time: 0.2184 data: 0.1371 max mem: 8255 +Train: [25] Total time: 0:19:04 (0.1832 s / it) +Averaged stats: lr: 0.000111 grad: 0.0809 (0.0828) loss: 0.8603 (0.8643) +Eval (hcp-train-subset): [25] [ 0/62] eta: 0:05:31 loss: 0.8982 (0.8982) time: 5.3452 data: 5.3135 max mem: 8255 +Eval (hcp-train-subset): [25] [61/62] eta: 0:00:00 loss: 0.8849 (0.8844) time: 0.1488 data: 0.1261 max mem: 8255 +Eval (hcp-train-subset): [25] Total time: 0:00:14 (0.2353 s / it) +Averaged stats (hcp-train-subset): loss: 0.8849 (0.8844) +Eval (hcp-val): [25] [ 0/62] eta: 0:05:34 loss: 0.8808 (0.8808) time: 5.3905 data: 5.3622 max mem: 8255 +Eval (hcp-val): [25] [61/62] eta: 0:00:00 loss: 0.8837 (0.8837) time: 0.1366 data: 0.1155 max mem: 8255 +Eval (hcp-val): [25] Total time: 0:00:14 (0.2309 s / it) +Averaged stats (hcp-val): loss: 0.8837 (0.8837) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +Train: [26] [ 0/6250] eta: 9:42:14 lr: 0.000111 grad: 0.1052 (0.1052) loss: 0.8499 (0.8499) time: 5.5895 data: 5.4193 max mem: 8255 +Train: [26] [ 100/6250] eta: 0:23:38 lr: 0.000111 grad: 0.0792 (0.0837) loss: 0.8785 (0.8846) time: 0.1670 data: 0.0657 max mem: 8255 +Train: [26] [ 200/6250] eta: 0:20:35 lr: 0.000110 grad: 0.0825 (0.0907) loss: 0.8717 (0.8763) time: 0.1705 data: 0.0869 max mem: 8255 +Train: [26] [ 300/6250] eta: 0:19:13 lr: 0.000110 grad: 0.0771 (0.0872) loss: 0.8704 (0.8733) time: 0.1784 data: 0.0941 max mem: 8255 +Train: [26] [ 400/6250] eta: 0:18:06 lr: 0.000110 grad: 0.0769 (0.0858) loss: 0.8722 (0.8717) time: 0.1576 data: 0.0736 max mem: 8255 +Train: [26] [ 500/6250] eta: 0:17:24 lr: 0.000110 grad: 0.0735 (0.0838) loss: 0.8692 (0.8710) time: 0.1898 data: 0.1132 max mem: 8255 +Train: [26] [ 600/6250] eta: 0:16:38 lr: 0.000110 grad: 0.0704 (0.0825) loss: 0.8698 (0.8706) time: 0.1751 data: 0.0891 max mem: 8255 +Train: [26] [ 700/6250] eta: 0:16:17 lr: 0.000110 grad: 0.0730 (0.0818) loss: 0.8602 (0.8698) time: 0.1991 data: 0.0974 max mem: 8255 +Train: [26] [ 800/6250] eta: 0:16:22 lr: 0.000110 grad: 0.0788 (0.0813) loss: 0.8692 (0.8693) time: 0.1663 data: 0.0636 max mem: 8255 +Train: [26] [ 900/6250] eta: 0:16:19 lr: 0.000110 grad: 0.0737 (0.0808) loss: 0.8628 (0.8687) time: 0.1515 data: 0.0620 max mem: 8255 +Train: [26] [1000/6250] eta: 0:15:53 lr: 0.000110 grad: 0.0716 (0.0806) loss: 0.8624 (0.8681) time: 0.2457 data: 0.1707 max mem: 8255 +Train: [26] [1100/6250] eta: 0:15:23 lr: 0.000110 grad: 0.0791 (0.0804) loss: 0.8578 (0.8676) time: 0.2104 data: 0.1218 max mem: 8255 +Train: [26] [1200/6250] eta: 0:14:52 lr: 0.000110 grad: 0.0711 (0.0800) loss: 0.8708 (0.8672) time: 0.1620 data: 0.0811 max mem: 8255 +Train: [26] [1300/6250] eta: 0:14:29 lr: 0.000110 grad: 0.0766 (0.0800) loss: 0.8630 (0.8667) time: 0.1809 data: 0.1057 max mem: 8255 +Train: [26] [1400/6250] eta: 0:14:07 lr: 0.000110 grad: 0.0734 (0.0799) loss: 0.8624 (0.8664) time: 0.2029 data: 0.1242 max mem: 8255 +Train: [26] [1500/6250] eta: 0:13:43 lr: 0.000110 grad: 0.0753 (0.0798) loss: 0.8663 (0.8661) time: 0.1873 data: 0.1120 max mem: 8255 +Train: [26] [1600/6250] eta: 0:13:19 lr: 0.000110 grad: 0.0715 (0.0796) loss: 0.8630 (0.8660) time: 0.1448 data: 0.0638 max mem: 8255 +Train: [26] [1700/6250] eta: 0:13:02 lr: 0.000110 grad: 0.0763 (0.0797) loss: 0.8559 (0.8657) time: 0.1457 data: 0.0652 max mem: 8255 +Train: [26] [1800/6250] eta: 0:12:52 lr: 0.000110 grad: 0.0802 (0.0796) loss: 0.8646 (0.8656) time: 0.1435 data: 0.0504 max mem: 8255 +Train: [26] [1900/6250] eta: 0:12:37 lr: 0.000110 grad: 0.0763 (0.0797) loss: 0.8630 (0.8655) time: 0.1436 data: 0.0560 max mem: 8255 +Train: [26] [2000/6250] eta: 0:12:31 lr: 0.000110 grad: 0.0826 (0.0799) loss: 0.8516 (0.8653) time: 0.3046 data: 0.2101 max mem: 8255 +Train: [26] [2100/6250] eta: 0:12:10 lr: 0.000110 grad: 0.0760 (0.0801) loss: 0.8609 (0.8651) time: 0.2018 data: 0.0773 max mem: 8255 +Train: [26] [2200/6250] eta: 0:11:55 lr: 0.000110 grad: 0.0764 (0.0800) loss: 0.8666 (0.8650) time: 0.1507 data: 0.0689 max mem: 8255 +Train: [26] [2300/6250] eta: 0:11:41 lr: 0.000110 grad: 0.0784 (0.0800) loss: 0.8638 (0.8649) time: 0.2751 data: 0.1619 max mem: 8255 +Train: [26] [2400/6250] eta: 0:11:21 lr: 0.000110 grad: 0.0797 (0.0801) loss: 0.8547 (0.8647) time: 0.2101 data: 0.1492 max mem: 8255 +Train: [26] [2500/6250] eta: 0:11:02 lr: 0.000110 grad: 0.0774 (0.0801) loss: 0.8568 (0.8645) time: 0.1737 data: 0.0926 max mem: 8255 +Train: [26] [2600/6250] eta: 0:10:44 lr: 0.000110 grad: 0.0801 (0.0801) loss: 0.8679 (0.8644) time: 0.2000 data: 0.1199 max mem: 8255 +Train: [26] [2700/6250] eta: 0:10:23 lr: 0.000110 grad: 0.0816 (0.0803) loss: 0.8578 (0.8642) time: 0.1542 data: 0.0786 max mem: 8255 +Train: [26] [2800/6250] eta: 0:10:03 lr: 0.000110 grad: 0.0748 (0.0802) loss: 0.8666 (0.8642) time: 0.1776 data: 0.1082 max mem: 8255 +Train: [26] [2900/6250] eta: 0:09:43 lr: 0.000110 grad: 0.0816 (0.0803) loss: 0.8582 (0.8641) time: 0.1431 data: 0.0736 max mem: 8255 +Train: [26] [3000/6250] eta: 0:09:24 lr: 0.000110 grad: 0.0798 (0.0803) loss: 0.8641 (0.8640) time: 0.1873 data: 0.1200 max mem: 8255 +Train: [26] [3100/6250] eta: 0:09:05 lr: 0.000110 grad: 0.0788 (0.0804) loss: 0.8546 (0.8638) time: 0.1463 data: 0.0719 max mem: 8255 +Train: [26] [3200/6250] eta: 0:08:49 lr: 0.000110 grad: 0.0805 (0.0804) loss: 0.8568 (0.8637) time: 0.1572 data: 0.0882 max mem: 8255 +Train: [26] [3300/6250] eta: 0:08:29 lr: 0.000110 grad: 0.0812 (0.0805) loss: 0.8578 (0.8636) time: 0.1466 data: 0.0762 max mem: 8255 +Train: [26] [3400/6250] eta: 0:08:11 lr: 0.000110 grad: 0.0810 (0.0806) loss: 0.8655 (0.8635) time: 0.1733 data: 0.1072 max mem: 8255 +Train: [26] [3500/6250] eta: 0:07:55 lr: 0.000110 grad: 0.0856 (0.0807) loss: 0.8569 (0.8634) time: 0.1509 data: 0.0696 max mem: 8255 +Train: [26] [3600/6250] eta: 0:07:37 lr: 0.000110 grad: 0.0813 (0.0807) loss: 0.8598 (0.8633) time: 0.1620 data: 0.0868 max mem: 8255 +Train: [26] [3700/6250] eta: 0:07:19 lr: 0.000110 grad: 0.0827 (0.0808) loss: 0.8647 (0.8633) time: 0.1510 data: 0.0728 max mem: 8255 +Train: [26] [3800/6250] eta: 0:07:01 lr: 0.000110 grad: 0.0790 (0.0808) loss: 0.8615 (0.8632) time: 0.1837 data: 0.1085 max mem: 8255 +Train: [26] [3900/6250] eta: 0:06:42 lr: 0.000110 grad: 0.0818 (0.0808) loss: 0.8628 (0.8632) time: 0.1368 data: 0.0679 max mem: 8255 +Train: [26] [4000/6250] eta: 0:06:23 lr: 0.000110 grad: 0.0716 (0.0808) loss: 0.8658 (0.8633) time: 0.1352 data: 0.0613 max mem: 8255 +Train: [26] [4100/6250] eta: 0:06:03 lr: 0.000110 grad: 0.0800 (0.0808) loss: 0.8562 (0.8632) time: 0.1206 data: 0.0425 max mem: 8255 +Train: [26] [4200/6250] eta: 0:05:44 lr: 0.000110 grad: 0.0790 (0.0809) loss: 0.8637 (0.8631) time: 0.1137 data: 0.0462 max mem: 8255 +Train: [26] [4300/6250] eta: 0:05:26 lr: 0.000110 grad: 0.0788 (0.0809) loss: 0.8646 (0.8631) time: 0.1383 data: 0.0616 max mem: 8255 +Train: [26] [4400/6250] eta: 0:05:07 lr: 0.000110 grad: 0.0801 (0.0809) loss: 0.8568 (0.8631) time: 0.1314 data: 0.0452 max mem: 8255 +Train: [26] [4500/6250] eta: 0:04:49 lr: 0.000110 grad: 0.0808 (0.0809) loss: 0.8590 (0.8631) time: 0.1216 data: 0.0466 max mem: 8255 +Train: [26] [4600/6250] eta: 0:04:31 lr: 0.000110 grad: 0.0862 (0.0810) loss: 0.8638 (0.8631) time: 0.1399 data: 0.0594 max mem: 8255 +Train: [26] [4700/6250] eta: 0:04:13 lr: 0.000110 grad: 0.0750 (0.0810) loss: 0.8642 (0.8631) time: 0.1364 data: 0.0524 max mem: 8255 +Train: [26] [4800/6250] eta: 0:03:56 lr: 0.000109 grad: 0.0727 (0.0810) loss: 0.8698 (0.8631) time: 0.1288 data: 0.0528 max mem: 8255 +Train: [26] [4900/6250] eta: 0:03:38 lr: 0.000109 grad: 0.0834 (0.0809) loss: 0.8632 (0.8631) time: 0.1228 data: 0.0478 max mem: 8255 +Train: [26] [5000/6250] eta: 0:03:21 lr: 0.000109 grad: 0.0786 (0.0809) loss: 0.8649 (0.8631) time: 0.1176 data: 0.0352 max mem: 8255 +Train: [26] [5100/6250] eta: 0:03:04 lr: 0.000109 grad: 0.0787 (0.0809) loss: 0.8649 (0.8631) time: 0.1265 data: 0.0377 max mem: 8255 +Train: [26] [5200/6250] eta: 0:02:47 lr: 0.000109 grad: 0.0776 (0.0810) loss: 0.8655 (0.8632) time: 0.1332 data: 0.0606 max mem: 8255 +Train: [26] [5300/6250] eta: 0:02:31 lr: 0.000109 grad: 0.0811 (0.0810) loss: 0.8648 (0.8631) time: 0.1163 data: 0.0467 max mem: 8255 +Train: [26] [5400/6250] eta: 0:02:14 lr: 0.000109 grad: 0.0741 (0.0810) loss: 0.8587 (0.8631) time: 0.1035 data: 0.0222 max mem: 8255 +Train: [26] [5500/6250] eta: 0:01:58 lr: 0.000109 grad: 0.0763 (0.0810) loss: 0.8631 (0.8631) time: 0.1277 data: 0.0511 max mem: 8255 +Train: [26] [5600/6250] eta: 0:01:42 lr: 0.000109 grad: 0.0768 (0.0810) loss: 0.8626 (0.8630) time: 0.1545 data: 0.0774 max mem: 8255 +Train: [26] [5700/6250] eta: 0:01:26 lr: 0.000109 grad: 0.0773 (0.0810) loss: 0.8613 (0.8630) time: 0.1505 data: 0.0807 max mem: 8255 +Train: [26] [5800/6250] eta: 0:01:10 lr: 0.000109 grad: 0.0882 (0.0811) loss: 0.8538 (0.8629) time: 0.1676 data: 0.0925 max mem: 8255 +Train: [26] [5900/6250] eta: 0:00:55 lr: 0.000109 grad: 0.0765 (0.0811) loss: 0.8632 (0.8629) time: 0.1646 data: 0.0776 max mem: 8255 +Train: [26] [6000/6250] eta: 0:00:39 lr: 0.000109 grad: 0.0850 (0.0812) loss: 0.8595 (0.8629) time: 0.1499 data: 0.0798 max mem: 8255 +Train: [26] [6100/6250] eta: 0:00:23 lr: 0.000109 grad: 0.0842 (0.0812) loss: 0.8554 (0.8628) time: 0.1446 data: 0.0756 max mem: 8255 +Train: [26] [6200/6250] eta: 0:00:07 lr: 0.000109 grad: 0.0806 (0.0812) loss: 0.8569 (0.8627) time: 0.1083 data: 0.0153 max mem: 8255 +Train: [26] [6249/6250] eta: 0:00:00 lr: 0.000109 grad: 0.0775 (0.0812) loss: 0.8566 (0.8627) time: 0.1543 data: 0.0689 max mem: 8255 +Train: [26] Total time: 0:16:29 (0.1583 s / it) +Averaged stats: lr: 0.000109 grad: 0.0775 (0.0812) loss: 0.8566 (0.8627) +Eval (hcp-train-subset): [26] [ 0/62] eta: 0:04:35 loss: 0.8965 (0.8965) time: 4.4515 data: 4.4255 max mem: 8255 +Eval (hcp-train-subset): [26] [61/62] eta: 0:00:00 loss: 0.8832 (0.8830) time: 0.1430 data: 0.1209 max mem: 8255 +Eval (hcp-train-subset): [26] Total time: 0:00:15 (0.2437 s / it) +Averaged stats (hcp-train-subset): loss: 0.8832 (0.8830) +Eval (hcp-val): [26] [ 0/62] eta: 0:04:59 loss: 0.8798 (0.8798) time: 4.8332 data: 4.8064 max mem: 8255 +Eval (hcp-val): [26] [61/62] eta: 0:00:00 loss: 0.8827 (0.8834) time: 0.1299 data: 0.1076 max mem: 8255 +Eval (hcp-val): [26] Total time: 0:00:14 (0.2389 s / it) +Averaged stats (hcp-val): loss: 0.8827 (0.8834) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +Train: [27] [ 0/6250] eta: 9:52:53 lr: 0.000109 grad: 0.1182 (0.1182) loss: 0.8804 (0.8804) time: 5.6917 data: 5.4903 max mem: 8255 +Train: [27] [ 100/6250] eta: 0:23:47 lr: 0.000109 grad: 0.0946 (0.1055) loss: 0.8632 (0.8687) time: 0.2075 data: 0.1142 max mem: 8255 +Train: [27] [ 200/6250] eta: 0:19:57 lr: 0.000109 grad: 0.0767 (0.0932) loss: 0.8622 (0.8670) time: 0.1729 data: 0.0918 max mem: 8255 +Train: [27] [ 300/6250] eta: 0:17:55 lr: 0.000109 grad: 0.0758 (0.0898) loss: 0.8679 (0.8675) time: 0.1348 data: 0.0493 max mem: 8255 +Train: [27] [ 400/6250] eta: 0:17:03 lr: 0.000109 grad: 0.0861 (0.0880) loss: 0.8597 (0.8666) time: 0.1560 data: 0.0832 max mem: 8255 +Train: [27] [ 500/6250] eta: 0:16:21 lr: 0.000109 grad: 0.0784 (0.0866) loss: 0.8678 (0.8660) time: 0.1439 data: 0.0467 max mem: 8255 +Train: [27] [ 600/6250] eta: 0:15:29 lr: 0.000109 grad: 0.0752 (0.0861) loss: 0.8662 (0.8656) time: 0.1365 data: 0.0536 max mem: 8255 +Train: [27] [ 700/6250] eta: 0:14:52 lr: 0.000109 grad: 0.0827 (0.0853) loss: 0.8616 (0.8654) time: 0.1428 data: 0.0613 max mem: 8255 +Train: [27] [ 800/6250] eta: 0:14:15 lr: 0.000109 grad: 0.0805 (0.0846) loss: 0.8594 (0.8653) time: 0.1281 data: 0.0336 max mem: 8255 +Train: [27] [ 900/6250] eta: 0:13:52 lr: 0.000109 grad: 0.0809 (0.0840) loss: 0.8604 (0.8654) time: 0.1387 data: 0.0623 max mem: 8255 +Train: [27] [1000/6250] eta: 0:13:27 lr: 0.000109 grad: 0.0750 (0.0835) loss: 0.8594 (0.8651) time: 0.1231 data: 0.0517 max mem: 8255 +Train: [27] [1100/6250] eta: 0:13:06 lr: 0.000109 grad: 0.0798 (0.0832) loss: 0.8559 (0.8649) time: 0.1160 data: 0.0425 max mem: 8255 +Train: [27] [1200/6250] eta: 0:12:56 lr: 0.000109 grad: 0.0804 (0.0830) loss: 0.8594 (0.8644) time: 0.1595 data: 0.0838 max mem: 8255 +Train: [27] [1300/6250] eta: 0:12:42 lr: 0.000109 grad: 0.0771 (0.0830) loss: 0.8535 (0.8640) time: 0.1152 data: 0.0376 max mem: 8255 +Train: [27] [1400/6250] eta: 0:12:28 lr: 0.000109 grad: 0.0796 (0.0832) loss: 0.8677 (0.8635) time: 0.1827 data: 0.1077 max mem: 8255 +Train: [27] [1500/6250] eta: 0:12:16 lr: 0.000109 grad: 0.0802 (0.0832) loss: 0.8571 (0.8631) time: 0.0824 data: 0.0002 max mem: 8255 +Train: [27] [1600/6250] eta: 0:11:55 lr: 0.000109 grad: 0.0827 (0.0834) loss: 0.8471 (0.8624) time: 0.1465 data: 0.0761 max mem: 8255 +Train: [27] [1700/6250] eta: 0:11:39 lr: 0.000109 grad: 0.0795 (0.0833) loss: 0.8531 (0.8621) time: 0.2068 data: 0.1272 max mem: 8255 +Train: [27] [1800/6250] eta: 0:11:18 lr: 0.000109 grad: 0.0803 (0.0832) loss: 0.8574 (0.8619) time: 0.1922 data: 0.1166 max mem: 8255 +Train: [27] [1900/6250] eta: 0:11:00 lr: 0.000109 grad: 0.0793 (0.0833) loss: 0.8580 (0.8616) time: 0.1581 data: 0.0917 max mem: 8255 +Train: [27] [2000/6250] eta: 0:10:43 lr: 0.000109 grad: 0.0784 (0.0833) loss: 0.8642 (0.8616) time: 0.1380 data: 0.0742 max mem: 8255 +Train: [27] [2100/6250] eta: 0:10:25 lr: 0.000109 grad: 0.0812 (0.0835) loss: 0.8593 (0.8614) time: 0.1410 data: 0.0708 max mem: 8255 +Train: [27] [2200/6250] eta: 0:10:07 lr: 0.000109 grad: 0.0806 (0.0835) loss: 0.8619 (0.8614) time: 0.1471 data: 0.0757 max mem: 8255 +Train: [27] [2300/6250] eta: 0:09:51 lr: 0.000109 grad: 0.0724 (0.0835) loss: 0.8686 (0.8613) time: 0.1362 data: 0.0584 max mem: 8255 +Train: [27] [2400/6250] eta: 0:09:35 lr: 0.000109 grad: 0.0845 (0.0836) loss: 0.8598 (0.8612) time: 0.1216 data: 0.0544 max mem: 8255 +Train: [27] [2500/6250] eta: 0:09:20 lr: 0.000109 grad: 0.0821 (0.0837) loss: 0.8551 (0.8611) time: 0.1648 data: 0.0883 max mem: 8255 +Train: [27] [2600/6250] eta: 0:09:08 lr: 0.000109 grad: 0.0866 (0.0838) loss: 0.8531 (0.8610) time: 0.0979 data: 0.0017 max mem: 8255 +Train: [27] [2700/6250] eta: 0:08:57 lr: 0.000109 grad: 0.0797 (0.0838) loss: 0.8590 (0.8609) time: 0.1393 data: 0.0575 max mem: 8255 +Train: [27] [2800/6250] eta: 0:08:44 lr: 0.000109 grad: 0.0881 (0.0838) loss: 0.8586 (0.8608) time: 0.1603 data: 0.0937 max mem: 8255 +Train: [27] [2900/6250] eta: 0:08:28 lr: 0.000109 grad: 0.0869 (0.0839) loss: 0.8611 (0.8608) time: 0.1550 data: 0.0777 max mem: 8255 +Train: [27] [3000/6250] eta: 0:08:12 lr: 0.000109 grad: 0.0781 (0.0839) loss: 0.8648 (0.8607) time: 0.1392 data: 0.0697 max mem: 8255 +Train: [27] [3100/6250] eta: 0:07:58 lr: 0.000108 grad: 0.0761 (0.0839) loss: 0.8666 (0.8607) time: 0.1435 data: 0.0515 max mem: 8255 +Train: [27] [3200/6250] eta: 0:07:43 lr: 0.000108 grad: 0.0790 (0.0839) loss: 0.8644 (0.8608) time: 0.1455 data: 0.0715 max mem: 8255 +Train: [27] [3300/6250] eta: 0:07:28 lr: 0.000108 grad: 0.0787 (0.0838) loss: 0.8567 (0.8609) time: 0.1458 data: 0.0626 max mem: 8255 +Train: [27] [3400/6250] eta: 0:07:12 lr: 0.000108 grad: 0.0770 (0.0837) loss: 0.8561 (0.8609) time: 0.1559 data: 0.0792 max mem: 8255 +Train: [27] [3500/6250] eta: 0:06:58 lr: 0.000108 grad: 0.0791 (0.0837) loss: 0.8600 (0.8609) time: 0.1535 data: 0.0820 max mem: 8255 +Train: [27] [3600/6250] eta: 0:06:44 lr: 0.000108 grad: 0.0763 (0.0837) loss: 0.8605 (0.8609) time: 0.1481 data: 0.0799 max mem: 8255 +Train: [27] [3700/6250] eta: 0:06:29 lr: 0.000108 grad: 0.0860 (0.0837) loss: 0.8539 (0.8609) time: 0.1589 data: 0.0880 max mem: 8255 +Train: [27] [3800/6250] eta: 0:06:14 lr: 0.000108 grad: 0.0824 (0.0836) loss: 0.8595 (0.8609) time: 0.1587 data: 0.0861 max mem: 8255 +Train: [27] [3900/6250] eta: 0:05:59 lr: 0.000108 grad: 0.0788 (0.0836) loss: 0.8643 (0.8610) time: 0.1609 data: 0.0796 max mem: 8255 +Train: [27] [4000/6250] eta: 0:05:43 lr: 0.000108 grad: 0.0783 (0.0835) loss: 0.8643 (0.8611) time: 0.1545 data: 0.0846 max mem: 8255 +Train: [27] [4100/6250] eta: 0:05:28 lr: 0.000108 grad: 0.0802 (0.0834) loss: 0.8642 (0.8611) time: 0.1365 data: 0.0511 max mem: 8255 +Train: [27] [4200/6250] eta: 0:05:12 lr: 0.000108 grad: 0.0737 (0.0834) loss: 0.8644 (0.8611) time: 0.1547 data: 0.0708 max mem: 8255 +Train: [27] [4300/6250] eta: 0:04:56 lr: 0.000108 grad: 0.0852 (0.0833) loss: 0.8656 (0.8611) time: 0.1316 data: 0.0455 max mem: 8255 +Train: [27] [4400/6250] eta: 0:04:41 lr: 0.000108 grad: 0.0806 (0.0833) loss: 0.8599 (0.8611) time: 0.1282 data: 0.0469 max mem: 8255 +Train: [27] [4500/6250] eta: 0:04:26 lr: 0.000108 grad: 0.0827 (0.0833) loss: 0.8621 (0.8611) time: 0.1788 data: 0.1092 max mem: 8255 +Train: [27] [4600/6250] eta: 0:04:11 lr: 0.000108 grad: 0.0798 (0.0834) loss: 0.8638 (0.8611) time: 0.1861 data: 0.1143 max mem: 8255 +Train: [27] [4700/6250] eta: 0:03:56 lr: 0.000108 grad: 0.0828 (0.0834) loss: 0.8612 (0.8610) time: 0.1318 data: 0.0520 max mem: 8255 +Train: [27] [4800/6250] eta: 0:03:41 lr: 0.000108 grad: 0.0754 (0.0835) loss: 0.8651 (0.8610) time: 0.1610 data: 0.0857 max mem: 8255 +Train: [27] [4900/6250] eta: 0:03:25 lr: 0.000108 grad: 0.0801 (0.0835) loss: 0.8617 (0.8610) time: 0.1317 data: 0.0608 max mem: 8255 +Train: [27] [5000/6250] eta: 0:03:09 lr: 0.000108 grad: 0.0793 (0.0834) loss: 0.8624 (0.8610) time: 0.1218 data: 0.0490 max mem: 8255 +Train: [27] [5100/6250] eta: 0:02:54 lr: 0.000108 grad: 0.0823 (0.0835) loss: 0.8567 (0.8610) time: 0.1110 data: 0.0314 max mem: 8255 +Train: [27] [5200/6250] eta: 0:02:38 lr: 0.000108 grad: 0.0745 (0.0835) loss: 0.8663 (0.8610) time: 0.1184 data: 0.0376 max mem: 8255 +Train: [27] [5300/6250] eta: 0:02:23 lr: 0.000108 grad: 0.0752 (0.0835) loss: 0.8596 (0.8610) time: 0.1435 data: 0.0752 max mem: 8255 +Train: [27] [5400/6250] eta: 0:02:08 lr: 0.000108 grad: 0.0738 (0.0834) loss: 0.8596 (0.8610) time: 0.1249 data: 0.0461 max mem: 8255 +Train: [27] [5500/6250] eta: 0:01:52 lr: 0.000108 grad: 0.0931 (0.0834) loss: 0.8580 (0.8611) time: 0.1395 data: 0.0603 max mem: 8255 +Train: [27] [5600/6250] eta: 0:01:37 lr: 0.000108 grad: 0.0810 (0.0835) loss: 0.8612 (0.8611) time: 0.1406 data: 0.0643 max mem: 8255 +Train: [27] [5700/6250] eta: 0:01:22 lr: 0.000108 grad: 0.0820 (0.0835) loss: 0.8646 (0.8611) time: 0.1365 data: 0.0481 max mem: 8255 +Train: [27] [5800/6250] eta: 0:01:07 lr: 0.000108 grad: 0.0757 (0.0834) loss: 0.8643 (0.8612) time: 0.1599 data: 0.0865 max mem: 8255 +Train: [27] [5900/6250] eta: 0:00:52 lr: 0.000108 grad: 0.0826 (0.0834) loss: 0.8630 (0.8612) time: 0.1534 data: 0.0796 max mem: 8255 +Train: [27] [6000/6250] eta: 0:00:37 lr: 0.000108 grad: 0.0757 (0.0834) loss: 0.8631 (0.8613) time: 0.1542 data: 0.0743 max mem: 8255 +Train: [27] [6100/6250] eta: 0:00:22 lr: 0.000108 grad: 0.0725 (0.0833) loss: 0.8672 (0.8614) time: 0.1373 data: 0.0721 max mem: 8255 +Train: [27] [6200/6250] eta: 0:00:07 lr: 0.000108 grad: 0.0764 (0.0832) loss: 0.8673 (0.8615) time: 0.1429 data: 0.0589 max mem: 8255 +Train: [27] [6249/6250] eta: 0:00:00 lr: 0.000108 grad: 0.0781 (0.0832) loss: 0.8619 (0.8615) time: 0.1408 data: 0.0539 max mem: 8255 +Train: [27] Total time: 0:15:45 (0.1513 s / it) +Averaged stats: lr: 0.000108 grad: 0.0781 (0.0832) loss: 0.8619 (0.8615) +Eval (hcp-train-subset): [27] [ 0/62] eta: 0:03:41 loss: 0.8971 (0.8971) time: 3.5659 data: 3.4926 max mem: 8255 +Eval (hcp-train-subset): [27] [61/62] eta: 0:00:00 loss: 0.8825 (0.8840) time: 0.1611 data: 0.1402 max mem: 8255 +Eval (hcp-train-subset): [27] Total time: 0:00:15 (0.2424 s / it) +Averaged stats (hcp-train-subset): loss: 0.8825 (0.8840) +Eval (hcp-val): [27] [ 0/62] eta: 0:03:40 loss: 0.8808 (0.8808) time: 3.5530 data: 3.4942 max mem: 8255 +Eval (hcp-val): [27] [61/62] eta: 0:00:00 loss: 0.8824 (0.8840) time: 0.1669 data: 0.1444 max mem: 8255 +Eval (hcp-val): [27] Total time: 0:00:15 (0.2445 s / it) +Averaged stats (hcp-val): loss: 0.8824 (0.8840) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +Train: [28] [ 0/6250] eta: 10:26:27 lr: 0.000108 grad: 0.0562 (0.0562) loss: 0.9020 (0.9020) time: 6.0141 data: 5.9175 max mem: 8255 +Train: [28] [ 100/6250] eta: 0:23:44 lr: 0.000108 grad: 0.0923 (0.1214) loss: 0.8634 (0.8689) time: 0.1761 data: 0.0777 max mem: 8255 +Train: [28] [ 200/6250] eta: 0:21:17 lr: 0.000108 grad: 0.0925 (0.1173) loss: 0.8545 (0.8624) time: 0.1873 data: 0.0851 max mem: 8255 +Train: [28] [ 300/6250] eta: 0:19:48 lr: 0.000108 grad: 0.0779 (0.1086) loss: 0.8765 (0.8627) time: 0.1562 data: 0.0693 max mem: 8255 +Train: [28] [ 400/6250] eta: 0:18:38 lr: 0.000108 grad: 0.0830 (0.1031) loss: 0.8636 (0.8623) time: 0.1559 data: 0.0733 max mem: 8255 +Train: [28] [ 500/6250] eta: 0:17:32 lr: 0.000108 grad: 0.0826 (0.0998) loss: 0.8511 (0.8620) time: 0.1599 data: 0.0886 max mem: 8255 +Train: [28] [ 600/6250] eta: 0:17:19 lr: 0.000108 grad: 0.0805 (0.0978) loss: 0.8656 (0.8616) time: 0.1347 data: 0.0403 max mem: 8255 +Train: [28] [ 700/6250] eta: 0:17:10 lr: 0.000108 grad: 0.0764 (0.0962) loss: 0.8627 (0.8612) time: 0.3190 data: 0.2041 max mem: 8255 +Train: [28] [ 800/6250] eta: 0:16:17 lr: 0.000108 grad: 0.0797 (0.0943) loss: 0.8601 (0.8613) time: 0.1618 data: 0.0802 max mem: 8255 +Train: [28] [ 900/6250] eta: 0:15:49 lr: 0.000108 grad: 0.0824 (0.0927) loss: 0.8577 (0.8614) time: 0.1967 data: 0.1203 max mem: 8255 +Train: [28] [1000/6250] eta: 0:15:21 lr: 0.000108 grad: 0.0765 (0.0915) loss: 0.8625 (0.8616) time: 0.1072 data: 0.0275 max mem: 8255 +Train: [28] [1100/6250] eta: 0:14:51 lr: 0.000108 grad: 0.0705 (0.0903) loss: 0.8698 (0.8617) time: 0.1316 data: 0.0508 max mem: 8255 +Train: [28] [1200/6250] eta: 0:14:27 lr: 0.000108 grad: 0.0794 (0.0892) loss: 0.8626 (0.8618) time: 0.0954 data: 0.0117 max mem: 8255 +Train: [28] [1300/6250] eta: 0:14:00 lr: 0.000107 grad: 0.0838 (0.0886) loss: 0.8595 (0.8617) time: 0.1428 data: 0.0676 max mem: 8255 +Train: [28] [1400/6250] eta: 0:13:33 lr: 0.000107 grad: 0.0800 (0.0880) loss: 0.8566 (0.8617) time: 0.1413 data: 0.0725 max mem: 8255 +Train: [28] [1500/6250] eta: 0:13:10 lr: 0.000107 grad: 0.0763 (0.0875) loss: 0.8652 (0.8617) time: 0.1579 data: 0.0830 max mem: 8255 +Train: [28] [1600/6250] eta: 0:12:45 lr: 0.000107 grad: 0.0733 (0.0870) loss: 0.8606 (0.8615) time: 0.1271 data: 0.0578 max mem: 8255 +Train: [28] [1700/6250] eta: 0:12:26 lr: 0.000107 grad: 0.0825 (0.0866) loss: 0.8558 (0.8615) time: 0.2006 data: 0.1304 max mem: 8255 +Train: [28] [1800/6250] eta: 0:12:07 lr: 0.000107 grad: 0.0821 (0.0862) loss: 0.8589 (0.8613) time: 0.1634 data: 0.0881 max mem: 8255 +Train: [28] [1900/6250] eta: 0:11:46 lr: 0.000107 grad: 0.0767 (0.0860) loss: 0.8613 (0.8611) time: 0.1515 data: 0.0849 max mem: 8255 +Train: [28] [2000/6250] eta: 0:11:29 lr: 0.000107 grad: 0.0783 (0.0858) loss: 0.8635 (0.8612) time: 0.1572 data: 0.0625 max mem: 8255 +Train: [28] [2100/6250] eta: 0:11:15 lr: 0.000107 grad: 0.0822 (0.0857) loss: 0.8571 (0.8613) time: 0.1222 data: 0.0448 max mem: 8255 +Train: [28] [2200/6250] eta: 0:10:56 lr: 0.000107 grad: 0.0817 (0.0855) loss: 0.8594 (0.8614) time: 0.1391 data: 0.0654 max mem: 8255 +Train: [28] [2300/6250] eta: 0:10:36 lr: 0.000107 grad: 0.0765 (0.0854) loss: 0.8640 (0.8613) time: 0.1436 data: 0.0658 max mem: 8255 +Train: [28] [2400/6250] eta: 0:10:16 lr: 0.000107 grad: 0.0772 (0.0852) loss: 0.8664 (0.8614) time: 0.1199 data: 0.0462 max mem: 8255 +Train: [28] [2500/6250] eta: 0:09:59 lr: 0.000107 grad: 0.0748 (0.0851) loss: 0.8576 (0.8613) time: 0.1550 data: 0.0835 max mem: 8255 +Train: [28] [2600/6250] eta: 0:09:39 lr: 0.000107 grad: 0.0826 (0.0851) loss: 0.8616 (0.8612) time: 0.1430 data: 0.0675 max mem: 8255 +Train: [28] [2700/6250] eta: 0:09:20 lr: 0.000107 grad: 0.0824 (0.0850) loss: 0.8541 (0.8612) time: 0.1239 data: 0.0458 max mem: 8255 +Train: [28] [2800/6250] eta: 0:09:01 lr: 0.000107 grad: 0.0771 (0.0849) loss: 0.8684 (0.8612) time: 0.1407 data: 0.0637 max mem: 8255 +Train: [28] [2900/6250] eta: 0:08:43 lr: 0.000107 grad: 0.0856 (0.0850) loss: 0.8557 (0.8610) time: 0.1327 data: 0.0496 max mem: 8255 +Train: [28] [3000/6250] eta: 0:08:25 lr: 0.000107 grad: 0.0831 (0.0851) loss: 0.8533 (0.8608) time: 0.1298 data: 0.0449 max mem: 8255 +Train: [28] [3100/6250] eta: 0:08:08 lr: 0.000107 grad: 0.0765 (0.0850) loss: 0.8586 (0.8608) time: 0.1424 data: 0.0627 max mem: 8255 +Train: [28] [3200/6250] eta: 0:07:51 lr: 0.000107 grad: 0.0786 (0.0849) loss: 0.8608 (0.8608) time: 0.1349 data: 0.0543 max mem: 8255 +Train: [28] [3300/6250] eta: 0:07:35 lr: 0.000107 grad: 0.0798 (0.0850) loss: 0.8591 (0.8607) time: 0.1711 data: 0.0968 max mem: 8255 +Train: [28] [3400/6250] eta: 0:07:20 lr: 0.000107 grad: 0.0763 (0.0849) loss: 0.8575 (0.8606) time: 0.1035 data: 0.0327 max mem: 8255 +Train: [28] [3500/6250] eta: 0:07:08 lr: 0.000107 grad: 0.0764 (0.0848) loss: 0.8653 (0.8606) time: 0.2723 data: 0.1639 max mem: 8255 +Train: [28] [3600/6250] eta: 0:06:51 lr: 0.000107 grad: 0.0781 (0.0848) loss: 0.8632 (0.8606) time: 0.1335 data: 0.0566 max mem: 8255 +Train: [28] [3700/6250] eta: 0:06:37 lr: 0.000107 grad: 0.0790 (0.0847) loss: 0.8594 (0.8606) time: 0.1378 data: 0.0616 max mem: 8255 +Train: [28] [3800/6250] eta: 0:06:22 lr: 0.000107 grad: 0.0770 (0.0845) loss: 0.8663 (0.8607) time: 0.1557 data: 0.0898 max mem: 8255 +Train: [28] [3900/6250] eta: 0:06:07 lr: 0.000107 grad: 0.0753 (0.0844) loss: 0.8630 (0.8607) time: 0.1984 data: 0.1153 max mem: 8255 +Train: [28] [4000/6250] eta: 0:05:52 lr: 0.000107 grad: 0.0791 (0.0843) loss: 0.8609 (0.8607) time: 0.1849 data: 0.1104 max mem: 8255 +Train: [28] [4100/6250] eta: 0:05:36 lr: 0.000107 grad: 0.0834 (0.0844) loss: 0.8637 (0.8607) time: 0.1598 data: 0.0866 max mem: 8255 +Train: [28] [4200/6250] eta: 0:05:21 lr: 0.000107 grad: 0.0796 (0.0844) loss: 0.8613 (0.8607) time: 0.1606 data: 0.0742 max mem: 8255 +Train: [28] [4300/6250] eta: 0:05:05 lr: 0.000107 grad: 0.0819 (0.0844) loss: 0.8632 (0.8607) time: 0.1680 data: 0.0922 max mem: 8255 +Train: [28] [4400/6250] eta: 0:04:49 lr: 0.000107 grad: 0.0721 (0.0843) loss: 0.8616 (0.8608) time: 0.1296 data: 0.0413 max mem: 8255 +Train: [28] [4500/6250] eta: 0:04:33 lr: 0.000107 grad: 0.0767 (0.0843) loss: 0.8609 (0.8608) time: 0.1127 data: 0.0336 max mem: 8255 +Train: [28] [4600/6250] eta: 0:04:17 lr: 0.000107 grad: 0.0817 (0.0842) loss: 0.8664 (0.8609) time: 0.1646 data: 0.0938 max mem: 8255 +Train: [28] [4700/6250] eta: 0:04:01 lr: 0.000107 grad: 0.0759 (0.0842) loss: 0.8709 (0.8609) time: 0.1108 data: 0.0299 max mem: 8255 +Train: [28] [4800/6250] eta: 0:03:47 lr: 0.000107 grad: 0.0795 (0.0842) loss: 0.8666 (0.8610) time: 0.3628 data: 0.2635 max mem: 8255 +Train: [28] [4900/6250] eta: 0:03:30 lr: 0.000107 grad: 0.0789 (0.0842) loss: 0.8615 (0.8610) time: 0.1406 data: 0.0643 max mem: 8255 +Train: [28] [5000/6250] eta: 0:03:14 lr: 0.000107 grad: 0.0788 (0.0841) loss: 0.8598 (0.8610) time: 0.1402 data: 0.0719 max mem: 8255 +Train: [28] [5100/6250] eta: 0:02:59 lr: 0.000107 grad: 0.0787 (0.0841) loss: 0.8670 (0.8611) time: 0.2132 data: 0.1194 max mem: 8255 +Train: [28] [5200/6250] eta: 0:02:43 lr: 0.000107 grad: 0.0761 (0.0840) loss: 0.8599 (0.8610) time: 0.1456 data: 0.0651 max mem: 8255 +Train: [28] [5300/6250] eta: 0:02:28 lr: 0.000107 grad: 0.0825 (0.0841) loss: 0.8583 (0.8610) time: 0.1643 data: 0.0873 max mem: 8255 +Train: [28] [5400/6250] eta: 0:02:12 lr: 0.000107 grad: 0.0798 (0.0840) loss: 0.8650 (0.8610) time: 0.1353 data: 0.0651 max mem: 8255 +Train: [28] [5500/6250] eta: 0:01:56 lr: 0.000107 grad: 0.0787 (0.0840) loss: 0.8608 (0.8610) time: 0.1381 data: 0.0697 max mem: 8255 +Train: [28] [5600/6250] eta: 0:01:40 lr: 0.000106 grad: 0.0842 (0.0840) loss: 0.8596 (0.8610) time: 0.2211 data: 0.1491 max mem: 8255 +Train: [28] [5700/6250] eta: 0:01:25 lr: 0.000106 grad: 0.0834 (0.0840) loss: 0.8608 (0.8610) time: 0.1645 data: 0.0987 max mem: 8255 +Train: [28] [5800/6250] eta: 0:01:09 lr: 0.000106 grad: 0.0794 (0.0840) loss: 0.8569 (0.8610) time: 0.1635 data: 0.1022 max mem: 8255 +Train: [28] [5900/6250] eta: 0:00:54 lr: 0.000106 grad: 0.0821 (0.0840) loss: 0.8607 (0.8610) time: 0.1373 data: 0.0676 max mem: 8255 +Train: [28] [6000/6250] eta: 0:00:38 lr: 0.000106 grad: 0.0749 (0.0840) loss: 0.8680 (0.8611) time: 0.1331 data: 0.0649 max mem: 8255 +Train: [28] [6100/6250] eta: 0:00:23 lr: 0.000106 grad: 0.0779 (0.0839) loss: 0.8672 (0.8611) time: 0.1408 data: 0.0615 max mem: 8255 +Train: [28] [6200/6250] eta: 0:00:07 lr: 0.000106 grad: 0.0860 (0.0839) loss: 0.8650 (0.8611) time: 0.1245 data: 0.0408 max mem: 8255 +Train: [28] [6249/6250] eta: 0:00:00 lr: 0.000106 grad: 0.0817 (0.0839) loss: 0.8596 (0.8611) time: 0.1859 data: 0.1095 max mem: 8255 +Train: [28] Total time: 0:16:10 (0.1553 s / it) +Averaged stats: lr: 0.000106 grad: 0.0817 (0.0839) loss: 0.8596 (0.8611) +Eval (hcp-train-subset): [28] [ 0/62] eta: 0:03:51 loss: 0.8896 (0.8896) time: 3.7261 data: 3.6477 max mem: 8255 +Eval (hcp-train-subset): [28] [61/62] eta: 0:00:00 loss: 0.8792 (0.8822) time: 0.1648 data: 0.1431 max mem: 8255 +Eval (hcp-train-subset): [28] Total time: 0:00:13 (0.2232 s / it) +Averaged stats (hcp-train-subset): loss: 0.8792 (0.8822) +Eval (hcp-val): [28] [ 0/62] eta: 0:05:19 loss: 0.8786 (0.8786) time: 5.1602 data: 5.1338 max mem: 8255 +Eval (hcp-val): [28] [61/62] eta: 0:00:00 loss: 0.8821 (0.8833) time: 0.1343 data: 0.1135 max mem: 8255 +Eval (hcp-val): [28] Total time: 0:00:14 (0.2282 s / it) +Averaged stats (hcp-val): loss: 0.8821 (0.8833) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +Train: [29] [ 0/6250] eta: 10:15:28 lr: 0.000106 grad: 0.0830 (0.0830) loss: 0.8692 (0.8692) time: 5.9086 data: 5.7970 max mem: 8255 +Train: [29] [ 100/6250] eta: 0:20:14 lr: 0.000106 grad: 0.0970 (0.1128) loss: 0.8713 (0.8717) time: 0.1347 data: 0.0437 max mem: 8255 +Train: [29] [ 200/6250] eta: 0:17:17 lr: 0.000106 grad: 0.0866 (0.1024) loss: 0.8586 (0.8654) time: 0.1438 data: 0.0683 max mem: 8255 +Train: [29] [ 300/6250] eta: 0:15:50 lr: 0.000106 grad: 0.0792 (0.0972) loss: 0.8595 (0.8640) time: 0.1373 data: 0.0543 max mem: 8255 +Train: [29] [ 400/6250] eta: 0:14:48 lr: 0.000106 grad: 0.0737 (0.0945) loss: 0.8723 (0.8641) time: 0.1232 data: 0.0423 max mem: 8255 +Train: [29] [ 500/6250] eta: 0:14:08 lr: 0.000106 grad: 0.0770 (0.0919) loss: 0.8583 (0.8636) time: 0.1359 data: 0.0595 max mem: 8255 +Train: [29] [ 600/6250] eta: 0:13:44 lr: 0.000106 grad: 0.0747 (0.0896) loss: 0.8656 (0.8642) time: 0.1479 data: 0.0639 max mem: 8255 +Train: [29] [ 700/6250] eta: 0:13:23 lr: 0.000106 grad: 0.0751 (0.0881) loss: 0.8659 (0.8644) time: 0.1390 data: 0.0588 max mem: 8255 +Train: [29] [ 800/6250] eta: 0:13:10 lr: 0.000106 grad: 0.0727 (0.0869) loss: 0.8605 (0.8644) time: 0.1463 data: 0.0702 max mem: 8255 +Train: [29] [ 900/6250] eta: 0:12:56 lr: 0.000106 grad: 0.0741 (0.0861) loss: 0.8600 (0.8642) time: 0.1656 data: 0.0902 max mem: 8255 +Train: [29] [1000/6250] eta: 0:12:39 lr: 0.000106 grad: 0.0751 (0.0855) loss: 0.8562 (0.8638) time: 0.1355 data: 0.0664 max mem: 8255 +Train: [29] [1100/6250] eta: 0:12:28 lr: 0.000106 grad: 0.0768 (0.0849) loss: 0.8597 (0.8635) time: 0.1582 data: 0.0902 max mem: 8255 +Train: [29] [1200/6250] eta: 0:12:19 lr: 0.000106 grad: 0.0775 (0.0845) loss: 0.8539 (0.8628) time: 0.0987 data: 0.0157 max mem: 8255 +Train: [29] [1300/6250] eta: 0:12:02 lr: 0.000106 grad: 0.0725 (0.0844) loss: 0.8693 (0.8624) time: 0.1300 data: 0.0515 max mem: 8255 +Train: [29] [1400/6250] eta: 0:11:56 lr: 0.000106 grad: 0.0774 (0.0847) loss: 0.8604 (0.8619) time: 0.2062 data: 0.0915 max mem: 8255 +Train: [29] [1500/6250] eta: 0:11:34 lr: 0.000106 grad: 0.0790 (0.0846) loss: 0.8614 (0.8616) time: 0.1318 data: 0.0504 max mem: 8255 +Train: [29] [1600/6250] eta: 0:11:19 lr: 0.000106 grad: 0.0793 (0.0849) loss: 0.8605 (0.8611) time: 0.1427 data: 0.0626 max mem: 8255 +Train: [29] [1700/6250] eta: 0:11:01 lr: 0.000106 grad: 0.0786 (0.0847) loss: 0.8544 (0.8608) time: 0.1109 data: 0.0376 max mem: 8255 +Train: [29] [1800/6250] eta: 0:10:45 lr: 0.000106 grad: 0.0767 (0.0848) loss: 0.8670 (0.8606) time: 0.1404 data: 0.0687 max mem: 8255 +Train: [29] [1900/6250] eta: 0:10:30 lr: 0.000106 grad: 0.0758 (0.0847) loss: 0.8626 (0.8604) time: 0.1395 data: 0.0679 max mem: 8255 +Train: [29] [2000/6250] eta: 0:10:14 lr: 0.000106 grad: 0.0821 (0.0848) loss: 0.8562 (0.8601) time: 0.1530 data: 0.0807 max mem: 8255 +Train: [29] [2100/6250] eta: 0:10:00 lr: 0.000106 grad: 0.0840 (0.0847) loss: 0.8655 (0.8600) time: 0.1456 data: 0.0793 max mem: 8255 +Train: [29] [2200/6250] eta: 0:09:48 lr: 0.000106 grad: 0.0766 (0.0846) loss: 0.8733 (0.8600) time: 0.1194 data: 0.0531 max mem: 8255 +Train: [29] [2300/6250] eta: 0:09:34 lr: 0.000106 grad: 0.0784 (0.0845) loss: 0.8661 (0.8600) time: 0.1512 data: 0.0790 max mem: 8255 +Train: [29] [2400/6250] eta: 0:09:21 lr: 0.000106 grad: 0.0774 (0.0845) loss: 0.8634 (0.8598) time: 0.1628 data: 0.1007 max mem: 8255 +Train: [29] [2500/6250] eta: 0:09:07 lr: 0.000106 grad: 0.0807 (0.0844) loss: 0.8575 (0.8598) time: 0.1674 data: 0.0952 max mem: 8255 +Train: [29] [2600/6250] eta: 0:08:53 lr: 0.000106 grad: 0.0817 (0.0844) loss: 0.8626 (0.8598) time: 0.1408 data: 0.0785 max mem: 8255 +Train: [29] [2700/6250] eta: 0:08:38 lr: 0.000106 grad: 0.0797 (0.0844) loss: 0.8660 (0.8599) time: 0.1500 data: 0.0757 max mem: 8255 +Train: [29] [2800/6250] eta: 0:08:24 lr: 0.000106 grad: 0.0810 (0.0845) loss: 0.8585 (0.8598) time: 0.1575 data: 0.0711 max mem: 8255 +Train: [29] [2900/6250] eta: 0:08:10 lr: 0.000106 grad: 0.0827 (0.0846) loss: 0.8550 (0.8596) time: 0.1801 data: 0.1036 max mem: 8255 +Train: [29] [3000/6250] eta: 0:07:55 lr: 0.000106 grad: 0.0742 (0.0847) loss: 0.8594 (0.8595) time: 0.1413 data: 0.0580 max mem: 8255 +Train: [29] [3100/6250] eta: 0:07:41 lr: 0.000106 grad: 0.0777 (0.0847) loss: 0.8623 (0.8596) time: 0.1651 data: 0.0909 max mem: 8255 +Train: [29] [3200/6250] eta: 0:07:27 lr: 0.000106 grad: 0.0781 (0.0846) loss: 0.8599 (0.8596) time: 0.1184 data: 0.0501 max mem: 8255 +Train: [29] [3300/6250] eta: 0:07:12 lr: 0.000106 grad: 0.0887 (0.0848) loss: 0.8634 (0.8595) time: 0.1672 data: 0.0844 max mem: 8255 +Train: [29] [3400/6250] eta: 0:06:57 lr: 0.000106 grad: 0.0832 (0.0848) loss: 0.8624 (0.8595) time: 0.1651 data: 0.0917 max mem: 8255 +Train: [29] [3500/6250] eta: 0:06:42 lr: 0.000105 grad: 0.0869 (0.0848) loss: 0.8594 (0.8595) time: 0.1200 data: 0.0390 max mem: 8255 +Train: [29] [3600/6250] eta: 0:06:27 lr: 0.000105 grad: 0.0845 (0.0849) loss: 0.8578 (0.8594) time: 0.1292 data: 0.0540 max mem: 8255 +Train: [29] [3700/6250] eta: 0:06:13 lr: 0.000105 grad: 0.0835 (0.0849) loss: 0.8576 (0.8594) time: 0.1598 data: 0.0713 max mem: 8255 +Train: [29] [3800/6250] eta: 0:05:59 lr: 0.000105 grad: 0.0765 (0.0849) loss: 0.8594 (0.8594) time: 0.1317 data: 0.0615 max mem: 8255 +Train: [29] [3900/6250] eta: 0:05:44 lr: 0.000105 grad: 0.0821 (0.0849) loss: 0.8608 (0.8594) time: 0.1485 data: 0.0742 max mem: 8255 +Train: [29] [4000/6250] eta: 0:05:30 lr: 0.000105 grad: 0.0733 (0.0849) loss: 0.8599 (0.8595) time: 0.1347 data: 0.0545 max mem: 8255 +Train: [29] [4100/6250] eta: 0:05:15 lr: 0.000105 grad: 0.0777 (0.0848) loss: 0.8603 (0.8595) time: 0.1501 data: 0.0770 max mem: 8255 +Train: [29] [4200/6250] eta: 0:05:00 lr: 0.000105 grad: 0.0871 (0.0847) loss: 0.8628 (0.8596) time: 0.1295 data: 0.0548 max mem: 8255 +Train: [29] [4300/6250] eta: 0:04:45 lr: 0.000105 grad: 0.0815 (0.0847) loss: 0.8622 (0.8597) time: 0.1315 data: 0.0562 max mem: 8255 +Train: [29] [4400/6250] eta: 0:04:30 lr: 0.000105 grad: 0.0818 (0.0846) loss: 0.8635 (0.8597) time: 0.1332 data: 0.0565 max mem: 8255 +Train: [29] [4500/6250] eta: 0:04:15 lr: 0.000105 grad: 0.0858 (0.0846) loss: 0.8599 (0.8597) time: 0.1257 data: 0.0491 max mem: 8255 +Train: [29] [4600/6250] eta: 0:04:00 lr: 0.000105 grad: 0.0780 (0.0845) loss: 0.8607 (0.8598) time: 0.1171 data: 0.0427 max mem: 8255 +Train: [29] [4700/6250] eta: 0:03:45 lr: 0.000105 grad: 0.0804 (0.0844) loss: 0.8665 (0.8599) time: 0.1441 data: 0.0738 max mem: 8255 +Train: [29] [4800/6250] eta: 0:03:31 lr: 0.000105 grad: 0.0837 (0.0845) loss: 0.8576 (0.8599) time: 0.1560 data: 0.0837 max mem: 8255 +Train: [29] [4900/6250] eta: 0:03:17 lr: 0.000105 grad: 0.0829 (0.0844) loss: 0.8582 (0.8599) time: 0.1581 data: 0.0872 max mem: 8255 +Train: [29] [5000/6250] eta: 0:03:03 lr: 0.000105 grad: 0.0805 (0.0844) loss: 0.8635 (0.8600) time: 0.1098 data: 0.0297 max mem: 8255 +Train: [29] [5100/6250] eta: 0:02:48 lr: 0.000105 grad: 0.0783 (0.0844) loss: 0.8635 (0.8600) time: 0.1713 data: 0.0924 max mem: 8255 +Train: [29] [5200/6250] eta: 0:02:33 lr: 0.000105 grad: 0.0779 (0.0844) loss: 0.8616 (0.8600) time: 0.1052 data: 0.0302 max mem: 8255 +Train: [29] [5300/6250] eta: 0:02:19 lr: 0.000105 grad: 0.0857 (0.0843) loss: 0.8578 (0.8600) time: 0.1367 data: 0.0612 max mem: 8255 +Train: [29] [5400/6250] eta: 0:02:04 lr: 0.000105 grad: 0.0806 (0.0843) loss: 0.8582 (0.8600) time: 0.1574 data: 0.0784 max mem: 8255 +Train: [29] [5500/6250] eta: 0:01:50 lr: 0.000105 grad: 0.0777 (0.0843) loss: 0.8618 (0.8601) time: 0.1556 data: 0.0929 max mem: 8255 +Train: [29] [5600/6250] eta: 0:01:35 lr: 0.000105 grad: 0.0794 (0.0842) loss: 0.8571 (0.8600) time: 0.1432 data: 0.0620 max mem: 8255 +Train: [29] [5700/6250] eta: 0:01:20 lr: 0.000105 grad: 0.0775 (0.0843) loss: 0.8645 (0.8601) time: 0.1342 data: 0.0545 max mem: 8255 +Train: [29] [5800/6250] eta: 0:01:05 lr: 0.000105 grad: 0.0746 (0.0843) loss: 0.8628 (0.8602) time: 0.1328 data: 0.0654 max mem: 8255 +Train: [29] [5900/6250] eta: 0:00:51 lr: 0.000105 grad: 0.0822 (0.0842) loss: 0.8638 (0.8602) time: 0.1675 data: 0.0925 max mem: 8255 +Train: [29] [6000/6250] eta: 0:00:36 lr: 0.000105 grad: 0.0747 (0.0841) loss: 0.8714 (0.8603) time: 0.1776 data: 0.1075 max mem: 8255 +Train: [29] [6100/6250] eta: 0:00:21 lr: 0.000105 grad: 0.0820 (0.0841) loss: 0.8652 (0.8604) time: 0.1403 data: 0.0618 max mem: 8255 +Train: [29] [6200/6250] eta: 0:00:07 lr: 0.000105 grad: 0.0739 (0.0840) loss: 0.8723 (0.8606) time: 0.1353 data: 0.0644 max mem: 8255 +Train: [29] [6249/6250] eta: 0:00:00 lr: 0.000105 grad: 0.0747 (0.0839) loss: 0.8670 (0.8606) time: 0.1513 data: 0.0762 max mem: 8255 +Train: [29] Total time: 0:15:21 (0.1474 s / it) +Averaged stats: lr: 0.000105 grad: 0.0747 (0.0839) loss: 0.8670 (0.8606) +Eval (hcp-train-subset): [29] [ 0/62] eta: 0:04:41 loss: 0.8962 (0.8962) time: 4.5421 data: 4.5125 max mem: 8255 +Eval (hcp-train-subset): [29] [61/62] eta: 0:00:00 loss: 0.8847 (0.8848) time: 0.1384 data: 0.1175 max mem: 8255 +Eval (hcp-train-subset): [29] Total time: 0:00:13 (0.2200 s / it) +Averaged stats (hcp-train-subset): loss: 0.8847 (0.8848) +Making plots (hcp-train-subset): example=10 +Eval (hcp-val): [29] [ 0/62] eta: 0:04:10 loss: 0.8794 (0.8794) time: 4.0372 data: 3.9614 max mem: 8255 +Eval (hcp-val): [29] [61/62] eta: 0:00:00 loss: 0.8835 (0.8832) time: 0.1335 data: 0.1113 max mem: 8255 +Eval (hcp-val): [29] Total time: 0:00:13 (0.2193 s / it) +Averaged stats (hcp-val): loss: 0.8835 (0.8832) +Making plots (hcp-val): example=53 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +Train: [30] [ 0/6250] eta: 10:43:21 lr: 0.000105 grad: 0.1446 (0.1446) loss: 0.8152 (0.8152) time: 6.1763 data: 6.0844 max mem: 8255 +Train: [30] [ 100/6250] eta: 0:20:12 lr: 0.000105 grad: 0.0924 (0.1175) loss: 0.8675 (0.8676) time: 0.1482 data: 0.0617 max mem: 8255 +Train: [30] [ 200/6250] eta: 0:17:26 lr: 0.000105 grad: 0.0788 (0.1003) loss: 0.8621 (0.8692) time: 0.1589 data: 0.0775 max mem: 8255 +Train: [30] [ 300/6250] eta: 0:16:15 lr: 0.000105 grad: 0.0737 (0.0945) loss: 0.8638 (0.8688) time: 0.1508 data: 0.0587 max mem: 8255 +Train: [30] [ 400/6250] eta: 0:15:40 lr: 0.000105 grad: 0.0732 (0.0904) loss: 0.8647 (0.8687) time: 0.1508 data: 0.0601 max mem: 8255 +Train: [30] [ 500/6250] eta: 0:15:22 lr: 0.000105 grad: 0.0761 (0.0884) loss: 0.8660 (0.8687) time: 0.1478 data: 0.0694 max mem: 8255 +Train: [30] [ 600/6250] eta: 0:14:50 lr: 0.000105 grad: 0.0788 (0.0869) loss: 0.8646 (0.8684) time: 0.1330 data: 0.0618 max mem: 8255 +Train: [30] [ 700/6250] eta: 0:14:25 lr: 0.000105 grad: 0.0774 (0.0861) loss: 0.8710 (0.8681) time: 0.1500 data: 0.0871 max mem: 8255 +Train: [30] [ 800/6250] eta: 0:14:05 lr: 0.000105 grad: 0.0796 (0.0852) loss: 0.8680 (0.8678) time: 0.1357 data: 0.0519 max mem: 8255 +Train: [30] [ 900/6250] eta: 0:13:40 lr: 0.000105 grad: 0.0788 (0.0845) loss: 0.8589 (0.8674) time: 0.1583 data: 0.0822 max mem: 8255 +Train: [30] [1000/6250] eta: 0:13:15 lr: 0.000105 grad: 0.0715 (0.0839) loss: 0.8642 (0.8672) time: 0.1314 data: 0.0606 max mem: 8255 +Train: [30] [1100/6250] eta: 0:12:51 lr: 0.000105 grad: 0.0789 (0.0833) loss: 0.8637 (0.8670) time: 0.1677 data: 0.0973 max mem: 8255 +Train: [30] [1200/6250] eta: 0:12:36 lr: 0.000105 grad: 0.0789 (0.0832) loss: 0.8608 (0.8665) time: 0.1611 data: 0.0872 max mem: 8255 +Train: [30] [1300/6250] eta: 0:12:18 lr: 0.000105 grad: 0.0765 (0.0830) loss: 0.8566 (0.8660) time: 0.1511 data: 0.0747 max mem: 8255 +Train: [30] [1400/6250] eta: 0:12:08 lr: 0.000104 grad: 0.0836 (0.0833) loss: 0.8659 (0.8655) time: 0.2076 data: 0.1225 max mem: 8255 +Train: [30] [1500/6250] eta: 0:11:54 lr: 0.000104 grad: 0.0793 (0.0834) loss: 0.8505 (0.8648) time: 0.1767 data: 0.1034 max mem: 8255 +Train: [30] [1600/6250] eta: 0:11:36 lr: 0.000104 grad: 0.0775 (0.0833) loss: 0.8580 (0.8642) time: 0.1368 data: 0.0637 max mem: 8255 +Train: [30] [1700/6250] eta: 0:11:29 lr: 0.000104 grad: 0.0785 (0.0832) loss: 0.8550 (0.8637) time: 0.1090 data: 0.0139 max mem: 8255 +Train: [30] [1800/6250] eta: 0:11:14 lr: 0.000104 grad: 0.0831 (0.0833) loss: 0.8547 (0.8633) time: 0.1863 data: 0.0948 max mem: 8255 +Train: [30] [1900/6250] eta: 0:10:59 lr: 0.000104 grad: 0.0796 (0.0832) loss: 0.8541 (0.8630) time: 0.1736 data: 0.0967 max mem: 8255 +Train: [30] [2000/6250] eta: 0:10:42 lr: 0.000104 grad: 0.0821 (0.0833) loss: 0.8603 (0.8627) time: 0.1238 data: 0.0244 max mem: 8255 +Train: [30] [2100/6250] eta: 0:10:27 lr: 0.000104 grad: 0.0827 (0.0832) loss: 0.8612 (0.8626) time: 0.1760 data: 0.0841 max mem: 8255 +Train: [30] [2200/6250] eta: 0:10:11 lr: 0.000104 grad: 0.0824 (0.0832) loss: 0.8494 (0.8623) time: 0.1410 data: 0.0658 max mem: 8255 +Train: [30] [2300/6250] eta: 0:09:58 lr: 0.000104 grad: 0.0806 (0.0832) loss: 0.8518 (0.8621) time: 0.1939 data: 0.1272 max mem: 8255 +Train: [30] [2400/6250] eta: 0:09:40 lr: 0.000104 grad: 0.0828 (0.0832) loss: 0.8581 (0.8618) time: 0.1181 data: 0.0396 max mem: 8255 +Train: [30] [2500/6250] eta: 0:09:23 lr: 0.000104 grad: 0.0806 (0.0833) loss: 0.8539 (0.8615) time: 0.1230 data: 0.0504 max mem: 8255 +Train: [30] [2600/6250] eta: 0:09:06 lr: 0.000104 grad: 0.0757 (0.0832) loss: 0.8640 (0.8613) time: 0.1450 data: 0.0748 max mem: 8255 +Train: [30] [2700/6250] eta: 0:08:49 lr: 0.000104 grad: 0.0799 (0.0834) loss: 0.8637 (0.8612) time: 0.1441 data: 0.0732 max mem: 8255 +Train: [30] [2800/6250] eta: 0:08:32 lr: 0.000104 grad: 0.0776 (0.0834) loss: 0.8628 (0.8610) time: 0.1493 data: 0.0774 max mem: 8255 +Train: [30] [2900/6250] eta: 0:08:16 lr: 0.000104 grad: 0.0789 (0.0834) loss: 0.8596 (0.8610) time: 0.1467 data: 0.0738 max mem: 8255 +Train: [30] [3000/6250] eta: 0:08:00 lr: 0.000104 grad: 0.0835 (0.0833) loss: 0.8619 (0.8609) time: 0.1533 data: 0.0843 max mem: 8255 +Train: [30] [3100/6250] eta: 0:07:44 lr: 0.000104 grad: 0.0820 (0.0832) loss: 0.8564 (0.8609) time: 0.1355 data: 0.0669 max mem: 8255 +Train: [30] [3200/6250] eta: 0:07:28 lr: 0.000104 grad: 0.0740 (0.0832) loss: 0.8614 (0.8608) time: 0.1511 data: 0.0739 max mem: 8255 +Train: [30] [3300/6250] eta: 0:07:13 lr: 0.000104 grad: 0.0760 (0.0832) loss: 0.8656 (0.8608) time: 0.1362 data: 0.0700 max mem: 8255 +Train: [30] [3400/6250] eta: 0:06:57 lr: 0.000104 grad: 0.0807 (0.0832) loss: 0.8653 (0.8607) time: 0.1580 data: 0.0914 max mem: 8255 +Train: [30] [3500/6250] eta: 0:06:44 lr: 0.000104 grad: 0.0870 (0.0833) loss: 0.8561 (0.8606) time: 0.1729 data: 0.1017 max mem: 8255 +Train: [30] [3600/6250] eta: 0:06:31 lr: 0.000104 grad: 0.0784 (0.0834) loss: 0.8605 (0.8606) time: 0.1601 data: 0.0931 max mem: 8255 +Train: [30] [3700/6250] eta: 0:06:17 lr: 0.000104 grad: 0.0800 (0.0834) loss: 0.8678 (0.8606) time: 0.1297 data: 0.0485 max mem: 8255 +Train: [30] [3800/6250] eta: 0:06:06 lr: 0.000104 grad: 0.0847 (0.0835) loss: 0.8581 (0.8605) time: 0.3480 data: 0.2389 max mem: 8255 +Train: [30] [3900/6250] eta: 0:05:52 lr: 0.000104 grad: 0.0793 (0.0836) loss: 0.8549 (0.8604) time: 0.1806 data: 0.1093 max mem: 8255 +Train: [30] [4000/6250] eta: 0:05:37 lr: 0.000104 grad: 0.0819 (0.0836) loss: 0.8539 (0.8604) time: 0.1771 data: 0.1048 max mem: 8255 +Train: [30] [4100/6250] eta: 0:05:22 lr: 0.000104 grad: 0.0855 (0.0836) loss: 0.8602 (0.8604) time: 0.1408 data: 0.0659 max mem: 8255 +Train: [30] [4200/6250] eta: 0:05:07 lr: 0.000104 grad: 0.0793 (0.0835) loss: 0.8594 (0.8603) time: 0.1495 data: 0.0751 max mem: 8255 +Train: [30] [4300/6250] eta: 0:04:52 lr: 0.000104 grad: 0.0803 (0.0835) loss: 0.8519 (0.8603) time: 0.1433 data: 0.0712 max mem: 8255 +Train: [30] [4400/6250] eta: 0:04:37 lr: 0.000104 grad: 0.0763 (0.0835) loss: 0.8641 (0.8603) time: 0.1510 data: 0.0753 max mem: 8255 +Train: [30] [4500/6250] eta: 0:04:22 lr: 0.000104 grad: 0.0796 (0.0835) loss: 0.8653 (0.8603) time: 0.1297 data: 0.0533 max mem: 8255 +Train: [30] [4600/6250] eta: 0:04:07 lr: 0.000104 grad: 0.0834 (0.0835) loss: 0.8613 (0.8604) time: 0.1476 data: 0.0722 max mem: 8255 +Train: [30] [4700/6250] eta: 0:03:52 lr: 0.000104 grad: 0.0759 (0.0835) loss: 0.8688 (0.8604) time: 0.1186 data: 0.0490 max mem: 8255 +Train: [30] [4800/6250] eta: 0:03:36 lr: 0.000104 grad: 0.0805 (0.0834) loss: 0.8599 (0.8604) time: 0.1382 data: 0.0537 max mem: 8255 +Train: [30] [4900/6250] eta: 0:03:21 lr: 0.000104 grad: 0.0784 (0.0834) loss: 0.8656 (0.8605) time: 0.1613 data: 0.0891 max mem: 8255 +Train: [30] [5000/6250] eta: 0:03:06 lr: 0.000104 grad: 0.0844 (0.0834) loss: 0.8536 (0.8604) time: 0.1517 data: 0.0791 max mem: 8255 +Train: [30] [5100/6250] eta: 0:02:51 lr: 0.000104 grad: 0.0863 (0.0834) loss: 0.8539 (0.8603) time: 0.1999 data: 0.1230 max mem: 8255 +Train: [30] [5200/6250] eta: 0:02:36 lr: 0.000104 grad: 0.0818 (0.0834) loss: 0.8601 (0.8602) time: 0.2040 data: 0.1242 max mem: 8255 +Train: [30] [5300/6250] eta: 0:02:22 lr: 0.000104 grad: 0.0793 (0.0835) loss: 0.8628 (0.8602) time: 0.0970 data: 0.0004 max mem: 8255 +Train: [30] [5400/6250] eta: 0:02:07 lr: 0.000103 grad: 0.0808 (0.0835) loss: 0.8636 (0.8602) time: 0.1344 data: 0.0608 max mem: 8255 +Train: [30] [5500/6250] eta: 0:01:52 lr: 0.000103 grad: 0.0859 (0.0835) loss: 0.8612 (0.8602) time: 0.1690 data: 0.0979 max mem: 8255 +Train: [30] [5600/6250] eta: 0:01:37 lr: 0.000103 grad: 0.0826 (0.0836) loss: 0.8595 (0.8602) time: 0.1293 data: 0.0543 max mem: 8255 +Train: [30] [5700/6250] eta: 0:01:22 lr: 0.000103 grad: 0.0823 (0.0836) loss: 0.8529 (0.8602) time: 0.1248 data: 0.0381 max mem: 8255 +Train: [30] [5800/6250] eta: 0:01:07 lr: 0.000103 grad: 0.0814 (0.0837) loss: 0.8622 (0.8602) time: 0.1513 data: 0.0766 max mem: 8255 +Train: [30] [5900/6250] eta: 0:00:52 lr: 0.000103 grad: 0.0793 (0.0837) loss: 0.8624 (0.8602) time: 0.1325 data: 0.0556 max mem: 8255 +Train: [30] [6000/6250] eta: 0:00:37 lr: 0.000103 grad: 0.0813 (0.0837) loss: 0.8595 (0.8602) time: 0.1342 data: 0.0618 max mem: 8255 +Train: [30] [6100/6250] eta: 0:00:22 lr: 0.000103 grad: 0.0828 (0.0837) loss: 0.8645 (0.8602) time: 0.1207 data: 0.0483 max mem: 8255 +Train: [30] [6200/6250] eta: 0:00:07 lr: 0.000103 grad: 0.0785 (0.0837) loss: 0.8638 (0.8602) time: 0.1712 data: 0.1015 max mem: 8255 +Train: [30] [6249/6250] eta: 0:00:00 lr: 0.000103 grad: 0.0793 (0.0838) loss: 0.8706 (0.8602) time: 0.1154 data: 0.0338 max mem: 8255 +Train: [30] Total time: 0:15:33 (0.1494 s / it) +Averaged stats: lr: 0.000103 grad: 0.0793 (0.0838) loss: 0.8706 (0.8602) +Eval (hcp-train-subset): [30] [ 0/62] eta: 0:04:05 loss: 0.8942 (0.8942) time: 3.9637 data: 3.9019 max mem: 8255 +Eval (hcp-train-subset): [30] [61/62] eta: 0:00:00 loss: 0.8812 (0.8814) time: 0.1465 data: 0.1246 max mem: 8255 +Eval (hcp-train-subset): [30] Total time: 0:00:13 (0.2175 s / it) +Averaged stats (hcp-train-subset): loss: 0.8812 (0.8814) +Eval (hcp-val): [30] [ 0/62] eta: 0:03:43 loss: 0.8764 (0.8764) time: 3.6080 data: 3.5184 max mem: 8255 +Eval (hcp-val): [30] [61/62] eta: 0:00:00 loss: 0.8803 (0.8820) time: 0.1293 data: 0.1085 max mem: 8255 +Eval (hcp-val): [30] Total time: 0:00:13 (0.2225 s / it) +Averaged stats (hcp-val): loss: 0.8803 (0.8820) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +Train: [31] [ 0/6250] eta: 9:39:28 lr: 0.000103 grad: 0.0624 (0.0624) loss: 0.9000 (0.9000) time: 5.5629 data: 5.4115 max mem: 8255 +Train: [31] [ 100/6250] eta: 0:22:35 lr: 0.000103 grad: 0.0953 (0.1032) loss: 0.8635 (0.8756) time: 0.1765 data: 0.0816 max mem: 8255 +Train: [31] [ 200/6250] eta: 0:18:37 lr: 0.000103 grad: 0.0812 (0.0971) loss: 0.8705 (0.8696) time: 0.1469 data: 0.0670 max mem: 8255 +Train: [31] [ 300/6250] eta: 0:17:10 lr: 0.000103 grad: 0.0729 (0.0939) loss: 0.8702 (0.8678) time: 0.1306 data: 0.0531 max mem: 8255 +Train: [31] [ 400/6250] eta: 0:15:52 lr: 0.000103 grad: 0.0710 (0.0888) loss: 0.8720 (0.8685) time: 0.1327 data: 0.0608 max mem: 8255 +Train: [31] [ 500/6250] eta: 0:15:06 lr: 0.000103 grad: 0.0746 (0.0862) loss: 0.8680 (0.8691) time: 0.1258 data: 0.0379 max mem: 8255 +Train: [31] [ 600/6250] eta: 0:14:28 lr: 0.000103 grad: 0.0739 (0.0844) loss: 0.8670 (0.8693) time: 0.1440 data: 0.0723 max mem: 8255 +Train: [31] [ 700/6250] eta: 0:14:09 lr: 0.000103 grad: 0.0736 (0.0831) loss: 0.8762 (0.8694) time: 0.1763 data: 0.0981 max mem: 8255 +Train: [31] [ 800/6250] eta: 0:13:50 lr: 0.000103 grad: 0.0711 (0.0822) loss: 0.8668 (0.8689) time: 0.1746 data: 0.0997 max mem: 8255 +Train: [31] [ 900/6250] eta: 0:13:37 lr: 0.000103 grad: 0.0749 (0.0816) loss: 0.8657 (0.8687) time: 0.1739 data: 0.0928 max mem: 8255 +Train: [31] [1000/6250] eta: 0:13:24 lr: 0.000103 grad: 0.0800 (0.0813) loss: 0.8615 (0.8684) time: 0.1575 data: 0.0784 max mem: 8255 +Train: [31] [1100/6250] eta: 0:13:04 lr: 0.000103 grad: 0.0797 (0.0811) loss: 0.8671 (0.8680) time: 0.1420 data: 0.0620 max mem: 8255 +Train: [31] [1200/6250] eta: 0:12:53 lr: 0.000103 grad: 0.0741 (0.0811) loss: 0.8632 (0.8676) time: 0.1407 data: 0.0605 max mem: 8255 +Train: [31] [1300/6250] eta: 0:12:37 lr: 0.000103 grad: 0.0735 (0.0808) loss: 0.8617 (0.8671) time: 0.1436 data: 0.0667 max mem: 8255 +Train: [31] [1400/6250] eta: 0:12:21 lr: 0.000103 grad: 0.0780 (0.0807) loss: 0.8592 (0.8667) time: 0.1457 data: 0.0585 max mem: 8255 +Train: [31] [1500/6250] eta: 0:12:06 lr: 0.000103 grad: 0.0719 (0.0806) loss: 0.8690 (0.8662) time: 0.1515 data: 0.0678 max mem: 8255 +Train: [31] [1600/6250] eta: 0:11:47 lr: 0.000103 grad: 0.0740 (0.0806) loss: 0.8567 (0.8659) time: 0.1339 data: 0.0664 max mem: 8255 +Train: [31] [1700/6250] eta: 0:11:32 lr: 0.000103 grad: 0.0801 (0.0806) loss: 0.8561 (0.8656) time: 0.1514 data: 0.0840 max mem: 8255 +Train: [31] [1800/6250] eta: 0:11:16 lr: 0.000103 grad: 0.0817 (0.0806) loss: 0.8570 (0.8651) time: 0.1499 data: 0.0751 max mem: 8255 +Train: [31] [1900/6250] eta: 0:10:58 lr: 0.000103 grad: 0.0748 (0.0808) loss: 0.8614 (0.8648) time: 0.1471 data: 0.0708 max mem: 8255 +Train: [31] [2000/6250] eta: 0:10:44 lr: 0.000103 grad: 0.0818 (0.0807) loss: 0.8552 (0.8644) time: 0.1577 data: 0.0836 max mem: 8255 +Train: [31] [2100/6250] eta: 0:10:30 lr: 0.000103 grad: 0.0786 (0.0808) loss: 0.8507 (0.8640) time: 0.1547 data: 0.0827 max mem: 8255 +Train: [31] [2200/6250] eta: 0:10:16 lr: 0.000103 grad: 0.0804 (0.0809) loss: 0.8556 (0.8637) time: 0.1667 data: 0.0864 max mem: 8255 +Train: [31] [2300/6250] eta: 0:10:02 lr: 0.000103 grad: 0.0781 (0.0809) loss: 0.8588 (0.8633) time: 0.1855 data: 0.1261 max mem: 8255 +Train: [31] [2400/6250] eta: 0:09:46 lr: 0.000103 grad: 0.0834 (0.0810) loss: 0.8607 (0.8630) time: 0.1625 data: 0.0902 max mem: 8255 +Train: [31] [2500/6250] eta: 0:09:29 lr: 0.000103 grad: 0.0796 (0.0811) loss: 0.8561 (0.8626) time: 0.1727 data: 0.0990 max mem: 8255 +Train: [31] [2600/6250] eta: 0:09:14 lr: 0.000103 grad: 0.0833 (0.0812) loss: 0.8522 (0.8623) time: 0.1339 data: 0.0567 max mem: 8255 +Train: [31] [2700/6250] eta: 0:08:58 lr: 0.000103 grad: 0.0808 (0.0813) loss: 0.8487 (0.8619) time: 0.1552 data: 0.0825 max mem: 8255 +Train: [31] [2800/6250] eta: 0:08:42 lr: 0.000103 grad: 0.0772 (0.0814) loss: 0.8522 (0.8616) time: 0.1440 data: 0.0760 max mem: 8255 +Train: [31] [2900/6250] eta: 0:08:25 lr: 0.000103 grad: 0.0800 (0.0814) loss: 0.8527 (0.8613) time: 0.1569 data: 0.0851 max mem: 8255 +Train: [31] [3000/6250] eta: 0:08:09 lr: 0.000103 grad: 0.0766 (0.0814) loss: 0.8605 (0.8612) time: 0.1512 data: 0.0784 max mem: 8255 +Train: [31] [3100/6250] eta: 0:07:53 lr: 0.000103 grad: 0.0799 (0.0815) loss: 0.8566 (0.8610) time: 0.1287 data: 0.0521 max mem: 8255 +Train: [31] [3200/6250] eta: 0:07:37 lr: 0.000102 grad: 0.0800 (0.0815) loss: 0.8599 (0.8609) time: 0.1462 data: 0.0656 max mem: 8255 +Train: [31] [3300/6250] eta: 0:07:20 lr: 0.000102 grad: 0.0777 (0.0816) loss: 0.8560 (0.8609) time: 0.1210 data: 0.0545 max mem: 8255 +Train: [31] [3400/6250] eta: 0:07:04 lr: 0.000102 grad: 0.0828 (0.0815) loss: 0.8528 (0.8608) time: 0.1426 data: 0.0512 max mem: 8255 +Train: [31] [3500/6250] eta: 0:06:47 lr: 0.000102 grad: 0.0818 (0.0814) loss: 0.8604 (0.8609) time: 0.1351 data: 0.0670 max mem: 8255 +Train: [31] [3600/6250] eta: 0:06:31 lr: 0.000102 grad: 0.0831 (0.0814) loss: 0.8589 (0.8609) time: 0.1231 data: 0.0513 max mem: 8255 +Train: [31] [3700/6250] eta: 0:06:15 lr: 0.000102 grad: 0.0784 (0.0814) loss: 0.8634 (0.8609) time: 0.1294 data: 0.0589 max mem: 8255 +Train: [31] [3800/6250] eta: 0:05:59 lr: 0.000102 grad: 0.0791 (0.0815) loss: 0.8623 (0.8609) time: 0.1300 data: 0.0612 max mem: 8255 +Train: [31] [3900/6250] eta: 0:05:43 lr: 0.000102 grad: 0.0750 (0.0814) loss: 0.8657 (0.8609) time: 0.1366 data: 0.0695 max mem: 8255 +Train: [31] [4000/6250] eta: 0:05:27 lr: 0.000102 grad: 0.0801 (0.0814) loss: 0.8537 (0.8609) time: 0.1292 data: 0.0578 max mem: 8255 +Train: [31] [4100/6250] eta: 0:05:12 lr: 0.000102 grad: 0.0821 (0.0815) loss: 0.8566 (0.8608) time: 0.1304 data: 0.0640 max mem: 8255 +Train: [31] [4200/6250] eta: 0:04:58 lr: 0.000102 grad: 0.0774 (0.0815) loss: 0.8661 (0.8607) time: 0.1752 data: 0.1043 max mem: 8255 +Train: [31] [4300/6250] eta: 0:04:44 lr: 0.000102 grad: 0.0754 (0.0815) loss: 0.8649 (0.8607) time: 0.1568 data: 0.0784 max mem: 8255 +Train: [31] [4400/6250] eta: 0:04:30 lr: 0.000102 grad: 0.0801 (0.0815) loss: 0.8521 (0.8606) time: 0.1804 data: 0.1160 max mem: 8255 +Train: [31] [4500/6250] eta: 0:04:16 lr: 0.000102 grad: 0.0758 (0.0816) loss: 0.8559 (0.8605) time: 0.1731 data: 0.1009 max mem: 8255 +Train: [31] [4600/6250] eta: 0:04:02 lr: 0.000102 grad: 0.0769 (0.0816) loss: 0.8595 (0.8605) time: 0.1514 data: 0.0757 max mem: 8255 +Train: [31] [4700/6250] eta: 0:03:47 lr: 0.000102 grad: 0.0885 (0.0817) loss: 0.8567 (0.8604) time: 0.1487 data: 0.0760 max mem: 8255 +Train: [31] [4800/6250] eta: 0:03:32 lr: 0.000102 grad: 0.0801 (0.0817) loss: 0.8564 (0.8603) time: 0.1337 data: 0.0577 max mem: 8255 +Train: [31] [4900/6250] eta: 0:03:17 lr: 0.000102 grad: 0.0794 (0.0817) loss: 0.8584 (0.8602) time: 0.1183 data: 0.0432 max mem: 8255 +Train: [31] [5000/6250] eta: 0:03:02 lr: 0.000102 grad: 0.0820 (0.0817) loss: 0.8584 (0.8602) time: 0.1517 data: 0.0874 max mem: 8255 +Train: [31] [5100/6250] eta: 0:02:48 lr: 0.000102 grad: 0.0777 (0.0817) loss: 0.8651 (0.8601) time: 0.1451 data: 0.0759 max mem: 8255 +Train: [31] [5200/6250] eta: 0:02:33 lr: 0.000102 grad: 0.0775 (0.0818) loss: 0.8619 (0.8601) time: 0.1839 data: 0.1121 max mem: 8255 +Train: [31] [5300/6250] eta: 0:02:19 lr: 0.000102 grad: 0.0852 (0.0818) loss: 0.8651 (0.8600) time: 0.1644 data: 0.0972 max mem: 8255 +Train: [31] [5400/6250] eta: 0:02:04 lr: 0.000102 grad: 0.0823 (0.0819) loss: 0.8523 (0.8599) time: 0.1413 data: 0.0724 max mem: 8255 +Train: [31] [5500/6250] eta: 0:01:49 lr: 0.000102 grad: 0.0826 (0.0819) loss: 0.8544 (0.8599) time: 0.1668 data: 0.0957 max mem: 8255 +Train: [31] [5600/6250] eta: 0:01:34 lr: 0.000102 grad: 0.0817 (0.0820) loss: 0.8607 (0.8599) time: 0.1202 data: 0.0343 max mem: 8255 +Train: [31] [5700/6250] eta: 0:01:20 lr: 0.000102 grad: 0.0811 (0.0820) loss: 0.8582 (0.8599) time: 0.3041 data: 0.2197 max mem: 8255 +Train: [31] [5800/6250] eta: 0:01:05 lr: 0.000102 grad: 0.0789 (0.0820) loss: 0.8589 (0.8599) time: 0.1201 data: 0.0455 max mem: 8255 +Train: [31] [5900/6250] eta: 0:00:51 lr: 0.000102 grad: 0.0829 (0.0821) loss: 0.8489 (0.8598) time: 0.1206 data: 0.0501 max mem: 8255 +Train: [31] [6000/6250] eta: 0:00:36 lr: 0.000102 grad: 0.0800 (0.0821) loss: 0.8560 (0.8598) time: 0.1914 data: 0.0936 max mem: 8255 +Train: [31] [6100/6250] eta: 0:00:22 lr: 0.000102 grad: 0.0795 (0.0821) loss: 0.8557 (0.8597) time: 0.2272 data: 0.1292 max mem: 8255 +Train: [31] [6200/6250] eta: 0:00:07 lr: 0.000102 grad: 0.0879 (0.0822) loss: 0.8593 (0.8597) time: 0.1771 data: 0.0791 max mem: 8255 +Train: [31] [6249/6250] eta: 0:00:00 lr: 0.000102 grad: 0.0767 (0.0822) loss: 0.8618 (0.8597) time: 0.1568 data: 0.0847 max mem: 8255 +Train: [31] Total time: 0:15:25 (0.1480 s / it) +Averaged stats: lr: 0.000102 grad: 0.0767 (0.0822) loss: 0.8618 (0.8597) +Eval (hcp-train-subset): [31] [ 0/62] eta: 0:04:54 loss: 0.8941 (0.8941) time: 4.7448 data: 4.7121 max mem: 8255 +Eval (hcp-train-subset): [31] [61/62] eta: 0:00:00 loss: 0.8817 (0.8827) time: 0.1387 data: 0.1181 max mem: 8255 +Eval (hcp-train-subset): [31] Total time: 0:00:13 (0.2203 s / it) +Averaged stats (hcp-train-subset): loss: 0.8817 (0.8827) +Eval (hcp-val): [31] [ 0/62] eta: 0:03:27 loss: 0.8799 (0.8799) time: 3.3494 data: 3.2782 max mem: 8255 +Eval (hcp-val): [31] [61/62] eta: 0:00:00 loss: 0.8800 (0.8824) time: 0.1521 data: 0.1302 max mem: 8255 +Eval (hcp-val): [31] Total time: 0:00:13 (0.2136 s / it) +Averaged stats (hcp-val): loss: 0.8800 (0.8824) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +Train: [32] [ 0/6250] eta: 7:13:34 lr: 0.000102 grad: 0.0432 (0.0432) loss: 0.9138 (0.9138) time: 4.1623 data: 3.9160 max mem: 8255 +Train: [32] [ 100/6250] eta: 0:20:53 lr: 0.000102 grad: 0.0816 (0.0957) loss: 0.8597 (0.8775) time: 0.1367 data: 0.0401 max mem: 8255 +Train: [32] [ 200/6250] eta: 0:17:39 lr: 0.000102 grad: 0.0826 (0.0972) loss: 0.8561 (0.8676) time: 0.1604 data: 0.0828 max mem: 8255 +Train: [32] [ 300/6250] eta: 0:16:21 lr: 0.000102 grad: 0.0786 (0.0933) loss: 0.8669 (0.8641) time: 0.1412 data: 0.0620 max mem: 8255 +Train: [32] [ 400/6250] eta: 0:15:24 lr: 0.000102 grad: 0.0741 (0.0905) loss: 0.8688 (0.8637) time: 0.1279 data: 0.0537 max mem: 8255 +Train: [32] [ 500/6250] eta: 0:14:31 lr: 0.000102 grad: 0.0808 (0.0889) loss: 0.8632 (0.8635) time: 0.1333 data: 0.0443 max mem: 8255 +Train: [32] [ 600/6250] eta: 0:14:00 lr: 0.000102 grad: 0.0853 (0.0881) loss: 0.8553 (0.8630) time: 0.1325 data: 0.0611 max mem: 8255 +Train: [32] [ 700/6250] eta: 0:13:26 lr: 0.000102 grad: 0.0808 (0.0877) loss: 0.8581 (0.8625) time: 0.1235 data: 0.0324 max mem: 8255 +Train: [32] [ 800/6250] eta: 0:12:57 lr: 0.000101 grad: 0.0744 (0.0870) loss: 0.8610 (0.8624) time: 0.1294 data: 0.0469 max mem: 8255 +Train: [32] [ 900/6250] eta: 0:12:38 lr: 0.000101 grad: 0.0795 (0.0862) loss: 0.8540 (0.8622) time: 0.1350 data: 0.0643 max mem: 8255 +Train: [32] [1000/6250] eta: 0:12:31 lr: 0.000101 grad: 0.0787 (0.0856) loss: 0.8578 (0.8621) time: 0.1121 data: 0.0244 max mem: 8255 +Train: [32] [1100/6250] eta: 0:12:10 lr: 0.000101 grad: 0.0790 (0.0852) loss: 0.8687 (0.8618) time: 0.1466 data: 0.0767 max mem: 8255 +Train: [32] [1200/6250] eta: 0:11:53 lr: 0.000101 grad: 0.0798 (0.0849) loss: 0.8552 (0.8616) time: 0.1650 data: 0.0943 max mem: 8255 +Train: [32] [1300/6250] eta: 0:11:34 lr: 0.000101 grad: 0.0800 (0.0845) loss: 0.8580 (0.8614) time: 0.1241 data: 0.0561 max mem: 8255 +Train: [32] [1400/6250] eta: 0:11:19 lr: 0.000101 grad: 0.0773 (0.0844) loss: 0.8583 (0.8610) time: 0.0774 data: 0.0013 max mem: 8255 +Train: [32] [1500/6250] eta: 0:11:00 lr: 0.000101 grad: 0.0773 (0.0842) loss: 0.8658 (0.8607) time: 0.1393 data: 0.0650 max mem: 8255 +Train: [32] [1600/6250] eta: 0:10:47 lr: 0.000101 grad: 0.0776 (0.0841) loss: 0.8565 (0.8604) time: 0.1239 data: 0.0482 max mem: 8255 +Train: [32] [1700/6250] eta: 0:10:33 lr: 0.000101 grad: 0.0847 (0.0839) loss: 0.8497 (0.8600) time: 0.1432 data: 0.0755 max mem: 8255 +Train: [32] [1800/6250] eta: 0:10:19 lr: 0.000101 grad: 0.0785 (0.0839) loss: 0.8591 (0.8597) time: 0.1037 data: 0.0168 max mem: 8255 +Train: [32] [1900/6250] eta: 0:10:02 lr: 0.000101 grad: 0.0814 (0.0838) loss: 0.8543 (0.8595) time: 0.1184 data: 0.0470 max mem: 8255 +Train: [32] [2000/6250] eta: 0:09:46 lr: 0.000101 grad: 0.0747 (0.0837) loss: 0.8581 (0.8595) time: 0.1245 data: 0.0594 max mem: 8255 +Train: [32] [2100/6250] eta: 0:09:31 lr: 0.000101 grad: 0.0757 (0.0836) loss: 0.8619 (0.8593) time: 0.1376 data: 0.0734 max mem: 8255 +Train: [32] [2200/6250] eta: 0:09:19 lr: 0.000101 grad: 0.0845 (0.0838) loss: 0.8524 (0.8592) time: 0.1864 data: 0.1180 max mem: 8255 +Train: [32] [2300/6250] eta: 0:09:03 lr: 0.000101 grad: 0.0796 (0.0839) loss: 0.8530 (0.8590) time: 0.1412 data: 0.0678 max mem: 8255 +Train: [32] [2400/6250] eta: 0:08:50 lr: 0.000101 grad: 0.0785 (0.0841) loss: 0.8686 (0.8589) time: 0.1768 data: 0.1120 max mem: 8255 +Train: [32] [2500/6250] eta: 0:08:34 lr: 0.000101 grad: 0.0830 (0.0843) loss: 0.8601 (0.8587) time: 0.1097 data: 0.0398 max mem: 8255 +Train: [32] [2600/6250] eta: 0:08:19 lr: 0.000101 grad: 0.0804 (0.0843) loss: 0.8562 (0.8586) time: 0.1194 data: 0.0399 max mem: 8255 +Train: [32] [2700/6250] eta: 0:08:05 lr: 0.000101 grad: 0.0830 (0.0843) loss: 0.8500 (0.8586) time: 0.1180 data: 0.0442 max mem: 8255 +Train: [32] [2800/6250] eta: 0:07:50 lr: 0.000101 grad: 0.0805 (0.0843) loss: 0.8538 (0.8585) time: 0.1295 data: 0.0602 max mem: 8255 +Train: [32] [2900/6250] eta: 0:07:35 lr: 0.000101 grad: 0.0806 (0.0842) loss: 0.8593 (0.8585) time: 0.1261 data: 0.0593 max mem: 8255 +Train: [32] [3000/6250] eta: 0:07:21 lr: 0.000101 grad: 0.0795 (0.0841) loss: 0.8627 (0.8585) time: 0.1519 data: 0.0778 max mem: 8255 +Train: [32] [3100/6250] eta: 0:07:07 lr: 0.000101 grad: 0.0805 (0.0841) loss: 0.8565 (0.8585) time: 0.1338 data: 0.0658 max mem: 8255 +Train: [32] [3200/6250] eta: 0:06:54 lr: 0.000101 grad: 0.0788 (0.0841) loss: 0.8573 (0.8585) time: 0.1416 data: 0.0726 max mem: 8255 +Train: [32] [3300/6250] eta: 0:06:41 lr: 0.000101 grad: 0.0775 (0.0840) loss: 0.8603 (0.8586) time: 0.1632 data: 0.0956 max mem: 8255 +Train: [32] [3400/6250] eta: 0:06:27 lr: 0.000101 grad: 0.0781 (0.0839) loss: 0.8648 (0.8586) time: 0.1570 data: 0.0925 max mem: 8255 +Train: [32] [3500/6250] eta: 0:06:16 lr: 0.000101 grad: 0.0824 (0.0838) loss: 0.8623 (0.8588) time: 0.1726 data: 0.1052 max mem: 8255 +Train: [32] [3600/6250] eta: 0:06:02 lr: 0.000101 grad: 0.0765 (0.0838) loss: 0.8599 (0.8588) time: 0.1354 data: 0.0638 max mem: 8255 +Train: [32] [3700/6250] eta: 0:05:50 lr: 0.000101 grad: 0.0762 (0.0837) loss: 0.8657 (0.8589) time: 0.1347 data: 0.0446 max mem: 8255 +Train: [32] [3800/6250] eta: 0:05:36 lr: 0.000101 grad: 0.0771 (0.0836) loss: 0.8652 (0.8590) time: 0.1148 data: 0.0304 max mem: 8255 +Train: [32] [3900/6250] eta: 0:05:22 lr: 0.000101 grad: 0.0838 (0.0836) loss: 0.8521 (0.8589) time: 0.0847 data: 0.0077 max mem: 8255 +Train: [32] [4000/6250] eta: 0:05:08 lr: 0.000101 grad: 0.0756 (0.0836) loss: 0.8659 (0.8590) time: 0.1506 data: 0.0771 max mem: 8255 +Train: [32] [4100/6250] eta: 0:04:55 lr: 0.000101 grad: 0.0812 (0.0835) loss: 0.8596 (0.8590) time: 0.1186 data: 0.0274 max mem: 8255 +Train: [32] [4200/6250] eta: 0:04:41 lr: 0.000101 grad: 0.0815 (0.0835) loss: 0.8604 (0.8591) time: 0.1355 data: 0.0709 max mem: 8255 +Train: [32] [4300/6250] eta: 0:04:27 lr: 0.000101 grad: 0.0872 (0.0834) loss: 0.8570 (0.8591) time: 0.1977 data: 0.1362 max mem: 8255 +Train: [32] [4400/6250] eta: 0:04:14 lr: 0.000101 grad: 0.0824 (0.0834) loss: 0.8575 (0.8591) time: 0.1474 data: 0.0714 max mem: 8255 +Train: [32] [4500/6250] eta: 0:04:00 lr: 0.000101 grad: 0.0833 (0.0834) loss: 0.8562 (0.8592) time: 0.1228 data: 0.0534 max mem: 8255 +Train: [32] [4600/6250] eta: 0:03:46 lr: 0.000101 grad: 0.0790 (0.0834) loss: 0.8578 (0.8592) time: 0.1333 data: 0.0648 max mem: 8255 +Train: [32] [4700/6250] eta: 0:03:32 lr: 0.000100 grad: 0.0789 (0.0834) loss: 0.8552 (0.8593) time: 0.1365 data: 0.0602 max mem: 8255 +Train: [32] [4800/6250] eta: 0:03:19 lr: 0.000100 grad: 0.0771 (0.0835) loss: 0.8625 (0.8593) time: 0.1340 data: 0.0653 max mem: 8255 +Train: [32] [4900/6250] eta: 0:03:04 lr: 0.000100 grad: 0.0768 (0.0834) loss: 0.8598 (0.8593) time: 0.1237 data: 0.0467 max mem: 8255 +Train: [32] [5000/6250] eta: 0:02:50 lr: 0.000100 grad: 0.0833 (0.0834) loss: 0.8632 (0.8594) time: 0.1018 data: 0.0256 max mem: 8255 +Train: [32] [5100/6250] eta: 0:02:36 lr: 0.000100 grad: 0.0787 (0.0834) loss: 0.8621 (0.8594) time: 0.1119 data: 0.0385 max mem: 8255 +Train: [32] [5200/6250] eta: 0:02:22 lr: 0.000100 grad: 0.0832 (0.0834) loss: 0.8545 (0.8594) time: 0.1195 data: 0.0376 max mem: 8255 +Train: [32] [5300/6250] eta: 0:02:08 lr: 0.000100 grad: 0.0803 (0.0834) loss: 0.8612 (0.8594) time: 0.1090 data: 0.0328 max mem: 8255 +Train: [32] [5400/6250] eta: 0:01:54 lr: 0.000100 grad: 0.0761 (0.0834) loss: 0.8516 (0.8594) time: 0.1232 data: 0.0455 max mem: 8255 +Train: [32] [5500/6250] eta: 0:01:40 lr: 0.000100 grad: 0.0802 (0.0834) loss: 0.8521 (0.8593) time: 0.1435 data: 0.0728 max mem: 8255 +Train: [32] [5600/6250] eta: 0:01:27 lr: 0.000100 grad: 0.0831 (0.0834) loss: 0.8595 (0.8593) time: 0.1192 data: 0.0493 max mem: 8255 +Train: [32] [5700/6250] eta: 0:01:13 lr: 0.000100 grad: 0.0803 (0.0834) loss: 0.8609 (0.8593) time: 0.1170 data: 0.0445 max mem: 8255 +Train: [32] [5800/6250] eta: 0:01:00 lr: 0.000100 grad: 0.0845 (0.0834) loss: 0.8546 (0.8593) time: 0.1177 data: 0.0476 max mem: 8255 +Train: [32] [5900/6250] eta: 0:00:46 lr: 0.000100 grad: 0.0794 (0.0835) loss: 0.8543 (0.8592) time: 0.1281 data: 0.0641 max mem: 8255 +Train: [32] [6000/6250] eta: 0:00:33 lr: 0.000100 grad: 0.0819 (0.0836) loss: 0.8582 (0.8592) time: 0.1181 data: 0.0466 max mem: 8255 +Train: [32] [6100/6250] eta: 0:00:20 lr: 0.000100 grad: 0.0824 (0.0836) loss: 0.8591 (0.8592) time: 0.1350 data: 0.0678 max mem: 8255 +Train: [32] [6200/6250] eta: 0:00:06 lr: 0.000100 grad: 0.0842 (0.0836) loss: 0.8506 (0.8592) time: 0.1372 data: 0.0680 max mem: 8255 +Train: [32] [6249/6250] eta: 0:00:00 lr: 0.000100 grad: 0.0768 (0.0836) loss: 0.8549 (0.8592) time: 0.1047 data: 0.0187 max mem: 8255 +Train: [32] Total time: 0:14:00 (0.1345 s / it) +Averaged stats: lr: 0.000100 grad: 0.0768 (0.0836) loss: 0.8549 (0.8592) +Eval (hcp-train-subset): [32] [ 0/62] eta: 0:05:32 loss: 0.8857 (0.8857) time: 5.3563 data: 5.3309 max mem: 8255 +Eval (hcp-train-subset): [32] [61/62] eta: 0:00:00 loss: 0.8753 (0.8776) time: 0.1339 data: 0.1124 max mem: 8255 +Eval (hcp-train-subset): [32] Total time: 0:00:12 (0.2071 s / it) +Averaged stats (hcp-train-subset): loss: 0.8753 (0.8776) +Eval (hcp-val): [32] [ 0/62] eta: 0:04:48 loss: 0.8782 (0.8782) time: 4.6506 data: 4.5999 max mem: 8255 +Eval (hcp-val): [32] [61/62] eta: 0:00:00 loss: 0.8803 (0.8820) time: 0.1246 data: 0.1037 max mem: 8255 +Eval (hcp-val): [32] Total time: 0:00:12 (0.2044 s / it) +Averaged stats (hcp-val): loss: 0.8803 (0.8820) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +Train: [33] [ 0/6250] eta: 9:17:51 lr: 0.000100 grad: nan (nan) loss: 0.9018 (0.9018) time: 5.3554 data: 5.2158 max mem: 8255 +Train: [33] [ 100/6250] eta: 0:19:23 lr: 0.000100 grad: 0.0964 (0.1048) loss: 0.8680 (0.8723) time: 0.1636 data: 0.0862 max mem: 8255 +Train: [33] [ 200/6250] eta: 0:16:43 lr: 0.000100 grad: 0.0839 (0.0976) loss: 0.8582 (0.8667) time: 0.1463 data: 0.0730 max mem: 8255 +Train: [33] [ 300/6250] eta: 0:15:01 lr: 0.000100 grad: 0.0752 (0.0943) loss: 0.8625 (0.8642) time: 0.1223 data: 0.0482 max mem: 8255 +Train: [33] [ 400/6250] eta: 0:14:02 lr: 0.000100 grad: 0.0700 (0.0917) loss: 0.8629 (0.8633) time: 0.1053 data: 0.0308 max mem: 8255 +Train: [33] [ 500/6250] eta: 0:13:23 lr: 0.000100 grad: 0.0779 (0.0897) loss: 0.8698 (0.8635) time: 0.1303 data: 0.0540 max mem: 8255 +Train: [33] [ 600/6250] eta: 0:12:45 lr: 0.000100 grad: 0.0803 (0.0881) loss: 0.8694 (0.8635) time: 0.1203 data: 0.0446 max mem: 8255 +Train: [33] [ 700/6250] eta: 0:12:13 lr: 0.000100 grad: 0.0723 (0.0867) loss: 0.8661 (0.8637) time: 0.1038 data: 0.0201 max mem: 8255 +Train: [33] [ 800/6250] eta: 0:11:50 lr: 0.000100 grad: 0.0819 (0.0862) loss: 0.8646 (0.8635) time: 0.1122 data: 0.0311 max mem: 8255 +Train: [33] [ 900/6250] eta: 0:11:31 lr: 0.000100 grad: 0.0768 (0.0853) loss: 0.8678 (0.8638) time: 0.1139 data: 0.0338 max mem: 8255 +Train: [33] [1000/6250] eta: 0:11:17 lr: 0.000100 grad: 0.0717 (0.0844) loss: 0.8633 (0.8641) time: 0.1344 data: 0.0618 max mem: 8255 +Train: [33] [1100/6250] eta: 0:11:02 lr: 0.000100 grad: 0.0729 (0.0836) loss: 0.8636 (0.8643) time: 0.1366 data: 0.0676 max mem: 8255 +Train: [33] [1200/6250] eta: 0:10:51 lr: 0.000100 grad: 0.0753 (0.0841) loss: 0.8592 (0.8641) time: 0.1196 data: 0.0426 max mem: 8255 +Train: [33] [1300/6250] eta: 0:10:41 lr: 0.000100 grad: 0.0784 (0.0839) loss: 0.8603 (0.8639) time: 0.1438 data: 0.0810 max mem: 8255 +Train: [33] [1400/6250] eta: 0:10:30 lr: 0.000100 grad: 0.0780 (0.0835) loss: 0.8630 (0.8638) time: 0.1256 data: 0.0486 max mem: 8255 +Train: [33] [1500/6250] eta: 0:10:18 lr: 0.000100 grad: 0.0796 (0.0834) loss: 0.8630 (0.8638) time: 0.1506 data: 0.0771 max mem: 8255 +Train: [33] [1600/6250] eta: 0:10:09 lr: 0.000100 grad: 0.0798 (0.0834) loss: 0.8646 (0.8635) time: 0.1649 data: 0.0954 max mem: 8255 +Train: [33] [1700/6250] eta: 0:09:53 lr: 0.000100 grad: 0.0808 (0.0833) loss: 0.8564 (0.8633) time: 0.1111 data: 0.0373 max mem: 8255 +Train: [33] [1800/6250] eta: 0:09:40 lr: 0.000100 grad: 0.0799 (0.0831) loss: 0.8664 (0.8632) time: 0.1251 data: 0.0537 max mem: 8255 +Train: [33] [1900/6250] eta: 0:09:26 lr: 0.000100 grad: 0.0822 (0.0831) loss: 0.8537 (0.8629) time: 0.1213 data: 0.0396 max mem: 8255 +Train: [33] [2000/6250] eta: 0:09:14 lr: 0.000100 grad: 0.0809 (0.0832) loss: 0.8523 (0.8626) time: 0.1391 data: 0.0757 max mem: 8255 +Train: [33] [2100/6250] eta: 0:09:00 lr: 0.000100 grad: 0.0790 (0.0832) loss: 0.8651 (0.8623) time: 0.1256 data: 0.0595 max mem: 8255 +Train: [33] [2200/6250] eta: 0:08:47 lr: 0.000099 grad: 0.0774 (0.0832) loss: 0.8580 (0.8621) time: 0.1349 data: 0.0751 max mem: 8255 +Train: [33] [2300/6250] eta: 0:08:34 lr: 0.000099 grad: 0.0797 (0.0832) loss: 0.8574 (0.8619) time: 0.1352 data: 0.0624 max mem: 8255 +Train: [33] [2400/6250] eta: 0:08:20 lr: 0.000099 grad: 0.0800 (0.0832) loss: 0.8571 (0.8617) time: 0.1268 data: 0.0592 max mem: 8255 +Train: [33] [2500/6250] eta: 0:08:07 lr: 0.000099 grad: 0.0786 (0.0833) loss: 0.8589 (0.8615) time: 0.1305 data: 0.0637 max mem: 8255 +Train: [33] [2600/6250] eta: 0:07:57 lr: 0.000099 grad: 0.0829 (0.0833) loss: 0.8530 (0.8614) time: 0.1623 data: 0.0865 max mem: 8255 +Train: [33] [2700/6250] eta: 0:07:46 lr: 0.000099 grad: 0.0793 (0.0833) loss: 0.8540 (0.8612) time: 0.1343 data: 0.0621 max mem: 8255 +Train: [33] [2800/6250] eta: 0:07:35 lr: 0.000099 grad: 0.0815 (0.0833) loss: 0.8548 (0.8611) time: 0.1599 data: 0.1021 max mem: 8255 +Train: [33] [2900/6250] eta: 0:07:22 lr: 0.000099 grad: 0.0845 (0.0833) loss: 0.8502 (0.8610) time: 0.1319 data: 0.0653 max mem: 8255 +Train: [33] [3000/6250] eta: 0:07:11 lr: 0.000099 grad: 0.0795 (0.0833) loss: 0.8539 (0.8608) time: 0.1466 data: 0.0758 max mem: 8255 +Train: [33] [3100/6250] eta: 0:06:58 lr: 0.000099 grad: 0.0775 (0.0834) loss: 0.8584 (0.8607) time: 0.1363 data: 0.0616 max mem: 8255 +Train: [33] [3200/6250] eta: 0:06:47 lr: 0.000099 grad: 0.0859 (0.0834) loss: 0.8522 (0.8606) time: 0.1714 data: 0.1110 max mem: 8255 +Train: [33] [3300/6250] eta: 0:06:33 lr: 0.000099 grad: 0.0861 (0.0835) loss: 0.8603 (0.8605) time: 0.1283 data: 0.0598 max mem: 8255 +Train: [33] [3400/6250] eta: 0:06:20 lr: 0.000099 grad: 0.0817 (0.0835) loss: 0.8586 (0.8604) time: 0.1356 data: 0.0659 max mem: 8255 +Train: [33] [3500/6250] eta: 0:06:06 lr: 0.000099 grad: 0.0842 (0.0835) loss: 0.8520 (0.8603) time: 0.1306 data: 0.0570 max mem: 8255 +Train: [33] [3600/6250] eta: 0:05:53 lr: 0.000099 grad: 0.0880 (0.0836) loss: 0.8539 (0.8603) time: 0.1512 data: 0.0862 max mem: 8255 +Train: [33] [3700/6250] eta: 0:05:40 lr: 0.000099 grad: 0.0800 (0.0836) loss: 0.8597 (0.8603) time: 0.1296 data: 0.0551 max mem: 8255 +Train: [33] [3800/6250] eta: 0:05:27 lr: 0.000099 grad: 0.0771 (0.0836) loss: 0.8651 (0.8604) time: 0.1178 data: 0.0389 max mem: 8255 +Train: [33] [3900/6250] eta: 0:05:13 lr: 0.000099 grad: 0.0854 (0.0836) loss: 0.8597 (0.8604) time: 0.1171 data: 0.0515 max mem: 8255 +Train: [33] [4000/6250] eta: 0:04:59 lr: 0.000099 grad: 0.0787 (0.0836) loss: 0.8613 (0.8604) time: 0.1288 data: 0.0597 max mem: 8255 +Train: [33] [4100/6250] eta: 0:04:46 lr: 0.000099 grad: 0.0841 (0.0835) loss: 0.8581 (0.8605) time: 0.1273 data: 0.0575 max mem: 8255 +Train: [33] [4200/6250] eta: 0:04:33 lr: 0.000099 grad: 0.0788 (0.0836) loss: 0.8606 (0.8605) time: 0.1438 data: 0.0736 max mem: 8255 +Train: [33] [4300/6250] eta: 0:04:19 lr: 0.000099 grad: 0.0761 (0.0835) loss: 0.8658 (0.8606) time: 0.1136 data: 0.0482 max mem: 8255 +Train: [33] [4400/6250] eta: 0:04:06 lr: 0.000099 grad: 0.0794 (0.0838) loss: 0.8630 (0.8606) time: 0.1517 data: 0.0872 max mem: 8255 +Train: [33] [4500/6250] eta: 0:03:52 lr: 0.000099 grad: 0.0892 (0.0838) loss: 0.8576 (0.8606) time: 0.1149 data: 0.0522 max mem: 8255 +Train: [33] [4600/6250] eta: 0:03:40 lr: 0.000099 grad: 0.0742 (0.0838) loss: 0.8598 (0.8606) time: 0.1667 data: 0.0995 max mem: 8255 +Train: [33] [4700/6250] eta: 0:03:27 lr: 0.000099 grad: 0.0805 (0.0837) loss: 0.8575 (0.8606) time: 0.1600 data: 0.0882 max mem: 8255 +Train: [33] [4800/6250] eta: 0:03:15 lr: 0.000099 grad: 0.0876 (0.0838) loss: 0.8559 (0.8605) time: 0.1600 data: 0.0869 max mem: 8255 +Train: [33] [4900/6250] eta: 0:03:02 lr: 0.000099 grad: 0.0806 (0.0839) loss: 0.8621 (0.8605) time: 0.1232 data: 0.0531 max mem: 8255 +Train: [33] [5000/6250] eta: 0:02:49 lr: 0.000099 grad: 0.0829 (0.0839) loss: 0.8569 (0.8604) time: 0.1522 data: 0.0842 max mem: 8255 +Train: [33] [5100/6250] eta: 0:02:35 lr: 0.000099 grad: 0.0814 (0.0838) loss: 0.8529 (0.8603) time: 0.1428 data: 0.0684 max mem: 8255 +Train: [33] [5200/6250] eta: 0:02:22 lr: 0.000099 grad: 0.0824 (0.0839) loss: 0.8546 (0.8603) time: 0.1361 data: 0.0717 max mem: 8255 +Train: [33] [5300/6250] eta: 0:02:08 lr: 0.000099 grad: 0.0815 (0.0839) loss: 0.8590 (0.8602) time: 0.1350 data: 0.0656 max mem: 8255 +Train: [33] [5400/6250] eta: 0:01:55 lr: 0.000099 grad: 0.0918 (0.0840) loss: 0.8506 (0.8601) time: 0.1136 data: 0.0292 max mem: 8255 +Train: [33] [5500/6250] eta: 0:01:41 lr: 0.000099 grad: 0.0853 (0.0840) loss: 0.8456 (0.8600) time: 0.1327 data: 0.0651 max mem: 8255 +Train: [33] [5600/6250] eta: 0:01:28 lr: 0.000099 grad: 0.0777 (0.0840) loss: 0.8596 (0.8599) time: 0.0955 data: 0.0002 max mem: 8255 +Train: [33] [5700/6250] eta: 0:01:14 lr: 0.000099 grad: 0.0814 (0.0840) loss: 0.8649 (0.8598) time: 0.1423 data: 0.0700 max mem: 8255 +Train: [33] [5800/6250] eta: 0:01:01 lr: 0.000099 grad: 0.0831 (0.0841) loss: 0.8618 (0.8598) time: 0.1589 data: 0.0960 max mem: 8255 +Train: [33] [5900/6250] eta: 0:00:47 lr: 0.000098 grad: 0.0858 (0.0841) loss: 0.8577 (0.8597) time: 0.0960 data: 0.0225 max mem: 8255 +Train: [33] [6000/6250] eta: 0:00:33 lr: 0.000098 grad: 0.0812 (0.0841) loss: 0.8630 (0.8597) time: 0.1458 data: 0.0758 max mem: 8255 +Train: [33] [6100/6250] eta: 0:00:20 lr: 0.000098 grad: 0.0872 (0.0841) loss: 0.8593 (0.8596) time: 0.1419 data: 0.0741 max mem: 8255 +Train: [33] [6200/6250] eta: 0:00:06 lr: 0.000098 grad: 0.0826 (0.0842) loss: 0.8622 (0.8596) time: 0.1337 data: 0.0589 max mem: 8255 +Train: [33] [6249/6250] eta: 0:00:00 lr: 0.000098 grad: 0.0797 (0.0842) loss: 0.8605 (0.8596) time: 0.1469 data: 0.0759 max mem: 8255 +Train: [33] Total time: 0:14:14 (0.1367 s / it) +Averaged stats: lr: 0.000098 grad: 0.0797 (0.0842) loss: 0.8605 (0.8596) +Eval (hcp-train-subset): [33] [ 0/62] eta: 0:04:08 loss: 0.8910 (0.8910) time: 4.0117 data: 3.9350 max mem: 8255 +Eval (hcp-train-subset): [33] [61/62] eta: 0:00:00 loss: 0.8804 (0.8821) time: 0.1134 data: 0.0928 max mem: 8255 +Eval (hcp-train-subset): [33] Total time: 0:00:13 (0.2126 s / it) +Averaged stats (hcp-train-subset): loss: 0.8804 (0.8821) +Eval (hcp-val): [33] [ 0/62] eta: 0:03:04 loss: 0.8794 (0.8794) time: 2.9733 data: 2.9134 max mem: 8255 +Eval (hcp-val): [33] [61/62] eta: 0:00:00 loss: 0.8800 (0.8826) time: 0.0997 data: 0.0781 max mem: 8255 +Eval (hcp-val): [33] Total time: 0:00:12 (0.2078 s / it) +Averaged stats (hcp-val): loss: 0.8800 (0.8826) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +Train: [34] [ 0/6250] eta: 6:34:10 lr: 0.000098 grad: 0.1090 (0.1090) loss: 0.8473 (0.8473) time: 3.7841 data: 3.6051 max mem: 8255 +Train: [34] [ 100/6250] eta: 0:19:50 lr: 0.000098 grad: 0.0964 (0.1081) loss: 0.8803 (0.8707) time: 0.1482 data: 0.0637 max mem: 8255 +Train: [34] [ 200/6250] eta: 0:16:20 lr: 0.000098 grad: 0.0993 (0.1038) loss: 0.8605 (0.8657) time: 0.1387 data: 0.0629 max mem: 8255 +Train: [34] [ 300/6250] eta: 0:14:46 lr: 0.000098 grad: 0.0788 (0.0975) loss: 0.8665 (0.8641) time: 0.1337 data: 0.0488 max mem: 8255 +Train: [34] [ 400/6250] eta: 0:13:49 lr: 0.000098 grad: 0.0800 (0.0937) loss: 0.8651 (0.8637) time: 0.1150 data: 0.0391 max mem: 8255 +Train: [34] [ 500/6250] eta: 0:13:14 lr: 0.000098 grad: 0.0757 (0.0913) loss: 0.8654 (0.8640) time: 0.1293 data: 0.0542 max mem: 8255 +Train: [34] [ 600/6250] eta: 0:12:51 lr: 0.000098 grad: 0.0785 (0.0899) loss: 0.8603 (0.8638) time: 0.1067 data: 0.0206 max mem: 8255 +Train: [34] [ 700/6250] eta: 0:12:27 lr: 0.000098 grad: 0.0759 (0.0883) loss: 0.8605 (0.8637) time: 0.1311 data: 0.0518 max mem: 8255 +Train: [34] [ 800/6250] eta: 0:12:08 lr: 0.000098 grad: 0.0789 (0.0875) loss: 0.8654 (0.8638) time: 0.1258 data: 0.0475 max mem: 8255 +Train: [34] [ 900/6250] eta: 0:11:56 lr: 0.000098 grad: 0.0770 (0.0867) loss: 0.8607 (0.8636) time: 0.1444 data: 0.0651 max mem: 8255 +Train: [34] [1000/6250] eta: 0:11:39 lr: 0.000098 grad: 0.0805 (0.0863) loss: 0.8581 (0.8632) time: 0.1263 data: 0.0524 max mem: 8255 +Train: [34] [1100/6250] eta: 0:11:34 lr: 0.000098 grad: 0.0770 (0.0859) loss: 0.8536 (0.8630) time: 0.0758 data: 0.0002 max mem: 8255 +Train: [34] [1200/6250] eta: 0:11:17 lr: 0.000098 grad: 0.0786 (0.0857) loss: 0.8584 (0.8626) time: 0.1262 data: 0.0576 max mem: 8255 +Train: [34] [1300/6250] eta: 0:11:02 lr: 0.000098 grad: 0.0824 (0.0854) loss: 0.8622 (0.8623) time: 0.1277 data: 0.0581 max mem: 8255 +Train: [34] [1400/6250] eta: 0:10:51 lr: 0.000098 grad: 0.0754 (0.0853) loss: 0.8618 (0.8621) time: 0.1512 data: 0.0821 max mem: 8255 +Train: [34] [1500/6250] eta: 0:10:37 lr: 0.000098 grad: 0.0774 (0.0851) loss: 0.8579 (0.8619) time: 0.1120 data: 0.0391 max mem: 8255 +Train: [34] [1600/6250] eta: 0:10:23 lr: 0.000098 grad: 0.0790 (0.0851) loss: 0.8549 (0.8615) time: 0.1232 data: 0.0488 max mem: 8255 +Train: [34] [1700/6250] eta: 0:10:10 lr: 0.000098 grad: 0.0795 (0.0849) loss: 0.8579 (0.8613) time: 0.1264 data: 0.0478 max mem: 8255 +Train: [34] [1800/6250] eta: 0:10:03 lr: 0.000098 grad: 0.0816 (0.0849) loss: 0.8563 (0.8611) time: 0.2187 data: 0.1428 max mem: 8255 +Train: [34] [1900/6250] eta: 0:09:47 lr: 0.000098 grad: 0.0808 (0.0849) loss: 0.8629 (0.8609) time: 0.1441 data: 0.0744 max mem: 8255 +Train: [34] [2000/6250] eta: 0:09:35 lr: 0.000098 grad: 0.0807 (0.0849) loss: 0.8556 (0.8606) time: 0.1238 data: 0.0497 max mem: 8255 +Train: [34] [2100/6250] eta: 0:09:21 lr: 0.000098 grad: 0.0798 (0.0848) loss: 0.8566 (0.8604) time: 0.1282 data: 0.0515 max mem: 8255 +Train: [34] [2200/6250] eta: 0:09:07 lr: 0.000098 grad: 0.0816 (0.0847) loss: 0.8567 (0.8602) time: 0.1507 data: 0.0822 max mem: 8255 +Train: [34] [2300/6250] eta: 0:08:52 lr: 0.000098 grad: 0.0739 (0.0846) loss: 0.8591 (0.8601) time: 0.1366 data: 0.0593 max mem: 8255 +Train: [34] [2400/6250] eta: 0:08:42 lr: 0.000098 grad: 0.0836 (0.0845) loss: 0.8568 (0.8600) time: 0.1818 data: 0.1164 max mem: 8255 +Train: [34] [2500/6250] eta: 0:08:27 lr: 0.000098 grad: 0.0874 (0.0845) loss: 0.8532 (0.8599) time: 0.1258 data: 0.0526 max mem: 8255 +Train: [34] [2600/6250] eta: 0:08:14 lr: 0.000098 grad: 0.0828 (0.0846) loss: 0.8624 (0.8598) time: 0.1283 data: 0.0546 max mem: 8255 +Train: [34] [2700/6250] eta: 0:08:02 lr: 0.000098 grad: 0.0854 (0.0846) loss: 0.8512 (0.8597) time: 0.1395 data: 0.0711 max mem: 8255 +Train: [34] [2800/6250] eta: 0:07:50 lr: 0.000098 grad: 0.0795 (0.0845) loss: 0.8589 (0.8596) time: 0.1590 data: 0.0905 max mem: 8255 +Train: [34] [2900/6250] eta: 0:07:35 lr: 0.000098 grad: 0.0788 (0.0845) loss: 0.8591 (0.8595) time: 0.1339 data: 0.0685 max mem: 8255 +Train: [34] [3000/6250] eta: 0:07:20 lr: 0.000098 grad: 0.0784 (0.0844) loss: 0.8584 (0.8594) time: 0.1261 data: 0.0574 max mem: 8255 +Train: [34] [3100/6250] eta: 0:07:07 lr: 0.000098 grad: 0.0821 (0.0843) loss: 0.8590 (0.8594) time: 0.1314 data: 0.0668 max mem: 8255 +Train: [34] [3200/6250] eta: 0:06:52 lr: 0.000098 grad: 0.0813 (0.0843) loss: 0.8525 (0.8594) time: 0.1252 data: 0.0505 max mem: 8255 +Train: [34] [3300/6250] eta: 0:06:38 lr: 0.000097 grad: 0.0883 (0.0843) loss: 0.8526 (0.8593) time: 0.1074 data: 0.0333 max mem: 8255 +Train: [34] [3400/6250] eta: 0:06:24 lr: 0.000097 grad: 0.0757 (0.0843) loss: 0.8649 (0.8592) time: 0.1335 data: 0.0606 max mem: 8255 +Train: [34] [3500/6250] eta: 0:06:12 lr: 0.000097 grad: 0.0856 (0.0843) loss: 0.8565 (0.8591) time: 0.1260 data: 0.0505 max mem: 8255 +Train: [34] [3600/6250] eta: 0:05:57 lr: 0.000097 grad: 0.0812 (0.0842) loss: 0.8532 (0.8591) time: 0.1137 data: 0.0364 max mem: 8255 +Train: [34] [3700/6250] eta: 0:05:43 lr: 0.000097 grad: 0.0783 (0.0842) loss: 0.8622 (0.8591) time: 0.1238 data: 0.0455 max mem: 8255 +Train: [34] [3800/6250] eta: 0:05:30 lr: 0.000097 grad: 0.0758 (0.0842) loss: 0.8552 (0.8591) time: 0.1250 data: 0.0531 max mem: 8255 +Train: [34] [3900/6250] eta: 0:05:16 lr: 0.000097 grad: 0.0839 (0.0843) loss: 0.8540 (0.8589) time: 0.1014 data: 0.0344 max mem: 8255 +Train: [34] [4000/6250] eta: 0:05:03 lr: 0.000097 grad: 0.0812 (0.0841) loss: 0.8558 (0.8589) time: 0.1451 data: 0.0805 max mem: 8255 +Train: [34] [4100/6250] eta: 0:04:50 lr: 0.000097 grad: 0.0848 (0.0841) loss: 0.8516 (0.8589) time: 0.1373 data: 0.0740 max mem: 8255 +Train: [34] [4200/6250] eta: 0:04:37 lr: 0.000097 grad: 0.0854 (0.0841) loss: 0.8503 (0.8588) time: 0.1931 data: 0.1213 max mem: 8255 +Train: [34] [4300/6250] eta: 0:04:22 lr: 0.000097 grad: 0.0788 (0.0840) loss: 0.8535 (0.8588) time: 0.1439 data: 0.0743 max mem: 8255 +Train: [34] [4400/6250] eta: 0:04:09 lr: 0.000097 grad: 0.0825 (0.0840) loss: 0.8504 (0.8587) time: 0.1243 data: 0.0608 max mem: 8255 +Train: [34] [4500/6250] eta: 0:03:55 lr: 0.000097 grad: 0.0857 (0.0840) loss: 0.8566 (0.8587) time: 0.1220 data: 0.0604 max mem: 8255 +Train: [34] [4600/6250] eta: 0:03:42 lr: 0.000097 grad: 0.0817 (0.0840) loss: 0.8527 (0.8586) time: 0.1181 data: 0.0445 max mem: 8255 +Train: [34] [4700/6250] eta: 0:03:28 lr: 0.000097 grad: 0.0810 (0.0841) loss: 0.8604 (0.8585) time: 0.1422 data: 0.0745 max mem: 8255 +Train: [34] [4800/6250] eta: 0:03:14 lr: 0.000097 grad: 0.0873 (0.0841) loss: 0.8582 (0.8585) time: 0.1282 data: 0.0582 max mem: 8255 +Train: [34] [4900/6250] eta: 0:03:01 lr: 0.000097 grad: 0.0852 (0.0841) loss: 0.8540 (0.8584) time: 0.1545 data: 0.0682 max mem: 8255 +Train: [34] [5000/6250] eta: 0:02:48 lr: 0.000097 grad: 0.0849 (0.0841) loss: 0.8542 (0.8583) time: 0.1393 data: 0.0664 max mem: 8255 +Train: [34] [5100/6250] eta: 0:02:34 lr: 0.000097 grad: 0.0824 (0.0843) loss: 0.8552 (0.8582) time: 0.1282 data: 0.0578 max mem: 8255 +Train: [34] [5200/6250] eta: 0:02:21 lr: 0.000097 grad: 0.0857 (0.0843) loss: 0.8582 (0.8582) time: 0.1498 data: 0.0790 max mem: 8255 +Train: [34] [5300/6250] eta: 0:02:08 lr: 0.000097 grad: 0.0785 (0.0844) loss: 0.8593 (0.8581) time: 0.1560 data: 0.0883 max mem: 8255 +Train: [34] [5400/6250] eta: 0:01:54 lr: 0.000097 grad: 0.0851 (0.0845) loss: 0.8583 (0.8581) time: 0.1310 data: 0.0657 max mem: 8255 +Train: [34] [5500/6250] eta: 0:01:40 lr: 0.000097 grad: 0.0888 (0.0846) loss: 0.8579 (0.8581) time: 0.1305 data: 0.0599 max mem: 8255 +Train: [34] [5600/6250] eta: 0:01:27 lr: 0.000097 grad: 0.0869 (0.0846) loss: 0.8554 (0.8580) time: 0.1435 data: 0.0665 max mem: 8255 +Train: [34] [5700/6250] eta: 0:01:13 lr: 0.000097 grad: 0.0841 (0.0847) loss: 0.8551 (0.8579) time: 0.1073 data: 0.0401 max mem: 8255 +Train: [34] [5800/6250] eta: 0:01:00 lr: 0.000097 grad: 0.0910 (0.0848) loss: 0.8443 (0.8578) time: 0.1013 data: 0.0195 max mem: 8255 +Train: [34] [5900/6250] eta: 0:00:46 lr: 0.000097 grad: 0.0889 (0.0848) loss: 0.8513 (0.8576) time: 0.1057 data: 0.0224 max mem: 8255 +Train: [34] [6000/6250] eta: 0:00:33 lr: 0.000097 grad: 0.0866 (0.0849) loss: 0.8479 (0.8575) time: 0.1187 data: 0.0489 max mem: 8255 +Train: [34] [6100/6250] eta: 0:00:19 lr: 0.000097 grad: 0.0854 (0.0849) loss: 0.8542 (0.8575) time: 0.1181 data: 0.0415 max mem: 8255 +Train: [34] [6200/6250] eta: 0:00:06 lr: 0.000097 grad: 0.0866 (0.0850) loss: 0.8478 (0.8573) time: 0.1194 data: 0.0387 max mem: 8255 +Train: [34] [6249/6250] eta: 0:00:00 lr: 0.000097 grad: 0.0849 (0.0850) loss: 0.8576 (0.8573) time: 0.1266 data: 0.0563 max mem: 8255 +Train: [34] Total time: 0:13:52 (0.1331 s / it) +Averaged stats: lr: 0.000097 grad: 0.0849 (0.0850) loss: 0.8576 (0.8573) +Eval (hcp-train-subset): [34] [ 0/62] eta: 0:03:52 loss: 0.8867 (0.8867) time: 3.7564 data: 3.6953 max mem: 8255 +Eval (hcp-train-subset): [34] [61/62] eta: 0:00:00 loss: 0.8833 (0.8829) time: 0.0887 data: 0.0677 max mem: 8255 +Eval (hcp-train-subset): [34] Total time: 0:00:13 (0.2109 s / it) +Averaged stats (hcp-train-subset): loss: 0.8833 (0.8829) +Making plots (hcp-train-subset): example=16 +Eval (hcp-val): [34] [ 0/62] eta: 0:03:21 loss: 0.8766 (0.8766) time: 3.2442 data: 3.1725 max mem: 8255 +Eval (hcp-val): [34] [61/62] eta: 0:00:00 loss: 0.8812 (0.8817) time: 0.1102 data: 0.0882 max mem: 8255 +Eval (hcp-val): [34] Total time: 0:00:13 (0.2160 s / it) +Averaged stats (hcp-val): loss: 0.8812 (0.8817) +Making plots (hcp-val): example=53 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +Train: [35] [ 0/6250] eta: 9:58:50 lr: 0.000097 grad: 0.0807 (0.0807) loss: 0.8739 (0.8739) time: 5.7489 data: 5.6580 max mem: 8255 +Train: [35] [ 100/6250] eta: 0:20:16 lr: 0.000097 grad: 0.0814 (0.0967) loss: 0.8798 (0.8867) time: 0.1797 data: 0.1026 max mem: 8255 +Train: [35] [ 200/6250] eta: 0:17:12 lr: 0.000097 grad: 0.0916 (0.0911) loss: 0.8627 (0.8783) time: 0.1190 data: 0.0397 max mem: 8255 +Train: [35] [ 300/6250] eta: 0:15:51 lr: 0.000097 grad: 0.0845 (0.0908) loss: 0.8595 (0.8728) time: 0.1290 data: 0.0518 max mem: 8255 +Train: [35] [ 400/6250] eta: 0:14:49 lr: 0.000097 grad: 0.0790 (0.0903) loss: 0.8645 (0.8681) time: 0.1354 data: 0.0646 max mem: 8255 +Train: [35] [ 500/6250] eta: 0:14:10 lr: 0.000097 grad: 0.0842 (0.0903) loss: 0.8547 (0.8651) time: 0.1466 data: 0.0646 max mem: 8255 +Train: [35] [ 600/6250] eta: 0:13:42 lr: 0.000097 grad: 0.0796 (0.0888) loss: 0.8603 (0.8636) time: 0.1328 data: 0.0612 max mem: 8255 +Train: [35] [ 700/6250] eta: 0:13:09 lr: 0.000096 grad: 0.0859 (0.0882) loss: 0.8553 (0.8620) time: 0.1331 data: 0.0595 max mem: 8255 +Train: [35] [ 800/6250] eta: 0:12:58 lr: 0.000096 grad: 0.0801 (0.0875) loss: 0.8517 (0.8612) time: 0.1737 data: 0.1043 max mem: 8255 +Train: [35] [ 900/6250] eta: 0:12:56 lr: 0.000096 grad: 0.0803 (0.0871) loss: 0.8550 (0.8606) time: 0.1742 data: 0.1014 max mem: 8255 +Train: [35] [1000/6250] eta: 0:12:47 lr: 0.000096 grad: 0.0808 (0.0866) loss: 0.8581 (0.8600) time: 0.1427 data: 0.0708 max mem: 8255 +Train: [35] [1100/6250] eta: 0:12:36 lr: 0.000096 grad: 0.0800 (0.0861) loss: 0.8557 (0.8595) time: 0.1579 data: 0.0920 max mem: 8255 +Train: [35] [1200/6250] eta: 0:12:31 lr: 0.000096 grad: 0.0811 (0.0859) loss: 0.8559 (0.8592) time: 0.1697 data: 0.1022 max mem: 8255 +Train: [35] [1300/6250] eta: 0:12:19 lr: 0.000096 grad: 0.0803 (0.0856) loss: 0.8543 (0.8588) time: 0.1585 data: 0.0830 max mem: 8255 +Train: [35] [1400/6250] eta: 0:12:06 lr: 0.000096 grad: 0.0789 (0.0855) loss: 0.8487 (0.8582) time: 0.1582 data: 0.0914 max mem: 8255 +Train: [35] [1500/6250] eta: 0:11:48 lr: 0.000096 grad: 0.0786 (0.0853) loss: 0.8567 (0.8578) time: 0.1161 data: 0.0449 max mem: 8255 +Train: [35] [1600/6250] eta: 0:11:33 lr: 0.000096 grad: 0.0831 (0.0851) loss: 0.8533 (0.8575) time: 0.1381 data: 0.0737 max mem: 8255 +Train: [35] [1700/6250] eta: 0:11:14 lr: 0.000096 grad: 0.0777 (0.0850) loss: 0.8587 (0.8574) time: 0.1524 data: 0.0740 max mem: 8255 +Train: [35] [1800/6250] eta: 0:10:59 lr: 0.000096 grad: 0.0809 (0.0850) loss: 0.8522 (0.8572) time: 0.1540 data: 0.0826 max mem: 8255 +Train: [35] [1900/6250] eta: 0:10:46 lr: 0.000096 grad: 0.0853 (0.0849) loss: 0.8573 (0.8572) time: 0.0954 data: 0.0144 max mem: 8255 +Train: [35] [2000/6250] eta: 0:10:28 lr: 0.000096 grad: 0.0823 (0.0848) loss: 0.8578 (0.8572) time: 0.1353 data: 0.0681 max mem: 8255 +Train: [35] [2100/6250] eta: 0:10:10 lr: 0.000096 grad: 0.0771 (0.0850) loss: 0.8640 (0.8572) time: 0.1266 data: 0.0360 max mem: 8255 +Train: [35] [2200/6250] eta: 0:09:54 lr: 0.000096 grad: 0.0783 (0.0850) loss: 0.8594 (0.8572) time: 0.1621 data: 0.0783 max mem: 8255 +Train: [35] [2300/6250] eta: 0:09:42 lr: 0.000096 grad: 0.0801 (0.0849) loss: 0.8541 (0.8572) time: 0.1182 data: 0.0405 max mem: 8255 +Train: [35] [2400/6250] eta: 0:09:24 lr: 0.000096 grad: 0.0838 (0.0848) loss: 0.8585 (0.8572) time: 0.1103 data: 0.0394 max mem: 8255 +Train: [35] [2500/6250] eta: 0:09:09 lr: 0.000096 grad: 0.0871 (0.0848) loss: 0.8496 (0.8570) time: 0.1748 data: 0.0979 max mem: 8255 +Train: [35] [2600/6250] eta: 0:08:50 lr: 0.000096 grad: 0.0788 (0.0848) loss: 0.8482 (0.8570) time: 0.1351 data: 0.0722 max mem: 8255 +Train: [35] [2700/6250] eta: 0:08:33 lr: 0.000096 grad: 0.0766 (0.0848) loss: 0.8636 (0.8571) time: 0.1284 data: 0.0626 max mem: 8255 +Train: [35] [2800/6250] eta: 0:08:18 lr: 0.000096 grad: 0.0811 (0.0846) loss: 0.8558 (0.8571) time: 0.1353 data: 0.0689 max mem: 8255 +Train: [35] [2900/6250] eta: 0:08:02 lr: 0.000096 grad: 0.0815 (0.0847) loss: 0.8581 (0.8571) time: 0.1230 data: 0.0533 max mem: 8255 +Train: [35] [3000/6250] eta: 0:07:46 lr: 0.000096 grad: 0.0770 (0.0846) loss: 0.8580 (0.8571) time: 0.1246 data: 0.0516 max mem: 8255 +Train: [35] [3100/6250] eta: 0:07:31 lr: 0.000096 grad: 0.0823 (0.0845) loss: 0.8680 (0.8572) time: 0.1587 data: 0.0807 max mem: 8255 +Train: [35] [3200/6250] eta: 0:07:16 lr: 0.000096 grad: 0.0788 (0.0845) loss: 0.8655 (0.8573) time: 0.1892 data: 0.1234 max mem: 8255 +Train: [35] [3300/6250] eta: 0:07:00 lr: 0.000096 grad: 0.0826 (0.0846) loss: 0.8496 (0.8573) time: 0.1077 data: 0.0405 max mem: 8255 +Train: [35] [3400/6250] eta: 0:06:45 lr: 0.000096 grad: 0.0844 (0.0846) loss: 0.8558 (0.8572) time: 0.1079 data: 0.0395 max mem: 8255 +Train: [35] [3500/6250] eta: 0:06:30 lr: 0.000096 grad: 0.0891 (0.0847) loss: 0.8618 (0.8573) time: 0.1199 data: 0.0488 max mem: 8255 +Train: [35] [3600/6250] eta: 0:06:15 lr: 0.000096 grad: 0.0793 (0.0846) loss: 0.8611 (0.8573) time: 0.1370 data: 0.0669 max mem: 8255 +Train: [35] [3700/6250] eta: 0:05:59 lr: 0.000096 grad: 0.0770 (0.0846) loss: 0.8516 (0.8572) time: 0.1285 data: 0.0542 max mem: 8255 +Train: [35] [3800/6250] eta: 0:05:45 lr: 0.000096 grad: 0.0858 (0.0846) loss: 0.8548 (0.8570) time: 0.1282 data: 0.0619 max mem: 8255 +Train: [35] [3900/6250] eta: 0:05:30 lr: 0.000096 grad: 0.0821 (0.0848) loss: 0.8532 (0.8570) time: 0.1205 data: 0.0573 max mem: 8255 +Train: [35] [4000/6250] eta: 0:05:15 lr: 0.000096 grad: 0.0835 (0.0849) loss: 0.8429 (0.8568) time: 0.1190 data: 0.0423 max mem: 8255 +Train: [35] [4100/6250] eta: 0:05:01 lr: 0.000096 grad: 0.0857 (0.0850) loss: 0.8580 (0.8567) time: 0.1182 data: 0.0419 max mem: 8255 +Train: [35] [4200/6250] eta: 0:04:47 lr: 0.000096 grad: 0.0824 (0.0851) loss: 0.8522 (0.8566) time: 0.1633 data: 0.0934 max mem: 8255 +Train: [35] [4300/6250] eta: 0:04:32 lr: 0.000095 grad: 0.0806 (0.0851) loss: 0.8577 (0.8565) time: 0.1355 data: 0.0686 max mem: 8255 +Train: [35] [4400/6250] eta: 0:04:19 lr: 0.000095 grad: 0.0815 (0.0851) loss: 0.8592 (0.8564) time: 0.1225 data: 0.0515 max mem: 8255 +Train: [35] [4500/6250] eta: 0:04:05 lr: 0.000095 grad: 0.0807 (0.0851) loss: 0.8562 (0.8563) time: 0.1322 data: 0.0643 max mem: 8255 +Train: [35] [4600/6250] eta: 0:03:50 lr: 0.000095 grad: 0.0800 (0.0851) loss: 0.8526 (0.8563) time: 0.1195 data: 0.0448 max mem: 8255 +Train: [35] [4700/6250] eta: 0:03:36 lr: 0.000095 grad: 0.0787 (0.0851) loss: 0.8533 (0.8563) time: 0.1299 data: 0.0590 max mem: 8255 +Train: [35] [4800/6250] eta: 0:03:22 lr: 0.000095 grad: 0.0813 (0.0851) loss: 0.8555 (0.8562) time: 0.1383 data: 0.0726 max mem: 8255 +Train: [35] [4900/6250] eta: 0:03:07 lr: 0.000095 grad: 0.0820 (0.0850) loss: 0.8646 (0.8563) time: 0.1155 data: 0.0378 max mem: 8255 +Train: [35] [5000/6250] eta: 0:02:53 lr: 0.000095 grad: 0.0829 (0.0850) loss: 0.8464 (0.8562) time: 0.1225 data: 0.0570 max mem: 8255 +Train: [35] [5100/6250] eta: 0:02:39 lr: 0.000095 grad: 0.0782 (0.0850) loss: 0.8542 (0.8562) time: 0.1382 data: 0.0664 max mem: 8255 +Train: [35] [5200/6250] eta: 0:02:25 lr: 0.000095 grad: 0.0796 (0.0849) loss: 0.8563 (0.8563) time: 0.1281 data: 0.0613 max mem: 8255 +Train: [35] [5300/6250] eta: 0:02:11 lr: 0.000095 grad: 0.0828 (0.0849) loss: 0.8576 (0.8563) time: 0.1462 data: 0.0637 max mem: 8255 +Train: [35] [5400/6250] eta: 0:01:57 lr: 0.000095 grad: 0.0777 (0.0849) loss: 0.8539 (0.8562) time: 0.1444 data: 0.0718 max mem: 8255 +Train: [35] [5500/6250] eta: 0:01:43 lr: 0.000095 grad: 0.0790 (0.0849) loss: 0.8544 (0.8562) time: 0.1555 data: 0.0779 max mem: 8255 +Train: [35] [5600/6250] eta: 0:01:30 lr: 0.000095 grad: 0.0800 (0.0848) loss: 0.8463 (0.8562) time: 0.1310 data: 0.0562 max mem: 8255 +Train: [35] [5700/6250] eta: 0:01:16 lr: 0.000095 grad: 0.0794 (0.0848) loss: 0.8592 (0.8562) time: 0.1344 data: 0.0634 max mem: 8255 +Train: [35] [5800/6250] eta: 0:01:02 lr: 0.000095 grad: 0.0776 (0.0848) loss: 0.8594 (0.8563) time: 0.1293 data: 0.0554 max mem: 8255 +Train: [35] [5900/6250] eta: 0:00:48 lr: 0.000095 grad: 0.0811 (0.0847) loss: 0.8518 (0.8563) time: 0.1182 data: 0.0463 max mem: 8255 +Train: [35] [6000/6250] eta: 0:00:34 lr: 0.000095 grad: 0.0771 (0.0847) loss: 0.8603 (0.8564) time: 0.1219 data: 0.0477 max mem: 8255 +Train: [35] [6100/6250] eta: 0:00:20 lr: 0.000095 grad: 0.0828 (0.0847) loss: 0.8505 (0.8564) time: 0.1214 data: 0.0533 max mem: 8255 +Train: [35] [6200/6250] eta: 0:00:06 lr: 0.000095 grad: 0.0792 (0.0846) loss: 0.8631 (0.8564) time: 0.1615 data: 0.0966 max mem: 8255 +Train: [35] [6249/6250] eta: 0:00:00 lr: 0.000095 grad: 0.0808 (0.0846) loss: 0.8589 (0.8564) time: 0.1226 data: 0.0511 max mem: 8255 +Train: [35] Total time: 0:14:21 (0.1379 s / it) +Averaged stats: lr: 0.000095 grad: 0.0808 (0.0846) loss: 0.8589 (0.8564) +Eval (hcp-train-subset): [35] [ 0/62] eta: 0:05:35 loss: 0.8908 (0.8908) time: 5.4059 data: 5.3752 max mem: 8255 +Eval (hcp-train-subset): [35] [61/62] eta: 0:00:00 loss: 0.8834 (0.8826) time: 0.1224 data: 0.1013 max mem: 8255 +Eval (hcp-train-subset): [35] Total time: 0:00:13 (0.2143 s / it) +Averaged stats (hcp-train-subset): loss: 0.8834 (0.8826) +Eval (hcp-val): [35] [ 0/62] eta: 0:04:58 loss: 0.8775 (0.8775) time: 4.8087 data: 4.7557 max mem: 8255 +Eval (hcp-val): [35] [61/62] eta: 0:00:00 loss: 0.8810 (0.8820) time: 0.1147 data: 0.0936 max mem: 8255 +Eval (hcp-val): [35] Total time: 0:00:12 (0.2074 s / it) +Averaged stats (hcp-val): loss: 0.8810 (0.8820) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +Train: [36] [ 0/6250] eta: 10:08:14 lr: 0.000095 grad: 0.1635 (0.1635) loss: 0.9260 (0.9260) time: 5.8391 data: 5.7451 max mem: 8255 +Train: [36] [ 100/6250] eta: 0:18:36 lr: 0.000095 grad: 0.0867 (0.0907) loss: 0.8672 (0.8757) time: 0.1256 data: 0.0307 max mem: 8255 +Train: [36] [ 200/6250] eta: 0:15:44 lr: 0.000095 grad: 0.0794 (0.0891) loss: 0.8696 (0.8702) time: 0.1205 data: 0.0415 max mem: 8255 +Train: [36] [ 300/6250] eta: 0:14:23 lr: 0.000095 grad: 0.0815 (0.0877) loss: 0.8678 (0.8691) time: 0.1217 data: 0.0518 max mem: 8255 +Train: [36] [ 400/6250] eta: 0:13:30 lr: 0.000095 grad: 0.0765 (0.0860) loss: 0.8628 (0.8684) time: 0.1308 data: 0.0510 max mem: 8255 +Train: [36] [ 500/6250] eta: 0:12:50 lr: 0.000095 grad: 0.0762 (0.0853) loss: 0.8599 (0.8672) time: 0.1198 data: 0.0360 max mem: 8255 +Train: [36] [ 600/6250] eta: 0:12:24 lr: 0.000095 grad: 0.0836 (0.0851) loss: 0.8522 (0.8657) time: 0.1154 data: 0.0365 max mem: 8255 +Train: [36] [ 700/6250] eta: 0:12:01 lr: 0.000095 grad: 0.0814 (0.0852) loss: 0.8517 (0.8646) time: 0.1268 data: 0.0499 max mem: 8255 +Train: [36] [ 800/6250] eta: 0:11:53 lr: 0.000095 grad: 0.0817 (0.0850) loss: 0.8595 (0.8635) time: 0.1174 data: 0.0444 max mem: 8255 +Train: [36] [ 900/6250] eta: 0:11:48 lr: 0.000095 grad: 0.0804 (0.0847) loss: 0.8557 (0.8631) time: 0.1473 data: 0.0769 max mem: 8255 +Train: [36] [1000/6250] eta: 0:11:37 lr: 0.000095 grad: 0.0799 (0.0845) loss: 0.8576 (0.8626) time: 0.1511 data: 0.0276 max mem: 8255 +Train: [36] [1100/6250] eta: 0:11:27 lr: 0.000095 grad: 0.0825 (0.0842) loss: 0.8622 (0.8621) time: 0.1355 data: 0.0557 max mem: 8255 +Train: [36] [1200/6250] eta: 0:11:18 lr: 0.000095 grad: 0.0817 (0.0842) loss: 0.8548 (0.8616) time: 0.1412 data: 0.0763 max mem: 8255 +Train: [36] [1300/6250] eta: 0:11:08 lr: 0.000095 grad: 0.0774 (0.0840) loss: 0.8567 (0.8611) time: 0.1577 data: 0.0838 max mem: 8255 +Train: [36] [1400/6250] eta: 0:11:05 lr: 0.000095 grad: 0.0806 (0.0839) loss: 0.8510 (0.8607) time: 0.0947 data: 0.0002 max mem: 8255 +Train: [36] [1500/6250] eta: 0:10:46 lr: 0.000095 grad: 0.0811 (0.0839) loss: 0.8547 (0.8602) time: 0.1111 data: 0.0375 max mem: 8255 +Train: [36] [1600/6250] eta: 0:10:31 lr: 0.000094 grad: 0.0777 (0.0838) loss: 0.8467 (0.8598) time: 0.1175 data: 0.0429 max mem: 8255 +Train: [36] [1700/6250] eta: 0:10:15 lr: 0.000094 grad: 0.0766 (0.0839) loss: 0.8548 (0.8594) time: 0.1168 data: 0.0420 max mem: 8255 +Train: [36] [1800/6250] eta: 0:09:59 lr: 0.000094 grad: 0.0807 (0.0841) loss: 0.8466 (0.8589) time: 0.1265 data: 0.0567 max mem: 8255 +Train: [36] [1900/6250] eta: 0:09:43 lr: 0.000094 grad: 0.0769 (0.0841) loss: 0.8565 (0.8585) time: 0.1246 data: 0.0565 max mem: 8255 +Train: [36] [2000/6250] eta: 0:09:29 lr: 0.000094 grad: 0.0849 (0.0842) loss: 0.8595 (0.8582) time: 0.1517 data: 0.0872 max mem: 8255 +Train: [36] [2100/6250] eta: 0:09:14 lr: 0.000094 grad: 0.0882 (0.0841) loss: 0.8523 (0.8580) time: 0.1142 data: 0.0402 max mem: 8255 +Train: [36] [2200/6250] eta: 0:09:00 lr: 0.000094 grad: 0.0870 (0.0842) loss: 0.8478 (0.8577) time: 0.1366 data: 0.0721 max mem: 8255 +Train: [36] [2300/6250] eta: 0:08:46 lr: 0.000094 grad: 0.0838 (0.0841) loss: 0.8501 (0.8574) time: 0.1276 data: 0.0603 max mem: 8255 +Train: [36] [2400/6250] eta: 0:08:32 lr: 0.000094 grad: 0.0865 (0.0841) loss: 0.8600 (0.8573) time: 0.1318 data: 0.0657 max mem: 8255 +Train: [36] [2500/6250] eta: 0:08:19 lr: 0.000094 grad: 0.0854 (0.0842) loss: 0.8491 (0.8571) time: 0.1238 data: 0.0600 max mem: 8255 +Train: [36] [2600/6250] eta: 0:08:06 lr: 0.000094 grad: 0.0823 (0.0843) loss: 0.8480 (0.8569) time: 0.1280 data: 0.0553 max mem: 8255 +Train: [36] [2700/6250] eta: 0:07:52 lr: 0.000094 grad: 0.0875 (0.0845) loss: 0.8543 (0.8568) time: 0.1360 data: 0.0694 max mem: 8255 +Train: [36] [2800/6250] eta: 0:07:39 lr: 0.000094 grad: 0.0843 (0.0845) loss: 0.8532 (0.8566) time: 0.1304 data: 0.0589 max mem: 8255 +Train: [36] [2900/6250] eta: 0:07:26 lr: 0.000094 grad: 0.0817 (0.0845) loss: 0.8554 (0.8565) time: 0.1307 data: 0.0549 max mem: 8255 +Train: [36] [3000/6250] eta: 0:07:12 lr: 0.000094 grad: 0.0824 (0.0845) loss: 0.8490 (0.8563) time: 0.1235 data: 0.0498 max mem: 8255 +Train: [36] [3100/6250] eta: 0:06:58 lr: 0.000094 grad: 0.0841 (0.0846) loss: 0.8566 (0.8563) time: 0.1306 data: 0.0583 max mem: 8255 +Train: [36] [3200/6250] eta: 0:06:46 lr: 0.000094 grad: 0.0831 (0.0846) loss: 0.8519 (0.8562) time: 0.1309 data: 0.0631 max mem: 8255 +Train: [36] [3300/6250] eta: 0:06:33 lr: 0.000094 grad: 0.0837 (0.0847) loss: 0.8506 (0.8561) time: 0.1407 data: 0.0705 max mem: 8255 +Train: [36] [3400/6250] eta: 0:06:20 lr: 0.000094 grad: 0.0849 (0.0848) loss: 0.8477 (0.8560) time: 0.1484 data: 0.0794 max mem: 8255 +Train: [36] [3500/6250] eta: 0:06:07 lr: 0.000094 grad: 0.0867 (0.0848) loss: 0.8550 (0.8560) time: 0.1287 data: 0.0644 max mem: 8255 +Train: [36] [3600/6250] eta: 0:05:54 lr: 0.000094 grad: 0.0800 (0.0848) loss: 0.8533 (0.8560) time: 0.1647 data: 0.0808 max mem: 8255 +Train: [36] [3700/6250] eta: 0:05:42 lr: 0.000094 grad: 0.0816 (0.0848) loss: 0.8598 (0.8559) time: 0.1682 data: 0.0945 max mem: 8255 +Train: [36] [3800/6250] eta: 0:05:28 lr: 0.000094 grad: 0.0823 (0.0848) loss: 0.8556 (0.8559) time: 0.1242 data: 0.0562 max mem: 8255 +Train: [36] [3900/6250] eta: 0:05:14 lr: 0.000094 grad: 0.0810 (0.0849) loss: 0.8606 (0.8559) time: 0.1406 data: 0.0678 max mem: 8255 +Train: [36] [4000/6250] eta: 0:05:00 lr: 0.000094 grad: 0.0873 (0.0851) loss: 0.8598 (0.8559) time: 0.1240 data: 0.0501 max mem: 8255 +Train: [36] [4100/6250] eta: 0:04:47 lr: 0.000094 grad: 0.0800 (0.0851) loss: 0.8548 (0.8559) time: 0.1384 data: 0.0671 max mem: 8255 +Train: [36] [4200/6250] eta: 0:04:33 lr: 0.000094 grad: 0.0839 (0.0853) loss: 0.8551 (0.8559) time: 0.1154 data: 0.0337 max mem: 8255 +Train: [36] [4300/6250] eta: 0:04:19 lr: 0.000094 grad: 0.0821 (0.0853) loss: 0.8531 (0.8559) time: 0.1171 data: 0.0472 max mem: 8255 +Train: [36] [4400/6250] eta: 0:04:06 lr: 0.000094 grad: 0.0787 (0.0853) loss: 0.8545 (0.8559) time: 0.1348 data: 0.0663 max mem: 8255 +Train: [36] [4500/6250] eta: 0:03:52 lr: 0.000094 grad: 0.0862 (0.0853) loss: 0.8497 (0.8558) time: 0.1274 data: 0.0583 max mem: 8255 +Train: [36] [4600/6250] eta: 0:03:39 lr: 0.000094 grad: 0.0809 (0.0854) loss: 0.8461 (0.8558) time: 0.1374 data: 0.0713 max mem: 8255 +Train: [36] [4700/6250] eta: 0:03:26 lr: 0.000094 grad: 0.0855 (0.0855) loss: 0.8510 (0.8558) time: 0.0970 data: 0.0257 max mem: 8255 +Train: [36] [4800/6250] eta: 0:03:13 lr: 0.000094 grad: 0.0877 (0.0855) loss: 0.8517 (0.8557) time: 0.1278 data: 0.0596 max mem: 8255 +Train: [36] [4900/6250] eta: 0:02:59 lr: 0.000094 grad: 0.0882 (0.0855) loss: 0.8525 (0.8557) time: 0.1377 data: 0.0724 max mem: 8255 +Train: [36] [5000/6250] eta: 0:02:46 lr: 0.000094 grad: 0.0862 (0.0855) loss: 0.8576 (0.8557) time: 0.1204 data: 0.0522 max mem: 8255 +Train: [36] [5100/6250] eta: 0:02:32 lr: 0.000093 grad: 0.0837 (0.0855) loss: 0.8541 (0.8557) time: 0.1474 data: 0.0719 max mem: 8255 +Train: [36] [5200/6250] eta: 0:02:19 lr: 0.000093 grad: 0.0917 (0.0857) loss: 0.8394 (0.8556) time: 0.1621 data: 0.0947 max mem: 8255 +Train: [36] [5300/6250] eta: 0:02:06 lr: 0.000093 grad: 0.0896 (0.0857) loss: 0.8570 (0.8556) time: 0.1318 data: 0.0658 max mem: 8255 +Train: [36] [5400/6250] eta: 0:01:53 lr: 0.000093 grad: 0.0824 (0.0857) loss: 0.8524 (0.8556) time: 0.1588 data: 0.0940 max mem: 8255 +Train: [36] [5500/6250] eta: 0:01:40 lr: 0.000093 grad: 0.0856 (0.0857) loss: 0.8520 (0.8556) time: 0.1542 data: 0.0768 max mem: 8255 +Train: [36] [5600/6250] eta: 0:01:27 lr: 0.000093 grad: 0.0848 (0.0857) loss: 0.8483 (0.8556) time: 0.1424 data: 0.0730 max mem: 8255 +Train: [36] [5700/6250] eta: 0:01:13 lr: 0.000093 grad: 0.0859 (0.0858) loss: 0.8591 (0.8556) time: 0.1534 data: 0.0819 max mem: 8255 +Train: [36] [5800/6250] eta: 0:01:00 lr: 0.000093 grad: 0.0766 (0.0858) loss: 0.8611 (0.8556) time: 0.1423 data: 0.0737 max mem: 8255 +Train: [36] [5900/6250] eta: 0:00:47 lr: 0.000093 grad: 0.0879 (0.0859) loss: 0.8554 (0.8556) time: 0.1366 data: 0.0693 max mem: 8255 +Train: [36] [6000/6250] eta: 0:00:33 lr: 0.000093 grad: 0.0836 (0.0859) loss: 0.8613 (0.8555) time: 0.1222 data: 0.0376 max mem: 8255 +Train: [36] [6100/6250] eta: 0:00:20 lr: 0.000093 grad: 0.0893 (0.0860) loss: 0.8536 (0.8555) time: 0.1088 data: 0.0390 max mem: 8255 +Train: [36] [6200/6250] eta: 0:00:06 lr: 0.000093 grad: 0.0887 (0.0861) loss: 0.8499 (0.8554) time: 0.1246 data: 0.0538 max mem: 8255 +Train: [36] [6249/6250] eta: 0:00:00 lr: 0.000093 grad: 0.0867 (0.0861) loss: 0.8555 (0.8554) time: 0.1083 data: 0.0373 max mem: 8255 +Train: [36] Total time: 0:14:03 (0.1349 s / it) +Averaged stats: lr: 0.000093 grad: 0.0867 (0.0861) loss: 0.8555 (0.8554) +Eval (hcp-train-subset): [36] [ 0/62] eta: 0:03:07 loss: 0.8866 (0.8866) time: 3.0231 data: 2.9269 max mem: 8255 +Eval (hcp-train-subset): [36] [61/62] eta: 0:00:00 loss: 0.8812 (0.8804) time: 0.1125 data: 0.0915 max mem: 8255 +Eval (hcp-train-subset): [36] Total time: 0:00:13 (0.2137 s / it) +Averaged stats (hcp-train-subset): loss: 0.8812 (0.8804) +Eval (hcp-val): [36] [ 0/62] eta: 0:03:23 loss: 0.8768 (0.8768) time: 3.2884 data: 3.1954 max mem: 8255 +Eval (hcp-val): [36] [61/62] eta: 0:00:00 loss: 0.8802 (0.8815) time: 0.1264 data: 0.1042 max mem: 8255 +Eval (hcp-val): [36] Total time: 0:00:13 (0.2115 s / it) +Averaged stats (hcp-val): loss: 0.8802 (0.8815) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +Train: [37] [ 0/6250] eta: 8:23:52 lr: 0.000093 grad: 0.0759 (0.0759) loss: 0.8839 (0.8839) time: 4.8372 data: 4.6688 max mem: 8255 +Train: [37] [ 100/6250] eta: 0:18:03 lr: 0.000093 grad: 0.0883 (0.1119) loss: 0.8779 (0.8689) time: 0.1310 data: 0.0291 max mem: 8255 +Train: [37] [ 200/6250] eta: 0:15:01 lr: 0.000093 grad: 0.0829 (0.1077) loss: 0.8621 (0.8630) time: 0.1214 data: 0.0360 max mem: 8255 +Train: [37] [ 300/6250] eta: 0:13:43 lr: 0.000093 grad: 0.0861 (0.1029) loss: 0.8530 (0.8604) time: 0.1125 data: 0.0359 max mem: 8255 +Train: [37] [ 400/6250] eta: 0:13:01 lr: 0.000093 grad: 0.0785 (0.0982) loss: 0.8681 (0.8603) time: 0.1135 data: 0.0476 max mem: 8255 +Train: [37] [ 500/6250] eta: 0:12:27 lr: 0.000093 grad: 0.0830 (0.0948) loss: 0.8556 (0.8598) time: 0.0988 data: 0.0154 max mem: 8255 +Train: [37] [ 600/6250] eta: 0:12:05 lr: 0.000093 grad: 0.0841 (0.0931) loss: 0.8570 (0.8593) time: 0.1264 data: 0.0453 max mem: 8255 +Train: [37] [ 700/6250] eta: 0:11:58 lr: 0.000093 grad: 0.0772 (0.0911) loss: 0.8562 (0.8592) time: 0.1425 data: 0.0664 max mem: 8255 +Train: [37] [ 800/6250] eta: 0:11:50 lr: 0.000093 grad: 0.0805 (0.0904) loss: 0.8554 (0.8591) time: 0.1324 data: 0.0552 max mem: 8255 +Train: [37] [ 900/6250] eta: 0:11:38 lr: 0.000093 grad: 0.0787 (0.0893) loss: 0.8600 (0.8588) time: 0.1473 data: 0.0771 max mem: 8255 +Train: [37] [1000/6250] eta: 0:11:26 lr: 0.000093 grad: 0.0833 (0.0888) loss: 0.8610 (0.8588) time: 0.1516 data: 0.0766 max mem: 8255 +Train: [37] [1100/6250] eta: 0:11:15 lr: 0.000093 grad: 0.0825 (0.0883) loss: 0.8557 (0.8585) time: 0.1569 data: 0.0841 max mem: 8255 +Train: [37] [1200/6250] eta: 0:10:58 lr: 0.000093 grad: 0.0812 (0.0880) loss: 0.8557 (0.8581) time: 0.1129 data: 0.0437 max mem: 8255 +Train: [37] [1300/6250] eta: 0:10:43 lr: 0.000093 grad: 0.0789 (0.0877) loss: 0.8505 (0.8575) time: 0.1287 data: 0.0638 max mem: 8255 +Train: [37] [1400/6250] eta: 0:10:32 lr: 0.000093 grad: 0.0831 (0.0875) loss: 0.8534 (0.8571) time: 0.1264 data: 0.0600 max mem: 8255 +Train: [37] [1500/6250] eta: 0:10:22 lr: 0.000093 grad: 0.0816 (0.0875) loss: 0.8515 (0.8565) time: 0.1513 data: 0.0820 max mem: 8255 +Train: [37] [1600/6250] eta: 0:10:10 lr: 0.000093 grad: 0.0844 (0.0874) loss: 0.8393 (0.8560) time: 0.1727 data: 0.1071 max mem: 8255 +Train: [37] [1700/6250] eta: 0:09:57 lr: 0.000093 grad: 0.0818 (0.0873) loss: 0.8513 (0.8559) time: 0.1267 data: 0.0564 max mem: 8255 +Train: [37] [1800/6250] eta: 0:09:47 lr: 0.000093 grad: 0.0844 (0.0874) loss: 0.8529 (0.8556) time: 0.1519 data: 0.0832 max mem: 8255 +Train: [37] [1900/6250] eta: 0:09:35 lr: 0.000093 grad: 0.0845 (0.0876) loss: 0.8570 (0.8554) time: 0.1460 data: 0.0703 max mem: 8255 +Train: [37] [2000/6250] eta: 0:09:22 lr: 0.000093 grad: 0.0885 (0.0875) loss: 0.8572 (0.8553) time: 0.1459 data: 0.0774 max mem: 8255 +Train: [37] [2100/6250] eta: 0:09:08 lr: 0.000093 grad: 0.0817 (0.0874) loss: 0.8555 (0.8552) time: 0.1195 data: 0.0535 max mem: 8255 +Train: [37] [2200/6250] eta: 0:08:55 lr: 0.000093 grad: 0.0880 (0.0874) loss: 0.8545 (0.8552) time: 0.1331 data: 0.0634 max mem: 8255 +Train: [37] [2300/6250] eta: 0:08:44 lr: 0.000092 grad: 0.0851 (0.0874) loss: 0.8508 (0.8551) time: 0.1534 data: 0.0659 max mem: 8255 +Train: [37] [2400/6250] eta: 0:08:32 lr: 0.000092 grad: 0.0821 (0.0873) loss: 0.8571 (0.8551) time: 0.1346 data: 0.0594 max mem: 8255 +Train: [37] [2500/6250] eta: 0:08:19 lr: 0.000092 grad: 0.0775 (0.0872) loss: 0.8572 (0.8552) time: 0.1374 data: 0.0704 max mem: 8255 +Train: [37] [2600/6250] eta: 0:08:08 lr: 0.000092 grad: 0.0843 (0.0871) loss: 0.8528 (0.8551) time: 0.1300 data: 0.0479 max mem: 8255 +Train: [37] [2700/6250] eta: 0:07:55 lr: 0.000092 grad: 0.0823 (0.0870) loss: 0.8576 (0.8551) time: 0.1386 data: 0.0678 max mem: 8255 +Train: [37] [2800/6250] eta: 0:07:43 lr: 0.000092 grad: 0.0874 (0.0871) loss: 0.8574 (0.8551) time: 0.1718 data: 0.0668 max mem: 8255 +Train: [37] [2900/6250] eta: 0:07:30 lr: 0.000092 grad: 0.0851 (0.0872) loss: 0.8535 (0.8551) time: 0.1129 data: 0.0399 max mem: 8255 +Train: [37] [3000/6250] eta: 0:07:18 lr: 0.000092 grad: 0.0837 (0.0871) loss: 0.8571 (0.8551) time: 0.1019 data: 0.0247 max mem: 8255 +Train: [37] [3100/6250] eta: 0:07:03 lr: 0.000092 grad: 0.0874 (0.0872) loss: 0.8543 (0.8551) time: 0.1269 data: 0.0573 max mem: 8255 +Train: [37] [3200/6250] eta: 0:06:50 lr: 0.000092 grad: 0.0888 (0.0873) loss: 0.8497 (0.8551) time: 0.1326 data: 0.0649 max mem: 8255 +Train: [37] [3300/6250] eta: 0:06:36 lr: 0.000092 grad: 0.0827 (0.0873) loss: 0.8580 (0.8551) time: 0.1238 data: 0.0540 max mem: 8255 +Train: [37] [3400/6250] eta: 0:06:22 lr: 0.000092 grad: 0.0831 (0.0873) loss: 0.8564 (0.8552) time: 0.1254 data: 0.0588 max mem: 8255 +Train: [37] [3500/6250] eta: 0:06:08 lr: 0.000092 grad: 0.0852 (0.0873) loss: 0.8561 (0.8552) time: 0.1295 data: 0.0573 max mem: 8255 +Train: [37] [3600/6250] eta: 0:05:55 lr: 0.000092 grad: 0.0826 (0.0872) loss: 0.8538 (0.8552) time: 0.1161 data: 0.0412 max mem: 8255 +Train: [37] [3700/6250] eta: 0:05:42 lr: 0.000092 grad: 0.0786 (0.0871) loss: 0.8571 (0.8552) time: 0.1367 data: 0.0706 max mem: 8255 +Train: [37] [3800/6250] eta: 0:05:28 lr: 0.000092 grad: 0.0831 (0.0870) loss: 0.8594 (0.8553) time: 0.1211 data: 0.0454 max mem: 8255 +Train: [37] [3900/6250] eta: 0:05:14 lr: 0.000092 grad: 0.0900 (0.0871) loss: 0.8538 (0.8554) time: 0.1230 data: 0.0532 max mem: 8255 +Train: [37] [4000/6250] eta: 0:05:00 lr: 0.000092 grad: 0.0846 (0.0870) loss: 0.8637 (0.8555) time: 0.1454 data: 0.0753 max mem: 8255 +Train: [37] [4100/6250] eta: 0:04:47 lr: 0.000092 grad: 0.0804 (0.0869) loss: 0.8634 (0.8556) time: 0.1456 data: 0.0787 max mem: 8255 +Train: [37] [4200/6250] eta: 0:04:34 lr: 0.000092 grad: 0.0850 (0.0869) loss: 0.8577 (0.8556) time: 0.1309 data: 0.0627 max mem: 8255 +Train: [37] [4300/6250] eta: 0:04:21 lr: 0.000092 grad: 0.0858 (0.0869) loss: 0.8610 (0.8557) time: 0.1647 data: 0.0986 max mem: 8255 +Train: [37] [4400/6250] eta: 0:04:07 lr: 0.000092 grad: 0.0825 (0.0868) loss: 0.8624 (0.8558) time: 0.1449 data: 0.0796 max mem: 8255 +Train: [37] [4500/6250] eta: 0:03:54 lr: 0.000092 grad: 0.0872 (0.0867) loss: 0.8542 (0.8558) time: 0.1457 data: 0.0775 max mem: 8255 +Train: [37] [4600/6250] eta: 0:03:41 lr: 0.000092 grad: 0.0812 (0.0867) loss: 0.8591 (0.8559) time: 0.1039 data: 0.0249 max mem: 8255 +Train: [37] [4700/6250] eta: 0:03:28 lr: 0.000092 grad: 0.0828 (0.0867) loss: 0.8613 (0.8559) time: 0.1511 data: 0.0826 max mem: 8255 +Train: [37] [4800/6250] eta: 0:03:15 lr: 0.000092 grad: 0.0867 (0.0867) loss: 0.8577 (0.8559) time: 0.1771 data: 0.1034 max mem: 8255 +Train: [37] [4900/6250] eta: 0:03:02 lr: 0.000092 grad: 0.0811 (0.0867) loss: 0.8588 (0.8559) time: 0.1445 data: 0.0734 max mem: 8255 +Train: [37] [5000/6250] eta: 0:02:48 lr: 0.000092 grad: 0.0862 (0.0868) loss: 0.8595 (0.8558) time: 0.1330 data: 0.0605 max mem: 8255 +Train: [37] [5100/6250] eta: 0:02:35 lr: 0.000092 grad: 0.0886 (0.0868) loss: 0.8553 (0.8558) time: 0.1421 data: 0.0768 max mem: 8255 +Train: [37] [5200/6250] eta: 0:02:21 lr: 0.000092 grad: 0.0865 (0.0868) loss: 0.8488 (0.8557) time: 0.1284 data: 0.0529 max mem: 8255 +Train: [37] [5300/6250] eta: 0:02:08 lr: 0.000092 grad: 0.0843 (0.0868) loss: 0.8528 (0.8556) time: 0.1014 data: 0.0309 max mem: 8255 +Train: [37] [5400/6250] eta: 0:01:54 lr: 0.000092 grad: 0.0843 (0.0869) loss: 0.8498 (0.8556) time: 0.0978 data: 0.0168 max mem: 8255 +Train: [37] [5500/6250] eta: 0:01:41 lr: 0.000092 grad: 0.0793 (0.0869) loss: 0.8524 (0.8556) time: 0.1798 data: 0.1111 max mem: 8255 +Train: [37] [5600/6250] eta: 0:01:27 lr: 0.000092 grad: 0.0840 (0.0869) loss: 0.8530 (0.8556) time: 0.2224 data: 0.1637 max mem: 8255 +Train: [37] [5700/6250] eta: 0:01:14 lr: 0.000091 grad: 0.0802 (0.0869) loss: 0.8605 (0.8556) time: 0.1261 data: 0.0586 max mem: 8255 +Train: [37] [5800/6250] eta: 0:01:01 lr: 0.000091 grad: 0.0826 (0.0868) loss: 0.8568 (0.8556) time: 0.1379 data: 0.0693 max mem: 8255 +Train: [37] [5900/6250] eta: 0:00:47 lr: 0.000091 grad: 0.0848 (0.0869) loss: 0.8526 (0.8556) time: 0.1418 data: 0.0746 max mem: 8255 +Train: [37] [6000/6250] eta: 0:00:33 lr: 0.000091 grad: 0.0908 (0.0869) loss: 0.8548 (0.8555) time: 0.1267 data: 0.0513 max mem: 8255 +Train: [37] [6100/6250] eta: 0:00:20 lr: 0.000091 grad: 0.0845 (0.0868) loss: 0.8497 (0.8555) time: 0.1156 data: 0.0373 max mem: 8255 +Train: [37] [6200/6250] eta: 0:00:06 lr: 0.000091 grad: 0.0927 (0.0869) loss: 0.8418 (0.8554) time: 0.1248 data: 0.0504 max mem: 8255 +Train: [37] [6249/6250] eta: 0:00:00 lr: 0.000091 grad: 0.0951 (0.0870) loss: 0.8517 (0.8554) time: 0.1364 data: 0.0573 max mem: 8255 +Train: [37] Total time: 0:14:11 (0.1363 s / it) +Averaged stats: lr: 0.000091 grad: 0.0951 (0.0870) loss: 0.8517 (0.8554) +Eval (hcp-train-subset): [37] [ 0/62] eta: 0:04:32 loss: 0.8909 (0.8909) time: 4.3945 data: 4.3629 max mem: 8255 +Eval (hcp-train-subset): [37] [61/62] eta: 0:00:00 loss: 0.8818 (0.8823) time: 0.1190 data: 0.0971 max mem: 8255 +Eval (hcp-train-subset): [37] Total time: 0:00:13 (0.2100 s / it) +Averaged stats (hcp-train-subset): loss: 0.8818 (0.8823) +Eval (hcp-val): [37] [ 0/62] eta: 0:04:30 loss: 0.8794 (0.8794) time: 4.3649 data: 4.3075 max mem: 8255 +Eval (hcp-val): [37] [61/62] eta: 0:00:00 loss: 0.8819 (0.8821) time: 0.1168 data: 0.0962 max mem: 8255 +Eval (hcp-val): [37] Total time: 0:00:12 (0.2015 s / it) +Averaged stats (hcp-val): loss: 0.8819 (0.8821) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +Train: [38] [ 0/6250] eta: 7:24:34 lr: 0.000091 grad: 0.0815 (0.0815) loss: 0.9087 (0.9087) time: 4.2679 data: 4.0269 max mem: 8255 +Train: [38] [ 100/6250] eta: 0:20:24 lr: 0.000091 grad: 0.0987 (0.1175) loss: 0.8590 (0.8707) time: 0.1581 data: 0.0734 max mem: 8255 +Train: [38] [ 200/6250] eta: 0:17:02 lr: 0.000091 grad: 0.0887 (0.1134) loss: 0.8555 (0.8623) time: 0.1172 data: 0.0327 max mem: 8255 +Train: [38] [ 300/6250] eta: 0:15:55 lr: 0.000091 grad: 0.0786 (0.1059) loss: 0.8581 (0.8609) time: 0.1373 data: 0.0469 max mem: 8255 +Train: [38] [ 400/6250] eta: 0:14:51 lr: 0.000091 grad: 0.0769 (0.1013) loss: 0.8615 (0.8610) time: 0.1222 data: 0.0432 max mem: 8255 +Train: [38] [ 500/6250] eta: 0:14:21 lr: 0.000091 grad: 0.0752 (0.0980) loss: 0.8649 (0.8610) time: 0.1299 data: 0.0546 max mem: 8255 +Train: [38] [ 600/6250] eta: 0:14:08 lr: 0.000091 grad: 0.0799 (0.0960) loss: 0.8555 (0.8606) time: 0.1537 data: 0.0782 max mem: 8255 +Train: [38] [ 700/6250] eta: 0:13:48 lr: 0.000091 grad: 0.0868 (0.0945) loss: 0.8554 (0.8602) time: 0.1466 data: 0.0730 max mem: 8255 +Train: [38] [ 800/6250] eta: 0:13:44 lr: 0.000091 grad: 0.0867 (0.0933) loss: 0.8484 (0.8597) time: 0.1493 data: 0.0707 max mem: 8255 +Train: [38] [ 900/6250] eta: 0:13:39 lr: 0.000091 grad: 0.0856 (0.0923) loss: 0.8498 (0.8591) time: 0.1555 data: 0.0834 max mem: 8255 +Train: [38] [1000/6250] eta: 0:13:35 lr: 0.000091 grad: 0.0878 (0.0915) loss: 0.8533 (0.8587) time: 0.1884 data: 0.1224 max mem: 8255 +Train: [38] [1100/6250] eta: 0:13:24 lr: 0.000091 grad: 0.0855 (0.0908) loss: 0.8472 (0.8585) time: 0.1659 data: 0.0936 max mem: 8255 +Train: [38] [1200/6250] eta: 0:13:11 lr: 0.000091 grad: 0.0805 (0.0903) loss: 0.8567 (0.8583) time: 0.1639 data: 0.0902 max mem: 8255 +Train: [38] [1300/6250] eta: 0:12:58 lr: 0.000091 grad: 0.0838 (0.0899) loss: 0.8435 (0.8579) time: 0.1595 data: 0.0846 max mem: 8255 +Train: [38] [1400/6250] eta: 0:12:45 lr: 0.000091 grad: 0.0797 (0.0895) loss: 0.8528 (0.8575) time: 0.1566 data: 0.0894 max mem: 8255 +Train: [38] [1500/6250] eta: 0:12:28 lr: 0.000091 grad: 0.0816 (0.0892) loss: 0.8503 (0.8572) time: 0.1449 data: 0.0757 max mem: 8255 +Train: [38] [1600/6250] eta: 0:12:07 lr: 0.000091 grad: 0.0827 (0.0889) loss: 0.8533 (0.8570) time: 0.1401 data: 0.0715 max mem: 8255 +Train: [38] [1700/6250] eta: 0:11:44 lr: 0.000091 grad: 0.0815 (0.0887) loss: 0.8480 (0.8566) time: 0.1338 data: 0.0606 max mem: 8255 +Train: [38] [1800/6250] eta: 0:11:26 lr: 0.000091 grad: 0.0864 (0.0885) loss: 0.8567 (0.8564) time: 0.1180 data: 0.0372 max mem: 8255 +Train: [38] [1900/6250] eta: 0:11:07 lr: 0.000091 grad: 0.0845 (0.0884) loss: 0.8479 (0.8562) time: 0.1398 data: 0.0667 max mem: 8255 +Train: [38] [2000/6250] eta: 0:10:55 lr: 0.000091 grad: 0.0791 (0.0881) loss: 0.8542 (0.8561) time: 0.1411 data: 0.0695 max mem: 8255 +Train: [38] [2100/6250] eta: 0:10:37 lr: 0.000091 grad: 0.0794 (0.0878) loss: 0.8544 (0.8559) time: 0.1651 data: 0.0964 max mem: 8255 +Train: [38] [2200/6250] eta: 0:10:19 lr: 0.000091 grad: 0.0832 (0.0877) loss: 0.8521 (0.8558) time: 0.1190 data: 0.0462 max mem: 8255 +Train: [38] [2300/6250] eta: 0:10:00 lr: 0.000091 grad: 0.0835 (0.0877) loss: 0.8480 (0.8556) time: 0.1490 data: 0.0805 max mem: 8255 +Train: [38] [2400/6250] eta: 0:09:43 lr: 0.000091 grad: 0.0850 (0.0878) loss: 0.8531 (0.8555) time: 0.1655 data: 0.0966 max mem: 8255 +Train: [38] [2500/6250] eta: 0:09:25 lr: 0.000091 grad: 0.0843 (0.0877) loss: 0.8511 (0.8554) time: 0.1219 data: 0.0404 max mem: 8255 +Train: [38] [2600/6250] eta: 0:09:07 lr: 0.000091 grad: 0.0887 (0.0877) loss: 0.8529 (0.8553) time: 0.1154 data: 0.0487 max mem: 8255 +Train: [38] [2700/6250] eta: 0:08:49 lr: 0.000091 grad: 0.0839 (0.0877) loss: 0.8463 (0.8551) time: 0.1292 data: 0.0563 max mem: 8255 +Train: [38] [2800/6250] eta: 0:08:32 lr: 0.000091 grad: 0.0851 (0.0878) loss: 0.8585 (0.8551) time: 0.1324 data: 0.0608 max mem: 8255 +Train: [38] [2900/6250] eta: 0:08:16 lr: 0.000090 grad: 0.0867 (0.0878) loss: 0.8488 (0.8550) time: 0.1152 data: 0.0448 max mem: 8255 +Train: [38] [3000/6250] eta: 0:07:59 lr: 0.000090 grad: 0.0884 (0.0877) loss: 0.8548 (0.8550) time: 0.1298 data: 0.0604 max mem: 8255 +Train: [38] [3100/6250] eta: 0:07:45 lr: 0.000090 grad: 0.0833 (0.0878) loss: 0.8537 (0.8549) time: 0.1656 data: 0.1029 max mem: 8255 +Train: [38] [3200/6250] eta: 0:07:28 lr: 0.000090 grad: 0.0892 (0.0878) loss: 0.8615 (0.8548) time: 0.1190 data: 0.0532 max mem: 8255 +Train: [38] [3300/6250] eta: 0:07:11 lr: 0.000090 grad: 0.0777 (0.0877) loss: 0.8569 (0.8548) time: 0.1138 data: 0.0400 max mem: 8255 +Train: [38] [3400/6250] eta: 0:06:56 lr: 0.000090 grad: 0.0834 (0.0877) loss: 0.8437 (0.8547) time: 0.1395 data: 0.0695 max mem: 8255 +Train: [38] [3500/6250] eta: 0:06:40 lr: 0.000090 grad: 0.0824 (0.0876) loss: 0.8619 (0.8547) time: 0.1274 data: 0.0547 max mem: 8255 +Train: [38] [3600/6250] eta: 0:06:25 lr: 0.000090 grad: 0.0873 (0.0876) loss: 0.8545 (0.8547) time: 0.1442 data: 0.0810 max mem: 8255 +Train: [38] [3700/6250] eta: 0:06:11 lr: 0.000090 grad: 0.0832 (0.0875) loss: 0.8554 (0.8547) time: 0.1311 data: 0.0472 max mem: 8255 +Train: [38] [3800/6250] eta: 0:05:55 lr: 0.000090 grad: 0.0814 (0.0874) loss: 0.8528 (0.8548) time: 0.1322 data: 0.0637 max mem: 8255 +Train: [38] [3900/6250] eta: 0:05:40 lr: 0.000090 grad: 0.0817 (0.0874) loss: 0.8542 (0.8547) time: 0.1361 data: 0.0650 max mem: 8255 +Train: [38] [4000/6250] eta: 0:05:27 lr: 0.000090 grad: 0.0880 (0.0875) loss: 0.8504 (0.8547) time: 0.3048 data: 0.2073 max mem: 8255 +Train: [38] [4100/6250] eta: 0:05:11 lr: 0.000090 grad: 0.0873 (0.0874) loss: 0.8436 (0.8547) time: 0.1208 data: 0.0451 max mem: 8255 +Train: [38] [4200/6250] eta: 0:04:56 lr: 0.000090 grad: 0.0842 (0.0874) loss: 0.8513 (0.8547) time: 0.1325 data: 0.0623 max mem: 8255 +Train: [38] [4300/6250] eta: 0:04:41 lr: 0.000090 grad: 0.0871 (0.0874) loss: 0.8575 (0.8546) time: 0.1307 data: 0.0658 max mem: 8255 +Train: [38] [4400/6250] eta: 0:04:26 lr: 0.000090 grad: 0.0883 (0.0874) loss: 0.8581 (0.8546) time: 0.1469 data: 0.0682 max mem: 8255 +Train: [38] [4500/6250] eta: 0:04:11 lr: 0.000090 grad: 0.0920 (0.0875) loss: 0.8473 (0.8545) time: 0.1323 data: 0.0622 max mem: 8255 +Train: [38] [4600/6250] eta: 0:03:56 lr: 0.000090 grad: 0.0869 (0.0876) loss: 0.8589 (0.8544) time: 0.1251 data: 0.0556 max mem: 8255 +Train: [38] [4700/6250] eta: 0:03:42 lr: 0.000090 grad: 0.0871 (0.0876) loss: 0.8506 (0.8543) time: 0.1521 data: 0.0839 max mem: 8255 +Train: [38] [4800/6250] eta: 0:03:27 lr: 0.000090 grad: 0.0827 (0.0877) loss: 0.8560 (0.8542) time: 0.1451 data: 0.0777 max mem: 8255 +Train: [38] [4900/6250] eta: 0:03:13 lr: 0.000090 grad: 0.0875 (0.0877) loss: 0.8524 (0.8542) time: 0.1311 data: 0.0626 max mem: 8255 +Train: [38] [5000/6250] eta: 0:02:58 lr: 0.000090 grad: 0.0840 (0.0877) loss: 0.8550 (0.8541) time: 0.1522 data: 0.0867 max mem: 8255 +Train: [38] [5100/6250] eta: 0:02:44 lr: 0.000090 grad: 0.0831 (0.0877) loss: 0.8517 (0.8541) time: 0.1227 data: 0.0507 max mem: 8255 +Train: [38] [5200/6250] eta: 0:02:29 lr: 0.000090 grad: 0.0863 (0.0877) loss: 0.8533 (0.8541) time: 0.1217 data: 0.0505 max mem: 8255 +Train: [38] [5300/6250] eta: 0:02:15 lr: 0.000090 grad: 0.0811 (0.0877) loss: 0.8557 (0.8541) time: 0.1310 data: 0.0601 max mem: 8255 +Train: [38] [5400/6250] eta: 0:02:01 lr: 0.000090 grad: 0.0869 (0.0877) loss: 0.8544 (0.8542) time: 0.1287 data: 0.0592 max mem: 8255 +Train: [38] [5500/6250] eta: 0:01:46 lr: 0.000090 grad: 0.0844 (0.0877) loss: 0.8627 (0.8542) time: 0.1439 data: 0.0749 max mem: 8255 +Train: [38] [5600/6250] eta: 0:01:32 lr: 0.000090 grad: 0.0845 (0.0877) loss: 0.8552 (0.8542) time: 0.1285 data: 0.0555 max mem: 8255 +Train: [38] [5700/6250] eta: 0:01:18 lr: 0.000090 grad: 0.0860 (0.0878) loss: 0.8472 (0.8542) time: 0.1456 data: 0.0761 max mem: 8255 +Train: [38] [5800/6250] eta: 0:01:04 lr: 0.000090 grad: 0.0876 (0.0878) loss: 0.8547 (0.8542) time: 0.1648 data: 0.1024 max mem: 8255 +Train: [38] [5900/6250] eta: 0:00:49 lr: 0.000090 grad: 0.0848 (0.0878) loss: 0.8514 (0.8542) time: 0.1451 data: 0.0703 max mem: 8255 +Train: [38] [6000/6250] eta: 0:00:35 lr: 0.000090 grad: 0.0841 (0.0878) loss: 0.8604 (0.8543) time: 0.1262 data: 0.0534 max mem: 8255 +Train: [38] [6100/6250] eta: 0:00:21 lr: 0.000090 grad: 0.0864 (0.0877) loss: 0.8626 (0.8543) time: 0.1424 data: 0.0675 max mem: 8255 +Train: [38] [6200/6250] eta: 0:00:07 lr: 0.000089 grad: 0.0849 (0.0877) loss: 0.8485 (0.8543) time: 0.1466 data: 0.0681 max mem: 8255 +Train: [38] [6249/6250] eta: 0:00:00 lr: 0.000089 grad: 0.0771 (0.0877) loss: 0.8668 (0.8543) time: 0.1590 data: 0.0933 max mem: 8255 +Train: [38] Total time: 0:14:59 (0.1439 s / it) +Averaged stats: lr: 0.000089 grad: 0.0771 (0.0877) loss: 0.8668 (0.8543) +Eval (hcp-train-subset): [38] [ 0/62] eta: 0:05:16 loss: 0.8724 (0.8724) time: 5.1075 data: 5.0817 max mem: 8255 +Eval (hcp-train-subset): [38] [61/62] eta: 0:00:00 loss: 0.8774 (0.8791) time: 0.1453 data: 0.1239 max mem: 8255 +Eval (hcp-train-subset): [38] Total time: 0:00:13 (0.2245 s / it) +Averaged stats (hcp-train-subset): loss: 0.8774 (0.8791) +Eval (hcp-val): [38] [ 0/62] eta: 0:04:07 loss: 0.8743 (0.8743) time: 3.9860 data: 3.8867 max mem: 8255 +Eval (hcp-val): [38] [61/62] eta: 0:00:00 loss: 0.8811 (0.8818) time: 0.1226 data: 0.1006 max mem: 8255 +Eval (hcp-val): [38] Total time: 0:00:13 (0.2152 s / it) +Averaged stats (hcp-val): loss: 0.8811 (0.8818) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +Train: [39] [ 0/6250] eta: 9:04:37 lr: 0.000089 grad: 0.1012 (0.1012) loss: 0.9096 (0.9096) time: 5.2284 data: 5.0954 max mem: 8255 +Train: [39] [ 100/6250] eta: 0:18:19 lr: 0.000089 grad: 0.0870 (0.1069) loss: 0.8587 (0.8723) time: 0.1262 data: 0.0396 max mem: 8255 +Train: [39] [ 200/6250] eta: 0:15:31 lr: 0.000089 grad: 0.0820 (0.0983) loss: 0.8695 (0.8671) time: 0.1329 data: 0.0554 max mem: 8255 +Train: [39] [ 300/6250] eta: 0:14:21 lr: 0.000089 grad: 0.0777 (0.0948) loss: 0.8628 (0.8650) time: 0.1071 data: 0.0277 max mem: 8255 +Train: [39] [ 400/6250] eta: 0:13:26 lr: 0.000089 grad: 0.0820 (0.0916) loss: 0.8656 (0.8645) time: 0.1126 data: 0.0275 max mem: 8255 +Train: [39] [ 500/6250] eta: 0:12:45 lr: 0.000089 grad: 0.0824 (0.0896) loss: 0.8636 (0.8644) time: 0.0915 data: 0.0045 max mem: 8255 +Train: [39] [ 600/6250] eta: 0:12:20 lr: 0.000089 grad: 0.0917 (0.0896) loss: 0.8594 (0.8632) time: 0.1315 data: 0.0505 max mem: 8255 +Train: [39] [ 700/6250] eta: 0:11:53 lr: 0.000089 grad: 0.0798 (0.0887) loss: 0.8633 (0.8628) time: 0.1175 data: 0.0411 max mem: 8255 +Train: [39] [ 800/6250] eta: 0:11:33 lr: 0.000089 grad: 0.0792 (0.0877) loss: 0.8651 (0.8626) time: 0.1244 data: 0.0442 max mem: 8255 +Train: [39] [ 900/6250] eta: 0:11:23 lr: 0.000089 grad: 0.0803 (0.0870) loss: 0.8584 (0.8627) time: 0.1451 data: 0.0670 max mem: 8255 +Train: [39] [1000/6250] eta: 0:11:10 lr: 0.000089 grad: 0.0792 (0.0867) loss: 0.8553 (0.8623) time: 0.1166 data: 0.0469 max mem: 8255 +Train: [39] [1100/6250] eta: 0:11:00 lr: 0.000089 grad: 0.0856 (0.0864) loss: 0.8553 (0.8620) time: 0.1440 data: 0.0674 max mem: 8255 +Train: [39] [1200/6250] eta: 0:10:46 lr: 0.000089 grad: 0.0772 (0.0861) loss: 0.8555 (0.8616) time: 0.1476 data: 0.0761 max mem: 8255 +Train: [39] [1300/6250] eta: 0:10:36 lr: 0.000089 grad: 0.0817 (0.0862) loss: 0.8539 (0.8612) time: 0.1142 data: 0.0414 max mem: 8255 +Train: [39] [1400/6250] eta: 0:10:28 lr: 0.000089 grad: 0.0830 (0.0861) loss: 0.8601 (0.8609) time: 0.1598 data: 0.0538 max mem: 8255 +Train: [39] [1500/6250] eta: 0:10:25 lr: 0.000089 grad: 0.0874 (0.0861) loss: 0.8469 (0.8603) time: 0.1306 data: 0.0582 max mem: 8255 +Train: [39] [1600/6250] eta: 0:10:13 lr: 0.000089 grad: 0.0816 (0.0862) loss: 0.8514 (0.8599) time: 0.1692 data: 0.0948 max mem: 8255 +Train: [39] [1700/6250] eta: 0:09:59 lr: 0.000089 grad: 0.0813 (0.0862) loss: 0.8566 (0.8596) time: 0.1295 data: 0.0560 max mem: 8255 +Train: [39] [1800/6250] eta: 0:09:46 lr: 0.000089 grad: 0.0823 (0.0863) loss: 0.8543 (0.8593) time: 0.1202 data: 0.0463 max mem: 8255 +Train: [39] [1900/6250] eta: 0:09:33 lr: 0.000089 grad: 0.0813 (0.0861) loss: 0.8581 (0.8593) time: 0.1226 data: 0.0504 max mem: 8255 +Train: [39] [2000/6250] eta: 0:09:19 lr: 0.000089 grad: 0.0860 (0.0861) loss: 0.8515 (0.8591) time: 0.1373 data: 0.0706 max mem: 8255 +Train: [39] [2100/6250] eta: 0:09:05 lr: 0.000089 grad: 0.0787 (0.0860) loss: 0.8574 (0.8589) time: 0.1258 data: 0.0533 max mem: 8255 +Train: [39] [2200/6250] eta: 0:08:52 lr: 0.000089 grad: 0.0897 (0.0861) loss: 0.8521 (0.8587) time: 0.1397 data: 0.0627 max mem: 8255 +Train: [39] [2300/6250] eta: 0:08:42 lr: 0.000089 grad: 0.0824 (0.0861) loss: 0.8515 (0.8585) time: 0.2049 data: 0.1391 max mem: 8255 +Train: [39] [2400/6250] eta: 0:08:27 lr: 0.000089 grad: 0.0820 (0.0862) loss: 0.8585 (0.8583) time: 0.1062 data: 0.0344 max mem: 8255 +Train: [39] [2500/6250] eta: 0:08:14 lr: 0.000089 grad: 0.0832 (0.0862) loss: 0.8501 (0.8581) time: 0.1330 data: 0.0592 max mem: 8255 +Train: [39] [2600/6250] eta: 0:08:02 lr: 0.000089 grad: 0.0809 (0.0862) loss: 0.8532 (0.8579) time: 0.1282 data: 0.0561 max mem: 8255 +Train: [39] [2700/6250] eta: 0:07:50 lr: 0.000089 grad: 0.0836 (0.0862) loss: 0.8518 (0.8576) time: 0.1484 data: 0.0798 max mem: 8255 +Train: [39] [2800/6250] eta: 0:07:37 lr: 0.000089 grad: 0.0864 (0.0863) loss: 0.8465 (0.8575) time: 0.1442 data: 0.0735 max mem: 8255 +Train: [39] [2900/6250] eta: 0:07:25 lr: 0.000089 grad: 0.0814 (0.0863) loss: 0.8574 (0.8574) time: 0.1370 data: 0.0737 max mem: 8255 +Train: [39] [3000/6250] eta: 0:07:12 lr: 0.000089 grad: 0.0898 (0.0864) loss: 0.8380 (0.8572) time: 0.1342 data: 0.0649 max mem: 8255 +Train: [39] [3100/6250] eta: 0:06:58 lr: 0.000089 grad: 0.0926 (0.0865) loss: 0.8435 (0.8570) time: 0.1393 data: 0.0713 max mem: 8255 +Train: [39] [3200/6250] eta: 0:06:45 lr: 0.000089 grad: 0.0835 (0.0866) loss: 0.8480 (0.8568) time: 0.1089 data: 0.0378 max mem: 8255 +Train: [39] [3300/6250] eta: 0:06:33 lr: 0.000088 grad: 0.0882 (0.0867) loss: 0.8553 (0.8564) time: 0.1325 data: 0.0608 max mem: 8255 +Train: [39] [3400/6250] eta: 0:06:20 lr: 0.000088 grad: 0.0922 (0.0869) loss: 0.8438 (0.8562) time: 0.1261 data: 0.0556 max mem: 8255 +Train: [39] [3500/6250] eta: 0:06:06 lr: 0.000088 grad: 0.0897 (0.0869) loss: 0.8435 (0.8560) time: 0.1231 data: 0.0493 max mem: 8255 +Train: [39] [3600/6250] eta: 0:05:53 lr: 0.000088 grad: 0.0849 (0.0870) loss: 0.8497 (0.8558) time: 0.1584 data: 0.0964 max mem: 8255 +Train: [39] [3700/6250] eta: 0:05:39 lr: 0.000088 grad: 0.0852 (0.0870) loss: 0.8490 (0.8556) time: 0.1298 data: 0.0615 max mem: 8255 +Train: [39] [3800/6250] eta: 0:05:25 lr: 0.000088 grad: 0.0878 (0.0871) loss: 0.8477 (0.8555) time: 0.1270 data: 0.0560 max mem: 8255 +Train: [39] [3900/6250] eta: 0:05:13 lr: 0.000088 grad: 0.0859 (0.0872) loss: 0.8430 (0.8553) time: 0.1021 data: 0.0222 max mem: 8255 +Train: [39] [4000/6250] eta: 0:04:59 lr: 0.000088 grad: 0.0862 (0.0872) loss: 0.8458 (0.8551) time: 0.0921 data: 0.0167 max mem: 8255 +Train: [39] [4100/6250] eta: 0:04:46 lr: 0.000088 grad: 0.0883 (0.0873) loss: 0.8477 (0.8549) time: 0.1214 data: 0.0487 max mem: 8255 +Train: [39] [4200/6250] eta: 0:04:33 lr: 0.000088 grad: 0.0817 (0.0873) loss: 0.8571 (0.8548) time: 0.1278 data: 0.0544 max mem: 8255 +Train: [39] [4300/6250] eta: 0:04:19 lr: 0.000088 grad: 0.0822 (0.0873) loss: 0.8535 (0.8547) time: 0.1216 data: 0.0541 max mem: 8255 +Train: [39] [4400/6250] eta: 0:04:06 lr: 0.000088 grad: 0.0907 (0.0875) loss: 0.8529 (0.8545) time: 0.1503 data: 0.0811 max mem: 8255 +Train: [39] [4500/6250] eta: 0:03:53 lr: 0.000088 grad: 0.0888 (0.0876) loss: 0.8542 (0.8544) time: 0.1387 data: 0.0632 max mem: 8255 +Train: [39] [4600/6250] eta: 0:03:39 lr: 0.000088 grad: 0.0884 (0.0876) loss: 0.8516 (0.8543) time: 0.1318 data: 0.0623 max mem: 8255 +Train: [39] [4700/6250] eta: 0:03:26 lr: 0.000088 grad: 0.0850 (0.0876) loss: 0.8544 (0.8543) time: 0.1218 data: 0.0480 max mem: 8255 +Train: [39] [4800/6250] eta: 0:03:13 lr: 0.000088 grad: 0.0837 (0.0876) loss: 0.8510 (0.8542) time: 0.1379 data: 0.0670 max mem: 8255 +Train: [39] [4900/6250] eta: 0:03:00 lr: 0.000088 grad: 0.0830 (0.0877) loss: 0.8566 (0.8542) time: 0.1199 data: 0.0217 max mem: 8255 +Train: [39] [5000/6250] eta: 0:02:47 lr: 0.000088 grad: 0.0827 (0.0877) loss: 0.8614 (0.8542) time: 0.1471 data: 0.0786 max mem: 8255 +Train: [39] [5100/6250] eta: 0:02:33 lr: 0.000088 grad: 0.0849 (0.0877) loss: 0.8549 (0.8542) time: 0.1387 data: 0.0640 max mem: 8255 +Train: [39] [5200/6250] eta: 0:02:20 lr: 0.000088 grad: 0.0840 (0.0877) loss: 0.8522 (0.8541) time: 0.0941 data: 0.0153 max mem: 8255 +Train: [39] [5300/6250] eta: 0:02:07 lr: 0.000088 grad: 0.0898 (0.0878) loss: 0.8493 (0.8540) time: 0.1375 data: 0.0578 max mem: 8255 +Train: [39] [5400/6250] eta: 0:01:53 lr: 0.000088 grad: 0.0920 (0.0878) loss: 0.8475 (0.8540) time: 0.1275 data: 0.0561 max mem: 8255 +Train: [39] [5500/6250] eta: 0:01:40 lr: 0.000088 grad: 0.0883 (0.0879) loss: 0.8460 (0.8539) time: 0.1145 data: 0.0430 max mem: 8255 +Train: [39] [5600/6250] eta: 0:01:26 lr: 0.000088 grad: 0.0895 (0.0880) loss: 0.8496 (0.8538) time: 0.1467 data: 0.0717 max mem: 8255 +Train: [39] [5700/6250] eta: 0:01:13 lr: 0.000088 grad: 0.0865 (0.0880) loss: 0.8403 (0.8537) time: 0.1176 data: 0.0434 max mem: 8255 +Train: [39] [5800/6250] eta: 0:01:00 lr: 0.000088 grad: 0.0914 (0.0881) loss: 0.8527 (0.8536) time: 0.0910 data: 0.0211 max mem: 8255 +Train: [39] [5900/6250] eta: 0:00:46 lr: 0.000088 grad: 0.0927 (0.0882) loss: 0.8466 (0.8535) time: 0.1106 data: 0.0400 max mem: 8255 +Train: [39] [6000/6250] eta: 0:00:33 lr: 0.000088 grad: 0.0841 (0.0882) loss: 0.8539 (0.8534) time: 0.1400 data: 0.0631 max mem: 8255 +Train: [39] [6100/6250] eta: 0:00:20 lr: 0.000088 grad: 0.0886 (0.0882) loss: 0.8493 (0.8533) time: 0.1356 data: 0.0633 max mem: 8255 +Train: [39] [6200/6250] eta: 0:00:06 lr: 0.000088 grad: 0.0891 (0.0883) loss: 0.8498 (0.8532) time: 0.1420 data: 0.0703 max mem: 8255 +Train: [39] [6249/6250] eta: 0:00:00 lr: 0.000088 grad: 0.0856 (0.0883) loss: 0.8439 (0.8531) time: 0.1501 data: 0.0747 max mem: 8255 +Train: [39] Total time: 0:14:01 (0.1346 s / it) +Averaged stats: lr: 0.000088 grad: 0.0856 (0.0883) loss: 0.8439 (0.8531) +Eval (hcp-train-subset): [39] [ 0/62] eta: 0:04:58 loss: 0.8765 (0.8765) time: 4.8134 data: 4.7877 max mem: 8255 +Eval (hcp-train-subset): [39] [61/62] eta: 0:00:00 loss: 0.8777 (0.8785) time: 0.1085 data: 0.0876 max mem: 8255 +Eval (hcp-train-subset): [39] Total time: 0:00:12 (0.1942 s / it) +Averaged stats (hcp-train-subset): loss: 0.8777 (0.8785) +Making plots (hcp-train-subset): example=38 +Eval (hcp-val): [39] [ 0/62] eta: 0:03:44 loss: 0.8760 (0.8760) time: 3.6238 data: 3.5635 max mem: 8255 +Eval (hcp-val): [39] [61/62] eta: 0:00:00 loss: 0.8794 (0.8811) time: 0.1102 data: 0.0897 max mem: 8255 +Eval (hcp-val): [39] Total time: 0:00:11 (0.1890 s / it) +Averaged stats (hcp-val): loss: 0.8794 (0.8811) +Making plots (hcp-val): example=10 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-00039.pth +Train: [40] [ 0/6250] eta: 6:50:18 lr: 0.000088 grad: 0.1218 (0.1218) loss: 0.7962 (0.7962) time: 3.9389 data: 3.6293 max mem: 8255 +Train: [40] [ 100/6250] eta: 0:17:26 lr: 0.000088 grad: 0.0990 (0.1212) loss: 0.8582 (0.8635) time: 0.1136 data: 0.0246 max mem: 8255 +Train: [40] [ 200/6250] eta: 0:14:45 lr: 0.000088 grad: 0.0863 (0.1119) loss: 0.8577 (0.8584) time: 0.1355 data: 0.0535 max mem: 8255 +Train: [40] [ 300/6250] eta: 0:13:44 lr: 0.000088 grad: 0.0818 (0.1059) loss: 0.8548 (0.8567) time: 0.1389 data: 0.0558 max mem: 8255 +Train: [40] [ 400/6250] eta: 0:13:09 lr: 0.000087 grad: 0.0897 (0.1017) loss: 0.8537 (0.8568) time: 0.1065 data: 0.0098 max mem: 8255 +Train: [40] [ 500/6250] eta: 0:12:49 lr: 0.000087 grad: 0.0887 (0.0991) loss: 0.8609 (0.8576) time: 0.1061 data: 0.0182 max mem: 8255 +Train: [40] [ 600/6250] eta: 0:12:33 lr: 0.000087 grad: 0.0836 (0.0970) loss: 0.8639 (0.8577) time: 0.1458 data: 0.0695 max mem: 8255 +Train: [40] [ 700/6250] eta: 0:12:19 lr: 0.000087 grad: 0.0841 (0.0967) loss: 0.8570 (0.8574) time: 0.1507 data: 0.0716 max mem: 8255 +Train: [40] [ 800/6250] eta: 0:12:01 lr: 0.000087 grad: 0.0826 (0.0955) loss: 0.8501 (0.8573) time: 0.1369 data: 0.0476 max mem: 8255 +Train: [40] [ 900/6250] eta: 0:11:47 lr: 0.000087 grad: 0.0865 (0.0945) loss: 0.8587 (0.8570) time: 0.1186 data: 0.0424 max mem: 8255 +Train: [40] [1000/6250] eta: 0:11:38 lr: 0.000087 grad: 0.0841 (0.0935) loss: 0.8533 (0.8567) time: 0.1297 data: 0.0507 max mem: 8255 +Train: [40] [1100/6250] eta: 0:11:25 lr: 0.000087 grad: 0.0826 (0.0927) loss: 0.8487 (0.8562) time: 0.1464 data: 0.0725 max mem: 8255 +Train: [40] [1200/6250] eta: 0:11:13 lr: 0.000087 grad: 0.0811 (0.0922) loss: 0.8492 (0.8558) time: 0.1525 data: 0.0907 max mem: 8255 +Train: [40] [1300/6250] eta: 0:10:57 lr: 0.000087 grad: 0.0871 (0.0919) loss: 0.8504 (0.8554) time: 0.1168 data: 0.0457 max mem: 8255 +Train: [40] [1400/6250] eta: 0:10:48 lr: 0.000087 grad: 0.0842 (0.0916) loss: 0.8427 (0.8548) time: 0.1283 data: 0.0530 max mem: 8255 +Train: [40] [1500/6250] eta: 0:10:33 lr: 0.000087 grad: 0.0879 (0.0915) loss: 0.8436 (0.8543) time: 0.1190 data: 0.0479 max mem: 8255 +Train: [40] [1600/6250] eta: 0:10:22 lr: 0.000087 grad: 0.0862 (0.0914) loss: 0.8438 (0.8539) time: 0.1309 data: 0.0591 max mem: 8255 +Train: [40] [1700/6250] eta: 0:10:10 lr: 0.000087 grad: 0.0864 (0.0915) loss: 0.8498 (0.8535) time: 0.1249 data: 0.0538 max mem: 8255 +Train: [40] [1800/6250] eta: 0:09:58 lr: 0.000087 grad: 0.0865 (0.0916) loss: 0.8427 (0.8531) time: 0.1774 data: 0.1060 max mem: 8255 +Train: [40] [1900/6250] eta: 0:09:45 lr: 0.000087 grad: 0.0865 (0.0915) loss: 0.8445 (0.8528) time: 0.1469 data: 0.0763 max mem: 8255 +Train: [40] [2000/6250] eta: 0:09:33 lr: 0.000087 grad: 0.0886 (0.0914) loss: 0.8538 (0.8526) time: 0.1168 data: 0.0445 max mem: 8255 +Train: [40] [2100/6250] eta: 0:09:19 lr: 0.000087 grad: 0.0849 (0.0913) loss: 0.8467 (0.8523) time: 0.1298 data: 0.0565 max mem: 8255 +Train: [40] [2200/6250] eta: 0:09:05 lr: 0.000087 grad: 0.0921 (0.0913) loss: 0.8426 (0.8520) time: 0.1218 data: 0.0453 max mem: 8255 +Train: [40] [2300/6250] eta: 0:08:51 lr: 0.000087 grad: 0.0890 (0.0914) loss: 0.8472 (0.8517) time: 0.1328 data: 0.0690 max mem: 8255 +Train: [40] [2400/6250] eta: 0:08:41 lr: 0.000087 grad: 0.0826 (0.0913) loss: 0.8535 (0.8517) time: 0.1216 data: 0.0493 max mem: 8255 +Train: [40] [2500/6250] eta: 0:08:27 lr: 0.000087 grad: 0.0964 (0.0913) loss: 0.8480 (0.8516) time: 0.1284 data: 0.0548 max mem: 8255 +Train: [40] [2600/6250] eta: 0:08:14 lr: 0.000087 grad: 0.0923 (0.0913) loss: 0.8479 (0.8514) time: 0.1464 data: 0.0721 max mem: 8255 +Train: [40] [2700/6250] eta: 0:08:01 lr: 0.000087 grad: 0.0853 (0.0912) loss: 0.8482 (0.8512) time: 0.1468 data: 0.0663 max mem: 8255 +Train: [40] [2800/6250] eta: 0:07:48 lr: 0.000087 grad: 0.0901 (0.0911) loss: 0.8503 (0.8512) time: 0.1361 data: 0.0635 max mem: 8255 +Train: [40] [2900/6250] eta: 0:07:34 lr: 0.000087 grad: 0.0882 (0.0910) loss: 0.8502 (0.8510) time: 0.1336 data: 0.0577 max mem: 8255 +Train: [40] [3000/6250] eta: 0:07:21 lr: 0.000087 grad: 0.0847 (0.0910) loss: 0.8515 (0.8510) time: 0.1430 data: 0.0684 max mem: 8255 +Train: [40] [3100/6250] eta: 0:07:08 lr: 0.000087 grad: 0.0864 (0.0909) loss: 0.8493 (0.8510) time: 0.1414 data: 0.0743 max mem: 8255 +Train: [40] [3200/6250] eta: 0:06:53 lr: 0.000087 grad: 0.0830 (0.0908) loss: 0.8469 (0.8510) time: 0.1313 data: 0.0576 max mem: 8255 +Train: [40] [3300/6250] eta: 0:06:38 lr: 0.000087 grad: 0.0967 (0.0909) loss: 0.8532 (0.8510) time: 0.1311 data: 0.0660 max mem: 8255 +Train: [40] [3400/6250] eta: 0:06:24 lr: 0.000087 grad: 0.0841 (0.0909) loss: 0.8563 (0.8509) time: 0.1323 data: 0.0555 max mem: 8255 +Train: [40] [3500/6250] eta: 0:06:10 lr: 0.000087 grad: 0.0830 (0.0909) loss: 0.8496 (0.8509) time: 0.0988 data: 0.0265 max mem: 8255 +Train: [40] [3600/6250] eta: 0:05:56 lr: 0.000087 grad: 0.0881 (0.0908) loss: 0.8561 (0.8509) time: 0.1314 data: 0.0641 max mem: 8255 +Train: [40] [3700/6250] eta: 0:05:42 lr: 0.000086 grad: 0.0865 (0.0907) loss: 0.8426 (0.8509) time: 0.1209 data: 0.0484 max mem: 8255 +Train: [40] [3800/6250] eta: 0:05:30 lr: 0.000086 grad: 0.0847 (0.0907) loss: 0.8579 (0.8509) time: 0.1706 data: 0.0993 max mem: 8255 +Train: [40] [3900/6250] eta: 0:05:16 lr: 0.000086 grad: 0.0850 (0.0906) loss: 0.8497 (0.8509) time: 0.1422 data: 0.0774 max mem: 8255 +Train: [40] [4000/6250] eta: 0:05:02 lr: 0.000086 grad: 0.0846 (0.0906) loss: 0.8495 (0.8508) time: 0.1248 data: 0.0532 max mem: 8255 +Train: [40] [4100/6250] eta: 0:04:48 lr: 0.000086 grad: 0.0861 (0.0905) loss: 0.8498 (0.8508) time: 0.1379 data: 0.0661 max mem: 8255 +Train: [40] [4200/6250] eta: 0:04:35 lr: 0.000086 grad: 0.0802 (0.0905) loss: 0.8530 (0.8509) time: 0.1252 data: 0.0551 max mem: 8255 +Train: [40] [4300/6250] eta: 0:04:21 lr: 0.000086 grad: 0.0850 (0.0905) loss: 0.8546 (0.8509) time: 0.1246 data: 0.0548 max mem: 8255 +Train: [40] [4400/6250] eta: 0:04:07 lr: 0.000086 grad: 0.0892 (0.0904) loss: 0.8496 (0.8510) time: 0.1327 data: 0.0642 max mem: 8255 +Train: [40] [4500/6250] eta: 0:03:54 lr: 0.000086 grad: 0.0849 (0.0904) loss: 0.8525 (0.8511) time: 0.1285 data: 0.0545 max mem: 8255 +Train: [40] [4600/6250] eta: 0:03:40 lr: 0.000086 grad: 0.0861 (0.0903) loss: 0.8556 (0.8512) time: 0.1294 data: 0.0620 max mem: 8255 +Train: [40] [4700/6250] eta: 0:03:27 lr: 0.000086 grad: 0.0861 (0.0903) loss: 0.8618 (0.8514) time: 0.1078 data: 0.0338 max mem: 8255 +Train: [40] [4800/6250] eta: 0:03:13 lr: 0.000086 grad: 0.0842 (0.0903) loss: 0.8537 (0.8514) time: 0.1160 data: 0.0448 max mem: 8255 +Train: [40] [4900/6250] eta: 0:03:00 lr: 0.000086 grad: 0.0894 (0.0903) loss: 0.8554 (0.8515) time: 0.1130 data: 0.0432 max mem: 8255 +Train: [40] [5000/6250] eta: 0:02:46 lr: 0.000086 grad: 0.0873 (0.0903) loss: 0.8568 (0.8515) time: 0.1215 data: 0.0521 max mem: 8255 +Train: [40] [5100/6250] eta: 0:02:33 lr: 0.000086 grad: 0.0908 (0.0902) loss: 0.8518 (0.8515) time: 0.1480 data: 0.0823 max mem: 8255 +Train: [40] [5200/6250] eta: 0:02:20 lr: 0.000086 grad: 0.0845 (0.0902) loss: 0.8540 (0.8516) time: 0.1643 data: 0.0982 max mem: 8255 +Train: [40] [5300/6250] eta: 0:02:06 lr: 0.000086 grad: 0.0867 (0.0902) loss: 0.8594 (0.8517) time: 0.1262 data: 0.0551 max mem: 8255 +Train: [40] [5400/6250] eta: 0:01:53 lr: 0.000086 grad: 0.0869 (0.0901) loss: 0.8551 (0.8518) time: 0.1617 data: 0.0899 max mem: 8255 +Train: [40] [5500/6250] eta: 0:01:40 lr: 0.000086 grad: 0.0814 (0.0901) loss: 0.8584 (0.8518) time: 0.1435 data: 0.0739 max mem: 8255 +Train: [40] [5600/6250] eta: 0:01:26 lr: 0.000086 grad: 0.0895 (0.0900) loss: 0.8505 (0.8519) time: 0.1366 data: 0.0603 max mem: 8255 +Train: [40] [5700/6250] eta: 0:01:13 lr: 0.000086 grad: 0.0883 (0.0900) loss: 0.8605 (0.8520) time: 0.1285 data: 0.0713 max mem: 8255 +Train: [40] [5800/6250] eta: 0:01:00 lr: 0.000086 grad: 0.0838 (0.0900) loss: 0.8544 (0.8520) time: 0.1575 data: 0.0900 max mem: 8255 +Train: [40] [5900/6250] eta: 0:00:46 lr: 0.000086 grad: 0.0860 (0.0900) loss: 0.8542 (0.8521) time: 0.1309 data: 0.0594 max mem: 8255 +Train: [40] [6000/6250] eta: 0:00:33 lr: 0.000086 grad: 0.0828 (0.0899) loss: 0.8567 (0.8521) time: 0.1277 data: 0.0679 max mem: 8255 +Train: [40] [6100/6250] eta: 0:00:20 lr: 0.000086 grad: 0.0820 (0.0899) loss: 0.8556 (0.8522) time: 0.2078 data: 0.1472 max mem: 8255 +Train: [40] [6200/6250] eta: 0:00:06 lr: 0.000086 grad: 0.0883 (0.0899) loss: 0.8572 (0.8522) time: 0.1248 data: 0.0615 max mem: 8255 +Train: [40] [6249/6250] eta: 0:00:00 lr: 0.000086 grad: 0.0853 (0.0899) loss: 0.8490 (0.8522) time: 0.1524 data: 0.0874 max mem: 8255 +Train: [40] Total time: 0:14:02 (0.1347 s / it) +Averaged stats: lr: 0.000086 grad: 0.0853 (0.0899) loss: 0.8490 (0.8522) +Eval (hcp-train-subset): [40] [ 0/62] eta: 0:03:06 loss: 0.8897 (0.8897) time: 3.0015 data: 2.9170 max mem: 8255 +Eval (hcp-train-subset): [40] [61/62] eta: 0:00:00 loss: 0.8753 (0.8782) time: 0.1547 data: 0.1340 max mem: 8255 +Eval (hcp-train-subset): [40] Total time: 0:00:13 (0.2184 s / it) +Averaged stats (hcp-train-subset): loss: 0.8753 (0.8782) +Eval (hcp-val): [40] [ 0/62] eta: 0:04:45 loss: 0.8791 (0.8791) time: 4.6052 data: 4.5731 max mem: 8255 +Eval (hcp-val): [40] [61/62] eta: 0:00:00 loss: 0.8783 (0.8802) time: 0.1289 data: 0.1073 max mem: 8255 +Eval (hcp-val): [40] Total time: 0:00:13 (0.2155 s / it) +Averaged stats (hcp-val): loss: 0.8783 (0.8802) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +Train: [41] [ 0/6250] eta: 8:50:33 lr: 0.000086 grad: 0.0720 (0.0720) loss: 0.9098 (0.9098) time: 5.0933 data: 4.8058 max mem: 8255 +Train: [41] [ 100/6250] eta: 0:19:49 lr: 0.000086 grad: 0.0835 (0.0916) loss: 0.8811 (0.8859) time: 0.1487 data: 0.0628 max mem: 8255 +Train: [41] [ 200/6250] eta: 0:17:13 lr: 0.000086 grad: 0.0834 (0.0889) loss: 0.8754 (0.8792) time: 0.1499 data: 0.0659 max mem: 8255 +Train: [41] [ 300/6250] eta: 0:15:37 lr: 0.000086 grad: 0.0813 (0.0872) loss: 0.8640 (0.8757) time: 0.1442 data: 0.0627 max mem: 8255 +Train: [41] [ 400/6250] eta: 0:14:38 lr: 0.000086 grad: 0.0832 (0.0870) loss: 0.8616 (0.8730) time: 0.1223 data: 0.0447 max mem: 8255 +Train: [41] [ 500/6250] eta: 0:13:46 lr: 0.000086 grad: 0.0878 (0.0870) loss: 0.8574 (0.8705) time: 0.1231 data: 0.0498 max mem: 8255 +Train: [41] [ 600/6250] eta: 0:13:06 lr: 0.000086 grad: 0.0843 (0.0873) loss: 0.8588 (0.8681) time: 0.1235 data: 0.0443 max mem: 8255 +Train: [41] [ 700/6250] eta: 0:12:35 lr: 0.000085 grad: 0.0831 (0.0873) loss: 0.8575 (0.8666) time: 0.1116 data: 0.0357 max mem: 8255 +Train: [41] [ 800/6250] eta: 0:12:15 lr: 0.000085 grad: 0.0856 (0.0871) loss: 0.8509 (0.8655) time: 0.1578 data: 0.0783 max mem: 8255 +Train: [41] [ 900/6250] eta: 0:12:16 lr: 0.000085 grad: 0.0826 (0.0868) loss: 0.8669 (0.8650) time: 0.1599 data: 0.0827 max mem: 8255 +Train: [41] [1000/6250] eta: 0:12:14 lr: 0.000085 grad: 0.0810 (0.0867) loss: 0.8611 (0.8645) time: 0.1553 data: 0.0754 max mem: 8255 +Train: [41] [1100/6250] eta: 0:12:09 lr: 0.000085 grad: 0.0796 (0.0862) loss: 0.8563 (0.8639) time: 0.1607 data: 0.0876 max mem: 8255 +Train: [41] [1200/6250] eta: 0:11:50 lr: 0.000085 grad: 0.0829 (0.0859) loss: 0.8578 (0.8635) time: 0.1372 data: 0.0660 max mem: 8255 +Train: [41] [1300/6250] eta: 0:11:33 lr: 0.000085 grad: 0.0810 (0.0859) loss: 0.8569 (0.8630) time: 0.1180 data: 0.0472 max mem: 8255 +Train: [41] [1400/6250] eta: 0:11:17 lr: 0.000085 grad: 0.0803 (0.0856) loss: 0.8549 (0.8624) time: 0.1180 data: 0.0446 max mem: 8255 +Train: [41] [1500/6250] eta: 0:10:59 lr: 0.000085 grad: 0.0823 (0.0858) loss: 0.8503 (0.8616) time: 0.1134 data: 0.0443 max mem: 8255 +Train: [41] [1600/6250] eta: 0:10:45 lr: 0.000085 grad: 0.0920 (0.0860) loss: 0.8543 (0.8611) time: 0.1585 data: 0.0760 max mem: 8255 +Train: [41] [1700/6250] eta: 0:10:32 lr: 0.000085 grad: 0.0848 (0.0862) loss: 0.8520 (0.8606) time: 0.1225 data: 0.0412 max mem: 8255 +Train: [41] [1800/6250] eta: 0:10:18 lr: 0.000085 grad: 0.0843 (0.0863) loss: 0.8509 (0.8601) time: 0.1590 data: 0.0949 max mem: 8255 +Train: [41] [1900/6250] eta: 0:10:03 lr: 0.000085 grad: 0.0902 (0.0863) loss: 0.8605 (0.8599) time: 0.1430 data: 0.0690 max mem: 8255 +Train: [41] [2000/6250] eta: 0:09:49 lr: 0.000085 grad: 0.0895 (0.0864) loss: 0.8507 (0.8596) time: 0.1376 data: 0.0681 max mem: 8255 +Train: [41] [2100/6250] eta: 0:09:33 lr: 0.000085 grad: 0.0849 (0.0864) loss: 0.8582 (0.8594) time: 0.1434 data: 0.0707 max mem: 8255 +Train: [41] [2200/6250] eta: 0:09:18 lr: 0.000085 grad: 0.0853 (0.0864) loss: 0.8503 (0.8592) time: 0.1277 data: 0.0573 max mem: 8255 +Train: [41] [2300/6250] eta: 0:09:06 lr: 0.000085 grad: 0.0823 (0.0864) loss: 0.8560 (0.8590) time: 0.1514 data: 0.0677 max mem: 8255 +Train: [41] [2400/6250] eta: 0:08:51 lr: 0.000085 grad: 0.0822 (0.0864) loss: 0.8566 (0.8590) time: 0.1492 data: 0.0707 max mem: 8255 +Train: [41] [2500/6250] eta: 0:08:38 lr: 0.000085 grad: 0.0827 (0.0864) loss: 0.8594 (0.8588) time: 0.1293 data: 0.0416 max mem: 8255 +Train: [41] [2600/6250] eta: 0:08:23 lr: 0.000085 grad: 0.0882 (0.0865) loss: 0.8503 (0.8586) time: 0.1110 data: 0.0443 max mem: 8255 +Train: [41] [2700/6250] eta: 0:08:07 lr: 0.000085 grad: 0.0872 (0.0865) loss: 0.8480 (0.8584) time: 0.1171 data: 0.0404 max mem: 8255 +Train: [41] [2800/6250] eta: 0:07:52 lr: 0.000085 grad: 0.0863 (0.0866) loss: 0.8512 (0.8581) time: 0.1100 data: 0.0432 max mem: 8255 +Train: [41] [2900/6250] eta: 0:07:38 lr: 0.000085 grad: 0.0930 (0.0868) loss: 0.8512 (0.8579) time: 0.1305 data: 0.0698 max mem: 8255 +Train: [41] [3000/6250] eta: 0:07:24 lr: 0.000085 grad: 0.0902 (0.0870) loss: 0.8475 (0.8575) time: 0.1352 data: 0.0673 max mem: 8255 +Train: [41] [3100/6250] eta: 0:07:11 lr: 0.000085 grad: 0.0853 (0.0871) loss: 0.8561 (0.8573) time: 0.1341 data: 0.0650 max mem: 8255 +Train: [41] [3200/6250] eta: 0:06:57 lr: 0.000085 grad: 0.0839 (0.0872) loss: 0.8537 (0.8571) time: 0.1076 data: 0.0348 max mem: 8255 +Train: [41] [3300/6250] eta: 0:06:43 lr: 0.000085 grad: 0.0860 (0.0874) loss: 0.8475 (0.8568) time: 0.1257 data: 0.0536 max mem: 8255 +Train: [41] [3400/6250] eta: 0:06:30 lr: 0.000085 grad: 0.0866 (0.0874) loss: 0.8444 (0.8565) time: 0.1284 data: 0.0660 max mem: 8255 +Train: [41] [3500/6250] eta: 0:06:16 lr: 0.000085 grad: 0.0884 (0.0876) loss: 0.8462 (0.8563) time: 0.1240 data: 0.0636 max mem: 8255 +Train: [41] [3600/6250] eta: 0:06:03 lr: 0.000085 grad: 0.0926 (0.0877) loss: 0.8419 (0.8560) time: 0.0878 data: 0.0074 max mem: 8255 +Train: [41] [3700/6250] eta: 0:05:50 lr: 0.000085 grad: 0.0824 (0.0878) loss: 0.8532 (0.8558) time: 0.1625 data: 0.0963 max mem: 8255 +Train: [41] [3800/6250] eta: 0:05:35 lr: 0.000085 grad: 0.0860 (0.0879) loss: 0.8563 (0.8557) time: 0.1006 data: 0.0301 max mem: 8255 +Train: [41] [3900/6250] eta: 0:05:21 lr: 0.000084 grad: 0.0887 (0.0879) loss: 0.8480 (0.8555) time: 0.1277 data: 0.0642 max mem: 8255 +Train: [41] [4000/6250] eta: 0:05:08 lr: 0.000084 grad: 0.0878 (0.0880) loss: 0.8457 (0.8554) time: 0.1579 data: 0.0904 max mem: 8255 +Train: [41] [4100/6250] eta: 0:04:53 lr: 0.000084 grad: 0.0869 (0.0880) loss: 0.8584 (0.8553) time: 0.1234 data: 0.0550 max mem: 8255 +Train: [41] [4200/6250] eta: 0:04:40 lr: 0.000084 grad: 0.0849 (0.0881) loss: 0.8504 (0.8552) time: 0.1155 data: 0.0417 max mem: 8255 +Train: [41] [4300/6250] eta: 0:04:27 lr: 0.000084 grad: 0.0830 (0.0881) loss: 0.8546 (0.8551) time: 0.1123 data: 0.0512 max mem: 8255 +Train: [41] [4400/6250] eta: 0:04:13 lr: 0.000084 grad: 0.0814 (0.0880) loss: 0.8591 (0.8551) time: 0.1159 data: 0.0436 max mem: 8255 +Train: [41] [4500/6250] eta: 0:03:59 lr: 0.000084 grad: 0.0911 (0.0881) loss: 0.8478 (0.8551) time: 0.1249 data: 0.0499 max mem: 8255 +Train: [41] [4600/6250] eta: 0:03:45 lr: 0.000084 grad: 0.0861 (0.0881) loss: 0.8522 (0.8550) time: 0.1427 data: 0.0715 max mem: 8255 +Train: [41] [4700/6250] eta: 0:03:32 lr: 0.000084 grad: 0.0917 (0.0881) loss: 0.8584 (0.8550) time: 0.1141 data: 0.0402 max mem: 8255 +Train: [41] [4800/6250] eta: 0:03:18 lr: 0.000084 grad: 0.0914 (0.0882) loss: 0.8536 (0.8549) time: 0.1198 data: 0.0472 max mem: 8255 +Train: [41] [4900/6250] eta: 0:03:04 lr: 0.000084 grad: 0.0858 (0.0882) loss: 0.8523 (0.8549) time: 0.1012 data: 0.0281 max mem: 8255 +Train: [41] [5000/6250] eta: 0:02:50 lr: 0.000084 grad: 0.0889 (0.0883) loss: 0.8518 (0.8548) time: 0.1681 data: 0.0996 max mem: 8255 +Train: [41] [5100/6250] eta: 0:02:36 lr: 0.000084 grad: 0.0925 (0.0883) loss: 0.8383 (0.8547) time: 0.1424 data: 0.0716 max mem: 8255 +Train: [41] [5200/6250] eta: 0:02:23 lr: 0.000084 grad: 0.0881 (0.0884) loss: 0.8527 (0.8546) time: 0.1242 data: 0.0556 max mem: 8255 +Train: [41] [5300/6250] eta: 0:02:09 lr: 0.000084 grad: 0.0864 (0.0884) loss: 0.8503 (0.8545) time: 0.1238 data: 0.0585 max mem: 8255 +Train: [41] [5400/6250] eta: 0:01:55 lr: 0.000084 grad: 0.0939 (0.0885) loss: 0.8453 (0.8544) time: 0.1098 data: 0.0387 max mem: 8255 +Train: [41] [5500/6250] eta: 0:01:42 lr: 0.000084 grad: 0.0896 (0.0885) loss: 0.8506 (0.8543) time: 0.1445 data: 0.0801 max mem: 8255 +Train: [41] [5600/6250] eta: 0:01:28 lr: 0.000084 grad: 0.0942 (0.0886) loss: 0.8572 (0.8543) time: 0.1306 data: 0.0648 max mem: 8255 +Train: [41] [5700/6250] eta: 0:01:14 lr: 0.000084 grad: 0.0891 (0.0887) loss: 0.8431 (0.8542) time: 0.1777 data: 0.1085 max mem: 8255 +Train: [41] [5800/6250] eta: 0:01:01 lr: 0.000084 grad: 0.0871 (0.0887) loss: 0.8527 (0.8541) time: 0.1172 data: 0.0408 max mem: 8255 +Train: [41] [5900/6250] eta: 0:00:47 lr: 0.000084 grad: 0.0860 (0.0888) loss: 0.8442 (0.8540) time: 0.1310 data: 0.0541 max mem: 8255 +Train: [41] [6000/6250] eta: 0:00:34 lr: 0.000084 grad: 0.0919 (0.0888) loss: 0.8549 (0.8539) time: 0.1718 data: 0.0658 max mem: 8255 +Train: [41] [6100/6250] eta: 0:00:20 lr: 0.000084 grad: 0.0848 (0.0889) loss: 0.8524 (0.8539) time: 0.1592 data: 0.0883 max mem: 8255 +Train: [41] [6200/6250] eta: 0:00:06 lr: 0.000084 grad: 0.0851 (0.0889) loss: 0.8562 (0.8539) time: 0.1714 data: 0.1056 max mem: 8255 +Train: [41] [6249/6250] eta: 0:00:00 lr: 0.000084 grad: 0.0868 (0.0889) loss: 0.8472 (0.8538) time: 0.1322 data: 0.0635 max mem: 8255 +Train: [41] Total time: 0:14:14 (0.1367 s / it) +Averaged stats: lr: 0.000084 grad: 0.0868 (0.0889) loss: 0.8472 (0.8538) +Eval (hcp-train-subset): [41] [ 0/62] eta: 0:03:13 loss: 0.8901 (0.8901) time: 3.1180 data: 3.0414 max mem: 8255 +Eval (hcp-train-subset): [41] [61/62] eta: 0:00:00 loss: 0.8780 (0.8787) time: 0.0984 data: 0.0770 max mem: 8255 +Eval (hcp-train-subset): [41] Total time: 0:00:11 (0.1840 s / it) +Averaged stats (hcp-train-subset): loss: 0.8780 (0.8787) +Eval (hcp-val): [41] [ 0/62] eta: 0:04:49 loss: 0.8764 (0.8764) time: 4.6730 data: 4.6464 max mem: 8255 +Eval (hcp-val): [41] [61/62] eta: 0:00:00 loss: 0.8780 (0.8796) time: 0.1536 data: 0.1320 max mem: 8255 +Eval (hcp-val): [41] Total time: 0:00:13 (0.2258 s / it) +Averaged stats (hcp-val): loss: 0.8780 (0.8796) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +Train: [42] [ 0/6250] eta: 8:55:13 lr: 0.000084 grad: 0.1136 (0.1136) loss: 0.8621 (0.8621) time: 5.1382 data: 5.0467 max mem: 8255 +Train: [42] [ 100/6250] eta: 0:20:11 lr: 0.000084 grad: 0.1037 (0.1146) loss: 0.8539 (0.8649) time: 0.1674 data: 0.0840 max mem: 8255 +Train: [42] [ 200/6250] eta: 0:16:46 lr: 0.000084 grad: 0.0939 (0.1114) loss: 0.8561 (0.8597) time: 0.1301 data: 0.0462 max mem: 8255 +Train: [42] [ 300/6250] eta: 0:15:20 lr: 0.000084 grad: 0.0907 (0.1047) loss: 0.8525 (0.8577) time: 0.1312 data: 0.0552 max mem: 8255 +Train: [42] [ 400/6250] eta: 0:14:12 lr: 0.000084 grad: 0.0887 (0.1013) loss: 0.8494 (0.8563) time: 0.1103 data: 0.0262 max mem: 8255 +Train: [42] [ 500/6250] eta: 0:13:19 lr: 0.000084 grad: 0.0857 (0.0989) loss: 0.8597 (0.8558) time: 0.1053 data: 0.0264 max mem: 8255 +Train: [42] [ 600/6250] eta: 0:12:41 lr: 0.000084 grad: 0.0796 (0.0973) loss: 0.8611 (0.8558) time: 0.1151 data: 0.0296 max mem: 8255 +Train: [42] [ 700/6250] eta: 0:12:14 lr: 0.000084 grad: 0.0818 (0.0958) loss: 0.8609 (0.8560) time: 0.1251 data: 0.0447 max mem: 8255 +Train: [42] [ 800/6250] eta: 0:11:53 lr: 0.000084 grad: 0.0778 (0.0945) loss: 0.8654 (0.8562) time: 0.0979 data: 0.0172 max mem: 8255 +Train: [42] [ 900/6250] eta: 0:11:36 lr: 0.000083 grad: 0.0847 (0.0936) loss: 0.8573 (0.8563) time: 0.1370 data: 0.0654 max mem: 8255 +Train: [42] [1000/6250] eta: 0:11:23 lr: 0.000083 grad: 0.0841 (0.0924) loss: 0.8529 (0.8566) time: 0.1170 data: 0.0463 max mem: 8255 +Train: [42] [1100/6250] eta: 0:11:09 lr: 0.000083 grad: 0.0810 (0.0919) loss: 0.8633 (0.8566) time: 0.1296 data: 0.0652 max mem: 8255 +Train: [42] [1200/6250] eta: 0:10:54 lr: 0.000083 grad: 0.0836 (0.0916) loss: 0.8550 (0.8563) time: 0.1323 data: 0.0639 max mem: 8255 +Train: [42] [1300/6250] eta: 0:10:42 lr: 0.000083 grad: 0.0858 (0.0911) loss: 0.8500 (0.8562) time: 0.1200 data: 0.0485 max mem: 8255 +Train: [42] [1400/6250] eta: 0:10:31 lr: 0.000083 grad: 0.0849 (0.0909) loss: 0.8534 (0.8559) time: 0.1392 data: 0.0764 max mem: 8255 +Train: [42] [1500/6250] eta: 0:10:17 lr: 0.000083 grad: 0.0824 (0.0906) loss: 0.8508 (0.8560) time: 0.1238 data: 0.0460 max mem: 8255 +Train: [42] [1600/6250] eta: 0:10:05 lr: 0.000083 grad: 0.0883 (0.0905) loss: 0.8522 (0.8558) time: 0.1268 data: 0.0482 max mem: 8255 +Train: [42] [1700/6250] eta: 0:09:53 lr: 0.000083 grad: 0.0886 (0.0903) loss: 0.8510 (0.8556) time: 0.1326 data: 0.0660 max mem: 8255 +Train: [42] [1800/6250] eta: 0:09:40 lr: 0.000083 grad: 0.0887 (0.0904) loss: 0.8546 (0.8554) time: 0.1445 data: 0.0747 max mem: 8255 +Train: [42] [1900/6250] eta: 0:09:26 lr: 0.000083 grad: 0.0838 (0.0903) loss: 0.8561 (0.8553) time: 0.1449 data: 0.0719 max mem: 8255 +Train: [42] [2000/6250] eta: 0:09:12 lr: 0.000083 grad: 0.0832 (0.0901) loss: 0.8535 (0.8553) time: 0.1536 data: 0.0911 max mem: 8255 +Train: [42] [2100/6250] eta: 0:09:01 lr: 0.000083 grad: 0.0805 (0.0900) loss: 0.8505 (0.8551) time: 0.1505 data: 0.0856 max mem: 8255 +Train: [42] [2200/6250] eta: 0:08:49 lr: 0.000083 grad: 0.0841 (0.0898) loss: 0.8520 (0.8551) time: 0.1401 data: 0.0695 max mem: 8255 +Train: [42] [2300/6250] eta: 0:08:37 lr: 0.000083 grad: 0.0915 (0.0897) loss: 0.8476 (0.8550) time: 0.1354 data: 0.0684 max mem: 8255 +Train: [42] [2400/6250] eta: 0:08:24 lr: 0.000083 grad: 0.0856 (0.0897) loss: 0.8524 (0.8549) time: 0.1137 data: 0.0426 max mem: 8255 +Train: [42] [2500/6250] eta: 0:08:12 lr: 0.000083 grad: 0.0833 (0.0895) loss: 0.8513 (0.8549) time: 0.1378 data: 0.0648 max mem: 8255 +Train: [42] [2600/6250] eta: 0:08:00 lr: 0.000083 grad: 0.0879 (0.0894) loss: 0.8495 (0.8547) time: 0.1327 data: 0.0636 max mem: 8255 +Train: [42] [2700/6250] eta: 0:07:48 lr: 0.000083 grad: 0.0928 (0.0894) loss: 0.8556 (0.8546) time: 0.1575 data: 0.0948 max mem: 8255 +Train: [42] [2800/6250] eta: 0:07:35 lr: 0.000083 grad: 0.0858 (0.0895) loss: 0.8480 (0.8545) time: 0.1408 data: 0.0748 max mem: 8255 +Train: [42] [2900/6250] eta: 0:07:23 lr: 0.000083 grad: 0.0875 (0.0896) loss: 0.8451 (0.8543) time: 0.1344 data: 0.0612 max mem: 8255 +Train: [42] [3000/6250] eta: 0:07:10 lr: 0.000083 grad: 0.0837 (0.0897) loss: 0.8518 (0.8541) time: 0.0997 data: 0.0227 max mem: 8255 +Train: [42] [3100/6250] eta: 0:06:57 lr: 0.000083 grad: 0.0894 (0.0897) loss: 0.8454 (0.8539) time: 0.1190 data: 0.0483 max mem: 8255 +Train: [42] [3200/6250] eta: 0:06:43 lr: 0.000083 grad: 0.0920 (0.0900) loss: 0.8396 (0.8537) time: 0.1319 data: 0.0655 max mem: 8255 +Train: [42] [3300/6250] eta: 0:06:30 lr: 0.000083 grad: 0.0858 (0.0900) loss: 0.8458 (0.8535) time: 0.1533 data: 0.0751 max mem: 8255 +Train: [42] [3400/6250] eta: 0:06:18 lr: 0.000083 grad: 0.0863 (0.0901) loss: 0.8514 (0.8534) time: 0.1434 data: 0.0795 max mem: 8255 +Train: [42] [3500/6250] eta: 0:06:04 lr: 0.000083 grad: 0.0912 (0.0902) loss: 0.8493 (0.8533) time: 0.1493 data: 0.0747 max mem: 8255 +Train: [42] [3600/6250] eta: 0:05:51 lr: 0.000083 grad: 0.0941 (0.0903) loss: 0.8423 (0.8530) time: 0.1220 data: 0.0430 max mem: 8255 +Train: [42] [3700/6250] eta: 0:05:38 lr: 0.000083 grad: 0.0903 (0.0903) loss: 0.8470 (0.8529) time: 0.1397 data: 0.0643 max mem: 8255 +Train: [42] [3800/6250] eta: 0:05:25 lr: 0.000083 grad: 0.0858 (0.0903) loss: 0.8448 (0.8527) time: 0.1305 data: 0.0653 max mem: 8255 +Train: [42] [3900/6250] eta: 0:05:12 lr: 0.000083 grad: 0.0850 (0.0903) loss: 0.8430 (0.8526) time: 0.1358 data: 0.0693 max mem: 8255 +Train: [42] [4000/6250] eta: 0:04:59 lr: 0.000083 grad: 0.0875 (0.0903) loss: 0.8480 (0.8524) time: 0.1259 data: 0.0572 max mem: 8255 +Train: [42] [4100/6250] eta: 0:04:45 lr: 0.000082 grad: 0.0844 (0.0903) loss: 0.8485 (0.8523) time: 0.1366 data: 0.0643 max mem: 8255 +Train: [42] [4200/6250] eta: 0:04:32 lr: 0.000082 grad: 0.0902 (0.0903) loss: 0.8482 (0.8523) time: 0.1551 data: 0.0898 max mem: 8255 +Train: [42] [4300/6250] eta: 0:04:19 lr: 0.000082 grad: 0.0853 (0.0902) loss: 0.8580 (0.8523) time: 0.1239 data: 0.0510 max mem: 8255 +Train: [42] [4400/6250] eta: 0:04:05 lr: 0.000082 grad: 0.0898 (0.0902) loss: 0.8458 (0.8523) time: 0.1329 data: 0.0628 max mem: 8255 +Train: [42] [4500/6250] eta: 0:03:52 lr: 0.000082 grad: 0.0831 (0.0901) loss: 0.8567 (0.8523) time: 0.1127 data: 0.0439 max mem: 8255 +Train: [42] [4600/6250] eta: 0:03:38 lr: 0.000082 grad: 0.0839 (0.0900) loss: 0.8581 (0.8524) time: 0.1422 data: 0.0776 max mem: 8255 +Train: [42] [4700/6250] eta: 0:03:25 lr: 0.000082 grad: 0.0822 (0.0899) loss: 0.8533 (0.8525) time: 0.1457 data: 0.0778 max mem: 8255 +Train: [42] [4800/6250] eta: 0:03:12 lr: 0.000082 grad: 0.0881 (0.0899) loss: 0.8568 (0.8525) time: 0.1245 data: 0.0534 max mem: 8255 +Train: [42] [4900/6250] eta: 0:02:59 lr: 0.000082 grad: 0.0852 (0.0898) loss: 0.8540 (0.8526) time: 0.1559 data: 0.0868 max mem: 8255 +Train: [42] [5000/6250] eta: 0:02:46 lr: 0.000082 grad: 0.0926 (0.0899) loss: 0.8496 (0.8526) time: 0.1611 data: 0.0947 max mem: 8255 +Train: [42] [5100/6250] eta: 0:02:32 lr: 0.000082 grad: 0.0892 (0.0898) loss: 0.8547 (0.8527) time: 0.1138 data: 0.0445 max mem: 8255 +Train: [42] [5200/6250] eta: 0:02:19 lr: 0.000082 grad: 0.0851 (0.0898) loss: 0.8551 (0.8528) time: 0.1259 data: 0.0518 max mem: 8255 +Train: [42] [5300/6250] eta: 0:02:06 lr: 0.000082 grad: 0.0849 (0.0898) loss: 0.8581 (0.8528) time: 0.1205 data: 0.0522 max mem: 8255 +Train: [42] [5400/6250] eta: 0:01:52 lr: 0.000082 grad: 0.0842 (0.0898) loss: 0.8528 (0.8528) time: 0.1231 data: 0.0457 max mem: 8255 +Train: [42] [5500/6250] eta: 0:01:39 lr: 0.000082 grad: 0.0812 (0.0898) loss: 0.8560 (0.8528) time: 0.1347 data: 0.0614 max mem: 8255 +Train: [42] [5600/6250] eta: 0:01:26 lr: 0.000082 grad: 0.0832 (0.0897) loss: 0.8504 (0.8529) time: 0.1115 data: 0.0402 max mem: 8255 +Train: [42] [5700/6250] eta: 0:01:12 lr: 0.000082 grad: 0.0865 (0.0898) loss: 0.8555 (0.8529) time: 0.1081 data: 0.0301 max mem: 8255 +Train: [42] [5800/6250] eta: 0:00:59 lr: 0.000082 grad: 0.0850 (0.0898) loss: 0.8603 (0.8529) time: 0.1311 data: 0.0588 max mem: 8255 +Train: [42] [5900/6250] eta: 0:00:46 lr: 0.000082 grad: 0.0853 (0.0897) loss: 0.8562 (0.8530) time: 0.1189 data: 0.0525 max mem: 8255 +Train: [42] [6000/6250] eta: 0:00:33 lr: 0.000082 grad: 0.0885 (0.0897) loss: 0.8536 (0.8530) time: 0.1320 data: 0.0581 max mem: 8255 +Train: [42] [6100/6250] eta: 0:00:19 lr: 0.000082 grad: 0.0824 (0.0897) loss: 0.8548 (0.8530) time: 0.1044 data: 0.0266 max mem: 8255 +Train: [42] [6200/6250] eta: 0:00:06 lr: 0.000082 grad: 0.0896 (0.0897) loss: 0.8562 (0.8531) time: 0.1247 data: 0.0566 max mem: 8255 +Train: [42] [6249/6250] eta: 0:00:00 lr: 0.000082 grad: 0.0824 (0.0897) loss: 0.8537 (0.8531) time: 0.1337 data: 0.0599 max mem: 8255 +Train: [42] Total time: 0:13:51 (0.1330 s / it) +Averaged stats: lr: 0.000082 grad: 0.0824 (0.0897) loss: 0.8537 (0.8531) +Eval (hcp-train-subset): [42] [ 0/62] eta: 0:05:39 loss: 0.8858 (0.8858) time: 5.4798 data: 5.4542 max mem: 8255 +Eval (hcp-train-subset): [42] [61/62] eta: 0:00:00 loss: 0.8773 (0.8798) time: 0.1461 data: 0.1244 max mem: 8255 +Eval (hcp-train-subset): [42] Total time: 0:00:13 (0.2123 s / it) +Averaged stats (hcp-train-subset): loss: 0.8773 (0.8798) +Eval (hcp-val): [42] [ 0/62] eta: 0:04:42 loss: 0.8763 (0.8763) time: 4.5488 data: 4.5194 max mem: 8255 +Eval (hcp-val): [42] [61/62] eta: 0:00:00 loss: 0.8795 (0.8801) time: 0.1404 data: 0.1183 max mem: 8255 +Eval (hcp-val): [42] Total time: 0:00:12 (0.2081 s / it) +Averaged stats (hcp-val): loss: 0.8795 (0.8801) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +Train: [43] [ 0/6250] eta: 8:36:57 lr: 0.000082 grad: 0.0863 (0.0863) loss: 0.8988 (0.8988) time: 4.9629 data: 4.7559 max mem: 8255 +Train: [43] [ 100/6250] eta: 0:19:08 lr: 0.000082 grad: 0.1111 (0.1151) loss: 0.8530 (0.8635) time: 0.1447 data: 0.0433 max mem: 8255 +Train: [43] [ 200/6250] eta: 0:16:28 lr: 0.000082 grad: 0.0866 (0.1075) loss: 0.8635 (0.8596) time: 0.1320 data: 0.0535 max mem: 8255 +Train: [43] [ 300/6250] eta: 0:15:19 lr: 0.000082 grad: 0.0799 (0.1023) loss: 0.8575 (0.8584) time: 0.1346 data: 0.0613 max mem: 8255 +Train: [43] [ 400/6250] eta: 0:14:35 lr: 0.000082 grad: 0.0743 (0.0975) loss: 0.8596 (0.8577) time: 0.1016 data: 0.0276 max mem: 8255 +Train: [43] [ 500/6250] eta: 0:14:01 lr: 0.000082 grad: 0.0886 (0.0955) loss: 0.8470 (0.8566) time: 0.1473 data: 0.0729 max mem: 8255 +Train: [43] [ 600/6250] eta: 0:13:25 lr: 0.000082 grad: 0.0817 (0.0937) loss: 0.8523 (0.8561) time: 0.1299 data: 0.0485 max mem: 8255 +Train: [43] [ 700/6250] eta: 0:12:56 lr: 0.000082 grad: 0.0855 (0.0929) loss: 0.8535 (0.8560) time: 0.1195 data: 0.0417 max mem: 8255 +Train: [43] [ 800/6250] eta: 0:12:41 lr: 0.000082 grad: 0.0802 (0.0917) loss: 0.8567 (0.8562) time: 0.1499 data: 0.0683 max mem: 8255 +Train: [43] [ 900/6250] eta: 0:12:16 lr: 0.000082 grad: 0.0834 (0.0907) loss: 0.8574 (0.8565) time: 0.1269 data: 0.0508 max mem: 8255 +Train: [43] [1000/6250] eta: 0:11:54 lr: 0.000081 grad: 0.0786 (0.0900) loss: 0.8596 (0.8566) time: 0.1176 data: 0.0481 max mem: 8255 +Train: [43] [1100/6250] eta: 0:11:41 lr: 0.000081 grad: 0.0805 (0.0895) loss: 0.8627 (0.8567) time: 0.1334 data: 0.0611 max mem: 8255 +Train: [43] [1200/6250] eta: 0:11:40 lr: 0.000081 grad: 0.0798 (0.0892) loss: 0.8564 (0.8565) time: 0.1677 data: 0.0993 max mem: 8255 +Train: [43] [1300/6250] eta: 0:11:43 lr: 0.000081 grad: 0.0832 (0.0888) loss: 0.8590 (0.8564) time: 0.2821 data: 0.2087 max mem: 8255 +Train: [43] [1400/6250] eta: 0:11:30 lr: 0.000081 grad: 0.0866 (0.0884) loss: 0.8521 (0.8562) time: 0.1621 data: 0.0904 max mem: 8255 +Train: [43] [1500/6250] eta: 0:11:23 lr: 0.000081 grad: 0.0860 (0.0884) loss: 0.8428 (0.8560) time: 0.1571 data: 0.0932 max mem: 8255 +Train: [43] [1600/6250] eta: 0:11:11 lr: 0.000081 grad: 0.0793 (0.0881) loss: 0.8536 (0.8559) time: 0.1405 data: 0.0706 max mem: 8255 +Train: [43] [1700/6250] eta: 0:10:58 lr: 0.000081 grad: 0.0860 (0.0881) loss: 0.8493 (0.8558) time: 0.1437 data: 0.0751 max mem: 8255 +Train: [43] [1800/6250] eta: 0:10:39 lr: 0.000081 grad: 0.0826 (0.0881) loss: 0.8584 (0.8556) time: 0.1232 data: 0.0585 max mem: 8255 +Train: [43] [1900/6250] eta: 0:10:22 lr: 0.000081 grad: 0.0819 (0.0879) loss: 0.8587 (0.8555) time: 0.1355 data: 0.0680 max mem: 8255 +Train: [43] [2000/6250] eta: 0:10:03 lr: 0.000081 grad: 0.0800 (0.0879) loss: 0.8591 (0.8554) time: 0.1328 data: 0.0593 max mem: 8255 +Train: [43] [2100/6250] eta: 0:09:46 lr: 0.000081 grad: 0.0860 (0.0878) loss: 0.8519 (0.8552) time: 0.1240 data: 0.0564 max mem: 8255 +Train: [43] [2200/6250] eta: 0:09:31 lr: 0.000081 grad: 0.0875 (0.0878) loss: 0.8514 (0.8551) time: 0.1447 data: 0.0769 max mem: 8255 +Train: [43] [2300/6250] eta: 0:09:15 lr: 0.000081 grad: 0.0842 (0.0878) loss: 0.8524 (0.8549) time: 0.1406 data: 0.0716 max mem: 8255 +Train: [43] [2400/6250] eta: 0:09:00 lr: 0.000081 grad: 0.0852 (0.0879) loss: 0.8559 (0.8547) time: 0.1243 data: 0.0549 max mem: 8255 +Train: [43] [2500/6250] eta: 0:08:49 lr: 0.000081 grad: 0.0842 (0.0879) loss: 0.8504 (0.8545) time: 0.1257 data: 0.0549 max mem: 8255 +Train: [43] [2600/6250] eta: 0:08:36 lr: 0.000081 grad: 0.0874 (0.0878) loss: 0.8488 (0.8544) time: 0.1610 data: 0.0800 max mem: 8255 +Train: [43] [2700/6250] eta: 0:08:21 lr: 0.000081 grad: 0.0846 (0.0878) loss: 0.8483 (0.8542) time: 0.1358 data: 0.0625 max mem: 8255 +Train: [43] [2800/6250] eta: 0:08:06 lr: 0.000081 grad: 0.0908 (0.0879) loss: 0.8493 (0.8540) time: 0.1456 data: 0.0680 max mem: 8255 +Train: [43] [2900/6250] eta: 0:07:52 lr: 0.000081 grad: 0.0905 (0.0881) loss: 0.8423 (0.8537) time: 0.1321 data: 0.0588 max mem: 8255 +Train: [43] [3000/6250] eta: 0:07:35 lr: 0.000081 grad: 0.0854 (0.0882) loss: 0.8400 (0.8534) time: 0.1295 data: 0.0598 max mem: 8255 +Train: [43] [3100/6250] eta: 0:07:21 lr: 0.000081 grad: 0.0829 (0.0883) loss: 0.8510 (0.8532) time: 0.1324 data: 0.0589 max mem: 8255 +Train: [43] [3200/6250] eta: 0:07:07 lr: 0.000081 grad: 0.0859 (0.0884) loss: 0.8409 (0.8529) time: 0.1379 data: 0.0647 max mem: 8255 +Train: [43] [3300/6250] eta: 0:06:53 lr: 0.000081 grad: 0.0935 (0.0885) loss: 0.8422 (0.8525) time: 0.1366 data: 0.0702 max mem: 8255 +Train: [43] [3400/6250] eta: 0:06:37 lr: 0.000081 grad: 0.0898 (0.0886) loss: 0.8478 (0.8522) time: 0.1143 data: 0.0420 max mem: 8255 +Train: [43] [3500/6250] eta: 0:06:22 lr: 0.000081 grad: 0.0942 (0.0887) loss: 0.8379 (0.8519) time: 0.1229 data: 0.0504 max mem: 8255 +Train: [43] [3600/6250] eta: 0:06:09 lr: 0.000081 grad: 0.0855 (0.0887) loss: 0.8428 (0.8518) time: 0.1501 data: 0.0833 max mem: 8255 +Train: [43] [3700/6250] eta: 0:05:55 lr: 0.000081 grad: 0.0877 (0.0887) loss: 0.8424 (0.8515) time: 0.1546 data: 0.0929 max mem: 8255 +Train: [43] [3800/6250] eta: 0:05:41 lr: 0.000081 grad: 0.0868 (0.0887) loss: 0.8459 (0.8513) time: 0.1278 data: 0.0581 max mem: 8255 +Train: [43] [3900/6250] eta: 0:05:27 lr: 0.000081 grad: 0.0863 (0.0890) loss: 0.8408 (0.8512) time: 0.1205 data: 0.0538 max mem: 8255 +Train: [43] [4000/6250] eta: 0:05:13 lr: 0.000081 grad: 0.0846 (0.0891) loss: 0.8531 (0.8510) time: 0.1664 data: 0.1006 max mem: 8255 +Train: [43] [4100/6250] eta: 0:04:59 lr: 0.000081 grad: 0.0851 (0.0891) loss: 0.8480 (0.8509) time: 0.1200 data: 0.0526 max mem: 8255 +Train: [43] [4200/6250] eta: 0:04:44 lr: 0.000080 grad: 0.0894 (0.0893) loss: 0.8459 (0.8508) time: 0.1335 data: 0.0697 max mem: 8255 +Train: [43] [4300/6250] eta: 0:04:30 lr: 0.000080 grad: 0.0871 (0.0894) loss: 0.8444 (0.8507) time: 0.1464 data: 0.0799 max mem: 8255 +Train: [43] [4400/6250] eta: 0:04:16 lr: 0.000080 grad: 0.0872 (0.0894) loss: 0.8541 (0.8505) time: 0.1221 data: 0.0517 max mem: 8255 +Train: [43] [4500/6250] eta: 0:04:02 lr: 0.000080 grad: 0.0888 (0.0895) loss: 0.8418 (0.8504) time: 0.1417 data: 0.0643 max mem: 8255 +Train: [43] [4600/6250] eta: 0:03:47 lr: 0.000080 grad: 0.0875 (0.0895) loss: 0.8463 (0.8504) time: 0.1242 data: 0.0557 max mem: 8255 +Train: [43] [4700/6250] eta: 0:03:33 lr: 0.000080 grad: 0.0894 (0.0895) loss: 0.8413 (0.8504) time: 0.1280 data: 0.0425 max mem: 8255 +Train: [43] [4800/6250] eta: 0:03:19 lr: 0.000080 grad: 0.0863 (0.0895) loss: 0.8584 (0.8504) time: 0.1270 data: 0.0571 max mem: 8255 +Train: [43] [4900/6250] eta: 0:03:05 lr: 0.000080 grad: 0.0877 (0.0895) loss: 0.8484 (0.8504) time: 0.1405 data: 0.0635 max mem: 8255 +Train: [43] [5000/6250] eta: 0:02:51 lr: 0.000080 grad: 0.0913 (0.0896) loss: 0.8491 (0.8504) time: 0.1177 data: 0.0487 max mem: 8255 +Train: [43] [5100/6250] eta: 0:02:37 lr: 0.000080 grad: 0.0826 (0.0896) loss: 0.8509 (0.8504) time: 0.1184 data: 0.0539 max mem: 8255 +Train: [43] [5200/6250] eta: 0:02:23 lr: 0.000080 grad: 0.0837 (0.0896) loss: 0.8499 (0.8504) time: 0.1203 data: 0.0508 max mem: 8255 +Train: [43] [5300/6250] eta: 0:02:09 lr: 0.000080 grad: 0.0832 (0.0895) loss: 0.8461 (0.8504) time: 0.1180 data: 0.0513 max mem: 8255 +Train: [43] [5400/6250] eta: 0:01:55 lr: 0.000080 grad: 0.0898 (0.0895) loss: 0.8505 (0.8504) time: 0.1261 data: 0.0498 max mem: 8255 +Train: [43] [5500/6250] eta: 0:01:42 lr: 0.000080 grad: 0.0819 (0.0895) loss: 0.8586 (0.8504) time: 0.1264 data: 0.0532 max mem: 8255 +Train: [43] [5600/6250] eta: 0:01:28 lr: 0.000080 grad: 0.0807 (0.0895) loss: 0.8573 (0.8505) time: 0.1266 data: 0.0578 max mem: 8255 +Train: [43] [5700/6250] eta: 0:01:14 lr: 0.000080 grad: 0.0836 (0.0895) loss: 0.8549 (0.8505) time: 0.1151 data: 0.0468 max mem: 8255 +Train: [43] [5800/6250] eta: 0:01:00 lr: 0.000080 grad: 0.0890 (0.0895) loss: 0.8492 (0.8505) time: 0.1331 data: 0.0640 max mem: 8255 +Train: [43] [5900/6250] eta: 0:00:47 lr: 0.000080 grad: 0.0903 (0.0895) loss: 0.8528 (0.8505) time: 0.1294 data: 0.0524 max mem: 8255 +Train: [43] [6000/6250] eta: 0:00:33 lr: 0.000080 grad: 0.0844 (0.0894) loss: 0.8547 (0.8505) time: 0.1649 data: 0.0912 max mem: 8255 +Train: [43] [6100/6250] eta: 0:00:20 lr: 0.000080 grad: 0.0862 (0.0894) loss: 0.8509 (0.8506) time: 0.1478 data: 0.0847 max mem: 8255 +Train: [43] [6200/6250] eta: 0:00:06 lr: 0.000080 grad: 0.0856 (0.0894) loss: 0.8546 (0.8506) time: 0.1630 data: 0.0893 max mem: 8255 +Train: [43] [6249/6250] eta: 0:00:00 lr: 0.000080 grad: 0.0849 (0.0894) loss: 0.8559 (0.8506) time: 0.1447 data: 0.0806 max mem: 8255 +Train: [43] Total time: 0:14:11 (0.1363 s / it) +Averaged stats: lr: 0.000080 grad: 0.0849 (0.0894) loss: 0.8559 (0.8506) +Eval (hcp-train-subset): [43] [ 0/62] eta: 0:04:38 loss: 0.8857 (0.8857) time: 4.4984 data: 4.4699 max mem: 8255 +Eval (hcp-train-subset): [43] [61/62] eta: 0:00:00 loss: 0.8773 (0.8791) time: 0.1202 data: 0.0980 max mem: 8255 +Eval (hcp-train-subset): [43] Total time: 0:00:12 (0.2090 s / it) +Averaged stats (hcp-train-subset): loss: 0.8773 (0.8791) +Eval (hcp-val): [43] [ 0/62] eta: 0:03:59 loss: 0.8769 (0.8769) time: 3.8606 data: 3.7862 max mem: 8255 +Eval (hcp-val): [43] [61/62] eta: 0:00:00 loss: 0.8797 (0.8803) time: 0.1186 data: 0.0955 max mem: 8255 +Eval (hcp-val): [43] Total time: 0:00:13 (0.2106 s / it) +Averaged stats (hcp-val): loss: 0.8797 (0.8803) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +Train: [44] [ 0/6250] eta: 8:50:38 lr: 0.000080 grad: 0.2113 (0.2113) loss: 0.8886 (0.8886) time: 5.0942 data: 5.0050 max mem: 8255 +Train: [44] [ 100/6250] eta: 0:19:33 lr: 0.000080 grad: 0.1070 (0.1108) loss: 0.8584 (0.8686) time: 0.1401 data: 0.0565 max mem: 8255 +Train: [44] [ 200/6250] eta: 0:16:17 lr: 0.000080 grad: 0.0933 (0.1104) loss: 0.8507 (0.8596) time: 0.1314 data: 0.0550 max mem: 8255 +Train: [44] [ 300/6250] eta: 0:14:48 lr: 0.000080 grad: 0.0927 (0.1050) loss: 0.8542 (0.8581) time: 0.1247 data: 0.0392 max mem: 8255 +Train: [44] [ 400/6250] eta: 0:14:08 lr: 0.000080 grad: 0.0947 (0.1027) loss: 0.8586 (0.8578) time: 0.1382 data: 0.0622 max mem: 8255 +Train: [44] [ 500/6250] eta: 0:13:31 lr: 0.000080 grad: 0.0892 (0.1012) loss: 0.8568 (0.8571) time: 0.1154 data: 0.0374 max mem: 8255 +Train: [44] [ 600/6250] eta: 0:13:39 lr: 0.000080 grad: 0.0904 (0.0999) loss: 0.8579 (0.8565) time: 0.1599 data: 0.0762 max mem: 8255 +Train: [44] [ 700/6250] eta: 0:13:29 lr: 0.000080 grad: 0.0944 (0.0996) loss: 0.8533 (0.8560) time: 0.1468 data: 0.0748 max mem: 8255 +Train: [44] [ 800/6250] eta: 0:13:09 lr: 0.000080 grad: 0.0930 (0.0992) loss: 0.8509 (0.8552) time: 0.1438 data: 0.0623 max mem: 8255 +Train: [44] [ 900/6250] eta: 0:12:48 lr: 0.000080 grad: 0.0912 (0.0985) loss: 0.8471 (0.8544) time: 0.1373 data: 0.0486 max mem: 8255 +Train: [44] [1000/6250] eta: 0:12:20 lr: 0.000080 grad: 0.0889 (0.0980) loss: 0.8500 (0.8539) time: 0.1030 data: 0.0260 max mem: 8255 +Train: [44] [1100/6250] eta: 0:11:55 lr: 0.000079 grad: 0.0871 (0.0975) loss: 0.8493 (0.8534) time: 0.1277 data: 0.0479 max mem: 8255 +Train: [44] [1200/6250] eta: 0:11:31 lr: 0.000079 grad: 0.0903 (0.0970) loss: 0.8448 (0.8530) time: 0.1157 data: 0.0476 max mem: 8255 +Train: [44] [1300/6250] eta: 0:11:09 lr: 0.000079 grad: 0.0897 (0.0967) loss: 0.8468 (0.8528) time: 0.1126 data: 0.0446 max mem: 8255 +Train: [44] [1400/6250] eta: 0:10:47 lr: 0.000079 grad: 0.0901 (0.0964) loss: 0.8474 (0.8523) time: 0.1016 data: 0.0070 max mem: 8255 +Train: [44] [1500/6250] eta: 0:10:29 lr: 0.000079 grad: 0.0897 (0.0961) loss: 0.8542 (0.8522) time: 0.1313 data: 0.0550 max mem: 8255 +Train: [44] [1600/6250] eta: 0:10:16 lr: 0.000079 grad: 0.0856 (0.0957) loss: 0.8444 (0.8521) time: 0.1308 data: 0.0667 max mem: 8255 +Train: [44] [1700/6250] eta: 0:10:09 lr: 0.000079 grad: 0.0866 (0.0954) loss: 0.8522 (0.8518) time: 0.1786 data: 0.1030 max mem: 8255 +Train: [44] [1800/6250] eta: 0:09:56 lr: 0.000079 grad: 0.0858 (0.0950) loss: 0.8522 (0.8516) time: 0.1311 data: 0.0613 max mem: 8255 +Train: [44] [1900/6250] eta: 0:09:44 lr: 0.000079 grad: 0.0892 (0.0948) loss: 0.8508 (0.8517) time: 0.1333 data: 0.0658 max mem: 8255 +Train: [44] [2000/6250] eta: 0:09:32 lr: 0.000079 grad: 0.0848 (0.0948) loss: 0.8589 (0.8517) time: 0.1129 data: 0.0436 max mem: 8255 +Train: [44] [2100/6250] eta: 0:09:19 lr: 0.000079 grad: 0.0876 (0.0946) loss: 0.8518 (0.8516) time: 0.1518 data: 0.0831 max mem: 8255 +Train: [44] [2200/6250] eta: 0:09:05 lr: 0.000079 grad: 0.0871 (0.0944) loss: 0.8475 (0.8516) time: 0.1166 data: 0.0372 max mem: 8255 +Train: [44] [2300/6250] eta: 0:09:00 lr: 0.000079 grad: 0.0869 (0.0942) loss: 0.8465 (0.8515) time: 0.2284 data: 0.1605 max mem: 8255 +Train: [44] [2400/6250] eta: 0:08:43 lr: 0.000079 grad: 0.0929 (0.0941) loss: 0.8472 (0.8513) time: 0.1325 data: 0.0576 max mem: 8255 +Train: [44] [2500/6250] eta: 0:08:29 lr: 0.000079 grad: 0.0855 (0.0940) loss: 0.8490 (0.8511) time: 0.1387 data: 0.0709 max mem: 8255 +Train: [44] [2600/6250] eta: 0:08:14 lr: 0.000079 grad: 0.0889 (0.0938) loss: 0.8483 (0.8510) time: 0.1366 data: 0.0683 max mem: 8255 +Train: [44] [2700/6250] eta: 0:07:59 lr: 0.000079 grad: 0.0867 (0.0936) loss: 0.8494 (0.8510) time: 0.1332 data: 0.0582 max mem: 8255 +Train: [44] [2800/6250] eta: 0:07:45 lr: 0.000079 grad: 0.0883 (0.0936) loss: 0.8484 (0.8510) time: 0.1506 data: 0.0698 max mem: 8255 +Train: [44] [2900/6250] eta: 0:07:31 lr: 0.000079 grad: 0.0829 (0.0934) loss: 0.8479 (0.8511) time: 0.1276 data: 0.0548 max mem: 8255 +Train: [44] [3000/6250] eta: 0:07:18 lr: 0.000079 grad: 0.0893 (0.0933) loss: 0.8485 (0.8511) time: 0.1449 data: 0.0832 max mem: 8255 +Train: [44] [3100/6250] eta: 0:07:04 lr: 0.000079 grad: 0.0893 (0.0934) loss: 0.8435 (0.8510) time: 0.1077 data: 0.0322 max mem: 8255 +Train: [44] [3200/6250] eta: 0:06:51 lr: 0.000079 grad: 0.0869 (0.0933) loss: 0.8492 (0.8508) time: 0.1460 data: 0.0818 max mem: 8255 +Train: [44] [3300/6250] eta: 0:06:37 lr: 0.000079 grad: 0.0870 (0.0932) loss: 0.8442 (0.8507) time: 0.1397 data: 0.0639 max mem: 8255 +Train: [44] [3400/6250] eta: 0:06:23 lr: 0.000079 grad: 0.0899 (0.0932) loss: 0.8513 (0.8507) time: 0.1274 data: 0.0548 max mem: 8255 +Train: [44] [3500/6250] eta: 0:06:09 lr: 0.000079 grad: 0.0936 (0.0931) loss: 0.8508 (0.8506) time: 0.0905 data: 0.0270 max mem: 8255 +Train: [44] [3600/6250] eta: 0:05:56 lr: 0.000079 grad: 0.0879 (0.0930) loss: 0.8535 (0.8506) time: 0.1477 data: 0.0829 max mem: 8255 +Train: [44] [3700/6250] eta: 0:05:42 lr: 0.000079 grad: 0.0793 (0.0929) loss: 0.8539 (0.8506) time: 0.1240 data: 0.0568 max mem: 8255 +Train: [44] [3800/6250] eta: 0:05:30 lr: 0.000079 grad: 0.0860 (0.0927) loss: 0.8528 (0.8507) time: 0.1587 data: 0.0889 max mem: 8255 +Train: [44] [3900/6250] eta: 0:05:16 lr: 0.000079 grad: 0.0874 (0.0926) loss: 0.8547 (0.8507) time: 0.1474 data: 0.0826 max mem: 8255 +Train: [44] [4000/6250] eta: 0:05:03 lr: 0.000079 grad: 0.0839 (0.0926) loss: 0.8520 (0.8508) time: 0.0877 data: 0.0002 max mem: 8255 +Train: [44] [4100/6250] eta: 0:04:50 lr: 0.000079 grad: 0.0903 (0.0926) loss: 0.8480 (0.8508) time: 0.1374 data: 0.0646 max mem: 8255 +Train: [44] [4200/6250] eta: 0:04:36 lr: 0.000078 grad: 0.0841 (0.0925) loss: 0.8513 (0.8508) time: 0.1290 data: 0.0556 max mem: 8255 +Train: [44] [4300/6250] eta: 0:04:23 lr: 0.000078 grad: 0.0842 (0.0924) loss: 0.8560 (0.8509) time: 0.1459 data: 0.0800 max mem: 8255 +Train: [44] [4400/6250] eta: 0:04:09 lr: 0.000078 grad: 0.0874 (0.0924) loss: 0.8607 (0.8509) time: 0.1383 data: 0.0689 max mem: 8255 +Train: [44] [4500/6250] eta: 0:03:55 lr: 0.000078 grad: 0.0930 (0.0924) loss: 0.8565 (0.8509) time: 0.1125 data: 0.0473 max mem: 8255 +Train: [44] [4600/6250] eta: 0:03:42 lr: 0.000078 grad: 0.0890 (0.0923) loss: 0.8489 (0.8510) time: 0.1522 data: 0.0843 max mem: 8255 +Train: [44] [4700/6250] eta: 0:03:28 lr: 0.000078 grad: 0.0885 (0.0923) loss: 0.8485 (0.8510) time: 0.1199 data: 0.0543 max mem: 8255 +Train: [44] [4800/6250] eta: 0:03:14 lr: 0.000078 grad: 0.0873 (0.0922) loss: 0.8513 (0.8510) time: 0.1341 data: 0.0587 max mem: 8255 +Train: [44] [4900/6250] eta: 0:03:01 lr: 0.000078 grad: 0.0879 (0.0922) loss: 0.8517 (0.8511) time: 0.0919 data: 0.0002 max mem: 8255 +Train: [44] [5000/6250] eta: 0:02:48 lr: 0.000078 grad: 0.0825 (0.0921) loss: 0.8513 (0.8511) time: 0.1280 data: 0.0542 max mem: 8255 +Train: [44] [5100/6250] eta: 0:02:34 lr: 0.000078 grad: 0.0888 (0.0921) loss: 0.8577 (0.8511) time: 0.1266 data: 0.0530 max mem: 8255 +Train: [44] [5200/6250] eta: 0:02:21 lr: 0.000078 grad: 0.0831 (0.0921) loss: 0.8551 (0.8510) time: 0.1465 data: 0.0660 max mem: 8255 +Train: [44] [5300/6250] eta: 0:02:08 lr: 0.000078 grad: 0.0840 (0.0921) loss: 0.8559 (0.8511) time: 0.1262 data: 0.0533 max mem: 8255 +Train: [44] [5400/6250] eta: 0:01:54 lr: 0.000078 grad: 0.0915 (0.0921) loss: 0.8443 (0.8511) time: 0.1351 data: 0.0596 max mem: 8255 +Train: [44] [5500/6250] eta: 0:01:41 lr: 0.000078 grad: 0.0871 (0.0921) loss: 0.8555 (0.8511) time: 0.1345 data: 0.0655 max mem: 8255 +Train: [44] [5600/6250] eta: 0:01:27 lr: 0.000078 grad: 0.0869 (0.0921) loss: 0.8564 (0.8512) time: 0.1054 data: 0.0316 max mem: 8255 +Train: [44] [5700/6250] eta: 0:01:14 lr: 0.000078 grad: 0.0804 (0.0920) loss: 0.8515 (0.8512) time: 0.1398 data: 0.0696 max mem: 8255 +Train: [44] [5800/6250] eta: 0:01:00 lr: 0.000078 grad: 0.0848 (0.0919) loss: 0.8544 (0.8513) time: 0.1182 data: 0.0467 max mem: 8255 +Train: [44] [5900/6250] eta: 0:00:47 lr: 0.000078 grad: 0.0878 (0.0919) loss: 0.8476 (0.8513) time: 0.1403 data: 0.0645 max mem: 8255 +Train: [44] [6000/6250] eta: 0:00:33 lr: 0.000078 grad: 0.0825 (0.0918) loss: 0.8492 (0.8513) time: 0.1174 data: 0.0409 max mem: 8255 +Train: [44] [6100/6250] eta: 0:00:20 lr: 0.000078 grad: 0.0872 (0.0918) loss: 0.8550 (0.8513) time: 0.1473 data: 0.0794 max mem: 8255 +Train: [44] [6200/6250] eta: 0:00:06 lr: 0.000078 grad: 0.0890 (0.0919) loss: 0.8497 (0.8513) time: 0.1467 data: 0.0816 max mem: 8255 +Train: [44] [6249/6250] eta: 0:00:00 lr: 0.000078 grad: 0.0895 (0.0919) loss: 0.8401 (0.8513) time: 0.1134 data: 0.0469 max mem: 8255 +Train: [44] Total time: 0:14:06 (0.1354 s / it) +Averaged stats: lr: 0.000078 grad: 0.0895 (0.0919) loss: 0.8401 (0.8513) +Eval (hcp-train-subset): [44] [ 0/62] eta: 0:05:14 loss: 0.8897 (0.8897) time: 5.0656 data: 5.0349 max mem: 8255 +Eval (hcp-train-subset): [44] [61/62] eta: 0:00:00 loss: 0.8767 (0.8778) time: 0.1350 data: 0.1138 max mem: 8255 +Eval (hcp-train-subset): [44] Total time: 0:00:13 (0.2100 s / it) +Averaged stats (hcp-train-subset): loss: 0.8767 (0.8778) +Making plots (hcp-train-subset): example=14 +Eval (hcp-val): [44] [ 0/62] eta: 0:04:31 loss: 0.8749 (0.8749) time: 4.3855 data: 4.3580 max mem: 8255 +Eval (hcp-val): [44] [61/62] eta: 0:00:00 loss: 0.8782 (0.8800) time: 0.1198 data: 0.0982 max mem: 8255 +Eval (hcp-val): [44] Total time: 0:00:12 (0.2090 s / it) +Averaged stats (hcp-val): loss: 0.8782 (0.8800) +Making plots (hcp-val): example=45 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +Train: [45] [ 0/6250] eta: 6:46:18 lr: 0.000078 grad: 0.0463 (0.0463) loss: 0.9234 (0.9234) time: 3.9006 data: 3.6651 max mem: 8255 +Train: [45] [ 100/6250] eta: 0:19:16 lr: 0.000078 grad: 0.0956 (0.1076) loss: 0.8639 (0.8793) time: 0.1503 data: 0.0581 max mem: 8255 +Train: [45] [ 200/6250] eta: 0:16:21 lr: 0.000078 grad: 0.1009 (0.1083) loss: 0.8480 (0.8690) time: 0.1407 data: 0.0511 max mem: 8255 +Train: [45] [ 300/6250] eta: 0:14:55 lr: 0.000078 grad: 0.0908 (0.1059) loss: 0.8510 (0.8637) time: 0.1141 data: 0.0301 max mem: 8255 +Train: [45] [ 400/6250] eta: 0:14:03 lr: 0.000078 grad: 0.0941 (0.1032) loss: 0.8468 (0.8596) time: 0.1163 data: 0.0364 max mem: 8255 +Train: [45] [ 500/6250] eta: 0:13:24 lr: 0.000078 grad: 0.0919 (0.1017) loss: 0.8464 (0.8581) time: 0.1289 data: 0.0366 max mem: 8255 +Train: [45] [ 600/6250] eta: 0:12:49 lr: 0.000078 grad: 0.0806 (0.0996) loss: 0.8593 (0.8570) time: 0.1033 data: 0.0126 max mem: 8255 +Train: [45] [ 700/6250] eta: 0:12:22 lr: 0.000078 grad: 0.0803 (0.0981) loss: 0.8541 (0.8565) time: 0.1403 data: 0.0661 max mem: 8255 +Train: [45] [ 800/6250] eta: 0:12:18 lr: 0.000078 grad: 0.0836 (0.0967) loss: 0.8555 (0.8567) time: 0.1503 data: 0.0687 max mem: 8255 +Train: [45] [ 900/6250] eta: 0:12:11 lr: 0.000078 grad: 0.0849 (0.0955) loss: 0.8577 (0.8567) time: 0.1315 data: 0.0582 max mem: 8255 +Train: [45] [1000/6250] eta: 0:11:54 lr: 0.000078 grad: 0.0897 (0.0948) loss: 0.8500 (0.8563) time: 0.1286 data: 0.0650 max mem: 8255 +Train: [45] [1100/6250] eta: 0:11:36 lr: 0.000077 grad: 0.0914 (0.0941) loss: 0.8488 (0.8560) time: 0.1177 data: 0.0449 max mem: 8255 +Train: [45] [1200/6250] eta: 0:11:16 lr: 0.000077 grad: 0.0882 (0.0936) loss: 0.8458 (0.8556) time: 0.1216 data: 0.0476 max mem: 8255 +Train: [45] [1300/6250] eta: 0:10:56 lr: 0.000077 grad: 0.0891 (0.0932) loss: 0.8509 (0.8551) time: 0.1135 data: 0.0471 max mem: 8255 +Train: [45] [1400/6250] eta: 0:10:37 lr: 0.000077 grad: 0.0835 (0.0929) loss: 0.8489 (0.8547) time: 0.1191 data: 0.0458 max mem: 8255 +Train: [45] [1500/6250] eta: 0:10:19 lr: 0.000077 grad: 0.0871 (0.0926) loss: 0.8469 (0.8544) time: 0.1226 data: 0.0477 max mem: 8255 +Train: [45] [1600/6250] eta: 0:10:02 lr: 0.000077 grad: 0.0912 (0.0925) loss: 0.8462 (0.8542) time: 0.1237 data: 0.0502 max mem: 8255 +Train: [45] [1700/6250] eta: 0:09:48 lr: 0.000077 grad: 0.0881 (0.0924) loss: 0.8495 (0.8540) time: 0.1192 data: 0.0457 max mem: 8255 +Train: [45] [1800/6250] eta: 0:09:35 lr: 0.000077 grad: 0.0836 (0.0924) loss: 0.8582 (0.8537) time: 0.1473 data: 0.0688 max mem: 8255 +Train: [45] [1900/6250] eta: 0:09:23 lr: 0.000077 grad: 0.0913 (0.0923) loss: 0.8417 (0.8534) time: 0.1359 data: 0.0652 max mem: 8255 +Train: [45] [2000/6250] eta: 0:09:13 lr: 0.000077 grad: 0.0874 (0.0922) loss: 0.8499 (0.8533) time: 0.1376 data: 0.0545 max mem: 8255 +Train: [45] [2100/6250] eta: 0:09:01 lr: 0.000077 grad: 0.0906 (0.0922) loss: 0.8533 (0.8530) time: 0.1039 data: 0.0201 max mem: 8255 +Train: [45] [2200/6250] eta: 0:08:48 lr: 0.000077 grad: 0.0923 (0.0923) loss: 0.8393 (0.8529) time: 0.1406 data: 0.0726 max mem: 8255 +Train: [45] [2300/6250] eta: 0:08:35 lr: 0.000077 grad: 0.0866 (0.0922) loss: 0.8530 (0.8528) time: 0.1408 data: 0.0787 max mem: 8255 +Train: [45] [2400/6250] eta: 0:08:23 lr: 0.000077 grad: 0.0934 (0.0922) loss: 0.8491 (0.8526) time: 0.1433 data: 0.0622 max mem: 8255 +Train: [45] [2500/6250] eta: 0:08:09 lr: 0.000077 grad: 0.0860 (0.0923) loss: 0.8500 (0.8525) time: 0.1281 data: 0.0684 max mem: 8255 +Train: [45] [2600/6250] eta: 0:07:56 lr: 0.000077 grad: 0.0964 (0.0923) loss: 0.8471 (0.8524) time: 0.1443 data: 0.0766 max mem: 8255 +Train: [45] [2700/6250] eta: 0:07:44 lr: 0.000077 grad: 0.0882 (0.0924) loss: 0.8479 (0.8523) time: 0.1405 data: 0.0670 max mem: 8255 +Train: [45] [2800/6250] eta: 0:07:32 lr: 0.000077 grad: 0.0964 (0.0924) loss: 0.8457 (0.8520) time: 0.1001 data: 0.0314 max mem: 8255 +Train: [45] [2900/6250] eta: 0:07:19 lr: 0.000077 grad: 0.0872 (0.0924) loss: 0.8501 (0.8519) time: 0.1401 data: 0.0667 max mem: 8255 +Train: [45] [3000/6250] eta: 0:07:06 lr: 0.000077 grad: 0.0872 (0.0925) loss: 0.8497 (0.8518) time: 0.1288 data: 0.0542 max mem: 8255 +Train: [45] [3100/6250] eta: 0:06:53 lr: 0.000077 grad: 0.0930 (0.0925) loss: 0.8424 (0.8516) time: 0.1366 data: 0.0669 max mem: 8255 +Train: [45] [3200/6250] eta: 0:06:40 lr: 0.000077 grad: 0.0939 (0.0926) loss: 0.8454 (0.8516) time: 0.1388 data: 0.0688 max mem: 8255 +Train: [45] [3300/6250] eta: 0:06:27 lr: 0.000077 grad: 0.0908 (0.0926) loss: 0.8479 (0.8514) time: 0.1273 data: 0.0538 max mem: 8255 +Train: [45] [3400/6250] eta: 0:06:13 lr: 0.000077 grad: 0.0961 (0.0926) loss: 0.8474 (0.8512) time: 0.1277 data: 0.0614 max mem: 8255 +Train: [45] [3500/6250] eta: 0:06:00 lr: 0.000077 grad: 0.0916 (0.0926) loss: 0.8433 (0.8511) time: 0.1275 data: 0.0595 max mem: 8255 +Train: [45] [3600/6250] eta: 0:05:48 lr: 0.000077 grad: 0.0977 (0.0928) loss: 0.8472 (0.8508) time: 0.1303 data: 0.0610 max mem: 8255 +Train: [45] [3700/6250] eta: 0:05:35 lr: 0.000077 grad: 0.0932 (0.0928) loss: 0.8442 (0.8506) time: 0.1474 data: 0.0804 max mem: 8255 +Train: [45] [3800/6250] eta: 0:05:22 lr: 0.000077 grad: 0.0965 (0.0929) loss: 0.8420 (0.8505) time: 0.1218 data: 0.0466 max mem: 8255 +Train: [45] [3900/6250] eta: 0:05:10 lr: 0.000077 grad: 0.0941 (0.0929) loss: 0.8436 (0.8502) time: 0.2180 data: 0.1454 max mem: 8255 +Train: [45] [4000/6250] eta: 0:04:56 lr: 0.000077 grad: 0.0936 (0.0931) loss: 0.8520 (0.8500) time: 0.1302 data: 0.0614 max mem: 8255 +Train: [45] [4100/6250] eta: 0:04:42 lr: 0.000077 grad: 0.0899 (0.0932) loss: 0.8453 (0.8498) time: 0.1090 data: 0.0344 max mem: 8255 +Train: [45] [4200/6250] eta: 0:04:29 lr: 0.000076 grad: 0.0869 (0.0932) loss: 0.8492 (0.8496) time: 0.1268 data: 0.0606 max mem: 8255 +Train: [45] [4300/6250] eta: 0:04:15 lr: 0.000076 grad: 0.0900 (0.0932) loss: 0.8522 (0.8495) time: 0.1106 data: 0.0439 max mem: 8255 +Train: [45] [4400/6250] eta: 0:04:02 lr: 0.000076 grad: 0.0891 (0.0932) loss: 0.8466 (0.8493) time: 0.1112 data: 0.0304 max mem: 8255 +Train: [45] [4500/6250] eta: 0:03:49 lr: 0.000076 grad: 0.0877 (0.0932) loss: 0.8481 (0.8492) time: 0.1142 data: 0.0379 max mem: 8255 +Train: [45] [4600/6250] eta: 0:03:36 lr: 0.000076 grad: 0.0902 (0.0932) loss: 0.8556 (0.8492) time: 0.1487 data: 0.0788 max mem: 8255 +Train: [45] [4700/6250] eta: 0:03:23 lr: 0.000076 grad: 0.0973 (0.0932) loss: 0.8379 (0.8491) time: 0.1797 data: 0.1019 max mem: 8255 +Train: [45] [4800/6250] eta: 0:03:10 lr: 0.000076 grad: 0.0874 (0.0932) loss: 0.8408 (0.8490) time: 0.1403 data: 0.0736 max mem: 8255 +Train: [45] [4900/6250] eta: 0:02:57 lr: 0.000076 grad: 0.0861 (0.0931) loss: 0.8507 (0.8490) time: 0.1143 data: 0.0403 max mem: 8255 +Train: [45] [5000/6250] eta: 0:02:44 lr: 0.000076 grad: 0.0908 (0.0931) loss: 0.8501 (0.8490) time: 0.1403 data: 0.0704 max mem: 8255 +Train: [45] [5100/6250] eta: 0:02:31 lr: 0.000076 grad: 0.0922 (0.0931) loss: 0.8483 (0.8490) time: 0.1435 data: 0.0708 max mem: 8255 +Train: [45] [5200/6250] eta: 0:02:18 lr: 0.000076 grad: 0.0891 (0.0931) loss: 0.8491 (0.8490) time: 0.1535 data: 0.0754 max mem: 8255 +Train: [45] [5300/6250] eta: 0:02:04 lr: 0.000076 grad: 0.0949 (0.0932) loss: 0.8500 (0.8490) time: 0.1487 data: 0.0787 max mem: 8255 +Train: [45] [5400/6250] eta: 0:01:51 lr: 0.000076 grad: 0.0931 (0.0932) loss: 0.8403 (0.8490) time: 0.1408 data: 0.0698 max mem: 8255 +Train: [45] [5500/6250] eta: 0:01:38 lr: 0.000076 grad: 0.0916 (0.0932) loss: 0.8452 (0.8490) time: 0.0995 data: 0.0189 max mem: 8255 +Train: [45] [5600/6250] eta: 0:01:25 lr: 0.000076 grad: 0.0893 (0.0932) loss: 0.8487 (0.8490) time: 0.1054 data: 0.0359 max mem: 8255 +Train: [45] [5700/6250] eta: 0:01:12 lr: 0.000076 grad: 0.0866 (0.0931) loss: 0.8500 (0.8490) time: 0.1555 data: 0.0868 max mem: 8255 +Train: [45] [5800/6250] eta: 0:00:59 lr: 0.000076 grad: 0.0907 (0.0931) loss: 0.8467 (0.8490) time: 0.1152 data: 0.0419 max mem: 8255 +Train: [45] [5900/6250] eta: 0:00:46 lr: 0.000076 grad: 0.0891 (0.0931) loss: 0.8518 (0.8491) time: 0.1186 data: 0.0442 max mem: 8255 +Train: [45] [6000/6250] eta: 0:00:32 lr: 0.000076 grad: 0.0844 (0.0930) loss: 0.8557 (0.8492) time: 0.1370 data: 0.0696 max mem: 8255 +Train: [45] [6100/6250] eta: 0:00:19 lr: 0.000076 grad: 0.0939 (0.0931) loss: 0.8524 (0.8492) time: 0.1224 data: 0.0566 max mem: 8255 +Train: [45] [6200/6250] eta: 0:00:06 lr: 0.000076 grad: 0.0851 (0.0931) loss: 0.8558 (0.8492) time: 0.1153 data: 0.0450 max mem: 8255 +Train: [45] [6249/6250] eta: 0:00:00 lr: 0.000076 grad: 0.0896 (0.0931) loss: 0.8522 (0.8492) time: 0.1185 data: 0.0490 max mem: 8255 +Train: [45] Total time: 0:13:45 (0.1321 s / it) +Averaged stats: lr: 0.000076 grad: 0.0896 (0.0931) loss: 0.8522 (0.8492) +Eval (hcp-train-subset): [45] [ 0/62] eta: 0:05:08 loss: 0.8887 (0.8887) time: 4.9792 data: 4.9537 max mem: 8255 +Eval (hcp-train-subset): [45] [61/62] eta: 0:00:00 loss: 0.8749 (0.8769) time: 0.1253 data: 0.1042 max mem: 8255 +Eval (hcp-train-subset): [45] Total time: 0:00:12 (0.2094 s / it) +Averaged stats (hcp-train-subset): loss: 0.8749 (0.8769) +Eval (hcp-val): [45] [ 0/62] eta: 0:03:47 loss: 0.8750 (0.8750) time: 3.6621 data: 3.5987 max mem: 8255 +Eval (hcp-val): [45] [61/62] eta: 0:00:00 loss: 0.8780 (0.8792) time: 0.1341 data: 0.1122 max mem: 8255 +Eval (hcp-val): [45] Total time: 0:00:12 (0.2020 s / it) +Averaged stats (hcp-val): loss: 0.8780 (0.8792) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +Train: [46] [ 0/6250] eta: 8:52:58 lr: 0.000076 grad: 0.1241 (0.1241) loss: 0.8825 (0.8825) time: 5.1165 data: 5.0037 max mem: 8255 +Train: [46] [ 100/6250] eta: 0:19:17 lr: 0.000076 grad: 0.0944 (0.1303) loss: 0.8488 (0.8556) time: 0.1342 data: 0.0405 max mem: 8255 +Train: [46] [ 200/6250] eta: 0:16:19 lr: 0.000076 grad: 0.0938 (0.1188) loss: 0.8516 (0.8501) time: 0.1183 data: 0.0334 max mem: 8255 +Train: [46] [ 300/6250] eta: 0:14:56 lr: 0.000076 grad: 0.0940 (0.1112) loss: 0.8489 (0.8501) time: 0.1218 data: 0.0434 max mem: 8255 +Train: [46] [ 400/6250] eta: 0:13:57 lr: 0.000076 grad: 0.0853 (0.1067) loss: 0.8595 (0.8508) time: 0.1336 data: 0.0592 max mem: 8255 +Train: [46] [ 500/6250] eta: 0:13:13 lr: 0.000076 grad: 0.0902 (0.1036) loss: 0.8581 (0.8516) time: 0.1174 data: 0.0408 max mem: 8255 +Train: [46] [ 600/6250] eta: 0:12:40 lr: 0.000076 grad: 0.0925 (0.1014) loss: 0.8506 (0.8521) time: 0.1225 data: 0.0367 max mem: 8255 +Train: [46] [ 700/6250] eta: 0:12:14 lr: 0.000076 grad: 0.0840 (0.0995) loss: 0.8580 (0.8529) time: 0.1246 data: 0.0462 max mem: 8255 +Train: [46] [ 800/6250] eta: 0:11:56 lr: 0.000076 grad: 0.0880 (0.0982) loss: 0.8598 (0.8534) time: 0.1264 data: 0.0523 max mem: 8255 +Train: [46] [ 900/6250] eta: 0:11:50 lr: 0.000076 grad: 0.0867 (0.0972) loss: 0.8511 (0.8536) time: 0.1480 data: 0.0700 max mem: 8255 +Train: [46] [1000/6250] eta: 0:11:43 lr: 0.000076 grad: 0.0868 (0.0967) loss: 0.8529 (0.8533) time: 0.1424 data: 0.0689 max mem: 8255 +Train: [46] [1100/6250] eta: 0:11:35 lr: 0.000075 grad: 0.0877 (0.0960) loss: 0.8565 (0.8532) time: 0.1173 data: 0.0456 max mem: 8255 +Train: [46] [1200/6250] eta: 0:11:27 lr: 0.000075 grad: 0.0918 (0.0955) loss: 0.8493 (0.8528) time: 0.1578 data: 0.0874 max mem: 8255 +Train: [46] [1300/6250] eta: 0:11:14 lr: 0.000075 grad: 0.0890 (0.0951) loss: 0.8494 (0.8524) time: 0.1386 data: 0.0617 max mem: 8255 +Train: [46] [1400/6250] eta: 0:11:00 lr: 0.000075 grad: 0.0915 (0.0949) loss: 0.8495 (0.8521) time: 0.1218 data: 0.0445 max mem: 8255 +Train: [46] [1500/6250] eta: 0:10:47 lr: 0.000075 grad: 0.0856 (0.0946) loss: 0.8487 (0.8516) time: 0.1524 data: 0.0849 max mem: 8255 +Train: [46] [1600/6250] eta: 0:10:33 lr: 0.000075 grad: 0.0895 (0.0944) loss: 0.8384 (0.8513) time: 0.1532 data: 0.0872 max mem: 8255 +Train: [46] [1700/6250] eta: 0:10:18 lr: 0.000075 grad: 0.0868 (0.0944) loss: 0.8509 (0.8509) time: 0.1691 data: 0.0981 max mem: 8255 +Train: [46] [1800/6250] eta: 0:09:58 lr: 0.000075 grad: 0.0882 (0.0942) loss: 0.8483 (0.8506) time: 0.1056 data: 0.0322 max mem: 8255 +Train: [46] [1900/6250] eta: 0:09:44 lr: 0.000075 grad: 0.0912 (0.0941) loss: 0.8453 (0.8503) time: 0.1340 data: 0.0619 max mem: 8255 +Train: [46] [2000/6250] eta: 0:09:33 lr: 0.000075 grad: 0.0960 (0.0942) loss: 0.8365 (0.8500) time: 0.1296 data: 0.0592 max mem: 8255 +Train: [46] [2100/6250] eta: 0:09:23 lr: 0.000075 grad: 0.0927 (0.0942) loss: 0.8481 (0.8499) time: 0.1560 data: 0.0870 max mem: 8255 +Train: [46] [2200/6250] eta: 0:09:11 lr: 0.000075 grad: 0.0927 (0.0943) loss: 0.8544 (0.8496) time: 0.1493 data: 0.0841 max mem: 8255 +Train: [46] [2300/6250] eta: 0:09:03 lr: 0.000075 grad: 0.0854 (0.0941) loss: 0.8466 (0.8495) time: 0.1851 data: 0.1211 max mem: 8255 +Train: [46] [2400/6250] eta: 0:08:52 lr: 0.000075 grad: 0.0877 (0.0941) loss: 0.8473 (0.8494) time: 0.1647 data: 0.0983 max mem: 8255 +Train: [46] [2500/6250] eta: 0:08:41 lr: 0.000075 grad: 0.0877 (0.0941) loss: 0.8490 (0.8492) time: 0.1703 data: 0.1120 max mem: 8255 +Train: [46] [2600/6250] eta: 0:08:29 lr: 0.000075 grad: 0.0889 (0.0940) loss: 0.8478 (0.8490) time: 0.1612 data: 0.0950 max mem: 8255 +Train: [46] [2700/6250] eta: 0:08:17 lr: 0.000075 grad: 0.0922 (0.0940) loss: 0.8476 (0.8488) time: 0.1214 data: 0.0480 max mem: 8255 +Train: [46] [2800/6250] eta: 0:08:03 lr: 0.000075 grad: 0.0895 (0.0939) loss: 0.8492 (0.8486) time: 0.1273 data: 0.0561 max mem: 8255 +Train: [46] [2900/6250] eta: 0:07:50 lr: 0.000075 grad: 0.0904 (0.0938) loss: 0.8472 (0.8485) time: 0.1337 data: 0.0614 max mem: 8255 +Train: [46] [3000/6250] eta: 0:07:35 lr: 0.000075 grad: 0.0920 (0.0938) loss: 0.8498 (0.8485) time: 0.1468 data: 0.0773 max mem: 8255 +Train: [46] [3100/6250] eta: 0:07:21 lr: 0.000075 grad: 0.0884 (0.0938) loss: 0.8474 (0.8484) time: 0.1299 data: 0.0497 max mem: 8255 +Train: [46] [3200/6250] eta: 0:07:07 lr: 0.000075 grad: 0.0918 (0.0938) loss: 0.8387 (0.8483) time: 0.1369 data: 0.0693 max mem: 8255 +Train: [46] [3300/6250] eta: 0:06:56 lr: 0.000075 grad: 0.0930 (0.0937) loss: 0.8459 (0.8484) time: 0.2315 data: 0.1598 max mem: 8255 +Train: [46] [3400/6250] eta: 0:06:41 lr: 0.000075 grad: 0.0941 (0.0936) loss: 0.8483 (0.8484) time: 0.2200 data: 0.1368 max mem: 8255 +Train: [46] [3500/6250] eta: 0:06:25 lr: 0.000075 grad: 0.0868 (0.0935) loss: 0.8507 (0.8485) time: 0.1188 data: 0.0442 max mem: 8255 +Train: [46] [3600/6250] eta: 0:06:10 lr: 0.000075 grad: 0.0869 (0.0934) loss: 0.8471 (0.8486) time: 0.1210 data: 0.0538 max mem: 8255 +Train: [46] [3700/6250] eta: 0:05:55 lr: 0.000075 grad: 0.0881 (0.0933) loss: 0.8487 (0.8486) time: 0.1302 data: 0.0614 max mem: 8255 +Train: [46] [3800/6250] eta: 0:05:41 lr: 0.000075 grad: 0.0911 (0.0933) loss: 0.8442 (0.8486) time: 0.1668 data: 0.1039 max mem: 8255 +Train: [46] [3900/6250] eta: 0:05:26 lr: 0.000075 grad: 0.0881 (0.0933) loss: 0.8439 (0.8487) time: 0.1353 data: 0.0698 max mem: 8255 +Train: [46] [4000/6250] eta: 0:05:12 lr: 0.000075 grad: 0.0903 (0.0933) loss: 0.8445 (0.8487) time: 0.1286 data: 0.0693 max mem: 8255 +Train: [46] [4100/6250] eta: 0:04:58 lr: 0.000075 grad: 0.0851 (0.0932) loss: 0.8498 (0.8487) time: 0.1442 data: 0.0797 max mem: 8255 +Train: [46] [4200/6250] eta: 0:04:44 lr: 0.000074 grad: 0.0895 (0.0932) loss: 0.8488 (0.8487) time: 0.1312 data: 0.0647 max mem: 8255 +Train: [46] [4300/6250] eta: 0:04:30 lr: 0.000074 grad: 0.0901 (0.0932) loss: 0.8517 (0.8488) time: 0.1439 data: 0.0755 max mem: 8255 +Train: [46] [4400/6250] eta: 0:04:16 lr: 0.000074 grad: 0.0905 (0.0931) loss: 0.8488 (0.8488) time: 0.0957 data: 0.0303 max mem: 8255 +Train: [46] [4500/6250] eta: 0:04:02 lr: 0.000074 grad: 0.0907 (0.0931) loss: 0.8520 (0.8488) time: 0.1236 data: 0.0465 max mem: 8255 +Train: [46] [4600/6250] eta: 0:03:48 lr: 0.000074 grad: 0.1026 (0.0932) loss: 0.8484 (0.8488) time: 0.1354 data: 0.0696 max mem: 8255 +Train: [46] [4700/6250] eta: 0:03:34 lr: 0.000074 grad: 0.0881 (0.0931) loss: 0.8515 (0.8488) time: 0.1433 data: 0.0760 max mem: 8255 +Train: [46] [4800/6250] eta: 0:03:20 lr: 0.000074 grad: 0.0934 (0.0932) loss: 0.8495 (0.8487) time: 0.1490 data: 0.0816 max mem: 8255 +Train: [46] [4900/6250] eta: 0:03:06 lr: 0.000074 grad: 0.0928 (0.0932) loss: 0.8414 (0.8487) time: 0.1375 data: 0.0739 max mem: 8255 +Train: [46] [5000/6250] eta: 0:02:53 lr: 0.000074 grad: 0.0953 (0.0933) loss: 0.8510 (0.8486) time: 0.0802 data: 0.0002 max mem: 8255 +Train: [46] [5100/6250] eta: 0:02:39 lr: 0.000074 grad: 0.0939 (0.0933) loss: 0.8477 (0.8486) time: 0.1346 data: 0.0559 max mem: 8255 +Train: [46] [5200/6250] eta: 0:02:25 lr: 0.000074 grad: 0.0878 (0.0932) loss: 0.8482 (0.8487) time: 0.1245 data: 0.0575 max mem: 8255 +Train: [46] [5300/6250] eta: 0:02:11 lr: 0.000074 grad: 0.0918 (0.0931) loss: 0.8540 (0.8487) time: 0.0795 data: 0.0002 max mem: 8255 +Train: [46] [5400/6250] eta: 0:01:57 lr: 0.000074 grad: 0.0930 (0.0932) loss: 0.8498 (0.8488) time: 0.1265 data: 0.0582 max mem: 8255 +Train: [46] [5500/6250] eta: 0:01:43 lr: 0.000074 grad: 0.0876 (0.0931) loss: 0.8506 (0.8488) time: 0.1226 data: 0.0592 max mem: 8255 +Train: [46] [5600/6250] eta: 0:01:29 lr: 0.000074 grad: 0.0899 (0.0932) loss: 0.8522 (0.8488) time: 0.1267 data: 0.0547 max mem: 8255 +Train: [46] [5700/6250] eta: 0:01:15 lr: 0.000074 grad: 0.0911 (0.0932) loss: 0.8525 (0.8488) time: 0.1188 data: 0.0493 max mem: 8255 +Train: [46] [5800/6250] eta: 0:01:01 lr: 0.000074 grad: 0.0946 (0.0932) loss: 0.8420 (0.8487) time: 0.1369 data: 0.0731 max mem: 8255 +Train: [46] [5900/6250] eta: 0:00:48 lr: 0.000074 grad: 0.0952 (0.0932) loss: 0.8414 (0.8487) time: 0.1317 data: 0.0559 max mem: 8255 +Train: [46] [6000/6250] eta: 0:00:34 lr: 0.000074 grad: 0.0908 (0.0933) loss: 0.8546 (0.8487) time: 0.1365 data: 0.0630 max mem: 8255 +Train: [46] [6100/6250] eta: 0:00:20 lr: 0.000074 grad: 0.0968 (0.0933) loss: 0.8434 (0.8486) time: 0.1774 data: 0.1046 max mem: 8255 +Train: [46] [6200/6250] eta: 0:00:06 lr: 0.000074 grad: 0.0886 (0.0933) loss: 0.8504 (0.8486) time: 0.1311 data: 0.0572 max mem: 8255 +Train: [46] [6249/6250] eta: 0:00:00 lr: 0.000074 grad: 0.0922 (0.0933) loss: 0.8507 (0.8486) time: 0.1427 data: 0.0672 max mem: 8255 +Train: [46] Total time: 0:14:22 (0.1381 s / it) +Averaged stats: lr: 0.000074 grad: 0.0922 (0.0933) loss: 0.8507 (0.8486) +Eval (hcp-train-subset): [46] [ 0/62] eta: 0:03:12 loss: 0.8852 (0.8852) time: 3.1043 data: 3.0398 max mem: 8255 +Eval (hcp-train-subset): [46] [61/62] eta: 0:00:00 loss: 0.8744 (0.8775) time: 0.1082 data: 0.0875 max mem: 8255 +Eval (hcp-train-subset): [46] Total time: 0:00:12 (0.2074 s / it) +Averaged stats (hcp-train-subset): loss: 0.8744 (0.8775) +Eval (hcp-val): [46] [ 0/62] eta: 0:03:12 loss: 0.8736 (0.8736) time: 3.0986 data: 3.0348 max mem: 8255 +Eval (hcp-val): [46] [61/62] eta: 0:00:00 loss: 0.8779 (0.8790) time: 0.1133 data: 0.0925 max mem: 8255 +Eval (hcp-val): [46] Total time: 0:00:13 (0.2124 s / it) +Averaged stats (hcp-val): loss: 0.8779 (0.8790) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +Train: [47] [ 0/6250] eta: 9:20:06 lr: 0.000074 grad: 0.0837 (0.0837) loss: 0.8701 (0.8701) time: 5.3770 data: 5.2685 max mem: 8255 +Train: [47] [ 100/6250] eta: 0:19:44 lr: 0.000074 grad: 0.0880 (0.1069) loss: 0.8716 (0.8686) time: 0.1502 data: 0.0640 max mem: 8255 +Train: [47] [ 200/6250] eta: 0:17:21 lr: 0.000074 grad: 0.0900 (0.1020) loss: 0.8591 (0.8637) time: 0.1540 data: 0.0683 max mem: 8255 +Train: [47] [ 300/6250] eta: 0:15:44 lr: 0.000074 grad: 0.0969 (0.0996) loss: 0.8503 (0.8614) time: 0.1397 data: 0.0483 max mem: 8255 +Train: [47] [ 400/6250] eta: 0:14:51 lr: 0.000074 grad: 0.0968 (0.0988) loss: 0.8529 (0.8593) time: 0.1275 data: 0.0437 max mem: 8255 +Train: [47] [ 500/6250] eta: 0:14:12 lr: 0.000074 grad: 0.0868 (0.0973) loss: 0.8514 (0.8581) time: 0.1131 data: 0.0278 max mem: 8255 +Train: [47] [ 600/6250] eta: 0:13:39 lr: 0.000074 grad: 0.0885 (0.0963) loss: 0.8507 (0.8571) time: 0.1460 data: 0.0639 max mem: 8255 +Train: [47] [ 700/6250] eta: 0:13:11 lr: 0.000074 grad: 0.0904 (0.0957) loss: 0.8506 (0.8563) time: 0.1361 data: 0.0575 max mem: 8255 +Train: [47] [ 800/6250] eta: 0:12:56 lr: 0.000074 grad: 0.0892 (0.0955) loss: 0.8504 (0.8552) time: 0.1468 data: 0.0574 max mem: 8255 +Train: [47] [ 900/6250] eta: 0:12:41 lr: 0.000074 grad: 0.0878 (0.0952) loss: 0.8440 (0.8541) time: 0.1409 data: 0.0715 max mem: 8255 +Train: [47] [1000/6250] eta: 0:12:22 lr: 0.000073 grad: 0.0884 (0.0948) loss: 0.8464 (0.8533) time: 0.1434 data: 0.0678 max mem: 8255 +Train: [47] [1100/6250] eta: 0:12:11 lr: 0.000073 grad: 0.0884 (0.0944) loss: 0.8503 (0.8529) time: 0.1814 data: 0.1128 max mem: 8255 +Train: [47] [1200/6250] eta: 0:11:58 lr: 0.000073 grad: 0.0880 (0.0942) loss: 0.8494 (0.8522) time: 0.1077 data: 0.0414 max mem: 8255 +Train: [47] [1300/6250] eta: 0:11:45 lr: 0.000073 grad: 0.0872 (0.0941) loss: 0.8513 (0.8519) time: 0.1714 data: 0.0982 max mem: 8255 +Train: [47] [1400/6250] eta: 0:11:32 lr: 0.000073 grad: 0.0834 (0.0939) loss: 0.8481 (0.8515) time: 0.1391 data: 0.0621 max mem: 8255 +Train: [47] [1500/6250] eta: 0:11:17 lr: 0.000073 grad: 0.0916 (0.0940) loss: 0.8436 (0.8512) time: 0.1214 data: 0.0415 max mem: 8255 +Train: [47] [1600/6250] eta: 0:11:03 lr: 0.000073 grad: 0.0879 (0.0938) loss: 0.8516 (0.8511) time: 0.1296 data: 0.0520 max mem: 8255 +Train: [47] [1700/6250] eta: 0:10:45 lr: 0.000073 grad: 0.0897 (0.0937) loss: 0.8470 (0.8509) time: 0.1214 data: 0.0412 max mem: 8255 +Train: [47] [1800/6250] eta: 0:10:27 lr: 0.000073 grad: 0.0923 (0.0936) loss: 0.8507 (0.8506) time: 0.1248 data: 0.0550 max mem: 8255 +Train: [47] [1900/6250] eta: 0:10:07 lr: 0.000073 grad: 0.0883 (0.0936) loss: 0.8463 (0.8505) time: 0.1258 data: 0.0478 max mem: 8255 +Train: [47] [2000/6250] eta: 0:09:47 lr: 0.000073 grad: 0.0886 (0.0935) loss: 0.8541 (0.8506) time: 0.1073 data: 0.0244 max mem: 8255 +Train: [47] [2100/6250] eta: 0:09:28 lr: 0.000073 grad: 0.0889 (0.0934) loss: 0.8485 (0.8505) time: 0.1109 data: 0.0389 max mem: 8255 +Train: [47] [2200/6250] eta: 0:09:10 lr: 0.000073 grad: 0.0886 (0.0932) loss: 0.8506 (0.8504) time: 0.1013 data: 0.0270 max mem: 8255 +Train: [47] [2300/6250] eta: 0:08:56 lr: 0.000073 grad: 0.0895 (0.0932) loss: 0.8410 (0.8502) time: 0.1468 data: 0.0777 max mem: 8255 +Train: [47] [2400/6250] eta: 0:08:42 lr: 0.000073 grad: 0.0961 (0.0933) loss: 0.8468 (0.8501) time: 0.1448 data: 0.0787 max mem: 8255 +Train: [47] [2500/6250] eta: 0:08:28 lr: 0.000073 grad: 0.0898 (0.0935) loss: 0.8434 (0.8500) time: 0.1435 data: 0.0755 max mem: 8255 +Train: [47] [2600/6250] eta: 0:08:13 lr: 0.000073 grad: 0.0948 (0.0936) loss: 0.8378 (0.8499) time: 0.1295 data: 0.0678 max mem: 8255 +Train: [47] [2700/6250] eta: 0:08:00 lr: 0.000073 grad: 0.0989 (0.0939) loss: 0.8391 (0.8497) time: 0.1351 data: 0.0702 max mem: 8255 +Train: [47] [2800/6250] eta: 0:07:45 lr: 0.000073 grad: 0.0941 (0.0941) loss: 0.8404 (0.8494) time: 0.1293 data: 0.0624 max mem: 8255 +Train: [47] [2900/6250] eta: 0:07:32 lr: 0.000073 grad: 0.0985 (0.0944) loss: 0.8382 (0.8491) time: 0.1463 data: 0.0750 max mem: 8255 +Train: [47] [3000/6250] eta: 0:07:17 lr: 0.000073 grad: 0.1024 (0.0945) loss: 0.8408 (0.8489) time: 0.1384 data: 0.0684 max mem: 8255 +Train: [47] [3100/6250] eta: 0:07:03 lr: 0.000073 grad: 0.0932 (0.0946) loss: 0.8424 (0.8487) time: 0.1286 data: 0.0579 max mem: 8255 +Train: [47] [3200/6250] eta: 0:06:49 lr: 0.000073 grad: 0.0933 (0.0947) loss: 0.8469 (0.8486) time: 0.1401 data: 0.0708 max mem: 8255 +Train: [47] [3300/6250] eta: 0:06:35 lr: 0.000073 grad: 0.0894 (0.0948) loss: 0.8417 (0.8484) time: 0.1158 data: 0.0433 max mem: 8255 +Train: [47] [3400/6250] eta: 0:06:20 lr: 0.000073 grad: 0.0934 (0.0948) loss: 0.8382 (0.8484) time: 0.1131 data: 0.0458 max mem: 8255 +Train: [47] [3500/6250] eta: 0:06:06 lr: 0.000073 grad: 0.0951 (0.0949) loss: 0.8464 (0.8484) time: 0.1230 data: 0.0464 max mem: 8255 +Train: [47] [3600/6250] eta: 0:05:52 lr: 0.000073 grad: 0.0948 (0.0949) loss: 0.8485 (0.8483) time: 0.1116 data: 0.0363 max mem: 8255 +Train: [47] [3700/6250] eta: 0:05:39 lr: 0.000073 grad: 0.0924 (0.0950) loss: 0.8371 (0.8482) time: 0.1409 data: 0.0758 max mem: 8255 +Train: [47] [3800/6250] eta: 0:05:26 lr: 0.000073 grad: 0.0921 (0.0950) loss: 0.8480 (0.8481) time: 0.1434 data: 0.0681 max mem: 8255 +Train: [47] [3900/6250] eta: 0:05:13 lr: 0.000073 grad: 0.0913 (0.0951) loss: 0.8442 (0.8481) time: 0.1361 data: 0.0725 max mem: 8255 +Train: [47] [4000/6250] eta: 0:05:00 lr: 0.000073 grad: 0.0969 (0.0952) loss: 0.8439 (0.8479) time: 0.1015 data: 0.0244 max mem: 8255 +Train: [47] [4100/6250] eta: 0:04:46 lr: 0.000072 grad: 0.0991 (0.0952) loss: 0.8330 (0.8478) time: 0.1247 data: 0.0545 max mem: 8255 +Train: [47] [4200/6250] eta: 0:04:34 lr: 0.000072 grad: 0.0952 (0.0952) loss: 0.8567 (0.8478) time: 0.1517 data: 0.0827 max mem: 8255 +Train: [47] [4300/6250] eta: 0:04:20 lr: 0.000072 grad: 0.0892 (0.0953) loss: 0.8429 (0.8478) time: 0.1404 data: 0.0718 max mem: 8255 +Train: [47] [4400/6250] eta: 0:04:07 lr: 0.000072 grad: 0.0908 (0.0952) loss: 0.8425 (0.8478) time: 0.1508 data: 0.0792 max mem: 8255 +Train: [47] [4500/6250] eta: 0:03:54 lr: 0.000072 grad: 0.0936 (0.0953) loss: 0.8451 (0.8477) time: 0.1324 data: 0.0630 max mem: 8255 +Train: [47] [4600/6250] eta: 0:03:40 lr: 0.000072 grad: 0.0896 (0.0953) loss: 0.8474 (0.8477) time: 0.1260 data: 0.0517 max mem: 8255 +Train: [47] [4700/6250] eta: 0:03:27 lr: 0.000072 grad: 0.0951 (0.0953) loss: 0.8401 (0.8476) time: 0.1603 data: 0.0949 max mem: 8255 +Train: [47] [4800/6250] eta: 0:03:13 lr: 0.000072 grad: 0.0933 (0.0953) loss: 0.8444 (0.8475) time: 0.1270 data: 0.0657 max mem: 8255 +Train: [47] [4900/6250] eta: 0:03:00 lr: 0.000072 grad: 0.0934 (0.0952) loss: 0.8471 (0.8475) time: 0.0753 data: 0.0004 max mem: 8255 +Train: [47] [5000/6250] eta: 0:02:47 lr: 0.000072 grad: 0.0968 (0.0952) loss: 0.8487 (0.8474) time: 0.2503 data: 0.1807 max mem: 8255 +Train: [47] [5100/6250] eta: 0:02:33 lr: 0.000072 grad: 0.0902 (0.0952) loss: 0.8548 (0.8474) time: 0.1253 data: 0.0580 max mem: 8255 +Train: [47] [5200/6250] eta: 0:02:19 lr: 0.000072 grad: 0.0950 (0.0952) loss: 0.8439 (0.8473) time: 0.1028 data: 0.0216 max mem: 8255 +Train: [47] [5300/6250] eta: 0:02:06 lr: 0.000072 grad: 0.0916 (0.0952) loss: 0.8388 (0.8473) time: 0.1278 data: 0.0525 max mem: 8255 +Train: [47] [5400/6250] eta: 0:01:53 lr: 0.000072 grad: 0.0847 (0.0952) loss: 0.8500 (0.8473) time: 0.1411 data: 0.0752 max mem: 8255 +Train: [47] [5500/6250] eta: 0:01:39 lr: 0.000072 grad: 0.0919 (0.0951) loss: 0.8491 (0.8473) time: 0.1045 data: 0.0289 max mem: 8255 +Train: [47] [5600/6250] eta: 0:01:26 lr: 0.000072 grad: 0.0900 (0.0951) loss: 0.8437 (0.8473) time: 0.1284 data: 0.0641 max mem: 8255 +Train: [47] [5700/6250] eta: 0:01:13 lr: 0.000072 grad: 0.0912 (0.0952) loss: 0.8512 (0.8474) time: 0.1588 data: 0.0814 max mem: 8255 +Train: [47] [5800/6250] eta: 0:01:00 lr: 0.000072 grad: 0.0871 (0.0952) loss: 0.8508 (0.8474) time: 0.1260 data: 0.0585 max mem: 8255 +Train: [47] [5900/6250] eta: 0:00:46 lr: 0.000072 grad: 0.0928 (0.0952) loss: 0.8504 (0.8475) time: 0.1767 data: 0.1082 max mem: 8255 +Train: [47] [6000/6250] eta: 0:00:33 lr: 0.000072 grad: 0.0912 (0.0952) loss: 0.8557 (0.8475) time: 0.1294 data: 0.0593 max mem: 8255 +Train: [47] [6100/6250] eta: 0:00:20 lr: 0.000072 grad: 0.0907 (0.0952) loss: 0.8532 (0.8475) time: 0.1269 data: 0.0575 max mem: 8255 +Train: [47] [6200/6250] eta: 0:00:06 lr: 0.000072 grad: 0.0915 (0.0952) loss: 0.8492 (0.8475) time: 0.1081 data: 0.0378 max mem: 8255 +Train: [47] [6249/6250] eta: 0:00:00 lr: 0.000072 grad: 0.0928 (0.0952) loss: 0.8509 (0.8476) time: 0.1343 data: 0.0575 max mem: 8255 +Train: [47] Total time: 0:13:59 (0.1342 s / it) +Averaged stats: lr: 0.000072 grad: 0.0928 (0.0952) loss: 0.8509 (0.8476) +Eval (hcp-train-subset): [47] [ 0/62] eta: 0:05:00 loss: 0.8915 (0.8915) time: 4.8443 data: 4.8177 max mem: 8255 +Eval (hcp-train-subset): [47] [61/62] eta: 0:00:00 loss: 0.8734 (0.8761) time: 0.1223 data: 0.1015 max mem: 8255 +Eval (hcp-train-subset): [47] Total time: 0:00:13 (0.2193 s / it) +Averaged stats (hcp-train-subset): loss: 0.8734 (0.8761) +Eval (hcp-val): [47] [ 0/62] eta: 0:05:16 loss: 0.8821 (0.8821) time: 5.1059 data: 5.0796 max mem: 8255 +Eval (hcp-val): [47] [61/62] eta: 0:00:00 loss: 0.8794 (0.8791) time: 0.1318 data: 0.1099 max mem: 8255 +Eval (hcp-val): [47] Total time: 0:00:13 (0.2240 s / it) +Averaged stats (hcp-val): loss: 0.8794 (0.8791) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +Train: [48] [ 0/6250] eta: 8:13:08 lr: 0.000072 grad: 0.2996 (0.2996) loss: 0.8881 (0.8881) time: 4.7342 data: 4.5759 max mem: 8255 +Train: [48] [ 100/6250] eta: 0:20:29 lr: 0.000072 grad: 0.1005 (0.1314) loss: 0.8651 (0.8666) time: 0.1387 data: 0.0517 max mem: 8255 +Train: [48] [ 200/6250] eta: 0:17:20 lr: 0.000072 grad: 0.0928 (0.1186) loss: 0.8553 (0.8606) time: 0.1576 data: 0.0724 max mem: 8255 +Train: [48] [ 300/6250] eta: 0:15:56 lr: 0.000072 grad: 0.0875 (0.1109) loss: 0.8602 (0.8583) time: 0.1413 data: 0.0492 max mem: 8255 +Train: [48] [ 400/6250] eta: 0:15:17 lr: 0.000072 grad: 0.0889 (0.1070) loss: 0.8533 (0.8578) time: 0.1387 data: 0.0631 max mem: 8255 +Train: [48] [ 500/6250] eta: 0:14:19 lr: 0.000072 grad: 0.0898 (0.1043) loss: 0.8512 (0.8577) time: 0.1193 data: 0.0367 max mem: 8255 +Train: [48] [ 600/6250] eta: 0:13:41 lr: 0.000072 grad: 0.0834 (0.1023) loss: 0.8606 (0.8575) time: 0.1392 data: 0.0721 max mem: 8255 +Train: [48] [ 700/6250] eta: 0:13:07 lr: 0.000072 grad: 0.0865 (0.1007) loss: 0.8555 (0.8575) time: 0.1350 data: 0.0548 max mem: 8255 +Train: [48] [ 800/6250] eta: 0:12:57 lr: 0.000072 grad: 0.0859 (0.0993) loss: 0.8609 (0.8574) time: 0.1635 data: 0.0891 max mem: 8255 +Train: [48] [ 900/6250] eta: 0:12:50 lr: 0.000071 grad: 0.0911 (0.0982) loss: 0.8549 (0.8573) time: 0.1425 data: 0.0702 max mem: 8255 +Train: [48] [1000/6250] eta: 0:12:38 lr: 0.000071 grad: 0.0872 (0.0973) loss: 0.8625 (0.8572) time: 0.1780 data: 0.0832 max mem: 8255 +Train: [48] [1100/6250] eta: 0:12:19 lr: 0.000071 grad: 0.0893 (0.0967) loss: 0.8513 (0.8569) time: 0.1475 data: 0.0578 max mem: 8255 +Train: [48] [1200/6250] eta: 0:12:05 lr: 0.000071 grad: 0.0926 (0.0964) loss: 0.8452 (0.8563) time: 0.1434 data: 0.0736 max mem: 8255 +Train: [48] [1300/6250] eta: 0:11:49 lr: 0.000071 grad: 0.0851 (0.0961) loss: 0.8545 (0.8557) time: 0.1632 data: 0.0780 max mem: 8255 +Train: [48] [1400/6250] eta: 0:11:44 lr: 0.000071 grad: 0.0935 (0.0958) loss: 0.8524 (0.8554) time: 0.0948 data: 0.0002 max mem: 8255 +Train: [48] [1500/6250] eta: 0:11:35 lr: 0.000071 grad: 0.0948 (0.0958) loss: 0.8365 (0.8547) time: 0.1352 data: 0.0663 max mem: 8255 +Train: [48] [1600/6250] eta: 0:11:20 lr: 0.000071 grad: 0.0890 (0.0958) loss: 0.8447 (0.8540) time: 0.1546 data: 0.0795 max mem: 8255 +Train: [48] [1700/6250] eta: 0:11:06 lr: 0.000071 grad: 0.0931 (0.0959) loss: 0.8462 (0.8534) time: 0.1623 data: 0.0878 max mem: 8255 +Train: [48] [1800/6250] eta: 0:10:50 lr: 0.000071 grad: 0.0991 (0.0962) loss: 0.8460 (0.8529) time: 0.1437 data: 0.0739 max mem: 8255 +Train: [48] [1900/6250] eta: 0:10:34 lr: 0.000071 grad: 0.0951 (0.0962) loss: 0.8434 (0.8525) time: 0.1309 data: 0.0596 max mem: 8255 +Train: [48] [2000/6250] eta: 0:10:18 lr: 0.000071 grad: 0.0971 (0.0961) loss: 0.8425 (0.8522) time: 0.1036 data: 0.0277 max mem: 8255 +Train: [48] [2100/6250] eta: 0:10:00 lr: 0.000071 grad: 0.0955 (0.0961) loss: 0.8415 (0.8518) time: 0.1217 data: 0.0469 max mem: 8255 +Train: [48] [2200/6250] eta: 0:09:43 lr: 0.000071 grad: 0.0912 (0.0960) loss: 0.8446 (0.8515) time: 0.1492 data: 0.0829 max mem: 8255 +Train: [48] [2300/6250] eta: 0:09:24 lr: 0.000071 grad: 0.0889 (0.0960) loss: 0.8407 (0.8512) time: 0.1366 data: 0.0567 max mem: 8255 +Train: [48] [2400/6250] eta: 0:09:05 lr: 0.000071 grad: 0.0913 (0.0961) loss: 0.8439 (0.8510) time: 0.1206 data: 0.0484 max mem: 8255 +Train: [48] [2500/6250] eta: 0:08:46 lr: 0.000071 grad: 0.0899 (0.0961) loss: 0.8470 (0.8507) time: 0.1092 data: 0.0379 max mem: 8255 +Train: [48] [2600/6250] eta: 0:08:28 lr: 0.000071 grad: 0.0900 (0.0960) loss: 0.8491 (0.8506) time: 0.1142 data: 0.0447 max mem: 8255 +Train: [48] [2700/6250] eta: 0:08:13 lr: 0.000071 grad: 0.0921 (0.0961) loss: 0.8475 (0.8504) time: 0.1457 data: 0.0802 max mem: 8255 +Train: [48] [2800/6250] eta: 0:07:59 lr: 0.000071 grad: 0.0934 (0.0960) loss: 0.8496 (0.8503) time: 0.1541 data: 0.0897 max mem: 8255 +Train: [48] [2900/6250] eta: 0:07:49 lr: 0.000071 grad: 0.0952 (0.0960) loss: 0.8480 (0.8503) time: 0.2230 data: 0.0891 max mem: 8255 +Train: [48] [3000/6250] eta: 0:07:37 lr: 0.000071 grad: 0.0928 (0.0959) loss: 0.8537 (0.8502) time: 0.1542 data: 0.0841 max mem: 8255 +Train: [48] [3100/6250] eta: 0:07:24 lr: 0.000071 grad: 0.0937 (0.0960) loss: 0.8549 (0.8502) time: 0.1483 data: 0.0708 max mem: 8255 +Train: [48] [3200/6250] eta: 0:07:08 lr: 0.000071 grad: 0.0890 (0.0959) loss: 0.8467 (0.8501) time: 0.1288 data: 0.0587 max mem: 8255 +Train: [48] [3300/6250] eta: 0:06:56 lr: 0.000071 grad: 0.0895 (0.0959) loss: 0.8516 (0.8501) time: 0.2026 data: 0.1386 max mem: 8255 +Train: [48] [3400/6250] eta: 0:06:41 lr: 0.000071 grad: 0.0880 (0.0958) loss: 0.8521 (0.8501) time: 0.1426 data: 0.0709 max mem: 8255 +Train: [48] [3500/6250] eta: 0:06:27 lr: 0.000071 grad: 0.0913 (0.0958) loss: 0.8505 (0.8500) time: 0.1970 data: 0.1180 max mem: 8255 +Train: [48] [3600/6250] eta: 0:06:13 lr: 0.000071 grad: 0.0955 (0.0958) loss: 0.8486 (0.8501) time: 0.1433 data: 0.0766 max mem: 8255 +Train: [48] [3700/6250] eta: 0:05:59 lr: 0.000071 grad: 0.0916 (0.0958) loss: 0.8513 (0.8500) time: 0.1680 data: 0.0846 max mem: 8255 +Train: [48] [3800/6250] eta: 0:05:47 lr: 0.000071 grad: 0.0880 (0.0958) loss: 0.8548 (0.8499) time: 0.1805 data: 0.0005 max mem: 8255 +Train: [48] [3900/6250] eta: 0:05:31 lr: 0.000070 grad: 0.0861 (0.0958) loss: 0.8543 (0.8499) time: 0.1047 data: 0.0144 max mem: 8255 +Train: [48] [4000/6250] eta: 0:05:17 lr: 0.000070 grad: 0.0941 (0.0957) loss: 0.8476 (0.8498) time: 0.1266 data: 0.0492 max mem: 8255 +Train: [48] [4100/6250] eta: 0:05:02 lr: 0.000070 grad: 0.0944 (0.0958) loss: 0.8475 (0.8498) time: 0.1296 data: 0.0561 max mem: 8255 +Train: [48] [4200/6250] eta: 0:04:48 lr: 0.000070 grad: 0.0917 (0.0959) loss: 0.8470 (0.8497) time: 0.1106 data: 0.0369 max mem: 8255 +Train: [48] [4300/6250] eta: 0:04:33 lr: 0.000070 grad: 0.0964 (0.0960) loss: 0.8473 (0.8497) time: 0.1186 data: 0.0455 max mem: 8255 +Train: [48] [4400/6250] eta: 0:04:19 lr: 0.000070 grad: 0.0951 (0.0960) loss: 0.8532 (0.8497) time: 0.1265 data: 0.0561 max mem: 8255 +Train: [48] [4500/6250] eta: 0:04:04 lr: 0.000070 grad: 0.0974 (0.0960) loss: 0.8491 (0.8496) time: 0.1235 data: 0.0427 max mem: 8255 +Train: [48] [4600/6250] eta: 0:03:50 lr: 0.000070 grad: 0.0916 (0.0960) loss: 0.8500 (0.8496) time: 0.1287 data: 0.0637 max mem: 8255 +Train: [48] [4700/6250] eta: 0:03:35 lr: 0.000070 grad: 0.0962 (0.0962) loss: 0.8435 (0.8495) time: 0.1199 data: 0.0462 max mem: 8255 +Train: [48] [4800/6250] eta: 0:03:21 lr: 0.000070 grad: 0.0927 (0.0962) loss: 0.8508 (0.8495) time: 0.1350 data: 0.0727 max mem: 8255 +Train: [48] [4900/6250] eta: 0:03:07 lr: 0.000070 grad: 0.0943 (0.0962) loss: 0.8460 (0.8494) time: 0.1163 data: 0.0414 max mem: 8255 +Train: [48] [5000/6250] eta: 0:02:53 lr: 0.000070 grad: 0.0898 (0.0962) loss: 0.8476 (0.8493) time: 0.1209 data: 0.0506 max mem: 8255 +Train: [48] [5100/6250] eta: 0:02:38 lr: 0.000070 grad: 0.0933 (0.0962) loss: 0.8473 (0.8493) time: 0.1257 data: 0.0570 max mem: 8255 +Train: [48] [5200/6250] eta: 0:02:25 lr: 0.000070 grad: 0.0970 (0.0963) loss: 0.8480 (0.8492) time: 0.1552 data: 0.0864 max mem: 8255 +Train: [48] [5300/6250] eta: 0:02:11 lr: 0.000070 grad: 0.0886 (0.0963) loss: 0.8483 (0.8492) time: 0.1339 data: 0.0577 max mem: 8255 +Train: [48] [5400/6250] eta: 0:01:57 lr: 0.000070 grad: 0.0909 (0.0963) loss: 0.8525 (0.8492) time: 0.1206 data: 0.0554 max mem: 8255 +Train: [48] [5500/6250] eta: 0:01:43 lr: 0.000070 grad: 0.0935 (0.0964) loss: 0.8522 (0.8492) time: 0.1324 data: 0.0571 max mem: 8255 +Train: [48] [5600/6250] eta: 0:01:29 lr: 0.000070 grad: 0.0962 (0.0964) loss: 0.8496 (0.8491) time: 0.1359 data: 0.0575 max mem: 8255 +Train: [48] [5700/6250] eta: 0:01:15 lr: 0.000070 grad: 0.0942 (0.0964) loss: 0.8500 (0.8491) time: 0.1412 data: 0.0703 max mem: 8255 +Train: [48] [5800/6250] eta: 0:01:02 lr: 0.000070 grad: 0.0912 (0.0964) loss: 0.8460 (0.8491) time: 0.0866 data: 0.0002 max mem: 8255 +Train: [48] [5900/6250] eta: 0:00:48 lr: 0.000070 grad: 0.0905 (0.0964) loss: 0.8534 (0.8490) time: 0.1391 data: 0.0665 max mem: 8255 +Train: [48] [6000/6250] eta: 0:00:34 lr: 0.000070 grad: 0.0884 (0.0964) loss: 0.8546 (0.8490) time: 0.1739 data: 0.1083 max mem: 8255 +Train: [48] [6100/6250] eta: 0:00:20 lr: 0.000070 grad: 0.0949 (0.0965) loss: 0.8449 (0.8490) time: 0.1335 data: 0.0557 max mem: 8255 +Train: [48] [6200/6250] eta: 0:00:06 lr: 0.000070 grad: 0.0975 (0.0965) loss: 0.8436 (0.8490) time: 0.1247 data: 0.0508 max mem: 8255 +Train: [48] [6249/6250] eta: 0:00:00 lr: 0.000070 grad: 0.0934 (0.0965) loss: 0.8477 (0.8489) time: 0.1385 data: 0.0651 max mem: 8255 +Train: [48] Total time: 0:14:22 (0.1379 s / it) +Averaged stats: lr: 0.000070 grad: 0.0934 (0.0965) loss: 0.8477 (0.8489) +Eval (hcp-train-subset): [48] [ 0/62] eta: 0:04:19 loss: 0.8880 (0.8880) time: 4.1820 data: 4.1033 max mem: 8255 +Eval (hcp-train-subset): [48] [61/62] eta: 0:00:00 loss: 0.8752 (0.8774) time: 0.1293 data: 0.1085 max mem: 8255 +Eval (hcp-train-subset): [48] Total time: 0:00:12 (0.2080 s / it) +Averaged stats (hcp-train-subset): loss: 0.8752 (0.8774) +Eval (hcp-val): [48] [ 0/62] eta: 0:03:36 loss: 0.8748 (0.8748) time: 3.4972 data: 3.3884 max mem: 8255 +Eval (hcp-val): [48] [61/62] eta: 0:00:00 loss: 0.8765 (0.8786) time: 0.1240 data: 0.1036 max mem: 8255 +Eval (hcp-val): [48] Total time: 0:00:12 (0.2056 s / it) +Averaged stats (hcp-val): loss: 0.8765 (0.8786) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +Train: [49] [ 0/6250] eta: 8:40:52 lr: 0.000070 grad: 0.1141 (0.1141) loss: 0.9189 (0.9189) time: 5.0003 data: 4.8706 max mem: 8255 +Train: [49] [ 100/6250] eta: 0:18:47 lr: 0.000070 grad: 0.0880 (0.0982) loss: 0.8737 (0.8807) time: 0.1460 data: 0.0642 max mem: 8255 +Train: [49] [ 200/6250] eta: 0:15:46 lr: 0.000070 grad: 0.0821 (0.0968) loss: 0.8657 (0.8734) time: 0.1204 data: 0.0302 max mem: 8255 +Train: [49] [ 300/6250] eta: 0:14:23 lr: 0.000070 grad: 0.0908 (0.0946) loss: 0.8587 (0.8703) time: 0.1104 data: 0.0296 max mem: 8255 +Train: [49] [ 400/6250] eta: 0:13:31 lr: 0.000070 grad: 0.0884 (0.0942) loss: 0.8476 (0.8669) time: 0.1173 data: 0.0367 max mem: 8255 +Train: [49] [ 500/6250] eta: 0:12:52 lr: 0.000070 grad: 0.0860 (0.0945) loss: 0.8524 (0.8643) time: 0.1109 data: 0.0404 max mem: 8255 +Train: [49] [ 600/6250] eta: 0:12:24 lr: 0.000070 grad: 0.0892 (0.0942) loss: 0.8451 (0.8621) time: 0.1368 data: 0.0546 max mem: 8255 +Train: [49] [ 700/6250] eta: 0:11:58 lr: 0.000069 grad: 0.0918 (0.0947) loss: 0.8487 (0.8602) time: 0.1039 data: 0.0331 max mem: 8255 +Train: [49] [ 800/6250] eta: 0:11:36 lr: 0.000069 grad: 0.0924 (0.0948) loss: 0.8476 (0.8585) time: 0.1206 data: 0.0466 max mem: 8255 +Train: [49] [ 900/6250] eta: 0:11:27 lr: 0.000069 grad: 0.0927 (0.0947) loss: 0.8435 (0.8575) time: 0.1232 data: 0.0420 max mem: 8255 +Train: [49] [1000/6250] eta: 0:11:13 lr: 0.000069 grad: 0.0944 (0.0949) loss: 0.8439 (0.8564) time: 0.1212 data: 0.0394 max mem: 8255 +Train: [49] [1100/6250] eta: 0:10:59 lr: 0.000069 grad: 0.0906 (0.0949) loss: 0.8507 (0.8556) time: 0.1299 data: 0.0545 max mem: 8255 +Train: [49] [1200/6250] eta: 0:10:50 lr: 0.000069 grad: 0.0936 (0.0951) loss: 0.8373 (0.8547) time: 0.1151 data: 0.0344 max mem: 8255 +Train: [49] [1300/6250] eta: 0:10:39 lr: 0.000069 grad: 0.0995 (0.0952) loss: 0.8384 (0.8540) time: 0.1524 data: 0.0846 max mem: 8255 +Train: [49] [1400/6250] eta: 0:10:27 lr: 0.000069 grad: 0.0949 (0.0951) loss: 0.8467 (0.8533) time: 0.1400 data: 0.0695 max mem: 8255 +Train: [49] [1500/6250] eta: 0:10:17 lr: 0.000069 grad: 0.0914 (0.0951) loss: 0.8566 (0.8529) time: 0.1516 data: 0.0758 max mem: 8255 +Train: [49] [1600/6250] eta: 0:10:05 lr: 0.000069 grad: 0.0929 (0.0951) loss: 0.8377 (0.8523) time: 0.1244 data: 0.0580 max mem: 8255 +Train: [49] [1700/6250] eta: 0:09:53 lr: 0.000069 grad: 0.0938 (0.0952) loss: 0.8472 (0.8517) time: 0.1401 data: 0.0642 max mem: 8255 +Train: [49] [1800/6250] eta: 0:09:44 lr: 0.000069 grad: 0.0897 (0.0954) loss: 0.8499 (0.8515) time: 0.1816 data: 0.1188 max mem: 8255 +Train: [49] [1900/6250] eta: 0:09:34 lr: 0.000069 grad: 0.0931 (0.0954) loss: 0.8470 (0.8512) time: 0.1405 data: 0.0729 max mem: 8255 +Train: [49] [2000/6250] eta: 0:09:23 lr: 0.000069 grad: 0.0932 (0.0953) loss: 0.8432 (0.8510) time: 0.1338 data: 0.0605 max mem: 8255 +Train: [49] [2100/6250] eta: 0:09:12 lr: 0.000069 grad: 0.0917 (0.0953) loss: 0.8536 (0.8509) time: 0.1449 data: 0.0732 max mem: 8255 +Train: [49] [2200/6250] eta: 0:08:59 lr: 0.000069 grad: 0.0927 (0.0953) loss: 0.8478 (0.8508) time: 0.1342 data: 0.0626 max mem: 8255 +Train: [49] [2300/6250] eta: 0:08:44 lr: 0.000069 grad: 0.0931 (0.0953) loss: 0.8431 (0.8507) time: 0.1070 data: 0.0294 max mem: 8255 +Train: [49] [2400/6250] eta: 0:08:29 lr: 0.000069 grad: 0.0932 (0.0952) loss: 0.8421 (0.8505) time: 0.1068 data: 0.0344 max mem: 8255 +Train: [49] [2500/6250] eta: 0:08:13 lr: 0.000069 grad: 0.0956 (0.0953) loss: 0.8438 (0.8504) time: 0.1201 data: 0.0480 max mem: 8255 +Train: [49] [2600/6250] eta: 0:07:57 lr: 0.000069 grad: 0.0955 (0.0952) loss: 0.8432 (0.8503) time: 0.1240 data: 0.0485 max mem: 8255 +Train: [49] [2700/6250] eta: 0:07:42 lr: 0.000069 grad: 0.0927 (0.0951) loss: 0.8452 (0.8503) time: 0.1174 data: 0.0447 max mem: 8255 +Train: [49] [2800/6250] eta: 0:07:28 lr: 0.000069 grad: 0.0916 (0.0950) loss: 0.8455 (0.8503) time: 0.1190 data: 0.0403 max mem: 8255 +Train: [49] [2900/6250] eta: 0:07:14 lr: 0.000069 grad: 0.0889 (0.0950) loss: 0.8516 (0.8503) time: 0.1293 data: 0.0582 max mem: 8255 +Train: [49] [3000/6250] eta: 0:07:01 lr: 0.000069 grad: 0.0933 (0.0949) loss: 0.8416 (0.8503) time: 0.1116 data: 0.0337 max mem: 8255 +Train: [49] [3100/6250] eta: 0:06:48 lr: 0.000069 grad: 0.0900 (0.0948) loss: 0.8449 (0.8502) time: 0.1401 data: 0.0657 max mem: 8255 +Train: [49] [3200/6250] eta: 0:06:35 lr: 0.000069 grad: 0.0941 (0.0948) loss: 0.8527 (0.8501) time: 0.1182 data: 0.0471 max mem: 8255 +Train: [49] [3300/6250] eta: 0:06:25 lr: 0.000069 grad: 0.0858 (0.0947) loss: 0.8558 (0.8502) time: 0.1439 data: 0.0699 max mem: 8255 +Train: [49] [3400/6250] eta: 0:06:12 lr: 0.000069 grad: 0.0930 (0.0946) loss: 0.8494 (0.8502) time: 0.1283 data: 0.0522 max mem: 8255 +Train: [49] [3500/6250] eta: 0:05:58 lr: 0.000069 grad: 0.0908 (0.0945) loss: 0.8510 (0.8502) time: 0.1339 data: 0.0567 max mem: 8255 +Train: [49] [3600/6250] eta: 0:05:46 lr: 0.000069 grad: 0.0860 (0.0945) loss: 0.8559 (0.8503) time: 0.1111 data: 0.0406 max mem: 8255 +Train: [49] [3700/6250] eta: 0:05:32 lr: 0.000069 grad: 0.0921 (0.0946) loss: 0.8514 (0.8503) time: 0.1265 data: 0.0536 max mem: 8255 +Train: [49] [3800/6250] eta: 0:05:19 lr: 0.000068 grad: 0.0863 (0.0947) loss: 0.8573 (0.8503) time: 0.1245 data: 0.0539 max mem: 8255 +Train: [49] [3900/6250] eta: 0:05:06 lr: 0.000068 grad: 0.0864 (0.0947) loss: 0.8597 (0.8503) time: 0.1535 data: 0.0738 max mem: 8255 +Train: [49] [4000/6250] eta: 0:04:53 lr: 0.000068 grad: 0.0923 (0.0947) loss: 0.8548 (0.8503) time: 0.1256 data: 0.0559 max mem: 8255 +Train: [49] [4100/6250] eta: 0:04:41 lr: 0.000068 grad: 0.0893 (0.0948) loss: 0.8607 (0.8503) time: 0.1710 data: 0.0994 max mem: 8255 +Train: [49] [4200/6250] eta: 0:04:28 lr: 0.000068 grad: 0.0936 (0.0948) loss: 0.8493 (0.8502) time: 0.1701 data: 0.1087 max mem: 8255 +Train: [49] [4300/6250] eta: 0:04:15 lr: 0.000068 grad: 0.0938 (0.0948) loss: 0.8519 (0.8501) time: 0.1259 data: 0.0565 max mem: 8255 +Train: [49] [4400/6250] eta: 0:04:01 lr: 0.000068 grad: 0.0875 (0.0948) loss: 0.8525 (0.8501) time: 0.1298 data: 0.0578 max mem: 8255 +Train: [49] [4500/6250] eta: 0:03:48 lr: 0.000068 grad: 0.0932 (0.0947) loss: 0.8478 (0.8501) time: 0.1223 data: 0.0537 max mem: 8255 +Train: [49] [4600/6250] eta: 0:03:35 lr: 0.000068 grad: 0.0894 (0.0947) loss: 0.8532 (0.8502) time: 0.0960 data: 0.0256 max mem: 8255 +Train: [49] [4700/6250] eta: 0:03:23 lr: 0.000068 grad: 0.0895 (0.0947) loss: 0.8590 (0.8502) time: 0.1294 data: 0.0601 max mem: 8255 +Train: [49] [4800/6250] eta: 0:03:09 lr: 0.000068 grad: 0.0926 (0.0947) loss: 0.8511 (0.8502) time: 0.1393 data: 0.0714 max mem: 8255 +Train: [49] [4900/6250] eta: 0:02:57 lr: 0.000068 grad: 0.0949 (0.0947) loss: 0.8502 (0.8502) time: 0.1291 data: 0.0537 max mem: 8255 +Train: [49] [5000/6250] eta: 0:02:43 lr: 0.000068 grad: 0.0942 (0.0947) loss: 0.8500 (0.8502) time: 0.1190 data: 0.0467 max mem: 8255 +Train: [49] [5100/6250] eta: 0:02:31 lr: 0.000068 grad: 0.0938 (0.0947) loss: 0.8325 (0.8501) time: 0.2129 data: 0.1382 max mem: 8255 +Train: [49] [5200/6250] eta: 0:02:18 lr: 0.000068 grad: 0.0908 (0.0947) loss: 0.8432 (0.8500) time: 0.0906 data: 0.0002 max mem: 8255 +Train: [49] [5300/6250] eta: 0:02:04 lr: 0.000068 grad: 0.0868 (0.0947) loss: 0.8492 (0.8499) time: 0.1237 data: 0.0438 max mem: 8255 +Train: [49] [5400/6250] eta: 0:01:51 lr: 0.000068 grad: 0.1032 (0.0948) loss: 0.8356 (0.8497) time: 0.1195 data: 0.0465 max mem: 8255 +Train: [49] [5500/6250] eta: 0:01:38 lr: 0.000068 grad: 0.0937 (0.0949) loss: 0.8418 (0.8496) time: 0.1259 data: 0.0601 max mem: 8255 +Train: [49] [5600/6250] eta: 0:01:25 lr: 0.000068 grad: 0.0974 (0.0950) loss: 0.8501 (0.8495) time: 0.1221 data: 0.0550 max mem: 8255 +Train: [49] [5700/6250] eta: 0:01:12 lr: 0.000068 grad: 0.0939 (0.0950) loss: 0.8467 (0.8494) time: 0.1152 data: 0.0496 max mem: 8255 +Train: [49] [5800/6250] eta: 0:00:59 lr: 0.000068 grad: 0.0909 (0.0951) loss: 0.8533 (0.8493) time: 0.1595 data: 0.0842 max mem: 8255 +Train: [49] [5900/6250] eta: 0:00:45 lr: 0.000068 grad: 0.0945 (0.0951) loss: 0.8389 (0.8492) time: 0.1259 data: 0.0613 max mem: 8255 +Train: [49] [6000/6250] eta: 0:00:32 lr: 0.000068 grad: 0.0947 (0.0952) loss: 0.8475 (0.8491) time: 0.1192 data: 0.0459 max mem: 8255 +Train: [49] [6100/6250] eta: 0:00:19 lr: 0.000068 grad: 0.0915 (0.0952) loss: 0.8458 (0.8490) time: 0.1172 data: 0.0484 max mem: 8255 +Train: [49] [6200/6250] eta: 0:00:06 lr: 0.000068 grad: 0.0970 (0.0953) loss: 0.8534 (0.8489) time: 0.1282 data: 0.0594 max mem: 8255 +Train: [49] [6249/6250] eta: 0:00:00 lr: 0.000068 grad: 0.1008 (0.0954) loss: 0.8425 (0.8489) time: 0.1192 data: 0.0500 max mem: 8255 +Train: [49] Total time: 0:13:45 (0.1320 s / it) +Averaged stats: lr: 0.000068 grad: 0.1008 (0.0954) loss: 0.8425 (0.8489) +Eval (hcp-train-subset): [49] [ 0/62] eta: 0:04:30 loss: 0.8801 (0.8801) time: 4.3661 data: 4.2755 max mem: 8255 +Eval (hcp-train-subset): [49] [61/62] eta: 0:00:00 loss: 0.8739 (0.8756) time: 0.1436 data: 0.1229 max mem: 8255 +Eval (hcp-train-subset): [49] Total time: 0:00:13 (0.2111 s / it) +Averaged stats (hcp-train-subset): loss: 0.8739 (0.8756) +Making plots (hcp-train-subset): example=33 +Eval (hcp-val): [49] [ 0/62] eta: 0:05:20 loss: 0.8732 (0.8732) time: 5.1624 data: 5.1163 max mem: 8255 +Eval (hcp-val): [49] [61/62] eta: 0:00:00 loss: 0.8773 (0.8793) time: 0.1098 data: 0.0877 max mem: 8255 +Eval (hcp-val): [49] Total time: 0:00:13 (0.2110 s / it) +Averaged stats (hcp-val): loss: 0.8773 (0.8793) +Making plots (hcp-val): example=47 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +Train: [50] [ 0/6250] eta: 7:41:23 lr: 0.000068 grad: 0.0993 (0.0993) loss: 0.8601 (0.8601) time: 4.4293 data: 4.2424 max mem: 8255 +Train: [50] [ 100/6250] eta: 0:18:47 lr: 0.000068 grad: 0.0897 (0.1248) loss: 0.8674 (0.8697) time: 0.1407 data: 0.0524 max mem: 8255 +Train: [50] [ 200/6250] eta: 0:16:03 lr: 0.000068 grad: 0.0924 (0.1176) loss: 0.8496 (0.8621) time: 0.1284 data: 0.0469 max mem: 8255 +Train: [50] [ 300/6250] eta: 0:14:41 lr: 0.000068 grad: 0.0941 (0.1107) loss: 0.8579 (0.8596) time: 0.1115 data: 0.0263 max mem: 8255 +Train: [50] [ 400/6250] eta: 0:13:49 lr: 0.000068 grad: 0.0932 (0.1071) loss: 0.8589 (0.8582) time: 0.1057 data: 0.0315 max mem: 8255 +Train: [50] [ 500/6250] eta: 0:13:03 lr: 0.000067 grad: 0.0976 (0.1045) loss: 0.8466 (0.8565) time: 0.1062 data: 0.0265 max mem: 8255 +Train: [50] [ 600/6250] eta: 0:12:32 lr: 0.000067 grad: 0.0931 (0.1024) loss: 0.8449 (0.8557) time: 0.1259 data: 0.0519 max mem: 8255 +Train: [50] [ 700/6250] eta: 0:12:05 lr: 0.000067 grad: 0.0849 (0.1008) loss: 0.8522 (0.8554) time: 0.1238 data: 0.0491 max mem: 8255 +Train: [50] [ 800/6250] eta: 0:11:48 lr: 0.000067 grad: 0.0867 (0.0993) loss: 0.8557 (0.8553) time: 0.1492 data: 0.0786 max mem: 8255 +Train: [50] [ 900/6250] eta: 0:11:39 lr: 0.000067 grad: 0.0891 (0.0985) loss: 0.8461 (0.8550) time: 0.1328 data: 0.0611 max mem: 8255 +Train: [50] [1000/6250] eta: 0:11:26 lr: 0.000067 grad: 0.0856 (0.0979) loss: 0.8563 (0.8545) time: 0.1297 data: 0.0590 max mem: 8255 +Train: [50] [1100/6250] eta: 0:11:14 lr: 0.000067 grad: 0.0835 (0.0972) loss: 0.8553 (0.8541) time: 0.1306 data: 0.0564 max mem: 8255 +Train: [50] [1200/6250] eta: 0:11:06 lr: 0.000067 grad: 0.0861 (0.0966) loss: 0.8494 (0.8537) time: 0.1364 data: 0.0697 max mem: 8255 +Train: [50] [1300/6250] eta: 0:10:52 lr: 0.000067 grad: 0.0875 (0.0961) loss: 0.8493 (0.8533) time: 0.1274 data: 0.0444 max mem: 8255 +Train: [50] [1400/6250] eta: 0:10:38 lr: 0.000067 grad: 0.0865 (0.0957) loss: 0.8512 (0.8531) time: 0.1421 data: 0.0739 max mem: 8255 +Train: [50] [1500/6250] eta: 0:10:27 lr: 0.000067 grad: 0.0859 (0.0954) loss: 0.8506 (0.8527) time: 0.1236 data: 0.0503 max mem: 8255 +Train: [50] [1600/6250] eta: 0:10:14 lr: 0.000067 grad: 0.0875 (0.0952) loss: 0.8515 (0.8526) time: 0.1506 data: 0.0754 max mem: 8255 +Train: [50] [1700/6250] eta: 0:09:58 lr: 0.000067 grad: 0.0887 (0.0951) loss: 0.8455 (0.8522) time: 0.1151 data: 0.0451 max mem: 8255 +Train: [50] [1800/6250] eta: 0:09:46 lr: 0.000067 grad: 0.0899 (0.0950) loss: 0.8465 (0.8519) time: 0.1390 data: 0.0732 max mem: 8255 +Train: [50] [1900/6250] eta: 0:09:33 lr: 0.000067 grad: 0.0900 (0.0949) loss: 0.8476 (0.8516) time: 0.1522 data: 0.0878 max mem: 8255 +Train: [50] [2000/6250] eta: 0:09:24 lr: 0.000067 grad: 0.0976 (0.0950) loss: 0.8415 (0.8514) time: 0.1601 data: 0.0816 max mem: 8255 +Train: [50] [2100/6250] eta: 0:09:13 lr: 0.000067 grad: 0.0908 (0.0949) loss: 0.8405 (0.8513) time: 0.1455 data: 0.0705 max mem: 8255 +Train: [50] [2200/6250] eta: 0:09:01 lr: 0.000067 grad: 0.0900 (0.0949) loss: 0.8523 (0.8511) time: 0.1643 data: 0.0906 max mem: 8255 +Train: [50] [2300/6250] eta: 0:08:49 lr: 0.000067 grad: 0.0888 (0.0948) loss: 0.8509 (0.8510) time: 0.1410 data: 0.0739 max mem: 8255 +Train: [50] [2400/6250] eta: 0:08:36 lr: 0.000067 grad: 0.0907 (0.0947) loss: 0.8506 (0.8510) time: 0.1313 data: 0.0541 max mem: 8255 +Train: [50] [2500/6250] eta: 0:08:23 lr: 0.000067 grad: 0.0857 (0.0945) loss: 0.8574 (0.8510) time: 0.1372 data: 0.0674 max mem: 8255 +Train: [50] [2600/6250] eta: 0:08:09 lr: 0.000067 grad: 0.0889 (0.0944) loss: 0.8518 (0.8510) time: 0.1246 data: 0.0569 max mem: 8255 +Train: [50] [2700/6250] eta: 0:07:55 lr: 0.000067 grad: 0.0945 (0.0945) loss: 0.8474 (0.8510) time: 0.1186 data: 0.0397 max mem: 8255 +Train: [50] [2800/6250] eta: 0:07:40 lr: 0.000067 grad: 0.0904 (0.0944) loss: 0.8473 (0.8511) time: 0.1222 data: 0.0578 max mem: 8255 +Train: [50] [2900/6250] eta: 0:07:29 lr: 0.000067 grad: 0.0879 (0.0945) loss: 0.8603 (0.8511) time: 0.1968 data: 0.0857 max mem: 8255 +Train: [50] [3000/6250] eta: 0:07:18 lr: 0.000067 grad: 0.0903 (0.0944) loss: 0.8522 (0.8511) time: 0.0859 data: 0.0002 max mem: 8255 +Train: [50] [3100/6250] eta: 0:07:07 lr: 0.000067 grad: 0.0881 (0.0943) loss: 0.8471 (0.8510) time: 0.1581 data: 0.0975 max mem: 8255 +Train: [50] [3200/6250] eta: 0:06:56 lr: 0.000067 grad: 0.0924 (0.0943) loss: 0.8470 (0.8509) time: 0.1505 data: 0.0826 max mem: 8255 +Train: [50] [3300/6250] eta: 0:06:45 lr: 0.000067 grad: 0.0949 (0.0943) loss: 0.8522 (0.8509) time: 0.1705 data: 0.1056 max mem: 8255 +Train: [50] [3400/6250] eta: 0:06:33 lr: 0.000067 grad: 0.0954 (0.0944) loss: 0.8466 (0.8508) time: 0.1478 data: 0.0792 max mem: 8255 +Train: [50] [3500/6250] eta: 0:06:21 lr: 0.000067 grad: 0.0915 (0.0944) loss: 0.8573 (0.8508) time: 0.1688 data: 0.1065 max mem: 8255 +Train: [50] [3600/6250] eta: 0:06:08 lr: 0.000066 grad: 0.0925 (0.0944) loss: 0.8405 (0.8508) time: 0.1309 data: 0.0605 max mem: 8255 +Train: [50] [3700/6250] eta: 0:05:55 lr: 0.000066 grad: 0.0870 (0.0944) loss: 0.8519 (0.8507) time: 0.1384 data: 0.0712 max mem: 8255 +Train: [50] [3800/6250] eta: 0:05:41 lr: 0.000066 grad: 0.0965 (0.0945) loss: 0.8491 (0.8507) time: 0.1241 data: 0.0482 max mem: 8255 +Train: [50] [3900/6250] eta: 0:05:26 lr: 0.000066 grad: 0.0939 (0.0945) loss: 0.8479 (0.8506) time: 0.1612 data: 0.0941 max mem: 8255 +Train: [50] [4000/6250] eta: 0:05:12 lr: 0.000066 grad: 0.0914 (0.0945) loss: 0.8545 (0.8507) time: 0.1302 data: 0.0600 max mem: 8255 +Train: [50] [4100/6250] eta: 0:04:58 lr: 0.000066 grad: 0.0977 (0.0944) loss: 0.8440 (0.8506) time: 0.1404 data: 0.0683 max mem: 8255 +Train: [50] [4200/6250] eta: 0:04:45 lr: 0.000066 grad: 0.0911 (0.0945) loss: 0.8516 (0.8506) time: 0.1043 data: 0.0104 max mem: 8255 +Train: [50] [4300/6250] eta: 0:04:31 lr: 0.000066 grad: 0.0918 (0.0944) loss: 0.8592 (0.8507) time: 0.1247 data: 0.0585 max mem: 8255 +Train: [50] [4400/6250] eta: 0:04:17 lr: 0.000066 grad: 0.0914 (0.0944) loss: 0.8609 (0.8508) time: 0.1331 data: 0.0575 max mem: 8255 +Train: [50] [4500/6250] eta: 0:04:04 lr: 0.000066 grad: 0.0946 (0.0945) loss: 0.8483 (0.8508) time: 0.1410 data: 0.0670 max mem: 8255 +Train: [50] [4600/6250] eta: 0:03:50 lr: 0.000066 grad: 0.0902 (0.0945) loss: 0.8532 (0.8508) time: 0.1349 data: 0.0647 max mem: 8255 +Train: [50] [4700/6250] eta: 0:03:36 lr: 0.000066 grad: 0.0869 (0.0945) loss: 0.8532 (0.8509) time: 0.1073 data: 0.0388 max mem: 8255 +Train: [50] [4800/6250] eta: 0:03:22 lr: 0.000066 grad: 0.0893 (0.0945) loss: 0.8562 (0.8510) time: 0.1283 data: 0.0507 max mem: 8255 +Train: [50] [4900/6250] eta: 0:03:07 lr: 0.000066 grad: 0.0990 (0.0945) loss: 0.8492 (0.8509) time: 0.1249 data: 0.0543 max mem: 8255 +Train: [50] [5000/6250] eta: 0:02:53 lr: 0.000066 grad: 0.0941 (0.0946) loss: 0.8493 (0.8509) time: 0.1493 data: 0.0804 max mem: 8255 +Train: [50] [5100/6250] eta: 0:02:39 lr: 0.000066 grad: 0.0972 (0.0947) loss: 0.8540 (0.8509) time: 0.1423 data: 0.0719 max mem: 8255 +Train: [50] [5200/6250] eta: 0:02:25 lr: 0.000066 grad: 0.0904 (0.0947) loss: 0.8521 (0.8509) time: 0.1176 data: 0.0497 max mem: 8255 +Train: [50] [5300/6250] eta: 0:02:11 lr: 0.000066 grad: 0.0885 (0.0947) loss: 0.8577 (0.8509) time: 0.1127 data: 0.0368 max mem: 8255 +Train: [50] [5400/6250] eta: 0:01:57 lr: 0.000066 grad: 0.0966 (0.0948) loss: 0.8455 (0.8509) time: 0.1201 data: 0.0504 max mem: 8255 +Train: [50] [5500/6250] eta: 0:01:43 lr: 0.000066 grad: 0.0947 (0.0948) loss: 0.8434 (0.8509) time: 0.1284 data: 0.0580 max mem: 8255 +Train: [50] [5600/6250] eta: 0:01:29 lr: 0.000066 grad: 0.0970 (0.0948) loss: 0.8508 (0.8509) time: 0.1314 data: 0.0599 max mem: 8255 +Train: [50] [5700/6250] eta: 0:01:15 lr: 0.000066 grad: 0.0939 (0.0948) loss: 0.8513 (0.8508) time: 0.1624 data: 0.0948 max mem: 8255 +Train: [50] [5800/6250] eta: 0:01:01 lr: 0.000066 grad: 0.0930 (0.0949) loss: 0.8500 (0.8507) time: 0.1402 data: 0.0670 max mem: 8255 +Train: [50] [5900/6250] eta: 0:00:48 lr: 0.000066 grad: 0.0947 (0.0949) loss: 0.8508 (0.8507) time: 0.1308 data: 0.0667 max mem: 8255 +Train: [50] [6000/6250] eta: 0:00:34 lr: 0.000066 grad: 0.1009 (0.0950) loss: 0.8404 (0.8507) time: 0.1345 data: 0.0718 max mem: 8255 +Train: [50] [6100/6250] eta: 0:00:20 lr: 0.000066 grad: 0.1017 (0.0950) loss: 0.8355 (0.8506) time: 0.1301 data: 0.0626 max mem: 8255 +Train: [50] [6200/6250] eta: 0:00:06 lr: 0.000066 grad: 0.0943 (0.0951) loss: 0.8557 (0.8505) time: 0.2181 data: 0.1485 max mem: 8255 +Train: [50] [6249/6250] eta: 0:00:00 lr: 0.000066 grad: 0.0993 (0.0951) loss: 0.8527 (0.8505) time: 0.1596 data: 0.0880 max mem: 8255 +Train: [50] Total time: 0:14:24 (0.1384 s / it) +Averaged stats: lr: 0.000066 grad: 0.0993 (0.0951) loss: 0.8527 (0.8505) +Eval (hcp-train-subset): [50] [ 0/62] eta: 0:04:43 loss: 0.8795 (0.8795) time: 4.5692 data: 4.5426 max mem: 8255 +Eval (hcp-train-subset): [50] [61/62] eta: 0:00:00 loss: 0.8708 (0.8741) time: 0.1157 data: 0.0950 max mem: 8255 +Eval (hcp-train-subset): [50] Total time: 0:00:12 (0.2061 s / it) +Averaged stats (hcp-train-subset): loss: 0.8708 (0.8741) +Eval (hcp-val): [50] [ 0/62] eta: 0:05:44 loss: 0.8759 (0.8759) time: 5.5638 data: 5.5386 max mem: 8255 +Eval (hcp-val): [50] [61/62] eta: 0:00:00 loss: 0.8780 (0.8789) time: 0.1275 data: 0.1072 max mem: 8255 +Eval (hcp-val): [50] Total time: 0:00:14 (0.2292 s / it) +Averaged stats (hcp-val): loss: 0.8780 (0.8789) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +Train: [51] [ 0/6250] eta: 7:30:21 lr: 0.000066 grad: 0.0910 (0.0910) loss: 0.8779 (0.8779) time: 4.3235 data: 4.1434 max mem: 8255 +Train: [51] [ 100/6250] eta: 0:20:51 lr: 0.000066 grad: 0.1034 (0.1230) loss: 0.8495 (0.8663) time: 0.1572 data: 0.0619 max mem: 8255 +Train: [51] [ 200/6250] eta: 0:17:48 lr: 0.000066 grad: 0.0887 (0.1117) loss: 0.8704 (0.8629) time: 0.1372 data: 0.0500 max mem: 8255 +Train: [51] [ 300/6250] eta: 0:16:22 lr: 0.000065 grad: 0.0847 (0.1047) loss: 0.8529 (0.8633) time: 0.1362 data: 0.0699 max mem: 8255 +Train: [51] [ 400/6250] eta: 0:15:24 lr: 0.000065 grad: 0.0831 (0.1003) loss: 0.8639 (0.8627) time: 0.1486 data: 0.0736 max mem: 8255 +Train: [51] [ 500/6250] eta: 0:14:40 lr: 0.000065 grad: 0.0907 (0.0986) loss: 0.8602 (0.8627) time: 0.1406 data: 0.0643 max mem: 8255 +Train: [51] [ 600/6250] eta: 0:14:02 lr: 0.000065 grad: 0.0882 (0.0972) loss: 0.8634 (0.8624) time: 0.1443 data: 0.0773 max mem: 8255 +Train: [51] [ 700/6250] eta: 0:13:40 lr: 0.000065 grad: 0.0940 (0.0966) loss: 0.8527 (0.8617) time: 0.1490 data: 0.0772 max mem: 8255 +Train: [51] [ 800/6250] eta: 0:13:23 lr: 0.000065 grad: 0.0850 (0.0962) loss: 0.8593 (0.8607) time: 0.2161 data: 0.1224 max mem: 8255 +Train: [51] [ 900/6250] eta: 0:13:10 lr: 0.000065 grad: 0.0850 (0.0960) loss: 0.8599 (0.8600) time: 0.2202 data: 0.1344 max mem: 8255 +Train: [51] [1000/6250] eta: 0:12:53 lr: 0.000065 grad: 0.0913 (0.0959) loss: 0.8556 (0.8594) time: 0.1399 data: 0.0652 max mem: 8255 +Train: [51] [1100/6250] eta: 0:12:43 lr: 0.000065 grad: 0.0899 (0.0956) loss: 0.8502 (0.8591) time: 0.1958 data: 0.1326 max mem: 8255 +Train: [51] [1200/6250] eta: 0:12:31 lr: 0.000065 grad: 0.0872 (0.0951) loss: 0.8509 (0.8586) time: 0.1371 data: 0.0625 max mem: 8255 +Train: [51] [1300/6250] eta: 0:12:12 lr: 0.000065 grad: 0.0889 (0.0951) loss: 0.8479 (0.8579) time: 0.1276 data: 0.0555 max mem: 8255 +Train: [51] [1400/6250] eta: 0:11:58 lr: 0.000065 grad: 0.0909 (0.0949) loss: 0.8507 (0.8574) time: 0.1561 data: 0.0930 max mem: 8255 +Train: [51] [1500/6250] eta: 0:11:43 lr: 0.000065 grad: 0.0917 (0.0946) loss: 0.8536 (0.8569) time: 0.1274 data: 0.0496 max mem: 8255 +Train: [51] [1600/6250] eta: 0:11:26 lr: 0.000065 grad: 0.0889 (0.0944) loss: 0.8456 (0.8565) time: 0.1379 data: 0.0691 max mem: 8255 +Train: [51] [1700/6250] eta: 0:11:18 lr: 0.000065 grad: 0.0890 (0.0943) loss: 0.8481 (0.8561) time: 0.2517 data: 0.1879 max mem: 8255 +Train: [51] [1800/6250] eta: 0:10:57 lr: 0.000065 grad: 0.0913 (0.0942) loss: 0.8482 (0.8558) time: 0.1508 data: 0.0802 max mem: 8255 +Train: [51] [1900/6250] eta: 0:10:40 lr: 0.000065 grad: 0.0872 (0.0942) loss: 0.8429 (0.8554) time: 0.1293 data: 0.0611 max mem: 8255 +Train: [51] [2000/6250] eta: 0:10:25 lr: 0.000065 grad: 0.0917 (0.0941) loss: 0.8510 (0.8551) time: 0.1550 data: 0.0927 max mem: 8255 +Train: [51] [2100/6250] eta: 0:10:10 lr: 0.000065 grad: 0.0975 (0.0941) loss: 0.8425 (0.8548) time: 0.1663 data: 0.0991 max mem: 8255 +Train: [51] [2200/6250] eta: 0:09:51 lr: 0.000065 grad: 0.0931 (0.0941) loss: 0.8482 (0.8546) time: 0.1345 data: 0.0673 max mem: 8255 +Train: [51] [2300/6250] eta: 0:09:36 lr: 0.000065 grad: 0.0921 (0.0943) loss: 0.8464 (0.8543) time: 0.1308 data: 0.0604 max mem: 8255 +Train: [51] [2400/6250] eta: 0:09:20 lr: 0.000065 grad: 0.0887 (0.0943) loss: 0.8541 (0.8540) time: 0.1445 data: 0.0749 max mem: 8255 +Train: [51] [2500/6250] eta: 0:09:05 lr: 0.000065 grad: 0.0899 (0.0944) loss: 0.8450 (0.8538) time: 0.1384 data: 0.0737 max mem: 8255 +Train: [51] [2600/6250] eta: 0:08:50 lr: 0.000065 grad: 0.0957 (0.0944) loss: 0.8523 (0.8536) time: 0.1886 data: 0.1218 max mem: 8255 +Train: [51] [2700/6250] eta: 0:08:31 lr: 0.000065 grad: 0.0907 (0.0945) loss: 0.8441 (0.8534) time: 0.1223 data: 0.0461 max mem: 8255 +Train: [51] [2800/6250] eta: 0:08:13 lr: 0.000065 grad: 0.0987 (0.0945) loss: 0.8378 (0.8531) time: 0.1104 data: 0.0334 max mem: 8255 +Train: [51] [2900/6250] eta: 0:07:56 lr: 0.000065 grad: 0.0913 (0.0946) loss: 0.8359 (0.8529) time: 0.1079 data: 0.0276 max mem: 8255 +Train: [51] [3000/6250] eta: 0:07:39 lr: 0.000065 grad: 0.0864 (0.0946) loss: 0.8542 (0.8526) time: 0.0937 data: 0.0227 max mem: 8255 +Train: [51] [3100/6250] eta: 0:07:22 lr: 0.000065 grad: 0.0929 (0.0946) loss: 0.8409 (0.8525) time: 0.1187 data: 0.0548 max mem: 8255 +Train: [51] [3200/6250] eta: 0:07:05 lr: 0.000065 grad: 0.0873 (0.0945) loss: 0.8512 (0.8524) time: 0.1184 data: 0.0467 max mem: 8255 +Train: [51] [3300/6250] eta: 0:06:50 lr: 0.000065 grad: 0.0929 (0.0945) loss: 0.8433 (0.8522) time: 0.1171 data: 0.0440 max mem: 8255 +Train: [51] [3400/6250] eta: 0:06:35 lr: 0.000064 grad: 0.0888 (0.0946) loss: 0.8462 (0.8521) time: 0.1300 data: 0.0644 max mem: 8255 +Train: [51] [3500/6250] eta: 0:06:20 lr: 0.000064 grad: 0.0938 (0.0947) loss: 0.8517 (0.8519) time: 0.1355 data: 0.0601 max mem: 8255 +Train: [51] [3600/6250] eta: 0:06:06 lr: 0.000064 grad: 0.0921 (0.0948) loss: 0.8492 (0.8518) time: 0.1612 data: 0.1004 max mem: 8255 +Train: [51] [3700/6250] eta: 0:05:51 lr: 0.000064 grad: 0.0972 (0.0949) loss: 0.8482 (0.8516) time: 0.1241 data: 0.0468 max mem: 8255 +Train: [51] [3800/6250] eta: 0:05:37 lr: 0.000064 grad: 0.0906 (0.0949) loss: 0.8502 (0.8515) time: 0.1512 data: 0.0826 max mem: 8255 +Train: [51] [3900/6250] eta: 0:05:23 lr: 0.000064 grad: 0.0938 (0.0949) loss: 0.8536 (0.8514) time: 0.1362 data: 0.0639 max mem: 8255 +Train: [51] [4000/6250] eta: 0:05:09 lr: 0.000064 grad: 0.0986 (0.0950) loss: 0.8454 (0.8513) time: 0.1519 data: 0.0808 max mem: 8255 +Train: [51] [4100/6250] eta: 0:04:55 lr: 0.000064 grad: 0.0966 (0.0951) loss: 0.8469 (0.8512) time: 0.1196 data: 0.0450 max mem: 8255 +Train: [51] [4200/6250] eta: 0:04:41 lr: 0.000064 grad: 0.0967 (0.0953) loss: 0.8430 (0.8511) time: 0.1575 data: 0.0861 max mem: 8255 +Train: [51] [4300/6250] eta: 0:04:28 lr: 0.000064 grad: 0.0950 (0.0953) loss: 0.8418 (0.8510) time: 0.1191 data: 0.0386 max mem: 8255 +Train: [51] [4400/6250] eta: 0:04:14 lr: 0.000064 grad: 0.0916 (0.0954) loss: 0.8487 (0.8509) time: 0.1196 data: 0.0477 max mem: 8255 +Train: [51] [4500/6250] eta: 0:04:00 lr: 0.000064 grad: 0.0974 (0.0954) loss: 0.8456 (0.8508) time: 0.1428 data: 0.0806 max mem: 8255 +Train: [51] [4600/6250] eta: 0:03:46 lr: 0.000064 grad: 0.0986 (0.0954) loss: 0.8512 (0.8507) time: 0.1256 data: 0.0566 max mem: 8255 +Train: [51] [4700/6250] eta: 0:03:32 lr: 0.000064 grad: 0.0940 (0.0955) loss: 0.8452 (0.8506) time: 0.1349 data: 0.0658 max mem: 8255 +Train: [51] [4800/6250] eta: 0:03:18 lr: 0.000064 grad: 0.0935 (0.0955) loss: 0.8460 (0.8505) time: 0.1386 data: 0.0711 max mem: 8255 +Train: [51] [4900/6250] eta: 0:03:04 lr: 0.000064 grad: 0.0904 (0.0955) loss: 0.8488 (0.8504) time: 0.1399 data: 0.0656 max mem: 8255 +Train: [51] [5000/6250] eta: 0:02:50 lr: 0.000064 grad: 0.0881 (0.0955) loss: 0.8518 (0.8504) time: 0.1300 data: 0.0619 max mem: 8255 +Train: [51] [5100/6250] eta: 0:02:36 lr: 0.000064 grad: 0.0951 (0.0955) loss: 0.8466 (0.8503) time: 0.1606 data: 0.0966 max mem: 8255 +Train: [51] [5200/6250] eta: 0:02:23 lr: 0.000064 grad: 0.0915 (0.0955) loss: 0.8420 (0.8502) time: 0.1308 data: 0.0547 max mem: 8255 +Train: [51] [5300/6250] eta: 0:02:09 lr: 0.000064 grad: 0.0964 (0.0955) loss: 0.8440 (0.8501) time: 0.1570 data: 0.0802 max mem: 8255 +Train: [51] [5400/6250] eta: 0:01:55 lr: 0.000064 grad: 0.0934 (0.0956) loss: 0.8457 (0.8500) time: 0.1348 data: 0.0662 max mem: 8255 +Train: [51] [5500/6250] eta: 0:01:42 lr: 0.000064 grad: 0.0932 (0.0956) loss: 0.8512 (0.8499) time: 0.1400 data: 0.0694 max mem: 8255 +Train: [51] [5600/6250] eta: 0:01:28 lr: 0.000064 grad: 0.0979 (0.0957) loss: 0.8493 (0.8499) time: 0.1233 data: 0.0598 max mem: 8255 +Train: [51] [5700/6250] eta: 0:01:15 lr: 0.000064 grad: 0.0943 (0.0957) loss: 0.8453 (0.8498) time: 0.1231 data: 0.0441 max mem: 8255 +Train: [51] [5800/6250] eta: 0:01:01 lr: 0.000064 grad: 0.0989 (0.0958) loss: 0.8461 (0.8498) time: 0.1598 data: 0.0891 max mem: 8255 +Train: [51] [5900/6250] eta: 0:00:47 lr: 0.000064 grad: 0.0923 (0.0958) loss: 0.8485 (0.8497) time: 0.1054 data: 0.0340 max mem: 8255 +Train: [51] [6000/6250] eta: 0:00:34 lr: 0.000064 grad: 0.0980 (0.0959) loss: 0.8449 (0.8497) time: 0.1290 data: 0.0553 max mem: 8255 +Train: [51] [6100/6250] eta: 0:00:20 lr: 0.000064 grad: 0.0950 (0.0959) loss: 0.8435 (0.8496) time: 0.1222 data: 0.0501 max mem: 8255 +Train: [51] [6200/6250] eta: 0:00:06 lr: 0.000064 grad: 0.0952 (0.0959) loss: 0.8434 (0.8496) time: 0.1338 data: 0.0681 max mem: 8255 +Train: [51] [6249/6250] eta: 0:00:00 lr: 0.000064 grad: 0.0964 (0.0960) loss: 0.8443 (0.8496) time: 0.1335 data: 0.0610 max mem: 8255 +Train: [51] Total time: 0:14:17 (0.1373 s / it) +Averaged stats: lr: 0.000064 grad: 0.0964 (0.0960) loss: 0.8443 (0.8496) +Eval (hcp-train-subset): [51] [ 0/62] eta: 0:05:18 loss: 0.8884 (0.8884) time: 5.1441 data: 5.1189 max mem: 8255 +Eval (hcp-train-subset): [51] [61/62] eta: 0:00:00 loss: 0.8727 (0.8743) time: 0.1329 data: 0.1111 max mem: 8255 +Eval (hcp-train-subset): [51] Total time: 0:00:13 (0.2189 s / it) +Averaged stats (hcp-train-subset): loss: 0.8727 (0.8743) +Eval (hcp-val): [51] [ 0/62] eta: 0:03:30 loss: 0.8792 (0.8792) time: 3.3932 data: 3.3144 max mem: 8255 +Eval (hcp-val): [51] [61/62] eta: 0:00:00 loss: 0.8776 (0.8803) time: 0.1329 data: 0.1120 max mem: 8255 +Eval (hcp-val): [51] Total time: 0:00:13 (0.2197 s / it) +Averaged stats (hcp-val): loss: 0.8776 (0.8803) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +Train: [52] [ 0/6250] eta: 8:00:48 lr: 0.000064 grad: nan (nan) loss: 0.8289 (0.8289) time: 4.6157 data: 4.4478 max mem: 8255 +Train: [52] [ 100/6250] eta: 0:19:26 lr: 0.000063 grad: 0.1180 (0.1134) loss: 0.8661 (0.8722) time: 0.1355 data: 0.0481 max mem: 8255 +Train: [52] [ 200/6250] eta: 0:16:27 lr: 0.000063 grad: 0.0944 (0.1064) loss: 0.8689 (0.8662) time: 0.1299 data: 0.0497 max mem: 8255 +Train: [52] [ 300/6250] eta: 0:14:59 lr: 0.000063 grad: 0.1042 (0.1030) loss: 0.8552 (0.8643) time: 0.1027 data: 0.0280 max mem: 8255 +Train: [52] [ 400/6250] eta: 0:14:12 lr: 0.000063 grad: 0.0906 (0.1006) loss: 0.8585 (0.8623) time: 0.1347 data: 0.0604 max mem: 8255 +Train: [52] [ 500/6250] eta: 0:13:23 lr: 0.000063 grad: 0.0984 (0.0999) loss: 0.8533 (0.8607) time: 0.1230 data: 0.0418 max mem: 8255 +Train: [52] [ 600/6250] eta: 0:12:47 lr: 0.000063 grad: 0.1007 (0.0998) loss: 0.8505 (0.8590) time: 0.1147 data: 0.0404 max mem: 8255 +Train: [52] [ 700/6250] eta: 0:12:22 lr: 0.000063 grad: 0.0968 (0.0994) loss: 0.8463 (0.8576) time: 0.1267 data: 0.0464 max mem: 8255 +Train: [52] [ 800/6250] eta: 0:12:00 lr: 0.000063 grad: 0.0940 (0.0992) loss: 0.8422 (0.8563) time: 0.1364 data: 0.0658 max mem: 8255 +Train: [52] [ 900/6250] eta: 0:11:39 lr: 0.000063 grad: 0.0883 (0.0989) loss: 0.8567 (0.8554) time: 0.1421 data: 0.0683 max mem: 8255 +Train: [52] [1000/6250] eta: 0:11:18 lr: 0.000063 grad: 0.0926 (0.0988) loss: 0.8460 (0.8547) time: 0.1234 data: 0.0445 max mem: 8255 +Train: [52] [1100/6250] eta: 0:11:04 lr: 0.000063 grad: 0.1042 (0.0988) loss: 0.8387 (0.8539) time: 0.1274 data: 0.0564 max mem: 8255 +Train: [52] [1200/6250] eta: 0:10:54 lr: 0.000063 grad: 0.0937 (0.0986) loss: 0.8487 (0.8531) time: 0.1770 data: 0.1000 max mem: 8255 +Train: [52] [1300/6250] eta: 0:10:38 lr: 0.000063 grad: 0.0946 (0.0986) loss: 0.8471 (0.8524) time: 0.1219 data: 0.0461 max mem: 8255 +Train: [52] [1400/6250] eta: 0:10:25 lr: 0.000063 grad: 0.0982 (0.0986) loss: 0.8452 (0.8518) time: 0.1253 data: 0.0548 max mem: 8255 +Train: [52] [1500/6250] eta: 0:10:15 lr: 0.000063 grad: 0.0961 (0.0986) loss: 0.8462 (0.8512) time: 0.1467 data: 0.0766 max mem: 8255 +Train: [52] [1600/6250] eta: 0:10:04 lr: 0.000063 grad: 0.0911 (0.0984) loss: 0.8430 (0.8507) time: 0.1041 data: 0.0289 max mem: 8255 +Train: [52] [1700/6250] eta: 0:09:51 lr: 0.000063 grad: 0.0916 (0.0985) loss: 0.8446 (0.8504) time: 0.1285 data: 0.0558 max mem: 8255 +Train: [52] [1800/6250] eta: 0:09:37 lr: 0.000063 grad: 0.0960 (0.0984) loss: 0.8471 (0.8500) time: 0.1356 data: 0.0637 max mem: 8255 +Train: [52] [1900/6250] eta: 0:09:24 lr: 0.000063 grad: 0.0943 (0.0983) loss: 0.8431 (0.8497) time: 0.1399 data: 0.0682 max mem: 8255 +Train: [52] [2000/6250] eta: 0:09:15 lr: 0.000063 grad: 0.0997 (0.0985) loss: 0.8392 (0.8493) time: 0.1653 data: 0.0924 max mem: 8255 +Train: [52] [2100/6250] eta: 0:09:00 lr: 0.000063 grad: 0.0961 (0.0984) loss: 0.8498 (0.8491) time: 0.1228 data: 0.0442 max mem: 8255 +Train: [52] [2200/6250] eta: 0:08:45 lr: 0.000063 grad: 0.1018 (0.0986) loss: 0.8400 (0.8487) time: 0.1038 data: 0.0314 max mem: 8255 +Train: [52] [2300/6250] eta: 0:08:32 lr: 0.000063 grad: 0.0973 (0.0988) loss: 0.8446 (0.8484) time: 0.1351 data: 0.0713 max mem: 8255 +Train: [52] [2400/6250] eta: 0:08:22 lr: 0.000063 grad: 0.0980 (0.0988) loss: 0.8396 (0.8480) time: 0.1343 data: 0.0517 max mem: 8255 +Train: [52] [2500/6250] eta: 0:08:11 lr: 0.000063 grad: 0.0950 (0.0988) loss: 0.8418 (0.8478) time: 0.1423 data: 0.0675 max mem: 8255 +Train: [52] [2600/6250] eta: 0:07:58 lr: 0.000063 grad: 0.1015 (0.0989) loss: 0.8349 (0.8474) time: 0.1313 data: 0.0596 max mem: 8255 +Train: [52] [2700/6250] eta: 0:07:46 lr: 0.000063 grad: 0.0970 (0.0990) loss: 0.8428 (0.8471) time: 0.1286 data: 0.0567 max mem: 8255 +Train: [52] [2800/6250] eta: 0:07:33 lr: 0.000063 grad: 0.0964 (0.0991) loss: 0.8419 (0.8469) time: 0.1322 data: 0.0612 max mem: 8255 +Train: [52] [2900/6250] eta: 0:07:19 lr: 0.000063 grad: 0.0991 (0.0992) loss: 0.8370 (0.8466) time: 0.1076 data: 0.0328 max mem: 8255 +Train: [52] [3000/6250] eta: 0:07:05 lr: 0.000063 grad: 0.0938 (0.0991) loss: 0.8392 (0.8463) time: 0.1117 data: 0.0407 max mem: 8255 +Train: [52] [3100/6250] eta: 0:06:51 lr: 0.000063 grad: 0.0953 (0.0992) loss: 0.8445 (0.8462) time: 0.1260 data: 0.0565 max mem: 8255 +Train: [52] [3200/6250] eta: 0:06:37 lr: 0.000062 grad: 0.0965 (0.0992) loss: 0.8467 (0.8460) time: 0.1125 data: 0.0423 max mem: 8255 +Train: [52] [3300/6250] eta: 0:06:22 lr: 0.000062 grad: 0.0996 (0.0993) loss: 0.8387 (0.8459) time: 0.1134 data: 0.0373 max mem: 8255 +Train: [52] [3400/6250] eta: 0:06:08 lr: 0.000062 grad: 0.0991 (0.0994) loss: 0.8406 (0.8457) time: 0.1265 data: 0.0563 max mem: 8255 +Train: [52] [3500/6250] eta: 0:05:55 lr: 0.000062 grad: 0.0919 (0.0994) loss: 0.8387 (0.8456) time: 0.1211 data: 0.0450 max mem: 8255 +Train: [52] [3600/6250] eta: 0:05:42 lr: 0.000062 grad: 0.0983 (0.0994) loss: 0.8417 (0.8454) time: 0.1342 data: 0.0539 max mem: 8255 +Train: [52] [3700/6250] eta: 0:05:30 lr: 0.000062 grad: 0.0950 (0.0995) loss: 0.8406 (0.8453) time: 0.1832 data: 0.0700 max mem: 8255 +Train: [52] [3800/6250] eta: 0:05:17 lr: 0.000062 grad: 0.0997 (0.0995) loss: 0.8479 (0.8452) time: 0.1311 data: 0.0494 max mem: 8255 +Train: [52] [3900/6250] eta: 0:05:05 lr: 0.000062 grad: 0.0963 (0.0995) loss: 0.8443 (0.8452) time: 0.2185 data: 0.1442 max mem: 8255 +Train: [52] [4000/6250] eta: 0:04:52 lr: 0.000062 grad: 0.0981 (0.0995) loss: 0.8397 (0.8452) time: 0.1303 data: 0.0575 max mem: 8255 +Train: [52] [4100/6250] eta: 0:04:39 lr: 0.000062 grad: 0.0979 (0.0995) loss: 0.8460 (0.8452) time: 0.1274 data: 0.0553 max mem: 8255 +Train: [52] [4200/6250] eta: 0:04:26 lr: 0.000062 grad: 0.0947 (0.0995) loss: 0.8570 (0.8452) time: 0.1473 data: 0.0696 max mem: 8255 +Train: [52] [4300/6250] eta: 0:04:13 lr: 0.000062 grad: 0.0954 (0.0996) loss: 0.8459 (0.8453) time: 0.1341 data: 0.0642 max mem: 8255 +Train: [52] [4400/6250] eta: 0:04:00 lr: 0.000062 grad: 0.1001 (0.0996) loss: 0.8415 (0.8452) time: 0.1475 data: 0.0825 max mem: 8255 +Train: [52] [4500/6250] eta: 0:03:47 lr: 0.000062 grad: 0.1034 (0.0997) loss: 0.8371 (0.8452) time: 0.1327 data: 0.0629 max mem: 8255 +Train: [52] [4600/6250] eta: 0:03:34 lr: 0.000062 grad: 0.1025 (0.0997) loss: 0.8422 (0.8451) time: 0.1302 data: 0.0504 max mem: 8255 +Train: [52] [4700/6250] eta: 0:03:22 lr: 0.000062 grad: 0.0989 (0.0998) loss: 0.8443 (0.8451) time: 0.1346 data: 0.0645 max mem: 8255 +Train: [52] [4800/6250] eta: 0:03:09 lr: 0.000062 grad: 0.0962 (0.0998) loss: 0.8385 (0.8451) time: 0.1410 data: 0.0706 max mem: 8255 +Train: [52] [4900/6250] eta: 0:02:56 lr: 0.000062 grad: 0.0969 (0.0999) loss: 0.8530 (0.8450) time: 0.1274 data: 0.0523 max mem: 8255 +Train: [52] [5000/6250] eta: 0:02:43 lr: 0.000062 grad: 0.1042 (0.0999) loss: 0.8458 (0.8450) time: 0.1184 data: 0.0376 max mem: 8255 +Train: [52] [5100/6250] eta: 0:02:30 lr: 0.000062 grad: 0.0997 (0.1000) loss: 0.8533 (0.8450) time: 0.1126 data: 0.0418 max mem: 8255 +Train: [52] [5200/6250] eta: 0:02:17 lr: 0.000062 grad: 0.1038 (0.1001) loss: 0.8428 (0.8449) time: 0.1406 data: 0.0804 max mem: 8255 +Train: [52] [5300/6250] eta: 0:02:04 lr: 0.000062 grad: 0.0981 (0.1001) loss: 0.8458 (0.8448) time: 0.1166 data: 0.0473 max mem: 8255 +Train: [52] [5400/6250] eta: 0:01:51 lr: 0.000062 grad: 0.1109 (0.1002) loss: 0.8429 (0.8448) time: 0.1291 data: 0.0599 max mem: 8255 +Train: [52] [5500/6250] eta: 0:01:38 lr: 0.000062 grad: 0.0986 (0.1002) loss: 0.8438 (0.8447) time: 0.1428 data: 0.0732 max mem: 8255 +Train: [52] [5600/6250] eta: 0:01:25 lr: 0.000062 grad: 0.0981 (0.1003) loss: 0.8337 (0.8446) time: 0.1324 data: 0.0630 max mem: 8255 +Train: [52] [5700/6250] eta: 0:01:12 lr: 0.000062 grad: 0.0962 (0.1003) loss: 0.8415 (0.8446) time: 0.1204 data: 0.0526 max mem: 8255 +Train: [52] [5800/6250] eta: 0:00:58 lr: 0.000062 grad: 0.0983 (0.1004) loss: 0.8413 (0.8446) time: 0.1167 data: 0.0492 max mem: 8255 +Train: [52] [5900/6250] eta: 0:00:45 lr: 0.000062 grad: 0.0979 (0.1004) loss: 0.8415 (0.8446) time: 0.1058 data: 0.0360 max mem: 8255 +Train: [52] [6000/6250] eta: 0:00:32 lr: 0.000062 grad: 0.1007 (0.1005) loss: 0.8403 (0.8445) time: 0.1441 data: 0.0733 max mem: 8255 +Train: [52] [6100/6250] eta: 0:00:19 lr: 0.000062 grad: 0.1027 (0.1006) loss: 0.8426 (0.8445) time: 0.1153 data: 0.0476 max mem: 8255 +Train: [52] [6200/6250] eta: 0:00:06 lr: 0.000061 grad: 0.0984 (0.1006) loss: 0.8475 (0.8446) time: 0.1964 data: 0.1303 max mem: 8255 +Train: [52] [6249/6250] eta: 0:00:00 lr: 0.000061 grad: 0.0988 (0.1006) loss: 0.8419 (0.8445) time: 0.1251 data: 0.0445 max mem: 8255 +Train: [52] Total time: 0:13:43 (0.1318 s / it) +Averaged stats: lr: 0.000061 grad: 0.0988 (0.1006) loss: 0.8419 (0.8445) +Eval (hcp-train-subset): [52] [ 0/62] eta: 0:05:28 loss: 0.8827 (0.8827) time: 5.2931 data: 5.2665 max mem: 8255 +Eval (hcp-train-subset): [52] [61/62] eta: 0:00:00 loss: 0.8724 (0.8737) time: 0.1291 data: 0.1071 max mem: 8255 +Eval (hcp-train-subset): [52] Total time: 0:00:13 (0.2133 s / it) +Averaged stats (hcp-train-subset): loss: 0.8724 (0.8737) +Eval (hcp-val): [52] [ 0/62] eta: 0:03:42 loss: 0.8742 (0.8742) time: 3.5869 data: 3.4972 max mem: 8255 +Eval (hcp-val): [52] [61/62] eta: 0:00:00 loss: 0.8758 (0.8778) time: 0.1052 data: 0.0848 max mem: 8255 +Eval (hcp-val): [52] Total time: 0:00:13 (0.2109 s / it) +Averaged stats (hcp-val): loss: 0.8758 (0.8778) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +Train: [53] [ 0/6250] eta: 9:53:21 lr: 0.000061 grad: 0.4773 (0.4773) loss: 0.8846 (0.8846) time: 5.6963 data: 5.5738 max mem: 8255 +Train: [53] [ 100/6250] eta: 0:18:48 lr: 0.000061 grad: 0.0983 (0.1198) loss: 0.8621 (0.8613) time: 0.1276 data: 0.0317 max mem: 8255 +Train: [53] [ 200/6250] eta: 0:15:51 lr: 0.000061 grad: 0.1029 (0.1120) loss: 0.8595 (0.8589) time: 0.1190 data: 0.0449 max mem: 8255 +Train: [53] [ 300/6250] eta: 0:14:22 lr: 0.000061 grad: 0.0986 (0.1081) loss: 0.8516 (0.8561) time: 0.1081 data: 0.0303 max mem: 8255 +Train: [53] [ 400/6250] eta: 0:13:29 lr: 0.000061 grad: 0.0964 (0.1057) loss: 0.8490 (0.8551) time: 0.1141 data: 0.0302 max mem: 8255 +Train: [53] [ 500/6250] eta: 0:13:02 lr: 0.000061 grad: 0.0954 (0.1043) loss: 0.8516 (0.8540) time: 0.1363 data: 0.0585 max mem: 8255 +Train: [53] [ 600/6250] eta: 0:12:32 lr: 0.000061 grad: 0.0961 (0.1027) loss: 0.8508 (0.8533) time: 0.1304 data: 0.0662 max mem: 8255 +Train: [53] [ 700/6250] eta: 0:12:12 lr: 0.000061 grad: 0.0891 (0.1014) loss: 0.8524 (0.8531) time: 0.1209 data: 0.0387 max mem: 8255 +Train: [53] [ 800/6250] eta: 0:11:58 lr: 0.000061 grad: 0.0901 (0.1005) loss: 0.8547 (0.8531) time: 0.1231 data: 0.0512 max mem: 8255 +Train: [53] [ 900/6250] eta: 0:11:47 lr: 0.000061 grad: 0.0931 (0.0999) loss: 0.8531 (0.8531) time: 0.1607 data: 0.0841 max mem: 8255 +Train: [53] [1000/6250] eta: 0:11:35 lr: 0.000061 grad: 0.0952 (0.0995) loss: 0.8523 (0.8526) time: 0.1292 data: 0.0515 max mem: 8255 +Train: [53] [1100/6250] eta: 0:11:18 lr: 0.000061 grad: 0.0888 (0.0992) loss: 0.8450 (0.8520) time: 0.1161 data: 0.0425 max mem: 8255 +Train: [53] [1200/6250] eta: 0:11:09 lr: 0.000061 grad: 0.0963 (0.0990) loss: 0.8432 (0.8515) time: 0.1462 data: 0.0819 max mem: 8255 +Train: [53] [1300/6250] eta: 0:10:54 lr: 0.000061 grad: 0.0903 (0.0990) loss: 0.8495 (0.8510) time: 0.1191 data: 0.0473 max mem: 8255 +Train: [53] [1400/6250] eta: 0:10:41 lr: 0.000061 grad: 0.0948 (0.0986) loss: 0.8497 (0.8507) time: 0.1162 data: 0.0321 max mem: 8255 +Train: [53] [1500/6250] eta: 0:10:31 lr: 0.000061 grad: 0.0974 (0.0986) loss: 0.8405 (0.8502) time: 0.0923 data: 0.0002 max mem: 8255 +Train: [53] [1600/6250] eta: 0:10:15 lr: 0.000061 grad: 0.0947 (0.0984) loss: 0.8456 (0.8496) time: 0.1200 data: 0.0522 max mem: 8255 +Train: [53] [1700/6250] eta: 0:10:03 lr: 0.000061 grad: 0.0911 (0.0982) loss: 0.8456 (0.8494) time: 0.1268 data: 0.0557 max mem: 8255 +Train: [53] [1800/6250] eta: 0:09:54 lr: 0.000061 grad: 0.0917 (0.0980) loss: 0.8513 (0.8492) time: 0.1603 data: 0.0955 max mem: 8255 +Train: [53] [1900/6250] eta: 0:09:41 lr: 0.000061 grad: 0.0962 (0.0980) loss: 0.8486 (0.8490) time: 0.1425 data: 0.0679 max mem: 8255 +Train: [53] [2000/6250] eta: 0:09:32 lr: 0.000061 grad: 0.0920 (0.0981) loss: 0.8561 (0.8489) time: 0.0844 data: 0.0111 max mem: 8255 +Train: [53] [2100/6250] eta: 0:09:17 lr: 0.000061 grad: 0.0968 (0.0980) loss: 0.8430 (0.8486) time: 0.1517 data: 0.0728 max mem: 8255 +Train: [53] [2200/6250] eta: 0:09:04 lr: 0.000061 grad: 0.0938 (0.0981) loss: 0.8473 (0.8484) time: 0.1400 data: 0.0681 max mem: 8255 +Train: [53] [2300/6250] eta: 0:08:52 lr: 0.000061 grad: 0.0992 (0.0982) loss: 0.8511 (0.8482) time: 0.1432 data: 0.0759 max mem: 8255 +Train: [53] [2400/6250] eta: 0:08:40 lr: 0.000061 grad: 0.0943 (0.0983) loss: 0.8438 (0.8481) time: 0.1245 data: 0.0486 max mem: 8255 +Train: [53] [2500/6250] eta: 0:08:27 lr: 0.000061 grad: 0.1015 (0.0983) loss: 0.8370 (0.8478) time: 0.1376 data: 0.0648 max mem: 8255 +Train: [53] [2600/6250] eta: 0:08:16 lr: 0.000061 grad: 0.1021 (0.0986) loss: 0.8339 (0.8476) time: 0.1552 data: 0.0674 max mem: 8255 +Train: [53] [2700/6250] eta: 0:08:03 lr: 0.000061 grad: 0.1014 (0.0987) loss: 0.8411 (0.8473) time: 0.1498 data: 0.0789 max mem: 8255 +Train: [53] [2800/6250] eta: 0:07:51 lr: 0.000061 grad: 0.0962 (0.0988) loss: 0.8433 (0.8472) time: 0.1624 data: 0.1003 max mem: 8255 +Train: [53] [2900/6250] eta: 0:07:39 lr: 0.000061 grad: 0.0920 (0.0988) loss: 0.8493 (0.8471) time: 0.1549 data: 0.0848 max mem: 8255 +Train: [53] [3000/6250] eta: 0:07:26 lr: 0.000060 grad: 0.1010 (0.0989) loss: 0.8454 (0.8471) time: 0.1392 data: 0.0710 max mem: 8255 +Train: [53] [3100/6250] eta: 0:07:12 lr: 0.000060 grad: 0.0938 (0.0990) loss: 0.8529 (0.8470) time: 0.1544 data: 0.0829 max mem: 8255 +Train: [53] [3200/6250] eta: 0:06:57 lr: 0.000060 grad: 0.0967 (0.0989) loss: 0.8437 (0.8470) time: 0.1453 data: 0.0714 max mem: 8255 +Train: [53] [3300/6250] eta: 0:06:43 lr: 0.000060 grad: 0.0918 (0.0990) loss: 0.8498 (0.8470) time: 0.1315 data: 0.0553 max mem: 8255 +Train: [53] [3400/6250] eta: 0:06:28 lr: 0.000060 grad: 0.0992 (0.0990) loss: 0.8439 (0.8470) time: 0.1176 data: 0.0464 max mem: 8255 +Train: [53] [3500/6250] eta: 0:06:14 lr: 0.000060 grad: 0.0944 (0.0991) loss: 0.8486 (0.8469) time: 0.1442 data: 0.0473 max mem: 8255 +Train: [53] [3600/6250] eta: 0:06:01 lr: 0.000060 grad: 0.0921 (0.0991) loss: 0.8491 (0.8469) time: 0.1369 data: 0.0600 max mem: 8255 +Train: [53] [3700/6250] eta: 0:05:48 lr: 0.000060 grad: 0.1037 (0.0992) loss: 0.8428 (0.8468) time: 0.1311 data: 0.0601 max mem: 8255 +Train: [53] [3800/6250] eta: 0:05:34 lr: 0.000060 grad: 0.0936 (0.0992) loss: 0.8443 (0.8467) time: 0.1615 data: 0.0854 max mem: 8255 +Train: [53] [3900/6250] eta: 0:05:22 lr: 0.000060 grad: 0.0962 (0.0993) loss: 0.8434 (0.8467) time: 0.1378 data: 0.0596 max mem: 8255 +Train: [53] [4000/6250] eta: 0:05:08 lr: 0.000060 grad: 0.0971 (0.0993) loss: 0.8452 (0.8467) time: 0.1444 data: 0.0555 max mem: 8255 +Train: [53] [4100/6250] eta: 0:04:56 lr: 0.000060 grad: 0.0943 (0.0992) loss: 0.8500 (0.8467) time: 0.1754 data: 0.0943 max mem: 8255 +Train: [53] [4200/6250] eta: 0:04:42 lr: 0.000060 grad: 0.0968 (0.0992) loss: 0.8429 (0.8466) time: 0.1621 data: 0.0896 max mem: 8255 +Train: [53] [4300/6250] eta: 0:04:28 lr: 0.000060 grad: 0.1002 (0.0992) loss: 0.8342 (0.8466) time: 0.1546 data: 0.0860 max mem: 8255 +Train: [53] [4400/6250] eta: 0:04:14 lr: 0.000060 grad: 0.0989 (0.0992) loss: 0.8482 (0.8465) time: 0.1551 data: 0.0813 max mem: 8255 +Train: [53] [4500/6250] eta: 0:04:00 lr: 0.000060 grad: 0.0951 (0.0992) loss: 0.8495 (0.8465) time: 0.1422 data: 0.0702 max mem: 8255 +Train: [53] [4600/6250] eta: 0:03:47 lr: 0.000060 grad: 0.0942 (0.0992) loss: 0.8460 (0.8465) time: 0.1427 data: 0.0747 max mem: 8255 +Train: [53] [4700/6250] eta: 0:03:33 lr: 0.000060 grad: 0.0972 (0.0991) loss: 0.8433 (0.8465) time: 0.1477 data: 0.0805 max mem: 8255 +Train: [53] [4800/6250] eta: 0:03:19 lr: 0.000060 grad: 0.0982 (0.0992) loss: 0.8436 (0.8465) time: 0.1397 data: 0.0656 max mem: 8255 +Train: [53] [4900/6250] eta: 0:03:06 lr: 0.000060 grad: 0.0947 (0.0991) loss: 0.8474 (0.8465) time: 0.1502 data: 0.0805 max mem: 8255 +Train: [53] [5000/6250] eta: 0:02:52 lr: 0.000060 grad: 0.0993 (0.0991) loss: 0.8449 (0.8466) time: 0.1245 data: 0.0535 max mem: 8255 +Train: [53] [5100/6250] eta: 0:02:39 lr: 0.000060 grad: 0.0955 (0.0991) loss: 0.8482 (0.8466) time: 0.2690 data: 0.1972 max mem: 8255 +Train: [53] [5200/6250] eta: 0:02:25 lr: 0.000060 grad: 0.0978 (0.0991) loss: 0.8416 (0.8465) time: 0.1413 data: 0.0748 max mem: 8255 +Train: [53] [5300/6250] eta: 0:02:11 lr: 0.000060 grad: 0.0956 (0.0991) loss: 0.8486 (0.8465) time: 0.1416 data: 0.0641 max mem: 8255 +Train: [53] [5400/6250] eta: 0:01:58 lr: 0.000060 grad: 0.0914 (0.0991) loss: 0.8406 (0.8465) time: 0.1728 data: 0.1069 max mem: 8255 +Train: [53] [5500/6250] eta: 0:01:44 lr: 0.000060 grad: 0.0936 (0.0992) loss: 0.8487 (0.8465) time: 0.1995 data: 0.1310 max mem: 8255 +Train: [53] [5600/6250] eta: 0:01:30 lr: 0.000060 grad: 0.0969 (0.0992) loss: 0.8486 (0.8465) time: 0.1388 data: 0.0715 max mem: 8255 +Train: [53] [5700/6250] eta: 0:01:16 lr: 0.000060 grad: 0.0984 (0.0991) loss: 0.8437 (0.8465) time: 0.2194 data: 0.1551 max mem: 8255 +Train: [53] [5800/6250] eta: 0:01:02 lr: 0.000060 grad: 0.0952 (0.0991) loss: 0.8417 (0.8465) time: 0.1394 data: 0.0702 max mem: 8255 +Train: [53] [5900/6250] eta: 0:00:48 lr: 0.000060 grad: 0.1004 (0.0991) loss: 0.8494 (0.8466) time: 0.1302 data: 0.0619 max mem: 8255 +Train: [53] [6000/6250] eta: 0:00:34 lr: 0.000059 grad: 0.0904 (0.0991) loss: 0.8482 (0.8467) time: 0.1234 data: 0.0510 max mem: 8255 +Train: [53] [6100/6250] eta: 0:00:20 lr: 0.000059 grad: 0.0894 (0.0991) loss: 0.8566 (0.8467) time: 0.1541 data: 0.0783 max mem: 8255 +Train: [53] [6200/6250] eta: 0:00:06 lr: 0.000059 grad: 0.0956 (0.0991) loss: 0.8564 (0.8468) time: 0.1500 data: 0.0774 max mem: 8255 +Train: [53] [6249/6250] eta: 0:00:00 lr: 0.000059 grad: 0.0964 (0.0991) loss: 0.8481 (0.8468) time: 0.1351 data: 0.0624 max mem: 8255 +Train: [53] Total time: 0:14:37 (0.1404 s / it) +Averaged stats: lr: 0.000059 grad: 0.0964 (0.0991) loss: 0.8481 (0.8468) +Eval (hcp-train-subset): [53] [ 0/62] eta: 0:04:42 loss: 0.8856 (0.8856) time: 4.5628 data: 4.5321 max mem: 8255 +Eval (hcp-train-subset): [53] [61/62] eta: 0:00:00 loss: 0.8701 (0.8722) time: 0.1218 data: 0.1014 max mem: 8255 +Eval (hcp-train-subset): [53] Total time: 0:00:12 (0.1983 s / it) +Averaged stats (hcp-train-subset): loss: 0.8701 (0.8722) +Eval (hcp-val): [53] [ 0/62] eta: 0:05:29 loss: 0.8723 (0.8723) time: 5.3220 data: 5.2734 max mem: 8255 +Eval (hcp-val): [53] [61/62] eta: 0:00:00 loss: 0.8770 (0.8784) time: 0.1254 data: 0.1048 max mem: 8255 +Eval (hcp-val): [53] Total time: 0:00:13 (0.2186 s / it) +Averaged stats (hcp-val): loss: 0.8770 (0.8784) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +Train: [54] [ 0/6250] eta: 11:28:55 lr: 0.000059 grad: 0.0969 (0.0969) loss: 0.8901 (0.8901) time: 6.6137 data: 6.5235 max mem: 8255 +Train: [54] [ 100/6250] eta: 0:20:23 lr: 0.000059 grad: 0.1014 (0.1251) loss: 0.8646 (0.8723) time: 0.1441 data: 0.0491 max mem: 8255 +Train: [54] [ 200/6250] eta: 0:17:40 lr: 0.000059 grad: 0.0943 (0.1136) loss: 0.8444 (0.8630) time: 0.1578 data: 0.0730 max mem: 8255 +Train: [54] [ 300/6250] eta: 0:16:30 lr: 0.000059 grad: 0.0928 (0.1085) loss: 0.8463 (0.8594) time: 0.1525 data: 0.0678 max mem: 8255 +Train: [54] [ 400/6250] eta: 0:15:33 lr: 0.000059 grad: 0.1038 (0.1064) loss: 0.8512 (0.8575) time: 0.1645 data: 0.0754 max mem: 8255 +Train: [54] [ 500/6250] eta: 0:14:52 lr: 0.000059 grad: 0.0934 (0.1053) loss: 0.8538 (0.8555) time: 0.1223 data: 0.0426 max mem: 8255 +Train: [54] [ 600/6250] eta: 0:14:10 lr: 0.000059 grad: 0.0998 (0.1044) loss: 0.8495 (0.8542) time: 0.1289 data: 0.0480 max mem: 8255 +Train: [54] [ 700/6250] eta: 0:13:34 lr: 0.000059 grad: 0.0926 (0.1036) loss: 0.8516 (0.8533) time: 0.1241 data: 0.0517 max mem: 8255 +Train: [54] [ 800/6250] eta: 0:13:09 lr: 0.000059 grad: 0.0940 (0.1028) loss: 0.8465 (0.8527) time: 0.1576 data: 0.0824 max mem: 8255 +Train: [54] [ 900/6250] eta: 0:12:58 lr: 0.000059 grad: 0.1030 (0.1026) loss: 0.8493 (0.8521) time: 0.1300 data: 0.0471 max mem: 8255 +Train: [54] [1000/6250] eta: 0:12:50 lr: 0.000059 grad: 0.0993 (0.1022) loss: 0.8571 (0.8521) time: 0.1575 data: 0.0908 max mem: 8255 +Train: [54] [1100/6250] eta: 0:12:33 lr: 0.000059 grad: 0.0964 (0.1018) loss: 0.8459 (0.8517) time: 0.1757 data: 0.1004 max mem: 8255 +Train: [54] [1200/6250] eta: 0:12:09 lr: 0.000059 grad: 0.0915 (0.1013) loss: 0.8449 (0.8513) time: 0.1224 data: 0.0454 max mem: 8255 +Train: [54] [1300/6250] eta: 0:11:50 lr: 0.000059 grad: 0.0984 (0.1012) loss: 0.8474 (0.8511) time: 0.1466 data: 0.0680 max mem: 8255 +Train: [54] [1400/6250] eta: 0:11:34 lr: 0.000059 grad: 0.0978 (0.1009) loss: 0.8458 (0.8509) time: 0.1515 data: 0.0659 max mem: 8255 +Train: [54] [1500/6250] eta: 0:11:21 lr: 0.000059 grad: 0.0927 (0.1006) loss: 0.8474 (0.8506) time: 0.1549 data: 0.0633 max mem: 8255 +Train: [54] [1600/6250] eta: 0:11:09 lr: 0.000059 grad: 0.0961 (0.1006) loss: 0.8345 (0.8501) time: 0.1303 data: 0.0445 max mem: 8255 +Train: [54] [1700/6250] eta: 0:11:00 lr: 0.000059 grad: 0.0952 (0.1004) loss: 0.8458 (0.8500) time: 0.2009 data: 0.1153 max mem: 8255 +Train: [54] [1800/6250] eta: 0:10:45 lr: 0.000059 grad: 0.0930 (0.1003) loss: 0.8474 (0.8498) time: 0.1456 data: 0.0627 max mem: 8255 +Train: [54] [1900/6250] eta: 0:10:37 lr: 0.000059 grad: 0.0951 (0.1001) loss: 0.8465 (0.8496) time: 0.1062 data: 0.0250 max mem: 8255 +Train: [54] [2000/6250] eta: 0:10:20 lr: 0.000059 grad: 0.0943 (0.1002) loss: 0.8459 (0.8493) time: 0.1178 data: 0.0408 max mem: 8255 +Train: [54] [2100/6250] eta: 0:10:03 lr: 0.000059 grad: 0.0919 (0.1001) loss: 0.8467 (0.8492) time: 0.1411 data: 0.0645 max mem: 8255 +Train: [54] [2200/6250] eta: 0:09:45 lr: 0.000059 grad: 0.0949 (0.1000) loss: 0.8466 (0.8491) time: 0.1192 data: 0.0437 max mem: 8255 +Train: [54] [2300/6250] eta: 0:09:29 lr: 0.000059 grad: 0.0913 (0.0999) loss: 0.8407 (0.8488) time: 0.1384 data: 0.0691 max mem: 8255 +Train: [54] [2400/6250] eta: 0:09:12 lr: 0.000059 grad: 0.0905 (0.0998) loss: 0.8412 (0.8486) time: 0.1256 data: 0.0530 max mem: 8255 +Train: [54] [2500/6250] eta: 0:08:56 lr: 0.000059 grad: 0.0997 (0.0999) loss: 0.8449 (0.8485) time: 0.1445 data: 0.0773 max mem: 8255 +Train: [54] [2600/6250] eta: 0:08:45 lr: 0.000059 grad: 0.0938 (0.0998) loss: 0.8411 (0.8483) time: 0.2445 data: 0.1585 max mem: 8255 +Train: [54] [2700/6250] eta: 0:08:30 lr: 0.000059 grad: 0.0962 (0.0997) loss: 0.8489 (0.8482) time: 0.1364 data: 0.0662 max mem: 8255 +Train: [54] [2800/6250] eta: 0:08:15 lr: 0.000058 grad: 0.0948 (0.0997) loss: 0.8488 (0.8481) time: 0.1886 data: 0.1267 max mem: 8255 +Train: [54] [2900/6250] eta: 0:08:01 lr: 0.000058 grad: 0.0972 (0.0996) loss: 0.8452 (0.8480) time: 0.1274 data: 0.0612 max mem: 8255 +Train: [54] [3000/6250] eta: 0:07:46 lr: 0.000058 grad: 0.0944 (0.0995) loss: 0.8455 (0.8479) time: 0.1296 data: 0.0557 max mem: 8255 +Train: [54] [3100/6250] eta: 0:07:32 lr: 0.000058 grad: 0.0916 (0.0994) loss: 0.8497 (0.8479) time: 0.1458 data: 0.0685 max mem: 8255 +Train: [54] [3200/6250] eta: 0:07:16 lr: 0.000058 grad: 0.0926 (0.0994) loss: 0.8519 (0.8478) time: 0.1333 data: 0.0551 max mem: 8255 +Train: [54] [3300/6250] eta: 0:07:00 lr: 0.000058 grad: 0.0916 (0.0993) loss: 0.8516 (0.8479) time: 0.1120 data: 0.0402 max mem: 8255 +Train: [54] [3400/6250] eta: 0:06:43 lr: 0.000058 grad: 0.0978 (0.0992) loss: 0.8373 (0.8477) time: 0.1135 data: 0.0376 max mem: 8255 +Train: [54] [3500/6250] eta: 0:06:27 lr: 0.000058 grad: 0.0931 (0.0991) loss: 0.8546 (0.8477) time: 0.1137 data: 0.0377 max mem: 8255 +Train: [54] [3600/6250] eta: 0:06:11 lr: 0.000058 grad: 0.0981 (0.0990) loss: 0.8430 (0.8476) time: 0.1172 data: 0.0421 max mem: 8255 +Train: [54] [3700/6250] eta: 0:05:55 lr: 0.000058 grad: 0.0984 (0.0991) loss: 0.8495 (0.8475) time: 0.1260 data: 0.0564 max mem: 8255 +Train: [54] [3800/6250] eta: 0:05:39 lr: 0.000058 grad: 0.0981 (0.0992) loss: 0.8475 (0.8475) time: 0.1048 data: 0.0271 max mem: 8255 +Train: [54] [3900/6250] eta: 0:05:24 lr: 0.000058 grad: 0.0969 (0.0992) loss: 0.8487 (0.8474) time: 0.1160 data: 0.0432 max mem: 8255 +Train: [54] [4000/6250] eta: 0:05:10 lr: 0.000058 grad: 0.0945 (0.0992) loss: 0.8427 (0.8473) time: 0.1270 data: 0.0507 max mem: 8255 +Train: [54] [4100/6250] eta: 0:04:56 lr: 0.000058 grad: 0.1007 (0.0993) loss: 0.8454 (0.8472) time: 0.1293 data: 0.0430 max mem: 8255 +Train: [54] [4200/6250] eta: 0:04:42 lr: 0.000058 grad: 0.0978 (0.0993) loss: 0.8424 (0.8472) time: 0.1260 data: 0.0570 max mem: 8255 +Train: [54] [4300/6250] eta: 0:04:27 lr: 0.000058 grad: 0.0973 (0.0992) loss: 0.8429 (0.8472) time: 0.1278 data: 0.0529 max mem: 8255 +Train: [54] [4400/6250] eta: 0:04:13 lr: 0.000058 grad: 0.0976 (0.0993) loss: 0.8435 (0.8471) time: 0.1114 data: 0.0471 max mem: 8255 +Train: [54] [4500/6250] eta: 0:03:59 lr: 0.000058 grad: 0.1005 (0.0993) loss: 0.8382 (0.8470) time: 0.1221 data: 0.0576 max mem: 8255 +Train: [54] [4600/6250] eta: 0:03:45 lr: 0.000058 grad: 0.1011 (0.0994) loss: 0.8369 (0.8468) time: 0.1259 data: 0.0563 max mem: 8255 +Train: [54] [4700/6250] eta: 0:03:31 lr: 0.000058 grad: 0.0931 (0.0996) loss: 0.8379 (0.8466) time: 0.1149 data: 0.0417 max mem: 8255 +Train: [54] [4800/6250] eta: 0:03:18 lr: 0.000058 grad: 0.0981 (0.0999) loss: 0.8393 (0.8464) time: 0.1655 data: 0.0532 max mem: 8255 +Train: [54] [4900/6250] eta: 0:03:04 lr: 0.000058 grad: 0.1001 (0.1000) loss: 0.8441 (0.8462) time: 0.1227 data: 0.0488 max mem: 8255 +Train: [54] [5000/6250] eta: 0:02:50 lr: 0.000058 grad: 0.1016 (0.1002) loss: 0.8402 (0.8460) time: 0.1263 data: 0.0530 max mem: 8255 +Train: [54] [5100/6250] eta: 0:02:36 lr: 0.000058 grad: 0.0971 (0.1002) loss: 0.8333 (0.8458) time: 0.1202 data: 0.0447 max mem: 8255 +Train: [54] [5200/6250] eta: 0:02:23 lr: 0.000058 grad: 0.1022 (0.1003) loss: 0.8334 (0.8457) time: 0.1148 data: 0.0420 max mem: 8255 +Train: [54] [5300/6250] eta: 0:02:09 lr: 0.000058 grad: 0.0964 (0.1004) loss: 0.8370 (0.8455) time: 0.1368 data: 0.0563 max mem: 8255 +Train: [54] [5400/6250] eta: 0:01:55 lr: 0.000058 grad: 0.1049 (0.1005) loss: 0.8426 (0.8454) time: 0.1394 data: 0.0743 max mem: 8255 +Train: [54] [5500/6250] eta: 0:01:41 lr: 0.000058 grad: 0.0990 (0.1005) loss: 0.8403 (0.8453) time: 0.1253 data: 0.0524 max mem: 8255 +Train: [54] [5600/6250] eta: 0:01:28 lr: 0.000058 grad: 0.0984 (0.1005) loss: 0.8431 (0.8452) time: 0.1376 data: 0.0707 max mem: 8255 +Train: [54] [5700/6250] eta: 0:01:14 lr: 0.000058 grad: 0.1026 (0.1006) loss: 0.8425 (0.8450) time: 0.1070 data: 0.0228 max mem: 8255 +Train: [54] [5800/6250] eta: 0:01:00 lr: 0.000057 grad: 0.1041 (0.1007) loss: 0.8441 (0.8449) time: 0.1473 data: 0.0837 max mem: 8255 +Train: [54] [5900/6250] eta: 0:00:47 lr: 0.000057 grad: 0.0997 (0.1008) loss: 0.8376 (0.8447) time: 0.1285 data: 0.0546 max mem: 8255 +Train: [54] [6000/6250] eta: 0:00:33 lr: 0.000057 grad: 0.1014 (0.1009) loss: 0.8419 (0.8447) time: 0.1090 data: 0.0471 max mem: 8255 +Train: [54] [6100/6250] eta: 0:00:20 lr: 0.000057 grad: 0.0984 (0.1009) loss: 0.8389 (0.8446) time: 0.1394 data: 0.0673 max mem: 8255 +Train: [54] [6200/6250] eta: 0:00:06 lr: 0.000057 grad: 0.1029 (0.1009) loss: 0.8434 (0.8446) time: 0.1398 data: 0.0694 max mem: 8255 +Train: [54] [6249/6250] eta: 0:00:00 lr: 0.000057 grad: 0.0995 (0.1010) loss: 0.8410 (0.8445) time: 0.1248 data: 0.0520 max mem: 8255 +Train: [54] Total time: 0:14:10 (0.1361 s / it) +Averaged stats: lr: 0.000057 grad: 0.0995 (0.1010) loss: 0.8410 (0.8445) +Eval (hcp-train-subset): [54] [ 0/62] eta: 0:03:24 loss: 0.8857 (0.8857) time: 3.2951 data: 3.2333 max mem: 8255 +Eval (hcp-train-subset): [54] [61/62] eta: 0:00:00 loss: 0.8677 (0.8714) time: 0.1166 data: 0.0955 max mem: 8255 +Eval (hcp-train-subset): [54] Total time: 0:00:11 (0.1931 s / it) +Averaged stats (hcp-train-subset): loss: 0.8677 (0.8714) +Making plots (hcp-train-subset): example=12 +Eval (hcp-val): [54] [ 0/62] eta: 0:05:12 loss: 0.8717 (0.8717) time: 5.0471 data: 5.0217 max mem: 8255 +Eval (hcp-val): [54] [61/62] eta: 0:00:00 loss: 0.8772 (0.8781) time: 0.1207 data: 0.0998 max mem: 8255 +Eval (hcp-val): [54] Total time: 0:00:13 (0.2117 s / it) +Averaged stats (hcp-val): loss: 0.8772 (0.8781) +Making plots (hcp-val): example=36 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +Train: [55] [ 0/6250] eta: 8:05:30 lr: 0.000057 grad: 0.1850 (0.1850) loss: 0.8532 (0.8532) time: 4.6609 data: 4.4184 max mem: 8255 +Train: [55] [ 100/6250] eta: 0:19:43 lr: 0.000057 grad: 0.0946 (0.1163) loss: 0.8741 (0.8762) time: 0.1456 data: 0.0548 max mem: 8255 +Train: [55] [ 200/6250] eta: 0:16:43 lr: 0.000057 grad: 0.0971 (0.1102) loss: 0.8525 (0.8693) time: 0.1370 data: 0.0539 max mem: 8255 +Train: [55] [ 300/6250] eta: 0:15:18 lr: 0.000057 grad: 0.0940 (0.1088) loss: 0.8519 (0.8652) time: 0.1194 data: 0.0357 max mem: 8255 +Train: [55] [ 400/6250] eta: 0:14:18 lr: 0.000057 grad: 0.0926 (0.1053) loss: 0.8576 (0.8638) time: 0.0996 data: 0.0252 max mem: 8255 +Train: [55] [ 500/6250] eta: 0:13:32 lr: 0.000057 grad: 0.0987 (0.1038) loss: 0.8512 (0.8619) time: 0.1037 data: 0.0236 max mem: 8255 +Train: [55] [ 600/6250] eta: 0:13:01 lr: 0.000057 grad: 0.0984 (0.1026) loss: 0.8484 (0.8596) time: 0.1238 data: 0.0498 max mem: 8255 +Train: [55] [ 700/6250] eta: 0:12:34 lr: 0.000057 grad: 0.1007 (0.1023) loss: 0.8417 (0.8580) time: 0.1269 data: 0.0522 max mem: 8255 +Train: [55] [ 800/6250] eta: 0:12:12 lr: 0.000057 grad: 0.0932 (0.1012) loss: 0.8575 (0.8573) time: 0.1220 data: 0.0517 max mem: 8255 +Train: [55] [ 900/6250] eta: 0:11:55 lr: 0.000057 grad: 0.0962 (0.1005) loss: 0.8482 (0.8566) time: 0.1392 data: 0.0698 max mem: 8255 +Train: [55] [1000/6250] eta: 0:11:39 lr: 0.000057 grad: 0.0963 (0.1004) loss: 0.8485 (0.8557) time: 0.1377 data: 0.0673 max mem: 8255 +Train: [55] [1100/6250] eta: 0:11:23 lr: 0.000057 grad: 0.0886 (0.0999) loss: 0.8490 (0.8551) time: 0.1335 data: 0.0612 max mem: 8255 +Train: [55] [1200/6250] eta: 0:11:12 lr: 0.000057 grad: 0.0913 (0.0994) loss: 0.8519 (0.8544) time: 0.1222 data: 0.0394 max mem: 8255 +Train: [55] [1300/6250] eta: 0:10:56 lr: 0.000057 grad: 0.1012 (0.0992) loss: 0.8401 (0.8538) time: 0.0920 data: 0.0136 max mem: 8255 +Train: [55] [1400/6250] eta: 0:10:49 lr: 0.000057 grad: 0.0943 (0.0991) loss: 0.8447 (0.8533) time: 0.1703 data: 0.1035 max mem: 8255 +Train: [55] [1500/6250] eta: 0:10:35 lr: 0.000057 grad: 0.0962 (0.0990) loss: 0.8506 (0.8527) time: 0.1481 data: 0.0818 max mem: 8255 +Train: [55] [1600/6250] eta: 0:10:20 lr: 0.000057 grad: 0.0956 (0.0990) loss: 0.8399 (0.8522) time: 0.1224 data: 0.0534 max mem: 8255 +Train: [55] [1700/6250] eta: 0:10:05 lr: 0.000057 grad: 0.0947 (0.0989) loss: 0.8444 (0.8517) time: 0.1184 data: 0.0426 max mem: 8255 +Train: [55] [1800/6250] eta: 0:09:58 lr: 0.000057 grad: 0.0972 (0.0988) loss: 0.8421 (0.8513) time: 0.0901 data: 0.0004 max mem: 8255 +Train: [55] [1900/6250] eta: 0:09:40 lr: 0.000057 grad: 0.0960 (0.0986) loss: 0.8374 (0.8510) time: 0.1202 data: 0.0521 max mem: 8255 +Train: [55] [2000/6250] eta: 0:09:27 lr: 0.000057 grad: 0.0944 (0.0986) loss: 0.8460 (0.8507) time: 0.1511 data: 0.0861 max mem: 8255 +Train: [55] [2100/6250] eta: 0:09:11 lr: 0.000057 grad: 0.0977 (0.0985) loss: 0.8491 (0.8504) time: 0.1299 data: 0.0615 max mem: 8255 +Train: [55] [2200/6250] eta: 0:08:57 lr: 0.000057 grad: 0.0921 (0.0986) loss: 0.8527 (0.8502) time: 0.1215 data: 0.0532 max mem: 8255 +Train: [55] [2300/6250] eta: 0:08:42 lr: 0.000057 grad: 0.1006 (0.0986) loss: 0.8443 (0.8500) time: 0.1194 data: 0.0413 max mem: 8255 +Train: [55] [2400/6250] eta: 0:08:28 lr: 0.000057 grad: 0.0966 (0.0986) loss: 0.8488 (0.8498) time: 0.1322 data: 0.0655 max mem: 8255 +Train: [55] [2500/6250] eta: 0:08:15 lr: 0.000057 grad: 0.0949 (0.0986) loss: 0.8494 (0.8496) time: 0.1442 data: 0.0745 max mem: 8255 +Train: [55] [2600/6250] eta: 0:08:02 lr: 0.000056 grad: 0.0938 (0.0986) loss: 0.8437 (0.8495) time: 0.1389 data: 0.0674 max mem: 8255 +Train: [55] [2700/6250] eta: 0:07:48 lr: 0.000056 grad: 0.0978 (0.0986) loss: 0.8443 (0.8495) time: 0.1304 data: 0.0723 max mem: 8255 +Train: [55] [2800/6250] eta: 0:07:35 lr: 0.000056 grad: 0.0951 (0.0987) loss: 0.8475 (0.8494) time: 0.1183 data: 0.0480 max mem: 8255 +Train: [55] [2900/6250] eta: 0:07:21 lr: 0.000056 grad: 0.0943 (0.0988) loss: 0.8483 (0.8493) time: 0.1313 data: 0.0617 max mem: 8255 +Train: [55] [3000/6250] eta: 0:07:10 lr: 0.000056 grad: 0.0940 (0.0988) loss: 0.8531 (0.8492) time: 0.1249 data: 0.0560 max mem: 8255 +Train: [55] [3100/6250] eta: 0:06:59 lr: 0.000056 grad: 0.0945 (0.0989) loss: 0.8400 (0.8490) time: 0.1456 data: 0.0792 max mem: 8255 +Train: [55] [3200/6250] eta: 0:06:47 lr: 0.000056 grad: 0.1059 (0.0990) loss: 0.8461 (0.8488) time: 0.1571 data: 0.0893 max mem: 8255 +Train: [55] [3300/6250] eta: 0:06:35 lr: 0.000056 grad: 0.1100 (0.0990) loss: 0.8351 (0.8487) time: 0.1562 data: 0.0908 max mem: 8255 +Train: [55] [3400/6250] eta: 0:06:23 lr: 0.000056 grad: 0.0970 (0.0991) loss: 0.8463 (0.8486) time: 0.1417 data: 0.0686 max mem: 8255 +Train: [55] [3500/6250] eta: 0:06:11 lr: 0.000056 grad: 0.1021 (0.0992) loss: 0.8428 (0.8484) time: 0.1394 data: 0.0647 max mem: 8255 +Train: [55] [3600/6250] eta: 0:05:58 lr: 0.000056 grad: 0.1044 (0.0993) loss: 0.8353 (0.8482) time: 0.1401 data: 0.0736 max mem: 8255 +Train: [55] [3700/6250] eta: 0:05:44 lr: 0.000056 grad: 0.1027 (0.0995) loss: 0.8459 (0.8480) time: 0.1347 data: 0.0696 max mem: 8255 +Train: [55] [3800/6250] eta: 0:05:30 lr: 0.000056 grad: 0.0964 (0.0996) loss: 0.8452 (0.8478) time: 0.1294 data: 0.0581 max mem: 8255 +Train: [55] [3900/6250] eta: 0:05:16 lr: 0.000056 grad: 0.1006 (0.0997) loss: 0.8406 (0.8476) time: 0.1274 data: 0.0539 max mem: 8255 +Train: [55] [4000/6250] eta: 0:05:02 lr: 0.000056 grad: 0.0992 (0.0998) loss: 0.8426 (0.8475) time: 0.1189 data: 0.0407 max mem: 8255 +Train: [55] [4100/6250] eta: 0:04:49 lr: 0.000056 grad: 0.1010 (0.0999) loss: 0.8420 (0.8474) time: 0.1336 data: 0.0656 max mem: 8255 +Train: [55] [4200/6250] eta: 0:04:36 lr: 0.000056 grad: 0.0988 (0.0999) loss: 0.8411 (0.8472) time: 0.1438 data: 0.0819 max mem: 8255 +Train: [55] [4300/6250] eta: 0:04:24 lr: 0.000056 grad: 0.1030 (0.1001) loss: 0.8424 (0.8470) time: 0.1775 data: 0.1086 max mem: 8255 +Train: [55] [4400/6250] eta: 0:04:12 lr: 0.000056 grad: 0.1031 (0.1002) loss: 0.8410 (0.8468) time: 0.1264 data: 0.0515 max mem: 8255 +Train: [55] [4500/6250] eta: 0:03:59 lr: 0.000056 grad: 0.1004 (0.1003) loss: 0.8377 (0.8467) time: 0.1521 data: 0.0833 max mem: 8255 +Train: [55] [4600/6250] eta: 0:03:46 lr: 0.000056 grad: 0.0968 (0.1003) loss: 0.8403 (0.8466) time: 0.1496 data: 0.0780 max mem: 8255 +Train: [55] [4700/6250] eta: 0:03:33 lr: 0.000056 grad: 0.1056 (0.1005) loss: 0.8405 (0.8464) time: 0.1584 data: 0.0888 max mem: 8255 +Train: [55] [4800/6250] eta: 0:03:19 lr: 0.000056 grad: 0.1015 (0.1006) loss: 0.8408 (0.8463) time: 0.1653 data: 0.1015 max mem: 8255 +Train: [55] [4900/6250] eta: 0:03:06 lr: 0.000056 grad: 0.0962 (0.1006) loss: 0.8417 (0.8461) time: 0.1637 data: 0.0981 max mem: 8255 +Train: [55] [5000/6250] eta: 0:02:52 lr: 0.000056 grad: 0.1048 (0.1007) loss: 0.8366 (0.8460) time: 0.1527 data: 0.0899 max mem: 8255 +Train: [55] [5100/6250] eta: 0:02:39 lr: 0.000056 grad: 0.1073 (0.1008) loss: 0.8374 (0.8459) time: 0.1879 data: 0.1032 max mem: 8255 +Train: [55] [5200/6250] eta: 0:02:25 lr: 0.000056 grad: 0.1079 (0.1009) loss: 0.8390 (0.8457) time: 0.1040 data: 0.0138 max mem: 8255 +Train: [55] [5300/6250] eta: 0:02:11 lr: 0.000056 grad: 0.1025 (0.1010) loss: 0.8362 (0.8455) time: 0.1432 data: 0.0822 max mem: 8255 +Train: [55] [5400/6250] eta: 0:01:58 lr: 0.000056 grad: 0.0943 (0.1011) loss: 0.8450 (0.8454) time: 0.3376 data: 0.2642 max mem: 8255 +Train: [55] [5500/6250] eta: 0:01:44 lr: 0.000056 grad: 0.1034 (0.1012) loss: 0.8439 (0.8453) time: 0.1292 data: 0.0526 max mem: 8255 +Train: [55] [5600/6250] eta: 0:01:30 lr: 0.000055 grad: 0.1043 (0.1013) loss: 0.8386 (0.8451) time: 0.1658 data: 0.0941 max mem: 8255 +Train: [55] [5700/6250] eta: 0:01:16 lr: 0.000055 grad: 0.1014 (0.1013) loss: 0.8416 (0.8451) time: 0.1085 data: 0.0363 max mem: 8255 +Train: [55] [5800/6250] eta: 0:01:02 lr: 0.000055 grad: 0.0982 (0.1014) loss: 0.8415 (0.8450) time: 0.1283 data: 0.0641 max mem: 8255 +Train: [55] [5900/6250] eta: 0:00:48 lr: 0.000055 grad: 0.0984 (0.1014) loss: 0.8423 (0.8450) time: 0.1299 data: 0.0536 max mem: 8255 +Train: [55] [6000/6250] eta: 0:00:34 lr: 0.000055 grad: 0.0955 (0.1014) loss: 0.8439 (0.8450) time: 0.1333 data: 0.0657 max mem: 8255 +Train: [55] [6100/6250] eta: 0:00:20 lr: 0.000055 grad: 0.1003 (0.1014) loss: 0.8434 (0.8450) time: 0.1175 data: 0.0540 max mem: 8255 +Train: [55] [6200/6250] eta: 0:00:06 lr: 0.000055 grad: 0.1049 (0.1015) loss: 0.8382 (0.8449) time: 0.0869 data: 0.0002 max mem: 8255 +Train: [55] [6249/6250] eta: 0:00:00 lr: 0.000055 grad: 0.1035 (0.1015) loss: 0.8405 (0.8449) time: 0.1319 data: 0.0624 max mem: 8255 +Train: [55] Total time: 0:14:34 (0.1399 s / it) +Averaged stats: lr: 0.000055 grad: 0.1035 (0.1015) loss: 0.8405 (0.8449) +Eval (hcp-train-subset): [55] [ 0/62] eta: 0:03:48 loss: 0.8842 (0.8842) time: 3.6813 data: 3.6256 max mem: 8255 +Eval (hcp-train-subset): [55] [61/62] eta: 0:00:00 loss: 0.8708 (0.8741) time: 0.1243 data: 0.1041 max mem: 8255 +Eval (hcp-train-subset): [55] Total time: 0:00:11 (0.1923 s / it) +Averaged stats (hcp-train-subset): loss: 0.8708 (0.8741) +Eval (hcp-val): [55] [ 0/62] eta: 0:04:32 loss: 0.8732 (0.8732) time: 4.3974 data: 4.3437 max mem: 8255 +Eval (hcp-val): [55] [61/62] eta: 0:00:00 loss: 0.8766 (0.8775) time: 0.1287 data: 0.1068 max mem: 8255 +Eval (hcp-val): [55] Total time: 0:00:13 (0.2188 s / it) +Averaged stats (hcp-val): loss: 0.8766 (0.8775) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +Train: [56] [ 0/6250] eta: 9:36:35 lr: 0.000055 grad: 0.0748 (0.0748) loss: 0.8962 (0.8962) time: 5.5353 data: 5.4395 max mem: 8255 +Train: [56] [ 100/6250] eta: 0:20:34 lr: 0.000055 grad: 0.1158 (0.1432) loss: 0.8547 (0.8565) time: 0.1584 data: 0.0671 max mem: 8255 +Train: [56] [ 200/6250] eta: 0:17:14 lr: 0.000055 grad: 0.1061 (0.1344) loss: 0.8459 (0.8490) time: 0.1368 data: 0.0521 max mem: 8255 +Train: [56] [ 300/6250] eta: 0:15:36 lr: 0.000055 grad: 0.0910 (0.1236) loss: 0.8571 (0.8481) time: 0.1178 data: 0.0402 max mem: 8255 +Train: [56] [ 400/6250] eta: 0:14:29 lr: 0.000055 grad: 0.0899 (0.1168) loss: 0.8501 (0.8488) time: 0.1295 data: 0.0524 max mem: 8255 +Train: [56] [ 500/6250] eta: 0:13:42 lr: 0.000055 grad: 0.1026 (0.1136) loss: 0.8511 (0.8493) time: 0.1390 data: 0.0577 max mem: 8255 +Train: [56] [ 600/6250] eta: 0:13:03 lr: 0.000055 grad: 0.0968 (0.1111) loss: 0.8488 (0.8491) time: 0.1251 data: 0.0477 max mem: 8255 +Train: [56] [ 700/6250] eta: 0:12:31 lr: 0.000055 grad: 0.0947 (0.1095) loss: 0.8489 (0.8489) time: 0.1162 data: 0.0308 max mem: 8255 +Train: [56] [ 800/6250] eta: 0:12:23 lr: 0.000055 grad: 0.0992 (0.1080) loss: 0.8507 (0.8485) time: 0.1603 data: 0.0769 max mem: 8255 +Train: [56] [ 900/6250] eta: 0:12:18 lr: 0.000055 grad: 0.0978 (0.1074) loss: 0.8474 (0.8485) time: 0.1665 data: 0.0970 max mem: 8255 +Train: [56] [1000/6250] eta: 0:12:21 lr: 0.000055 grad: 0.0905 (0.1066) loss: 0.8512 (0.8485) time: 0.1643 data: 0.0896 max mem: 8255 +Train: [56] [1100/6250] eta: 0:12:12 lr: 0.000055 grad: 0.0950 (0.1059) loss: 0.8477 (0.8483) time: 0.1551 data: 0.0887 max mem: 8255 +Train: [56] [1200/6250] eta: 0:12:02 lr: 0.000055 grad: 0.1035 (0.1055) loss: 0.8405 (0.8481) time: 0.1370 data: 0.0630 max mem: 8255 +Train: [56] [1300/6250] eta: 0:11:51 lr: 0.000055 grad: 0.0969 (0.1051) loss: 0.8451 (0.8479) time: 0.1643 data: 0.0960 max mem: 8255 +Train: [56] [1400/6250] eta: 0:11:39 lr: 0.000055 grad: 0.1003 (0.1049) loss: 0.8389 (0.8477) time: 0.1604 data: 0.0897 max mem: 8255 +Train: [56] [1500/6250] eta: 0:11:29 lr: 0.000055 grad: 0.1002 (0.1049) loss: 0.8362 (0.8473) time: 0.1591 data: 0.0924 max mem: 8255 +Train: [56] [1600/6250] eta: 0:11:16 lr: 0.000055 grad: 0.1043 (0.1050) loss: 0.8442 (0.8471) time: 0.1545 data: 0.0786 max mem: 8255 +Train: [56] [1700/6250] eta: 0:11:01 lr: 0.000055 grad: 0.1022 (0.1050) loss: 0.8466 (0.8470) time: 0.1419 data: 0.0721 max mem: 8255 +Train: [56] [1800/6250] eta: 0:10:44 lr: 0.000055 grad: 0.1006 (0.1049) loss: 0.8437 (0.8469) time: 0.1371 data: 0.0680 max mem: 8255 +Train: [56] [1900/6250] eta: 0:10:26 lr: 0.000055 grad: 0.0982 (0.1048) loss: 0.8452 (0.8468) time: 0.1326 data: 0.0649 max mem: 8255 +Train: [56] [2000/6250] eta: 0:10:11 lr: 0.000055 grad: 0.0987 (0.1048) loss: 0.8416 (0.8466) time: 0.2080 data: 0.0791 max mem: 8255 +Train: [56] [2100/6250] eta: 0:09:59 lr: 0.000055 grad: 0.1055 (0.1048) loss: 0.8469 (0.8465) time: 0.1058 data: 0.0204 max mem: 8255 +Train: [56] [2200/6250] eta: 0:09:44 lr: 0.000055 grad: 0.0975 (0.1047) loss: 0.8437 (0.8463) time: 0.1413 data: 0.0717 max mem: 8255 +Train: [56] [2300/6250] eta: 0:09:28 lr: 0.000055 grad: 0.1038 (0.1047) loss: 0.8356 (0.8461) time: 0.1387 data: 0.0651 max mem: 8255 +Train: [56] [2400/6250] eta: 0:09:13 lr: 0.000054 grad: 0.1023 (0.1047) loss: 0.8431 (0.8459) time: 0.1464 data: 0.0648 max mem: 8255 +Train: [56] [2500/6250] eta: 0:09:01 lr: 0.000054 grad: 0.1016 (0.1046) loss: 0.8423 (0.8458) time: 0.1216 data: 0.0504 max mem: 8255 +Train: [56] [2600/6250] eta: 0:08:44 lr: 0.000054 grad: 0.0956 (0.1045) loss: 0.8461 (0.8457) time: 0.1417 data: 0.0705 max mem: 8255 +Train: [56] [2700/6250] eta: 0:08:28 lr: 0.000054 grad: 0.0984 (0.1045) loss: 0.8426 (0.8456) time: 0.1409 data: 0.0559 max mem: 8255 +Train: [56] [2800/6250] eta: 0:08:14 lr: 0.000054 grad: 0.1004 (0.1044) loss: 0.8410 (0.8455) time: 0.1008 data: 0.0003 max mem: 8255 +Train: [56] [2900/6250] eta: 0:08:01 lr: 0.000054 grad: 0.1018 (0.1043) loss: 0.8390 (0.8455) time: 0.2110 data: 0.1402 max mem: 8255 +Train: [56] [3000/6250] eta: 0:07:47 lr: 0.000054 grad: 0.1025 (0.1042) loss: 0.8423 (0.8454) time: 0.1142 data: 0.0400 max mem: 8255 +Train: [56] [3100/6250] eta: 0:07:31 lr: 0.000054 grad: 0.1071 (0.1043) loss: 0.8334 (0.8452) time: 0.1358 data: 0.0667 max mem: 8255 +Train: [56] [3200/6250] eta: 0:07:16 lr: 0.000054 grad: 0.1037 (0.1042) loss: 0.8337 (0.8450) time: 0.1256 data: 0.0556 max mem: 8255 +Train: [56] [3300/6250] eta: 0:07:02 lr: 0.000054 grad: 0.1010 (0.1043) loss: 0.8409 (0.8448) time: 0.1560 data: 0.0843 max mem: 8255 +Train: [56] [3400/6250] eta: 0:06:48 lr: 0.000054 grad: 0.0991 (0.1043) loss: 0.8362 (0.8447) time: 0.1478 data: 0.0845 max mem: 8255 +Train: [56] [3500/6250] eta: 0:06:32 lr: 0.000054 grad: 0.1021 (0.1042) loss: 0.8373 (0.8445) time: 0.1257 data: 0.0583 max mem: 8255 +Train: [56] [3600/6250] eta: 0:06:18 lr: 0.000054 grad: 0.1095 (0.1043) loss: 0.8419 (0.8444) time: 0.1341 data: 0.0590 max mem: 8255 +Train: [56] [3700/6250] eta: 0:06:03 lr: 0.000054 grad: 0.0980 (0.1043) loss: 0.8327 (0.8443) time: 0.1255 data: 0.0615 max mem: 8255 +Train: [56] [3800/6250] eta: 0:05:48 lr: 0.000054 grad: 0.1016 (0.1043) loss: 0.8428 (0.8442) time: 0.1174 data: 0.0481 max mem: 8255 +Train: [56] [3900/6250] eta: 0:05:32 lr: 0.000054 grad: 0.0993 (0.1043) loss: 0.8432 (0.8442) time: 0.1168 data: 0.0443 max mem: 8255 +Train: [56] [4000/6250] eta: 0:05:17 lr: 0.000054 grad: 0.0972 (0.1043) loss: 0.8383 (0.8441) time: 0.1075 data: 0.0342 max mem: 8255 +Train: [56] [4100/6250] eta: 0:05:01 lr: 0.000054 grad: 0.0950 (0.1043) loss: 0.8447 (0.8440) time: 0.1220 data: 0.0494 max mem: 8255 +Train: [56] [4200/6250] eta: 0:04:46 lr: 0.000054 grad: 0.1077 (0.1043) loss: 0.8374 (0.8440) time: 0.1107 data: 0.0382 max mem: 8255 +Train: [56] [4300/6250] eta: 0:04:31 lr: 0.000054 grad: 0.0970 (0.1043) loss: 0.8402 (0.8439) time: 0.1231 data: 0.0525 max mem: 8255 +Train: [56] [4400/6250] eta: 0:04:16 lr: 0.000054 grad: 0.1018 (0.1043) loss: 0.8389 (0.8438) time: 0.1160 data: 0.0448 max mem: 8255 +Train: [56] [4500/6250] eta: 0:04:02 lr: 0.000054 grad: 0.1006 (0.1043) loss: 0.8491 (0.8438) time: 0.1217 data: 0.0545 max mem: 8255 +Train: [56] [4600/6250] eta: 0:03:47 lr: 0.000054 grad: 0.1001 (0.1043) loss: 0.8407 (0.8438) time: 0.1142 data: 0.0463 max mem: 8255 +Train: [56] [4700/6250] eta: 0:03:33 lr: 0.000054 grad: 0.0978 (0.1042) loss: 0.8475 (0.8437) time: 0.1695 data: 0.0783 max mem: 8255 +Train: [56] [4800/6250] eta: 0:03:19 lr: 0.000054 grad: 0.1118 (0.1042) loss: 0.8413 (0.8436) time: 0.1322 data: 0.0591 max mem: 8255 +Train: [56] [4900/6250] eta: 0:03:05 lr: 0.000054 grad: 0.1027 (0.1043) loss: 0.8398 (0.8435) time: 0.1036 data: 0.0315 max mem: 8255 +Train: [56] [5000/6250] eta: 0:02:51 lr: 0.000054 grad: 0.0993 (0.1043) loss: 0.8449 (0.8435) time: 0.1266 data: 0.0570 max mem: 8255 +Train: [56] [5100/6250] eta: 0:02:37 lr: 0.000054 grad: 0.1024 (0.1043) loss: 0.8373 (0.8435) time: 0.1336 data: 0.0667 max mem: 8255 +Train: [56] [5200/6250] eta: 0:02:23 lr: 0.000054 grad: 0.1030 (0.1043) loss: 0.8390 (0.8434) time: 0.1475 data: 0.0806 max mem: 8255 +Train: [56] [5300/6250] eta: 0:02:09 lr: 0.000054 grad: 0.1046 (0.1043) loss: 0.8417 (0.8434) time: 0.1185 data: 0.0456 max mem: 8255 +Train: [56] [5400/6250] eta: 0:01:56 lr: 0.000054 grad: 0.1023 (0.1043) loss: 0.8429 (0.8433) time: 0.1293 data: 0.0592 max mem: 8255 +Train: [56] [5500/6250] eta: 0:01:42 lr: 0.000053 grad: 0.1078 (0.1043) loss: 0.8377 (0.8433) time: 0.1211 data: 0.0492 max mem: 8255 +Train: [56] [5600/6250] eta: 0:01:28 lr: 0.000053 grad: 0.0977 (0.1043) loss: 0.8438 (0.8432) time: 0.1233 data: 0.0498 max mem: 8255 +Train: [56] [5700/6250] eta: 0:01:14 lr: 0.000053 grad: 0.1018 (0.1044) loss: 0.8408 (0.8432) time: 0.1212 data: 0.0505 max mem: 8255 +Train: [56] [5800/6250] eta: 0:01:01 lr: 0.000053 grad: 0.1065 (0.1044) loss: 0.8409 (0.8431) time: 0.1364 data: 0.0629 max mem: 8255 +Train: [56] [5900/6250] eta: 0:00:47 lr: 0.000053 grad: 0.1042 (0.1044) loss: 0.8355 (0.8431) time: 0.1221 data: 0.0493 max mem: 8255 +Train: [56] [6000/6250] eta: 0:00:33 lr: 0.000053 grad: 0.1071 (0.1044) loss: 0.8361 (0.8430) time: 0.1188 data: 0.0469 max mem: 8255 +Train: [56] [6100/6250] eta: 0:00:20 lr: 0.000053 grad: 0.1035 (0.1045) loss: 0.8354 (0.8429) time: 0.1251 data: 0.0532 max mem: 8255 +Train: [56] [6200/6250] eta: 0:00:06 lr: 0.000053 grad: 0.1038 (0.1045) loss: 0.8452 (0.8428) time: 0.1418 data: 0.0761 max mem: 8255 +Train: [56] [6249/6250] eta: 0:00:00 lr: 0.000053 grad: 0.0992 (0.1045) loss: 0.8320 (0.8428) time: 0.1202 data: 0.0571 max mem: 8255 +Train: [56] Total time: 0:14:12 (0.1365 s / it) +Averaged stats: lr: 0.000053 grad: 0.0992 (0.1045) loss: 0.8320 (0.8428) +Eval (hcp-train-subset): [56] [ 0/62] eta: 0:04:45 loss: 0.8872 (0.8872) time: 4.5972 data: 4.5697 max mem: 8255 +Eval (hcp-train-subset): [56] [61/62] eta: 0:00:00 loss: 0.8725 (0.8733) time: 0.1159 data: 0.0950 max mem: 8255 +Eval (hcp-train-subset): [56] Total time: 0:00:13 (0.2145 s / it) +Averaged stats (hcp-train-subset): loss: 0.8725 (0.8733) +Eval (hcp-val): [56] [ 0/62] eta: 0:04:51 loss: 0.8765 (0.8765) time: 4.7082 data: 4.6787 max mem: 8255 +Eval (hcp-val): [56] [61/62] eta: 0:00:00 loss: 0.8772 (0.8788) time: 0.1426 data: 0.1221 max mem: 8255 +Eval (hcp-val): [56] Total time: 0:00:13 (0.2215 s / it) +Averaged stats (hcp-val): loss: 0.8772 (0.8788) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +Train: [57] [ 0/6250] eta: 10:14:12 lr: 0.000053 grad: 0.1793 (0.1793) loss: 0.8730 (0.8730) time: 5.8963 data: 5.8059 max mem: 8255 +Train: [57] [ 100/6250] eta: 0:20:44 lr: 0.000053 grad: 0.1027 (0.1437) loss: 0.8480 (0.8608) time: 0.1612 data: 0.0508 max mem: 8255 +Train: [57] [ 200/6250] eta: 0:17:33 lr: 0.000053 grad: 0.1011 (0.1264) loss: 0.8497 (0.8570) time: 0.1181 data: 0.0228 max mem: 8255 +Train: [57] [ 300/6250] eta: 0:16:18 lr: 0.000053 grad: 0.1080 (0.1211) loss: 0.8504 (0.8554) time: 0.1452 data: 0.0624 max mem: 8255 +Train: [57] [ 400/6250] eta: 0:15:13 lr: 0.000053 grad: 0.0958 (0.1166) loss: 0.8508 (0.8539) time: 0.1266 data: 0.0503 max mem: 8255 +Train: [57] [ 500/6250] eta: 0:14:22 lr: 0.000053 grad: 0.0982 (0.1137) loss: 0.8488 (0.8536) time: 0.1339 data: 0.0602 max mem: 8255 +Train: [57] [ 600/6250] eta: 0:13:52 lr: 0.000053 grad: 0.1067 (0.1125) loss: 0.8420 (0.8524) time: 0.1260 data: 0.0487 max mem: 8255 +Train: [57] [ 700/6250] eta: 0:13:39 lr: 0.000053 grad: 0.0957 (0.1109) loss: 0.8507 (0.8517) time: 0.1197 data: 0.0372 max mem: 8255 +Train: [57] [ 800/6250] eta: 0:13:54 lr: 0.000053 grad: 0.1012 (0.1098) loss: 0.8497 (0.8512) time: 0.0983 data: 0.0120 max mem: 8255 +Train: [57] [ 900/6250] eta: 0:13:31 lr: 0.000053 grad: 0.1048 (0.1088) loss: 0.8456 (0.8508) time: 0.1286 data: 0.0527 max mem: 8255 +Train: [57] [1000/6250] eta: 0:13:07 lr: 0.000053 grad: 0.1056 (0.1083) loss: 0.8375 (0.8505) time: 0.1300 data: 0.0541 max mem: 8255 +Train: [57] [1100/6250] eta: 0:12:45 lr: 0.000053 grad: 0.0997 (0.1076) loss: 0.8475 (0.8503) time: 0.1233 data: 0.0545 max mem: 8255 +Train: [57] [1200/6250] eta: 0:12:21 lr: 0.000053 grad: 0.0941 (0.1070) loss: 0.8452 (0.8501) time: 0.1247 data: 0.0563 max mem: 8255 +Train: [57] [1300/6250] eta: 0:12:01 lr: 0.000053 grad: 0.0993 (0.1065) loss: 0.8409 (0.8499) time: 0.1269 data: 0.0466 max mem: 8255 +Train: [57] [1400/6250] eta: 0:11:47 lr: 0.000053 grad: 0.0933 (0.1061) loss: 0.8417 (0.8495) time: 0.1760 data: 0.1052 max mem: 8255 +Train: [57] [1500/6250] eta: 0:11:28 lr: 0.000053 grad: 0.0991 (0.1056) loss: 0.8488 (0.8493) time: 0.1304 data: 0.0681 max mem: 8255 +Train: [57] [1600/6250] eta: 0:11:11 lr: 0.000053 grad: 0.0941 (0.1054) loss: 0.8447 (0.8489) time: 0.1479 data: 0.0797 max mem: 8255 +Train: [57] [1700/6250] eta: 0:10:51 lr: 0.000053 grad: 0.0959 (0.1052) loss: 0.8415 (0.8485) time: 0.1256 data: 0.0536 max mem: 8255 +Train: [57] [1800/6250] eta: 0:10:35 lr: 0.000053 grad: 0.0990 (0.1048) loss: 0.8510 (0.8481) time: 0.1147 data: 0.0317 max mem: 8255 +Train: [57] [1900/6250] eta: 0:10:17 lr: 0.000053 grad: 0.0974 (0.1046) loss: 0.8518 (0.8480) time: 0.1196 data: 0.0419 max mem: 8255 +Train: [57] [2000/6250] eta: 0:10:00 lr: 0.000053 grad: 0.1012 (0.1045) loss: 0.8373 (0.8479) time: 0.1251 data: 0.0534 max mem: 8255 +Train: [57] [2100/6250] eta: 0:09:44 lr: 0.000053 grad: 0.0983 (0.1043) loss: 0.8447 (0.8478) time: 0.1136 data: 0.0468 max mem: 8255 +Train: [57] [2200/6250] eta: 0:09:27 lr: 0.000053 grad: 0.1021 (0.1042) loss: 0.8459 (0.8477) time: 0.1300 data: 0.0570 max mem: 8255 +Train: [57] [2300/6250] eta: 0:09:13 lr: 0.000052 grad: 0.0934 (0.1040) loss: 0.8498 (0.8478) time: 0.1393 data: 0.0653 max mem: 8255 +Train: [57] [2400/6250] eta: 0:08:59 lr: 0.000052 grad: 0.1041 (0.1039) loss: 0.8498 (0.8478) time: 0.1454 data: 0.0801 max mem: 8255 +Train: [57] [2500/6250] eta: 0:08:44 lr: 0.000052 grad: 0.0949 (0.1040) loss: 0.8423 (0.8478) time: 0.1122 data: 0.0370 max mem: 8255 +Train: [57] [2600/6250] eta: 0:08:29 lr: 0.000052 grad: 0.0999 (0.1039) loss: 0.8418 (0.8477) time: 0.1486 data: 0.0803 max mem: 8255 +Train: [57] [2700/6250] eta: 0:08:14 lr: 0.000052 grad: 0.1000 (0.1039) loss: 0.8472 (0.8477) time: 0.1396 data: 0.0656 max mem: 8255 +Train: [57] [2800/6250] eta: 0:08:00 lr: 0.000052 grad: 0.1025 (0.1040) loss: 0.8368 (0.8474) time: 0.1227 data: 0.0489 max mem: 8255 +Train: [57] [2900/6250] eta: 0:07:46 lr: 0.000052 grad: 0.1034 (0.1040) loss: 0.8424 (0.8472) time: 0.1171 data: 0.0531 max mem: 8255 +Train: [57] [3000/6250] eta: 0:07:31 lr: 0.000052 grad: 0.0895 (0.1040) loss: 0.8485 (0.8471) time: 0.1339 data: 0.0582 max mem: 8255 +Train: [57] [3100/6250] eta: 0:07:17 lr: 0.000052 grad: 0.0959 (0.1039) loss: 0.8501 (0.8470) time: 0.1315 data: 0.0547 max mem: 8255 +Train: [57] [3200/6250] eta: 0:07:02 lr: 0.000052 grad: 0.0963 (0.1038) loss: 0.8494 (0.8471) time: 0.1381 data: 0.0659 max mem: 8255 +Train: [57] [3300/6250] eta: 0:06:48 lr: 0.000052 grad: 0.1028 (0.1037) loss: 0.8444 (0.8470) time: 0.1437 data: 0.0761 max mem: 8255 +Train: [57] [3400/6250] eta: 0:06:34 lr: 0.000052 grad: 0.0977 (0.1036) loss: 0.8524 (0.8470) time: 0.1593 data: 0.0832 max mem: 8255 +Train: [57] [3500/6250] eta: 0:06:22 lr: 0.000052 grad: 0.0937 (0.1035) loss: 0.8471 (0.8470) time: 0.1524 data: 0.0816 max mem: 8255 +Train: [57] [3600/6250] eta: 0:06:10 lr: 0.000052 grad: 0.0968 (0.1035) loss: 0.8449 (0.8469) time: 0.1853 data: 0.1147 max mem: 8255 +Train: [57] [3700/6250] eta: 0:05:56 lr: 0.000052 grad: 0.0932 (0.1035) loss: 0.8483 (0.8469) time: 0.1465 data: 0.0749 max mem: 8255 +Train: [57] [3800/6250] eta: 0:05:43 lr: 0.000052 grad: 0.1066 (0.1035) loss: 0.8356 (0.8468) time: 0.1664 data: 0.0970 max mem: 8255 +Train: [57] [3900/6250] eta: 0:05:29 lr: 0.000052 grad: 0.1013 (0.1035) loss: 0.8505 (0.8468) time: 0.1579 data: 0.0844 max mem: 8255 +Train: [57] [4000/6250] eta: 0:05:15 lr: 0.000052 grad: 0.1007 (0.1035) loss: 0.8440 (0.8468) time: 0.1422 data: 0.0685 max mem: 8255 +Train: [57] [4100/6250] eta: 0:05:00 lr: 0.000052 grad: 0.0986 (0.1036) loss: 0.8425 (0.8468) time: 0.1314 data: 0.0533 max mem: 8255 +Train: [57] [4200/6250] eta: 0:04:46 lr: 0.000052 grad: 0.0994 (0.1036) loss: 0.8451 (0.8467) time: 0.1204 data: 0.0410 max mem: 8255 +Train: [57] [4300/6250] eta: 0:04:31 lr: 0.000052 grad: 0.0993 (0.1037) loss: 0.8472 (0.8466) time: 0.1134 data: 0.0371 max mem: 8255 +Train: [57] [4400/6250] eta: 0:04:16 lr: 0.000052 grad: 0.1014 (0.1037) loss: 0.8489 (0.8465) time: 0.1349 data: 0.0683 max mem: 8255 +Train: [57] [4500/6250] eta: 0:04:03 lr: 0.000052 grad: 0.0971 (0.1036) loss: 0.8481 (0.8465) time: 0.1433 data: 0.0754 max mem: 8255 +Train: [57] [4600/6250] eta: 0:03:50 lr: 0.000052 grad: 0.0986 (0.1036) loss: 0.8485 (0.8464) time: 0.1958 data: 0.1326 max mem: 8255 +Train: [57] [4700/6250] eta: 0:03:37 lr: 0.000052 grad: 0.0994 (0.1035) loss: 0.8397 (0.8464) time: 0.1869 data: 0.1282 max mem: 8255 +Train: [57] [4800/6250] eta: 0:03:24 lr: 0.000052 grad: 0.0963 (0.1035) loss: 0.8459 (0.8464) time: 0.1665 data: 0.1011 max mem: 8255 +Train: [57] [4900/6250] eta: 0:03:10 lr: 0.000052 grad: 0.0953 (0.1035) loss: 0.8501 (0.8464) time: 0.1769 data: 0.1121 max mem: 8255 +Train: [57] [5000/6250] eta: 0:02:56 lr: 0.000052 grad: 0.0979 (0.1035) loss: 0.8409 (0.8463) time: 0.1132 data: 0.0408 max mem: 8255 +Train: [57] [5100/6250] eta: 0:02:42 lr: 0.000052 grad: 0.1000 (0.1035) loss: 0.8377 (0.8463) time: 0.1522 data: 0.0831 max mem: 8255 +Train: [57] [5200/6250] eta: 0:02:27 lr: 0.000052 grad: 0.0996 (0.1035) loss: 0.8482 (0.8462) time: 0.1083 data: 0.0304 max mem: 8255 +Train: [57] [5300/6250] eta: 0:02:13 lr: 0.000052 grad: 0.0964 (0.1034) loss: 0.8434 (0.8462) time: 0.1376 data: 0.0681 max mem: 8255 +Train: [57] [5400/6250] eta: 0:01:59 lr: 0.000051 grad: 0.0987 (0.1034) loss: 0.8426 (0.8462) time: 0.1335 data: 0.0666 max mem: 8255 +Train: [57] [5500/6250] eta: 0:01:45 lr: 0.000051 grad: 0.0992 (0.1034) loss: 0.8395 (0.8462) time: 0.0959 data: 0.0121 max mem: 8255 +Train: [57] [5600/6250] eta: 0:01:32 lr: 0.000051 grad: 0.1006 (0.1033) loss: 0.8423 (0.8461) time: 0.0959 data: 0.0112 max mem: 8255 +Train: [57] [5700/6250] eta: 0:01:17 lr: 0.000051 grad: 0.1015 (0.1033) loss: 0.8426 (0.8461) time: 0.1343 data: 0.0599 max mem: 8255 +Train: [57] [5800/6250] eta: 0:01:03 lr: 0.000051 grad: 0.1063 (0.1033) loss: 0.8451 (0.8461) time: 0.1468 data: 0.0823 max mem: 8255 +Train: [57] [5900/6250] eta: 0:00:49 lr: 0.000051 grad: 0.1053 (0.1034) loss: 0.8395 (0.8461) time: 0.1121 data: 0.0381 max mem: 8255 +Train: [57] [6000/6250] eta: 0:00:35 lr: 0.000051 grad: 0.0997 (0.1034) loss: 0.8529 (0.8462) time: 0.1470 data: 0.0659 max mem: 8255 +Train: [57] [6100/6250] eta: 0:00:21 lr: 0.000051 grad: 0.0985 (0.1034) loss: 0.8557 (0.8462) time: 0.1311 data: 0.0641 max mem: 8255 +Train: [57] [6200/6250] eta: 0:00:07 lr: 0.000051 grad: 0.1028 (0.1035) loss: 0.8475 (0.8462) time: 0.1245 data: 0.0516 max mem: 8255 +Train: [57] [6249/6250] eta: 0:00:00 lr: 0.000051 grad: 0.1082 (0.1035) loss: 0.8413 (0.8462) time: 0.1269 data: 0.0683 max mem: 8255 +Train: [57] Total time: 0:14:45 (0.1417 s / it) +Averaged stats: lr: 0.000051 grad: 0.1082 (0.1035) loss: 0.8413 (0.8462) +Eval (hcp-train-subset): [57] [ 0/62] eta: 0:04:32 loss: 0.8846 (0.8846) time: 4.3959 data: 4.3709 max mem: 8255 +Eval (hcp-train-subset): [57] [61/62] eta: 0:00:00 loss: 0.8690 (0.8707) time: 0.1228 data: 0.1013 max mem: 8255 +Eval (hcp-train-subset): [57] Total time: 0:00:12 (0.2047 s / it) +Averaged stats (hcp-train-subset): loss: 0.8690 (0.8707) +Eval (hcp-val): [57] [ 0/62] eta: 0:04:05 loss: 0.8752 (0.8752) time: 3.9522 data: 3.8861 max mem: 8255 +Eval (hcp-val): [57] [61/62] eta: 0:00:00 loss: 0.8768 (0.8776) time: 0.1320 data: 0.1097 max mem: 8255 +Eval (hcp-val): [57] Total time: 0:00:13 (0.2142 s / it) +Averaged stats (hcp-val): loss: 0.8768 (0.8776) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +Train: [58] [ 0/6250] eta: 10:01:50 lr: 0.000051 grad: 0.1991 (0.1991) loss: 0.8907 (0.8907) time: 5.7777 data: 5.6793 max mem: 8255 +Train: [58] [ 100/6250] eta: 0:19:37 lr: 0.000051 grad: 0.1129 (0.1215) loss: 0.8619 (0.8709) time: 0.1513 data: 0.0662 max mem: 8255 +Train: [58] [ 200/6250] eta: 0:16:41 lr: 0.000051 grad: 0.1143 (0.1215) loss: 0.8511 (0.8606) time: 0.1455 data: 0.0602 max mem: 8255 +Train: [58] [ 300/6250] eta: 0:15:28 lr: 0.000051 grad: 0.0982 (0.1165) loss: 0.8514 (0.8569) time: 0.1106 data: 0.0260 max mem: 8255 +Train: [58] [ 400/6250] eta: 0:14:29 lr: 0.000051 grad: 0.0977 (0.1129) loss: 0.8597 (0.8548) time: 0.1241 data: 0.0479 max mem: 8255 +Train: [58] [ 500/6250] eta: 0:13:43 lr: 0.000051 grad: 0.0880 (0.1103) loss: 0.8556 (0.8535) time: 0.1137 data: 0.0332 max mem: 8255 +Train: [58] [ 600/6250] eta: 0:13:03 lr: 0.000051 grad: 0.0943 (0.1088) loss: 0.8578 (0.8529) time: 0.1203 data: 0.0412 max mem: 8255 +Train: [58] [ 700/6250] eta: 0:12:33 lr: 0.000051 grad: 0.0926 (0.1072) loss: 0.8563 (0.8528) time: 0.1175 data: 0.0418 max mem: 8255 +Train: [58] [ 800/6250] eta: 0:12:15 lr: 0.000051 grad: 0.0917 (0.1061) loss: 0.8550 (0.8531) time: 0.1212 data: 0.0361 max mem: 8255 +Train: [58] [ 900/6250] eta: 0:12:05 lr: 0.000051 grad: 0.1012 (0.1052) loss: 0.8533 (0.8534) time: 0.1420 data: 0.0720 max mem: 8255 +Train: [58] [1000/6250] eta: 0:11:46 lr: 0.000051 grad: 0.0903 (0.1044) loss: 0.8566 (0.8533) time: 0.1180 data: 0.0475 max mem: 8255 +Train: [58] [1100/6250] eta: 0:11:28 lr: 0.000051 grad: 0.0965 (0.1040) loss: 0.8511 (0.8530) time: 0.1262 data: 0.0551 max mem: 8255 +Train: [58] [1200/6250] eta: 0:11:13 lr: 0.000051 grad: 0.0965 (0.1037) loss: 0.8419 (0.8525) time: 0.1310 data: 0.0643 max mem: 8255 +Train: [58] [1300/6250] eta: 0:11:01 lr: 0.000051 grad: 0.0977 (0.1034) loss: 0.8479 (0.8521) time: 0.0889 data: 0.0071 max mem: 8255 +Train: [58] [1400/6250] eta: 0:10:56 lr: 0.000051 grad: 0.0993 (0.1032) loss: 0.8439 (0.8518) time: 0.2384 data: 0.1687 max mem: 8255 +Train: [58] [1500/6250] eta: 0:10:40 lr: 0.000051 grad: 0.1009 (0.1035) loss: 0.8523 (0.8513) time: 0.1091 data: 0.0354 max mem: 8255 +Train: [58] [1600/6250] eta: 0:10:28 lr: 0.000051 grad: 0.0986 (0.1034) loss: 0.8442 (0.8510) time: 0.1326 data: 0.0601 max mem: 8255 +Train: [58] [1700/6250] eta: 0:10:15 lr: 0.000051 grad: 0.1037 (0.1035) loss: 0.8398 (0.8506) time: 0.1422 data: 0.0683 max mem: 8255 +Train: [58] [1800/6250] eta: 0:10:04 lr: 0.000051 grad: 0.1049 (0.1035) loss: 0.8422 (0.8502) time: 0.1526 data: 0.0726 max mem: 8255 +Train: [58] [1900/6250] eta: 0:09:48 lr: 0.000051 grad: 0.0977 (0.1033) loss: 0.8525 (0.8500) time: 0.1340 data: 0.0641 max mem: 8255 +Train: [58] [2000/6250] eta: 0:09:36 lr: 0.000051 grad: 0.1018 (0.1033) loss: 0.8469 (0.8498) time: 0.1440 data: 0.0710 max mem: 8255 +Train: [58] [2100/6250] eta: 0:09:21 lr: 0.000051 grad: 0.0970 (0.1034) loss: 0.8440 (0.8496) time: 0.1285 data: 0.0637 max mem: 8255 +Train: [58] [2200/6250] eta: 0:09:07 lr: 0.000050 grad: 0.1054 (0.1034) loss: 0.8353 (0.8492) time: 0.1334 data: 0.0692 max mem: 8255 +Train: [58] [2300/6250] eta: 0:08:52 lr: 0.000050 grad: 0.1018 (0.1035) loss: 0.8437 (0.8489) time: 0.1288 data: 0.0587 max mem: 8255 +Train: [58] [2400/6250] eta: 0:08:38 lr: 0.000050 grad: 0.1070 (0.1037) loss: 0.8442 (0.8486) time: 0.1346 data: 0.0625 max mem: 8255 +Train: [58] [2500/6250] eta: 0:08:24 lr: 0.000050 grad: 0.1065 (0.1037) loss: 0.8363 (0.8482) time: 0.1202 data: 0.0572 max mem: 8255 +Train: [58] [2600/6250] eta: 0:08:12 lr: 0.000050 grad: 0.0994 (0.1037) loss: 0.8441 (0.8481) time: 0.0996 data: 0.0183 max mem: 8255 +Train: [58] [2700/6250] eta: 0:07:57 lr: 0.000050 grad: 0.1059 (0.1037) loss: 0.8401 (0.8478) time: 0.1266 data: 0.0566 max mem: 8255 +Train: [58] [2800/6250] eta: 0:07:43 lr: 0.000050 grad: 0.1034 (0.1037) loss: 0.8461 (0.8476) time: 0.1320 data: 0.0551 max mem: 8255 +Train: [58] [2900/6250] eta: 0:07:28 lr: 0.000050 grad: 0.0993 (0.1036) loss: 0.8403 (0.8474) time: 0.1167 data: 0.0406 max mem: 8255 +Train: [58] [3000/6250] eta: 0:07:15 lr: 0.000050 grad: 0.0920 (0.1036) loss: 0.8419 (0.8473) time: 0.1267 data: 0.0603 max mem: 8255 +Train: [58] [3100/6250] eta: 0:07:01 lr: 0.000050 grad: 0.1001 (0.1035) loss: 0.8433 (0.8472) time: 0.1228 data: 0.0488 max mem: 8255 +Train: [58] [3200/6250] eta: 0:06:49 lr: 0.000050 grad: 0.1004 (0.1035) loss: 0.8451 (0.8471) time: 0.1310 data: 0.0607 max mem: 8255 +Train: [58] [3300/6250] eta: 0:06:35 lr: 0.000050 grad: 0.1019 (0.1035) loss: 0.8459 (0.8469) time: 0.1120 data: 0.0382 max mem: 8255 +Train: [58] [3400/6250] eta: 0:06:22 lr: 0.000050 grad: 0.0959 (0.1035) loss: 0.8476 (0.8468) time: 0.1251 data: 0.0518 max mem: 8255 +Train: [58] [3500/6250] eta: 0:06:09 lr: 0.000050 grad: 0.0992 (0.1035) loss: 0.8421 (0.8467) time: 0.1565 data: 0.0876 max mem: 8255 +Train: [58] [3600/6250] eta: 0:05:56 lr: 0.000050 grad: 0.0976 (0.1035) loss: 0.8378 (0.8465) time: 0.1207 data: 0.0537 max mem: 8255 +Train: [58] [3700/6250] eta: 0:05:42 lr: 0.000050 grad: 0.1001 (0.1034) loss: 0.8435 (0.8465) time: 0.1299 data: 0.0661 max mem: 8255 +Train: [58] [3800/6250] eta: 0:05:29 lr: 0.000050 grad: 0.1004 (0.1034) loss: 0.8415 (0.8464) time: 0.1497 data: 0.0734 max mem: 8255 +Train: [58] [3900/6250] eta: 0:05:16 lr: 0.000050 grad: 0.0986 (0.1034) loss: 0.8442 (0.8463) time: 0.1336 data: 0.0540 max mem: 8255 +Train: [58] [4000/6250] eta: 0:05:03 lr: 0.000050 grad: 0.0979 (0.1034) loss: 0.8400 (0.8462) time: 0.1313 data: 0.0491 max mem: 8255 +Train: [58] [4100/6250] eta: 0:04:50 lr: 0.000050 grad: 0.1048 (0.1034) loss: 0.8428 (0.8461) time: 0.1289 data: 0.0543 max mem: 8255 +Train: [58] [4200/6250] eta: 0:04:36 lr: 0.000050 grad: 0.0959 (0.1034) loss: 0.8429 (0.8460) time: 0.1347 data: 0.0644 max mem: 8255 +Train: [58] [4300/6250] eta: 0:04:22 lr: 0.000050 grad: 0.1012 (0.1034) loss: 0.8441 (0.8459) time: 0.1193 data: 0.0486 max mem: 8255 +Train: [58] [4400/6250] eta: 0:04:08 lr: 0.000050 grad: 0.1004 (0.1034) loss: 0.8388 (0.8458) time: 0.0959 data: 0.0264 max mem: 8255 +Train: [58] [4500/6250] eta: 0:03:54 lr: 0.000050 grad: 0.1015 (0.1034) loss: 0.8330 (0.8457) time: 0.1050 data: 0.0335 max mem: 8255 +Train: [58] [4600/6250] eta: 0:03:40 lr: 0.000050 grad: 0.0961 (0.1034) loss: 0.8453 (0.8456) time: 0.1132 data: 0.0422 max mem: 8255 +Train: [58] [4700/6250] eta: 0:03:26 lr: 0.000050 grad: 0.1012 (0.1034) loss: 0.8484 (0.8455) time: 0.1349 data: 0.0632 max mem: 8255 +Train: [58] [4800/6250] eta: 0:03:12 lr: 0.000050 grad: 0.1014 (0.1035) loss: 0.8413 (0.8454) time: 0.1230 data: 0.0417 max mem: 8255 +Train: [58] [4900/6250] eta: 0:02:59 lr: 0.000050 grad: 0.1015 (0.1035) loss: 0.8385 (0.8453) time: 0.1349 data: 0.0675 max mem: 8255 +Train: [58] [5000/6250] eta: 0:02:46 lr: 0.000050 grad: 0.1066 (0.1036) loss: 0.8391 (0.8452) time: 0.1264 data: 0.0547 max mem: 8255 +Train: [58] [5100/6250] eta: 0:02:32 lr: 0.000050 grad: 0.1029 (0.1036) loss: 0.8492 (0.8451) time: 0.1357 data: 0.0693 max mem: 8255 +Train: [58] [5200/6250] eta: 0:02:19 lr: 0.000050 grad: 0.1083 (0.1036) loss: 0.8341 (0.8450) time: 0.1272 data: 0.0608 max mem: 8255 +Train: [58] [5300/6250] eta: 0:02:06 lr: 0.000049 grad: 0.1007 (0.1037) loss: 0.8456 (0.8450) time: 0.1373 data: 0.0651 max mem: 8255 +Train: [58] [5400/6250] eta: 0:01:52 lr: 0.000049 grad: 0.1033 (0.1038) loss: 0.8404 (0.8449) time: 0.1165 data: 0.0485 max mem: 8255 +Train: [58] [5500/6250] eta: 0:01:39 lr: 0.000049 grad: 0.1036 (0.1038) loss: 0.8374 (0.8449) time: 0.1276 data: 0.0569 max mem: 8255 +Train: [58] [5600/6250] eta: 0:01:26 lr: 0.000049 grad: 0.0987 (0.1038) loss: 0.8530 (0.8449) time: 0.1160 data: 0.0441 max mem: 8255 +Train: [58] [5700/6250] eta: 0:01:12 lr: 0.000049 grad: 0.1045 (0.1039) loss: 0.8444 (0.8449) time: 0.1258 data: 0.0562 max mem: 8255 +Train: [58] [5800/6250] eta: 0:00:59 lr: 0.000049 grad: 0.1004 (0.1039) loss: 0.8467 (0.8448) time: 0.1418 data: 0.0743 max mem: 8255 +Train: [58] [5900/6250] eta: 0:00:46 lr: 0.000049 grad: 0.0986 (0.1039) loss: 0.8448 (0.8448) time: 0.1413 data: 0.0674 max mem: 8255 +Train: [58] [6000/6250] eta: 0:00:33 lr: 0.000049 grad: 0.1004 (0.1040) loss: 0.8449 (0.8448) time: 0.1184 data: 0.0439 max mem: 8255 +Train: [58] [6100/6250] eta: 0:00:19 lr: 0.000049 grad: 0.1024 (0.1040) loss: 0.8432 (0.8448) time: 0.1233 data: 0.0498 max mem: 8255 +Train: [58] [6200/6250] eta: 0:00:06 lr: 0.000049 grad: 0.1074 (0.1040) loss: 0.8381 (0.8448) time: 0.1190 data: 0.0445 max mem: 8255 +Train: [58] [6249/6250] eta: 0:00:00 lr: 0.000049 grad: 0.1043 (0.1040) loss: 0.8403 (0.8447) time: 0.1454 data: 0.0655 max mem: 8255 +Train: [58] Total time: 0:13:50 (0.1330 s / it) +Averaged stats: lr: 0.000049 grad: 0.1043 (0.1040) loss: 0.8403 (0.8447) +Eval (hcp-train-subset): [58] [ 0/62] eta: 0:05:46 loss: 0.8896 (0.8896) time: 5.5945 data: 5.5692 max mem: 8255 +Eval (hcp-train-subset): [58] [61/62] eta: 0:00:00 loss: 0.8714 (0.8731) time: 0.1245 data: 0.1039 max mem: 8255 +Eval (hcp-train-subset): [58] Total time: 0:00:13 (0.2212 s / it) +Averaged stats (hcp-train-subset): loss: 0.8714 (0.8731) +Eval (hcp-val): [58] [ 0/62] eta: 0:04:41 loss: 0.8760 (0.8760) time: 4.5454 data: 4.5197 max mem: 8255 +Eval (hcp-val): [58] [61/62] eta: 0:00:00 loss: 0.8781 (0.8777) time: 0.1210 data: 0.1003 max mem: 8255 +Eval (hcp-val): [58] Total time: 0:00:13 (0.2128 s / it) +Averaged stats (hcp-val): loss: 0.8781 (0.8777) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +Train: [59] [ 0/6250] eta: 9:04:01 lr: 0.000049 grad: 0.1564 (0.1564) loss: 0.8838 (0.8838) time: 5.2226 data: 5.0469 max mem: 8255 +Train: [59] [ 100/6250] eta: 0:19:37 lr: 0.000049 grad: 0.1129 (0.1477) loss: 0.8551 (0.8605) time: 0.1421 data: 0.0497 max mem: 8255 +Train: [59] [ 200/6250] eta: 0:16:50 lr: 0.000049 grad: 0.1127 (0.1378) loss: 0.8479 (0.8510) time: 0.1386 data: 0.0609 max mem: 8255 +Train: [59] [ 300/6250] eta: 0:15:17 lr: 0.000049 grad: 0.1068 (0.1295) loss: 0.8377 (0.8485) time: 0.1070 data: 0.0377 max mem: 8255 +Train: [59] [ 400/6250] eta: 0:14:18 lr: 0.000049 grad: 0.1100 (0.1261) loss: 0.8339 (0.8458) time: 0.1150 data: 0.0372 max mem: 8255 +Train: [59] [ 500/6250] eta: 0:13:43 lr: 0.000049 grad: 0.1122 (0.1238) loss: 0.8348 (0.8445) time: 0.1222 data: 0.0379 max mem: 8255 +Train: [59] [ 600/6250] eta: 0:13:14 lr: 0.000049 grad: 0.1068 (0.1215) loss: 0.8324 (0.8429) time: 0.1356 data: 0.0527 max mem: 8255 +Train: [59] [ 700/6250] eta: 0:12:44 lr: 0.000049 grad: 0.1051 (0.1200) loss: 0.8444 (0.8422) time: 0.1179 data: 0.0425 max mem: 8255 +Train: [59] [ 800/6250] eta: 0:12:24 lr: 0.000049 grad: 0.1054 (0.1182) loss: 0.8515 (0.8423) time: 0.1275 data: 0.0492 max mem: 8255 +Train: [59] [ 900/6250] eta: 0:12:12 lr: 0.000049 grad: 0.1035 (0.1170) loss: 0.8457 (0.8419) time: 0.1428 data: 0.0699 max mem: 8255 +Train: [59] [1000/6250] eta: 0:12:04 lr: 0.000049 grad: 0.1087 (0.1161) loss: 0.8428 (0.8416) time: 0.1153 data: 0.0369 max mem: 8255 +Train: [59] [1100/6250] eta: 0:11:53 lr: 0.000049 grad: 0.0963 (0.1149) loss: 0.8476 (0.8415) time: 0.1359 data: 0.0596 max mem: 8255 +Train: [59] [1200/6250] eta: 0:11:42 lr: 0.000049 grad: 0.1068 (0.1144) loss: 0.8329 (0.8411) time: 0.1235 data: 0.0429 max mem: 8255 +Train: [59] [1300/6250] eta: 0:11:30 lr: 0.000049 grad: 0.1055 (0.1137) loss: 0.8481 (0.8409) time: 0.1842 data: 0.1165 max mem: 8255 +Train: [59] [1400/6250] eta: 0:11:13 lr: 0.000049 grad: 0.1029 (0.1129) loss: 0.8382 (0.8408) time: 0.1218 data: 0.0529 max mem: 8255 +Train: [59] [1500/6250] eta: 0:11:00 lr: 0.000049 grad: 0.1022 (0.1123) loss: 0.8376 (0.8407) time: 0.1293 data: 0.0587 max mem: 8255 +Train: [59] [1600/6250] eta: 0:10:49 lr: 0.000049 grad: 0.1009 (0.1117) loss: 0.8433 (0.8406) time: 0.1743 data: 0.1032 max mem: 8255 +Train: [59] [1700/6250] eta: 0:10:32 lr: 0.000049 grad: 0.0985 (0.1112) loss: 0.8427 (0.8404) time: 0.1199 data: 0.0469 max mem: 8255 +Train: [59] [1800/6250] eta: 0:10:20 lr: 0.000049 grad: 0.0982 (0.1107) loss: 0.8399 (0.8403) time: 0.1531 data: 0.0820 max mem: 8255 +Train: [59] [1900/6250] eta: 0:10:08 lr: 0.000049 grad: 0.1024 (0.1104) loss: 0.8383 (0.8403) time: 0.1725 data: 0.1084 max mem: 8255 +Train: [59] [2000/6250] eta: 0:09:54 lr: 0.000049 grad: 0.1015 (0.1100) loss: 0.8391 (0.8403) time: 0.1406 data: 0.0677 max mem: 8255 +Train: [59] [2100/6250] eta: 0:09:40 lr: 0.000048 grad: 0.1020 (0.1097) loss: 0.8413 (0.8403) time: 0.1195 data: 0.0384 max mem: 8255 +Train: [59] [2200/6250] eta: 0:09:27 lr: 0.000048 grad: 0.1011 (0.1097) loss: 0.8335 (0.8402) time: 0.1281 data: 0.0597 max mem: 8255 +Train: [59] [2300/6250] eta: 0:09:16 lr: 0.000048 grad: 0.1029 (0.1094) loss: 0.8349 (0.8403) time: 0.2000 data: 0.1388 max mem: 8255 +Train: [59] [2400/6250] eta: 0:08:59 lr: 0.000048 grad: 0.1018 (0.1091) loss: 0.8369 (0.8402) time: 0.1220 data: 0.0490 max mem: 8255 +Train: [59] [2500/6250] eta: 0:08:43 lr: 0.000048 grad: 0.1066 (0.1089) loss: 0.8385 (0.8403) time: 0.1056 data: 0.0338 max mem: 8255 +Train: [59] [2600/6250] eta: 0:08:28 lr: 0.000048 grad: 0.1048 (0.1087) loss: 0.8381 (0.8402) time: 0.1105 data: 0.0313 max mem: 8255 +Train: [59] [2700/6250] eta: 0:08:13 lr: 0.000048 grad: 0.1000 (0.1087) loss: 0.8432 (0.8402) time: 0.1289 data: 0.0623 max mem: 8255 +Train: [59] [2800/6250] eta: 0:07:58 lr: 0.000048 grad: 0.1015 (0.1085) loss: 0.8440 (0.8402) time: 0.1222 data: 0.0484 max mem: 8255 +Train: [59] [2900/6250] eta: 0:07:45 lr: 0.000048 grad: 0.1044 (0.1084) loss: 0.8425 (0.8402) time: 0.2045 data: 0.1268 max mem: 8255 +Train: [59] [3000/6250] eta: 0:07:32 lr: 0.000048 grad: 0.0980 (0.1082) loss: 0.8378 (0.8403) time: 0.0922 data: 0.0190 max mem: 8255 +Train: [59] [3100/6250] eta: 0:07:17 lr: 0.000048 grad: 0.0955 (0.1080) loss: 0.8484 (0.8403) time: 0.1264 data: 0.0522 max mem: 8255 +Train: [59] [3200/6250] eta: 0:07:03 lr: 0.000048 grad: 0.1057 (0.1080) loss: 0.8438 (0.8403) time: 0.1442 data: 0.0702 max mem: 8255 +Train: [59] [3300/6250] eta: 0:06:48 lr: 0.000048 grad: 0.1031 (0.1081) loss: 0.8442 (0.8403) time: 0.1130 data: 0.0305 max mem: 8255 +Train: [59] [3400/6250] eta: 0:06:34 lr: 0.000048 grad: 0.1116 (0.1080) loss: 0.8290 (0.8402) time: 0.1349 data: 0.0645 max mem: 8255 +Train: [59] [3500/6250] eta: 0:06:19 lr: 0.000048 grad: 0.1037 (0.1081) loss: 0.8374 (0.8402) time: 0.1168 data: 0.0487 max mem: 8255 +Train: [59] [3600/6250] eta: 0:06:04 lr: 0.000048 grad: 0.1100 (0.1081) loss: 0.8316 (0.8401) time: 0.1269 data: 0.0627 max mem: 8255 +Train: [59] [3700/6250] eta: 0:05:50 lr: 0.000048 grad: 0.1082 (0.1081) loss: 0.8409 (0.8401) time: 0.1292 data: 0.0599 max mem: 8255 +Train: [59] [3800/6250] eta: 0:05:39 lr: 0.000048 grad: 0.1013 (0.1081) loss: 0.8415 (0.8401) time: 0.1439 data: 0.0736 max mem: 8255 +Train: [59] [3900/6250] eta: 0:05:25 lr: 0.000048 grad: 0.1019 (0.1080) loss: 0.8324 (0.8401) time: 0.1374 data: 0.0616 max mem: 8255 +Train: [59] [4000/6250] eta: 0:05:11 lr: 0.000048 grad: 0.1037 (0.1080) loss: 0.8406 (0.8400) time: 0.1377 data: 0.0694 max mem: 8255 +Train: [59] [4100/6250] eta: 0:04:58 lr: 0.000048 grad: 0.1051 (0.1081) loss: 0.8356 (0.8400) time: 0.1440 data: 0.0711 max mem: 8255 +Train: [59] [4200/6250] eta: 0:04:44 lr: 0.000048 grad: 0.1017 (0.1080) loss: 0.8401 (0.8400) time: 0.1207 data: 0.0508 max mem: 8255 +Train: [59] [4300/6250] eta: 0:04:30 lr: 0.000048 grad: 0.1053 (0.1080) loss: 0.8337 (0.8400) time: 0.1333 data: 0.0599 max mem: 8255 +Train: [59] [4400/6250] eta: 0:04:15 lr: 0.000048 grad: 0.1040 (0.1079) loss: 0.8405 (0.8400) time: 0.1180 data: 0.0531 max mem: 8255 +Train: [59] [4500/6250] eta: 0:04:00 lr: 0.000048 grad: 0.1045 (0.1079) loss: 0.8372 (0.8401) time: 0.1009 data: 0.0261 max mem: 8255 +Train: [59] [4600/6250] eta: 0:03:46 lr: 0.000048 grad: 0.0987 (0.1079) loss: 0.8440 (0.8401) time: 0.1221 data: 0.0501 max mem: 8255 +Train: [59] [4700/6250] eta: 0:03:31 lr: 0.000048 grad: 0.1116 (0.1078) loss: 0.8360 (0.8401) time: 0.1138 data: 0.0428 max mem: 8255 +Train: [59] [4800/6250] eta: 0:03:18 lr: 0.000048 grad: 0.1002 (0.1078) loss: 0.8398 (0.8402) time: 0.1451 data: 0.0825 max mem: 8255 +Train: [59] [4900/6250] eta: 0:03:05 lr: 0.000048 grad: 0.1039 (0.1077) loss: 0.8414 (0.8402) time: 0.1682 data: 0.1051 max mem: 8255 +Train: [59] [5000/6250] eta: 0:02:52 lr: 0.000048 grad: 0.1038 (0.1077) loss: 0.8425 (0.8402) time: 0.1507 data: 0.0672 max mem: 8255 +Train: [59] [5100/6250] eta: 0:02:38 lr: 0.000048 grad: 0.1028 (0.1077) loss: 0.8477 (0.8402) time: 0.1406 data: 0.0690 max mem: 8255 +Train: [59] [5200/6250] eta: 0:02:25 lr: 0.000047 grad: 0.1056 (0.1077) loss: 0.8360 (0.8403) time: 0.1396 data: 0.0701 max mem: 8255 +Train: [59] [5300/6250] eta: 0:02:11 lr: 0.000047 grad: 0.1043 (0.1077) loss: 0.8393 (0.8403) time: 0.1580 data: 0.0920 max mem: 8255 +Train: [59] [5400/6250] eta: 0:01:57 lr: 0.000047 grad: 0.1014 (0.1077) loss: 0.8394 (0.8404) time: 0.1208 data: 0.0468 max mem: 8255 +Train: [59] [5500/6250] eta: 0:01:44 lr: 0.000047 grad: 0.1081 (0.1077) loss: 0.8363 (0.8404) time: 0.1374 data: 0.0668 max mem: 8255 +Train: [59] [5600/6250] eta: 0:01:30 lr: 0.000047 grad: 0.1065 (0.1077) loss: 0.8426 (0.8404) time: 0.1090 data: 0.0295 max mem: 8255 +Train: [59] [5700/6250] eta: 0:01:16 lr: 0.000047 grad: 0.1059 (0.1077) loss: 0.8377 (0.8404) time: 0.1112 data: 0.0433 max mem: 8255 +Train: [59] [5800/6250] eta: 0:01:02 lr: 0.000047 grad: 0.1037 (0.1078) loss: 0.8379 (0.8404) time: 0.1405 data: 0.0608 max mem: 8255 +Train: [59] [5900/6250] eta: 0:00:48 lr: 0.000047 grad: 0.1025 (0.1078) loss: 0.8440 (0.8405) time: 0.1408 data: 0.0649 max mem: 8255 +Train: [59] [6000/6250] eta: 0:00:34 lr: 0.000047 grad: 0.1083 (0.1079) loss: 0.8392 (0.8405) time: 0.1350 data: 0.0663 max mem: 8255 +Train: [59] [6100/6250] eta: 0:00:20 lr: 0.000047 grad: 0.1037 (0.1079) loss: 0.8456 (0.8404) time: 0.1285 data: 0.0589 max mem: 8255 +Train: [59] [6200/6250] eta: 0:00:06 lr: 0.000047 grad: 0.1058 (0.1079) loss: 0.8362 (0.8405) time: 0.1662 data: 0.0986 max mem: 8255 +Train: [59] [6249/6250] eta: 0:00:00 lr: 0.000047 grad: 0.1015 (0.1079) loss: 0.8407 (0.8405) time: 0.1397 data: 0.0664 max mem: 8255 +Train: [59] Total time: 0:14:32 (0.1397 s / it) +Averaged stats: lr: 0.000047 grad: 0.1015 (0.1079) loss: 0.8407 (0.8405) +Eval (hcp-train-subset): [59] [ 0/62] eta: 0:04:33 loss: 0.8819 (0.8819) time: 4.4134 data: 4.3882 max mem: 8255 +Eval (hcp-train-subset): [59] [61/62] eta: 0:00:00 loss: 0.8690 (0.8705) time: 0.1272 data: 0.1060 max mem: 8255 +Eval (hcp-train-subset): [59] Total time: 0:00:12 (0.1970 s / it) +Averaged stats (hcp-train-subset): loss: 0.8690 (0.8705) +Making plots (hcp-train-subset): example=38 +Eval (hcp-val): [59] [ 0/62] eta: 0:03:21 loss: 0.8772 (0.8772) time: 3.2570 data: 3.1598 max mem: 8255 +Eval (hcp-val): [59] [61/62] eta: 0:00:00 loss: 0.8764 (0.8777) time: 0.1264 data: 0.1045 max mem: 8255 +Eval (hcp-val): [59] Total time: 0:00:12 (0.2070 s / it) +Averaged stats (hcp-val): loss: 0.8764 (0.8777) +Making plots (hcp-val): example=59 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-00059.pth +Train: [60] [ 0/6250] eta: 7:14:51 lr: 0.000047 grad: 0.0964 (0.0964) loss: 0.8597 (0.8597) time: 4.1746 data: 3.9207 max mem: 8255 +Train: [60] [ 100/6250] eta: 0:21:09 lr: 0.000047 grad: 0.1177 (0.1288) loss: 0.8440 (0.8637) time: 0.1468 data: 0.0589 max mem: 8255 +Train: [60] [ 200/6250] eta: 0:17:51 lr: 0.000047 grad: 0.1109 (0.1264) loss: 0.8543 (0.8579) time: 0.1402 data: 0.0547 max mem: 8255 +Train: [60] [ 300/6250] eta: 0:16:31 lr: 0.000047 grad: 0.1121 (0.1232) loss: 0.8391 (0.8525) time: 0.1513 data: 0.0704 max mem: 8255 +Train: [60] [ 400/6250] eta: 0:15:27 lr: 0.000047 grad: 0.1151 (0.1209) loss: 0.8364 (0.8493) time: 0.1303 data: 0.0500 max mem: 8255 +Train: [60] [ 500/6250] eta: 0:14:32 lr: 0.000047 grad: 0.1058 (0.1192) loss: 0.8328 (0.8468) time: 0.1313 data: 0.0499 max mem: 8255 +Train: [60] [ 600/6250] eta: 0:13:46 lr: 0.000047 grad: 0.1060 (0.1176) loss: 0.8458 (0.8459) time: 0.1150 data: 0.0436 max mem: 8255 +Train: [60] [ 700/6250] eta: 0:13:06 lr: 0.000047 grad: 0.0960 (0.1154) loss: 0.8474 (0.8455) time: 0.1145 data: 0.0397 max mem: 8255 +Train: [60] [ 800/6250] eta: 0:12:39 lr: 0.000047 grad: 0.0967 (0.1138) loss: 0.8533 (0.8461) time: 0.1143 data: 0.0408 max mem: 8255 +Train: [60] [ 900/6250] eta: 0:12:16 lr: 0.000047 grad: 0.0953 (0.1121) loss: 0.8521 (0.8464) time: 0.1420 data: 0.0603 max mem: 8255 +Train: [60] [1000/6250] eta: 0:11:58 lr: 0.000047 grad: 0.1006 (0.1110) loss: 0.8362 (0.8465) time: 0.1315 data: 0.0696 max mem: 8255 +Train: [60] [1100/6250] eta: 0:11:37 lr: 0.000047 grad: 0.1006 (0.1100) loss: 0.8492 (0.8468) time: 0.1241 data: 0.0517 max mem: 8255 +Train: [60] [1200/6250] eta: 0:11:20 lr: 0.000047 grad: 0.1033 (0.1095) loss: 0.8441 (0.8468) time: 0.1385 data: 0.0764 max mem: 8255 +Train: [60] [1300/6250] eta: 0:11:05 lr: 0.000047 grad: 0.0976 (0.1089) loss: 0.8495 (0.8468) time: 0.1284 data: 0.0536 max mem: 8255 +Train: [60] [1400/6250] eta: 0:10:53 lr: 0.000047 grad: 0.1068 (0.1084) loss: 0.8445 (0.8468) time: 0.1281 data: 0.0529 max mem: 8255 +Train: [60] [1500/6250] eta: 0:10:38 lr: 0.000047 grad: 0.0989 (0.1079) loss: 0.8420 (0.8468) time: 0.1362 data: 0.0660 max mem: 8255 +Train: [60] [1600/6250] eta: 0:10:24 lr: 0.000047 grad: 0.1026 (0.1078) loss: 0.8411 (0.8465) time: 0.1356 data: 0.0645 max mem: 8255 +Train: [60] [1700/6250] eta: 0:10:12 lr: 0.000047 grad: 0.1019 (0.1075) loss: 0.8441 (0.8464) time: 0.1404 data: 0.0627 max mem: 8255 +Train: [60] [1800/6250] eta: 0:09:59 lr: 0.000047 grad: 0.1050 (0.1074) loss: 0.8431 (0.8461) time: 0.1294 data: 0.0461 max mem: 8255 +Train: [60] [1900/6250] eta: 0:09:45 lr: 0.000047 grad: 0.0985 (0.1072) loss: 0.8421 (0.8459) time: 0.1276 data: 0.0527 max mem: 8255 +Train: [60] [2000/6250] eta: 0:09:33 lr: 0.000047 grad: 0.1048 (0.1072) loss: 0.8417 (0.8457) time: 0.1009 data: 0.0186 max mem: 8255 +Train: [60] [2100/6250] eta: 0:09:27 lr: 0.000046 grad: 0.1060 (0.1071) loss: 0.8437 (0.8456) time: 0.2474 data: 0.1591 max mem: 8255 +Train: [60] [2200/6250] eta: 0:09:09 lr: 0.000046 grad: 0.1040 (0.1071) loss: 0.8359 (0.8454) time: 0.1326 data: 0.0590 max mem: 8255 +Train: [60] [2300/6250] eta: 0:08:54 lr: 0.000046 grad: 0.1053 (0.1071) loss: 0.8366 (0.8451) time: 0.1195 data: 0.0540 max mem: 8255 +Train: [60] [2400/6250] eta: 0:08:41 lr: 0.000046 grad: 0.1036 (0.1071) loss: 0.8458 (0.8449) time: 0.1674 data: 0.0945 max mem: 8255 +Train: [60] [2500/6250] eta: 0:08:26 lr: 0.000046 grad: 0.0969 (0.1071) loss: 0.8373 (0.8447) time: 0.1524 data: 0.0814 max mem: 8255 +Train: [60] [2600/6250] eta: 0:08:13 lr: 0.000046 grad: 0.1056 (0.1071) loss: 0.8453 (0.8446) time: 0.0982 data: 0.0248 max mem: 8255 +Train: [60] [2700/6250] eta: 0:07:59 lr: 0.000046 grad: 0.1090 (0.1072) loss: 0.8374 (0.8443) time: 0.1092 data: 0.0373 max mem: 8255 +Train: [60] [2800/6250] eta: 0:07:44 lr: 0.000046 grad: 0.1064 (0.1073) loss: 0.8396 (0.8441) time: 0.1184 data: 0.0566 max mem: 8255 +Train: [60] [2900/6250] eta: 0:07:30 lr: 0.000046 grad: 0.1025 (0.1074) loss: 0.8419 (0.8440) time: 0.1353 data: 0.0619 max mem: 8255 +Train: [60] [3000/6250] eta: 0:07:16 lr: 0.000046 grad: 0.1114 (0.1074) loss: 0.8322 (0.8438) time: 0.1229 data: 0.0503 max mem: 8255 +Train: [60] [3100/6250] eta: 0:07:02 lr: 0.000046 grad: 0.1080 (0.1074) loss: 0.8458 (0.8437) time: 0.1244 data: 0.0540 max mem: 8255 +Train: [60] [3200/6250] eta: 0:06:48 lr: 0.000046 grad: 0.1066 (0.1075) loss: 0.8364 (0.8436) time: 0.1421 data: 0.0835 max mem: 8255 +Train: [60] [3300/6250] eta: 0:06:35 lr: 0.000046 grad: 0.1129 (0.1075) loss: 0.8403 (0.8435) time: 0.1364 data: 0.0683 max mem: 8255 +Train: [60] [3400/6250] eta: 0:06:22 lr: 0.000046 grad: 0.1047 (0.1075) loss: 0.8387 (0.8434) time: 0.1559 data: 0.0916 max mem: 8255 +Train: [60] [3500/6250] eta: 0:06:08 lr: 0.000046 grad: 0.1015 (0.1075) loss: 0.8495 (0.8435) time: 0.1251 data: 0.0539 max mem: 8255 +Train: [60] [3600/6250] eta: 0:05:55 lr: 0.000046 grad: 0.1031 (0.1076) loss: 0.8328 (0.8434) time: 0.1261 data: 0.0578 max mem: 8255 +Train: [60] [3700/6250] eta: 0:05:41 lr: 0.000046 grad: 0.1042 (0.1077) loss: 0.8462 (0.8433) time: 0.1262 data: 0.0570 max mem: 8255 +Train: [60] [3800/6250] eta: 0:05:28 lr: 0.000046 grad: 0.1055 (0.1077) loss: 0.8442 (0.8433) time: 0.1408 data: 0.0732 max mem: 8255 +Train: [60] [3900/6250] eta: 0:05:14 lr: 0.000046 grad: 0.1011 (0.1079) loss: 0.8485 (0.8433) time: 0.1320 data: 0.0680 max mem: 8255 +Train: [60] [4000/6250] eta: 0:05:02 lr: 0.000046 grad: 0.1076 (0.1080) loss: 0.8427 (0.8432) time: 0.1624 data: 0.0736 max mem: 8255 +Train: [60] [4100/6250] eta: 0:04:49 lr: 0.000046 grad: 0.1069 (0.1080) loss: 0.8396 (0.8432) time: 0.1383 data: 0.0731 max mem: 8255 +Train: [60] [4200/6250] eta: 0:04:37 lr: 0.000046 grad: 0.1104 (0.1081) loss: 0.8405 (0.8432) time: 0.1554 data: 0.0846 max mem: 8255 +Train: [60] [4300/6250] eta: 0:04:24 lr: 0.000046 grad: 0.1090 (0.1081) loss: 0.8413 (0.8431) time: 0.1473 data: 0.0817 max mem: 8255 +Train: [60] [4400/6250] eta: 0:04:11 lr: 0.000046 grad: 0.1102 (0.1082) loss: 0.8407 (0.8431) time: 0.1353 data: 0.0557 max mem: 8255 +Train: [60] [4500/6250] eta: 0:03:57 lr: 0.000046 grad: 0.1041 (0.1082) loss: 0.8425 (0.8430) time: 0.1236 data: 0.0472 max mem: 8255 +Train: [60] [4600/6250] eta: 0:03:43 lr: 0.000046 grad: 0.1102 (0.1083) loss: 0.8455 (0.8430) time: 0.1379 data: 0.0689 max mem: 8255 +Train: [60] [4700/6250] eta: 0:03:30 lr: 0.000046 grad: 0.1047 (0.1083) loss: 0.8394 (0.8429) time: 0.1395 data: 0.0657 max mem: 8255 +Train: [60] [4800/6250] eta: 0:03:16 lr: 0.000046 grad: 0.1057 (0.1084) loss: 0.8402 (0.8429) time: 0.1064 data: 0.0213 max mem: 8255 +Train: [60] [4900/6250] eta: 0:03:02 lr: 0.000046 grad: 0.1060 (0.1084) loss: 0.8434 (0.8429) time: 0.1215 data: 0.0466 max mem: 8255 +Train: [60] [5000/6250] eta: 0:02:49 lr: 0.000046 grad: 0.1013 (0.1084) loss: 0.8455 (0.8428) time: 0.1057 data: 0.0223 max mem: 8255 +Train: [60] [5100/6250] eta: 0:02:35 lr: 0.000046 grad: 0.1039 (0.1084) loss: 0.8418 (0.8428) time: 0.1395 data: 0.0649 max mem: 8255 +Train: [60] [5200/6250] eta: 0:02:22 lr: 0.000045 grad: 0.1080 (0.1085) loss: 0.8356 (0.8428) time: 0.1429 data: 0.0698 max mem: 8255 +Train: [60] [5300/6250] eta: 0:02:08 lr: 0.000045 grad: 0.1055 (0.1086) loss: 0.8333 (0.8426) time: 0.1622 data: 0.0925 max mem: 8255 +Train: [60] [5400/6250] eta: 0:01:55 lr: 0.000045 grad: 0.1125 (0.1087) loss: 0.8285 (0.8425) time: 0.1433 data: 0.0721 max mem: 8255 +Train: [60] [5500/6250] eta: 0:01:41 lr: 0.000045 grad: 0.1068 (0.1087) loss: 0.8420 (0.8425) time: 0.1351 data: 0.0634 max mem: 8255 +Train: [60] [5600/6250] eta: 0:01:28 lr: 0.000045 grad: 0.1130 (0.1088) loss: 0.8347 (0.8424) time: 0.1361 data: 0.0709 max mem: 8255 +Train: [60] [5700/6250] eta: 0:01:14 lr: 0.000045 grad: 0.1148 (0.1088) loss: 0.8371 (0.8423) time: 0.1310 data: 0.0638 max mem: 8255 +Train: [60] [5800/6250] eta: 0:01:00 lr: 0.000045 grad: 0.1068 (0.1088) loss: 0.8353 (0.8422) time: 0.1442 data: 0.0675 max mem: 8255 +Train: [60] [5900/6250] eta: 0:00:47 lr: 0.000045 grad: 0.1110 (0.1089) loss: 0.8424 (0.8422) time: 0.1468 data: 0.0725 max mem: 8255 +Train: [60] [6000/6250] eta: 0:00:33 lr: 0.000045 grad: 0.1038 (0.1089) loss: 0.8329 (0.8421) time: 0.1445 data: 0.0698 max mem: 8255 +Train: [60] [6100/6250] eta: 0:00:20 lr: 0.000045 grad: 0.1118 (0.1089) loss: 0.8368 (0.8421) time: 0.1625 data: 0.0870 max mem: 8255 +Train: [60] [6200/6250] eta: 0:00:06 lr: 0.000045 grad: 0.1044 (0.1089) loss: 0.8383 (0.8420) time: 0.1189 data: 0.0426 max mem: 8255 +Train: [60] [6249/6250] eta: 0:00:00 lr: 0.000045 grad: 0.1112 (0.1089) loss: 0.8420 (0.8420) time: 0.1404 data: 0.0698 max mem: 8255 +Train: [60] Total time: 0:14:15 (0.1368 s / it) +Averaged stats: lr: 0.000045 grad: 0.1112 (0.1089) loss: 0.8420 (0.8420) +Eval (hcp-train-subset): [60] [ 0/62] eta: 0:05:33 loss: 0.8776 (0.8776) time: 5.3721 data: 5.3440 max mem: 8255 +Eval (hcp-train-subset): [60] [61/62] eta: 0:00:00 loss: 0.8695 (0.8712) time: 0.1351 data: 0.1143 max mem: 8255 +Eval (hcp-train-subset): [60] Total time: 0:00:13 (0.2178 s / it) +Averaged stats (hcp-train-subset): loss: 0.8695 (0.8712) +Eval (hcp-val): [60] [ 0/62] eta: 0:04:59 loss: 0.8720 (0.8720) time: 4.8288 data: 4.8020 max mem: 8255 +Eval (hcp-val): [60] [61/62] eta: 0:00:00 loss: 0.8760 (0.8774) time: 0.1274 data: 0.1067 max mem: 8255 +Eval (hcp-val): [60] Total time: 0:00:13 (0.2144 s / it) +Averaged stats (hcp-val): loss: 0.8760 (0.8774) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +Train: [61] [ 0/6250] eta: 8:12:14 lr: 0.000045 grad: 0.1210 (0.1210) loss: 0.8784 (0.8784) time: 4.7256 data: 4.5036 max mem: 8255 +Train: [61] [ 100/6250] eta: 0:19:15 lr: 0.000045 grad: 0.0954 (0.1251) loss: 0.8730 (0.8733) time: 0.1309 data: 0.0498 max mem: 8255 +Train: [61] [ 200/6250] eta: 0:16:10 lr: 0.000045 grad: 0.1074 (0.1181) loss: 0.8666 (0.8673) time: 0.1361 data: 0.0473 max mem: 8255 +Train: [61] [ 300/6250] eta: 0:14:44 lr: 0.000045 grad: 0.1028 (0.1152) loss: 0.8540 (0.8635) time: 0.1288 data: 0.0456 max mem: 8255 +Train: [61] [ 400/6250] eta: 0:13:52 lr: 0.000045 grad: 0.1007 (0.1128) loss: 0.8554 (0.8605) time: 0.1263 data: 0.0410 max mem: 8255 +Train: [61] [ 500/6250] eta: 0:13:31 lr: 0.000045 grad: 0.1058 (0.1120) loss: 0.8491 (0.8579) time: 0.1142 data: 0.0354 max mem: 8255 +Train: [61] [ 600/6250] eta: 0:12:58 lr: 0.000045 grad: 0.1098 (0.1121) loss: 0.8356 (0.8553) time: 0.1194 data: 0.0364 max mem: 8255 +Train: [61] [ 700/6250] eta: 0:12:43 lr: 0.000045 grad: 0.1053 (0.1117) loss: 0.8476 (0.8533) time: 0.1384 data: 0.0610 max mem: 8255 +Train: [61] [ 800/6250] eta: 0:12:33 lr: 0.000045 grad: 0.1098 (0.1120) loss: 0.8406 (0.8514) time: 0.1746 data: 0.0957 max mem: 8255 +Train: [61] [ 900/6250] eta: 0:12:13 lr: 0.000045 grad: 0.1134 (0.1121) loss: 0.8342 (0.8497) time: 0.1399 data: 0.0674 max mem: 8255 +Train: [61] [1000/6250] eta: 0:12:09 lr: 0.000045 grad: 0.1040 (0.1119) loss: 0.8389 (0.8485) time: 0.1861 data: 0.1167 max mem: 8255 +Train: [61] [1100/6250] eta: 0:11:46 lr: 0.000045 grad: 0.1088 (0.1116) loss: 0.8368 (0.8476) time: 0.1343 data: 0.0577 max mem: 8255 +Train: [61] [1200/6250] eta: 0:11:30 lr: 0.000045 grad: 0.1054 (0.1113) loss: 0.8286 (0.8468) time: 0.0969 data: 0.0179 max mem: 8255 +Train: [61] [1300/6250] eta: 0:11:14 lr: 0.000045 grad: 0.1163 (0.1113) loss: 0.8244 (0.8455) time: 0.1289 data: 0.0514 max mem: 8255 +Train: [61] [1400/6250] eta: 0:11:00 lr: 0.000045 grad: 0.1052 (0.1111) loss: 0.8349 (0.8447) time: 0.1298 data: 0.0538 max mem: 8255 +Train: [61] [1500/6250] eta: 0:10:46 lr: 0.000045 grad: 0.1021 (0.1112) loss: 0.8357 (0.8438) time: 0.1200 data: 0.0476 max mem: 8255 +Train: [61] [1600/6250] eta: 0:10:32 lr: 0.000045 grad: 0.1078 (0.1110) loss: 0.8366 (0.8432) time: 0.1412 data: 0.0690 max mem: 8255 +Train: [61] [1700/6250] eta: 0:10:18 lr: 0.000045 grad: 0.1096 (0.1111) loss: 0.8244 (0.8425) time: 0.1312 data: 0.0544 max mem: 8255 +Train: [61] [1800/6250] eta: 0:10:06 lr: 0.000045 grad: 0.1093 (0.1112) loss: 0.8297 (0.8419) time: 0.1556 data: 0.0919 max mem: 8255 +Train: [61] [1900/6250] eta: 0:09:53 lr: 0.000045 grad: 0.1081 (0.1114) loss: 0.8333 (0.8413) time: 0.1084 data: 0.0405 max mem: 8255 +Train: [61] [2000/6250] eta: 0:09:40 lr: 0.000045 grad: 0.1068 (0.1114) loss: 0.8391 (0.8410) time: 0.1472 data: 0.0838 max mem: 8255 +Train: [61] [2100/6250] eta: 0:09:28 lr: 0.000044 grad: 0.1101 (0.1113) loss: 0.8362 (0.8407) time: 0.0978 data: 0.0323 max mem: 8255 +Train: [61] [2200/6250] eta: 0:09:15 lr: 0.000044 grad: 0.1061 (0.1111) loss: 0.8402 (0.8404) time: 0.1376 data: 0.0622 max mem: 8255 +Train: [61] [2300/6250] eta: 0:09:03 lr: 0.000044 grad: 0.1112 (0.1111) loss: 0.8343 (0.8400) time: 0.1495 data: 0.0793 max mem: 8255 +Train: [61] [2400/6250] eta: 0:08:49 lr: 0.000044 grad: 0.1015 (0.1111) loss: 0.8258 (0.8398) time: 0.1444 data: 0.0750 max mem: 8255 +Train: [61] [2500/6250] eta: 0:08:34 lr: 0.000044 grad: 0.1061 (0.1110) loss: 0.8267 (0.8395) time: 0.1315 data: 0.0547 max mem: 8255 +Train: [61] [2600/6250] eta: 0:08:20 lr: 0.000044 grad: 0.1056 (0.1110) loss: 0.8378 (0.8393) time: 0.1185 data: 0.0515 max mem: 8255 +Train: [61] [2700/6250] eta: 0:08:07 lr: 0.000044 grad: 0.1031 (0.1110) loss: 0.8368 (0.8392) time: 0.1667 data: 0.1052 max mem: 8255 +Train: [61] [2800/6250] eta: 0:07:53 lr: 0.000044 grad: 0.1134 (0.1110) loss: 0.8301 (0.8389) time: 0.1307 data: 0.0537 max mem: 8255 +Train: [61] [2900/6250] eta: 0:07:42 lr: 0.000044 grad: 0.1058 (0.1109) loss: 0.8416 (0.8389) time: 0.0997 data: 0.0139 max mem: 8255 +Train: [61] [3000/6250] eta: 0:07:27 lr: 0.000044 grad: 0.1077 (0.1109) loss: 0.8382 (0.8388) time: 0.1204 data: 0.0476 max mem: 8255 +Train: [61] [3100/6250] eta: 0:07:13 lr: 0.000044 grad: 0.1074 (0.1109) loss: 0.8371 (0.8385) time: 0.1650 data: 0.0816 max mem: 8255 +Train: [61] [3200/6250] eta: 0:06:59 lr: 0.000044 grad: 0.1107 (0.1110) loss: 0.8245 (0.8383) time: 0.1264 data: 0.0415 max mem: 8255 +Train: [61] [3300/6250] eta: 0:06:45 lr: 0.000044 grad: 0.1099 (0.1110) loss: 0.8250 (0.8382) time: 0.1302 data: 0.0549 max mem: 8255 +Train: [61] [3400/6250] eta: 0:06:31 lr: 0.000044 grad: 0.1042 (0.1110) loss: 0.8382 (0.8380) time: 0.1298 data: 0.0626 max mem: 8255 +Train: [61] [3500/6250] eta: 0:06:16 lr: 0.000044 grad: 0.1077 (0.1110) loss: 0.8417 (0.8379) time: 0.1188 data: 0.0528 max mem: 8255 +Train: [61] [3600/6250] eta: 0:06:02 lr: 0.000044 grad: 0.1113 (0.1110) loss: 0.8378 (0.8379) time: 0.1200 data: 0.0568 max mem: 8255 +Train: [61] [3700/6250] eta: 0:05:48 lr: 0.000044 grad: 0.1097 (0.1111) loss: 0.8376 (0.8379) time: 0.1208 data: 0.0467 max mem: 8255 +Train: [61] [3800/6250] eta: 0:05:35 lr: 0.000044 grad: 0.1059 (0.1111) loss: 0.8450 (0.8378) time: 0.0813 data: 0.0002 max mem: 8255 +Train: [61] [3900/6250] eta: 0:05:21 lr: 0.000044 grad: 0.1079 (0.1111) loss: 0.8358 (0.8378) time: 0.1310 data: 0.0636 max mem: 8255 +Train: [61] [4000/6250] eta: 0:05:07 lr: 0.000044 grad: 0.1142 (0.1111) loss: 0.8395 (0.8378) time: 0.0976 data: 0.0254 max mem: 8255 +Train: [61] [4100/6250] eta: 0:04:55 lr: 0.000044 grad: 0.1054 (0.1111) loss: 0.8368 (0.8378) time: 0.1363 data: 0.0769 max mem: 8255 +Train: [61] [4200/6250] eta: 0:04:41 lr: 0.000044 grad: 0.1143 (0.1111) loss: 0.8411 (0.8378) time: 0.1344 data: 0.0646 max mem: 8255 +Train: [61] [4300/6250] eta: 0:04:27 lr: 0.000044 grad: 0.1155 (0.1112) loss: 0.8416 (0.8379) time: 0.1337 data: 0.0642 max mem: 8255 +Train: [61] [4400/6250] eta: 0:04:14 lr: 0.000044 grad: 0.1080 (0.1112) loss: 0.8400 (0.8378) time: 0.1494 data: 0.0724 max mem: 8255 +Train: [61] [4500/6250] eta: 0:04:00 lr: 0.000044 grad: 0.1104 (0.1113) loss: 0.8375 (0.8378) time: 0.1524 data: 0.0797 max mem: 8255 +Train: [61] [4600/6250] eta: 0:03:46 lr: 0.000044 grad: 0.1139 (0.1114) loss: 0.8434 (0.8378) time: 0.1335 data: 0.0589 max mem: 8255 +Train: [61] [4700/6250] eta: 0:03:32 lr: 0.000044 grad: 0.1060 (0.1114) loss: 0.8389 (0.8378) time: 0.1394 data: 0.0592 max mem: 8255 +Train: [61] [4800/6250] eta: 0:03:17 lr: 0.000044 grad: 0.1135 (0.1114) loss: 0.8356 (0.8378) time: 0.1145 data: 0.0410 max mem: 8255 +Train: [61] [4900/6250] eta: 0:03:03 lr: 0.000044 grad: 0.1129 (0.1116) loss: 0.8316 (0.8378) time: 0.1115 data: 0.0290 max mem: 8255 +Train: [61] [5000/6250] eta: 0:02:49 lr: 0.000044 grad: 0.1109 (0.1116) loss: 0.8375 (0.8377) time: 0.1285 data: 0.0522 max mem: 8255 +Train: [61] [5100/6250] eta: 0:02:35 lr: 0.000044 grad: 0.1114 (0.1117) loss: 0.8330 (0.8377) time: 0.1069 data: 0.0348 max mem: 8255 +Train: [61] [5200/6250] eta: 0:02:21 lr: 0.000044 grad: 0.1144 (0.1118) loss: 0.8258 (0.8377) time: 0.1162 data: 0.0438 max mem: 8255 +Train: [61] [5300/6250] eta: 0:02:08 lr: 0.000043 grad: 0.1077 (0.1118) loss: 0.8356 (0.8376) time: 0.1163 data: 0.0335 max mem: 8255 +Train: [61] [5400/6250] eta: 0:01:54 lr: 0.000043 grad: 0.1068 (0.1119) loss: 0.8327 (0.8375) time: 0.1308 data: 0.0578 max mem: 8255 +Train: [61] [5500/6250] eta: 0:01:40 lr: 0.000043 grad: 0.1100 (0.1119) loss: 0.8354 (0.8375) time: 0.1355 data: 0.0640 max mem: 8255 +Train: [61] [5600/6250] eta: 0:01:27 lr: 0.000043 grad: 0.1168 (0.1120) loss: 0.8313 (0.8374) time: 0.1344 data: 0.0657 max mem: 8255 +Train: [61] [5700/6250] eta: 0:01:14 lr: 0.000043 grad: 0.1074 (0.1120) loss: 0.8409 (0.8374) time: 0.1514 data: 0.0670 max mem: 8255 +Train: [61] [5800/6250] eta: 0:01:00 lr: 0.000043 grad: 0.1103 (0.1120) loss: 0.8316 (0.8374) time: 0.1761 data: 0.1123 max mem: 8255 +Train: [61] [5900/6250] eta: 0:00:47 lr: 0.000043 grad: 0.1109 (0.1120) loss: 0.8373 (0.8374) time: 0.1596 data: 0.0900 max mem: 8255 +Train: [61] [6000/6250] eta: 0:00:34 lr: 0.000043 grad: 0.1126 (0.1120) loss: 0.8378 (0.8374) time: 0.1776 data: 0.1092 max mem: 8255 +Train: [61] [6100/6250] eta: 0:00:20 lr: 0.000043 grad: 0.1046 (0.1120) loss: 0.8451 (0.8374) time: 0.1585 data: 0.0720 max mem: 8255 +Train: [61] [6200/6250] eta: 0:00:06 lr: 0.000043 grad: 0.1070 (0.1120) loss: 0.8364 (0.8374) time: 0.1600 data: 0.0812 max mem: 8255 +Train: [61] [6249/6250] eta: 0:00:00 lr: 0.000043 grad: 0.1112 (0.1120) loss: 0.8413 (0.8374) time: 0.1431 data: 0.0744 max mem: 8255 +Train: [61] Total time: 0:14:20 (0.1377 s / it) +Averaged stats: lr: 0.000043 grad: 0.1112 (0.1120) loss: 0.8413 (0.8374) +Eval (hcp-train-subset): [61] [ 0/62] eta: 0:03:43 loss: 0.8782 (0.8782) time: 3.6120 data: 3.5466 max mem: 8255 +Eval (hcp-train-subset): [61] [61/62] eta: 0:00:00 loss: 0.8680 (0.8696) time: 0.1240 data: 0.1027 max mem: 8255 +Eval (hcp-train-subset): [61] Total time: 0:00:14 (0.2323 s / it) +Averaged stats (hcp-train-subset): loss: 0.8680 (0.8696) +Eval (hcp-val): [61] [ 0/62] eta: 0:05:30 loss: 0.8744 (0.8744) time: 5.3356 data: 5.3099 max mem: 8255 +Eval (hcp-val): [61] [61/62] eta: 0:00:00 loss: 0.8756 (0.8772) time: 0.1102 data: 0.0893 max mem: 8255 +Eval (hcp-val): [61] Total time: 0:00:14 (0.2363 s / it) +Averaged stats (hcp-val): loss: 0.8756 (0.8772) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +Train: [62] [ 0/6250] eta: 8:28:27 lr: 0.000043 grad: 0.2669 (0.2669) loss: 0.8788 (0.8788) time: 4.8812 data: 4.6230 max mem: 8255 +Train: [62] [ 100/6250] eta: 0:22:12 lr: 0.000043 grad: 0.1075 (0.1308) loss: 0.8607 (0.8679) time: 0.1852 data: 0.0993 max mem: 8255 +Train: [62] [ 200/6250] eta: 0:18:23 lr: 0.000043 grad: 0.1080 (0.1295) loss: 0.8545 (0.8582) time: 0.1370 data: 0.0469 max mem: 8255 +Train: [62] [ 300/6250] eta: 0:16:58 lr: 0.000043 grad: 0.1112 (0.1293) loss: 0.8432 (0.8534) time: 0.1625 data: 0.0765 max mem: 8255 +Train: [62] [ 400/6250] eta: 0:16:12 lr: 0.000043 grad: 0.1094 (0.1302) loss: 0.8542 (0.8501) time: 0.1584 data: 0.0722 max mem: 8255 +Train: [62] [ 500/6250] eta: 0:15:19 lr: 0.000043 grad: 0.1099 (0.1285) loss: 0.8371 (0.8477) time: 0.1442 data: 0.0665 max mem: 8255 +Train: [62] [ 600/6250] eta: 0:14:49 lr: 0.000043 grad: 0.1084 (0.1265) loss: 0.8345 (0.8458) time: 0.1482 data: 0.0615 max mem: 8255 +Train: [62] [ 700/6250] eta: 0:14:22 lr: 0.000043 grad: 0.1098 (0.1248) loss: 0.8374 (0.8442) time: 0.1262 data: 0.0499 max mem: 8255 +Train: [62] [ 800/6250] eta: 0:13:55 lr: 0.000043 grad: 0.1090 (0.1235) loss: 0.8389 (0.8435) time: 0.1356 data: 0.0469 max mem: 8255 +Train: [62] [ 900/6250] eta: 0:13:48 lr: 0.000043 grad: 0.1127 (0.1224) loss: 0.8365 (0.8429) time: 0.1723 data: 0.0967 max mem: 8255 +Train: [62] [1000/6250] eta: 0:13:28 lr: 0.000043 grad: 0.1081 (0.1215) loss: 0.8390 (0.8425) time: 0.1293 data: 0.0453 max mem: 8255 +Train: [62] [1100/6250] eta: 0:13:12 lr: 0.000043 grad: 0.1082 (0.1209) loss: 0.8416 (0.8423) time: 0.1325 data: 0.0528 max mem: 8255 +Train: [62] [1200/6250] eta: 0:12:57 lr: 0.000043 grad: 0.1095 (0.1203) loss: 0.8385 (0.8420) time: 0.1497 data: 0.0738 max mem: 8255 +Train: [62] [1300/6250] eta: 0:12:37 lr: 0.000043 grad: 0.1028 (0.1194) loss: 0.8454 (0.8419) time: 0.1541 data: 0.0805 max mem: 8255 +Train: [62] [1400/6250] eta: 0:12:23 lr: 0.000043 grad: 0.1035 (0.1188) loss: 0.8397 (0.8418) time: 0.1470 data: 0.0763 max mem: 8255 +Train: [62] [1500/6250] eta: 0:12:07 lr: 0.000043 grad: 0.1034 (0.1183) loss: 0.8459 (0.8417) time: 0.1617 data: 0.0868 max mem: 8255 +Train: [62] [1600/6250] eta: 0:11:53 lr: 0.000043 grad: 0.1139 (0.1179) loss: 0.8390 (0.8414) time: 0.1628 data: 0.0824 max mem: 8255 +Train: [62] [1700/6250] eta: 0:11:35 lr: 0.000043 grad: 0.1094 (0.1175) loss: 0.8372 (0.8413) time: 0.1102 data: 0.0282 max mem: 8255 +Train: [62] [1800/6250] eta: 0:11:19 lr: 0.000043 grad: 0.1040 (0.1172) loss: 0.8446 (0.8412) time: 0.1529 data: 0.0687 max mem: 8255 +Train: [62] [1900/6250] eta: 0:11:08 lr: 0.000043 grad: 0.1068 (0.1168) loss: 0.8372 (0.8410) time: 0.0962 data: 0.0184 max mem: 8255 +Train: [62] [2000/6250] eta: 0:10:53 lr: 0.000043 grad: 0.1089 (0.1164) loss: 0.8354 (0.8409) time: 0.1598 data: 0.0794 max mem: 8255 +Train: [62] [2100/6250] eta: 0:10:36 lr: 0.000043 grad: 0.1011 (0.1160) loss: 0.8437 (0.8409) time: 0.1452 data: 0.0711 max mem: 8255 +Train: [62] [2200/6250] eta: 0:10:19 lr: 0.000042 grad: 0.0976 (0.1157) loss: 0.8439 (0.8410) time: 0.1564 data: 0.0756 max mem: 8255 +Train: [62] [2300/6250] eta: 0:10:02 lr: 0.000042 grad: 0.1054 (0.1153) loss: 0.8430 (0.8410) time: 0.1058 data: 0.0361 max mem: 8255 +Train: [62] [2400/6250] eta: 0:09:46 lr: 0.000042 grad: 0.1059 (0.1149) loss: 0.8425 (0.8412) time: 0.1338 data: 0.0604 max mem: 8255 +Train: [62] [2500/6250] eta: 0:09:31 lr: 0.000042 grad: 0.1069 (0.1147) loss: 0.8400 (0.8411) time: 0.1454 data: 0.0618 max mem: 8255 +Train: [62] [2600/6250] eta: 0:09:16 lr: 0.000042 grad: 0.1155 (0.1145) loss: 0.8411 (0.8411) time: 0.1521 data: 0.0697 max mem: 8255 +Train: [62] [2700/6250] eta: 0:09:02 lr: 0.000042 grad: 0.0999 (0.1143) loss: 0.8447 (0.8411) time: 0.2140 data: 0.1441 max mem: 8255 +Train: [62] [2800/6250] eta: 0:08:45 lr: 0.000042 grad: 0.1015 (0.1141) loss: 0.8402 (0.8410) time: 0.1383 data: 0.0601 max mem: 8255 +Train: [62] [2900/6250] eta: 0:08:28 lr: 0.000042 grad: 0.1015 (0.1140) loss: 0.8362 (0.8411) time: 0.1235 data: 0.0506 max mem: 8255 +Train: [62] [3000/6250] eta: 0:08:13 lr: 0.000042 grad: 0.1061 (0.1138) loss: 0.8427 (0.8410) time: 0.1567 data: 0.0880 max mem: 8255 +Train: [62] [3100/6250] eta: 0:07:58 lr: 0.000042 grad: 0.1090 (0.1136) loss: 0.8459 (0.8410) time: 0.1597 data: 0.0859 max mem: 8255 +Train: [62] [3200/6250] eta: 0:07:42 lr: 0.000042 grad: 0.1099 (0.1136) loss: 0.8322 (0.8410) time: 0.1510 data: 0.0731 max mem: 8255 +Train: [62] [3300/6250] eta: 0:07:27 lr: 0.000042 grad: 0.1103 (0.1136) loss: 0.8351 (0.8409) time: 0.1472 data: 0.0699 max mem: 8255 +Train: [62] [3400/6250] eta: 0:07:11 lr: 0.000042 grad: 0.1072 (0.1135) loss: 0.8402 (0.8408) time: 0.1324 data: 0.0590 max mem: 8255 +Train: [62] [3500/6250] eta: 0:06:56 lr: 0.000042 grad: 0.1121 (0.1137) loss: 0.8374 (0.8407) time: 0.1629 data: 0.0829 max mem: 8255 +Train: [62] [3600/6250] eta: 0:06:40 lr: 0.000042 grad: 0.1065 (0.1136) loss: 0.8348 (0.8407) time: 0.1393 data: 0.0642 max mem: 8255 +Train: [62] [3700/6250] eta: 0:06:24 lr: 0.000042 grad: 0.1057 (0.1135) loss: 0.8424 (0.8406) time: 0.1231 data: 0.0430 max mem: 8255 +Train: [62] [3800/6250] eta: 0:06:09 lr: 0.000042 grad: 0.1032 (0.1135) loss: 0.8433 (0.8406) time: 0.1489 data: 0.0672 max mem: 8255 +Train: [62] [3900/6250] eta: 0:05:54 lr: 0.000042 grad: 0.1117 (0.1134) loss: 0.8413 (0.8406) time: 0.1339 data: 0.0553 max mem: 8255 +Train: [62] [4000/6250] eta: 0:05:39 lr: 0.000042 grad: 0.1089 (0.1134) loss: 0.8410 (0.8406) time: 0.1612 data: 0.0811 max mem: 8255 +Train: [62] [4100/6250] eta: 0:05:25 lr: 0.000042 grad: 0.1035 (0.1134) loss: 0.8502 (0.8406) time: 0.1485 data: 0.0654 max mem: 8255 +Train: [62] [4200/6250] eta: 0:05:10 lr: 0.000042 grad: 0.1060 (0.1134) loss: 0.8373 (0.8406) time: 0.1599 data: 0.0736 max mem: 8255 +Train: [62] [4300/6250] eta: 0:04:56 lr: 0.000042 grad: 0.1159 (0.1135) loss: 0.8399 (0.8405) time: 0.1485 data: 0.0665 max mem: 8255 +Train: [62] [4400/6250] eta: 0:04:41 lr: 0.000042 grad: 0.1107 (0.1134) loss: 0.8335 (0.8404) time: 0.1550 data: 0.0720 max mem: 8255 +Train: [62] [4500/6250] eta: 0:04:27 lr: 0.000042 grad: 0.1027 (0.1134) loss: 0.8315 (0.8403) time: 0.1672 data: 0.0810 max mem: 8255 +Train: [62] [4600/6250] eta: 0:04:12 lr: 0.000042 grad: 0.1104 (0.1134) loss: 0.8430 (0.8403) time: 0.1433 data: 0.0697 max mem: 8255 +Train: [62] [4700/6250] eta: 0:03:57 lr: 0.000042 grad: 0.1052 (0.1134) loss: 0.8411 (0.8403) time: 0.1636 data: 0.0855 max mem: 8255 +Train: [62] [4800/6250] eta: 0:03:41 lr: 0.000042 grad: 0.1161 (0.1135) loss: 0.8416 (0.8403) time: 0.1478 data: 0.0546 max mem: 8255 +Train: [62] [4900/6250] eta: 0:03:26 lr: 0.000042 grad: 0.1032 (0.1134) loss: 0.8359 (0.8402) time: 0.1347 data: 0.0485 max mem: 8255 +Train: [62] [5000/6250] eta: 0:03:11 lr: 0.000042 grad: 0.1095 (0.1134) loss: 0.8392 (0.8402) time: 0.1417 data: 0.0615 max mem: 8255 +Train: [62] [5100/6250] eta: 0:02:55 lr: 0.000042 grad: 0.1013 (0.1134) loss: 0.8487 (0.8402) time: 0.1554 data: 0.0674 max mem: 8255 +Train: [62] [5200/6250] eta: 0:02:40 lr: 0.000042 grad: 0.1061 (0.1133) loss: 0.8423 (0.8402) time: 0.1588 data: 0.0840 max mem: 8255 +Train: [62] [5300/6250] eta: 0:02:25 lr: 0.000042 grad: 0.1027 (0.1133) loss: 0.8471 (0.8403) time: 0.1269 data: 0.0358 max mem: 8255 +Train: [62] [5400/6250] eta: 0:02:09 lr: 0.000041 grad: 0.1053 (0.1132) loss: 0.8499 (0.8403) time: 0.1612 data: 0.0791 max mem: 8255 +Train: [62] [5500/6250] eta: 0:01:54 lr: 0.000041 grad: 0.1118 (0.1132) loss: 0.8381 (0.8404) time: 0.1289 data: 0.0585 max mem: 8255 +Train: [62] [5600/6250] eta: 0:01:39 lr: 0.000041 grad: 0.1064 (0.1132) loss: 0.8471 (0.8404) time: 0.1173 data: 0.0532 max mem: 8255 +Train: [62] [5700/6250] eta: 0:01:23 lr: 0.000041 grad: 0.1080 (0.1132) loss: 0.8413 (0.8404) time: 0.1076 data: 0.0290 max mem: 8255 +Train: [62] [5800/6250] eta: 0:01:08 lr: 0.000041 grad: 0.1040 (0.1131) loss: 0.8434 (0.8404) time: 0.1536 data: 0.0716 max mem: 8255 +Train: [62] [5900/6250] eta: 0:00:53 lr: 0.000041 grad: 0.1108 (0.1131) loss: 0.8422 (0.8404) time: 0.1543 data: 0.0802 max mem: 8255 +Train: [62] [6000/6250] eta: 0:00:38 lr: 0.000041 grad: 0.1124 (0.1130) loss: 0.8459 (0.8405) time: 0.1466 data: 0.0639 max mem: 8255 +Train: [62] [6100/6250] eta: 0:00:22 lr: 0.000041 grad: 0.1061 (0.1131) loss: 0.8466 (0.8405) time: 0.1354 data: 0.0324 max mem: 8255 +Train: [62] [6200/6250] eta: 0:00:07 lr: 0.000041 grad: 0.1072 (0.1131) loss: 0.8414 (0.8405) time: 0.1101 data: 0.0216 max mem: 8255 +Train: [62] [6249/6250] eta: 0:00:00 lr: 0.000041 grad: 0.1041 (0.1131) loss: 0.8458 (0.8405) time: 0.1395 data: 0.0768 max mem: 8255 +Train: [62] Total time: 0:16:04 (0.1543 s / it) +Averaged stats: lr: 0.000041 grad: 0.1041 (0.1131) loss: 0.8458 (0.8405) +Eval (hcp-train-subset): [62] [ 0/62] eta: 0:05:28 loss: 0.8737 (0.8737) time: 5.3063 data: 5.2804 max mem: 8255 +Eval (hcp-train-subset): [62] [61/62] eta: 0:00:00 loss: 0.8646 (0.8665) time: 0.1523 data: 0.1318 max mem: 8255 +Eval (hcp-train-subset): [62] Total time: 0:00:14 (0.2272 s / it) +Averaged stats (hcp-train-subset): loss: 0.8646 (0.8665) +Eval (hcp-val): [62] [ 0/62] eta: 0:03:44 loss: 0.8721 (0.8721) time: 3.6148 data: 3.5414 max mem: 8255 +Eval (hcp-val): [62] [61/62] eta: 0:00:00 loss: 0.8763 (0.8768) time: 0.1627 data: 0.1416 max mem: 8255 +Eval (hcp-val): [62] Total time: 0:00:14 (0.2397 s / it) +Averaged stats (hcp-val): loss: 0.8763 (0.8768) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +Train: [63] [ 0/6250] eta: 11:48:10 lr: 0.000041 grad: 0.5627 (0.5627) loss: 0.7781 (0.7781) time: 6.7985 data: 6.6933 max mem: 8255 +Train: [63] [ 100/6250] eta: 0:24:20 lr: 0.000041 grad: 0.1144 (0.1506) loss: 0.8695 (0.8607) time: 0.1673 data: 0.0618 max mem: 8255 +Train: [63] [ 200/6250] eta: 0:20:14 lr: 0.000041 grad: 0.1032 (0.1308) loss: 0.8514 (0.8589) time: 0.1931 data: 0.1080 max mem: 8255 +Train: [63] [ 300/6250] eta: 0:18:30 lr: 0.000041 grad: 0.1021 (0.1236) loss: 0.8557 (0.8580) time: 0.1555 data: 0.0547 max mem: 8255 +Train: [63] [ 400/6250] eta: 0:17:27 lr: 0.000041 grad: 0.1067 (0.1221) loss: 0.8521 (0.8563) time: 0.1434 data: 0.0465 max mem: 8255 +Train: [63] [ 500/6250] eta: 0:17:01 lr: 0.000041 grad: 0.1035 (0.1201) loss: 0.8437 (0.8550) time: 0.1696 data: 0.0703 max mem: 8255 +Train: [63] [ 600/6250] eta: 0:16:27 lr: 0.000041 grad: 0.1066 (0.1188) loss: 0.8463 (0.8535) time: 0.1561 data: 0.0764 max mem: 8255 +Train: [63] [ 700/6250] eta: 0:15:58 lr: 0.000041 grad: 0.1107 (0.1176) loss: 0.8500 (0.8521) time: 0.1514 data: 0.0770 max mem: 8255 +Train: [63] [ 800/6250] eta: 0:15:36 lr: 0.000041 grad: 0.1089 (0.1169) loss: 0.8510 (0.8516) time: 0.1923 data: 0.1071 max mem: 8255 +Train: [63] [ 900/6250] eta: 0:15:08 lr: 0.000041 grad: 0.1051 (0.1162) loss: 0.8509 (0.8511) time: 0.1382 data: 0.0529 max mem: 8255 +Train: [63] [1000/6250] eta: 0:14:49 lr: 0.000041 grad: 0.1122 (0.1156) loss: 0.8426 (0.8506) time: 0.1666 data: 0.0771 max mem: 8255 +Train: [63] [1100/6250] eta: 0:14:40 lr: 0.000041 grad: 0.1082 (0.1154) loss: 0.8506 (0.8501) time: 0.2946 data: 0.2171 max mem: 8255 +Train: [63] [1200/6250] eta: 0:14:11 lr: 0.000041 grad: 0.1072 (0.1150) loss: 0.8401 (0.8496) time: 0.1974 data: 0.1332 max mem: 8255 +Train: [63] [1300/6250] eta: 0:13:56 lr: 0.000041 grad: 0.1125 (0.1148) loss: 0.8383 (0.8490) time: 0.1124 data: 0.0214 max mem: 8255 +Train: [63] [1400/6250] eta: 0:13:35 lr: 0.000041 grad: 0.1129 (0.1146) loss: 0.8427 (0.8485) time: 0.1583 data: 0.0758 max mem: 8255 +Train: [63] [1500/6250] eta: 0:13:20 lr: 0.000041 grad: 0.1091 (0.1145) loss: 0.8378 (0.8481) time: 0.1827 data: 0.1098 max mem: 8255 +Train: [63] [1600/6250] eta: 0:12:54 lr: 0.000041 grad: 0.1105 (0.1145) loss: 0.8398 (0.8477) time: 0.1650 data: 0.0748 max mem: 8255 +Train: [63] [1700/6250] eta: 0:12:33 lr: 0.000041 grad: 0.1120 (0.1145) loss: 0.8285 (0.8469) time: 0.1654 data: 0.0908 max mem: 8255 +Train: [63] [1800/6250] eta: 0:12:13 lr: 0.000041 grad: 0.1119 (0.1145) loss: 0.8287 (0.8463) time: 0.1399 data: 0.0535 max mem: 8255 +Train: [63] [1900/6250] eta: 0:11:51 lr: 0.000041 grad: 0.1124 (0.1145) loss: 0.8464 (0.8459) time: 0.1559 data: 0.0779 max mem: 8255 +Train: [63] [2000/6250] eta: 0:11:30 lr: 0.000041 grad: 0.1067 (0.1144) loss: 0.8381 (0.8458) time: 0.1361 data: 0.0594 max mem: 8255 +Train: [63] [2100/6250] eta: 0:11:11 lr: 0.000041 grad: 0.1122 (0.1142) loss: 0.8424 (0.8456) time: 0.1375 data: 0.0413 max mem: 8255 +Train: [63] [2200/6250] eta: 0:10:52 lr: 0.000041 grad: 0.1072 (0.1142) loss: 0.8402 (0.8454) time: 0.1407 data: 0.0591 max mem: 8255 +Train: [63] [2300/6250] eta: 0:10:36 lr: 0.000041 grad: 0.1123 (0.1141) loss: 0.8427 (0.8451) time: 0.1814 data: 0.1011 max mem: 8255 +Train: [63] [2400/6250] eta: 0:10:18 lr: 0.000040 grad: 0.1158 (0.1141) loss: 0.8369 (0.8448) time: 0.1306 data: 0.0510 max mem: 8255 +Train: [63] [2500/6250] eta: 0:10:03 lr: 0.000040 grad: 0.1037 (0.1139) loss: 0.8401 (0.8448) time: 0.1611 data: 0.0803 max mem: 8255 +Train: [63] [2600/6250] eta: 0:09:50 lr: 0.000040 grad: 0.1120 (0.1138) loss: 0.8447 (0.8446) time: 0.1042 data: 0.0002 max mem: 8255 +Train: [63] [2700/6250] eta: 0:09:32 lr: 0.000040 grad: 0.1009 (0.1137) loss: 0.8561 (0.8446) time: 0.1627 data: 0.0863 max mem: 8255 +Train: [63] [2800/6250] eta: 0:09:14 lr: 0.000040 grad: 0.1085 (0.1136) loss: 0.8406 (0.8446) time: 0.1628 data: 0.0945 max mem: 8255 +Train: [63] [2900/6250] eta: 0:08:56 lr: 0.000040 grad: 0.1079 (0.1136) loss: 0.8437 (0.8444) time: 0.1455 data: 0.0715 max mem: 8255 +Train: [63] [3000/6250] eta: 0:08:40 lr: 0.000040 grad: 0.1050 (0.1134) loss: 0.8471 (0.8443) time: 0.1838 data: 0.1032 max mem: 8255 +Train: [63] [3100/6250] eta: 0:08:24 lr: 0.000040 grad: 0.1018 (0.1132) loss: 0.8468 (0.8443) time: 0.1489 data: 0.0773 max mem: 8255 +Train: [63] [3200/6250] eta: 0:08:06 lr: 0.000040 grad: 0.1042 (0.1131) loss: 0.8445 (0.8442) time: 0.1448 data: 0.0728 max mem: 8255 +Train: [63] [3300/6250] eta: 0:07:50 lr: 0.000040 grad: 0.1094 (0.1130) loss: 0.8372 (0.8442) time: 0.1324 data: 0.0557 max mem: 8255 +Train: [63] [3400/6250] eta: 0:07:33 lr: 0.000040 grad: 0.1085 (0.1129) loss: 0.8442 (0.8442) time: 0.1536 data: 0.0704 max mem: 8255 +Train: [63] [3500/6250] eta: 0:07:16 lr: 0.000040 grad: 0.1037 (0.1129) loss: 0.8421 (0.8440) time: 0.1140 data: 0.0206 max mem: 8255 +Train: [63] [3600/6250] eta: 0:07:00 lr: 0.000040 grad: 0.1137 (0.1128) loss: 0.8389 (0.8439) time: 0.1426 data: 0.0721 max mem: 8255 +Train: [63] [3700/6250] eta: 0:06:43 lr: 0.000040 grad: 0.1042 (0.1128) loss: 0.8468 (0.8439) time: 0.1142 data: 0.0235 max mem: 8255 +Train: [63] [3800/6250] eta: 0:06:27 lr: 0.000040 grad: 0.1087 (0.1128) loss: 0.8455 (0.8437) time: 0.1532 data: 0.0781 max mem: 8255 +Train: [63] [3900/6250] eta: 0:06:10 lr: 0.000040 grad: 0.1123 (0.1128) loss: 0.8311 (0.8435) time: 0.1566 data: 0.0808 max mem: 8255 +Train: [63] [4000/6250] eta: 0:05:54 lr: 0.000040 grad: 0.1068 (0.1128) loss: 0.8379 (0.8433) time: 0.1366 data: 0.0708 max mem: 8255 +Train: [63] [4100/6250] eta: 0:05:37 lr: 0.000040 grad: 0.1098 (0.1128) loss: 0.8403 (0.8431) time: 0.1335 data: 0.0612 max mem: 8255 +Train: [63] [4200/6250] eta: 0:05:20 lr: 0.000040 grad: 0.1110 (0.1129) loss: 0.8370 (0.8429) time: 0.1411 data: 0.0733 max mem: 8255 +Train: [63] [4300/6250] eta: 0:05:04 lr: 0.000040 grad: 0.1173 (0.1129) loss: 0.8407 (0.8428) time: 0.1484 data: 0.0764 max mem: 8255 +Train: [63] [4400/6250] eta: 0:04:47 lr: 0.000040 grad: 0.1125 (0.1129) loss: 0.8413 (0.8426) time: 0.1326 data: 0.0648 max mem: 8255 +Train: [63] [4500/6250] eta: 0:04:30 lr: 0.000040 grad: 0.1113 (0.1129) loss: 0.8403 (0.8425) time: 0.1302 data: 0.0555 max mem: 8255 +Train: [63] [4600/6250] eta: 0:04:15 lr: 0.000040 grad: 0.1110 (0.1129) loss: 0.8391 (0.8424) time: 0.1384 data: 0.0659 max mem: 8255 +Train: [63] [4700/6250] eta: 0:04:00 lr: 0.000040 grad: 0.1087 (0.1129) loss: 0.8460 (0.8424) time: 0.1819 data: 0.0992 max mem: 8255 +Train: [63] [4800/6250] eta: 0:03:45 lr: 0.000040 grad: 0.1113 (0.1130) loss: 0.8385 (0.8422) time: 0.2096 data: 0.1274 max mem: 8255 +Train: [63] [4900/6250] eta: 0:03:30 lr: 0.000040 grad: 0.1087 (0.1130) loss: 0.8456 (0.8422) time: 0.1621 data: 0.0837 max mem: 8255 +Train: [63] [5000/6250] eta: 0:03:14 lr: 0.000040 grad: 0.1134 (0.1130) loss: 0.8397 (0.8421) time: 0.1699 data: 0.0923 max mem: 8255 +Train: [63] [5100/6250] eta: 0:02:59 lr: 0.000040 grad: 0.1071 (0.1130) loss: 0.8458 (0.8421) time: 0.1377 data: 0.0318 max mem: 8255 +Train: [63] [5200/6250] eta: 0:02:43 lr: 0.000040 grad: 0.1126 (0.1130) loss: 0.8381 (0.8421) time: 0.1438 data: 0.0612 max mem: 8255 +Train: [63] [5300/6250] eta: 0:02:28 lr: 0.000040 grad: 0.1152 (0.1129) loss: 0.8399 (0.8422) time: 0.2121 data: 0.1395 max mem: 8255 +Train: [63] [5400/6250] eta: 0:02:12 lr: 0.000040 grad: 0.1086 (0.1129) loss: 0.8457 (0.8422) time: 0.1262 data: 0.0472 max mem: 8255 +Train: [63] [5500/6250] eta: 0:01:57 lr: 0.000040 grad: 0.1116 (0.1129) loss: 0.8515 (0.8422) time: 0.1610 data: 0.0925 max mem: 8255 +Train: [63] [5600/6250] eta: 0:01:41 lr: 0.000039 grad: 0.1124 (0.1130) loss: 0.8443 (0.8423) time: 0.1605 data: 0.0947 max mem: 8255 +Train: [63] [5700/6250] eta: 0:01:26 lr: 0.000039 grad: 0.1107 (0.1131) loss: 0.8389 (0.8423) time: 0.1531 data: 0.0821 max mem: 8255 +Train: [63] [5800/6250] eta: 0:01:10 lr: 0.000039 grad: 0.1122 (0.1131) loss: 0.8420 (0.8422) time: 0.1670 data: 0.1033 max mem: 8255 +Train: [63] [5900/6250] eta: 0:00:54 lr: 0.000039 grad: 0.1056 (0.1132) loss: 0.8455 (0.8422) time: 0.1568 data: 0.0756 max mem: 8255 +Train: [63] [6000/6250] eta: 0:00:39 lr: 0.000039 grad: 0.1124 (0.1133) loss: 0.8407 (0.8421) time: 0.1385 data: 0.0534 max mem: 8255 +Train: [63] [6100/6250] eta: 0:00:23 lr: 0.000039 grad: 0.1126 (0.1133) loss: 0.8398 (0.8420) time: 0.1583 data: 0.0735 max mem: 8255 +Train: [63] [6200/6250] eta: 0:00:07 lr: 0.000039 grad: 0.1185 (0.1134) loss: 0.8399 (0.8419) time: 0.1420 data: 0.0564 max mem: 8255 +Train: [63] [6249/6250] eta: 0:00:00 lr: 0.000039 grad: 0.1149 (0.1134) loss: 0.8348 (0.8419) time: 0.1684 data: 0.0951 max mem: 8255 +Train: [63] Total time: 0:16:25 (0.1576 s / it) +Averaged stats: lr: 0.000039 grad: 0.1149 (0.1134) loss: 0.8348 (0.8419) +Eval (hcp-train-subset): [63] [ 0/62] eta: 0:05:14 loss: 0.8841 (0.8841) time: 5.0675 data: 5.0397 max mem: 8255 +Eval (hcp-train-subset): [63] [61/62] eta: 0:00:00 loss: 0.8686 (0.8684) time: 0.1494 data: 0.1283 max mem: 8255 +Eval (hcp-train-subset): [63] Total time: 0:00:15 (0.2518 s / it) +Averaged stats (hcp-train-subset): loss: 0.8686 (0.8684) +Eval (hcp-val): [63] [ 0/62] eta: 0:05:29 loss: 0.8728 (0.8728) time: 5.3086 data: 5.2541 max mem: 8255 +Eval (hcp-val): [63] [61/62] eta: 0:00:00 loss: 0.8753 (0.8767) time: 0.1169 data: 0.0941 max mem: 8255 +Eval (hcp-val): [63] Total time: 0:00:17 (0.2874 s / it) +Averaged stats (hcp-val): loss: 0.8753 (0.8767) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +Train: [64] [ 0/6250] eta: 9:10:12 lr: 0.000039 grad: 0.1136 (0.1136) loss: 0.8687 (0.8687) time: 5.2821 data: 5.0683 max mem: 8255 +Train: [64] [ 100/6250] eta: 0:25:38 lr: 0.000039 grad: 0.0985 (0.1147) loss: 0.8683 (0.8712) time: 0.1855 data: 0.0780 max mem: 8255 +Train: [64] [ 200/6250] eta: 0:22:23 lr: 0.000039 grad: 0.1240 (0.1190) loss: 0.8413 (0.8630) time: 0.1949 data: 0.0991 max mem: 8255 +Train: [64] [ 300/6250] eta: 0:20:44 lr: 0.000039 grad: 0.1256 (0.1227) loss: 0.8446 (0.8569) time: 0.1568 data: 0.0376 max mem: 8255 +Train: [64] [ 400/6250] eta: 0:19:24 lr: 0.000039 grad: 0.1210 (0.1219) loss: 0.8370 (0.8531) time: 0.1561 data: 0.0674 max mem: 8255 +Train: [64] [ 500/6250] eta: 0:18:53 lr: 0.000039 grad: 0.1068 (0.1207) loss: 0.8485 (0.8506) time: 0.1416 data: 0.0003 max mem: 8255 +Train: [64] [ 600/6250] eta: 0:18:03 lr: 0.000039 grad: 0.1078 (0.1191) loss: 0.8353 (0.8487) time: 0.1911 data: 0.0944 max mem: 8255 +Train: [64] [ 700/6250] eta: 0:17:20 lr: 0.000039 grad: 0.1067 (0.1182) loss: 0.8445 (0.8475) time: 0.1690 data: 0.0779 max mem: 8255 +Train: [64] [ 800/6250] eta: 0:17:26 lr: 0.000039 grad: 0.1038 (0.1174) loss: 0.8459 (0.8466) time: 0.2215 data: 0.1190 max mem: 8255 +Train: [64] [ 900/6250] eta: 0:17:03 lr: 0.000039 grad: 0.1049 (0.1168) loss: 0.8525 (0.8461) time: 0.2115 data: 0.1181 max mem: 8255 +Train: [64] [1000/6250] eta: 0:16:32 lr: 0.000039 grad: 0.1112 (0.1165) loss: 0.8443 (0.8455) time: 0.2101 data: 0.1353 max mem: 8255 +Train: [64] [1100/6250] eta: 0:15:49 lr: 0.000039 grad: 0.1170 (0.1164) loss: 0.8436 (0.8448) time: 0.1261 data: 0.0381 max mem: 8255 +Train: [64] [1200/6250] eta: 0:15:24 lr: 0.000039 grad: 0.1031 (0.1158) loss: 0.8473 (0.8446) time: 0.1294 data: 0.0473 max mem: 8255 +Train: [64] [1300/6250] eta: 0:14:58 lr: 0.000039 grad: 0.1061 (0.1153) loss: 0.8330 (0.8440) time: 0.1747 data: 0.0917 max mem: 8255 +Train: [64] [1400/6250] eta: 0:14:29 lr: 0.000039 grad: 0.1075 (0.1152) loss: 0.8462 (0.8436) time: 0.1379 data: 0.0591 max mem: 8255 +Train: [64] [1500/6250] eta: 0:14:00 lr: 0.000039 grad: 0.1119 (0.1150) loss: 0.8420 (0.8432) time: 0.1448 data: 0.0604 max mem: 8255 +Train: [64] [1600/6250] eta: 0:13:38 lr: 0.000039 grad: 0.1109 (0.1149) loss: 0.8413 (0.8429) time: 0.1430 data: 0.0686 max mem: 8255 +Train: [64] [1700/6250] eta: 0:13:17 lr: 0.000039 grad: 0.1070 (0.1147) loss: 0.8414 (0.8426) time: 0.1418 data: 0.0513 max mem: 8255 +Train: [64] [1800/6250] eta: 0:12:54 lr: 0.000039 grad: 0.1098 (0.1149) loss: 0.8402 (0.8423) time: 0.1539 data: 0.0849 max mem: 8255 +Train: [64] [1900/6250] eta: 0:12:34 lr: 0.000039 grad: 0.1014 (0.1147) loss: 0.8281 (0.8419) time: 0.1597 data: 0.0798 max mem: 8255 +Train: [64] [2000/6250] eta: 0:12:12 lr: 0.000039 grad: 0.1059 (0.1145) loss: 0.8396 (0.8417) time: 0.1542 data: 0.0776 max mem: 8255 +Train: [64] [2100/6250] eta: 0:11:51 lr: 0.000039 grad: 0.1089 (0.1145) loss: 0.8443 (0.8414) time: 0.1431 data: 0.0519 max mem: 8255 +Train: [64] [2200/6250] eta: 0:11:30 lr: 0.000039 grad: 0.1155 (0.1144) loss: 0.8332 (0.8412) time: 0.1668 data: 0.0846 max mem: 8255 +Train: [64] [2300/6250] eta: 0:11:11 lr: 0.000039 grad: 0.1179 (0.1144) loss: 0.8364 (0.8409) time: 0.1581 data: 0.0785 max mem: 8255 +Train: [64] [2400/6250] eta: 0:10:52 lr: 0.000039 grad: 0.1105 (0.1143) loss: 0.8437 (0.8408) time: 0.1513 data: 0.0718 max mem: 8255 +Train: [64] [2500/6250] eta: 0:10:33 lr: 0.000039 grad: 0.1067 (0.1142) loss: 0.8412 (0.8406) time: 0.1892 data: 0.0980 max mem: 8255 +Train: [64] [2600/6250] eta: 0:10:18 lr: 0.000039 grad: 0.1103 (0.1142) loss: 0.8405 (0.8405) time: 0.2077 data: 0.1333 max mem: 8255 +Train: [64] [2700/6250] eta: 0:10:01 lr: 0.000038 grad: 0.1088 (0.1142) loss: 0.8361 (0.8404) time: 0.1577 data: 0.0783 max mem: 8255 +Train: [64] [2800/6250] eta: 0:09:45 lr: 0.000038 grad: 0.1163 (0.1142) loss: 0.8367 (0.8403) time: 0.1948 data: 0.1091 max mem: 8255 +Train: [64] [2900/6250] eta: 0:09:29 lr: 0.000038 grad: 0.1046 (0.1143) loss: 0.8418 (0.8401) time: 0.1508 data: 0.0840 max mem: 8255 +Train: [64] [3000/6250] eta: 0:09:12 lr: 0.000038 grad: 0.1098 (0.1142) loss: 0.8374 (0.8400) time: 0.2080 data: 0.0614 max mem: 8255 +Train: [64] [3100/6250] eta: 0:08:56 lr: 0.000038 grad: 0.1128 (0.1141) loss: 0.8475 (0.8399) time: 0.1534 data: 0.0698 max mem: 8255 +Train: [64] [3200/6250] eta: 0:08:38 lr: 0.000038 grad: 0.1103 (0.1141) loss: 0.8308 (0.8398) time: 0.1523 data: 0.0730 max mem: 8255 +Train: [64] [3300/6250] eta: 0:08:24 lr: 0.000038 grad: 0.1042 (0.1140) loss: 0.8423 (0.8398) time: 0.1995 data: 0.1077 max mem: 8255 +Train: [64] [3400/6250] eta: 0:08:05 lr: 0.000038 grad: 0.1059 (0.1140) loss: 0.8515 (0.8398) time: 0.1548 data: 0.0826 max mem: 8255 +Train: [64] [3500/6250] eta: 0:07:46 lr: 0.000038 grad: 0.1101 (0.1139) loss: 0.8410 (0.8398) time: 0.1433 data: 0.0682 max mem: 8255 +Train: [64] [3600/6250] eta: 0:07:27 lr: 0.000038 grad: 0.1007 (0.1138) loss: 0.8429 (0.8397) time: 0.1379 data: 0.0510 max mem: 8255 +Train: [64] [3700/6250] eta: 0:07:10 lr: 0.000038 grad: 0.1053 (0.1138) loss: 0.8442 (0.8397) time: 0.1659 data: 0.0864 max mem: 8255 +Train: [64] [3800/6250] eta: 0:06:51 lr: 0.000038 grad: 0.1160 (0.1138) loss: 0.8411 (0.8397) time: 0.1349 data: 0.0526 max mem: 8255 +Train: [64] [3900/6250] eta: 0:06:33 lr: 0.000038 grad: 0.1106 (0.1138) loss: 0.8371 (0.8397) time: 0.1463 data: 0.0665 max mem: 8255 +Train: [64] [4000/6250] eta: 0:06:15 lr: 0.000038 grad: 0.1117 (0.1137) loss: 0.8376 (0.8397) time: 0.1391 data: 0.0662 max mem: 8255 +Train: [64] [4100/6250] eta: 0:05:58 lr: 0.000038 grad: 0.1054 (0.1136) loss: 0.8396 (0.8398) time: 0.1485 data: 0.0797 max mem: 8255 +Train: [64] [4200/6250] eta: 0:05:40 lr: 0.000038 grad: 0.1072 (0.1136) loss: 0.8393 (0.8398) time: 0.1362 data: 0.0677 max mem: 8255 +Train: [64] [4300/6250] eta: 0:05:22 lr: 0.000038 grad: 0.1146 (0.1135) loss: 0.8326 (0.8398) time: 0.1509 data: 0.0617 max mem: 8255 +Train: [64] [4400/6250] eta: 0:05:06 lr: 0.000038 grad: 0.1061 (0.1135) loss: 0.8427 (0.8397) time: 0.1624 data: 0.0875 max mem: 8255 +Train: [64] [4500/6250] eta: 0:04:49 lr: 0.000038 grad: 0.1061 (0.1135) loss: 0.8411 (0.8397) time: 0.1741 data: 0.0866 max mem: 8255 +Train: [64] [4600/6250] eta: 0:04:32 lr: 0.000038 grad: 0.1117 (0.1135) loss: 0.8328 (0.8397) time: 0.2192 data: 0.1551 max mem: 8255 +Train: [64] [4700/6250] eta: 0:04:17 lr: 0.000038 grad: 0.1075 (0.1134) loss: 0.8402 (0.8398) time: 0.1808 data: 0.1047 max mem: 8255 +Train: [64] [4800/6250] eta: 0:04:00 lr: 0.000038 grad: 0.1071 (0.1133) loss: 0.8404 (0.8398) time: 0.1463 data: 0.0711 max mem: 8255 +Train: [64] [4900/6250] eta: 0:03:44 lr: 0.000038 grad: 0.1067 (0.1132) loss: 0.8395 (0.8398) time: 0.1936 data: 0.1181 max mem: 8255 +Train: [64] [5000/6250] eta: 0:03:28 lr: 0.000038 grad: 0.1081 (0.1131) loss: 0.8418 (0.8398) time: 0.1550 data: 0.0766 max mem: 8255 +Train: [64] [5100/6250] eta: 0:03:12 lr: 0.000038 grad: 0.1089 (0.1131) loss: 0.8427 (0.8399) time: 0.1696 data: 0.0749 max mem: 8255 +Train: [64] [5200/6250] eta: 0:02:55 lr: 0.000038 grad: 0.1015 (0.1129) loss: 0.8472 (0.8400) time: 0.1836 data: 0.0977 max mem: 8255 +Train: [64] [5300/6250] eta: 0:02:39 lr: 0.000038 grad: 0.1117 (0.1129) loss: 0.8405 (0.8401) time: 0.1684 data: 0.0863 max mem: 8255 +Train: [64] [5400/6250] eta: 0:02:22 lr: 0.000038 grad: 0.1059 (0.1129) loss: 0.8387 (0.8402) time: 0.1698 data: 0.0836 max mem: 8255 +Train: [64] [5500/6250] eta: 0:02:05 lr: 0.000038 grad: 0.1046 (0.1129) loss: 0.8435 (0.8402) time: 0.1842 data: 0.1016 max mem: 8255 +Train: [64] [5600/6250] eta: 0:01:48 lr: 0.000038 grad: 0.1101 (0.1128) loss: 0.8423 (0.8403) time: 0.1222 data: 0.0521 max mem: 8255 +Train: [64] [5700/6250] eta: 0:01:31 lr: 0.000038 grad: 0.1143 (0.1128) loss: 0.8442 (0.8403) time: 0.1632 data: 0.0834 max mem: 8255 +Train: [64] [5800/6250] eta: 0:01:15 lr: 0.000038 grad: 0.1108 (0.1128) loss: 0.8430 (0.8403) time: 0.1679 data: 0.0954 max mem: 8255 +Train: [64] [5900/6250] eta: 0:00:58 lr: 0.000037 grad: 0.1113 (0.1128) loss: 0.8426 (0.8403) time: 0.1591 data: 0.0868 max mem: 8255 +Train: [64] [6000/6250] eta: 0:00:41 lr: 0.000037 grad: 0.1131 (0.1128) loss: 0.8376 (0.8403) time: 0.1722 data: 0.1008 max mem: 8255 +Train: [64] [6100/6250] eta: 0:00:24 lr: 0.000037 grad: 0.1115 (0.1129) loss: 0.8458 (0.8403) time: 0.1526 data: 0.0756 max mem: 8255 +Train: [64] [6200/6250] eta: 0:00:08 lr: 0.000037 grad: 0.1031 (0.1129) loss: 0.8513 (0.8403) time: 0.1455 data: 0.0709 max mem: 8255 +Train: [64] [6249/6250] eta: 0:00:00 lr: 0.000037 grad: 0.1148 (0.1129) loss: 0.8397 (0.8403) time: 0.1559 data: 0.0784 max mem: 8255 +Train: [64] Total time: 0:17:24 (0.1672 s / it) +Averaged stats: lr: 0.000037 grad: 0.1148 (0.1129) loss: 0.8397 (0.8403) +Eval (hcp-train-subset): [64] [ 0/62] eta: 0:05:30 loss: 0.8756 (0.8756) time: 5.3239 data: 5.2981 max mem: 8255 +Eval (hcp-train-subset): [64] [61/62] eta: 0:00:00 loss: 0.8658 (0.8673) time: 0.1409 data: 0.1197 max mem: 8255 +Eval (hcp-train-subset): [64] Total time: 0:00:14 (0.2375 s / it) +Averaged stats (hcp-train-subset): loss: 0.8658 (0.8673) +Making plots (hcp-train-subset): example=28 +Eval (hcp-val): [64] [ 0/62] eta: 0:05:44 loss: 0.8742 (0.8742) time: 5.5494 data: 5.5213 max mem: 8255 +Eval (hcp-val): [64] [61/62] eta: 0:00:00 loss: 0.8760 (0.8762) time: 0.1015 data: 0.0795 max mem: 8255 +Eval (hcp-val): [64] Total time: 0:00:14 (0.2386 s / it) +Averaged stats (hcp-val): loss: 0.8760 (0.8762) +Making plots (hcp-val): example=43 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +Train: [65] [ 0/6250] eta: 8:33:02 lr: 0.000037 grad: 0.0731 (0.0731) loss: 0.8863 (0.8863) time: 4.9251 data: 4.7085 max mem: 8255 +Train: [65] [ 100/6250] eta: 0:20:43 lr: 0.000037 grad: 0.1242 (0.1483) loss: 0.8494 (0.8632) time: 0.1573 data: 0.0638 max mem: 8255 +Train: [65] [ 200/6250] eta: 0:18:49 lr: 0.000037 grad: 0.1189 (0.1348) loss: 0.8433 (0.8579) time: 0.1631 data: 0.0658 max mem: 8255 +Train: [65] [ 300/6250] eta: 0:18:32 lr: 0.000037 grad: 0.1152 (0.1294) loss: 0.8472 (0.8551) time: 0.2053 data: 0.0992 max mem: 8255 +Train: [65] [ 400/6250] eta: 0:17:47 lr: 0.000037 grad: 0.1110 (0.1254) loss: 0.8427 (0.8528) time: 0.1663 data: 0.0760 max mem: 8255 +Train: [65] [ 500/6250] eta: 0:17:10 lr: 0.000037 grad: 0.1123 (0.1234) loss: 0.8456 (0.8511) time: 0.1702 data: 0.0893 max mem: 8255 +Train: [65] [ 600/6250] eta: 0:17:05 lr: 0.000037 grad: 0.1101 (0.1212) loss: 0.8470 (0.8498) time: 0.2139 data: 0.1238 max mem: 8255 +Train: [65] [ 700/6250] eta: 0:16:26 lr: 0.000037 grad: 0.1062 (0.1193) loss: 0.8424 (0.8491) time: 0.1611 data: 0.0496 max mem: 8255 +Train: [65] [ 800/6250] eta: 0:16:19 lr: 0.000037 grad: 0.1072 (0.1181) loss: 0.8478 (0.8488) time: 0.2809 data: 0.1267 max mem: 8255 +Train: [65] [ 900/6250] eta: 0:16:13 lr: 0.000037 grad: 0.1157 (0.1173) loss: 0.8430 (0.8485) time: 0.2973 data: 0.2067 max mem: 8255 +Train: [65] [1000/6250] eta: 0:15:36 lr: 0.000037 grad: 0.1021 (0.1168) loss: 0.8555 (0.8485) time: 0.1620 data: 0.0938 max mem: 8255 +Train: [65] [1100/6250] eta: 0:15:10 lr: 0.000037 grad: 0.1135 (0.1161) loss: 0.8457 (0.8483) time: 0.1479 data: 0.0592 max mem: 8255 +Train: [65] [1200/6250] eta: 0:14:44 lr: 0.000037 grad: 0.1041 (0.1153) loss: 0.8498 (0.8482) time: 0.1284 data: 0.0512 max mem: 8255 +Train: [65] [1300/6250] eta: 0:14:18 lr: 0.000037 grad: 0.1085 (0.1147) loss: 0.8436 (0.8479) time: 0.1605 data: 0.0785 max mem: 8255 +Train: [65] [1400/6250] eta: 0:13:54 lr: 0.000037 grad: 0.1045 (0.1143) loss: 0.8500 (0.8476) time: 0.1302 data: 0.0442 max mem: 8255 +Train: [65] [1500/6250] eta: 0:13:31 lr: 0.000037 grad: 0.1048 (0.1139) loss: 0.8421 (0.8475) time: 0.1485 data: 0.0783 max mem: 8255 +Train: [65] [1600/6250] eta: 0:13:09 lr: 0.000037 grad: 0.1059 (0.1137) loss: 0.8456 (0.8473) time: 0.1384 data: 0.0557 max mem: 8255 +Train: [65] [1700/6250] eta: 0:12:49 lr: 0.000037 grad: 0.1052 (0.1134) loss: 0.8531 (0.8472) time: 0.1482 data: 0.0663 max mem: 8255 +Train: [65] [1800/6250] eta: 0:12:27 lr: 0.000037 grad: 0.1040 (0.1131) loss: 0.8469 (0.8471) time: 0.1653 data: 0.0822 max mem: 8255 +Train: [65] [1900/6250] eta: 0:12:03 lr: 0.000037 grad: 0.1107 (0.1128) loss: 0.8435 (0.8470) time: 0.1116 data: 0.0351 max mem: 8255 +Train: [65] [2000/6250] eta: 0:11:43 lr: 0.000037 grad: 0.1059 (0.1126) loss: 0.8481 (0.8469) time: 0.1409 data: 0.0637 max mem: 8255 +Train: [65] [2100/6250] eta: 0:11:23 lr: 0.000037 grad: 0.1031 (0.1124) loss: 0.8448 (0.8468) time: 0.1494 data: 0.0810 max mem: 8255 +Train: [65] [2200/6250] eta: 0:11:04 lr: 0.000037 grad: 0.1061 (0.1124) loss: 0.8479 (0.8468) time: 0.1629 data: 0.0857 max mem: 8255 +Train: [65] [2300/6250] eta: 0:10:47 lr: 0.000037 grad: 0.1071 (0.1122) loss: 0.8496 (0.8468) time: 0.1606 data: 0.0922 max mem: 8255 +Train: [65] [2400/6250] eta: 0:10:29 lr: 0.000037 grad: 0.1119 (0.1122) loss: 0.8464 (0.8467) time: 0.1341 data: 0.0450 max mem: 8255 +Train: [65] [2500/6250] eta: 0:10:10 lr: 0.000037 grad: 0.1050 (0.1122) loss: 0.8449 (0.8465) time: 0.1455 data: 0.0700 max mem: 8255 +Train: [65] [2600/6250] eta: 0:09:51 lr: 0.000037 grad: 0.1136 (0.1123) loss: 0.8414 (0.8465) time: 0.1615 data: 0.0849 max mem: 8255 +Train: [65] [2700/6250] eta: 0:09:34 lr: 0.000037 grad: 0.1120 (0.1123) loss: 0.8448 (0.8464) time: 0.1597 data: 0.0851 max mem: 8255 +Train: [65] [2800/6250] eta: 0:09:16 lr: 0.000037 grad: 0.1089 (0.1122) loss: 0.8437 (0.8464) time: 0.1665 data: 0.0967 max mem: 8255 +Train: [65] [2900/6250] eta: 0:08:59 lr: 0.000037 grad: 0.1104 (0.1122) loss: 0.8421 (0.8463) time: 0.1487 data: 0.0690 max mem: 8255 +Train: [65] [3000/6250] eta: 0:08:45 lr: 0.000036 grad: 0.1105 (0.1122) loss: 0.8404 (0.8462) time: 0.2165 data: 0.1436 max mem: 8255 +Train: [65] [3100/6250] eta: 0:08:30 lr: 0.000036 grad: 0.1112 (0.1122) loss: 0.8395 (0.8460) time: 0.1177 data: 0.0328 max mem: 8255 +Train: [65] [3200/6250] eta: 0:08:14 lr: 0.000036 grad: 0.1084 (0.1122) loss: 0.8391 (0.8458) time: 0.1621 data: 0.0851 max mem: 8255 +Train: [65] [3300/6250] eta: 0:07:58 lr: 0.000036 grad: 0.1056 (0.1122) loss: 0.8431 (0.8457) time: 0.2276 data: 0.0544 max mem: 8255 +Train: [65] [3400/6250] eta: 0:07:45 lr: 0.000036 grad: 0.1097 (0.1122) loss: 0.8379 (0.8456) time: 0.1606 data: 0.0760 max mem: 8255 +Train: [65] [3500/6250] eta: 0:07:27 lr: 0.000036 grad: 0.1063 (0.1121) loss: 0.8435 (0.8456) time: 0.1468 data: 0.0742 max mem: 8255 +Train: [65] [3600/6250] eta: 0:07:11 lr: 0.000036 grad: 0.1066 (0.1121) loss: 0.8404 (0.8456) time: 0.1814 data: 0.1041 max mem: 8255 +Train: [65] [3700/6250] eta: 0:06:54 lr: 0.000036 grad: 0.1053 (0.1120) loss: 0.8481 (0.8456) time: 0.1630 data: 0.0897 max mem: 8255 +Train: [65] [3800/6250] eta: 0:06:37 lr: 0.000036 grad: 0.1117 (0.1120) loss: 0.8475 (0.8455) time: 0.1464 data: 0.0680 max mem: 8255 +Train: [65] [3900/6250] eta: 0:06:21 lr: 0.000036 grad: 0.1053 (0.1120) loss: 0.8455 (0.8455) time: 0.1784 data: 0.1027 max mem: 8255 +Train: [65] [4000/6250] eta: 0:06:04 lr: 0.000036 grad: 0.1097 (0.1119) loss: 0.8434 (0.8456) time: 0.1576 data: 0.0871 max mem: 8255 +Train: [65] [4100/6250] eta: 0:05:48 lr: 0.000036 grad: 0.1035 (0.1119) loss: 0.8474 (0.8456) time: 0.1590 data: 0.0880 max mem: 8255 +Train: [65] [4200/6250] eta: 0:05:31 lr: 0.000036 grad: 0.1062 (0.1118) loss: 0.8386 (0.8456) time: 0.1336 data: 0.0683 max mem: 8255 +Train: [65] [4300/6250] eta: 0:05:14 lr: 0.000036 grad: 0.1051 (0.1118) loss: 0.8464 (0.8457) time: 0.1588 data: 0.0795 max mem: 8255 +Train: [65] [4400/6250] eta: 0:04:58 lr: 0.000036 grad: 0.1076 (0.1118) loss: 0.8514 (0.8457) time: 0.1733 data: 0.0682 max mem: 8255 +Train: [65] [4500/6250] eta: 0:04:41 lr: 0.000036 grad: 0.1069 (0.1117) loss: 0.8462 (0.8458) time: 0.1403 data: 0.0718 max mem: 8255 +Train: [65] [4600/6250] eta: 0:04:24 lr: 0.000036 grad: 0.1137 (0.1117) loss: 0.8496 (0.8458) time: 0.1367 data: 0.0589 max mem: 8255 +Train: [65] [4700/6250] eta: 0:04:07 lr: 0.000036 grad: 0.1047 (0.1118) loss: 0.8515 (0.8458) time: 0.1634 data: 0.0957 max mem: 8255 +Train: [65] [4800/6250] eta: 0:03:51 lr: 0.000036 grad: 0.1120 (0.1118) loss: 0.8490 (0.8458) time: 0.1697 data: 0.0953 max mem: 8255 +Train: [65] [4900/6250] eta: 0:03:35 lr: 0.000036 grad: 0.1078 (0.1117) loss: 0.8448 (0.8457) time: 0.1593 data: 0.0913 max mem: 8255 +Train: [65] [5000/6250] eta: 0:03:20 lr: 0.000036 grad: 0.1140 (0.1118) loss: 0.8448 (0.8457) time: 0.1796 data: 0.0888 max mem: 8255 +Train: [65] [5100/6250] eta: 0:03:04 lr: 0.000036 grad: 0.1050 (0.1118) loss: 0.8544 (0.8457) time: 0.1590 data: 0.0776 max mem: 8255 +Train: [65] [5200/6250] eta: 0:02:48 lr: 0.000036 grad: 0.1076 (0.1119) loss: 0.8353 (0.8456) time: 0.2470 data: 0.1432 max mem: 8255 +Train: [65] [5300/6250] eta: 0:02:32 lr: 0.000036 grad: 0.1106 (0.1119) loss: 0.8358 (0.8455) time: 0.1519 data: 0.0827 max mem: 8255 +Train: [65] [5400/6250] eta: 0:02:17 lr: 0.000036 grad: 0.1077 (0.1120) loss: 0.8470 (0.8453) time: 0.1864 data: 0.0817 max mem: 8255 +Train: [65] [5500/6250] eta: 0:02:00 lr: 0.000036 grad: 0.1052 (0.1119) loss: 0.8459 (0.8453) time: 0.1475 data: 0.0810 max mem: 8255 +Train: [65] [5600/6250] eta: 0:01:44 lr: 0.000036 grad: 0.1103 (0.1120) loss: 0.8450 (0.8452) time: 0.1218 data: 0.0319 max mem: 8255 +Train: [65] [5700/6250] eta: 0:01:28 lr: 0.000036 grad: 0.1125 (0.1120) loss: 0.8440 (0.8451) time: 0.1974 data: 0.1028 max mem: 8255 +Train: [65] [5800/6250] eta: 0:01:12 lr: 0.000036 grad: 0.1179 (0.1120) loss: 0.8374 (0.8450) time: 0.1515 data: 0.0751 max mem: 8255 +Train: [65] [5900/6250] eta: 0:00:56 lr: 0.000036 grad: 0.1077 (0.1120) loss: 0.8413 (0.8450) time: 0.1757 data: 0.0890 max mem: 8255 +Train: [65] [6000/6250] eta: 0:00:40 lr: 0.000036 grad: 0.1062 (0.1120) loss: 0.8449 (0.8450) time: 0.1312 data: 0.0367 max mem: 8255 +Train: [65] [6100/6250] eta: 0:00:24 lr: 0.000036 grad: 0.1037 (0.1120) loss: 0.8449 (0.8449) time: 0.2123 data: 0.1436 max mem: 8255 +Train: [65] [6200/6250] eta: 0:00:08 lr: 0.000036 grad: 0.1086 (0.1120) loss: 0.8443 (0.8449) time: 0.1310 data: 0.0499 max mem: 8255 +Train: [65] [6249/6250] eta: 0:00:00 lr: 0.000036 grad: 0.1091 (0.1120) loss: 0.8436 (0.8449) time: 0.1693 data: 0.1008 max mem: 8255 +Train: [65] Total time: 0:16:52 (0.1620 s / it) +Averaged stats: lr: 0.000036 grad: 0.1091 (0.1120) loss: 0.8436 (0.8449) +Eval (hcp-train-subset): [65] [ 0/62] eta: 0:05:42 loss: 0.8780 (0.8780) time: 5.5249 data: 5.4987 max mem: 8255 +Eval (hcp-train-subset): [65] [61/62] eta: 0:00:00 loss: 0.8674 (0.8683) time: 0.1118 data: 0.0903 max mem: 8255 +Eval (hcp-train-subset): [65] Total time: 0:00:13 (0.2150 s / it) +Averaged stats (hcp-train-subset): loss: 0.8674 (0.8683) +Eval (hcp-val): [65] [ 0/62] eta: 0:03:44 loss: 0.8717 (0.8717) time: 3.6131 data: 3.5428 max mem: 8255 +Eval (hcp-val): [65] [61/62] eta: 0:00:00 loss: 0.8762 (0.8767) time: 0.1085 data: 0.0877 max mem: 8255 +Eval (hcp-val): [65] Total time: 0:00:12 (0.2091 s / it) +Averaged stats (hcp-val): loss: 0.8762 (0.8767) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +Train: [66] [ 0/6250] eta: 10:41:23 lr: 0.000036 grad: 0.1916 (0.1916) loss: 0.8755 (0.8755) time: 6.1573 data: 6.0640 max mem: 8255 +Train: [66] [ 100/6250] eta: 0:20:29 lr: 0.000035 grad: 0.1238 (0.1495) loss: 0.8529 (0.8625) time: 0.1376 data: 0.0266 max mem: 8255 +Train: [66] [ 200/6250] eta: 0:17:40 lr: 0.000035 grad: 0.1217 (0.1344) loss: 0.8410 (0.8577) time: 0.1629 data: 0.0662 max mem: 8255 +Train: [66] [ 300/6250] eta: 0:16:52 lr: 0.000035 grad: 0.1118 (0.1288) loss: 0.8504 (0.8542) time: 0.1387 data: 0.0469 max mem: 8255 +Train: [66] [ 400/6250] eta: 0:16:25 lr: 0.000035 grad: 0.1111 (0.1254) loss: 0.8358 (0.8515) time: 0.1663 data: 0.0662 max mem: 8255 +Train: [66] [ 500/6250] eta: 0:15:56 lr: 0.000035 grad: 0.1134 (0.1223) loss: 0.8356 (0.8500) time: 0.1540 data: 0.0636 max mem: 8255 +Train: [66] [ 600/6250] eta: 0:15:31 lr: 0.000035 grad: 0.1092 (0.1205) loss: 0.8442 (0.8490) time: 0.1470 data: 0.0620 max mem: 8255 +Train: [66] [ 700/6250] eta: 0:15:07 lr: 0.000035 grad: 0.1113 (0.1194) loss: 0.8470 (0.8485) time: 0.1520 data: 0.0481 max mem: 8255 +Train: [66] [ 800/6250] eta: 0:14:53 lr: 0.000035 grad: 0.1045 (0.1186) loss: 0.8366 (0.8474) time: 0.1693 data: 0.0838 max mem: 8255 +Train: [66] [ 900/6250] eta: 0:14:33 lr: 0.000035 grad: 0.1117 (0.1178) loss: 0.8350 (0.8466) time: 0.1668 data: 0.0667 max mem: 8255 +Train: [66] [1000/6250] eta: 0:14:09 lr: 0.000035 grad: 0.1080 (0.1175) loss: 0.8501 (0.8462) time: 0.1316 data: 0.0595 max mem: 8255 +Train: [66] [1100/6250] eta: 0:13:54 lr: 0.000035 grad: 0.1092 (0.1169) loss: 0.8405 (0.8458) time: 0.1304 data: 0.0440 max mem: 8255 +Train: [66] [1200/6250] eta: 0:13:33 lr: 0.000035 grad: 0.1094 (0.1164) loss: 0.8412 (0.8452) time: 0.1557 data: 0.0873 max mem: 8255 +Train: [66] [1300/6250] eta: 0:13:16 lr: 0.000035 grad: 0.1214 (0.1162) loss: 0.8299 (0.8445) time: 0.1740 data: 0.0906 max mem: 8255 +Train: [66] [1400/6250] eta: 0:12:57 lr: 0.000035 grad: 0.1101 (0.1160) loss: 0.8438 (0.8439) time: 0.1556 data: 0.0751 max mem: 8255 +Train: [66] [1500/6250] eta: 0:12:38 lr: 0.000035 grad: 0.1097 (0.1159) loss: 0.8390 (0.8434) time: 0.1504 data: 0.0618 max mem: 8255 +Train: [66] [1600/6250] eta: 0:12:24 lr: 0.000035 grad: 0.1139 (0.1158) loss: 0.8314 (0.8429) time: 0.1671 data: 0.0713 max mem: 8255 +Train: [66] [1700/6250] eta: 0:12:03 lr: 0.000035 grad: 0.1158 (0.1158) loss: 0.8335 (0.8424) time: 0.1365 data: 0.0686 max mem: 8255 +Train: [66] [1800/6250] eta: 0:11:53 lr: 0.000035 grad: 0.1085 (0.1155) loss: 0.8367 (0.8422) time: 0.2266 data: 0.1424 max mem: 8255 +Train: [66] [1900/6250] eta: 0:11:38 lr: 0.000035 grad: 0.1102 (0.1155) loss: 0.8389 (0.8419) time: 0.1705 data: 0.0816 max mem: 8255 +Train: [66] [2000/6250] eta: 0:11:29 lr: 0.000035 grad: 0.1086 (0.1154) loss: 0.8357 (0.8416) time: 0.2862 data: 0.2114 max mem: 8255 +Train: [66] [2100/6250] eta: 0:11:11 lr: 0.000035 grad: 0.1092 (0.1152) loss: 0.8396 (0.8414) time: 0.1675 data: 0.0912 max mem: 8255 +Train: [66] [2200/6250] eta: 0:10:51 lr: 0.000035 grad: 0.1084 (0.1150) loss: 0.8318 (0.8412) time: 0.1388 data: 0.0569 max mem: 8255 +Train: [66] [2300/6250] eta: 0:10:35 lr: 0.000035 grad: 0.1110 (0.1148) loss: 0.8309 (0.8409) time: 0.1699 data: 0.0868 max mem: 8255 +Train: [66] [2400/6250] eta: 0:10:17 lr: 0.000035 grad: 0.1082 (0.1146) loss: 0.8394 (0.8409) time: 0.1200 data: 0.0410 max mem: 8255 +Train: [66] [2500/6250] eta: 0:09:58 lr: 0.000035 grad: 0.1130 (0.1146) loss: 0.8395 (0.8408) time: 0.1304 data: 0.0469 max mem: 8255 +Train: [66] [2600/6250] eta: 0:09:40 lr: 0.000035 grad: 0.1107 (0.1144) loss: 0.8400 (0.8408) time: 0.1341 data: 0.0464 max mem: 8255 +Train: [66] [2700/6250] eta: 0:09:23 lr: 0.000035 grad: 0.1047 (0.1143) loss: 0.8361 (0.8408) time: 0.1497 data: 0.0763 max mem: 8255 +Train: [66] [2800/6250] eta: 0:09:07 lr: 0.000035 grad: 0.1113 (0.1141) loss: 0.8463 (0.8409) time: 0.1646 data: 0.0877 max mem: 8255 +Train: [66] [2900/6250] eta: 0:08:53 lr: 0.000035 grad: 0.1100 (0.1140) loss: 0.8450 (0.8410) time: 0.1810 data: 0.0925 max mem: 8255 +Train: [66] [3000/6250] eta: 0:08:36 lr: 0.000035 grad: 0.1076 (0.1139) loss: 0.8411 (0.8411) time: 0.1594 data: 0.0788 max mem: 8255 +Train: [66] [3100/6250] eta: 0:08:19 lr: 0.000035 grad: 0.1115 (0.1138) loss: 0.8414 (0.8412) time: 0.1437 data: 0.0695 max mem: 8255 +Train: [66] [3200/6250] eta: 0:08:02 lr: 0.000035 grad: 0.1142 (0.1139) loss: 0.8434 (0.8412) time: 0.1461 data: 0.0689 max mem: 8255 +Train: [66] [3300/6250] eta: 0:07:46 lr: 0.000035 grad: 0.1124 (0.1139) loss: 0.8417 (0.8411) time: 0.1299 data: 0.0569 max mem: 8255 +Train: [66] [3400/6250] eta: 0:07:30 lr: 0.000035 grad: 0.1087 (0.1141) loss: 0.8392 (0.8410) time: 0.2153 data: 0.1190 max mem: 8255 +Train: [66] [3500/6250] eta: 0:07:15 lr: 0.000034 grad: 0.1082 (0.1140) loss: 0.8466 (0.8411) time: 0.1372 data: 0.0445 max mem: 8255 +Train: [66] [3600/6250] eta: 0:07:02 lr: 0.000034 grad: 0.1145 (0.1141) loss: 0.8386 (0.8410) time: 0.1297 data: 0.0535 max mem: 8255 +Train: [66] [3700/6250] eta: 0:06:48 lr: 0.000034 grad: 0.1155 (0.1142) loss: 0.8337 (0.8409) time: 0.1862 data: 0.1176 max mem: 8255 +Train: [66] [3800/6250] eta: 0:06:34 lr: 0.000034 grad: 0.1130 (0.1143) loss: 0.8387 (0.8408) time: 0.1544 data: 0.0692 max mem: 8255 +Train: [66] [3900/6250] eta: 0:06:18 lr: 0.000034 grad: 0.1153 (0.1144) loss: 0.8407 (0.8407) time: 0.1679 data: 0.0876 max mem: 8255 +Train: [66] [4000/6250] eta: 0:06:02 lr: 0.000034 grad: 0.1127 (0.1143) loss: 0.8405 (0.8408) time: 0.1260 data: 0.0489 max mem: 8255 +Train: [66] [4100/6250] eta: 0:05:46 lr: 0.000034 grad: 0.1105 (0.1142) loss: 0.8465 (0.8408) time: 0.1702 data: 0.0754 max mem: 8255 +Train: [66] [4200/6250] eta: 0:05:29 lr: 0.000034 grad: 0.1141 (0.1143) loss: 0.8424 (0.8408) time: 0.1404 data: 0.0575 max mem: 8255 +Train: [66] [4300/6250] eta: 0:05:12 lr: 0.000034 grad: 0.1172 (0.1143) loss: 0.8399 (0.8409) time: 0.1396 data: 0.0587 max mem: 8255 +Train: [66] [4400/6250] eta: 0:04:56 lr: 0.000034 grad: 0.1036 (0.1142) loss: 0.8386 (0.8410) time: 0.1419 data: 0.0585 max mem: 8255 +Train: [66] [4500/6250] eta: 0:04:39 lr: 0.000034 grad: 0.1115 (0.1142) loss: 0.8384 (0.8411) time: 0.1200 data: 0.0502 max mem: 8255 +Train: [66] [4600/6250] eta: 0:04:23 lr: 0.000034 grad: 0.1138 (0.1143) loss: 0.8460 (0.8411) time: 0.1156 data: 0.0406 max mem: 8255 +Train: [66] [4700/6250] eta: 0:04:07 lr: 0.000034 grad: 0.1177 (0.1143) loss: 0.8373 (0.8412) time: 0.1914 data: 0.1137 max mem: 8255 +Train: [66] [4800/6250] eta: 0:03:51 lr: 0.000034 grad: 0.1223 (0.1144) loss: 0.8376 (0.8411) time: 0.1697 data: 0.0898 max mem: 8255 +Train: [66] [4900/6250] eta: 0:03:35 lr: 0.000034 grad: 0.1211 (0.1145) loss: 0.8326 (0.8411) time: 0.1929 data: 0.1165 max mem: 8255 +Train: [66] [5000/6250] eta: 0:03:19 lr: 0.000034 grad: 0.1204 (0.1146) loss: 0.8359 (0.8410) time: 0.1953 data: 0.1148 max mem: 8255 +Train: [66] [5100/6250] eta: 0:03:04 lr: 0.000034 grad: 0.1167 (0.1147) loss: 0.8345 (0.8410) time: 0.1702 data: 0.1015 max mem: 8255 +Train: [66] [5200/6250] eta: 0:02:48 lr: 0.000034 grad: 0.1198 (0.1147) loss: 0.8325 (0.8409) time: 0.2245 data: 0.1394 max mem: 8255 +Train: [66] [5300/6250] eta: 0:02:33 lr: 0.000034 grad: 0.1094 (0.1148) loss: 0.8375 (0.8408) time: 0.1736 data: 0.0993 max mem: 8255 +Train: [66] [5400/6250] eta: 0:02:17 lr: 0.000034 grad: 0.1090 (0.1148) loss: 0.8383 (0.8407) time: 0.1715 data: 0.0628 max mem: 8255 +Train: [66] [5500/6250] eta: 0:02:01 lr: 0.000034 grad: 0.1112 (0.1149) loss: 0.8388 (0.8407) time: 0.1758 data: 0.0855 max mem: 8255 +Train: [66] [5600/6250] eta: 0:01:45 lr: 0.000034 grad: 0.1198 (0.1150) loss: 0.8324 (0.8407) time: 0.1584 data: 0.0661 max mem: 8255 +Train: [66] [5700/6250] eta: 0:01:29 lr: 0.000034 grad: 0.1163 (0.1151) loss: 0.8333 (0.8406) time: 0.1474 data: 0.0666 max mem: 8255 +Train: [66] [5800/6250] eta: 0:01:12 lr: 0.000034 grad: 0.1114 (0.1151) loss: 0.8364 (0.8405) time: 0.1388 data: 0.0612 max mem: 8255 +Train: [66] [5900/6250] eta: 0:00:56 lr: 0.000034 grad: 0.1131 (0.1151) loss: 0.8353 (0.8404) time: 0.1425 data: 0.0622 max mem: 8255 +Train: [66] [6000/6250] eta: 0:00:40 lr: 0.000034 grad: 0.1143 (0.1152) loss: 0.8340 (0.8403) time: 0.2225 data: 0.1203 max mem: 8255 +Train: [66] [6100/6250] eta: 0:00:24 lr: 0.000034 grad: 0.1181 (0.1152) loss: 0.8306 (0.8402) time: 0.1144 data: 0.0308 max mem: 8255 +Train: [66] [6200/6250] eta: 0:00:08 lr: 0.000034 grad: 0.1125 (0.1153) loss: 0.8382 (0.8401) time: 0.1710 data: 0.0734 max mem: 8255 +Train: [66] [6249/6250] eta: 0:00:00 lr: 0.000034 grad: 0.1082 (0.1153) loss: 0.8419 (0.8400) time: 0.2040 data: 0.0660 max mem: 8255 +Train: [66] Total time: 0:17:01 (0.1635 s / it) +Averaged stats: lr: 0.000034 grad: 0.1082 (0.1153) loss: 0.8419 (0.8400) +Eval (hcp-train-subset): [66] [ 0/62] eta: 0:04:13 loss: 0.8777 (0.8777) time: 4.0813 data: 3.9923 max mem: 8255 +Eval (hcp-train-subset): [66] [61/62] eta: 0:00:00 loss: 0.8625 (0.8641) time: 0.1148 data: 0.0943 max mem: 8255 +Eval (hcp-train-subset): [66] Total time: 0:00:14 (0.2381 s / it) +Averaged stats (hcp-train-subset): loss: 0.8625 (0.8641) +Eval (hcp-val): [66] [ 0/62] eta: 0:05:15 loss: 0.8723 (0.8723) time: 5.0918 data: 5.0656 max mem: 8255 +Eval (hcp-val): [66] [61/62] eta: 0:00:00 loss: 0.8737 (0.8759) time: 0.1176 data: 0.0963 max mem: 8255 +Eval (hcp-val): [66] Total time: 0:00:14 (0.2277 s / it) +Averaged stats (hcp-val): loss: 0.8737 (0.8759) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +Train: [67] [ 0/6250] eta: 7:38:33 lr: 0.000034 grad: 0.0755 (0.0755) loss: 0.8936 (0.8936) time: 4.4022 data: 4.0923 max mem: 8255 +Train: [67] [ 100/6250] eta: 0:21:35 lr: 0.000034 grad: 0.1498 (0.1624) loss: 0.8453 (0.8549) time: 0.1033 data: 0.0007 max mem: 8255 +Train: [67] [ 200/6250] eta: 0:18:36 lr: 0.000034 grad: 0.1300 (0.1506) loss: 0.8390 (0.8488) time: 0.1684 data: 0.0611 max mem: 8255 +Train: [67] [ 300/6250] eta: 0:17:22 lr: 0.000034 grad: 0.1191 (0.1415) loss: 0.8391 (0.8456) time: 0.1385 data: 0.0392 max mem: 8255 +Train: [67] [ 400/6250] eta: 0:16:32 lr: 0.000034 grad: 0.1263 (0.1368) loss: 0.8194 (0.8425) time: 0.1621 data: 0.0716 max mem: 8255 +Train: [67] [ 500/6250] eta: 0:15:53 lr: 0.000034 grad: 0.1149 (0.1330) loss: 0.8420 (0.8419) time: 0.1512 data: 0.0752 max mem: 8255 +Train: [67] [ 600/6250] eta: 0:15:19 lr: 0.000033 grad: 0.1180 (0.1310) loss: 0.8372 (0.8416) time: 0.1646 data: 0.0845 max mem: 8255 +Train: [67] [ 700/6250] eta: 0:14:58 lr: 0.000033 grad: 0.1098 (0.1289) loss: 0.8485 (0.8417) time: 0.1516 data: 0.0648 max mem: 8255 +Train: [67] [ 800/6250] eta: 0:14:53 lr: 0.000033 grad: 0.1085 (0.1271) loss: 0.8507 (0.8420) time: 0.2093 data: 0.1278 max mem: 8255 +Train: [67] [ 900/6250] eta: 0:14:47 lr: 0.000033 grad: 0.1115 (0.1257) loss: 0.8467 (0.8423) time: 0.1807 data: 0.0846 max mem: 8255 +Train: [67] [1000/6250] eta: 0:14:42 lr: 0.000033 grad: 0.1101 (0.1242) loss: 0.8442 (0.8428) time: 0.2411 data: 0.1389 max mem: 8255 +Train: [67] [1100/6250] eta: 0:14:35 lr: 0.000033 grad: 0.1078 (0.1229) loss: 0.8483 (0.8429) time: 0.2356 data: 0.1489 max mem: 8255 +Train: [67] [1200/6250] eta: 0:14:25 lr: 0.000033 grad: 0.1102 (0.1220) loss: 0.8358 (0.8430) time: 0.2909 data: 0.1896 max mem: 8255 +Train: [67] [1300/6250] eta: 0:13:55 lr: 0.000033 grad: 0.1135 (0.1215) loss: 0.8395 (0.8428) time: 0.1466 data: 0.0624 max mem: 8255 +Train: [67] [1400/6250] eta: 0:13:41 lr: 0.000033 grad: 0.1145 (0.1211) loss: 0.8411 (0.8427) time: 0.1886 data: 0.1062 max mem: 8255 +Train: [67] [1500/6250] eta: 0:13:27 lr: 0.000033 grad: 0.1082 (0.1207) loss: 0.8435 (0.8424) time: 0.2103 data: 0.1308 max mem: 8255 +Train: [67] [1600/6250] eta: 0:13:12 lr: 0.000033 grad: 0.1116 (0.1205) loss: 0.8466 (0.8423) time: 0.1753 data: 0.0890 max mem: 8255 +Train: [67] [1700/6250] eta: 0:12:51 lr: 0.000033 grad: 0.1099 (0.1202) loss: 0.8455 (0.8421) time: 0.1750 data: 0.0923 max mem: 8255 +Train: [67] [1800/6250] eta: 0:12:36 lr: 0.000033 grad: 0.1138 (0.1198) loss: 0.8325 (0.8419) time: 0.1307 data: 0.0240 max mem: 8255 +Train: [67] [1900/6250] eta: 0:12:19 lr: 0.000033 grad: 0.1103 (0.1194) loss: 0.8360 (0.8418) time: 0.1503 data: 0.0594 max mem: 8255 +Train: [67] [2000/6250] eta: 0:12:01 lr: 0.000033 grad: 0.1075 (0.1192) loss: 0.8421 (0.8415) time: 0.1671 data: 0.0998 max mem: 8255 +Train: [67] [2100/6250] eta: 0:11:45 lr: 0.000033 grad: 0.1113 (0.1190) loss: 0.8319 (0.8411) time: 0.1649 data: 0.0849 max mem: 8255 +Train: [67] [2200/6250] eta: 0:11:31 lr: 0.000033 grad: 0.1190 (0.1188) loss: 0.8421 (0.8409) time: 0.2428 data: 0.1587 max mem: 8255 +Train: [67] [2300/6250] eta: 0:11:11 lr: 0.000033 grad: 0.1179 (0.1187) loss: 0.8383 (0.8409) time: 0.1340 data: 0.0403 max mem: 8255 +Train: [67] [2400/6250] eta: 0:10:53 lr: 0.000033 grad: 0.1088 (0.1185) loss: 0.8473 (0.8408) time: 0.1792 data: 0.0991 max mem: 8255 +Train: [67] [2500/6250] eta: 0:10:33 lr: 0.000033 grad: 0.1218 (0.1183) loss: 0.8359 (0.8406) time: 0.1603 data: 0.0873 max mem: 8255 +Train: [67] [2600/6250] eta: 0:10:14 lr: 0.000033 grad: 0.1116 (0.1183) loss: 0.8419 (0.8405) time: 0.1360 data: 0.0620 max mem: 8255 +Train: [67] [2700/6250] eta: 0:09:56 lr: 0.000033 grad: 0.1176 (0.1182) loss: 0.8357 (0.8403) time: 0.1700 data: 0.0971 max mem: 8255 +Train: [67] [2800/6250] eta: 0:09:37 lr: 0.000033 grad: 0.1184 (0.1182) loss: 0.8420 (0.8401) time: 0.1637 data: 0.0988 max mem: 8255 +Train: [67] [2900/6250] eta: 0:09:17 lr: 0.000033 grad: 0.1065 (0.1180) loss: 0.8354 (0.8399) time: 0.1440 data: 0.0705 max mem: 8255 +Train: [67] [3000/6250] eta: 0:08:58 lr: 0.000033 grad: 0.1198 (0.1179) loss: 0.8395 (0.8398) time: 0.1421 data: 0.0610 max mem: 8255 +Train: [67] [3100/6250] eta: 0:08:39 lr: 0.000033 grad: 0.1144 (0.1177) loss: 0.8398 (0.8399) time: 0.1388 data: 0.0584 max mem: 8255 +Train: [67] [3200/6250] eta: 0:08:21 lr: 0.000033 grad: 0.1103 (0.1177) loss: 0.8360 (0.8398) time: 0.1513 data: 0.0790 max mem: 8255 +Train: [67] [3300/6250] eta: 0:08:03 lr: 0.000033 grad: 0.1145 (0.1176) loss: 0.8372 (0.8397) time: 0.1541 data: 0.0687 max mem: 8255 +Train: [67] [3400/6250] eta: 0:07:47 lr: 0.000033 grad: 0.1089 (0.1175) loss: 0.8407 (0.8397) time: 0.1673 data: 0.0928 max mem: 8255 +Train: [67] [3500/6250] eta: 0:07:31 lr: 0.000033 grad: 0.1157 (0.1175) loss: 0.8464 (0.8397) time: 0.2023 data: 0.1072 max mem: 8255 +Train: [67] [3600/6250] eta: 0:07:15 lr: 0.000033 grad: 0.1163 (0.1174) loss: 0.8338 (0.8397) time: 0.2227 data: 0.1468 max mem: 8255 +Train: [67] [3700/6250] eta: 0:06:58 lr: 0.000033 grad: 0.1130 (0.1175) loss: 0.8348 (0.8396) time: 0.1835 data: 0.1051 max mem: 8255 +Train: [67] [3800/6250] eta: 0:06:42 lr: 0.000033 grad: 0.1153 (0.1175) loss: 0.8390 (0.8395) time: 0.1846 data: 0.1037 max mem: 8255 +Train: [67] [3900/6250] eta: 0:06:25 lr: 0.000033 grad: 0.1107 (0.1176) loss: 0.8442 (0.8394) time: 0.1556 data: 0.0738 max mem: 8255 +Train: [67] [4000/6250] eta: 0:06:09 lr: 0.000032 grad: 0.1120 (0.1176) loss: 0.8351 (0.8393) time: 0.1887 data: 0.1186 max mem: 8255 +Train: [67] [4100/6250] eta: 0:05:53 lr: 0.000032 grad: 0.1180 (0.1176) loss: 0.8357 (0.8393) time: 0.1290 data: 0.0358 max mem: 8255 +Train: [67] [4200/6250] eta: 0:05:37 lr: 0.000032 grad: 0.1160 (0.1177) loss: 0.8354 (0.8392) time: 0.1846 data: 0.0997 max mem: 8255 +Train: [67] [4300/6250] eta: 0:05:22 lr: 0.000032 grad: 0.1143 (0.1178) loss: 0.8412 (0.8392) time: 0.1592 data: 0.0660 max mem: 8255 +Train: [67] [4400/6250] eta: 0:05:05 lr: 0.000032 grad: 0.1129 (0.1179) loss: 0.8418 (0.8391) time: 0.1764 data: 0.0955 max mem: 8255 +Train: [67] [4500/6250] eta: 0:04:48 lr: 0.000032 grad: 0.1120 (0.1179) loss: 0.8322 (0.8391) time: 0.1667 data: 0.0868 max mem: 8255 +Train: [67] [4600/6250] eta: 0:04:31 lr: 0.000032 grad: 0.1158 (0.1179) loss: 0.8384 (0.8391) time: 0.1437 data: 0.0776 max mem: 8255 +Train: [67] [4700/6250] eta: 0:04:14 lr: 0.000032 grad: 0.1186 (0.1179) loss: 0.8299 (0.8390) time: 0.1355 data: 0.0576 max mem: 8255 +Train: [67] [4800/6250] eta: 0:03:57 lr: 0.000032 grad: 0.1146 (0.1179) loss: 0.8471 (0.8390) time: 0.1323 data: 0.0570 max mem: 8255 +Train: [67] [4900/6250] eta: 0:03:40 lr: 0.000032 grad: 0.1111 (0.1179) loss: 0.8476 (0.8391) time: 0.1629 data: 0.0829 max mem: 8255 +Train: [67] [5000/6250] eta: 0:03:23 lr: 0.000032 grad: 0.1109 (0.1178) loss: 0.8422 (0.8391) time: 0.1495 data: 0.0806 max mem: 8255 +Train: [67] [5100/6250] eta: 0:03:07 lr: 0.000032 grad: 0.1131 (0.1178) loss: 0.8414 (0.8391) time: 0.1601 data: 0.0772 max mem: 8255 +Train: [67] [5200/6250] eta: 0:02:51 lr: 0.000032 grad: 0.1125 (0.1178) loss: 0.8435 (0.8392) time: 0.1515 data: 0.0610 max mem: 8255 +Train: [67] [5300/6250] eta: 0:02:35 lr: 0.000032 grad: 0.1164 (0.1177) loss: 0.8441 (0.8393) time: 0.2002 data: 0.1234 max mem: 8255 +Train: [67] [5400/6250] eta: 0:02:20 lr: 0.000032 grad: 0.1130 (0.1177) loss: 0.8386 (0.8393) time: 0.2374 data: 0.1650 max mem: 8255 +Train: [67] [5500/6250] eta: 0:02:04 lr: 0.000032 grad: 0.1174 (0.1177) loss: 0.8424 (0.8393) time: 0.1979 data: 0.1336 max mem: 8255 +Train: [67] [5600/6250] eta: 0:01:47 lr: 0.000032 grad: 0.1173 (0.1177) loss: 0.8371 (0.8394) time: 0.1896 data: 0.1095 max mem: 8255 +Train: [67] [5700/6250] eta: 0:01:31 lr: 0.000032 grad: 0.1157 (0.1177) loss: 0.8415 (0.8394) time: 0.1500 data: 0.0672 max mem: 8255 +Train: [67] [5800/6250] eta: 0:01:14 lr: 0.000032 grad: 0.1126 (0.1176) loss: 0.8487 (0.8395) time: 0.1436 data: 0.0428 max mem: 8255 +Train: [67] [5900/6250] eta: 0:00:58 lr: 0.000032 grad: 0.1133 (0.1176) loss: 0.8507 (0.8396) time: 0.2023 data: 0.1087 max mem: 8255 +Train: [67] [6000/6250] eta: 0:00:41 lr: 0.000032 grad: 0.1138 (0.1176) loss: 0.8391 (0.8396) time: 0.1793 data: 0.0985 max mem: 8255 +Train: [67] [6100/6250] eta: 0:00:25 lr: 0.000032 grad: 0.1133 (0.1176) loss: 0.8345 (0.8396) time: 0.1564 data: 0.0391 max mem: 8255 +Train: [67] [6200/6250] eta: 0:00:08 lr: 0.000032 grad: 0.1154 (0.1176) loss: 0.8382 (0.8396) time: 0.0805 data: 0.0002 max mem: 8255 +Train: [67] [6249/6250] eta: 0:00:00 lr: 0.000032 grad: 0.1159 (0.1175) loss: 0.8367 (0.8396) time: 0.1378 data: 0.0561 max mem: 8255 +Train: [67] Total time: 0:17:35 (0.1689 s / it) +Averaged stats: lr: 0.000032 grad: 0.1159 (0.1175) loss: 0.8367 (0.8396) +Eval (hcp-train-subset): [67] [ 0/62] eta: 0:03:58 loss: 0.8719 (0.8719) time: 3.8406 data: 3.7515 max mem: 8255 +Eval (hcp-train-subset): [67] [61/62] eta: 0:00:00 loss: 0.8646 (0.8650) time: 0.0984 data: 0.0778 max mem: 8255 +Eval (hcp-train-subset): [67] Total time: 0:00:16 (0.2588 s / it) +Averaged stats (hcp-train-subset): loss: 0.8646 (0.8650) +Eval (hcp-val): [67] [ 0/62] eta: 0:05:56 loss: 0.8734 (0.8734) time: 5.7477 data: 5.7204 max mem: 8255 +Eval (hcp-val): [67] [61/62] eta: 0:00:00 loss: 0.8741 (0.8756) time: 0.1292 data: 0.1083 max mem: 8255 +Eval (hcp-val): [67] Total time: 0:00:13 (0.2189 s / it) +Averaged stats (hcp-val): loss: 0.8741 (0.8756) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +Train: [68] [ 0/6250] eta: 8:08:05 lr: 0.000032 grad: nan (nan) loss: 0.8100 (0.8100) time: 4.6856 data: 4.4501 max mem: 8255 +Train: [68] [ 100/6250] eta: 0:23:52 lr: 0.000032 grad: 0.1413 (0.1774) loss: 0.8469 (0.8456) time: 0.1947 data: 0.0905 max mem: 8255 +Train: [68] [ 200/6250] eta: 0:19:30 lr: 0.000032 grad: 0.1269 (0.1544) loss: 0.8321 (0.8422) time: 0.1931 data: 0.1013 max mem: 8255 +Train: [68] [ 300/6250] eta: 0:18:01 lr: 0.000032 grad: 0.1395 (0.1487) loss: 0.8459 (0.8413) time: 0.1783 data: 0.0527 max mem: 8255 +Train: [68] [ 400/6250] eta: 0:17:00 lr: 0.000032 grad: 0.1284 (0.1449) loss: 0.8460 (0.8406) time: 0.1431 data: 0.0566 max mem: 8255 +Train: [68] [ 500/6250] eta: 0:16:19 lr: 0.000032 grad: 0.1388 (0.1431) loss: 0.8416 (0.8404) time: 0.1440 data: 0.0600 max mem: 8255 +Train: [68] [ 600/6250] eta: 0:15:27 lr: 0.000032 grad: 0.1185 (0.1404) loss: 0.8381 (0.8407) time: 0.1292 data: 0.0607 max mem: 8255 +Train: [68] [ 700/6250] eta: 0:14:39 lr: 0.000032 grad: 0.1099 (0.1372) loss: 0.8467 (0.8414) time: 0.1219 data: 0.0455 max mem: 8255 +Train: [68] [ 800/6250] eta: 0:14:16 lr: 0.000032 grad: 0.1145 (0.1344) loss: 0.8481 (0.8421) time: 0.2081 data: 0.1303 max mem: 8255 +Train: [68] [ 900/6250] eta: 0:13:57 lr: 0.000032 grad: 0.1101 (0.1321) loss: 0.8473 (0.8425) time: 0.1440 data: 0.0679 max mem: 8255 +Train: [68] [1000/6250] eta: 0:13:53 lr: 0.000032 grad: 0.1070 (0.1302) loss: 0.8452 (0.8429) time: 0.2073 data: 0.1268 max mem: 8255 +Train: [68] [1100/6250] eta: 0:13:37 lr: 0.000032 grad: 0.1155 (0.1290) loss: 0.8454 (0.8430) time: 0.1428 data: 0.0590 max mem: 8255 +Train: [68] [1200/6250] eta: 0:13:26 lr: 0.000032 grad: 0.1086 (0.1276) loss: 0.8442 (0.8433) time: 0.1234 data: 0.0228 max mem: 8255 +Train: [68] [1300/6250] eta: 0:13:23 lr: 0.000031 grad: 0.1178 (0.1267) loss: 0.8475 (0.8432) time: 0.2556 data: 0.1798 max mem: 8255 +Train: [68] [1400/6250] eta: 0:12:59 lr: 0.000031 grad: 0.1097 (0.1258) loss: 0.8504 (0.8432) time: 0.1583 data: 0.0806 max mem: 8255 +Train: [68] [1500/6250] eta: 0:12:54 lr: 0.000031 grad: 0.1111 (0.1250) loss: 0.8451 (0.8432) time: 0.1183 data: 0.0003 max mem: 8255 +Train: [68] [1600/6250] eta: 0:12:30 lr: 0.000031 grad: 0.1145 (0.1244) loss: 0.8445 (0.8432) time: 0.1430 data: 0.0649 max mem: 8255 +Train: [68] [1700/6250] eta: 0:12:11 lr: 0.000031 grad: 0.1156 (0.1239) loss: 0.8445 (0.8430) time: 0.1648 data: 0.0845 max mem: 8255 +Train: [68] [1800/6250] eta: 0:11:51 lr: 0.000031 grad: 0.1114 (0.1235) loss: 0.8384 (0.8429) time: 0.1351 data: 0.0620 max mem: 8255 +Train: [68] [1900/6250] eta: 0:11:33 lr: 0.000031 grad: 0.1135 (0.1230) loss: 0.8357 (0.8427) time: 0.1438 data: 0.0653 max mem: 8255 +Train: [68] [2000/6250] eta: 0:11:21 lr: 0.000031 grad: 0.1126 (0.1227) loss: 0.8418 (0.8427) time: 0.1174 data: 0.0113 max mem: 8255 +Train: [68] [2100/6250] eta: 0:11:08 lr: 0.000031 grad: 0.1104 (0.1222) loss: 0.8481 (0.8427) time: 0.1688 data: 0.0914 max mem: 8255 +Train: [68] [2200/6250] eta: 0:10:52 lr: 0.000031 grad: 0.1108 (0.1219) loss: 0.8482 (0.8427) time: 0.1837 data: 0.1024 max mem: 8255 +Train: [68] [2300/6250] eta: 0:10:35 lr: 0.000031 grad: 0.1123 (0.1217) loss: 0.8421 (0.8426) time: 0.1568 data: 0.0802 max mem: 8255 +Train: [68] [2400/6250] eta: 0:10:18 lr: 0.000031 grad: 0.1113 (0.1216) loss: 0.8365 (0.8426) time: 0.1546 data: 0.0778 max mem: 8255 +Train: [68] [2500/6250] eta: 0:10:03 lr: 0.000031 grad: 0.1190 (0.1215) loss: 0.8408 (0.8425) time: 0.1789 data: 0.1048 max mem: 8255 +Train: [68] [2600/6250] eta: 0:09:46 lr: 0.000031 grad: 0.1079 (0.1212) loss: 0.8419 (0.8424) time: 0.1587 data: 0.0796 max mem: 8255 +Train: [68] [2700/6250] eta: 0:09:28 lr: 0.000031 grad: 0.1147 (0.1210) loss: 0.8441 (0.8423) time: 0.1498 data: 0.0732 max mem: 8255 +Train: [68] [2800/6250] eta: 0:09:13 lr: 0.000031 grad: 0.1145 (0.1208) loss: 0.8455 (0.8423) time: 0.1228 data: 0.0428 max mem: 8255 +Train: [68] [2900/6250] eta: 0:08:55 lr: 0.000031 grad: 0.1084 (0.1206) loss: 0.8390 (0.8422) time: 0.1221 data: 0.0416 max mem: 8255 +Train: [68] [3000/6250] eta: 0:08:37 lr: 0.000031 grad: 0.1169 (0.1205) loss: 0.8381 (0.8420) time: 0.1467 data: 0.0693 max mem: 8255 +Train: [68] [3100/6250] eta: 0:08:19 lr: 0.000031 grad: 0.1232 (0.1204) loss: 0.8401 (0.8418) time: 0.1531 data: 0.0805 max mem: 8255 +Train: [68] [3200/6250] eta: 0:08:02 lr: 0.000031 grad: 0.1111 (0.1202) loss: 0.8358 (0.8417) time: 0.1495 data: 0.0724 max mem: 8255 +Train: [68] [3300/6250] eta: 0:07:45 lr: 0.000031 grad: 0.1170 (0.1201) loss: 0.8405 (0.8416) time: 0.1420 data: 0.0736 max mem: 8255 +Train: [68] [3400/6250] eta: 0:07:29 lr: 0.000031 grad: 0.1115 (0.1200) loss: 0.8423 (0.8415) time: 0.1689 data: 0.1010 max mem: 8255 +Train: [68] [3500/6250] eta: 0:07:11 lr: 0.000031 grad: 0.1138 (0.1198) loss: 0.8394 (0.8415) time: 0.1371 data: 0.0591 max mem: 8255 +Train: [68] [3600/6250] eta: 0:06:55 lr: 0.000031 grad: 0.1102 (0.1197) loss: 0.8355 (0.8413) time: 0.1476 data: 0.0722 max mem: 8255 +Train: [68] [3700/6250] eta: 0:06:39 lr: 0.000031 grad: 0.1110 (0.1195) loss: 0.8415 (0.8413) time: 0.1299 data: 0.0519 max mem: 8255 +Train: [68] [3800/6250] eta: 0:06:23 lr: 0.000031 grad: 0.1159 (0.1196) loss: 0.8319 (0.8413) time: 0.2039 data: 0.1146 max mem: 8255 +Train: [68] [3900/6250] eta: 0:06:10 lr: 0.000031 grad: 0.1129 (0.1195) loss: 0.8363 (0.8412) time: 0.1790 data: 0.0532 max mem: 8255 +Train: [68] [4000/6250] eta: 0:05:56 lr: 0.000031 grad: 0.1111 (0.1195) loss: 0.8419 (0.8411) time: 0.1574 data: 0.0786 max mem: 8255 +Train: [68] [4100/6250] eta: 0:05:41 lr: 0.000031 grad: 0.1135 (0.1194) loss: 0.8395 (0.8410) time: 0.1391 data: 0.0642 max mem: 8255 +Train: [68] [4200/6250] eta: 0:05:25 lr: 0.000031 grad: 0.1175 (0.1193) loss: 0.8290 (0.8410) time: 0.1517 data: 0.0758 max mem: 8255 +Train: [68] [4300/6250] eta: 0:05:11 lr: 0.000031 grad: 0.1107 (0.1193) loss: 0.8440 (0.8409) time: 0.1890 data: 0.0915 max mem: 8255 +Train: [68] [4400/6250] eta: 0:04:55 lr: 0.000031 grad: 0.1114 (0.1193) loss: 0.8433 (0.8410) time: 0.1253 data: 0.0495 max mem: 8255 +Train: [68] [4500/6250] eta: 0:04:39 lr: 0.000031 grad: 0.1096 (0.1192) loss: 0.8443 (0.8410) time: 0.1772 data: 0.0804 max mem: 8255 +Train: [68] [4600/6250] eta: 0:04:24 lr: 0.000031 grad: 0.1227 (0.1192) loss: 0.8428 (0.8410) time: 0.1800 data: 0.1024 max mem: 8255 +Train: [68] [4700/6250] eta: 0:04:07 lr: 0.000031 grad: 0.1173 (0.1192) loss: 0.8392 (0.8410) time: 0.1711 data: 0.1010 max mem: 8255 +Train: [68] [4800/6250] eta: 0:03:51 lr: 0.000030 grad: 0.1171 (0.1192) loss: 0.8335 (0.8410) time: 0.1835 data: 0.1073 max mem: 8255 +Train: [68] [4900/6250] eta: 0:03:35 lr: 0.000030 grad: 0.1070 (0.1192) loss: 0.8432 (0.8409) time: 0.1647 data: 0.0940 max mem: 8255 +Train: [68] [5000/6250] eta: 0:03:19 lr: 0.000030 grad: 0.1145 (0.1192) loss: 0.8402 (0.8409) time: 0.1739 data: 0.1014 max mem: 8255 +Train: [68] [5100/6250] eta: 0:03:02 lr: 0.000030 grad: 0.1139 (0.1191) loss: 0.8492 (0.8410) time: 0.1365 data: 0.0573 max mem: 8255 +Train: [68] [5200/6250] eta: 0:02:46 lr: 0.000030 grad: 0.1157 (0.1192) loss: 0.8335 (0.8409) time: 0.1683 data: 0.0979 max mem: 8255 +Train: [68] [5300/6250] eta: 0:02:30 lr: 0.000030 grad: 0.1112 (0.1191) loss: 0.8442 (0.8409) time: 0.1468 data: 0.0623 max mem: 8255 +Train: [68] [5400/6250] eta: 0:02:14 lr: 0.000030 grad: 0.1181 (0.1191) loss: 0.8357 (0.8409) time: 0.1718 data: 0.0890 max mem: 8255 +Train: [68] [5500/6250] eta: 0:01:59 lr: 0.000030 grad: 0.1203 (0.1191) loss: 0.8429 (0.8408) time: 0.1552 data: 0.0617 max mem: 8255 +Train: [68] [5600/6250] eta: 0:01:43 lr: 0.000030 grad: 0.1201 (0.1192) loss: 0.8362 (0.8407) time: 0.1976 data: 0.1173 max mem: 8255 +Train: [68] [5700/6250] eta: 0:01:27 lr: 0.000030 grad: 0.1138 (0.1192) loss: 0.8386 (0.8406) time: 0.1802 data: 0.1024 max mem: 8255 +Train: [68] [5800/6250] eta: 0:01:12 lr: 0.000030 grad: 0.1166 (0.1193) loss: 0.8396 (0.8405) time: 0.1261 data: 0.0443 max mem: 8255 +Train: [68] [5900/6250] eta: 0:00:56 lr: 0.000030 grad: 0.1186 (0.1194) loss: 0.8351 (0.8404) time: 0.2892 data: 0.1896 max mem: 8255 +Train: [68] [6000/6250] eta: 0:00:40 lr: 0.000030 grad: 0.1186 (0.1194) loss: 0.8282 (0.8403) time: 0.1628 data: 0.0859 max mem: 8255 +Train: [68] [6100/6250] eta: 0:00:24 lr: 0.000030 grad: 0.1131 (0.1194) loss: 0.8400 (0.8402) time: 0.2101 data: 0.1273 max mem: 8255 +Train: [68] [6200/6250] eta: 0:00:08 lr: 0.000030 grad: 0.1186 (0.1195) loss: 0.8274 (0.8401) time: 0.1505 data: 0.0772 max mem: 8255 +Train: [68] [6249/6250] eta: 0:00:00 lr: 0.000030 grad: 0.1221 (0.1195) loss: 0.8376 (0.8401) time: 0.2510 data: 0.1421 max mem: 8255 +Train: [68] Total time: 0:16:59 (0.1631 s / it) +Averaged stats: lr: 0.000030 grad: 0.1221 (0.1195) loss: 0.8376 (0.8401) +Eval (hcp-train-subset): [68] [ 0/62] eta: 0:05:46 loss: 0.8647 (0.8647) time: 5.5893 data: 5.5595 max mem: 8255 +Eval (hcp-train-subset): [68] [61/62] eta: 0:00:00 loss: 0.8586 (0.8638) time: 0.0982 data: 0.0776 max mem: 8255 +Eval (hcp-train-subset): [68] Total time: 0:00:15 (0.2520 s / it) +Averaged stats (hcp-train-subset): loss: 0.8586 (0.8638) +Eval (hcp-val): [68] [ 0/62] eta: 0:06:04 loss: 0.8746 (0.8746) time: 5.8850 data: 5.8561 max mem: 8255 +Eval (hcp-val): [68] [61/62] eta: 0:00:00 loss: 0.8740 (0.8755) time: 0.1315 data: 0.1109 max mem: 8255 +Eval (hcp-val): [68] Total time: 0:00:14 (0.2383 s / it) +Averaged stats (hcp-val): loss: 0.8740 (0.8755) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +Train: [69] [ 0/6250] eta: 12:22:19 lr: 0.000030 grad: 0.1195 (0.1195) loss: 0.8740 (0.8740) time: 7.1263 data: 7.0291 max mem: 8255 +Train: [69] [ 100/6250] eta: 0:23:51 lr: 0.000030 grad: 0.1147 (0.1372) loss: 0.8630 (0.8686) time: 0.1726 data: 0.0723 max mem: 8255 +Train: [69] [ 200/6250] eta: 0:22:35 lr: 0.000030 grad: 0.1043 (0.1280) loss: 0.8611 (0.8655) time: 0.2510 data: 0.1046 max mem: 8255 +Train: [69] [ 300/6250] eta: 0:20:23 lr: 0.000030 grad: 0.1095 (0.1229) loss: 0.8707 (0.8642) time: 0.2178 data: 0.1102 max mem: 8255 +Train: [69] [ 400/6250] eta: 0:18:51 lr: 0.000030 grad: 0.1101 (0.1203) loss: 0.8597 (0.8636) time: 0.1475 data: 0.0609 max mem: 8255 +Train: [69] [ 500/6250] eta: 0:17:59 lr: 0.000030 grad: 0.1106 (0.1194) loss: 0.8439 (0.8614) time: 0.1429 data: 0.0516 max mem: 8255 +Train: [69] [ 600/6250] eta: 0:17:21 lr: 0.000030 grad: 0.1114 (0.1191) loss: 0.8483 (0.8593) time: 0.1315 data: 0.0389 max mem: 8255 +Train: [69] [ 700/6250] eta: 0:16:51 lr: 0.000030 grad: 0.1184 (0.1188) loss: 0.8391 (0.8576) time: 0.2094 data: 0.1251 max mem: 8255 +Train: [69] [ 800/6250] eta: 0:16:16 lr: 0.000030 grad: 0.1157 (0.1190) loss: 0.8452 (0.8557) time: 0.1801 data: 0.0917 max mem: 8255 +Train: [69] [ 900/6250] eta: 0:16:24 lr: 0.000030 grad: 0.1166 (0.1191) loss: 0.8420 (0.8541) time: 0.2239 data: 0.1386 max mem: 8255 +Train: [69] [1000/6250] eta: 0:16:10 lr: 0.000030 grad: 0.1292 (0.1193) loss: 0.8386 (0.8527) time: 0.0959 data: 0.0056 max mem: 8255 +Train: [69] [1100/6250] eta: 0:15:41 lr: 0.000030 grad: 0.1102 (0.1191) loss: 0.8505 (0.8518) time: 0.1810 data: 0.1027 max mem: 8255 +Train: [69] [1200/6250] eta: 0:15:22 lr: 0.000030 grad: 0.1126 (0.1188) loss: 0.8434 (0.8510) time: 0.1814 data: 0.0846 max mem: 8255 +Train: [69] [1300/6250] eta: 0:14:56 lr: 0.000030 grad: 0.1108 (0.1185) loss: 0.8389 (0.8503) time: 0.1535 data: 0.0634 max mem: 8255 +Train: [69] [1400/6250] eta: 0:15:01 lr: 0.000030 grad: 0.1166 (0.1182) loss: 0.8434 (0.8497) time: 0.4549 data: 0.3454 max mem: 8255 +Train: [69] [1500/6250] eta: 0:14:37 lr: 0.000030 grad: 0.1159 (0.1181) loss: 0.8339 (0.8491) time: 0.1120 data: 0.0005 max mem: 8255 +Train: [69] [1600/6250] eta: 0:14:26 lr: 0.000030 grad: 0.1152 (0.1181) loss: 0.8282 (0.8484) time: 0.1795 data: 0.0878 max mem: 8255 +Train: [69] [1700/6250] eta: 0:14:12 lr: 0.000030 grad: 0.1125 (0.1180) loss: 0.8428 (0.8479) time: 0.3791 data: 0.2856 max mem: 8255 +Train: [69] [1800/6250] eta: 0:13:40 lr: 0.000030 grad: 0.1140 (0.1179) loss: 0.8390 (0.8474) time: 0.1601 data: 0.0737 max mem: 8255 +Train: [69] [1900/6250] eta: 0:13:19 lr: 0.000030 grad: 0.1122 (0.1177) loss: 0.8441 (0.8470) time: 0.1953 data: 0.1206 max mem: 8255 +Train: [69] [2000/6250] eta: 0:13:10 lr: 0.000030 grad: 0.1165 (0.1176) loss: 0.8376 (0.8467) time: 0.1292 data: 0.0102 max mem: 8255 +Train: [69] [2100/6250] eta: 0:12:44 lr: 0.000029 grad: 0.1080 (0.1176) loss: 0.8452 (0.8465) time: 0.1531 data: 0.0770 max mem: 8255 +Train: [69] [2200/6250] eta: 0:12:22 lr: 0.000029 grad: 0.1171 (0.1175) loss: 0.8443 (0.8463) time: 0.1303 data: 0.0453 max mem: 8255 +Train: [69] [2300/6250] eta: 0:11:59 lr: 0.000029 grad: 0.1176 (0.1177) loss: 0.8453 (0.8461) time: 0.1415 data: 0.0550 max mem: 8255 +Train: [69] [2400/6250] eta: 0:11:36 lr: 0.000029 grad: 0.1182 (0.1177) loss: 0.8325 (0.8459) time: 0.1537 data: 0.0722 max mem: 8255 +Train: [69] [2500/6250] eta: 0:11:15 lr: 0.000029 grad: 0.1150 (0.1178) loss: 0.8416 (0.8456) time: 0.1496 data: 0.0716 max mem: 8255 +Train: [69] [2600/6250] eta: 0:10:56 lr: 0.000029 grad: 0.1165 (0.1180) loss: 0.8400 (0.8454) time: 0.1533 data: 0.0698 max mem: 8255 +Train: [69] [2700/6250] eta: 0:10:35 lr: 0.000029 grad: 0.1089 (0.1179) loss: 0.8431 (0.8452) time: 0.1259 data: 0.0494 max mem: 8255 +Train: [69] [2800/6250] eta: 0:10:14 lr: 0.000029 grad: 0.1094 (0.1178) loss: 0.8471 (0.8450) time: 0.1650 data: 0.0932 max mem: 8255 +Train: [69] [2900/6250] eta: 0:09:53 lr: 0.000029 grad: 0.1165 (0.1178) loss: 0.8309 (0.8449) time: 0.1671 data: 0.0939 max mem: 8255 +Train: [69] [3000/6250] eta: 0:09:32 lr: 0.000029 grad: 0.1153 (0.1178) loss: 0.8412 (0.8447) time: 0.1426 data: 0.0751 max mem: 8255 +Train: [69] [3100/6250] eta: 0:09:14 lr: 0.000029 grad: 0.1199 (0.1179) loss: 0.8360 (0.8446) time: 0.1747 data: 0.0886 max mem: 8255 +Train: [69] [3200/6250] eta: 0:08:55 lr: 0.000029 grad: 0.1223 (0.1180) loss: 0.8408 (0.8445) time: 0.1422 data: 0.0717 max mem: 8255 +Train: [69] [3300/6250] eta: 0:08:36 lr: 0.000029 grad: 0.1224 (0.1182) loss: 0.8372 (0.8444) time: 0.1430 data: 0.0572 max mem: 8255 +Train: [69] [3400/6250] eta: 0:08:16 lr: 0.000029 grad: 0.1199 (0.1183) loss: 0.8387 (0.8442) time: 0.1580 data: 0.0851 max mem: 8255 +Train: [69] [3500/6250] eta: 0:07:57 lr: 0.000029 grad: 0.1164 (0.1183) loss: 0.8360 (0.8441) time: 0.1510 data: 0.0710 max mem: 8255 +Train: [69] [3600/6250] eta: 0:07:38 lr: 0.000029 grad: 0.1180 (0.1184) loss: 0.8410 (0.8441) time: 0.1504 data: 0.0783 max mem: 8255 +Train: [69] [3700/6250] eta: 0:07:19 lr: 0.000029 grad: 0.1167 (0.1183) loss: 0.8339 (0.8440) time: 0.1589 data: 0.0888 max mem: 8255 +Train: [69] [3800/6250] eta: 0:07:00 lr: 0.000029 grad: 0.1157 (0.1183) loss: 0.8396 (0.8439) time: 0.1576 data: 0.0757 max mem: 8255 +Train: [69] [3900/6250] eta: 0:06:42 lr: 0.000029 grad: 0.1169 (0.1183) loss: 0.8414 (0.8439) time: 0.1585 data: 0.0747 max mem: 8255 +Train: [69] [4000/6250] eta: 0:06:24 lr: 0.000029 grad: 0.1175 (0.1183) loss: 0.8437 (0.8439) time: 0.1700 data: 0.0923 max mem: 8255 +Train: [69] [4100/6250] eta: 0:06:13 lr: 0.000029 grad: 0.1169 (0.1184) loss: 0.8428 (0.8439) time: 0.6361 data: 0.5631 max mem: 8255 +Train: [69] [4200/6250] eta: 0:05:54 lr: 0.000029 grad: 0.1198 (0.1184) loss: 0.8382 (0.8438) time: 0.1921 data: 0.1087 max mem: 8255 +Train: [69] [4300/6250] eta: 0:05:39 lr: 0.000029 grad: 0.1137 (0.1184) loss: 0.8379 (0.8438) time: 0.1999 data: 0.1328 max mem: 8255 +Train: [69] [4400/6250] eta: 0:05:22 lr: 0.000029 grad: 0.1117 (0.1183) loss: 0.8441 (0.8438) time: 0.1764 data: 0.0863 max mem: 8255 +Train: [69] [4500/6250] eta: 0:05:04 lr: 0.000029 grad: 0.1091 (0.1183) loss: 0.8462 (0.8437) time: 0.1738 data: 0.0964 max mem: 8255 +Train: [69] [4600/6250] eta: 0:04:47 lr: 0.000029 grad: 0.1171 (0.1183) loss: 0.8480 (0.8437) time: 0.1276 data: 0.0291 max mem: 8255 +Train: [69] [4700/6250] eta: 0:04:29 lr: 0.000029 grad: 0.1183 (0.1183) loss: 0.8335 (0.8437) time: 0.1736 data: 0.0823 max mem: 8255 +Train: [69] [4800/6250] eta: 0:04:12 lr: 0.000029 grad: 0.1173 (0.1183) loss: 0.8413 (0.8436) time: 0.1935 data: 0.1179 max mem: 8255 +Train: [69] [4900/6250] eta: 0:03:54 lr: 0.000029 grad: 0.1149 (0.1183) loss: 0.8420 (0.8436) time: 0.1477 data: 0.0679 max mem: 8255 +Train: [69] [5000/6250] eta: 0:03:36 lr: 0.000029 grad: 0.1102 (0.1182) loss: 0.8426 (0.8436) time: 0.1302 data: 0.0498 max mem: 8255 +Train: [69] [5100/6250] eta: 0:03:18 lr: 0.000029 grad: 0.1173 (0.1182) loss: 0.8405 (0.8436) time: 0.1461 data: 0.0644 max mem: 8255 +Train: [69] [5200/6250] eta: 0:03:00 lr: 0.000029 grad: 0.1155 (0.1182) loss: 0.8436 (0.8435) time: 0.1460 data: 0.0749 max mem: 8255 +Train: [69] [5300/6250] eta: 0:02:43 lr: 0.000029 grad: 0.1181 (0.1182) loss: 0.8376 (0.8434) time: 0.1344 data: 0.0658 max mem: 8255 +Train: [69] [5400/6250] eta: 0:02:25 lr: 0.000029 grad: 0.1146 (0.1182) loss: 0.8431 (0.8434) time: 0.1425 data: 0.0587 max mem: 8255 +Train: [69] [5500/6250] eta: 0:02:08 lr: 0.000029 grad: 0.1182 (0.1182) loss: 0.8456 (0.8433) time: 0.1604 data: 0.0787 max mem: 8255 +Train: [69] [5600/6250] eta: 0:01:51 lr: 0.000028 grad: 0.1199 (0.1182) loss: 0.8374 (0.8433) time: 0.1646 data: 0.0917 max mem: 8255 +Train: [69] [5700/6250] eta: 0:01:33 lr: 0.000028 grad: 0.1096 (0.1182) loss: 0.8389 (0.8432) time: 0.1271 data: 0.0515 max mem: 8255 +Train: [69] [5800/6250] eta: 0:01:16 lr: 0.000028 grad: 0.1194 (0.1183) loss: 0.8503 (0.8432) time: 0.1373 data: 0.0584 max mem: 8255 +Train: [69] [5900/6250] eta: 0:00:59 lr: 0.000028 grad: 0.1180 (0.1183) loss: 0.8373 (0.8432) time: 0.1916 data: 0.1258 max mem: 8255 +Train: [69] [6000/6250] eta: 0:00:42 lr: 0.000028 grad: 0.1173 (0.1184) loss: 0.8439 (0.8431) time: 0.1953 data: 0.1029 max mem: 8255 +Train: [69] [6100/6250] eta: 0:00:25 lr: 0.000028 grad: 0.1147 (0.1185) loss: 0.8478 (0.8431) time: 0.1699 data: 0.0752 max mem: 8255 +Train: [69] [6200/6250] eta: 0:00:08 lr: 0.000028 grad: 0.1127 (0.1185) loss: 0.8397 (0.8430) time: 0.1672 data: 0.0893 max mem: 8255 +Train: [69] [6249/6250] eta: 0:00:00 lr: 0.000028 grad: 0.1157 (0.1185) loss: 0.8449 (0.8430) time: 0.3005 data: 0.1924 max mem: 8255 +Train: [69] Total time: 0:17:59 (0.1728 s / it) +Averaged stats: lr: 0.000028 grad: 0.1157 (0.1185) loss: 0.8449 (0.8430) +Eval (hcp-train-subset): [69] [ 0/62] eta: 0:05:53 loss: 0.8740 (0.8740) time: 5.6948 data: 5.6668 max mem: 8255 +Eval (hcp-train-subset): [69] [61/62] eta: 0:00:00 loss: 0.8624 (0.8645) time: 0.1278 data: 0.1057 max mem: 8255 +Eval (hcp-train-subset): [69] Total time: 0:00:16 (0.2603 s / it) +Averaged stats (hcp-train-subset): loss: 0.8624 (0.8645) +Making plots (hcp-train-subset): example=47 +Eval (hcp-val): [69] [ 0/62] eta: 0:04:49 loss: 0.8709 (0.8709) time: 4.6623 data: 4.5581 max mem: 8255 +Eval (hcp-val): [69] [61/62] eta: 0:00:00 loss: 0.8736 (0.8758) time: 0.1629 data: 0.1405 max mem: 8255 +Eval (hcp-val): [69] Total time: 0:00:15 (0.2516 s / it) +Averaged stats (hcp-val): loss: 0.8736 (0.8758) +Making plots (hcp-val): example=54 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +Train: [70] [ 0/6250] eta: 11:02:05 lr: 0.000028 grad: 0.0835 (0.0835) loss: 0.9004 (0.9004) time: 6.3561 data: 6.1607 max mem: 8255 +Train: [70] [ 100/6250] eta: 0:25:18 lr: 0.000028 grad: 0.1236 (0.1721) loss: 0.8447 (0.8462) time: 0.1889 data: 0.0947 max mem: 8255 +Train: [70] [ 200/6250] eta: 0:20:33 lr: 0.000028 grad: 0.1234 (0.1532) loss: 0.8510 (0.8459) time: 0.1535 data: 0.0679 max mem: 8255 +Train: [70] [ 300/6250] eta: 0:18:52 lr: 0.000028 grad: 0.1275 (0.1474) loss: 0.8484 (0.8449) time: 0.1524 data: 0.0592 max mem: 8255 +Train: [70] [ 400/6250] eta: 0:18:03 lr: 0.000028 grad: 0.1220 (0.1427) loss: 0.8415 (0.8438) time: 0.1659 data: 0.0710 max mem: 8255 +Train: [70] [ 500/6250] eta: 0:17:37 lr: 0.000028 grad: 0.1214 (0.1397) loss: 0.8428 (0.8434) time: 0.1427 data: 0.0111 max mem: 8255 +Train: [70] [ 600/6250] eta: 0:17:25 lr: 0.000028 grad: 0.1244 (0.1373) loss: 0.8317 (0.8428) time: 0.3102 data: 0.2294 max mem: 8255 +Train: [70] [ 700/6250] eta: 0:16:33 lr: 0.000028 grad: 0.1153 (0.1348) loss: 0.8364 (0.8426) time: 0.1149 data: 0.0149 max mem: 8255 +Train: [70] [ 800/6250] eta: 0:16:08 lr: 0.000028 grad: 0.1165 (0.1331) loss: 0.8344 (0.8421) time: 0.1786 data: 0.0986 max mem: 8255 +Train: [70] [ 900/6250] eta: 0:15:36 lr: 0.000028 grad: 0.1210 (0.1317) loss: 0.8380 (0.8416) time: 0.1375 data: 0.0475 max mem: 8255 +Train: [70] [1000/6250] eta: 0:15:05 lr: 0.000028 grad: 0.1163 (0.1307) loss: 0.8461 (0.8412) time: 0.1532 data: 0.0662 max mem: 8255 +Train: [70] [1100/6250] eta: 0:14:52 lr: 0.000028 grad: 0.1262 (0.1298) loss: 0.8360 (0.8410) time: 0.1050 data: 0.0003 max mem: 8255 +Train: [70] [1200/6250] eta: 0:14:30 lr: 0.000028 grad: 0.1243 (0.1292) loss: 0.8332 (0.8406) time: 0.1768 data: 0.0986 max mem: 8255 +Train: [70] [1300/6250] eta: 0:14:08 lr: 0.000028 grad: 0.1184 (0.1286) loss: 0.8363 (0.8401) time: 0.1654 data: 0.0751 max mem: 8255 +Train: [70] [1400/6250] eta: 0:13:45 lr: 0.000028 grad: 0.1121 (0.1280) loss: 0.8389 (0.8398) time: 0.1664 data: 0.0879 max mem: 8255 +Train: [70] [1500/6250] eta: 0:13:21 lr: 0.000028 grad: 0.1179 (0.1275) loss: 0.8383 (0.8393) time: 0.1618 data: 0.0768 max mem: 8255 +Train: [70] [1600/6250] eta: 0:13:15 lr: 0.000028 grad: 0.1168 (0.1274) loss: 0.8303 (0.8388) time: 0.1006 data: 0.0002 max mem: 8255 +Train: [70] [1700/6250] eta: 0:12:57 lr: 0.000028 grad: 0.1207 (0.1272) loss: 0.8291 (0.8384) time: 0.1833 data: 0.1033 max mem: 8255 +Train: [70] [1800/6250] eta: 0:12:41 lr: 0.000028 grad: 0.1113 (0.1267) loss: 0.8368 (0.8382) time: 0.1980 data: 0.0815 max mem: 8255 +Train: [70] [1900/6250] eta: 0:12:28 lr: 0.000028 grad: 0.1245 (0.1264) loss: 0.8311 (0.8379) time: 0.1781 data: 0.0994 max mem: 8255 +Train: [70] [2000/6250] eta: 0:12:32 lr: 0.000028 grad: 0.1220 (0.1263) loss: 0.8262 (0.8376) time: 0.1280 data: 0.0237 max mem: 8255 +Train: [70] [2100/6250] eta: 0:12:12 lr: 0.000028 grad: 0.1285 (0.1262) loss: 0.8258 (0.8373) time: 0.1598 data: 0.0749 max mem: 8255 +Train: [70] [2200/6250] eta: 0:11:58 lr: 0.000028 grad: 0.1172 (0.1261) loss: 0.8229 (0.8370) time: 0.1015 data: 0.0151 max mem: 8255 +Train: [70] [2300/6250] eta: 0:11:37 lr: 0.000028 grad: 0.1210 (0.1259) loss: 0.8347 (0.8370) time: 0.1834 data: 0.1008 max mem: 8255 +Train: [70] [2400/6250] eta: 0:11:19 lr: 0.000028 grad: 0.1086 (0.1257) loss: 0.8509 (0.8369) time: 0.2039 data: 0.1327 max mem: 8255 +Train: [70] [2500/6250] eta: 0:11:06 lr: 0.000028 grad: 0.1234 (0.1256) loss: 0.8308 (0.8369) time: 0.1000 data: 0.0106 max mem: 8255 +Train: [70] [2600/6250] eta: 0:10:44 lr: 0.000028 grad: 0.1232 (0.1255) loss: 0.8364 (0.8368) time: 0.1825 data: 0.1167 max mem: 8255 +Train: [70] [2700/6250] eta: 0:10:27 lr: 0.000028 grad: 0.1174 (0.1254) loss: 0.8323 (0.8367) time: 0.1982 data: 0.1135 max mem: 8255 +Train: [70] [2800/6250] eta: 0:10:07 lr: 0.000028 grad: 0.1201 (0.1252) loss: 0.8346 (0.8366) time: 0.1661 data: 0.0925 max mem: 8255 +Train: [70] [2900/6250] eta: 0:09:47 lr: 0.000028 grad: 0.1197 (0.1251) loss: 0.8390 (0.8365) time: 0.1508 data: 0.0781 max mem: 8255 +Train: [70] [3000/6250] eta: 0:09:27 lr: 0.000027 grad: 0.1193 (0.1251) loss: 0.8326 (0.8364) time: 0.1513 data: 0.0607 max mem: 8255 +Train: [70] [3100/6250] eta: 0:09:07 lr: 0.000027 grad: 0.1222 (0.1250) loss: 0.8388 (0.8363) time: 0.1540 data: 0.0806 max mem: 8255 +Train: [70] [3200/6250] eta: 0:08:46 lr: 0.000027 grad: 0.1210 (0.1250) loss: 0.8341 (0.8362) time: 0.1387 data: 0.0654 max mem: 8255 +Train: [70] [3300/6250] eta: 0:08:26 lr: 0.000027 grad: 0.1220 (0.1249) loss: 0.8286 (0.8361) time: 0.1448 data: 0.0732 max mem: 8255 +Train: [70] [3400/6250] eta: 0:08:06 lr: 0.000027 grad: 0.1186 (0.1248) loss: 0.8326 (0.8361) time: 0.1591 data: 0.0853 max mem: 8255 +Train: [70] [3500/6250] eta: 0:07:47 lr: 0.000027 grad: 0.1171 (0.1247) loss: 0.8359 (0.8360) time: 0.1205 data: 0.0546 max mem: 8255 +Train: [70] [3600/6250] eta: 0:07:27 lr: 0.000027 grad: 0.1149 (0.1246) loss: 0.8426 (0.8360) time: 0.1100 data: 0.0415 max mem: 8255 +Train: [70] [3700/6250] eta: 0:07:08 lr: 0.000027 grad: 0.1186 (0.1245) loss: 0.8387 (0.8360) time: 0.1315 data: 0.0559 max mem: 8255 +Train: [70] [3800/6250] eta: 0:06:51 lr: 0.000027 grad: 0.1106 (0.1244) loss: 0.8432 (0.8360) time: 0.1379 data: 0.0579 max mem: 8255 +Train: [70] [3900/6250] eta: 0:06:32 lr: 0.000027 grad: 0.1202 (0.1243) loss: 0.8350 (0.8360) time: 0.1390 data: 0.0539 max mem: 8255 +Train: [70] [4000/6250] eta: 0:06:13 lr: 0.000027 grad: 0.1196 (0.1243) loss: 0.8391 (0.8360) time: 0.1351 data: 0.0611 max mem: 8255 +Train: [70] [4100/6250] eta: 0:05:55 lr: 0.000027 grad: 0.1161 (0.1241) loss: 0.8427 (0.8361) time: 0.1321 data: 0.0631 max mem: 8255 +Train: [70] [4200/6250] eta: 0:05:37 lr: 0.000027 grad: 0.1157 (0.1240) loss: 0.8457 (0.8362) time: 0.1158 data: 0.0366 max mem: 8255 +Train: [70] [4300/6250] eta: 0:05:19 lr: 0.000027 grad: 0.1233 (0.1239) loss: 0.8368 (0.8363) time: 0.1333 data: 0.0550 max mem: 8255 +Train: [70] [4400/6250] eta: 0:05:02 lr: 0.000027 grad: 0.1150 (0.1238) loss: 0.8403 (0.8364) time: 0.1606 data: 0.0755 max mem: 8255 +Train: [70] [4500/6250] eta: 0:04:45 lr: 0.000027 grad: 0.1151 (0.1237) loss: 0.8424 (0.8365) time: 0.1491 data: 0.0806 max mem: 8255 +Train: [70] [4600/6250] eta: 0:04:28 lr: 0.000027 grad: 0.1152 (0.1235) loss: 0.8400 (0.8367) time: 0.1553 data: 0.0717 max mem: 8255 +Train: [70] [4700/6250] eta: 0:04:11 lr: 0.000027 grad: 0.1168 (0.1234) loss: 0.8456 (0.8368) time: 0.1285 data: 0.0576 max mem: 8255 +Train: [70] [4800/6250] eta: 0:03:54 lr: 0.000027 grad: 0.1166 (0.1233) loss: 0.8338 (0.8370) time: 0.1508 data: 0.0537 max mem: 8255 +Train: [70] [4900/6250] eta: 0:03:38 lr: 0.000027 grad: 0.1146 (0.1232) loss: 0.8369 (0.8371) time: 0.1212 data: 0.0447 max mem: 8255 +Train: [70] [5000/6250] eta: 0:03:21 lr: 0.000027 grad: 0.1155 (0.1231) loss: 0.8403 (0.8372) time: 0.1379 data: 0.0665 max mem: 8255 +Train: [70] [5100/6250] eta: 0:03:04 lr: 0.000027 grad: 0.1157 (0.1230) loss: 0.8459 (0.8373) time: 0.1448 data: 0.0703 max mem: 8255 +Train: [70] [5200/6250] eta: 0:02:48 lr: 0.000027 grad: 0.1174 (0.1229) loss: 0.8371 (0.8374) time: 0.1616 data: 0.0987 max mem: 8255 +Train: [70] [5300/6250] eta: 0:02:31 lr: 0.000027 grad: 0.1235 (0.1229) loss: 0.8388 (0.8374) time: 0.1974 data: 0.1251 max mem: 8255 +Train: [70] [5400/6250] eta: 0:02:14 lr: 0.000027 grad: 0.1200 (0.1229) loss: 0.8390 (0.8374) time: 0.1164 data: 0.0449 max mem: 8255 +Train: [70] [5500/6250] eta: 0:01:58 lr: 0.000027 grad: 0.1202 (0.1229) loss: 0.8347 (0.8375) time: 0.1380 data: 0.0621 max mem: 8255 +Train: [70] [5600/6250] eta: 0:01:42 lr: 0.000027 grad: 0.1158 (0.1230) loss: 0.8422 (0.8375) time: 0.1559 data: 0.0975 max mem: 8255 +Train: [70] [5700/6250] eta: 0:01:26 lr: 0.000027 grad: 0.1215 (0.1230) loss: 0.8332 (0.8375) time: 0.1550 data: 0.0728 max mem: 8255 +Train: [70] [5800/6250] eta: 0:01:10 lr: 0.000027 grad: 0.1221 (0.1231) loss: 0.8380 (0.8375) time: 0.1733 data: 0.0883 max mem: 8255 +Train: [70] [5900/6250] eta: 0:00:55 lr: 0.000027 grad: 0.1230 (0.1231) loss: 0.8395 (0.8376) time: 0.1381 data: 0.0647 max mem: 8255 +Train: [70] [6000/6250] eta: 0:00:39 lr: 0.000027 grad: 0.1212 (0.1231) loss: 0.8385 (0.8376) time: 0.1617 data: 0.1009 max mem: 8255 +Train: [70] [6100/6250] eta: 0:00:23 lr: 0.000027 grad: 0.1161 (0.1232) loss: 0.8346 (0.8376) time: 0.1331 data: 0.0622 max mem: 8255 +Train: [70] [6200/6250] eta: 0:00:07 lr: 0.000027 grad: 0.1251 (0.1232) loss: 0.8372 (0.8375) time: 0.1424 data: 0.0579 max mem: 8255 +Train: [70] [6249/6250] eta: 0:00:00 lr: 0.000027 grad: 0.1274 (0.1232) loss: 0.8413 (0.8376) time: 0.1303 data: 0.0487 max mem: 8255 +Train: [70] Total time: 0:16:27 (0.1581 s / it) +Averaged stats: lr: 0.000027 grad: 0.1274 (0.1232) loss: 0.8413 (0.8376) +Eval (hcp-train-subset): [70] [ 0/62] eta: 0:06:20 loss: 0.8725 (0.8725) time: 6.1337 data: 6.1072 max mem: 8255 +Eval (hcp-train-subset): [70] [61/62] eta: 0:00:00 loss: 0.8597 (0.8620) time: 0.1618 data: 0.1413 max mem: 8255 +Eval (hcp-train-subset): [70] Total time: 0:00:15 (0.2464 s / it) +Averaged stats (hcp-train-subset): loss: 0.8597 (0.8620) +Eval (hcp-val): [70] [ 0/62] eta: 0:04:37 loss: 0.8707 (0.8707) time: 4.4815 data: 4.4292 max mem: 8255 +Eval (hcp-val): [70] [61/62] eta: 0:00:00 loss: 0.8741 (0.8746) time: 0.1049 data: 0.0832 max mem: 8255 +Eval (hcp-val): [70] Total time: 0:00:15 (0.2446 s / it) +Averaged stats (hcp-val): loss: 0.8741 (0.8746) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +Train: [71] [ 0/6250] eta: 12:30:16 lr: 0.000027 grad: 0.1480 (0.1480) loss: 0.8815 (0.8815) time: 7.2026 data: 7.1044 max mem: 8255 +Train: [71] [ 100/6250] eta: 0:21:47 lr: 0.000027 grad: 0.1325 (0.1749) loss: 0.8524 (0.8466) time: 0.1674 data: 0.0804 max mem: 8255 +Train: [71] [ 200/6250] eta: 0:17:50 lr: 0.000027 grad: 0.1266 (0.1533) loss: 0.8508 (0.8452) time: 0.1635 data: 0.0776 max mem: 8255 +Train: [71] [ 300/6250] eta: 0:16:29 lr: 0.000027 grad: 0.1277 (0.1457) loss: 0.8389 (0.8459) time: 0.1614 data: 0.0605 max mem: 8255 +Train: [71] [ 400/6250] eta: 0:16:08 lr: 0.000026 grad: 0.1352 (0.1421) loss: 0.8380 (0.8446) time: 0.1688 data: 0.0854 max mem: 8255 +Train: [71] [ 500/6250] eta: 0:16:06 lr: 0.000026 grad: 0.1283 (0.1393) loss: 0.8435 (0.8444) time: 0.1413 data: 0.0633 max mem: 8255 +Train: [71] [ 600/6250] eta: 0:15:23 lr: 0.000026 grad: 0.1198 (0.1376) loss: 0.8423 (0.8437) time: 0.1349 data: 0.0517 max mem: 8255 +Train: [71] [ 700/6250] eta: 0:14:57 lr: 0.000026 grad: 0.1228 (0.1365) loss: 0.8424 (0.8434) time: 0.1805 data: 0.1116 max mem: 8255 +Train: [71] [ 800/6250] eta: 0:15:06 lr: 0.000026 grad: 0.1170 (0.1350) loss: 0.8386 (0.8437) time: 0.1573 data: 0.0807 max mem: 8255 +Train: [71] [ 900/6250] eta: 0:14:30 lr: 0.000026 grad: 0.1178 (0.1340) loss: 0.8504 (0.8435) time: 0.1358 data: 0.0635 max mem: 8255 +Train: [71] [1000/6250] eta: 0:14:01 lr: 0.000026 grad: 0.1190 (0.1327) loss: 0.8435 (0.8433) time: 0.1310 data: 0.0604 max mem: 8255 +Train: [71] [1100/6250] eta: 0:13:34 lr: 0.000026 grad: 0.1162 (0.1316) loss: 0.8435 (0.8433) time: 0.1440 data: 0.0698 max mem: 8255 +Train: [71] [1200/6250] eta: 0:13:06 lr: 0.000026 grad: 0.1209 (0.1309) loss: 0.8399 (0.8430) time: 0.1186 data: 0.0465 max mem: 8255 +Train: [71] [1300/6250] eta: 0:12:43 lr: 0.000026 grad: 0.1195 (0.1302) loss: 0.8501 (0.8428) time: 0.1377 data: 0.0713 max mem: 8255 +Train: [71] [1400/6250] eta: 0:12:17 lr: 0.000026 grad: 0.1113 (0.1295) loss: 0.8484 (0.8426) time: 0.1360 data: 0.0654 max mem: 8255 +Train: [71] [1500/6250] eta: 0:11:55 lr: 0.000026 grad: 0.1182 (0.1290) loss: 0.8333 (0.8423) time: 0.1347 data: 0.0673 max mem: 8255 +Train: [71] [1600/6250] eta: 0:11:36 lr: 0.000026 grad: 0.1194 (0.1287) loss: 0.8426 (0.8423) time: 0.1102 data: 0.0369 max mem: 8255 +Train: [71] [1700/6250] eta: 0:11:17 lr: 0.000026 grad: 0.1097 (0.1282) loss: 0.8394 (0.8423) time: 0.1412 data: 0.0723 max mem: 8255 +Train: [71] [1800/6250] eta: 0:10:59 lr: 0.000026 grad: 0.1196 (0.1278) loss: 0.8511 (0.8422) time: 0.1352 data: 0.0672 max mem: 8255 +Train: [71] [1900/6250] eta: 0:10:42 lr: 0.000026 grad: 0.1202 (0.1276) loss: 0.8405 (0.8421) time: 0.0978 data: 0.0168 max mem: 8255 +Train: [71] [2000/6250] eta: 0:10:26 lr: 0.000026 grad: 0.1223 (0.1271) loss: 0.8428 (0.8421) time: 0.1305 data: 0.0647 max mem: 8255 +Train: [71] [2100/6250] eta: 0:10:09 lr: 0.000026 grad: 0.1198 (0.1267) loss: 0.8394 (0.8420) time: 0.1462 data: 0.0700 max mem: 8255 +Train: [71] [2200/6250] eta: 0:09:52 lr: 0.000026 grad: 0.1166 (0.1265) loss: 0.8344 (0.8418) time: 0.1030 data: 0.0280 max mem: 8255 +Train: [71] [2300/6250] eta: 0:09:36 lr: 0.000026 grad: 0.1238 (0.1263) loss: 0.8354 (0.8415) time: 0.1516 data: 0.0804 max mem: 8255 +Train: [71] [2400/6250] eta: 0:09:20 lr: 0.000026 grad: 0.1253 (0.1262) loss: 0.8338 (0.8412) time: 0.1484 data: 0.0726 max mem: 8255 +Train: [71] [2500/6250] eta: 0:09:05 lr: 0.000026 grad: 0.1236 (0.1261) loss: 0.8358 (0.8409) time: 0.1370 data: 0.0626 max mem: 8255 +Train: [71] [2600/6250] eta: 0:08:50 lr: 0.000026 grad: 0.1189 (0.1260) loss: 0.8321 (0.8407) time: 0.1628 data: 0.0929 max mem: 8255 +Train: [71] [2700/6250] eta: 0:08:37 lr: 0.000026 grad: 0.1230 (0.1259) loss: 0.8382 (0.8405) time: 0.0895 data: 0.0062 max mem: 8255 +Train: [71] [2800/6250] eta: 0:08:21 lr: 0.000026 grad: 0.1169 (0.1258) loss: 0.8452 (0.8404) time: 0.1641 data: 0.0913 max mem: 8255 +Train: [71] [2900/6250] eta: 0:08:06 lr: 0.000026 grad: 0.1189 (0.1256) loss: 0.8438 (0.8403) time: 0.1340 data: 0.0665 max mem: 8255 +Train: [71] [3000/6250] eta: 0:07:51 lr: 0.000026 grad: 0.1070 (0.1254) loss: 0.8454 (0.8404) time: 0.1030 data: 0.0293 max mem: 8255 +Train: [71] [3100/6250] eta: 0:07:39 lr: 0.000026 grad: 0.1202 (0.1252) loss: 0.8413 (0.8404) time: 0.1796 data: 0.0924 max mem: 8255 +Train: [71] [3200/6250] eta: 0:07:22 lr: 0.000026 grad: 0.1154 (0.1250) loss: 0.8436 (0.8404) time: 0.1189 data: 0.0425 max mem: 8255 +Train: [71] [3300/6250] eta: 0:07:07 lr: 0.000026 grad: 0.1149 (0.1248) loss: 0.8446 (0.8405) time: 0.1485 data: 0.0699 max mem: 8255 +Train: [71] [3400/6250] eta: 0:06:52 lr: 0.000026 grad: 0.1146 (0.1246) loss: 0.8363 (0.8406) time: 0.1258 data: 0.0520 max mem: 8255 +Train: [71] [3500/6250] eta: 0:06:36 lr: 0.000026 grad: 0.1209 (0.1245) loss: 0.8407 (0.8407) time: 0.1312 data: 0.0597 max mem: 8255 +Train: [71] [3600/6250] eta: 0:06:21 lr: 0.000026 grad: 0.1173 (0.1244) loss: 0.8490 (0.8407) time: 0.1194 data: 0.0502 max mem: 8255 +Train: [71] [3700/6250] eta: 0:06:07 lr: 0.000026 grad: 0.1139 (0.1243) loss: 0.8456 (0.8408) time: 0.0735 data: 0.0002 max mem: 8255 +Train: [71] [3800/6250] eta: 0:05:51 lr: 0.000026 grad: 0.1159 (0.1242) loss: 0.8390 (0.8409) time: 0.1163 data: 0.0429 max mem: 8255 +Train: [71] [3900/6250] eta: 0:05:36 lr: 0.000026 grad: 0.1224 (0.1241) loss: 0.8420 (0.8409) time: 0.1231 data: 0.0476 max mem: 8255 +Train: [71] [4000/6250] eta: 0:05:22 lr: 0.000026 grad: 0.1212 (0.1241) loss: 0.8345 (0.8409) time: 0.1614 data: 0.0832 max mem: 8255 +Train: [71] [4100/6250] eta: 0:05:07 lr: 0.000026 grad: 0.1198 (0.1240) loss: 0.8414 (0.8410) time: 0.1294 data: 0.0555 max mem: 8255 +Train: [71] [4200/6250] eta: 0:04:52 lr: 0.000025 grad: 0.1150 (0.1240) loss: 0.8337 (0.8409) time: 0.1135 data: 0.0487 max mem: 8255 +Train: [71] [4300/6250] eta: 0:04:38 lr: 0.000025 grad: 0.1175 (0.1239) loss: 0.8433 (0.8409) time: 0.1607 data: 0.0963 max mem: 8255 +Train: [71] [4400/6250] eta: 0:04:23 lr: 0.000025 grad: 0.1208 (0.1238) loss: 0.8411 (0.8409) time: 0.1466 data: 0.0760 max mem: 8255 +Train: [71] [4500/6250] eta: 0:04:09 lr: 0.000025 grad: 0.1157 (0.1237) loss: 0.8444 (0.8409) time: 0.1209 data: 0.0560 max mem: 8255 +Train: [71] [4600/6250] eta: 0:03:54 lr: 0.000025 grad: 0.1133 (0.1236) loss: 0.8417 (0.8409) time: 0.1205 data: 0.0552 max mem: 8255 +Train: [71] [4700/6250] eta: 0:03:39 lr: 0.000025 grad: 0.1163 (0.1235) loss: 0.8456 (0.8410) time: 0.1268 data: 0.0545 max mem: 8255 +Train: [71] [4800/6250] eta: 0:03:26 lr: 0.000025 grad: 0.1129 (0.1235) loss: 0.8425 (0.8411) time: 0.1893 data: 0.1254 max mem: 8255 +Train: [71] [4900/6250] eta: 0:03:11 lr: 0.000025 grad: 0.1142 (0.1235) loss: 0.8401 (0.8411) time: 0.1125 data: 0.0389 max mem: 8255 +Train: [71] [5000/6250] eta: 0:02:56 lr: 0.000025 grad: 0.1162 (0.1233) loss: 0.8532 (0.8412) time: 0.1159 data: 0.0446 max mem: 8255 +Train: [71] [5100/6250] eta: 0:02:42 lr: 0.000025 grad: 0.1186 (0.1232) loss: 0.8452 (0.8412) time: 0.1327 data: 0.0624 max mem: 8255 +Train: [71] [5200/6250] eta: 0:02:28 lr: 0.000025 grad: 0.1162 (0.1231) loss: 0.8423 (0.8413) time: 0.1304 data: 0.0622 max mem: 8255 +Train: [71] [5300/6250] eta: 0:02:13 lr: 0.000025 grad: 0.1102 (0.1229) loss: 0.8479 (0.8414) time: 0.1351 data: 0.0656 max mem: 8255 +Train: [71] [5400/6250] eta: 0:02:00 lr: 0.000025 grad: 0.1104 (0.1228) loss: 0.8390 (0.8415) time: 0.0856 data: 0.0002 max mem: 8255 +Train: [71] [5500/6250] eta: 0:01:45 lr: 0.000025 grad: 0.1167 (0.1227) loss: 0.8457 (0.8416) time: 0.1363 data: 0.0710 max mem: 8255 +Train: [71] [5600/6250] eta: 0:01:31 lr: 0.000025 grad: 0.1164 (0.1226) loss: 0.8411 (0.8417) time: 0.1433 data: 0.0605 max mem: 8255 +Train: [71] [5700/6250] eta: 0:01:18 lr: 0.000025 grad: 0.1123 (0.1225) loss: 0.8411 (0.8417) time: 0.2271 data: 0.1327 max mem: 8255 +Train: [71] [5800/6250] eta: 0:01:03 lr: 0.000025 grad: 0.1204 (0.1225) loss: 0.8353 (0.8417) time: 0.1493 data: 0.0762 max mem: 8255 +Train: [71] [5900/6250] eta: 0:00:49 lr: 0.000025 grad: 0.1181 (0.1225) loss: 0.8395 (0.8417) time: 0.1628 data: 0.0885 max mem: 8255 +Train: [71] [6000/6250] eta: 0:00:35 lr: 0.000025 grad: 0.1177 (0.1224) loss: 0.8428 (0.8417) time: 0.1592 data: 0.0818 max mem: 8255 +Train: [71] [6100/6250] eta: 0:00:21 lr: 0.000025 grad: 0.1145 (0.1224) loss: 0.8438 (0.8417) time: 0.1818 data: 0.1094 max mem: 8255 +Train: [71] [6200/6250] eta: 0:00:07 lr: 0.000025 grad: 0.1204 (0.1224) loss: 0.8359 (0.8417) time: 0.1736 data: 0.1079 max mem: 8255 +Train: [71] [6249/6250] eta: 0:00:00 lr: 0.000025 grad: 0.1131 (0.1225) loss: 0.8509 (0.8417) time: 0.1599 data: 0.0880 max mem: 8255 +Train: [71] Total time: 0:15:01 (0.1443 s / it) +Averaged stats: lr: 0.000025 grad: 0.1131 (0.1225) loss: 0.8509 (0.8417) +Eval (hcp-train-subset): [71] [ 0/62] eta: 0:04:00 loss: 0.8735 (0.8735) time: 3.8860 data: 3.8138 max mem: 8255 +Eval (hcp-train-subset): [71] [61/62] eta: 0:00:00 loss: 0.8602 (0.8615) time: 0.1314 data: 0.1081 max mem: 8255 +Eval (hcp-train-subset): [71] Total time: 0:00:13 (0.2130 s / it) +Averaged stats (hcp-train-subset): loss: 0.8602 (0.8615) +Eval (hcp-val): [71] [ 0/62] eta: 0:04:48 loss: 0.8746 (0.8746) time: 4.6513 data: 4.6232 max mem: 8255 +Eval (hcp-val): [71] [61/62] eta: 0:00:00 loss: 0.8729 (0.8757) time: 0.1203 data: 0.0993 max mem: 8255 +Eval (hcp-val): [71] Total time: 0:00:12 (0.2083 s / it) +Averaged stats (hcp-val): loss: 0.8729 (0.8757) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +Train: [72] [ 0/6250] eta: 9:22:26 lr: 0.000025 grad: 0.2752 (0.2752) loss: 0.8794 (0.8794) time: 5.3994 data: 5.2726 max mem: 8255 +Train: [72] [ 100/6250] eta: 0:18:57 lr: 0.000025 grad: 0.1458 (0.1698) loss: 0.8484 (0.8572) time: 0.1261 data: 0.0338 max mem: 8255 +Train: [72] [ 200/6250] eta: 0:16:39 lr: 0.000025 grad: 0.1299 (0.1534) loss: 0.8459 (0.8501) time: 0.1467 data: 0.0673 max mem: 8255 +Train: [72] [ 300/6250] eta: 0:15:04 lr: 0.000025 grad: 0.1245 (0.1477) loss: 0.8443 (0.8472) time: 0.1377 data: 0.0499 max mem: 8255 +Train: [72] [ 400/6250] eta: 0:14:01 lr: 0.000025 grad: 0.1155 (0.1410) loss: 0.8538 (0.8479) time: 0.1224 data: 0.0375 max mem: 8255 +Train: [72] [ 500/6250] eta: 0:13:23 lr: 0.000025 grad: 0.1282 (0.1385) loss: 0.8477 (0.8471) time: 0.1150 data: 0.0344 max mem: 8255 +Train: [72] [ 600/6250] eta: 0:12:50 lr: 0.000025 grad: 0.1220 (0.1365) loss: 0.8326 (0.8458) time: 0.1268 data: 0.0533 max mem: 8255 +Train: [72] [ 700/6250] eta: 0:12:33 lr: 0.000025 grad: 0.1167 (0.1346) loss: 0.8408 (0.8449) time: 0.1285 data: 0.0519 max mem: 8255 +Train: [72] [ 800/6250] eta: 0:12:21 lr: 0.000025 grad: 0.1201 (0.1335) loss: 0.8442 (0.8443) time: 0.1358 data: 0.0567 max mem: 8255 +Train: [72] [ 900/6250] eta: 0:12:08 lr: 0.000025 grad: 0.1247 (0.1320) loss: 0.8454 (0.8443) time: 0.1367 data: 0.0518 max mem: 8255 +Train: [72] [1000/6250] eta: 0:12:00 lr: 0.000025 grad: 0.1229 (0.1310) loss: 0.8443 (0.8442) time: 0.1302 data: 0.0556 max mem: 8255 +Train: [72] [1100/6250] eta: 0:11:56 lr: 0.000025 grad: 0.1147 (0.1299) loss: 0.8436 (0.8440) time: 0.1319 data: 0.0537 max mem: 8255 +Train: [72] [1200/6250] eta: 0:11:55 lr: 0.000025 grad: 0.1146 (0.1292) loss: 0.8450 (0.8437) time: 0.1464 data: 0.0759 max mem: 8255 +Train: [72] [1300/6250] eta: 0:11:43 lr: 0.000025 grad: 0.1156 (0.1285) loss: 0.8418 (0.8435) time: 0.1476 data: 0.0746 max mem: 8255 +Train: [72] [1400/6250] eta: 0:11:29 lr: 0.000025 grad: 0.1200 (0.1278) loss: 0.8349 (0.8432) time: 0.1373 data: 0.0704 max mem: 8255 +Train: [72] [1500/6250] eta: 0:11:12 lr: 0.000025 grad: 0.1186 (0.1275) loss: 0.8424 (0.8429) time: 0.1384 data: 0.0651 max mem: 8255 +Train: [72] [1600/6250] eta: 0:10:56 lr: 0.000025 grad: 0.1217 (0.1268) loss: 0.8374 (0.8428) time: 0.1332 data: 0.0677 max mem: 8255 +Train: [72] [1700/6250] eta: 0:10:39 lr: 0.000024 grad: 0.1186 (0.1264) loss: 0.8385 (0.8428) time: 0.1125 data: 0.0458 max mem: 8255 +Train: [72] [1800/6250] eta: 0:10:24 lr: 0.000024 grad: 0.1180 (0.1263) loss: 0.8371 (0.8425) time: 0.1339 data: 0.0694 max mem: 8255 +Train: [72] [1900/6250] eta: 0:10:10 lr: 0.000024 grad: 0.1161 (0.1263) loss: 0.8379 (0.8424) time: 0.1666 data: 0.0990 max mem: 8255 +Train: [72] [2000/6250] eta: 0:09:57 lr: 0.000024 grad: 0.1250 (0.1261) loss: 0.8396 (0.8423) time: 0.1797 data: 0.0885 max mem: 8255 +Train: [72] [2100/6250] eta: 0:09:40 lr: 0.000024 grad: 0.1147 (0.1259) loss: 0.8416 (0.8422) time: 0.1125 data: 0.0349 max mem: 8255 +Train: [72] [2200/6250] eta: 0:09:33 lr: 0.000024 grad: 0.1195 (0.1257) loss: 0.8418 (0.8422) time: 0.2953 data: 0.1913 max mem: 8255 +Train: [72] [2300/6250] eta: 0:09:16 lr: 0.000024 grad: 0.1195 (0.1255) loss: 0.8378 (0.8421) time: 0.1430 data: 0.0695 max mem: 8255 +Train: [72] [2400/6250] eta: 0:09:01 lr: 0.000024 grad: 0.1184 (0.1254) loss: 0.8452 (0.8418) time: 0.1510 data: 0.0803 max mem: 8255 +Train: [72] [2500/6250] eta: 0:08:46 lr: 0.000024 grad: 0.1185 (0.1254) loss: 0.8382 (0.8417) time: 0.1231 data: 0.0594 max mem: 8255 +Train: [72] [2600/6250] eta: 0:08:32 lr: 0.000024 grad: 0.1144 (0.1253) loss: 0.8439 (0.8415) time: 0.1338 data: 0.0613 max mem: 8255 +Train: [72] [2700/6250] eta: 0:08:16 lr: 0.000024 grad: 0.1212 (0.1252) loss: 0.8443 (0.8415) time: 0.1318 data: 0.0647 max mem: 8255 +Train: [72] [2800/6250] eta: 0:08:01 lr: 0.000024 grad: 0.1211 (0.1252) loss: 0.8380 (0.8414) time: 0.1348 data: 0.0618 max mem: 8255 +Train: [72] [2900/6250] eta: 0:07:47 lr: 0.000024 grad: 0.1181 (0.1251) loss: 0.8375 (0.8413) time: 0.1398 data: 0.0773 max mem: 8255 +Train: [72] [3000/6250] eta: 0:07:33 lr: 0.000024 grad: 0.1196 (0.1251) loss: 0.8371 (0.8412) time: 0.1372 data: 0.0681 max mem: 8255 +Train: [72] [3100/6250] eta: 0:07:20 lr: 0.000024 grad: 0.1260 (0.1251) loss: 0.8476 (0.8412) time: 0.1313 data: 0.0673 max mem: 8255 +Train: [72] [3200/6250] eta: 0:07:06 lr: 0.000024 grad: 0.1215 (0.1252) loss: 0.8444 (0.8411) time: 0.1372 data: 0.0624 max mem: 8255 +Train: [72] [3300/6250] eta: 0:06:53 lr: 0.000024 grad: 0.1293 (0.1253) loss: 0.8390 (0.8411) time: 0.1363 data: 0.0688 max mem: 8255 +Train: [72] [3400/6250] eta: 0:06:39 lr: 0.000024 grad: 0.1232 (0.1255) loss: 0.8395 (0.8410) time: 0.1295 data: 0.0603 max mem: 8255 +Train: [72] [3500/6250] eta: 0:06:25 lr: 0.000024 grad: 0.1190 (0.1255) loss: 0.8449 (0.8410) time: 0.1435 data: 0.0742 max mem: 8255 +Train: [72] [3600/6250] eta: 0:06:13 lr: 0.000024 grad: 0.1328 (0.1257) loss: 0.8429 (0.8409) time: 0.1720 data: 0.0952 max mem: 8255 +Train: [72] [3700/6250] eta: 0:05:57 lr: 0.000024 grad: 0.1237 (0.1257) loss: 0.8371 (0.8409) time: 0.1282 data: 0.0514 max mem: 8255 +Train: [72] [3800/6250] eta: 0:05:43 lr: 0.000024 grad: 0.1225 (0.1257) loss: 0.8402 (0.8408) time: 0.1309 data: 0.0681 max mem: 8255 +Train: [72] [3900/6250] eta: 0:05:29 lr: 0.000024 grad: 0.1196 (0.1256) loss: 0.8439 (0.8408) time: 0.1909 data: 0.0544 max mem: 8255 +Train: [72] [4000/6250] eta: 0:05:15 lr: 0.000024 grad: 0.1187 (0.1256) loss: 0.8433 (0.8409) time: 0.1280 data: 0.0567 max mem: 8255 +Train: [72] [4100/6250] eta: 0:05:02 lr: 0.000024 grad: 0.1218 (0.1255) loss: 0.8451 (0.8408) time: 0.1567 data: 0.0751 max mem: 8255 +Train: [72] [4200/6250] eta: 0:04:48 lr: 0.000024 grad: 0.1220 (0.1255) loss: 0.8432 (0.8408) time: 0.1243 data: 0.0572 max mem: 8255 +Train: [72] [4300/6250] eta: 0:04:34 lr: 0.000024 grad: 0.1214 (0.1255) loss: 0.8368 (0.8408) time: 0.1132 data: 0.0418 max mem: 8255 +Train: [72] [4400/6250] eta: 0:04:19 lr: 0.000024 grad: 0.1197 (0.1255) loss: 0.8347 (0.8407) time: 0.1218 data: 0.0578 max mem: 8255 +Train: [72] [4500/6250] eta: 0:04:05 lr: 0.000024 grad: 0.1212 (0.1255) loss: 0.8378 (0.8406) time: 0.1520 data: 0.0684 max mem: 8255 +Train: [72] [4600/6250] eta: 0:03:50 lr: 0.000024 grad: 0.1275 (0.1256) loss: 0.8326 (0.8404) time: 0.1302 data: 0.0681 max mem: 8255 +Train: [72] [4700/6250] eta: 0:03:36 lr: 0.000024 grad: 0.1245 (0.1256) loss: 0.8334 (0.8402) time: 0.1346 data: 0.0630 max mem: 8255 +Train: [72] [4800/6250] eta: 0:03:21 lr: 0.000024 grad: 0.1243 (0.1257) loss: 0.8380 (0.8401) time: 0.1198 data: 0.0441 max mem: 8255 +Train: [72] [4900/6250] eta: 0:03:07 lr: 0.000024 grad: 0.1236 (0.1257) loss: 0.8331 (0.8399) time: 0.1207 data: 0.0489 max mem: 8255 +Train: [72] [5000/6250] eta: 0:02:53 lr: 0.000024 grad: 0.1213 (0.1258) loss: 0.8377 (0.8397) time: 0.1407 data: 0.0767 max mem: 8255 +Train: [72] [5100/6250] eta: 0:02:39 lr: 0.000024 grad: 0.1158 (0.1259) loss: 0.8334 (0.8396) time: 0.1494 data: 0.0833 max mem: 8255 +Train: [72] [5200/6250] eta: 0:02:25 lr: 0.000024 grad: 0.1257 (0.1259) loss: 0.8276 (0.8395) time: 0.1296 data: 0.0608 max mem: 8255 +Train: [72] [5300/6250] eta: 0:02:11 lr: 0.000024 grad: 0.1208 (0.1259) loss: 0.8355 (0.8394) time: 0.1436 data: 0.0764 max mem: 8255 +Train: [72] [5400/6250] eta: 0:01:58 lr: 0.000024 grad: 0.1222 (0.1259) loss: 0.8384 (0.8394) time: 0.1479 data: 0.0796 max mem: 8255 +Train: [72] [5500/6250] eta: 0:01:44 lr: 0.000023 grad: 0.1202 (0.1259) loss: 0.8354 (0.8393) time: 0.1309 data: 0.0598 max mem: 8255 +Train: [72] [5600/6250] eta: 0:01:30 lr: 0.000023 grad: 0.1193 (0.1259) loss: 0.8421 (0.8393) time: 0.1422 data: 0.0677 max mem: 8255 +Train: [72] [5700/6250] eta: 0:01:16 lr: 0.000023 grad: 0.1162 (0.1258) loss: 0.8353 (0.8392) time: 0.1332 data: 0.0660 max mem: 8255 +Train: [72] [5800/6250] eta: 0:01:02 lr: 0.000023 grad: 0.1190 (0.1259) loss: 0.8453 (0.8393) time: 0.1375 data: 0.0636 max mem: 8255 +Train: [72] [5900/6250] eta: 0:00:48 lr: 0.000023 grad: 0.1187 (0.1258) loss: 0.8420 (0.8393) time: 0.1577 data: 0.0860 max mem: 8255 +Train: [72] [6000/6250] eta: 0:00:34 lr: 0.000023 grad: 0.1155 (0.1257) loss: 0.8423 (0.8393) time: 0.0826 data: 0.0002 max mem: 8255 +Train: [72] [6100/6250] eta: 0:00:20 lr: 0.000023 grad: 0.1094 (0.1256) loss: 0.8453 (0.8393) time: 0.1406 data: 0.0670 max mem: 8255 +Train: [72] [6200/6250] eta: 0:00:06 lr: 0.000023 grad: 0.1143 (0.1255) loss: 0.8458 (0.8394) time: 0.1567 data: 0.0851 max mem: 8255 +Train: [72] [6249/6250] eta: 0:00:00 lr: 0.000023 grad: 0.1230 (0.1256) loss: 0.8376 (0.8394) time: 0.1262 data: 0.0556 max mem: 8255 +Train: [72] Total time: 0:14:36 (0.1402 s / it) +Averaged stats: lr: 0.000023 grad: 0.1230 (0.1256) loss: 0.8376 (0.8394) +Eval (hcp-train-subset): [72] [ 0/62] eta: 0:05:58 loss: 0.8689 (0.8689) time: 5.7786 data: 5.7523 max mem: 8255 +Eval (hcp-train-subset): [72] [61/62] eta: 0:00:00 loss: 0.8571 (0.8606) time: 0.1304 data: 0.1087 max mem: 8255 +Eval (hcp-train-subset): [72] Total time: 0:00:13 (0.2200 s / it) +Averaged stats (hcp-train-subset): loss: 0.8571 (0.8606) +Eval (hcp-val): [72] [ 0/62] eta: 0:05:55 loss: 0.8705 (0.8705) time: 5.7312 data: 5.7055 max mem: 8255 +Eval (hcp-val): [72] [61/62] eta: 0:00:00 loss: 0.8719 (0.8749) time: 0.0951 data: 0.0747 max mem: 8255 +Eval (hcp-val): [72] Total time: 0:00:13 (0.2103 s / it) +Averaged stats (hcp-val): loss: 0.8719 (0.8749) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +Train: [73] [ 0/6250] eta: 9:04:48 lr: 0.000023 grad: 0.1404 (0.1404) loss: 0.8957 (0.8957) time: 5.2302 data: 4.9313 max mem: 8255 +Train: [73] [ 100/6250] eta: 0:19:10 lr: 0.000023 grad: 0.1409 (0.1511) loss: 0.8324 (0.8466) time: 0.1261 data: 0.0319 max mem: 8255 +Train: [73] [ 200/6250] eta: 0:16:14 lr: 0.000023 grad: 0.1305 (0.1463) loss: 0.8332 (0.8399) time: 0.1219 data: 0.0376 max mem: 8255 +Train: [73] [ 300/6250] eta: 0:15:00 lr: 0.000023 grad: 0.1271 (0.1411) loss: 0.8417 (0.8402) time: 0.1540 data: 0.0623 max mem: 8255 +Train: [73] [ 400/6250] eta: 0:14:18 lr: 0.000023 grad: 0.1271 (0.1394) loss: 0.8290 (0.8388) time: 0.1398 data: 0.0488 max mem: 8255 +Train: [73] [ 500/6250] eta: 0:13:47 lr: 0.000023 grad: 0.1261 (0.1379) loss: 0.8343 (0.8376) time: 0.1126 data: 0.0032 max mem: 8255 +Train: [73] [ 600/6250] eta: 0:13:19 lr: 0.000023 grad: 0.1221 (0.1369) loss: 0.8385 (0.8369) time: 0.1247 data: 0.0526 max mem: 8255 +Train: [73] [ 700/6250] eta: 0:12:59 lr: 0.000023 grad: 0.1227 (0.1367) loss: 0.8429 (0.8364) time: 0.1450 data: 0.0705 max mem: 8255 +Train: [73] [ 800/6250] eta: 0:12:50 lr: 0.000023 grad: 0.1301 (0.1362) loss: 0.8360 (0.8362) time: 0.1380 data: 0.0510 max mem: 8255 +Train: [73] [ 900/6250] eta: 0:12:56 lr: 0.000023 grad: 0.1237 (0.1360) loss: 0.8416 (0.8364) time: 0.1569 data: 0.0786 max mem: 8255 +Train: [73] [1000/6250] eta: 0:12:47 lr: 0.000023 grad: 0.1212 (0.1357) loss: 0.8356 (0.8364) time: 0.1601 data: 0.0872 max mem: 8255 +Train: [73] [1100/6250] eta: 0:12:32 lr: 0.000023 grad: 0.1271 (0.1352) loss: 0.8319 (0.8364) time: 0.1293 data: 0.0605 max mem: 8255 +Train: [73] [1200/6250] eta: 0:12:17 lr: 0.000023 grad: 0.1162 (0.1346) loss: 0.8303 (0.8365) time: 0.1793 data: 0.1093 max mem: 8255 +Train: [73] [1300/6250] eta: 0:12:00 lr: 0.000023 grad: 0.1188 (0.1337) loss: 0.8474 (0.8369) time: 0.1416 data: 0.0735 max mem: 8255 +Train: [73] [1400/6250] eta: 0:11:45 lr: 0.000023 grad: 0.1196 (0.1330) loss: 0.8388 (0.8370) time: 0.1427 data: 0.0707 max mem: 8255 +Train: [73] [1500/6250] eta: 0:11:31 lr: 0.000023 grad: 0.1191 (0.1323) loss: 0.8359 (0.8369) time: 0.1521 data: 0.0890 max mem: 8255 +Train: [73] [1600/6250] eta: 0:11:19 lr: 0.000023 grad: 0.1251 (0.1321) loss: 0.8367 (0.8369) time: 0.1673 data: 0.0961 max mem: 8255 +Train: [73] [1700/6250] eta: 0:11:03 lr: 0.000023 grad: 0.1194 (0.1316) loss: 0.8415 (0.8370) time: 0.1099 data: 0.0314 max mem: 8255 +Train: [73] [1800/6250] eta: 0:10:48 lr: 0.000023 grad: 0.1174 (0.1313) loss: 0.8376 (0.8368) time: 0.1369 data: 0.0433 max mem: 8255 +Train: [73] [1900/6250] eta: 0:10:34 lr: 0.000023 grad: 0.1204 (0.1307) loss: 0.8362 (0.8368) time: 0.1945 data: 0.1296 max mem: 8255 +Train: [73] [2000/6250] eta: 0:10:16 lr: 0.000023 grad: 0.1218 (0.1303) loss: 0.8402 (0.8369) time: 0.1336 data: 0.0590 max mem: 8255 +Train: [73] [2100/6250] eta: 0:10:02 lr: 0.000023 grad: 0.1150 (0.1299) loss: 0.8458 (0.8371) time: 0.1568 data: 0.0762 max mem: 8255 +Train: [73] [2200/6250] eta: 0:09:50 lr: 0.000023 grad: 0.1189 (0.1295) loss: 0.8376 (0.8372) time: 0.1030 data: 0.0347 max mem: 8255 +Train: [73] [2300/6250] eta: 0:09:34 lr: 0.000023 grad: 0.1219 (0.1293) loss: 0.8332 (0.8373) time: 0.1545 data: 0.0797 max mem: 8255 +Train: [73] [2400/6250] eta: 0:09:23 lr: 0.000023 grad: 0.1288 (0.1292) loss: 0.8267 (0.8375) time: 0.1703 data: 0.0887 max mem: 8255 +Train: [73] [2500/6250] eta: 0:09:09 lr: 0.000023 grad: 0.1164 (0.1290) loss: 0.8498 (0.8376) time: 0.0972 data: 0.0004 max mem: 8255 +Train: [73] [2600/6250] eta: 0:08:52 lr: 0.000023 grad: 0.1239 (0.1288) loss: 0.8412 (0.8377) time: 0.1303 data: 0.0558 max mem: 8255 +Train: [73] [2700/6250] eta: 0:08:37 lr: 0.000023 grad: 0.1270 (0.1287) loss: 0.8412 (0.8378) time: 0.1567 data: 0.0937 max mem: 8255 +Train: [73] [2800/6250] eta: 0:08:20 lr: 0.000023 grad: 0.1190 (0.1285) loss: 0.8371 (0.8378) time: 0.1385 data: 0.0719 max mem: 8255 +Train: [73] [2900/6250] eta: 0:08:09 lr: 0.000023 grad: 0.1142 (0.1284) loss: 0.8413 (0.8376) time: 0.0876 data: 0.0002 max mem: 8255 +Train: [73] [3000/6250] eta: 0:07:52 lr: 0.000023 grad: 0.1222 (0.1283) loss: 0.8360 (0.8376) time: 0.1244 data: 0.0516 max mem: 8255 +Train: [73] [3100/6250] eta: 0:07:36 lr: 0.000023 grad: 0.1234 (0.1282) loss: 0.8332 (0.8374) time: 0.1206 data: 0.0476 max mem: 8255 +Train: [73] [3200/6250] eta: 0:07:20 lr: 0.000022 grad: 0.1203 (0.1281) loss: 0.8394 (0.8374) time: 0.1371 data: 0.0633 max mem: 8255 +Train: [73] [3300/6250] eta: 0:07:06 lr: 0.000022 grad: 0.1239 (0.1280) loss: 0.8394 (0.8374) time: 0.1127 data: 0.0318 max mem: 8255 +Train: [73] [3400/6250] eta: 0:06:52 lr: 0.000022 grad: 0.1173 (0.1279) loss: 0.8389 (0.8374) time: 0.1733 data: 0.1107 max mem: 8255 +Train: [73] [3500/6250] eta: 0:06:36 lr: 0.000022 grad: 0.1331 (0.1279) loss: 0.8362 (0.8374) time: 0.1260 data: 0.0570 max mem: 8255 +Train: [73] [3600/6250] eta: 0:06:24 lr: 0.000022 grad: 0.1156 (0.1279) loss: 0.8388 (0.8374) time: 0.1194 data: 0.0367 max mem: 8255 +Train: [73] [3700/6250] eta: 0:06:08 lr: 0.000022 grad: 0.1157 (0.1277) loss: 0.8425 (0.8374) time: 0.1355 data: 0.0655 max mem: 8255 +Train: [73] [3800/6250] eta: 0:05:52 lr: 0.000022 grad: 0.1212 (0.1277) loss: 0.8294 (0.8374) time: 0.1456 data: 0.0686 max mem: 8255 +Train: [73] [3900/6250] eta: 0:05:38 lr: 0.000022 grad: 0.1197 (0.1277) loss: 0.8392 (0.8374) time: 0.0965 data: 0.0066 max mem: 8255 +Train: [73] [4000/6250] eta: 0:05:22 lr: 0.000022 grad: 0.1226 (0.1276) loss: 0.8381 (0.8374) time: 0.1326 data: 0.0635 max mem: 8255 +Train: [73] [4100/6250] eta: 0:05:08 lr: 0.000022 grad: 0.1247 (0.1276) loss: 0.8348 (0.8375) time: 0.1372 data: 0.0673 max mem: 8255 +Train: [73] [4200/6250] eta: 0:04:54 lr: 0.000022 grad: 0.1200 (0.1275) loss: 0.8348 (0.8375) time: 0.1405 data: 0.0692 max mem: 8255 +Train: [73] [4300/6250] eta: 0:04:39 lr: 0.000022 grad: 0.1328 (0.1277) loss: 0.8243 (0.8373) time: 0.1319 data: 0.0688 max mem: 8255 +Train: [73] [4400/6250] eta: 0:04:25 lr: 0.000022 grad: 0.1320 (0.1276) loss: 0.8321 (0.8373) time: 0.1409 data: 0.0724 max mem: 8255 +Train: [73] [4500/6250] eta: 0:04:10 lr: 0.000022 grad: 0.1204 (0.1276) loss: 0.8365 (0.8372) time: 0.1258 data: 0.0511 max mem: 8255 +Train: [73] [4600/6250] eta: 0:03:56 lr: 0.000022 grad: 0.1176 (0.1276) loss: 0.8347 (0.8372) time: 0.1252 data: 0.0566 max mem: 8255 +Train: [73] [4700/6250] eta: 0:03:41 lr: 0.000022 grad: 0.1263 (0.1277) loss: 0.8375 (0.8371) time: 0.1657 data: 0.0966 max mem: 8255 +Train: [73] [4800/6250] eta: 0:03:26 lr: 0.000022 grad: 0.1261 (0.1277) loss: 0.8381 (0.8370) time: 0.1236 data: 0.0439 max mem: 8255 +Train: [73] [4900/6250] eta: 0:03:12 lr: 0.000022 grad: 0.1238 (0.1277) loss: 0.8415 (0.8370) time: 0.2101 data: 0.1053 max mem: 8255 +Train: [73] [5000/6250] eta: 0:02:58 lr: 0.000022 grad: 0.1257 (0.1277) loss: 0.8329 (0.8369) time: 0.1164 data: 0.0415 max mem: 8255 +Train: [73] [5100/6250] eta: 0:02:43 lr: 0.000022 grad: 0.1332 (0.1278) loss: 0.8321 (0.8369) time: 0.1466 data: 0.0752 max mem: 8255 +Train: [73] [5200/6250] eta: 0:02:29 lr: 0.000022 grad: 0.1273 (0.1278) loss: 0.8368 (0.8368) time: 0.1144 data: 0.0434 max mem: 8255 +Train: [73] [5300/6250] eta: 0:02:14 lr: 0.000022 grad: 0.1208 (0.1278) loss: 0.8314 (0.8368) time: 0.1331 data: 0.0629 max mem: 8255 +Train: [73] [5400/6250] eta: 0:02:00 lr: 0.000022 grad: 0.1228 (0.1278) loss: 0.8328 (0.8368) time: 0.1491 data: 0.0815 max mem: 8255 +Train: [73] [5500/6250] eta: 0:01:46 lr: 0.000022 grad: 0.1206 (0.1277) loss: 0.8338 (0.8367) time: 0.1282 data: 0.0585 max mem: 8255 +Train: [73] [5600/6250] eta: 0:01:32 lr: 0.000022 grad: 0.1265 (0.1277) loss: 0.8407 (0.8367) time: 0.1629 data: 0.0954 max mem: 8255 +Train: [73] [5700/6250] eta: 0:01:17 lr: 0.000022 grad: 0.1206 (0.1277) loss: 0.8373 (0.8368) time: 0.1538 data: 0.0903 max mem: 8255 +Train: [73] [5800/6250] eta: 0:01:03 lr: 0.000022 grad: 0.1244 (0.1277) loss: 0.8369 (0.8368) time: 0.1454 data: 0.0759 max mem: 8255 +Train: [73] [5900/6250] eta: 0:00:49 lr: 0.000022 grad: 0.1173 (0.1276) loss: 0.8379 (0.8368) time: 0.1605 data: 0.0897 max mem: 8255 +Train: [73] [6000/6250] eta: 0:00:35 lr: 0.000022 grad: 0.1238 (0.1277) loss: 0.8292 (0.8368) time: 0.1405 data: 0.0776 max mem: 8255 +Train: [73] [6100/6250] eta: 0:00:21 lr: 0.000022 grad: 0.1227 (0.1276) loss: 0.8278 (0.8368) time: 0.1343 data: 0.0646 max mem: 8255 +Train: [73] [6200/6250] eta: 0:00:07 lr: 0.000022 grad: 0.1300 (0.1277) loss: 0.8271 (0.8367) time: 0.1482 data: 0.0823 max mem: 8255 +Train: [73] [6249/6250] eta: 0:00:00 lr: 0.000022 grad: 0.1224 (0.1277) loss: 0.8294 (0.8366) time: 0.1458 data: 0.0726 max mem: 8255 +Train: [73] Total time: 0:14:51 (0.1426 s / it) +Averaged stats: lr: 0.000022 grad: 0.1224 (0.1277) loss: 0.8294 (0.8366) +Eval (hcp-train-subset): [73] [ 0/62] eta: 0:04:13 loss: 0.8616 (0.8616) time: 4.0940 data: 4.0317 max mem: 8255 +Eval (hcp-train-subset): [73] [61/62] eta: 0:00:00 loss: 0.8584 (0.8596) time: 0.1225 data: 0.1023 max mem: 8255 +Eval (hcp-train-subset): [73] Total time: 0:00:13 (0.2230 s / it) +Averaged stats (hcp-train-subset): loss: 0.8584 (0.8596) +Eval (hcp-val): [73] [ 0/62] eta: 0:04:22 loss: 0.8673 (0.8673) time: 4.2330 data: 4.2078 max mem: 8255 +Eval (hcp-val): [73] [61/62] eta: 0:00:00 loss: 0.8725 (0.8746) time: 0.0977 data: 0.0774 max mem: 8255 +Eval (hcp-val): [73] Total time: 0:00:12 (0.2053 s / it) +Averaged stats (hcp-val): loss: 0.8725 (0.8746) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +Train: [74] [ 0/6250] eta: 6:27:49 lr: 0.000022 grad: 0.0866 (0.0866) loss: 0.8838 (0.8838) time: 3.7231 data: 3.4920 max mem: 8255 +Train: [74] [ 100/6250] eta: 0:18:59 lr: 0.000022 grad: 0.1246 (0.1564) loss: 0.8558 (0.8669) time: 0.1402 data: 0.0485 max mem: 8255 +Train: [74] [ 200/6250] eta: 0:16:05 lr: 0.000022 grad: 0.1244 (0.1408) loss: 0.8554 (0.8631) time: 0.1133 data: 0.0187 max mem: 8255 +Train: [74] [ 300/6250] eta: 0:14:53 lr: 0.000022 grad: 0.1141 (0.1362) loss: 0.8540 (0.8608) time: 0.1221 data: 0.0395 max mem: 8255 +Train: [74] [ 400/6250] eta: 0:14:21 lr: 0.000022 grad: 0.1283 (0.1346) loss: 0.8545 (0.8583) time: 0.1458 data: 0.0708 max mem: 8255 +Train: [74] [ 500/6250] eta: 0:14:02 lr: 0.000022 grad: 0.1220 (0.1330) loss: 0.8452 (0.8569) time: 0.1363 data: 0.0478 max mem: 8255 +Train: [74] [ 600/6250] eta: 0:13:47 lr: 0.000022 grad: 0.1255 (0.1323) loss: 0.8492 (0.8558) time: 0.1350 data: 0.0597 max mem: 8255 +Train: [74] [ 700/6250] eta: 0:13:31 lr: 0.000022 grad: 0.1272 (0.1313) loss: 0.8452 (0.8545) time: 0.1441 data: 0.0649 max mem: 8255 +Train: [74] [ 800/6250] eta: 0:13:13 lr: 0.000022 grad: 0.1256 (0.1306) loss: 0.8420 (0.8534) time: 0.1181 data: 0.0363 max mem: 8255 +Train: [74] [ 900/6250] eta: 0:12:49 lr: 0.000021 grad: 0.1166 (0.1298) loss: 0.8480 (0.8526) time: 0.1343 data: 0.0569 max mem: 8255 +Train: [74] [1000/6250] eta: 0:12:21 lr: 0.000021 grad: 0.1181 (0.1292) loss: 0.8377 (0.8519) time: 0.1209 data: 0.0507 max mem: 8255 +Train: [74] [1100/6250] eta: 0:11:54 lr: 0.000021 grad: 0.1225 (0.1285) loss: 0.8464 (0.8513) time: 0.1178 data: 0.0446 max mem: 8255 +Train: [74] [1200/6250] eta: 0:11:30 lr: 0.000021 grad: 0.1188 (0.1279) loss: 0.8466 (0.8508) time: 0.1105 data: 0.0274 max mem: 8255 +Train: [74] [1300/6250] eta: 0:11:11 lr: 0.000021 grad: 0.1190 (0.1277) loss: 0.8396 (0.8503) time: 0.1366 data: 0.0680 max mem: 8255 +Train: [74] [1400/6250] eta: 0:10:51 lr: 0.000021 grad: 0.1240 (0.1275) loss: 0.8423 (0.8497) time: 0.1144 data: 0.0366 max mem: 8255 +Train: [74] [1500/6250] eta: 0:10:32 lr: 0.000021 grad: 0.1182 (0.1272) loss: 0.8368 (0.8490) time: 0.1156 data: 0.0438 max mem: 8255 +Train: [74] [1600/6250] eta: 0:10:14 lr: 0.000021 grad: 0.1256 (0.1271) loss: 0.8340 (0.8483) time: 0.1062 data: 0.0337 max mem: 8255 +Train: [74] [1700/6250] eta: 0:09:56 lr: 0.000021 grad: 0.1306 (0.1271) loss: 0.8346 (0.8477) time: 0.1046 data: 0.0277 max mem: 8255 +Train: [74] [1800/6250] eta: 0:09:40 lr: 0.000021 grad: 0.1250 (0.1270) loss: 0.8373 (0.8473) time: 0.1326 data: 0.0616 max mem: 8255 +Train: [74] [1900/6250] eta: 0:09:26 lr: 0.000021 grad: 0.1314 (0.1271) loss: 0.8435 (0.8467) time: 0.1275 data: 0.0496 max mem: 8255 +Train: [74] [2000/6250] eta: 0:09:12 lr: 0.000021 grad: 0.1261 (0.1270) loss: 0.8295 (0.8463) time: 0.1278 data: 0.0470 max mem: 8255 +Train: [74] [2100/6250] eta: 0:09:01 lr: 0.000021 grad: 0.1244 (0.1271) loss: 0.8360 (0.8458) time: 0.1608 data: 0.0908 max mem: 8255 +Train: [74] [2200/6250] eta: 0:08:47 lr: 0.000021 grad: 0.1214 (0.1271) loss: 0.8360 (0.8454) time: 0.1279 data: 0.0432 max mem: 8255 +Train: [74] [2300/6250] eta: 0:08:34 lr: 0.000021 grad: 0.1220 (0.1272) loss: 0.8348 (0.8449) time: 0.0984 data: 0.0108 max mem: 8255 +Train: [74] [2400/6250] eta: 0:08:19 lr: 0.000021 grad: 0.1274 (0.1272) loss: 0.8313 (0.8447) time: 0.1254 data: 0.0517 max mem: 8255 +Train: [74] [2500/6250] eta: 0:08:04 lr: 0.000021 grad: 0.1211 (0.1271) loss: 0.8411 (0.8443) time: 0.1257 data: 0.0576 max mem: 8255 +Train: [74] [2600/6250] eta: 0:07:49 lr: 0.000021 grad: 0.1234 (0.1271) loss: 0.8369 (0.8442) time: 0.1027 data: 0.0341 max mem: 8255 +Train: [74] [2700/6250] eta: 0:07:35 lr: 0.000021 grad: 0.1223 (0.1271) loss: 0.8363 (0.8439) time: 0.1152 data: 0.0406 max mem: 8255 +Train: [74] [2800/6250] eta: 0:07:21 lr: 0.000021 grad: 0.1228 (0.1271) loss: 0.8392 (0.8438) time: 0.1095 data: 0.0358 max mem: 8255 +Train: [74] [2900/6250] eta: 0:07:07 lr: 0.000021 grad: 0.1206 (0.1270) loss: 0.8382 (0.8437) time: 0.1340 data: 0.0629 max mem: 8255 +Train: [74] [3000/6250] eta: 0:06:52 lr: 0.000021 grad: 0.1252 (0.1269) loss: 0.8358 (0.8436) time: 0.1127 data: 0.0407 max mem: 8255 +Train: [74] [3100/6250] eta: 0:06:39 lr: 0.000021 grad: 0.1198 (0.1269) loss: 0.8482 (0.8436) time: 0.1187 data: 0.0457 max mem: 8255 +Train: [74] [3200/6250] eta: 0:06:25 lr: 0.000021 grad: 0.1177 (0.1268) loss: 0.8433 (0.8435) time: 0.1028 data: 0.0317 max mem: 8255 +Train: [74] [3300/6250] eta: 0:06:12 lr: 0.000021 grad: 0.1230 (0.1267) loss: 0.8383 (0.8434) time: 0.1235 data: 0.0501 max mem: 8255 +Train: [74] [3400/6250] eta: 0:06:00 lr: 0.000021 grad: 0.1264 (0.1268) loss: 0.8385 (0.8433) time: 0.1352 data: 0.0556 max mem: 8255 +Train: [74] [3500/6250] eta: 0:05:47 lr: 0.000021 grad: 0.1214 (0.1268) loss: 0.8372 (0.8432) time: 0.1349 data: 0.0546 max mem: 8255 +Train: [74] [3600/6250] eta: 0:05:34 lr: 0.000021 grad: 0.1265 (0.1268) loss: 0.8431 (0.8431) time: 0.1270 data: 0.0548 max mem: 8255 +Train: [74] [3700/6250] eta: 0:05:21 lr: 0.000021 grad: 0.1219 (0.1268) loss: 0.8403 (0.8429) time: 0.1216 data: 0.0502 max mem: 8255 +Train: [74] [3800/6250] eta: 0:05:09 lr: 0.000021 grad: 0.1227 (0.1267) loss: 0.8416 (0.8428) time: 0.1353 data: 0.0664 max mem: 8255 +Train: [74] [3900/6250] eta: 0:04:56 lr: 0.000021 grad: 0.1300 (0.1266) loss: 0.8420 (0.8429) time: 0.1385 data: 0.0602 max mem: 8255 +Train: [74] [4000/6250] eta: 0:04:44 lr: 0.000021 grad: 0.1222 (0.1266) loss: 0.8379 (0.8428) time: 0.1110 data: 0.0475 max mem: 8255 +Train: [74] [4100/6250] eta: 0:04:32 lr: 0.000021 grad: 0.1184 (0.1266) loss: 0.8356 (0.8427) time: 0.1247 data: 0.0570 max mem: 8255 +Train: [74] [4200/6250] eta: 0:04:19 lr: 0.000021 grad: 0.1210 (0.1265) loss: 0.8400 (0.8426) time: 0.1254 data: 0.0547 max mem: 8255 +Train: [74] [4300/6250] eta: 0:04:07 lr: 0.000021 grad: 0.1209 (0.1265) loss: 0.8415 (0.8426) time: 0.1422 data: 0.0680 max mem: 8255 +Train: [74] [4400/6250] eta: 0:03:55 lr: 0.000021 grad: 0.1217 (0.1264) loss: 0.8389 (0.8425) time: 0.1881 data: 0.1119 max mem: 8255 +Train: [74] [4500/6250] eta: 0:03:42 lr: 0.000021 grad: 0.1189 (0.1264) loss: 0.8395 (0.8423) time: 0.1195 data: 0.0501 max mem: 8255 +Train: [74] [4600/6250] eta: 0:03:29 lr: 0.000021 grad: 0.1191 (0.1264) loss: 0.8361 (0.8423) time: 0.1147 data: 0.0394 max mem: 8255 +Train: [74] [4700/6250] eta: 0:03:17 lr: 0.000021 grad: 0.1236 (0.1263) loss: 0.8391 (0.8422) time: 0.1327 data: 0.0556 max mem: 8255 +Train: [74] [4800/6250] eta: 0:03:04 lr: 0.000021 grad: 0.1206 (0.1262) loss: 0.8393 (0.8422) time: 0.1473 data: 0.0461 max mem: 8255 +Train: [74] [4900/6250] eta: 0:02:52 lr: 0.000020 grad: 0.1207 (0.1263) loss: 0.8368 (0.8422) time: 0.1825 data: 0.1027 max mem: 8255 +Train: [74] [5000/6250] eta: 0:02:39 lr: 0.000020 grad: 0.1256 (0.1263) loss: 0.8399 (0.8422) time: 0.1271 data: 0.0606 max mem: 8255 +Train: [74] [5100/6250] eta: 0:02:27 lr: 0.000020 grad: 0.1284 (0.1263) loss: 0.8421 (0.8422) time: 0.1695 data: 0.0904 max mem: 8255 +Train: [74] [5200/6250] eta: 0:02:14 lr: 0.000020 grad: 0.1246 (0.1263) loss: 0.8306 (0.8422) time: 0.1364 data: 0.0640 max mem: 8255 +Train: [74] [5300/6250] eta: 0:02:02 lr: 0.000020 grad: 0.1254 (0.1264) loss: 0.8285 (0.8421) time: 0.0910 data: 0.0002 max mem: 8255 +Train: [74] [5400/6250] eta: 0:01:49 lr: 0.000020 grad: 0.1234 (0.1265) loss: 0.8373 (0.8419) time: 0.1162 data: 0.0467 max mem: 8255 +Train: [74] [5500/6250] eta: 0:01:36 lr: 0.000020 grad: 0.1228 (0.1266) loss: 0.8374 (0.8418) time: 0.1192 data: 0.0415 max mem: 8255 +Train: [74] [5600/6250] eta: 0:01:23 lr: 0.000020 grad: 0.1367 (0.1268) loss: 0.8293 (0.8417) time: 0.0915 data: 0.0092 max mem: 8255 +Train: [74] [5700/6250] eta: 0:01:10 lr: 0.000020 grad: 0.1270 (0.1268) loss: 0.8342 (0.8415) time: 0.1227 data: 0.0525 max mem: 8255 +Train: [74] [5800/6250] eta: 0:00:57 lr: 0.000020 grad: 0.1277 (0.1268) loss: 0.8366 (0.8414) time: 0.0919 data: 0.0132 max mem: 8255 +Train: [74] [5900/6250] eta: 0:00:44 lr: 0.000020 grad: 0.1273 (0.1269) loss: 0.8286 (0.8413) time: 0.1225 data: 0.0495 max mem: 8255 +Train: [74] [6000/6250] eta: 0:00:32 lr: 0.000020 grad: 0.1327 (0.1269) loss: 0.8354 (0.8412) time: 0.1244 data: 0.0538 max mem: 8255 +Train: [74] [6100/6250] eta: 0:00:19 lr: 0.000020 grad: 0.1274 (0.1270) loss: 0.8421 (0.8411) time: 0.1240 data: 0.0524 max mem: 8255 +Train: [74] [6200/6250] eta: 0:00:06 lr: 0.000020 grad: 0.1328 (0.1270) loss: 0.8366 (0.8410) time: 0.1464 data: 0.0798 max mem: 8255 +Train: [74] [6249/6250] eta: 0:00:00 lr: 0.000020 grad: 0.1279 (0.1271) loss: 0.8469 (0.8410) time: 0.1239 data: 0.0545 max mem: 8255 +Train: [74] Total time: 0:13:26 (0.1290 s / it) +Averaged stats: lr: 0.000020 grad: 0.1279 (0.1271) loss: 0.8469 (0.8410) +Eval (hcp-train-subset): [74] [ 0/62] eta: 0:04:06 loss: 0.8580 (0.8580) time: 3.9757 data: 3.9050 max mem: 8255 +Eval (hcp-train-subset): [74] [61/62] eta: 0:00:00 loss: 0.8573 (0.8583) time: 0.1332 data: 0.1124 max mem: 8255 +Eval (hcp-train-subset): [74] Total time: 0:00:13 (0.2253 s / it) +Averaged stats (hcp-train-subset): loss: 0.8573 (0.8583) +Making plots (hcp-train-subset): example=30 +Eval (hcp-val): [74] [ 0/62] eta: 0:10:13 loss: 0.8705 (0.8705) time: 9.8991 data: 9.8772 max mem: 8255 +Eval (hcp-val): [74] [61/62] eta: 0:00:00 loss: 0.8738 (0.8742) time: 0.1070 data: 0.0853 max mem: 8255 +Eval (hcp-val): [74] Total time: 0:00:17 (0.2781 s / it) +Averaged stats (hcp-val): loss: 0.8738 (0.8742) +Making plots (hcp-val): example=48 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +Train: [75] [ 0/6250] eta: 8:48:40 lr: 0.000020 grad: 0.3244 (0.3244) loss: 0.7950 (0.7950) time: 5.0754 data: 4.8084 max mem: 8255 +Train: [75] [ 100/6250] eta: 0:22:34 lr: 0.000020 grad: 0.1689 (0.1861) loss: 0.8322 (0.8493) time: 0.1356 data: 0.0455 max mem: 8255 +Train: [75] [ 200/6250] eta: 0:19:20 lr: 0.000020 grad: 0.1362 (0.1664) loss: 0.8608 (0.8512) time: 0.1475 data: 0.0594 max mem: 8255 +Train: [75] [ 300/6250] eta: 0:17:44 lr: 0.000020 grad: 0.1399 (0.1607) loss: 0.8428 (0.8498) time: 0.1355 data: 0.0549 max mem: 8255 +Train: [75] [ 400/6250] eta: 0:16:51 lr: 0.000020 grad: 0.1420 (0.1566) loss: 0.8429 (0.8476) time: 0.1554 data: 0.0720 max mem: 8255 +Train: [75] [ 500/6250] eta: 0:16:03 lr: 0.000020 grad: 0.1394 (0.1526) loss: 0.8439 (0.8469) time: 0.1551 data: 0.0755 max mem: 8255 +Train: [75] [ 600/6250] eta: 0:15:21 lr: 0.000020 grad: 0.1266 (0.1506) loss: 0.8448 (0.8466) time: 0.1349 data: 0.0450 max mem: 8255 +Train: [75] [ 700/6250] eta: 0:14:41 lr: 0.000020 grad: 0.1260 (0.1477) loss: 0.8446 (0.8465) time: 0.1287 data: 0.0445 max mem: 8255 +Train: [75] [ 800/6250] eta: 0:14:05 lr: 0.000020 grad: 0.1285 (0.1453) loss: 0.8450 (0.8465) time: 0.1187 data: 0.0344 max mem: 8255 +Train: [75] [ 900/6250] eta: 0:13:59 lr: 0.000020 grad: 0.1254 (0.1434) loss: 0.8527 (0.8459) time: 0.2184 data: 0.1347 max mem: 8255 +Train: [75] [1000/6250] eta: 0:13:46 lr: 0.000020 grad: 0.1243 (0.1419) loss: 0.8418 (0.8455) time: 0.1698 data: 0.0967 max mem: 8255 +Train: [75] [1100/6250] eta: 0:13:39 lr: 0.000020 grad: 0.1185 (0.1402) loss: 0.8396 (0.8451) time: 0.2296 data: 0.1616 max mem: 8255 +Train: [75] [1200/6250] eta: 0:13:26 lr: 0.000020 grad: 0.1188 (0.1390) loss: 0.8413 (0.8447) time: 0.1403 data: 0.0653 max mem: 8255 +Train: [75] [1300/6250] eta: 0:13:11 lr: 0.000020 grad: 0.1198 (0.1378) loss: 0.8377 (0.8444) time: 0.1642 data: 0.0981 max mem: 8255 +Train: [75] [1400/6250] eta: 0:12:44 lr: 0.000020 grad: 0.1265 (0.1369) loss: 0.8405 (0.8441) time: 0.1180 data: 0.0406 max mem: 8255 +Train: [75] [1500/6250] eta: 0:12:33 lr: 0.000020 grad: 0.1218 (0.1361) loss: 0.8395 (0.8438) time: 0.2886 data: 0.1918 max mem: 8255 +Train: [75] [1600/6250] eta: 0:12:07 lr: 0.000020 grad: 0.1236 (0.1354) loss: 0.8344 (0.8436) time: 0.1554 data: 0.0703 max mem: 8255 +Train: [75] [1700/6250] eta: 0:11:48 lr: 0.000020 grad: 0.1227 (0.1347) loss: 0.8331 (0.8433) time: 0.1353 data: 0.0601 max mem: 8255 +Train: [75] [1800/6250] eta: 0:11:33 lr: 0.000020 grad: 0.1219 (0.1341) loss: 0.8405 (0.8431) time: 0.1844 data: 0.0601 max mem: 8255 +Train: [75] [1900/6250] eta: 0:11:15 lr: 0.000020 grad: 0.1234 (0.1336) loss: 0.8421 (0.8429) time: 0.1345 data: 0.0490 max mem: 8255 +Train: [75] [2000/6250] eta: 0:10:59 lr: 0.000020 grad: 0.1196 (0.1330) loss: 0.8378 (0.8429) time: 0.1980 data: 0.1144 max mem: 8255 +Train: [75] [2100/6250] eta: 0:10:43 lr: 0.000020 grad: 0.1229 (0.1326) loss: 0.8403 (0.8429) time: 0.1470 data: 0.0766 max mem: 8255 +Train: [75] [2200/6250] eta: 0:10:29 lr: 0.000020 grad: 0.1215 (0.1322) loss: 0.8480 (0.8428) time: 0.2795 data: 0.1979 max mem: 8255 +Train: [75] [2300/6250] eta: 0:10:08 lr: 0.000020 grad: 0.1236 (0.1320) loss: 0.8436 (0.8429) time: 0.1297 data: 0.0534 max mem: 8255 +Train: [75] [2400/6250] eta: 0:09:49 lr: 0.000020 grad: 0.1174 (0.1318) loss: 0.8408 (0.8427) time: 0.1337 data: 0.0597 max mem: 8255 +Train: [75] [2500/6250] eta: 0:09:31 lr: 0.000020 grad: 0.1242 (0.1316) loss: 0.8359 (0.8425) time: 0.1364 data: 0.0673 max mem: 8255 +Train: [75] [2600/6250] eta: 0:09:11 lr: 0.000020 grad: 0.1248 (0.1314) loss: 0.8329 (0.8424) time: 0.1273 data: 0.0557 max mem: 8255 +Train: [75] [2700/6250] eta: 0:08:53 lr: 0.000020 grad: 0.1230 (0.1313) loss: 0.8398 (0.8424) time: 0.1295 data: 0.0651 max mem: 8255 +Train: [75] [2800/6250] eta: 0:08:36 lr: 0.000019 grad: 0.1278 (0.1311) loss: 0.8337 (0.8423) time: 0.1356 data: 0.0680 max mem: 8255 +Train: [75] [2900/6250] eta: 0:08:18 lr: 0.000019 grad: 0.1237 (0.1308) loss: 0.8408 (0.8423) time: 0.1265 data: 0.0542 max mem: 8255 +Train: [75] [3000/6250] eta: 0:08:01 lr: 0.000019 grad: 0.1206 (0.1306) loss: 0.8397 (0.8422) time: 0.1246 data: 0.0460 max mem: 8255 +Train: [75] [3100/6250] eta: 0:07:45 lr: 0.000019 grad: 0.1152 (0.1304) loss: 0.8479 (0.8422) time: 0.1443 data: 0.0647 max mem: 8255 +Train: [75] [3200/6250] eta: 0:07:30 lr: 0.000019 grad: 0.1201 (0.1304) loss: 0.8437 (0.8421) time: 0.1909 data: 0.1241 max mem: 8255 +Train: [75] [3300/6250] eta: 0:07:13 lr: 0.000019 grad: 0.1292 (0.1304) loss: 0.8333 (0.8419) time: 0.1334 data: 0.0644 max mem: 8255 +Train: [75] [3400/6250] eta: 0:06:57 lr: 0.000019 grad: 0.1307 (0.1304) loss: 0.8374 (0.8418) time: 0.1332 data: 0.0633 max mem: 8255 +Train: [75] [3500/6250] eta: 0:06:41 lr: 0.000019 grad: 0.1236 (0.1305) loss: 0.8338 (0.8416) time: 0.1398 data: 0.0770 max mem: 8255 +Train: [75] [3600/6250] eta: 0:06:28 lr: 0.000019 grad: 0.1282 (0.1304) loss: 0.8402 (0.8414) time: 0.1303 data: 0.0552 max mem: 8255 +Train: [75] [3700/6250] eta: 0:06:13 lr: 0.000019 grad: 0.1317 (0.1304) loss: 0.8308 (0.8412) time: 0.0994 data: 0.0218 max mem: 8255 +Train: [75] [3800/6250] eta: 0:05:58 lr: 0.000019 grad: 0.1228 (0.1304) loss: 0.8359 (0.8411) time: 0.1863 data: 0.1064 max mem: 8255 +Train: [75] [3900/6250] eta: 0:05:42 lr: 0.000019 grad: 0.1251 (0.1303) loss: 0.8318 (0.8409) time: 0.1381 data: 0.0722 max mem: 8255 +Train: [75] [4000/6250] eta: 0:05:27 lr: 0.000019 grad: 0.1283 (0.1302) loss: 0.8290 (0.8408) time: 0.1207 data: 0.0529 max mem: 8255 +Train: [75] [4100/6250] eta: 0:05:11 lr: 0.000019 grad: 0.1281 (0.1302) loss: 0.8410 (0.8406) time: 0.1301 data: 0.0531 max mem: 8255 +Train: [75] [4200/6250] eta: 0:04:56 lr: 0.000019 grad: 0.1283 (0.1302) loss: 0.8323 (0.8405) time: 0.1310 data: 0.0587 max mem: 8255 +Train: [75] [4300/6250] eta: 0:04:41 lr: 0.000019 grad: 0.1283 (0.1302) loss: 0.8336 (0.8405) time: 0.1360 data: 0.0616 max mem: 8255 +Train: [75] [4400/6250] eta: 0:04:27 lr: 0.000019 grad: 0.1387 (0.1303) loss: 0.8319 (0.8403) time: 0.2067 data: 0.1386 max mem: 8255 +Train: [75] [4500/6250] eta: 0:04:12 lr: 0.000019 grad: 0.1280 (0.1303) loss: 0.8345 (0.8402) time: 0.1424 data: 0.0777 max mem: 8255 +Train: [75] [4600/6250] eta: 0:03:57 lr: 0.000019 grad: 0.1280 (0.1303) loss: 0.8328 (0.8401) time: 0.1302 data: 0.0616 max mem: 8255 +Train: [75] [4700/6250] eta: 0:03:42 lr: 0.000019 grad: 0.1343 (0.1304) loss: 0.8253 (0.8399) time: 0.1205 data: 0.0343 max mem: 8255 +Train: [75] [4800/6250] eta: 0:03:27 lr: 0.000019 grad: 0.1346 (0.1304) loss: 0.8181 (0.8398) time: 0.1250 data: 0.0577 max mem: 8255 +Train: [75] [4900/6250] eta: 0:03:12 lr: 0.000019 grad: 0.1404 (0.1304) loss: 0.8343 (0.8398) time: 0.1209 data: 0.0514 max mem: 8255 +Train: [75] [5000/6250] eta: 0:02:58 lr: 0.000019 grad: 0.1236 (0.1304) loss: 0.8390 (0.8396) time: 0.1299 data: 0.0494 max mem: 8255 +Train: [75] [5100/6250] eta: 0:02:43 lr: 0.000019 grad: 0.1354 (0.1304) loss: 0.8290 (0.8396) time: 0.1368 data: 0.0747 max mem: 8255 +Train: [75] [5200/6250] eta: 0:02:29 lr: 0.000019 grad: 0.1301 (0.1304) loss: 0.8352 (0.8395) time: 0.1142 data: 0.0441 max mem: 8255 +Train: [75] [5300/6250] eta: 0:02:15 lr: 0.000019 grad: 0.1290 (0.1305) loss: 0.8391 (0.8394) time: 0.1660 data: 0.0914 max mem: 8255 +Train: [75] [5400/6250] eta: 0:02:00 lr: 0.000019 grad: 0.1262 (0.1306) loss: 0.8297 (0.8392) time: 0.1127 data: 0.0300 max mem: 8255 +Train: [75] [5500/6250] eta: 0:01:46 lr: 0.000019 grad: 0.1317 (0.1306) loss: 0.8313 (0.8391) time: 0.1124 data: 0.0409 max mem: 8255 +Train: [75] [5600/6250] eta: 0:01:32 lr: 0.000019 grad: 0.1236 (0.1306) loss: 0.8343 (0.8390) time: 0.1306 data: 0.0571 max mem: 8255 +Train: [75] [5700/6250] eta: 0:01:17 lr: 0.000019 grad: 0.1270 (0.1306) loss: 0.8249 (0.8389) time: 0.1227 data: 0.0530 max mem: 8255 +Train: [75] [5800/6250] eta: 0:01:03 lr: 0.000019 grad: 0.1291 (0.1306) loss: 0.8289 (0.8388) time: 0.1426 data: 0.0742 max mem: 8255 +Train: [75] [5900/6250] eta: 0:00:49 lr: 0.000019 grad: 0.1193 (0.1306) loss: 0.8426 (0.8388) time: 0.1471 data: 0.0795 max mem: 8255 +Train: [75] [6000/6250] eta: 0:00:35 lr: 0.000019 grad: 0.1313 (0.1305) loss: 0.8344 (0.8388) time: 0.0933 data: 0.0002 max mem: 8255 +Train: [75] [6100/6250] eta: 0:00:21 lr: 0.000019 grad: 0.1302 (0.1306) loss: 0.8354 (0.8387) time: 0.1290 data: 0.0586 max mem: 8255 +Train: [75] [6200/6250] eta: 0:00:07 lr: 0.000019 grad: 0.1352 (0.1306) loss: 0.8325 (0.8386) time: 0.1277 data: 0.0516 max mem: 8255 +Train: [75] [6249/6250] eta: 0:00:00 lr: 0.000019 grad: 0.1247 (0.1306) loss: 0.8328 (0.8386) time: 0.1421 data: 0.0711 max mem: 8255 +Train: [75] Total time: 0:14:49 (0.1423 s / it) +Averaged stats: lr: 0.000019 grad: 0.1247 (0.1306) loss: 0.8328 (0.8386) +Eval (hcp-train-subset): [75] [ 0/62] eta: 0:05:11 loss: 0.8623 (0.8623) time: 5.0223 data: 4.9967 max mem: 8255 +Eval (hcp-train-subset): [75] [61/62] eta: 0:00:00 loss: 0.8564 (0.8587) time: 0.1221 data: 0.1004 max mem: 8255 +Eval (hcp-train-subset): [75] Total time: 0:00:12 (0.1952 s / it) +Averaged stats (hcp-train-subset): loss: 0.8564 (0.8587) +Eval (hcp-val): [75] [ 0/62] eta: 0:03:57 loss: 0.8697 (0.8697) time: 3.8300 data: 3.7782 max mem: 8255 +Eval (hcp-val): [75] [61/62] eta: 0:00:00 loss: 0.8732 (0.8749) time: 0.1404 data: 0.1193 max mem: 8255 +Eval (hcp-val): [75] Total time: 0:00:13 (0.2213 s / it) +Averaged stats (hcp-val): loss: 0.8732 (0.8749) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +Train: [76] [ 0/6250] eta: 10:57:05 lr: 0.000019 grad: 0.2593 (0.2593) loss: 0.8520 (0.8520) time: 6.3081 data: 6.2183 max mem: 8255 +Train: [76] [ 100/6250] eta: 0:20:30 lr: 0.000019 grad: 0.1330 (0.1541) loss: 0.8395 (0.8536) time: 0.1556 data: 0.0693 max mem: 8255 +Train: [76] [ 200/6250] eta: 0:17:25 lr: 0.000019 grad: 0.1260 (0.1465) loss: 0.8527 (0.8491) time: 0.1656 data: 0.0906 max mem: 8255 +Train: [76] [ 300/6250] eta: 0:15:49 lr: 0.000019 grad: 0.1262 (0.1437) loss: 0.8464 (0.8479) time: 0.1433 data: 0.0627 max mem: 8255 +Train: [76] [ 400/6250] eta: 0:14:52 lr: 0.000019 grad: 0.1219 (0.1414) loss: 0.8432 (0.8477) time: 0.1586 data: 0.0701 max mem: 8255 +Train: [76] [ 500/6250] eta: 0:14:40 lr: 0.000019 grad: 0.1285 (0.1392) loss: 0.8387 (0.8468) time: 0.1819 data: 0.0949 max mem: 8255 +Train: [76] [ 600/6250] eta: 0:14:10 lr: 0.000019 grad: 0.1226 (0.1376) loss: 0.8386 (0.8461) time: 0.1438 data: 0.0624 max mem: 8255 +Train: [76] [ 700/6250] eta: 0:13:56 lr: 0.000019 grad: 0.1225 (0.1364) loss: 0.8500 (0.8462) time: 0.1671 data: 0.0935 max mem: 8255 +Train: [76] [ 800/6250] eta: 0:13:28 lr: 0.000018 grad: 0.1222 (0.1349) loss: 0.8458 (0.8460) time: 0.1406 data: 0.0598 max mem: 8255 +Train: [76] [ 900/6250] eta: 0:13:03 lr: 0.000018 grad: 0.1174 (0.1342) loss: 0.8437 (0.8460) time: 0.1302 data: 0.0477 max mem: 8255 +Train: [76] [1000/6250] eta: 0:12:48 lr: 0.000018 grad: 0.1180 (0.1331) loss: 0.8445 (0.8462) time: 0.1482 data: 0.0661 max mem: 8255 +Train: [76] [1100/6250] eta: 0:12:36 lr: 0.000018 grad: 0.1180 (0.1322) loss: 0.8466 (0.8460) time: 0.1451 data: 0.0657 max mem: 8255 +Train: [76] [1200/6250] eta: 0:12:19 lr: 0.000018 grad: 0.1151 (0.1314) loss: 0.8511 (0.8459) time: 0.1451 data: 0.0737 max mem: 8255 +Train: [76] [1300/6250] eta: 0:12:01 lr: 0.000018 grad: 0.1209 (0.1306) loss: 0.8471 (0.8460) time: 0.1328 data: 0.0566 max mem: 8255 +Train: [76] [1400/6250] eta: 0:11:48 lr: 0.000018 grad: 0.1204 (0.1302) loss: 0.8478 (0.8461) time: 0.1641 data: 0.0900 max mem: 8255 +Train: [76] [1500/6250] eta: 0:11:41 lr: 0.000018 grad: 0.1210 (0.1299) loss: 0.8471 (0.8459) time: 0.1637 data: 0.0546 max mem: 8255 +Train: [76] [1600/6250] eta: 0:11:22 lr: 0.000018 grad: 0.1269 (0.1298) loss: 0.8433 (0.8456) time: 0.1345 data: 0.0603 max mem: 8255 +Train: [76] [1700/6250] eta: 0:11:06 lr: 0.000018 grad: 0.1212 (0.1297) loss: 0.8476 (0.8454) time: 0.1484 data: 0.0662 max mem: 8255 +Train: [76] [1800/6250] eta: 0:10:53 lr: 0.000018 grad: 0.1366 (0.1297) loss: 0.8341 (0.8451) time: 0.1407 data: 0.0498 max mem: 8255 +Train: [76] [1900/6250] eta: 0:10:39 lr: 0.000018 grad: 0.1234 (0.1295) loss: 0.8404 (0.8449) time: 0.1351 data: 0.0525 max mem: 8255 +Train: [76] [2000/6250] eta: 0:10:21 lr: 0.000018 grad: 0.1184 (0.1292) loss: 0.8400 (0.8447) time: 0.1443 data: 0.0678 max mem: 8255 +Train: [76] [2100/6250] eta: 0:10:07 lr: 0.000018 grad: 0.1282 (0.1290) loss: 0.8419 (0.8445) time: 0.1489 data: 0.0703 max mem: 8255 +Train: [76] [2200/6250] eta: 0:09:55 lr: 0.000018 grad: 0.1180 (0.1288) loss: 0.8449 (0.8444) time: 0.1702 data: 0.1016 max mem: 8255 +Train: [76] [2300/6250] eta: 0:09:38 lr: 0.000018 grad: 0.1240 (0.1287) loss: 0.8381 (0.8443) time: 0.1493 data: 0.0742 max mem: 8255 +Train: [76] [2400/6250] eta: 0:09:20 lr: 0.000018 grad: 0.1280 (0.1287) loss: 0.8371 (0.8442) time: 0.1344 data: 0.0548 max mem: 8255 +Train: [76] [2500/6250] eta: 0:09:06 lr: 0.000018 grad: 0.1229 (0.1286) loss: 0.8414 (0.8442) time: 0.1503 data: 0.0709 max mem: 8255 +Train: [76] [2600/6250] eta: 0:08:52 lr: 0.000018 grad: 0.1220 (0.1285) loss: 0.8441 (0.8442) time: 0.1460 data: 0.0795 max mem: 8255 +Train: [76] [2700/6250] eta: 0:08:37 lr: 0.000018 grad: 0.1235 (0.1286) loss: 0.8421 (0.8441) time: 0.1233 data: 0.0488 max mem: 8255 +Train: [76] [2800/6250] eta: 0:08:23 lr: 0.000018 grad: 0.1225 (0.1285) loss: 0.8375 (0.8441) time: 0.1675 data: 0.0936 max mem: 8255 +Train: [76] [2900/6250] eta: 0:08:09 lr: 0.000018 grad: 0.1243 (0.1285) loss: 0.8467 (0.8440) time: 0.1763 data: 0.1083 max mem: 8255 +Train: [76] [3000/6250] eta: 0:07:52 lr: 0.000018 grad: 0.1345 (0.1287) loss: 0.8395 (0.8439) time: 0.1217 data: 0.0431 max mem: 8255 +Train: [76] [3100/6250] eta: 0:07:37 lr: 0.000018 grad: 0.1300 (0.1287) loss: 0.8382 (0.8438) time: 0.1459 data: 0.0487 max mem: 8255 +Train: [76] [3200/6250] eta: 0:07:24 lr: 0.000018 grad: 0.1204 (0.1287) loss: 0.8486 (0.8437) time: 0.1554 data: 0.0758 max mem: 8255 +Train: [76] [3300/6250] eta: 0:07:09 lr: 0.000018 grad: 0.1262 (0.1288) loss: 0.8379 (0.8435) time: 0.1445 data: 0.0696 max mem: 8255 +Train: [76] [3400/6250] eta: 0:06:57 lr: 0.000018 grad: 0.1288 (0.1289) loss: 0.8313 (0.8433) time: 0.3037 data: 0.2313 max mem: 8255 +Train: [76] [3500/6250] eta: 0:06:43 lr: 0.000018 grad: 0.1163 (0.1288) loss: 0.8439 (0.8432) time: 0.1409 data: 0.0642 max mem: 8255 +Train: [76] [3600/6250] eta: 0:06:28 lr: 0.000018 grad: 0.1255 (0.1288) loss: 0.8350 (0.8431) time: 0.1305 data: 0.0554 max mem: 8255 +Train: [76] [3700/6250] eta: 0:06:15 lr: 0.000018 grad: 0.1337 (0.1288) loss: 0.8433 (0.8430) time: 0.2304 data: 0.1563 max mem: 8255 +Train: [76] [3800/6250] eta: 0:05:59 lr: 0.000018 grad: 0.1307 (0.1288) loss: 0.8413 (0.8430) time: 0.1425 data: 0.0590 max mem: 8255 +Train: [76] [3900/6250] eta: 0:05:44 lr: 0.000018 grad: 0.1216 (0.1288) loss: 0.8378 (0.8429) time: 0.1242 data: 0.0532 max mem: 8255 +Train: [76] [4000/6250] eta: 0:05:29 lr: 0.000018 grad: 0.1302 (0.1288) loss: 0.8425 (0.8429) time: 0.1433 data: 0.0758 max mem: 8255 +Train: [76] [4100/6250] eta: 0:05:15 lr: 0.000018 grad: 0.1325 (0.1287) loss: 0.8456 (0.8429) time: 0.2084 data: 0.1179 max mem: 8255 +Train: [76] [4200/6250] eta: 0:05:00 lr: 0.000018 grad: 0.1240 (0.1288) loss: 0.8463 (0.8429) time: 0.1506 data: 0.0706 max mem: 8255 +Train: [76] [4300/6250] eta: 0:04:45 lr: 0.000018 grad: 0.1263 (0.1287) loss: 0.8452 (0.8430) time: 0.1165 data: 0.0426 max mem: 8255 +Train: [76] [4400/6250] eta: 0:04:30 lr: 0.000018 grad: 0.1292 (0.1287) loss: 0.8467 (0.8430) time: 0.1349 data: 0.0580 max mem: 8255 +Train: [76] [4500/6250] eta: 0:04:16 lr: 0.000018 grad: 0.1194 (0.1287) loss: 0.8435 (0.8430) time: 0.1105 data: 0.0254 max mem: 8255 +Train: [76] [4600/6250] eta: 0:04:01 lr: 0.000018 grad: 0.1235 (0.1286) loss: 0.8437 (0.8430) time: 0.1302 data: 0.0553 max mem: 8255 +Train: [76] [4700/6250] eta: 0:03:46 lr: 0.000018 grad: 0.1219 (0.1286) loss: 0.8486 (0.8431) time: 0.1492 data: 0.0714 max mem: 8255 +Train: [76] [4800/6250] eta: 0:03:32 lr: 0.000018 grad: 0.1299 (0.1286) loss: 0.8394 (0.8431) time: 0.1364 data: 0.0623 max mem: 8255 +Train: [76] [4900/6250] eta: 0:03:17 lr: 0.000018 grad: 0.1219 (0.1285) loss: 0.8394 (0.8431) time: 0.1681 data: 0.1034 max mem: 8255 +Train: [76] [5000/6250] eta: 0:03:02 lr: 0.000018 grad: 0.1287 (0.1285) loss: 0.8419 (0.8431) time: 0.1986 data: 0.1244 max mem: 8255 +Train: [76] [5100/6250] eta: 0:02:48 lr: 0.000017 grad: 0.1294 (0.1287) loss: 0.8468 (0.8431) time: 0.1438 data: 0.0639 max mem: 8255 +Train: [76] [5200/6250] eta: 0:02:33 lr: 0.000017 grad: 0.1259 (0.1286) loss: 0.8379 (0.8431) time: 0.1909 data: 0.1183 max mem: 8255 +Train: [76] [5300/6250] eta: 0:02:18 lr: 0.000017 grad: 0.1259 (0.1286) loss: 0.8469 (0.8430) time: 0.1638 data: 0.0832 max mem: 8255 +Train: [76] [5400/6250] eta: 0:02:04 lr: 0.000017 grad: 0.1249 (0.1286) loss: 0.8414 (0.8430) time: 0.1530 data: 0.0657 max mem: 8255 +Train: [76] [5500/6250] eta: 0:01:49 lr: 0.000017 grad: 0.1165 (0.1285) loss: 0.8531 (0.8430) time: 0.1239 data: 0.0366 max mem: 8255 +Train: [76] [5600/6250] eta: 0:01:34 lr: 0.000017 grad: 0.1165 (0.1285) loss: 0.8415 (0.8431) time: 0.1364 data: 0.0688 max mem: 8255 +Train: [76] [5700/6250] eta: 0:01:20 lr: 0.000017 grad: 0.1227 (0.1284) loss: 0.8462 (0.8432) time: 0.1456 data: 0.0784 max mem: 8255 +Train: [76] [5800/6250] eta: 0:01:05 lr: 0.000017 grad: 0.1222 (0.1283) loss: 0.8363 (0.8432) time: 0.1422 data: 0.0542 max mem: 8255 +Train: [76] [5900/6250] eta: 0:00:51 lr: 0.000017 grad: 0.1211 (0.1283) loss: 0.8508 (0.8432) time: 0.1869 data: 0.0922 max mem: 8255 +Train: [76] [6000/6250] eta: 0:00:36 lr: 0.000017 grad: 0.1206 (0.1282) loss: 0.8513 (0.8433) time: 0.1543 data: 0.0678 max mem: 8255 +Train: [76] [6100/6250] eta: 0:00:22 lr: 0.000017 grad: 0.1268 (0.1281) loss: 0.8378 (0.8433) time: 0.2637 data: 0.1622 max mem: 8255 +Train: [76] [6200/6250] eta: 0:00:07 lr: 0.000017 grad: 0.1251 (0.1281) loss: 0.8432 (0.8433) time: 0.1673 data: 0.0710 max mem: 8255 +Train: [76] [6249/6250] eta: 0:00:00 lr: 0.000017 grad: 0.1263 (0.1281) loss: 0.8430 (0.8434) time: 0.1539 data: 0.0721 max mem: 8255 +Train: [76] Total time: 0:15:35 (0.1497 s / it) +Averaged stats: lr: 0.000017 grad: 0.1263 (0.1281) loss: 0.8430 (0.8434) +Eval (hcp-train-subset): [76] [ 0/62] eta: 0:05:30 loss: 0.8587 (0.8587) time: 5.3234 data: 5.2839 max mem: 8255 +Eval (hcp-train-subset): [76] [61/62] eta: 0:00:00 loss: 0.8523 (0.8568) time: 0.1310 data: 0.1103 max mem: 8255 +Eval (hcp-train-subset): [76] Total time: 0:00:16 (0.2587 s / it) +Averaged stats (hcp-train-subset): loss: 0.8523 (0.8568) +Eval (hcp-val): [76] [ 0/62] eta: 0:04:14 loss: 0.8694 (0.8694) time: 4.1044 data: 4.0397 max mem: 8255 +Eval (hcp-val): [76] [61/62] eta: 0:00:00 loss: 0.8727 (0.8742) time: 0.1383 data: 0.1169 max mem: 8255 +Eval (hcp-val): [76] Total time: 0:00:15 (0.2422 s / it) +Averaged stats (hcp-val): loss: 0.8727 (0.8742) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +Train: [77] [ 0/6250] eta: 12:44:06 lr: 0.000017 grad: 0.3385 (0.3385) loss: 0.8764 (0.8764) time: 7.3355 data: 7.2320 max mem: 8255 +Train: [77] [ 100/6250] eta: 0:24:20 lr: 0.000017 grad: 0.1308 (0.1568) loss: 0.8667 (0.8670) time: 0.1861 data: 0.0817 max mem: 8255 +Train: [77] [ 200/6250] eta: 0:20:51 lr: 0.000017 grad: 0.1151 (0.1409) loss: 0.8545 (0.8631) time: 0.1714 data: 0.0795 max mem: 8255 +Train: [77] [ 300/6250] eta: 0:19:25 lr: 0.000017 grad: 0.1178 (0.1374) loss: 0.8531 (0.8595) time: 0.1805 data: 0.0906 max mem: 8255 +Train: [77] [ 400/6250] eta: 0:18:20 lr: 0.000017 grad: 0.1276 (0.1353) loss: 0.8425 (0.8571) time: 0.1603 data: 0.0797 max mem: 8255 +Train: [77] [ 500/6250] eta: 0:17:31 lr: 0.000017 grad: 0.1314 (0.1352) loss: 0.8458 (0.8547) time: 0.1596 data: 0.0671 max mem: 8255 +Train: [77] [ 600/6250] eta: 0:17:07 lr: 0.000017 grad: 0.1210 (0.1343) loss: 0.8496 (0.8537) time: 0.1620 data: 0.0731 max mem: 8255 +Train: [77] [ 700/6250] eta: 0:16:30 lr: 0.000017 grad: 0.1323 (0.1337) loss: 0.8381 (0.8528) time: 0.1709 data: 0.0858 max mem: 8255 +Train: [77] [ 800/6250] eta: 0:15:58 lr: 0.000017 grad: 0.1258 (0.1336) loss: 0.8362 (0.8519) time: 0.1528 data: 0.0738 max mem: 8255 +Train: [77] [ 900/6250] eta: 0:15:37 lr: 0.000017 grad: 0.1284 (0.1334) loss: 0.8388 (0.8510) time: 0.1633 data: 0.0770 max mem: 8255 +Train: [77] [1000/6250] eta: 0:15:06 lr: 0.000017 grad: 0.1194 (0.1336) loss: 0.8499 (0.8503) time: 0.1396 data: 0.0531 max mem: 8255 +Train: [77] [1100/6250] eta: 0:14:30 lr: 0.000017 grad: 0.1297 (0.1335) loss: 0.8354 (0.8494) time: 0.1268 data: 0.0464 max mem: 8255 +Train: [77] [1200/6250] eta: 0:13:57 lr: 0.000017 grad: 0.1239 (0.1333) loss: 0.8489 (0.8487) time: 0.1247 data: 0.0381 max mem: 8255 +Train: [77] [1300/6250] eta: 0:13:27 lr: 0.000017 grad: 0.1224 (0.1333) loss: 0.8426 (0.8481) time: 0.1283 data: 0.0534 max mem: 8255 +Train: [77] [1400/6250] eta: 0:13:01 lr: 0.000017 grad: 0.1252 (0.1331) loss: 0.8447 (0.8474) time: 0.1401 data: 0.0644 max mem: 8255 +Train: [77] [1500/6250] eta: 0:12:39 lr: 0.000017 grad: 0.1286 (0.1330) loss: 0.8362 (0.8469) time: 0.1414 data: 0.0658 max mem: 8255 +Train: [77] [1600/6250] eta: 0:12:19 lr: 0.000017 grad: 0.1263 (0.1327) loss: 0.8440 (0.8467) time: 0.1476 data: 0.0677 max mem: 8255 +Train: [77] [1700/6250] eta: 0:11:57 lr: 0.000017 grad: 0.1252 (0.1327) loss: 0.8399 (0.8464) time: 0.1312 data: 0.0553 max mem: 8255 +Train: [77] [1800/6250] eta: 0:11:35 lr: 0.000017 grad: 0.1231 (0.1326) loss: 0.8384 (0.8460) time: 0.1459 data: 0.0729 max mem: 8255 +Train: [77] [1900/6250] eta: 0:11:14 lr: 0.000017 grad: 0.1267 (0.1325) loss: 0.8386 (0.8455) time: 0.1344 data: 0.0546 max mem: 8255 +Train: [77] [2000/6250] eta: 0:10:58 lr: 0.000017 grad: 0.1252 (0.1323) loss: 0.8398 (0.8452) time: 0.1622 data: 0.0644 max mem: 8255 +Train: [77] [2100/6250] eta: 0:10:42 lr: 0.000017 grad: 0.1320 (0.1322) loss: 0.8315 (0.8448) time: 0.1257 data: 0.0506 max mem: 8255 +Train: [77] [2200/6250] eta: 0:10:28 lr: 0.000017 grad: 0.1305 (0.1321) loss: 0.8324 (0.8444) time: 0.1999 data: 0.1317 max mem: 8255 +Train: [77] [2300/6250] eta: 0:10:11 lr: 0.000017 grad: 0.1304 (0.1322) loss: 0.8333 (0.8441) time: 0.1330 data: 0.0517 max mem: 8255 +Train: [77] [2400/6250] eta: 0:09:56 lr: 0.000017 grad: 0.1335 (0.1321) loss: 0.8310 (0.8438) time: 0.1030 data: 0.0304 max mem: 8255 +Train: [77] [2500/6250] eta: 0:09:39 lr: 0.000017 grad: 0.1318 (0.1322) loss: 0.8206 (0.8434) time: 0.1470 data: 0.0781 max mem: 8255 +Train: [77] [2600/6250] eta: 0:09:23 lr: 0.000017 grad: 0.1328 (0.1323) loss: 0.8368 (0.8428) time: 0.1326 data: 0.0570 max mem: 8255 +Train: [77] [2700/6250] eta: 0:09:07 lr: 0.000017 grad: 0.1295 (0.1324) loss: 0.8247 (0.8425) time: 0.1344 data: 0.0568 max mem: 8255 +Train: [77] [2800/6250] eta: 0:08:52 lr: 0.000017 grad: 0.1328 (0.1325) loss: 0.8405 (0.8422) time: 0.1855 data: 0.1191 max mem: 8255 +Train: [77] [2900/6250] eta: 0:08:34 lr: 0.000017 grad: 0.1268 (0.1325) loss: 0.8355 (0.8419) time: 0.1347 data: 0.0586 max mem: 8255 +Train: [77] [3000/6250] eta: 0:08:17 lr: 0.000017 grad: 0.1259 (0.1326) loss: 0.8309 (0.8416) time: 0.1366 data: 0.0639 max mem: 8255 +Train: [77] [3100/6250] eta: 0:08:00 lr: 0.000017 grad: 0.1310 (0.1327) loss: 0.8396 (0.8413) time: 0.1477 data: 0.0757 max mem: 8255 +Train: [77] [3200/6250] eta: 0:07:44 lr: 0.000017 grad: 0.1216 (0.1326) loss: 0.8437 (0.8412) time: 0.1240 data: 0.0560 max mem: 8255 +Train: [77] [3300/6250] eta: 0:07:30 lr: 0.000016 grad: 0.1297 (0.1325) loss: 0.8329 (0.8411) time: 0.1915 data: 0.1131 max mem: 8255 +Train: [77] [3400/6250] eta: 0:07:13 lr: 0.000016 grad: 0.1242 (0.1324) loss: 0.8354 (0.8409) time: 0.1505 data: 0.0785 max mem: 8255 +Train: [77] [3500/6250] eta: 0:06:57 lr: 0.000016 grad: 0.1197 (0.1324) loss: 0.8350 (0.8408) time: 0.1503 data: 0.0812 max mem: 8255 +Train: [77] [3600/6250] eta: 0:06:41 lr: 0.000016 grad: 0.1283 (0.1324) loss: 0.8425 (0.8407) time: 0.1655 data: 0.0868 max mem: 8255 +Train: [77] [3700/6250] eta: 0:06:25 lr: 0.000016 grad: 0.1320 (0.1325) loss: 0.8339 (0.8404) time: 0.1517 data: 0.0807 max mem: 8255 +Train: [77] [3800/6250] eta: 0:06:12 lr: 0.000016 grad: 0.1293 (0.1324) loss: 0.8372 (0.8403) time: 0.2955 data: 0.2215 max mem: 8255 +Train: [77] [3900/6250] eta: 0:05:57 lr: 0.000016 grad: 0.1307 (0.1324) loss: 0.8372 (0.8401) time: 0.1669 data: 0.0888 max mem: 8255 +Train: [77] [4000/6250] eta: 0:05:41 lr: 0.000016 grad: 0.1290 (0.1324) loss: 0.8393 (0.8400) time: 0.1373 data: 0.0604 max mem: 8255 +Train: [77] [4100/6250] eta: 0:05:26 lr: 0.000016 grad: 0.1273 (0.1324) loss: 0.8344 (0.8399) time: 0.1554 data: 0.0671 max mem: 8255 +Train: [77] [4200/6250] eta: 0:05:11 lr: 0.000016 grad: 0.1299 (0.1324) loss: 0.8302 (0.8398) time: 0.1447 data: 0.0709 max mem: 8255 +Train: [77] [4300/6250] eta: 0:04:58 lr: 0.000016 grad: 0.1338 (0.1323) loss: 0.8338 (0.8398) time: 0.0921 data: 0.0002 max mem: 8255 +Train: [77] [4400/6250] eta: 0:04:42 lr: 0.000016 grad: 0.1258 (0.1323) loss: 0.8383 (0.8398) time: 0.1584 data: 0.0910 max mem: 8255 +Train: [77] [4500/6250] eta: 0:04:26 lr: 0.000016 grad: 0.1305 (0.1323) loss: 0.8348 (0.8397) time: 0.1211 data: 0.0476 max mem: 8255 +Train: [77] [4600/6250] eta: 0:04:10 lr: 0.000016 grad: 0.1298 (0.1323) loss: 0.8390 (0.8397) time: 0.1344 data: 0.0594 max mem: 8255 +Train: [77] [4700/6250] eta: 0:03:55 lr: 0.000016 grad: 0.1305 (0.1322) loss: 0.8354 (0.8397) time: 0.1069 data: 0.0264 max mem: 8255 +Train: [77] [4800/6250] eta: 0:03:39 lr: 0.000016 grad: 0.1289 (0.1322) loss: 0.8399 (0.8396) time: 0.1368 data: 0.0485 max mem: 8255 +Train: [77] [4900/6250] eta: 0:03:24 lr: 0.000016 grad: 0.1334 (0.1322) loss: 0.8371 (0.8396) time: 0.1245 data: 0.0459 max mem: 8255 +Train: [77] [5000/6250] eta: 0:03:09 lr: 0.000016 grad: 0.1276 (0.1322) loss: 0.8365 (0.8395) time: 0.1392 data: 0.0528 max mem: 8255 +Train: [77] [5100/6250] eta: 0:02:53 lr: 0.000016 grad: 0.1269 (0.1323) loss: 0.8371 (0.8395) time: 0.1541 data: 0.0739 max mem: 8255 +Train: [77] [5200/6250] eta: 0:02:38 lr: 0.000016 grad: 0.1310 (0.1323) loss: 0.8405 (0.8395) time: 0.1540 data: 0.0793 max mem: 8255 +Train: [77] [5300/6250] eta: 0:02:23 lr: 0.000016 grad: 0.1267 (0.1323) loss: 0.8360 (0.8395) time: 0.1385 data: 0.0695 max mem: 8255 +Train: [77] [5400/6250] eta: 0:02:08 lr: 0.000016 grad: 0.1278 (0.1323) loss: 0.8402 (0.8395) time: 0.1420 data: 0.0749 max mem: 8255 +Train: [77] [5500/6250] eta: 0:01:53 lr: 0.000016 grad: 0.1268 (0.1323) loss: 0.8451 (0.8395) time: 0.1498 data: 0.0725 max mem: 8255 +Train: [77] [5600/6250] eta: 0:01:37 lr: 0.000016 grad: 0.1237 (0.1323) loss: 0.8495 (0.8395) time: 0.1052 data: 0.0219 max mem: 8255 +Train: [77] [5700/6250] eta: 0:01:22 lr: 0.000016 grad: 0.1321 (0.1323) loss: 0.8446 (0.8395) time: 0.1892 data: 0.1157 max mem: 8255 +Train: [77] [5800/6250] eta: 0:01:07 lr: 0.000016 grad: 0.1248 (0.1323) loss: 0.8435 (0.8396) time: 0.1963 data: 0.1240 max mem: 8255 +Train: [77] [5900/6250] eta: 0:00:52 lr: 0.000016 grad: 0.1368 (0.1324) loss: 0.8382 (0.8395) time: 0.1347 data: 0.0428 max mem: 8255 +Train: [77] [6000/6250] eta: 0:00:37 lr: 0.000016 grad: 0.1325 (0.1324) loss: 0.8447 (0.8396) time: 0.1437 data: 0.0658 max mem: 8255 +Train: [77] [6100/6250] eta: 0:00:22 lr: 0.000016 grad: 0.1318 (0.1325) loss: 0.8373 (0.8395) time: 0.1205 data: 0.0360 max mem: 8255 +Train: [77] [6200/6250] eta: 0:00:07 lr: 0.000016 grad: 0.1255 (0.1325) loss: 0.8430 (0.8396) time: 0.2067 data: 0.1370 max mem: 8255 +Train: [77] [6249/6250] eta: 0:00:00 lr: 0.000016 grad: 0.1329 (0.1326) loss: 0.8412 (0.8396) time: 0.1402 data: 0.0550 max mem: 8255 +Train: [77] Total time: 0:15:45 (0.1513 s / it) +Averaged stats: lr: 0.000016 grad: 0.1329 (0.1326) loss: 0.8412 (0.8396) +Eval (hcp-train-subset): [77] [ 0/62] eta: 0:04:01 loss: 0.8627 (0.8627) time: 3.8999 data: 3.8433 max mem: 8255 +Eval (hcp-train-subset): [77] [61/62] eta: 0:00:00 loss: 0.8529 (0.8580) time: 0.1313 data: 0.1085 max mem: 8255 +Eval (hcp-train-subset): [77] Total time: 0:00:13 (0.2161 s / it) +Averaged stats (hcp-train-subset): loss: 0.8529 (0.8580) +Eval (hcp-val): [77] [ 0/62] eta: 0:05:02 loss: 0.8701 (0.8701) time: 4.8866 data: 4.8554 max mem: 8255 +Eval (hcp-val): [77] [61/62] eta: 0:00:00 loss: 0.8720 (0.8730) time: 0.1574 data: 0.1350 max mem: 8255 +Eval (hcp-val): [77] Total time: 0:00:14 (0.2342 s / it) +Averaged stats (hcp-val): loss: 0.8720 (0.8730) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +Train: [78] [ 0/6250] eta: 10:49:42 lr: 0.000016 grad: 0.1357 (0.1357) loss: 0.8702 (0.8702) time: 6.2372 data: 6.0493 max mem: 8255 +Train: [78] [ 100/6250] eta: 0:24:47 lr: 0.000016 grad: 0.1574 (0.1677) loss: 0.8509 (0.8620) time: 0.1866 data: 0.0953 max mem: 8255 +Train: [78] [ 200/6250] eta: 0:20:47 lr: 0.000016 grad: 0.1359 (0.1585) loss: 0.8438 (0.8522) time: 0.1607 data: 0.0716 max mem: 8255 +Train: [78] [ 300/6250] eta: 0:19:07 lr: 0.000016 grad: 0.1160 (0.1479) loss: 0.8594 (0.8526) time: 0.1645 data: 0.0694 max mem: 8255 +Train: [78] [ 400/6250] eta: 0:18:44 lr: 0.000016 grad: 0.1331 (0.1444) loss: 0.8490 (0.8526) time: 0.1738 data: 0.0747 max mem: 8255 +Train: [78] [ 500/6250] eta: 0:18:06 lr: 0.000016 grad: 0.1285 (0.1415) loss: 0.8528 (0.8515) time: 0.1367 data: 0.0394 max mem: 8255 +Train: [78] [ 600/6250] eta: 0:17:30 lr: 0.000016 grad: 0.1282 (0.1390) loss: 0.8436 (0.8508) time: 0.1728 data: 0.0667 max mem: 8255 +Train: [78] [ 700/6250] eta: 0:16:58 lr: 0.000016 grad: 0.1263 (0.1379) loss: 0.8435 (0.8498) time: 0.1261 data: 0.0025 max mem: 8255 +Train: [78] [ 800/6250] eta: 0:16:24 lr: 0.000016 grad: 0.1279 (0.1370) loss: 0.8459 (0.8485) time: 0.1701 data: 0.0924 max mem: 8255 +Train: [78] [ 900/6250] eta: 0:15:55 lr: 0.000016 grad: 0.1219 (0.1359) loss: 0.8480 (0.8479) time: 0.1402 data: 0.0669 max mem: 8255 +Train: [78] [1000/6250] eta: 0:15:29 lr: 0.000016 grad: 0.1278 (0.1353) loss: 0.8363 (0.8471) time: 0.1682 data: 0.0818 max mem: 8255 +Train: [78] [1100/6250] eta: 0:15:03 lr: 0.000016 grad: 0.1344 (0.1348) loss: 0.8400 (0.8464) time: 0.1775 data: 0.0985 max mem: 8255 +Train: [78] [1200/6250] eta: 0:14:35 lr: 0.000016 grad: 0.1297 (0.1345) loss: 0.8344 (0.8456) time: 0.1624 data: 0.0927 max mem: 8255 +Train: [78] [1300/6250] eta: 0:14:08 lr: 0.000016 grad: 0.1270 (0.1340) loss: 0.8420 (0.8450) time: 0.1731 data: 0.0985 max mem: 8255 +Train: [78] [1400/6250] eta: 0:13:42 lr: 0.000016 grad: 0.1204 (0.1336) loss: 0.8403 (0.8445) time: 0.1491 data: 0.0637 max mem: 8255 +Train: [78] [1500/6250] eta: 0:13:15 lr: 0.000015 grad: 0.1257 (0.1331) loss: 0.8447 (0.8442) time: 0.1292 data: 0.0391 max mem: 8255 +Train: [78] [1600/6250] eta: 0:12:53 lr: 0.000015 grad: 0.1307 (0.1327) loss: 0.8341 (0.8437) time: 0.1306 data: 0.0374 max mem: 8255 +Train: [78] [1700/6250] eta: 0:12:32 lr: 0.000015 grad: 0.1238 (0.1323) loss: 0.8399 (0.8433) time: 0.1908 data: 0.1031 max mem: 8255 +Train: [78] [1800/6250] eta: 0:12:11 lr: 0.000015 grad: 0.1281 (0.1322) loss: 0.8380 (0.8431) time: 0.1002 data: 0.0212 max mem: 8255 +Train: [78] [1900/6250] eta: 0:11:46 lr: 0.000015 grad: 0.1256 (0.1320) loss: 0.8351 (0.8428) time: 0.1237 data: 0.0535 max mem: 8255 +Train: [78] [2000/6250] eta: 0:11:26 lr: 0.000015 grad: 0.1208 (0.1318) loss: 0.8446 (0.8426) time: 0.1483 data: 0.0606 max mem: 8255 +Train: [78] [2100/6250] eta: 0:11:06 lr: 0.000015 grad: 0.1195 (0.1316) loss: 0.8288 (0.8424) time: 0.1357 data: 0.0688 max mem: 8255 +Train: [78] [2200/6250] eta: 0:10:50 lr: 0.000015 grad: 0.1135 (0.1313) loss: 0.8388 (0.8424) time: 0.1722 data: 0.0850 max mem: 8255 +Train: [78] [2300/6250] eta: 0:10:37 lr: 0.000015 grad: 0.1269 (0.1311) loss: 0.8440 (0.8423) time: 0.0945 data: 0.0002 max mem: 8255 +Train: [78] [2400/6250] eta: 0:10:19 lr: 0.000015 grad: 0.1331 (0.1311) loss: 0.8393 (0.8422) time: 0.1331 data: 0.0564 max mem: 8255 +Train: [78] [2500/6250] eta: 0:10:02 lr: 0.000015 grad: 0.1291 (0.1311) loss: 0.8392 (0.8420) time: 0.1748 data: 0.0920 max mem: 8255 +Train: [78] [2600/6250] eta: 0:09:46 lr: 0.000015 grad: 0.1323 (0.1311) loss: 0.8394 (0.8418) time: 0.1473 data: 0.0736 max mem: 8255 +Train: [78] [2700/6250] eta: 0:09:27 lr: 0.000015 grad: 0.1358 (0.1312) loss: 0.8361 (0.8415) time: 0.1293 data: 0.0573 max mem: 8255 +Train: [78] [2800/6250] eta: 0:09:10 lr: 0.000015 grad: 0.1248 (0.1312) loss: 0.8402 (0.8412) time: 0.1539 data: 0.0734 max mem: 8255 +Train: [78] [2900/6250] eta: 0:08:56 lr: 0.000015 grad: 0.1308 (0.1313) loss: 0.8367 (0.8411) time: 0.1315 data: 0.0657 max mem: 8255 +Train: [78] [3000/6250] eta: 0:08:42 lr: 0.000015 grad: 0.1305 (0.1313) loss: 0.8325 (0.8409) time: 0.1644 data: 0.0865 max mem: 8255 +Train: [78] [3100/6250] eta: 0:08:25 lr: 0.000015 grad: 0.1299 (0.1313) loss: 0.8302 (0.8407) time: 0.1236 data: 0.0286 max mem: 8255 +Train: [78] [3200/6250] eta: 0:08:08 lr: 0.000015 grad: 0.1254 (0.1313) loss: 0.8376 (0.8405) time: 0.1330 data: 0.0567 max mem: 8255 +Train: [78] [3300/6250] eta: 0:07:51 lr: 0.000015 grad: 0.1359 (0.1315) loss: 0.8271 (0.8402) time: 0.1191 data: 0.0206 max mem: 8255 +Train: [78] [3400/6250] eta: 0:07:35 lr: 0.000015 grad: 0.1286 (0.1316) loss: 0.8340 (0.8399) time: 0.1714 data: 0.1011 max mem: 8255 +Train: [78] [3500/6250] eta: 0:07:19 lr: 0.000015 grad: 0.1366 (0.1317) loss: 0.8266 (0.8397) time: 0.1171 data: 0.0317 max mem: 8255 +Train: [78] [3600/6250] eta: 0:07:02 lr: 0.000015 grad: 0.1286 (0.1318) loss: 0.8326 (0.8395) time: 0.1462 data: 0.0710 max mem: 8255 +Train: [78] [3700/6250] eta: 0:06:46 lr: 0.000015 grad: 0.1370 (0.1319) loss: 0.8186 (0.8392) time: 0.1664 data: 0.0953 max mem: 8255 +Train: [78] [3800/6250] eta: 0:06:29 lr: 0.000015 grad: 0.1409 (0.1322) loss: 0.8344 (0.8390) time: 0.1260 data: 0.0544 max mem: 8255 +Train: [78] [3900/6250] eta: 0:06:13 lr: 0.000015 grad: 0.1356 (0.1322) loss: 0.8278 (0.8388) time: 0.1616 data: 0.0868 max mem: 8255 +Train: [78] [4000/6250] eta: 0:05:57 lr: 0.000015 grad: 0.1385 (0.1324) loss: 0.8311 (0.8387) time: 0.1534 data: 0.0739 max mem: 8255 +Train: [78] [4100/6250] eta: 0:05:41 lr: 0.000015 grad: 0.1264 (0.1325) loss: 0.8328 (0.8385) time: 0.1310 data: 0.0560 max mem: 8255 +Train: [78] [4200/6250] eta: 0:05:24 lr: 0.000015 grad: 0.1283 (0.1326) loss: 0.8396 (0.8385) time: 0.1542 data: 0.0765 max mem: 8255 +Train: [78] [4300/6250] eta: 0:05:09 lr: 0.000015 grad: 0.1324 (0.1326) loss: 0.8331 (0.8384) time: 0.1893 data: 0.1074 max mem: 8255 +Train: [78] [4400/6250] eta: 0:04:52 lr: 0.000015 grad: 0.1359 (0.1327) loss: 0.8351 (0.8383) time: 0.1536 data: 0.0663 max mem: 8255 +Train: [78] [4500/6250] eta: 0:04:39 lr: 0.000015 grad: 0.1395 (0.1329) loss: 0.8341 (0.8382) time: 0.1612 data: 0.0888 max mem: 8255 +Train: [78] [4600/6250] eta: 0:04:23 lr: 0.000015 grad: 0.1378 (0.1330) loss: 0.8320 (0.8382) time: 0.1568 data: 0.0851 max mem: 8255 +Train: [78] [4700/6250] eta: 0:04:08 lr: 0.000015 grad: 0.1370 (0.1332) loss: 0.8360 (0.8381) time: 0.1865 data: 0.1133 max mem: 8255 +Train: [78] [4800/6250] eta: 0:03:52 lr: 0.000015 grad: 0.1342 (0.1333) loss: 0.8302 (0.8380) time: 0.1835 data: 0.1014 max mem: 8255 +Train: [78] [4900/6250] eta: 0:03:36 lr: 0.000015 grad: 0.1346 (0.1334) loss: 0.8374 (0.8379) time: 0.1146 data: 0.0150 max mem: 8255 +Train: [78] [5000/6250] eta: 0:03:20 lr: 0.000015 grad: 0.1358 (0.1335) loss: 0.8390 (0.8379) time: 0.1479 data: 0.0668 max mem: 8255 +Train: [78] [5100/6250] eta: 0:03:04 lr: 0.000015 grad: 0.1263 (0.1336) loss: 0.8394 (0.8379) time: 0.1764 data: 0.1007 max mem: 8255 +Train: [78] [5200/6250] eta: 0:02:47 lr: 0.000015 grad: 0.1334 (0.1336) loss: 0.8484 (0.8379) time: 0.1057 data: 0.0315 max mem: 8255 +Train: [78] [5300/6250] eta: 0:02:31 lr: 0.000015 grad: 0.1363 (0.1337) loss: 0.8424 (0.8379) time: 0.1457 data: 0.0667 max mem: 8255 +Train: [78] [5400/6250] eta: 0:02:15 lr: 0.000015 grad: 0.1355 (0.1338) loss: 0.8314 (0.8378) time: 0.1450 data: 0.0683 max mem: 8255 +Train: [78] [5500/6250] eta: 0:01:59 lr: 0.000015 grad: 0.1267 (0.1339) loss: 0.8426 (0.8379) time: 0.1483 data: 0.0693 max mem: 8255 +Train: [78] [5600/6250] eta: 0:01:43 lr: 0.000015 grad: 0.1362 (0.1339) loss: 0.8350 (0.8378) time: 0.1353 data: 0.0608 max mem: 8255 +Train: [78] [5700/6250] eta: 0:01:27 lr: 0.000015 grad: 0.1332 (0.1339) loss: 0.8323 (0.8378) time: 0.1471 data: 0.0771 max mem: 8255 +Train: [78] [5800/6250] eta: 0:01:11 lr: 0.000015 grad: 0.1338 (0.1340) loss: 0.8366 (0.8377) time: 0.1753 data: 0.1067 max mem: 8255 +Train: [78] [5900/6250] eta: 0:00:55 lr: 0.000015 grad: 0.1356 (0.1340) loss: 0.8317 (0.8377) time: 0.1514 data: 0.0786 max mem: 8255 +Train: [78] [6000/6250] eta: 0:00:39 lr: 0.000015 grad: 0.1377 (0.1341) loss: 0.8381 (0.8376) time: 0.1387 data: 0.0571 max mem: 8255 +Train: [78] [6100/6250] eta: 0:00:23 lr: 0.000015 grad: 0.1318 (0.1341) loss: 0.8373 (0.8376) time: 0.1178 data: 0.0479 max mem: 8255 +Train: [78] [6200/6250] eta: 0:00:07 lr: 0.000014 grad: 0.1352 (0.1342) loss: 0.8337 (0.8375) time: 0.1513 data: 0.0830 max mem: 8255 +Train: [78] [6249/6250] eta: 0:00:00 lr: 0.000014 grad: 0.1322 (0.1342) loss: 0.8277 (0.8375) time: 0.2212 data: 0.1361 max mem: 8255 +Train: [78] Total time: 0:16:37 (0.1596 s / it) +Averaged stats: lr: 0.000014 grad: 0.1322 (0.1342) loss: 0.8277 (0.8375) +Eval (hcp-train-subset): [78] [ 0/62] eta: 0:06:59 loss: 0.8589 (0.8589) time: 6.7636 data: 6.7324 max mem: 8255 +Eval (hcp-train-subset): [78] [61/62] eta: 0:00:00 loss: 0.8513 (0.8565) time: 0.1150 data: 0.0942 max mem: 8255 +Eval (hcp-train-subset): [78] Total time: 0:00:15 (0.2487 s / it) +Averaged stats (hcp-train-subset): loss: 0.8513 (0.8565) +Eval (hcp-val): [78] [ 0/62] eta: 0:05:36 loss: 0.8682 (0.8682) time: 5.4241 data: 5.3968 max mem: 8255 +Eval (hcp-val): [78] [61/62] eta: 0:00:00 loss: 0.8716 (0.8729) time: 0.1234 data: 0.1026 max mem: 8255 +Eval (hcp-val): [78] Total time: 0:00:14 (0.2334 s / it) +Averaged stats (hcp-val): loss: 0.8716 (0.8729) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +Train: [79] [ 0/6250] eta: 7:48:05 lr: 0.000014 grad: 0.3383 (0.3383) loss: 0.7807 (0.7807) time: 4.4937 data: 4.2627 max mem: 8255 +Train: [79] [ 100/6250] eta: 0:21:11 lr: 0.000014 grad: 0.1562 (0.1757) loss: 0.8530 (0.8525) time: 0.1714 data: 0.0668 max mem: 8255 +Train: [79] [ 200/6250] eta: 0:18:24 lr: 0.000014 grad: 0.1435 (0.1622) loss: 0.8403 (0.8486) time: 0.1434 data: 0.0448 max mem: 8255 +Train: [79] [ 300/6250] eta: 0:17:13 lr: 0.000014 grad: 0.1490 (0.1583) loss: 0.8294 (0.8460) time: 0.1662 data: 0.0737 max mem: 8255 +Train: [79] [ 400/6250] eta: 0:16:41 lr: 0.000014 grad: 0.1267 (0.1536) loss: 0.8395 (0.8455) time: 0.1702 data: 0.0648 max mem: 8255 +Train: [79] [ 500/6250] eta: 0:16:07 lr: 0.000014 grad: 0.1332 (0.1510) loss: 0.8502 (0.8446) time: 0.1467 data: 0.0427 max mem: 8255 +Train: [79] [ 600/6250] eta: 0:15:30 lr: 0.000014 grad: 0.1448 (0.1493) loss: 0.8216 (0.8429) time: 0.1304 data: 0.0527 max mem: 8255 +Train: [79] [ 700/6250] eta: 0:14:53 lr: 0.000014 grad: 0.1346 (0.1482) loss: 0.8328 (0.8421) time: 0.1295 data: 0.0413 max mem: 8255 +Train: [79] [ 800/6250] eta: 0:14:44 lr: 0.000014 grad: 0.1304 (0.1463) loss: 0.8364 (0.8415) time: 0.1713 data: 0.0716 max mem: 8255 +Train: [79] [ 900/6250] eta: 0:15:20 lr: 0.000014 grad: 0.1375 (0.1448) loss: 0.8413 (0.8411) time: 0.2684 data: 0.1995 max mem: 8255 +Train: [79] [1000/6250] eta: 0:15:03 lr: 0.000014 grad: 0.1260 (0.1435) loss: 0.8339 (0.8408) time: 0.2305 data: 0.1401 max mem: 8255 +Train: [79] [1100/6250] eta: 0:15:05 lr: 0.000014 grad: 0.1321 (0.1425) loss: 0.8333 (0.8402) time: 0.1237 data: 0.0003 max mem: 8255 +Train: [79] [1200/6250] eta: 0:14:42 lr: 0.000014 grad: 0.1291 (0.1417) loss: 0.8307 (0.8396) time: 0.1733 data: 0.0999 max mem: 8255 +Train: [79] [1300/6250] eta: 0:14:13 lr: 0.000014 grad: 0.1311 (0.1409) loss: 0.8370 (0.8394) time: 0.1486 data: 0.0798 max mem: 8255 +Train: [79] [1400/6250] eta: 0:13:52 lr: 0.000014 grad: 0.1288 (0.1402) loss: 0.8399 (0.8391) time: 0.1434 data: 0.0666 max mem: 8255 +Train: [79] [1500/6250] eta: 0:13:29 lr: 0.000014 grad: 0.1257 (0.1398) loss: 0.8344 (0.8388) time: 0.1527 data: 0.0725 max mem: 8255 +Train: [79] [1600/6250] eta: 0:13:11 lr: 0.000014 grad: 0.1258 (0.1394) loss: 0.8452 (0.8387) time: 0.1731 data: 0.1030 max mem: 8255 +Train: [79] [1700/6250] eta: 0:12:50 lr: 0.000014 grad: 0.1387 (0.1390) loss: 0.8373 (0.8385) time: 0.1489 data: 0.0649 max mem: 8255 +Train: [79] [1800/6250] eta: 0:12:30 lr: 0.000014 grad: 0.1256 (0.1385) loss: 0.8442 (0.8385) time: 0.1355 data: 0.0496 max mem: 8255 +Train: [79] [1900/6250] eta: 0:12:08 lr: 0.000014 grad: 0.1275 (0.1380) loss: 0.8371 (0.8385) time: 0.1367 data: 0.0594 max mem: 8255 +Train: [79] [2000/6250] eta: 0:11:49 lr: 0.000014 grad: 0.1270 (0.1375) loss: 0.8374 (0.8386) time: 0.1821 data: 0.0942 max mem: 8255 +Train: [79] [2100/6250] eta: 0:11:34 lr: 0.000014 grad: 0.1276 (0.1371) loss: 0.8407 (0.8386) time: 0.3453 data: 0.2600 max mem: 8255 +Train: [79] [2200/6250] eta: 0:11:10 lr: 0.000014 grad: 0.1261 (0.1366) loss: 0.8430 (0.8387) time: 0.1753 data: 0.0852 max mem: 8255 +Train: [79] [2300/6250] eta: 0:10:54 lr: 0.000014 grad: 0.1274 (0.1364) loss: 0.8455 (0.8387) time: 0.1770 data: 0.0512 max mem: 8255 +Train: [79] [2400/6250] eta: 0:10:38 lr: 0.000014 grad: 0.1227 (0.1361) loss: 0.8393 (0.8388) time: 0.1299 data: 0.0395 max mem: 8255 +Train: [79] [2500/6250] eta: 0:10:26 lr: 0.000014 grad: 0.1289 (0.1358) loss: 0.8390 (0.8388) time: 0.3274 data: 0.2250 max mem: 8255 +Train: [79] [2600/6250] eta: 0:10:06 lr: 0.000014 grad: 0.1264 (0.1357) loss: 0.8363 (0.8388) time: 0.1539 data: 0.0889 max mem: 8255 +Train: [79] [2700/6250] eta: 0:09:49 lr: 0.000014 grad: 0.1300 (0.1356) loss: 0.8342 (0.8388) time: 0.1411 data: 0.0687 max mem: 8255 +Train: [79] [2800/6250] eta: 0:09:32 lr: 0.000014 grad: 0.1328 (0.1354) loss: 0.8333 (0.8388) time: 0.1847 data: 0.1189 max mem: 8255 +Train: [79] [2900/6250] eta: 0:09:13 lr: 0.000014 grad: 0.1356 (0.1354) loss: 0.8321 (0.8386) time: 0.1801 data: 0.1070 max mem: 8255 +Train: [79] [3000/6250] eta: 0:08:53 lr: 0.000014 grad: 0.1319 (0.1354) loss: 0.8342 (0.8385) time: 0.1453 data: 0.0734 max mem: 8255 +Train: [79] [3100/6250] eta: 0:08:36 lr: 0.000014 grad: 0.1301 (0.1352) loss: 0.8401 (0.8385) time: 0.1706 data: 0.1066 max mem: 8255 +Train: [79] [3200/6250] eta: 0:08:20 lr: 0.000014 grad: 0.1295 (0.1351) loss: 0.8372 (0.8384) time: 0.1244 data: 0.0540 max mem: 8255 +Train: [79] [3300/6250] eta: 0:08:01 lr: 0.000014 grad: 0.1314 (0.1350) loss: 0.8376 (0.8383) time: 0.1233 data: 0.0587 max mem: 8255 +Train: [79] [3400/6250] eta: 0:07:43 lr: 0.000014 grad: 0.1332 (0.1349) loss: 0.8377 (0.8383) time: 0.1470 data: 0.0685 max mem: 8255 +Train: [79] [3500/6250] eta: 0:07:28 lr: 0.000014 grad: 0.1298 (0.1348) loss: 0.8382 (0.8383) time: 0.2132 data: 0.0807 max mem: 8255 +Train: [79] [3600/6250] eta: 0:07:13 lr: 0.000014 grad: 0.1318 (0.1348) loss: 0.8392 (0.8382) time: 0.1256 data: 0.0558 max mem: 8255 +Train: [79] [3700/6250] eta: 0:06:56 lr: 0.000014 grad: 0.1304 (0.1348) loss: 0.8362 (0.8381) time: 0.1811 data: 0.0981 max mem: 8255 +Train: [79] [3800/6250] eta: 0:06:40 lr: 0.000014 grad: 0.1245 (0.1348) loss: 0.8405 (0.8380) time: 0.1543 data: 0.0685 max mem: 8255 +Train: [79] [3900/6250] eta: 0:06:23 lr: 0.000014 grad: 0.1423 (0.1348) loss: 0.8362 (0.8379) time: 0.1453 data: 0.0677 max mem: 8255 +Train: [79] [4000/6250] eta: 0:06:05 lr: 0.000014 grad: 0.1297 (0.1349) loss: 0.8418 (0.8378) time: 0.1242 data: 0.0459 max mem: 8255 +Train: [79] [4100/6250] eta: 0:05:48 lr: 0.000014 grad: 0.1242 (0.1349) loss: 0.8295 (0.8377) time: 0.1400 data: 0.0652 max mem: 8255 +Train: [79] [4200/6250] eta: 0:05:31 lr: 0.000014 grad: 0.1329 (0.1350) loss: 0.8341 (0.8376) time: 0.1518 data: 0.0652 max mem: 8255 +Train: [79] [4300/6250] eta: 0:05:15 lr: 0.000014 grad: 0.1497 (0.1351) loss: 0.8334 (0.8374) time: 0.1307 data: 0.0613 max mem: 8255 +Train: [79] [4400/6250] eta: 0:04:58 lr: 0.000014 grad: 0.1289 (0.1351) loss: 0.8434 (0.8374) time: 0.1429 data: 0.0775 max mem: 8255 +Train: [79] [4500/6250] eta: 0:04:41 lr: 0.000014 grad: 0.1404 (0.1352) loss: 0.8342 (0.8372) time: 0.1455 data: 0.0842 max mem: 8255 +Train: [79] [4600/6250] eta: 0:04:25 lr: 0.000014 grad: 0.1345 (0.1353) loss: 0.8295 (0.8371) time: 0.1440 data: 0.0655 max mem: 8255 +Train: [79] [4700/6250] eta: 0:04:08 lr: 0.000013 grad: 0.1410 (0.1353) loss: 0.8320 (0.8371) time: 0.1421 data: 0.0655 max mem: 8255 +Train: [79] [4800/6250] eta: 0:03:52 lr: 0.000013 grad: 0.1317 (0.1353) loss: 0.8394 (0.8370) time: 0.1984 data: 0.1398 max mem: 8255 +Train: [79] [4900/6250] eta: 0:03:36 lr: 0.000013 grad: 0.1335 (0.1355) loss: 0.8245 (0.8369) time: 0.1261 data: 0.0473 max mem: 8255 +Train: [79] [5000/6250] eta: 0:03:22 lr: 0.000013 grad: 0.1419 (0.1356) loss: 0.8314 (0.8368) time: 0.2697 data: 0.1620 max mem: 8255 +Train: [79] [5100/6250] eta: 0:03:05 lr: 0.000013 grad: 0.1405 (0.1356) loss: 0.8347 (0.8368) time: 0.1711 data: 0.1036 max mem: 8255 +Train: [79] [5200/6250] eta: 0:02:50 lr: 0.000013 grad: 0.1297 (0.1357) loss: 0.8364 (0.8368) time: 0.1024 data: 0.0003 max mem: 8255 +Train: [79] [5300/6250] eta: 0:02:33 lr: 0.000013 grad: 0.1328 (0.1356) loss: 0.8330 (0.8368) time: 0.1497 data: 0.0673 max mem: 8255 +Train: [79] [5400/6250] eta: 0:02:17 lr: 0.000013 grad: 0.1389 (0.1356) loss: 0.8356 (0.8368) time: 0.1288 data: 0.0329 max mem: 8255 +Train: [79] [5500/6250] eta: 0:02:01 lr: 0.000013 grad: 0.1328 (0.1356) loss: 0.8326 (0.8368) time: 0.1582 data: 0.0874 max mem: 8255 +Train: [79] [5600/6250] eta: 0:01:45 lr: 0.000013 grad: 0.1288 (0.1356) loss: 0.8377 (0.8368) time: 0.1619 data: 0.0905 max mem: 8255 +Train: [79] [5700/6250] eta: 0:01:29 lr: 0.000013 grad: 0.1267 (0.1356) loss: 0.8444 (0.8368) time: 0.1430 data: 0.0597 max mem: 8255 +Train: [79] [5800/6250] eta: 0:01:12 lr: 0.000013 grad: 0.1365 (0.1356) loss: 0.8348 (0.8368) time: 0.1574 data: 0.0409 max mem: 8255 +Train: [79] [5900/6250] eta: 0:00:56 lr: 0.000013 grad: 0.1325 (0.1357) loss: 0.8341 (0.8368) time: 0.2056 data: 0.0991 max mem: 8255 +Train: [79] [6000/6250] eta: 0:00:40 lr: 0.000013 grad: 0.1355 (0.1357) loss: 0.8416 (0.8368) time: 0.1525 data: 0.0904 max mem: 8255 +Train: [79] [6100/6250] eta: 0:00:24 lr: 0.000013 grad: 0.1334 (0.1358) loss: 0.8423 (0.8368) time: 0.1489 data: 0.0598 max mem: 8255 +Train: [79] [6200/6250] eta: 0:00:08 lr: 0.000013 grad: 0.1280 (0.1358) loss: 0.8458 (0.8369) time: 0.1440 data: 0.0756 max mem: 8255 +Train: [79] [6249/6250] eta: 0:00:00 lr: 0.000013 grad: 0.1370 (0.1358) loss: 0.8321 (0.8369) time: 0.2309 data: 0.1464 max mem: 8255 +Train: [79] Total time: 0:16:59 (0.1631 s / it) +Averaged stats: lr: 0.000013 grad: 0.1370 (0.1358) loss: 0.8321 (0.8369) +Eval (hcp-train-subset): [79] [ 0/62] eta: 0:06:30 loss: 0.8631 (0.8631) time: 6.2919 data: 6.2649 max mem: 8255 +Eval (hcp-train-subset): [79] [61/62] eta: 0:00:00 loss: 0.8545 (0.8558) time: 0.1506 data: 0.1294 max mem: 8255 +Eval (hcp-train-subset): [79] Total time: 0:00:15 (0.2532 s / it) +Averaged stats (hcp-train-subset): loss: 0.8545 (0.8558) +Making plots (hcp-train-subset): example=26 +Eval (hcp-val): [79] [ 0/62] eta: 0:04:52 loss: 0.8700 (0.8700) time: 4.7258 data: 4.6116 max mem: 8255 +Eval (hcp-val): [79] [61/62] eta: 0:00:00 loss: 0.8724 (0.8734) time: 0.1073 data: 0.0864 max mem: 8255 +Eval (hcp-val): [79] Total time: 0:00:13 (0.2255 s / it) +Averaged stats (hcp-val): loss: 0.8724 (0.8734) +Making plots (hcp-val): example=1 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-00079.pth +Train: [80] [ 0/6250] eta: 9:44:16 lr: 0.000013 grad: 0.2533 (0.2533) loss: 0.8695 (0.8695) time: 5.6091 data: 5.4733 max mem: 8255 +Train: [80] [ 100/6250] eta: 0:20:55 lr: 0.000013 grad: 0.1155 (0.1658) loss: 0.8632 (0.8591) time: 0.1335 data: 0.0426 max mem: 8255 +Train: [80] [ 200/6250] eta: 0:17:57 lr: 0.000013 grad: 0.1286 (0.1533) loss: 0.8617 (0.8612) time: 0.1737 data: 0.0697 max mem: 8255 +Train: [80] [ 300/6250] eta: 0:16:59 lr: 0.000013 grad: 0.1351 (0.1505) loss: 0.8478 (0.8597) time: 0.1607 data: 0.0564 max mem: 8255 +Train: [80] [ 400/6250] eta: 0:16:05 lr: 0.000013 grad: 0.1385 (0.1490) loss: 0.8574 (0.8578) time: 0.1463 data: 0.0687 max mem: 8255 +Train: [80] [ 500/6250] eta: 0:15:19 lr: 0.000013 grad: 0.1413 (0.1480) loss: 0.8436 (0.8559) time: 0.1445 data: 0.0656 max mem: 8255 +Train: [80] [ 600/6250] eta: 0:14:47 lr: 0.000013 grad: 0.1378 (0.1469) loss: 0.8488 (0.8545) time: 0.1449 data: 0.0576 max mem: 8255 +Train: [80] [ 700/6250] eta: 0:14:19 lr: 0.000013 grad: 0.1350 (0.1463) loss: 0.8364 (0.8527) time: 0.1405 data: 0.0648 max mem: 8255 +Train: [80] [ 800/6250] eta: 0:13:44 lr: 0.000013 grad: 0.1313 (0.1447) loss: 0.8526 (0.8520) time: 0.1302 data: 0.0523 max mem: 8255 +Train: [80] [ 900/6250] eta: 0:13:25 lr: 0.000013 grad: 0.1310 (0.1432) loss: 0.8454 (0.8515) time: 0.1380 data: 0.0622 max mem: 8255 +Train: [80] [1000/6250] eta: 0:13:04 lr: 0.000013 grad: 0.1258 (0.1422) loss: 0.8430 (0.8508) time: 0.1357 data: 0.0612 max mem: 8255 +Train: [80] [1100/6250] eta: 0:12:51 lr: 0.000013 grad: 0.1265 (0.1413) loss: 0.8391 (0.8502) time: 0.1578 data: 0.0597 max mem: 8255 +Train: [80] [1200/6250] eta: 0:12:47 lr: 0.000013 grad: 0.1255 (0.1405) loss: 0.8482 (0.8495) time: 0.1919 data: 0.0932 max mem: 8255 +Train: [80] [1300/6250] eta: 0:12:37 lr: 0.000013 grad: 0.1267 (0.1398) loss: 0.8452 (0.8489) time: 0.1547 data: 0.0835 max mem: 8255 +Train: [80] [1400/6250] eta: 0:12:28 lr: 0.000013 grad: 0.1238 (0.1392) loss: 0.8478 (0.8484) time: 0.1580 data: 0.0787 max mem: 8255 +Train: [80] [1500/6250] eta: 0:12:16 lr: 0.000013 grad: 0.1264 (0.1387) loss: 0.8421 (0.8480) time: 0.1502 data: 0.0736 max mem: 8255 +Train: [80] [1600/6250] eta: 0:12:11 lr: 0.000013 grad: 0.1298 (0.1382) loss: 0.8350 (0.8475) time: 0.1852 data: 0.1002 max mem: 8255 +Train: [80] [1700/6250] eta: 0:12:05 lr: 0.000013 grad: 0.1320 (0.1378) loss: 0.8441 (0.8470) time: 0.1860 data: 0.0907 max mem: 8255 +Train: [80] [1800/6250] eta: 0:11:53 lr: 0.000013 grad: 0.1281 (0.1374) loss: 0.8450 (0.8467) time: 0.1532 data: 0.0747 max mem: 8255 +Train: [80] [1900/6250] eta: 0:11:35 lr: 0.000013 grad: 0.1295 (0.1372) loss: 0.8443 (0.8464) time: 0.1375 data: 0.0589 max mem: 8255 +Train: [80] [2000/6250] eta: 0:11:25 lr: 0.000013 grad: 0.1257 (0.1370) loss: 0.8369 (0.8460) time: 0.3199 data: 0.2300 max mem: 8255 +Train: [80] [2100/6250] eta: 0:11:04 lr: 0.000013 grad: 0.1341 (0.1367) loss: 0.8459 (0.8458) time: 0.1572 data: 0.0857 max mem: 8255 +Train: [80] [2200/6250] eta: 0:10:47 lr: 0.000013 grad: 0.1257 (0.1364) loss: 0.8404 (0.8455) time: 0.1444 data: 0.0718 max mem: 8255 +Train: [80] [2300/6250] eta: 0:10:28 lr: 0.000013 grad: 0.1297 (0.1362) loss: 0.8346 (0.8452) time: 0.1290 data: 0.0633 max mem: 8255 +Train: [80] [2400/6250] eta: 0:10:17 lr: 0.000013 grad: 0.1281 (0.1360) loss: 0.8354 (0.8449) time: 0.2274 data: 0.1220 max mem: 8255 +Train: [80] [2500/6250] eta: 0:10:02 lr: 0.000013 grad: 0.1338 (0.1358) loss: 0.8411 (0.8446) time: 0.1663 data: 0.0803 max mem: 8255 +Train: [80] [2600/6250] eta: 0:09:46 lr: 0.000013 grad: 0.1309 (0.1356) loss: 0.8352 (0.8443) time: 0.2033 data: 0.1270 max mem: 8255 +Train: [80] [2700/6250] eta: 0:09:31 lr: 0.000013 grad: 0.1290 (0.1356) loss: 0.8351 (0.8440) time: 0.1366 data: 0.0617 max mem: 8255 +Train: [80] [2800/6250] eta: 0:09:15 lr: 0.000013 grad: 0.1352 (0.1356) loss: 0.8307 (0.8437) time: 0.1602 data: 0.0644 max mem: 8255 +Train: [80] [2900/6250] eta: 0:08:58 lr: 0.000013 grad: 0.1331 (0.1356) loss: 0.8354 (0.8433) time: 0.1376 data: 0.0646 max mem: 8255 +Train: [80] [3000/6250] eta: 0:08:39 lr: 0.000013 grad: 0.1335 (0.1355) loss: 0.8315 (0.8430) time: 0.1264 data: 0.0563 max mem: 8255 +Train: [80] [3100/6250] eta: 0:08:22 lr: 0.000013 grad: 0.1269 (0.1354) loss: 0.8326 (0.8427) time: 0.1746 data: 0.1058 max mem: 8255 +Train: [80] [3200/6250] eta: 0:08:06 lr: 0.000013 grad: 0.1307 (0.1353) loss: 0.8334 (0.8425) time: 0.1669 data: 0.0967 max mem: 8255 +Train: [80] [3300/6250] eta: 0:07:50 lr: 0.000013 grad: 0.1248 (0.1352) loss: 0.8351 (0.8423) time: 0.1321 data: 0.0548 max mem: 8255 +Train: [80] [3400/6250] eta: 0:07:34 lr: 0.000012 grad: 0.1274 (0.1351) loss: 0.8404 (0.8421) time: 0.1418 data: 0.0658 max mem: 8255 +Train: [80] [3500/6250] eta: 0:07:17 lr: 0.000012 grad: 0.1341 (0.1350) loss: 0.8342 (0.8420) time: 0.1438 data: 0.0682 max mem: 8255 +Train: [80] [3600/6250] eta: 0:07:00 lr: 0.000012 grad: 0.1279 (0.1349) loss: 0.8398 (0.8418) time: 0.1596 data: 0.0882 max mem: 8255 +Train: [80] [3700/6250] eta: 0:06:44 lr: 0.000012 grad: 0.1274 (0.1348) loss: 0.8359 (0.8417) time: 0.1627 data: 0.0896 max mem: 8255 +Train: [80] [3800/6250] eta: 0:06:27 lr: 0.000012 grad: 0.1246 (0.1347) loss: 0.8402 (0.8417) time: 0.1522 data: 0.0831 max mem: 8255 +Train: [80] [3900/6250] eta: 0:06:11 lr: 0.000012 grad: 0.1259 (0.1345) loss: 0.8414 (0.8417) time: 0.1680 data: 0.0961 max mem: 8255 +Train: [80] [4000/6250] eta: 0:05:54 lr: 0.000012 grad: 0.1324 (0.1344) loss: 0.8410 (0.8418) time: 0.1442 data: 0.0685 max mem: 8255 +Train: [80] [4100/6250] eta: 0:05:39 lr: 0.000012 grad: 0.1285 (0.1343) loss: 0.8383 (0.8418) time: 0.1792 data: 0.1100 max mem: 8255 +Train: [80] [4200/6250] eta: 0:05:26 lr: 0.000012 grad: 0.1247 (0.1342) loss: 0.8468 (0.8419) time: 0.1053 data: 0.0003 max mem: 8255 +Train: [80] [4300/6250] eta: 0:05:09 lr: 0.000012 grad: 0.1258 (0.1340) loss: 0.8409 (0.8419) time: 0.1372 data: 0.0556 max mem: 8255 +Train: [80] [4400/6250] eta: 0:04:54 lr: 0.000012 grad: 0.1205 (0.1339) loss: 0.8466 (0.8420) time: 0.1411 data: 0.0761 max mem: 8255 +Train: [80] [4500/6250] eta: 0:04:38 lr: 0.000012 grad: 0.1339 (0.1338) loss: 0.8413 (0.8421) time: 0.0896 data: 0.0004 max mem: 8255 +Train: [80] [4600/6250] eta: 0:04:21 lr: 0.000012 grad: 0.1298 (0.1337) loss: 0.8398 (0.8421) time: 0.1470 data: 0.0755 max mem: 8255 +Train: [80] [4700/6250] eta: 0:04:05 lr: 0.000012 grad: 0.1278 (0.1337) loss: 0.8384 (0.8421) time: 0.1707 data: 0.1022 max mem: 8255 +Train: [80] [4800/6250] eta: 0:03:48 lr: 0.000012 grad: 0.1264 (0.1336) loss: 0.8430 (0.8421) time: 0.1378 data: 0.0663 max mem: 8255 +Train: [80] [4900/6250] eta: 0:03:32 lr: 0.000012 grad: 0.1298 (0.1335) loss: 0.8387 (0.8421) time: 0.1293 data: 0.0530 max mem: 8255 +Train: [80] [5000/6250] eta: 0:03:16 lr: 0.000012 grad: 0.1289 (0.1335) loss: 0.8386 (0.8420) time: 0.1812 data: 0.1083 max mem: 8255 +Train: [80] [5100/6250] eta: 0:03:01 lr: 0.000012 grad: 0.1356 (0.1335) loss: 0.8426 (0.8420) time: 0.1510 data: 0.0803 max mem: 8255 +Train: [80] [5200/6250] eta: 0:02:45 lr: 0.000012 grad: 0.1315 (0.1336) loss: 0.8391 (0.8419) time: 0.1494 data: 0.0703 max mem: 8255 +Train: [80] [5300/6250] eta: 0:02:29 lr: 0.000012 grad: 0.1283 (0.1335) loss: 0.8468 (0.8418) time: 0.1633 data: 0.0928 max mem: 8255 +Train: [80] [5400/6250] eta: 0:02:14 lr: 0.000012 grad: 0.1260 (0.1336) loss: 0.8346 (0.8417) time: 0.0919 data: 0.0002 max mem: 8255 +Train: [80] [5500/6250] eta: 0:01:58 lr: 0.000012 grad: 0.1259 (0.1335) loss: 0.8411 (0.8418) time: 0.1417 data: 0.0581 max mem: 8255 +Train: [80] [5600/6250] eta: 0:01:42 lr: 0.000012 grad: 0.1330 (0.1336) loss: 0.8380 (0.8417) time: 0.0893 data: 0.0002 max mem: 8255 +Train: [80] [5700/6250] eta: 0:01:26 lr: 0.000012 grad: 0.1362 (0.1337) loss: 0.8409 (0.8416) time: 0.1233 data: 0.0555 max mem: 8255 +Train: [80] [5800/6250] eta: 0:01:11 lr: 0.000012 grad: 0.1289 (0.1337) loss: 0.8360 (0.8416) time: 0.1312 data: 0.0420 max mem: 8255 +Train: [80] [5900/6250] eta: 0:00:55 lr: 0.000012 grad: 0.1364 (0.1338) loss: 0.8326 (0.8415) time: 0.1651 data: 0.0720 max mem: 8255 +Train: [80] [6000/6250] eta: 0:00:39 lr: 0.000012 grad: 0.1340 (0.1338) loss: 0.8339 (0.8415) time: 0.1384 data: 0.0694 max mem: 8255 +Train: [80] [6100/6250] eta: 0:00:23 lr: 0.000012 grad: 0.1268 (0.1338) loss: 0.8399 (0.8414) time: 0.1177 data: 0.0344 max mem: 8255 +Train: [80] [6200/6250] eta: 0:00:07 lr: 0.000012 grad: 0.1345 (0.1338) loss: 0.8386 (0.8414) time: 0.1617 data: 0.0871 max mem: 8255 +Train: [80] [6249/6250] eta: 0:00:00 lr: 0.000012 grad: 0.1386 (0.1338) loss: 0.8348 (0.8414) time: 0.1501 data: 0.0710 max mem: 8255 +Train: [80] Total time: 0:16:29 (0.1584 s / it) +Averaged stats: lr: 0.000012 grad: 0.1386 (0.1338) loss: 0.8348 (0.8414) +Eval (hcp-train-subset): [80] [ 0/62] eta: 0:06:25 loss: 0.8632 (0.8632) time: 6.2256 data: 6.1987 max mem: 8255 +Eval (hcp-train-subset): [80] [61/62] eta: 0:00:00 loss: 0.8503 (0.8543) time: 0.1426 data: 0.1206 max mem: 8255 +Eval (hcp-train-subset): [80] Total time: 0:00:14 (0.2276 s / it) +Averaged stats (hcp-train-subset): loss: 0.8503 (0.8543) +Eval (hcp-val): [80] [ 0/62] eta: 0:05:25 loss: 0.8679 (0.8679) time: 5.2473 data: 5.2210 max mem: 8255 +Eval (hcp-val): [80] [61/62] eta: 0:00:00 loss: 0.8729 (0.8729) time: 0.1495 data: 0.1267 max mem: 8255 +Eval (hcp-val): [80] Total time: 0:00:15 (0.2439 s / it) +Averaged stats (hcp-val): loss: 0.8729 (0.8729) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +Train: [81] [ 0/6250] eta: 11:26:57 lr: 0.000012 grad: nan (nan) loss: 0.8543 (0.8543) time: 6.5947 data: 6.5040 max mem: 8255 +Train: [81] [ 100/6250] eta: 0:21:46 lr: 0.000012 grad: 0.1348 (0.1558) loss: 0.8567 (0.8650) time: 0.1814 data: 0.0669 max mem: 8255 +Train: [81] [ 200/6250] eta: 0:18:39 lr: 0.000012 grad: 0.1232 (0.1553) loss: 0.8518 (0.8579) time: 0.1714 data: 0.0766 max mem: 8255 +Train: [81] [ 300/6250] eta: 0:17:08 lr: 0.000012 grad: 0.1376 (0.1531) loss: 0.8365 (0.8530) time: 0.1642 data: 0.0731 max mem: 8255 +Train: [81] [ 400/6250] eta: 0:16:23 lr: 0.000012 grad: 0.1381 (0.1511) loss: 0.8350 (0.8504) time: 0.1410 data: 0.0588 max mem: 8255 +Train: [81] [ 500/6250] eta: 0:15:44 lr: 0.000012 grad: 0.1335 (0.1487) loss: 0.8534 (0.8487) time: 0.1383 data: 0.0600 max mem: 8255 +Train: [81] [ 600/6250] eta: 0:15:18 lr: 0.000012 grad: 0.1259 (0.1466) loss: 0.8445 (0.8479) time: 0.1645 data: 0.0888 max mem: 8255 +Train: [81] [ 700/6250] eta: 0:14:58 lr: 0.000012 grad: 0.1279 (0.1451) loss: 0.8422 (0.8473) time: 0.1673 data: 0.0917 max mem: 8255 +Train: [81] [ 800/6250] eta: 0:14:39 lr: 0.000012 grad: 0.1283 (0.1435) loss: 0.8498 (0.8469) time: 0.1270 data: 0.0467 max mem: 8255 +Train: [81] [ 900/6250] eta: 0:14:22 lr: 0.000012 grad: 0.1308 (0.1424) loss: 0.8417 (0.8467) time: 0.1604 data: 0.0811 max mem: 8255 +Train: [81] [1000/6250] eta: 0:14:01 lr: 0.000012 grad: 0.1292 (0.1417) loss: 0.8425 (0.8461) time: 0.1462 data: 0.0740 max mem: 8255 +Train: [81] [1100/6250] eta: 0:13:38 lr: 0.000012 grad: 0.1342 (0.1412) loss: 0.8386 (0.8453) time: 0.1450 data: 0.0764 max mem: 8255 +Train: [81] [1200/6250] eta: 0:13:18 lr: 0.000012 grad: 0.1318 (0.1405) loss: 0.8385 (0.8448) time: 0.1769 data: 0.0965 max mem: 8255 +Train: [81] [1300/6250] eta: 0:12:52 lr: 0.000012 grad: 0.1291 (0.1400) loss: 0.8438 (0.8442) time: 0.1564 data: 0.0797 max mem: 8255 +Train: [81] [1400/6250] eta: 0:12:36 lr: 0.000012 grad: 0.1275 (0.1397) loss: 0.8334 (0.8438) time: 0.2116 data: 0.1342 max mem: 8255 +Train: [81] [1500/6250] eta: 0:12:18 lr: 0.000012 grad: 0.1351 (0.1394) loss: 0.8372 (0.8433) time: 0.1464 data: 0.0763 max mem: 8255 +Train: [81] [1600/6250] eta: 0:12:00 lr: 0.000012 grad: 0.1371 (0.1390) loss: 0.8314 (0.8428) time: 0.1493 data: 0.0755 max mem: 8255 +Train: [81] [1700/6250] eta: 0:11:43 lr: 0.000012 grad: 0.1280 (0.1386) loss: 0.8497 (0.8427) time: 0.1498 data: 0.0690 max mem: 8255 +Train: [81] [1800/6250] eta: 0:11:30 lr: 0.000012 grad: 0.1215 (0.1384) loss: 0.8442 (0.8425) time: 0.1424 data: 0.0635 max mem: 8255 +Train: [81] [1900/6250] eta: 0:11:17 lr: 0.000012 grad: 0.1342 (0.1383) loss: 0.8384 (0.8422) time: 0.1514 data: 0.0761 max mem: 8255 +Train: [81] [2000/6250] eta: 0:11:02 lr: 0.000012 grad: 0.1351 (0.1383) loss: 0.8329 (0.8419) time: 0.1351 data: 0.0538 max mem: 8255 +Train: [81] [2100/6250] eta: 0:10:51 lr: 0.000012 grad: 0.1315 (0.1382) loss: 0.8402 (0.8418) time: 0.0990 data: 0.0002 max mem: 8255 +Train: [81] [2200/6250] eta: 0:10:33 lr: 0.000012 grad: 0.1311 (0.1383) loss: 0.8359 (0.8417) time: 0.1567 data: 0.0753 max mem: 8255 +Train: [81] [2300/6250] eta: 0:10:24 lr: 0.000011 grad: 0.1308 (0.1382) loss: 0.8311 (0.8414) time: 0.1960 data: 0.1178 max mem: 8255 +Train: [81] [2400/6250] eta: 0:10:17 lr: 0.000011 grad: 0.1347 (0.1382) loss: 0.8324 (0.8412) time: 0.4815 data: 0.3506 max mem: 8255 +Train: [81] [2500/6250] eta: 0:09:55 lr: 0.000011 grad: 0.1345 (0.1383) loss: 0.8424 (0.8410) time: 0.0954 data: 0.0155 max mem: 8255 +Train: [81] [2600/6250] eta: 0:09:36 lr: 0.000011 grad: 0.1412 (0.1384) loss: 0.8408 (0.8409) time: 0.1507 data: 0.0785 max mem: 8255 +Train: [81] [2700/6250] eta: 0:09:21 lr: 0.000011 grad: 0.1351 (0.1385) loss: 0.8383 (0.8407) time: 0.2215 data: 0.1068 max mem: 8255 +Train: [81] [2800/6250] eta: 0:09:02 lr: 0.000011 grad: 0.1371 (0.1387) loss: 0.8412 (0.8406) time: 0.1144 data: 0.0416 max mem: 8255 +Train: [81] [2900/6250] eta: 0:08:50 lr: 0.000011 grad: 0.1298 (0.1386) loss: 0.8393 (0.8405) time: 0.3259 data: 0.2387 max mem: 8255 +Train: [81] [3000/6250] eta: 0:08:33 lr: 0.000011 grad: 0.1319 (0.1386) loss: 0.8366 (0.8405) time: 0.0958 data: 0.0152 max mem: 8255 +Train: [81] [3100/6250] eta: 0:08:19 lr: 0.000011 grad: 0.1307 (0.1385) loss: 0.8350 (0.8404) time: 0.1164 data: 0.0394 max mem: 8255 +Train: [81] [3200/6250] eta: 0:08:04 lr: 0.000011 grad: 0.1327 (0.1386) loss: 0.8405 (0.8404) time: 0.1561 data: 0.0673 max mem: 8255 +Train: [81] [3300/6250] eta: 0:07:47 lr: 0.000011 grad: 0.1308 (0.1385) loss: 0.8398 (0.8403) time: 0.1000 data: 0.0273 max mem: 8255 +Train: [81] [3400/6250] eta: 0:07:31 lr: 0.000011 grad: 0.1344 (0.1383) loss: 0.8444 (0.8404) time: 0.1583 data: 0.0866 max mem: 8255 +Train: [81] [3500/6250] eta: 0:07:14 lr: 0.000011 grad: 0.1300 (0.1383) loss: 0.8467 (0.8405) time: 0.1496 data: 0.0745 max mem: 8255 +Train: [81] [3600/6250] eta: 0:06:57 lr: 0.000011 grad: 0.1330 (0.1382) loss: 0.8446 (0.8404) time: 0.1440 data: 0.0720 max mem: 8255 +Train: [81] [3700/6250] eta: 0:06:42 lr: 0.000011 grad: 0.1245 (0.1381) loss: 0.8444 (0.8404) time: 0.2481 data: 0.1351 max mem: 8255 +Train: [81] [3800/6250] eta: 0:06:25 lr: 0.000011 grad: 0.1314 (0.1381) loss: 0.8417 (0.8404) time: 0.1473 data: 0.0753 max mem: 8255 +Train: [81] [3900/6250] eta: 0:06:14 lr: 0.000011 grad: 0.1395 (0.1380) loss: 0.8385 (0.8404) time: 0.1403 data: 0.0507 max mem: 8255 +Train: [81] [4000/6250] eta: 0:05:56 lr: 0.000011 grad: 0.1256 (0.1380) loss: 0.8429 (0.8404) time: 0.1349 data: 0.0556 max mem: 8255 +Train: [81] [4100/6250] eta: 0:05:40 lr: 0.000011 grad: 0.1323 (0.1379) loss: 0.8388 (0.8404) time: 0.1082 data: 0.0266 max mem: 8255 +Train: [81] [4200/6250] eta: 0:05:24 lr: 0.000011 grad: 0.1348 (0.1379) loss: 0.8363 (0.8404) time: 0.1570 data: 0.0832 max mem: 8255 +Train: [81] [4300/6250] eta: 0:05:07 lr: 0.000011 grad: 0.1334 (0.1378) loss: 0.8482 (0.8404) time: 0.1523 data: 0.0718 max mem: 8255 +Train: [81] [4400/6250] eta: 0:04:51 lr: 0.000011 grad: 0.1313 (0.1378) loss: 0.8343 (0.8404) time: 0.1492 data: 0.0789 max mem: 8255 +Train: [81] [4500/6250] eta: 0:04:35 lr: 0.000011 grad: 0.1282 (0.1377) loss: 0.8390 (0.8404) time: 0.1605 data: 0.0892 max mem: 8255 +Train: [81] [4600/6250] eta: 0:04:19 lr: 0.000011 grad: 0.1376 (0.1377) loss: 0.8281 (0.8403) time: 0.1336 data: 0.0645 max mem: 8255 +Train: [81] [4700/6250] eta: 0:04:02 lr: 0.000011 grad: 0.1346 (0.1377) loss: 0.8360 (0.8403) time: 0.1027 data: 0.0220 max mem: 8255 +Train: [81] [4800/6250] eta: 0:03:46 lr: 0.000011 grad: 0.1346 (0.1377) loss: 0.8397 (0.8403) time: 0.1726 data: 0.0970 max mem: 8255 +Train: [81] [4900/6250] eta: 0:03:31 lr: 0.000011 grad: 0.1438 (0.1377) loss: 0.8331 (0.8402) time: 0.1522 data: 0.0713 max mem: 8255 +Train: [81] [5000/6250] eta: 0:03:15 lr: 0.000011 grad: 0.1359 (0.1377) loss: 0.8332 (0.8402) time: 0.0995 data: 0.0304 max mem: 8255 +Train: [81] [5100/6250] eta: 0:02:59 lr: 0.000011 grad: 0.1325 (0.1377) loss: 0.8329 (0.8401) time: 0.1093 data: 0.0234 max mem: 8255 +Train: [81] [5200/6250] eta: 0:02:44 lr: 0.000011 grad: 0.1310 (0.1377) loss: 0.8365 (0.8401) time: 0.1693 data: 0.1026 max mem: 8255 +Train: [81] [5300/6250] eta: 0:02:28 lr: 0.000011 grad: 0.1359 (0.1377) loss: 0.8382 (0.8400) time: 0.1939 data: 0.1166 max mem: 8255 +Train: [81] [5400/6250] eta: 0:02:12 lr: 0.000011 grad: 0.1284 (0.1377) loss: 0.8312 (0.8400) time: 0.1495 data: 0.0821 max mem: 8255 +Train: [81] [5500/6250] eta: 0:01:56 lr: 0.000011 grad: 0.1396 (0.1377) loss: 0.8377 (0.8399) time: 0.1350 data: 0.0596 max mem: 8255 +Train: [81] [5600/6250] eta: 0:01:41 lr: 0.000011 grad: 0.1307 (0.1377) loss: 0.8376 (0.8398) time: 0.1644 data: 0.0920 max mem: 8255 +Train: [81] [5700/6250] eta: 0:01:25 lr: 0.000011 grad: 0.1310 (0.1376) loss: 0.8385 (0.8398) time: 0.1266 data: 0.0450 max mem: 8255 +Train: [81] [5800/6250] eta: 0:01:09 lr: 0.000011 grad: 0.1323 (0.1377) loss: 0.8362 (0.8397) time: 0.1470 data: 0.0819 max mem: 8255 +Train: [81] [5900/6250] eta: 0:00:54 lr: 0.000011 grad: 0.1430 (0.1377) loss: 0.8337 (0.8396) time: 0.1004 data: 0.0112 max mem: 8255 +Train: [81] [6000/6250] eta: 0:00:38 lr: 0.000011 grad: 0.1398 (0.1377) loss: 0.8292 (0.8396) time: 0.1404 data: 0.0672 max mem: 8255 +Train: [81] [6100/6250] eta: 0:00:23 lr: 0.000011 grad: 0.1409 (0.1378) loss: 0.8340 (0.8395) time: 0.1490 data: 0.0780 max mem: 8255 +Train: [81] [6200/6250] eta: 0:00:07 lr: 0.000011 grad: 0.1428 (0.1378) loss: 0.8370 (0.8395) time: 0.1374 data: 0.0599 max mem: 8255 +Train: [81] [6249/6250] eta: 0:00:00 lr: 0.000011 grad: 0.1345 (0.1379) loss: 0.8375 (0.8394) time: 0.1525 data: 0.0723 max mem: 8255 +Train: [81] Total time: 0:16:17 (0.1564 s / it) +Averaged stats: lr: 0.000011 grad: 0.1345 (0.1379) loss: 0.8375 (0.8394) +Eval (hcp-train-subset): [81] [ 0/62] eta: 0:06:29 loss: 0.8627 (0.8627) time: 6.2870 data: 6.2587 max mem: 8255 +Eval (hcp-train-subset): [81] [61/62] eta: 0:00:00 loss: 0.8519 (0.8533) time: 0.1377 data: 0.1167 max mem: 8255 +Eval (hcp-train-subset): [81] Total time: 0:00:15 (0.2525 s / it) +Averaged stats (hcp-train-subset): loss: 0.8519 (0.8533) +Eval (hcp-val): [81] [ 0/62] eta: 0:08:55 loss: 0.8714 (0.8714) time: 8.6317 data: 8.6037 max mem: 8255 +Eval (hcp-val): [81] [61/62] eta: 0:00:00 loss: 0.8710 (0.8731) time: 0.1515 data: 0.1305 max mem: 8255 +Eval (hcp-val): [81] Total time: 0:00:16 (0.2654 s / it) +Averaged stats (hcp-val): loss: 0.8710 (0.8731) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +Train: [82] [ 0/6250] eta: 13:49:52 lr: 0.000011 grad: 0.1277 (0.1277) loss: 0.9143 (0.9143) time: 7.9668 data: 7.8505 max mem: 8255 +Train: [82] [ 100/6250] eta: 0:24:01 lr: 0.000011 grad: 0.1431 (0.1693) loss: 0.8595 (0.8608) time: 0.1673 data: 0.0747 max mem: 8255 +Train: [82] [ 200/6250] eta: 0:20:26 lr: 0.000011 grad: 0.1382 (0.1581) loss: 0.8457 (0.8567) time: 0.1701 data: 0.0813 max mem: 8255 +Train: [82] [ 300/6250] eta: 0:18:07 lr: 0.000011 grad: 0.1229 (0.1522) loss: 0.8532 (0.8547) time: 0.1435 data: 0.0544 max mem: 8255 +Train: [82] [ 400/6250] eta: 0:17:24 lr: 0.000011 grad: 0.1300 (0.1478) loss: 0.8479 (0.8529) time: 0.1393 data: 0.0494 max mem: 8255 +Train: [82] [ 500/6250] eta: 0:17:12 lr: 0.000011 grad: 0.1320 (0.1449) loss: 0.8450 (0.8515) time: 0.1800 data: 0.0885 max mem: 8255 +Train: [82] [ 600/6250] eta: 0:17:12 lr: 0.000011 grad: 0.1323 (0.1437) loss: 0.8375 (0.8494) time: 0.2067 data: 0.1101 max mem: 8255 +Train: [82] [ 700/6250] eta: 0:17:21 lr: 0.000011 grad: 0.1378 (0.1435) loss: 0.8388 (0.8478) time: 0.1258 data: 0.0547 max mem: 8255 +Train: [82] [ 800/6250] eta: 0:16:35 lr: 0.000011 grad: 0.1254 (0.1427) loss: 0.8356 (0.8468) time: 0.1602 data: 0.0558 max mem: 8255 +Train: [82] [ 900/6250] eta: 0:16:28 lr: 0.000011 grad: 0.1286 (0.1419) loss: 0.8431 (0.8463) time: 0.1097 data: 0.0271 max mem: 8255 +Train: [82] [1000/6250] eta: 0:15:50 lr: 0.000011 grad: 0.1322 (0.1419) loss: 0.8392 (0.8455) time: 0.1326 data: 0.0544 max mem: 8255 +Train: [82] [1100/6250] eta: 0:15:23 lr: 0.000011 grad: 0.1314 (0.1416) loss: 0.8423 (0.8447) time: 0.2061 data: 0.1298 max mem: 8255 +Train: [82] [1200/6250] eta: 0:14:49 lr: 0.000011 grad: 0.1317 (0.1417) loss: 0.8316 (0.8441) time: 0.1520 data: 0.0767 max mem: 8255 +Train: [82] [1300/6250] eta: 0:14:28 lr: 0.000011 grad: 0.1396 (0.1414) loss: 0.8401 (0.8434) time: 0.1652 data: 0.0979 max mem: 8255 +Train: [82] [1400/6250] eta: 0:14:02 lr: 0.000010 grad: 0.1316 (0.1412) loss: 0.8335 (0.8429) time: 0.1782 data: 0.1074 max mem: 8255 +Train: [82] [1500/6250] eta: 0:13:37 lr: 0.000010 grad: 0.1375 (0.1412) loss: 0.8412 (0.8425) time: 0.1566 data: 0.0939 max mem: 8255 +Train: [82] [1600/6250] eta: 0:13:21 lr: 0.000010 grad: 0.1371 (0.1412) loss: 0.8373 (0.8420) time: 0.2213 data: 0.1502 max mem: 8255 +Train: [82] [1700/6250] eta: 0:12:54 lr: 0.000010 grad: 0.1363 (0.1411) loss: 0.8295 (0.8414) time: 0.1482 data: 0.0779 max mem: 8255 +Train: [82] [1800/6250] eta: 0:12:40 lr: 0.000010 grad: 0.1341 (0.1411) loss: 0.8329 (0.8411) time: 0.1319 data: 0.0402 max mem: 8255 +Train: [82] [1900/6250] eta: 0:12:19 lr: 0.000010 grad: 0.1459 (0.1410) loss: 0.8378 (0.8409) time: 0.1742 data: 0.0963 max mem: 8255 +Train: [82] [2000/6250] eta: 0:11:57 lr: 0.000010 grad: 0.1361 (0.1410) loss: 0.8329 (0.8405) time: 0.1469 data: 0.0718 max mem: 8255 +Train: [82] [2100/6250] eta: 0:11:34 lr: 0.000010 grad: 0.1309 (0.1409) loss: 0.8413 (0.8402) time: 0.1474 data: 0.0660 max mem: 8255 +Train: [82] [2200/6250] eta: 0:11:11 lr: 0.000010 grad: 0.1343 (0.1408) loss: 0.8380 (0.8400) time: 0.1232 data: 0.0550 max mem: 8255 +Train: [82] [2300/6250] eta: 0:10:50 lr: 0.000010 grad: 0.1314 (0.1407) loss: 0.8379 (0.8397) time: 0.1409 data: 0.0775 max mem: 8255 +Train: [82] [2400/6250] eta: 0:10:28 lr: 0.000010 grad: 0.1329 (0.1407) loss: 0.8298 (0.8395) time: 0.1468 data: 0.0747 max mem: 8255 +Train: [82] [2500/6250] eta: 0:10:10 lr: 0.000010 grad: 0.1381 (0.1405) loss: 0.8403 (0.8396) time: 0.1390 data: 0.0604 max mem: 8255 +Train: [82] [2600/6250] eta: 0:09:50 lr: 0.000010 grad: 0.1366 (0.1405) loss: 0.8285 (0.8394) time: 0.1320 data: 0.0545 max mem: 8255 +Train: [82] [2700/6250] eta: 0:09:33 lr: 0.000010 grad: 0.1313 (0.1404) loss: 0.8380 (0.8393) time: 0.1779 data: 0.1056 max mem: 8255 +Train: [82] [2800/6250] eta: 0:09:15 lr: 0.000010 grad: 0.1379 (0.1404) loss: 0.8364 (0.8392) time: 0.1447 data: 0.0634 max mem: 8255 +Train: [82] [2900/6250] eta: 0:08:58 lr: 0.000010 grad: 0.1429 (0.1403) loss: 0.8382 (0.8391) time: 0.1827 data: 0.1153 max mem: 8255 +Train: [82] [3000/6250] eta: 0:08:41 lr: 0.000010 grad: 0.1402 (0.1402) loss: 0.8332 (0.8390) time: 0.1231 data: 0.0235 max mem: 8255 +Train: [82] [3100/6250] eta: 0:08:26 lr: 0.000010 grad: 0.1377 (0.1402) loss: 0.8378 (0.8389) time: 0.0984 data: 0.0003 max mem: 8255 +Train: [82] [3200/6250] eta: 0:08:12 lr: 0.000010 grad: 0.1383 (0.1402) loss: 0.8307 (0.8388) time: 0.2632 data: 0.1689 max mem: 8255 +Train: [82] [3300/6250] eta: 0:07:57 lr: 0.000010 grad: 0.1405 (0.1402) loss: 0.8367 (0.8387) time: 0.1801 data: 0.1011 max mem: 8255 +Train: [82] [3400/6250] eta: 0:07:44 lr: 0.000010 grad: 0.1367 (0.1402) loss: 0.8366 (0.8385) time: 0.0973 data: 0.0002 max mem: 8255 +Train: [82] [3500/6250] eta: 0:07:26 lr: 0.000010 grad: 0.1417 (0.1403) loss: 0.8375 (0.8385) time: 0.1486 data: 0.0743 max mem: 8255 +Train: [82] [3600/6250] eta: 0:07:09 lr: 0.000010 grad: 0.1355 (0.1402) loss: 0.8354 (0.8385) time: 0.1176 data: 0.0444 max mem: 8255 +Train: [82] [3700/6250] eta: 0:06:51 lr: 0.000010 grad: 0.1352 (0.1401) loss: 0.8399 (0.8385) time: 0.1343 data: 0.0604 max mem: 8255 +Train: [82] [3800/6250] eta: 0:06:35 lr: 0.000010 grad: 0.1393 (0.1401) loss: 0.8415 (0.8385) time: 0.0927 data: 0.0002 max mem: 8255 +Train: [82] [3900/6250] eta: 0:06:18 lr: 0.000010 grad: 0.1355 (0.1400) loss: 0.8350 (0.8385) time: 0.1249 data: 0.0472 max mem: 8255 +Train: [82] [4000/6250] eta: 0:06:00 lr: 0.000010 grad: 0.1308 (0.1400) loss: 0.8419 (0.8385) time: 0.1381 data: 0.0635 max mem: 8255 +Train: [82] [4100/6250] eta: 0:05:43 lr: 0.000010 grad: 0.1312 (0.1400) loss: 0.8434 (0.8384) time: 0.1239 data: 0.0470 max mem: 8255 +Train: [82] [4200/6250] eta: 0:05:27 lr: 0.000010 grad: 0.1336 (0.1400) loss: 0.8410 (0.8384) time: 0.2075 data: 0.1292 max mem: 8255 +Train: [82] [4300/6250] eta: 0:05:10 lr: 0.000010 grad: 0.1409 (0.1399) loss: 0.8360 (0.8383) time: 0.1272 data: 0.0548 max mem: 8255 +Train: [82] [4400/6250] eta: 0:04:54 lr: 0.000010 grad: 0.1410 (0.1400) loss: 0.8331 (0.8383) time: 0.1142 data: 0.0373 max mem: 8255 +Train: [82] [4500/6250] eta: 0:04:37 lr: 0.000010 grad: 0.1368 (0.1400) loss: 0.8358 (0.8382) time: 0.1398 data: 0.0582 max mem: 8255 +Train: [82] [4600/6250] eta: 0:04:21 lr: 0.000010 grad: 0.1326 (0.1400) loss: 0.8298 (0.8381) time: 0.1492 data: 0.0754 max mem: 8255 +Train: [82] [4700/6250] eta: 0:04:06 lr: 0.000010 grad: 0.1369 (0.1400) loss: 0.8369 (0.8382) time: 0.2170 data: 0.1365 max mem: 8255 +Train: [82] [4800/6250] eta: 0:03:50 lr: 0.000010 grad: 0.1374 (0.1401) loss: 0.8285 (0.8381) time: 0.1469 data: 0.0761 max mem: 8255 +Train: [82] [4900/6250] eta: 0:03:33 lr: 0.000010 grad: 0.1364 (0.1401) loss: 0.8419 (0.8380) time: 0.1441 data: 0.0623 max mem: 8255 +Train: [82] [5000/6250] eta: 0:03:17 lr: 0.000010 grad: 0.1419 (0.1401) loss: 0.8338 (0.8380) time: 0.1583 data: 0.0867 max mem: 8255 +Train: [82] [5100/6250] eta: 0:03:01 lr: 0.000010 grad: 0.1310 (0.1402) loss: 0.8407 (0.8380) time: 0.2064 data: 0.1421 max mem: 8255 +Train: [82] [5200/6250] eta: 0:02:45 lr: 0.000010 grad: 0.1347 (0.1401) loss: 0.8376 (0.8380) time: 0.1402 data: 0.0590 max mem: 8255 +Train: [82] [5300/6250] eta: 0:02:29 lr: 0.000010 grad: 0.1307 (0.1400) loss: 0.8401 (0.8380) time: 0.1359 data: 0.0595 max mem: 8255 +Train: [82] [5400/6250] eta: 0:02:13 lr: 0.000010 grad: 0.1382 (0.1400) loss: 0.8362 (0.8380) time: 0.1540 data: 0.0769 max mem: 8255 +Train: [82] [5500/6250] eta: 0:01:57 lr: 0.000010 grad: 0.1352 (0.1399) loss: 0.8325 (0.8380) time: 0.1420 data: 0.0710 max mem: 8255 +Train: [82] [5600/6250] eta: 0:01:42 lr: 0.000010 grad: 0.1326 (0.1399) loss: 0.8396 (0.8379) time: 0.1089 data: 0.0006 max mem: 8255 +Train: [82] [5700/6250] eta: 0:01:26 lr: 0.000010 grad: 0.1324 (0.1398) loss: 0.8326 (0.8379) time: 0.1394 data: 0.0599 max mem: 8255 +Train: [82] [5800/6250] eta: 0:01:10 lr: 0.000010 grad: 0.1384 (0.1398) loss: 0.8341 (0.8378) time: 0.1314 data: 0.0564 max mem: 8255 +Train: [82] [5900/6250] eta: 0:00:54 lr: 0.000010 grad: 0.1304 (0.1398) loss: 0.8387 (0.8378) time: 0.2335 data: 0.1491 max mem: 8255 +Train: [82] [6000/6250] eta: 0:00:39 lr: 0.000010 grad: 0.1348 (0.1398) loss: 0.8411 (0.8377) time: 0.1416 data: 0.0678 max mem: 8255 +Train: [82] [6100/6250] eta: 0:00:23 lr: 0.000010 grad: 0.1356 (0.1398) loss: 0.8401 (0.8377) time: 0.1514 data: 0.0777 max mem: 8255 +Train: [82] [6200/6250] eta: 0:00:07 lr: 0.000010 grad: 0.1329 (0.1398) loss: 0.8441 (0.8377) time: 0.1365 data: 0.0613 max mem: 8255 +Train: [82] [6249/6250] eta: 0:00:00 lr: 0.000010 grad: 0.1450 (0.1398) loss: 0.8390 (0.8377) time: 0.2036 data: 0.1030 max mem: 8255 +Train: [82] Total time: 0:16:22 (0.1572 s / it) +Averaged stats: lr: 0.000010 grad: 0.1450 (0.1398) loss: 0.8390 (0.8377) +Eval (hcp-train-subset): [82] [ 0/62] eta: 0:06:11 loss: 0.8585 (0.8585) time: 5.9960 data: 5.9667 max mem: 8255 +Eval (hcp-train-subset): [82] [61/62] eta: 0:00:00 loss: 0.8477 (0.8523) time: 0.1402 data: 0.1179 max mem: 8255 +Eval (hcp-train-subset): [82] Total time: 0:00:16 (0.2589 s / it) +Averaged stats (hcp-train-subset): loss: 0.8477 (0.8523) +Eval (hcp-val): [82] [ 0/62] eta: 0:06:16 loss: 0.8708 (0.8708) time: 6.0734 data: 6.0466 max mem: 8255 +Eval (hcp-val): [82] [61/62] eta: 0:00:00 loss: 0.8730 (0.8728) time: 0.1202 data: 0.0993 max mem: 8255 +Eval (hcp-val): [82] Total time: 0:00:13 (0.2149 s / it) +Averaged stats (hcp-val): loss: 0.8730 (0.8728) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +Train: [83] [ 0/6250] eta: 9:50:00 lr: 0.000010 grad: 0.3027 (0.3027) loss: 0.8778 (0.8778) time: 5.6640 data: 5.5013 max mem: 8255 +Train: [83] [ 100/6250] eta: 0:23:07 lr: 0.000010 grad: 0.1649 (0.1859) loss: 0.8502 (0.8635) time: 0.1856 data: 0.0816 max mem: 8255 +Train: [83] [ 200/6250] eta: 0:20:55 lr: 0.000010 grad: 0.1552 (0.1748) loss: 0.8446 (0.8551) time: 0.1689 data: 0.0642 max mem: 8255 +Train: [83] [ 300/6250] eta: 0:19:42 lr: 0.000010 grad: 0.1503 (0.1685) loss: 0.8421 (0.8502) time: 0.1665 data: 0.0775 max mem: 8255 +Train: [83] [ 400/6250] eta: 0:19:10 lr: 0.000010 grad: 0.1374 (0.1647) loss: 0.8437 (0.8482) time: 0.2100 data: 0.1150 max mem: 8255 +Train: [83] [ 500/6250] eta: 0:18:08 lr: 0.000010 grad: 0.1343 (0.1612) loss: 0.8411 (0.8473) time: 0.1557 data: 0.0772 max mem: 8255 +Train: [83] [ 600/6250] eta: 0:17:22 lr: 0.000010 grad: 0.1405 (0.1587) loss: 0.8454 (0.8470) time: 0.1406 data: 0.0545 max mem: 8255 +Train: [83] [ 700/6250] eta: 0:16:49 lr: 0.000009 grad: 0.1373 (0.1575) loss: 0.8504 (0.8459) time: 0.2144 data: 0.1327 max mem: 8255 +Train: [83] [ 800/6250] eta: 0:16:24 lr: 0.000009 grad: 0.1335 (0.1560) loss: 0.8385 (0.8457) time: 0.1201 data: 0.0267 max mem: 8255 +Train: [83] [ 900/6250] eta: 0:15:44 lr: 0.000009 grad: 0.1399 (0.1549) loss: 0.8387 (0.8452) time: 0.1478 data: 0.0563 max mem: 8255 +Train: [83] [1000/6250] eta: 0:15:21 lr: 0.000009 grad: 0.1456 (0.1536) loss: 0.8459 (0.8448) time: 0.1998 data: 0.1216 max mem: 8255 +Train: [83] [1100/6250] eta: 0:14:47 lr: 0.000009 grad: 0.1418 (0.1526) loss: 0.8379 (0.8445) time: 0.1464 data: 0.0632 max mem: 8255 +Train: [83] [1200/6250] eta: 0:14:29 lr: 0.000009 grad: 0.1458 (0.1517) loss: 0.8436 (0.8442) time: 0.1584 data: 0.0884 max mem: 8255 +Train: [83] [1300/6250] eta: 0:14:00 lr: 0.000009 grad: 0.1364 (0.1510) loss: 0.8387 (0.8440) time: 0.1411 data: 0.0677 max mem: 8255 +Train: [83] [1400/6250] eta: 0:13:38 lr: 0.000009 grad: 0.1439 (0.1504) loss: 0.8353 (0.8437) time: 0.1773 data: 0.1060 max mem: 8255 +Train: [83] [1500/6250] eta: 0:13:11 lr: 0.000009 grad: 0.1393 (0.1499) loss: 0.8427 (0.8434) time: 0.1199 data: 0.0292 max mem: 8255 +Train: [83] [1600/6250] eta: 0:12:58 lr: 0.000009 grad: 0.1376 (0.1495) loss: 0.8367 (0.8431) time: 0.2006 data: 0.1239 max mem: 8255 +Train: [83] [1700/6250] eta: 0:12:38 lr: 0.000009 grad: 0.1459 (0.1491) loss: 0.8304 (0.8428) time: 0.1710 data: 0.0948 max mem: 8255 +Train: [83] [1800/6250] eta: 0:12:19 lr: 0.000009 grad: 0.1448 (0.1489) loss: 0.8381 (0.8426) time: 0.1273 data: 0.0588 max mem: 8255 +Train: [83] [1900/6250] eta: 0:12:03 lr: 0.000009 grad: 0.1398 (0.1486) loss: 0.8342 (0.8424) time: 0.2371 data: 0.1400 max mem: 8255 +Train: [83] [2000/6250] eta: 0:11:38 lr: 0.000009 grad: 0.1418 (0.1481) loss: 0.8351 (0.8422) time: 0.1510 data: 0.0761 max mem: 8255 +Train: [83] [2100/6250] eta: 0:11:22 lr: 0.000009 grad: 0.1351 (0.1477) loss: 0.8395 (0.8420) time: 0.1557 data: 0.0864 max mem: 8255 +Train: [83] [2200/6250] eta: 0:11:03 lr: 0.000009 grad: 0.1296 (0.1474) loss: 0.8486 (0.8420) time: 0.1655 data: 0.0819 max mem: 8255 +Train: [83] [2300/6250] eta: 0:10:44 lr: 0.000009 grad: 0.1320 (0.1469) loss: 0.8449 (0.8420) time: 0.1431 data: 0.0697 max mem: 8255 +Train: [83] [2400/6250] eta: 0:10:25 lr: 0.000009 grad: 0.1331 (0.1467) loss: 0.8425 (0.8419) time: 0.1449 data: 0.0643 max mem: 8255 +Train: [83] [2500/6250] eta: 0:10:06 lr: 0.000009 grad: 0.1386 (0.1464) loss: 0.8427 (0.8419) time: 0.1354 data: 0.0583 max mem: 8255 +Train: [83] [2600/6250] eta: 0:09:48 lr: 0.000009 grad: 0.1352 (0.1461) loss: 0.8412 (0.8418) time: 0.1871 data: 0.1176 max mem: 8255 +Train: [83] [2700/6250] eta: 0:09:27 lr: 0.000009 grad: 0.1359 (0.1458) loss: 0.8389 (0.8418) time: 0.1363 data: 0.0695 max mem: 8255 +Train: [83] [2800/6250] eta: 0:09:09 lr: 0.000009 grad: 0.1334 (0.1456) loss: 0.8373 (0.8417) time: 0.1469 data: 0.0525 max mem: 8255 +Train: [83] [2900/6250] eta: 0:08:49 lr: 0.000009 grad: 0.1384 (0.1453) loss: 0.8388 (0.8416) time: 0.1316 data: 0.0638 max mem: 8255 +Train: [83] [3000/6250] eta: 0:08:30 lr: 0.000009 grad: 0.1345 (0.1451) loss: 0.8336 (0.8415) time: 0.1330 data: 0.0623 max mem: 8255 +Train: [83] [3100/6250] eta: 0:08:13 lr: 0.000009 grad: 0.1395 (0.1449) loss: 0.8365 (0.8414) time: 0.1713 data: 0.0968 max mem: 8255 +Train: [83] [3200/6250] eta: 0:07:56 lr: 0.000009 grad: 0.1396 (0.1447) loss: 0.8388 (0.8414) time: 0.1487 data: 0.0737 max mem: 8255 +Train: [83] [3300/6250] eta: 0:07:40 lr: 0.000009 grad: 0.1410 (0.1445) loss: 0.8307 (0.8413) time: 0.1646 data: 0.0810 max mem: 8255 +Train: [83] [3400/6250] eta: 0:07:24 lr: 0.000009 grad: 0.1369 (0.1444) loss: 0.8374 (0.8412) time: 0.1427 data: 0.0652 max mem: 8255 +Train: [83] [3500/6250] eta: 0:07:08 lr: 0.000009 grad: 0.1351 (0.1443) loss: 0.8382 (0.8411) time: 0.1547 data: 0.0771 max mem: 8255 +Train: [83] [3600/6250] eta: 0:06:52 lr: 0.000009 grad: 0.1439 (0.1442) loss: 0.8429 (0.8411) time: 0.1746 data: 0.1094 max mem: 8255 +Train: [83] [3700/6250] eta: 0:06:35 lr: 0.000009 grad: 0.1334 (0.1441) loss: 0.8399 (0.8410) time: 0.1436 data: 0.0632 max mem: 8255 +Train: [83] [3800/6250] eta: 0:06:22 lr: 0.000009 grad: 0.1341 (0.1440) loss: 0.8401 (0.8410) time: 0.3471 data: 0.2516 max mem: 8255 +Train: [83] [3900/6250] eta: 0:06:04 lr: 0.000009 grad: 0.1395 (0.1439) loss: 0.8404 (0.8410) time: 0.1193 data: 0.0440 max mem: 8255 +Train: [83] [4000/6250] eta: 0:05:48 lr: 0.000009 grad: 0.1386 (0.1438) loss: 0.8349 (0.8409) time: 0.1289 data: 0.0569 max mem: 8255 +Train: [83] [4100/6250] eta: 0:05:33 lr: 0.000009 grad: 0.1458 (0.1438) loss: 0.8347 (0.8408) time: 0.2757 data: 0.1946 max mem: 8255 +Train: [83] [4200/6250] eta: 0:05:18 lr: 0.000009 grad: 0.1409 (0.1437) loss: 0.8367 (0.8407) time: 0.1395 data: 0.0527 max mem: 8255 +Train: [83] [4300/6250] eta: 0:05:02 lr: 0.000009 grad: 0.1401 (0.1437) loss: 0.8369 (0.8405) time: 0.1476 data: 0.0838 max mem: 8255 +Train: [83] [4400/6250] eta: 0:04:46 lr: 0.000009 grad: 0.1411 (0.1436) loss: 0.8403 (0.8404) time: 0.1175 data: 0.0378 max mem: 8255 +Train: [83] [4500/6250] eta: 0:04:30 lr: 0.000009 grad: 0.1393 (0.1435) loss: 0.8360 (0.8403) time: 0.1436 data: 0.0724 max mem: 8255 +Train: [83] [4600/6250] eta: 0:04:15 lr: 0.000009 grad: 0.1415 (0.1436) loss: 0.8383 (0.8402) time: 0.1778 data: 0.0871 max mem: 8255 +Train: [83] [4700/6250] eta: 0:04:00 lr: 0.000009 grad: 0.1364 (0.1435) loss: 0.8375 (0.8402) time: 0.1421 data: 0.0701 max mem: 8255 +Train: [83] [4800/6250] eta: 0:03:44 lr: 0.000009 grad: 0.1418 (0.1436) loss: 0.8355 (0.8401) time: 0.1591 data: 0.0842 max mem: 8255 +Train: [83] [4900/6250] eta: 0:03:29 lr: 0.000009 grad: 0.1397 (0.1436) loss: 0.8464 (0.8401) time: 0.1494 data: 0.0692 max mem: 8255 +Train: [83] [5000/6250] eta: 0:03:13 lr: 0.000009 grad: 0.1449 (0.1436) loss: 0.8428 (0.8400) time: 0.1291 data: 0.0590 max mem: 8255 +Train: [83] [5100/6250] eta: 0:02:57 lr: 0.000009 grad: 0.1372 (0.1437) loss: 0.8362 (0.8400) time: 0.1601 data: 0.0828 max mem: 8255 +Train: [83] [5200/6250] eta: 0:02:42 lr: 0.000009 grad: 0.1370 (0.1436) loss: 0.8411 (0.8399) time: 0.1154 data: 0.0168 max mem: 8255 +Train: [83] [5300/6250] eta: 0:02:27 lr: 0.000009 grad: 0.1414 (0.1436) loss: 0.8364 (0.8398) time: 0.1256 data: 0.0439 max mem: 8255 +Train: [83] [5400/6250] eta: 0:02:11 lr: 0.000009 grad: 0.1360 (0.1436) loss: 0.8426 (0.8398) time: 0.1989 data: 0.1218 max mem: 8255 +Train: [83] [5500/6250] eta: 0:01:56 lr: 0.000009 grad: 0.1337 (0.1435) loss: 0.8365 (0.8397) time: 0.1287 data: 0.0645 max mem: 8255 +Train: [83] [5600/6250] eta: 0:01:40 lr: 0.000009 grad: 0.1389 (0.1435) loss: 0.8402 (0.8397) time: 0.1510 data: 0.0764 max mem: 8255 +Train: [83] [5700/6250] eta: 0:01:25 lr: 0.000009 grad: 0.1354 (0.1434) loss: 0.8412 (0.8397) time: 0.1505 data: 0.0836 max mem: 8255 +Train: [83] [5800/6250] eta: 0:01:09 lr: 0.000009 grad: 0.1323 (0.1433) loss: 0.8436 (0.8397) time: 0.1407 data: 0.0559 max mem: 8255 +Train: [83] [5900/6250] eta: 0:00:53 lr: 0.000009 grad: 0.1375 (0.1432) loss: 0.8379 (0.8397) time: 0.1148 data: 0.0301 max mem: 8255 +Train: [83] [6000/6250] eta: 0:00:38 lr: 0.000009 grad: 0.1382 (0.1432) loss: 0.8334 (0.8397) time: 0.1307 data: 0.0552 max mem: 8255 +Train: [83] [6100/6250] eta: 0:00:23 lr: 0.000009 grad: 0.1389 (0.1432) loss: 0.8349 (0.8397) time: 0.1539 data: 0.0709 max mem: 8255 +Train: [83] [6200/6250] eta: 0:00:07 lr: 0.000009 grad: 0.1430 (0.1432) loss: 0.8405 (0.8397) time: 0.1452 data: 0.0705 max mem: 8255 +Train: [83] [6249/6250] eta: 0:00:00 lr: 0.000009 grad: 0.1383 (0.1432) loss: 0.8403 (0.8397) time: 0.1722 data: 0.1027 max mem: 8255 +Train: [83] Total time: 0:16:09 (0.1551 s / it) +Averaged stats: lr: 0.000009 grad: 0.1383 (0.1432) loss: 0.8403 (0.8397) +Eval (hcp-train-subset): [83] [ 0/62] eta: 0:06:32 loss: 0.8569 (0.8569) time: 6.3330 data: 6.3027 max mem: 8255 +Eval (hcp-train-subset): [83] [61/62] eta: 0:00:00 loss: 0.8487 (0.8521) time: 0.1278 data: 0.1069 max mem: 8255 +Eval (hcp-train-subset): [83] Total time: 0:00:15 (0.2562 s / it) +Averaged stats (hcp-train-subset): loss: 0.8487 (0.8521) +Eval (hcp-val): [83] [ 0/62] eta: 0:06:39 loss: 0.8713 (0.8713) time: 6.4468 data: 6.4199 max mem: 8255 +Eval (hcp-val): [83] [61/62] eta: 0:00:00 loss: 0.8712 (0.8734) time: 0.1574 data: 0.1351 max mem: 8255 +Eval (hcp-val): [83] Total time: 0:00:14 (0.2418 s / it) +Averaged stats (hcp-val): loss: 0.8712 (0.8734) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +Train: [84] [ 0/6250] eta: 12:07:06 lr: 0.000009 grad: 0.4355 (0.4355) loss: 0.8150 (0.8150) time: 6.9802 data: 6.8795 max mem: 8255 +Train: [84] [ 100/6250] eta: 0:20:57 lr: 0.000009 grad: 0.1606 (0.1779) loss: 0.8443 (0.8512) time: 0.1536 data: 0.0582 max mem: 8255 +Train: [84] [ 200/6250] eta: 0:18:24 lr: 0.000009 grad: 0.1448 (0.1668) loss: 0.8496 (0.8491) time: 0.1660 data: 0.0628 max mem: 8255 +Train: [84] [ 300/6250] eta: 0:17:48 lr: 0.000008 grad: 0.1416 (0.1603) loss: 0.8464 (0.8488) time: 0.2015 data: 0.1044 max mem: 8255 +Train: [84] [ 400/6250] eta: 0:17:09 lr: 0.000008 grad: 0.1544 (0.1563) loss: 0.8461 (0.8480) time: 0.1787 data: 0.0864 max mem: 8255 +Train: [84] [ 500/6250] eta: 0:16:32 lr: 0.000008 grad: 0.1308 (0.1547) loss: 0.8539 (0.8467) time: 0.1560 data: 0.0686 max mem: 8255 +Train: [84] [ 600/6250] eta: 0:16:11 lr: 0.000008 grad: 0.1464 (0.1535) loss: 0.8458 (0.8461) time: 0.1937 data: 0.1177 max mem: 8255 +Train: [84] [ 700/6250] eta: 0:15:33 lr: 0.000008 grad: 0.1379 (0.1529) loss: 0.8405 (0.8451) time: 0.1453 data: 0.0587 max mem: 8255 +Train: [84] [ 800/6250] eta: 0:15:11 lr: 0.000008 grad: 0.1408 (0.1525) loss: 0.8450 (0.8443) time: 0.1558 data: 0.0770 max mem: 8255 +Train: [84] [ 900/6250] eta: 0:14:54 lr: 0.000008 grad: 0.1492 (0.1525) loss: 0.8379 (0.8434) time: 0.1005 data: 0.0002 max mem: 8255 +Train: [84] [1000/6250] eta: 0:14:47 lr: 0.000008 grad: 0.1397 (0.1520) loss: 0.8431 (0.8431) time: 0.2322 data: 0.1599 max mem: 8255 +Train: [84] [1100/6250] eta: 0:15:00 lr: 0.000008 grad: 0.1414 (0.1515) loss: 0.8360 (0.8426) time: 0.2841 data: 0.1725 max mem: 8255 +Train: [84] [1200/6250] eta: 0:15:10 lr: 0.000008 grad: 0.1382 (0.1507) loss: 0.8381 (0.8425) time: 0.1299 data: 0.0339 max mem: 8255 +Train: [84] [1300/6250] eta: 0:14:46 lr: 0.000008 grad: 0.1406 (0.1502) loss: 0.8359 (0.8419) time: 0.1802 data: 0.1003 max mem: 8255 +Train: [84] [1400/6250] eta: 0:14:17 lr: 0.000008 grad: 0.1385 (0.1498) loss: 0.8395 (0.8417) time: 0.1436 data: 0.0518 max mem: 8255 +Train: [84] [1500/6250] eta: 0:14:08 lr: 0.000008 grad: 0.1454 (0.1494) loss: 0.8370 (0.8414) time: 0.3032 data: 0.2100 max mem: 8255 +Train: [84] [1600/6250] eta: 0:13:38 lr: 0.000008 grad: 0.1421 (0.1489) loss: 0.8352 (0.8412) time: 0.1174 data: 0.0278 max mem: 8255 +Train: [84] [1700/6250] eta: 0:13:17 lr: 0.000008 grad: 0.1459 (0.1486) loss: 0.8388 (0.8410) time: 0.1692 data: 0.0880 max mem: 8255 +Train: [84] [1800/6250] eta: 0:12:57 lr: 0.000008 grad: 0.1435 (0.1484) loss: 0.8386 (0.8409) time: 0.1260 data: 0.0504 max mem: 8255 +Train: [84] [1900/6250] eta: 0:12:34 lr: 0.000008 grad: 0.1380 (0.1482) loss: 0.8418 (0.8407) time: 0.1424 data: 0.0487 max mem: 8255 +Train: [84] [2000/6250] eta: 0:12:11 lr: 0.000008 grad: 0.1358 (0.1480) loss: 0.8385 (0.8405) time: 0.1611 data: 0.0810 max mem: 8255 +Train: [84] [2100/6250] eta: 0:11:50 lr: 0.000008 grad: 0.1408 (0.1478) loss: 0.8357 (0.8404) time: 0.1575 data: 0.0792 max mem: 8255 +Train: [84] [2200/6250] eta: 0:11:30 lr: 0.000008 grad: 0.1421 (0.1477) loss: 0.8305 (0.8403) time: 0.1651 data: 0.0777 max mem: 8255 +Train: [84] [2300/6250] eta: 0:11:14 lr: 0.000008 grad: 0.1332 (0.1475) loss: 0.8434 (0.8402) time: 0.1603 data: 0.0824 max mem: 8255 +Train: [84] [2400/6250] eta: 0:10:56 lr: 0.000008 grad: 0.1393 (0.1473) loss: 0.8372 (0.8401) time: 0.1677 data: 0.0847 max mem: 8255 +Train: [84] [2500/6250] eta: 0:10:39 lr: 0.000008 grad: 0.1398 (0.1471) loss: 0.8367 (0.8401) time: 0.1604 data: 0.0786 max mem: 8255 +Train: [84] [2600/6250] eta: 0:10:19 lr: 0.000008 grad: 0.1376 (0.1469) loss: 0.8399 (0.8400) time: 0.1203 data: 0.0412 max mem: 8255 +Train: [84] [2700/6250] eta: 0:09:59 lr: 0.000008 grad: 0.1385 (0.1468) loss: 0.8392 (0.8399) time: 0.1667 data: 0.0900 max mem: 8255 +Train: [84] [2800/6250] eta: 0:09:39 lr: 0.000008 grad: 0.1396 (0.1466) loss: 0.8409 (0.8399) time: 0.1176 data: 0.0519 max mem: 8255 +Train: [84] [2900/6250] eta: 0:09:20 lr: 0.000008 grad: 0.1450 (0.1466) loss: 0.8380 (0.8398) time: 0.1494 data: 0.0745 max mem: 8255 +Train: [84] [3000/6250] eta: 0:09:00 lr: 0.000008 grad: 0.1398 (0.1465) loss: 0.8458 (0.8398) time: 0.1601 data: 0.0793 max mem: 8255 +Train: [84] [3100/6250] eta: 0:08:41 lr: 0.000008 grad: 0.1415 (0.1463) loss: 0.8358 (0.8397) time: 0.1387 data: 0.0689 max mem: 8255 +Train: [84] [3200/6250] eta: 0:08:23 lr: 0.000008 grad: 0.1327 (0.1462) loss: 0.8417 (0.8396) time: 0.1166 data: 0.0414 max mem: 8255 +Train: [84] [3300/6250] eta: 0:08:06 lr: 0.000008 grad: 0.1455 (0.1462) loss: 0.8299 (0.8395) time: 0.1775 data: 0.1026 max mem: 8255 +Train: [84] [3400/6250] eta: 0:07:49 lr: 0.000008 grad: 0.1374 (0.1461) loss: 0.8323 (0.8393) time: 0.1520 data: 0.0782 max mem: 8255 +Train: [84] [3500/6250] eta: 0:07:33 lr: 0.000008 grad: 0.1416 (0.1460) loss: 0.8356 (0.8392) time: 0.1705 data: 0.0844 max mem: 8255 +Train: [84] [3600/6250] eta: 0:07:15 lr: 0.000008 grad: 0.1326 (0.1459) loss: 0.8389 (0.8392) time: 0.1234 data: 0.0480 max mem: 8255 +Train: [84] [3700/6250] eta: 0:07:00 lr: 0.000008 grad: 0.1339 (0.1457) loss: 0.8346 (0.8392) time: 0.2609 data: 0.1501 max mem: 8255 +Train: [84] [3800/6250] eta: 0:06:44 lr: 0.000008 grad: 0.1445 (0.1456) loss: 0.8332 (0.8393) time: 0.1053 data: 0.0004 max mem: 8255 +Train: [84] [3900/6250] eta: 0:06:30 lr: 0.000008 grad: 0.1373 (0.1454) loss: 0.8350 (0.8393) time: 0.1375 data: 0.0002 max mem: 8255 +Train: [84] [4000/6250] eta: 0:06:12 lr: 0.000008 grad: 0.1294 (0.1452) loss: 0.8441 (0.8393) time: 0.1007 data: 0.0002 max mem: 8255 +Train: [84] [4100/6250] eta: 0:05:55 lr: 0.000008 grad: 0.1401 (0.1450) loss: 0.8428 (0.8394) time: 0.1493 data: 0.0579 max mem: 8255 +Train: [84] [4200/6250] eta: 0:05:39 lr: 0.000008 grad: 0.1345 (0.1449) loss: 0.8459 (0.8395) time: 0.1418 data: 0.0477 max mem: 8255 +Train: [84] [4300/6250] eta: 0:05:22 lr: 0.000008 grad: 0.1382 (0.1447) loss: 0.8402 (0.8395) time: 0.1267 data: 0.0357 max mem: 8255 +Train: [84] [4400/6250] eta: 0:05:06 lr: 0.000008 grad: 0.1280 (0.1446) loss: 0.8457 (0.8396) time: 0.1859 data: 0.0968 max mem: 8255 +Train: [84] [4500/6250] eta: 0:04:48 lr: 0.000008 grad: 0.1346 (0.1444) loss: 0.8421 (0.8396) time: 0.1774 data: 0.1098 max mem: 8255 +Train: [84] [4600/6250] eta: 0:04:31 lr: 0.000008 grad: 0.1353 (0.1443) loss: 0.8361 (0.8397) time: 0.1414 data: 0.0674 max mem: 8255 +Train: [84] [4700/6250] eta: 0:04:15 lr: 0.000008 grad: 0.1366 (0.1441) loss: 0.8374 (0.8397) time: 0.1616 data: 0.0580 max mem: 8255 +Train: [84] [4800/6250] eta: 0:03:58 lr: 0.000008 grad: 0.1347 (0.1441) loss: 0.8368 (0.8397) time: 0.1230 data: 0.0395 max mem: 8255 +Train: [84] [4900/6250] eta: 0:03:42 lr: 0.000008 grad: 0.1397 (0.1440) loss: 0.8397 (0.8397) time: 0.2022 data: 0.1296 max mem: 8255 +Train: [84] [5000/6250] eta: 0:03:25 lr: 0.000008 grad: 0.1376 (0.1440) loss: 0.8429 (0.8397) time: 0.1179 data: 0.0500 max mem: 8255 +Train: [84] [5100/6250] eta: 0:03:08 lr: 0.000008 grad: 0.1354 (0.1440) loss: 0.8384 (0.8397) time: 0.1560 data: 0.0840 max mem: 8255 +Train: [84] [5200/6250] eta: 0:02:52 lr: 0.000008 grad: 0.1349 (0.1440) loss: 0.8359 (0.8398) time: 0.1739 data: 0.1088 max mem: 8255 +Train: [84] [5300/6250] eta: 0:02:35 lr: 0.000008 grad: 0.1454 (0.1439) loss: 0.8276 (0.8397) time: 0.1638 data: 0.0946 max mem: 8255 +Train: [84] [5400/6250] eta: 0:02:18 lr: 0.000008 grad: 0.1364 (0.1438) loss: 0.8382 (0.8397) time: 0.1387 data: 0.0604 max mem: 8255 +Train: [84] [5500/6250] eta: 0:02:02 lr: 0.000008 grad: 0.1404 (0.1439) loss: 0.8331 (0.8397) time: 0.2982 data: 0.1931 max mem: 8255 +Train: [84] [5600/6250] eta: 0:01:46 lr: 0.000008 grad: 0.1395 (0.1439) loss: 0.8392 (0.8396) time: 0.1909 data: 0.1072 max mem: 8255 +Train: [84] [5700/6250] eta: 0:01:30 lr: 0.000008 grad: 0.1329 (0.1439) loss: 0.8383 (0.8396) time: 0.2011 data: 0.1231 max mem: 8255 +Train: [84] [5800/6250] eta: 0:01:13 lr: 0.000008 grad: 0.1386 (0.1438) loss: 0.8303 (0.8395) time: 0.1573 data: 0.0677 max mem: 8255 +Train: [84] [5900/6250] eta: 0:00:57 lr: 0.000008 grad: 0.1380 (0.1438) loss: 0.8351 (0.8395) time: 0.1310 data: 0.0368 max mem: 8255 +Train: [84] [6000/6250] eta: 0:00:40 lr: 0.000008 grad: 0.1375 (0.1437) loss: 0.8420 (0.8395) time: 0.1427 data: 0.0761 max mem: 8255 +Train: [84] [6100/6250] eta: 0:00:24 lr: 0.000008 grad: 0.1409 (0.1436) loss: 0.8307 (0.8395) time: 0.1425 data: 0.0631 max mem: 8255 +Train: [84] [6200/6250] eta: 0:00:08 lr: 0.000008 grad: 0.1347 (0.1436) loss: 0.8422 (0.8395) time: 0.1317 data: 0.0555 max mem: 8255 +Train: [84] [6249/6250] eta: 0:00:00 lr: 0.000008 grad: 0.1343 (0.1436) loss: 0.8392 (0.8395) time: 0.1572 data: 0.0750 max mem: 8255 +Train: [84] Total time: 0:17:01 (0.1635 s / it) +Averaged stats: lr: 0.000008 grad: 0.1343 (0.1436) loss: 0.8392 (0.8395) +Eval (hcp-train-subset): [84] [ 0/62] eta: 0:05:34 loss: 0.8556 (0.8556) time: 5.3929 data: 5.3620 max mem: 8255 +Eval (hcp-train-subset): [84] [61/62] eta: 0:00:00 loss: 0.8474 (0.8511) time: 0.1474 data: 0.1264 max mem: 8255 +Eval (hcp-train-subset): [84] Total time: 0:00:14 (0.2341 s / it) +Averaged stats (hcp-train-subset): loss: 0.8474 (0.8511) +Making plots (hcp-train-subset): example=9 +Eval (hcp-val): [84] [ 0/62] eta: 0:04:18 loss: 0.8679 (0.8679) time: 4.1763 data: 4.1314 max mem: 8255 +Eval (hcp-val): [84] [61/62] eta: 0:00:00 loss: 0.8721 (0.8729) time: 0.1286 data: 0.1078 max mem: 8255 +Eval (hcp-val): [84] Total time: 0:00:13 (0.2257 s / it) +Averaged stats (hcp-val): loss: 0.8721 (0.8729) +Making plots (hcp-val): example=39 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +Train: [85] [ 0/6250] eta: 11:12:31 lr: 0.000008 grad: 0.1873 (0.1873) loss: 0.8646 (0.8646) time: 6.4562 data: 6.3648 max mem: 8255 +Train: [85] [ 100/6250] eta: 0:20:57 lr: 0.000008 grad: 0.1522 (0.1728) loss: 0.8583 (0.8601) time: 0.1535 data: 0.0534 max mem: 8255 +Train: [85] [ 200/6250] eta: 0:17:52 lr: 0.000008 grad: 0.1561 (0.1720) loss: 0.8410 (0.8535) time: 0.1443 data: 0.0502 max mem: 8255 +Train: [85] [ 300/6250] eta: 0:16:31 lr: 0.000007 grad: 0.1629 (0.1713) loss: 0.8440 (0.8499) time: 0.1307 data: 0.0482 max mem: 8255 +Train: [85] [ 400/6250] eta: 0:15:51 lr: 0.000007 grad: 0.1542 (0.1676) loss: 0.8514 (0.8485) time: 0.1694 data: 0.0689 max mem: 8255 +Train: [85] [ 500/6250] eta: 0:15:38 lr: 0.000007 grad: 0.1407 (0.1650) loss: 0.8479 (0.8478) time: 0.1620 data: 0.0685 max mem: 8255 +Train: [85] [ 600/6250] eta: 0:14:54 lr: 0.000007 grad: 0.1429 (0.1617) loss: 0.8502 (0.8473) time: 0.1454 data: 0.0733 max mem: 8255 +Train: [85] [ 700/6250] eta: 0:14:21 lr: 0.000007 grad: 0.1399 (0.1596) loss: 0.8409 (0.8467) time: 0.1311 data: 0.0564 max mem: 8255 +Train: [85] [ 800/6250] eta: 0:14:00 lr: 0.000007 grad: 0.1454 (0.1585) loss: 0.8478 (0.8463) time: 0.1471 data: 0.0593 max mem: 8255 +Train: [85] [ 900/6250] eta: 0:13:45 lr: 0.000007 grad: 0.1433 (0.1576) loss: 0.8411 (0.8458) time: 0.1579 data: 0.0728 max mem: 8255 +Train: [85] [1000/6250] eta: 0:13:21 lr: 0.000007 grad: 0.1388 (0.1569) loss: 0.8368 (0.8454) time: 0.1306 data: 0.0425 max mem: 8255 +Train: [85] [1100/6250] eta: 0:13:04 lr: 0.000007 grad: 0.1364 (0.1556) loss: 0.8432 (0.8450) time: 0.1699 data: 0.0935 max mem: 8255 +Train: [85] [1200/6250] eta: 0:12:43 lr: 0.000007 grad: 0.1489 (0.1547) loss: 0.8331 (0.8446) time: 0.1434 data: 0.0592 max mem: 8255 +Train: [85] [1300/6250] eta: 0:12:37 lr: 0.000007 grad: 0.1354 (0.1539) loss: 0.8406 (0.8443) time: 0.1821 data: 0.0882 max mem: 8255 +Train: [85] [1400/6250] eta: 0:12:23 lr: 0.000007 grad: 0.1422 (0.1533) loss: 0.8375 (0.8437) time: 0.1693 data: 0.0694 max mem: 8255 +Train: [85] [1500/6250] eta: 0:12:23 lr: 0.000007 grad: 0.1413 (0.1528) loss: 0.8307 (0.8433) time: 0.1933 data: 0.1119 max mem: 8255 +Train: [85] [1600/6250] eta: 0:12:10 lr: 0.000007 grad: 0.1428 (0.1523) loss: 0.8376 (0.8430) time: 0.1729 data: 0.0548 max mem: 8255 +Train: [85] [1700/6250] eta: 0:12:08 lr: 0.000007 grad: 0.1427 (0.1520) loss: 0.8389 (0.8423) time: 0.1973 data: 0.1237 max mem: 8255 +Train: [85] [1800/6250] eta: 0:11:59 lr: 0.000007 grad: 0.1374 (0.1517) loss: 0.8332 (0.8418) time: 0.2979 data: 0.2046 max mem: 8255 +Train: [85] [1900/6250] eta: 0:11:41 lr: 0.000007 grad: 0.1462 (0.1514) loss: 0.8317 (0.8414) time: 0.1905 data: 0.1099 max mem: 8255 +Train: [85] [2000/6250] eta: 0:11:26 lr: 0.000007 grad: 0.1341 (0.1510) loss: 0.8293 (0.8409) time: 0.1374 data: 0.0484 max mem: 8255 +Train: [85] [2100/6250] eta: 0:11:09 lr: 0.000007 grad: 0.1473 (0.1508) loss: 0.8330 (0.8404) time: 0.1364 data: 0.0620 max mem: 8255 +Train: [85] [2200/6250] eta: 0:10:53 lr: 0.000007 grad: 0.1364 (0.1506) loss: 0.8319 (0.8399) time: 0.0919 data: 0.0002 max mem: 8255 +Train: [85] [2300/6250] eta: 0:10:36 lr: 0.000007 grad: 0.1386 (0.1503) loss: 0.8348 (0.8397) time: 0.1340 data: 0.0469 max mem: 8255 +Train: [85] [2400/6250] eta: 0:10:20 lr: 0.000007 grad: 0.1441 (0.1502) loss: 0.8252 (0.8393) time: 0.1306 data: 0.0447 max mem: 8255 +Train: [85] [2500/6250] eta: 0:10:03 lr: 0.000007 grad: 0.1434 (0.1501) loss: 0.8295 (0.8389) time: 0.1431 data: 0.0677 max mem: 8255 +Train: [85] [2600/6250] eta: 0:09:47 lr: 0.000007 grad: 0.1408 (0.1501) loss: 0.8385 (0.8387) time: 0.1514 data: 0.0710 max mem: 8255 +Train: [85] [2700/6250] eta: 0:09:30 lr: 0.000007 grad: 0.1397 (0.1499) loss: 0.8277 (0.8385) time: 0.1365 data: 0.0574 max mem: 8255 +Train: [85] [2800/6250] eta: 0:09:13 lr: 0.000007 grad: 0.1449 (0.1498) loss: 0.8334 (0.8383) time: 0.1601 data: 0.0866 max mem: 8255 +Train: [85] [2900/6250] eta: 0:08:56 lr: 0.000007 grad: 0.1317 (0.1495) loss: 0.8444 (0.8383) time: 0.1608 data: 0.0919 max mem: 8255 +Train: [85] [3000/6250] eta: 0:08:41 lr: 0.000007 grad: 0.1411 (0.1494) loss: 0.8385 (0.8382) time: 0.1892 data: 0.1073 max mem: 8255 +Train: [85] [3100/6250] eta: 0:08:26 lr: 0.000007 grad: 0.1400 (0.1493) loss: 0.8348 (0.8380) time: 0.1887 data: 0.1041 max mem: 8255 +Train: [85] [3200/6250] eta: 0:08:07 lr: 0.000007 grad: 0.1422 (0.1491) loss: 0.8345 (0.8380) time: 0.1510 data: 0.0791 max mem: 8255 +Train: [85] [3300/6250] eta: 0:07:51 lr: 0.000007 grad: 0.1471 (0.1490) loss: 0.8337 (0.8380) time: 0.1488 data: 0.0778 max mem: 8255 +Train: [85] [3400/6250] eta: 0:07:35 lr: 0.000007 grad: 0.1402 (0.1488) loss: 0.8385 (0.8379) time: 0.1575 data: 0.0838 max mem: 8255 +Train: [85] [3500/6250] eta: 0:07:20 lr: 0.000007 grad: 0.1335 (0.1486) loss: 0.8423 (0.8379) time: 0.2153 data: 0.1397 max mem: 8255 +Train: [85] [3600/6250] eta: 0:07:02 lr: 0.000007 grad: 0.1467 (0.1485) loss: 0.8413 (0.8379) time: 0.1471 data: 0.0770 max mem: 8255 +Train: [85] [3700/6250] eta: 0:06:45 lr: 0.000007 grad: 0.1316 (0.1483) loss: 0.8404 (0.8380) time: 0.1507 data: 0.0760 max mem: 8255 +Train: [85] [3800/6250] eta: 0:06:28 lr: 0.000007 grad: 0.1416 (0.1480) loss: 0.8456 (0.8380) time: 0.1134 data: 0.0286 max mem: 8255 +Train: [85] [3900/6250] eta: 0:06:11 lr: 0.000007 grad: 0.1400 (0.1479) loss: 0.8358 (0.8381) time: 0.1419 data: 0.0624 max mem: 8255 +Train: [85] [4000/6250] eta: 0:05:54 lr: 0.000007 grad: 0.1356 (0.1478) loss: 0.8389 (0.8381) time: 0.1389 data: 0.0657 max mem: 8255 +Train: [85] [4100/6250] eta: 0:05:38 lr: 0.000007 grad: 0.1353 (0.1477) loss: 0.8404 (0.8381) time: 0.2254 data: 0.1589 max mem: 8255 +Train: [85] [4200/6250] eta: 0:05:22 lr: 0.000007 grad: 0.1418 (0.1475) loss: 0.8368 (0.8382) time: 0.1336 data: 0.0483 max mem: 8255 +Train: [85] [4300/6250] eta: 0:05:07 lr: 0.000007 grad: 0.1355 (0.1473) loss: 0.8399 (0.8383) time: 0.1212 data: 0.0221 max mem: 8255 +Train: [85] [4400/6250] eta: 0:04:53 lr: 0.000007 grad: 0.1420 (0.1472) loss: 0.8352 (0.8383) time: 0.1652 data: 0.0740 max mem: 8255 +Train: [85] [4500/6250] eta: 0:04:40 lr: 0.000007 grad: 0.1438 (0.1472) loss: 0.8325 (0.8383) time: 0.1742 data: 0.0935 max mem: 8255 +Train: [85] [4600/6250] eta: 0:04:24 lr: 0.000007 grad: 0.1362 (0.1471) loss: 0.8431 (0.8383) time: 0.1408 data: 0.0488 max mem: 8255 +Train: [85] [4700/6250] eta: 0:04:09 lr: 0.000007 grad: 0.1490 (0.1471) loss: 0.8333 (0.8383) time: 0.2267 data: 0.1259 max mem: 8255 +Train: [85] [4800/6250] eta: 0:03:54 lr: 0.000007 grad: 0.1471 (0.1471) loss: 0.8402 (0.8382) time: 0.2428 data: 0.1349 max mem: 8255 +Train: [85] [4900/6250] eta: 0:03:38 lr: 0.000007 grad: 0.1426 (0.1471) loss: 0.8385 (0.8382) time: 0.1343 data: 0.0531 max mem: 8255 +Train: [85] [5000/6250] eta: 0:03:22 lr: 0.000007 grad: 0.1474 (0.1471) loss: 0.8342 (0.8381) time: 0.1620 data: 0.0793 max mem: 8255 +Train: [85] [5100/6250] eta: 0:03:06 lr: 0.000007 grad: 0.1429 (0.1472) loss: 0.8309 (0.8380) time: 0.1017 data: 0.0002 max mem: 8255 +Train: [85] [5200/6250] eta: 0:02:49 lr: 0.000007 grad: 0.1479 (0.1472) loss: 0.8320 (0.8379) time: 0.1489 data: 0.0707 max mem: 8255 +Train: [85] [5300/6250] eta: 0:02:33 lr: 0.000007 grad: 0.1384 (0.1471) loss: 0.8393 (0.8379) time: 0.1779 data: 0.1058 max mem: 8255 +Train: [85] [5400/6250] eta: 0:02:17 lr: 0.000007 grad: 0.1362 (0.1470) loss: 0.8350 (0.8379) time: 0.1701 data: 0.1015 max mem: 8255 +Train: [85] [5500/6250] eta: 0:02:01 lr: 0.000007 grad: 0.1342 (0.1469) loss: 0.8420 (0.8379) time: 0.1973 data: 0.1310 max mem: 8255 +Train: [85] [5600/6250] eta: 0:01:45 lr: 0.000007 grad: 0.1365 (0.1469) loss: 0.8365 (0.8380) time: 0.1867 data: 0.1084 max mem: 8255 +Train: [85] [5700/6250] eta: 0:01:28 lr: 0.000007 grad: 0.1377 (0.1468) loss: 0.8425 (0.8380) time: 0.1760 data: 0.1035 max mem: 8255 +Train: [85] [5800/6250] eta: 0:01:13 lr: 0.000007 grad: 0.1368 (0.1467) loss: 0.8421 (0.8380) time: 0.2898 data: 0.1699 max mem: 8255 +Train: [85] [5900/6250] eta: 0:00:56 lr: 0.000007 grad: 0.1410 (0.1468) loss: 0.8387 (0.8379) time: 0.1504 data: 0.0722 max mem: 8255 +Train: [85] [6000/6250] eta: 0:00:40 lr: 0.000007 grad: 0.1477 (0.1467) loss: 0.8330 (0.8379) time: 0.1405 data: 0.0344 max mem: 8255 +Train: [85] [6100/6250] eta: 0:00:24 lr: 0.000007 grad: 0.1355 (0.1466) loss: 0.8412 (0.8379) time: 0.1242 data: 0.0531 max mem: 8255 +Train: [85] [6200/6250] eta: 0:00:08 lr: 0.000007 grad: 0.1384 (0.1467) loss: 0.8333 (0.8379) time: 0.1293 data: 0.0565 max mem: 8255 +Train: [85] [6249/6250] eta: 0:00:00 lr: 0.000007 grad: 0.1456 (0.1467) loss: 0.8359 (0.8379) time: 0.1594 data: 0.0795 max mem: 8255 +Train: [85] Total time: 0:16:59 (0.1632 s / it) +Averaged stats: lr: 0.000007 grad: 0.1456 (0.1467) loss: 0.8359 (0.8379) +Eval (hcp-train-subset): [85] [ 0/62] eta: 0:05:54 loss: 0.8591 (0.8591) time: 5.7208 data: 5.6953 max mem: 8255 +Eval (hcp-train-subset): [85] [61/62] eta: 0:00:00 loss: 0.8484 (0.8511) time: 0.1486 data: 0.1279 max mem: 8255 +Eval (hcp-train-subset): [85] Total time: 0:00:14 (0.2281 s / it) +Averaged stats (hcp-train-subset): loss: 0.8484 (0.8511) +Eval (hcp-val): [85] [ 0/62] eta: 0:05:40 loss: 0.8704 (0.8704) time: 5.4842 data: 5.4534 max mem: 8255 +Eval (hcp-val): [85] [61/62] eta: 0:00:00 loss: 0.8709 (0.8725) time: 0.1433 data: 0.1212 max mem: 8255 +Eval (hcp-val): [85] Total time: 0:00:15 (0.2549 s / it) +Averaged stats (hcp-val): loss: 0.8709 (0.8725) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +Train: [86] [ 0/6250] eta: 9:17:29 lr: 0.000007 grad: 0.1017 (0.1017) loss: 0.8974 (0.8974) time: 5.3519 data: 5.1514 max mem: 8255 +Train: [86] [ 100/6250] eta: 0:20:34 lr: 0.000007 grad: 0.1547 (0.2037) loss: 0.8382 (0.8443) time: 0.1473 data: 0.0578 max mem: 8255 +Train: [86] [ 200/6250] eta: 0:17:56 lr: 0.000007 grad: 0.1322 (0.1794) loss: 0.8522 (0.8439) time: 0.1535 data: 0.0646 max mem: 8255 +Train: [86] [ 300/6250] eta: 0:17:07 lr: 0.000007 grad: 0.1589 (0.1709) loss: 0.8390 (0.8438) time: 0.1672 data: 0.0792 max mem: 8255 +Train: [86] [ 400/6250] eta: 0:16:16 lr: 0.000007 grad: 0.1547 (0.1679) loss: 0.8439 (0.8421) time: 0.1482 data: 0.0651 max mem: 8255 +Train: [86] [ 500/6250] eta: 0:15:28 lr: 0.000007 grad: 0.1451 (0.1649) loss: 0.8453 (0.8411) time: 0.1079 data: 0.0267 max mem: 8255 +Train: [86] [ 600/6250] eta: 0:15:01 lr: 0.000006 grad: 0.1445 (0.1626) loss: 0.8479 (0.8410) time: 0.1459 data: 0.0634 max mem: 8255 +Train: [86] [ 700/6250] eta: 0:14:47 lr: 0.000006 grad: 0.1461 (0.1603) loss: 0.8413 (0.8411) time: 0.1670 data: 0.0958 max mem: 8255 +Train: [86] [ 800/6250] eta: 0:14:27 lr: 0.000006 grad: 0.1374 (0.1584) loss: 0.8474 (0.8416) time: 0.1054 data: 0.0199 max mem: 8255 +Train: [86] [ 900/6250] eta: 0:14:20 lr: 0.000006 grad: 0.1405 (0.1567) loss: 0.8439 (0.8422) time: 0.1818 data: 0.0904 max mem: 8255 +Train: [86] [1000/6250] eta: 0:13:56 lr: 0.000006 grad: 0.1447 (0.1555) loss: 0.8385 (0.8421) time: 0.1637 data: 0.0811 max mem: 8255 +Train: [86] [1100/6250] eta: 0:13:36 lr: 0.000006 grad: 0.1391 (0.1544) loss: 0.8493 (0.8422) time: 0.1234 data: 0.0327 max mem: 8255 +Train: [86] [1200/6250] eta: 0:13:18 lr: 0.000006 grad: 0.1391 (0.1532) loss: 0.8378 (0.8424) time: 0.1819 data: 0.1020 max mem: 8255 +Train: [86] [1300/6250] eta: 0:13:12 lr: 0.000006 grad: 0.1338 (0.1524) loss: 0.8405 (0.8421) time: 0.2196 data: 0.1330 max mem: 8255 +Train: [86] [1400/6250] eta: 0:12:55 lr: 0.000006 grad: 0.1382 (0.1517) loss: 0.8383 (0.8419) time: 0.2183 data: 0.1151 max mem: 8255 +Train: [86] [1500/6250] eta: 0:12:35 lr: 0.000006 grad: 0.1305 (0.1510) loss: 0.8419 (0.8416) time: 0.1579 data: 0.0836 max mem: 8255 +Train: [86] [1600/6250] eta: 0:12:19 lr: 0.000006 grad: 0.1305 (0.1504) loss: 0.8449 (0.8415) time: 0.1601 data: 0.0878 max mem: 8255 +Train: [86] [1700/6250] eta: 0:12:04 lr: 0.000006 grad: 0.1392 (0.1501) loss: 0.8363 (0.8412) time: 0.1933 data: 0.1075 max mem: 8255 +Train: [86] [1800/6250] eta: 0:11:47 lr: 0.000006 grad: 0.1494 (0.1498) loss: 0.8342 (0.8409) time: 0.1194 data: 0.0489 max mem: 8255 +Train: [86] [1900/6250] eta: 0:11:34 lr: 0.000006 grad: 0.1311 (0.1494) loss: 0.8395 (0.8408) time: 0.1453 data: 0.0244 max mem: 8255 +Train: [86] [2000/6250] eta: 0:11:25 lr: 0.000006 grad: 0.1388 (0.1492) loss: 0.8398 (0.8406) time: 0.1388 data: 0.0548 max mem: 8255 +Train: [86] [2100/6250] eta: 0:11:21 lr: 0.000006 grad: 0.1390 (0.1487) loss: 0.8389 (0.8404) time: 0.1251 data: 0.0347 max mem: 8255 +Train: [86] [2200/6250] eta: 0:11:19 lr: 0.000006 grad: 0.1496 (0.1484) loss: 0.8460 (0.8405) time: 0.1770 data: 0.0996 max mem: 8255 +Train: [86] [2300/6250] eta: 0:10:57 lr: 0.000006 grad: 0.1382 (0.1482) loss: 0.8359 (0.8404) time: 0.1711 data: 0.1072 max mem: 8255 +Train: [86] [2400/6250] eta: 0:10:40 lr: 0.000006 grad: 0.1416 (0.1478) loss: 0.8387 (0.8404) time: 0.1564 data: 0.0906 max mem: 8255 +Train: [86] [2500/6250] eta: 0:10:22 lr: 0.000006 grad: 0.1382 (0.1475) loss: 0.8480 (0.8405) time: 0.1517 data: 0.0761 max mem: 8255 +Train: [86] [2600/6250] eta: 0:10:06 lr: 0.000006 grad: 0.1439 (0.1472) loss: 0.8455 (0.8406) time: 0.1250 data: 0.0555 max mem: 8255 +Train: [86] [2700/6250] eta: 0:09:47 lr: 0.000006 grad: 0.1368 (0.1470) loss: 0.8365 (0.8407) time: 0.1479 data: 0.0700 max mem: 8255 +Train: [86] [2800/6250] eta: 0:09:29 lr: 0.000006 grad: 0.1441 (0.1469) loss: 0.8390 (0.8408) time: 0.1685 data: 0.0898 max mem: 8255 +Train: [86] [2900/6250] eta: 0:09:12 lr: 0.000006 grad: 0.1437 (0.1469) loss: 0.8350 (0.8407) time: 0.1472 data: 0.0739 max mem: 8255 +Train: [86] [3000/6250] eta: 0:08:53 lr: 0.000006 grad: 0.1435 (0.1467) loss: 0.8391 (0.8408) time: 0.1413 data: 0.0661 max mem: 8255 +Train: [86] [3100/6250] eta: 0:08:35 lr: 0.000006 grad: 0.1375 (0.1465) loss: 0.8397 (0.8408) time: 0.1217 data: 0.0450 max mem: 8255 +Train: [86] [3200/6250] eta: 0:08:18 lr: 0.000006 grad: 0.1312 (0.1464) loss: 0.8468 (0.8407) time: 0.1776 data: 0.0993 max mem: 8255 +Train: [86] [3300/6250] eta: 0:08:01 lr: 0.000006 grad: 0.1407 (0.1463) loss: 0.8410 (0.8407) time: 0.1473 data: 0.0685 max mem: 8255 +Train: [86] [3400/6250] eta: 0:07:45 lr: 0.000006 grad: 0.1366 (0.1463) loss: 0.8379 (0.8406) time: 0.1581 data: 0.0773 max mem: 8255 +Train: [86] [3500/6250] eta: 0:07:29 lr: 0.000006 grad: 0.1433 (0.1462) loss: 0.8344 (0.8405) time: 0.1449 data: 0.0714 max mem: 8255 +Train: [86] [3600/6250] eta: 0:07:13 lr: 0.000006 grad: 0.1372 (0.1461) loss: 0.8391 (0.8404) time: 0.2368 data: 0.0940 max mem: 8255 +Train: [86] [3700/6250] eta: 0:06:56 lr: 0.000006 grad: 0.1351 (0.1461) loss: 0.8386 (0.8403) time: 0.1389 data: 0.0634 max mem: 8255 +Train: [86] [3800/6250] eta: 0:06:38 lr: 0.000006 grad: 0.1519 (0.1463) loss: 0.8354 (0.8402) time: 0.1374 data: 0.0461 max mem: 8255 +Train: [86] [3900/6250] eta: 0:06:21 lr: 0.000006 grad: 0.1377 (0.1462) loss: 0.8355 (0.8400) time: 0.1603 data: 0.0904 max mem: 8255 +Train: [86] [4000/6250] eta: 0:06:04 lr: 0.000006 grad: 0.1403 (0.1462) loss: 0.8407 (0.8399) time: 0.1464 data: 0.0816 max mem: 8255 +Train: [86] [4100/6250] eta: 0:05:47 lr: 0.000006 grad: 0.1399 (0.1461) loss: 0.8280 (0.8398) time: 0.1404 data: 0.0646 max mem: 8255 +Train: [86] [4200/6250] eta: 0:05:31 lr: 0.000006 grad: 0.1516 (0.1462) loss: 0.8322 (0.8397) time: 0.1705 data: 0.0973 max mem: 8255 +Train: [86] [4300/6250] eta: 0:05:14 lr: 0.000006 grad: 0.1421 (0.1463) loss: 0.8340 (0.8396) time: 0.1430 data: 0.0755 max mem: 8255 +Train: [86] [4400/6250] eta: 0:04:57 lr: 0.000006 grad: 0.1377 (0.1463) loss: 0.8329 (0.8395) time: 0.1008 data: 0.0159 max mem: 8255 +Train: [86] [4500/6250] eta: 0:04:40 lr: 0.000006 grad: 0.1365 (0.1462) loss: 0.8360 (0.8394) time: 0.1171 data: 0.0357 max mem: 8255 +Train: [86] [4600/6250] eta: 0:04:23 lr: 0.000006 grad: 0.1396 (0.1462) loss: 0.8399 (0.8394) time: 0.1289 data: 0.0618 max mem: 8255 +Train: [86] [4700/6250] eta: 0:04:07 lr: 0.000006 grad: 0.1432 (0.1462) loss: 0.8374 (0.8394) time: 0.1290 data: 0.0322 max mem: 8255 +Train: [86] [4800/6250] eta: 0:03:51 lr: 0.000006 grad: 0.1438 (0.1462) loss: 0.8363 (0.8393) time: 0.1876 data: 0.1240 max mem: 8255 +Train: [86] [4900/6250] eta: 0:03:35 lr: 0.000006 grad: 0.1433 (0.1462) loss: 0.8307 (0.8392) time: 0.2687 data: 0.1657 max mem: 8255 +Train: [86] [5000/6250] eta: 0:03:20 lr: 0.000006 grad: 0.1454 (0.1462) loss: 0.8350 (0.8392) time: 0.1315 data: 0.0543 max mem: 8255 +Train: [86] [5100/6250] eta: 0:03:04 lr: 0.000006 grad: 0.1377 (0.1462) loss: 0.8362 (0.8392) time: 0.1834 data: 0.0903 max mem: 8255 +Train: [86] [5200/6250] eta: 0:02:49 lr: 0.000006 grad: 0.1461 (0.1462) loss: 0.8288 (0.8392) time: 0.1370 data: 0.0141 max mem: 8255 +Train: [86] [5300/6250] eta: 0:02:32 lr: 0.000006 grad: 0.1402 (0.1462) loss: 0.8315 (0.8391) time: 0.1380 data: 0.0703 max mem: 8255 +Train: [86] [5400/6250] eta: 0:02:16 lr: 0.000006 grad: 0.1482 (0.1462) loss: 0.8330 (0.8391) time: 0.2379 data: 0.1504 max mem: 8255 +Train: [86] [5500/6250] eta: 0:02:00 lr: 0.000006 grad: 0.1355 (0.1461) loss: 0.8358 (0.8391) time: 0.1458 data: 0.0502 max mem: 8255 +Train: [86] [5600/6250] eta: 0:01:45 lr: 0.000006 grad: 0.1429 (0.1461) loss: 0.8287 (0.8390) time: 0.1343 data: 0.0646 max mem: 8255 +Train: [86] [5700/6250] eta: 0:01:29 lr: 0.000006 grad: 0.1472 (0.1462) loss: 0.8344 (0.8389) time: 0.3060 data: 0.1526 max mem: 8255 +Train: [86] [5800/6250] eta: 0:01:13 lr: 0.000006 grad: 0.1403 (0.1462) loss: 0.8374 (0.8388) time: 0.1069 data: 0.0228 max mem: 8255 +Train: [86] [5900/6250] eta: 0:00:56 lr: 0.000006 grad: 0.1427 (0.1462) loss: 0.8378 (0.8388) time: 0.1399 data: 0.0596 max mem: 8255 +Train: [86] [6000/6250] eta: 0:00:40 lr: 0.000006 grad: 0.1413 (0.1462) loss: 0.8416 (0.8387) time: 0.1413 data: 0.0722 max mem: 8255 +Train: [86] [6100/6250] eta: 0:00:24 lr: 0.000006 grad: 0.1433 (0.1462) loss: 0.8312 (0.8387) time: 0.1514 data: 0.0786 max mem: 8255 +Train: [86] [6200/6250] eta: 0:00:08 lr: 0.000006 grad: 0.1305 (0.1462) loss: 0.8369 (0.8386) time: 0.1552 data: 0.0885 max mem: 8255 +Train: [86] [6249/6250] eta: 0:00:00 lr: 0.000006 grad: 0.1393 (0.1462) loss: 0.8358 (0.8387) time: 0.2976 data: 0.1706 max mem: 8255 +Train: [86] Total time: 0:17:00 (0.1632 s / it) +Averaged stats: lr: 0.000006 grad: 0.1393 (0.1462) loss: 0.8358 (0.8387) +Eval (hcp-train-subset): [86] [ 0/62] eta: 0:04:22 loss: 0.8561 (0.8561) time: 4.2335 data: 4.1639 max mem: 8255 +Eval (hcp-train-subset): [86] [61/62] eta: 0:00:00 loss: 0.8480 (0.8497) time: 0.1269 data: 0.1043 max mem: 8255 +Eval (hcp-train-subset): [86] Total time: 0:00:14 (0.2335 s / it) +Averaged stats (hcp-train-subset): loss: 0.8480 (0.8497) +Eval (hcp-val): [86] [ 0/62] eta: 0:05:46 loss: 0.8714 (0.8714) time: 5.5888 data: 5.5590 max mem: 8255 +Eval (hcp-val): [86] [61/62] eta: 0:00:00 loss: 0.8709 (0.8718) time: 0.1201 data: 0.0995 max mem: 8255 +Eval (hcp-val): [86] Total time: 0:00:14 (0.2299 s / it) +Averaged stats (hcp-val): loss: 0.8709 (0.8718) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +Train: [87] [ 0/6250] eta: 11:13:08 lr: 0.000006 grad: 0.0957 (0.0957) loss: 0.8998 (0.8998) time: 6.4622 data: 6.3242 max mem: 8255 +Train: [87] [ 100/6250] eta: 0:21:36 lr: 0.000006 grad: 0.1279 (0.1594) loss: 0.8568 (0.8571) time: 0.1574 data: 0.0633 max mem: 8255 +Train: [87] [ 200/6250] eta: 0:18:51 lr: 0.000006 grad: 0.1385 (0.1611) loss: 0.8500 (0.8501) time: 0.1840 data: 0.0970 max mem: 8255 +Train: [87] [ 300/6250] eta: 0:17:22 lr: 0.000006 grad: 0.1465 (0.1569) loss: 0.8484 (0.8477) time: 0.1553 data: 0.0735 max mem: 8255 +Train: [87] [ 400/6250] eta: 0:16:37 lr: 0.000006 grad: 0.1367 (0.1534) loss: 0.8407 (0.8473) time: 0.1529 data: 0.0570 max mem: 8255 +Train: [87] [ 500/6250] eta: 0:15:58 lr: 0.000006 grad: 0.1425 (0.1520) loss: 0.8395 (0.8475) time: 0.1433 data: 0.0507 max mem: 8255 +Train: [87] [ 600/6250] eta: 0:15:24 lr: 0.000006 grad: 0.1415 (0.1504) loss: 0.8478 (0.8482) time: 0.1652 data: 0.0782 max mem: 8255 +Train: [87] [ 700/6250] eta: 0:15:02 lr: 0.000006 grad: 0.1326 (0.1494) loss: 0.8541 (0.8482) time: 0.1671 data: 0.0845 max mem: 8255 +Train: [87] [ 800/6250] eta: 0:14:29 lr: 0.000006 grad: 0.1415 (0.1487) loss: 0.8453 (0.8481) time: 0.1403 data: 0.0387 max mem: 8255 +Train: [87] [ 900/6250] eta: 0:14:17 lr: 0.000006 grad: 0.1442 (0.1485) loss: 0.8427 (0.8476) time: 0.1300 data: 0.0106 max mem: 8255 +Train: [87] [1000/6250] eta: 0:13:55 lr: 0.000006 grad: 0.1410 (0.1488) loss: 0.8418 (0.8467) time: 0.1548 data: 0.0782 max mem: 8255 +Train: [87] [1100/6250] eta: 0:13:32 lr: 0.000006 grad: 0.1406 (0.1488) loss: 0.8375 (0.8461) time: 0.1422 data: 0.0618 max mem: 8255 +Train: [87] [1200/6250] eta: 0:13:13 lr: 0.000006 grad: 0.1435 (0.1486) loss: 0.8362 (0.8454) time: 0.1645 data: 0.0911 max mem: 8255 +Train: [87] [1300/6250] eta: 0:12:57 lr: 0.000006 grad: 0.1465 (0.1486) loss: 0.8318 (0.8446) time: 0.2038 data: 0.1343 max mem: 8255 +Train: [87] [1400/6250] eta: 0:12:42 lr: 0.000005 grad: 0.1432 (0.1484) loss: 0.8415 (0.8441) time: 0.1964 data: 0.1134 max mem: 8255 +Train: [87] [1500/6250] eta: 0:12:20 lr: 0.000005 grad: 0.1362 (0.1480) loss: 0.8410 (0.8438) time: 0.1438 data: 0.0639 max mem: 8255 +Train: [87] [1600/6250] eta: 0:12:00 lr: 0.000005 grad: 0.1425 (0.1478) loss: 0.8348 (0.8434) time: 0.1282 data: 0.0492 max mem: 8255 +Train: [87] [1700/6250] eta: 0:11:42 lr: 0.000005 grad: 0.1403 (0.1478) loss: 0.8330 (0.8431) time: 0.1071 data: 0.0272 max mem: 8255 +Train: [87] [1800/6250] eta: 0:11:24 lr: 0.000005 grad: 0.1302 (0.1478) loss: 0.8417 (0.8429) time: 0.1265 data: 0.0444 max mem: 8255 +Train: [87] [1900/6250] eta: 0:11:12 lr: 0.000005 grad: 0.1477 (0.1476) loss: 0.8357 (0.8426) time: 0.2320 data: 0.1482 max mem: 8255 +Train: [87] [2000/6250] eta: 0:10:52 lr: 0.000005 grad: 0.1472 (0.1476) loss: 0.8309 (0.8423) time: 0.1402 data: 0.0670 max mem: 8255 +Train: [87] [2100/6250] eta: 0:10:35 lr: 0.000005 grad: 0.1562 (0.1477) loss: 0.8309 (0.8420) time: 0.1350 data: 0.0463 max mem: 8255 +Train: [87] [2200/6250] eta: 0:10:34 lr: 0.000005 grad: 0.1436 (0.1477) loss: 0.8354 (0.8417) time: 0.3686 data: 0.2926 max mem: 8255 +Train: [87] [2300/6250] eta: 0:10:19 lr: 0.000005 grad: 0.1444 (0.1477) loss: 0.8268 (0.8414) time: 0.1922 data: 0.1112 max mem: 8255 +Train: [87] [2400/6250] eta: 0:10:09 lr: 0.000005 grad: 0.1500 (0.1477) loss: 0.8282 (0.8410) time: 0.2202 data: 0.1012 max mem: 8255 +Train: [87] [2500/6250] eta: 0:09:58 lr: 0.000005 grad: 0.1427 (0.1475) loss: 0.8285 (0.8408) time: 0.1555 data: 0.0550 max mem: 8255 +Train: [87] [2600/6250] eta: 0:09:44 lr: 0.000005 grad: 0.1430 (0.1474) loss: 0.8383 (0.8406) time: 0.2154 data: 0.0982 max mem: 8255 +Train: [87] [2700/6250] eta: 0:09:29 lr: 0.000005 grad: 0.1358 (0.1473) loss: 0.8348 (0.8404) time: 0.1391 data: 0.0483 max mem: 8255 +Train: [87] [2800/6250] eta: 0:09:14 lr: 0.000005 grad: 0.1405 (0.1471) loss: 0.8342 (0.8402) time: 0.1293 data: 0.0464 max mem: 8255 +Train: [87] [2900/6250] eta: 0:09:00 lr: 0.000005 grad: 0.1451 (0.1472) loss: 0.8309 (0.8399) time: 0.1363 data: 0.0476 max mem: 8255 +Train: [87] [3000/6250] eta: 0:08:43 lr: 0.000005 grad: 0.1417 (0.1472) loss: 0.8321 (0.8396) time: 0.1531 data: 0.0654 max mem: 8255 +Train: [87] [3100/6250] eta: 0:08:27 lr: 0.000005 grad: 0.1436 (0.1472) loss: 0.8302 (0.8394) time: 0.1713 data: 0.1031 max mem: 8255 +Train: [87] [3200/6250] eta: 0:08:11 lr: 0.000005 grad: 0.1542 (0.1473) loss: 0.8322 (0.8391) time: 0.1528 data: 0.0808 max mem: 8255 +Train: [87] [3300/6250] eta: 0:07:55 lr: 0.000005 grad: 0.1471 (0.1474) loss: 0.8305 (0.8390) time: 0.1327 data: 0.0518 max mem: 8255 +Train: [87] [3400/6250] eta: 0:07:38 lr: 0.000005 grad: 0.1464 (0.1476) loss: 0.8289 (0.8388) time: 0.1291 data: 0.0530 max mem: 8255 +Train: [87] [3500/6250] eta: 0:07:22 lr: 0.000005 grad: 0.1444 (0.1477) loss: 0.8325 (0.8386) time: 0.1657 data: 0.0806 max mem: 8255 +Train: [87] [3600/6250] eta: 0:07:05 lr: 0.000005 grad: 0.1593 (0.1480) loss: 0.8284 (0.8383) time: 0.1777 data: 0.1012 max mem: 8255 +Train: [87] [3700/6250] eta: 0:06:47 lr: 0.000005 grad: 0.1570 (0.1481) loss: 0.8286 (0.8381) time: 0.1405 data: 0.0685 max mem: 8255 +Train: [87] [3800/6250] eta: 0:06:30 lr: 0.000005 grad: 0.1549 (0.1482) loss: 0.8243 (0.8380) time: 0.1117 data: 0.0342 max mem: 8255 +Train: [87] [3900/6250] eta: 0:06:14 lr: 0.000005 grad: 0.1524 (0.1484) loss: 0.8304 (0.8378) time: 0.1593 data: 0.0674 max mem: 8255 +Train: [87] [4000/6250] eta: 0:05:58 lr: 0.000005 grad: 0.1562 (0.1486) loss: 0.8295 (0.8376) time: 0.1251 data: 0.0490 max mem: 8255 +Train: [87] [4100/6250] eta: 0:05:42 lr: 0.000005 grad: 0.1496 (0.1488) loss: 0.8227 (0.8374) time: 0.0891 data: 0.0073 max mem: 8255 +Train: [87] [4200/6250] eta: 0:05:27 lr: 0.000005 grad: 0.1438 (0.1488) loss: 0.8405 (0.8374) time: 0.1614 data: 0.0714 max mem: 8255 +Train: [87] [4300/6250] eta: 0:05:10 lr: 0.000005 grad: 0.1372 (0.1489) loss: 0.8413 (0.8373) time: 0.1405 data: 0.0642 max mem: 8255 +Train: [87] [4400/6250] eta: 0:04:55 lr: 0.000005 grad: 0.1435 (0.1489) loss: 0.8303 (0.8373) time: 0.3175 data: 0.2443 max mem: 8255 +Train: [87] [4500/6250] eta: 0:04:37 lr: 0.000005 grad: 0.1509 (0.1490) loss: 0.8301 (0.8372) time: 0.1387 data: 0.0433 max mem: 8255 +Train: [87] [4600/6250] eta: 0:04:21 lr: 0.000005 grad: 0.1409 (0.1490) loss: 0.8373 (0.8372) time: 0.1058 data: 0.0197 max mem: 8255 +Train: [87] [4700/6250] eta: 0:04:05 lr: 0.000005 grad: 0.1457 (0.1491) loss: 0.8370 (0.8371) time: 0.1446 data: 0.0667 max mem: 8255 +Train: [87] [4800/6250] eta: 0:03:48 lr: 0.000005 grad: 0.1515 (0.1491) loss: 0.8290 (0.8371) time: 0.0930 data: 0.0226 max mem: 8255 +Train: [87] [4900/6250] eta: 0:03:32 lr: 0.000005 grad: 0.1527 (0.1492) loss: 0.8348 (0.8370) time: 0.0915 data: 0.0133 max mem: 8255 +Train: [87] [5000/6250] eta: 0:03:16 lr: 0.000005 grad: 0.1432 (0.1494) loss: 0.8409 (0.8369) time: 0.1252 data: 0.0538 max mem: 8255 +Train: [87] [5100/6250] eta: 0:03:00 lr: 0.000005 grad: 0.1523 (0.1494) loss: 0.8360 (0.8368) time: 0.1576 data: 0.0757 max mem: 8255 +Train: [87] [5200/6250] eta: 0:02:44 lr: 0.000005 grad: 0.1439 (0.1495) loss: 0.8345 (0.8368) time: 0.1725 data: 0.1067 max mem: 8255 +Train: [87] [5300/6250] eta: 0:02:28 lr: 0.000005 grad: 0.1429 (0.1494) loss: 0.8389 (0.8368) time: 0.0998 data: 0.0225 max mem: 8255 +Train: [87] [5400/6250] eta: 0:02:12 lr: 0.000005 grad: 0.1392 (0.1494) loss: 0.8384 (0.8368) time: 0.1242 data: 0.0528 max mem: 8255 +Train: [87] [5500/6250] eta: 0:01:56 lr: 0.000005 grad: 0.1440 (0.1494) loss: 0.8404 (0.8368) time: 0.1472 data: 0.0669 max mem: 8255 +Train: [87] [5600/6250] eta: 0:01:40 lr: 0.000005 grad: 0.1429 (0.1494) loss: 0.8344 (0.8368) time: 0.1384 data: 0.0732 max mem: 8255 +Train: [87] [5700/6250] eta: 0:01:24 lr: 0.000005 grad: 0.1445 (0.1494) loss: 0.8391 (0.8368) time: 0.1296 data: 0.0602 max mem: 8255 +Train: [87] [5800/6250] eta: 0:01:09 lr: 0.000005 grad: 0.1402 (0.1493) loss: 0.8404 (0.8368) time: 0.1384 data: 0.0736 max mem: 8255 +Train: [87] [5900/6250] eta: 0:00:53 lr: 0.000005 grad: 0.1454 (0.1493) loss: 0.8416 (0.8368) time: 0.2559 data: 0.1742 max mem: 8255 +Train: [87] [6000/6250] eta: 0:00:38 lr: 0.000005 grad: 0.1377 (0.1492) loss: 0.8359 (0.8368) time: 0.0936 data: 0.0002 max mem: 8255 +Train: [87] [6100/6250] eta: 0:00:23 lr: 0.000005 grad: 0.1429 (0.1492) loss: 0.8340 (0.8368) time: 0.1212 data: 0.0475 max mem: 8255 +Train: [87] [6200/6250] eta: 0:00:07 lr: 0.000005 grad: 0.1456 (0.1492) loss: 0.8374 (0.8368) time: 0.1340 data: 0.0619 max mem: 8255 +Train: [87] [6249/6250] eta: 0:00:00 lr: 0.000005 grad: 0.1412 (0.1491) loss: 0.8390 (0.8367) time: 0.1547 data: 0.0764 max mem: 8255 +Train: [87] Total time: 0:16:05 (0.1545 s / it) +Averaged stats: lr: 0.000005 grad: 0.1412 (0.1491) loss: 0.8390 (0.8367) +Eval (hcp-train-subset): [87] [ 0/62] eta: 0:03:54 loss: 0.8547 (0.8547) time: 3.7763 data: 3.7106 max mem: 8255 +Eval (hcp-train-subset): [87] [61/62] eta: 0:00:00 loss: 0.8467 (0.8486) time: 0.1108 data: 0.0905 max mem: 8255 +Eval (hcp-train-subset): [87] Total time: 0:00:12 (0.2040 s / it) +Averaged stats (hcp-train-subset): loss: 0.8467 (0.8486) +Eval (hcp-val): [87] [ 0/62] eta: 0:04:36 loss: 0.8664 (0.8664) time: 4.4664 data: 4.3928 max mem: 8255 +Eval (hcp-val): [87] [61/62] eta: 0:00:00 loss: 0.8701 (0.8722) time: 0.1227 data: 0.1019 max mem: 8255 +Eval (hcp-val): [87] Total time: 0:00:14 (0.2267 s / it) +Averaged stats (hcp-val): loss: 0.8701 (0.8722) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +Train: [88] [ 0/6250] eta: 11:12:55 lr: 0.000005 grad: 0.3411 (0.3411) loss: 0.8483 (0.8483) time: 6.4600 data: 6.3504 max mem: 8255 +Train: [88] [ 100/6250] eta: 0:21:02 lr: 0.000005 grad: 0.1346 (0.1703) loss: 0.8787 (0.8750) time: 0.1619 data: 0.0718 max mem: 8255 +Train: [88] [ 200/6250] eta: 0:17:23 lr: 0.000005 grad: 0.1589 (0.1638) loss: 0.8575 (0.8669) time: 0.1336 data: 0.0383 max mem: 8255 +Train: [88] [ 300/6250] eta: 0:16:26 lr: 0.000005 grad: 0.1558 (0.1606) loss: 0.8531 (0.8600) time: 0.1553 data: 0.0556 max mem: 8255 +Train: [88] [ 400/6250] eta: 0:15:41 lr: 0.000005 grad: 0.1599 (0.1584) loss: 0.8457 (0.8573) time: 0.1423 data: 0.0545 max mem: 8255 +Train: [88] [ 500/6250] eta: 0:14:52 lr: 0.000005 grad: 0.1555 (0.1580) loss: 0.8494 (0.8548) time: 0.1399 data: 0.0611 max mem: 8255 +Train: [88] [ 600/6250] eta: 0:14:14 lr: 0.000005 grad: 0.1470 (0.1570) loss: 0.8479 (0.8534) time: 0.1598 data: 0.0895 max mem: 8255 +Train: [88] [ 700/6250] eta: 0:14:14 lr: 0.000005 grad: 0.1409 (0.1558) loss: 0.8449 (0.8525) time: 0.1137 data: 0.0002 max mem: 8255 +Train: [88] [ 800/6250] eta: 0:13:46 lr: 0.000005 grad: 0.1385 (0.1547) loss: 0.8473 (0.8517) time: 0.1244 data: 0.0376 max mem: 8255 +Train: [88] [ 900/6250] eta: 0:13:32 lr: 0.000005 grad: 0.1460 (0.1540) loss: 0.8501 (0.8511) time: 0.1350 data: 0.0403 max mem: 8255 +Train: [88] [1000/6250] eta: 0:13:18 lr: 0.000005 grad: 0.1407 (0.1535) loss: 0.8394 (0.8504) time: 0.1821 data: 0.1189 max mem: 8255 +Train: [88] [1100/6250] eta: 0:12:54 lr: 0.000005 grad: 0.1463 (0.1528) loss: 0.8499 (0.8498) time: 0.1257 data: 0.0570 max mem: 8255 +Train: [88] [1200/6250] eta: 0:12:32 lr: 0.000005 grad: 0.1492 (0.1526) loss: 0.8424 (0.8494) time: 0.1374 data: 0.0678 max mem: 8255 +Train: [88] [1300/6250] eta: 0:12:19 lr: 0.000005 grad: 0.1390 (0.1522) loss: 0.8418 (0.8488) time: 0.1439 data: 0.0537 max mem: 8255 +Train: [88] [1400/6250] eta: 0:11:56 lr: 0.000005 grad: 0.1408 (0.1518) loss: 0.8432 (0.8484) time: 0.1122 data: 0.0440 max mem: 8255 +Train: [88] [1500/6250] eta: 0:11:39 lr: 0.000005 grad: 0.1428 (0.1515) loss: 0.8459 (0.8480) time: 0.1523 data: 0.0864 max mem: 8255 +Train: [88] [1600/6250] eta: 0:11:22 lr: 0.000005 grad: 0.1392 (0.1510) loss: 0.8438 (0.8476) time: 0.1421 data: 0.0736 max mem: 8255 +Train: [88] [1700/6250] eta: 0:11:06 lr: 0.000005 grad: 0.1369 (0.1505) loss: 0.8475 (0.8474) time: 0.1520 data: 0.0781 max mem: 8255 +Train: [88] [1800/6250] eta: 0:10:51 lr: 0.000005 grad: 0.1406 (0.1501) loss: 0.8409 (0.8471) time: 0.1207 data: 0.0507 max mem: 8255 +Train: [88] [1900/6250] eta: 0:10:38 lr: 0.000005 grad: 0.1469 (0.1499) loss: 0.8388 (0.8469) time: 0.2073 data: 0.1418 max mem: 8255 +Train: [88] [2000/6250] eta: 0:10:21 lr: 0.000005 grad: 0.1380 (0.1495) loss: 0.8384 (0.8466) time: 0.1479 data: 0.0682 max mem: 8255 +Train: [88] [2100/6250] eta: 0:10:06 lr: 0.000005 grad: 0.1420 (0.1493) loss: 0.8388 (0.8464) time: 0.1403 data: 0.0590 max mem: 8255 +Train: [88] [2200/6250] eta: 0:09:49 lr: 0.000005 grad: 0.1393 (0.1490) loss: 0.8423 (0.8462) time: 0.1324 data: 0.0598 max mem: 8255 +Train: [88] [2300/6250] eta: 0:09:32 lr: 0.000005 grad: 0.1500 (0.1490) loss: 0.8358 (0.8458) time: 0.1421 data: 0.0662 max mem: 8255 +Train: [88] [2400/6250] eta: 0:09:16 lr: 0.000005 grad: 0.1422 (0.1489) loss: 0.8307 (0.8456) time: 0.1260 data: 0.0596 max mem: 8255 +Train: [88] [2500/6250] eta: 0:09:02 lr: 0.000005 grad: 0.1395 (0.1488) loss: 0.8376 (0.8453) time: 0.1435 data: 0.0751 max mem: 8255 +Train: [88] [2600/6250] eta: 0:08:49 lr: 0.000005 grad: 0.1442 (0.1486) loss: 0.8377 (0.8450) time: 0.1150 data: 0.0297 max mem: 8255 +Train: [88] [2700/6250] eta: 0:08:35 lr: 0.000005 grad: 0.1481 (0.1487) loss: 0.8347 (0.8447) time: 0.1709 data: 0.0955 max mem: 8255 +Train: [88] [2800/6250] eta: 0:08:18 lr: 0.000005 grad: 0.1338 (0.1485) loss: 0.8460 (0.8444) time: 0.1351 data: 0.0628 max mem: 8255 +Train: [88] [2900/6250] eta: 0:08:02 lr: 0.000004 grad: 0.1347 (0.1483) loss: 0.8436 (0.8443) time: 0.1344 data: 0.0600 max mem: 8255 +Train: [88] [3000/6250] eta: 0:07:46 lr: 0.000004 grad: 0.1433 (0.1484) loss: 0.8414 (0.8441) time: 0.1173 data: 0.0284 max mem: 8255 +Train: [88] [3100/6250] eta: 0:07:34 lr: 0.000004 grad: 0.1366 (0.1482) loss: 0.8362 (0.8439) time: 0.1339 data: 0.0611 max mem: 8255 +Train: [88] [3200/6250] eta: 0:07:21 lr: 0.000004 grad: 0.1431 (0.1482) loss: 0.8362 (0.8437) time: 0.1434 data: 0.0687 max mem: 8255 +Train: [88] [3300/6250] eta: 0:07:08 lr: 0.000004 grad: 0.1468 (0.1482) loss: 0.8333 (0.8435) time: 0.1830 data: 0.1077 max mem: 8255 +Train: [88] [3400/6250] eta: 0:06:55 lr: 0.000004 grad: 0.1400 (0.1481) loss: 0.8393 (0.8434) time: 0.1634 data: 0.0877 max mem: 8255 +Train: [88] [3500/6250] eta: 0:06:41 lr: 0.000004 grad: 0.1423 (0.1481) loss: 0.8411 (0.8433) time: 0.1682 data: 0.0983 max mem: 8255 +Train: [88] [3600/6250] eta: 0:06:25 lr: 0.000004 grad: 0.1440 (0.1480) loss: 0.8355 (0.8432) time: 0.1394 data: 0.0749 max mem: 8255 +Train: [88] [3700/6250] eta: 0:06:10 lr: 0.000004 grad: 0.1424 (0.1479) loss: 0.8430 (0.8431) time: 0.1008 data: 0.0285 max mem: 8255 +Train: [88] [3800/6250] eta: 0:05:55 lr: 0.000004 grad: 0.1443 (0.1478) loss: 0.8410 (0.8431) time: 0.1221 data: 0.0346 max mem: 8255 +Train: [88] [3900/6250] eta: 0:05:42 lr: 0.000004 grad: 0.1529 (0.1478) loss: 0.8425 (0.8431) time: 0.0976 data: 0.0002 max mem: 8255 +Train: [88] [4000/6250] eta: 0:05:27 lr: 0.000004 grad: 0.1536 (0.1478) loss: 0.8401 (0.8431) time: 0.1291 data: 0.0541 max mem: 8255 +Train: [88] [4100/6250] eta: 0:05:13 lr: 0.000004 grad: 0.1463 (0.1477) loss: 0.8431 (0.8430) time: 0.1467 data: 0.0610 max mem: 8255 +Train: [88] [4200/6250] eta: 0:04:59 lr: 0.000004 grad: 0.1458 (0.1477) loss: 0.8425 (0.8429) time: 0.1871 data: 0.1037 max mem: 8255 +Train: [88] [4300/6250] eta: 0:04:45 lr: 0.000004 grad: 0.1398 (0.1477) loss: 0.8419 (0.8429) time: 0.1611 data: 0.0952 max mem: 8255 +Train: [88] [4400/6250] eta: 0:04:30 lr: 0.000004 grad: 0.1456 (0.1476) loss: 0.8428 (0.8430) time: 0.1472 data: 0.0792 max mem: 8255 +Train: [88] [4500/6250] eta: 0:04:18 lr: 0.000004 grad: 0.1370 (0.1475) loss: 0.8467 (0.8430) time: 0.1661 data: 0.0978 max mem: 8255 +Train: [88] [4600/6250] eta: 0:04:02 lr: 0.000004 grad: 0.1470 (0.1474) loss: 0.8456 (0.8431) time: 0.1092 data: 0.0332 max mem: 8255 +Train: [88] [4700/6250] eta: 0:03:47 lr: 0.000004 grad: 0.1417 (0.1474) loss: 0.8415 (0.8432) time: 0.1521 data: 0.0802 max mem: 8255 +Train: [88] [4800/6250] eta: 0:03:31 lr: 0.000004 grad: 0.1445 (0.1473) loss: 0.8478 (0.8432) time: 0.1239 data: 0.0509 max mem: 8255 +Train: [88] [4900/6250] eta: 0:03:16 lr: 0.000004 grad: 0.1421 (0.1472) loss: 0.8443 (0.8432) time: 0.1255 data: 0.0555 max mem: 8255 +Train: [88] [5000/6250] eta: 0:03:01 lr: 0.000004 grad: 0.1339 (0.1471) loss: 0.8500 (0.8433) time: 0.1317 data: 0.0649 max mem: 8255 +Train: [88] [5100/6250] eta: 0:02:46 lr: 0.000004 grad: 0.1367 (0.1470) loss: 0.8497 (0.8433) time: 0.1216 data: 0.0545 max mem: 8255 +Train: [88] [5200/6250] eta: 0:02:31 lr: 0.000004 grad: 0.1329 (0.1470) loss: 0.8437 (0.8433) time: 0.1019 data: 0.0269 max mem: 8255 +Train: [88] [5300/6250] eta: 0:02:17 lr: 0.000004 grad: 0.1376 (0.1469) loss: 0.8413 (0.8433) time: 0.1283 data: 0.0602 max mem: 8255 +Train: [88] [5400/6250] eta: 0:02:02 lr: 0.000004 grad: 0.1358 (0.1468) loss: 0.8411 (0.8434) time: 0.1072 data: 0.0387 max mem: 8255 +Train: [88] [5500/6250] eta: 0:01:48 lr: 0.000004 grad: 0.1387 (0.1466) loss: 0.8489 (0.8434) time: 0.1131 data: 0.0321 max mem: 8255 +Train: [88] [5600/6250] eta: 0:01:33 lr: 0.000004 grad: 0.1318 (0.1466) loss: 0.8473 (0.8435) time: 0.0925 data: 0.0227 max mem: 8255 +Train: [88] [5700/6250] eta: 0:01:19 lr: 0.000004 grad: 0.1388 (0.1464) loss: 0.8426 (0.8435) time: 0.1403 data: 0.0704 max mem: 8255 +Train: [88] [5800/6250] eta: 0:01:04 lr: 0.000004 grad: 0.1404 (0.1464) loss: 0.8469 (0.8436) time: 0.1259 data: 0.0539 max mem: 8255 +Train: [88] [5900/6250] eta: 0:00:50 lr: 0.000004 grad: 0.1393 (0.1463) loss: 0.8407 (0.8436) time: 0.1482 data: 0.0735 max mem: 8255 +Train: [88] [6000/6250] eta: 0:00:35 lr: 0.000004 grad: 0.1466 (0.1463) loss: 0.8407 (0.8435) time: 0.1261 data: 0.0475 max mem: 8255 +Train: [88] [6100/6250] eta: 0:00:21 lr: 0.000004 grad: 0.1493 (0.1464) loss: 0.8462 (0.8435) time: 0.1337 data: 0.0638 max mem: 8255 +Train: [88] [6200/6250] eta: 0:00:07 lr: 0.000004 grad: 0.1405 (0.1464) loss: 0.8415 (0.8435) time: 0.1286 data: 0.0563 max mem: 8255 +Train: [88] [6249/6250] eta: 0:00:00 lr: 0.000004 grad: 0.1486 (0.1464) loss: 0.8415 (0.8435) time: 0.1461 data: 0.0776 max mem: 8255 +Train: [88] Total time: 0:15:01 (0.1443 s / it) +Averaged stats: lr: 0.000004 grad: 0.1486 (0.1464) loss: 0.8415 (0.8435) +Eval (hcp-train-subset): [88] [ 0/62] eta: 0:04:14 loss: 0.8556 (0.8556) time: 4.1127 data: 4.0529 max mem: 8255 +Eval (hcp-train-subset): [88] [61/62] eta: 0:00:00 loss: 0.8447 (0.8477) time: 0.1360 data: 0.1142 max mem: 8255 +Eval (hcp-train-subset): [88] Total time: 0:00:13 (0.2186 s / it) +Averaged stats (hcp-train-subset): loss: 0.8447 (0.8477) +Eval (hcp-val): [88] [ 0/62] eta: 0:04:46 loss: 0.8661 (0.8661) time: 4.6195 data: 4.5618 max mem: 8255 +Eval (hcp-val): [88] [61/62] eta: 0:00:00 loss: 0.8696 (0.8716) time: 0.1238 data: 0.1033 max mem: 8255 +Eval (hcp-val): [88] Total time: 0:00:13 (0.2212 s / it) +Averaged stats (hcp-val): loss: 0.8696 (0.8716) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +Train: [89] [ 0/6250] eta: 11:30:12 lr: 0.000004 grad: nan (nan) loss: 0.7900 (0.7900) time: 6.6259 data: 6.5412 max mem: 8255 +Train: [89] [ 100/6250] eta: 0:19:21 lr: 0.000004 grad: 0.1651 (0.1853) loss: 0.8455 (0.8503) time: 0.1295 data: 0.0440 max mem: 8255 +Train: [89] [ 200/6250] eta: 0:16:28 lr: 0.000004 grad: 0.1399 (0.1754) loss: 0.8469 (0.8480) time: 0.1410 data: 0.0525 max mem: 8255 +Train: [89] [ 300/6250] eta: 0:15:37 lr: 0.000004 grad: 0.1382 (0.1670) loss: 0.8557 (0.8473) time: 0.1655 data: 0.0674 max mem: 8255 +Train: [89] [ 400/6250] eta: 0:14:52 lr: 0.000004 grad: 0.1416 (0.1641) loss: 0.8448 (0.8472) time: 0.1588 data: 0.0730 max mem: 8255 +Train: [89] [ 500/6250] eta: 0:14:05 lr: 0.000004 grad: 0.1575 (0.1615) loss: 0.8545 (0.8469) time: 0.1368 data: 0.0621 max mem: 8255 +Train: [89] [ 600/6250] eta: 0:13:42 lr: 0.000004 grad: 0.1413 (0.1605) loss: 0.8412 (0.8463) time: 0.1392 data: 0.0569 max mem: 8255 +Train: [89] [ 700/6250] eta: 0:13:34 lr: 0.000004 grad: 0.1484 (0.1590) loss: 0.8408 (0.8462) time: 0.1511 data: 0.0690 max mem: 8255 +Train: [89] [ 800/6250] eta: 0:13:22 lr: 0.000004 grad: 0.1525 (0.1583) loss: 0.8484 (0.8456) time: 0.1471 data: 0.0591 max mem: 8255 +Train: [89] [ 900/6250] eta: 0:13:43 lr: 0.000004 grad: 0.1421 (0.1570) loss: 0.8479 (0.8455) time: 0.2466 data: 0.1611 max mem: 8255 +Train: [89] [1000/6250] eta: 0:14:07 lr: 0.000004 grad: 0.1532 (0.1565) loss: 0.8451 (0.8453) time: 0.1598 data: 0.0688 max mem: 8255 +Train: [89] [1100/6250] eta: 0:13:44 lr: 0.000004 grad: 0.1347 (0.1554) loss: 0.8501 (0.8451) time: 0.1708 data: 0.0924 max mem: 8255 +Train: [89] [1200/6250] eta: 0:13:17 lr: 0.000004 grad: 0.1427 (0.1549) loss: 0.8398 (0.8447) time: 0.1005 data: 0.0224 max mem: 8255 +Train: [89] [1300/6250] eta: 0:12:55 lr: 0.000004 grad: 0.1406 (0.1543) loss: 0.8359 (0.8442) time: 0.1521 data: 0.0670 max mem: 8255 +Train: [89] [1400/6250] eta: 0:12:29 lr: 0.000004 grad: 0.1387 (0.1535) loss: 0.8438 (0.8439) time: 0.1369 data: 0.0663 max mem: 8255 +Train: [89] [1500/6250] eta: 0:12:06 lr: 0.000004 grad: 0.1401 (0.1527) loss: 0.8350 (0.8438) time: 0.1187 data: 0.0498 max mem: 8255 +Train: [89] [1600/6250] eta: 0:11:52 lr: 0.000004 grad: 0.1372 (0.1521) loss: 0.8415 (0.8435) time: 0.0940 data: 0.0002 max mem: 8255 +Train: [89] [1700/6250] eta: 0:11:30 lr: 0.000004 grad: 0.1373 (0.1516) loss: 0.8415 (0.8433) time: 0.1300 data: 0.0585 max mem: 8255 +Train: [89] [1800/6250] eta: 0:11:22 lr: 0.000004 grad: 0.1397 (0.1511) loss: 0.8346 (0.8432) time: 0.2200 data: 0.1438 max mem: 8255 +Train: [89] [1900/6250] eta: 0:11:01 lr: 0.000004 grad: 0.1367 (0.1507) loss: 0.8370 (0.8430) time: 0.1950 data: 0.1262 max mem: 8255 +Train: [89] [2000/6250] eta: 0:10:39 lr: 0.000004 grad: 0.1415 (0.1504) loss: 0.8477 (0.8430) time: 0.1198 data: 0.0365 max mem: 8255 +Train: [89] [2100/6250] eta: 0:10:22 lr: 0.000004 grad: 0.1387 (0.1502) loss: 0.8387 (0.8429) time: 0.1219 data: 0.0378 max mem: 8255 +Train: [89] [2200/6250] eta: 0:10:07 lr: 0.000004 grad: 0.1492 (0.1499) loss: 0.8455 (0.8429) time: 0.2081 data: 0.0920 max mem: 8255 +Train: [89] [2300/6250] eta: 0:09:49 lr: 0.000004 grad: 0.1388 (0.1497) loss: 0.8428 (0.8429) time: 0.1139 data: 0.0260 max mem: 8255 +Train: [89] [2400/6250] eta: 0:09:31 lr: 0.000004 grad: 0.1357 (0.1495) loss: 0.8398 (0.8429) time: 0.1328 data: 0.0595 max mem: 8255 +Train: [89] [2500/6250] eta: 0:09:15 lr: 0.000004 grad: 0.1367 (0.1493) loss: 0.8546 (0.8429) time: 0.1358 data: 0.0583 max mem: 8255 +Train: [89] [2600/6250] eta: 0:08:58 lr: 0.000004 grad: 0.1362 (0.1490) loss: 0.8495 (0.8431) time: 0.1326 data: 0.0607 max mem: 8255 +Train: [89] [2700/6250] eta: 0:08:43 lr: 0.000004 grad: 0.1443 (0.1488) loss: 0.8463 (0.8432) time: 0.1039 data: 0.0210 max mem: 8255 +Train: [89] [2800/6250] eta: 0:08:27 lr: 0.000004 grad: 0.1411 (0.1485) loss: 0.8442 (0.8433) time: 0.1426 data: 0.0714 max mem: 8255 +Train: [89] [2900/6250] eta: 0:08:11 lr: 0.000004 grad: 0.1337 (0.1483) loss: 0.8454 (0.8435) time: 0.1436 data: 0.0762 max mem: 8255 +Train: [89] [3000/6250] eta: 0:07:56 lr: 0.000004 grad: 0.1408 (0.1482) loss: 0.8467 (0.8436) time: 0.1400 data: 0.0652 max mem: 8255 +Train: [89] [3100/6250] eta: 0:07:41 lr: 0.000004 grad: 0.1434 (0.1481) loss: 0.8484 (0.8437) time: 0.1441 data: 0.0729 max mem: 8255 +Train: [89] [3200/6250] eta: 0:07:26 lr: 0.000004 grad: 0.1395 (0.1480) loss: 0.8382 (0.8437) time: 0.1598 data: 0.0878 max mem: 8255 +Train: [89] [3300/6250] eta: 0:07:12 lr: 0.000004 grad: 0.1348 (0.1478) loss: 0.8433 (0.8437) time: 0.1905 data: 0.1203 max mem: 8255 +Train: [89] [3400/6250] eta: 0:06:57 lr: 0.000004 grad: 0.1393 (0.1478) loss: 0.8475 (0.8438) time: 0.1563 data: 0.0813 max mem: 8255 +Train: [89] [3500/6250] eta: 0:06:42 lr: 0.000004 grad: 0.1510 (0.1477) loss: 0.8426 (0.8437) time: 0.1104 data: 0.0400 max mem: 8255 +Train: [89] [3600/6250] eta: 0:06:26 lr: 0.000004 grad: 0.1375 (0.1478) loss: 0.8325 (0.8435) time: 0.1352 data: 0.0569 max mem: 8255 +Train: [89] [3700/6250] eta: 0:06:11 lr: 0.000004 grad: 0.1440 (0.1478) loss: 0.8385 (0.8434) time: 0.1418 data: 0.0644 max mem: 8255 +Train: [89] [3800/6250] eta: 0:05:56 lr: 0.000004 grad: 0.1470 (0.1479) loss: 0.8480 (0.8434) time: 0.1442 data: 0.0745 max mem: 8255 +Train: [89] [3900/6250] eta: 0:05:41 lr: 0.000004 grad: 0.1458 (0.1479) loss: 0.8357 (0.8433) time: 0.1366 data: 0.0593 max mem: 8255 +Train: [89] [4000/6250] eta: 0:05:26 lr: 0.000004 grad: 0.1432 (0.1480) loss: 0.8434 (0.8432) time: 0.1296 data: 0.0550 max mem: 8255 +Train: [89] [4100/6250] eta: 0:05:11 lr: 0.000004 grad: 0.1438 (0.1479) loss: 0.8499 (0.8432) time: 0.1525 data: 0.0773 max mem: 8255 +Train: [89] [4200/6250] eta: 0:04:56 lr: 0.000004 grad: 0.1460 (0.1480) loss: 0.8443 (0.8431) time: 0.1183 data: 0.0353 max mem: 8255 +Train: [89] [4300/6250] eta: 0:04:41 lr: 0.000004 grad: 0.1384 (0.1480) loss: 0.8358 (0.8432) time: 0.1360 data: 0.0593 max mem: 8255 +Train: [89] [4400/6250] eta: 0:04:27 lr: 0.000004 grad: 0.1410 (0.1478) loss: 0.8399 (0.8431) time: 0.1712 data: 0.0583 max mem: 8255 +Train: [89] [4500/6250] eta: 0:04:12 lr: 0.000004 grad: 0.1471 (0.1478) loss: 0.8456 (0.8432) time: 0.1696 data: 0.0952 max mem: 8255 +Train: [89] [4600/6250] eta: 0:03:57 lr: 0.000004 grad: 0.1363 (0.1477) loss: 0.8486 (0.8432) time: 0.1218 data: 0.0435 max mem: 8255 +Train: [89] [4700/6250] eta: 0:03:44 lr: 0.000004 grad: 0.1380 (0.1476) loss: 0.8415 (0.8432) time: 0.0952 data: 0.0002 max mem: 8255 +Train: [89] [4800/6250] eta: 0:03:30 lr: 0.000004 grad: 0.1351 (0.1475) loss: 0.8459 (0.8432) time: 0.1079 data: 0.0301 max mem: 8255 +Train: [89] [4900/6250] eta: 0:03:15 lr: 0.000004 grad: 0.1388 (0.1474) loss: 0.8444 (0.8432) time: 0.0904 data: 0.0002 max mem: 8255 +Train: [89] [5000/6250] eta: 0:03:01 lr: 0.000004 grad: 0.1395 (0.1473) loss: 0.8493 (0.8432) time: 0.1212 data: 0.0449 max mem: 8255 +Train: [89] [5100/6250] eta: 0:02:46 lr: 0.000004 grad: 0.1465 (0.1472) loss: 0.8361 (0.8432) time: 0.1058 data: 0.0373 max mem: 8255 +Train: [89] [5200/6250] eta: 0:02:32 lr: 0.000003 grad: 0.1365 (0.1471) loss: 0.8356 (0.8432) time: 0.1369 data: 0.0638 max mem: 8255 +Train: [89] [5300/6250] eta: 0:02:17 lr: 0.000003 grad: 0.1352 (0.1470) loss: 0.8432 (0.8432) time: 0.1571 data: 0.0669 max mem: 8255 +Train: [89] [5400/6250] eta: 0:02:03 lr: 0.000003 grad: 0.1370 (0.1470) loss: 0.8494 (0.8432) time: 0.1656 data: 0.0929 max mem: 8255 +Train: [89] [5500/6250] eta: 0:01:48 lr: 0.000003 grad: 0.1529 (0.1470) loss: 0.8400 (0.8432) time: 0.1204 data: 0.0541 max mem: 8255 +Train: [89] [5600/6250] eta: 0:01:33 lr: 0.000003 grad: 0.1446 (0.1470) loss: 0.8457 (0.8432) time: 0.1170 data: 0.0443 max mem: 8255 +Train: [89] [5700/6250] eta: 0:01:19 lr: 0.000003 grad: 0.1463 (0.1471) loss: 0.8423 (0.8432) time: 0.1422 data: 0.0738 max mem: 8255 +Train: [89] [5800/6250] eta: 0:01:04 lr: 0.000003 grad: 0.1450 (0.1472) loss: 0.8399 (0.8431) time: 0.1371 data: 0.0647 max mem: 8255 +Train: [89] [5900/6250] eta: 0:00:50 lr: 0.000003 grad: 0.1444 (0.1472) loss: 0.8363 (0.8430) time: 0.1364 data: 0.0660 max mem: 8255 +Train: [89] [6000/6250] eta: 0:00:36 lr: 0.000003 grad: 0.1468 (0.1473) loss: 0.8429 (0.8430) time: 0.2108 data: 0.1380 max mem: 8255 +Train: [89] [6100/6250] eta: 0:00:21 lr: 0.000003 grad: 0.1513 (0.1474) loss: 0.8455 (0.8430) time: 0.1217 data: 0.0513 max mem: 8255 +Train: [89] [6200/6250] eta: 0:00:07 lr: 0.000003 grad: 0.1485 (0.1474) loss: 0.8476 (0.8430) time: 0.1414 data: 0.0733 max mem: 8255 +Train: [89] [6249/6250] eta: 0:00:00 lr: 0.000003 grad: 0.1517 (0.1474) loss: 0.8306 (0.8430) time: 0.1292 data: 0.0559 max mem: 8255 +Train: [89] Total time: 0:15:02 (0.1445 s / it) +Averaged stats: lr: 0.000003 grad: 0.1517 (0.1474) loss: 0.8306 (0.8430) +Eval (hcp-train-subset): [89] [ 0/62] eta: 0:05:37 loss: 0.8511 (0.8511) time: 5.4425 data: 5.4155 max mem: 8255 +Eval (hcp-train-subset): [89] [61/62] eta: 0:00:00 loss: 0.8459 (0.8469) time: 0.1386 data: 0.1167 max mem: 8255 +Eval (hcp-train-subset): [89] Total time: 0:00:13 (0.2219 s / it) +Averaged stats (hcp-train-subset): loss: 0.8459 (0.8469) +Making plots (hcp-train-subset): example=55 +Eval (hcp-val): [89] [ 0/62] eta: 0:04:23 loss: 0.8692 (0.8692) time: 4.2472 data: 4.1602 max mem: 8255 +Eval (hcp-val): [89] [61/62] eta: 0:00:00 loss: 0.8700 (0.8715) time: 0.1220 data: 0.1012 max mem: 8255 +Eval (hcp-val): [89] Total time: 0:00:13 (0.2138 s / it) +Averaged stats (hcp-val): loss: 0.8700 (0.8715) +Making plots (hcp-val): example=15 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +Train: [90] [ 0/6250] eta: 11:47:35 lr: 0.000003 grad: 0.3142 (0.3142) loss: 0.7736 (0.7736) time: 6.7929 data: 6.6670 max mem: 8255 +Train: [90] [ 100/6250] eta: 0:20:31 lr: 0.000003 grad: 0.1666 (0.2083) loss: 0.8453 (0.8423) time: 0.1719 data: 0.0813 max mem: 8255 +Train: [90] [ 200/6250] eta: 0:17:21 lr: 0.000003 grad: 0.1386 (0.1847) loss: 0.8551 (0.8468) time: 0.1348 data: 0.0449 max mem: 8255 +Train: [90] [ 300/6250] eta: 0:15:43 lr: 0.000003 grad: 0.1522 (0.1755) loss: 0.8432 (0.8476) time: 0.1313 data: 0.0459 max mem: 8255 +Train: [90] [ 400/6250] eta: 0:14:34 lr: 0.000003 grad: 0.1620 (0.1716) loss: 0.8386 (0.8466) time: 0.1242 data: 0.0298 max mem: 8255 +Train: [90] [ 500/6250] eta: 0:13:54 lr: 0.000003 grad: 0.1624 (0.1714) loss: 0.8353 (0.8441) time: 0.1142 data: 0.0269 max mem: 8255 +Train: [90] [ 600/6250] eta: 0:13:15 lr: 0.000003 grad: 0.1600 (0.1710) loss: 0.8308 (0.8417) time: 0.1014 data: 0.0169 max mem: 8255 +Train: [90] [ 700/6250] eta: 0:12:45 lr: 0.000003 grad: 0.1548 (0.1695) loss: 0.8358 (0.8407) time: 0.1143 data: 0.0223 max mem: 8255 +Train: [90] [ 800/6250] eta: 0:12:26 lr: 0.000003 grad: 0.1485 (0.1679) loss: 0.8350 (0.8402) time: 0.1448 data: 0.0626 max mem: 8255 +Train: [90] [ 900/6250] eta: 0:12:34 lr: 0.000003 grad: 0.1482 (0.1664) loss: 0.8431 (0.8402) time: 0.2019 data: 0.1225 max mem: 8255 +Train: [90] [1000/6250] eta: 0:12:29 lr: 0.000003 grad: 0.1563 (0.1656) loss: 0.8400 (0.8400) time: 0.1369 data: 0.0460 max mem: 8255 +Train: [90] [1100/6250] eta: 0:12:21 lr: 0.000003 grad: 0.1483 (0.1645) loss: 0.8472 (0.8403) time: 0.0935 data: 0.0002 max mem: 8255 +Train: [90] [1200/6250] eta: 0:12:17 lr: 0.000003 grad: 0.1502 (0.1635) loss: 0.8345 (0.8401) time: 0.1776 data: 0.1022 max mem: 8255 +Train: [90] [1300/6250] eta: 0:12:06 lr: 0.000003 grad: 0.1504 (0.1624) loss: 0.8380 (0.8401) time: 0.1559 data: 0.0807 max mem: 8255 +Train: [90] [1400/6250] eta: 0:11:55 lr: 0.000003 grad: 0.1453 (0.1617) loss: 0.8326 (0.8401) time: 0.1383 data: 0.0648 max mem: 8255 +Train: [90] [1500/6250] eta: 0:11:35 lr: 0.000003 grad: 0.1427 (0.1610) loss: 0.8355 (0.8399) time: 0.1300 data: 0.0527 max mem: 8255 +Train: [90] [1600/6250] eta: 0:11:17 lr: 0.000003 grad: 0.1432 (0.1606) loss: 0.8335 (0.8398) time: 0.1212 data: 0.0467 max mem: 8255 +Train: [90] [1700/6250] eta: 0:11:04 lr: 0.000003 grad: 0.1467 (0.1600) loss: 0.8404 (0.8399) time: 0.1515 data: 0.0531 max mem: 8255 +Train: [90] [1800/6250] eta: 0:10:59 lr: 0.000003 grad: 0.1384 (0.1593) loss: 0.8410 (0.8400) time: 0.2343 data: 0.0944 max mem: 8255 +Train: [90] [1900/6250] eta: 0:10:40 lr: 0.000003 grad: 0.1588 (0.1588) loss: 0.8374 (0.8401) time: 0.1475 data: 0.0748 max mem: 8255 +Train: [90] [2000/6250] eta: 0:10:22 lr: 0.000003 grad: 0.1479 (0.1583) loss: 0.8432 (0.8400) time: 0.1173 data: 0.0384 max mem: 8255 +Train: [90] [2100/6250] eta: 0:10:07 lr: 0.000003 grad: 0.1435 (0.1577) loss: 0.8474 (0.8403) time: 0.1716 data: 0.0780 max mem: 8255 +Train: [90] [2200/6250] eta: 0:09:53 lr: 0.000003 grad: 0.1463 (0.1573) loss: 0.8509 (0.8404) time: 0.1491 data: 0.0825 max mem: 8255 +Train: [90] [2300/6250] eta: 0:09:37 lr: 0.000003 grad: 0.1449 (0.1568) loss: 0.8427 (0.8405) time: 0.1500 data: 0.0566 max mem: 8255 +Train: [90] [2400/6250] eta: 0:09:21 lr: 0.000003 grad: 0.1391 (0.1565) loss: 0.8400 (0.8406) time: 0.1386 data: 0.0616 max mem: 8255 +Train: [90] [2500/6250] eta: 0:09:05 lr: 0.000003 grad: 0.1469 (0.1559) loss: 0.8457 (0.8408) time: 0.1364 data: 0.0610 max mem: 8255 +Train: [90] [2600/6250] eta: 0:08:51 lr: 0.000003 grad: 0.1476 (0.1555) loss: 0.8389 (0.8409) time: 0.1029 data: 0.0229 max mem: 8255 +Train: [90] [2700/6250] eta: 0:08:35 lr: 0.000003 grad: 0.1577 (0.1552) loss: 0.8359 (0.8410) time: 0.1185 data: 0.0505 max mem: 8255 +Train: [90] [2800/6250] eta: 0:08:19 lr: 0.000003 grad: 0.1514 (0.1550) loss: 0.8391 (0.8410) time: 0.1191 data: 0.0424 max mem: 8255 +Train: [90] [2900/6250] eta: 0:08:05 lr: 0.000003 grad: 0.1487 (0.1549) loss: 0.8422 (0.8411) time: 0.0918 data: 0.0060 max mem: 8255 +Train: [90] [3000/6250] eta: 0:07:49 lr: 0.000003 grad: 0.1431 (0.1547) loss: 0.8417 (0.8411) time: 0.1148 data: 0.0345 max mem: 8255 +Train: [90] [3100/6250] eta: 0:07:34 lr: 0.000003 grad: 0.1474 (0.1545) loss: 0.8452 (0.8411) time: 0.1608 data: 0.0705 max mem: 8255 +Train: [90] [3200/6250] eta: 0:07:22 lr: 0.000003 grad: 0.1518 (0.1545) loss: 0.8406 (0.8411) time: 0.1182 data: 0.0370 max mem: 8255 +Train: [90] [3300/6250] eta: 0:07:06 lr: 0.000003 grad: 0.1482 (0.1544) loss: 0.8420 (0.8410) time: 0.1396 data: 0.0719 max mem: 8255 +Train: [90] [3400/6250] eta: 0:06:50 lr: 0.000003 grad: 0.1468 (0.1544) loss: 0.8413 (0.8410) time: 0.1266 data: 0.0544 max mem: 8255 +Train: [90] [3500/6250] eta: 0:06:35 lr: 0.000003 grad: 0.1587 (0.1544) loss: 0.8432 (0.8410) time: 0.1406 data: 0.0777 max mem: 8255 +Train: [90] [3600/6250] eta: 0:06:20 lr: 0.000003 grad: 0.1465 (0.1544) loss: 0.8429 (0.8410) time: 0.1234 data: 0.0480 max mem: 8255 +Train: [90] [3700/6250] eta: 0:06:06 lr: 0.000003 grad: 0.1533 (0.1543) loss: 0.8393 (0.8409) time: 0.2252 data: 0.1639 max mem: 8255 +Train: [90] [3800/6250] eta: 0:05:51 lr: 0.000003 grad: 0.1427 (0.1544) loss: 0.8467 (0.8409) time: 0.1325 data: 0.0549 max mem: 8255 +Train: [90] [3900/6250] eta: 0:05:36 lr: 0.000003 grad: 0.1465 (0.1546) loss: 0.8433 (0.8409) time: 0.1355 data: 0.0695 max mem: 8255 +Train: [90] [4000/6250] eta: 0:05:22 lr: 0.000003 grad: 0.1577 (0.1545) loss: 0.8437 (0.8409) time: 0.1300 data: 0.0576 max mem: 8255 +Train: [90] [4100/6250] eta: 0:05:07 lr: 0.000003 grad: 0.1483 (0.1544) loss: 0.8482 (0.8410) time: 0.1275 data: 0.0579 max mem: 8255 +Train: [90] [4200/6250] eta: 0:04:53 lr: 0.000003 grad: 0.1458 (0.1544) loss: 0.8455 (0.8410) time: 0.1708 data: 0.1104 max mem: 8255 +Train: [90] [4300/6250] eta: 0:04:37 lr: 0.000003 grad: 0.1491 (0.1543) loss: 0.8408 (0.8410) time: 0.1459 data: 0.0774 max mem: 8255 +Train: [90] [4400/6250] eta: 0:04:22 lr: 0.000003 grad: 0.1398 (0.1543) loss: 0.8463 (0.8411) time: 0.1098 data: 0.0384 max mem: 8255 +Train: [90] [4500/6250] eta: 0:04:06 lr: 0.000003 grad: 0.1541 (0.1543) loss: 0.8471 (0.8411) time: 0.1025 data: 0.0290 max mem: 8255 +Train: [90] [4600/6250] eta: 0:03:51 lr: 0.000003 grad: 0.1455 (0.1542) loss: 0.8389 (0.8411) time: 0.0974 data: 0.0247 max mem: 8255 +Train: [90] [4700/6250] eta: 0:03:36 lr: 0.000003 grad: 0.1512 (0.1541) loss: 0.8380 (0.8412) time: 0.1207 data: 0.0469 max mem: 8255 +Train: [90] [4800/6250] eta: 0:03:22 lr: 0.000003 grad: 0.1473 (0.1540) loss: 0.8401 (0.8413) time: 0.1347 data: 0.0621 max mem: 8255 +Train: [90] [4900/6250] eta: 0:03:08 lr: 0.000003 grad: 0.1551 (0.1539) loss: 0.8451 (0.8413) time: 0.1263 data: 0.0592 max mem: 8255 +Train: [90] [5000/6250] eta: 0:02:55 lr: 0.000003 grad: 0.1414 (0.1538) loss: 0.8438 (0.8414) time: 0.1684 data: 0.1033 max mem: 8255 +Train: [90] [5100/6250] eta: 0:02:41 lr: 0.000003 grad: 0.1352 (0.1537) loss: 0.8503 (0.8414) time: 0.1632 data: 0.0957 max mem: 8255 +Train: [90] [5200/6250] eta: 0:02:27 lr: 0.000003 grad: 0.1432 (0.1536) loss: 0.8414 (0.8415) time: 0.1397 data: 0.0691 max mem: 8255 +Train: [90] [5300/6250] eta: 0:02:13 lr: 0.000003 grad: 0.1423 (0.1535) loss: 0.8488 (0.8416) time: 0.1328 data: 0.0639 max mem: 8255 +Train: [90] [5400/6250] eta: 0:01:59 lr: 0.000003 grad: 0.1453 (0.1533) loss: 0.8342 (0.8415) time: 0.1133 data: 0.0382 max mem: 8255 +Train: [90] [5500/6250] eta: 0:01:45 lr: 0.000003 grad: 0.1382 (0.1532) loss: 0.8370 (0.8416) time: 0.1414 data: 0.0621 max mem: 8255 +Train: [90] [5600/6250] eta: 0:01:31 lr: 0.000003 grad: 0.1462 (0.1531) loss: 0.8466 (0.8416) time: 0.1578 data: 0.0935 max mem: 8255 +Train: [90] [5700/6250] eta: 0:01:17 lr: 0.000003 grad: 0.1421 (0.1531) loss: 0.8438 (0.8416) time: 0.1950 data: 0.0862 max mem: 8255 +Train: [90] [5800/6250] eta: 0:01:03 lr: 0.000003 grad: 0.1517 (0.1531) loss: 0.8426 (0.8416) time: 0.1190 data: 0.0534 max mem: 8255 +Train: [90] [5900/6250] eta: 0:00:49 lr: 0.000003 grad: 0.1441 (0.1529) loss: 0.8482 (0.8417) time: 0.1454 data: 0.0690 max mem: 8255 +Train: [90] [6000/6250] eta: 0:00:35 lr: 0.000003 grad: 0.1433 (0.1529) loss: 0.8487 (0.8417) time: 0.1502 data: 0.0486 max mem: 8255 +Train: [90] [6100/6250] eta: 0:00:21 lr: 0.000003 grad: 0.1479 (0.1529) loss: 0.8346 (0.8417) time: 0.1581 data: 0.0938 max mem: 8255 +Train: [90] [6200/6250] eta: 0:00:07 lr: 0.000003 grad: 0.1421 (0.1528) loss: 0.8422 (0.8417) time: 0.1732 data: 0.0957 max mem: 8255 +Train: [90] [6249/6250] eta: 0:00:00 lr: 0.000003 grad: 0.1490 (0.1527) loss: 0.8405 (0.8417) time: 0.1511 data: 0.0854 max mem: 8255 +Train: [90] Total time: 0:14:51 (0.1427 s / it) +Averaged stats: lr: 0.000003 grad: 0.1490 (0.1527) loss: 0.8405 (0.8417) +Eval (hcp-train-subset): [90] [ 0/62] eta: 0:05:28 loss: 0.8517 (0.8517) time: 5.3005 data: 5.2734 max mem: 8255 +Eval (hcp-train-subset): [90] [61/62] eta: 0:00:00 loss: 0.8452 (0.8466) time: 0.1265 data: 0.1057 max mem: 8255 +Eval (hcp-train-subset): [90] Total time: 0:00:13 (0.2204 s / it) +Averaged stats (hcp-train-subset): loss: 0.8452 (0.8466) +Eval (hcp-val): [90] [ 0/62] eta: 0:04:10 loss: 0.8695 (0.8695) time: 4.0456 data: 3.9610 max mem: 8255 +Eval (hcp-val): [90] [61/62] eta: 0:00:00 loss: 0.8697 (0.8711) time: 0.1206 data: 0.1000 max mem: 8255 +Eval (hcp-val): [90] Total time: 0:00:13 (0.2214 s / it) +Averaged stats (hcp-val): loss: 0.8697 (0.8711) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +Train: [91] [ 0/6250] eta: 8:04:48 lr: 0.000003 grad: 0.1168 (0.1168) loss: 0.9024 (0.9024) time: 4.6541 data: 4.4630 max mem: 8255 +Train: [91] [ 100/6250] eta: 0:21:10 lr: 0.000003 grad: 0.2124 (0.2268) loss: 0.8335 (0.8454) time: 0.1754 data: 0.0944 max mem: 8255 +Train: [91] [ 200/6250] eta: 0:17:51 lr: 0.000003 grad: 0.1801 (0.2146) loss: 0.8313 (0.8393) time: 0.1650 data: 0.0743 max mem: 8255 +Train: [91] [ 300/6250] eta: 0:16:35 lr: 0.000003 grad: 0.1715 (0.1998) loss: 0.8435 (0.8389) time: 0.1440 data: 0.0343 max mem: 8255 +Train: [91] [ 400/6250] eta: 0:15:34 lr: 0.000003 grad: 0.1415 (0.1897) loss: 0.8532 (0.8404) time: 0.1311 data: 0.0513 max mem: 8255 +Train: [91] [ 500/6250] eta: 0:14:40 lr: 0.000003 grad: 0.1454 (0.1832) loss: 0.8523 (0.8416) time: 0.1280 data: 0.0477 max mem: 8255 +Train: [91] [ 600/6250] eta: 0:14:09 lr: 0.000003 grad: 0.1547 (0.1802) loss: 0.8462 (0.8422) time: 0.1449 data: 0.0583 max mem: 8255 +Train: [91] [ 700/6250] eta: 0:13:44 lr: 0.000003 grad: 0.1691 (0.1770) loss: 0.8402 (0.8423) time: 0.1111 data: 0.0208 max mem: 8255 +Train: [91] [ 800/6250] eta: 0:13:38 lr: 0.000003 grad: 0.1496 (0.1742) loss: 0.8534 (0.8427) time: 0.1627 data: 0.0894 max mem: 8255 +Train: [91] [ 900/6250] eta: 0:13:46 lr: 0.000003 grad: 0.1548 (0.1720) loss: 0.8464 (0.8430) time: 0.1981 data: 0.1030 max mem: 8255 +Train: [91] [1000/6250] eta: 0:14:03 lr: 0.000003 grad: 0.1502 (0.1700) loss: 0.8384 (0.8433) time: 0.1740 data: 0.0912 max mem: 8255 +Train: [91] [1100/6250] eta: 0:13:29 lr: 0.000003 grad: 0.1476 (0.1683) loss: 0.8524 (0.8435) time: 0.1668 data: 0.1014 max mem: 8255 +Train: [91] [1200/6250] eta: 0:13:07 lr: 0.000003 grad: 0.1486 (0.1667) loss: 0.8394 (0.8437) time: 0.1343 data: 0.0670 max mem: 8255 +Train: [91] [1300/6250] eta: 0:12:47 lr: 0.000003 grad: 0.1433 (0.1655) loss: 0.8468 (0.8439) time: 0.1779 data: 0.0787 max mem: 8255 +Train: [91] [1400/6250] eta: 0:12:39 lr: 0.000003 grad: 0.1557 (0.1646) loss: 0.8361 (0.8438) time: 0.1359 data: 0.0626 max mem: 8255 +Train: [91] [1500/6250] eta: 0:12:13 lr: 0.000003 grad: 0.1532 (0.1638) loss: 0.8437 (0.8437) time: 0.1185 data: 0.0504 max mem: 8255 +Train: [91] [1600/6250] eta: 0:11:49 lr: 0.000003 grad: 0.1475 (0.1638) loss: 0.8461 (0.8435) time: 0.1200 data: 0.0489 max mem: 8255 +Train: [91] [1700/6250] eta: 0:11:28 lr: 0.000003 grad: 0.1427 (0.1630) loss: 0.8447 (0.8435) time: 0.1520 data: 0.0826 max mem: 8255 +Train: [91] [1800/6250] eta: 0:11:08 lr: 0.000003 grad: 0.1500 (0.1625) loss: 0.8390 (0.8433) time: 0.1376 data: 0.0634 max mem: 8255 +Train: [91] [1900/6250] eta: 0:10:52 lr: 0.000003 grad: 0.1571 (0.1619) loss: 0.8381 (0.8432) time: 0.1468 data: 0.0822 max mem: 8255 +Train: [91] [2000/6250] eta: 0:10:35 lr: 0.000003 grad: 0.1461 (0.1615) loss: 0.8518 (0.8433) time: 0.1493 data: 0.0744 max mem: 8255 +Train: [91] [2100/6250] eta: 0:10:27 lr: 0.000003 grad: 0.1528 (0.1612) loss: 0.8353 (0.8431) time: 0.2582 data: 0.1881 max mem: 8255 +Train: [91] [2200/6250] eta: 0:10:08 lr: 0.000003 grad: 0.1454 (0.1609) loss: 0.8434 (0.8431) time: 0.1118 data: 0.0188 max mem: 8255 +Train: [91] [2300/6250] eta: 0:09:53 lr: 0.000003 grad: 0.1576 (0.1607) loss: 0.8441 (0.8430) time: 0.1739 data: 0.1019 max mem: 8255 +Train: [91] [2400/6250] eta: 0:09:41 lr: 0.000003 grad: 0.1505 (0.1603) loss: 0.8423 (0.8429) time: 0.1226 data: 0.0550 max mem: 8255 +Train: [91] [2500/6250] eta: 0:09:26 lr: 0.000003 grad: 0.1610 (0.1600) loss: 0.8351 (0.8429) time: 0.1592 data: 0.0895 max mem: 8255 +Train: [91] [2600/6250] eta: 0:09:09 lr: 0.000003 grad: 0.1495 (0.1597) loss: 0.8356 (0.8427) time: 0.1365 data: 0.0673 max mem: 8255 +Train: [91] [2700/6250] eta: 0:08:51 lr: 0.000002 grad: 0.1487 (0.1595) loss: 0.8440 (0.8427) time: 0.1330 data: 0.0593 max mem: 8255 +Train: [91] [2800/6250] eta: 0:08:36 lr: 0.000002 grad: 0.1509 (0.1591) loss: 0.8439 (0.8426) time: 0.1587 data: 0.0851 max mem: 8255 +Train: [91] [2900/6250] eta: 0:08:19 lr: 0.000002 grad: 0.1440 (0.1588) loss: 0.8423 (0.8426) time: 0.0878 data: 0.0080 max mem: 8255 +Train: [91] [3000/6250] eta: 0:08:03 lr: 0.000002 grad: 0.1403 (0.1586) loss: 0.8479 (0.8425) time: 0.1473 data: 0.0783 max mem: 8255 +Train: [91] [3100/6250] eta: 0:07:48 lr: 0.000002 grad: 0.1529 (0.1585) loss: 0.8379 (0.8424) time: 0.1813 data: 0.1119 max mem: 8255 +Train: [91] [3200/6250] eta: 0:07:31 lr: 0.000002 grad: 0.1483 (0.1584) loss: 0.8468 (0.8424) time: 0.1209 data: 0.0574 max mem: 8255 +Train: [91] [3300/6250] eta: 0:07:15 lr: 0.000002 grad: 0.1450 (0.1583) loss: 0.8453 (0.8423) time: 0.1233 data: 0.0542 max mem: 8255 +Train: [91] [3400/6250] eta: 0:07:01 lr: 0.000002 grad: 0.1481 (0.1581) loss: 0.8425 (0.8423) time: 0.0864 data: 0.0092 max mem: 8255 +Train: [91] [3500/6250] eta: 0:06:46 lr: 0.000002 grad: 0.1538 (0.1580) loss: 0.8403 (0.8423) time: 0.1563 data: 0.0842 max mem: 8255 +Train: [91] [3600/6250] eta: 0:06:31 lr: 0.000002 grad: 0.1460 (0.1579) loss: 0.8450 (0.8422) time: 0.0809 data: 0.0026 max mem: 8255 +Train: [91] [3700/6250] eta: 0:06:15 lr: 0.000002 grad: 0.1524 (0.1577) loss: 0.8363 (0.8421) time: 0.1295 data: 0.0654 max mem: 8255 +Train: [91] [3800/6250] eta: 0:06:02 lr: 0.000002 grad: 0.1521 (0.1576) loss: 0.8392 (0.8421) time: 0.1048 data: 0.0002 max mem: 8255 +Train: [91] [3900/6250] eta: 0:05:47 lr: 0.000002 grad: 0.1550 (0.1575) loss: 0.8371 (0.8420) time: 0.1551 data: 0.0769 max mem: 8255 +Train: [91] [4000/6250] eta: 0:05:32 lr: 0.000002 grad: 0.1554 (0.1573) loss: 0.8425 (0.8419) time: 0.1603 data: 0.0866 max mem: 8255 +Train: [91] [4100/6250] eta: 0:05:17 lr: 0.000002 grad: 0.1528 (0.1573) loss: 0.8417 (0.8418) time: 0.1282 data: 0.0664 max mem: 8255 +Train: [91] [4200/6250] eta: 0:05:02 lr: 0.000002 grad: 0.1496 (0.1574) loss: 0.8393 (0.8417) time: 0.1406 data: 0.0681 max mem: 8255 +Train: [91] [4300/6250] eta: 0:04:47 lr: 0.000002 grad: 0.1515 (0.1574) loss: 0.8348 (0.8416) time: 0.1328 data: 0.0616 max mem: 8255 +Train: [91] [4400/6250] eta: 0:04:32 lr: 0.000002 grad: 0.1508 (0.1574) loss: 0.8407 (0.8415) time: 0.1476 data: 0.0746 max mem: 8255 +Train: [91] [4500/6250] eta: 0:04:17 lr: 0.000002 grad: 0.1514 (0.1574) loss: 0.8427 (0.8414) time: 0.1098 data: 0.0268 max mem: 8255 +Train: [91] [4600/6250] eta: 0:04:02 lr: 0.000002 grad: 0.1563 (0.1573) loss: 0.8316 (0.8414) time: 0.1218 data: 0.0376 max mem: 8255 +Train: [91] [4700/6250] eta: 0:03:46 lr: 0.000002 grad: 0.1574 (0.1572) loss: 0.8280 (0.8412) time: 0.1239 data: 0.0520 max mem: 8255 +Train: [91] [4800/6250] eta: 0:03:31 lr: 0.000002 grad: 0.1506 (0.1572) loss: 0.8419 (0.8412) time: 0.1395 data: 0.0591 max mem: 8255 +Train: [91] [4900/6250] eta: 0:03:16 lr: 0.000002 grad: 0.1656 (0.1571) loss: 0.8386 (0.8411) time: 0.1220 data: 0.0521 max mem: 8255 +Train: [91] [5000/6250] eta: 0:03:01 lr: 0.000002 grad: 0.1518 (0.1571) loss: 0.8411 (0.8411) time: 0.1341 data: 0.0618 max mem: 8255 +Train: [91] [5100/6250] eta: 0:02:47 lr: 0.000002 grad: 0.1598 (0.1572) loss: 0.8402 (0.8410) time: 0.1702 data: 0.1022 max mem: 8255 +Train: [91] [5200/6250] eta: 0:02:33 lr: 0.000002 grad: 0.1473 (0.1572) loss: 0.8460 (0.8409) time: 0.1646 data: 0.0954 max mem: 8255 +Train: [91] [5300/6250] eta: 0:02:18 lr: 0.000002 grad: 0.1567 (0.1574) loss: 0.8387 (0.8408) time: 0.0941 data: 0.0197 max mem: 8255 +Train: [91] [5400/6250] eta: 0:02:04 lr: 0.000002 grad: 0.1512 (0.1574) loss: 0.8368 (0.8407) time: 0.2387 data: 0.1726 max mem: 8255 +Train: [91] [5500/6250] eta: 0:01:50 lr: 0.000002 grad: 0.1665 (0.1575) loss: 0.8376 (0.8407) time: 0.1459 data: 0.0795 max mem: 8255 +Train: [91] [5600/6250] eta: 0:01:35 lr: 0.000002 grad: 0.1549 (0.1575) loss: 0.8466 (0.8406) time: 0.1818 data: 0.1146 max mem: 8255 +Train: [91] [5700/6250] eta: 0:01:21 lr: 0.000002 grad: 0.1616 (0.1576) loss: 0.8310 (0.8405) time: 0.2081 data: 0.1494 max mem: 8255 +Train: [91] [5800/6250] eta: 0:01:06 lr: 0.000002 grad: 0.1641 (0.1577) loss: 0.8329 (0.8404) time: 0.1127 data: 0.0422 max mem: 8255 +Train: [91] [5900/6250] eta: 0:00:51 lr: 0.000002 grad: 0.1583 (0.1577) loss: 0.8408 (0.8404) time: 0.1580 data: 0.0935 max mem: 8255 +Train: [91] [6000/6250] eta: 0:00:37 lr: 0.000002 grad: 0.1518 (0.1578) loss: 0.8290 (0.8403) time: 0.1692 data: 0.1058 max mem: 8255 +Train: [91] [6100/6250] eta: 0:00:22 lr: 0.000002 grad: 0.1523 (0.1578) loss: 0.8359 (0.8403) time: 0.2242 data: 0.1576 max mem: 8255 +Train: [91] [6200/6250] eta: 0:00:07 lr: 0.000002 grad: 0.1551 (0.1577) loss: 0.8388 (0.8403) time: 0.1409 data: 0.0685 max mem: 8255 +Train: [91] [6249/6250] eta: 0:00:00 lr: 0.000002 grad: 0.1550 (0.1577) loss: 0.8386 (0.8403) time: 0.1516 data: 0.0754 max mem: 8255 +Train: [91] Total time: 0:15:32 (0.1492 s / it) +Averaged stats: lr: 0.000002 grad: 0.1550 (0.1577) loss: 0.8386 (0.8403) +Eval (hcp-train-subset): [91] [ 0/62] eta: 0:05:30 loss: 0.8514 (0.8514) time: 5.3353 data: 5.3097 max mem: 8255 +Eval (hcp-train-subset): [91] [61/62] eta: 0:00:00 loss: 0.8436 (0.8446) time: 0.1199 data: 0.0993 max mem: 8255 +Eval (hcp-train-subset): [91] Total time: 0:00:13 (0.2210 s / it) +Averaged stats (hcp-train-subset): loss: 0.8436 (0.8446) +Eval (hcp-val): [91] [ 0/62] eta: 0:04:48 loss: 0.8681 (0.8681) time: 4.6593 data: 4.6252 max mem: 8255 +Eval (hcp-val): [91] [61/62] eta: 0:00:00 loss: 0.8683 (0.8712) time: 0.1007 data: 0.0786 max mem: 8255 +Eval (hcp-val): [91] Total time: 0:00:13 (0.2183 s / it) +Averaged stats (hcp-val): loss: 0.8683 (0.8712) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +Train: [92] [ 0/6250] eta: 11:28:05 lr: 0.000002 grad: 0.2755 (0.2755) loss: 0.7889 (0.7889) time: 6.6057 data: 6.5173 max mem: 8255 +Train: [92] [ 100/6250] eta: 0:20:28 lr: 0.000002 grad: 0.1795 (0.1982) loss: 0.8449 (0.8423) time: 0.1379 data: 0.0480 max mem: 8255 +Train: [92] [ 200/6250] eta: 0:17:22 lr: 0.000002 grad: 0.1526 (0.1868) loss: 0.8360 (0.8409) time: 0.1451 data: 0.0644 max mem: 8255 +Train: [92] [ 300/6250] eta: 0:16:02 lr: 0.000002 grad: 0.1495 (0.1794) loss: 0.8504 (0.8408) time: 0.1197 data: 0.0397 max mem: 8255 +Train: [92] [ 400/6250] eta: 0:15:05 lr: 0.000002 grad: 0.1584 (0.1744) loss: 0.8465 (0.8423) time: 0.1452 data: 0.0567 max mem: 8255 +Train: [92] [ 500/6250] eta: 0:14:13 lr: 0.000002 grad: 0.1617 (0.1715) loss: 0.8408 (0.8421) time: 0.1203 data: 0.0424 max mem: 8255 +Train: [92] [ 600/6250] eta: 0:14:01 lr: 0.000002 grad: 0.1529 (0.1690) loss: 0.8409 (0.8420) time: 0.2252 data: 0.1417 max mem: 8255 +Train: [92] [ 700/6250] eta: 0:13:37 lr: 0.000002 grad: 0.1547 (0.1673) loss: 0.8426 (0.8417) time: 0.1528 data: 0.0790 max mem: 8255 +Train: [92] [ 800/6250] eta: 0:13:35 lr: 0.000002 grad: 0.1534 (0.1657) loss: 0.8412 (0.8417) time: 0.0943 data: 0.0095 max mem: 8255 +Train: [92] [ 900/6250] eta: 0:13:19 lr: 0.000002 grad: 0.1630 (0.1654) loss: 0.8464 (0.8417) time: 0.1419 data: 0.0534 max mem: 8255 +Train: [92] [1000/6250] eta: 0:12:59 lr: 0.000002 grad: 0.1603 (0.1649) loss: 0.8442 (0.8414) time: 0.1137 data: 0.0378 max mem: 8255 +Train: [92] [1100/6250] eta: 0:12:38 lr: 0.000002 grad: 0.1458 (0.1642) loss: 0.8404 (0.8412) time: 0.1186 data: 0.0476 max mem: 8255 +Train: [92] [1200/6250] eta: 0:12:17 lr: 0.000002 grad: 0.1404 (0.1630) loss: 0.8416 (0.8413) time: 0.1275 data: 0.0596 max mem: 8255 +Train: [92] [1300/6250] eta: 0:11:57 lr: 0.000002 grad: 0.1505 (0.1622) loss: 0.8400 (0.8413) time: 0.1223 data: 0.0523 max mem: 8255 +Train: [92] [1400/6250] eta: 0:11:38 lr: 0.000002 grad: 0.1516 (0.1615) loss: 0.8443 (0.8414) time: 0.1137 data: 0.0407 max mem: 8255 +Train: [92] [1500/6250] eta: 0:11:19 lr: 0.000002 grad: 0.1442 (0.1607) loss: 0.8426 (0.8413) time: 0.1232 data: 0.0506 max mem: 8255 +Train: [92] [1600/6250] eta: 0:11:04 lr: 0.000002 grad: 0.1449 (0.1602) loss: 0.8479 (0.8413) time: 0.1415 data: 0.0666 max mem: 8255 +Train: [92] [1700/6250] eta: 0:10:46 lr: 0.000002 grad: 0.1564 (0.1598) loss: 0.8338 (0.8411) time: 0.1654 data: 0.1010 max mem: 8255 +Train: [92] [1800/6250] eta: 0:10:30 lr: 0.000002 grad: 0.1527 (0.1596) loss: 0.8366 (0.8411) time: 0.0960 data: 0.0019 max mem: 8255 +Train: [92] [1900/6250] eta: 0:10:15 lr: 0.000002 grad: 0.1460 (0.1594) loss: 0.8364 (0.8409) time: 0.1636 data: 0.1004 max mem: 8255 +Train: [92] [2000/6250] eta: 0:09:59 lr: 0.000002 grad: 0.1596 (0.1591) loss: 0.8358 (0.8408) time: 0.1250 data: 0.0531 max mem: 8255 +Train: [92] [2100/6250] eta: 0:09:43 lr: 0.000002 grad: 0.1502 (0.1588) loss: 0.8424 (0.8408) time: 0.1126 data: 0.0433 max mem: 8255 +Train: [92] [2200/6250] eta: 0:09:27 lr: 0.000002 grad: 0.1561 (0.1587) loss: 0.8343 (0.8406) time: 0.1394 data: 0.0623 max mem: 8255 +Train: [92] [2300/6250] eta: 0:09:10 lr: 0.000002 grad: 0.1488 (0.1584) loss: 0.8361 (0.8405) time: 0.1261 data: 0.0572 max mem: 8255 +Train: [92] [2400/6250] eta: 0:09:01 lr: 0.000002 grad: 0.1476 (0.1582) loss: 0.8389 (0.8404) time: 0.2352 data: 0.1646 max mem: 8255 +Train: [92] [2500/6250] eta: 0:08:44 lr: 0.000002 grad: 0.1422 (0.1580) loss: 0.8433 (0.8403) time: 0.1310 data: 0.0582 max mem: 8255 +Train: [92] [2600/6250] eta: 0:08:29 lr: 0.000002 grad: 0.1445 (0.1578) loss: 0.8428 (0.8402) time: 0.1521 data: 0.0872 max mem: 8255 +Train: [92] [2700/6250] eta: 0:08:14 lr: 0.000002 grad: 0.1482 (0.1575) loss: 0.8340 (0.8400) time: 0.1276 data: 0.0565 max mem: 8255 +Train: [92] [2800/6250] eta: 0:07:57 lr: 0.000002 grad: 0.1414 (0.1572) loss: 0.8280 (0.8400) time: 0.1224 data: 0.0536 max mem: 8255 +Train: [92] [2900/6250] eta: 0:07:43 lr: 0.000002 grad: 0.1430 (0.1569) loss: 0.8372 (0.8399) time: 0.1251 data: 0.0520 max mem: 8255 +Train: [92] [3000/6250] eta: 0:07:29 lr: 0.000002 grad: 0.1439 (0.1567) loss: 0.8440 (0.8399) time: 0.1505 data: 0.0862 max mem: 8255 +Train: [92] [3100/6250] eta: 0:07:16 lr: 0.000002 grad: 0.1429 (0.1564) loss: 0.8427 (0.8399) time: 0.1827 data: 0.1199 max mem: 8255 +Train: [92] [3200/6250] eta: 0:07:03 lr: 0.000002 grad: 0.1443 (0.1562) loss: 0.8433 (0.8399) time: 0.1369 data: 0.0598 max mem: 8255 +Train: [92] [3300/6250] eta: 0:06:49 lr: 0.000002 grad: 0.1454 (0.1560) loss: 0.8339 (0.8399) time: 0.1507 data: 0.0838 max mem: 8255 +Train: [92] [3400/6250] eta: 0:06:40 lr: 0.000002 grad: 0.1448 (0.1558) loss: 0.8443 (0.8399) time: 0.1768 data: 0.0914 max mem: 8255 +Train: [92] [3500/6250] eta: 0:06:23 lr: 0.000002 grad: 0.1477 (0.1555) loss: 0.8411 (0.8400) time: 0.1190 data: 0.0526 max mem: 8255 +Train: [92] [3600/6250] eta: 0:06:09 lr: 0.000002 grad: 0.1486 (0.1554) loss: 0.8410 (0.8400) time: 0.1271 data: 0.0539 max mem: 8255 +Train: [92] [3700/6250] eta: 0:05:56 lr: 0.000002 grad: 0.1505 (0.1552) loss: 0.8392 (0.8401) time: 0.1264 data: 0.0504 max mem: 8255 +Train: [92] [3800/6250] eta: 0:05:42 lr: 0.000002 grad: 0.1342 (0.1549) loss: 0.8431 (0.8402) time: 0.1652 data: 0.0941 max mem: 8255 +Train: [92] [3900/6250] eta: 0:05:29 lr: 0.000002 grad: 0.1442 (0.1547) loss: 0.8424 (0.8404) time: 0.0897 data: 0.0009 max mem: 8255 +Train: [92] [4000/6250] eta: 0:05:14 lr: 0.000002 grad: 0.1470 (0.1545) loss: 0.8439 (0.8404) time: 0.1197 data: 0.0447 max mem: 8255 +Train: [92] [4100/6250] eta: 0:05:00 lr: 0.000002 grad: 0.1439 (0.1544) loss: 0.8461 (0.8404) time: 0.1284 data: 0.0559 max mem: 8255 +Train: [92] [4200/6250] eta: 0:04:47 lr: 0.000002 grad: 0.1440 (0.1542) loss: 0.8449 (0.8405) time: 0.1237 data: 0.0620 max mem: 8255 +Train: [92] [4300/6250] eta: 0:04:32 lr: 0.000002 grad: 0.1416 (0.1541) loss: 0.8439 (0.8406) time: 0.1430 data: 0.0800 max mem: 8255 +Train: [92] [4400/6250] eta: 0:04:19 lr: 0.000002 grad: 0.1369 (0.1540) loss: 0.8519 (0.8407) time: 0.1506 data: 0.0749 max mem: 8255 +Train: [92] [4500/6250] eta: 0:04:05 lr: 0.000002 grad: 0.1407 (0.1538) loss: 0.8408 (0.8407) time: 0.1553 data: 0.0892 max mem: 8255 +Train: [92] [4600/6250] eta: 0:03:52 lr: 0.000002 grad: 0.1500 (0.1536) loss: 0.8452 (0.8408) time: 0.1526 data: 0.0799 max mem: 8255 +Train: [92] [4700/6250] eta: 0:03:38 lr: 0.000002 grad: 0.1489 (0.1535) loss: 0.8388 (0.8408) time: 0.1394 data: 0.0653 max mem: 8255 +Train: [92] [4800/6250] eta: 0:03:24 lr: 0.000002 grad: 0.1408 (0.1534) loss: 0.8402 (0.8408) time: 0.1390 data: 0.0659 max mem: 8255 +Train: [92] [4900/6250] eta: 0:03:10 lr: 0.000002 grad: 0.1443 (0.1533) loss: 0.8472 (0.8409) time: 0.1354 data: 0.0553 max mem: 8255 +Train: [92] [5000/6250] eta: 0:02:55 lr: 0.000002 grad: 0.1431 (0.1531) loss: 0.8548 (0.8409) time: 0.1263 data: 0.0565 max mem: 8255 +Train: [92] [5100/6250] eta: 0:02:41 lr: 0.000002 grad: 0.1474 (0.1530) loss: 0.8411 (0.8410) time: 0.1516 data: 0.0658 max mem: 8255 +Train: [92] [5200/6250] eta: 0:02:28 lr: 0.000002 grad: 0.1488 (0.1529) loss: 0.8450 (0.8411) time: 0.1204 data: 0.0149 max mem: 8255 +Train: [92] [5300/6250] eta: 0:02:14 lr: 0.000002 grad: 0.1459 (0.1528) loss: 0.8442 (0.8410) time: 0.2525 data: 0.1529 max mem: 8255 +Train: [92] [5400/6250] eta: 0:02:00 lr: 0.000002 grad: 0.1456 (0.1527) loss: 0.8365 (0.8411) time: 0.1442 data: 0.0791 max mem: 8255 +Train: [92] [5500/6250] eta: 0:01:46 lr: 0.000002 grad: 0.1448 (0.1527) loss: 0.8427 (0.8411) time: 0.2144 data: 0.1408 max mem: 8255 +Train: [92] [5600/6250] eta: 0:01:32 lr: 0.000002 grad: 0.1443 (0.1527) loss: 0.8460 (0.8411) time: 0.1562 data: 0.0896 max mem: 8255 +Train: [92] [5700/6250] eta: 0:01:18 lr: 0.000002 grad: 0.1424 (0.1527) loss: 0.8389 (0.8411) time: 0.1430 data: 0.0823 max mem: 8255 +Train: [92] [5800/6250] eta: 0:01:03 lr: 0.000002 grad: 0.1399 (0.1527) loss: 0.8380 (0.8411) time: 0.1449 data: 0.0809 max mem: 8255 +Train: [92] [5900/6250] eta: 0:00:49 lr: 0.000002 grad: 0.1533 (0.1528) loss: 0.8359 (0.8411) time: 0.1246 data: 0.0557 max mem: 8255 +Train: [92] [6000/6250] eta: 0:00:35 lr: 0.000002 grad: 0.1470 (0.1528) loss: 0.8515 (0.8411) time: 0.1444 data: 0.0507 max mem: 8255 +Train: [92] [6100/6250] eta: 0:00:21 lr: 0.000002 grad: 0.1464 (0.1527) loss: 0.8491 (0.8412) time: 0.1385 data: 0.0733 max mem: 8255 +Train: [92] [6200/6250] eta: 0:00:07 lr: 0.000002 grad: 0.1400 (0.1526) loss: 0.8421 (0.8413) time: 0.1191 data: 0.0494 max mem: 8255 +Train: [92] [6249/6250] eta: 0:00:00 lr: 0.000002 grad: 0.1352 (0.1525) loss: 0.8418 (0.8413) time: 0.0969 data: 0.0263 max mem: 8255 +Train: [92] Total time: 0:14:49 (0.1424 s / it) +Averaged stats: lr: 0.000002 grad: 0.1352 (0.1525) loss: 0.8418 (0.8413) +Eval (hcp-train-subset): [92] [ 0/62] eta: 0:05:18 loss: 0.8526 (0.8526) time: 5.1383 data: 5.1012 max mem: 8255 +Eval (hcp-train-subset): [92] [61/62] eta: 0:00:00 loss: 0.8408 (0.8439) time: 0.1418 data: 0.1209 max mem: 8255 +Eval (hcp-train-subset): [92] Total time: 0:00:13 (0.2117 s / it) +Averaged stats (hcp-train-subset): loss: 0.8408 (0.8439) +Eval (hcp-val): [92] [ 0/62] eta: 0:05:50 loss: 0.8661 (0.8661) time: 5.6548 data: 5.6278 max mem: 8255 +Eval (hcp-val): [92] [61/62] eta: 0:00:00 loss: 0.8702 (0.8716) time: 0.1288 data: 0.1081 max mem: 8255 +Eval (hcp-val): [92] Total time: 0:00:13 (0.2161 s / it) +Averaged stats (hcp-val): loss: 0.8702 (0.8716) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +Train: [93] [ 0/6250] eta: 10:49:35 lr: 0.000002 grad: 0.2256 (0.2256) loss: 0.8346 (0.8346) time: 6.2362 data: 6.1059 max mem: 8255 +Train: [93] [ 100/6250] eta: 0:19:56 lr: 0.000002 grad: 0.2120 (0.2392) loss: 0.8463 (0.8444) time: 0.1475 data: 0.0575 max mem: 8255 +Train: [93] [ 200/6250] eta: 0:16:37 lr: 0.000002 grad: 0.1613 (0.2105) loss: 0.8467 (0.8446) time: 0.1514 data: 0.0701 max mem: 8255 +Train: [93] [ 300/6250] eta: 0:15:38 lr: 0.000002 grad: 0.1561 (0.1946) loss: 0.8465 (0.8457) time: 0.1147 data: 0.0301 max mem: 8255 +Train: [93] [ 400/6250] eta: 0:14:47 lr: 0.000002 grad: 0.1564 (0.1853) loss: 0.8425 (0.8468) time: 0.1216 data: 0.0479 max mem: 8255 +Train: [93] [ 500/6250] eta: 0:13:53 lr: 0.000002 grad: 0.1554 (0.1803) loss: 0.8442 (0.8466) time: 0.1202 data: 0.0414 max mem: 8255 +Train: [93] [ 600/6250] eta: 0:13:06 lr: 0.000002 grad: 0.1427 (0.1757) loss: 0.8412 (0.8464) time: 0.0931 data: 0.0125 max mem: 8255 +Train: [93] [ 700/6250] eta: 0:12:37 lr: 0.000002 grad: 0.1553 (0.1733) loss: 0.8498 (0.8460) time: 0.1277 data: 0.0517 max mem: 8255 +Train: [93] [ 800/6250] eta: 0:12:06 lr: 0.000002 grad: 0.1427 (0.1706) loss: 0.8448 (0.8460) time: 0.1272 data: 0.0459 max mem: 8255 +Train: [93] [ 900/6250] eta: 0:11:56 lr: 0.000002 grad: 0.1513 (0.1686) loss: 0.8436 (0.8462) time: 0.1596 data: 0.0783 max mem: 8255 +Train: [93] [1000/6250] eta: 0:11:45 lr: 0.000002 grad: 0.1495 (0.1664) loss: 0.8496 (0.8464) time: 0.1037 data: 0.0182 max mem: 8255 +Train: [93] [1100/6250] eta: 0:11:30 lr: 0.000002 grad: 0.1417 (0.1648) loss: 0.8505 (0.8465) time: 0.1129 data: 0.0371 max mem: 8255 +Train: [93] [1200/6250] eta: 0:11:15 lr: 0.000002 grad: 0.1504 (0.1638) loss: 0.8455 (0.8464) time: 0.1357 data: 0.0670 max mem: 8255 +Train: [93] [1300/6250] eta: 0:11:04 lr: 0.000002 grad: 0.1479 (0.1630) loss: 0.8516 (0.8463) time: 0.1365 data: 0.0632 max mem: 8255 +Train: [93] [1400/6250] eta: 0:10:52 lr: 0.000002 grad: 0.1513 (0.1624) loss: 0.8474 (0.8463) time: 0.1508 data: 0.0536 max mem: 8255 +Train: [93] [1500/6250] eta: 0:10:45 lr: 0.000002 grad: 0.1511 (0.1617) loss: 0.8440 (0.8462) time: 0.0959 data: 0.0003 max mem: 8255 +Train: [93] [1600/6250] eta: 0:10:32 lr: 0.000002 grad: 0.1519 (0.1611) loss: 0.8397 (0.8460) time: 0.1257 data: 0.0598 max mem: 8255 +Train: [93] [1700/6250] eta: 0:10:21 lr: 0.000002 grad: 0.1490 (0.1607) loss: 0.8523 (0.8459) time: 0.1582 data: 0.0721 max mem: 8255 +Train: [93] [1800/6250] eta: 0:10:18 lr: 0.000002 grad: 0.1469 (0.1601) loss: 0.8463 (0.8459) time: 0.2134 data: 0.1327 max mem: 8255 +Train: [93] [1900/6250] eta: 0:10:01 lr: 0.000002 grad: 0.1528 (0.1597) loss: 0.8448 (0.8459) time: 0.1537 data: 0.0948 max mem: 8255 +Train: [93] [2000/6250] eta: 0:09:48 lr: 0.000002 grad: 0.1490 (0.1594) loss: 0.8417 (0.8457) time: 0.1492 data: 0.0826 max mem: 8255 +Train: [93] [2100/6250] eta: 0:09:34 lr: 0.000002 grad: 0.1452 (0.1590) loss: 0.8492 (0.8457) time: 0.1318 data: 0.0519 max mem: 8255 +Train: [93] [2200/6250] eta: 0:09:19 lr: 0.000002 grad: 0.1520 (0.1587) loss: 0.8423 (0.8456) time: 0.1284 data: 0.0595 max mem: 8255 +Train: [93] [2300/6250] eta: 0:09:06 lr: 0.000001 grad: 0.1491 (0.1584) loss: 0.8443 (0.8456) time: 0.1384 data: 0.0567 max mem: 8255 +Train: [93] [2400/6250] eta: 0:08:52 lr: 0.000001 grad: 0.1450 (0.1582) loss: 0.8445 (0.8455) time: 0.1276 data: 0.0592 max mem: 8255 +Train: [93] [2500/6250] eta: 0:08:38 lr: 0.000001 grad: 0.1544 (0.1580) loss: 0.8362 (0.8453) time: 0.1448 data: 0.0679 max mem: 8255 +Train: [93] [2600/6250] eta: 0:08:23 lr: 0.000001 grad: 0.1566 (0.1581) loss: 0.8354 (0.8451) time: 0.1419 data: 0.0371 max mem: 8255 +Train: [93] [2700/6250] eta: 0:08:11 lr: 0.000001 grad: 0.1473 (0.1578) loss: 0.8437 (0.8448) time: 0.1441 data: 0.0716 max mem: 8255 +Train: [93] [2800/6250] eta: 0:07:55 lr: 0.000001 grad: 0.1535 (0.1577) loss: 0.8427 (0.8447) time: 0.1288 data: 0.0502 max mem: 8255 +Train: [93] [2900/6250] eta: 0:07:41 lr: 0.000001 grad: 0.1500 (0.1576) loss: 0.8443 (0.8444) time: 0.1344 data: 0.0568 max mem: 8255 +Train: [93] [3000/6250] eta: 0:07:27 lr: 0.000001 grad: 0.1484 (0.1576) loss: 0.8337 (0.8441) time: 0.1389 data: 0.0690 max mem: 8255 +Train: [93] [3100/6250] eta: 0:07:13 lr: 0.000001 grad: 0.1444 (0.1575) loss: 0.8397 (0.8440) time: 0.1395 data: 0.0616 max mem: 8255 +Train: [93] [3200/6250] eta: 0:06:58 lr: 0.000001 grad: 0.1517 (0.1574) loss: 0.8459 (0.8439) time: 0.1274 data: 0.0573 max mem: 8255 +Train: [93] [3300/6250] eta: 0:06:45 lr: 0.000001 grad: 0.1551 (0.1575) loss: 0.8368 (0.8437) time: 0.0966 data: 0.0012 max mem: 8255 +Train: [93] [3400/6250] eta: 0:06:32 lr: 0.000001 grad: 0.1417 (0.1573) loss: 0.8444 (0.8436) time: 0.1561 data: 0.0821 max mem: 8255 +Train: [93] [3500/6250] eta: 0:06:19 lr: 0.000001 grad: 0.1486 (0.1571) loss: 0.8410 (0.8436) time: 0.1412 data: 0.0591 max mem: 8255 +Train: [93] [3600/6250] eta: 0:06:05 lr: 0.000001 grad: 0.1533 (0.1569) loss: 0.8410 (0.8434) time: 0.1415 data: 0.0632 max mem: 8255 +Train: [93] [3700/6250] eta: 0:05:51 lr: 0.000001 grad: 0.1524 (0.1569) loss: 0.8292 (0.8432) time: 0.1587 data: 0.0797 max mem: 8255 +Train: [93] [3800/6250] eta: 0:05:37 lr: 0.000001 grad: 0.1464 (0.1567) loss: 0.8423 (0.8430) time: 0.1477 data: 0.0721 max mem: 8255 +Train: [93] [3900/6250] eta: 0:05:23 lr: 0.000001 grad: 0.1422 (0.1566) loss: 0.8413 (0.8429) time: 0.1415 data: 0.0633 max mem: 8255 +Train: [93] [4000/6250] eta: 0:05:09 lr: 0.000001 grad: 0.1410 (0.1563) loss: 0.8408 (0.8429) time: 0.1293 data: 0.0588 max mem: 8255 +Train: [93] [4100/6250] eta: 0:04:55 lr: 0.000001 grad: 0.1476 (0.1562) loss: 0.8377 (0.8428) time: 0.1384 data: 0.0732 max mem: 8255 +Train: [93] [4200/6250] eta: 0:04:42 lr: 0.000001 grad: 0.1513 (0.1560) loss: 0.8374 (0.8428) time: 0.1396 data: 0.0715 max mem: 8255 +Train: [93] [4300/6250] eta: 0:04:29 lr: 0.000001 grad: 0.1402 (0.1558) loss: 0.8387 (0.8427) time: 0.1583 data: 0.0861 max mem: 8255 +Train: [93] [4400/6250] eta: 0:04:15 lr: 0.000001 grad: 0.1418 (0.1556) loss: 0.8383 (0.8427) time: 0.1822 data: 0.1075 max mem: 8255 +Train: [93] [4500/6250] eta: 0:04:02 lr: 0.000001 grad: 0.1533 (0.1555) loss: 0.8401 (0.8426) time: 0.1209 data: 0.0521 max mem: 8255 +Train: [93] [4600/6250] eta: 0:03:48 lr: 0.000001 grad: 0.1421 (0.1555) loss: 0.8421 (0.8425) time: 0.1459 data: 0.0711 max mem: 8255 +Train: [93] [4700/6250] eta: 0:03:34 lr: 0.000001 grad: 0.1603 (0.1555) loss: 0.8348 (0.8424) time: 0.1536 data: 0.0798 max mem: 8255 +Train: [93] [4800/6250] eta: 0:03:20 lr: 0.000001 grad: 0.1513 (0.1556) loss: 0.8315 (0.8423) time: 0.1445 data: 0.0704 max mem: 8255 +Train: [93] [4900/6250] eta: 0:03:06 lr: 0.000001 grad: 0.1543 (0.1557) loss: 0.8318 (0.8422) time: 0.1436 data: 0.0677 max mem: 8255 +Train: [93] [5000/6250] eta: 0:02:52 lr: 0.000001 grad: 0.1575 (0.1558) loss: 0.8402 (0.8420) time: 0.1418 data: 0.0719 max mem: 8255 +Train: [93] [5100/6250] eta: 0:02:38 lr: 0.000001 grad: 0.1577 (0.1559) loss: 0.8281 (0.8419) time: 0.1164 data: 0.0425 max mem: 8255 +Train: [93] [5200/6250] eta: 0:02:24 lr: 0.000001 grad: 0.1454 (0.1559) loss: 0.8436 (0.8418) time: 0.1248 data: 0.0459 max mem: 8255 +Train: [93] [5300/6250] eta: 0:02:10 lr: 0.000001 grad: 0.1549 (0.1558) loss: 0.8410 (0.8418) time: 0.1103 data: 0.0304 max mem: 8255 +Train: [93] [5400/6250] eta: 0:01:56 lr: 0.000001 grad: 0.1485 (0.1558) loss: 0.8417 (0.8417) time: 0.1195 data: 0.0406 max mem: 8255 +Train: [93] [5500/6250] eta: 0:01:42 lr: 0.000001 grad: 0.1526 (0.1558) loss: 0.8383 (0.8417) time: 0.1333 data: 0.0569 max mem: 8255 +Train: [93] [5600/6250] eta: 0:01:28 lr: 0.000001 grad: 0.1474 (0.1558) loss: 0.8422 (0.8416) time: 0.1210 data: 0.0516 max mem: 8255 +Train: [93] [5700/6250] eta: 0:01:14 lr: 0.000001 grad: 0.1405 (0.1557) loss: 0.8400 (0.8415) time: 0.1365 data: 0.0610 max mem: 8255 +Train: [93] [5800/6250] eta: 0:01:01 lr: 0.000001 grad: 0.1474 (0.1557) loss: 0.8352 (0.8415) time: 0.0945 data: 0.0002 max mem: 8255 +Train: [93] [5900/6250] eta: 0:00:47 lr: 0.000001 grad: 0.1561 (0.1557) loss: 0.8357 (0.8415) time: 0.1323 data: 0.0639 max mem: 8255 +Train: [93] [6000/6250] eta: 0:00:34 lr: 0.000001 grad: 0.1537 (0.1556) loss: 0.8255 (0.8414) time: 0.1412 data: 0.0687 max mem: 8255 +Train: [93] [6100/6250] eta: 0:00:20 lr: 0.000001 grad: 0.1488 (0.1556) loss: 0.8319 (0.8413) time: 0.0951 data: 0.0103 max mem: 8255 +Train: [93] [6200/6250] eta: 0:00:06 lr: 0.000001 grad: 0.1512 (0.1557) loss: 0.8420 (0.8413) time: 0.1672 data: 0.0752 max mem: 8255 +Train: [93] [6249/6250] eta: 0:00:00 lr: 0.000001 grad: 0.1536 (0.1557) loss: 0.8295 (0.8412) time: 0.1579 data: 0.0402 max mem: 8255 +Train: [93] Total time: 0:14:21 (0.1379 s / it) +Averaged stats: lr: 0.000001 grad: 0.1536 (0.1557) loss: 0.8295 (0.8412) +Eval (hcp-train-subset): [93] [ 0/62] eta: 0:04:49 loss: 0.8498 (0.8498) time: 4.6678 data: 4.6030 max mem: 8255 +Eval (hcp-train-subset): [93] [61/62] eta: 0:00:00 loss: 0.8415 (0.8430) time: 0.1128 data: 0.0923 max mem: 8255 +Eval (hcp-train-subset): [93] Total time: 0:00:13 (0.2143 s / it) +Averaged stats (hcp-train-subset): loss: 0.8415 (0.8430) +Eval (hcp-val): [93] [ 0/62] eta: 0:05:43 loss: 0.8663 (0.8663) time: 5.5347 data: 5.5099 max mem: 8255 +Eval (hcp-val): [93] [61/62] eta: 0:00:00 loss: 0.8702 (0.8713) time: 0.1078 data: 0.0867 max mem: 8255 +Eval (hcp-val): [93] Total time: 0:00:13 (0.2233 s / it) +Averaged stats (hcp-val): loss: 0.8702 (0.8713) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +Train: [94] [ 0/6250] eta: 8:49:25 lr: 0.000001 grad: 0.1223 (0.1223) loss: 0.8982 (0.8982) time: 5.0825 data: 4.8370 max mem: 8255 +Train: [94] [ 100/6250] eta: 0:20:38 lr: 0.000001 grad: 0.1763 (0.1758) loss: 0.8292 (0.8553) time: 0.1417 data: 0.0366 max mem: 8255 +Train: [94] [ 200/6250] eta: 0:17:48 lr: 0.000001 grad: 0.1545 (0.1772) loss: 0.8550 (0.8482) time: 0.1646 data: 0.0732 max mem: 8255 +Train: [94] [ 300/6250] eta: 0:16:17 lr: 0.000001 grad: 0.1616 (0.1687) loss: 0.8543 (0.8488) time: 0.1366 data: 0.0316 max mem: 8255 +Train: [94] [ 400/6250] eta: 0:15:18 lr: 0.000001 grad: 0.1496 (0.1661) loss: 0.8456 (0.8479) time: 0.1226 data: 0.0268 max mem: 8255 +Train: [94] [ 500/6250] eta: 0:14:43 lr: 0.000001 grad: 0.1638 (0.1653) loss: 0.8398 (0.8467) time: 0.1571 data: 0.0785 max mem: 8255 +Train: [94] [ 600/6250] eta: 0:14:01 lr: 0.000001 grad: 0.1600 (0.1636) loss: 0.8400 (0.8460) time: 0.1276 data: 0.0454 max mem: 8255 +Train: [94] [ 700/6250] eta: 0:13:32 lr: 0.000001 grad: 0.1667 (0.1638) loss: 0.8353 (0.8448) time: 0.1378 data: 0.0668 max mem: 8255 +Train: [94] [ 800/6250] eta: 0:13:22 lr: 0.000001 grad: 0.1627 (0.1643) loss: 0.8352 (0.8441) time: 0.1675 data: 0.0621 max mem: 8255 +Train: [94] [ 900/6250] eta: 0:13:06 lr: 0.000001 grad: 0.1710 (0.1644) loss: 0.8348 (0.8435) time: 0.1420 data: 0.0691 max mem: 8255 +Train: [94] [1000/6250] eta: 0:13:00 lr: 0.000001 grad: 0.1527 (0.1641) loss: 0.8488 (0.8435) time: 0.1513 data: 0.0698 max mem: 8255 +Train: [94] [1100/6250] eta: 0:12:47 lr: 0.000001 grad: 0.1548 (0.1634) loss: 0.8398 (0.8432) time: 0.1285 data: 0.0536 max mem: 8255 +Train: [94] [1200/6250] eta: 0:12:52 lr: 0.000001 grad: 0.1531 (0.1629) loss: 0.8378 (0.8431) time: 0.3195 data: 0.2438 max mem: 8255 +Train: [94] [1300/6250] eta: 0:12:31 lr: 0.000001 grad: 0.1491 (0.1626) loss: 0.8450 (0.8427) time: 0.1843 data: 0.1108 max mem: 8255 +Train: [94] [1400/6250] eta: 0:12:19 lr: 0.000001 grad: 0.1560 (0.1624) loss: 0.8443 (0.8423) time: 0.1708 data: 0.0959 max mem: 8255 +Train: [94] [1500/6250] eta: 0:12:07 lr: 0.000001 grad: 0.1449 (0.1623) loss: 0.8475 (0.8423) time: 0.2287 data: 0.1618 max mem: 8255 +Train: [94] [1600/6250] eta: 0:11:52 lr: 0.000001 grad: 0.1524 (0.1620) loss: 0.8432 (0.8422) time: 0.1352 data: 0.0683 max mem: 8255 +Train: [94] [1700/6250] eta: 0:11:37 lr: 0.000001 grad: 0.1473 (0.1618) loss: 0.8409 (0.8421) time: 0.1712 data: 0.1054 max mem: 8255 +Train: [94] [1800/6250] eta: 0:11:23 lr: 0.000001 grad: 0.1572 (0.1616) loss: 0.8369 (0.8420) time: 0.1555 data: 0.0833 max mem: 8255 +Train: [94] [1900/6250] eta: 0:11:11 lr: 0.000001 grad: 0.1517 (0.1615) loss: 0.8426 (0.8420) time: 0.1991 data: 0.1333 max mem: 8255 +Train: [94] [2000/6250] eta: 0:10:52 lr: 0.000001 grad: 0.1481 (0.1614) loss: 0.8484 (0.8422) time: 0.1298 data: 0.0527 max mem: 8255 +Train: [94] [2100/6250] eta: 0:10:36 lr: 0.000001 grad: 0.1545 (0.1614) loss: 0.8377 (0.8422) time: 0.1511 data: 0.0787 max mem: 8255 +Train: [94] [2200/6250] eta: 0:10:18 lr: 0.000001 grad: 0.1567 (0.1614) loss: 0.8353 (0.8421) time: 0.1515 data: 0.0764 max mem: 8255 +Train: [94] [2300/6250] eta: 0:10:01 lr: 0.000001 grad: 0.1435 (0.1614) loss: 0.8457 (0.8421) time: 0.1637 data: 0.0780 max mem: 8255 +Train: [94] [2400/6250] eta: 0:09:44 lr: 0.000001 grad: 0.1518 (0.1614) loss: 0.8403 (0.8420) time: 0.1428 data: 0.0713 max mem: 8255 +Train: [94] [2500/6250] eta: 0:09:27 lr: 0.000001 grad: 0.1599 (0.1614) loss: 0.8428 (0.8420) time: 0.1298 data: 0.0531 max mem: 8255 +Train: [94] [2600/6250] eta: 0:09:11 lr: 0.000001 grad: 0.1545 (0.1613) loss: 0.8434 (0.8420) time: 0.1597 data: 0.0698 max mem: 8255 +Train: [94] [2700/6250] eta: 0:08:54 lr: 0.000001 grad: 0.1497 (0.1612) loss: 0.8434 (0.8420) time: 0.1286 data: 0.0511 max mem: 8255 +Train: [94] [2800/6250] eta: 0:08:39 lr: 0.000001 grad: 0.1400 (0.1610) loss: 0.8478 (0.8420) time: 0.1786 data: 0.1030 max mem: 8255 +Train: [94] [2900/6250] eta: 0:08:28 lr: 0.000001 grad: 0.1470 (0.1607) loss: 0.8454 (0.8422) time: 0.1004 data: 0.0004 max mem: 8255 +Train: [94] [3000/6250] eta: 0:08:11 lr: 0.000001 grad: 0.1463 (0.1604) loss: 0.8428 (0.8423) time: 0.1348 data: 0.0548 max mem: 8255 +Train: [94] [3100/6250] eta: 0:07:53 lr: 0.000001 grad: 0.1445 (0.1601) loss: 0.8472 (0.8424) time: 0.1295 data: 0.0495 max mem: 8255 +Train: [94] [3200/6250] eta: 0:07:38 lr: 0.000001 grad: 0.1422 (0.1600) loss: 0.8407 (0.8424) time: 0.1699 data: 0.0976 max mem: 8255 +Train: [94] [3300/6250] eta: 0:07:25 lr: 0.000001 grad: 0.1504 (0.1597) loss: 0.8509 (0.8425) time: 0.0962 data: 0.0011 max mem: 8255 +Train: [94] [3400/6250] eta: 0:07:08 lr: 0.000001 grad: 0.1521 (0.1595) loss: 0.8466 (0.8426) time: 0.1261 data: 0.0528 max mem: 8255 +Train: [94] [3500/6250] eta: 0:06:51 lr: 0.000001 grad: 0.1399 (0.1594) loss: 0.8452 (0.8427) time: 0.1188 data: 0.0475 max mem: 8255 +Train: [94] [3600/6250] eta: 0:06:34 lr: 0.000001 grad: 0.1550 (0.1592) loss: 0.8484 (0.8428) time: 0.1287 data: 0.0376 max mem: 8255 +Train: [94] [3700/6250] eta: 0:06:19 lr: 0.000001 grad: 0.1554 (0.1591) loss: 0.8507 (0.8429) time: 0.1259 data: 0.0517 max mem: 8255 +Train: [94] [3800/6250] eta: 0:06:04 lr: 0.000001 grad: 0.1520 (0.1590) loss: 0.8438 (0.8429) time: 0.1289 data: 0.0619 max mem: 8255 +Train: [94] [3900/6250] eta: 0:05:51 lr: 0.000001 grad: 0.1476 (0.1589) loss: 0.8509 (0.8430) time: 0.4264 data: 0.2961 max mem: 8255 +Train: [94] [4000/6250] eta: 0:05:34 lr: 0.000001 grad: 0.1472 (0.1588) loss: 0.8483 (0.8431) time: 0.1513 data: 0.0918 max mem: 8255 +Train: [94] [4100/6250] eta: 0:05:19 lr: 0.000001 grad: 0.1641 (0.1588) loss: 0.8427 (0.8432) time: 0.1435 data: 0.0720 max mem: 8255 +Train: [94] [4200/6250] eta: 0:05:04 lr: 0.000001 grad: 0.1508 (0.1588) loss: 0.8493 (0.8433) time: 0.1411 data: 0.0723 max mem: 8255 +Train: [94] [4300/6250] eta: 0:04:48 lr: 0.000001 grad: 0.1527 (0.1588) loss: 0.8440 (0.8433) time: 0.1118 data: 0.0366 max mem: 8255 +Train: [94] [4400/6250] eta: 0:04:33 lr: 0.000001 grad: 0.1544 (0.1589) loss: 0.8410 (0.8433) time: 0.1281 data: 0.0550 max mem: 8255 +Train: [94] [4500/6250] eta: 0:04:18 lr: 0.000001 grad: 0.1524 (0.1590) loss: 0.8421 (0.8432) time: 0.1420 data: 0.0698 max mem: 8255 +Train: [94] [4600/6250] eta: 0:04:02 lr: 0.000001 grad: 0.1569 (0.1589) loss: 0.8389 (0.8432) time: 0.1286 data: 0.0564 max mem: 8255 +Train: [94] [4700/6250] eta: 0:03:47 lr: 0.000001 grad: 0.1526 (0.1589) loss: 0.8369 (0.8432) time: 0.1597 data: 0.0837 max mem: 8255 +Train: [94] [4800/6250] eta: 0:03:33 lr: 0.000001 grad: 0.1417 (0.1588) loss: 0.8421 (0.8433) time: 0.1513 data: 0.0742 max mem: 8255 +Train: [94] [4900/6250] eta: 0:03:18 lr: 0.000001 grad: 0.1535 (0.1586) loss: 0.8346 (0.8433) time: 0.1394 data: 0.0672 max mem: 8255 +Train: [94] [5000/6250] eta: 0:03:03 lr: 0.000001 grad: 0.1495 (0.1586) loss: 0.8421 (0.8433) time: 0.1286 data: 0.0510 max mem: 8255 +Train: [94] [5100/6250] eta: 0:02:48 lr: 0.000001 grad: 0.1468 (0.1584) loss: 0.8516 (0.8434) time: 0.1385 data: 0.0606 max mem: 8255 +Train: [94] [5200/6250] eta: 0:02:33 lr: 0.000001 grad: 0.1432 (0.1583) loss: 0.8566 (0.8435) time: 0.1304 data: 0.0613 max mem: 8255 +Train: [94] [5300/6250] eta: 0:02:18 lr: 0.000001 grad: 0.1516 (0.1582) loss: 0.8491 (0.8437) time: 0.1181 data: 0.0481 max mem: 8255 +Train: [94] [5400/6250] eta: 0:02:03 lr: 0.000001 grad: 0.1540 (0.1581) loss: 0.8451 (0.8437) time: 0.1207 data: 0.0428 max mem: 8255 +Train: [94] [5500/6250] eta: 0:01:48 lr: 0.000001 grad: 0.1514 (0.1580) loss: 0.8426 (0.8438) time: 0.1209 data: 0.0466 max mem: 8255 +Train: [94] [5600/6250] eta: 0:01:33 lr: 0.000001 grad: 0.1494 (0.1580) loss: 0.8495 (0.8438) time: 0.1127 data: 0.0354 max mem: 8255 +Train: [94] [5700/6250] eta: 0:01:19 lr: 0.000001 grad: 0.1489 (0.1579) loss: 0.8450 (0.8439) time: 0.1177 data: 0.0351 max mem: 8255 +Train: [94] [5800/6250] eta: 0:01:04 lr: 0.000001 grad: 0.1528 (0.1579) loss: 0.8367 (0.8439) time: 0.0935 data: 0.0183 max mem: 8255 +Train: [94] [5900/6250] eta: 0:00:50 lr: 0.000001 grad: 0.1496 (0.1579) loss: 0.8458 (0.8439) time: 0.1430 data: 0.0681 max mem: 8255 +Train: [94] [6000/6250] eta: 0:00:35 lr: 0.000001 grad: 0.1618 (0.1580) loss: 0.8443 (0.8439) time: 0.1840 data: 0.1090 max mem: 8255 +Train: [94] [6100/6250] eta: 0:00:21 lr: 0.000001 grad: 0.1551 (0.1580) loss: 0.8446 (0.8438) time: 0.1205 data: 0.0514 max mem: 8255 +Train: [94] [6200/6250] eta: 0:00:07 lr: 0.000001 grad: 0.1536 (0.1580) loss: 0.8387 (0.8438) time: 0.2406 data: 0.1711 max mem: 8255 +Train: [94] [6249/6250] eta: 0:00:00 lr: 0.000001 grad: 0.1570 (0.1581) loss: 0.8402 (0.8438) time: 0.1240 data: 0.0523 max mem: 8255 +Train: [94] Total time: 0:14:58 (0.1438 s / it) +Averaged stats: lr: 0.000001 grad: 0.1570 (0.1581) loss: 0.8402 (0.8438) +Eval (hcp-train-subset): [94] [ 0/62] eta: 0:04:02 loss: 0.8502 (0.8502) time: 3.9070 data: 3.8389 max mem: 8255 +Eval (hcp-train-subset): [94] [61/62] eta: 0:00:00 loss: 0.8402 (0.8431) time: 0.1171 data: 0.0968 max mem: 8255 +Eval (hcp-train-subset): [94] Total time: 0:00:12 (0.2030 s / it) +Averaged stats (hcp-train-subset): loss: 0.8402 (0.8431) +Making plots (hcp-train-subset): example=2 +Eval (hcp-val): [94] [ 0/62] eta: 0:03:43 loss: 0.8667 (0.8667) time: 3.6032 data: 3.4977 max mem: 8255 +Eval (hcp-val): [94] [61/62] eta: 0:00:00 loss: 0.8691 (0.8708) time: 0.1113 data: 0.0893 max mem: 8255 +Eval (hcp-val): [94] Total time: 0:00:13 (0.2159 s / it) +Averaged stats (hcp-val): loss: 0.8691 (0.8708) +Making plots (hcp-val): example=53 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +Train: [95] [ 0/6250] eta: 8:40:38 lr: 0.000001 grad: 0.0889 (0.0889) loss: 0.9134 (0.9134) time: 4.9982 data: 4.7039 max mem: 8255 +Train: [95] [ 100/6250] eta: 0:21:31 lr: 0.000001 grad: 0.1989 (0.2127) loss: 0.8526 (0.8446) time: 0.1626 data: 0.0580 max mem: 8255 +Train: [95] [ 200/6250] eta: 0:18:28 lr: 0.000001 grad: 0.1746 (0.1948) loss: 0.8455 (0.8438) time: 0.1654 data: 0.0780 max mem: 8255 +Train: [95] [ 300/6250] eta: 0:16:53 lr: 0.000001 grad: 0.1785 (0.1933) loss: 0.8407 (0.8422) time: 0.1441 data: 0.0551 max mem: 8255 +Train: [95] [ 400/6250] eta: 0:15:44 lr: 0.000001 grad: 0.1813 (0.1884) loss: 0.8366 (0.8427) time: 0.1461 data: 0.0672 max mem: 8255 +Train: [95] [ 500/6250] eta: 0:15:35 lr: 0.000001 grad: 0.1705 (0.1851) loss: 0.8337 (0.8423) time: 0.1567 data: 0.0514 max mem: 8255 +Train: [95] [ 600/6250] eta: 0:14:48 lr: 0.000001 grad: 0.1483 (0.1827) loss: 0.8479 (0.8420) time: 0.1369 data: 0.0549 max mem: 8255 +Train: [95] [ 700/6250] eta: 0:14:40 lr: 0.000001 grad: 0.1492 (0.1803) loss: 0.8470 (0.8421) time: 0.1664 data: 0.0816 max mem: 8255 +Train: [95] [ 800/6250] eta: 0:14:21 lr: 0.000001 grad: 0.1558 (0.1780) loss: 0.8381 (0.8422) time: 0.1191 data: 0.0350 max mem: 8255 +Train: [95] [ 900/6250] eta: 0:13:53 lr: 0.000001 grad: 0.1453 (0.1761) loss: 0.8465 (0.8425) time: 0.1178 data: 0.0311 max mem: 8255 +Train: [95] [1000/6250] eta: 0:13:24 lr: 0.000001 grad: 0.1466 (0.1747) loss: 0.8468 (0.8426) time: 0.1390 data: 0.0606 max mem: 8255 +Train: [95] [1100/6250] eta: 0:13:07 lr: 0.000001 grad: 0.1420 (0.1729) loss: 0.8480 (0.8428) time: 0.1494 data: 0.0820 max mem: 8255 +Train: [95] [1200/6250] eta: 0:12:37 lr: 0.000001 grad: 0.1564 (0.1717) loss: 0.8422 (0.8430) time: 0.1079 data: 0.0375 max mem: 8255 +Train: [95] [1300/6250] eta: 0:12:17 lr: 0.000001 grad: 0.1508 (0.1709) loss: 0.8432 (0.8427) time: 0.1411 data: 0.0636 max mem: 8255 +Train: [95] [1400/6250] eta: 0:12:02 lr: 0.000001 grad: 0.1455 (0.1696) loss: 0.8465 (0.8427) time: 0.1027 data: 0.0223 max mem: 8255 +Train: [95] [1500/6250] eta: 0:11:42 lr: 0.000001 grad: 0.1542 (0.1689) loss: 0.8444 (0.8427) time: 0.1343 data: 0.0639 max mem: 8255 +Train: [95] [1600/6250] eta: 0:11:19 lr: 0.000001 grad: 0.1529 (0.1683) loss: 0.8414 (0.8425) time: 0.1358 data: 0.0589 max mem: 8255 +Train: [95] [1700/6250] eta: 0:11:11 lr: 0.000001 grad: 0.1488 (0.1675) loss: 0.8478 (0.8426) time: 0.2162 data: 0.1528 max mem: 8255 +Train: [95] [1800/6250] eta: 0:10:50 lr: 0.000001 grad: 0.1622 (0.1669) loss: 0.8386 (0.8427) time: 0.1390 data: 0.0683 max mem: 8255 +Train: [95] [1900/6250] eta: 0:10:34 lr: 0.000001 grad: 0.1530 (0.1665) loss: 0.8363 (0.8426) time: 0.1112 data: 0.0372 max mem: 8255 +Train: [95] [2000/6250] eta: 0:10:17 lr: 0.000001 grad: 0.1560 (0.1664) loss: 0.8421 (0.8425) time: 0.1317 data: 0.0581 max mem: 8255 +Train: [95] [2100/6250] eta: 0:10:03 lr: 0.000001 grad: 0.1585 (0.1663) loss: 0.8476 (0.8425) time: 0.1074 data: 0.0265 max mem: 8255 +Train: [95] [2200/6250] eta: 0:09:44 lr: 0.000001 grad: 0.1554 (0.1660) loss: 0.8399 (0.8424) time: 0.1445 data: 0.0713 max mem: 8255 +Train: [95] [2300/6250] eta: 0:09:28 lr: 0.000001 grad: 0.1621 (0.1659) loss: 0.8427 (0.8424) time: 0.1549 data: 0.0811 max mem: 8255 +Train: [95] [2400/6250] eta: 0:09:13 lr: 0.000001 grad: 0.1649 (0.1660) loss: 0.8363 (0.8422) time: 0.1376 data: 0.0649 max mem: 8255 +Train: [95] [2500/6250] eta: 0:09:00 lr: 0.000001 grad: 0.1647 (0.1660) loss: 0.8393 (0.8422) time: 0.0976 data: 0.0310 max mem: 8255 +Train: [95] [2600/6250] eta: 0:08:44 lr: 0.000001 grad: 0.1649 (0.1661) loss: 0.8472 (0.8420) time: 0.1456 data: 0.0683 max mem: 8255 +Train: [95] [2700/6250] eta: 0:08:30 lr: 0.000001 grad: 0.1623 (0.1662) loss: 0.8429 (0.8419) time: 0.0956 data: 0.0157 max mem: 8255 +Train: [95] [2800/6250] eta: 0:08:18 lr: 0.000001 grad: 0.1670 (0.1661) loss: 0.8344 (0.8417) time: 0.1837 data: 0.1148 max mem: 8255 +Train: [95] [2900/6250] eta: 0:08:02 lr: 0.000001 grad: 0.1602 (0.1662) loss: 0.8435 (0.8415) time: 0.1290 data: 0.0600 max mem: 8255 +Train: [95] [3000/6250] eta: 0:07:49 lr: 0.000001 grad: 0.1645 (0.1662) loss: 0.8349 (0.8413) time: 0.1004 data: 0.0296 max mem: 8255 +Train: [95] [3100/6250] eta: 0:07:34 lr: 0.000001 grad: 0.1630 (0.1663) loss: 0.8454 (0.8411) time: 0.1918 data: 0.1195 max mem: 8255 +Train: [95] [3200/6250] eta: 0:07:20 lr: 0.000001 grad: 0.1553 (0.1663) loss: 0.8411 (0.8410) time: 0.1638 data: 0.0935 max mem: 8255 +Train: [95] [3300/6250] eta: 0:07:06 lr: 0.000001 grad: 0.1571 (0.1662) loss: 0.8354 (0.8408) time: 0.1539 data: 0.0879 max mem: 8255 +Train: [95] [3400/6250] eta: 0:06:51 lr: 0.000001 grad: 0.1503 (0.1659) loss: 0.8367 (0.8407) time: 0.1498 data: 0.0837 max mem: 8255 +Train: [95] [3500/6250] eta: 0:06:37 lr: 0.000001 grad: 0.1656 (0.1658) loss: 0.8363 (0.8407) time: 0.1349 data: 0.0671 max mem: 8255 +Train: [95] [3600/6250] eta: 0:06:22 lr: 0.000001 grad: 0.1595 (0.1656) loss: 0.8380 (0.8406) time: 0.1068 data: 0.0318 max mem: 8255 +Train: [95] [3700/6250] eta: 0:06:08 lr: 0.000001 grad: 0.1476 (0.1653) loss: 0.8425 (0.8405) time: 0.1804 data: 0.1057 max mem: 8255 +Train: [95] [3800/6250] eta: 0:05:54 lr: 0.000001 grad: 0.1586 (0.1652) loss: 0.8403 (0.8404) time: 0.1144 data: 0.0284 max mem: 8255 +Train: [95] [3900/6250] eta: 0:05:39 lr: 0.000001 grad: 0.1527 (0.1651) loss: 0.8372 (0.8404) time: 0.1298 data: 0.0619 max mem: 8255 +Train: [95] [4000/6250] eta: 0:05:24 lr: 0.000001 grad: 0.1537 (0.1651) loss: 0.8449 (0.8404) time: 0.1367 data: 0.0545 max mem: 8255 +Train: [95] [4100/6250] eta: 0:05:09 lr: 0.000001 grad: 0.1534 (0.1652) loss: 0.8415 (0.8404) time: 0.1412 data: 0.0696 max mem: 8255 +Train: [95] [4200/6250] eta: 0:04:55 lr: 0.000001 grad: 0.1460 (0.1650) loss: 0.8445 (0.8405) time: 0.1544 data: 0.0793 max mem: 8255 +Train: [95] [4300/6250] eta: 0:04:42 lr: 0.000001 grad: 0.1550 (0.1649) loss: 0.8395 (0.8405) time: 0.0857 data: 0.0002 max mem: 8255 +Train: [95] [4400/6250] eta: 0:04:27 lr: 0.000001 grad: 0.1605 (0.1648) loss: 0.8429 (0.8405) time: 0.2164 data: 0.1229 max mem: 8255 +Train: [95] [4500/6250] eta: 0:04:13 lr: 0.000001 grad: 0.1568 (0.1647) loss: 0.8401 (0.8405) time: 0.0876 data: 0.0002 max mem: 8255 +Train: [95] [4600/6250] eta: 0:03:58 lr: 0.000001 grad: 0.1550 (0.1645) loss: 0.8449 (0.8406) time: 0.1397 data: 0.0700 max mem: 8255 +Train: [95] [4700/6250] eta: 0:03:43 lr: 0.000001 grad: 0.1595 (0.1645) loss: 0.8457 (0.8406) time: 0.1369 data: 0.0600 max mem: 8255 +Train: [95] [4800/6250] eta: 0:03:28 lr: 0.000001 grad: 0.1543 (0.1644) loss: 0.8347 (0.8405) time: 0.1439 data: 0.0735 max mem: 8255 +Train: [95] [4900/6250] eta: 0:03:14 lr: 0.000001 grad: 0.1646 (0.1643) loss: 0.8402 (0.8405) time: 0.1451 data: 0.0657 max mem: 8255 +Train: [95] [5000/6250] eta: 0:03:00 lr: 0.000001 grad: 0.1546 (0.1643) loss: 0.8402 (0.8405) time: 0.1176 data: 0.0381 max mem: 8255 +Train: [95] [5100/6250] eta: 0:02:45 lr: 0.000001 grad: 0.1633 (0.1643) loss: 0.8386 (0.8404) time: 0.1326 data: 0.0700 max mem: 8255 +Train: [95] [5200/6250] eta: 0:02:31 lr: 0.000001 grad: 0.1561 (0.1643) loss: 0.8361 (0.8403) time: 0.1610 data: 0.0951 max mem: 8255 +Train: [95] [5300/6250] eta: 0:02:16 lr: 0.000001 grad: 0.1508 (0.1642) loss: 0.8383 (0.8403) time: 0.1476 data: 0.0753 max mem: 8255 +Train: [95] [5400/6250] eta: 0:02:02 lr: 0.000001 grad: 0.1627 (0.1641) loss: 0.8400 (0.8402) time: 0.1456 data: 0.0668 max mem: 8255 +Train: [95] [5500/6250] eta: 0:01:48 lr: 0.000001 grad: 0.1548 (0.1641) loss: 0.8409 (0.8402) time: 0.1345 data: 0.0547 max mem: 8255 +Train: [95] [5600/6250] eta: 0:01:33 lr: 0.000001 grad: 0.1572 (0.1640) loss: 0.8419 (0.8402) time: 0.1292 data: 0.0577 max mem: 8255 +Train: [95] [5700/6250] eta: 0:01:18 lr: 0.000001 grad: 0.1592 (0.1640) loss: 0.8312 (0.8401) time: 0.1337 data: 0.0545 max mem: 8255 +Train: [95] [5800/6250] eta: 0:01:04 lr: 0.000001 grad: 0.1523 (0.1639) loss: 0.8429 (0.8401) time: 0.1289 data: 0.0571 max mem: 8255 +Train: [95] [5900/6250] eta: 0:00:50 lr: 0.000001 grad: 0.1540 (0.1639) loss: 0.8392 (0.8401) time: 0.1384 data: 0.0655 max mem: 8255 +Train: [95] [6000/6250] eta: 0:00:35 lr: 0.000001 grad: 0.1499 (0.1638) loss: 0.8437 (0.8401) time: 0.1214 data: 0.0459 max mem: 8255 +Train: [95] [6100/6250] eta: 0:00:21 lr: 0.000001 grad: 0.1554 (0.1638) loss: 0.8413 (0.8401) time: 0.0943 data: 0.0002 max mem: 8255 +Train: [95] [6200/6250] eta: 0:00:07 lr: 0.000001 grad: 0.1514 (0.1637) loss: 0.8451 (0.8402) time: 0.1730 data: 0.1035 max mem: 8255 +Train: [95] [6249/6250] eta: 0:00:00 lr: 0.000001 grad: 0.1559 (0.1637) loss: 0.8384 (0.8402) time: 0.1660 data: 0.1023 max mem: 8255 +Train: [95] Total time: 0:15:01 (0.1443 s / it) +Averaged stats: lr: 0.000001 grad: 0.1559 (0.1637) loss: 0.8384 (0.8402) +Eval (hcp-train-subset): [95] [ 0/62] eta: 0:03:59 loss: 0.8527 (0.8527) time: 3.8699 data: 3.8101 max mem: 8255 +Eval (hcp-train-subset): [95] [61/62] eta: 0:00:00 loss: 0.8381 (0.8428) time: 0.1263 data: 0.1055 max mem: 8255 +Eval (hcp-train-subset): [95] Total time: 0:00:13 (0.2172 s / it) +Averaged stats (hcp-train-subset): loss: 0.8381 (0.8428) +Eval (hcp-val): [95] [ 0/62] eta: 0:03:44 loss: 0.8697 (0.8697) time: 3.6210 data: 3.5276 max mem: 8255 +Eval (hcp-val): [95] [61/62] eta: 0:00:00 loss: 0.8700 (0.8712) time: 0.1305 data: 0.1095 max mem: 8255 +Eval (hcp-val): [95] Total time: 0:00:13 (0.2119 s / it) +Averaged stats (hcp-val): loss: 0.8700 (0.8712) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +Train: [96] [ 0/6250] eta: 8:46:31 lr: 0.000001 grad: 0.2333 (0.2333) loss: 0.7969 (0.7969) time: 5.0547 data: 4.7542 max mem: 8255 +Train: [96] [ 100/6250] eta: 0:19:53 lr: 0.000001 grad: 0.1873 (0.2185) loss: 0.8546 (0.8446) time: 0.1367 data: 0.0535 max mem: 8255 +Train: [96] [ 200/6250] eta: 0:16:08 lr: 0.000001 grad: 0.1861 (0.2031) loss: 0.8442 (0.8462) time: 0.1258 data: 0.0259 max mem: 8255 +Train: [96] [ 300/6250] eta: 0:14:48 lr: 0.000001 grad: 0.1672 (0.1962) loss: 0.8473 (0.8457) time: 0.1212 data: 0.0319 max mem: 8255 +Train: [96] [ 400/6250] eta: 0:13:54 lr: 0.000001 grad: 0.1560 (0.1903) loss: 0.8476 (0.8460) time: 0.1374 data: 0.0486 max mem: 8255 +Train: [96] [ 500/6250] eta: 0:13:15 lr: 0.000001 grad: 0.1566 (0.1877) loss: 0.8414 (0.8448) time: 0.1251 data: 0.0465 max mem: 8255 +Train: [96] [ 600/6250] eta: 0:12:49 lr: 0.000001 grad: 0.1641 (0.1842) loss: 0.8363 (0.8438) time: 0.1243 data: 0.0501 max mem: 8255 +Train: [96] [ 700/6250] eta: 0:12:54 lr: 0.000001 grad: 0.1491 (0.1818) loss: 0.8501 (0.8434) time: 0.2535 data: 0.1671 max mem: 8255 +Train: [96] [ 800/6250] eta: 0:12:31 lr: 0.000001 grad: 0.1562 (0.1799) loss: 0.8396 (0.8429) time: 0.1453 data: 0.0662 max mem: 8255 +Train: [96] [ 900/6250] eta: 0:12:39 lr: 0.000001 grad: 0.1751 (0.1785) loss: 0.8328 (0.8428) time: 0.1004 data: 0.0133 max mem: 8255 +Train: [96] [1000/6250] eta: 0:12:38 lr: 0.000001 grad: 0.1551 (0.1773) loss: 0.8429 (0.8427) time: 0.1476 data: 0.0730 max mem: 8255 +Train: [96] [1100/6250] eta: 0:12:28 lr: 0.000000 grad: 0.1589 (0.1756) loss: 0.8443 (0.8426) time: 0.1535 data: 0.0820 max mem: 8255 +Train: [96] [1200/6250] eta: 0:12:16 lr: 0.000000 grad: 0.1644 (0.1742) loss: 0.8398 (0.8426) time: 0.1098 data: 0.0355 max mem: 8255 +Train: [96] [1300/6250] eta: 0:11:57 lr: 0.000000 grad: 0.1536 (0.1733) loss: 0.8477 (0.8427) time: 0.1456 data: 0.0773 max mem: 8255 +Train: [96] [1400/6250] eta: 0:11:40 lr: 0.000000 grad: 0.1573 (0.1725) loss: 0.8462 (0.8429) time: 0.1376 data: 0.0606 max mem: 8255 +Train: [96] [1500/6250] eta: 0:11:25 lr: 0.000000 grad: 0.1568 (0.1717) loss: 0.8459 (0.8431) time: 0.1399 data: 0.0583 max mem: 8255 +Train: [96] [1600/6250] eta: 0:11:11 lr: 0.000000 grad: 0.1491 (0.1711) loss: 0.8391 (0.8432) time: 0.1641 data: 0.0700 max mem: 8255 +Train: [96] [1700/6250] eta: 0:11:00 lr: 0.000000 grad: 0.1491 (0.1705) loss: 0.8510 (0.8432) time: 0.1936 data: 0.1119 max mem: 8255 +Train: [96] [1800/6250] eta: 0:10:45 lr: 0.000000 grad: 0.1435 (0.1697) loss: 0.8423 (0.8432) time: 0.1612 data: 0.0902 max mem: 8255 +Train: [96] [1900/6250] eta: 0:10:31 lr: 0.000000 grad: 0.1426 (0.1692) loss: 0.8515 (0.8431) time: 0.1271 data: 0.0447 max mem: 8255 +Train: [96] [2000/6250] eta: 0:10:15 lr: 0.000000 grad: 0.1540 (0.1686) loss: 0.8447 (0.8430) time: 0.1446 data: 0.0687 max mem: 8255 +Train: [96] [2100/6250] eta: 0:10:01 lr: 0.000000 grad: 0.1586 (0.1682) loss: 0.8423 (0.8430) time: 0.1145 data: 0.0200 max mem: 8255 +Train: [96] [2200/6250] eta: 0:09:48 lr: 0.000000 grad: 0.1602 (0.1678) loss: 0.8397 (0.8430) time: 0.0839 data: 0.0071 max mem: 8255 +Train: [96] [2300/6250] eta: 0:09:32 lr: 0.000000 grad: 0.1596 (0.1675) loss: 0.8441 (0.8430) time: 0.0973 data: 0.0151 max mem: 8255 +Train: [96] [2400/6250] eta: 0:09:15 lr: 0.000000 grad: 0.1474 (0.1671) loss: 0.8507 (0.8430) time: 0.1398 data: 0.0652 max mem: 8255 +Train: [96] [2500/6250] eta: 0:09:02 lr: 0.000000 grad: 0.1552 (0.1665) loss: 0.8410 (0.8431) time: 0.1175 data: 0.0248 max mem: 8255 +Train: [96] [2600/6250] eta: 0:08:46 lr: 0.000000 grad: 0.1566 (0.1663) loss: 0.8415 (0.8430) time: 0.1270 data: 0.0565 max mem: 8255 +Train: [96] [2700/6250] eta: 0:08:33 lr: 0.000000 grad: 0.1596 (0.1661) loss: 0.8470 (0.8430) time: 0.1467 data: 0.0666 max mem: 8255 +Train: [96] [2800/6250] eta: 0:08:17 lr: 0.000000 grad: 0.1565 (0.1661) loss: 0.8437 (0.8428) time: 0.0875 data: 0.0056 max mem: 8255 +Train: [96] [2900/6250] eta: 0:08:00 lr: 0.000000 grad: 0.1450 (0.1660) loss: 0.8425 (0.8427) time: 0.1275 data: 0.0567 max mem: 8255 +Train: [96] [3000/6250] eta: 0:07:44 lr: 0.000000 grad: 0.1615 (0.1658) loss: 0.8352 (0.8426) time: 0.1110 data: 0.0449 max mem: 8255 +Train: [96] [3100/6250] eta: 0:07:31 lr: 0.000000 grad: 0.1540 (0.1656) loss: 0.8427 (0.8425) time: 0.1085 data: 0.0388 max mem: 8255 +Train: [96] [3200/6250] eta: 0:07:15 lr: 0.000000 grad: 0.1503 (0.1654) loss: 0.8487 (0.8425) time: 0.1231 data: 0.0398 max mem: 8255 +Train: [96] [3300/6250] eta: 0:07:00 lr: 0.000000 grad: 0.1553 (0.1654) loss: 0.8414 (0.8424) time: 0.1295 data: 0.0625 max mem: 8255 +Train: [96] [3400/6250] eta: 0:06:43 lr: 0.000000 grad: 0.1555 (0.1652) loss: 0.8456 (0.8424) time: 0.1132 data: 0.0410 max mem: 8255 +Train: [96] [3500/6250] eta: 0:06:29 lr: 0.000000 grad: 0.1493 (0.1650) loss: 0.8454 (0.8425) time: 0.1350 data: 0.0694 max mem: 8255 +Train: [96] [3600/6250] eta: 0:06:14 lr: 0.000000 grad: 0.1494 (0.1647) loss: 0.8425 (0.8425) time: 0.1037 data: 0.0367 max mem: 8255 +Train: [96] [3700/6250] eta: 0:05:59 lr: 0.000000 grad: 0.1446 (0.1644) loss: 0.8475 (0.8426) time: 0.1511 data: 0.0755 max mem: 8255 +Train: [96] [3800/6250] eta: 0:05:45 lr: 0.000000 grad: 0.1477 (0.1643) loss: 0.8460 (0.8427) time: 0.1511 data: 0.0901 max mem: 8255 +Train: [96] [3900/6250] eta: 0:05:32 lr: 0.000000 grad: 0.1491 (0.1641) loss: 0.8415 (0.8428) time: 0.1611 data: 0.1007 max mem: 8255 +Train: [96] [4000/6250] eta: 0:05:18 lr: 0.000000 grad: 0.1540 (0.1639) loss: 0.8407 (0.8429) time: 0.1026 data: 0.0310 max mem: 8255 +Train: [96] [4100/6250] eta: 0:05:04 lr: 0.000000 grad: 0.1532 (0.1637) loss: 0.8455 (0.8429) time: 0.1002 data: 0.0322 max mem: 8255 +Train: [96] [4200/6250] eta: 0:04:50 lr: 0.000000 grad: 0.1427 (0.1635) loss: 0.8463 (0.8429) time: 0.1526 data: 0.0849 max mem: 8255 +Train: [96] [4300/6250] eta: 0:04:36 lr: 0.000000 grad: 0.1502 (0.1634) loss: 0.8412 (0.8430) time: 0.1462 data: 0.0778 max mem: 8255 +Train: [96] [4400/6250] eta: 0:04:22 lr: 0.000000 grad: 0.1595 (0.1632) loss: 0.8479 (0.8430) time: 0.1065 data: 0.0295 max mem: 8255 +Train: [96] [4500/6250] eta: 0:04:08 lr: 0.000000 grad: 0.1506 (0.1631) loss: 0.8426 (0.8430) time: 0.1111 data: 0.0396 max mem: 8255 +Train: [96] [4600/6250] eta: 0:03:53 lr: 0.000000 grad: 0.1501 (0.1631) loss: 0.8427 (0.8430) time: 0.1378 data: 0.0678 max mem: 8255 +Train: [96] [4700/6250] eta: 0:03:39 lr: 0.000000 grad: 0.1481 (0.1630) loss: 0.8413 (0.8430) time: 0.1189 data: 0.0503 max mem: 8255 +Train: [96] [4800/6250] eta: 0:03:24 lr: 0.000000 grad: 0.1536 (0.1629) loss: 0.8471 (0.8430) time: 0.1257 data: 0.0563 max mem: 8255 +Train: [96] [4900/6250] eta: 0:03:10 lr: 0.000000 grad: 0.1464 (0.1628) loss: 0.8402 (0.8430) time: 0.1269 data: 0.0501 max mem: 8255 +Train: [96] [5000/6250] eta: 0:02:56 lr: 0.000000 grad: 0.1467 (0.1627) loss: 0.8392 (0.8430) time: 0.0887 data: 0.0002 max mem: 8255 +Train: [96] [5100/6250] eta: 0:02:42 lr: 0.000000 grad: 0.1551 (0.1627) loss: 0.8439 (0.8429) time: 0.1415 data: 0.0727 max mem: 8255 +Train: [96] [5200/6250] eta: 0:02:28 lr: 0.000000 grad: 0.1511 (0.1626) loss: 0.8425 (0.8429) time: 0.1889 data: 0.1130 max mem: 8255 +Train: [96] [5300/6250] eta: 0:02:14 lr: 0.000000 grad: 0.1535 (0.1626) loss: 0.8458 (0.8428) time: 0.1532 data: 0.0732 max mem: 8255 +Train: [96] [5400/6250] eta: 0:02:00 lr: 0.000000 grad: 0.1500 (0.1626) loss: 0.8402 (0.8428) time: 0.1410 data: 0.0745 max mem: 8255 +Train: [96] [5500/6250] eta: 0:01:46 lr: 0.000000 grad: 0.1628 (0.1626) loss: 0.8347 (0.8427) time: 0.1495 data: 0.0752 max mem: 8255 +Train: [96] [5600/6250] eta: 0:01:32 lr: 0.000000 grad: 0.1617 (0.1625) loss: 0.8332 (0.8427) time: 0.1434 data: 0.0699 max mem: 8255 +Train: [96] [5700/6250] eta: 0:01:18 lr: 0.000000 grad: 0.1556 (0.1624) loss: 0.8473 (0.8426) time: 0.1495 data: 0.0741 max mem: 8255 +Train: [96] [5800/6250] eta: 0:01:04 lr: 0.000000 grad: 0.1602 (0.1624) loss: 0.8313 (0.8425) time: 0.1581 data: 0.0823 max mem: 8255 +Train: [96] [5900/6250] eta: 0:00:49 lr: 0.000000 grad: 0.1498 (0.1623) loss: 0.8444 (0.8424) time: 0.1309 data: 0.0602 max mem: 8255 +Train: [96] [6000/6250] eta: 0:00:35 lr: 0.000000 grad: 0.1560 (0.1623) loss: 0.8369 (0.8423) time: 0.1416 data: 0.0721 max mem: 8255 +Train: [96] [6100/6250] eta: 0:00:21 lr: 0.000000 grad: 0.1554 (0.1623) loss: 0.8393 (0.8423) time: 0.1485 data: 0.0818 max mem: 8255 +Train: [96] [6200/6250] eta: 0:00:07 lr: 0.000000 grad: 0.1489 (0.1622) loss: 0.8303 (0.8422) time: 0.1202 data: 0.0552 max mem: 8255 +Train: [96] [6249/6250] eta: 0:00:00 lr: 0.000000 grad: 0.1445 (0.1622) loss: 0.8369 (0.8422) time: 0.1411 data: 0.0483 max mem: 8255 +Train: [96] Total time: 0:14:49 (0.1423 s / it) +Averaged stats: lr: 0.000000 grad: 0.1445 (0.1622) loss: 0.8369 (0.8422) +Eval (hcp-train-subset): [96] [ 0/62] eta: 0:03:50 loss: 0.8500 (0.8500) time: 3.7099 data: 3.6517 max mem: 8255 +Eval (hcp-train-subset): [96] [61/62] eta: 0:00:00 loss: 0.8369 (0.8427) time: 0.1161 data: 0.0943 max mem: 8255 +Eval (hcp-train-subset): [96] Total time: 0:00:13 (0.2107 s / it) +Averaged stats (hcp-train-subset): loss: 0.8369 (0.8427) +Eval (hcp-val): [96] [ 0/62] eta: 0:03:45 loss: 0.8664 (0.8664) time: 3.6384 data: 3.5524 max mem: 8255 +Eval (hcp-val): [96] [61/62] eta: 0:00:00 loss: 0.8698 (0.8708) time: 0.1216 data: 0.1008 max mem: 8255 +Eval (hcp-val): [96] Total time: 0:00:12 (0.2018 s / it) +Averaged stats (hcp-val): loss: 0.8698 (0.8708) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +Train: [97] [ 0/6250] eta: 9:58:18 lr: 0.000000 grad: 0.1611 (0.1611) loss: 0.8615 (0.8615) time: 5.7438 data: 5.6489 max mem: 8255 +Train: [97] [ 100/6250] eta: 0:20:03 lr: 0.000000 grad: 0.1771 (0.1878) loss: 0.8552 (0.8590) time: 0.1485 data: 0.0543 max mem: 8255 +Train: [97] [ 200/6250] eta: 0:16:58 lr: 0.000000 grad: 0.1616 (0.1830) loss: 0.8442 (0.8552) time: 0.1377 data: 0.0490 max mem: 8255 +Train: [97] [ 300/6250] eta: 0:15:28 lr: 0.000000 grad: 0.1734 (0.1833) loss: 0.8413 (0.8513) time: 0.1334 data: 0.0427 max mem: 8255 +Train: [97] [ 400/6250] eta: 0:14:28 lr: 0.000000 grad: 0.1790 (0.1815) loss: 0.8397 (0.8485) time: 0.1434 data: 0.0541 max mem: 8255 +Train: [97] [ 500/6250] eta: 0:13:43 lr: 0.000000 grad: 0.1672 (0.1802) loss: 0.8481 (0.8474) time: 0.1347 data: 0.0492 max mem: 8255 +Train: [97] [ 600/6250] eta: 0:13:14 lr: 0.000000 grad: 0.1701 (0.1787) loss: 0.8402 (0.8464) time: 0.1378 data: 0.0460 max mem: 8255 +Train: [97] [ 700/6250] eta: 0:13:07 lr: 0.000000 grad: 0.1658 (0.1785) loss: 0.8423 (0.8453) time: 0.1437 data: 0.0700 max mem: 8255 +Train: [97] [ 800/6250] eta: 0:12:49 lr: 0.000000 grad: 0.1712 (0.1778) loss: 0.8344 (0.8445) time: 0.1238 data: 0.0394 max mem: 8255 +Train: [97] [ 900/6250] eta: 0:12:52 lr: 0.000000 grad: 0.1676 (0.1775) loss: 0.8366 (0.8436) time: 0.2543 data: 0.1726 max mem: 8255 +Train: [97] [1000/6250] eta: 0:12:42 lr: 0.000000 grad: 0.1668 (0.1766) loss: 0.8412 (0.8432) time: 0.1746 data: 0.1078 max mem: 8255 +Train: [97] [1100/6250] eta: 0:12:35 lr: 0.000000 grad: 0.1616 (0.1761) loss: 0.8355 (0.8427) time: 0.1361 data: 0.0506 max mem: 8255 +Train: [97] [1200/6250] eta: 0:12:31 lr: 0.000000 grad: 0.1567 (0.1758) loss: 0.8396 (0.8423) time: 0.1531 data: 0.0704 max mem: 8255 +Train: [97] [1300/6250] eta: 0:12:19 lr: 0.000000 grad: 0.1628 (0.1753) loss: 0.8444 (0.8422) time: 0.1683 data: 0.0958 max mem: 8255 +Train: [97] [1400/6250] eta: 0:12:06 lr: 0.000000 grad: 0.1612 (0.1747) loss: 0.8372 (0.8421) time: 0.1588 data: 0.0865 max mem: 8255 +Train: [97] [1500/6250] eta: 0:11:52 lr: 0.000000 grad: 0.1518 (0.1742) loss: 0.8376 (0.8419) time: 0.1567 data: 0.0725 max mem: 8255 +Train: [97] [1600/6250] eta: 0:11:32 lr: 0.000000 grad: 0.1596 (0.1737) loss: 0.8408 (0.8418) time: 0.1426 data: 0.0731 max mem: 8255 +Train: [97] [1700/6250] eta: 0:11:15 lr: 0.000000 grad: 0.1535 (0.1731) loss: 0.8405 (0.8417) time: 0.1607 data: 0.0891 max mem: 8255 +Train: [97] [1800/6250] eta: 0:10:55 lr: 0.000000 grad: 0.1634 (0.1726) loss: 0.8398 (0.8417) time: 0.1457 data: 0.0705 max mem: 8255 +Train: [97] [1900/6250] eta: 0:10:36 lr: 0.000000 grad: 0.1605 (0.1722) loss: 0.8329 (0.8416) time: 0.1409 data: 0.0645 max mem: 8255 +Train: [97] [2000/6250] eta: 0:10:20 lr: 0.000000 grad: 0.1639 (0.1721) loss: 0.8453 (0.8415) time: 0.0866 data: 0.0044 max mem: 8255 +Train: [97] [2100/6250] eta: 0:10:04 lr: 0.000000 grad: 0.1623 (0.1717) loss: 0.8434 (0.8415) time: 0.0937 data: 0.0190 max mem: 8255 +Train: [97] [2200/6250] eta: 0:09:49 lr: 0.000000 grad: 0.1640 (0.1715) loss: 0.8476 (0.8415) time: 0.2054 data: 0.1393 max mem: 8255 +Train: [97] [2300/6250] eta: 0:09:29 lr: 0.000000 grad: 0.1649 (0.1712) loss: 0.8402 (0.8415) time: 0.1275 data: 0.0593 max mem: 8255 +Train: [97] [2400/6250] eta: 0:09:12 lr: 0.000000 grad: 0.1588 (0.1708) loss: 0.8403 (0.8415) time: 0.1249 data: 0.0413 max mem: 8255 +Train: [97] [2500/6250] eta: 0:08:56 lr: 0.000000 grad: 0.1447 (0.1705) loss: 0.8535 (0.8416) time: 0.1236 data: 0.0449 max mem: 8255 +Train: [97] [2600/6250] eta: 0:08:41 lr: 0.000000 grad: 0.1591 (0.1701) loss: 0.8495 (0.8419) time: 0.1233 data: 0.0501 max mem: 8255 +Train: [97] [2700/6250] eta: 0:08:27 lr: 0.000000 grad: 0.1612 (0.1697) loss: 0.8411 (0.8420) time: 0.1573 data: 0.0813 max mem: 8255 +Train: [97] [2800/6250] eta: 0:08:11 lr: 0.000000 grad: 0.1545 (0.1694) loss: 0.8491 (0.8421) time: 0.1304 data: 0.0562 max mem: 8255 +Train: [97] [2900/6250] eta: 0:07:56 lr: 0.000000 grad: 0.1515 (0.1689) loss: 0.8476 (0.8424) time: 0.1164 data: 0.0511 max mem: 8255 +Train: [97] [3000/6250] eta: 0:07:42 lr: 0.000000 grad: 0.1531 (0.1687) loss: 0.8494 (0.8426) time: 0.1287 data: 0.0569 max mem: 8255 +Train: [97] [3100/6250] eta: 0:07:29 lr: 0.000000 grad: 0.1605 (0.1685) loss: 0.8505 (0.8427) time: 0.1181 data: 0.0421 max mem: 8255 +Train: [97] [3200/6250] eta: 0:07:14 lr: 0.000000 grad: 0.1637 (0.1682) loss: 0.8375 (0.8428) time: 0.1475 data: 0.0715 max mem: 8255 +Train: [97] [3300/6250] eta: 0:07:02 lr: 0.000000 grad: 0.1557 (0.1681) loss: 0.8394 (0.8428) time: 0.1783 data: 0.1102 max mem: 8255 +Train: [97] [3400/6250] eta: 0:06:46 lr: 0.000000 grad: 0.1580 (0.1678) loss: 0.8478 (0.8430) time: 0.1091 data: 0.0502 max mem: 8255 +Train: [97] [3500/6250] eta: 0:06:32 lr: 0.000000 grad: 0.1494 (0.1675) loss: 0.8526 (0.8432) time: 0.1162 data: 0.0448 max mem: 8255 +Train: [97] [3600/6250] eta: 0:06:18 lr: 0.000000 grad: 0.1577 (0.1672) loss: 0.8515 (0.8432) time: 0.1581 data: 0.0949 max mem: 8255 +Train: [97] [3700/6250] eta: 0:06:04 lr: 0.000000 grad: 0.1414 (0.1668) loss: 0.8442 (0.8434) time: 0.1374 data: 0.0727 max mem: 8255 +Train: [97] [3800/6250] eta: 0:05:50 lr: 0.000000 grad: 0.1574 (0.1665) loss: 0.8500 (0.8434) time: 0.0875 data: 0.0074 max mem: 8255 +Train: [97] [3900/6250] eta: 0:05:35 lr: 0.000000 grad: 0.1447 (0.1662) loss: 0.8463 (0.8435) time: 0.1342 data: 0.0656 max mem: 8255 +Train: [97] [4000/6250] eta: 0:05:21 lr: 0.000000 grad: 0.1494 (0.1659) loss: 0.8490 (0.8435) time: 0.1461 data: 0.0338 max mem: 8255 +Train: [97] [4100/6250] eta: 0:05:06 lr: 0.000000 grad: 0.1589 (0.1657) loss: 0.8428 (0.8435) time: 0.1216 data: 0.0484 max mem: 8255 +Train: [97] [4200/6250] eta: 0:04:52 lr: 0.000000 grad: 0.1474 (0.1654) loss: 0.8383 (0.8436) time: 0.1074 data: 0.0366 max mem: 8255 +Train: [97] [4300/6250] eta: 0:04:39 lr: 0.000000 grad: 0.1386 (0.1652) loss: 0.8485 (0.8436) time: 0.1980 data: 0.1243 max mem: 8255 +Train: [97] [4400/6250] eta: 0:04:24 lr: 0.000000 grad: 0.1549 (0.1650) loss: 0.8394 (0.8436) time: 0.1274 data: 0.0526 max mem: 8255 +Train: [97] [4500/6250] eta: 0:04:09 lr: 0.000000 grad: 0.1485 (0.1649) loss: 0.8400 (0.8435) time: 0.1403 data: 0.0587 max mem: 8255 +Train: [97] [4600/6250] eta: 0:03:54 lr: 0.000000 grad: 0.1582 (0.1648) loss: 0.8419 (0.8435) time: 0.0973 data: 0.0068 max mem: 8255 +Train: [97] [4700/6250] eta: 0:03:40 lr: 0.000000 grad: 0.1645 (0.1647) loss: 0.8431 (0.8435) time: 0.1120 data: 0.0411 max mem: 8255 +Train: [97] [4800/6250] eta: 0:03:25 lr: 0.000000 grad: 0.1510 (0.1646) loss: 0.8448 (0.8434) time: 0.0980 data: 0.0239 max mem: 8255 +Train: [97] [4900/6250] eta: 0:03:11 lr: 0.000000 grad: 0.1582 (0.1645) loss: 0.8384 (0.8434) time: 0.1456 data: 0.0747 max mem: 8255 +Train: [97] [5000/6250] eta: 0:02:57 lr: 0.000000 grad: 0.1521 (0.1645) loss: 0.8434 (0.8433) time: 0.1369 data: 0.0665 max mem: 8255 +Train: [97] [5100/6250] eta: 0:02:43 lr: 0.000000 grad: 0.1546 (0.1643) loss: 0.8347 (0.8433) time: 0.1327 data: 0.0647 max mem: 8255 +Train: [97] [5200/6250] eta: 0:02:29 lr: 0.000000 grad: 0.1599 (0.1643) loss: 0.8363 (0.8432) time: 0.1036 data: 0.0343 max mem: 8255 +Train: [97] [5300/6250] eta: 0:02:15 lr: 0.000000 grad: 0.1474 (0.1641) loss: 0.8449 (0.8432) time: 0.1460 data: 0.0774 max mem: 8255 +Train: [97] [5400/6250] eta: 0:02:01 lr: 0.000000 grad: 0.1545 (0.1640) loss: 0.8459 (0.8432) time: 0.1173 data: 0.0378 max mem: 8255 +Train: [97] [5500/6250] eta: 0:01:46 lr: 0.000000 grad: 0.1540 (0.1639) loss: 0.8476 (0.8432) time: 0.1594 data: 0.0941 max mem: 8255 +Train: [97] [5600/6250] eta: 0:01:32 lr: 0.000000 grad: 0.1579 (0.1639) loss: 0.8405 (0.8432) time: 0.1420 data: 0.0766 max mem: 8255 +Train: [97] [5700/6250] eta: 0:01:18 lr: 0.000000 grad: 0.1474 (0.1638) loss: 0.8511 (0.8432) time: 0.1407 data: 0.0683 max mem: 8255 +Train: [97] [5800/6250] eta: 0:01:04 lr: 0.000000 grad: 0.1550 (0.1636) loss: 0.8419 (0.8433) time: 0.1296 data: 0.0552 max mem: 8255 +Train: [97] [5900/6250] eta: 0:00:49 lr: 0.000000 grad: 0.1522 (0.1636) loss: 0.8462 (0.8433) time: 0.1328 data: 0.0487 max mem: 8255 +Train: [97] [6000/6250] eta: 0:00:35 lr: 0.000000 grad: 0.1518 (0.1635) loss: 0.8487 (0.8434) time: 0.1417 data: 0.0590 max mem: 8255 +Train: [97] [6100/6250] eta: 0:00:21 lr: 0.000000 grad: 0.1549 (0.1633) loss: 0.8508 (0.8435) time: 0.1265 data: 0.0439 max mem: 8255 +Train: [97] [6200/6250] eta: 0:00:07 lr: 0.000000 grad: 0.1449 (0.1632) loss: 0.8495 (0.8435) time: 0.1218 data: 0.0457 max mem: 8255 +Train: [97] [6249/6250] eta: 0:00:00 lr: 0.000000 grad: 0.1434 (0.1632) loss: 0.8505 (0.8436) time: 0.1228 data: 0.0379 max mem: 8255 +Train: [97] Total time: 0:14:56 (0.1434 s / it) +Averaged stats: lr: 0.000000 grad: 0.1434 (0.1632) loss: 0.8505 (0.8436) +Eval (hcp-train-subset): [97] [ 0/62] eta: 0:06:06 loss: 0.8504 (0.8504) time: 5.9036 data: 5.8774 max mem: 8255 +Eval (hcp-train-subset): [97] [61/62] eta: 0:00:00 loss: 0.8368 (0.8424) time: 0.1346 data: 0.1139 max mem: 8255 +Eval (hcp-train-subset): [97] Total time: 0:00:14 (0.2344 s / it) +Averaged stats (hcp-train-subset): loss: 0.8368 (0.8424) +Eval (hcp-val): [97] [ 0/62] eta: 0:05:21 loss: 0.8654 (0.8654) time: 5.1823 data: 5.0925 max mem: 8255 +Eval (hcp-val): [97] [61/62] eta: 0:00:00 loss: 0.8689 (0.8701) time: 0.1255 data: 0.1039 max mem: 8255 +Eval (hcp-val): [97] Total time: 0:00:14 (0.2356 s / it) +Averaged stats (hcp-val): loss: 0.8689 (0.8701) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +Train: [98] [ 0/6250] eta: 8:57:30 lr: 0.000000 grad: 0.0873 (0.0873) loss: 0.9110 (0.9110) time: 5.1601 data: 4.8814 max mem: 8255 +Train: [98] [ 100/6250] eta: 0:21:54 lr: 0.000000 grad: 0.1919 (0.1948) loss: 0.8410 (0.8522) time: 0.1508 data: 0.0513 max mem: 8255 +Train: [98] [ 200/6250] eta: 0:18:10 lr: 0.000000 grad: 0.1634 (0.1917) loss: 0.8383 (0.8500) time: 0.1285 data: 0.0371 max mem: 8255 +Train: [98] [ 300/6250] eta: 0:16:25 lr: 0.000000 grad: 0.1746 (0.1872) loss: 0.8439 (0.8493) time: 0.1162 data: 0.0196 max mem: 8255 +Train: [98] [ 400/6250] eta: 0:15:39 lr: 0.000000 grad: 0.1792 (0.1843) loss: 0.8329 (0.8471) time: 0.1328 data: 0.0392 max mem: 8255 +Train: [98] [ 500/6250] eta: 0:15:02 lr: 0.000000 grad: 0.1638 (0.1822) loss: 0.8366 (0.8447) time: 0.1492 data: 0.0626 max mem: 8255 +Train: [98] [ 600/6250] eta: 0:14:32 lr: 0.000000 grad: 0.1566 (0.1805) loss: 0.8347 (0.8431) time: 0.0952 data: 0.0181 max mem: 8255 +Train: [98] [ 700/6250] eta: 0:14:30 lr: 0.000000 grad: 0.1587 (0.1787) loss: 0.8334 (0.8420) time: 0.1638 data: 0.0667 max mem: 8255 +Train: [98] [ 800/6250] eta: 0:14:17 lr: 0.000000 grad: 0.1683 (0.1783) loss: 0.8381 (0.8411) time: 0.1427 data: 0.0712 max mem: 8255 +Train: [98] [ 900/6250] eta: 0:13:49 lr: 0.000000 grad: 0.1519 (0.1768) loss: 0.8425 (0.8410) time: 0.1283 data: 0.0548 max mem: 8255 +Train: [98] [1000/6250] eta: 0:13:34 lr: 0.000000 grad: 0.1549 (0.1758) loss: 0.8397 (0.8411) time: 0.1104 data: 0.0259 max mem: 8255 +Train: [98] [1100/6250] eta: 0:13:08 lr: 0.000000 grad: 0.1528 (0.1749) loss: 0.8450 (0.8414) time: 0.1260 data: 0.0601 max mem: 8255 +Train: [98] [1200/6250] eta: 0:12:44 lr: 0.000000 grad: 0.1531 (0.1736) loss: 0.8453 (0.8418) time: 0.1218 data: 0.0515 max mem: 8255 +Train: [98] [1300/6250] eta: 0:12:22 lr: 0.000000 grad: 0.1525 (0.1727) loss: 0.8441 (0.8419) time: 0.1440 data: 0.0780 max mem: 8255 +Train: [98] [1400/6250] eta: 0:12:02 lr: 0.000000 grad: 0.1515 (0.1715) loss: 0.8492 (0.8423) time: 0.1478 data: 0.0621 max mem: 8255 +Train: [98] [1500/6250] eta: 0:11:44 lr: 0.000000 grad: 0.1476 (0.1704) loss: 0.8479 (0.8427) time: 0.1280 data: 0.0608 max mem: 8255 +Train: [98] [1600/6250] eta: 0:11:27 lr: 0.000000 grad: 0.1544 (0.1697) loss: 0.8480 (0.8430) time: 0.1665 data: 0.0858 max mem: 8255 +Train: [98] [1700/6250] eta: 0:11:09 lr: 0.000000 grad: 0.1484 (0.1690) loss: 0.8430 (0.8432) time: 0.1434 data: 0.0716 max mem: 8255 +Train: [98] [1800/6250] eta: 0:10:51 lr: 0.000000 grad: 0.1579 (0.1684) loss: 0.8406 (0.8432) time: 0.1464 data: 0.0735 max mem: 8255 +Train: [98] [1900/6250] eta: 0:10:34 lr: 0.000000 grad: 0.1510 (0.1677) loss: 0.8456 (0.8434) time: 0.1315 data: 0.0581 max mem: 8255 +Train: [98] [2000/6250] eta: 0:10:17 lr: 0.000000 grad: 0.1572 (0.1669) loss: 0.8434 (0.8437) time: 0.1194 data: 0.0537 max mem: 8255 +Train: [98] [2100/6250] eta: 0:10:00 lr: 0.000000 grad: 0.1517 (0.1664) loss: 0.8468 (0.8437) time: 0.1411 data: 0.0682 max mem: 8255 +Train: [98] [2200/6250] eta: 0:09:44 lr: 0.000000 grad: 0.1526 (0.1661) loss: 0.8426 (0.8438) time: 0.1316 data: 0.0545 max mem: 8255 +Train: [98] [2300/6250] eta: 0:09:30 lr: 0.000000 grad: 0.1460 (0.1657) loss: 0.8455 (0.8440) time: 0.1642 data: 0.0983 max mem: 8255 +Train: [98] [2400/6250] eta: 0:09:15 lr: 0.000000 grad: 0.1578 (0.1654) loss: 0.8456 (0.8441) time: 0.1337 data: 0.0653 max mem: 8255 +Train: [98] [2500/6250] eta: 0:09:01 lr: 0.000000 grad: 0.1506 (0.1652) loss: 0.8493 (0.8443) time: 0.1418 data: 0.0688 max mem: 8255 +Train: [98] [2600/6250] eta: 0:08:47 lr: 0.000000 grad: 0.1476 (0.1651) loss: 0.8443 (0.8444) time: 0.1511 data: 0.0748 max mem: 8255 +Train: [98] [2700/6250] eta: 0:08:33 lr: 0.000000 grad: 0.1668 (0.1650) loss: 0.8414 (0.8445) time: 0.1502 data: 0.0909 max mem: 8255 +Train: [98] [2800/6250] eta: 0:08:18 lr: 0.000000 grad: 0.1607 (0.1650) loss: 0.8478 (0.8445) time: 0.1342 data: 0.0562 max mem: 8255 +Train: [98] [2900/6250] eta: 0:08:02 lr: 0.000000 grad: 0.1562 (0.1647) loss: 0.8388 (0.8446) time: 0.1147 data: 0.0400 max mem: 8255 +Train: [98] [3000/6250] eta: 0:07:47 lr: 0.000000 grad: 0.1549 (0.1645) loss: 0.8460 (0.8447) time: 0.1452 data: 0.0734 max mem: 8255 +Train: [98] [3100/6250] eta: 0:07:33 lr: 0.000000 grad: 0.1623 (0.1644) loss: 0.8501 (0.8447) time: 0.1920 data: 0.1081 max mem: 8255 +Train: [98] [3200/6250] eta: 0:07:17 lr: 0.000000 grad: 0.1531 (0.1642) loss: 0.8448 (0.8447) time: 0.1214 data: 0.0438 max mem: 8255 +Train: [98] [3300/6250] eta: 0:07:02 lr: 0.000000 grad: 0.1609 (0.1641) loss: 0.8459 (0.8447) time: 0.1514 data: 0.0834 max mem: 8255 +Train: [98] [3400/6250] eta: 0:06:47 lr: 0.000000 grad: 0.1671 (0.1640) loss: 0.8412 (0.8446) time: 0.1238 data: 0.0521 max mem: 8255 +Train: [98] [3500/6250] eta: 0:06:32 lr: 0.000000 grad: 0.1478 (0.1637) loss: 0.8511 (0.8446) time: 0.1057 data: 0.0380 max mem: 8255 +Train: [98] [3600/6250] eta: 0:06:17 lr: 0.000000 grad: 0.1501 (0.1636) loss: 0.8447 (0.8446) time: 0.1493 data: 0.0775 max mem: 8255 +Train: [98] [3700/6250] eta: 0:06:03 lr: 0.000000 grad: 0.1614 (0.1635) loss: 0.8413 (0.8445) time: 0.1122 data: 0.0329 max mem: 8255 +Train: [98] [3800/6250] eta: 0:05:49 lr: 0.000000 grad: 0.1545 (0.1634) loss: 0.8416 (0.8445) time: 0.1567 data: 0.0949 max mem: 8255 +Train: [98] [3900/6250] eta: 0:05:34 lr: 0.000000 grad: 0.1756 (0.1635) loss: 0.8418 (0.8445) time: 0.1322 data: 0.0588 max mem: 8255 +Train: [98] [4000/6250] eta: 0:05:19 lr: 0.000000 grad: 0.1543 (0.1636) loss: 0.8458 (0.8445) time: 0.1392 data: 0.0618 max mem: 8255 +Train: [98] [4100/6250] eta: 0:05:05 lr: 0.000000 grad: 0.1512 (0.1637) loss: 0.8439 (0.8445) time: 0.1273 data: 0.0611 max mem: 8255 +Train: [98] [4200/6250] eta: 0:04:50 lr: 0.000000 grad: 0.1581 (0.1637) loss: 0.8455 (0.8446) time: 0.1356 data: 0.0648 max mem: 8255 +Train: [98] [4300/6250] eta: 0:04:36 lr: 0.000000 grad: 0.1720 (0.1639) loss: 0.8440 (0.8446) time: 0.1110 data: 0.0379 max mem: 8255 +Train: [98] [4400/6250] eta: 0:04:21 lr: 0.000000 grad: 0.1665 (0.1641) loss: 0.8460 (0.8446) time: 0.1473 data: 0.0763 max mem: 8255 +Train: [98] [4500/6250] eta: 0:04:07 lr: 0.000000 grad: 0.1665 (0.1642) loss: 0.8478 (0.8446) time: 0.1409 data: 0.0562 max mem: 8255 +Train: [98] [4600/6250] eta: 0:03:53 lr: 0.000000 grad: 0.1548 (0.1643) loss: 0.8477 (0.8447) time: 0.1441 data: 0.0677 max mem: 8255 +Train: [98] [4700/6250] eta: 0:03:39 lr: 0.000000 grad: 0.1662 (0.1644) loss: 0.8437 (0.8447) time: 0.1811 data: 0.0649 max mem: 8255 +Train: [98] [4800/6250] eta: 0:03:25 lr: 0.000000 grad: 0.1645 (0.1644) loss: 0.8466 (0.8447) time: 0.1377 data: 0.0685 max mem: 8255 +Train: [98] [4900/6250] eta: 0:03:10 lr: 0.000000 grad: 0.1583 (0.1644) loss: 0.8503 (0.8447) time: 0.1348 data: 0.0604 max mem: 8255 +Train: [98] [5000/6250] eta: 0:02:56 lr: 0.000000 grad: 0.1602 (0.1643) loss: 0.8504 (0.8447) time: 0.1568 data: 0.0794 max mem: 8255 +Train: [98] [5100/6250] eta: 0:02:42 lr: 0.000000 grad: 0.1546 (0.1643) loss: 0.8452 (0.8447) time: 0.1126 data: 0.0304 max mem: 8255 +Train: [98] [5200/6250] eta: 0:02:28 lr: 0.000000 grad: 0.1620 (0.1642) loss: 0.8400 (0.8447) time: 0.1308 data: 0.0688 max mem: 8255 +Train: [98] [5300/6250] eta: 0:02:13 lr: 0.000000 grad: 0.1637 (0.1641) loss: 0.8431 (0.8448) time: 0.1180 data: 0.0418 max mem: 8255 +Train: [98] [5400/6250] eta: 0:01:59 lr: 0.000000 grad: 0.1562 (0.1640) loss: 0.8440 (0.8448) time: 0.1326 data: 0.0626 max mem: 8255 +Train: [98] [5500/6250] eta: 0:01:45 lr: 0.000000 grad: 0.1596 (0.1639) loss: 0.8462 (0.8448) time: 0.1499 data: 0.0585 max mem: 8255 +Train: [98] [5600/6250] eta: 0:01:31 lr: 0.000000 grad: 0.1480 (0.1639) loss: 0.8554 (0.8448) time: 0.1044 data: 0.0301 max mem: 8255 +Train: [98] [5700/6250] eta: 0:01:17 lr: 0.000000 grad: 0.1510 (0.1639) loss: 0.8391 (0.8447) time: 0.1229 data: 0.0460 max mem: 8255 +Train: [98] [5800/6250] eta: 0:01:03 lr: 0.000000 grad: 0.1529 (0.1638) loss: 0.8459 (0.8447) time: 0.1563 data: 0.0951 max mem: 8255 +Train: [98] [5900/6250] eta: 0:00:49 lr: 0.000000 grad: 0.1631 (0.1638) loss: 0.8517 (0.8446) time: 0.1139 data: 0.0359 max mem: 8255 +Train: [98] [6000/6250] eta: 0:00:35 lr: 0.000000 grad: 0.1543 (0.1638) loss: 0.8422 (0.8446) time: 0.1319 data: 0.0559 max mem: 8255 +Train: [98] [6100/6250] eta: 0:00:21 lr: 0.000000 grad: 0.1633 (0.1639) loss: 0.8350 (0.8445) time: 0.1200 data: 0.0539 max mem: 8255 +Train: [98] [6200/6250] eta: 0:00:06 lr: 0.000000 grad: 0.1523 (0.1640) loss: 0.8408 (0.8444) time: 0.1091 data: 0.0329 max mem: 8255 +Train: [98] [6249/6250] eta: 0:00:00 lr: 0.000000 grad: 0.1573 (0.1640) loss: 0.8407 (0.8443) time: 0.1126 data: 0.0315 max mem: 8255 +Train: [98] Total time: 0:14:39 (0.1407 s / it) +Averaged stats: lr: 0.000000 grad: 0.1573 (0.1640) loss: 0.8407 (0.8443) +Eval (hcp-train-subset): [98] [ 0/62] eta: 0:03:53 loss: 0.8517 (0.8517) time: 3.7597 data: 3.6957 max mem: 8255 +Eval (hcp-train-subset): [98] [61/62] eta: 0:00:00 loss: 0.8371 (0.8422) time: 0.1091 data: 0.0881 max mem: 8255 +Eval (hcp-train-subset): [98] Total time: 0:00:12 (0.2002 s / it) +Averaged stats (hcp-train-subset): loss: 0.8371 (0.8422) +Eval (hcp-val): [98] [ 0/62] eta: 0:06:14 loss: 0.8677 (0.8677) time: 6.0398 data: 6.0062 max mem: 8255 +Eval (hcp-val): [98] [61/62] eta: 0:00:00 loss: 0.8690 (0.8701) time: 0.1312 data: 0.1104 max mem: 8255 +Eval (hcp-val): [98] Total time: 0:00:14 (0.2285 s / it) +Averaged stats (hcp-val): loss: 0.8690 (0.8701) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +Train: [99] [ 0/6250] eta: 11:17:41 lr: 0.000000 grad: 0.2072 (0.2072) loss: 0.7805 (0.7805) time: 6.5058 data: 6.4127 max mem: 8255 +Train: [99] [ 100/6250] eta: 0:18:53 lr: 0.000000 grad: 0.1967 (0.2191) loss: 0.8262 (0.8338) time: 0.1220 data: 0.0224 max mem: 8255 +Train: [99] [ 200/6250] eta: 0:15:47 lr: 0.000000 grad: 0.1750 (0.2093) loss: 0.8314 (0.8303) time: 0.1127 data: 0.0160 max mem: 8255 +Train: [99] [ 300/6250] eta: 0:14:20 lr: 0.000000 grad: 0.1815 (0.2015) loss: 0.8333 (0.8301) time: 0.1127 data: 0.0234 max mem: 8255 +Train: [99] [ 400/6250] eta: 0:13:23 lr: 0.000000 grad: 0.1772 (0.1956) loss: 0.8386 (0.8321) time: 0.1219 data: 0.0395 max mem: 8255 +Train: [99] [ 500/6250] eta: 0:12:48 lr: 0.000000 grad: 0.1451 (0.1898) loss: 0.8465 (0.8348) time: 0.1248 data: 0.0358 max mem: 8255 +Train: [99] [ 600/6250] eta: 0:12:23 lr: 0.000000 grad: 0.1460 (0.1847) loss: 0.8435 (0.8369) time: 0.1361 data: 0.0564 max mem: 8255 +Train: [99] [ 700/6250] eta: 0:12:08 lr: 0.000000 grad: 0.1589 (0.1823) loss: 0.8419 (0.8382) time: 0.1130 data: 0.0310 max mem: 8255 +Train: [99] [ 800/6250] eta: 0:12:01 lr: 0.000000 grad: 0.1624 (0.1805) loss: 0.8468 (0.8390) time: 0.1461 data: 0.0675 max mem: 8255 +Train: [99] [ 900/6250] eta: 0:11:58 lr: 0.000000 grad: 0.1551 (0.1778) loss: 0.8418 (0.8398) time: 0.1437 data: 0.0519 max mem: 8255 +Train: [99] [1000/6250] eta: 0:11:41 lr: 0.000000 grad: 0.1612 (0.1760) loss: 0.8474 (0.8403) time: 0.1130 data: 0.0296 max mem: 8255 +Train: [99] [1100/6250] eta: 0:11:43 lr: 0.000000 grad: 0.1616 (0.1745) loss: 0.8425 (0.8407) time: 0.0849 data: 0.0002 max mem: 8255 +Train: [99] [1200/6250] eta: 0:11:26 lr: 0.000000 grad: 0.1558 (0.1734) loss: 0.8443 (0.8410) time: 0.1031 data: 0.0093 max mem: 8255 +Train: [99] [1300/6250] eta: 0:11:12 lr: 0.000000 grad: 0.1479 (0.1723) loss: 0.8448 (0.8414) time: 0.1643 data: 0.0769 max mem: 8255 +Train: [99] [1400/6250] eta: 0:11:01 lr: 0.000000 grad: 0.1485 (0.1714) loss: 0.8482 (0.8416) time: 0.1648 data: 0.0839 max mem: 8255 +Train: [99] [1500/6250] eta: 0:10:48 lr: 0.000000 grad: 0.1604 (0.1705) loss: 0.8406 (0.8418) time: 0.1193 data: 0.0460 max mem: 8255 +Train: [99] [1600/6250] eta: 0:10:33 lr: 0.000000 grad: 0.1568 (0.1698) loss: 0.8394 (0.8418) time: 0.1278 data: 0.0612 max mem: 8255 +Train: [99] [1700/6250] eta: 0:10:20 lr: 0.000000 grad: 0.1584 (0.1691) loss: 0.8449 (0.8420) time: 0.1496 data: 0.0766 max mem: 8255 +Train: [99] [1800/6250] eta: 0:10:13 lr: 0.000000 grad: 0.1417 (0.1682) loss: 0.8501 (0.8422) time: 0.2053 data: 0.1313 max mem: 8255 +Train: [99] [1900/6250] eta: 0:09:57 lr: 0.000000 grad: 0.1597 (0.1677) loss: 0.8358 (0.8423) time: 0.1308 data: 0.0437 max mem: 8255 +Train: [99] [2000/6250] eta: 0:09:42 lr: 0.000000 grad: 0.1525 (0.1671) loss: 0.8452 (0.8424) time: 0.1343 data: 0.0617 max mem: 8255 +Train: [99] [2100/6250] eta: 0:09:28 lr: 0.000000 grad: 0.1506 (0.1665) loss: 0.8449 (0.8426) time: 0.1355 data: 0.0652 max mem: 8255 +Train: [99] [2200/6250] eta: 0:09:15 lr: 0.000000 grad: 0.1558 (0.1662) loss: 0.8511 (0.8428) time: 0.1220 data: 0.0515 max mem: 8255 +Train: [99] [2300/6250] eta: 0:09:01 lr: 0.000000 grad: 0.1490 (0.1657) loss: 0.8490 (0.8430) time: 0.1328 data: 0.0573 max mem: 8255 +Train: [99] [2400/6250] eta: 0:08:47 lr: 0.000000 grad: 0.1393 (0.1654) loss: 0.8525 (0.8432) time: 0.1396 data: 0.0685 max mem: 8255 +Train: [99] [2500/6250] eta: 0:08:33 lr: 0.000000 grad: 0.1467 (0.1652) loss: 0.8499 (0.8434) time: 0.1400 data: 0.0655 max mem: 8255 +Train: [99] [2600/6250] eta: 0:08:18 lr: 0.000000 grad: 0.1472 (0.1651) loss: 0.8453 (0.8435) time: 0.1257 data: 0.0522 max mem: 8255 +Train: [99] [2700/6250] eta: 0:08:04 lr: 0.000000 grad: 0.1501 (0.1649) loss: 0.8453 (0.8437) time: 0.1301 data: 0.0557 max mem: 8255 +Train: [99] [2800/6250] eta: 0:07:50 lr: 0.000000 grad: 0.1506 (0.1646) loss: 0.8534 (0.8438) time: 0.1390 data: 0.0718 max mem: 8255 +Train: [99] [2900/6250] eta: 0:07:35 lr: 0.000000 grad: 0.1540 (0.1644) loss: 0.8494 (0.8439) time: 0.1356 data: 0.0662 max mem: 8255 +Train: [99] [3000/6250] eta: 0:07:22 lr: 0.000000 grad: 0.1577 (0.1641) loss: 0.8460 (0.8440) time: 0.1564 data: 0.0823 max mem: 8255 +Train: [99] [3100/6250] eta: 0:07:07 lr: 0.000000 grad: 0.1565 (0.1640) loss: 0.8471 (0.8441) time: 0.1171 data: 0.0443 max mem: 8255 +Train: [99] [3200/6250] eta: 0:06:52 lr: 0.000000 grad: 0.1624 (0.1638) loss: 0.8453 (0.8442) time: 0.1286 data: 0.0584 max mem: 8255 +Train: [99] [3300/6250] eta: 0:06:39 lr: 0.000000 grad: 0.1460 (0.1636) loss: 0.8494 (0.8444) time: 0.1494 data: 0.0735 max mem: 8255 +Train: [99] [3400/6250] eta: 0:06:25 lr: 0.000000 grad: 0.1432 (0.1634) loss: 0.8501 (0.8444) time: 0.1301 data: 0.0654 max mem: 8255 +Train: [99] [3500/6250] eta: 0:06:12 lr: 0.000000 grad: 0.1542 (0.1632) loss: 0.8465 (0.8445) time: 0.1210 data: 0.0496 max mem: 8255 +Train: [99] [3600/6250] eta: 0:05:59 lr: 0.000000 grad: 0.1455 (0.1630) loss: 0.8490 (0.8447) time: 0.1446 data: 0.0721 max mem: 8255 +Train: [99] [3700/6250] eta: 0:05:47 lr: 0.000000 grad: 0.1569 (0.1628) loss: 0.8462 (0.8448) time: 0.1813 data: 0.1217 max mem: 8255 +Train: [99] [3800/6250] eta: 0:05:34 lr: 0.000000 grad: 0.1535 (0.1628) loss: 0.8455 (0.8449) time: 0.1303 data: 0.0608 max mem: 8255 +Train: [99] [3900/6250] eta: 0:05:21 lr: 0.000000 grad: 0.1500 (0.1628) loss: 0.8455 (0.8449) time: 0.1292 data: 0.0624 max mem: 8255 +Train: [99] [4000/6250] eta: 0:05:08 lr: 0.000000 grad: 0.1573 (0.1628) loss: 0.8427 (0.8449) time: 0.1602 data: 0.0835 max mem: 8255 +Train: [99] [4100/6250] eta: 0:04:54 lr: 0.000000 grad: 0.1565 (0.1629) loss: 0.8466 (0.8449) time: 0.1391 data: 0.0661 max mem: 8255 +Train: [99] [4200/6250] eta: 0:04:40 lr: 0.000000 grad: 0.1794 (0.1631) loss: 0.8450 (0.8449) time: 0.1380 data: 0.0658 max mem: 8255 +Train: [99] [4300/6250] eta: 0:04:26 lr: 0.000000 grad: 0.1619 (0.1630) loss: 0.8416 (0.8450) time: 0.1244 data: 0.0453 max mem: 8255 +Train: [99] [4400/6250] eta: 0:04:13 lr: 0.000000 grad: 0.1524 (0.1629) loss: 0.8435 (0.8450) time: 0.1618 data: 0.0861 max mem: 8255 +Train: [99] [4500/6250] eta: 0:04:00 lr: 0.000000 grad: 0.1503 (0.1628) loss: 0.8447 (0.8450) time: 0.1323 data: 0.0621 max mem: 8255 +Train: [99] [4600/6250] eta: 0:03:47 lr: 0.000000 grad: 0.1516 (0.1629) loss: 0.8449 (0.8450) time: 0.2149 data: 0.1437 max mem: 8255 +Train: [99] [4700/6250] eta: 0:03:33 lr: 0.000000 grad: 0.1592 (0.1629) loss: 0.8440 (0.8450) time: 0.1267 data: 0.0593 max mem: 8255 +Train: [99] [4800/6250] eta: 0:03:19 lr: 0.000000 grad: 0.1619 (0.1629) loss: 0.8457 (0.8449) time: 0.1377 data: 0.0670 max mem: 8255 +Train: [99] [4900/6250] eta: 0:03:05 lr: 0.000000 grad: 0.1556 (0.1630) loss: 0.8451 (0.8449) time: 0.0927 data: 0.0141 max mem: 8255 +Train: [99] [5000/6250] eta: 0:02:51 lr: 0.000000 grad: 0.1633 (0.1631) loss: 0.8381 (0.8448) time: 0.1376 data: 0.0696 max mem: 8255 +Train: [99] [5100/6250] eta: 0:02:38 lr: 0.000000 grad: 0.1552 (0.1631) loss: 0.8440 (0.8448) time: 0.2202 data: 0.1543 max mem: 8255 +Train: [99] [5200/6250] eta: 0:02:24 lr: 0.000000 grad: 0.1601 (0.1633) loss: 0.8419 (0.8447) time: 0.1352 data: 0.0632 max mem: 8255 +Train: [99] [5300/6250] eta: 0:02:10 lr: 0.000000 grad: 0.1618 (0.1634) loss: 0.8461 (0.8447) time: 0.1341 data: 0.0553 max mem: 8255 +Train: [99] [5400/6250] eta: 0:01:56 lr: 0.000000 grad: 0.1644 (0.1637) loss: 0.8452 (0.8447) time: 0.1364 data: 0.0592 max mem: 8255 +Train: [99] [5500/6250] eta: 0:01:43 lr: 0.000000 grad: 0.1599 (0.1638) loss: 0.8387 (0.8446) time: 0.1309 data: 0.0578 max mem: 8255 +Train: [99] [5600/6250] eta: 0:01:29 lr: 0.000000 grad: 0.1757 (0.1639) loss: 0.8394 (0.8446) time: 0.1305 data: 0.0585 max mem: 8255 +Train: [99] [5700/6250] eta: 0:01:15 lr: 0.000000 grad: 0.1588 (0.1640) loss: 0.8414 (0.8446) time: 0.1357 data: 0.0731 max mem: 8255 +Train: [99] [5800/6250] eta: 0:01:01 lr: 0.000000 grad: 0.1668 (0.1641) loss: 0.8432 (0.8445) time: 0.1554 data: 0.0811 max mem: 8255 +Train: [99] [5900/6250] eta: 0:00:48 lr: 0.000000 grad: 0.1577 (0.1642) loss: 0.8425 (0.8445) time: 0.1822 data: 0.1155 max mem: 8255 +Train: [99] [6000/6250] eta: 0:00:34 lr: 0.000000 grad: 0.1613 (0.1643) loss: 0.8444 (0.8444) time: 0.1513 data: 0.0729 max mem: 8255 +Train: [99] [6100/6250] eta: 0:00:20 lr: 0.000000 grad: 0.1599 (0.1645) loss: 0.8444 (0.8443) time: 0.1407 data: 0.0682 max mem: 8255 +Train: [99] [6200/6250] eta: 0:00:06 lr: 0.000000 grad: 0.1647 (0.1648) loss: 0.8402 (0.8442) time: 0.1491 data: 0.0819 max mem: 8255 +Train: [99] [6249/6250] eta: 0:00:00 lr: 0.000000 grad: 0.1717 (0.1649) loss: 0.8394 (0.8442) time: 0.1521 data: 0.0841 max mem: 8255 +Train: [99] Total time: 0:14:33 (0.1398 s / it) +Averaged stats: lr: 0.000000 grad: 0.1717 (0.1649) loss: 0.8394 (0.8442) +Eval (hcp-train-subset): [99] [ 0/62] eta: 0:05:32 loss: 0.8513 (0.8513) time: 5.3603 data: 5.3276 max mem: 8255 +Eval (hcp-train-subset): [99] [61/62] eta: 0:00:00 loss: 0.8383 (0.8424) time: 0.1465 data: 0.1247 max mem: 8255 +Eval (hcp-train-subset): [99] Total time: 0:00:14 (0.2322 s / it) +Averaged stats (hcp-train-subset): loss: 0.8383 (0.8424) +Making plots (hcp-train-subset): example=56 +Eval (hcp-val): [99] [ 0/62] eta: 0:05:28 loss: 0.8698 (0.8698) time: 5.3024 data: 5.2760 max mem: 8255 +Eval (hcp-val): [99] [61/62] eta: 0:00:00 loss: 0.8696 (0.8704) time: 0.1392 data: 0.1174 max mem: 8255 +Eval (hcp-val): [99] Total time: 0:00:14 (0.2263 s / it) +Averaged stats (hcp-val): loss: 0.8696 (0.8704) +Making plots (hcp-val): example=50 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +saving checkpoint experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-00099.pth +done! training time: 1 day, 3:47:21 diff --git a/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_age__patch__attn/config.yaml b/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_age__patch__attn/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..cfa5cf8c3eb87e578aa5439eaad58bc9ef634f58 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_age__patch__attn/config.yaml @@ -0,0 +1,98 @@ +output_root: experiments/input_space_v3/output +name_prefix: eval_probe +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_1; eval v2 (aabc_age patch attn) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +dataset_kwargs: {} +classifier_kwargs: + embed_dim: null + dropout: 0.0 + xavier_init: true + norm: true +lr_scale_grid: +- 0.02 +- 0.023 +- 0.028 +- 0.033 +- 0.038 +- 0.045 +- 0.053 +- 0.062 +- 0.074 +- 0.087 +- 0.1 +- 0.12 +- 0.14 +- 0.17 +- 0.2 +- 0.23 +- 0.27 +- 0.32 +- 0.38 +- 0.44 +- 0.52 +- 0.61 +- 0.72 +- 0.85 +- 1 +- 1.2 +- 1.4 +- 1.6 +- 1.9 +- 2.3 +- 2.7 +- 3.1 +- 3.7 +- 4.3 +- 5.1 +- 6 +- 7.1 +- 8.3 +- 9.8 +- 12 +- 14 +- 16 +- 19 +- 22 +- 26 +- 31 +- 36 +- 43 +- 50 +wd_scale_grid: +- 1.0 +num_workers: 8 +prefetch_factor: null +balanced_sampling: false +epochs: 20 +steps_per_epoch: 200 +batch_size: 4 +accum_iter: 4 +lr: 0.0003 +warmup_epochs: 5 +no_decay: false +weight_decay: 0.05 +clip_grad: 1.0 +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +early_stopping: true +amp: true +device: cuda +seed: 4466 +debug: false +wandb: false +wandb_entity: null +wandb_project: fMRI-fm-eval +name: input_space_v3/flat_lr1e-3_1/eval_v2/aabc_age__patch__attn +base_lr: 3.0e-05 +model: flat_mae +representation: patch +classifier: attn +dataset: aabc_age +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_age__patch__attn +remote_dir: null diff --git a/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_age__patch__attn/eval_log.json b/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_age__patch__attn/eval_log.json new file mode 100644 index 0000000000000000000000000000000000000000..22ffdf47de7f8ca7d1c1a22aadfd31eacdb154cc --- /dev/null +++ b/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_age__patch__attn/eval_log.json @@ -0,0 +1 @@ +{"eval/epoch": 4, "eval/id_best": 27, "eval/lr_best": 0.00047999999999999996, "eval/wd_best": 0.05, "eval/train/loss": 0.7455049157142639, "eval/train/acc": 0.6527472527472528, "eval/train/acc_std": 0.018765473026311374, "eval/train/f1": 0.6277436116459593, "eval/train/f1_std": 0.022186241437448337, "eval/train/bacc": 0.66084089103124, "eval/train/bacc_std": 0.018430580611927462, "eval/validation/loss": 1.3573294878005981, "eval/validation/acc": 0.5471698113207547, "eval/validation/acc_std": 0.0550459337624561, "eval/validation/f1": 0.49924538254709033, "eval/validation/f1_std": 0.06451258501746018, "eval/validation/bacc": 0.5309065934065934, "eval/validation/bacc_std": 0.0556606639831592, "eval/test/loss": 1.480803370475769, "eval/test/acc": 0.4230769230769231, "eval/test/acc_std": 0.059341492413769736, "eval/test/f1": 0.36177884615384615, "eval/test/f1_std": 0.05158249538627643, "eval/test/bacc": 0.40796703296703296, "eval/test/bacc_std": 0.05819170167751674} diff --git a/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_age__patch__attn/eval_log_best.json b/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_age__patch__attn/eval_log_best.json new file mode 100644 index 0000000000000000000000000000000000000000..f4b7fb5a1200e8183b6519a76a227441ff1b5b29 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_age__patch__attn/eval_log_best.json @@ -0,0 +1 @@ +{"eval/best/epoch": 4, "eval/best/id_best": 27, "eval/best/lr_best": 0.00047999999999999996, "eval/best/wd_best": 0.05, "eval/best/train/loss": 0.7455049157142639, "eval/best/train/acc": 0.6527472527472528, "eval/best/train/acc_std": 0.018765473026311374, "eval/best/train/f1": 0.6277436116459593, "eval/best/train/f1_std": 0.022186241437448337, "eval/best/train/bacc": 0.66084089103124, "eval/best/train/bacc_std": 0.018430580611927462, "eval/best/validation/loss": 1.3573294878005981, "eval/best/validation/acc": 0.5471698113207547, "eval/best/validation/acc_std": 0.0550459337624561, "eval/best/validation/f1": 0.49924538254709033, "eval/best/validation/f1_std": 0.06451258501746018, "eval/best/validation/bacc": 0.5309065934065934, "eval/best/validation/bacc_std": 0.0556606639831592, "eval/best/test/loss": 1.480803370475769, "eval/best/test/acc": 0.4230769230769231, "eval/best/test/acc_std": 0.059341492413769736, "eval/best/test/f1": 0.36177884615384615, "eval/best/test/f1_std": 0.05158249538627643, "eval/best/test/bacc": 0.40796703296703296, "eval/best/test/bacc_std": 0.05819170167751674} diff --git a/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_age__patch__attn/eval_log_last.json b/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_age__patch__attn/eval_log_last.json new file mode 100644 index 0000000000000000000000000000000000000000..fd03b8cd24fc441069e88bc319826c4d437b770f --- /dev/null +++ b/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_age__patch__attn/eval_log_last.json @@ -0,0 +1 @@ +{"eval/last/epoch": 19, "eval/last/id_best": 9, "eval/last/lr_best": 2.6099999999999997e-05, "eval/last/wd_best": 0.05, "eval/last/train/loss": 1.0141990184783936, "eval/last/train/acc": 0.5846153846153846, "eval/last/train/acc_std": 0.02186711842590666, "eval/last/train/f1": 0.5843840140079207, "eval/last/train/f1_std": 0.021987356093763556, "eval/last/train/bacc": 0.5858561596606096, "eval/last/train/bacc_std": 0.0219229663651034, "eval/last/validation/loss": 1.196008324623108, "eval/last/validation/acc": 0.4528301886792453, "eval/last/validation/acc_std": 0.06955136710683214, "eval/last/validation/f1": 0.4489224137931035, "eval/last/validation/f1_std": 0.07162535633268452, "eval/last/validation/bacc": 0.4487179487179487, "eval/last/validation/bacc_std": 0.06963081707822269, "eval/last/test/loss": 1.3205338716506958, "eval/last/test/acc": 0.4230769230769231, "eval/last/test/acc_std": 0.061064751257610524, "eval/last/test/f1": 0.4130861040068201, "eval/last/test/f1_std": 0.060411480537465964, "eval/last/test/bacc": 0.4139194139194139, "eval/last/test/bacc_std": 0.06059533643078067} diff --git a/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_age__patch__attn/eval_table.csv b/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_age__patch__attn/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..46ce3eaf474f01c49322cc5b1e8c64539b5a2db1 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_age__patch__attn/eval_table.csv @@ -0,0 +1,4 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std,bacc,bacc_std +flat_mae,patch,attn,aabc_age,best,4,0.00047999999999999996,0.05,27,"[1.6, 1.0]",train,0.7455049157142639,0.6527472527472528,0.018765473026311374,0.6277436116459593,0.022186241437448337,0.66084089103124,0.018430580611927462 +flat_mae,patch,attn,aabc_age,best,4,0.00047999999999999996,0.05,27,"[1.6, 1.0]",validation,1.3573294878005981,0.5471698113207547,0.0550459337624561,0.49924538254709033,0.06451258501746018,0.5309065934065934,0.0556606639831592 +flat_mae,patch,attn,aabc_age,best,4,0.00047999999999999996,0.05,27,"[1.6, 1.0]",test,1.480803370475769,0.4230769230769231,0.059341492413769736,0.36177884615384615,0.05158249538627643,0.40796703296703296,0.05819170167751674 diff --git a/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_age__patch__attn/eval_table_best.csv b/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_age__patch__attn/eval_table_best.csv new file mode 100644 index 0000000000000000000000000000000000000000..46ce3eaf474f01c49322cc5b1e8c64539b5a2db1 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_age__patch__attn/eval_table_best.csv @@ -0,0 +1,4 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std,bacc,bacc_std +flat_mae,patch,attn,aabc_age,best,4,0.00047999999999999996,0.05,27,"[1.6, 1.0]",train,0.7455049157142639,0.6527472527472528,0.018765473026311374,0.6277436116459593,0.022186241437448337,0.66084089103124,0.018430580611927462 +flat_mae,patch,attn,aabc_age,best,4,0.00047999999999999996,0.05,27,"[1.6, 1.0]",validation,1.3573294878005981,0.5471698113207547,0.0550459337624561,0.49924538254709033,0.06451258501746018,0.5309065934065934,0.0556606639831592 +flat_mae,patch,attn,aabc_age,best,4,0.00047999999999999996,0.05,27,"[1.6, 1.0]",test,1.480803370475769,0.4230769230769231,0.059341492413769736,0.36177884615384615,0.05158249538627643,0.40796703296703296,0.05819170167751674 diff --git a/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_age__patch__attn/eval_table_last.csv b/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_age__patch__attn/eval_table_last.csv new file mode 100644 index 0000000000000000000000000000000000000000..9caa0ba54db50c8d5641e97cb4028bca2f906d48 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_age__patch__attn/eval_table_last.csv @@ -0,0 +1,4 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std,bacc,bacc_std +flat_mae,patch,attn,aabc_age,last,19,2.6099999999999997e-05,0.05,9,"[0.087, 1.0]",train,1.0141990184783936,0.5846153846153846,0.02186711842590666,0.5843840140079207,0.021987356093763556,0.5858561596606096,0.0219229663651034 +flat_mae,patch,attn,aabc_age,last,19,2.6099999999999997e-05,0.05,9,"[0.087, 1.0]",validation,1.196008324623108,0.4528301886792453,0.06955136710683214,0.4489224137931035,0.07162535633268452,0.4487179487179487,0.06963081707822269 +flat_mae,patch,attn,aabc_age,last,19,2.6099999999999997e-05,0.05,9,"[0.087, 1.0]",test,1.3205338716506958,0.4230769230769231,0.061064751257610524,0.4130861040068201,0.060411480537465964,0.4139194139194139,0.06059533643078067 diff --git a/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_age__patch__attn/log.txt b/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_age__patch__attn/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..224374f85e5ea6d3ff081a090d898a8bfa49070a --- /dev/null +++ b/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_age__patch__attn/log.txt @@ -0,0 +1,1197 @@ +fMRI foundation model probe eval +version: 0.1.dev95+g65be98d36 +sha: 28a47a6a336052f679e36c7962a91fe73a2e9637, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-04-24 08:02:35 +config: +output_root: experiments/input_space_v3/output +name_prefix: eval_probe +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_1; eval v2 (aabc_age patch attn) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +dataset_kwargs: {} +classifier_kwargs: + embed_dim: null + dropout: 0.0 + xavier_init: true + norm: true +lr_scale_grid: +- 0.02 +- 0.023 +- 0.028 +- 0.033 +- 0.038 +- 0.045 +- 0.053 +- 0.062 +- 0.074 +- 0.087 +- 0.1 +- 0.12 +- 0.14 +- 0.17 +- 0.2 +- 0.23 +- 0.27 +- 0.32 +- 0.38 +- 0.44 +- 0.52 +- 0.61 +- 0.72 +- 0.85 +- 1 +- 1.2 +- 1.4 +- 1.6 +- 1.9 +- 2.3 +- 2.7 +- 3.1 +- 3.7 +- 4.3 +- 5.1 +- 6 +- 7.1 +- 8.3 +- 9.8 +- 12 +- 14 +- 16 +- 19 +- 22 +- 26 +- 31 +- 36 +- 43 +- 50 +wd_scale_grid: +- 1.0 +num_workers: 8 +prefetch_factor: null +balanced_sampling: false +epochs: 20 +steps_per_epoch: 200 +batch_size: 4 +accum_iter: 4 +lr: 0.0003 +warmup_epochs: 5 +no_decay: false +weight_decay: 0.05 +clip_grad: 1.0 +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +early_stopping: true +amp: true +device: cuda +seed: 4466 +debug: false +wandb: false +wandb_entity: null +wandb_project: fMRI-fm-eval +name: input_space_v3/flat_lr1e-3_1/eval_v2/aabc_age__patch__attn +base_lr: 3.0e-05 +model: flat_mae +representation: patch +classifier: attn +dataset: aabc_age +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_age__patch__attn +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=True, reg_tokens=0, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: aabc_age (flat) +train (n=455): +HFDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'segment', 'bold', 'mean', 'std'], + num_rows: 471 +}), + labels=[0 1 2 3], + counts=[110 127 109 109] +) + +validation (n=53): +HFDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'segment', 'bold', 'mean', 'std'], + num_rows: 58 +}), + labels=[0 1 2 3], + counts=[14 13 12 14] +) + +test (n=52): +HFDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'segment', 'bold', 'mean', 'std'], + num_rows: 55 +}), + labels=[0 1 2 3], + counts=[13 13 12 14] +) + +running backbone on example batch to get embedding dim +embedding feature dim (patch): 768 +initializing sweep of classifier heads +classifiers: +ModuleList( + (0-48): 49 x AttnPoolClassifier( + (kv): Linear(in_features=768, out_features=1536, bias=True) + (linear): Linear(in_features=768, out_features=4, bias=True) + ) +) +classifier params (train): 58.1M (58.1M) +setting up optimizer +total batch size: 16 = 4 bs per gpu x 4 accum +lr: 3.00e-04 +full schedule: epochs = 20 (steps = 4000) (decay = True) +warmup: epochs = 5 (steps = 1000) +start training for 20 epochs +train: [0] [ 0/800] eta: 1:12:14 lr: nan time: 5.4179 data: 4.8447 max mem: 29566 +train: [0] [ 20/800] eta: 0:11:11 lr: 0.000001 loss: 1.3738 (1.3891) grad: 0.2606 (0.2846) time: 0.6333 data: 0.0548 max mem: 30263 +train: [0] [ 40/800] eta: 0:09:08 lr: 0.000003 loss: 1.4011 (1.4060) grad: 0.3106 (0.3395) time: 0.5761 data: 0.0021 max mem: 30263 +train: [0] [ 60/800] eta: 0:08:23 lr: 0.000004 loss: 1.3738 (1.3963) grad: 0.3106 (0.3175) time: 0.5957 data: 0.0030 max mem: 30263 +train: [0] [ 80/800] eta: 0:07:51 lr: 0.000006 loss: 1.3738 (1.3893) grad: 0.3106 (0.3317) time: 0.5750 data: 0.0029 max mem: 30263 +train: [0] [100/800] eta: 0:07:31 lr: 0.000007 loss: 1.3769 (1.3868) grad: 0.3018 (0.3226) time: 0.6042 data: 0.0032 max mem: 30263 +train: [0] [120/800] eta: 0:07:47 lr: 0.000009 loss: 1.3630 (1.3821) grad: 0.3018 (0.3394) time: 0.9047 data: 0.2747 max mem: 30263 +train: [0] [140/800] eta: 0:07:29 lr: 0.000010 loss: 1.3538 (1.3824) grad: 0.3482 (0.3497) time: 0.6366 data: 0.0039 max mem: 30263 +train: [0] [160/800] eta: 0:07:10 lr: 0.000012 loss: 1.3538 (1.3798) grad: 0.3104 (0.3507) time: 0.6128 data: 0.0031 max mem: 30263 +train: [0] [180/800] eta: 0:06:51 lr: 0.000013 loss: 1.3452 (1.3747) grad: 0.4093 (0.3641) time: 0.5985 data: 0.0035 max mem: 30263 +train: [0] [200/800] eta: 0:06:34 lr: 0.000015 loss: 1.3452 (1.3687) grad: 0.3518 (0.3564) time: 0.6003 data: 0.0034 max mem: 30263 +train: [0] [220/800] eta: 0:06:18 lr: 0.000016 loss: 1.3232 (1.3588) grad: 0.3518 (0.3521) time: 0.5939 data: 0.0033 max mem: 30263 +train: [0] [240/800] eta: 0:06:15 lr: 0.000018 loss: 1.3232 (1.3596) grad: 0.3747 (0.3576) time: 0.8825 data: 0.2892 max mem: 30263 +train: [0] [260/800] eta: 0:06:01 lr: 0.000019 loss: 1.3232 (1.3575) grad: 0.3427 (0.3536) time: 0.6493 data: 0.0321 max mem: 30263 +train: [0] [280/800] eta: 0:05:45 lr: 0.000021 loss: 1.3268 (1.3582) grad: 0.3236 (0.3502) time: 0.6008 data: 0.0027 max mem: 30263 +train: [0] [300/800] eta: 0:05:29 lr: 0.000022 loss: 1.3140 (1.3499) grad: 0.3080 (0.3406) time: 0.5874 data: 0.0028 max mem: 30263 +train: [0] [320/800] eta: 0:05:14 lr: 0.000024 loss: 1.3140 (1.3515) grad: 0.2748 (0.3390) time: 0.5963 data: 0.0033 max mem: 30263 +train: [0] [340/800] eta: 0:05:06 lr: 0.000025 loss: 1.3562 (1.3490) grad: 0.2499 (0.3375) time: 0.8586 data: 0.2777 max mem: 30263 +train: [0] [360/800] eta: 0:04:54 lr: 0.000027 loss: 1.3045 (1.3454) grad: 0.2499 (0.3370) time: 0.6979 data: 0.0441 max mem: 30263 +train: [0] [380/800] eta: 0:04:39 lr: 0.000028 loss: 1.3341 (1.3475) grad: 0.3308 (0.3386) time: 0.5978 data: 0.0031 max mem: 30263 +train: [0] [400/800] eta: 0:04:25 lr: 0.000030 loss: 1.3341 (1.3490) grad: 0.3308 (0.3394) time: 0.6188 data: 0.0036 max mem: 30263 +train: [0] [420/800] eta: 0:04:10 lr: 0.000031 loss: 1.3208 (1.3438) grad: 0.3382 (0.3413) time: 0.6119 data: 0.0030 max mem: 30263 +train: [0] [440/800] eta: 0:03:56 lr: 0.000033 loss: 1.3282 (1.3414) grad: 0.3245 (0.3374) time: 0.5931 data: 0.0035 max mem: 30263 +train: [0] [460/800] eta: 0:03:46 lr: 0.000034 loss: 1.2839 (1.3356) grad: 0.2633 (0.3358) time: 0.8405 data: 0.2678 max mem: 30263 +train: [0] [480/800] eta: 0:03:32 lr: 0.000036 loss: 1.2342 (1.3290) grad: 0.3295 (0.3371) time: 0.6066 data: 0.0032 max mem: 30263 +train: [0] [500/800] eta: 0:03:17 lr: 0.000037 loss: 1.2035 (1.3245) grad: 0.3396 (0.3397) time: 0.5879 data: 0.0028 max mem: 30263 +train: [0] [520/800] eta: 0:03:03 lr: 0.000039 loss: 1.2035 (1.3207) grad: 0.3449 (0.3390) time: 0.5730 data: 0.0030 max mem: 30263 +train: [0] [540/800] eta: 0:02:50 lr: 0.000040 loss: 1.2035 (1.3187) grad: 0.3396 (0.3386) time: 0.6165 data: 0.0038 max mem: 30263 +train: [0] [560/800] eta: 0:02:36 lr: 0.000042 loss: 1.2116 (1.3148) grad: 0.3331 (0.3407) time: 0.6166 data: 0.0036 max mem: 30263 +train: [0] [580/800] eta: 0:02:25 lr: 0.000043 loss: 1.2116 (1.3122) grad: 0.3248 (0.3424) time: 0.8308 data: 0.2655 max mem: 30263 +train: [0] [600/800] eta: 0:02:11 lr: 0.000045 loss: 1.2034 (1.3085) grad: 0.3248 (0.3404) time: 0.6301 data: 0.0276 max mem: 30263 +train: [0] [620/800] eta: 0:01:58 lr: 0.000046 loss: 1.2102 (1.3073) grad: 0.3197 (0.3394) time: 0.6331 data: 0.0370 max mem: 30263 +train: [0] [640/800] eta: 0:01:44 lr: 0.000048 loss: 1.2658 (1.3073) grad: 0.3020 (0.3389) time: 0.5953 data: 0.0287 max mem: 30263 +train: [0] [660/800] eta: 0:01:31 lr: 0.000049 loss: 1.2829 (1.3063) grad: 0.2762 (0.3368) time: 0.6097 data: 0.0029 max mem: 30263 +train: [0] [680/800] eta: 0:01:19 lr: 0.000051 loss: 1.3003 (1.3062) grad: 0.2915 (0.3366) time: 0.8829 data: 0.2742 max mem: 30263 +train: [0] [700/800] eta: 0:01:05 lr: 0.000052 loss: 1.2913 (1.3037) grad: 0.2891 (0.3351) time: 0.5910 data: 0.0025 max mem: 30263 +train: [0] [720/800] eta: 0:00:52 lr: 0.000054 loss: 1.2747 (1.3022) grad: 0.2811 (0.3339) time: 0.6046 data: 0.0036 max mem: 30263 +train: [0] [740/800] eta: 0:00:39 lr: 0.000055 loss: 1.2395 (1.3005) grad: 0.2811 (0.3317) time: 0.6912 data: 0.1037 max mem: 30263 +train: [0] [760/800] eta: 0:00:26 lr: 0.000057 loss: 1.2223 (1.2974) grad: 0.2588 (0.3306) time: 0.6008 data: 0.0032 max mem: 30263 +train: [0] [780/800] eta: 0:00:13 lr: 0.000058 loss: 1.1478 (1.2911) grad: 0.2587 (0.3290) time: 0.6021 data: 0.0029 max mem: 30263 +train: [0] [799/800] eta: 0:00:00 lr: 0.000060 loss: 1.1512 (1.2890) grad: 0.2587 (0.3292) time: 0.8982 data: 0.3290 max mem: 30263 +train: [0] Total time: 0:08:49 (0.6623 s / it) +train: [0] Summary: lr: 0.000060 loss: 1.1512 (1.2890) grad: 0.2587 (0.3292) +eval (validation): [0] [ 0/14] eta: 0:01:27 time: 6.2571 data: 5.9647 max mem: 30263 +eval (validation): [0] [13/14] eta: 0:00:00 time: 0.8269 data: 0.4275 max mem: 30263 +eval (validation): [0] Total time: 0:00:11 (0.8468 s / it) +cv: [0] best hparam: (36, 1.0) (046) ('046_lr3.6e+01_wd1.0e+00') loss: 1.271 acc: 0.472 f1: 0.434 bacc: 0.480 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_age__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_age__patch__attn/checkpoint-best.pth +train: [1] [ 0/800] eta: 1:09:13 lr: nan time: 5.1918 data: 4.7565 max mem: 30263 +train: [1] [ 20/800] eta: 0:10:38 lr: 0.000061 loss: 1.2948 (1.2167) grad: 0.2576 (0.2692) time: 0.5995 data: 0.0035 max mem: 30263 +train: [1] [ 40/800] eta: 0:09:03 lr: 0.000063 loss: 1.2948 (1.3072) grad: 0.2576 (0.2738) time: 0.6058 data: 0.0032 max mem: 30263 +train: [1] [ 60/800] eta: 0:08:22 lr: 0.000064 loss: 1.1688 (1.2369) grad: 0.2893 (0.2799) time: 0.6079 data: 0.0027 max mem: 30263 +train: [1] [ 80/800] eta: 0:07:56 lr: 0.000066 loss: 1.1688 (1.2242) grad: 0.2893 (0.2893) time: 0.6087 data: 0.0035 max mem: 30263 +train: [1] [100/800] eta: 0:07:35 lr: 0.000067 loss: 1.1787 (1.2341) grad: 0.2905 (0.2914) time: 0.6044 data: 0.0033 max mem: 30263 +train: [1] [120/800] eta: 0:07:43 lr: 0.000069 loss: 1.1806 (1.2374) grad: 0.2944 (0.3002) time: 0.8390 data: 0.2655 max mem: 30263 +train: [1] [140/800] eta: 0:07:27 lr: 0.000070 loss: 1.2348 (1.2420) grad: 0.3038 (0.3049) time: 0.6597 data: 0.0481 max mem: 30263 +train: [1] [160/800] eta: 0:07:08 lr: 0.000072 loss: 1.2350 (1.2400) grad: 0.3104 (0.3044) time: 0.6045 data: 0.0024 max mem: 30263 +train: [1] [180/800] eta: 0:06:50 lr: 0.000073 loss: 1.2299 (1.2283) grad: 0.3281 (0.3047) time: 0.6040 data: 0.0039 max mem: 30263 +train: [1] [200/800] eta: 0:06:32 lr: 0.000075 loss: 1.1980 (1.2287) grad: 0.3113 (0.3067) time: 0.5878 data: 0.0030 max mem: 30263 +train: [1] [220/800] eta: 0:06:16 lr: 0.000076 loss: 1.2039 (1.2306) grad: 0.3113 (0.3073) time: 0.5988 data: 0.0033 max mem: 30263 +train: [1] [240/800] eta: 0:06:15 lr: 0.000078 loss: 1.1568 (1.2258) grad: 0.3113 (0.3068) time: 0.9073 data: 0.2981 max mem: 30263 +train: [1] [260/800] eta: 0:06:00 lr: 0.000079 loss: 1.1831 (1.2250) grad: 0.3086 (0.3074) time: 0.6302 data: 0.0315 max mem: 30263 +train: [1] [280/800] eta: 0:05:45 lr: 0.000081 loss: 1.1464 (1.2178) grad: 0.3129 (0.3118) time: 0.6179 data: 0.0020 max mem: 30263 +train: [1] [300/800] eta: 0:05:30 lr: 0.000082 loss: 1.1777 (1.2192) grad: 0.3275 (0.3192) time: 0.5996 data: 0.0031 max mem: 30263 +train: [1] [320/800] eta: 0:05:15 lr: 0.000084 loss: 1.1777 (1.2171) grad: 0.3167 (0.3187) time: 0.5992 data: 0.0032 max mem: 30263 +train: [1] [340/800] eta: 0:05:06 lr: 0.000085 loss: 1.1653 (1.2104) grad: 0.3106 (0.3203) time: 0.8399 data: 0.2735 max mem: 30263 +train: [1] [360/800] eta: 0:04:52 lr: 0.000087 loss: 1.1777 (1.2101) grad: 0.2989 (0.3182) time: 0.6063 data: 0.0037 max mem: 30263 +train: [1] [380/800] eta: 0:04:37 lr: 0.000088 loss: 1.1332 (1.1981) grad: 0.2791 (0.3171) time: 0.6011 data: 0.0028 max mem: 30263 +train: [1] [400/800] eta: 0:04:22 lr: 0.000090 loss: 1.0695 (1.1957) grad: 0.2791 (0.3178) time: 0.5907 data: 0.0041 max mem: 30263 +train: [1] [420/800] eta: 0:04:08 lr: 0.000091 loss: 1.1332 (1.1990) grad: 0.2968 (0.3192) time: 0.5865 data: 0.0023 max mem: 30263 +train: [1] [440/800] eta: 0:03:54 lr: 0.000093 loss: 1.1101 (1.2025) grad: 0.3167 (0.3188) time: 0.5925 data: 0.0029 max mem: 30263 +train: [1] [460/800] eta: 0:03:45 lr: 0.000094 loss: 1.1161 (1.1989) grad: 0.3277 (0.3189) time: 0.9026 data: 0.3361 max mem: 30263 +train: [1] [480/800] eta: 0:03:30 lr: 0.000096 loss: 1.1397 (1.1989) grad: 0.3321 (0.3213) time: 0.6001 data: 0.0030 max mem: 30263 +train: [1] [500/800] eta: 0:03:17 lr: 0.000097 loss: 1.1617 (1.1974) grad: 0.3167 (0.3206) time: 0.6370 data: 0.0490 max mem: 30263 +train: [1] [520/800] eta: 0:03:03 lr: 0.000099 loss: 1.1161 (1.1926) grad: 0.3033 (0.3190) time: 0.6048 data: 0.0051 max mem: 30263 +train: [1] [540/800] eta: 0:02:49 lr: 0.000100 loss: 1.1348 (1.1910) grad: 0.3070 (0.3188) time: 0.5897 data: 0.0027 max mem: 30263 +train: [1] [560/800] eta: 0:02:36 lr: 0.000102 loss: 1.1394 (1.1919) grad: 0.2685 (0.3175) time: 0.5710 data: 0.0031 max mem: 30263 +train: [1] [580/800] eta: 0:02:24 lr: 0.000103 loss: 1.1095 (1.1850) grad: 0.2696 (0.3173) time: 0.8703 data: 0.2699 max mem: 30263 +train: [1] [600/800] eta: 0:02:11 lr: 0.000105 loss: 1.1098 (1.1857) grad: 0.2981 (0.3180) time: 0.6376 data: 0.0184 max mem: 30263 +train: [1] [620/800] eta: 0:01:58 lr: 0.000106 loss: 1.1098 (1.1844) grad: 0.2981 (0.3183) time: 0.6045 data: 0.0029 max mem: 30263 +train: [1] [640/800] eta: 0:01:44 lr: 0.000108 loss: 1.0681 (1.1803) grad: 0.2981 (0.3172) time: 0.5744 data: 0.0036 max mem: 30263 +train: [1] [660/800] eta: 0:01:31 lr: 0.000109 loss: 1.1279 (1.1857) grad: 0.2896 (0.3165) time: 0.6096 data: 0.0034 max mem: 30263 +train: [1] [680/800] eta: 0:01:18 lr: 0.000111 loss: 1.1496 (1.1854) grad: 0.2896 (0.3180) time: 0.8459 data: 0.2640 max mem: 30263 +train: [1] [700/800] eta: 0:01:05 lr: 0.000112 loss: 1.1383 (1.1854) grad: 0.2896 (0.3178) time: 0.6149 data: 0.0033 max mem: 30263 +train: [1] [720/800] eta: 0:00:52 lr: 0.000114 loss: 1.1599 (1.1869) grad: 0.2969 (0.3189) time: 0.6520 data: 0.0039 max mem: 30263 +train: [1] [740/800] eta: 0:00:39 lr: 0.000115 loss: 1.1599 (1.1868) grad: 0.3266 (0.3205) time: 0.6118 data: 0.0036 max mem: 30263 +train: [1] [760/800] eta: 0:00:26 lr: 0.000117 loss: 1.1106 (1.1910) grad: 0.3511 (0.3237) time: 0.5964 data: 0.0032 max mem: 30263 +train: [1] [780/800] eta: 0:00:13 lr: 0.000118 loss: 1.1599 (1.1905) grad: 0.3669 (0.3254) time: 0.5978 data: 0.0034 max mem: 30263 +train: [1] [799/800] eta: 0:00:00 lr: 0.000120 loss: 1.1650 (1.1873) grad: 0.3682 (0.3267) time: 0.8149 data: 0.2662 max mem: 30263 +train: [1] Total time: 0:08:45 (0.6573 s / it) +train: [1] Summary: lr: 0.000120 loss: 1.1650 (1.1873) grad: 0.3682 (0.3267) +eval (validation): [1] [ 0/14] eta: 0:01:13 time: 5.2267 data: 4.9085 max mem: 30263 +eval (validation): [1] [13/14] eta: 0:00:00 time: 0.7969 data: 0.3934 max mem: 30263 +eval (validation): [1] Total time: 0:00:11 (0.8142 s / it) +cv: [1] best hparam: (22, 1.0) (043) ('043_lr2.2e+01_wd1.0e+00') loss: 1.310 acc: 0.491 f1: 0.484 bacc: 0.481 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_age__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_age__patch__attn/checkpoint-best.pth +train: [2] [ 0/800] eta: 1:12:11 lr: nan time: 5.4148 data: 4.9610 max mem: 30263 +train: [2] [ 20/800] eta: 0:10:38 lr: 0.000121 loss: 1.2616 (1.3825) grad: 0.3568 (0.3467) time: 0.5884 data: 0.0130 max mem: 30263 +train: [2] [ 40/800] eta: 0:09:23 lr: 0.000123 loss: 1.1307 (1.2767) grad: 0.3568 (0.3811) time: 0.6595 data: 0.0552 max mem: 30263 +train: [2] [ 60/800] eta: 0:08:39 lr: 0.000124 loss: 1.2117 (1.2222) grad: 0.3551 (0.3703) time: 0.6223 data: 0.0207 max mem: 30263 +train: [2] [ 80/800] eta: 0:08:05 lr: 0.000126 loss: 1.1281 (1.1838) grad: 0.3551 (0.3768) time: 0.5901 data: 0.0020 max mem: 30263 +train: [2] [100/800] eta: 0:07:40 lr: 0.000127 loss: 1.1035 (1.1598) grad: 0.3348 (0.3813) time: 0.5931 data: 0.0034 max mem: 30263 +train: [2] [120/800] eta: 0:07:55 lr: 0.000129 loss: 1.0190 (1.1542) grad: 0.3427 (0.3848) time: 0.9074 data: 0.3302 max mem: 30263 +train: [2] [140/800] eta: 0:07:31 lr: 0.000130 loss: 1.0190 (1.1447) grad: 0.3985 (0.3903) time: 0.5922 data: 0.0055 max mem: 30263 +train: [2] [160/800] eta: 0:07:11 lr: 0.000132 loss: 1.1012 (1.1591) grad: 0.4454 (0.4068) time: 0.6075 data: 0.0144 max mem: 30263 +train: [2] [180/800] eta: 0:06:52 lr: 0.000133 loss: 1.0541 (1.1433) grad: 0.4249 (0.4036) time: 0.5917 data: 0.0027 max mem: 30263 +train: [2] [200/800] eta: 0:06:33 lr: 0.000135 loss: 1.1012 (1.1485) grad: 0.3990 (0.4056) time: 0.5720 data: 0.0035 max mem: 30263 +train: [2] [220/800] eta: 0:06:16 lr: 0.000136 loss: 1.1143 (1.1432) grad: 0.3990 (0.4021) time: 0.5871 data: 0.0032 max mem: 30263 +train: [2] [240/800] eta: 0:06:15 lr: 0.000138 loss: 1.1143 (1.1505) grad: 0.3984 (0.4009) time: 0.9030 data: 0.2722 max mem: 30263 +train: [2] [260/800] eta: 0:05:59 lr: 0.000139 loss: 1.1720 (1.1458) grad: 0.3800 (0.3982) time: 0.5961 data: 0.0033 max mem: 30263 +train: [2] [280/800] eta: 0:05:43 lr: 0.000141 loss: 1.1293 (1.1504) grad: 0.3524 (0.3974) time: 0.6045 data: 0.0035 max mem: 30263 +train: [2] [300/800] eta: 0:05:28 lr: 0.000142 loss: 1.1720 (1.1470) grad: 0.3800 (0.3972) time: 0.5997 data: 0.0035 max mem: 30263 +train: [2] [320/800] eta: 0:05:14 lr: 0.000144 loss: 1.1286 (1.1438) grad: 0.3752 (0.3971) time: 0.6167 data: 0.0037 max mem: 30263 +train: [2] [340/800] eta: 0:05:06 lr: 0.000145 loss: 1.1293 (1.1562) grad: 0.3998 (0.3970) time: 0.8456 data: 0.2747 max mem: 30263 +train: [2] [360/800] eta: 0:04:51 lr: 0.000147 loss: 1.0943 (1.1415) grad: 0.3998 (0.3984) time: 0.6131 data: 0.0029 max mem: 30263 +train: [2] [380/800] eta: 0:04:36 lr: 0.000148 loss: 1.0943 (1.1450) grad: 0.3752 (0.3995) time: 0.5951 data: 0.0032 max mem: 30263 +train: [2] [400/800] eta: 0:04:22 lr: 0.000150 loss: 1.0849 (1.1402) grad: 0.3998 (0.4034) time: 0.6004 data: 0.0033 max mem: 30263 +train: [2] [420/800] eta: 0:04:08 lr: 0.000151 loss: 1.0238 (1.1388) grad: 0.3964 (0.4038) time: 0.6058 data: 0.0033 max mem: 30263 +train: [2] [440/800] eta: 0:03:54 lr: 0.000153 loss: 1.1505 (1.1465) grad: 0.4054 (0.4054) time: 0.6033 data: 0.0034 max mem: 30263 +train: [2] [460/800] eta: 0:03:44 lr: 0.000154 loss: 1.1505 (1.1430) grad: 0.4217 (0.4064) time: 0.8586 data: 0.2856 max mem: 30263 +train: [2] [480/800] eta: 0:03:31 lr: 0.000156 loss: 1.1505 (1.1372) grad: 0.4087 (0.4104) time: 0.6976 data: 0.0254 max mem: 30263 +train: [2] [500/800] eta: 0:03:17 lr: 0.000157 loss: 1.1505 (1.1397) grad: 0.4081 (0.4080) time: 0.6062 data: 0.0026 max mem: 30263 +train: [2] [520/800] eta: 0:03:04 lr: 0.000159 loss: 1.1385 (1.1388) grad: 0.3865 (0.4069) time: 0.6378 data: 0.0040 max mem: 30263 +train: [2] [540/800] eta: 0:02:50 lr: 0.000160 loss: 1.0670 (1.1354) grad: 0.3865 (0.4079) time: 0.5807 data: 0.0036 max mem: 30263 +train: [2] [560/800] eta: 0:02:36 lr: 0.000162 loss: 1.0670 (1.1349) grad: 0.3711 (0.4067) time: 0.5859 data: 0.0032 max mem: 30263 +train: [2] [580/800] eta: 0:02:25 lr: 0.000163 loss: 1.0560 (1.1327) grad: 0.3711 (0.4069) time: 0.9168 data: 0.2896 max mem: 30263 +train: [2] [600/800] eta: 0:02:12 lr: 0.000165 loss: 1.0024 (1.1303) grad: 0.3912 (0.4090) time: 0.5981 data: 0.0037 max mem: 30263 +train: [2] [620/800] eta: 0:01:58 lr: 0.000166 loss: 1.0470 (1.1325) grad: 0.4050 (0.4117) time: 0.6161 data: 0.0031 max mem: 30263 +train: [2] [640/800] eta: 0:01:45 lr: 0.000168 loss: 1.0532 (1.1347) grad: 0.4643 (0.4147) time: 0.6120 data: 0.0037 max mem: 30263 +train: [2] [660/800] eta: 0:01:31 lr: 0.000169 loss: 0.9866 (1.1332) grad: 0.4676 (0.4170) time: 0.5970 data: 0.0034 max mem: 30263 +train: [2] [680/800] eta: 0:01:19 lr: 0.000171 loss: 0.9866 (1.1315) grad: 0.4765 (0.4188) time: 0.8182 data: 0.2641 max mem: 30263 +train: [2] [700/800] eta: 0:01:05 lr: 0.000172 loss: 1.0234 (1.1331) grad: 0.4628 (0.4220) time: 0.6250 data: 0.0028 max mem: 30263 +train: [2] [720/800] eta: 0:00:52 lr: 0.000174 loss: 1.0234 (1.1326) grad: 0.4628 (0.4269) time: 0.6207 data: 0.0035 max mem: 30263 +train: [2] [740/800] eta: 0:00:39 lr: 0.000175 loss: 1.1399 (1.1378) grad: 0.5018 (0.4301) time: 0.6209 data: 0.0036 max mem: 30263 +train: [2] [760/800] eta: 0:00:26 lr: 0.000177 loss: 1.1755 (1.1370) grad: 0.5028 (0.4323) time: 0.5974 data: 0.0035 max mem: 30263 +train: [2] [780/800] eta: 0:00:13 lr: 0.000178 loss: 1.2315 (1.1387) grad: 0.5004 (0.4345) time: 0.6087 data: 0.0034 max mem: 30263 +train: [2] [799/800] eta: 0:00:00 lr: 0.000180 loss: 1.2436 (1.1433) grad: 0.5028 (0.4375) time: 0.9075 data: 0.2693 max mem: 30263 +train: [2] Total time: 0:08:49 (0.6613 s / it) +train: [2] Summary: lr: 0.000180 loss: 1.2436 (1.1433) grad: 0.5028 (0.4375) +eval (validation): [2] [ 0/14] eta: 0:01:14 time: 5.2921 data: 4.9364 max mem: 30263 +eval (validation): [2] [13/14] eta: 0:00:00 time: 0.7742 data: 0.3782 max mem: 30263 +eval (validation): [2] Total time: 0:00:11 (0.7915 s / it) +cv: [2] best hparam: (2.7, 1.0) (030) ('030_lr2.7e+00_wd1.0e+00') loss: 1.203 acc: 0.509 f1: 0.497 bacc: 0.506 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_age__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_age__patch__attn/checkpoint-best.pth +train: [3] [ 0/800] eta: 1:11:52 lr: nan time: 5.3907 data: 4.9629 max mem: 30263 +train: [3] [ 20/800] eta: 0:10:49 lr: 0.000181 loss: 0.9933 (1.1056) grad: 0.5388 (0.5654) time: 0.6046 data: 0.0245 max mem: 30263 +train: [3] [ 40/800] eta: 0:09:25 lr: 0.000183 loss: 0.9808 (1.0586) grad: 0.5257 (0.5335) time: 0.6519 data: 0.0427 max mem: 30263 +train: [3] [ 60/800] eta: 0:08:36 lr: 0.000184 loss: 0.9808 (1.0353) grad: 0.5270 (0.5218) time: 0.6013 data: 0.0030 max mem: 30263 +train: [3] [ 80/800] eta: 0:08:01 lr: 0.000186 loss: 0.9933 (1.0463) grad: 0.5270 (0.5513) time: 0.5837 data: 0.0024 max mem: 30263 +train: [3] [100/800] eta: 0:07:38 lr: 0.000187 loss: 1.0335 (1.0927) grad: 0.5270 (0.5669) time: 0.5973 data: 0.0033 max mem: 30263 +train: [3] [120/800] eta: 0:07:46 lr: 0.000189 loss: 1.0500 (1.1198) grad: 0.5288 (0.5677) time: 0.8442 data: 0.2717 max mem: 30263 +train: [3] [140/800] eta: 0:07:26 lr: 0.000190 loss: 1.0704 (1.1355) grad: 0.5930 (0.5907) time: 0.6173 data: 0.0032 max mem: 30263 +train: [3] [160/800] eta: 0:07:08 lr: 0.000192 loss: 1.1874 (1.1286) grad: 0.6157 (0.5895) time: 0.6139 data: 0.0035 max mem: 30263 +train: [3] [180/800] eta: 0:06:49 lr: 0.000193 loss: 1.1932 (1.1495) grad: 0.6425 (0.6131) time: 0.5936 data: 0.0029 max mem: 30263 +train: [3] [200/800] eta: 0:06:32 lr: 0.000195 loss: 1.1932 (1.1708) grad: 0.6935 (0.6333) time: 0.5922 data: 0.0034 max mem: 30263 +train: [3] [220/800] eta: 0:06:16 lr: 0.000196 loss: 1.2090 (1.1822) grad: 0.6935 (0.6466) time: 0.6014 data: 0.0035 max mem: 30263 +train: [3] [240/800] eta: 0:06:15 lr: 0.000198 loss: 1.2795 (1.2011) grad: 0.6935 (0.6490) time: 0.9053 data: 0.2777 max mem: 30263 +train: [3] [260/800] eta: 0:05:58 lr: 0.000199 loss: 1.3041 (1.2170) grad: 0.6859 (0.6682) time: 0.5774 data: 0.0033 max mem: 30263 +train: [3] [280/800] eta: 0:05:41 lr: 0.000201 loss: 1.3018 (1.2119) grad: 0.7064 (0.6835) time: 0.5822 data: 0.0036 max mem: 30263 +train: [3] [300/800] eta: 0:05:26 lr: 0.000202 loss: 1.3207 (1.2192) grad: 0.8344 (0.7044) time: 0.5884 data: 0.0036 max mem: 30263 +train: [3] [320/800] eta: 0:05:11 lr: 0.000204 loss: 1.2677 (1.2097) grad: 0.8967 (0.7082) time: 0.5987 data: 0.0029 max mem: 30263 +WARNING: classifier 48 (50, 1.0) diverged (loss=30.25 > 27.73) at step 684. Freezing. +train: [3] [340/800] eta: 0:05:04 lr: 0.000205 loss: 1.2308 (1.2112) grad: 0.8302 (0.7159) time: 0.8523 data: 0.2744 max mem: 30263 +train: [3] [360/800] eta: 0:04:50 lr: 0.000207 loss: 1.0233 (1.2036) grad: 0.6713 (0.7069) time: 0.6605 data: 0.0036 max mem: 30263 +train: [3] [380/800] eta: 0:04:36 lr: 0.000208 loss: 0.9774 (1.1886) grad: 0.5930 (0.6961) time: 0.5891 data: 0.0033 max mem: 30263 +train: [3] [400/800] eta: 0:04:21 lr: 0.000210 loss: 1.0164 (1.1900) grad: 0.5517 (0.6875) time: 0.5877 data: 0.0037 max mem: 30263 +train: [3] [420/800] eta: 0:04:07 lr: 0.000211 loss: 0.9565 (1.1837) grad: 0.5272 (0.6820) time: 0.6113 data: 0.0033 max mem: 30263 +train: [3] [440/800] eta: 0:03:53 lr: 0.000213 loss: 1.1509 (1.1853) grad: 0.5328 (0.6848) time: 0.5853 data: 0.0035 max mem: 30263 +train: [3] [460/800] eta: 0:03:44 lr: 0.000214 loss: 1.1509 (1.1749) grad: 0.5517 (0.6791) time: 0.8847 data: 0.2752 max mem: 30263 +train: [3] [480/800] eta: 0:03:30 lr: 0.000216 loss: 1.0063 (1.1708) grad: 0.5540 (0.6750) time: 0.6168 data: 0.0035 max mem: 30263 +train: [3] [500/800] eta: 0:03:16 lr: 0.000217 loss: 1.0672 (1.1669) grad: 0.5993 (0.6742) time: 0.6252 data: 0.0044 max mem: 30263 +train: [3] [520/800] eta: 0:03:03 lr: 0.000219 loss: 1.0063 (1.1613) grad: 0.5993 (0.6716) time: 0.5967 data: 0.0032 max mem: 30263 +train: [3] [540/800] eta: 0:02:49 lr: 0.000220 loss: 1.0171 (1.1521) grad: 0.6192 (0.6718) time: 0.6016 data: 0.0040 max mem: 30263 +train: [3] [560/800] eta: 0:02:35 lr: 0.000222 loss: 1.0672 (1.1524) grad: 0.6262 (0.6728) time: 0.5894 data: 0.0029 max mem: 30263 +train: [3] [580/800] eta: 0:02:24 lr: 0.000223 loss: 1.0591 (1.1488) grad: 0.6215 (0.6706) time: 0.9108 data: 0.3356 max mem: 30263 +train: [3] [600/800] eta: 0:02:11 lr: 0.000225 loss: 1.0591 (1.1476) grad: 0.6131 (0.6675) time: 0.6336 data: 0.0466 max mem: 30263 +train: [3] [620/800] eta: 0:01:58 lr: 0.000226 loss: 1.1008 (1.1483) grad: 0.6027 (0.6667) time: 0.6008 data: 0.0026 max mem: 30263 +train: [3] [640/800] eta: 0:01:44 lr: 0.000228 loss: 1.0422 (1.1455) grad: 0.6027 (0.6660) time: 0.5755 data: 0.0035 max mem: 30263 +train: [3] [660/800] eta: 0:01:31 lr: 0.000229 loss: 1.1008 (1.1464) grad: 0.6537 (0.6694) time: 0.5930 data: 0.0023 max mem: 30263 +train: [3] [680/800] eta: 0:01:18 lr: 0.000231 loss: 1.1008 (1.1450) grad: 0.7007 (0.6746) time: 0.8190 data: 0.2573 max mem: 30263 +train: [3] [700/800] eta: 0:01:05 lr: 0.000232 loss: 1.0864 (1.1426) grad: 0.7601 (0.6841) time: 0.5943 data: 0.0032 max mem: 30263 +train: [3] [720/800] eta: 0:00:52 lr: 0.000234 loss: 1.1202 (1.1413) grad: 0.8069 (0.6881) time: 0.6288 data: 0.0210 max mem: 30263 +WARNING: classifier 47 (43, 1.0) diverged (loss=34.69 > 27.73) at step 782. Freezing. +train: [3] [740/800] eta: 0:00:39 lr: 0.000235 loss: 1.1202 (1.1450) grad: 0.8495 (0.7056) time: 0.5898 data: 0.0034 max mem: 30263 +train: [3] [760/800] eta: 0:00:26 lr: 0.000237 loss: 1.1302 (1.1441) grad: 0.8732 (0.7125) time: 0.6278 data: 0.0035 max mem: 30263 +train: [3] [780/800] eta: 0:00:13 lr: 0.000238 loss: 1.0992 (1.1414) grad: 0.8312 (0.7145) time: 0.6388 data: 0.0038 max mem: 30263 +train: [3] [799/800] eta: 0:00:00 lr: 0.000240 loss: 1.1302 (1.1416) grad: 0.8480 (0.7206) time: 0.8392 data: 0.2669 max mem: 30263 +train: [3] Total time: 0:08:45 (0.6571 s / it) +train: [3] Summary: lr: 0.000240 loss: 1.1302 (1.1416) grad: 0.8480 (0.7206) +eval (validation): [3] [ 0/14] eta: 0:01:15 time: 5.3583 data: 5.0390 max mem: 30263 +eval (validation): [3] [13/14] eta: 0:00:00 time: 0.7950 data: 0.3835 max mem: 30263 +eval (validation): [3] Total time: 0:00:11 (0.8102 s / it) +cv: [3] best hparam: (1, 1.0) (024) ('024_lr1.0e+00_wd1.0e+00') loss: 1.202 acc: 0.491 f1: 0.483 bacc: 0.487 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_age__patch__attn/checkpoint-last.pth +train: [4] [ 0/800] eta: 1:10:17 lr: nan time: 5.2725 data: 4.8280 max mem: 30263 +train: [4] [ 20/800] eta: 0:10:17 lr: 0.000241 loss: 1.3948 (1.3938) grad: 0.7458 (0.8159) time: 0.5675 data: 0.0124 max mem: 30263 +WARNING: classifier 46 (36, 1.0) diverged (loss=40.38 > 27.73) at step 808. Freezing. +train: [4] [ 40/800] eta: 0:08:52 lr: 0.000243 loss: 1.3398 (1.3770) grad: 0.7458 (0.8901) time: 0.6064 data: 0.0324 max mem: 30263 +train: [4] [ 60/800] eta: 0:08:22 lr: 0.000244 loss: 1.3274 (1.3530) grad: 0.7458 (0.8128) time: 0.6317 data: 0.0412 max mem: 30263 +train: [4] [ 80/800] eta: 0:07:54 lr: 0.000246 loss: 1.2403 (1.2905) grad: 0.7337 (0.7890) time: 0.6019 data: 0.0396 max mem: 30263 +train: [4] [100/800] eta: 0:07:32 lr: 0.000247 loss: 1.1837 (1.2379) grad: 0.7087 (0.7880) time: 0.5929 data: 0.0030 max mem: 30263 +train: [4] [120/800] eta: 0:07:40 lr: 0.000249 loss: 1.0647 (1.2188) grad: 0.7349 (0.7801) time: 0.8317 data: 0.2681 max mem: 30263 +train: [4] [140/800] eta: 0:07:16 lr: 0.000250 loss: 1.0292 (1.1994) grad: 0.7182 (0.7662) time: 0.5672 data: 0.0037 max mem: 30263 +train: [4] [160/800] eta: 0:07:00 lr: 0.000252 loss: 1.0292 (1.1732) grad: 0.7182 (0.7535) time: 0.6201 data: 0.0607 max mem: 30263 +train: [4] [180/800] eta: 0:06:43 lr: 0.000253 loss: 1.0291 (1.1470) grad: 0.6589 (0.7427) time: 0.6047 data: 0.0229 max mem: 30263 +train: [4] [200/800] eta: 0:06:27 lr: 0.000255 loss: 1.0142 (1.1400) grad: 0.6470 (0.7341) time: 0.5968 data: 0.0035 max mem: 30263 +train: [4] [220/800] eta: 0:06:11 lr: 0.000256 loss: 0.9975 (1.1381) grad: 0.6470 (0.7336) time: 0.5845 data: 0.0033 max mem: 30263 +train: [4] [240/800] eta: 0:06:08 lr: 0.000258 loss: 0.9359 (1.1197) grad: 0.6589 (0.7302) time: 0.8629 data: 0.2796 max mem: 30263 +train: [4] [260/800] eta: 0:05:51 lr: 0.000259 loss: 1.0434 (1.1228) grad: 0.6799 (0.7285) time: 0.5717 data: 0.0037 max mem: 30263 +train: [4] [280/800] eta: 0:05:36 lr: 0.000261 loss: 1.0464 (1.1340) grad: 0.7127 (0.7373) time: 0.5852 data: 0.0024 max mem: 30263 +train: [4] [300/800] eta: 0:05:21 lr: 0.000262 loss: 1.0464 (1.1247) grad: 0.7127 (0.7342) time: 0.5904 data: 0.0029 max mem: 30263 +WARNING: classifier 45 (31, 1.0) diverged (loss=29.23 > 27.73) at step 878. Freezing. +train: [4] [320/800] eta: 0:05:06 lr: 0.000264 loss: 1.0938 (1.1295) grad: 0.7485 (0.7310) time: 0.5779 data: 0.0033 max mem: 30263 +train: [4] [340/800] eta: 0:04:59 lr: 0.000265 loss: 1.0705 (1.1272) grad: 0.6878 (0.7223) time: 0.8299 data: 0.2742 max mem: 30263 +train: [4] [360/800] eta: 0:04:45 lr: 0.000267 loss: 1.0529 (1.1176) grad: 0.6198 (0.7154) time: 0.6055 data: 0.0035 max mem: 30263 +train: [4] [380/800] eta: 0:04:30 lr: 0.000268 loss: 1.0633 (1.1133) grad: 0.5488 (0.7065) time: 0.5736 data: 0.0033 max mem: 30263 +train: [4] [400/800] eta: 0:04:17 lr: 0.000270 loss: 0.9947 (1.1099) grad: 0.5488 (0.7065) time: 0.6474 data: 0.0040 max mem: 30263 +train: [4] [420/800] eta: 0:04:04 lr: 0.000271 loss: 0.8989 (1.1005) grad: 0.5919 (0.7036) time: 0.6039 data: 0.0035 max mem: 30263 +WARNING: classifier 44 (26, 1.0) diverged (loss=51.94 > 27.73) at step 907. Freezing. +train: [4] [440/800] eta: 0:03:50 lr: 0.000273 loss: 0.8910 (1.1076) grad: 0.5919 (0.6979) time: 0.5789 data: 0.0034 max mem: 30263 +train: [4] [460/800] eta: 0:03:40 lr: 0.000274 loss: 0.8816 (1.0997) grad: 0.5919 (0.6865) time: 0.8453 data: 0.2791 max mem: 30263 +train: [4] [480/800] eta: 0:03:27 lr: 0.000276 loss: 0.8753 (1.0895) grad: 0.4320 (0.6741) time: 0.6578 data: 0.0034 max mem: 30263 +train: [4] [500/800] eta: 0:03:13 lr: 0.000277 loss: 0.8984 (1.0843) grad: 0.4026 (0.6634) time: 0.5865 data: 0.0034 max mem: 30263 +train: [4] [520/800] eta: 0:03:00 lr: 0.000279 loss: 0.8984 (1.0782) grad: 0.3886 (0.6531) time: 0.5790 data: 0.0035 max mem: 30263 +train: [4] [540/800] eta: 0:02:46 lr: 0.000280 loss: 0.8753 (1.0733) grad: 0.3963 (0.6454) time: 0.5693 data: 0.0031 max mem: 30263 +train: [4] [560/800] eta: 0:02:33 lr: 0.000282 loss: 0.9242 (1.0670) grad: 0.4026 (0.6374) time: 0.5701 data: 0.0033 max mem: 30263 +train: [4] [580/800] eta: 0:02:22 lr: 0.000283 loss: 0.8942 (1.0598) grad: 0.4054 (0.6306) time: 0.8899 data: 0.2965 max mem: 30263 +train: [4] [600/800] eta: 0:02:08 lr: 0.000285 loss: 0.9034 (1.0568) grad: 0.4054 (0.6220) time: 0.5804 data: 0.0034 max mem: 30263 +train: [4] [620/800] eta: 0:01:55 lr: 0.000286 loss: 0.8942 (1.0503) grad: 0.4054 (0.6170) time: 0.6339 data: 0.0036 max mem: 30263 +train: [4] [640/800] eta: 0:01:43 lr: 0.000288 loss: 0.8648 (1.0475) grad: 0.4256 (0.6112) time: 0.6351 data: 0.0040 max mem: 30263 +train: [4] [660/800] eta: 0:01:30 lr: 0.000289 loss: 0.8643 (1.0466) grad: 0.4383 (0.6078) time: 0.6485 data: 0.0043 max mem: 30263 +train: [4] [680/800] eta: 0:01:18 lr: 0.000291 loss: 0.8562 (1.0405) grad: 0.4731 (0.6035) time: 0.8549 data: 0.2747 max mem: 30263 +train: [4] [700/800] eta: 0:01:04 lr: 0.000292 loss: 0.8562 (1.0359) grad: 0.4763 (0.5998) time: 0.5922 data: 0.0189 max mem: 30263 +train: [4] [720/800] eta: 0:00:51 lr: 0.000294 loss: 0.8392 (1.0321) grad: 0.4944 (0.5980) time: 0.6125 data: 0.0387 max mem: 30263 +train: [4] [740/800] eta: 0:00:38 lr: 0.000295 loss: 0.8054 (1.0241) grad: 0.4763 (0.5939) time: 0.5733 data: 0.0028 max mem: 30263 +train: [4] [760/800] eta: 0:00:25 lr: 0.000297 loss: 0.8315 (1.0243) grad: 0.5049 (0.5930) time: 0.5863 data: 0.0035 max mem: 30263 +train: [4] [780/800] eta: 0:00:12 lr: 0.000298 loss: 0.8315 (1.0222) grad: 0.5049 (0.5902) time: 0.5948 data: 0.0033 max mem: 30263 +train: [4] [799/800] eta: 0:00:00 lr: 0.000300 loss: 0.8511 (1.0177) grad: 0.4888 (0.5871) time: 0.8207 data: 0.2607 max mem: 30263 +train: [4] Total time: 0:08:38 (0.6478 s / it) +train: [4] Summary: lr: 0.000300 loss: 0.8511 (1.0177) grad: 0.4888 (0.5871) +eval (validation): [4] [ 0/14] eta: 0:01:13 time: 5.2245 data: 4.8748 max mem: 30263 +eval (validation): [4] [13/14] eta: 0:00:00 time: 0.7828 data: 0.3699 max mem: 30263 +eval (validation): [4] Total time: 0:00:11 (0.8004 s / it) +cv: [4] best hparam: (1.6, 1.0) (027) ('027_lr1.6e+00_wd1.0e+00') loss: 1.357 acc: 0.547 f1: 0.499 bacc: 0.531 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_age__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_age__patch__attn/checkpoint-best.pth +train: [5] [ 0/800] eta: 1:14:15 lr: nan time: 5.5699 data: 5.0823 max mem: 30263 +train: [5] [ 20/800] eta: 0:11:02 lr: 0.000300 loss: 0.7116 (0.8064) grad: 0.5331 (0.5484) time: 0.6133 data: 0.0047 max mem: 30263 +train: [5] [ 40/800] eta: 0:09:07 lr: 0.000300 loss: 0.7602 (0.8347) grad: 0.4095 (0.4697) time: 0.5853 data: 0.0037 max mem: 30263 +train: [5] [ 60/800] eta: 0:08:21 lr: 0.000300 loss: 0.7989 (0.8696) grad: 0.4328 (0.4741) time: 0.5910 data: 0.0040 max mem: 30263 +train: [5] [ 80/800] eta: 0:07:48 lr: 0.000300 loss: 0.7989 (0.8758) grad: 0.4328 (0.4725) time: 0.5657 data: 0.0028 max mem: 30263 +train: [5] [100/800] eta: 0:07:20 lr: 0.000300 loss: 0.8998 (0.8984) grad: 0.4218 (0.4870) time: 0.5451 data: 0.0030 max mem: 30263 +train: [5] [120/800] eta: 0:07:31 lr: 0.000300 loss: 0.9302 (0.9004) grad: 0.4700 (0.4868) time: 0.8412 data: 0.2733 max mem: 30263 +train: [5] [140/800] eta: 0:07:14 lr: 0.000300 loss: 0.9241 (0.8957) grad: 0.4700 (0.4775) time: 0.6242 data: 0.0044 max mem: 30263 +train: [5] [160/800] eta: 0:06:54 lr: 0.000300 loss: 0.9439 (0.9122) grad: 0.4955 (0.4810) time: 0.5745 data: 0.0033 max mem: 30263 +train: [5] [180/800] eta: 0:06:37 lr: 0.000300 loss: 0.9210 (0.9073) grad: 0.4871 (0.4741) time: 0.5888 data: 0.0033 max mem: 30263 +train: [5] [200/800] eta: 0:06:25 lr: 0.000300 loss: 0.8589 (0.8939) grad: 0.4500 (0.4697) time: 0.6525 data: 0.0042 max mem: 30263 +train: [5] [220/800] eta: 0:06:08 lr: 0.000300 loss: 0.8589 (0.8967) grad: 0.4500 (0.4660) time: 0.5628 data: 0.0032 max mem: 30263 +train: [5] [240/800] eta: 0:06:08 lr: 0.000300 loss: 0.8541 (0.9012) grad: 0.4388 (0.4746) time: 0.9105 data: 0.3374 max mem: 30263 +train: [5] [260/800] eta: 0:05:51 lr: 0.000300 loss: 0.8317 (0.8971) grad: 0.4388 (0.4751) time: 0.5697 data: 0.0029 max mem: 30263 +train: [5] [280/800] eta: 0:05:36 lr: 0.000300 loss: 0.8613 (0.8905) grad: 0.4543 (0.4794) time: 0.5852 data: 0.0030 max mem: 30263 +train: [5] [300/800] eta: 0:05:21 lr: 0.000300 loss: 0.8664 (0.8942) grad: 0.5229 (0.4902) time: 0.5954 data: 0.0035 max mem: 30263 +train: [5] [320/800] eta: 0:05:07 lr: 0.000299 loss: 0.8023 (0.8949) grad: 0.5318 (0.4940) time: 0.5903 data: 0.0044 max mem: 30263 +train: [5] [340/800] eta: 0:04:59 lr: 0.000299 loss: 0.8967 (0.9056) grad: 0.5569 (0.5037) time: 0.8382 data: 0.2719 max mem: 30263 +train: [5] [360/800] eta: 0:04:47 lr: 0.000299 loss: 0.9316 (0.8998) grad: 0.5724 (0.5109) time: 0.6769 data: 0.0393 max mem: 30263 +train: [5] [380/800] eta: 0:04:33 lr: 0.000299 loss: 0.9376 (0.9030) grad: 0.6231 (0.5182) time: 0.6180 data: 0.0036 max mem: 30263 +train: [5] [400/800] eta: 0:04:19 lr: 0.000299 loss: 0.9793 (0.9064) grad: 0.6428 (0.5207) time: 0.5965 data: 0.0031 max mem: 30263 +train: [5] [420/800] eta: 0:04:05 lr: 0.000299 loss: 0.9661 (0.9177) grad: 0.6337 (0.5244) time: 0.5981 data: 0.0034 max mem: 30263 +train: [5] [440/800] eta: 0:03:51 lr: 0.000299 loss: 0.9715 (0.9148) grad: 0.5797 (0.5274) time: 0.5539 data: 0.0025 max mem: 30263 +train: [5] [460/800] eta: 0:03:42 lr: 0.000299 loss: 0.9661 (0.9192) grad: 0.5736 (0.5289) time: 0.8994 data: 0.2733 max mem: 30263 +train: [5] [480/800] eta: 0:03:28 lr: 0.000299 loss: 0.9661 (0.9200) grad: 0.5525 (0.5283) time: 0.6405 data: 0.0058 max mem: 30263 +train: [5] [500/800] eta: 0:03:14 lr: 0.000299 loss: 0.8725 (0.9128) grad: 0.5091 (0.5257) time: 0.5796 data: 0.0036 max mem: 30263 +train: [5] [520/800] eta: 0:03:01 lr: 0.000299 loss: 0.8750 (0.9155) grad: 0.5049 (0.5274) time: 0.5924 data: 0.0035 max mem: 30263 +train: [5] [540/800] eta: 0:02:47 lr: 0.000299 loss: 0.8750 (0.9147) grad: 0.5049 (0.5299) time: 0.5875 data: 0.0038 max mem: 30263 +train: [5] [560/800] eta: 0:02:34 lr: 0.000298 loss: 0.8395 (0.9106) grad: 0.5239 (0.5280) time: 0.5448 data: 0.0026 max mem: 30263 +train: [5] [580/800] eta: 0:02:23 lr: 0.000298 loss: 0.8395 (0.9077) grad: 0.5360 (0.5288) time: 0.9247 data: 0.3352 max mem: 30263 +train: [5] [600/800] eta: 0:02:09 lr: 0.000298 loss: 0.8824 (0.9106) grad: 0.5318 (0.5277) time: 0.5773 data: 0.0034 max mem: 30263 +train: [5] [620/800] eta: 0:01:56 lr: 0.000298 loss: 0.8421 (0.9081) grad: 0.5115 (0.5255) time: 0.5697 data: 0.0035 max mem: 30263 +train: [5] [640/800] eta: 0:01:43 lr: 0.000298 loss: 0.8087 (0.9015) grad: 0.4719 (0.5221) time: 0.6345 data: 0.0036 max mem: 30263 +train: [5] [660/800] eta: 0:01:30 lr: 0.000298 loss: 0.8087 (0.8989) grad: 0.4652 (0.5206) time: 0.6178 data: 0.0035 max mem: 30263 +train: [5] [680/800] eta: 0:01:18 lr: 0.000298 loss: 0.7440 (0.8961) grad: 0.4516 (0.5199) time: 0.9344 data: 0.3549 max mem: 30263 +train: [5] [700/800] eta: 0:01:05 lr: 0.000298 loss: 0.7568 (0.8936) grad: 0.4719 (0.5195) time: 0.6816 data: 0.0419 max mem: 30263 +train: [5] [720/800] eta: 0:00:52 lr: 0.000297 loss: 0.7961 (0.8918) grad: 0.4895 (0.5179) time: 0.5682 data: 0.0035 max mem: 30263 +train: [5] [740/800] eta: 0:00:39 lr: 0.000297 loss: 0.7440 (0.8866) grad: 0.5022 (0.5184) time: 0.6081 data: 0.0303 max mem: 30263 +train: [5] [760/800] eta: 0:00:25 lr: 0.000297 loss: 0.8080 (0.8862) grad: 0.5098 (0.5180) time: 0.5911 data: 0.0028 max mem: 30263 +train: [5] [780/800] eta: 0:00:12 lr: 0.000297 loss: 0.8136 (0.8866) grad: 0.4842 (0.5195) time: 0.5494 data: 0.0030 max mem: 30263 +train: [5] [799/800] eta: 0:00:00 lr: 0.000297 loss: 0.8136 (0.8873) grad: 0.4842 (0.5192) time: 0.8562 data: 0.2818 max mem: 30263 +train: [5] Total time: 0:08:41 (0.6525 s / it) +train: [5] Summary: lr: 0.000297 loss: 0.8136 (0.8873) grad: 0.4842 (0.5192) +eval (validation): [5] [ 0/14] eta: 0:01:12 time: 5.1890 data: 4.8878 max mem: 30263 +eval (validation): [5] [13/14] eta: 0:00:00 time: 0.7608 data: 0.3798 max mem: 30263 +eval (validation): [5] Total time: 0:00:10 (0.7787 s / it) +cv: [5] best hparam: (1.4, 1.0) (026) ('026_lr1.4e+00_wd1.0e+00') loss: 1.666 acc: 0.509 f1: 0.420 bacc: 0.494 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_age__patch__attn/checkpoint-last.pth +train: [6] [ 0/800] eta: 1:10:28 lr: nan time: 5.2859 data: 4.8120 max mem: 30263 +train: [6] [ 20/800] eta: 0:11:51 lr: 0.000297 loss: 0.7373 (0.7603) grad: 0.4735 (0.4775) time: 0.6933 data: 0.0176 max mem: 30263 +train: [6] [ 40/800] eta: 0:09:37 lr: 0.000296 loss: 0.7371 (0.7621) grad: 0.4809 (0.5182) time: 0.6014 data: 0.0027 max mem: 30263 +train: [6] [ 60/800] eta: 0:08:54 lr: 0.000296 loss: 0.7545 (0.8011) grad: 0.4809 (0.5083) time: 0.6432 data: 0.0038 max mem: 30263 +train: [6] [ 80/800] eta: 0:08:14 lr: 0.000296 loss: 0.7373 (0.7872) grad: 0.4866 (0.5110) time: 0.5806 data: 0.0035 max mem: 30263 +train: [6] [100/800] eta: 0:07:49 lr: 0.000296 loss: 0.7291 (0.7824) grad: 0.5054 (0.5083) time: 0.6053 data: 0.0038 max mem: 30263 +train: [6] [120/800] eta: 0:07:56 lr: 0.000296 loss: 0.8203 (0.7976) grad: 0.4987 (0.5179) time: 0.8503 data: 0.2678 max mem: 30263 +train: [6] [140/800] eta: 0:07:36 lr: 0.000296 loss: 0.7097 (0.7798) grad: 0.5018 (0.5136) time: 0.6400 data: 0.0343 max mem: 30263 +train: [6] [160/800] eta: 0:07:15 lr: 0.000295 loss: 0.8184 (0.7950) grad: 0.4987 (0.5224) time: 0.5972 data: 0.0031 max mem: 30263 +train: [6] [180/800] eta: 0:06:54 lr: 0.000295 loss: 0.8451 (0.7995) grad: 0.5018 (0.5279) time: 0.5800 data: 0.0032 max mem: 30263 +train: [6] [200/800] eta: 0:06:35 lr: 0.000295 loss: 0.8116 (0.8066) grad: 0.5301 (0.5315) time: 0.5770 data: 0.0033 max mem: 30263 +train: [6] [220/800] eta: 0:06:19 lr: 0.000295 loss: 0.8704 (0.8136) grad: 0.5539 (0.5390) time: 0.5900 data: 0.0039 max mem: 30263 +train: [6] [240/800] eta: 0:06:18 lr: 0.000295 loss: 0.8141 (0.8144) grad: 0.5539 (0.5365) time: 0.9118 data: 0.2850 max mem: 30263 +train: [6] [260/800] eta: 0:05:59 lr: 0.000294 loss: 0.7663 (0.8025) grad: 0.5108 (0.5246) time: 0.5593 data: 0.0035 max mem: 30263 +train: [6] [280/800] eta: 0:05:43 lr: 0.000294 loss: 0.7031 (0.7965) grad: 0.4773 (0.5227) time: 0.5948 data: 0.0033 max mem: 30263 +train: [6] [300/800] eta: 0:05:28 lr: 0.000294 loss: 0.6989 (0.8009) grad: 0.4555 (0.5220) time: 0.5864 data: 0.0033 max mem: 30263 +train: [6] [320/800] eta: 0:05:12 lr: 0.000294 loss: 0.6656 (0.7918) grad: 0.4151 (0.5144) time: 0.5891 data: 0.0035 max mem: 30263 +train: [6] [340/800] eta: 0:05:05 lr: 0.000293 loss: 0.6831 (0.7883) grad: 0.4405 (0.5114) time: 0.8512 data: 0.2864 max mem: 30263 +train: [6] [360/800] eta: 0:04:51 lr: 0.000293 loss: 0.6914 (0.7826) grad: 0.3834 (0.5039) time: 0.6626 data: 0.0729 max mem: 30263 +train: [6] [380/800] eta: 0:04:36 lr: 0.000293 loss: 0.6831 (0.7766) grad: 0.3752 (0.4998) time: 0.5813 data: 0.0209 max mem: 30263 +train: [6] [400/800] eta: 0:04:22 lr: 0.000293 loss: 0.6914 (0.7763) grad: 0.3752 (0.4939) time: 0.6003 data: 0.0033 max mem: 30263 +train: [6] [420/800] eta: 0:04:07 lr: 0.000292 loss: 0.7429 (0.7791) grad: 0.3834 (0.4905) time: 0.5750 data: 0.0030 max mem: 30263 +train: [6] [440/800] eta: 0:03:53 lr: 0.000292 loss: 0.7498 (0.7782) grad: 0.3872 (0.4857) time: 0.5692 data: 0.0033 max mem: 30263 +train: [6] [460/800] eta: 0:03:43 lr: 0.000292 loss: 0.7246 (0.7736) grad: 0.3861 (0.4807) time: 0.8671 data: 0.2881 max mem: 30263 +train: [6] [480/800] eta: 0:03:30 lr: 0.000292 loss: 0.7246 (0.7730) grad: 0.3955 (0.4798) time: 0.6435 data: 0.0513 max mem: 30263 +train: [6] [500/800] eta: 0:03:16 lr: 0.000291 loss: 0.7124 (0.7756) grad: 0.3872 (0.4797) time: 0.5775 data: 0.0026 max mem: 30263 +train: [6] [520/800] eta: 0:03:02 lr: 0.000291 loss: 0.7460 (0.7754) grad: 0.4296 (0.4781) time: 0.5921 data: 0.0032 max mem: 30263 +train: [6] [540/800] eta: 0:02:48 lr: 0.000291 loss: 0.7714 (0.7786) grad: 0.4240 (0.4741) time: 0.5682 data: 0.0034 max mem: 30263 +train: [6] [560/800] eta: 0:02:35 lr: 0.000291 loss: 0.7556 (0.7750) grad: 0.4157 (0.4726) time: 0.5721 data: 0.0027 max mem: 30263 +train: [6] [580/800] eta: 0:02:23 lr: 0.000290 loss: 0.7061 (0.7720) grad: 0.4004 (0.4681) time: 0.8812 data: 0.3032 max mem: 30263 +train: [6] [600/800] eta: 0:02:10 lr: 0.000290 loss: 0.6511 (0.7675) grad: 0.3630 (0.4663) time: 0.6133 data: 0.0036 max mem: 30263 +train: [6] [620/800] eta: 0:01:57 lr: 0.000290 loss: 0.6511 (0.7663) grad: 0.3996 (0.4636) time: 0.5777 data: 0.0035 max mem: 30263 +train: [6] [640/800] eta: 0:01:43 lr: 0.000290 loss: 0.6604 (0.7641) grad: 0.3377 (0.4596) time: 0.5834 data: 0.0038 max mem: 30263 +train: [6] [660/800] eta: 0:01:30 lr: 0.000289 loss: 0.6753 (0.7599) grad: 0.3425 (0.4573) time: 0.5878 data: 0.0033 max mem: 30263 +train: [6] [680/800] eta: 0:01:18 lr: 0.000289 loss: 0.6826 (0.7584) grad: 0.3668 (0.4568) time: 0.8373 data: 0.2736 max mem: 30263 +train: [6] [700/800] eta: 0:01:05 lr: 0.000289 loss: 0.7132 (0.7592) grad: 0.3595 (0.4537) time: 0.6140 data: 0.0400 max mem: 30263 +train: [6] [720/800] eta: 0:00:51 lr: 0.000288 loss: 0.7149 (0.7587) grad: 0.3614 (0.4505) time: 0.5503 data: 0.0032 max mem: 30263 +train: [6] [740/800] eta: 0:00:38 lr: 0.000288 loss: 0.7444 (0.7586) grad: 0.3391 (0.4470) time: 0.5680 data: 0.0031 max mem: 30263 +train: [6] [760/800] eta: 0:00:25 lr: 0.000288 loss: 0.7450 (0.7594) grad: 0.3211 (0.4434) time: 0.5701 data: 0.0018 max mem: 30263 +train: [6] [780/800] eta: 0:00:12 lr: 0.000287 loss: 0.7444 (0.7581) grad: 0.3188 (0.4398) time: 0.5741 data: 0.0032 max mem: 30263 +train: [6] [799/800] eta: 0:00:00 lr: 0.000287 loss: 0.7444 (0.7568) grad: 0.3188 (0.4374) time: 0.8569 data: 0.2535 max mem: 30263 +train: [6] Total time: 0:08:38 (0.6481 s / it) +train: [6] Summary: lr: 0.000287 loss: 0.7444 (0.7568) grad: 0.3188 (0.4374) +eval (validation): [6] [ 0/14] eta: 0:01:11 time: 5.0737 data: 4.7569 max mem: 30263 +eval (validation): [6] [13/14] eta: 0:00:00 time: 0.7588 data: 0.3447 max mem: 30263 +eval (validation): [6] Total time: 0:00:10 (0.7765 s / it) +cv: [6] best hparam: (0.32, 1.0) (017) ('017_lr3.2e-01_wd1.0e+00') loss: 1.182 acc: 0.472 f1: 0.458 bacc: 0.464 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_age__patch__attn/checkpoint-last.pth +train: [7] [ 0/800] eta: 1:05:11 lr: nan time: 4.8894 data: 4.4000 max mem: 30263 +train: [7] [ 20/800] eta: 0:10:22 lr: 0.000287 loss: 0.6210 (0.6663) grad: 0.2939 (0.2967) time: 0.5933 data: 0.0035 max mem: 30263 +train: [7] [ 40/800] eta: 0:09:03 lr: 0.000286 loss: 0.5992 (0.6535) grad: 0.2939 (0.3134) time: 0.6285 data: 0.0033 max mem: 30263 +train: [7] [ 60/800] eta: 0:08:17 lr: 0.000286 loss: 0.6210 (0.6615) grad: 0.2939 (0.3018) time: 0.5857 data: 0.0032 max mem: 30263 +train: [7] [ 80/800] eta: 0:07:47 lr: 0.000286 loss: 0.6512 (0.6839) grad: 0.2974 (0.3036) time: 0.5801 data: 0.0034 max mem: 30263 +train: [7] [100/800] eta: 0:07:25 lr: 0.000285 loss: 0.6950 (0.6840) grad: 0.3099 (0.3091) time: 0.5817 data: 0.0035 max mem: 30263 +train: [7] [120/800] eta: 0:07:33 lr: 0.000285 loss: 0.7046 (0.6772) grad: 0.3140 (0.3181) time: 0.8223 data: 0.2530 max mem: 30263 +train: [7] [140/800] eta: 0:07:13 lr: 0.000285 loss: 0.7032 (0.6732) grad: 0.3280 (0.3234) time: 0.5904 data: 0.0032 max mem: 30263 +train: [7] [160/800] eta: 0:06:54 lr: 0.000284 loss: 0.7032 (0.6762) grad: 0.3140 (0.3157) time: 0.5816 data: 0.0029 max mem: 30263 +train: [7] [180/800] eta: 0:06:36 lr: 0.000284 loss: 0.6859 (0.6728) grad: 0.2966 (0.3112) time: 0.5731 data: 0.0034 max mem: 30263 +train: [7] [200/800] eta: 0:06:19 lr: 0.000284 loss: 0.6859 (0.6757) grad: 0.2565 (0.3051) time: 0.5702 data: 0.0034 max mem: 30263 +train: [7] [220/800] eta: 0:06:03 lr: 0.000283 loss: 0.6859 (0.6803) grad: 0.2565 (0.3027) time: 0.5764 data: 0.0034 max mem: 30263 +train: [7] [240/800] eta: 0:06:02 lr: 0.000283 loss: 0.6859 (0.6755) grad: 0.2744 (0.3009) time: 0.8746 data: 0.2531 max mem: 30263 +train: [7] [260/800] eta: 0:05:46 lr: 0.000283 loss: 0.6883 (0.6769) grad: 0.2744 (0.3001) time: 0.5811 data: 0.0033 max mem: 30263 +train: [7] [280/800] eta: 0:05:31 lr: 0.000282 loss: 0.6883 (0.6721) grad: 0.2866 (0.2995) time: 0.5785 data: 0.0034 max mem: 30263 +train: [7] [300/800] eta: 0:05:17 lr: 0.000282 loss: 0.6579 (0.6681) grad: 0.2879 (0.2966) time: 0.5833 data: 0.0034 max mem: 30263 +train: [7] [320/800] eta: 0:05:02 lr: 0.000282 loss: 0.6579 (0.6692) grad: 0.2866 (0.2973) time: 0.5728 data: 0.0034 max mem: 30263 +train: [7] [340/800] eta: 0:04:54 lr: 0.000281 loss: 0.6579 (0.6699) grad: 0.2757 (0.2934) time: 0.8111 data: 0.2587 max mem: 30263 +train: [7] [360/800] eta: 0:04:40 lr: 0.000281 loss: 0.6644 (0.6699) grad: 0.2496 (0.2900) time: 0.5868 data: 0.0029 max mem: 30263 +train: [7] [380/800] eta: 0:04:26 lr: 0.000280 loss: 0.6674 (0.6676) grad: 0.2496 (0.2883) time: 0.5751 data: 0.0026 max mem: 30263 +train: [7] [400/800] eta: 0:04:12 lr: 0.000280 loss: 0.6514 (0.6695) grad: 0.2189 (0.2886) time: 0.5779 data: 0.0030 max mem: 30263 +train: [7] [420/800] eta: 0:03:59 lr: 0.000280 loss: 0.6606 (0.6701) grad: 0.2258 (0.2871) time: 0.5731 data: 0.0035 max mem: 30263 +train: [7] [440/800] eta: 0:03:45 lr: 0.000279 loss: 0.6266 (0.6698) grad: 0.2630 (0.2861) time: 0.5722 data: 0.0034 max mem: 30263 +train: [7] [460/800] eta: 0:03:36 lr: 0.000279 loss: 0.6266 (0.6687) grad: 0.2717 (0.2859) time: 0.8692 data: 0.2640 max mem: 30263 +train: [7] [480/800] eta: 0:03:23 lr: 0.000278 loss: 0.6606 (0.6692) grad: 0.2420 (0.2827) time: 0.5992 data: 0.0033 max mem: 30263 +train: [7] [500/800] eta: 0:03:10 lr: 0.000278 loss: 0.6657 (0.6710) grad: 0.2455 (0.2827) time: 0.5888 data: 0.0034 max mem: 30263 +train: [7] [520/800] eta: 0:02:56 lr: 0.000278 loss: 0.6724 (0.6711) grad: 0.2345 (0.2827) time: 0.5813 data: 0.0035 max mem: 30263 +train: [7] [540/800] eta: 0:02:43 lr: 0.000277 loss: 0.6753 (0.6710) grad: 0.2345 (0.2834) time: 0.5841 data: 0.0034 max mem: 30263 +train: [7] [560/800] eta: 0:02:30 lr: 0.000277 loss: 0.6724 (0.6721) grad: 0.2573 (0.2831) time: 0.5758 data: 0.0032 max mem: 30263 +train: [7] [580/800] eta: 0:02:20 lr: 0.000276 loss: 0.6549 (0.6699) grad: 0.2360 (0.2804) time: 0.9213 data: 0.2536 max mem: 30263 +train: [7] [600/800] eta: 0:02:07 lr: 0.000276 loss: 0.6231 (0.6680) grad: 0.2396 (0.2806) time: 0.5918 data: 0.0034 max mem: 30263 +train: [7] [620/800] eta: 0:01:54 lr: 0.000275 loss: 0.6231 (0.6665) grad: 0.2457 (0.2800) time: 0.5879 data: 0.0035 max mem: 30263 +train: [7] [640/800] eta: 0:01:41 lr: 0.000275 loss: 0.5987 (0.6647) grad: 0.2457 (0.2799) time: 0.5937 data: 0.0034 max mem: 30263 +train: [7] [660/800] eta: 0:01:28 lr: 0.000275 loss: 0.6185 (0.6693) grad: 0.2541 (0.2788) time: 0.6110 data: 0.0036 max mem: 30263 +train: [7] [680/800] eta: 0:01:16 lr: 0.000274 loss: 0.6362 (0.6703) grad: 0.2521 (0.2781) time: 0.8100 data: 0.2525 max mem: 30263 +train: [7] [700/800] eta: 0:01:03 lr: 0.000274 loss: 0.6401 (0.6690) grad: 0.2444 (0.2770) time: 0.6660 data: 0.0041 max mem: 30263 +train: [7] [720/800] eta: 0:00:50 lr: 0.000273 loss: 0.6571 (0.6691) grad: 0.2445 (0.2786) time: 0.5769 data: 0.0033 max mem: 30263 +train: [7] [740/800] eta: 0:00:38 lr: 0.000273 loss: 0.6401 (0.6673) grad: 0.2562 (0.2777) time: 0.5735 data: 0.0035 max mem: 30263 +train: [7] [760/800] eta: 0:00:25 lr: 0.000272 loss: 0.6538 (0.6715) grad: 0.2363 (0.2765) time: 0.5801 data: 0.0035 max mem: 30263 +train: [7] [780/800] eta: 0:00:12 lr: 0.000272 loss: 0.6314 (0.6680) grad: 0.2363 (0.2750) time: 0.5721 data: 0.0034 max mem: 30263 +train: [7] [799/800] eta: 0:00:00 lr: 0.000271 loss: 0.6305 (0.6684) grad: 0.2027 (0.2728) time: 0.8537 data: 0.2538 max mem: 30263 +train: [7] Total time: 0:08:30 (0.6383 s / it) +train: [7] Summary: lr: 0.000271 loss: 0.6305 (0.6684) grad: 0.2027 (0.2728) +eval (validation): [7] [ 0/14] eta: 0:01:10 time: 5.0187 data: 4.7125 max mem: 30263 +eval (validation): [7] [13/14] eta: 0:00:00 time: 0.7479 data: 0.3553 max mem: 30263 +eval (validation): [7] Total time: 0:00:10 (0.7634 s / it) +cv: [7] best hparam: (0.27, 1.0) (016) ('016_lr2.7e-01_wd1.0e+00') loss: 1.209 acc: 0.453 f1: 0.447 bacc: 0.450 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_age__patch__attn/checkpoint-last.pth +train: [8] [ 0/800] eta: 1:09:06 lr: nan time: 5.1837 data: 4.7059 max mem: 30263 +train: [8] [ 20/800] eta: 0:10:41 lr: 0.000271 loss: 0.5893 (0.5797) grad: 0.2834 (0.2884) time: 0.6045 data: 0.0040 max mem: 30263 +train: [8] [ 40/800] eta: 0:08:53 lr: 0.000270 loss: 0.6024 (0.6214) grad: 0.2739 (0.2647) time: 0.5756 data: 0.0029 max mem: 30263 +train: [8] [ 60/800] eta: 0:08:09 lr: 0.000270 loss: 0.6724 (0.6465) grad: 0.2516 (0.2436) time: 0.5791 data: 0.0035 max mem: 30263 +train: [8] [ 80/800] eta: 0:07:42 lr: 0.000270 loss: 0.6724 (0.6638) grad: 0.2533 (0.2513) time: 0.5834 data: 0.0035 max mem: 30263 +train: [8] [100/800] eta: 0:07:21 lr: 0.000269 loss: 0.6964 (0.6676) grad: 0.2516 (0.2532) time: 0.5849 data: 0.0036 max mem: 30263 +train: [8] [120/800] eta: 0:07:30 lr: 0.000269 loss: 0.6964 (0.6650) grad: 0.2109 (0.2473) time: 0.8177 data: 0.2587 max mem: 30263 +train: [8] [140/800] eta: 0:07:09 lr: 0.000268 loss: 0.6490 (0.6632) grad: 0.2258 (0.2467) time: 0.5842 data: 0.0039 max mem: 30263 +train: [8] [160/800] eta: 0:06:49 lr: 0.000268 loss: 0.6238 (0.6528) grad: 0.2258 (0.2521) time: 0.5653 data: 0.0030 max mem: 30263 +train: [8] [180/800] eta: 0:06:31 lr: 0.000267 loss: 0.6238 (0.6574) grad: 0.2258 (0.2519) time: 0.5680 data: 0.0034 max mem: 30263 +train: [8] [200/800] eta: 0:06:14 lr: 0.000267 loss: 0.6238 (0.6528) grad: 0.2351 (0.2486) time: 0.5558 data: 0.0033 max mem: 30263 +train: [8] [220/800] eta: 0:05:59 lr: 0.000266 loss: 0.6236 (0.6479) grad: 0.2337 (0.2439) time: 0.5681 data: 0.0034 max mem: 30263 +train: [8] [240/800] eta: 0:05:57 lr: 0.000266 loss: 0.5900 (0.6399) grad: 0.2060 (0.2409) time: 0.8398 data: 0.2645 max mem: 30263 +train: [8] [260/800] eta: 0:05:41 lr: 0.000265 loss: 0.5900 (0.6440) grad: 0.2233 (0.2457) time: 0.5709 data: 0.0029 max mem: 30263 +train: [8] [280/800] eta: 0:05:26 lr: 0.000265 loss: 0.5852 (0.6425) grad: 0.2233 (0.2448) time: 0.5738 data: 0.0033 max mem: 30263 +train: [8] [300/800] eta: 0:05:12 lr: 0.000264 loss: 0.6002 (0.6424) grad: 0.2411 (0.2491) time: 0.5798 data: 0.0034 max mem: 30263 +train: [8] [320/800] eta: 0:04:58 lr: 0.000264 loss: 0.6566 (0.6409) grad: 0.2503 (0.2477) time: 0.5696 data: 0.0034 max mem: 30263 +train: [8] [340/800] eta: 0:04:51 lr: 0.000263 loss: 0.6017 (0.6370) grad: 0.2503 (0.2487) time: 0.8282 data: 0.2639 max mem: 30263 +train: [8] [360/800] eta: 0:04:37 lr: 0.000263 loss: 0.6191 (0.6347) grad: 0.2441 (0.2490) time: 0.5963 data: 0.0293 max mem: 30263 +train: [8] [380/800] eta: 0:04:24 lr: 0.000262 loss: 0.6017 (0.6376) grad: 0.2421 (0.2519) time: 0.6078 data: 0.0032 max mem: 30263 +train: [8] [400/800] eta: 0:04:11 lr: 0.000262 loss: 0.6191 (0.6355) grad: 0.2441 (0.2544) time: 0.5843 data: 0.0033 max mem: 30263 +train: [8] [420/800] eta: 0:03:57 lr: 0.000261 loss: 0.6228 (0.6340) grad: 0.2595 (0.2572) time: 0.5737 data: 0.0034 max mem: 30263 +train: [8] [440/800] eta: 0:03:44 lr: 0.000260 loss: 0.6342 (0.6319) grad: 0.2536 (0.2568) time: 0.5868 data: 0.0039 max mem: 30263 +train: [8] [460/800] eta: 0:03:35 lr: 0.000260 loss: 0.6342 (0.6346) grad: 0.2921 (0.2612) time: 0.8476 data: 0.2604 max mem: 30263 +train: [8] [480/800] eta: 0:03:22 lr: 0.000259 loss: 0.6471 (0.6374) grad: 0.2708 (0.2606) time: 0.6128 data: 0.0044 max mem: 30263 +train: [8] [500/800] eta: 0:03:09 lr: 0.000259 loss: 0.6360 (0.6356) grad: 0.2708 (0.2615) time: 0.5836 data: 0.0034 max mem: 30263 +train: [8] [520/800] eta: 0:02:56 lr: 0.000258 loss: 0.6612 (0.6383) grad: 0.2749 (0.2604) time: 0.5775 data: 0.0035 max mem: 30263 +train: [8] [540/800] eta: 0:02:42 lr: 0.000258 loss: 0.6711 (0.6398) grad: 0.2698 (0.2611) time: 0.5751 data: 0.0035 max mem: 30263 +train: [8] [560/800] eta: 0:02:30 lr: 0.000257 loss: 0.6316 (0.6386) grad: 0.2589 (0.2597) time: 0.5814 data: 0.0034 max mem: 30263 +train: [8] [580/800] eta: 0:02:19 lr: 0.000257 loss: 0.6316 (0.6390) grad: 0.2457 (0.2584) time: 0.8737 data: 0.3195 max mem: 30263 +train: [8] [600/800] eta: 0:02:06 lr: 0.000256 loss: 0.6224 (0.6373) grad: 0.2457 (0.2580) time: 0.5706 data: 0.0033 max mem: 30263 +train: [8] [620/800] eta: 0:01:53 lr: 0.000256 loss: 0.5902 (0.6366) grad: 0.2538 (0.2600) time: 0.5734 data: 0.0024 max mem: 30263 +train: [8] [640/800] eta: 0:01:40 lr: 0.000255 loss: 0.6043 (0.6387) grad: 0.2538 (0.2594) time: 0.5755 data: 0.0036 max mem: 30263 +train: [8] [660/800] eta: 0:01:27 lr: 0.000254 loss: 0.6100 (0.6393) grad: 0.2538 (0.2584) time: 0.5809 data: 0.0035 max mem: 30263 +train: [8] [680/800] eta: 0:01:15 lr: 0.000254 loss: 0.6261 (0.6410) grad: 0.2538 (0.2580) time: 0.8382 data: 0.2650 max mem: 30263 +train: [8] [700/800] eta: 0:01:03 lr: 0.000253 loss: 0.6532 (0.6416) grad: 0.2359 (0.2577) time: 0.6196 data: 0.0038 max mem: 30263 +train: [8] [720/800] eta: 0:00:50 lr: 0.000253 loss: 0.6622 (0.6420) grad: 0.2581 (0.2589) time: 0.5852 data: 0.0037 max mem: 30263 +train: [8] [740/800] eta: 0:00:37 lr: 0.000252 loss: 0.5906 (0.6394) grad: 0.2413 (0.2571) time: 0.5818 data: 0.0034 max mem: 30263 +train: [8] [760/800] eta: 0:00:25 lr: 0.000252 loss: 0.5906 (0.6380) grad: 0.2413 (0.2565) time: 0.5741 data: 0.0033 max mem: 30263 +train: [8] [780/800] eta: 0:00:12 lr: 0.000251 loss: 0.5456 (0.6355) grad: 0.2237 (0.2550) time: 0.5783 data: 0.0034 max mem: 30263 +train: [8] [799/800] eta: 0:00:00 lr: 0.000250 loss: 0.5226 (0.6325) grad: 0.1894 (0.2542) time: 0.8648 data: 0.2620 max mem: 30263 +train: [8] Total time: 0:08:26 (0.6334 s / it) +train: [8] Summary: lr: 0.000250 loss: 0.5226 (0.6325) grad: 0.1894 (0.2542) +eval (validation): [8] [ 0/14] eta: 0:01:09 time: 4.9950 data: 4.6932 max mem: 30263 +eval (validation): [8] [13/14] eta: 0:00:00 time: 0.7485 data: 0.3486 max mem: 30263 +eval (validation): [8] Total time: 0:00:10 (0.7680 s / it) +cv: [8] best hparam: (0.27, 1.0) (016) ('016_lr2.7e-01_wd1.0e+00') loss: 1.215 acc: 0.491 f1: 0.466 bacc: 0.483 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_age__patch__attn/checkpoint-last.pth +train: [9] [ 0/800] eta: 1:09:04 lr: nan time: 5.1804 data: 4.7536 max mem: 30263 +train: [9] [ 20/800] eta: 0:11:00 lr: 0.000250 loss: 0.7547 (0.7640) grad: 0.3111 (0.2999) time: 0.6301 data: 0.0035 max mem: 30263 +train: [9] [ 40/800] eta: 0:08:57 lr: 0.000249 loss: 0.6369 (0.6491) grad: 0.2888 (0.2867) time: 0.5605 data: 0.0028 max mem: 30263 +train: [9] [ 60/800] eta: 0:08:10 lr: 0.000249 loss: 0.6369 (0.6247) grad: 0.2627 (0.2569) time: 0.5703 data: 0.0034 max mem: 30263 +train: [9] [ 80/800] eta: 0:07:42 lr: 0.000248 loss: 0.5931 (0.6162) grad: 0.2348 (0.2565) time: 0.5809 data: 0.0035 max mem: 30263 +train: [9] [100/800] eta: 0:07:20 lr: 0.000248 loss: 0.5620 (0.5946) grad: 0.2210 (0.2560) time: 0.5766 data: 0.0029 max mem: 30263 +train: [9] [120/800] eta: 0:07:30 lr: 0.000247 loss: 0.5926 (0.6056) grad: 0.2148 (0.2508) time: 0.8351 data: 0.2581 max mem: 30263 +train: [9] [140/800] eta: 0:07:14 lr: 0.000246 loss: 0.5926 (0.5988) grad: 0.2210 (0.2483) time: 0.6277 data: 0.0039 max mem: 30263 +train: [9] [160/800] eta: 0:06:54 lr: 0.000246 loss: 0.6006 (0.6109) grad: 0.2285 (0.2467) time: 0.5683 data: 0.0033 max mem: 30263 +train: [9] [180/800] eta: 0:06:36 lr: 0.000245 loss: 0.6120 (0.6157) grad: 0.2148 (0.2454) time: 0.5787 data: 0.0036 max mem: 30263 +train: [9] [200/800] eta: 0:06:20 lr: 0.000244 loss: 0.6555 (0.6191) grad: 0.2468 (0.2511) time: 0.5789 data: 0.0034 max mem: 30263 +train: [9] [220/800] eta: 0:06:03 lr: 0.000244 loss: 0.6555 (0.6206) grad: 0.2135 (0.2455) time: 0.5649 data: 0.0033 max mem: 30263 +train: [9] [240/800] eta: 0:06:00 lr: 0.000243 loss: 0.6555 (0.6215) grad: 0.2408 (0.2474) time: 0.8367 data: 0.2621 max mem: 30263 +train: [9] [260/800] eta: 0:05:45 lr: 0.000243 loss: 0.6160 (0.6214) grad: 0.2487 (0.2486) time: 0.5761 data: 0.0035 max mem: 30263 +train: [9] [280/800] eta: 0:05:30 lr: 0.000242 loss: 0.5964 (0.6162) grad: 0.2326 (0.2471) time: 0.5819 data: 0.0029 max mem: 30263 +train: [9] [300/800] eta: 0:05:16 lr: 0.000241 loss: 0.5791 (0.6173) grad: 0.2492 (0.2481) time: 0.6010 data: 0.0035 max mem: 30263 +train: [9] [320/800] eta: 0:05:02 lr: 0.000241 loss: 0.5820 (0.6188) grad: 0.2338 (0.2457) time: 0.5809 data: 0.0037 max mem: 30263 +train: [9] [340/800] eta: 0:04:55 lr: 0.000240 loss: 0.5791 (0.6172) grad: 0.2338 (0.2459) time: 0.8280 data: 0.2659 max mem: 30263 +train: [9] [360/800] eta: 0:04:42 lr: 0.000240 loss: 0.5875 (0.6179) grad: 0.2635 (0.2484) time: 0.6387 data: 0.0384 max mem: 30263 +train: [9] [380/800] eta: 0:04:28 lr: 0.000239 loss: 0.5969 (0.6228) grad: 0.2742 (0.2503) time: 0.5822 data: 0.0027 max mem: 30263 +train: [9] [400/800] eta: 0:04:14 lr: 0.000238 loss: 0.5875 (0.6184) grad: 0.2776 (0.2514) time: 0.5889 data: 0.0034 max mem: 30263 +train: [9] [420/800] eta: 0:04:00 lr: 0.000238 loss: 0.6431 (0.6213) grad: 0.2778 (0.2515) time: 0.5764 data: 0.0032 max mem: 30263 +train: [9] [440/800] eta: 0:03:46 lr: 0.000237 loss: 0.6412 (0.6220) grad: 0.2561 (0.2506) time: 0.5723 data: 0.0036 max mem: 30263 +train: [9] [460/800] eta: 0:03:37 lr: 0.000236 loss: 0.6229 (0.6225) grad: 0.2493 (0.2494) time: 0.8661 data: 0.2740 max mem: 30263 +train: [9] [480/800] eta: 0:03:24 lr: 0.000236 loss: 0.5970 (0.6181) grad: 0.2493 (0.2495) time: 0.6054 data: 0.0027 max mem: 30263 +train: [9] [500/800] eta: 0:03:10 lr: 0.000235 loss: 0.5765 (0.6155) grad: 0.2193 (0.2468) time: 0.5702 data: 0.0031 max mem: 30263 +train: [9] [520/800] eta: 0:02:57 lr: 0.000234 loss: 0.5792 (0.6190) grad: 0.2140 (0.2461) time: 0.5800 data: 0.0034 max mem: 30263 +train: [9] [540/800] eta: 0:02:44 lr: 0.000234 loss: 0.5810 (0.6194) grad: 0.2124 (0.2460) time: 0.5706 data: 0.0035 max mem: 30263 +train: [9] [560/800] eta: 0:02:31 lr: 0.000233 loss: 0.6169 (0.6195) grad: 0.2124 (0.2472) time: 0.5679 data: 0.0033 max mem: 30263 +train: [9] [580/800] eta: 0:02:20 lr: 0.000232 loss: 0.6163 (0.6167) grad: 0.2234 (0.2467) time: 0.8627 data: 0.2604 max mem: 30263 +train: [9] [600/800] eta: 0:02:07 lr: 0.000232 loss: 0.6006 (0.6145) grad: 0.2319 (0.2467) time: 0.5840 data: 0.0034 max mem: 30263 +train: [9] [620/800] eta: 0:01:54 lr: 0.000231 loss: 0.5811 (0.6158) grad: 0.2234 (0.2445) time: 0.5823 data: 0.0034 max mem: 30263 +train: [9] [640/800] eta: 0:01:41 lr: 0.000230 loss: 0.5642 (0.6154) grad: 0.2173 (0.2470) time: 0.6000 data: 0.0035 max mem: 30263 +train: [9] [660/800] eta: 0:01:28 lr: 0.000230 loss: 0.6433 (0.6192) grad: 0.2319 (0.2487) time: 0.5840 data: 0.0035 max mem: 30263 +train: [9] [680/800] eta: 0:01:16 lr: 0.000229 loss: 0.6295 (0.6188) grad: 0.2287 (0.2487) time: 0.8161 data: 0.2647 max mem: 30263 +train: [9] [700/800] eta: 0:01:03 lr: 0.000228 loss: 0.6063 (0.6169) grad: 0.2360 (0.2475) time: 0.5841 data: 0.0167 max mem: 30263 +train: [9] [720/800] eta: 0:00:50 lr: 0.000228 loss: 0.6409 (0.6193) grad: 0.2554 (0.2482) time: 0.6040 data: 0.0039 max mem: 30263 +train: [9] [740/800] eta: 0:00:38 lr: 0.000227 loss: 0.6072 (0.6196) grad: 0.2360 (0.2474) time: 0.6124 data: 0.0034 max mem: 30263 +train: [9] [760/800] eta: 0:00:25 lr: 0.000226 loss: 0.5931 (0.6193) grad: 0.2460 (0.2474) time: 0.5934 data: 0.0035 max mem: 30263 +train: [9] [780/800] eta: 0:00:12 lr: 0.000226 loss: 0.6132 (0.6189) grad: 0.2529 (0.2473) time: 0.5998 data: 0.0035 max mem: 30263 +train: [9] [799/800] eta: 0:00:00 lr: 0.000225 loss: 0.6110 (0.6207) grad: 0.2429 (0.2470) time: 0.8627 data: 0.2643 max mem: 30263 +train: [9] Total time: 0:08:30 (0.6381 s / it) +train: [9] Summary: lr: 0.000225 loss: 0.6110 (0.6207) grad: 0.2429 (0.2470) +eval (validation): [9] [ 0/14] eta: 0:01:11 time: 5.0810 data: 4.7759 max mem: 30263 +eval (validation): [9] [13/14] eta: 0:00:00 time: 0.7627 data: 0.3717 max mem: 30263 +eval (validation): [9] Total time: 0:00:10 (0.7807 s / it) +cv: [9] best hparam: (0.17, 1.0) (013) ('013_lr1.7e-01_wd1.0e+00') loss: 1.185 acc: 0.434 f1: 0.436 bacc: 0.429 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_age__patch__attn/checkpoint-last.pth +train: [10] [ 0/800] eta: 1:07:58 lr: nan time: 5.0979 data: 4.6238 max mem: 30263 +train: [10] [ 20/800] eta: 0:10:48 lr: 0.000224 loss: 0.6581 (0.6736) grad: 0.2264 (0.2435) time: 0.6182 data: 0.0040 max mem: 30263 +train: [10] [ 40/800] eta: 0:09:02 lr: 0.000224 loss: 0.6581 (0.6746) grad: 0.2093 (0.2195) time: 0.5908 data: 0.0029 max mem: 30263 +train: [10] [ 60/800] eta: 0:08:17 lr: 0.000223 loss: 0.6007 (0.6287) grad: 0.2093 (0.2122) time: 0.5862 data: 0.0057 max mem: 30263 +train: [10] [ 80/800] eta: 0:07:47 lr: 0.000222 loss: 0.5596 (0.6248) grad: 0.2093 (0.2223) time: 0.5812 data: 0.0021 max mem: 30263 +train: [10] [100/800] eta: 0:07:23 lr: 0.000222 loss: 0.5596 (0.6252) grad: 0.2202 (0.2333) time: 0.5711 data: 0.0030 max mem: 30263 +train: [10] [120/800] eta: 0:07:32 lr: 0.000221 loss: 0.5459 (0.6200) grad: 0.2212 (0.2415) time: 0.8271 data: 0.2557 max mem: 30263 +train: [10] [140/800] eta: 0:07:10 lr: 0.000220 loss: 0.5766 (0.6115) grad: 0.2271 (0.2382) time: 0.5735 data: 0.0034 max mem: 30263 +train: [10] [160/800] eta: 0:06:51 lr: 0.000220 loss: 0.5766 (0.6055) grad: 0.2318 (0.2396) time: 0.5765 data: 0.0030 max mem: 30263 +train: [10] [180/800] eta: 0:06:34 lr: 0.000219 loss: 0.5360 (0.5965) grad: 0.2318 (0.2379) time: 0.5729 data: 0.0031 max mem: 30263 +train: [10] [200/800] eta: 0:06:18 lr: 0.000218 loss: 0.5441 (0.5959) grad: 0.2341 (0.2410) time: 0.5839 data: 0.0036 max mem: 30263 +train: [10] [220/800] eta: 0:06:02 lr: 0.000217 loss: 0.5605 (0.5988) grad: 0.2341 (0.2388) time: 0.5632 data: 0.0033 max mem: 30263 +train: [10] [240/800] eta: 0:05:58 lr: 0.000217 loss: 0.5765 (0.6022) grad: 0.2185 (0.2356) time: 0.8210 data: 0.2594 max mem: 30263 +train: [10] [260/800] eta: 0:05:46 lr: 0.000216 loss: 0.6429 (0.6075) grad: 0.2108 (0.2326) time: 0.6532 data: 0.0037 max mem: 30263 +train: [10] [280/800] eta: 0:05:31 lr: 0.000215 loss: 0.6429 (0.6089) grad: 0.2067 (0.2304) time: 0.5726 data: 0.0029 max mem: 30263 +train: [10] [300/800] eta: 0:05:16 lr: 0.000215 loss: 0.6429 (0.6066) grad: 0.2148 (0.2366) time: 0.5830 data: 0.0034 max mem: 30263 +train: [10] [320/800] eta: 0:05:02 lr: 0.000214 loss: 0.6106 (0.6037) grad: 0.2431 (0.2378) time: 0.5846 data: 0.0033 max mem: 30263 +train: [10] [340/800] eta: 0:04:54 lr: 0.000213 loss: 0.5841 (0.6028) grad: 0.2431 (0.2359) time: 0.8097 data: 0.2554 max mem: 30263 +train: [10] [360/800] eta: 0:04:40 lr: 0.000213 loss: 0.5712 (0.6012) grad: 0.2445 (0.2368) time: 0.5768 data: 0.0031 max mem: 30263 +train: [10] [380/800] eta: 0:04:26 lr: 0.000212 loss: 0.5449 (0.5966) grad: 0.2076 (0.2356) time: 0.5825 data: 0.0033 max mem: 30263 +train: [10] [400/800] eta: 0:04:12 lr: 0.000211 loss: 0.5449 (0.5982) grad: 0.2035 (0.2365) time: 0.5952 data: 0.0031 max mem: 30263 +train: [10] [420/800] eta: 0:03:59 lr: 0.000210 loss: 0.5840 (0.5996) grad: 0.2090 (0.2379) time: 0.5763 data: 0.0034 max mem: 30263 +train: [10] [440/800] eta: 0:03:46 lr: 0.000210 loss: 0.5777 (0.5987) grad: 0.2290 (0.2390) time: 0.5903 data: 0.0036 max mem: 30263 +train: [10] [460/800] eta: 0:03:36 lr: 0.000209 loss: 0.5882 (0.5978) grad: 0.2502 (0.2388) time: 0.8117 data: 0.2601 max mem: 30263 +train: [10] [480/800] eta: 0:03:23 lr: 0.000208 loss: 0.5777 (0.5978) grad: 0.2290 (0.2371) time: 0.6021 data: 0.0027 max mem: 30263 +train: [10] [500/800] eta: 0:03:09 lr: 0.000207 loss: 0.5777 (0.6006) grad: 0.2054 (0.2354) time: 0.6011 data: 0.0033 max mem: 30263 +train: [10] [520/800] eta: 0:02:56 lr: 0.000207 loss: 0.5882 (0.6015) grad: 0.2054 (0.2368) time: 0.5806 data: 0.0035 max mem: 30263 +train: [10] [540/800] eta: 0:02:43 lr: 0.000206 loss: 0.5738 (0.5974) grad: 0.2110 (0.2361) time: 0.6090 data: 0.0036 max mem: 30263 +train: [10] [560/800] eta: 0:02:30 lr: 0.000205 loss: 0.5737 (0.5981) grad: 0.2234 (0.2365) time: 0.5881 data: 0.0033 max mem: 30263 +train: [10] [580/800] eta: 0:02:20 lr: 0.000205 loss: 0.5491 (0.5981) grad: 0.2409 (0.2371) time: 0.9154 data: 0.2860 max mem: 30263 +train: [10] [600/800] eta: 0:02:07 lr: 0.000204 loss: 0.5815 (0.5994) grad: 0.2232 (0.2364) time: 0.6016 data: 0.0036 max mem: 30263 +train: [10] [620/800] eta: 0:01:54 lr: 0.000203 loss: 0.5992 (0.5985) grad: 0.2232 (0.2369) time: 0.6019 data: 0.0030 max mem: 30263 +train: [10] [640/800] eta: 0:01:41 lr: 0.000202 loss: 0.5992 (0.5972) grad: 0.2346 (0.2377) time: 0.5878 data: 0.0034 max mem: 30263 +train: [10] [660/800] eta: 0:01:28 lr: 0.000202 loss: 0.6023 (0.5986) grad: 0.2232 (0.2362) time: 0.5811 data: 0.0035 max mem: 30263 +train: [10] [680/800] eta: 0:01:16 lr: 0.000201 loss: 0.5679 (0.5990) grad: 0.2393 (0.2381) time: 0.8595 data: 0.2722 max mem: 30263 +train: [10] [700/800] eta: 0:01:03 lr: 0.000200 loss: 0.5467 (0.5986) grad: 0.2213 (0.2366) time: 0.5946 data: 0.0030 max mem: 30263 +train: [10] [720/800] eta: 0:00:51 lr: 0.000199 loss: 0.5509 (0.5979) grad: 0.2037 (0.2368) time: 0.6099 data: 0.0037 max mem: 30263 +train: [10] [740/800] eta: 0:00:38 lr: 0.000199 loss: 0.5467 (0.5968) grad: 0.2175 (0.2373) time: 0.5849 data: 0.0031 max mem: 30263 +train: [10] [760/800] eta: 0:00:25 lr: 0.000198 loss: 0.5616 (0.5961) grad: 0.1967 (0.2355) time: 0.5944 data: 0.0034 max mem: 30263 +train: [10] [780/800] eta: 0:00:12 lr: 0.000197 loss: 0.5864 (0.5963) grad: 0.2126 (0.2352) time: 0.5698 data: 0.0035 max mem: 30263 +train: [10] [799/800] eta: 0:00:00 lr: 0.000196 loss: 0.5939 (0.5965) grad: 0.2126 (0.2353) time: 0.8937 data: 0.2569 max mem: 30263 +train: [10] Total time: 0:08:32 (0.6403 s / it) +train: [10] Summary: lr: 0.000196 loss: 0.5939 (0.5965) grad: 0.2126 (0.2353) +eval (validation): [10] [ 0/14] eta: 0:01:11 time: 5.1037 data: 4.7905 max mem: 30263 +eval (validation): [10] [13/14] eta: 0:00:00 time: 0.7657 data: 0.3540 max mem: 30263 +eval (validation): [10] Total time: 0:00:10 (0.7845 s / it) +cv: [10] best hparam: (0.2, 1.0) (014) ('014_lr2.0e-01_wd1.0e+00') loss: 1.188 acc: 0.434 f1: 0.431 bacc: 0.431 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_age__patch__attn/checkpoint-last.pth +train: [11] [ 0/800] eta: 1:10:30 lr: nan time: 5.2875 data: 4.7820 max mem: 30263 +train: [11] [ 20/800] eta: 0:11:05 lr: 0.000196 loss: 0.5141 (0.5122) grad: 0.1742 (0.2078) time: 0.6319 data: 0.0041 max mem: 30263 +train: [11] [ 40/800] eta: 0:09:13 lr: 0.000195 loss: 0.5141 (0.5612) grad: 0.1916 (0.2125) time: 0.5975 data: 0.0034 max mem: 30263 +train: [11] [ 60/800] eta: 0:08:28 lr: 0.000194 loss: 0.5335 (0.5513) grad: 0.1960 (0.2111) time: 0.6031 data: 0.0033 max mem: 30263 +train: [11] [ 80/800] eta: 0:07:55 lr: 0.000193 loss: 0.5363 (0.5703) grad: 0.1960 (0.2124) time: 0.5798 data: 0.0030 max mem: 30263 +train: [11] [100/800] eta: 0:07:31 lr: 0.000193 loss: 0.5923 (0.6038) grad: 0.2125 (0.2241) time: 0.5822 data: 0.0033 max mem: 30263 +train: [11] [120/800] eta: 0:07:46 lr: 0.000192 loss: 0.5616 (0.5879) grad: 0.2089 (0.2221) time: 0.8874 data: 0.2666 max mem: 30263 +train: [11] [140/800] eta: 0:07:23 lr: 0.000191 loss: 0.5363 (0.5763) grad: 0.2207 (0.2204) time: 0.5893 data: 0.0034 max mem: 30263 +train: [11] [160/800] eta: 0:07:02 lr: 0.000190 loss: 0.5261 (0.5745) grad: 0.2264 (0.2242) time: 0.5737 data: 0.0035 max mem: 30263 +train: [11] [180/800] eta: 0:06:44 lr: 0.000190 loss: 0.5049 (0.5743) grad: 0.2213 (0.2317) time: 0.5939 data: 0.0034 max mem: 30263 +train: [11] [200/800] eta: 0:06:28 lr: 0.000189 loss: 0.5261 (0.5753) grad: 0.2213 (0.2274) time: 0.6111 data: 0.0034 max mem: 30263 +train: [11] [220/800] eta: 0:06:11 lr: 0.000188 loss: 0.5571 (0.5730) grad: 0.2213 (0.2250) time: 0.5702 data: 0.0032 max mem: 30263 +train: [11] [240/800] eta: 0:06:08 lr: 0.000187 loss: 0.5571 (0.5713) grad: 0.2213 (0.2280) time: 0.8390 data: 0.2636 max mem: 30263 +train: [11] [260/800] eta: 0:05:52 lr: 0.000187 loss: 0.5963 (0.5820) grad: 0.1797 (0.2256) time: 0.6009 data: 0.0036 max mem: 30263 +train: [11] [280/800] eta: 0:05:37 lr: 0.000186 loss: 0.5702 (0.5833) grad: 0.2267 (0.2275) time: 0.5939 data: 0.0035 max mem: 30263 +train: [11] [300/800] eta: 0:05:22 lr: 0.000185 loss: 0.5702 (0.5797) grad: 0.2311 (0.2257) time: 0.5983 data: 0.0036 max mem: 30263 +train: [11] [320/800] eta: 0:05:07 lr: 0.000184 loss: 0.5857 (0.5807) grad: 0.2311 (0.2254) time: 0.5789 data: 0.0034 max mem: 30263 +train: [11] [340/800] eta: 0:05:00 lr: 0.000184 loss: 0.5369 (0.5783) grad: 0.2338 (0.2291) time: 0.8332 data: 0.2535 max mem: 30263 +train: [11] [360/800] eta: 0:04:46 lr: 0.000183 loss: 0.5548 (0.5835) grad: 0.2183 (0.2284) time: 0.6110 data: 0.0034 max mem: 30263 +train: [11] [380/800] eta: 0:04:31 lr: 0.000182 loss: 0.5857 (0.5826) grad: 0.2183 (0.2286) time: 0.5809 data: 0.0029 max mem: 30263 +train: [11] [400/800] eta: 0:04:17 lr: 0.000181 loss: 0.5567 (0.5795) grad: 0.2012 (0.2255) time: 0.5702 data: 0.0032 max mem: 30263 +train: [11] [420/800] eta: 0:04:03 lr: 0.000181 loss: 0.5650 (0.5790) grad: 0.1837 (0.2240) time: 0.5724 data: 0.0032 max mem: 30263 +train: [11] [440/800] eta: 0:03:49 lr: 0.000180 loss: 0.5354 (0.5799) grad: 0.1923 (0.2254) time: 0.5859 data: 0.0035 max mem: 30263 +train: [11] [460/800] eta: 0:03:40 lr: 0.000179 loss: 0.5475 (0.5805) grad: 0.1949 (0.2274) time: 0.8870 data: 0.3241 max mem: 30263 +train: [11] [480/800] eta: 0:03:26 lr: 0.000178 loss: 0.5475 (0.5781) grad: 0.1957 (0.2263) time: 0.6077 data: 0.0418 max mem: 30263 +train: [11] [500/800] eta: 0:03:13 lr: 0.000177 loss: 0.5656 (0.5776) grad: 0.2222 (0.2272) time: 0.6377 data: 0.0036 max mem: 30263 +train: [11] [520/800] eta: 0:03:00 lr: 0.000177 loss: 0.5786 (0.5797) grad: 0.2167 (0.2285) time: 0.6063 data: 0.0034 max mem: 30263 +train: [11] [540/800] eta: 0:02:46 lr: 0.000176 loss: 0.5656 (0.5811) grad: 0.2222 (0.2300) time: 0.5861 data: 0.0036 max mem: 30263 +train: [11] [560/800] eta: 0:02:33 lr: 0.000175 loss: 0.5628 (0.5784) grad: 0.2225 (0.2299) time: 0.5571 data: 0.0032 max mem: 30263 +train: [11] [580/800] eta: 0:02:22 lr: 0.000174 loss: 0.5459 (0.5759) grad: 0.2225 (0.2290) time: 0.8567 data: 0.2956 max mem: 30263 +train: [11] [600/800] eta: 0:02:08 lr: 0.000174 loss: 0.5219 (0.5736) grad: 0.2176 (0.2278) time: 0.5865 data: 0.0180 max mem: 30263 +train: [11] [620/800] eta: 0:01:55 lr: 0.000173 loss: 0.5024 (0.5718) grad: 0.1981 (0.2268) time: 0.5625 data: 0.0022 max mem: 30263 +train: [11] [640/800] eta: 0:01:42 lr: 0.000172 loss: 0.5078 (0.5743) grad: 0.2115 (0.2276) time: 0.5951 data: 0.0035 max mem: 30263 +train: [11] [660/800] eta: 0:01:29 lr: 0.000171 loss: 0.5414 (0.5744) grad: 0.2176 (0.2291) time: 0.5717 data: 0.0031 max mem: 30263 +train: [11] [680/800] eta: 0:01:17 lr: 0.000170 loss: 0.5198 (0.5712) grad: 0.2115 (0.2287) time: 0.8086 data: 0.2519 max mem: 30263 +train: [11] [700/800] eta: 0:01:04 lr: 0.000170 loss: 0.5789 (0.5718) grad: 0.2150 (0.2291) time: 0.6196 data: 0.0035 max mem: 30263 +train: [11] [720/800] eta: 0:00:51 lr: 0.000169 loss: 0.5363 (0.5725) grad: 0.2133 (0.2285) time: 0.5806 data: 0.0030 max mem: 30263 +train: [11] [740/800] eta: 0:00:38 lr: 0.000168 loss: 0.5663 (0.5734) grad: 0.2068 (0.2279) time: 0.5658 data: 0.0029 max mem: 30263 +train: [11] [760/800] eta: 0:00:25 lr: 0.000167 loss: 0.5790 (0.5727) grad: 0.2133 (0.2284) time: 0.5749 data: 0.0039 max mem: 30263 +train: [11] [780/800] eta: 0:00:12 lr: 0.000167 loss: 0.5663 (0.5725) grad: 0.2133 (0.2292) time: 0.5520 data: 0.0024 max mem: 30263 +train: [11] [799/800] eta: 0:00:00 lr: 0.000166 loss: 0.5693 (0.5738) grad: 0.2157 (0.2285) time: 0.8623 data: 0.3132 max mem: 30263 +train: [11] Total time: 0:08:33 (0.6413 s / it) +train: [11] Summary: lr: 0.000166 loss: 0.5693 (0.5738) grad: 0.2157 (0.2285) +eval (validation): [11] [ 0/14] eta: 0:01:08 time: 4.9186 data: 4.5498 max mem: 30263 +eval (validation): [11] [13/14] eta: 0:00:00 time: 0.7398 data: 0.3357 max mem: 30263 +eval (validation): [11] Total time: 0:00:10 (0.7576 s / it) +cv: [11] best hparam: (0.12, 1.0) (011) ('011_lr1.2e-01_wd1.0e+00') loss: 1.195 acc: 0.453 f1: 0.455 bacc: 0.449 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_age__patch__attn/checkpoint-last.pth +train: [12] [ 0/800] eta: 1:09:30 lr: nan time: 5.2134 data: 4.7663 max mem: 30263 +train: [12] [ 20/800] eta: 0:11:00 lr: 0.000165 loss: 0.5443 (0.5758) grad: 0.2129 (0.2062) time: 0.6289 data: 0.0439 max mem: 30263 +train: [12] [ 40/800] eta: 0:08:59 lr: 0.000164 loss: 0.5342 (0.5561) grad: 0.1892 (0.2187) time: 0.5649 data: 0.0028 max mem: 30263 +train: [12] [ 60/800] eta: 0:08:22 lr: 0.000163 loss: 0.5493 (0.5652) grad: 0.1981 (0.2205) time: 0.6184 data: 0.0039 max mem: 30263 +train: [12] [ 80/800] eta: 0:07:57 lr: 0.000163 loss: 0.5342 (0.5537) grad: 0.1981 (0.2355) time: 0.6137 data: 0.0036 max mem: 30263 +train: [12] [100/800] eta: 0:07:32 lr: 0.000162 loss: 0.5348 (0.5678) grad: 0.1969 (0.2211) time: 0.5760 data: 0.0034 max mem: 30263 +train: [12] [120/800] eta: 0:07:34 lr: 0.000161 loss: 0.5493 (0.5709) grad: 0.2156 (0.2306) time: 0.7809 data: 0.2463 max mem: 30263 +train: [12] [140/800] eta: 0:07:11 lr: 0.000160 loss: 0.5458 (0.5703) grad: 0.2156 (0.2263) time: 0.5654 data: 0.0038 max mem: 30263 +train: [12] [160/800] eta: 0:06:53 lr: 0.000160 loss: 0.5735 (0.5682) grad: 0.2156 (0.2254) time: 0.5895 data: 0.0390 max mem: 30263 +train: [12] [180/800] eta: 0:06:36 lr: 0.000159 loss: 0.5735 (0.5762) grad: 0.2205 (0.2234) time: 0.5914 data: 0.0133 max mem: 30263 +train: [12] [200/800] eta: 0:06:22 lr: 0.000158 loss: 0.5676 (0.5724) grad: 0.2205 (0.2274) time: 0.6089 data: 0.0028 max mem: 30263 +train: [12] [220/800] eta: 0:06:05 lr: 0.000157 loss: 0.5689 (0.5751) grad: 0.2203 (0.2255) time: 0.5584 data: 0.0036 max mem: 30263 +train: [12] [240/800] eta: 0:06:05 lr: 0.000156 loss: 0.5689 (0.5748) grad: 0.2126 (0.2238) time: 0.9162 data: 0.3457 max mem: 30263 +train: [12] [260/800] eta: 0:05:49 lr: 0.000156 loss: 0.5700 (0.5788) grad: 0.2219 (0.2285) time: 0.5666 data: 0.0032 max mem: 30263 +train: [12] [280/800] eta: 0:05:33 lr: 0.000155 loss: 0.5689 (0.5738) grad: 0.2126 (0.2269) time: 0.5730 data: 0.0036 max mem: 30263 +train: [12] [300/800] eta: 0:05:17 lr: 0.000154 loss: 0.5226 (0.5745) grad: 0.2185 (0.2255) time: 0.5580 data: 0.0032 max mem: 30263 +train: [12] [320/800] eta: 0:05:03 lr: 0.000153 loss: 0.5544 (0.5804) grad: 0.2220 (0.2268) time: 0.5690 data: 0.0036 max mem: 30263 +train: [12] [340/800] eta: 0:04:56 lr: 0.000152 loss: 0.5399 (0.5805) grad: 0.2081 (0.2253) time: 0.8342 data: 0.2649 max mem: 30263 +train: [12] [360/800] eta: 0:04:41 lr: 0.000152 loss: 0.5688 (0.5813) grad: 0.2185 (0.2259) time: 0.5942 data: 0.0033 max mem: 30263 +train: [12] [380/800] eta: 0:04:27 lr: 0.000151 loss: 0.5544 (0.5791) grad: 0.2220 (0.2262) time: 0.5800 data: 0.0034 max mem: 30263 +train: [12] [400/800] eta: 0:04:13 lr: 0.000150 loss: 0.5594 (0.5794) grad: 0.2333 (0.2286) time: 0.5807 data: 0.0034 max mem: 30263 +train: [12] [420/800] eta: 0:04:00 lr: 0.000149 loss: 0.5546 (0.5772) grad: 0.2333 (0.2276) time: 0.5722 data: 0.0036 max mem: 30263 +train: [12] [440/800] eta: 0:03:46 lr: 0.000149 loss: 0.5533 (0.5756) grad: 0.2333 (0.2290) time: 0.5643 data: 0.0030 max mem: 30263 +train: [12] [460/800] eta: 0:03:36 lr: 0.000148 loss: 0.5594 (0.5759) grad: 0.2348 (0.2285) time: 0.8374 data: 0.2864 max mem: 30263 +train: [12] [480/800] eta: 0:03:24 lr: 0.000147 loss: 0.5546 (0.5751) grad: 0.2183 (0.2277) time: 0.6478 data: 0.0296 max mem: 30263 +train: [12] [500/800] eta: 0:03:11 lr: 0.000146 loss: 0.5624 (0.5735) grad: 0.2348 (0.2280) time: 0.6512 data: 0.0032 max mem: 30263 +train: [12] [520/800] eta: 0:02:58 lr: 0.000145 loss: 0.5449 (0.5739) grad: 0.2196 (0.2282) time: 0.5615 data: 0.0032 max mem: 30263 +train: [12] [540/800] eta: 0:02:44 lr: 0.000145 loss: 0.5542 (0.5749) grad: 0.2100 (0.2264) time: 0.5765 data: 0.0038 max mem: 30263 +train: [12] [560/800] eta: 0:02:31 lr: 0.000144 loss: 0.5541 (0.5736) grad: 0.2100 (0.2267) time: 0.5699 data: 0.0033 max mem: 30263 +train: [12] [580/800] eta: 0:02:20 lr: 0.000143 loss: 0.5613 (0.5777) grad: 0.2100 (0.2276) time: 0.8862 data: 0.2670 max mem: 30263 +train: [12] [600/800] eta: 0:02:07 lr: 0.000142 loss: 0.5541 (0.5747) grad: 0.2100 (0.2278) time: 0.5991 data: 0.0040 max mem: 30263 +train: [12] [620/800] eta: 0:01:54 lr: 0.000141 loss: 0.5191 (0.5729) grad: 0.2411 (0.2299) time: 0.6209 data: 0.0033 max mem: 30263 +train: [12] [640/800] eta: 0:01:41 lr: 0.000141 loss: 0.5121 (0.5717) grad: 0.2461 (0.2310) time: 0.6149 data: 0.0037 max mem: 30263 +train: [12] [660/800] eta: 0:01:28 lr: 0.000140 loss: 0.5020 (0.5711) grad: 0.2517 (0.2318) time: 0.5672 data: 0.0037 max mem: 30263 +train: [12] [680/800] eta: 0:01:16 lr: 0.000139 loss: 0.5020 (0.5697) grad: 0.2517 (0.2308) time: 0.8418 data: 0.2661 max mem: 30263 +train: [12] [700/800] eta: 0:01:04 lr: 0.000138 loss: 0.6040 (0.5721) grad: 0.2280 (0.2309) time: 0.6285 data: 0.0034 max mem: 30263 +train: [12] [720/800] eta: 0:00:51 lr: 0.000138 loss: 0.5644 (0.5706) grad: 0.2160 (0.2305) time: 0.6158 data: 0.0036 max mem: 30263 +train: [12] [740/800] eta: 0:00:38 lr: 0.000137 loss: 0.5644 (0.5712) grad: 0.2160 (0.2304) time: 0.5718 data: 0.0036 max mem: 30263 +train: [12] [760/800] eta: 0:00:25 lr: 0.000136 loss: 0.5644 (0.5710) grad: 0.2302 (0.2311) time: 0.5725 data: 0.0036 max mem: 30263 +train: [12] [780/800] eta: 0:00:12 lr: 0.000135 loss: 0.5269 (0.5730) grad: 0.2302 (0.2320) time: 0.5642 data: 0.0031 max mem: 30263 +train: [12] [799/800] eta: 0:00:00 lr: 0.000134 loss: 0.5392 (0.5728) grad: 0.2660 (0.2334) time: 0.8286 data: 0.2697 max mem: 30263 +train: [12] Total time: 0:08:32 (0.6402 s / it) +train: [12] Summary: lr: 0.000134 loss: 0.5392 (0.5728) grad: 0.2660 (0.2334) +eval (validation): [12] [ 0/14] eta: 0:01:11 time: 5.1409 data: 4.7885 max mem: 30263 +eval (validation): [12] [13/14] eta: 0:00:00 time: 0.7624 data: 0.3714 max mem: 30263 +eval (validation): [12] Total time: 0:00:10 (0.7765 s / it) +cv: [12] best hparam: (0.23, 1.0) (015) ('015_lr2.3e-01_wd1.0e+00') loss: 1.205 acc: 0.491 f1: 0.485 bacc: 0.487 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_age__patch__attn/checkpoint-last.pth +train: [13] [ 0/800] eta: 1:11:23 lr: nan time: 5.3544 data: 4.9175 max mem: 30263 +train: [13] [ 20/800] eta: 0:11:01 lr: 0.000134 loss: 0.6356 (0.6261) grad: 0.1980 (0.2006) time: 0.6223 data: 0.0362 max mem: 30263 +train: [13] [ 40/800] eta: 0:09:01 lr: 0.000133 loss: 0.5915 (0.6096) grad: 0.1989 (0.2198) time: 0.5698 data: 0.0030 max mem: 30263 +train: [13] [ 60/800] eta: 0:08:23 lr: 0.000132 loss: 0.5915 (0.5940) grad: 0.1980 (0.2071) time: 0.6173 data: 0.0035 max mem: 30263 +train: [13] [ 80/800] eta: 0:07:51 lr: 0.000131 loss: 0.5651 (0.5744) grad: 0.2048 (0.2202) time: 0.5778 data: 0.0038 max mem: 30263 +train: [13] [100/800] eta: 0:07:29 lr: 0.000130 loss: 0.5376 (0.5695) grad: 0.2189 (0.2186) time: 0.5861 data: 0.0036 max mem: 30263 +train: [13] [120/800] eta: 0:07:40 lr: 0.000130 loss: 0.5376 (0.5824) grad: 0.2122 (0.2192) time: 0.8526 data: 0.2584 max mem: 30263 +train: [13] [140/800] eta: 0:07:21 lr: 0.000129 loss: 0.5119 (0.5715) grad: 0.2269 (0.2223) time: 0.6236 data: 0.0044 max mem: 30263 +train: [13] [160/800] eta: 0:07:04 lr: 0.000128 loss: 0.5485 (0.5736) grad: 0.2108 (0.2240) time: 0.6231 data: 0.0031 max mem: 30263 +train: [13] [180/800] eta: 0:06:48 lr: 0.000127 loss: 0.5485 (0.5705) grad: 0.2061 (0.2214) time: 0.6160 data: 0.0038 max mem: 30263 +train: [13] [200/800] eta: 0:06:29 lr: 0.000127 loss: 0.5485 (0.5675) grad: 0.2024 (0.2173) time: 0.5755 data: 0.0034 max mem: 30263 +train: [13] [220/800] eta: 0:06:13 lr: 0.000126 loss: 0.5702 (0.5726) grad: 0.2024 (0.2198) time: 0.5799 data: 0.0034 max mem: 30263 +train: [13] [240/800] eta: 0:06:10 lr: 0.000125 loss: 0.5513 (0.5734) grad: 0.2011 (0.2227) time: 0.8509 data: 0.2500 max mem: 30263 +train: [13] [260/800] eta: 0:05:53 lr: 0.000124 loss: 0.5702 (0.5773) grad: 0.2048 (0.2212) time: 0.5817 data: 0.0033 max mem: 30263 +train: [13] [280/800] eta: 0:05:37 lr: 0.000124 loss: 0.5882 (0.5784) grad: 0.2385 (0.2235) time: 0.5765 data: 0.0038 max mem: 30263 +train: [13] [300/800] eta: 0:05:22 lr: 0.000123 loss: 0.5859 (0.5802) grad: 0.2547 (0.2288) time: 0.5835 data: 0.0032 max mem: 30263 +train: [13] [320/800] eta: 0:05:07 lr: 0.000122 loss: 0.5848 (0.5803) grad: 0.2342 (0.2293) time: 0.5864 data: 0.0035 max mem: 30263 +train: [13] [340/800] eta: 0:05:02 lr: 0.000121 loss: 0.5730 (0.5761) grad: 0.2342 (0.2283) time: 0.9351 data: 0.3778 max mem: 30263 +train: [13] [360/800] eta: 0:04:48 lr: 0.000120 loss: 0.5488 (0.5710) grad: 0.2233 (0.2282) time: 0.6258 data: 0.0485 max mem: 30263 +train: [13] [380/800] eta: 0:04:34 lr: 0.000120 loss: 0.5189 (0.5672) grad: 0.2033 (0.2282) time: 0.5938 data: 0.0033 max mem: 30263 +train: [13] [400/800] eta: 0:04:19 lr: 0.000119 loss: 0.4934 (0.5690) grad: 0.2233 (0.2325) time: 0.5853 data: 0.0036 max mem: 30263 +train: [13] [420/800] eta: 0:04:05 lr: 0.000118 loss: 0.5213 (0.5735) grad: 0.2482 (0.2315) time: 0.5792 data: 0.0034 max mem: 30263 +train: [13] [440/800] eta: 0:03:51 lr: 0.000117 loss: 0.5213 (0.5710) grad: 0.2521 (0.2325) time: 0.5706 data: 0.0033 max mem: 30263 +train: [13] [460/800] eta: 0:03:41 lr: 0.000117 loss: 0.5628 (0.5729) grad: 0.2525 (0.2327) time: 0.8620 data: 0.2649 max mem: 30263 +train: [13] [480/800] eta: 0:03:28 lr: 0.000116 loss: 0.5393 (0.5717) grad: 0.2349 (0.2348) time: 0.6417 data: 0.0041 max mem: 30263 +train: [13] [500/800] eta: 0:03:14 lr: 0.000115 loss: 0.5038 (0.5695) grad: 0.2349 (0.2343) time: 0.5677 data: 0.0032 max mem: 30263 +train: [13] [520/800] eta: 0:03:00 lr: 0.000114 loss: 0.5654 (0.5701) grad: 0.2349 (0.2338) time: 0.5673 data: 0.0034 max mem: 30263 +train: [13] [540/800] eta: 0:02:47 lr: 0.000114 loss: 0.5260 (0.5686) grad: 0.2349 (0.2337) time: 0.5681 data: 0.0033 max mem: 30263 +train: [13] [560/800] eta: 0:02:33 lr: 0.000113 loss: 0.5500 (0.5719) grad: 0.2313 (0.2360) time: 0.5626 data: 0.0034 max mem: 30263 +train: [13] [580/800] eta: 0:02:22 lr: 0.000112 loss: 0.5500 (0.5707) grad: 0.2253 (0.2349) time: 0.8856 data: 0.2605 max mem: 30263 +train: [13] [600/800] eta: 0:02:09 lr: 0.000111 loss: 0.5260 (0.5703) grad: 0.2253 (0.2345) time: 0.5824 data: 0.0033 max mem: 30263 +train: [13] [620/800] eta: 0:01:55 lr: 0.000110 loss: 0.5491 (0.5700) grad: 0.2138 (0.2340) time: 0.5726 data: 0.0034 max mem: 30263 +train: [13] [640/800] eta: 0:01:42 lr: 0.000110 loss: 0.5491 (0.5703) grad: 0.2138 (0.2348) time: 0.5592 data: 0.0034 max mem: 30263 +train: [13] [660/800] eta: 0:01:29 lr: 0.000109 loss: 0.5159 (0.5678) grad: 0.2138 (0.2340) time: 0.5679 data: 0.0034 max mem: 30263 +train: [13] [680/800] eta: 0:01:17 lr: 0.000108 loss: 0.5159 (0.5674) grad: 0.2138 (0.2341) time: 0.9116 data: 0.3593 max mem: 30263 +train: [13] [700/800] eta: 0:01:04 lr: 0.000107 loss: 0.5538 (0.5690) grad: 0.2239 (0.2361) time: 0.5700 data: 0.0022 max mem: 30263 +train: [13] [720/800] eta: 0:00:51 lr: 0.000107 loss: 0.5177 (0.5681) grad: 0.2243 (0.2369) time: 0.5996 data: 0.0376 max mem: 30263 +train: [13] [740/800] eta: 0:00:38 lr: 0.000106 loss: 0.5832 (0.5673) grad: 0.2439 (0.2367) time: 0.6073 data: 0.0412 max mem: 30263 +train: [13] [760/800] eta: 0:00:25 lr: 0.000105 loss: 0.5205 (0.5663) grad: 0.2427 (0.2361) time: 0.5690 data: 0.0026 max mem: 30263 +train: [13] [780/800] eta: 0:00:12 lr: 0.000104 loss: 0.5177 (0.5655) grad: 0.2427 (0.2362) time: 0.5824 data: 0.0025 max mem: 30263 +train: [13] [799/800] eta: 0:00:00 lr: 0.000104 loss: 0.5100 (0.5641) grad: 0.2226 (0.2360) time: 0.8701 data: 0.3105 max mem: 30263 +train: [13] Total time: 0:08:36 (0.6453 s / it) +train: [13] Summary: lr: 0.000104 loss: 0.5100 (0.5641) grad: 0.2226 (0.2360) +eval (validation): [13] [ 0/14] eta: 0:01:10 time: 5.0259 data: 4.7275 max mem: 30263 +eval (validation): [13] [13/14] eta: 0:00:00 time: 0.7572 data: 0.3734 max mem: 30263 +eval (validation): [13] Total time: 0:00:10 (0.7727 s / it) +cv: [13] best hparam: (0.32, 1.0) (017) ('017_lr3.2e-01_wd1.0e+00') loss: 1.263 acc: 0.472 f1: 0.466 bacc: 0.465 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_age__patch__attn/checkpoint-last.pth +train: [14] [ 0/800] eta: 1:09:20 lr: nan time: 5.2010 data: 4.7757 max mem: 30263 +train: [14] [ 20/800] eta: 0:10:17 lr: 0.000103 loss: 0.5375 (0.5443) grad: 0.2341 (0.2437) time: 0.5710 data: 0.0032 max mem: 30263 +train: [14] [ 40/800] eta: 0:08:40 lr: 0.000102 loss: 0.5689 (0.5816) grad: 0.2281 (0.2406) time: 0.5739 data: 0.0031 max mem: 30263 +train: [14] [ 60/800] eta: 0:07:56 lr: 0.000101 loss: 0.5729 (0.5985) grad: 0.2341 (0.2485) time: 0.5571 data: 0.0032 max mem: 30263 +train: [14] [ 80/800] eta: 0:07:26 lr: 0.000101 loss: 0.5729 (0.5932) grad: 0.2281 (0.2401) time: 0.5521 data: 0.0018 max mem: 30263 +train: [14] [100/800] eta: 0:07:10 lr: 0.000100 loss: 0.5729 (0.5765) grad: 0.2056 (0.2273) time: 0.5892 data: 0.0030 max mem: 30263 +train: [14] [120/800] eta: 0:07:22 lr: 0.000099 loss: 0.5351 (0.5662) grad: 0.1685 (0.2195) time: 0.8363 data: 0.2654 max mem: 30263 +train: [14] [140/800] eta: 0:07:08 lr: 0.000099 loss: 0.5275 (0.5636) grad: 0.1996 (0.2214) time: 0.6330 data: 0.0038 max mem: 30263 +train: [14] [160/800] eta: 0:06:50 lr: 0.000098 loss: 0.4918 (0.5547) grad: 0.1927 (0.2222) time: 0.5912 data: 0.0029 max mem: 30263 +train: [14] [180/800] eta: 0:06:37 lr: 0.000097 loss: 0.5112 (0.5565) grad: 0.1959 (0.2205) time: 0.6378 data: 0.0037 max mem: 30263 +train: [14] [200/800] eta: 0:06:24 lr: 0.000096 loss: 0.5407 (0.5598) grad: 0.2088 (0.2208) time: 0.6468 data: 0.0042 max mem: 30263 +train: [14] [220/800] eta: 0:06:08 lr: 0.000096 loss: 0.5254 (0.5587) grad: 0.2142 (0.2241) time: 0.5781 data: 0.0031 max mem: 30263 +train: [14] [240/800] eta: 0:06:06 lr: 0.000095 loss: 0.5407 (0.5559) grad: 0.2142 (0.2269) time: 0.8605 data: 0.2710 max mem: 30263 +train: [14] [260/800] eta: 0:05:52 lr: 0.000094 loss: 0.5254 (0.5537) grad: 0.2245 (0.2318) time: 0.6240 data: 0.0039 max mem: 30263 +train: [14] [280/800] eta: 0:05:36 lr: 0.000093 loss: 0.5254 (0.5549) grad: 0.2439 (0.2321) time: 0.5732 data: 0.0031 max mem: 30263 +train: [14] [300/800] eta: 0:05:20 lr: 0.000093 loss: 0.5739 (0.5634) grad: 0.2504 (0.2368) time: 0.5715 data: 0.0039 max mem: 30263 +train: [14] [320/800] eta: 0:05:05 lr: 0.000092 loss: 0.5739 (0.5610) grad: 0.2439 (0.2340) time: 0.5602 data: 0.0035 max mem: 30263 +train: [14] [340/800] eta: 0:04:57 lr: 0.000091 loss: 0.5835 (0.5634) grad: 0.2439 (0.2342) time: 0.8116 data: 0.2557 max mem: 30263 +train: [14] [360/800] eta: 0:04:43 lr: 0.000090 loss: 0.5664 (0.5612) grad: 0.2060 (0.2354) time: 0.6025 data: 0.0032 max mem: 30263 +train: [14] [380/800] eta: 0:04:29 lr: 0.000090 loss: 0.5357 (0.5597) grad: 0.2060 (0.2352) time: 0.5737 data: 0.0031 max mem: 30263 +train: [14] [400/800] eta: 0:04:14 lr: 0.000089 loss: 0.5441 (0.5619) grad: 0.2170 (0.2345) time: 0.5619 data: 0.0033 max mem: 30263 +train: [14] [420/800] eta: 0:04:00 lr: 0.000088 loss: 0.5441 (0.5617) grad: 0.2170 (0.2348) time: 0.5731 data: 0.0030 max mem: 30263 +train: [14] [440/800] eta: 0:03:47 lr: 0.000088 loss: 0.5331 (0.5585) grad: 0.2292 (0.2353) time: 0.5776 data: 0.0027 max mem: 30263 +train: [14] [460/800] eta: 0:03:39 lr: 0.000087 loss: 0.5118 (0.5531) grad: 0.2390 (0.2348) time: 0.9497 data: 0.3669 max mem: 30263 +train: [14] [480/800] eta: 0:03:25 lr: 0.000086 loss: 0.4691 (0.5508) grad: 0.2390 (0.2361) time: 0.5805 data: 0.0021 max mem: 30263 +train: [14] [500/800] eta: 0:03:12 lr: 0.000085 loss: 0.4725 (0.5509) grad: 0.2522 (0.2380) time: 0.6011 data: 0.0032 max mem: 30263 +train: [14] [520/800] eta: 0:02:58 lr: 0.000085 loss: 0.4761 (0.5517) grad: 0.2396 (0.2379) time: 0.5868 data: 0.0034 max mem: 30263 +train: [14] [540/800] eta: 0:02:45 lr: 0.000084 loss: 0.5363 (0.5507) grad: 0.2522 (0.2388) time: 0.5749 data: 0.0038 max mem: 30263 +train: [14] [560/800] eta: 0:02:32 lr: 0.000083 loss: 0.5098 (0.5472) grad: 0.2522 (0.2382) time: 0.5885 data: 0.0031 max mem: 30263 +train: [14] [580/800] eta: 0:02:21 lr: 0.000083 loss: 0.5098 (0.5462) grad: 0.2396 (0.2384) time: 0.8891 data: 0.2935 max mem: 30263 +train: [14] [600/800] eta: 0:02:08 lr: 0.000082 loss: 0.5072 (0.5465) grad: 0.2326 (0.2387) time: 0.6035 data: 0.0039 max mem: 30263 +train: [14] [620/800] eta: 0:01:55 lr: 0.000081 loss: 0.5072 (0.5472) grad: 0.2326 (0.2395) time: 0.5719 data: 0.0031 max mem: 30263 +train: [14] [640/800] eta: 0:01:41 lr: 0.000081 loss: 0.5400 (0.5473) grad: 0.2326 (0.2392) time: 0.5678 data: 0.0036 max mem: 30263 +train: [14] [660/800] eta: 0:01:28 lr: 0.000080 loss: 0.5401 (0.5477) grad: 0.2264 (0.2395) time: 0.5565 data: 0.0036 max mem: 30263 +train: [14] [680/800] eta: 0:01:16 lr: 0.000079 loss: 0.5387 (0.5462) grad: 0.2264 (0.2406) time: 0.8213 data: 0.2655 max mem: 30263 +train: [14] [700/800] eta: 0:01:04 lr: 0.000078 loss: 0.5401 (0.5486) grad: 0.2264 (0.2406) time: 0.6378 data: 0.0035 max mem: 30263 +train: [14] [720/800] eta: 0:00:51 lr: 0.000078 loss: 0.5387 (0.5492) grad: 0.2490 (0.2415) time: 0.5606 data: 0.0035 max mem: 30263 +train: [14] [740/800] eta: 0:00:38 lr: 0.000077 loss: 0.5321 (0.5496) grad: 0.2364 (0.2404) time: 0.5590 data: 0.0036 max mem: 30263 +train: [14] [760/800] eta: 0:00:25 lr: 0.000076 loss: 0.5321 (0.5493) grad: 0.2347 (0.2413) time: 0.5547 data: 0.0025 max mem: 30263 +train: [14] [780/800] eta: 0:00:12 lr: 0.000076 loss: 0.5315 (0.5494) grad: 0.2225 (0.2422) time: 0.5756 data: 0.0033 max mem: 30263 +train: [14] [799/800] eta: 0:00:00 lr: 0.000075 loss: 0.5255 (0.5488) grad: 0.2199 (0.2423) time: 0.8553 data: 0.2997 max mem: 30263 +train: [14] Total time: 0:08:30 (0.6384 s / it) +train: [14] Summary: lr: 0.000075 loss: 0.5255 (0.5488) grad: 0.2199 (0.2423) +eval (validation): [14] [ 0/14] eta: 0:01:10 time: 5.0366 data: 4.6843 max mem: 30263 +eval (validation): [14] [13/14] eta: 0:00:00 time: 0.7678 data: 0.3376 max mem: 30263 +eval (validation): [14] Total time: 0:00:10 (0.7835 s / it) +cv: [14] best hparam: (8.3, 1.0) (037) ('037_lr8.3e+00_wd1.0e+00') loss: 4.083 acc: 0.434 f1: 0.435 bacc: 0.435 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_age__patch__attn/checkpoint-last.pth +train: [15] [ 0/800] eta: 1:10:57 lr: nan time: 5.3223 data: 4.8392 max mem: 30263 +train: [15] [ 20/800] eta: 0:11:08 lr: 0.000074 loss: 0.5507 (0.5374) grad: 0.2598 (0.2495) time: 0.6337 data: 0.0038 max mem: 30263 +train: [15] [ 40/800] eta: 0:09:07 lr: 0.000074 loss: 0.5507 (0.5578) grad: 0.2274 (0.2512) time: 0.5768 data: 0.0032 max mem: 30263 +train: [15] [ 60/800] eta: 0:08:19 lr: 0.000073 loss: 0.5838 (0.5646) grad: 0.2265 (0.2410) time: 0.5805 data: 0.0037 max mem: 30263 +train: [15] [ 80/800] eta: 0:07:50 lr: 0.000072 loss: 0.5611 (0.5425) grad: 0.2265 (0.2459) time: 0.5921 data: 0.0037 max mem: 30263 +train: [15] [100/800] eta: 0:07:27 lr: 0.000072 loss: 0.5166 (0.5261) grad: 0.2189 (0.2357) time: 0.5813 data: 0.0036 max mem: 30263 +train: [15] [120/800] eta: 0:07:33 lr: 0.000071 loss: 0.5118 (0.5241) grad: 0.2147 (0.2350) time: 0.8030 data: 0.2559 max mem: 30263 +train: [15] [140/800] eta: 0:07:18 lr: 0.000070 loss: 0.4739 (0.5249) grad: 0.2030 (0.2319) time: 0.6548 data: 0.0436 max mem: 30263 +train: [15] [160/800] eta: 0:06:57 lr: 0.000070 loss: 0.5117 (0.5336) grad: 0.2146 (0.2344) time: 0.5661 data: 0.0022 max mem: 30263 +train: [15] [180/800] eta: 0:06:39 lr: 0.000069 loss: 0.5296 (0.5377) grad: 0.2030 (0.2284) time: 0.5789 data: 0.0032 max mem: 30263 +train: [15] [200/800] eta: 0:06:22 lr: 0.000068 loss: 0.5410 (0.5294) grad: 0.2066 (0.2294) time: 0.5687 data: 0.0035 max mem: 30263 +train: [15] [220/800] eta: 0:06:06 lr: 0.000068 loss: 0.5490 (0.5341) grad: 0.2066 (0.2264) time: 0.5738 data: 0.0034 max mem: 30263 +train: [15] [240/800] eta: 0:06:03 lr: 0.000067 loss: 0.5296 (0.5349) grad: 0.2066 (0.2305) time: 0.8565 data: 0.2623 max mem: 30263 +train: [15] [260/800] eta: 0:05:49 lr: 0.000066 loss: 0.5331 (0.5373) grad: 0.2237 (0.2282) time: 0.6208 data: 0.0033 max mem: 30263 +train: [15] [280/800] eta: 0:05:34 lr: 0.000066 loss: 0.5331 (0.5373) grad: 0.2093 (0.2253) time: 0.5744 data: 0.0031 max mem: 30263 +train: [15] [300/800] eta: 0:05:18 lr: 0.000065 loss: 0.5331 (0.5405) grad: 0.2093 (0.2233) time: 0.5608 data: 0.0036 max mem: 30263 +train: [15] [320/800] eta: 0:05:03 lr: 0.000064 loss: 0.5538 (0.5402) grad: 0.1500 (0.2224) time: 0.5562 data: 0.0032 max mem: 30263 +train: [15] [340/800] eta: 0:04:55 lr: 0.000064 loss: 0.5046 (0.5385) grad: 0.1779 (0.2232) time: 0.7961 data: 0.2607 max mem: 30263 +train: [15] [360/800] eta: 0:04:42 lr: 0.000063 loss: 0.5046 (0.5353) grad: 0.1928 (0.2227) time: 0.6605 data: 0.0217 max mem: 30263 +train: [15] [380/800] eta: 0:04:28 lr: 0.000063 loss: 0.4966 (0.5319) grad: 0.1830 (0.2209) time: 0.5894 data: 0.0034 max mem: 30263 +train: [15] [400/800] eta: 0:04:14 lr: 0.000062 loss: 0.4966 (0.5345) grad: 0.1984 (0.2196) time: 0.5574 data: 0.0034 max mem: 30263 +train: [15] [420/800] eta: 0:04:00 lr: 0.000061 loss: 0.4966 (0.5342) grad: 0.2091 (0.2210) time: 0.5824 data: 0.0032 max mem: 30263 +train: [15] [440/800] eta: 0:03:46 lr: 0.000061 loss: 0.5002 (0.5325) grad: 0.2053 (0.2202) time: 0.5704 data: 0.0033 max mem: 30263 +train: [15] [460/800] eta: 0:03:37 lr: 0.000060 loss: 0.5296 (0.5338) grad: 0.2139 (0.2211) time: 0.8475 data: 0.2637 max mem: 30263 +train: [15] [480/800] eta: 0:03:24 lr: 0.000059 loss: 0.5135 (0.5343) grad: 0.2329 (0.2217) time: 0.6117 data: 0.0030 max mem: 30263 +train: [15] [500/800] eta: 0:03:10 lr: 0.000059 loss: 0.5122 (0.5327) grad: 0.2174 (0.2212) time: 0.5708 data: 0.0033 max mem: 30263 +train: [15] [520/800] eta: 0:02:57 lr: 0.000058 loss: 0.5122 (0.5316) grad: 0.2190 (0.2215) time: 0.5629 data: 0.0029 max mem: 30263 +train: [15] [540/800] eta: 0:02:43 lr: 0.000057 loss: 0.5103 (0.5313) grad: 0.2228 (0.2246) time: 0.5625 data: 0.0031 max mem: 30263 +train: [15] [560/800] eta: 0:02:30 lr: 0.000057 loss: 0.5067 (0.5327) grad: 0.2223 (0.2250) time: 0.5458 data: 0.0023 max mem: 30263 +train: [15] [580/800] eta: 0:02:19 lr: 0.000056 loss: 0.5067 (0.5312) grad: 0.2223 (0.2245) time: 0.8578 data: 0.2661 max mem: 30263 +train: [15] [600/800] eta: 0:02:06 lr: 0.000056 loss: 0.4859 (0.5301) grad: 0.2214 (0.2229) time: 0.5667 data: 0.0034 max mem: 30263 +train: [15] [620/800] eta: 0:01:53 lr: 0.000055 loss: 0.4859 (0.5314) grad: 0.1695 (0.2214) time: 0.5598 data: 0.0026 max mem: 30263 +train: [15] [640/800] eta: 0:01:40 lr: 0.000054 loss: 0.4916 (0.5309) grad: 0.1685 (0.2216) time: 0.6330 data: 0.0036 max mem: 30263 +train: [15] [660/800] eta: 0:01:28 lr: 0.000054 loss: 0.5357 (0.5330) grad: 0.1949 (0.2242) time: 0.5908 data: 0.0036 max mem: 30263 +train: [15] [680/800] eta: 0:01:16 lr: 0.000053 loss: 0.5379 (0.5330) grad: 0.2570 (0.2259) time: 0.8103 data: 0.2616 max mem: 30263 +train: [15] [700/800] eta: 0:01:03 lr: 0.000053 loss: 0.5379 (0.5339) grad: 0.2592 (0.2268) time: 0.6175 data: 0.0037 max mem: 30263 +train: [15] [720/800] eta: 0:00:50 lr: 0.000052 loss: 0.5480 (0.5360) grad: 0.2768 (0.2277) time: 0.5717 data: 0.0030 max mem: 30263 +train: [15] [740/800] eta: 0:00:37 lr: 0.000051 loss: 0.5379 (0.5366) grad: 0.2795 (0.2287) time: 0.5509 data: 0.0031 max mem: 30263 +train: [15] [760/800] eta: 0:00:25 lr: 0.000051 loss: 0.5505 (0.5356) grad: 0.2288 (0.2284) time: 0.5740 data: 0.0034 max mem: 30263 +train: [15] [780/800] eta: 0:00:12 lr: 0.000050 loss: 0.5205 (0.5350) grad: 0.2270 (0.2290) time: 0.5673 data: 0.0035 max mem: 30263 +train: [15] [799/800] eta: 0:00:00 lr: 0.000050 loss: 0.4839 (0.5356) grad: 0.2269 (0.2301) time: 0.8119 data: 0.2612 max mem: 30263 +train: [15] Total time: 0:08:25 (0.6324 s / it) +train: [15] Summary: lr: 0.000050 loss: 0.4839 (0.5356) grad: 0.2269 (0.2301) +eval (validation): [15] [ 0/14] eta: 0:01:12 time: 5.1646 data: 4.8528 max mem: 30263 +eval (validation): [15] [13/14] eta: 0:00:00 time: 0.7741 data: 0.3842 max mem: 30263 +eval (validation): [15] Total time: 0:00:11 (0.7900 s / it) +cv: [15] best hparam: (0.32, 1.0) (017) ('017_lr3.2e-01_wd1.0e+00') loss: 1.282 acc: 0.472 f1: 0.469 bacc: 0.467 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_age__patch__attn/checkpoint-last.pth +train: [16] [ 0/800] eta: 1:09:17 lr: nan time: 5.1970 data: 4.7672 max mem: 30263 +train: [16] [ 20/800] eta: 0:11:13 lr: 0.000049 loss: 0.5241 (0.5247) grad: 0.2345 (0.2420) time: 0.6462 data: 0.0633 max mem: 30263 +train: [16] [ 40/800] eta: 0:09:16 lr: 0.000048 loss: 0.4868 (0.5393) grad: 0.2236 (0.2493) time: 0.5946 data: 0.0356 max mem: 30263 +train: [16] [ 60/800] eta: 0:08:19 lr: 0.000048 loss: 0.5070 (0.5408) grad: 0.2345 (0.2534) time: 0.5577 data: 0.0024 max mem: 30263 +train: [16] [ 80/800] eta: 0:07:48 lr: 0.000047 loss: 0.4900 (0.5306) grad: 0.2345 (0.2533) time: 0.5795 data: 0.0037 max mem: 30263 +train: [16] [100/800] eta: 0:07:25 lr: 0.000047 loss: 0.4900 (0.5306) grad: 0.2510 (0.2499) time: 0.5753 data: 0.0035 max mem: 30263 +train: [16] [120/800] eta: 0:07:37 lr: 0.000046 loss: 0.4900 (0.5253) grad: 0.2467 (0.2429) time: 0.8594 data: 0.2583 max mem: 30263 +train: [16] [140/800] eta: 0:07:18 lr: 0.000046 loss: 0.4756 (0.5230) grad: 0.2135 (0.2382) time: 0.6134 data: 0.0040 max mem: 30263 +train: [16] [160/800] eta: 0:06:57 lr: 0.000045 loss: 0.4756 (0.5186) grad: 0.2135 (0.2410) time: 0.5643 data: 0.0034 max mem: 30263 +train: [16] [180/800] eta: 0:06:39 lr: 0.000045 loss: 0.4541 (0.5205) grad: 0.2164 (0.2406) time: 0.5826 data: 0.0034 max mem: 30263 +train: [16] [200/800] eta: 0:06:21 lr: 0.000044 loss: 0.4869 (0.5304) grad: 0.2164 (0.2377) time: 0.5630 data: 0.0033 max mem: 30263 +train: [16] [220/800] eta: 0:06:05 lr: 0.000043 loss: 0.5005 (0.5320) grad: 0.2386 (0.2369) time: 0.5609 data: 0.0034 max mem: 30263 +train: [16] [240/800] eta: 0:06:02 lr: 0.000043 loss: 0.5293 (0.5316) grad: 0.2164 (0.2338) time: 0.8364 data: 0.2723 max mem: 30263 +train: [16] [260/800] eta: 0:05:48 lr: 0.000042 loss: 0.5293 (0.5321) grad: 0.2121 (0.2318) time: 0.6337 data: 0.0096 max mem: 30263 +train: [16] [280/800] eta: 0:05:33 lr: 0.000042 loss: 0.5311 (0.5312) grad: 0.2194 (0.2295) time: 0.5971 data: 0.0036 max mem: 30263 +train: [16] [300/800] eta: 0:05:18 lr: 0.000041 loss: 0.5237 (0.5284) grad: 0.2121 (0.2263) time: 0.5711 data: 0.0034 max mem: 30263 +train: [16] [320/800] eta: 0:05:03 lr: 0.000041 loss: 0.5049 (0.5250) grad: 0.2068 (0.2256) time: 0.5620 data: 0.0034 max mem: 30263 +train: [16] [340/800] eta: 0:04:56 lr: 0.000040 loss: 0.5049 (0.5266) grad: 0.1961 (0.2225) time: 0.8221 data: 0.2681 max mem: 30263 +train: [16] [360/800] eta: 0:04:41 lr: 0.000040 loss: 0.5296 (0.5294) grad: 0.1961 (0.2222) time: 0.5549 data: 0.0028 max mem: 30263 +train: [16] [380/800] eta: 0:04:27 lr: 0.000039 loss: 0.5477 (0.5317) grad: 0.2021 (0.2204) time: 0.5907 data: 0.0357 max mem: 30263 +train: [16] [400/800] eta: 0:04:13 lr: 0.000039 loss: 0.5477 (0.5301) grad: 0.2021 (0.2203) time: 0.5722 data: 0.0129 max mem: 30263 +train: [16] [420/800] eta: 0:03:59 lr: 0.000038 loss: 0.5477 (0.5291) grad: 0.2133 (0.2224) time: 0.5694 data: 0.0030 max mem: 30263 +train: [16] [440/800] eta: 0:03:45 lr: 0.000038 loss: 0.5495 (0.5303) grad: 0.2225 (0.2249) time: 0.5760 data: 0.0026 max mem: 30263 +train: [16] [460/800] eta: 0:03:36 lr: 0.000037 loss: 0.4818 (0.5295) grad: 0.2133 (0.2239) time: 0.8256 data: 0.2620 max mem: 30263 +train: [16] [480/800] eta: 0:03:23 lr: 0.000036 loss: 0.5315 (0.5318) grad: 0.2291 (0.2241) time: 0.5931 data: 0.0032 max mem: 30263 +train: [16] [500/800] eta: 0:03:09 lr: 0.000036 loss: 0.5533 (0.5324) grad: 0.2099 (0.2230) time: 0.5870 data: 0.0033 max mem: 30263 +train: [16] [520/800] eta: 0:02:56 lr: 0.000035 loss: 0.5160 (0.5328) grad: 0.2042 (0.2229) time: 0.6064 data: 0.0039 max mem: 30263 +train: [16] [540/800] eta: 0:02:43 lr: 0.000035 loss: 0.5333 (0.5337) grad: 0.1757 (0.2221) time: 0.5799 data: 0.0036 max mem: 30263 +train: [16] [560/800] eta: 0:02:30 lr: 0.000034 loss: 0.4886 (0.5318) grad: 0.1945 (0.2218) time: 0.5577 data: 0.0034 max mem: 30263 +train: [16] [580/800] eta: 0:02:19 lr: 0.000034 loss: 0.4955 (0.5331) grad: 0.2012 (0.2227) time: 0.8432 data: 0.2860 max mem: 30263 +train: [16] [600/800] eta: 0:02:06 lr: 0.000033 loss: 0.4721 (0.5333) grad: 0.1938 (0.2215) time: 0.5927 data: 0.0041 max mem: 30263 +train: [16] [620/800] eta: 0:01:53 lr: 0.000033 loss: 0.4721 (0.5321) grad: 0.2154 (0.2220) time: 0.5691 data: 0.0026 max mem: 30263 +train: [16] [640/800] eta: 0:01:40 lr: 0.000032 loss: 0.4922 (0.5321) grad: 0.2159 (0.2223) time: 0.5619 data: 0.0034 max mem: 30263 +train: [16] [660/800] eta: 0:01:27 lr: 0.000032 loss: 0.4914 (0.5317) grad: 0.2201 (0.2222) time: 0.5696 data: 0.0034 max mem: 30263 +train: [16] [680/800] eta: 0:01:15 lr: 0.000031 loss: 0.4922 (0.5308) grad: 0.2312 (0.2220) time: 0.8275 data: 0.2597 max mem: 30263 +train: [16] [700/800] eta: 0:01:03 lr: 0.000031 loss: 0.5329 (0.5308) grad: 0.1838 (0.2199) time: 0.6128 data: 0.0031 max mem: 30263 +train: [16] [720/800] eta: 0:00:50 lr: 0.000031 loss: 0.5329 (0.5302) grad: 0.1986 (0.2204) time: 0.5775 data: 0.0032 max mem: 30263 +train: [16] [740/800] eta: 0:00:37 lr: 0.000030 loss: 0.5101 (0.5299) grad: 0.1986 (0.2203) time: 0.6135 data: 0.0036 max mem: 30263 +train: [16] [760/800] eta: 0:00:25 lr: 0.000030 loss: 0.5101 (0.5323) grad: 0.2084 (0.2207) time: 0.5825 data: 0.0034 max mem: 30263 +train: [16] [780/800] eta: 0:00:12 lr: 0.000029 loss: 0.5090 (0.5326) grad: 0.2294 (0.2214) time: 0.5848 data: 0.0034 max mem: 30263 +train: [16] [799/800] eta: 0:00:00 lr: 0.000029 loss: 0.5090 (0.5316) grad: 0.2294 (0.2209) time: 0.8786 data: 0.3143 max mem: 30263 +train: [16] Total time: 0:08:27 (0.6347 s / it) +train: [16] Summary: lr: 0.000029 loss: 0.5090 (0.5316) grad: 0.2294 (0.2209) +eval (validation): [16] [ 0/14] eta: 0:01:12 time: 5.1943 data: 4.8364 max mem: 30263 +eval (validation): [16] [13/14] eta: 0:00:00 time: 0.7982 data: 0.3901 max mem: 30263 +eval (validation): [16] Total time: 0:00:11 (0.8155 s / it) +cv: [16] best hparam: (0.38, 1.0) (018) ('018_lr3.8e-01_wd1.0e+00') loss: 1.390 acc: 0.472 f1: 0.466 bacc: 0.465 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_age__patch__attn/checkpoint-last.pth +train: [17] [ 0/800] eta: 1:09:57 lr: nan time: 5.2465 data: 4.8022 max mem: 30263 +train: [17] [ 20/800] eta: 0:11:35 lr: 0.000028 loss: 0.5078 (0.5404) grad: 0.3164 (0.2946) time: 0.6735 data: 0.0043 max mem: 30263 +train: [17] [ 40/800] eta: 0:09:22 lr: 0.000028 loss: 0.4805 (0.5473) grad: 0.2458 (0.2586) time: 0.5807 data: 0.0031 max mem: 30263 +train: [17] [ 60/800] eta: 0:08:28 lr: 0.000027 loss: 0.5078 (0.5570) grad: 0.2284 (0.2353) time: 0.5784 data: 0.0034 max mem: 30263 +train: [17] [ 80/800] eta: 0:07:56 lr: 0.000027 loss: 0.5078 (0.5515) grad: 0.2023 (0.2326) time: 0.5861 data: 0.0034 max mem: 30263 +train: [17] [100/800] eta: 0:07:32 lr: 0.000026 loss: 0.5462 (0.5558) grad: 0.2023 (0.2380) time: 0.5824 data: 0.0034 max mem: 30263 +train: [17] [120/800] eta: 0:07:42 lr: 0.000026 loss: 0.6029 (0.5625) grad: 0.2110 (0.2442) time: 0.8487 data: 0.2577 max mem: 30263 +train: [17] [140/800] eta: 0:07:20 lr: 0.000026 loss: 0.5847 (0.5659) grad: 0.2400 (0.2404) time: 0.5948 data: 0.0037 max mem: 30263 +train: [17] [160/800] eta: 0:07:02 lr: 0.000025 loss: 0.5847 (0.5627) grad: 0.2532 (0.2406) time: 0.6121 data: 0.0029 max mem: 30263 +train: [17] [180/800] eta: 0:06:43 lr: 0.000025 loss: 0.5671 (0.5567) grad: 0.2400 (0.2404) time: 0.5651 data: 0.0033 max mem: 30263 +train: [17] [200/800] eta: 0:06:25 lr: 0.000024 loss: 0.5481 (0.5545) grad: 0.2266 (0.2414) time: 0.5693 data: 0.0035 max mem: 30263 +train: [17] [220/800] eta: 0:06:08 lr: 0.000024 loss: 0.5225 (0.5507) grad: 0.2266 (0.2402) time: 0.5656 data: 0.0033 max mem: 30263 +train: [17] [240/800] eta: 0:06:05 lr: 0.000023 loss: 0.5225 (0.5517) grad: 0.2172 (0.2376) time: 0.8403 data: 0.2682 max mem: 30263 +train: [17] [260/800] eta: 0:05:50 lr: 0.000023 loss: 0.5189 (0.5495) grad: 0.2107 (0.2382) time: 0.6080 data: 0.0369 max mem: 30263 +train: [17] [280/800] eta: 0:05:33 lr: 0.000023 loss: 0.4992 (0.5465) grad: 0.1978 (0.2341) time: 0.5567 data: 0.0023 max mem: 30263 +train: [17] [300/800] eta: 0:05:18 lr: 0.000022 loss: 0.4992 (0.5429) grad: 0.2086 (0.2350) time: 0.5626 data: 0.0029 max mem: 30263 +train: [17] [320/800] eta: 0:05:03 lr: 0.000022 loss: 0.5189 (0.5505) grad: 0.2086 (0.2357) time: 0.5537 data: 0.0031 max mem: 30263 +train: [17] [340/800] eta: 0:04:55 lr: 0.000021 loss: 0.5136 (0.5476) grad: 0.2061 (0.2327) time: 0.8158 data: 0.2660 max mem: 30263 +train: [17] [360/800] eta: 0:04:41 lr: 0.000021 loss: 0.5278 (0.5482) grad: 0.2061 (0.2322) time: 0.5969 data: 0.0031 max mem: 30263 +train: [17] [380/800] eta: 0:04:28 lr: 0.000021 loss: 0.5278 (0.5454) grad: 0.2003 (0.2304) time: 0.6298 data: 0.0038 max mem: 30263 +train: [17] [400/800] eta: 0:04:15 lr: 0.000020 loss: 0.5136 (0.5452) grad: 0.2003 (0.2352) time: 0.6210 data: 0.0040 max mem: 30263 +train: [17] [420/800] eta: 0:04:01 lr: 0.000020 loss: 0.5621 (0.5501) grad: 0.2195 (0.2358) time: 0.5995 data: 0.0031 max mem: 30263 +train: [17] [440/800] eta: 0:03:48 lr: 0.000019 loss: 0.5012 (0.5466) grad: 0.2195 (0.2350) time: 0.5764 data: 0.0035 max mem: 30263 +train: [17] [460/800] eta: 0:03:38 lr: 0.000019 loss: 0.5012 (0.5446) grad: 0.2180 (0.2332) time: 0.8139 data: 0.2620 max mem: 30263 +train: [17] [480/800] eta: 0:03:24 lr: 0.000019 loss: 0.4883 (0.5431) grad: 0.2067 (0.2322) time: 0.5872 data: 0.0031 max mem: 30263 +train: [17] [500/800] eta: 0:03:10 lr: 0.000018 loss: 0.4514 (0.5427) grad: 0.1897 (0.2317) time: 0.5663 data: 0.0035 max mem: 30263 +train: [17] [520/800] eta: 0:02:57 lr: 0.000018 loss: 0.4784 (0.5439) grad: 0.2203 (0.2328) time: 0.5700 data: 0.0032 max mem: 30263 +train: [17] [540/800] eta: 0:02:44 lr: 0.000017 loss: 0.4910 (0.5460) grad: 0.2604 (0.2349) time: 0.6006 data: 0.0037 max mem: 30263 +train: [17] [560/800] eta: 0:02:31 lr: 0.000017 loss: 0.5186 (0.5456) grad: 0.2604 (0.2344) time: 0.5648 data: 0.0033 max mem: 30263 +train: [17] [580/800] eta: 0:02:20 lr: 0.000017 loss: 0.5186 (0.5446) grad: 0.2447 (0.2342) time: 0.8915 data: 0.3078 max mem: 30263 +train: [17] [600/800] eta: 0:02:07 lr: 0.000016 loss: 0.4978 (0.5410) grad: 0.2434 (0.2352) time: 0.5766 data: 0.0034 max mem: 30263 +train: [17] [620/800] eta: 0:01:54 lr: 0.000016 loss: 0.4801 (0.5388) grad: 0.2358 (0.2353) time: 0.5850 data: 0.0037 max mem: 30263 +train: [17] [640/800] eta: 0:01:41 lr: 0.000016 loss: 0.4714 (0.5401) grad: 0.2358 (0.2362) time: 0.5766 data: 0.0034 max mem: 30263 +train: [17] [660/800] eta: 0:01:28 lr: 0.000015 loss: 0.4656 (0.5400) grad: 0.2374 (0.2371) time: 0.5770 data: 0.0034 max mem: 30263 +train: [17] [680/800] eta: 0:01:16 lr: 0.000015 loss: 0.4871 (0.5386) grad: 0.2255 (0.2349) time: 0.9105 data: 0.3605 max mem: 30263 +train: [17] [700/800] eta: 0:01:03 lr: 0.000015 loss: 0.4933 (0.5371) grad: 0.2135 (0.2347) time: 0.5566 data: 0.0025 max mem: 30263 +train: [17] [720/800] eta: 0:00:50 lr: 0.000014 loss: 0.5003 (0.5375) grad: 0.2102 (0.2343) time: 0.5577 data: 0.0027 max mem: 30263 +train: [17] [740/800] eta: 0:00:38 lr: 0.000014 loss: 0.5003 (0.5385) grad: 0.1898 (0.2339) time: 0.5821 data: 0.0034 max mem: 30263 +train: [17] [760/800] eta: 0:00:25 lr: 0.000014 loss: 0.5645 (0.5393) grad: 0.1902 (0.2334) time: 0.6002 data: 0.0039 max mem: 30263 +train: [17] [780/800] eta: 0:00:12 lr: 0.000013 loss: 0.5536 (0.5390) grad: 0.2114 (0.2335) time: 0.5670 data: 0.0034 max mem: 30263 +train: [17] [799/800] eta: 0:00:00 lr: 0.000013 loss: 0.5520 (0.5423) grad: 0.2114 (0.2321) time: 0.8778 data: 0.2623 max mem: 30263 +train: [17] Total time: 0:08:30 (0.6381 s / it) +train: [17] Summary: lr: 0.000013 loss: 0.5520 (0.5423) grad: 0.2114 (0.2321) +eval (validation): [17] [ 0/14] eta: 0:01:14 time: 5.3377 data: 5.0063 max mem: 30263 +eval (validation): [17] [13/14] eta: 0:00:00 time: 0.7859 data: 0.3829 max mem: 30263 +eval (validation): [17] Total time: 0:00:11 (0.8040 s / it) +cv: [17] best hparam: (0.087, 1.0) (009) ('009_lr8.7e-02_wd1.0e+00') loss: 1.196 acc: 0.453 f1: 0.449 bacc: 0.449 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_age__patch__attn/checkpoint-last.pth +train: [18] [ 0/800] eta: 1:11:50 lr: nan time: 5.3880 data: 4.9082 max mem: 30263 +train: [18] [ 20/800] eta: 0:10:51 lr: 0.000013 loss: 0.6230 (0.6551) grad: 0.2672 (0.2571) time: 0.6075 data: 0.0022 max mem: 30263 +train: [18] [ 40/800] eta: 0:09:00 lr: 0.000012 loss: 0.4693 (0.5538) grad: 0.2129 (0.2256) time: 0.5815 data: 0.0035 max mem: 30263 +train: [18] [ 60/800] eta: 0:08:15 lr: 0.000012 loss: 0.5226 (0.5310) grad: 0.2129 (0.2208) time: 0.5824 data: 0.0033 max mem: 30263 +train: [18] [ 80/800] eta: 0:07:48 lr: 0.000012 loss: 0.4793 (0.5203) grad: 0.2080 (0.2184) time: 0.5929 data: 0.0034 max mem: 30263 +train: [18] [100/800] eta: 0:07:23 lr: 0.000011 loss: 0.4717 (0.5249) grad: 0.2024 (0.2249) time: 0.5680 data: 0.0033 max mem: 30263 +train: [18] [120/800] eta: 0:07:32 lr: 0.000011 loss: 0.5141 (0.5359) grad: 0.2099 (0.2307) time: 0.8270 data: 0.2728 max mem: 30263 +train: [18] [140/800] eta: 0:07:11 lr: 0.000011 loss: 0.5016 (0.5304) grad: 0.1900 (0.2251) time: 0.5841 data: 0.0039 max mem: 30263 +train: [18] [160/800] eta: 0:06:52 lr: 0.000011 loss: 0.5194 (0.5335) grad: 0.2099 (0.2239) time: 0.5749 data: 0.0030 max mem: 30263 +train: [18] [180/800] eta: 0:06:35 lr: 0.000010 loss: 0.5194 (0.5344) grad: 0.2201 (0.2262) time: 0.5827 data: 0.0032 max mem: 30263 +train: [18] [200/800] eta: 0:06:19 lr: 0.000010 loss: 0.5216 (0.5369) grad: 0.2259 (0.2323) time: 0.5799 data: 0.0032 max mem: 30263 +train: [18] [220/800] eta: 0:06:03 lr: 0.000010 loss: 0.5194 (0.5320) grad: 0.2550 (0.2363) time: 0.5717 data: 0.0034 max mem: 30263 +train: [18] [240/800] eta: 0:06:01 lr: 0.000009 loss: 0.5113 (0.5317) grad: 0.2259 (0.2322) time: 0.8625 data: 0.2885 max mem: 30263 +train: [18] [260/800] eta: 0:05:45 lr: 0.000009 loss: 0.5113 (0.5328) grad: 0.2240 (0.2285) time: 0.5714 data: 0.0034 max mem: 30263 +train: [18] [280/800] eta: 0:05:30 lr: 0.000009 loss: 0.4939 (0.5316) grad: 0.2068 (0.2285) time: 0.5837 data: 0.0036 max mem: 30263 +train: [18] [300/800] eta: 0:05:15 lr: 0.000009 loss: 0.5113 (0.5356) grad: 0.2068 (0.2293) time: 0.5691 data: 0.0027 max mem: 30263 +train: [18] [320/800] eta: 0:05:01 lr: 0.000008 loss: 0.5265 (0.5356) grad: 0.1817 (0.2257) time: 0.5691 data: 0.0032 max mem: 30263 +train: [18] [340/800] eta: 0:04:54 lr: 0.000008 loss: 0.5122 (0.5331) grad: 0.1891 (0.2243) time: 0.8315 data: 0.2649 max mem: 30263 +train: [18] [360/800] eta: 0:04:41 lr: 0.000008 loss: 0.5420 (0.5347) grad: 0.1922 (0.2241) time: 0.6205 data: 0.0034 max mem: 30263 +train: [18] [380/800] eta: 0:04:26 lr: 0.000008 loss: 0.5217 (0.5323) grad: 0.1922 (0.2250) time: 0.5748 data: 0.0032 max mem: 30263 +train: [18] [400/800] eta: 0:04:12 lr: 0.000007 loss: 0.5122 (0.5317) grad: 0.2103 (0.2241) time: 0.5756 data: 0.0033 max mem: 30263 +train: [18] [420/800] eta: 0:03:59 lr: 0.000007 loss: 0.5217 (0.5307) grad: 0.2234 (0.2253) time: 0.5663 data: 0.0035 max mem: 30263 +train: [18] [440/800] eta: 0:03:45 lr: 0.000007 loss: 0.5059 (0.5315) grad: 0.2069 (0.2245) time: 0.5788 data: 0.0032 max mem: 30263 +train: [18] [460/800] eta: 0:03:36 lr: 0.000007 loss: 0.5136 (0.5327) grad: 0.2128 (0.2254) time: 0.8436 data: 0.2679 max mem: 30263 +train: [18] [480/800] eta: 0:03:23 lr: 0.000006 loss: 0.5136 (0.5342) grad: 0.2128 (0.2254) time: 0.6130 data: 0.0032 max mem: 30263 +train: [18] [500/800] eta: 0:03:09 lr: 0.000006 loss: 0.5866 (0.5357) grad: 0.2011 (0.2243) time: 0.5585 data: 0.0036 max mem: 30263 +train: [18] [520/800] eta: 0:02:56 lr: 0.000006 loss: 0.5261 (0.5360) grad: 0.2128 (0.2244) time: 0.5757 data: 0.0033 max mem: 30263 +train: [18] [540/800] eta: 0:02:43 lr: 0.000006 loss: 0.5195 (0.5342) grad: 0.1891 (0.2229) time: 0.5833 data: 0.0034 max mem: 30263 +train: [18] [560/800] eta: 0:02:30 lr: 0.000006 loss: 0.5214 (0.5345) grad: 0.2011 (0.2242) time: 0.5682 data: 0.0033 max mem: 30263 +train: [18] [580/800] eta: 0:02:19 lr: 0.000005 loss: 0.5214 (0.5343) grad: 0.2040 (0.2245) time: 0.8559 data: 0.2633 max mem: 30263 +train: [18] [600/800] eta: 0:02:06 lr: 0.000005 loss: 0.5112 (0.5333) grad: 0.2123 (0.2267) time: 0.5719 data: 0.0031 max mem: 30263 +train: [18] [620/800] eta: 0:01:53 lr: 0.000005 loss: 0.5477 (0.5350) grad: 0.2193 (0.2261) time: 0.5703 data: 0.0036 max mem: 30263 +train: [18] [640/800] eta: 0:01:40 lr: 0.000005 loss: 0.5231 (0.5341) grad: 0.2422 (0.2257) time: 0.5640 data: 0.0032 max mem: 30263 +train: [18] [660/800] eta: 0:01:27 lr: 0.000005 loss: 0.5112 (0.5348) grad: 0.2193 (0.2258) time: 0.5624 data: 0.0032 max mem: 30263 +train: [18] [680/800] eta: 0:01:15 lr: 0.000004 loss: 0.5150 (0.5337) grad: 0.2003 (0.2243) time: 0.8123 data: 0.2633 max mem: 30263 +train: [18] [700/800] eta: 0:01:03 lr: 0.000004 loss: 0.4789 (0.5318) grad: 0.2003 (0.2252) time: 0.6792 data: 0.0536 max mem: 30263 +train: [18] [720/800] eta: 0:00:50 lr: 0.000004 loss: 0.4958 (0.5313) grad: 0.2003 (0.2256) time: 0.5686 data: 0.0029 max mem: 30263 +train: [18] [740/800] eta: 0:00:37 lr: 0.000004 loss: 0.5121 (0.5339) grad: 0.2076 (0.2257) time: 0.5897 data: 0.0037 max mem: 30263 +train: [18] [760/800] eta: 0:00:25 lr: 0.000004 loss: 0.5061 (0.5340) grad: 0.2150 (0.2257) time: 0.5766 data: 0.0035 max mem: 30263 +train: [18] [780/800] eta: 0:00:12 lr: 0.000003 loss: 0.5343 (0.5347) grad: 0.2090 (0.2250) time: 0.5731 data: 0.0034 max mem: 30263 +train: [18] [799/800] eta: 0:00:00 lr: 0.000003 loss: 0.5690 (0.5350) grad: 0.2150 (0.2252) time: 0.9355 data: 0.3607 max mem: 30263 +train: [18] Total time: 0:08:28 (0.6353 s / it) +train: [18] Summary: lr: 0.000003 loss: 0.5690 (0.5350) grad: 0.2150 (0.2252) +eval (validation): [18] [ 0/14] eta: 0:01:10 time: 5.0340 data: 4.6857 max mem: 30263 +eval (validation): [18] [13/14] eta: 0:00:00 time: 0.7573 data: 0.3767 max mem: 30263 +eval (validation): [18] Total time: 0:00:10 (0.7748 s / it) +cv: [18] best hparam: (0.087, 1.0) (009) ('009_lr8.7e-02_wd1.0e+00') loss: 1.196 acc: 0.453 f1: 0.449 bacc: 0.449 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_age__patch__attn/checkpoint-last.pth +train: [19] [ 0/800] eta: 1:09:55 lr: nan time: 5.2443 data: 4.7840 max mem: 30263 +train: [19] [ 20/800] eta: 0:10:14 lr: 0.000003 loss: 0.5283 (0.5470) grad: 0.2308 (0.2268) time: 0.5647 data: 0.0023 max mem: 30263 +train: [19] [ 40/800] eta: 0:08:33 lr: 0.000003 loss: 0.4679 (0.5323) grad: 0.2409 (0.2493) time: 0.5591 data: 0.0029 max mem: 30263 +train: [19] [ 60/800] eta: 0:07:50 lr: 0.000003 loss: 0.4844 (0.5200) grad: 0.2409 (0.2389) time: 0.5543 data: 0.0028 max mem: 30263 +train: [19] [ 80/800] eta: 0:07:33 lr: 0.000003 loss: 0.5201 (0.5418) grad: 0.2032 (0.2286) time: 0.6113 data: 0.0037 max mem: 30263 +train: [19] [100/800] eta: 0:07:17 lr: 0.000003 loss: 0.5197 (0.5442) grad: 0.2032 (0.2342) time: 0.6056 data: 0.0034 max mem: 30263 +train: [19] [120/800] eta: 0:07:26 lr: 0.000002 loss: 0.5453 (0.5607) grad: 0.2032 (0.2360) time: 0.8131 data: 0.2592 max mem: 30263 +train: [19] [140/800] eta: 0:07:03 lr: 0.000002 loss: 0.5609 (0.5561) grad: 0.2119 (0.2364) time: 0.5557 data: 0.0032 max mem: 30263 +train: [19] [160/800] eta: 0:06:45 lr: 0.000002 loss: 0.5363 (0.5533) grad: 0.2537 (0.2384) time: 0.5700 data: 0.0187 max mem: 30263 +train: [19] [180/800] eta: 0:06:27 lr: 0.000002 loss: 0.5271 (0.5465) grad: 0.2700 (0.2444) time: 0.5676 data: 0.0025 max mem: 30263 +train: [19] [200/800] eta: 0:06:14 lr: 0.000002 loss: 0.5145 (0.5434) grad: 0.2333 (0.2420) time: 0.6092 data: 0.0042 max mem: 30263 +train: [19] [220/800] eta: 0:06:00 lr: 0.000002 loss: 0.5336 (0.5438) grad: 0.2505 (0.2416) time: 0.5895 data: 0.0036 max mem: 30263 +train: [19] [240/800] eta: 0:05:57 lr: 0.000002 loss: 0.5241 (0.5419) grad: 0.2348 (0.2400) time: 0.8343 data: 0.2669 max mem: 30263 +train: [19] [260/800] eta: 0:05:41 lr: 0.000001 loss: 0.5336 (0.5424) grad: 0.2348 (0.2434) time: 0.5536 data: 0.0033 max mem: 30263 +train: [19] [280/800] eta: 0:05:26 lr: 0.000001 loss: 0.5617 (0.5448) grad: 0.2348 (0.2380) time: 0.5731 data: 0.0038 max mem: 30263 +train: [19] [300/800] eta: 0:05:13 lr: 0.000001 loss: 0.5424 (0.5427) grad: 0.2165 (0.2357) time: 0.6057 data: 0.0029 max mem: 30263 +train: [19] [320/800] eta: 0:04:59 lr: 0.000001 loss: 0.5354 (0.5430) grad: 0.1878 (0.2339) time: 0.5982 data: 0.0035 max mem: 30263 +train: [19] [340/800] eta: 0:04:52 lr: 0.000001 loss: 0.5388 (0.5442) grad: 0.1774 (0.2354) time: 0.8232 data: 0.2621 max mem: 30263 +train: [19] [360/800] eta: 0:04:38 lr: 0.000001 loss: 0.5329 (0.5448) grad: 0.1930 (0.2350) time: 0.5740 data: 0.0032 max mem: 30263 +train: [19] [380/800] eta: 0:04:24 lr: 0.000001 loss: 0.5139 (0.5442) grad: 0.2249 (0.2346) time: 0.5544 data: 0.0030 max mem: 30263 +train: [19] [400/800] eta: 0:04:10 lr: 0.000001 loss: 0.5979 (0.5520) grad: 0.2334 (0.2355) time: 0.5608 data: 0.0033 max mem: 30263 +train: [19] [420/800] eta: 0:03:56 lr: 0.000001 loss: 0.5211 (0.5498) grad: 0.2496 (0.2374) time: 0.5500 data: 0.0022 max mem: 30263 +train: [19] [440/800] eta: 0:03:42 lr: 0.000001 loss: 0.5139 (0.5477) grad: 0.2334 (0.2377) time: 0.5691 data: 0.0033 max mem: 30263 +train: [19] [460/800] eta: 0:03:33 lr: 0.000001 loss: 0.5211 (0.5482) grad: 0.2196 (0.2355) time: 0.8439 data: 0.2957 max mem: 30263 +train: [19] [480/800] eta: 0:03:20 lr: 0.000001 loss: 0.4968 (0.5478) grad: 0.1989 (0.2327) time: 0.5708 data: 0.0018 max mem: 30263 +train: [19] [500/800] eta: 0:03:07 lr: 0.000000 loss: 0.4968 (0.5483) grad: 0.1857 (0.2334) time: 0.6096 data: 0.0039 max mem: 30263 +train: [19] [520/800] eta: 0:02:54 lr: 0.000000 loss: 0.5303 (0.5465) grad: 0.1831 (0.2317) time: 0.5887 data: 0.0024 max mem: 30263 +train: [19] [540/800] eta: 0:02:41 lr: 0.000000 loss: 0.5303 (0.5455) grad: 0.1857 (0.2322) time: 0.5621 data: 0.0029 max mem: 30263 +train: [19] [560/800] eta: 0:02:28 lr: 0.000000 loss: 0.4849 (0.5440) grad: 0.2190 (0.2327) time: 0.5655 data: 0.0027 max mem: 30263 +train: [19] [580/800] eta: 0:02:18 lr: 0.000000 loss: 0.4849 (0.5423) grad: 0.2097 (0.2306) time: 0.8874 data: 0.3038 max mem: 30263 +train: [19] [600/800] eta: 0:02:05 lr: 0.000000 loss: 0.5107 (0.5428) grad: 0.2074 (0.2296) time: 0.5848 data: 0.0033 max mem: 30263 +train: [19] [620/800] eta: 0:01:52 lr: 0.000000 loss: 0.5107 (0.5433) grad: 0.1973 (0.2282) time: 0.5641 data: 0.0035 max mem: 30263 +train: [19] [640/800] eta: 0:01:40 lr: 0.000000 loss: 0.5149 (0.5422) grad: 0.1924 (0.2289) time: 0.6302 data: 0.0040 max mem: 30263 +train: [19] [660/800] eta: 0:01:27 lr: 0.000000 loss: 0.5149 (0.5420) grad: 0.2216 (0.2307) time: 0.6457 data: 0.0038 max mem: 30263 +train: [19] [680/800] eta: 0:01:15 lr: 0.000000 loss: 0.5233 (0.5415) grad: 0.2264 (0.2314) time: 0.8070 data: 0.2567 max mem: 30263 +train: [19] [700/800] eta: 0:01:03 lr: 0.000000 loss: 0.4946 (0.5389) grad: 0.2450 (0.2314) time: 0.5682 data: 0.0026 max mem: 30263 +train: [19] [720/800] eta: 0:00:50 lr: 0.000000 loss: 0.4573 (0.5374) grad: 0.2283 (0.2300) time: 0.5684 data: 0.0034 max mem: 30263 +train: [19] [740/800] eta: 0:00:37 lr: 0.000000 loss: 0.4887 (0.5398) grad: 0.2216 (0.2298) time: 0.5530 data: 0.0029 max mem: 30263 +train: [19] [760/800] eta: 0:00:24 lr: 0.000000 loss: 0.5097 (0.5414) grad: 0.1855 (0.2277) time: 0.5726 data: 0.0033 max mem: 30263 +train: [19] [780/800] eta: 0:00:12 lr: 0.000000 loss: 0.5826 (0.5416) grad: 0.1829 (0.2282) time: 0.5685 data: 0.0027 max mem: 30263 +train: [19] [799/800] eta: 0:00:00 lr: 0.000000 loss: 0.5999 (0.5426) grad: 0.1872 (0.2277) time: 0.8421 data: 0.2897 max mem: 30263 +train: [19] Total time: 0:08:23 (0.6294 s / it) +train: [19] Summary: lr: 0.000000 loss: 0.5999 (0.5426) grad: 0.1872 (0.2277) +eval (validation): [19] [ 0/14] eta: 0:01:10 time: 5.0038 data: 4.7082 max mem: 30263 +eval (validation): [19] [13/14] eta: 0:00:00 time: 0.7480 data: 0.3591 max mem: 30263 +eval (validation): [19] Total time: 0:00:10 (0.7644 s / it) +cv: [19] best hparam: (0.087, 1.0) (009) ('009_lr8.7e-02_wd1.0e+00') loss: 1.196 acc: 0.453 f1: 0.449 bacc: 0.449 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_age__patch__attn/checkpoint-last.pth +evaluating last checkpoint: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_age__patch__attn/checkpoint-last.pth +eval model info: +{"score": 0.4487179487179487, "hparam": [0.087, 1.0], "hparam_id": 9, "epoch": 19, "is_best": false, "best_score": 0.5309065934065934} +eval (train): [20] [ 0/114] eta: 0:10:26 time: 5.4987 data: 5.1585 max mem: 30263 +eval (train): [20] [ 20/114] eta: 0:01:15 time: 0.5725 data: 0.0860 max mem: 30263 +eval (train): [20] [ 40/114] eta: 0:00:54 time: 0.6680 data: 0.1505 max mem: 30263 +eval (train): [20] [ 60/114] eta: 0:00:38 time: 0.6688 data: 0.1057 max mem: 30263 +eval (train): [20] [ 80/114] eta: 0:00:24 time: 0.7291 data: 0.2606 max mem: 30263 +eval (train): [20] [100/114] eta: 0:00:09 time: 0.5411 data: 0.0679 max mem: 30263 +eval (train): [20] [113/114] eta: 0:00:00 time: 0.5667 data: 0.1445 max mem: 30263 +eval (train): [20] Total time: 0:01:16 (0.6743 s / it) +eval (validation): [20] [ 0/14] eta: 0:01:14 time: 5.3376 data: 5.0334 max mem: 30263 +eval (validation): [20] [13/14] eta: 0:00:00 time: 0.8302 data: 0.4385 max mem: 30263 +eval (validation): [20] Total time: 0:00:11 (0.8393 s / it) +eval (test): [20] [ 0/13] eta: 0:01:10 time: 5.4200 data: 5.0987 max mem: 30263 +eval (test): [20] [12/13] eta: 0:00:00 time: 0.9148 data: 0.5102 max mem: 30263 +eval (test): [20] Total time: 0:00:12 (0.9244 s / it) +evaluating best checkpoint: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_age__patch__attn/checkpoint-best.pth +eval model info: +{"score": 0.5309065934065934, "hparam": [1.6, 1.0], "hparam_id": 27, "epoch": 4, "is_best": true, "best_score": 0.5309065934065934} +eval (train): [20] [ 0/114] eta: 0:10:20 time: 5.4420 data: 5.1384 max mem: 30263 +eval (train): [20] [ 20/114] eta: 0:01:21 time: 0.6430 data: 0.1396 max mem: 30263 +eval (train): [20] [ 40/114] eta: 0:00:53 time: 0.5776 data: 0.0669 max mem: 30263 +eval (train): [20] [ 60/114] eta: 0:00:38 time: 0.6620 data: 0.1008 max mem: 30263 +eval (train): [20] [ 80/114] eta: 0:00:23 time: 0.6381 data: 0.1235 max mem: 30263 +eval (train): [20] [100/114] eta: 0:00:09 time: 0.5795 data: 0.0790 max mem: 30263 +eval (train): [20] [113/114] eta: 0:00:00 time: 0.5727 data: 0.1312 max mem: 30263 +eval (train): [20] Total time: 0:01:15 (0.6589 s / it) +eval (validation): [20] [ 0/14] eta: 0:01:18 time: 5.6391 data: 5.2803 max mem: 30263 +eval (validation): [20] [13/14] eta: 0:00:00 time: 0.8667 data: 0.4617 max mem: 30263 +eval (validation): [20] Total time: 0:00:12 (0.8764 s / it) +eval (test): [20] [ 0/13] eta: 0:01:13 time: 5.6571 data: 5.3526 max mem: 30263 +eval (test): [20] [12/13] eta: 0:00:00 time: 0.9222 data: 0.5061 max mem: 30263 +eval (test): [20] Total time: 0:00:12 (0.9313 s / it) +eval results: + +| model | repr | clf | dataset | ckpt | epoch | lr | wd | hparam_id | hparam | split | loss | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:------|:----------|:-------|--------:|--------:|-----:|------------:|:-----------|:-----------|-------:|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | attn | aabc_age | best | 4 | 0.00048 | 0.05 | 27 | [1.6, 1.0] | train | 0.7455 | 0.65275 | 0.018765 | 0.62774 | 0.022186 | 0.66084 | 0.018431 | +| flat_mae | patch | attn | aabc_age | best | 4 | 0.00048 | 0.05 | 27 | [1.6, 1.0] | validation | 1.3573 | 0.54717 | 0.055046 | 0.49925 | 0.064513 | 0.53091 | 0.055661 | +| flat_mae | patch | attn | aabc_age | best | 4 | 0.00048 | 0.05 | 27 | [1.6, 1.0] | test | 1.4808 | 0.42308 | 0.059341 | 0.36178 | 0.051582 | 0.40797 | 0.058192 | + + +done! total time: 3:01:12 diff --git a/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_age__patch__attn/train_log.json b/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_age__patch__attn/train_log.json new file mode 100644 index 0000000000000000000000000000000000000000..c3911fa9bd84f8f1d55588f6878502382a3a6c51 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_age__patch__attn/train_log.json @@ -0,0 +1,20 @@ +{"epoch": 0, "train/lr": 2.987987987987988e-05, "train/loss": 1.2889715802669526, "train/grad": 0.3292441893368959, "train/loss_000_lr2.0e-02_wd1.0e+00": 1.39693359375, "train/loss_001_lr2.3e-02_wd1.0e+00": 1.396142578125, "train/loss_002_lr2.8e-02_wd1.0e+00": 1.39509765625, "train/loss_003_lr3.3e-02_wd1.0e+00": 1.393779296875, "train/loss_004_lr3.8e-02_wd1.0e+00": 1.3927734375, "train/loss_005_lr4.5e-02_wd1.0e+00": 1.39140625, "train/loss_006_lr5.3e-02_wd1.0e+00": 1.38974609375, "train/loss_007_lr6.2e-02_wd1.0e+00": 1.3880859375, "train/loss_008_lr7.4e-02_wd1.0e+00": 1.386015625, "train/loss_009_lr8.7e-02_wd1.0e+00": 1.383896484375, "train/loss_010_lr1.0e-01_wd1.0e+00": 1.38193359375, "train/loss_011_lr1.2e-01_wd1.0e+00": 1.379130859375, "train/loss_012_lr1.4e-01_wd1.0e+00": 1.376533203125, "train/loss_013_lr1.7e-01_wd1.0e+00": 1.372822265625, "train/loss_014_lr2.0e-01_wd1.0e+00": 1.369453125, "train/loss_015_lr2.3e-01_wd1.0e+00": 1.365908203125, "train/loss_016_lr2.7e-01_wd1.0e+00": 1.3617138671875, "train/loss_017_lr3.2e-01_wd1.0e+00": 1.3568408203125, "train/loss_018_lr3.8e-01_wd1.0e+00": 1.3509765625, "train/loss_019_lr4.4e-01_wd1.0e+00": 1.345625, "train/loss_020_lr5.2e-01_wd1.0e+00": 1.338828125, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.331484375, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.323642578125, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.3150146484375, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.30612548828125, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.29544189453125, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.28606201171875, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.27818115234375, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.26750732421875, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.255469970703125, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.2455322265625, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.237216796875, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.22748779296875, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.2202178955078125, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.2130120849609376, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.20641845703125, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.1983612060546875, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.1901409912109375, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.1817950439453124, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.1739447021484375, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.1703155517578125, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.1688787841796875, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.1672052001953126, "train/loss_043_lr2.2e+01_wd1.0e+00": 1.1641897583007812, "train/loss_044_lr2.6e+01_wd1.0e+00": 1.1625968933105468, "train/loss_045_lr3.1e+01_wd1.0e+00": 1.163914909362793, "train/loss_046_lr3.6e+01_wd1.0e+00": 1.1678853034973145, "train/loss_047_lr4.3e+01_wd1.0e+00": 1.1670172119140625, "train/loss_048_lr5.0e+01_wd1.0e+00": 1.1609058570861817, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.047599286269396544, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.04751313115470111, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.0473758854623884, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.04725266860798001, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.047129345731809734, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.04697710727341473, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.04682753207162023, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.04667401072569191, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.04649179038591683, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.04633036412298679, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.04619324835948646, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.04601951574906707, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.04587107956875116, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.045698700211942195, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.045555296293459835, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.045448159063234926, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.045330393817275765, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.045216272426769136, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.0451097899954766, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.04503685271833092, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.04495449448004365, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.044905722280964254, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.04486571678891778, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.04484194829128683, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.04485777914058417, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.044891837714239956, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.04494734986219555, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.04502107270993292, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.045176316280849275, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.045426365956664085, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.04573501926846802, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.046053762417286634, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.04650583039503545, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.04689859244972468, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.04728111152537167, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.047451381171122194, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.04741407381370664, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0473127620248124, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.04720129694789648, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.04696160497143865, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.04673114530742169, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.04658755648881197, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.046435706000775095, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.046101465304382146, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.045761527232825755, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.04577416919637471, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.04633074862882495, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.047683423589915036, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.048111349414102736, "validation/loss_000_lr2.0e-02_wd1.0e+00": 1.3861640691757202, "validation/loss_001_lr2.3e-02_wd1.0e+00": 1.3851760625839233, "validation/loss_002_lr2.8e-02_wd1.0e+00": 1.383726716041565, "validation/loss_003_lr3.3e-02_wd1.0e+00": 1.3822500705718994, "validation/loss_004_lr3.8e-02_wd1.0e+00": 1.3810007572174072, "validation/loss_005_lr4.5e-02_wd1.0e+00": 1.3792814016342163, "validation/loss_006_lr5.3e-02_wd1.0e+00": 1.3774751424789429, "validation/loss_007_lr6.2e-02_wd1.0e+00": 1.3754870891571045, "validation/loss_008_lr7.4e-02_wd1.0e+00": 1.3729990720748901, "validation/loss_009_lr8.7e-02_wd1.0e+00": 1.3703417778015137, "validation/loss_010_lr1.0e-01_wd1.0e+00": 1.3677054643630981, "validation/loss_011_lr1.2e-01_wd1.0e+00": 1.3635603189468384, "validation/loss_012_lr1.4e-01_wd1.0e+00": 1.3594337701797485, "validation/loss_013_lr1.7e-01_wd1.0e+00": 1.3531264066696167, "validation/loss_014_lr2.0e-01_wd1.0e+00": 1.3468577861785889, "validation/loss_015_lr2.3e-01_wd1.0e+00": 1.3409463167190552, "validation/loss_016_lr2.7e-01_wd1.0e+00": 1.3331520557403564, "validation/loss_017_lr3.2e-01_wd1.0e+00": 1.3240445852279663, "validation/loss_018_lr3.8e-01_wd1.0e+00": 1.314163327217102, "validation/loss_019_lr4.4e-01_wd1.0e+00": 1.3051011562347412, "validation/loss_020_lr5.2e-01_wd1.0e+00": 1.2944992780685425, "validation/loss_021_lr6.1e-01_wd1.0e+00": 1.2839232683181763, "validation/loss_022_lr7.2e-01_wd1.0e+00": 1.2729628086090088, "validation/loss_023_lr8.5e-01_wd1.0e+00": 1.2626328468322754, "validation/loss_024_lr1.0e+00_wd1.0e+00": 1.2534010410308838, "validation/loss_025_lr1.2e+00_wd1.0e+00": 1.2442675828933716, "validation/loss_026_lr1.4e+00_wd1.0e+00": 1.2385352849960327, "validation/loss_027_lr1.6e+00_wd1.0e+00": 1.2347252368927002, "validation/loss_028_lr1.9e+00_wd1.0e+00": 1.2328225374221802, "validation/loss_029_lr2.3e+00_wd1.0e+00": 1.2325036525726318, "validation/loss_030_lr2.7e+00_wd1.0e+00": 1.2311874628067017, "validation/loss_031_lr3.1e+00_wd1.0e+00": 1.2275022268295288, "validation/loss_032_lr3.7e+00_wd1.0e+00": 1.2208536863327026, "validation/loss_033_lr4.3e+00_wd1.0e+00": 1.2164348363876343, "validation/loss_034_lr5.1e+00_wd1.0e+00": 1.2133599519729614, "validation/loss_035_lr6.0e+00_wd1.0e+00": 1.2096209526062012, "validation/loss_036_lr7.1e+00_wd1.0e+00": 1.2144593000411987, "validation/loss_037_lr8.3e+00_wd1.0e+00": 1.2314364910125732, "validation/loss_038_lr9.8e+00_wd1.0e+00": 1.2481825351715088, "validation/loss_039_lr1.2e+01_wd1.0e+00": 1.2575359344482422, "validation/loss_040_lr1.4e+01_wd1.0e+00": 1.2557330131530762, "validation/loss_041_lr1.6e+01_wd1.0e+00": 1.2442195415496826, "validation/loss_042_lr1.9e+01_wd1.0e+00": 1.2465308904647827, "validation/loss_043_lr2.2e+01_wd1.0e+00": 1.2936338186264038, "validation/loss_044_lr2.6e+01_wd1.0e+00": 1.3698822259902954, "validation/loss_045_lr3.1e+01_wd1.0e+00": 1.3204706907272339, "validation/loss_046_lr3.6e+01_wd1.0e+00": 1.2714731693267822, "validation/loss_047_lr4.3e+01_wd1.0e+00": 1.213991403579712, "validation/loss_048_lr5.0e+01_wd1.0e+00": 1.1632273197174072, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.2641509433962264, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.2641509433962264, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.2641509433962264, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.2641509433962264, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.2830188679245283, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.2641509433962264, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.32075471698113206, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.39622641509433965, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.37735849056603776, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.39622641509433965, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.37735849056603776, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.37735849056603776, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.33962264150943394, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.3584905660377358, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.3584905660377358, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.37735849056603776, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.37735849056603776, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.3584905660377358, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.3584905660377358, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.3584905660377358, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.3584905660377358, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.33962264150943394, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.33962264150943394, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.3584905660377358, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.37735849056603776, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.41509433962264153, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.39622641509433965, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.41509433962264153, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.4339622641509434, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.4339622641509434, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.41509433962264153, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.41509433962264153, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.41509433962264153, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.41509433962264153, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.41509433962264153, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.4339622641509434, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.4339622641509434, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.4716981132075472, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.4339622641509434, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.39622641509433965, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.37735849056603776, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.37735849056603776, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.41509433962264153, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.37735849056603776, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.4339622641509434, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.41509433962264153, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.4716981132075472, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.4528301886792453, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.4716981132075472, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.1044776119402985, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.1044776119402985, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.10606060606060606, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.1076923076923077, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.140625, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.13596914175506267, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.22023809523809523, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.2848800505050505, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.2791666666666667, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.29766414141414144, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.276580459770115, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.2685574229691877, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.238388969521045, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.2539173789173789, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.2539173789173789, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.2872412854030501, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.2872412854030501, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.2775599128540305, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.2775599128540305, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.2775599128540305, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.2796007291805611, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.26637960148598444, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.26637960148598444, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.3051948051948052, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.3267894895801873, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.38257575757575757, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.36762866762866764, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.37857142857142856, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.3834704315648054, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.3834704315648054, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.3425837320574162, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.365631673597842, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.37152780631041504, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.3756909756909757, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.37546473134708425, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.4096590909090909, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.4241835048384898, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.4727233157614741, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.4311526846809105, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.39258373205741626, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.3792037786774629, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.37754800525698357, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.40052006465668705, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.3168834841628959, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.36216931216931214, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.363655462184874, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.4343137254901961, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.39316239316239315, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.4703973819541841, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.25, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.25, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.25, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.25, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.26785714285714285, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.25, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.3076923076923077, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.3846153846153846, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.3695054945054945, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.38873626373626374, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.3708791208791209, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.37225274725274726, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.33653846153846156, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.35439560439560436, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.35439560439560436, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.37225274725274726, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.37225274725274726, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.353021978021978, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.353021978021978, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.353021978021978, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.353021978021978, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.33379120879120877, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.33379120879120877, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.35027472527472525, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.36813186813186816, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.4068223443223443, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.38896520146520147, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.4081959706959707, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.42742673992673996, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.42742673992673996, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.4065934065934066, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.4081959706959707, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.40544871794871795, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.4040750915750916, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.4040750915750916, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.4249084249084249, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.42925824175824173, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.4768772893772894, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.44116300366300365, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.4040750915750916, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.3804945054945055, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.377518315018315, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.41735347985347987, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.3756868131868132, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.43223443223443225, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.4219322344322345, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.4798534798534798, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.46016483516483514, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.4725274725274725, "id_best": 46, "lr_best": 0.010799999999999999, "wd_best": 0.05, "train/loss_best": 1.1678853034973145, "validation/loss_best": 1.2714731693267822, "validation/acc_best": 0.4716981132075472, "validation/f1_best": 0.4343137254901961, "validation/bacc_best": 0.4798534798534798} +{"epoch": 1, "train/lr": 8.993993993993998e-05, "train/loss": 1.187254554927349, "train/grad": 0.32670367307960985, "train/loss_000_lr2.0e-02_wd1.0e+00": 1.373203125, "train/loss_001_lr2.3e-02_wd1.0e+00": 1.370166015625, "train/loss_002_lr2.8e-02_wd1.0e+00": 1.36541015625, "train/loss_003_lr3.3e-02_wd1.0e+00": 1.361044921875, "train/loss_004_lr3.8e-02_wd1.0e+00": 1.35693359375, "train/loss_005_lr4.5e-02_wd1.0e+00": 1.3516796875, "train/loss_006_lr5.3e-02_wd1.0e+00": 1.3458984375, "train/loss_007_lr6.2e-02_wd1.0e+00": 1.34001953125, "train/loss_008_lr7.4e-02_wd1.0e+00": 1.3325048828125, "train/loss_009_lr8.7e-02_wd1.0e+00": 1.32486328125, "train/loss_010_lr1.0e-01_wd1.0e+00": 1.317626953125, "train/loss_011_lr1.2e-01_wd1.0e+00": 1.3074169921875, "train/loss_012_lr1.4e-01_wd1.0e+00": 1.2979541015625, "train/loss_013_lr1.7e-01_wd1.0e+00": 1.284921875, "train/loss_014_lr2.0e-01_wd1.0e+00": 1.273349609375, "train/loss_015_lr2.3e-01_wd1.0e+00": 1.262802734375, "train/loss_016_lr2.7e-01_wd1.0e+00": 1.2504150390625, "train/loss_017_lr3.2e-01_wd1.0e+00": 1.23677978515625, "train/loss_018_lr3.8e-01_wd1.0e+00": 1.2230224609375, "train/loss_019_lr4.4e-01_wd1.0e+00": 1.21137939453125, "train/loss_020_lr5.2e-01_wd1.0e+00": 1.1985498046875, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.18684326171875, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.175086669921875, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.163961181640625, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.15383544921875, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.14296630859375, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.1345269775390625, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.127022705078125, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.117618408203125, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.1069122314453126, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.0984625244140624, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.0913275146484376, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.0826885986328125, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.07634765625, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.0674624633789063, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.0581002807617188, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.0521173858642578, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.0463455963134765, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.0350653839111328, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.036126022338867, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.041485824584961, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.0327245330810546, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.0457782745361328, "train/loss_043_lr2.2e+01_wd1.0e+00": 1.0373218727111817, "train/loss_044_lr2.6e+01_wd1.0e+00": 1.0370559310913086, "train/loss_045_lr3.1e+01_wd1.0e+00": 1.0667845344543456, "train/loss_046_lr3.6e+01_wd1.0e+00": 1.0955912590026855, "train/loss_047_lr4.3e+01_wd1.0e+00": 1.248158414363861, "train/loss_048_lr5.0e+01_wd1.0e+00": 1.2318147134780884, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.043421382484957576, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.04324758506380021, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.043016503397375346, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.042843450717628004, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.04270555376075208, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.04255084218457341, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.04242642229422927, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.04231086597777903, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.0421936284005642, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.04208241041284055, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.041994535801932215, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.041871971283107996, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.041769418115727604, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.04165242168586701, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.04156658827792853, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.04149740863125771, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.04142599290236831, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.04138279522769153, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.041361952195875344, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.04137071326840669, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.04143817231059074, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.041547288531437514, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.04172228122130037, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.041916484264656904, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.04215089705772698, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.042421886594966055, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.04268064228817821, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.04292423947714269, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.04321370474994182, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.04345662514679134, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.04362499201670289, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0436760436091572, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.04344832599163055, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.04309467592742294, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.04271007803268731, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.04226120966486633, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.04163494314998388, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.041190749034285545, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.04058394409250468, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.04075881457421929, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.041435010428540406, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.04136031751520932, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.04412020082585513, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.04600194537080824, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.05193492976482958, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.05130795027129352, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.05761382279451936, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.07377925896085799, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.07420484068803489, "validation/loss_000_lr2.0e-02_wd1.0e+00": 1.3716065883636475, "validation/loss_001_lr2.3e-02_wd1.0e+00": 1.369032382965088, "validation/loss_002_lr2.8e-02_wd1.0e+00": 1.364842414855957, "validation/loss_003_lr3.3e-02_wd1.0e+00": 1.3606066703796387, "validation/loss_004_lr3.8e-02_wd1.0e+00": 1.3563538789749146, "validation/loss_005_lr4.5e-02_wd1.0e+00": 1.3504340648651123, "validation/loss_006_lr5.3e-02_wd1.0e+00": 1.3438798189163208, "validation/loss_007_lr6.2e-02_wd1.0e+00": 1.3365956544876099, "validation/loss_008_lr7.4e-02_wd1.0e+00": 1.3275563716888428, "validation/loss_009_lr8.7e-02_wd1.0e+00": 1.3183928728103638, "validation/loss_010_lr1.0e-01_wd1.0e+00": 1.3099141120910645, "validation/loss_011_lr1.2e-01_wd1.0e+00": 1.2983142137527466, "validation/loss_012_lr1.4e-01_wd1.0e+00": 1.2876367568969727, "validation/loss_013_lr1.7e-01_wd1.0e+00": 1.2739481925964355, "validation/loss_014_lr2.0e-01_wd1.0e+00": 1.2622747421264648, "validation/loss_015_lr2.3e-01_wd1.0e+00": 1.252126693725586, "validation/loss_016_lr2.7e-01_wd1.0e+00": 1.2410130500793457, "validation/loss_017_lr3.2e-01_wd1.0e+00": 1.2298539876937866, "validation/loss_018_lr3.8e-01_wd1.0e+00": 1.2199602127075195, "validation/loss_019_lr4.4e-01_wd1.0e+00": 1.2134190797805786, "validation/loss_020_lr5.2e-01_wd1.0e+00": 1.2079601287841797, "validation/loss_021_lr6.1e-01_wd1.0e+00": 1.2045204639434814, "validation/loss_022_lr7.2e-01_wd1.0e+00": 1.202500343322754, "validation/loss_023_lr8.5e-01_wd1.0e+00": 1.2023276090621948, "validation/loss_024_lr1.0e+00_wd1.0e+00": 1.2043639421463013, "validation/loss_025_lr1.2e+00_wd1.0e+00": 1.2098400592803955, "validation/loss_026_lr1.4e+00_wd1.0e+00": 1.2127392292022705, "validation/loss_027_lr1.6e+00_wd1.0e+00": 1.2092833518981934, "validation/loss_028_lr1.9e+00_wd1.0e+00": 1.2021740674972534, "validation/loss_029_lr2.3e+00_wd1.0e+00": 1.207513451576233, "validation/loss_030_lr2.7e+00_wd1.0e+00": 1.2200990915298462, "validation/loss_031_lr3.1e+00_wd1.0e+00": 1.2184725999832153, "validation/loss_032_lr3.7e+00_wd1.0e+00": 1.1905843019485474, "validation/loss_033_lr4.3e+00_wd1.0e+00": 1.1723885536193848, "validation/loss_034_lr5.1e+00_wd1.0e+00": 1.1677899360656738, "validation/loss_035_lr6.0e+00_wd1.0e+00": 1.1691094636917114, "validation/loss_036_lr7.1e+00_wd1.0e+00": 1.1862311363220215, "validation/loss_037_lr8.3e+00_wd1.0e+00": 1.2338796854019165, "validation/loss_038_lr9.8e+00_wd1.0e+00": 1.3693023920059204, "validation/loss_039_lr1.2e+01_wd1.0e+00": 1.4037318229675293, "validation/loss_040_lr1.4e+01_wd1.0e+00": 1.4011375904083252, "validation/loss_041_lr1.6e+01_wd1.0e+00": 1.3503210544586182, "validation/loss_042_lr1.9e+01_wd1.0e+00": 1.3920691013336182, "validation/loss_043_lr2.2e+01_wd1.0e+00": 1.3095444440841675, "validation/loss_044_lr2.6e+01_wd1.0e+00": 1.3210054636001587, "validation/loss_045_lr3.1e+01_wd1.0e+00": 1.4303473234176636, "validation/loss_046_lr3.6e+01_wd1.0e+00": 1.7046624422073364, "validation/loss_047_lr4.3e+01_wd1.0e+00": 1.5476430654525757, "validation/loss_048_lr5.0e+01_wd1.0e+00": 1.4168951511383057, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.37735849056603776, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.39622641509433965, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.3584905660377358, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.33962264150943394, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.33962264150943394, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.37735849056603776, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.37735849056603776, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.3584905660377358, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.3584905660377358, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.3584905660377358, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.3584905660377358, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.3584905660377358, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.3584905660377358, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.39622641509433965, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.37735849056603776, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.37735849056603776, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.37735849056603776, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.3584905660377358, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.33962264150943394, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.33962264150943394, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.33962264150943394, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.3584905660377358, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.33962264150943394, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.3584905660377358, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.33962264150943394, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.37735849056603776, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.3584905660377358, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.3584905660377358, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.39622641509433965, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.41509433962264153, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.4528301886792453, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.4716981132075472, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.4339622641509434, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.4528301886792453, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.4716981132075472, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.4716981132075472, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.49056603773584906, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.4716981132075472, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.4528301886792453, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.4716981132075472, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.4528301886792453, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.39622641509433965, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.37735849056603776, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.49056603773584906, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.49056603773584906, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.49056603773584906, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.4339622641509434, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.39622641509433965, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.4339622641509434, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.283944092083627, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.3001792114695341, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.2627551020408163, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.238388969521045, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.238388969521045, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.2872412854030501, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.2872412854030501, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.2775599128540305, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.2796007291805611, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.2796007291805611, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.2796007291805611, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.2796007291805611, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.28077627852740294, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.32965116279069767, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.3244565217391304, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.3244565217391304, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.3244565217391304, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.312037037037037, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.29393939393939394, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.29032258064516125, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.28136428944618597, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.29698928944618597, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.2821603128054741, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.29936461388074287, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.29393939393939394, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.35016089305577625, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.33773148148148147, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.33773148148148147, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.35834701696770666, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.3746031746031746, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.4248481781376518, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.4458943833943834, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.4145658263305322, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.4501157407407407, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.4554131054131054, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.4489107383844225, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.44725975975975973, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.42125, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.3880411255411256, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.40954223081882657, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.4011289364230541, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.35778809313292076, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.37700071667462975, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.484012539184953, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.44739621230495596, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.43799642218246865, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.3296296296296296, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.2869971264367816, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.4128205128205128, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.3695054945054945, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.38873626373626374, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.35302197802197804, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.33653846153846156, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.33653846153846156, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.37225274725274726, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.37225274725274726, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.353021978021978, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.353021978021978, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.353021978021978, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.353021978021978, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.353021978021978, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.3516483516483516, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.3873626373626374, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.3667582417582418, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.3667582417582418, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.3667582417582418, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.34615384615384615, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.326923076923077, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.32554945054945056, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.32554945054945056, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.3434065934065934, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.32554945054945056, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.3447802197802198, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.326923076923077, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.36561355311355315, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.34775641025641024, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.34775641025641024, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.3820970695970696, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.3999542124542125, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.43864468864468864, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.4578754578754579, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.4221611721611722, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.44597069597069594, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.4652014652014652, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.46222527472527475, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.4805402930402931, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.4626831501831502, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.44184981684981683, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.4626831501831502, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.44482600732600736, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.3926282051282051, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.37133699633699635, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.481456043956044, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.47596153846153844, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.47275641025641024, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.41369047619047616, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.3901098901098901, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.43246336996337, "id_best": 43, "lr_best": 0.006599999999999999, "wd_best": 0.05, "train/loss_best": 1.0373218727111817, "validation/loss_best": 1.3095444440841675, "validation/acc_best": 0.49056603773584906, "validation/f1_best": 0.484012539184953, "validation/bacc_best": 0.481456043956044} +{"epoch": 2, "train/lr": 0.00014999999999999988, "train/loss": 1.1432710561156272, "train/grad": 0.43747767619788647, "train/loss_000_lr2.0e-02_wd1.0e+00": 1.350771484375, "train/loss_001_lr2.3e-02_wd1.0e+00": 1.345634765625, "train/loss_002_lr2.8e-02_wd1.0e+00": 1.33748046875, "train/loss_003_lr3.3e-02_wd1.0e+00": 1.3298974609375, "train/loss_004_lr3.8e-02_wd1.0e+00": 1.32248046875, "train/loss_005_lr4.5e-02_wd1.0e+00": 1.3130908203125, "train/loss_006_lr5.3e-02_wd1.0e+00": 1.3031201171875, "train/loss_007_lr6.2e-02_wd1.0e+00": 1.292734375, "train/loss_008_lr7.4e-02_wd1.0e+00": 1.2803173828125, "train/loss_009_lr8.7e-02_wd1.0e+00": 1.2681494140625, "train/loss_010_lr1.0e-01_wd1.0e+00": 1.2575341796875, "train/loss_011_lr1.2e-01_wd1.0e+00": 1.24338134765625, "train/loss_012_lr1.4e-01_wd1.0e+00": 1.23141357421875, "train/loss_013_lr1.7e-01_wd1.0e+00": 1.21667724609375, "train/loss_014_lr2.0e-01_wd1.0e+00": 1.2050634765625, "train/loss_015_lr2.3e-01_wd1.0e+00": 1.1951953125, "train/loss_016_lr2.7e-01_wd1.0e+00": 1.185128173828125, "train/loss_017_lr3.2e-01_wd1.0e+00": 1.174754638671875, "train/loss_018_lr3.8e-01_wd1.0e+00": 1.16498779296875, "train/loss_019_lr4.4e-01_wd1.0e+00": 1.157034912109375, "train/loss_020_lr5.2e-01_wd1.0e+00": 1.14775390625, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.13940185546875, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.1311376953125, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.12455078125, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.118052978515625, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.107734375, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.0931573486328126, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.0769345092773437, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.0604812622070312, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.0456607055664062, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.032212371826172, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.0233474731445313, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.0194900512695313, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.0140432739257812, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.001888198852539, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.991780138015747, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.9643408107757568, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.9340405464172363, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.893402235507965, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.8643003129959106, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.8706431293487549, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.8859687422215938, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.8629567381739617, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.9794544646143913, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.9534419567883015, "train/loss_045_lr3.1e+01_wd1.0e+00": 1.0882405711710452, "train/loss_046_lr3.6e+01_wd1.0e+00": 1.1826502600312232, "train/loss_047_lr4.3e+01_wd1.0e+00": 1.4005076637864113, "train/loss_048_lr5.0e+01_wd1.0e+00": 1.8378611825406552, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.0449962512543425, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.04488900354597718, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.04474514318164438, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.04461992134340107, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.04451466809492558, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.04439108665566891, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.04425478586927056, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.04412626582197845, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.04400561571121216, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.04389007054269314, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.043812171490862965, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.0437459976458922, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.04371439637616277, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.04375361130107194, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.04384227753151208, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.04397283283993602, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.04419264284428209, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.044485140186734495, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.04481723890639842, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.04509298214688897, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.04536309308372438, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.045603527147322895, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.045902784480713305, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.046271222000941636, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.046667415481060744, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.04721979749388993, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.04777376446407288, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.04823898836039007, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.04887272015213966, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.04933577064424753, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.049189253272488714, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.049028277788311245, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.04907403741963208, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0485797986947, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0482292857253924, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.047602701685391366, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.04692724699154496, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.04776682877447456, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.05018994682002813, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.05622861433774233, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.056040199985727665, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.06251138303428888, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0673600241355598, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.08150512214750051, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0851161704864353, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.10263768027536571, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.10810834679752589, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.12035097885876894, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.1495301559753716, "validation/loss_000_lr2.0e-02_wd1.0e+00": 1.349411129951477, "validation/loss_001_lr2.3e-02_wd1.0e+00": 1.3436444997787476, "validation/loss_002_lr2.8e-02_wd1.0e+00": 1.334360122680664, "validation/loss_003_lr3.3e-02_wd1.0e+00": 1.3256803750991821, "validation/loss_004_lr3.8e-02_wd1.0e+00": 1.317498803138733, "validation/loss_005_lr4.5e-02_wd1.0e+00": 1.3069143295288086, "validation/loss_006_lr5.3e-02_wd1.0e+00": 1.2959907054901123, "validation/loss_007_lr6.2e-02_wd1.0e+00": 1.2851909399032593, "validation/loss_008_lr7.4e-02_wd1.0e+00": 1.2727079391479492, "validation/loss_009_lr8.7e-02_wd1.0e+00": 1.2611632347106934, "validation/loss_010_lr1.0e-01_wd1.0e+00": 1.2517684698104858, "validation/loss_011_lr1.2e-01_wd1.0e+00": 1.240288257598877, "validation/loss_012_lr1.4e-01_wd1.0e+00": 1.2316375970840454, "validation/loss_013_lr1.7e-01_wd1.0e+00": 1.222772240638733, "validation/loss_014_lr2.0e-01_wd1.0e+00": 1.2177079916000366, "validation/loss_015_lr2.3e-01_wd1.0e+00": 1.2146164178848267, "validation/loss_016_lr2.7e-01_wd1.0e+00": 1.2132625579833984, "validation/loss_017_lr3.2e-01_wd1.0e+00": 1.2139127254486084, "validation/loss_018_lr3.8e-01_wd1.0e+00": 1.2176547050476074, "validation/loss_019_lr4.4e-01_wd1.0e+00": 1.2226266860961914, "validation/loss_020_lr5.2e-01_wd1.0e+00": 1.2296092510223389, "validation/loss_021_lr6.1e-01_wd1.0e+00": 1.235108733177185, "validation/loss_022_lr7.2e-01_wd1.0e+00": 1.2398451566696167, "validation/loss_023_lr8.5e-01_wd1.0e+00": 1.2481385469436646, "validation/loss_024_lr1.0e+00_wd1.0e+00": 1.2630239725112915, "validation/loss_025_lr1.2e+00_wd1.0e+00": 1.2829862833023071, "validation/loss_026_lr1.4e+00_wd1.0e+00": 1.303908348083496, "validation/loss_027_lr1.6e+00_wd1.0e+00": 1.3091453313827515, "validation/loss_028_lr1.9e+00_wd1.0e+00": 1.2794183492660522, "validation/loss_029_lr2.3e+00_wd1.0e+00": 1.2376426458358765, "validation/loss_030_lr2.7e+00_wd1.0e+00": 1.2025785446166992, "validation/loss_031_lr3.1e+00_wd1.0e+00": 1.1922599077224731, "validation/loss_032_lr3.7e+00_wd1.0e+00": 1.220574975013733, "validation/loss_033_lr4.3e+00_wd1.0e+00": 1.2300806045532227, "validation/loss_034_lr5.1e+00_wd1.0e+00": 1.263261318206787, "validation/loss_035_lr6.0e+00_wd1.0e+00": 1.2660937309265137, "validation/loss_036_lr7.1e+00_wd1.0e+00": 1.3092621564865112, "validation/loss_037_lr8.3e+00_wd1.0e+00": 1.3689326047897339, "validation/loss_038_lr9.8e+00_wd1.0e+00": 1.6560090780258179, "validation/loss_039_lr1.2e+01_wd1.0e+00": 1.7864539623260498, "validation/loss_040_lr1.4e+01_wd1.0e+00": 1.7958017587661743, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.334088087081909, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.0602176189422607, "validation/loss_043_lr2.2e+01_wd1.0e+00": 1.7315577268600464, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.073788642883301, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.6117701530456543, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.647022247314453, "validation/loss_047_lr4.3e+01_wd1.0e+00": 2.0545616149902344, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.71229887008667, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.37735849056603776, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.37735849056603776, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.37735849056603776, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.37735849056603776, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.37735849056603776, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.3584905660377358, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.3584905660377358, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.3584905660377358, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.37735849056603776, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.39622641509433965, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.39622641509433965, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.39622641509433965, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.37735849056603776, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.37735849056603776, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.37735849056603776, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.3584905660377358, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.37735849056603776, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.37735849056603776, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.37735849056603776, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.37735849056603776, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.39622641509433965, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.39622641509433965, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.37735849056603776, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.33962264150943394, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.3584905660377358, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.3584905660377358, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.37735849056603776, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.41509433962264153, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.4528301886792453, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.4528301886792453, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.5094339622641509, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.4716981132075472, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.49056603773584906, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.4339622641509434, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.4528301886792453, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.39622641509433965, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.39622641509433965, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.39622641509433965, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.39622641509433965, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.33962264150943394, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.4716981132075472, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.37735849056603776, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.33962264150943394, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.4339622641509434, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.37735849056603776, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.39622641509433965, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.2830188679245283, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.3018867924528302, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.4339622641509434, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.2921668667466987, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.29429271708683474, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.29429271708683474, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.2909671572223901, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.28810741687979535, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.2777777777777778, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.2930232558139535, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.3035476718403548, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.3244565217391304, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.36241439719700586, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.36241439719700586, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.36520146520146524, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.34945533769063175, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.3497354497354497, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.3513125763125763, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.3137214137214137, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.32894736842105265, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.32894736842105265, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.32410865874363326, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.32410865874363326, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.33907154673283707, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.33907154673283707, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.33017241379310347, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.301510989010989, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.31957671957671957, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.32304347826086954, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.3360154738878143, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.36416666666666664, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.4222013366750209, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.3980237504431053, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.49749373433583954, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.4695027195027195, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.4971067905850515, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.44172494172494176, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.42847060179183594, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.3736645299145299, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.37731182795698925, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.3791726015919564, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.3711827122153209, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.30868983957219254, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.4358796296296297, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.3263565891472868, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.30589430894308944, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.38128557874762814, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.321233164983165, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.33773291925465837, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.18125, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.29807451320609213, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.2941176470588235, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.3708791208791209, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.3708791208791209, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.3708791208791209, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.3708791208791209, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.3708791208791209, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.3516483516483516, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.35027472527472525, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.3489010989010989, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.3667582417582418, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.3875915750915751, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.3875915750915751, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.38621794871794873, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.3669871794871795, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.3669871794871795, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.3669871794871795, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.34615384615384615, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.3653846153846154, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.3653846153846154, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.3653846153846154, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.3653846153846154, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.3846153846153846, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.3846153846153846, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.3653846153846154, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.3282967032967033, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.3475274725274725, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.3489010989010989, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.36813186813186816, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.4065934065934066, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.44826007326007333, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.4439102564102564, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.5064102564102564, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.4693223443223443, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.4901556776556777, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.43383699633699635, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.4514652014652014, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.3921703296703297, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.3937728937728938, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.39102564102564097, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.3942307692307693, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.34065934065934067, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.4716117216117216, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.38095238095238093, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.34523809523809523, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.4178113553113553, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.375, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.391025641025641, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.2722069597069597, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.3106684981684982, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.4107142857142857, "id_best": 30, "lr_best": 0.00081, "wd_best": 0.05, "train/loss_best": 1.032212371826172, "validation/loss_best": 1.2025785446166992, "validation/acc_best": 0.5094339622641509, "validation/f1_best": 0.49749373433583954, "validation/bacc_best": 0.5064102564102564} +{"epoch": 3, "train/lr": 0.0002100600600600602, "train/loss": 1.1415645709633828, "train/grad": 0.7206283223628998, "train/loss_000_lr2.0e-02_wd1.0e+00": 1.3156201171875, "train/loss_001_lr2.3e-02_wd1.0e+00": 1.30693359375, "train/loss_002_lr2.8e-02_wd1.0e+00": 1.2936181640625, "train/loss_003_lr3.3e-02_wd1.0e+00": 1.28125, "train/loss_004_lr3.8e-02_wd1.0e+00": 1.2701123046875, "train/loss_005_lr4.5e-02_wd1.0e+00": 1.2560546875, "train/loss_006_lr5.3e-02_wd1.0e+00": 1.2420751953125, "train/loss_007_lr6.2e-02_wd1.0e+00": 1.22801513671875, "train/loss_008_lr7.4e-02_wd1.0e+00": 1.2127099609375, "train/loss_009_lr8.7e-02_wd1.0e+00": 1.19853515625, "train/loss_010_lr1.0e-01_wd1.0e+00": 1.18698974609375, "train/loss_011_lr1.2e-01_wd1.0e+00": 1.1724365234375, "train/loss_012_lr1.4e-01_wd1.0e+00": 1.1612060546875, "train/loss_013_lr1.7e-01_wd1.0e+00": 1.147957763671875, "train/loss_014_lr2.0e-01_wd1.0e+00": 1.1371435546875, "train/loss_015_lr2.3e-01_wd1.0e+00": 1.12830078125, "train/loss_016_lr2.7e-01_wd1.0e+00": 1.118043212890625, "train/loss_017_lr3.2e-01_wd1.0e+00": 1.1068359375, "train/loss_018_lr3.8e-01_wd1.0e+00": 1.0952996826171875, "train/loss_019_lr4.4e-01_wd1.0e+00": 1.0852288818359375, "train/loss_020_lr5.2e-01_wd1.0e+00": 1.0737835693359374, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.0626495361328125, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.05078857421875, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.0399459838867187, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.0301751708984375, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.0133944702148439, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.986611328125, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.9543670654296875, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.918185806274414, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.8841754913330078, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.8650564575195312, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.8498186492919921, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.8180381965637207, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.7749116802215577, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.7302162981033326, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.6517333446443081, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.5655310398340225, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.5180368140339852, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.4442348615825176, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.4532398118078709, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.4839693307876587, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.6367428225278854, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.75704062089324, "train/loss_043_lr2.2e+01_wd1.0e+00": 1.1745257008075713, "train/loss_044_lr2.6e+01_wd1.0e+00": 1.4665348775684834, "train/loss_045_lr3.1e+01_wd1.0e+00": 1.4537574046850203, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.014875065088272, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.615146610736847, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.704812033623457, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.043539831954985855, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.04343660943210125, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.04329397190362215, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.04317456885240972, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.04308424923568964, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.042989050513133405, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.042907621255144475, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.04285273734945804, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.04283322550356388, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.04285561555996537, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.04292035413440317, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.04304796538781375, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.04321810477413237, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.043484151349402964, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.043749541668221356, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.043990150610916316, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.044293407541699706, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.04461613397113979, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.04494511732365936, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.04522374134976417, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.04553936579730362, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.046030549937859176, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.04676931364927441, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.047531881127506496, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.047940141768194736, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.04760747730266303, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.046878605312667784, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.04602483288384974, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.045403933925554155, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.04518908708356321, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.04494821190834045, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0448847816651687, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.04459352956153453, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.04591977713629603, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.047776850471273065, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.04802253623027355, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.050426425393670794, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.05379010504344478, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.054542126725427804, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.07743829985614865, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.07065779815427958, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.09117354898131452, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.10965169961098581, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.1448189216060564, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.15098445228300988, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.1622619911280344, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.2775576538685709, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.24996558656916024, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.19545335970818997, "validation/loss_000_lr2.0e-02_wd1.0e+00": 1.3213006258010864, "validation/loss_001_lr2.3e-02_wd1.0e+00": 1.313011884689331, "validation/loss_002_lr2.8e-02_wd1.0e+00": 1.3006168603897095, "validation/loss_003_lr3.3e-02_wd1.0e+00": 1.289656162261963, "validation/loss_004_lr3.8e-02_wd1.0e+00": 1.280032992362976, "validation/loss_005_lr4.5e-02_wd1.0e+00": 1.2685590982437134, "validation/loss_006_lr5.3e-02_wd1.0e+00": 1.2576947212219238, "validation/loss_007_lr6.2e-02_wd1.0e+00": 1.2480961084365845, "validation/loss_008_lr7.4e-02_wd1.0e+00": 1.2380398511886597, "validation/loss_009_lr8.7e-02_wd1.0e+00": 1.230399489402771, "validation/loss_010_lr1.0e-01_wd1.0e+00": 1.2246037721633911, "validation/loss_011_lr1.2e-01_wd1.0e+00": 1.2184425592422485, "validation/loss_012_lr1.4e-01_wd1.0e+00": 1.2148189544677734, "validation/loss_013_lr1.7e-01_wd1.0e+00": 1.2116930484771729, "validation/loss_014_lr2.0e-01_wd1.0e+00": 1.2102128267288208, "validation/loss_015_lr2.3e-01_wd1.0e+00": 1.2088338136672974, "validation/loss_016_lr2.7e-01_wd1.0e+00": 1.208175778388977, "validation/loss_017_lr3.2e-01_wd1.0e+00": 1.2077823877334595, "validation/loss_018_lr3.8e-01_wd1.0e+00": 1.2093902826309204, "validation/loss_019_lr4.4e-01_wd1.0e+00": 1.2132422924041748, "validation/loss_020_lr5.2e-01_wd1.0e+00": 1.2189682722091675, "validation/loss_021_lr6.1e-01_wd1.0e+00": 1.2240359783172607, "validation/loss_022_lr7.2e-01_wd1.0e+00": 1.2227146625518799, "validation/loss_023_lr8.5e-01_wd1.0e+00": 1.2124826908111572, "validation/loss_024_lr1.0e+00_wd1.0e+00": 1.2024405002593994, "validation/loss_025_lr1.2e+00_wd1.0e+00": 1.214345097541809, "validation/loss_026_lr1.4e+00_wd1.0e+00": 1.211295485496521, "validation/loss_027_lr1.6e+00_wd1.0e+00": 1.2507177591323853, "validation/loss_028_lr1.9e+00_wd1.0e+00": 1.2969049215316772, "validation/loss_029_lr2.3e+00_wd1.0e+00": 1.3541975021362305, "validation/loss_030_lr2.7e+00_wd1.0e+00": 1.4601057767868042, "validation/loss_031_lr3.1e+00_wd1.0e+00": 1.6003422737121582, "validation/loss_032_lr3.7e+00_wd1.0e+00": 1.7078462839126587, "validation/loss_033_lr4.3e+00_wd1.0e+00": 1.7503458261489868, "validation/loss_034_lr5.1e+00_wd1.0e+00": 1.9785622358322144, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.3658549785614014, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.605719566345215, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.2995247840881348, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.9880833625793457, "validation/loss_039_lr1.2e+01_wd1.0e+00": 5.146650314331055, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.694976329803467, "validation/loss_041_lr1.6e+01_wd1.0e+00": 4.405184745788574, "validation/loss_042_lr1.9e+01_wd1.0e+00": 7.185561656951904, "validation/loss_043_lr2.2e+01_wd1.0e+00": 8.169482231140137, "validation/loss_044_lr2.6e+01_wd1.0e+00": 10.936554908752441, "validation/loss_045_lr3.1e+01_wd1.0e+00": 6.283687591552734, "validation/loss_046_lr3.6e+01_wd1.0e+00": 9.908052444458008, "validation/loss_047_lr4.3e+01_wd1.0e+00": 1.3862943649291992, "validation/loss_048_lr5.0e+01_wd1.0e+00": 1.3862943649291992, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.37735849056603776, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.37735849056603776, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.33962264150943394, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.3584905660377358, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.3584905660377358, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.37735849056603776, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.37735849056603776, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.37735849056603776, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.37735849056603776, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.39622641509433965, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.41509433962264153, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.39622641509433965, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.39622641509433965, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.41509433962264153, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.41509433962264153, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.41509433962264153, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.41509433962264153, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.4528301886792453, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.4528301886792453, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.41509433962264153, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.4339622641509434, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.4528301886792453, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.49056603773584906, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.4716981132075472, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.49056603773584906, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.4716981132075472, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.39622641509433965, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.3584905660377358, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.32075471698113206, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.32075471698113206, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.2641509433962264, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.33962264150943394, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.37735849056603776, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.32075471698113206, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.37735849056603776, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.4339622641509434, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.39622641509433965, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.39622641509433965, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.3018867924528302, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.32075471698113206, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.4339622641509434, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.37735849056603776, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.4716981132075472, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.41509433962264153, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.2641509433962264, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.32075471698113206, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.4716981132075472, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.2641509433962264, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.2641509433962264, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.2909671572223901, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.28810741687979535, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.26722488038277514, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.3035476718403548, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.3035476718403548, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.3244565217391304, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.3244565217391304, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.3244565217391304, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.3244565217391304, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.36241439719700586, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.38198621553884715, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.36679536679536684, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.36679536679536684, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.3776785714285714, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.3776785714285714, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.3776785714285714, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.3776785714285714, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.42934587813620073, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.42934587813620073, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.39626623376623377, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.43055151448264795, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.4458110516934046, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.47394957983193275, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.45773809523809517, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.4828517854833645, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.45927795031055896, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.4002982311805841, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.35211598746081507, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.3214285714285714, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.3220739706540924, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.25910019214809943, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.33040935672514615, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.33856231487810434, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.27544797823435596, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.31463894234792067, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.40580086580086583, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.39418404073576485, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.39866372053872057, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.23360938578329882, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.25709706959706957, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.3961314255431902, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.3622747747747748, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.4202195653808557, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.3021431828545371, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.2004643962848297, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.27929292929292926, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.40886281017859966, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.1044776119402985, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.1044776119402985, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.3708791208791209, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.3708791208791209, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.33241758241758246, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.3489010989010989, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.3489010989010989, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.3667582417582418, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.3667582417582418, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.3667582417582418, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.3667582417582418, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.3875915750915751, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.40544871794871795, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.38621794871794873, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.38621794871794873, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.4040750915750916, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.4040750915750916, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.4040750915750916, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.4040750915750916, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.4441391941391941, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.4441391941391941, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.4097985347985348, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.4306318681318681, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.44848901098901095, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.4869505494505495, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.4677197802197802, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.4871794871794872, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.4665750915750916, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.39812271062271065, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.36378205128205127, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.32532051282051283, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.32532051282051283, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.27037545787545786, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.3431776556776557, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.37477106227106227, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.31845238095238093, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.3720238095238095, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.4269688644688645, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.38965201465201466, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.3967490842490843, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.29006410256410253, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.3166208791208791, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.44024725274725274, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.37408424908424914, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.47023809523809523, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.3942307692307692, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.27976190476190477, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.3315018315018315, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.4551282051282051, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.25, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.25, "id_best": 24, "lr_best": 0.0003, "wd_best": 0.05, "train/loss_best": 1.0301751708984375, "validation/loss_best": 1.2024405002593994, "validation/acc_best": 0.49056603773584906, "validation/f1_best": 0.4828517854833645, "validation/bacc_best": 0.4871794871794872} +{"epoch": 4, "train/lr": 0.0002701201201201201, "train/loss": 1.0177459385991097, "train/grad": 0.5871272855252028, "train/loss_000_lr2.0e-02_wd1.0e+00": 1.2823486328125, "train/loss_001_lr2.3e-02_wd1.0e+00": 1.27158203125, "train/loss_002_lr2.8e-02_wd1.0e+00": 1.255751953125, "train/loss_003_lr3.3e-02_wd1.0e+00": 1.2417919921875, "train/loss_004_lr3.8e-02_wd1.0e+00": 1.23009765625, "train/loss_005_lr4.5e-02_wd1.0e+00": 1.215791015625, "train/loss_006_lr5.3e-02_wd1.0e+00": 1.20232666015625, "train/loss_007_lr6.2e-02_wd1.0e+00": 1.19016845703125, "train/loss_008_lr7.4e-02_wd1.0e+00": 1.177509765625, "train/loss_009_lr8.7e-02_wd1.0e+00": 1.16658203125, "train/loss_010_lr1.0e-01_wd1.0e+00": 1.1580078125, "train/loss_011_lr1.2e-01_wd1.0e+00": 1.147896728515625, "train/loss_012_lr1.4e-01_wd1.0e+00": 1.1393408203125, "train/loss_013_lr1.7e-01_wd1.0e+00": 1.128753662109375, "train/loss_014_lr2.0e-01_wd1.0e+00": 1.11909423828125, "train/loss_015_lr2.3e-01_wd1.0e+00": 1.11002685546875, "train/loss_016_lr2.7e-01_wd1.0e+00": 1.0984576416015626, "train/loss_017_lr3.2e-01_wd1.0e+00": 1.0851837158203126, "train/loss_018_lr3.8e-01_wd1.0e+00": 1.0696182250976562, "train/loss_019_lr4.4e-01_wd1.0e+00": 1.0546676635742187, "train/loss_020_lr5.2e-01_wd1.0e+00": 1.0353427124023438, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.0131741333007813, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.9861383056640625, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.9581808471679687, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.9341867065429688, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.9100310134887696, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.8831706619262696, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.8442682838439941, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.7992882347106933, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.7346123027801513, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.6630023384094238, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.5772592616081238, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.48306841611862184, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.3541654148697853, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.29029918238520624, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.23843609496951104, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.15552766501903534, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.1781539164483547, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.28107819840312004, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.2509268383681774, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.6495536486804485, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.5441389070451259, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.8578417001664639, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.270391932427883, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.4489177298545837, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.434655063897371, "train/loss_046_lr3.6e+01_wd1.0e+00": 1.983119838833809, "train/loss_047_lr4.3e+01_wd1.0e+00": 1.3828125, "train/loss_048_lr5.0e+01_wd1.0e+00": 1.3828125, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.04320644250605255, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.043063947930932045, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.042893461170606315, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.04276444646064192, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.04266912010964006, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.04258068443741649, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.04254625403787941, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.04255139269866049, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.042606806489638986, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.04270393829792738, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.04282998882699758, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.04305412182118744, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.04329101105686277, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.04365189362317324, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.04398691348731518, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.04429480485618115, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.0447201232612133, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.045333091886714104, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.04616428353823721, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.04693202125839889, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.04776396896224469, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.048317478518001736, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.04810184341389686, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.04718850891571492, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.04682950322050601, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.04685459868982434, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.047168383551761506, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.04763515181839466, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.049138969806954265, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.050598951927386226, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.04872106400318444, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.049924348117783665, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.05077675539534539, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.04533726646797732, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.048604324649786576, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.04644379628472962, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.03830014957173262, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.04584418775135418, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.05486123759910697, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.05379440939876076, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.10087015963221348, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.08391205104308028, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.137723047520858, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.25212123689983856, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.17266953963786363, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.12621972863562406, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.026491246670484542, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 1.2948726415634155, "validation/loss_001_lr2.3e-02_wd1.0e+00": 1.2855260372161865, "validation/loss_002_lr2.8e-02_wd1.0e+00": 1.272301197052002, "validation/loss_003_lr3.3e-02_wd1.0e+00": 1.2615647315979004, "validation/loss_004_lr3.8e-02_wd1.0e+00": 1.2527722120285034, "validation/loss_005_lr4.5e-02_wd1.0e+00": 1.243199348449707, "validation/loss_006_lr5.3e-02_wd1.0e+00": 1.235032558441162, "validation/loss_007_lr6.2e-02_wd1.0e+00": 1.2281055450439453, "validation/loss_008_lr7.4e-02_wd1.0e+00": 1.2213410139083862, "validation/loss_009_lr8.7e-02_wd1.0e+00": 1.2163712978363037, "validation/loss_010_lr1.0e-01_wd1.0e+00": 1.212255835533142, "validation/loss_011_lr1.2e-01_wd1.0e+00": 1.2081615924835205, "validation/loss_012_lr1.4e-01_wd1.0e+00": 1.2046023607254028, "validation/loss_013_lr1.7e-01_wd1.0e+00": 1.2008192539215088, "validation/loss_014_lr2.0e-01_wd1.0e+00": 1.197818398475647, "validation/loss_015_lr2.3e-01_wd1.0e+00": 1.1957182884216309, "validation/loss_016_lr2.7e-01_wd1.0e+00": 1.195020318031311, "validation/loss_017_lr3.2e-01_wd1.0e+00": 1.1974996328353882, "validation/loss_018_lr3.8e-01_wd1.0e+00": 1.2076462507247925, "validation/loss_019_lr4.4e-01_wd1.0e+00": 1.2204769849777222, "validation/loss_020_lr5.2e-01_wd1.0e+00": 1.2321956157684326, "validation/loss_021_lr6.1e-01_wd1.0e+00": 1.232627034187317, "validation/loss_022_lr7.2e-01_wd1.0e+00": 1.21396005153656, "validation/loss_023_lr8.5e-01_wd1.0e+00": 1.2247480154037476, "validation/loss_024_lr1.0e+00_wd1.0e+00": 1.224722981452942, "validation/loss_025_lr1.2e+00_wd1.0e+00": 1.2309377193450928, "validation/loss_026_lr1.4e+00_wd1.0e+00": 1.2643649578094482, "validation/loss_027_lr1.6e+00_wd1.0e+00": 1.3573294878005981, "validation/loss_028_lr1.9e+00_wd1.0e+00": 1.485314130783081, "validation/loss_029_lr2.3e+00_wd1.0e+00": 1.6685231924057007, "validation/loss_030_lr2.7e+00_wd1.0e+00": 1.9041846990585327, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.2644755840301514, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.53672194480896, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.96636962890625, "validation/loss_034_lr5.1e+00_wd1.0e+00": 4.191149711608887, "validation/loss_035_lr6.0e+00_wd1.0e+00": 4.414078235626221, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.8947598934173584, "validation/loss_037_lr8.3e+00_wd1.0e+00": 4.287919998168945, "validation/loss_038_lr9.8e+00_wd1.0e+00": 5.609824180603027, "validation/loss_039_lr1.2e+01_wd1.0e+00": 4.590548038482666, "validation/loss_040_lr1.4e+01_wd1.0e+00": 7.2951459884643555, "validation/loss_041_lr1.6e+01_wd1.0e+00": 7.10386848449707, "validation/loss_042_lr1.9e+01_wd1.0e+00": 10.35689926147461, "validation/loss_043_lr2.2e+01_wd1.0e+00": 10.711742401123047, "validation/loss_044_lr2.6e+01_wd1.0e+00": 1.3862943649291992, "validation/loss_045_lr3.1e+01_wd1.0e+00": 1.3862943649291992, "validation/loss_046_lr3.6e+01_wd1.0e+00": 1.3862943649291992, "validation/loss_047_lr4.3e+01_wd1.0e+00": 1.3862943649291992, "validation/loss_048_lr5.0e+01_wd1.0e+00": 1.3862943649291992, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.37735849056603776, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.3584905660377358, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.37735849056603776, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.37735849056603776, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.37735849056603776, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.39622641509433965, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.41509433962264153, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.41509433962264153, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.41509433962264153, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.4339622641509434, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.41509433962264153, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.39622641509433965, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.39622641509433965, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.3584905660377358, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.3584905660377358, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.3584905660377358, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.37735849056603776, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.39622641509433965, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.3584905660377358, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.37735849056603776, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.37735849056603776, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.41509433962264153, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.4528301886792453, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.4528301886792453, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.4528301886792453, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.4528301886792453, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.4716981132075472, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.5471698113207547, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.5094339622641509, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.41509433962264153, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.5283018867924528, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.4716981132075472, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.4339622641509434, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.41509433962264153, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.3584905660377358, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.3584905660377358, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.41509433962264153, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.4716981132075472, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.37735849056603776, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.32075471698113206, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.41509433962264153, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.37735849056603776, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.3584905660377358, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.49056603773584906, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.2641509433962264, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.2641509433962264, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.2641509433962264, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.2641509433962264, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.2641509433962264, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.28810741687979535, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.2777777777777778, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.3049043062200957, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.31666666666666665, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.3244565217391304, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.36534322124651963, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.3985391919424903, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.3985391919424903, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.3967341986901286, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.4291219936250362, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.4119047619047619, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.3937159331896174, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.3937159331896174, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.34573502722323046, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.34573502722323046, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.346360153256705, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.36322302558398223, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.40171491794209846, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.3697619047619048, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.38537037037037036, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.3729260935143288, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.4021903075611516, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.4067899842093391, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.39623121976063147, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.41515151515151516, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.4081292686989838, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.41800356506238856, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.49924538254709033, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.47840755735492574, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.36587793011941616, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.4803085299455535, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.39979952479952485, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.3847926267281106, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.4071404682274248, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.31845238095238093, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.33004250651309475, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.39046683046683045, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.43073280885780885, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.3268886131789358, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.2982369717396941, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.370959595959596, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.35756761159986966, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.3186175115207373, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.45791527818023764, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.1044776119402985, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.1044776119402985, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.1044776119402985, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.1044776119402985, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.1044776119402985, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.3708791208791209, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.3516483516483516, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.3695054945054945, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.36813186813186816, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.3667582417582418, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.3875915750915751, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.4084249084249084, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.4084249084249084, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.4084249084249084, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.4278846153846154, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.4100274725274725, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.3907967032967033, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.3907967032967033, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.3507326007326007, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.3507326007326007, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.3507326007326007, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.3685897435897436, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.389423076923077, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.35370879120879123, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.37293956043956045, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.37133699633699635, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.4084249084249084, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.44253663003663, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.44116300366300365, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.44276556776556775, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.43864468864468864, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.4551282051282052, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.5309065934065934, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.496565934065934, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.4091117216117216, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.5114468864468864, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.45833333333333337, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.42857142857142855, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.4072802197802198, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.36149267399267404, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.35256410256410253, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.40293040293040294, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.4576465201465202, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.36401098901098905, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.3092948717948718, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.4015567765567766, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.36698717948717946, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.35714285714285715, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.4819139194139194, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.25, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.25, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.25, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.25, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.25, "id_best": 27, "lr_best": 0.00047999999999999996, "wd_best": 0.05, "train/loss_best": 0.8442682838439941, "validation/loss_best": 1.3573294878005981, "validation/acc_best": 0.5471698113207547, "validation/f1_best": 0.49924538254709033, "validation/bacc_best": 0.5309065934065934} +{"epoch": 5, "train/lr": 0.00029891323817685334, "train/loss": 0.8872777190804482, "train/grad": 0.5191785795986652, "train/loss_000_lr2.0e-02_wd1.0e+00": 1.25326171875, "train/loss_001_lr2.3e-02_wd1.0e+00": 1.2412646484375, "train/loss_002_lr2.8e-02_wd1.0e+00": 1.223994140625, "train/loss_003_lr3.3e-02_wd1.0e+00": 1.20978759765625, "train/loss_004_lr3.8e-02_wd1.0e+00": 1.19780517578125, "train/loss_005_lr4.5e-02_wd1.0e+00": 1.18395751953125, "train/loss_006_lr5.3e-02_wd1.0e+00": 1.1715966796875, "train/loss_007_lr6.2e-02_wd1.0e+00": 1.16028076171875, "train/loss_008_lr7.4e-02_wd1.0e+00": 1.148369140625, "train/loss_009_lr8.7e-02_wd1.0e+00": 1.13779296875, "train/loss_010_lr1.0e-01_wd1.0e+00": 1.12851806640625, "train/loss_011_lr1.2e-01_wd1.0e+00": 1.116171875, "train/loss_012_lr1.4e-01_wd1.0e+00": 1.104794921875, "train/loss_013_lr1.7e-01_wd1.0e+00": 1.088880615234375, "train/loss_014_lr2.0e-01_wd1.0e+00": 1.0736968994140625, "train/loss_015_lr2.3e-01_wd1.0e+00": 1.058597412109375, "train/loss_016_lr2.7e-01_wd1.0e+00": 1.0390106201171876, "train/loss_017_lr3.2e-01_wd1.0e+00": 1.015699462890625, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.9908050537109375, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.969697265625, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.9474290466308594, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.9274816131591797, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.902879867553711, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.87237548828125, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.831957778930664, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.7682289505004882, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.7005448722839356, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.6323565483093262, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.525377459526062, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.3654580672085285, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.23424887537956238, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.16503074929118156, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.07726223856210708, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.09871878653764725, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.05542145162820816, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.007272205203771591, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.060659633576869966, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.2511391779780388, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.5329896128177642, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.7445539593696594, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.667306074500084, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.8710527305305004, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.4525553765892982, "train/loss_043_lr2.2e+01_wd1.0e+00": 1.356263729929924, "train/loss_044_lr2.6e+01_wd1.0e+00": 1.3828125, "train/loss_045_lr3.1e+01_wd1.0e+00": 1.3828125, "train/loss_046_lr3.6e+01_wd1.0e+00": 1.3828125, "train/loss_047_lr4.3e+01_wd1.0e+00": 1.3828125, "train/loss_048_lr5.0e+01_wd1.0e+00": 1.3828125, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.04327189524192363, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.043145978851243855, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.04299322321079671, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.042893104767426846, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.042828763448633254, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.04279608712531626, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.042805932657793165, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.04285957457963377, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.04295301434583962, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.04308250480797142, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.04319552781060338, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.04337043766397983, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.04354036222677678, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.043808801718987524, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.04409452143590897, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.04437833752948791, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.04475652494933456, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.04531219225842506, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.04614236619323492, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.047151458458974956, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.04841428061947226, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.04926049462053925, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.04966210727114231, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.05046115427277982, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.050391013929620386, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.050207495549693705, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.05090927854180336, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.05205728496890515, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.051739256996661424, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.046033436607103795, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.034675994850695134, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.028837143522687257, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.019896168661507545, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.02742854127762257, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.014432884787893271, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.005681267506133736, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.025662684605340474, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.06720479326794702, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.09819438670806449, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.10921118670819852, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.10096722404392494, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.1351302224999199, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.19885221880457693, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.21654955864376801, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 1.27033531665802, "validation/loss_001_lr2.3e-02_wd1.0e+00": 1.2608261108398438, "validation/loss_002_lr2.8e-02_wd1.0e+00": 1.2481733560562134, "validation/loss_003_lr3.3e-02_wd1.0e+00": 1.2386400699615479, "validation/loss_004_lr3.8e-02_wd1.0e+00": 1.2314749956130981, "validation/loss_005_lr4.5e-02_wd1.0e+00": 1.2240628004074097, "validation/loss_006_lr5.3e-02_wd1.0e+00": 1.218550443649292, "validation/loss_007_lr6.2e-02_wd1.0e+00": 1.214254379272461, "validation/loss_008_lr7.4e-02_wd1.0e+00": 1.2107874155044556, "validation/loss_009_lr8.7e-02_wd1.0e+00": 1.2082297801971436, "validation/loss_010_lr1.0e-01_wd1.0e+00": 1.2060072422027588, "validation/loss_011_lr1.2e-01_wd1.0e+00": 1.2037464380264282, "validation/loss_012_lr1.4e-01_wd1.0e+00": 1.201460838317871, "validation/loss_013_lr1.7e-01_wd1.0e+00": 1.1986117362976074, "validation/loss_014_lr2.0e-01_wd1.0e+00": 1.1950196027755737, "validation/loss_015_lr2.3e-01_wd1.0e+00": 1.1917881965637207, "validation/loss_016_lr2.7e-01_wd1.0e+00": 1.188338279724121, "validation/loss_017_lr3.2e-01_wd1.0e+00": 1.1875486373901367, "validation/loss_018_lr3.8e-01_wd1.0e+00": 1.190406322479248, "validation/loss_019_lr4.4e-01_wd1.0e+00": 1.1960313320159912, "validation/loss_020_lr5.2e-01_wd1.0e+00": 1.202072024345398, "validation/loss_021_lr6.1e-01_wd1.0e+00": 1.1976537704467773, "validation/loss_022_lr7.2e-01_wd1.0e+00": 1.2038801908493042, "validation/loss_023_lr8.5e-01_wd1.0e+00": 1.2598766088485718, "validation/loss_024_lr1.0e+00_wd1.0e+00": 1.372738003730774, "validation/loss_025_lr1.2e+00_wd1.0e+00": 1.5779292583465576, "validation/loss_026_lr1.4e+00_wd1.0e+00": 1.6660622358322144, "validation/loss_027_lr1.6e+00_wd1.0e+00": 1.8519868850708008, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.2462031841278076, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.8662097454071045, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.233096122741699, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.599148750305176, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.4995882511138916, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.9996304512023926, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.756466865539551, "validation/loss_035_lr6.0e+00_wd1.0e+00": 4.035581111907959, "validation/loss_036_lr7.1e+00_wd1.0e+00": 4.508461952209473, "validation/loss_037_lr8.3e+00_wd1.0e+00": 5.239446640014648, "validation/loss_038_lr9.8e+00_wd1.0e+00": 7.926334381103516, "validation/loss_039_lr1.2e+01_wd1.0e+00": 7.583824157714844, "validation/loss_040_lr1.4e+01_wd1.0e+00": 9.321694374084473, "validation/loss_041_lr1.6e+01_wd1.0e+00": 10.308378219604492, "validation/loss_042_lr1.9e+01_wd1.0e+00": 17.582109451293945, "validation/loss_043_lr2.2e+01_wd1.0e+00": 17.02684783935547, "validation/loss_044_lr2.6e+01_wd1.0e+00": 1.3862943649291992, "validation/loss_045_lr3.1e+01_wd1.0e+00": 1.3862943649291992, "validation/loss_046_lr3.6e+01_wd1.0e+00": 1.3862943649291992, "validation/loss_047_lr4.3e+01_wd1.0e+00": 1.3862943649291992, "validation/loss_048_lr5.0e+01_wd1.0e+00": 1.3862943649291992, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.37735849056603776, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.37735849056603776, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.39622641509433965, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.39622641509433965, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.39622641509433965, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.4339622641509434, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.41509433962264153, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.39622641509433965, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.39622641509433965, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.39622641509433965, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.37735849056603776, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.37735849056603776, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.3584905660377358, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.37735849056603776, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.37735849056603776, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.39622641509433965, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.41509433962264153, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.41509433962264153, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.4339622641509434, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.41509433962264153, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.41509433962264153, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.41509433962264153, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.41509433962264153, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.37735849056603776, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.41509433962264153, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.4716981132075472, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.5094339622641509, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.39622641509433965, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.49056603773584906, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.41509433962264153, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.39622641509433965, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.41509433962264153, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.39622641509433965, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.3584905660377358, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.3584905660377358, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.37735849056603776, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.3584905660377358, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.39622641509433965, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.33962264150943394, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.3018867924528302, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.4339622641509434, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.3584905660377358, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.3584905660377358, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.32075471698113206, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.2641509433962264, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.2641509433962264, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.2641509433962264, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.2641509433962264, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.2641509433962264, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.3244565217391304, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.3244565217391304, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.36241439719700586, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.36241439719700586, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.3666666666666667, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.4277968481822437, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.40922333971902936, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.39252210387078806, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.39252210387078806, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.39173538685423237, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.3730295566502463, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.3730295566502463, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.34573502722323046, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.37056650246305417, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.36964057653712823, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.38528097062579825, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.4106914796569969, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.41954022988505746, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.436183608058608, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.4176623376623376, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.4176623376623376, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.4175, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.41214285714285714, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.35794602698650674, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.3565284351288408, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.3835294117647059, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.4195815170008719, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.33607387236419495, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.4469744887202193, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.3851220538720539, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.3894306418219462, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.41012820512820514, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.38271362526621994, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.33627450980392154, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.3510079575596817, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.38001628001628, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.35166046319272126, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.4035964912280702, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.3498135198135198, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.3008933658933659, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.4180555555555555, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.3579365079365079, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.2996031746031746, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.30222222222222217, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.1044776119402985, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.1044776119402985, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.1044776119402985, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.1044776119402985, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.1044776119402985, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.3667582417582418, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.3667582417582418, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.3875915750915751, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.3875915750915751, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.38621794871794873, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.4278846153846154, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.40865384615384615, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.3907967032967033, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.3907967032967033, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.3907967032967033, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.3715659340659341, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.3715659340659341, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.3507326007326007, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.3715659340659341, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.3715659340659341, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.389423076923077, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.41025641025641024, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.41025641025641024, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.4294871794871795, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.4116300366300366, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.4116300366300366, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.4132326007326007, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.41185897435897434, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.3733974358974359, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.40476190476190477, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.45535714285714285, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.49404761904761907, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.3839285714285714, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.4835164835164836, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.41208791208791207, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.3926282051282051, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.4075091575091575, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.38965201465201466, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.36149267399267393, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.35096153846153844, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.37477106227106227, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.35393772893772896, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.40132783882783885, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.33722527472527475, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.29876373626373626, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.4409340659340659, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.3564560439560439, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.34523809523809523, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.3179945054945055, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.25, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.25, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.25, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.25, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.25, "id_best": 26, "lr_best": 0.00041999999999999996, "wd_best": 0.05, "train/loss_best": 0.7005448722839356, "validation/loss_best": 1.6660622358322144, "validation/acc_best": 0.5094339622641509, "validation/f1_best": 0.4195815170008719, "validation/bacc_best": 0.49404761904761907} +{"epoch": 6, "train/lr": 0.0002924170901991409, "train/loss": 0.7568066664040088, "train/grad": 0.43739603996276855, "train/loss_000_lr2.0e-02_wd1.0e+00": 1.2282470703125, "train/loss_001_lr2.3e-02_wd1.0e+00": 1.2160595703125, "train/loss_002_lr2.8e-02_wd1.0e+00": 1.19927978515625, "train/loss_003_lr3.3e-02_wd1.0e+00": 1.185771484375, "train/loss_004_lr3.8e-02_wd1.0e+00": 1.17478759765625, "train/loss_005_lr4.5e-02_wd1.0e+00": 1.16216552734375, "train/loss_006_lr5.3e-02_wd1.0e+00": 1.150711669921875, "train/loss_007_lr6.2e-02_wd1.0e+00": 1.1399560546875, "train/loss_008_lr7.4e-02_wd1.0e+00": 1.12766357421875, "train/loss_009_lr8.7e-02_wd1.0e+00": 1.115732421875, "train/loss_010_lr1.0e-01_wd1.0e+00": 1.105142822265625, "train/loss_011_lr1.2e-01_wd1.0e+00": 1.089991455078125, "train/loss_012_lr1.4e-01_wd1.0e+00": 1.0756439208984374, "train/loss_013_lr1.7e-01_wd1.0e+00": 1.055279541015625, "train/loss_014_lr2.0e-01_wd1.0e+00": 1.035211181640625, "train/loss_015_lr2.3e-01_wd1.0e+00": 1.014969482421875, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.9885809326171875, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.9578143310546875, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.9267723083496093, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.9026478576660156, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.8769551849365235, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.8490139770507813, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.8099695587158203, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.7596545791625977, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.6859066009521484, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.5730088329315186, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.4552341282367706, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.31469015836715697, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.1739850291609764, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.04289317086338997, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.012461247742176057, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.005541692227125168, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.002778610736131668, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.0015869188308715821, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.0012472379207611084, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.0006588836014270783, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.20131904274225235, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.08232022494077683, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.004421099722385406, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.13570074409246444, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.3665323379635811, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.05357854306697846, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.1003019806742669, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.8072764533758163, "train/loss_044_lr2.6e+01_wd1.0e+00": 1.3828125, "train/loss_045_lr3.1e+01_wd1.0e+00": 1.3828125, "train/loss_046_lr3.6e+01_wd1.0e+00": 1.3828125, "train/loss_047_lr4.3e+01_wd1.0e+00": 1.3828125, "train/loss_048_lr5.0e+01_wd1.0e+00": 1.3828125, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.044306860249489544, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.044291047919541596, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.04431011575274169, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.04436732617206871, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.0444500466203317, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.04457118213642389, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.044736115145497024, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.044917046953924, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.04513770364690572, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.045350641468539836, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.045548922824673356, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.0458220572443679, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.04609095145016909, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.04649712896440178, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.04692192564252764, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.04738513844553381, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.04807306318543851, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.048939187433570626, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.04987836878746748, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.05067337025888264, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.051354720490053296, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.05165338220074773, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.052221512785181404, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.052677525151520965, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.05248188198544085, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.050685259979218245, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.04890287850983441, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.04365751266945153, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.03448929739068262, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.012464474865701049, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.004834503381862305, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.00187606733845314, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.000834558327915147, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0006691859100283182, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.00038484889362734977, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.00024254890235170023, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.04956644020777276, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.027217458938822006, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.007694799068490283, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.044146539643275556, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.07562172519053638, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.020356538641627394, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.20819978622387456, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.1411428815484957, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 1.2543771266937256, "validation/loss_001_lr2.3e-02_wd1.0e+00": 1.2457524538040161, "validation/loss_002_lr2.8e-02_wd1.0e+00": 1.2351267337799072, "validation/loss_003_lr3.3e-02_wd1.0e+00": 1.2277201414108276, "validation/loss_004_lr3.8e-02_wd1.0e+00": 1.2226521968841553, "validation/loss_005_lr4.5e-02_wd1.0e+00": 1.2174173593521118, "validation/loss_006_lr5.3e-02_wd1.0e+00": 1.2139959335327148, "validation/loss_007_lr6.2e-02_wd1.0e+00": 1.2113457918167114, "validation/loss_008_lr7.4e-02_wd1.0e+00": 1.2091552019119263, "validation/loss_009_lr8.7e-02_wd1.0e+00": 1.2068625688552856, "validation/loss_010_lr1.0e-01_wd1.0e+00": 1.205257773399353, "validation/loss_011_lr1.2e-01_wd1.0e+00": 1.202196717262268, "validation/loss_012_lr1.4e-01_wd1.0e+00": 1.1988731622695923, "validation/loss_013_lr1.7e-01_wd1.0e+00": 1.1941362619400024, "validation/loss_014_lr2.0e-01_wd1.0e+00": 1.1898289918899536, "validation/loss_015_lr2.3e-01_wd1.0e+00": 1.1854394674301147, "validation/loss_016_lr2.7e-01_wd1.0e+00": 1.1806267499923706, "validation/loss_017_lr3.2e-01_wd1.0e+00": 1.1816949844360352, "validation/loss_018_lr3.8e-01_wd1.0e+00": 1.1916372776031494, "validation/loss_019_lr4.4e-01_wd1.0e+00": 1.2079670429229736, "validation/loss_020_lr5.2e-01_wd1.0e+00": 1.2240357398986816, "validation/loss_021_lr6.1e-01_wd1.0e+00": 1.2443666458129883, "validation/loss_022_lr7.2e-01_wd1.0e+00": 1.2852469682693481, "validation/loss_023_lr8.5e-01_wd1.0e+00": 1.3546327352523804, "validation/loss_024_lr1.0e+00_wd1.0e+00": 1.5207511186599731, "validation/loss_025_lr1.2e+00_wd1.0e+00": 1.8016037940979004, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.118555784225464, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.5366015434265137, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.211944818496704, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.8370234966278076, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.935502052307129, "validation/loss_031_lr3.1e+00_wd1.0e+00": 4.050131797790527, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.7088301181793213, "validation/loss_033_lr4.3e+00_wd1.0e+00": 4.1178460121154785, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.8903157711029053, "validation/loss_035_lr6.0e+00_wd1.0e+00": 4.013797283172607, "validation/loss_036_lr7.1e+00_wd1.0e+00": 6.176074504852295, "validation/loss_037_lr8.3e+00_wd1.0e+00": 5.38545036315918, "validation/loss_038_lr9.8e+00_wd1.0e+00": 6.4913811683654785, "validation/loss_039_lr1.2e+01_wd1.0e+00": 8.54954719543457, "validation/loss_040_lr1.4e+01_wd1.0e+00": 11.256954193115234, "validation/loss_041_lr1.6e+01_wd1.0e+00": 8.58448600769043, "validation/loss_042_lr1.9e+01_wd1.0e+00": 25.024171829223633, "validation/loss_043_lr2.2e+01_wd1.0e+00": 13.42264461517334, "validation/loss_044_lr2.6e+01_wd1.0e+00": 1.3862943649291992, "validation/loss_045_lr3.1e+01_wd1.0e+00": 1.3862943649291992, "validation/loss_046_lr3.6e+01_wd1.0e+00": 1.3862943649291992, "validation/loss_047_lr4.3e+01_wd1.0e+00": 1.3862943649291992, "validation/loss_048_lr5.0e+01_wd1.0e+00": 1.3862943649291992, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.39622641509433965, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.39622641509433965, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.39622641509433965, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.41509433962264153, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.4339622641509434, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.41509433962264153, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.39622641509433965, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.39622641509433965, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.39622641509433965, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.39622641509433965, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.39622641509433965, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.3584905660377358, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.3584905660377358, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.39622641509433965, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.41509433962264153, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.41509433962264153, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.41509433962264153, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.4716981132075472, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.4528301886792453, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.4339622641509434, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.41509433962264153, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.39622641509433965, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.4339622641509434, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.4528301886792453, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.4528301886792453, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.41509433962264153, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.39622641509433965, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.39622641509433965, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.33962264150943394, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.32075471698113206, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.3584905660377358, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.4339622641509434, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.41509433962264153, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.39622641509433965, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.41509433962264153, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.3584905660377358, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.37735849056603776, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.37735849056603776, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.33962264150943394, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.24528301886792453, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.37735849056603776, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.4339622641509434, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.33962264150943394, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.3018867924528302, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.2641509433962264, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.2641509433962264, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.2641509433962264, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.2641509433962264, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.2641509433962264, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.36241439719700586, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.36241439719700586, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.36241439719700586, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.4010057471264368, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.4291219936250362, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.41003980539584256, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.3937159331896174, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.3937159331896174, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.3937159331896174, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.3937159331896174, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.392135989010989, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.346514994382508, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.346514994382508, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.3871985999481462, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.412807881773399, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.41954022988505746, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.41782300733913635, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.4580486563245184, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.42564587688426697, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.4040631808278867, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.38072325987927014, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.3728156565656566, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.39811165845648605, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.41301843317972353, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.38277649769585254, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.3658357771260997, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.37476190476190474, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.37513118440779614, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.3301220650358581, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.31142886683209264, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.3611111111111111, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.4278205128205128, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.40095238095238095, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.3875606641123882, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.40003096742227173, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.36292226292226293, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.36356788372917404, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.37248866261658253, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.34065934065934067, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.2453150714020279, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.34691199060269273, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.42376926616057053, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.3212842907999442, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.3033126293995859, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.1044776119402985, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.1044776119402985, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.1044776119402985, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.1044776119402985, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.1044776119402985, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.3875915750915751, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.3875915750915751, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.3875915750915751, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.40705128205128205, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.4278846153846154, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.4100274725274725, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.3907967032967033, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.3907967032967033, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.3907967032967033, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.3907967032967033, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.3907967032967033, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.3507326007326007, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.3507326007326007, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.389423076923077, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.41025641025641024, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.41025641025641024, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.41025641025641024, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.46382783882783885, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.4429945054945055, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.42376373626373626, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.40453296703296704, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.38667582417582413, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.42559523809523814, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.44345238095238093, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.4375, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.4017857142857143, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.38530219780219777, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.38530219780219777, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.3317307692307692, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.31387362637362637, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.35393772893772896, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.4283424908424909, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.4134615384615385, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.38965201465201466, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.4075091575091575, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.3569139194139194, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.37293956043956045, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.3816391941391941, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.3358516483516484, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.24679487179487178, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.36744505494505497, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.4249084249084249, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.3376831501831502, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.30471611721611724, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.25, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.25, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.25, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.25, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.25, "id_best": 17, "lr_best": 9.599999999999999e-05, "wd_best": 0.05, "train/loss_best": 0.9578143310546875, "validation/loss_best": 1.1816949844360352, "validation/acc_best": 0.4716981132075472, "validation/f1_best": 0.4580486563245184, "validation/bacc_best": 0.46382783882783885} +{"epoch": 7, "train/lr": 0.00027969249556793234, "train/loss": 0.6684260241687298, "train/grad": 0.27283284910023214, "train/loss_000_lr2.0e-02_wd1.0e+00": 1.2199755859375, "train/loss_001_lr2.3e-02_wd1.0e+00": 1.20884521484375, "train/loss_002_lr2.8e-02_wd1.0e+00": 1.1939013671875, "train/loss_003_lr3.3e-02_wd1.0e+00": 1.182177734375, "train/loss_004_lr3.8e-02_wd1.0e+00": 1.17226806640625, "train/loss_005_lr4.5e-02_wd1.0e+00": 1.1610595703125, "train/loss_006_lr5.3e-02_wd1.0e+00": 1.15027099609375, "train/loss_007_lr6.2e-02_wd1.0e+00": 1.13938720703125, "train/loss_008_lr7.4e-02_wd1.0e+00": 1.1263818359375, "train/loss_009_lr8.7e-02_wd1.0e+00": 1.113443603515625, "train/loss_010_lr1.0e-01_wd1.0e+00": 1.101275634765625, "train/loss_011_lr1.2e-01_wd1.0e+00": 1.08331298828125, "train/loss_012_lr1.4e-01_wd1.0e+00": 1.065718994140625, "train/loss_013_lr1.7e-01_wd1.0e+00": 1.0402630615234374, "train/loss_014_lr2.0e-01_wd1.0e+00": 1.0150863647460937, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.989827880859375, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.9569676208496094, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.9187324523925782, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.8801704406738281, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.8485200500488281, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.8122097396850586, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.7718545532226563, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.716036262512207, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.6343024253845215, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.5050208044052124, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.3068485796451569, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.13859521329402924, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.06089154839515686, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.017456085085868836, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.006367837935686111, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0034279949963092805, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.0024426621198654175, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.0014104633033275604, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.0008615067601203918, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.0008931848406791687, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.0005470141768455505, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.1449258928000927, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.00012896165251731872, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.0001723681390285492, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.011264885663986207, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.0002062109112739563, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.00013710349798202516, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.04634978637099266, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.08887578591704369, "train/loss_044_lr2.6e+01_wd1.0e+00": 1.3828125, "train/loss_045_lr3.1e+01_wd1.0e+00": 1.3828125, "train/loss_046_lr3.6e+01_wd1.0e+00": 1.3828125, "train/loss_047_lr4.3e+01_wd1.0e+00": 1.3828125, "train/loss_048_lr5.0e+01_wd1.0e+00": 1.3828125, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.04278284997213632, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.042751991120167074, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.04274648523889482, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.04278407150879502, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.04283403066452593, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.042936065993271766, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.04305552283767611, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.04318051489070058, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.04333207916468382, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.04348984012380242, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.04364739852491766, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.0439039495959878, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.04421747746877372, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.044766866941936316, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.045467297583818435, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.04636946904473007, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.047851061886176466, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.04982917194254696, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.052076085433363915, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.05377181628718972, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.05498046420514584, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.05557142669335008, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.05591080856509507, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.05652154733426869, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.05508676023222506, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.04577834988478571, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.028004139973782004, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.01628244045889005, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.00497698587103514, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0017260763308149763, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0009662423109693918, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0006878862979647238, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0004364512798929354, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0002905852779804263, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.00026356122336437695, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.00018106921885191696, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0429397056076607, "train/grad_037_lr8.3e+00_wd1.0e+00": 9.351677170229777e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0001418920063764517, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.006968376044762417, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0013121076658464403, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0006676571615691529, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.026443104016882144, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.02204851078647211, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 1.2425312995910645, "validation/loss_001_lr2.3e-02_wd1.0e+00": 1.2351624965667725, "validation/loss_002_lr2.8e-02_wd1.0e+00": 1.2261183261871338, "validation/loss_003_lr3.3e-02_wd1.0e+00": 1.2200708389282227, "validation/loss_004_lr3.8e-02_wd1.0e+00": 1.2162549495697021, "validation/loss_005_lr4.5e-02_wd1.0e+00": 1.2128117084503174, "validation/loss_006_lr5.3e-02_wd1.0e+00": 1.2100889682769775, "validation/loss_007_lr6.2e-02_wd1.0e+00": 1.2083630561828613, "validation/loss_008_lr7.4e-02_wd1.0e+00": 1.2065365314483643, "validation/loss_009_lr8.7e-02_wd1.0e+00": 1.2050950527191162, "validation/loss_010_lr1.0e-01_wd1.0e+00": 1.2035795450210571, "validation/loss_011_lr1.2e-01_wd1.0e+00": 1.2019662857055664, "validation/loss_012_lr1.4e-01_wd1.0e+00": 1.2005703449249268, "validation/loss_013_lr1.7e-01_wd1.0e+00": 1.1998144388198853, "validation/loss_014_lr2.0e-01_wd1.0e+00": 1.201136589050293, "validation/loss_015_lr2.3e-01_wd1.0e+00": 1.2051209211349487, "validation/loss_016_lr2.7e-01_wd1.0e+00": 1.2086971998214722, "validation/loss_017_lr3.2e-01_wd1.0e+00": 1.20701003074646, "validation/loss_018_lr3.8e-01_wd1.0e+00": 1.2087125778198242, "validation/loss_019_lr4.4e-01_wd1.0e+00": 1.2181689739227295, "validation/loss_020_lr5.2e-01_wd1.0e+00": 1.2482876777648926, "validation/loss_021_lr6.1e-01_wd1.0e+00": 1.2981760501861572, "validation/loss_022_lr7.2e-01_wd1.0e+00": 1.3821027278900146, "validation/loss_023_lr8.5e-01_wd1.0e+00": 1.5697935819625854, "validation/loss_024_lr1.0e+00_wd1.0e+00": 1.8315380811691284, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.3361661434173584, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.902806043624878, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.4152119159698486, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.9022579193115234, "validation/loss_029_lr2.3e+00_wd1.0e+00": 4.265035152435303, "validation/loss_030_lr2.7e+00_wd1.0e+00": 4.2155985832214355, "validation/loss_031_lr3.1e+00_wd1.0e+00": 4.283623695373535, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.8359434604644775, "validation/loss_033_lr4.3e+00_wd1.0e+00": 4.177395343780518, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.962559938430786, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.9745678901672363, "validation/loss_036_lr7.1e+00_wd1.0e+00": 6.561892509460449, "validation/loss_037_lr8.3e+00_wd1.0e+00": 5.035988807678223, "validation/loss_038_lr9.8e+00_wd1.0e+00": 6.0960283279418945, "validation/loss_039_lr1.2e+01_wd1.0e+00": 7.907431602478027, "validation/loss_040_lr1.4e+01_wd1.0e+00": 9.300954818725586, "validation/loss_041_lr1.6e+01_wd1.0e+00": 8.029312133789062, "validation/loss_042_lr1.9e+01_wd1.0e+00": 19.87620735168457, "validation/loss_043_lr2.2e+01_wd1.0e+00": 17.290035247802734, "validation/loss_044_lr2.6e+01_wd1.0e+00": 1.3862943649291992, "validation/loss_045_lr3.1e+01_wd1.0e+00": 1.3862943649291992, "validation/loss_046_lr3.6e+01_wd1.0e+00": 1.3862943649291992, "validation/loss_047_lr4.3e+01_wd1.0e+00": 1.3862943649291992, "validation/loss_048_lr5.0e+01_wd1.0e+00": 1.3862943649291992, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.39622641509433965, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.41509433962264153, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.4339622641509434, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.4339622641509434, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.41509433962264153, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.41509433962264153, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.39622641509433965, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.39622641509433965, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.37735849056603776, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.37735849056603776, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.37735849056603776, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.41509433962264153, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.4339622641509434, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.41509433962264153, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.4339622641509434, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.4339622641509434, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.4528301886792453, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.4339622641509434, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.4339622641509434, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.4339622641509434, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.4339622641509434, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.41509433962264153, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.39622641509433965, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.41509433962264153, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.3584905660377358, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.33962264150943394, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.37735849056603776, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.3584905660377358, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.33962264150943394, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.3018867924528302, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.3584905660377358, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.4339622641509434, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.39622641509433965, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.37735849056603776, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.39622641509433965, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.3584905660377358, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.41509433962264153, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.3584905660377358, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.3584905660377358, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.37735849056603776, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.39622641509433965, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.37735849056603776, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.32075471698113206, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.39622641509433965, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.2641509433962264, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.2641509433962264, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.2641509433962264, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.2641509433962264, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.2641509433962264, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.36241439719700586, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.394051116333725, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.42674104124408385, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.42674104124408385, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.41041716903785874, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.41041716903785874, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.3937159331896174, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.3937159331896174, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.3648414595839732, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.3648414595839732, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.3648414595839732, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.39646464646464646, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.4217741935483871, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.41005999932585024, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.42948898927159795, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.432767573432535, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.44747345578547626, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.42870670995671, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.43465909090909094, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.43437476501992633, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.43103862931449144, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.41036922015182886, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.3937728937728938, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.41607142857142854, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.35206517620310723, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.3402116402116402, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.37802604802604806, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.3588328912466844, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.3376006975144906, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.29638888888888887, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.3611111111111111, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.4278205128205128, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.38614420062695926, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.37309116809116805, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.38822751322751325, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.36292226292226293, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.4023543783663724, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.35691194581280783, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.35851458885941645, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.3629818031430935, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.383678955453149, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.3756054664975204, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.31650246305418717, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.407512006460113, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.1044776119402985, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.1044776119402985, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.1044776119402985, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.1044776119402985, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.1044776119402985, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.3875915750915751, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.4084249084249084, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.4278846153846154, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.4278846153846154, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.40865384615384615, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.40865384615384615, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.3907967032967033, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.3907967032967033, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.36996336996337, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.36996336996337, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.36996336996337, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.40705128205128205, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.4278846153846154, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.4116300366300366, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.4308608058608059, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.4308608058608059, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.45009157509157505, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.4308608058608059, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.43383699633699635, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.43246336996337, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.4310897435897436, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.41185897435897434, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.3926282051282052, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.41185897435897434, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.35096153846153844, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.3331043956043956, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.37179487179487175, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.3539377289377289, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.3331043956043956, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.2960164835164835, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.35393772893772896, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.4283424908424909, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.3956043956043956, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.3717948717948718, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.38965201465201466, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.3569139194139194, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.40567765567765574, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.36080586080586075, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.35370879120879123, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.3685897435897436, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.3896520146520146, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.37133699633699635, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.315018315018315, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.39514652014652013, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.25, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.25, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.25, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.25, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.25, "id_best": 16, "lr_best": 8.1e-05, "wd_best": 0.05, "train/loss_best": 0.9569676208496094, "validation/loss_best": 1.2086971998214722, "validation/acc_best": 0.4528301886792453, "validation/f1_best": 0.44747345578547626, "validation/bacc_best": 0.45009157509157505} +{"epoch": 8, "train/lr": 0.0002612959497061927, "train/loss": 0.632468281686306, "train/grad": 0.25416603665798904, "train/loss_000_lr2.0e-02_wd1.0e+00": 1.18587646484375, "train/loss_001_lr2.3e-02_wd1.0e+00": 1.17462890625, "train/loss_002_lr2.8e-02_wd1.0e+00": 1.159912109375, "train/loss_003_lr3.3e-02_wd1.0e+00": 1.14858642578125, "train/loss_004_lr3.8e-02_wd1.0e+00": 1.1395556640625, "train/loss_005_lr4.5e-02_wd1.0e+00": 1.129139404296875, "train/loss_006_lr5.3e-02_wd1.0e+00": 1.119287109375, "train/loss_007_lr6.2e-02_wd1.0e+00": 1.10941650390625, "train/loss_008_lr7.4e-02_wd1.0e+00": 1.0974591064453125, "train/loss_009_lr8.7e-02_wd1.0e+00": 1.085189208984375, "train/loss_010_lr1.0e-01_wd1.0e+00": 1.073721923828125, "train/loss_011_lr1.2e-01_wd1.0e+00": 1.05639892578125, "train/loss_012_lr1.4e-01_wd1.0e+00": 1.0394210815429688, "train/loss_013_lr1.7e-01_wd1.0e+00": 1.0140185546875, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.9882984924316406, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.9622972106933594, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.9292317199707031, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.8914992523193359, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.8480684661865234, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.8079005813598633, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.7639192008972168, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.7189444541931153, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.6425090599060058, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.5116944932937622, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.313121135532856, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.09552778661251068, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.027976409792900087, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.013516865819692612, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.007301291823387146, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0035823050141334536, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0022354485094547272, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.001714978516101837, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.0011252258718013764, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.0007674276828765869, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.0007154631614685058, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.0005123251676559448, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.009154547452926636, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.00016298174858093262, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.00020869642496109008, "train/loss_039_lr1.2e+01_wd1.0e+00": 4.0564239025115964e-05, "train/loss_040_lr1.4e+01_wd1.0e+00": 5.203738808631897e-05, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.00011448934674263, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.4489293098449707e-05, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.0020651520788669588, "train/loss_044_lr2.6e+01_wd1.0e+00": 1.3828125, "train/loss_045_lr3.1e+01_wd1.0e+00": 1.3828125, "train/loss_046_lr3.6e+01_wd1.0e+00": 1.3828125, "train/loss_047_lr4.3e+01_wd1.0e+00": 1.3828125, "train/loss_048_lr5.0e+01_wd1.0e+00": 1.3828125, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.043740777210332454, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.04376575098838657, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.043845193488523365, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.04395704421680421, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.044083802457898856, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.04427306072320789, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.04446435543708503, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.04466569166164845, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.044921996714547274, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.04519149017520249, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.045491776708513496, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.04597182534635067, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.046498355939984325, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.04738846942782402, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.04843574066646397, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.04974200411699712, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.05169707275927067, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.05399544312618673, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.05612430744804442, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.05730587102472782, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.05781245829537511, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.05826808479614556, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.05900756084360182, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.05707154270261526, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.04687492994125932, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.02332631027442403, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.008087615832919256, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.003748217924730852, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0019613106464385056, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.001005204914981732, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0006436419134843163, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.00047427337158296724, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0003197033056494547, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0002290156917661079, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0002173748254426755, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.00016024286194806335, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.00444681183717563, "train/grad_037_lr8.3e+00_wd1.0e+00": 9.290678808397957e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.00013221604402588127, "train/grad_039_lr1.2e+01_wd1.0e+00": 4.27508709119806e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 5.523915173434091e-05, "train/grad_041_lr1.6e+01_wd1.0e+00": 8.776085487895102e-05, "train/grad_042_lr1.9e+01_wd1.0e+00": 3.0464279877128707e-05, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0005597988507626651, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 1.234947919845581, "validation/loss_001_lr2.3e-02_wd1.0e+00": 1.2285531759262085, "validation/loss_002_lr2.8e-02_wd1.0e+00": 1.2208884954452515, "validation/loss_003_lr3.3e-02_wd1.0e+00": 1.216300368309021, "validation/loss_004_lr3.8e-02_wd1.0e+00": 1.213120460510254, "validation/loss_005_lr4.5e-02_wd1.0e+00": 1.2102110385894775, "validation/loss_006_lr5.3e-02_wd1.0e+00": 1.2079049348831177, "validation/loss_007_lr6.2e-02_wd1.0e+00": 1.2058606147766113, "validation/loss_008_lr7.4e-02_wd1.0e+00": 1.2035696506500244, "validation/loss_009_lr8.7e-02_wd1.0e+00": 1.2010793685913086, "validation/loss_010_lr1.0e-01_wd1.0e+00": 1.1991149187088013, "validation/loss_011_lr1.2e-01_wd1.0e+00": 1.1960771083831787, "validation/loss_012_lr1.4e-01_wd1.0e+00": 1.1944122314453125, "validation/loss_013_lr1.7e-01_wd1.0e+00": 1.195975661277771, "validation/loss_014_lr2.0e-01_wd1.0e+00": 1.2019189596176147, "validation/loss_015_lr2.3e-01_wd1.0e+00": 1.208620309829712, "validation/loss_016_lr2.7e-01_wd1.0e+00": 1.2145599126815796, "validation/loss_017_lr3.2e-01_wd1.0e+00": 1.2174705266952515, "validation/loss_018_lr3.8e-01_wd1.0e+00": 1.2381521463394165, "validation/loss_019_lr4.4e-01_wd1.0e+00": 1.288116693496704, "validation/loss_020_lr5.2e-01_wd1.0e+00": 1.3721964359283447, "validation/loss_021_lr6.1e-01_wd1.0e+00": 1.4373751878738403, "validation/loss_022_lr7.2e-01_wd1.0e+00": 1.5810128450393677, "validation/loss_023_lr8.5e-01_wd1.0e+00": 1.89639151096344, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.350267171859741, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.0033111572265625, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.4445881843566895, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.8287792205810547, "validation/loss_028_lr1.9e+00_wd1.0e+00": 4.264970779418945, "validation/loss_029_lr2.3e+00_wd1.0e+00": 4.498462200164795, "validation/loss_030_lr2.7e+00_wd1.0e+00": 4.385184288024902, "validation/loss_031_lr3.1e+00_wd1.0e+00": 4.430203914642334, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.9233508110046387, "validation/loss_033_lr4.3e+00_wd1.0e+00": 4.221991062164307, "validation/loss_034_lr5.1e+00_wd1.0e+00": 4.011569499969482, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.9462311267852783, "validation/loss_036_lr7.1e+00_wd1.0e+00": 6.586421012878418, "validation/loss_037_lr8.3e+00_wd1.0e+00": 4.782529354095459, "validation/loss_038_lr9.8e+00_wd1.0e+00": 5.763751983642578, "validation/loss_039_lr1.2e+01_wd1.0e+00": 7.12811803817749, "validation/loss_040_lr1.4e+01_wd1.0e+00": 8.315143585205078, "validation/loss_041_lr1.6e+01_wd1.0e+00": 7.0592875480651855, "validation/loss_042_lr1.9e+01_wd1.0e+00": 17.2952823638916, "validation/loss_043_lr2.2e+01_wd1.0e+00": 14.565079689025879, "validation/loss_044_lr2.6e+01_wd1.0e+00": 1.3862943649291992, "validation/loss_045_lr3.1e+01_wd1.0e+00": 1.3862943649291992, "validation/loss_046_lr3.6e+01_wd1.0e+00": 1.3862943649291992, "validation/loss_047_lr4.3e+01_wd1.0e+00": 1.3862943649291992, "validation/loss_048_lr5.0e+01_wd1.0e+00": 1.3862943649291992, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.39622641509433965, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.41509433962264153, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.41509433962264153, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.39622641509433965, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.37735849056603776, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.37735849056603776, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.37735849056603776, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.37735849056603776, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.39622641509433965, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.39622641509433965, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.39622641509433965, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.39622641509433965, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.4339622641509434, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.4339622641509434, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.4528301886792453, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.4528301886792453, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.49056603773584906, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.4716981132075472, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.4528301886792453, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.41509433962264153, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.39622641509433965, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.3584905660377358, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.37735849056603776, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.3584905660377358, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.3584905660377358, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.3584905660377358, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.3584905660377358, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.37735849056603776, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.3584905660377358, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.32075471698113206, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.33962264150943394, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.41509433962264153, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.39622641509433965, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.37735849056603776, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.39622641509433965, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.37735849056603776, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.37735849056603776, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.37735849056603776, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.33962264150943394, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.32075471698113206, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.41509433962264153, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.37735849056603776, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.33962264150943394, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.39622641509433965, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.2641509433962264, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.2641509433962264, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.2641509433962264, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.2641509433962264, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.2641509433962264, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.36241439719700586, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.4029201615408512, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.4029201615408512, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.38743737105806075, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.37095543345543347, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.37095543345543347, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.37095543345543347, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.37095543345543347, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.3842490842490842, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.381155642445965, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.381155642445965, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.37888291517323774, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.4096590909090909, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.4039128497248702, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.42028985507246375, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.4382958074534161, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.46647727272727274, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.44919786096256686, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.4343527183600713, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.39595418812686367, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.372707336523126, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.34435481063770534, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.3735632183908046, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.35581918081918085, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.34973544973544973, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.358974358974359, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.35967846967846967, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.3757559681697613, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.35128205128205126, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.3101979117967898, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.33972934472934474, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.4057142857142857, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.38614420062695926, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.37309116809116805, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.38822751322751325, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.37962962962962965, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.366270283661588, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.3771043771043771, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.33794871794871795, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.3090954522738631, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.4052380952380953, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.37881059470264866, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.3362068965517241, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.39381429101117643, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.1044776119402985, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.1044776119402985, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.1044776119402985, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.1044776119402985, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.1044776119402985, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.3875915750915751, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.40705128205128205, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.40705128205128205, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.38782051282051283, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.36996336996337, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.36996336996337, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.36996336996337, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.36996336996337, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.38782051282051283, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.38644688644688646, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.38644688644688646, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.38644688644688646, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.4249084249084249, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.42628205128205127, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.4441391941391941, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.4457417582417582, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.4828296703296703, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.4635989010989011, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.4457417582417582, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.4100274725274725, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.3921703296703297, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.35828754578754585, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.3717948717948718, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.3523351648351648, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.35096153846153844, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.3539377289377289, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.3539377289377289, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.37179487179487175, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.35096153846153844, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.31387362637362637, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.3331043956043956, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.4075091575091575, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.3956043956043956, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.3717948717948718, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.38965201465201466, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.37477106227106227, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.3685897435897436, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.37866300366300365, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.3328754578754579, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.31204212454212454, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.4088827838827839, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.37133699633699635, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.3342490842490842, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.3937728937728937, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.25, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.25, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.25, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.25, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.25, "id_best": 16, "lr_best": 8.1e-05, "wd_best": 0.05, "train/loss_best": 0.9292317199707031, "validation/loss_best": 1.2145599126815796, "validation/acc_best": 0.49056603773584906, "validation/f1_best": 0.46647727272727274, "validation/bacc_best": 0.4828296703296703} +{"epoch": 9, "train/lr": 0.00023803200426111704, "train/loss": 0.6207380010187626, "train/grad": 0.2470161771401763, "train/loss_000_lr2.0e-02_wd1.0e+00": 1.1943798828125, "train/loss_001_lr2.3e-02_wd1.0e+00": 1.18442626953125, "train/loss_002_lr2.8e-02_wd1.0e+00": 1.171376953125, "train/loss_003_lr3.3e-02_wd1.0e+00": 1.161162109375, "train/loss_004_lr3.8e-02_wd1.0e+00": 1.15240234375, "train/loss_005_lr4.5e-02_wd1.0e+00": 1.142030029296875, "train/loss_006_lr5.3e-02_wd1.0e+00": 1.13127197265625, "train/loss_007_lr6.2e-02_wd1.0e+00": 1.120224609375, "train/loss_008_lr7.4e-02_wd1.0e+00": 1.10627685546875, "train/loss_009_lr8.7e-02_wd1.0e+00": 1.0919952392578125, "train/loss_010_lr1.0e-01_wd1.0e+00": 1.0783282470703126, "train/loss_011_lr1.2e-01_wd1.0e+00": 1.058167724609375, "train/loss_012_lr1.4e-01_wd1.0e+00": 1.038372802734375, "train/loss_013_lr1.7e-01_wd1.0e+00": 1.0093679809570313, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.9811978149414062, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.9532691955566406, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.9184051513671875, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.8809664154052734, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.840225715637207, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.8046538162231446, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.7583255004882813, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.6833137893676757, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.5323028993606568, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.3262094184756279, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.12303490355610848, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.028841373026371003, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.011456860601902008, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.006863461881875992, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.004416534453630447, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0024916353821754457, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0016239549219608307, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.001268795281648636, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.000887092649936676, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.0006784062087535858, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.0006020411849021912, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.0004683740437030792, "train/loss_036_lr7.1e+00_wd1.0e+00": 4.9621760845184325e-05, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.000201241672039032, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.0002221931517124176, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.962054848670959e-05, "train/loss_040_lr1.4e+01_wd1.0e+00": 9.222894906997681e-05, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.00018278524279594422, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.1310895681381227e-05, "train/loss_043_lr2.2e+01_wd1.0e+00": 5.0976872444152835e-06, "train/loss_044_lr2.6e+01_wd1.0e+00": 1.3828125, "train/loss_045_lr3.1e+01_wd1.0e+00": 1.3828125, "train/loss_046_lr3.6e+01_wd1.0e+00": 1.3828125, "train/loss_047_lr4.3e+01_wd1.0e+00": 1.3828125, "train/loss_048_lr5.0e+01_wd1.0e+00": 1.3828125, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.04399780760519206, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.04402752141933888, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.04411998727824539, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.04423421582672745, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.04435694415587932, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.04449980340432376, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.044643577462993564, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.04479515105020255, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.04498267146758735, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.045199830206111076, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.04546477663796395, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.04594854930881411, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.04656884177122265, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.0477651162398979, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.049330484098754825, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.051038171919062736, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.05296419930644333, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.05471747623756528, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.056269951639696954, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.05747253911569714, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.05835634714923799, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.057957630660384896, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.056340594599023464, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0489530413877219, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.028052857487928122, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.008023139589931816, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.003261472652084194, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0019368426725850441, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0011987545085139573, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0006750340606959071, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.000449218368739821, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0003469917131587863, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0002510837671070476, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.00019171874679159374, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0001811863269904279, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.00013820476993714692, "train/grad_036_lr7.1e+00_wd1.0e+00": 3.980167620090569e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.00010494336811234462, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.00013757746366309222, "train/grad_039_lr1.2e+01_wd1.0e+00": 4.753372489417984e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 9.078138431963368e-05, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.00013626606723278202, "train/grad_042_lr1.9e+01_wd1.0e+00": 5.220035822195398e-05, "train/grad_043_lr2.2e+01_wd1.0e+00": 2.6323930831571526e-05, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 1.2289745807647705, "validation/loss_001_lr2.3e-02_wd1.0e+00": 1.2234011888504028, "validation/loss_002_lr2.8e-02_wd1.0e+00": 1.2169638872146606, "validation/loss_003_lr3.3e-02_wd1.0e+00": 1.2131229639053345, "validation/loss_004_lr3.8e-02_wd1.0e+00": 1.2104711532592773, "validation/loss_005_lr4.5e-02_wd1.0e+00": 1.2078509330749512, "validation/loss_006_lr5.3e-02_wd1.0e+00": 1.2055883407592773, "validation/loss_007_lr6.2e-02_wd1.0e+00": 1.2032381296157837, "validation/loss_008_lr7.4e-02_wd1.0e+00": 1.2003251314163208, "validation/loss_009_lr8.7e-02_wd1.0e+00": 1.197710633277893, "validation/loss_010_lr1.0e-01_wd1.0e+00": 1.195043921470642, "validation/loss_011_lr1.2e-01_wd1.0e+00": 1.1919981241226196, "validation/loss_012_lr1.4e-01_wd1.0e+00": 1.1889101266860962, "validation/loss_013_lr1.7e-01_wd1.0e+00": 1.1848493814468384, "validation/loss_014_lr2.0e-01_wd1.0e+00": 1.1821647882461548, "validation/loss_015_lr2.3e-01_wd1.0e+00": 1.1815383434295654, "validation/loss_016_lr2.7e-01_wd1.0e+00": 1.185659646987915, "validation/loss_017_lr3.2e-01_wd1.0e+00": 1.2035335302352905, "validation/loss_018_lr3.8e-01_wd1.0e+00": 1.244257926940918, "validation/loss_019_lr4.4e-01_wd1.0e+00": 1.3115015029907227, "validation/loss_020_lr5.2e-01_wd1.0e+00": 1.426181435585022, "validation/loss_021_lr6.1e-01_wd1.0e+00": 1.5816699266433716, "validation/loss_022_lr7.2e-01_wd1.0e+00": 1.8055428266525269, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.187340259552002, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.8204052448272705, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.4409677982330322, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.78224515914917, "validation/loss_027_lr1.6e+00_wd1.0e+00": 4.132410526275635, "validation/loss_028_lr1.9e+00_wd1.0e+00": 4.519710540771484, "validation/loss_029_lr2.3e+00_wd1.0e+00": 4.690306663513184, "validation/loss_030_lr2.7e+00_wd1.0e+00": 4.53514289855957, "validation/loss_031_lr3.1e+00_wd1.0e+00": 4.544798374176025, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.9952170848846436, "validation/loss_033_lr4.3e+00_wd1.0e+00": 4.260594367980957, "validation/loss_034_lr5.1e+00_wd1.0e+00": 4.060819149017334, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.9292516708374023, "validation/loss_036_lr7.1e+00_wd1.0e+00": 6.229203224182129, "validation/loss_037_lr8.3e+00_wd1.0e+00": 4.579750061035156, "validation/loss_038_lr9.8e+00_wd1.0e+00": 5.4877800941467285, "validation/loss_039_lr1.2e+01_wd1.0e+00": 6.5195417404174805, "validation/loss_040_lr1.4e+01_wd1.0e+00": 7.58634614944458, "validation/loss_041_lr1.6e+01_wd1.0e+00": 6.3049397468566895, "validation/loss_042_lr1.9e+01_wd1.0e+00": 15.159070014953613, "validation/loss_043_lr2.2e+01_wd1.0e+00": 12.233433723449707, "validation/loss_044_lr2.6e+01_wd1.0e+00": 1.3862943649291992, "validation/loss_045_lr3.1e+01_wd1.0e+00": 1.3862943649291992, "validation/loss_046_lr3.6e+01_wd1.0e+00": 1.3862943649291992, "validation/loss_047_lr4.3e+01_wd1.0e+00": 1.3862943649291992, "validation/loss_048_lr5.0e+01_wd1.0e+00": 1.3862943649291992, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.39622641509433965, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.41509433962264153, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.4339622641509434, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.41509433962264153, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.39622641509433965, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.39622641509433965, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.39622641509433965, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.37735849056603776, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.3584905660377358, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.3584905660377358, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.37735849056603776, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.41509433962264153, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.41509433962264153, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.4339622641509434, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.4339622641509434, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.4339622641509434, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.4339622641509434, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.39622641509433965, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.39622641509433965, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.37735849056603776, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.32075471698113206, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.2830188679245283, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.2641509433962264, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.32075471698113206, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.33962264150943394, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.3584905660377358, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.3584905660377358, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.37735849056603776, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.3584905660377358, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.3018867924528302, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.3584905660377358, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.39622641509433965, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.39622641509433965, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.37735849056603776, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.39622641509433965, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.39622641509433965, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.37735849056603776, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.39622641509433965, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.3584905660377358, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.3584905660377358, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.41509433962264153, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.39622641509433965, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.37735849056603776, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.41509433962264153, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.2641509433962264, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.2641509433962264, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.2641509433962264, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.2641509433962264, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.2641509433962264, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.36679536679536684, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.4010057471264368, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.4291219936250362, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.4130909658293026, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.3958737341090282, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.3958737341090282, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.3958737341090282, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.3664378218130754, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.34728843335628656, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.34728843335628656, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.36262537272973705, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.41342364532019704, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.420468509984639, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.436183608058608, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.436183608058608, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.4284422474077647, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.4260369815092454, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.39616402116402116, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.3953856405130768, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.3754180602006689, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.32171122994652407, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.28345959595959597, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.2653416149068323, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.31856514924356005, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.33169278996865204, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.35384615384615387, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.35574074074074075, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.3757559681697613, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.35128205128205126, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.29345878136200715, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.3611111111111111, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.39007122507122505, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.38614420062695926, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.37309116809116805, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.38822751322751325, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.3951465201465202, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.366270283661588, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.397217190016103, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.3594566544566544, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.3536955636955637, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.4076923076923077, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.39653944395323704, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.37609427609427615, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.4171386677838291, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.1044776119402985, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.1044776119402985, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.1044776119402985, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.1044776119402985, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.1044776119402985, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.38621794871794873, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.40705128205128205, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.4278846153846154, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.40865384615384615, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.3907967032967033, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.3907967032967033, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.3907967032967033, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.36996336996337, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.3507326007326007, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.3507326007326007, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.3685897435897436, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.41025641025641024, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.41025641025641024, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.4294871794871795, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.4294871794871795, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.42811355311355315, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.42811355311355315, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.39400183150183155, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.39400183150183155, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.37477106227106227, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.3211996336996337, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.2841117216117216, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.26625457875457875, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.31684981684981683, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.3347069597069597, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.35096153846153844, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.3539377289377289, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.37179487179487175, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.35096153846153844, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.2960164835164835, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.35393772893772896, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.38965201465201466, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.3956043956043956, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.3717948717948718, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.38965201465201466, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.3896520146520146, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.3685897435897436, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.3965201465201465, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.35370879120879123, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.3507326007326007, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.4088827838827839, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.3891941391941392, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.37133699633699635, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.4116300366300366, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.25, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.25, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.25, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.25, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.25, "id_best": 13, "lr_best": 5.1e-05, "wd_best": 0.05, "train/loss_best": 1.0093679809570313, "validation/loss_best": 1.1848493814468384, "validation/acc_best": 0.4339622641509434, "validation/f1_best": 0.436183608058608, "validation/bacc_best": 0.4294871794871795} +{"epoch": 10, "train/lr": 0.00021091808096876188, "train/loss": 0.596526168435812, "train/grad": 0.23532405007630586, "train/loss_000_lr2.0e-02_wd1.0e+00": 1.18337158203125, "train/loss_001_lr2.3e-02_wd1.0e+00": 1.17340576171875, "train/loss_002_lr2.8e-02_wd1.0e+00": 1.16007568359375, "train/loss_003_lr3.3e-02_wd1.0e+00": 1.14961669921875, "train/loss_004_lr3.8e-02_wd1.0e+00": 1.140511474609375, "train/loss_005_lr4.5e-02_wd1.0e+00": 1.12943115234375, "train/loss_006_lr5.3e-02_wd1.0e+00": 1.118272705078125, "train/loss_007_lr6.2e-02_wd1.0e+00": 1.10637451171875, "train/loss_008_lr7.4e-02_wd1.0e+00": 1.0914971923828125, "train/loss_009_lr8.7e-02_wd1.0e+00": 1.075906982421875, "train/loss_010_lr1.0e-01_wd1.0e+00": 1.0604144287109376, "train/loss_011_lr1.2e-01_wd1.0e+00": 1.03718994140625, "train/loss_012_lr1.4e-01_wd1.0e+00": 1.0136590576171876, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.9783319091796875, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.9433198547363282, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.9100837707519531, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.8690017700195313, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.821900863647461, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.7683608245849609, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.7190800857543945, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.6520354461669922, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.5587271595001221, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.3920151388645172, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.18108029380440713, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.04665571436285973, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.013737520277500153, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.0068257865309715275, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.00451009139418602, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.002965656816959381, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0017448605597019196, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0012227109074592591, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.0010034802556037903, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.0007924558222293853, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.0005841697752475739, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.0005577750504016876, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.0004513399302959442, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.535911440849304e-05, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.00019241809844970702, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.0002653510868549347, "train/loss_039_lr1.2e+01_wd1.0e+00": 6.765976548194885e-05, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.0001179252564907074, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.00025641903281211855, "train/loss_042_lr1.9e+01_wd1.0e+00": 5.709096789360046e-05, "train/loss_043_lr2.2e+01_wd1.0e+00": 1.2381225824356079e-05, "train/loss_044_lr2.6e+01_wd1.0e+00": 1.3828125, "train/loss_045_lr3.1e+01_wd1.0e+00": 1.3828125, "train/loss_046_lr3.6e+01_wd1.0e+00": 1.3828125, "train/loss_047_lr4.3e+01_wd1.0e+00": 1.3828125, "train/loss_048_lr5.0e+01_wd1.0e+00": 1.3828125, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.04088811449240893, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.040931932195089754, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.04105016323272139, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.04116323477588594, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.041268910709768535, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.04140292740892619, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.04153742107562721, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.04167160275392234, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.04184150430373847, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.042055760817602275, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.04231702099554241, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.042816174710169436, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.04349349400028586, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.044902137294411656, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.04674456031061709, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.04868802332319319, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.05095889506861567, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.053226414043456315, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.055762742469087245, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.057651056637987495, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.05896754071116447, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.05971710220910609, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.05607277883216739, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.03891403742600232, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.013364449564833195, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.004028760362998583, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0019771490304265173, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0012828260569949634, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0008533902642375323, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0005194036549073644, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0003533991663425695, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.00027635682974505474, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.00021197997772105738, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0001660135600104695, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0001593609125848161, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0001284069492976414, "train/grad_036_lr7.1e+00_wd1.0e+00": 3.120418783481682e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.00011105159661155994, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.00015004738485004056, "train/grad_039_lr1.2e+01_wd1.0e+00": 6.796211662305041e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.00013184131654170984, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.00018929248052472757, "train/grad_042_lr1.9e+01_wd1.0e+00": 8.878076453364708e-05, "train/grad_043_lr2.2e+01_wd1.0e+00": 5.360297303161533e-05, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 1.2256499528884888, "validation/loss_001_lr2.3e-02_wd1.0e+00": 1.220893144607544, "validation/loss_002_lr2.8e-02_wd1.0e+00": 1.2158840894699097, "validation/loss_003_lr3.3e-02_wd1.0e+00": 1.2128612995147705, "validation/loss_004_lr3.8e-02_wd1.0e+00": 1.2107840776443481, "validation/loss_005_lr4.5e-02_wd1.0e+00": 1.2089357376098633, "validation/loss_006_lr5.3e-02_wd1.0e+00": 1.2070273160934448, "validation/loss_007_lr6.2e-02_wd1.0e+00": 1.2052134275436401, "validation/loss_008_lr7.4e-02_wd1.0e+00": 1.2036889791488647, "validation/loss_009_lr8.7e-02_wd1.0e+00": 1.2015734910964966, "validation/loss_010_lr1.0e-01_wd1.0e+00": 1.2002137899398804, "validation/loss_011_lr1.2e-01_wd1.0e+00": 1.1971641778945923, "validation/loss_012_lr1.4e-01_wd1.0e+00": 1.193930745124817, "validation/loss_013_lr1.7e-01_wd1.0e+00": 1.1908845901489258, "validation/loss_014_lr2.0e-01_wd1.0e+00": 1.188498854637146, "validation/loss_015_lr2.3e-01_wd1.0e+00": 1.190540075302124, "validation/loss_016_lr2.7e-01_wd1.0e+00": 1.198757529258728, "validation/loss_017_lr3.2e-01_wd1.0e+00": 1.2220473289489746, "validation/loss_018_lr3.8e-01_wd1.0e+00": 1.271375298500061, "validation/loss_019_lr4.4e-01_wd1.0e+00": 1.3371254205703735, "validation/loss_020_lr5.2e-01_wd1.0e+00": 1.4320062398910522, "validation/loss_021_lr6.1e-01_wd1.0e+00": 1.6156489849090576, "validation/loss_022_lr7.2e-01_wd1.0e+00": 1.9346891641616821, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.4954209327697754, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.197748899459839, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.7317471504211426, "validation/loss_026_lr1.4e+00_wd1.0e+00": 4.007523059844971, "validation/loss_027_lr1.6e+00_wd1.0e+00": 4.325471878051758, "validation/loss_028_lr1.9e+00_wd1.0e+00": 4.698231220245361, "validation/loss_029_lr2.3e+00_wd1.0e+00": 4.827276229858398, "validation/loss_030_lr2.7e+00_wd1.0e+00": 4.6288743019104, "validation/loss_031_lr3.1e+00_wd1.0e+00": 4.631222248077393, "validation/loss_032_lr3.7e+00_wd1.0e+00": 4.045937538146973, "validation/loss_033_lr4.3e+00_wd1.0e+00": 4.292227745056152, "validation/loss_034_lr5.1e+00_wd1.0e+00": 4.099981784820557, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.9254150390625, "validation/loss_036_lr7.1e+00_wd1.0e+00": 5.928092002868652, "validation/loss_037_lr8.3e+00_wd1.0e+00": 4.419421672821045, "validation/loss_038_lr9.8e+00_wd1.0e+00": 5.279391288757324, "validation/loss_039_lr1.2e+01_wd1.0e+00": 6.034610271453857, "validation/loss_040_lr1.4e+01_wd1.0e+00": 7.035788536071777, "validation/loss_041_lr1.6e+01_wd1.0e+00": 5.778907775878906, "validation/loss_042_lr1.9e+01_wd1.0e+00": 13.440513610839844, "validation/loss_043_lr2.2e+01_wd1.0e+00": 10.330018997192383, "validation/loss_044_lr2.6e+01_wd1.0e+00": 1.3862943649291992, "validation/loss_045_lr3.1e+01_wd1.0e+00": 1.3862943649291992, "validation/loss_046_lr3.6e+01_wd1.0e+00": 1.3862943649291992, "validation/loss_047_lr4.3e+01_wd1.0e+00": 1.3862943649291992, "validation/loss_048_lr5.0e+01_wd1.0e+00": 1.3862943649291992, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.41509433962264153, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.41509433962264153, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.41509433962264153, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.41509433962264153, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.39622641509433965, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.39622641509433965, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.39622641509433965, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.37735849056603776, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.37735849056603776, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.37735849056603776, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.39622641509433965, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.4339622641509434, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.4339622641509434, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.41509433962264153, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.4339622641509434, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.39622641509433965, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.39622641509433965, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.39622641509433965, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.37735849056603776, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.41509433962264153, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.39622641509433965, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.4339622641509434, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.3584905660377358, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.39622641509433965, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.3584905660377358, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.37735849056603776, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.3584905660377358, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.37735849056603776, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.33962264150943394, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.3018867924528302, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.3584905660377358, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.39622641509433965, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.41509433962264153, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.37735849056603776, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.41509433962264153, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.39622641509433965, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.37735849056603776, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.39622641509433965, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.3584905660377358, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.3584905660377358, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.39622641509433965, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.39622641509433965, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.3584905660377358, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.39622641509433965, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.2641509433962264, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.2641509433962264, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.2641509433962264, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.2641509433962264, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.2641509433962264, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.4029201615408512, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.4010057471264368, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.4119047619047619, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.4119047619047619, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.3958737341090282, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.3958737341090282, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.3958737341090282, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.3653980119497361, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.3653980119497361, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.37689710387078806, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.39735449735449735, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.43766233766233764, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.43766233766233764, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.4187675070028011, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.43148880105401843, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.40006193484454355, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.3978673178673179, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.3889558717144924, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.36544369608885735, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.39742234961923506, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.37242234961923504, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.416958041958042, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.35128205128205126, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.3956596360628619, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.3456782668573547, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.36841604631927216, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.35574074074074075, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.37637362637362637, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.3351282051282051, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.29345878136200715, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.3611111111111111, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.39007122507122505, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.4093553223388306, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.37309116809116805, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.40235437836637233, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.38508287065258584, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.3682224821655107, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.397217190016103, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.3596866096866097, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.3536955636955637, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.3941520467836257, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.3952340252340252, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.3612387612387612, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.39469795632137844, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.1044776119402985, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.1044776119402985, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.1044776119402985, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.1044776119402985, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.1044776119402985, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.40705128205128205, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.40705128205128205, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.4100274725274725, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.4100274725274725, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.3907967032967033, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.3907967032967033, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.3907967032967033, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.36996336996337, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.36996336996337, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.3715659340659341, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.3923992673992674, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.4294871794871795, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.4294871794871795, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.4116300366300366, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.4308608058608059, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.39537545787545786, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.39537545787545786, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.3926282051282051, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.3733974358974359, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.4091117216117216, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.3898809523809524, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.4269688644688645, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.35096153846153844, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.3894230769230769, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.35256410256410253, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.36881868131868134, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.3539377289377289, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.37179487179487175, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.3331043956043956, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.2960164835164835, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.35393772893772896, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.38965201465201466, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.41483516483516486, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.3717948717948718, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.4075091575091575, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.3866758241758242, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.3685897435897436, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.3965201465201465, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.35370879120879123, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.3507326007326007, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.3910256410256411, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.3891941391941392, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.35347985347985345, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.3907967032967033, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.25, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.25, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.25, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.25, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.25, "id_best": 14, "lr_best": 5.9999999999999995e-05, "wd_best": 0.05, "train/loss_best": 0.9433198547363282, "validation/loss_best": 1.188498854637146, "validation/acc_best": 0.4339622641509434, "validation/f1_best": 0.43148880105401843, "validation/bacc_best": 0.4308608058608059} +{"epoch": 11, "train/lr": 0.00018113997589164516, "train/loss": 0.5737865523993969, "train/grad": 0.22846669513732196, "train/loss_000_lr2.0e-02_wd1.0e+00": 1.174033203125, "train/loss_001_lr2.3e-02_wd1.0e+00": 1.16405517578125, "train/loss_002_lr2.8e-02_wd1.0e+00": 1.15036865234375, "train/loss_003_lr3.3e-02_wd1.0e+00": 1.1392431640625, "train/loss_004_lr3.8e-02_wd1.0e+00": 1.128974609375, "train/loss_005_lr4.5e-02_wd1.0e+00": 1.11616455078125, "train/loss_006_lr5.3e-02_wd1.0e+00": 1.10222412109375, "train/loss_007_lr6.2e-02_wd1.0e+00": 1.087647705078125, "train/loss_008_lr7.4e-02_wd1.0e+00": 1.068526611328125, "train/loss_009_lr8.7e-02_wd1.0e+00": 1.048690185546875, "train/loss_010_lr1.0e-01_wd1.0e+00": 1.0290625, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.99965087890625, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.9703677368164062, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.9276043701171875, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.88828369140625, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.8533479309082032, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.8117582702636719, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.7643978881835938, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.7094442749023437, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.6556705093383789, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.570356216430664, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.4419436502456665, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.26027956292033194, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.08933763712644577, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.025297417044639586, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.008581023514270782, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.0044945600628852845, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0031139352917671204, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0021503522992134096, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.001375068873167038, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0009531791508197784, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.0007743264734745025, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.0006070256233215332, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.0004750299453735352, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.00047942027449607847, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.0003690731525421143, "train/loss_036_lr7.1e+00_wd1.0e+00": 4.699245095252991e-05, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.00022537142038345337, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.0002710425853729248, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.00012786343693733216, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.00019127070903778075, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.0003718063235282898, "train/loss_042_lr1.9e+01_wd1.0e+00": 8.564397692680359e-05, "train/loss_043_lr2.2e+01_wd1.0e+00": 5.561783909797668e-05, "train/loss_044_lr2.6e+01_wd1.0e+00": 1.3828125, "train/loss_045_lr3.1e+01_wd1.0e+00": 1.3828125, "train/loss_046_lr3.6e+01_wd1.0e+00": 1.3828125, "train/loss_047_lr4.3e+01_wd1.0e+00": 1.3828125, "train/loss_048_lr5.0e+01_wd1.0e+00": 1.3828125, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.041260076588951054, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.04127522115129977, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.0413366987882182, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.04141675690654665, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.04148932634852827, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.04160139711108059, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.041719650598242876, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.041857811356894675, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.04207614361308515, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.04234000554773956, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.04266648330260068, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.04330352309625596, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.04414036924485117, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.04579418024048209, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.04776830167509615, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.049660906894132495, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.051851122472435236, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.054163344595581295, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.05609904515556991, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.05687562722712755, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.05650989606976509, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.0538394985627383, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.04423898668028414, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.022421857824083416, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.007740501707885415, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0026368344441289084, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0013929829763947054, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0009696245889062994, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0006668459696811624, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.00041874474933138115, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0002917305213122745, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.000232983665264328, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.00018036214820313034, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.00014651938352471916, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.00014021013017554652, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.00011711957971783704, "train/grad_036_lr7.1e+00_wd1.0e+00": 3.413072166537745e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.00011238142064030398, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.00014987164381182082, "train/grad_039_lr1.2e+01_wd1.0e+00": 8.935078984336543e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.00014916634030782917, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.00020604290939218116, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.00017012176341752377, "train/grad_043_lr2.2e+01_wd1.0e+00": 7.30328003394623e-05, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 1.223659634590149, "validation/loss_001_lr2.3e-02_wd1.0e+00": 1.2196338176727295, "validation/loss_002_lr2.8e-02_wd1.0e+00": 1.2155234813690186, "validation/loss_003_lr3.3e-02_wd1.0e+00": 1.21287202835083, "validation/loss_004_lr3.8e-02_wd1.0e+00": 1.2110776901245117, "validation/loss_005_lr4.5e-02_wd1.0e+00": 1.2094378471374512, "validation/loss_006_lr5.3e-02_wd1.0e+00": 1.2078471183776855, "validation/loss_007_lr6.2e-02_wd1.0e+00": 1.2061219215393066, "validation/loss_008_lr7.4e-02_wd1.0e+00": 1.2035775184631348, "validation/loss_009_lr8.7e-02_wd1.0e+00": 1.2009326219558716, "validation/loss_010_lr1.0e-01_wd1.0e+00": 1.1983686685562134, "validation/loss_011_lr1.2e-01_wd1.0e+00": 1.1946532726287842, "validation/loss_012_lr1.4e-01_wd1.0e+00": 1.1917425394058228, "validation/loss_013_lr1.7e-01_wd1.0e+00": 1.1900209188461304, "validation/loss_014_lr2.0e-01_wd1.0e+00": 1.1918394565582275, "validation/loss_015_lr2.3e-01_wd1.0e+00": 1.1987422704696655, "validation/loss_016_lr2.7e-01_wd1.0e+00": 1.2131534814834595, "validation/loss_017_lr3.2e-01_wd1.0e+00": 1.2385810613632202, "validation/loss_018_lr3.8e-01_wd1.0e+00": 1.2943925857543945, "validation/loss_019_lr4.4e-01_wd1.0e+00": 1.3790574073791504, "validation/loss_020_lr5.2e-01_wd1.0e+00": 1.533066987991333, "validation/loss_021_lr6.1e-01_wd1.0e+00": 1.8215993642807007, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.209324598312378, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.8536174297332764, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.4710705280303955, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.9191396236419678, "validation/loss_026_lr1.4e+00_wd1.0e+00": 4.170004367828369, "validation/loss_027_lr1.6e+00_wd1.0e+00": 4.467044830322266, "validation/loss_028_lr1.9e+00_wd1.0e+00": 4.829994201660156, "validation/loss_029_lr2.3e+00_wd1.0e+00": 4.919163703918457, "validation/loss_030_lr2.7e+00_wd1.0e+00": 4.699409008026123, "validation/loss_031_lr3.1e+00_wd1.0e+00": 4.694725036621094, "validation/loss_032_lr3.7e+00_wd1.0e+00": 4.0877604484558105, "validation/loss_033_lr4.3e+00_wd1.0e+00": 4.317549228668213, "validation/loss_034_lr5.1e+00_wd1.0e+00": 4.130107879638672, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.923551559448242, "validation/loss_036_lr7.1e+00_wd1.0e+00": 5.693509578704834, "validation/loss_037_lr8.3e+00_wd1.0e+00": 4.299254894256592, "validation/loss_038_lr9.8e+00_wd1.0e+00": 5.1240315437316895, "validation/loss_039_lr1.2e+01_wd1.0e+00": 5.674437522888184, "validation/loss_040_lr1.4e+01_wd1.0e+00": 6.63901424407959, "validation/loss_041_lr1.6e+01_wd1.0e+00": 5.418557167053223, "validation/loss_042_lr1.9e+01_wd1.0e+00": 12.13737964630127, "validation/loss_043_lr2.2e+01_wd1.0e+00": 8.937588691711426, "validation/loss_044_lr2.6e+01_wd1.0e+00": 1.3862943649291992, "validation/loss_045_lr3.1e+01_wd1.0e+00": 1.3862943649291992, "validation/loss_046_lr3.6e+01_wd1.0e+00": 1.3862943649291992, "validation/loss_047_lr4.3e+01_wd1.0e+00": 1.3862943649291992, "validation/loss_048_lr5.0e+01_wd1.0e+00": 1.3862943649291992, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.4339622641509434, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.41509433962264153, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.41509433962264153, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.39622641509433965, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.39622641509433965, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.39622641509433965, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.39622641509433965, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.39622641509433965, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.41509433962264153, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.41509433962264153, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.4339622641509434, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.4528301886792453, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.4339622641509434, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.41509433962264153, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.41509433962264153, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.4339622641509434, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.41509433962264153, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.41509433962264153, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.39622641509433965, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.4339622641509434, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.39622641509433965, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.33962264150943394, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.3584905660377358, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.39622641509433965, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.3584905660377358, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.3584905660377358, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.3584905660377358, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.37735849056603776, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.33962264150943394, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.3018867924528302, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.33962264150943394, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.39622641509433965, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.41509433962264153, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.37735849056603776, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.39622641509433965, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.39622641509433965, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.39622641509433965, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.41509433962264153, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.3584905660377358, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.3584905660377358, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.39622641509433965, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.39622641509433965, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.3584905660377358, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.37735849056603776, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.2641509433962264, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.2641509433962264, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.2641509433962264, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.2641509433962264, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.2641509433962264, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.4181110102843315, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.4029201615408512, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.4010057471264368, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.3850140056022409, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.3850140056022409, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.3850140056022409, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.38246884960880906, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.38246884960880906, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.39821428571428574, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.3970588235294118, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.42674104124408385, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.45490196078431366, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.43766233766233764, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.4187675070028011, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.4159944914420618, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.4342683496961196, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.4166666666666667, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.414021164021164, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.3955017683465959, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.41922590292155515, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.3706896551724138, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.30837789661319076, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.349025974025974, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.3860930735930736, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.35384615384615387, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.35384615384615387, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.35574074074074075, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.37802604802604806, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.3351282051282051, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.29638888888888887, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.3389944984772571, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.39007122507122505, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.4093553223388306, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.37309116809116805, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.38822751322751325, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.38508287065258584, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.39185960591133007, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.4161439665471923, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.3596866096866097, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.3536955636955637, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.3941520467836257, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.3952340252340252, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.36600066600066594, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.3815686125468734, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.1044776119402985, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.1044776119402985, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.1044776119402985, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.1044776119402985, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.1044776119402985, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.4262820512820513, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.40705128205128205, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.40705128205128205, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.38919413919413914, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.38919413919413914, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.38919413919413914, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.38919413919413914, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.38919413919413914, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.40705128205128205, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.40705128205128205, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.4278846153846154, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.4487179487179487, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.4294871794871795, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.4116300366300366, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.413003663003663, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.43246336996337, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.41460622710622713, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.4132326007326007, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.3926282051282052, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.4269688644688645, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.38988095238095244, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.33630952380952384, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.35096153846153844, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.38965201465201466, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.35096153846153844, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.35096153846153844, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.3539377289377289, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.37179487179487175, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.3331043956043956, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.2960164835164835, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.3347069597069597, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.38965201465201466, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.41483516483516486, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.3717948717948718, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.38965201465201466, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.3866758241758242, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.3894230769230769, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.41437728937728935, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.35370879120879123, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.3507326007326007, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.3910256410256411, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.3891941391941392, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.35347985347985345, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.37293956043956045, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.25, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.25, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.25, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.25, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.25, "id_best": 11, "lr_best": 3.5999999999999994e-05, "wd_best": 0.05, "train/loss_best": 0.99965087890625, "validation/loss_best": 1.1946532726287842, "validation/acc_best": 0.4528301886792453, "validation/f1_best": 0.45490196078431366, "validation/bacc_best": 0.4487179487179487} +{"epoch": 12, "train/lr": 0.0001499999999999999, "train/loss": 0.5727721746265888, "train/grad": 0.2333801344409585, "train/loss_000_lr2.0e-02_wd1.0e+00": 1.1867138671875, "train/loss_001_lr2.3e-02_wd1.0e+00": 1.17875244140625, "train/loss_002_lr2.8e-02_wd1.0e+00": 1.167481689453125, "train/loss_003_lr3.3e-02_wd1.0e+00": 1.158006591796875, "train/loss_004_lr3.8e-02_wd1.0e+00": 1.149249267578125, "train/loss_005_lr4.5e-02_wd1.0e+00": 1.1378271484375, "train/loss_006_lr5.3e-02_wd1.0e+00": 1.1248876953125, "train/loss_007_lr6.2e-02_wd1.0e+00": 1.1107147216796875, "train/loss_008_lr7.4e-02_wd1.0e+00": 1.091983642578125, "train/loss_009_lr8.7e-02_wd1.0e+00": 1.0722015380859375, "train/loss_010_lr1.0e-01_wd1.0e+00": 1.0521249389648437, "train/loss_011_lr1.2e-01_wd1.0e+00": 1.021798095703125, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.9911700439453125, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.9457461547851562, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.9021363830566407, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.8617475128173828, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.8115702819824219, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.7510766220092774, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.6808397483825683, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.6135839080810547, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.5119474601745605, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.3612259531021118, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.17563437357544898, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.05421411916613579, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.017592244148254395, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.0068509714305400845, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.003819114863872528, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0027247564494609832, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.00196232944726944, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0012019897997379303, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0008366420865058899, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.000718979686498642, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.0005847926437854766, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.00047127589583396913, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.0004565174877643585, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.00035808369517326355, "train/loss_036_lr7.1e+00_wd1.0e+00": 5.2148997783660887e-05, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.00024079009890556335, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.00032514378428459166, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.00013767436146736145, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.00021477729082107543, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.0003718951344490051, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.00011531561613082885, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.00010491937398910523, "train/loss_044_lr2.6e+01_wd1.0e+00": 1.3828125, "train/loss_045_lr3.1e+01_wd1.0e+00": 1.3828125, "train/loss_046_lr3.6e+01_wd1.0e+00": 1.3828125, "train/loss_047_lr4.3e+01_wd1.0e+00": 1.3828125, "train/loss_048_lr5.0e+01_wd1.0e+00": 1.3828125, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.04127041061408818, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.04132727461401373, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.04142715340480208, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.04152612095233053, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.041609969050623474, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.04171931759919971, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.041836512773297724, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.04197164850309491, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.04218558131251484, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.04247988634742796, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.04285766096320003, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.0436557688890025, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.04475738647393882, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.04697134766262025, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.0494243979640305, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.05158364187926054, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.05401637695729732, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.056792756747454404, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.05963010374456644, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.06126676185056567, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.06143522215075791, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.056320645464584235, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.038026550197973845, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.014420022636186332, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.00512024097610265, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0019795232807518913, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.001100256294303108, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0007934030704200268, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0005695546828792431, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0003650423080398468, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0002504292402591091, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.00020466442358156201, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.00016312848612869856, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0001351354698454088, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0001324307274990133, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0001065910034958506, "train/grad_036_lr7.1e+00_wd1.0e+00": 3.6493648418343125e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.00010980642712183908, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.00014740604358848942, "train/grad_039_lr1.2e+01_wd1.0e+00": 9.805969601302422e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0001545369390532869, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0002112546808029947, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0001876411527595321, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0001252968864226811, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 1.2209339141845703, "validation/loss_001_lr2.3e-02_wd1.0e+00": 1.2167936563491821, "validation/loss_002_lr2.8e-02_wd1.0e+00": 1.2127982378005981, "validation/loss_003_lr3.3e-02_wd1.0e+00": 1.2102794647216797, "validation/loss_004_lr3.8e-02_wd1.0e+00": 1.2086416482925415, "validation/loss_005_lr4.5e-02_wd1.0e+00": 1.2066503763198853, "validation/loss_006_lr5.3e-02_wd1.0e+00": 1.2047755718231201, "validation/loss_007_lr6.2e-02_wd1.0e+00": 1.2030235528945923, "validation/loss_008_lr7.4e-02_wd1.0e+00": 1.200319528579712, "validation/loss_009_lr8.7e-02_wd1.0e+00": 1.1978487968444824, "validation/loss_010_lr1.0e-01_wd1.0e+00": 1.1954623460769653, "validation/loss_011_lr1.2e-01_wd1.0e+00": 1.1919941902160645, "validation/loss_012_lr1.4e-01_wd1.0e+00": 1.189819097518921, "validation/loss_013_lr1.7e-01_wd1.0e+00": 1.18991219997406, "validation/loss_014_lr2.0e-01_wd1.0e+00": 1.1953668594360352, "validation/loss_015_lr2.3e-01_wd1.0e+00": 1.2053605318069458, "validation/loss_016_lr2.7e-01_wd1.0e+00": 1.2233130931854248, "validation/loss_017_lr3.2e-01_wd1.0e+00": 1.259328842163086, "validation/loss_018_lr3.8e-01_wd1.0e+00": 1.3336584568023682, "validation/loss_019_lr4.4e-01_wd1.0e+00": 1.4428073167800903, "validation/loss_020_lr5.2e-01_wd1.0e+00": 1.6285878419876099, "validation/loss_021_lr6.1e-01_wd1.0e+00": 1.9936689138412476, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.4236226081848145, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.040837526321411, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.634786367416382, "validation/loss_025_lr1.2e+00_wd1.0e+00": 4.034846305847168, "validation/loss_026_lr1.4e+00_wd1.0e+00": 4.288390159606934, "validation/loss_027_lr1.6e+00_wd1.0e+00": 4.576268196105957, "validation/loss_028_lr1.9e+00_wd1.0e+00": 4.929813385009766, "validation/loss_029_lr2.3e+00_wd1.0e+00": 4.999684810638428, "validation/loss_030_lr2.7e+00_wd1.0e+00": 4.762056827545166, "validation/loss_031_lr3.1e+00_wd1.0e+00": 4.751289367675781, "validation/loss_032_lr3.7e+00_wd1.0e+00": 4.130313396453857, "validation/loss_033_lr4.3e+00_wd1.0e+00": 4.3427815437316895, "validation/loss_034_lr5.1e+00_wd1.0e+00": 4.162619590759277, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.9306082725524902, "validation/loss_036_lr7.1e+00_wd1.0e+00": 5.501430988311768, "validation/loss_037_lr8.3e+00_wd1.0e+00": 4.201469421386719, "validation/loss_038_lr9.8e+00_wd1.0e+00": 5.017598628997803, "validation/loss_039_lr1.2e+01_wd1.0e+00": 5.40122127532959, "validation/loss_040_lr1.4e+01_wd1.0e+00": 6.3445820808410645, "validation/loss_041_lr1.6e+01_wd1.0e+00": 5.172171115875244, "validation/loss_042_lr1.9e+01_wd1.0e+00": 11.171793937683105, "validation/loss_043_lr2.2e+01_wd1.0e+00": 8.107429504394531, "validation/loss_044_lr2.6e+01_wd1.0e+00": 1.3862943649291992, "validation/loss_045_lr3.1e+01_wd1.0e+00": 1.3862943649291992, "validation/loss_046_lr3.6e+01_wd1.0e+00": 1.3862943649291992, "validation/loss_047_lr4.3e+01_wd1.0e+00": 1.3862943649291992, "validation/loss_048_lr5.0e+01_wd1.0e+00": 1.3862943649291992, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.41509433962264153, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.4339622641509434, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.39622641509433965, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.39622641509433965, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.39622641509433965, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.39622641509433965, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.37735849056603776, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.37735849056603776, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.3584905660377358, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.41509433962264153, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.4339622641509434, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.4339622641509434, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.4339622641509434, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.4339622641509434, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.4339622641509434, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.49056603773584906, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.4716981132075472, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.49056603773584906, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.4716981132075472, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.4528301886792453, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.39622641509433965, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.3584905660377358, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.37735849056603776, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.3584905660377358, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.3584905660377358, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.3584905660377358, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.3584905660377358, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.37735849056603776, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.33962264150943394, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.2830188679245283, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.33962264150943394, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.39622641509433965, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.41509433962264153, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.37735849056603776, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.41509433962264153, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.39622641509433965, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.41509433962264153, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.41509433962264153, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.3584905660377358, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.3584905660377358, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.3584905660377358, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.39622641509433965, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.37735849056603776, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.3584905660377358, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.2641509433962264, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.2641509433962264, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.2641509433962264, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.2641509433962264, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.2641509433962264, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.4010057471264368, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.4291219936250362, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.3958737341090282, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.3958737341090282, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.3958737341090282, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.3958737341090282, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.3653980119497361, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.3653980119497361, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.34857918263090676, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.4144316730523627, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.43105567032152126, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.43570075757575755, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.43570075757575755, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.43148880105401843, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.4284044057516696, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.48510971786833856, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.46797360248447206, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.4882079409603953, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.4706004140786749, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.45470212657712655, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.40925595238095236, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.36721639180409793, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.3720878136200717, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.3529032258064516, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.35384615384615387, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.35384615384615387, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.35752234993614307, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.37802604802604806, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.3351282051282051, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.28240126731506043, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.3389944984772571, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.39007122507122505, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.4093553223388306, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.37309116809116805, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.40235437836637233, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.38508287065258584, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.411564039408867, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.4161439665471923, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.3596866096866097, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.35583231583231584, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.34857142857142853, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.3952340252340252, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.38643904482614166, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.3647250639386189, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.1044776119402985, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.1044776119402985, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.1044776119402985, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.1044776119402985, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.1044776119402985, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.40705128205128205, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.4278846153846154, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.3907967032967033, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.3907967032967033, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.3907967032967033, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.3907967032967033, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.36996336996337, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.36996336996337, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.3507326007326007, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.41025641025641024, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.4294871794871795, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.4294871794871795, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.4294871794871795, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.4308608058608059, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.4294871794871795, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.48740842490842495, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.46955128205128205, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.48740842490842495, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.4681776556776557, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.4473443223443223, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.391025641025641, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.3553113553113553, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.36881868131868134, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.35096153846153844, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.35096153846153844, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.35096153846153844, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.3539377289377289, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.37179487179487175, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.3331043956043956, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.27815934065934067, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.3347069597069597, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.38965201465201466, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.41483516483516486, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.3717948717948718, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.4075091575091575, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.3866758241758242, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.40865384615384615, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.41437728937728935, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.35370879120879123, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.3507326007326007, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.35256410256410253, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.3891941391941392, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.3743131868131868, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.3550824175824176, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.25, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.25, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.25, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.25, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.25, "id_best": 15, "lr_best": 6.9e-05, "wd_best": 0.05, "train/loss_best": 0.8617475128173828, "validation/loss_best": 1.2053605318069458, "validation/acc_best": 0.49056603773584906, "validation/f1_best": 0.48510971786833856, "validation/bacc_best": 0.48740842490842495} +{"epoch": 13, "train/lr": 0.00011886002410835478, "train/loss": 0.5641235457360745, "train/grad": 0.23595026522874832, "train/loss_000_lr2.0e-02_wd1.0e+00": 1.170341796875, "train/loss_001_lr2.3e-02_wd1.0e+00": 1.161494140625, "train/loss_002_lr2.8e-02_wd1.0e+00": 1.149775390625, "train/loss_003_lr3.3e-02_wd1.0e+00": 1.1397607421875, "train/loss_004_lr3.8e-02_wd1.0e+00": 1.13091064453125, "train/loss_005_lr4.5e-02_wd1.0e+00": 1.119542236328125, "train/loss_006_lr5.3e-02_wd1.0e+00": 1.107327880859375, "train/loss_007_lr6.2e-02_wd1.0e+00": 1.0936944580078125, "train/loss_008_lr7.4e-02_wd1.0e+00": 1.0763604736328125, "train/loss_009_lr8.7e-02_wd1.0e+00": 1.057454833984375, "train/loss_010_lr1.0e-01_wd1.0e+00": 1.038958740234375, "train/loss_011_lr1.2e-01_wd1.0e+00": 1.0102304077148438, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.9810977172851563, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.9375445556640625, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.8967857360839844, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.8578819274902344, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.8072727966308594, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.7438188552856445, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.6685208892822265, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.5930209636688233, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.47896671533584595, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.31071691274642943, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.13003151804208757, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.03622182339429855, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.012584446519613266, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.005195570588111878, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.002975254058837891, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.002186969369649887, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0016430415213108062, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0010563479363918304, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0007230046391487121, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.0006373216211795807, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.000524800568819046, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.0004422511160373688, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.0004084396362304687, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.00032377392053604124, "train/loss_036_lr7.1e+00_wd1.0e+00": 5.018964409828186e-05, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.00022862866520881653, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.0002853374183177948, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.00014922857284545898, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.000225515216588974, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.00040261030197143556, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.00012436792254447938, "train/loss_043_lr2.2e+01_wd1.0e+00": 9.241297841072082e-05, "train/loss_044_lr2.6e+01_wd1.0e+00": 1.3828125, "train/loss_045_lr3.1e+01_wd1.0e+00": 1.3828125, "train/loss_046_lr3.6e+01_wd1.0e+00": 1.3828125, "train/loss_047_lr4.3e+01_wd1.0e+00": 1.3828125, "train/loss_048_lr5.0e+01_wd1.0e+00": 1.3828125, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.04228800158482045, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.04233417857903987, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.042444986384361984, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.04254527005366981, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.042656247802078724, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.04279931275174022, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.04296959561761469, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.04318873056676239, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.043513913550414146, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.043954994156956674, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.04450003397185356, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.04554971157107502, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.046927391113713385, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.049599577826447784, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.05230669299140572, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.05452323439531028, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.056748866951093074, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.058626330867409704, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.0600847546197474, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.060689445324242114, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.059666509013623, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.05125660628080368, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.029876013319008052, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.01027113715885207, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.003833916446892545, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.001593826120661106, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0009143406371003948, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0006701383723702747, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0004930267835879931, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.00032252188706479503, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.00022711074358085172, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.00018613850006659048, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.00014885383136061135, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.00012620188843357028, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.00012020007276078104, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.00010019082685175818, "train/grad_036_lr7.1e+00_wd1.0e+00": 3.964336097453725e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.00010822706582302999, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0001446595067909584, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.00010263575252935198, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.00015551137528518666, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.00020167379624581373, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.00019401297742038318, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.00017474448520879538, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 1.2195417881011963, "validation/loss_001_lr2.3e-02_wd1.0e+00": 1.2156999111175537, "validation/loss_002_lr2.8e-02_wd1.0e+00": 1.2121394872665405, "validation/loss_003_lr3.3e-02_wd1.0e+00": 1.2099233865737915, "validation/loss_004_lr3.8e-02_wd1.0e+00": 1.208469271659851, "validation/loss_005_lr4.5e-02_wd1.0e+00": 1.2067643404006958, "validation/loss_006_lr5.3e-02_wd1.0e+00": 1.2053412199020386, "validation/loss_007_lr6.2e-02_wd1.0e+00": 1.20339834690094, "validation/loss_008_lr7.4e-02_wd1.0e+00": 1.201066493988037, "validation/loss_009_lr8.7e-02_wd1.0e+00": 1.19868004322052, "validation/loss_010_lr1.0e-01_wd1.0e+00": 1.195990800857544, "validation/loss_011_lr1.2e-01_wd1.0e+00": 1.191784143447876, "validation/loss_012_lr1.4e-01_wd1.0e+00": 1.1882398128509521, "validation/loss_013_lr1.7e-01_wd1.0e+00": 1.1870843172073364, "validation/loss_014_lr2.0e-01_wd1.0e+00": 1.1919115781784058, "validation/loss_015_lr2.3e-01_wd1.0e+00": 1.2007005214691162, "validation/loss_016_lr2.7e-01_wd1.0e+00": 1.220391869544983, "validation/loss_017_lr3.2e-01_wd1.0e+00": 1.262808084487915, "validation/loss_018_lr3.8e-01_wd1.0e+00": 1.3471399545669556, "validation/loss_019_lr4.4e-01_wd1.0e+00": 1.4617488384246826, "validation/loss_020_lr5.2e-01_wd1.0e+00": 1.6714445352554321, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.054903507232666, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.54317307472229, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.2080492973327637, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.7742083072662354, "validation/loss_025_lr1.2e+00_wd1.0e+00": 4.136528968811035, "validation/loss_026_lr1.4e+00_wd1.0e+00": 4.372392654418945, "validation/loss_027_lr1.6e+00_wd1.0e+00": 4.653733730316162, "validation/loss_028_lr1.9e+00_wd1.0e+00": 5.0078043937683105, "validation/loss_029_lr2.3e+00_wd1.0e+00": 5.059703350067139, "validation/loss_030_lr2.7e+00_wd1.0e+00": 4.8074870109558105, "validation/loss_031_lr3.1e+00_wd1.0e+00": 4.7908711433410645, "validation/loss_032_lr3.7e+00_wd1.0e+00": 4.158547878265381, "validation/loss_033_lr4.3e+00_wd1.0e+00": 4.36391019821167, "validation/loss_034_lr5.1e+00_wd1.0e+00": 4.188883304595947, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.939896583557129, "validation/loss_036_lr7.1e+00_wd1.0e+00": 5.360350608825684, "validation/loss_037_lr8.3e+00_wd1.0e+00": 4.133441925048828, "validation/loss_038_lr9.8e+00_wd1.0e+00": 4.936776638031006, "validation/loss_039_lr1.2e+01_wd1.0e+00": 5.219818115234375, "validation/loss_040_lr1.4e+01_wd1.0e+00": 6.141756534576416, "validation/loss_041_lr1.6e+01_wd1.0e+00": 5.016107082366943, "validation/loss_042_lr1.9e+01_wd1.0e+00": 10.482951164245605, "validation/loss_043_lr2.2e+01_wd1.0e+00": 7.524596214294434, "validation/loss_044_lr2.6e+01_wd1.0e+00": 1.3862943649291992, "validation/loss_045_lr3.1e+01_wd1.0e+00": 1.3862943649291992, "validation/loss_046_lr3.6e+01_wd1.0e+00": 1.3862943649291992, "validation/loss_047_lr4.3e+01_wd1.0e+00": 1.3862943649291992, "validation/loss_048_lr5.0e+01_wd1.0e+00": 1.3862943649291992, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.41509433962264153, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.4339622641509434, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.39622641509433965, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.39622641509433965, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.39622641509433965, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.37735849056603776, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.37735849056603776, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.37735849056603776, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.3584905660377358, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.4528301886792453, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.4339622641509434, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.4339622641509434, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.41509433962264153, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.4339622641509434, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.4528301886792453, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.4339622641509434, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.41509433962264153, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.4716981132075472, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.4339622641509434, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.4528301886792453, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.4339622641509434, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.3584905660377358, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.37735849056603776, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.3584905660377358, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.33962264150943394, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.3584905660377358, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.37735849056603776, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.37735849056603776, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.33962264150943394, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.2830188679245283, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.33962264150943394, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.39622641509433965, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.41509433962264153, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.37735849056603776, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.41509433962264153, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.39622641509433965, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.41509433962264153, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.4339622641509434, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.3584905660377358, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.3584905660377358, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.3584905660377358, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.39622641509433965, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.39622641509433965, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.3584905660377358, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.2641509433962264, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.2641509433962264, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.2641509433962264, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.2641509433962264, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.2641509433962264, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.4010057471264368, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.4291219936250362, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.3958737341090282, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.3958737341090282, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.3958737341090282, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.3664378218130754, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.3653980119497361, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.3653980119497361, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.34857918263090676, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.4489224137931035, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.43105567032152126, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.43766233766233764, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.4187675070028011, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.4269719978720317, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.4386183008202644, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.4191377813397449, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.4060320267216819, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.4657794057794058, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.4163751457604531, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.4246305418719212, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.41236263736263734, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.3521889400921659, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.366010101010101, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.3360416666666667, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.3323717948717949, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.35384615384615387, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.37243589743589745, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.37802604802604806, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.3351282051282051, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.28240126731506043, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.3389944984772571, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.39007122507122505, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.4093553223388306, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.37309116809116805, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.40235437836637233, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.38508287065258584, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.411564039408867, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.43580870279146144, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.3596866096866097, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.35583231583231584, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.34857142857142853, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.3921428571428571, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.404520202020202, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.3647250639386189, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.1044776119402985, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.1044776119402985, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.1044776119402985, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.1044776119402985, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.1044776119402985, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.40705128205128205, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.4278846153846154, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.3907967032967033, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.3907967032967033, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.3907967032967033, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.36996336996337, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.36996336996337, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.36996336996337, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.3507326007326007, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.4487179487179487, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.4294871794871795, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.4294871794871795, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.4116300366300366, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.4294871794871795, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.4473443223443223, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.42811355311355315, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.41185897435897434, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.46543040293040294, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.4269688644688645, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.4448260073260073, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.4269688644688645, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.35393772893772896, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.36881868131868134, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.34958791208791207, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.3317307692307692, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.35096153846153844, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.37179487179487175, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.37179487179487175, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.3331043956043956, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.27815934065934067, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.3347069597069597, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.38965201465201466, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.41483516483516486, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.3717948717948718, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.4075091575091575, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.3866758241758242, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.40865384615384615, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.4352106227106227, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.35370879120879123, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.3507326007326007, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.35256410256410253, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.3891941391941392, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.3951465201465202, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.3550824175824176, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.25, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.25, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.25, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.25, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.25, "id_best": 17, "lr_best": 9.599999999999999e-05, "wd_best": 0.05, "train/loss_best": 0.7438188552856445, "validation/loss_best": 1.262808084487915, "validation/acc_best": 0.4716981132075472, "validation/f1_best": 0.4657794057794058, "validation/bacc_best": 0.46543040293040294} +{"epoch": 14, "train/lr": 8.9081919031238e-05, "train/loss": 0.5488327318429946, "train/grad": 0.24228377129882575, "train/loss_000_lr2.0e-02_wd1.0e+00": 1.15999267578125, "train/loss_001_lr2.3e-02_wd1.0e+00": 1.15077392578125, "train/loss_002_lr2.8e-02_wd1.0e+00": 1.137890625, "train/loss_003_lr3.3e-02_wd1.0e+00": 1.126893310546875, "train/loss_004_lr3.8e-02_wd1.0e+00": 1.116439208984375, "train/loss_005_lr4.5e-02_wd1.0e+00": 1.103016357421875, "train/loss_006_lr5.3e-02_wd1.0e+00": 1.0883837890625, "train/loss_007_lr6.2e-02_wd1.0e+00": 1.0722882080078124, "train/loss_008_lr7.4e-02_wd1.0e+00": 1.0513836669921874, "train/loss_009_lr8.7e-02_wd1.0e+00": 1.029232177734375, "train/loss_010_lr1.0e-01_wd1.0e+00": 1.0073477172851562, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.9740347290039062, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.9410922241210937, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.8943476867675781, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.8513885498046875, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.8111576843261719, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.7594532012939453, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.695790901184082, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.6219866561889649, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.5468438243865967, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.42889817714691164, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.2613182008266449, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.09674566507339477, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.026618653237819673, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.009806681722402573, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.004320111274719238, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.0025906676054000856, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0019501125812530517, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0013970781862735749, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0009136776626110077, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.000673733651638031, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.0005591732263565064, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.00047814741730690003, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.00040714651346206664, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.00039000913500785827, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.00033733949065208437, "train/loss_036_lr7.1e+00_wd1.0e+00": 4.2200237512588504e-05, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.00024010121822357178, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.000309007465839386, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.00017322733998298645, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.00021011918783187867, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.0003620140254497528, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.00011156827211380005, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.00015207365155220031, "train/loss_044_lr2.6e+01_wd1.0e+00": 1.3828125, "train/loss_045_lr3.1e+01_wd1.0e+00": 1.3828125, "train/loss_046_lr3.6e+01_wd1.0e+00": 1.3828125, "train/loss_047_lr4.3e+01_wd1.0e+00": 1.3828125, "train/loss_048_lr5.0e+01_wd1.0e+00": 1.3828125, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.0435119440080598, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.04355735854711384, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.0436475794063881, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.04373810202814639, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.043821026580408214, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.04394267323426902, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.04409292405936867, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.044287111749872564, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.04457966849673539, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.04500148068182171, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.04551698652561754, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.046577204503118995, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.04802005421370268, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.05089367947541177, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.05382350076921284, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.0562946568056941, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.058891987428069115, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.06136899028904736, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.06349157884716988, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.06427683436311782, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.061644267234951255, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.04945575837511569, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.024621478943154217, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.00800926381838508, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.003133516808738932, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.00136080713593401, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0008101351246295963, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0006020980354514904, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0004380052131455159, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.00029133152434951626, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0002088802350772312, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.00017231250880286097, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.00013722421614147605, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.00011786655191826867, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.00011143932433697046, "train/grad_035_lr6.0e+00_wd1.0e+00": 9.365223952045198e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 4.1567846449197535e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.00010532063699429272, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.00013711090765809785, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.00010910831400224197, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0001464930813904175, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.00019271883668807278, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.00017759355683925684, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.00018889519578475954, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 1.218430995941162, "validation/loss_001_lr2.3e-02_wd1.0e+00": 1.21519935131073, "validation/loss_002_lr2.8e-02_wd1.0e+00": 1.2118011713027954, "validation/loss_003_lr3.3e-02_wd1.0e+00": 1.20953369140625, "validation/loss_004_lr3.8e-02_wd1.0e+00": 1.207947015762329, "validation/loss_005_lr4.5e-02_wd1.0e+00": 1.2060233354568481, "validation/loss_006_lr5.3e-02_wd1.0e+00": 1.2041438817977905, "validation/loss_007_lr6.2e-02_wd1.0e+00": 1.2018194198608398, "validation/loss_008_lr7.4e-02_wd1.0e+00": 1.1989336013793945, "validation/loss_009_lr8.7e-02_wd1.0e+00": 1.195742130279541, "validation/loss_010_lr1.0e-01_wd1.0e+00": 1.1925948858261108, "validation/loss_011_lr1.2e-01_wd1.0e+00": 1.1885842084884644, "validation/loss_012_lr1.4e-01_wd1.0e+00": 1.1857110261917114, "validation/loss_013_lr1.7e-01_wd1.0e+00": 1.1870129108428955, "validation/loss_014_lr2.0e-01_wd1.0e+00": 1.1962693929672241, "validation/loss_015_lr2.3e-01_wd1.0e+00": 1.210745096206665, "validation/loss_016_lr2.7e-01_wd1.0e+00": 1.2386724948883057, "validation/loss_017_lr3.2e-01_wd1.0e+00": 1.2933076620101929, "validation/loss_018_lr3.8e-01_wd1.0e+00": 1.3877822160720825, "validation/loss_019_lr4.4e-01_wd1.0e+00": 1.5067332983016968, "validation/loss_020_lr5.2e-01_wd1.0e+00": 1.7290339469909668, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.1104371547698975, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.626119613647461, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.3224363327026367, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.8647546768188477, "validation/loss_025_lr1.2e+00_wd1.0e+00": 4.210816383361816, "validation/loss_026_lr1.4e+00_wd1.0e+00": 4.441460609436035, "validation/loss_027_lr1.6e+00_wd1.0e+00": 4.7155866622924805, "validation/loss_028_lr1.9e+00_wd1.0e+00": 5.068614482879639, "validation/loss_029_lr2.3e+00_wd1.0e+00": 5.106107711791992, "validation/loss_030_lr2.7e+00_wd1.0e+00": 4.845272064208984, "validation/loss_031_lr3.1e+00_wd1.0e+00": 4.823955059051514, "validation/loss_032_lr3.7e+00_wd1.0e+00": 4.177517890930176, "validation/loss_033_lr4.3e+00_wd1.0e+00": 4.37957763671875, "validation/loss_034_lr5.1e+00_wd1.0e+00": 4.214094161987305, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.947828531265259, "validation/loss_036_lr7.1e+00_wd1.0e+00": 5.255397796630859, "validation/loss_037_lr8.3e+00_wd1.0e+00": 4.083314418792725, "validation/loss_038_lr9.8e+00_wd1.0e+00": 4.8886308670043945, "validation/loss_039_lr1.2e+01_wd1.0e+00": 5.095513820648193, "validation/loss_040_lr1.4e+01_wd1.0e+00": 6.008533954620361, "validation/loss_041_lr1.6e+01_wd1.0e+00": 4.913815975189209, "validation/loss_042_lr1.9e+01_wd1.0e+00": 10.012540817260742, "validation/loss_043_lr2.2e+01_wd1.0e+00": 7.078979015350342, "validation/loss_044_lr2.6e+01_wd1.0e+00": 1.3862943649291992, "validation/loss_045_lr3.1e+01_wd1.0e+00": 1.3862943649291992, "validation/loss_046_lr3.6e+01_wd1.0e+00": 1.3862943649291992, "validation/loss_047_lr4.3e+01_wd1.0e+00": 1.3862943649291992, "validation/loss_048_lr5.0e+01_wd1.0e+00": 1.3862943649291992, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.41509433962264153, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.41509433962264153, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.4339622641509434, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.39622641509433965, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.39622641509433965, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.37735849056603776, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.37735849056603776, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.3584905660377358, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.37735849056603776, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.41509433962264153, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.4339622641509434, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.4339622641509434, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.4339622641509434, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.4339622641509434, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.4339622641509434, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.41509433962264153, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.41509433962264153, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.4339622641509434, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.37735849056603776, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.37735849056603776, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.3584905660377358, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.32075471698113206, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.3584905660377358, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.3584905660377358, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.3584905660377358, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.3584905660377358, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.3584905660377358, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.37735849056603776, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.33962264150943394, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.2830188679245283, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.32075471698113206, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.39622641509433965, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.41509433962264153, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.37735849056603776, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.41509433962264153, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.39622641509433965, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.41509433962264153, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.4339622641509434, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.3584905660377358, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.3584905660377358, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.3584905660377358, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.37735849056603776, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.37735849056603776, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.33962264150943394, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.2641509433962264, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.2641509433962264, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.2641509433962264, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.2641509433962264, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.2641509433962264, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.4010057471264368, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.4010057471264368, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.4291219936250362, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.3958737341090282, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.3958737341090282, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.3664378218130754, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.3653980119497361, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.34857918263090676, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.3639161220043573, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.4144316730523627, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.4340773809523809, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.43766233766233764, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.43766233766233764, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.4284044057516696, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.43481182795698925, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.41782464846980977, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.4166666666666667, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.43681230965713724, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.3841568669759413, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.37703804347826086, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.3566378467657667, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.3281861053600184, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.3510819475055099, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.3474686454849498, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.35384615384615387, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.35384615384615387, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.35692307692307695, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.37802604802604806, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.3351282051282051, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.28240126731506043, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.31761273209549074, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.39007122507122505, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.4093553223388306, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.37309116809116805, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.40235437836637233, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.38508287065258584, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.411564039408867, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.4350925925925926, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.3596866096866097, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.35583231583231584, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.34857142857142853, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.37605413105413105, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.38417832167832167, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.3463917306052856, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.1044776119402985, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.1044776119402985, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.1044776119402985, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.1044776119402985, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.1044776119402985, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.40705128205128205, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.40705128205128205, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.4278846153846154, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.3907967032967033, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.3907967032967033, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.36996336996337, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.36996336996337, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.3507326007326007, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.3685897435897436, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.41025641025641024, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.4294871794871795, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.4294871794871795, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.4294871794871795, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.4294871794871795, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.43246336996337, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.41460622710622713, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.41460622710622713, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.43246336996337, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.37614468864468864, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.37477106227106227, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.3569139194139194, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.3182234432234432, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.35096153846153844, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.35096153846153844, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.35096153846153844, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.35096153846153844, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.3539377289377289, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.37179487179487175, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.3331043956043956, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.27815934065934067, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.31387362637362637, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.38965201465201466, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.41483516483516486, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.3717948717948718, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.4075091575091575, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.3866758241758242, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.40865384615384615, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.4352106227106227, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.35370879120879123, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.3507326007326007, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.35256410256410253, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.36996336996337, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.3759157509157509, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.33722527472527475, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.25, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.25, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.25, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.25, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.25, "id_best": 37, "lr_best": 0.00249, "wd_best": 0.05, "train/loss_best": 0.00024010121822357178, "validation/loss_best": 4.083314418792725, "validation/acc_best": 0.4339622641509434, "validation/f1_best": 0.4350925925925926, "validation/bacc_best": 0.4352106227106227} +{"epoch": 15, "train/lr": 6.196799573888289e-05, "train/loss": 0.5355851715803146, "train/grad": 0.2300844145938754, "train/loss_000_lr2.0e-02_wd1.0e+00": 1.1405712890625, "train/loss_001_lr2.3e-02_wd1.0e+00": 1.130133056640625, "train/loss_002_lr2.8e-02_wd1.0e+00": 1.115806884765625, "train/loss_003_lr3.3e-02_wd1.0e+00": 1.1036181640625, "train/loss_004_lr3.8e-02_wd1.0e+00": 1.0925634765625, "train/loss_005_lr4.5e-02_wd1.0e+00": 1.078486328125, "train/loss_006_lr5.3e-02_wd1.0e+00": 1.0632470703125, "train/loss_007_lr6.2e-02_wd1.0e+00": 1.047091064453125, "train/loss_008_lr7.4e-02_wd1.0e+00": 1.0259112548828124, "train/loss_009_lr8.7e-02_wd1.0e+00": 1.0038031005859376, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.9819287109375, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.9486355590820312, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.9154638671875, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.8680754089355469, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.8234264373779296, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.7812167358398437, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.727007942199707, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.6609856033325195, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.5868645095825196, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.5109726619720459, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.3871962761878967, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.22032776921987535, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.0731031608581543, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.021047351509332658, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.008190201669931412, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.003731572926044464, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.002253599911928177, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0017033785581588746, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0012406063079833983, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0007995259761810303, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0005938537418842315, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.000506511926651001, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.00043889120221138003, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.0003746363520622253, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.0003590381145477295, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.00028686001896858213, "train/loss_036_lr7.1e+00_wd1.0e+00": 5.756333470344544e-05, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.0002093443274497986, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.0002846451103687286, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.00016645550727844237, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.0002050440013408661, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.00040571600198745727, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.00014212802052497863, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.00017823636531829834, "train/loss_044_lr2.6e+01_wd1.0e+00": 1.3828125, "train/loss_045_lr3.1e+01_wd1.0e+00": 1.3828125, "train/loss_046_lr3.6e+01_wd1.0e+00": 1.3828125, "train/loss_047_lr4.3e+01_wd1.0e+00": 1.3828125, "train/loss_048_lr5.0e+01_wd1.0e+00": 1.3828125, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.041624326640740034, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.0417112263571471, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.041878972467966374, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.04202034183777869, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.042150954552926126, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.04232266124337911, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.04251021272037178, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.04273706267122179, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.04307045854628086, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.043535168808884916, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.044087914880365134, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.04520824851933867, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.04670774484053254, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.04952642358839512, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.05221076604910195, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.05436513983644545, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.056615068800747397, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.05874125425703824, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.06035225524567068, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.060233782045543194, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.056135009052231906, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.04308640878181905, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.019665223679039626, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.006552498108940199, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0026352442690404133, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.001189180503715761, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0007146845197712536, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.000534379552336759, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.00039438920161046555, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0002668169318349101, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.00019413469490245916, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.000159425992933393, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.00012814541416446444, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0001111639388363983, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.00010655567408321076, "train/grad_035_lr6.0e+00_wd1.0e+00": 8.770551941779559e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 4.4311845260409656e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.00010455869162342423, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0001368999192254705, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.00010808299260133935, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.00014843586690858502, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.00018602608904075168, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0001886646650771434, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.00020160016251168143, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 1.217912197113037, "validation/loss_001_lr2.3e-02_wd1.0e+00": 1.2148106098175049, "validation/loss_002_lr2.8e-02_wd1.0e+00": 1.2115744352340698, "validation/loss_003_lr3.3e-02_wd1.0e+00": 1.209564208984375, "validation/loss_004_lr3.8e-02_wd1.0e+00": 1.2080916166305542, "validation/loss_005_lr4.5e-02_wd1.0e+00": 1.2061183452606201, "validation/loss_006_lr5.3e-02_wd1.0e+00": 1.2043447494506836, "validation/loss_007_lr6.2e-02_wd1.0e+00": 1.2021671533584595, "validation/loss_008_lr7.4e-02_wd1.0e+00": 1.1997425556182861, "validation/loss_009_lr8.7e-02_wd1.0e+00": 1.1967724561691284, "validation/loss_010_lr1.0e-01_wd1.0e+00": 1.1936668157577515, "validation/loss_011_lr1.2e-01_wd1.0e+00": 1.189307451248169, "validation/loss_012_lr1.4e-01_wd1.0e+00": 1.186099648475647, "validation/loss_013_lr1.7e-01_wd1.0e+00": 1.1865520477294922, "validation/loss_014_lr2.0e-01_wd1.0e+00": 1.1928179264068604, "validation/loss_015_lr2.3e-01_wd1.0e+00": 1.2044018507003784, "validation/loss_016_lr2.7e-01_wd1.0e+00": 1.2282449007034302, "validation/loss_017_lr3.2e-01_wd1.0e+00": 1.2821681499481201, "validation/loss_018_lr3.8e-01_wd1.0e+00": 1.3841397762298584, "validation/loss_019_lr4.4e-01_wd1.0e+00": 1.5179450511932373, "validation/loss_020_lr5.2e-01_wd1.0e+00": 1.7701185941696167, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.175692319869995, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.6975014209747314, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.385012149810791, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.9302213191986084, "validation/loss_025_lr1.2e+00_wd1.0e+00": 4.270231246948242, "validation/loss_026_lr1.4e+00_wd1.0e+00": 4.494338512420654, "validation/loss_027_lr1.6e+00_wd1.0e+00": 4.763044357299805, "validation/loss_028_lr1.9e+00_wd1.0e+00": 5.110135078430176, "validation/loss_029_lr2.3e+00_wd1.0e+00": 5.145925998687744, "validation/loss_030_lr2.7e+00_wd1.0e+00": 4.8810319900512695, "validation/loss_031_lr3.1e+00_wd1.0e+00": 4.85056734085083, "validation/loss_032_lr3.7e+00_wd1.0e+00": 4.20094108581543, "validation/loss_033_lr4.3e+00_wd1.0e+00": 4.398617267608643, "validation/loss_034_lr5.1e+00_wd1.0e+00": 4.232673645019531, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.9612748622894287, "validation/loss_036_lr7.1e+00_wd1.0e+00": 5.1858038902282715, "validation/loss_037_lr8.3e+00_wd1.0e+00": 4.058244705200195, "validation/loss_038_lr9.8e+00_wd1.0e+00": 4.860773086547852, "validation/loss_039_lr1.2e+01_wd1.0e+00": 5.012998104095459, "validation/loss_040_lr1.4e+01_wd1.0e+00": 5.918623447418213, "validation/loss_041_lr1.6e+01_wd1.0e+00": 4.854380130767822, "validation/loss_042_lr1.9e+01_wd1.0e+00": 9.686164855957031, "validation/loss_043_lr2.2e+01_wd1.0e+00": 6.825984001159668, "validation/loss_044_lr2.6e+01_wd1.0e+00": 1.3862943649291992, "validation/loss_045_lr3.1e+01_wd1.0e+00": 1.3862943649291992, "validation/loss_046_lr3.6e+01_wd1.0e+00": 1.3862943649291992, "validation/loss_047_lr4.3e+01_wd1.0e+00": 1.3862943649291992, "validation/loss_048_lr5.0e+01_wd1.0e+00": 1.3862943649291992, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.41509433962264153, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.4339622641509434, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.39622641509433965, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.39622641509433965, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.39622641509433965, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.37735849056603776, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.37735849056603776, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.3584905660377358, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.37735849056603776, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.4528301886792453, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.4339622641509434, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.4339622641509434, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.4339622641509434, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.4528301886792453, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.4339622641509434, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.4339622641509434, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.4528301886792453, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.4716981132075472, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.4339622641509434, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.41509433962264153, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.3584905660377358, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.3584905660377358, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.37735849056603776, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.33962264150943394, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.3584905660377358, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.3584905660377358, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.3584905660377358, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.37735849056603776, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.33962264150943394, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.2830188679245283, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.32075471698113206, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.39622641509433965, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.41509433962264153, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.37735849056603776, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.41509433962264153, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.39622641509433965, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.41509433962264153, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.4339622641509434, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.3584905660377358, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.3584905660377358, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.3584905660377358, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.33962264150943394, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.41509433962264153, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.33962264150943394, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.2641509433962264, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.2641509433962264, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.2641509433962264, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.2641509433962264, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.2641509433962264, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.4010057471264368, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.4291219936250362, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.3958737341090282, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.3958737341090282, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.3958737341090282, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.3664378218130754, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.3653980119497361, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.34857918263090676, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.3639161220043573, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.4489224137931035, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.43766233766233764, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.436183608058608, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.43766233766233764, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.4468703148425787, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.43333333333333335, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.43333333333333335, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.45210622710622705, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.4693732193732194, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.42802583750859613, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.40832810867293623, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.34939861447575327, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.3541104447776112, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.3680660744896369, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.32173190235690236, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.35384615384615387, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.35384615384615387, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.35692307692307695, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.37802604802604806, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.3351282051282051, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.28240126731506043, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.31761273209549074, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.39007122507122505, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.4093553223388306, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.37309116809116805, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.40235437836637233, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.38508287065258584, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.411564039408867, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.4350925925925926, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.3596866096866097, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.35583231583231584, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.34857142857142853, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.3351282051282051, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.42143603678929764, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.3463917306052856, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.1044776119402985, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.1044776119402985, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.1044776119402985, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.1044776119402985, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.1044776119402985, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.40705128205128205, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.4278846153846154, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.3907967032967033, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.3907967032967033, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.3907967032967033, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.36996336996337, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.36996336996337, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.3507326007326007, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.3685897435897436, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.4487179487179487, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.4294871794871795, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.4294871794871795, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.4294871794871795, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.4473443223443223, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.43246336996337, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.43246336996337, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.4503205128205129, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.4668040293040293, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.4283424908424909, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.41048534798534797, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.35554029304029305, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.35393772893772896, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.36881868131868134, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.3317307692307692, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.35096153846153844, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.35096153846153844, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.3539377289377289, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.37179487179487175, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.3331043956043956, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.27815934065934067, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.31387362637362637, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.38965201465201466, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.41483516483516486, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.3717948717948718, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.4075091575091575, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.3866758241758242, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.40865384615384615, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.4352106227106227, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.35370879120879123, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.3507326007326007, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.35256410256410253, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.3315018315018315, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.41460622710622713, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.33722527472527475, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.25, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.25, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.25, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.25, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.25, "id_best": 17, "lr_best": 9.599999999999999e-05, "wd_best": 0.05, "train/loss_best": 0.6609856033325195, "validation/loss_best": 1.2821681499481201, "validation/acc_best": 0.4716981132075472, "validation/f1_best": 0.4693732193732194, "validation/bacc_best": 0.4668040293040293} +{"epoch": 16, "train/lr": 3.870405029380728e-05, "train/loss": 0.5315809631347657, "train/grad": 0.2209262714534998, "train/loss_000_lr2.0e-02_wd1.0e+00": 1.1279638671875, "train/loss_001_lr2.3e-02_wd1.0e+00": 1.117410888671875, "train/loss_002_lr2.8e-02_wd1.0e+00": 1.103253173828125, "train/loss_003_lr3.3e-02_wd1.0e+00": 1.091514892578125, "train/loss_004_lr3.8e-02_wd1.0e+00": 1.080947265625, "train/loss_005_lr4.5e-02_wd1.0e+00": 1.06755859375, "train/loss_006_lr5.3e-02_wd1.0e+00": 1.053572998046875, "train/loss_007_lr6.2e-02_wd1.0e+00": 1.038341064453125, "train/loss_008_lr7.4e-02_wd1.0e+00": 1.018739013671875, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.9979913330078125, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.977103271484375, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.9456427001953125, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.9137420654296875, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.8674089050292969, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.8240094757080079, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.7822554779052734, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.7270193862915039, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.6574541854858399, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.5774758338928223, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.49640908241271975, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.3687227034568787, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.19678863227367402, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.06161019831895828, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.01917622298002243, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.007859740406274796, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.003626253753900528, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.0021473567187786104, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0015940448641777038, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0011950437724590301, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0007964260876178741, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0005851274728775024, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.0004939071834087372, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.0004062727093696594, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.00034404143691062927, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.0003434222936630249, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.00028651997447013853, "train/loss_036_lr7.1e+00_wd1.0e+00": 6.706476211547852e-05, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.0002176983654499054, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.0002917516231536865, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.00018573090434074403, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.00021622985601425172, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.0003490877151489258, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.0001132519543170929, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.00017501085996627809, "train/loss_044_lr2.6e+01_wd1.0e+00": 1.3828125, "train/loss_045_lr3.1e+01_wd1.0e+00": 1.3828125, "train/loss_046_lr3.6e+01_wd1.0e+00": 1.3828125, "train/loss_047_lr4.3e+01_wd1.0e+00": 1.3828125, "train/loss_048_lr5.0e+01_wd1.0e+00": 1.3828125, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.040922054438851774, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.041002655695192514, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.04115899051073939, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.04129420918412507, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.04140615299809724, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.041562945349141955, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.04172750086057931, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.04192653654608876, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.04223281549289823, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.04263698147144169, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.04313598153647035, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.044175311783328654, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.045572512736544016, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.04823604442179203, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.05067690704017878, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.05256304981186986, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.05438168914057315, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.055977370059117675, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.056870814645662904, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.056228228565305474, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.05193394139409065, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.038866876396350565, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.016769064168911427, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.005670447876909747, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0023289137810934336, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0010685368831036613, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0006664963861112483, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0005086005242628744, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.00037275872404279653, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.00025247449259040877, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.00018283083467395044, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.00015048756406031317, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.00012350934237474577, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.00010618845926728682, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.00010384408040408743, "train/grad_035_lr6.0e+00_wd1.0e+00": 8.425320127571468e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 4.289751483725013e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.00010164444679503504, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.00012700892464636126, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.00010509834783533733, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.000136078040418397, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.00017927246319231926, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.00017731523726769116, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0002149402038589443, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 1.2177698612213135, "validation/loss_001_lr2.3e-02_wd1.0e+00": 1.214648723602295, "validation/loss_002_lr2.8e-02_wd1.0e+00": 1.2116525173187256, "validation/loss_003_lr3.3e-02_wd1.0e+00": 1.2094781398773193, "validation/loss_004_lr3.8e-02_wd1.0e+00": 1.2078717947006226, "validation/loss_005_lr4.5e-02_wd1.0e+00": 1.2061814069747925, "validation/loss_006_lr5.3e-02_wd1.0e+00": 1.2042630910873413, "validation/loss_007_lr6.2e-02_wd1.0e+00": 1.2020139694213867, "validation/loss_008_lr7.4e-02_wd1.0e+00": 1.1993420124053955, "validation/loss_009_lr8.7e-02_wd1.0e+00": 1.1964898109436035, "validation/loss_010_lr1.0e-01_wd1.0e+00": 1.193526029586792, "validation/loss_011_lr1.2e-01_wd1.0e+00": 1.189300298690796, "validation/loss_012_lr1.4e-01_wd1.0e+00": 1.1867181062698364, "validation/loss_013_lr1.7e-01_wd1.0e+00": 1.1885737180709839, "validation/loss_014_lr2.0e-01_wd1.0e+00": 1.1972144842147827, "validation/loss_015_lr2.3e-01_wd1.0e+00": 1.2100054025650024, "validation/loss_016_lr2.7e-01_wd1.0e+00": 1.2358976602554321, "validation/loss_017_lr3.2e-01_wd1.0e+00": 1.2900242805480957, "validation/loss_018_lr3.8e-01_wd1.0e+00": 1.3898606300354004, "validation/loss_019_lr4.4e-01_wd1.0e+00": 1.5232676267623901, "validation/loss_020_lr5.2e-01_wd1.0e+00": 1.7828049659729004, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.2015888690948486, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.7475168704986572, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.4346768856048584, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.9732282161712646, "validation/loss_025_lr1.2e+00_wd1.0e+00": 4.302282333374023, "validation/loss_026_lr1.4e+00_wd1.0e+00": 4.525391578674316, "validation/loss_027_lr1.6e+00_wd1.0e+00": 4.792639255523682, "validation/loss_028_lr1.9e+00_wd1.0e+00": 5.148810386657715, "validation/loss_029_lr2.3e+00_wd1.0e+00": 5.166893005371094, "validation/loss_030_lr2.7e+00_wd1.0e+00": 4.89757776260376, "validation/loss_031_lr3.1e+00_wd1.0e+00": 4.868563175201416, "validation/loss_032_lr3.7e+00_wd1.0e+00": 4.212784290313721, "validation/loss_033_lr4.3e+00_wd1.0e+00": 4.409961700439453, "validation/loss_034_lr5.1e+00_wd1.0e+00": 4.246552467346191, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.96317458152771, "validation/loss_036_lr7.1e+00_wd1.0e+00": 5.139144420623779, "validation/loss_037_lr8.3e+00_wd1.0e+00": 4.036421298980713, "validation/loss_038_lr9.8e+00_wd1.0e+00": 4.850610256195068, "validation/loss_039_lr1.2e+01_wd1.0e+00": 4.966352939605713, "validation/loss_040_lr1.4e+01_wd1.0e+00": 5.8779168128967285, "validation/loss_041_lr1.6e+01_wd1.0e+00": 4.8203582763671875, "validation/loss_042_lr1.9e+01_wd1.0e+00": 9.496941566467285, "validation/loss_043_lr2.2e+01_wd1.0e+00": 6.675727844238281, "validation/loss_044_lr2.6e+01_wd1.0e+00": 1.3862943649291992, "validation/loss_045_lr3.1e+01_wd1.0e+00": 1.3862943649291992, "validation/loss_046_lr3.6e+01_wd1.0e+00": 1.3862943649291992, "validation/loss_047_lr4.3e+01_wd1.0e+00": 1.3862943649291992, "validation/loss_048_lr5.0e+01_wd1.0e+00": 1.3862943649291992, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.41509433962264153, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.41509433962264153, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.39622641509433965, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.39622641509433965, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.39622641509433965, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.37735849056603776, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.37735849056603776, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.3584905660377358, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.37735849056603776, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.4339622641509434, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.4339622641509434, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.4339622641509434, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.4339622641509434, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.4339622641509434, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.4339622641509434, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.4339622641509434, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.4339622641509434, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.4339622641509434, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.4716981132075472, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.4339622641509434, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.39622641509433965, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.33962264150943394, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.39622641509433965, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.33962264150943394, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.3584905660377358, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.3584905660377358, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.3584905660377358, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.37735849056603776, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.33962264150943394, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.2830188679245283, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.32075471698113206, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.39622641509433965, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.39622641509433965, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.37735849056603776, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.39622641509433965, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.39622641509433965, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.41509433962264153, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.4339622641509434, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.3584905660377358, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.3584905660377358, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.33962264150943394, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.33962264150943394, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.41509433962264153, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.33962264150943394, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.2641509433962264, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.2641509433962264, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.2641509433962264, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.2641509433962264, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.2641509433962264, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.4010057471264368, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.4119047619047619, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.3958737341090282, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.3958737341090282, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.3958737341090282, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.3664378218130754, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.3653980119497361, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.34857918263090676, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.3639161220043573, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.43197142123727217, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.43766233766233764, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.43766233766233764, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.43766233766233764, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.4269719978720317, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.43333333333333335, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.43333333333333335, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.43236074270557023, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.4348544973544973, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.4657794057794058, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.42802583750859613, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.39218515742128934, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.3390804597701149, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.3840489804725429, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.32173190235690236, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.35384615384615387, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.35384615384615387, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.3588328912466844, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.37802604802604806, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.3351282051282051, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.28240126731506043, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.31761273209549074, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.39007122507122505, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.3924753694581281, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.37309116809116805, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.37895788757857723, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.38508287065258584, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.411564039408867, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.4350925925925926, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.3596866096866097, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.35583231583231584, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.33343438171024375, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.3351282051282051, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.42143603678929764, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.3463917306052856, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.1044776119402985, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.1044776119402985, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.1044776119402985, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.1044776119402985, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.1044776119402985, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.40705128205128205, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.4100274725274725, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.3907967032967033, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.3907967032967033, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.3907967032967033, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.36996336996337, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.36996336996337, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.3507326007326007, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.3685897435897436, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.4294871794871795, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.4294871794871795, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.4294871794871795, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.4294871794871795, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.4294871794871795, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.43246336996337, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.43246336996337, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.43246336996337, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.4310897435897436, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.46543040293040294, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.4283424908424909, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.3926282051282051, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.33608058608058605, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.38667582417582413, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.3317307692307692, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.35096153846153844, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.35096153846153844, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.3539377289377289, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.37179487179487175, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.3331043956043956, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.27815934065934067, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.31387362637362637, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.38965201465201466, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.39400183150183155, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.3717948717948718, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.3882783882783883, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.3866758241758242, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.40865384615384615, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.4352106227106227, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.35370879120879123, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.3507326007326007, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.33470695970695974, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.3315018315018315, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.41460622710622713, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.33722527472527475, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.25, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.25, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.25, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.25, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.25, "id_best": 18, "lr_best": 0.00011399999999999999, "wd_best": 0.05, "train/loss_best": 0.5774758338928223, "validation/loss_best": 1.3898606300354004, "validation/acc_best": 0.4716981132075472, "validation/f1_best": 0.4657794057794058, "validation/bacc_best": 0.46543040293040294} +{"epoch": 17, "train/lr": 2.030750443206766e-05, "train/loss": 0.5422964328527451, "train/grad": 0.23206818412989377, "train/loss_000_lr2.0e-02_wd1.0e+00": 1.1559326171875, "train/loss_001_lr2.3e-02_wd1.0e+00": 1.1464111328125, "train/loss_002_lr2.8e-02_wd1.0e+00": 1.1335986328125, "train/loss_003_lr3.3e-02_wd1.0e+00": 1.1222265625, "train/loss_004_lr3.8e-02_wd1.0e+00": 1.112025146484375, "train/loss_005_lr4.5e-02_wd1.0e+00": 1.098558349609375, "train/loss_006_lr5.3e-02_wd1.0e+00": 1.0839959716796874, "train/loss_007_lr6.2e-02_wd1.0e+00": 1.0679864501953125, "train/loss_008_lr7.4e-02_wd1.0e+00": 1.0472930908203124, "train/loss_009_lr8.7e-02_wd1.0e+00": 1.0252267456054687, "train/loss_010_lr1.0e-01_wd1.0e+00": 1.0035595703125, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.9700906372070313, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.9368046569824219, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.8885775756835937, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.8437343597412109, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.8009806060791016, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.7459984588623046, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.6774719619750976, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.5986532878875732, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.5161509323120117, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.3787961411476135, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.20313168078660965, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.06254768833518028, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.018364407420158387, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.007308509349822998, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.0034078359603881836, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.0020365084707736967, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0015578651428222656, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0011344237625598907, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0007464216649532318, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0005550074577331543, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.00048316508531570434, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.0004052242636680603, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.0003394491970539093, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.0003211553394794464, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.00028337925672531126, "train/loss_036_lr7.1e+00_wd1.0e+00": 6.593510508537292e-05, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.00024234503507614136, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.00028553083539009096, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.00018716394901275636, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.00021946057677268982, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.00036674633622169495, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.00014923900365829468, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.00025124743580818177, "train/loss_044_lr2.6e+01_wd1.0e+00": 1.3828125, "train/loss_045_lr3.1e+01_wd1.0e+00": 1.3828125, "train/loss_046_lr3.6e+01_wd1.0e+00": 1.3828125, "train/loss_047_lr4.3e+01_wd1.0e+00": 1.3828125, "train/loss_048_lr5.0e+01_wd1.0e+00": 1.3828125, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.04409531779587269, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.0440945384092629, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.044112857114523646, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.044145404305309055, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.04417837306391448, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.044242719956673685, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.04432108069304377, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.04444591965526343, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.044657555436715485, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.04499257139861584, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.04542992966249585, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.04636511392891407, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.047710839482024314, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.05031931851990521, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.052809291305020455, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.0548031507153064, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.056852240357547996, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.058654745658859614, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.05954017502255738, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.058522549057379365, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.05330848595127463, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.03835709784179926, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.016035798457451164, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.005354198104469105, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0022312695634900594, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0010238916279922705, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0006336591736180708, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0004837670044071274, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0003610209927865071, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.00024382772106037009, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.00017621855517063522, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0001465125646609522, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.00011936429245906766, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.00010509983741940231, "train/grad_034_lr5.1e+00_wd1.0e+00": 9.668263850471703e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 8.185457860236056e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 4.398704462118985e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 9.724262069084944e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.00012623228211850802, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.00010221065915629878, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.00013336734787458226, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.00017282027469263993, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0001669596313222843, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.00019871476453204196, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 1.2176498174667358, "validation/loss_001_lr2.3e-02_wd1.0e+00": 1.2145012617111206, "validation/loss_002_lr2.8e-02_wd1.0e+00": 1.2112057209014893, "validation/loss_003_lr3.3e-02_wd1.0e+00": 1.2093790769577026, "validation/loss_004_lr3.8e-02_wd1.0e+00": 1.207543969154358, "validation/loss_005_lr4.5e-02_wd1.0e+00": 1.205878496170044, "validation/loss_006_lr5.3e-02_wd1.0e+00": 1.2039974927902222, "validation/loss_007_lr6.2e-02_wd1.0e+00": 1.2017385959625244, "validation/loss_008_lr7.4e-02_wd1.0e+00": 1.1988170146942139, "validation/loss_009_lr8.7e-02_wd1.0e+00": 1.1961945295333862, "validation/loss_010_lr1.0e-01_wd1.0e+00": 1.193246603012085, "validation/loss_011_lr1.2e-01_wd1.0e+00": 1.1893471479415894, "validation/loss_012_lr1.4e-01_wd1.0e+00": 1.186720848083496, "validation/loss_013_lr1.7e-01_wd1.0e+00": 1.1888048648834229, "validation/loss_014_lr2.0e-01_wd1.0e+00": 1.1978390216827393, "validation/loss_015_lr2.3e-01_wd1.0e+00": 1.211503028869629, "validation/loss_016_lr2.7e-01_wd1.0e+00": 1.2387924194335938, "validation/loss_017_lr3.2e-01_wd1.0e+00": 1.2945202589035034, "validation/loss_018_lr3.8e-01_wd1.0e+00": 1.3977686166763306, "validation/loss_019_lr4.4e-01_wd1.0e+00": 1.5336264371871948, "validation/loss_020_lr5.2e-01_wd1.0e+00": 1.800958275794983, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.2298452854156494, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.7773385047912598, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.4517719745635986, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.9892635345458984, "validation/loss_025_lr1.2e+00_wd1.0e+00": 4.322447776794434, "validation/loss_026_lr1.4e+00_wd1.0e+00": 4.546081066131592, "validation/loss_027_lr1.6e+00_wd1.0e+00": 4.809032440185547, "validation/loss_028_lr1.9e+00_wd1.0e+00": 5.161007404327393, "validation/loss_029_lr2.3e+00_wd1.0e+00": 5.183449745178223, "validation/loss_030_lr2.7e+00_wd1.0e+00": 4.911337852478027, "validation/loss_031_lr3.1e+00_wd1.0e+00": 4.882802486419678, "validation/loss_032_lr3.7e+00_wd1.0e+00": 4.225045204162598, "validation/loss_033_lr4.3e+00_wd1.0e+00": 4.4141340255737305, "validation/loss_034_lr5.1e+00_wd1.0e+00": 4.257580280303955, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.9741499423980713, "validation/loss_036_lr7.1e+00_wd1.0e+00": 5.12260103225708, "validation/loss_037_lr8.3e+00_wd1.0e+00": 4.027979850769043, "validation/loss_038_lr9.8e+00_wd1.0e+00": 4.839044570922852, "validation/loss_039_lr1.2e+01_wd1.0e+00": 4.946818828582764, "validation/loss_040_lr1.4e+01_wd1.0e+00": 5.8531575202941895, "validation/loss_041_lr1.6e+01_wd1.0e+00": 4.805566787719727, "validation/loss_042_lr1.9e+01_wd1.0e+00": 9.400333404541016, "validation/loss_043_lr2.2e+01_wd1.0e+00": 6.5908894538879395, "validation/loss_044_lr2.6e+01_wd1.0e+00": 1.3862943649291992, "validation/loss_045_lr3.1e+01_wd1.0e+00": 1.3862943649291992, "validation/loss_046_lr3.6e+01_wd1.0e+00": 1.3862943649291992, "validation/loss_047_lr4.3e+01_wd1.0e+00": 1.3862943649291992, "validation/loss_048_lr5.0e+01_wd1.0e+00": 1.3862943649291992, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.41509433962264153, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.41509433962264153, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.39622641509433965, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.39622641509433965, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.39622641509433965, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.37735849056603776, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.37735849056603776, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.3584905660377358, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.37735849056603776, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.4528301886792453, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.4339622641509434, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.4339622641509434, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.4339622641509434, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.4339622641509434, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.4339622641509434, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.4339622641509434, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.4339622641509434, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.4339622641509434, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.4528301886792453, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.41509433962264153, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.3584905660377358, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.32075471698113206, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.37735849056603776, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.32075471698113206, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.3584905660377358, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.3584905660377358, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.3584905660377358, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.37735849056603776, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.33962264150943394, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.2830188679245283, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.32075471698113206, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.39622641509433965, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.39622641509433965, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.37735849056603776, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.39622641509433965, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.39622641509433965, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.41509433962264153, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.4339622641509434, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.3584905660377358, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.3584905660377358, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.33962264150943394, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.33962264150943394, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.41509433962264153, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.33962264150943394, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.2641509433962264, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.2641509433962264, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.2641509433962264, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.2641509433962264, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.2641509433962264, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.4010057471264368, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.4119047619047619, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.3958737341090282, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.3958737341090282, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.3958737341090282, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.3664378218130754, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.3653980119497361, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.34857918263090676, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.3639161220043573, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.4489224137931035, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.43766233766233764, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.43766233766233764, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.43766233766233764, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.4284044057516696, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.43333333333333335, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.43333333333333335, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.43236074270557023, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.4348544973544973, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.45085470085470086, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.4128123728123728, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.36008995502248875, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.3281861053600184, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.3680660744896369, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.3081429536127993, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.35384615384615387, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.35384615384615387, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.35692307692307695, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.37802604802604806, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.3351282051282051, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.28240126731506043, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.31761273209549074, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.39007122507122505, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.3924753694581281, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.37309116809116805, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.37895788757857723, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.38508287065258584, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.411564039408867, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.4350925925925926, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.3596866096866097, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.35583231583231584, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.33343438171024375, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.3351282051282051, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.42143603678929764, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.3463917306052856, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.1044776119402985, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.1044776119402985, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.1044776119402985, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.1044776119402985, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.1044776119402985, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.40705128205128205, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.4100274725274725, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.3907967032967033, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.3907967032967033, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.3907967032967033, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.36996336996337, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.36996336996337, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.3507326007326007, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.3685897435897436, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.4487179487179487, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.4294871794871795, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.4294871794871795, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.4294871794871795, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.4294871794871795, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.43246336996337, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.43246336996337, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.43246336996337, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.4310897435897436, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.44757326007326004, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.41048534798534797, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.3569139194139194, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.3182234432234432, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.36881868131868134, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.31387362637362637, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.35096153846153844, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.35096153846153844, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.3539377289377289, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.37179487179487175, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.3331043956043956, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.27815934065934067, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.31387362637362637, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.38965201465201466, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.39400183150183155, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.3717948717948718, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.3882783882783883, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.3866758241758242, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.40865384615384615, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.4352106227106227, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.35370879120879123, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.3507326007326007, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.33470695970695974, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.3315018315018315, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.41460622710622713, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.33722527472527475, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.25, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.25, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.25, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.25, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.25, "id_best": 9, "lr_best": 2.6099999999999997e-05, "wd_best": 0.05, "train/loss_best": 1.0252267456054687, "validation/loss_best": 1.1961945295333862, "validation/acc_best": 0.4528301886792453, "validation/f1_best": 0.4489224137931035, "validation/bacc_best": 0.4487179487179487} +{"epoch": 18, "train/lr": 7.5829098008590064e-06, "train/loss": 0.5349619472026825, "train/grad": 0.2252245043590665, "train/loss_000_lr2.0e-02_wd1.0e+00": 1.1463916015625, "train/loss_001_lr2.3e-02_wd1.0e+00": 1.13702880859375, "train/loss_002_lr2.8e-02_wd1.0e+00": 1.1239306640625, "train/loss_003_lr3.3e-02_wd1.0e+00": 1.11249267578125, "train/loss_004_lr3.8e-02_wd1.0e+00": 1.102017822265625, "train/loss_005_lr4.5e-02_wd1.0e+00": 1.08840576171875, "train/loss_006_lr5.3e-02_wd1.0e+00": 1.0734576416015624, "train/loss_007_lr6.2e-02_wd1.0e+00": 1.0569366455078124, "train/loss_008_lr7.4e-02_wd1.0e+00": 1.0360400390625, "train/loss_009_lr8.7e-02_wd1.0e+00": 1.0138540649414063, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.9920599365234375, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.9588641357421875, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.9258619689941406, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.8768898010253906, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.8297749328613281, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.7845122528076172, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.7255424118041992, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.6525983619689941, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.5687794589996338, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.4824349403381348, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.3465713310241699, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.17805802971124648, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.05197914645075798, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.015994828939437867, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.0065110066533088685, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.0030675579607486723, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.0018793213367462158, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0014387968182563782, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.001079089492559433, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0007429677248001099, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0005406704545021057, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.00045998647809028623, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.0003909049928188324, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.000317351371049881, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.000325789600610733, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.0002671132981777191, "train/loss_036_lr7.1e+00_wd1.0e+00": 7.316485047340393e-05, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.00021295890212059021, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.0003007407486438751, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.00016321003437042237, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.00019460409879684448, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.00036751434206962587, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.0001234753429889679, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.00014003843069076538, "train/loss_044_lr2.6e+01_wd1.0e+00": 1.3828125, "train/loss_045_lr3.1e+01_wd1.0e+00": 1.3828125, "train/loss_046_lr3.6e+01_wd1.0e+00": 1.3828125, "train/loss_047_lr4.3e+01_wd1.0e+00": 1.3828125, "train/loss_048_lr5.0e+01_wd1.0e+00": 1.3828125, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.04237522506155074, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.04243181894998997, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.042539133885875345, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.0426415535248816, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.04272179608233273, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.0428366115456447, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.04297185824252665, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.04312733263708651, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.0433945800550282, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.04377976949792355, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.0442585921799764, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.04528081432916224, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.04669767423532903, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.04937715836800635, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.05186361356638372, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.053792242063209414, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.055717871002852914, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.057295167818665504, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.05787699417211115, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.05656556892208755, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.050795717444270846, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.03593014679383486, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.014823577154893429, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.005074774851091206, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0021620816047652623, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.001005409135686932, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0006149991579877678, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.00046904946211725476, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0003516808589483844, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.00023691183854680276, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0001723750968449167, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.00014204011666151927, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0001157662968398654, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0001036895283323247, "train/grad_034_lr5.1e+00_wd1.0e+00": 9.698103929622448e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 8.121756591208395e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 4.310014124087047e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 9.679422396629888e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.00012284989553791093, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.00010309158419204323, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.00013073088649662168, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.00016914148339310485, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.00016674593649226673, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.00019684677606289115, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 1.2173911333084106, "validation/loss_001_lr2.3e-02_wd1.0e+00": 1.2144358158111572, "validation/loss_002_lr2.8e-02_wd1.0e+00": 1.211141586303711, "validation/loss_003_lr3.3e-02_wd1.0e+00": 1.209062933921814, "validation/loss_004_lr3.8e-02_wd1.0e+00": 1.2075495719909668, "validation/loss_005_lr4.5e-02_wd1.0e+00": 1.205775499343872, "validation/loss_006_lr5.3e-02_wd1.0e+00": 1.2037967443466187, "validation/loss_007_lr6.2e-02_wd1.0e+00": 1.2015794515609741, "validation/loss_008_lr7.4e-02_wd1.0e+00": 1.1988714933395386, "validation/loss_009_lr8.7e-02_wd1.0e+00": 1.1958273649215698, "validation/loss_010_lr1.0e-01_wd1.0e+00": 1.193220853805542, "validation/loss_011_lr1.2e-01_wd1.0e+00": 1.189495325088501, "validation/loss_012_lr1.4e-01_wd1.0e+00": 1.1869440078735352, "validation/loss_013_lr1.7e-01_wd1.0e+00": 1.1888244152069092, "validation/loss_014_lr2.0e-01_wd1.0e+00": 1.1976354122161865, "validation/loss_015_lr2.3e-01_wd1.0e+00": 1.21176016330719, "validation/loss_016_lr2.7e-01_wd1.0e+00": 1.2386279106140137, "validation/loss_017_lr3.2e-01_wd1.0e+00": 1.2947725057601929, "validation/loss_018_lr3.8e-01_wd1.0e+00": 1.399010181427002, "validation/loss_019_lr4.4e-01_wd1.0e+00": 1.5360310077667236, "validation/loss_020_lr5.2e-01_wd1.0e+00": 1.8047571182250977, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.234306573867798, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.783513307571411, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.462857723236084, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.998015880584717, "validation/loss_025_lr1.2e+00_wd1.0e+00": 4.330915451049805, "validation/loss_026_lr1.4e+00_wd1.0e+00": 4.548745632171631, "validation/loss_027_lr1.6e+00_wd1.0e+00": 4.820377826690674, "validation/loss_028_lr1.9e+00_wd1.0e+00": 5.168809413909912, "validation/loss_029_lr2.3e+00_wd1.0e+00": 5.19031286239624, "validation/loss_030_lr2.7e+00_wd1.0e+00": 4.914052486419678, "validation/loss_031_lr3.1e+00_wd1.0e+00": 4.886480331420898, "validation/loss_032_lr3.7e+00_wd1.0e+00": 4.225662708282471, "validation/loss_033_lr4.3e+00_wd1.0e+00": 4.418206691741943, "validation/loss_034_lr5.1e+00_wd1.0e+00": 4.261195182800293, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.978769540786743, "validation/loss_036_lr7.1e+00_wd1.0e+00": 5.118882179260254, "validation/loss_037_lr8.3e+00_wd1.0e+00": 4.028886318206787, "validation/loss_038_lr9.8e+00_wd1.0e+00": 4.838617324829102, "validation/loss_039_lr1.2e+01_wd1.0e+00": 4.939539909362793, "validation/loss_040_lr1.4e+01_wd1.0e+00": 5.8468403816223145, "validation/loss_041_lr1.6e+01_wd1.0e+00": 4.805358409881592, "validation/loss_042_lr1.9e+01_wd1.0e+00": 9.370460510253906, "validation/loss_043_lr2.2e+01_wd1.0e+00": 6.56651496887207, "validation/loss_044_lr2.6e+01_wd1.0e+00": 1.3862943649291992, "validation/loss_045_lr3.1e+01_wd1.0e+00": 1.3862943649291992, "validation/loss_046_lr3.6e+01_wd1.0e+00": 1.3862943649291992, "validation/loss_047_lr4.3e+01_wd1.0e+00": 1.3862943649291992, "validation/loss_048_lr5.0e+01_wd1.0e+00": 1.3862943649291992, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.4339622641509434, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.41509433962264153, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.39622641509433965, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.39622641509433965, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.39622641509433965, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.37735849056603776, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.37735849056603776, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.3584905660377358, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.37735849056603776, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.4528301886792453, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.4339622641509434, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.4339622641509434, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.4339622641509434, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.4339622641509434, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.4339622641509434, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.4339622641509434, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.4339622641509434, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.4339622641509434, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.4528301886792453, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.41509433962264153, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.3584905660377358, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.32075471698113206, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.39622641509433965, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.32075471698113206, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.3584905660377358, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.3584905660377358, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.37735849056603776, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.37735849056603776, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.33962264150943394, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.2830188679245283, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.32075471698113206, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.39622641509433965, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.39622641509433965, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.37735849056603776, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.39622641509433965, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.39622641509433965, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.41509433962264153, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.4339622641509434, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.3584905660377358, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.3584905660377358, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.33962264150943394, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.33962264150943394, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.41509433962264153, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.33962264150943394, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.2641509433962264, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.2641509433962264, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.2641509433962264, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.2641509433962264, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.2641509433962264, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.4291219936250362, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.4119047619047619, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.3958737341090282, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.3958737341090282, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.3958737341090282, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.3664378218130754, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.3653980119497361, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.34857918263090676, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.3639161220043573, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.4489224137931035, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.43766233766233764, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.43766233766233764, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.43766233766233764, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.4269719978720317, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.43333333333333335, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.43333333333333335, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.43236074270557023, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.4348544973544973, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.44885632885632887, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.4128123728123728, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.3618172217310148, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.3281861053600184, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.3840489804725429, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.3081429536127993, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.35384615384615387, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.35384615384615387, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.3738461538461539, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.37802604802604806, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.3351282051282051, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.28240126731506043, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.31761273209549074, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.39007122507122505, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.3924753694581281, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.37309116809116805, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.37895788757857723, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.38508287065258584, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.411564039408867, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.4350925925925926, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.3596866096866097, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.35583231583231584, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.33343438171024375, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.3351282051282051, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.42143603678929764, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.3463917306052856, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.1044776119402985, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.1044776119402985, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.1044776119402985, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.1044776119402985, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.1044776119402985, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.4278846153846154, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.4100274725274725, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.3907967032967033, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.3907967032967033, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.3907967032967033, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.36996336996337, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.36996336996337, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.3507326007326007, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.3685897435897436, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.4487179487179487, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.4294871794871795, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.4294871794871795, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.4294871794871795, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.4294871794871795, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.43246336996337, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.43246336996337, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.43246336996337, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.4310897435897436, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.44757326007326004, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.41048534798534797, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.3539377289377289, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.3182234432234432, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.38667582417582413, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.31387362637362637, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.35096153846153844, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.35096153846153844, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.37179487179487175, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.37179487179487175, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.3331043956043956, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.27815934065934067, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.31387362637362637, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.38965201465201466, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.39400183150183155, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.3717948717948718, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.3882783882783883, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.3866758241758242, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.40865384615384615, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.4352106227106227, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.35370879120879123, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.3507326007326007, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.33470695970695974, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.3315018315018315, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.41460622710622713, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.33722527472527475, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.25, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.25, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.25, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.25, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.25, "id_best": 9, "lr_best": 2.6099999999999997e-05, "wd_best": 0.05, "train/loss_best": 1.0138540649414063, "validation/loss_best": 1.1958273649215698, "validation/acc_best": 0.4528301886792453, "validation/f1_best": 0.4489224137931035, "validation/bacc_best": 0.4487179487179487} +{"epoch": 19, "train/lr": 1.0867618231465446e-06, "train/loss": 0.5425640997290612, "train/grad": 0.22767734788358213, "train/loss_000_lr2.0e-02_wd1.0e+00": 1.15813232421875, "train/loss_001_lr2.3e-02_wd1.0e+00": 1.14871337890625, "train/loss_002_lr2.8e-02_wd1.0e+00": 1.135556640625, "train/loss_003_lr3.3e-02_wd1.0e+00": 1.12435302734375, "train/loss_004_lr3.8e-02_wd1.0e+00": 1.114266357421875, "train/loss_005_lr4.5e-02_wd1.0e+00": 1.10165771484375, "train/loss_006_lr5.3e-02_wd1.0e+00": 1.0876434326171875, "train/loss_007_lr6.2e-02_wd1.0e+00": 1.072388916015625, "train/loss_008_lr7.4e-02_wd1.0e+00": 1.0532427978515626, "train/loss_009_lr8.7e-02_wd1.0e+00": 1.0325418090820313, "train/loss_010_lr1.0e-01_wd1.0e+00": 1.011943359375, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.98013427734375, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.9477629089355468, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.8986703491210938, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.8514984893798828, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.8055150604248047, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.7456879425048828, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.6715411758422851, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.5878800487518311, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.5016235685348511, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.3608400821685791, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.18489593580365182, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.05780803635716438, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.01738190934062004, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.007218026518821716, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.003336758464574814, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.0019752980768680574, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0014918282628059386, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0011391445994377136, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0007602168619632721, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0005575454235076904, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.00046340331435203554, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.00039692580699920657, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.00033872693777084353, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.00032715633511543274, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.00025545626878738405, "train/loss_036_lr7.1e+00_wd1.0e+00": 6.996065378189086e-05, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.00023448914289474486, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.00028618186712265015, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.0001615549623966217, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.00020820960402488707, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.00037767887115478513, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.0001348268985748291, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.0001659218966960907, "train/loss_044_lr2.6e+01_wd1.0e+00": 1.3828125, "train/loss_045_lr3.1e+01_wd1.0e+00": 1.3828125, "train/loss_046_lr3.6e+01_wd1.0e+00": 1.3828125, "train/loss_047_lr4.3e+01_wd1.0e+00": 1.3828125, "train/loss_048_lr5.0e+01_wd1.0e+00": 1.3828125, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.04204513506032526, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.04215787591412663, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.04233347372151911, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.0424753251625225, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.04258690174203366, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.04272976891603321, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.0428817420033738, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.043054639692418274, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.043355593085289, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.04376471980940551, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.044295614855363964, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.04539556929841638, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.04693012598901987, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.049824096420779826, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.052584218047559264, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.054822794860228896, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.05716969205066562, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.059180023791268466, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.05999706741422415, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.058562696939334274, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.05246008677408099, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.03730282977223396, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.015096104557160287, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.005158508814056404, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.002199276535247918, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0010182212556537706, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0006296561603812734, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0004786880747997202, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.00035643870418425647, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0002368122665939154, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.00017252267873118398, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.00014169065914757084, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.00011768225045670989, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.00010535422383327386, "train/grad_034_lr5.1e+00_wd1.0e+00": 9.56103319185786e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 7.964220865687821e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 4.192695433459903e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 9.394452953984e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.00012321427413553466, "train/grad_039_lr1.2e+01_wd1.0e+00": 9.983463833123097e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0001290929577874067, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.00016584151743700203, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.00016496529502690454, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.00019520690058662637, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 1.217395544052124, "validation/loss_001_lr2.3e-02_wd1.0e+00": 1.2143269777297974, "validation/loss_002_lr2.8e-02_wd1.0e+00": 1.2113819122314453, "validation/loss_003_lr3.3e-02_wd1.0e+00": 1.2090986967086792, "validation/loss_004_lr3.8e-02_wd1.0e+00": 1.2075411081314087, "validation/loss_005_lr4.5e-02_wd1.0e+00": 1.2057709693908691, "validation/loss_006_lr5.3e-02_wd1.0e+00": 1.2037633657455444, "validation/loss_007_lr6.2e-02_wd1.0e+00": 1.2016332149505615, "validation/loss_008_lr7.4e-02_wd1.0e+00": 1.1987563371658325, "validation/loss_009_lr8.7e-02_wd1.0e+00": 1.196008324623108, "validation/loss_010_lr1.0e-01_wd1.0e+00": 1.1930081844329834, "validation/loss_011_lr1.2e-01_wd1.0e+00": 1.1890350580215454, "validation/loss_012_lr1.4e-01_wd1.0e+00": 1.1868939399719238, "validation/loss_013_lr1.7e-01_wd1.0e+00": 1.1889809370040894, "validation/loss_014_lr2.0e-01_wd1.0e+00": 1.1979649066925049, "validation/loss_015_lr2.3e-01_wd1.0e+00": 1.2116202116012573, "validation/loss_016_lr2.7e-01_wd1.0e+00": 1.237766146659851, "validation/loss_017_lr3.2e-01_wd1.0e+00": 1.2948421239852905, "validation/loss_018_lr3.8e-01_wd1.0e+00": 1.3989553451538086, "validation/loss_019_lr4.4e-01_wd1.0e+00": 1.5363491773605347, "validation/loss_020_lr5.2e-01_wd1.0e+00": 1.8068002462387085, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.235867977142334, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.785977840423584, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.4661738872528076, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.99931001663208, "validation/loss_025_lr1.2e+00_wd1.0e+00": 4.330435752868652, "validation/loss_026_lr1.4e+00_wd1.0e+00": 4.551975250244141, "validation/loss_027_lr1.6e+00_wd1.0e+00": 4.819756031036377, "validation/loss_028_lr1.9e+00_wd1.0e+00": 5.1682329177856445, "validation/loss_029_lr2.3e+00_wd1.0e+00": 5.190500736236572, "validation/loss_030_lr2.7e+00_wd1.0e+00": 4.91447639465332, "validation/loss_031_lr3.1e+00_wd1.0e+00": 4.8865556716918945, "validation/loss_032_lr3.7e+00_wd1.0e+00": 4.224419593811035, "validation/loss_033_lr4.3e+00_wd1.0e+00": 4.421126365661621, "validation/loss_034_lr5.1e+00_wd1.0e+00": 4.2620849609375, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.9789624214172363, "validation/loss_036_lr7.1e+00_wd1.0e+00": 5.113592147827148, "validation/loss_037_lr8.3e+00_wd1.0e+00": 4.0288801193237305, "validation/loss_038_lr9.8e+00_wd1.0e+00": 4.839527130126953, "validation/loss_039_lr1.2e+01_wd1.0e+00": 4.937875270843506, "validation/loss_040_lr1.4e+01_wd1.0e+00": 5.847280979156494, "validation/loss_041_lr1.6e+01_wd1.0e+00": 4.806123733520508, "validation/loss_042_lr1.9e+01_wd1.0e+00": 9.368443489074707, "validation/loss_043_lr2.2e+01_wd1.0e+00": 6.560953617095947, "validation/loss_044_lr2.6e+01_wd1.0e+00": 1.3862943649291992, "validation/loss_045_lr3.1e+01_wd1.0e+00": 1.3862943649291992, "validation/loss_046_lr3.6e+01_wd1.0e+00": 1.3862943649291992, "validation/loss_047_lr4.3e+01_wd1.0e+00": 1.3862943649291992, "validation/loss_048_lr5.0e+01_wd1.0e+00": 1.3862943649291992, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.4339622641509434, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.41509433962264153, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.39622641509433965, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.39622641509433965, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.39622641509433965, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.37735849056603776, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.37735849056603776, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.3584905660377358, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.37735849056603776, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.4528301886792453, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.4339622641509434, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.4339622641509434, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.4339622641509434, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.4339622641509434, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.4339622641509434, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.4339622641509434, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.4339622641509434, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.4339622641509434, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.4528301886792453, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.41509433962264153, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.37735849056603776, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.32075471698113206, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.37735849056603776, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.32075471698113206, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.3584905660377358, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.3584905660377358, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.3584905660377358, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.37735849056603776, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.33962264150943394, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.2830188679245283, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.32075471698113206, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.39622641509433965, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.39622641509433965, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.37735849056603776, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.39622641509433965, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.39622641509433965, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.41509433962264153, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.4339622641509434, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.3584905660377358, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.3584905660377358, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.33962264150943394, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.33962264150943394, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.41509433962264153, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.33962264150943394, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.2641509433962264, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.2641509433962264, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.2641509433962264, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.2641509433962264, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.2641509433962264, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.4291219936250362, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.4119047619047619, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.3958737341090282, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.3958737341090282, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.3958737341090282, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.3664378218130754, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.3653980119497361, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.34857918263090676, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.3639161220043573, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.4489224137931035, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.43766233766233764, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.43766233766233764, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.43766233766233764, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.4269719978720317, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.43333333333333335, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.43333333333333335, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.43236074270557023, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.4348544973544973, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.44885632885632887, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.4128123728123728, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.37856732348111655, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.3281861053600184, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.3680660744896369, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.3081429536127993, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.35384615384615387, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.35384615384615387, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.35692307692307695, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.37802604802604806, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.3351282051282051, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.28240126731506043, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.31761273209549074, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.39007122507122505, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.3924753694581281, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.37309116809116805, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.37895788757857723, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.38508287065258584, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.411564039408867, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.4350925925925926, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.3596866096866097, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.35583231583231584, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.33343438171024375, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.3351282051282051, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.42143603678929764, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.3463917306052856, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.1044776119402985, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.1044776119402985, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.1044776119402985, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.1044776119402985, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.1044776119402985, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.4278846153846154, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.4100274725274725, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.3907967032967033, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.3907967032967033, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.3907967032967033, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.36996336996337, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.36996336996337, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.3507326007326007, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.3685897435897436, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.4487179487179487, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.4294871794871795, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.4294871794871795, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.4294871794871795, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.4294871794871795, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.43246336996337, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.43246336996337, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.43246336996337, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.4310897435897436, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.44757326007326004, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.41048534798534797, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.37477106227106227, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.3182234432234432, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.36881868131868134, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.31387362637362637, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.35096153846153844, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.35096153846153844, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.3539377289377289, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.37179487179487175, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.3331043956043956, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.27815934065934067, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.31387362637362637, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.38965201465201466, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.39400183150183155, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.3717948717948718, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.3882783882783883, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.3866758241758242, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.40865384615384615, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.4352106227106227, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.35370879120879123, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.3507326007326007, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.33470695970695974, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.3315018315018315, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.41460622710622713, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.33722527472527475, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.25, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.25, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.25, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.25, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.25, "id_best": 9, "lr_best": 2.6099999999999997e-05, "wd_best": 0.05, "train/loss_best": 1.0325418090820313, "validation/loss_best": 1.196008324623108, "validation/acc_best": 0.4528301886792453, "validation/f1_best": 0.4489224137931035, "validation/bacc_best": 0.4487179487179487} diff --git a/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_age__patch__logistic/config.yaml b/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_age__patch__logistic/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..6c352263d47f3aa664f87d08c564310b221fbbea --- /dev/null +++ b/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_age__patch__logistic/config.yaml @@ -0,0 +1,30 @@ +output_root: experiments/input_space_v3/output +name_prefix: eval_logistic +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_1; eval v2 (aabc_age patch logistic) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: input_space_v3/flat_lr1e-3_1/eval_v2/aabc_age__patch__logistic +model: flat_mae +representation: patch +dataset: aabc_age +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_age__patch__logistic +remote_dir: null diff --git a/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_age__patch__logistic/eval_table.csv b/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_age__patch__logistic/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..b702c31c1b9fa3a19da4a94d708e7ab9baaacc2d --- /dev/null +++ b/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_age__patch__logistic/eval_table.csv @@ -0,0 +1,203 @@ +model,repr,clf,dataset,trial,C,split,acc,acc_std,f1,f1_std,bacc,bacc_std +flat_mae,patch,logistic,aabc_age,,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,,21.54434690031882,test,0.36538461538461536,0.06036255108893673,0.3613448969331322,0.05976378108166214,0.3578296703296704,0.0600864614266622 +flat_mae,patch,logistic,aabc_age,1,0.046415888336127774,train,0.84251968503937,0.01622331792180901,0.8425370441134362,0.01631713079266062,0.8434519379963905,0.016162535728129382 +flat_mae,patch,logistic,aabc_age,1,0.046415888336127774,test,0.5192307692307693,0.06382218039254983,0.5163817663817664,0.06335767788589786,0.5187728937728938,0.06358161483130018 +flat_mae,patch,logistic,aabc_age,2,0.000774263682681127,train,0.5728346456692913,0.020756888246960797,0.5663194372951337,0.021415417319662483,0.5734956289833502,0.020792836910598193 +flat_mae,patch,logistic,aabc_age,2,0.000774263682681127,test,0.6153846153846154,0.06333437142302982,0.6053304979620769,0.06564534145894432,0.6094322344322344,0.06321334770106317 +flat_mae,patch,logistic,aabc_age,3,0.046415888336127774,train,0.8346456692913385,0.015654970605408672,0.8353830224770874,0.01562594745609448,0.8352874485269156,0.015693520132311345 +flat_mae,patch,logistic,aabc_age,3,0.046415888336127774,test,0.5576923076923077,0.06691435619572796,0.5465201465201465,0.06852409227187303,0.5517399267399268,0.06692031653594371 +flat_mae,patch,logistic,aabc_age,4,0.005994842503189409,train,0.6811023622047244,0.020638161409568742,0.6797545876822604,0.021023789395770653,0.682001346403549,0.020627476081855153 +flat_mae,patch,logistic,aabc_age,4,0.005994842503189409,test,0.5576923076923077,0.06394657302141711,0.5443438003220612,0.06744043895073963,0.5588369963369964,0.06421714292071055 +flat_mae,patch,logistic,aabc_age,5,0.046415888336127774,train,0.8562992125984252,0.014907744798651139,0.8555135601436992,0.015051798857629094,0.8568621509084388,0.014811727101906454 +flat_mae,patch,logistic,aabc_age,5,0.046415888336127774,test,0.4423076923076923,0.06289843414387579,0.4297745358090186,0.06353943028089844,0.44024725274725274,0.06273416974216957 +flat_mae,patch,logistic,aabc_age,6,0.005994842503189409,train,0.6791338582677166,0.020299952873742665,0.677678864045267,0.020577937675732575,0.6797176628198907,0.020323765704970537 +flat_mae,patch,logistic,aabc_age,6,0.005994842503189409,test,0.5769230769230769,0.06281252042302944,0.5650174912543728,0.06641467250436271,0.5780677655677656,0.06319855939422216 +flat_mae,patch,logistic,aabc_age,7,0.046415888336127774,train,0.8366141732283464,0.014938329836611489,0.8358375862261266,0.01509666743445721,0.8376887266513102,0.014962548418381275 +flat_mae,patch,logistic,aabc_age,7,0.046415888336127774,test,0.5384615384615384,0.06506055440622198,0.5255749902826364,0.06416718757348683,0.5309065934065934,0.06475540588526522 +flat_mae,patch,logistic,aabc_age,8,0.000774263682681127,train,0.5708661417322834,0.02093332336032799,0.5571995605263348,0.021690376199157844,0.5685363998856899,0.020860720470790167 +flat_mae,patch,logistic,aabc_age,8,0.000774263682681127,test,0.4230769230769231,0.05916609856104179,0.4214993717716041,0.05698006354679332,0.4297161172161172,0.06054243022336343 +flat_mae,patch,logistic,aabc_age,9,0.005994842503189409,train,0.6909448818897638,0.0200727221952667,0.6909472653429056,0.020321664616705055,0.6917292079426302,0.020063204915262537 +flat_mae,patch,logistic,aabc_age,9,0.005994842503189409,test,0.5,0.06431068266878719,0.47665983956306535,0.06563334516295799,0.4935897435897436,0.0637415472602576 +flat_mae,patch,logistic,aabc_age,10,0.000774263682681127,train,0.5807086614173228,0.02032363354816656,0.5751224393189929,0.02088081201449756,0.5810574014795096,0.020281705747083014 +flat_mae,patch,logistic,aabc_age,10,0.000774263682681127,test,0.5192307692307693,0.06665617644290861,0.5147619047619048,0.06698588085121501,0.516025641025641,0.06645645813581935 +flat_mae,patch,logistic,aabc_age,11,0.046415888336127774,train,0.8307086614173228,0.016305721150966755,0.8300878635559183,0.016587245525711038,0.8322430565278516,0.016226093043264576 +flat_mae,patch,logistic,aabc_age,11,0.046415888336127774,test,0.5961538461538461,0.06694698953861947,0.6045698924731182,0.06604406096257033,0.5977564102564102,0.06686124645128659 +flat_mae,patch,logistic,aabc_age,12,0.005994842503189409,train,0.6968503937007874,0.019059713443421777,0.6955050664099762,0.019372704565153033,0.6983803120127199,0.019013333360779674 +flat_mae,patch,logistic,aabc_age,12,0.005994842503189409,test,0.4230769230769231,0.06327520430065746,0.4210717443476064,0.06344491271792675,0.4255952380952381,0.06359159341364597 +flat_mae,patch,logistic,aabc_age,13,0.005994842503189409,train,0.6712598425196851,0.019998256170488962,0.6684959287977861,0.020425872981163152,0.6722058769939527,0.019988359298484925 +flat_mae,patch,logistic,aabc_age,13,0.005994842503189409,test,0.4423076923076923,0.06244376168025967,0.4363154960981048,0.06252062985517931,0.44459706959706957,0.06305813109101174 +flat_mae,patch,logistic,aabc_age,14,0.046415888336127774,train,0.8562992125984252,0.014937095039987415,0.8557124098871578,0.015135298776142985,0.8578823824438183,0.014842042713056778 +flat_mae,patch,logistic,aabc_age,14,0.046415888336127774,test,0.6153846153846154,0.06716995797555533,0.6167628667628667,0.0678016033270939,0.6185897435897435,0.06689950578815797 +flat_mae,patch,logistic,aabc_age,15,0.046415888336127774,train,0.8366141732283464,0.016479080484668663,0.8360820352212852,0.016598246892696292,0.8377387133215315,0.016436788187455854 +flat_mae,patch,logistic,aabc_age,15,0.046415888336127774,test,0.38461538461538464,0.06615316412886352,0.3885856494552147,0.06554809449461915,0.38278388278388276,0.0660921684944768 +flat_mae,patch,logistic,aabc_age,16,0.046415888336127774,train,0.8346456692913385,0.0162046646272705,0.8343477853912636,0.016382215545258882,0.8355050164080946,0.01618028018483895 +flat_mae,patch,logistic,aabc_age,16,0.046415888336127774,test,0.5,0.06839100731570492,0.4976731601731602,0.06932336617339238,0.49977106227106227,0.06832329483935812 +flat_mae,patch,logistic,aabc_age,17,0.005994842503189409,train,0.6811023622047244,0.02006159527393596,0.679547483516174,0.02028268925213595,0.6824364821659068,0.01994560214242373 +flat_mae,patch,logistic,aabc_age,17,0.005994842503189409,test,0.5384615384615384,0.058383994625259804,0.5062760802261408,0.06077896748856684,0.532051282051282,0.057477522015765586 +flat_mae,patch,logistic,aabc_age,18,0.046415888336127774,train,0.8366141732283464,0.015310140325966774,0.8367432762175302,0.015372920151459414,0.8376211187807951,0.015216843552443637 +flat_mae,patch,logistic,aabc_age,18,0.046415888336127774,test,0.40384615384615385,0.06002310945493455,0.3941356918943126,0.061362704181427925,0.40453296703296704,0.06028452492418795 +flat_mae,patch,logistic,aabc_age,19,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,19,21.54434690031882,test,0.40384615384615385,0.06797062539921024,0.4119738326189939,0.06722622223116158,0.40773809523809523,0.06864506091029224 +flat_mae,patch,logistic,aabc_age,20,0.005994842503189409,train,0.6771653543307087,0.02241996671072048,0.6764848750178274,0.022693907411032634,0.6787717519932335,0.02232185691693289 +flat_mae,patch,logistic,aabc_age,20,0.005994842503189409,test,0.5384615384615384,0.0632633735890667,0.5132348551278942,0.06837362271891072,0.5364010989010989,0.06315095823210158 +flat_mae,patch,logistic,aabc_age,21,0.046415888336127774,train,0.8484251968503937,0.015437439121468746,0.8482853089545878,0.015612519224895663,0.8483125123468275,0.015504264932337327 +flat_mae,patch,logistic,aabc_age,21,0.046415888336127774,test,0.5192307692307693,0.06672449538230821,0.5067534414610876,0.06820480327094554,0.5247252747252746,0.06719454379018638 +flat_mae,patch,logistic,aabc_age,22,0.005994842503189409,train,0.6830708661417323,0.019980008918954777,0.6810398309097676,0.02011031953128996,0.6839674887655858,0.01999965807488853 +flat_mae,patch,logistic,aabc_age,22,0.005994842503189409,test,0.38461538461538464,0.06376078630178963,0.39570099976749595,0.06261176625297372,0.38713369963369965,0.06415886757288594 +flat_mae,patch,logistic,aabc_age,23,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,23,2.782559402207126,test,0.5576923076923077,0.061669331996347575,0.5513498806152479,0.06245205867664573,0.5544871794871794,0.06173051846176813 +flat_mae,patch,logistic,aabc_age,24,0.005994842503189409,train,0.702755905511811,0.021831587281652392,0.7015095635330953,0.022180710207660784,0.7029233451415354,0.021839914771731445 +flat_mae,patch,logistic,aabc_age,24,0.005994842503189409,test,0.40384615384615385,0.06297941572239082,0.4112091356918943,0.060948264220029136,0.40315934065934067,0.0629689505010752 +flat_mae,patch,logistic,aabc_age,25,0.005994842503189409,train,0.6948818897637795,0.019917291316767612,0.6931112532666704,0.020008264430808283,0.695996655088619,0.01979059118879021 +flat_mae,patch,logistic,aabc_age,25,0.005994842503189409,test,0.3076923076923077,0.06189391334271682,0.2983508245877061,0.0609351906339869,0.3054029304029304,0.061510460212664674 +flat_mae,patch,logistic,aabc_age,26,0.000774263682681127,train,0.5767716535433071,0.02205556788877017,0.5703000987003124,0.022696807033391393,0.5761724930905716,0.021997731507516435 +flat_mae,patch,logistic,aabc_age,26,0.000774263682681127,test,0.4807692307692308,0.06706457190449908,0.48065476190476186,0.06709257511923554,0.4789377289377289,0.06705789049687207 +flat_mae,patch,logistic,aabc_age,27,0.005994842503189409,train,0.6948818897637795,0.020190534844708657,0.6921738562552173,0.020566596079960777,0.6951440047641972,0.02016850995086418 +flat_mae,patch,logistic,aabc_age,27,0.005994842503189409,test,0.36538461538461536,0.05952121594800457,0.3388888888888889,0.059593719879657246,0.3603479853479853,0.05875415716473792 +flat_mae,patch,logistic,aabc_age,28,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,28,21.54434690031882,test,0.5,0.07070418206122425,0.50118161408484,0.07152315363771392,0.4983974358974359,0.07078048757275869 +flat_mae,patch,logistic,aabc_age,29,0.046415888336127774,train,0.8405511811023622,0.017135773742947356,0.8410331808430179,0.017164308280490252,0.8418033368559751,0.017099781581225475 +flat_mae,patch,logistic,aabc_age,29,0.046415888336127774,test,0.4230769230769231,0.059506488632325744,0.42040312628547927,0.06048151234299964,0.42124542124542125,0.059663690730506196 +flat_mae,patch,logistic,aabc_age,30,0.046415888336127774,train,0.8287401574803149,0.0171302261920063,0.8290739183586499,0.017259201757888868,0.8299417517438994,0.017131312950524374 +flat_mae,patch,logistic,aabc_age,30,0.046415888336127774,test,0.5384615384615384,0.06960661865761578,0.5480895915678524,0.06783011372874352,0.5368589743589743,0.06928927725159015 +flat_mae,patch,logistic,aabc_age,31,9.999999999999999e-05,train,0.484251968503937,0.021006765411847345,0.4571542187806855,0.021832865943038217,0.4813701957655417,0.020872774771967202 +flat_mae,patch,logistic,aabc_age,31,9.999999999999999e-05,test,0.5192307692307693,0.05624885271676803,0.4540354147250699,0.047472912564200456,0.5068681318681318,0.054819871130277656 +flat_mae,patch,logistic,aabc_age,32,0.046415888336127774,train,0.8287401574803149,0.01597871204567118,0.8289277671481061,0.01606111904536856,0.8297741705329418,0.015983069850988026 +flat_mae,patch,logistic,aabc_age,32,0.046415888336127774,test,0.5,0.06922490359766859,0.5083541178719396,0.06705369910535389,0.4981684981684981,0.06916124365643214 +flat_mae,patch,logistic,aabc_age,33,0.005994842503189409,train,0.6811023622047244,0.020790999375482407,0.6801580017777727,0.021033424757221437,0.6817161706518549,0.0207698084178441 +flat_mae,patch,logistic,aabc_age,33,0.005994842503189409,test,0.5576923076923077,0.06274880653760269,0.5610095723242274,0.06465646512953763,0.5576923076923077,0.0632548012818985 +flat_mae,patch,logistic,aabc_age,34,0.005994842503189409,train,0.6791338582677166,0.02001229394606769,0.6758371159518046,0.02058864119722186,0.6800028385715847,0.019923488114886107 +flat_mae,patch,logistic,aabc_age,34,0.005994842503189409,test,0.40384615384615385,0.06955398907646998,0.4125000000000001,0.07032608628085507,0.4049908424908425,0.06970072394267178 +flat_mae,patch,logistic,aabc_age,35,0.046415888336127774,train,0.8385826771653543,0.01636255522424378,0.8377349246914465,0.016632881129183534,0.8392697199212105,0.016333869183611103 +flat_mae,patch,logistic,aabc_age,35,0.046415888336127774,test,0.46153846153846156,0.062425387416361625,0.4656707875457875,0.062169629914232034,0.4610805860805861,0.062431976485544854 +flat_mae,patch,logistic,aabc_age,36,0.3593813663804626,train,0.9921259842519685,0.0037147729539066246,0.992201116705927,0.0036735276782812487,0.9921030650819254,0.0037351755984979637 +flat_mae,patch,logistic,aabc_age,36,0.3593813663804626,test,0.4230769230769231,0.06387972935513431,0.4251851851851852,0.06387688715209074,0.4301739926739927,0.06462439265304444 +flat_mae,patch,logistic,aabc_age,37,0.005994842503189409,train,0.6948818897637795,0.022039797322238056,0.6939886333348668,0.022283958015000483,0.6965817508616408,0.022079412570811283 +flat_mae,patch,logistic,aabc_age,37,0.005994842503189409,test,0.46153846153846156,0.06472485004245086,0.44462962962962965,0.06430924120218762,0.4537545787545788,0.06416886722791552 +flat_mae,patch,logistic,aabc_age,38,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,38,2.782559402207126,test,0.4423076923076923,0.06396812954615085,0.44372605363984674,0.062336404253656115,0.43887362637362637,0.06389709105117665 +flat_mae,patch,logistic,aabc_age,39,0.046415888336127774,train,0.844488188976378,0.015921590843697448,0.8440869720065122,0.01611251520997901,0.8452005124772484,0.01588429961238327 +flat_mae,patch,logistic,aabc_age,39,0.046415888336127774,test,0.5192307692307693,0.0682155910617604,0.5214135821552701,0.06805862951942754,0.5146520146520146,0.06819533668891838 +flat_mae,patch,logistic,aabc_age,40,0.3593813663804626,train,0.9901574803149606,0.004337317791521758,0.9901513217707847,0.004340833046260566,0.9900369493794461,0.004403727593072709 +flat_mae,patch,logistic,aabc_age,40,0.3593813663804626,test,0.4423076923076923,0.05999727557917174,0.4227193942711184,0.05889417929488195,0.440018315018315,0.059557013238407605 +flat_mae,patch,logistic,aabc_age,41,0.005994842503189409,train,0.6948818897637795,0.01950130752288138,0.6947135425444658,0.019558033188205034,0.6968992920832622,0.019539248667434533 +flat_mae,patch,logistic,aabc_age,41,0.005994842503189409,test,0.4230769230769231,0.06537840468240692,0.4168183765260227,0.0653083792042069,0.42239010989010994,0.06546727874878863 +flat_mae,patch,logistic,aabc_age,42,0.046415888336127774,train,0.84251968503937,0.016752794746318123,0.842620692944192,0.01683349081616605,0.8438194658882331,0.01675238806493625 +flat_mae,patch,logistic,aabc_age,42,0.046415888336127774,test,0.5,0.06070346977400509,0.483199309436191,0.06309919666705456,0.5070970695970696,0.06143006604987377 +flat_mae,patch,logistic,aabc_age,43,0.005994842503189409,train,0.6889763779527559,0.019405196304683108,0.6875049876084172,0.01962756970315607,0.6898482946514023,0.019389437794396096 +flat_mae,patch,logistic,aabc_age,43,0.005994842503189409,test,0.5384615384615384,0.06890307058538592,0.5362292277614858,0.06993228159978784,0.535485347985348,0.06915418324166912 +flat_mae,patch,logistic,aabc_age,44,0.005994842503189409,train,0.6830708661417323,0.02004686794124778,0.6815748041062365,0.02030646030586569,0.6847201657495651,0.02002223533076648 +flat_mae,patch,logistic,aabc_age,44,0.005994842503189409,test,0.5384615384615384,0.07066014795396157,0.5317252088241593,0.07300227939327764,0.535485347985348,0.07088418051073271 +flat_mae,patch,logistic,aabc_age,45,0.046415888336127774,train,0.8405511811023622,0.015747308546397807,0.8405826932075419,0.015835369597253426,0.8412682277531748,0.01570292158572908 +flat_mae,patch,logistic,aabc_age,45,0.046415888336127774,test,0.46153846153846156,0.06554166658829784,0.45767877284006314,0.06696799112587501,0.4640567765567766,0.06592212970025227 +flat_mae,patch,logistic,aabc_age,46,0.000774263682681127,train,0.5669291338582677,0.02150765853501378,0.5585051659317827,0.022097855694648977,0.5661594557997963,0.021496484955717262 +flat_mae,patch,logistic,aabc_age,46,0.000774263682681127,test,0.5192307692307693,0.06260971435297359,0.5007352941176471,0.06797521113831917,0.5157967032967032,0.06255393475139216 +flat_mae,patch,logistic,aabc_age,47,0.005994842503189409,train,0.6830708661417323,0.0191333313008669,0.6817017479011365,0.019281514966254187,0.6854728427335445,0.019033838483597722 +flat_mae,patch,logistic,aabc_age,47,0.005994842503189409,test,0.4807692307692308,0.06422818972250102,0.47290805267663616,0.06760285137187264,0.4819139194139195,0.06422892974493875 +flat_mae,patch,logistic,aabc_age,48,0.000774263682681127,train,0.5767716535433071,0.02156402972579003,0.567222787816529,0.02253295690431279,0.5753698294363709,0.021555666778053918 +flat_mae,patch,logistic,aabc_age,48,0.000774263682681127,test,0.5,0.06322004166907083,0.48747771836007125,0.06712906565533484,0.4965659340659341,0.06290293262931561 +flat_mae,patch,logistic,aabc_age,49,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,49,1291.5496650148827,test,0.4230769230769231,0.06361752391528946,0.42653985507246384,0.06439140355658643,0.4212454212454212,0.06362258173389435 +flat_mae,patch,logistic,aabc_age,50,0.000774263682681127,train,0.5826771653543307,0.020316585343686085,0.5713768838676476,0.02136488434154508,0.5808331207601234,0.020261691879132373 +flat_mae,patch,logistic,aabc_age,50,0.000774263682681127,test,0.46153846153846156,0.06578007108143993,0.46030695708115066,0.06754350508223267,0.4597069597069597,0.06593200663247284 +flat_mae,patch,logistic,aabc_age,51,0.005994842503189409,train,0.687007874015748,0.01957745839106174,0.6872229394420296,0.019709303808255908,0.6894874795977668,0.01944882207317214 +flat_mae,patch,logistic,aabc_age,51,0.005994842503189409,test,0.46153846153846156,0.06972278158671918,0.46011904761904765,0.07006874477963,0.4626831501831502,0.0698980896947373 +flat_mae,patch,logistic,aabc_age,52,0.046415888336127774,train,0.8366141732283464,0.01631361340316623,0.8356132101629044,0.016636578325541277,0.837856307862268,0.016191978281256965 +flat_mae,patch,logistic,aabc_age,52,0.046415888336127774,test,0.4423076923076923,0.06570206872176497,0.44664835164835165,0.06519118434775434,0.4494047619047619,0.06625525765351573 +flat_mae,patch,logistic,aabc_age,53,9.999999999999999e-05,train,0.4881889763779528,0.020764797720027244,0.47052023092661366,0.021277504487179022,0.4861375096137433,0.020657338104731828 +flat_mae,patch,logistic,aabc_age,53,9.999999999999999e-05,test,0.5,0.058569788443729204,0.45706605222734253,0.05766571594240479,0.4933608058608059,0.057686464215084124 +flat_mae,patch,logistic,aabc_age,54,0.3593813663804626,train,0.9940944881889764,0.0032820669621333215,0.9940853895896431,0.0032880279611736275,0.9940692074439622,0.003298614823085451 +flat_mae,patch,logistic,aabc_age,54,0.3593813663804626,test,0.4423076923076923,0.06528973885688318,0.4272486772486772,0.0650540185946747,0.4491758241758242,0.06589996376560961 +flat_mae,patch,logistic,aabc_age,55,0.000774263682681127,train,0.5767716535433071,0.02110571831051222,0.565260483827638,0.02184387139169824,0.5756550051880649,0.02101209634122327 +flat_mae,patch,logistic,aabc_age,55,0.000774263682681127,test,0.5,0.06364026115782906,0.4964269509981851,0.06607775239783045,0.4981684981684982,0.06383607529032104 +flat_mae,patch,logistic,aabc_age,56,0.000774263682681127,train,0.5866141732283464,0.021515917685969797,0.5807330575106092,0.02181554536106837,0.5855328267378099,0.021482964103526615 +flat_mae,patch,logistic,aabc_age,56,0.000774263682681127,test,0.40384615384615385,0.06090387955113121,0.38267682781614676,0.061091420333888626,0.40293040293040294,0.06088914447362108 +flat_mae,patch,logistic,aabc_age,57,0.046415888336127774,train,0.8405511811023622,0.016297726643056325,0.8406331628467851,0.01640479699661813,0.8407831053205956,0.01629367911256091 +flat_mae,patch,logistic,aabc_age,57,0.046415888336127774,test,0.4423076923076923,0.06722284762343493,0.4432848186296462,0.06549792702549874,0.44024725274725274,0.06695736816435065 +flat_mae,patch,logistic,aabc_age,58,0.046415888336127774,train,0.844488188976378,0.016435655090732373,0.844352399067388,0.016661756963022592,0.8455180536988698,0.01637875632517618 +flat_mae,patch,logistic,aabc_age,58,0.046415888336127774,test,0.36538461538461536,0.05302862908805563,0.3431077694235589,0.055157960279206004,0.3630952380952381,0.052427761580892664 +flat_mae,patch,logistic,aabc_age,59,0.046415888336127774,train,0.844488188976378,0.016219480513971363,0.8442325800635618,0.01634001690865894,0.8462207440126278,0.016110437561975294 +flat_mae,patch,logistic,aabc_age,59,0.046415888336127774,test,0.4807692307692308,0.0694811178641001,0.48645962732919257,0.06966005342767094,0.4821428571428571,0.06957404383418024 +flat_mae,patch,logistic,aabc_age,60,0.005994842503189409,train,0.6751968503937008,0.021408093483842344,0.6731644947442825,0.0216574313904354,0.6761881483882476,0.021337867990823867 +flat_mae,patch,logistic,aabc_age,60,0.005994842503189409,test,0.4230769230769231,0.061496752692446914,0.4130668536699392,0.0661015907274849,0.42399267399267393,0.06177799988187703 +flat_mae,patch,logistic,aabc_age,61,0.3593813663804626,train,0.9940944881889764,0.003489850477901979,0.9941147905677075,0.0034863289677674876,0.9938516395627832,0.0036303695405206947 +flat_mae,patch,logistic,aabc_age,61,0.3593813663804626,test,0.4230769230769231,0.06856409776959499,0.42727272727272725,0.06976702940717863,0.421474358974359,0.0686159254300565 +flat_mae,patch,logistic,aabc_age,62,0.046415888336127774,train,0.8228346456692913,0.016434775651152075,0.822831295014144,0.01657594071944741,0.8247136495016197,0.016435019420627382 +flat_mae,patch,logistic,aabc_age,62,0.046415888336127774,test,0.6153846153846154,0.06044749298592973,0.6094179894179894,0.06270773991181341,0.6167582417582418,0.060786699415631334 +flat_mae,patch,logistic,aabc_age,63,0.005994842503189409,train,0.6909448818897638,0.019362473700712295,0.6903064060211087,0.019493482838022255,0.6910941254993872,0.019417812534197186 +flat_mae,patch,logistic,aabc_age,63,0.005994842503189409,test,0.40384615384615385,0.05170918909329744,0.3606584047760518,0.05033279643743934,0.4056776556776557,0.05233210803663641 +flat_mae,patch,logistic,aabc_age,64,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,64,2.782559402207126,test,0.4230769230769231,0.06798994878726322,0.4277370777370777,0.06798982603027305,0.4212454212454212,0.06804398290494236 +flat_mae,patch,logistic,aabc_age,65,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,65,21.54434690031882,test,0.4423076923076923,0.06672245570027048,0.4395120621507428,0.0667954116334929,0.43887362637362637,0.06657890631154557 +flat_mae,patch,logistic,aabc_age,66,0.005994842503189409,train,0.7047244094488189,0.019551142651885033,0.70428337883844,0.019689346534294088,0.7059920711791005,0.01952254392898281 +flat_mae,patch,logistic,aabc_age,66,0.005994842503189409,test,0.36538461538461536,0.06512055275051452,0.37008152173913045,0.06569686596652159,0.36492673992673996,0.06520679518127023 +flat_mae,patch,logistic,aabc_age,67,0.046415888336127774,train,0.8405511811023622,0.016387728003456083,0.8406379364624285,0.016533482423832502,0.840900699861332,0.016340354033971594 +flat_mae,patch,logistic,aabc_age,67,0.046415888336127774,test,0.5192307692307693,0.06246488954633237,0.484375,0.06733354651167807,0.5114468864468864,0.06187806704069776 +flat_mae,patch,logistic,aabc_age,68,0.005994842503189409,train,0.6830708661417323,0.019637095552322473,0.6819367348564715,0.01975460450663083,0.6838498942248493,0.019619097351318 +flat_mae,patch,logistic,aabc_age,68,0.005994842503189409,test,0.5192307692307693,0.061081912216301805,0.5044726533213375,0.06357814825377892,0.5171703296703297,0.06110720271700992 +flat_mae,patch,logistic,aabc_age,69,0.046415888336127774,train,0.844488188976378,0.016819031727767716,0.8439811882930347,0.016975866124619227,0.8449329579258482,0.016842715528756044 +flat_mae,patch,logistic,aabc_age,69,0.046415888336127774,test,0.38461538461538464,0.06450842796182922,0.39001322751322753,0.06209113885067869,0.3914835164835164,0.0655137920413032 +flat_mae,patch,logistic,aabc_age,70,0.000774263682681127,train,0.5708661417322834,0.020871775721343005,0.5657306316354777,0.021384538574715402,0.5709943775185131,0.020864290355406993 +flat_mae,patch,logistic,aabc_age,70,0.000774263682681127,test,0.4230769230769231,0.06199656413461186,0.40388605923410675,0.06228256920221505,0.41804029304029305,0.06155384903195036 +flat_mae,patch,logistic,aabc_age,71,0.046415888336127774,train,0.8503937007874016,0.015637098948901213,0.850332509783138,0.01573949554786253,0.8516164274658652,0.015586947088155717 +flat_mae,patch,logistic,aabc_age,71,0.046415888336127774,test,0.4807692307692308,0.06680179106836005,0.4832671957671958,0.06689683060986362,0.4819139194139194,0.06713709366606323 +flat_mae,patch,logistic,aabc_age,72,0.005994842503189409,train,0.6791338582677166,0.02081701988029586,0.6798741057633845,0.020846999171585022,0.6813229901282919,0.020753783089090372 +flat_mae,patch,logistic,aabc_age,72,0.005994842503189409,test,0.5961538461538461,0.06386249790803093,0.5935057471264368,0.06556177178337477,0.5918040293040293,0.06417585374694068 +flat_mae,patch,logistic,aabc_age,73,0.3593813663804626,train,0.9921259842519685,0.004197616673777087,0.992239418246442,0.004127231477091108,0.9923706196333255,0.004060646573762971 +flat_mae,patch,logistic,aabc_age,73,0.3593813663804626,test,0.4230769230769231,0.05655979451014286,0.4208791208791209,0.05641669570313965,0.4285714285714286,0.0574239782145545 +flat_mae,patch,logistic,aabc_age,74,0.3593813663804626,train,0.9901574803149606,0.004227701236714277,0.9901513217707847,0.00422753328681744,0.9900369493794461,0.004285851572999973 +flat_mae,patch,logistic,aabc_age,74,0.3593813663804626,test,0.4807692307692308,0.06619278818043996,0.4999019607843137,0.06510359481439482,0.4821428571428571,0.06633390190152014 +flat_mae,patch,logistic,aabc_age,75,0.005994842503189409,train,0.6968503937007874,0.01985480301907842,0.6948250979822863,0.020026032561204853,0.6976952428992557,0.019815219197733665 +flat_mae,patch,logistic,aabc_age,75,0.005994842503189409,test,0.5192307692307693,0.06895672255696914,0.5215488215488215,0.07042901852894937,0.521978021978022,0.0692248221588424 +flat_mae,patch,logistic,aabc_age,76,0.046415888336127774,train,0.8307086614173228,0.016965927330546374,0.830716718509822,0.017121891507538622,0.8319078941059364,0.01694571245082712 +flat_mae,patch,logistic,aabc_age,76,0.046415888336127774,test,0.5,0.06605729761386955,0.4972145096283027,0.06688719128163513,0.4981684981684982,0.06603064922320297 +flat_mae,patch,logistic,aabc_age,77,0.046415888336127774,train,0.8228346456692913,0.01628989567865314,0.8227624069033949,0.01642140142880312,0.8234758500850613,0.016254730360129227 +flat_mae,patch,logistic,aabc_age,77,0.046415888336127774,test,0.4230769230769231,0.06754655418486216,0.42564935064935067,0.0680292576946857,0.42559523809523814,0.06789706072309044 +flat_mae,patch,logistic,aabc_age,78,0.3593813663804626,train,0.9921259842519685,0.003933195004070588,0.9920867443145884,0.003956779523875813,0.9921030650819254,0.003965952412637317 +flat_mae,patch,logistic,aabc_age,78,0.3593813663804626,test,0.4423076923076923,0.06911961161681374,0.4478787878787879,0.06981667834330604,0.4420787545787546,0.06928195283143487 +flat_mae,patch,logistic,aabc_age,79,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,79,166.81005372000556,test,0.4230769230769231,0.06731301077888542,0.42698611733094494,0.0677557644893142,0.42422161172161177,0.06728303171992643 +flat_mae,patch,logistic,aabc_age,80,0.005994842503189409,train,0.6614173228346457,0.021078798616892342,0.6597602946204532,0.02146526945272539,0.6632630579087783,0.02102656083363064 +flat_mae,patch,logistic,aabc_age,80,0.005994842503189409,test,0.5,0.06270320811324016,0.48544973544973546,0.06503867304384674,0.49793956043956045,0.06264079289247888 +flat_mae,patch,logistic,aabc_age,81,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,81,21.54434690031882,test,0.46153846153846156,0.061875088906755804,0.45633533133533133,0.06205250579903118,0.4567307692307693,0.06167989135587098 +flat_mae,patch,logistic,aabc_age,82,0.005994842503189409,train,0.6732283464566929,0.020990033329249345,0.6731887316401536,0.021118564838714687,0.6744719393773172,0.020992551976465084 +flat_mae,patch,logistic,aabc_age,82,0.005994842503189409,test,0.5384615384615384,0.0704954885459023,0.5388810970858656,0.07105629896518642,0.5382326007326008,0.07068349530476242 +flat_mae,patch,logistic,aabc_age,83,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,83,166.81005372000556,test,0.38461538461538464,0.061896685728252146,0.37731481481481477,0.061236236842725916,0.3823260073260073,0.061717901546825986 +flat_mae,patch,logistic,aabc_age,84,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,84,166.81005372000556,test,0.4230769230769231,0.06399947993501715,0.4262599469496021,0.0638885259345082,0.42124542124542125,0.06360504978887783 +flat_mae,patch,logistic,aabc_age,85,0.005994842503189409,train,0.6732283464566929,0.02072657042738724,0.6720829641342871,0.020936789486645787,0.6744219527070958,0.020655548343983813 +flat_mae,patch,logistic,aabc_age,85,0.005994842503189409,test,0.4807692307692308,0.057128993457710456,0.46189639667900534,0.06294160699592435,0.4832875457875458,0.057492334840604606 +flat_mae,patch,logistic,aabc_age,86,0.3593813663804626,train,0.9921259842519685,0.004088462783376633,0.9920530784117041,0.004134084032746319,0.9920530784117041,0.004145323987439087 +flat_mae,patch,logistic,aabc_age,86,0.3593813663804626,test,0.46153846153846156,0.06385239774843895,0.4425150519978106,0.06347299500057726,0.4565018315018315,0.06340865467893571 +flat_mae,patch,logistic,aabc_age,87,0.000774263682681127,train,0.5708661417322834,0.02066822606928658,0.5597943909170132,0.021548503794453975,0.5694390368803331,0.02064259180938966 +flat_mae,patch,logistic,aabc_age,87,0.000774263682681127,test,0.5576923076923077,0.06611469100634068,0.5630440348182284,0.06656592297756488,0.55746336996337,0.06620659966531875 +flat_mae,patch,logistic,aabc_age,88,0.000774263682681127,train,0.5590551181102362,0.01980228822033548,0.5498078424078927,0.020430185175303813,0.5595679281687953,0.019725720262722193 +flat_mae,patch,logistic,aabc_age,88,0.000774263682681127,test,0.4807692307692308,0.06926173452796634,0.47990515231894537,0.06979483994551022,0.48054029304029305,0.06935807827386689 +flat_mae,patch,logistic,aabc_age,89,0.005994842503189409,train,0.6850393700787402,0.020021742088047988,0.6836116822347081,0.020276332862159595,0.6867862814520445,0.01992789654534468 +flat_mae,patch,logistic,aabc_age,89,0.005994842503189409,test,0.4807692307692308,0.06929922897186284,0.47686202686202683,0.07003235772013672,0.4775641025641026,0.0691276579233789 +flat_mae,patch,logistic,aabc_age,90,0.046415888336127774,train,0.8149606299212598,0.016591242058345893,0.8142457746799002,0.016889769590807176,0.8162316188105233,0.016585681855557765 +flat_mae,patch,logistic,aabc_age,90,0.046415888336127774,test,0.5961538461538461,0.05702790503483994,0.5714454747416208,0.06095268615659556,0.5927197802197802,0.056834672792501574 +flat_mae,patch,logistic,aabc_age,91,0.005994842503189409,train,0.7007874015748031,0.02048292092451902,0.6999704813410674,0.020573775057966315,0.7017598664336993,0.02041678551290491 +flat_mae,patch,logistic,aabc_age,91,0.005994842503189409,test,0.4807692307692308,0.06521226152537908,0.4744607244607244,0.0680591125147902,0.4819139194139195,0.06539954316997813 +flat_mae,patch,logistic,aabc_age,92,0.005994842503189409,train,0.6771653543307087,0.02049146413266276,0.6751301192536252,0.020786631745643217,0.6784042241013907,0.020461582490591892 +flat_mae,patch,logistic,aabc_age,92,0.005994842503189409,test,0.5192307692307693,0.05401807718460453,0.4902297655000251,0.0607833839983359,0.5215201465201466,0.05443429107957942 +flat_mae,patch,logistic,aabc_age,93,0.005994842503189409,train,0.6968503937007874,0.020400729567334925,0.6968456945302275,0.020537768268127334,0.6980451495908045,0.020413000067039652 +flat_mae,patch,logistic,aabc_age,93,0.005994842503189409,test,0.4230769230769231,0.06064957791918381,0.42324786324786323,0.05854267693855118,0.42376373626373626,0.0609887201686518 +flat_mae,patch,logistic,aabc_age,94,0.000774263682681127,train,0.5807086614173228,0.020494045232988534,0.570066361556064,0.02106540472282468,0.5793021141604445,0.02039622070477544 +flat_mae,patch,logistic,aabc_age,94,0.000774263682681127,test,0.40384615384615385,0.05642027154684847,0.3803973835450696,0.05842386044716697,0.40293040293040294,0.05614933274066714 +flat_mae,patch,logistic,aabc_age,95,0.005994842503189409,train,0.6771653543307087,0.02018094836823468,0.6767068135972499,0.020267151032838913,0.6788217386634547,0.020141476544627248 +flat_mae,patch,logistic,aabc_age,95,0.005994842503189409,test,0.5192307692307693,0.06440775937304154,0.4961777047983944,0.06388298685543525,0.5114468864468864,0.06385924866573221 +flat_mae,patch,logistic,aabc_age,96,0.046415888336127774,train,0.8228346456692913,0.01727085032835795,0.8225692087454708,0.01743101135444351,0.8228231464415244,0.017299279692671327 +flat_mae,patch,logistic,aabc_age,96,0.046415888336127774,test,0.5769230769230769,0.06601751381396845,0.5855797101449275,0.06519329558232398,0.5755494505494505,0.06625625926435108 +flat_mae,patch,logistic,aabc_age,97,0.005994842503189409,train,0.6830708661417323,0.019975004530703156,0.6827845667194158,0.020021826567639924,0.6838998808950707,0.019963004245833204 +flat_mae,patch,logistic,aabc_age,97,0.005994842503189409,test,0.40384615384615385,0.059617853546890316,0.3813681868743048,0.05636496198917753,0.3985805860805861,0.05871491471300625 +flat_mae,patch,logistic,aabc_age,98,0.046415888336127774,train,0.844488188976378,0.01473635458043451,0.8443325080250194,0.014784352255865274,0.8452005124772483,0.014671120222112402 +flat_mae,patch,logistic,aabc_age,98,0.046415888336127774,test,0.4807692307692308,0.06466686365085189,0.4756963981101912,0.06589184995841067,0.4805402930402931,0.06485901701851583 +flat_mae,patch,logistic,aabc_age,99,0.046415888336127774,train,0.8366141732283464,0.015071102689460813,0.8358719148369139,0.01527463627330885,0.83742117209991,0.015003946747982087 +flat_mae,patch,logistic,aabc_age,99,0.046415888336127774,test,0.4807692307692308,0.07053992952083758,0.4843879952575605,0.06876088617730514,0.48489010989010983,0.07110140727267253 +flat_mae,patch,logistic,aabc_age,100,0.005994842503189409,train,0.7047244094488189,0.019742484684846615,0.702240835612524,0.02008789145775288,0.7062948681310883,0.019619070988114766 +flat_mae,patch,logistic,aabc_age,100,0.005994842503189409,test,0.4423076923076923,0.0682261619292602,0.4441880341880342,0.06765897742685888,0.44482600732600736,0.06870829995054614 diff --git a/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_age__patch__logistic/log.txt b/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_age__patch__logistic/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..47f38c47003a8bc6d90bfc8e4ef06217e0c8c467 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_age__patch__logistic/log.txt @@ -0,0 +1,245 @@ +fMRI foundation model logistic probe eval +version: 0.1.dev86+gf97f52698 +sha: bcce2b486277d3a5b520775efd9cdf1a2affce36, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-04-08 22:02:44 +config: +output_root: experiments/input_space_v3/output +name_prefix: eval_logistic +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_1; eval v2 (aabc_age patch logistic) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: input_space_v3/flat_lr1e-3_1/eval_v2/aabc_age__patch__logistic +model: flat_mae +representation: patch +dataset: aabc_age +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_age__patch__logistic +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=True, reg_tokens=0, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: aabc_age (flat) +train (n=455): +HFDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'segment', 'bold', 'mean', 'std'], + num_rows: 471 +}), + labels=[0 1 2 3], + counts=[110 127 109 109] +) + +validation (n=53): +HFDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'segment', 'bold', 'mean', 'std'], + num_rows: 58 +}), + labels=[0 1 2 3], + counts=[14 13 12 14] +) + +test (n=52): +HFDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'segment', 'bold', 'mean', 'std'], + num_rows: 55 +}), + labels=[0 1 2 3], + counts=[13 13 12 14] +) + +extracting features for all splits +extract (train) [ 0/228] eta: 0:25:43 time: 6.7706 data: 6.0049 max mem: 3205 +extract (train) [ 20/228] eta: 0:02:07 time: 0.3051 data: 0.1156 max mem: 3393 +extract (train) [ 40/228] eta: 0:01:22 time: 0.2569 data: 0.0915 max mem: 3393 +extract (train) [ 60/228] eta: 0:01:03 time: 0.2573 data: 0.0926 max mem: 3393 +extract (train) [ 80/228] eta: 0:00:51 time: 0.2626 data: 0.0968 max mem: 3393 +extract (train) [100/228] eta: 0:00:42 time: 0.2423 data: 0.0864 max mem: 3393 +extract (train) [120/228] eta: 0:00:34 time: 0.2490 data: 0.0906 max mem: 3393 +extract (train) [140/228] eta: 0:00:26 time: 0.2408 data: 0.0831 max mem: 3393 +extract (train) [160/228] eta: 0:00:20 time: 0.2388 data: 0.0828 max mem: 3393 +extract (train) [180/228] eta: 0:00:13 time: 0.2322 data: 0.0802 max mem: 3393 +extract (train) [200/228] eta: 0:00:07 time: 0.2429 data: 0.0851 max mem: 3393 +extract (train) [220/228] eta: 0:00:02 time: 0.1967 data: 0.0612 max mem: 3393 +extract (train) [227/228] eta: 0:00:00 time: 0.1916 data: 0.0603 max mem: 3393 +extract (train) Total time: 0:01:03 (0.2770 s / it) +extract (validation) [ 0/27] eta: 0:02:31 time: 5.5954 data: 5.4284 max mem: 3393 +extract (validation) [20/27] eta: 0:00:03 time: 0.2306 data: 0.0770 max mem: 3393 +extract (validation) [26/27] eta: 0:00:00 time: 0.2039 data: 0.0672 max mem: 3393 +extract (validation) Total time: 0:00:11 (0.4367 s / it) +extract (test) [ 0/26] eta: 0:02:25 time: 5.5801 data: 5.3749 max mem: 3393 +extract (test) [20/26] eta: 0:00:02 time: 0.2225 data: 0.0705 max mem: 3393 +extract (test) [25/26] eta: 0:00:00 time: 0.2005 data: 0.0594 max mem: 3393 +extract (test) Total time: 0:00:11 (0.4333 s / it) +feature extraction time: 0:01:26 +train features: (455, 768) +validation features: (53, 768) +test features: (52, 768) +evaluating fixed splits +eval results (fixed splits): + +| model | repr | clf | dataset | trial | C | split | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|-------:|:--------|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | aabc_age | | 21.544 | train | 1 | 0 | 1 | 0 | 1 | 0 | +| flat_mae | patch | logistic | aabc_age | | 21.544 | test | 0.36538 | 0.060363 | 0.36134 | 0.059764 | 0.35783 | 0.060086 | + + +evaluating random splits (n=100) +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 1, "C": 0.046415888336127774, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.06382218039254983, "f1": 0.5163817663817664, "f1_std": 0.06335767788589786, "bacc": 0.5187728937728938, "bacc_std": 0.06358161483130018} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 2, "C": 0.000774263682681127, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.06333437142302982, "f1": 0.6053304979620769, "f1_std": 0.06564534145894432, "bacc": 0.6094322344322344, "bacc_std": 0.06321334770106317} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 3, "C": 0.046415888336127774, "split": "test", "acc": 0.5576923076923077, "acc_std": 0.06691435619572796, "f1": 0.5465201465201465, "f1_std": 0.06852409227187303, "bacc": 0.5517399267399268, "bacc_std": 0.06692031653594371} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 4, "C": 0.005994842503189409, "split": "test", "acc": 0.5576923076923077, "acc_std": 0.06394657302141711, "f1": 0.5443438003220612, "f1_std": 0.06744043895073963, "bacc": 0.5588369963369964, "bacc_std": 0.06421714292071055} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 5, "C": 0.046415888336127774, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.06289843414387579, "f1": 0.4297745358090186, "f1_std": 0.06353943028089844, "bacc": 0.44024725274725274, "bacc_std": 0.06273416974216957} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 6, "C": 0.005994842503189409, "split": "test", "acc": 0.5769230769230769, "acc_std": 0.06281252042302944, "f1": 0.5650174912543728, "f1_std": 0.06641467250436271, "bacc": 0.5780677655677656, "bacc_std": 0.06319855939422216} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 7, "C": 0.046415888336127774, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.06506055440622198, "f1": 0.5255749902826364, "f1_std": 0.06416718757348683, "bacc": 0.5309065934065934, "bacc_std": 0.06475540588526522} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 8, "C": 0.000774263682681127, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.05916609856104179, "f1": 0.4214993717716041, "f1_std": 0.05698006354679332, "bacc": 0.4297161172161172, "bacc_std": 0.06054243022336343} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 9, "C": 0.005994842503189409, "split": "test", "acc": 0.5, "acc_std": 0.06431068266878719, "f1": 0.47665983956306535, "f1_std": 0.06563334516295799, "bacc": 0.4935897435897436, "bacc_std": 0.0637415472602576} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 10, "C": 0.000774263682681127, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.06665617644290861, "f1": 0.5147619047619048, "f1_std": 0.06698588085121501, "bacc": 0.516025641025641, "bacc_std": 0.06645645813581935} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 11, "C": 0.046415888336127774, "split": "test", "acc": 0.5961538461538461, "acc_std": 0.06694698953861947, "f1": 0.6045698924731182, "f1_std": 0.06604406096257033, "bacc": 0.5977564102564102, "bacc_std": 0.06686124645128659} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 12, "C": 0.005994842503189409, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.06327520430065746, "f1": 0.4210717443476064, "f1_std": 0.06344491271792675, "bacc": 0.4255952380952381, "bacc_std": 0.06359159341364597} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 13, "C": 0.005994842503189409, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.06244376168025967, "f1": 0.4363154960981048, "f1_std": 0.06252062985517931, "bacc": 0.44459706959706957, "bacc_std": 0.06305813109101174} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 14, "C": 0.046415888336127774, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.06716995797555533, "f1": 0.6167628667628667, "f1_std": 0.0678016033270939, "bacc": 0.6185897435897435, "bacc_std": 0.06689950578815797} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 15, "C": 0.046415888336127774, "split": "test", "acc": 0.38461538461538464, "acc_std": 0.06615316412886352, "f1": 0.3885856494552147, "f1_std": 0.06554809449461915, "bacc": 0.38278388278388276, "bacc_std": 0.0660921684944768} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 16, "C": 0.046415888336127774, "split": "test", "acc": 0.5, "acc_std": 0.06839100731570492, "f1": 0.4976731601731602, "f1_std": 0.06932336617339238, "bacc": 0.49977106227106227, "bacc_std": 0.06832329483935812} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 17, "C": 0.005994842503189409, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.058383994625259804, "f1": 0.5062760802261408, "f1_std": 0.06077896748856684, "bacc": 0.532051282051282, "bacc_std": 0.057477522015765586} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 18, "C": 0.046415888336127774, "split": "test", "acc": 0.40384615384615385, "acc_std": 0.06002310945493455, "f1": 0.3941356918943126, "f1_std": 0.061362704181427925, "bacc": 0.40453296703296704, "bacc_std": 0.06028452492418795} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 19, "C": 21.54434690031882, "split": "test", "acc": 0.40384615384615385, "acc_std": 0.06797062539921024, "f1": 0.4119738326189939, "f1_std": 0.06722622223116158, "bacc": 0.40773809523809523, "bacc_std": 0.06864506091029224} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 20, "C": 0.005994842503189409, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.0632633735890667, "f1": 0.5132348551278942, "f1_std": 0.06837362271891072, "bacc": 0.5364010989010989, "bacc_std": 0.06315095823210158} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 21, "C": 0.046415888336127774, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.06672449538230821, "f1": 0.5067534414610876, "f1_std": 0.06820480327094554, "bacc": 0.5247252747252746, "bacc_std": 0.06719454379018638} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 22, "C": 0.005994842503189409, "split": "test", "acc": 0.38461538461538464, "acc_std": 0.06376078630178963, "f1": 0.39570099976749595, "f1_std": 0.06261176625297372, "bacc": 0.38713369963369965, "bacc_std": 0.06415886757288594} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 23, "C": 2.782559402207126, "split": "test", "acc": 0.5576923076923077, "acc_std": 0.061669331996347575, "f1": 0.5513498806152479, "f1_std": 0.06245205867664573, "bacc": 0.5544871794871794, "bacc_std": 0.06173051846176813} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 24, "C": 0.005994842503189409, "split": "test", "acc": 0.40384615384615385, "acc_std": 0.06297941572239082, "f1": 0.4112091356918943, "f1_std": 0.060948264220029136, "bacc": 0.40315934065934067, "bacc_std": 0.0629689505010752} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 25, "C": 0.005994842503189409, "split": "test", "acc": 0.3076923076923077, "acc_std": 0.06189391334271682, "f1": 0.2983508245877061, "f1_std": 0.0609351906339869, "bacc": 0.3054029304029304, "bacc_std": 0.061510460212664674} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 26, "C": 0.000774263682681127, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.06706457190449908, "f1": 0.48065476190476186, "f1_std": 0.06709257511923554, "bacc": 0.4789377289377289, "bacc_std": 0.06705789049687207} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 27, "C": 0.005994842503189409, "split": "test", "acc": 0.36538461538461536, "acc_std": 0.05952121594800457, "f1": 0.3388888888888889, "f1_std": 0.059593719879657246, "bacc": 0.3603479853479853, "bacc_std": 0.05875415716473792} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 28, "C": 21.54434690031882, "split": "test", "acc": 0.5, "acc_std": 0.07070418206122425, "f1": 0.50118161408484, "f1_std": 0.07152315363771392, "bacc": 0.4983974358974359, "bacc_std": 0.07078048757275869} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 29, "C": 0.046415888336127774, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.059506488632325744, "f1": 0.42040312628547927, "f1_std": 0.06048151234299964, "bacc": 0.42124542124542125, "bacc_std": 0.059663690730506196} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 30, "C": 0.046415888336127774, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.06960661865761578, "f1": 0.5480895915678524, "f1_std": 0.06783011372874352, "bacc": 0.5368589743589743, "bacc_std": 0.06928927725159015} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 31, "C": 9.999999999999999e-05, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.05624885271676803, "f1": 0.4540354147250699, "f1_std": 0.047472912564200456, "bacc": 0.5068681318681318, "bacc_std": 0.054819871130277656} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 32, "C": 0.046415888336127774, "split": "test", "acc": 0.5, "acc_std": 0.06922490359766859, "f1": 0.5083541178719396, "f1_std": 0.06705369910535389, "bacc": 0.4981684981684981, "bacc_std": 0.06916124365643214} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 33, "C": 0.005994842503189409, "split": "test", "acc": 0.5576923076923077, "acc_std": 0.06274880653760269, "f1": 0.5610095723242274, "f1_std": 0.06465646512953763, "bacc": 0.5576923076923077, "bacc_std": 0.0632548012818985} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 34, "C": 0.005994842503189409, "split": "test", "acc": 0.40384615384615385, "acc_std": 0.06955398907646998, "f1": 0.4125000000000001, "f1_std": 0.07032608628085507, "bacc": 0.4049908424908425, "bacc_std": 0.06970072394267178} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 35, "C": 0.046415888336127774, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.062425387416361625, "f1": 0.4656707875457875, "f1_std": 0.062169629914232034, "bacc": 0.4610805860805861, "bacc_std": 0.062431976485544854} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 36, "C": 0.3593813663804626, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.06387972935513431, "f1": 0.4251851851851852, "f1_std": 0.06387688715209074, "bacc": 0.4301739926739927, "bacc_std": 0.06462439265304444} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 37, "C": 0.005994842503189409, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.06472485004245086, "f1": 0.44462962962962965, "f1_std": 0.06430924120218762, "bacc": 0.4537545787545788, "bacc_std": 0.06416886722791552} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 38, "C": 2.782559402207126, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.06396812954615085, "f1": 0.44372605363984674, "f1_std": 0.062336404253656115, "bacc": 0.43887362637362637, "bacc_std": 0.06389709105117665} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 39, "C": 0.046415888336127774, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.0682155910617604, "f1": 0.5214135821552701, "f1_std": 0.06805862951942754, "bacc": 0.5146520146520146, "bacc_std": 0.06819533668891838} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 40, "C": 0.3593813663804626, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.05999727557917174, "f1": 0.4227193942711184, "f1_std": 0.05889417929488195, "bacc": 0.440018315018315, "bacc_std": 0.059557013238407605} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 41, "C": 0.005994842503189409, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.06537840468240692, "f1": 0.4168183765260227, "f1_std": 0.0653083792042069, "bacc": 0.42239010989010994, "bacc_std": 0.06546727874878863} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 42, "C": 0.046415888336127774, "split": "test", "acc": 0.5, "acc_std": 0.06070346977400509, "f1": 0.483199309436191, "f1_std": 0.06309919666705456, "bacc": 0.5070970695970696, "bacc_std": 0.06143006604987377} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 43, "C": 0.005994842503189409, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.06890307058538592, "f1": 0.5362292277614858, "f1_std": 0.06993228159978784, "bacc": 0.535485347985348, "bacc_std": 0.06915418324166912} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 44, "C": 0.005994842503189409, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.07066014795396157, "f1": 0.5317252088241593, "f1_std": 0.07300227939327764, "bacc": 0.535485347985348, "bacc_std": 0.07088418051073271} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 45, "C": 0.046415888336127774, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.06554166658829784, "f1": 0.45767877284006314, "f1_std": 0.06696799112587501, "bacc": 0.4640567765567766, "bacc_std": 0.06592212970025227} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 46, "C": 0.000774263682681127, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.06260971435297359, "f1": 0.5007352941176471, "f1_std": 0.06797521113831917, "bacc": 0.5157967032967032, "bacc_std": 0.06255393475139216} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 47, "C": 0.005994842503189409, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.06422818972250102, "f1": 0.47290805267663616, "f1_std": 0.06760285137187264, "bacc": 0.4819139194139195, "bacc_std": 0.06422892974493875} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 48, "C": 0.000774263682681127, "split": "test", "acc": 0.5, "acc_std": 0.06322004166907083, "f1": 0.48747771836007125, "f1_std": 0.06712906565533484, "bacc": 0.4965659340659341, "bacc_std": 0.06290293262931561} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 49, "C": 1291.5496650148827, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.06361752391528946, "f1": 0.42653985507246384, "f1_std": 0.06439140355658643, "bacc": 0.4212454212454212, "bacc_std": 0.06362258173389435} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 50, "C": 0.000774263682681127, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.06578007108143993, "f1": 0.46030695708115066, "f1_std": 0.06754350508223267, "bacc": 0.4597069597069597, "bacc_std": 0.06593200663247284} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 51, "C": 0.005994842503189409, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.06972278158671918, "f1": 0.46011904761904765, "f1_std": 0.07006874477963, "bacc": 0.4626831501831502, "bacc_std": 0.0698980896947373} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 52, "C": 0.046415888336127774, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.06570206872176497, "f1": 0.44664835164835165, "f1_std": 0.06519118434775434, "bacc": 0.4494047619047619, "bacc_std": 0.06625525765351573} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 53, "C": 9.999999999999999e-05, "split": "test", "acc": 0.5, "acc_std": 0.058569788443729204, "f1": 0.45706605222734253, "f1_std": 0.05766571594240479, "bacc": 0.4933608058608059, "bacc_std": 0.057686464215084124} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 54, "C": 0.3593813663804626, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.06528973885688318, "f1": 0.4272486772486772, "f1_std": 0.0650540185946747, "bacc": 0.4491758241758242, "bacc_std": 0.06589996376560961} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 55, "C": 0.000774263682681127, "split": "test", "acc": 0.5, "acc_std": 0.06364026115782906, "f1": 0.4964269509981851, "f1_std": 0.06607775239783045, "bacc": 0.4981684981684982, "bacc_std": 0.06383607529032104} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 56, "C": 0.000774263682681127, "split": "test", "acc": 0.40384615384615385, "acc_std": 0.06090387955113121, "f1": 0.38267682781614676, "f1_std": 0.061091420333888626, "bacc": 0.40293040293040294, "bacc_std": 0.06088914447362108} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 57, "C": 0.046415888336127774, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.06722284762343493, "f1": 0.4432848186296462, "f1_std": 0.06549792702549874, "bacc": 0.44024725274725274, "bacc_std": 0.06695736816435065} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 58, "C": 0.046415888336127774, "split": "test", "acc": 0.36538461538461536, "acc_std": 0.05302862908805563, "f1": 0.3431077694235589, "f1_std": 0.055157960279206004, "bacc": 0.3630952380952381, "bacc_std": 0.052427761580892664} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 59, "C": 0.046415888336127774, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.0694811178641001, "f1": 0.48645962732919257, "f1_std": 0.06966005342767094, "bacc": 0.4821428571428571, "bacc_std": 0.06957404383418024} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 60, "C": 0.005994842503189409, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.061496752692446914, "f1": 0.4130668536699392, "f1_std": 0.0661015907274849, "bacc": 0.42399267399267393, "bacc_std": 0.06177799988187703} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 61, "C": 0.3593813663804626, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.06856409776959499, "f1": 0.42727272727272725, "f1_std": 0.06976702940717863, "bacc": 0.421474358974359, "bacc_std": 0.0686159254300565} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 62, "C": 0.046415888336127774, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.06044749298592973, "f1": 0.6094179894179894, "f1_std": 0.06270773991181341, "bacc": 0.6167582417582418, "bacc_std": 0.060786699415631334} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 63, "C": 0.005994842503189409, "split": "test", "acc": 0.40384615384615385, "acc_std": 0.05170918909329744, "f1": 0.3606584047760518, "f1_std": 0.05033279643743934, "bacc": 0.4056776556776557, "bacc_std": 0.05233210803663641} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 64, "C": 2.782559402207126, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.06798994878726322, "f1": 0.4277370777370777, "f1_std": 0.06798982603027305, "bacc": 0.4212454212454212, "bacc_std": 0.06804398290494236} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 65, "C": 21.54434690031882, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.06672245570027048, "f1": 0.4395120621507428, "f1_std": 0.0667954116334929, "bacc": 0.43887362637362637, "bacc_std": 0.06657890631154557} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 66, "C": 0.005994842503189409, "split": "test", "acc": 0.36538461538461536, "acc_std": 0.06512055275051452, "f1": 0.37008152173913045, "f1_std": 0.06569686596652159, "bacc": 0.36492673992673996, "bacc_std": 0.06520679518127023} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 67, "C": 0.046415888336127774, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.06246488954633237, "f1": 0.484375, "f1_std": 0.06733354651167807, "bacc": 0.5114468864468864, "bacc_std": 0.06187806704069776} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 68, "C": 0.005994842503189409, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.061081912216301805, "f1": 0.5044726533213375, "f1_std": 0.06357814825377892, "bacc": 0.5171703296703297, "bacc_std": 0.06110720271700992} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 69, "C": 0.046415888336127774, "split": "test", "acc": 0.38461538461538464, "acc_std": 0.06450842796182922, "f1": 0.39001322751322753, "f1_std": 0.06209113885067869, "bacc": 0.3914835164835164, "bacc_std": 0.0655137920413032} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 70, "C": 0.000774263682681127, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.06199656413461186, "f1": 0.40388605923410675, "f1_std": 0.06228256920221505, "bacc": 0.41804029304029305, "bacc_std": 0.06155384903195036} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 71, "C": 0.046415888336127774, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.06680179106836005, "f1": 0.4832671957671958, "f1_std": 0.06689683060986362, "bacc": 0.4819139194139194, "bacc_std": 0.06713709366606323} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 72, "C": 0.005994842503189409, "split": "test", "acc": 0.5961538461538461, "acc_std": 0.06386249790803093, "f1": 0.5935057471264368, "f1_std": 0.06556177178337477, "bacc": 0.5918040293040293, "bacc_std": 0.06417585374694068} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 73, "C": 0.3593813663804626, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.05655979451014286, "f1": 0.4208791208791209, "f1_std": 0.05641669570313965, "bacc": 0.4285714285714286, "bacc_std": 0.0574239782145545} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 74, "C": 0.3593813663804626, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.06619278818043996, "f1": 0.4999019607843137, "f1_std": 0.06510359481439482, "bacc": 0.4821428571428571, "bacc_std": 0.06633390190152014} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 75, "C": 0.005994842503189409, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.06895672255696914, "f1": 0.5215488215488215, "f1_std": 0.07042901852894937, "bacc": 0.521978021978022, "bacc_std": 0.0692248221588424} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 76, "C": 0.046415888336127774, "split": "test", "acc": 0.5, "acc_std": 0.06605729761386955, "f1": 0.4972145096283027, "f1_std": 0.06688719128163513, "bacc": 0.4981684981684982, "bacc_std": 0.06603064922320297} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 77, "C": 0.046415888336127774, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.06754655418486216, "f1": 0.42564935064935067, "f1_std": 0.0680292576946857, "bacc": 0.42559523809523814, "bacc_std": 0.06789706072309044} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 78, "C": 0.3593813663804626, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.06911961161681374, "f1": 0.4478787878787879, "f1_std": 0.06981667834330604, "bacc": 0.4420787545787546, "bacc_std": 0.06928195283143487} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 79, "C": 166.81005372000556, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.06731301077888542, "f1": 0.42698611733094494, "f1_std": 0.0677557644893142, "bacc": 0.42422161172161177, "bacc_std": 0.06728303171992643} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 80, "C": 0.005994842503189409, "split": "test", "acc": 0.5, "acc_std": 0.06270320811324016, "f1": 0.48544973544973546, "f1_std": 0.06503867304384674, "bacc": 0.49793956043956045, "bacc_std": 0.06264079289247888} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 81, "C": 21.54434690031882, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.061875088906755804, "f1": 0.45633533133533133, "f1_std": 0.06205250579903118, "bacc": 0.4567307692307693, "bacc_std": 0.06167989135587098} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 82, "C": 0.005994842503189409, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.0704954885459023, "f1": 0.5388810970858656, "f1_std": 0.07105629896518642, "bacc": 0.5382326007326008, "bacc_std": 0.07068349530476242} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 83, "C": 166.81005372000556, "split": "test", "acc": 0.38461538461538464, "acc_std": 0.061896685728252146, "f1": 0.37731481481481477, "f1_std": 0.061236236842725916, "bacc": 0.3823260073260073, "bacc_std": 0.061717901546825986} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 84, "C": 166.81005372000556, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.06399947993501715, "f1": 0.4262599469496021, "f1_std": 0.0638885259345082, "bacc": 0.42124542124542125, "bacc_std": 0.06360504978887783} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 85, "C": 0.005994842503189409, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.057128993457710456, "f1": 0.46189639667900534, "f1_std": 0.06294160699592435, "bacc": 0.4832875457875458, "bacc_std": 0.057492334840604606} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 86, "C": 0.3593813663804626, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.06385239774843895, "f1": 0.4425150519978106, "f1_std": 0.06347299500057726, "bacc": 0.4565018315018315, "bacc_std": 0.06340865467893571} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 87, "C": 0.000774263682681127, "split": "test", "acc": 0.5576923076923077, "acc_std": 0.06611469100634068, "f1": 0.5630440348182284, "f1_std": 0.06656592297756488, "bacc": 0.55746336996337, "bacc_std": 0.06620659966531875} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 88, "C": 0.000774263682681127, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.06926173452796634, "f1": 0.47990515231894537, "f1_std": 0.06979483994551022, "bacc": 0.48054029304029305, "bacc_std": 0.06935807827386689} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 89, "C": 0.005994842503189409, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.06929922897186284, "f1": 0.47686202686202683, "f1_std": 0.07003235772013672, "bacc": 0.4775641025641026, "bacc_std": 0.0691276579233789} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 90, "C": 0.046415888336127774, "split": "test", "acc": 0.5961538461538461, "acc_std": 0.05702790503483994, "f1": 0.5714454747416208, "f1_std": 0.06095268615659556, "bacc": 0.5927197802197802, "bacc_std": 0.056834672792501574} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 91, "C": 0.005994842503189409, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.06521226152537908, "f1": 0.4744607244607244, "f1_std": 0.0680591125147902, "bacc": 0.4819139194139195, "bacc_std": 0.06539954316997813} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 92, "C": 0.005994842503189409, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.05401807718460453, "f1": 0.4902297655000251, "f1_std": 0.0607833839983359, "bacc": 0.5215201465201466, "bacc_std": 0.05443429107957942} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 93, "C": 0.005994842503189409, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.06064957791918381, "f1": 0.42324786324786323, "f1_std": 0.05854267693855118, "bacc": 0.42376373626373626, "bacc_std": 0.0609887201686518} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 94, "C": 0.000774263682681127, "split": "test", "acc": 0.40384615384615385, "acc_std": 0.05642027154684847, "f1": 0.3803973835450696, "f1_std": 0.05842386044716697, "bacc": 0.40293040293040294, "bacc_std": 0.05614933274066714} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 95, "C": 0.005994842503189409, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.06440775937304154, "f1": 0.4961777047983944, "f1_std": 0.06388298685543525, "bacc": 0.5114468864468864, "bacc_std": 0.06385924866573221} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 96, "C": 0.046415888336127774, "split": "test", "acc": 0.5769230769230769, "acc_std": 0.06601751381396845, "f1": 0.5855797101449275, "f1_std": 0.06519329558232398, "bacc": 0.5755494505494505, "bacc_std": 0.06625625926435108} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 97, "C": 0.005994842503189409, "split": "test", "acc": 0.40384615384615385, "acc_std": 0.059617853546890316, "f1": 0.3813681868743048, "f1_std": 0.05636496198917753, "bacc": 0.3985805860805861, "bacc_std": 0.05871491471300625} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 98, "C": 0.046415888336127774, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.06466686365085189, "f1": 0.4756963981101912, "f1_std": 0.06589184995841067, "bacc": 0.4805402930402931, "bacc_std": 0.06485901701851583} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 99, "C": 0.046415888336127774, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.07053992952083758, "f1": 0.4843879952575605, "f1_std": 0.06876088617730514, "bacc": 0.48489010989010983, "bacc_std": 0.07110140727267253} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 100, "C": 0.005994842503189409, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.0682261619292602, "f1": 0.4441880341880342, "f1_std": 0.06765897742685888, "bacc": 0.44482600732600736, "bacc_std": 0.06870829995054614} +eval results (random splits): + +| model | repr | clf | dataset | split | n_trials | C | C_std | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|-----------:|------:|--------:|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | aabc_age | train | 100 | 18.91 | 131.72 | 0.77364 | 0.14316 | 0.77156 | 0.14595 | 0.7742 | 0.14326 | +| flat_mae | patch | logistic | aabc_age | test | 100 | 18.91 | 131.72 | 0.47519 | 0.063886 | 0.46828 | 0.064103 | 0.47433 | 0.063237 | + + +done! total time: 0:05:51 diff --git a/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_sex__patch__attn/config.yaml b/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_sex__patch__attn/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..eccd24b2b7e7f4ce28d147fc7d1f973ede1e8b1d --- /dev/null +++ b/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_sex__patch__attn/config.yaml @@ -0,0 +1,98 @@ +output_root: experiments/input_space_v3/output +name_prefix: eval_probe +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_1; eval v2 (aabc_sex patch attn) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +dataset_kwargs: {} +classifier_kwargs: + embed_dim: null + dropout: 0.0 + xavier_init: true + norm: true +lr_scale_grid: +- 0.02 +- 0.023 +- 0.028 +- 0.033 +- 0.038 +- 0.045 +- 0.053 +- 0.062 +- 0.074 +- 0.087 +- 0.1 +- 0.12 +- 0.14 +- 0.17 +- 0.2 +- 0.23 +- 0.27 +- 0.32 +- 0.38 +- 0.44 +- 0.52 +- 0.61 +- 0.72 +- 0.85 +- 1 +- 1.2 +- 1.4 +- 1.6 +- 1.9 +- 2.3 +- 2.7 +- 3.1 +- 3.7 +- 4.3 +- 5.1 +- 6 +- 7.1 +- 8.3 +- 9.8 +- 12 +- 14 +- 16 +- 19 +- 22 +- 26 +- 31 +- 36 +- 43 +- 50 +wd_scale_grid: +- 1.0 +num_workers: 8 +prefetch_factor: null +balanced_sampling: false +epochs: 20 +steps_per_epoch: 200 +batch_size: 4 +accum_iter: 4 +lr: 0.0003 +warmup_epochs: 5 +no_decay: false +weight_decay: 0.05 +clip_grad: 1.0 +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +early_stopping: true +amp: true +device: cuda +seed: 4466 +debug: false +wandb: false +wandb_entity: null +wandb_project: fMRI-fm-eval +name: input_space_v3/flat_lr1e-3_1/eval_v2/aabc_sex__patch__attn +base_lr: 3.0e-05 +model: flat_mae +representation: patch +classifier: attn +dataset: aabc_sex +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_sex__patch__attn +remote_dir: null diff --git a/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_sex__patch__attn/eval_log.json b/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_sex__patch__attn/eval_log.json new file mode 100644 index 0000000000000000000000000000000000000000..1d5a9907805c43e256d930d670e7a3e08ccde68c --- /dev/null +++ b/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_sex__patch__attn/eval_log.json @@ -0,0 +1 @@ +{"eval/epoch": 3, "eval/id_best": 39, "eval/lr_best": 0.0036, "eval/wd_best": 0.05, "eval/train/loss": 0.02298835664987564, "eval/train/acc": 0.9915074309978769, "eval/train/acc_std": 0.004238634297568672, "eval/train/f1": 0.9913320328315359, "eval/train/f1_std": 0.004326271199507291, "eval/train/bacc": 0.9913320328315359, "eval/train/bacc_std": 0.00435823474598854, "eval/validation/loss": 0.665527880191803, "eval/validation/acc": 0.9482758620689655, "eval/validation/acc_std": 0.029081765905881955, "eval/validation/f1": 0.944568333864288, "eval/validation/f1_std": 0.03151306328333821, "eval/validation/bacc": 0.9406565656565656, "eval/validation/bacc_std": 0.03332909790967508, "eval/test/loss": 0.450775146484375, "eval/test/acc": 0.9272727272727272, "eval/test/acc_std": 0.036165478265630865, "eval/test/f1": 0.9242424242424243, "eval/test/f1_std": 0.037961499120668984, "eval/test/bacc": 0.9242424242424243, "eval/test/bacc_std": 0.03874943644247919} diff --git a/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_sex__patch__attn/eval_log_best.json b/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_sex__patch__attn/eval_log_best.json new file mode 100644 index 0000000000000000000000000000000000000000..2e0c82cfcffc11f9a4e487f68e60a3ca13fc4ef0 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_sex__patch__attn/eval_log_best.json @@ -0,0 +1 @@ +{"eval/best/epoch": 3, "eval/best/id_best": 39, "eval/best/lr_best": 0.0036, "eval/best/wd_best": 0.05, "eval/best/train/loss": 0.02298835664987564, "eval/best/train/acc": 0.9915074309978769, "eval/best/train/acc_std": 0.004238634297568672, "eval/best/train/f1": 0.9913320328315359, "eval/best/train/f1_std": 0.004326271199507291, "eval/best/train/bacc": 0.9913320328315359, "eval/best/train/bacc_std": 0.00435823474598854, "eval/best/validation/loss": 0.665527880191803, "eval/best/validation/acc": 0.9482758620689655, "eval/best/validation/acc_std": 0.029081765905881955, "eval/best/validation/f1": 0.944568333864288, "eval/best/validation/f1_std": 0.03151306328333821, "eval/best/validation/bacc": 0.9406565656565656, "eval/best/validation/bacc_std": 0.03332909790967508, "eval/best/test/loss": 0.450775146484375, "eval/best/test/acc": 0.9272727272727272, "eval/best/test/acc_std": 0.036165478265630865, "eval/best/test/f1": 0.9242424242424243, "eval/best/test/f1_std": 0.037961499120668984, "eval/best/test/bacc": 0.9242424242424243, "eval/best/test/bacc_std": 0.03874943644247919} diff --git a/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_sex__patch__attn/eval_log_last.json b/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_sex__patch__attn/eval_log_last.json new file mode 100644 index 0000000000000000000000000000000000000000..6e554f713b8a4b225b2329834d8d0e7dce6b95b4 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_sex__patch__attn/eval_log_last.json @@ -0,0 +1 @@ +{"eval/last/epoch": 19, "eval/last/id_best": 32, "eval/last/lr_best": 0.0011099999999999999, "eval/last/wd_best": 0.05, "eval/last/train/loss": 0.00010226845188299194, "eval/last/train/acc": 1.0, "eval/last/train/acc_std": 0.0, "eval/last/train/f1": 1.0, "eval/last/train/f1_std": 0.0, "eval/last/train/bacc": 1.0, "eval/last/train/bacc_std": 0.0, "eval/last/validation/loss": 0.704197108745575, "eval/last/validation/acc": 0.9482758620689655, "eval/last/validation/acc_std": 0.029081765905881955, "eval/last/validation/f1": 0.944568333864288, "eval/last/validation/f1_std": 0.03151306328333821, "eval/last/validation/bacc": 0.9406565656565656, "eval/last/validation/bacc_std": 0.03332909790967508, "eval/last/test/loss": 0.7462900876998901, "eval/last/test/acc": 0.8727272727272727, "eval/last/test/acc_std": 0.045455999976728, "eval/last/test/f1": 0.8711943793911007, "eval/last/test/f1_std": 0.045382452322359115, "eval/last/test/bacc": 0.8863636363636365, "eval/last/test/bacc_std": 0.04200079528303858} diff --git a/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_sex__patch__attn/eval_table.csv b/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_sex__patch__attn/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..91c6d9bd8e8e7b5ec4229b41d77e964adb050d23 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_sex__patch__attn/eval_table.csv @@ -0,0 +1,4 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std,bacc,bacc_std +flat_mae,patch,attn,aabc_sex,best,3,0.0036,0.05,39,"[12, 1.0]",train,0.02298835664987564,0.9915074309978769,0.004238634297568672,0.9913320328315359,0.004326271199507291,0.9913320328315359,0.00435823474598854 +flat_mae,patch,attn,aabc_sex,best,3,0.0036,0.05,39,"[12, 1.0]",validation,0.665527880191803,0.9482758620689655,0.029081765905881955,0.944568333864288,0.03151306328333821,0.9406565656565656,0.03332909790967508 +flat_mae,patch,attn,aabc_sex,best,3,0.0036,0.05,39,"[12, 1.0]",test,0.450775146484375,0.9272727272727272,0.036165478265630865,0.9242424242424243,0.037961499120668984,0.9242424242424243,0.03874943644247919 diff --git a/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_sex__patch__attn/eval_table_best.csv b/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_sex__patch__attn/eval_table_best.csv new file mode 100644 index 0000000000000000000000000000000000000000..91c6d9bd8e8e7b5ec4229b41d77e964adb050d23 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_sex__patch__attn/eval_table_best.csv @@ -0,0 +1,4 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std,bacc,bacc_std +flat_mae,patch,attn,aabc_sex,best,3,0.0036,0.05,39,"[12, 1.0]",train,0.02298835664987564,0.9915074309978769,0.004238634297568672,0.9913320328315359,0.004326271199507291,0.9913320328315359,0.00435823474598854 +flat_mae,patch,attn,aabc_sex,best,3,0.0036,0.05,39,"[12, 1.0]",validation,0.665527880191803,0.9482758620689655,0.029081765905881955,0.944568333864288,0.03151306328333821,0.9406565656565656,0.03332909790967508 +flat_mae,patch,attn,aabc_sex,best,3,0.0036,0.05,39,"[12, 1.0]",test,0.450775146484375,0.9272727272727272,0.036165478265630865,0.9242424242424243,0.037961499120668984,0.9242424242424243,0.03874943644247919 diff --git a/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_sex__patch__attn/eval_table_last.csv b/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_sex__patch__attn/eval_table_last.csv new file mode 100644 index 0000000000000000000000000000000000000000..fc6ff8dff0d7019b3294e10a86ca5e985c4e1f93 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_sex__patch__attn/eval_table_last.csv @@ -0,0 +1,4 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std,bacc,bacc_std +flat_mae,patch,attn,aabc_sex,last,19,0.0011099999999999999,0.05,32,"[3.7, 1.0]",train,0.00010226845188299194,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,attn,aabc_sex,last,19,0.0011099999999999999,0.05,32,"[3.7, 1.0]",validation,0.704197108745575,0.9482758620689655,0.029081765905881955,0.944568333864288,0.03151306328333821,0.9406565656565656,0.03332909790967508 +flat_mae,patch,attn,aabc_sex,last,19,0.0011099999999999999,0.05,32,"[3.7, 1.0]",test,0.7462900876998901,0.8727272727272727,0.045455999976728,0.8711943793911007,0.045382452322359115,0.8863636363636365,0.04200079528303858 diff --git a/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_sex__patch__attn/log.txt b/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_sex__patch__attn/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..26acec9a68b3ea3a5c146d1f8b18837ecb6f6233 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_sex__patch__attn/log.txt @@ -0,0 +1,1197 @@ +fMRI foundation model probe eval +version: 0.1.dev95+g65be98d36 +sha: 28a47a6a336052f679e36c7962a91fe73a2e9637, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-04-24 08:34:37 +config: +output_root: experiments/input_space_v3/output +name_prefix: eval_probe +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_1; eval v2 (aabc_sex patch attn) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +dataset_kwargs: {} +classifier_kwargs: + embed_dim: null + dropout: 0.0 + xavier_init: true + norm: true +lr_scale_grid: +- 0.02 +- 0.023 +- 0.028 +- 0.033 +- 0.038 +- 0.045 +- 0.053 +- 0.062 +- 0.074 +- 0.087 +- 0.1 +- 0.12 +- 0.14 +- 0.17 +- 0.2 +- 0.23 +- 0.27 +- 0.32 +- 0.38 +- 0.44 +- 0.52 +- 0.61 +- 0.72 +- 0.85 +- 1 +- 1.2 +- 1.4 +- 1.6 +- 1.9 +- 2.3 +- 2.7 +- 3.1 +- 3.7 +- 4.3 +- 5.1 +- 6 +- 7.1 +- 8.3 +- 9.8 +- 12 +- 14 +- 16 +- 19 +- 22 +- 26 +- 31 +- 36 +- 43 +- 50 +wd_scale_grid: +- 1.0 +num_workers: 8 +prefetch_factor: null +balanced_sampling: false +epochs: 20 +steps_per_epoch: 200 +batch_size: 4 +accum_iter: 4 +lr: 0.0003 +warmup_epochs: 5 +no_decay: false +weight_decay: 0.05 +clip_grad: 1.0 +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +early_stopping: true +amp: true +device: cuda +seed: 4466 +debug: false +wandb: false +wandb_entity: null +wandb_project: fMRI-fm-eval +name: input_space_v3/flat_lr1e-3_1/eval_v2/aabc_sex__patch__attn +base_lr: 3.0e-05 +model: flat_mae +representation: patch +classifier: attn +dataset: aabc_sex +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_sex__patch__attn +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=True, reg_tokens=0, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: aabc_sex (flat) +train (n=471): +HFDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'segment', 'bold', 'mean', 'std'], + num_rows: 471 +}), + labels=[0 1], + counts=[269 202] +) + +validation (n=58): +HFDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'segment', 'bold', 'mean', 'std'], + num_rows: 58 +}), + labels=[0 1], + counts=[36 22] +) + +test (n=55): +HFDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'segment', 'bold', 'mean', 'std'], + num_rows: 55 +}), + labels=[0 1], + counts=[33 22] +) + +running backbone on example batch to get embedding dim +embedding feature dim (patch): 768 +initializing sweep of classifier heads +classifiers: +ModuleList( + (0-48): 49 x AttnPoolClassifier( + (kv): Linear(in_features=768, out_features=1536, bias=True) + (linear): Linear(in_features=768, out_features=2, bias=True) + ) +) +classifier params (train): 58.0M (58.0M) +setting up optimizer +total batch size: 16 = 4 bs per gpu x 4 accum +lr: 3.00e-04 +full schedule: epochs = 20 (steps = 4000) (decay = True) +warmup: epochs = 5 (steps = 1000) +start training for 20 epochs +train: [0] [ 0/800] eta: 1:17:09 lr: nan time: 5.7868 data: 5.0422 max mem: 29565 +train: [0] [ 20/800] eta: 0:11:46 lr: 0.000001 loss: 0.6855 (0.6848) grad: 0.3107 (0.3422) time: 0.6618 data: 0.0505 max mem: 30262 +train: [0] [ 40/800] eta: 0:10:02 lr: 0.000003 loss: 0.6836 (0.6849) grad: 0.2334 (0.3009) time: 0.6737 data: 0.0035 max mem: 30262 +train: [0] [ 60/800] eta: 0:09:07 lr: 0.000004 loss: 0.6784 (0.6740) grad: 0.3107 (0.3216) time: 0.6304 data: 0.0033 max mem: 30262 +train: [0] [ 80/800] eta: 0:08:30 lr: 0.000006 loss: 0.6855 (0.6836) grad: 0.2708 (0.3004) time: 0.6141 data: 0.0033 max mem: 30262 +train: [0] [100/800] eta: 0:08:04 lr: 0.000007 loss: 0.6861 (0.6838) grad: 0.2708 (0.2951) time: 0.6228 data: 0.0033 max mem: 30262 +train: [0] [120/800] eta: 0:08:14 lr: 0.000009 loss: 0.6819 (0.6822) grad: 0.2708 (0.2848) time: 0.9095 data: 0.2839 max mem: 30262 +train: [0] [140/800] eta: 0:07:55 lr: 0.000010 loss: 0.6800 (0.6745) grad: 0.2159 (0.2723) time: 0.6748 data: 0.0472 max mem: 30262 +train: [0] [160/800] eta: 0:07:34 lr: 0.000012 loss: 0.6543 (0.6736) grad: 0.2159 (0.2805) time: 0.6377 data: 0.0028 max mem: 30262 +train: [0] [180/800] eta: 0:07:16 lr: 0.000013 loss: 0.6397 (0.6631) grad: 0.1995 (0.2785) time: 0.6522 data: 0.0316 max mem: 30262 +train: [0] [200/800] eta: 0:06:56 lr: 0.000015 loss: 0.6304 (0.6543) grad: 0.1995 (0.2717) time: 0.6064 data: 0.0025 max mem: 30262 +train: [0] [220/800] eta: 0:06:38 lr: 0.000016 loss: 0.5944 (0.6487) grad: 0.1995 (0.2678) time: 0.6171 data: 0.0030 max mem: 30262 +train: [0] [240/800] eta: 0:06:34 lr: 0.000018 loss: 0.5699 (0.6442) grad: 0.1983 (0.2630) time: 0.9049 data: 0.3058 max mem: 30262 +train: [0] [260/800] eta: 0:06:21 lr: 0.000019 loss: 0.5496 (0.6396) grad: 0.1953 (0.2622) time: 0.7171 data: 0.0847 max mem: 30262 +train: [0] [280/800] eta: 0:06:04 lr: 0.000021 loss: 0.5699 (0.6335) grad: 0.2036 (0.2637) time: 0.6339 data: 0.0030 max mem: 30262 +train: [0] [300/800] eta: 0:05:47 lr: 0.000022 loss: 0.5725 (0.6313) grad: 0.2036 (0.2602) time: 0.6148 data: 0.0036 max mem: 30262 +train: [0] [320/800] eta: 0:05:31 lr: 0.000024 loss: 0.5482 (0.6270) grad: 0.2072 (0.2628) time: 0.6249 data: 0.0038 max mem: 30262 +train: [0] [340/800] eta: 0:05:15 lr: 0.000025 loss: 0.5717 (0.6279) grad: 0.2072 (0.2621) time: 0.6145 data: 0.0027 max mem: 30262 +train: [0] [360/800] eta: 0:05:07 lr: 0.000027 loss: 0.5482 (0.6195) grad: 0.2063 (0.2606) time: 0.8990 data: 0.2919 max mem: 30262 +train: [0] [380/800] eta: 0:04:51 lr: 0.000028 loss: 0.5374 (0.6156) grad: 0.2003 (0.2595) time: 0.6172 data: 0.0084 max mem: 30262 +train: [0] [400/800] eta: 0:04:36 lr: 0.000030 loss: 0.5374 (0.6132) grad: 0.1839 (0.2564) time: 0.6600 data: 0.0480 max mem: 30262 +train: [0] [420/800] eta: 0:04:22 lr: 0.000031 loss: 0.5374 (0.6126) grad: 0.1839 (0.2543) time: 0.6723 data: 0.0024 max mem: 30262 +train: [0] [440/800] eta: 0:04:07 lr: 0.000033 loss: 0.5380 (0.6092) grad: 0.1756 (0.2556) time: 0.6253 data: 0.0029 max mem: 30262 +train: [0] [460/800] eta: 0:03:52 lr: 0.000034 loss: 0.5249 (0.6044) grad: 0.1907 (0.2538) time: 0.6091 data: 0.0035 max mem: 30262 +train: [0] [480/800] eta: 0:03:43 lr: 0.000036 loss: 0.4705 (0.5988) grad: 0.1907 (0.2510) time: 0.9893 data: 0.3911 max mem: 30262 +train: [0] [500/800] eta: 0:03:29 lr: 0.000037 loss: 0.5096 (0.5985) grad: 0.2007 (0.2516) time: 0.6881 data: 0.0597 max mem: 30262 +train: [0] [520/800] eta: 0:03:14 lr: 0.000039 loss: 0.5096 (0.5936) grad: 0.2118 (0.2553) time: 0.6208 data: 0.0230 max mem: 30262 +train: [0] [540/800] eta: 0:02:59 lr: 0.000040 loss: 0.5139 (0.5906) grad: 0.2336 (0.2552) time: 0.6109 data: 0.0023 max mem: 30262 +train: [0] [560/800] eta: 0:02:45 lr: 0.000042 loss: 0.5139 (0.5885) grad: 0.2336 (0.2543) time: 0.6261 data: 0.0033 max mem: 30262 +train: [0] [580/800] eta: 0:02:30 lr: 0.000043 loss: 0.4803 (0.5850) grad: 0.2052 (0.2513) time: 0.6007 data: 0.0027 max mem: 30262 +train: [0] [600/800] eta: 0:02:19 lr: 0.000045 loss: 0.4664 (0.5812) grad: 0.1858 (0.2520) time: 1.0836 data: 0.3907 max mem: 30262 +train: [0] [620/800] eta: 0:02:05 lr: 0.000046 loss: 0.4803 (0.5811) grad: 0.1858 (0.2540) time: 0.6552 data: 0.0033 max mem: 30262 +train: [0] [640/800] eta: 0:01:51 lr: 0.000048 loss: 0.4695 (0.5769) grad: 0.1876 (0.2541) time: 0.6115 data: 0.0023 max mem: 30262 +train: [0] [660/800] eta: 0:01:37 lr: 0.000049 loss: 0.4209 (0.5723) grad: 0.1789 (0.2508) time: 0.6928 data: 0.0844 max mem: 30262 +train: [0] [680/800] eta: 0:01:23 lr: 0.000051 loss: 0.4764 (0.5717) grad: 0.1623 (0.2484) time: 0.6066 data: 0.0021 max mem: 30262 +train: [0] [700/800] eta: 0:01:08 lr: 0.000052 loss: 0.4464 (0.5666) grad: 0.1595 (0.2480) time: 0.5933 data: 0.0031 max mem: 30262 +train: [0] [720/800] eta: 0:00:55 lr: 0.000054 loss: 0.4464 (0.5641) grad: 0.1595 (0.2462) time: 0.9822 data: 0.3577 max mem: 30262 +train: [0] [740/800] eta: 0:00:41 lr: 0.000055 loss: 0.4394 (0.5590) grad: 0.1554 (0.2439) time: 0.6156 data: 0.0027 max mem: 30262 +train: [0] [760/800] eta: 0:00:27 lr: 0.000057 loss: 0.4037 (0.5546) grad: 0.1759 (0.2427) time: 0.6360 data: 0.0309 max mem: 30262 +train: [0] [780/800] eta: 0:00:13 lr: 0.000058 loss: 0.4230 (0.5559) grad: 0.1918 (0.2434) time: 0.6232 data: 0.0032 max mem: 30262 +train: [0] [799/800] eta: 0:00:00 lr: 0.000060 loss: 0.4037 (0.5514) grad: 0.1845 (0.2421) time: 0.6570 data: 0.0031 max mem: 30262 +train: [0] Total time: 0:09:13 (0.6914 s / it) +train: [0] Summary: lr: 0.000060 loss: 0.4037 (0.5514) grad: 0.1845 (0.2421) +eval (validation): [0] [ 0/15] eta: 0:01:21 time: 5.4067 data: 5.0882 max mem: 30262 +eval (validation): [0] [14/15] eta: 0:00:00 time: 0.9687 data: 0.5502 max mem: 30262 +eval (validation): [0] Total time: 0:00:14 (0.9822 s / it) +cv: [0] best hparam: (3.1, 1.0) (031) ('031_lr3.1e+00_wd1.0e+00') loss: 0.341 acc: 0.914 f1: 0.908 bacc: 0.904 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_sex__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_sex__patch__attn/checkpoint-best.pth +train: [1] [ 0/800] eta: 1:17:50 lr: nan time: 5.8383 data: 5.3319 max mem: 30262 +train: [1] [ 20/800] eta: 0:12:26 lr: 0.000061 loss: 0.5487 (0.4806) grad: 0.1670 (0.1988) time: 0.7130 data: 0.1052 max mem: 30262 +train: [1] [ 40/800] eta: 0:09:57 lr: 0.000063 loss: 0.3576 (0.4346) grad: 0.1546 (0.1780) time: 0.6077 data: 0.0029 max mem: 30262 +train: [1] [ 60/800] eta: 0:08:55 lr: 0.000064 loss: 0.4314 (0.4537) grad: 0.1670 (0.1984) time: 0.5962 data: 0.0030 max mem: 30262 +train: [1] [ 80/800] eta: 0:08:25 lr: 0.000066 loss: 0.3654 (0.4306) grad: 0.1701 (0.2040) time: 0.6356 data: 0.0029 max mem: 30262 +train: [1] [100/800] eta: 0:08:03 lr: 0.000067 loss: 0.3654 (0.4269) grad: 0.1765 (0.2029) time: 0.6418 data: 0.0046 max mem: 30262 +train: [1] [120/800] eta: 0:08:09 lr: 0.000069 loss: 0.3946 (0.4293) grad: 0.2057 (0.2087) time: 0.8705 data: 0.2872 max mem: 30262 +train: [1] [140/800] eta: 0:07:56 lr: 0.000070 loss: 0.3785 (0.4406) grad: 0.2155 (0.2120) time: 0.7293 data: 0.1246 max mem: 30262 +train: [1] [160/800] eta: 0:07:35 lr: 0.000072 loss: 0.3946 (0.4349) grad: 0.2057 (0.2085) time: 0.6419 data: 0.0267 max mem: 30262 +train: [1] [180/800] eta: 0:07:17 lr: 0.000073 loss: 0.4001 (0.4390) grad: 0.2155 (0.2184) time: 0.6563 data: 0.0521 max mem: 30262 +train: [1] [200/800] eta: 0:06:59 lr: 0.000075 loss: 0.3689 (0.4307) grad: 0.2045 (0.2165) time: 0.6497 data: 0.0040 max mem: 30262 +train: [1] [220/800] eta: 0:06:42 lr: 0.000076 loss: 0.3667 (0.4276) grad: 0.1830 (0.2176) time: 0.6338 data: 0.0027 max mem: 30262 +train: [1] [240/800] eta: 0:06:38 lr: 0.000078 loss: 0.3821 (0.4358) grad: 0.1830 (0.2149) time: 0.9118 data: 0.3164 max mem: 30262 +train: [1] [260/800] eta: 0:06:21 lr: 0.000079 loss: 0.3937 (0.4367) grad: 0.1702 (0.2169) time: 0.6514 data: 0.0320 max mem: 30262 +train: [1] [280/800] eta: 0:06:04 lr: 0.000081 loss: 0.4122 (0.4390) grad: 0.2253 (0.2195) time: 0.6183 data: 0.0033 max mem: 30262 +train: [1] [300/800] eta: 0:05:48 lr: 0.000082 loss: 0.4122 (0.4373) grad: 0.2253 (0.2217) time: 0.6278 data: 0.0034 max mem: 30262 +train: [1] [320/800] eta: 0:05:33 lr: 0.000084 loss: 0.3993 (0.4386) grad: 0.2253 (0.2202) time: 0.6704 data: 0.0033 max mem: 30262 +train: [1] [340/800] eta: 0:05:17 lr: 0.000085 loss: 0.3805 (0.4343) grad: 0.2046 (0.2179) time: 0.6255 data: 0.0036 max mem: 30262 +train: [1] [360/800] eta: 0:05:09 lr: 0.000087 loss: 0.3415 (0.4332) grad: 0.1632 (0.2149) time: 0.9199 data: 0.3151 max mem: 30262 +train: [1] [380/800] eta: 0:04:54 lr: 0.000088 loss: 0.3443 (0.4326) grad: 0.1563 (0.2163) time: 0.6673 data: 0.0025 max mem: 30262 +train: [1] [400/800] eta: 0:04:38 lr: 0.000090 loss: 0.3443 (0.4351) grad: 0.1713 (0.2214) time: 0.6224 data: 0.0037 max mem: 30262 +train: [1] [420/800] eta: 0:04:23 lr: 0.000091 loss: 0.3443 (0.4326) grad: 0.2069 (0.2208) time: 0.6067 data: 0.0034 max mem: 30262 +train: [1] [440/800] eta: 0:04:08 lr: 0.000093 loss: 0.3971 (0.4352) grad: 0.2244 (0.2216) time: 0.6262 data: 0.0025 max mem: 30262 +train: [1] [460/800] eta: 0:03:53 lr: 0.000094 loss: 0.3971 (0.4305) grad: 0.2315 (0.2213) time: 0.6097 data: 0.0031 max mem: 30262 +train: [1] [480/800] eta: 0:03:43 lr: 0.000096 loss: 0.3092 (0.4266) grad: 0.2122 (0.2212) time: 0.9467 data: 0.3338 max mem: 30262 +train: [1] [500/800] eta: 0:03:28 lr: 0.000097 loss: 0.3297 (0.4289) grad: 0.2183 (0.2214) time: 0.6126 data: 0.0031 max mem: 30262 +train: [1] [520/800] eta: 0:03:13 lr: 0.000099 loss: 0.3253 (0.4284) grad: 0.2122 (0.2201) time: 0.6267 data: 0.0034 max mem: 30262 +train: [1] [540/800] eta: 0:02:59 lr: 0.000100 loss: 0.3265 (0.4256) grad: 0.1901 (0.2193) time: 0.6944 data: 0.0036 max mem: 30262 +train: [1] [560/800] eta: 0:02:45 lr: 0.000102 loss: 0.3761 (0.4240) grad: 0.1901 (0.2205) time: 0.6331 data: 0.0039 max mem: 30262 +train: [1] [580/800] eta: 0:02:31 lr: 0.000103 loss: 0.3485 (0.4211) grad: 0.1923 (0.2210) time: 0.6105 data: 0.0032 max mem: 30262 +train: [1] [600/800] eta: 0:02:19 lr: 0.000105 loss: 0.3511 (0.4222) grad: 0.1955 (0.2209) time: 1.0123 data: 0.2981 max mem: 30262 +train: [1] [620/800] eta: 0:02:05 lr: 0.000106 loss: 0.3511 (0.4200) grad: 0.2139 (0.2214) time: 0.6351 data: 0.0035 max mem: 30262 +train: [1] [640/800] eta: 0:01:51 lr: 0.000108 loss: 0.3514 (0.4212) grad: 0.2139 (0.2212) time: 0.6438 data: 0.0039 max mem: 30262 +train: [1] [660/800] eta: 0:01:36 lr: 0.000109 loss: 0.3514 (0.4173) grad: 0.2029 (0.2197) time: 0.6147 data: 0.0036 max mem: 30262 +train: [1] [680/800] eta: 0:01:22 lr: 0.000111 loss: 0.3514 (0.4174) grad: 0.2029 (0.2197) time: 0.6136 data: 0.0038 max mem: 30262 +train: [1] [700/800] eta: 0:01:08 lr: 0.000112 loss: 0.3768 (0.4175) grad: 0.1987 (0.2204) time: 0.6003 data: 0.0032 max mem: 30262 +train: [1] [720/800] eta: 0:00:55 lr: 0.000114 loss: 0.3768 (0.4173) grad: 0.1732 (0.2184) time: 0.9012 data: 0.2888 max mem: 30262 +train: [1] [740/800] eta: 0:00:41 lr: 0.000115 loss: 0.3791 (0.4153) grad: 0.1732 (0.2184) time: 0.6080 data: 0.0036 max mem: 30262 +train: [1] [760/800] eta: 0:00:27 lr: 0.000117 loss: 0.3906 (0.4151) grad: 0.1603 (0.2167) time: 0.6459 data: 0.0395 max mem: 30262 +train: [1] [780/800] eta: 0:00:13 lr: 0.000118 loss: 0.3906 (0.4150) grad: 0.1603 (0.2162) time: 0.6447 data: 0.0393 max mem: 30262 +train: [1] [799/800] eta: 0:00:00 lr: 0.000120 loss: 0.3565 (0.4126) grad: 0.1964 (0.2166) time: 0.5936 data: 0.0026 max mem: 30262 +train: [1] Total time: 0:09:08 (0.6861 s / it) +train: [1] Summary: lr: 0.000120 loss: 0.3565 (0.4126) grad: 0.1964 (0.2166) +eval (validation): [1] [ 0/15] eta: 0:01:25 time: 5.6870 data: 5.3129 max mem: 30262 +eval (validation): [1] [14/15] eta: 0:00:00 time: 0.8307 data: 0.3766 max mem: 30262 +eval (validation): [1] Total time: 0:00:12 (0.8462 s / it) +cv: [1] best hparam: (0.52, 1.0) (020) ('020_lr5.2e-01_wd1.0e+00') loss: 0.360 acc: 0.914 f1: 0.908 bacc: 0.904 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_sex__patch__attn/checkpoint-last.pth +train: [2] [ 0/800] eta: 1:12:05 lr: nan time: 5.4075 data: 4.9482 max mem: 30262 +train: [2] [ 20/800] eta: 0:10:47 lr: 0.000121 loss: 0.3582 (0.3644) grad: 0.2035 (0.2331) time: 0.6011 data: 0.0036 max mem: 30262 +train: [2] [ 40/800] eta: 0:09:32 lr: 0.000123 loss: 0.3919 (0.4195) grad: 0.2035 (0.2394) time: 0.6725 data: 0.0764 max mem: 30262 +train: [2] [ 60/800] eta: 0:08:52 lr: 0.000124 loss: 0.4517 (0.4061) grad: 0.2035 (0.2225) time: 0.6487 data: 0.0360 max mem: 30262 +train: [2] [ 80/800] eta: 0:08:17 lr: 0.000126 loss: 0.3767 (0.3835) grad: 0.2058 (0.2301) time: 0.6082 data: 0.0028 max mem: 30262 +train: [2] [100/800] eta: 0:07:51 lr: 0.000127 loss: 0.3794 (0.3833) grad: 0.2389 (0.2390) time: 0.5970 data: 0.0030 max mem: 30262 +train: [2] [120/800] eta: 0:08:03 lr: 0.000129 loss: 0.3218 (0.3610) grad: 0.2228 (0.2360) time: 0.9054 data: 0.2949 max mem: 30262 +train: [2] [140/800] eta: 0:07:46 lr: 0.000130 loss: 0.3461 (0.3758) grad: 0.2277 (0.2409) time: 0.6833 data: 0.0397 max mem: 30262 +train: [2] [160/800] eta: 0:07:31 lr: 0.000132 loss: 0.3293 (0.3661) grad: 0.2277 (0.2432) time: 0.6904 data: 0.0549 max mem: 30262 +train: [2] [180/800] eta: 0:07:15 lr: 0.000133 loss: 0.2870 (0.3770) grad: 0.2236 (0.2437) time: 0.6816 data: 0.0658 max mem: 30262 +train: [2] [200/800] eta: 0:07:01 lr: 0.000135 loss: 0.3160 (0.3804) grad: 0.2397 (0.2441) time: 0.6947 data: 0.0861 max mem: 30262 +train: [2] [220/800] eta: 0:06:44 lr: 0.000136 loss: 0.3160 (0.3799) grad: 0.2397 (0.2424) time: 0.6463 data: 0.0617 max mem: 30262 +train: [2] [240/800] eta: 0:06:41 lr: 0.000138 loss: 0.2870 (0.3735) grad: 0.2168 (0.2411) time: 0.9450 data: 0.3055 max mem: 30262 +train: [2] [260/800] eta: 0:06:28 lr: 0.000139 loss: 0.2669 (0.3720) grad: 0.2695 (0.2461) time: 0.7415 data: 0.0038 max mem: 30262 +train: [2] [280/800] eta: 0:06:11 lr: 0.000141 loss: 0.2460 (0.3657) grad: 0.2591 (0.2457) time: 0.6452 data: 0.0027 max mem: 30262 +train: [2] [300/800] eta: 0:05:53 lr: 0.000142 loss: 0.2490 (0.3660) grad: 0.2620 (0.2467) time: 0.6059 data: 0.0034 max mem: 30262 +train: [2] [320/800] eta: 0:05:36 lr: 0.000144 loss: 0.3173 (0.3646) grad: 0.2979 (0.2511) time: 0.6175 data: 0.0027 max mem: 30262 +train: [2] [340/800] eta: 0:05:19 lr: 0.000145 loss: 0.3244 (0.3714) grad: 0.2998 (0.2575) time: 0.6045 data: 0.0031 max mem: 30262 +train: [2] [360/800] eta: 0:05:12 lr: 0.000147 loss: 0.3460 (0.3704) grad: 0.3163 (0.2674) time: 0.9618 data: 0.2948 max mem: 30262 +train: [2] [380/800] eta: 0:04:56 lr: 0.000148 loss: 0.3617 (0.3911) grad: 0.3312 (0.2766) time: 0.6225 data: 0.0031 max mem: 30262 +train: [2] [400/800] eta: 0:04:40 lr: 0.000150 loss: 0.3907 (0.4067) grad: 0.3834 (0.2864) time: 0.6075 data: 0.0035 max mem: 30262 +train: [2] [420/800] eta: 0:04:24 lr: 0.000151 loss: 0.3567 (0.4020) grad: 0.3777 (0.2885) time: 0.6194 data: 0.0037 max mem: 30262 +WARNING: classifier 46 (36, 1.0) diverged (loss=14.50 > 13.86) at step 506. Freezing. +train: [2] [440/800] eta: 0:04:09 lr: 0.000153 loss: 0.4289 (0.4063) grad: 0.3790 (0.2938) time: 0.6182 data: 0.0031 max mem: 30262 +train: [2] [460/800] eta: 0:03:54 lr: 0.000154 loss: 0.3418 (0.4026) grad: 0.3645 (0.2944) time: 0.6084 data: 0.0029 max mem: 30262 +train: [2] [480/800] eta: 0:03:44 lr: 0.000156 loss: 0.3091 (0.4017) grad: 0.3085 (0.2954) time: 0.9793 data: 0.2817 max mem: 30262 +train: [2] [500/800] eta: 0:03:29 lr: 0.000157 loss: 0.3709 (0.4041) grad: 0.2896 (0.2946) time: 0.6294 data: 0.0029 max mem: 30262 +train: [2] [520/800] eta: 0:03:14 lr: 0.000159 loss: 0.3091 (0.4030) grad: 0.2753 (0.2937) time: 0.6061 data: 0.0037 max mem: 30262 +train: [2] [540/800] eta: 0:02:59 lr: 0.000160 loss: 0.3068 (0.3993) grad: 0.2750 (0.2935) time: 0.6141 data: 0.0027 max mem: 30262 +train: [2] [560/800] eta: 0:02:45 lr: 0.000162 loss: 0.2907 (0.3996) grad: 0.2288 (0.2913) time: 0.6285 data: 0.0193 max mem: 30262 +train: [2] [580/800] eta: 0:02:31 lr: 0.000163 loss: 0.2907 (0.4055) grad: 0.2472 (0.2917) time: 0.6487 data: 0.0630 max mem: 30262 +train: [2] [600/800] eta: 0:02:19 lr: 0.000165 loss: 0.2818 (0.4032) grad: 0.2866 (0.2926) time: 0.9725 data: 0.3199 max mem: 30262 +train: [2] [620/800] eta: 0:02:05 lr: 0.000166 loss: 0.2773 (0.3992) grad: 0.2911 (0.2961) time: 0.6122 data: 0.0039 max mem: 30262 +train: [2] [640/800] eta: 0:01:50 lr: 0.000168 loss: 0.3233 (0.4025) grad: 0.3018 (0.2956) time: 0.6090 data: 0.0033 max mem: 30262 +train: [2] [660/800] eta: 0:01:36 lr: 0.000169 loss: 0.2818 (0.4001) grad: 0.3349 (0.2979) time: 0.6180 data: 0.0035 max mem: 30262 +train: [2] [680/800] eta: 0:01:22 lr: 0.000171 loss: 0.3661 (0.4056) grad: 0.3738 (0.3065) time: 0.6450 data: 0.0036 max mem: 30262 +train: [2] [700/800] eta: 0:01:08 lr: 0.000172 loss: 0.3711 (0.4048) grad: 0.3819 (0.3104) time: 0.6037 data: 0.0029 max mem: 30262 +train: [2] [720/800] eta: 0:00:55 lr: 0.000174 loss: 0.3023 (0.4047) grad: 0.4154 (0.3114) time: 0.9036 data: 0.2748 max mem: 30262 +train: [2] [740/800] eta: 0:00:41 lr: 0.000175 loss: 0.3023 (0.4021) grad: 0.4167 (0.3123) time: 0.6269 data: 0.0042 max mem: 30262 +train: [2] [760/800] eta: 0:00:27 lr: 0.000177 loss: 0.2884 (0.3989) grad: 0.3848 (0.3134) time: 0.6139 data: 0.0032 max mem: 30262 +train: [2] [780/800] eta: 0:00:13 lr: 0.000178 loss: 0.2777 (0.3970) grad: 0.3848 (0.3156) time: 0.6223 data: 0.0036 max mem: 30262 +train: [2] [799/800] eta: 0:00:00 lr: 0.000180 loss: 0.2777 (0.3963) grad: 0.3576 (0.3165) time: 0.6251 data: 0.0033 max mem: 30262 +train: [2] Total time: 0:09:08 (0.6858 s / it) +train: [2] Summary: lr: 0.000180 loss: 0.2777 (0.3963) grad: 0.3576 (0.3165) +eval (validation): [2] [ 0/15] eta: 0:01:28 time: 5.9303 data: 5.6001 max mem: 30262 +eval (validation): [2] [14/15] eta: 0:00:00 time: 0.8890 data: 0.4611 max mem: 30262 +eval (validation): [2] Total time: 0:00:13 (0.9046 s / it) +cv: [2] best hparam: (0.12, 1.0) (011) ('011_lr1.2e-01_wd1.0e+00') loss: 0.418 acc: 0.914 f1: 0.908 bacc: 0.904 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_sex__patch__attn/checkpoint-last.pth +train: [3] [ 0/800] eta: 1:09:02 lr: nan time: 5.1776 data: 4.7308 max mem: 30262 +train: [3] [ 20/800] eta: 0:11:44 lr: 0.000181 loss: 0.4152 (0.3698) grad: 0.3468 (0.3663) time: 0.6895 data: 0.0045 max mem: 30262 +train: [3] [ 40/800] eta: 0:09:39 lr: 0.000183 loss: 0.4152 (0.3773) grad: 0.3468 (0.3938) time: 0.6138 data: 0.0029 max mem: 30262 +train: [3] [ 60/800] eta: 0:08:44 lr: 0.000184 loss: 0.3922 (0.3816) grad: 0.3468 (0.3787) time: 0.6005 data: 0.0030 max mem: 30262 +train: [3] [ 80/800] eta: 0:08:14 lr: 0.000186 loss: 0.3284 (0.3645) grad: 0.3373 (0.3548) time: 0.6196 data: 0.0027 max mem: 30262 +WARNING: classifier 47 (43, 1.0) diverged (loss=22.75 > 13.86) at step 623. Freezing. +WARNING: classifier 48 (50, 1.0) diverged (loss=19.70 > 13.86) at step 623. Freezing. +train: [3] [100/800] eta: 0:07:58 lr: 0.000187 loss: 0.3542 (0.4473) grad: 0.2970 (0.3828) time: 0.6662 data: 0.0679 max mem: 30262 +train: [3] [120/800] eta: 0:08:09 lr: 0.000189 loss: 0.3922 (0.4870) grad: 0.2927 (0.3697) time: 0.9056 data: 0.3031 max mem: 30262 +train: [3] [140/800] eta: 0:07:55 lr: 0.000190 loss: 0.3625 (0.4611) grad: 0.2397 (0.3473) time: 0.7208 data: 0.0033 max mem: 30262 +train: [3] [160/800] eta: 0:07:33 lr: 0.000192 loss: 0.3625 (0.4406) grad: 0.2494 (0.3411) time: 0.6246 data: 0.0038 max mem: 30262 +train: [3] [180/800] eta: 0:07:12 lr: 0.000193 loss: 0.3042 (0.4262) grad: 0.2397 (0.3278) time: 0.6104 data: 0.0034 max mem: 30262 +train: [3] [200/800] eta: 0:06:52 lr: 0.000195 loss: 0.2690 (0.4236) grad: 0.2613 (0.3296) time: 0.6035 data: 0.0034 max mem: 30262 +train: [3] [220/800] eta: 0:06:37 lr: 0.000196 loss: 0.2562 (0.4114) grad: 0.2613 (0.3198) time: 0.6672 data: 0.0031 max mem: 30262 +train: [3] [240/800] eta: 0:06:33 lr: 0.000198 loss: 0.2539 (0.4037) grad: 0.2342 (0.3089) time: 0.8824 data: 0.2898 max mem: 30262 +train: [3] [260/800] eta: 0:06:21 lr: 0.000199 loss: 0.2432 (0.3893) grad: 0.2002 (0.2978) time: 0.7585 data: 0.1685 max mem: 30262 +train: [3] [280/800] eta: 0:06:06 lr: 0.000201 loss: 0.2432 (0.3940) grad: 0.1998 (0.2986) time: 0.6717 data: 0.0589 max mem: 30262 +train: [3] [300/800] eta: 0:05:50 lr: 0.000202 loss: 0.2451 (0.3932) grad: 0.1998 (0.2979) time: 0.6720 data: 0.0595 max mem: 30262 +train: [3] [320/800] eta: 0:05:36 lr: 0.000204 loss: 0.2612 (0.3906) grad: 0.2220 (0.2946) time: 0.6762 data: 0.0637 max mem: 30262 +train: [3] [340/800] eta: 0:05:21 lr: 0.000205 loss: 0.3203 (0.3836) grad: 0.2220 (0.2885) time: 0.6842 data: 0.0778 max mem: 30262 +train: [3] [360/800] eta: 0:05:12 lr: 0.000207 loss: 0.3203 (0.3816) grad: 0.2060 (0.2828) time: 0.8823 data: 0.3000 max mem: 30262 +train: [3] [380/800] eta: 0:04:56 lr: 0.000208 loss: 0.3203 (0.3855) grad: 0.2006 (0.2786) time: 0.6372 data: 0.0532 max mem: 30262 +train: [3] [400/800] eta: 0:04:40 lr: 0.000210 loss: 0.3250 (0.3895) grad: 0.1993 (0.2785) time: 0.6019 data: 0.0030 max mem: 30262 +train: [3] [420/800] eta: 0:04:24 lr: 0.000211 loss: 0.3726 (0.3927) grad: 0.2129 (0.2779) time: 0.5948 data: 0.0023 max mem: 30262 +train: [3] [440/800] eta: 0:04:09 lr: 0.000213 loss: 0.3337 (0.3843) grad: 0.2129 (0.2770) time: 0.6123 data: 0.0036 max mem: 30262 +train: [3] [460/800] eta: 0:03:53 lr: 0.000214 loss: 0.3337 (0.3845) grad: 0.2422 (0.2797) time: 0.5977 data: 0.0035 max mem: 30262 +train: [3] [480/800] eta: 0:03:42 lr: 0.000216 loss: 0.3306 (0.3901) grad: 0.3036 (0.2808) time: 0.8768 data: 0.2885 max mem: 30262 +train: [3] [500/800] eta: 0:03:28 lr: 0.000217 loss: 0.2877 (0.3893) grad: 0.2379 (0.2795) time: 0.6396 data: 0.0207 max mem: 30262 +train: [3] [520/800] eta: 0:03:13 lr: 0.000219 loss: 0.2601 (0.3818) grad: 0.2379 (0.2770) time: 0.6491 data: 0.0036 max mem: 30262 +train: [3] [540/800] eta: 0:02:59 lr: 0.000220 loss: 0.2587 (0.3799) grad: 0.2379 (0.2771) time: 0.6365 data: 0.0030 max mem: 30262 +train: [3] [560/800] eta: 0:02:44 lr: 0.000222 loss: 0.2294 (0.3777) grad: 0.2327 (0.2772) time: 0.6028 data: 0.0032 max mem: 30262 +train: [3] [580/800] eta: 0:02:30 lr: 0.000223 loss: 0.2293 (0.3731) grad: 0.2327 (0.2779) time: 0.5686 data: 0.0030 max mem: 30262 +train: [3] [600/800] eta: 0:02:18 lr: 0.000225 loss: 0.2358 (0.3728) grad: 0.2810 (0.2783) time: 0.9715 data: 0.3736 max mem: 30262 +train: [3] [620/800] eta: 0:02:04 lr: 0.000226 loss: 0.2358 (0.3732) grad: 0.2607 (0.2784) time: 0.6359 data: 0.0041 max mem: 30262 +train: [3] [640/800] eta: 0:01:49 lr: 0.000228 loss: 0.2358 (0.3713) grad: 0.2439 (0.2768) time: 0.6003 data: 0.0033 max mem: 30262 +train: [3] [660/800] eta: 0:01:35 lr: 0.000229 loss: 0.2347 (0.3695) grad: 0.2413 (0.2766) time: 0.6078 data: 0.0027 max mem: 30262 +train: [3] [680/800] eta: 0:01:21 lr: 0.000231 loss: 0.2397 (0.3698) grad: 0.2349 (0.2768) time: 0.6251 data: 0.0315 max mem: 30262 +train: [3] [700/800] eta: 0:01:08 lr: 0.000232 loss: 0.2397 (0.3677) grad: 0.2385 (0.2770) time: 0.6412 data: 0.0607 max mem: 30262 +train: [3] [720/800] eta: 0:00:55 lr: 0.000234 loss: 0.2422 (0.3656) grad: 0.2413 (0.2789) time: 0.9603 data: 0.3038 max mem: 30262 +train: [3] [740/800] eta: 0:00:41 lr: 0.000235 loss: 0.3039 (0.3641) grad: 0.3160 (0.2797) time: 0.6170 data: 0.0026 max mem: 30262 +train: [3] [760/800] eta: 0:00:27 lr: 0.000237 loss: 0.2571 (0.3626) grad: 0.3094 (0.2801) time: 0.5950 data: 0.0035 max mem: 30262 +train: [3] [780/800] eta: 0:00:13 lr: 0.000238 loss: 0.2852 (0.3606) grad: 0.2720 (0.2797) time: 0.6044 data: 0.0036 max mem: 30262 +train: [3] [799/800] eta: 0:00:00 lr: 0.000240 loss: 0.2571 (0.3580) grad: 0.2617 (0.2805) time: 0.6057 data: 0.0034 max mem: 30262 +train: [3] Total time: 0:09:05 (0.6817 s / it) +train: [3] Summary: lr: 0.000240 loss: 0.2571 (0.3580) grad: 0.2617 (0.2805) +eval (validation): [3] [ 0/15] eta: 0:01:24 time: 5.6080 data: 5.2861 max mem: 30262 +eval (validation): [3] [14/15] eta: 0:00:00 time: 0.8019 data: 0.3687 max mem: 30262 +eval (validation): [3] Total time: 0:00:12 (0.8160 s / it) +cv: [3] best hparam: (12, 1.0) (039) ('039_lr1.2e+01_wd1.0e+00') loss: 0.666 acc: 0.948 f1: 0.945 bacc: 0.941 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_sex__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_sex__patch__attn/checkpoint-best.pth +train: [4] [ 0/800] eta: 1:15:49 lr: nan time: 5.6867 data: 5.2091 max mem: 30262 +train: [4] [ 20/800] eta: 0:11:28 lr: 0.000241 loss: 0.2032 (0.2975) grad: 0.2597 (0.2755) time: 0.6426 data: 0.0033 max mem: 30262 +train: [4] [ 40/800] eta: 0:09:25 lr: 0.000243 loss: 0.2010 (0.3084) grad: 0.2597 (0.2744) time: 0.5995 data: 0.0032 max mem: 30262 +train: [4] [ 60/800] eta: 0:08:41 lr: 0.000244 loss: 0.2010 (0.2937) grad: 0.2955 (0.3083) time: 0.6219 data: 0.0031 max mem: 30262 +train: [4] [ 80/800] eta: 0:08:11 lr: 0.000246 loss: 0.2032 (0.2911) grad: 0.3169 (0.3480) time: 0.6186 data: 0.0036 max mem: 30262 +WARNING: classifier 45 (31, 1.0) diverged (loss=21.00 > 13.86) at step 824. Freezing. +train: [4] [100/800] eta: 0:07:49 lr: 0.000247 loss: 0.2140 (0.3092) grad: 0.3257 (0.3657) time: 0.6228 data: 0.0035 max mem: 30262 +train: [4] [120/800] eta: 0:07:57 lr: 0.000249 loss: 0.2344 (0.3086) grad: 0.3815 (0.3565) time: 0.8596 data: 0.2788 max mem: 30262 +train: [4] [140/800] eta: 0:07:33 lr: 0.000250 loss: 0.2432 (0.3125) grad: 0.3862 (0.3582) time: 0.5962 data: 0.0034 max mem: 30262 +WARNING: classifier 42 (19, 1.0) diverged (loss=23.14 > 13.86) at step 840. Freezing. +train: [4] [160/800] eta: 0:07:17 lr: 0.000252 loss: 0.2889 (0.3287) grad: 0.3906 (0.3769) time: 0.6547 data: 0.0074 max mem: 30262 +train: [4] [180/800] eta: 0:07:00 lr: 0.000253 loss: 0.2432 (0.3213) grad: 0.3731 (0.3717) time: 0.6335 data: 0.0046 max mem: 30262 +train: [4] [200/800] eta: 0:06:44 lr: 0.000255 loss: 0.3067 (0.3362) grad: 0.3731 (0.3796) time: 0.6338 data: 0.0038 max mem: 30262 +train: [4] [220/800] eta: 0:06:27 lr: 0.000256 loss: 0.3067 (0.3463) grad: 0.3556 (0.3776) time: 0.6197 data: 0.0036 max mem: 30262 +train: [4] [240/800] eta: 0:06:23 lr: 0.000258 loss: 0.2731 (0.3403) grad: 0.3305 (0.3764) time: 0.8732 data: 0.2844 max mem: 30262 +train: [4] [260/800] eta: 0:06:08 lr: 0.000259 loss: 0.3533 (0.3455) grad: 0.3480 (0.3755) time: 0.6509 data: 0.0583 max mem: 30262 +train: [4] [280/800] eta: 0:05:52 lr: 0.000261 loss: 0.3553 (0.3483) grad: 0.3305 (0.3709) time: 0.6178 data: 0.0028 max mem: 30262 +train: [4] [300/800] eta: 0:05:36 lr: 0.000262 loss: 0.3151 (0.3453) grad: 0.2905 (0.3622) time: 0.5990 data: 0.0030 max mem: 30262 +WARNING: classifier 43 (22, 1.0) diverged (loss=17.60 > 13.86) at step 879. Freezing. +train: [4] [320/800] eta: 0:05:20 lr: 0.000264 loss: 0.3151 (0.3513) grad: 0.2905 (0.3620) time: 0.5766 data: 0.0030 max mem: 30262 +train: [4] [340/800] eta: 0:05:04 lr: 0.000265 loss: 0.3064 (0.3525) grad: 0.2479 (0.3522) time: 0.5976 data: 0.0030 max mem: 30262 +train: [4] [360/800] eta: 0:04:57 lr: 0.000267 loss: 0.2796 (0.3467) grad: 0.2558 (0.3486) time: 0.8884 data: 0.3200 max mem: 30262 +train: [4] [380/800] eta: 0:04:42 lr: 0.000268 loss: 0.2751 (0.3455) grad: 0.2742 (0.3460) time: 0.6301 data: 0.0512 max mem: 30262 +train: [4] [400/800] eta: 0:04:27 lr: 0.000270 loss: 0.2487 (0.3427) grad: 0.2742 (0.3514) time: 0.5782 data: 0.0023 max mem: 30262 +train: [4] [420/800] eta: 0:04:12 lr: 0.000271 loss: 0.2601 (0.3424) grad: 0.2769 (0.3531) time: 0.6030 data: 0.0289 max mem: 30262 +train: [4] [440/800] eta: 0:03:58 lr: 0.000273 loss: 0.2751 (0.3388) grad: 0.2894 (0.3619) time: 0.5802 data: 0.0025 max mem: 30262 +train: [4] [460/800] eta: 0:03:43 lr: 0.000274 loss: 0.2700 (0.3372) grad: 0.3103 (0.3597) time: 0.5877 data: 0.0032 max mem: 30262 +train: [4] [480/800] eta: 0:03:33 lr: 0.000276 loss: 0.2700 (0.3342) grad: 0.2894 (0.3557) time: 0.9061 data: 0.3017 max mem: 30262 +WARNING: classifier 44 (26, 1.0) diverged (loss=21.50 > 13.86) at step 921. Freezing. +train: [4] [500/800] eta: 0:03:20 lr: 0.000277 loss: 0.2904 (0.3433) grad: 0.2403 (0.3509) time: 0.6259 data: 0.0242 max mem: 30262 +train: [4] [520/800] eta: 0:03:05 lr: 0.000279 loss: 0.3377 (0.3450) grad: 0.2125 (0.3449) time: 0.6025 data: 0.0032 max mem: 30262 +train: [4] [540/800] eta: 0:02:52 lr: 0.000280 loss: 0.3088 (0.3418) grad: 0.2002 (0.3391) time: 0.6532 data: 0.0041 max mem: 30262 +train: [4] [560/800] eta: 0:02:38 lr: 0.000282 loss: 0.3377 (0.3426) grad: 0.1930 (0.3348) time: 0.6060 data: 0.0037 max mem: 30262 +train: [4] [580/800] eta: 0:02:24 lr: 0.000283 loss: 0.3022 (0.3414) grad: 0.2002 (0.3312) time: 0.5818 data: 0.0032 max mem: 30262 +train: [4] [600/800] eta: 0:02:13 lr: 0.000285 loss: 0.3022 (0.3401) grad: 0.2002 (0.3257) time: 0.9304 data: 0.3595 max mem: 30262 +train: [4] [620/800] eta: 0:02:00 lr: 0.000286 loss: 0.3014 (0.3374) grad: 0.1604 (0.3209) time: 0.7260 data: 0.1334 max mem: 30262 +train: [4] [640/800] eta: 0:01:47 lr: 0.000288 loss: 0.2545 (0.3350) grad: 0.1604 (0.3161) time: 0.6383 data: 0.0578 max mem: 30262 +train: [4] [660/800] eta: 0:01:33 lr: 0.000289 loss: 0.2348 (0.3319) grad: 0.1589 (0.3116) time: 0.7193 data: 0.0858 max mem: 30262 +train: [4] [680/800] eta: 0:01:20 lr: 0.000291 loss: 0.2262 (0.3294) grad: 0.1863 (0.3088) time: 0.5849 data: 0.0024 max mem: 30262 +train: [4] [700/800] eta: 0:01:06 lr: 0.000292 loss: 0.2262 (0.3276) grad: 0.2057 (0.3074) time: 0.5674 data: 0.0027 max mem: 30262 +train: [4] [720/800] eta: 0:00:53 lr: 0.000294 loss: 0.2136 (0.3247) grad: 0.1863 (0.3027) time: 0.9103 data: 0.3373 max mem: 30262 +train: [4] [740/800] eta: 0:00:40 lr: 0.000295 loss: 0.2131 (0.3216) grad: 0.1630 (0.2981) time: 0.6456 data: 0.0506 max mem: 30262 +train: [4] [760/800] eta: 0:00:26 lr: 0.000297 loss: 0.2051 (0.3194) grad: 0.1407 (0.2944) time: 0.6495 data: 0.0036 max mem: 30262 +train: [4] [780/800] eta: 0:00:13 lr: 0.000298 loss: 0.2036 (0.3166) grad: 0.1404 (0.2904) time: 0.5936 data: 0.0032 max mem: 30262 +train: [4] [799/800] eta: 0:00:00 lr: 0.000300 loss: 0.2222 (0.3180) grad: 0.1453 (0.2873) time: 0.6270 data: 0.0050 max mem: 30262 +train: [4] Total time: 0:08:54 (0.6680 s / it) +train: [4] Summary: lr: 0.000300 loss: 0.2222 (0.3180) grad: 0.1453 (0.2873) +eval (validation): [4] [ 0/15] eta: 0:01:16 time: 5.1316 data: 4.7769 max mem: 30262 +eval (validation): [4] [14/15] eta: 0:00:00 time: 0.7644 data: 0.3445 max mem: 30262 +eval (validation): [4] Total time: 0:00:11 (0.7822 s / it) +cv: [4] best hparam: (0.12, 1.0) (011) ('011_lr1.2e-01_wd1.0e+00') loss: 0.345 acc: 0.914 f1: 0.908 bacc: 0.904 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_sex__patch__attn/checkpoint-last.pth +train: [5] [ 0/800] eta: 1:14:42 lr: nan time: 5.6033 data: 5.0899 max mem: 30262 +train: [5] [ 20/800] eta: 0:11:58 lr: 0.000300 loss: 0.2949 (0.3960) grad: 0.1678 (0.1969) time: 0.6867 data: 0.0045 max mem: 30262 +train: [5] [ 40/800] eta: 0:09:39 lr: 0.000300 loss: 0.2810 (0.3393) grad: 0.1678 (0.1902) time: 0.5954 data: 0.0037 max mem: 30262 +train: [5] [ 60/800] eta: 0:08:43 lr: 0.000300 loss: 0.2810 (0.3200) grad: 0.1678 (0.1752) time: 0.5936 data: 0.0031 max mem: 30262 +train: [5] [ 80/800] eta: 0:08:07 lr: 0.000300 loss: 0.2589 (0.2989) grad: 0.1638 (0.1690) time: 0.5863 data: 0.0030 max mem: 30262 +train: [5] [100/800] eta: 0:07:44 lr: 0.000300 loss: 0.2589 (0.2953) grad: 0.1475 (0.1670) time: 0.6059 data: 0.0033 max mem: 30262 +train: [5] [120/800] eta: 0:08:03 lr: 0.000300 loss: 0.2589 (0.2865) grad: 0.1372 (0.1605) time: 0.9543 data: 0.3861 max mem: 30262 +train: [5] [140/800] eta: 0:07:52 lr: 0.000300 loss: 0.2589 (0.2829) grad: 0.1372 (0.1604) time: 0.7486 data: 0.1466 max mem: 30262 +train: [5] [160/800] eta: 0:07:38 lr: 0.000300 loss: 0.2631 (0.2805) grad: 0.1469 (0.1654) time: 0.7214 data: 0.1393 max mem: 30262 +train: [5] [180/800] eta: 0:07:18 lr: 0.000300 loss: 0.2631 (0.2788) grad: 0.1410 (0.1668) time: 0.6300 data: 0.0510 max mem: 30262 +train: [5] [200/800] eta: 0:07:03 lr: 0.000300 loss: 0.2874 (0.2934) grad: 0.1495 (0.1733) time: 0.6953 data: 0.1059 max mem: 30262 +train: [5] [220/800] eta: 0:06:48 lr: 0.000300 loss: 0.2770 (0.2962) grad: 0.1694 (0.1824) time: 0.6766 data: 0.0830 max mem: 30262 +train: [5] [240/800] eta: 0:06:40 lr: 0.000300 loss: 0.2882 (0.3006) grad: 0.2028 (0.1840) time: 0.8400 data: 0.2858 max mem: 30262 +train: [5] [260/800] eta: 0:06:25 lr: 0.000300 loss: 0.2742 (0.3026) grad: 0.2099 (0.1938) time: 0.7058 data: 0.0053 max mem: 30262 +train: [5] [280/800] eta: 0:06:07 lr: 0.000300 loss: 0.2417 (0.2962) grad: 0.2028 (0.1928) time: 0.6138 data: 0.0030 max mem: 30262 +train: [5] [300/800] eta: 0:05:49 lr: 0.000300 loss: 0.2412 (0.2936) grad: 0.1789 (0.1920) time: 0.5974 data: 0.0037 max mem: 30262 +train: [5] [320/800] eta: 0:05:32 lr: 0.000299 loss: 0.2417 (0.2974) grad: 0.1827 (0.1943) time: 0.5888 data: 0.0033 max mem: 30262 +train: [5] [340/800] eta: 0:05:15 lr: 0.000299 loss: 0.2419 (0.2951) grad: 0.1789 (0.1938) time: 0.5900 data: 0.0032 max mem: 30262 +train: [5] [360/800] eta: 0:05:07 lr: 0.000299 loss: 0.2603 (0.2952) grad: 0.1771 (0.1924) time: 0.8970 data: 0.3021 max mem: 30262 +train: [5] [380/800] eta: 0:04:52 lr: 0.000299 loss: 0.2603 (0.2963) grad: 0.1630 (0.1891) time: 0.6754 data: 0.0483 max mem: 30262 +train: [5] [400/800] eta: 0:04:38 lr: 0.000299 loss: 0.2419 (0.2965) grad: 0.1630 (0.1902) time: 0.6736 data: 0.0620 max mem: 30262 +train: [5] [420/800] eta: 0:04:23 lr: 0.000299 loss: 0.3005 (0.2991) grad: 0.1845 (0.1913) time: 0.6606 data: 0.0831 max mem: 30262 +train: [5] [440/800] eta: 0:04:08 lr: 0.000299 loss: 0.3005 (0.3061) grad: 0.2023 (0.1948) time: 0.6056 data: 0.0156 max mem: 30262 +train: [5] [460/800] eta: 0:03:53 lr: 0.000299 loss: 0.3027 (0.3058) grad: 0.2023 (0.1927) time: 0.5955 data: 0.0023 max mem: 30262 +train: [5] [480/800] eta: 0:03:41 lr: 0.000299 loss: 0.3110 (0.3064) grad: 0.1960 (0.1915) time: 0.8321 data: 0.2702 max mem: 30262 +train: [5] [500/800] eta: 0:03:28 lr: 0.000299 loss: 0.2919 (0.3050) grad: 0.1656 (0.1911) time: 0.7304 data: 0.0040 max mem: 30262 +train: [5] [520/800] eta: 0:03:14 lr: 0.000299 loss: 0.2769 (0.3041) grad: 0.1656 (0.1909) time: 0.7285 data: 0.0042 max mem: 30262 +train: [5] [540/800] eta: 0:03:00 lr: 0.000299 loss: 0.2769 (0.3064) grad: 0.1704 (0.1901) time: 0.6295 data: 0.0038 max mem: 30262 +train: [5] [560/800] eta: 0:02:45 lr: 0.000298 loss: 0.2769 (0.3068) grad: 0.1761 (0.1907) time: 0.6081 data: 0.0036 max mem: 30262 +train: [5] [580/800] eta: 0:02:31 lr: 0.000298 loss: 0.2896 (0.3066) grad: 0.1753 (0.1897) time: 0.5926 data: 0.0035 max mem: 30262 +train: [5] [600/800] eta: 0:02:18 lr: 0.000298 loss: 0.2775 (0.3041) grad: 0.1652 (0.1873) time: 0.9018 data: 0.3117 max mem: 30262 +train: [5] [620/800] eta: 0:02:05 lr: 0.000298 loss: 0.2381 (0.2994) grad: 0.1532 (0.1859) time: 0.7498 data: 0.1762 max mem: 30262 +train: [5] [640/800] eta: 0:01:51 lr: 0.000298 loss: 0.1883 (0.2964) grad: 0.1382 (0.1851) time: 0.7342 data: 0.0840 max mem: 30262 +train: [5] [660/800] eta: 0:01:37 lr: 0.000298 loss: 0.1906 (0.2953) grad: 0.1374 (0.1838) time: 0.6096 data: 0.0026 max mem: 30262 +train: [5] [680/800] eta: 0:01:23 lr: 0.000298 loss: 0.1927 (0.2964) grad: 0.1437 (0.1856) time: 0.6399 data: 0.0039 max mem: 30262 +train: [5] [700/800] eta: 0:01:09 lr: 0.000298 loss: 0.2365 (0.2972) grad: 0.1528 (0.1848) time: 0.6329 data: 0.0032 max mem: 30262 +train: [5] [720/800] eta: 0:00:55 lr: 0.000297 loss: 0.2688 (0.2954) grad: 0.1569 (0.1847) time: 0.9804 data: 0.3938 max mem: 30262 +train: [5] [740/800] eta: 0:00:41 lr: 0.000297 loss: 0.2828 (0.2975) grad: 0.1528 (0.1833) time: 0.5815 data: 0.0020 max mem: 30262 +train: [5] [760/800] eta: 0:00:27 lr: 0.000297 loss: 0.2365 (0.2953) grad: 0.1467 (0.1822) time: 0.5917 data: 0.0038 max mem: 30262 +train: [5] [780/800] eta: 0:00:13 lr: 0.000297 loss: 0.1996 (0.2929) grad: 0.1368 (0.1807) time: 0.5963 data: 0.0043 max mem: 30262 +train: [5] [799/800] eta: 0:00:00 lr: 0.000297 loss: 0.2018 (0.2916) grad: 0.1204 (0.1804) time: 0.5849 data: 0.0032 max mem: 30262 +train: [5] Total time: 0:09:10 (0.6881 s / it) +train: [5] Summary: lr: 0.000297 loss: 0.2018 (0.2916) grad: 0.1204 (0.1804) +eval (validation): [5] [ 0/15] eta: 0:01:24 time: 5.6651 data: 5.2785 max mem: 30262 +eval (validation): [5] [14/15] eta: 0:00:00 time: 0.8549 data: 0.3549 max mem: 30262 +eval (validation): [5] Total time: 0:00:13 (0.8720 s / it) +cv: [5] best hparam: (2.3, 1.0) (029) ('029_lr2.3e+00_wd1.0e+00') loss: 0.487 acc: 0.931 f1: 0.925 bacc: 0.918 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_sex__patch__attn/checkpoint-last.pth +train: [6] [ 0/800] eta: 1:13:48 lr: nan time: 5.5359 data: 5.0751 max mem: 30262 +train: [6] [ 20/800] eta: 0:12:05 lr: 0.000297 loss: 0.3046 (0.3328) grad: 0.1527 (0.1621) time: 0.6998 data: 0.0623 max mem: 30262 +train: [6] [ 40/800] eta: 0:09:49 lr: 0.000296 loss: 0.2205 (0.2637) grad: 0.1265 (0.1336) time: 0.6131 data: 0.0028 max mem: 30262 +train: [6] [ 60/800] eta: 0:09:04 lr: 0.000296 loss: 0.2730 (0.2699) grad: 0.1271 (0.1340) time: 0.6557 data: 0.0040 max mem: 30262 +train: [6] [ 80/800] eta: 0:08:27 lr: 0.000296 loss: 0.2540 (0.2642) grad: 0.1271 (0.1334) time: 0.6103 data: 0.0039 max mem: 30262 +train: [6] [100/800] eta: 0:07:59 lr: 0.000296 loss: 0.2205 (0.2652) grad: 0.1241 (0.1327) time: 0.6041 data: 0.0033 max mem: 30262 +train: [6] [120/800] eta: 0:08:08 lr: 0.000296 loss: 0.2410 (0.2672) grad: 0.1312 (0.1406) time: 0.8906 data: 0.2861 max mem: 30262 +train: [6] [140/800] eta: 0:07:55 lr: 0.000296 loss: 0.2410 (0.2864) grad: 0.1261 (0.1410) time: 0.7249 data: 0.0046 max mem: 30262 +train: [6] [160/800] eta: 0:07:32 lr: 0.000295 loss: 0.2312 (0.2781) grad: 0.1309 (0.1426) time: 0.6148 data: 0.0035 max mem: 30262 +train: [6] [180/800] eta: 0:07:12 lr: 0.000295 loss: 0.2253 (0.2790) grad: 0.1483 (0.1494) time: 0.6197 data: 0.0041 max mem: 30262 +train: [6] [200/800] eta: 0:06:52 lr: 0.000295 loss: 0.2214 (0.2741) grad: 0.1483 (0.1507) time: 0.5997 data: 0.0039 max mem: 30262 +train: [6] [220/800] eta: 0:06:32 lr: 0.000295 loss: 0.2143 (0.2777) grad: 0.1493 (0.1516) time: 0.5761 data: 0.0028 max mem: 30262 +train: [6] [240/800] eta: 0:06:30 lr: 0.000295 loss: 0.2214 (0.2799) grad: 0.1702 (0.1554) time: 0.9075 data: 0.2960 max mem: 30262 +train: [6] [260/800] eta: 0:06:16 lr: 0.000294 loss: 0.2306 (0.2794) grad: 0.1702 (0.1539) time: 0.6965 data: 0.0054 max mem: 30262 +train: [6] [280/800] eta: 0:05:59 lr: 0.000294 loss: 0.2715 (0.2813) grad: 0.1479 (0.1527) time: 0.6361 data: 0.0028 max mem: 30262 +train: [6] [300/800] eta: 0:05:42 lr: 0.000294 loss: 0.2132 (0.2754) grad: 0.1458 (0.1542) time: 0.5976 data: 0.0039 max mem: 30262 +train: [6] [320/800] eta: 0:05:26 lr: 0.000294 loss: 0.2132 (0.2723) grad: 0.1364 (0.1554) time: 0.5832 data: 0.0034 max mem: 30262 +train: [6] [340/800] eta: 0:05:11 lr: 0.000293 loss: 0.2209 (0.2752) grad: 0.1458 (0.1558) time: 0.6379 data: 0.0554 max mem: 30262 +train: [6] [360/800] eta: 0:05:03 lr: 0.000293 loss: 0.2209 (0.2765) grad: 0.1663 (0.1602) time: 0.9068 data: 0.2826 max mem: 30262 +train: [6] [380/800] eta: 0:04:49 lr: 0.000293 loss: 0.2283 (0.2783) grad: 0.1672 (0.1642) time: 0.6746 data: 0.0044 max mem: 30262 +train: [6] [400/800] eta: 0:04:33 lr: 0.000293 loss: 0.2304 (0.2749) grad: 0.1602 (0.1633) time: 0.6024 data: 0.0037 max mem: 30262 +train: [6] [420/800] eta: 0:04:18 lr: 0.000292 loss: 0.2148 (0.2714) grad: 0.1494 (0.1610) time: 0.6019 data: 0.0027 max mem: 30262 +train: [6] [440/800] eta: 0:04:03 lr: 0.000292 loss: 0.1936 (0.2704) grad: 0.1293 (0.1610) time: 0.5894 data: 0.0040 max mem: 30262 +train: [6] [460/800] eta: 0:03:48 lr: 0.000292 loss: 0.2323 (0.2690) grad: 0.1072 (0.1602) time: 0.5667 data: 0.0026 max mem: 30262 +train: [6] [480/800] eta: 0:03:37 lr: 0.000292 loss: 0.2339 (0.2683) grad: 0.1298 (0.1590) time: 0.8642 data: 0.2777 max mem: 30262 +train: [6] [500/800] eta: 0:03:22 lr: 0.000291 loss: 0.2323 (0.2651) grad: 0.1302 (0.1582) time: 0.5992 data: 0.0030 max mem: 30262 +train: [6] [520/800] eta: 0:03:08 lr: 0.000291 loss: 0.2323 (0.2649) grad: 0.1285 (0.1562) time: 0.6123 data: 0.0036 max mem: 30262 +train: [6] [540/800] eta: 0:02:54 lr: 0.000291 loss: 0.2119 (0.2615) grad: 0.1285 (0.1555) time: 0.5950 data: 0.0026 max mem: 30262 +train: [6] [560/800] eta: 0:02:40 lr: 0.000291 loss: 0.2071 (0.2632) grad: 0.1261 (0.1546) time: 0.6285 data: 0.0031 max mem: 30262 +train: [6] [580/800] eta: 0:02:26 lr: 0.000290 loss: 0.2279 (0.2630) grad: 0.1305 (0.1543) time: 0.5956 data: 0.0033 max mem: 30262 +train: [6] [600/800] eta: 0:02:14 lr: 0.000290 loss: 0.2119 (0.2647) grad: 0.1305 (0.1532) time: 0.8782 data: 0.2816 max mem: 30262 +train: [6] [620/800] eta: 0:02:01 lr: 0.000290 loss: 0.2257 (0.2629) grad: 0.1177 (0.1529) time: 0.6324 data: 0.0276 max mem: 30262 +train: [6] [640/800] eta: 0:01:47 lr: 0.000290 loss: 0.2020 (0.2612) grad: 0.1036 (0.1523) time: 0.6010 data: 0.0027 max mem: 30262 +train: [6] [660/800] eta: 0:01:33 lr: 0.000289 loss: 0.2257 (0.2617) grad: 0.1044 (0.1520) time: 0.6151 data: 0.0035 max mem: 30262 +train: [6] [680/800] eta: 0:01:20 lr: 0.000289 loss: 0.2257 (0.2628) grad: 0.1074 (0.1522) time: 0.6012 data: 0.0037 max mem: 30262 +train: [6] [700/800] eta: 0:01:06 lr: 0.000289 loss: 0.2339 (0.2618) grad: 0.1047 (0.1507) time: 0.6009 data: 0.0024 max mem: 30262 +train: [6] [720/800] eta: 0:00:53 lr: 0.000288 loss: 0.2339 (0.2612) grad: 0.1074 (0.1504) time: 0.9623 data: 0.2900 max mem: 30262 +train: [6] [740/800] eta: 0:00:40 lr: 0.000288 loss: 0.2263 (0.2611) grad: 0.0973 (0.1493) time: 0.5907 data: 0.0028 max mem: 30262 +train: [6] [760/800] eta: 0:00:26 lr: 0.000288 loss: 0.2424 (0.2622) grad: 0.0973 (0.1489) time: 0.6158 data: 0.0031 max mem: 30262 +train: [6] [780/800] eta: 0:00:13 lr: 0.000287 loss: 0.2190 (0.2605) grad: 0.1010 (0.1474) time: 0.6014 data: 0.0033 max mem: 30262 +train: [6] [799/800] eta: 0:00:00 lr: 0.000287 loss: 0.2124 (0.2586) grad: 0.1072 (0.1470) time: 0.6049 data: 0.0032 max mem: 30262 +train: [6] Total time: 0:08:53 (0.6666 s / it) +train: [6] Summary: lr: 0.000287 loss: 0.2124 (0.2586) grad: 0.1072 (0.1470) +eval (validation): [6] [ 0/15] eta: 0:01:20 time: 5.3558 data: 4.9663 max mem: 30262 +eval (validation): [6] [14/15] eta: 0:00:00 time: 0.7864 data: 0.3719 max mem: 30262 +eval (validation): [6] Total time: 0:00:12 (0.8015 s / it) +cv: [6] best hparam: (3.7, 1.0) (032) ('032_lr3.7e+00_wd1.0e+00') loss: 0.604 acc: 0.948 f1: 0.945 bacc: 0.941 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_sex__patch__attn/checkpoint-last.pth +train: [7] [ 0/800] eta: 1:16:03 lr: nan time: 5.7044 data: 5.2307 max mem: 30262 +train: [7] [ 20/800] eta: 0:12:27 lr: 0.000287 loss: 0.1970 (0.2161) grad: 0.1713 (0.1814) time: 0.7213 data: 0.0304 max mem: 30262 +train: [7] [ 40/800] eta: 0:10:30 lr: 0.000286 loss: 0.1796 (0.2288) grad: 0.1530 (0.1612) time: 0.6941 data: 0.1106 max mem: 30262 +train: [7] [ 60/800] eta: 0:09:39 lr: 0.000286 loss: 0.1970 (0.2382) grad: 0.1561 (0.1609) time: 0.6877 data: 0.0985 max mem: 30262 +train: [7] [ 80/800] eta: 0:09:15 lr: 0.000286 loss: 0.1970 (0.2342) grad: 0.1428 (0.1480) time: 0.7391 data: 0.1585 max mem: 30262 +train: [7] [100/800] eta: 0:08:45 lr: 0.000285 loss: 0.1957 (0.2290) grad: 0.1227 (0.1499) time: 0.6669 data: 0.0809 max mem: 30262 +train: [7] [120/800] eta: 0:08:47 lr: 0.000285 loss: 0.2010 (0.2329) grad: 0.1027 (0.1467) time: 0.8971 data: 0.3256 max mem: 30262 +train: [7] [140/800] eta: 0:08:24 lr: 0.000285 loss: 0.1957 (0.2257) grad: 0.0906 (0.1385) time: 0.6922 data: 0.0857 max mem: 30262 +train: [7] [160/800] eta: 0:07:55 lr: 0.000284 loss: 0.1842 (0.2245) grad: 0.0942 (0.1341) time: 0.5911 data: 0.0031 max mem: 30262 +train: [7] [180/800] eta: 0:07:29 lr: 0.000284 loss: 0.1977 (0.2263) grad: 0.0906 (0.1285) time: 0.5932 data: 0.0040 max mem: 30262 +train: [7] [200/800] eta: 0:07:07 lr: 0.000284 loss: 0.2006 (0.2314) grad: 0.0963 (0.1277) time: 0.5947 data: 0.0039 max mem: 30262 +train: [7] [220/800] eta: 0:06:46 lr: 0.000283 loss: 0.2111 (0.2306) grad: 0.0963 (0.1238) time: 0.5828 data: 0.0029 max mem: 30262 +train: [7] [240/800] eta: 0:06:39 lr: 0.000283 loss: 0.2487 (0.2345) grad: 0.0923 (0.1220) time: 0.8449 data: 0.2868 max mem: 30262 +train: [7] [260/800] eta: 0:06:23 lr: 0.000283 loss: 0.1786 (0.2288) grad: 0.1037 (0.1225) time: 0.6679 data: 0.0660 max mem: 30262 +train: [7] [280/800] eta: 0:06:05 lr: 0.000282 loss: 0.1731 (0.2280) grad: 0.1071 (0.1281) time: 0.6040 data: 0.0033 max mem: 30262 +train: [7] [300/800] eta: 0:05:47 lr: 0.000282 loss: 0.1772 (0.2306) grad: 0.1101 (0.1306) time: 0.5867 data: 0.0029 max mem: 30262 +train: [7] [320/800] eta: 0:05:30 lr: 0.000282 loss: 0.1786 (0.2326) grad: 0.1257 (0.1346) time: 0.6183 data: 0.0038 max mem: 30262 +train: [7] [340/800] eta: 0:05:14 lr: 0.000281 loss: 0.2041 (0.2300) grad: 0.1396 (0.1360) time: 0.5976 data: 0.0029 max mem: 30262 +train: [7] [360/800] eta: 0:05:07 lr: 0.000281 loss: 0.2158 (0.2302) grad: 0.1397 (0.1360) time: 0.9338 data: 0.2803 max mem: 30262 +train: [7] [380/800] eta: 0:04:50 lr: 0.000280 loss: 0.2041 (0.2283) grad: 0.1242 (0.1359) time: 0.5978 data: 0.0023 max mem: 30262 +train: [7] [400/800] eta: 0:04:35 lr: 0.000280 loss: 0.2037 (0.2278) grad: 0.0980 (0.1338) time: 0.5940 data: 0.0039 max mem: 30262 +train: [7] [420/800] eta: 0:04:19 lr: 0.000280 loss: 0.2037 (0.2266) grad: 0.1012 (0.1330) time: 0.6077 data: 0.0028 max mem: 30262 +train: [7] [440/800] eta: 0:04:04 lr: 0.000279 loss: 0.2037 (0.2263) grad: 0.1066 (0.1376) time: 0.5831 data: 0.0033 max mem: 30262 +train: [7] [460/800] eta: 0:03:49 lr: 0.000279 loss: 0.1881 (0.2257) grad: 0.1165 (0.1409) time: 0.5850 data: 0.0030 max mem: 30262 +train: [7] [480/800] eta: 0:03:38 lr: 0.000278 loss: 0.1704 (0.2235) grad: 0.1178 (0.1411) time: 0.8512 data: 0.2750 max mem: 30262 +train: [7] [500/800] eta: 0:03:23 lr: 0.000278 loss: 0.1545 (0.2210) grad: 0.1401 (0.1419) time: 0.5908 data: 0.0037 max mem: 30262 +train: [7] [520/800] eta: 0:03:09 lr: 0.000278 loss: 0.1595 (0.2204) grad: 0.1375 (0.1416) time: 0.6074 data: 0.0025 max mem: 30262 +train: [7] [540/800] eta: 0:02:55 lr: 0.000277 loss: 0.1704 (0.2240) grad: 0.1375 (0.1456) time: 0.6468 data: 0.0036 max mem: 30262 +train: [7] [560/800] eta: 0:02:41 lr: 0.000277 loss: 0.1761 (0.2240) grad: 0.1506 (0.1469) time: 0.6338 data: 0.0033 max mem: 30262 +train: [7] [580/800] eta: 0:02:27 lr: 0.000276 loss: 0.1940 (0.2244) grad: 0.1344 (0.1459) time: 0.5881 data: 0.0034 max mem: 30262 +train: [7] [600/800] eta: 0:02:15 lr: 0.000276 loss: 0.1940 (0.2250) grad: 0.1324 (0.1443) time: 0.9217 data: 0.2973 max mem: 30262 +train: [7] [620/800] eta: 0:02:02 lr: 0.000275 loss: 0.1940 (0.2252) grad: 0.1283 (0.1446) time: 0.6433 data: 0.0038 max mem: 30262 +train: [7] [640/800] eta: 0:01:48 lr: 0.000275 loss: 0.1940 (0.2275) grad: 0.1095 (0.1444) time: 0.6092 data: 0.0040 max mem: 30262 +train: [7] [660/800] eta: 0:01:34 lr: 0.000275 loss: 0.2237 (0.2271) grad: 0.0945 (0.1426) time: 0.6023 data: 0.0167 max mem: 30262 +train: [7] [680/800] eta: 0:01:20 lr: 0.000274 loss: 0.2434 (0.2295) grad: 0.1095 (0.1420) time: 0.6006 data: 0.0031 max mem: 30262 +train: [7] [700/800] eta: 0:01:06 lr: 0.000274 loss: 0.2434 (0.2299) grad: 0.1075 (0.1413) time: 0.5689 data: 0.0022 max mem: 30262 +train: [7] [720/800] eta: 0:00:54 lr: 0.000273 loss: 0.2118 (0.2289) grad: 0.1085 (0.1423) time: 0.9776 data: 0.4045 max mem: 30262 +train: [7] [740/800] eta: 0:00:40 lr: 0.000273 loss: 0.2084 (0.2278) grad: 0.1129 (0.1418) time: 0.5999 data: 0.0022 max mem: 30262 +train: [7] [760/800] eta: 0:00:26 lr: 0.000272 loss: 0.1784 (0.2274) grad: 0.1146 (0.1413) time: 0.5765 data: 0.0032 max mem: 30262 +train: [7] [780/800] eta: 0:00:13 lr: 0.000272 loss: 0.1784 (0.2279) grad: 0.1195 (0.1414) time: 0.5855 data: 0.0022 max mem: 30262 +train: [7] [799/800] eta: 0:00:00 lr: 0.000271 loss: 0.1935 (0.2285) grad: 0.1224 (0.1416) time: 0.6058 data: 0.0035 max mem: 30262 +train: [7] Total time: 0:08:55 (0.6689 s / it) +train: [7] Summary: lr: 0.000271 loss: 0.1935 (0.2285) grad: 0.1224 (0.1416) +eval (validation): [7] [ 0/15] eta: 0:01:21 time: 5.4379 data: 5.1196 max mem: 30262 +eval (validation): [7] [14/15] eta: 0:00:00 time: 0.7863 data: 0.3664 max mem: 30262 +eval (validation): [7] Total time: 0:00:12 (0.8003 s / it) +cv: [7] best hparam: (3.7, 1.0) (032) ('032_lr3.7e+00_wd1.0e+00') loss: 0.632 acc: 0.948 f1: 0.945 bacc: 0.941 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_sex__patch__attn/checkpoint-last.pth +train: [8] [ 0/800] eta: 1:17:34 lr: nan time: 5.8184 data: 5.3086 max mem: 30262 +train: [8] [ 20/800] eta: 0:11:40 lr: 0.000271 loss: 0.2456 (0.2650) grad: 0.1424 (0.1332) time: 0.6514 data: 0.0518 max mem: 30262 +train: [8] [ 40/800] eta: 0:10:20 lr: 0.000270 loss: 0.1634 (0.2373) grad: 0.1424 (0.1373) time: 0.7326 data: 0.0919 max mem: 30262 +train: [8] [ 60/800] eta: 0:09:25 lr: 0.000270 loss: 0.2403 (0.2685) grad: 0.1386 (0.1399) time: 0.6565 data: 0.0789 max mem: 30262 +train: [8] [ 80/800] eta: 0:08:55 lr: 0.000270 loss: 0.1885 (0.2582) grad: 0.1286 (0.1343) time: 0.6817 data: 0.0937 max mem: 30262 +train: [8] [100/800] eta: 0:08:29 lr: 0.000269 loss: 0.1846 (0.2443) grad: 0.1062 (0.1340) time: 0.6619 data: 0.0041 max mem: 30262 +train: [8] [120/800] eta: 0:08:25 lr: 0.000269 loss: 0.2107 (0.2424) grad: 0.0994 (0.1294) time: 0.8191 data: 0.2706 max mem: 30262 +train: [8] [140/800] eta: 0:08:06 lr: 0.000268 loss: 0.1988 (0.2400) grad: 0.0960 (0.1292) time: 0.7008 data: 0.0943 max mem: 30262 +train: [8] [160/800] eta: 0:07:41 lr: 0.000268 loss: 0.2107 (0.2399) grad: 0.0960 (0.1249) time: 0.6110 data: 0.0031 max mem: 30262 +train: [8] [180/800] eta: 0:07:19 lr: 0.000267 loss: 0.2040 (0.2346) grad: 0.0947 (0.1259) time: 0.6141 data: 0.0041 max mem: 30262 +train: [8] [200/800] eta: 0:06:58 lr: 0.000267 loss: 0.2123 (0.2483) grad: 0.0960 (0.1300) time: 0.5817 data: 0.0025 max mem: 30262 +train: [8] [220/800] eta: 0:06:42 lr: 0.000266 loss: 0.1982 (0.2418) grad: 0.1285 (0.1319) time: 0.6605 data: 0.0966 max mem: 30262 +train: [8] [240/800] eta: 0:06:37 lr: 0.000266 loss: 0.2040 (0.2432) grad: 0.1332 (0.1384) time: 0.8924 data: 0.2826 max mem: 30262 +train: [8] [260/800] eta: 0:06:20 lr: 0.000265 loss: 0.2204 (0.2418) grad: 0.1419 (0.1434) time: 0.6465 data: 0.0044 max mem: 30262 +train: [8] [280/800] eta: 0:06:03 lr: 0.000265 loss: 0.2009 (0.2418) grad: 0.1419 (0.1443) time: 0.6297 data: 0.0028 max mem: 30262 +train: [8] [300/800] eta: 0:05:46 lr: 0.000264 loss: 0.2009 (0.2395) grad: 0.1280 (0.1432) time: 0.6107 data: 0.0042 max mem: 30262 +train: [8] [320/800] eta: 0:05:29 lr: 0.000264 loss: 0.1869 (0.2386) grad: 0.0979 (0.1399) time: 0.5853 data: 0.0036 max mem: 30262 +train: [8] [340/800] eta: 0:05:13 lr: 0.000263 loss: 0.1777 (0.2388) grad: 0.0964 (0.1396) time: 0.5944 data: 0.0031 max mem: 30262 +train: [8] [360/800] eta: 0:05:05 lr: 0.000263 loss: 0.1721 (0.2361) grad: 0.0964 (0.1381) time: 0.9105 data: 0.2958 max mem: 30262 +train: [8] [380/800] eta: 0:04:49 lr: 0.000262 loss: 0.1777 (0.2359) grad: 0.1125 (0.1410) time: 0.6107 data: 0.0033 max mem: 30262 +train: [8] [400/800] eta: 0:04:34 lr: 0.000262 loss: 0.1721 (0.2326) grad: 0.1302 (0.1383) time: 0.5982 data: 0.0037 max mem: 30262 +train: [8] [420/800] eta: 0:04:19 lr: 0.000261 loss: 0.1731 (0.2316) grad: 0.1079 (0.1362) time: 0.6075 data: 0.0039 max mem: 30262 +train: [8] [440/800] eta: 0:04:03 lr: 0.000260 loss: 0.1744 (0.2348) grad: 0.1240 (0.1370) time: 0.5868 data: 0.0035 max mem: 30262 +train: [8] [460/800] eta: 0:03:49 lr: 0.000260 loss: 0.1772 (0.2330) grad: 0.1048 (0.1375) time: 0.6060 data: 0.0031 max mem: 30262 +train: [8] [480/800] eta: 0:03:38 lr: 0.000259 loss: 0.2001 (0.2331) grad: 0.1048 (0.1357) time: 0.8968 data: 0.2931 max mem: 30262 +train: [8] [500/800] eta: 0:03:23 lr: 0.000259 loss: 0.2001 (0.2332) grad: 0.1230 (0.1344) time: 0.5950 data: 0.0031 max mem: 30262 +train: [8] [520/800] eta: 0:03:09 lr: 0.000258 loss: 0.2001 (0.2326) grad: 0.1045 (0.1354) time: 0.6433 data: 0.0034 max mem: 30262 +train: [8] [540/800] eta: 0:02:55 lr: 0.000258 loss: 0.2099 (0.2329) grad: 0.1181 (0.1355) time: 0.5749 data: 0.0032 max mem: 30262 +train: [8] [560/800] eta: 0:02:41 lr: 0.000257 loss: 0.1969 (0.2332) grad: 0.1230 (0.1355) time: 0.5720 data: 0.0027 max mem: 30262 +train: [8] [580/800] eta: 0:02:26 lr: 0.000257 loss: 0.1969 (0.2358) grad: 0.1239 (0.1357) time: 0.5583 data: 0.0029 max mem: 30262 +train: [8] [600/800] eta: 0:02:14 lr: 0.000256 loss: 0.1771 (0.2335) grad: 0.1239 (0.1349) time: 0.8728 data: 0.2658 max mem: 30262 +train: [8] [620/800] eta: 0:02:01 lr: 0.000256 loss: 0.1771 (0.2342) grad: 0.1218 (0.1360) time: 0.6371 data: 0.0038 max mem: 30262 +train: [8] [640/800] eta: 0:01:47 lr: 0.000255 loss: 0.2398 (0.2377) grad: 0.1101 (0.1374) time: 0.5767 data: 0.0031 max mem: 30262 +train: [8] [660/800] eta: 0:01:33 lr: 0.000254 loss: 0.2398 (0.2378) grad: 0.1101 (0.1384) time: 0.5889 data: 0.0042 max mem: 30262 +train: [8] [680/800] eta: 0:01:20 lr: 0.000254 loss: 0.2533 (0.2380) grad: 0.1257 (0.1391) time: 0.6939 data: 0.0974 max mem: 30262 +train: [8] [700/800] eta: 0:01:06 lr: 0.000253 loss: 0.2291 (0.2374) grad: 0.1071 (0.1382) time: 0.6537 data: 0.0799 max mem: 30262 +train: [8] [720/800] eta: 0:00:54 lr: 0.000253 loss: 0.2040 (0.2356) grad: 0.1198 (0.1373) time: 0.9901 data: 0.3403 max mem: 30262 +train: [8] [740/800] eta: 0:00:40 lr: 0.000252 loss: 0.1999 (0.2348) grad: 0.1024 (0.1373) time: 0.5906 data: 0.0030 max mem: 30262 +train: [8] [760/800] eta: 0:00:26 lr: 0.000252 loss: 0.1999 (0.2348) grad: 0.0981 (0.1369) time: 0.5966 data: 0.0032 max mem: 30262 +train: [8] [780/800] eta: 0:00:13 lr: 0.000251 loss: 0.1999 (0.2354) grad: 0.0903 (0.1366) time: 0.5823 data: 0.0033 max mem: 30262 +train: [8] [799/800] eta: 0:00:00 lr: 0.000250 loss: 0.1999 (0.2335) grad: 0.1012 (0.1361) time: 0.5802 data: 0.0022 max mem: 30262 +train: [8] Total time: 0:08:54 (0.6682 s / it) +train: [8] Summary: lr: 0.000250 loss: 0.1999 (0.2335) grad: 0.1012 (0.1361) +eval (validation): [8] [ 0/15] eta: 0:01:22 time: 5.4952 data: 5.1324 max mem: 30262 +eval (validation): [8] [14/15] eta: 0:00:00 time: 0.8877 data: 0.4154 max mem: 30262 +eval (validation): [8] Total time: 0:00:13 (0.9029 s / it) +cv: [8] best hparam: (3.7, 1.0) (032) ('032_lr3.7e+00_wd1.0e+00') loss: 0.650 acc: 0.948 f1: 0.945 bacc: 0.941 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_sex__patch__attn/checkpoint-last.pth +train: [9] [ 0/800] eta: 1:16:22 lr: nan time: 5.7280 data: 5.2476 max mem: 30262 +train: [9] [ 20/800] eta: 0:12:01 lr: 0.000250 loss: 0.2118 (0.2024) grad: 0.1010 (0.1099) time: 0.6846 data: 0.0697 max mem: 30262 +train: [9] [ 40/800] eta: 0:10:30 lr: 0.000249 loss: 0.2131 (0.2129) grad: 0.1010 (0.1078) time: 0.7305 data: 0.1305 max mem: 30262 +train: [9] [ 60/800] eta: 0:09:46 lr: 0.000249 loss: 0.2118 (0.1964) grad: 0.1219 (0.1313) time: 0.7138 data: 0.1417 max mem: 30262 +train: [9] [ 80/800] eta: 0:09:27 lr: 0.000248 loss: 0.2118 (0.2035) grad: 0.1219 (0.1357) time: 0.7753 data: 0.1531 max mem: 30262 +train: [9] [100/800] eta: 0:08:59 lr: 0.000248 loss: 0.1990 (0.2100) grad: 0.1219 (0.1296) time: 0.6995 data: 0.1291 max mem: 30262 +train: [9] [120/800] eta: 0:08:57 lr: 0.000247 loss: 0.1946 (0.2167) grad: 0.1247 (0.1308) time: 0.8909 data: 0.3231 max mem: 30262 +train: [9] [140/800] eta: 0:08:29 lr: 0.000246 loss: 0.2275 (0.2252) grad: 0.1157 (0.1351) time: 0.6665 data: 0.0914 max mem: 30262 +train: [9] [160/800] eta: 0:08:04 lr: 0.000246 loss: 0.1912 (0.2168) grad: 0.1090 (0.1336) time: 0.6489 data: 0.0823 max mem: 30262 +train: [9] [180/800] eta: 0:07:46 lr: 0.000245 loss: 0.1912 (0.2177) grad: 0.1133 (0.1343) time: 0.7119 data: 0.1213 max mem: 30262 +train: [9] [200/800] eta: 0:07:22 lr: 0.000244 loss: 0.2275 (0.2221) grad: 0.1040 (0.1311) time: 0.6104 data: 0.0398 max mem: 30262 +train: [9] [220/800] eta: 0:07:01 lr: 0.000244 loss: 0.1878 (0.2218) grad: 0.0894 (0.1312) time: 0.6134 data: 0.0643 max mem: 30262 +train: [9] [240/800] eta: 0:06:52 lr: 0.000243 loss: 0.1868 (0.2159) grad: 0.1040 (0.1301) time: 0.8485 data: 0.2847 max mem: 30262 +train: [9] [260/800] eta: 0:06:33 lr: 0.000243 loss: 0.1869 (0.2245) grad: 0.0932 (0.1384) time: 0.6298 data: 0.0047 max mem: 30262 +train: [9] [280/800] eta: 0:06:14 lr: 0.000242 loss: 0.1742 (0.2214) grad: 0.1056 (0.1383) time: 0.6210 data: 0.0039 max mem: 30262 +train: [9] [300/800] eta: 0:05:57 lr: 0.000241 loss: 0.1742 (0.2198) grad: 0.1156 (0.1401) time: 0.6221 data: 0.0045 max mem: 30262 +train: [9] [320/800] eta: 0:05:41 lr: 0.000241 loss: 0.1843 (0.2195) grad: 0.1259 (0.1406) time: 0.6506 data: 0.0039 max mem: 30262 +train: [9] [340/800] eta: 0:05:25 lr: 0.000240 loss: 0.1937 (0.2228) grad: 0.1489 (0.1423) time: 0.6468 data: 0.0039 max mem: 30262 +train: [9] [360/800] eta: 0:05:16 lr: 0.000240 loss: 0.1942 (0.2229) grad: 0.1489 (0.1428) time: 0.9386 data: 0.3370 max mem: 30262 +train: [9] [380/800] eta: 0:05:00 lr: 0.000239 loss: 0.1937 (0.2211) grad: 0.1266 (0.1420) time: 0.6264 data: 0.0028 max mem: 30262 +train: [9] [400/800] eta: 0:04:44 lr: 0.000238 loss: 0.1937 (0.2199) grad: 0.1236 (0.1412) time: 0.6240 data: 0.0038 max mem: 30262 +train: [9] [420/800] eta: 0:04:27 lr: 0.000238 loss: 0.1743 (0.2203) grad: 0.1165 (0.1401) time: 0.5950 data: 0.0035 max mem: 30262 +train: [9] [440/800] eta: 0:04:11 lr: 0.000237 loss: 0.1943 (0.2221) grad: 0.1043 (0.1390) time: 0.5770 data: 0.0036 max mem: 30262 +train: [9] [460/800] eta: 0:03:55 lr: 0.000236 loss: 0.1828 (0.2222) grad: 0.1005 (0.1404) time: 0.5803 data: 0.0028 max mem: 30262 +train: [9] [480/800] eta: 0:03:44 lr: 0.000236 loss: 0.1828 (0.2205) grad: 0.1092 (0.1408) time: 0.8980 data: 0.2980 max mem: 30262 +train: [9] [500/800] eta: 0:03:29 lr: 0.000235 loss: 0.1828 (0.2203) grad: 0.1257 (0.1409) time: 0.5973 data: 0.0030 max mem: 30262 +train: [9] [520/800] eta: 0:03:14 lr: 0.000234 loss: 0.1799 (0.2209) grad: 0.1257 (0.1407) time: 0.6332 data: 0.0042 max mem: 30262 +train: [9] [540/800] eta: 0:02:59 lr: 0.000234 loss: 0.1887 (0.2205) grad: 0.1383 (0.1428) time: 0.5754 data: 0.0044 max mem: 30262 +train: [9] [560/800] eta: 0:02:45 lr: 0.000233 loss: 0.1946 (0.2197) grad: 0.1102 (0.1421) time: 0.6050 data: 0.0339 max mem: 30262 +train: [9] [580/800] eta: 0:02:30 lr: 0.000232 loss: 0.1946 (0.2204) grad: 0.1010 (0.1425) time: 0.5958 data: 0.0368 max mem: 30262 +train: [9] [600/800] eta: 0:02:18 lr: 0.000232 loss: 0.1846 (0.2193) grad: 0.1102 (0.1426) time: 0.8994 data: 0.3109 max mem: 30262 +train: [9] [620/800] eta: 0:02:04 lr: 0.000231 loss: 0.2069 (0.2199) grad: 0.1076 (0.1428) time: 0.6139 data: 0.0294 max mem: 30262 +train: [9] [640/800] eta: 0:01:49 lr: 0.000230 loss: 0.2100 (0.2214) grad: 0.1076 (0.1438) time: 0.5844 data: 0.0029 max mem: 30262 +train: [9] [660/800] eta: 0:01:35 lr: 0.000230 loss: 0.2100 (0.2217) grad: 0.1076 (0.1428) time: 0.5710 data: 0.0029 max mem: 30262 +train: [9] [680/800] eta: 0:01:21 lr: 0.000229 loss: 0.1900 (0.2199) grad: 0.1039 (0.1417) time: 0.5936 data: 0.0037 max mem: 30262 +train: [9] [700/800] eta: 0:01:07 lr: 0.000228 loss: 0.1900 (0.2202) grad: 0.0996 (0.1409) time: 0.5814 data: 0.0033 max mem: 30262 +train: [9] [720/800] eta: 0:00:54 lr: 0.000228 loss: 0.1900 (0.2205) grad: 0.0926 (0.1396) time: 0.9394 data: 0.3510 max mem: 30262 +train: [9] [740/800] eta: 0:00:41 lr: 0.000227 loss: 0.1838 (0.2199) grad: 0.0926 (0.1386) time: 0.6791 data: 0.0576 max mem: 30262 +train: [9] [760/800] eta: 0:00:27 lr: 0.000226 loss: 0.2063 (0.2184) grad: 0.0996 (0.1382) time: 0.5980 data: 0.0027 max mem: 30262 +train: [9] [780/800] eta: 0:00:13 lr: 0.000226 loss: 0.2063 (0.2186) grad: 0.1028 (0.1378) time: 0.5862 data: 0.0041 max mem: 30262 +train: [9] [799/800] eta: 0:00:00 lr: 0.000225 loss: 0.1945 (0.2184) grad: 0.1093 (0.1384) time: 0.5977 data: 0.0035 max mem: 30262 +train: [9] Total time: 0:09:02 (0.6781 s / it) +train: [9] Summary: lr: 0.000225 loss: 0.1945 (0.2184) grad: 0.1093 (0.1384) +eval (validation): [9] [ 0/15] eta: 0:01:17 time: 5.1557 data: 4.8487 max mem: 30262 +eval (validation): [9] [14/15] eta: 0:00:00 time: 0.7665 data: 0.3399 max mem: 30262 +eval (validation): [9] Total time: 0:00:11 (0.7835 s / it) +cv: [9] best hparam: (3.7, 1.0) (032) ('032_lr3.7e+00_wd1.0e+00') loss: 0.663 acc: 0.948 f1: 0.945 bacc: 0.941 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_sex__patch__attn/checkpoint-last.pth +train: [10] [ 0/800] eta: 1:12:19 lr: nan time: 5.4238 data: 4.9715 max mem: 30262 +train: [10] [ 20/800] eta: 0:12:37 lr: 0.000224 loss: 0.2440 (0.2353) grad: 0.1206 (0.1118) time: 0.7492 data: 0.0841 max mem: 30262 +train: [10] [ 40/800] eta: 0:09:51 lr: 0.000224 loss: 0.1794 (0.2215) grad: 0.0916 (0.1074) time: 0.5762 data: 0.0027 max mem: 30262 +train: [10] [ 60/800] eta: 0:08:49 lr: 0.000223 loss: 0.1700 (0.1976) grad: 0.0916 (0.0972) time: 0.5877 data: 0.0035 max mem: 30262 +train: [10] [ 80/800] eta: 0:08:12 lr: 0.000222 loss: 0.1750 (0.2071) grad: 0.0926 (0.1054) time: 0.5864 data: 0.0032 max mem: 30262 +train: [10] [100/800] eta: 0:07:44 lr: 0.000222 loss: 0.1750 (0.2072) grad: 0.0926 (0.1151) time: 0.5781 data: 0.0030 max mem: 30262 +train: [10] [120/800] eta: 0:07:48 lr: 0.000221 loss: 0.1776 (0.2047) grad: 0.1077 (0.1185) time: 0.8214 data: 0.2722 max mem: 30262 +train: [10] [140/800] eta: 0:07:31 lr: 0.000220 loss: 0.1852 (0.2162) grad: 0.1170 (0.1209) time: 0.6482 data: 0.0480 max mem: 30262 +train: [10] [160/800] eta: 0:07:09 lr: 0.000220 loss: 0.1840 (0.2121) grad: 0.1108 (0.1198) time: 0.5901 data: 0.0036 max mem: 30262 +train: [10] [180/800] eta: 0:06:50 lr: 0.000219 loss: 0.1840 (0.2106) grad: 0.1077 (0.1186) time: 0.5827 data: 0.0037 max mem: 30262 +train: [10] [200/800] eta: 0:06:32 lr: 0.000218 loss: 0.1840 (0.2134) grad: 0.1050 (0.1246) time: 0.5753 data: 0.0031 max mem: 30262 +train: [10] [220/800] eta: 0:06:14 lr: 0.000217 loss: 0.1908 (0.2170) grad: 0.1050 (0.1258) time: 0.5622 data: 0.0031 max mem: 30262 +train: [10] [240/800] eta: 0:06:09 lr: 0.000217 loss: 0.2022 (0.2202) grad: 0.1255 (0.1266) time: 0.8272 data: 0.2806 max mem: 30262 +train: [10] [260/800] eta: 0:05:54 lr: 0.000216 loss: 0.2434 (0.2199) grad: 0.1255 (0.1256) time: 0.6165 data: 0.0168 max mem: 30262 +train: [10] [280/800] eta: 0:05:41 lr: 0.000215 loss: 0.2022 (0.2177) grad: 0.1166 (0.1257) time: 0.6590 data: 0.0089 max mem: 30262 +train: [10] [300/800] eta: 0:05:26 lr: 0.000215 loss: 0.2146 (0.2188) grad: 0.1115 (0.1258) time: 0.5837 data: 0.0028 max mem: 30262 +train: [10] [320/800] eta: 0:05:11 lr: 0.000214 loss: 0.2194 (0.2225) grad: 0.1161 (0.1272) time: 0.5922 data: 0.0032 max mem: 30262 +train: [10] [340/800] eta: 0:04:56 lr: 0.000213 loss: 0.1906 (0.2196) grad: 0.1161 (0.1287) time: 0.5895 data: 0.0032 max mem: 30262 +train: [10] [360/800] eta: 0:04:49 lr: 0.000213 loss: 0.2194 (0.2197) grad: 0.1251 (0.1299) time: 0.8677 data: 0.3087 max mem: 30262 +train: [10] [380/800] eta: 0:04:35 lr: 0.000212 loss: 0.2194 (0.2226) grad: 0.1251 (0.1293) time: 0.6153 data: 0.0429 max mem: 30262 +train: [10] [400/800] eta: 0:04:20 lr: 0.000211 loss: 0.1962 (0.2232) grad: 0.1229 (0.1294) time: 0.5775 data: 0.0030 max mem: 30262 +train: [10] [420/800] eta: 0:04:06 lr: 0.000210 loss: 0.2157 (0.2231) grad: 0.1229 (0.1290) time: 0.5865 data: 0.0034 max mem: 30262 +train: [10] [440/800] eta: 0:03:52 lr: 0.000210 loss: 0.1831 (0.2229) grad: 0.1032 (0.1282) time: 0.6096 data: 0.0317 max mem: 30262 +train: [10] [460/800] eta: 0:03:39 lr: 0.000209 loss: 0.1831 (0.2235) grad: 0.1066 (0.1284) time: 0.6119 data: 0.0452 max mem: 30262 +train: [10] [480/800] eta: 0:03:29 lr: 0.000208 loss: 0.1708 (0.2209) grad: 0.0845 (0.1269) time: 0.8693 data: 0.2687 max mem: 30262 +train: [10] [500/800] eta: 0:03:15 lr: 0.000207 loss: 0.1574 (0.2198) grad: 0.0845 (0.1259) time: 0.5789 data: 0.0028 max mem: 30262 +train: [10] [520/800] eta: 0:03:01 lr: 0.000207 loss: 0.1638 (0.2202) grad: 0.1263 (0.1285) time: 0.5734 data: 0.0034 max mem: 30262 +train: [10] [540/800] eta: 0:02:47 lr: 0.000206 loss: 0.1638 (0.2187) grad: 0.1263 (0.1282) time: 0.5902 data: 0.0036 max mem: 30262 +train: [10] [560/800] eta: 0:02:34 lr: 0.000205 loss: 0.2023 (0.2227) grad: 0.1263 (0.1281) time: 0.5773 data: 0.0037 max mem: 30262 +train: [10] [580/800] eta: 0:02:20 lr: 0.000205 loss: 0.2228 (0.2230) grad: 0.1263 (0.1281) time: 0.5621 data: 0.0029 max mem: 30262 +train: [10] [600/800] eta: 0:02:09 lr: 0.000204 loss: 0.2023 (0.2217) grad: 0.1232 (0.1285) time: 0.8762 data: 0.2591 max mem: 30262 +train: [10] [620/800] eta: 0:01:56 lr: 0.000203 loss: 0.2150 (0.2212) grad: 0.1151 (0.1289) time: 0.5849 data: 0.0031 max mem: 30262 +train: [10] [640/800] eta: 0:01:43 lr: 0.000202 loss: 0.1925 (0.2221) grad: 0.1143 (0.1288) time: 0.5732 data: 0.0033 max mem: 30262 +train: [10] [660/800] eta: 0:01:29 lr: 0.000202 loss: 0.1925 (0.2237) grad: 0.1143 (0.1287) time: 0.5750 data: 0.0035 max mem: 30262 +train: [10] [680/800] eta: 0:01:16 lr: 0.000201 loss: 0.2306 (0.2255) grad: 0.1143 (0.1319) time: 0.5790 data: 0.0037 max mem: 30262 +train: [10] [700/800] eta: 0:01:03 lr: 0.000200 loss: 0.2117 (0.2257) grad: 0.1224 (0.1326) time: 0.5805 data: 0.0035 max mem: 30262 +train: [10] [720/800] eta: 0:00:51 lr: 0.000199 loss: 0.2109 (0.2241) grad: 0.1224 (0.1322) time: 0.9390 data: 0.2739 max mem: 30262 +train: [10] [740/800] eta: 0:00:38 lr: 0.000199 loss: 0.2109 (0.2248) grad: 0.1373 (0.1330) time: 0.6104 data: 0.0036 max mem: 30262 +train: [10] [760/800] eta: 0:00:25 lr: 0.000198 loss: 0.1870 (0.2243) grad: 0.1373 (0.1337) time: 0.5817 data: 0.0037 max mem: 30262 +train: [10] [780/800] eta: 0:00:12 lr: 0.000197 loss: 0.1979 (0.2242) grad: 0.1373 (0.1334) time: 0.5727 data: 0.0031 max mem: 30262 +train: [10] [799/800] eta: 0:00:00 lr: 0.000196 loss: 0.1870 (0.2232) grad: 0.1441 (0.1350) time: 0.5583 data: 0.0031 max mem: 30262 +train: [10] Total time: 0:08:32 (0.6408 s / it) +train: [10] Summary: lr: 0.000196 loss: 0.1870 (0.2232) grad: 0.1441 (0.1350) +eval (validation): [10] [ 0/15] eta: 0:01:18 time: 5.2606 data: 4.9389 max mem: 30262 +eval (validation): [10] [14/15] eta: 0:00:00 time: 0.7653 data: 0.3553 max mem: 30262 +eval (validation): [10] Total time: 0:00:11 (0.7805 s / it) +cv: [10] best hparam: (3.7, 1.0) (032) ('032_lr3.7e+00_wd1.0e+00') loss: 0.674 acc: 0.948 f1: 0.945 bacc: 0.941 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_sex__patch__attn/checkpoint-last.pth +train: [11] [ 0/800] eta: 1:12:53 lr: nan time: 5.4674 data: 4.9858 max mem: 30262 +train: [11] [ 20/800] eta: 0:11:46 lr: 0.000196 loss: 0.1918 (0.1889) grad: 0.1490 (0.1567) time: 0.6778 data: 0.0041 max mem: 30262 +train: [11] [ 40/800] eta: 0:09:43 lr: 0.000195 loss: 0.1708 (0.1987) grad: 0.1476 (0.1622) time: 0.6217 data: 0.0526 max mem: 30262 +train: [11] [ 60/800] eta: 0:08:56 lr: 0.000194 loss: 0.1708 (0.1983) grad: 0.1221 (0.1340) time: 0.6401 data: 0.0869 max mem: 30262 +train: [11] [ 80/800] eta: 0:08:21 lr: 0.000193 loss: 0.1708 (0.1993) grad: 0.1081 (0.1367) time: 0.6098 data: 0.0617 max mem: 30262 +train: [11] [100/800] eta: 0:08:02 lr: 0.000193 loss: 0.1708 (0.2182) grad: 0.1081 (0.1430) time: 0.6596 data: 0.0959 max mem: 30262 +train: [11] [120/800] eta: 0:08:04 lr: 0.000192 loss: 0.1768 (0.2124) grad: 0.0870 (0.1370) time: 0.8262 data: 0.2798 max mem: 30262 +train: [11] [140/800] eta: 0:07:44 lr: 0.000191 loss: 0.1768 (0.2098) grad: 0.0987 (0.1320) time: 0.6503 data: 0.0618 max mem: 30262 +train: [11] [160/800] eta: 0:07:23 lr: 0.000190 loss: 0.1687 (0.2049) grad: 0.0964 (0.1254) time: 0.6201 data: 0.0044 max mem: 30262 +train: [11] [180/800] eta: 0:07:04 lr: 0.000190 loss: 0.1687 (0.2068) grad: 0.0914 (0.1252) time: 0.6209 data: 0.0031 max mem: 30262 +train: [11] [200/800] eta: 0:06:43 lr: 0.000189 loss: 0.1710 (0.2102) grad: 0.0914 (0.1292) time: 0.5628 data: 0.0036 max mem: 30262 +train: [11] [220/800] eta: 0:06:24 lr: 0.000188 loss: 0.1710 (0.2068) grad: 0.0948 (0.1338) time: 0.5632 data: 0.0027 max mem: 30262 +train: [11] [240/800] eta: 0:06:23 lr: 0.000187 loss: 0.1728 (0.2058) grad: 0.1436 (0.1336) time: 0.9337 data: 0.3501 max mem: 30262 +train: [11] [260/800] eta: 0:06:06 lr: 0.000187 loss: 0.1850 (0.2066) grad: 0.1468 (0.1328) time: 0.5881 data: 0.0035 max mem: 30262 +train: [11] [280/800] eta: 0:05:48 lr: 0.000186 loss: 0.1850 (0.2082) grad: 0.1160 (0.1310) time: 0.5651 data: 0.0031 max mem: 30262 +train: [11] [300/800] eta: 0:05:31 lr: 0.000185 loss: 0.1850 (0.2147) grad: 0.1023 (0.1316) time: 0.5697 data: 0.0036 max mem: 30262 +train: [11] [320/800] eta: 0:05:15 lr: 0.000184 loss: 0.1746 (0.2140) grad: 0.0873 (0.1307) time: 0.5783 data: 0.0039 max mem: 30262 +train: [11] [340/800] eta: 0:05:00 lr: 0.000184 loss: 0.1641 (0.2133) grad: 0.0819 (0.1271) time: 0.5664 data: 0.0034 max mem: 30262 +train: [11] [360/800] eta: 0:04:52 lr: 0.000183 loss: 0.1517 (0.2092) grad: 0.0671 (0.1257) time: 0.8916 data: 0.3280 max mem: 30262 +train: [11] [380/800] eta: 0:04:37 lr: 0.000182 loss: 0.1517 (0.2101) grad: 0.0907 (0.1270) time: 0.5873 data: 0.0029 max mem: 30262 +train: [11] [400/800] eta: 0:04:22 lr: 0.000181 loss: 0.1525 (0.2109) grad: 0.0907 (0.1256) time: 0.5764 data: 0.0041 max mem: 30262 +train: [11] [420/800] eta: 0:04:08 lr: 0.000181 loss: 0.1525 (0.2088) grad: 0.1072 (0.1278) time: 0.5726 data: 0.0035 max mem: 30262 +train: [11] [440/800] eta: 0:03:54 lr: 0.000180 loss: 0.2150 (0.2113) grad: 0.1157 (0.1275) time: 0.6178 data: 0.0664 max mem: 30262 +train: [11] [460/800] eta: 0:03:40 lr: 0.000179 loss: 0.2150 (0.2118) grad: 0.1009 (0.1267) time: 0.6067 data: 0.0390 max mem: 30262 +train: [11] [480/800] eta: 0:03:30 lr: 0.000178 loss: 0.2150 (0.2166) grad: 0.0944 (0.1254) time: 0.8415 data: 0.2732 max mem: 30262 +train: [11] [500/800] eta: 0:03:17 lr: 0.000177 loss: 0.2199 (0.2171) grad: 0.0896 (0.1269) time: 0.6669 data: 0.1085 max mem: 30262 +train: [11] [520/800] eta: 0:03:04 lr: 0.000177 loss: 0.1913 (0.2162) grad: 0.0796 (0.1273) time: 0.6726 data: 0.0039 max mem: 30262 +train: [11] [540/800] eta: 0:02:51 lr: 0.000176 loss: 0.1813 (0.2143) grad: 0.0859 (0.1267) time: 0.6328 data: 0.0026 max mem: 30262 +train: [11] [560/800] eta: 0:02:37 lr: 0.000175 loss: 0.1813 (0.2150) grad: 0.1024 (0.1273) time: 0.6012 data: 0.0040 max mem: 30262 +train: [11] [580/800] eta: 0:02:23 lr: 0.000174 loss: 0.1520 (0.2130) grad: 0.0898 (0.1268) time: 0.5644 data: 0.0035 max mem: 30262 +train: [11] [600/800] eta: 0:02:11 lr: 0.000174 loss: 0.1520 (0.2140) grad: 0.1015 (0.1268) time: 0.8300 data: 0.2660 max mem: 30262 +train: [11] [620/800] eta: 0:01:58 lr: 0.000173 loss: 0.1734 (0.2151) grad: 0.0987 (0.1264) time: 0.5901 data: 0.0138 max mem: 30262 +train: [11] [640/800] eta: 0:01:44 lr: 0.000172 loss: 0.1734 (0.2145) grad: 0.0987 (0.1265) time: 0.6093 data: 0.0272 max mem: 30262 +train: [11] [660/800] eta: 0:01:31 lr: 0.000171 loss: 0.2023 (0.2160) grad: 0.1066 (0.1270) time: 0.6112 data: 0.0038 max mem: 30262 +train: [11] [680/800] eta: 0:01:18 lr: 0.000170 loss: 0.1985 (0.2148) grad: 0.0976 (0.1267) time: 0.5748 data: 0.0030 max mem: 30262 +train: [11] [700/800] eta: 0:01:04 lr: 0.000170 loss: 0.1867 (0.2134) grad: 0.1173 (0.1275) time: 0.5606 data: 0.0027 max mem: 30262 +train: [11] [720/800] eta: 0:00:52 lr: 0.000169 loss: 0.1671 (0.2120) grad: 0.1164 (0.1273) time: 0.8213 data: 0.2719 max mem: 30262 +train: [11] [740/800] eta: 0:00:39 lr: 0.000168 loss: 0.1628 (0.2119) grad: 0.1162 (0.1279) time: 0.6723 data: 0.1120 max mem: 30262 +train: [11] [760/800] eta: 0:00:26 lr: 0.000167 loss: 0.1641 (0.2108) grad: 0.1164 (0.1281) time: 0.5773 data: 0.0034 max mem: 30262 +train: [11] [780/800] eta: 0:00:13 lr: 0.000167 loss: 0.1655 (0.2107) grad: 0.1018 (0.1294) time: 0.5820 data: 0.0037 max mem: 30262 +train: [11] [799/800] eta: 0:00:00 lr: 0.000166 loss: 0.1668 (0.2108) grad: 0.1079 (0.1294) time: 0.5799 data: 0.0032 max mem: 30262 +train: [11] Total time: 0:08:38 (0.6487 s / it) +train: [11] Summary: lr: 0.000166 loss: 0.1668 (0.2108) grad: 0.1079 (0.1294) +eval (validation): [11] [ 0/15] eta: 0:01:18 time: 5.2141 data: 4.9051 max mem: 30262 +eval (validation): [11] [14/15] eta: 0:00:00 time: 0.8861 data: 0.4864 max mem: 30262 +eval (validation): [11] Total time: 0:00:13 (0.8995 s / it) +cv: [11] best hparam: (3.7, 1.0) (032) ('032_lr3.7e+00_wd1.0e+00') loss: 0.680 acc: 0.948 f1: 0.945 bacc: 0.941 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_sex__patch__attn/checkpoint-last.pth +train: [12] [ 0/800] eta: 1:12:47 lr: nan time: 5.4590 data: 4.9735 max mem: 30262 +train: [12] [ 20/800] eta: 0:10:47 lr: 0.000165 loss: 0.1582 (0.1656) grad: 0.1317 (0.1231) time: 0.5989 data: 0.0032 max mem: 30262 +train: [12] [ 40/800] eta: 0:08:52 lr: 0.000164 loss: 0.1582 (0.1673) grad: 0.0741 (0.0955) time: 0.5655 data: 0.0032 max mem: 30262 +train: [12] [ 60/800] eta: 0:08:13 lr: 0.000163 loss: 0.1700 (0.1787) grad: 0.0801 (0.1135) time: 0.5983 data: 0.0033 max mem: 30262 +train: [12] [ 80/800] eta: 0:07:45 lr: 0.000163 loss: 0.1697 (0.1802) grad: 0.0801 (0.1054) time: 0.5822 data: 0.0040 max mem: 30262 +train: [12] [100/800] eta: 0:07:20 lr: 0.000162 loss: 0.1700 (0.1981) grad: 0.0804 (0.1087) time: 0.5615 data: 0.0028 max mem: 30262 +train: [12] [120/800] eta: 0:07:27 lr: 0.000161 loss: 0.1722 (0.2018) grad: 0.1035 (0.1210) time: 0.7993 data: 0.2673 max mem: 30262 +train: [12] [140/800] eta: 0:07:08 lr: 0.000160 loss: 0.1697 (0.2053) grad: 0.1005 (0.1172) time: 0.5977 data: 0.0394 max mem: 30262 +train: [12] [160/800] eta: 0:06:55 lr: 0.000160 loss: 0.1900 (0.2080) grad: 0.1028 (0.1188) time: 0.6466 data: 0.0987 max mem: 30262 +train: [12] [180/800] eta: 0:06:38 lr: 0.000159 loss: 0.1951 (0.2169) grad: 0.1026 (0.1182) time: 0.5892 data: 0.0426 max mem: 30262 +train: [12] [200/800] eta: 0:06:20 lr: 0.000158 loss: 0.2185 (0.2235) grad: 0.1026 (0.1208) time: 0.5613 data: 0.0029 max mem: 30262 +train: [12] [220/800] eta: 0:06:04 lr: 0.000157 loss: 0.2185 (0.2229) grad: 0.1026 (0.1201) time: 0.5640 data: 0.0026 max mem: 30262 +train: [12] [240/800] eta: 0:06:02 lr: 0.000156 loss: 0.2336 (0.2207) grad: 0.1191 (0.1223) time: 0.8647 data: 0.2721 max mem: 30262 +train: [12] [260/800] eta: 0:05:47 lr: 0.000156 loss: 0.1962 (0.2202) grad: 0.1191 (0.1219) time: 0.5934 data: 0.0035 max mem: 30262 +train: [12] [280/800] eta: 0:05:31 lr: 0.000155 loss: 0.1962 (0.2209) grad: 0.1191 (0.1245) time: 0.5606 data: 0.0034 max mem: 30262 +train: [12] [300/800] eta: 0:05:16 lr: 0.000154 loss: 0.1903 (0.2180) grad: 0.1254 (0.1273) time: 0.5782 data: 0.0031 max mem: 30262 +train: [12] [320/800] eta: 0:05:01 lr: 0.000153 loss: 0.1866 (0.2201) grad: 0.0932 (0.1248) time: 0.5600 data: 0.0034 max mem: 30262 +train: [12] [340/800] eta: 0:04:47 lr: 0.000152 loss: 0.1776 (0.2180) grad: 0.1060 (0.1236) time: 0.5503 data: 0.0025 max mem: 30262 +train: [12] [360/800] eta: 0:04:41 lr: 0.000152 loss: 0.1776 (0.2180) grad: 0.0972 (0.1223) time: 0.8923 data: 0.2719 max mem: 30262 +train: [12] [380/800] eta: 0:04:27 lr: 0.000151 loss: 0.1776 (0.2191) grad: 0.1066 (0.1280) time: 0.5816 data: 0.0023 max mem: 30262 +train: [12] [400/800] eta: 0:04:13 lr: 0.000150 loss: 0.1845 (0.2197) grad: 0.1182 (0.1295) time: 0.5749 data: 0.0040 max mem: 30262 +train: [12] [420/800] eta: 0:03:59 lr: 0.000149 loss: 0.1845 (0.2191) grad: 0.1328 (0.1305) time: 0.5689 data: 0.0057 max mem: 30262 +train: [12] [440/800] eta: 0:03:46 lr: 0.000149 loss: 0.1599 (0.2182) grad: 0.1328 (0.1295) time: 0.6043 data: 0.0524 max mem: 30262 +train: [12] [460/800] eta: 0:03:33 lr: 0.000148 loss: 0.1599 (0.2196) grad: 0.1084 (0.1287) time: 0.6050 data: 0.0175 max mem: 30262 +train: [12] [480/800] eta: 0:03:24 lr: 0.000147 loss: 0.1568 (0.2176) grad: 0.1011 (0.1288) time: 0.8719 data: 0.3206 max mem: 30262 +train: [12] [500/800] eta: 0:03:11 lr: 0.000146 loss: 0.1623 (0.2171) grad: 0.0942 (0.1274) time: 0.6175 data: 0.0159 max mem: 30262 +train: [12] [520/800] eta: 0:02:57 lr: 0.000145 loss: 0.1568 (0.2140) grad: 0.1002 (0.1277) time: 0.5792 data: 0.0028 max mem: 30262 +train: [12] [540/800] eta: 0:02:44 lr: 0.000145 loss: 0.1615 (0.2132) grad: 0.0856 (0.1260) time: 0.5859 data: 0.0040 max mem: 30262 +train: [12] [560/800] eta: 0:02:31 lr: 0.000144 loss: 0.1615 (0.2110) grad: 0.0898 (0.1250) time: 0.5702 data: 0.0036 max mem: 30262 +train: [12] [580/800] eta: 0:02:18 lr: 0.000143 loss: 0.1615 (0.2148) grad: 0.1082 (0.1268) time: 0.5706 data: 0.0034 max mem: 30262 +train: [12] [600/800] eta: 0:02:07 lr: 0.000142 loss: 0.1725 (0.2143) grad: 0.1082 (0.1265) time: 0.8609 data: 0.2781 max mem: 30262 +train: [12] [620/800] eta: 0:01:54 lr: 0.000141 loss: 0.1749 (0.2132) grad: 0.1115 (0.1256) time: 0.5568 data: 0.0034 max mem: 30262 +train: [12] [640/800] eta: 0:01:41 lr: 0.000141 loss: 0.1753 (0.2123) grad: 0.1232 (0.1256) time: 0.5686 data: 0.0035 max mem: 30262 +train: [12] [660/800] eta: 0:01:28 lr: 0.000140 loss: 0.1700 (0.2111) grad: 0.1003 (0.1253) time: 0.5705 data: 0.0034 max mem: 30262 +train: [12] [680/800] eta: 0:01:15 lr: 0.000139 loss: 0.1700 (0.2094) grad: 0.0932 (0.1244) time: 0.5601 data: 0.0039 max mem: 30262 +train: [12] [700/800] eta: 0:01:02 lr: 0.000138 loss: 0.1416 (0.2072) grad: 0.0918 (0.1235) time: 0.5947 data: 0.0024 max mem: 30262 +train: [12] [720/800] eta: 0:00:50 lr: 0.000138 loss: 0.1438 (0.2063) grad: 0.0893 (0.1222) time: 0.9153 data: 0.3216 max mem: 30262 +train: [12] [740/800] eta: 0:00:38 lr: 0.000137 loss: 0.1438 (0.2064) grad: 0.0817 (0.1231) time: 0.6223 data: 0.0223 max mem: 30262 +train: [12] [760/800] eta: 0:00:25 lr: 0.000136 loss: 0.1600 (0.2067) grad: 0.0893 (0.1237) time: 0.6634 data: 0.0041 max mem: 30262 +train: [12] [780/800] eta: 0:00:12 lr: 0.000135 loss: 0.1878 (0.2074) grad: 0.0893 (0.1240) time: 0.5915 data: 0.0039 max mem: 30262 +train: [12] [799/800] eta: 0:00:00 lr: 0.000134 loss: 0.1808 (0.2062) grad: 0.0929 (0.1236) time: 0.6092 data: 0.0042 max mem: 30262 +train: [12] Total time: 0:08:27 (0.6339 s / it) +train: [12] Summary: lr: 0.000134 loss: 0.1808 (0.2062) grad: 0.0929 (0.1236) +eval (validation): [12] [ 0/15] eta: 0:01:18 time: 5.2059 data: 4.9079 max mem: 30262 +eval (validation): [12] [14/15] eta: 0:00:00 time: 0.7525 data: 0.3497 max mem: 30262 +eval (validation): [12] Total time: 0:00:11 (0.7681 s / it) +cv: [12] best hparam: (3.7, 1.0) (032) ('032_lr3.7e+00_wd1.0e+00') loss: 0.685 acc: 0.931 f1: 0.927 bacc: 0.927 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_sex__patch__attn/checkpoint-last.pth +train: [13] [ 0/800] eta: 1:12:34 lr: nan time: 5.4426 data: 4.9385 max mem: 30262 +train: [13] [ 20/800] eta: 0:11:22 lr: 0.000134 loss: 0.2117 (0.2309) grad: 0.0855 (0.1122) time: 0.6463 data: 0.0410 max mem: 30262 +train: [13] [ 40/800] eta: 0:09:35 lr: 0.000133 loss: 0.2001 (0.2087) grad: 0.0855 (0.1292) time: 0.6349 data: 0.0719 max mem: 30262 +train: [13] [ 60/800] eta: 0:08:48 lr: 0.000132 loss: 0.2001 (0.1948) grad: 0.1009 (0.1247) time: 0.6267 data: 0.0623 max mem: 30262 +train: [13] [ 80/800] eta: 0:08:14 lr: 0.000131 loss: 0.1680 (0.1811) grad: 0.1009 (0.1219) time: 0.6004 data: 0.0435 max mem: 30262 +train: [13] [100/800] eta: 0:07:41 lr: 0.000130 loss: 0.1501 (0.1796) grad: 0.1009 (0.1185) time: 0.5459 data: 0.0029 max mem: 30262 +train: [13] [120/800] eta: 0:07:47 lr: 0.000130 loss: 0.1631 (0.1954) grad: 0.1009 (0.1266) time: 0.8318 data: 0.2665 max mem: 30262 +train: [13] [140/800] eta: 0:07:27 lr: 0.000129 loss: 0.1687 (0.1958) grad: 0.1212 (0.1282) time: 0.6273 data: 0.0042 max mem: 30262 +train: [13] [160/800] eta: 0:07:05 lr: 0.000128 loss: 0.1785 (0.1913) grad: 0.1212 (0.1314) time: 0.5634 data: 0.0038 max mem: 30262 +train: [13] [180/800] eta: 0:06:44 lr: 0.000127 loss: 0.1687 (0.1892) grad: 0.1330 (0.1332) time: 0.5547 data: 0.0030 max mem: 30262 +train: [13] [200/800] eta: 0:06:26 lr: 0.000127 loss: 0.1785 (0.1969) grad: 0.1330 (0.1355) time: 0.5648 data: 0.0032 max mem: 30262 +train: [13] [220/800] eta: 0:06:10 lr: 0.000126 loss: 0.1653 (0.1967) grad: 0.1288 (0.1343) time: 0.5918 data: 0.0409 max mem: 30262 +train: [13] [240/800] eta: 0:06:07 lr: 0.000125 loss: 0.1823 (0.2062) grad: 0.1124 (0.1318) time: 0.8414 data: 0.2990 max mem: 30262 +train: [13] [260/800] eta: 0:05:51 lr: 0.000124 loss: 0.2109 (0.2039) grad: 0.1065 (0.1296) time: 0.5846 data: 0.0183 max mem: 30262 +train: [13] [280/800] eta: 0:05:35 lr: 0.000124 loss: 0.1610 (0.1985) grad: 0.1032 (0.1279) time: 0.5776 data: 0.0024 max mem: 30262 +train: [13] [300/800] eta: 0:05:20 lr: 0.000123 loss: 0.1610 (0.2024) grad: 0.0880 (0.1273) time: 0.5860 data: 0.0286 max mem: 30262 +train: [13] [320/800] eta: 0:05:05 lr: 0.000122 loss: 0.1412 (0.2002) grad: 0.0880 (0.1249) time: 0.5772 data: 0.0075 max mem: 30262 +train: [13] [340/800] eta: 0:04:51 lr: 0.000121 loss: 0.1412 (0.2032) grad: 0.0978 (0.1247) time: 0.5667 data: 0.0033 max mem: 30262 +train: [13] [360/800] eta: 0:04:46 lr: 0.000120 loss: 0.1640 (0.2008) grad: 0.0978 (0.1250) time: 0.9626 data: 0.3456 max mem: 30262 +train: [13] [380/800] eta: 0:04:34 lr: 0.000120 loss: 0.1855 (0.2011) grad: 0.0978 (0.1225) time: 0.7071 data: 0.1442 max mem: 30262 +train: [13] [400/800] eta: 0:04:22 lr: 0.000119 loss: 0.1855 (0.1998) grad: 0.1168 (0.1242) time: 0.6963 data: 0.1365 max mem: 30262 +train: [13] [420/800] eta: 0:04:10 lr: 0.000118 loss: 0.1895 (0.2032) grad: 0.1220 (0.1250) time: 0.7350 data: 0.1903 max mem: 30262 +train: [13] [440/800] eta: 0:03:57 lr: 0.000117 loss: 0.1895 (0.2022) grad: 0.1063 (0.1239) time: 0.6809 data: 0.1249 max mem: 30262 +train: [13] [460/800] eta: 0:03:43 lr: 0.000117 loss: 0.1862 (0.2011) grad: 0.1269 (0.1254) time: 0.5820 data: 0.0223 max mem: 30262 +train: [13] [480/800] eta: 0:03:33 lr: 0.000116 loss: 0.1862 (0.2010) grad: 0.1190 (0.1268) time: 0.9250 data: 0.2773 max mem: 30262 +train: [13] [500/800] eta: 0:03:20 lr: 0.000115 loss: 0.1830 (0.2022) grad: 0.1063 (0.1252) time: 0.6764 data: 0.0041 max mem: 30262 +train: [13] [520/800] eta: 0:03:07 lr: 0.000114 loss: 0.1698 (0.2011) grad: 0.1099 (0.1241) time: 0.6389 data: 0.0029 max mem: 30262 +train: [13] [540/800] eta: 0:02:53 lr: 0.000114 loss: 0.1698 (0.2029) grad: 0.1009 (0.1250) time: 0.6264 data: 0.0040 max mem: 30262 +train: [13] [560/800] eta: 0:02:39 lr: 0.000113 loss: 0.1827 (0.2036) grad: 0.1012 (0.1245) time: 0.5811 data: 0.0038 max mem: 30262 +train: [13] [580/800] eta: 0:02:25 lr: 0.000112 loss: 0.1887 (0.2047) grad: 0.1051 (0.1233) time: 0.5540 data: 0.0025 max mem: 30262 +train: [13] [600/800] eta: 0:02:13 lr: 0.000111 loss: 0.1887 (0.2036) grad: 0.1157 (0.1246) time: 0.9166 data: 0.3146 max mem: 30262 +train: [13] [620/800] eta: 0:01:59 lr: 0.000110 loss: 0.1887 (0.2044) grad: 0.1068 (0.1248) time: 0.5726 data: 0.0035 max mem: 30262 +train: [13] [640/800] eta: 0:01:45 lr: 0.000110 loss: 0.1798 (0.2070) grad: 0.1057 (0.1239) time: 0.5729 data: 0.0035 max mem: 30262 +train: [13] [660/800] eta: 0:01:32 lr: 0.000109 loss: 0.1742 (0.2060) grad: 0.1037 (0.1235) time: 0.5832 data: 0.0036 max mem: 30262 +train: [13] [680/800] eta: 0:01:18 lr: 0.000108 loss: 0.1788 (0.2051) grad: 0.0870 (0.1220) time: 0.5855 data: 0.0038 max mem: 30262 +train: [13] [700/800] eta: 0:01:05 lr: 0.000107 loss: 0.1742 (0.2053) grad: 0.0770 (0.1206) time: 0.5581 data: 0.0034 max mem: 30262 +train: [13] [720/800] eta: 0:00:52 lr: 0.000107 loss: 0.1579 (0.2048) grad: 0.0777 (0.1208) time: 0.8467 data: 0.2738 max mem: 30262 +train: [13] [740/800] eta: 0:00:39 lr: 0.000106 loss: 0.1579 (0.2046) grad: 0.0770 (0.1193) time: 0.6312 data: 0.0653 max mem: 30262 +train: [13] [760/800] eta: 0:00:26 lr: 0.000105 loss: 0.1721 (0.2040) grad: 0.0786 (0.1192) time: 0.5608 data: 0.0022 max mem: 30262 +train: [13] [780/800] eta: 0:00:13 lr: 0.000104 loss: 0.1603 (0.2043) grad: 0.0886 (0.1192) time: 0.5606 data: 0.0031 max mem: 30262 +train: [13] [799/800] eta: 0:00:00 lr: 0.000104 loss: 0.1557 (0.2030) grad: 0.0873 (0.1188) time: 0.5676 data: 0.0032 max mem: 30262 +train: [13] Total time: 0:08:41 (0.6525 s / it) +train: [13] Summary: lr: 0.000104 loss: 0.1557 (0.2030) grad: 0.0873 (0.1188) +eval (validation): [13] [ 0/15] eta: 0:01:17 time: 5.1866 data: 4.8881 max mem: 30262 +eval (validation): [13] [14/15] eta: 0:00:00 time: 0.8612 data: 0.4594 max mem: 30262 +eval (validation): [13] Total time: 0:00:13 (0.8744 s / it) +cv: [13] best hparam: (3.7, 1.0) (032) ('032_lr3.7e+00_wd1.0e+00') loss: 0.691 acc: 0.948 f1: 0.945 bacc: 0.941 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_sex__patch__attn/checkpoint-last.pth +train: [14] [ 0/800] eta: 1:33:51 lr: nan time: 7.0398 data: 6.6041 max mem: 30262 +train: [14] [ 20/800] eta: 0:11:22 lr: 0.000103 loss: 0.2129 (0.2427) grad: 0.0648 (0.0598) time: 0.5668 data: 0.0023 max mem: 30262 +train: [14] [ 40/800] eta: 0:09:24 lr: 0.000102 loss: 0.1938 (0.2047) grad: 0.0708 (0.0858) time: 0.6029 data: 0.0036 max mem: 30262 +train: [14] [ 60/800] eta: 0:08:38 lr: 0.000101 loss: 0.1938 (0.2022) grad: 0.0998 (0.1065) time: 0.6140 data: 0.0031 max mem: 30262 +train: [14] [ 80/800] eta: 0:08:01 lr: 0.000101 loss: 0.1633 (0.1995) grad: 0.0998 (0.1123) time: 0.5717 data: 0.0033 max mem: 30262 +train: [14] [100/800] eta: 0:07:33 lr: 0.000100 loss: 0.1535 (0.1920) grad: 0.1161 (0.1135) time: 0.5617 data: 0.0031 max mem: 30262 +train: [14] [120/800] eta: 0:07:39 lr: 0.000099 loss: 0.1562 (0.1911) grad: 0.1285 (0.1161) time: 0.8149 data: 0.2703 max mem: 30262 +train: [14] [140/800] eta: 0:07:20 lr: 0.000099 loss: 0.1667 (0.1960) grad: 0.1254 (0.1150) time: 0.6267 data: 0.0690 max mem: 30262 +train: [14] [160/800] eta: 0:07:09 lr: 0.000098 loss: 0.1667 (0.1981) grad: 0.1216 (0.1149) time: 0.6916 data: 0.1330 max mem: 30262 +train: [14] [180/800] eta: 0:06:55 lr: 0.000097 loss: 0.1865 (0.1934) grad: 0.1216 (0.1153) time: 0.6622 data: 0.0999 max mem: 30262 +train: [14] [200/800] eta: 0:06:41 lr: 0.000096 loss: 0.1593 (0.2021) grad: 0.0926 (0.1131) time: 0.6688 data: 0.0878 max mem: 30262 +train: [14] [220/800] eta: 0:06:24 lr: 0.000096 loss: 0.1532 (0.2006) grad: 0.0925 (0.1102) time: 0.5887 data: 0.0242 max mem: 30262 +train: [14] [240/800] eta: 0:06:19 lr: 0.000095 loss: 0.1593 (0.2038) grad: 0.0925 (0.1121) time: 0.8351 data: 0.2730 max mem: 30262 +train: [14] [260/800] eta: 0:06:00 lr: 0.000094 loss: 0.1593 (0.2065) grad: 0.0899 (0.1112) time: 0.5652 data: 0.0036 max mem: 30262 +train: [14] [280/800] eta: 0:05:43 lr: 0.000093 loss: 0.1588 (0.2033) grad: 0.0905 (0.1130) time: 0.5616 data: 0.0031 max mem: 30262 +train: [14] [300/800] eta: 0:05:28 lr: 0.000093 loss: 0.1614 (0.2059) grad: 0.1092 (0.1153) time: 0.5900 data: 0.0028 max mem: 30262 +train: [14] [320/800] eta: 0:05:12 lr: 0.000092 loss: 0.1614 (0.2049) grad: 0.1092 (0.1168) time: 0.5730 data: 0.0031 max mem: 30262 +train: [14] [340/800] eta: 0:04:57 lr: 0.000091 loss: 0.1614 (0.2037) grad: 0.1141 (0.1157) time: 0.5719 data: 0.0038 max mem: 30262 +train: [14] [360/800] eta: 0:04:49 lr: 0.000090 loss: 0.1619 (0.2022) grad: 0.1211 (0.1178) time: 0.8648 data: 0.3309 max mem: 30262 +train: [14] [380/800] eta: 0:04:35 lr: 0.000090 loss: 0.1619 (0.2021) grad: 0.1211 (0.1174) time: 0.6208 data: 0.0661 max mem: 30262 +train: [14] [400/800] eta: 0:04:21 lr: 0.000089 loss: 0.1619 (0.2010) grad: 0.0953 (0.1165) time: 0.5988 data: 0.0334 max mem: 30262 +train: [14] [420/800] eta: 0:04:07 lr: 0.000088 loss: 0.1619 (0.2053) grad: 0.0916 (0.1163) time: 0.5988 data: 0.0048 max mem: 30262 +train: [14] [440/800] eta: 0:03:52 lr: 0.000088 loss: 0.2049 (0.2065) grad: 0.0909 (0.1157) time: 0.5472 data: 0.0025 max mem: 30262 +train: [14] [460/800] eta: 0:03:38 lr: 0.000087 loss: 0.2201 (0.2086) grad: 0.0909 (0.1168) time: 0.5669 data: 0.0030 max mem: 30262 +train: [14] [480/800] eta: 0:03:28 lr: 0.000086 loss: 0.1956 (0.2069) grad: 0.0909 (0.1168) time: 0.8680 data: 0.2721 max mem: 30262 +train: [14] [500/800] eta: 0:03:14 lr: 0.000085 loss: 0.1831 (0.2045) grad: 0.0829 (0.1151) time: 0.5687 data: 0.0028 max mem: 30262 +train: [14] [520/800] eta: 0:03:00 lr: 0.000085 loss: 0.1699 (0.2031) grad: 0.0904 (0.1150) time: 0.5682 data: 0.0031 max mem: 30262 +train: [14] [540/800] eta: 0:02:47 lr: 0.000084 loss: 0.1673 (0.2053) grad: 0.0806 (0.1145) time: 0.5687 data: 0.0036 max mem: 30262 +train: [14] [560/800] eta: 0:02:33 lr: 0.000083 loss: 0.1673 (0.2071) grad: 0.0904 (0.1142) time: 0.5659 data: 0.0035 max mem: 30262 +train: [14] [580/800] eta: 0:02:20 lr: 0.000083 loss: 0.1673 (0.2086) grad: 0.0956 (0.1135) time: 0.5473 data: 0.0033 max mem: 30262 +train: [14] [600/800] eta: 0:02:08 lr: 0.000082 loss: 0.1673 (0.2071) grad: 0.0808 (0.1126) time: 0.7993 data: 0.2582 max mem: 30262 +train: [14] [620/800] eta: 0:01:55 lr: 0.000081 loss: 0.1673 (0.2073) grad: 0.0784 (0.1113) time: 0.5628 data: 0.0036 max mem: 30262 +train: [14] [640/800] eta: 0:01:42 lr: 0.000081 loss: 0.1654 (0.2079) grad: 0.0756 (0.1107) time: 0.6155 data: 0.0495 max mem: 30262 +train: [14] [660/800] eta: 0:01:29 lr: 0.000080 loss: 0.1673 (0.2078) grad: 0.0767 (0.1111) time: 0.6349 data: 0.0819 max mem: 30262 +train: [14] [680/800] eta: 0:01:16 lr: 0.000079 loss: 0.1684 (0.2073) grad: 0.0808 (0.1114) time: 0.5934 data: 0.0477 max mem: 30262 +train: [14] [700/800] eta: 0:01:03 lr: 0.000078 loss: 0.1622 (0.2070) grad: 0.1042 (0.1122) time: 0.5874 data: 0.0471 max mem: 30262 +train: [14] [720/800] eta: 0:00:51 lr: 0.000078 loss: 0.1806 (0.2059) grad: 0.1234 (0.1139) time: 0.9346 data: 0.3195 max mem: 30262 +train: [14] [740/800] eta: 0:00:38 lr: 0.000077 loss: 0.1637 (0.2049) grad: 0.1255 (0.1146) time: 0.5598 data: 0.0027 max mem: 30262 +train: [14] [760/800] eta: 0:00:25 lr: 0.000076 loss: 0.1652 (0.2048) grad: 0.1437 (0.1154) time: 0.5836 data: 0.0035 max mem: 30262 +train: [14] [780/800] eta: 0:00:12 lr: 0.000076 loss: 0.1529 (0.2031) grad: 0.1479 (0.1157) time: 0.5615 data: 0.0035 max mem: 30262 +train: [14] [799/800] eta: 0:00:00 lr: 0.000075 loss: 0.1616 (0.2031) grad: 0.1284 (0.1153) time: 0.5472 data: 0.0036 max mem: 30262 +train: [14] Total time: 0:08:29 (0.6367 s / it) +train: [14] Summary: lr: 0.000075 loss: 0.1616 (0.2031) grad: 0.1284 (0.1153) +eval (validation): [14] [ 0/15] eta: 0:01:17 time: 5.1563 data: 4.8367 max mem: 30262 +eval (validation): [14] [14/15] eta: 0:00:00 time: 0.9157 data: 0.4516 max mem: 30262 +eval (validation): [14] Total time: 0:00:13 (0.9317 s / it) +cv: [14] best hparam: (3.7, 1.0) (032) ('032_lr3.7e+00_wd1.0e+00') loss: 0.694 acc: 0.931 f1: 0.927 bacc: 0.927 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_sex__patch__attn/checkpoint-last.pth +train: [15] [ 0/800] eta: 1:10:39 lr: nan time: 5.2995 data: 4.8364 max mem: 30262 +train: [15] [ 20/800] eta: 0:11:05 lr: 0.000074 loss: 0.1723 (0.1993) grad: 0.0867 (0.1023) time: 0.6308 data: 0.0574 max mem: 30262 +train: [15] [ 40/800] eta: 0:08:59 lr: 0.000074 loss: 0.1723 (0.1923) grad: 0.0716 (0.0908) time: 0.5582 data: 0.0029 max mem: 30262 +train: [15] [ 60/800] eta: 0:08:11 lr: 0.000073 loss: 0.1719 (0.1769) grad: 0.0867 (0.0988) time: 0.5718 data: 0.0030 max mem: 30262 +train: [15] [ 80/800] eta: 0:07:40 lr: 0.000072 loss: 0.1700 (0.1944) grad: 0.0867 (0.1148) time: 0.5635 data: 0.0038 max mem: 30262 +train: [15] [100/800] eta: 0:07:19 lr: 0.000072 loss: 0.1696 (0.2130) grad: 0.0928 (0.1158) time: 0.5783 data: 0.0026 max mem: 30262 +train: [15] [120/800] eta: 0:07:25 lr: 0.000071 loss: 0.1653 (0.2150) grad: 0.1060 (0.1195) time: 0.7924 data: 0.2570 max mem: 30262 +train: [15] [140/800] eta: 0:07:06 lr: 0.000070 loss: 0.1696 (0.2099) grad: 0.1113 (0.1236) time: 0.5930 data: 0.0170 max mem: 30262 +train: [15] [160/800] eta: 0:06:52 lr: 0.000070 loss: 0.1653 (0.2079) grad: 0.1113 (0.1251) time: 0.6343 data: 0.0036 max mem: 30262 +train: [15] [180/800] eta: 0:06:35 lr: 0.000069 loss: 0.1917 (0.2094) grad: 0.0990 (0.1217) time: 0.5832 data: 0.0037 max mem: 30262 +train: [15] [200/800] eta: 0:06:18 lr: 0.000068 loss: 0.1702 (0.2079) grad: 0.1002 (0.1233) time: 0.5767 data: 0.0032 max mem: 30262 +train: [15] [220/800] eta: 0:06:03 lr: 0.000068 loss: 0.1702 (0.2066) grad: 0.0936 (0.1207) time: 0.5755 data: 0.0028 max mem: 30262 +train: [15] [240/800] eta: 0:06:01 lr: 0.000067 loss: 0.1802 (0.2052) grad: 0.1002 (0.1238) time: 0.8617 data: 0.2735 max mem: 30262 +train: [15] [260/800] eta: 0:05:45 lr: 0.000066 loss: 0.1802 (0.2133) grad: 0.1002 (0.1212) time: 0.5733 data: 0.0035 max mem: 30262 +train: [15] [280/800] eta: 0:05:30 lr: 0.000066 loss: 0.1802 (0.2111) grad: 0.0915 (0.1183) time: 0.5809 data: 0.0032 max mem: 30262 +train: [15] [300/800] eta: 0:05:15 lr: 0.000065 loss: 0.1836 (0.2145) grad: 0.0937 (0.1178) time: 0.5701 data: 0.0029 max mem: 30262 +train: [15] [320/800] eta: 0:05:01 lr: 0.000064 loss: 0.1836 (0.2158) grad: 0.0796 (0.1183) time: 0.5788 data: 0.0031 max mem: 30262 +train: [15] [340/800] eta: 0:04:47 lr: 0.000064 loss: 0.1745 (0.2149) grad: 0.0699 (0.1175) time: 0.5590 data: 0.0032 max mem: 30262 +train: [15] [360/800] eta: 0:04:40 lr: 0.000063 loss: 0.1794 (0.2137) grad: 0.0740 (0.1194) time: 0.8614 data: 0.2668 max mem: 30262 +train: [15] [380/800] eta: 0:04:26 lr: 0.000063 loss: 0.1690 (0.2149) grad: 0.0639 (0.1196) time: 0.5784 data: 0.0033 max mem: 30262 +train: [15] [400/800] eta: 0:04:12 lr: 0.000062 loss: 0.1687 (0.2167) grad: 0.0619 (0.1211) time: 0.5616 data: 0.0029 max mem: 30262 +train: [15] [420/800] eta: 0:03:58 lr: 0.000061 loss: 0.1687 (0.2162) grad: 0.0850 (0.1191) time: 0.5747 data: 0.0034 max mem: 30262 +train: [15] [440/800] eta: 0:03:45 lr: 0.000061 loss: 0.1699 (0.2158) grad: 0.1002 (0.1203) time: 0.5651 data: 0.0033 max mem: 30262 +train: [15] [460/800] eta: 0:03:31 lr: 0.000060 loss: 0.1687 (0.2126) grad: 0.0874 (0.1196) time: 0.5568 data: 0.0032 max mem: 30262 +train: [15] [480/800] eta: 0:03:23 lr: 0.000059 loss: 0.1592 (0.2109) grad: 0.0796 (0.1176) time: 0.9682 data: 0.3603 max mem: 30262 +train: [15] [500/800] eta: 0:03:10 lr: 0.000059 loss: 0.1522 (0.2090) grad: 0.0860 (0.1177) time: 0.6221 data: 0.0608 max mem: 30262 +train: [15] [520/800] eta: 0:02:58 lr: 0.000058 loss: 0.1522 (0.2086) grad: 0.0796 (0.1170) time: 0.6286 data: 0.0888 max mem: 30262 +train: [15] [540/800] eta: 0:02:45 lr: 0.000057 loss: 0.1621 (0.2073) grad: 0.0963 (0.1171) time: 0.6895 data: 0.1444 max mem: 30262 +train: [15] [560/800] eta: 0:02:33 lr: 0.000057 loss: 0.1658 (0.2108) grad: 0.1155 (0.1183) time: 0.6296 data: 0.0752 max mem: 30262 +train: [15] [580/800] eta: 0:02:19 lr: 0.000056 loss: 0.1741 (0.2123) grad: 0.1155 (0.1218) time: 0.5980 data: 0.0472 max mem: 30262 +train: [15] [600/800] eta: 0:02:09 lr: 0.000056 loss: 0.1755 (0.2130) grad: 0.1155 (0.1218) time: 0.9106 data: 0.3246 max mem: 30262 +train: [15] [620/800] eta: 0:01:55 lr: 0.000055 loss: 0.1792 (0.2119) grad: 0.1029 (0.1226) time: 0.5584 data: 0.0032 max mem: 30262 +train: [15] [640/800] eta: 0:01:42 lr: 0.000054 loss: 0.1792 (0.2116) grad: 0.0941 (0.1237) time: 0.6231 data: 0.0034 max mem: 30262 +train: [15] [660/800] eta: 0:01:29 lr: 0.000054 loss: 0.1758 (0.2108) grad: 0.0941 (0.1228) time: 0.6365 data: 0.0041 max mem: 30262 +train: [15] [680/800] eta: 0:01:16 lr: 0.000053 loss: 0.1758 (0.2100) grad: 0.1025 (0.1247) time: 0.5892 data: 0.0035 max mem: 30262 +train: [15] [700/800] eta: 0:01:03 lr: 0.000053 loss: 0.1515 (0.2102) grad: 0.1011 (0.1243) time: 0.5586 data: 0.0033 max mem: 30262 +train: [15] [720/800] eta: 0:00:51 lr: 0.000052 loss: 0.1515 (0.2090) grad: 0.0936 (0.1235) time: 0.9224 data: 0.3434 max mem: 30262 +train: [15] [740/800] eta: 0:00:38 lr: 0.000051 loss: 0.1892 (0.2093) grad: 0.0631 (0.1224) time: 0.6246 data: 0.0028 max mem: 30262 +train: [15] [760/800] eta: 0:00:25 lr: 0.000051 loss: 0.1825 (0.2084) grad: 0.0631 (0.1222) time: 0.5963 data: 0.0036 max mem: 30262 +train: [15] [780/800] eta: 0:00:12 lr: 0.000050 loss: 0.1653 (0.2072) grad: 0.0848 (0.1217) time: 0.6556 data: 0.0040 max mem: 30262 +train: [15] [799/800] eta: 0:00:00 lr: 0.000050 loss: 0.1653 (0.2068) grad: 0.0905 (0.1230) time: 0.5644 data: 0.0033 max mem: 30262 +train: [15] Total time: 0:08:34 (0.6426 s / it) +train: [15] Summary: lr: 0.000050 loss: 0.1653 (0.2068) grad: 0.0905 (0.1230) +eval (validation): [15] [ 0/15] eta: 0:01:19 time: 5.2881 data: 4.9247 max mem: 30262 +eval (validation): [15] [14/15] eta: 0:00:00 time: 0.8041 data: 0.3306 max mem: 30262 +eval (validation): [15] Total time: 0:00:12 (0.8210 s / it) +cv: [15] best hparam: (3.7, 1.0) (032) ('032_lr3.7e+00_wd1.0e+00') loss: 0.699 acc: 0.948 f1: 0.945 bacc: 0.941 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_sex__patch__attn/checkpoint-last.pth +train: [16] [ 0/800] eta: 1:11:25 lr: nan time: 5.3565 data: 4.8896 max mem: 30262 +train: [16] [ 20/800] eta: 0:11:34 lr: 0.000049 loss: 0.1449 (0.2122) grad: 0.0700 (0.0742) time: 0.6665 data: 0.0512 max mem: 30262 +train: [16] [ 40/800] eta: 0:09:16 lr: 0.000048 loss: 0.1931 (0.2093) grad: 0.0875 (0.0923) time: 0.5671 data: 0.0028 max mem: 30262 +train: [16] [ 60/800] eta: 0:08:24 lr: 0.000048 loss: 0.2139 (0.2165) grad: 0.0990 (0.1312) time: 0.5763 data: 0.0041 max mem: 30262 +train: [16] [ 80/800] eta: 0:07:47 lr: 0.000047 loss: 0.1931 (0.2056) grad: 0.0867 (0.1244) time: 0.5497 data: 0.0022 max mem: 30262 +train: [16] [100/800] eta: 0:07:21 lr: 0.000047 loss: 0.1931 (0.2038) grad: 0.1053 (0.1248) time: 0.5597 data: 0.0030 max mem: 30262 +train: [16] [120/800] eta: 0:07:32 lr: 0.000046 loss: 0.1860 (0.2066) grad: 0.0809 (0.1249) time: 0.8404 data: 0.2662 max mem: 30262 +train: [16] [140/800] eta: 0:07:11 lr: 0.000046 loss: 0.1675 (0.2107) grad: 0.0764 (0.1193) time: 0.5825 data: 0.0033 max mem: 30262 +train: [16] [160/800] eta: 0:06:50 lr: 0.000045 loss: 0.1720 (0.2050) grad: 0.0778 (0.1153) time: 0.5551 data: 0.0036 max mem: 30262 +train: [16] [180/800] eta: 0:06:35 lr: 0.000045 loss: 0.1675 (0.1990) grad: 0.0778 (0.1155) time: 0.6109 data: 0.0033 max mem: 30262 +train: [16] [200/800] eta: 0:06:18 lr: 0.000044 loss: 0.1663 (0.1975) grad: 0.0847 (0.1191) time: 0.5720 data: 0.0032 max mem: 30262 +train: [16] [220/800] eta: 0:06:03 lr: 0.000043 loss: 0.1458 (0.1943) grad: 0.1111 (0.1199) time: 0.5730 data: 0.0034 max mem: 30262 +train: [16] [240/800] eta: 0:06:00 lr: 0.000043 loss: 0.1428 (0.1925) grad: 0.1183 (0.1209) time: 0.8256 data: 0.2705 max mem: 30262 +train: [16] [260/800] eta: 0:05:49 lr: 0.000042 loss: 0.1407 (0.1940) grad: 0.1015 (0.1220) time: 0.6982 data: 0.0649 max mem: 30262 +train: [16] [280/800] eta: 0:05:33 lr: 0.000042 loss: 0.1407 (0.1928) grad: 0.1015 (0.1270) time: 0.5705 data: 0.0033 max mem: 30262 +train: [16] [300/800] eta: 0:05:19 lr: 0.000041 loss: 0.1770 (0.1934) grad: 0.0925 (0.1262) time: 0.5871 data: 0.0037 max mem: 30262 +train: [16] [320/800] eta: 0:05:04 lr: 0.000041 loss: 0.1891 (0.1938) grad: 0.0925 (0.1259) time: 0.5868 data: 0.0039 max mem: 30262 +train: [16] [340/800] eta: 0:04:50 lr: 0.000040 loss: 0.1879 (0.1928) grad: 0.0925 (0.1242) time: 0.5925 data: 0.0042 max mem: 30262 +train: [16] [360/800] eta: 0:04:44 lr: 0.000040 loss: 0.1859 (0.1922) grad: 0.0925 (0.1232) time: 0.9064 data: 0.3273 max mem: 30262 +train: [16] [380/800] eta: 0:04:30 lr: 0.000039 loss: 0.1719 (0.1917) grad: 0.1009 (0.1233) time: 0.5787 data: 0.0025 max mem: 30262 +train: [16] [400/800] eta: 0:04:16 lr: 0.000039 loss: 0.1534 (0.1892) grad: 0.0837 (0.1213) time: 0.5888 data: 0.0041 max mem: 30262 +train: [16] [420/800] eta: 0:04:02 lr: 0.000038 loss: 0.1534 (0.1902) grad: 0.1009 (0.1222) time: 0.5813 data: 0.0034 max mem: 30262 +train: [16] [440/800] eta: 0:03:48 lr: 0.000038 loss: 0.1714 (0.1919) grad: 0.1009 (0.1233) time: 0.5706 data: 0.0036 max mem: 30262 +train: [16] [460/800] eta: 0:03:34 lr: 0.000037 loss: 0.1714 (0.1911) grad: 0.1019 (0.1222) time: 0.5676 data: 0.0032 max mem: 30262 +train: [16] [480/800] eta: 0:03:25 lr: 0.000036 loss: 0.1960 (0.1932) grad: 0.1096 (0.1217) time: 0.8681 data: 0.2685 max mem: 30262 +train: [16] [500/800] eta: 0:03:11 lr: 0.000036 loss: 0.2039 (0.1946) grad: 0.1210 (0.1259) time: 0.5648 data: 0.0036 max mem: 30262 +train: [16] [520/800] eta: 0:02:58 lr: 0.000035 loss: 0.1851 (0.1928) grad: 0.1210 (0.1249) time: 0.6076 data: 0.0043 max mem: 30262 +train: [16] [540/800] eta: 0:02:45 lr: 0.000035 loss: 0.1489 (0.1911) grad: 0.1244 (0.1247) time: 0.5860 data: 0.0039 max mem: 30262 +train: [16] [560/800] eta: 0:02:32 lr: 0.000034 loss: 0.1489 (0.1907) grad: 0.1244 (0.1244) time: 0.5681 data: 0.0035 max mem: 30262 +train: [16] [580/800] eta: 0:02:18 lr: 0.000034 loss: 0.1390 (0.1889) grad: 0.1105 (0.1237) time: 0.5529 data: 0.0032 max mem: 30262 +train: [16] [600/800] eta: 0:02:07 lr: 0.000033 loss: 0.1568 (0.1897) grad: 0.1033 (0.1235) time: 0.8946 data: 0.2686 max mem: 30262 +train: [16] [620/800] eta: 0:01:54 lr: 0.000033 loss: 0.1648 (0.1896) grad: 0.1033 (0.1230) time: 0.5680 data: 0.0032 max mem: 30262 +train: [16] [640/800] eta: 0:01:41 lr: 0.000032 loss: 0.1568 (0.1887) grad: 0.0777 (0.1218) time: 0.5622 data: 0.0032 max mem: 30262 +train: [16] [660/800] eta: 0:01:28 lr: 0.000032 loss: 0.1568 (0.1877) grad: 0.0836 (0.1215) time: 0.5801 data: 0.0040 max mem: 30262 +train: [16] [680/800] eta: 0:01:15 lr: 0.000031 loss: 0.1487 (0.1881) grad: 0.0777 (0.1210) time: 0.5713 data: 0.0032 max mem: 30262 +train: [16] [700/800] eta: 0:01:02 lr: 0.000031 loss: 0.1490 (0.1881) grad: 0.0739 (0.1207) time: 0.5499 data: 0.0031 max mem: 30262 +train: [16] [720/800] eta: 0:00:50 lr: 0.000031 loss: 0.1494 (0.1885) grad: 0.0792 (0.1201) time: 0.8617 data: 0.2711 max mem: 30262 +train: [16] [740/800] eta: 0:00:38 lr: 0.000030 loss: 0.1494 (0.1876) grad: 0.0792 (0.1205) time: 0.5876 data: 0.0047 max mem: 30262 +train: [16] [760/800] eta: 0:00:25 lr: 0.000030 loss: 0.1573 (0.1879) grad: 0.0828 (0.1211) time: 0.5628 data: 0.0035 max mem: 30262 +train: [16] [780/800] eta: 0:00:12 lr: 0.000029 loss: 0.1573 (0.1879) grad: 0.0897 (0.1215) time: 0.5602 data: 0.0037 max mem: 30262 +train: [16] [799/800] eta: 0:00:00 lr: 0.000029 loss: 0.1669 (0.1883) grad: 0.0910 (0.1215) time: 0.5648 data: 0.0022 max mem: 30262 +train: [16] Total time: 0:08:23 (0.6292 s / it) +train: [16] Summary: lr: 0.000029 loss: 0.1669 (0.1883) grad: 0.0910 (0.1215) +eval (validation): [16] [ 0/15] eta: 0:01:20 time: 5.3796 data: 5.0681 max mem: 30262 +eval (validation): [16] [14/15] eta: 0:00:00 time: 0.8454 data: 0.4332 max mem: 30262 +eval (validation): [16] Total time: 0:00:12 (0.8603 s / it) +cv: [16] best hparam: (3.7, 1.0) (032) ('032_lr3.7e+00_wd1.0e+00') loss: 0.702 acc: 0.948 f1: 0.945 bacc: 0.941 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_sex__patch__attn/checkpoint-last.pth +train: [17] [ 0/800] eta: 1:10:35 lr: nan time: 5.2946 data: 4.8740 max mem: 30262 +train: [17] [ 20/800] eta: 0:10:42 lr: 0.000028 loss: 0.1939 (0.1984) grad: 0.0822 (0.0902) time: 0.6007 data: 0.0035 max mem: 30262 +train: [17] [ 40/800] eta: 0:08:55 lr: 0.000028 loss: 0.1724 (0.1798) grad: 0.1055 (0.1175) time: 0.5787 data: 0.0035 max mem: 30262 +train: [17] [ 60/800] eta: 0:08:07 lr: 0.000027 loss: 0.1779 (0.1777) grad: 0.1062 (0.1169) time: 0.5640 data: 0.0033 max mem: 30262 +train: [17] [ 80/800] eta: 0:07:36 lr: 0.000027 loss: 0.1662 (0.1736) grad: 0.1055 (0.1131) time: 0.5610 data: 0.0028 max mem: 30262 +train: [17] [100/800] eta: 0:07:14 lr: 0.000026 loss: 0.1626 (0.1779) grad: 0.1055 (0.1068) time: 0.5690 data: 0.0029 max mem: 30262 +train: [17] [120/800] eta: 0:07:27 lr: 0.000026 loss: 0.1519 (0.1803) grad: 0.0923 (0.1072) time: 0.8421 data: 0.2785 max mem: 30262 +train: [17] [140/800] eta: 0:07:13 lr: 0.000026 loss: 0.1626 (0.1944) grad: 0.0897 (0.1072) time: 0.6499 data: 0.0856 max mem: 30262 +train: [17] [160/800] eta: 0:07:02 lr: 0.000025 loss: 0.1601 (0.1887) grad: 0.0784 (0.1031) time: 0.6799 data: 0.1178 max mem: 30262 +train: [17] [180/800] eta: 0:06:43 lr: 0.000025 loss: 0.1662 (0.1892) grad: 0.0872 (0.1009) time: 0.5729 data: 0.0026 max mem: 30262 +train: [17] [200/800] eta: 0:06:24 lr: 0.000024 loss: 0.1729 (0.1938) grad: 0.0895 (0.1039) time: 0.5654 data: 0.0035 max mem: 30262 +train: [17] [220/800] eta: 0:06:07 lr: 0.000024 loss: 0.1662 (0.1927) grad: 0.0872 (0.1043) time: 0.5564 data: 0.0036 max mem: 30262 +train: [17] [240/800] eta: 0:06:06 lr: 0.000023 loss: 0.1662 (0.1900) grad: 0.1005 (0.1041) time: 0.8737 data: 0.2742 max mem: 30262 +train: [17] [260/800] eta: 0:05:50 lr: 0.000023 loss: 0.1917 (0.1992) grad: 0.1225 (0.1073) time: 0.5887 data: 0.0036 max mem: 30262 +train: [17] [280/800] eta: 0:05:34 lr: 0.000023 loss: 0.1595 (0.1995) grad: 0.1225 (0.1068) time: 0.5611 data: 0.0033 max mem: 30262 +train: [17] [300/800] eta: 0:05:18 lr: 0.000022 loss: 0.1577 (0.1986) grad: 0.1062 (0.1061) time: 0.5670 data: 0.0036 max mem: 30262 +train: [17] [320/800] eta: 0:05:04 lr: 0.000022 loss: 0.1714 (0.1981) grad: 0.0789 (0.1063) time: 0.5952 data: 0.0034 max mem: 30262 +train: [17] [340/800] eta: 0:04:50 lr: 0.000021 loss: 0.1577 (0.1961) grad: 0.0789 (0.1080) time: 0.5607 data: 0.0033 max mem: 30262 +train: [17] [360/800] eta: 0:04:43 lr: 0.000021 loss: 0.1571 (0.1963) grad: 0.0749 (0.1069) time: 0.8708 data: 0.2889 max mem: 30262 +train: [17] [380/800] eta: 0:04:29 lr: 0.000021 loss: 0.1646 (0.1976) grad: 0.1044 (0.1095) time: 0.6129 data: 0.0437 max mem: 30262 +train: [17] [400/800] eta: 0:04:16 lr: 0.000020 loss: 0.1601 (0.1975) grad: 0.1063 (0.1100) time: 0.6371 data: 0.0520 max mem: 30262 +train: [17] [420/800] eta: 0:04:03 lr: 0.000020 loss: 0.1851 (0.1979) grad: 0.1244 (0.1115) time: 0.6243 data: 0.0218 max mem: 30262 +train: [17] [440/800] eta: 0:03:49 lr: 0.000019 loss: 0.1950 (0.1975) grad: 0.1101 (0.1108) time: 0.5881 data: 0.0041 max mem: 30262 +train: [17] [460/800] eta: 0:03:36 lr: 0.000019 loss: 0.1851 (0.1976) grad: 0.1035 (0.1110) time: 0.5872 data: 0.0035 max mem: 30262 +train: [17] [480/800] eta: 0:03:27 lr: 0.000019 loss: 0.1892 (0.1974) grad: 0.1035 (0.1116) time: 0.9103 data: 0.2747 max mem: 30262 +train: [17] [500/800] eta: 0:03:13 lr: 0.000018 loss: 0.1685 (0.1956) grad: 0.1008 (0.1116) time: 0.5855 data: 0.0036 max mem: 30262 +train: [17] [520/800] eta: 0:02:59 lr: 0.000018 loss: 0.1545 (0.1934) grad: 0.0877 (0.1097) time: 0.5747 data: 0.0028 max mem: 30262 +train: [17] [540/800] eta: 0:02:46 lr: 0.000017 loss: 0.1545 (0.1939) grad: 0.0709 (0.1081) time: 0.5867 data: 0.0032 max mem: 30262 +train: [17] [560/800] eta: 0:02:33 lr: 0.000017 loss: 0.1623 (0.1943) grad: 0.0684 (0.1087) time: 0.5829 data: 0.0033 max mem: 30262 +train: [17] [580/800] eta: 0:02:20 lr: 0.000017 loss: 0.1596 (0.1933) grad: 0.0573 (0.1083) time: 0.5854 data: 0.0038 max mem: 30262 +train: [17] [600/800] eta: 0:02:09 lr: 0.000016 loss: 0.1930 (0.1964) grad: 0.0684 (0.1102) time: 0.9117 data: 0.2790 max mem: 30262 +train: [17] [620/800] eta: 0:01:56 lr: 0.000016 loss: 0.1930 (0.1965) grad: 0.0716 (0.1092) time: 0.6055 data: 0.0039 max mem: 30262 +train: [17] [640/800] eta: 0:01:42 lr: 0.000016 loss: 0.1629 (0.1959) grad: 0.0716 (0.1083) time: 0.5899 data: 0.0028 max mem: 30262 +train: [17] [660/800] eta: 0:01:29 lr: 0.000015 loss: 0.1723 (0.1960) grad: 0.0831 (0.1075) time: 0.5715 data: 0.0031 max mem: 30262 +train: [17] [680/800] eta: 0:01:16 lr: 0.000015 loss: 0.1723 (0.1972) grad: 0.0760 (0.1065) time: 0.5707 data: 0.0033 max mem: 30262 +train: [17] [700/800] eta: 0:01:03 lr: 0.000015 loss: 0.1661 (0.1969) grad: 0.0782 (0.1059) time: 0.5495 data: 0.0027 max mem: 30262 +train: [17] [720/800] eta: 0:00:51 lr: 0.000014 loss: 0.1733 (0.1963) grad: 0.0782 (0.1079) time: 0.8307 data: 0.2758 max mem: 30262 +train: [17] [740/800] eta: 0:00:38 lr: 0.000014 loss: 0.1733 (0.1962) grad: 0.0933 (0.1094) time: 0.5580 data: 0.0030 max mem: 30262 +train: [17] [760/800] eta: 0:00:25 lr: 0.000014 loss: 0.1702 (0.1970) grad: 0.0989 (0.1091) time: 0.5547 data: 0.0030 max mem: 30262 +train: [17] [780/800] eta: 0:00:12 lr: 0.000013 loss: 0.1702 (0.1964) grad: 0.0959 (0.1088) time: 0.5949 data: 0.0035 max mem: 30262 +train: [17] [799/800] eta: 0:00:00 lr: 0.000013 loss: 0.1512 (0.1958) grad: 0.0959 (0.1097) time: 0.5764 data: 0.0036 max mem: 30262 +train: [17] Total time: 0:08:27 (0.6348 s / it) +train: [17] Summary: lr: 0.000013 loss: 0.1512 (0.1958) grad: 0.0959 (0.1097) +eval (validation): [17] [ 0/15] eta: 0:01:16 time: 5.1026 data: 4.7943 max mem: 30262 +eval (validation): [17] [14/15] eta: 0:00:00 time: 0.7549 data: 0.3573 max mem: 30262 +eval (validation): [17] Total time: 0:00:11 (0.7699 s / it) +cv: [17] best hparam: (3.7, 1.0) (032) ('032_lr3.7e+00_wd1.0e+00') loss: 0.703 acc: 0.948 f1: 0.945 bacc: 0.941 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_sex__patch__attn/checkpoint-last.pth +train: [18] [ 0/800] eta: 1:12:03 lr: nan time: 5.4039 data: 4.9291 max mem: 30262 +train: [18] [ 20/800] eta: 0:11:14 lr: 0.000013 loss: 0.2114 (0.2011) grad: 0.0745 (0.0975) time: 0.6377 data: 0.0032 max mem: 30262 +train: [18] [ 40/800] eta: 0:09:05 lr: 0.000012 loss: 0.2040 (0.2058) grad: 0.0745 (0.0962) time: 0.5642 data: 0.0033 max mem: 30262 +train: [18] [ 60/800] eta: 0:08:13 lr: 0.000012 loss: 0.1771 (0.1861) grad: 0.0936 (0.0997) time: 0.5621 data: 0.0034 max mem: 30262 +train: [18] [ 80/800] eta: 0:07:42 lr: 0.000012 loss: 0.1771 (0.1883) grad: 0.1069 (0.1214) time: 0.5670 data: 0.0036 max mem: 30262 +train: [18] [100/800] eta: 0:07:17 lr: 0.000011 loss: 0.1771 (0.1959) grad: 0.1069 (0.1211) time: 0.5563 data: 0.0035 max mem: 30262 +train: [18] [120/800] eta: 0:07:32 lr: 0.000011 loss: 0.1706 (0.1909) grad: 0.1069 (0.1195) time: 0.8717 data: 0.3221 max mem: 30262 +train: [18] [140/800] eta: 0:07:14 lr: 0.000011 loss: 0.1706 (0.1877) grad: 0.1069 (0.1191) time: 0.6106 data: 0.0039 max mem: 30262 +train: [18] [160/800] eta: 0:06:52 lr: 0.000011 loss: 0.1687 (0.1901) grad: 0.0982 (0.1216) time: 0.5453 data: 0.0027 max mem: 30262 +train: [18] [180/800] eta: 0:06:37 lr: 0.000010 loss: 0.1580 (0.1978) grad: 0.0868 (0.1141) time: 0.6127 data: 0.0034 max mem: 30262 +train: [18] [200/800] eta: 0:06:20 lr: 0.000010 loss: 0.1580 (0.1975) grad: 0.0946 (0.1157) time: 0.5713 data: 0.0033 max mem: 30262 +train: [18] [220/800] eta: 0:06:04 lr: 0.000010 loss: 0.1739 (0.2010) grad: 0.0968 (0.1197) time: 0.5659 data: 0.0032 max mem: 30262 +train: [18] [240/800] eta: 0:06:02 lr: 0.000009 loss: 0.1782 (0.1993) grad: 0.0968 (0.1194) time: 0.8590 data: 0.2707 max mem: 30262 +train: [18] [260/800] eta: 0:05:45 lr: 0.000009 loss: 0.1817 (0.1996) grad: 0.1164 (0.1175) time: 0.5671 data: 0.0034 max mem: 30262 +train: [18] [280/800] eta: 0:05:31 lr: 0.000009 loss: 0.1933 (0.2076) grad: 0.1113 (0.1158) time: 0.5978 data: 0.0030 max mem: 30262 +train: [18] [300/800] eta: 0:05:16 lr: 0.000009 loss: 0.1817 (0.2061) grad: 0.0993 (0.1182) time: 0.5605 data: 0.0032 max mem: 30262 +train: [18] [320/800] eta: 0:05:01 lr: 0.000008 loss: 0.1597 (0.2026) grad: 0.0957 (0.1177) time: 0.5771 data: 0.0126 max mem: 30262 +train: [18] [340/800] eta: 0:04:47 lr: 0.000008 loss: 0.1597 (0.2046) grad: 0.0882 (0.1149) time: 0.5625 data: 0.0029 max mem: 30262 +train: [18] [360/800] eta: 0:04:39 lr: 0.000008 loss: 0.1442 (0.2023) grad: 0.0723 (0.1121) time: 0.8214 data: 0.2675 max mem: 30262 +train: [18] [380/800] eta: 0:04:26 lr: 0.000008 loss: 0.1541 (0.2000) grad: 0.0723 (0.1103) time: 0.6023 data: 0.0247 max mem: 30262 +train: [18] [400/800] eta: 0:04:12 lr: 0.000007 loss: 0.1553 (0.1995) grad: 0.0723 (0.1118) time: 0.5739 data: 0.0031 max mem: 30262 +train: [18] [420/800] eta: 0:03:58 lr: 0.000007 loss: 0.1537 (0.2009) grad: 0.0925 (0.1131) time: 0.5768 data: 0.0032 max mem: 30262 +train: [18] [440/800] eta: 0:03:45 lr: 0.000007 loss: 0.1537 (0.2000) grad: 0.1235 (0.1137) time: 0.5640 data: 0.0032 max mem: 30262 +train: [18] [460/800] eta: 0:03:31 lr: 0.000007 loss: 0.1531 (0.1990) grad: 0.1123 (0.1116) time: 0.5665 data: 0.0035 max mem: 30262 +train: [18] [480/800] eta: 0:03:22 lr: 0.000006 loss: 0.1678 (0.1978) grad: 0.0962 (0.1111) time: 0.8278 data: 0.2759 max mem: 30262 +train: [18] [500/800] eta: 0:03:08 lr: 0.000006 loss: 0.1750 (0.1966) grad: 0.0931 (0.1105) time: 0.5715 data: 0.0039 max mem: 30262 +train: [18] [520/800] eta: 0:02:55 lr: 0.000006 loss: 0.1750 (0.1972) grad: 0.0931 (0.1106) time: 0.5698 data: 0.0110 max mem: 30262 +train: [18] [540/800] eta: 0:02:43 lr: 0.000006 loss: 0.1671 (0.1959) grad: 0.0994 (0.1109) time: 0.6839 data: 0.0801 max mem: 30262 +train: [18] [560/800] eta: 0:02:30 lr: 0.000006 loss: 0.1564 (0.1946) grad: 0.0965 (0.1100) time: 0.5566 data: 0.0028 max mem: 30262 +train: [18] [580/800] eta: 0:02:17 lr: 0.000005 loss: 0.1519 (0.1948) grad: 0.0819 (0.1082) time: 0.5489 data: 0.0028 max mem: 30262 +train: [18] [600/800] eta: 0:02:05 lr: 0.000005 loss: 0.1504 (0.1936) grad: 0.0819 (0.1081) time: 0.8076 data: 0.2660 max mem: 30262 +train: [18] [620/800] eta: 0:01:52 lr: 0.000005 loss: 0.1512 (0.1934) grad: 0.0801 (0.1082) time: 0.5495 data: 0.0035 max mem: 30262 +train: [18] [640/800] eta: 0:01:40 lr: 0.000005 loss: 0.1455 (0.1914) grad: 0.0801 (0.1086) time: 0.6336 data: 0.0873 max mem: 30262 +train: [18] [660/800] eta: 0:01:27 lr: 0.000005 loss: 0.1381 (0.1911) grad: 0.1000 (0.1082) time: 0.5535 data: 0.0021 max mem: 30262 +train: [18] [680/800] eta: 0:01:14 lr: 0.000004 loss: 0.1592 (0.1951) grad: 0.1045 (0.1097) time: 0.5785 data: 0.0034 max mem: 30262 +train: [18] [700/800] eta: 0:01:02 lr: 0.000004 loss: 0.1763 (0.1955) grad: 0.1045 (0.1102) time: 0.5574 data: 0.0033 max mem: 30262 +train: [18] [720/800] eta: 0:00:50 lr: 0.000004 loss: 0.2060 (0.1958) grad: 0.1045 (0.1111) time: 0.8903 data: 0.2743 max mem: 30262 +train: [18] [740/800] eta: 0:00:37 lr: 0.000004 loss: 0.2063 (0.1954) grad: 0.1093 (0.1106) time: 0.5603 data: 0.0031 max mem: 30262 +train: [18] [760/800] eta: 0:00:25 lr: 0.000004 loss: 0.1778 (0.1950) grad: 0.1009 (0.1103) time: 0.6386 data: 0.0039 max mem: 30262 +train: [18] [780/800] eta: 0:00:12 lr: 0.000003 loss: 0.1697 (0.1966) grad: 0.1025 (0.1119) time: 0.6101 data: 0.0038 max mem: 30262 +train: [18] [799/800] eta: 0:00:00 lr: 0.000003 loss: 0.1628 (0.1955) grad: 0.1143 (0.1123) time: 0.5631 data: 0.0032 max mem: 30262 +train: [18] Total time: 0:08:21 (0.6263 s / it) +train: [18] Summary: lr: 0.000003 loss: 0.1628 (0.1955) grad: 0.1143 (0.1123) +eval (validation): [18] [ 0/15] eta: 0:01:17 time: 5.1461 data: 4.8458 max mem: 30262 +eval (validation): [18] [14/15] eta: 0:00:00 time: 0.7576 data: 0.3692 max mem: 30262 +eval (validation): [18] Total time: 0:00:11 (0.7734 s / it) +cv: [18] best hparam: (3.7, 1.0) (032) ('032_lr3.7e+00_wd1.0e+00') loss: 0.704 acc: 0.948 f1: 0.945 bacc: 0.941 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_sex__patch__attn/checkpoint-last.pth +train: [19] [ 0/800] eta: 1:11:00 lr: nan time: 5.3252 data: 4.8487 max mem: 30262 +train: [19] [ 20/800] eta: 0:10:34 lr: 0.000003 loss: 0.1372 (0.1409) grad: 0.1193 (0.1564) time: 0.5878 data: 0.0045 max mem: 30262 +train: [19] [ 40/800] eta: 0:09:05 lr: 0.000003 loss: 0.1361 (0.1488) grad: 0.1193 (0.1422) time: 0.6179 data: 0.0034 max mem: 30262 +train: [19] [ 60/800] eta: 0:08:17 lr: 0.000003 loss: 0.1571 (0.1626) grad: 0.1193 (0.1399) time: 0.5773 data: 0.0041 max mem: 30262 +train: [19] [ 80/800] eta: 0:07:43 lr: 0.000003 loss: 0.1412 (0.1657) grad: 0.0916 (0.1255) time: 0.5563 data: 0.0037 max mem: 30262 +train: [19] [100/800] eta: 0:07:18 lr: 0.000003 loss: 0.1443 (0.1706) grad: 0.0916 (0.1237) time: 0.5555 data: 0.0034 max mem: 30262 +train: [19] [120/800] eta: 0:07:26 lr: 0.000002 loss: 0.1443 (0.1643) grad: 0.0874 (0.1225) time: 0.8101 data: 0.2759 max mem: 30262 +train: [19] [140/800] eta: 0:07:14 lr: 0.000002 loss: 0.1412 (0.1747) grad: 0.0804 (0.1175) time: 0.6713 data: 0.0036 max mem: 30262 +train: [19] [160/800] eta: 0:06:53 lr: 0.000002 loss: 0.1624 (0.1775) grad: 0.0908 (0.1168) time: 0.5624 data: 0.0029 max mem: 30262 +train: [19] [180/800] eta: 0:06:35 lr: 0.000002 loss: 0.1634 (0.1860) grad: 0.0887 (0.1187) time: 0.5626 data: 0.0037 max mem: 30262 +train: [19] [200/800] eta: 0:06:17 lr: 0.000002 loss: 0.1803 (0.1855) grad: 0.0771 (0.1153) time: 0.5479 data: 0.0022 max mem: 30262 +train: [19] [220/800] eta: 0:06:01 lr: 0.000002 loss: 0.2039 (0.1867) grad: 0.0771 (0.1152) time: 0.5681 data: 0.0035 max mem: 30262 +train: [19] [240/800] eta: 0:05:59 lr: 0.000002 loss: 0.1847 (0.1891) grad: 0.0759 (0.1135) time: 0.8591 data: 0.3176 max mem: 30262 +train: [19] [260/800] eta: 0:05:44 lr: 0.000001 loss: 0.1659 (0.1869) grad: 0.0778 (0.1154) time: 0.5887 data: 0.0538 max mem: 30262 +train: [19] [280/800] eta: 0:05:29 lr: 0.000001 loss: 0.1559 (0.1858) grad: 0.1083 (0.1146) time: 0.5659 data: 0.0024 max mem: 30262 +train: [19] [300/800] eta: 0:05:14 lr: 0.000001 loss: 0.1437 (0.1856) grad: 0.1186 (0.1159) time: 0.5660 data: 0.0037 max mem: 30262 +train: [19] [320/800] eta: 0:05:01 lr: 0.000001 loss: 0.1392 (0.1866) grad: 0.1207 (0.1167) time: 0.6056 data: 0.0030 max mem: 30262 +train: [19] [340/800] eta: 0:04:46 lr: 0.000001 loss: 0.1437 (0.1897) grad: 0.0821 (0.1145) time: 0.5611 data: 0.0031 max mem: 30262 +train: [19] [360/800] eta: 0:04:40 lr: 0.000001 loss: 0.1506 (0.1919) grad: 0.0795 (0.1137) time: 0.8775 data: 0.2619 max mem: 30262 +train: [19] [380/800] eta: 0:04:28 lr: 0.000001 loss: 0.1659 (0.1928) grad: 0.0922 (0.1151) time: 0.6519 data: 0.0025 max mem: 30262 +train: [19] [400/800] eta: 0:04:14 lr: 0.000001 loss: 0.1713 (0.1935) grad: 0.0922 (0.1150) time: 0.5731 data: 0.0037 max mem: 30262 +train: [19] [420/800] eta: 0:04:00 lr: 0.000001 loss: 0.1713 (0.1923) grad: 0.0993 (0.1157) time: 0.5626 data: 0.0033 max mem: 30262 +train: [19] [440/800] eta: 0:03:46 lr: 0.000001 loss: 0.1558 (0.1906) grad: 0.0999 (0.1150) time: 0.5627 data: 0.0031 max mem: 30262 +train: [19] [460/800] eta: 0:03:32 lr: 0.000001 loss: 0.1480 (0.1894) grad: 0.0912 (0.1145) time: 0.5543 data: 0.0028 max mem: 30262 +train: [19] [480/800] eta: 0:03:22 lr: 0.000001 loss: 0.1480 (0.1891) grad: 0.0945 (0.1162) time: 0.8129 data: 0.2623 max mem: 30262 +train: [19] [500/800] eta: 0:03:10 lr: 0.000000 loss: 0.1480 (0.1895) grad: 0.0999 (0.1163) time: 0.6810 data: 0.0485 max mem: 30262 +train: [19] [520/800] eta: 0:02:56 lr: 0.000000 loss: 0.1511 (0.1900) grad: 0.1062 (0.1168) time: 0.5550 data: 0.0033 max mem: 30262 +train: [19] [540/800] eta: 0:02:44 lr: 0.000000 loss: 0.1574 (0.1894) grad: 0.1101 (0.1182) time: 0.6050 data: 0.0046 max mem: 30262 +train: [19] [560/800] eta: 0:02:31 lr: 0.000000 loss: 0.1746 (0.1913) grad: 0.1316 (0.1189) time: 0.6619 data: 0.0031 max mem: 30262 +train: [19] [580/800] eta: 0:02:18 lr: 0.000000 loss: 0.1731 (0.1908) grad: 0.1101 (0.1176) time: 0.5901 data: 0.0036 max mem: 30262 +train: [19] [600/800] eta: 0:02:07 lr: 0.000000 loss: 0.1731 (0.1901) grad: 0.1197 (0.1180) time: 0.8848 data: 0.2695 max mem: 30262 +train: [19] [620/800] eta: 0:01:54 lr: 0.000000 loss: 0.1987 (0.1912) grad: 0.0966 (0.1178) time: 0.5618 data: 0.0037 max mem: 30262 +train: [19] [640/800] eta: 0:01:41 lr: 0.000000 loss: 0.1581 (0.1910) grad: 0.0891 (0.1178) time: 0.5778 data: 0.0030 max mem: 30262 +train: [19] [660/800] eta: 0:01:28 lr: 0.000000 loss: 0.1581 (0.1912) grad: 0.0981 (0.1175) time: 0.6020 data: 0.0439 max mem: 30262 +train: [19] [680/800] eta: 0:01:15 lr: 0.000000 loss: 0.1657 (0.1919) grad: 0.0895 (0.1164) time: 0.6088 data: 0.0615 max mem: 30262 +train: [19] [700/800] eta: 0:01:03 lr: 0.000000 loss: 0.1552 (0.1911) grad: 0.0895 (0.1156) time: 0.5388 data: 0.0023 max mem: 30262 +train: [19] [720/800] eta: 0:00:50 lr: 0.000000 loss: 0.1552 (0.1912) grad: 0.0921 (0.1173) time: 0.8732 data: 0.2856 max mem: 30262 +train: [19] [740/800] eta: 0:00:38 lr: 0.000000 loss: 0.1500 (0.1909) grad: 0.0921 (0.1166) time: 0.6222 data: 0.0032 max mem: 30262 +train: [19] [760/800] eta: 0:00:25 lr: 0.000000 loss: 0.1500 (0.1921) grad: 0.1010 (0.1174) time: 0.5573 data: 0.0040 max mem: 30262 +train: [19] [780/800] eta: 0:00:12 lr: 0.000000 loss: 0.1602 (0.1930) grad: 0.1140 (0.1180) time: 0.5951 data: 0.0038 max mem: 30262 +train: [19] [799/800] eta: 0:00:00 lr: 0.000000 loss: 0.1636 (0.1928) grad: 0.1140 (0.1188) time: 0.5576 data: 0.0036 max mem: 30262 +train: [19] Total time: 0:08:25 (0.6320 s / it) +train: [19] Summary: lr: 0.000000 loss: 0.1636 (0.1928) grad: 0.1140 (0.1188) +eval (validation): [19] [ 0/15] eta: 0:01:18 time: 5.2116 data: 4.8492 max mem: 30262 +eval (validation): [19] [14/15] eta: 0:00:00 time: 0.7866 data: 0.3792 max mem: 30262 +eval (validation): [19] Total time: 0:00:12 (0.8025 s / it) +cv: [19] best hparam: (3.7, 1.0) (032) ('032_lr3.7e+00_wd1.0e+00') loss: 0.704 acc: 0.948 f1: 0.945 bacc: 0.941 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_sex__patch__attn/checkpoint-last.pth +evaluating last checkpoint: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_sex__patch__attn/checkpoint-last.pth +eval model info: +{"score": 0.9406565656565656, "hparam": [3.7, 1.0], "hparam_id": 32, "epoch": 19, "is_best": false, "best_score": 0.9406565656565656} +eval (train): [20] [ 0/118] eta: 0:11:07 time: 5.6564 data: 5.2999 max mem: 30262 +eval (train): [20] [ 20/118] eta: 0:01:36 time: 0.7497 data: 0.2974 max mem: 30262 +eval (train): [20] [ 40/118] eta: 0:01:05 time: 0.6982 data: 0.1874 max mem: 30262 +eval (train): [20] [ 60/118] eta: 0:00:44 time: 0.5873 data: 0.0128 max mem: 30262 +eval (train): [20] [ 80/118] eta: 0:00:27 time: 0.6036 data: 0.0409 max mem: 30262 +eval (train): [20] [100/118] eta: 0:00:12 time: 0.6057 data: 0.1538 max mem: 30262 +eval (train): [20] [117/118] eta: 0:00:00 time: 0.5413 data: 0.1205 max mem: 30262 +eval (train): [20] Total time: 0:01:20 (0.6817 s / it) +eval (validation): [20] [ 0/15] eta: 0:01:22 time: 5.5172 data: 5.2131 max mem: 30262 +eval (validation): [20] [14/15] eta: 0:00:00 time: 0.8514 data: 0.4423 max mem: 30262 +eval (validation): [20] Total time: 0:00:12 (0.8625 s / it) +eval (test): [20] [ 0/14] eta: 0:01:19 time: 5.6484 data: 5.3308 max mem: 30262 +eval (test): [20] [13/14] eta: 0:00:00 time: 0.8977 data: 0.4722 max mem: 30262 +eval (test): [20] Total time: 0:00:12 (0.9085 s / it) +evaluating best checkpoint: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_sex__patch__attn/checkpoint-best.pth +eval model info: +{"score": 0.9406565656565656, "hparam": [12, 1.0], "hparam_id": 39, "epoch": 3, "is_best": true, "best_score": 0.9406565656565656} +eval (train): [20] [ 0/118] eta: 0:11:22 time: 5.7877 data: 5.4081 max mem: 30262 +eval (train): [20] [ 20/118] eta: 0:01:30 time: 0.6758 data: 0.1120 max mem: 30262 +eval (train): [20] [ 40/118] eta: 0:00:59 time: 0.5894 data: 0.0173 max mem: 30262 +eval (train): [20] [ 60/118] eta: 0:00:41 time: 0.6028 data: 0.0255 max mem: 30262 +eval (train): [20] [ 80/118] eta: 0:00:25 time: 0.5925 data: 0.0151 max mem: 30262 +eval (train): [20] [100/118] eta: 0:00:12 time: 0.6399 data: 0.0673 max mem: 30262 +eval (train): [20] [117/118] eta: 0:00:00 time: 0.5403 data: 0.0799 max mem: 30262 +eval (train): [20] Total time: 0:01:17 (0.6552 s / it) +eval (validation): [20] [ 0/15] eta: 0:01:24 time: 5.6640 data: 5.3195 max mem: 30262 +eval (validation): [20] [14/15] eta: 0:00:00 time: 0.8423 data: 0.4371 max mem: 30262 +eval (validation): [20] Total time: 0:00:12 (0.8514 s / it) +eval (test): [20] [ 0/14] eta: 0:01:17 time: 5.5605 data: 5.2269 max mem: 30262 +eval (test): [20] [13/14] eta: 0:00:00 time: 0.8808 data: 0.4755 max mem: 30262 +eval (test): [20] Total time: 0:00:12 (0.8927 s / it) +eval results: + +| model | repr | clf | dataset | ckpt | epoch | lr | wd | hparam_id | hparam | split | loss | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:------|:----------|:-------|--------:|-------:|-----:|------------:|:----------|:-----------|---------:|--------:|----------:|--------:|----------:|--------:|-----------:| +| flat_mae | patch | attn | aabc_sex | best | 3 | 0.0036 | 0.05 | 39 | [12, 1.0] | train | 0.022988 | 0.99151 | 0.0042386 | 0.99133 | 0.0043263 | 0.99133 | 0.0043582 | +| flat_mae | patch | attn | aabc_sex | best | 3 | 0.0036 | 0.05 | 39 | [12, 1.0] | validation | 0.66553 | 0.94828 | 0.029082 | 0.94457 | 0.031513 | 0.94066 | 0.033329 | +| flat_mae | patch | attn | aabc_sex | best | 3 | 0.0036 | 0.05 | 39 | [12, 1.0] | test | 0.45078 | 0.92727 | 0.036165 | 0.92424 | 0.037961 | 0.92424 | 0.038749 | + + +done! total time: 3:05:47 diff --git a/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_sex__patch__attn/train_log.json b/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_sex__patch__attn/train_log.json new file mode 100644 index 0000000000000000000000000000000000000000..37f323928e2a834460d6d011cf7412cca0f670c9 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_sex__patch__attn/train_log.json @@ -0,0 +1,20 @@ +{"epoch": 0, "train/lr": 2.987987987987988e-05, "train/loss": 0.5514294676482677, "train/grad": 0.24213724926114083, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.6869580078125, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.6860546875, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.6847412109375, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.683359375, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.682138671875, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.6805322265625, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.6787255859375, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.676953125, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.67451416015625, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.67216064453125, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.66982421875, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.666396484375, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.66325927734375, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.6586181640625, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.65431884765625, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.6501123046875, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.6448193359375, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.63864990234375, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.6315576171875, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.62509033203125, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.616722412109375, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.608126220703125, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.598360595703125, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.587855224609375, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.576678466796875, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.563248291015625, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.55127685546875, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.5403997802734375, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.5263290405273438, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.5105986022949218, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.49694175720214845, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.4848898315429688, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.4700752258300781, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.4589984321594238, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.4486002540588379, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.44004054069519044, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.431856050491333, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.4244525909423828, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.4167872619628906, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.41083529472351077, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.4090677118301392, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.4076469135284424, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.4033262062072754, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.3981272077560425, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.39801137924194335, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.3978882431983948, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.3874109184741974, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.3749901485443115, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.37171892285346986, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.03701634265016764, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.03683290432207286, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.03654156647156924, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.03629494859836996, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.03607899568974972, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.03580001848749816, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.03555626961402595, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.035301542105153204, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.03503085300792009, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.0347907835803926, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.03458445380441844, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.03432886860333383, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.034105202457867564, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.033826542780734596, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.03359334103297442, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.03339528172975406, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.03315230167238042, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.03288733616936952, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.032617075461894275, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.03237982806283981, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.032090924121439456, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.03181791931157932, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.03154759344877675, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.03130040660034865, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.031076147677376865, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0308619809593074, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.03070181033341214, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.030574735715053977, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.030563066655304283, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.030714061968028547, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.03078417469980195, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.030607431998942048, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.030313110963907094, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.030144912998657673, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.029888387843966482, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.029891055654734374, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.03035578318638727, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.03093198126880452, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.03132017202209681, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.03135643237503245, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.03143149398267269, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.03139039502479136, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.031104265036992727, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.030856057363562287, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.03109787601046264, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.03247939316323027, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.03289466662798077, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.028719463325105606, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.027977694303262978, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.6716450452804565, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.6688637137413025, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.6647056937217712, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.6608911752700806, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.6574917435646057, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.6532427668571472, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.6488156914710999, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.6442291140556335, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.6387635469436646, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.6331972479820251, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.6280144453048706, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.620262086391449, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.6129494309425354, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.6022257804870605, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.59189373254776, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.5821217894554138, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.5694209933280945, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.554243803024292, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.5375944375991821, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.5219911336898804, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.5032780766487122, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.48450809717178345, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.4644978642463684, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.44497552514076233, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.42695531249046326, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.40932953357696533, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.3963783383369446, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.3859797716140747, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.37362053990364075, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.36006805300712585, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.34843534231185913, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.34055134654045105, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.33412399888038635, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.3323911726474762, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.3372465968132019, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.3380412459373474, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.3358954191207886, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.33659908175468445, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.34176090359687805, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.3426474928855896, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.3406054973602295, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.3388076424598694, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.33808764815330505, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.339181512594223, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.34233975410461426, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.3369171917438507, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.3628843128681183, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.323118656873703, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.34130600094795227, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.6206896551724138, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.6206896551724138, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.6206896551724138, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.6206896551724138, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.6206896551724138, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.6206896551724138, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.6206896551724138, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.6206896551724138, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.6206896551724138, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.6379310344827587, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.6551724137931034, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.6724137931034483, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.7241379310344828, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.7241379310344828, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.7586206896551724, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.7413793103448276, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.7758620689655172, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.7931034482758621, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.7931034482758621, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.8103448275862069, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.8620689655172413, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.8620689655172413, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.8620689655172413, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.8793103448275862, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.896551724137931, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.896551724137931, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.896551724137931, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.896551724137931, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.896551724137931, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.896551724137931, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.896551724137931, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.896551724137931, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.896551724137931, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.8793103448275862, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.8793103448275862, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.8793103448275862, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.8793103448275862, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.8793103448275862, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.8793103448275862, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.8793103448275862, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.8793103448275862, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.8793103448275862, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.8448275862068966, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.8620689655172413, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.8448275862068966, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.3829787234042553, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.3829787234042553, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.3829787234042553, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.3829787234042553, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.3829787234042553, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.3829787234042553, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.3829787234042553, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.3829787234042553, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.3829787234042553, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.43057503506311356, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.4746376811594203, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.5156043956043956, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.6233766233766234, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.6233766233766234, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.6852713178294574, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.6698292220113852, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.7340388007054673, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.7583333333333333, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.7583333333333333, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.7817310981867944, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.8473684210526315, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.8473684210526315, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.8473684210526315, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.8706594456833386, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.8901515151515151, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.8901515151515151, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.8901515151515151, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.8901515151515151, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.8901515151515151, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.8901515151515151, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.8901515151515151, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.8901515151515151, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.8901515151515151, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.8706594456833386, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.8706594456833386, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.8706594456833386, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.8706594456833386, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.8706594456833386, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.8706594456833386, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.8706594456833386, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.8706594456833386, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.8706594456833386, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.8366197183098592, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.8507078507078507, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.8302439024390245, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.5, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.5, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.5, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.5, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.5, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.5, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.5, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.5, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.5, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.5227272727272727, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.5454545454545454, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.5681818181818181, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.6363636363636364, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.6363636363636364, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.6818181818181819, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.6679292929292929, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.7222222222222222, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.7449494949494949, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.7449494949494949, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.7676767676767677, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.8358585858585859, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.8358585858585859, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.8358585858585859, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.8674242424242424, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.8901515151515151, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.8901515151515151, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.8901515151515151, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.8901515151515151, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.8901515151515151, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.8901515151515151, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.8901515151515151, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.8901515151515151, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.8901515151515151, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.8674242424242424, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.8674242424242424, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.8674242424242424, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.8674242424242424, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.8674242424242424, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.8674242424242424, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.8674242424242424, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.8674242424242424, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.8674242424242424, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.8396464646464648, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.8446969696969697, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.821969696969697, "id_best": 31, "lr_best": 0.0009299999999999999, "wd_best": 0.05, "train/loss_best": 0.4848898315429688, "validation/loss_best": 0.34055134654045105, "validation/acc_best": 0.9137931034482759, "validation/f1_best": 0.9076138897738133, "validation/bacc_best": 0.904040404040404} +{"epoch": 1, "train/lr": 8.993993993993998e-05, "train/loss": 0.412611726000905, "train/grad": 0.21658122420310974, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.6612255859375, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.65791015625, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.65252197265625, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.64746337890625, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.642333984375, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.635537109375, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.62799072265625, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.61982666015625, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.60934814453125, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.59857177734375, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.5883056640625, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.57343994140625, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.559605712890625, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.540736083984375, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.5239404296875, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.508792724609375, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.491019287109375, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.47205413818359376, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.45300506591796874, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.43705322265625, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.41929405212402343, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.4030701446533203, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.38695343017578127, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.3716340446472168, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.3575787258148193, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.3436673450469971, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.3338644504547119, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.3265452146530151, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.3178479766845703, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.3068874931335449, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.2970536494255066, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.28851712942123414, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.27593589782714845, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.2726217436790466, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.2707145607471466, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.2685400712490082, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.26633347272872926, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.26542028188705447, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.2642177385091782, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.2616667786240578, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.2599648082256317, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.25746665358543397, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.2555162630975246, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.2491661587357521, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.25144760608673095, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.24918095052242278, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.2529851472377777, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.2828144460916519, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.3603870087862015, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.03200566318817437, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.03178676309529692, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.03148701722733677, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.03125538824591786, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.031049761194735764, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.03081062705721706, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.030561670092865825, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.03031242377590388, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.03000861606094986, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.029712355900555848, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.029446090972051024, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.029083879282698035, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.028772855033166705, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.028385774705093354, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.028076104370411484, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.027833624116610736, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.027574319827836008, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.02732702692504972, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.027125355754978955, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.026976729999296366, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.02681010774569586, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.026669335474725813, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.026542378852609544, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.026465789526700974, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.02653069212799892, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.027029563358519228, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.027815400150138885, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.028640130534768105, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.029331682664342225, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.029174665445461868, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.02871023883810267, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.028595342542976143, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.028089269048068674, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.027526713204570116, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.027548424859996885, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.02745657049585134, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.027163077329751106, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.026230736789293586, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.02513886396540329, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.02392343696206808, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.022895428086631, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.022186429321300237, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.021487106059212238, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.02079129605554044, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.02087418648879975, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.020525294195394964, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.02072357782628387, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.032398278068285435, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0437566045532003, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.6372676491737366, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.6323094964027405, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.6244348287582397, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.6169317960739136, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.6096680164337158, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.5998833775520325, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.5892631411552429, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.5777829885482788, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.5634557008743286, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.5489289164543152, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.53555828332901, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.5166841745376587, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.4998449981212616, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.47804680466651917, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.45950135588645935, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.4436023533344269, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.4255688786506653, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.406546026468277, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.38734638690948486, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.37267228960990906, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.35964715480804443, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.3516102135181427, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.34632036089897156, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.3415810465812683, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.3361559510231018, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.3324428200721741, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.3328588306903839, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.33548837900161743, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.3394402861595154, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.3427380323410034, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.3447555601596832, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.3425605595111847, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.3391469120979309, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.3442951738834381, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.3415876626968384, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.3384179174900055, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.3353208005428314, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.3347006142139435, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.33531156182289124, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.3388974666595459, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.3239342272281647, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.3367839753627777, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.3271021246910095, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.3995891511440277, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.4017689824104309, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.3195086419582367, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.2946704030036926, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.3158155679702759, "validation/loss_048_lr5.0e+01_wd1.0e+00": 1.1101821660995483, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.6379310344827587, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.6379310344827587, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.6724137931034483, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.7068965517241379, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.7241379310344828, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.7413793103448276, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.7586206896551724, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.7586206896551724, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.7931034482758621, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.7931034482758621, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.8620689655172413, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.8620689655172413, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.896551724137931, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.896551724137931, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.896551724137931, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.896551724137931, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.896551724137931, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.896551724137931, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.896551724137931, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9137931034482759, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.896551724137931, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.896551724137931, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.896551724137931, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.896551724137931, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.896551724137931, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.8793103448275862, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.8793103448275862, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.8793103448275862, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.8620689655172413, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.8793103448275862, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.8793103448275862, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.8620689655172413, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.8620689655172413, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.8620689655172413, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.8793103448275862, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.8793103448275862, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.8793103448275862, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.8793103448275862, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.896551724137931, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.8620689655172413, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.8620689655172413, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.8620689655172413, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.8448275862068966, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.896551724137931, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.896551724137931, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.896551724137931, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.6896551724137931, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.43057503506311356, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.43057503506311356, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.5156043956043956, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.5896795672076571, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.6233766233766234, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.6551724137931034, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.6852713178294574, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.7087517934002869, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.7583333333333333, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.7583333333333333, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.8473684210526315, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.8473684210526315, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.8901515151515151, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.8901515151515151, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.8901515151515151, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.8901515151515151, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.8901515151515151, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.8901515151515151, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.8901515151515151, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9076138897738133, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.888030888030888, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.8679674796747967, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.888030888030888, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.888030888030888, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.888030888030888, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.888030888030888, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.8706594456833386, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.8706594456833386, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.8679674796747967, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.8473684210526315, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.8679674796747967, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.8679674796747967, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.8473684210526315, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.8473684210526315, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.8473684210526315, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.8679674796747967, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.8679674796747967, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.8679674796747967, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.8679674796747967, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.888030888030888, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.843454790823212, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.8559006211180125, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.843454790823212, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.8214163530619227, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.8919254658385093, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.8919254658385093, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.8825910931174089, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.6892857142857143, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.5227272727272727, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.5227272727272727, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.5681818181818181, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.6136363636363636, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.6363636363636364, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.6590909090909091, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.6818181818181819, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.6994949494949495, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.7449494949494949, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.7449494949494949, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.8358585858585859, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.8358585858585859, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.8901515151515151, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.8901515151515151, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.8901515151515151, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.8901515151515151, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.8901515151515151, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.8901515151515151, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.8901515151515151, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.904040404040404, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.8813131313131313, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.8585858585858586, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.8813131313131313, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.8813131313131313, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.8813131313131313, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.8813131313131313, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.8674242424242424, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.8674242424242424, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.8585858585858586, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.8358585858585859, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.8585858585858586, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.8585858585858586, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.8358585858585859, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.8358585858585859, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.8358585858585859, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.8585858585858586, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.8585858585858586, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.8585858585858586, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.8585858585858586, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.8813131313131313, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.827020202020202, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.8623737373737375, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.827020202020202, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.8042929292929293, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.898989898989899, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.898989898989899, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.8636363636363636, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.7411616161616161, "id_best": 20, "lr_best": 0.000156, "wd_best": 0.05, "train/loss_best": 0.41929405212402343, "validation/loss_best": 0.35964715480804443, "validation/acc_best": 0.9137931034482759, "validation/f1_best": 0.9076138897738133, "validation/bacc_best": 0.904040404040404} +{"epoch": 2, "train/lr": 0.00014999999999999988, "train/loss": 0.39632446646690367, "train/grad": 0.3165227679163218, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.62410400390625, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.6166357421875, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.60476318359375, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.5934912109375, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.5827587890625, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.568404541015625, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.5531591796875, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.537196044921875, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.51783935546875, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.4990020751953125, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.4821551513671875, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.4596820068359375, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.44078643798828127, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.417720947265625, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.39942207336425783, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.38471771240234376, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.3690482711791992, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.35414955139160154, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.34079593658447266, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.3309708786010742, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.32095105171203614, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.31244357585906984, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.3042739820480347, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.2958735656738281, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.2883396863937378, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.282258186340332, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.2761199975013733, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.26934376716613767, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.26156842470169067, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.2564677166938782, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.25365272521972654, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.2522235643863678, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.2563092714548111, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.254354145526886, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.24880484402179717, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.24361291408538818, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.23873111933469773, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.2390158650279045, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.2561741563677788, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.2230043238401413, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.2176761171221733, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.25813279062509537, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.23001736372709275, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.3832896415889263, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.38764266595244407, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.691323373913765, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.7689265519380569, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.5580709613859653, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.9144937986135483, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.03158035155385733, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.03139488460263237, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.03110971494112164, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.030860645812936127, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.030639360435307027, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.030343381706625223, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.030058915349654852, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.029766384190879763, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.02946643949020654, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.029185783513821662, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.02895328971091658, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.028697377948556094, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.028513670065440238, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.028312840685248374, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.02812039686832577, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.027905729664489627, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.027547613845672458, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.02711256707087159, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.026803293984849007, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.026650587893091143, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.026683012915309518, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.026906434332486243, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.02713302142219618, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.02736007494851947, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.027819571001455188, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.02833475855179131, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.028409123502206056, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.027908353235106917, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.027518960116431117, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.027766816715011373, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.027974776562768967, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0274707365850918, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.02753693164559081, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.027417915214318783, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.026059866885188968, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.024488721166271717, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.02337901558028534, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.022792684304295107, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.022996006791945547, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.023037438262836076, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.022515417204995173, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.028154124073917045, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.030382053267530865, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.047011967112775895, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.04411282176850364, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.09570575201586769, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.041887139976024626, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.07744563174390351, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.10795088457771045, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.598304033279419, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.5890835523605347, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.5746817588806152, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.5610496401786804, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.5482474565505981, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.531559407711029, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.5141867399215698, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.49636024236679077, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.4755408465862274, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.45599937438964844, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.43936023116111755, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.418381005525589, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.4019801616668701, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.38382622599601746, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.3709978461265564, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.36190900206565857, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.35286644101142883, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.34520265460014343, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.33929571509361267, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.3343059718608856, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.32986417412757874, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.3291168510913849, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.330519437789917, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.3328361213207245, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.33777809143066406, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.34548354148864746, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.3633461594581604, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.3891637623310089, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.4075033366680145, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.4066650867462158, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.40358567237854004, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.40436115860939026, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.4024869203567505, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.39598459005355835, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.3885110318660736, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.383344829082489, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.37780997157096863, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.3775613605976105, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.40565821528434753, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.45379218459129333, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.5389117002487183, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.8622685074806213, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.6956474184989929, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.8280249238014221, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.6795746088027954, "validation/loss_045_lr3.1e+01_wd1.0e+00": 1.9349567890167236, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.5621010065078735, "validation/loss_048_lr5.0e+01_wd1.0e+00": 2.6156811714172363, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.7241379310344828, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.7413793103448276, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.7413793103448276, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.7758620689655172, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.7931034482758621, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.7931034482758621, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.8448275862068966, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.8620689655172413, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.8620689655172413, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.8793103448275862, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.896551724137931, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9137931034482759, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9137931034482759, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9137931034482759, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.896551724137931, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.896551724137931, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.896551724137931, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9137931034482759, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9137931034482759, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9137931034482759, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.8620689655172413, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.8793103448275862, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.8620689655172413, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.8620689655172413, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.8448275862068966, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.8448275862068966, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.8448275862068966, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.8448275862068966, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.8448275862068966, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.8448275862068966, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.8620689655172413, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.8793103448275862, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.896551724137931, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.896551724137931, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.896551724137931, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9137931034482759, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.896551724137931, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.8448275862068966, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.8275862068965517, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.8448275862068966, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.7586206896551724, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.8620689655172413, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.6206896551724138, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.8793103448275862, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.8275862068965517, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.6233766233766234, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.6551724137931034, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.6698292220113852, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.7340388007054673, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.7583333333333333, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.7583333333333333, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.8261738261738262, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.8473684210526315, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.8473684210526315, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.8679674796747967, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.888030888030888, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9076138897738133, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9076138897738133, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9076138897738133, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.8901515151515151, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.8901515151515151, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.8901515151515151, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9076138897738133, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9076138897738133, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9076138897738133, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.8507078507078507, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.8679674796747967, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.8473684210526315, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.8473684210526315, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.8261738261738262, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.8261738261738262, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.8261738261738262, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.8261738261738262, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.8261738261738262, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.8261738261738262, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.8473684210526315, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.8679674796747967, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.888030888030888, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.888030888030888, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.888030888030888, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9056910569105692, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.8919254658385093, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.8366197183098592, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.8223039215686274, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.8390379278445883, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.7560096153846154, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.8507078507078507, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.3829787234042553, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.8729264475743349, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.7986111111111112, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.6363636363636364, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.6590909090909091, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.6679292929292929, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.7222222222222222, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.7449494949494949, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.7449494949494949, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.8131313131313131, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.8358585858585859, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.8358585858585859, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.8585858585858586, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.8813131313131313, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.904040404040404, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.904040404040404, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.904040404040404, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.8901515151515151, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.8901515151515151, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.8901515151515151, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.904040404040404, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.904040404040404, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.904040404040404, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.8446969696969697, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.8585858585858586, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.8358585858585859, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.8358585858585859, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.8131313131313131, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.8131313131313131, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.8131313131313131, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.8131313131313131, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.8131313131313131, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.8131313131313131, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.8358585858585859, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.8585858585858586, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.8813131313131313, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.8813131313131313, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.8813131313131313, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.8952020202020202, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.898989898989899, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.8396464646464648, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.8345959595959596, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.8484848484848485, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.779040404040404, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.8446969696969697, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.5, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.8762626262626263, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.7815656565656566, "id_best": 11, "lr_best": 3.5999999999999994e-05, "wd_best": 0.05, "train/loss_best": 0.4596820068359375, "validation/loss_best": 0.418381005525589, "validation/acc_best": 0.9137931034482759, "validation/f1_best": 0.9076138897738133, "validation/bacc_best": 0.904040404040404} +{"epoch": 3, "train/lr": 0.0002100600600600602, "train/loss": 0.35802663017064335, "train/grad": 0.2805497855693102, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.585634765625, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.57443603515625, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.55701904296875, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.540919189453125, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.5262335205078125, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.5077154541015625, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.489027099609375, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.4706988525390625, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.45029434204101565, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.43219268798828125, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.41735816955566407, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.39964702606201175, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.3860372734069824, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.3707615852355957, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.3593093299865723, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.35039435386657714, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.3411046886444092, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.3324510383605957, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.32474220514297486, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.3188836693763733, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.3118314063549042, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.30312161445617675, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.29237663745880127, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.2810253536701202, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.27343942284584044, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.2697844535112381, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.26655737340450286, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.26211288273334504, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.2603612369298935, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.25586304888129235, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.2495308232307434, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.24071668311953545, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.21730051964521407, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.19650922179222108, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.15596869543194772, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.1349535770714283, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.13101202756166458, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.13369395852088928, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.09936956688761711, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.1452416944503784, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.1197023855149746, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.20005416497588158, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.12269873186945915, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.1949220936000347, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.5149193224310875, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.778605086505413, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.69140625, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.7996641993522644, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.9057025218009949, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.028184394906274973, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.027827496072277427, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.02729558411054313, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.02681440149899572, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.026386079038493337, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.025861490443348886, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.025355818634852766, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.024889502795413136, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.024402808984741568, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.024013420934788882, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.023731133434921503, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.023457282576709985, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.023335343985818328, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.02331718208035454, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.023442279980517924, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.023638912949245423, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.0240086963865906, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.024597980929538608, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.02541307938983664, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.026073426159564407, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.02648832120699808, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.026753113132435828, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.027494566387031228, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.02831954425899312, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.02897532153641805, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.029332065087510274, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.02900352588389069, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.02900676162680611, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.02893902118084952, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.028630679046036677, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.027539479492697864, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.02614570990903303, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.024667969689471648, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.024047886924818157, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.022317172597395254, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.02039808232919313, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.019329987837554654, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.020110354370553977, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.016265474247702513, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.026418466908144183, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.02511743941048735, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0316824643675136, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.022427125652533277, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.028678248474443536, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.06883075900122095, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.11151978896695805, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.01358729641357627, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.027773553517836263, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.5566127300262451, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.5437136292457581, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.5237990021705627, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.5058258175849915, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.4896738529205322, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.4695838987827301, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.4499449133872986, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.43123430013656616, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.4108598232269287, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.39365464448928833, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.38013744354248047, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.3648536205291748, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.3541322350502014, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.3437008261680603, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.33713942766189575, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.333105206489563, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.3299713730812073, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.32841217517852783, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.3289108872413635, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.3301060199737549, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.3299742341041565, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.33833563327789307, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.34693557024002075, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.3434048593044281, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.34234002232551575, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.33998894691467285, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.3387235701084137, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.3468765318393707, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.34877917170524597, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.33799898624420166, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.3351975083351135, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.33390843868255615, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.3574715852737427, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.38141122460365295, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.4835931956768036, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.4914102256298065, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.6136981844902039, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.905756413936615, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.8074626326560974, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.665527880191803, "validation/loss_040_lr1.4e+01_wd1.0e+00": 1.3110053539276123, "validation/loss_041_lr1.6e+01_wd1.0e+00": 5.130394458770752, "validation/loss_042_lr1.9e+01_wd1.0e+00": 1.2021336555480957, "validation/loss_043_lr2.2e+01_wd1.0e+00": 1.2263084650039673, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.665020763874054, "validation/loss_045_lr3.1e+01_wd1.0e+00": 6.016181468963623, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.6931472420692444, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.7931034482758621, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.8448275862068966, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.8620689655172413, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.8793103448275862, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9137931034482759, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.896551724137931, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.896551724137931, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.896551724137931, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.896551724137931, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.896551724137931, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.896551724137931, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9137931034482759, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9137931034482759, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9137931034482759, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.896551724137931, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.896551724137931, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.896551724137931, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.896551724137931, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.896551724137931, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.896551724137931, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.8793103448275862, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.8620689655172413, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.8620689655172413, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.8620689655172413, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.8620689655172413, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.8620689655172413, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.8620689655172413, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.8620689655172413, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.8620689655172413, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.8793103448275862, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.896551724137931, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.896551724137931, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.8103448275862069, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9482758620689655, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.8793103448275862, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.7241379310344828, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.896551724137931, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.8448275862068966, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.8275862068965517, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.7758620689655172, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.6206896551724138, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.6206896551724138, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.6206896551724138, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.7583333333333333, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.8261738261738262, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.8473684210526315, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.8679674796747967, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.9076138897738133, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.8901515151515151, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.8901515151515151, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.8901515151515151, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.8901515151515151, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.8901515151515151, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.8901515151515151, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9076138897738133, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9076138897738133, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9076138897738133, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.888030888030888, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.888030888030888, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.888030888030888, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.888030888030888, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.888030888030888, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.888030888030888, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.8706594456833386, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.8507078507078507, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.8507078507078507, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.8473684210526315, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.8473684210526315, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.8473684210526315, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.8473684210526315, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.8507078507078507, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.8507078507078507, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.8706594456833386, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.8919254658385093, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.8919254658385093, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9092331768388107, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.8075414781297134, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9092331768388107, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.944568333864288, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.8679674796747967, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.6403100775193798, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.8901515151515151, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.8409990862016448, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.8242424242424242, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.7752608047690015, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.3829787234042553, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.3829787234042553, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.3829787234042553, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.7449494949494949, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.8131313131313131, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.8358585858585859, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.8585858585858586, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.904040404040404, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.8901515151515151, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.8901515151515151, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.8901515151515151, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.8901515151515151, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.8901515151515151, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.8901515151515151, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.904040404040404, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.904040404040404, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.904040404040404, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.8813131313131313, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.8813131313131313, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.8813131313131313, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.8813131313131313, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.8813131313131313, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.8813131313131313, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.8674242424242424, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.8446969696969697, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.8446969696969697, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.8358585858585859, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.8358585858585859, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.8358585858585859, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.8358585858585859, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.8446969696969697, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.8446969696969697, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.8674242424242424, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.898989898989899, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.898989898989899, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.9128787878787878, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.8295454545454546, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.9128787878787878, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.9406565656565656, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.8585858585858586, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.6452020202020202, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.8901515151515151, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.8573232323232323, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.8434343434343434, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.8106060606060606, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.5, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.5, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.5, "id_best": 39, "lr_best": 0.0036, "wd_best": 0.05, "train/loss_best": 0.1452416944503784, "validation/loss_best": 0.665527880191803, "validation/acc_best": 0.9482758620689655, "validation/f1_best": 0.944568333864288, "validation/bacc_best": 0.9406565656565656} +{"epoch": 4, "train/lr": 0.0002701201201201201, "train/loss": 0.3179501338303089, "train/grad": 0.2873043566569686, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.518109130859375, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.501488037109375, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.4767095947265625, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.4550238037109375, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.4361065673828125, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.413243408203125, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.39180328369140627, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.3720660400390625, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.3514617919921875, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.33427059173583984, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.3208585739135742, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.30525535583496094, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.2935028076171875, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.2806362438201904, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.27103456497192385, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.2633120632171631, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.25499298095703127, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.24687836170196534, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.23862143039703368, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.23014504194259644, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.22250331044197083, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.2192539417743683, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.21047423243522645, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.1982543033361435, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.18918455004692078, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.18442048072814943, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.18171010076999664, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.1792014728486538, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.17087553322315216, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.13959098488092422, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.10529194727540016, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.08586325973272324, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.057856701016426086, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.03182222172617912, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.029469881504774094, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.02025467962026596, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.053143782764673235, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.04213759064674377, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.1252632448077202, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.05269760102033615, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.40009842067956924, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.34033418133854865, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.7824295531213283, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.7886556161940098, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.8990047271549702, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.8400262033939362, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.69140625, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.69140625, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.69140625, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.02762740507721901, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.027223814683966337, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.02665095399133861, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.026159520568326114, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.02574320155661553, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.025259792204014957, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.02484659480396658, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.02449702186975628, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.0241949980892241, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.02399053066270426, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.023893904893193395, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.02386190483113751, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.02394392584450543, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.02418650074629113, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.024523744937032462, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.024843682278878988, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.025229365199338646, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.025853754826821385, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.02655698743648827, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.02687826445326209, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.02721833239076659, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.02780266477027908, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.02815806771395728, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.028686603815294802, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.02923200430115685, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.029143316159024834, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0288505856518168, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.028496754306834193, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.027233235908206553, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.023628091864520685, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.020329857998585794, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.019150740780460182, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.012287991816046997, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.00810454645430582, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.010751032178227433, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.007463824230890168, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.01925664685827542, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.012525030530848653, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.027902486052621498, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.011223827354483547, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0581821857176476, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.055106040993430055, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.021997182749051946, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.03955021411832092, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.08016602043705462, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.023262977734960947, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.5098699331283569, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.49402105808258057, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.4709451496601105, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.4515622854232788, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.43533647060394287, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.41682112216949463, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.40023258328437805, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.38636475801467896, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.3726102113723755, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.36194005608558655, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.3541896343231201, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.3454511761665344, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.33986395597457886, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.33321261405944824, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.3289016783237457, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.32885491847991943, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.33589109778404236, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.3481471836566925, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.3653709888458252, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.3873862028121948, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.39764830470085144, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.39640259742736816, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.4052298665046692, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.4223932921886444, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.39867693185806274, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.36525121331214905, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.3386994004249573, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.32237565517425537, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.32253801822662354, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.3623946011066437, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.42107921838760376, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.5239084362983704, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.6194557547569275, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.6604703664779663, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.8577690720558167, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.8975377082824707, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.6951751112937927, "validation/loss_037_lr8.3e+00_wd1.0e+00": 1.191547155380249, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.8706006407737732, "validation/loss_039_lr1.2e+01_wd1.0e+00": 1.0563751459121704, "validation/loss_040_lr1.4e+01_wd1.0e+00": 1.4775670766830444, "validation/loss_041_lr1.6e+01_wd1.0e+00": 1.997199296951294, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.6931472420692444, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.8620689655172413, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.8793103448275862, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.896551724137931, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.896551724137931, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.896551724137931, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.896551724137931, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.896551724137931, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.896551724137931, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.896551724137931, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.896551724137931, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.896551724137931, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9137931034482759, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9137931034482759, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.896551724137931, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.896551724137931, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.8620689655172413, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.8620689655172413, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.8620689655172413, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.8620689655172413, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.8620689655172413, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.8620689655172413, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.8448275862068966, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.8448275862068966, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.8448275862068966, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.8620689655172413, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.8620689655172413, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.8620689655172413, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.896551724137931, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.896551724137931, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.896551724137931, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.896551724137931, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.8448275862068966, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.8620689655172413, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.8620689655172413, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.8793103448275862, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9137931034482759, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.8793103448275862, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.896551724137931, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.6206896551724138, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.6206896551724138, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.6206896551724138, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.6206896551724138, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.6206896551724138, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.6206896551724138, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.6206896551724138, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.8473684210526315, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.8679674796747967, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.8901515151515151, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.8901515151515151, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.8901515151515151, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.8901515151515151, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.8901515151515151, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.8901515151515151, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.8901515151515151, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.8901515151515151, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.8901515151515151, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9076138897738133, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9076138897738133, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.8901515151515151, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.888030888030888, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.8473684210526315, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.8473684210526315, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.8473684210526315, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.8473684210526315, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.8473684210526315, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.8473684210526315, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.8261738261738262, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.8261738261738262, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.8261738261738262, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.8473684210526315, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.8507078507078507, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.8507078507078507, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.8901515151515151, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.8901515151515151, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.888030888030888, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.888030888030888, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.8390379278445883, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.8559006211180125, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.8473684210526315, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.8706594456833386, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9076138897738133, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.8729264475743349, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.8901515151515151, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.3829787234042553, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.3829787234042553, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.3829787234042553, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.3829787234042553, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.3829787234042553, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.3829787234042553, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.3829787234042553, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.8358585858585859, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.8585858585858586, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.8901515151515151, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.8901515151515151, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.8901515151515151, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.8901515151515151, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.8901515151515151, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.8901515151515151, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.8901515151515151, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.8901515151515151, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.8901515151515151, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.904040404040404, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.904040404040404, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.8901515151515151, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.8813131313131313, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.8358585858585859, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.8358585858585859, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.8358585858585859, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.8358585858585859, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.8358585858585859, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.8358585858585859, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.8131313131313131, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.8131313131313131, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.8131313131313131, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.8358585858585859, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.8446969696969697, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.8446969696969697, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.8901515151515151, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.8901515151515151, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.8813131313131313, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.8813131313131313, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.8484848484848485, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.8623737373737375, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.8358585858585859, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.8674242424242424, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.904040404040404, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.8762626262626263, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.8901515151515151, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.5, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.5, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.5, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.5, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.5, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.5, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.5, "id_best": 11, "lr_best": 3.5999999999999994e-05, "wd_best": 0.05, "train/loss_best": 0.30525535583496094, "validation/loss_best": 0.3454511761665344, "validation/acc_best": 0.9137931034482759, "validation/f1_best": 0.9076138897738133, "validation/bacc_best": 0.904040404040404} +{"epoch": 5, "train/lr": 0.00029891323817685334, "train/loss": 0.291613215431571, "train/grad": 0.18036332957446574, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.4987554931640625, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.4815032958984375, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.457030029296875, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.43702667236328124, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.42040740966796875, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.4017695617675781, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.38530704498291013, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.3709754180908203, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.35658275604248046, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.3446719837188721, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.33537631034851073, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.3239329433441162, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.31495962142944334, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.3042757225036621, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.29545881748199465, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.2873524236679077, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.2774483060836792, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.2668745493888855, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.25609569311141966, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.24709628343582155, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.23962127029895783, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.23759701132774352, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.2375866374373436, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.23632104963064193, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.22788746833801268, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.2165609009563923, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.1996893295645714, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.17358286157250405, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.10910163313150406, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.052171837091445926, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.031762452721595766, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.011531572639942169, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.05215729922056198, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.0007345806062221527, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.050673744082450865, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.00044719263911247254, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.004011998772621155, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.16364369437098503, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.12121506437659263, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.0003404141962528229, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.00025166377425193785, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.01941405311226845, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.69140625, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.69140625, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.69140625, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.69140625, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.69140625, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.69140625, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.69140625, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.028766958303749562, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.02837735027540475, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.0278272019373253, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.027364573841914534, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.026983229760080576, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.02656939030159265, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.026250967772211878, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.026010672885458917, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.02581428036093712, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.0256796960439533, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.02560551095055416, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.025570515361614525, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.025639086817391216, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.025886925908271224, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.026250681418459862, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.02677138740895316, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.02760377459228039, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.028277810525614767, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.02848144250921905, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.02864380259765312, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.02971345690311864, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.030806695914361627, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.03140870243310928, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.03159333780524321, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.030742242695996538, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.028836416751146315, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.027039167523616923, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.025757114994921722, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.02115545858105179, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.013451331394317095, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.010424641356639768, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.004350324793540495, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.01229743740369031, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.00026840758491744057, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.010947556657984024, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.00014097636886617693, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.002540960726146011, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.028636167507191584, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.017359130328665526, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.00012494832139225309, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0001439100303729379, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.004926130922996426, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.47133782505989075, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.4549933671951294, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.43249085545539856, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.4146277606487274, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.4004350006580353, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.3846648335456848, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.3707047700881958, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.35887259244918823, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.34721142053604126, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.33848974108695984, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.33318254351615906, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.33024609088897705, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.3309047520160675, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.3338940441608429, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.3362208604812622, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.33821940422058105, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.34140744805336, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.3441894054412842, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.3464699685573578, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.3524843156337738, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.36578983068466187, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.3699147701263428, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.3665328621864319, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.3575708568096161, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.34074458479881287, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.33531880378723145, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.3501410186290741, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.373332679271698, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.40313777327537537, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.48720991611480713, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.5304983258247375, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.63898766040802, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.5429172515869141, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.7328576445579529, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.7916814088821411, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.920758068561554, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.9340497851371765, "validation/loss_037_lr8.3e+00_wd1.0e+00": 1.3889580965042114, "validation/loss_038_lr9.8e+00_wd1.0e+00": 1.917701244354248, "validation/loss_039_lr1.2e+01_wd1.0e+00": 1.025841236114502, "validation/loss_040_lr1.4e+01_wd1.0e+00": 1.3424372673034668, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.578639268875122, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.6931472420692444, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.896551724137931, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.896551724137931, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.896551724137931, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.896551724137931, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.896551724137931, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.896551724137931, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.896551724137931, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.896551724137931, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9137931034482759, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9137931034482759, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.896551724137931, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.896551724137931, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.896551724137931, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.8620689655172413, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.8620689655172413, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.8620689655172413, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.8620689655172413, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.8620689655172413, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.8448275862068966, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.8620689655172413, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.8620689655172413, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.8448275862068966, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.8448275862068966, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.8620689655172413, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.896551724137931, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.896551724137931, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.896551724137931, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9310344827586207, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9310344827586207, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.8793103448275862, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.8275862068965517, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.8448275862068966, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9137931034482759, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.896551724137931, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.8620689655172413, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.6206896551724138, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.6206896551724138, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.6206896551724138, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.6206896551724138, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.6206896551724138, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.6206896551724138, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.6206896551724138, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.8901515151515151, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.8901515151515151, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.8901515151515151, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.8901515151515151, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.8901515151515151, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.8901515151515151, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.8901515151515151, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.8901515151515151, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9076138897738133, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9076138897738133, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.888030888030888, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.888030888030888, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.888030888030888, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.8679674796747967, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.8473684210526315, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.8473684210526315, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.8507078507078507, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.8507078507078507, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.8507078507078507, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.8302439024390245, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.8473684210526315, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.8473684210526315, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.8302439024390245, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.8302439024390245, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.8507078507078507, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.8901515151515151, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.8901515151515151, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.888030888030888, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9253539253539254, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9253539253539254, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9092331768388107, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.8729264475743349, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.8223039215686274, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.8390379278445883, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9076138897738133, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.8901515151515151, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.8559006211180125, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.3829787234042553, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.3829787234042553, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.3829787234042553, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.3829787234042553, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.3829787234042553, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.3829787234042553, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.3829787234042553, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.8901515151515151, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.8901515151515151, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.8901515151515151, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.8901515151515151, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.8901515151515151, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.8901515151515151, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.8901515151515151, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.8901515151515151, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.904040404040404, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.904040404040404, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.8813131313131313, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.8813131313131313, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.8813131313131313, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.8585858585858586, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.8358585858585859, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.8358585858585859, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.8446969696969697, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.8446969696969697, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.8446969696969697, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.821969696969697, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.8358585858585859, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.8358585858585859, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.821969696969697, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.821969696969697, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.8446969696969697, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.8901515151515151, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.8901515151515151, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.8813131313131313, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.9179292929292929, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.9179292929292929, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.9128787878787878, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.8762626262626263, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.8345959595959596, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.8484848484848485, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.904040404040404, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.8901515151515151, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.8623737373737375, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.5, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.5, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.5, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.5, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.5, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.5, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.5, "id_best": 29, "lr_best": 0.0006899999999999999, "wd_best": 0.05, "train/loss_best": 0.052171837091445926, "validation/loss_best": 0.48720991611480713, "validation/acc_best": 0.9310344827586207, "validation/f1_best": 0.9253539253539254, "validation/bacc_best": 0.9179292929292929} +{"epoch": 6, "train/lr": 0.0002924170901991409, "train/loss": 0.2585829335823655, "train/grad": 0.14696164464578032, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.45436859130859375, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.4375267028808594, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.41458328247070314, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.39694679260253907, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.3829619216918945, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.36782161712646483, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.3546488952636719, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.34315592765808106, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.33125075340271, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.32110219478607177, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.312791051864624, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.3021158790588379, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.2933571910858154, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.2827738046646118, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.27410086393356325, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.26683605432510377, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.25847301602363587, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.2491422438621521, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.24032390475273133, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.2336272794008255, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.22553391575813295, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.21709391802549363, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.2071566465497017, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.19458588019013404, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.17567541301250458, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.13864744544029237, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.08961446166038513, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.044873235374689104, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.009828927218914032, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0021624960005283355, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0009302987158298493, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.000537152886390686, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.001128847748041153, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.00033688217401504515, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.00028300464153289793, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.00016273334622383118, "train/loss_036_lr7.1e+00_wd1.0e+00": 7.504448294639587e-05, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.002707878798246384, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.0005501268804073334, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.0001813587546348572, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.00020490124821662904, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.0005417916178703308, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.69140625, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.69140625, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.69140625, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.69140625, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.69140625, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.69140625, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.69140625, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.026338377841748296, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.025831444072537124, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.025168961174786092, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.024697430632077157, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.024370056698098778, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.024085568976588548, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.0239389861212112, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.023928244307171553, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.024013417216483503, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.02417319386266172, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.024356341122183947, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.02470681256381795, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.02513225961010903, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.025906693094875664, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.026723557263612748, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.02750451683299616, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.028606952142436057, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.02955549208680168, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.029482828298350795, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.029060825721826403, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.028535969802178443, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.027994842929765583, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.02736973138060421, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.026698772285599262, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.026150093249743805, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.023700396333588288, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.019872200344980228, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.014195784259791254, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0032618205291510094, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0009157790082281281, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0004113510093065997, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0002455387597501613, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0003993674823686888, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.00014011849673579491, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.00015202423748263526, "train/grad_035_lr6.0e+00_wd1.0e+00": 6.543593478625098e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 4.525002680026091e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.002472033747654354, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0002425847260156791, "train/grad_039_lr1.2e+01_wd1.0e+00": 7.936827157465132e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.00013636670178122757, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0001794371607577644, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.44029131531715393, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.4242223799228668, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.4031158983707428, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.3870737552642822, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.3748355805873871, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.36202874779701233, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.35162353515625, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.3432849645614624, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.33616912364959717, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.3316127061843872, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.3295399844646454, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.32887622714042664, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.330074280500412, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.33418262004852295, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.3398681581020355, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.345388799905777, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.349959135055542, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.349738210439682, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.34878984093666077, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.347933828830719, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.346887469291687, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.3461952805519104, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.3486640155315399, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.36423632502555847, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.39464473724365234, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.4328354597091675, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.40911978483200073, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.4779660701751709, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.540168285369873, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.5983356237411499, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.584145724773407, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.6567868590354919, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.6041226983070374, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.7692004442214966, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.8220655918121338, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.9217650294303894, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.9107843637466431, "validation/loss_037_lr8.3e+00_wd1.0e+00": 1.1915539503097534, "validation/loss_038_lr9.8e+00_wd1.0e+00": 1.8250758647918701, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.9937098026275635, "validation/loss_040_lr1.4e+01_wd1.0e+00": 1.2555595636367798, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.1127023696899414, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.6931472420692444, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.896551724137931, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.896551724137931, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.896551724137931, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.896551724137931, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.896551724137931, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.896551724137931, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9137931034482759, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.9137931034482759, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9137931034482759, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.896551724137931, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.896551724137931, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.896551724137931, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.8620689655172413, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.8620689655172413, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.8448275862068966, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.8448275862068966, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.8448275862068966, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.896551724137931, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.896551724137931, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9310344827586207, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9482758620689655, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.896551724137931, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.896551724137931, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.8793103448275862, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9137931034482759, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.896551724137931, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.8793103448275862, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.6206896551724138, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.6206896551724138, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.6206896551724138, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.6206896551724138, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.6206896551724138, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.6206896551724138, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.6206896551724138, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.8901515151515151, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.8901515151515151, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.8901515151515151, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.8901515151515151, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.8901515151515151, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.8901515151515151, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.9076138897738133, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9076138897738133, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9076138897738133, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.888030888030888, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.888030888030888, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.888030888030888, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.8507078507078507, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.8507078507078507, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.8302439024390245, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.8302439024390245, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.8302439024390245, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.888030888030888, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.888030888030888, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9253539253539254, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.944568333864288, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.8901515151515151, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.8901515151515151, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.8729264475743349, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9076138897738133, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.8901515151515151, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.8706594456833386, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.3829787234042553, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.3829787234042553, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.3829787234042553, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.3829787234042553, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.3829787234042553, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.3829787234042553, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.3829787234042553, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.8901515151515151, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.8901515151515151, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.8901515151515151, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.8901515151515151, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.8901515151515151, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.8901515151515151, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.904040404040404, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.904040404040404, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.904040404040404, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.8813131313131313, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.8813131313131313, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.8813131313131313, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.8446969696969697, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.8446969696969697, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.821969696969697, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.821969696969697, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.821969696969697, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.8813131313131313, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.8813131313131313, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.9179292929292929, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.9406565656565656, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.8901515151515151, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.8901515151515151, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.8762626262626263, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.904040404040404, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.8901515151515151, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.8674242424242424, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.5, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.5, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.5, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.5, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.5, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.5, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.5, "id_best": 32, "lr_best": 0.0011099999999999999, "wd_best": 0.05, "train/loss_best": 0.001128847748041153, "validation/loss_best": 0.6041226983070374, "validation/acc_best": 0.9482758620689655, "validation/f1_best": 0.944568333864288, "validation/bacc_best": 0.9406565656565656} +{"epoch": 7, "train/lr": 0.00027969249556793234, "train/loss": 0.22852993968874216, "train/grad": 0.1416381386294961, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.41544769287109373, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.39747306823730466, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.37375602722167967, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.35556713104248044, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.34125858306884765, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.3257791709899902, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.31214844703674316, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.3000973606109619, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.2876639413833618, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.27700570583343503, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.26812167167663575, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.2566923785209656, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.24705960512161254, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.23498090982437134, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.22503383398056032, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.2164207673072815, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.20618743062019348, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.1958383572101593, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.18763328939676285, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.18087664514780044, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.1689072461426258, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.1577352298796177, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.14469336554408074, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.1244858580827713, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.09120979726314545, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.04459400117397308, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.013141036480665207, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0036170487105846405, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0015322555601596831, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0008674702048301697, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0005566109716892242, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.0003403507173061371, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.00040938764810562135, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.00021755218505859375, "train/loss_034_lr5.1e+00_wd1.0e+00": 9.904652833938598e-05, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.00012478113174438477, "train/loss_036_lr7.1e+00_wd1.0e+00": 7.362604141235352e-05, "train/loss_037_lr8.3e+00_wd1.0e+00": 4.325836896896362e-05, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.2164881229400635e-05, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.00014996901154518127, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.0002012835443019867, "train/loss_041_lr1.6e+01_wd1.0e+00": 6.01997971534729e-05, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.69140625, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.69140625, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.69140625, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.69140625, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.69140625, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.69140625, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.69140625, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.023978003947995603, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.023618495943956076, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.023219932306092234, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.022985725190956145, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.022864003397990017, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.022821303613018245, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.02288894466822967, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.023049913111608474, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.023314709537662567, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.02363809136673808, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.02398186710430309, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.024513884130865336, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.025050086558330804, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.025976058098021896, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.02702260237187147, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.027848889674060046, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.02835615787655115, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.028554334426298737, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.029044180874479936, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.029706148838158697, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.02990683457814157, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.02994735383312218, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.029876754950964823, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.02861369260470383, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.025424652149667964, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.017329758759442485, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.005816691991676635, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0015847949545423035, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0006772931094383239, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.00037522337461723507, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.00023890860277333558, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.000156796002036117, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.00016714797223926325, "train/grad_033_lr4.3e+00_wd1.0e+00": 9.55392788372933e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 5.761581285440798e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 5.1020889161463854e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 4.151247964216509e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 2.7601209804775094e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 1.5985793577847906e-05, "train/grad_039_lr1.2e+01_wd1.0e+00": 6.811455043063574e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0001335368917924562, "train/grad_041_lr1.6e+01_wd1.0e+00": 4.2390352941946704e-05, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.417259156703949, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.4025684595108032, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.38410720229148865, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.3706999719142914, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.3608996868133545, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.3506215810775757, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.34233358502388, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.33610770106315613, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.330954372882843, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.32813236117362976, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.32748880982398987, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.32930219173431396, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.33309805393218994, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.33912837505340576, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.34532430768013, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.35364624857902527, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.36941930651664734, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.38519150018692017, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.38568994402885437, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.3718763589859009, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.34433528780937195, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.328622043132782, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.33258554339408875, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.3643152713775635, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.4149947464466095, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.448096364736557, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.5381434559822083, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.5600518584251404, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.601594865322113, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.6426061391830444, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.6109219193458557, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.6731699705123901, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.6315203905105591, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.7906947731971741, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.8127028346061707, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.917218029499054, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.8927748203277588, "validation/loss_037_lr8.3e+00_wd1.0e+00": 1.124831199645996, "validation/loss_038_lr9.8e+00_wd1.0e+00": 1.6823471784591675, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.9728055596351624, "validation/loss_040_lr1.4e+01_wd1.0e+00": 1.1896519660949707, "validation/loss_041_lr1.6e+01_wd1.0e+00": 1.9096108675003052, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.6931472420692444, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.896551724137931, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.896551724137931, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.896551724137931, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.896551724137931, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.896551724137931, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.9137931034482759, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9137931034482759, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.9137931034482759, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.896551724137931, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.896551724137931, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.8620689655172413, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.8620689655172413, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.8620689655172413, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.8620689655172413, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.896551724137931, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9310344827586207, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9482758620689655, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.896551724137931, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.896551724137931, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.8793103448275862, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9137931034482759, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.896551724137931, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.8793103448275862, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.6206896551724138, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.6206896551724138, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.6206896551724138, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.6206896551724138, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.6206896551724138, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.6206896551724138, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.6206896551724138, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.8901515151515151, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.8901515151515151, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.8901515151515151, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.8901515151515151, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.8901515151515151, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.9076138897738133, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.9076138897738133, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9076138897738133, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.888030888030888, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.888030888030888, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.8559006211180125, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.8559006211180125, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.8559006211180125, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.8559006211180125, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.8729264475743349, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.8901515151515151, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9092331768388107, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9267676767676767, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.944568333864288, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.8901515151515151, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.8901515151515151, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.8729264475743349, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9076138897738133, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.8901515151515151, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.8706594456833386, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.3829787234042553, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.3829787234042553, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.3829787234042553, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.3829787234042553, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.3829787234042553, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.3829787234042553, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.3829787234042553, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.8901515151515151, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.8901515151515151, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.8901515151515151, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.8901515151515151, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.8901515151515151, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.904040404040404, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.904040404040404, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.904040404040404, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.8813131313131313, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.8813131313131313, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.8623737373737375, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.8623737373737375, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.8623737373737375, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.8623737373737375, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.8762626262626263, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.8901515151515151, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.9128787878787878, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.9267676767676767, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.9406565656565656, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.8901515151515151, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.8901515151515151, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.8762626262626263, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.904040404040404, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.8901515151515151, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.8674242424242424, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.5, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.5, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.5, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.5, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.5, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.5, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.5, "id_best": 32, "lr_best": 0.0011099999999999999, "wd_best": 0.05, "train/loss_best": 0.00040938764810562135, "validation/loss_best": 0.6315203905105591, "validation/acc_best": 0.9482758620689655, "validation/f1_best": 0.944568333864288, "validation/bacc_best": 0.9406565656565656} +{"epoch": 8, "train/lr": 0.0002612959497061927, "train/loss": 0.23349105708301068, "train/grad": 0.13614764677360655, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.4046961975097656, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.3906183624267578, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.37255619049072264, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.35919803619384766, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.3487773704528809, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.3371767044067383, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.32670988082885744, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.31683786392211916, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.3060421323776245, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.29669708251953125, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.2889154672622681, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.27949881076812744, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.2719729042053223, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.2623869299888611, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.25388992071151734, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.2466953682899475, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.23918034732341767, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.22939520120620727, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.21728144586086273, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.20599146366119384, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.19144359841942787, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.17419826105237007, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.14093562722206116, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.09234885424375534, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.03141689747571945, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.008587877303361892, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.002812511771917343, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0014648208022117616, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0008802217245101929, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0005632291734218597, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.00036612838506698607, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.0002838470041751862, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.00034063205122947693, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.0002050900459289551, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.0001112113893032074, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.00011495545506477356, "train/loss_036_lr7.1e+00_wd1.0e+00": 9.183347225189209e-05, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.657832741737366e-05, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.2647103071212766e-05, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.0001512002944946289, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.0001783628761768341, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.00013633251190185548, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.69140625, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.69140625, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.69140625, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.69140625, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.69140625, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.69140625, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.69140625, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.026548203483689577, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.02618098061066121, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.025719230438116938, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.025390267150942235, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.02516236410709098, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.024928184477612376, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.024788764901459218, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.024716619921382518, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.024754728474654257, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.024938239452894778, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.025228435890749096, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.02573717342223972, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.026158401884604245, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.026651647640392184, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.02703996697673574, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.027335320403799414, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.027729836725629866, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.02788657622411847, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.027687817710684612, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.027611094620078803, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.027110218388261272, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.026205656655365603, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.024119523482513613, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.02033458474004874, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.009799413954024203, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0035084620301131506, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0010576001432309567, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0005771198103775532, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.00037273203904987897, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.00023516070753430541, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.00015978274510871415, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.00011478159475700523, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0001196735803358706, "train/grad_033_lr4.3e+00_wd1.0e+00": 7.504248038003424e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 5.102784756957135e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 4.632073363836753e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 4.015343193572107e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 2.6373706875668645e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 2.5349321560335092e-05, "train/grad_039_lr1.2e+01_wd1.0e+00": 5.939581628865653e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0001237446539579423, "train/grad_041_lr1.6e+01_wd1.0e+00": 7.060534946624841e-05, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.40211907029151917, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.38883721828460693, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.3722418546676636, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.3607369065284729, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.3524114787578583, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.34389206767082214, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.3374350070953369, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.33255767822265625, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.32913777232170105, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.32806912064552307, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.3291294574737549, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.3340754806995392, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.3430597186088562, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.36441487073898315, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.37960052490234375, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.37981554865837097, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.3690940737724304, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.35411161184310913, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.3404463827610016, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.33024343848228455, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.32000237703323364, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.31715595722198486, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.3616044223308563, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.411851167678833, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.49383315443992615, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.5332980751991272, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.5911754369735718, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.6015928983688354, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.6330514550209045, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.6695746183395386, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.6290345788002014, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.6844196915626526, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.6502417325973511, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.8097102046012878, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.8075090646743774, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.913560688495636, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.8796550035476685, "validation/loss_037_lr8.3e+00_wd1.0e+00": 1.0728881359100342, "validation/loss_038_lr9.8e+00_wd1.0e+00": 1.5666049718856812, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.9626142382621765, "validation/loss_040_lr1.4e+01_wd1.0e+00": 1.1474121809005737, "validation/loss_041_lr1.6e+01_wd1.0e+00": 1.797820806503296, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.6931472420692444, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.896551724137931, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.896551724137931, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.896551724137931, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.896551724137931, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9137931034482759, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.9137931034482759, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9137931034482759, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.9137931034482759, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.8793103448275862, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.8793103448275862, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.8620689655172413, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.8275862068965517, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.8275862068965517, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.8620689655172413, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.8620689655172413, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.896551724137931, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9137931034482759, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9310344827586207, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9482758620689655, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.896551724137931, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.8793103448275862, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9137931034482759, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.896551724137931, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.8793103448275862, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.6206896551724138, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.6206896551724138, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.6206896551724138, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.6206896551724138, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.6206896551724138, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.6206896551724138, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.6206896551724138, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.8901515151515151, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.8901515151515151, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.8901515151515151, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.8901515151515151, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.9076138897738133, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.9076138897738133, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.9076138897738133, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9076138897738133, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.8706594456833386, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.8706594456833386, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.8535353535353536, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.8223039215686274, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.8223039215686274, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.8559006211180125, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.8729264475743349, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.8507078507078507, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.888030888030888, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9076138897738133, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9092331768388107, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9267676767676767, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.944568333864288, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.8901515151515151, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9092331768388107, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.8729264475743349, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9076138897738133, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.8901515151515151, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.8706594456833386, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.3829787234042553, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.3829787234042553, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.3829787234042553, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.3829787234042553, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.3829787234042553, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.3829787234042553, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.3829787234042553, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.8901515151515151, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.8901515151515151, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.8901515151515151, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.8901515151515151, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.904040404040404, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.904040404040404, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.904040404040404, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.904040404040404, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.8674242424242424, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.8674242424242424, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.8535353535353536, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.8345959595959596, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.8345959595959596, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.8623737373737375, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.8762626262626263, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.8446969696969697, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.8813131313131313, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.904040404040404, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.9128787878787878, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.9267676767676767, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.9406565656565656, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.8901515151515151, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.9128787878787878, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.8762626262626263, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.904040404040404, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.8901515151515151, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.8674242424242424, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.5, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.5, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.5, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.5, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.5, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.5, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.5, "id_best": 32, "lr_best": 0.0011099999999999999, "wd_best": 0.05, "train/loss_best": 0.00034063205122947693, "validation/loss_best": 0.6502417325973511, "validation/acc_best": 0.9482758620689655, "validation/f1_best": 0.944568333864288, "validation/bacc_best": 0.9406565656565656} +{"epoch": 9, "train/lr": 0.00023803200426111704, "train/loss": 0.21838854677975178, "train/grad": 0.13840728618204592, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.39342369079589845, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.37932945251464845, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.3613505554199219, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.34774667739868165, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.336915225982666, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.3246730613708496, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.31342479705810544, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.3027864408493042, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.2910058832168579, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.2804898452758789, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.2714476203918457, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.2597325563430786, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.2496825313568115, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.23518959522247315, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.22121611833572388, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.20917937517166138, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.19584846436977388, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.18234201669692993, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.17047648906707763, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.1597764965891838, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.14131864324212073, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.11480092138051987, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.07461422994732857, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.027291249930858612, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.009050329774618148, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.0030471283197402955, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.0014355823397636414, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0008484195172786713, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0005798386037349701, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.00040203168988227843, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.00029253244400024415, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.0002036188542842865, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.00023469164967536925, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.00014891117811203003, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.00010802105069160462, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.00010445192456245422, "train/loss_036_lr7.1e+00_wd1.0e+00": 9.048685431480408e-05, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.623098134994507e-05, "train/loss_038_lr9.8e+00_wd1.0e+00": 5.182325839996338e-05, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.0001521739363670349, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.0001927180588245392, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.00015436336398124694, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.69140625, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.69140625, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.69140625, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.69140625, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.69140625, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.69140625, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.69140625, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.025561123597435655, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.02523068114882335, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.02486781862564385, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.02466549343196675, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.024559794894885273, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.02448917839443311, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.024469629237428306, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.02450143331894651, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.02461877398425713, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.024806056013330816, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.025084979608654977, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.02570616302313283, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.026555765080265702, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.027890309616923334, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.02885377735365182, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.029537734214682133, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.030146838291548194, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.030385513838846235, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.030572810331359505, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.031008365454617888, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.031041606237413363, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.02925244333455339, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.022918790092226117, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.011394241975503974, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.004913612130694673, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0013918270015346934, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0006378158150073432, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0003834300118978717, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.00026269485010743665, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.00017901790361975146, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.00012510154161191167, "train/grad_031_lr3.1e+00_wd1.0e+00": 9.607242583570041e-05, "train/grad_032_lr3.7e+00_wd1.0e+00": 9.300599892867468e-05, "train/grad_033_lr4.3e+00_wd1.0e+00": 6.058525535308945e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 4.391621937315904e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 3.988608562281115e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 3.872773261306861e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 2.7119193382389995e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 3.9755222370887466e-05, "train/grad_039_lr1.2e+01_wd1.0e+00": 5.7424911216230615e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.00011797014978810694, "train/grad_041_lr1.6e+01_wd1.0e+00": 8.205641572139655e-05, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.39059993624687195, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.37822622060775757, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.3633102774620056, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.3530985713005066, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.34546685218811035, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.33833104372024536, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.3332400619983673, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.32997384667396545, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.3286017179489136, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.3293203115463257, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.3314788341522217, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.336344838142395, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.3410676419734955, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.344508558511734, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.34734004735946655, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.3526482880115509, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.356781929731369, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.35453420877456665, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.34847962856292725, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.3414764106273651, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.334087610244751, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.3714445233345032, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.4222124218940735, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.5051432847976685, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.5813084840774536, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.5894733667373657, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.6294636130332947, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.6310144066810608, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.6599161028862, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.6895610690116882, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.6444875597953796, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.6941319704055786, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.6630542874336243, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.8264858722686768, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.8026168942451477, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.9110603928565979, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.8738213777542114, "validation/loss_037_lr8.3e+00_wd1.0e+00": 1.0316275358200073, "validation/loss_038_lr9.8e+00_wd1.0e+00": 1.4780501127243042, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.9611432552337646, "validation/loss_040_lr1.4e+01_wd1.0e+00": 1.1205230951309204, "validation/loss_041_lr1.6e+01_wd1.0e+00": 1.7245725393295288, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.6931472420692444, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.896551724137931, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.896551724137931, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.896551724137931, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.9137931034482759, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9137931034482759, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.9137931034482759, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9137931034482759, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.8793103448275862, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.8793103448275862, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.8793103448275862, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.8448275862068966, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.8448275862068966, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.8448275862068966, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.8620689655172413, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.8448275862068966, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.8448275862068966, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.8448275862068966, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.896551724137931, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.896551724137931, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.896551724137931, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.896551724137931, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.896551724137931, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9482758620689655, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.896551724137931, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.8793103448275862, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9137931034482759, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.896551724137931, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.8793103448275862, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.6206896551724138, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.6206896551724138, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.6206896551724138, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.6206896551724138, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.6206896551724138, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.6206896551724138, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.6206896551724138, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.8901515151515151, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.8901515151515151, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.8901515151515151, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.9076138897738133, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.9076138897738133, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.9076138897738133, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.9076138897738133, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.8706594456833386, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.8706594456833386, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.8706594456833386, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.8302439024390245, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.8302439024390245, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.8302439024390245, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.8507078507078507, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.8302439024390245, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.8302439024390245, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.8302439024390245, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.888030888030888, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.888030888030888, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.888030888030888, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.888030888030888, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.8901515151515151, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9092331768388107, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.944568333864288, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.8901515151515151, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9092331768388107, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.8729264475743349, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9076138897738133, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.8901515151515151, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.8706594456833386, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.3829787234042553, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.3829787234042553, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.3829787234042553, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.3829787234042553, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.3829787234042553, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.3829787234042553, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.3829787234042553, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.8901515151515151, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.8901515151515151, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.8901515151515151, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.904040404040404, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.904040404040404, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.904040404040404, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.904040404040404, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.8674242424242424, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.8674242424242424, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.8674242424242424, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.821969696969697, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.821969696969697, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.821969696969697, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.8446969696969697, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.821969696969697, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.821969696969697, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.821969696969697, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.8813131313131313, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.8813131313131313, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.8813131313131313, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.8813131313131313, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.8901515151515151, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.9128787878787878, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.9406565656565656, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.8901515151515151, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.9128787878787878, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.8762626262626263, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.904040404040404, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.8901515151515151, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.8674242424242424, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.5, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.5, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.5, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.5, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.5, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.5, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.5, "id_best": 32, "lr_best": 0.0011099999999999999, "wd_best": 0.05, "train/loss_best": 0.00023469164967536925, "validation/loss_best": 0.6630542874336243, "validation/acc_best": 0.9482758620689655, "validation/f1_best": 0.944568333864288, "validation/bacc_best": 0.9406565656565656} +{"epoch": 10, "train/lr": 0.00021091808096876188, "train/loss": 0.22322017021477222, "train/grad": 0.13500110542401672, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.40381134033203125, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.3915399169921875, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.37591894149780275, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.3637628746032715, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.3537948703765869, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.34221753120422366, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.33097991943359373, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.320144681930542, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.3079235506057739, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.2966276025772095, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.28674092769622805, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.27314451694488523, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.26150883674621583, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.24667770862579347, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.23488733172416687, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.22478796780109406, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.21258849561214446, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.19914325684309006, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.18607906013727188, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.17335261300206184, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.1465998685359955, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.10010187640786171, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.0427301087975502, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.012054603546857834, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.004432796388864517, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.002036478966474533, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.0010936325788497925, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0006998187303543091, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0004877312481403351, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0003394298255443573, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.00026082023978233335, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.00020159423351287842, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.00019038349390029907, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.0001459537446498871, "train/loss_034_lr5.1e+00_wd1.0e+00": 9.893417358398437e-05, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.0001064649224281311, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.00010152220726013184, "train/loss_037_lr8.3e+00_wd1.0e+00": 6.072774529457092e-05, "train/loss_038_lr9.8e+00_wd1.0e+00": 9.218931198120118e-05, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.0001320740580558777, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.00019791960716247558, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.000147932767868042, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.69140625, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.69140625, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.69140625, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.69140625, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.69140625, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.69140625, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.69140625, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.023578935319092123, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.023489953211974352, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.023518966601695866, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.02363730421056971, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.023807314964942636, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.024044481734745205, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.024293061119969935, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.02454199061729014, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.024839487604331224, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.02514855795307085, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.025488881412893533, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.026076742368750273, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.026746603038627654, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.027772954481188206, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.028677742588333787, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.029430448145139964, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.030450370183680207, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.03175969770178199, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.03264491035952233, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.032817179001285696, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.029765900427591988, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.02233085021667648, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.01375338084937539, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.005145321938398411, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0018220299951644846, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0007980030137332506, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0004321119938595075, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0002681988306358107, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.00019874497011187486, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0001385176060671256, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.00010204130153624646, "train/grad_031_lr3.1e+00_wd1.0e+00": 8.258576156208619e-05, "train/grad_032_lr3.7e+00_wd1.0e+00": 7.687801455404042e-05, "train/grad_033_lr4.3e+00_wd1.0e+00": 5.34530457252913e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 3.9793161385546227e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 3.5531385217097976e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 3.662107099216882e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 3.283045209402147e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 4.2840095233119266e-05, "train/grad_039_lr1.2e+01_wd1.0e+00": 5.080682410891768e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.00011238945600382522, "train/grad_041_lr1.6e+01_wd1.0e+00": 7.944674062002832e-05, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.382426917552948, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.37107235193252563, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.357254296541214, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.3476364016532898, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.34066319465637207, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.33419519662857056, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.32957324385643005, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.3273437023162842, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.3272857964038849, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.3295881152153015, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.3334178328514099, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.34037113189697266, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.34819597005844116, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.3581118881702423, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.36236223578453064, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.36040040850639343, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.35307052731513977, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.3444004952907562, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.3392013907432556, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.3305981755256653, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.34345585107803345, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.4172115921974182, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.4931527376174927, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.5940534472465515, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.6425169706344604, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.629514217376709, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.6570656895637512, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.6524084806442261, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.6790209412574768, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.708471417427063, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.6571961045265198, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.7040483951568604, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.673750102519989, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.8434714078903198, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.7980465292930603, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.9123819470405579, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.8703282475471497, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.9996899962425232, "validation/loss_038_lr9.8e+00_wd1.0e+00": 1.4113081693649292, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.9673563241958618, "validation/loss_040_lr1.4e+01_wd1.0e+00": 1.1042072772979736, "validation/loss_041_lr1.6e+01_wd1.0e+00": 1.68606698513031, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.6931472420692444, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.896551724137931, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.896551724137931, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.9137931034482759, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.9137931034482759, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9137931034482759, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.9137931034482759, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.896551724137931, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.896551724137931, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.8793103448275862, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.8793103448275862, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.8448275862068966, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.8448275862068966, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.8448275862068966, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.8448275862068966, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.8448275862068966, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.8620689655172413, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.8620689655172413, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.8620689655172413, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.8620689655172413, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.896551724137931, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.896551724137931, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.896551724137931, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.896551724137931, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.896551724137931, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.896551724137931, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9482758620689655, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.896551724137931, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.8793103448275862, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9137931034482759, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.896551724137931, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.8793103448275862, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.6206896551724138, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.6206896551724138, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.6206896551724138, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.6206896551724138, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.6206896551724138, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.6206896551724138, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.6206896551724138, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.8901515151515151, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.8901515151515151, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.9076138897738133, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.9076138897738133, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.9076138897738133, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.9076138897738133, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.888030888030888, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.888030888030888, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.8706594456833386, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.8706594456833386, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.8302439024390245, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.8302439024390245, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.8302439024390245, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.8302439024390245, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.8302439024390245, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.8507078507078507, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.8535353535353536, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.8535353535353536, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.8535353535353536, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.888030888030888, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.888030888030888, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.888030888030888, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.888030888030888, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.8901515151515151, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.8901515151515151, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.944568333864288, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.8901515151515151, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9092331768388107, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.8729264475743349, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9076138897738133, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.8901515151515151, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.8706594456833386, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.3829787234042553, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.3829787234042553, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.3829787234042553, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.3829787234042553, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.3829787234042553, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.3829787234042553, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.3829787234042553, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.8901515151515151, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.8901515151515151, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.904040404040404, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.904040404040404, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.904040404040404, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.904040404040404, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.8813131313131313, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.8813131313131313, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.8674242424242424, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.8674242424242424, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.821969696969697, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.821969696969697, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.821969696969697, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.821969696969697, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.821969696969697, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.8446969696969697, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.8535353535353536, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.8535353535353536, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.8535353535353536, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.8813131313131313, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.8813131313131313, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.8813131313131313, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.8813131313131313, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.8901515151515151, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.8901515151515151, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.9406565656565656, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.8901515151515151, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.9128787878787878, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.8762626262626263, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.904040404040404, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.8901515151515151, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.8674242424242424, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.5, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.5, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.5, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.5, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.5, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.5, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.5, "id_best": 32, "lr_best": 0.0011099999999999999, "wd_best": 0.05, "train/loss_best": 0.00019038349390029907, "validation/loss_best": 0.673750102519989, "validation/acc_best": 0.9482758620689655, "validation/f1_best": 0.944568333864288, "validation/bacc_best": 0.9406565656565656} +{"epoch": 11, "train/lr": 0.00018113997589164516, "train/loss": 0.21084116965532304, "train/grad": 0.12940393963828684, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.37842277526855467, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.366556396484375, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.3513371658325195, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.33949716567993166, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.3296349334716797, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.31788536071777346, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.30655001640319823, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.2955921506881714, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.28319751262664794, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.2717188024520874, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.2619324159622192, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.2488419532775879, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.23747118949890136, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.22298212647438048, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.21053008258342742, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.19989914774894715, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.18781446009874345, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.17475433513522148, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.15957449331879617, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.14282759726047517, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.11018183574080467, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.06349361300468445, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.018130123168230056, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.005474246144294739, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.0024361521005630492, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.0013078990578651428, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.0007436096668243409, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0005126745998859406, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0003612956404685974, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0002658013999462128, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0002087266743183136, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.00016339436173439025, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.00014628350734710693, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.00011330395936965942, "train/loss_034_lr5.1e+00_wd1.0e+00": 8.087903261184692e-05, "train/loss_035_lr6.0e+00_wd1.0e+00": 8.609279990196228e-05, "train/loss_036_lr7.1e+00_wd1.0e+00": 8.652463555335998e-05, "train/loss_037_lr8.3e+00_wd1.0e+00": 5.8528184890747074e-05, "train/loss_038_lr9.8e+00_wd1.0e+00": 7.832825183868409e-05, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.00012650370597839356, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.00017843738198280334, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.00011943578720092773, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.69140625, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.69140625, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.69140625, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.69140625, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.69140625, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.69140625, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.69140625, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.02417866302654147, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.0239388065924868, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.02370075710583478, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.02357193481642753, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.02348851622082293, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.023431787190493197, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.023422319842502475, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.023462143950164317, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.023591981902718544, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.02383063062792644, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.024206089298240842, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.024937650361098348, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.02577937294030562, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.02694358641281724, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.02790178233990446, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.028676983067998662, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.029452167961280792, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.030111207572044805, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.03062668423750438, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.03091237655375153, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.02993282532203011, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.021667740311240778, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.008318066217325394, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0023896473080458236, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.001061351000216746, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0005734532575934282, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.00032896383242587035, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.00021579869772722304, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.00015699379461921127, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0001148141961721194, "train/grad_030_lr2.7e+00_wd1.0e+00": 8.597624649837598e-05, "train/grad_031_lr3.1e+00_wd1.0e+00": 7.239630610968106e-05, "train/grad_032_lr3.7e+00_wd1.0e+00": 6.757018907364909e-05, "train/grad_033_lr4.3e+00_wd1.0e+00": 4.639060125896321e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 3.7902249572709935e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 3.333744204269351e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 3.5215911669013164e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 3.536762462936771e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 4.997686449090821e-05, "train/grad_039_lr1.2e+01_wd1.0e+00": 4.729491096867378e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 9.962633983604973e-05, "train/grad_041_lr1.6e+01_wd1.0e+00": 7.279663531847724e-05, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.3756687343120575, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.36508476734161377, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.35246431827545166, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.3436145782470703, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.337812215089798, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.33213937282562256, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.3285891115665436, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.3272879123687744, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.32806989550590515, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.33117178082466125, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.3352501392364502, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.34154942631721497, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.3456968069076538, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.3473033905029297, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.3467600643634796, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.3451847732067108, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.3421562910079956, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.3370494842529297, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.3305971622467041, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.3288872241973877, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.3846346437931061, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.43760210275650024, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.5412105917930603, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.6316587328910828, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.6676313877105713, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.6478937268257141, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.6710211038589478, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.6672858595848083, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.6890890002250671, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.7198761701583862, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.6667170524597168, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.7103435397148132, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.6800166964530945, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.8503171801567078, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.7955048680305481, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.9119970202445984, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.869829535484314, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.9781361222267151, "validation/loss_038_lr9.8e+00_wd1.0e+00": 1.3633027076721191, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.9691829681396484, "validation/loss_040_lr1.4e+01_wd1.0e+00": 1.0947840213775635, "validation/loss_041_lr1.6e+01_wd1.0e+00": 1.6500357389450073, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.6931472420692444, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.896551724137931, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.896551724137931, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.9137931034482759, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.9137931034482759, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9137931034482759, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.9137931034482759, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.896551724137931, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.8793103448275862, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.8793103448275862, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.8793103448275862, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.8620689655172413, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.8620689655172413, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.896551724137931, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.896551724137931, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.896551724137931, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.896551724137931, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.896551724137931, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9482758620689655, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.896551724137931, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.8793103448275862, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9137931034482759, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.896551724137931, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.8793103448275862, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.6206896551724138, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.6206896551724138, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.6206896551724138, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.6206896551724138, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.6206896551724138, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.6206896551724138, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.6206896551724138, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.8901515151515151, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.8901515151515151, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.9076138897738133, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.9076138897738133, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.9076138897738133, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.9076138897738133, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.888030888030888, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.8706594456833386, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.8706594456833386, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.8706594456833386, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.8535353535353536, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.8729264475743349, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.8729264475743349, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.8729264475743349, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.8729264475743349, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.857843137254902, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.8729264475743349, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.888030888030888, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.888030888030888, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.888030888030888, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.8901515151515151, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.8901515151515151, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.944568333864288, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.8901515151515151, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9092331768388107, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.8729264475743349, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9076138897738133, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.8901515151515151, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.8706594456833386, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.3829787234042553, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.3829787234042553, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.3829787234042553, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.3829787234042553, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.3829787234042553, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.3829787234042553, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.3829787234042553, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.8901515151515151, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.8901515151515151, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.904040404040404, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.904040404040404, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.904040404040404, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.904040404040404, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.8813131313131313, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.8674242424242424, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.8674242424242424, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.8674242424242424, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.8535353535353536, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.8762626262626263, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.8762626262626263, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.8762626262626263, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.8762626262626263, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.8712121212121212, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.8762626262626263, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.8813131313131313, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.8813131313131313, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.8813131313131313, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.8901515151515151, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.8901515151515151, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.9406565656565656, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.8901515151515151, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.9128787878787878, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.8762626262626263, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.904040404040404, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.8901515151515151, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.8674242424242424, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.5, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.5, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.5, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.5, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.5, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.5, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.5, "id_best": 32, "lr_best": 0.0011099999999999999, "wd_best": 0.05, "train/loss_best": 0.00014628350734710693, "validation/loss_best": 0.6800166964530945, "validation/acc_best": 0.9482758620689655, "validation/f1_best": 0.944568333864288, "validation/bacc_best": 0.9406565656565656} +{"epoch": 12, "train/lr": 0.0001499999999999999, "train/loss": 0.2061881384253502, "train/grad": 0.12355227836407721, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.3720256805419922, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.36017072677612305, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.34497671127319335, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.33320695877075196, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.32325258255004885, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.3115365791320801, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.30019207000732423, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.28915092945098875, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.2767589902877808, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.26494174003601073, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.25451790809631347, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.24041046619415282, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.22802356719970704, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.21288698434829711, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.2008908772468567, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.19093814849853516, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.17939065247774125, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.16523840606212617, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.14756920352578162, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.12597896546125412, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.08513753280043602, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.03727656200528145, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.009594981521368028, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.0035933615267276764, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.0017899926006793975, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.0009865722060203553, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.0006182944774627686, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.00043591290712356566, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0003116565942764282, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0002386721968650818, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.00018129989504814148, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.00013977393507957458, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.0001551765203475952, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.00010197743773460388, "train/loss_034_lr5.1e+00_wd1.0e+00": 7.398903369903564e-05, "train/loss_035_lr6.0e+00_wd1.0e+00": 7.386744022369385e-05, "train/loss_036_lr7.1e+00_wd1.0e+00": 7.803827524185181e-05, "train/loss_037_lr8.3e+00_wd1.0e+00": 7.496967911720276e-05, "train/loss_038_lr9.8e+00_wd1.0e+00": 8.474066853523255e-05, "train/loss_039_lr1.2e+01_wd1.0e+00": 9.847030043601989e-05, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.00014299437403678895, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.0001281796395778656, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.69140625, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.69140625, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.69140625, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.69140625, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.69140625, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.69140625, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.69140625, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.023113525465596467, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.022941480556037275, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.022811975292861462, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.0227872548205778, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.02281808717409149, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.02291042193071917, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.023077426578383894, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.023305061217397453, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.023646093395072967, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.024051090262364596, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.024497585236094892, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.025237684340681882, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.025948907060083, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.026841086433269084, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.027588479109108447, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.028205156394978986, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.028891838713316246, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.029367493371246382, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.029203923534369097, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.02790663615625817, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.023175911644357255, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.014596465713402722, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.004634316278388724, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.001727412559412187, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0008233942253536952, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0004532391630073107, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0002664920809706928, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.00017274398534482315, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.00013129087141351193, "train/grad_029_lr2.3e+00_wd1.0e+00": 9.877961801748824e-05, "train/grad_030_lr2.7e+00_wd1.0e+00": 7.681185001331414e-05, "train/grad_031_lr3.1e+00_wd1.0e+00": 6.035198498125283e-05, "train/grad_032_lr3.7e+00_wd1.0e+00": 6.283804122347191e-05, "train/grad_033_lr4.3e+00_wd1.0e+00": 4.07018285562799e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 3.4138715170826115e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 3.130377566350262e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 3.2822986850504775e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 3.353886860672617e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 4.795232683335371e-05, "train/grad_039_lr1.2e+01_wd1.0e+00": 4.562098523081204e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 9.374663663464843e-05, "train/grad_041_lr1.6e+01_wd1.0e+00": 6.828579169013694e-05, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.37245604395866394, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.36267873644828796, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.3510352373123169, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.3433709442615509, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.3379511535167694, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.33316248655319214, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.33064767718315125, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.33016231656074524, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.3323368430137634, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.33682408928871155, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.34206098318099976, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.34921038150787354, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.35232245922088623, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.3499242961406708, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.3450518846511841, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.34028109908103943, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.3345542252063751, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.3275093138217926, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.31750184297561646, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.3149372935295105, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.39588215947151184, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.4837134778499603, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.5948522090911865, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.6637808084487915, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.6846814751625061, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.6623566746711731, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.6817033886909485, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.6743534803390503, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.6956128478050232, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.724983811378479, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.669854998588562, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.7123942971229553, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.6851580142974854, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.8574458360671997, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.7953704595565796, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.9137380123138428, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.8691127300262451, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.9613122344017029, "validation/loss_038_lr9.8e+00_wd1.0e+00": 1.3289029598236084, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.9702006578445435, "validation/loss_040_lr1.4e+01_wd1.0e+00": 1.0888104438781738, "validation/loss_041_lr1.6e+01_wd1.0e+00": 1.6238529682159424, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.6931472420692444, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.896551724137931, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.896551724137931, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.9137931034482759, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.9137931034482759, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9137931034482759, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.896551724137931, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.8793103448275862, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.8793103448275862, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.8793103448275862, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.8793103448275862, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.8620689655172413, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.8620689655172413, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.896551724137931, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.896551724137931, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.896551724137931, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.8793103448275862, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.896551724137931, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9310344827586207, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.896551724137931, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.8793103448275862, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.896551724137931, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9137931034482759, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.896551724137931, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.8793103448275862, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.6206896551724138, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.6206896551724138, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.6206896551724138, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.6206896551724138, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.6206896551724138, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.6206896551724138, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.6206896551724138, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.8901515151515151, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.8901515151515151, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.9076138897738133, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.9076138897738133, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.9076138897738133, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.8901515151515151, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.8706594456833386, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.8706594456833386, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.8706594456833386, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.8706594456833386, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.8507078507078507, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.8507078507078507, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.8679674796747967, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.888030888030888, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.888030888030888, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.888030888030888, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.8706594456833386, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.8901515151515151, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9092331768388107, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9267676767676767, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.8901515151515151, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9092331768388107, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.8729264475743349, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.8901515151515151, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9076138897738133, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.8901515151515151, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.8706594456833386, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.3829787234042553, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.3829787234042553, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.3829787234042553, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.3829787234042553, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.3829787234042553, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.3829787234042553, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.3829787234042553, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.8901515151515151, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.8901515151515151, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.904040404040404, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.904040404040404, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.904040404040404, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.8901515151515151, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.8674242424242424, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.8674242424242424, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.8674242424242424, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.8674242424242424, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.8446969696969697, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.8446969696969697, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.8585858585858586, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.8813131313131313, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.8813131313131313, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.8813131313131313, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.8674242424242424, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.8901515151515151, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.9128787878787878, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.9267676767676767, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.8901515151515151, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.9128787878787878, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.8762626262626263, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.8901515151515151, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.904040404040404, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.8901515151515151, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.8674242424242424, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.5, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.5, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.5, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.5, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.5, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.5, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.5, "id_best": 32, "lr_best": 0.0011099999999999999, "wd_best": 0.05, "train/loss_best": 0.0001551765203475952, "validation/loss_best": 0.6851580142974854, "validation/acc_best": 0.9310344827586207, "validation/f1_best": 0.9267676767676767, "validation/bacc_best": 0.9267676767676767} +{"epoch": 13, "train/lr": 0.00011886002410835478, "train/loss": 0.20299565330147742, "train/grad": 0.11881110845133662, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.36127922058105466, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.349695987701416, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.3347733211517334, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.32345224380493165, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.31402178764343264, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.3030999517440796, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.2930170106887817, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.28338624477386476, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.2728777265548706, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.2631459999084473, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.25450165748596193, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.2427113914489746, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.2322402286529541, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.21792456686496733, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.2049143308401108, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.1923511853814125, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.17617454811930655, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.1560365742444992, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.13208458721637725, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.10299320444464684, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.05915871679782867, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.022372392863035204, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.006817773729562759, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.0028420476615428924, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.0015175828337669372, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.0008694742619991303, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.0005340921878814697, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0003771066665649414, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0002661900222301483, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.00021749511361122132, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0001654648780822754, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.00012462258338928224, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.0001294073462486267, "train/loss_033_lr4.3e+00_wd1.0e+00": 9.510591626167297e-05, "train/loss_034_lr5.1e+00_wd1.0e+00": 6.789550185203553e-05, "train/loss_035_lr6.0e+00_wd1.0e+00": 7.540524005889892e-05, "train/loss_036_lr7.1e+00_wd1.0e+00": 7.79484212398529e-05, "train/loss_037_lr8.3e+00_wd1.0e+00": 6.590113043785095e-05, "train/loss_038_lr9.8e+00_wd1.0e+00": 9.188622236251831e-05, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.00010097131133079528, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.00016867607831954956, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.00012556374073028565, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.69140625, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.69140625, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.69140625, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.69140625, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.69140625, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.69140625, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.69140625, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.023902366247493773, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.023651429996825755, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.02336022012401372, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.023174532800912858, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.023053685852792116, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.02296335651539266, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.022948588642757384, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.023017250553239138, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.02321781691396609, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.023539771579671652, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.02394323986256495, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.02462977472692728, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.025270856628194453, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.026039371374063192, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.026646996650379152, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.027120003290474416, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.02754491915460676, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.027681927639059724, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.02696329523343593, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.02454984951065853, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.018892888452974148, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.009537761634564958, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.003057503386444296, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.00125930343507207, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0006599880842804851, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.00038191254478078915, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.00023999078807719344, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.00015592027202842473, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.00011922120176905082, "train/grad_029_lr2.3e+00_wd1.0e+00": 9.035402574568252e-05, "train/grad_030_lr2.7e+00_wd1.0e+00": 6.891646959957143e-05, "train/grad_031_lr3.1e+00_wd1.0e+00": 5.5978764447672805e-05, "train/grad_032_lr3.7e+00_wd1.0e+00": 5.2891836547246384e-05, "train/grad_033_lr4.3e+00_wd1.0e+00": 3.865764146098627e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 3.2190122870758844e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 2.8157488939939414e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 3.046291608654883e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 3.473895352328782e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 4.5830884781032924e-05, "train/grad_039_lr1.2e+01_wd1.0e+00": 3.985174986723905e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 7.87878391640362e-05, "train/grad_041_lr1.6e+01_wd1.0e+00": 6.449198294674829e-05, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.36755692958831787, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.35800570249557495, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.3469901382923126, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.3394933044910431, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.33452308177948, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.33026123046875, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.32838886976242065, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.3284147381782532, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.3308255672454834, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.3353077471256256, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.3405812084674835, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.3464515805244446, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.3486931622028351, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.346749484539032, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.3435574173927307, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.33940693736076355, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.33301326632499695, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.32476064562797546, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.31498581171035767, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.3202756345272064, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.40415820479393005, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.4928670823574066, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.6139652729034424, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.6876657605171204, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.7058091163635254, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.6768278479576111, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.6919695734977722, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.6833659410476685, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.7033354043960571, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.7335731387138367, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.6767941117286682, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.7175082564353943, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.6912945508956909, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.864399790763855, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.7951719164848328, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.9138317704200745, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.871504008769989, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.9502774477005005, "validation/loss_038_lr9.8e+00_wd1.0e+00": 1.304351568222046, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.9772066473960876, "validation/loss_040_lr1.4e+01_wd1.0e+00": 1.083924412727356, "validation/loss_041_lr1.6e+01_wd1.0e+00": 1.606115460395813, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.6931472420692444, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.896551724137931, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.9137931034482759, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.9137931034482759, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.9137931034482759, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9137931034482759, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.896551724137931, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.8793103448275862, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.8793103448275862, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.8793103448275862, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.8793103448275862, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.8620689655172413, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.8620689655172413, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.896551724137931, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.896551724137931, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.896551724137931, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.896551724137931, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.8793103448275862, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.896551724137931, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.896551724137931, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9482758620689655, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.896551724137931, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.8793103448275862, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.896551724137931, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9137931034482759, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.896551724137931, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.8793103448275862, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.6206896551724138, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.6206896551724138, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.6206896551724138, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.6206896551724138, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.6206896551724138, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.6206896551724138, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.6206896551724138, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.8901515151515151, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.9076138897738133, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.9076138897738133, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.9076138897738133, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.9076138897738133, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.888030888030888, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.8706594456833386, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.8706594456833386, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.8706594456833386, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.8706594456833386, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.8535353535353536, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.8535353535353536, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.888030888030888, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.888030888030888, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.888030888030888, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.888030888030888, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.8706594456833386, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.8901515151515151, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.8901515151515151, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.944568333864288, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.8901515151515151, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9092331768388107, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.8729264475743349, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.8901515151515151, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9076138897738133, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.8901515151515151, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.8706594456833386, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.3829787234042553, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.3829787234042553, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.3829787234042553, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.3829787234042553, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.3829787234042553, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.3829787234042553, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.3829787234042553, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.8901515151515151, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.904040404040404, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.904040404040404, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.904040404040404, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.904040404040404, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.8813131313131313, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.8674242424242424, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.8674242424242424, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.8674242424242424, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.8674242424242424, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.8535353535353536, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.8535353535353536, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.8813131313131313, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.8813131313131313, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.8813131313131313, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.8813131313131313, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.8674242424242424, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.8901515151515151, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.8901515151515151, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.9406565656565656, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.8901515151515151, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.9128787878787878, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.8762626262626263, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.8901515151515151, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.904040404040404, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.8901515151515151, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.8674242424242424, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.5, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.5, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.5, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.5, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.5, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.5, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.5, "id_best": 32, "lr_best": 0.0011099999999999999, "wd_best": 0.05, "train/loss_best": 0.0001294073462486267, "validation/loss_best": 0.6912945508956909, "validation/acc_best": 0.9482758620689655, "validation/f1_best": 0.944568333864288, "validation/bacc_best": 0.9406565656565656} +{"epoch": 14, "train/lr": 8.9081919031238e-05, "train/loss": 0.2030581361055374, "train/grad": 0.11530141768045724, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.36095001220703127, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.34982831954956056, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.33516286849975585, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.32357688903808596, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.3138156604766846, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.3022194051742554, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.2913873386383057, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.28096201419830324, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.269642596244812, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.2593927574157715, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.2505293130874634, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.23887211799621583, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.2288532090187073, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.21554147481918334, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.20366547584533692, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.1928584110736847, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.17933278366923333, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.1626951178908348, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.1408946293592453, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.1122928075492382, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.06643473580479622, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.018897182196378707, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.005545931458473205, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.0023603379726409913, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.0012633050978183747, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.0007055912911891937, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.00042444393038749696, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.00029760703444480896, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.00021584272384643553, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.00017573162913322448, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.00014165788888931274, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.00010718852281570435, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.0001300041377544403, "train/loss_033_lr4.3e+00_wd1.0e+00": 7.58834183216095e-05, "train/loss_034_lr5.1e+00_wd1.0e+00": 7.838711142539978e-05, "train/loss_035_lr6.0e+00_wd1.0e+00": 7.448270916938781e-05, "train/loss_036_lr7.1e+00_wd1.0e+00": 7.055625319480896e-05, "train/loss_037_lr8.3e+00_wd1.0e+00": 6.532490253448486e-05, "train/loss_038_lr9.8e+00_wd1.0e+00": 8.273422718048095e-05, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.00010835036635398865, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.00015807971358299254, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.00011862531304359437, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.69140625, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.69140625, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.69140625, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.69140625, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.69140625, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.69140625, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.69140625, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.022736811339855195, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.022542153948452322, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.022370744433719666, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.022286135584581642, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.02224988048430532, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.022248287037946284, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.022308952913153917, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.02242651197593659, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.02265723195625469, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.02297463810769841, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.023374255927046762, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.024057459337636828, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.024710506080882624, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.025499478306155652, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.026131084356456995, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.02659284169320017, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.026994688875274734, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.027138931745430455, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.026418098122812806, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.024025441856356338, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.01783878764428664, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.00778396463021636, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.002445370627538068, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0010083067543200741, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0005414160836198789, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0003151691501125242, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.00019498045549653397, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.00012831111784862516, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.00010045433493132804, "train/grad_029_lr2.3e+00_wd1.0e+00": 7.727721049150205e-05, "train/grad_030_lr2.7e+00_wd1.0e+00": 5.96573435677783e-05, "train/grad_031_lr3.1e+00_wd1.0e+00": 4.923423573757191e-05, "train/grad_032_lr3.7e+00_wd1.0e+00": 5.072767876512785e-05, "train/grad_033_lr4.3e+00_wd1.0e+00": 3.3194059209336043e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 3.05944994866536e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 2.641155225944658e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 2.8790946263370643e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 3.453715807612667e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 4.435998715402789e-05, "train/grad_039_lr1.2e+01_wd1.0e+00": 3.746046582079998e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 7.574014436443122e-05, "train/grad_041_lr1.6e+01_wd1.0e+00": 6.0948698708207516e-05, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.3657352328300476, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.35658764839172363, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.34613266587257385, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.33919557929039, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.33452343940734863, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.3309258222579956, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.32942384481430054, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.32979294657707214, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.3328157067298889, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.3373870253562927, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.3423789143562317, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.34742164611816406, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.3482058346271515, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.3458954989910126, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.3433816432952881, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.34076911211013794, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.3377310633659363, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.3330461382865906, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.32773810625076294, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.3418218493461609, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.43166014552116394, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.5250993371009827, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.6398887634277344, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.7093585729598999, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.721057116985321, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.6887791752815247, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.7006331086158752, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.689963161945343, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.7112120389938354, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.7386877536773682, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.6813027858734131, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.7213259935379028, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.6943714022636414, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.8723646402359009, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.7944772243499756, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.9177268743515015, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.8748806118965149, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.9423286318778992, "validation/loss_038_lr9.8e+00_wd1.0e+00": 1.2888729572296143, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.9806613326072693, "validation/loss_040_lr1.4e+01_wd1.0e+00": 1.0818349123001099, "validation/loss_041_lr1.6e+01_wd1.0e+00": 1.5980314016342163, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.6931472420692444, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.896551724137931, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.896551724137931, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.9137931034482759, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.9137931034482759, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9137931034482759, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.896551724137931, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.8793103448275862, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.8793103448275862, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.8793103448275862, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.8793103448275862, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.8620689655172413, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.8620689655172413, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.896551724137931, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.896551724137931, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.896551724137931, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.8793103448275862, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.896551724137931, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.896551724137931, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9310344827586207, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.896551724137931, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.8793103448275862, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.896551724137931, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9137931034482759, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.896551724137931, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.8793103448275862, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.6206896551724138, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.6206896551724138, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.6206896551724138, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.6206896551724138, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.6206896551724138, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.6206896551724138, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.6206896551724138, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.8901515151515151, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.8901515151515151, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.9076138897738133, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.9076138897738133, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.9076138897738133, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.8901515151515151, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.8706594456833386, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.8706594456833386, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.8706594456833386, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.8706594456833386, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.8507078507078507, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.8507078507078507, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.8679674796747967, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.888030888030888, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.888030888030888, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.888030888030888, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.8706594456833386, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.8901515151515151, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.8901515151515151, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9267676767676767, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.8901515151515151, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9092331768388107, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.8729264475743349, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.8901515151515151, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9076138897738133, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.8901515151515151, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.8706594456833386, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.3829787234042553, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.3829787234042553, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.3829787234042553, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.3829787234042553, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.3829787234042553, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.3829787234042553, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.3829787234042553, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.8901515151515151, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.8901515151515151, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.904040404040404, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.904040404040404, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.904040404040404, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.8901515151515151, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.8674242424242424, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.8674242424242424, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.8674242424242424, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.8674242424242424, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.8446969696969697, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.8446969696969697, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.8585858585858586, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.8813131313131313, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.8813131313131313, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.8813131313131313, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.8674242424242424, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.8901515151515151, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.8901515151515151, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.9267676767676767, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.8901515151515151, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.9128787878787878, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.8762626262626263, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.8901515151515151, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.904040404040404, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.8901515151515151, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.8674242424242424, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.5, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.5, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.5, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.5, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.5, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.5, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.5, "id_best": 32, "lr_best": 0.0011099999999999999, "wd_best": 0.05, "train/loss_best": 0.0001300041377544403, "validation/loss_best": 0.6943714022636414, "validation/acc_best": 0.9310344827586207, "validation/f1_best": 0.9267676767676767, "validation/bacc_best": 0.9267676767676767} +{"epoch": 15, "train/lr": 6.196799573888289e-05, "train/loss": 0.20683653485029935, "train/grad": 0.12300725067034364, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.37759841918945314, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.3673486518859863, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.35397010803222656, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.34309730529785154, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.33404112339019776, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.32289804458618165, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.31208670139312744, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.30139158248901365, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.2890873670578003, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.27739615440368653, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.2667981052398682, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.2522425150871277, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.23939204216003418, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.2221453869342804, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.20685689955949782, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.19292844504117965, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.17553277164697648, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.1548883455991745, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.1289801986515522, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.09653205201029777, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.05291181161999702, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.015470873117446899, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.004919407367706299, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.002196221053600311, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.0012473280727863312, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.0007401245832443237, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.00046149924397468565, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0003191901743412018, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.00023295596241950989, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0001847715675830841, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.00014921948313713075, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.0001222197711467743, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.00012881219387054444, "train/loss_033_lr4.3e+00_wd1.0e+00": 9.226009249687195e-05, "train/loss_034_lr5.1e+00_wd1.0e+00": 7.798537611961365e-05, "train/loss_035_lr6.0e+00_wd1.0e+00": 7.377728819847106e-05, "train/loss_036_lr7.1e+00_wd1.0e+00": 7.609263062477111e-05, "train/loss_037_lr8.3e+00_wd1.0e+00": 5.569949746131897e-05, "train/loss_038_lr9.8e+00_wd1.0e+00": 8.796259760856628e-05, "train/loss_039_lr1.2e+01_wd1.0e+00": 8.655250072479247e-05, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.000139351487159729, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.0001602594554424286, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.69140625, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.69140625, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.69140625, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.69140625, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.69140625, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.69140625, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.69140625, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.025198692129924892, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.025044947399292142, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.024900834267027674, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.024810391592327504, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.02477251858683303, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.02476074614794925, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.024814762701280416, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.02495336576132104, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.02522928254213184, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.02563867063028738, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.026138065829873085, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.026956119642127307, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.027610181216150522, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.028277805550023915, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.028672660011798145, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.028846381183248015, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.02876302319811657, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.028242133846506475, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.026724436387885363, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.02348867755383253, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.016326167110237294, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.006504366912558908, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.002167786105819687, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0009265793955728441, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0005114796570842373, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0002974231823782247, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.00018727998799477063, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0001277210406260565, "train/grad_028_lr1.9e+00_wd1.0e+00": 9.672913758663526e-05, "train/grad_029_lr2.3e+00_wd1.0e+00": 7.635800322191245e-05, "train/grad_030_lr2.7e+00_wd1.0e+00": 6.12515153383697e-05, "train/grad_031_lr3.1e+00_wd1.0e+00": 4.8457429043082814e-05, "train/grad_032_lr3.7e+00_wd1.0e+00": 4.7024055295139536e-05, "train/grad_033_lr4.3e+00_wd1.0e+00": 3.2121988319318006e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 2.8932033074369202e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 2.621703300349054e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 2.8061610054805898e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 3.320428973040634e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 4.348768994269392e-05, "train/grad_039_lr1.2e+01_wd1.0e+00": 3.4787325108140974e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 7.424367836641465e-05, "train/grad_041_lr1.6e+01_wd1.0e+00": 5.802666859684891e-05, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.36377233266830444, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.3547424376010895, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.3443026840686798, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.3373079001903534, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.3326028883457184, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.3288560211658478, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.32720747590065, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.3276022970676422, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.33049389719963074, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.334873229265213, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.3398345708847046, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.3452247679233551, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.3466552197933197, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.3448888957500458, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.3418723940849304, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.33734315633773804, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.3296794891357422, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.31996747851371765, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.31060317158699036, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.3309990167617798, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.42987287044525146, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.5347583293914795, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.6493262052536011, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.718062698841095, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.7294761538505554, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.6954754590988159, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.7059960961341858, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.6947439908981323, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.7146072387695312, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.7432973384857178, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.685507595539093, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.7252762317657471, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.6986045241355896, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.8775908350944519, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.7948858141899109, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.9189085364341736, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.8771712779998779, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.9392909407615662, "validation/loss_038_lr9.8e+00_wd1.0e+00": 1.282659649848938, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.9867461919784546, "validation/loss_040_lr1.4e+01_wd1.0e+00": 1.08551025390625, "validation/loss_041_lr1.6e+01_wd1.0e+00": 1.59243643283844, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.6931472420692444, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.896551724137931, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.9137931034482759, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.9137931034482759, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.9137931034482759, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9137931034482759, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.896551724137931, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.8793103448275862, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.8793103448275862, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.8793103448275862, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.8793103448275862, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.8620689655172413, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.8620689655172413, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.8448275862068966, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.8448275862068966, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.896551724137931, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.896551724137931, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.8793103448275862, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.896551724137931, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.896551724137931, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9482758620689655, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.896551724137931, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.8793103448275862, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.896551724137931, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9137931034482759, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.896551724137931, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.8793103448275862, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.6206896551724138, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.6206896551724138, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.6206896551724138, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.6206896551724138, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.6206896551724138, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.6206896551724138, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.6206896551724138, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.8901515151515151, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.9076138897738133, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.9076138897738133, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.9076138897738133, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.9076138897738133, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.888030888030888, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.8706594456833386, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.8706594456833386, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.8706594456833386, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.8706594456833386, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.8507078507078507, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.8535353535353536, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.833705001592864, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.833705001592864, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.888030888030888, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.888030888030888, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.8706594456833386, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.8901515151515151, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.8901515151515151, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.944568333864288, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.8901515151515151, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9092331768388107, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.8729264475743349, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.8901515151515151, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9076138897738133, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.8901515151515151, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.8706594456833386, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.3829787234042553, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.3829787234042553, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.3829787234042553, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.3829787234042553, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.3829787234042553, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.3829787234042553, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.3829787234042553, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.8901515151515151, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.904040404040404, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.904040404040404, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.904040404040404, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.904040404040404, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.8813131313131313, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.8674242424242424, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.8674242424242424, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.8674242424242424, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.8674242424242424, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.8446969696969697, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.8535353535353536, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.8308080808080808, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.8308080808080808, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.8813131313131313, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.8813131313131313, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.8674242424242424, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.8901515151515151, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.8901515151515151, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.9406565656565656, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.8901515151515151, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.9128787878787878, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.8762626262626263, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.8901515151515151, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.904040404040404, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.8901515151515151, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.8674242424242424, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.5, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.5, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.5, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.5, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.5, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.5, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.5, "id_best": 32, "lr_best": 0.0011099999999999999, "wd_best": 0.05, "train/loss_best": 0.00012881219387054444, "validation/loss_best": 0.6986045241355896, "validation/acc_best": 0.9482758620689655, "validation/f1_best": 0.944568333864288, "validation/bacc_best": 0.9406565656565656} +{"epoch": 16, "train/lr": 3.870405029380728e-05, "train/loss": 0.18826222766190767, "train/grad": 0.12153318939730524, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.336199951171875, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.3232576942443848, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.3065511703491211, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.29350712776184085, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.2830750322341919, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.2710934257507324, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.2600576066970825, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.2498032569885254, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.23844473361968993, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.22787189960479737, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.2183924436569214, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.20515265226364135, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.19343690752983092, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.17821302950382234, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.16478170394897462, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.15273901224136352, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.13802676245570183, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.12068258702754975, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.09855748489499092, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.07078344509005546, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.035908080190420154, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.010264634191989898, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.0033641290664672852, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.0015280623733997345, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.0008621835708618165, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.0005451683700084686, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.0003456158936023712, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0002489803731441498, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.00018671751022338867, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0001485629379749298, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.00011944517493247986, "train/loss_031_lr3.1e+00_wd1.0e+00": 8.973464369773864e-05, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.00010667800903320312, "train/loss_033_lr4.3e+00_wd1.0e+00": 6.78493082523346e-05, "train/loss_034_lr5.1e+00_wd1.0e+00": 5.771979689598084e-05, "train/loss_035_lr6.0e+00_wd1.0e+00": 5.809962749481201e-05, "train/loss_036_lr7.1e+00_wd1.0e+00": 5.894482135772705e-05, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.859102725982666e-05, "train/loss_038_lr9.8e+00_wd1.0e+00": 6.66654109954834e-05, "train/loss_039_lr1.2e+01_wd1.0e+00": 7.46588408946991e-05, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.00012859925627708435, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.00010854929685592651, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.69140625, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.69140625, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.69140625, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.69140625, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.69140625, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.69140625, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.69140625, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.024616028626915067, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.024477592383045702, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.024363127136602998, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.02430008108727634, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.024289804969448596, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.024307270175777374, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.024392064777202904, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.024557178274262695, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.024899869430810212, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.025356378578580915, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.02590226432075724, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.026760929357260467, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.027471320130862297, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.02826209379825741, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.028749273647554217, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.02895144630689174, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.028812439014436676, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.028160359078319742, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.02635037987551186, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.022801763776806185, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.015405763761373236, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.005395333854830824, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.001881880074934088, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0008616817852407622, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.00048548697284559237, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0002962555633325792, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0001858788557922253, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.00012228072402592716, "train/grad_028_lr1.9e+00_wd1.0e+00": 9.638407826400907e-05, "train/grad_029_lr2.3e+00_wd1.0e+00": 7.145319632797964e-05, "train/grad_030_lr2.7e+00_wd1.0e+00": 5.8751843100708355e-05, "train/grad_031_lr3.1e+00_wd1.0e+00": 4.5338167691966194e-05, "train/grad_032_lr3.7e+00_wd1.0e+00": 4.574596181953439e-05, "train/grad_033_lr4.3e+00_wd1.0e+00": 3.203201543783507e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 2.8425518193060384e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 2.5360778566891893e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 2.7183739172187414e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 3.245547608768273e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 4.2297233170494053e-05, "train/grad_039_lr1.2e+01_wd1.0e+00": 3.349878199514933e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 6.948170452858449e-05, "train/grad_041_lr1.6e+01_wd1.0e+00": 5.482489788789735e-05, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.36248618364334106, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.35372647643089294, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.3434223234653473, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.33670634031295776, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.3323165774345398, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.3287345767021179, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.32720309495925903, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.3279762268066406, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.3310738801956177, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.33596670627593994, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.34096360206604004, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.3460308909416199, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.347382515668869, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.3456363379955292, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.34247884154319763, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.3382752537727356, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.3315190076828003, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.3227722644805908, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.31583210825920105, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.34168541431427, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.4381142556667328, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.5463875532150269, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.6573852300643921, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.7258281707763672, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.7366765141487122, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.7002202272415161, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.7104761004447937, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.6984825730323792, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.7176623940467834, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.7464479804039001, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.689166247844696, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.7274978756904602, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.7016326189041138, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.880859375, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.7955890893936157, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.9218344688415527, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.8801892995834351, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.9385854005813599, "validation/loss_038_lr9.8e+00_wd1.0e+00": 1.2767741680145264, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.9917773604393005, "validation/loss_040_lr1.4e+01_wd1.0e+00": 1.0883731842041016, "validation/loss_041_lr1.6e+01_wd1.0e+00": 1.5931832790374756, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.6931472420692444, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.896551724137931, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.9137931034482759, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.9137931034482759, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.9137931034482759, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9137931034482759, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.896551724137931, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.8793103448275862, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.8793103448275862, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.8793103448275862, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.8793103448275862, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.8620689655172413, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.8448275862068966, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.8448275862068966, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.896551724137931, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.896551724137931, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.896551724137931, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.8793103448275862, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.896551724137931, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.896551724137931, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9482758620689655, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.896551724137931, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.8793103448275862, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.896551724137931, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9137931034482759, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.896551724137931, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.8793103448275862, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.6206896551724138, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.6206896551724138, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.6206896551724138, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.6206896551724138, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.6206896551724138, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.6206896551724138, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.6206896551724138, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.8901515151515151, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.9076138897738133, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.9076138897738133, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.9076138897738133, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.9076138897738133, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.888030888030888, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.8706594456833386, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.8706594456833386, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.8706594456833386, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.8706594456833386, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.8535353535353536, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.833705001592864, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.833705001592864, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.888030888030888, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.888030888030888, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.888030888030888, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.8706594456833386, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.8901515151515151, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.8901515151515151, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.944568333864288, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.8901515151515151, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9092331768388107, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.8729264475743349, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.8901515151515151, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9076138897738133, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.8901515151515151, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.8706594456833386, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.3829787234042553, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.3829787234042553, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.3829787234042553, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.3829787234042553, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.3829787234042553, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.3829787234042553, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.3829787234042553, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.8901515151515151, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.904040404040404, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.904040404040404, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.904040404040404, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.904040404040404, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.8813131313131313, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.8674242424242424, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.8674242424242424, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.8674242424242424, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.8674242424242424, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.8535353535353536, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.8308080808080808, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.8308080808080808, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.8813131313131313, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.8813131313131313, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.8813131313131313, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.8674242424242424, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.8901515151515151, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.8901515151515151, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.9406565656565656, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.8901515151515151, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.9128787878787878, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.8762626262626263, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.8901515151515151, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.904040404040404, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.8901515151515151, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.8674242424242424, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.5, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.5, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.5, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.5, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.5, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.5, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.5, "id_best": 32, "lr_best": 0.0011099999999999999, "wd_best": 0.05, "train/loss_best": 0.00010667800903320312, "validation/loss_best": 0.7016326189041138, "validation/acc_best": 0.9482758620689655, "validation/f1_best": 0.944568333864288, "validation/bacc_best": 0.9406565656565656} +{"epoch": 17, "train/lr": 2.030750443206766e-05, "train/loss": 0.19576329041272403, "train/grad": 0.10969295800663531, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.3592674446105957, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.3474883079528809, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.33212733268737793, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.319773473739624, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.30943703174591064, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.29733264446258545, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.28564235687255857, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.274626784324646, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.26206111907958984, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.2502360248565674, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.2392703437805176, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.22420005798339843, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.21092651009559632, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.1935655003786087, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.17841910153627397, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.16462203919887541, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.147804394364357, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.12775995552539826, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.10227898046374322, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.07157265171408653, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.035351592600345615, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.010211614668369293, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.003389330506324768, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.0015571705996990203, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.000915316492319107, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.000599750280380249, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.0003977544605731964, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0002628600597381592, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.00020774543285369872, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.00015108987689018249, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.00012738153338432312, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.00010890662670135499, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.00011869445443153381, "train/loss_033_lr4.3e+00_wd1.0e+00": 7.652625441551209e-05, "train/loss_034_lr5.1e+00_wd1.0e+00": 7.362827658653259e-05, "train/loss_035_lr6.0e+00_wd1.0e+00": 6.575807929039001e-05, "train/loss_036_lr7.1e+00_wd1.0e+00": 6.745323538780212e-05, "train/loss_037_lr8.3e+00_wd1.0e+00": 5.924969911575317e-05, "train/loss_038_lr9.8e+00_wd1.0e+00": 6.700769066810609e-05, "train/loss_039_lr1.2e+01_wd1.0e+00": 8.302584290504456e-05, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.00015088781714439392, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.00010286584496498108, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.69140625, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.69140625, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.69140625, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.69140625, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.69140625, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.69140625, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.69140625, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.02225143081508577, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.021994012901559473, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.0217481634975411, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.021618506973609328, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.02155690354062244, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.02152700750157237, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.021568671071436257, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.02168473559897393, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.02191980750998482, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.022275866649579257, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.02272984882351011, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.02349231401225552, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.024164864518679677, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.024984210864640772, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.025612419234821573, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.025997902747476473, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.026135458687786012, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.025815996745368466, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.024386946840095333, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.021363952430547214, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.0145282122323988, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.004975933831883594, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0016967864032631042, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.000763088875255562, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.00043660274081503303, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.00027517825570839706, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.00017449415902319742, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.00011688556078070179, "train/grad_028_lr1.9e+00_wd1.0e+00": 9.008912769218114e-05, "train/grad_029_lr2.3e+00_wd1.0e+00": 7.159558717830805e-05, "train/grad_030_lr2.7e+00_wd1.0e+00": 5.7843174290610476e-05, "train/grad_031_lr3.1e+00_wd1.0e+00": 4.6089681286503035e-05, "train/grad_032_lr3.7e+00_wd1.0e+00": 4.436976944418802e-05, "train/grad_033_lr4.3e+00_wd1.0e+00": 3.083122162820473e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 2.8165048340724753e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 2.366180196247569e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 2.7038853256726726e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 3.1442866073945194e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 4.047521409166421e-05, "train/grad_039_lr1.2e+01_wd1.0e+00": 3.162697840878082e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 6.466446439148398e-05, "train/grad_041_lr1.6e+01_wd1.0e+00": 5.2425343868520715e-05, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.3620665371417999, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.35342177748680115, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.34310564398765564, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.3365364074707031, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.3321850001811981, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.32863524556159973, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.3273480236530304, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.3281336724758148, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.3312925100326538, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.3362852931022644, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.3414461612701416, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.34639444947242737, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.34744346141815186, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.34561073780059814, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.34225085377693176, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.33803218603134155, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.3313620686531067, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.32269325852394104, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.3162376880645752, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.3437269330024719, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.4408712387084961, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.5516124963760376, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.6626814603805542, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.7308509945869446, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.7408315539360046, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.7027088403701782, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.711488664150238, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.7000473141670227, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.7189667820930481, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.7476524710655212, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.6906643509864807, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.7288011908531189, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.7025946378707886, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.8837443590164185, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.7963181734085083, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.9211241602897644, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.8820467591285706, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.9374546408653259, "validation/loss_038_lr9.8e+00_wd1.0e+00": 1.2760945558547974, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.991774320602417, "validation/loss_040_lr1.4e+01_wd1.0e+00": 1.08928382396698, "validation/loss_041_lr1.6e+01_wd1.0e+00": 1.5930278301239014, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.6931472420692444, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.896551724137931, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.9137931034482759, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.9137931034482759, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.9137931034482759, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9137931034482759, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.8793103448275862, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.8793103448275862, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.8793103448275862, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.8793103448275862, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.8793103448275862, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.8620689655172413, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.8448275862068966, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.8448275862068966, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.896551724137931, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.896551724137931, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.896551724137931, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.8793103448275862, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.896551724137931, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.896551724137931, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9482758620689655, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.896551724137931, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.8793103448275862, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.896551724137931, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9137931034482759, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.896551724137931, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.8793103448275862, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.6206896551724138, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.6206896551724138, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.6206896551724138, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.6206896551724138, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.6206896551724138, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.6206896551724138, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.6206896551724138, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.8901515151515151, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.9076138897738133, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.9076138897738133, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.9076138897738133, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.9076138897738133, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.8706594456833386, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.8706594456833386, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.8706594456833386, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.8706594456833386, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.8706594456833386, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.8535353535353536, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.833705001592864, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.833705001592864, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.888030888030888, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.888030888030888, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.888030888030888, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.8706594456833386, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.8901515151515151, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.8901515151515151, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.944568333864288, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.8901515151515151, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9092331768388107, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.8729264475743349, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.8901515151515151, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9076138897738133, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.8901515151515151, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.8706594456833386, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.3829787234042553, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.3829787234042553, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.3829787234042553, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.3829787234042553, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.3829787234042553, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.3829787234042553, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.3829787234042553, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.8901515151515151, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.904040404040404, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.904040404040404, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.904040404040404, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.904040404040404, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.8674242424242424, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.8674242424242424, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.8674242424242424, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.8674242424242424, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.8674242424242424, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.8535353535353536, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.8308080808080808, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.8308080808080808, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.8813131313131313, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.8813131313131313, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.8813131313131313, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.8674242424242424, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.8901515151515151, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.8901515151515151, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.9406565656565656, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.8901515151515151, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.9128787878787878, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.8762626262626263, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.8901515151515151, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.904040404040404, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.8901515151515151, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.8674242424242424, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.5, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.5, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.5, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.5, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.5, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.5, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.5, "id_best": 32, "lr_best": 0.0011099999999999999, "wd_best": 0.05, "train/loss_best": 0.00011869445443153381, "validation/loss_best": 0.7025946378707886, "validation/acc_best": 0.9482758620689655, "validation/f1_best": 0.944568333864288, "validation/bacc_best": 0.9406565656565656} +{"epoch": 18, "train/lr": 7.5829098008590064e-06, "train/loss": 0.1954590981826186, "train/grad": 0.11225427401252092, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.3565011787414551, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.34529052734375, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.3301618480682373, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.31808804512023925, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.3080273103713989, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.29603230476379394, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.28467741012573244, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.2736410284042358, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.2612894105911255, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.24953210353851318, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.23893896579742432, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.2240683603286743, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.2107822823524475, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.1929381513595581, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.17705926895141602, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.16287073701620103, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.14571448177099228, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.12622373372316362, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.1028592298924923, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.07652369499206543, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.03805751174688339, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.009894824922084808, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.00330438569188118, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.0016120480000972749, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.000977860540151596, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.0006076343357563019, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.0003702378273010254, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0002518889307975769, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0002010001242160797, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.00015491113066673279, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.00012312084436416626, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.0001029612123966217, "train/loss_032_lr3.7e+00_wd1.0e+00": 9.182572364807128e-05, "train/loss_033_lr4.3e+00_wd1.0e+00": 7.009401917457581e-05, "train/loss_034_lr5.1e+00_wd1.0e+00": 6.698533892631531e-05, "train/loss_035_lr6.0e+00_wd1.0e+00": 6.644785404205322e-05, "train/loss_036_lr7.1e+00_wd1.0e+00": 6.610706448554993e-05, "train/loss_037_lr8.3e+00_wd1.0e+00": 4.924461245536804e-05, "train/loss_038_lr9.8e+00_wd1.0e+00": 5.6554824113845824e-05, "train/loss_039_lr1.2e+01_wd1.0e+00": 8.408904075622558e-05, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.00013376697897911073, "train/loss_041_lr1.6e+01_wd1.0e+00": 8.874684572219848e-05, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.69140625, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.69140625, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.69140625, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.69140625, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.69140625, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.69140625, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.69140625, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.02305987707572058, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.022841347286012025, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.022669622814282774, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.022596334214322267, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.02261351316003129, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.02269638262456283, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.022836757809855043, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.023068135022185743, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.023421498476527632, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.023867959277704357, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.024363679860252885, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.025076557758729905, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.025564438987057656, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.02598306889878586, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.026163668745430187, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.02616410133894533, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.025902934736805036, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.025239429824287073, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.0236168855545111, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.02054791627684608, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.013418425887066406, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.004656217089759594, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0016428340974289314, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0007617473242771667, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.00043432448978819593, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.00026066159289257486, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.00016392379915032508, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.00011160201404891267, "train/grad_028_lr1.9e+00_wd1.0e+00": 8.574066651362956e-05, "train/grad_029_lr2.3e+00_wd1.0e+00": 6.717958079661912e-05, "train/grad_030_lr2.7e+00_wd1.0e+00": 5.508718866849449e-05, "train/grad_031_lr3.1e+00_wd1.0e+00": 4.45227466536835e-05, "train/grad_032_lr3.7e+00_wd1.0e+00": 4.25383401147883e-05, "train/grad_033_lr4.3e+00_wd1.0e+00": 3.0130767059404205e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 2.7019390474976036e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 2.336168486749557e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 2.5747354368377273e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 3.075371891732459e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 3.97628497520941e-05, "train/grad_039_lr1.2e+01_wd1.0e+00": 3.085384525775226e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 6.410679947485676e-05, "train/grad_041_lr1.6e+01_wd1.0e+00": 5.136206474006144e-05, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.36194026470184326, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.35316383838653564, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.34301140904426575, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.3365655839443207, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.3321669399738312, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.3287501633167267, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.3274713456630707, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.32827141880989075, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.3313964605331421, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.33617880940437317, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.3412226736545563, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.3461574912071228, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.3472370207309723, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.34552001953125, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.34221935272216797, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.3385571241378784, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.3323647677898407, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.324340283870697, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.3190387785434723, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.34743937849998474, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.4441012740135193, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.555987536907196, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.6667077541351318, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.7346674203872681, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.7428226470947266, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.7040826678276062, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.7113088369369507, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.701041579246521, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.7206735014915466, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.7486351728439331, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.6910072565078735, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.7288382053375244, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.7036668062210083, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.8843411207199097, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.7971288561820984, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.9224364161491394, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.8820191621780396, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.9377755522727966, "validation/loss_038_lr9.8e+00_wd1.0e+00": 1.2760396003723145, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.9929103255271912, "validation/loss_040_lr1.4e+01_wd1.0e+00": 1.093137264251709, "validation/loss_041_lr1.6e+01_wd1.0e+00": 1.5934875011444092, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.6931472420692444, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.896551724137931, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.9137931034482759, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.9137931034482759, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.9137931034482759, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9137931034482759, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.8793103448275862, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.8793103448275862, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.8793103448275862, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.8793103448275862, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.8793103448275862, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.8620689655172413, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.8620689655172413, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.8620689655172413, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.896551724137931, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.896551724137931, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.896551724137931, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.8793103448275862, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.896551724137931, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.896551724137931, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9482758620689655, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.896551724137931, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.8793103448275862, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.896551724137931, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9137931034482759, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.896551724137931, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.8793103448275862, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.6206896551724138, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.6206896551724138, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.6206896551724138, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.6206896551724138, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.6206896551724138, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.6206896551724138, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.6206896551724138, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.8901515151515151, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.9076138897738133, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.9076138897738133, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.9076138897738133, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.9076138897738133, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.8706594456833386, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.8706594456833386, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.8706594456833386, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.8706594456833386, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.8706594456833386, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.8507078507078507, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.8507078507078507, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.8507078507078507, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.888030888030888, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.888030888030888, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.888030888030888, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.8706594456833386, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.8901515151515151, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.8901515151515151, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.944568333864288, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.8901515151515151, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9092331768388107, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.8729264475743349, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.8901515151515151, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9076138897738133, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.8901515151515151, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.8706594456833386, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.3829787234042553, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.3829787234042553, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.3829787234042553, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.3829787234042553, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.3829787234042553, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.3829787234042553, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.3829787234042553, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.8901515151515151, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.904040404040404, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.904040404040404, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.904040404040404, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.904040404040404, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.8674242424242424, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.8674242424242424, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.8674242424242424, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.8674242424242424, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.8674242424242424, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.8446969696969697, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.8446969696969697, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.8446969696969697, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.8813131313131313, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.8813131313131313, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.8813131313131313, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.8674242424242424, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.8901515151515151, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.8901515151515151, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.9406565656565656, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.8901515151515151, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.9128787878787878, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.8762626262626263, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.8901515151515151, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.904040404040404, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.8901515151515151, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.8674242424242424, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.5, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.5, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.5, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.5, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.5, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.5, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.5, "id_best": 32, "lr_best": 0.0011099999999999999, "wd_best": 0.05, "train/loss_best": 9.182572364807128e-05, "validation/loss_best": 0.7036668062210083, "validation/acc_best": 0.9482758620689655, "validation/f1_best": 0.944568333864288, "validation/bacc_best": 0.9406565656565656} +{"epoch": 19, "train/lr": 1.0867618231465446e-06, "train/loss": 0.1928070256859064, "train/grad": 0.11882239118218423, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.3485833740234375, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.3377630615234375, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.3232557678222656, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.3116538619995117, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.30182220458984377, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.2899056625366211, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.2781109428405762, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.2666951847076416, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.2536886215209961, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.2412312412261963, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.2299766159057617, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.2145841383934021, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.2011377489566803, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.18407633006572724, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.1695327290892601, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.15691652357578278, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.141826788187027, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.12428681671619415, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.10207994595170021, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.07483443185687065, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.03782026305794716, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.009820491820573807, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.0031742946803569793, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.0014711794257164, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.0008539488911628723, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.0005507534742355347, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.00035970538854598996, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.00026171505451202395, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0001897113025188446, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.00016530662775039674, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.00011733844876289367, "train/loss_031_lr3.1e+00_wd1.0e+00": 9.823158383369446e-05, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.0001188206672668457, "train/loss_033_lr4.3e+00_wd1.0e+00": 7.44067132472992e-05, "train/loss_034_lr5.1e+00_wd1.0e+00": 6.250962615013122e-05, "train/loss_035_lr6.0e+00_wd1.0e+00": 7.352828979492187e-05, "train/loss_036_lr7.1e+00_wd1.0e+00": 5.573779344558716e-05, "train/loss_037_lr8.3e+00_wd1.0e+00": 5.050703883171081e-05, "train/loss_038_lr9.8e+00_wd1.0e+00": 7.898539304733276e-05, "train/loss_039_lr1.2e+01_wd1.0e+00": 8.183464407920837e-05, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.0001391257345676422, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.00012031152844429016, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.69140625, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.69140625, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.69140625, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.69140625, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.69140625, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.69140625, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.69140625, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.024763989597558975, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.024690150199458003, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.024606819010805338, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.02454164753202349, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.024489652290940286, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.024444006781559436, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.024435279918834568, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.0245037256879732, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.024699501062277706, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.02499232002068311, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.025379081836435943, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.02602585741551593, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.026623598209116608, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.02727974092354998, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.0276833696779795, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.027791767541784793, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.02754490577150136, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.026725747756427155, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.024665801433147862, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.020980819102260285, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.014357695964281447, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.004829129375102639, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.001693062335389186, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0007818442180996498, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.00044011709288724885, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.00026312723988553444, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.00016397007899712434, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0001153184748650915, "train/grad_028_lr1.9e+00_wd1.0e+00": 8.694852690723565e-05, "train/grad_029_lr2.3e+00_wd1.0e+00": 7.07106987627526e-05, "train/grad_030_lr2.7e+00_wd1.0e+00": 5.694128976244883e-05, "train/grad_031_lr3.1e+00_wd1.0e+00": 4.763130369269675e-05, "train/grad_032_lr3.7e+00_wd1.0e+00": 4.3363497793507124e-05, "train/grad_033_lr4.3e+00_wd1.0e+00": 2.9643358559496846e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 2.6994424067083857e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 2.358889531251407e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 2.5925470897050218e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 3.19499966838066e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 4.052269582572876e-05, "train/grad_039_lr1.2e+01_wd1.0e+00": 3.0391451135898252e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 6.297768355750577e-05, "train/grad_041_lr1.6e+01_wd1.0e+00": 5.021637865013418e-05, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.3618401885032654, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.3530815839767456, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.34308475255966187, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.336513489484787, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.3321249783039093, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.32867395877838135, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.3273541331291199, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.3280627727508545, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.3314538598060608, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.33618953824043274, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.34120795130729675, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.3462006747722626, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.34693312644958496, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.34513962268829346, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.3423577547073364, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.3384853005409241, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.33236968517303467, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.3245505392551422, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.3191511631011963, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.34767282009124756, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.4439769983291626, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.5564684867858887, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.6678062677383423, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.734108030796051, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.74262934923172, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.7041560411453247, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.7121198773384094, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.7010884881019592, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.7204747200012207, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.7485353946685791, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.691059947013855, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.7288815975189209, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.704197108745575, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.8844694495201111, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.7973368167877197, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.9227418303489685, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.8828432559967041, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.9374811053276062, "validation/loss_038_lr9.8e+00_wd1.0e+00": 1.276054859161377, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.9939412474632263, "validation/loss_040_lr1.4e+01_wd1.0e+00": 1.093267798423767, "validation/loss_041_lr1.6e+01_wd1.0e+00": 1.5943204164505005, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.6931472420692444, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.896551724137931, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.9137931034482759, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.9137931034482759, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.9137931034482759, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9137931034482759, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.8793103448275862, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.8793103448275862, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.8793103448275862, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.8793103448275862, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.8793103448275862, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.8620689655172413, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.8620689655172413, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.8620689655172413, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.896551724137931, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.896551724137931, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.896551724137931, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.8793103448275862, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.8793103448275862, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.896551724137931, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.896551724137931, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9482758620689655, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.896551724137931, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.8793103448275862, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.896551724137931, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9137931034482759, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9137931034482759, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.896551724137931, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.8793103448275862, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.6206896551724138, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.6206896551724138, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.6206896551724138, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.6206896551724138, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.6206896551724138, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.6206896551724138, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.6206896551724138, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.8901515151515151, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.9076138897738133, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.9076138897738133, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.9076138897738133, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.9076138897738133, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.8706594456833386, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.8706594456833386, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.8706594456833386, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.8706594456833386, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.8706594456833386, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.8507078507078507, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.8507078507078507, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.8507078507078507, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.888030888030888, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.888030888030888, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.888030888030888, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.8706594456833386, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.8706594456833386, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.8901515151515151, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.8901515151515151, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.944568333864288, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.8901515151515151, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9092331768388107, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.8729264475743349, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.8901515151515151, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9076138897738133, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9076138897738133, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.8901515151515151, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.8706594456833386, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.3829787234042553, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.3829787234042553, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.3829787234042553, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.3829787234042553, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.3829787234042553, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.3829787234042553, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.3829787234042553, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.8901515151515151, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.904040404040404, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.904040404040404, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.904040404040404, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.904040404040404, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.8674242424242424, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.8674242424242424, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.8674242424242424, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.8674242424242424, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.8674242424242424, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.8446969696969697, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.8446969696969697, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.8446969696969697, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.8813131313131313, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.8813131313131313, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.8813131313131313, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.8674242424242424, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.8674242424242424, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.8901515151515151, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.8901515151515151, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.9406565656565656, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.8901515151515151, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.9128787878787878, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.8762626262626263, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.8901515151515151, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.904040404040404, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.904040404040404, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.8901515151515151, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.8674242424242424, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.5, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.5, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.5, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.5, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.5, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.5, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.5, "id_best": 32, "lr_best": 0.0011099999999999999, "wd_best": 0.05, "train/loss_best": 0.0001188206672668457, "validation/loss_best": 0.704197108745575, "validation/acc_best": 0.9482758620689655, "validation/f1_best": 0.944568333864288, "validation/bacc_best": 0.9406565656565656} diff --git a/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_sex__patch__logistic/config.yaml b/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_sex__patch__logistic/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..bdfa65d3bda97e3dcb7b69e747efb5849bd4e4da --- /dev/null +++ b/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_sex__patch__logistic/config.yaml @@ -0,0 +1,30 @@ +output_root: experiments/input_space_v3/output +name_prefix: eval_logistic +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_1; eval v2 (aabc_sex patch logistic) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: input_space_v3/flat_lr1e-3_1/eval_v2/aabc_sex__patch__logistic +model: flat_mae +representation: patch +dataset: aabc_sex +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_sex__patch__logistic +remote_dir: null diff --git a/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_sex__patch__logistic/eval_table.csv b/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_sex__patch__logistic/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..b1ecb4109e2e207cb0567a380b5e17447547fe79 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_sex__patch__logistic/eval_table.csv @@ -0,0 +1,203 @@ +model,repr,clf,dataset,trial,C,split,acc,acc_std,f1,f1_std,bacc,bacc_std +flat_mae,patch,logistic,aabc_sex,,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,,2.782559402207126,test,0.9818181818181818,0.018236245807649803,0.9811965811965813,0.018630506104314964,0.9848484848484849,0.015196871506374818 +flat_mae,patch,logistic,aabc_sex,1,0.3593813663804626,train,0.994328922495274,0.0035885749167717655,0.9941822314276811,0.0036852603051151203,0.99388170813916,0.003919536747416668 +flat_mae,patch,logistic,aabc_sex,1,0.3593813663804626,test,0.8363636363636363,0.048407239401212276,0.8307692307692308,0.05073489798417324,0.8288043478260869,0.050783296381626285 +flat_mae,patch,logistic,aabc_sex,2,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,2,21.54434690031882,test,0.9272727272727272,0.0353856860447767,0.9260752688172043,0.03573551023220552,0.9313858695652174,0.03420827335714145 +flat_mae,patch,logistic,aabc_sex,3,0.3593813663804626,train,0.994328922495274,0.0031964492290777868,0.9941893034853195,0.003272720350309746,0.9944898736774231,0.0031471664532196682 +flat_mae,patch,logistic,aabc_sex,3,0.3593813663804626,test,0.8363636363636363,0.04981478422389005,0.8281846581048247,0.053588622915386894,0.8226902173913043,0.05371862551203422 +flat_mae,patch,logistic,aabc_sex,4,0.005994842503189409,train,0.9206049149338374,0.011618968645641149,0.9176012461059191,0.012246481562442766,0.9131275828717137,0.012879380840708823 +flat_mae,patch,logistic,aabc_sex,4,0.005994842503189409,test,0.8545454545454545,0.049053130244428415,0.8521505376344086,0.049355777433201735,0.8566576086956521,0.04818348065463546 +flat_mae,patch,logistic,aabc_sex,5,0.046415888336127774,train,0.9546313799621928,0.009222113666441696,0.9535421545667447,0.009422646395736731,0.9540944928045957,0.009343839900487854 +flat_mae,patch,logistic,aabc_sex,5,0.046415888336127774,test,0.8727272727272727,0.0447266223160396,0.8663658451926415,0.04814473548321278,0.8600543478260869,0.04905479270055572 +flat_mae,patch,logistic,aabc_sex,6,0.3593813663804626,train,0.994328922495274,0.0031884615858694416,0.9941893034853195,0.003265079907795842,0.9944898736774231,0.0031527383774431115 +flat_mae,patch,logistic,aabc_sex,6,0.3593813663804626,test,0.9272727272727272,0.03665158718221091,0.9252717391304348,0.037676477828171816,0.9252717391304348,0.03793582409885245 +flat_mae,patch,logistic,aabc_sex,7,0.005994842503189409,train,0.9206049149338374,0.011721067717868886,0.9179590570719602,0.012192348404927505,0.9149520794865031,0.012561169973390775 +flat_mae,patch,logistic,aabc_sex,7,0.005994842503189409,test,0.8545454545454545,0.04726187287972379,0.8484848484848485,0.050149524267093536,0.8444293478260869,0.050437037491613365 +flat_mae,patch,logistic,aabc_sex,8,0.005994842503189409,train,0.9224952741020794,0.011374004431835165,0.9197408200949537,0.011910752170740049,0.9159779008763446,0.012417344790684555 +flat_mae,patch,logistic,aabc_sex,8,0.005994842503189409,test,0.8545454545454545,0.045858265295012704,0.8521505376344086,0.04638234499419379,0.8566576086956521,0.04609714182836298 +flat_mae,patch,logistic,aabc_sex,9,0.3593813663804626,train,0.996219281663516,0.002628118701288447,0.9961238606055277,0.0026940629764745285,0.9961238606055277,0.0027040550456311125 +flat_mae,patch,logistic,aabc_sex,9,0.3593813663804626,test,0.9090909090909091,0.03859131063074105,0.905982905982906,0.0402361986123722,0.9035326086956521,0.04113998536435305 +flat_mae,patch,logistic,aabc_sex,10,0.3593813663804626,train,0.994328922495274,0.0032355064142038765,0.9941893034853195,0.003313760683290754,0.9944898736774231,0.0032274963916457456 +flat_mae,patch,logistic,aabc_sex,10,0.3593813663804626,test,0.9454545454545454,0.02871325319588342,0.9435897435897436,0.029899947742777263,0.9408967391304348,0.030996496914842624 +flat_mae,patch,logistic,aabc_sex,11,0.046415888336127774,train,0.9489603024574669,0.009894563167731588,0.9477037313678753,0.01013172039140151,0.9479762009437558,0.010163988867759603 +flat_mae,patch,logistic,aabc_sex,11,0.046415888336127774,test,0.9454545454545454,0.03091488715706213,0.9435897435897436,0.03233676076163877,0.9408967391304348,0.03368639204805854 +flat_mae,patch,logistic,aabc_sex,12,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,12,21.54434690031882,test,0.8181818181818182,0.05215468410775932,0.8106060606060606,0.05551496676886814,0.8070652173913043,0.05561450464576429 +flat_mae,patch,logistic,aabc_sex,13,0.046415888336127774,train,0.9546313799621928,0.00923777657735167,0.9534863272663325,0.009472103946731574,0.9534863272663325,0.009572636093907964 +flat_mae,patch,logistic,aabc_sex,13,0.046415888336127774,test,0.8545454545454545,0.04593831293203224,0.8484848484848485,0.04817113584286549,0.8444293478260869,0.048309051878182976 +flat_mae,patch,logistic,aabc_sex,14,0.046415888336127774,train,0.9489603024574669,0.009115514193482537,0.9477037313678753,0.009327605423612537,0.9479762009437558,0.009313610586596669 +flat_mae,patch,logistic,aabc_sex,14,0.046415888336127774,test,0.9454545454545454,0.030822874408089524,0.9442755825734549,0.031362397895195265,0.9470108695652174,0.03035665668891174 +flat_mae,patch,logistic,aabc_sex,15,0.3593813663804626,train,0.994328922495274,0.003355983333240755,0.9941893034853195,0.003437619457190766,0.9944898736774231,0.003352016803023945 +flat_mae,patch,logistic,aabc_sex,15,0.3593813663804626,test,0.9090909090909091,0.03842139555460781,0.9071259709557582,0.039140143088070616,0.9096467391304348,0.0385358136660011 +flat_mae,patch,logistic,aabc_sex,16,0.3593813663804626,train,0.9924385633270322,0.0036152841097563354,0.9922570257611241,0.0036975342256835037,0.9928558867493186,0.0034843832777556884 +flat_mae,patch,logistic,aabc_sex,16,0.3593813663804626,test,0.8909090909090909,0.04039828160980109,0.884453781512605,0.0445160889506563,0.8756793478260869,0.04597494581773473 +flat_mae,patch,logistic,aabc_sex,17,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,17,2.782559402207126,test,0.9090909090909091,0.03642066437324325,0.9045470322804582,0.03953597459509306,0.8974184782608696,0.04113794738454493 +flat_mae,patch,logistic,aabc_sex,18,0.000774263682681127,train,0.8922495274102079,0.013230891609945353,0.8877422237113978,0.014023814195424526,0.8825361235675138,0.014428746701213321 +flat_mae,patch,logistic,aabc_sex,18,0.000774263682681127,test,0.8727272727272727,0.04425290203865701,0.8711943793911007,0.04443531354761817,0.8783967391304348,0.04283113976051379 +flat_mae,patch,logistic,aabc_sex,19,0.046415888336127774,train,0.9546313799621928,0.008743989919652294,0.9534289990316049,0.008989322312329942,0.9528781617280695,0.009220986965350562 +flat_mae,patch,logistic,aabc_sex,19,0.046415888336127774,test,0.8727272727272727,0.04330619027001195,0.8711943793911007,0.0435022813079782,0.8783967391304348,0.04215863482067107 +flat_mae,patch,logistic,aabc_sex,20,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,20,21.54434690031882,test,0.8363636363636363,0.05017343803545376,0.8328267477203647,0.05137990131322007,0.8349184782608696,0.051167154525668744 +flat_mae,patch,logistic,aabc_sex,21,0.005994842503189409,train,0.9168241965973535,0.011591342076026377,0.9141715094840557,0.012014078414388528,0.911684105630294,0.012238716714630676 +flat_mae,patch,logistic,aabc_sex,21,0.005994842503189409,test,0.8,0.0518411304845617,0.790003471017008,0.05582040684415123,0.7853260869565217,0.05523019886877215 +flat_mae,patch,logistic,aabc_sex,22,0.046415888336127774,train,0.945179584120983,0.009875438934687966,0.9438299336914217,0.01011523705265237,0.9441000615492834,0.010182036019366087 +flat_mae,patch,logistic,aabc_sex,22,0.046415888336127774,test,0.9636363636363636,0.026259757729900295,0.9626358695652174,0.027077372978828982,0.9626358695652174,0.027412093937197488 +flat_mae,patch,logistic,aabc_sex,23,0.3593813663804626,train,0.994328922495274,0.0032673894437360218,0.9941893034853195,0.0033458338745570187,0.9944898736774231,0.0032271468843667744 +flat_mae,patch,logistic,aabc_sex,23,0.3593813663804626,test,0.9636363636363636,0.025883042727362,0.9626358695652174,0.02661787356522646,0.9626358695652174,0.02682501323928264 +flat_mae,patch,logistic,aabc_sex,24,0.046415888336127774,train,0.9527410207939508,0.009589376753786608,0.9515185952306762,0.009846461503343684,0.9512441747999649,0.01002663859271495 +flat_mae,patch,logistic,aabc_sex,24,0.046415888336127774,test,0.8727272727272727,0.04437941597163565,0.8663658451926415,0.04788913918531563,0.8600543478260869,0.04862966265227339 +flat_mae,patch,logistic,aabc_sex,25,0.046415888336127774,train,0.945179584120983,0.009771145672473011,0.9438299336914217,0.01000937519838532,0.9441000615492834,0.010073680641580962 +flat_mae,patch,logistic,aabc_sex,25,0.046415888336127774,test,0.9090909090909091,0.03718519211187021,0.905982905982906,0.03885529002851244,0.9035326086956521,0.03962913093877616 +flat_mae,patch,logistic,aabc_sex,26,0.046415888336127774,train,0.9527410207939508,0.008844679253617635,0.9514580924590283,0.009095127938783894,0.9506360092617017,0.009276581236365095 +flat_mae,patch,logistic,aabc_sex,26,0.046415888336127774,test,0.8363636363636363,0.048307609379547437,0.8307692307692308,0.05071198843845818,0.8288043478260869,0.05097988034242785 +flat_mae,patch,logistic,aabc_sex,27,0.046415888336127774,train,0.9508506616257089,0.009235541197726538,0.9495480822842386,0.009501924195125104,0.9490020223335971,0.009752886992772597 +flat_mae,patch,logistic,aabc_sex,27,0.046415888336127774,test,0.9090909090909091,0.03627232171110708,0.905982905982906,0.03789855769254333,0.9035326086956521,0.038683346961095245 +flat_mae,patch,logistic,aabc_sex,28,0.005994842503189409,train,0.9224952741020794,0.011745734180233542,0.9201850291269996,0.01215151950470621,0.918410563029397,0.012471882084530298 +flat_mae,patch,logistic,aabc_sex,28,0.005994842503189409,test,0.8363636363636363,0.046125893124458014,0.8250265111346766,0.0520884930395006,0.8165760869565217,0.05169468085166391 +flat_mae,patch,logistic,aabc_sex,29,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,29,2.782559402207126,test,0.8727272727272727,0.045176970656363724,0.8699763593380614,0.04601626646262724,0.8722826086956521,0.04554198286042417 +flat_mae,patch,logistic,aabc_sex,30,0.005994842503189409,train,0.9243856332703214,0.01118573616427131,0.9220798350272499,0.011577559249244605,0.9200445499575016,0.011853176426346129 +flat_mae,patch,logistic,aabc_sex,30,0.005994842503189409,test,0.8545454545454545,0.04929889945630941,0.8521505376344086,0.05002573040084873,0.8566576086956521,0.04968821287355245 +flat_mae,patch,logistic,aabc_sex,31,0.005994842503189409,train,0.9187145557655955,0.011801111226424278,0.9161793372319689,0.01226065112960182,0.9139262580966616,0.012635341573147045 +flat_mae,patch,logistic,aabc_sex,31,0.005994842503189409,test,0.8181818181818182,0.04893232297168157,0.8151881720430108,0.04943589054650981,0.8192934782608696,0.04883158441903988 +flat_mae,patch,logistic,aabc_sex,32,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,32,2.782559402207126,test,0.8727272727272727,0.040381175550533124,0.8639095086603039,0.0454640231143023,0.8539402173913043,0.04593545648593131 +flat_mae,patch,logistic,aabc_sex,33,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,33,2.782559402207126,test,0.8727272727272727,0.042992891974494775,0.8639095086603039,0.048667803791494386,0.8539402173913043,0.049242298579422986 +flat_mae,patch,logistic,aabc_sex,34,0.046415888336127774,train,0.9489603024574669,0.009557742695402134,0.9475747398557507,0.009832366516116174,0.9467598698672295,0.01003096339463264 +flat_mae,patch,logistic,aabc_sex,34,0.046415888336127774,test,0.9090909090909091,0.03946449811628482,0.905982905982906,0.04114296822957627,0.9035326086956521,0.04188197505602587 +flat_mae,patch,logistic,aabc_sex,35,0.046415888336127774,train,0.9508506616257089,0.009320920756678147,0.9495480822842386,0.009583017231147037,0.9490020223335971,0.009790021889860664 +flat_mae,patch,logistic,aabc_sex,35,0.046415888336127774,test,0.8727272727272727,0.04495361797002595,0.8683760683760684,0.04684389018125935,0.8661684782608696,0.0473314864027336 +flat_mae,patch,logistic,aabc_sex,36,0.005994842503189409,train,0.9035916824196597,0.011945358327775428,0.900308545034642,0.012470987645734927,0.8972053694422463,0.012839315202071992 +flat_mae,patch,logistic,aabc_sex,36,0.005994842503189409,test,0.9454545454545454,0.029110993067145142,0.9447975911676145,0.029120815115645973,0.953125,0.025017259667077848 +flat_mae,patch,logistic,aabc_sex,37,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,37,21.54434690031882,test,0.7818181818181819,0.055726308756307415,0.7758152173913043,0.05772022448411101,0.7758152173913043,0.057739640071292286 +flat_mae,patch,logistic,aabc_sex,38,0.005994842503189409,train,0.9206049149338374,0.012192860010766773,0.9181838267786124,0.012636977611593148,0.9161684105630294,0.012957771248565494 +flat_mae,patch,logistic,aabc_sex,38,0.005994842503189409,test,0.8727272727272727,0.03842621350455337,0.8609606356085229,0.045946520475160735,0.8478260869565217,0.045944385711966004 +flat_mae,patch,logistic,aabc_sex,39,0.005994842503189409,train,0.9149338374291115,0.011954535725731656,0.9121602922455305,0.012447145221210862,0.9094419531639262,0.012825652183572787 +flat_mae,patch,logistic,aabc_sex,39,0.005994842503189409,test,0.8545454545454545,0.04493468538237718,0.8484848484848485,0.047644316975713745,0.8444293478260869,0.04804545468819149 +flat_mae,patch,logistic,aabc_sex,40,0.005994842503189409,train,0.9168241965973535,0.011841289499909433,0.9141715094840557,0.012329955784419741,0.911684105630294,0.012739183469825789 +flat_mae,patch,logistic,aabc_sex,40,0.005994842503189409,test,0.8909090909090909,0.04055313420951426,0.8863636363636364,0.042888060399667256,0.8817934782608696,0.04388967871138887 +flat_mae,patch,logistic,aabc_sex,41,0.005994842503189409,train,0.9111531190926276,0.012627247767993757,0.9081274826789838,0.01315032287131397,0.9049576482311907,0.013481843794345687 +flat_mae,patch,logistic,aabc_sex,41,0.005994842503189409,test,0.9272727272727272,0.03416641819435285,0.9252717391304348,0.03524888199023617,0.9252717391304348,0.035489316032539533 +flat_mae,patch,logistic,aabc_sex,42,0.005994842503189409,train,0.9224952741020794,0.01150289627239933,0.9198558891454965,0.012008315477750518,0.9165860664146077,0.01246521474855681 +flat_mae,patch,logistic,aabc_sex,42,0.005994842503189409,test,0.8,0.05223843618329353,0.7989365237620472,0.05225509975885865,0.8097826086956521,0.05120275560762482 +flat_mae,patch,logistic,aabc_sex,43,0.046415888336127774,train,0.9508506616257089,0.009496604561295424,0.9496101878718604,0.009741106322358424,0.9496101878718604,0.009913892761115413 +flat_mae,patch,logistic,aabc_sex,43,0.046415888336127774,test,0.9090909090909091,0.03864609503115451,0.905982905982906,0.04048164460660702,0.9035326086956521,0.041341957165139276 +flat_mae,patch,logistic,aabc_sex,44,0.046415888336127774,train,0.9546313799621928,0.009127333753858564,0.9533701592525121,0.009403800692635696,0.9522699961898062,0.009655852228396551 +flat_mae,patch,logistic,aabc_sex,44,0.046415888336127774,test,0.8363636363636363,0.04723460000906672,0.8307692307692308,0.04929775705928655,0.8288043478260869,0.049386314312881055 +flat_mae,patch,logistic,aabc_sex,45,0.046415888336127774,train,0.9508506616257089,0.009813407040931737,0.9496101878718604,0.010072010531878497,0.9496101878718604,0.010234609381197602 +flat_mae,patch,logistic,aabc_sex,45,0.046415888336127774,test,0.9454545454545454,0.029636051309006792,0.9442755825734549,0.030153074846303876,0.9470108695652174,0.029203401300312418 +flat_mae,patch,logistic,aabc_sex,46,0.3593813663804626,train,0.994328922495274,0.003397425105386065,0.9941893034853195,0.0034786360996861545,0.9944898736774231,0.003362262473237597 +flat_mae,patch,logistic,aabc_sex,46,0.3593813663804626,test,0.8909090909090909,0.04417059341138683,0.8879076086956521,0.045656459689068216,0.8879076086956521,0.046057127244062676 +flat_mae,patch,logistic,aabc_sex,47,0.005994842503189409,train,0.9206049149338374,0.011660933618939169,0.9180728045075076,0.012121713122196525,0.9155602450247662,0.01253998712024415 +flat_mae,patch,logistic,aabc_sex,47,0.005994842503189409,test,0.8545454545454545,0.04417958842110063,0.84593837535014,0.04852819167835517,0.8383152173913043,0.04881317694160748 +flat_mae,patch,logistic,aabc_sex,48,0.046415888336127774,train,0.947069943289225,0.009670515849257938,0.9456671655368724,0.009938996593265133,0.9451258829391249,0.010108801075806785 +flat_mae,patch,logistic,aabc_sex,48,0.046415888336127774,test,0.9454545454545454,0.029484855336509224,0.9435897435897436,0.03076348751065444,0.9408967391304348,0.032068083736800514 +flat_mae,patch,logistic,aabc_sex,49,0.3593813663804626,train,0.9924385633270322,0.003602409609971727,0.9922570257611241,0.003683848363686642,0.9928558867493186,0.00345835570704134 +flat_mae,patch,logistic,aabc_sex,49,0.3593813663804626,test,0.8545454545454545,0.048321293836325684,0.8521505376344086,0.0490418392808871,0.8566576086956521,0.04859489092625449 +flat_mae,patch,logistic,aabc_sex,50,0.3593813663804626,train,0.994328922495274,0.0030584562577701834,0.9941893034853195,0.003130940007070459,0.9944898736774231,0.0029921385019799508 +flat_mae,patch,logistic,aabc_sex,50,0.3593813663804626,test,0.8363636363636363,0.050045929318200406,0.8328267477203647,0.05113469514307957,0.8349184782608696,0.05101152473430231 +flat_mae,patch,logistic,aabc_sex,51,0.005994842503189409,train,0.9092627599243857,0.012139523336763061,0.9061057862974795,0.0126994275413426,0.9027154957648231,0.013152254998495528 +flat_mae,patch,logistic,aabc_sex,51,0.005994842503189409,test,0.9272727272727272,0.03307692012004896,0.9229691876750701,0.03672999300755881,0.9130434782608696,0.03954849144788462 +flat_mae,patch,logistic,aabc_sex,52,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,52,21.54434690031882,test,0.8727272727272727,0.04428457933572529,0.8711943793911007,0.044542313857261914,0.8783967391304348,0.0433679367100539 +flat_mae,patch,logistic,aabc_sex,53,0.3593813663804626,train,0.996219281663516,0.0026626136678187763,0.9961285128805621,0.002721877634271188,0.9967320261437909,0.002301507565810669 +flat_mae,patch,logistic,aabc_sex,53,0.3593813663804626,test,0.8727272727272727,0.044530995798172525,0.8699763593380614,0.0456411318074383,0.8722826086956521,0.0455899116659409 +flat_mae,patch,logistic,aabc_sex,54,0.046415888336127774,train,0.9584120982986768,0.008783651871087924,0.9573624666608048,0.009011708619846499,0.9573624666608048,0.009165903431900907 +flat_mae,patch,logistic,aabc_sex,54,0.046415888336127774,test,0.8181818181818182,0.052206975247210095,0.8166666666666667,0.05218672838856008,0.8254076086956521,0.05040407039614957 +flat_mae,patch,logistic,aabc_sex,55,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,55,2.782559402207126,test,0.8363636363636363,0.04793885913198217,0.8307692307692308,0.05009338609620308,0.8288043478260869,0.0502515547574218 +flat_mae,patch,logistic,aabc_sex,56,0.3593813663804626,train,0.998109640831758,0.0018688033754851864,0.998060743809227,0.0019196440158559733,0.9977578475336323,0.0022165851695777135 +flat_mae,patch,logistic,aabc_sex,56,0.3593813663804626,test,0.8545454545454545,0.046759097757981746,0.8505434782608696,0.04837743093584775,0.8505434782608696,0.04869409677615898 +flat_mae,patch,logistic,aabc_sex,57,0.046415888336127774,train,0.9527410207939508,0.009197190087306715,0.9514580924590283,0.009465189184826197,0.9506360092617017,0.009660450202204263 +flat_mae,patch,logistic,aabc_sex,57,0.046415888336127774,test,0.8545454545454545,0.0469619997603126,0.8505434782608696,0.048491533225318836,0.8505434782608696,0.048781053118725604 +flat_mae,patch,logistic,aabc_sex,58,0.3593813663804626,train,0.994328922495274,0.0034063642785538196,0.9941893034853195,0.0034872490559057522,0.9944898736774231,0.003330794804173136 +flat_mae,patch,logistic,aabc_sex,58,0.3593813663804626,test,0.7818181818181819,0.055979346840841854,0.78,0.055913953560239045,0.7880434782608696,0.054889272925712246 +flat_mae,patch,logistic,aabc_sex,59,0.005994842503189409,train,0.9092627599243857,0.012221267198169749,0.9061057862974795,0.01278357304450476,0.9027154957648231,0.013195142260768372 +flat_mae,patch,logistic,aabc_sex,59,0.005994842503189409,test,0.9090909090909091,0.03843338768904192,0.905982905982906,0.0401744775158635,0.9035326086956521,0.04106417990276156 +flat_mae,patch,logistic,aabc_sex,60,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,60,2.782559402207126,test,0.8545454545454545,0.04934887105476845,0.8484848484848485,0.05224656122858452,0.8444293478260869,0.05243715463936776 +flat_mae,patch,logistic,aabc_sex,61,0.005994842503189409,train,0.9054820415879017,0.013081815936007346,0.9023322107999527,0.013624044472469805,0.899447521908614,0.013961781987718582 +flat_mae,patch,logistic,aabc_sex,61,0.005994842503189409,test,0.9636363636363636,0.02531063213698058,0.9626358695652174,0.026022461191530157,0.9626358695652174,0.0261650091948636 +flat_mae,patch,logistic,aabc_sex,62,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,62,21.54434690031882,test,0.9090909090909091,0.039228662147520375,0.905982905982906,0.041272523437060164,0.9035326086956521,0.04239079274356835 +flat_mae,patch,logistic,aabc_sex,63,0.046415888336127774,train,0.9508506616257089,0.009586431640565196,0.9496101878718604,0.009832319396221124,0.9496101878718604,0.009949155216827928 +flat_mae,patch,logistic,aabc_sex,63,0.046415888336127774,test,0.8909090909090909,0.04165404943952921,0.8863636363636364,0.044492796260203214,0.8817934782608696,0.04560488492804874 +flat_mae,patch,logistic,aabc_sex,64,0.3593813663804626,train,0.996219281663516,0.002548260251916649,0.9961238606055277,0.00261258871503736,0.9961238606055277,0.002654227683205732 +flat_mae,patch,logistic,aabc_sex,64,0.3593813663804626,test,0.8727272727272727,0.04414827009143296,0.8720505151213027,0.043999652408152776,0.8845108695652174,0.040741872815095906 +flat_mae,patch,logistic,aabc_sex,65,0.005994842503189409,train,0.9073724007561437,0.012502278764991565,0.904218013856813,0.013061210059096922,0.9010815088367186,0.013478567589829077 +flat_mae,patch,logistic,aabc_sex,65,0.005994842503189409,test,0.9090909090909091,0.03826477568013747,0.9045470322804582,0.041497043154271794,0.8974184782608696,0.043090696607070364 +flat_mae,patch,logistic,aabc_sex,66,0.005994842503189409,train,0.9111531190926276,0.012151806884939328,0.9081274826789838,0.012660316447519674,0.9049576482311907,0.012982750265821139 +flat_mae,patch,logistic,aabc_sex,66,0.005994842503189409,test,0.8909090909090909,0.03801967302844782,0.884453781512605,0.04192477312390346,0.8756793478260869,0.04330364176496135 +flat_mae,patch,logistic,aabc_sex,67,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,67,2.782559402207126,test,0.8545454545454545,0.04737738066152566,0.8521505376344086,0.04792496597265691,0.8566576086956521,0.04743389673568413 +flat_mae,patch,logistic,aabc_sex,68,0.005994842503189409,train,0.9130434782608695,0.01259455055199236,0.9101456339359566,0.01314903473520846,0.9071998006975586,0.01362603900898278 +flat_mae,patch,logistic,aabc_sex,68,0.005994842503189409,test,0.9454545454545454,0.031105068546077808,0.9427282193682749,0.03394496212456062,0.9347826086956521,0.03719084282683216 +flat_mae,patch,logistic,aabc_sex,69,0.005994842503189409,train,0.9054820415879017,0.012688200575870072,0.9021935273932079,0.01325651055013065,0.8988393563703508,0.013648659678049627 +flat_mae,patch,logistic,aabc_sex,69,0.005994842503189409,test,0.9454545454545454,0.03036744668525523,0.9435897435897436,0.03189169077445457,0.9408967391304348,0.03358300441958605 +flat_mae,patch,logistic,aabc_sex,70,0.3593813663804626,train,0.9924385633270322,0.0037109228640460554,0.9922570257611241,0.003795548560827541,0.9928558867493186,0.0035762968390789284 +flat_mae,patch,logistic,aabc_sex,70,0.3593813663804626,test,0.8909090909090909,0.04170064113505187,0.8891129032258065,0.04219482788134156,0.8940217391304348,0.04121312552005411 +flat_mae,patch,logistic,aabc_sex,71,0.005994842503189409,train,0.9187145557655955,0.011767157699967529,0.9161793372319689,0.012190430089073745,0.9139262580966616,0.012461476318956166 +flat_mae,patch,logistic,aabc_sex,71,0.005994842503189409,test,0.8545454545454545,0.04695381940827382,0.8484848484848485,0.04964478745814904,0.8444293478260869,0.04967264805793455 +flat_mae,patch,logistic,aabc_sex,72,0.005994842503189409,train,0.9111531190926276,0.012076478432367295,0.9081274826789838,0.01262374192867187,0.9049576482311907,0.013037122746714421 +flat_mae,patch,logistic,aabc_sex,72,0.005994842503189409,test,0.9090909090909091,0.038291720616454354,0.905982905982906,0.04005179686179571,0.9035326086956521,0.041101666329433906 +flat_mae,patch,logistic,aabc_sex,73,0.3593813663804626,train,0.9924385633270322,0.003750914663866126,0.9922570257611241,0.0038357900759580666,0.9928558867493186,0.0035993572542669843 +flat_mae,patch,logistic,aabc_sex,73,0.3593813663804626,test,0.8909090909090909,0.03780872259323543,0.8821428571428571,0.04395642673888715,0.8695652173913043,0.04520608136147715 +flat_mae,patch,logistic,aabc_sex,74,0.005994842503189409,train,0.9168241965973535,0.011648598733406875,0.9140523455039584,0.012140293143092565,0.9110759400920307,0.012538547996910796 +flat_mae,patch,logistic,aabc_sex,74,0.005994842503189409,test,0.9090909090909091,0.03945050670572994,0.905982905982906,0.04122527157904843,0.9035326086956521,0.04222734334658748 +flat_mae,patch,logistic,aabc_sex,75,0.3593813663804626,train,0.994328922495274,0.003267422253781212,0.9941893034853195,0.003346103186348423,0.9944898736774231,0.003237453493993717 +flat_mae,patch,logistic,aabc_sex,75,0.3593813663804626,test,0.9090909090909091,0.03646451461964469,0.9071259709557582,0.03727505265281507,0.9096467391304348,0.03708450931046663 +flat_mae,patch,logistic,aabc_sex,76,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,76,166.81005372000556,test,0.8909090909090909,0.03917042230396648,0.884453781512605,0.04333527693939028,0.8756793478260869,0.04475086058285178 +flat_mae,patch,logistic,aabc_sex,77,0.000774263682681127,train,0.8865784499054821,0.013541506591075588,0.8822874944370271,0.014193899661847092,0.8782423283214631,0.014540558632366543 +flat_mae,patch,logistic,aabc_sex,77,0.000774263682681127,test,0.9090909090909091,0.03861227484356551,0.9045470322804582,0.041686657760974404,0.8974184782608696,0.04336821013993287 +flat_mae,patch,logistic,aabc_sex,78,0.046415888336127774,train,0.947069943289225,0.009570419321167114,0.945734048477388,0.009820090380302475,0.945734048477388,0.010013235856359918 +flat_mae,patch,logistic,aabc_sex,78,0.046415888336127774,test,0.9636363636363636,0.025706390497242017,0.9626358695652174,0.026540339045327124,0.9626358695652174,0.02723542260642285 +flat_mae,patch,logistic,aabc_sex,79,0.3593813663804626,train,0.994328922495274,0.0033216574562756284,0.9941893034853195,0.0034015306961548654,0.9944898736774231,0.003287297729046818 +flat_mae,patch,logistic,aabc_sex,79,0.3593813663804626,test,0.9090909090909091,0.03863268003830629,0.905982905982906,0.0404626736943188,0.9035326086956521,0.04151462324140386 +flat_mae,patch,logistic,aabc_sex,80,0.3593813663804626,train,0.996219281663516,0.0026985828910675957,0.9961285128805621,0.0027581549739984974,0.9967320261437909,0.0023325986100894694 +flat_mae,patch,logistic,aabc_sex,80,0.3593813663804626,test,0.9090909090909091,0.03905750792894799,0.905982905982906,0.04065828746560567,0.9035326086956521,0.04128828337757451 +flat_mae,patch,logistic,aabc_sex,81,0.005994842503189409,train,0.9035916824196597,0.012722089675463243,0.900308545034642,0.01324641916117821,0.8972053694422463,0.0135609109054026 +flat_mae,patch,logistic,aabc_sex,81,0.005994842503189409,test,0.9454545454545454,0.0316801369059568,0.9435897435897436,0.03315235830077053,0.9408967391304348,0.03468729433235747 +flat_mae,patch,logistic,aabc_sex,82,0.046415888336127774,train,0.945179584120983,0.00944778062162697,0.9437615704675844,0.009697022725760484,0.9434918960110203,0.009823061041741379 +flat_mae,patch,logistic,aabc_sex,82,0.046415888336127774,test,0.9454545454545454,0.027356936660947163,0.9427282193682749,0.02963889793733553,0.9347826086956521,0.03270938079026291 +flat_mae,patch,logistic,aabc_sex,83,0.005994842503189409,train,0.9130434782608695,0.012441288822928121,0.9103918102813374,0.01288560866012556,0.9084161317740849,0.0131407766895048 +flat_mae,patch,logistic,aabc_sex,83,0.005994842503189409,test,0.8363636363636363,0.050267265854917184,0.8281846581048247,0.053724367620689606,0.8226902173913043,0.053326287049421654 +flat_mae,patch,logistic,aabc_sex,84,0.005994842503189409,train,0.9168241965973535,0.012357392830675131,0.9140523455039584,0.012860169114549716,0.9110759400920307,0.01320692719452188 +flat_mae,patch,logistic,aabc_sex,84,0.005994842503189409,test,0.8545454545454545,0.04703901668731064,0.84593837535014,0.05153895521612,0.8383152173913043,0.05177717234427552 +flat_mae,patch,logistic,aabc_sex,85,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,85,21.54434690031882,test,0.8727272727272727,0.0454850806527093,0.8683760683760684,0.04739327598986589,0.8661684782608696,0.047867431699131865 +flat_mae,patch,logistic,aabc_sex,86,0.3593813663804626,train,0.9924385633270322,0.0038070463254123864,0.9922570257611241,0.0038943101063456183,0.9928558867493186,0.0036853233676000605 +flat_mae,patch,logistic,aabc_sex,86,0.3593813663804626,test,0.9090909090909091,0.03964155095330494,0.905982905982906,0.0414572076291978,0.9035326086956521,0.04245339620666587 +flat_mae,patch,logistic,aabc_sex,87,0.005994842503189409,train,0.9149338374291115,0.012432916823884893,0.9121602922455305,0.01293860650994832,0.9094419531639262,0.013348636380354086 +flat_mae,patch,logistic,aabc_sex,87,0.005994842503189409,test,0.9090909090909091,0.03812116394466292,0.905982905982906,0.039860536595707305,0.9035326086956521,0.04071843125906204 +flat_mae,patch,logistic,aabc_sex,88,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,88,2.782559402207126,test,0.8545454545454545,0.04696312603108494,0.84593837535014,0.0514854424399647,0.8383152173913043,0.05158592904444072 +flat_mae,patch,logistic,aabc_sex,89,0.046415888336127774,train,0.9489603024574669,0.009989439143810624,0.9476400828491303,0.010252237925354036,0.9473680354054925,0.01040100955184164 +flat_mae,patch,logistic,aabc_sex,89,0.046415888336127774,test,0.8727272727272727,0.03977874344109006,0.8609606356085229,0.04769197901313258,0.8478260869565217,0.04756154107086856 +flat_mae,patch,logistic,aabc_sex,90,0.3593813663804626,train,0.994328922495274,0.0032588037619607413,0.9941893034853195,0.003335934411840426,0.9944898736774231,0.00318363790548241 +flat_mae,patch,logistic,aabc_sex,90,0.3593813663804626,test,0.8181818181818182,0.0524067877756181,0.8131793478260869,0.054381696129473855,0.8131793478260869,0.05464387537290644 +flat_mae,patch,logistic,aabc_sex,91,0.046415888336127774,train,0.9508506616257089,0.009616444190592866,0.9496101878718604,0.009856616912010115,0.9496101878718604,0.00992368518037381 +flat_mae,patch,logistic,aabc_sex,91,0.046415888336127774,test,0.8909090909090909,0.042825249368463394,0.8863636363636364,0.045282555918791816,0.8817934782608696,0.0460380098557039 +flat_mae,patch,logistic,aabc_sex,92,0.3593813663804626,train,0.9924385633270322,0.0036369861931188695,0.9922570257611241,0.0037196527120785076,0.9928558867493186,0.003490515467595137 +flat_mae,patch,logistic,aabc_sex,92,0.3593813663804626,test,0.9090909090909091,0.03713900624847099,0.905982905982906,0.0388883413802114,0.9035326086956521,0.03987116898218594 +flat_mae,patch,logistic,aabc_sex,93,0.005994842503189409,train,0.9168241965973535,0.012582594149176325,0.9141715094840557,0.013058045358323295,0.911684105630294,0.013348286692999813 +flat_mae,patch,logistic,aabc_sex,93,0.005994842503189409,test,0.8909090909090909,0.04240068610079537,0.884453781512605,0.046758251855734144,0.8756793478260869,0.04800878508566021 +flat_mae,patch,logistic,aabc_sex,94,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,94,2.782559402207126,test,0.9272727272727272,0.03316417463678003,0.9252717391304348,0.034210226628930904,0.9252717391304348,0.0344897299973835 +flat_mae,patch,logistic,aabc_sex,95,0.046415888336127774,train,0.9527410207939508,0.009128899666258001,0.9514580924590283,0.009403973968764462,0.9506360092617017,0.009661854906936844 +flat_mae,patch,logistic,aabc_sex,95,0.046415888336127774,test,0.8909090909090909,0.04064927596358435,0.8879076086956521,0.04188686244696155,0.8879076086956521,0.04200561672683881 +flat_mae,patch,logistic,aabc_sex,96,0.005994842503189409,train,0.9168241965973535,0.012188962624142298,0.9140523455039584,0.012696778674256367,0.9110759400920307,0.013059884114887343 +flat_mae,patch,logistic,aabc_sex,96,0.005994842503189409,test,0.9090909090909091,0.03917496248818132,0.905982905982906,0.04082068657018065,0.9035326086956521,0.0415421272530122 +flat_mae,patch,logistic,aabc_sex,97,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,97,21.54434690031882,test,0.8727272727272727,0.04463588594449074,0.8711943793911007,0.04494122137472313,0.8783967391304348,0.04337333628518834 +flat_mae,patch,logistic,aabc_sex,98,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,98,2.782559402207126,test,0.8727272727272727,0.04363187855738371,0.8663658451926415,0.047106348141746836,0.8600543478260869,0.047952190989900806 +flat_mae,patch,logistic,aabc_sex,99,0.005994842503189409,train,0.9168241965973535,0.012605168944747574,0.9141715094840557,0.013080398236097768,0.911684105630294,0.013385419465285906 +flat_mae,patch,logistic,aabc_sex,99,0.005994842503189409,test,0.9090909090909091,0.038232883600766404,0.9027925061859314,0.043677507200051424,0.8913043478260869,0.04571323039222069 +flat_mae,patch,logistic,aabc_sex,100,0.005994842503189409,train,0.9187145557655955,0.012003048963302452,0.9159464203233256,0.012553454900237267,0.9127099270201353,0.013084581174850987 +flat_mae,patch,logistic,aabc_sex,100,0.005994842503189409,test,0.8909090909090909,0.04118740078556881,0.8891129032258065,0.04168347179019156,0.8940217391304348,0.04052573939511523 diff --git a/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_sex__patch__logistic/log.txt b/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_sex__patch__logistic/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..c0cb14e9494e1b3c7611504ee4b355b302663a01 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_sex__patch__logistic/log.txt @@ -0,0 +1,245 @@ +fMRI foundation model logistic probe eval +version: 0.1.dev86+gf97f52698 +sha: bcce2b486277d3a5b520775efd9cdf1a2affce36, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-04-08 22:02:48 +config: +output_root: experiments/input_space_v3/output +name_prefix: eval_logistic +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_1; eval v2 (aabc_sex patch logistic) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: input_space_v3/flat_lr1e-3_1/eval_v2/aabc_sex__patch__logistic +model: flat_mae +representation: patch +dataset: aabc_sex +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/aabc_sex__patch__logistic +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=True, reg_tokens=0, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: aabc_sex (flat) +train (n=471): +HFDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'segment', 'bold', 'mean', 'std'], + num_rows: 471 +}), + labels=[0 1], + counts=[269 202] +) + +validation (n=58): +HFDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'segment', 'bold', 'mean', 'std'], + num_rows: 58 +}), + labels=[0 1], + counts=[36 22] +) + +test (n=55): +HFDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'segment', 'bold', 'mean', 'std'], + num_rows: 55 +}), + labels=[0 1], + counts=[33 22] +) + +extracting features for all splits +extract (train) [ 0/236] eta: 0:27:28 time: 6.9866 data: 5.9351 max mem: 3205 +extract (train) [ 20/236] eta: 0:02:16 time: 0.3159 data: 0.1290 max mem: 3393 +extract (train) [ 40/236] eta: 0:01:26 time: 0.2389 data: 0.0838 max mem: 3393 +extract (train) [ 60/236] eta: 0:01:06 time: 0.2398 data: 0.0847 max mem: 3393 +extract (train) [ 80/236] eta: 0:00:52 time: 0.2199 data: 0.0752 max mem: 3393 +extract (train) [100/236] eta: 0:00:43 time: 0.2525 data: 0.0908 max mem: 3393 +extract (train) [120/236] eta: 0:00:35 time: 0.2172 data: 0.0741 max mem: 3393 +extract (train) [140/236] eta: 0:00:28 time: 0.2386 data: 0.0840 max mem: 3393 +extract (train) [160/236] eta: 0:00:22 time: 0.2709 data: 0.1011 max mem: 3393 +extract (train) [180/236] eta: 0:00:16 time: 0.2751 data: 0.1020 max mem: 3393 +extract (train) [200/236] eta: 0:00:10 time: 0.2708 data: 0.0994 max mem: 3393 +extract (train) [220/236] eta: 0:00:04 time: 0.2139 data: 0.0676 max mem: 3393 +extract (train) [235/236] eta: 0:00:00 time: 0.2064 data: 0.0661 max mem: 3393 +extract (train) Total time: 0:01:05 (0.2791 s / it) +extract (validation) [ 0/29] eta: 0:02:49 time: 5.8313 data: 5.6122 max mem: 3393 +extract (validation) [20/29] eta: 0:00:04 time: 0.2371 data: 0.0817 max mem: 3393 +extract (validation) [28/29] eta: 0:00:00 time: 0.2040 data: 0.0672 max mem: 3393 +extract (validation) Total time: 0:00:12 (0.4396 s / it) +extract (test) [ 0/28] eta: 0:02:39 time: 5.7028 data: 5.5453 max mem: 3393 +extract (test) [20/28] eta: 0:00:03 time: 0.2385 data: 0.0901 max mem: 3393 +extract (test) [27/28] eta: 0:00:00 time: 0.2106 data: 0.0754 max mem: 3393 +extract (test) Total time: 0:00:12 (0.4429 s / it) +feature extraction time: 0:01:31 +train features: (471, 768) +validation features: (58, 768) +test features: (55, 768) +evaluating fixed splits +eval results (fixed splits): + +| model | repr | clf | dataset | trial | C | split | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|-------:|:--------|--------:|----------:|-------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | aabc_sex | | 2.7826 | train | 1 | 0 | 1 | 0 | 1 | 0 | +| flat_mae | patch | logistic | aabc_sex | | 2.7826 | test | 0.98182 | 0.018236 | 0.9812 | 0.018631 | 0.98485 | 0.015197 | + + +evaluating random splits (n=100) +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 1, "C": 0.3593813663804626, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.048407239401212276, "f1": 0.8307692307692308, "f1_std": 0.05073489798417324, "bacc": 0.8288043478260869, "bacc_std": 0.050783296381626285} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 2, "C": 21.54434690031882, "split": "test", "acc": 0.9272727272727272, "acc_std": 0.0353856860447767, "f1": 0.9260752688172043, "f1_std": 0.03573551023220552, "bacc": 0.9313858695652174, "bacc_std": 0.03420827335714145} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 3, "C": 0.3593813663804626, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.04981478422389005, "f1": 0.8281846581048247, "f1_std": 0.053588622915386894, "bacc": 0.8226902173913043, "bacc_std": 0.05371862551203422} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 4, "C": 0.005994842503189409, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.049053130244428415, "f1": 0.8521505376344086, "f1_std": 0.049355777433201735, "bacc": 0.8566576086956521, "bacc_std": 0.04818348065463546} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 5, "C": 0.046415888336127774, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.0447266223160396, "f1": 0.8663658451926415, "f1_std": 0.04814473548321278, "bacc": 0.8600543478260869, "bacc_std": 0.04905479270055572} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 6, "C": 0.3593813663804626, "split": "test", "acc": 0.9272727272727272, "acc_std": 0.03665158718221091, "f1": 0.9252717391304348, "f1_std": 0.037676477828171816, "bacc": 0.9252717391304348, "bacc_std": 0.03793582409885245} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 7, "C": 0.005994842503189409, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.04726187287972379, "f1": 0.8484848484848485, "f1_std": 0.050149524267093536, "bacc": 0.8444293478260869, "bacc_std": 0.050437037491613365} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 8, "C": 0.005994842503189409, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.045858265295012704, "f1": 0.8521505376344086, "f1_std": 0.04638234499419379, "bacc": 0.8566576086956521, "bacc_std": 0.04609714182836298} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 9, "C": 0.3593813663804626, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.03859131063074105, "f1": 0.905982905982906, "f1_std": 0.0402361986123722, "bacc": 0.9035326086956521, "bacc_std": 0.04113998536435305} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 10, "C": 0.3593813663804626, "split": "test", "acc": 0.9454545454545454, "acc_std": 0.02871325319588342, "f1": 0.9435897435897436, "f1_std": 0.029899947742777263, "bacc": 0.9408967391304348, "bacc_std": 0.030996496914842624} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 11, "C": 0.046415888336127774, "split": "test", "acc": 0.9454545454545454, "acc_std": 0.03091488715706213, "f1": 0.9435897435897436, "f1_std": 0.03233676076163877, "bacc": 0.9408967391304348, "bacc_std": 0.03368639204805854} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 12, "C": 21.54434690031882, "split": "test", "acc": 0.8181818181818182, "acc_std": 0.05215468410775932, "f1": 0.8106060606060606, "f1_std": 0.05551496676886814, "bacc": 0.8070652173913043, "bacc_std": 0.05561450464576429} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 13, "C": 0.046415888336127774, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.04593831293203224, "f1": 0.8484848484848485, "f1_std": 0.04817113584286549, "bacc": 0.8444293478260869, "bacc_std": 0.048309051878182976} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 14, "C": 0.046415888336127774, "split": "test", "acc": 0.9454545454545454, "acc_std": 0.030822874408089524, "f1": 0.9442755825734549, "f1_std": 0.031362397895195265, "bacc": 0.9470108695652174, "bacc_std": 0.03035665668891174} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 15, "C": 0.3593813663804626, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.03842139555460781, "f1": 0.9071259709557582, "f1_std": 0.039140143088070616, "bacc": 0.9096467391304348, "bacc_std": 0.0385358136660011} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 16, "C": 0.3593813663804626, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.04039828160980109, "f1": 0.884453781512605, "f1_std": 0.0445160889506563, "bacc": 0.8756793478260869, "bacc_std": 0.04597494581773473} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 17, "C": 2.782559402207126, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.03642066437324325, "f1": 0.9045470322804582, "f1_std": 0.03953597459509306, "bacc": 0.8974184782608696, "bacc_std": 0.04113794738454493} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 18, "C": 0.000774263682681127, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.04425290203865701, "f1": 0.8711943793911007, "f1_std": 0.04443531354761817, "bacc": 0.8783967391304348, "bacc_std": 0.04283113976051379} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 19, "C": 0.046415888336127774, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.04330619027001195, "f1": 0.8711943793911007, "f1_std": 0.0435022813079782, "bacc": 0.8783967391304348, "bacc_std": 0.04215863482067107} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 20, "C": 21.54434690031882, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.05017343803545376, "f1": 0.8328267477203647, "f1_std": 0.05137990131322007, "bacc": 0.8349184782608696, "bacc_std": 0.051167154525668744} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 21, "C": 0.005994842503189409, "split": "test", "acc": 0.8, "acc_std": 0.0518411304845617, "f1": 0.790003471017008, "f1_std": 0.05582040684415123, "bacc": 0.7853260869565217, "bacc_std": 0.05523019886877215} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 22, "C": 0.046415888336127774, "split": "test", "acc": 0.9636363636363636, "acc_std": 0.026259757729900295, "f1": 0.9626358695652174, "f1_std": 0.027077372978828982, "bacc": 0.9626358695652174, "bacc_std": 0.027412093937197488} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 23, "C": 0.3593813663804626, "split": "test", "acc": 0.9636363636363636, "acc_std": 0.025883042727362, "f1": 0.9626358695652174, "f1_std": 0.02661787356522646, "bacc": 0.9626358695652174, "bacc_std": 0.02682501323928264} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 24, "C": 0.046415888336127774, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.04437941597163565, "f1": 0.8663658451926415, "f1_std": 0.04788913918531563, "bacc": 0.8600543478260869, "bacc_std": 0.04862966265227339} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 25, "C": 0.046415888336127774, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.03718519211187021, "f1": 0.905982905982906, "f1_std": 0.03885529002851244, "bacc": 0.9035326086956521, "bacc_std": 0.03962913093877616} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 26, "C": 0.046415888336127774, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.048307609379547437, "f1": 0.8307692307692308, "f1_std": 0.05071198843845818, "bacc": 0.8288043478260869, "bacc_std": 0.05097988034242785} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 27, "C": 0.046415888336127774, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.03627232171110708, "f1": 0.905982905982906, "f1_std": 0.03789855769254333, "bacc": 0.9035326086956521, "bacc_std": 0.038683346961095245} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 28, "C": 0.005994842503189409, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.046125893124458014, "f1": 0.8250265111346766, "f1_std": 0.0520884930395006, "bacc": 0.8165760869565217, "bacc_std": 0.05169468085166391} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 29, "C": 2.782559402207126, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.045176970656363724, "f1": 0.8699763593380614, "f1_std": 0.04601626646262724, "bacc": 0.8722826086956521, "bacc_std": 0.04554198286042417} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 30, "C": 0.005994842503189409, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.04929889945630941, "f1": 0.8521505376344086, "f1_std": 0.05002573040084873, "bacc": 0.8566576086956521, "bacc_std": 0.04968821287355245} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 31, "C": 0.005994842503189409, "split": "test", "acc": 0.8181818181818182, "acc_std": 0.04893232297168157, "f1": 0.8151881720430108, "f1_std": 0.04943589054650981, "bacc": 0.8192934782608696, "bacc_std": 0.04883158441903988} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 32, "C": 2.782559402207126, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.040381175550533124, "f1": 0.8639095086603039, "f1_std": 0.0454640231143023, "bacc": 0.8539402173913043, "bacc_std": 0.04593545648593131} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 33, "C": 2.782559402207126, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.042992891974494775, "f1": 0.8639095086603039, "f1_std": 0.048667803791494386, "bacc": 0.8539402173913043, "bacc_std": 0.049242298579422986} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 34, "C": 0.046415888336127774, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.03946449811628482, "f1": 0.905982905982906, "f1_std": 0.04114296822957627, "bacc": 0.9035326086956521, "bacc_std": 0.04188197505602587} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 35, "C": 0.046415888336127774, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.04495361797002595, "f1": 0.8683760683760684, "f1_std": 0.04684389018125935, "bacc": 0.8661684782608696, "bacc_std": 0.0473314864027336} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 36, "C": 0.005994842503189409, "split": "test", "acc": 0.9454545454545454, "acc_std": 0.029110993067145142, "f1": 0.9447975911676145, "f1_std": 0.029120815115645973, "bacc": 0.953125, "bacc_std": 0.025017259667077848} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 37, "C": 21.54434690031882, "split": "test", "acc": 0.7818181818181819, "acc_std": 0.055726308756307415, "f1": 0.7758152173913043, "f1_std": 0.05772022448411101, "bacc": 0.7758152173913043, "bacc_std": 0.057739640071292286} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 38, "C": 0.005994842503189409, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.03842621350455337, "f1": 0.8609606356085229, "f1_std": 0.045946520475160735, "bacc": 0.8478260869565217, "bacc_std": 0.045944385711966004} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 39, "C": 0.005994842503189409, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.04493468538237718, "f1": 0.8484848484848485, "f1_std": 0.047644316975713745, "bacc": 0.8444293478260869, "bacc_std": 0.04804545468819149} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 40, "C": 0.005994842503189409, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.04055313420951426, "f1": 0.8863636363636364, "f1_std": 0.042888060399667256, "bacc": 0.8817934782608696, "bacc_std": 0.04388967871138887} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 41, "C": 0.005994842503189409, "split": "test", "acc": 0.9272727272727272, "acc_std": 0.03416641819435285, "f1": 0.9252717391304348, "f1_std": 0.03524888199023617, "bacc": 0.9252717391304348, "bacc_std": 0.035489316032539533} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 42, "C": 0.005994842503189409, "split": "test", "acc": 0.8, "acc_std": 0.05223843618329353, "f1": 0.7989365237620472, "f1_std": 0.05225509975885865, "bacc": 0.8097826086956521, "bacc_std": 0.05120275560762482} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 43, "C": 0.046415888336127774, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.03864609503115451, "f1": 0.905982905982906, "f1_std": 0.04048164460660702, "bacc": 0.9035326086956521, "bacc_std": 0.041341957165139276} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 44, "C": 0.046415888336127774, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.04723460000906672, "f1": 0.8307692307692308, "f1_std": 0.04929775705928655, "bacc": 0.8288043478260869, "bacc_std": 0.049386314312881055} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 45, "C": 0.046415888336127774, "split": "test", "acc": 0.9454545454545454, "acc_std": 0.029636051309006792, "f1": 0.9442755825734549, "f1_std": 0.030153074846303876, "bacc": 0.9470108695652174, "bacc_std": 0.029203401300312418} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 46, "C": 0.3593813663804626, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.04417059341138683, "f1": 0.8879076086956521, "f1_std": 0.045656459689068216, "bacc": 0.8879076086956521, "bacc_std": 0.046057127244062676} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 47, "C": 0.005994842503189409, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.04417958842110063, "f1": 0.84593837535014, "f1_std": 0.04852819167835517, "bacc": 0.8383152173913043, "bacc_std": 0.04881317694160748} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 48, "C": 0.046415888336127774, "split": "test", "acc": 0.9454545454545454, "acc_std": 0.029484855336509224, "f1": 0.9435897435897436, "f1_std": 0.03076348751065444, "bacc": 0.9408967391304348, "bacc_std": 0.032068083736800514} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 49, "C": 0.3593813663804626, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.048321293836325684, "f1": 0.8521505376344086, "f1_std": 0.0490418392808871, "bacc": 0.8566576086956521, "bacc_std": 0.04859489092625449} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 50, "C": 0.3593813663804626, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.050045929318200406, "f1": 0.8328267477203647, "f1_std": 0.05113469514307957, "bacc": 0.8349184782608696, "bacc_std": 0.05101152473430231} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 51, "C": 0.005994842503189409, "split": "test", "acc": 0.9272727272727272, "acc_std": 0.03307692012004896, "f1": 0.9229691876750701, "f1_std": 0.03672999300755881, "bacc": 0.9130434782608696, "bacc_std": 0.03954849144788462} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 52, "C": 21.54434690031882, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.04428457933572529, "f1": 0.8711943793911007, "f1_std": 0.044542313857261914, "bacc": 0.8783967391304348, "bacc_std": 0.0433679367100539} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 53, "C": 0.3593813663804626, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.044530995798172525, "f1": 0.8699763593380614, "f1_std": 0.0456411318074383, "bacc": 0.8722826086956521, "bacc_std": 0.0455899116659409} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 54, "C": 0.046415888336127774, "split": "test", "acc": 0.8181818181818182, "acc_std": 0.052206975247210095, "f1": 0.8166666666666667, "f1_std": 0.05218672838856008, "bacc": 0.8254076086956521, "bacc_std": 0.05040407039614957} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 55, "C": 2.782559402207126, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.04793885913198217, "f1": 0.8307692307692308, "f1_std": 0.05009338609620308, "bacc": 0.8288043478260869, "bacc_std": 0.0502515547574218} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 56, "C": 0.3593813663804626, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.046759097757981746, "f1": 0.8505434782608696, "f1_std": 0.04837743093584775, "bacc": 0.8505434782608696, "bacc_std": 0.04869409677615898} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 57, "C": 0.046415888336127774, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.0469619997603126, "f1": 0.8505434782608696, "f1_std": 0.048491533225318836, "bacc": 0.8505434782608696, "bacc_std": 0.048781053118725604} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 58, "C": 0.3593813663804626, "split": "test", "acc": 0.7818181818181819, "acc_std": 0.055979346840841854, "f1": 0.78, "f1_std": 0.055913953560239045, "bacc": 0.7880434782608696, "bacc_std": 0.054889272925712246} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 59, "C": 0.005994842503189409, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.03843338768904192, "f1": 0.905982905982906, "f1_std": 0.0401744775158635, "bacc": 0.9035326086956521, "bacc_std": 0.04106417990276156} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 60, "C": 2.782559402207126, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.04934887105476845, "f1": 0.8484848484848485, "f1_std": 0.05224656122858452, "bacc": 0.8444293478260869, "bacc_std": 0.05243715463936776} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 61, "C": 0.005994842503189409, "split": "test", "acc": 0.9636363636363636, "acc_std": 0.02531063213698058, "f1": 0.9626358695652174, "f1_std": 0.026022461191530157, "bacc": 0.9626358695652174, "bacc_std": 0.0261650091948636} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 62, "C": 21.54434690031882, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.039228662147520375, "f1": 0.905982905982906, "f1_std": 0.041272523437060164, "bacc": 0.9035326086956521, "bacc_std": 0.04239079274356835} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 63, "C": 0.046415888336127774, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.04165404943952921, "f1": 0.8863636363636364, "f1_std": 0.044492796260203214, "bacc": 0.8817934782608696, "bacc_std": 0.04560488492804874} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 64, "C": 0.3593813663804626, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.04414827009143296, "f1": 0.8720505151213027, "f1_std": 0.043999652408152776, "bacc": 0.8845108695652174, "bacc_std": 0.040741872815095906} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 65, "C": 0.005994842503189409, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.03826477568013747, "f1": 0.9045470322804582, "f1_std": 0.041497043154271794, "bacc": 0.8974184782608696, "bacc_std": 0.043090696607070364} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 66, "C": 0.005994842503189409, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.03801967302844782, "f1": 0.884453781512605, "f1_std": 0.04192477312390346, "bacc": 0.8756793478260869, "bacc_std": 0.04330364176496135} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 67, "C": 2.782559402207126, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.04737738066152566, "f1": 0.8521505376344086, "f1_std": 0.04792496597265691, "bacc": 0.8566576086956521, "bacc_std": 0.04743389673568413} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 68, "C": 0.005994842503189409, "split": "test", "acc": 0.9454545454545454, "acc_std": 0.031105068546077808, "f1": 0.9427282193682749, "f1_std": 0.03394496212456062, "bacc": 0.9347826086956521, "bacc_std": 0.03719084282683216} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 69, "C": 0.005994842503189409, "split": "test", "acc": 0.9454545454545454, "acc_std": 0.03036744668525523, "f1": 0.9435897435897436, "f1_std": 0.03189169077445457, "bacc": 0.9408967391304348, "bacc_std": 0.03358300441958605} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 70, "C": 0.3593813663804626, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.04170064113505187, "f1": 0.8891129032258065, "f1_std": 0.04219482788134156, "bacc": 0.8940217391304348, "bacc_std": 0.04121312552005411} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 71, "C": 0.005994842503189409, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.04695381940827382, "f1": 0.8484848484848485, "f1_std": 0.04964478745814904, "bacc": 0.8444293478260869, "bacc_std": 0.04967264805793455} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 72, "C": 0.005994842503189409, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.038291720616454354, "f1": 0.905982905982906, "f1_std": 0.04005179686179571, "bacc": 0.9035326086956521, "bacc_std": 0.041101666329433906} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 73, "C": 0.3593813663804626, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.03780872259323543, "f1": 0.8821428571428571, "f1_std": 0.04395642673888715, "bacc": 0.8695652173913043, "bacc_std": 0.04520608136147715} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 74, "C": 0.005994842503189409, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.03945050670572994, "f1": 0.905982905982906, "f1_std": 0.04122527157904843, "bacc": 0.9035326086956521, "bacc_std": 0.04222734334658748} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 75, "C": 0.3593813663804626, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.03646451461964469, "f1": 0.9071259709557582, "f1_std": 0.03727505265281507, "bacc": 0.9096467391304348, "bacc_std": 0.03708450931046663} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 76, "C": 166.81005372000556, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.03917042230396648, "f1": 0.884453781512605, "f1_std": 0.04333527693939028, "bacc": 0.8756793478260869, "bacc_std": 0.04475086058285178} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 77, "C": 0.000774263682681127, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.03861227484356551, "f1": 0.9045470322804582, "f1_std": 0.041686657760974404, "bacc": 0.8974184782608696, "bacc_std": 0.04336821013993287} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 78, "C": 0.046415888336127774, "split": "test", "acc": 0.9636363636363636, "acc_std": 0.025706390497242017, "f1": 0.9626358695652174, "f1_std": 0.026540339045327124, "bacc": 0.9626358695652174, "bacc_std": 0.02723542260642285} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 79, "C": 0.3593813663804626, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.03863268003830629, "f1": 0.905982905982906, "f1_std": 0.0404626736943188, "bacc": 0.9035326086956521, "bacc_std": 0.04151462324140386} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 80, "C": 0.3593813663804626, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.03905750792894799, "f1": 0.905982905982906, "f1_std": 0.04065828746560567, "bacc": 0.9035326086956521, "bacc_std": 0.04128828337757451} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 81, "C": 0.005994842503189409, "split": "test", "acc": 0.9454545454545454, "acc_std": 0.0316801369059568, "f1": 0.9435897435897436, "f1_std": 0.03315235830077053, "bacc": 0.9408967391304348, "bacc_std": 0.03468729433235747} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 82, "C": 0.046415888336127774, "split": "test", "acc": 0.9454545454545454, "acc_std": 0.027356936660947163, "f1": 0.9427282193682749, "f1_std": 0.02963889793733553, "bacc": 0.9347826086956521, "bacc_std": 0.03270938079026291} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 83, "C": 0.005994842503189409, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.050267265854917184, "f1": 0.8281846581048247, "f1_std": 0.053724367620689606, "bacc": 0.8226902173913043, "bacc_std": 0.053326287049421654} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 84, "C": 0.005994842503189409, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.04703901668731064, "f1": 0.84593837535014, "f1_std": 0.05153895521612, "bacc": 0.8383152173913043, "bacc_std": 0.05177717234427552} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 85, "C": 21.54434690031882, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.0454850806527093, "f1": 0.8683760683760684, "f1_std": 0.04739327598986589, "bacc": 0.8661684782608696, "bacc_std": 0.047867431699131865} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 86, "C": 0.3593813663804626, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.03964155095330494, "f1": 0.905982905982906, "f1_std": 0.0414572076291978, "bacc": 0.9035326086956521, "bacc_std": 0.04245339620666587} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 87, "C": 0.005994842503189409, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.03812116394466292, "f1": 0.905982905982906, "f1_std": 0.039860536595707305, "bacc": 0.9035326086956521, "bacc_std": 0.04071843125906204} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 88, "C": 2.782559402207126, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.04696312603108494, "f1": 0.84593837535014, "f1_std": 0.0514854424399647, "bacc": 0.8383152173913043, "bacc_std": 0.05158592904444072} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 89, "C": 0.046415888336127774, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.03977874344109006, "f1": 0.8609606356085229, "f1_std": 0.04769197901313258, "bacc": 0.8478260869565217, "bacc_std": 0.04756154107086856} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 90, "C": 0.3593813663804626, "split": "test", "acc": 0.8181818181818182, "acc_std": 0.0524067877756181, "f1": 0.8131793478260869, "f1_std": 0.054381696129473855, "bacc": 0.8131793478260869, "bacc_std": 0.05464387537290644} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 91, "C": 0.046415888336127774, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.042825249368463394, "f1": 0.8863636363636364, "f1_std": 0.045282555918791816, "bacc": 0.8817934782608696, "bacc_std": 0.0460380098557039} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 92, "C": 0.3593813663804626, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.03713900624847099, "f1": 0.905982905982906, "f1_std": 0.0388883413802114, "bacc": 0.9035326086956521, "bacc_std": 0.03987116898218594} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 93, "C": 0.005994842503189409, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.04240068610079537, "f1": 0.884453781512605, "f1_std": 0.046758251855734144, "bacc": 0.8756793478260869, "bacc_std": 0.04800878508566021} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 94, "C": 2.782559402207126, "split": "test", "acc": 0.9272727272727272, "acc_std": 0.03316417463678003, "f1": 0.9252717391304348, "f1_std": 0.034210226628930904, "bacc": 0.9252717391304348, "bacc_std": 0.0344897299973835} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 95, "C": 0.046415888336127774, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.04064927596358435, "f1": 0.8879076086956521, "f1_std": 0.04188686244696155, "bacc": 0.8879076086956521, "bacc_std": 0.04200561672683881} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 96, "C": 0.005994842503189409, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.03917496248818132, "f1": 0.905982905982906, "f1_std": 0.04082068657018065, "bacc": 0.9035326086956521, "bacc_std": 0.0415421272530122} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 97, "C": 21.54434690031882, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.04463588594449074, "f1": 0.8711943793911007, "f1_std": 0.04494122137472313, "bacc": 0.8783967391304348, "bacc_std": 0.04337333628518834} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 98, "C": 2.782559402207126, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.04363187855738371, "f1": 0.8663658451926415, "f1_std": 0.047106348141746836, "bacc": 0.8600543478260869, "bacc_std": 0.047952190989900806} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 99, "C": 0.005994842503189409, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.038232883600766404, "f1": 0.9027925061859314, "f1_std": 0.043677507200051424, "bacc": 0.8913043478260869, "bacc_std": 0.04571323039222069} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 100, "C": 0.005994842503189409, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.04118740078556881, "f1": 0.8891129032258065, "f1_std": 0.04168347179019156, "bacc": 0.8940217391304348, "bacc_std": 0.04052573939511523} +eval results (random splits): + +| model | repr | clf | dataset | split | n_trials | C | C_std | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|-----------:|-------:|--------:|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | aabc_sex | train | 100 | 3.7656 | 17.466 | 0.95749 | 0.036918 | 0.95616 | 0.038165 | 0.95517 | 0.039502 | +| flat_mae | patch | logistic | aabc_sex | test | 100 | 3.7656 | 17.466 | 0.88473 | 0.041927 | 0.88061 | 0.043185 | 0.8788 | 0.043075 | + + +done! total time: 0:05:37 diff --git a/input_space_v3/flat_lr1e-3_1/eval_v2/abide_dx__patch__attn/config.yaml b/input_space_v3/flat_lr1e-3_1/eval_v2/abide_dx__patch__attn/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..29606b5559fa0a22602c56875a6acf9a1b33e22a --- /dev/null +++ b/input_space_v3/flat_lr1e-3_1/eval_v2/abide_dx__patch__attn/config.yaml @@ -0,0 +1,98 @@ +output_root: experiments/input_space_v3/output +name_prefix: eval_probe +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_1; eval v2 (abide_dx patch attn) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +dataset_kwargs: {} +classifier_kwargs: + embed_dim: null + dropout: 0.0 + xavier_init: true + norm: true +lr_scale_grid: +- 0.02 +- 0.023 +- 0.028 +- 0.033 +- 0.038 +- 0.045 +- 0.053 +- 0.062 +- 0.074 +- 0.087 +- 0.1 +- 0.12 +- 0.14 +- 0.17 +- 0.2 +- 0.23 +- 0.27 +- 0.32 +- 0.38 +- 0.44 +- 0.52 +- 0.61 +- 0.72 +- 0.85 +- 1 +- 1.2 +- 1.4 +- 1.6 +- 1.9 +- 2.3 +- 2.7 +- 3.1 +- 3.7 +- 4.3 +- 5.1 +- 6 +- 7.1 +- 8.3 +- 9.8 +- 12 +- 14 +- 16 +- 19 +- 22 +- 26 +- 31 +- 36 +- 43 +- 50 +wd_scale_grid: +- 1.0 +num_workers: 8 +prefetch_factor: null +balanced_sampling: false +epochs: 20 +steps_per_epoch: 200 +batch_size: 4 +accum_iter: 4 +lr: 0.0003 +warmup_epochs: 5 +no_decay: false +weight_decay: 0.05 +clip_grad: 1.0 +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +early_stopping: true +amp: true +device: cuda +seed: 4466 +debug: false +wandb: false +wandb_entity: null +wandb_project: fMRI-fm-eval +name: input_space_v3/flat_lr1e-3_1/eval_v2/abide_dx__patch__attn +base_lr: 3.0e-05 +model: flat_mae +representation: patch +classifier: attn +dataset: abide_dx +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/abide_dx__patch__attn +remote_dir: null diff --git a/input_space_v3/flat_lr1e-3_1/eval_v2/abide_dx__patch__attn/eval_log.json b/input_space_v3/flat_lr1e-3_1/eval_v2/abide_dx__patch__attn/eval_log.json new file mode 100644 index 0000000000000000000000000000000000000000..eb83ab72cb74e913801795903c55e1f8a0b9642e --- /dev/null +++ b/input_space_v3/flat_lr1e-3_1/eval_v2/abide_dx__patch__attn/eval_log.json @@ -0,0 +1 @@ +{"eval/epoch": 0, "eval/id_best": 48, "eval/lr_best": 0.015, "eval/wd_best": 0.05, "eval/train/loss": 0.626124918460846, "eval/train/acc": 0.6505190311418685, "eval/train/acc_std": 0.020118449008742073, "eval/train/f1": 0.6493055555555556, "eval/train/f1_std": 0.020149910289164078, "eval/train/bacc": 0.6511731978713111, "eval/train/bacc_std": 0.020236117130520388, "eval/validation/loss": 0.6461275219917297, "eval/validation/acc": 0.6774193548387096, "eval/validation/acc_std": 0.04282742211863544, "eval/validation/f1": 0.6704756842944459, "eval/validation/f1_std": 0.04436330139575299, "eval/validation/bacc": 0.6698412698412699, "eval/validation/bacc_std": 0.04420273868397583, "eval/test/loss": 0.6715538501739502, "eval/test/acc": 0.5564516129032258, "eval/test/acc_std": 0.04404195804773512, "eval/test/f1": 0.5550336008351275, "eval/test/f1_std": 0.044325605632155256, "eval/test/bacc": 0.5555119141136423, "eval/test/bacc_std": 0.044348267611726576} diff --git a/input_space_v3/flat_lr1e-3_1/eval_v2/abide_dx__patch__attn/eval_log_best.json b/input_space_v3/flat_lr1e-3_1/eval_v2/abide_dx__patch__attn/eval_log_best.json new file mode 100644 index 0000000000000000000000000000000000000000..d8b6daf570547470da81eac2f1d14933aba7db00 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_1/eval_v2/abide_dx__patch__attn/eval_log_best.json @@ -0,0 +1 @@ +{"eval/best/epoch": 0, "eval/best/id_best": 48, "eval/best/lr_best": 0.015, "eval/best/wd_best": 0.05, "eval/best/train/loss": 0.626124918460846, "eval/best/train/acc": 0.6505190311418685, "eval/best/train/acc_std": 0.020118449008742073, "eval/best/train/f1": 0.6493055555555556, "eval/best/train/f1_std": 0.020149910289164078, "eval/best/train/bacc": 0.6511731978713111, "eval/best/train/bacc_std": 0.020236117130520388, "eval/best/validation/loss": 0.6461275219917297, "eval/best/validation/acc": 0.6774193548387096, "eval/best/validation/acc_std": 0.04282742211863544, "eval/best/validation/f1": 0.6704756842944459, "eval/best/validation/f1_std": 0.04436330139575299, "eval/best/validation/bacc": 0.6698412698412699, "eval/best/validation/bacc_std": 0.04420273868397583, "eval/best/test/loss": 0.6715538501739502, "eval/best/test/acc": 0.5564516129032258, "eval/best/test/acc_std": 0.04404195804773512, "eval/best/test/f1": 0.5550336008351275, "eval/best/test/f1_std": 0.044325605632155256, "eval/best/test/bacc": 0.5555119141136423, "eval/best/test/bacc_std": 0.044348267611726576} diff --git a/input_space_v3/flat_lr1e-3_1/eval_v2/abide_dx__patch__attn/eval_log_last.json b/input_space_v3/flat_lr1e-3_1/eval_v2/abide_dx__patch__attn/eval_log_last.json new file mode 100644 index 0000000000000000000000000000000000000000..07bd58178cf09965f42b2593727db607ff1f4663 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_1/eval_v2/abide_dx__patch__attn/eval_log_last.json @@ -0,0 +1 @@ +{"eval/last/epoch": 19, "eval/last/id_best": 16, "eval/last/lr_best": 8.1e-05, "eval/last/wd_best": 0.05, "eval/last/train/loss": 0.5259659290313721, "eval/last/train/acc": 0.7370242214532872, "eval/last/train/acc_std": 0.017968448339085136, "eval/last/train/f1": 0.731622678396872, "eval/last/train/f1_std": 0.01832202865740958, "eval/last/train/bacc": 0.7301402999516207, "eval/last/train/bacc_std": 0.018142942033252348, "eval/last/validation/loss": 0.6350160241127014, "eval/last/validation/acc": 0.6612903225806451, "eval/last/validation/acc_std": 0.040964770021744826, "eval/last/validation/f1": 0.6457142857142857, "eval/last/validation/f1_std": 0.04364776207603223, "eval/last/validation/bacc": 0.644973544973545, "eval/last/validation/bacc_std": 0.042227495314595895, "eval/last/test/loss": 0.6814483404159546, "eval/last/test/acc": 0.5725806451612904, "eval/last/test/acc_std": 0.043023149759083286, "eval/last/test/f1": 0.5599598259122867, "eval/last/test/f1_std": 0.04534407631797194, "eval/last/test/bacc": 0.5625818277035873, "eval/last/test/bacc_std": 0.04362542719262019} diff --git a/input_space_v3/flat_lr1e-3_1/eval_v2/abide_dx__patch__attn/eval_table.csv b/input_space_v3/flat_lr1e-3_1/eval_v2/abide_dx__patch__attn/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..e5b0f1448bb13d563d3418561f4a34294fe47b7a --- /dev/null +++ b/input_space_v3/flat_lr1e-3_1/eval_v2/abide_dx__patch__attn/eval_table.csv @@ -0,0 +1,4 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std,bacc,bacc_std +flat_mae,patch,attn,abide_dx,best,0,0.015,0.05,48,"[50, 1.0]",train,0.626124918460846,0.6505190311418685,0.020118449008742073,0.6493055555555556,0.020149910289164078,0.6511731978713111,0.020236117130520388 +flat_mae,patch,attn,abide_dx,best,0,0.015,0.05,48,"[50, 1.0]",validation,0.6461275219917297,0.6774193548387096,0.04282742211863544,0.6704756842944459,0.04436330139575299,0.6698412698412699,0.04420273868397583 +flat_mae,patch,attn,abide_dx,best,0,0.015,0.05,48,"[50, 1.0]",test,0.6715538501739502,0.5564516129032258,0.04404195804773512,0.5550336008351275,0.044325605632155256,0.5555119141136423,0.044348267611726576 diff --git a/input_space_v3/flat_lr1e-3_1/eval_v2/abide_dx__patch__attn/eval_table_best.csv b/input_space_v3/flat_lr1e-3_1/eval_v2/abide_dx__patch__attn/eval_table_best.csv new file mode 100644 index 0000000000000000000000000000000000000000..e5b0f1448bb13d563d3418561f4a34294fe47b7a --- /dev/null +++ b/input_space_v3/flat_lr1e-3_1/eval_v2/abide_dx__patch__attn/eval_table_best.csv @@ -0,0 +1,4 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std,bacc,bacc_std +flat_mae,patch,attn,abide_dx,best,0,0.015,0.05,48,"[50, 1.0]",train,0.626124918460846,0.6505190311418685,0.020118449008742073,0.6493055555555556,0.020149910289164078,0.6511731978713111,0.020236117130520388 +flat_mae,patch,attn,abide_dx,best,0,0.015,0.05,48,"[50, 1.0]",validation,0.6461275219917297,0.6774193548387096,0.04282742211863544,0.6704756842944459,0.04436330139575299,0.6698412698412699,0.04420273868397583 +flat_mae,patch,attn,abide_dx,best,0,0.015,0.05,48,"[50, 1.0]",test,0.6715538501739502,0.5564516129032258,0.04404195804773512,0.5550336008351275,0.044325605632155256,0.5555119141136423,0.044348267611726576 diff --git a/input_space_v3/flat_lr1e-3_1/eval_v2/abide_dx__patch__attn/eval_table_last.csv b/input_space_v3/flat_lr1e-3_1/eval_v2/abide_dx__patch__attn/eval_table_last.csv new file mode 100644 index 0000000000000000000000000000000000000000..600f42ce87e3d76907b2d6f6464c7e6b5c7a85e6 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_1/eval_v2/abide_dx__patch__attn/eval_table_last.csv @@ -0,0 +1,4 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std,bacc,bacc_std +flat_mae,patch,attn,abide_dx,last,19,8.1e-05,0.05,16,"[0.27, 1.0]",train,0.5259659290313721,0.7370242214532872,0.017968448339085136,0.731622678396872,0.01832202865740958,0.7301402999516207,0.018142942033252348 +flat_mae,patch,attn,abide_dx,last,19,8.1e-05,0.05,16,"[0.27, 1.0]",validation,0.6350160241127014,0.6612903225806451,0.040964770021744826,0.6457142857142857,0.04364776207603223,0.644973544973545,0.042227495314595895 +flat_mae,patch,attn,abide_dx,last,19,8.1e-05,0.05,16,"[0.27, 1.0]",test,0.6814483404159546,0.5725806451612904,0.043023149759083286,0.5599598259122867,0.04534407631797194,0.5625818277035873,0.04362542719262019 diff --git a/input_space_v3/flat_lr1e-3_1/eval_v2/abide_dx__patch__attn/log.txt b/input_space_v3/flat_lr1e-3_1/eval_v2/abide_dx__patch__attn/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..86496ad18500c8d2518f664c3cfd87948047fee5 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_1/eval_v2/abide_dx__patch__attn/log.txt @@ -0,0 +1,1224 @@ +fMRI foundation model probe eval +version: 0.1.dev95+g65be98d36 +sha: 28a47a6a336052f679e36c7962a91fe73a2e9637, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-04-24 07:15:12 +config: +output_root: experiments/input_space_v3/output +name_prefix: eval_probe +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_1; eval v2 (abide_dx patch attn) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +dataset_kwargs: {} +classifier_kwargs: + embed_dim: null + dropout: 0.0 + xavier_init: true + norm: true +lr_scale_grid: +- 0.02 +- 0.023 +- 0.028 +- 0.033 +- 0.038 +- 0.045 +- 0.053 +- 0.062 +- 0.074 +- 0.087 +- 0.1 +- 0.12 +- 0.14 +- 0.17 +- 0.2 +- 0.23 +- 0.27 +- 0.32 +- 0.38 +- 0.44 +- 0.52 +- 0.61 +- 0.72 +- 0.85 +- 1 +- 1.2 +- 1.4 +- 1.6 +- 1.9 +- 2.3 +- 2.7 +- 3.1 +- 3.7 +- 4.3 +- 5.1 +- 6 +- 7.1 +- 8.3 +- 9.8 +- 12 +- 14 +- 16 +- 19 +- 22 +- 26 +- 31 +- 36 +- 43 +- 50 +wd_scale_grid: +- 1.0 +num_workers: 8 +prefetch_factor: null +balanced_sampling: false +epochs: 20 +steps_per_epoch: 200 +batch_size: 4 +accum_iter: 4 +lr: 0.0003 +warmup_epochs: 5 +no_decay: false +weight_decay: 0.05 +clip_grad: 1.0 +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +early_stopping: true +amp: true +device: cuda +seed: 4466 +debug: false +wandb: false +wandb_entity: null +wandb_project: fMRI-fm-eval +name: input_space_v3/flat_lr1e-3_1/eval_v2/abide_dx__patch__attn +base_lr: 3.0e-05 +model: flat_mae +representation: patch +classifier: attn +dataset: abide_dx +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/abide_dx__patch__attn +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=True, reg_tokens=0, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: abide_dx (flat) +train (n=578): +HFDataset( + dataset=Dataset({ + features: ['sub', 'site', 'dataset', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 578 +}), + labels=['Autism' 'Control'], + counts=[260 318] +) + +validation (n=124): +HFDataset( + dataset=Dataset({ + features: ['sub', 'site', 'dataset', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 124 +}), + labels=['Autism' 'Control'], + counts=[54 70] +) + +test (n=124): +HFDataset( + dataset=Dataset({ + features: ['sub', 'site', 'dataset', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 124 +}), + labels=['Autism' 'Control'], + counts=[57 67] +) + +running backbone on example batch to get embedding dim +embedding feature dim (patch): 768 +initializing sweep of classifier heads +classifiers: +ModuleList( + (0-48): 49 x AttnPoolClassifier( + (kv): Linear(in_features=768, out_features=1536, bias=True) + (linear): Linear(in_features=768, out_features=2, bias=True) + ) +) +classifier params (train): 58.0M (58.0M) +setting up optimizer +total batch size: 16 = 4 bs per gpu x 4 accum +lr: 3.00e-04 +full schedule: epochs = 20 (steps = 4000) (decay = True) +warmup: epochs = 5 (steps = 1000) +start training for 20 epochs +train: [0] [ 0/800] eta: 1:04:59 lr: nan time: 4.8745 data: 4.2005 max mem: 24352 +train: [0] [ 20/800] eta: 0:09:47 lr: 0.000001 loss: 0.6859 (0.6969) grad: 0.2407 (0.2499) time: 0.5477 data: 0.0069 max mem: 25051 +train: [0] [ 40/800] eta: 0:08:02 lr: 0.000003 loss: 0.7045 (0.7001) grad: 0.2449 (0.2850) time: 0.5094 data: 0.0028 max mem: 25051 +train: [0] [ 60/800] eta: 0:07:20 lr: 0.000004 loss: 0.7045 (0.7019) grad: 0.2449 (0.2845) time: 0.5141 data: 0.0034 max mem: 25051 +train: [0] [ 80/800] eta: 0:06:53 lr: 0.000006 loss: 0.7014 (0.7020) grad: 0.2958 (0.3265) time: 0.5108 data: 0.0032 max mem: 25051 +train: [0] [100/800] eta: 0:06:30 lr: 0.000007 loss: 0.7014 (0.6963) grad: 0.3200 (0.3576) time: 0.4917 data: 0.0031 max mem: 25051 +train: [0] [120/800] eta: 0:06:13 lr: 0.000009 loss: 0.6975 (0.6944) grad: 0.2629 (0.3397) time: 0.5063 data: 0.0030 max mem: 25051 +train: [0] [140/800] eta: 0:05:57 lr: 0.000010 loss: 0.6951 (0.6959) grad: 0.2971 (0.3574) time: 0.4970 data: 0.0029 max mem: 25051 +train: [0] [160/800] eta: 0:05:59 lr: 0.000012 loss: 0.6975 (0.7009) grad: 0.2971 (0.3587) time: 0.7028 data: 0.2178 max mem: 25051 +train: [0] [180/800] eta: 0:05:44 lr: 0.000013 loss: 0.7070 (0.7049) grad: 0.2862 (0.3511) time: 0.4980 data: 0.0027 max mem: 25051 +train: [0] [200/800] eta: 0:05:35 lr: 0.000015 loss: 0.7124 (0.7053) grad: 0.2862 (0.3382) time: 0.5917 data: 0.1004 max mem: 25051 +train: [0] [220/800] eta: 0:05:21 lr: 0.000016 loss: 0.7155 (0.7046) grad: 0.2770 (0.3303) time: 0.5087 data: 0.0025 max mem: 25051 +train: [0] [240/800] eta: 0:05:07 lr: 0.000018 loss: 0.7106 (0.7052) grad: 0.1994 (0.3171) time: 0.4897 data: 0.0030 max mem: 25051 +train: [0] [260/800] eta: 0:04:54 lr: 0.000019 loss: 0.6967 (0.7039) grad: 0.1922 (0.3141) time: 0.5002 data: 0.0028 max mem: 25051 +train: [0] [280/800] eta: 0:04:42 lr: 0.000021 loss: 0.7023 (0.7051) grad: 0.1754 (0.3125) time: 0.5260 data: 0.0029 max mem: 25051 +train: [0] [300/800] eta: 0:04:38 lr: 0.000022 loss: 0.6967 (0.7049) grad: 0.1736 (0.3057) time: 0.7409 data: 0.2189 max mem: 25051 +train: [0] [320/800] eta: 0:04:26 lr: 0.000024 loss: 0.6966 (0.7048) grad: 0.1867 (0.2995) time: 0.5305 data: 0.0027 max mem: 25051 +train: [0] [340/800] eta: 0:04:14 lr: 0.000025 loss: 0.6966 (0.7027) grad: 0.1867 (0.2955) time: 0.5071 data: 0.0028 max mem: 25051 +train: [0] [360/800] eta: 0:04:01 lr: 0.000027 loss: 0.6955 (0.7026) grad: 0.2030 (0.2915) time: 0.5071 data: 0.0030 max mem: 25051 +train: [0] [380/800] eta: 0:03:49 lr: 0.000028 loss: 0.6941 (0.7019) grad: 0.2367 (0.2895) time: 0.5018 data: 0.0031 max mem: 25051 +train: [0] [400/800] eta: 0:03:37 lr: 0.000030 loss: 0.6911 (0.7010) grad: 0.2880 (0.2926) time: 0.4806 data: 0.0030 max mem: 25051 +train: [0] [420/800] eta: 0:03:25 lr: 0.000031 loss: 0.6911 (0.7000) grad: 0.2880 (0.2926) time: 0.4938 data: 0.0029 max mem: 25051 +train: [0] [440/800] eta: 0:03:18 lr: 0.000033 loss: 0.6757 (0.6994) grad: 0.2961 (0.2953) time: 0.7856 data: 0.2475 max mem: 25051 +train: [0] [460/800] eta: 0:03:07 lr: 0.000034 loss: 0.6911 (0.7006) grad: 0.2936 (0.2934) time: 0.5022 data: 0.0023 max mem: 25051 +train: [0] [480/800] eta: 0:02:55 lr: 0.000036 loss: 0.6971 (0.7019) grad: 0.2534 (0.2930) time: 0.5038 data: 0.0033 max mem: 25051 +train: [0] [500/800] eta: 0:02:43 lr: 0.000037 loss: 0.6977 (0.7016) grad: 0.2633 (0.2930) time: 0.4961 data: 0.0032 max mem: 25051 +train: [0] [520/800] eta: 0:02:33 lr: 0.000039 loss: 0.6971 (0.6997) grad: 0.2170 (0.2895) time: 0.5528 data: 0.0031 max mem: 25051 +train: [0] [540/800] eta: 0:02:21 lr: 0.000040 loss: 0.6627 (0.6974) grad: 0.2236 (0.2887) time: 0.5242 data: 0.0033 max mem: 25051 +train: [0] [560/800] eta: 0:02:10 lr: 0.000042 loss: 0.6627 (0.6982) grad: 0.2444 (0.2876) time: 0.5010 data: 0.0031 max mem: 25051 +train: [0] [580/800] eta: 0:02:01 lr: 0.000043 loss: 0.6601 (0.6978) grad: 0.2125 (0.2848) time: 0.7282 data: 0.2254 max mem: 25051 +train: [0] [600/800] eta: 0:01:49 lr: 0.000045 loss: 0.6816 (0.6979) grad: 0.2157 (0.2830) time: 0.5080 data: 0.0032 max mem: 25051 +train: [0] [620/800] eta: 0:01:38 lr: 0.000046 loss: 0.7022 (0.6981) grad: 0.2130 (0.2820) time: 0.5066 data: 0.0017 max mem: 25051 +train: [0] [640/800] eta: 0:01:27 lr: 0.000048 loss: 0.6816 (0.6967) grad: 0.2157 (0.2815) time: 0.4988 data: 0.0030 max mem: 25051 +train: [0] [660/800] eta: 0:01:16 lr: 0.000049 loss: 0.6816 (0.6951) grad: 0.2470 (0.2833) time: 0.5217 data: 0.0029 max mem: 25051 +train: [0] [680/800] eta: 0:01:05 lr: 0.000051 loss: 0.6707 (0.6948) grad: 0.2728 (0.2836) time: 0.5339 data: 0.0032 max mem: 25051 +train: [0] [700/800] eta: 0:00:54 lr: 0.000052 loss: 0.6603 (0.6932) grad: 0.3023 (0.2858) time: 0.4966 data: 0.0032 max mem: 25051 +train: [0] [720/800] eta: 0:00:43 lr: 0.000054 loss: 0.6707 (0.6942) grad: 0.3096 (0.2874) time: 0.7545 data: 0.2801 max mem: 25051 +train: [0] [740/800] eta: 0:00:32 lr: 0.000055 loss: 0.6869 (0.6939) grad: 0.3096 (0.2881) time: 0.5233 data: 0.0019 max mem: 25051 +train: [0] [760/800] eta: 0:00:21 lr: 0.000057 loss: 0.6910 (0.6945) grad: 0.2810 (0.2872) time: 0.4877 data: 0.0032 max mem: 25051 +train: [0] [780/800] eta: 0:00:10 lr: 0.000058 loss: 0.7040 (0.6950) grad: 0.2603 (0.2878) time: 0.4877 data: 0.0032 max mem: 25051 +train: [0] [799/800] eta: 0:00:00 lr: 0.000060 loss: 0.6869 (0.6933) grad: 0.2611 (0.2877) time: 0.4956 data: 0.0030 max mem: 25051 +train: [0] Total time: 0:07:15 (0.5449 s / it) +train: [0] Summary: lr: 0.000060 loss: 0.6869 (0.6933) grad: 0.2611 (0.2877) +eval (validation): [0] [ 0/31] eta: 0:02:18 time: 4.4592 data: 4.1613 max mem: 25051 +eval (validation): [0] [20/31] eta: 0:00:07 time: 0.4599 data: 0.0381 max mem: 25051 +eval (validation): [0] [30/31] eta: 0:00:00 time: 0.4020 data: 0.0019 max mem: 25051 +eval (validation): [0] Total time: 0:00:17 (0.5601 s / it) +cv: [0] best hparam: (50, 1.0) (048) ('048_lr5.0e+01_wd1.0e+00') loss: 0.646 acc: 0.677 f1: 0.670 bacc: 0.670 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/abide_dx__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/abide_dx__patch__attn/checkpoint-best.pth +train: [1] [ 0/800] eta: 0:58:36 lr: nan time: 4.3951 data: 4.0095 max mem: 25051 +train: [1] [ 20/800] eta: 0:08:53 lr: 0.000061 loss: 0.7001 (0.7307) grad: 0.2743 (0.2821) time: 0.4981 data: 0.0081 max mem: 25051 +train: [1] [ 40/800] eta: 0:07:31 lr: 0.000063 loss: 0.6665 (0.6974) grad: 0.2743 (0.2990) time: 0.5004 data: 0.0028 max mem: 25051 +train: [1] [ 60/800] eta: 0:06:54 lr: 0.000064 loss: 0.7001 (0.6980) grad: 0.2743 (0.3249) time: 0.4912 data: 0.0029 max mem: 25051 +train: [1] [ 80/800] eta: 0:06:29 lr: 0.000066 loss: 0.6665 (0.7020) grad: 0.2743 (0.3332) time: 0.4825 data: 0.0031 max mem: 25051 +train: [1] [100/800] eta: 0:06:14 lr: 0.000067 loss: 0.6358 (0.6825) grad: 0.2674 (0.3110) time: 0.5074 data: 0.0030 max mem: 25051 +train: [1] [120/800] eta: 0:05:59 lr: 0.000069 loss: 0.6596 (0.6857) grad: 0.2491 (0.3045) time: 0.4988 data: 0.0031 max mem: 25051 +train: [1] [140/800] eta: 0:05:44 lr: 0.000070 loss: 0.6653 (0.6858) grad: 0.2431 (0.3010) time: 0.4803 data: 0.0028 max mem: 25051 +train: [1] [160/800] eta: 0:05:48 lr: 0.000072 loss: 0.6709 (0.6944) grad: 0.2068 (0.2884) time: 0.7032 data: 0.2173 max mem: 25051 +train: [1] [180/800] eta: 0:05:33 lr: 0.000073 loss: 0.6908 (0.6906) grad: 0.1957 (0.2773) time: 0.4920 data: 0.0022 max mem: 25051 +train: [1] [200/800] eta: 0:05:20 lr: 0.000075 loss: 0.6908 (0.6862) grad: 0.1957 (0.2837) time: 0.4974 data: 0.0029 max mem: 25051 +train: [1] [220/800] eta: 0:05:07 lr: 0.000076 loss: 0.6723 (0.6819) grad: 0.1941 (0.2753) time: 0.4837 data: 0.0029 max mem: 25051 +train: [1] [240/800] eta: 0:04:54 lr: 0.000078 loss: 0.6681 (0.6758) grad: 0.2046 (0.2823) time: 0.4837 data: 0.0027 max mem: 25051 +train: [1] [260/800] eta: 0:04:42 lr: 0.000079 loss: 0.6605 (0.6756) grad: 0.2699 (0.2849) time: 0.4952 data: 0.0029 max mem: 25051 +train: [1] [280/800] eta: 0:04:31 lr: 0.000081 loss: 0.6681 (0.6785) grad: 0.2489 (0.2825) time: 0.4956 data: 0.0029 max mem: 25051 +train: [1] [300/800] eta: 0:04:26 lr: 0.000082 loss: 0.6894 (0.6797) grad: 0.2670 (0.2818) time: 0.6986 data: 0.2098 max mem: 25051 +train: [1] [320/800] eta: 0:04:15 lr: 0.000084 loss: 0.6693 (0.6775) grad: 0.2489 (0.2801) time: 0.5263 data: 0.0027 max mem: 25051 +train: [1] [340/800] eta: 0:04:04 lr: 0.000085 loss: 0.6738 (0.6777) grad: 0.2489 (0.2809) time: 0.4959 data: 0.0028 max mem: 25051 +train: [1] [360/800] eta: 0:03:52 lr: 0.000087 loss: 0.6414 (0.6720) grad: 0.2004 (0.2754) time: 0.5061 data: 0.0029 max mem: 25051 +train: [1] [380/800] eta: 0:03:41 lr: 0.000088 loss: 0.6367 (0.6690) grad: 0.2004 (0.2765) time: 0.5117 data: 0.0031 max mem: 25051 +train: [1] [400/800] eta: 0:03:30 lr: 0.000090 loss: 0.6034 (0.6657) grad: 0.1949 (0.2738) time: 0.5077 data: 0.0036 max mem: 25051 +train: [1] [420/800] eta: 0:03:19 lr: 0.000091 loss: 0.6034 (0.6640) grad: 0.2272 (0.2746) time: 0.4957 data: 0.0030 max mem: 25051 +train: [1] [440/800] eta: 0:03:12 lr: 0.000093 loss: 0.6220 (0.6662) grad: 0.2784 (0.2777) time: 0.6907 data: 0.2099 max mem: 25051 +train: [1] [460/800] eta: 0:03:00 lr: 0.000094 loss: 0.6457 (0.6660) grad: 0.2817 (0.2785) time: 0.5086 data: 0.0021 max mem: 25051 +train: [1] [480/800] eta: 0:02:50 lr: 0.000096 loss: 0.6753 (0.6670) grad: 0.2995 (0.2800) time: 0.5130 data: 0.0026 max mem: 25051 +train: [1] [500/800] eta: 0:02:39 lr: 0.000097 loss: 0.6844 (0.6668) grad: 0.2970 (0.2781) time: 0.4967 data: 0.0028 max mem: 25051 +train: [1] [520/800] eta: 0:02:27 lr: 0.000099 loss: 0.6549 (0.6664) grad: 0.2719 (0.2779) time: 0.4869 data: 0.0032 max mem: 25051 +train: [1] [540/800] eta: 0:02:17 lr: 0.000100 loss: 0.6748 (0.6665) grad: 0.2389 (0.2780) time: 0.5053 data: 0.0029 max mem: 25051 +train: [1] [560/800] eta: 0:02:06 lr: 0.000102 loss: 0.6622 (0.6663) grad: 0.2345 (0.2807) time: 0.5042 data: 0.0030 max mem: 25051 +train: [1] [580/800] eta: 0:01:57 lr: 0.000103 loss: 0.6581 (0.6653) grad: 0.2820 (0.2817) time: 0.7208 data: 0.2199 max mem: 25051 +train: [1] [600/800] eta: 0:01:46 lr: 0.000105 loss: 0.6589 (0.6669) grad: 0.2764 (0.2819) time: 0.4931 data: 0.0028 max mem: 25051 +train: [1] [620/800] eta: 0:01:35 lr: 0.000106 loss: 0.6589 (0.6693) grad: 0.3107 (0.2842) time: 0.4830 data: 0.0030 max mem: 25051 +train: [1] [640/800] eta: 0:01:24 lr: 0.000108 loss: 0.6782 (0.6698) grad: 0.3107 (0.2846) time: 0.5028 data: 0.0029 max mem: 25051 +train: [1] [660/800] eta: 0:01:13 lr: 0.000109 loss: 0.6660 (0.6692) grad: 0.2764 (0.2851) time: 0.4823 data: 0.0031 max mem: 25051 +train: [1] [680/800] eta: 0:01:03 lr: 0.000111 loss: 0.6660 (0.6697) grad: 0.3197 (0.2877) time: 0.4922 data: 0.0029 max mem: 25051 +train: [1] [700/800] eta: 0:00:52 lr: 0.000112 loss: 0.6431 (0.6683) grad: 0.2715 (0.2886) time: 0.5014 data: 0.0029 max mem: 25051 +train: [1] [720/800] eta: 0:00:42 lr: 0.000114 loss: 0.6381 (0.6649) grad: 0.2715 (0.2883) time: 0.7128 data: 0.2158 max mem: 25051 +train: [1] [740/800] eta: 0:00:31 lr: 0.000115 loss: 0.6381 (0.6650) grad: 0.2727 (0.2905) time: 0.4684 data: 0.0034 max mem: 25051 +train: [1] [760/800] eta: 0:00:21 lr: 0.000117 loss: 0.6248 (0.6672) grad: 0.3178 (0.2966) time: 0.4569 data: 0.0024 max mem: 25051 +train: [1] [780/800] eta: 0:00:10 lr: 0.000118 loss: 0.6557 (0.6687) grad: 0.3354 (0.2986) time: 0.5122 data: 0.0029 max mem: 25051 +train: [1] [799/800] eta: 0:00:00 lr: 0.000120 loss: 0.6939 (0.6687) grad: 0.3807 (0.3011) time: 0.5239 data: 0.0031 max mem: 25051 +train: [1] Total time: 0:07:02 (0.5278 s / it) +train: [1] Summary: lr: 0.000120 loss: 0.6939 (0.6687) grad: 0.3807 (0.3011) +eval (validation): [1] [ 0/31] eta: 0:02:10 time: 4.2176 data: 3.9580 max mem: 25051 +eval (validation): [1] [20/31] eta: 0:00:06 time: 0.4060 data: 0.0269 max mem: 25051 +eval (validation): [1] [30/31] eta: 0:00:00 time: 0.3610 data: 0.0264 max mem: 25051 +eval (validation): [1] Total time: 0:00:15 (0.5147 s / it) +cv: [1] best hparam: (14, 1.0) (040) ('040_lr1.4e+01_wd1.0e+00') loss: 0.615 acc: 0.669 f1: 0.664 bacc: 0.665 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/abide_dx__patch__attn/checkpoint-last.pth +train: [2] [ 0/800] eta: 0:59:07 lr: nan time: 4.4338 data: 4.0110 max mem: 25051 +train: [2] [ 20/800] eta: 0:08:44 lr: 0.000121 loss: 0.6458 (0.6910) grad: 0.4184 (0.4261) time: 0.4846 data: 0.0022 max mem: 25051 +train: [2] [ 40/800] eta: 0:07:25 lr: 0.000123 loss: 0.6286 (0.6575) grad: 0.4065 (0.3764) time: 0.4954 data: 0.0027 max mem: 25051 +train: [2] [ 60/800] eta: 0:06:46 lr: 0.000124 loss: 0.6458 (0.6673) grad: 0.4208 (0.3938) time: 0.4757 data: 0.0030 max mem: 25051 +train: [2] [ 80/800] eta: 0:06:26 lr: 0.000126 loss: 0.6458 (0.6664) grad: 0.4065 (0.3839) time: 0.4960 data: 0.0032 max mem: 25051 +train: [2] [100/800] eta: 0:06:11 lr: 0.000127 loss: 0.6679 (0.6803) grad: 0.4208 (0.4016) time: 0.5040 data: 0.0031 max mem: 25051 +train: [2] [120/800] eta: 0:05:55 lr: 0.000129 loss: 0.6717 (0.6753) grad: 0.4208 (0.3987) time: 0.4837 data: 0.0030 max mem: 25051 +train: [2] [140/800] eta: 0:05:39 lr: 0.000130 loss: 0.6679 (0.6712) grad: 0.3710 (0.3942) time: 0.4701 data: 0.0029 max mem: 25051 +train: [2] [160/800] eta: 0:05:45 lr: 0.000132 loss: 0.6679 (0.6708) grad: 0.3723 (0.3850) time: 0.7138 data: 0.2222 max mem: 25051 +train: [2] [180/800] eta: 0:05:32 lr: 0.000133 loss: 0.6470 (0.6681) grad: 0.3268 (0.3801) time: 0.5015 data: 0.0034 max mem: 25051 +train: [2] [200/800] eta: 0:05:17 lr: 0.000135 loss: 0.6470 (0.6685) grad: 0.3200 (0.3799) time: 0.4758 data: 0.0023 max mem: 25051 +train: [2] [220/800] eta: 0:05:04 lr: 0.000136 loss: 0.6569 (0.6679) grad: 0.3223 (0.3834) time: 0.4853 data: 0.0029 max mem: 25051 +train: [2] [240/800] eta: 0:04:52 lr: 0.000138 loss: 0.6742 (0.6719) grad: 0.3223 (0.3797) time: 0.4954 data: 0.0030 max mem: 25051 +train: [2] [260/800] eta: 0:04:41 lr: 0.000139 loss: 0.6742 (0.6705) grad: 0.3362 (0.3842) time: 0.5023 data: 0.0031 max mem: 25051 +train: [2] [280/800] eta: 0:04:29 lr: 0.000141 loss: 0.6749 (0.6759) grad: 0.3822 (0.3875) time: 0.4714 data: 0.0030 max mem: 25051 +train: [2] [300/800] eta: 0:04:24 lr: 0.000142 loss: 0.6636 (0.6721) grad: 0.3610 (0.3867) time: 0.6905 data: 0.2084 max mem: 25051 +train: [2] [320/800] eta: 0:04:13 lr: 0.000144 loss: 0.6307 (0.6692) grad: 0.3610 (0.3829) time: 0.5040 data: 0.0027 max mem: 25051 +train: [2] [340/800] eta: 0:04:01 lr: 0.000145 loss: 0.6307 (0.6694) grad: 0.3610 (0.3803) time: 0.4865 data: 0.0031 max mem: 25051 +train: [2] [360/800] eta: 0:03:50 lr: 0.000147 loss: 0.6307 (0.6742) grad: 0.3313 (0.3786) time: 0.4790 data: 0.0035 max mem: 25051 +train: [2] [380/800] eta: 0:03:39 lr: 0.000148 loss: 0.6610 (0.6738) grad: 0.3268 (0.3758) time: 0.5054 data: 0.0032 max mem: 25051 +train: [2] [400/800] eta: 0:03:28 lr: 0.000150 loss: 0.7111 (0.6787) grad: 0.3433 (0.3824) time: 0.4984 data: 0.0030 max mem: 25051 +train: [2] [420/800] eta: 0:03:16 lr: 0.000151 loss: 0.7061 (0.6780) grad: 0.3759 (0.3922) time: 0.4634 data: 0.0030 max mem: 25051 +train: [2] [440/800] eta: 0:03:09 lr: 0.000153 loss: 0.6764 (0.6796) grad: 0.4330 (0.3943) time: 0.7101 data: 0.2178 max mem: 25051 +train: [2] [460/800] eta: 0:02:59 lr: 0.000154 loss: 0.6764 (0.6799) grad: 0.4584 (0.3946) time: 0.5306 data: 0.0039 max mem: 25051 +train: [2] [480/800] eta: 0:02:48 lr: 0.000156 loss: 0.6510 (0.6783) grad: 0.4360 (0.3936) time: 0.4875 data: 0.0019 max mem: 25051 +train: [2] [500/800] eta: 0:02:37 lr: 0.000157 loss: 0.6510 (0.6791) grad: 0.4127 (0.3932) time: 0.4866 data: 0.0029 max mem: 25051 +train: [2] [520/800] eta: 0:02:26 lr: 0.000159 loss: 0.6519 (0.6790) grad: 0.3588 (0.3954) time: 0.4816 data: 0.0032 max mem: 25051 +train: [2] [540/800] eta: 0:02:15 lr: 0.000160 loss: 0.6560 (0.6814) grad: 0.3950 (0.3959) time: 0.5022 data: 0.0034 max mem: 25051 +train: [2] [560/800] eta: 0:02:04 lr: 0.000162 loss: 0.6369 (0.6793) grad: 0.3950 (0.3990) time: 0.4931 data: 0.0031 max mem: 25051 +train: [2] [580/800] eta: 0:01:55 lr: 0.000163 loss: 0.6362 (0.6765) grad: 0.3950 (0.3997) time: 0.6906 data: 0.2267 max mem: 25051 +train: [2] [600/800] eta: 0:01:45 lr: 0.000165 loss: 0.6129 (0.6731) grad: 0.3855 (0.3979) time: 0.5125 data: 0.0099 max mem: 25051 +WARNING: classifier 48 (50, 1.0) diverged (loss=24.19 > 13.86) at step 555. Freezing. +train: [2] [620/800] eta: 0:01:34 lr: 0.000166 loss: 0.5934 (0.6748) grad: 0.3807 (0.4001) time: 0.4870 data: 0.0028 max mem: 25051 +train: [2] [640/800] eta: 0:01:23 lr: 0.000168 loss: 0.5934 (0.6741) grad: 0.3702 (0.3979) time: 0.5113 data: 0.0028 max mem: 25051 +train: [2] [660/800] eta: 0:01:13 lr: 0.000169 loss: 0.5911 (0.6721) grad: 0.3138 (0.3957) time: 0.4911 data: 0.0032 max mem: 25051 +train: [2] [680/800] eta: 0:01:02 lr: 0.000171 loss: 0.5911 (0.6714) grad: 0.3600 (0.3965) time: 0.4910 data: 0.0030 max mem: 25051 +train: [2] [700/800] eta: 0:00:52 lr: 0.000172 loss: 0.6333 (0.6725) grad: 0.3724 (0.3987) time: 0.4877 data: 0.0031 max mem: 25051 +train: [2] [720/800] eta: 0:00:42 lr: 0.000174 loss: 0.6539 (0.6756) grad: 0.3799 (0.3994) time: 0.6827 data: 0.2116 max mem: 25051 +train: [2] [740/800] eta: 0:00:31 lr: 0.000175 loss: 0.6966 (0.6758) grad: 0.3978 (0.3994) time: 0.4815 data: 0.0024 max mem: 25051 +train: [2] [760/800] eta: 0:00:20 lr: 0.000177 loss: 0.6941 (0.6738) grad: 0.3813 (0.3974) time: 0.5053 data: 0.0025 max mem: 25051 +train: [2] [780/800] eta: 0:00:10 lr: 0.000178 loss: 0.6634 (0.6728) grad: 0.3792 (0.3972) time: 0.4975 data: 0.0030 max mem: 25051 +train: [2] [799/800] eta: 0:00:00 lr: 0.000180 loss: 0.6353 (0.6702) grad: 0.3763 (0.3963) time: 0.4930 data: 0.0027 max mem: 25051 +train: [2] Total time: 0:06:58 (0.5228 s / it) +train: [2] Summary: lr: 0.000180 loss: 0.6353 (0.6702) grad: 0.3763 (0.3963) +eval (validation): [2] [ 0/31] eta: 0:02:27 time: 4.7457 data: 4.4554 max mem: 25051 +eval (validation): [2] [20/31] eta: 0:00:06 time: 0.4059 data: 0.0347 max mem: 25051 +eval (validation): [2] [30/31] eta: 0:00:00 time: 0.3905 data: 0.0344 max mem: 25051 +eval (validation): [2] Total time: 0:00:16 (0.5356 s / it) +cv: [2] best hparam: (9.8, 1.0) (038) ('038_lr9.8e+00_wd1.0e+00') loss: 0.663 acc: 0.653 f1: 0.649 bacc: 0.651 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/abide_dx__patch__attn/checkpoint-last.pth +train: [3] [ 0/800] eta: 0:57:06 lr: nan time: 4.2835 data: 3.8374 max mem: 25051 +train: [3] [ 20/800] eta: 0:08:37 lr: 0.000181 loss: 0.6691 (0.6716) grad: 0.3898 (0.3590) time: 0.4823 data: 0.0071 max mem: 25051 +train: [3] [ 40/800] eta: 0:07:18 lr: 0.000183 loss: 0.6612 (0.6435) grad: 0.3365 (0.3329) time: 0.4863 data: 0.0025 max mem: 25051 +train: [3] [ 60/800] eta: 0:06:46 lr: 0.000184 loss: 0.6586 (0.6325) grad: 0.3336 (0.3227) time: 0.4915 data: 0.0033 max mem: 25051 +train: [3] [ 80/800] eta: 0:06:25 lr: 0.000186 loss: 0.6427 (0.6225) grad: 0.3336 (0.3335) time: 0.4937 data: 0.0031 max mem: 25051 +train: [3] [100/800] eta: 0:06:07 lr: 0.000187 loss: 0.5955 (0.6093) grad: 0.3313 (0.3281) time: 0.4836 data: 0.0030 max mem: 25051 +train: [3] [120/800] eta: 0:05:53 lr: 0.000189 loss: 0.5955 (0.6088) grad: 0.3280 (0.3276) time: 0.4915 data: 0.0030 max mem: 25051 +train: [3] [140/800] eta: 0:05:39 lr: 0.000190 loss: 0.5955 (0.6108) grad: 0.3648 (0.3523) time: 0.4882 data: 0.0028 max mem: 25051 +train: [3] [160/800] eta: 0:05:49 lr: 0.000192 loss: 0.5919 (0.6050) grad: 0.3751 (0.3599) time: 0.7668 data: 0.2109 max mem: 25051 +train: [3] [180/800] eta: 0:05:35 lr: 0.000193 loss: 0.5976 (0.6076) grad: 0.3791 (0.3683) time: 0.5058 data: 0.0027 max mem: 25051 +train: [3] [200/800] eta: 0:05:21 lr: 0.000195 loss: 0.5995 (0.6212) grad: 0.4807 (0.3862) time: 0.4735 data: 0.0032 max mem: 25051 +train: [3] [220/800] eta: 0:05:07 lr: 0.000196 loss: 0.5995 (0.6187) grad: 0.4374 (0.3941) time: 0.4768 data: 0.0030 max mem: 25051 +train: [3] [240/800] eta: 0:04:54 lr: 0.000198 loss: 0.6613 (0.6279) grad: 0.4374 (0.3980) time: 0.4852 data: 0.0029 max mem: 25051 +train: [3] [260/800] eta: 0:04:43 lr: 0.000199 loss: 0.6830 (0.6345) grad: 0.4658 (0.4043) time: 0.5171 data: 0.0032 max mem: 25051 +train: [3] [280/800] eta: 0:04:31 lr: 0.000201 loss: 0.6511 (0.6410) grad: 0.4478 (0.4101) time: 0.4685 data: 0.0029 max mem: 25051 +train: [3] [300/800] eta: 0:04:28 lr: 0.000202 loss: 0.6794 (0.6459) grad: 0.4891 (0.4294) time: 0.7693 data: 0.2927 max mem: 25051 +train: [3] [320/800] eta: 0:04:17 lr: 0.000204 loss: 0.6496 (0.6398) grad: 0.5125 (0.4372) time: 0.5029 data: 0.0035 max mem: 25051 +WARNING: classifier 46 (36, 1.0) diverged (loss=29.06 > 13.86) at step 685. Freezing. +train: [3] [340/800] eta: 0:04:04 lr: 0.000205 loss: 0.6496 (0.6485) grad: 0.5297 (0.4595) time: 0.4784 data: 0.0025 max mem: 25051 +train: [3] [360/800] eta: 0:03:53 lr: 0.000207 loss: 0.6213 (0.6445) grad: 0.5627 (0.4664) time: 0.4947 data: 0.0031 max mem: 25051 +train: [3] [380/800] eta: 0:03:42 lr: 0.000208 loss: 0.5545 (0.6445) grad: 0.5046 (0.4697) time: 0.5030 data: 0.0033 max mem: 25051 +train: [3] [400/800] eta: 0:03:30 lr: 0.000210 loss: 0.6651 (0.6518) grad: 0.5046 (0.4721) time: 0.4872 data: 0.0031 max mem: 25051 +train: [3] [420/800] eta: 0:03:19 lr: 0.000211 loss: 0.6956 (0.6570) grad: 0.5526 (0.4778) time: 0.4765 data: 0.0028 max mem: 25051 +train: [3] [440/800] eta: 0:03:11 lr: 0.000213 loss: 0.7094 (0.6582) grad: 0.5581 (0.4850) time: 0.6645 data: 0.2089 max mem: 25051 +WARNING: classifier 47 (43, 1.0) diverged (loss=19.41 > 13.86) at step 715. Freezing. +train: [3] [460/800] eta: 0:02:59 lr: 0.000214 loss: 0.7275 (0.6615) grad: 0.5899 (0.4992) time: 0.4903 data: 0.0027 max mem: 25051 +train: [3] [480/800] eta: 0:02:49 lr: 0.000216 loss: 0.6981 (0.6610) grad: 0.5925 (0.4972) time: 0.5200 data: 0.0034 max mem: 25051 +train: [3] [500/800] eta: 0:02:37 lr: 0.000217 loss: 0.6473 (0.6552) grad: 0.4846 (0.4929) time: 0.4753 data: 0.0032 max mem: 25051 +train: [3] [520/800] eta: 0:02:26 lr: 0.000219 loss: 0.6654 (0.6561) grad: 0.4102 (0.4914) time: 0.4827 data: 0.0034 max mem: 25051 +train: [3] [540/800] eta: 0:02:16 lr: 0.000220 loss: 0.5730 (0.6529) grad: 0.3860 (0.4871) time: 0.4925 data: 0.0034 max mem: 25051 +train: [3] [560/800] eta: 0:02:05 lr: 0.000222 loss: 0.5730 (0.6502) grad: 0.3691 (0.4807) time: 0.4731 data: 0.0030 max mem: 25051 +train: [3] [580/800] eta: 0:01:55 lr: 0.000223 loss: 0.5966 (0.6502) grad: 0.3789 (0.4776) time: 0.6754 data: 0.2170 max mem: 25051 +train: [3] [600/800] eta: 0:01:45 lr: 0.000225 loss: 0.5768 (0.6470) grad: 0.3437 (0.4734) time: 0.5074 data: 0.0047 max mem: 25051 +train: [3] [620/800] eta: 0:01:34 lr: 0.000226 loss: 0.5843 (0.6455) grad: 0.3362 (0.4703) time: 0.4916 data: 0.0029 max mem: 25051 +train: [3] [640/800] eta: 0:01:23 lr: 0.000228 loss: 0.5884 (0.6465) grad: 0.3799 (0.4681) time: 0.4867 data: 0.0031 max mem: 25051 +train: [3] [660/800] eta: 0:01:13 lr: 0.000229 loss: 0.5884 (0.6444) grad: 0.3691 (0.4648) time: 0.4777 data: 0.0030 max mem: 25051 +train: [3] [680/800] eta: 0:01:02 lr: 0.000231 loss: 0.5914 (0.6428) grad: 0.3692 (0.4638) time: 0.4829 data: 0.0030 max mem: 25051 +train: [3] [700/800] eta: 0:00:52 lr: 0.000232 loss: 0.6346 (0.6420) grad: 0.3801 (0.4639) time: 0.4881 data: 0.0032 max mem: 25051 +train: [3] [720/800] eta: 0:00:41 lr: 0.000234 loss: 0.6264 (0.6423) grad: 0.4336 (0.4643) time: 0.6726 data: 0.2075 max mem: 25051 +train: [3] [740/800] eta: 0:00:31 lr: 0.000235 loss: 0.6264 (0.6396) grad: 0.4404 (0.4640) time: 0.4875 data: 0.0068 max mem: 25051 +train: [3] [760/800] eta: 0:00:20 lr: 0.000237 loss: 0.6264 (0.6365) grad: 0.4336 (0.4631) time: 0.5104 data: 0.0027 max mem: 25051 +train: [3] [780/800] eta: 0:00:10 lr: 0.000238 loss: 0.5682 (0.6344) grad: 0.4157 (0.4613) time: 0.4887 data: 0.0029 max mem: 25051 +train: [3] [799/800] eta: 0:00:00 lr: 0.000240 loss: 0.5003 (0.6332) grad: 0.4157 (0.4609) time: 0.4795 data: 0.0033 max mem: 25051 +train: [3] Total time: 0:06:57 (0.5219 s / it) +train: [3] Summary: lr: 0.000240 loss: 0.5003 (0.6332) grad: 0.4157 (0.4609) +eval (validation): [3] [ 0/31] eta: 0:02:09 time: 4.1856 data: 3.9253 max mem: 25051 +eval (validation): [3] [20/31] eta: 0:00:06 time: 0.4125 data: 0.0308 max mem: 25051 +eval (validation): [3] [30/31] eta: 0:00:00 time: 0.3713 data: 0.0019 max mem: 25051 +eval (validation): [3] Total time: 0:00:16 (0.5268 s / it) +cv: [3] best hparam: (2.7, 1.0) (030) ('030_lr2.7e+00_wd1.0e+00') loss: 0.729 acc: 0.661 f1: 0.602 bacc: 0.622 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/abide_dx__patch__attn/checkpoint-last.pth +train: [4] [ 0/800] eta: 0:58:30 lr: nan time: 4.3877 data: 3.9758 max mem: 25051 +train: [4] [ 20/800] eta: 0:08:56 lr: 0.000241 loss: 0.6434 (0.5926) grad: 0.4049 (0.4376) time: 0.5027 data: 0.0021 max mem: 25051 +train: [4] [ 40/800] eta: 0:07:19 lr: 0.000243 loss: 0.6076 (0.6290) grad: 0.4352 (0.4920) time: 0.4647 data: 0.0028 max mem: 25051 +train: [4] [ 60/800] eta: 0:06:44 lr: 0.000244 loss: 0.6316 (0.6410) grad: 0.4535 (0.4909) time: 0.4804 data: 0.0027 max mem: 25051 +train: [4] [ 80/800] eta: 0:06:22 lr: 0.000246 loss: 0.6076 (0.6214) grad: 0.4317 (0.4632) time: 0.4868 data: 0.0030 max mem: 25051 +train: [4] [100/800] eta: 0:06:05 lr: 0.000247 loss: 0.5924 (0.5986) grad: 0.4370 (0.4556) time: 0.4860 data: 0.0033 max mem: 25051 +train: [4] [120/800] eta: 0:05:49 lr: 0.000249 loss: 0.5535 (0.5850) grad: 0.4249 (0.4527) time: 0.4681 data: 0.0030 max mem: 25051 +WARNING: classifier 44 (26, 1.0) diverged (loss=14.59 > 13.86) at step 835. Freezing. +train: [4] [140/800] eta: 0:05:35 lr: 0.000250 loss: 0.5040 (0.5938) grad: 0.4207 (0.4605) time: 0.4741 data: 0.0027 max mem: 25051 +train: [4] [160/800] eta: 0:05:41 lr: 0.000252 loss: 0.4870 (0.5787) grad: 0.4141 (0.4444) time: 0.7072 data: 0.2457 max mem: 25051 +train: [4] [180/800] eta: 0:05:28 lr: 0.000253 loss: 0.4959 (0.5764) grad: 0.3639 (0.4247) time: 0.5036 data: 0.0019 max mem: 25051 +train: [4] [200/800] eta: 0:05:15 lr: 0.000255 loss: 0.5076 (0.5839) grad: 0.3502 (0.4249) time: 0.4865 data: 0.0028 max mem: 25051 +train: [4] [220/800] eta: 0:05:02 lr: 0.000256 loss: 0.4840 (0.5817) grad: 0.3502 (0.4298) time: 0.4881 data: 0.0032 max mem: 25051 +train: [4] [240/800] eta: 0:04:50 lr: 0.000258 loss: 0.5433 (0.5846) grad: 0.3536 (0.4239) time: 0.4798 data: 0.0029 max mem: 25051 +train: [4] [260/800] eta: 0:04:39 lr: 0.000259 loss: 0.5433 (0.5767) grad: 0.3800 (0.4180) time: 0.4960 data: 0.0032 max mem: 25051 +train: [4] [280/800] eta: 0:04:27 lr: 0.000261 loss: 0.5130 (0.5696) grad: 0.3536 (0.4116) time: 0.4780 data: 0.0031 max mem: 25051 +train: [4] [300/800] eta: 0:04:22 lr: 0.000262 loss: 0.5433 (0.5729) grad: 0.3606 (0.4125) time: 0.6690 data: 0.2188 max mem: 25051 +train: [4] [320/800] eta: 0:04:10 lr: 0.000264 loss: 0.5130 (0.5713) grad: 0.3657 (0.4147) time: 0.4726 data: 0.0180 max mem: 25051 +train: [4] [340/800] eta: 0:03:59 lr: 0.000265 loss: 0.5854 (0.5781) grad: 0.3823 (0.4136) time: 0.5112 data: 0.0031 max mem: 25051 +train: [4] [360/800] eta: 0:03:47 lr: 0.000267 loss: 0.5793 (0.5754) grad: 0.4317 (0.4173) time: 0.4744 data: 0.0024 max mem: 25051 +train: [4] [380/800] eta: 0:03:36 lr: 0.000268 loss: 0.5841 (0.5796) grad: 0.4274 (0.4233) time: 0.4870 data: 0.0034 max mem: 25051 +train: [4] [400/800] eta: 0:03:26 lr: 0.000270 loss: 0.6181 (0.5825) grad: 0.4274 (0.4287) time: 0.5012 data: 0.0032 max mem: 25051 +WARNING: classifier 45 (31, 1.0) diverged (loss=14.55 > 13.86) at step 903. Freezing. +train: [4] [420/800] eta: 0:03:15 lr: 0.000271 loss: 0.6507 (0.5938) grad: 0.4239 (0.4286) time: 0.4752 data: 0.0029 max mem: 25051 +train: [4] [440/800] eta: 0:03:08 lr: 0.000273 loss: 0.6161 (0.5919) grad: 0.3942 (0.4240) time: 0.7202 data: 0.2081 max mem: 25051 +train: [4] [460/800] eta: 0:02:57 lr: 0.000274 loss: 0.5864 (0.5901) grad: 0.3541 (0.4179) time: 0.5241 data: 0.0024 max mem: 25051 +train: [4] [480/800] eta: 0:02:47 lr: 0.000276 loss: 0.5662 (0.5862) grad: 0.2934 (0.4115) time: 0.5032 data: 0.0033 max mem: 25051 +train: [4] [500/800] eta: 0:02:36 lr: 0.000277 loss: 0.5192 (0.5854) grad: 0.2934 (0.4081) time: 0.4808 data: 0.0030 max mem: 25051 +train: [4] [520/800] eta: 0:02:25 lr: 0.000279 loss: 0.5192 (0.5836) grad: 0.2720 (0.4047) time: 0.4964 data: 0.0031 max mem: 25051 +train: [4] [540/800] eta: 0:02:14 lr: 0.000280 loss: 0.5021 (0.5799) grad: 0.2720 (0.4000) time: 0.5018 data: 0.0030 max mem: 25051 +train: [4] [560/800] eta: 0:02:04 lr: 0.000282 loss: 0.5259 (0.5778) grad: 0.2815 (0.3971) time: 0.5389 data: 0.0039 max mem: 25051 +train: [4] [580/800] eta: 0:01:55 lr: 0.000283 loss: 0.4923 (0.5726) grad: 0.2812 (0.3932) time: 0.6600 data: 0.2063 max mem: 25051 +train: [4] [600/800] eta: 0:01:44 lr: 0.000285 loss: 0.4554 (0.5706) grad: 0.2812 (0.3921) time: 0.5184 data: 0.0197 max mem: 25051 +train: [4] [620/800] eta: 0:01:34 lr: 0.000286 loss: 0.4906 (0.5699) grad: 0.2917 (0.3915) time: 0.4996 data: 0.0017 max mem: 25051 +train: [4] [640/800] eta: 0:01:23 lr: 0.000288 loss: 0.4909 (0.5674) grad: 0.2643 (0.3875) time: 0.4742 data: 0.0029 max mem: 25051 +train: [4] [660/800] eta: 0:01:12 lr: 0.000289 loss: 0.5035 (0.5652) grad: 0.2795 (0.3865) time: 0.4677 data: 0.0033 max mem: 25051 +train: [4] [680/800] eta: 0:01:02 lr: 0.000291 loss: 0.5035 (0.5646) grad: 0.3014 (0.3878) time: 0.4922 data: 0.0031 max mem: 25051 +train: [4] [700/800] eta: 0:00:51 lr: 0.000292 loss: 0.5450 (0.5667) grad: 0.3232 (0.3874) time: 0.4883 data: 0.0029 max mem: 25051 +train: [4] [720/800] eta: 0:00:41 lr: 0.000294 loss: 0.5689 (0.5673) grad: 0.3297 (0.3859) time: 0.6705 data: 0.2043 max mem: 25051 +train: [4] [740/800] eta: 0:00:31 lr: 0.000295 loss: 0.5577 (0.5650) grad: 0.3293 (0.3838) time: 0.4949 data: 0.0034 max mem: 25051 +train: [4] [760/800] eta: 0:00:20 lr: 0.000297 loss: 0.5356 (0.5636) grad: 0.3289 (0.3828) time: 0.5067 data: 0.0024 max mem: 25051 +train: [4] [780/800] eta: 0:00:10 lr: 0.000298 loss: 0.5193 (0.5629) grad: 0.3001 (0.3808) time: 0.4932 data: 0.0030 max mem: 25051 +train: [4] [799/800] eta: 0:00:00 lr: 0.000300 loss: 0.4949 (0.5605) grad: 0.2708 (0.3784) time: 0.4815 data: 0.0029 max mem: 25051 +train: [4] Total time: 0:06:56 (0.5203 s / it) +train: [4] Summary: lr: 0.000300 loss: 0.4949 (0.5605) grad: 0.2708 (0.3784) +eval (validation): [4] [ 0/31] eta: 0:02:09 time: 4.1666 data: 3.9170 max mem: 25051 +eval (validation): [4] [20/31] eta: 0:00:06 time: 0.4007 data: 0.0198 max mem: 25051 +eval (validation): [4] [30/31] eta: 0:00:00 time: 0.4030 data: 0.0111 max mem: 25051 +eval (validation): [4] Total time: 0:00:16 (0.5224 s / it) +cv: [4] best hparam: (5.1, 1.0) (034) ('034_lr5.1e+00_wd1.0e+00') loss: 2.158 acc: 0.669 f1: 0.641 bacc: 0.644 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/abide_dx__patch__attn/checkpoint-last.pth +train: [5] [ 0/800] eta: 0:58:46 lr: nan time: 4.4085 data: 4.0157 max mem: 25051 +train: [5] [ 20/800] eta: 0:08:29 lr: 0.000300 loss: 0.5327 (0.4941) grad: 0.3639 (0.3466) time: 0.4659 data: 0.0062 max mem: 25051 +train: [5] [ 40/800] eta: 0:07:11 lr: 0.000300 loss: 0.5029 (0.4848) grad: 0.3588 (0.3487) time: 0.4779 data: 0.0023 max mem: 25051 +train: [5] [ 60/800] eta: 0:06:44 lr: 0.000300 loss: 0.5029 (0.4906) grad: 0.3588 (0.3459) time: 0.5045 data: 0.0026 max mem: 25051 +train: [5] [ 80/800] eta: 0:06:28 lr: 0.000300 loss: 0.5029 (0.4990) grad: 0.3588 (0.3506) time: 0.5148 data: 0.0030 max mem: 25051 +train: [5] [100/800] eta: 0:06:12 lr: 0.000300 loss: 0.5054 (0.5160) grad: 0.3513 (0.3609) time: 0.5056 data: 0.0034 max mem: 25051 +train: [5] [120/800] eta: 0:05:55 lr: 0.000300 loss: 0.5476 (0.5444) grad: 0.4274 (0.4391) time: 0.4768 data: 0.0027 max mem: 25051 +WARNING: classifier 42 (19, 1.0) diverged (loss=13.94 > 13.86) at step 1031. Freezing. +train: [5] [140/800] eta: 0:05:40 lr: 0.000300 loss: 0.5571 (0.5577) grad: 0.4546 (0.4553) time: 0.4681 data: 0.0029 max mem: 25051 +train: [5] [160/800] eta: 0:05:47 lr: 0.000300 loss: 0.5476 (0.5487) grad: 0.4542 (0.4436) time: 0.7392 data: 0.2339 max mem: 25051 +train: [5] [180/800] eta: 0:05:35 lr: 0.000300 loss: 0.5344 (0.5377) grad: 0.4542 (0.4404) time: 0.5172 data: 0.0027 max mem: 25051 +train: [5] [200/800] eta: 0:05:22 lr: 0.000300 loss: 0.5118 (0.5370) grad: 0.3044 (0.4336) time: 0.5135 data: 0.0034 max mem: 25051 +train: [5] [220/800] eta: 0:05:10 lr: 0.000300 loss: 0.5118 (0.5457) grad: 0.3732 (0.4341) time: 0.5197 data: 0.0032 max mem: 25051 +train: [5] [240/800] eta: 0:04:59 lr: 0.000300 loss: 0.4881 (0.5412) grad: 0.3994 (0.4320) time: 0.5138 data: 0.0032 max mem: 25051 +WARNING: classifier 43 (22, 1.0) diverged (loss=14.50 > 13.86) at step 1064. Freezing. +train: [5] [260/800] eta: 0:04:46 lr: 0.000300 loss: 0.5142 (0.5467) grad: 0.4078 (0.4332) time: 0.4775 data: 0.0032 max mem: 25051 +train: [5] [280/800] eta: 0:04:33 lr: 0.000300 loss: 0.5142 (0.5433) grad: 0.3806 (0.4204) time: 0.4775 data: 0.0031 max mem: 25051 +train: [5] [300/800] eta: 0:04:28 lr: 0.000300 loss: 0.5120 (0.5394) grad: 0.2826 (0.4079) time: 0.6961 data: 0.2334 max mem: 25051 +train: [5] [320/800] eta: 0:04:16 lr: 0.000299 loss: 0.5100 (0.5349) grad: 0.2530 (0.3955) time: 0.4856 data: 0.0024 max mem: 25051 +train: [5] [340/800] eta: 0:04:04 lr: 0.000299 loss: 0.4535 (0.5327) grad: 0.2191 (0.3872) time: 0.4906 data: 0.0027 max mem: 25051 +train: [5] [360/800] eta: 0:03:52 lr: 0.000299 loss: 0.5100 (0.5358) grad: 0.2077 (0.3818) time: 0.4929 data: 0.0033 max mem: 25051 +train: [5] [380/800] eta: 0:03:41 lr: 0.000299 loss: 0.5133 (0.5330) grad: 0.2296 (0.3766) time: 0.4906 data: 0.0032 max mem: 25051 +train: [5] [400/800] eta: 0:03:30 lr: 0.000299 loss: 0.5132 (0.5289) grad: 0.2366 (0.3703) time: 0.5043 data: 0.0032 max mem: 25051 +train: [5] [420/800] eta: 0:03:19 lr: 0.000299 loss: 0.5132 (0.5277) grad: 0.2772 (0.3725) time: 0.4856 data: 0.0033 max mem: 25051 +train: [5] [440/800] eta: 0:03:12 lr: 0.000299 loss: 0.5022 (0.5292) grad: 0.2614 (0.3681) time: 0.7541 data: 0.2215 max mem: 25051 +train: [5] [460/800] eta: 0:03:00 lr: 0.000299 loss: 0.4662 (0.5266) grad: 0.2526 (0.3626) time: 0.4760 data: 0.0027 max mem: 25051 +train: [5] [480/800] eta: 0:02:49 lr: 0.000299 loss: 0.4662 (0.5239) grad: 0.2306 (0.3558) time: 0.4911 data: 0.0029 max mem: 25051 +train: [5] [500/800] eta: 0:02:38 lr: 0.000299 loss: 0.4662 (0.5221) grad: 0.2036 (0.3505) time: 0.4875 data: 0.0034 max mem: 25051 +train: [5] [520/800] eta: 0:02:27 lr: 0.000299 loss: 0.4635 (0.5203) grad: 0.2301 (0.3497) time: 0.4809 data: 0.0033 max mem: 25051 +train: [5] [540/800] eta: 0:02:16 lr: 0.000299 loss: 0.4669 (0.5196) grad: 0.2576 (0.3491) time: 0.4846 data: 0.0030 max mem: 25051 +train: [5] [560/800] eta: 0:02:05 lr: 0.000298 loss: 0.4810 (0.5170) grad: 0.2653 (0.3473) time: 0.4883 data: 0.0030 max mem: 25051 +train: [5] [580/800] eta: 0:01:57 lr: 0.000298 loss: 0.4810 (0.5177) grad: 0.2845 (0.3458) time: 0.7547 data: 0.2887 max mem: 25051 +train: [5] [600/800] eta: 0:01:46 lr: 0.000298 loss: 0.4945 (0.5180) grad: 0.2653 (0.3416) time: 0.4844 data: 0.0025 max mem: 25051 +train: [5] [620/800] eta: 0:01:35 lr: 0.000298 loss: 0.4848 (0.5172) grad: 0.2510 (0.3382) time: 0.4766 data: 0.0029 max mem: 25051 +train: [5] [640/800] eta: 0:01:24 lr: 0.000298 loss: 0.4986 (0.5157) grad: 0.2509 (0.3348) time: 0.4661 data: 0.0032 max mem: 25051 +train: [5] [660/800] eta: 0:01:13 lr: 0.000298 loss: 0.4993 (0.5151) grad: 0.2157 (0.3312) time: 0.4775 data: 0.0030 max mem: 25051 +train: [5] [680/800] eta: 0:01:02 lr: 0.000298 loss: 0.4993 (0.5147) grad: 0.2230 (0.3283) time: 0.4803 data: 0.0031 max mem: 25051 +train: [5] [700/800] eta: 0:00:52 lr: 0.000298 loss: 0.4993 (0.5146) grad: 0.2233 (0.3255) time: 0.4908 data: 0.0030 max mem: 25051 +train: [5] [720/800] eta: 0:00:42 lr: 0.000297 loss: 0.4939 (0.5136) grad: 0.2233 (0.3238) time: 0.6748 data: 0.2132 max mem: 25051 +train: [5] [740/800] eta: 0:00:31 lr: 0.000297 loss: 0.4570 (0.5114) grad: 0.2542 (0.3240) time: 0.5167 data: 0.0022 max mem: 25051 +train: [5] [760/800] eta: 0:00:21 lr: 0.000297 loss: 0.4570 (0.5103) grad: 0.2328 (0.3208) time: 0.5131 data: 0.0042 max mem: 25051 +train: [5] [780/800] eta: 0:00:10 lr: 0.000297 loss: 0.4530 (0.5102) grad: 0.2542 (0.3187) time: 0.4950 data: 0.0031 max mem: 25051 +train: [5] [799/800] eta: 0:00:00 lr: 0.000297 loss: 0.4404 (0.5100) grad: 0.2571 (0.3174) time: 0.4736 data: 0.0035 max mem: 25051 +train: [5] Total time: 0:06:59 (0.5247 s / it) +train: [5] Summary: lr: 0.000297 loss: 0.4404 (0.5100) grad: 0.2571 (0.3174) +eval (validation): [5] [ 0/31] eta: 0:02:12 time: 4.2796 data: 4.0132 max mem: 25051 +eval (validation): [5] [20/31] eta: 0:00:06 time: 0.4289 data: 0.0247 max mem: 25051 +eval (validation): [5] [30/31] eta: 0:00:00 time: 0.3919 data: 0.0024 max mem: 25051 +eval (validation): [5] Total time: 0:00:16 (0.5404 s / it) +cv: [5] best hparam: (5.1, 1.0) (034) ('034_lr5.1e+00_wd1.0e+00') loss: 2.081 acc: 0.653 f1: 0.633 bacc: 0.634 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/abide_dx__patch__attn/checkpoint-last.pth +train: [6] [ 0/800] eta: 1:15:35 lr: nan time: 5.6699 data: 5.2596 max mem: 25051 +train: [6] [ 20/800] eta: 0:09:25 lr: 0.000297 loss: 0.5118 (0.4637) grad: 0.3181 (0.3198) time: 0.4776 data: 0.0020 max mem: 25051 +train: [6] [ 40/800] eta: 0:07:42 lr: 0.000296 loss: 0.4100 (0.4584) grad: 0.2559 (0.2780) time: 0.4855 data: 0.0025 max mem: 25051 +train: [6] [ 60/800] eta: 0:07:03 lr: 0.000296 loss: 0.4350 (0.4564) grad: 0.2748 (0.2902) time: 0.4975 data: 0.0027 max mem: 25051 +train: [6] [ 80/800] eta: 0:06:37 lr: 0.000296 loss: 0.4350 (0.4633) grad: 0.2687 (0.2997) time: 0.4941 data: 0.0030 max mem: 25051 +train: [6] [100/800] eta: 0:06:14 lr: 0.000296 loss: 0.4350 (0.4625) grad: 0.2687 (0.2944) time: 0.4655 data: 0.0032 max mem: 25051 +train: [6] [120/800] eta: 0:06:00 lr: 0.000296 loss: 0.4334 (0.4566) grad: 0.2599 (0.2785) time: 0.4997 data: 0.0026 max mem: 25051 +train: [6] [140/800] eta: 0:05:44 lr: 0.000296 loss: 0.4197 (0.4458) grad: 0.2508 (0.2705) time: 0.4747 data: 0.0028 max mem: 25051 +train: [6] [160/800] eta: 0:05:48 lr: 0.000295 loss: 0.4271 (0.4555) grad: 0.2424 (0.2753) time: 0.7042 data: 0.2038 max mem: 25051 +train: [6] [180/800] eta: 0:05:33 lr: 0.000295 loss: 0.4213 (0.4519) grad: 0.2264 (0.2720) time: 0.4929 data: 0.0029 max mem: 25051 +train: [6] [200/800] eta: 0:05:23 lr: 0.000295 loss: 0.4358 (0.4538) grad: 0.2424 (0.2659) time: 0.5423 data: 0.0036 max mem: 25051 +train: [6] [220/800] eta: 0:05:09 lr: 0.000295 loss: 0.4406 (0.4515) grad: 0.2021 (0.2618) time: 0.4841 data: 0.0032 max mem: 25051 +train: [6] [240/800] eta: 0:04:56 lr: 0.000295 loss: 0.4358 (0.4538) grad: 0.2021 (0.2589) time: 0.4701 data: 0.0029 max mem: 25051 +train: [6] [260/800] eta: 0:04:43 lr: 0.000294 loss: 0.4591 (0.4524) grad: 0.1884 (0.2568) time: 0.4702 data: 0.0029 max mem: 25051 +train: [6] [280/800] eta: 0:04:30 lr: 0.000294 loss: 0.4447 (0.4513) grad: 0.1884 (0.2541) time: 0.4757 data: 0.0031 max mem: 25051 +train: [6] [300/800] eta: 0:04:26 lr: 0.000294 loss: 0.4586 (0.4519) grad: 0.1940 (0.2497) time: 0.7031 data: 0.2092 max mem: 25051 +train: [6] [320/800] eta: 0:04:14 lr: 0.000294 loss: 0.3997 (0.4476) grad: 0.1788 (0.2474) time: 0.4768 data: 0.0023 max mem: 25051 +train: [6] [340/800] eta: 0:04:02 lr: 0.000293 loss: 0.4004 (0.4481) grad: 0.1769 (0.2442) time: 0.4844 data: 0.0032 max mem: 25051 +train: [6] [360/800] eta: 0:03:50 lr: 0.000293 loss: 0.4434 (0.4519) grad: 0.1769 (0.2468) time: 0.4882 data: 0.0033 max mem: 25051 +train: [6] [380/800] eta: 0:03:39 lr: 0.000293 loss: 0.4434 (0.4522) grad: 0.1805 (0.2459) time: 0.4880 data: 0.0031 max mem: 25051 +train: [6] [400/800] eta: 0:03:28 lr: 0.000293 loss: 0.4748 (0.4541) grad: 0.1911 (0.2444) time: 0.5008 data: 0.0033 max mem: 25051 +train: [6] [420/800] eta: 0:03:17 lr: 0.000292 loss: 0.4774 (0.4567) grad: 0.2463 (0.2448) time: 0.4766 data: 0.0031 max mem: 25051 +train: [6] [440/800] eta: 0:03:10 lr: 0.000292 loss: 0.4550 (0.4563) grad: 0.1911 (0.2456) time: 0.7378 data: 0.2624 max mem: 25051 +train: [6] [460/800] eta: 0:02:59 lr: 0.000292 loss: 0.4550 (0.4558) grad: 0.2232 (0.2472) time: 0.4923 data: 0.0022 max mem: 25051 +train: [6] [480/800] eta: 0:02:48 lr: 0.000292 loss: 0.4387 (0.4527) grad: 0.2232 (0.2457) time: 0.4875 data: 0.0027 max mem: 25051 +train: [6] [500/800] eta: 0:02:37 lr: 0.000291 loss: 0.4261 (0.4524) grad: 0.2122 (0.2455) time: 0.4939 data: 0.0032 max mem: 25051 +train: [6] [520/800] eta: 0:02:26 lr: 0.000291 loss: 0.4352 (0.4516) grad: 0.2104 (0.2435) time: 0.4775 data: 0.0026 max mem: 25051 +train: [6] [540/800] eta: 0:02:15 lr: 0.000291 loss: 0.4352 (0.4512) grad: 0.2079 (0.2423) time: 0.4941 data: 0.0029 max mem: 25051 +train: [6] [560/800] eta: 0:02:05 lr: 0.000291 loss: 0.4182 (0.4499) grad: 0.1995 (0.2407) time: 0.5086 data: 0.0032 max mem: 25051 +train: [6] [580/800] eta: 0:01:56 lr: 0.000290 loss: 0.4182 (0.4507) grad: 0.1899 (0.2382) time: 0.7200 data: 0.2132 max mem: 25051 +train: [6] [600/800] eta: 0:01:45 lr: 0.000290 loss: 0.4344 (0.4507) grad: 0.1899 (0.2371) time: 0.5016 data: 0.0028 max mem: 25051 +train: [6] [620/800] eta: 0:01:34 lr: 0.000290 loss: 0.4182 (0.4497) grad: 0.1899 (0.2377) time: 0.4665 data: 0.0028 max mem: 25051 +train: [6] [640/800] eta: 0:01:23 lr: 0.000290 loss: 0.4361 (0.4498) grad: 0.1833 (0.2367) time: 0.4947 data: 0.0030 max mem: 25051 +train: [6] [660/800] eta: 0:01:13 lr: 0.000289 loss: 0.4237 (0.4489) grad: 0.1904 (0.2345) time: 0.4805 data: 0.0030 max mem: 25051 +train: [6] [680/800] eta: 0:01:02 lr: 0.000289 loss: 0.4072 (0.4484) grad: 0.2169 (0.2369) time: 0.4900 data: 0.0029 max mem: 25051 +train: [6] [700/800] eta: 0:00:52 lr: 0.000289 loss: 0.4153 (0.4480) grad: 0.2544 (0.2388) time: 0.4874 data: 0.0029 max mem: 25051 +train: [6] [720/800] eta: 0:00:42 lr: 0.000288 loss: 0.4237 (0.4481) grad: 0.2730 (0.2399) time: 0.6782 data: 0.2159 max mem: 25051 +train: [6] [740/800] eta: 0:00:31 lr: 0.000288 loss: 0.4405 (0.4482) grad: 0.2730 (0.2391) time: 0.5048 data: 0.0028 max mem: 25051 +train: [6] [760/800] eta: 0:00:20 lr: 0.000288 loss: 0.4428 (0.4482) grad: 0.2180 (0.2367) time: 0.5114 data: 0.0027 max mem: 25051 +train: [6] [780/800] eta: 0:00:10 lr: 0.000287 loss: 0.4446 (0.4481) grad: 0.2011 (0.2367) time: 0.4928 data: 0.0030 max mem: 25051 +train: [6] [799/800] eta: 0:00:00 lr: 0.000287 loss: 0.4405 (0.4477) grad: 0.1822 (0.2361) time: 0.4872 data: 0.0031 max mem: 25051 +train: [6] Total time: 0:06:58 (0.5232 s / it) +train: [6] Summary: lr: 0.000287 loss: 0.4405 (0.4477) grad: 0.1822 (0.2361) +eval (validation): [6] [ 0/31] eta: 0:02:08 time: 4.1462 data: 3.8479 max mem: 25051 +eval (validation): [6] [20/31] eta: 0:00:06 time: 0.4072 data: 0.0382 max mem: 25051 +eval (validation): [6] [30/31] eta: 0:00:00 time: 0.3905 data: 0.0218 max mem: 25051 +eval (validation): [6] Total time: 0:00:16 (0.5201 s / it) +cv: [6] best hparam: (0.61, 1.0) (021) ('021_lr6.1e-01_wd1.0e+00') loss: 0.628 acc: 0.653 f1: 0.630 bacc: 0.631 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/abide_dx__patch__attn/checkpoint-last.pth +train: [7] [ 0/800] eta: 0:57:40 lr: nan time: 4.3252 data: 3.9086 max mem: 25051 +train: [7] [ 20/800] eta: 0:08:37 lr: 0.000287 loss: 0.4707 (0.4830) grad: 0.2053 (0.1755) time: 0.4801 data: 0.0028 max mem: 25051 +train: [7] [ 40/800] eta: 0:07:14 lr: 0.000286 loss: 0.4262 (0.4457) grad: 0.2240 (0.2522) time: 0.4753 data: 0.0022 max mem: 25051 +train: [7] [ 60/800] eta: 0:06:38 lr: 0.000286 loss: 0.4262 (0.4480) grad: 0.2624 (0.2579) time: 0.4696 data: 0.0027 max mem: 25051 +train: [7] [ 80/800] eta: 0:06:21 lr: 0.000286 loss: 0.4236 (0.4411) grad: 0.2616 (0.2623) time: 0.5063 data: 0.0033 max mem: 25051 +train: [7] [100/800] eta: 0:06:05 lr: 0.000285 loss: 0.4095 (0.4336) grad: 0.2624 (0.2452) time: 0.4915 data: 0.0030 max mem: 25051 +train: [7] [120/800] eta: 0:05:50 lr: 0.000285 loss: 0.4050 (0.4310) grad: 0.2277 (0.2379) time: 0.4799 data: 0.0028 max mem: 25051 +train: [7] [140/800] eta: 0:05:35 lr: 0.000285 loss: 0.4050 (0.4311) grad: 0.2039 (0.2402) time: 0.4699 data: 0.0028 max mem: 25051 +train: [7] [160/800] eta: 0:05:40 lr: 0.000284 loss: 0.4050 (0.4253) grad: 0.1893 (0.2387) time: 0.6944 data: 0.2007 max mem: 25051 +train: [7] [180/800] eta: 0:05:28 lr: 0.000284 loss: 0.4113 (0.4259) grad: 0.1893 (0.2344) time: 0.5140 data: 0.0031 max mem: 25051 +train: [7] [200/800] eta: 0:05:15 lr: 0.000284 loss: 0.4184 (0.4242) grad: 0.1864 (0.2319) time: 0.4844 data: 0.0031 max mem: 25051 +train: [7] [220/800] eta: 0:05:02 lr: 0.000283 loss: 0.4113 (0.4245) grad: 0.1694 (0.2272) time: 0.4734 data: 0.0032 max mem: 25051 +train: [7] [240/800] eta: 0:04:49 lr: 0.000283 loss: 0.4184 (0.4273) grad: 0.1861 (0.2346) time: 0.4783 data: 0.0029 max mem: 25051 +train: [7] [260/800] eta: 0:04:38 lr: 0.000283 loss: 0.4184 (0.4308) grad: 0.1861 (0.2368) time: 0.4868 data: 0.0027 max mem: 25051 +train: [7] [280/800] eta: 0:04:27 lr: 0.000282 loss: 0.4079 (0.4270) grad: 0.2177 (0.2388) time: 0.5013 data: 0.0032 max mem: 25051 +train: [7] [300/800] eta: 0:04:23 lr: 0.000282 loss: 0.4073 (0.4240) grad: 0.2218 (0.2370) time: 0.7053 data: 0.2121 max mem: 25051 +train: [7] [320/800] eta: 0:04:11 lr: 0.000282 loss: 0.4041 (0.4279) grad: 0.2015 (0.2376) time: 0.4873 data: 0.0027 max mem: 25051 +train: [7] [340/800] eta: 0:03:59 lr: 0.000281 loss: 0.4041 (0.4291) grad: 0.2108 (0.2380) time: 0.4647 data: 0.0029 max mem: 25051 +train: [7] [360/800] eta: 0:03:48 lr: 0.000281 loss: 0.4041 (0.4256) grad: 0.1987 (0.2332) time: 0.4757 data: 0.0029 max mem: 25051 +train: [7] [380/800] eta: 0:03:36 lr: 0.000280 loss: 0.4208 (0.4257) grad: 0.1987 (0.2321) time: 0.4676 data: 0.0032 max mem: 25051 +train: [7] [400/800] eta: 0:03:25 lr: 0.000280 loss: 0.4208 (0.4267) grad: 0.1746 (0.2285) time: 0.4768 data: 0.0029 max mem: 25051 +train: [7] [420/800] eta: 0:03:14 lr: 0.000280 loss: 0.4012 (0.4272) grad: 0.1746 (0.2326) time: 0.4752 data: 0.0029 max mem: 25051 +train: [7] [440/800] eta: 0:03:06 lr: 0.000279 loss: 0.4387 (0.4273) grad: 0.2045 (0.2311) time: 0.6574 data: 0.2042 max mem: 25051 +train: [7] [460/800] eta: 0:02:56 lr: 0.000279 loss: 0.4411 (0.4277) grad: 0.1746 (0.2271) time: 0.5195 data: 0.0027 max mem: 25051 +train: [7] [480/800] eta: 0:02:45 lr: 0.000278 loss: 0.4424 (0.4278) grad: 0.1921 (0.2242) time: 0.4908 data: 0.0028 max mem: 25051 +train: [7] [500/800] eta: 0:02:34 lr: 0.000278 loss: 0.4424 (0.4275) grad: 0.1486 (0.2226) time: 0.4742 data: 0.0030 max mem: 25051 +train: [7] [520/800] eta: 0:02:24 lr: 0.000278 loss: 0.4237 (0.4260) grad: 0.1430 (0.2231) time: 0.5051 data: 0.0031 max mem: 25051 +train: [7] [540/800] eta: 0:02:13 lr: 0.000277 loss: 0.3885 (0.4231) grad: 0.1451 (0.2213) time: 0.4992 data: 0.0033 max mem: 25051 +train: [7] [560/800] eta: 0:02:03 lr: 0.000277 loss: 0.3830 (0.4213) grad: 0.1451 (0.2205) time: 0.4843 data: 0.0030 max mem: 25051 +train: [7] [580/800] eta: 0:01:54 lr: 0.000276 loss: 0.3771 (0.4206) grad: 0.1596 (0.2183) time: 0.6737 data: 0.2096 max mem: 25051 +train: [7] [600/800] eta: 0:01:43 lr: 0.000276 loss: 0.3721 (0.4183) grad: 0.1650 (0.2192) time: 0.4914 data: 0.0029 max mem: 25051 +train: [7] [620/800] eta: 0:01:33 lr: 0.000275 loss: 0.3843 (0.4197) grad: 0.1650 (0.2191) time: 0.4860 data: 0.0024 max mem: 25051 +train: [7] [640/800] eta: 0:01:22 lr: 0.000275 loss: 0.3985 (0.4211) grad: 0.1596 (0.2170) time: 0.4738 data: 0.0029 max mem: 25051 +train: [7] [660/800] eta: 0:01:12 lr: 0.000275 loss: 0.4094 (0.4209) grad: 0.2038 (0.2186) time: 0.5058 data: 0.0034 max mem: 25051 +train: [7] [680/800] eta: 0:01:01 lr: 0.000274 loss: 0.4316 (0.4206) grad: 0.1893 (0.2181) time: 0.4933 data: 0.0032 max mem: 25051 +train: [7] [700/800] eta: 0:00:51 lr: 0.000274 loss: 0.4346 (0.4225) grad: 0.2128 (0.2207) time: 0.4835 data: 0.0031 max mem: 25051 +train: [7] [720/800] eta: 0:00:41 lr: 0.000273 loss: 0.4102 (0.4214) grad: 0.2366 (0.2239) time: 0.6848 data: 0.2092 max mem: 25051 +train: [7] [740/800] eta: 0:00:31 lr: 0.000273 loss: 0.4190 (0.4215) grad: 0.2299 (0.2236) time: 0.5050 data: 0.0029 max mem: 25051 +train: [7] [760/800] eta: 0:00:20 lr: 0.000272 loss: 0.4278 (0.4231) grad: 0.2522 (0.2269) time: 0.4915 data: 0.0029 max mem: 25051 +train: [7] [780/800] eta: 0:00:10 lr: 0.000272 loss: 0.4190 (0.4228) grad: 0.2400 (0.2279) time: 0.5015 data: 0.0033 max mem: 25051 +train: [7] [799/800] eta: 0:00:00 lr: 0.000271 loss: 0.4264 (0.4222) grad: 0.2420 (0.2291) time: 0.4909 data: 0.0032 max mem: 25051 +train: [7] Total time: 0:06:53 (0.5167 s / it) +train: [7] Summary: lr: 0.000271 loss: 0.4264 (0.4222) grad: 0.2420 (0.2291) +eval (validation): [7] [ 0/31] eta: 0:02:06 time: 4.0940 data: 3.8411 max mem: 25051 +eval (validation): [7] [20/31] eta: 0:00:06 time: 0.4350 data: 0.0769 max mem: 25051 +eval (validation): [7] [30/31] eta: 0:00:00 time: 0.3968 data: 0.0444 max mem: 25051 +eval (validation): [7] Total time: 0:00:16 (0.5294 s / it) +cv: [7] best hparam: (6, 1.0) (035) ('035_lr6.0e+00_wd1.0e+00') loss: 2.684 acc: 0.637 f1: 0.622 bacc: 0.621 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/abide_dx__patch__attn/checkpoint-last.pth +train: [8] [ 0/800] eta: 0:56:16 lr: nan time: 4.2208 data: 3.8046 max mem: 25051 +train: [8] [ 20/800] eta: 0:08:32 lr: 0.000271 loss: 0.3955 (0.3985) grad: 0.2734 (0.2456) time: 0.4783 data: 0.0032 max mem: 25051 +train: [8] [ 40/800] eta: 0:07:12 lr: 0.000270 loss: 0.3955 (0.4043) grad: 0.2208 (0.2266) time: 0.4782 data: 0.0021 max mem: 25051 +train: [8] [ 60/800] eta: 0:06:36 lr: 0.000270 loss: 0.4186 (0.4238) grad: 0.2520 (0.2443) time: 0.4661 data: 0.0028 max mem: 25051 +train: [8] [ 80/800] eta: 0:06:13 lr: 0.000270 loss: 0.4234 (0.4393) grad: 0.2520 (0.2613) time: 0.4696 data: 0.0034 max mem: 25051 +train: [8] [100/800] eta: 0:05:59 lr: 0.000269 loss: 0.4234 (0.4295) grad: 0.2520 (0.2631) time: 0.4906 data: 0.0032 max mem: 25051 +train: [8] [120/800] eta: 0:05:46 lr: 0.000269 loss: 0.4377 (0.4343) grad: 0.2698 (0.2755) time: 0.4894 data: 0.0033 max mem: 25051 +train: [8] [140/800] eta: 0:05:31 lr: 0.000268 loss: 0.4351 (0.4308) grad: 0.2744 (0.2730) time: 0.4535 data: 0.0027 max mem: 25051 +train: [8] [160/800] eta: 0:05:33 lr: 0.000268 loss: 0.4345 (0.4288) grad: 0.2744 (0.2747) time: 0.6640 data: 0.2081 max mem: 25051 +train: [8] [180/800] eta: 0:05:20 lr: 0.000267 loss: 0.4309 (0.4190) grad: 0.2698 (0.2611) time: 0.4724 data: 0.0078 max mem: 25051 +train: [8] [200/800] eta: 0:05:08 lr: 0.000267 loss: 0.3875 (0.4183) grad: 0.2111 (0.2649) time: 0.4865 data: 0.0099 max mem: 25051 +train: [8] [220/800] eta: 0:04:55 lr: 0.000266 loss: 0.4063 (0.4225) grad: 0.2111 (0.2639) time: 0.4710 data: 0.0025 max mem: 25051 +train: [8] [240/800] eta: 0:04:43 lr: 0.000266 loss: 0.4218 (0.4250) grad: 0.1973 (0.2604) time: 0.4792 data: 0.0031 max mem: 25051 +train: [8] [260/800] eta: 0:04:33 lr: 0.000265 loss: 0.4396 (0.4230) grad: 0.2281 (0.2587) time: 0.4976 data: 0.0032 max mem: 25051 +train: [8] [280/800] eta: 0:04:21 lr: 0.000265 loss: 0.4439 (0.4244) grad: 0.1965 (0.2522) time: 0.4686 data: 0.0030 max mem: 25051 +train: [8] [300/800] eta: 0:04:17 lr: 0.000264 loss: 0.4218 (0.4218) grad: 0.1849 (0.2482) time: 0.6753 data: 0.2196 max mem: 25051 +train: [8] [320/800] eta: 0:04:06 lr: 0.000264 loss: 0.4000 (0.4232) grad: 0.1849 (0.2459) time: 0.4789 data: 0.0026 max mem: 25051 +train: [8] [340/800] eta: 0:03:54 lr: 0.000263 loss: 0.3938 (0.4222) grad: 0.1906 (0.2477) time: 0.4748 data: 0.0028 max mem: 25051 +train: [8] [360/800] eta: 0:03:43 lr: 0.000263 loss: 0.3938 (0.4240) grad: 0.2231 (0.2485) time: 0.4766 data: 0.0028 max mem: 25051 +train: [8] [380/800] eta: 0:03:32 lr: 0.000262 loss: 0.3861 (0.4215) grad: 0.2231 (0.2455) time: 0.4792 data: 0.0032 max mem: 25051 +train: [8] [400/800] eta: 0:03:22 lr: 0.000262 loss: 0.3918 (0.4201) grad: 0.1983 (0.2417) time: 0.4857 data: 0.0030 max mem: 25051 +train: [8] [420/800] eta: 0:03:11 lr: 0.000261 loss: 0.3760 (0.4178) grad: 0.1550 (0.2375) time: 0.4768 data: 0.0030 max mem: 25051 +train: [8] [440/800] eta: 0:03:04 lr: 0.000260 loss: 0.3654 (0.4171) grad: 0.1550 (0.2351) time: 0.6687 data: 0.1974 max mem: 25051 +train: [8] [460/800] eta: 0:02:53 lr: 0.000260 loss: 0.3760 (0.4163) grad: 0.1546 (0.2330) time: 0.4969 data: 0.0017 max mem: 25051 +train: [8] [480/800] eta: 0:02:43 lr: 0.000259 loss: 0.3619 (0.4146) grad: 0.1546 (0.2309) time: 0.5154 data: 0.0030 max mem: 25051 +train: [8] [500/800] eta: 0:02:33 lr: 0.000259 loss: 0.3755 (0.4134) grad: 0.1707 (0.2331) time: 0.4964 data: 0.0031 max mem: 25051 +train: [8] [520/800] eta: 0:02:22 lr: 0.000258 loss: 0.3755 (0.4121) grad: 0.1546 (0.2322) time: 0.4872 data: 0.0032 max mem: 25051 +train: [8] [540/800] eta: 0:02:12 lr: 0.000258 loss: 0.3739 (0.4099) grad: 0.1431 (0.2275) time: 0.4894 data: 0.0033 max mem: 25051 +train: [8] [560/800] eta: 0:02:02 lr: 0.000257 loss: 0.3755 (0.4092) grad: 0.1924 (0.2264) time: 0.4875 data: 0.0029 max mem: 25051 +train: [8] [580/800] eta: 0:01:53 lr: 0.000257 loss: 0.3686 (0.4083) grad: 0.1263 (0.2233) time: 0.6669 data: 0.2127 max mem: 25051 +train: [8] [600/800] eta: 0:01:42 lr: 0.000256 loss: 0.3489 (0.4057) grad: 0.1263 (0.2209) time: 0.4765 data: 0.0027 max mem: 25051 +train: [8] [620/800] eta: 0:01:32 lr: 0.000256 loss: 0.3590 (0.4052) grad: 0.1539 (0.2210) time: 0.4972 data: 0.0016 max mem: 25051 +train: [8] [640/800] eta: 0:01:21 lr: 0.000255 loss: 0.3686 (0.4049) grad: 0.1539 (0.2209) time: 0.4833 data: 0.0027 max mem: 25051 +train: [8] [660/800] eta: 0:01:11 lr: 0.000254 loss: 0.3721 (0.4041) grad: 0.1643 (0.2201) time: 0.4738 data: 0.0032 max mem: 25051 +train: [8] [680/800] eta: 0:01:01 lr: 0.000254 loss: 0.3892 (0.4038) grad: 0.1802 (0.2193) time: 0.4728 data: 0.0032 max mem: 25051 +train: [8] [700/800] eta: 0:00:50 lr: 0.000253 loss: 0.3732 (0.4028) grad: 0.1690 (0.2177) time: 0.4941 data: 0.0032 max mem: 25051 +train: [8] [720/800] eta: 0:00:41 lr: 0.000253 loss: 0.3732 (0.4022) grad: 0.1528 (0.2155) time: 0.6680 data: 0.2055 max mem: 25051 +train: [8] [740/800] eta: 0:00:30 lr: 0.000252 loss: 0.3863 (0.4027) grad: 0.1515 (0.2143) time: 0.5073 data: 0.0033 max mem: 25051 +train: [8] [760/800] eta: 0:00:20 lr: 0.000252 loss: 0.3863 (0.4024) grad: 0.1211 (0.2118) time: 0.4760 data: 0.0029 max mem: 25051 +train: [8] [780/800] eta: 0:00:10 lr: 0.000251 loss: 0.3920 (0.4016) grad: 0.1310 (0.2107) time: 0.4757 data: 0.0031 max mem: 25051 +train: [8] [799/800] eta: 0:00:00 lr: 0.000250 loss: 0.3920 (0.4006) grad: 0.1310 (0.2088) time: 0.4858 data: 0.0028 max mem: 25051 +train: [8] Total time: 0:06:48 (0.5108 s / it) +train: [8] Summary: lr: 0.000250 loss: 0.3920 (0.4006) grad: 0.1310 (0.2088) +eval (validation): [8] [ 0/31] eta: 0:02:34 time: 4.9765 data: 4.6895 max mem: 25051 +eval (validation): [8] [20/31] eta: 0:00:06 time: 0.3816 data: 0.0024 max mem: 25051 +eval (validation): [8] [30/31] eta: 0:00:00 time: 0.4084 data: 0.0365 max mem: 25051 +eval (validation): [8] Total time: 0:00:17 (0.5527 s / it) +cv: [8] best hparam: (1.4, 1.0) (026) ('026_lr1.4e+00_wd1.0e+00') loss: 2.017 acc: 0.645 f1: 0.634 bacc: 0.633 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/abide_dx__patch__attn/checkpoint-last.pth +train: [9] [ 0/800] eta: 0:57:22 lr: nan time: 4.3031 data: 3.9522 max mem: 25051 +train: [9] [ 20/800] eta: 0:08:38 lr: 0.000250 loss: 0.4134 (0.3743) grad: 0.1792 (0.2356) time: 0.4835 data: 0.0309 max mem: 25051 +train: [9] [ 40/800] eta: 0:07:14 lr: 0.000249 loss: 0.3837 (0.3716) grad: 0.1792 (0.2164) time: 0.4744 data: 0.0028 max mem: 25051 +train: [9] [ 60/800] eta: 0:06:38 lr: 0.000249 loss: 0.3837 (0.3752) grad: 0.2092 (0.2123) time: 0.4674 data: 0.0027 max mem: 25051 +train: [9] [ 80/800] eta: 0:06:15 lr: 0.000248 loss: 0.3857 (0.3835) grad: 0.1792 (0.2064) time: 0.4725 data: 0.0028 max mem: 25051 +train: [9] [100/800] eta: 0:05:59 lr: 0.000248 loss: 0.3857 (0.3922) grad: 0.1952 (0.2093) time: 0.4773 data: 0.0030 max mem: 25051 +train: [9] [120/800] eta: 0:05:44 lr: 0.000247 loss: 0.3873 (0.3922) grad: 0.1757 (0.2010) time: 0.4785 data: 0.0030 max mem: 25051 +train: [9] [140/800] eta: 0:05:31 lr: 0.000246 loss: 0.3873 (0.3942) grad: 0.1731 (0.2061) time: 0.4753 data: 0.0029 max mem: 25051 +train: [9] [160/800] eta: 0:05:43 lr: 0.000246 loss: 0.3868 (0.3913) grad: 0.1731 (0.2016) time: 0.7721 data: 0.2869 max mem: 25051 +train: [9] [180/800] eta: 0:05:30 lr: 0.000245 loss: 0.3834 (0.3915) grad: 0.1543 (0.2076) time: 0.5050 data: 0.0018 max mem: 25051 +train: [9] [200/800] eta: 0:05:17 lr: 0.000244 loss: 0.3768 (0.3929) grad: 0.1504 (0.1991) time: 0.4984 data: 0.0031 max mem: 25051 +train: [9] [220/800] eta: 0:05:04 lr: 0.000244 loss: 0.3666 (0.3894) grad: 0.1425 (0.1969) time: 0.4785 data: 0.0027 max mem: 25051 +train: [9] [240/800] eta: 0:04:51 lr: 0.000243 loss: 0.3766 (0.3913) grad: 0.1425 (0.1988) time: 0.4816 data: 0.0030 max mem: 25051 +train: [9] [260/800] eta: 0:04:40 lr: 0.000243 loss: 0.3861 (0.3930) grad: 0.1310 (0.1965) time: 0.5089 data: 0.0031 max mem: 25051 +train: [9] [280/800] eta: 0:04:28 lr: 0.000242 loss: 0.3835 (0.3935) grad: 0.1513 (0.1986) time: 0.4662 data: 0.0032 max mem: 25051 +train: [9] [300/800] eta: 0:04:25 lr: 0.000241 loss: 0.3766 (0.3901) grad: 0.1945 (0.1984) time: 0.7411 data: 0.2176 max mem: 25051 +train: [9] [320/800] eta: 0:04:13 lr: 0.000241 loss: 0.3747 (0.3893) grad: 0.1930 (0.1969) time: 0.4894 data: 0.0027 max mem: 25051 +train: [9] [340/800] eta: 0:04:02 lr: 0.000240 loss: 0.3589 (0.3873) grad: 0.1930 (0.1963) time: 0.4849 data: 0.0028 max mem: 25051 +train: [9] [360/800] eta: 0:03:49 lr: 0.000240 loss: 0.3556 (0.3852) grad: 0.1785 (0.1957) time: 0.4615 data: 0.0035 max mem: 25051 +train: [9] [380/800] eta: 0:03:38 lr: 0.000239 loss: 0.3747 (0.3889) grad: 0.1637 (0.1977) time: 0.4746 data: 0.0030 max mem: 25051 +train: [9] [400/800] eta: 0:03:27 lr: 0.000238 loss: 0.3740 (0.3882) grad: 0.1581 (0.1967) time: 0.4753 data: 0.0030 max mem: 25051 +train: [9] [420/800] eta: 0:03:16 lr: 0.000238 loss: 0.3782 (0.3873) grad: 0.1569 (0.1935) time: 0.4832 data: 0.0032 max mem: 25051 +train: [9] [440/800] eta: 0:03:08 lr: 0.000237 loss: 0.3811 (0.3864) grad: 0.1577 (0.1956) time: 0.6742 data: 0.2135 max mem: 25051 +train: [9] [460/800] eta: 0:02:57 lr: 0.000236 loss: 0.3782 (0.3869) grad: 0.1376 (0.1935) time: 0.5101 data: 0.0032 max mem: 25051 +train: [9] [480/800] eta: 0:02:46 lr: 0.000236 loss: 0.3820 (0.3883) grad: 0.1292 (0.1921) time: 0.4800 data: 0.0025 max mem: 25051 +train: [9] [500/800] eta: 0:02:35 lr: 0.000235 loss: 0.3820 (0.3892) grad: 0.1298 (0.1921) time: 0.4739 data: 0.0030 max mem: 25051 +train: [9] [520/800] eta: 0:02:25 lr: 0.000234 loss: 0.3965 (0.3892) grad: 0.1298 (0.1910) time: 0.4962 data: 0.0031 max mem: 25051 +train: [9] [540/800] eta: 0:02:14 lr: 0.000234 loss: 0.3924 (0.3880) grad: 0.1463 (0.1904) time: 0.4864 data: 0.0029 max mem: 25051 +train: [9] [560/800] eta: 0:02:03 lr: 0.000233 loss: 0.3737 (0.3878) grad: 0.1466 (0.1893) time: 0.4850 data: 0.0030 max mem: 25051 +train: [9] [580/800] eta: 0:01:54 lr: 0.000232 loss: 0.3716 (0.3874) grad: 0.1507 (0.1898) time: 0.6928 data: 0.2230 max mem: 25051 +train: [9] [600/800] eta: 0:01:44 lr: 0.000232 loss: 0.3716 (0.3880) grad: 0.1466 (0.1882) time: 0.5050 data: 0.0044 max mem: 25051 +train: [9] [620/800] eta: 0:01:33 lr: 0.000231 loss: 0.3772 (0.3873) grad: 0.1563 (0.1896) time: 0.4622 data: 0.0023 max mem: 25051 +train: [9] [640/800] eta: 0:01:22 lr: 0.000230 loss: 0.3775 (0.3875) grad: 0.1563 (0.1876) time: 0.4846 data: 0.0031 max mem: 25051 +train: [9] [660/800] eta: 0:01:12 lr: 0.000230 loss: 0.3903 (0.3882) grad: 0.1563 (0.1875) time: 0.5303 data: 0.0031 max mem: 25051 +train: [9] [680/800] eta: 0:01:02 lr: 0.000229 loss: 0.3969 (0.3889) grad: 0.1446 (0.1855) time: 0.5006 data: 0.0032 max mem: 25051 +train: [9] [700/800] eta: 0:00:51 lr: 0.000228 loss: 0.3834 (0.3878) grad: 0.1298 (0.1862) time: 0.4805 data: 0.0027 max mem: 25051 +train: [9] [720/800] eta: 0:00:41 lr: 0.000228 loss: 0.3834 (0.3882) grad: 0.1493 (0.1888) time: 0.6988 data: 0.2281 max mem: 25051 +train: [9] [740/800] eta: 0:00:31 lr: 0.000227 loss: 0.3806 (0.3877) grad: 0.1383 (0.1870) time: 0.5254 data: 0.0033 max mem: 25051 +train: [9] [760/800] eta: 0:00:20 lr: 0.000226 loss: 0.3480 (0.3860) grad: 0.1438 (0.1863) time: 0.4743 data: 0.0031 max mem: 25051 +train: [9] [780/800] eta: 0:00:10 lr: 0.000226 loss: 0.3491 (0.3853) grad: 0.1440 (0.1855) time: 0.4502 data: 0.0029 max mem: 25051 +train: [9] [799/800] eta: 0:00:00 lr: 0.000225 loss: 0.3480 (0.3847) grad: 0.1328 (0.1856) time: 0.4628 data: 0.0029 max mem: 25051 +train: [9] Total time: 0:06:54 (0.5182 s / it) +train: [9] Summary: lr: 0.000225 loss: 0.3480 (0.3847) grad: 0.1328 (0.1856) +eval (validation): [9] [ 0/31] eta: 0:02:14 time: 4.3293 data: 4.0214 max mem: 25051 +eval (validation): [9] [20/31] eta: 0:00:06 time: 0.3849 data: 0.0069 max mem: 25051 +eval (validation): [9] [30/31] eta: 0:00:00 time: 0.3797 data: 0.0066 max mem: 25051 +eval (validation): [9] Total time: 0:00:15 (0.5144 s / it) +cv: [9] best hparam: (0.61, 1.0) (021) ('021_lr6.1e-01_wd1.0e+00') loss: 0.743 acc: 0.669 f1: 0.663 bacc: 0.663 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/abide_dx__patch__attn/checkpoint-last.pth +train: [10] [ 0/800] eta: 0:58:07 lr: nan time: 4.3591 data: 3.9560 max mem: 25051 +train: [10] [ 20/800] eta: 0:08:47 lr: 0.000224 loss: 0.3633 (0.3479) grad: 0.1520 (0.1735) time: 0.4925 data: 0.0028 max mem: 25051 +train: [10] [ 40/800] eta: 0:07:16 lr: 0.000224 loss: 0.3617 (0.3597) grad: 0.1520 (0.1861) time: 0.4657 data: 0.0025 max mem: 25051 +train: [10] [ 60/800] eta: 0:06:45 lr: 0.000223 loss: 0.3617 (0.3584) grad: 0.1844 (0.1907) time: 0.4933 data: 0.0025 max mem: 25051 +train: [10] [ 80/800] eta: 0:06:22 lr: 0.000222 loss: 0.3565 (0.3554) grad: 0.1844 (0.1884) time: 0.4815 data: 0.0029 max mem: 25051 +train: [10] [100/800] eta: 0:06:03 lr: 0.000222 loss: 0.3565 (0.3571) grad: 0.1779 (0.1894) time: 0.4735 data: 0.0031 max mem: 25051 +train: [10] [120/800] eta: 0:05:48 lr: 0.000221 loss: 0.3647 (0.3637) grad: 0.1761 (0.1855) time: 0.4769 data: 0.0032 max mem: 25051 +train: [10] [140/800] eta: 0:05:34 lr: 0.000220 loss: 0.3647 (0.3669) grad: 0.1624 (0.1842) time: 0.4737 data: 0.0027 max mem: 25051 +train: [10] [160/800] eta: 0:05:38 lr: 0.000220 loss: 0.3592 (0.3649) grad: 0.1403 (0.1760) time: 0.6814 data: 0.2046 max mem: 25051 +train: [10] [180/800] eta: 0:05:23 lr: 0.000219 loss: 0.3477 (0.3592) grad: 0.1397 (0.1761) time: 0.4629 data: 0.0019 max mem: 25051 +train: [10] [200/800] eta: 0:05:11 lr: 0.000218 loss: 0.3384 (0.3608) grad: 0.1140 (0.1761) time: 0.4991 data: 0.0029 max mem: 25051 +train: [10] [220/800] eta: 0:04:59 lr: 0.000217 loss: 0.3468 (0.3643) grad: 0.1163 (0.1809) time: 0.4871 data: 0.0031 max mem: 25051 +train: [10] [240/800] eta: 0:04:47 lr: 0.000217 loss: 0.3557 (0.3637) grad: 0.1258 (0.1837) time: 0.4739 data: 0.0030 max mem: 25051 +train: [10] [260/800] eta: 0:04:34 lr: 0.000216 loss: 0.3734 (0.3647) grad: 0.1264 (0.1797) time: 0.4647 data: 0.0031 max mem: 25051 +train: [10] [280/800] eta: 0:04:23 lr: 0.000215 loss: 0.3734 (0.3661) grad: 0.1452 (0.1805) time: 0.4867 data: 0.0030 max mem: 25051 +train: [10] [300/800] eta: 0:04:19 lr: 0.000215 loss: 0.3694 (0.3667) grad: 0.1476 (0.1809) time: 0.6871 data: 0.2166 max mem: 25051 +train: [10] [320/800] eta: 0:04:07 lr: 0.000214 loss: 0.3739 (0.3676) grad: 0.1476 (0.1781) time: 0.4705 data: 0.0025 max mem: 25051 +train: [10] [340/800] eta: 0:03:56 lr: 0.000213 loss: 0.3739 (0.3675) grad: 0.1476 (0.1772) time: 0.4872 data: 0.0028 max mem: 25051 +train: [10] [360/800] eta: 0:03:45 lr: 0.000213 loss: 0.3744 (0.3685) grad: 0.1361 (0.1767) time: 0.4932 data: 0.0028 max mem: 25051 +train: [10] [380/800] eta: 0:03:34 lr: 0.000212 loss: 0.3744 (0.3676) grad: 0.1324 (0.1746) time: 0.4736 data: 0.0031 max mem: 25051 +train: [10] [400/800] eta: 0:03:23 lr: 0.000211 loss: 0.3594 (0.3665) grad: 0.1413 (0.1737) time: 0.4711 data: 0.0034 max mem: 25051 +train: [10] [420/800] eta: 0:03:12 lr: 0.000210 loss: 0.3544 (0.3659) grad: 0.1413 (0.1726) time: 0.4688 data: 0.0032 max mem: 25051 +train: [10] [440/800] eta: 0:03:06 lr: 0.000210 loss: 0.3489 (0.3643) grad: 0.1474 (0.1733) time: 0.7153 data: 0.2103 max mem: 25051 +train: [10] [460/800] eta: 0:02:55 lr: 0.000209 loss: 0.3387 (0.3634) grad: 0.1600 (0.1733) time: 0.4721 data: 0.0028 max mem: 25051 +train: [10] [480/800] eta: 0:02:44 lr: 0.000208 loss: 0.3405 (0.3637) grad: 0.1417 (0.1712) time: 0.4741 data: 0.0027 max mem: 25051 +train: [10] [500/800] eta: 0:02:33 lr: 0.000207 loss: 0.3489 (0.3653) grad: 0.1474 (0.1716) time: 0.4821 data: 0.0031 max mem: 25051 +train: [10] [520/800] eta: 0:02:22 lr: 0.000207 loss: 0.3722 (0.3654) grad: 0.1417 (0.1712) time: 0.4694 data: 0.0032 max mem: 25051 +train: [10] [540/800] eta: 0:02:12 lr: 0.000206 loss: 0.3563 (0.3648) grad: 0.1266 (0.1700) time: 0.4783 data: 0.0032 max mem: 25051 +train: [10] [560/800] eta: 0:02:01 lr: 0.000205 loss: 0.3522 (0.3636) grad: 0.1472 (0.1727) time: 0.4796 data: 0.0029 max mem: 25051 +train: [10] [580/800] eta: 0:01:53 lr: 0.000205 loss: 0.3522 (0.3634) grad: 0.1184 (0.1703) time: 0.6940 data: 0.2088 max mem: 25051 +train: [10] [600/800] eta: 0:01:42 lr: 0.000204 loss: 0.3128 (0.3613) grad: 0.1278 (0.1704) time: 0.5029 data: 0.0030 max mem: 25051 +train: [10] [620/800] eta: 0:01:32 lr: 0.000203 loss: 0.3300 (0.3614) grad: 0.1421 (0.1709) time: 0.4936 data: 0.0032 max mem: 25051 +train: [10] [640/800] eta: 0:01:22 lr: 0.000202 loss: 0.3319 (0.3614) grad: 0.1370 (0.1710) time: 0.4841 data: 0.0030 max mem: 25051 +train: [10] [660/800] eta: 0:01:11 lr: 0.000202 loss: 0.3319 (0.3617) grad: 0.1698 (0.1742) time: 0.4842 data: 0.0034 max mem: 25051 +train: [10] [680/800] eta: 0:01:01 lr: 0.000201 loss: 0.3569 (0.3625) grad: 0.1939 (0.1755) time: 0.4908 data: 0.0032 max mem: 25051 +train: [10] [700/800] eta: 0:00:51 lr: 0.000200 loss: 0.3656 (0.3623) grad: 0.1698 (0.1739) time: 0.4749 data: 0.0032 max mem: 25051 +train: [10] [720/800] eta: 0:00:41 lr: 0.000199 loss: 0.3376 (0.3616) grad: 0.1531 (0.1735) time: 0.6573 data: 0.2035 max mem: 25051 +train: [10] [740/800] eta: 0:00:30 lr: 0.000199 loss: 0.3656 (0.3621) grad: 0.1351 (0.1726) time: 0.5076 data: 0.0036 max mem: 25051 +train: [10] [760/800] eta: 0:00:20 lr: 0.000198 loss: 0.3361 (0.3618) grad: 0.1344 (0.1726) time: 0.4786 data: 0.0030 max mem: 25051 +train: [10] [780/800] eta: 0:00:10 lr: 0.000197 loss: 0.3457 (0.3616) grad: 0.1351 (0.1727) time: 0.4758 data: 0.0031 max mem: 25051 +train: [10] [799/800] eta: 0:00:00 lr: 0.000196 loss: 0.3483 (0.3612) grad: 0.1352 (0.1728) time: 0.4652 data: 0.0029 max mem: 25051 +train: [10] Total time: 0:06:48 (0.5112 s / it) +train: [10] Summary: lr: 0.000196 loss: 0.3483 (0.3612) grad: 0.1352 (0.1728) +eval (validation): [10] [ 0/31] eta: 0:02:51 time: 5.5340 data: 5.2732 max mem: 25051 +eval (validation): [10] [20/31] eta: 0:00:06 time: 0.3596 data: 0.0017 max mem: 25051 +eval (validation): [10] [30/31] eta: 0:00:00 time: 0.3676 data: 0.0020 max mem: 25051 +eval (validation): [10] Total time: 0:00:16 (0.5358 s / it) +cv: [10] best hparam: (0.44, 1.0) (019) ('019_lr4.4e-01_wd1.0e+00') loss: 0.635 acc: 0.661 f1: 0.654 bacc: 0.653 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/abide_dx__patch__attn/checkpoint-last.pth +train: [11] [ 0/800] eta: 0:57:25 lr: nan time: 4.3063 data: 3.9235 max mem: 25051 +train: [11] [ 20/800] eta: 0:08:38 lr: 0.000196 loss: 0.3974 (0.3879) grad: 0.1209 (0.1798) time: 0.4827 data: 0.0019 max mem: 25051 +train: [11] [ 40/800] eta: 0:07:15 lr: 0.000195 loss: 0.3717 (0.3871) grad: 0.1525 (0.1742) time: 0.4756 data: 0.0031 max mem: 25051 +train: [11] [ 60/800] eta: 0:06:41 lr: 0.000194 loss: 0.3443 (0.3595) grad: 0.1525 (0.1645) time: 0.4826 data: 0.0031 max mem: 25051 +train: [11] [ 80/800] eta: 0:06:21 lr: 0.000193 loss: 0.3443 (0.3616) grad: 0.1803 (0.1795) time: 0.4871 data: 0.0031 max mem: 25051 +train: [11] [100/800] eta: 0:06:02 lr: 0.000193 loss: 0.3394 (0.3526) grad: 0.1803 (0.1753) time: 0.4740 data: 0.0029 max mem: 25051 +train: [11] [120/800] eta: 0:05:47 lr: 0.000192 loss: 0.3391 (0.3570) grad: 0.1990 (0.1800) time: 0.4783 data: 0.0028 max mem: 25051 +train: [11] [140/800] eta: 0:05:34 lr: 0.000191 loss: 0.3663 (0.3590) grad: 0.1991 (0.1778) time: 0.4806 data: 0.0028 max mem: 25051 +train: [11] [160/800] eta: 0:05:37 lr: 0.000190 loss: 0.3573 (0.3582) grad: 0.1935 (0.1807) time: 0.6645 data: 0.2164 max mem: 25051 +train: [11] [180/800] eta: 0:05:22 lr: 0.000190 loss: 0.3611 (0.3553) grad: 0.1935 (0.1793) time: 0.4615 data: 0.0019 max mem: 25051 +train: [11] [200/800] eta: 0:05:09 lr: 0.000189 loss: 0.3611 (0.3553) grad: 0.1554 (0.1782) time: 0.4763 data: 0.0030 max mem: 25051 +train: [11] [220/800] eta: 0:04:57 lr: 0.000188 loss: 0.3453 (0.3551) grad: 0.1709 (0.1781) time: 0.4944 data: 0.0029 max mem: 25051 +train: [11] [240/800] eta: 0:04:45 lr: 0.000187 loss: 0.3529 (0.3571) grad: 0.1641 (0.1790) time: 0.4717 data: 0.0030 max mem: 25051 +train: [11] [260/800] eta: 0:04:33 lr: 0.000187 loss: 0.3529 (0.3556) grad: 0.1621 (0.1761) time: 0.4700 data: 0.0027 max mem: 25051 +train: [11] [280/800] eta: 0:04:23 lr: 0.000186 loss: 0.3529 (0.3552) grad: 0.1380 (0.1718) time: 0.4951 data: 0.0031 max mem: 25051 +train: [11] [300/800] eta: 0:04:19 lr: 0.000185 loss: 0.3400 (0.3511) grad: 0.1438 (0.1711) time: 0.6872 data: 0.2192 max mem: 25051 +train: [11] [320/800] eta: 0:04:07 lr: 0.000184 loss: 0.3393 (0.3520) grad: 0.1380 (0.1699) time: 0.4770 data: 0.0024 max mem: 25051 +train: [11] [340/800] eta: 0:03:55 lr: 0.000184 loss: 0.3400 (0.3526) grad: 0.1431 (0.1713) time: 0.4663 data: 0.0028 max mem: 25051 +train: [11] [360/800] eta: 0:03:45 lr: 0.000183 loss: 0.3400 (0.3538) grad: 0.1532 (0.1716) time: 0.4928 data: 0.0028 max mem: 25051 +train: [11] [380/800] eta: 0:03:34 lr: 0.000182 loss: 0.3645 (0.3546) grad: 0.1710 (0.1750) time: 0.4771 data: 0.0028 max mem: 25051 +train: [11] [400/800] eta: 0:03:23 lr: 0.000181 loss: 0.3551 (0.3535) grad: 0.1710 (0.1745) time: 0.4927 data: 0.0035 max mem: 25051 +train: [11] [420/800] eta: 0:03:12 lr: 0.000181 loss: 0.3527 (0.3539) grad: 0.1710 (0.1757) time: 0.4789 data: 0.0032 max mem: 25051 +train: [11] [440/800] eta: 0:03:06 lr: 0.000180 loss: 0.3430 (0.3535) grad: 0.1696 (0.1767) time: 0.7190 data: 0.2188 max mem: 25051 +train: [11] [460/800] eta: 0:02:55 lr: 0.000179 loss: 0.3276 (0.3516) grad: 0.1507 (0.1752) time: 0.5096 data: 0.0029 max mem: 25051 +train: [11] [480/800] eta: 0:02:44 lr: 0.000178 loss: 0.3341 (0.3530) grad: 0.1507 (0.1762) time: 0.4667 data: 0.0033 max mem: 25051 +train: [11] [500/800] eta: 0:02:34 lr: 0.000177 loss: 0.3417 (0.3527) grad: 0.1537 (0.1795) time: 0.4850 data: 0.0032 max mem: 25051 +train: [11] [520/800] eta: 0:02:23 lr: 0.000177 loss: 0.3470 (0.3533) grad: 0.1537 (0.1810) time: 0.4865 data: 0.0031 max mem: 25051 +train: [11] [540/800] eta: 0:02:12 lr: 0.000176 loss: 0.3555 (0.3538) grad: 0.2088 (0.1811) time: 0.4884 data: 0.0030 max mem: 25051 +train: [11] [560/800] eta: 0:02:02 lr: 0.000175 loss: 0.3555 (0.3558) grad: 0.1888 (0.1814) time: 0.4744 data: 0.0029 max mem: 25051 +train: [11] [580/800] eta: 0:01:53 lr: 0.000174 loss: 0.3716 (0.3564) grad: 0.1828 (0.1813) time: 0.7078 data: 0.2164 max mem: 25051 +train: [11] [600/800] eta: 0:01:43 lr: 0.000174 loss: 0.3716 (0.3570) grad: 0.1813 (0.1830) time: 0.4790 data: 0.0028 max mem: 25051 +train: [11] [620/800] eta: 0:01:32 lr: 0.000173 loss: 0.3714 (0.3563) grad: 0.1810 (0.1818) time: 0.4750 data: 0.0025 max mem: 25051 +train: [11] [640/800] eta: 0:01:22 lr: 0.000172 loss: 0.3575 (0.3558) grad: 0.1810 (0.1829) time: 0.4698 data: 0.0029 max mem: 25051 +train: [11] [660/800] eta: 0:01:11 lr: 0.000171 loss: 0.3471 (0.3564) grad: 0.1539 (0.1817) time: 0.4683 data: 0.0031 max mem: 25051 +train: [11] [680/800] eta: 0:01:01 lr: 0.000170 loss: 0.3471 (0.3570) grad: 0.1539 (0.1810) time: 0.5171 data: 0.0034 max mem: 25051 +train: [11] [700/800] eta: 0:00:51 lr: 0.000170 loss: 0.3471 (0.3561) grad: 0.1392 (0.1813) time: 0.4982 data: 0.0033 max mem: 25051 +train: [11] [720/800] eta: 0:00:41 lr: 0.000169 loss: 0.3471 (0.3568) grad: 0.1392 (0.1836) time: 0.6725 data: 0.2148 max mem: 25051 +train: [11] [740/800] eta: 0:00:30 lr: 0.000168 loss: 0.3471 (0.3566) grad: 0.1390 (0.1824) time: 0.5121 data: 0.0033 max mem: 25051 +train: [11] [760/800] eta: 0:00:20 lr: 0.000167 loss: 0.3440 (0.3564) grad: 0.1484 (0.1834) time: 0.4791 data: 0.0024 max mem: 25051 +train: [11] [780/800] eta: 0:00:10 lr: 0.000167 loss: 0.3545 (0.3563) grad: 0.1504 (0.1847) time: 0.4672 data: 0.0028 max mem: 25051 +train: [11] [799/800] eta: 0:00:00 lr: 0.000166 loss: 0.3545 (0.3562) grad: 0.1504 (0.1870) time: 0.4654 data: 0.0029 max mem: 25051 +train: [11] Total time: 0:06:50 (0.5128 s / it) +train: [11] Summary: lr: 0.000166 loss: 0.3545 (0.3562) grad: 0.1504 (0.1870) +eval (validation): [11] [ 0/31] eta: 0:02:15 time: 4.3696 data: 4.0771 max mem: 25051 +eval (validation): [11] [20/31] eta: 0:00:06 time: 0.4445 data: 0.0025 max mem: 25051 +eval (validation): [11] [30/31] eta: 0:00:00 time: 0.3681 data: 0.0019 max mem: 25051 +eval (validation): [11] Total time: 0:00:16 (0.5462 s / it) +cv: [11] best hparam: (0.38, 1.0) (018) ('018_lr3.8e-01_wd1.0e+00') loss: 0.639 acc: 0.677 f1: 0.665 bacc: 0.663 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/abide_dx__patch__attn/checkpoint-last.pth +train: [12] [ 0/800] eta: 1:02:34 lr: nan time: 4.6930 data: 4.2864 max mem: 25051 +train: [12] [ 20/800] eta: 0:08:53 lr: 0.000165 loss: 0.3506 (0.3399) grad: 0.1187 (0.1173) time: 0.4829 data: 0.0019 max mem: 25051 +train: [12] [ 40/800] eta: 0:07:18 lr: 0.000164 loss: 0.3184 (0.3372) grad: 0.1084 (0.1267) time: 0.4649 data: 0.0027 max mem: 25051 +train: [12] [ 60/800] eta: 0:06:42 lr: 0.000163 loss: 0.3519 (0.3490) grad: 0.1219 (0.1401) time: 0.4769 data: 0.0030 max mem: 25051 +train: [12] [ 80/800] eta: 0:06:19 lr: 0.000163 loss: 0.3427 (0.3380) grad: 0.1246 (0.1478) time: 0.4734 data: 0.0027 max mem: 25051 +train: [12] [100/800] eta: 0:06:00 lr: 0.000162 loss: 0.3753 (0.3648) grad: 0.1376 (0.1532) time: 0.4663 data: 0.0029 max mem: 25051 +train: [12] [120/800] eta: 0:05:46 lr: 0.000161 loss: 0.3753 (0.3617) grad: 0.1632 (0.1537) time: 0.4834 data: 0.0031 max mem: 25051 +train: [12] [140/800] eta: 0:05:32 lr: 0.000160 loss: 0.3641 (0.3642) grad: 0.1661 (0.1572) time: 0.4746 data: 0.0030 max mem: 25051 +train: [12] [160/800] eta: 0:05:35 lr: 0.000160 loss: 0.3779 (0.3632) grad: 0.1661 (0.1556) time: 0.6674 data: 0.2074 max mem: 25051 +train: [12] [180/800] eta: 0:05:24 lr: 0.000159 loss: 0.3454 (0.3611) grad: 0.1482 (0.1604) time: 0.5096 data: 0.0031 max mem: 25051 +train: [12] [200/800] eta: 0:05:10 lr: 0.000158 loss: 0.3621 (0.3633) grad: 0.1482 (0.1615) time: 0.4709 data: 0.0030 max mem: 25051 +train: [12] [220/800] eta: 0:04:58 lr: 0.000157 loss: 0.3629 (0.3622) grad: 0.1726 (0.1692) time: 0.4811 data: 0.0030 max mem: 25051 +train: [12] [240/800] eta: 0:04:45 lr: 0.000156 loss: 0.3634 (0.3614) grad: 0.1895 (0.1725) time: 0.4674 data: 0.0030 max mem: 25051 +train: [12] [260/800] eta: 0:04:34 lr: 0.000156 loss: 0.3654 (0.3599) grad: 0.1895 (0.1740) time: 0.4895 data: 0.0030 max mem: 25051 +train: [12] [280/800] eta: 0:04:23 lr: 0.000155 loss: 0.3634 (0.3576) grad: 0.1549 (0.1712) time: 0.4728 data: 0.0030 max mem: 25051 +train: [12] [300/800] eta: 0:04:19 lr: 0.000154 loss: 0.3351 (0.3548) grad: 0.1498 (0.1746) time: 0.6817 data: 0.2245 max mem: 25051 +train: [12] [320/800] eta: 0:04:07 lr: 0.000153 loss: 0.3271 (0.3554) grad: 0.1484 (0.1726) time: 0.4800 data: 0.0026 max mem: 25051 +train: [12] [340/800] eta: 0:03:55 lr: 0.000152 loss: 0.3271 (0.3563) grad: 0.1280 (0.1714) time: 0.4699 data: 0.0023 max mem: 25051 +train: [12] [360/800] eta: 0:03:44 lr: 0.000152 loss: 0.3271 (0.3554) grad: 0.1279 (0.1686) time: 0.4755 data: 0.0028 max mem: 25051 +train: [12] [380/800] eta: 0:03:33 lr: 0.000151 loss: 0.3730 (0.3564) grad: 0.1204 (0.1686) time: 0.4688 data: 0.0032 max mem: 25051 +train: [12] [400/800] eta: 0:03:22 lr: 0.000150 loss: 0.3499 (0.3560) grad: 0.1279 (0.1699) time: 0.4818 data: 0.0032 max mem: 25051 +train: [12] [420/800] eta: 0:03:12 lr: 0.000149 loss: 0.3504 (0.3578) grad: 0.1279 (0.1757) time: 0.4898 data: 0.0032 max mem: 25051 +train: [12] [440/800] eta: 0:03:05 lr: 0.000149 loss: 0.3403 (0.3555) grad: 0.1595 (0.1753) time: 0.6895 data: 0.2139 max mem: 25051 +train: [12] [460/800] eta: 0:02:54 lr: 0.000148 loss: 0.3504 (0.3580) grad: 0.1390 (0.1731) time: 0.4719 data: 0.0018 max mem: 25051 +train: [12] [480/800] eta: 0:02:43 lr: 0.000147 loss: 0.3552 (0.3580) grad: 0.1235 (0.1717) time: 0.4937 data: 0.0022 max mem: 25051 +train: [12] [500/800] eta: 0:02:33 lr: 0.000146 loss: 0.3421 (0.3579) grad: 0.1171 (0.1719) time: 0.4864 data: 0.0030 max mem: 25051 +train: [12] [520/800] eta: 0:02:22 lr: 0.000145 loss: 0.3574 (0.3583) grad: 0.1200 (0.1704) time: 0.4637 data: 0.0029 max mem: 25051 +train: [12] [540/800] eta: 0:02:12 lr: 0.000145 loss: 0.3451 (0.3570) grad: 0.1209 (0.1688) time: 0.4748 data: 0.0032 max mem: 25051 +train: [12] [560/800] eta: 0:02:01 lr: 0.000144 loss: 0.3490 (0.3574) grad: 0.1242 (0.1686) time: 0.4760 data: 0.0029 max mem: 25051 +train: [12] [580/800] eta: 0:01:53 lr: 0.000143 loss: 0.3599 (0.3580) grad: 0.1242 (0.1671) time: 0.7115 data: 0.2064 max mem: 25051 +train: [12] [600/800] eta: 0:01:42 lr: 0.000142 loss: 0.3599 (0.3580) grad: 0.1249 (0.1707) time: 0.4976 data: 0.0025 max mem: 25051 +train: [12] [620/800] eta: 0:01:32 lr: 0.000141 loss: 0.3604 (0.3577) grad: 0.1249 (0.1696) time: 0.4925 data: 0.0031 max mem: 25051 +train: [12] [640/800] eta: 0:01:21 lr: 0.000141 loss: 0.3392 (0.3564) grad: 0.1249 (0.1694) time: 0.4854 data: 0.0033 max mem: 25051 +train: [12] [660/800] eta: 0:01:11 lr: 0.000140 loss: 0.3342 (0.3553) grad: 0.1346 (0.1683) time: 0.4825 data: 0.0033 max mem: 25051 +train: [12] [680/800] eta: 0:01:01 lr: 0.000139 loss: 0.3283 (0.3541) grad: 0.1174 (0.1682) time: 0.4820 data: 0.0031 max mem: 25051 +train: [12] [700/800] eta: 0:00:50 lr: 0.000138 loss: 0.3093 (0.3534) grad: 0.1131 (0.1671) time: 0.4562 data: 0.0028 max mem: 25051 +train: [12] [720/800] eta: 0:00:40 lr: 0.000138 loss: 0.3220 (0.3531) grad: 0.1114 (0.1662) time: 0.6482 data: 0.2054 max mem: 25051 +train: [12] [740/800] eta: 0:00:30 lr: 0.000137 loss: 0.3330 (0.3538) grad: 0.1114 (0.1669) time: 0.4993 data: 0.0030 max mem: 25051 +train: [12] [760/800] eta: 0:00:20 lr: 0.000136 loss: 0.3403 (0.3539) grad: 0.1375 (0.1687) time: 0.5000 data: 0.0029 max mem: 25051 +train: [12] [780/800] eta: 0:00:10 lr: 0.000135 loss: 0.3474 (0.3543) grad: 0.1498 (0.1684) time: 0.4550 data: 0.0032 max mem: 25051 +train: [12] [799/800] eta: 0:00:00 lr: 0.000134 loss: 0.3420 (0.3539) grad: 0.1737 (0.1688) time: 0.5021 data: 0.0027 max mem: 25051 +train: [12] Total time: 0:06:48 (0.5105 s / it) +train: [12] Summary: lr: 0.000134 loss: 0.3420 (0.3539) grad: 0.1737 (0.1688) +eval (validation): [12] [ 0/31] eta: 0:02:16 time: 4.4133 data: 4.1202 max mem: 25051 +eval (validation): [12] [20/31] eta: 0:00:07 time: 0.4745 data: 0.0028 max mem: 25051 +eval (validation): [12] [30/31] eta: 0:00:00 time: 0.3907 data: 0.0022 max mem: 25051 +eval (validation): [12] Total time: 0:00:17 (0.5628 s / it) +cv: [12] best hparam: (1.2, 1.0) (025) ('025_lr1.2e+00_wd1.0e+00') loss: 2.274 acc: 0.645 f1: 0.631 bacc: 0.631 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/abide_dx__patch__attn/checkpoint-last.pth +train: [13] [ 0/800] eta: 0:56:24 lr: nan time: 4.2311 data: 3.8859 max mem: 25051 +train: [13] [ 20/800] eta: 0:08:28 lr: 0.000134 loss: 0.3333 (0.3211) grad: 0.1635 (0.1573) time: 0.4727 data: 0.0023 max mem: 25051 +train: [13] [ 40/800] eta: 0:07:14 lr: 0.000133 loss: 0.3333 (0.3361) grad: 0.1223 (0.1402) time: 0.4888 data: 0.0022 max mem: 25051 +train: [13] [ 60/800] eta: 0:06:42 lr: 0.000132 loss: 0.3421 (0.3401) grad: 0.1223 (0.1393) time: 0.4854 data: 0.0028 max mem: 25051 +train: [13] [ 80/800] eta: 0:06:21 lr: 0.000131 loss: 0.3421 (0.3447) grad: 0.1207 (0.1339) time: 0.4873 data: 0.0030 max mem: 25051 +train: [13] [100/800] eta: 0:06:04 lr: 0.000130 loss: 0.3474 (0.3428) grad: 0.1076 (0.1491) time: 0.4863 data: 0.0031 max mem: 25051 +train: [13] [120/800] eta: 0:05:50 lr: 0.000130 loss: 0.3562 (0.3489) grad: 0.1101 (0.1505) time: 0.4839 data: 0.0028 max mem: 25051 +train: [13] [140/800] eta: 0:05:34 lr: 0.000129 loss: 0.3600 (0.3505) grad: 0.1337 (0.1537) time: 0.4615 data: 0.0025 max mem: 25051 +train: [13] [160/800] eta: 0:05:41 lr: 0.000128 loss: 0.3562 (0.3531) grad: 0.1706 (0.1550) time: 0.7188 data: 0.2315 max mem: 25051 +train: [13] [180/800] eta: 0:05:27 lr: 0.000127 loss: 0.3600 (0.3569) grad: 0.1337 (0.1553) time: 0.4864 data: 0.0020 max mem: 25051 +train: [13] [200/800] eta: 0:05:14 lr: 0.000127 loss: 0.3493 (0.3546) grad: 0.1337 (0.1592) time: 0.4776 data: 0.0029 max mem: 25051 +train: [13] [220/800] eta: 0:05:00 lr: 0.000126 loss: 0.3509 (0.3573) grad: 0.1751 (0.1631) time: 0.4597 data: 0.0031 max mem: 25051 +train: [13] [240/800] eta: 0:04:48 lr: 0.000125 loss: 0.3493 (0.3550) grad: 0.1751 (0.1709) time: 0.4868 data: 0.0026 max mem: 25051 +train: [13] [260/800] eta: 0:04:37 lr: 0.000124 loss: 0.3493 (0.3539) grad: 0.1676 (0.1687) time: 0.4955 data: 0.0029 max mem: 25051 +train: [13] [280/800] eta: 0:04:25 lr: 0.000124 loss: 0.3478 (0.3526) grad: 0.1751 (0.1720) time: 0.4719 data: 0.0030 max mem: 25051 +train: [13] [300/800] eta: 0:04:20 lr: 0.000123 loss: 0.3478 (0.3556) grad: 0.1620 (0.1743) time: 0.6663 data: 0.2126 max mem: 25051 +train: [13] [320/800] eta: 0:04:08 lr: 0.000122 loss: 0.3586 (0.3550) grad: 0.1613 (0.1715) time: 0.4847 data: 0.0026 max mem: 25051 +train: [13] [340/800] eta: 0:03:57 lr: 0.000121 loss: 0.3586 (0.3560) grad: 0.1470 (0.1698) time: 0.4783 data: 0.0024 max mem: 25051 +train: [13] [360/800] eta: 0:03:46 lr: 0.000120 loss: 0.3588 (0.3554) grad: 0.1390 (0.1718) time: 0.4763 data: 0.0032 max mem: 25051 +train: [13] [380/800] eta: 0:03:35 lr: 0.000120 loss: 0.3415 (0.3547) grad: 0.1186 (0.1703) time: 0.4738 data: 0.0032 max mem: 25051 +train: [13] [400/800] eta: 0:03:24 lr: 0.000119 loss: 0.3394 (0.3541) grad: 0.1390 (0.1719) time: 0.4946 data: 0.0030 max mem: 25051 +train: [13] [420/800] eta: 0:03:13 lr: 0.000118 loss: 0.3209 (0.3535) grad: 0.1557 (0.1695) time: 0.4823 data: 0.0034 max mem: 25051 +train: [13] [440/800] eta: 0:03:06 lr: 0.000117 loss: 0.3209 (0.3526) grad: 0.1028 (0.1669) time: 0.6961 data: 0.2141 max mem: 25051 +train: [13] [460/800] eta: 0:02:55 lr: 0.000117 loss: 0.3302 (0.3540) grad: 0.1107 (0.1653) time: 0.4920 data: 0.0024 max mem: 25051 +train: [13] [480/800] eta: 0:02:45 lr: 0.000116 loss: 0.3333 (0.3539) grad: 0.1132 (0.1676) time: 0.4843 data: 0.0029 max mem: 25051 +train: [13] [500/800] eta: 0:02:34 lr: 0.000115 loss: 0.3333 (0.3531) grad: 0.1313 (0.1684) time: 0.5099 data: 0.0030 max mem: 25051 +train: [13] [520/800] eta: 0:02:23 lr: 0.000114 loss: 0.3333 (0.3522) grad: 0.1247 (0.1662) time: 0.4714 data: 0.0031 max mem: 25051 +train: [13] [540/800] eta: 0:02:13 lr: 0.000114 loss: 0.3292 (0.3525) grad: 0.1313 (0.1645) time: 0.4873 data: 0.0031 max mem: 25051 +train: [13] [560/800] eta: 0:02:02 lr: 0.000113 loss: 0.3292 (0.3523) grad: 0.1136 (0.1642) time: 0.4806 data: 0.0031 max mem: 25051 +train: [13] [580/800] eta: 0:01:53 lr: 0.000112 loss: 0.3214 (0.3512) grad: 0.1112 (0.1639) time: 0.6790 data: 0.2016 max mem: 25051 +train: [13] [600/800] eta: 0:01:43 lr: 0.000111 loss: 0.3174 (0.3505) grad: 0.1248 (0.1647) time: 0.5175 data: 0.0028 max mem: 25051 +train: [13] [620/800] eta: 0:01:33 lr: 0.000110 loss: 0.3136 (0.3494) grad: 0.1308 (0.1649) time: 0.5044 data: 0.0034 max mem: 25051 +train: [13] [640/800] eta: 0:01:22 lr: 0.000110 loss: 0.3094 (0.3480) grad: 0.1439 (0.1676) time: 0.5191 data: 0.0033 max mem: 25051 +train: [13] [660/800] eta: 0:01:12 lr: 0.000109 loss: 0.3094 (0.3477) grad: 0.1535 (0.1676) time: 0.4638 data: 0.0030 max mem: 25051 +train: [13] [680/800] eta: 0:01:01 lr: 0.000108 loss: 0.3189 (0.3481) grad: 0.1535 (0.1665) time: 0.4833 data: 0.0030 max mem: 25051 +train: [13] [700/800] eta: 0:00:51 lr: 0.000107 loss: 0.3293 (0.3486) grad: 0.1535 (0.1665) time: 0.4900 data: 0.0029 max mem: 25051 +train: [13] [720/800] eta: 0:00:41 lr: 0.000107 loss: 0.3586 (0.3486) grad: 0.1471 (0.1673) time: 0.6785 data: 0.2052 max mem: 25051 +train: [13] [740/800] eta: 0:00:31 lr: 0.000106 loss: 0.3586 (0.3488) grad: 0.1453 (0.1664) time: 0.4859 data: 0.0020 max mem: 25051 +train: [13] [760/800] eta: 0:00:20 lr: 0.000105 loss: 0.3531 (0.3495) grad: 0.1471 (0.1675) time: 0.4949 data: 0.0024 max mem: 25051 +train: [13] [780/800] eta: 0:00:10 lr: 0.000104 loss: 0.3657 (0.3496) grad: 0.1546 (0.1689) time: 0.4846 data: 0.0031 max mem: 25051 +train: [13] [799/800] eta: 0:00:00 lr: 0.000104 loss: 0.3631 (0.3493) grad: 0.1372 (0.1680) time: 0.4689 data: 0.0029 max mem: 25051 +train: [13] Total time: 0:06:52 (0.5152 s / it) +train: [13] Summary: lr: 0.000104 loss: 0.3631 (0.3493) grad: 0.1372 (0.1680) +eval (validation): [13] [ 0/31] eta: 0:02:07 time: 4.1125 data: 3.8484 max mem: 25051 +eval (validation): [13] [20/31] eta: 0:00:06 time: 0.4330 data: 0.0372 max mem: 25051 +eval (validation): [13] [30/31] eta: 0:00:00 time: 0.4236 data: 0.0322 max mem: 25051 +eval (validation): [13] Total time: 0:00:16 (0.5405 s / it) +cv: [13] best hparam: (0.27, 1.0) (016) ('016_lr2.7e-01_wd1.0e+00') loss: 0.634 acc: 0.653 f1: 0.636 bacc: 0.636 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/abide_dx__patch__attn/checkpoint-last.pth +train: [14] [ 0/800] eta: 1:00:37 lr: nan time: 4.5471 data: 4.1844 max mem: 25051 +train: [14] [ 20/800] eta: 0:08:53 lr: 0.000103 loss: 0.3358 (0.3512) grad: 0.1678 (0.1597) time: 0.4904 data: 0.0020 max mem: 25051 +train: [14] [ 40/800] eta: 0:07:19 lr: 0.000102 loss: 0.3506 (0.3604) grad: 0.1165 (0.1684) time: 0.4684 data: 0.0023 max mem: 25051 +train: [14] [ 60/800] eta: 0:06:44 lr: 0.000101 loss: 0.3506 (0.3535) grad: 0.1699 (0.1851) time: 0.4829 data: 0.0031 max mem: 25051 +train: [14] [ 80/800] eta: 0:06:22 lr: 0.000101 loss: 0.3506 (0.3559) grad: 0.1678 (0.1860) time: 0.4817 data: 0.0030 max mem: 25051 +train: [14] [100/800] eta: 0:06:06 lr: 0.000100 loss: 0.3506 (0.3556) grad: 0.1494 (0.1790) time: 0.4964 data: 0.0035 max mem: 25051 +train: [14] [120/800] eta: 0:05:52 lr: 0.000099 loss: 0.3462 (0.3632) grad: 0.1734 (0.1888) time: 0.4856 data: 0.0031 max mem: 25051 +train: [14] [140/800] eta: 0:05:40 lr: 0.000099 loss: 0.3615 (0.3634) grad: 0.1734 (0.1929) time: 0.5029 data: 0.0031 max mem: 25051 +train: [14] [160/800] eta: 0:05:46 lr: 0.000098 loss: 0.3491 (0.3596) grad: 0.1494 (0.1814) time: 0.7245 data: 0.2152 max mem: 25051 +train: [14] [180/800] eta: 0:05:31 lr: 0.000097 loss: 0.3491 (0.3574) grad: 0.1219 (0.1750) time: 0.4856 data: 0.0030 max mem: 25051 +train: [14] [200/800] eta: 0:05:17 lr: 0.000096 loss: 0.3491 (0.3582) grad: 0.1219 (0.1725) time: 0.4750 data: 0.0031 max mem: 25051 +train: [14] [220/800] eta: 0:05:04 lr: 0.000096 loss: 0.3491 (0.3568) grad: 0.1169 (0.1702) time: 0.4820 data: 0.0030 max mem: 25051 +train: [14] [240/800] eta: 0:04:52 lr: 0.000095 loss: 0.3575 (0.3568) grad: 0.1204 (0.1702) time: 0.4862 data: 0.0028 max mem: 25051 +train: [14] [260/800] eta: 0:04:40 lr: 0.000094 loss: 0.3643 (0.3572) grad: 0.1204 (0.1678) time: 0.4986 data: 0.0032 max mem: 25051 +train: [14] [280/800] eta: 0:04:28 lr: 0.000093 loss: 0.3575 (0.3536) grad: 0.1134 (0.1636) time: 0.4708 data: 0.0029 max mem: 25051 +train: [14] [300/800] eta: 0:04:24 lr: 0.000093 loss: 0.3517 (0.3531) grad: 0.1108 (0.1600) time: 0.6995 data: 0.2211 max mem: 25051 +train: [14] [320/800] eta: 0:04:12 lr: 0.000092 loss: 0.3328 (0.3514) grad: 0.1044 (0.1586) time: 0.4958 data: 0.0026 max mem: 25051 +train: [14] [340/800] eta: 0:04:00 lr: 0.000091 loss: 0.3278 (0.3513) grad: 0.1132 (0.1567) time: 0.4781 data: 0.0030 max mem: 25051 +train: [14] [360/800] eta: 0:03:49 lr: 0.000090 loss: 0.3328 (0.3502) grad: 0.1132 (0.1583) time: 0.4772 data: 0.0030 max mem: 25051 +train: [14] [380/800] eta: 0:03:38 lr: 0.000090 loss: 0.3346 (0.3508) grad: 0.1333 (0.1606) time: 0.4942 data: 0.0028 max mem: 25051 +train: [14] [400/800] eta: 0:03:27 lr: 0.000089 loss: 0.3450 (0.3502) grad: 0.1561 (0.1644) time: 0.5113 data: 0.0034 max mem: 25051 +train: [14] [420/800] eta: 0:03:16 lr: 0.000088 loss: 0.3564 (0.3513) grad: 0.1803 (0.1658) time: 0.4829 data: 0.0029 max mem: 25051 +train: [14] [440/800] eta: 0:03:09 lr: 0.000088 loss: 0.3519 (0.3533) grad: 0.1869 (0.1688) time: 0.7070 data: 0.2406 max mem: 25051 +train: [14] [460/800] eta: 0:02:58 lr: 0.000087 loss: 0.3519 (0.3527) grad: 0.1869 (0.1697) time: 0.4936 data: 0.0023 max mem: 25051 +train: [14] [480/800] eta: 0:02:47 lr: 0.000086 loss: 0.3519 (0.3524) grad: 0.1850 (0.1684) time: 0.4764 data: 0.0023 max mem: 25051 +train: [14] [500/800] eta: 0:02:36 lr: 0.000085 loss: 0.3465 (0.3518) grad: 0.1517 (0.1689) time: 0.5102 data: 0.0030 max mem: 25051 +train: [14] [520/800] eta: 0:02:25 lr: 0.000085 loss: 0.3287 (0.3516) grad: 0.1356 (0.1673) time: 0.4879 data: 0.0031 max mem: 25051 +train: [14] [540/800] eta: 0:02:15 lr: 0.000084 loss: 0.3287 (0.3515) grad: 0.1085 (0.1653) time: 0.5074 data: 0.0031 max mem: 25051 +train: [14] [560/800] eta: 0:02:04 lr: 0.000083 loss: 0.3293 (0.3514) grad: 0.1006 (0.1643) time: 0.4897 data: 0.0030 max mem: 25051 +train: [14] [580/800] eta: 0:01:55 lr: 0.000083 loss: 0.3290 (0.3498) grad: 0.1407 (0.1682) time: 0.6858 data: 0.2148 max mem: 25051 +train: [14] [600/800] eta: 0:01:44 lr: 0.000082 loss: 0.3290 (0.3509) grad: 0.1407 (0.1681) time: 0.4737 data: 0.0022 max mem: 25051 +train: [14] [620/800] eta: 0:01:33 lr: 0.000081 loss: 0.3375 (0.3518) grad: 0.1776 (0.1700) time: 0.4613 data: 0.0025 max mem: 25051 +train: [14] [640/800] eta: 0:01:23 lr: 0.000081 loss: 0.3290 (0.3516) grad: 0.1947 (0.1710) time: 0.4736 data: 0.0027 max mem: 25051 +train: [14] [660/800] eta: 0:01:12 lr: 0.000080 loss: 0.3621 (0.3507) grad: 0.1549 (0.1706) time: 0.4758 data: 0.0029 max mem: 25051 +train: [14] [680/800] eta: 0:01:02 lr: 0.000079 loss: 0.3316 (0.3494) grad: 0.1549 (0.1698) time: 0.5143 data: 0.0033 max mem: 25051 +train: [14] [700/800] eta: 0:00:51 lr: 0.000078 loss: 0.3316 (0.3503) grad: 0.1275 (0.1687) time: 0.4721 data: 0.0031 max mem: 25051 +train: [14] [720/800] eta: 0:00:41 lr: 0.000078 loss: 0.3316 (0.3504) grad: 0.1293 (0.1681) time: 0.6776 data: 0.2138 max mem: 25051 +train: [14] [740/800] eta: 0:00:31 lr: 0.000077 loss: 0.3290 (0.3497) grad: 0.1463 (0.1694) time: 0.4729 data: 0.0026 max mem: 25051 +train: [14] [760/800] eta: 0:00:20 lr: 0.000076 loss: 0.3603 (0.3508) grad: 0.1463 (0.1689) time: 0.5082 data: 0.0200 max mem: 25051 +train: [14] [780/800] eta: 0:00:10 lr: 0.000076 loss: 0.3396 (0.3503) grad: 0.1629 (0.1687) time: 0.4999 data: 0.0022 max mem: 25051 +train: [14] [799/800] eta: 0:00:00 lr: 0.000075 loss: 0.3396 (0.3507) grad: 0.1572 (0.1686) time: 0.4830 data: 0.0032 max mem: 25051 +train: [14] Total time: 0:06:55 (0.5189 s / it) +train: [14] Summary: lr: 0.000075 loss: 0.3396 (0.3507) grad: 0.1572 (0.1686) +eval (validation): [14] [ 0/31] eta: 0:02:13 time: 4.3065 data: 3.9994 max mem: 25051 +eval (validation): [14] [20/31] eta: 0:00:06 time: 0.4326 data: 0.0032 max mem: 25051 +eval (validation): [14] [30/31] eta: 0:00:00 time: 0.3616 data: 0.0023 max mem: 25051 +eval (validation): [14] Total time: 0:00:16 (0.5373 s / it) +cv: [14] best hparam: (1.2, 1.0) (025) ('025_lr1.2e+00_wd1.0e+00') loss: 2.369 acc: 0.645 f1: 0.631 bacc: 0.631 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/abide_dx__patch__attn/checkpoint-last.pth +train: [15] [ 0/800] eta: 0:55:40 lr: nan time: 4.1755 data: 3.8183 max mem: 25051 +train: [15] [ 20/800] eta: 0:08:58 lr: 0.000074 loss: 0.3204 (0.3179) grad: 0.1505 (0.1365) time: 0.5167 data: 0.0019 max mem: 25051 +train: [15] [ 40/800] eta: 0:07:29 lr: 0.000074 loss: 0.3204 (0.3499) grad: 0.1547 (0.1925) time: 0.4882 data: 0.0023 max mem: 25051 +train: [15] [ 60/800] eta: 0:06:53 lr: 0.000073 loss: 0.3407 (0.3440) grad: 0.1505 (0.1737) time: 0.4889 data: 0.0029 max mem: 25051 +train: [15] [ 80/800] eta: 0:06:28 lr: 0.000072 loss: 0.3407 (0.3455) grad: 0.1412 (0.1639) time: 0.4835 data: 0.0029 max mem: 25051 +train: [15] [100/800] eta: 0:06:10 lr: 0.000072 loss: 0.3121 (0.3306) grad: 0.1325 (0.1590) time: 0.4898 data: 0.0031 max mem: 25051 +train: [15] [120/800] eta: 0:05:55 lr: 0.000071 loss: 0.3006 (0.3367) grad: 0.1324 (0.1617) time: 0.4882 data: 0.0029 max mem: 25051 +train: [15] [140/800] eta: 0:05:41 lr: 0.000070 loss: 0.3207 (0.3364) grad: 0.1324 (0.1614) time: 0.4796 data: 0.0026 max mem: 25051 +train: [15] [160/800] eta: 0:05:47 lr: 0.000070 loss: 0.3207 (0.3367) grad: 0.1434 (0.1611) time: 0.7308 data: 0.2536 max mem: 25051 +train: [15] [180/800] eta: 0:05:32 lr: 0.000069 loss: 0.3385 (0.3387) grad: 0.1434 (0.1561) time: 0.4781 data: 0.0022 max mem: 25051 +train: [15] [200/800] eta: 0:05:18 lr: 0.000068 loss: 0.3453 (0.3418) grad: 0.1217 (0.1534) time: 0.4754 data: 0.0026 max mem: 25051 +train: [15] [220/800] eta: 0:05:05 lr: 0.000068 loss: 0.3504 (0.3426) grad: 0.1191 (0.1505) time: 0.4909 data: 0.0031 max mem: 25051 +train: [15] [240/800] eta: 0:04:52 lr: 0.000067 loss: 0.3504 (0.3444) grad: 0.1191 (0.1582) time: 0.4794 data: 0.0031 max mem: 25051 +train: [15] [260/800] eta: 0:04:40 lr: 0.000066 loss: 0.3570 (0.3454) grad: 0.1390 (0.1647) time: 0.4736 data: 0.0031 max mem: 25051 +train: [15] [280/800] eta: 0:04:28 lr: 0.000066 loss: 0.3363 (0.3453) grad: 0.1884 (0.1682) time: 0.4703 data: 0.0027 max mem: 25051 +train: [15] [300/800] eta: 0:04:23 lr: 0.000065 loss: 0.3363 (0.3444) grad: 0.1884 (0.1639) time: 0.6873 data: 0.2089 max mem: 25051 +train: [15] [320/800] eta: 0:04:11 lr: 0.000064 loss: 0.3363 (0.3443) grad: 0.1392 (0.1620) time: 0.4921 data: 0.0027 max mem: 25051 +train: [15] [340/800] eta: 0:03:59 lr: 0.000064 loss: 0.3309 (0.3424) grad: 0.1337 (0.1609) time: 0.4628 data: 0.0031 max mem: 25051 +train: [15] [360/800] eta: 0:03:47 lr: 0.000063 loss: 0.3372 (0.3440) grad: 0.1373 (0.1642) time: 0.4637 data: 0.0030 max mem: 25051 +train: [15] [380/800] eta: 0:03:36 lr: 0.000063 loss: 0.3358 (0.3426) grad: 0.1466 (0.1665) time: 0.4658 data: 0.0030 max mem: 25051 +train: [15] [400/800] eta: 0:03:25 lr: 0.000062 loss: 0.3441 (0.3441) grad: 0.1666 (0.1661) time: 0.4659 data: 0.0029 max mem: 25051 +train: [15] [420/800] eta: 0:03:13 lr: 0.000061 loss: 0.3523 (0.3447) grad: 0.1716 (0.1663) time: 0.4634 data: 0.0028 max mem: 25051 +train: [15] [440/800] eta: 0:03:06 lr: 0.000061 loss: 0.3586 (0.3447) grad: 0.1391 (0.1653) time: 0.7057 data: 0.2057 max mem: 25051 +train: [15] [460/800] eta: 0:02:55 lr: 0.000060 loss: 0.3727 (0.3456) grad: 0.1391 (0.1638) time: 0.4775 data: 0.0023 max mem: 25051 +train: [15] [480/800] eta: 0:02:45 lr: 0.000059 loss: 0.3460 (0.3448) grad: 0.1373 (0.1634) time: 0.4810 data: 0.0032 max mem: 25051 +train: [15] [500/800] eta: 0:02:34 lr: 0.000059 loss: 0.3460 (0.3463) grad: 0.1368 (0.1628) time: 0.4790 data: 0.0029 max mem: 25051 +train: [15] [520/800] eta: 0:02:23 lr: 0.000058 loss: 0.3508 (0.3475) grad: 0.1373 (0.1625) time: 0.4725 data: 0.0028 max mem: 25051 +train: [15] [540/800] eta: 0:02:13 lr: 0.000057 loss: 0.3508 (0.3482) grad: 0.1354 (0.1611) time: 0.4807 data: 0.0030 max mem: 25051 +train: [15] [560/800] eta: 0:02:02 lr: 0.000057 loss: 0.3662 (0.3490) grad: 0.1294 (0.1600) time: 0.4709 data: 0.0028 max mem: 25051 +train: [15] [580/800] eta: 0:01:53 lr: 0.000056 loss: 0.3564 (0.3491) grad: 0.1470 (0.1614) time: 0.7034 data: 0.2123 max mem: 25051 +train: [15] [600/800] eta: 0:01:43 lr: 0.000056 loss: 0.3441 (0.3484) grad: 0.1339 (0.1606) time: 0.4948 data: 0.0023 max mem: 25051 +train: [15] [620/800] eta: 0:01:32 lr: 0.000055 loss: 0.3441 (0.3489) grad: 0.1470 (0.1615) time: 0.4744 data: 0.0028 max mem: 25051 +train: [15] [640/800] eta: 0:01:22 lr: 0.000054 loss: 0.3218 (0.3486) grad: 0.1681 (0.1640) time: 0.4775 data: 0.0030 max mem: 25051 +train: [15] [660/800] eta: 0:01:11 lr: 0.000054 loss: 0.3218 (0.3485) grad: 0.1681 (0.1660) time: 0.4751 data: 0.0030 max mem: 25051 +train: [15] [680/800] eta: 0:01:01 lr: 0.000053 loss: 0.3499 (0.3493) grad: 0.2089 (0.1682) time: 0.4724 data: 0.0028 max mem: 25051 +train: [15] [700/800] eta: 0:00:51 lr: 0.000053 loss: 0.3386 (0.3496) grad: 0.1983 (0.1673) time: 0.4684 data: 0.0029 max mem: 25051 +train: [15] [720/800] eta: 0:00:41 lr: 0.000052 loss: 0.3386 (0.3492) grad: 0.1583 (0.1679) time: 0.6758 data: 0.2042 max mem: 25051 +train: [15] [740/800] eta: 0:00:30 lr: 0.000051 loss: 0.3353 (0.3489) grad: 0.1583 (0.1688) time: 0.5200 data: 0.0213 max mem: 25051 +train: [15] [760/800] eta: 0:00:20 lr: 0.000051 loss: 0.3353 (0.3492) grad: 0.1258 (0.1678) time: 0.4724 data: 0.0030 max mem: 25051 +train: [15] [780/800] eta: 0:00:10 lr: 0.000050 loss: 0.3353 (0.3493) grad: 0.1229 (0.1675) time: 0.4757 data: 0.0030 max mem: 25051 +train: [15] [799/800] eta: 0:00:00 lr: 0.000050 loss: 0.3295 (0.3485) grad: 0.1181 (0.1661) time: 0.4715 data: 0.0029 max mem: 25051 +train: [15] Total time: 0:06:49 (0.5120 s / it) +train: [15] Summary: lr: 0.000050 loss: 0.3295 (0.3485) grad: 0.1181 (0.1661) +eval (validation): [15] [ 0/31] eta: 0:02:09 time: 4.1680 data: 3.9189 max mem: 25051 +eval (validation): [15] [20/31] eta: 0:00:06 time: 0.4106 data: 0.0374 max mem: 25051 +eval (validation): [15] [30/31] eta: 0:00:00 time: 0.3643 data: 0.0016 max mem: 25051 +eval (validation): [15] Total time: 0:00:16 (0.5241 s / it) +cv: [15] best hparam: (0.32, 1.0) (017) ('017_lr3.2e-01_wd1.0e+00') loss: 0.641 acc: 0.653 f1: 0.641 bacc: 0.640 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/abide_dx__patch__attn/checkpoint-last.pth +train: [16] [ 0/800] eta: 0:56:07 lr: nan time: 4.2096 data: 3.8573 max mem: 25051 +train: [16] [ 20/800] eta: 0:09:26 lr: 0.000049 loss: 0.3093 (0.3283) grad: 0.1516 (0.1413) time: 0.5524 data: 0.0135 max mem: 25051 +train: [16] [ 40/800] eta: 0:07:38 lr: 0.000048 loss: 0.3116 (0.3408) grad: 0.0982 (0.1325) time: 0.4736 data: 0.0029 max mem: 25051 +train: [16] [ 60/800] eta: 0:06:55 lr: 0.000048 loss: 0.3116 (0.3308) grad: 0.1233 (0.1287) time: 0.4741 data: 0.0030 max mem: 25051 +train: [16] [ 80/800] eta: 0:06:28 lr: 0.000047 loss: 0.3093 (0.3287) grad: 0.1244 (0.1310) time: 0.4737 data: 0.0030 max mem: 25051 +train: [16] [100/800] eta: 0:06:08 lr: 0.000047 loss: 0.3256 (0.3365) grad: 0.1244 (0.1361) time: 0.4750 data: 0.0031 max mem: 25051 +train: [16] [120/800] eta: 0:05:51 lr: 0.000046 loss: 0.3256 (0.3383) grad: 0.1244 (0.1370) time: 0.4721 data: 0.0029 max mem: 25051 +train: [16] [140/800] eta: 0:05:36 lr: 0.000046 loss: 0.3206 (0.3345) grad: 0.1435 (0.1504) time: 0.4679 data: 0.0028 max mem: 25051 +train: [16] [160/800] eta: 0:05:40 lr: 0.000045 loss: 0.3206 (0.3323) grad: 0.2153 (0.1589) time: 0.6896 data: 0.2055 max mem: 25051 +train: [16] [180/800] eta: 0:05:26 lr: 0.000045 loss: 0.3206 (0.3355) grad: 0.2139 (0.1627) time: 0.4720 data: 0.0018 max mem: 25051 +train: [16] [200/800] eta: 0:05:12 lr: 0.000044 loss: 0.3206 (0.3349) grad: 0.2139 (0.1641) time: 0.4725 data: 0.0029 max mem: 25051 +train: [16] [220/800] eta: 0:04:59 lr: 0.000043 loss: 0.3447 (0.3355) grad: 0.1743 (0.1646) time: 0.4736 data: 0.0028 max mem: 25051 +train: [16] [240/800] eta: 0:04:47 lr: 0.000043 loss: 0.3493 (0.3361) grad: 0.1421 (0.1618) time: 0.4703 data: 0.0030 max mem: 25051 +train: [16] [260/800] eta: 0:04:35 lr: 0.000042 loss: 0.3328 (0.3366) grad: 0.1280 (0.1576) time: 0.4756 data: 0.0029 max mem: 25051 +train: [16] [280/800] eta: 0:04:23 lr: 0.000042 loss: 0.3328 (0.3364) grad: 0.1253 (0.1556) time: 0.4687 data: 0.0028 max mem: 25051 +train: [16] [300/800] eta: 0:04:20 lr: 0.000041 loss: 0.3241 (0.3335) grad: 0.1280 (0.1595) time: 0.7071 data: 0.2110 max mem: 25051 +train: [16] [320/800] eta: 0:04:08 lr: 0.000041 loss: 0.3153 (0.3324) grad: 0.1345 (0.1594) time: 0.4814 data: 0.0026 max mem: 25051 +train: [16] [340/800] eta: 0:03:57 lr: 0.000040 loss: 0.3181 (0.3324) grad: 0.1488 (0.1616) time: 0.4822 data: 0.0031 max mem: 25051 +train: [16] [360/800] eta: 0:03:45 lr: 0.000040 loss: 0.3104 (0.3296) grad: 0.1495 (0.1629) time: 0.4785 data: 0.0030 max mem: 25051 +train: [16] [380/800] eta: 0:03:35 lr: 0.000039 loss: 0.3104 (0.3280) grad: 0.1480 (0.1627) time: 0.4820 data: 0.0032 max mem: 25051 +train: [16] [400/800] eta: 0:03:24 lr: 0.000039 loss: 0.3214 (0.3297) grad: 0.1455 (0.1632) time: 0.4736 data: 0.0030 max mem: 25051 +train: [16] [420/800] eta: 0:03:13 lr: 0.000038 loss: 0.3013 (0.3294) grad: 0.1480 (0.1655) time: 0.4753 data: 0.0029 max mem: 25051 +train: [16] [440/800] eta: 0:03:05 lr: 0.000038 loss: 0.3168 (0.3289) grad: 0.1546 (0.1658) time: 0.6856 data: 0.2263 max mem: 25051 +train: [16] [460/800] eta: 0:02:55 lr: 0.000037 loss: 0.3209 (0.3290) grad: 0.1416 (0.1646) time: 0.4819 data: 0.0019 max mem: 25051 +train: [16] [480/800] eta: 0:02:44 lr: 0.000036 loss: 0.3209 (0.3296) grad: 0.1546 (0.1659) time: 0.4875 data: 0.0029 max mem: 25051 +train: [16] [500/800] eta: 0:02:33 lr: 0.000036 loss: 0.3345 (0.3307) grad: 0.1544 (0.1654) time: 0.4812 data: 0.0031 max mem: 25051 +train: [16] [520/800] eta: 0:02:23 lr: 0.000035 loss: 0.3345 (0.3292) grad: 0.1416 (0.1637) time: 0.4808 data: 0.0030 max mem: 25051 +train: [16] [540/800] eta: 0:02:12 lr: 0.000035 loss: 0.3368 (0.3300) grad: 0.1544 (0.1638) time: 0.4792 data: 0.0030 max mem: 25051 +train: [16] [560/800] eta: 0:02:02 lr: 0.000034 loss: 0.3368 (0.3331) grad: 0.1544 (0.1654) time: 0.4765 data: 0.0031 max mem: 25051 +train: [16] [580/800] eta: 0:01:53 lr: 0.000034 loss: 0.3505 (0.3336) grad: 0.1368 (0.1634) time: 0.6616 data: 0.2072 max mem: 25051 +train: [16] [600/800] eta: 0:01:42 lr: 0.000033 loss: 0.3616 (0.3350) grad: 0.1377 (0.1643) time: 0.4619 data: 0.0030 max mem: 25051 +train: [16] [620/800] eta: 0:01:32 lr: 0.000033 loss: 0.3765 (0.3361) grad: 0.1377 (0.1647) time: 0.4750 data: 0.0026 max mem: 25051 +train: [16] [640/800] eta: 0:01:21 lr: 0.000032 loss: 0.3505 (0.3362) grad: 0.1368 (0.1637) time: 0.4865 data: 0.0033 max mem: 25051 +train: [16] [660/800] eta: 0:01:11 lr: 0.000032 loss: 0.3478 (0.3358) grad: 0.1558 (0.1632) time: 0.4781 data: 0.0031 max mem: 25051 +train: [16] [680/800] eta: 0:01:00 lr: 0.000031 loss: 0.3052 (0.3344) grad: 0.1558 (0.1643) time: 0.4691 data: 0.0031 max mem: 25051 +train: [16] [700/800] eta: 0:00:50 lr: 0.000031 loss: 0.3046 (0.3346) grad: 0.1317 (0.1629) time: 0.4670 data: 0.0029 max mem: 25051 +train: [16] [720/800] eta: 0:00:40 lr: 0.000031 loss: 0.3218 (0.3356) grad: 0.1166 (0.1615) time: 0.6676 data: 0.2058 max mem: 25051 +train: [16] [740/800] eta: 0:00:30 lr: 0.000030 loss: 0.3218 (0.3359) grad: 0.1317 (0.1637) time: 0.4844 data: 0.0071 max mem: 25051 +train: [16] [760/800] eta: 0:00:20 lr: 0.000030 loss: 0.3241 (0.3345) grad: 0.1273 (0.1648) time: 0.4859 data: 0.0025 max mem: 25051 +train: [16] [780/800] eta: 0:00:10 lr: 0.000029 loss: 0.3241 (0.3351) grad: 0.1386 (0.1655) time: 0.4879 data: 0.0031 max mem: 25051 +train: [16] [799/800] eta: 0:00:00 lr: 0.000029 loss: 0.3065 (0.3346) grad: 0.2091 (0.1682) time: 0.4759 data: 0.0030 max mem: 25051 +train: [16] Total time: 0:06:47 (0.5091 s / it) +train: [16] Summary: lr: 0.000029 loss: 0.3065 (0.3346) grad: 0.2091 (0.1682) +eval (validation): [16] [ 0/31] eta: 0:02:05 time: 4.0537 data: 3.8016 max mem: 25051 +eval (validation): [16] [20/31] eta: 0:00:06 time: 0.4066 data: 0.0263 max mem: 25051 +eval (validation): [16] [30/31] eta: 0:00:00 time: 0.3698 data: 0.0018 max mem: 25051 +eval (validation): [16] Total time: 0:00:15 (0.5140 s / it) +cv: [16] best hparam: (0.2, 1.0) (014) ('014_lr2.0e-01_wd1.0e+00') loss: 0.633 acc: 0.653 f1: 0.639 bacc: 0.638 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/abide_dx__patch__attn/checkpoint-last.pth +train: [17] [ 0/800] eta: 0:56:21 lr: nan time: 4.2269 data: 3.8391 max mem: 25051 +train: [17] [ 20/800] eta: 0:09:10 lr: 0.000028 loss: 0.3264 (0.3140) grad: 0.2012 (0.2116) time: 0.5299 data: 0.0027 max mem: 25051 +train: [17] [ 40/800] eta: 0:07:32 lr: 0.000028 loss: 0.3264 (0.3467) grad: 0.2094 (0.2343) time: 0.4795 data: 0.0027 max mem: 25051 +train: [17] [ 60/800] eta: 0:06:54 lr: 0.000027 loss: 0.3264 (0.3378) grad: 0.1915 (0.2003) time: 0.4857 data: 0.0029 max mem: 25051 +train: [17] [ 80/800] eta: 0:06:28 lr: 0.000027 loss: 0.3192 (0.3318) grad: 0.1915 (0.2071) time: 0.4796 data: 0.0029 max mem: 25051 +train: [17] [100/800] eta: 0:06:11 lr: 0.000026 loss: 0.3192 (0.3363) grad: 0.1780 (0.1993) time: 0.4948 data: 0.0032 max mem: 25051 +train: [17] [120/800] eta: 0:05:55 lr: 0.000026 loss: 0.3266 (0.3468) grad: 0.1780 (0.2044) time: 0.4852 data: 0.0031 max mem: 25051 +train: [17] [140/800] eta: 0:05:40 lr: 0.000026 loss: 0.3266 (0.3453) grad: 0.1420 (0.1902) time: 0.4726 data: 0.0028 max mem: 25051 +train: [17] [160/800] eta: 0:05:41 lr: 0.000025 loss: 0.3521 (0.3456) grad: 0.1200 (0.1876) time: 0.6597 data: 0.2021 max mem: 25051 +train: [17] [180/800] eta: 0:05:26 lr: 0.000025 loss: 0.3313 (0.3396) grad: 0.1420 (0.1890) time: 0.4706 data: 0.0024 max mem: 25051 +train: [17] [200/800] eta: 0:05:13 lr: 0.000024 loss: 0.3301 (0.3441) grad: 0.1200 (0.1851) time: 0.4868 data: 0.0031 max mem: 25051 +train: [17] [220/800] eta: 0:05:00 lr: 0.000024 loss: 0.3503 (0.3470) grad: 0.1448 (0.1913) time: 0.4787 data: 0.0029 max mem: 25051 +train: [17] [240/800] eta: 0:04:49 lr: 0.000023 loss: 0.3301 (0.3467) grad: 0.1669 (0.1902) time: 0.4846 data: 0.0030 max mem: 25051 +train: [17] [260/800] eta: 0:04:37 lr: 0.000023 loss: 0.3443 (0.3428) grad: 0.1626 (0.1894) time: 0.4815 data: 0.0030 max mem: 25051 +train: [17] [280/800] eta: 0:04:25 lr: 0.000023 loss: 0.3117 (0.3386) grad: 0.1626 (0.1872) time: 0.4731 data: 0.0029 max mem: 25051 +train: [17] [300/800] eta: 0:04:22 lr: 0.000022 loss: 0.3036 (0.3383) grad: 0.1567 (0.1834) time: 0.7150 data: 0.2129 max mem: 25051 +train: [17] [320/800] eta: 0:04:10 lr: 0.000022 loss: 0.3060 (0.3412) grad: 0.1222 (0.1796) time: 0.4849 data: 0.0026 max mem: 25051 +train: [17] [340/800] eta: 0:03:58 lr: 0.000021 loss: 0.3339 (0.3414) grad: 0.1076 (0.1768) time: 0.4776 data: 0.0031 max mem: 25051 +train: [17] [360/800] eta: 0:03:47 lr: 0.000021 loss: 0.3343 (0.3413) grad: 0.1172 (0.1772) time: 0.4898 data: 0.0030 max mem: 25051 +train: [17] [380/800] eta: 0:03:36 lr: 0.000021 loss: 0.3341 (0.3423) grad: 0.1172 (0.1774) time: 0.4771 data: 0.0030 max mem: 25051 +train: [17] [400/800] eta: 0:03:25 lr: 0.000020 loss: 0.3227 (0.3393) grad: 0.1238 (0.1789) time: 0.4723 data: 0.0030 max mem: 25051 +train: [17] [420/800] eta: 0:03:14 lr: 0.000020 loss: 0.2974 (0.3380) grad: 0.1489 (0.1782) time: 0.4748 data: 0.0030 max mem: 25051 +train: [17] [440/800] eta: 0:03:06 lr: 0.000019 loss: 0.2974 (0.3385) grad: 0.1515 (0.1773) time: 0.6685 data: 0.2063 max mem: 25051 +train: [17] [460/800] eta: 0:02:56 lr: 0.000019 loss: 0.3158 (0.3384) grad: 0.1414 (0.1752) time: 0.4995 data: 0.0023 max mem: 25051 +train: [17] [480/800] eta: 0:02:45 lr: 0.000019 loss: 0.3292 (0.3381) grad: 0.1390 (0.1749) time: 0.4806 data: 0.0030 max mem: 25051 +train: [17] [500/800] eta: 0:02:34 lr: 0.000018 loss: 0.3418 (0.3372) grad: 0.1320 (0.1730) time: 0.4789 data: 0.0032 max mem: 25051 +train: [17] [520/800] eta: 0:02:23 lr: 0.000018 loss: 0.3293 (0.3369) grad: 0.1390 (0.1747) time: 0.4824 data: 0.0028 max mem: 25051 +train: [17] [540/800] eta: 0:02:13 lr: 0.000017 loss: 0.3209 (0.3366) grad: 0.1464 (0.1726) time: 0.4958 data: 0.0031 max mem: 25051 +train: [17] [560/800] eta: 0:02:03 lr: 0.000017 loss: 0.3293 (0.3365) grad: 0.1464 (0.1759) time: 0.5097 data: 0.0031 max mem: 25051 +train: [17] [580/800] eta: 0:01:54 lr: 0.000017 loss: 0.3335 (0.3373) grad: 0.1464 (0.1760) time: 0.6955 data: 0.2116 max mem: 25051 +train: [17] [600/800] eta: 0:01:43 lr: 0.000016 loss: 0.3219 (0.3366) grad: 0.1464 (0.1787) time: 0.4810 data: 0.0024 max mem: 25051 +train: [17] [620/800] eta: 0:01:33 lr: 0.000016 loss: 0.3280 (0.3371) grad: 0.1445 (0.1786) time: 0.4869 data: 0.0026 max mem: 25051 +train: [17] [640/800] eta: 0:01:22 lr: 0.000016 loss: 0.3219 (0.3366) grad: 0.1381 (0.1789) time: 0.4764 data: 0.0030 max mem: 25051 +train: [17] [660/800] eta: 0:01:12 lr: 0.000015 loss: 0.3178 (0.3356) grad: 0.2236 (0.1811) time: 0.4771 data: 0.0031 max mem: 25051 +train: [17] [680/800] eta: 0:01:01 lr: 0.000015 loss: 0.3280 (0.3362) grad: 0.1445 (0.1808) time: 0.4802 data: 0.0031 max mem: 25051 +train: [17] [700/800] eta: 0:00:51 lr: 0.000015 loss: 0.3238 (0.3357) grad: 0.1459 (0.1800) time: 0.4758 data: 0.0029 max mem: 25051 +train: [17] [720/800] eta: 0:00:41 lr: 0.000014 loss: 0.3043 (0.3349) grad: 0.1477 (0.1790) time: 0.6688 data: 0.2057 max mem: 25051 +train: [17] [740/800] eta: 0:00:30 lr: 0.000014 loss: 0.3377 (0.3352) grad: 0.1254 (0.1776) time: 0.4760 data: 0.0030 max mem: 25051 +train: [17] [760/800] eta: 0:00:20 lr: 0.000014 loss: 0.3175 (0.3347) grad: 0.1243 (0.1775) time: 0.4699 data: 0.0023 max mem: 25051 +train: [17] [780/800] eta: 0:00:10 lr: 0.000013 loss: 0.3175 (0.3341) grad: 0.1012 (0.1758) time: 0.4638 data: 0.0028 max mem: 25051 +train: [17] [799/800] eta: 0:00:00 lr: 0.000013 loss: 0.3377 (0.3337) grad: 0.1121 (0.1757) time: 0.4695 data: 0.0029 max mem: 25051 +train: [17] Total time: 0:06:49 (0.5123 s / it) +train: [17] Summary: lr: 0.000013 loss: 0.3377 (0.3337) grad: 0.1121 (0.1757) +eval (validation): [17] [ 0/31] eta: 0:02:12 time: 4.2861 data: 3.9686 max mem: 25051 +eval (validation): [17] [20/31] eta: 0:00:06 time: 0.4055 data: 0.0021 max mem: 25051 +eval (validation): [17] [30/31] eta: 0:00:00 time: 0.3735 data: 0.0020 max mem: 25051 +eval (validation): [17] Total time: 0:00:16 (0.5241 s / it) +cv: [17] best hparam: (0.38, 1.0) (018) ('018_lr3.8e-01_wd1.0e+00') loss: 0.675 acc: 0.653 f1: 0.645 bacc: 0.644 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/abide_dx__patch__attn/checkpoint-last.pth +train: [18] [ 0/800] eta: 0:55:22 lr: nan time: 4.1526 data: 3.7427 max mem: 25051 +train: [18] [ 20/800] eta: 0:08:51 lr: 0.000013 loss: 0.3833 (0.3724) grad: 0.0936 (0.1078) time: 0.5078 data: 0.0040 max mem: 25051 +train: [18] [ 40/800] eta: 0:07:20 lr: 0.000012 loss: 0.3237 (0.3351) grad: 0.0944 (0.1242) time: 0.4724 data: 0.0024 max mem: 25051 +train: [18] [ 60/800] eta: 0:06:46 lr: 0.000012 loss: 0.3362 (0.3381) grad: 0.1213 (0.1496) time: 0.4871 data: 0.0032 max mem: 25051 +train: [18] [ 80/800] eta: 0:06:20 lr: 0.000012 loss: 0.3362 (0.3436) grad: 0.1213 (0.1606) time: 0.4660 data: 0.0029 max mem: 25051 +train: [18] [100/800] eta: 0:06:04 lr: 0.000011 loss: 0.3496 (0.3466) grad: 0.1657 (0.1657) time: 0.4900 data: 0.0030 max mem: 25051 +train: [18] [120/800] eta: 0:05:50 lr: 0.000011 loss: 0.3586 (0.3465) grad: 0.1799 (0.1792) time: 0.4880 data: 0.0031 max mem: 25051 +train: [18] [140/800] eta: 0:05:36 lr: 0.000011 loss: 0.3636 (0.3442) grad: 0.1799 (0.1759) time: 0.4723 data: 0.0029 max mem: 25051 +train: [18] [160/800] eta: 0:05:42 lr: 0.000011 loss: 0.3636 (0.3470) grad: 0.1871 (0.1820) time: 0.7196 data: 0.2058 max mem: 25051 +train: [18] [180/800] eta: 0:05:29 lr: 0.000010 loss: 0.3461 (0.3452) grad: 0.2124 (0.1859) time: 0.4945 data: 0.0034 max mem: 25051 +train: [18] [200/800] eta: 0:05:15 lr: 0.000010 loss: 0.3532 (0.3469) grad: 0.1678 (0.1818) time: 0.4772 data: 0.0031 max mem: 25051 +train: [18] [220/800] eta: 0:05:01 lr: 0.000010 loss: 0.3540 (0.3486) grad: 0.1176 (0.1766) time: 0.4638 data: 0.0030 max mem: 25051 +train: [18] [240/800] eta: 0:04:49 lr: 0.000009 loss: 0.3540 (0.3497) grad: 0.1252 (0.1825) time: 0.4896 data: 0.0031 max mem: 25051 +train: [18] [260/800] eta: 0:04:38 lr: 0.000009 loss: 0.3532 (0.3488) grad: 0.1252 (0.1827) time: 0.4843 data: 0.0030 max mem: 25051 +train: [18] [280/800] eta: 0:04:26 lr: 0.000009 loss: 0.3492 (0.3477) grad: 0.1282 (0.1795) time: 0.4743 data: 0.0029 max mem: 25051 +train: [18] [300/800] eta: 0:04:22 lr: 0.000009 loss: 0.3304 (0.3454) grad: 0.1252 (0.1744) time: 0.6931 data: 0.2074 max mem: 25051 +train: [18] [320/800] eta: 0:04:10 lr: 0.000008 loss: 0.3184 (0.3437) grad: 0.1171 (0.1711) time: 0.4760 data: 0.0024 max mem: 25051 +train: [18] [340/800] eta: 0:03:58 lr: 0.000008 loss: 0.3151 (0.3428) grad: 0.0992 (0.1717) time: 0.4753 data: 0.0029 max mem: 25051 +train: [18] [360/800] eta: 0:03:46 lr: 0.000008 loss: 0.3135 (0.3409) grad: 0.1171 (0.1731) time: 0.4597 data: 0.0030 max mem: 25051 +train: [18] [380/800] eta: 0:03:35 lr: 0.000008 loss: 0.3135 (0.3393) grad: 0.1427 (0.1734) time: 0.4828 data: 0.0030 max mem: 25051 +train: [18] [400/800] eta: 0:03:24 lr: 0.000007 loss: 0.3160 (0.3393) grad: 0.1427 (0.1746) time: 0.4705 data: 0.0031 max mem: 25051 +train: [18] [420/800] eta: 0:03:13 lr: 0.000007 loss: 0.3139 (0.3391) grad: 0.1427 (0.1761) time: 0.4689 data: 0.0031 max mem: 25051 +train: [18] [440/800] eta: 0:03:05 lr: 0.000007 loss: 0.3467 (0.3400) grad: 0.1567 (0.1796) time: 0.6579 data: 0.2080 max mem: 25051 +train: [18] [460/800] eta: 0:02:54 lr: 0.000007 loss: 0.3502 (0.3396) grad: 0.1679 (0.1795) time: 0.4734 data: 0.0023 max mem: 25051 +train: [18] [480/800] eta: 0:02:43 lr: 0.000006 loss: 0.3553 (0.3399) grad: 0.1567 (0.1787) time: 0.4677 data: 0.0029 max mem: 25051 +train: [18] [500/800] eta: 0:02:33 lr: 0.000006 loss: 0.3553 (0.3404) grad: 0.1708 (0.1806) time: 0.4656 data: 0.0029 max mem: 25051 +train: [18] [520/800] eta: 0:02:22 lr: 0.000006 loss: 0.3206 (0.3399) grad: 0.1708 (0.1822) time: 0.4804 data: 0.0030 max mem: 25051 +train: [18] [540/800] eta: 0:02:12 lr: 0.000006 loss: 0.3224 (0.3399) grad: 0.1464 (0.1808) time: 0.4765 data: 0.0030 max mem: 25051 +train: [18] [560/800] eta: 0:02:01 lr: 0.000006 loss: 0.3200 (0.3395) grad: 0.1507 (0.1792) time: 0.4916 data: 0.0028 max mem: 25051 +train: [18] [580/800] eta: 0:01:52 lr: 0.000005 loss: 0.3224 (0.3392) grad: 0.1300 (0.1783) time: 0.6824 data: 0.2189 max mem: 25051 +train: [18] [600/800] eta: 0:01:42 lr: 0.000005 loss: 0.3229 (0.3393) grad: 0.1300 (0.1791) time: 0.4939 data: 0.0029 max mem: 25051 +train: [18] [620/800] eta: 0:01:32 lr: 0.000005 loss: 0.3276 (0.3391) grad: 0.1286 (0.1773) time: 0.4776 data: 0.0019 max mem: 25051 +train: [18] [640/800] eta: 0:01:21 lr: 0.000005 loss: 0.3299 (0.3397) grad: 0.1268 (0.1768) time: 0.4858 data: 0.0030 max mem: 25051 +train: [18] [660/800] eta: 0:01:11 lr: 0.000005 loss: 0.3276 (0.3400) grad: 0.1268 (0.1769) time: 0.4813 data: 0.0029 max mem: 25051 +train: [18] [680/800] eta: 0:01:01 lr: 0.000004 loss: 0.3276 (0.3410) grad: 0.1185 (0.1747) time: 0.4834 data: 0.0030 max mem: 25051 +train: [18] [700/800] eta: 0:00:50 lr: 0.000004 loss: 0.3456 (0.3408) grad: 0.1180 (0.1733) time: 0.4995 data: 0.0032 max mem: 25051 +train: [18] [720/800] eta: 0:00:41 lr: 0.000004 loss: 0.3456 (0.3413) grad: 0.1180 (0.1725) time: 0.6924 data: 0.2109 max mem: 25051 +train: [18] [740/800] eta: 0:00:30 lr: 0.000004 loss: 0.3456 (0.3410) grad: 0.1188 (0.1727) time: 0.5239 data: 0.0029 max mem: 25051 +train: [18] [760/800] eta: 0:00:20 lr: 0.000004 loss: 0.3204 (0.3401) grad: 0.1459 (0.1731) time: 0.5010 data: 0.0023 max mem: 25051 +train: [18] [780/800] eta: 0:00:10 lr: 0.000003 loss: 0.3289 (0.3403) grad: 0.1608 (0.1724) time: 0.4971 data: 0.0032 max mem: 25051 +train: [18] [799/800] eta: 0:00:00 lr: 0.000003 loss: 0.3008 (0.3402) grad: 0.1459 (0.1711) time: 0.4803 data: 0.0031 max mem: 25051 +train: [18] Total time: 0:06:50 (0.5129 s / it) +train: [18] Summary: lr: 0.000003 loss: 0.3008 (0.3402) grad: 0.1459 (0.1711) +eval (validation): [18] [ 0/31] eta: 0:02:05 time: 4.0542 data: 3.8031 max mem: 25051 +eval (validation): [18] [20/31] eta: 0:00:06 time: 0.4498 data: 0.0848 max mem: 25051 +eval (validation): [18] [30/31] eta: 0:00:00 time: 0.3619 data: 0.0016 max mem: 25051 +eval (validation): [18] Total time: 0:00:16 (0.5475 s / it) +cv: [18] best hparam: (0.27, 1.0) (016) ('016_lr2.7e-01_wd1.0e+00') loss: 0.635 acc: 0.653 f1: 0.639 bacc: 0.638 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/abide_dx__patch__attn/checkpoint-last.pth +train: [19] [ 0/800] eta: 0:57:00 lr: nan time: 4.2754 data: 3.8499 max mem: 25051 +train: [19] [ 20/800] eta: 0:09:23 lr: 0.000003 loss: 0.3356 (0.3239) grad: 0.1223 (0.1437) time: 0.5445 data: 0.0028 max mem: 25051 +train: [19] [ 40/800] eta: 0:07:43 lr: 0.000003 loss: 0.3424 (0.3390) grad: 0.1223 (0.1704) time: 0.4907 data: 0.0029 max mem: 25051 +train: [19] [ 60/800] eta: 0:07:06 lr: 0.000003 loss: 0.3424 (0.3457) grad: 0.1223 (0.1513) time: 0.5106 data: 0.0033 max mem: 25051 +train: [19] [ 80/800] eta: 0:06:36 lr: 0.000003 loss: 0.3257 (0.3355) grad: 0.1223 (0.1515) time: 0.4724 data: 0.0031 max mem: 25051 +train: [19] [100/800] eta: 0:06:15 lr: 0.000003 loss: 0.3337 (0.3395) grad: 0.1498 (0.1596) time: 0.4779 data: 0.0032 max mem: 25051 +train: [19] [120/800] eta: 0:05:57 lr: 0.000002 loss: 0.3257 (0.3356) grad: 0.1516 (0.1632) time: 0.4689 data: 0.0030 max mem: 25051 +train: [19] [140/800] eta: 0:05:42 lr: 0.000002 loss: 0.3257 (0.3366) grad: 0.1769 (0.1709) time: 0.4772 data: 0.0027 max mem: 25051 +train: [19] [160/800] eta: 0:05:43 lr: 0.000002 loss: 0.3273 (0.3337) grad: 0.1544 (0.1675) time: 0.6644 data: 0.2029 max mem: 25051 +train: [19] [180/800] eta: 0:05:28 lr: 0.000002 loss: 0.3119 (0.3360) grad: 0.1514 (0.1704) time: 0.4724 data: 0.0026 max mem: 25051 +train: [19] [200/800] eta: 0:05:14 lr: 0.000002 loss: 0.3154 (0.3357) grad: 0.1447 (0.1653) time: 0.4681 data: 0.0023 max mem: 25051 +train: [19] [220/800] eta: 0:05:00 lr: 0.000002 loss: 0.3243 (0.3408) grad: 0.1206 (0.1632) time: 0.4721 data: 0.0031 max mem: 25051 +train: [19] [240/800] eta: 0:04:48 lr: 0.000002 loss: 0.3498 (0.3435) grad: 0.1324 (0.1702) time: 0.4743 data: 0.0032 max mem: 25051 +train: [19] [260/800] eta: 0:04:36 lr: 0.000001 loss: 0.3498 (0.3401) grad: 0.1182 (0.1698) time: 0.4628 data: 0.0029 max mem: 25051 +train: [19] [280/800] eta: 0:04:23 lr: 0.000001 loss: 0.3243 (0.3372) grad: 0.1496 (0.1705) time: 0.4595 data: 0.0029 max mem: 25051 +train: [19] [300/800] eta: 0:04:19 lr: 0.000001 loss: 0.3190 (0.3371) grad: 0.1546 (0.1685) time: 0.6780 data: 0.2071 max mem: 25051 +train: [19] [320/800] eta: 0:04:08 lr: 0.000001 loss: 0.3190 (0.3389) grad: 0.1546 (0.1716) time: 0.4874 data: 0.0024 max mem: 25051 +train: [19] [340/800] eta: 0:03:56 lr: 0.000001 loss: 0.3190 (0.3378) grad: 0.1550 (0.1724) time: 0.4687 data: 0.0025 max mem: 25051 +train: [19] [360/800] eta: 0:03:45 lr: 0.000001 loss: 0.3296 (0.3391) grad: 0.1546 (0.1720) time: 0.4717 data: 0.0029 max mem: 25051 +train: [19] [380/800] eta: 0:03:34 lr: 0.000001 loss: 0.3321 (0.3387) grad: 0.1591 (0.1718) time: 0.4791 data: 0.0032 max mem: 25051 +train: [19] [400/800] eta: 0:03:23 lr: 0.000001 loss: 0.3166 (0.3379) grad: 0.1487 (0.1697) time: 0.4720 data: 0.0030 max mem: 25051 +train: [19] [420/800] eta: 0:03:12 lr: 0.000001 loss: 0.3166 (0.3355) grad: 0.1548 (0.1710) time: 0.4704 data: 0.0029 max mem: 25051 +train: [19] [440/800] eta: 0:03:05 lr: 0.000001 loss: 0.3269 (0.3371) grad: 0.1548 (0.1693) time: 0.7262 data: 0.2162 max mem: 25051 +train: [19] [460/800] eta: 0:02:55 lr: 0.000001 loss: 0.3236 (0.3367) grad: 0.1451 (0.1694) time: 0.4893 data: 0.0020 max mem: 25051 +train: [19] [480/800] eta: 0:02:44 lr: 0.000001 loss: 0.3270 (0.3375) grad: 0.1548 (0.1700) time: 0.4918 data: 0.0030 max mem: 25051 +train: [19] [500/800] eta: 0:02:33 lr: 0.000000 loss: 0.3294 (0.3369) grad: 0.1451 (0.1734) time: 0.4869 data: 0.0031 max mem: 25051 +train: [19] [520/800] eta: 0:02:23 lr: 0.000000 loss: 0.3256 (0.3361) grad: 0.1377 (0.1726) time: 0.4931 data: 0.0030 max mem: 25051 +train: [19] [540/800] eta: 0:02:12 lr: 0.000000 loss: 0.3154 (0.3354) grad: 0.1302 (0.1701) time: 0.4872 data: 0.0030 max mem: 25051 +train: [19] [560/800] eta: 0:02:02 lr: 0.000000 loss: 0.3154 (0.3351) grad: 0.1265 (0.1697) time: 0.4931 data: 0.0030 max mem: 25051 +train: [19] [580/800] eta: 0:01:53 lr: 0.000000 loss: 0.3084 (0.3347) grad: 0.1163 (0.1683) time: 0.6894 data: 0.2191 max mem: 25051 +train: [19] [600/800] eta: 0:01:43 lr: 0.000000 loss: 0.3128 (0.3355) grad: 0.1110 (0.1689) time: 0.5043 data: 0.0272 max mem: 25051 +train: [19] [620/800] eta: 0:01:32 lr: 0.000000 loss: 0.3128 (0.3342) grad: 0.1163 (0.1692) time: 0.4816 data: 0.0016 max mem: 25051 +train: [19] [640/800] eta: 0:01:22 lr: 0.000000 loss: 0.3128 (0.3335) grad: 0.1337 (0.1681) time: 0.4896 data: 0.0027 max mem: 25051 +train: [19] [660/800] eta: 0:01:11 lr: 0.000000 loss: 0.3128 (0.3325) grad: 0.1528 (0.1704) time: 0.4746 data: 0.0032 max mem: 25051 +train: [19] [680/800] eta: 0:01:01 lr: 0.000000 loss: 0.3046 (0.3332) grad: 0.1528 (0.1705) time: 0.4812 data: 0.0029 max mem: 25051 +train: [19] [700/800] eta: 0:00:51 lr: 0.000000 loss: 0.3317 (0.3346) grad: 0.1505 (0.1690) time: 0.4883 data: 0.0029 max mem: 25051 +train: [19] [720/800] eta: 0:00:41 lr: 0.000000 loss: 0.3317 (0.3351) grad: 0.1520 (0.1708) time: 0.7004 data: 0.2154 max mem: 25051 +train: [19] [740/800] eta: 0:00:31 lr: 0.000000 loss: 0.3587 (0.3350) grad: 0.1505 (0.1711) time: 0.5184 data: 0.0119 max mem: 25051 +train: [19] [760/800] eta: 0:00:20 lr: 0.000000 loss: 0.3587 (0.3359) grad: 0.1606 (0.1724) time: 0.4782 data: 0.0023 max mem: 25051 +train: [19] [780/800] eta: 0:00:10 lr: 0.000000 loss: 0.3419 (0.3355) grad: 0.1789 (0.1720) time: 0.4770 data: 0.0031 max mem: 25051 +train: [19] [799/800] eta: 0:00:00 lr: 0.000000 loss: 0.3403 (0.3348) grad: 0.1789 (0.1727) time: 0.4781 data: 0.0031 max mem: 25051 +train: [19] Total time: 0:06:51 (0.5143 s / it) +train: [19] Summary: lr: 0.000000 loss: 0.3403 (0.3348) grad: 0.1789 (0.1727) +eval (validation): [19] [ 0/31] eta: 0:02:04 time: 4.0093 data: 3.7134 max mem: 25051 +eval (validation): [19] [20/31] eta: 0:00:06 time: 0.3908 data: 0.0023 max mem: 25051 +eval (validation): [19] [30/31] eta: 0:00:00 time: 0.3674 data: 0.0020 max mem: 25051 +eval (validation): [19] Total time: 0:00:15 (0.5087 s / it) +cv: [19] best hparam: (0.27, 1.0) (016) ('016_lr2.7e-01_wd1.0e+00') loss: 0.635 acc: 0.661 f1: 0.646 bacc: 0.645 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/abide_dx__patch__attn/checkpoint-last.pth +evaluating last checkpoint: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/abide_dx__patch__attn/checkpoint-last.pth +eval model info: +{"score": 0.644973544973545, "hparam": [0.27, 1.0], "hparam_id": 16, "epoch": 19, "is_best": false, "best_score": 0.6698412698412699} +eval (train): [20] [ 0/145] eta: 0:10:44 time: 4.4466 data: 4.1383 max mem: 25051 +eval (train): [20] [ 20/145] eta: 0:01:22 time: 0.4674 data: 0.0273 max mem: 25051 +eval (train): [20] [ 40/145] eta: 0:00:57 time: 0.4341 data: 0.0374 max mem: 25051 +eval (train): [20] [ 60/145] eta: 0:00:42 time: 0.4053 data: 0.0068 max mem: 25051 +eval (train): [20] [ 80/145] eta: 0:00:31 time: 0.4348 data: 0.0472 max mem: 25051 +eval (train): [20] [100/145] eta: 0:00:21 time: 0.4745 data: 0.0151 max mem: 25051 +eval (train): [20] [120/145] eta: 0:00:12 time: 0.4682 data: 0.0033 max mem: 25051 +eval (train): [20] [140/145] eta: 0:00:02 time: 0.3867 data: 0.0126 max mem: 25051 +eval (train): [20] [144/145] eta: 0:00:00 time: 0.3788 data: 0.0126 max mem: 25051 +eval (train): [20] Total time: 0:01:07 (0.4652 s / it) +eval (validation): [20] [ 0/31] eta: 0:02:13 time: 4.3195 data: 4.0245 max mem: 25051 +eval (validation): [20] [20/31] eta: 0:00:06 time: 0.4376 data: 0.0021 max mem: 25051 +eval (validation): [20] [30/31] eta: 0:00:00 time: 0.3917 data: 0.0189 max mem: 25051 +eval (validation): [20] Total time: 0:00:17 (0.5522 s / it) +eval (test): [20] [ 0/31] eta: 0:02:08 time: 4.1570 data: 3.9056 max mem: 25051 +eval (test): [20] [20/31] eta: 0:00:07 time: 0.5247 data: 0.0757 max mem: 25051 +eval (test): [20] [30/31] eta: 0:00:00 time: 0.4345 data: 0.0025 max mem: 25051 +eval (test): [20] Total time: 0:00:18 (0.5997 s / it) +evaluating best checkpoint: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/abide_dx__patch__attn/checkpoint-best.pth +eval model info: +{"score": 0.6698412698412699, "hparam": [50, 1.0], "hparam_id": 48, "epoch": 0, "is_best": true, "best_score": 0.6698412698412699} +eval (train): [20] [ 0/145] eta: 0:10:03 time: 4.1634 data: 3.8729 max mem: 25051 +eval (train): [20] [ 20/145] eta: 0:01:24 time: 0.5056 data: 0.1344 max mem: 25051 +eval (train): [20] [ 40/145] eta: 0:00:59 time: 0.4469 data: 0.0447 max mem: 25051 +eval (train): [20] [ 60/145] eta: 0:00:43 time: 0.3982 data: 0.0174 max mem: 25051 +eval (train): [20] [ 80/145] eta: 0:00:32 time: 0.4412 data: 0.0433 max mem: 25051 +eval (train): [20] [100/145] eta: 0:00:22 time: 0.5064 data: 0.0733 max mem: 25051 +eval (train): [20] [120/145] eta: 0:00:11 time: 0.3867 data: 0.0179 max mem: 25051 +eval (train): [20] [140/145] eta: 0:00:02 time: 0.4137 data: 0.0384 max mem: 25051 +eval (train): [20] [144/145] eta: 0:00:00 time: 0.4053 data: 0.0378 max mem: 25051 +eval (train): [20] Total time: 0:01:07 (0.4672 s / it) +eval (validation): [20] [ 0/31] eta: 0:02:11 time: 4.2557 data: 3.9999 max mem: 25051 +eval (validation): [20] [20/31] eta: 0:00:07 time: 0.4638 data: 0.0720 max mem: 25051 +eval (validation): [20] [30/31] eta: 0:00:00 time: 0.3901 data: 0.0178 max mem: 25051 +eval (validation): [20] Total time: 0:00:17 (0.5672 s / it) +eval (test): [20] [ 0/31] eta: 0:02:13 time: 4.2919 data: 4.0217 max mem: 25051 +eval (test): [20] [20/31] eta: 0:00:07 time: 0.4662 data: 0.0637 max mem: 25051 +eval (test): [20] [30/31] eta: 0:00:00 time: 0.4174 data: 0.0317 max mem: 25051 +eval (test): [20] Total time: 0:00:17 (0.5725 s / it) +eval results: + +| model | repr | clf | dataset | ckpt | epoch | lr | wd | hparam_id | hparam | split | loss | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:------|:----------|:-------|--------:|------:|-----:|------------:|:----------|:-----------|--------:|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | attn | abide_dx | best | 0 | 0.015 | 0.05 | 48 | [50, 1.0] | train | 0.62612 | 0.65052 | 0.020118 | 0.64931 | 0.02015 | 0.65117 | 0.020236 | +| flat_mae | patch | attn | abide_dx | best | 0 | 0.015 | 0.05 | 48 | [50, 1.0] | validation | 0.64613 | 0.67742 | 0.042827 | 0.67048 | 0.044363 | 0.66984 | 0.044203 | +| flat_mae | patch | attn | abide_dx | best | 0 | 0.015 | 0.05 | 48 | [50, 1.0] | test | 0.67155 | 0.55645 | 0.044042 | 0.55503 | 0.044326 | 0.55551 | 0.044348 | + + +done! total time: 2:29:12 diff --git a/input_space_v3/flat_lr1e-3_1/eval_v2/abide_dx__patch__attn/train_log.json b/input_space_v3/flat_lr1e-3_1/eval_v2/abide_dx__patch__attn/train_log.json new file mode 100644 index 0000000000000000000000000000000000000000..9eaec255da0cb45b719be38398b5074ee982ba39 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_1/eval_v2/abide_dx__patch__attn/train_log.json @@ -0,0 +1,20 @@ +{"epoch": 0, "train/lr": 2.987987987987988e-05, "train/loss": 0.6932909455895424, "train/grad": 0.2876513925939798, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.6944384765625, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.6940771484375, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.69357421875, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.6932568359375, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.6929296875, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.692587890625, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.69244140625, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.69232421875, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.6922265625, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.69216796875, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.69220703125, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.6922265625, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.6922705078125, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.69224853515625, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.6922265625, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.69212158203125, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.6920654296875, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.6920361328125, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.6919677734375, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.69186279296875, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.69172119140625, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.69160400390625, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.6914501953125, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.69121826171875, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.690712890625, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.69020263671875, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.69012939453125, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.6902978515625, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.69025634765625, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.68916259765625, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.68718505859375, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.685152587890625, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.68272705078125, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.681514892578125, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.6815087890625, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.682947998046875, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.685526123046875, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.688504638671875, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.692340087890625, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.6955389404296874, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.6954705810546875, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.69456298828125, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.6966162109375, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.70068115234375, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.7041314697265625, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.7059686279296875, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.7124285888671875, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.722208251953125, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.7182302856445313, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.040025526490062475, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.03975207919254899, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.03936204918660224, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.03902646339032799, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.03874735104385763, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.03841427447274327, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.03809997845441103, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.03781193671748042, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.037511938754469155, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.03725303512997925, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.037053877166472377, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.0368153220647946, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.036635684710927305, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.03643583038356155, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.0362793557299301, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.03618646426126361, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.03609072906896472, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.03602609682828188, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.0359996770741418, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.035988387917168435, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.03601898733526468, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.03606839078478515, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.03615296386182308, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.036284356592223045, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.036478376584127545, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0367593204556033, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.037066564029082656, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.03737679264042527, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.03776133073028177, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.038161339983344075, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.038606638852506876, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.03919362921034917, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.04007886314066127, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.04053221130277961, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.04052698348183185, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.040520322842057796, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.04096459087682888, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.04157431820873171, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.04203210562467575, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.04163825436960906, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.040627013710327446, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.03992435547988862, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0396011442062445, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.03961952424841002, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.03965010604588315, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.041016170540824536, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.04210402934346348, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.04386973824817687, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.042436437117867175, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.6871254444122314, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.6862044930458069, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.6849820613861084, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.6841206550598145, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.6835924386978149, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.6831501722335815, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.6828688979148865, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.6827108263969421, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.6826629042625427, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.6826376914978027, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.6826189160346985, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.6826919913291931, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.6827446818351746, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.6828652024269104, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.6829698085784912, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.6831942796707153, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.6832910776138306, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.683297872543335, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.6831604242324829, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.6827926635742188, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.6821252703666687, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.6812286376953125, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.6801103353500366, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.6787412762641907, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.6774415373802185, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.6755595207214355, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.6737468838691711, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.6721481680870056, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.6718246340751648, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.677401602268219, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.6812188029289246, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.6823139190673828, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.6920865774154663, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.708452582359314, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.7100123167037964, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.6955140233039856, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.6866753101348877, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.6796492338180542, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.6687036156654358, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.6652544736862183, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.6721101999282837, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.6845208406448364, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.7082094550132751, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.7042545080184937, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.722394585609436, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.6911801099777222, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.7695620059967041, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.6844218969345093, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.6461275219917297, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.5564516129032258, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.5887096774193549, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.5887096774193549, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.5645161290322581, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.5645161290322581, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.5645161290322581, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.5645161290322581, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.5645161290322581, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.5645161290322581, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.5645161290322581, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.5645161290322581, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.5645161290322581, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.5645161290322581, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.5645161290322581, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.5645161290322581, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.5645161290322581, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.5564516129032258, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.5564516129032258, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.5725806451612904, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.5725806451612904, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.5806451612903226, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.5806451612903226, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.5725806451612904, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.5645161290322581, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.5645161290322581, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.5564516129032258, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.5725806451612904, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.5806451612903226, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.5887096774193549, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.5806451612903226, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.5887096774193549, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.5887096774193549, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.5887096774193549, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.5725806451612904, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.5725806451612904, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.5887096774193549, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.5887096774193549, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.6129032258064516, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.6048387096774194, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.5806451612903226, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.5403225806451613, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.5483870967741935, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.5241935483870968, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.5, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.4838709677419355, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.532258064516129, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.5, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.532258064516129, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.6774193548387096, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.46614481409001957, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.4574002574002574, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.41912372554422705, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.36082474226804123, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.36082474226804123, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.36082474226804123, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.36082474226804123, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.36082474226804123, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.36082474226804123, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.36082474226804123, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.36082474226804123, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.36082474226804123, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.36082474226804123, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.36082474226804123, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.36082474226804123, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.36082474226804123, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.35751295336787564, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.35751295336787564, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.3963442638008634, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.3963442638008634, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.44086021505376344, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.44086021505376344, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.4474989491382934, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.4626003210272873, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.4626003210272873, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.46614481409001957, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.4855577299412916, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.48250401284109146, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.4785190071740744, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.44086021505376344, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.4456035767511177, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.4456035767511177, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.4456035767511177, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.4106358174154784, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.4106358174154784, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.46834804539722574, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.46834804539722574, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.5137254901960784, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.5317148362235067, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.5694444444444444, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.5395739691225327, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.5473272490221643, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.47768972656528874, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.44192799070847855, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.4015082956259427, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.5197649572649572, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.4202111613876319, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.5107482993197279, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.6704756842944459, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.5119047619047619, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.5341269841269841, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.5277777777777778, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.5, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.5, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.5, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.5, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.5, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.5, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.5, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.5, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.5, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.5, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.5, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.5, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.5, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.4928571428571429, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.4928571428571429, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.5113756613756614, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.5113756613756614, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.5248677248677249, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.5248677248677249, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.5198412698412699, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.5169312169312169, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.5169312169312169, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.5119047619047619, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.5283068783068783, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.5333333333333333, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.5383597883597884, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.5248677248677249, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.532010582010582, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.532010582010582, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.532010582010582, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.5134920634920634, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.5134920634920634, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.5362433862433862, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.5362433862433862, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.564021164021164, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.5632275132275132, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.5693121693121693, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.5441798941798941, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.5640211640211641, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.5722222222222222, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.5507936507936508, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.5407407407407407, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.5624338624338624, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.5571428571428572, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.5687830687830688, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.6698412698412699, "id_best": 48, "lr_best": 0.015, "wd_best": 0.05, "train/loss_best": 0.7182302856445313, "validation/loss_best": 0.6461275219917297, "validation/acc_best": 0.6774193548387096, "validation/f1_best": 0.6704756842944459, "validation/bacc_best": 0.6698412698412699} +{"epoch": 1, "train/lr": 8.993993993993998e-05, "train/loss": 0.6687449526786804, "train/grad": 0.3010814468935132, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.68443115234375, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.6839404296875, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.68342529296875, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.6829296875, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.6826708984375, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.68225830078125, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.6818212890625, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.6814404296875, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.68091552734375, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.68029052734375, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.6797802734375, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.67915283203125, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.67845947265625, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.67755615234375, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.676630859375, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.67557373046875, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.67406005859375, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.671806640625, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.66885009765625, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.6662841796875, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.663447265625, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.66057373046875, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.656739501953125, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.65263427734375, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.648651123046875, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.645150146484375, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.6441162109375, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.6448382568359375, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.6471905517578125, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.6501690673828125, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.65181640625, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.652249755859375, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.6521173095703126, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.6510589599609375, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.6501507568359375, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.6503253173828125, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.6500823974609375, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.64964599609375, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.648873291015625, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.6429629516601563, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.6423602294921875, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.6338345336914063, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.6433004760742187, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.6504733276367187, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.6893824005126953, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.6961384582519531, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.722158002257347, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.7613578510284423, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.7444270050525665, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.036338528776541354, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.036242533235345036, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.03613891830900684, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.036099370669107886, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.0360745763592422, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.036070774940308185, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.036074177902191876, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.03610518763540313, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.03614166088635102, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.03618089818395674, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.03624253849964589, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.03631805735873059, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.036397492811083794, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.03651042712619528, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.03660355744184926, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.0366898572538048, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.03679200031328946, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.03690896313637495, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.03707690479233861, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.037260502260178324, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.03750473492313176, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.03765174529980868, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.03759160673711449, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.03752621633931994, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.03752659166697413, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.037647027932107446, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.03787990250624716, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0381859075371176, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.038629073083866386, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.03887022734852508, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.03888758895918727, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.03866881666239351, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.03765872342512012, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.03621366693638265, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.03464236615691334, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.03366800491232425, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.03234994113910943, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.03126849020132795, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.030647353210952133, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.02966973024653271, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.02914109976263717, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.028281439437996596, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.03191366784274578, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.035330358031205836, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.04522102598100901, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0532193905999884, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.056229631640017035, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.06429583214223385, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.07614172994159162, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.6829372644424438, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.6828722953796387, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.6828621625900269, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.6829140186309814, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.6829155683517456, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.682913064956665, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.6827795505523682, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.6826379299163818, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.6824124455451965, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.6819637417793274, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.6814562082290649, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.680460512638092, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.679365336894989, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.677621066570282, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.6759696006774902, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.6745558381080627, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.6727544069290161, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.6705145835876465, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.6679053902626038, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.6656613349914551, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.6638320684432983, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.6646614670753479, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.6679152250289917, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.6651390194892883, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.6553477644920349, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.6478098034858704, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.6461650729179382, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.645942747592926, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.6454803943634033, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.6451383233070374, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.6454074382781982, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.6456875205039978, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.6466982960700989, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.6484248042106628, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.6512265801429749, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.6518635749816895, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.6506989002227783, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.6406199336051941, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.6255743503570557, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.6301127076148987, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.6145957112312317, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.9522897005081177, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.9882752895355225, "validation/loss_043_lr2.2e+01_wd1.0e+00": 1.378461241722107, "validation/loss_044_lr2.6e+01_wd1.0e+00": 1.0993260145187378, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.9668365120887756, "validation/loss_046_lr3.6e+01_wd1.0e+00": 2.1096041202545166, "validation/loss_047_lr4.3e+01_wd1.0e+00": 1.5430314540863037, "validation/loss_048_lr5.0e+01_wd1.0e+00": 1.9438451528549194, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.5645161290322581, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.5645161290322581, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.5645161290322581, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.5564516129032258, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.5564516129032258, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.5725806451612904, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.5645161290322581, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.5483870967741935, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.5564516129032258, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.5645161290322581, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.5564516129032258, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.5483870967741935, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.5483870967741935, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.5645161290322581, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.5806451612903226, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.5806451612903226, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.5806451612903226, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.5806451612903226, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.5887096774193549, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.5967741935483871, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.5967741935483871, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.6048387096774194, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.5967741935483871, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.5967741935483871, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.6290322580645161, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.6290322580645161, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.6129032258064516, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.6370967741935484, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.6290322580645161, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.6370967741935484, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.6370967741935484, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.6290322580645161, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.6129032258064516, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.5967741935483871, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.6129032258064516, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.6129032258064516, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.6129032258064516, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.6451612903225806, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.6129032258064516, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.6532258064516129, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.6693548387096774, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.49193548387096775, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.47580645161290325, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.47580645161290325, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.5403225806451613, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.5483870967741935, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.4596774193548387, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.5564516129032258, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.5, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.36082474226804123, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.36082474226804123, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.36082474226804123, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.35751295336787564, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.35751295336787564, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.3963442638008634, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.39237749546279493, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.39784946236559143, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.4266498528793611, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.4529411764705882, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.4573088246996101, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.4426966292134832, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.4426966292134832, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.4529411764705882, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.46320346320346323, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.46320346320346323, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.46320346320346323, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.46320346320346323, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.4785190071740744, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.4934640522875817, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.48384948384948384, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.46734461295695623, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.450354609929078, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.450354609929078, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.5339869281045752, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.5809579782544814, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.5814345991561182, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.6160990712074303, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.6119727891156463, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.6217205613178767, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.6217205613178767, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.6145945945945945, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.6003223207091055, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.58994708994709, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.610369206598586, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.6112852664576802, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.6119947848761408, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.6336287939833467, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.5627387599177196, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.6530227110040997, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.6644445911160979, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.42957283680175246, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.4041546536556517, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.3962999026290166, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.4953951595630756, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.5203094777562862, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.34966731898238745, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.5343756400628115, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.42797619047619045, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.5, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.5, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.5, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.4928571428571429, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.4928571428571429, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.5113756613756614, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.5042328042328043, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.4920634920634921, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.5034391534391535, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.5148148148148148, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.5097883597883598, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.5005291005291005, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.5005291005291005, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.5148148148148148, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.5291005291005291, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.5291005291005291, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.5291005291005291, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.5291005291005291, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.5383597883597884, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.5476190476190477, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.5455026455026455, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.5484126984126985, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.5391534391534392, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.5391534391534392, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.5804232804232804, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.5952380952380952, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.5873015873015873, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.6171957671957672, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.6121693121693121, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.6214285714285714, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.6214285714285714, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.6142857142857143, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.6, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.58994708994709, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.6126984126984127, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.6148148148148148, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.6169312169312169, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.6328042328042328, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.5788359788359788, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.6611111111111111, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.6648148148148147, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.5436507936507936, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.5293650793650794, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.5314814814814814, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.5886243386243386, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.5894179894179894, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.5214285714285715, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.5944444444444444, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.555026455026455, "id_best": 40, "lr_best": 0.0042, "wd_best": 0.05, "train/loss_best": 0.6423602294921875, "validation/loss_best": 0.6145957112312317, "validation/acc_best": 0.6693548387096774, "validation/f1_best": 0.6644445911160979, "validation/bacc_best": 0.6648148148148147} +{"epoch": 2, "train/lr": 0.00014999999999999988, "train/loss": 0.6701799073815345, "train/grad": 0.3962735355645418, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.67776611328125, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.677119140625, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.67607177734375, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.67524169921875, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.67433837890625, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.6731396484375, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.67194580078125, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.67057861328125, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.66908203125, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.66758056640625, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.66624267578125, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.66440185546875, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.6628125, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.6608154296875, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.6590869140625, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.65728271484375, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.65496826171875, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.651988525390625, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.648560791015625, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.646055908203125, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.6446826171875, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.64558349609375, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.649049072265625, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.653243408203125, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.655736083984375, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.65661865234375, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.6570001220703126, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.6567132568359375, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.65556884765625, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.6539569091796875, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.65212890625, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.65005859375, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.6466015625, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.6423941040039063, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.6398721313476563, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.6409599304199218, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.6408885192871093, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.6525249481201172, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.6433160781860352, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.6334185028076171, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.6299717903137207, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.5873807114362717, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.5652698451280593, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.6142644906044006, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.6255775298178196, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.6975823098421097, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.7691508275270462, "train/loss_047_lr4.3e+01_wd1.0e+00": 1.0183514593541623, "train/loss_048_lr5.0e+01_wd1.0e+00": 1.0558720850944519, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.03377724532503635, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.033779278509318826, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.033782481672242286, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.03380460083950311, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.03381892998702824, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.033827639361843465, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.03385557929053903, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.03389421593397856, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.03395597396884113, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.03405547838658094, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.03416169936303049, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.034364967439323664, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.034562343815341595, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.03488124986179173, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.03518164568580687, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.03543388681486249, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.0357287471415475, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.03615512364543974, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.036614429079927506, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.03688262790907174, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.03700074343476444, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.03725518431514502, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.037864787797443566, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.03842851801775396, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.038345645330846306, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.03776524493005127, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.03695274462457746, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.03592531330883503, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.03414079350885004, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0318823911389336, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.030071346517652274, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.028485113512724636, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.02693995908368379, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.025654300996102393, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.02507650909945369, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.025548027800396084, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.027079071018379183, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.03176474144682288, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.034777435092255476, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.04640025352593511, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.04905706794001162, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.05459797759540379, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.051422994048334655, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.06620364234782755, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.07613151545636355, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.08857312457635999, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.10144791821949184, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.1406058124313131, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.12011235013604164, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.6823795437812805, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.6822981238365173, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.6821350455284119, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.6819403767585754, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.681691586971283, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.6813235878944397, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.6808732151985168, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.6802036166191101, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.679297149181366, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.6781998872756958, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.6770726442337036, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.6753725409507751, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.6738668084144592, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.6717684864997864, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.6699272394180298, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.6687694787979126, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.6688591837882996, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.6706123948097229, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.6706510186195374, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.6678788661956787, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.6649459600448608, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.6643885970115662, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.6636878848075867, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.6633899211883545, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.6691049337387085, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.6830967664718628, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.6917392015457153, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.694972574710846, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.6938817501068115, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.6890668272972107, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.6827630400657654, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.6739493012428284, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.6486942768096924, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.632841169834137, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.6468530297279358, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.6665565371513367, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.645595908164978, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.6607222557067871, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.6629377603530884, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.7424564957618713, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.9138487577438354, "validation/loss_041_lr1.6e+01_wd1.0e+00": 1.0139116048812866, "validation/loss_042_lr1.9e+01_wd1.0e+00": 1.09820556640625, "validation/loss_043_lr2.2e+01_wd1.0e+00": 1.2726414203643799, "validation/loss_044_lr2.6e+01_wd1.0e+00": 1.1186330318450928, "validation/loss_045_lr3.1e+01_wd1.0e+00": 1.879448652267456, "validation/loss_046_lr3.6e+01_wd1.0e+00": 1.5705486536026, "validation/loss_047_lr4.3e+01_wd1.0e+00": 2.5102524757385254, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.6931473016738892, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.5564516129032258, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.5564516129032258, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.5725806451612904, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.5645161290322581, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.5806451612903226, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.5725806451612904, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.5725806451612904, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.5403225806451613, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.5483870967741935, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.5403225806451613, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.532258064516129, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.5403225806451613, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.5483870967741935, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.5725806451612904, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.5725806451612904, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.5806451612903226, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.5887096774193549, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.5887096774193549, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.6048387096774194, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.5887096774193549, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.5887096774193549, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.5564516129032258, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.5483870967741935, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.5806451612903226, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.6129032258064516, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.6209677419354839, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.6048387096774194, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.5967741935483871, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.5967741935483871, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.6048387096774194, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.6129032258064516, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.6209677419354839, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.6612903225806451, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.5887096774193549, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.6048387096774194, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.5967741935483871, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.6290322580645161, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.6370967741935484, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.6532258064516129, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.5967741935483871, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.5645161290322581, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.5645161290322581, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.5645161290322581, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.5887096774193549, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.6290322580645161, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.5, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.5403225806451613, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.5080645161290323, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.43548387096774194, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.35751295336787564, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.35751295336787564, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.3963442638008634, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.39237749546279493, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.42836879432624114, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.43612183612183614, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.4474989491382934, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.42773864464415834, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.452020202020202, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.44673189823874754, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.44144144144144143, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.4552601156069364, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.46878824969400246, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.5008733956102377, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.4934874759152216, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.4911616161616162, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.4879766820500364, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.4785190071740744, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.5080560278519958, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.4967772738123657, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.5382256297918948, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.5180552611122888, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.5116736990154711, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.5319396051103369, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.5377446411929171, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.5194194771996372, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.46734461295695623, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.450354609929078, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.450354609929078, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.46734461295695623, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.4838709677419355, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.5100462379150904, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.6015911872705019, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.548511458556436, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.5931704050887178, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.5958279009126467, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.6169755573462261, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.6129032258064516, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.6493719997369632, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.5929621848739496, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.5475675675675675, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.5644028103044496, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.5634941329856584, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.4785190071740744, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.6025641025641026, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.4967268918565069, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.5239442311578096, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.4905368087829191, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.30337078651685395, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.4928571428571429, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.4928571428571429, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.5113756613756614, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.5042328042328043, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.5227513227513227, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.5177248677248677, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.5198412698412699, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.4912698412698413, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.5026455026455026, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.4955026455026455, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.4883597883597884, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.4976190476190476, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.5068783068783069, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.5325396825396825, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.5304232804232804, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.5354497354497354, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.5404761904761904, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.5383597883597884, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.5568783068783069, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.5425925925925926, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.5552910052910053, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.5288359788359789, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.5216931216931217, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.5481481481481482, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.5703703703703704, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.5711640211640212, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.5484126984126985, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.5391534391534392, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.5391534391534392, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.5484126984126985, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.5576719576719577, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.569047619047619, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.6216931216931217, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.5595238095238095, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.5928571428571429, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.6005291005291005, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.6164021164021164, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.6150793650793651, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.6505291005291005, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.5941798941798941, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.5486772486772487, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.571957671957672, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.5677248677248676, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.5383597883597884, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.6058201058201058, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.4978835978835978, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.5251322751322751, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.5410052910052909, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.5, "id_best": 38, "lr_best": 0.00294, "wd_best": 0.05, "train/loss_best": 0.6433160781860352, "validation/loss_best": 0.6629377603530884, "validation/acc_best": 0.6532258064516129, "validation/f1_best": 0.6493719997369632, "validation/bacc_best": 0.6505291005291005} +{"epoch": 3, "train/lr": 0.0002100600600600602, "train/loss": 0.6331671947240829, "train/grad": 0.46085975259542467, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.67736572265625, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.676416015625, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.67495361328125, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.67362548828125, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.67221435546875, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.6705126953125, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.6687255859375, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.6667333984375, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.66440185546875, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.6620751953125, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.6597998046875, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.6567724609375, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.65388427734375, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.649942626953125, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.6464794921875, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.643660888671875, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.64074462890625, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.638236083984375, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.6364013671875, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.63457763671875, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.631126708984375, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.6275689697265625, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.62505126953125, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.6237957763671875, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.623143310546875, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.62189453125, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.6202841186523438, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.6178250122070312, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.6135427856445312, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.6072578430175781, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.5979856872558593, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.5873305511474609, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.5577383041381836, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.526710319519043, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.46841538533568383, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.44914610028266905, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.40537453413009644, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.37242028266191485, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.30834746748209, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.40384862139821054, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.37862069755792616, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.4054871991276741, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.4017220689356327, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.6877989983558654, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.9640371975302696, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.8636921064555645, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.8549766302108764, "train/loss_047_lr4.3e+01_wd1.0e+00": 1.721121333539486, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.69140625, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.031667651920579375, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.031659803236834705, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.03165304734837264, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.03165046591311693, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.03164253787137568, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.03166140718851238, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.031670576077885926, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.031694677211344245, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.03172920431010425, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.03177482982166111, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.03179963110480458, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.03184577343054116, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.03190917647443712, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.03199285788461566, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.032159595312550665, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.03241977888625115, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.0327558371797204, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.033104590815491976, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.033297834512777624, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.03329742616508156, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.03308038017246872, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.03287776975426823, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.03259741716086864, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.03216930335853249, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.03173620590474457, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.03090117351617664, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.02959573226515204, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.028289106932934373, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.026620262670330703, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.024997297460213303, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.02435996207874268, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0253031905554235, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.02630488038063049, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0289943091198802, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.03250082718208432, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.03418673079926521, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.03607367172837257, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.03573891785228625, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.035351415895856914, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.05440185958519578, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.04984213215298951, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.07557224311749451, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.08365221151500009, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.11648054333403707, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.14832904847338796, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.13539583768928423, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.06567539621144533, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.1676884276419878, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.6820014715194702, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.6816695332527161, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.6811250448226929, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.6803780198097229, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.679683268070221, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.678595244884491, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.6773086786270142, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.6758878231048584, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.6742508411407471, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.6726347208023071, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.6711481809616089, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.6691653728485107, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.6673974394798279, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.6653438806533813, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.6641871333122253, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.6635807752609253, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.6631453037261963, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.6616899967193604, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.6598908305168152, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.6629801988601685, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.6777371764183044, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.6966239809989929, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.7124068737030029, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.7228089570999146, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.7265771627426147, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.7192806005477905, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.7060992121696472, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.6942970752716064, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.686513364315033, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.6934345364570618, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.7285853624343872, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.744120180606842, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.7780935168266296, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.9860225319862366, "validation/loss_034_lr5.1e+00_wd1.0e+00": 1.3509331941604614, "validation/loss_035_lr6.0e+00_wd1.0e+00": 1.3478425741195679, "validation/loss_036_lr7.1e+00_wd1.0e+00": 1.1035789251327515, "validation/loss_037_lr8.3e+00_wd1.0e+00": 1.3951544761657715, "validation/loss_038_lr9.8e+00_wd1.0e+00": 1.423723816871643, "validation/loss_039_lr1.2e+01_wd1.0e+00": 1.518473505973816, "validation/loss_040_lr1.4e+01_wd1.0e+00": 1.7146949768066406, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.240231990814209, "validation/loss_042_lr1.9e+01_wd1.0e+00": 4.293094158172607, "validation/loss_043_lr2.2e+01_wd1.0e+00": 1.5654305219650269, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.797574281692505, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.7720608711242676, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.6931473016738892, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.5806451612903226, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.5725806451612904, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.5725806451612904, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.5564516129032258, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.5564516129032258, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.5483870967741935, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.5645161290322581, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.5403225806451613, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.5403225806451613, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.5645161290322581, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.5564516129032258, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.5725806451612904, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.5806451612903226, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.5806451612903226, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.5887096774193549, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.5725806451612904, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.5564516129032258, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.5725806451612904, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.5887096774193549, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.5806451612903226, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.5967741935483871, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.5967741935483871, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.6048387096774194, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.6129032258064516, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.6048387096774194, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.5967741935483871, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.6129032258064516, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.6129032258064516, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.6048387096774194, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.6209677419354839, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.6612903225806451, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.6532258064516129, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.6370967741935484, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.6129032258064516, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.6290322580645161, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.6048387096774194, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.5725806451612904, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.5887096774193549, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.5564516129032258, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.5806451612903226, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.5806451612903226, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.6209677419354839, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.5967741935483871, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.6129032258064516, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.6048387096774194, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.6290322580645161, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.43548387096774194, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.43548387096774194, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.43548387096774194, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.44086021505376344, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.43612183612183614, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.4474989491382934, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.43761853714851157, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.43761853714851157, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.4326797385620915, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.4626003210272873, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.44673189823874754, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.44673189823874754, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.48776009791921665, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.4891768406860909, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.5141568714423006, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.5263003232441963, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.5319396051103369, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.5531057875768497, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.5440860215053763, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.5307877536979704, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.5513074349696183, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.548511458556436, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.5067319461444308, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.5024077046548956, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.4934640522875817, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.4989692421868558, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.5044955044955045, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.4989692421868558, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.5024077046548956, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.5303030303030303, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.551131221719457, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.566216891554223, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.5744432274552757, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.6015911872705019, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.5950482266271739, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.592552026286966, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.5303030303030303, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.5698340874811463, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.5614579574160953, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.5623043623043623, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.5880398671096345, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.5541026479241582, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.5802083333333333, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.5371805914441573, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.6118548118548119, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.575109649122807, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.6125, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.5243835616438356, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.5636474908200735, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.30337078651685395, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.30337078651685395, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.30337078651685395, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.5248677248677249, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.5177248677248677, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.5198412698412699, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.5055555555555555, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.5055555555555555, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.4984126984126984, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.5169312169312169, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.4955026455026455, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.4955026455026455, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.5232804232804232, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.5182539682539682, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.5367724867724868, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.5460317460317461, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.5481481481481482, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.5616402116402117, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.5494708994708994, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.5351851851851852, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.5537037037037037, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.5595238095238095, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.5396825396825397, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.5497354497354497, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.5476190476190477, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.5547619047619048, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.5619047619047619, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.5547619047619048, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.5497354497354497, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.5682539682539682, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.5746031746031746, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.575925925925926, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.5880952380952381, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.6216931216931217, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.6145502645502645, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.6044973544973544, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.5682539682539682, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.591005291005291, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.5738095238095238, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.5621693121693122, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.5933862433862434, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.5563492063492064, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.5862433862433862, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.5502645502645502, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.6113756613756614, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.5772486772486772, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.6190476190476191, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.5611111111111111, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.5888888888888889, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.5, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.5, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.5, "id_best": 30, "lr_best": 0.00081, "wd_best": 0.05, "train/loss_best": 0.5979856872558593, "validation/loss_best": 0.7285853624343872, "validation/acc_best": 0.6612903225806451, "validation/f1_best": 0.6015911872705019, "validation/bacc_best": 0.6216931216931217} +{"epoch": 4, "train/lr": 0.0002701201201201201, "train/loss": 0.5605431888997555, "train/grad": 0.37844509616494176, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.66890625, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.6678271484375, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.666162109375, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.66454345703125, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.66329345703125, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.6615185546875, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.65962646484375, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.6576220703125, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.65499755859375, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.65200927734375, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.64940185546875, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.645640869140625, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.6425, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.639083251953125, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.637235107421875, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.636141357421875, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.6352252197265625, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.6336651611328125, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.6306781005859375, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.62607177734375, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.6199630737304688, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.6164486694335938, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.6157357788085938, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.6158451843261719, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.6156846618652344, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.6129127502441406, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.6056806945800781, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.5964460754394532, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.5773179626464844, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.5231259059906006, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.48618337750434876, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.4605742782354355, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.3272553986310959, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.23586280047893524, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.14562765941023825, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.21002565190196038, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.22740919694304465, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.24026281595230103, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.19428356409072875, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.2341849148273468, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.30313697069883344, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.3062733402848244, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.394104111790657, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.6121605409681797, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.8902990090847015, "train/loss_045_lr3.1e+01_wd1.0e+00": 1.1334446363151074, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.69140625, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.69140625, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.69140625, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.03470022754278034, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.03472270119469613, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.03476521321106702, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.03482938526663929, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.03487683198880404, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.03495806267950684, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.03504444564692676, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.03513571654912084, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.035293718478642405, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.03550160275306553, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.03575400060042739, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.03619359306525439, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.036616461877711115, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.03717445634771138, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.03773187747923657, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.03818987217033282, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.038631312877405434, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.0388225978682749, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.03847294551320374, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.03774111566133797, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.03676435751374811, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.036130427191965284, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.03549426077399403, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.03465429833158851, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.03358755314024165, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.03216705997241661, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.030824054670520126, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.029756345683708788, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.02921001071576029, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.030398279493674636, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.03259434631559998, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.03431771140079945, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.03566690366715193, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.03097868283803109, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.02283298864742392, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0391526026558131, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.03649059048475465, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.051530535354686435, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.035163479867260324, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.044931027807106144, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.05633940315878135, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.06151492644563405, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.08998855369630292, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.11208229981421028, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.04701841406524181, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.09513082536286674, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.6805336475372314, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.6797555685043335, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.678430438041687, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.6769949197769165, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.6756138205528259, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.6736705303192139, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.6717102527618408, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.6696956157684326, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.6674138307571411, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.665021538734436, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.6631402373313904, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.6614922881126404, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.6615196466445923, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.6618674397468567, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.6600469946861267, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.6568201184272766, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.6512463092803955, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.6458168029785156, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.6424039006233215, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.6406058669090271, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.6396306753158569, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.6374645233154297, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.635550856590271, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.6344175934791565, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.6336020231246948, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.6329329609870911, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.6346825361251831, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.6405984163284302, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.6638543009757996, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.8488367795944214, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.9818129539489746, "validation/loss_031_lr3.1e+00_wd1.0e+00": 1.0562103986740112, "validation/loss_032_lr3.7e+00_wd1.0e+00": 1.5363291501998901, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.112332344055176, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.1581854820251465, "validation/loss_035_lr6.0e+00_wd1.0e+00": 1.9885135889053345, "validation/loss_036_lr7.1e+00_wd1.0e+00": 1.882416844367981, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.8274245262145996, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.4988861083984375, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.816063165664673, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.541710138320923, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.9945151805877686, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.5278894901275635, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.9125125408172607, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.6931473016738892, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.5806451612903226, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.5725806451612904, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.5725806451612904, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.5725806451612904, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.5725806451612904, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.5725806451612904, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.5806451612903226, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.5806451612903226, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.5806451612903226, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.5967741935483871, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.5967741935483871, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.6048387096774194, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.6048387096774194, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.6048387096774194, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.6129032258064516, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.6129032258064516, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.6129032258064516, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.6209677419354839, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.6290322580645161, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.6290322580645161, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.6370967741935484, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.6290322580645161, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.6209677419354839, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.6209677419354839, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.6290322580645161, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.6532258064516129, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.6532258064516129, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.6290322580645161, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.6370967741935484, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.6290322580645161, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.6370967741935484, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.6612903225806451, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.6370967741935484, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.6129032258064516, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.6693548387096774, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.6129032258064516, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.6129032258064516, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.6129032258064516, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.5645161290322581, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.5, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.5725806451612904, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.5645161290322581, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.5806451612903226, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.6048387096774194, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.43548387096774194, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.43548387096774194, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.43548387096774194, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.43548387096774194, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.43548387096774194, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.44086021505376344, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.43612183612183614, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.4474989491382934, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.4474989491382934, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.4474989491382934, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.4474989491382934, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.46320346320346323, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.46320346320346323, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.46320346320346323, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.4934640522875817, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.4934640522875817, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.4989692421868558, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.4891971416561581, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.4891971416561581, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.5223113964686998, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.5223113964686998, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.5446756425948592, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.569157980335625, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.5859465737514518, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.5859465737514518, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.592552026286966, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.5905828308929084, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.5839223245520098, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.5881563140414104, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.5905828308929084, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.605825386264508, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.6232068405059713, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.6119727891156463, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.6094351508364246, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.6025641025641026, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.5874916833000665, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.6015911872705019, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.6129032258064516, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.5814345991561182, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.6407321037382516, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.6003223207091055, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.6025641025641025, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.6112852664576802, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.5645161290322581, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.4689140646587455, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.5643931861867832, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.5603991596638656, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.5802083333333333, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.5931704050887178, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.30337078651685395, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.30337078651685395, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.30337078651685395, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.30337078651685395, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.30337078651685395, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.5248677248677249, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.5177248677248677, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.5198412698412699, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.5198412698412699, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.5198412698412699, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.5198412698412699, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.5291005291005291, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.5291005291005291, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.5291005291005291, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.5476190476190477, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.5476190476190477, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.5547619047619048, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.5526455026455026, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.5526455026455026, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.5661375661375662, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.5661375661375662, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.5724867724867725, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.5859788359788359, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.5973544973544973, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.5973544973544973, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.6044973544973544, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.5994708994708995, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.5923280423280424, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.5944444444444444, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.5994708994708995, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.6187830687830688, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.6272486772486773, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.6121693121693121, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.6129629629629629, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.6058201058201058, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.6023809523809524, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.6216931216931217, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.6150793650793651, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.5873015873015873, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.6436507936507936, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.6, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.602116402116402, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.6317460317460317, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.5740740740740741, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.4767195767195767, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.5642857142857143, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.5613756613756614, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.5862433862433862, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.5928571428571429, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.5, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.5, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.5, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.5, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.5, "id_best": 34, "lr_best": 0.0015299999999999997, "wd_best": 0.05, "train/loss_best": 0.14562765941023825, "validation/loss_best": 2.1581854820251465, "validation/acc_best": 0.6693548387096774, "validation/f1_best": 0.6407321037382516, "validation/bacc_best": 0.6436507936507936} +{"epoch": 5, "train/lr": 0.00029891323817685334, "train/loss": 0.5100068244338035, "train/grad": 0.3174244713783264, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.67378173828125, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.6721240234375, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.6696875, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.66735107421875, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.66510498046875, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.66204345703125, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.6588232421875, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.65544189453125, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.65126953125, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.6473486328125, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.643795166015625, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.639163818359375, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.63501708984375, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.6300048828125, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.6257476806640625, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.622359619140625, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.619222412109375, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.6162200927734375, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.61272705078125, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.608863525390625, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.6043246459960937, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.6009588623046875, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.5972283935546875, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.5914266967773437, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.5791972351074218, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.5439656829833984, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.4930048751831055, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.4465894603729248, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.3685257697105408, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.19987967669963835, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.15108702152967454, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.09884215638041496, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.08286995261907577, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.03477820053696632, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.1554094848036766, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.13235035553574562, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.04664079889655113, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.12104720234870911, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.3228182885050774, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.20049576207995415, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.09299641117453575, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.11615946993231774, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.8210339312255382, "train/loss_043_lr2.2e+01_wd1.0e+00": 1.255575939565897, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.69140625, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.69140625, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.69140625, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.69140625, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.69140625, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.035754525545053185, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.03577724813017994, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.03578559736721218, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.035797597547061744, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.03579758212901652, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.03579856948461384, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.03580983303952962, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.03581324089318514, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.03589121669530868, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.03604456441942602, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.0361930028302595, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.03637021655682474, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.03645748684182763, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.036487441309727725, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.03650608038995415, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.03635771242901683, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.036047220448963344, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.035439841710031034, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.03467022092547268, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.03425385133363307, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.03418077370151877, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.034092305046506226, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.03346963277552277, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.032337860702537, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.031044614613056184, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.030901675424538554, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.03103943316731602, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.03134927107952535, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.03143045041710138, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.025895243538543583, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.021926563740707936, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.017242766286653933, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.01658185042448167, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.014631676236367639, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.028757243618201755, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.03288100508576463, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.011727207521214495, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.02263315335592779, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.06173293682100848, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.04901273901108652, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.026077516945715046, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.033479529556443594, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.029876558487194414, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0939737772513763, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.6773619055747986, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.6760513186454773, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.6739049553871155, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.6719129085540771, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.6700880527496338, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.6679617166519165, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.6659456491470337, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.6644154787063599, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.6626749634742737, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.6606184840202332, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.6583889722824097, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.6543565392494202, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.6502059698104858, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.6457775831222534, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.6439076066017151, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.6450786590576172, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.6478062272071838, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.6469264626502991, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.6445949673652649, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.6443594694137573, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.6406375169754028, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.6336539387702942, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.6266024708747864, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.6208027005195618, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.6463563442230225, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.679746687412262, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.836664080619812, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.9628369212150574, "validation/loss_028_lr1.9e+00_wd1.0e+00": 1.2853789329528809, "validation/loss_029_lr2.3e+00_wd1.0e+00": 1.7657445669174194, "validation/loss_030_lr2.7e+00_wd1.0e+00": 1.6809502840042114, "validation/loss_031_lr3.1e+00_wd1.0e+00": 1.818143367767334, "validation/loss_032_lr3.7e+00_wd1.0e+00": 1.9779748916625977, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.493400812149048, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.0814061164855957, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.494431257247925, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.993377447128296, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.0771820545196533, "validation/loss_038_lr9.8e+00_wd1.0e+00": 4.556786060333252, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.711188554763794, "validation/loss_040_lr1.4e+01_wd1.0e+00": 4.2239603996276855, "validation/loss_041_lr1.6e+01_wd1.0e+00": 4.120182514190674, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.6931473016738892, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.5725806451612904, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.5725806451612904, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.5806451612903226, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.5806451612903226, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.5887096774193549, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.5806451612903226, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.5806451612903226, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.5806451612903226, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.5967741935483871, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.6129032258064516, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.6048387096774194, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.6209677419354839, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.6290322580645161, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.6209677419354839, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.6129032258064516, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.6370967741935484, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.6370967741935484, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.6370967741935484, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.6290322580645161, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.6209677419354839, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.6370967741935484, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.6451612903225806, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.6612903225806451, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.6532258064516129, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.6129032258064516, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.6129032258064516, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.6290322580645161, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.6370967741935484, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.6048387096774194, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.6048387096774194, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.6290322580645161, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.5967741935483871, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.6209677419354839, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.6129032258064516, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.6532258064516129, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.6370967741935484, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.6048387096774194, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.5806451612903226, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.5806451612903226, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.5725806451612904, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.6209677419354839, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.5887096774193549, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.43548387096774194, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.43548387096774194, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.43548387096774194, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.43548387096774194, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.43548387096774194, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.43548387096774194, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.43548387096774194, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.4474989491382934, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.4474989491382934, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.46320346320346323, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.46320346320346323, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.4785190071740744, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.46320346320346323, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.46320346320346323, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.46320346320346323, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.4735054347826087, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.5044955044955045, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.5080560278519958, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.5508285163776493, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.5698340874811463, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.569157980335625, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.5627387599177196, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.5632093933463796, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.5632093933463796, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.5632093933463796, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.5570052811432122, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.5508285163776493, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.5762132604237867, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.594047619047619, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.6219512195121951, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.626793588577028, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.5727820844099913, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.5727820844099913, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.5636474908200735, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.5820537787431653, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.5614579574160953, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.578494623655914, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.6145945945945945, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.58994708994709, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.6021028196900389, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.6003223207091055, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.6331613347093223, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.6301451580831179, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.566216891554223, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.5735449735449736, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.5465541490857947, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.4855577299412916, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.5634783911317505, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.5435582822085889, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.30337078651685395, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.30337078651685395, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.30337078651685395, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.30337078651685395, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.30337078651685395, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.30337078651685395, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.30337078651685395, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.5198412698412699, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.5198412698412699, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.5291005291005291, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.5291005291005291, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.5383597883597884, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.5291005291005291, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.5291005291005291, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.5291005291005291, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.5433862433862434, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.5619047619047619, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.5568783068783069, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.5796296296296296, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.591005291005291, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.5859788359788359, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.5788359788359788, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.593915343915344, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.593915343915344, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.593915343915344, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.5867724867724867, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.5796296296296296, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.5981481481481481, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.6095238095238095, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.6301587301587301, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.6293650793650793, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.5830687830687831, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.5830687830687831, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.5888888888888889, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.6002645502645503, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.5738095238095238, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.5822751322751323, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.6142857142857143, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.58994708994709, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.602910052910053, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.6, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.6335978835978836, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.62989417989418, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.575925925925926, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.5735449735449736, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.5544973544973545, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.5283068783068783, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.5838624338624339, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.5574074074074075, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.5, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.5, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.5, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.5, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.5, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.5, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.5, "id_best": 34, "lr_best": 0.0015299999999999997, "wd_best": 0.05, "train/loss_best": 0.1554094848036766, "validation/loss_best": 2.0814061164855957, "validation/acc_best": 0.6532258064516129, "validation/f1_best": 0.6331613347093223, "validation/bacc_best": 0.6335978835978836} +{"epoch": 6, "train/lr": 0.0002924170901991409, "train/loss": 0.44772895619273184, "train/grad": 0.23613307397812605, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.663466796875, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.66148681640625, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.658564453125, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.6558837890625, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.6535009765625, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.6505908203125, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.64744140625, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.6442236328125, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.6402197265625, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.636500244140625, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.633416748046875, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.63002197265625, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.627720947265625, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.62510986328125, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.6226593017578125, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.6201556396484375, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.616295166015625, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.6115576171875, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.607747802734375, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.6053067016601562, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.6025820922851562, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.5975650024414062, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.58679443359375, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.5583636474609375, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.49248340606689456, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.3639292001724243, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.26430803835391997, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.1793779507279396, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.07996126160025596, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.02235129341483116, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.00391014963388443, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.0018729537725448609, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.001014300137758255, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.000551055520772934, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.0010443982481956483, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.0004772096872329712, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.0785354308784008, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.00026053547859191897, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.03512164413928986, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.10896656021475792, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.3178372879326343, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.0896971832215786, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.69140625, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.69140625, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.69140625, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.69140625, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.69140625, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.69140625, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.69140625, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.03339858617866412, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.03337217417079955, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.03336298276204616, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.03335743133444339, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.03338186313863844, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.033422028643544766, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.033512417892925445, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.03360529738245532, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.0337688330700621, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.03395714248763397, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.034121563476510346, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.03434740398544818, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.03453520986717194, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.03480487656081095, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.03520705251488834, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.0355562410177663, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.03583822885528207, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.036021147686988116, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.036405790252611044, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.036965342718176544, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.037362757408991455, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.037333019208163024, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.03710971711203456, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.03695207373704761, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.03700277345720679, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.03493854441680014, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.030916221456136553, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.027365813942160457, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.01812033329391852, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.011654203332582255, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0017381835235573816, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0007938293503684691, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0004081774852784292, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0002909544637623185, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0004745600108162762, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0004061241402723681, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.02737515335156786, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0003164243311653081, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.015901043973819355, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.02395664398845838, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.08327987109929282, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0320148686351331, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.6751652359962463, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.6736072301864624, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.6710744500160217, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.6688348054885864, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.6668449640274048, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.6642621159553528, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.6617891192436218, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.6593590974807739, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.6564690470695496, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.6539941430091858, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.6520339846611023, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.649201512336731, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.6465297341346741, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.64325350522995, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.6415485739707947, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.6412240266799927, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.6415489912033081, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.6421560049057007, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.6425140500068665, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.6385425925254822, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.6319963335990906, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.6277285218238831, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.633211612701416, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.6545701622962952, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.69415682554245, "validation/loss_025_lr1.2e+00_wd1.0e+00": 1.0483145713806152, "validation/loss_026_lr1.4e+00_wd1.0e+00": 1.2254277467727661, "validation/loss_027_lr1.6e+00_wd1.0e+00": 1.4717416763305664, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.0393383502960205, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.2895913124084473, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.0722641944885254, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.1289422512054443, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.0926668643951416, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.509981155395508, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.2518396377563477, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.676278829574585, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.752739191055298, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.9642741680145264, "validation/loss_038_lr9.8e+00_wd1.0e+00": 4.613992214202881, "validation/loss_039_lr1.2e+01_wd1.0e+00": 4.073624610900879, "validation/loss_040_lr1.4e+01_wd1.0e+00": 4.8804497718811035, "validation/loss_041_lr1.6e+01_wd1.0e+00": 4.292771816253662, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.6931473016738892, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.5725806451612904, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.5725806451612904, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.5725806451612904, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.5806451612903226, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.5806451612903226, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.5967741935483871, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.5967741935483871, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.6048387096774194, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.6209677419354839, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.6129032258064516, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.6209677419354839, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.6290322580645161, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.6290322580645161, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.6370967741935484, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.6370967741935484, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.6209677419354839, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.6290322580645161, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.6290322580645161, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.6290322580645161, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.6370967741935484, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.6370967741935484, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.6532258064516129, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.6290322580645161, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.6290322580645161, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.6209677419354839, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.6048387096774194, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.6451612903225806, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.6370967741935484, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.6129032258064516, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.6048387096774194, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.6370967741935484, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.6048387096774194, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.6209677419354839, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.6048387096774194, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.6451612903225806, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.6370967741935484, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.5887096774193549, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.5725806451612904, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.5483870967741935, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.5564516129032258, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.5725806451612904, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.5080645161290323, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.43548387096774194, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.43548387096774194, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.43548387096774194, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.43548387096774194, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.43548387096774194, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.43548387096774194, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.43548387096774194, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.4678973362480771, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.4678973362480771, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.4678973362480771, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.48250401284109146, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.48250401284109146, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.5107323232323233, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.5107323232323233, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.5317148362235067, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.5573782942203995, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.551131221719457, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.5634783911317505, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.575595238095238, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.575595238095238, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.5874916833000665, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.5874916833000665, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.569157980335625, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.575595238095238, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.5698340874811463, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.5636474908200735, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.5874916833000665, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.6016277575497966, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.6301075268817204, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.6091008771929824, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.6145945945945945, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.6097756946769334, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.5385433280170122, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.6039488966318234, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.6056815772736909, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.5978378378378378, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.5907590759075907, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.6241664982824813, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.5907590759075907, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.607462787095036, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.5931704050887178, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.6313513513513513, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.6241664982824813, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.548511458556436, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.5662332519305657, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.5454307410316837, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.5180552611122888, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.5725528455284552, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.5007590258068775, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.30337078651685395, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.30337078651685395, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.30337078651685395, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.30337078651685395, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.30337078651685395, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.30337078651685395, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.30337078651685395, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.5240740740740741, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.5240740740740741, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.5240740740740741, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.5333333333333333, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.5333333333333333, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.5518518518518518, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.5518518518518518, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.5632275132275132, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.5817460317460317, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.5746031746031746, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.5838624338624339, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.5931216931216932, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.5931216931216932, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.6023809523809524, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.6023809523809524, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.5859788359788359, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.5931216931216932, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.591005291005291, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.5888888888888889, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.6023809523809524, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.6087301587301588, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.6314814814814815, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.6100529100529101, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.6142857142857143, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.6092592592592592, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.5653439153439154, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.6137566137566137, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.6108465608465609, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.5978835978835979, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.5907407407407407, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.6235449735449735, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.5907407407407407, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.6071428571428572, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.5928571428571429, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.6306878306878307, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.6235449735449735, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.5595238095238095, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.5664021164021165, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.5470899470899471, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.5288359788359789, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.5833333333333333, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.5007936507936508, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.5, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.5, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.5, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.5, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.5, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.5, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.5, "id_best": 21, "lr_best": 0.00018299999999999998, "wd_best": 0.05, "train/loss_best": 0.5975650024414062, "validation/loss_best": 0.6277285218238831, "validation/acc_best": 0.6532258064516129, "validation/f1_best": 0.6301075268817204, "validation/bacc_best": 0.6314814814814815} +{"epoch": 7, "train/lr": 0.00027969249556793234, "train/loss": 0.4221766859292984, "train/grad": 0.22906787395477296, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.667216796875, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.6650830078125, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.66179931640625, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.65892333984375, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.65611572265625, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.65249755859375, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.648671875, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.644703369140625, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.640264892578125, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.636492919921875, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.6336572265625, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.630645751953125, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.62857177734375, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.6260052490234375, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.6227886962890625, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.61873779296875, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.6124261474609375, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.60470458984375, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.595550537109375, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.5866561889648437, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.5731027221679688, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.5548345947265625, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.5190793609619141, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.4352917861938477, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.3179334408044815, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.18823009610176086, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.0989988735318184, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.04300801038742066, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.004948020726442337, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0018080641329288483, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0013604921102523804, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.0008926893770694733, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.0005308616161346435, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.0003199192881584167, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.0004927687346935272, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.0002825221419334412, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.13581862002611161, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.00020069032907485962, "train/loss_038_lr9.8e+00_wd1.0e+00": 8.491545915603638e-05, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.0013001517951488496, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.109923115670681, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.1668598946928978, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.69140625, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.69140625, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.69140625, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.69140625, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.69140625, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.69140625, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.69140625, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.033959198514930906, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.03397056424524635, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.0340047788573429, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.03406385563779622, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.03410364471841604, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.03419178718701005, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.034285555235110225, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.034362852415069936, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.0344871875597164, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.034616424283012745, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.0347750336676836, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.034970947494730356, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.03520150381606072, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.03553835375234485, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.03595289524178952, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.036316888439469036, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.03653786574024707, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.03641276875510812, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.035969326184131206, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.0353881096560508, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.034800563021562994, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.034842938664369286, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.03486215747427195, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0341071394411847, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.03201762745622545, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.031123937484808267, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.02201901082531549, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.012379244075273164, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0016385251074825646, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0006244893927214435, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0003974662354812608, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0002840084967465373, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0001751927605846504, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.00012293777233935544, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.00018927781649836107, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.00013971181695978884, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.03389125255845784, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.00010711612734098708, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0001472777528556435, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0009680710328723308, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.03725263983100669, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.051951650116782384, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.6736692786216736, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.6721720099449158, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.6701054573059082, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.6683183312416077, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.6669109463691711, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.6655871868133545, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.6644216179847717, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.6635858416557312, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.6626971364021301, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.6620032787322998, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.6609326004981995, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.6592081785202026, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.6582003235816956, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.6572443842887878, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.6571381688117981, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.6580053567886353, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.6592057347297668, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.6570594310760498, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.6510164141654968, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.6478852033615112, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.6477996706962585, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.6635293364524841, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.6984935402870178, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.8170730471611023, "validation/loss_024_lr1.0e+00_wd1.0e+00": 1.0763508081436157, "validation/loss_025_lr1.2e+00_wd1.0e+00": 1.3868285417556763, "validation/loss_026_lr1.4e+00_wd1.0e+00": 1.724479079246521, "validation/loss_027_lr1.6e+00_wd1.0e+00": 1.8365567922592163, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.391627788543701, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.4673354625701904, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.24522066116333, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.2323904037475586, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.170553684234619, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.5470032691955566, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.3054394721984863, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.6843807697296143, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.8878276348114014, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.85585355758667, "validation/loss_038_lr9.8e+00_wd1.0e+00": 4.26573371887207, "validation/loss_039_lr1.2e+01_wd1.0e+00": 4.012800216674805, "validation/loss_040_lr1.4e+01_wd1.0e+00": 4.789012432098389, "validation/loss_041_lr1.6e+01_wd1.0e+00": 11.090886116027832, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.6931473016738892, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.5725806451612904, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.5725806451612904, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.5806451612903226, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.5806451612903226, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.5887096774193549, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.5887096774193549, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.5887096774193549, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.6048387096774194, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.6048387096774194, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.6048387096774194, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.6129032258064516, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.6129032258064516, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.6129032258064516, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.6209677419354839, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.6129032258064516, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.6129032258064516, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.6129032258064516, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.6209677419354839, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.6209677419354839, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.6048387096774194, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.5967741935483871, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.6290322580645161, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.5725806451612904, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.5967741935483871, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.5806451612903226, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.6290322580645161, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.6290322580645161, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.6209677419354839, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.6129032258064516, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.5967741935483871, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.6290322580645161, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.6048387096774194, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.6290322580645161, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.6048387096774194, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.6290322580645161, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.6370967741935484, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.5887096774193549, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.5725806451612904, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.5806451612903226, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.5241935483870968, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.5806451612903226, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.5806451612903226, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.43548387096774194, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.43548387096774194, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.43548387096774194, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.43548387096774194, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.43548387096774194, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.43548387096774194, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.43548387096774194, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.4474989491382934, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.4474989491382934, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.46320346320346323, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.46320346320346323, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.4785190071740744, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.4785190071740744, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.4785190071740744, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.4989692421868558, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.4989692421868558, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.4989692421868558, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.5137254901960784, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.5223113964686998, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.5223113964686998, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.5362457229251214, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.5303030303030303, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.5303030303030303, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.5303030303030303, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.5437964774951076, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.569157980335625, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.5563344286235852, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.5499419279907085, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.5809579782544814, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.5440860215053763, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.5860042735042735, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.5735449735449736, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.6210470369386127, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.6169755573462261, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.6097756946769334, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.6003223207091055, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.5836690840719849, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.6145945945945945, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.5931704050887178, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.6145945945945945, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.5907590759075907, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.6145945945945945, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.6217205613178767, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.548511458556436, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.5662332519305657, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.5752305665349143, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.5005120502491978, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.5788923719958203, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.4911616161616162, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.30337078651685395, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.30337078651685395, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.30337078651685395, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.30337078651685395, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.30337078651685395, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.30337078651685395, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.30337078651685395, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.5198412698412699, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.5198412698412699, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.5291005291005291, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.5291005291005291, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.5383597883597884, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.5383597883597884, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.5383597883597884, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.5547619047619048, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.5547619047619048, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.5547619047619048, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.564021164021164, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.5661375661375662, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.5661375661375662, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.5753968253968254, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.5682539682539682, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.5682539682539682, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.5682539682539682, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.5775132275132275, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.5859788359788359, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.5716931216931217, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.5645502645502646, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.5952380952380952, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.5494708994708994, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.5857142857142856, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.5735449735449736, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.6206349206349207, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.6164021164021164, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.6092592592592592, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.6, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.5835978835978836, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.6142857142857143, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.5928571428571429, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.6142857142857143, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.5907407407407407, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.6142857142857143, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.6214285714285714, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.5595238095238095, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.5664021164021165, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.5756613756613758, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.5044973544973546, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.582010582010582, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.5354497354497354, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.5, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.5, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.5, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.5, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.5, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.5, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.5, "id_best": 35, "lr_best": 0.0018, "wd_best": 0.05, "train/loss_best": 0.0002825221419334412, "validation/loss_best": 2.6843807697296143, "validation/acc_best": 0.6370967741935484, "validation/f1_best": 0.6217205613178767, "validation/bacc_best": 0.6214285714285714} +{"epoch": 8, "train/lr": 0.0002612959497061927, "train/loss": 0.40058797955513, "train/grad": 0.20875128839164972, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.66373779296875, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.66098388671875, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.65674072265625, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.65304931640625, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.64965576171875, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.645458984375, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.641251220703125, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.63705810546875, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.632257080078125, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.627608642578125, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.623363037109375, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.6174041748046875, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.61222900390625, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.6053778076171875, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.5991561889648438, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.593529052734375, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.5874224853515625, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.5811215209960937, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.5738444519042969, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.56361083984375, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.5405818176269531, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.500159683227539, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.4231894087791443, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.29410442501306533, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.158937529027462, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.04587508991360664, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.012808695733547211, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0044956450164318085, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0019403113424777984, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0008713291585445405, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.000812242329120636, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.0005568431317806244, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.0003929729759693146, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.00023124724626541137, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.0003464952111244202, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.00024461120367050174, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.007452091127634048, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.000203162282705307, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.0001267164945602417, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.00020601779222488405, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.0020032018423080445, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.3685680989921093, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.69140625, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.69140625, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.69140625, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.69140625, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.69140625, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.69140625, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.69140625, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.03364121722523123, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.03363739009946585, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.033651319718919694, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.03366635172162205, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.033680705968290564, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.033705665282905105, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.03376104914583266, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.033816365622915324, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.033879727367311714, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.03389014696702361, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.03386481258552521, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.033853350975550714, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.03396612024866044, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.03418508775997907, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.034377608774229886, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.034434883571229875, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.03447186856530607, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.03450847900938243, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.034564602077007296, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.03452742130961269, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.034148616180755195, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.03494461454916745, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.035301248161122206, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0331434321962297, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.026727759850909933, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.011467919049900957, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0041244556001038294, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0014780879850150087, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0006068646224593976, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.00031824029627387063, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.00025015872483891144, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.00018605518804179155, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.00013066888985122205, "train/grad_033_lr4.3e+00_wd1.0e+00": 9.250793760656961e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0001393900688890426, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.00011442417298212603, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0017786529922589266, "train/grad_037_lr8.3e+00_wd1.0e+00": 9.679680101498889e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 7.218978873737569e-05, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.00014185362542320945, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0022011125951842203, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.07682937035184559, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.6726744174957275, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.6709309220314026, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.668463945388794, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.666232168674469, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.6643378734588623, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.662000834941864, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.6597391963005066, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.6577344536781311, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.6555801033973694, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.6543197631835938, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.6536276340484619, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.6535494327545166, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.6534104943275452, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.653164267539978, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.652174174785614, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.6494924426078796, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.6468261480331421, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.6481756567955017, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.6564666032791138, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.6655173301696777, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.6732171177864075, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.7059529423713684, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.7899842262268066, "validation/loss_023_lr8.5e-01_wd1.0e+00": 1.0093016624450684, "validation/loss_024_lr1.0e+00_wd1.0e+00": 1.4055407047271729, "validation/loss_025_lr1.2e+00_wd1.0e+00": 1.7470183372497559, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.016833543777466, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.065734386444092, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.5577123165130615, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.5461487770080566, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.3357796669006348, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.292910099029541, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.216695547103882, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.5729000568389893, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.337531089782715, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.671137571334839, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.3563687801361084, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.7738561630249023, "validation/loss_038_lr9.8e+00_wd1.0e+00": 4.016676902770996, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.8057053089141846, "validation/loss_040_lr1.4e+01_wd1.0e+00": 4.465467929840088, "validation/loss_041_lr1.6e+01_wd1.0e+00": 6.893159866333008, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.6931473016738892, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.5725806451612904, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.5725806451612904, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.5725806451612904, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.5806451612903226, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.5887096774193549, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.5887096774193549, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.5725806451612904, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.5806451612903226, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.5887096774193549, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.5967741935483871, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.5967741935483871, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.6209677419354839, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.6209677419354839, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.6209677419354839, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.6129032258064516, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.6129032258064516, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.5967741935483871, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.5967741935483871, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.6129032258064516, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.6209677419354839, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.6209677419354839, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.5806451612903226, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.5967741935483871, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.6129032258064516, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.5806451612903226, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.6370967741935484, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.6451612903225806, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.6129032258064516, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.6129032258064516, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.6048387096774194, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.6290322580645161, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.6048387096774194, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.6290322580645161, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.6129032258064516, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.6290322580645161, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.6370967741935484, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.5645161290322581, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.5806451612903226, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.5725806451612904, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.5403225806451613, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.5725806451612904, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.5806451612903226, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.43548387096774194, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.43548387096774194, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.43548387096774194, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.43548387096774194, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.43548387096774194, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.43548387096774194, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.43548387096774194, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.4678973362480771, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.4678973362480771, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.4678973362480771, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.4911616161616162, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.5049706457925636, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.5126011560693642, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.5077522282975058, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.5263003232441963, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.5382256297918948, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.5324283559577677, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.5324283559577677, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.5508285163776493, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.5508285163776493, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.5508285163776493, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.5446756425948592, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.5571428571428572, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.5499419279907085, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.5499419279907085, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.551131221719457, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.5573782942203995, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.569157980335625, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.5507246376811594, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.5860042735042735, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.6025641025641025, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.5716183895827798, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.6160990712074303, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.6336287939833467, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.5978378378378378, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.6003223207091055, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.5931704050887178, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.6145945945945945, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.5931704050887178, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.6145945945945945, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.6003223207091055, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.6145945945945945, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.6217205613178767, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.555142173797502, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.5735449735449736, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.5662332519305657, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.5174438451560046, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.5678306043269548, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.5545730864879801, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.30337078651685395, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.30337078651685395, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.30337078651685395, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.30337078651685395, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.30337078651685395, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.30337078651685395, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.30337078651685395, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.5240740740740741, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.5240740740740741, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.5240740740740741, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.5354497354497354, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.5447089947089947, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.5468253968253969, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.5346560846560847, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.5460317460317461, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.5552910052910053, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.5582010582010581, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.5582010582010581, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.5796296296296296, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.5796296296296296, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.5796296296296296, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.5724867724867725, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.5767195767195767, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.5645502645502646, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.5645502645502646, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.5746031746031746, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.5817460317460317, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.5859788359788359, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.5566137566137566, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.5857142857142856, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.602116402116402, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.5714285714285714, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.6171957671957672, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.6328042328042328, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.5978835978835979, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.6, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.5928571428571429, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.6142857142857143, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.5928571428571429, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.6142857142857143, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.6, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.6142857142857143, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.6214285714285714, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.555026455026455, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.5735449735449736, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.5664021164021165, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.5208994708994709, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.5685185185185185, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.5587301587301587, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.5, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.5, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.5, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.5, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.5, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.5, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.5, "id_best": 26, "lr_best": 0.00041999999999999996, "wd_best": 0.05, "train/loss_best": 0.012808695733547211, "validation/loss_best": 2.016833543777466, "validation/acc_best": 0.6451612903225806, "validation/f1_best": 0.6336287939833467, "validation/bacc_best": 0.6328042328042328} +{"epoch": 9, "train/lr": 0.00023803200426111704, "train/loss": 0.3847224250435829, "train/grad": 0.185625359416008, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.6578955078125, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.6553369140625, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.65168212890625, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.648291015625, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.645355224609375, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.641634521484375, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.637921142578125, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.63433837890625, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.629970703125, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.6260552978515626, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.6225726318359375, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.61829833984375, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.614678955078125, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.6094021606445312, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.6039877319335938, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.5982846069335938, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.5914501953125, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.5831678771972656, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.5704779052734374, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.5514960479736328, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.518393783569336, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.4666777229309082, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.3465617927908897, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.1944902454316616, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.06113052070140838, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.009993197172880173, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.004116269052028656, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0026117810606956482, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0012351757287979127, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0007134348154067994, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0005597750842571259, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.00042671561241149905, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.0003223253786563873, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.00023024603724479674, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.00027629464864730835, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.0002227647602558136, "train/loss_036_lr7.1e+00_wd1.0e+00": 5.356445908546448e-05, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.00020076349377632141, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.00013203546404838562, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.00025805070996284487, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.00012405365705490113, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.010527789890766144, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.69140625, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.69140625, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.69140625, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.69140625, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.69140625, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.69140625, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.69140625, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.033790401732549075, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.033801972940564154, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.033831182359717785, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.03386383763514459, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.03390522273723036, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.03399447699077427, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.03409448585473001, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.034234695341438054, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.03441900952719152, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.03459990022704005, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.03478606907185167, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.035093779773451385, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.03548382923007012, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.036014212970621885, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.0362554039619863, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.03637622521724552, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.03674274063203484, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.03741283264011144, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.03801723369862884, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.03835074952803552, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.039335751053877176, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.03966420232784003, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.036338741267099975, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.02881636229576543, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.015327561970916576, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.00322683299324126, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0013726399890583707, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0008585835805570241, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0004033465291104221, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.00022624435172474477, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.00018509208708564984, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.00014894683112288477, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.00010902461384830531, "train/grad_033_lr4.3e+00_wd1.0e+00": 8.138085222071823e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.00011618733370141854, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0001012991703987609, "train/grad_036_lr7.1e+00_wd1.0e+00": 4.480735459823748e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 8.996505159529989e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 8.006216739914863e-05, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.000133473817753611, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.00011892041575237044, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.007909963893140125, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.6700193285942078, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.6682096123695374, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.6654666662216187, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.6632701754570007, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.6613684892654419, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.6593503355979919, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.6575867533683777, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.6563044786453247, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.6552862524986267, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.6542750000953674, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.6530891060829163, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.6520804166793823, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.6521392464637756, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.6548494696617126, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.660899817943573, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.6694748997688293, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.6810199618339539, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.6902903914451599, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.6830347776412964, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.6674795746803284, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.6892256736755371, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.7428932785987854, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.8843383193016052, "validation/loss_023_lr8.5e-01_wd1.0e+00": 1.1946260929107666, "validation/loss_024_lr1.0e+00_wd1.0e+00": 1.737924337387085, "validation/loss_025_lr1.2e+00_wd1.0e+00": 1.9755502939224243, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.1753506660461426, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.2008204460144043, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.668606758117676, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.596182346343994, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.4017460346221924, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.3369710445404053, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.2489073276519775, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.5782711505889893, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.3529300689697266, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.6592283248901367, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.1922450065612793, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.711843252182007, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.82515287399292, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.6647531986236572, "validation/loss_040_lr1.4e+01_wd1.0e+00": 4.053881645202637, "validation/loss_041_lr1.6e+01_wd1.0e+00": 5.495606899261475, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.6931473016738892, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.5887096774193549, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.5887096774193549, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.5967741935483871, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.5967741935483871, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.6048387096774194, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.6129032258064516, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.6129032258064516, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.6209677419354839, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.6209677419354839, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.6290322580645161, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.6209677419354839, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.6129032258064516, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.6209677419354839, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.6209677419354839, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.6209677419354839, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.6129032258064516, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.5887096774193549, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.5806451612903226, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.6129032258064516, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.6451612903225806, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.6370967741935484, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.6693548387096774, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.6612903225806451, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.6129032258064516, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.6048387096774194, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.6451612903225806, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.6290322580645161, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.6209677419354839, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.6129032258064516, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.5967741935483871, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.6209677419354839, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.5967741935483871, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.6209677419354839, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.6129032258064516, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.6290322580645161, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.6451612903225806, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.5645161290322581, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.5806451612903226, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.5725806451612904, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.5564516129032258, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.5725806451612904, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.5564516129032258, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.43548387096774194, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.43548387096774194, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.43548387096774194, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.43548387096774194, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.43548387096774194, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.43548387096774194, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.43548387096774194, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.4785190071740744, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.4785190071740744, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.4934640522875817, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.4934640522875817, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.5080560278519958, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.5223113964686998, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.5303030303030303, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.5437964774951076, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.5437964774951076, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.5570052811432122, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.5508285163776493, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.5377446411929171, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.5508285163776493, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.5362457229251214, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.5281353736539551, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.5137254901960784, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.4785190071740744, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.46320346320346323, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.5377446411929171, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.6039488966318234, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.6190346145968457, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.6630211440312852, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.6539994685091681, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.6025641025641025, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.5931704050887178, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.6260964912280702, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.6191239316239316, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.6049081418208935, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.6003223207091055, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.5836690840719849, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.607462787095036, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.5860042735042735, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.607462787095036, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.6003223207091055, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.6145945945945945, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.6313513513513513, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.555142173797502, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.5735449735449736, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.5662332519305657, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.5376584638329605, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.5678306043269548, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.5498646953996436, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.30337078651685395, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.30337078651685395, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.30337078651685395, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.30337078651685395, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.30337078651685395, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.30337078651685395, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.30337078651685395, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.5383597883597884, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.5383597883597884, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.5476190476190477, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.5476190476190477, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.5568783068783069, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.5661375661375662, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.5682539682539682, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.5775132275132275, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.5775132275132275, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.5867724867724867, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.5796296296296296, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.5703703703703704, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.5796296296296296, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.5753968253968254, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.5732804232804233, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.564021164021164, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.5383597883597884, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.5291005291005291, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.5703703703703704, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.6137566137566137, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.6193121693121693, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.6626984126984128, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.6534391534391535, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.602116402116402, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.5928571428571429, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.6264550264550265, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.6185185185185185, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.605026455026455, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.6, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.5835978835978836, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.6071428571428572, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.5857142857142856, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.6071428571428572, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.6, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.6142857142857143, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.6306878306878307, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.555026455026455, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.5735449735449736, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.5664021164021165, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.5394179894179894, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.5685185185185185, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.55, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.5, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.5, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.5, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.5, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.5, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.5, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.5, "id_best": 21, "lr_best": 0.00018299999999999998, "wd_best": 0.05, "train/loss_best": 0.4666777229309082, "validation/loss_best": 0.7428932785987854, "validation/acc_best": 0.6693548387096774, "validation/f1_best": 0.6630211440312852, "validation/bacc_best": 0.6626984126984128} +{"epoch": 10, "train/lr": 0.00021091808096876188, "train/loss": 0.36115263916552065, "train/grad": 0.17283011898398398, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.64392822265625, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.64081298828125, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.63603271484375, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.63183349609375, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.627919921875, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.62321533203125, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.618355712890625, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.613486328125, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.6077783203125, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.602293701171875, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.5973065185546875, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.5899822998046875, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.5830697631835937, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.5737420654296875, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.5658175659179687, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.55915771484375, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.5507278442382812, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.5395140075683593, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.5207688903808594, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.49269155502319334, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.4273390293121338, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.32120539784431457, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.18985364377498626, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.07086050555109978, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.01682950958609581, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.004457838982343674, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.002236994504928589, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0015886354446411133, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0008466264605522156, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0005102398991584778, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.000423935204744339, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.0003492218255996704, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.00025309398770332334, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.0001693105697631836, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.00022964924573898315, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.00020105436444282533, "train/loss_036_lr7.1e+00_wd1.0e+00": 5.577757954597473e-05, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.00019219473004341125, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.00014568477869033813, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.0002628278732299805, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.0001521618664264679, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.774404525756836e-05, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.69140625, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.69140625, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.69140625, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.69140625, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.69140625, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.69140625, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.69140625, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.03404827915132046, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.03405057868454606, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.034075664496049284, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.0341175145143643, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.034165647714398804, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.03425365938106552, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.034384151455014944, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.03451476989779621, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.034712442629970613, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.03488913146778941, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.03501191172748804, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.035135990418493745, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.03522275864612311, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.035274403425864874, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.03531339744571596, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.035395212527364495, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.03544185495469719, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.03534323079045862, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.035298705650493506, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.03542245712131262, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.0362600443745032, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.03530589062254876, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.029820077503100038, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.016961722408887, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.005373443544376641, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0015798735872522228, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0008096618163835955, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.000565923603498959, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.00028753978562235717, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.00018222685206637835, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.00015057472145599604, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0001226009574747877, "train/grad_032_lr3.7e+00_wd1.0e+00": 9.242881626050803e-05, "train/grad_033_lr4.3e+00_wd1.0e+00": 7.359565478509466e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 9.624480635920918e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 9.028424482721676e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 4.188600877220949e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 8.612197364072926e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 8.76416410713432e-05, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.00012327544196068628, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.00011561115326941263, "train/grad_041_lr1.6e+01_wd1.0e+00": 5.1202214284079286e-05, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.6682663559913635, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.6662054657936096, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.6631295084953308, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.6604273319244385, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.6581485271453857, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.6554703712463379, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.653034508228302, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.6509276628494263, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.6491064429283142, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.648306131362915, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.6484566330909729, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.64900803565979, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.6486570239067078, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.6472252011299133, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.6470615267753601, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.6462404131889343, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.6413010954856873, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.6308537125587463, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.6212473511695862, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.6345173120498657, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.6958919167518616, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.8084819912910461, "validation/loss_022_lr7.2e-01_wd1.0e+00": 1.047096610069275, "validation/loss_023_lr8.5e-01_wd1.0e+00": 1.4450480937957764, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.0038504600524902, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.106086492538452, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.285224437713623, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.2807250022888184, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.745643138885498, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.640820026397705, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.446200370788574, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.370922803878784, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.270902633666992, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.5901834964752197, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.374715805053711, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.6559691429138184, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.0606272220611572, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.6760671138763428, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.6872167587280273, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.5784833431243896, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.7453384399414062, "validation/loss_041_lr1.6e+01_wd1.0e+00": 4.944741249084473, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.6931473016738892, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.5725806451612904, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.5806451612903226, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.5967741935483871, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.5967741935483871, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.5967741935483871, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.6290322580645161, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.6209677419354839, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.6129032258064516, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.6209677419354839, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.6129032258064516, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.6129032258064516, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.6048387096774194, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.6209677419354839, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.6129032258064516, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.6129032258064516, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.6129032258064516, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.6209677419354839, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.6451612903225806, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.6451612903225806, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.6612903225806451, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.5967741935483871, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.6290322580645161, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.6370967741935484, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.6129032258064516, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.6209677419354839, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.6370967741935484, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.6290322580645161, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.6209677419354839, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.6048387096774194, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.5887096774193549, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.6209677419354839, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.5967741935483871, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.6209677419354839, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.6209677419354839, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.6370967741935484, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.6451612903225806, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.5806451612903226, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.5806451612903226, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.5645161290322581, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.5564516129032258, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.5483870967741935, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.5645161290322581, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.43548387096774194, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.43548387096774194, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.43548387096774194, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.43548387096774194, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.43548387096774194, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.43548387096774194, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.43548387096774194, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.4678973362480771, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.48250401284109146, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.5107323232323233, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.5107323232323233, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.5257037943696451, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.5636474908200735, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.5573782942203995, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.551131221719457, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.5573782942203995, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.5446756425948592, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.5377446411929171, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.5243835616438356, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.5362457229251214, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.5223113964686998, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.5303030303030303, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.5303030303030303, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.5437964774951076, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.599177196591243, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.6260964912280702, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.6539994685091681, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.58994708994709, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.6119727891156463, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.6160990712074303, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.5978378378378378, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.6049081418208935, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.6190346145968457, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.6191239316239316, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.607462787095036, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.5931704050887178, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.5740553647201454, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.607462787095036, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.5860042735042735, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.607462787095036, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.607462787095036, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.6217205613178767, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.6313513513513513, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.5694444444444444, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.5735449735449736, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.5571428571428572, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.5376584638329605, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.5407407407407407, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.555142173797502, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.30337078651685395, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.30337078651685395, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.30337078651685395, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.30337078651685395, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.30337078651685395, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.30337078651685395, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.30337078651685395, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.5240740740740741, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.5333333333333333, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.5518518518518518, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.5518518518518518, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.5560846560846561, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.5888888888888889, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.5817460317460317, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.5746031746031746, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.5817460317460317, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.5724867724867725, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.5703703703703704, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.5611111111111111, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.5753968253968254, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.5661375661375662, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.5682539682539682, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.5682539682539682, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.5775132275132275, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.6116402116402117, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.6264550264550265, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.6534391534391535, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.58994708994709, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.6121693121693121, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.6171957671957672, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.5978835978835979, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.605026455026455, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.6193121693121693, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.6185185185185185, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.6071428571428572, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.5928571428571429, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.5743386243386244, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.6071428571428572, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.5857142857142856, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.6071428571428572, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.6071428571428572, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.6214285714285714, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.6306878306878307, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.5693121693121693, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.5735449735449736, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.5571428571428572, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.5394179894179894, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.5407407407407407, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.555026455026455, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.5, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.5, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.5, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.5, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.5, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.5, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.5, "id_best": 19, "lr_best": 0.00013199999999999998, "wd_best": 0.05, "train/loss_best": 0.49269155502319334, "validation/loss_best": 0.6345173120498657, "validation/acc_best": 0.6612903225806451, "validation/f1_best": 0.6539994685091681, "validation/bacc_best": 0.6534391534391535} +{"epoch": 11, "train/lr": 0.00018113997589164516, "train/loss": 0.3561952555924654, "train/grad": 0.1870183366164565, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.64734619140625, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.64419677734375, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.63917724609375, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.634837646484375, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.63089111328125, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.625899658203125, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.62092529296875, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.61589111328125, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.609825439453125, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.604029541015625, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.5988055419921875, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.5917974853515625, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.5857635498046875, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.5777053833007812, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.5704867553710937, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.5634649658203125, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.5533872985839844, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.5377890014648438, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.5108167648315429, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.4711207675933838, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.3797535538673401, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.24530208244919777, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.10961448624730111, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.027999073415994644, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.007852468490600586, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.0029162357747554777, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.0016618536412715912, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0011571675539016723, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0006457407772541046, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.00038767829537391665, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.00033659398555755613, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.00028382718563079834, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.00020636096596717834, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.000163775235414505, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.00020089179277420045, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.000202639102935791, "train/loss_036_lr7.1e+00_wd1.0e+00": 5.010917782783508e-05, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.00018235579133033753, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.00018848255276679993, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.00024207606911659242, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.00016435325145721435, "train/loss_041_lr1.6e+01_wd1.0e+00": 5.480244755744934e-05, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.69140625, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.69140625, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.69140625, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.69140625, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.69140625, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.69140625, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.69140625, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.03683193820761517, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.03679982211207971, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.03679018581053242, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.0367974818404764, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.03682392601389438, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.03688793700188398, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.036994292051531374, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.03709424450527877, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.037214542394503954, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.03735092642717063, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.03745091917924583, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.03764103565830737, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.037857462298125026, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.038184093944728374, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.038545547805260864, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.0389343633223325, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.039333799320738765, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.039619908998720345, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.03983001682907343, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.04047699125483632, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.040446594855748114, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.03524848961038515, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.023983364227460696, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.009141873648623004, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0027172642975347118, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0010859305775375106, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0006145026641024742, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0004410497572825989, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.00023062735162056924, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.00014950469609175342, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.00012503792717325269, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.00010599973712487554, "train/grad_032_lr3.7e+00_wd1.0e+00": 7.993024382358272e-05, "train/grad_033_lr4.3e+00_wd1.0e+00": 6.52391307767175e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 8.63500718639898e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 8.031048121210915e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 4.416271231711733e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 7.854917118265802e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 9.386823367663055e-05, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.00011811843179202696, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0001221833105697101, "train/grad_041_lr1.6e+01_wd1.0e+00": 6.485968733096037e-05, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.6684916615486145, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.6665825843811035, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.6638887524604797, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.6616991758346558, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.6599175333976746, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.6579208970069885, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.6565338373184204, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.6557022929191589, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.6562830209732056, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.6579801440238953, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.6597699522972107, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.6616477966308594, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.6630536913871765, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.664431631565094, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.6615663170814514, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.6532658338546753, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.6412727236747742, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.6349970698356628, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.6389075517654419, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.6724034547805786, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.7750945687294006, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.9436900019645691, "validation/loss_022_lr7.2e-01_wd1.0e+00": 1.2104475498199463, "validation/loss_023_lr8.5e-01_wd1.0e+00": 1.6626015901565552, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.1726064682006836, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.1837408542633057, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.3685991764068604, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.349672555923462, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.810908079147339, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.671764850616455, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.4821441173553467, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.3950393199920654, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.2945635318756104, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.600706100463867, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.3799712657928467, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.6479880809783936, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.955604076385498, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.652122974395752, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.5953752994537354, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.5060038566589355, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.5288023948669434, "validation/loss_041_lr1.6e+01_wd1.0e+00": 4.531848430633545, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.6931473016738892, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.5806451612903226, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.5806451612903226, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.5725806451612904, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.5725806451612904, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.5806451612903226, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.5806451612903226, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.5806451612903226, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.5806451612903226, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.5887096774193549, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.5967741935483871, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.5967741935483871, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.6048387096774194, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.5806451612903226, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.5645161290322581, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.5725806451612904, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.5967741935483871, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.6209677419354839, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.6451612903225806, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.6774193548387096, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.6693548387096774, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.6290322580645161, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.6129032258064516, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.6370967741935484, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.6129032258064516, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.6129032258064516, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.6451612903225806, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.6129032258064516, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.5887096774193549, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.6048387096774194, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.5967741935483871, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.6290322580645161, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.5967741935483871, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.6209677419354839, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.6290322580645161, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.6290322580645161, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.6451612903225806, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.5806451612903226, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.5967741935483871, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.5564516129032258, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.5564516129032258, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.5483870967741935, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.5645161290322581, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.43548387096774194, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.43548387096774194, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.43548387096774194, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.43548387096774194, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.43548387096774194, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.43548387096774194, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.43548387096774194, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.5263003232441963, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.5263003232441963, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.5308060255586493, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.5355805243445693, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.5545730864879801, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.5613605442176871, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.5670158474348643, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.5694444444444444, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.5826018084614877, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.5950888192267503, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.5958279009126467, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.6046072753302532, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.5806451612903226, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.5634941329856584, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.5718845677806006, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.5966692688004163, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.6197559861681998, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.6375232527238905, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.6648648648648648, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.6553454003118433, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.6059684995855208, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.5951020408163266, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.6241664982824813, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.6003223207091055, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.6003223207091055, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.6313513513513513, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.6045708211533352, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.5808311791608669, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.5931704050887178, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.5860042735042735, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.6169755573462261, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.5860042735042735, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.607462787095036, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.6169755573462261, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.6145945945945945, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.6313513513513513, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.5694444444444444, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.58994708994709, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.5498646953996436, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.5376584638329605, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.5407407407407407, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.5503626107977437, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.30337078651685395, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.30337078651685395, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.30337078651685395, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.30337078651685395, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.30337078651685395, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.30337078651685395, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.30337078651685395, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.5460317460317461, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.5460317460317461, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.5431216931216931, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.5452380952380952, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.5587301587301587, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.5629629629629629, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.5671957671957671, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.5693121693121693, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.5828042328042329, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.5984126984126985, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.6005291005291005, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.611904761904762, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.5904761904761904, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.5804232804232804, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.5875661375661376, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.6047619047619047, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.624074074074074, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.6370370370370371, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.6634920634920636, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.6542328042328043, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.607936507936508, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.5957671957671957, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.6235449735449735, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.6, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.6, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.6306878306878307, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.6042328042328042, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.5806878306878307, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.5928571428571429, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.5857142857142856, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.6164021164021164, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.5857142857142856, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.6071428571428572, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.6164021164021164, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.6142857142857143, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.6306878306878307, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.5693121693121693, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.58994708994709, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.55, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.5394179894179894, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.5407407407407407, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.5507936507936508, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.5, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.5, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.5, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.5, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.5, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.5, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.5, "id_best": 18, "lr_best": 0.00011399999999999999, "wd_best": 0.05, "train/loss_best": 0.5108167648315429, "validation/loss_best": 0.6389075517654419, "validation/acc_best": 0.6774193548387096, "validation/f1_best": 0.6648648648648648, "validation/bacc_best": 0.6634920634920636} +{"epoch": 12, "train/lr": 0.0001499999999999999, "train/loss": 0.3539060977101326, "train/grad": 0.16876196658238768, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.651923828125, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.64825927734375, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.64290283203125, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.63835693359375, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.6342822265625, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.629442138671875, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.62465576171875, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.620128173828125, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.6150128173828125, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.6101800537109375, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.6058026123046875, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.5993731689453125, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.5931988525390625, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.5840347290039063, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.575279541015625, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.5672590637207031, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.5562815856933594, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.5377449798583984, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.5061046600341796, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.44882807254791257, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.3290290778875351, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.18637613967061042, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.06760152623057365, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.01626947596669197, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.005364474058151245, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.0023808223009109497, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.001339842528104782, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0010127364099025726, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.000540996640920639, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0003798598051071167, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0003075282275676727, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.00025497868657112124, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.00019828125834465027, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.00016420185565948486, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.00020219802856445313, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.00016324222087860107, "train/loss_036_lr7.1e+00_wd1.0e+00": 5.403369665145874e-05, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.0001915222406387329, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.00019643962383270264, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.00022818058729171754, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.0001425255835056305, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.00010599270462989807, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.69140625, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.69140625, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.69140625, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.69140625, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.69140625, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.69140625, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.69140625, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.03234658934641629, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.03236556124407798, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.03245409085415304, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.032557855462655425, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.03265992141794413, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.03285566265694797, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.03310054245404899, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.03336485584266484, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.033724468988366424, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.034104591910727323, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.03443435341119766, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.03484910120256245, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.03519754197914153, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.03541195060592145, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.035426450781524184, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.035624581836163995, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.03604342430364341, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.036437494019046425, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.03685079199727625, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.03790985361207277, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.0370916158426553, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.03214950690744445, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.018072783405077644, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.005089977069728775, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0018109564669430255, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0008025960219310946, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0004846131971498835, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.00035104744827549436, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.00019462766331344029, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.00013610389588393447, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.00010777964609587798, "train/grad_031_lr3.1e+00_wd1.0e+00": 9.235066513610946e-05, "train/grad_032_lr3.7e+00_wd1.0e+00": 7.241136974698747e-05, "train/grad_033_lr4.3e+00_wd1.0e+00": 6.008170467339369e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 7.706781118486106e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 7.393262783580213e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 4.4393024449504995e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 7.582041467685485e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 9.569427384917617e-05, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.00011057260896905064, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.00013166378319937167, "train/grad_041_lr1.6e+01_wd1.0e+00": 9.554682280496607e-05, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.666645348072052, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.6645609736442566, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.6615872383117676, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.6590951681137085, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.6569473147392273, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.6543469429016113, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.6518893241882324, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.6494840979576111, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.6468559503555298, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.6444315314292908, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.6425397396087646, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.6403071284294128, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.6389896869659424, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.6396373510360718, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.6432520747184753, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.6461026072502136, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.6477757096290588, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.6504883170127869, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.6589180827140808, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.7034689784049988, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.8030530214309692, "validation/loss_021_lr6.1e-01_wd1.0e+00": 1.0161854028701782, "validation/loss_022_lr7.2e-01_wd1.0e+00": 1.3913612365722656, "validation/loss_023_lr8.5e-01_wd1.0e+00": 1.8120813369750977, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.288036584854126, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.274334192276001, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.4392292499542236, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.4063310623168945, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.8689000606536865, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.7041473388671875, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.5201570987701416, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.422755002975464, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.320662021636963, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.6107821464538574, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.3963370323181152, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.6536996364593506, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.877366304397583, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.6402578353881836, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.538281202316284, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.473241090774536, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.3861355781555176, "validation/loss_041_lr1.6e+01_wd1.0e+00": 4.23991060256958, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.6931473016738892, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.5806451612903226, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.5887096774193549, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.5967741935483871, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.5887096774193549, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.5967741935483871, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.5967741935483871, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.5967741935483871, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.6209677419354839, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.6290322580645161, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.6129032258064516, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.6290322580645161, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.6209677419354839, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.6129032258064516, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.6290322580645161, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.6129032258064516, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.6129032258064516, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.6290322580645161, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.6290322580645161, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.6532258064516129, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.6532258064516129, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.6048387096774194, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.6129032258064516, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.6209677419354839, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.6129032258064516, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.6048387096774194, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.6451612903225806, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.6209677419354839, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.5967741935483871, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.6048387096774194, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.5887096774193549, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.6209677419354839, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.5967741935483871, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.6209677419354839, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.6209677419354839, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.6370967741935484, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.6451612903225806, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.5887096774193549, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.5967741935483871, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.5564516129032258, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.5483870967741935, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.5564516129032258, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.5725806451612904, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.43548387096774194, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.43548387096774194, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.43548387096774194, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.43548387096774194, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.43548387096774194, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.43548387096774194, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.43548387096774194, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.4911616161616162, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.5049706457925636, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.518484001242622, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.5263276159089207, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.544519541580958, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.544519541580958, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.5549813379270744, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.5839223245520098, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.5905828308929084, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.5772727272727273, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.5905828308929084, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.5793576326236016, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.5627387599177196, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.575595238095238, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.5446756425948592, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.5377446411929171, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.5698340874811463, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.575595238095238, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.6193331905475834, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.626793588577028, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.5931704050887178, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.5978378378378378, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.5956989247311828, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.5951020408163266, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.5907590759075907, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.6313513513513513, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.6118548118548119, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.5860042735042735, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.5931704050887178, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.5740553647201454, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.6049081418208935, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.5860042735042735, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.607462787095036, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.607462787095036, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.6217205613178767, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.6313513513513513, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.5765651155005022, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.58994708994709, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.5498646953996436, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.5308108108108108, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.5498646953996436, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.5599598259122867, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.30337078651685395, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.30337078651685395, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.30337078651685395, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.30337078651685395, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.30337078651685395, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.30337078651685395, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.30337078651685395, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.5354497354497354, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.5447089947089947, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.553968253968254, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.551058201058201, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.5624338624338625, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.5624338624338625, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.5666666666666667, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.5923280423280424, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.5994708994708995, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.5851851851851853, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.5994708994708995, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.5902116402116402, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.5788359788359788, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.5931216931216932, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.5724867724867725, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.5703703703703704, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.591005291005291, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.5931216931216932, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.6251322751322751, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.6293650793650793, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.5928571428571429, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.5978835978835979, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.5986772486772487, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.5957671957671957, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.5907407407407407, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.6306878306878307, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.6113756613756614, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.5857142857142856, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.5928571428571429, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.5743386243386244, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.605026455026455, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.5857142857142856, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.6071428571428572, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.6071428571428572, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.6214285714285714, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.6306878306878307, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.5764550264550264, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.58994708994709, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.55, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.5322751322751322, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.55, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.56005291005291, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.5, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.5, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.5, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.5, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.5, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.5, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.5, "id_best": 25, "lr_best": 0.00035999999999999997, "wd_best": 0.05, "train/loss_best": 0.0023808223009109497, "validation/loss_best": 2.274334192276001, "validation/acc_best": 0.6451612903225806, "validation/f1_best": 0.6313513513513513, "validation/bacc_best": 0.6306878306878307} +{"epoch": 13, "train/lr": 0.00011886002410835478, "train/loss": 0.3492655545473099, "train/grad": 0.16797535210847855, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.6501953125, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.64672607421875, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.6416259765625, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.637047119140625, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.63295654296875, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.627947998046875, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.62290771484375, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.617852783203125, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.61201904296875, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.6064593505859375, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.6013995361328125, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.5943511962890625, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.5880560302734374, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.579169921875, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.5698854064941407, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.5604055786132812, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.546730728149414, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.5245087432861328, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.4875506591796875, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.42755173206329344, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.29403557658195495, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.1471235392987728, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.037362172156572344, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.0096516352891922, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.003944225013256073, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.001845761388540268, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.0011228826642036439, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0008162003755569458, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0004871430993080139, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0003050540387630463, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0002796438336372376, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.0002555815875530243, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.00018190518021583558, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.00014974594116210938, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.00019227489829063416, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.00015637084841728212, "train/loss_036_lr7.1e+00_wd1.0e+00": 6.241813302040101e-05, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.00016753867268562317, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.00017033860087394714, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.00021253973245620726, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.00020229533314704894, "train/loss_041_lr1.6e+01_wd1.0e+00": 9.650558233261109e-05, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.69140625, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.69140625, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.69140625, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.69140625, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.69140625, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.69140625, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.69140625, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.03257642517797649, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.032580590583384035, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.032618325091898444, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.03266184363979846, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.03272857354488224, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.03284790143836289, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.03298528837505728, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.033154179733246567, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.03339797060471028, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.03367174131330103, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.03395836712792516, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.03438862707000226, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.03486484677065164, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.03553654063958675, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.03605636802967638, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.03641238891519606, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.03679958088789135, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.037405250705778596, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.03788051466923207, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.03814841551706195, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.03613713269121945, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.029622133076190948, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.011862021728884429, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0034178551788500043, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.001443520916363923, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.000704061117139645, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0004294226265483303, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.00030927472689654676, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0001688944000761694, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.00012091977740965377, "train/grad_030_lr2.7e+00_wd1.0e+00": 9.847090002040203e-05, "train/grad_031_lr3.1e+00_wd1.0e+00": 8.377988924621605e-05, "train/grad_032_lr3.7e+00_wd1.0e+00": 6.625993718444079e-05, "train/grad_033_lr4.3e+00_wd1.0e+00": 5.5969222205476396e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 7.106276917511423e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 7.057693406750331e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 4.4769123515493445e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 7.121542529148428e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 8.972512682930755e-05, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0001045194260268545, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.00012918265140626772, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0001128792083297725, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.6661133170127869, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.6640477776527405, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.6610823273658752, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.6585846543312073, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.6564629077911377, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.6538925766944885, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.6514157056808472, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.6491255164146423, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.646480143070221, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.6441115736961365, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.6420140862464905, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.6394614577293396, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.6373921632766724, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.6350671052932739, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.6336737275123596, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.6331149339675903, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.6339843273162842, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.6379172801971436, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.6580621600151062, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.7329257726669312, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.8703480362892151, "validation/loss_021_lr6.1e-01_wd1.0e+00": 1.1275343894958496, "validation/loss_022_lr7.2e-01_wd1.0e+00": 1.5013420581817627, "validation/loss_023_lr8.5e-01_wd1.0e+00": 1.9014256000518799, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.37300705909729, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.330615520477295, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.4821877479553223, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.4466493129730225, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.907083034515381, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.7292943000793457, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.5495212078094482, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.4427905082702637, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.3367180824279785, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.621843099594116, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.408202886581421, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.6585915088653564, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.81642746925354, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.63877272605896, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.5050790309906006, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.4539568424224854, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.288947820663452, "validation/loss_041_lr1.6e+01_wd1.0e+00": 4.047252655029297, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.6931473016738892, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.5887096774193549, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.5967741935483871, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.6048387096774194, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.5967741935483871, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.5967741935483871, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.5967741935483871, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.6048387096774194, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.6129032258064516, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.5967741935483871, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.5967741935483871, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.6048387096774194, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.6048387096774194, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.6290322580645161, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.6451612903225806, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.6451612903225806, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.6451612903225806, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.6532258064516129, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.6370967741935484, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.6451612903225806, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.6370967741935484, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.6129032258064516, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.6048387096774194, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.6048387096774194, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.6209677419354839, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.6048387096774194, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.6451612903225806, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.6209677419354839, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.6048387096774194, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.6048387096774194, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.5887096774193549, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.6209677419354839, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.5967741935483871, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.6209677419354839, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.6129032258064516, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.6370967741935484, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.6451612903225806, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.5887096774193549, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.5967741935483871, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.5564516129032258, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.5483870967741935, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.5645161290322581, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.5725806451612904, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.43548387096774194, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.43548387096774194, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.43548387096774194, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.43548387096774194, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.43548387096774194, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.43548387096774194, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.43548387096774194, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.4967772738123657, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.5107323232323233, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.5243835616438356, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.5324283559577677, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.5386904761904762, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.544519541580958, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.5563344286235852, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.5772727272727273, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.5639943741209563, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.5680044593088072, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.578494623655914, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.578494623655914, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.6091008771929824, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.6231003039513678, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.6231003039513678, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.6260964912280702, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.6359664095036526, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.6190346145968457, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.6198439241917503, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.6129032258064516, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.588836695219674, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.5819745442036464, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.5819745442036464, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.607462787095036, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.5907590759075907, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.6313513513513513, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.6118548118548119, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.5931704050887178, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.5931704050887178, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.5765651155005022, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.6049081418208935, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.5860042735042735, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.607462787095036, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.5978378378378378, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.6217205613178767, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.6313513513513513, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.5765651155005022, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.58994708994709, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.5498646953996436, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.5308108108108108, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.5588932806324111, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.5623043623043623, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.30337078651685395, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.30337078651685395, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.30337078651685395, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.30337078651685395, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.30337078651685395, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.30337078651685395, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.30337078651685395, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.5425925925925926, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.5518518518518518, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.5611111111111111, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.5582010582010581, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.5603174603174603, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.5624338624338625, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.5716931216931217, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.5851851851851853, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.5708994708994709, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.573015873015873, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.5822751322751323, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.5822751322751323, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.6100529100529101, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.6243386243386243, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.6243386243386243, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.6264550264550265, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.6357142857142857, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.6193121693121693, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.6222222222222222, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.6150793650793651, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.5915343915343916, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.5843915343915345, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.5843915343915345, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.6071428571428572, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.5907407407407407, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.6306878306878307, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.6113756613756614, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.5928571428571429, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.5928571428571429, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.5764550264550264, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.605026455026455, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.5857142857142856, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.6071428571428572, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.5978835978835979, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.6214285714285714, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.6306878306878307, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.5764550264550264, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.58994708994709, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.55, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.5322751322751322, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.5592592592592592, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.5621693121693122, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.5, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.5, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.5, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.5, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.5, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.5, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.5, "id_best": 16, "lr_best": 8.1e-05, "wd_best": 0.05, "train/loss_best": 0.546730728149414, "validation/loss_best": 0.6339843273162842, "validation/acc_best": 0.6532258064516129, "validation/f1_best": 0.6359664095036526, "validation/bacc_best": 0.6357142857142857} +{"epoch": 14, "train/lr": 8.9081919031238e-05, "train/loss": 0.3506961362808943, "train/grad": 0.16859707536175847, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.658994140625, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.6559716796875, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.65134765625, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.64739013671875, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.6439794921875, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.639698486328125, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.63532958984375, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.631019287109375, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.626011962890625, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.6209295654296875, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.61635009765625, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.6095745849609375, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.6031182861328125, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.5933413696289063, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.5835504150390625, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.5729542541503906, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.5560677337646485, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.5266746520996094, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.47953248500823975, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.3940799105167389, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.2425983476638794, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.11068806931376457, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.02789973944425583, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.0077542953193187715, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.0032580694556236267, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.0015682244300842284, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.0010085020959377288, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0007687115669250488, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.00043734833598136903, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0002875395119190216, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.000246361643075943, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.00021691888570785523, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.0001592247188091278, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.0001374751329421997, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.00014773204922676085, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.00016210585832595825, "train/loss_036_lr7.1e+00_wd1.0e+00": 7.179215550422669e-05, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.00016049206256866456, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.00020284801721572875, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.0002377103269100189, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.00019839614629745483, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.00014165043830871582, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.69140625, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.69140625, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.69140625, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.69140625, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.69140625, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.69140625, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.69140625, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.03424538987223059, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.03420432982966304, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.03418026925530285, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.03416155017912388, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.03417572770733386, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.03421627309639007, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.03426988271996379, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.034345837314613166, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.03445529541466385, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.03458480566740036, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.034721630630083385, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.03493944426532835, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.03517423911485821, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.035566629045642915, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.03607055867556483, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.03658938284032047, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.03722222521435469, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.03762824520468712, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.037883020918816325, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.037456473568454385, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.03319304675096646, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.02438135242671706, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.00854902642662637, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0027261708374135196, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0011755488006747327, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0005548531936801737, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0003673842573334696, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0002767833733378211, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.00015265928042936138, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.00010931239057754283, "train/grad_030_lr2.7e+00_wd1.0e+00": 8.922114921915636e-05, "train/grad_031_lr3.1e+00_wd1.0e+00": 7.82271698653858e-05, "train/grad_032_lr3.7e+00_wd1.0e+00": 6.230238205716888e-05, "train/grad_033_lr4.3e+00_wd1.0e+00": 5.265416639531395e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 6.659235526967677e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 6.5057195602094e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 4.621221475900939e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 6.447890477829787e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 8.667580822930177e-05, "train/grad_039_lr1.2e+01_wd1.0e+00": 9.763343020040338e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.00012737986371575972, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.00012349439056229096, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.6657506823539734, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.6636687517166138, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.6607589721679688, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.6583564877510071, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.6561895608901978, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.653710663318634, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.6513276100158691, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.6489241719245911, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.6461954712867737, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.6437806487083435, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.6417465209960938, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.639388382434845, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.6377807855606079, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.6365262269973755, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.6360124945640564, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.6352363228797913, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.635273814201355, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.6408877968788147, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.6661893129348755, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.7301955819129944, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.8830755352973938, "validation/loss_021_lr6.1e-01_wd1.0e+00": 1.1717033386230469, "validation/loss_022_lr7.2e-01_wd1.0e+00": 1.5667738914489746, "validation/loss_023_lr8.5e-01_wd1.0e+00": 1.981155276298523, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.435580253601074, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.3685879707336426, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.519545316696167, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.4782755374908447, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.934237003326416, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.749197006225586, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.5697295665740967, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.4562556743621826, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.3493778705596924, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.633841037750244, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.4196321964263916, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.663661003112793, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.7795205116271973, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.6373345851898193, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.4841504096984863, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.4475882053375244, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.230238199234009, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.922332763671875, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.6931473016738892, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.5806451612903226, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.5967741935483871, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.5967741935483871, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.6048387096774194, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.5967741935483871, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.6129032258064516, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.6048387096774194, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.6129032258064516, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.6290322580645161, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.6370967741935484, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.6290322580645161, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.6129032258064516, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.6048387096774194, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.6290322580645161, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.6209677419354839, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.6290322580645161, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.6290322580645161, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.6209677419354839, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.6290322580645161, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.5967741935483871, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.6209677419354839, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.5887096774193549, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.5887096774193549, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.6129032258064516, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.6048387096774194, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.6451612903225806, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.6209677419354839, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.6048387096774194, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.6048387096774194, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.5887096774193549, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.6209677419354839, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.5967741935483871, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.6209677419354839, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.6129032258064516, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.6370967741935484, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.6370967741935484, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.5887096774193549, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.5887096774193549, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.5564516129032258, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.5564516129032258, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.5645161290322581, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.5806451612903226, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.43548387096774194, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.43548387096774194, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.43548387096774194, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.43548387096774194, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.43548387096774194, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.43548387096774194, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.43548387096774194, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.48250401284109146, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.5107323232323233, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.5107323232323233, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.5385433280170122, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.5324283559577677, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.5571428571428572, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.5508242773711836, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.5627387599177196, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.5905828308929084, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.6016277575497966, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.5948863636363637, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.5727820844099913, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.566216891554223, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.5905828308929084, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.5793576326236016, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.5905828308929084, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.6059684995855208, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.6118548118548119, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.6210470369386127, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.58994708994709, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.6118548118548119, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.5649122807017544, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.5682392298764252, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.5951020408163266, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.5907590759075907, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.6313513513513513, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.6118548118548119, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.5931704050887178, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.5931704050887178, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.5765651155005022, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.6049081418208935, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.5860042735042735, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.607462787095036, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.5978378378378378, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.6217205613178767, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.6217205613178767, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.5765651155005022, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.5808311791608669, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.5498646953996436, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.5376584638329605, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.5588932806324111, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.5694444444444444, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.30337078651685395, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.30337078651685395, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.30337078651685395, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.30337078651685395, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.30337078651685395, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.30337078651685395, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.30337078651685395, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.5333333333333333, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.5518518518518518, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.5518518518518518, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.5653439153439154, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.5582010582010581, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.5767195767195767, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.5695767195767196, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.5788359788359788, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.5994708994708995, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.6087301587301588, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.6015873015873016, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.5830687830687831, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.575925925925926, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.5994708994708995, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.5902116402116402, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.5994708994708995, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.607936507936508, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.6113756613756614, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.6206349206349207, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.58994708994709, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.6113756613756614, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.5679894179894179, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.5701058201058201, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.5957671957671957, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.5907407407407407, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.6306878306878307, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.6113756613756614, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.5928571428571429, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.5928571428571429, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.5764550264550264, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.605026455026455, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.5857142857142856, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.6071428571428572, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.5978835978835979, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.6214285714285714, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.6214285714285714, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.5764550264550264, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.5806878306878307, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.55, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.5394179894179894, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.5592592592592592, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.5693121693121693, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.5, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.5, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.5, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.5, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.5, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.5, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.5, "id_best": 25, "lr_best": 0.00035999999999999997, "wd_best": 0.05, "train/loss_best": 0.0015682244300842284, "validation/loss_best": 2.3685879707336426, "validation/acc_best": 0.6451612903225806, "validation/f1_best": 0.6313513513513513, "validation/bacc_best": 0.6306878306878307} +{"epoch": 15, "train/lr": 6.196799573888289e-05, "train/loss": 0.34852899827063083, "train/grad": 0.16606945736333728, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.66102783203125, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.6582373046875, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.65387451171875, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.6500390625, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.646497802734375, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.64215576171875, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.637657470703125, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.632884521484375, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.6271734619140625, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.621341552734375, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.6159490966796874, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.6079898071289063, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.6005078125, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.589266357421875, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.5778858947753907, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.5658747863769531, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.547282943725586, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.5156240844726563, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.465679874420166, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.3731033909320831, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.2231839720904827, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.08931621968746185, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.020914062559604644, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.006376233100891113, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.002773105651140213, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.0013141609728336335, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.0008331714570522309, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0006795363128185273, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0003950124979019165, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0002592933177947998, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.00021806031465530396, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.00019472852349281311, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.00015328720211982727, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.00013977393507957458, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.00017012596130371092, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.00013228088617324828, "train/loss_036_lr7.1e+00_wd1.0e+00": 6.650179624557495e-05, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.00016155868768692017, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.00016360342502593994, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.00021977588534355163, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.00020274803042411805, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.0001570741832256317, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.69140625, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.69140625, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.69140625, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.69140625, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.69140625, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.69140625, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.69140625, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.03377035590121522, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.03375410114182159, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.03377139570889995, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.033786751525476576, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.03382731078891084, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.033905877466313544, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.03400865587638691, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.03410854910500347, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.034249870863277465, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.03444118137005717, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.03461478118319064, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.03491176642477512, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.035202298066578805, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.03557203623931855, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.03596607437357306, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.036459725904278456, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.0371732778288424, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.037945304922759535, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.03809617012739182, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.03726936621125788, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.032453738555777815, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.021062176446430384, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.00688960769562982, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.002232407203846378, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0010177548608044163, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0005172798722924199, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0003236763445966062, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0002442435392731568, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.00013848471842720756, "train/grad_029_lr2.3e+00_wd1.0e+00": 9.90049983283825e-05, "train/grad_030_lr2.7e+00_wd1.0e+00": 8.172962317075872e-05, "train/grad_031_lr3.1e+00_wd1.0e+00": 7.246781045068929e-05, "train/grad_032_lr3.7e+00_wd1.0e+00": 5.910053883781074e-05, "train/grad_033_lr4.3e+00_wd1.0e+00": 5.0788909575203434e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 6.357217772347212e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 6.144951403712184e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 4.352676574285397e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 6.311753923000651e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 8.21626297624789e-05, "train/grad_039_lr1.2e+01_wd1.0e+00": 9.155257525890192e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0001240805535974232, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.00012455698250048996, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.665480375289917, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.6633467674255371, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.6603754162788391, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.6579304933547974, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.6557322144508362, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.6532110571861267, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.6506980061531067, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.6483010649681091, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.6456230878829956, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.6432723999023438, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.6412798166275024, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.6387747526168823, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.636881947517395, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.6347270011901855, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.633871853351593, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.6337082386016846, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.6347067356109619, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.640627384185791, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.6686914563179016, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.7445876002311707, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.9242919683456421, "validation/loss_021_lr6.1e-01_wd1.0e+00": 1.2308235168457031, "validation/loss_022_lr7.2e-01_wd1.0e+00": 1.6256080865859985, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.0113484859466553, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.4680607318878174, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.395374059677124, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.544015407562256, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.4964659214019775, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.9517276287078857, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.763934373855591, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.581785202026367, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.469167947769165, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.3597121238708496, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.638641834259033, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.422316074371338, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.663536548614502, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.750148057937622, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.6428892612457275, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.4735727310180664, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.4439525604248047, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.1935336589813232, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.8453023433685303, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.6931473016738892, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.5806451612903226, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.5887096774193549, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.5806451612903226, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.5887096774193549, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.5725806451612904, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.5967741935483871, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.5967741935483871, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.5887096774193549, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.6048387096774194, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.5967741935483871, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.6048387096774194, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.6048387096774194, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.6290322580645161, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.6451612903225806, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.6451612903225806, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.6451612903225806, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.6370967741935484, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.6532258064516129, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.6532258064516129, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.6209677419354839, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.6209677419354839, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.6048387096774194, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.5967741935483871, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.6209677419354839, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.6048387096774194, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.6451612903225806, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.6209677419354839, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.5806451612903226, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.6129032258064516, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.5887096774193549, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.6209677419354839, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.5967741935483871, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.6209677419354839, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.6048387096774194, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.6370967741935484, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.6451612903225806, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.5887096774193549, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.5887096774193549, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.5564516129032258, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.5483870967741935, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.5725806451612904, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.5725806451612904, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.43548387096774194, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.43548387096774194, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.43548387096774194, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.43548387096774194, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.43548387096774194, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.43548387096774194, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.43548387096774194, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.4992233612923268, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.5126011560693642, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.5202380952380952, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.5382256297918948, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.5256586070010827, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.5596590909090909, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.5639943741209563, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.5612903225806452, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.578494623655914, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.571704890853827, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.578494623655914, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.578494623655914, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.6091008771929824, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.6260964912280702, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.6313513513513513, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.6336287939833467, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.626380984265149, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.6408702094699266, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.6408702094699266, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.607462787095036, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.6049081418208935, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.578494623655914, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.575109649122807, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.6049081418208935, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.5907590759075907, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.6313513513513513, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.6118548118548119, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.5716183895827798, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.6025641025641025, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.5765651155005022, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.6049081418208935, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.5860042735042735, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.607462787095036, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.5907590759075907, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.6217205613178767, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.6313513513513513, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.5765651155005022, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.5808311791608669, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.5498646953996436, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.5308108108108108, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.5662332519305657, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.5623043623043623, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.30337078651685395, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.30337078651685395, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.30337078651685395, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.30337078651685395, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.30337078651685395, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.30337078651685395, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.30337078651685395, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.5375661375661376, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.5468253968253969, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.5439153439153439, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.5552910052910053, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.5410052910052909, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.5687830687830688, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.5708994708994709, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.5658730158730159, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.5822751322751323, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.5751322751322752, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.5822751322751323, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.5822751322751323, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.6100529100529101, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.6264550264550265, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.6306878306878307, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.6328042328042328, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.6256613756613757, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.63994708994709, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.63994708994709, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.6071428571428572, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.605026455026455, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.5822751322751323, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.5772486772486772, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.605026455026455, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.5907407407407407, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.6306878306878307, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.6113756613756614, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.5714285714285714, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.602116402116402, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.5764550264550264, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.605026455026455, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.5857142857142856, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.6071428571428572, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.5907407407407407, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.6214285714285714, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.6306878306878307, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.5764550264550264, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.5806878306878307, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.55, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.5322751322751322, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.5664021164021165, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.5621693121693122, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.5, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.5, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.5, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.5, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.5, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.5, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.5, "id_best": 17, "lr_best": 9.599999999999999e-05, "wd_best": 0.05, "train/loss_best": 0.5156240844726563, "validation/loss_best": 0.640627384185791, "validation/acc_best": 0.6532258064516129, "validation/f1_best": 0.6408702094699266, "validation/bacc_best": 0.63994708994709} +{"epoch": 16, "train/lr": 3.870405029380728e-05, "train/loss": 0.334582287222147, "train/grad": 0.16818889455869793, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.64289794921875, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.638779296875, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.63253662109375, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.627042236328125, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.6220556640625, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.61578125, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.609334716796875, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.602794189453125, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.5949420166015625, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.5872705078125, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.5802813720703125, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.5703463745117188, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.561181640625, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.5479165649414063, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.5353128051757813, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.5224501037597656, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.5041387176513672, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.4768167877197266, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.43634780883789065, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.35147083520889283, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.1943107245862484, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.07124818250536918, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.016692816615104675, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.005328542888164521, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.002334185987710953, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.001154365837574005, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.0008013914525508881, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0006309701502323151, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.00034738928079605105, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.00023063942790031434, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.00022247880697250365, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.00019815608859062196, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.00015640199184417723, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.0001265430450439453, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.00015559077262878419, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.00015139207243919373, "train/loss_036_lr7.1e+00_wd1.0e+00": 6.926894187927247e-05, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.00014857441186904907, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.00016689926385879517, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.00018370628356933593, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.000166730135679245, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.0001662309467792511, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.69140625, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.69140625, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.69140625, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.69140625, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.69140625, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.69140625, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.69140625, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.03493808069266379, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.034902140721678736, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.03488411205355078, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.03488274508621544, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.034887214535847304, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.0349228008184582, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.03497006850782782, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.03503219051286578, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.035110403993166985, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.035225886488333344, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.03533896196633577, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.035507918749935925, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.03571506955195218, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.03598008953034878, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.03627420532051474, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.036634505414403974, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.03713370854966343, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.03769402477424592, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.03765898843295872, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.03669708422385156, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.032429959396831694, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.01984259852906689, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.00589017245452851, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0019862042959721293, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0009013640241755639, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0004778039670782164, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.00029913311616837747, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0002235275979001017, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.00012963039044734616, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.00010003453906392678, "train/grad_030_lr2.7e+00_wd1.0e+00": 8.044375615099852e-05, "train/grad_031_lr3.1e+00_wd1.0e+00": 6.983135587688593e-05, "train/grad_032_lr3.7e+00_wd1.0e+00": 5.553856787173572e-05, "train/grad_033_lr4.3e+00_wd1.0e+00": 4.890744981366879e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 6.048370075177445e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 6.016513713348104e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 4.729268954918098e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 5.992028693299289e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 8.152058390692218e-05, "train/grad_039_lr1.2e+01_wd1.0e+00": 8.713811442703445e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.00011590363845641605, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0001260234611822142, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.66513592004776, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.6630081534385681, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.6600703001022339, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.6575042009353638, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.655333936214447, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.6528112292289734, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.6501851081848145, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.6478517651557922, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.645178496837616, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.6427344679832458, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.6407472491264343, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.6380388140678406, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.6360849142074585, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.6340233683586121, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.6329063177108765, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.6327422261238098, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.6339786052703857, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.6404305100440979, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.6702187061309814, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.7472589612007141, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.9352262616157532, "validation/loss_021_lr6.1e-01_wd1.0e+00": 1.261191487312317, "validation/loss_022_lr7.2e-01_wd1.0e+00": 1.6482642889022827, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.038588523864746, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.4928009510040283, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.412879705429077, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.5605931282043457, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.513045310974121, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.9687283039093018, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.7725343704223633, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.590149164199829, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.4757914543151855, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.3674120903015137, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.644148111343384, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.4290664196014404, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.670358419418335, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.735663652420044, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.6451964378356934, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.47015380859375, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.446295976638794, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.1774392127990723, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.7987148761749268, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.6931473016738892, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.5967741935483871, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.5967741935483871, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.6209677419354839, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.5887096774193549, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.5967741935483871, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.6048387096774194, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.6209677419354839, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.6290322580645161, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.6209677419354839, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.6129032258064516, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.6129032258064516, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.6290322580645161, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.6451612903225806, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.6451612903225806, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.6532258064516129, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.6370967741935484, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.6209677419354839, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.6209677419354839, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.6451612903225806, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.5967741935483871, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.6129032258064516, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.5887096774193549, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.6048387096774194, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.6209677419354839, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.6048387096774194, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.6451612903225806, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.6209677419354839, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.5806451612903226, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.6129032258064516, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.5887096774193549, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.6209677419354839, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.5967741935483871, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.6209677419354839, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.6129032258064516, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.6370967741935484, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.6451612903225806, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.5887096774193549, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.5887096774193549, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.5564516129032258, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.5483870967741935, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.5645161290322581, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.5725806451612904, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.43548387096774194, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.43548387096774194, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.43548387096774194, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.43548387096774194, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.43548387096774194, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.43548387096774194, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.43548387096774194, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.5107323232323233, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.5107323232323233, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.5508285163776493, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.5263276159089207, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.544519541580958, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.5563344286235852, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.5793576326236016, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.5905828308929084, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.5881563140414104, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.5814345991561182, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.5852842809364549, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.5988748241912799, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.6198439241917503, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.6231003039513678, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.63853298081486, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.626380984265149, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.6118548118548119, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.6137071651090342, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.6375232527238905, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.5880946053680574, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.6025641025641025, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.5612903225806452, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.585171024783232, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.607462787095036, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.5907590759075907, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.6313513513513513, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.6118548118548119, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.5716183895827798, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.6025641025641025, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.5765651155005022, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.6049081418208935, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.5860042735042735, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.607462787095036, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.6003223207091055, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.6217205613178767, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.6313513513513513, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.5765651155005022, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.5808311791608669, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.5498646953996436, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.5308108108108108, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.5588932806324111, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.5623043623043623, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.30337078651685395, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.30337078651685395, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.30337078651685395, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.30337078651685395, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.30337078651685395, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.30337078651685395, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.30337078651685395, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.5518518518518518, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.5518518518518518, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.5796296296296296, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.551058201058201, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.5624338624338625, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.5716931216931217, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.5902116402116402, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.5994708994708995, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.5944444444444444, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.5873015873015873, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.5894179894179894, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.6037037037037037, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.6222222222222222, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.6243386243386243, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.6378306878306879, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.6256613756613757, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.6113756613756614, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.6134920634920635, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.6370370370370371, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.5878306878306878, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.602116402116402, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.5658730158730159, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.5865079365079364, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.6071428571428572, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.5907407407407407, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.6306878306878307, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.6113756613756614, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.5714285714285714, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.602116402116402, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.5764550264550264, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.605026455026455, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.5857142857142856, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.6071428571428572, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.6, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.6214285714285714, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.6306878306878307, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.5764550264550264, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.5806878306878307, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.55, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.5322751322751322, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.5592592592592592, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.5621693121693122, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.5, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.5, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.5, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.5, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.5, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.5, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.5, "id_best": 14, "lr_best": 5.9999999999999995e-05, "wd_best": 0.05, "train/loss_best": 0.5353128051757813, "validation/loss_best": 0.6329063177108765, "validation/acc_best": 0.6532258064516129, "validation/f1_best": 0.63853298081486, "validation/bacc_best": 0.6378306878306879} +{"epoch": 17, "train/lr": 2.030750443206766e-05, "train/loss": 0.33374131567776205, "train/grad": 0.175733545422554, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.64087158203125, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.6365283203125, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.63038330078125, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.6248193359375, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.619886474609375, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.613885498046875, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.607860107421875, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.601826171875, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.5947265625, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.587872314453125, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.5816705322265625, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.5726751708984374, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.564315185546875, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.55193115234375, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.5396511840820313, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.526591796875, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.5066929626464843, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.47391155242919925, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.4241986608505249, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.3324443769454956, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.18578290060162544, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.06789929702877999, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.015146898180246353, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.004669569432735443, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.0022930920124053953, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.001167054921388626, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.0007686494290828705, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0005945625901222229, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0003372283279895782, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0002424575388431549, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.00020943045616149901, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.00019375145435333253, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.00014973849058151246, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.0001275484263896942, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.00014409899711608886, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.00013004198670387267, "train/loss_036_lr7.1e+00_wd1.0e+00": 6.104618310928344e-05, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.0001259540021419525, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.00015924617648124695, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.00018724098801612855, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.00019395902752876283, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.0001550033688545227, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.69140625, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.69140625, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.69140625, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.69140625, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.69140625, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.69140625, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.69140625, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.03653685493394732, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.03650752297602594, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.036504344190470876, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.03651710299309343, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.03654147255700082, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.03660813296213746, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.036689495448954404, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.03678739311173558, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.03690859282854944, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.037056711628101764, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.037202074583619835, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.03741602944210172, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.03764425468165428, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.03794629167765379, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.03826677526813001, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.038636679789051415, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.039158692555502056, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.039690561052411796, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.03983184904325753, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.03838294114917517, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.03275372549891472, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.019491570693207904, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.00562720502843149, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.001878712344332598, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0008780954334361013, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.00047046130028320475, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0003023248281169799, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.00022495215638627995, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0001249696253807997, "train/grad_029_lr2.3e+00_wd1.0e+00": 9.473504366724227e-05, "train/grad_030_lr2.7e+00_wd1.0e+00": 7.703651856900252e-05, "train/grad_031_lr3.1e+00_wd1.0e+00": 6.713334916639723e-05, "train/grad_032_lr3.7e+00_wd1.0e+00": 5.4157689819476216e-05, "train/grad_033_lr4.3e+00_wd1.0e+00": 4.742094179164269e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 5.753620035648055e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 5.8701160055534275e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 4.397241218015324e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 5.957015800504451e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 7.638096833034069e-05, "train/grad_039_lr1.2e+01_wd1.0e+00": 8.312423426104943e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.00011385932296718693, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0001268570750011122, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.6650832891464233, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.6629378795623779, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.6599714159965515, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.6574631333351135, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.6551957130432129, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.6526981592178345, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.6502492427825928, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.6478617191314697, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.6452813744544983, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.6428704261779785, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.6408323645591736, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.6383631229400635, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.6364889740943909, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.6344720721244812, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.6334027051925659, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.6334778666496277, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.635054886341095, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.6425622701644897, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.6747024655342102, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.7546619176864624, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.9503141641616821, "validation/loss_021_lr6.1e-01_wd1.0e+00": 1.2847685813903809, "validation/loss_022_lr7.2e-01_wd1.0e+00": 1.6753941774368286, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.0598344802856445, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.510532855987549, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.4244513511657715, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.5716686248779297, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.521554946899414, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.9789905548095703, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.7775495052337646, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.5997204780578613, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.481907844543457, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.374204158782959, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.64931058883667, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.432861089706421, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.6749956607818604, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.72763991355896, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.6498055458068848, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.4714083671569824, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.448786735534668, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.1688811779022217, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.77958083152771, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.6931473016738892, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.5967741935483871, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.5967741935483871, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.6209677419354839, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.5887096774193549, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.5967741935483871, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.6048387096774194, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.6129032258064516, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.6290322580645161, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.6129032258064516, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.6209677419354839, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.6209677419354839, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.6290322580645161, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.6209677419354839, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.6370967741935484, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.6370967741935484, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.6532258064516129, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.6451612903225806, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.6451612903225806, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.6532258064516129, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.6048387096774194, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.6129032258064516, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.5967741935483871, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.5967741935483871, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.6209677419354839, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.6048387096774194, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.6451612903225806, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.6209677419354839, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.6048387096774194, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.6129032258064516, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.5887096774193549, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.6209677419354839, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.5967741935483871, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.6209677419354839, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.6129032258064516, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.6370967741935484, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.6451612903225806, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.5887096774193549, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.5887096774193549, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.5564516129032258, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.5483870967741935, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.5725806451612904, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.5806451612903226, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.43548387096774194, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.43548387096774194, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.43548387096774194, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.43548387096774194, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.43548387096774194, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.43548387096774194, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.43548387096774194, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.5107323232323233, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.5107323232323233, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.5508285163776493, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.5263276159089207, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.5386904761904762, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.5563344286235852, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.5679442508710801, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.5905828308929084, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.5772727272727273, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.5881563140414104, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.5881563140414104, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.5988748241912799, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.5881563140414104, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.6094351508364246, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.6160990712074303, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.6359664095036526, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.6336287939833467, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.6336287939833467, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.6448884448884449, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.5953379953379954, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.6003223207091055, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.5680044593088072, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.575109649122807, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.6049081418208935, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.5907590759075907, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.6313513513513513, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.6118548118548119, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.5931704050887178, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.6025641025641025, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.5765651155005022, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.6049081418208935, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.5860042735042735, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.607462787095036, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.6003223207091055, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.6217205613178767, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.6313513513513513, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.5765651155005022, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.5808311791608669, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.5498646953996436, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.5308108108108108, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.5662332519305657, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.5694444444444444, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.30337078651685395, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.30337078651685395, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.30337078651685395, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.30337078651685395, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.30337078651685395, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.30337078651685395, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.30337078651685395, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.5518518518518518, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.5518518518518518, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.5796296296296296, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.551058201058201, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.5603174603174603, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.5716931216931217, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.580952380952381, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.5994708994708995, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.5851851851851853, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.5944444444444444, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.5944444444444444, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.6037037037037037, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.5944444444444444, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.6129629629629629, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.6171957671957672, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.6357142857142857, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.6328042328042328, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.6328042328042328, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.6441798941798942, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.5949735449735449, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.6, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.573015873015873, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.5772486772486772, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.605026455026455, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.5907407407407407, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.6306878306878307, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.6113756613756614, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.5928571428571429, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.602116402116402, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.5764550264550264, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.605026455026455, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.5857142857142856, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.6071428571428572, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.6, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.6214285714285714, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.6306878306878307, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.5764550264550264, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.5806878306878307, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.55, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.5322751322751322, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.5664021164021165, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.5693121693121693, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.5, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.5, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.5, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.5, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.5, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.5, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.5, "id_best": 18, "lr_best": 0.00011399999999999999, "wd_best": 0.05, "train/loss_best": 0.4241986608505249, "validation/loss_best": 0.6747024655342102, "validation/acc_best": 0.6532258064516129, "validation/f1_best": 0.6448884448884449, "validation/bacc_best": 0.6441798941798942} +{"epoch": 18, "train/lr": 7.5829098008590064e-06, "train/loss": 0.3401706178486347, "train/grad": 0.1711370195262134, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.65329833984375, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.6498095703125, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.6447802734375, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.6402197265625, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.635987548828125, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.630850830078125, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.6252392578125, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.619815673828125, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.61310302734375, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.6065673828125, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.6005010986328125, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.59176513671875, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.5834906005859375, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.5709527587890625, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.5582757568359376, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.5446017456054687, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.5234666442871094, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.4877170562744141, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.4302955436706543, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.3407093334197998, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.18462770700454711, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.06515204459428788, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.015298289507627487, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.004786772131919861, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.002211008071899414, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.0012184230983257294, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.000772147923707962, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0005904401838779449, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0003475368022918701, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0002480392158031464, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.00020669370889663696, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.000184708833694458, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.00014296069741249085, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.00012455180287361146, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.00012803465127944947, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.0001291544735431671, "train/loss_036_lr7.1e+00_wd1.0e+00": 6.55500590801239e-05, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.0001400160789489746, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.00015440702438354492, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.00017802849411964418, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.00019421592354774476, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.000168791264295578, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.69140625, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.69140625, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.69140625, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.69140625, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.69140625, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.69140625, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.69140625, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.0358932526409626, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.035850020102225245, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.03581913924776017, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.03581023782026023, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.03582232289947569, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.035875957584939895, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.03595250483136624, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.036054846816696226, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.03617625685408712, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.03633592681027949, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.03647224735002965, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.03668003070633859, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.03687490817159414, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.03711234392598271, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.037335686273872855, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.037588728959672156, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.03789685448165983, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.03811910750344396, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.038237523697316644, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.036707690148614344, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.030664616127032786, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.018336306549608706, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0052252896077698095, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0017862383293686434, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0008590368636942003, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.00045071381027810274, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0003032521522982279, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.00022757703765819315, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.00012828928938688478, "train/grad_029_lr2.3e+00_wd1.0e+00": 9.574980233082897e-05, "train/grad_030_lr2.7e+00_wd1.0e+00": 7.686919989509989e-05, "train/grad_031_lr3.1e+00_wd1.0e+00": 6.727197222971881e-05, "train/grad_032_lr3.7e+00_wd1.0e+00": 5.419389530970875e-05, "train/grad_033_lr4.3e+00_wd1.0e+00": 4.682162149038049e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 5.6652483335710714e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 5.7411036809753565e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 4.783040900861124e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 5.728836665639392e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 7.598366867568985e-05, "train/grad_039_lr1.2e+01_wd1.0e+00": 8.092926966355662e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.00011374825591133231, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.00012823343335629288, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.6650177836418152, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.6629163026809692, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.6599534749984741, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.6574249267578125, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.6552057862281799, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.6526418328285217, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.6502225399017334, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.6479085683822632, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.6452112793922424, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.6429306864738464, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.640862762928009, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.638374924659729, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.6365785002708435, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.6345162987709045, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.6335133910179138, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.633462131023407, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.6351563930511475, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.6424556374549866, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.6750930547714233, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.7559174299240112, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.9535387754440308, "validation/loss_021_lr6.1e-01_wd1.0e+00": 1.288279414176941, "validation/loss_022_lr7.2e-01_wd1.0e+00": 1.6819640398025513, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.0697779655456543, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.5147626399993896, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.426528215408325, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.57543683052063, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.5248584747314453, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.9812560081481934, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.7808585166931152, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.602290153503418, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.4840550422668457, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.375823497772217, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.6510443687438965, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.434443473815918, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.676825761795044, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.7255940437316895, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.6514251232147217, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.47379207611084, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.4509642124176025, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.166029691696167, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.771721839904785, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.6931473016738892, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.5967741935483871, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.5967741935483871, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.6209677419354839, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.5887096774193549, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.5967741935483871, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.6048387096774194, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.6209677419354839, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.6290322580645161, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.6129032258064516, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.6290322580645161, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.6290322580645161, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.6290322580645161, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.6209677419354839, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.6370967741935484, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.6370967741935484, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.6451612903225806, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.6532258064516129, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.6451612903225806, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.6451612903225806, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.6209677419354839, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.6129032258064516, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.5887096774193549, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.5967741935483871, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.6209677419354839, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.6048387096774194, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.6451612903225806, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.6209677419354839, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.6048387096774194, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.6129032258064516, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.5887096774193549, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.6209677419354839, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.5967741935483871, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.6209677419354839, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.6129032258064516, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.6370967741935484, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.6451612903225806, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.5887096774193549, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.5887096774193549, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.5564516129032258, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.5483870967741935, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.5725806451612904, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.5806451612903226, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.43548387096774194, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.43548387096774194, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.43548387096774194, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.43548387096774194, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.43548387096774194, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.43548387096774194, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.43548387096774194, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.5107323232323233, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.5107323232323233, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.5508285163776493, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.5263276159089207, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.5386904761904762, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.5563344286235852, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.5744432274552757, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.5905828308929084, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.5772727272727273, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.5948863636363637, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.5948863636363637, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.5988748241912799, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.5881563140414104, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.6094351508364246, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.6129032258064516, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.6260964912280702, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.63853298081486, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.6336287939833467, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.6356837606837606, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.6097756946769334, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.6003223207091055, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.5612903225806452, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.575109649122807, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.6049081418208935, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.5907590759075907, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.6313513513513513, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.6118548118548119, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.5931704050887178, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.6025641025641025, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.5765651155005022, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.6049081418208935, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.5860042735042735, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.607462787095036, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.6003223207091055, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.6217205613178767, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.6313513513513513, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.5765651155005022, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.5808311791608669, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.5498646953996436, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.5308108108108108, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.5662332519305657, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.5694444444444444, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.30337078651685395, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.30337078651685395, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.30337078651685395, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.30337078651685395, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.30337078651685395, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.30337078651685395, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.30337078651685395, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.5518518518518518, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.5518518518518518, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.5796296296296296, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.551058201058201, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.5603174603174603, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.5716931216931217, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.5880952380952381, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.5994708994708995, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.5851851851851853, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.6015873015873016, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.6015873015873016, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.6037037037037037, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.5944444444444444, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.6129629629629629, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.6150793650793651, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.6264550264550265, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.6378306878306879, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.6328042328042328, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.6349206349206349, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.6092592592592592, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.6, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.5658730158730159, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.5772486772486772, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.605026455026455, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.5907407407407407, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.6306878306878307, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.6113756613756614, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.5928571428571429, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.602116402116402, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.5764550264550264, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.605026455026455, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.5857142857142856, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.6071428571428572, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.6, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.6214285714285714, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.6306878306878307, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.5764550264550264, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.5806878306878307, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.55, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.5322751322751322, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.5664021164021165, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.5693121693121693, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.5, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.5, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.5, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.5, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.5, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.5, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.5, "id_best": 16, "lr_best": 8.1e-05, "wd_best": 0.05, "train/loss_best": 0.5234666442871094, "validation/loss_best": 0.6351563930511475, "validation/acc_best": 0.6532258064516129, "validation/f1_best": 0.63853298081486, "validation/bacc_best": 0.6378306878306879} +{"epoch": 19, "train/lr": 1.0867618231465446e-06, "train/loss": 0.334762486666441, "train/grad": 0.17271619774401187, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.639453125, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.63544189453125, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.62958984375, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.624403076171875, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.619884033203125, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.6141845703125, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.608375244140625, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.602821044921875, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.596148681640625, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.5898394775390625, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.584169921875, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.5759271240234375, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.5684332275390624, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.5573345947265625, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.5462698364257812, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.5346279907226562, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.5165535736083985, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.484671630859375, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.42997524261474607, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.33233943104743957, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.18225621297955513, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.0645227862894535, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.01464377149939537, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.004743717610836029, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.0021780966222286224, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.001129700094461441, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.0007176905870437622, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.000535450130701065, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0003390577435493469, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.00022880017757415772, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.00020092502236366273, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.0001893995702266693, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.0001419191062450409, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.00012272194027900695, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.00013110294938087463, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.00013326704502105712, "train/loss_036_lr7.1e+00_wd1.0e+00": 6.478160619735718e-05, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.00014358043670654298, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.0001505400240421295, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.0001733890175819397, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.00017759665846824645, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.00015049248933792113, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.69140625, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.69140625, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.69140625, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.69140625, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.69140625, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.69140625, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.69140625, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.036565383402630686, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.03654697123449296, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.03656928802840412, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.03660912983119488, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.03665739647112787, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.03674876833334565, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.03684366394765675, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.03695761064998806, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.03708966770209372, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.03724254416301846, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.03737395337317139, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.03757875727489591, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.037775152265094224, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.038029420459643005, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.038285395968705414, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.03857330951839685, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.0389255957165733, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.038824096843600275, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.0375982118723914, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.03466208723839372, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.028010769749525936, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.01628791298251599, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.00489818285102956, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0017293367617821787, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.000812212146629463, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.000418974144376989, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.00027973483622190543, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0002191150453836599, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0001261792125797001, "train/grad_029_lr2.3e+00_wd1.0e+00": 9.17950036637194e-05, "train/grad_030_lr2.7e+00_wd1.0e+00": 7.49358935172495e-05, "train/grad_031_lr3.1e+00_wd1.0e+00": 6.529087980197801e-05, "train/grad_032_lr3.7e+00_wd1.0e+00": 5.315315270763676e-05, "train/grad_033_lr4.3e+00_wd1.0e+00": 4.515254847888173e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 5.6505394350097047e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 5.6959912958518546e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 4.401220047071774e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 5.682036975031224e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 7.540526797811253e-05, "train/grad_039_lr1.2e+01_wd1.0e+00": 7.964231350001682e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.00010820079505805325, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.00012412295188063638, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.6650276184082031, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.6628664135932922, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.6599136590957642, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.6573765873908997, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.6551651358604431, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.6526644229888916, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.6502194404602051, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.6478803753852844, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.6451739072799683, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.6428688764572144, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.6408275365829468, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.638380229473114, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.6365254521369934, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.6344591975212097, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.6334754228591919, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.6333512663841248, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.6350160241127014, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.6423261165618896, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.6749246716499329, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.7558547258377075, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.9536841511726379, "validation/loss_021_lr6.1e-01_wd1.0e+00": 1.2897002696990967, "validation/loss_022_lr7.2e-01_wd1.0e+00": 1.6831568479537964, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.0693917274475098, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.5160770416259766, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.426478147506714, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.575472593307495, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.526280403137207, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.982877731323242, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.7810609340667725, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.6035149097442627, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.484713554382324, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.37662935256958, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.651545286178589, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.434891700744629, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.6781067848205566, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.7258787155151367, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.6508593559265137, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.4735569953918457, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.4510586261749268, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.1672136783599854, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.7710981369018555, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.6931473016738892, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.5967741935483871, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.5967741935483871, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.6209677419354839, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.5887096774193549, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.5967741935483871, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.6048387096774194, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.6129032258064516, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.6290322580645161, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.6129032258064516, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.6209677419354839, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.6290322580645161, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.6290322580645161, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.6209677419354839, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.6370967741935484, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.6370967741935484, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.6451612903225806, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.6612903225806451, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.6451612903225806, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.6532258064516129, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.6209677419354839, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.6129032258064516, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.5967741935483871, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.5967741935483871, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.6209677419354839, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.6048387096774194, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.6451612903225806, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.6209677419354839, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.5967741935483871, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.6129032258064516, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.5887096774193549, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.6209677419354839, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.5967741935483871, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.6209677419354839, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.6129032258064516, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.6370967741935484, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.6451612903225806, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.5887096774193549, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.5887096774193549, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.5564516129032258, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.5483870967741935, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.5725806451612904, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.5806451612903226, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.43548387096774194, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.43548387096774194, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.43548387096774194, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.43548387096774194, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.43548387096774194, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.43548387096774194, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.43548387096774194, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.5107323232323233, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.5107323232323233, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.5508285163776493, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.5263276159089207, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.5386904761904762, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.5563344286235852, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.5679442508710801, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.5905828308929084, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.5772727272727273, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.5881563140414104, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.5948863636363637, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.5988748241912799, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.5881563140414104, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.6094351508364246, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.6129032258064516, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.6260964912280702, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.6457142857142857, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.6336287939833467, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.6429862738533645, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.6097756946769334, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.6003223207091055, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.5680044593088072, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.575109649122807, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.6049081418208935, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.5907590759075907, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.6313513513513513, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.6118548118548119, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.5860042735042735, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.6025641025641025, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.5765651155005022, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.6049081418208935, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.5860042735042735, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.607462787095036, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.6003223207091055, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.6217205613178767, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.6313513513513513, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.5765651155005022, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.5808311791608669, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.5498646953996436, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.5308108108108108, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.5662332519305657, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.5694444444444444, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.30337078651685395, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.30337078651685395, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.30337078651685395, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.30337078651685395, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.30337078651685395, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.30337078651685395, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.30337078651685395, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.5518518518518518, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.5518518518518518, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.5796296296296296, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.551058201058201, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.5603174603174603, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.5716931216931217, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.580952380952381, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.5994708994708995, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.5851851851851853, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.5944444444444444, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.6015873015873016, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.6037037037037037, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.5944444444444444, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.6129629629629629, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.6150793650793651, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.6264550264550265, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.644973544973545, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.6328042328042328, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.642063492063492, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.6092592592592592, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.6, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.573015873015873, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.5772486772486772, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.605026455026455, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.5907407407407407, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.6306878306878307, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.6113756613756614, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.5857142857142856, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.602116402116402, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.5764550264550264, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.605026455026455, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.5857142857142856, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.6071428571428572, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.6, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.6214285714285714, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.6306878306878307, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.5764550264550264, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.5806878306878307, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.55, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.5322751322751322, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.5664021164021165, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.5693121693121693, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.5, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.5, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.5, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.5, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.5, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.5, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.5, "id_best": 16, "lr_best": 8.1e-05, "wd_best": 0.05, "train/loss_best": 0.5165535736083985, "validation/loss_best": 0.6350160241127014, "validation/acc_best": 0.6612903225806451, "validation/f1_best": 0.6457142857142857, "validation/bacc_best": 0.644973544973545} diff --git a/input_space_v3/flat_lr1e-3_1/eval_v2/abide_dx__patch__logistic/config.yaml b/input_space_v3/flat_lr1e-3_1/eval_v2/abide_dx__patch__logistic/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..bce2a6072da1e4bb625885406aa3e715ba65e5df --- /dev/null +++ b/input_space_v3/flat_lr1e-3_1/eval_v2/abide_dx__patch__logistic/config.yaml @@ -0,0 +1,30 @@ +output_root: experiments/input_space_v3/output +name_prefix: eval_logistic +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_1; eval v2 (abide_dx patch logistic) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: input_space_v3/flat_lr1e-3_1/eval_v2/abide_dx__patch__logistic +model: flat_mae +representation: patch +dataset: abide_dx +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/abide_dx__patch__logistic +remote_dir: null diff --git a/input_space_v3/flat_lr1e-3_1/eval_v2/abide_dx__patch__logistic/eval_table.csv b/input_space_v3/flat_lr1e-3_1/eval_v2/abide_dx__patch__logistic/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..187313a1ba422bb867fbf532892cb8456be683b0 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_1/eval_v2/abide_dx__patch__logistic/eval_table.csv @@ -0,0 +1,203 @@ +model,repr,clf,dataset,trial,C,split,acc,acc_std,f1,f1_std,bacc,bacc_std +flat_mae,patch,logistic,abide_dx,,0.046415888336127774,train,0.8105413105413105,0.014134172468635086,0.8074463324142113,0.014372175740868387,0.8061346772604898,0.014340667012817164 +flat_mae,patch,logistic,abide_dx,,0.046415888336127774,test,0.5967741935483871,0.04369336381675493,0.58994708994709,0.045154815049940275,0.5902068604346689,0.04440486792531996 +flat_mae,patch,logistic,abide_dx,1,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,1,166.81005372000556,test,0.5806451612903226,0.04500760428292359,0.5796610169491525,0.045268674344655736,0.58140756302521,0.045390134425310195 +flat_mae,patch,logistic,abide_dx,2,0.3593813663804626,train,0.905982905982906,0.010528306447183541,0.9048076923076923,0.010653229012776532,0.9040974529346621,0.010648235572396534 +flat_mae,patch,logistic,abide_dx,2,0.3593813663804626,test,0.7096774193548387,0.04090117464583321,0.7089960886571056,0.040970210420567574,0.7116596638655461,0.04081760143473344 +flat_mae,patch,logistic,abide_dx,3,2.782559402207126,train,0.99002849002849,0.003965746470952781,0.98993121507736,0.004000659171919322,0.9903654485049834,0.003843355696537553 +flat_mae,patch,logistic,abide_dx,3,2.782559402207126,test,0.6532258064516129,0.04195972934346077,0.6480760345851759,0.04267420758771784,0.6475840336134454,0.04238115239191262 +flat_mae,patch,logistic,abide_dx,4,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,4,21.54434690031882,test,0.717741935483871,0.03795159576655358,0.7168395641678085,0.03804069145833692,0.7190126050420168,0.03796853923882177 +flat_mae,patch,logistic,abide_dx,5,2.782559402207126,train,0.9843304843304843,0.004837075766405932,0.9841495630969315,0.004899443563056271,0.9837209302325581,0.005069615392321438 +flat_mae,patch,logistic,abide_dx,5,2.782559402207126,test,0.6129032258064516,0.043714054655244056,0.6092436974789917,0.04436966032022113,0.6092436974789917,0.044191476889235796 +flat_mae,patch,logistic,abide_dx,6,0.046415888336127774,train,0.8034188034188035,0.015173115155141111,0.7995115894039735,0.015576296468809502,0.7974898486526394,0.015541280996443262 +flat_mae,patch,logistic,abide_dx,6,0.046415888336127774,test,0.5725806451612904,0.04601850903470598,0.5599598259122867,0.047899641454191524,0.5614495798319328,0.04665392109304478 +flat_mae,patch,logistic,abide_dx,7,2.782559402207126,train,0.9857549857549858,0.00419295309714678,0.9855860443342066,0.004248542799107446,0.9850129198966409,0.004426640653060003 +flat_mae,patch,logistic,abide_dx,7,2.782559402207126,test,0.6612903225806451,0.04103186181082759,0.6555555555555556,0.042137600858448074,0.654936974789916,0.041728325791099675 +flat_mae,patch,logistic,abide_dx,8,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,8,1291.5496650148827,test,0.6129032258064516,0.039961284593831276,0.607905138339921,0.040465388095375115,0.6076680672268908,0.04029412690258479 +flat_mae,patch,logistic,abide_dx,9,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,9,21.54434690031882,test,0.6854838709677419,0.04185046903661664,0.6761968530297957,0.04377035349960309,0.6754201680672269,0.042744054380805495 +flat_mae,patch,logistic,abide_dx,10,0.3593813663804626,train,0.896011396011396,0.011189879322043171,0.8948107369160001,0.011328421788995414,0.8944629014396457,0.011389098237478055 +flat_mae,patch,logistic,abide_dx,10,0.3593813663804626,test,0.6935483870967742,0.0401041665258952,0.6915422885572139,0.04046645807385967,0.6922268907563025,0.04067784913962407 +flat_mae,patch,logistic,abide_dx,11,10000.0,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,11,10000.0,test,0.6209677419354839,0.04280549139599316,0.6197559861681998,0.042708429896886606,0.6213235294117647,0.04266040238895434 +flat_mae,patch,logistic,abide_dx,12,0.046415888336127774,train,0.8105413105413105,0.014478647895306356,0.8075860150236482,0.014759134818414132,0.806312292358804,0.014770329167421724 +flat_mae,patch,logistic,abide_dx,12,0.046415888336127774,test,0.6129032258064516,0.04350696656212754,0.6045708211533352,0.044632274209381165,0.6045168067226891,0.043953799122527615 +flat_mae,patch,logistic,abide_dx,13,0.046415888336127774,train,0.801994301994302,0.015048426306187008,0.7993225609417514,0.015312112714839099,0.7985603543743078,0.015369375323665795 +flat_mae,patch,logistic,abide_dx,13,0.046415888336127774,test,0.6370967741935484,0.04319886919454981,0.6330637206549615,0.04365651777997638,0.6328781512605042,0.04352180701148341 +flat_mae,patch,logistic,abide_dx,14,2.782559402207126,train,0.9957264957264957,0.0024620462175477384,0.9956848064617256,0.002483439279974219,0.9961240310077519,0.0022330186624270067 +flat_mae,patch,logistic,abide_dx,14,2.782559402207126,test,0.6129032258064516,0.04387422900591739,0.6025641025641025,0.045727603351582116,0.6029411764705883,0.04462227992153873 +flat_mae,patch,logistic,abide_dx,15,0.046415888336127774,train,0.8048433048433048,0.013972453410420712,0.8017991282574423,0.014334632078608852,0.8005537098560354,0.01445204710303085 +flat_mae,patch,logistic,abide_dx,15,0.046415888336127774,test,0.6774193548387096,0.04243293968660964,0.6743697478991597,0.04313820079756886,0.6743697478991597,0.04323833955258539 +flat_mae,patch,logistic,abide_dx,16,0.3593813663804626,train,0.905982905982906,0.011774462433628494,0.904867892605764,0.011945112946408144,0.9043927648578811,0.012076559825288139 +flat_mae,patch,logistic,abide_dx,16,0.3593813663804626,test,0.6370967741935484,0.042197725328420484,0.626380984265149,0.04361030127701566,0.6265756302521008,0.042517544107308035 +flat_mae,patch,logistic,abide_dx,17,10000.0,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,17,10000.0,test,0.6290322580645161,0.04374058840346541,0.6227513227513227,0.04484059350618811,0.6223739495798319,0.044344495752018785 +flat_mae,patch,logistic,abide_dx,18,0.046415888336127774,train,0.8005698005698005,0.015270123731022102,0.7973858904053107,0.01554342103176743,0.7960871170173496,0.015518225928426431 +flat_mae,patch,logistic,abide_dx,18,0.046415888336127774,test,0.6693548387096774,0.0412805274419998,0.6553454003118433,0.04437126263063947,0.6559873949579832,0.042336451997234535 +flat_mae,patch,logistic,abide_dx,19,0.3593813663804626,train,0.8988603988603988,0.011447201269129795,0.8976926345347398,0.011579964264662892,0.8973421926910299,0.011613994246896993 +flat_mae,patch,logistic,abide_dx,19,0.3593813663804626,test,0.5403225806451613,0.045518815219883005,0.5292707292707293,0.04728234805582466,0.5304621848739496,0.046187937227068786 +flat_mae,patch,logistic,abide_dx,20,0.3593813663804626,train,0.896011396011396,0.011756358043561864,0.8948746089543054,0.01191399436218563,0.8947582133628644,0.012045108777260704 +flat_mae,patch,logistic,abide_dx,20,0.3593813663804626,test,0.6532258064516129,0.04168241256416925,0.6480760345851759,0.0425700564502607,0.6475840336134454,0.04234312125376591 +flat_mae,patch,logistic,abide_dx,21,2.782559402207126,train,0.9857549857549858,0.004647046790317174,0.9856200581752632,0.00468642255780687,0.9861941675895165,0.004550497825464908 +flat_mae,patch,logistic,abide_dx,21,2.782559402207126,test,0.5967741935483871,0.04354992828814056,0.5963541666666667,0.04350507253083394,0.5992647058823529,0.04333105013566372 +flat_mae,patch,logistic,abide_dx,22,2.782559402207126,train,0.99002849002849,0.003685957925099261,0.989913358334411,0.0037331857389137596,0.9894795127353266,0.003920930006663342 +flat_mae,patch,logistic,abide_dx,22,2.782559402207126,test,0.6290322580645161,0.043093426927187206,0.6227513227513227,0.04399200091769339,0.6223739495798319,0.04365189986153042 +flat_mae,patch,logistic,abide_dx,23,2.782559402207126,train,0.99002849002849,0.0036844502850234277,0.9899194830504128,0.0037268498316149483,0.9897748246585456,0.0038139561543815825 +flat_mae,patch,logistic,abide_dx,23,2.782559402207126,test,0.6290322580645161,0.04351999970829252,0.6145945945945945,0.04601078061102287,0.6160714285714286,0.04433914490236562 +flat_mae,patch,logistic,abide_dx,24,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,24,166.81005372000556,test,0.6290322580645161,0.04454618842533899,0.6266038229903116,0.04473246450769769,0.6271008403361344,0.04472277931209889 +flat_mae,patch,logistic,abide_dx,25,0.3593813663804626,train,0.9116809116809117,0.01077232654217919,0.9105769230769231,0.010920722336535732,0.9098560354374308,0.01099929795176453 +flat_mae,patch,logistic,abide_dx,25,0.3593813663804626,test,0.6129032258064516,0.04292158229663759,0.6092436974789917,0.04338892140778375,0.6092436974789917,0.043254547776126494 +flat_mae,patch,logistic,abide_dx,26,0.3593813663804626,train,0.9145299145299145,0.00990706853207823,0.9134053173904819,0.010062986483422373,0.9124400147655962,0.010181172043339754 +flat_mae,patch,logistic,abide_dx,26,0.3593813663804626,test,0.6290322580645161,0.04221249697831959,0.6169755573462261,0.04444702268278988,0.6176470588235294,0.043081887287489615 +flat_mae,patch,logistic,abide_dx,27,2.782559402207126,train,0.9871794871794872,0.004176583761495318,0.9870469879839183,0.004218548369393805,0.9871908453303803,0.004197898457645839 +flat_mae,patch,logistic,abide_dx,27,2.782559402207126,test,0.6048387096774194,0.04494280096968858,0.6035753898349319,0.04508992925030588,0.6050420168067226,0.045242681921609434 +flat_mae,patch,logistic,abide_dx,28,0.3593813663804626,train,0.9116809116809117,0.01058507278569797,0.9107939266740999,0.010691347505752036,0.9110372831303064,0.01073037686539471 +flat_mae,patch,logistic,abide_dx,28,0.3593813663804626,test,0.6451612903225806,0.04115583882900507,0.6447916666666667,0.04127173914320862,0.648109243697479,0.041366350310244944 +flat_mae,patch,logistic,abide_dx,29,0.3593813663804626,train,0.8931623931623932,0.011037542624181508,0.8920582331993202,0.01115352235786645,0.8921742340346992,0.011190638312771345 +flat_mae,patch,logistic,abide_dx,29,0.3593813663804626,test,0.7096774193548387,0.04011249789021766,0.7059288537549406,0.04073449915444729,0.7053571428571428,0.04058333383933353 +flat_mae,patch,logistic,abide_dx,30,0.3593813663804626,train,0.905982905982906,0.011050169275661392,0.9049833887043189,0.011170242328110558,0.9049833887043189,0.011208200963735197 +flat_mae,patch,logistic,abide_dx,30,0.3593813663804626,test,0.6935483870967742,0.040086418095320014,0.6869519000797236,0.04158501819825407,0.6859243697478992,0.04087519671879717 +flat_mae,patch,logistic,abide_dx,31,0.046415888336127774,train,0.801994301994302,0.015117014226440679,0.7981402372800712,0.015620518196642619,0.7961978589885567,0.015671681337652246 +flat_mae,patch,logistic,abide_dx,31,0.046415888336127774,test,0.6693548387096774,0.04228359238787222,0.6667322189446083,0.04276696138682026,0.6670168067226891,0.042763385560810725 +flat_mae,patch,logistic,abide_dx,32,2.782559402207126,train,0.99002849002849,0.003583691139694174,0.98993121507736,0.0036155726782535523,0.9903654485049834,0.0034907218212758633 +flat_mae,patch,logistic,abide_dx,32,2.782559402207126,test,0.5967741935483871,0.04322843937575914,0.5915678524374176,0.04370458807615033,0.5913865546218487,0.043567191472364895 +flat_mae,patch,logistic,abide_dx,33,0.046415888336127774,train,0.7977207977207977,0.015079402291569606,0.7941859024652104,0.015419625759126032,0.7926172019195274,0.015403723416974695 +flat_mae,patch,logistic,abide_dx,33,0.046415888336127774,test,0.6209677419354839,0.042679881917590624,0.6137071651090342,0.04386567443767284,0.6134453781512605,0.04327038065584293 +flat_mae,patch,logistic,abide_dx,34,0.3593813663804626,train,0.8931623931623932,0.011520041221520772,0.8919944612544233,0.011669719141289964,0.8918789221114802,0.011788380339996542 +flat_mae,patch,logistic,abide_dx,34,0.3593813663804626,test,0.6290322580645161,0.04278177084639416,0.6242424242424243,0.04351714124760208,0.6239495798319328,0.04317404077156884 +flat_mae,patch,logistic,abide_dx,35,0.046415888336127774,train,0.8062678062678063,0.015106931565880296,0.8022551594435837,0.015609199481501204,0.8000738279808047,0.015613752948315695 +flat_mae,patch,logistic,abide_dx,35,0.046415888336127774,test,0.6774193548387096,0.04068588269889882,0.6732542819499341,0.04112394206512272,0.6727941176470589,0.04088590861535841 +flat_mae,patch,logistic,abide_dx,36,2.782559402207126,train,0.9857549857549858,0.004477526813056141,0.9855949175914374,0.0045323857497639765,0.9853082318198597,0.004659928620316877 +flat_mae,patch,logistic,abide_dx,36,2.782559402207126,test,0.6451612903225806,0.04257065804187934,0.6356837606837606,0.044412917832733344,0.6355042016806722,0.043398175983400275 +flat_mae,patch,logistic,abide_dx,37,0.3593813663804626,train,0.9074074074074074,0.010703807971998549,0.9061580320950635,0.010882918021594782,0.905094130675526,0.010994411516212053 +flat_mae,patch,logistic,abide_dx,37,0.3593813663804626,test,0.6774193548387096,0.040684373686058484,0.6760710553814002,0.041049849640820466,0.6775210084033614,0.04127988263080961 +flat_mae,patch,logistic,abide_dx,38,2.782559402207126,train,0.9814814814814815,0.005044411973495314,0.9812676654781918,0.00510893676328829,0.9808416389811738,0.005279094732401527 +flat_mae,patch,logistic,abide_dx,38,2.782559402207126,test,0.6209677419354839,0.04269962604656074,0.6153389215233318,0.04352115068224644,0.6150210084033614,0.04319636657761545 +flat_mae,patch,logistic,abide_dx,39,0.3593813663804626,train,0.9145299145299145,0.010459874859191712,0.9135162660052399,0.010601005056247012,0.9130306386120339,0.010688058209091056 +flat_mae,patch,logistic,abide_dx,39,0.3593813663804626,test,0.6290322580645161,0.04120784352967629,0.6274817136886102,0.041225406886145184,0.6286764705882353,0.0412760644404526 +flat_mae,patch,logistic,abide_dx,40,0.046415888336127774,train,0.811965811965812,0.014567255241969827,0.8089638395250072,0.014889229940800526,0.8076042820228866,0.014937373428327402 +flat_mae,patch,logistic,abide_dx,40,0.046415888336127774,test,0.5564516129032258,0.042135290129505544,0.5376584638329605,0.045463481645789845,0.542016806722689,0.043050270334791106 +flat_mae,patch,logistic,abide_dx,41,2.782559402207126,train,0.99002849002849,0.0037788508357287647,0.9899254350986032,0.003815733947759295,0.9900701365817646,0.0037523451487043577 +flat_mae,patch,logistic,abide_dx,41,2.782559402207126,test,0.6370967741935484,0.04512498540733822,0.6351748937561295,0.045492566368562554,0.6360294117647058,0.04539016900465371 +flat_mae,patch,logistic,abide_dx,42,2.782559402207126,train,0.9857549857549858,0.004365835428562777,0.9855860443342066,0.0044241534510420675,0.9850129198966409,0.004619655451260195 +flat_mae,patch,logistic,abide_dx,42,2.782559402207126,test,0.6048387096774194,0.04634787924500846,0.6017043592264831,0.04676741748226135,0.601890756302521,0.046704989390403476 +flat_mae,patch,logistic,abide_dx,43,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,43,166.81005372000556,test,0.6693548387096774,0.043539592899381974,0.6667322189446083,0.04383511895418788,0.6670168067226891,0.043742443068532096 +flat_mae,patch,logistic,abide_dx,44,0.005994842503189409,train,0.7108262108262108,0.01617507636799865,0.702270794725923,0.016828130537181213,0.700812107788852,0.01653040053785316 +flat_mae,patch,logistic,abide_dx,44,0.005994842503189409,test,0.5887096774193549,0.04096107070396721,0.5649122807017544,0.04482951922838205,0.5714285714285714,0.041758915422843663 +flat_mae,patch,logistic,abide_dx,45,0.3593813663804626,train,0.9131054131054132,0.010416108320195582,0.9122073630021137,0.010520599001922176,0.912329272794389,0.010551018180756192 +flat_mae,patch,logistic,abide_dx,45,0.3593813663804626,test,0.6774193548387096,0.04204589682913773,0.671957671957672,0.0430017896233825,0.671218487394958,0.04265955982436926 +flat_mae,patch,logistic,abide_dx,46,0.3593813663804626,train,0.9116809116809117,0.010913986649487442,0.9106334748720812,0.011059712959136788,0.9101513473606497,0.011155915585133742 +flat_mae,patch,logistic,abide_dx,46,0.3593813663804626,test,0.5887096774193549,0.04330576379582337,0.5880398671096345,0.04341151013090361,0.5903361344537814,0.04348969713134549 +flat_mae,patch,logistic,abide_dx,47,0.046415888336127774,train,0.7991452991452992,0.01511631055993626,0.7957124842370744,0.015451517034210365,0.794204503506829,0.01541943782025145 +flat_mae,patch,logistic,abide_dx,47,0.046415888336127774,test,0.6451612903225806,0.040258387612433826,0.6356837606837606,0.04190534824433022,0.6355042016806722,0.040994363682638604 +flat_mae,patch,logistic,abide_dx,48,10000.0,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,48,10000.0,test,0.5887096774193549,0.044577809069024255,0.5880398671096345,0.04480948148768099,0.5903361344537814,0.04499543582286021 +flat_mae,patch,logistic,abide_dx,49,0.3593813663804626,train,0.9116809116809117,0.010310240188821755,0.9104591836734695,0.01049124118295831,0.909265411590993,0.01064778275157166 +flat_mae,patch,logistic,abide_dx,49,0.3593813663804626,test,0.5887096774193549,0.04420880358317768,0.5880398671096345,0.04433098214476621,0.5903361344537814,0.04464262999200738 +flat_mae,patch,logistic,abide_dx,50,0.005994842503189409,train,0.7207977207977208,0.017146749386428496,0.7137698042870457,0.017772170316279312,0.712218530823182,0.01754639835719072 +flat_mae,patch,logistic,abide_dx,50,0.005994842503189409,test,0.5483870967741935,0.044168143745875216,0.5276190476190477,0.04655231050191952,0.5330882352941176,0.044554092970338605 +flat_mae,patch,logistic,abide_dx,51,0.3593813663804626,train,0.9358974358974359,0.00938576693730741,0.9351168164313222,0.009521014467794629,0.9344776670358066,0.009670891829221904 +flat_mae,patch,logistic,abide_dx,51,0.3593813663804626,test,0.5887096774193549,0.04474809828012611,0.5765651155005022,0.04703476077404137,0.5777310924369747,0.045463635051972845 +flat_mae,patch,logistic,abide_dx,52,2.782559402207126,train,0.98005698005698,0.005371327006017206,0.9798204620678894,0.00544113580099437,0.9792543373938722,0.005593700839201804 +flat_mae,patch,logistic,abide_dx,52,2.782559402207126,test,0.7016129032258065,0.04168472172120123,0.6958971299794525,0.04289468437095952,0.6948529411764706,0.04255500728886321 +flat_mae,patch,logistic,abide_dx,53,0.046415888336127774,train,0.7991452991452992,0.014910454766711559,0.7953983120391749,0.015319241897523561,0.7936138796603913,0.015325125890014571 +flat_mae,patch,logistic,abide_dx,53,0.046415888336127774,test,0.6612903225806451,0.044127791319092245,0.6539994685091681,0.04543296113480199,0.6533613445378151,0.04478989133176045 +flat_mae,patch,logistic,abide_dx,54,0.3593813663804626,train,0.9116809116809117,0.010373287839829262,0.9106334748720812,0.010520331054454603,0.9101513473606497,0.010656513741333027 +flat_mae,patch,logistic,abide_dx,54,0.3593813663804626,test,0.6129032258064516,0.04359238816503772,0.6025641025641025,0.045220145438597176,0.6029411764705883,0.04422382694548001 +flat_mae,patch,logistic,abide_dx,55,2.782559402207126,train,0.9943019943019943,0.0030103203678843566,0.994237967036575,0.0030464282649167265,0.9939461055740126,0.0032087453141669436 +flat_mae,patch,logistic,abide_dx,55,2.782559402207126,test,0.5967741935483871,0.04341224537970119,0.5915678524374176,0.043843828572623575,0.5913865546218487,0.04357448278640143 +flat_mae,patch,logistic,abide_dx,56,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,56,166.81005372000556,test,0.6370967741935484,0.042056574552135274,0.6330637206549615,0.04246872565404776,0.6328781512605042,0.042301077373325516 +flat_mae,patch,logistic,abide_dx,57,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,57,1291.5496650148827,test,0.6290322580645161,0.04292023371346817,0.6266038229903116,0.04324340816290291,0.6271008403361344,0.043194322813753516 +flat_mae,patch,logistic,abide_dx,58,0.3593813663804626,train,0.9102564102564102,0.010301482162092956,0.9092753474537156,0.010399226518941228,0.9091546696197859,0.010363902287660218 +flat_mae,patch,logistic,abide_dx,58,0.3593813663804626,test,0.6129032258064516,0.04181315594888559,0.6092436974789917,0.042382105168384095,0.6092436974789917,0.04229353006876125 +flat_mae,patch,logistic,abide_dx,59,0.005994842503189409,train,0.7108262108262108,0.015977104339820997,0.7013573522724177,0.016795755444394257,0.6999261720191953,0.016445788430001957 +flat_mae,patch,logistic,abide_dx,59,0.005994842503189409,test,0.6129032258064516,0.0460022479430827,0.6112852664576802,0.046072522610990936,0.6123949579831933,0.0461153932682332 +flat_mae,patch,logistic,abide_dx,60,0.3593813663804626,train,0.9074074074074074,0.011087099118008363,0.9063951997538335,0.011206063539410354,0.9062753783684017,0.01122555258786687 +flat_mae,patch,logistic,abide_dx,60,0.3593813663804626,test,0.6451612903225806,0.04337354087305768,0.6391534391534391,0.04470860130929421,0.6386554621848739,0.04431053143157829 +flat_mae,patch,logistic,abide_dx,61,0.3593813663804626,train,0.9031339031339032,0.011365721497792393,0.9020454396217743,0.0114896482163928,0.9018087855297157,0.011511066258482205 +flat_mae,patch,logistic,abide_dx,61,0.3593813663804626,test,0.5645161290322581,0.04402746044996529,0.555142173797502,0.045292154290839,0.555672268907563,0.0445118703664962 +flat_mae,patch,logistic,abide_dx,62,0.046415888336127774,train,0.8162393162393162,0.014304519305829173,0.8133729017898544,0.014581535948575213,0.8120708748615726,0.0145864503378209 +flat_mae,patch,logistic,abide_dx,62,0.046415888336127774,test,0.5564516129032258,0.04429313890442,0.5498646953996436,0.04504732460952543,0.5498949579831933,0.044703467259195884 +flat_mae,patch,logistic,abide_dx,63,0.3593813663804626,train,0.9002849002849003,0.011126153525746073,0.8991023103394467,0.011277101291230643,0.8986341823551125,0.011354555203816266 +flat_mae,patch,logistic,abide_dx,63,0.3593813663804626,test,0.6290322580645161,0.043533019988790486,0.6242424242424243,0.0442133948421959,0.6239495798319328,0.04397342653657019 +flat_mae,patch,logistic,abide_dx,64,2.782559402207126,train,0.9857549857549858,0.004339378331084972,0.9856119236571128,0.004381903137794096,0.9858988556662975,0.004347872579010036 +flat_mae,patch,logistic,abide_dx,64,2.782559402207126,test,0.6451612903225806,0.04439893409300738,0.6428384393820372,0.04456721612654003,0.6433823529411764,0.044483542461023914 +flat_mae,patch,logistic,abide_dx,65,0.046415888336127774,train,0.8076923076923077,0.014123585012549322,0.8044055700142201,0.014450784765223811,0.8028423772609818,0.014489993730957832 +flat_mae,patch,logistic,abide_dx,65,0.046415888336127774,test,0.6854838709677419,0.04015408343161491,0.6761968530297957,0.04206325037592033,0.6754201680672269,0.04103295437295641 +flat_mae,patch,logistic,abide_dx,66,0.3593813663804626,train,0.9045584045584045,0.010937342345632761,0.9032705869287578,0.011123256796247313,0.9022148394241418,0.011248118361926317 +flat_mae,patch,logistic,abide_dx,66,0.3593813663804626,test,0.6370967741935484,0.04254451057201968,0.6351748937561295,0.04278553970284203,0.6360294117647058,0.04280428937335435 +flat_mae,patch,logistic,abide_dx,67,2.782559402207126,train,0.9928774928774928,0.00332311971646558,0.9928038822132881,0.0033555097589764602,0.9929494278331488,0.003274130933885066 +flat_mae,patch,logistic,abide_dx,67,2.782559402207126,test,0.7258064516129032,0.041284979493004144,0.7246603970741902,0.04144660428568821,0.7263655462184874,0.04145082541029077 +flat_mae,patch,logistic,abide_dx,68,0.3593813663804626,train,0.8945868945868946,0.011580661811365571,0.8935282350626352,0.011675748042809388,0.8937615356220008,0.011647227587132996 +flat_mae,patch,logistic,abide_dx,68,0.3593813663804626,test,0.7016129032258065,0.04011721574286304,0.699246148803671,0.040406435629701566,0.6995798319327731,0.04024095640096194 +flat_mae,patch,logistic,abide_dx,69,0.3593813663804626,train,0.9031339031339032,0.010875271577616651,0.9022700471698113,0.010962695366663878,0.9029900332225913,0.010967717335306104 +flat_mae,patch,logistic,abide_dx,69,0.3593813663804626,test,0.6935483870967742,0.04264766231502643,0.6883597883597883,0.04359461244392388,0.6875,0.043157079869111804 +flat_mae,patch,logistic,abide_dx,70,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,70,166.81005372000556,test,0.7096774193548387,0.04176442780358264,0.7047619047619047,0.04265889937440716,0.703781512605042,0.042300080534327336 +flat_mae,patch,logistic,abide_dx,71,2.782559402207126,train,0.99002849002849,0.003718157202350129,0.98993121507736,0.003751273586466972,0.9903654485049834,0.0036324235554884244 +flat_mae,patch,logistic,abide_dx,71,2.782559402207126,test,0.6935483870967742,0.03855513505521555,0.6883597883597883,0.03952038488628483,0.6875,0.03927049275679046 +flat_mae,patch,logistic,abide_dx,72,0.3593813663804626,train,0.9045584045584045,0.01052823397746111,0.9033342033816792,0.010682963867957062,0.9025101513473606,0.010771801789722575 +flat_mae,patch,logistic,abide_dx,72,0.3593813663804626,test,0.6129032258064516,0.044445183649477644,0.6063492063492064,0.04530350272314058,0.60609243697479,0.04481971368523324 +flat_mae,patch,logistic,abide_dx,73,0.3593813663804626,train,0.9102564102564102,0.010289886409643099,0.9092753474537156,0.010408776961084582,0.9091546696197859,0.010471459042203276 +flat_mae,patch,logistic,abide_dx,73,0.3593813663804626,test,0.5564516129032258,0.043613821807467035,0.5498646953996436,0.04455020590177814,0.5498949579831933,0.04422492554076517 +flat_mae,patch,logistic,abide_dx,74,2.782559402207126,train,0.9786324786324786,0.005314357206007869,0.978411646639864,0.005366454589075333,0.9785529715762273,0.005340363090037279 +flat_mae,patch,logistic,abide_dx,74,2.782559402207126,test,0.6451612903225806,0.041691208519854556,0.6418067226890756,0.042392740884674415,0.6418067226890756,0.04226016441685707 +flat_mae,patch,logistic,abide_dx,75,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,75,166.81005372000556,test,0.6370967741935484,0.04103214077382302,0.6330637206549615,0.04178731625360229,0.6328781512605042,0.041561350724096655 +flat_mae,patch,logistic,abide_dx,76,0.3593813663804626,train,0.9031339031339032,0.011643390156922175,0.9020454396217743,0.011797603320378451,0.9018087855297157,0.011901326173807063 +flat_mae,patch,logistic,abide_dx,76,0.3593813663804626,test,0.6451612903225806,0.04304247351785047,0.6405797101449275,0.04400386771146085,0.6402310924369747,0.043646623644762364 +flat_mae,patch,logistic,abide_dx,77,2.782559402207126,train,0.9857549857549858,0.004652988627014222,0.9856035437430786,0.0047026587234726405,0.9856035437430786,0.004734642469591328 +flat_mae,patch,logistic,abide_dx,77,2.782559402207126,test,0.5725806451612904,0.044763222603101054,0.5723303182143554,0.044980176088642125,0.5756302521008403,0.04494695733798361 +flat_mae,patch,logistic,abide_dx,78,2.782559402207126,train,0.9957264957264957,0.002387952203867736,0.995679778450177,0.002415040399791409,0.9955334071613142,0.0025087787389945 +flat_mae,patch,logistic,abide_dx,78,2.782559402207126,test,0.5564516129032258,0.04514436318717369,0.5550336008351275,0.04537705264898889,0.5561974789915967,0.045559153873392856 +flat_mae,patch,logistic,abide_dx,79,2.782559402207126,train,0.9886039886039886,0.00404824257578156,0.988482834994463,0.004091337936075368,0.988482834994463,0.004110914266696194 +flat_mae,patch,logistic,abide_dx,79,2.782559402207126,test,0.5725806451612904,0.04379505707192769,0.5643931861867832,0.04493364271585374,0.5646008403361344,0.04427257634191281 +flat_mae,patch,logistic,abide_dx,80,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,80,1291.5496650148827,test,0.6370967741935484,0.04588966487512974,0.6330637206549615,0.04649687245741384,0.6328781512605042,0.04627877079844874 +flat_mae,patch,logistic,abide_dx,81,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,81,166.81005372000556,test,0.6451612903225806,0.04229546485800375,0.6288435374149659,0.045836952011695783,0.6307773109243697,0.043320064075994466 +flat_mae,patch,logistic,abide_dx,82,0.046415888336127774,train,0.7877492877492878,0.014476652000291914,0.7834423388674605,0.014869966497644145,0.7815060908084164,0.014822546847837783 +flat_mae,patch,logistic,abide_dx,82,0.046415888336127774,test,0.6935483870967742,0.04186313858908117,0.6895915678524374,0.04250580725397456,0.6890756302521008,0.042339128334694456 +flat_mae,patch,logistic,abide_dx,83,0.3593813663804626,train,0.9002849002849003,0.01105644342425082,0.8991644231400617,0.011182575965202989,0.8989294942783315,0.011242821536627015 +flat_mae,patch,logistic,abide_dx,83,0.3593813663804626,test,0.6209677419354839,0.044305400600519664,0.6209430894308943,0.044348260833741715,0.6260504201680672,0.04422991691018329 +flat_mae,patch,logistic,abide_dx,84,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,84,166.81005372000556,test,0.5887096774193549,0.04400600659029372,0.5884687967723043,0.04412922848356856,0.5919117647058824,0.044500924947283506 +flat_mae,patch,logistic,abide_dx,85,0.3593813663804626,train,0.896011396011396,0.011293431122254059,0.8949366803140049,0.011417134590207942,0.8950535252860834,0.01146865141284913 +flat_mae,patch,logistic,abide_dx,85,0.3593813663804626,test,0.717741935483871,0.03844998914086144,0.7123351229535362,0.03957811297783097,0.7111344537815126,0.03912306716448346 +flat_mae,patch,logistic,abide_dx,86,0.3593813663804626,train,0.9045584045584045,0.011098785990469984,0.9033961489088576,0.011259382437795295,0.9028054632705795,0.01137091860572403 +flat_mae,patch,logistic,abide_dx,86,0.3593813663804626,test,0.6532258064516129,0.04405684059159975,0.6480760345851759,0.045001585968183405,0.6475840336134454,0.044548429348024055 +flat_mae,patch,logistic,abide_dx,87,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,87,21.54434690031882,test,0.6532258064516129,0.04650723316574068,0.6513893429225237,0.04663183429106865,0.6523109243697479,0.046625992347429986 +flat_mae,patch,logistic,abide_dx,88,2.782559402207126,train,0.9871794871794872,0.004125193799831684,0.9870469879839183,0.004166182228556281,0.9871908453303803,0.004130348499988254 +flat_mae,patch,logistic,abide_dx,88,2.782559402207126,test,0.6129032258064516,0.04261522300833292,0.6092436974789917,0.043136229278776125,0.6092436974789917,0.04295999131463211 +flat_mae,patch,logistic,abide_dx,89,0.3593813663804626,train,0.9045584045584045,0.011162224097008091,0.9033961489088576,0.011318381767391859,0.9028054632705795,0.01141211367543037 +flat_mae,patch,logistic,abide_dx,89,0.3593813663804626,test,0.6129032258064516,0.04364148948625108,0.6125,0.04363980283703338,0.615546218487395,0.043768439008284005 +flat_mae,patch,logistic,abide_dx,90,0.3593813663804626,train,0.9074074074074074,0.010414159997420791,0.9064504687727442,0.010511984356717075,0.9065706902916205,0.010515195517851251 +flat_mae,patch,logistic,abide_dx,90,0.3593813663804626,test,0.6370967741935484,0.042497781052436755,0.626380984265149,0.04398665750159167,0.6265756302521008,0.04285402869874927 +flat_mae,patch,logistic,abide_dx,91,2.782559402207126,train,0.9843304843304843,0.004940844533907238,0.9841591876506488,0.004995556739886136,0.984016242155777,0.005040530257355461 +flat_mae,patch,logistic,abide_dx,91,2.782559402207126,test,0.6451612903225806,0.042869329321346024,0.6450689565443664,0.042900846474274744,0.6496848739495797,0.04282234997887301 +flat_mae,patch,logistic,abide_dx,92,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,92,21.54434690031882,test,0.6209677419354839,0.04479416155560122,0.6167554415729598,0.04527361273509786,0.6165966386554622,0.04497636761614783 +flat_mae,patch,logistic,abide_dx,93,0.3593813663804626,train,0.9002849002849003,0.011555999474494372,0.8991644231400617,0.011691297703237801,0.8989294942783315,0.011738990059840653 +flat_mae,patch,logistic,abide_dx,93,0.3593813663804626,test,0.5725806451612904,0.045861538321238494,0.5703170970905524,0.04590624496519968,0.5709033613445378,0.04581887673692179 +flat_mae,patch,logistic,abide_dx,94,0.3593813663804626,train,0.915954415954416,0.010315365144386733,0.9149309370988447,0.010465683416664016,0.9143226282761167,0.010585693478314699 +flat_mae,patch,logistic,abide_dx,94,0.3593813663804626,test,0.7016129032258065,0.04041039148355679,0.699246148803671,0.04084565093021231,0.6995798319327731,0.040880309212909895 +flat_mae,patch,logistic,abide_dx,95,2.782559402207126,train,0.9871794871794872,0.0042491232336187255,0.9870469879839183,0.004290954585512511,0.9871908453303803,0.004248809170054556 +flat_mae,patch,logistic,abide_dx,95,2.782559402207126,test,0.7096774193548387,0.03949892647285246,0.7019230769230769,0.041772342906047165,0.7006302521008403,0.04086829799771626 +flat_mae,patch,logistic,abide_dx,96,0.3593813663804626,train,0.9131054131054132,0.010240624128713849,0.9122073630021137,0.010354681402633445,0.912329272794389,0.010430819489097028 +flat_mae,patch,logistic,abide_dx,96,0.3593813663804626,test,0.5564516129032258,0.04380646052068892,0.5541026479241582,0.044220853981366486,0.5546218487394958,0.044262088478968314 +flat_mae,patch,logistic,abide_dx,97,10000.0,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,97,10000.0,test,0.6370967741935484,0.043874774502772024,0.6283716283716283,0.04526967984344464,0.6281512605042017,0.044467293578670124 +flat_mae,patch,logistic,abide_dx,98,0.046415888336127774,train,0.801994301994302,0.01463749902781009,0.798610179496123,0.014993930244554487,0.7970837947582133,0.015020302570616258 +flat_mae,patch,logistic,abide_dx,98,0.046415888336127774,test,0.6612903225806451,0.042768451908714845,0.6522435897435898,0.044540229382224746,0.6517857142857143,0.043530702908137216 +flat_mae,patch,logistic,abide_dx,99,0.3593813663804626,train,0.8945868945868946,0.010895109522087573,0.8934662236987818,0.011015777573858888,0.8934662236987818,0.011077894108877507 +flat_mae,patch,logistic,abide_dx,99,0.3593813663804626,test,0.6612903225806451,0.041067350965171424,0.6580882352941176,0.04165600238770201,0.6580882352941176,0.04174015237184777 +flat_mae,patch,logistic,abide_dx,100,0.3593813663804626,train,0.9102564102564102,0.010974348619722763,0.9091635430038512,0.011124517085227952,0.9085640457733482,0.011191257848674451 +flat_mae,patch,logistic,abide_dx,100,0.3593813663804626,test,0.6532258064516129,0.04249586807361234,0.6465831510572015,0.043452175022067246,0.6460084033613445,0.04298222298821884 diff --git a/input_space_v3/flat_lr1e-3_1/eval_v2/abide_dx__patch__logistic/log.txt b/input_space_v3/flat_lr1e-3_1/eval_v2/abide_dx__patch__logistic/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..91eacdfeb592cfbde43e0482e6596b31dd12754e --- /dev/null +++ b/input_space_v3/flat_lr1e-3_1/eval_v2/abide_dx__patch__logistic/log.txt @@ -0,0 +1,252 @@ +fMRI foundation model logistic probe eval +version: 0.1.dev86+gf97f52698 +sha: bcce2b486277d3a5b520775efd9cdf1a2affce36, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-04-08 21:55:17 +config: +output_root: experiments/input_space_v3/output +name_prefix: eval_logistic +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_1; eval v2 (abide_dx patch logistic) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: input_space_v3/flat_lr1e-3_1/eval_v2/abide_dx__patch__logistic +model: flat_mae +representation: patch +dataset: abide_dx +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/abide_dx__patch__logistic +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=True, reg_tokens=0, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: abide_dx (flat) +train (n=578): +HFDataset( + dataset=Dataset({ + features: ['sub', 'site', 'dataset', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 578 +}), + labels=['Autism' 'Control'], + counts=[260 318] +) + +validation (n=124): +HFDataset( + dataset=Dataset({ + features: ['sub', 'site', 'dataset', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 124 +}), + labels=['Autism' 'Control'], + counts=[54 70] +) + +test (n=124): +HFDataset( + dataset=Dataset({ + features: ['sub', 'site', 'dataset', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 124 +}), + labels=['Autism' 'Control'], + counts=[57 67] +) + +extracting features for all splits +extract (train) [ 0/289] eta: 0:24:42 time: 5.1306 data: 4.5271 max mem: 2698 +extract (train) [ 20/289] eta: 0:06:15 time: 1.2082 data: 1.0510 max mem: 2851 +extract (train) [ 40/289] eta: 0:03:24 time: 0.2208 data: 0.0761 max mem: 2851 +extract (train) [ 60/289] eta: 0:02:22 time: 0.2137 data: 0.0738 max mem: 2851 +extract (train) [ 80/289] eta: 0:01:49 time: 0.2216 data: 0.0819 max mem: 2851 +extract (train) [100/289] eta: 0:01:27 time: 0.2063 data: 0.0708 max mem: 2851 +extract (train) [120/289] eta: 0:01:10 time: 0.1822 data: 0.0586 max mem: 2851 +extract (train) [140/289] eta: 0:00:57 time: 0.1937 data: 0.0657 max mem: 2851 +extract (train) [160/289] eta: 0:00:46 time: 0.2002 data: 0.0679 max mem: 2851 +extract (train) [180/289] eta: 0:00:37 time: 0.2045 data: 0.0706 max mem: 2851 +extract (train) [200/289] eta: 0:00:29 time: 0.2037 data: 0.0707 max mem: 2851 +extract (train) [220/289] eta: 0:00:21 time: 0.1978 data: 0.0671 max mem: 2851 +extract (train) [240/289] eta: 0:00:15 time: 0.1990 data: 0.0690 max mem: 2851 +extract (train) [260/289] eta: 0:00:08 time: 0.2367 data: 0.0870 max mem: 2851 +extract (train) [280/289] eta: 0:00:02 time: 0.1747 data: 0.0560 max mem: 2851 +extract (train) [288/289] eta: 0:00:00 time: 0.1734 data: 0.0539 max mem: 2851 +extract (train) Total time: 0:01:24 (0.2917 s / it) +extract (validation) [ 0/62] eta: 0:04:48 time: 4.6580 data: 4.3749 max mem: 2851 +extract (validation) [20/62] eta: 0:00:19 time: 0.2573 data: 0.0996 max mem: 2851 +extract (validation) [40/62] eta: 0:00:07 time: 0.1762 data: 0.0539 max mem: 2851 +extract (validation) [60/62] eta: 0:00:00 time: 0.1741 data: 0.0557 max mem: 2851 +extract (validation) [61/62] eta: 0:00:00 time: 0.1733 data: 0.0554 max mem: 2851 +extract (validation) Total time: 0:00:17 (0.2786 s / it) +extract (test) [ 0/62] eta: 0:04:19 time: 4.1779 data: 4.0099 max mem: 2851 +extract (test) [20/62] eta: 0:00:18 time: 0.2584 data: 0.1005 max mem: 2851 +extract (test) [40/62] eta: 0:00:07 time: 0.1911 data: 0.0638 max mem: 2851 +extract (test) [60/62] eta: 0:00:00 time: 0.1612 data: 0.0498 max mem: 2851 +extract (test) [61/62] eta: 0:00:00 time: 0.1599 data: 0.0486 max mem: 2851 +extract (test) Total time: 0:00:17 (0.2748 s / it) +feature extraction time: 0:01:58 +train features: (578, 768) +validation features: (124, 768) +test features: (124, 768) +evaluating fixed splits +eval results (fixed splits): + +| model | repr | clf | dataset | trial | C | split | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|---------:|:--------|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | abide_dx | | 0.046416 | train | 0.81054 | 0.014134 | 0.80745 | 0.014372 | 0.80613 | 0.014341 | +| flat_mae | patch | logistic | abide_dx | | 0.046416 | test | 0.59677 | 0.043693 | 0.58995 | 0.045155 | 0.59021 | 0.044405 | + + +evaluating random splits (n=100) +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 1, "C": 166.81005372000556, "split": "test", "acc": 0.5806451612903226, "acc_std": 0.04500760428292359, "f1": 0.5796610169491525, "f1_std": 0.045268674344655736, "bacc": 0.58140756302521, "bacc_std": 0.045390134425310195} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 2, "C": 0.3593813663804626, "split": "test", "acc": 0.7096774193548387, "acc_std": 0.04090117464583321, "f1": 0.7089960886571056, "f1_std": 0.040970210420567574, "bacc": 0.7116596638655461, "bacc_std": 0.04081760143473344} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 3, "C": 2.782559402207126, "split": "test", "acc": 0.6532258064516129, "acc_std": 0.04195972934346077, "f1": 0.6480760345851759, "f1_std": 0.04267420758771784, "bacc": 0.6475840336134454, "bacc_std": 0.04238115239191262} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 4, "C": 21.54434690031882, "split": "test", "acc": 0.717741935483871, "acc_std": 0.03795159576655358, "f1": 0.7168395641678085, "f1_std": 0.03804069145833692, "bacc": 0.7190126050420168, "bacc_std": 0.03796853923882177} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 5, "C": 2.782559402207126, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.043714054655244056, "f1": 0.6092436974789917, "f1_std": 0.04436966032022113, "bacc": 0.6092436974789917, "bacc_std": 0.044191476889235796} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 6, "C": 0.046415888336127774, "split": "test", "acc": 0.5725806451612904, "acc_std": 0.04601850903470598, "f1": 0.5599598259122867, "f1_std": 0.047899641454191524, "bacc": 0.5614495798319328, "bacc_std": 0.04665392109304478} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 7, "C": 2.782559402207126, "split": "test", "acc": 0.6612903225806451, "acc_std": 0.04103186181082759, "f1": 0.6555555555555556, "f1_std": 0.042137600858448074, "bacc": 0.654936974789916, "bacc_std": 0.041728325791099675} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 8, "C": 1291.5496650148827, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.039961284593831276, "f1": 0.607905138339921, "f1_std": 0.040465388095375115, "bacc": 0.6076680672268908, "bacc_std": 0.04029412690258479} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 9, "C": 21.54434690031882, "split": "test", "acc": 0.6854838709677419, "acc_std": 0.04185046903661664, "f1": 0.6761968530297957, "f1_std": 0.04377035349960309, "bacc": 0.6754201680672269, "bacc_std": 0.042744054380805495} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 10, "C": 0.3593813663804626, "split": "test", "acc": 0.6935483870967742, "acc_std": 0.0401041665258952, "f1": 0.6915422885572139, "f1_std": 0.04046645807385967, "bacc": 0.6922268907563025, "bacc_std": 0.04067784913962407} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 11, "C": 10000.0, "split": "test", "acc": 0.6209677419354839, "acc_std": 0.04280549139599316, "f1": 0.6197559861681998, "f1_std": 0.042708429896886606, "bacc": 0.6213235294117647, "bacc_std": 0.04266040238895434} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 12, "C": 0.046415888336127774, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.04350696656212754, "f1": 0.6045708211533352, "f1_std": 0.044632274209381165, "bacc": 0.6045168067226891, "bacc_std": 0.043953799122527615} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 13, "C": 0.046415888336127774, "split": "test", "acc": 0.6370967741935484, "acc_std": 0.04319886919454981, "f1": 0.6330637206549615, "f1_std": 0.04365651777997638, "bacc": 0.6328781512605042, "bacc_std": 0.04352180701148341} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 14, "C": 2.782559402207126, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.04387422900591739, "f1": 0.6025641025641025, "f1_std": 0.045727603351582116, "bacc": 0.6029411764705883, "bacc_std": 0.04462227992153873} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 15, "C": 0.046415888336127774, "split": "test", "acc": 0.6774193548387096, "acc_std": 0.04243293968660964, "f1": 0.6743697478991597, "f1_std": 0.04313820079756886, "bacc": 0.6743697478991597, "bacc_std": 0.04323833955258539} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 16, "C": 0.3593813663804626, "split": "test", "acc": 0.6370967741935484, "acc_std": 0.042197725328420484, "f1": 0.626380984265149, "f1_std": 0.04361030127701566, "bacc": 0.6265756302521008, "bacc_std": 0.042517544107308035} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 17, "C": 10000.0, "split": "test", "acc": 0.6290322580645161, "acc_std": 0.04374058840346541, "f1": 0.6227513227513227, "f1_std": 0.04484059350618811, "bacc": 0.6223739495798319, "bacc_std": 0.044344495752018785} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 18, "C": 0.046415888336127774, "split": "test", "acc": 0.6693548387096774, "acc_std": 0.0412805274419998, "f1": 0.6553454003118433, "f1_std": 0.04437126263063947, "bacc": 0.6559873949579832, "bacc_std": 0.042336451997234535} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 19, "C": 0.3593813663804626, "split": "test", "acc": 0.5403225806451613, "acc_std": 0.045518815219883005, "f1": 0.5292707292707293, "f1_std": 0.04728234805582466, "bacc": 0.5304621848739496, "bacc_std": 0.046187937227068786} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 20, "C": 0.3593813663804626, "split": "test", "acc": 0.6532258064516129, "acc_std": 0.04168241256416925, "f1": 0.6480760345851759, "f1_std": 0.0425700564502607, "bacc": 0.6475840336134454, "bacc_std": 0.04234312125376591} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 21, "C": 2.782559402207126, "split": "test", "acc": 0.5967741935483871, "acc_std": 0.04354992828814056, "f1": 0.5963541666666667, "f1_std": 0.04350507253083394, "bacc": 0.5992647058823529, "bacc_std": 0.04333105013566372} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 22, "C": 2.782559402207126, "split": "test", "acc": 0.6290322580645161, "acc_std": 0.043093426927187206, "f1": 0.6227513227513227, "f1_std": 0.04399200091769339, "bacc": 0.6223739495798319, "bacc_std": 0.04365189986153042} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 23, "C": 2.782559402207126, "split": "test", "acc": 0.6290322580645161, "acc_std": 0.04351999970829252, "f1": 0.6145945945945945, "f1_std": 0.04601078061102287, "bacc": 0.6160714285714286, "bacc_std": 0.04433914490236562} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 24, "C": 166.81005372000556, "split": "test", "acc": 0.6290322580645161, "acc_std": 0.04454618842533899, "f1": 0.6266038229903116, "f1_std": 0.04473246450769769, "bacc": 0.6271008403361344, "bacc_std": 0.04472277931209889} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 25, "C": 0.3593813663804626, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.04292158229663759, "f1": 0.6092436974789917, "f1_std": 0.04338892140778375, "bacc": 0.6092436974789917, "bacc_std": 0.043254547776126494} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 26, "C": 0.3593813663804626, "split": "test", "acc": 0.6290322580645161, "acc_std": 0.04221249697831959, "f1": 0.6169755573462261, "f1_std": 0.04444702268278988, "bacc": 0.6176470588235294, "bacc_std": 0.043081887287489615} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 27, "C": 2.782559402207126, "split": "test", "acc": 0.6048387096774194, "acc_std": 0.04494280096968858, "f1": 0.6035753898349319, "f1_std": 0.04508992925030588, "bacc": 0.6050420168067226, "bacc_std": 0.045242681921609434} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 28, "C": 0.3593813663804626, "split": "test", "acc": 0.6451612903225806, "acc_std": 0.04115583882900507, "f1": 0.6447916666666667, "f1_std": 0.04127173914320862, "bacc": 0.648109243697479, "bacc_std": 0.041366350310244944} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 29, "C": 0.3593813663804626, "split": "test", "acc": 0.7096774193548387, "acc_std": 0.04011249789021766, "f1": 0.7059288537549406, "f1_std": 0.04073449915444729, "bacc": 0.7053571428571428, "bacc_std": 0.04058333383933353} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 30, "C": 0.3593813663804626, "split": "test", "acc": 0.6935483870967742, "acc_std": 0.040086418095320014, "f1": 0.6869519000797236, "f1_std": 0.04158501819825407, "bacc": 0.6859243697478992, "bacc_std": 0.04087519671879717} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 31, "C": 0.046415888336127774, "split": "test", "acc": 0.6693548387096774, "acc_std": 0.04228359238787222, "f1": 0.6667322189446083, "f1_std": 0.04276696138682026, "bacc": 0.6670168067226891, "bacc_std": 0.042763385560810725} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 32, "C": 2.782559402207126, "split": "test", "acc": 0.5967741935483871, "acc_std": 0.04322843937575914, "f1": 0.5915678524374176, "f1_std": 0.04370458807615033, "bacc": 0.5913865546218487, "bacc_std": 0.043567191472364895} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 33, "C": 0.046415888336127774, "split": "test", "acc": 0.6209677419354839, "acc_std": 0.042679881917590624, "f1": 0.6137071651090342, "f1_std": 0.04386567443767284, "bacc": 0.6134453781512605, "bacc_std": 0.04327038065584293} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 34, "C": 0.3593813663804626, "split": "test", "acc": 0.6290322580645161, "acc_std": 0.04278177084639416, "f1": 0.6242424242424243, "f1_std": 0.04351714124760208, "bacc": 0.6239495798319328, "bacc_std": 0.04317404077156884} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 35, "C": 0.046415888336127774, "split": "test", "acc": 0.6774193548387096, "acc_std": 0.04068588269889882, "f1": 0.6732542819499341, "f1_std": 0.04112394206512272, "bacc": 0.6727941176470589, "bacc_std": 0.04088590861535841} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 36, "C": 2.782559402207126, "split": "test", "acc": 0.6451612903225806, "acc_std": 0.04257065804187934, "f1": 0.6356837606837606, "f1_std": 0.044412917832733344, "bacc": 0.6355042016806722, "bacc_std": 0.043398175983400275} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 37, "C": 0.3593813663804626, "split": "test", "acc": 0.6774193548387096, "acc_std": 0.040684373686058484, "f1": 0.6760710553814002, "f1_std": 0.041049849640820466, "bacc": 0.6775210084033614, "bacc_std": 0.04127988263080961} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 38, "C": 2.782559402207126, "split": "test", "acc": 0.6209677419354839, "acc_std": 0.04269962604656074, "f1": 0.6153389215233318, "f1_std": 0.04352115068224644, "bacc": 0.6150210084033614, "bacc_std": 0.04319636657761545} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 39, "C": 0.3593813663804626, "split": "test", "acc": 0.6290322580645161, "acc_std": 0.04120784352967629, "f1": 0.6274817136886102, "f1_std": 0.041225406886145184, "bacc": 0.6286764705882353, "bacc_std": 0.0412760644404526} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 40, "C": 0.046415888336127774, "split": "test", "acc": 0.5564516129032258, "acc_std": 0.042135290129505544, "f1": 0.5376584638329605, "f1_std": 0.045463481645789845, "bacc": 0.542016806722689, "bacc_std": 0.043050270334791106} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 41, "C": 2.782559402207126, "split": "test", "acc": 0.6370967741935484, "acc_std": 0.04512498540733822, "f1": 0.6351748937561295, "f1_std": 0.045492566368562554, "bacc": 0.6360294117647058, "bacc_std": 0.04539016900465371} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 42, "C": 2.782559402207126, "split": "test", "acc": 0.6048387096774194, "acc_std": 0.04634787924500846, "f1": 0.6017043592264831, "f1_std": 0.04676741748226135, "bacc": 0.601890756302521, "bacc_std": 0.046704989390403476} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 43, "C": 166.81005372000556, "split": "test", "acc": 0.6693548387096774, "acc_std": 0.043539592899381974, "f1": 0.6667322189446083, "f1_std": 0.04383511895418788, "bacc": 0.6670168067226891, "bacc_std": 0.043742443068532096} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 44, "C": 0.005994842503189409, "split": "test", "acc": 0.5887096774193549, "acc_std": 0.04096107070396721, "f1": 0.5649122807017544, "f1_std": 0.04482951922838205, "bacc": 0.5714285714285714, "bacc_std": 0.041758915422843663} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 45, "C": 0.3593813663804626, "split": "test", "acc": 0.6774193548387096, "acc_std": 0.04204589682913773, "f1": 0.671957671957672, "f1_std": 0.0430017896233825, "bacc": 0.671218487394958, "bacc_std": 0.04265955982436926} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 46, "C": 0.3593813663804626, "split": "test", "acc": 0.5887096774193549, "acc_std": 0.04330576379582337, "f1": 0.5880398671096345, "f1_std": 0.04341151013090361, "bacc": 0.5903361344537814, "bacc_std": 0.04348969713134549} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 47, "C": 0.046415888336127774, "split": "test", "acc": 0.6451612903225806, "acc_std": 0.040258387612433826, "f1": 0.6356837606837606, "f1_std": 0.04190534824433022, "bacc": 0.6355042016806722, "bacc_std": 0.040994363682638604} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 48, "C": 10000.0, "split": "test", "acc": 0.5887096774193549, "acc_std": 0.044577809069024255, "f1": 0.5880398671096345, "f1_std": 0.04480948148768099, "bacc": 0.5903361344537814, "bacc_std": 0.04499543582286021} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 49, "C": 0.3593813663804626, "split": "test", "acc": 0.5887096774193549, "acc_std": 0.04420880358317768, "f1": 0.5880398671096345, "f1_std": 0.04433098214476621, "bacc": 0.5903361344537814, "bacc_std": 0.04464262999200738} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 50, "C": 0.005994842503189409, "split": "test", "acc": 0.5483870967741935, "acc_std": 0.044168143745875216, "f1": 0.5276190476190477, "f1_std": 0.04655231050191952, "bacc": 0.5330882352941176, "bacc_std": 0.044554092970338605} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 51, "C": 0.3593813663804626, "split": "test", "acc": 0.5887096774193549, "acc_std": 0.04474809828012611, "f1": 0.5765651155005022, "f1_std": 0.04703476077404137, "bacc": 0.5777310924369747, "bacc_std": 0.045463635051972845} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 52, "C": 2.782559402207126, "split": "test", "acc": 0.7016129032258065, "acc_std": 0.04168472172120123, "f1": 0.6958971299794525, "f1_std": 0.04289468437095952, "bacc": 0.6948529411764706, "bacc_std": 0.04255500728886321} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 53, "C": 0.046415888336127774, "split": "test", "acc": 0.6612903225806451, "acc_std": 0.044127791319092245, "f1": 0.6539994685091681, "f1_std": 0.04543296113480199, "bacc": 0.6533613445378151, "bacc_std": 0.04478989133176045} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 54, "C": 0.3593813663804626, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.04359238816503772, "f1": 0.6025641025641025, "f1_std": 0.045220145438597176, "bacc": 0.6029411764705883, "bacc_std": 0.04422382694548001} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 55, "C": 2.782559402207126, "split": "test", "acc": 0.5967741935483871, "acc_std": 0.04341224537970119, "f1": 0.5915678524374176, "f1_std": 0.043843828572623575, "bacc": 0.5913865546218487, "bacc_std": 0.04357448278640143} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 56, "C": 166.81005372000556, "split": "test", "acc": 0.6370967741935484, "acc_std": 0.042056574552135274, "f1": 0.6330637206549615, "f1_std": 0.04246872565404776, "bacc": 0.6328781512605042, "bacc_std": 0.042301077373325516} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 57, "C": 1291.5496650148827, "split": "test", "acc": 0.6290322580645161, "acc_std": 0.04292023371346817, "f1": 0.6266038229903116, "f1_std": 0.04324340816290291, "bacc": 0.6271008403361344, "bacc_std": 0.043194322813753516} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 58, "C": 0.3593813663804626, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.04181315594888559, "f1": 0.6092436974789917, "f1_std": 0.042382105168384095, "bacc": 0.6092436974789917, "bacc_std": 0.04229353006876125} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 59, "C": 0.005994842503189409, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.0460022479430827, "f1": 0.6112852664576802, "f1_std": 0.046072522610990936, "bacc": 0.6123949579831933, "bacc_std": 0.0461153932682332} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 60, "C": 0.3593813663804626, "split": "test", "acc": 0.6451612903225806, "acc_std": 0.04337354087305768, "f1": 0.6391534391534391, "f1_std": 0.04470860130929421, "bacc": 0.6386554621848739, "bacc_std": 0.04431053143157829} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 61, "C": 0.3593813663804626, "split": "test", "acc": 0.5645161290322581, "acc_std": 0.04402746044996529, "f1": 0.555142173797502, "f1_std": 0.045292154290839, "bacc": 0.555672268907563, "bacc_std": 0.0445118703664962} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 62, "C": 0.046415888336127774, "split": "test", "acc": 0.5564516129032258, "acc_std": 0.04429313890442, "f1": 0.5498646953996436, "f1_std": 0.04504732460952543, "bacc": 0.5498949579831933, "bacc_std": 0.044703467259195884} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 63, "C": 0.3593813663804626, "split": "test", "acc": 0.6290322580645161, "acc_std": 0.043533019988790486, "f1": 0.6242424242424243, "f1_std": 0.0442133948421959, "bacc": 0.6239495798319328, "bacc_std": 0.04397342653657019} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 64, "C": 2.782559402207126, "split": "test", "acc": 0.6451612903225806, "acc_std": 0.04439893409300738, "f1": 0.6428384393820372, "f1_std": 0.04456721612654003, "bacc": 0.6433823529411764, "bacc_std": 0.044483542461023914} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 65, "C": 0.046415888336127774, "split": "test", "acc": 0.6854838709677419, "acc_std": 0.04015408343161491, "f1": 0.6761968530297957, "f1_std": 0.04206325037592033, "bacc": 0.6754201680672269, "bacc_std": 0.04103295437295641} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 66, "C": 0.3593813663804626, "split": "test", "acc": 0.6370967741935484, "acc_std": 0.04254451057201968, "f1": 0.6351748937561295, "f1_std": 0.04278553970284203, "bacc": 0.6360294117647058, "bacc_std": 0.04280428937335435} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 67, "C": 2.782559402207126, "split": "test", "acc": 0.7258064516129032, "acc_std": 0.041284979493004144, "f1": 0.7246603970741902, "f1_std": 0.04144660428568821, "bacc": 0.7263655462184874, "bacc_std": 0.04145082541029077} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 68, "C": 0.3593813663804626, "split": "test", "acc": 0.7016129032258065, "acc_std": 0.04011721574286304, "f1": 0.699246148803671, "f1_std": 0.040406435629701566, "bacc": 0.6995798319327731, "bacc_std": 0.04024095640096194} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 69, "C": 0.3593813663804626, "split": "test", "acc": 0.6935483870967742, "acc_std": 0.04264766231502643, "f1": 0.6883597883597883, "f1_std": 0.04359461244392388, "bacc": 0.6875, "bacc_std": 0.043157079869111804} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 70, "C": 166.81005372000556, "split": "test", "acc": 0.7096774193548387, "acc_std": 0.04176442780358264, "f1": 0.7047619047619047, "f1_std": 0.04265889937440716, "bacc": 0.703781512605042, "bacc_std": 0.042300080534327336} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 71, "C": 2.782559402207126, "split": "test", "acc": 0.6935483870967742, "acc_std": 0.03855513505521555, "f1": 0.6883597883597883, "f1_std": 0.03952038488628483, "bacc": 0.6875, "bacc_std": 0.03927049275679046} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 72, "C": 0.3593813663804626, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.044445183649477644, "f1": 0.6063492063492064, "f1_std": 0.04530350272314058, "bacc": 0.60609243697479, "bacc_std": 0.04481971368523324} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 73, "C": 0.3593813663804626, "split": "test", "acc": 0.5564516129032258, "acc_std": 0.043613821807467035, "f1": 0.5498646953996436, "f1_std": 0.04455020590177814, "bacc": 0.5498949579831933, "bacc_std": 0.04422492554076517} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 74, "C": 2.782559402207126, "split": "test", "acc": 0.6451612903225806, "acc_std": 0.041691208519854556, "f1": 0.6418067226890756, "f1_std": 0.042392740884674415, "bacc": 0.6418067226890756, "bacc_std": 0.04226016441685707} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 75, "C": 166.81005372000556, "split": "test", "acc": 0.6370967741935484, "acc_std": 0.04103214077382302, "f1": 0.6330637206549615, "f1_std": 0.04178731625360229, "bacc": 0.6328781512605042, "bacc_std": 0.041561350724096655} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 76, "C": 0.3593813663804626, "split": "test", "acc": 0.6451612903225806, "acc_std": 0.04304247351785047, "f1": 0.6405797101449275, "f1_std": 0.04400386771146085, "bacc": 0.6402310924369747, "bacc_std": 0.043646623644762364} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 77, "C": 2.782559402207126, "split": "test", "acc": 0.5725806451612904, "acc_std": 0.044763222603101054, "f1": 0.5723303182143554, "f1_std": 0.044980176088642125, "bacc": 0.5756302521008403, "bacc_std": 0.04494695733798361} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 78, "C": 2.782559402207126, "split": "test", "acc": 0.5564516129032258, "acc_std": 0.04514436318717369, "f1": 0.5550336008351275, "f1_std": 0.04537705264898889, "bacc": 0.5561974789915967, "bacc_std": 0.045559153873392856} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 79, "C": 2.782559402207126, "split": "test", "acc": 0.5725806451612904, "acc_std": 0.04379505707192769, "f1": 0.5643931861867832, "f1_std": 0.04493364271585374, "bacc": 0.5646008403361344, "bacc_std": 0.04427257634191281} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 80, "C": 1291.5496650148827, "split": "test", "acc": 0.6370967741935484, "acc_std": 0.04588966487512974, "f1": 0.6330637206549615, "f1_std": 0.04649687245741384, "bacc": 0.6328781512605042, "bacc_std": 0.04627877079844874} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 81, "C": 166.81005372000556, "split": "test", "acc": 0.6451612903225806, "acc_std": 0.04229546485800375, "f1": 0.6288435374149659, "f1_std": 0.045836952011695783, "bacc": 0.6307773109243697, "bacc_std": 0.043320064075994466} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 82, "C": 0.046415888336127774, "split": "test", "acc": 0.6935483870967742, "acc_std": 0.04186313858908117, "f1": 0.6895915678524374, "f1_std": 0.04250580725397456, "bacc": 0.6890756302521008, "bacc_std": 0.042339128334694456} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 83, "C": 0.3593813663804626, "split": "test", "acc": 0.6209677419354839, "acc_std": 0.044305400600519664, "f1": 0.6209430894308943, "f1_std": 0.044348260833741715, "bacc": 0.6260504201680672, "bacc_std": 0.04422991691018329} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 84, "C": 166.81005372000556, "split": "test", "acc": 0.5887096774193549, "acc_std": 0.04400600659029372, "f1": 0.5884687967723043, "f1_std": 0.04412922848356856, "bacc": 0.5919117647058824, "bacc_std": 0.044500924947283506} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 85, "C": 0.3593813663804626, "split": "test", "acc": 0.717741935483871, "acc_std": 0.03844998914086144, "f1": 0.7123351229535362, "f1_std": 0.03957811297783097, "bacc": 0.7111344537815126, "bacc_std": 0.03912306716448346} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 86, "C": 0.3593813663804626, "split": "test", "acc": 0.6532258064516129, "acc_std": 0.04405684059159975, "f1": 0.6480760345851759, "f1_std": 0.045001585968183405, "bacc": 0.6475840336134454, "bacc_std": 0.044548429348024055} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 87, "C": 21.54434690031882, "split": "test", "acc": 0.6532258064516129, "acc_std": 0.04650723316574068, "f1": 0.6513893429225237, "f1_std": 0.04663183429106865, "bacc": 0.6523109243697479, "bacc_std": 0.046625992347429986} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 88, "C": 2.782559402207126, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.04261522300833292, "f1": 0.6092436974789917, "f1_std": 0.043136229278776125, "bacc": 0.6092436974789917, "bacc_std": 0.04295999131463211} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 89, "C": 0.3593813663804626, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.04364148948625108, "f1": 0.6125, "f1_std": 0.04363980283703338, "bacc": 0.615546218487395, "bacc_std": 0.043768439008284005} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 90, "C": 0.3593813663804626, "split": "test", "acc": 0.6370967741935484, "acc_std": 0.042497781052436755, "f1": 0.626380984265149, "f1_std": 0.04398665750159167, "bacc": 0.6265756302521008, "bacc_std": 0.04285402869874927} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 91, "C": 2.782559402207126, "split": "test", "acc": 0.6451612903225806, "acc_std": 0.042869329321346024, "f1": 0.6450689565443664, "f1_std": 0.042900846474274744, "bacc": 0.6496848739495797, "bacc_std": 0.04282234997887301} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 92, "C": 21.54434690031882, "split": "test", "acc": 0.6209677419354839, "acc_std": 0.04479416155560122, "f1": 0.6167554415729598, "f1_std": 0.04527361273509786, "bacc": 0.6165966386554622, "bacc_std": 0.04497636761614783} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 93, "C": 0.3593813663804626, "split": "test", "acc": 0.5725806451612904, "acc_std": 0.045861538321238494, "f1": 0.5703170970905524, "f1_std": 0.04590624496519968, "bacc": 0.5709033613445378, "bacc_std": 0.04581887673692179} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 94, "C": 0.3593813663804626, "split": "test", "acc": 0.7016129032258065, "acc_std": 0.04041039148355679, "f1": 0.699246148803671, "f1_std": 0.04084565093021231, "bacc": 0.6995798319327731, "bacc_std": 0.040880309212909895} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 95, "C": 2.782559402207126, "split": "test", "acc": 0.7096774193548387, "acc_std": 0.03949892647285246, "f1": 0.7019230769230769, "f1_std": 0.041772342906047165, "bacc": 0.7006302521008403, "bacc_std": 0.04086829799771626} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 96, "C": 0.3593813663804626, "split": "test", "acc": 0.5564516129032258, "acc_std": 0.04380646052068892, "f1": 0.5541026479241582, "f1_std": 0.044220853981366486, "bacc": 0.5546218487394958, "bacc_std": 0.044262088478968314} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 97, "C": 10000.0, "split": "test", "acc": 0.6370967741935484, "acc_std": 0.043874774502772024, "f1": 0.6283716283716283, "f1_std": 0.04526967984344464, "bacc": 0.6281512605042017, "bacc_std": 0.044467293578670124} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 98, "C": 0.046415888336127774, "split": "test", "acc": 0.6612903225806451, "acc_std": 0.042768451908714845, "f1": 0.6522435897435898, "f1_std": 0.044540229382224746, "bacc": 0.6517857142857143, "bacc_std": 0.043530702908137216} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 99, "C": 0.3593813663804626, "split": "test", "acc": 0.6612903225806451, "acc_std": 0.041067350965171424, "f1": 0.6580882352941176, "f1_std": 0.04165600238770201, "bacc": 0.6580882352941176, "bacc_std": 0.04174015237184777} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 100, "C": 0.3593813663804626, "split": "test", "acc": 0.6532258064516129, "acc_std": 0.04249586807361234, "f1": 0.6465831510572015, "f1_std": 0.043452175022067246, "bacc": 0.6460084033613445, "bacc_std": 0.04298222298821884} +eval results (random splits): + +| model | repr | clf | dataset | split | n_trials | C | C_std | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|-----------:|-------:|--------:|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | abide_dx | train | 100 | 453.79 | 1971.1 | 0.92313 | 0.076365 | 0.92193 | 0.077944 | 0.92152 | 0.078458 | +| flat_mae | patch | logistic | abide_dx | test | 100 | 453.79 | 1971.1 | 0.6346 | 0.044092 | 0.62913 | 0.045206 | 0.62976 | 0.044621 | + + +done! total time: 0:06:30 diff --git a/input_space_v3/flat_lr1e-3_1/eval_v2/adhd200_dx__patch__attn/config.yaml b/input_space_v3/flat_lr1e-3_1/eval_v2/adhd200_dx__patch__attn/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..2f9505805ea00485704dd206035fbabdcb9eab8f --- /dev/null +++ b/input_space_v3/flat_lr1e-3_1/eval_v2/adhd200_dx__patch__attn/config.yaml @@ -0,0 +1,98 @@ +output_root: experiments/input_space_v3/output +name_prefix: eval_probe +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_1; eval v2 (adhd200_dx patch attn) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +dataset_kwargs: {} +classifier_kwargs: + embed_dim: null + dropout: 0.0 + xavier_init: true + norm: true +lr_scale_grid: +- 0.02 +- 0.023 +- 0.028 +- 0.033 +- 0.038 +- 0.045 +- 0.053 +- 0.062 +- 0.074 +- 0.087 +- 0.1 +- 0.12 +- 0.14 +- 0.17 +- 0.2 +- 0.23 +- 0.27 +- 0.32 +- 0.38 +- 0.44 +- 0.52 +- 0.61 +- 0.72 +- 0.85 +- 1 +- 1.2 +- 1.4 +- 1.6 +- 1.9 +- 2.3 +- 2.7 +- 3.1 +- 3.7 +- 4.3 +- 5.1 +- 6 +- 7.1 +- 8.3 +- 9.8 +- 12 +- 14 +- 16 +- 19 +- 22 +- 26 +- 31 +- 36 +- 43 +- 50 +wd_scale_grid: +- 1.0 +num_workers: 8 +prefetch_factor: null +balanced_sampling: false +epochs: 20 +steps_per_epoch: 200 +batch_size: 4 +accum_iter: 4 +lr: 0.0003 +warmup_epochs: 5 +no_decay: false +weight_decay: 0.05 +clip_grad: 1.0 +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +early_stopping: true +amp: true +device: cuda +seed: 4466 +debug: false +wandb: false +wandb_entity: null +wandb_project: fMRI-fm-eval +name: input_space_v3/flat_lr1e-3_1/eval_v2/adhd200_dx__patch__attn +base_lr: 3.0e-05 +model: flat_mae +representation: patch +classifier: attn +dataset: adhd200_dx +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/adhd200_dx__patch__attn +remote_dir: null diff --git a/input_space_v3/flat_lr1e-3_1/eval_v2/adhd200_dx__patch__attn/eval_log.json b/input_space_v3/flat_lr1e-3_1/eval_v2/adhd200_dx__patch__attn/eval_log.json new file mode 100644 index 0000000000000000000000000000000000000000..dee61d87b66c9de2ae13f6701a663f6d41f82135 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_1/eval_v2/adhd200_dx__patch__attn/eval_log.json @@ -0,0 +1 @@ +{"eval/epoch": 9, "eval/id_best": 9, "eval/lr_best": 2.6099999999999997e-05, "eval/wd_best": 0.05, "eval/train/loss": 0.5861364006996155, "eval/train/acc": 0.6877076411960132, "eval/train/acc_std": 0.02712777957672768, "eval/train/f1": 0.6818038686459739, "eval/train/f1_std": 0.0277717116711551, "eval/train/bacc": 0.6814997754827121, "eval/train/bacc_std": 0.027835538654150737, "eval/validation/loss": 0.593696117401123, "eval/validation/acc": 0.796875, "eval/validation/acc_std": 0.048592493954828044, "eval/validation/f1": 0.7881334351922588, "eval/validation/f1_std": 0.05262082445599683, "eval/validation/bacc": 0.7837301587301587, "eval/validation/bacc_std": 0.05147947155355822, "eval/test/loss": 0.7004579901695251, "eval/test/acc": 0.6, "eval/test/acc_std": 0.059916312445288396, "eval/test/f1": 0.588206627680312, "eval/test/f1_std": 0.062207333628680805, "eval/test/bacc": 0.5878378378378378, "eval/test/bacc_std": 0.06145882517266482} diff --git a/input_space_v3/flat_lr1e-3_1/eval_v2/adhd200_dx__patch__attn/eval_log_best.json b/input_space_v3/flat_lr1e-3_1/eval_v2/adhd200_dx__patch__attn/eval_log_best.json new file mode 100644 index 0000000000000000000000000000000000000000..61ad7b3c38b6e7f0035aae71742a0c1198ab5034 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_1/eval_v2/adhd200_dx__patch__attn/eval_log_best.json @@ -0,0 +1 @@ +{"eval/best/epoch": 9, "eval/best/id_best": 9, "eval/best/lr_best": 2.6099999999999997e-05, "eval/best/wd_best": 0.05, "eval/best/train/loss": 0.5861364006996155, "eval/best/train/acc": 0.6877076411960132, "eval/best/train/acc_std": 0.02712777957672768, "eval/best/train/f1": 0.6818038686459739, "eval/best/train/f1_std": 0.0277717116711551, "eval/best/train/bacc": 0.6814997754827121, "eval/best/train/bacc_std": 0.027835538654150737, "eval/best/validation/loss": 0.593696117401123, "eval/best/validation/acc": 0.796875, "eval/best/validation/acc_std": 0.048592493954828044, "eval/best/validation/f1": 0.7881334351922588, "eval/best/validation/f1_std": 0.05262082445599683, "eval/best/validation/bacc": 0.7837301587301587, "eval/best/validation/bacc_std": 0.05147947155355822, "eval/best/test/loss": 0.7004579901695251, "eval/best/test/acc": 0.6, "eval/best/test/acc_std": 0.059916312445288396, "eval/best/test/f1": 0.588206627680312, "eval/best/test/f1_std": 0.062207333628680805, "eval/best/test/bacc": 0.5878378378378378, "eval/best/test/bacc_std": 0.06145882517266482} diff --git a/input_space_v3/flat_lr1e-3_1/eval_v2/adhd200_dx__patch__attn/eval_log_last.json b/input_space_v3/flat_lr1e-3_1/eval_v2/adhd200_dx__patch__attn/eval_log_last.json new file mode 100644 index 0000000000000000000000000000000000000000..36b6b5b259c9d54fb7a062283af1044e1ed66cb4 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_1/eval_v2/adhd200_dx__patch__attn/eval_log_last.json @@ -0,0 +1 @@ +{"eval/last/epoch": 19, "eval/last/id_best": 2, "eval/last/lr_best": 8.4e-06, "eval/last/wd_best": 0.05, "eval/last/train/loss": 0.6143454909324646, "eval/last/train/acc": 0.6511627906976745, "eval/last/train/acc_std": 0.026881177795475556, "eval/last/train/f1": 0.6324016888237551, "eval/last/train/f1_std": 0.029096252093383092, "eval/last/train/bacc": 0.6325101032779524, "eval/last/train/bacc_std": 0.027870054050612398, "eval/last/validation/loss": 0.6090863347053528, "eval/last/validation/acc": 0.78125, "eval/last/validation/acc_std": 0.04931487636859693, "eval/last/validation/f1": 0.7666666666666666, "eval/last/validation/f1_std": 0.055982661945376155, "eval/last/validation/bacc": 0.7619047619047619, "eval/last/validation/bacc_std": 0.05302565849241093, "eval/last/test/loss": 0.693565309047699, "eval/last/test/acc": 0.5692307692307692, "eval/last/test/acc_std": 0.05655059838334863, "eval/last/test/f1": 0.5289855072463768, "eval/last/test/f1_std": 0.06324288256744032, "eval/last/test/bacc": 0.5390926640926641, "eval/last/test/bacc_std": 0.05776449541007152} diff --git a/input_space_v3/flat_lr1e-3_1/eval_v2/adhd200_dx__patch__attn/eval_table.csv b/input_space_v3/flat_lr1e-3_1/eval_v2/adhd200_dx__patch__attn/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..0094a356b1c312012daedc54e1156cea7874491c --- /dev/null +++ b/input_space_v3/flat_lr1e-3_1/eval_v2/adhd200_dx__patch__attn/eval_table.csv @@ -0,0 +1,4 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std,bacc,bacc_std +flat_mae,patch,attn,adhd200_dx,best,9,2.6099999999999997e-05,0.05,9,"[0.087, 1.0]",train,0.5861364006996155,0.6877076411960132,0.02712777957672768,0.6818038686459739,0.0277717116711551,0.6814997754827121,0.027835538654150737 +flat_mae,patch,attn,adhd200_dx,best,9,2.6099999999999997e-05,0.05,9,"[0.087, 1.0]",validation,0.593696117401123,0.796875,0.048592493954828044,0.7881334351922588,0.05262082445599683,0.7837301587301587,0.05147947155355822 +flat_mae,patch,attn,adhd200_dx,best,9,2.6099999999999997e-05,0.05,9,"[0.087, 1.0]",test,0.7004579901695251,0.6,0.059916312445288396,0.588206627680312,0.062207333628680805,0.5878378378378378,0.06145882517266482 diff --git a/input_space_v3/flat_lr1e-3_1/eval_v2/adhd200_dx__patch__attn/eval_table_best.csv b/input_space_v3/flat_lr1e-3_1/eval_v2/adhd200_dx__patch__attn/eval_table_best.csv new file mode 100644 index 0000000000000000000000000000000000000000..0094a356b1c312012daedc54e1156cea7874491c --- /dev/null +++ b/input_space_v3/flat_lr1e-3_1/eval_v2/adhd200_dx__patch__attn/eval_table_best.csv @@ -0,0 +1,4 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std,bacc,bacc_std +flat_mae,patch,attn,adhd200_dx,best,9,2.6099999999999997e-05,0.05,9,"[0.087, 1.0]",train,0.5861364006996155,0.6877076411960132,0.02712777957672768,0.6818038686459739,0.0277717116711551,0.6814997754827121,0.027835538654150737 +flat_mae,patch,attn,adhd200_dx,best,9,2.6099999999999997e-05,0.05,9,"[0.087, 1.0]",validation,0.593696117401123,0.796875,0.048592493954828044,0.7881334351922588,0.05262082445599683,0.7837301587301587,0.05147947155355822 +flat_mae,patch,attn,adhd200_dx,best,9,2.6099999999999997e-05,0.05,9,"[0.087, 1.0]",test,0.7004579901695251,0.6,0.059916312445288396,0.588206627680312,0.062207333628680805,0.5878378378378378,0.06145882517266482 diff --git a/input_space_v3/flat_lr1e-3_1/eval_v2/adhd200_dx__patch__attn/eval_table_last.csv b/input_space_v3/flat_lr1e-3_1/eval_v2/adhd200_dx__patch__attn/eval_table_last.csv new file mode 100644 index 0000000000000000000000000000000000000000..ee3ea1d357533e2950b828bf38a61691f97e615f --- /dev/null +++ b/input_space_v3/flat_lr1e-3_1/eval_v2/adhd200_dx__patch__attn/eval_table_last.csv @@ -0,0 +1,4 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std,bacc,bacc_std +flat_mae,patch,attn,adhd200_dx,last,19,8.4e-06,0.05,2,"[0.028, 1.0]",train,0.6143454909324646,0.6511627906976745,0.026881177795475556,0.6324016888237551,0.029096252093383092,0.6325101032779524,0.027870054050612398 +flat_mae,patch,attn,adhd200_dx,last,19,8.4e-06,0.05,2,"[0.028, 1.0]",validation,0.6090863347053528,0.78125,0.04931487636859693,0.7666666666666666,0.055982661945376155,0.7619047619047619,0.05302565849241093 +flat_mae,patch,attn,adhd200_dx,last,19,8.4e-06,0.05,2,"[0.028, 1.0]",test,0.693565309047699,0.5692307692307692,0.05655059838334863,0.5289855072463768,0.06324288256744032,0.5390926640926641,0.05776449541007152 diff --git a/input_space_v3/flat_lr1e-3_1/eval_v2/adhd200_dx__patch__attn/log.txt b/input_space_v3/flat_lr1e-3_1/eval_v2/adhd200_dx__patch__attn/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..aa79892b876e6be2473dc41da16367a96fd65a81 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_1/eval_v2/adhd200_dx__patch__attn/log.txt @@ -0,0 +1,1194 @@ +fMRI foundation model probe eval +version: 0.1.dev95+g65be98d36 +sha: 28a47a6a336052f679e36c7962a91fe73a2e9637, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-04-24 07:15:12 +config: +output_root: experiments/input_space_v3/output +name_prefix: eval_probe +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_1; eval v2 (adhd200_dx patch attn) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +dataset_kwargs: {} +classifier_kwargs: + embed_dim: null + dropout: 0.0 + xavier_init: true + norm: true +lr_scale_grid: +- 0.02 +- 0.023 +- 0.028 +- 0.033 +- 0.038 +- 0.045 +- 0.053 +- 0.062 +- 0.074 +- 0.087 +- 0.1 +- 0.12 +- 0.14 +- 0.17 +- 0.2 +- 0.23 +- 0.27 +- 0.32 +- 0.38 +- 0.44 +- 0.52 +- 0.61 +- 0.72 +- 0.85 +- 1 +- 1.2 +- 1.4 +- 1.6 +- 1.9 +- 2.3 +- 2.7 +- 3.1 +- 3.7 +- 4.3 +- 5.1 +- 6 +- 7.1 +- 8.3 +- 9.8 +- 12 +- 14 +- 16 +- 19 +- 22 +- 26 +- 31 +- 36 +- 43 +- 50 +wd_scale_grid: +- 1.0 +num_workers: 8 +prefetch_factor: null +balanced_sampling: false +epochs: 20 +steps_per_epoch: 200 +batch_size: 4 +accum_iter: 4 +lr: 0.0003 +warmup_epochs: 5 +no_decay: false +weight_decay: 0.05 +clip_grad: 1.0 +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +early_stopping: true +amp: true +device: cuda +seed: 4466 +debug: false +wandb: false +wandb_entity: null +wandb_project: fMRI-fm-eval +name: input_space_v3/flat_lr1e-3_1/eval_v2/adhd200_dx__patch__attn +base_lr: 3.0e-05 +model: flat_mae +representation: patch +classifier: attn +dataset: adhd200_dx +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/adhd200_dx__patch__attn +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=True, reg_tokens=0, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: adhd200_dx (flat) +train (n=301): +HFDataset( + dataset=Dataset({ + features: ['sub', 'site', 'gender', 'dx', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 301 +}), + labels=['ADHD' 'Control'], + counts=[131 170] +) + +validation (n=64): +HFDataset( + dataset=Dataset({ + features: ['sub', 'site', 'gender', 'dx', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 64 +}), + labels=['ADHD' 'Control'], + counts=[28 36] +) + +test (n=65): +HFDataset( + dataset=Dataset({ + features: ['sub', 'site', 'gender', 'dx', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 65 +}), + labels=['ADHD' 'Control'], + counts=[28 37] +) + +running backbone on example batch to get embedding dim +embedding feature dim (patch): 768 +initializing sweep of classifier heads +classifiers: +ModuleList( + (0-48): 49 x AttnPoolClassifier( + (kv): Linear(in_features=768, out_features=1536, bias=True) + (linear): Linear(in_features=768, out_features=2, bias=True) + ) +) +classifier params (train): 58.0M (58.0M) +setting up optimizer +total batch size: 16 = 4 bs per gpu x 4 accum +lr: 3.00e-04 +full schedule: epochs = 20 (steps = 4000) (decay = True) +warmup: epochs = 5 (steps = 1000) +start training for 20 epochs +train: [0] [ 0/800] eta: 1:01:19 lr: nan time: 4.5999 data: 3.8095 max mem: 24352 +train: [0] [ 20/800] eta: 0:09:51 lr: 0.000001 loss: 0.7109 (0.7184) grad: 0.3794 (0.3165) time: 0.5669 data: 0.0069 max mem: 25051 +train: [0] [ 40/800] eta: 0:08:22 lr: 0.000003 loss: 0.7109 (0.7148) grad: 0.3457 (0.3471) time: 0.5591 data: 0.0033 max mem: 25051 +train: [0] [ 60/800] eta: 0:07:36 lr: 0.000004 loss: 0.7096 (0.7069) grad: 0.2954 (0.3150) time: 0.5265 data: 0.0027 max mem: 25051 +train: [0] [ 80/800] eta: 0:07:40 lr: 0.000006 loss: 0.7073 (0.7072) grad: 0.2954 (0.3237) time: 0.7080 data: 0.2217 max mem: 25051 +train: [0] [100/800] eta: 0:07:13 lr: 0.000007 loss: 0.6987 (0.7043) grad: 0.2313 (0.3041) time: 0.5345 data: 0.0027 max mem: 25051 +train: [0] [120/800] eta: 0:06:50 lr: 0.000009 loss: 0.6950 (0.7025) grad: 0.2500 (0.3028) time: 0.5270 data: 0.0028 max mem: 25051 +train: [0] [140/800] eta: 0:06:31 lr: 0.000010 loss: 0.6987 (0.7046) grad: 0.2946 (0.3008) time: 0.5294 data: 0.0024 max mem: 25051 +train: [0] [160/800] eta: 0:06:38 lr: 0.000012 loss: 0.6916 (0.7007) grad: 0.2552 (0.3032) time: 0.8339 data: 0.2970 max mem: 25051 +train: [0] [180/800] eta: 0:06:19 lr: 0.000013 loss: 0.6950 (0.7013) grad: 0.2552 (0.2991) time: 0.5313 data: 0.0023 max mem: 25051 +train: [0] [200/800] eta: 0:06:03 lr: 0.000015 loss: 0.6888 (0.6982) grad: 0.2311 (0.2910) time: 0.5503 data: 0.0031 max mem: 25051 +train: [0] [220/800] eta: 0:05:47 lr: 0.000016 loss: 0.6813 (0.6980) grad: 0.2401 (0.2950) time: 0.5313 data: 0.0029 max mem: 25051 +train: [0] [240/800] eta: 0:05:43 lr: 0.000018 loss: 0.6924 (0.6987) grad: 0.2359 (0.2924) time: 0.7718 data: 0.2426 max mem: 25051 +train: [0] [260/800] eta: 0:05:27 lr: 0.000019 loss: 0.6924 (0.6989) grad: 0.2347 (0.2883) time: 0.5238 data: 0.0029 max mem: 25051 +train: [0] [280/800] eta: 0:05:12 lr: 0.000021 loss: 0.6990 (0.6977) grad: 0.2347 (0.2795) time: 0.5222 data: 0.0027 max mem: 25051 +train: [0] [300/800] eta: 0:05:05 lr: 0.000022 loss: 0.6867 (0.6913) grad: 0.2070 (0.2812) time: 0.7455 data: 0.2242 max mem: 25051 +train: [0] [320/800] eta: 0:04:53 lr: 0.000024 loss: 0.6764 (0.6866) grad: 0.2379 (0.2815) time: 0.6165 data: 0.0693 max mem: 25051 +train: [0] [340/800] eta: 0:04:38 lr: 0.000025 loss: 0.6764 (0.6881) grad: 0.2379 (0.2777) time: 0.5152 data: 0.0030 max mem: 25051 +train: [0] [360/800] eta: 0:04:23 lr: 0.000027 loss: 0.6698 (0.6885) grad: 0.2547 (0.2801) time: 0.4944 data: 0.0034 max mem: 25051 +train: [0] [380/800] eta: 0:04:14 lr: 0.000028 loss: 0.6770 (0.6859) grad: 0.2547 (0.2837) time: 0.7329 data: 0.2406 max mem: 25051 +train: [0] [400/800] eta: 0:04:01 lr: 0.000030 loss: 0.7000 (0.6868) grad: 0.2370 (0.2844) time: 0.5432 data: 0.0030 max mem: 25051 +train: [0] [420/800] eta: 0:03:47 lr: 0.000031 loss: 0.7125 (0.6871) grad: 0.2415 (0.2855) time: 0.4942 data: 0.0029 max mem: 25051 +train: [0] [440/800] eta: 0:03:34 lr: 0.000033 loss: 0.6521 (0.6846) grad: 0.3028 (0.2886) time: 0.5278 data: 0.0229 max mem: 25051 +train: [0] [460/800] eta: 0:03:24 lr: 0.000034 loss: 0.6567 (0.6842) grad: 0.3236 (0.2909) time: 0.7263 data: 0.2296 max mem: 25051 +train: [0] [480/800] eta: 0:03:11 lr: 0.000036 loss: 0.6573 (0.6830) grad: 0.3236 (0.2902) time: 0.5328 data: 0.0028 max mem: 25051 +train: [0] [500/800] eta: 0:02:58 lr: 0.000037 loss: 0.6573 (0.6826) grad: 0.3236 (0.2916) time: 0.5018 data: 0.0022 max mem: 25051 +train: [0] [520/800] eta: 0:02:45 lr: 0.000039 loss: 0.6573 (0.6823) grad: 0.3157 (0.2927) time: 0.4852 data: 0.0023 max mem: 25051 +train: [0] [540/800] eta: 0:02:35 lr: 0.000040 loss: 0.6573 (0.6827) grad: 0.3173 (0.2977) time: 0.7833 data: 0.2255 max mem: 25051 +train: [0] [560/800] eta: 0:02:22 lr: 0.000042 loss: 0.6457 (0.6807) grad: 0.3478 (0.3002) time: 0.5245 data: 0.0031 max mem: 25051 +train: [0] [580/800] eta: 0:02:10 lr: 0.000043 loss: 0.6457 (0.6791) grad: 0.3449 (0.2991) time: 0.5259 data: 0.0032 max mem: 25051 +train: [0] [600/800] eta: 0:01:59 lr: 0.000045 loss: 0.6699 (0.6807) grad: 0.2353 (0.2947) time: 0.7133 data: 0.2208 max mem: 25051 +train: [0] [620/800] eta: 0:01:47 lr: 0.000046 loss: 0.6686 (0.6793) grad: 0.2077 (0.2941) time: 0.5852 data: 0.0835 max mem: 25051 +train: [0] [640/800] eta: 0:01:34 lr: 0.000048 loss: 0.6686 (0.6787) grad: 0.1818 (0.2909) time: 0.5303 data: 0.0022 max mem: 25051 +train: [0] [660/800] eta: 0:01:22 lr: 0.000049 loss: 0.6686 (0.6790) grad: 0.1816 (0.2878) time: 0.5116 data: 0.0027 max mem: 25051 +train: [0] [680/800] eta: 0:01:11 lr: 0.000051 loss: 0.6664 (0.6810) grad: 0.1955 (0.2875) time: 0.7091 data: 0.2233 max mem: 25051 +train: [0] [700/800] eta: 0:00:59 lr: 0.000052 loss: 0.6718 (0.6792) grad: 0.1955 (0.2859) time: 0.5872 data: 0.0049 max mem: 25051 +train: [0] [720/800] eta: 0:00:47 lr: 0.000054 loss: 0.6718 (0.6793) grad: 0.1955 (0.2840) time: 0.5280 data: 0.0030 max mem: 25051 +train: [0] [740/800] eta: 0:00:35 lr: 0.000055 loss: 0.6572 (0.6777) grad: 0.1955 (0.2829) time: 0.4826 data: 0.0029 max mem: 25051 +train: [0] [760/800] eta: 0:00:23 lr: 0.000057 loss: 0.5834 (0.6763) grad: 0.1867 (0.2803) time: 0.7071 data: 0.2138 max mem: 25051 +train: [0] [780/800] eta: 0:00:11 lr: 0.000058 loss: 0.6176 (0.6758) grad: 0.2044 (0.2793) time: 0.5254 data: 0.0025 max mem: 25051 +train: [0] [799/800] eta: 0:00:00 lr: 0.000060 loss: 0.5834 (0.6754) grad: 0.2044 (0.2779) time: 0.5191 data: 0.0031 max mem: 25051 +train: [0] Total time: 0:07:51 (0.5895 s / it) +train: [0] Summary: lr: 0.000060 loss: 0.5834 (0.6754) grad: 0.2044 (0.2779) +eval (validation): [0] [ 0/16] eta: 0:01:08 time: 4.2947 data: 3.9692 max mem: 25051 +eval (validation): [0] [15/16] eta: 0:00:00 time: 0.6526 data: 0.2577 max mem: 25051 +eval (validation): [0] Total time: 0:00:10 (0.6683 s / it) +cv: [0] best hparam: (0.85, 1.0) (023) ('023_lr8.5e-01_wd1.0e+00') loss: 0.633 acc: 0.734 f1: 0.731 bacc: 0.732 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/adhd200_dx__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/adhd200_dx__patch__attn/checkpoint-best.pth +train: [1] [ 0/800] eta: 1:06:14 lr: nan time: 4.9679 data: 4.5876 max mem: 25051 +train: [1] [ 20/800] eta: 0:09:32 lr: 0.000061 loss: 0.6304 (0.7271) grad: 0.2076 (0.2846) time: 0.5219 data: 0.0022 max mem: 25051 +train: [1] [ 40/800] eta: 0:07:51 lr: 0.000063 loss: 0.6277 (0.6741) grad: 0.2076 (0.2893) time: 0.5021 data: 0.0030 max mem: 25051 +train: [1] [ 60/800] eta: 0:07:14 lr: 0.000064 loss: 0.6304 (0.6853) grad: 0.2833 (0.3275) time: 0.5184 data: 0.0025 max mem: 25051 +train: [1] [ 80/800] eta: 0:07:29 lr: 0.000066 loss: 0.6742 (0.6896) grad: 0.2859 (0.3354) time: 0.7363 data: 0.2232 max mem: 25051 +train: [1] [100/800] eta: 0:07:06 lr: 0.000067 loss: 0.6828 (0.6909) grad: 0.3156 (0.3343) time: 0.5511 data: 0.0033 max mem: 25051 +train: [1] [120/800] eta: 0:06:43 lr: 0.000069 loss: 0.6828 (0.6924) grad: 0.2997 (0.3215) time: 0.5100 data: 0.0029 max mem: 25051 +train: [1] [140/800] eta: 0:06:25 lr: 0.000070 loss: 0.6812 (0.6869) grad: 0.2764 (0.3107) time: 0.5323 data: 0.0032 max mem: 25051 +train: [1] [160/800] eta: 0:06:35 lr: 0.000072 loss: 0.6264 (0.6653) grad: 0.2373 (0.3019) time: 0.8542 data: 0.3434 max mem: 25051 +train: [1] [180/800] eta: 0:06:16 lr: 0.000073 loss: 0.6489 (0.6761) grad: 0.2455 (0.3176) time: 0.5237 data: 0.0101 max mem: 25051 +train: [1] [200/800] eta: 0:05:59 lr: 0.000075 loss: 0.6574 (0.6761) grad: 0.2808 (0.3175) time: 0.5159 data: 0.0029 max mem: 25051 +train: [1] [220/800] eta: 0:05:43 lr: 0.000076 loss: 0.6489 (0.6716) grad: 0.2959 (0.3150) time: 0.5276 data: 0.0027 max mem: 25051 +train: [1] [240/800] eta: 0:05:42 lr: 0.000078 loss: 0.6771 (0.6702) grad: 0.3093 (0.3191) time: 0.8204 data: 0.2374 max mem: 25051 +train: [1] [260/800] eta: 0:05:24 lr: 0.000079 loss: 0.6531 (0.6677) grad: 0.2935 (0.3181) time: 0.4885 data: 0.0027 max mem: 25051 +train: [1] [280/800] eta: 0:05:09 lr: 0.000081 loss: 0.6310 (0.6625) grad: 0.2880 (0.3156) time: 0.5192 data: 0.0032 max mem: 25051 +train: [1] [300/800] eta: 0:05:02 lr: 0.000082 loss: 0.6128 (0.6579) grad: 0.2738 (0.3106) time: 0.7390 data: 0.2260 max mem: 25051 +train: [1] [320/800] eta: 0:04:50 lr: 0.000084 loss: 0.6128 (0.6567) grad: 0.2322 (0.3057) time: 0.5970 data: 0.0041 max mem: 25051 +train: [1] [340/800] eta: 0:04:36 lr: 0.000085 loss: 0.6128 (0.6564) grad: 0.2316 (0.2992) time: 0.5407 data: 0.0029 max mem: 25051 +train: [1] [360/800] eta: 0:04:22 lr: 0.000087 loss: 0.6363 (0.6557) grad: 0.2063 (0.2968) time: 0.5368 data: 0.0033 max mem: 25051 +train: [1] [380/800] eta: 0:04:14 lr: 0.000088 loss: 0.6093 (0.6485) grad: 0.2249 (0.2967) time: 0.7801 data: 0.2430 max mem: 25051 +train: [1] [400/800] eta: 0:04:01 lr: 0.000090 loss: 0.5848 (0.6464) grad: 0.1874 (0.2911) time: 0.5306 data: 0.0104 max mem: 25051 +train: [1] [420/800] eta: 0:03:47 lr: 0.000091 loss: 0.5848 (0.6473) grad: 0.2108 (0.2903) time: 0.5265 data: 0.0022 max mem: 25051 +train: [1] [440/800] eta: 0:03:34 lr: 0.000093 loss: 0.5824 (0.6451) grad: 0.2486 (0.2920) time: 0.5315 data: 0.0029 max mem: 25051 +train: [1] [460/800] eta: 0:03:25 lr: 0.000094 loss: 0.6085 (0.6477) grad: 0.2734 (0.2922) time: 0.7591 data: 0.2297 max mem: 25051 +train: [1] [480/800] eta: 0:03:12 lr: 0.000096 loss: 0.6085 (0.6457) grad: 0.2915 (0.2908) time: 0.5415 data: 0.0025 max mem: 25051 +train: [1] [500/800] eta: 0:02:59 lr: 0.000097 loss: 0.6085 (0.6454) grad: 0.2922 (0.2904) time: 0.5069 data: 0.0032 max mem: 25051 +train: [1] [520/800] eta: 0:02:46 lr: 0.000099 loss: 0.6532 (0.6460) grad: 0.3144 (0.2926) time: 0.4997 data: 0.0032 max mem: 25051 +train: [1] [540/800] eta: 0:02:35 lr: 0.000100 loss: 0.6057 (0.6458) grad: 0.3014 (0.2939) time: 0.7555 data: 0.2321 max mem: 25051 +train: [1] [560/800] eta: 0:02:23 lr: 0.000102 loss: 0.6475 (0.6454) grad: 0.2922 (0.2916) time: 0.5263 data: 0.0028 max mem: 25051 +train: [1] [580/800] eta: 0:02:10 lr: 0.000103 loss: 0.5950 (0.6422) grad: 0.2708 (0.2885) time: 0.5233 data: 0.0030 max mem: 25051 +train: [1] [600/800] eta: 0:01:59 lr: 0.000105 loss: 0.5950 (0.6420) grad: 0.2176 (0.2865) time: 0.7422 data: 0.2281 max mem: 25051 +train: [1] [620/800] eta: 0:01:47 lr: 0.000106 loss: 0.6458 (0.6443) grad: 0.2067 (0.2849) time: 0.5884 data: 0.0712 max mem: 25051 +train: [1] [640/800] eta: 0:01:35 lr: 0.000108 loss: 0.6458 (0.6448) grad: 0.2067 (0.2824) time: 0.5252 data: 0.0029 max mem: 25051 +train: [1] [660/800] eta: 0:01:23 lr: 0.000109 loss: 0.7015 (0.6461) grad: 0.1973 (0.2812) time: 0.5329 data: 0.0028 max mem: 25051 +train: [1] [680/800] eta: 0:01:11 lr: 0.000111 loss: 0.6625 (0.6458) grad: 0.1823 (0.2794) time: 0.7215 data: 0.2241 max mem: 25051 +train: [1] [700/800] eta: 0:00:59 lr: 0.000112 loss: 0.6364 (0.6469) grad: 0.1859 (0.2793) time: 0.5332 data: 0.0027 max mem: 25051 +train: [1] [720/800] eta: 0:00:47 lr: 0.000114 loss: 0.5859 (0.6462) grad: 0.2242 (0.2798) time: 0.5291 data: 0.0028 max mem: 25051 +train: [1] [740/800] eta: 0:00:35 lr: 0.000115 loss: 0.6352 (0.6473) grad: 0.2565 (0.2805) time: 0.5198 data: 0.0025 max mem: 25051 +train: [1] [760/800] eta: 0:00:23 lr: 0.000117 loss: 0.6352 (0.6482) grad: 0.2702 (0.2836) time: 0.7735 data: 0.2539 max mem: 25051 +train: [1] [780/800] eta: 0:00:11 lr: 0.000118 loss: 0.6113 (0.6456) grad: 0.3312 (0.2873) time: 0.5485 data: 0.0034 max mem: 25051 +train: [1] [799/800] eta: 0:00:00 lr: 0.000120 loss: 0.6242 (0.6453) grad: 0.3170 (0.2876) time: 0.5203 data: 0.0031 max mem: 25051 +train: [1] Total time: 0:07:55 (0.5946 s / it) +train: [1] Summary: lr: 0.000120 loss: 0.6242 (0.6453) grad: 0.3170 (0.2876) +eval (validation): [1] [ 0/16] eta: 0:01:11 time: 4.4589 data: 4.1819 max mem: 25051 +eval (validation): [1] [15/16] eta: 0:00:00 time: 0.6633 data: 0.2884 max mem: 25051 +eval (validation): [1] Total time: 0:00:10 (0.6790 s / it) +cv: [1] best hparam: (14, 1.0) (040) ('040_lr1.4e+01_wd1.0e+00') loss: 0.561 acc: 0.781 f1: 0.773 bacc: 0.770 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/adhd200_dx__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/adhd200_dx__patch__attn/checkpoint-best.pth +train: [2] [ 0/800] eta: 1:01:20 lr: nan time: 4.6000 data: 4.1655 max mem: 25051 +train: [2] [ 20/800] eta: 0:09:30 lr: 0.000121 loss: 0.5433 (0.5666) grad: 0.3428 (0.3348) time: 0.5382 data: 0.0025 max mem: 25051 +train: [2] [ 40/800] eta: 0:07:58 lr: 0.000123 loss: 0.5746 (0.6272) grad: 0.2855 (0.3265) time: 0.5229 data: 0.0027 max mem: 25051 +train: [2] [ 60/800] eta: 0:07:19 lr: 0.000124 loss: 0.6677 (0.6481) grad: 0.3166 (0.3294) time: 0.5188 data: 0.0032 max mem: 25051 +train: [2] [ 80/800] eta: 0:07:30 lr: 0.000126 loss: 0.6062 (0.6450) grad: 0.2855 (0.3198) time: 0.7252 data: 0.2294 max mem: 25051 +train: [2] [100/800] eta: 0:07:07 lr: 0.000127 loss: 0.6410 (0.6385) grad: 0.3060 (0.3384) time: 0.5508 data: 0.0037 max mem: 25051 +train: [2] [120/800] eta: 0:06:44 lr: 0.000129 loss: 0.6410 (0.6329) grad: 0.3086 (0.3360) time: 0.5126 data: 0.0031 max mem: 25051 +train: [2] [140/800] eta: 0:06:23 lr: 0.000130 loss: 0.6266 (0.6358) grad: 0.3060 (0.3296) time: 0.4952 data: 0.0029 max mem: 25051 +train: [2] [160/800] eta: 0:06:21 lr: 0.000132 loss: 0.6266 (0.6350) grad: 0.3060 (0.3248) time: 0.7005 data: 0.2201 max mem: 25051 +train: [2] [180/800] eta: 0:06:02 lr: 0.000133 loss: 0.6084 (0.6376) grad: 0.3124 (0.3264) time: 0.4996 data: 0.0024 max mem: 25051 +train: [2] [200/800] eta: 0:05:49 lr: 0.000135 loss: 0.6279 (0.6394) grad: 0.3170 (0.3275) time: 0.5567 data: 0.0030 max mem: 25051 +train: [2] [220/800] eta: 0:05:34 lr: 0.000136 loss: 0.6019 (0.6469) grad: 0.3290 (0.3360) time: 0.5304 data: 0.0030 max mem: 25051 +train: [2] [240/800] eta: 0:05:31 lr: 0.000138 loss: 0.6019 (0.6423) grad: 0.3488 (0.3451) time: 0.7580 data: 0.2290 max mem: 25051 +train: [2] [260/800] eta: 0:05:16 lr: 0.000139 loss: 0.6676 (0.6469) grad: 0.3543 (0.3475) time: 0.5109 data: 0.0032 max mem: 25051 +train: [2] [280/800] eta: 0:05:02 lr: 0.000141 loss: 0.6619 (0.6467) grad: 0.3701 (0.3463) time: 0.5126 data: 0.0030 max mem: 25051 +train: [2] [300/800] eta: 0:04:55 lr: 0.000142 loss: 0.6629 (0.6443) grad: 0.3543 (0.3517) time: 0.7339 data: 0.2303 max mem: 25051 +train: [2] [320/800] eta: 0:04:42 lr: 0.000144 loss: 0.6619 (0.6411) grad: 0.3480 (0.3532) time: 0.5617 data: 0.0024 max mem: 25051 +train: [2] [340/800] eta: 0:04:30 lr: 0.000145 loss: 0.6030 (0.6413) grad: 0.3121 (0.3475) time: 0.5536 data: 0.0028 max mem: 25051 +train: [2] [360/800] eta: 0:04:16 lr: 0.000147 loss: 0.6115 (0.6422) grad: 0.3121 (0.3458) time: 0.5172 data: 0.0029 max mem: 25051 +train: [2] [380/800] eta: 0:04:07 lr: 0.000148 loss: 0.6115 (0.6447) grad: 0.3073 (0.3507) time: 0.7008 data: 0.2200 max mem: 25051 +train: [2] [400/800] eta: 0:03:54 lr: 0.000150 loss: 0.6221 (0.6419) grad: 0.3081 (0.3547) time: 0.5113 data: 0.0026 max mem: 25051 +train: [2] [420/800] eta: 0:03:41 lr: 0.000151 loss: 0.5682 (0.6357) grad: 0.3595 (0.3529) time: 0.5292 data: 0.0028 max mem: 25051 +train: [2] [440/800] eta: 0:03:28 lr: 0.000153 loss: 0.5698 (0.6421) grad: 0.3595 (0.3561) time: 0.5253 data: 0.0031 max mem: 25051 +train: [2] [460/800] eta: 0:03:19 lr: 0.000154 loss: 0.5698 (0.6406) grad: 0.3504 (0.3601) time: 0.7615 data: 0.2229 max mem: 25051 +train: [2] [480/800] eta: 0:03:08 lr: 0.000156 loss: 0.5470 (0.6343) grad: 0.3005 (0.3591) time: 0.5972 data: 0.0029 max mem: 25051 +train: [2] [500/800] eta: 0:02:55 lr: 0.000157 loss: 0.5629 (0.6325) grad: 0.3268 (0.3587) time: 0.5288 data: 0.0034 max mem: 25051 +train: [2] [520/800] eta: 0:02:43 lr: 0.000159 loss: 0.5505 (0.6336) grad: 0.3281 (0.3578) time: 0.4899 data: 0.0030 max mem: 25051 +train: [2] [540/800] eta: 0:02:32 lr: 0.000160 loss: 0.5011 (0.6293) grad: 0.3100 (0.3553) time: 0.7426 data: 0.2290 max mem: 25051 +train: [2] [560/800] eta: 0:02:20 lr: 0.000162 loss: 0.5181 (0.6262) grad: 0.3281 (0.3545) time: 0.5188 data: 0.0030 max mem: 25051 +train: [2] [580/800] eta: 0:02:08 lr: 0.000163 loss: 0.5067 (0.6231) grad: 0.3416 (0.3580) time: 0.4983 data: 0.0027 max mem: 25051 +train: [2] [600/800] eta: 0:01:57 lr: 0.000165 loss: 0.5181 (0.6253) grad: 0.3416 (0.3582) time: 0.7839 data: 0.2998 max mem: 25051 +train: [2] [620/800] eta: 0:01:45 lr: 0.000166 loss: 0.5830 (0.6250) grad: 0.3465 (0.3588) time: 0.5177 data: 0.0020 max mem: 25051 +train: [2] [640/800] eta: 0:01:33 lr: 0.000168 loss: 0.5846 (0.6246) grad: 0.3995 (0.3618) time: 0.5004 data: 0.0023 max mem: 25051 +train: [2] [660/800] eta: 0:01:21 lr: 0.000169 loss: 0.5830 (0.6210) grad: 0.3995 (0.3643) time: 0.5154 data: 0.0025 max mem: 25051 +train: [2] [680/800] eta: 0:01:10 lr: 0.000171 loss: 0.5542 (0.6189) grad: 0.3484 (0.3637) time: 0.7236 data: 0.2337 max mem: 25051 +train: [2] [700/800] eta: 0:00:58 lr: 0.000172 loss: 0.5367 (0.6169) grad: 0.3553 (0.3638) time: 0.5369 data: 0.0316 max mem: 25051 +train: [2] [720/800] eta: 0:00:46 lr: 0.000174 loss: 0.5384 (0.6157) grad: 0.3454 (0.3639) time: 0.5317 data: 0.0108 max mem: 25051 +train: [2] [740/800] eta: 0:00:34 lr: 0.000175 loss: 0.5617 (0.6187) grad: 0.3454 (0.3643) time: 0.5106 data: 0.0018 max mem: 25051 +train: [2] [760/800] eta: 0:00:23 lr: 0.000177 loss: 0.5600 (0.6154) grad: 0.3547 (0.3660) time: 0.7315 data: 0.2309 max mem: 25051 +train: [2] [780/800] eta: 0:00:11 lr: 0.000178 loss: 0.5598 (0.6135) grad: 0.3547 (0.3654) time: 0.5055 data: 0.0022 max mem: 25051 +train: [2] [799/800] eta: 0:00:00 lr: 0.000180 loss: 0.5552 (0.6131) grad: 0.3810 (0.3670) time: 0.5128 data: 0.0023 max mem: 25051 +train: [2] Total time: 0:07:45 (0.5822 s / it) +train: [2] Summary: lr: 0.000180 loss: 0.5552 (0.6131) grad: 0.3810 (0.3670) +eval (validation): [2] [ 0/16] eta: 0:01:09 time: 4.3676 data: 4.1164 max mem: 25051 +eval (validation): [2] [15/16] eta: 0:00:00 time: 0.6436 data: 0.2979 max mem: 25051 +eval (validation): [2] Total time: 0:00:10 (0.6598 s / it) +cv: [2] best hparam: (1.2, 1.0) (025) ('025_lr1.2e+00_wd1.0e+00') loss: 0.593 acc: 0.781 f1: 0.770 bacc: 0.766 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/adhd200_dx__patch__attn/checkpoint-last.pth +train: [3] [ 0/800] eta: 0:57:56 lr: nan time: 4.3462 data: 3.9780 max mem: 25051 +train: [3] [ 20/800] eta: 0:08:49 lr: 0.000181 loss: 0.5519 (0.5354) grad: 0.3989 (0.3899) time: 0.4953 data: 0.0024 max mem: 25051 +train: [3] [ 40/800] eta: 0:07:33 lr: 0.000183 loss: 0.5289 (0.5199) grad: 0.3989 (0.4178) time: 0.5109 data: 0.0025 max mem: 25051 +train: [3] [ 60/800] eta: 0:07:03 lr: 0.000184 loss: 0.5519 (0.5181) grad: 0.3970 (0.3845) time: 0.5213 data: 0.0034 max mem: 25051 +train: [3] [ 80/800] eta: 0:07:20 lr: 0.000186 loss: 0.5458 (0.5323) grad: 0.3970 (0.3935) time: 0.7329 data: 0.2258 max mem: 25051 +train: [3] [100/800] eta: 0:07:00 lr: 0.000187 loss: 0.5289 (0.5260) grad: 0.3634 (0.3894) time: 0.5561 data: 0.0030 max mem: 25051 +train: [3] [120/800] eta: 0:06:41 lr: 0.000189 loss: 0.5209 (0.5308) grad: 0.3471 (0.3859) time: 0.5360 data: 0.0027 max mem: 25051 +train: [3] [140/800] eta: 0:06:20 lr: 0.000190 loss: 0.5209 (0.5362) grad: 0.3509 (0.3876) time: 0.4940 data: 0.0029 max mem: 25051 +train: [3] [160/800] eta: 0:06:18 lr: 0.000192 loss: 0.5209 (0.5426) grad: 0.3509 (0.3911) time: 0.6985 data: 0.2121 max mem: 25051 +train: [3] [180/800] eta: 0:06:00 lr: 0.000193 loss: 0.5157 (0.5341) grad: 0.4035 (0.3985) time: 0.4986 data: 0.0019 max mem: 25051 +train: [3] [200/800] eta: 0:05:44 lr: 0.000195 loss: 0.5646 (0.5445) grad: 0.4313 (0.4133) time: 0.5017 data: 0.0028 max mem: 25051 +train: [3] [220/800] eta: 0:05:29 lr: 0.000196 loss: 0.5560 (0.5494) grad: 0.4548 (0.4242) time: 0.5116 data: 0.0029 max mem: 25051 +train: [3] [240/800] eta: 0:05:27 lr: 0.000198 loss: 0.5314 (0.5481) grad: 0.4548 (0.4260) time: 0.7767 data: 0.2219 max mem: 25051 +train: [3] [260/800] eta: 0:05:13 lr: 0.000199 loss: 0.5364 (0.5459) grad: 0.4434 (0.4274) time: 0.5243 data: 0.0029 max mem: 25051 +train: [3] [280/800] eta: 0:04:59 lr: 0.000201 loss: 0.5244 (0.5446) grad: 0.5113 (0.4356) time: 0.5211 data: 0.0028 max mem: 25051 +WARNING: classifier 48 (50, 1.0) diverged (loss=30.25 > 13.86) at step 675. Freezing. +train: [3] [300/800] eta: 0:04:52 lr: 0.000202 loss: 0.5031 (0.5653) grad: 0.4892 (0.4548) time: 0.7192 data: 0.2146 max mem: 25051 +train: [3] [320/800] eta: 0:04:39 lr: 0.000204 loss: 0.5244 (0.5672) grad: 0.5113 (0.4635) time: 0.5243 data: 0.0040 max mem: 25051 +train: [3] [340/800] eta: 0:04:25 lr: 0.000205 loss: 0.5377 (0.5663) grad: 0.4828 (0.4625) time: 0.4984 data: 0.0021 max mem: 25051 +train: [3] [360/800] eta: 0:04:12 lr: 0.000207 loss: 0.5631 (0.5738) grad: 0.4758 (0.4639) time: 0.5067 data: 0.0028 max mem: 25051 +train: [3] [380/800] eta: 0:04:03 lr: 0.000208 loss: 0.5675 (0.5794) grad: 0.4758 (0.4657) time: 0.7212 data: 0.2220 max mem: 25051 +train: [3] [400/800] eta: 0:03:50 lr: 0.000210 loss: 0.5631 (0.5757) grad: 0.4758 (0.4669) time: 0.5050 data: 0.0031 max mem: 25051 +train: [3] [420/800] eta: 0:03:37 lr: 0.000211 loss: 0.4870 (0.5719) grad: 0.4535 (0.4603) time: 0.4894 data: 0.0025 max mem: 25051 +train: [3] [440/800] eta: 0:03:25 lr: 0.000213 loss: 0.4744 (0.5733) grad: 0.4445 (0.4587) time: 0.5222 data: 0.0031 max mem: 25051 +train: [3] [460/800] eta: 0:03:16 lr: 0.000214 loss: 0.4744 (0.5717) grad: 0.4335 (0.4592) time: 0.7708 data: 0.2300 max mem: 25051 +train: [3] [480/800] eta: 0:03:04 lr: 0.000216 loss: 0.5097 (0.5699) grad: 0.3919 (0.4568) time: 0.5048 data: 0.0026 max mem: 25051 +train: [3] [500/800] eta: 0:02:52 lr: 0.000217 loss: 0.5339 (0.5666) grad: 0.4445 (0.4568) time: 0.5114 data: 0.0027 max mem: 25051 +train: [3] [520/800] eta: 0:02:40 lr: 0.000219 loss: 0.5348 (0.5688) grad: 0.4499 (0.4558) time: 0.5172 data: 0.0031 max mem: 25051 +train: [3] [540/800] eta: 0:02:30 lr: 0.000220 loss: 0.5359 (0.5689) grad: 0.4404 (0.4597) time: 0.7576 data: 0.2439 max mem: 25051 +train: [3] [560/800] eta: 0:02:18 lr: 0.000222 loss: 0.5359 (0.5670) grad: 0.4358 (0.4602) time: 0.5049 data: 0.0030 max mem: 25051 +train: [3] [580/800] eta: 0:02:06 lr: 0.000223 loss: 0.5388 (0.5648) grad: 0.4339 (0.4585) time: 0.5304 data: 0.0032 max mem: 25051 +WARNING: classifier 47 (43, 1.0) diverged (loss=13.95 > 13.86) at step 749. Freezing. +train: [3] [600/800] eta: 0:01:55 lr: 0.000225 loss: 0.5705 (0.5687) grad: 0.4248 (0.4570) time: 0.7390 data: 0.2300 max mem: 25051 +train: [3] [620/800] eta: 0:01:43 lr: 0.000226 loss: 0.5705 (0.5677) grad: 0.3596 (0.4515) time: 0.5044 data: 0.0070 max mem: 25051 +train: [3] [640/800] eta: 0:01:31 lr: 0.000228 loss: 0.5705 (0.5640) grad: 0.3519 (0.4469) time: 0.5008 data: 0.0025 max mem: 25051 +train: [3] [660/800] eta: 0:01:20 lr: 0.000229 loss: 0.5444 (0.5629) grad: 0.3376 (0.4436) time: 0.5354 data: 0.0029 max mem: 25051 +train: [3] [680/800] eta: 0:01:09 lr: 0.000231 loss: 0.5254 (0.5642) grad: 0.3166 (0.4416) time: 0.7594 data: 0.2259 max mem: 25051 +train: [3] [700/800] eta: 0:00:57 lr: 0.000232 loss: 0.5092 (0.5638) grad: 0.3166 (0.4397) time: 0.5238 data: 0.0029 max mem: 25051 +train: [3] [720/800] eta: 0:00:46 lr: 0.000234 loss: 0.5242 (0.5645) grad: 0.3376 (0.4378) time: 0.5216 data: 0.0028 max mem: 25051 +train: [3] [740/800] eta: 0:00:34 lr: 0.000235 loss: 0.5242 (0.5639) grad: 0.3811 (0.4376) time: 0.5154 data: 0.0029 max mem: 25051 +train: [3] [760/800] eta: 0:00:23 lr: 0.000237 loss: 0.4936 (0.5628) grad: 0.3557 (0.4353) time: 0.7943 data: 0.2836 max mem: 25051 +train: [3] [780/800] eta: 0:00:11 lr: 0.000238 loss: 0.4936 (0.5596) grad: 0.4175 (0.4375) time: 0.5284 data: 0.0026 max mem: 25051 +train: [3] [799/800] eta: 0:00:00 lr: 0.000240 loss: 0.5354 (0.5612) grad: 0.4241 (0.4383) time: 0.5651 data: 0.0035 max mem: 25051 +train: [3] Total time: 0:07:43 (0.5788 s / it) +train: [3] Summary: lr: 0.000240 loss: 0.5354 (0.5612) grad: 0.4241 (0.4383) +eval (validation): [3] [ 0/16] eta: 0:01:14 time: 4.6420 data: 4.3229 max mem: 25051 +eval (validation): [3] [15/16] eta: 0:00:00 time: 0.6942 data: 0.2715 max mem: 25051 +eval (validation): [3] Total time: 0:00:11 (0.7067 s / it) +cv: [3] best hparam: (1.9, 1.0) (028) ('028_lr1.9e+00_wd1.0e+00') loss: 0.575 acc: 0.750 f1: 0.737 bacc: 0.734 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/adhd200_dx__patch__attn/checkpoint-last.pth +train: [4] [ 0/800] eta: 1:01:08 lr: nan time: 4.5858 data: 4.1556 max mem: 25051 +WARNING: classifier 46 (36, 1.0) diverged (loss=15.78 > 13.86) at step 805. Freezing. +train: [4] [ 20/800] eta: 0:09:47 lr: 0.000241 loss: 0.5883 (0.5868) grad: 0.5115 (0.5350) time: 0.5613 data: 0.0020 max mem: 25051 +train: [4] [ 40/800] eta: 0:08:01 lr: 0.000243 loss: 0.5117 (0.5795) grad: 0.4142 (0.4693) time: 0.5069 data: 0.0029 max mem: 25051 +train: [4] [ 60/800] eta: 0:07:16 lr: 0.000244 loss: 0.5654 (0.5683) grad: 0.4443 (0.4468) time: 0.5021 data: 0.0032 max mem: 25051 +train: [4] [ 80/800] eta: 0:07:29 lr: 0.000246 loss: 0.5451 (0.5900) grad: 0.4092 (0.4254) time: 0.7296 data: 0.2281 max mem: 25051 +train: [4] [100/800] eta: 0:07:03 lr: 0.000247 loss: 0.5102 (0.5725) grad: 0.3808 (0.4291) time: 0.5258 data: 0.0050 max mem: 25051 +train: [4] [120/800] eta: 0:06:40 lr: 0.000249 loss: 0.5061 (0.5632) grad: 0.3817 (0.4320) time: 0.5064 data: 0.0025 max mem: 25051 +WARNING: classifier 45 (31, 1.0) diverged (loss=14.03 > 13.86) at step 834. Freezing. +train: [4] [140/800] eta: 0:06:20 lr: 0.000250 loss: 0.5061 (0.5654) grad: 0.3817 (0.4280) time: 0.5020 data: 0.0030 max mem: 25051 +train: [4] [160/800] eta: 0:06:19 lr: 0.000252 loss: 0.4823 (0.5576) grad: 0.3674 (0.4071) time: 0.7078 data: 0.2242 max mem: 25051 +train: [4] [180/800] eta: 0:06:04 lr: 0.000253 loss: 0.5046 (0.5554) grad: 0.3056 (0.3920) time: 0.5491 data: 0.0024 max mem: 25051 +train: [4] [200/800] eta: 0:05:48 lr: 0.000255 loss: 0.5046 (0.5504) grad: 0.2840 (0.3856) time: 0.5105 data: 0.0030 max mem: 25051 +train: [4] [220/800] eta: 0:05:32 lr: 0.000256 loss: 0.4928 (0.5446) grad: 0.2649 (0.3785) time: 0.5011 data: 0.0030 max mem: 25051 +train: [4] [240/800] eta: 0:05:30 lr: 0.000258 loss: 0.5265 (0.5467) grad: 0.2822 (0.3740) time: 0.7721 data: 0.2182 max mem: 25051 +train: [4] [260/800] eta: 0:05:14 lr: 0.000259 loss: 0.5084 (0.5404) grad: 0.2933 (0.3689) time: 0.5010 data: 0.0031 max mem: 25051 +train: [4] [280/800] eta: 0:05:00 lr: 0.000261 loss: 0.5320 (0.5425) grad: 0.3191 (0.3697) time: 0.5064 data: 0.0030 max mem: 25051 +train: [4] [300/800] eta: 0:04:53 lr: 0.000262 loss: 0.5320 (0.5426) grad: 0.3491 (0.3764) time: 0.7338 data: 0.2276 max mem: 25051 +train: [4] [320/800] eta: 0:04:41 lr: 0.000264 loss: 0.5231 (0.5386) grad: 0.3453 (0.3768) time: 0.5738 data: 0.0409 max mem: 25051 +WARNING: classifier 44 (26, 1.0) diverged (loss=18.00 > 13.86) at step 882. Freezing. +train: [4] [340/800] eta: 0:04:28 lr: 0.000265 loss: 0.5348 (0.5417) grad: 0.4444 (0.3817) time: 0.5314 data: 0.0226 max mem: 25051 +train: [4] [360/800] eta: 0:04:14 lr: 0.000267 loss: 0.5231 (0.5416) grad: 0.4011 (0.3803) time: 0.5101 data: 0.0029 max mem: 25051 +train: [4] [380/800] eta: 0:04:07 lr: 0.000268 loss: 0.5034 (0.5364) grad: 0.3803 (0.3828) time: 0.7437 data: 0.2205 max mem: 25051 +train: [4] [400/800] eta: 0:03:53 lr: 0.000270 loss: 0.5034 (0.5341) grad: 0.3803 (0.3839) time: 0.4892 data: 0.0029 max mem: 25051 +train: [4] [420/800] eta: 0:03:40 lr: 0.000271 loss: 0.4881 (0.5322) grad: 0.4011 (0.3906) time: 0.5143 data: 0.0029 max mem: 25051 +train: [4] [440/800] eta: 0:03:27 lr: 0.000273 loss: 0.4881 (0.5329) grad: 0.4392 (0.3914) time: 0.5042 data: 0.0029 max mem: 25051 +train: [4] [460/800] eta: 0:03:18 lr: 0.000274 loss: 0.5024 (0.5321) grad: 0.4092 (0.3923) time: 0.7303 data: 0.2236 max mem: 25051 +train: [4] [480/800] eta: 0:03:05 lr: 0.000276 loss: 0.4881 (0.5317) grad: 0.4092 (0.3955) time: 0.5065 data: 0.0032 max mem: 25051 +train: [4] [500/800] eta: 0:02:53 lr: 0.000277 loss: 0.4858 (0.5305) grad: 0.3956 (0.3953) time: 0.5202 data: 0.0032 max mem: 25051 +train: [4] [520/800] eta: 0:02:40 lr: 0.000279 loss: 0.4787 (0.5325) grad: 0.3880 (0.3974) time: 0.4893 data: 0.0032 max mem: 25051 +train: [4] [540/800] eta: 0:02:31 lr: 0.000280 loss: 0.4713 (0.5317) grad: 0.3840 (0.3961) time: 0.7776 data: 0.2332 max mem: 25051 +train: [4] [560/800] eta: 0:02:18 lr: 0.000282 loss: 0.5246 (0.5334) grad: 0.3956 (0.3959) time: 0.4911 data: 0.0031 max mem: 25051 +train: [4] [580/800] eta: 0:02:06 lr: 0.000283 loss: 0.5246 (0.5341) grad: 0.3308 (0.3932) time: 0.4864 data: 0.0028 max mem: 25051 +train: [4] [600/800] eta: 0:01:55 lr: 0.000285 loss: 0.5246 (0.5347) grad: 0.3421 (0.3961) time: 0.6780 data: 0.2071 max mem: 25051 +train: [4] [620/800] eta: 0:01:43 lr: 0.000286 loss: 0.5178 (0.5335) grad: 0.3322 (0.3939) time: 0.5212 data: 0.0039 max mem: 25051 +train: [4] [640/800] eta: 0:01:32 lr: 0.000288 loss: 0.5013 (0.5327) grad: 0.3421 (0.3961) time: 0.5263 data: 0.0030 max mem: 25051 +train: [4] [660/800] eta: 0:01:20 lr: 0.000289 loss: 0.4982 (0.5328) grad: 0.3322 (0.3940) time: 0.5181 data: 0.0024 max mem: 25051 +train: [4] [680/800] eta: 0:01:09 lr: 0.000291 loss: 0.5013 (0.5315) grad: 0.3283 (0.3931) time: 0.7203 data: 0.2239 max mem: 25051 +train: [4] [700/800] eta: 0:00:57 lr: 0.000292 loss: 0.4744 (0.5287) grad: 0.3426 (0.3917) time: 0.5008 data: 0.0032 max mem: 25051 +train: [4] [720/800] eta: 0:00:45 lr: 0.000294 loss: 0.4707 (0.5280) grad: 0.3654 (0.3976) time: 0.4847 data: 0.0020 max mem: 25051 +train: [4] [740/800] eta: 0:00:34 lr: 0.000295 loss: 0.4996 (0.5324) grad: 0.3957 (0.3985) time: 0.4812 data: 0.0025 max mem: 25051 +train: [4] [760/800] eta: 0:00:22 lr: 0.000297 loss: 0.4960 (0.5329) grad: 0.3755 (0.3956) time: 0.6934 data: 0.2088 max mem: 25051 +train: [4] [780/800] eta: 0:00:11 lr: 0.000298 loss: 0.4960 (0.5314) grad: 0.3755 (0.3935) time: 0.5132 data: 0.0024 max mem: 25051 +train: [4] [799/800] eta: 0:00:00 lr: 0.000300 loss: 0.4611 (0.5289) grad: 0.2855 (0.3913) time: 0.5268 data: 0.0030 max mem: 25051 +train: [4] Total time: 0:07:37 (0.5716 s / it) +train: [4] Summary: lr: 0.000300 loss: 0.4611 (0.5289) grad: 0.2855 (0.3913) +eval (validation): [4] [ 0/16] eta: 0:01:10 time: 4.4053 data: 4.1014 max mem: 25051 +eval (validation): [4] [15/16] eta: 0:00:00 time: 0.6760 data: 0.3051 max mem: 25051 +eval (validation): [4] Total time: 0:00:11 (0.6928 s / it) +cv: [4] best hparam: (0.44, 1.0) (019) ('019_lr4.4e-01_wd1.0e+00') loss: 0.579 acc: 0.781 f1: 0.773 bacc: 0.770 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/adhd200_dx__patch__attn/checkpoint-last.pth +train: [5] [ 0/800] eta: 1:00:00 lr: nan time: 4.5008 data: 4.1365 max mem: 25051 +train: [5] [ 20/800] eta: 0:09:59 lr: 0.000300 loss: 0.5585 (0.5656) grad: 0.2920 (0.2863) time: 0.5819 data: 0.0599 max mem: 25051 +train: [5] [ 40/800] eta: 0:08:19 lr: 0.000300 loss: 0.5400 (0.5077) grad: 0.3282 (0.3624) time: 0.5391 data: 0.0024 max mem: 25051 +train: [5] [ 60/800] eta: 0:07:27 lr: 0.000300 loss: 0.5400 (0.5271) grad: 0.3979 (0.4223) time: 0.4991 data: 0.0033 max mem: 25051 +train: [5] [ 80/800] eta: 0:07:36 lr: 0.000300 loss: 0.5329 (0.5202) grad: 0.4139 (0.4368) time: 0.7239 data: 0.2254 max mem: 25051 +train: [5] [100/800] eta: 0:07:08 lr: 0.000300 loss: 0.4988 (0.5254) grad: 0.4633 (0.4395) time: 0.5251 data: 0.0027 max mem: 25051 +train: [5] [120/800] eta: 0:06:45 lr: 0.000300 loss: 0.4988 (0.5262) grad: 0.4925 (0.4435) time: 0.5095 data: 0.0030 max mem: 25051 +train: [5] [140/800] eta: 0:06:23 lr: 0.000300 loss: 0.4908 (0.5071) grad: 0.4219 (0.4326) time: 0.4899 data: 0.0023 max mem: 25051 +train: [5] [160/800] eta: 0:06:24 lr: 0.000300 loss: 0.4908 (0.5124) grad: 0.3467 (0.4241) time: 0.7363 data: 0.2509 max mem: 25051 +train: [5] [180/800] eta: 0:06:08 lr: 0.000300 loss: 0.4490 (0.5150) grad: 0.3412 (0.4137) time: 0.5519 data: 0.0301 max mem: 25051 +WARNING: classifier 43 (22, 1.0) diverged (loss=19.94 > 13.86) at step 1049. Freezing. +train: [5] [200/800] eta: 0:05:51 lr: 0.000300 loss: 0.4457 (0.5224) grad: 0.3464 (0.4288) time: 0.5068 data: 0.0031 max mem: 25051 +train: [5] [220/800] eta: 0:05:34 lr: 0.000300 loss: 0.5313 (0.5228) grad: 0.3439 (0.4237) time: 0.4917 data: 0.0020 max mem: 25051 +train: [5] [240/800] eta: 0:05:32 lr: 0.000300 loss: 0.4468 (0.5145) grad: 0.3412 (0.4126) time: 0.7716 data: 0.2513 max mem: 25051 +train: [5] [260/800] eta: 0:05:16 lr: 0.000300 loss: 0.4468 (0.5120) grad: 0.3256 (0.4022) time: 0.5021 data: 0.0032 max mem: 25051 +train: [5] [280/800] eta: 0:05:02 lr: 0.000300 loss: 0.4316 (0.5083) grad: 0.3114 (0.4012) time: 0.5074 data: 0.0032 max mem: 25051 +train: [5] [300/800] eta: 0:04:54 lr: 0.000300 loss: 0.4103 (0.5020) grad: 0.2766 (0.3956) time: 0.7050 data: 0.2223 max mem: 25051 +train: [5] [320/800] eta: 0:04:42 lr: 0.000299 loss: 0.4251 (0.4981) grad: 0.2851 (0.3902) time: 0.5663 data: 0.0032 max mem: 25051 +train: [5] [340/800] eta: 0:04:28 lr: 0.000299 loss: 0.4316 (0.4984) grad: 0.3156 (0.3849) time: 0.5081 data: 0.0028 max mem: 25051 +train: [5] [360/800] eta: 0:04:14 lr: 0.000299 loss: 0.4251 (0.4946) grad: 0.3059 (0.3812) time: 0.4911 data: 0.0026 max mem: 25051 +WARNING: classifier 42 (19, 1.0) diverged (loss=16.84 > 13.86) at step 1093. Freezing. +train: [5] [380/800] eta: 0:04:06 lr: 0.000299 loss: 0.4620 (0.4961) grad: 0.3020 (0.3753) time: 0.7444 data: 0.2216 max mem: 25051 +train: [5] [400/800] eta: 0:03:54 lr: 0.000299 loss: 0.4992 (0.4970) grad: 0.2701 (0.3663) time: 0.5628 data: 0.0028 max mem: 25051 +train: [5] [420/800] eta: 0:03:40 lr: 0.000299 loss: 0.4259 (0.4934) grad: 0.2510 (0.3600) time: 0.4910 data: 0.0028 max mem: 25051 +train: [5] [440/800] eta: 0:03:27 lr: 0.000299 loss: 0.4378 (0.4925) grad: 0.2311 (0.3605) time: 0.4841 data: 0.0027 max mem: 25051 +train: [5] [460/800] eta: 0:03:18 lr: 0.000299 loss: 0.4469 (0.4895) grad: 0.2087 (0.3547) time: 0.7655 data: 0.2872 max mem: 25051 +train: [5] [480/800] eta: 0:03:05 lr: 0.000299 loss: 0.4378 (0.4885) grad: 0.2311 (0.3490) time: 0.4861 data: 0.0024 max mem: 25051 +train: [5] [500/800] eta: 0:02:52 lr: 0.000299 loss: 0.4471 (0.4872) grad: 0.2308 (0.3443) time: 0.4714 data: 0.0025 max mem: 25051 +train: [5] [520/800] eta: 0:02:40 lr: 0.000299 loss: 0.4469 (0.4835) grad: 0.2081 (0.3402) time: 0.4838 data: 0.0019 max mem: 25051 +train: [5] [540/800] eta: 0:02:31 lr: 0.000299 loss: 0.4550 (0.4822) grad: 0.2057 (0.3346) time: 0.8247 data: 0.2809 max mem: 25051 +train: [5] [560/800] eta: 0:02:18 lr: 0.000298 loss: 0.4447 (0.4809) grad: 0.1975 (0.3294) time: 0.4877 data: 0.0028 max mem: 25051 +train: [5] [580/800] eta: 0:02:06 lr: 0.000298 loss: 0.4447 (0.4797) grad: 0.1780 (0.3254) time: 0.5111 data: 0.0020 max mem: 25051 +train: [5] [600/800] eta: 0:01:56 lr: 0.000298 loss: 0.4433 (0.4781) grad: 0.1780 (0.3226) time: 0.7623 data: 0.2848 max mem: 25051 +train: [5] [620/800] eta: 0:01:44 lr: 0.000298 loss: 0.4408 (0.4774) grad: 0.1722 (0.3160) time: 0.5448 data: 0.0063 max mem: 25051 +train: [5] [640/800] eta: 0:01:32 lr: 0.000298 loss: 0.4433 (0.4767) grad: 0.1881 (0.3147) time: 0.4964 data: 0.0025 max mem: 25051 +train: [5] [660/800] eta: 0:01:20 lr: 0.000298 loss: 0.4574 (0.4760) grad: 0.1881 (0.3120) time: 0.5058 data: 0.0029 max mem: 25051 +train: [5] [680/800] eta: 0:01:09 lr: 0.000298 loss: 0.4576 (0.4742) grad: 0.1768 (0.3077) time: 0.6999 data: 0.2169 max mem: 25051 +train: [5] [700/800] eta: 0:00:57 lr: 0.000298 loss: 0.4574 (0.4738) grad: 0.1965 (0.3051) time: 0.5410 data: 0.0036 max mem: 25051 +train: [5] [720/800] eta: 0:00:46 lr: 0.000297 loss: 0.4447 (0.4726) grad: 0.1795 (0.3019) time: 0.4857 data: 0.0025 max mem: 25051 +train: [5] [740/800] eta: 0:00:34 lr: 0.000297 loss: 0.4162 (0.4711) grad: 0.1795 (0.3004) time: 0.4988 data: 0.0030 max mem: 25051 +train: [5] [760/800] eta: 0:00:23 lr: 0.000297 loss: 0.4142 (0.4699) grad: 0.1968 (0.2987) time: 0.7705 data: 0.2949 max mem: 25051 +train: [5] [780/800] eta: 0:00:11 lr: 0.000297 loss: 0.4162 (0.4696) grad: 0.1913 (0.2954) time: 0.5016 data: 0.0023 max mem: 25051 +train: [5] [799/800] eta: 0:00:00 lr: 0.000297 loss: 0.4162 (0.4681) grad: 0.1968 (0.2927) time: 0.4820 data: 0.0033 max mem: 25051 +train: [5] Total time: 0:07:40 (0.5755 s / it) +train: [5] Summary: lr: 0.000297 loss: 0.4162 (0.4681) grad: 0.1968 (0.2927) +eval (validation): [5] [ 0/16] eta: 0:01:02 time: 3.9318 data: 3.6695 max mem: 25051 +eval (validation): [5] [15/16] eta: 0:00:00 time: 0.5856 data: 0.2311 max mem: 25051 +eval (validation): [5] Total time: 0:00:09 (0.5965 s / it) +cv: [5] best hparam: (0.23, 1.0) (015) ('015_lr2.3e-01_wd1.0e+00') loss: 0.598 acc: 0.766 f1: 0.756 bacc: 0.752 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/adhd200_dx__patch__attn/checkpoint-last.pth +train: [6] [ 0/800] eta: 0:59:46 lr: nan time: 4.4836 data: 4.0584 max mem: 25051 +train: [6] [ 20/800] eta: 0:09:04 lr: 0.000297 loss: 0.3624 (0.3979) grad: 0.1307 (0.2303) time: 0.5089 data: 0.0023 max mem: 25051 +train: [6] [ 40/800] eta: 0:07:45 lr: 0.000296 loss: 0.4210 (0.4124) grad: 0.1307 (0.1864) time: 0.5212 data: 0.0025 max mem: 25051 +train: [6] [ 60/800] eta: 0:07:10 lr: 0.000296 loss: 0.4210 (0.4144) grad: 0.1611 (0.1906) time: 0.5201 data: 0.0032 max mem: 25051 +train: [6] [ 80/800] eta: 0:07:19 lr: 0.000296 loss: 0.4210 (0.4315) grad: 0.1630 (0.2033) time: 0.6969 data: 0.2147 max mem: 25051 +train: [6] [100/800] eta: 0:06:58 lr: 0.000296 loss: 0.4402 (0.4386) grad: 0.1776 (0.2118) time: 0.5447 data: 0.0028 max mem: 25051 +train: [6] [120/800] eta: 0:06:40 lr: 0.000296 loss: 0.4402 (0.4413) grad: 0.1837 (0.2058) time: 0.5507 data: 0.0035 max mem: 25051 +train: [6] [140/800] eta: 0:06:19 lr: 0.000296 loss: 0.4203 (0.4335) grad: 0.1911 (0.2123) time: 0.4862 data: 0.0023 max mem: 25051 +train: [6] [160/800] eta: 0:06:25 lr: 0.000295 loss: 0.4132 (0.4334) grad: 0.2138 (0.2187) time: 0.7960 data: 0.3032 max mem: 25051 +train: [6] [180/800] eta: 0:06:07 lr: 0.000295 loss: 0.4030 (0.4367) grad: 0.1942 (0.2195) time: 0.5151 data: 0.0023 max mem: 25051 +train: [6] [200/800] eta: 0:05:50 lr: 0.000295 loss: 0.4159 (0.4428) grad: 0.1929 (0.2161) time: 0.5000 data: 0.0025 max mem: 25051 +train: [6] [220/800] eta: 0:05:33 lr: 0.000295 loss: 0.4159 (0.4375) grad: 0.1929 (0.2155) time: 0.4832 data: 0.0080 max mem: 25051 +train: [6] [240/800] eta: 0:05:31 lr: 0.000295 loss: 0.4499 (0.4352) grad: 0.1939 (0.2206) time: 0.7837 data: 0.2331 max mem: 25051 +train: [6] [260/800] eta: 0:05:16 lr: 0.000294 loss: 0.4499 (0.4382) grad: 0.1929 (0.2174) time: 0.5150 data: 0.0032 max mem: 25051 +train: [6] [280/800] eta: 0:05:01 lr: 0.000294 loss: 0.4183 (0.4369) grad: 0.1945 (0.2206) time: 0.5130 data: 0.0036 max mem: 25051 +train: [6] [300/800] eta: 0:04:54 lr: 0.000294 loss: 0.4315 (0.4368) grad: 0.1939 (0.2212) time: 0.7088 data: 0.2277 max mem: 25051 +train: [6] [320/800] eta: 0:04:43 lr: 0.000294 loss: 0.4239 (0.4332) grad: 0.1829 (0.2205) time: 0.5985 data: 0.1084 max mem: 25051 +train: [6] [340/800] eta: 0:04:29 lr: 0.000293 loss: 0.4069 (0.4308) grad: 0.1871 (0.2183) time: 0.5091 data: 0.0105 max mem: 25051 +train: [6] [360/800] eta: 0:04:14 lr: 0.000293 loss: 0.3784 (0.4307) grad: 0.1831 (0.2182) time: 0.4838 data: 0.0027 max mem: 25051 +train: [6] [380/800] eta: 0:04:07 lr: 0.000293 loss: 0.3781 (0.4290) grad: 0.1831 (0.2198) time: 0.7552 data: 0.2717 max mem: 25051 +train: [6] [400/800] eta: 0:03:54 lr: 0.000293 loss: 0.3827 (0.4289) grad: 0.1831 (0.2192) time: 0.5371 data: 0.0282 max mem: 25051 +train: [6] [420/800] eta: 0:03:41 lr: 0.000292 loss: 0.3859 (0.4275) grad: 0.1650 (0.2182) time: 0.4996 data: 0.0025 max mem: 25051 +train: [6] [440/800] eta: 0:03:28 lr: 0.000292 loss: 0.3827 (0.4249) grad: 0.1650 (0.2188) time: 0.4991 data: 0.0030 max mem: 25051 +train: [6] [460/800] eta: 0:03:19 lr: 0.000292 loss: 0.3746 (0.4259) grad: 0.1474 (0.2143) time: 0.7660 data: 0.2599 max mem: 25051 +train: [6] [480/800] eta: 0:03:06 lr: 0.000292 loss: 0.3746 (0.4246) grad: 0.1359 (0.2116) time: 0.5077 data: 0.0024 max mem: 25051 +train: [6] [500/800] eta: 0:02:53 lr: 0.000291 loss: 0.3627 (0.4230) grad: 0.1177 (0.2072) time: 0.4965 data: 0.0025 max mem: 25051 +train: [6] [520/800] eta: 0:02:41 lr: 0.000291 loss: 0.3627 (0.4213) grad: 0.1167 (0.2041) time: 0.4837 data: 0.0032 max mem: 25051 +train: [6] [540/800] eta: 0:02:30 lr: 0.000291 loss: 0.3650 (0.4212) grad: 0.1189 (0.2035) time: 0.7042 data: 0.2238 max mem: 25051 +train: [6] [560/800] eta: 0:02:18 lr: 0.000291 loss: 0.3693 (0.4201) grad: 0.1150 (0.2016) time: 0.5048 data: 0.0033 max mem: 25051 +train: [6] [580/800] eta: 0:02:06 lr: 0.000290 loss: 0.3775 (0.4185) grad: 0.1509 (0.2020) time: 0.4823 data: 0.0034 max mem: 25051 +train: [6] [600/800] eta: 0:01:55 lr: 0.000290 loss: 0.3917 (0.4178) grad: 0.1509 (0.2002) time: 0.7324 data: 0.2341 max mem: 25051 +train: [6] [620/800] eta: 0:01:44 lr: 0.000290 loss: 0.3917 (0.4186) grad: 0.1624 (0.1998) time: 0.5647 data: 0.0025 max mem: 25051 +train: [6] [640/800] eta: 0:01:32 lr: 0.000290 loss: 0.3775 (0.4174) grad: 0.1484 (0.1983) time: 0.4902 data: 0.0026 max mem: 25051 +train: [6] [660/800] eta: 0:01:20 lr: 0.000289 loss: 0.4080 (0.4191) grad: 0.1414 (0.1963) time: 0.5012 data: 0.0033 max mem: 25051 +train: [6] [680/800] eta: 0:01:09 lr: 0.000289 loss: 0.4561 (0.4197) grad: 0.1441 (0.1970) time: 0.7047 data: 0.2230 max mem: 25051 +train: [6] [700/800] eta: 0:00:57 lr: 0.000289 loss: 0.4186 (0.4193) grad: 0.1484 (0.1977) time: 0.5240 data: 0.0265 max mem: 25051 +train: [6] [720/800] eta: 0:00:46 lr: 0.000288 loss: 0.4186 (0.4190) grad: 0.1562 (0.1985) time: 0.5260 data: 0.0059 max mem: 25051 +train: [6] [740/800] eta: 0:00:34 lr: 0.000288 loss: 0.4046 (0.4182) grad: 0.2030 (0.1987) time: 0.4961 data: 0.0027 max mem: 25051 +train: [6] [760/800] eta: 0:00:23 lr: 0.000288 loss: 0.3979 (0.4177) grad: 0.2030 (0.1990) time: 0.7281 data: 0.2235 max mem: 25051 +train: [6] [780/800] eta: 0:00:11 lr: 0.000287 loss: 0.3860 (0.4172) grad: 0.1723 (0.1982) time: 0.5224 data: 0.0027 max mem: 25051 +train: [6] [799/800] eta: 0:00:00 lr: 0.000287 loss: 0.3896 (0.4172) grad: 0.1723 (0.1984) time: 0.4847 data: 0.0030 max mem: 25051 +train: [6] Total time: 0:07:39 (0.5739 s / it) +train: [6] Summary: lr: 0.000287 loss: 0.3896 (0.4172) grad: 0.1723 (0.1984) +eval (validation): [6] [ 0/16] eta: 0:01:08 time: 4.3119 data: 4.0420 max mem: 25051 +eval (validation): [6] [15/16] eta: 0:00:00 time: 0.6300 data: 0.2542 max mem: 25051 +eval (validation): [6] Total time: 0:00:10 (0.6461 s / it) +cv: [6] best hparam: (0.074, 1.0) (008) ('008_lr7.4e-02_wd1.0e+00') loss: 0.607 acc: 0.781 f1: 0.770 bacc: 0.766 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/adhd200_dx__patch__attn/checkpoint-last.pth +train: [7] [ 0/800] eta: 1:01:07 lr: nan time: 4.5838 data: 4.2238 max mem: 25051 +train: [7] [ 20/800] eta: 0:09:51 lr: 0.000287 loss: 0.3441 (0.3481) grad: 0.1260 (0.1824) time: 0.5673 data: 0.0030 max mem: 25051 +train: [7] [ 40/800] eta: 0:08:18 lr: 0.000286 loss: 0.4029 (0.4623) grad: 0.1726 (0.1964) time: 0.5489 data: 0.0036 max mem: 25051 +train: [7] [ 60/800] eta: 0:07:39 lr: 0.000286 loss: 0.3892 (0.4333) grad: 0.2007 (0.2076) time: 0.5504 data: 0.0036 max mem: 25051 +train: [7] [ 80/800] eta: 0:07:46 lr: 0.000286 loss: 0.3892 (0.4223) grad: 0.1897 (0.1933) time: 0.7260 data: 0.2153 max mem: 25051 +train: [7] [100/800] eta: 0:07:11 lr: 0.000285 loss: 0.4200 (0.4212) grad: 0.1916 (0.2063) time: 0.4903 data: 0.0030 max mem: 25051 +train: [7] [120/800] eta: 0:06:43 lr: 0.000285 loss: 0.3871 (0.4207) grad: 0.2007 (0.2068) time: 0.4763 data: 0.0031 max mem: 25051 +train: [7] [140/800] eta: 0:06:22 lr: 0.000285 loss: 0.4267 (0.4246) grad: 0.1916 (0.2109) time: 0.4967 data: 0.0033 max mem: 25051 +train: [7] [160/800] eta: 0:06:22 lr: 0.000284 loss: 0.4125 (0.4189) grad: 0.2045 (0.2111) time: 0.7250 data: 0.2253 max mem: 25051 +train: [7] [180/800] eta: 0:06:04 lr: 0.000284 loss: 0.4125 (0.4132) grad: 0.1992 (0.2088) time: 0.5076 data: 0.0026 max mem: 25051 +train: [7] [200/800] eta: 0:05:47 lr: 0.000284 loss: 0.4125 (0.4113) grad: 0.1832 (0.2122) time: 0.4989 data: 0.0033 max mem: 25051 +train: [7] [220/800] eta: 0:05:30 lr: 0.000283 loss: 0.3687 (0.4087) grad: 0.1983 (0.2153) time: 0.4781 data: 0.0026 max mem: 25051 +train: [7] [240/800] eta: 0:05:25 lr: 0.000283 loss: 0.3687 (0.4082) grad: 0.1961 (0.2146) time: 0.7199 data: 0.2112 max mem: 25051 +train: [7] [260/800] eta: 0:05:11 lr: 0.000283 loss: 0.3765 (0.4070) grad: 0.1983 (0.2168) time: 0.5158 data: 0.0028 max mem: 25051 +train: [7] [280/800] eta: 0:04:57 lr: 0.000282 loss: 0.3765 (0.4053) grad: 0.1936 (0.2112) time: 0.5124 data: 0.0023 max mem: 25051 +train: [7] [300/800] eta: 0:04:50 lr: 0.000282 loss: 0.3718 (0.4013) grad: 0.1560 (0.2059) time: 0.7079 data: 0.2223 max mem: 25051 +train: [7] [320/800] eta: 0:04:37 lr: 0.000282 loss: 0.3666 (0.3986) grad: 0.1278 (0.2025) time: 0.5401 data: 0.0422 max mem: 25051 +train: [7] [340/800] eta: 0:04:24 lr: 0.000281 loss: 0.3553 (0.3983) grad: 0.1253 (0.2006) time: 0.4994 data: 0.0026 max mem: 25051 +train: [7] [360/800] eta: 0:04:10 lr: 0.000281 loss: 0.3653 (0.3994) grad: 0.1476 (0.2004) time: 0.5060 data: 0.0032 max mem: 25051 +train: [7] [380/800] eta: 0:04:03 lr: 0.000280 loss: 0.3492 (0.3986) grad: 0.1559 (0.1991) time: 0.7302 data: 0.2235 max mem: 25051 +train: [7] [400/800] eta: 0:03:50 lr: 0.000280 loss: 0.3482 (0.3965) grad: 0.1350 (0.1952) time: 0.5095 data: 0.0027 max mem: 25051 +train: [7] [420/800] eta: 0:03:37 lr: 0.000280 loss: 0.3482 (0.3971) grad: 0.1559 (0.1992) time: 0.4873 data: 0.0032 max mem: 25051 +train: [7] [440/800] eta: 0:03:24 lr: 0.000279 loss: 0.3453 (0.3954) grad: 0.1482 (0.1978) time: 0.4927 data: 0.0034 max mem: 25051 +train: [7] [460/800] eta: 0:03:15 lr: 0.000279 loss: 0.3631 (0.3964) grad: 0.1482 (0.1951) time: 0.7574 data: 0.2484 max mem: 25051 +train: [7] [480/800] eta: 0:03:03 lr: 0.000278 loss: 0.4052 (0.3969) grad: 0.1607 (0.1935) time: 0.4936 data: 0.0023 max mem: 25051 +train: [7] [500/800] eta: 0:02:50 lr: 0.000278 loss: 0.4056 (0.3972) grad: 0.1455 (0.1932) time: 0.5007 data: 0.0031 max mem: 25051 +train: [7] [520/800] eta: 0:02:38 lr: 0.000278 loss: 0.4106 (0.3969) grad: 0.1455 (0.1935) time: 0.5034 data: 0.0026 max mem: 25051 +train: [7] [540/800] eta: 0:02:29 lr: 0.000277 loss: 0.4056 (0.3964) grad: 0.1826 (0.1953) time: 0.7706 data: 0.2247 max mem: 25051 +train: [7] [560/800] eta: 0:02:17 lr: 0.000277 loss: 0.4106 (0.3970) grad: 0.2062 (0.1955) time: 0.4931 data: 0.0027 max mem: 25051 +train: [7] [580/800] eta: 0:02:05 lr: 0.000276 loss: 0.3813 (0.3957) grad: 0.1431 (0.1940) time: 0.4965 data: 0.0031 max mem: 25051 +train: [7] [600/800] eta: 0:01:54 lr: 0.000276 loss: 0.4132 (0.3980) grad: 0.1371 (0.1936) time: 0.7099 data: 0.2320 max mem: 25051 +train: [7] [620/800] eta: 0:01:42 lr: 0.000275 loss: 0.4004 (0.3975) grad: 0.1371 (0.1946) time: 0.4991 data: 0.0032 max mem: 25051 +train: [7] [640/800] eta: 0:01:30 lr: 0.000275 loss: 0.3656 (0.3962) grad: 0.1417 (0.1943) time: 0.4863 data: 0.0025 max mem: 25051 +train: [7] [660/800] eta: 0:01:19 lr: 0.000275 loss: 0.3788 (0.3946) grad: 0.1483 (0.1952) time: 0.5075 data: 0.0036 max mem: 25051 +train: [7] [680/800] eta: 0:01:08 lr: 0.000274 loss: 0.3522 (0.3938) grad: 0.1692 (0.1963) time: 0.7330 data: 0.2210 max mem: 25051 +train: [7] [700/800] eta: 0:00:57 lr: 0.000274 loss: 0.3366 (0.3929) grad: 0.2001 (0.1981) time: 0.5187 data: 0.0041 max mem: 25051 +train: [7] [720/800] eta: 0:00:45 lr: 0.000273 loss: 0.3467 (0.3927) grad: 0.1999 (0.1975) time: 0.5037 data: 0.0036 max mem: 25051 +train: [7] [740/800] eta: 0:00:33 lr: 0.000273 loss: 0.3721 (0.3939) grad: 0.2098 (0.1985) time: 0.4982 data: 0.0032 max mem: 25051 +train: [7] [760/800] eta: 0:00:22 lr: 0.000272 loss: 0.3651 (0.3939) grad: 0.2313 (0.2008) time: 0.7466 data: 0.2476 max mem: 25051 +train: [7] [780/800] eta: 0:00:11 lr: 0.000272 loss: 0.3651 (0.3932) grad: 0.2078 (0.2016) time: 0.4937 data: 0.0027 max mem: 25051 +train: [7] [799/800] eta: 0:00:00 lr: 0.000271 loss: 0.3637 (0.3933) grad: 0.2078 (0.2004) time: 0.4969 data: 0.0027 max mem: 25051 +train: [7] Total time: 0:07:34 (0.5678 s / it) +train: [7] Summary: lr: 0.000271 loss: 0.3637 (0.3933) grad: 0.2078 (0.2004) +eval (validation): [7] [ 0/16] eta: 0:01:12 time: 4.5040 data: 4.2413 max mem: 25051 +eval (validation): [7] [15/16] eta: 0:00:00 time: 0.7169 data: 0.3458 max mem: 25051 +eval (validation): [7] Total time: 0:00:11 (0.7326 s / it) +cv: [7] best hparam: (0.053, 1.0) (006) ('006_lr5.3e-02_wd1.0e+00') loss: 0.608 acc: 0.781 f1: 0.770 bacc: 0.766 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/adhd200_dx__patch__attn/checkpoint-last.pth +train: [8] [ 0/800] eta: 1:00:01 lr: nan time: 4.5016 data: 4.1476 max mem: 25051 +train: [8] [ 20/800] eta: 0:08:43 lr: 0.000271 loss: 0.3052 (0.3012) grad: 0.1307 (0.1589) time: 0.4794 data: 0.0019 max mem: 25051 +train: [8] [ 40/800] eta: 0:07:39 lr: 0.000270 loss: 0.3236 (0.3715) grad: 0.1405 (0.1599) time: 0.5351 data: 0.0394 max mem: 25051 +train: [8] [ 60/800] eta: 0:07:09 lr: 0.000270 loss: 0.3303 (0.3835) grad: 0.1636 (0.1712) time: 0.5299 data: 0.0127 max mem: 25051 +train: [8] [ 80/800] eta: 0:07:22 lr: 0.000270 loss: 0.3528 (0.3835) grad: 0.1635 (0.1846) time: 0.7208 data: 0.2074 max mem: 25051 +train: [8] [100/800] eta: 0:07:02 lr: 0.000269 loss: 0.3619 (0.3766) grad: 0.1741 (0.2019) time: 0.5553 data: 0.0030 max mem: 25051 +train: [8] [120/800] eta: 0:06:39 lr: 0.000269 loss: 0.3528 (0.3777) grad: 0.1821 (0.1968) time: 0.5085 data: 0.0035 max mem: 25051 +train: [8] [140/800] eta: 0:06:19 lr: 0.000268 loss: 0.3619 (0.3833) grad: 0.1635 (0.1940) time: 0.5044 data: 0.0032 max mem: 25051 +train: [8] [160/800] eta: 0:06:21 lr: 0.000268 loss: 0.3450 (0.3862) grad: 0.1469 (0.1894) time: 0.7410 data: 0.2271 max mem: 25051 +train: [8] [180/800] eta: 0:06:03 lr: 0.000267 loss: 0.3731 (0.3867) grad: 0.1444 (0.1874) time: 0.5107 data: 0.0030 max mem: 25051 +train: [8] [200/800] eta: 0:05:46 lr: 0.000267 loss: 0.3731 (0.3908) grad: 0.1444 (0.1882) time: 0.4904 data: 0.0029 max mem: 25051 +train: [8] [220/800] eta: 0:05:30 lr: 0.000266 loss: 0.3731 (0.3896) grad: 0.1444 (0.1928) time: 0.4867 data: 0.0029 max mem: 25051 +train: [8] [240/800] eta: 0:05:26 lr: 0.000266 loss: 0.4090 (0.3914) grad: 0.1484 (0.1991) time: 0.7298 data: 0.2404 max mem: 25051 +train: [8] [260/800] eta: 0:05:12 lr: 0.000265 loss: 0.4188 (0.3928) grad: 0.1546 (0.2013) time: 0.5321 data: 0.0272 max mem: 25051 +train: [8] [280/800] eta: 0:04:57 lr: 0.000265 loss: 0.4034 (0.3916) grad: 0.1533 (0.1973) time: 0.4880 data: 0.0028 max mem: 25051 +train: [8] [300/800] eta: 0:04:49 lr: 0.000264 loss: 0.3689 (0.3886) grad: 0.1568 (0.1975) time: 0.6646 data: 0.2065 max mem: 25051 +train: [8] [320/800] eta: 0:04:35 lr: 0.000264 loss: 0.3421 (0.3865) grad: 0.1716 (0.2006) time: 0.4939 data: 0.0030 max mem: 25051 +train: [8] [340/800] eta: 0:04:21 lr: 0.000263 loss: 0.3421 (0.3859) grad: 0.1786 (0.2020) time: 0.4992 data: 0.0025 max mem: 25051 +train: [8] [360/800] eta: 0:04:08 lr: 0.000263 loss: 0.3421 (0.3844) grad: 0.2088 (0.2031) time: 0.4833 data: 0.0021 max mem: 25051 +train: [8] [380/800] eta: 0:04:00 lr: 0.000262 loss: 0.3455 (0.3831) grad: 0.2007 (0.2025) time: 0.7265 data: 0.2223 max mem: 25051 +train: [8] [400/800] eta: 0:03:47 lr: 0.000262 loss: 0.3515 (0.3832) grad: 0.1786 (0.2010) time: 0.4945 data: 0.0030 max mem: 25051 +train: [8] [420/800] eta: 0:03:34 lr: 0.000261 loss: 0.3494 (0.3824) grad: 0.1764 (0.1998) time: 0.4822 data: 0.0026 max mem: 25051 +train: [8] [440/800] eta: 0:03:21 lr: 0.000260 loss: 0.3515 (0.3834) grad: 0.1717 (0.1996) time: 0.4742 data: 0.0030 max mem: 25051 +train: [8] [460/800] eta: 0:03:12 lr: 0.000260 loss: 0.3780 (0.3840) grad: 0.1631 (0.2001) time: 0.7061 data: 0.2185 max mem: 25051 +train: [8] [480/800] eta: 0:03:01 lr: 0.000259 loss: 0.3825 (0.3849) grad: 0.1696 (0.1985) time: 0.5476 data: 0.0026 max mem: 25051 +train: [8] [500/800] eta: 0:02:49 lr: 0.000259 loss: 0.3825 (0.3835) grad: 0.1696 (0.1969) time: 0.5424 data: 0.0037 max mem: 25051 +train: [8] [520/800] eta: 0:02:37 lr: 0.000258 loss: 0.3751 (0.3819) grad: 0.1640 (0.1966) time: 0.4939 data: 0.0032 max mem: 25051 +train: [8] [540/800] eta: 0:02:28 lr: 0.000258 loss: 0.3785 (0.3828) grad: 0.1640 (0.1979) time: 0.7703 data: 0.2567 max mem: 25051 +train: [8] [560/800] eta: 0:02:16 lr: 0.000257 loss: 0.3785 (0.3828) grad: 0.1667 (0.1987) time: 0.5227 data: 0.0033 max mem: 25051 +train: [8] [580/800] eta: 0:02:04 lr: 0.000257 loss: 0.3785 (0.3812) grad: 0.1640 (0.1981) time: 0.5105 data: 0.0031 max mem: 25051 +train: [8] [600/800] eta: 0:01:54 lr: 0.000256 loss: 0.3809 (0.3822) grad: 0.1815 (0.2028) time: 0.6918 data: 0.2199 max mem: 25051 +train: [8] [620/800] eta: 0:01:42 lr: 0.000256 loss: 0.3416 (0.3802) grad: 0.1767 (0.2021) time: 0.5124 data: 0.0027 max mem: 25051 +train: [8] [640/800] eta: 0:01:30 lr: 0.000255 loss: 0.3492 (0.3808) grad: 0.1896 (0.2019) time: 0.5028 data: 0.0029 max mem: 25051 +train: [8] [660/800] eta: 0:01:18 lr: 0.000254 loss: 0.3492 (0.3793) grad: 0.1967 (0.2017) time: 0.4909 data: 0.0033 max mem: 25051 +train: [8] [680/800] eta: 0:01:08 lr: 0.000254 loss: 0.3473 (0.3794) grad: 0.1584 (0.2016) time: 0.8047 data: 0.3121 max mem: 25051 +train: [8] [700/800] eta: 0:00:57 lr: 0.000253 loss: 0.3718 (0.3794) grad: 0.1584 (0.2012) time: 0.5296 data: 0.0033 max mem: 25051 +train: [8] [720/800] eta: 0:00:45 lr: 0.000253 loss: 0.3473 (0.3792) grad: 0.1511 (0.2000) time: 0.5005 data: 0.0251 max mem: 25051 +train: [8] [740/800] eta: 0:00:33 lr: 0.000252 loss: 0.3459 (0.3783) grad: 0.1452 (0.1978) time: 0.4705 data: 0.0021 max mem: 25051 +train: [8] [760/800] eta: 0:00:22 lr: 0.000252 loss: 0.3379 (0.3771) grad: 0.1238 (0.1970) time: 0.7131 data: 0.2198 max mem: 25051 +train: [8] [780/800] eta: 0:00:11 lr: 0.000251 loss: 0.3368 (0.3762) grad: 0.1452 (0.1986) time: 0.5276 data: 0.0025 max mem: 25051 +train: [8] [799/800] eta: 0:00:00 lr: 0.000250 loss: 0.3377 (0.3763) grad: 0.1507 (0.2004) time: 0.5181 data: 0.0030 max mem: 25051 +train: [8] Total time: 0:07:33 (0.5673 s / it) +train: [8] Summary: lr: 0.000250 loss: 0.3377 (0.3763) grad: 0.1507 (0.2004) +eval (validation): [8] [ 0/16] eta: 0:01:08 time: 4.2807 data: 4.0346 max mem: 25051 +eval (validation): [8] [15/16] eta: 0:00:00 time: 0.6033 data: 0.2611 max mem: 25051 +eval (validation): [8] Total time: 0:00:09 (0.6208 s / it) +cv: [8] best hparam: (0.1, 1.0) (010) ('010_lr1.0e-01_wd1.0e+00') loss: 0.593 acc: 0.781 f1: 0.773 bacc: 0.770 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/adhd200_dx__patch__attn/checkpoint-last.pth +train: [9] [ 0/800] eta: 1:01:38 lr: nan time: 4.6233 data: 4.2249 max mem: 25051 +train: [9] [ 20/800] eta: 0:09:36 lr: 0.000250 loss: 0.3441 (0.3597) grad: 0.1879 (0.1963) time: 0.5452 data: 0.0024 max mem: 25051 +train: [9] [ 40/800] eta: 0:07:50 lr: 0.000249 loss: 0.3441 (0.3688) grad: 0.1833 (0.1961) time: 0.4934 data: 0.0031 max mem: 25051 +train: [9] [ 60/800] eta: 0:07:07 lr: 0.000249 loss: 0.3996 (0.3769) grad: 0.1879 (0.2106) time: 0.4905 data: 0.0032 max mem: 25051 +train: [9] [ 80/800] eta: 0:07:18 lr: 0.000248 loss: 0.3996 (0.3798) grad: 0.1860 (0.2090) time: 0.7039 data: 0.2050 max mem: 25051 +train: [9] [100/800] eta: 0:06:50 lr: 0.000248 loss: 0.3695 (0.3781) grad: 0.1885 (0.2153) time: 0.4962 data: 0.0030 max mem: 25051 +train: [9] [120/800] eta: 0:06:30 lr: 0.000247 loss: 0.3695 (0.3779) grad: 0.1924 (0.2299) time: 0.5138 data: 0.0033 max mem: 25051 +train: [9] [140/800] eta: 0:06:11 lr: 0.000246 loss: 0.3569 (0.3742) grad: 0.2058 (0.2364) time: 0.4989 data: 0.0032 max mem: 25051 +train: [9] [160/800] eta: 0:06:12 lr: 0.000246 loss: 0.3695 (0.3766) grad: 0.2058 (0.2332) time: 0.7139 data: 0.2094 max mem: 25051 +train: [9] [180/800] eta: 0:05:56 lr: 0.000245 loss: 0.3569 (0.3727) grad: 0.1845 (0.2239) time: 0.5212 data: 0.0026 max mem: 25051 +train: [9] [200/800] eta: 0:05:41 lr: 0.000244 loss: 0.3499 (0.3704) grad: 0.1834 (0.2254) time: 0.5188 data: 0.0027 max mem: 25051 +train: [9] [220/800] eta: 0:05:26 lr: 0.000244 loss: 0.3428 (0.3735) grad: 0.1845 (0.2290) time: 0.5003 data: 0.0031 max mem: 25051 +train: [9] [240/800] eta: 0:05:23 lr: 0.000243 loss: 0.3410 (0.3727) grad: 0.2007 (0.2280) time: 0.7244 data: 0.2156 max mem: 25051 +train: [9] [260/800] eta: 0:05:07 lr: 0.000243 loss: 0.3623 (0.3758) grad: 0.2063 (0.2254) time: 0.4904 data: 0.0034 max mem: 25051 +train: [9] [280/800] eta: 0:04:53 lr: 0.000242 loss: 0.3743 (0.3744) grad: 0.1981 (0.2229) time: 0.4994 data: 0.0024 max mem: 25051 +train: [9] [300/800] eta: 0:04:47 lr: 0.000241 loss: 0.3783 (0.3747) grad: 0.1845 (0.2191) time: 0.7088 data: 0.2286 max mem: 25051 +train: [9] [320/800] eta: 0:04:34 lr: 0.000241 loss: 0.3831 (0.3767) grad: 0.1515 (0.2145) time: 0.5385 data: 0.0102 max mem: 25051 +train: [9] [340/800] eta: 0:04:22 lr: 0.000240 loss: 0.3932 (0.3777) grad: 0.1437 (0.2119) time: 0.5238 data: 0.0025 max mem: 25051 +train: [9] [360/800] eta: 0:04:09 lr: 0.000240 loss: 0.3884 (0.3766) grad: 0.1223 (0.2079) time: 0.5055 data: 0.0025 max mem: 25051 +train: [9] [380/800] eta: 0:04:00 lr: 0.000239 loss: 0.3838 (0.3752) grad: 0.1343 (0.2097) time: 0.7033 data: 0.2329 max mem: 25051 +train: [9] [400/800] eta: 0:03:48 lr: 0.000238 loss: 0.3781 (0.3755) grad: 0.1355 (0.2066) time: 0.5223 data: 0.0027 max mem: 25051 +train: [9] [420/800] eta: 0:03:36 lr: 0.000238 loss: 0.3274 (0.3719) grad: 0.1355 (0.2035) time: 0.5264 data: 0.0404 max mem: 25051 +train: [9] [440/800] eta: 0:03:23 lr: 0.000237 loss: 0.3274 (0.3702) grad: 0.1355 (0.2002) time: 0.5115 data: 0.0286 max mem: 25051 +train: [9] [460/800] eta: 0:03:14 lr: 0.000236 loss: 0.3329 (0.3701) grad: 0.1314 (0.1974) time: 0.7243 data: 0.2194 max mem: 25051 +train: [9] [480/800] eta: 0:03:01 lr: 0.000236 loss: 0.3425 (0.3713) grad: 0.1405 (0.1970) time: 0.4722 data: 0.0032 max mem: 25051 +train: [9] [500/800] eta: 0:02:49 lr: 0.000235 loss: 0.3438 (0.3687) grad: 0.1371 (0.1961) time: 0.5037 data: 0.0028 max mem: 25051 +train: [9] [520/800] eta: 0:02:37 lr: 0.000234 loss: 0.3613 (0.3688) grad: 0.1525 (0.1971) time: 0.5096 data: 0.0029 max mem: 25051 +train: [9] [540/800] eta: 0:02:28 lr: 0.000234 loss: 0.3510 (0.3700) grad: 0.1699 (0.1967) time: 0.7230 data: 0.2282 max mem: 25051 +train: [9] [560/800] eta: 0:02:16 lr: 0.000233 loss: 0.3510 (0.3702) grad: 0.1725 (0.1959) time: 0.5074 data: 0.0029 max mem: 25051 +train: [9] [580/800] eta: 0:02:04 lr: 0.000232 loss: 0.3719 (0.3695) grad: 0.2021 (0.1960) time: 0.5504 data: 0.0031 max mem: 25051 +train: [9] [600/800] eta: 0:01:55 lr: 0.000232 loss: 0.3609 (0.3685) grad: 0.2042 (0.1963) time: 0.8432 data: 0.3271 max mem: 25051 +train: [9] [620/800] eta: 0:01:43 lr: 0.000231 loss: 0.3592 (0.3684) grad: 0.2042 (0.1977) time: 0.5081 data: 0.0021 max mem: 25051 +train: [9] [640/800] eta: 0:01:31 lr: 0.000230 loss: 0.3609 (0.3684) grad: 0.2042 (0.1976) time: 0.4916 data: 0.0029 max mem: 25051 +train: [9] [660/800] eta: 0:01:19 lr: 0.000230 loss: 0.3690 (0.3697) grad: 0.1900 (0.1975) time: 0.4935 data: 0.0027 max mem: 25051 +train: [9] [680/800] eta: 0:01:08 lr: 0.000229 loss: 0.3720 (0.3696) grad: 0.1579 (0.1979) time: 0.7167 data: 0.2095 max mem: 25051 +train: [9] [700/800] eta: 0:00:57 lr: 0.000228 loss: 0.3720 (0.3690) grad: 0.1727 (0.1976) time: 0.4774 data: 0.0027 max mem: 25051 +train: [9] [720/800] eta: 0:00:45 lr: 0.000228 loss: 0.3516 (0.3693) grad: 0.1505 (0.1970) time: 0.4983 data: 0.0029 max mem: 25051 +train: [9] [740/800] eta: 0:00:33 lr: 0.000227 loss: 0.3516 (0.3698) grad: 0.1579 (0.1968) time: 0.4857 data: 0.0030 max mem: 25051 +train: [9] [760/800] eta: 0:00:22 lr: 0.000226 loss: 0.3588 (0.3701) grad: 0.1727 (0.1975) time: 0.7133 data: 0.2119 max mem: 25051 +train: [9] [780/800] eta: 0:00:11 lr: 0.000226 loss: 0.3588 (0.3700) grad: 0.1620 (0.1976) time: 0.4824 data: 0.0026 max mem: 25051 +train: [9] [799/800] eta: 0:00:00 lr: 0.000225 loss: 0.3686 (0.3700) grad: 0.1620 (0.1966) time: 0.4770 data: 0.0028 max mem: 25051 +train: [9] Total time: 0:07:32 (0.5662 s / it) +train: [9] Summary: lr: 0.000225 loss: 0.3686 (0.3700) grad: 0.1620 (0.1966) +eval (validation): [9] [ 0/16] eta: 0:01:13 time: 4.5758 data: 4.2425 max mem: 25051 +eval (validation): [9] [15/16] eta: 0:00:00 time: 0.6837 data: 0.2671 max mem: 25051 +eval (validation): [9] Total time: 0:00:11 (0.6985 s / it) +cv: [9] best hparam: (0.087, 1.0) (009) ('009_lr8.7e-02_wd1.0e+00') loss: 0.594 acc: 0.797 f1: 0.788 bacc: 0.784 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/adhd200_dx__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/adhd200_dx__patch__attn/checkpoint-best.pth +train: [10] [ 0/800] eta: 0:58:34 lr: nan time: 4.3932 data: 3.9632 max mem: 25051 +train: [10] [ 20/800] eta: 0:09:15 lr: 0.000224 loss: 0.4077 (0.3667) grad: 0.1596 (0.1646) time: 0.5275 data: 0.0027 max mem: 25051 +train: [10] [ 40/800] eta: 0:07:46 lr: 0.000224 loss: 0.4194 (0.4127) grad: 0.1305 (0.1518) time: 0.5121 data: 0.0027 max mem: 25051 +train: [10] [ 60/800] eta: 0:07:06 lr: 0.000223 loss: 0.4179 (0.3930) grad: 0.1596 (0.1556) time: 0.5003 data: 0.0034 max mem: 25051 +train: [10] [ 80/800] eta: 0:07:23 lr: 0.000222 loss: 0.3934 (0.3827) grad: 0.1353 (0.1553) time: 0.7332 data: 0.2188 max mem: 25051 +train: [10] [100/800] eta: 0:06:52 lr: 0.000222 loss: 0.3681 (0.3693) grad: 0.1281 (0.1471) time: 0.4818 data: 0.0029 max mem: 25051 +train: [10] [120/800] eta: 0:06:29 lr: 0.000221 loss: 0.3171 (0.3640) grad: 0.1187 (0.1441) time: 0.4934 data: 0.0029 max mem: 25051 +train: [10] [140/800] eta: 0:06:11 lr: 0.000220 loss: 0.3171 (0.3675) grad: 0.1187 (0.1494) time: 0.4958 data: 0.0027 max mem: 25051 +train: [10] [160/800] eta: 0:06:11 lr: 0.000220 loss: 0.3139 (0.3634) grad: 0.1162 (0.1505) time: 0.7124 data: 0.2302 max mem: 25051 +train: [10] [180/800] eta: 0:05:55 lr: 0.000219 loss: 0.3641 (0.3661) grad: 0.1151 (0.1476) time: 0.5065 data: 0.0042 max mem: 25051 +train: [10] [200/800] eta: 0:05:39 lr: 0.000218 loss: 0.3641 (0.3650) grad: 0.1233 (0.1568) time: 0.5006 data: 0.0032 max mem: 25051 +train: [10] [220/800] eta: 0:05:23 lr: 0.000217 loss: 0.3785 (0.3681) grad: 0.1294 (0.1571) time: 0.4801 data: 0.0021 max mem: 25051 +train: [10] [240/800] eta: 0:05:22 lr: 0.000217 loss: 0.3417 (0.3642) grad: 0.1594 (0.1584) time: 0.7748 data: 0.2266 max mem: 25051 +train: [10] [260/800] eta: 0:05:07 lr: 0.000216 loss: 0.3322 (0.3606) grad: 0.1473 (0.1556) time: 0.4912 data: 0.0028 max mem: 25051 +train: [10] [280/800] eta: 0:04:53 lr: 0.000215 loss: 0.3307 (0.3583) grad: 0.1300 (0.1577) time: 0.5003 data: 0.0033 max mem: 25051 +train: [10] [300/800] eta: 0:04:47 lr: 0.000215 loss: 0.3260 (0.3593) grad: 0.1454 (0.1646) time: 0.7155 data: 0.2294 max mem: 25051 +train: [10] [320/800] eta: 0:04:33 lr: 0.000214 loss: 0.3260 (0.3588) grad: 0.1454 (0.1638) time: 0.5016 data: 0.0019 max mem: 25051 +train: [10] [340/800] eta: 0:04:20 lr: 0.000213 loss: 0.3483 (0.3593) grad: 0.1487 (0.1644) time: 0.4998 data: 0.0029 max mem: 25051 +train: [10] [360/800] eta: 0:04:07 lr: 0.000213 loss: 0.3483 (0.3584) grad: 0.1636 (0.1639) time: 0.5054 data: 0.0025 max mem: 25051 +train: [10] [380/800] eta: 0:03:59 lr: 0.000212 loss: 0.3483 (0.3590) grad: 0.1636 (0.1648) time: 0.6891 data: 0.2205 max mem: 25051 +train: [10] [400/800] eta: 0:03:46 lr: 0.000211 loss: 0.3454 (0.3582) grad: 0.1636 (0.1666) time: 0.5099 data: 0.0223 max mem: 25051 +train: [10] [420/800] eta: 0:03:34 lr: 0.000210 loss: 0.3357 (0.3579) grad: 0.1758 (0.1700) time: 0.5231 data: 0.0175 max mem: 25051 +train: [10] [440/800] eta: 0:03:21 lr: 0.000210 loss: 0.3292 (0.3563) grad: 0.1806 (0.1719) time: 0.4849 data: 0.0021 max mem: 25051 +train: [10] [460/800] eta: 0:03:13 lr: 0.000209 loss: 0.3300 (0.3558) grad: 0.1923 (0.1737) time: 0.7300 data: 0.2407 max mem: 25051 +train: [10] [480/800] eta: 0:03:01 lr: 0.000208 loss: 0.3465 (0.3576) grad: 0.1880 (0.1750) time: 0.5232 data: 0.0220 max mem: 25051 +train: [10] [500/800] eta: 0:02:49 lr: 0.000207 loss: 0.3264 (0.3553) grad: 0.1880 (0.1778) time: 0.5252 data: 0.0024 max mem: 25051 +train: [10] [520/800] eta: 0:02:37 lr: 0.000207 loss: 0.3465 (0.3561) grad: 0.2003 (0.1809) time: 0.5073 data: 0.0025 max mem: 25051 +train: [10] [540/800] eta: 0:02:27 lr: 0.000206 loss: 0.3651 (0.3567) grad: 0.2045 (0.1833) time: 0.6922 data: 0.2184 max mem: 25051 +train: [10] [560/800] eta: 0:02:15 lr: 0.000205 loss: 0.3581 (0.3568) grad: 0.2106 (0.1842) time: 0.4883 data: 0.0028 max mem: 25051 +train: [10] [580/800] eta: 0:02:03 lr: 0.000205 loss: 0.3651 (0.3568) grad: 0.2268 (0.1865) time: 0.4951 data: 0.0033 max mem: 25051 +train: [10] [600/800] eta: 0:01:53 lr: 0.000204 loss: 0.3436 (0.3551) grad: 0.2033 (0.1860) time: 0.6824 data: 0.2170 max mem: 25051 +train: [10] [620/800] eta: 0:01:41 lr: 0.000203 loss: 0.3436 (0.3558) grad: 0.2148 (0.1883) time: 0.5186 data: 0.0152 max mem: 25051 +train: [10] [640/800] eta: 0:01:30 lr: 0.000202 loss: 0.3619 (0.3569) grad: 0.2148 (0.1883) time: 0.5073 data: 0.0026 max mem: 25051 +train: [10] [660/800] eta: 0:01:18 lr: 0.000202 loss: 0.3619 (0.3568) grad: 0.1912 (0.1883) time: 0.4922 data: 0.0030 max mem: 25051 +train: [10] [680/800] eta: 0:01:07 lr: 0.000201 loss: 0.3619 (0.3553) grad: 0.1912 (0.1879) time: 0.7001 data: 0.2165 max mem: 25051 +train: [10] [700/800] eta: 0:00:56 lr: 0.000200 loss: 0.3643 (0.3564) grad: 0.1813 (0.1881) time: 0.5412 data: 0.0159 max mem: 25051 +train: [10] [720/800] eta: 0:00:44 lr: 0.000199 loss: 0.3460 (0.3556) grad: 0.1656 (0.1863) time: 0.5137 data: 0.0035 max mem: 25051 +train: [10] [740/800] eta: 0:00:33 lr: 0.000199 loss: 0.3440 (0.3553) grad: 0.1636 (0.1855) time: 0.4926 data: 0.0028 max mem: 25051 +train: [10] [760/800] eta: 0:00:22 lr: 0.000198 loss: 0.3368 (0.3556) grad: 0.1345 (0.1841) time: 0.7249 data: 0.2171 max mem: 25051 +train: [10] [780/800] eta: 0:00:11 lr: 0.000197 loss: 0.3220 (0.3546) grad: 0.1229 (0.1841) time: 0.5689 data: 0.0032 max mem: 25051 +train: [10] [799/800] eta: 0:00:00 lr: 0.000196 loss: 0.3220 (0.3537) grad: 0.1345 (0.1847) time: 0.5074 data: 0.0035 max mem: 25051 +train: [10] Total time: 0:07:31 (0.5639 s / it) +train: [10] Summary: lr: 0.000196 loss: 0.3220 (0.3537) grad: 0.1345 (0.1847) +eval (validation): [10] [ 0/16] eta: 0:01:11 time: 4.4772 data: 4.1763 max mem: 25051 +eval (validation): [10] [15/16] eta: 0:00:00 time: 0.6414 data: 0.2876 max mem: 25051 +eval (validation): [10] Total time: 0:00:10 (0.6542 s / it) +cv: [10] best hparam: (0.087, 1.0) (009) ('009_lr8.7e-02_wd1.0e+00') loss: 0.592 acc: 0.781 f1: 0.767 bacc: 0.762 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/adhd200_dx__patch__attn/checkpoint-last.pth +train: [11] [ 0/800] eta: 1:00:04 lr: nan time: 4.5055 data: 4.1359 max mem: 25051 +train: [11] [ 20/800] eta: 0:09:27 lr: 0.000196 loss: 0.3965 (0.3978) grad: 0.1328 (0.1647) time: 0.5389 data: 0.0032 max mem: 25051 +train: [11] [ 40/800] eta: 0:07:49 lr: 0.000195 loss: 0.3551 (0.3651) grad: 0.1388 (0.1843) time: 0.5015 data: 0.0031 max mem: 25051 +train: [11] [ 60/800] eta: 0:07:10 lr: 0.000194 loss: 0.3471 (0.3470) grad: 0.1605 (0.1926) time: 0.5075 data: 0.0035 max mem: 25051 +train: [11] [ 80/800] eta: 0:07:29 lr: 0.000193 loss: 0.3551 (0.3544) grad: 0.1395 (0.1934) time: 0.7557 data: 0.2732 max mem: 25051 +train: [11] [100/800] eta: 0:07:08 lr: 0.000193 loss: 0.3586 (0.3625) grad: 0.1700 (0.2062) time: 0.5650 data: 0.0033 max mem: 25051 +train: [11] [120/800] eta: 0:06:47 lr: 0.000192 loss: 0.3413 (0.3535) grad: 0.1700 (0.1973) time: 0.5327 data: 0.0030 max mem: 25051 +train: [11] [140/800] eta: 0:06:25 lr: 0.000191 loss: 0.3645 (0.3516) grad: 0.1581 (0.1982) time: 0.4963 data: 0.0033 max mem: 25051 +train: [11] [160/800] eta: 0:06:26 lr: 0.000190 loss: 0.3619 (0.3513) grad: 0.1650 (0.1937) time: 0.7396 data: 0.2155 max mem: 25051 +train: [11] [180/800] eta: 0:06:05 lr: 0.000190 loss: 0.3431 (0.3528) grad: 0.1454 (0.1906) time: 0.4776 data: 0.0024 max mem: 25051 +train: [11] [200/800] eta: 0:05:49 lr: 0.000189 loss: 0.3431 (0.3465) grad: 0.1454 (0.1914) time: 0.5103 data: 0.0028 max mem: 25051 +train: [11] [220/800] eta: 0:05:33 lr: 0.000188 loss: 0.3257 (0.3461) grad: 0.1443 (0.1892) time: 0.4969 data: 0.0027 max mem: 25051 +train: [11] [240/800] eta: 0:05:30 lr: 0.000187 loss: 0.3223 (0.3481) grad: 0.1438 (0.1849) time: 0.7545 data: 0.2209 max mem: 25051 +train: [11] [260/800] eta: 0:05:15 lr: 0.000187 loss: 0.2980 (0.3491) grad: 0.1268 (0.1843) time: 0.5129 data: 0.0027 max mem: 25051 +train: [11] [280/800] eta: 0:05:00 lr: 0.000186 loss: 0.3509 (0.3475) grad: 0.1427 (0.1841) time: 0.4953 data: 0.0028 max mem: 25051 +train: [11] [300/800] eta: 0:04:52 lr: 0.000185 loss: 0.3083 (0.3452) grad: 0.1623 (0.1873) time: 0.7010 data: 0.2266 max mem: 25051 +train: [11] [320/800] eta: 0:04:40 lr: 0.000184 loss: 0.3357 (0.3500) grad: 0.1623 (0.1873) time: 0.5607 data: 0.0032 max mem: 25051 +train: [11] [340/800] eta: 0:04:26 lr: 0.000184 loss: 0.3301 (0.3490) grad: 0.1997 (0.1920) time: 0.4925 data: 0.0031 max mem: 25051 +train: [11] [360/800] eta: 0:04:12 lr: 0.000183 loss: 0.3357 (0.3498) grad: 0.1915 (0.1913) time: 0.4951 data: 0.0026 max mem: 25051 +train: [11] [380/800] eta: 0:04:03 lr: 0.000182 loss: 0.3595 (0.3483) grad: 0.1997 (0.1924) time: 0.6976 data: 0.2220 max mem: 25051 +train: [11] [400/800] eta: 0:03:50 lr: 0.000181 loss: 0.3186 (0.3464) grad: 0.2342 (0.1940) time: 0.4890 data: 0.0032 max mem: 25051 +train: [11] [420/800] eta: 0:03:37 lr: 0.000181 loss: 0.3186 (0.3458) grad: 0.2089 (0.1967) time: 0.4979 data: 0.0026 max mem: 25051 +train: [11] [440/800] eta: 0:03:24 lr: 0.000180 loss: 0.3206 (0.3469) grad: 0.2356 (0.2006) time: 0.4781 data: 0.0021 max mem: 25051 +train: [11] [460/800] eta: 0:03:15 lr: 0.000179 loss: 0.3453 (0.3477) grad: 0.2161 (0.2014) time: 0.7385 data: 0.2595 max mem: 25051 +train: [11] [480/800] eta: 0:03:03 lr: 0.000178 loss: 0.3575 (0.3503) grad: 0.1774 (0.1985) time: 0.5197 data: 0.0325 max mem: 25051 +train: [11] [500/800] eta: 0:02:50 lr: 0.000177 loss: 0.3921 (0.3519) grad: 0.1774 (0.1998) time: 0.4929 data: 0.0027 max mem: 25051 +train: [11] [520/800] eta: 0:02:38 lr: 0.000177 loss: 0.3616 (0.3515) grad: 0.1772 (0.2003) time: 0.4960 data: 0.0027 max mem: 25051 +train: [11] [540/800] eta: 0:02:28 lr: 0.000176 loss: 0.3582 (0.3484) grad: 0.1523 (0.1977) time: 0.7157 data: 0.2304 max mem: 25051 +train: [11] [560/800] eta: 0:02:17 lr: 0.000175 loss: 0.3290 (0.3478) grad: 0.1536 (0.1975) time: 0.5319 data: 0.0397 max mem: 25051 +train: [11] [580/800] eta: 0:02:05 lr: 0.000174 loss: 0.3106 (0.3469) grad: 0.1447 (0.1961) time: 0.4949 data: 0.0023 max mem: 25051 +train: [11] [600/800] eta: 0:01:55 lr: 0.000174 loss: 0.2950 (0.3457) grad: 0.1187 (0.1941) time: 0.7778 data: 0.3037 max mem: 25051 +train: [11] [620/800] eta: 0:01:43 lr: 0.000173 loss: 0.3288 (0.3461) grad: 0.1141 (0.1919) time: 0.5146 data: 0.0239 max mem: 25051 +train: [11] [640/800] eta: 0:01:31 lr: 0.000172 loss: 0.3300 (0.3461) grad: 0.1301 (0.1922) time: 0.4959 data: 0.0026 max mem: 25051 +train: [11] [660/800] eta: 0:01:19 lr: 0.000171 loss: 0.3547 (0.3462) grad: 0.1401 (0.1922) time: 0.4978 data: 0.0022 max mem: 25051 +train: [11] [680/800] eta: 0:01:08 lr: 0.000170 loss: 0.3300 (0.3447) grad: 0.1424 (0.1904) time: 0.7291 data: 0.2289 max mem: 25051 +train: [11] [700/800] eta: 0:00:57 lr: 0.000170 loss: 0.3462 (0.3459) grad: 0.1510 (0.1896) time: 0.5299 data: 0.0032 max mem: 25051 +train: [11] [720/800] eta: 0:00:45 lr: 0.000169 loss: 0.3322 (0.3454) grad: 0.1510 (0.1915) time: 0.4879 data: 0.0167 max mem: 25051 +train: [11] [740/800] eta: 0:00:34 lr: 0.000168 loss: 0.3322 (0.3454) grad: 0.1510 (0.1911) time: 0.4990 data: 0.0025 max mem: 25051 +train: [11] [760/800] eta: 0:00:22 lr: 0.000167 loss: 0.3462 (0.3457) grad: 0.1607 (0.1922) time: 0.6981 data: 0.2230 max mem: 25051 +train: [11] [780/800] eta: 0:00:11 lr: 0.000167 loss: 0.3584 (0.3471) grad: 0.1802 (0.1929) time: 0.4881 data: 0.0085 max mem: 25051 +train: [11] [799/800] eta: 0:00:00 lr: 0.000166 loss: 0.3584 (0.3464) grad: 0.1739 (0.1928) time: 0.5442 data: 0.0026 max mem: 25051 +train: [11] Total time: 0:07:35 (0.5690 s / it) +train: [11] Summary: lr: 0.000166 loss: 0.3584 (0.3464) grad: 0.1739 (0.1928) +eval (validation): [11] [ 0/16] eta: 0:01:12 time: 4.5416 data: 4.2089 max mem: 25051 +eval (validation): [11] [15/16] eta: 0:00:00 time: 0.6447 data: 0.2645 max mem: 25051 +eval (validation): [11] Total time: 0:00:10 (0.6602 s / it) +cv: [11] best hparam: (0.033, 1.0) (003) ('003_lr3.3e-02_wd1.0e+00') loss: 0.609 acc: 0.781 f1: 0.770 bacc: 0.766 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/adhd200_dx__patch__attn/checkpoint-last.pth +train: [12] [ 0/800] eta: 1:00:22 lr: nan time: 4.5279 data: 4.0989 max mem: 25051 +train: [12] [ 20/800] eta: 0:08:43 lr: 0.000165 loss: 0.3682 (0.3651) grad: 0.2370 (0.2230) time: 0.4780 data: 0.0037 max mem: 25051 +train: [12] [ 40/800] eta: 0:07:27 lr: 0.000164 loss: 0.3457 (0.3587) grad: 0.2197 (0.2275) time: 0.5030 data: 0.0026 max mem: 25051 +train: [12] [ 60/800] eta: 0:07:03 lr: 0.000163 loss: 0.3520 (0.3670) grad: 0.2197 (0.2180) time: 0.5372 data: 0.0031 max mem: 25051 +train: [12] [ 80/800] eta: 0:07:21 lr: 0.000163 loss: 0.3406 (0.3535) grad: 0.1878 (0.2005) time: 0.7396 data: 0.2610 max mem: 25051 +train: [12] [100/800] eta: 0:06:57 lr: 0.000162 loss: 0.3393 (0.3526) grad: 0.1484 (0.1852) time: 0.5262 data: 0.0034 max mem: 25051 +train: [12] [120/800] eta: 0:06:34 lr: 0.000161 loss: 0.3250 (0.3502) grad: 0.1432 (0.1798) time: 0.4975 data: 0.0026 max mem: 25051 +train: [12] [140/800] eta: 0:06:14 lr: 0.000160 loss: 0.3220 (0.3476) grad: 0.1432 (0.1813) time: 0.4884 data: 0.0028 max mem: 25051 +train: [12] [160/800] eta: 0:06:15 lr: 0.000160 loss: 0.3185 (0.3453) grad: 0.1214 (0.1719) time: 0.7217 data: 0.2251 max mem: 25051 +train: [12] [180/800] eta: 0:05:57 lr: 0.000159 loss: 0.3157 (0.3452) grad: 0.1369 (0.1713) time: 0.5036 data: 0.0030 max mem: 25051 +train: [12] [200/800] eta: 0:05:42 lr: 0.000158 loss: 0.2872 (0.3444) grad: 0.1444 (0.1735) time: 0.5156 data: 0.0034 max mem: 25051 +train: [12] [220/800] eta: 0:05:28 lr: 0.000157 loss: 0.2870 (0.3409) grad: 0.1369 (0.1675) time: 0.5184 data: 0.0035 max mem: 25051 +train: [12] [240/800] eta: 0:05:23 lr: 0.000156 loss: 0.3288 (0.3453) grad: 0.1431 (0.1662) time: 0.7015 data: 0.2123 max mem: 25051 +train: [12] [260/800] eta: 0:05:08 lr: 0.000156 loss: 0.3288 (0.3459) grad: 0.1219 (0.1647) time: 0.5028 data: 0.0028 max mem: 25051 +train: [12] [280/800] eta: 0:04:55 lr: 0.000155 loss: 0.3288 (0.3442) grad: 0.1431 (0.1705) time: 0.5261 data: 0.0031 max mem: 25051 +train: [12] [300/800] eta: 0:04:48 lr: 0.000154 loss: 0.3392 (0.3443) grad: 0.1702 (0.1794) time: 0.7057 data: 0.2219 max mem: 25051 +train: [12] [320/800] eta: 0:04:35 lr: 0.000153 loss: 0.3261 (0.3432) grad: 0.2191 (0.1834) time: 0.5171 data: 0.0320 max mem: 25051 +train: [12] [340/800] eta: 0:04:21 lr: 0.000152 loss: 0.3261 (0.3433) grad: 0.2382 (0.1844) time: 0.4877 data: 0.0022 max mem: 25051 +train: [12] [360/800] eta: 0:04:08 lr: 0.000152 loss: 0.3252 (0.3426) grad: 0.1673 (0.1833) time: 0.4967 data: 0.0029 max mem: 25051 +train: [12] [380/800] eta: 0:04:01 lr: 0.000151 loss: 0.3165 (0.3418) grad: 0.1509 (0.1848) time: 0.7439 data: 0.2249 max mem: 25051 +train: [12] [400/800] eta: 0:03:50 lr: 0.000150 loss: 0.3207 (0.3430) grad: 0.1478 (0.1847) time: 0.5917 data: 0.0043 max mem: 25051 +train: [12] [420/800] eta: 0:03:37 lr: 0.000149 loss: 0.3207 (0.3443) grad: 0.1643 (0.1867) time: 0.5064 data: 0.0031 max mem: 25051 +train: [12] [440/800] eta: 0:03:24 lr: 0.000149 loss: 0.3256 (0.3447) grad: 0.1589 (0.1854) time: 0.4913 data: 0.0034 max mem: 25051 +train: [12] [460/800] eta: 0:03:14 lr: 0.000148 loss: 0.3256 (0.3437) grad: 0.1571 (0.1859) time: 0.6875 data: 0.2121 max mem: 25051 +train: [12] [480/800] eta: 0:03:02 lr: 0.000147 loss: 0.3208 (0.3422) grad: 0.1571 (0.1836) time: 0.5018 data: 0.0031 max mem: 25051 +train: [12] [500/800] eta: 0:02:50 lr: 0.000146 loss: 0.3106 (0.3411) grad: 0.1559 (0.1851) time: 0.5024 data: 0.0028 max mem: 25051 +train: [12] [520/800] eta: 0:02:38 lr: 0.000145 loss: 0.2958 (0.3405) grad: 0.1571 (0.1862) time: 0.4844 data: 0.0027 max mem: 25051 +train: [12] [540/800] eta: 0:02:28 lr: 0.000145 loss: 0.2958 (0.3398) grad: 0.1392 (0.1842) time: 0.7414 data: 0.2264 max mem: 25051 +train: [12] [560/800] eta: 0:02:16 lr: 0.000144 loss: 0.3178 (0.3395) grad: 0.1403 (0.1835) time: 0.4826 data: 0.0029 max mem: 25051 +train: [12] [580/800] eta: 0:02:04 lr: 0.000143 loss: 0.3207 (0.3399) grad: 0.1503 (0.1863) time: 0.4890 data: 0.0031 max mem: 25051 +train: [12] [600/800] eta: 0:01:53 lr: 0.000142 loss: 0.3178 (0.3381) grad: 0.1390 (0.1853) time: 0.6729 data: 0.2086 max mem: 25051 +train: [12] [620/800] eta: 0:01:41 lr: 0.000141 loss: 0.3178 (0.3374) grad: 0.1403 (0.1871) time: 0.4783 data: 0.0029 max mem: 25051 +train: [12] [640/800] eta: 0:01:30 lr: 0.000141 loss: 0.3153 (0.3373) grad: 0.1540 (0.1874) time: 0.5052 data: 0.0024 max mem: 25051 +train: [12] [660/800] eta: 0:01:18 lr: 0.000140 loss: 0.3094 (0.3366) grad: 0.1500 (0.1870) time: 0.5164 data: 0.0245 max mem: 25051 +train: [12] [680/800] eta: 0:01:08 lr: 0.000139 loss: 0.3094 (0.3362) grad: 0.1624 (0.1881) time: 0.7397 data: 0.2760 max mem: 25051 +train: [12] [700/800] eta: 0:00:56 lr: 0.000138 loss: 0.3132 (0.3360) grad: 0.1611 (0.1891) time: 0.4771 data: 0.0027 max mem: 25051 +train: [12] [720/800] eta: 0:00:45 lr: 0.000138 loss: 0.3175 (0.3362) grad: 0.1585 (0.1882) time: 0.5075 data: 0.0020 max mem: 25051 +train: [12] [740/800] eta: 0:00:33 lr: 0.000137 loss: 0.3268 (0.3368) grad: 0.1624 (0.1879) time: 0.4963 data: 0.0027 max mem: 25051 +train: [12] [760/800] eta: 0:00:22 lr: 0.000136 loss: 0.3268 (0.3366) grad: 0.1487 (0.1869) time: 0.6972 data: 0.2258 max mem: 25051 +train: [12] [780/800] eta: 0:00:11 lr: 0.000135 loss: 0.3355 (0.3367) grad: 0.1604 (0.1879) time: 0.5236 data: 0.0225 max mem: 25051 +train: [12] [799/800] eta: 0:00:00 lr: 0.000134 loss: 0.3407 (0.3380) grad: 0.1414 (0.1863) time: 0.4896 data: 0.0027 max mem: 25051 +train: [12] Total time: 0:07:30 (0.5627 s / it) +train: [12] Summary: lr: 0.000134 loss: 0.3407 (0.3380) grad: 0.1414 (0.1863) +eval (validation): [12] [ 0/16] eta: 0:01:07 time: 4.2260 data: 3.9268 max mem: 25051 +eval (validation): [12] [15/16] eta: 0:00:00 time: 0.6173 data: 0.2473 max mem: 25051 +eval (validation): [12] Total time: 0:00:10 (0.6295 s / it) +cv: [12] best hparam: (0.074, 1.0) (008) ('008_lr7.4e-02_wd1.0e+00') loss: 0.600 acc: 0.766 f1: 0.737 bacc: 0.736 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/adhd200_dx__patch__attn/checkpoint-last.pth +train: [13] [ 0/800] eta: 0:58:48 lr: nan time: 4.4107 data: 4.0514 max mem: 25051 +train: [13] [ 20/800] eta: 0:08:45 lr: 0.000134 loss: 0.3449 (0.3237) grad: 0.2335 (0.2186) time: 0.4864 data: 0.0024 max mem: 25051 +train: [13] [ 40/800] eta: 0:07:17 lr: 0.000133 loss: 0.3244 (0.3247) grad: 0.1868 (0.1908) time: 0.4744 data: 0.0022 max mem: 25051 +train: [13] [ 60/800] eta: 0:06:44 lr: 0.000132 loss: 0.3449 (0.3371) grad: 0.1868 (0.1766) time: 0.4851 data: 0.0025 max mem: 25051 +train: [13] [ 80/800] eta: 0:06:56 lr: 0.000131 loss: 0.3412 (0.3394) grad: 0.1577 (0.1685) time: 0.6785 data: 0.2070 max mem: 25051 +train: [13] [100/800] eta: 0:06:39 lr: 0.000130 loss: 0.3412 (0.3434) grad: 0.1416 (0.1681) time: 0.5361 data: 0.0340 max mem: 25051 +train: [13] [120/800] eta: 0:06:21 lr: 0.000130 loss: 0.3412 (0.3349) grad: 0.1311 (0.1594) time: 0.5105 data: 0.0018 max mem: 25051 +train: [13] [140/800] eta: 0:06:04 lr: 0.000129 loss: 0.3028 (0.3327) grad: 0.1394 (0.1562) time: 0.5018 data: 0.0028 max mem: 25051 +train: [13] [160/800] eta: 0:06:07 lr: 0.000128 loss: 0.3076 (0.3337) grad: 0.1394 (0.1603) time: 0.7301 data: 0.2279 max mem: 25051 +train: [13] [180/800] eta: 0:05:51 lr: 0.000127 loss: 0.3076 (0.3402) grad: 0.1413 (0.1617) time: 0.5042 data: 0.0020 max mem: 25051 +train: [13] [200/800] eta: 0:05:35 lr: 0.000127 loss: 0.3453 (0.3414) grad: 0.1471 (0.1647) time: 0.4839 data: 0.0033 max mem: 25051 +train: [13] [220/800] eta: 0:05:19 lr: 0.000126 loss: 0.3452 (0.3401) grad: 0.1465 (0.1615) time: 0.4719 data: 0.0021 max mem: 25051 +train: [13] [240/800] eta: 0:05:18 lr: 0.000125 loss: 0.3631 (0.3400) grad: 0.1494 (0.1654) time: 0.7607 data: 0.2224 max mem: 25051 +train: [13] [260/800] eta: 0:05:03 lr: 0.000124 loss: 0.3619 (0.3414) grad: 0.1568 (0.1733) time: 0.4977 data: 0.0031 max mem: 25051 +train: [13] [280/800] eta: 0:04:50 lr: 0.000124 loss: 0.3383 (0.3382) grad: 0.2057 (0.1774) time: 0.5054 data: 0.0029 max mem: 25051 +train: [13] [300/800] eta: 0:04:44 lr: 0.000123 loss: 0.3438 (0.3385) grad: 0.2025 (0.1767) time: 0.7257 data: 0.2312 max mem: 25051 +train: [13] [320/800] eta: 0:04:32 lr: 0.000122 loss: 0.3436 (0.3397) grad: 0.1953 (0.1791) time: 0.5255 data: 0.0024 max mem: 25051 +train: [13] [340/800] eta: 0:04:19 lr: 0.000121 loss: 0.3049 (0.3361) grad: 0.1915 (0.1793) time: 0.5119 data: 0.0029 max mem: 25051 +train: [13] [360/800] eta: 0:04:06 lr: 0.000120 loss: 0.3186 (0.3354) grad: 0.1709 (0.1757) time: 0.4892 data: 0.0032 max mem: 25051 +train: [13] [380/800] eta: 0:03:59 lr: 0.000120 loss: 0.3186 (0.3359) grad: 0.1691 (0.1763) time: 0.7763 data: 0.2763 max mem: 25051 +train: [13] [400/800] eta: 0:03:47 lr: 0.000119 loss: 0.3191 (0.3360) grad: 0.1473 (0.1760) time: 0.5319 data: 0.0036 max mem: 25051 +train: [13] [420/800] eta: 0:03:34 lr: 0.000118 loss: 0.3239 (0.3348) grad: 0.1473 (0.1770) time: 0.4843 data: 0.0024 max mem: 25051 +train: [13] [440/800] eta: 0:03:22 lr: 0.000117 loss: 0.3263 (0.3348) grad: 0.2172 (0.1834) time: 0.5157 data: 0.0034 max mem: 25051 +train: [13] [460/800] eta: 0:03:13 lr: 0.000117 loss: 0.3263 (0.3337) grad: 0.2211 (0.1848) time: 0.7156 data: 0.2258 max mem: 25051 +train: [13] [480/800] eta: 0:03:01 lr: 0.000116 loss: 0.3391 (0.3343) grad: 0.2303 (0.1857) time: 0.4921 data: 0.0039 max mem: 25051 +train: [13] [500/800] eta: 0:02:49 lr: 0.000115 loss: 0.3374 (0.3327) grad: 0.2219 (0.1859) time: 0.5008 data: 0.0025 max mem: 25051 +train: [13] [520/800] eta: 0:02:36 lr: 0.000114 loss: 0.3374 (0.3328) grad: 0.2211 (0.1880) time: 0.4873 data: 0.0029 max mem: 25051 +train: [13] [540/800] eta: 0:02:27 lr: 0.000114 loss: 0.3342 (0.3329) grad: 0.1842 (0.1878) time: 0.7886 data: 0.2173 max mem: 25051 +train: [13] [560/800] eta: 0:02:16 lr: 0.000113 loss: 0.3116 (0.3327) grad: 0.2050 (0.1894) time: 0.5053 data: 0.0033 max mem: 25051 +train: [13] [580/800] eta: 0:02:04 lr: 0.000112 loss: 0.3342 (0.3332) grad: 0.1842 (0.1895) time: 0.4908 data: 0.0031 max mem: 25051 +train: [13] [600/800] eta: 0:01:53 lr: 0.000111 loss: 0.3342 (0.3331) grad: 0.1687 (0.1886) time: 0.7102 data: 0.2274 max mem: 25051 +train: [13] [620/800] eta: 0:01:42 lr: 0.000110 loss: 0.3270 (0.3320) grad: 0.1717 (0.1898) time: 0.5933 data: 0.0721 max mem: 25051 +train: [13] [640/800] eta: 0:01:30 lr: 0.000110 loss: 0.3157 (0.3307) grad: 0.1644 (0.1896) time: 0.5012 data: 0.0022 max mem: 25051 +train: [13] [660/800] eta: 0:01:19 lr: 0.000109 loss: 0.3157 (0.3320) grad: 0.1661 (0.1899) time: 0.5154 data: 0.0032 max mem: 25051 +train: [13] [680/800] eta: 0:01:08 lr: 0.000108 loss: 0.3077 (0.3321) grad: 0.1814 (0.1898) time: 0.7476 data: 0.2310 max mem: 25051 +train: [13] [700/800] eta: 0:00:56 lr: 0.000107 loss: 0.3077 (0.3329) grad: 0.1661 (0.1889) time: 0.4962 data: 0.0025 max mem: 25051 +train: [13] [720/800] eta: 0:00:45 lr: 0.000107 loss: 0.3415 (0.3350) grad: 0.1661 (0.1893) time: 0.4956 data: 0.0029 max mem: 25051 +train: [13] [740/800] eta: 0:00:33 lr: 0.000106 loss: 0.3680 (0.3363) grad: 0.1519 (0.1887) time: 0.5065 data: 0.0027 max mem: 25051 +train: [13] [760/800] eta: 0:00:22 lr: 0.000105 loss: 0.3680 (0.3355) grad: 0.1588 (0.1912) time: 0.7416 data: 0.2295 max mem: 25051 +train: [13] [780/800] eta: 0:00:11 lr: 0.000104 loss: 0.3680 (0.3366) grad: 0.1521 (0.1914) time: 0.5693 data: 0.0026 max mem: 25051 +train: [13] [799/800] eta: 0:00:00 lr: 0.000104 loss: 0.3352 (0.3356) grad: 0.1521 (0.1903) time: 0.5000 data: 0.0026 max mem: 25051 +train: [13] Total time: 0:07:35 (0.5688 s / it) +train: [13] Summary: lr: 0.000104 loss: 0.3352 (0.3356) grad: 0.1521 (0.1903) +eval (validation): [13] [ 0/16] eta: 0:01:39 time: 6.2319 data: 5.9394 max mem: 25051 +eval (validation): [13] [15/16] eta: 0:00:00 time: 0.7600 data: 0.3956 max mem: 25051 +eval (validation): [13] Total time: 0:00:12 (0.7712 s / it) +cv: [13] best hparam: (0.074, 1.0) (008) ('008_lr7.4e-02_wd1.0e+00') loss: 0.594 acc: 0.781 f1: 0.767 bacc: 0.762 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/adhd200_dx__patch__attn/checkpoint-last.pth +train: [14] [ 0/800] eta: 1:22:57 lr: nan time: 6.2215 data: 5.8128 max mem: 25051 +train: [14] [ 20/800] eta: 0:10:27 lr: 0.000103 loss: 0.4330 (0.3748) grad: 0.2135 (0.2014) time: 0.5330 data: 0.0332 max mem: 25051 +train: [14] [ 40/800] eta: 0:08:17 lr: 0.000102 loss: 0.3067 (0.3474) grad: 0.2047 (0.1987) time: 0.4980 data: 0.0230 max mem: 25051 +train: [14] [ 60/800] eta: 0:07:28 lr: 0.000101 loss: 0.3067 (0.3323) grad: 0.2047 (0.2014) time: 0.5049 data: 0.0020 max mem: 25051 +train: [14] [ 80/800] eta: 0:07:34 lr: 0.000101 loss: 0.2988 (0.3210) grad: 0.2020 (0.1932) time: 0.7071 data: 0.2248 max mem: 25051 +train: [14] [100/800] eta: 0:07:01 lr: 0.000100 loss: 0.2988 (0.3188) grad: 0.1521 (0.1808) time: 0.4838 data: 0.0025 max mem: 25051 +train: [14] [120/800] eta: 0:06:36 lr: 0.000099 loss: 0.3039 (0.3256) grad: 0.1521 (0.1850) time: 0.4920 data: 0.0026 max mem: 25051 +train: [14] [140/800] eta: 0:06:17 lr: 0.000099 loss: 0.3142 (0.3253) grad: 0.1521 (0.1846) time: 0.4983 data: 0.0023 max mem: 25051 +train: [14] [160/800] eta: 0:06:16 lr: 0.000098 loss: 0.3188 (0.3283) grad: 0.1327 (0.1786) time: 0.7117 data: 0.2146 max mem: 25051 +train: [14] [180/800] eta: 0:06:00 lr: 0.000097 loss: 0.3352 (0.3285) grad: 0.1327 (0.1778) time: 0.5264 data: 0.0024 max mem: 25051 +train: [14] [200/800] eta: 0:05:43 lr: 0.000096 loss: 0.3352 (0.3285) grad: 0.1069 (0.1767) time: 0.4936 data: 0.0034 max mem: 25051 +train: [14] [220/800] eta: 0:05:28 lr: 0.000096 loss: 0.3236 (0.3267) grad: 0.1069 (0.1715) time: 0.5043 data: 0.0031 max mem: 25051 +train: [14] [240/800] eta: 0:05:24 lr: 0.000095 loss: 0.3236 (0.3310) grad: 0.1464 (0.1755) time: 0.7290 data: 0.2135 max mem: 25051 +train: [14] [260/800] eta: 0:05:09 lr: 0.000094 loss: 0.3236 (0.3330) grad: 0.1348 (0.1712) time: 0.4980 data: 0.0030 max mem: 25051 +train: [14] [280/800] eta: 0:04:56 lr: 0.000093 loss: 0.3167 (0.3305) grad: 0.1133 (0.1665) time: 0.5117 data: 0.0032 max mem: 25051 +train: [14] [300/800] eta: 0:04:48 lr: 0.000093 loss: 0.3127 (0.3281) grad: 0.1388 (0.1679) time: 0.6896 data: 0.2151 max mem: 25051 +train: [14] [320/800] eta: 0:04:37 lr: 0.000092 loss: 0.3132 (0.3283) grad: 0.1348 (0.1684) time: 0.5717 data: 0.0722 max mem: 25051 +train: [14] [340/800] eta: 0:04:23 lr: 0.000091 loss: 0.3132 (0.3285) grad: 0.1486 (0.1695) time: 0.5203 data: 0.0031 max mem: 25051 +train: [14] [360/800] eta: 0:04:11 lr: 0.000090 loss: 0.3201 (0.3302) grad: 0.1539 (0.1690) time: 0.5167 data: 0.0031 max mem: 25051 +train: [14] [380/800] eta: 0:04:03 lr: 0.000090 loss: 0.3431 (0.3338) grad: 0.1539 (0.1734) time: 0.7367 data: 0.2782 max mem: 25051 +train: [14] [400/800] eta: 0:03:51 lr: 0.000089 loss: 0.3496 (0.3341) grad: 0.1567 (0.1793) time: 0.5674 data: 0.0661 max mem: 25051 +train: [14] [420/800] eta: 0:03:39 lr: 0.000088 loss: 0.3332 (0.3319) grad: 0.2264 (0.1821) time: 0.5312 data: 0.0417 max mem: 25051 +train: [14] [440/800] eta: 0:03:26 lr: 0.000088 loss: 0.3122 (0.3303) grad: 0.2342 (0.1876) time: 0.5023 data: 0.0024 max mem: 25051 +train: [14] [460/800] eta: 0:03:17 lr: 0.000087 loss: 0.3086 (0.3319) grad: 0.2424 (0.1936) time: 0.7373 data: 0.2436 max mem: 25051 +train: [14] [480/800] eta: 0:03:04 lr: 0.000086 loss: 0.3086 (0.3346) grad: 0.2264 (0.1958) time: 0.4789 data: 0.0020 max mem: 25051 +train: [14] [500/800] eta: 0:02:51 lr: 0.000085 loss: 0.3087 (0.3325) grad: 0.2142 (0.1935) time: 0.4973 data: 0.0030 max mem: 25051 +train: [14] [520/800] eta: 0:02:39 lr: 0.000085 loss: 0.3481 (0.3325) grad: 0.1901 (0.1926) time: 0.4723 data: 0.0028 max mem: 25051 +train: [14] [540/800] eta: 0:02:30 lr: 0.000084 loss: 0.3170 (0.3333) grad: 0.1482 (0.1934) time: 0.7973 data: 0.2312 max mem: 25051 +train: [14] [560/800] eta: 0:02:18 lr: 0.000083 loss: 0.3087 (0.3324) grad: 0.1482 (0.1939) time: 0.5170 data: 0.0034 max mem: 25051 +train: [14] [580/800] eta: 0:02:05 lr: 0.000083 loss: 0.3170 (0.3309) grad: 0.1848 (0.1954) time: 0.4843 data: 0.0033 max mem: 25051 +train: [14] [600/800] eta: 0:01:55 lr: 0.000082 loss: 0.3170 (0.3311) grad: 0.2065 (0.1958) time: 0.7251 data: 0.2296 max mem: 25051 +train: [14] [620/800] eta: 0:01:43 lr: 0.000081 loss: 0.3291 (0.3331) grad: 0.1956 (0.1954) time: 0.4992 data: 0.0118 max mem: 25051 +train: [14] [640/800] eta: 0:01:31 lr: 0.000081 loss: 0.3262 (0.3315) grad: 0.1955 (0.1938) time: 0.4946 data: 0.0029 max mem: 25051 +train: [14] [660/800] eta: 0:01:19 lr: 0.000080 loss: 0.3373 (0.3320) grad: 0.1642 (0.1923) time: 0.5014 data: 0.0026 max mem: 25051 +train: [14] [680/800] eta: 0:01:08 lr: 0.000079 loss: 0.3338 (0.3310) grad: 0.1264 (0.1901) time: 0.7284 data: 0.2222 max mem: 25051 +train: [14] [700/800] eta: 0:00:57 lr: 0.000078 loss: 0.3155 (0.3309) grad: 0.1344 (0.1900) time: 0.5419 data: 0.0278 max mem: 25051 +train: [14] [720/800] eta: 0:00:45 lr: 0.000078 loss: 0.3233 (0.3308) grad: 0.1334 (0.1884) time: 0.5068 data: 0.0193 max mem: 25051 +train: [14] [740/800] eta: 0:00:34 lr: 0.000077 loss: 0.2875 (0.3300) grad: 0.1334 (0.1880) time: 0.5039 data: 0.0025 max mem: 25051 +train: [14] [760/800] eta: 0:00:23 lr: 0.000076 loss: 0.3254 (0.3303) grad: 0.1392 (0.1884) time: 0.7632 data: 0.2227 max mem: 25051 +train: [14] [780/800] eta: 0:00:11 lr: 0.000076 loss: 0.3171 (0.3294) grad: 0.1392 (0.1883) time: 0.5442 data: 0.0041 max mem: 25051 +train: [14] [799/800] eta: 0:00:00 lr: 0.000075 loss: 0.3254 (0.3297) grad: 0.1392 (0.1864) time: 0.4996 data: 0.0033 max mem: 25051 +train: [14] Total time: 0:07:38 (0.5730 s / it) +train: [14] Summary: lr: 0.000075 loss: 0.3254 (0.3297) grad: 0.1392 (0.1864) +eval (validation): [14] [ 0/16] eta: 0:01:10 time: 4.4233 data: 4.1395 max mem: 25051 +eval (validation): [14] [15/16] eta: 0:00:00 time: 0.6200 data: 0.2599 max mem: 25051 +eval (validation): [14] Total time: 0:00:10 (0.6338 s / it) +cv: [14] best hparam: (0.074, 1.0) (008) ('008_lr7.4e-02_wd1.0e+00') loss: 0.592 acc: 0.781 f1: 0.767 bacc: 0.762 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/adhd200_dx__patch__attn/checkpoint-last.pth +train: [15] [ 0/800] eta: 0:58:34 lr: nan time: 4.3928 data: 4.0188 max mem: 25051 +train: [15] [ 20/800] eta: 0:08:55 lr: 0.000074 loss: 0.2603 (0.3041) grad: 0.0911 (0.0975) time: 0.5013 data: 0.0030 max mem: 25051 +train: [15] [ 40/800] eta: 0:07:33 lr: 0.000074 loss: 0.2795 (0.3249) grad: 0.1141 (0.1653) time: 0.5027 data: 0.0028 max mem: 25051 +train: [15] [ 60/800] eta: 0:06:57 lr: 0.000073 loss: 0.3173 (0.3271) grad: 0.1551 (0.1707) time: 0.4961 data: 0.0025 max mem: 25051 +train: [15] [ 80/800] eta: 0:07:20 lr: 0.000072 loss: 0.3008 (0.3205) grad: 0.1084 (0.1509) time: 0.7606 data: 0.2814 max mem: 25051 +train: [15] [100/800] eta: 0:06:51 lr: 0.000072 loss: 0.3079 (0.3233) grad: 0.1551 (0.1494) time: 0.4879 data: 0.0031 max mem: 25051 +train: [15] [120/800] eta: 0:06:26 lr: 0.000071 loss: 0.3173 (0.3214) grad: 0.1551 (0.1586) time: 0.4738 data: 0.0023 max mem: 25051 +train: [15] [140/800] eta: 0:06:07 lr: 0.000070 loss: 0.3042 (0.3248) grad: 0.1469 (0.1630) time: 0.4857 data: 0.0028 max mem: 25051 +train: [15] [160/800] eta: 0:06:08 lr: 0.000070 loss: 0.3523 (0.3302) grad: 0.1565 (0.1652) time: 0.7037 data: 0.2238 max mem: 25051 +train: [15] [180/800] eta: 0:05:51 lr: 0.000069 loss: 0.3284 (0.3285) grad: 0.1635 (0.1668) time: 0.4995 data: 0.0026 max mem: 25051 +train: [15] [200/800] eta: 0:05:35 lr: 0.000068 loss: 0.3284 (0.3337) grad: 0.1385 (0.1770) time: 0.4908 data: 0.0029 max mem: 25051 +train: [15] [220/800] eta: 0:05:20 lr: 0.000068 loss: 0.3224 (0.3299) grad: 0.1479 (0.1763) time: 0.4885 data: 0.0030 max mem: 25051 +train: [15] [240/800] eta: 0:05:17 lr: 0.000067 loss: 0.3159 (0.3284) grad: 0.1718 (0.1856) time: 0.7303 data: 0.2116 max mem: 25051 +train: [15] [260/800] eta: 0:05:03 lr: 0.000066 loss: 0.3193 (0.3286) grad: 0.1600 (0.1831) time: 0.4955 data: 0.0029 max mem: 25051 +train: [15] [280/800] eta: 0:04:49 lr: 0.000066 loss: 0.3193 (0.3303) grad: 0.1600 (0.1804) time: 0.4979 data: 0.0032 max mem: 25051 +train: [15] [300/800] eta: 0:04:43 lr: 0.000065 loss: 0.3193 (0.3284) grad: 0.1574 (0.1773) time: 0.6884 data: 0.2163 max mem: 25051 +train: [15] [320/800] eta: 0:04:29 lr: 0.000064 loss: 0.3193 (0.3296) grad: 0.1574 (0.1787) time: 0.5000 data: 0.0021 max mem: 25051 +train: [15] [340/800] eta: 0:04:16 lr: 0.000064 loss: 0.3133 (0.3292) grad: 0.1247 (0.1744) time: 0.4724 data: 0.0028 max mem: 25051 +train: [15] [360/800] eta: 0:04:03 lr: 0.000063 loss: 0.3021 (0.3282) grad: 0.1319 (0.1782) time: 0.4911 data: 0.0033 max mem: 25051 +train: [15] [380/800] eta: 0:03:55 lr: 0.000063 loss: 0.3122 (0.3285) grad: 0.1319 (0.1750) time: 0.7020 data: 0.2075 max mem: 25051 +train: [15] [400/800] eta: 0:03:43 lr: 0.000062 loss: 0.3133 (0.3282) grad: 0.1319 (0.1767) time: 0.4992 data: 0.0025 max mem: 25051 +train: [15] [420/800] eta: 0:03:31 lr: 0.000061 loss: 0.3163 (0.3294) grad: 0.1656 (0.1789) time: 0.5036 data: 0.0031 max mem: 25051 +train: [15] [440/800] eta: 0:03:19 lr: 0.000061 loss: 0.3170 (0.3297) grad: 0.1556 (0.1785) time: 0.5091 data: 0.0032 max mem: 25051 +train: [15] [460/800] eta: 0:03:11 lr: 0.000060 loss: 0.3163 (0.3300) grad: 0.1542 (0.1761) time: 0.7972 data: 0.2289 max mem: 25051 +train: [15] [480/800] eta: 0:02:59 lr: 0.000059 loss: 0.3163 (0.3288) grad: 0.1386 (0.1763) time: 0.4863 data: 0.0022 max mem: 25051 +train: [15] [500/800] eta: 0:02:47 lr: 0.000059 loss: 0.3155 (0.3286) grad: 0.1341 (0.1767) time: 0.5083 data: 0.0029 max mem: 25051 +train: [15] [520/800] eta: 0:02:35 lr: 0.000058 loss: 0.3196 (0.3296) grad: 0.1311 (0.1757) time: 0.4982 data: 0.0030 max mem: 25051 +train: [15] [540/800] eta: 0:02:26 lr: 0.000057 loss: 0.3228 (0.3292) grad: 0.1380 (0.1758) time: 0.7132 data: 0.2336 max mem: 25051 +train: [15] [560/800] eta: 0:02:14 lr: 0.000057 loss: 0.3228 (0.3286) grad: 0.1538 (0.1757) time: 0.5038 data: 0.0027 max mem: 25051 +train: [15] [580/800] eta: 0:02:02 lr: 0.000056 loss: 0.3216 (0.3285) grad: 0.1423 (0.1739) time: 0.4928 data: 0.0028 max mem: 25051 +train: [15] [600/800] eta: 0:01:52 lr: 0.000056 loss: 0.3153 (0.3287) grad: 0.1423 (0.1755) time: 0.7016 data: 0.2257 max mem: 25051 +train: [15] [620/800] eta: 0:01:40 lr: 0.000055 loss: 0.3187 (0.3295) grad: 0.1662 (0.1763) time: 0.5007 data: 0.0034 max mem: 25051 +train: [15] [640/800] eta: 0:01:29 lr: 0.000054 loss: 0.3193 (0.3290) grad: 0.1471 (0.1776) time: 0.4896 data: 0.0025 max mem: 25051 +train: [15] [660/800] eta: 0:01:17 lr: 0.000054 loss: 0.3351 (0.3287) grad: 0.1600 (0.1778) time: 0.4955 data: 0.0030 max mem: 25051 +train: [15] [680/800] eta: 0:01:07 lr: 0.000053 loss: 0.3383 (0.3292) grad: 0.1638 (0.1771) time: 0.7184 data: 0.2103 max mem: 25051 +train: [15] [700/800] eta: 0:00:55 lr: 0.000053 loss: 0.3351 (0.3286) grad: 0.1471 (0.1767) time: 0.4937 data: 0.0031 max mem: 25051 +train: [15] [720/800] eta: 0:00:44 lr: 0.000052 loss: 0.3383 (0.3300) grad: 0.1372 (0.1768) time: 0.5563 data: 0.0048 max mem: 25051 +train: [15] [740/800] eta: 0:00:33 lr: 0.000051 loss: 0.3449 (0.3298) grad: 0.1638 (0.1780) time: 0.4952 data: 0.0031 max mem: 25051 +train: [15] [760/800] eta: 0:00:22 lr: 0.000051 loss: 0.3240 (0.3287) grad: 0.1256 (0.1764) time: 0.8037 data: 0.3139 max mem: 25051 +train: [15] [780/800] eta: 0:00:11 lr: 0.000050 loss: 0.3007 (0.3275) grad: 0.1256 (0.1766) time: 0.5179 data: 0.0154 max mem: 25051 +train: [15] [799/800] eta: 0:00:00 lr: 0.000050 loss: 0.2859 (0.3266) grad: 0.1568 (0.1773) time: 0.5053 data: 0.0203 max mem: 25051 +train: [15] Total time: 0:07:29 (0.5616 s / it) +train: [15] Summary: lr: 0.000050 loss: 0.2859 (0.3266) grad: 0.1568 (0.1773) +eval (validation): [15] [ 0/16] eta: 0:01:10 time: 4.4080 data: 4.1466 max mem: 25051 +eval (validation): [15] [15/16] eta: 0:00:00 time: 0.6201 data: 0.2604 max mem: 25051 +eval (validation): [15] Total time: 0:00:10 (0.6331 s / it) +cv: [15] best hparam: (0.053, 1.0) (006) ('006_lr5.3e-02_wd1.0e+00') loss: 0.598 acc: 0.781 f1: 0.767 bacc: 0.762 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/adhd200_dx__patch__attn/checkpoint-last.pth +train: [16] [ 0/800] eta: 1:01:49 lr: nan time: 4.6371 data: 4.1966 max mem: 25051 +train: [16] [ 20/800] eta: 0:09:59 lr: 0.000049 loss: 0.3533 (0.3558) grad: 0.1979 (0.2078) time: 0.5745 data: 0.0031 max mem: 25051 +train: [16] [ 40/800] eta: 0:08:02 lr: 0.000048 loss: 0.2974 (0.3284) grad: 0.1482 (0.1823) time: 0.4958 data: 0.0032 max mem: 25051 +train: [16] [ 60/800] eta: 0:07:15 lr: 0.000048 loss: 0.3104 (0.3222) grad: 0.1911 (0.1815) time: 0.4918 data: 0.0028 max mem: 25051 +train: [16] [ 80/800] eta: 0:07:20 lr: 0.000047 loss: 0.3223 (0.3264) grad: 0.1911 (0.1814) time: 0.6848 data: 0.2151 max mem: 25051 +train: [16] [100/800] eta: 0:07:01 lr: 0.000047 loss: 0.3015 (0.3258) grad: 0.1911 (0.1811) time: 0.5620 data: 0.0217 max mem: 25051 +train: [16] [120/800] eta: 0:06:36 lr: 0.000046 loss: 0.3244 (0.3324) grad: 0.1881 (0.1752) time: 0.4843 data: 0.0036 max mem: 25051 +train: [16] [140/800] eta: 0:06:19 lr: 0.000046 loss: 0.3343 (0.3319) grad: 0.1935 (0.1826) time: 0.5307 data: 0.0145 max mem: 25051 +train: [16] [160/800] eta: 0:06:18 lr: 0.000045 loss: 0.3220 (0.3321) grad: 0.1560 (0.1811) time: 0.7048 data: 0.2263 max mem: 25051 +train: [16] [180/800] eta: 0:05:59 lr: 0.000045 loss: 0.3343 (0.3328) grad: 0.1525 (0.1788) time: 0.4914 data: 0.0029 max mem: 25051 +train: [16] [200/800] eta: 0:05:42 lr: 0.000044 loss: 0.3220 (0.3317) grad: 0.1560 (0.1748) time: 0.4861 data: 0.0026 max mem: 25051 +train: [16] [220/800] eta: 0:05:26 lr: 0.000043 loss: 0.3221 (0.3291) grad: 0.1477 (0.1681) time: 0.4813 data: 0.0029 max mem: 25051 +train: [16] [240/800] eta: 0:05:26 lr: 0.000043 loss: 0.3221 (0.3282) grad: 0.1123 (0.1629) time: 0.8075 data: 0.3094 max mem: 25051 +train: [16] [260/800] eta: 0:05:12 lr: 0.000042 loss: 0.3128 (0.3296) grad: 0.1041 (0.1604) time: 0.5357 data: 0.0493 max mem: 25051 +train: [16] [280/800] eta: 0:04:58 lr: 0.000042 loss: 0.2958 (0.3279) grad: 0.1032 (0.1588) time: 0.4928 data: 0.0230 max mem: 25051 +train: [16] [300/800] eta: 0:04:51 lr: 0.000041 loss: 0.2958 (0.3267) grad: 0.1057 (0.1620) time: 0.7110 data: 0.2429 max mem: 25051 +train: [16] [320/800] eta: 0:04:37 lr: 0.000041 loss: 0.2825 (0.3235) grad: 0.1353 (0.1598) time: 0.5041 data: 0.0050 max mem: 25051 +train: [16] [340/800] eta: 0:04:23 lr: 0.000040 loss: 0.3057 (0.3254) grad: 0.1057 (0.1594) time: 0.4861 data: 0.0022 max mem: 25051 +train: [16] [360/800] eta: 0:04:10 lr: 0.000040 loss: 0.3057 (0.3236) grad: 0.1395 (0.1620) time: 0.5028 data: 0.0030 max mem: 25051 +train: [16] [380/800] eta: 0:04:01 lr: 0.000039 loss: 0.3070 (0.3231) grad: 0.1274 (0.1612) time: 0.7045 data: 0.2259 max mem: 25051 +train: [16] [400/800] eta: 0:03:49 lr: 0.000039 loss: 0.3070 (0.3220) grad: 0.1821 (0.1646) time: 0.5304 data: 0.0539 max mem: 25051 +train: [16] [420/800] eta: 0:03:36 lr: 0.000038 loss: 0.3009 (0.3220) grad: 0.1276 (0.1612) time: 0.4797 data: 0.0074 max mem: 25051 +train: [16] [440/800] eta: 0:03:23 lr: 0.000038 loss: 0.3009 (0.3235) grad: 0.1225 (0.1608) time: 0.4949 data: 0.0023 max mem: 25051 +train: [16] [460/800] eta: 0:03:14 lr: 0.000037 loss: 0.3009 (0.3230) grad: 0.1225 (0.1630) time: 0.7249 data: 0.2161 max mem: 25051 +train: [16] [480/800] eta: 0:03:01 lr: 0.000036 loss: 0.3009 (0.3225) grad: 0.1170 (0.1641) time: 0.4799 data: 0.0028 max mem: 25051 +train: [16] [500/800] eta: 0:02:49 lr: 0.000036 loss: 0.2946 (0.3247) grad: 0.1266 (0.1634) time: 0.4922 data: 0.0020 max mem: 25051 +train: [16] [520/800] eta: 0:02:37 lr: 0.000035 loss: 0.3018 (0.3240) grad: 0.1266 (0.1632) time: 0.4697 data: 0.0028 max mem: 25051 +train: [16] [540/800] eta: 0:02:27 lr: 0.000035 loss: 0.3184 (0.3239) grad: 0.1154 (0.1623) time: 0.7026 data: 0.2077 max mem: 25051 +train: [16] [560/800] eta: 0:02:15 lr: 0.000034 loss: 0.3191 (0.3243) grad: 0.1102 (0.1608) time: 0.4812 data: 0.0025 max mem: 25051 +train: [16] [580/800] eta: 0:02:03 lr: 0.000034 loss: 0.3249 (0.3248) grad: 0.1154 (0.1659) time: 0.4869 data: 0.0028 max mem: 25051 +train: [16] [600/800] eta: 0:01:53 lr: 0.000033 loss: 0.3191 (0.3238) grad: 0.1325 (0.1664) time: 0.7064 data: 0.2212 max mem: 25051 +train: [16] [620/800] eta: 0:01:41 lr: 0.000033 loss: 0.3134 (0.3235) grad: 0.1383 (0.1664) time: 0.5170 data: 0.0245 max mem: 25051 +train: [16] [640/800] eta: 0:01:29 lr: 0.000032 loss: 0.3134 (0.3239) grad: 0.1818 (0.1674) time: 0.4965 data: 0.0031 max mem: 25051 +train: [16] [660/800] eta: 0:01:18 lr: 0.000032 loss: 0.2927 (0.3231) grad: 0.1374 (0.1666) time: 0.4860 data: 0.0018 max mem: 25051 +train: [16] [680/800] eta: 0:01:07 lr: 0.000031 loss: 0.2920 (0.3225) grad: 0.1358 (0.1658) time: 0.7709 data: 0.2912 max mem: 25051 +train: [16] [700/800] eta: 0:00:56 lr: 0.000031 loss: 0.2927 (0.3227) grad: 0.1287 (0.1656) time: 0.5008 data: 0.0060 max mem: 25051 +train: [16] [720/800] eta: 0:00:45 lr: 0.000031 loss: 0.3100 (0.3228) grad: 0.1374 (0.1691) time: 0.4962 data: 0.0021 max mem: 25051 +train: [16] [740/800] eta: 0:00:33 lr: 0.000030 loss: 0.3225 (0.3251) grad: 0.1440 (0.1690) time: 0.5084 data: 0.0027 max mem: 25051 +train: [16] [760/800] eta: 0:00:22 lr: 0.000030 loss: 0.3289 (0.3254) grad: 0.1681 (0.1692) time: 0.7103 data: 0.2229 max mem: 25051 +train: [16] [780/800] eta: 0:00:11 lr: 0.000029 loss: 0.3272 (0.3248) grad: 0.1706 (0.1690) time: 0.5597 data: 0.0033 max mem: 25051 +train: [16] [799/800] eta: 0:00:00 lr: 0.000029 loss: 0.3272 (0.3245) grad: 0.1678 (0.1693) time: 0.4951 data: 0.0030 max mem: 25051 +train: [16] Total time: 0:07:30 (0.5635 s / it) +train: [16] Summary: lr: 0.000029 loss: 0.3272 (0.3245) grad: 0.1678 (0.1693) +eval (validation): [16] [ 0/16] eta: 0:01:10 time: 4.3915 data: 4.0959 max mem: 25051 +eval (validation): [16] [15/16] eta: 0:00:00 time: 0.6842 data: 0.3192 max mem: 25051 +eval (validation): [16] Total time: 0:00:11 (0.7010 s / it) +cv: [16] best hparam: (0.028, 1.0) (002) ('002_lr2.8e-02_wd1.0e+00') loss: 0.609 acc: 0.781 f1: 0.767 bacc: 0.762 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/adhd200_dx__patch__attn/checkpoint-last.pth +train: [17] [ 0/800] eta: 0:58:50 lr: nan time: 4.4129 data: 3.9914 max mem: 25051 +train: [17] [ 20/800] eta: 0:09:28 lr: 0.000028 loss: 0.2959 (0.2972) grad: 0.2014 (0.1981) time: 0.5450 data: 0.0024 max mem: 25051 +train: [17] [ 40/800] eta: 0:07:41 lr: 0.000028 loss: 0.3251 (0.3253) grad: 0.2014 (0.2018) time: 0.4793 data: 0.0025 max mem: 25051 +train: [17] [ 60/800] eta: 0:07:01 lr: 0.000027 loss: 0.3361 (0.3308) grad: 0.1969 (0.1913) time: 0.4920 data: 0.0027 max mem: 25051 +train: [17] [ 80/800] eta: 0:07:12 lr: 0.000027 loss: 0.3313 (0.3312) grad: 0.1874 (0.1887) time: 0.6969 data: 0.2229 max mem: 25051 +train: [17] [100/800] eta: 0:06:52 lr: 0.000026 loss: 0.3361 (0.3294) grad: 0.1706 (0.1933) time: 0.5409 data: 0.0296 max mem: 25051 +train: [17] [120/800] eta: 0:06:32 lr: 0.000026 loss: 0.3313 (0.3268) grad: 0.1349 (0.1871) time: 0.5193 data: 0.0022 max mem: 25051 +train: [17] [140/800] eta: 0:06:13 lr: 0.000026 loss: 0.3075 (0.3251) grad: 0.1648 (0.1942) time: 0.4932 data: 0.0031 max mem: 25051 +train: [17] [160/800] eta: 0:06:16 lr: 0.000025 loss: 0.2851 (0.3244) grad: 0.1648 (0.1926) time: 0.7543 data: 0.2255 max mem: 25051 +train: [17] [180/800] eta: 0:06:02 lr: 0.000025 loss: 0.2885 (0.3257) grad: 0.1449 (0.1873) time: 0.5543 data: 0.0032 max mem: 25051 +train: [17] [200/800] eta: 0:05:45 lr: 0.000024 loss: 0.2863 (0.3259) grad: 0.1449 (0.1844) time: 0.4931 data: 0.0033 max mem: 25051 +train: [17] [220/800] eta: 0:05:29 lr: 0.000024 loss: 0.3135 (0.3295) grad: 0.1308 (0.1837) time: 0.4925 data: 0.0032 max mem: 25051 +train: [17] [240/800] eta: 0:05:27 lr: 0.000023 loss: 0.3355 (0.3295) grad: 0.1143 (0.1817) time: 0.7711 data: 0.2237 max mem: 25051 +train: [17] [260/800] eta: 0:05:12 lr: 0.000023 loss: 0.3135 (0.3275) grad: 0.1384 (0.1795) time: 0.5067 data: 0.0030 max mem: 25051 +train: [17] [280/800] eta: 0:04:59 lr: 0.000023 loss: 0.3181 (0.3284) grad: 0.1384 (0.1767) time: 0.5288 data: 0.0037 max mem: 25051 +train: [17] [300/800] eta: 0:04:54 lr: 0.000022 loss: 0.3146 (0.3269) grad: 0.1384 (0.1808) time: 0.7614 data: 0.2747 max mem: 25051 +train: [17] [320/800] eta: 0:04:39 lr: 0.000022 loss: 0.2930 (0.3237) grad: 0.1335 (0.1772) time: 0.5012 data: 0.0024 max mem: 25051 +train: [17] [340/800] eta: 0:04:25 lr: 0.000021 loss: 0.3187 (0.3246) grad: 0.1097 (0.1737) time: 0.4996 data: 0.0033 max mem: 25051 +train: [17] [360/800] eta: 0:04:12 lr: 0.000021 loss: 0.2862 (0.3241) grad: 0.1335 (0.1740) time: 0.5010 data: 0.0021 max mem: 25051 +train: [17] [380/800] eta: 0:04:03 lr: 0.000021 loss: 0.2862 (0.3238) grad: 0.1093 (0.1732) time: 0.7098 data: 0.2304 max mem: 25051 +train: [17] [400/800] eta: 0:03:50 lr: 0.000020 loss: 0.3332 (0.3240) grad: 0.1279 (0.1743) time: 0.5014 data: 0.0034 max mem: 25051 +train: [17] [420/800] eta: 0:03:37 lr: 0.000020 loss: 0.3093 (0.3245) grad: 0.1279 (0.1720) time: 0.4909 data: 0.0017 max mem: 25051 +train: [17] [440/800] eta: 0:03:24 lr: 0.000019 loss: 0.3093 (0.3223) grad: 0.1208 (0.1704) time: 0.4851 data: 0.0030 max mem: 25051 +train: [17] [460/800] eta: 0:03:15 lr: 0.000019 loss: 0.3261 (0.3246) grad: 0.1525 (0.1716) time: 0.7211 data: 0.2108 max mem: 25051 +train: [17] [480/800] eta: 0:03:02 lr: 0.000019 loss: 0.3262 (0.3251) grad: 0.1208 (0.1691) time: 0.4870 data: 0.0025 max mem: 25051 +train: [17] [500/800] eta: 0:02:50 lr: 0.000018 loss: 0.3412 (0.3257) grad: 0.1645 (0.1715) time: 0.4896 data: 0.0029 max mem: 25051 +train: [17] [520/800] eta: 0:02:38 lr: 0.000018 loss: 0.3480 (0.3257) grad: 0.1468 (0.1704) time: 0.4975 data: 0.0028 max mem: 25051 +train: [17] [540/800] eta: 0:02:29 lr: 0.000017 loss: 0.3412 (0.3272) grad: 0.1414 (0.1709) time: 0.7704 data: 0.2660 max mem: 25051 +train: [17] [560/800] eta: 0:02:17 lr: 0.000017 loss: 0.3237 (0.3258) grad: 0.1414 (0.1698) time: 0.5312 data: 0.0625 max mem: 25051 +train: [17] [580/800] eta: 0:02:05 lr: 0.000017 loss: 0.3212 (0.3265) grad: 0.1306 (0.1701) time: 0.5137 data: 0.0288 max mem: 25051 +train: [17] [600/800] eta: 0:01:54 lr: 0.000016 loss: 0.3135 (0.3269) grad: 0.1306 (0.1691) time: 0.6843 data: 0.2245 max mem: 25051 +train: [17] [620/800] eta: 0:01:42 lr: 0.000016 loss: 0.3135 (0.3262) grad: 0.1306 (0.1686) time: 0.5122 data: 0.0037 max mem: 25051 +train: [17] [640/800] eta: 0:01:31 lr: 0.000016 loss: 0.3284 (0.3274) grad: 0.1370 (0.1693) time: 0.4926 data: 0.0022 max mem: 25051 +train: [17] [660/800] eta: 0:01:19 lr: 0.000015 loss: 0.3075 (0.3257) grad: 0.1370 (0.1700) time: 0.4967 data: 0.0030 max mem: 25051 +train: [17] [680/800] eta: 0:01:08 lr: 0.000015 loss: 0.2969 (0.3258) grad: 0.1370 (0.1699) time: 0.7024 data: 0.2256 max mem: 25051 +train: [17] [700/800] eta: 0:00:57 lr: 0.000015 loss: 0.2877 (0.3250) grad: 0.1520 (0.1694) time: 0.5602 data: 0.0752 max mem: 25051 +train: [17] [720/800] eta: 0:00:45 lr: 0.000014 loss: 0.2874 (0.3248) grad: 0.1194 (0.1674) time: 0.4926 data: 0.0253 max mem: 25051 +train: [17] [740/800] eta: 0:00:33 lr: 0.000014 loss: 0.2874 (0.3242) grad: 0.1134 (0.1655) time: 0.4750 data: 0.0031 max mem: 25051 +train: [17] [760/800] eta: 0:00:22 lr: 0.000014 loss: 0.3096 (0.3262) grad: 0.1134 (0.1666) time: 0.7232 data: 0.2500 max mem: 25051 +train: [17] [780/800] eta: 0:00:11 lr: 0.000013 loss: 0.3137 (0.3256) grad: 0.1134 (0.1685) time: 0.5006 data: 0.0022 max mem: 25051 +train: [17] [799/800] eta: 0:00:00 lr: 0.000013 loss: 0.3284 (0.3257) grad: 0.1207 (0.1680) time: 0.5086 data: 0.0030 max mem: 25051 +train: [17] Total time: 0:07:33 (0.5671 s / it) +train: [17] Summary: lr: 0.000013 loss: 0.3284 (0.3257) grad: 0.1207 (0.1680) +eval (validation): [17] [ 0/16] eta: 0:01:10 time: 4.4097 data: 4.1562 max mem: 25051 +eval (validation): [17] [15/16] eta: 0:00:00 time: 0.6301 data: 0.2872 max mem: 25051 +eval (validation): [17] Total time: 0:00:10 (0.6465 s / it) +cv: [17] best hparam: (0.028, 1.0) (002) ('002_lr2.8e-02_wd1.0e+00') loss: 0.609 acc: 0.781 f1: 0.767 bacc: 0.762 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/adhd200_dx__patch__attn/checkpoint-last.pth +train: [18] [ 0/800] eta: 1:02:48 lr: nan time: 4.7112 data: 4.2614 max mem: 25051 +train: [18] [ 20/800] eta: 0:10:04 lr: 0.000013 loss: 0.2806 (0.3024) grad: 0.2762 (0.2257) time: 0.5777 data: 0.0032 max mem: 25051 +train: [18] [ 40/800] eta: 0:08:05 lr: 0.000012 loss: 0.3358 (0.3245) grad: 0.1986 (0.2136) time: 0.4968 data: 0.0027 max mem: 25051 +train: [18] [ 60/800] eta: 0:07:28 lr: 0.000012 loss: 0.3362 (0.3295) grad: 0.2340 (0.2127) time: 0.5395 data: 0.0036 max mem: 25051 +train: [18] [ 80/800] eta: 0:07:35 lr: 0.000012 loss: 0.3344 (0.3259) grad: 0.1986 (0.2044) time: 0.7126 data: 0.2245 max mem: 25051 +train: [18] [100/800] eta: 0:07:03 lr: 0.000011 loss: 0.3344 (0.3293) grad: 0.1890 (0.2013) time: 0.4899 data: 0.0038 max mem: 25051 +train: [18] [120/800] eta: 0:06:40 lr: 0.000011 loss: 0.3199 (0.3265) grad: 0.1664 (0.1985) time: 0.5108 data: 0.0017 max mem: 25051 +train: [18] [140/800] eta: 0:06:21 lr: 0.000011 loss: 0.3084 (0.3233) grad: 0.1623 (0.1939) time: 0.5078 data: 0.0025 max mem: 25051 +train: [18] [160/800] eta: 0:06:20 lr: 0.000011 loss: 0.3125 (0.3266) grad: 0.1426 (0.1812) time: 0.7112 data: 0.2243 max mem: 25051 +train: [18] [180/800] eta: 0:06:04 lr: 0.000010 loss: 0.3081 (0.3261) grad: 0.1067 (0.1814) time: 0.5332 data: 0.0029 max mem: 25051 +train: [18] [200/800] eta: 0:05:47 lr: 0.000010 loss: 0.2971 (0.3228) grad: 0.0969 (0.1743) time: 0.5113 data: 0.0034 max mem: 25051 +train: [18] [220/800] eta: 0:05:31 lr: 0.000010 loss: 0.3101 (0.3213) grad: 0.1145 (0.1737) time: 0.4862 data: 0.0031 max mem: 25051 +train: [18] [240/800] eta: 0:05:30 lr: 0.000009 loss: 0.2854 (0.3169) grad: 0.1348 (0.1713) time: 0.7974 data: 0.2334 max mem: 25051 +train: [18] [260/800] eta: 0:05:15 lr: 0.000009 loss: 0.2839 (0.3166) grad: 0.1348 (0.1689) time: 0.5062 data: 0.0028 max mem: 25051 +train: [18] [280/800] eta: 0:05:00 lr: 0.000009 loss: 0.2839 (0.3169) grad: 0.1469 (0.1679) time: 0.5097 data: 0.0031 max mem: 25051 +train: [18] [300/800] eta: 0:04:53 lr: 0.000009 loss: 0.2865 (0.3169) grad: 0.1401 (0.1642) time: 0.7135 data: 0.2266 max mem: 25051 +train: [18] [320/800] eta: 0:04:40 lr: 0.000008 loss: 0.3117 (0.3184) grad: 0.1166 (0.1636) time: 0.5294 data: 0.0026 max mem: 25051 +train: [18] [340/800] eta: 0:04:26 lr: 0.000008 loss: 0.3117 (0.3173) grad: 0.1202 (0.1631) time: 0.5045 data: 0.0032 max mem: 25051 +train: [18] [360/800] eta: 0:04:12 lr: 0.000008 loss: 0.2976 (0.3155) grad: 0.1170 (0.1627) time: 0.5053 data: 0.0031 max mem: 25051 +train: [18] [380/800] eta: 0:04:04 lr: 0.000008 loss: 0.2836 (0.3136) grad: 0.1202 (0.1619) time: 0.6990 data: 0.2169 max mem: 25051 +train: [18] [400/800] eta: 0:03:51 lr: 0.000007 loss: 0.2790 (0.3127) grad: 0.1235 (0.1644) time: 0.5266 data: 0.0037 max mem: 25051 +train: [18] [420/800] eta: 0:03:38 lr: 0.000007 loss: 0.2790 (0.3117) grad: 0.1252 (0.1645) time: 0.4882 data: 0.0022 max mem: 25051 +train: [18] [440/800] eta: 0:03:25 lr: 0.000007 loss: 0.2696 (0.3102) grad: 0.1211 (0.1622) time: 0.4862 data: 0.0021 max mem: 25051 +train: [18] [460/800] eta: 0:03:16 lr: 0.000007 loss: 0.2696 (0.3105) grad: 0.1252 (0.1608) time: 0.7332 data: 0.2090 max mem: 25051 +train: [18] [480/800] eta: 0:03:03 lr: 0.000006 loss: 0.2884 (0.3113) grad: 0.1044 (0.1616) time: 0.5052 data: 0.0029 max mem: 25051 +train: [18] [500/800] eta: 0:02:51 lr: 0.000006 loss: 0.3020 (0.3108) grad: 0.1168 (0.1634) time: 0.5013 data: 0.0035 max mem: 25051 +train: [18] [520/800] eta: 0:02:39 lr: 0.000006 loss: 0.3064 (0.3111) grad: 0.1182 (0.1620) time: 0.4971 data: 0.0028 max mem: 25051 +train: [18] [540/800] eta: 0:02:29 lr: 0.000006 loss: 0.3188 (0.3111) grad: 0.1119 (0.1602) time: 0.7374 data: 0.2206 max mem: 25051 +train: [18] [560/800] eta: 0:02:17 lr: 0.000006 loss: 0.3064 (0.3109) grad: 0.1157 (0.1614) time: 0.4908 data: 0.0032 max mem: 25051 +train: [18] [580/800] eta: 0:02:05 lr: 0.000005 loss: 0.3249 (0.3125) grad: 0.1152 (0.1618) time: 0.4944 data: 0.0023 max mem: 25051 +train: [18] [600/800] eta: 0:01:55 lr: 0.000005 loss: 0.3266 (0.3136) grad: 0.1598 (0.1653) time: 0.7543 data: 0.2838 max mem: 25051 +train: [18] [620/800] eta: 0:01:43 lr: 0.000005 loss: 0.3485 (0.3160) grad: 0.1641 (0.1652) time: 0.5141 data: 0.0069 max mem: 25051 +train: [18] [640/800] eta: 0:01:31 lr: 0.000005 loss: 0.3382 (0.3151) grad: 0.1947 (0.1670) time: 0.5288 data: 0.0389 max mem: 25051 +train: [18] [660/800] eta: 0:01:19 lr: 0.000005 loss: 0.3310 (0.3157) grad: 0.1539 (0.1650) time: 0.5062 data: 0.0051 max mem: 25051 +train: [18] [680/800] eta: 0:01:08 lr: 0.000004 loss: 0.3298 (0.3155) grad: 0.1507 (0.1649) time: 0.6899 data: 0.2150 max mem: 25051 +train: [18] [700/800] eta: 0:00:57 lr: 0.000004 loss: 0.3086 (0.3160) grad: 0.1252 (0.1633) time: 0.5527 data: 0.0303 max mem: 25051 +train: [18] [720/800] eta: 0:00:45 lr: 0.000004 loss: 0.3344 (0.3169) grad: 0.1220 (0.1638) time: 0.5048 data: 0.0026 max mem: 25051 +train: [18] [740/800] eta: 0:00:34 lr: 0.000004 loss: 0.3124 (0.3167) grad: 0.1507 (0.1661) time: 0.4812 data: 0.0029 max mem: 25051 +train: [18] [760/800] eta: 0:00:23 lr: 0.000004 loss: 0.3344 (0.3178) grad: 0.1319 (0.1656) time: 0.8233 data: 0.2889 max mem: 25051 +train: [18] [780/800] eta: 0:00:11 lr: 0.000003 loss: 0.3275 (0.3183) grad: 0.1466 (0.1655) time: 0.5351 data: 0.0029 max mem: 25051 +train: [18] [799/800] eta: 0:00:00 lr: 0.000003 loss: 0.3275 (0.3196) grad: 0.1377 (0.1670) time: 0.5368 data: 0.0038 max mem: 25051 +train: [18] Total time: 0:07:39 (0.5738 s / it) +train: [18] Summary: lr: 0.000003 loss: 0.3275 (0.3196) grad: 0.1377 (0.1670) +eval (validation): [18] [ 0/16] eta: 0:01:15 time: 4.7320 data: 4.4171 max mem: 25051 +eval (validation): [18] [15/16] eta: 0:00:00 time: 0.6591 data: 0.2981 max mem: 25051 +eval (validation): [18] Total time: 0:00:10 (0.6727 s / it) +cv: [18] best hparam: (0.028, 1.0) (002) ('002_lr2.8e-02_wd1.0e+00') loss: 0.609 acc: 0.781 f1: 0.767 bacc: 0.762 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/adhd200_dx__patch__attn/checkpoint-last.pth +train: [19] [ 0/800] eta: 1:02:30 lr: nan time: 4.6883 data: 4.3220 max mem: 25051 +train: [19] [ 20/800] eta: 0:10:08 lr: 0.000003 loss: 0.3011 (0.3078) grad: 0.1486 (0.1606) time: 0.5849 data: 0.0445 max mem: 25051 +train: [19] [ 40/800] eta: 0:08:22 lr: 0.000003 loss: 0.3011 (0.3157) grad: 0.1511 (0.1763) time: 0.5363 data: 0.0026 max mem: 25051 +train: [19] [ 60/800] eta: 0:07:38 lr: 0.000003 loss: 0.3264 (0.3310) grad: 0.1511 (0.1833) time: 0.5358 data: 0.0035 max mem: 25051 +train: [19] [ 80/800] eta: 0:07:49 lr: 0.000003 loss: 0.3011 (0.3297) grad: 0.1486 (0.1904) time: 0.7503 data: 0.2688 max mem: 25051 +train: [19] [100/800] eta: 0:07:17 lr: 0.000003 loss: 0.3004 (0.3268) grad: 0.1352 (0.1766) time: 0.5133 data: 0.0032 max mem: 25051 +train: [19] [120/800] eta: 0:06:51 lr: 0.000002 loss: 0.2976 (0.3183) grad: 0.1289 (0.1695) time: 0.5076 data: 0.0016 max mem: 25051 +train: [19] [140/800] eta: 0:06:29 lr: 0.000002 loss: 0.2976 (0.3233) grad: 0.1060 (0.1607) time: 0.4963 data: 0.0028 max mem: 25051 +train: [19] [160/800] eta: 0:06:25 lr: 0.000002 loss: 0.2998 (0.3244) grad: 0.1182 (0.1612) time: 0.6916 data: 0.2165 max mem: 25051 +train: [19] [180/800] eta: 0:06:06 lr: 0.000002 loss: 0.3046 (0.3222) grad: 0.1289 (0.1597) time: 0.4991 data: 0.0023 max mem: 25051 +train: [19] [200/800] eta: 0:05:49 lr: 0.000002 loss: 0.3248 (0.3239) grad: 0.1303 (0.1575) time: 0.5063 data: 0.0030 max mem: 25051 +train: [19] [220/800] eta: 0:05:35 lr: 0.000002 loss: 0.3046 (0.3218) grad: 0.1449 (0.1623) time: 0.5422 data: 0.0038 max mem: 25051 +train: [19] [240/800] eta: 0:05:33 lr: 0.000002 loss: 0.3000 (0.3222) grad: 0.1361 (0.1598) time: 0.7765 data: 0.2944 max mem: 25051 +train: [19] [260/800] eta: 0:05:17 lr: 0.000001 loss: 0.3000 (0.3208) grad: 0.1124 (0.1562) time: 0.4983 data: 0.0238 max mem: 25051 +train: [19] [280/800] eta: 0:05:02 lr: 0.000001 loss: 0.2926 (0.3190) grad: 0.1115 (0.1554) time: 0.5102 data: 0.0221 max mem: 25051 +train: [19] [300/800] eta: 0:04:56 lr: 0.000001 loss: 0.3014 (0.3193) grad: 0.1074 (0.1581) time: 0.7490 data: 0.2864 max mem: 25051 +train: [19] [320/800] eta: 0:04:43 lr: 0.000001 loss: 0.3053 (0.3232) grad: 0.1239 (0.1580) time: 0.5361 data: 0.0466 max mem: 25051 +train: [19] [340/800] eta: 0:04:30 lr: 0.000001 loss: 0.3053 (0.3219) grad: 0.1329 (0.1568) time: 0.5441 data: 0.0549 max mem: 25051 +train: [19] [360/800] eta: 0:04:16 lr: 0.000001 loss: 0.3080 (0.3197) grad: 0.1397 (0.1600) time: 0.4964 data: 0.0018 max mem: 25051 +train: [19] [380/800] eta: 0:04:06 lr: 0.000001 loss: 0.3146 (0.3219) grad: 0.1708 (0.1641) time: 0.6923 data: 0.2223 max mem: 25051 +train: [19] [400/800] eta: 0:03:53 lr: 0.000001 loss: 0.3152 (0.3234) grad: 0.1523 (0.1613) time: 0.5188 data: 0.0328 max mem: 25051 +train: [19] [420/800] eta: 0:03:40 lr: 0.000001 loss: 0.3146 (0.3231) grad: 0.1708 (0.1639) time: 0.5025 data: 0.0021 max mem: 25051 +train: [19] [440/800] eta: 0:03:27 lr: 0.000001 loss: 0.2909 (0.3220) grad: 0.1893 (0.1655) time: 0.4853 data: 0.0031 max mem: 25051 +train: [19] [460/800] eta: 0:03:17 lr: 0.000001 loss: 0.2790 (0.3208) grad: 0.1373 (0.1638) time: 0.6906 data: 0.2160 max mem: 25051 +train: [19] [480/800] eta: 0:03:05 lr: 0.000001 loss: 0.2750 (0.3213) grad: 0.1730 (0.1654) time: 0.5523 data: 0.0025 max mem: 25051 +train: [19] [500/800] eta: 0:02:53 lr: 0.000000 loss: 0.2909 (0.3207) grad: 0.1426 (0.1644) time: 0.5107 data: 0.0031 max mem: 25051 +train: [19] [520/800] eta: 0:02:41 lr: 0.000000 loss: 0.3027 (0.3209) grad: 0.1386 (0.1647) time: 0.5199 data: 0.0037 max mem: 25051 +train: [19] [540/800] eta: 0:02:31 lr: 0.000000 loss: 0.2966 (0.3197) grad: 0.1386 (0.1636) time: 0.7910 data: 0.3000 max mem: 25051 +train: [19] [560/800] eta: 0:02:19 lr: 0.000000 loss: 0.2863 (0.3189) grad: 0.1167 (0.1617) time: 0.4957 data: 0.0030 max mem: 25051 +train: [19] [580/800] eta: 0:02:06 lr: 0.000000 loss: 0.2841 (0.3175) grad: 0.0993 (0.1601) time: 0.5007 data: 0.0034 max mem: 25051 +train: [19] [600/800] eta: 0:01:56 lr: 0.000000 loss: 0.2841 (0.3175) grad: 0.1020 (0.1619) time: 0.6782 data: 0.2177 max mem: 25051 +train: [19] [620/800] eta: 0:01:44 lr: 0.000000 loss: 0.2662 (0.3155) grad: 0.1070 (0.1618) time: 0.5102 data: 0.0064 max mem: 25051 +train: [19] [640/800] eta: 0:01:32 lr: 0.000000 loss: 0.2662 (0.3157) grad: 0.1715 (0.1634) time: 0.5370 data: 0.0509 max mem: 25051 +train: [19] [660/800] eta: 0:01:20 lr: 0.000000 loss: 0.3132 (0.3169) grad: 0.1852 (0.1638) time: 0.5669 data: 0.0463 max mem: 25051 +train: [19] [680/800] eta: 0:01:09 lr: 0.000000 loss: 0.2729 (0.3155) grad: 0.1444 (0.1633) time: 0.6934 data: 0.2190 max mem: 25051 +train: [19] [700/800] eta: 0:00:57 lr: 0.000000 loss: 0.3132 (0.3157) grad: 0.1444 (0.1636) time: 0.4898 data: 0.0027 max mem: 25051 +train: [19] [720/800] eta: 0:00:45 lr: 0.000000 loss: 0.3186 (0.3167) grad: 0.1209 (0.1653) time: 0.4669 data: 0.0030 max mem: 25051 +train: [19] [740/800] eta: 0:00:34 lr: 0.000000 loss: 0.2963 (0.3163) grad: 0.1299 (0.1646) time: 0.4937 data: 0.0019 max mem: 25051 +train: [19] [760/800] eta: 0:00:23 lr: 0.000000 loss: 0.3260 (0.3166) grad: 0.1588 (0.1651) time: 0.7917 data: 0.2892 max mem: 25051 +train: [19] [780/800] eta: 0:00:11 lr: 0.000000 loss: 0.3409 (0.3171) grad: 0.1588 (0.1648) time: 0.5035 data: 0.0022 max mem: 25051 +train: [19] [799/800] eta: 0:00:00 lr: 0.000000 loss: 0.3409 (0.3179) grad: 0.1588 (0.1657) time: 0.5044 data: 0.0033 max mem: 25051 +train: [19] Total time: 0:07:39 (0.5748 s / it) +train: [19] Summary: lr: 0.000000 loss: 0.3409 (0.3179) grad: 0.1588 (0.1657) +eval (validation): [19] [ 0/16] eta: 0:01:11 time: 4.4902 data: 4.2173 max mem: 25051 +eval (validation): [19] [15/16] eta: 0:00:00 time: 0.6520 data: 0.2922 max mem: 25051 +eval (validation): [19] Total time: 0:00:10 (0.6661 s / it) +cv: [19] best hparam: (0.028, 1.0) (002) ('002_lr2.8e-02_wd1.0e+00') loss: 0.609 acc: 0.781 f1: 0.767 bacc: 0.762 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/adhd200_dx__patch__attn/checkpoint-last.pth +evaluating last checkpoint: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/adhd200_dx__patch__attn/checkpoint-last.pth +eval model info: +{"score": 0.7619047619047619, "hparam": [0.028, 1.0], "hparam_id": 2, "epoch": 19, "is_best": false, "best_score": 0.7837301587301587} +eval (train): [20] [ 0/76] eta: 0:05:50 time: 4.6068 data: 4.2811 max mem: 25051 +eval (train): [20] [20/76] eta: 0:00:42 time: 0.5662 data: 0.1508 max mem: 25051 +eval (train): [20] [40/76] eta: 0:00:23 time: 0.5295 data: 0.1249 max mem: 25051 +eval (train): [20] [60/76] eta: 0:00:09 time: 0.5673 data: 0.1733 max mem: 25051 +eval (train): [20] [75/76] eta: 0:00:00 time: 0.4433 data: 0.0715 max mem: 25051 +eval (train): [20] Total time: 0:00:44 (0.5829 s / it) +eval (validation): [20] [ 0/16] eta: 0:01:13 time: 4.5772 data: 4.2458 max mem: 25051 +eval (validation): [20] [15/16] eta: 0:00:00 time: 0.6815 data: 0.2782 max mem: 25051 +eval (validation): [20] Total time: 0:00:11 (0.6919 s / it) +eval (test): [20] [ 0/17] eta: 0:01:15 time: 4.4291 data: 4.1152 max mem: 25051 +eval (test): [20] [16/17] eta: 0:00:00 time: 0.6500 data: 0.2444 max mem: 25051 +eval (test): [20] Total time: 0:00:11 (0.6589 s / it) +evaluating best checkpoint: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/adhd200_dx__patch__attn/checkpoint-best.pth +eval model info: +{"score": 0.7837301587301587, "hparam": [0.087, 1.0], "hparam_id": 9, "epoch": 9, "is_best": true, "best_score": 0.7837301587301587} +eval (train): [20] [ 0/76] eta: 0:05:37 time: 4.4349 data: 4.1789 max mem: 25051 +eval (train): [20] [20/76] eta: 0:00:40 time: 0.5405 data: 0.1469 max mem: 25051 +eval (train): [20] [40/76] eta: 0:00:21 time: 0.4805 data: 0.0839 max mem: 25051 +eval (train): [20] [60/76] eta: 0:00:09 time: 0.4764 data: 0.0734 max mem: 25051 +eval (train): [20] [75/76] eta: 0:00:00 time: 0.4822 data: 0.0986 max mem: 25051 +eval (train): [20] Total time: 0:00:41 (0.5475 s / it) +eval (validation): [20] [ 0/16] eta: 0:01:12 time: 4.5031 data: 4.2373 max mem: 25051 +eval (validation): [20] [15/16] eta: 0:00:00 time: 0.7471 data: 0.3744 max mem: 25051 +eval (validation): [20] Total time: 0:00:12 (0.7585 s / it) +eval (test): [20] [ 0/17] eta: 0:01:21 time: 4.7870 data: 4.4676 max mem: 25051 +eval (test): [20] [16/17] eta: 0:00:00 time: 0.7856 data: 0.4162 max mem: 25051 +eval (test): [20] Total time: 0:00:13 (0.7970 s / it) +eval results: + +| model | repr | clf | dataset | ckpt | epoch | lr | wd | hparam_id | hparam | split | loss | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:------|:-----------|:-------|--------:|---------:|-----:|------------:|:-------------|:-----------|--------:|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | attn | adhd200_dx | best | 9 | 2.61e-05 | 0.05 | 9 | [0.087, 1.0] | train | 0.58614 | 0.68771 | 0.027128 | 0.6818 | 0.027772 | 0.6815 | 0.027836 | +| flat_mae | patch | attn | adhd200_dx | best | 9 | 2.61e-05 | 0.05 | 9 | [0.087, 1.0] | validation | 0.5937 | 0.79688 | 0.048592 | 0.78813 | 0.052621 | 0.78373 | 0.051479 | +| flat_mae | patch | attn | adhd200_dx | best | 9 | 2.61e-05 | 0.05 | 9 | [0.087, 1.0] | test | 0.70046 | 0.6 | 0.059916 | 0.58821 | 0.062207 | 0.58784 | 0.061459 | + + +done! total time: 2:40:43 diff --git a/input_space_v3/flat_lr1e-3_1/eval_v2/adhd200_dx__patch__attn/train_log.json b/input_space_v3/flat_lr1e-3_1/eval_v2/adhd200_dx__patch__attn/train_log.json new file mode 100644 index 0000000000000000000000000000000000000000..c9d1de07b46d8d9d37cf5dcc530b96530cbad025 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_1/eval_v2/adhd200_dx__patch__attn/train_log.json @@ -0,0 +1,20 @@ +{"epoch": 0, "train/lr": 2.987987987987988e-05, "train/loss": 0.6753529052436352, "train/grad": 0.2778871288895607, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.7029150390625, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.7019970703125, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.7005419921875, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.6990673828125, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.697958984375, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.69642578125, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.6948095703125, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.6933447265625, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.691640625, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.68998046875, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.6885302734375, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.6867041015625, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.6852197265625, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.683447265625, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.68196533203125, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.680908203125, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.679658203125, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.67841796875, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.677275390625, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.6764111328125, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.6754931640625, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.674501953125, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.6733251953125, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.671962890625, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.67041259765625, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.668515625, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.666923828125, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.665650634765625, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.664263916015625, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.662945556640625, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.66124267578125, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.65926025390625, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.656671142578125, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.65499267578125, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.65389404296875, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.654569091796875, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.65717041015625, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.6599896240234375, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.66229248046875, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.658958740234375, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.6588385009765625, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.659647216796875, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.6609173583984375, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.6636395263671875, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.6682632446289063, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.6729559326171874, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.677166748046875, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.6820233154296875, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.6885855102539062, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.040672953175380826, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.04035954795777798, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.03991681362036616, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.03955489196814597, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.03925455417949706, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.0389173498051241, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.03861296228133142, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.03834732834249735, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.03807509846054018, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.0378619316034019, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.0376955890073441, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.037508210602682085, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.037367879673838617, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.03723931957036257, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.037160272719338534, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.03712032682262361, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.03711428515147418, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.03713411542121321, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.037201642990112305, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.037266531204804776, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.03736418354324997, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.037441275632008914, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.037484096959233285, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.037509408947080373, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0374990504514426, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.03736501389183104, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.03715895785251632, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.036936701962258664, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0367385496548377, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.036754345018416644, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.036813245145604016, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.036853472064249215, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.03689360454212874, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.036909524877555666, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.03701611425494775, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.03741200321353972, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.03789244209416211, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.03802863721968606, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.03756665253546089, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.03621158105088398, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.036335441709961745, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.03638298630481586, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.036143574027810245, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.03567621116992086, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.03506478554103523, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.03479496848769486, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.03543826972367242, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.03677271066466346, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.03853285848163068, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.6879174709320068, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.6864351034164429, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.6845382452011108, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.6830813884735107, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.6818917393684387, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.6804535388946533, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.6791192293167114, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.67781662940979, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.6760532855987549, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.6743098497390747, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.6725648641586304, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.6701458096504211, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.667859673500061, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.6647682189941406, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.6619301438331604, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.6593533158302307, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.6564761400222778, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.6535858511924744, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.6509708166122437, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.648870587348938, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.6462122201919556, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.6428275108337402, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.6382768750190735, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.6328907012939453, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.6279433965682983, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.6258977651596069, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.630275547504425, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.6386351585388184, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.6494265794754028, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.6627501845359802, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.686638355255127, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.7136372923851013, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.7310720086097717, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.7271490097045898, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.7033213376998901, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.6830587387084961, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.6730955243110657, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.6684905886650085, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.6669450998306274, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.6346408724784851, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.639464795589447, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.6372301578521729, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.633338212966919, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.6293089985847473, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.625029444694519, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.6137517690658569, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.6068501472473145, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.6044245958328247, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.6088199615478516, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.5625, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.578125, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.5625, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.5625, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.5625, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.5625, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.5625, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.5625, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.5625, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.5625, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.5625, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.5625, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.546875, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.5625, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.578125, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.5625, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.65625, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.71875, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.71875, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.671875, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.6875, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.703125, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.71875, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.734375, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.734375, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.703125, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.671875, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.59375, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.59375, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.609375, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.59375, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.578125, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.5625, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.578125, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.609375, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.625, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.65625, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.671875, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.65625, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.6875, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.6875, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.6875, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.6875, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.6875, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.671875, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.703125, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.703125, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.71875, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.71875, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.4166666666666667, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.3981191222570533, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.36, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.36, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.36, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.36, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.36, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.36, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.36, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.36, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.36, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.36, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.35353535353535354, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.3904761904761905, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.4253408713002993, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.43929912390488113, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.6190476190476191, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.708502024291498, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.7142857142857143, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.6698599852616065, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.6862745098039216, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.7024712503058478, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.7176470588235294, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.7311588831233011, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.7262893081761006, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.6744310575635877, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.6008316008316008, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.4583333333333333, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.4583333333333333, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.46790821416694384, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.4340136054421769, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.3981191222570533, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.36, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.3981191222570533, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.46790821416694384, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.5, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.5594493116395495, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.5870967741935484, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.5748792270531401, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.6257309941520468, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.6257309941520468, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.6257309941520468, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.6257309941520468, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.6257309941520468, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.6127917026793431, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.6590972806279787, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.6744310575635877, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.7142857142857143, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.7142857142857143, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.5079365079365079, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.5178571428571429, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.5, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.5, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.5, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.5, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.5, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.5, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.5, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.5, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.5, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.5, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.4861111111111111, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.503968253968254, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.5218253968253969, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.5119047619047619, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.626984126984127, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.7063492063492063, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.7142857142857143, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.6726190476190477, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.6904761904761905, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.7083333333333333, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.7222222222222222, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.7321428571428572, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.7242063492063493, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.6765873015873016, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.628968253968254, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.5396825396825397, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.5396825396825397, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.5535714285714286, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.5357142857142857, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.5178571428571429, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.5, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.5178571428571429, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.5535714285714286, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.5714285714285714, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.6071428571428571, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.625, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.6111111111111112, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.6468253968253969, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.6468253968253969, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.6468253968253969, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.6468253968253969, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.6468253968253969, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.6329365079365079, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.6686507936507936, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.6765873015873016, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.7142857142857143, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.7142857142857143, "id_best": 23, "lr_best": 0.00025499999999999996, "wd_best": 0.05, "train/loss_best": 0.671962890625, "validation/loss_best": 0.6328907012939453, "validation/acc_best": 0.734375, "validation/f1_best": 0.7311588831233011, "validation/bacc_best": 0.7321428571428572} +{"epoch": 1, "train/lr": 8.993993993993998e-05, "train/loss": 0.6452708502113819, "train/grad": 0.2875894271209836, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.676494140625, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.675380859375, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.6740771484375, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.672841796875, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.6719140625, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.67066650390625, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.66940673828125, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.668154296875, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.66659423828125, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.66509033203125, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.66376708984375, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.66178466796875, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.66025390625, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.65802490234375, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.6562255859375, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.654571533203125, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.652681884765625, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.6506396484375, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.648489990234375, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.64681396484375, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.64485107421875, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.64301025390625, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.6409423828125, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.638524169921875, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.6367620849609374, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.63625, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.6364593505859375, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.636341552734375, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.6343612670898438, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.6302960205078125, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.6272647094726562, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.6261163330078126, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.628455810546875, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.6335671997070312, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.6365682983398437, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.6346240234375, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.6300921630859375, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.6276254272460937, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.6204603576660156, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.5998541259765625, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.5937559509277344, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.5955010986328125, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.6056144714355469, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.6032295989990234, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.5952008056640625, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.6401580333709717, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.6688906955718994, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.7572920429706573, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.6523296783864498, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.032849468828644604, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.032732148312497884, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.03261449674842879, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.032554288625251504, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.03253518101293593, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.03251454239245504, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.03251754503697157, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.03252039664890617, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.03253609260544181, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.032569368202239275, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.032592630097642544, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.03266692841891199, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.032739909649826586, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.032870576297864315, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.03301786146592349, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.03315505643840879, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.03335590990958735, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.033588553867302834, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.03387578629888594, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.03417939153965563, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.034606543686240915, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.035045042145065965, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.035297509452793745, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.035216547893360255, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.034994680813979356, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.03498202023562044, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.03529674503719434, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.03569453025935218, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.03603433269076049, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.036336291199550036, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.036439830707386135, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.03651482636108994, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.036318832151591776, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.035511773116886615, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.03437638217350468, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.03387642591260374, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.033143021524883805, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.03294147249078378, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.03135105935623869, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.029057703528087585, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.029105213871225714, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.03004259165842086, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.033179662688635286, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.034410478938370945, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.03922310996800661, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.04568418471608311, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.05870077923871577, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.07194126126356423, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.06700323218945414, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.6755046844482422, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.6739238500595093, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.671583890914917, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.6692694425582886, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.6671403646469116, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.6644607782363892, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.6615791916847229, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.6586126685142517, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.6551060676574707, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.6517146825790405, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.6487988829612732, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.6447315812110901, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.6412890553474426, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.6370640993118286, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.633428692817688, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.6304574012756348, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.6270453333854675, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.6235576868057251, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.6208175420761108, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.6193075180053711, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.6189426183700562, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.6229650974273682, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.6359066367149353, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.652749240398407, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.661952555179596, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.6705747246742249, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.674936056137085, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.6679450273513794, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.6496438980102539, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.6296568512916565, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.6199663877487183, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.6147586107254028, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.6083396077156067, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.6072710156440735, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.6105900406837463, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.6231330633163452, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.6459279656410217, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.6547079086303711, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.6153563857078552, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.569685697555542, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.5614181756973267, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.5800886154174805, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.6392616033554077, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.6560335755348206, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.7632762789726257, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.7279894351959229, "validation/loss_046_lr3.6e+01_wd1.0e+00": 1.0462770462036133, "validation/loss_047_lr4.3e+01_wd1.0e+00": 1.2121520042419434, "validation/loss_048_lr5.0e+01_wd1.0e+00": 1.82326340675354, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.5625, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.5625, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.5625, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.5625, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.5625, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.5625, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.546875, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.546875, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.578125, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.59375, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.5625, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.65625, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.65625, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.703125, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.703125, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.703125, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.71875, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.71875, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.71875, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.71875, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.703125, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.65625, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.640625, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.625, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.625, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.625, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.625, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.640625, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.65625, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.671875, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.671875, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.71875, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.734375, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.734375, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.734375, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.6875, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.671875, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.640625, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.71875, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.734375, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.78125, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.75, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.640625, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.625, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.59375, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.625, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.46875, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.53125, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.578125, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.36, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.36, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.36, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.36, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.36, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.36, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.35353535353535354, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.35353535353535354, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.4253408713002993, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.4583333333333333, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.43929912390488113, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.6, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.6101882613510521, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.6805883898082479, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.6805883898082479, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.6805883898082479, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.7, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.7, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.694591728525981, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.6883116883116883, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.6673050615595075, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.5883040935672514, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.5477726574500767, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.5, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.5, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.5, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.5, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.5304625199362042, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.5748792270531401, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.6008316008316008, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.6008316008316008, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.6727272727272727, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.6949817774039809, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.6949817774039809, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.6949817774039809, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.6257309941520468, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.6008316008316008, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.5477726574500767, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.6727272727272727, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.7327437975927291, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.7732793522267206, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.7374358974358974, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.6362737830491723, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.5508771929824561, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.5733333333333333, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.6156156156156156, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.4231177094379639, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.5195195195195195, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.578021978021978, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.5, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.5, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.5, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.5, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.5, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.5, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.4861111111111111, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.4861111111111111, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.5218253968253969, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.5396825396825397, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.5119047619047619, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.6190476190476191, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.623015873015873, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.6805555555555556, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.6805555555555556, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.6805555555555556, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.6984126984126984, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.6984126984126984, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.6944444444444444, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.6904761904761905, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.6726190476190476, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.6150793650793651, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.5932539682539683, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.5714285714285714, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.5714285714285714, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.5714285714285714, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.5714285714285714, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.5892857142857143, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.6111111111111112, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.628968253968254, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.628968253968254, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.6825396825396826, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.7003968253968254, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.7003968253968254, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.7003968253968254, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.6468253968253969, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.628968253968254, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.5932539682539683, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.6825396825396826, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.7361111111111112, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.7698412698412699, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.7341269841269842, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.6369047619047619, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.5833333333333333, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.5753968253968254, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.6150793650793651, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.5119047619047619, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.5595238095238095, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.5892857142857143, "id_best": 40, "lr_best": 0.0042, "wd_best": 0.05, "train/loss_best": 0.5937559509277344, "validation/loss_best": 0.5614181756973267, "validation/acc_best": 0.78125, "validation/f1_best": 0.7732793522267206, "validation/bacc_best": 0.7698412698412699} +{"epoch": 2, "train/lr": 0.00014999999999999988, "train/loss": 0.6130873456597328, "train/grad": 0.367012050151825, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.67632080078125, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.6751171875, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.673369140625, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.671806640625, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.6702783203125, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.6685302734375, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.6667236328125, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.66493896484375, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.6628955078125, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.66096923828125, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.659324951171875, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.6569775390625, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.655035400390625, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.652435302734375, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.65014404296875, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.648001708984375, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.6452716064453125, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.6422216796875, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.638883056640625, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.6358551025390625, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.6317132568359375, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.6271182250976562, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.6229769897460937, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.6224520874023437, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.6256637573242188, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.6283056640625, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.6291714477539062, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.6302908325195312, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.6313253784179688, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.6312879943847656, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.6295539855957031, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.6269734191894532, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.6219966125488281, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.6164790344238281, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.6095518493652343, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.6033039855957031, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.5896773719787598, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.5672615432739258, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.5272453141212463, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.47994387209415434, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.4878751340508461, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.47857855051755904, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.4417559938132763, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.6165030451118946, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.3683984971046448, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.5299631649255753, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.7241300110518932, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.6352268858253955, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.4314565293490887, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.03431406425544992, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.03426294329110533, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.034229049035348, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.03418266305001452, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.03415834878804162, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.03414079094072804, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.034132576892152426, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.03414711067918688, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.03419162716483697, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.03427015673602, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.03435327081475407, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.03451541810994968, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.034701689621433614, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.03494709534803406, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.03517848078161478, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.03539793143281713, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.03561955666635185, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.035768674868158996, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.03589582551503554, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.03607082032132894, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.03645308604929596, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.03696874476969242, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.037747473712079226, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.03855466706678271, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.03886474426137283, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0386289514019154, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.03807038915809244, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.03755126768257469, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.03684713348047808, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.035863458393141624, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.03478860167786479, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0337723569595255, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.032192307498771694, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.030472735362127423, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.028344757694285364, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.02715068231103942, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.027664819085039198, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.028254613615572452, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.030656213271431625, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.03468917978927493, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.052300333998864516, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.05144630831782706, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0482282480946742, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.06726867544464767, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.05314443645387655, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0802701707277447, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.11305700559983961, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0848662538593635, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.08155892338400009, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.66459059715271, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.662330150604248, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.6591117978096008, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.6563656330108643, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.6538071036338806, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.6510401964187622, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.6483041048049927, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.6459014415740967, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.6432345509529114, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.641056478023529, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.6393271088600159, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.6377450823783875, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.636788010597229, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.6347541809082031, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.6310802102088928, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.6251174211502075, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.616145133972168, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.6076816320419312, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.6042865514755249, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.6064108610153198, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.6119813919067383, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.614278256893158, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.6071833372116089, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.5968028903007507, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.5917000770568848, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.5927996039390564, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.5940386652946472, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.5930311679840088, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.591273844242096, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.5900310277938843, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.5888296961784363, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.5926117300987244, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.6108721494674683, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.6384587287902832, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.656369686126709, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.6539736390113831, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.7023105621337891, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.8217129111289978, "validation/loss_038_lr9.8e+00_wd1.0e+00": 1.1385554075241089, "validation/loss_039_lr1.2e+01_wd1.0e+00": 1.6859886646270752, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.0179476737976074, "validation/loss_041_lr1.6e+01_wd1.0e+00": 1.8869576454162598, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.1016595363616943, "validation/loss_043_lr2.2e+01_wd1.0e+00": 1.7196162939071655, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.354656219482422, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.5750174522399902, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.5223453044891357, "validation/loss_047_lr4.3e+01_wd1.0e+00": 5.192884922027588, "validation/loss_048_lr5.0e+01_wd1.0e+00": 2.8911843299865723, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.5625, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.5625, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.546875, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.546875, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.546875, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.5625, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.59375, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.59375, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.59375, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.59375, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.59375, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.59375, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.59375, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.609375, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.640625, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.65625, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.71875, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.765625, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.75, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.6875, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.671875, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.65625, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.65625, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.6875, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.734375, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.78125, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.765625, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.765625, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.78125, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.765625, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.75, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.71875, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.71875, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.71875, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.6875, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.6875, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.703125, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.671875, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.625, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.578125, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.578125, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.65625, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.59375, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.59375, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.546875, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.59375, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.546875, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.609375, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.609375, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.36, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.36, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.35353535353535354, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.35353535353535354, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.35353535353535354, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.3904761904761905, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.4583333333333333, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.4583333333333333, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.4583333333333333, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.4583333333333333, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.4583333333333333, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.4583333333333333, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.4583333333333333, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.48963317384370014, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.5477726574500767, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.5883040935672514, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.6883116883116883, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.7520020666494446, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.746031746031746, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.6862745098039216, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.6717948717948719, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.6559139784946236, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.6559139784946236, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.6847290640394088, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.7262893081761006, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.7702564102564102, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.747832939322301, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.747832939322301, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.7666666666666666, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.7555385790679909, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.7408906882591093, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.7117117117117118, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.7142857142857143, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.716256157635468, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.6862745098039216, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.6862745098039216, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.6903488668194551, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.640160642570281, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.6, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.577195987276731, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.578021978021978, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.6476476476476476, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.59375, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.5933528836754643, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.5458771715194519, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.5588547189819725, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.5440923605993613, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.48963317384370014, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.5974842767295597, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.5, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.5, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.4861111111111111, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.4861111111111111, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.4861111111111111, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.503968253968254, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.5396825396825397, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.5396825396825397, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.5396825396825397, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.5396825396825397, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.5396825396825397, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.5396825396825397, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.5396825396825397, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.5575396825396826, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.5932539682539683, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.6150793650793651, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.6904761904761905, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.748015873015873, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.746031746031746, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.6904761904761905, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.6845238095238095, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.6706349206349207, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.6706349206349207, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.6865079365079365, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.7242063492063493, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.7658730158730158, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.7440476190476191, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.7440476190476191, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.7619047619047619, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.751984126984127, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.7380952380952381, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.7103174603174603, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.7142857142857143, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.7182539682539683, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.6904761904761905, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.6904761904761905, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.6884920634920635, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.6448412698412699, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.6031746031746031, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.5932539682539683, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.5853174603174603, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.6468253968253967, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.6031746031746033, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.6071428571428572, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.5615079365079365, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.5674603174603174, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.5654761904761905, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.5575396825396826, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.5972222222222222, "id_best": 25, "lr_best": 0.00035999999999999997, "wd_best": 0.05, "train/loss_best": 0.6283056640625, "validation/loss_best": 0.5927996039390564, "validation/acc_best": 0.78125, "validation/f1_best": 0.7702564102564102, "validation/bacc_best": 0.7658730158730158} +{"epoch": 3, "train/lr": 0.0002100600600600602, "train/loss": 0.5612490451335908, "train/grad": 0.43832813039422036, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.66377685546875, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.6619677734375, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.659482421875, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.657177734375, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.65517578125, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.65270751953125, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.65006591796875, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.64743896484375, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.64420166015625, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.64098388671875, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.638121337890625, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.634071044921875, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.630618896484375, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.626070556640625, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.62181396484375, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.6180712890625, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.613658447265625, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.6098199462890626, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.6066265869140625, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.6037762451171875, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.600654296875, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.598359375, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.5951153564453125, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.5891110229492188, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.58126953125, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.5745639038085938, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.5708613586425781, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.5681947326660156, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.5650650024414062, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.5621755981445312, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.5604599380493164, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.5597772979736328, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.5479635047912598, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.5229908084869385, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.46205127954483033, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.40822243094444277, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.3051373213529587, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.17968271687626838, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.16381291225552558, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.2183607941865921, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.0473445925116539, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.18278573378920554, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.290105289965868, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.6380103407800197, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.42640876725316046, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.3735580450296402, "train/loss_046_lr3.6e+01_wd1.0e+00": 1.0534697405993938, "train/loss_047_lr4.3e+01_wd1.0e+00": 1.3193253947794437, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.7007399351894855, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.03259921220364049, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.03254716194467619, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.032481070877984165, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.03242892612237483, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.03240315716946498, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.03237929762806743, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.03239305569091812, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.03241188270039856, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.03246042417595163, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.03252558642532676, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.032611333809327334, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.03276382775977254, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.032925814751069996, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.03313168490305543, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.03325863103149459, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.03329225971829146, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.03335022391518578, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.033569912682287394, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.03417834042105824, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.034910483246203515, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.03551558833103627, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.03591487898956984, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.03644530587363988, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.036534915957599876, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.03598205354530364, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.03521453181747347, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.03441475622355938, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.03332937702070922, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.031586065744049846, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.02964507761411369, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.028451576421502978, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.028320138293784113, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.028806002442725003, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.029737306777387857, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.03194390024989843, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.03398551852558739, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.03591750606836285, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.028889701402949868, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.035564972051943186, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.04203485110405381, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.013402842114210216, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.041530049073953704, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0698077003544563, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.11891504446720774, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0770756108407204, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.06455949546325392, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.14353414147476698, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.14614565245157793, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0375430763949862, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.6527386903762817, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.6498658657073975, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.6456310749053955, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.6420131325721741, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.6389457583427429, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.6354112029075623, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.6320141553878784, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.6289945244789124, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.6255645751953125, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.6226586699485779, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.6202993988990784, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.6176721453666687, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.6158958673477173, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.6136813759803772, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.6124603748321533, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.6116505861282349, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.6091780066490173, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.6024276614189148, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.5956276655197144, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.5916532874107361, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.5876883864402771, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.5870892405509949, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.5947239398956299, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.6064487099647522, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.6041252613067627, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.587713897228241, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.5797316431999207, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.5773485898971558, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.5748821496963501, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.5729082822799683, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.5776333808898926, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.5927190184593201, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.6613379716873169, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.7842239141464233, "validation/loss_034_lr5.1e+00_wd1.0e+00": 1.5363948345184326, "validation/loss_035_lr6.0e+00_wd1.0e+00": 1.9914716482162476, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.0624170303344727, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.662527084350586, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.3965799808502197, "validation/loss_039_lr1.2e+01_wd1.0e+00": 4.195179462432861, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.7185027599334717, "validation/loss_041_lr1.6e+01_wd1.0e+00": 5.422213554382324, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.186701774597168, "validation/loss_043_lr2.2e+01_wd1.0e+00": 4.848390579223633, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.0370595455169678, "validation/loss_045_lr3.1e+01_wd1.0e+00": 7.8542938232421875, "validation/loss_046_lr3.6e+01_wd1.0e+00": 12.393697738647461, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.6931473016738892, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.5625, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.640625, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.640625, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.6875, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.703125, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.734375, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.703125, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.734375, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.734375, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.734375, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.71875, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.6875, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.6875, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.6875, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.65625, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.671875, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.671875, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.6875, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.703125, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.703125, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.703125, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.6875, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.6875, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.640625, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.65625, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.71875, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.734375, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.71875, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.75, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.734375, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.71875, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.71875, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.671875, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.65625, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.640625, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.640625, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.6875, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.5625, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.5625, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.484375, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.5625, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.609375, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.625, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.609375, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.640625, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.59375, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.625, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.4375, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.4375, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.43929912390488113, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.5759147219821377, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.5972640218878249, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.6717948717948719, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.6903488668194551, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.7262893081761006, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.6971357409713574, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.7311588831233011, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.7311588831233011, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.7311588831233011, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.716256157635468, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.6862745098039216, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.6862745098039216, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.6862745098039216, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.6559139784946236, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.6717948717948719, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.6717948717948719, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.6871945259042034, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.7024712503058478, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.7024712503058478, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.7013018914271678, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.6862745098039216, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.6875, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.6398336187912894, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.6559139784946236, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.716256157635468, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.7290161892901619, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.7117117117117118, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.7374358974358974, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.7087014725568943, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.7046153846153846, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.7117117117117118, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.640160642570281, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.6267232237539766, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.5477726574500767, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.5759147219821377, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.6717948717948719, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.5586206896551724, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.5465587044534412, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.48323954000489355, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.5515515515515516, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.5866701110824076, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.625, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.5866701110824076, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.6133438402941949, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.59375, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.5636363636363637, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.30434782608695654, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.30434782608695654, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.5119047619047619, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.6011904761904762, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.6091269841269842, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.6706349206349207, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.6884920634920635, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.7242063492063493, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.6964285714285714, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.7321428571428572, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.7321428571428572, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.7321428571428572, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.7182539682539683, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.6904761904761905, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.6904761904761905, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.6904761904761905, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.6626984126984128, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.6845238095238095, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.6845238095238095, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.6944444444444444, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.7083333333333333, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.7083333333333333, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.7043650793650793, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.6904761904761905, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.6984126984126984, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.6567460317460317, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.6706349206349207, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.7182539682539683, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.7281746031746033, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.7103174603174603, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.7341269841269842, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.7083333333333333, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.7023809523809523, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.7103174603174603, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.6448412698412699, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.6309523809523809, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.5932539682539683, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.6011904761904762, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.6706349206349207, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.5595238095238095, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.5476190476190476, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.498015873015873, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.5515873015873016, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.5892857142857143, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.6349206349206349, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.5892857142857143, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.6170634920634921, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.6031746031746033, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.5873015873015872, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.5, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.5, "id_best": 28, "lr_best": 0.00057, "wd_best": 0.05, "train/loss_best": 0.5650650024414062, "validation/loss_best": 0.5748821496963501, "validation/acc_best": 0.75, "validation/f1_best": 0.7374358974358974, "validation/bacc_best": 0.7341269841269842} +{"epoch": 4, "train/lr": 0.0002701201201201201, "train/loss": 0.5288806396722794, "train/grad": 0.3913136901333928, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.65632080078125, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.654580078125, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.65222900390625, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.6503515625, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.64877197265625, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.64693603515625, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.645189208984375, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.6435791015625, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.641614990234375, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.639700927734375, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.6378515625, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.63485595703125, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.631488037109375, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.62510009765625, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.6179278564453125, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.6116302490234375, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.6060235595703125, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.60200439453125, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.5979794311523438, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.5921456909179688, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.5806161499023438, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.5719294738769531, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.5666259765625, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.5620217895507813, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.5576614379882813, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.5497000122070312, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.5393609619140625, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.5273015213012695, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.5058586025238037, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.47032336711883543, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.42363877192139626, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.3666236774623394, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.30400692015886305, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.13989480063319207, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.1003427304327488, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.014563621878623962, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.009473454654216767, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.000609644502401352, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.2550858667492866, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.07730686202645302, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.0002656520903110504, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.7442544561624527, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.4614817775785923, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.8951183462142944, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.8615639822185039, "train/loss_045_lr3.1e+01_wd1.0e+00": 1.0103313320875167, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.80009765625, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.69140625, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.69140625, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.03166580667719245, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.031645261894445866, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.03164509759284556, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.03165915240067989, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.03168589506763965, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.03174475664272904, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.03182296483311802, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.03193722989410162, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.03209704295732081, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.0322932849265635, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.0325254289386794, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.03297917343210429, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.03355623364448548, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.03453380578197539, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.03518076647538692, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.035464968285523354, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.03572066707536578, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.03608200706075877, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.036422119222115724, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.036084842439740895, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.03512938142288476, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.03445777787361294, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.03408482530154288, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.03374138065148145, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.03362212161533534, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0336284757591784, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.033113279663957655, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.03224131297320128, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.031050829393789173, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.030116886026225986, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.03178930424153805, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.030923669112380595, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.03159648586501135, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.017840824117010923, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.018894195133179893, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.004655274584547442, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0033247974037840322, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.00031466494888263694, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.05769041904512731, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.020798361514282535, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.00011391268742954707, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.1008400762322728, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.08444763604717885, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.16116793118029243, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.03971247690377822, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.04528706636888273, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.007938249036669731, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.6433085799217224, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.6402204036712646, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.6359284520149231, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.6322792768478394, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.6291388273239136, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.6254763007164001, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.621857762336731, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.6186609864234924, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.6151464581489563, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.6121253371238708, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.6093897819519043, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.6060295104980469, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.6032960414886475, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.6007647514343262, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.6011224389076233, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.6046179533004761, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.6049538254737854, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.5949423313140869, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.5817375183105469, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.578824520111084, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.5855651497840881, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.6062468886375427, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.6370477676391602, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.6400553584098816, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.6129319071769714, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.5886504650115967, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.5961207151412964, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.6194134950637817, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.6705031991004944, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.8423258662223816, "validation/loss_030_lr2.7e+00_wd1.0e+00": 1.0850543975830078, "validation/loss_031_lr3.1e+00_wd1.0e+00": 1.6957414150238037, "validation/loss_032_lr3.7e+00_wd1.0e+00": 1.95475172996521, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.4187850952148438, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.1525046825408936, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.6597330570220947, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.7793259620666504, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.8507065773010254, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.919238805770874, "validation/loss_039_lr1.2e+01_wd1.0e+00": 4.6961541175842285, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.736656427383423, "validation/loss_041_lr1.6e+01_wd1.0e+00": 5.913448333740234, "validation/loss_042_lr1.9e+01_wd1.0e+00": 5.616332054138184, "validation/loss_043_lr2.2e+01_wd1.0e+00": 10.532974243164062, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.6931473016738892, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.65625, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.6875, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.703125, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.703125, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.703125, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.703125, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.71875, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.75, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.765625, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.765625, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.765625, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.78125, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.78125, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.78125, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.75, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.71875, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.71875, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.75, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.78125, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.78125, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.71875, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.671875, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.65625, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.640625, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.703125, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.703125, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.65625, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.671875, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.640625, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.625, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.609375, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.609375, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.6875, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.625, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.59375, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.5625, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.609375, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.578125, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.671875, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.515625, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.546875, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.625, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.53125, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.640625, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.4375, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.4375, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.4375, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.4375, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.4375, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.6, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.64562569213732, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.6805883898082479, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.6805883898082479, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.6805883898082479, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.6805883898082479, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.7, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.7374358974358974, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.7520020666494446, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.7520020666494446, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.7520020666494446, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.7702564102564102, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.7666666666666666, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.7624602332979851, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.722943722943723, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.6727272727272727, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.6727272727272727, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.7165005537098561, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.7702564102564102, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.7732793522267206, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.6883116883116883, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.6127917026793431, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.5883040935672514, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.5759147219821377, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.6673050615595075, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.6858692844226298, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.6507936507936507, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.6698599852616065, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.6384180790960452, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.6, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.5974842767295597, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.5925642984466514, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.6717948717948719, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.6061538461538462, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.5588547189819725, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.5515515515515516, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.6014943960149439, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.5730170496664195, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.6698599852616065, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.48747093774218553, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.5413886829750432, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.6, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.5238095238095238, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.6362737830491723, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.30434782608695654, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.30434782608695654, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.30434782608695654, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.30434782608695654, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.30434782608695654, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.6190476190476191, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.6547619047619048, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.6805555555555556, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.6805555555555556, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.6805555555555556, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.6805555555555556, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.6984126984126984, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.7341269841269842, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.748015873015873, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.748015873015873, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.748015873015873, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.7658730158730158, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.7619047619047619, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.7579365079365079, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.7222222222222222, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.6825396825396826, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.6825396825396826, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.7182539682539683, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.7658730158730158, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.7698412698412699, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.6904761904761905, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.6329365079365079, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.6150793650793651, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.6011904761904762, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.6726190476190476, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.6845238095238095, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.6507936507936507, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.6726190476190477, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.6408730158730158, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.6031746031746031, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.5972222222222222, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.5932539682539683, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.6706349206349207, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.6071428571428572, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.5674603174603174, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.5515873015873016, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.6011904761904762, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.5734126984126984, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.6726190476190477, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.5535714285714286, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.5416666666666667, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.6031746031746031, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.5238095238095238, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.6369047619047619, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.5, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.5, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.5, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.5, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.5, "id_best": 19, "lr_best": 0.00013199999999999998, "wd_best": 0.05, "train/loss_best": 0.5921456909179688, "validation/loss_best": 0.578824520111084, "validation/acc_best": 0.78125, "validation/f1_best": 0.7732793522267206, "validation/bacc_best": 0.7698412698412699} +{"epoch": 5, "train/lr": 0.00029891323817685334, "train/loss": 0.4681116585433483, "train/grad": 0.2927334365621209, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.65063720703125, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.64826904296875, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.64470458984375, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.64152099609375, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.6388134765625, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.635357666015625, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.63184814453125, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.6284228515625, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.624464111328125, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.620733642578125, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.61766845703125, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.613494873046875, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.6102923583984375, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.6063336181640625, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.6035980224609375, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.6019677734375, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.600797119140625, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.5995841979980469, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.596861572265625, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.5881596374511718, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.5748187255859375, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.5589109802246094, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.5342913436889648, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.518524169921875, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.5070577812194824, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.48758727073669433, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.46386834621429446, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.43709566473960876, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.36855556041002274, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.21176958665251733, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.09938913390040398, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.041026446223258975, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.026252725273370744, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.0007604099810123444, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.043308908492326735, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.00039131730794906617, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.0002762565016746521, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.00023754924535751343, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.06541605040431023, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.35840516835451125, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.00017791450023651122, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.050106611549854276, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.7272471743822098, "train/loss_043_lr2.2e+01_wd1.0e+00": 1.0014360316097737, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.69140625, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.69140625, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.69140625, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.69140625, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.69140625, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.03533526931889355, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.03533542610704899, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.035365157518535854, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.03541417732834816, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.03547332084737718, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.03558292684145272, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.0357109926873818, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.03588733927812427, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.03614463495556265, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.036448917835950854, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.03675785595085472, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.037222048249095675, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.03765046332962811, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.038295589461922644, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.03889275803230703, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.039389906409196554, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.040067001832649114, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.0410255243210122, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.04212528608273715, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.04210717403097078, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.04224202431272715, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.04184739576652646, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.040762784788385034, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.04012017470318824, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.040076778237707916, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.03926622837781906, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.03886539564467967, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.039691317472606895, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.04118522814475, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.028204246262903326, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.01647041471936973, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.010409331794508035, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.005719597381284984, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.00023982887010788546, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.010125850855729368, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.00013524667809178937, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.00011032219517801423, "train/grad_037_lr8.3e+00_wd1.0e+00": 9.730271997341334e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.018689663911852908, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.048018323536241976, "train/grad_040_lr1.4e+01_wd1.0e+00": 7.43758788530613e-05, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.017929093864913453, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.04927605789205652, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.04989772703687871, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.6381406188011169, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.6353630423545837, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.6316049098968506, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.6285906434059143, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.6260486841201782, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.6231251358985901, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.6204020380973816, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.6177826523780823, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.6151026487350464, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.6128163933753967, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.6108482480049133, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.6090332865715027, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.6075242757797241, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.6046197414398193, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.6014583110809326, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.5983083844184875, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.5954011082649231, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.5938011407852173, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.5940737128257751, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.5918301343917847, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.5859155654907227, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.5967345237731934, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.5999794006347656, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.6108205318450928, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.6292459964752197, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.6699199080467224, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.7348062992095947, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.8629670739173889, "validation/loss_028_lr1.9e+00_wd1.0e+00": 1.396396279335022, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.089722156524658, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.311063766479492, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.7510170936584473, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.8606767654418945, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.6916286945343018, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.806519031524658, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.841982841491699, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.8721749782562256, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.8566508293151855, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.778499126434326, "validation/loss_039_lr1.2e+01_wd1.0e+00": 5.1944756507873535, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.720184326171875, "validation/loss_041_lr1.6e+01_wd1.0e+00": 8.398651123046875, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.6931473016738892, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.625, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.671875, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.703125, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.71875, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.71875, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.71875, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.734375, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.734375, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.734375, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.734375, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.734375, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.75, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.765625, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.765625, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.765625, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.765625, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.734375, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.71875, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.703125, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.703125, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.71875, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.703125, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.71875, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.734375, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.703125, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.6875, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.640625, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.578125, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.5625, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.609375, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.609375, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.609375, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.609375, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.625, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.640625, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.5625, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.609375, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.578125, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.671875, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.609375, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.546875, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.609375, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.4375, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.4375, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.4375, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.4375, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.4375, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.4375, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.4375, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.5508771929824561, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.6232127838519764, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.6744310575635877, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.6883116883116883, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.6883116883116883, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.6883116883116883, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.7087014725568943, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.7087014725568943, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.7087014725568943, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.7087014725568943, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.7087014725568943, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.722943722943723, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.7429718875502007, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.7429718875502007, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.747832939322301, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.7555385790679909, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.7290161892901619, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.716256157635468, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.7013018914271678, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.7013018914271678, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.7117117117117118, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.6940880503144654, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.7117117117117118, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.7290161892901619, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.6940880503144654, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.6796796796796797, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.6362737830491723, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.5652830188679245, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.5249204665959704, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.5622435020519836, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.5866701110824076, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.5974842767295597, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.5925642984466514, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.6061538461538462, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.6133438402941949, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.5515515515515516, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.6014943960149439, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.5730170496664195, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.640160642570281, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.5925642984466514, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.5413886829750432, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.6014943960149439, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.30434782608695654, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.30434782608695654, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.30434782608695654, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.30434782608695654, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.30434782608695654, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.30434782608695654, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.30434782608695654, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.5833333333333333, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.6369047619047619, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.6765873015873016, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.6904761904761905, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.6904761904761905, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.6904761904761905, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.7083333333333333, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.7083333333333333, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.7083333333333333, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.7083333333333333, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.7083333333333333, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.7222222222222222, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.7400793650793651, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.7400793650793651, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.7440476190476191, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.751984126984127, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.7281746031746033, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.7182539682539683, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.7043650793650793, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.7043650793650793, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.7103174603174603, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.6924603174603174, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.7103174603174603, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.7281746031746033, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.6924603174603174, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.6785714285714286, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.6369047619047619, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.5654761904761905, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.5357142857142857, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.5773809523809524, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.5892857142857143, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.5972222222222222, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.5932539682539683, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.6071428571428572, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.6170634920634921, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.5515873015873016, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.6011904761904762, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.5734126984126984, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.6448412698412699, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.5932539682539683, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.5416666666666667, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.6011904761904762, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.5, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.5, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.5, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.5, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.5, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.5, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.5, "id_best": 15, "lr_best": 6.9e-05, "wd_best": 0.05, "train/loss_best": 0.6019677734375, "validation/loss_best": 0.5983083844184875, "validation/acc_best": 0.765625, "validation/f1_best": 0.7555385790679909, "validation/bacc_best": 0.751984126984127} +{"epoch": 6, "train/lr": 0.0002924170901991409, "train/loss": 0.41723824948072435, "train/grad": 0.19841830922290682, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.645029296875, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.64208740234375, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.63784423828125, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.634205322265625, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.6308251953125, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.626781005859375, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.622838134765625, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.61904541015625, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.61470947265625, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.6103912353515625, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.60666748046875, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.6014031982421875, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.5966485595703125, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.590914306640625, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.5858694458007813, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.5806182861328125, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.5732421875, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.5639495849609375, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.5536248779296875, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.5449456787109375, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.5333249664306641, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.518479118347168, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.5053071975708008, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.4960834503173828, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.4761712193489075, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.41488919079303743, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.3040214587748051, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.2075873339176178, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.05569460719823837, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.004303224682807923, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0019217804074287415, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.0008855253458023071, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.0007368721067905426, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.0003894193470478058, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.00016465887427330017, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.0002723422646522522, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.00020894870162010192, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.00019245445728302001, "train/loss_038_lr9.8e+00_wd1.0e+00": 5.2340924739837646e-05, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.002258492261171341, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.00017686069011688233, "train/loss_041_lr1.6e+01_wd1.0e+00": 6.915897130966187e-05, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.69140625, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.69140625, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.69140625, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.69140625, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.69140625, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.69140625, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.69140625, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.030183550459332763, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.03022158318432048, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.030319189107976853, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.030428911070339383, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.03053921280661598, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.030716797050554304, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.030920042102225126, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.031155733074992895, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.031480067069642244, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.031806537988595666, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.032136171986348924, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.03262550307670608, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.03306648936588317, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.03360791092272848, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.034060649313032626, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.03458945308811963, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.03541351646184921, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.03595325163565576, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.03600720613729209, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.036271536350250246, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.03683301183860749, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.037714732172898946, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.04050627020653337, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.04235788213089108, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.04246843660250306, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.04176820616237819, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.03828528087818995, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.03303382606827654, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.013208162402588642, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.001298979037310346, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0005452132299978985, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0002794872208869492, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.00023335865476838082, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.00012195827870527865, "train/grad_034_lr5.1e+00_wd1.0e+00": 8.084231187012847e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 8.799925795301533e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 7.392709718260448e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 7.251131087286922e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 3.889232391833808e-05, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.000864703108041085, "train/grad_040_lr1.4e+01_wd1.0e+00": 6.475100294665027e-05, "train/grad_041_lr1.6e+01_wd1.0e+00": 6.213773592655624e-05, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.6318765878677368, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.6288858652114868, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.6247051358222961, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.6212709546089172, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.6185674667358398, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.6152970790863037, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.6124542355537415, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.6097469329833984, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.6071860790252686, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.6052124500274658, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.6035131216049194, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.6008256673812866, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.5978320837020874, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.5943942070007324, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.5920419096946716, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.5900861620903015, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.5878245830535889, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.587415874004364, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.5961292386054993, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.616780161857605, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.6229697465896606, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.6098884344100952, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.615226686000824, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.6303268074989319, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.6644659638404846, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.7907816171646118, "validation/loss_026_lr1.4e+00_wd1.0e+00": 1.170762538909912, "validation/loss_027_lr1.6e+00_wd1.0e+00": 1.6263279914855957, "validation/loss_028_lr1.9e+00_wd1.0e+00": 1.987256646156311, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.3261120319366455, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.6010310649871826, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.922992467880249, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.0757970809936523, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.804762363433838, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.781658887863159, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.949909210205078, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.9170188903808594, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.8447823524475098, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.629915475845337, "validation/loss_039_lr1.2e+01_wd1.0e+00": 4.27006196975708, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.7099430561065674, "validation/loss_041_lr1.6e+01_wd1.0e+00": 7.323831081390381, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.6931473016738892, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.703125, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.703125, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.703125, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.734375, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.75, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.75, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.75, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.75, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.78125, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.765625, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.75, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.78125, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.765625, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.75, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.734375, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.734375, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.71875, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.734375, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.734375, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.703125, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.671875, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.703125, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.703125, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.6875, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.671875, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.625, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.5625, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.578125, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.578125, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.625, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.625, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.625, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.609375, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.625, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.65625, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.578125, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.609375, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.578125, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.671875, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.625, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.546875, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.609375, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.4375, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.4375, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.4375, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.4375, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.4375, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.4375, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.4375, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.6805883898082479, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.6805883898082479, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.6805883898082479, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.7189356755360372, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.7374358974358974, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.7408906882591093, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.7408906882591093, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.7408906882591093, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.7702564102564102, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.7520020666494446, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.7333333333333334, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.7666666666666666, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.7555385790679909, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.7437437437437437, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.7290161892901619, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.7290161892901619, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.7117117117117118, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.7262893081761006, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.722943722943723, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.6673050615595075, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.640160642570281, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.6940880503144654, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.6940880503144654, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.6796796796796797, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.6652552926525529, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.6156156156156156, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.5405128205128206, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.5599694423223835, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.5536037199690003, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.6, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.6, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.611336032388664, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.5925642984466514, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.6061538461538462, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.6333333333333333, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.5652830188679245, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.6014943960149439, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.5730170496664195, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.6322845417236662, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.6061538461538462, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.5413886829750432, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.6014943960149439, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.30434782608695654, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.30434782608695654, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.30434782608695654, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.30434782608695654, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.30434782608695654, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.30434782608695654, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.30434782608695654, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.6805555555555556, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.6805555555555556, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.6805555555555556, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.7162698412698413, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.7341269841269842, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.7380952380952381, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.7380952380952381, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.7380952380952381, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.7658730158730158, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.748015873015873, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.7301587301587301, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.7619047619047619, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.751984126984127, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.7420634920634921, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.7281746031746033, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.7281746031746033, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.7103174603174603, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.7242063492063493, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.7202380952380952, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.6726190476190476, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.6448412698412699, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.6924603174603174, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.6924603174603174, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.6785714285714286, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.6646825396825397, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.6150793650793651, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.5436507936507936, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.5615079365079365, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.5575396825396826, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.6031746031746031, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.6031746031746031, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.6111111111111112, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.5932539682539683, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.6071428571428572, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.6349206349206349, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.5654761904761905, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.6011904761904762, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.5734126984126984, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.6408730158730158, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.6071428571428572, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.5416666666666667, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.6011904761904762, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.5, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.5, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.5, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.5, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.5, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.5, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.5, "id_best": 8, "lr_best": 2.2199999999999998e-05, "wd_best": 0.05, "train/loss_best": 0.61470947265625, "validation/loss_best": 0.6071860790252686, "validation/acc_best": 0.78125, "validation/f1_best": 0.7702564102564102, "validation/bacc_best": 0.7658730158730158} +{"epoch": 7, "train/lr": 0.00027969249556793234, "train/loss": 0.3933169399946928, "train/grad": 0.20035412166267633, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.638555908203125, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.635843505859375, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.6319384765625, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.6284326171875, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.625313720703125, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.621497802734375, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.61761962890625, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.613604736328125, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.608883056640625, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.60434326171875, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.600167236328125, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.5941375732421875, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.588414306640625, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.5801055908203125, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.5717111206054688, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.5634567260742187, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.5540899658203124, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.5451830291748047, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.5349434661865234, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.5217288970947266, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.5045426177978516, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.487228479385376, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.4640221166610718, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.429038724899292, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.36367169678211214, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.21273984313011168, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.07050827711820602, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.013668053895235061, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0030588743090629576, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0011196894943714141, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0008355021476745605, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.0005163191258907318, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.00046042010188102723, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.0002610884606838226, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.00014761194586753845, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.00021655067801475524, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.00016935601830482484, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.0001651027798652649, "train/loss_038_lr9.8e+00_wd1.0e+00": 5.2551478147506715e-05, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.7707964181900025e-05, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.00015903741121292114, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.00010644495487213134, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.69140625, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.69140625, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.69140625, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.69140625, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.69140625, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.69140625, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.69140625, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.03352247566916049, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.03348724972456694, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.033452251232229176, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.0334344650618732, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.03343845174182206, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.033457114682532846, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.03348305927123874, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.0335396661516279, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.03363858534488827, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.033766487990505994, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.0339428543811664, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.034240527597721664, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.034554091119207445, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.034949348166119304, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.03532339120283723, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.03575176335405558, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.03650237977039069, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.037322195465676486, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.03805944419465959, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.03896302632521838, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.04043026709463447, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.04250714994501323, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.045615213154815135, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.045472484389320014, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.042614019634202124, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.034804433635436, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.01706086808000691, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0037676181719871237, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0009548143579741009, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0003409869263123255, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0002566949623724213, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.00016454699432870258, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.00015008856516942614, "train/grad_033_lr4.3e+00_wd1.0e+00": 8.588311358835199e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 6.094403934412185e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 6.848897757663508e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 6.196597461894271e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 6.064089561732544e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 4.099248318091497e-05, "train/grad_039_lr1.2e+01_wd1.0e+00": 2.213797639869064e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 5.860877824488853e-05, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.00010821286796023344, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.6280868053436279, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.6251826286315918, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.6211628913879395, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.6178156137466431, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.6150126457214355, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.6115813255310059, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.6082876920700073, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.605083167552948, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.6011929512023926, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.59787917137146, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.5951718688011169, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.5913683176040649, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.5880088806152344, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.5858275890350342, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.5873997211456299, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.5882248878479004, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.5868260860443115, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.5814780592918396, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.5734338760375977, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.5704469084739685, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.5743274092674255, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.5820215940475464, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.6022143363952637, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.677802324295044, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.8388876914978027, "validation/loss_025_lr1.2e+00_wd1.0e+00": 1.2728173732757568, "validation/loss_026_lr1.4e+00_wd1.0e+00": 1.837193250656128, "validation/loss_027_lr1.6e+00_wd1.0e+00": 1.9979207515716553, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.199342727661133, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.4729580879211426, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.7425601482391357, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.025157928466797, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.187041759490967, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.8759095668792725, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.7724249362945557, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.0342841148376465, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.9512248039245605, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.8296966552734375, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.418745517730713, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.8946027755737305, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.713374376296997, "validation/loss_041_lr1.6e+01_wd1.0e+00": 6.559974193572998, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.6931473016738892, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.71875, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.71875, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.71875, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.734375, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.75, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.75, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.78125, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.78125, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.765625, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.765625, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.765625, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.765625, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.765625, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.78125, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.765625, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.75, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.75, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.734375, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.6875, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.71875, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.6875, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.71875, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.6875, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.640625, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.609375, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.5625, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.578125, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.5625, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.546875, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.640625, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.609375, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.609375, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.609375, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.625, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.65625, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.578125, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.625, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.578125, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.6875, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.640625, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.578125, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.59375, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.4375, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.4375, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.4375, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.4375, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.4375, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.4375, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.4375, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.694591728525981, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.694591728525981, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.694591728525981, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.7142106645652745, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.7333333333333334, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.7333333333333334, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.7702564102564102, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.7702564102564102, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.7520020666494446, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.7555385790679909, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.7584905660377359, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.7584905660377359, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.7584905660377359, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.7666666666666666, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.747832939322301, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.7285259809119831, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.7285259809119831, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.7087014725568943, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.6761133603238867, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.7117117117117118, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.6717948717948719, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.708502024291498, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.6796796796796797, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.6398336187912894, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.6092796092796093, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.5515515515515516, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.5652830188679245, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.5515515515515516, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.5273745861981156, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.6133438402941949, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.5866701110824076, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.5925642984466514, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.5925642984466514, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.6061538461538462, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.6333333333333333, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.5652830188679245, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.6156156156156156, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.5730170496664195, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.6536796536796536, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.6251591545709193, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.5730170496664195, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.5835835835835836, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.30434782608695654, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.30434782608695654, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.30434782608695654, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.30434782608695654, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.30434782608695654, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.30434782608695654, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.30434782608695654, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.6944444444444444, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.6944444444444444, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.6944444444444444, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.7123015873015872, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.7301587301587301, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.7301587301587301, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.7658730158730158, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.7658730158730158, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.748015873015873, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.751984126984127, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.7559523809523809, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.7559523809523809, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.7559523809523809, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.7619047619047619, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.7440476190476191, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.7261904761904762, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.7261904761904762, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.7083333333333333, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.6746031746031746, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.7103174603174603, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.6706349206349207, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.7063492063492063, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.6785714285714286, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.6448412698412699, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.6170634920634921, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.5515873015873016, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.5654761904761905, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.5515873015873016, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.5297619047619048, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.6170634920634921, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.5892857142857143, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.5932539682539683, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.5932539682539683, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.6071428571428572, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.6349206349206349, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.5654761904761905, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.6150793650793651, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.5734126984126984, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.6587301587301587, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.625, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.5734126984126984, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.5833333333333333, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.5, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.5, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.5, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.5, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.5, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.5, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.5, "id_best": 6, "lr_best": 1.5899999999999997e-05, "wd_best": 0.05, "train/loss_best": 0.61761962890625, "validation/loss_best": 0.6082876920700073, "validation/acc_best": 0.78125, "validation/f1_best": 0.7702564102564102, "validation/bacc_best": 0.7658730158730158} +{"epoch": 8, "train/lr": 0.0002612959497061927, "train/loss": 0.3762555231899023, "train/grad": 0.20042542565613986, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.635469970703125, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.63240966796875, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.62779541015625, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.623717041015625, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.620157470703125, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.61564697265625, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.61096923828125, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.6063519287109375, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.60076171875, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.59521484375, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.590257568359375, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.5828887939453125, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.5758673095703125, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.5658883666992187, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.5565567016601562, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.5482107543945313, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.5390205383300781, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.53007568359375, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.520640869140625, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.5085112762451172, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.4862569522857666, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.449316189289093, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.39798649072647097, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.3204372897744179, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.19803363785147668, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.04306602105498314, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.007235568910837173, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0033044935762882232, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.00154681533575058, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0006945659220218658, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0005178034305572509, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.00036079272627830505, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.00032139331102371216, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.0001987329125404358, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.00011965319514274597, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.00017442584037780762, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.0001413843035697937, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.00014613091945648194, "train/loss_038_lr9.8e+00_wd1.0e+00": 6.375625729560852e-05, "train/loss_039_lr1.2e+01_wd1.0e+00": 4.232257604598999e-05, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.00015174224972724915, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.00014900073409080506, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.69140625, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.69140625, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.69140625, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.69140625, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.69140625, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.69140625, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.69140625, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.03305758476955816, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.032997534091118726, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.032919888203032314, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.032886600717902184, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.032884767057839784, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.032906395525205884, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.03296344271162525, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.03306848012143746, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.03325342860771343, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.03349337297258899, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.033763755867257716, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.034194327616132794, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.03465719901025295, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.0352680255100131, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.035923683010041715, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.036581656131893396, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.0375741054629907, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.038553205826319756, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.03995522784534842, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.04217375099658966, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.045062564495019615, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.04705735408701003, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.048073799922131004, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.045946029755286874, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.04235580361448228, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.016310492430930027, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.002365425359021174, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0009682583410176448, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0004542476582719246, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.000208818830542441, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.00016706351798347895, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.00011787884277509874, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.00010927869438091875, "train/grad_033_lr4.3e+00_wd1.0e+00": 6.573105219104036e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 5.3218541897877006e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 5.752725257025304e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 5.3849716018703474e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 5.221152358444669e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 4.6943514172888004e-05, "train/grad_039_lr1.2e+01_wd1.0e+00": 3.010824502723608e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 5.263162100163754e-05, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.00011299880925378148, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.6245304346084595, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.6215444803237915, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.6174959540367126, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.6144117712974548, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.6115281581878662, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.608324408531189, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.6053463220596313, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.602260947227478, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.5992172360420227, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.5960162281990051, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.5934880971908569, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.5897315740585327, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.5866488218307495, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.5858994126319885, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.5916965007781982, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.5975629091262817, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.5982088446617126, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.5975072979927063, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.6041792035102844, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.611620306968689, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.6163309216499329, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.6275381445884705, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.6856718063354492, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.8854013681411743, "validation/loss_024_lr1.0e+00_wd1.0e+00": 1.219866156578064, "validation/loss_025_lr1.2e+00_wd1.0e+00": 1.768724799156189, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.1058144569396973, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.195639133453369, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.348947763442993, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.577754497528076, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.8290464878082275, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.087517738342285, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.2509841918945312, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.926281213760376, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.7616612911224365, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.0917789936065674, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.979846954345703, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.8255372047424316, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.24576997756958, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.5990207195281982, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.723879337310791, "validation/loss_041_lr1.6e+01_wd1.0e+00": 6.006134986877441, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.6931473016738892, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.703125, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.71875, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.734375, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.75, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.765625, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.75, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.75, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.75, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.75, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.75, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.78125, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.75, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.75, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.71875, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.6875, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.6875, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.6875, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.71875, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.703125, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.703125, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.71875, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.71875, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.65625, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.65625, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.59375, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.53125, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.546875, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.578125, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.5625, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.640625, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.625, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.609375, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.609375, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.625, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.65625, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.578125, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.609375, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.578125, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.6875, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.640625, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.609375, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.609375, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.4375, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.4375, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.4375, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.4375, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.4375, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.4375, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.4375, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.6805883898082479, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.7, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.7189356755360372, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.7374358974358974, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.7555385790679909, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.7408906882591093, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.7408906882591093, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.7408906882591093, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.7408906882591093, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.7408906882591093, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.7732793522267206, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.7437437437437437, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.7437437437437437, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.716256157635468, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.6862745098039216, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.6871945259042034, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.6871945259042034, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.7176470588235294, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.7024712503058478, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.7024712503058478, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.716256157635468, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.7142857142857143, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.6507936507936507, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.6333333333333333, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.5733333333333333, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.5195195195195195, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.537733499377335, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.5652830188679245, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.5405128205128206, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.6133438402941949, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.6061538461538462, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.5925642984466514, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.5925642984466514, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.6, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.6333333333333333, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.5652830188679245, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.6014943960149439, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.5730170496664195, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.6536796536796536, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.6296855345911949, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.6014943960149439, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.5974842767295597, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.30434782608695654, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.30434782608695654, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.30434782608695654, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.30434782608695654, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.30434782608695654, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.30434782608695654, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.30434782608695654, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.6805555555555556, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.6984126984126984, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.7162698412698413, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.7341269841269842, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.751984126984127, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.7380952380952381, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.7380952380952381, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.7380952380952381, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.7380952380952381, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.7380952380952381, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.7698412698412699, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.7420634920634921, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.7420634920634921, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.7182539682539683, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.6904761904761905, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.6944444444444444, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.6944444444444444, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.7222222222222222, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.7083333333333333, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.7083333333333333, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.7182539682539683, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.7142857142857143, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.6507936507936507, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.6349206349206349, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.5753968253968254, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.5198412698412699, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.5376984126984128, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.5654761904761905, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.5436507936507936, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.6170634920634921, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.6071428571428572, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.5932539682539683, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.5932539682539683, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.6031746031746031, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.6349206349206349, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.5654761904761905, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.6011904761904762, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.5734126984126984, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.6587301587301587, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.628968253968254, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.6011904761904762, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.5972222222222222, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.5, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.5, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.5, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.5, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.5, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.5, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.5, "id_best": 10, "lr_best": 2.9999999999999997e-05, "wd_best": 0.05, "train/loss_best": 0.590257568359375, "validation/loss_best": 0.5934880971908569, "validation/acc_best": 0.78125, "validation/f1_best": 0.7732793522267206, "validation/bacc_best": 0.7698412698412699} +{"epoch": 9, "train/lr": 0.00023803200426111704, "train/loss": 0.36996912755072114, "train/grad": 0.19662342477589845, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.6414794921875, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.638367919921875, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.633951416015625, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.629862060546875, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.6264892578125, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.622265625, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.61802734375, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.613687744140625, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.608297119140625, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.6029718017578125, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.5976776123046875, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.589761962890625, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.5816671752929687, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.5700543212890625, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.5594891357421875, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.5491224670410156, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.535712890625, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.5213148880004883, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.5053427124023437, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.48643184661865235, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.45861981868743895, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.42282580614089965, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.35062179654836656, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.22625744819641114, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.07905293464660644, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.010708416551351548, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.0032790158689022064, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0017544172704219818, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0009961278736591338, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0004903128743171691, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0003928057849407196, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.00028969705104827883, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.0002501025795936584, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.00017251446843147278, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.0001220753788948059, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.00015296220779418947, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.00013094723224639892, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.00012954369187355042, "train/loss_038_lr9.8e+00_wd1.0e+00": 6.732150912284851e-05, "train/loss_039_lr1.2e+01_wd1.0e+00": 6.15699589252472e-05, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.00013946130871772766, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.0001539541780948639, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.69140625, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.69140625, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.69140625, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.69140625, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.69140625, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.69140625, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.69140625, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.03249182135798037, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.03249569645151496, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.03252336270641536, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.03257167651318014, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.032641253424808385, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.032768123308196666, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.032947557733859864, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.03321879572700709, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.03362930410541594, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.03416221505962312, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.034674392477609214, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.03532634564675391, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.035705792647786436, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.03596011508721858, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.03656338084954768, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.0375049261841923, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.03874462108127773, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.040147327515296635, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.041901484308764336, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.04377392387483269, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.045386510668322444, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.04715667233336717, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.045338084450922904, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.040050065480172634, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.021074494161875918, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0037677252785942982, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0010524417128908682, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0005821061329334043, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.00033489715548057575, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.00016157255515281577, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0001310493794062495, "train/grad_031_lr3.1e+00_wd1.0e+00": 9.536798008866754e-05, "train/grad_032_lr3.7e+00_wd1.0e+00": 8.740347610910249e-05, "train/grad_033_lr4.3e+00_wd1.0e+00": 5.490757136612956e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 4.909669696189667e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 5.028356908042042e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 4.6939885951360335e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 4.687654908593686e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 5.01383099960151e-05, "train/grad_039_lr1.2e+01_wd1.0e+00": 4.010592513502331e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 4.7874794440758705e-05, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.00010806570599051213, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.6219689249992371, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.6190235614776611, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.6149846911430359, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.6115831136703491, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.6087766289710999, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.605586051940918, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.6026270389556885, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.5997810363769531, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.5967907905578613, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.593696117401123, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.5909161567687988, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.5876129865646362, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.5850690007209778, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.5819115042686462, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.5792014598846436, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.5783041715621948, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.5776300430297852, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.5793564319610596, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.5847042798995972, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.5954294204711914, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.6244692802429199, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.7014013528823853, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.8170379400253296, "validation/loss_023_lr8.5e-01_wd1.0e+00": 1.125053882598877, "validation/loss_024_lr1.0e+00_wd1.0e+00": 1.5752520561218262, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.0497968196868896, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.2508764266967773, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.2923827171325684, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.421539545059204, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.6369616985321045, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.8812363147735596, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.132190227508545, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.2990963459014893, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.954479455947876, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.7581052780151367, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.141050100326538, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.0048959255218506, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.831697702407837, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.118192672729492, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.3787624835968018, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.7400481700897217, "validation/loss_041_lr1.6e+01_wd1.0e+00": 5.588323593139648, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.6931473016738892, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.71875, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.75, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.765625, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.78125, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.765625, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.75, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.75, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.75, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.765625, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.796875, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.78125, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.765625, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.75, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.765625, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.765625, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.734375, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.734375, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.71875, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.6875, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.703125, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.6875, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.640625, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.65625, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.609375, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.5625, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.546875, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.546875, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.5625, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.5625, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.640625, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.625, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.59375, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.609375, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.609375, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.65625, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.578125, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.609375, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.609375, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.6875, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.640625, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.640625, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.59375, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.4375, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.4375, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.4375, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.4375, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.4375, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.4375, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.4375, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.694591728525981, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.7333333333333334, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.7520020666494446, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.7702564102564102, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.7555385790679909, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.7408906882591093, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.7408906882591093, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.7437437437437437, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.7584905660377359, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.7881334351922588, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.7732793522267206, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.7555385790679909, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.7374358974358974, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.7555385790679909, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.7584905660377359, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.7290161892901619, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.7290161892901619, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.7117117117117118, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.6796796796796797, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.6971357409713574, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.6825396825396826, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.6398336187912894, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.6389743589743591, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.5925642984466514, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.5465587044534412, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.537733499377335, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.537733499377335, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.5515515515515516, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.5405128205128206, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.6133438402941949, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.6061538461538462, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.5789473684210527, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.5925642984466514, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.5866701110824076, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.6333333333333333, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.5652830188679245, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.6014943960149439, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.6014943960149439, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.6536796536796536, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.6296855345911949, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.6296855345911949, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.5789473684210527, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.30434782608695654, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.30434782608695654, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.30434782608695654, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.30434782608695654, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.30434782608695654, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.30434782608695654, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.30434782608695654, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.6944444444444444, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.7301587301587301, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.748015873015873, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.7658730158730158, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.751984126984127, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.7380952380952381, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.7380952380952381, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.7420634920634921, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.7559523809523809, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.7837301587301587, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.7698412698412699, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.751984126984127, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.7341269841269842, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.751984126984127, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.7559523809523809, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.7281746031746033, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.7281746031746033, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.7103174603174603, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.6785714285714286, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.6964285714285714, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.6825396825396826, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.6448412698412699, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.6388888888888888, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.5932539682539683, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.5476190476190476, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.5376984126984128, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.5376984126984128, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.5515873015873016, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.5436507936507936, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.6170634920634921, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.6071428571428572, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.5793650793650793, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.5932539682539683, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.5892857142857143, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.6349206349206349, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.5654761904761905, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.6011904761904762, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.6011904761904762, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.6587301587301587, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.628968253968254, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.628968253968254, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.5793650793650793, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.5, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.5, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.5, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.5, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.5, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.5, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.5, "id_best": 9, "lr_best": 2.6099999999999997e-05, "wd_best": 0.05, "train/loss_best": 0.6029718017578125, "validation/loss_best": 0.593696117401123, "validation/acc_best": 0.796875, "validation/f1_best": 0.7881334351922588, "validation/bacc_best": 0.7837301587301587} +{"epoch": 10, "train/lr": 0.00021091808096876188, "train/loss": 0.35374510191380976, "train/grad": 0.1846842694655061, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.62388916015625, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.620535888671875, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.61543701171875, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.61111083984375, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.6071826171875, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.6023370361328125, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.5974261474609375, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.5922979736328124, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.5860186767578125, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.5797186279296875, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.57382568359375, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.56576904296875, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.5587594604492188, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.5502546691894531, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.5425439453125, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.5330593872070313, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.5179769897460937, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.5013653564453125, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.4826887893676758, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.45971376419067383, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.4211118984222412, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.36068764626979827, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.24459707334637643, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.10878767475485801, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.025556223541498183, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.005202477276325226, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.0019222798943519593, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.001098821610212326, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0006469801068305969, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.00035272851586341857, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.000295528918504715, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.00023089215159416199, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.00022376090288162232, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.00014065071940422058, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.00011329740285873413, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.00013178750872612, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.00011808767914772033, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.00010877147316932678, "train/loss_038_lr9.8e+00_wd1.0e+00": 7.621005177497864e-05, "train/loss_039_lr1.2e+01_wd1.0e+00": 9.209692478179932e-05, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.0001248466968536377, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.0001357439160346985, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.69140625, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.69140625, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.69140625, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.69140625, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.69140625, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.69140625, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.69140625, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.031820561720523985, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.03187797788530588, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.031966782666277144, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.03205916520440951, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.03214903698535636, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.03227695297915489, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.03243034347891807, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.032616707440465686, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.03291700984351337, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.033324106223881246, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.033814166798256336, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.03475876032374799, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.035948908398859204, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.037997795213013885, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.039550304468721154, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.04005358534865081, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.04004665153566748, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.03976048490498215, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.04002493823878467, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.040171946855261924, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.039655932048335674, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.03969299157615751, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.037718526730313895, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.023924354491755367, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.007730059288442135, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.001788159803400049, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.000644020494146389, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0003590598962910008, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.00022139050593978027, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.00011911225237781764, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.00010024701934526093, "train/grad_031_lr3.1e+00_wd1.0e+00": 7.695099133343319e-05, "train/grad_032_lr3.7e+00_wd1.0e+00": 7.307980113182566e-05, "train/grad_033_lr4.3e+00_wd1.0e+00": 4.588434238939954e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 4.360047741556628e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 4.338522834586911e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 4.2005532718576434e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 4.249859906849452e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 5.324129688915491e-05, "train/grad_039_lr1.2e+01_wd1.0e+00": 5.206288951939086e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 4.1740325345926974e-05, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.00010326448087980111, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.6204071044921875, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.6177999973297119, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.6140389442443848, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.6110817193984985, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.6086576581001282, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.6060272455215454, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.6032136678695679, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.6001442670822144, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.5959457755088806, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.5916723012924194, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.5879440307617188, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.5833364725112915, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.5800851583480835, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.5779831409454346, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.577357292175293, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.5748497247695923, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.5772172212600708, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.5854714512825012, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.5995920300483704, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.6226169466972351, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.6765917539596558, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.7743408679962158, "validation/loss_022_lr7.2e-01_wd1.0e+00": 1.0202760696411133, "validation/loss_023_lr8.5e-01_wd1.0e+00": 1.4210991859436035, "validation/loss_024_lr1.0e+00_wd1.0e+00": 1.7927048206329346, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.216337203979492, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.349778413772583, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.3785128593444824, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.496026039123535, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.703859567642212, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.9370617866516113, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.1701619625091553, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.3314871788024902, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.9923977851867676, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.7551283836364746, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.1924924850463867, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.0370166301727295, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.836005449295044, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.0020363330841064, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.2208690643310547, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.7495405673980713, "validation/loss_041_lr1.6e+01_wd1.0e+00": 5.294281959533691, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.6931473016738892, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.71875, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.734375, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.734375, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.734375, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.734375, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.734375, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.75, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.765625, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.765625, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.78125, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.765625, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.765625, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.765625, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.765625, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.765625, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.734375, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.71875, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.71875, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.703125, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.6875, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.6875, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.671875, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.609375, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.625, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.53125, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.546875, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.5625, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.578125, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.5625, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.640625, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.625, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.609375, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.609375, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.640625, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.65625, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.578125, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.59375, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.609375, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.671875, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.640625, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.625, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.59375, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.4375, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.4375, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.4375, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.4375, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.4375, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.4375, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.4375, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.6883116883116883, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.7087014725568943, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.7087014725568943, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.7087014725568943, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.7087014725568943, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.7087014725568943, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.7285259809119831, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.7429718875502007, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.747832939322301, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.7666666666666666, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.7520020666494446, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.7555385790679909, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.7555385790679909, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.7555385790679909, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.7520020666494446, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.7262893081761006, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.7117117117117118, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.7142857142857143, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.6971357409713574, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.6796796796796797, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.6796796796796797, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.6652552926525529, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.6014943960149439, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.6061538461538462, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.5238095238095238, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.537733499377335, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.5515515515515516, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.5652830188679245, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.5405128205128206, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.6133438402941949, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.6061538461538462, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.5925642984466514, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.5925642984466514, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.6133438402941949, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.6333333333333333, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.5652830188679245, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.5835835835835836, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.6014943960149439, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.6322845417236662, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.6296855345911949, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.611336032388664, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.5789473684210527, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.30434782608695654, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.30434782608695654, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.30434782608695654, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.30434782608695654, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.30434782608695654, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.30434782608695654, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.30434782608695654, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.6904761904761905, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.7083333333333333, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.7083333333333333, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.7083333333333333, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.7083333333333333, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.7083333333333333, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.7261904761904762, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.7400793650793651, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.7440476190476191, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.7619047619047619, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.748015873015873, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.751984126984127, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.751984126984127, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.751984126984127, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.748015873015873, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.7242063492063493, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.7103174603174603, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.7142857142857143, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.6964285714285714, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.6785714285714286, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.6785714285714286, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.6646825396825397, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.6011904761904762, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.6071428571428572, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.5238095238095238, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.5376984126984128, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.5515873015873016, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.5654761904761905, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.5436507936507936, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.6170634920634921, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.6071428571428572, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.5932539682539683, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.5932539682539683, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.6170634920634921, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.6349206349206349, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.5654761904761905, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.5833333333333333, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.6011904761904762, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.6408730158730158, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.628968253968254, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.6111111111111112, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.5793650793650793, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.5, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.5, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.5, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.5, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.5, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.5, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.5, "id_best": 9, "lr_best": 2.6099999999999997e-05, "wd_best": 0.05, "train/loss_best": 0.5797186279296875, "validation/loss_best": 0.5916723012924194, "validation/acc_best": 0.78125, "validation/f1_best": 0.7666666666666666, "validation/bacc_best": 0.7619047619047619} +{"epoch": 11, "train/lr": 0.00018113997589164516, "train/loss": 0.34641908667981625, "train/grad": 0.19283439099788666, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.62898193359375, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.626038818359375, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.621463623046875, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.6171630859375, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.613138427734375, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.60794921875, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.6024664306640625, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.59643798828125, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.5890606689453125, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.5813958740234375, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.5742633056640625, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.563896484375, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.5540316772460937, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.5402265930175781, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.5267823791503906, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.5141034698486329, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.4989985656738281, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.480744514465332, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.4583079195022583, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.43225602626800536, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.3835492956638336, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.29357143357396126, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.1629949676990509, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.04851324215531349, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.010567594766616822, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.0030155575275421145, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.0013458579778671265, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0008445851504802704, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0005589400231838227, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.00032777115702629087, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.00026144370436668394, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.00020015984773635864, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.00019467458128929137, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.00012561947107315064, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.00010977432131767273, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.00013130694627761842, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.00010533571243286133, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.00010622158646583557, "train/loss_038_lr9.8e+00_wd1.0e+00": 7.68539309501648e-05, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.00011197850108146667, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.00011010199785232544, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.0001620425283908844, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.69140625, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.69140625, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.69140625, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.69140625, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.69140625, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.69140625, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.69140625, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.03232859321404249, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.03229661866556853, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.03226793036796152, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.03224761135177687, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.03226406999165192, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.03232291974825784, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.03239124572137371, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.03250256632221862, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.032665160296019166, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.03288798801135272, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.03317570130340755, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.03375114470720291, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.03444759803591296, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.03570322007406503, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.03723658408038318, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.039033852769061926, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.041516061183065174, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.04309875747188926, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.044766625380143525, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.04751877614762634, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.05008522035554051, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.048620075550861654, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.041829518794547764, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.017711348620359786, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.003859660252928734, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0010740397835616023, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0004445424383084173, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.00026514838929870166, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0001709042181028053, "train/grad_029_lr2.3e+00_wd1.0e+00": 9.735715448186966e-05, "train/grad_030_lr2.7e+00_wd1.0e+00": 8.364091257135443e-05, "train/grad_031_lr3.1e+00_wd1.0e+00": 6.654721144968789e-05, "train/grad_032_lr3.7e+00_wd1.0e+00": 6.49150718072633e-05, "train/grad_033_lr4.3e+00_wd1.0e+00": 4.135513023356907e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 4.119747922686656e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 3.9591284903508494e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 3.756293954211287e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 3.775106879857048e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 5.462869575156404e-05, "train/grad_039_lr1.2e+01_wd1.0e+00": 6.59098714686479e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 3.830701110928203e-05, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.00010113413362432766, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.6183130145072937, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.6155338883399963, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.6115773320198059, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.60863196849823, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.6060411930084229, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.603049635887146, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.600185751914978, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.5974699854850769, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.5937954783439636, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.5905807018280029, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.5876731276512146, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.5837891101837158, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.5805823802947998, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.5784218311309814, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.578485906124115, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.579674482345581, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.580930233001709, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.5862421989440918, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.6071401834487915, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.6500911116600037, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.7305632829666138, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.8822134733200073, "validation/loss_022_lr7.2e-01_wd1.0e+00": 1.2109851837158203, "validation/loss_023_lr8.5e-01_wd1.0e+00": 1.6105833053588867, "validation/loss_024_lr1.0e+00_wd1.0e+00": 1.9564423561096191, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.322209119796753, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.4184181690216064, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.443192958831787, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.5593340396881104, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.7477989196777344, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.979888916015625, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.204094886779785, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.366851806640625, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.018047571182251, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.761272668838501, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.2377023696899414, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.061758279800415, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.845553159713745, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.9272618293762207, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.1239676475524902, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.7631473541259766, "validation/loss_041_lr1.6e+01_wd1.0e+00": 5.090492248535156, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.6931473016738892, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.734375, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.75, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.75, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.78125, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.765625, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.765625, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.765625, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.78125, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.78125, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.78125, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.765625, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.765625, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.75, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.75, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.75, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.71875, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.6875, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.703125, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.71875, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.6875, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.65625, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.65625, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.640625, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.578125, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.546875, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.546875, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.578125, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.59375, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.578125, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.640625, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.640625, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.609375, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.609375, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.640625, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.65625, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.578125, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.59375, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.609375, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.671875, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.640625, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.65625, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.59375, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.4375, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.4375, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.4375, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.4375, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.4375, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.4375, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.4375, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.7142106645652745, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.7333333333333334, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.7333333333333334, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.7702564102564102, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.7520020666494446, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.7520020666494446, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.7520020666494446, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.7666666666666666, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.7666666666666666, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.7666666666666666, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.7520020666494446, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.7520020666494446, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.7374358974358974, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.7374358974358974, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.7333333333333334, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.7, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.6717948717948719, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.6940880503144654, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.7142857142857143, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.6847290640394088, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.6532019704433498, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.6476476476476476, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.6251591545709193, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.5652830188679245, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.5413886829750432, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.537733499377335, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.5652830188679245, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.5789473684210527, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.5536037199690003, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.6133438402941949, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.619736502195815, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.5925642984466514, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.5925642984466514, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.6133438402941949, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.6333333333333333, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.5652830188679245, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.5835835835835836, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.6014943960149439, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.6322845417236662, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.6296855345911949, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.6437246963562753, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.5789473684210527, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.30434782608695654, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.30434782608695654, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.30434782608695654, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.30434782608695654, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.30434782608695654, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.30434782608695654, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.30434782608695654, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.7123015873015872, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.7301587301587301, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.7301587301587301, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.7658730158730158, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.748015873015873, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.748015873015873, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.748015873015873, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.7619047619047619, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.7619047619047619, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.7619047619047619, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.748015873015873, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.748015873015873, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.7341269841269842, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.7341269841269842, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.7301587301587301, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.6984126984126984, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.6706349206349207, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.6924603174603174, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.7142857142857143, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.6865079365079365, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.6547619047619048, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.6468253968253967, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.625, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.5654761904761905, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.5416666666666667, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.5376984126984128, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.5654761904761905, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.5793650793650793, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.5575396825396826, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.6170634920634921, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.621031746031746, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.5932539682539683, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.5932539682539683, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.6170634920634921, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.6349206349206349, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.5654761904761905, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.5833333333333333, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.6011904761904762, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.6408730158730158, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.628968253968254, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.6428571428571428, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.5793650793650793, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.5, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.5, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.5, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.5, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.5, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.5, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.5, "id_best": 3, "lr_best": 9.9e-06, "wd_best": 0.05, "train/loss_best": 0.6171630859375, "validation/loss_best": 0.60863196849823, "validation/acc_best": 0.78125, "validation/f1_best": 0.7702564102564102, "validation/bacc_best": 0.7658730158730158} +{"epoch": 12, "train/lr": 0.0001499999999999999, "train/loss": 0.3379554992169142, "train/grad": 0.18634827688336372, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.631932373046875, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.6282470703125, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.62263671875, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.6174609375, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.612833251953125, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.606890869140625, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.600594482421875, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.5940997314453125, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.586177978515625, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.5782049560546875, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.5708941650390625, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.5599020385742187, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.5495138549804688, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.5341769409179687, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.5183767700195312, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.5017398071289062, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.47897186279296877, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.45132606506347656, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.419109992980957, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.38312143325805664, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.3224319911003113, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.21861247792840005, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.09493248015642167, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.024659752994775772, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.006850786060094833, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.0022792933881282808, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.0010599316656589508, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0006768755614757538, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.00045122787356376647, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.00026670396327972413, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.00022480368614196777, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.0001718086004257202, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.00017162606120109557, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.00010920867323875427, "train/loss_034_lr5.1e+00_wd1.0e+00": 9.934455156326293e-05, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.00011036977171897888, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.00010393589735031129, "train/loss_037_lr8.3e+00_wd1.0e+00": 9.617477655410767e-05, "train/loss_038_lr9.8e+00_wd1.0e+00": 8.088454604148864e-05, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.00011674970388412475, "train/loss_040_lr1.4e+01_wd1.0e+00": 9.92557406425476e-05, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.00015910953283309936, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.69140625, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.69140625, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.69140625, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.69140625, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.69140625, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.69140625, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.69140625, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.031329785655252636, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.03137820052914322, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.031476779826916754, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.03159722682554275, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.031738440725021064, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.03194899961352348, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.03217867474071681, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.03247032397426665, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.032846816685050725, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.033278681230731307, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.03372192664537579, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.03445568716153503, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.03528948317747563, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.036716853589750825, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.03815110070630908, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.03950070283841342, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.04129898318089545, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.04288746902253479, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.044446169226430354, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.04631845670286566, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.04742002835031599, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.04582860792521387, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0293419684516266, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.009011765936156735, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0024499151871714277, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0007997026701195863, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.00034910321279312483, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.00022158343976116156, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.000148288578257052, "train/grad_029_lr2.3e+00_wd1.0e+00": 8.533403792171157e-05, "train/grad_030_lr2.7e+00_wd1.0e+00": 7.275687396941067e-05, "train/grad_031_lr3.1e+00_wd1.0e+00": 5.874132354620088e-05, "train/grad_032_lr3.7e+00_wd1.0e+00": 5.6445765831085734e-05, "train/grad_033_lr4.3e+00_wd1.0e+00": 3.627354570198804e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 3.7727410542629514e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 3.5634273199320884e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 3.517910714890604e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 3.384555511274812e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 5.17376282641635e-05, "train/grad_039_lr1.2e+01_wd1.0e+00": 6.687238119127415e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 3.4414561987432535e-05, "train/grad_041_lr1.6e+01_wd1.0e+00": 9.824863470214495e-05, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.6186113953590393, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.6161773800849915, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.6127306818962097, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.6104004383087158, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.6085466146469116, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.6066358089447021, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.6047372221946716, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.602824866771698, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.6002374887466431, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.5974075198173523, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.5946735143661499, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.5910792946815491, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.5876737833023071, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.5852582454681396, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.5853608846664429, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.5870815515518188, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.5921563506126404, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.6055933237075806, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.6408675909042358, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.6916088461875916, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.7857871055603027, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.9985082745552063, "validation/loss_022_lr7.2e-01_wd1.0e+00": 1.3676948547363281, "validation/loss_023_lr8.5e-01_wd1.0e+00": 1.7420495748519897, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.0823018550872803, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.4129838943481445, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.475576162338257, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.4966752529144287, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.602184772491455, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.7935667037963867, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.016944408416748, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.234863758087158, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.3973488807678223, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.051462173461914, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.7672224044799805, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.2728304862976074, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.092515468597412, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.860037326812744, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.8641369342803955, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.0624780654907227, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.7788047790527344, "validation/loss_041_lr1.6e+01_wd1.0e+00": 4.962259292602539, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.6931473016738892, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.734375, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.734375, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.734375, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.734375, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.734375, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.75, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.75, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.75, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.765625, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.765625, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.765625, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.75, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.75, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.75, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.71875, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.703125, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.6875, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.671875, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.671875, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.640625, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.640625, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.625, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.59375, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.5625, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.546875, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.546875, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.59375, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.59375, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.578125, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.640625, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.65625, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.609375, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.609375, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.609375, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.640625, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.578125, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.59375, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.609375, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.671875, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.640625, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.65625, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.59375, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.4375, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.4375, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.4375, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.4375, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.4375, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.4375, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.4375, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.7087014725568943, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.7087014725568943, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.7087014725568943, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.7087014725568943, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.7087014725568943, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.722943722943723, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.722943722943723, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.722943722943723, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.7373461012311902, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.7373461012311902, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.7373461012311902, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.7285259809119831, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.7333333333333334, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.7333333333333334, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.7046153846153846, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.6903488668194551, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.6761133603238867, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.6618867924528302, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.6652552926525529, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.6362737830491723, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.6362737830491723, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.6216748768472906, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.592156862745098, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.5555555555555556, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.537733499377335, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.537733499377335, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.5835835835835836, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.5789473684210527, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.5536037199690003, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.6133438402941949, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.6333333333333333, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.5925642984466514, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.5925642984466514, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.5797215655371684, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.619736502195815, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.5652830188679245, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.5835835835835836, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.6014943960149439, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.6322845417236662, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.6296855345911949, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.6437246963562753, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.5789473684210527, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.30434782608695654, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.30434782608695654, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.30434782608695654, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.30434782608695654, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.30434782608695654, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.30434782608695654, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.30434782608695654, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.7083333333333333, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.7083333333333333, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.7083333333333333, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.7083333333333333, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.7083333333333333, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.7222222222222222, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.7222222222222222, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.7222222222222222, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.7361111111111112, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.7361111111111112, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.7361111111111112, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.7261904761904762, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.7301587301587301, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.7301587301587301, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.7023809523809523, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.6884920634920635, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.6746031746031746, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.6607142857142857, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.6646825396825397, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.6369047619047619, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.6369047619047619, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.623015873015873, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.5952380952380952, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.5555555555555556, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.5376984126984128, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.5376984126984128, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.5833333333333333, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.5793650793650793, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.5575396825396826, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.6170634920634921, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.6349206349206349, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.5932539682539683, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.5932539682539683, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.5853174603174603, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.621031746031746, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.5654761904761905, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.5833333333333333, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.6011904761904762, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.6408730158730158, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.628968253968254, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.6428571428571428, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.5793650793650793, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.5, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.5, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.5, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.5, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.5, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.5, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.5, "id_best": 8, "lr_best": 2.2199999999999998e-05, "wd_best": 0.05, "train/loss_best": 0.586177978515625, "validation/loss_best": 0.6002374887466431, "validation/acc_best": 0.765625, "validation/f1_best": 0.7373461012311902, "validation/bacc_best": 0.7361111111111112} +{"epoch": 13, "train/lr": 0.00011886002410835478, "train/loss": 0.33555559657514095, "train/grad": 0.19028392098844052, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.630496826171875, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.626693115234375, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.6210302734375, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.6159716796875, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.611549072265625, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.6058856201171875, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.60017578125, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.5941033935546876, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.5867669677734375, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.5789105224609375, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.57162109375, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.5604898071289063, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.5496533203125, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.5336944580078125, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.5175192260742187, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.5017768859863281, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.4818121337890625, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.45852373123168944, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.4263001537322998, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.3810075867176056, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.29601951599121096, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.17032997518777848, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.057568451911211016, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.014583539664745331, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.004639799296855926, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.0017679707705974578, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.0008511060476303101, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0005505986511707306, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0003667660057544708, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.00023068949580192565, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0001998889446258545, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.0001593659818172455, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.00015591442584991455, "train/loss_033_lr4.3e+00_wd1.0e+00": 9.990394115447997e-05, "train/loss_034_lr5.1e+00_wd1.0e+00": 9.777009487152099e-05, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.00010499060153961182, "train/loss_036_lr7.1e+00_wd1.0e+00": 9.255647659301757e-05, "train/loss_037_lr8.3e+00_wd1.0e+00": 8.395209908485413e-05, "train/loss_038_lr9.8e+00_wd1.0e+00": 8.34241509437561e-05, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.00013615638017654418, "train/loss_040_lr1.4e+01_wd1.0e+00": 9.364292025566102e-05, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.00018320053815841674, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.69140625, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.69140625, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.69140625, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.69140625, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.69140625, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.69140625, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.69140625, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.03318860705941915, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.03320172179024666, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.03325267866253853, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.03332496565766632, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.033410730767063794, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.03357828780543059, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.03376994064543396, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.03404680355917662, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.03446052212268114, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.03500944334082305, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.035617511956952515, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.036592518584802745, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.037607218050397934, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.03904938952997327, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.04046516982838511, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.041879393351264296, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.04384794896934181, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.045987722552381455, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.04738148338161409, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.0479304472822696, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.046036111642606556, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.03904799380106851, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.020005523019935936, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.006010945189627819, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0018457010012934915, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0006746666443359573, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0003057063261439907, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.00019820057743345388, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.00013733719499214202, "train/grad_029_lr2.3e+00_wd1.0e+00": 8.049250775911787e-05, "train/grad_030_lr2.7e+00_wd1.0e+00": 7.086988831360941e-05, "train/grad_031_lr3.1e+00_wd1.0e+00": 5.784216281881527e-05, "train/grad_032_lr3.7e+00_wd1.0e+00": 5.2894372897753785e-05, "train/grad_033_lr4.3e+00_wd1.0e+00": 3.461313680418243e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 3.679080218262243e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 3.374544711277849e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 3.2941631661742574e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 3.236774535707809e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 4.953394150426504e-05, "train/grad_039_lr1.2e+01_wd1.0e+00": 6.8573572744981e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 3.185734198723367e-05, "train/grad_041_lr1.6e+01_wd1.0e+00": 9.315290391214149e-05, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.6172861456871033, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.6147273778915405, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.6112144589424133, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.6083298921585083, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.6060048937797546, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.6030879616737366, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.6003438234329224, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.5974718332290649, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.5939021706581116, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.5904797315597534, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.5874417424201965, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.5837834477424622, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.5810866951942444, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.5794204473495483, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.5813237428665161, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.585665225982666, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.5941882133483887, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.6108565330505371, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.6455488801002502, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.6989600658416748, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.8250212669372559, "validation/loss_021_lr6.1e-01_wd1.0e+00": 1.0809011459350586, "validation/loss_022_lr7.2e-01_wd1.0e+00": 1.468224287033081, "validation/loss_023_lr8.5e-01_wd1.0e+00": 1.8448207378387451, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.1605892181396484, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.4737308025360107, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.509626865386963, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.519594669342041, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.621488571166992, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.806762218475342, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.0372610092163086, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.2514543533325195, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.416006326675415, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.0679726600646973, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.776129961013794, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.303968906402588, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.1131577491760254, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.8684914112091064, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.8210811614990234, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.0351033210754395, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.7948503494262695, "validation/loss_041_lr1.6e+01_wd1.0e+00": 4.868206977844238, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.6931473016738892, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.734375, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.734375, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.734375, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.75, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.75, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.75, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.765625, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.765625, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.78125, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.765625, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.765625, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.75, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.765625, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.734375, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.71875, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.703125, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.71875, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.703125, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.703125, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.703125, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.640625, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.625, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.578125, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.578125, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.546875, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.546875, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.59375, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.59375, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.578125, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.640625, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.65625, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.609375, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.609375, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.609375, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.640625, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.578125, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.609375, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.609375, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.671875, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.640625, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.65625, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.59375, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.4375, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.4375, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.4375, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.4375, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.4375, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.4375, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.4375, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.7087014725568943, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.7087014725568943, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.7087014725568943, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.7285259809119831, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.7285259809119831, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.7285259809119831, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.747832939322301, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.747832939322301, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.7666666666666666, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.7520020666494446, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.7520020666494446, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.7374358974358974, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.7555385790679909, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.7262893081761006, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.708502024291498, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.6903488668194551, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.7046153846153846, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.6903488668194551, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.6940880503144654, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.6940880503144654, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.6362737830491723, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.6216748768472906, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.5696139476961395, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.5652830188679245, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.537733499377335, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.537733499377335, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.5835835835835836, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.5789473684210527, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.5536037199690003, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.6133438402941949, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.6333333333333333, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.5925642984466514, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.5925642984466514, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.5797215655371684, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.619736502195815, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.5652830188679245, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.5974842767295597, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.6014943960149439, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.6322845417236662, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.6296855345911949, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.6437246963562753, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.5789473684210527, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.30434782608695654, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.30434782608695654, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.30434782608695654, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.30434782608695654, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.30434782608695654, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.30434782608695654, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.30434782608695654, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.7083333333333333, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.7083333333333333, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.7083333333333333, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.7261904761904762, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.7261904761904762, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.7261904761904762, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.7440476190476191, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.7440476190476191, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.7619047619047619, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.748015873015873, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.748015873015873, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.7341269841269842, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.751984126984127, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.7242063492063493, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.7063492063492063, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.6884920634920635, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.7023809523809523, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.6884920634920635, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.6924603174603174, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.6924603174603174, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.6369047619047619, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.623015873015873, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.5694444444444444, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.5654761904761905, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.5376984126984128, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.5376984126984128, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.5833333333333333, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.5793650793650793, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.5575396825396826, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.6170634920634921, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.6349206349206349, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.5932539682539683, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.5932539682539683, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.5853174603174603, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.621031746031746, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.5654761904761905, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.5972222222222222, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.6011904761904762, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.6408730158730158, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.628968253968254, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.6428571428571428, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.5793650793650793, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.5, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.5, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.5, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.5, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.5, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.5, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.5, "id_best": 8, "lr_best": 2.2199999999999998e-05, "wd_best": 0.05, "train/loss_best": 0.5867669677734375, "validation/loss_best": 0.5939021706581116, "validation/acc_best": 0.78125, "validation/f1_best": 0.7666666666666666, "validation/bacc_best": 0.7619047619047619} +{"epoch": 14, "train/lr": 8.9081919031238e-05, "train/loss": 0.3297101037949324, "train/grad": 0.18637477220967413, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.630902099609375, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.62717041015625, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.621402587890625, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.616409912109375, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.61160888671875, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.6054351806640625, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.5988861083984375, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.5921044921875, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.583609619140625, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.5749530029296875, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.5668218994140625, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.5546383666992187, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.542763671875, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.5251914978027343, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.5077916717529297, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.4903068923950195, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.46553781509399417, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.4321442937850952, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.38729882836341856, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.33552665263414383, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.24854830175638198, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.13442049622535707, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.04248072072863579, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.011227200925350189, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.004039984941482544, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.0015807585418224335, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.0007355268299579621, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.00047308921813964843, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0003425651788711548, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.00020889684557914734, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0001805208623409271, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.00014753103256225585, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.00014439240097999573, "train/loss_033_lr4.3e+00_wd1.0e+00": 9.187892079353333e-05, "train/loss_034_lr5.1e+00_wd1.0e+00": 9.662970900535584e-05, "train/loss_035_lr6.0e+00_wd1.0e+00": 9.91511344909668e-05, "train/loss_036_lr7.1e+00_wd1.0e+00": 8.210316300392151e-05, "train/loss_037_lr8.3e+00_wd1.0e+00": 8.571535348892212e-05, "train/loss_038_lr9.8e+00_wd1.0e+00": 8.657023310661316e-05, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.00013309001922607423, "train/loss_040_lr1.4e+01_wd1.0e+00": 8.239373564720154e-05, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.00016023576259613037, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.69140625, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.69140625, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.69140625, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.69140625, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.69140625, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.69140625, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.69140625, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.03316814608871937, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.03319103987654671, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.033259967020712794, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.03336073625832796, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.033470864163246, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.033672826429829, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.03391024694312364, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.03420782960485667, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.034644055040553214, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.03516556310001761, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.03577724945964292, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.03682084684725851, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.03795862847939133, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.03970852901227772, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.041508421078324316, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.04320602614432573, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.045012367153540254, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.04582429818809033, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.045836762888357044, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.045443928609602155, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.04139569774735719, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.030904585227835922, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.013533285716548563, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0041473430121550334, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.001452790482144337, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0005661078286357224, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0002537863930047024, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0001645997669038479, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.00011322162587021012, "train/grad_029_lr2.3e+00_wd1.0e+00": 6.943065605355514e-05, "train/grad_030_lr2.7e+00_wd1.0e+00": 6.155652509733045e-05, "train/grad_031_lr3.1e+00_wd1.0e+00": 5.0931340501847445e-05, "train/grad_032_lr3.7e+00_wd1.0e+00": 4.9222002166970925e-05, "train/grad_033_lr4.3e+00_wd1.0e+00": 3.123424009572773e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 3.43504411421236e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 3.09290402356055e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 3.003977186381235e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 2.9137231906588567e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 4.726375239009428e-05, "train/grad_039_lr1.2e+01_wd1.0e+00": 6.588948364480985e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 2.8889083394005867e-05, "train/grad_041_lr1.6e+01_wd1.0e+00": 9.017384900744218e-05, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.6162127256393433, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.6137267351150513, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.6099646091461182, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.6071585416793823, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.6045851707458496, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.601539134979248, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.5984782576560974, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.5954505205154419, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.5916433334350586, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.5877321362495422, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.5843012928962708, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.5801247358322144, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.5771948099136353, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.5753983855247498, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.5763298869132996, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.5800811648368835, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.5891693830490112, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.6111795902252197, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.6570824980735779, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.7256495952606201, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.8704854846000671, "validation/loss_021_lr6.1e-01_wd1.0e+00": 1.1469042301177979, "validation/loss_022_lr7.2e-01_wd1.0e+00": 1.5432817935943604, "validation/loss_023_lr8.5e-01_wd1.0e+00": 1.9000513553619385, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.2150890827178955, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.5174100399017334, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.5363714694976807, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.5430071353912354, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.6371684074401855, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.8268346786499023, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.0489282608032227, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.2675933837890625, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.428816795349121, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.0790529251098633, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.785046100616455, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.3281216621398926, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.1322832107543945, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.8799400329589844, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.7914185523986816, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.0122969150543213, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.800424814224243, "validation/loss_041_lr1.6e+01_wd1.0e+00": 4.809810161590576, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.6931473016738892, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.75, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.765625, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.75, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.765625, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.765625, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.765625, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.765625, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.765625, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.78125, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.765625, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.75, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.765625, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.734375, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.734375, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.71875, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.703125, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.6875, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.6875, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.6875, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.6875, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.6875, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.703125, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.625, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.5625, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.53125, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.5625, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.59375, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.59375, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.578125, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.640625, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.65625, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.609375, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.625, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.59375, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.640625, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.578125, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.609375, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.625, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.671875, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.640625, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.65625, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.59375, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.4375, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.4375, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.4375, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.4375, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.4375, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.4375, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.4375, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.7285259809119831, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.747832939322301, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.7285259809119831, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.747832939322301, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.747832939322301, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.7520020666494446, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.747832939322301, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.747832939322301, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.7666666666666666, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.7520020666494446, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.7374358974358974, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.7555385790679909, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.7290161892901619, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.7290161892901619, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.7117117117117118, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.6940880503144654, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.6796796796796797, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.6796796796796797, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.6796796796796797, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.6796796796796797, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.6796796796796797, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.6940880503144654, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.611336032388664, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.5515515515515516, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.5238095238095238, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.5515515515515516, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.5835835835835836, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.5789473684210527, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.5536037199690003, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.6133438402941949, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.6333333333333333, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.5925642984466514, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.611336032388664, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.5666666666666667, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.619736502195815, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.5652830188679245, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.5974842767295597, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.6156156156156156, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.6322845417236662, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.6296855345911949, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.6437246963562753, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.5789473684210527, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.30434782608695654, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.30434782608695654, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.30434782608695654, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.30434782608695654, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.30434782608695654, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.30434782608695654, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.30434782608695654, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.7261904761904762, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.7440476190476191, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.7261904761904762, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.7440476190476191, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.7440476190476191, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.748015873015873, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.7440476190476191, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.7440476190476191, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.7619047619047619, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.748015873015873, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.7341269841269842, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.751984126984127, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.7281746031746033, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.7281746031746033, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.7103174603174603, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.6924603174603174, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.6785714285714286, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.6785714285714286, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.6785714285714286, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.6785714285714286, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.6785714285714286, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.6924603174603174, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.6111111111111112, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.5515873015873016, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.5238095238095238, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.5515873015873016, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.5833333333333333, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.5793650793650793, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.5575396825396826, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.6170634920634921, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.6349206349206349, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.5932539682539683, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.6111111111111112, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.5714285714285714, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.621031746031746, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.5654761904761905, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.5972222222222222, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.6150793650793651, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.6408730158730158, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.628968253968254, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.6428571428571428, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.5793650793650793, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.5, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.5, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.5, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.5, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.5, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.5, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.5, "id_best": 8, "lr_best": 2.2199999999999998e-05, "wd_best": 0.05, "train/loss_best": 0.583609619140625, "validation/loss_best": 0.5916433334350586, "validation/acc_best": 0.78125, "validation/f1_best": 0.7666666666666666, "validation/bacc_best": 0.7619047619047619} +{"epoch": 15, "train/lr": 6.196799573888289e-05, "train/loss": 0.3265897349268198, "train/grad": 0.17731778491288425, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.624532470703125, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.62082763671875, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.615086669921875, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.609913330078125, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.6051409912109375, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.5989947509765625, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.5923040771484375, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.585322265625, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.5766534423828125, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.567789306640625, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.5592193603515625, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.5462884521484375, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.533687744140625, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.5151287078857422, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.49726806640625, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.48026447296142577, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.4581098937988281, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.4293104696273804, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.3888948893547058, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.3375428146123886, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.24475905895233155, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.12475413963198662, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.034309804141521454, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.008939681500196457, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.0033970822393894194, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.0014269286394119262, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.0007197284698486329, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0004810892045497894, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0003505723178386688, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0002152399718761444, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.00019407764077186584, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.00015641808509826661, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.00015213996171951295, "train/loss_033_lr4.3e+00_wd1.0e+00": 9.501263499259948e-05, "train/loss_034_lr5.1e+00_wd1.0e+00": 9.556397795677184e-05, "train/loss_035_lr6.0e+00_wd1.0e+00": 9.630903601646423e-05, "train/loss_036_lr7.1e+00_wd1.0e+00": 8.213117718696594e-05, "train/loss_037_lr8.3e+00_wd1.0e+00": 7.855340838432312e-05, "train/loss_038_lr9.8e+00_wd1.0e+00": 8.855998516082763e-05, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.00012706071138381957, "train/loss_040_lr1.4e+01_wd1.0e+00": 7.945790886878967e-05, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.0001751720905303955, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.69140625, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.69140625, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.69140625, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.69140625, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.69140625, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.69140625, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.69140625, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.032610368290916084, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.03259937180671841, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.032621145269367845, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.03265594283118844, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.03272736162412912, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.03287073566345498, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.033049740297719836, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.033289814926683904, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.03365440714173019, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.03413216400425881, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.03467447011731565, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.03558349325321615, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.036541923461481926, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.037882837923243644, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.03904779003933072, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.040050443853251634, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.04123639211058617, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.04259733332786709, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.043916556281037626, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.04470518792513758, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.04198307321406901, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.02989254518877715, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.011254477509646676, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0032401158873108216, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0012118420394835994, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0005006080948078307, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.00023551228317955975, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.00015884702270341222, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.00011163200621012947, "train/grad_029_lr2.3e+00_wd1.0e+00": 6.794444083425332e-05, "train/grad_030_lr2.7e+00_wd1.0e+00": 5.9520449958654354e-05, "train/grad_031_lr3.1e+00_wd1.0e+00": 4.977808998319233e-05, "train/grad_032_lr3.7e+00_wd1.0e+00": 4.613710834291851e-05, "train/grad_033_lr4.3e+00_wd1.0e+00": 2.981561263823096e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 3.301424938172204e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 2.936888387466752e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 2.8203283141010615e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 2.736809554789943e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 4.5851478134295576e-05, "train/grad_039_lr1.2e+01_wd1.0e+00": 6.361754282323773e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 2.7117289305351734e-05, "train/grad_041_lr1.6e+01_wd1.0e+00": 8.419005024961734e-05, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.6156669855117798, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.6128536462783813, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.6091727018356323, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.606229305267334, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.6036989688873291, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.6005682945251465, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.5975463390350342, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.5944334268569946, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.5906296968460083, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.5871308445930481, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.5840074419975281, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.5805283784866333, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.5786162614822388, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.5784839987754822, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.5806993842124939, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.5855427384376526, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.5959895849227905, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.6186513304710388, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.6649345755577087, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.7399110794067383, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.9008073806762695, "validation/loss_021_lr6.1e-01_wd1.0e+00": 1.1979589462280273, "validation/loss_022_lr7.2e-01_wd1.0e+00": 1.5946927070617676, "validation/loss_023_lr8.5e-01_wd1.0e+00": 1.938564419746399, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.2550947666168213, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.550121545791626, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.5584259033203125, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.5611281394958496, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.652275562286377, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.8397269248962402, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.0632808208465576, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.281010627746582, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.446275234222412, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.094285249710083, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.793193817138672, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.345393657684326, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.1513915061950684, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.8876707553863525, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.7723913192749023, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.0055272579193115, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.817803382873535, "validation/loss_041_lr1.6e+01_wd1.0e+00": 4.776956081390381, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.6931473016738892, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.75, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.75, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.765625, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.765625, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.765625, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.765625, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.78125, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.78125, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.765625, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.765625, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.75, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.765625, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.75, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.734375, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.703125, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.6875, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.671875, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.6875, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.6875, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.6875, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.65625, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.640625, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.625, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.5625, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.5625, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.5625, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.59375, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.59375, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.578125, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.640625, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.65625, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.609375, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.625, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.59375, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.640625, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.578125, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.625, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.625, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.671875, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.640625, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.65625, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.59375, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.4375, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.4375, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.4375, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.4375, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.4375, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.4375, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.4375, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.7333333333333334, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.7333333333333334, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.7520020666494446, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.7520020666494446, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.7520020666494446, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.7520020666494446, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.7666666666666666, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.7666666666666666, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.7520020666494446, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.7520020666494446, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.7374358974358974, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.7555385790679909, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.7408906882591093, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.7262893081761006, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.6940880503144654, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.6761133603238867, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.6618867924528302, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.6796796796796797, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.6796796796796797, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.6796796796796797, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.6507936507936507, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.6362737830491723, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.611336032388664, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.5515515515515516, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.5515515515515516, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.5515515515515516, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.5835835835835836, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.5789473684210527, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.5536037199690003, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.6133438402941949, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.6333333333333333, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.5925642984466514, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.611336032388664, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.5666666666666667, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.619736502195815, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.5652830188679245, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.611336032388664, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.6156156156156156, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.6322845417236662, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.6296855345911949, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.6437246963562753, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.5789473684210527, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.30434782608695654, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.30434782608695654, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.30434782608695654, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.30434782608695654, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.30434782608695654, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.30434782608695654, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.30434782608695654, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.7301587301587301, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.7301587301587301, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.748015873015873, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.748015873015873, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.748015873015873, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.748015873015873, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.7619047619047619, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.7619047619047619, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.748015873015873, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.748015873015873, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.7341269841269842, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.751984126984127, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.7380952380952381, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.7242063492063493, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.6924603174603174, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.6746031746031746, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.6607142857142857, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.6785714285714286, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.6785714285714286, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.6785714285714286, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.6507936507936507, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.6369047619047619, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.6111111111111112, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.5515873015873016, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.5515873015873016, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.5515873015873016, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.5833333333333333, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.5793650793650793, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.5575396825396826, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.6170634920634921, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.6349206349206349, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.5932539682539683, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.6111111111111112, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.5714285714285714, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.621031746031746, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.5654761904761905, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.6111111111111112, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.6150793650793651, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.6408730158730158, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.628968253968254, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.6428571428571428, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.5793650793650793, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.5, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.5, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.5, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.5, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.5, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.5, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.5, "id_best": 6, "lr_best": 1.5899999999999997e-05, "wd_best": 0.05, "train/loss_best": 0.5923040771484375, "validation/loss_best": 0.5975463390350342, "validation/acc_best": 0.78125, "validation/f1_best": 0.7666666666666666, "validation/bacc_best": 0.7619047619047619} +{"epoch": 16, "train/lr": 3.870405029380728e-05, "train/loss": 0.32454791247844694, "train/grad": 0.169324202965945, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.628677978515625, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.624840087890625, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.618912353515625, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.613509521484375, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.6085302734375, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.6019598388671875, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.5948773193359375, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.587286376953125, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.577705078125, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.5677978515625, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.5582266235351563, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.5439801025390625, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.5303390502929688, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.5107294464111328, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.4922798156738281, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.47451358795166015, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.45063018798828125, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.41901010036468506, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.3753119146823883, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.32028445333242417, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.21907604441046716, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.10149757951498031, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.028122906386852265, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.007773666679859161, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.0030337370932102203, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.0012684372067451478, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.000627698004245758, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.00043270483613014224, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.00031058117747306824, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0001961730420589447, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.00017128512263298035, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.00014325946569442748, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.00013963311910629274, "train/loss_033_lr4.3e+00_wd1.0e+00": 8.634939789772034e-05, "train/loss_034_lr5.1e+00_wd1.0e+00": 8.469641208648682e-05, "train/loss_035_lr6.0e+00_wd1.0e+00": 8.447229862213135e-05, "train/loss_036_lr7.1e+00_wd1.0e+00": 7.726341485977173e-05, "train/loss_037_lr8.3e+00_wd1.0e+00": 7.429227232933045e-05, "train/loss_038_lr9.8e+00_wd1.0e+00": 7.00359046459198e-05, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.00011752456426620483, "train/loss_040_lr1.4e+01_wd1.0e+00": 6.86788558959961e-05, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.00014533519744873048, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.69140625, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.69140625, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.69140625, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.69140625, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.69140625, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.69140625, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.69140625, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.03201882260385901, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.031995521350763736, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.03198340271599591, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.032009219988249245, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.03206464638002217, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.03217207194771618, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.03233646491076797, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.032537175118923185, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.03284750920720399, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.03326353652402759, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.033738881130702794, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.0345370533503592, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.035407790741883216, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.03667280033230782, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.037878632685169576, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.0389449500432238, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.04014716744888574, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.041143744164146484, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.04172288243193179, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.041767055243253706, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.03844337174436077, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.02505212598363869, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.009137550637824461, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0027830568701028824, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.001100196471379604, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.00047098377319343854, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.00022402661608794005, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.00015007380970928353, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.00010342889381718124, "train/grad_029_lr2.3e+00_wd1.0e+00": 6.32227363257698e-05, "train/grad_030_lr2.7e+00_wd1.0e+00": 5.5387042461916284e-05, "train/grad_031_lr3.1e+00_wd1.0e+00": 4.589691432556719e-05, "train/grad_032_lr3.7e+00_wd1.0e+00": 4.4038810915481005e-05, "train/grad_033_lr4.3e+00_wd1.0e+00": 2.825117991051229e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 3.1602471858604984e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 2.7880008435658965e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 2.6921265407509055e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 2.541388781992282e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 4.48930126981395e-05, "train/grad_039_lr1.2e+01_wd1.0e+00": 6.077356005789625e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 2.5629294063946873e-05, "train/grad_041_lr1.6e+01_wd1.0e+00": 7.9344930438765e-05, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.6153377294540405, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.6127610802650452, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.6091016530990601, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.6062220931053162, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.6037277579307556, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.6009446382522583, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.5979037880897522, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.5949556827545166, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.5911502838134766, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.5878708958625793, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.584977388381958, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.5816008448600769, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.5797568559646606, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.5798717141151428, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.5825371146202087, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.5882130861282349, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.6003082990646362, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.625809907913208, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.6771563291549683, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.7576791644096375, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.9311977028846741, "validation/loss_021_lr6.1e-01_wd1.0e+00": 1.242400884628296, "validation/loss_022_lr7.2e-01_wd1.0e+00": 1.6352243423461914, "validation/loss_023_lr8.5e-01_wd1.0e+00": 1.9702553749084473, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.281332492828369, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.5683727264404297, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.571819543838501, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.575176954269409, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.662576675415039, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.8529469966888428, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.074531078338623, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.288504123687744, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.4523468017578125, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.106675148010254, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.8025553226470947, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.3620684146881104, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.1631834506988525, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.896677017211914, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.7608463764190674, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.0019171237945557, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.8275580406188965, "validation/loss_041_lr1.6e+01_wd1.0e+00": 4.760100841522217, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.6931473016738892, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.75, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.75, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.78125, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.765625, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.765625, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.765625, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.765625, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.765625, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.765625, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.765625, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.75, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.75, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.765625, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.734375, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.703125, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.6875, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.671875, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.703125, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.6875, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.6875, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.671875, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.671875, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.609375, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.5625, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.5625, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.5625, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.59375, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.59375, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.578125, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.640625, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.65625, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.609375, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.625, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.59375, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.640625, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.578125, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.625, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.625, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.671875, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.640625, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.65625, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.59375, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.4375, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.4375, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.4375, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.4375, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.4375, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.4375, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.4375, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.7333333333333334, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.7333333333333334, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.7666666666666666, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.7520020666494446, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.7520020666494446, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.7520020666494446, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.747832939322301, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.747832939322301, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.7520020666494446, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.7520020666494446, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.7374358974358974, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.7374358974358974, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.7555385790679909, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.7262893081761006, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.6940880503144654, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.6761133603238867, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.6618867924528302, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.6940880503144654, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.6796796796796797, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.6796796796796797, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.6618867924528302, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.6577540106951871, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.5925642984466514, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.5515515515515516, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.5515515515515516, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.5515515515515516, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.5835835835835836, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.5789473684210527, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.5536037199690003, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.6133438402941949, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.6333333333333333, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.5925642984466514, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.611336032388664, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.5666666666666667, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.619736502195815, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.5652830188679245, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.611336032388664, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.6156156156156156, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.6322845417236662, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.6333748443337484, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.6437246963562753, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.5789473684210527, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.30434782608695654, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.30434782608695654, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.30434782608695654, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.30434782608695654, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.30434782608695654, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.30434782608695654, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.30434782608695654, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.7301587301587301, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.7301587301587301, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.7619047619047619, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.748015873015873, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.748015873015873, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.748015873015873, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.7440476190476191, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.7440476190476191, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.748015873015873, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.748015873015873, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.7341269841269842, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.7341269841269842, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.751984126984127, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.7242063492063493, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.6924603174603174, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.6746031746031746, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.6607142857142857, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.6924603174603174, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.6785714285714286, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.6785714285714286, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.6607142857142857, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.6567460317460317, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.5932539682539683, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.5515873015873016, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.5515873015873016, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.5515873015873016, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.5833333333333333, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.5793650793650793, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.5575396825396826, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.6170634920634921, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.6349206349206349, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.5932539682539683, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.6111111111111112, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.5714285714285714, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.621031746031746, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.5654761904761905, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.6111111111111112, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.6150793650793651, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.6408730158730158, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.6329365079365079, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.6428571428571428, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.5793650793650793, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.5, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.5, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.5, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.5, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.5, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.5, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.5, "id_best": 2, "lr_best": 8.4e-06, "wd_best": 0.05, "train/loss_best": 0.618912353515625, "validation/loss_best": 0.6091016530990601, "validation/acc_best": 0.78125, "validation/f1_best": 0.7666666666666666, "validation/bacc_best": 0.7619047619047619} +{"epoch": 17, "train/lr": 2.030750443206766e-05, "train/loss": 0.32574243396520614, "train/grad": 0.16797511842101812, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.635987548828125, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.632694091796875, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.62759033203125, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.62288330078125, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.6184246826171875, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.6124249267578125, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.605804443359375, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.5986859130859375, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.58947509765625, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.5796087646484375, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.5698165893554688, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.5548080444335938, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.539638671875, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.5168724060058594, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.4947257232666016, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.47313671112060546, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.44475790023803713, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.4083041429519653, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.3599810576438904, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.3024722254276276, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.20162458926439286, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.09176062107086182, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.025685129016637803, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.007250656634569168, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.002963823527097702, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.0012990683317184448, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.0006473629176616669, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.00044049426913261413, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.00031346917152404787, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0001936928927898407, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.00016916349530220033, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.0001390784978866577, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.00013235345482826233, "train/loss_033_lr4.3e+00_wd1.0e+00": 8.514463901519775e-05, "train/loss_034_lr5.1e+00_wd1.0e+00": 8.473142981529235e-05, "train/loss_035_lr6.0e+00_wd1.0e+00": 8.300513029098511e-05, "train/loss_036_lr7.1e+00_wd1.0e+00": 7.530584931373596e-05, "train/loss_037_lr8.3e+00_wd1.0e+00": 7.050827145576476e-05, "train/loss_038_lr9.8e+00_wd1.0e+00": 7.951363921165466e-05, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.00011733993887901306, "train/loss_040_lr1.4e+01_wd1.0e+00": 7.276609539985657e-05, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.00015551239252090454, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.69140625, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.69140625, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.69140625, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.69140625, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.69140625, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.69140625, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.69140625, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.031777917777653784, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.031787953560706225, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.031830595028586685, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.03190146585460752, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.03199220835696906, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.032136597875505685, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.032338909804821014, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.03255669576115906, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.032887252736836674, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.03328140920028091, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.033705772361718116, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.03446231370326132, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.03529477177653462, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.03653503656387329, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.037771589090116325, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.03885222708340734, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.04009375941008329, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.04107730897143483, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.041572601068764925, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.041397122628986836, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.03760623375419527, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.024021413875743747, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.008578830090118571, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0026127038203412668, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0010432706568099092, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0004526450901539647, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0002121977994829649, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.00014112153119640424, "train/grad_028_lr1.9e+00_wd1.0e+00": 9.895842857076786e-05, "train/grad_029_lr2.3e+00_wd1.0e+00": 6.157452785373607e-05, "train/grad_030_lr2.7e+00_wd1.0e+00": 5.4780897071395886e-05, "train/grad_031_lr3.1e+00_wd1.0e+00": 4.573823275677569e-05, "train/grad_032_lr3.7e+00_wd1.0e+00": 4.319079597735254e-05, "train/grad_033_lr4.3e+00_wd1.0e+00": 2.697972130135895e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 3.0744369485091735e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 2.6791664447500806e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 2.567004322372668e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 2.4963515775198174e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 4.346274724582599e-05, "train/grad_039_lr1.2e+01_wd1.0e+00": 5.8736122754226016e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 2.4387460287016437e-05, "train/grad_041_lr1.6e+01_wd1.0e+00": 7.9147439952294e-05, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.6154038906097412, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.6127792596817017, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.6091948747634888, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.6064159870147705, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.6037487387657166, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.6006850004196167, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.5977932214736938, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.5950294733047485, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.5915142893791199, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.5879932045936584, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.5852967500686646, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.5820342302322388, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.5805619359016418, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.5808451175689697, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.5837440490722656, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.5893113017082214, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.6017561554908752, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.6274808049201965, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.6801168918609619, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.7644336223602295, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.9434601068496704, "validation/loss_021_lr6.1e-01_wd1.0e+00": 1.2602709531784058, "validation/loss_022_lr7.2e-01_wd1.0e+00": 1.6549545526504517, "validation/loss_023_lr8.5e-01_wd1.0e+00": 1.9834153652191162, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.294173240661621, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.581292152404785, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.5800697803497314, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.580502510070801, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.6669833660125732, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.8576788902282715, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.080002784729004, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.2950778007507324, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.4596059322357178, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.110257148742676, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.80755615234375, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.3685853481292725, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.1682448387145996, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.9022505283355713, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.762407064437866, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.0044264793395996, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.8343355655670166, "validation/loss_041_lr1.6e+01_wd1.0e+00": 4.7563886642456055, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.6931473016738892, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.75, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.765625, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.78125, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.78125, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.765625, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.765625, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.765625, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.765625, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.765625, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.765625, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.765625, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.75, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.765625, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.71875, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.703125, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.6875, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.671875, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.703125, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.6875, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.6875, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.671875, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.671875, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.609375, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.5625, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.5625, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.5625, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.59375, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.59375, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.578125, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.640625, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.65625, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.609375, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.625, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.59375, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.640625, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.578125, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.625, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.625, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.671875, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.640625, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.65625, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.59375, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.4375, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.4375, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.4375, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.4375, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.4375, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.4375, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.4375, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.7333333333333334, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.747832939322301, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.7666666666666666, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.7666666666666666, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.7520020666494446, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.7520020666494446, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.747832939322301, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.747832939322301, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.7520020666494446, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.7520020666494446, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.7520020666494446, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.7374358974358974, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.7555385790679909, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.708502024291498, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.6903488668194551, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.6761133603238867, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.6618867924528302, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.6940880503144654, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.6796796796796797, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.6796796796796797, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.6618867924528302, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.6577540106951871, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.5925642984466514, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.5515515515515516, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.5515515515515516, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.5515515515515516, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.5835835835835836, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.5789473684210527, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.5536037199690003, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.6133438402941949, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.6333333333333333, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.5925642984466514, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.611336032388664, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.5666666666666667, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.619736502195815, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.5652830188679245, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.611336032388664, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.6156156156156156, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.6322845417236662, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.6333748443337484, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.6437246963562753, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.5789473684210527, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.30434782608695654, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.30434782608695654, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.30434782608695654, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.30434782608695654, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.30434782608695654, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.30434782608695654, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.30434782608695654, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.7301587301587301, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.7440476190476191, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.7619047619047619, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.7619047619047619, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.748015873015873, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.748015873015873, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.7440476190476191, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.7440476190476191, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.748015873015873, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.748015873015873, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.748015873015873, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.7341269841269842, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.751984126984127, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.7063492063492063, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.6884920634920635, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.6746031746031746, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.6607142857142857, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.6924603174603174, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.6785714285714286, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.6785714285714286, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.6607142857142857, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.6567460317460317, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.5932539682539683, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.5515873015873016, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.5515873015873016, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.5515873015873016, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.5833333333333333, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.5793650793650793, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.5575396825396826, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.6170634920634921, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.6349206349206349, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.5932539682539683, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.6111111111111112, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.5714285714285714, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.621031746031746, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.5654761904761905, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.6111111111111112, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.6150793650793651, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.6408730158730158, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.6329365079365079, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.6428571428571428, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.5793650793650793, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.5, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.5, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.5, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.5, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.5, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.5, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.5, "id_best": 2, "lr_best": 8.4e-06, "wd_best": 0.05, "train/loss_best": 0.62759033203125, "validation/loss_best": 0.6091948747634888, "validation/acc_best": 0.78125, "validation/f1_best": 0.7666666666666666, "validation/bacc_best": 0.7619047619047619} +{"epoch": 18, "train/lr": 7.5829098008590064e-06, "train/loss": 0.31960577435791493, "train/grad": 0.16695864656940101, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.61989990234375, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.61641357421875, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.610843505859375, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.605809326171875, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.6009210205078125, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.5947320556640625, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.5879339599609374, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.5805743408203125, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.5713470458984375, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.5617144775390625, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.5523681640625, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.5382373046875, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.5242486572265626, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.50349609375, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.483148193359375, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.4631341552734375, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.43646629333496095, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.4015440034866333, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.3544840598106384, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.2969371691346169, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.19379595488309861, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.08632047787308693, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.023450497686862946, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.006598986387252807, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.002667418867349625, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.0011345867812633515, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.0005798093974590301, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.00039108037948608397, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.00028288841247558593, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.000173158198595047, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.00015359774231910706, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.0001275685429573059, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.00013213559985160827, "train/loss_033_lr4.3e+00_wd1.0e+00": 7.932230830192565e-05, "train/loss_034_lr5.1e+00_wd1.0e+00": 8.31151008605957e-05, "train/loss_035_lr6.0e+00_wd1.0e+00": 7.86629319190979e-05, "train/loss_036_lr7.1e+00_wd1.0e+00": 7.109001278877259e-05, "train/loss_037_lr8.3e+00_wd1.0e+00": 6.757855415344238e-05, "train/loss_038_lr9.8e+00_wd1.0e+00": 8.063301444053649e-05, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.000120573490858078, "train/loss_040_lr1.4e+01_wd1.0e+00": 6.527885794639587e-05, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.00013176590204238891, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.69140625, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.69140625, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.69140625, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.69140625, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.69140625, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.69140625, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.69140625, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.03233148231636733, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.032290522339753804, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.03225912047550082, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.03226288169855252, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.03230716454796493, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.03240244660992175, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.03256105367327109, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.03275499619776383, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.033067472162656486, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.03347014477476477, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.03390933999791741, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.03468815890140831, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.035508056073449555, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.03669262126553804, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.03779567764140666, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.03871821126900613, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.03970021699555218, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.04034209196921438, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.0404076615627855, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.03969165359158069, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.034844461306929586, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.021687518467660993, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0076446620241040365, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.002385068575385958, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.000947946298692841, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.00040387135373748606, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.00020087906541448318, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0001348962926203967, "train/grad_028_lr1.9e+00_wd1.0e+00": 9.538136813716847e-05, "train/grad_029_lr2.3e+00_wd1.0e+00": 6.0856992386106865e-05, "train/grad_030_lr2.7e+00_wd1.0e+00": 5.37400389339382e-05, "train/grad_031_lr3.1e+00_wd1.0e+00": 4.392885123706946e-05, "train/grad_032_lr3.7e+00_wd1.0e+00": 4.247426469646598e-05, "train/grad_033_lr4.3e+00_wd1.0e+00": 2.6985846975549066e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 2.9944439988867087e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 2.6023708437605818e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 2.549315500573357e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 2.4552946099447583e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 4.280259513961937e-05, "train/grad_039_lr1.2e+01_wd1.0e+00": 5.7720725653780394e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 2.339798055800202e-05, "train/grad_041_lr1.6e+01_wd1.0e+00": 7.542831806404138e-05, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.6152922511100769, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.6125905513763428, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.609114408493042, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.6061928272247314, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.603706955909729, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.6006721258163452, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.5977055430412292, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.5948810577392578, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.5913323163986206, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.5877889394760132, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.5848639607429504, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.5817084312438965, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.5798120498657227, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.5802186131477356, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.5831055045127869, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.5885416269302368, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.6009775400161743, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.6271622180938721, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.6806725859642029, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.7661867141723633, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.9483475685119629, "validation/loss_021_lr6.1e-01_wd1.0e+00": 1.2677751779556274, "validation/loss_022_lr7.2e-01_wd1.0e+00": 1.6621226072311401, "validation/loss_023_lr8.5e-01_wd1.0e+00": 1.9900434017181396, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.3011465072631836, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.586447238922119, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.5829389095306396, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.58378267288208, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.6704041957855225, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.8604745864868164, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.0848944187164307, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.297985553741455, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.4647321701049805, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.112380266189575, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.8090250492095947, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.3732903003692627, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.171945333480835, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.9048938751220703, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.7621920108795166, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.004333019256592, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.836803674697876, "validation/loss_041_lr1.6e+01_wd1.0e+00": 4.75726842880249, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.6931473016738892, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.75, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.765625, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.78125, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.78125, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.765625, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.765625, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.765625, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.765625, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.765625, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.765625, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.75, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.75, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.765625, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.71875, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.71875, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.6875, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.671875, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.703125, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.6875, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.6875, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.671875, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.671875, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.609375, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.5625, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.5625, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.5625, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.59375, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.59375, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.578125, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.640625, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.65625, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.609375, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.625, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.59375, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.640625, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.578125, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.625, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.625, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.671875, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.640625, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.65625, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.59375, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.4375, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.4375, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.4375, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.4375, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.4375, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.4375, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.4375, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.7333333333333334, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.747832939322301, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.7666666666666666, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.7666666666666666, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.7520020666494446, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.7520020666494446, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.747832939322301, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.747832939322301, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.7520020666494446, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.7520020666494446, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.7374358974358974, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.7374358974358974, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.7555385790679909, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.708502024291498, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.708502024291498, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.6761133603238867, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.6618867924528302, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.6940880503144654, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.6796796796796797, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.6796796796796797, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.6618867924528302, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.6577540106951871, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.5925642984466514, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.5515515515515516, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.5515515515515516, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.5515515515515516, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.5835835835835836, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.5789473684210527, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.5536037199690003, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.6133438402941949, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.6333333333333333, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.5925642984466514, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.611336032388664, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.5666666666666667, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.619736502195815, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.5652830188679245, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.611336032388664, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.6156156156156156, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.6322845417236662, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.6333748443337484, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.6437246963562753, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.5789473684210527, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.30434782608695654, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.30434782608695654, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.30434782608695654, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.30434782608695654, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.30434782608695654, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.30434782608695654, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.30434782608695654, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.7301587301587301, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.7440476190476191, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.7619047619047619, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.7619047619047619, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.748015873015873, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.748015873015873, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.7440476190476191, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.7440476190476191, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.748015873015873, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.748015873015873, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.7341269841269842, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.7341269841269842, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.751984126984127, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.7063492063492063, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.7063492063492063, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.6746031746031746, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.6607142857142857, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.6924603174603174, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.6785714285714286, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.6785714285714286, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.6607142857142857, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.6567460317460317, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.5932539682539683, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.5515873015873016, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.5515873015873016, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.5515873015873016, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.5833333333333333, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.5793650793650793, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.5575396825396826, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.6170634920634921, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.6349206349206349, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.5932539682539683, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.6111111111111112, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.5714285714285714, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.621031746031746, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.5654761904761905, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.6111111111111112, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.6150793650793651, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.6408730158730158, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.6329365079365079, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.6428571428571428, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.5793650793650793, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.5, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.5, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.5, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.5, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.5, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.5, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.5, "id_best": 2, "lr_best": 8.4e-06, "wd_best": 0.05, "train/loss_best": 0.610843505859375, "validation/loss_best": 0.609114408493042, "validation/acc_best": 0.78125, "validation/f1_best": 0.7666666666666666, "validation/bacc_best": 0.7619047619047619} +{"epoch": 19, "train/lr": 1.0867618231465446e-06, "train/loss": 0.31786205753684044, "train/grad": 0.16566294766962528, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.621077880859375, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.61685546875, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.6101708984375, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.604302978515625, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.5986505126953126, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.59157470703125, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.5840264892578125, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.5758929443359375, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.56575927734375, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.555439453125, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.5453436279296875, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.53002197265625, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.5154360961914063, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.49439056396484377, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.47466842651367186, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.4556779479980469, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.43063011169433596, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.39805216789245607, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.3536210918426514, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.29825204610824585, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.19550497323274613, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.08456408202648164, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.02282802328467369, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.0064932449162006375, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.00259985014796257, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.001115037053823471, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.0005383330583572387, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0003698042035102844, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.00026661977171897887, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.00016387835144996644, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0001416832208633423, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.00011878177523612977, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.00011251330375671387, "train/loss_033_lr4.3e+00_wd1.0e+00": 7.066816091537476e-05, "train/loss_034_lr5.1e+00_wd1.0e+00": 7.629439234733581e-05, "train/loss_035_lr6.0e+00_wd1.0e+00": 7.104679942131042e-05, "train/loss_036_lr7.1e+00_wd1.0e+00": 6.539344787597656e-05, "train/loss_037_lr8.3e+00_wd1.0e+00": 5.8899223804473875e-05, "train/loss_038_lr9.8e+00_wd1.0e+00": 6.978273391723633e-05, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.00011302545666694641, "train/loss_040_lr1.4e+01_wd1.0e+00": 6.822988390922546e-05, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.00014248713850975036, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.69140625, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.69140625, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.69140625, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.69140625, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.69140625, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.69140625, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.69140625, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.031510360604152084, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.031541124773211776, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.0315879386710003, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.03165743114426732, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.031746826875023546, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.03188668590970337, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.03207897230517119, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.032300585419870916, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.032639018644113095, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.03307414251379669, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.03354614617303014, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.034401389558333904, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.03531414533732459, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.03669223569566384, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.037964168447069825, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.039003207152709364, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.04008683800231665, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.0407579282252118, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.04074540159665048, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.03990033440291882, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.03489448721986264, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.021564213128294797, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.00762718046142254, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0023658344690920784, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0009562071747495793, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0004136577283134102, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.00019691252240590983, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.00013438734164083143, "train/grad_028_lr1.9e+00_wd1.0e+00": 9.740043733472704e-05, "train/grad_029_lr2.3e+00_wd1.0e+00": 6.107696608523839e-05, "train/grad_030_lr2.7e+00_wd1.0e+00": 5.349883871531347e-05, "train/grad_031_lr3.1e+00_wd1.0e+00": 4.5647312522305586e-05, "train/grad_032_lr3.7e+00_wd1.0e+00": 4.232287920331146e-05, "train/grad_033_lr4.3e+00_wd1.0e+00": 2.6909967452866112e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 2.991677211866772e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 2.608055917562524e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 2.528787420487788e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 2.426640720386786e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 4.2673904864471976e-05, "train/grad_039_lr1.2e+01_wd1.0e+00": 5.6838420381382096e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 2.338608302125067e-05, "train/grad_041_lr1.6e+01_wd1.0e+00": 7.528570251565725e-05, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.6153285503387451, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.6125882267951965, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.6090863347053528, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.6061928868293762, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.6037914156913757, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.6006465554237366, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.5976036190986633, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.5949249863624573, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.5912755727767944, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.587841272354126, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.5849877595901489, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.5818031430244446, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.580310583114624, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.5805314779281616, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.5832655429840088, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.5887097716331482, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.601408839225769, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.6277391910552979, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.6814342737197876, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.7667586803436279, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.9494302868843079, "validation/loss_021_lr6.1e-01_wd1.0e+00": 1.26950204372406, "validation/loss_022_lr7.2e-01_wd1.0e+00": 1.6634702682495117, "validation/loss_023_lr8.5e-01_wd1.0e+00": 1.9911377429962158, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.3020119667053223, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.5874216556549072, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.582756996154785, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.585045337677002, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.6717042922973633, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.861889362335205, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.086092472076416, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.2983407974243164, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.465491533279419, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.112617254257202, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.809730052947998, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.373492479324341, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.17189359664917, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.905451774597168, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.761880874633789, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.0047242641448975, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.83856463432312, "validation/loss_041_lr1.6e+01_wd1.0e+00": 4.757399082183838, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.6931473016738892, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.75, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.765625, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.78125, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.78125, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.765625, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.765625, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.765625, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.765625, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.765625, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.765625, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.765625, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.75, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.765625, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.71875, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.703125, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.6875, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.6875, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.703125, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.6875, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.6875, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.671875, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.671875, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.609375, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.5625, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.5625, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.5625, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.59375, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.59375, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.578125, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.640625, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.65625, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.609375, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.625, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.59375, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.640625, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.578125, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.625, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.625, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.671875, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.640625, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.65625, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.59375, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.4375, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.4375, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.4375, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.4375, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.4375, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.4375, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.4375, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.7333333333333334, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.747832939322301, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.7666666666666666, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.7666666666666666, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.7520020666494446, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.7520020666494446, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.747832939322301, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.747832939322301, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.7520020666494446, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.7520020666494446, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.7520020666494446, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.7374358974358974, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.7555385790679909, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.708502024291498, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.6903488668194551, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.6761133603238867, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.6761133603238867, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.6940880503144654, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.6796796796796797, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.6796796796796797, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.6618867924528302, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.6577540106951871, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.5925642984466514, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.5515515515515516, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.5515515515515516, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.5515515515515516, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.5835835835835836, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.5789473684210527, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.5536037199690003, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.6133438402941949, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.6333333333333333, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.5925642984466514, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.611336032388664, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.5666666666666667, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.619736502195815, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.5652830188679245, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.611336032388664, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.6156156156156156, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.6322845417236662, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.6333748443337484, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.6437246963562753, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.5789473684210527, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.30434782608695654, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.30434782608695654, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.30434782608695654, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.30434782608695654, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.30434782608695654, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.30434782608695654, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.30434782608695654, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.7301587301587301, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.7440476190476191, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.7619047619047619, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.7619047619047619, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.748015873015873, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.748015873015873, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.7440476190476191, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.7440476190476191, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.748015873015873, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.748015873015873, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.748015873015873, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.7341269841269842, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.751984126984127, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.7063492063492063, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.6884920634920635, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.6746031746031746, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.6746031746031746, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.6924603174603174, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.6785714285714286, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.6785714285714286, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.6607142857142857, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.6567460317460317, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.5932539682539683, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.5515873015873016, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.5515873015873016, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.5515873015873016, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.5833333333333333, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.5793650793650793, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.5575396825396826, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.6170634920634921, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.6349206349206349, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.5932539682539683, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.6111111111111112, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.5714285714285714, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.621031746031746, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.5654761904761905, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.6111111111111112, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.6150793650793651, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.6408730158730158, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.6329365079365079, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.6428571428571428, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.5793650793650793, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.5, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.5, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.5, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.5, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.5, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.5, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.5, "id_best": 2, "lr_best": 8.4e-06, "wd_best": 0.05, "train/loss_best": 0.6101708984375, "validation/loss_best": 0.6090863347053528, "validation/acc_best": 0.78125, "validation/f1_best": 0.7666666666666666, "validation/bacc_best": 0.7619047619047619} diff --git a/input_space_v3/flat_lr1e-3_1/eval_v2/adhd200_dx__patch__logistic/config.yaml b/input_space_v3/flat_lr1e-3_1/eval_v2/adhd200_dx__patch__logistic/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..87d1f89263eb3ec86950626e6e2633498c3bf45f --- /dev/null +++ b/input_space_v3/flat_lr1e-3_1/eval_v2/adhd200_dx__patch__logistic/config.yaml @@ -0,0 +1,30 @@ +output_root: experiments/input_space_v3/output +name_prefix: eval_logistic +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_1; eval v2 (adhd200_dx patch logistic) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: input_space_v3/flat_lr1e-3_1/eval_v2/adhd200_dx__patch__logistic +model: flat_mae +representation: patch +dataset: adhd200_dx +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/adhd200_dx__patch__logistic +remote_dir: null diff --git a/input_space_v3/flat_lr1e-3_1/eval_v2/adhd200_dx__patch__logistic/eval_table.csv b/input_space_v3/flat_lr1e-3_1/eval_v2/adhd200_dx__patch__logistic/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..2789c02ee9e2f145a3beddf0980ed8199b8b772b --- /dev/null +++ b/input_space_v3/flat_lr1e-3_1/eval_v2/adhd200_dx__patch__logistic/eval_table.csv @@ -0,0 +1,203 @@ +model,repr,clf,dataset,trial,C,split,acc,acc_std,f1,f1_std,bacc,bacc_std +flat_mae,patch,logistic,adhd200_dx,,0.005994842503189409,train,0.736986301369863,0.02210686680122968,0.72473604826546,0.023663577831906528,0.7217897050741894,0.023047133294477693 +flat_mae,patch,logistic,adhd200_dx,,0.005994842503189409,test,0.6461538461538462,0.055188541817382655,0.6167649320687003,0.06236840768762398,0.6196911196911197,0.057498034391689316 +flat_mae,patch,logistic,adhd200_dx,1,0.005994842503189409,train,0.7342465753424657,0.02131112334515273,0.721529640320589,0.022940409865546785,0.7186450509861391,0.022334565908782227 +flat_mae,patch,logistic,adhd200_dx,1,0.005994842503189409,test,0.5692307692307692,0.057030053324966475,0.5565302144249512,0.05846364318275646,0.5564671814671815,0.05758818871724876 +flat_mae,patch,logistic,adhd200_dx,2,0.046415888336127774,train,0.8191780821917808,0.01992808161502117,0.8152834008097165,0.020506274811823225,0.8139769188496062,0.020624491108043357 +flat_mae,patch,logistic,adhd200_dx,2,0.046415888336127774,test,0.6307692307692307,0.06107731059749181,0.6153846153846154,0.0646001916713054,0.6148648648648649,0.0627834935726728 +flat_mae,patch,logistic,adhd200_dx,3,0.005994842503189409,train,0.736986301369863,0.023984166917228013,0.7272387594968239,0.02522813122576137,0.724659583562313,0.024891754328264445 +flat_mae,patch,logistic,adhd200_dx,3,0.005994842503189409,test,0.5538461538461539,0.057277367299254665,0.5167905665214048,0.06237050928721482,0.5255791505791506,0.05802576577732097 +flat_mae,patch,logistic,adhd200_dx,4,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adhd200_dx,4,166.81005372000556,test,0.6461538461538462,0.05888631912321959,0.6375757575757576,0.060965838472192266,0.6370656370656371,0.06040203328770341 +flat_mae,patch,logistic,adhd200_dx,5,0.005994842503189409,train,0.7616438356164383,0.022221731184499993,0.7540831261761494,0.02351382334926847,0.751526531110704,0.023426746882766834 +flat_mae,patch,logistic,adhd200_dx,5,0.005994842503189409,test,0.5538461538461539,0.060532352345447245,0.5500119360229172,0.06108462540450254,0.5516409266409266,0.06178934530054559 +flat_mae,patch,logistic,adhd200_dx,6,0.005994842503189409,train,0.7315068493150685,0.022459253988008583,0.7196708463949844,0.02384137661754196,0.7169353361421505,0.023262844731275097 +flat_mae,patch,logistic,adhd200_dx,6,0.005994842503189409,test,0.7076923076923077,0.05605491812636824,0.7006060606060607,0.058021802501924034,0.6998069498069499,0.05760684942049024 +flat_mae,patch,logistic,adhd200_dx,7,0.046415888336127774,train,0.8246575342465754,0.018733216044608876,0.8196194712132444,0.019537290568089703,0.8166788789155524,0.019649674773669357 +flat_mae,patch,logistic,adhd200_dx,7,0.046415888336127774,test,0.5846153846153846,0.056394846380009335,0.5644080416976918,0.059206475922165984,0.5656370656370656,0.05718639485720542 +flat_mae,patch,logistic,adhd200_dx,8,10000.0,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adhd200_dx,8,10000.0,test,0.5230769230769231,0.061997243687538804,0.521263958184842,0.061904911362818234,0.5246138996138996,0.06233668231192845 +flat_mae,patch,logistic,adhd200_dx,9,0.005994842503189409,train,0.7589041095890411,0.02334008605787404,0.751976772918211,0.02407970776676991,0.7498168162667155,0.023921902435657425 +flat_mae,patch,logistic,adhd200_dx,9,0.005994842503189409,test,0.6153846153846154,0.06175993990860737,0.6018132810585641,0.06449627806797452,0.6013513513513513,0.06310811970499651 +flat_mae,patch,logistic,adhd200_dx,10,0.3593813663804626,train,0.9643835616438357,0.009445342067416146,0.9635865519649449,0.009721253507228488,0.9612719057214386,0.010297439992730063 +flat_mae,patch,logistic,adhd200_dx,10,0.3593813663804626,test,0.5076923076923077,0.06265071768172734,0.4980694980694981,0.0633051524790109,0.4980694980694981,0.06305204665354289 +flat_mae,patch,logistic,adhd200_dx,11,0.005994842503189409,train,0.7287671232876712,0.021324366039273446,0.7157879834199825,0.023052664396493,0.7130732124320693,0.022384566931022153 +flat_mae,patch,logistic,adhd200_dx,11,0.005994842503189409,test,0.5692307692307692,0.05839659550747719,0.5512820512820513,0.061063217726435706,0.5521235521235521,0.05922848616285002 +flat_mae,patch,logistic,adhd200_dx,12,0.005994842503189409,train,0.7643835616438356,0.021869162454618698,0.7566666666666667,0.022763524658556866,0.7539537155767234,0.022527204993019096 +flat_mae,patch,logistic,adhd200_dx,12,0.005994842503189409,test,0.6153846153846154,0.05730516256677695,0.5905769715293525,0.06376911927964216,0.5926640926640927,0.05966650454813879 +flat_mae,patch,logistic,adhd200_dx,13,0.000774263682681127,train,0.6931506849315069,0.022299333487183035,0.6737534316542169,0.024621696718383088,0.6729101789094462,0.023335048679786134 +flat_mae,patch,logistic,adhd200_dx,13,0.000774263682681127,test,0.6,0.05722159562540318,0.5775,0.061777789960338815,0.5791505791505791,0.05871631637500129 +flat_mae,patch,logistic,adhd200_dx,14,0.046415888336127774,train,0.8273972602739726,0.01933224845593935,0.8226036644165864,0.02014130046500072,0.8198235330036027,0.02029993956154053 +flat_mae,patch,logistic,adhd200_dx,14,0.046415888336127774,test,0.6153846153846154,0.056751833898893295,0.5905769715293525,0.06291956490580695,0.5926640926640927,0.05927875561539454 +flat_mae,patch,logistic,adhd200_dx,15,0.005994842503189409,train,0.7534246575342466,0.022288290062217463,0.7448266219239373,0.023328176422004514,0.7420925688465531,0.023020253586112944 +flat_mae,patch,logistic,adhd200_dx,15,0.005994842503189409,test,0.6153846153846154,0.0601410570705415,0.606060606060606,0.061334677494769466,0.6056949806949807,0.06092306413252225 +flat_mae,patch,logistic,adhd200_dx,16,0.005994842503189409,train,0.7589041095890411,0.020439612874067203,0.7510077519379845,0.02139202471592628,0.7483818770226537,0.02122183091923951 +flat_mae,patch,logistic,adhd200_dx,16,0.005994842503189409,test,0.6,0.06166242130490362,0.5921814671814671,0.06293219270530465,0.5921814671814671,0.06266679919641048 +flat_mae,patch,logistic,adhd200_dx,17,0.046415888336127774,train,0.8273972602739726,0.018944832849275707,0.8226036644165864,0.01951917674003299,0.8198235330036027,0.01946599603547941 +flat_mae,patch,logistic,adhd200_dx,17,0.046415888336127774,test,0.5230769230769231,0.05912558092337552,0.49987589972697943,0.0626245707761221,0.502895752895753,0.05990240558996929 +flat_mae,patch,logistic,adhd200_dx,18,0.005994842503189409,train,0.726027397260274,0.022365812449423778,0.7146118721461188,0.02373495256078271,0.7120809672101117,0.02320578709368965 +flat_mae,patch,logistic,adhd200_dx,18,0.005994842503189409,test,0.6307692307692307,0.057991070522581574,0.6153846153846154,0.06119687847692137,0.6148648648648649,0.05938303406935956 +flat_mae,patch,logistic,adhd200_dx,19,0.005994842503189409,train,0.7397260273972602,0.02305446877898466,0.7279303878414111,0.024494396909008002,0.7249343591622397,0.023902720185431218 +flat_mae,patch,logistic,adhd200_dx,19,0.005994842503189409,test,0.6615384615384615,0.05848241732430932,0.6474358974358974,0.06175183841855442,0.6462355212355213,0.060207361471745754 +flat_mae,patch,logistic,adhd200_dx,20,0.000774263682681127,train,0.6794520547945205,0.022337824870972165,0.6615254143252305,0.024323248314686644,0.6607742565793491,0.023267901338637768 +flat_mae,patch,logistic,adhd200_dx,20,0.000774263682681127,test,0.6153846153846154,0.05895561262810378,0.6018132810585641,0.061800283214614844,0.6013513513513513,0.06059439258286527 +flat_mae,patch,logistic,adhd200_dx,21,0.046415888336127774,train,0.8246575342465754,0.018789794525416577,0.8192733799591508,0.019537066848109248,0.8159614092935215,0.019503854917460962 +flat_mae,patch,logistic,adhd200_dx,21,0.046415888336127774,test,0.676923076923077,0.05643022397186452,0.6690909090909091,0.05837607882387025,0.6684362934362934,0.0581366076018027 +flat_mae,patch,logistic,adhd200_dx,22,0.005994842503189409,train,0.7315068493150685,0.02177938756369547,0.7215562336530079,0.022844703485848033,0.7190877450082432,0.02249030648268085 +flat_mae,patch,logistic,adhd200_dx,22,0.005994842503189409,test,0.5846153846153846,0.06466664633278112,0.578226387887527,0.06608254741354343,0.5786679536679536,0.06623582228848263 +flat_mae,patch,logistic,adhd200_dx,23,0.005994842503189409,train,0.736986301369863,0.02239701545674921,0.7283720930232558,0.023365651866701993,0.7260945228063748,0.023084120621950536 +flat_mae,patch,logistic,adhd200_dx,23,0.005994842503189409,test,0.6,0.052728183182953955,0.5626293995859213,0.059363276830879816,0.5704633204633205,0.05396988089119899 +flat_mae,patch,logistic,adhd200_dx,24,0.046415888336127774,train,0.8054794520547945,0.02087368043277306,0.7993092179138691,0.021821366620754328,0.7961012395432618,0.021788642510676196 +flat_mae,patch,logistic,adhd200_dx,24,0.046415888336127774,test,0.6461538461538462,0.05057151243360718,0.6091503267973856,0.05819852087188557,0.6153474903474904,0.05235163413979055 +flat_mae,patch,logistic,adhd200_dx,25,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adhd200_dx,25,21.54434690031882,test,0.5846153846153846,0.06236529910570765,0.578226387887527,0.06367101221920407,0.5786679536679536,0.06368087931408309 +flat_mae,patch,logistic,adhd200_dx,26,0.005994842503189409,train,0.7342465753424657,0.02194264620036398,0.7234870080677283,0.023380897632379886,0.7207974598522318,0.02291381839830741 +flat_mae,patch,logistic,adhd200_dx,26,0.005994842503189409,test,0.7230769230769231,0.05205712838204404,0.7027439024390244,0.05971381338807358,0.7002895752895753,0.05581980004239406 +flat_mae,patch,logistic,adhd200_dx,27,0.005994842503189409,train,0.7342465753424657,0.021409623004976928,0.7234870080677283,0.023046528281237714,0.7207974598522318,0.022606254198031417 +flat_mae,patch,logistic,adhd200_dx,27,0.005994842503189409,test,0.6,0.056649981068219134,0.588206627680312,0.05851296762370158,0.5878378378378378,0.05756208618144019 +flat_mae,patch,logistic,adhd200_dx,28,0.046415888336127774,train,0.8410958904109589,0.01885945171848287,0.8371237766972364,0.019488897700048222,0.8348293338218233,0.019604613572449834 +flat_mae,patch,logistic,adhd200_dx,28,0.046415888336127774,test,0.5384615384615384,0.05523030640474602,0.5248538011695907,0.057016554702592474,0.525096525096525,0.05605969797487614 +flat_mae,patch,logistic,adhd200_dx,29,0.005994842503189409,train,0.7561643835616438,0.02206628884512549,0.7473969875817451,0.023339873360030156,0.7445197533125725,0.023075392498029604 +flat_mae,patch,logistic,adhd200_dx,29,0.005994842503189409,test,0.5230769230769231,0.05906547164654153,0.4923154446963971,0.06284549463893928,0.4985521235521235,0.05968707845560607 +flat_mae,patch,logistic,adhd200_dx,30,0.000774263682681127,train,0.6958904109589041,0.02222443800383322,0.6797258519695497,0.024416114339817722,0.6782072418635892,0.02337100228967046 +flat_mae,patch,logistic,adhd200_dx,30,0.000774263682681127,test,0.46153846153846156,0.060631243532585505,0.4484848484848485,0.061799554288565234,0.4488416988416989,0.06121211173775657 +flat_mae,patch,logistic,adhd200_dx,31,0.005994842503189409,train,0.7424657534246575,0.021997509881422916,0.7334855828983347,0.022986394379420263,0.7309488917384136,0.022651704726062687 +flat_mae,patch,logistic,adhd200_dx,31,0.005994842503189409,test,0.6,0.0596020253021518,0.5775,0.06458294767552464,0.5791505791505791,0.06142982766012953 +flat_mae,patch,logistic,adhd200_dx,32,0.3593813663804626,train,0.9506849315068493,0.011132191591183586,0.9496227456753772,0.011410789168424328,0.9477010441472797,0.01176585654731358 +flat_mae,patch,logistic,adhd200_dx,32,0.3593813663804626,test,0.5230769230769231,0.06243557626411365,0.5189782764382908,0.06301545602466557,0.5202702702702703,0.06324433087962135 +flat_mae,patch,logistic,adhd200_dx,33,0.005994842503189409,train,0.7315068493150685,0.0240976956966228,0.7209480122324159,0.025438252079865692,0.7183702753862123,0.02495529657472014 +flat_mae,patch,logistic,adhd200_dx,33,0.005994842503189409,test,0.6153846153846154,0.06017671019343066,0.6139225469232596,0.06040977003595826,0.6187258687258688,0.06084496760893288 +flat_mae,patch,logistic,adhd200_dx,34,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adhd200_dx,34,1291.5496650148827,test,0.5230769230769231,0.060998702091148896,0.5189782764382908,0.06162028261225651,0.5202702702702703,0.061635576407767796 +flat_mae,patch,logistic,adhd200_dx,35,0.005994842503189409,train,0.7397260273972602,0.023413190175578073,0.7279303878414111,0.02495310273873884,0.7249343591622397,0.02432513598788974 +flat_mae,patch,logistic,adhd200_dx,35,0.005994842503189409,test,0.6307692307692307,0.05642345393403486,0.61,0.06139348194558014,0.6105212355212355,0.058396271529567965 +flat_mae,patch,logistic,adhd200_dx,36,0.005994842503189409,train,0.7452054794520548,0.022661182062121508,0.7376353560414589,0.023712522619591368,0.7355284850705257,0.023621590860506532 +flat_mae,patch,logistic,adhd200_dx,36,0.005994842503189409,test,0.6307692307692307,0.05499731246795816,0.6036585365853658,0.06092695318057618,0.6061776061776062,0.056776369262307703 +flat_mae,patch,logistic,adhd200_dx,37,0.000774263682681127,train,0.673972602739726,0.021022894524816003,0.6475147088658957,0.023950537362090338,0.6494626610490322,0.022066968178121073 +flat_mae,patch,logistic,adhd200_dx,37,0.000774263682681127,test,0.6153846153846154,0.05235382580980188,0.5834401435529352,0.060346068917281635,0.5883204633204633,0.054720703795302666 +flat_mae,patch,logistic,adhd200_dx,38,0.005994842503189409,train,0.7506849315068493,0.021839517707211802,0.7417205153925708,0.023009034011906487,0.7389479147585027,0.022717986493990837 +flat_mae,patch,logistic,adhd200_dx,38,0.005994842503189409,test,0.6153846153846154,0.05685997333843323,0.5966741126830479,0.06002274234674323,0.597007722007722,0.057711837019269775 +flat_mae,patch,logistic,adhd200_dx,39,0.005994842503189409,train,0.7616438356164383,0.021950558408597262,0.7530734597709193,0.023044482951553393,0.7500915918666422,0.02276745709772906 +flat_mae,patch,logistic,adhd200_dx,39,0.005994842503189409,test,0.6461538461538462,0.05893232303434893,0.6289401836684041,0.0624022877183475,0.6283783783783784,0.06027785430203463 +flat_mae,patch,logistic,adhd200_dx,40,0.005994842503189409,train,0.7342465753424657,0.022680888396235374,0.7263508552260378,0.02357113343801979,0.7243848079623862,0.02338917057062166 +flat_mae,patch,logistic,adhd200_dx,40,0.005994842503189409,test,0.7230769230769231,0.050488276218375275,0.7027439024390244,0.057814406749156215,0.7002895752895753,0.054086873611829435 +flat_mae,patch,logistic,adhd200_dx,41,0.005994842503189409,train,0.7534246575342466,0.022008767423412016,0.7453488372093022,0.023151222349698145,0.742810038468584,0.02294558863098052 +flat_mae,patch,logistic,adhd200_dx,41,0.005994842503189409,test,0.6,0.06099975749297028,0.5953065134099617,0.06173730091792685,0.5965250965250966,0.06165636094734389 +flat_mae,patch,logistic,adhd200_dx,42,0.005994842503189409,train,0.7479452054794521,0.022561306316145266,0.736833855799373,0.024029896382377795,0.7336508518043597,0.02353557187950186 +flat_mae,patch,logistic,adhd200_dx,42,0.005994842503189409,test,0.5846153846153846,0.06361300153661233,0.5810455956075435,0.06370737080898675,0.583011583011583,0.0636243688415284 +flat_mae,patch,logistic,adhd200_dx,43,0.005994842503189409,train,0.7287671232876712,0.02250487472474421,0.7177857092650011,0.02393652071386515,0.715225621298162,0.023465230028292837 +flat_mae,patch,logistic,adhd200_dx,43,0.005994842503189409,test,0.6307692307692307,0.058054053571604064,0.61,0.06253380112310643,0.6105212355212355,0.059571723255644644 +flat_mae,patch,logistic,adhd200_dx,44,0.005994842503189409,train,0.7534246575342466,0.021122368012956326,0.7431506849315068,0.022478833117306554,0.7399401599804604,0.02204227373768779 +flat_mae,patch,logistic,adhd200_dx,44,0.005994842503189409,test,0.6153846153846154,0.05844359238722634,0.6018132810585641,0.06086477057653474,0.6013513513513513,0.0596477169108376 +flat_mae,patch,logistic,adhd200_dx,45,0.005994842503189409,train,0.7616438356164383,0.021483111234304453,0.7530734597709193,0.022821478752139784,0.7500915918666422,0.02264477708652141 +flat_mae,patch,logistic,adhd200_dx,45,0.005994842503189409,test,0.5692307692307692,0.0583861538258848,0.5376016260162602,0.06436461001417502,0.5434362934362934,0.059904838277729806 +flat_mae,patch,logistic,adhd200_dx,46,0.046415888336127774,train,0.8164383561643835,0.02018097813291519,0.8109846113416963,0.02100347622760571,0.8079623862734322,0.021019036335744496 +flat_mae,patch,logistic,adhd200_dx,46,0.046415888336127774,test,0.6,0.060507823348642555,0.5953065134099617,0.060825207089236645,0.5965250965250966,0.06074034265849366 +flat_mae,patch,logistic,adhd200_dx,47,0.005994842503189409,train,0.7753424657534247,0.022018439533481596,0.7659817351598173,0.023532765259280684,0.7622275141967393,0.023159918634463025 +flat_mae,patch,logistic,adhd200_dx,47,0.005994842503189409,test,0.5384615384615384,0.05964251690266941,0.5125,0.06294422073578794,0.5164092664092664,0.06035136137838817 +flat_mae,patch,logistic,adhd200_dx,48,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adhd200_dx,48,21.54434690031882,test,0.6461538461538462,0.061546799435145766,0.6458185264155414,0.0617382329566013,0.6544401544401545,0.06108288232753081 +flat_mae,patch,logistic,adhd200_dx,49,0.005994842503189409,train,0.7452054794520548,0.021724364841637263,0.7348896056731828,0.02300337312783065,0.7319411369603712,0.022595178841778873 +flat_mae,patch,logistic,adhd200_dx,49,0.005994842503189409,test,0.5538461538461539,0.05543706063914006,0.5250692869740489,0.05932347239519175,0.5299227799227799,0.05613691074492593 +flat_mae,patch,logistic,adhd200_dx,50,0.005994842503189409,train,0.7424657534246575,0.02252835647716049,0.7317351598173516,0.024058043008860223,0.7287964828723209,0.02357784589645989 +flat_mae,patch,logistic,adhd200_dx,50,0.005994842503189409,test,0.6153846153846154,0.058226052039397916,0.6018132810585641,0.06075063875306767,0.6013513513513513,0.05932541001755602 +flat_mae,patch,logistic,adhd200_dx,51,0.000774263682681127,train,0.6794520547945205,0.02470456640838205,0.6692842041679251,0.025624647374978188,0.667948952799658,0.02528033059233077 +flat_mae,patch,logistic,adhd200_dx,51,0.000774263682681127,test,0.5076923076923077,0.061636683152641904,0.48,0.06514522175670766,0.48503861003861004,0.062411912821212695 +flat_mae,patch,logistic,adhd200_dx,52,0.005994842503189409,train,0.7205479452054795,0.022730692379589874,0.7101911819653755,0.023895112531951476,0.7079440679001038,0.02351494741164251 +flat_mae,patch,logistic,adhd200_dx,52,0.005994842503189409,test,0.6923076923076923,0.050537756698047116,0.6697154471544715,0.056854284922725935,0.6689189189189189,0.053228058595478946 +flat_mae,patch,logistic,adhd200_dx,53,0.005994842503189409,train,0.7424657534246575,0.023154882654204234,0.7345577768150028,0.02413991119501665,0.7323838309824754,0.023946545552883464 +flat_mae,patch,logistic,adhd200_dx,53,0.005994842503189409,test,0.5846153846153846,0.052787473859332426,0.5308740978348035,0.06241624762346807,0.5482625482625483,0.054531797873224715 +flat_mae,patch,logistic,adhd200_dx,54,0.005994842503189409,train,0.7479452054794521,0.02148139423704671,0.7407029898690387,0.022387954736923035,0.738673139158576,0.022278538137778473 +flat_mae,patch,logistic,adhd200_dx,54,0.005994842503189409,test,0.6,0.05950282376075071,0.588206627680312,0.06157724154233597,0.5878378378378378,0.06053995159915649 +flat_mae,patch,logistic,adhd200_dx,55,0.005994842503189409,train,0.7452054794520548,0.02331639871935646,0.738129218900675,0.02419143424688771,0.7362459546925566,0.024069022814140046 +flat_mae,patch,logistic,adhd200_dx,55,0.005994842503189409,test,0.5692307692307692,0.059442865014932046,0.5666666666666667,0.05986143274299147,0.5694980694980695,0.06014335314329599 +flat_mae,patch,logistic,adhd200_dx,56,0.046415888336127774,train,0.8191780821917808,0.019611772614181767,0.8136256730828744,0.0204898293259889,0.8103895707394517,0.020554397541015103 +flat_mae,patch,logistic,adhd200_dx,56,0.046415888336127774,test,0.6307692307692307,0.05772224864093291,0.6235521235521235,0.05857203279275898,0.6235521235521235,0.05828805722293264 +flat_mae,patch,logistic,adhd200_dx,57,0.005994842503189409,train,0.7616438356164383,0.022248035582010325,0.7535869759212843,0.023326233921661173,0.7508090614886731,0.023080339458408025 +flat_mae,patch,logistic,adhd200_dx,57,0.005994842503189409,test,0.6153846153846154,0.05509191029435862,0.5905769715293525,0.061266105638531625,0.5926640926640927,0.0571515634346359 +flat_mae,patch,logistic,adhd200_dx,58,0.005994842503189409,train,0.7561643835616438,0.021250032839156458,0.7484298647089345,0.022273681846877398,0.7459546925566343,0.02210899363643342 +flat_mae,patch,logistic,adhd200_dx,58,0.005994842503189409,test,0.6307692307692307,0.05844705083645616,0.6235521235521235,0.05939752276613207,0.6235521235521235,0.05901740993557954 +flat_mae,patch,logistic,adhd200_dx,59,0.005994842503189409,train,0.7315068493150685,0.022910067390562606,0.7215562336530079,0.02393753426648655,0.7190877450082432,0.02353059190327141 +flat_mae,patch,logistic,adhd200_dx,59,0.005994842503189409,test,0.6,0.05855677263393001,0.570630081300813,0.06376628859551649,0.5748069498069498,0.05999070547857539 +flat_mae,patch,logistic,adhd200_dx,60,0.005994842503189409,train,0.7315068493150685,0.02308892857260569,0.7237923152952805,0.023994146364575628,0.7219576234963668,0.023814399810847722 +flat_mae,patch,logistic,adhd200_dx,60,0.005994842503189409,test,0.6307692307692307,0.060519909189324005,0.6153846153846154,0.0635462731011157,0.6148648648648649,0.061910714584818 +flat_mae,patch,logistic,adhd200_dx,61,0.005994842503189409,train,0.7534246575342466,0.02264291721778262,0.7437277663358921,0.023956158605898094,0.7406576296024913,0.02360779500839864 +flat_mae,patch,logistic,adhd200_dx,61,0.005994842503189409,test,0.6,0.061424016658675196,0.5833333333333333,0.0653390287867694,0.5834942084942085,0.06338053402232253 +flat_mae,patch,logistic,adhd200_dx,62,0.005994842503189409,train,0.7452054794520548,0.023233714122928257,0.7365929742606834,0.024249629906863437,0.7340935458264639,0.023924028245398084 +flat_mae,patch,logistic,adhd200_dx,62,0.005994842503189409,test,0.5846153846153846,0.05706194288178232,0.5810455956075435,0.05744929462852472,0.583011583011583,0.057952981920473726 +flat_mae,patch,logistic,adhd200_dx,63,0.005994842503189409,train,0.7424657534246575,0.02347828516465474,0.7355561721543964,0.02431709399379138,0.7338187702265372,0.0242513392349762 +flat_mae,patch,logistic,adhd200_dx,63,0.005994842503189409,test,0.6461538461538462,0.057362594248647016,0.6289401836684041,0.0607991165525109,0.6283783783783784,0.05880371294892321 +flat_mae,patch,logistic,adhd200_dx,64,0.005994842503189409,train,0.7205479452054795,0.021654309239751306,0.7082288401253918,0.023143331792180016,0.7057916590340111,0.022595632610951422 +flat_mae,patch,logistic,adhd200_dx,64,0.005994842503189409,test,0.676923076923077,0.05358569092761005,0.6690909090909091,0.05483491903885424,0.6684362934362934,0.05431984728253862 +flat_mae,patch,logistic,adhd200_dx,65,0.005994842503189409,train,0.7397260273972602,0.02219645545218077,0.7285693038693062,0.023541143545745935,0.7256518287842706,0.02308408813627613 +flat_mae,patch,logistic,adhd200_dx,65,0.005994842503189409,test,0.6923076923076923,0.05564812527079278,0.6794871794871795,0.05880017755853895,0.6776061776061776,0.057362836908692066 +flat_mae,patch,logistic,adhd200_dx,66,0.005994842503189409,train,0.7534246575342466,0.02258431793913933,0.7448266219239373,0.023731858871582256,0.7420925688465531,0.02346512357551632 +flat_mae,patch,logistic,adhd200_dx,66,0.005994842503189409,test,0.6,0.060611479764892236,0.588206627680312,0.062026929240961155,0.5878378378378378,0.06134073130477672 +flat_mae,patch,logistic,adhd200_dx,67,0.046415888336127774,train,0.8164383561643835,0.019336796095595434,0.810233648123288,0.020231517697174174,0.8065274470293704,0.020178982266570555 +flat_mae,patch,logistic,adhd200_dx,67,0.046415888336127774,test,0.6307692307692307,0.05783779808718486,0.6153846153846154,0.06136336365480444,0.6148648648648649,0.05935220008420243 +flat_mae,patch,logistic,adhd200_dx,68,0.000774263682681127,train,0.6684931506849315,0.023314595877572255,0.6449444886605729,0.026256864308498214,0.6460432313610551,0.024443298037742592 +flat_mae,patch,logistic,adhd200_dx,68,0.000774263682681127,test,0.6153846153846154,0.05274822636464078,0.5751633986928104,0.060910793706564985,0.583976833976834,0.05470302695296367 +flat_mae,patch,logistic,adhd200_dx,69,0.005994842503189409,train,0.7698630136986301,0.021714415179993216,0.7618381804623415,0.023004684290959403,0.7588080845087622,0.02285676625986305 +flat_mae,patch,logistic,adhd200_dx,69,0.005994842503189409,test,0.6,0.05670130603882838,0.570630081300813,0.06277919195560008,0.5748069498069498,0.058238041429629045 +flat_mae,patch,logistic,adhd200_dx,70,0.005994842503189409,train,0.7452054794520548,0.022203112953089625,0.7354763296317943,0.023457964547348886,0.7326586065824021,0.023107235189083326 +flat_mae,patch,logistic,adhd200_dx,70,0.005994842503189409,test,0.5538461538461539,0.06067338888131431,0.5321419707123356,0.0645414462802145,0.5342664092664092,0.062156289621645065 +flat_mae,patch,logistic,adhd200_dx,71,0.005994842503189409,train,0.7452054794520548,0.02136513822021928,0.734283634314163,0.022841297933973423,0.7312236673383403,0.022367607191545562 +flat_mae,patch,logistic,adhd200_dx,71,0.005994842503189409,test,0.6615384615384615,0.05699454972385388,0.6474358974358974,0.06059926701905896,0.6462355212355213,0.05900700227304202 +flat_mae,patch,logistic,adhd200_dx,72,0.005994842503189409,train,0.7397260273972602,0.022357195786038883,0.730928307040483,0.023377650023114697,0.7285217072723942,0.023075934074946035 +flat_mae,patch,logistic,adhd200_dx,72,0.005994842503189409,test,0.6461538461538462,0.05891942949144733,0.6289401836684041,0.06282707331491111,0.6283783783783784,0.060672395975667905 +flat_mae,patch,logistic,adhd200_dx,73,0.000774263682681127,train,0.684931506849315,0.02342432107424789,0.6681844412297135,0.02530460305939831,0.6670635647554497,0.024294367420374354 +flat_mae,patch,logistic,adhd200_dx,73,0.000774263682681127,test,0.5538461538461539,0.061154765353517514,0.5250692869740489,0.06612794524507659,0.5299227799227799,0.06248451917665427 +flat_mae,patch,logistic,adhd200_dx,74,0.005994842503189409,train,0.736986301369863,0.022371767319057396,0.7283720930232558,0.023398278367482872,0.7260945228063748,0.023144852825627504 +flat_mae,patch,logistic,adhd200_dx,74,0.005994842503189409,test,0.6307692307692307,0.06151700395132982,0.6235521235521235,0.06294434749507762,0.6235521235521235,0.06234699624319913 +flat_mae,patch,logistic,adhd200_dx,75,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adhd200_dx,75,21.54434690031882,test,0.46153846153846156,0.06174706183269301,0.4532564287430906,0.06195589714709461,0.4531853281853282,0.06233319939539225 +flat_mae,patch,logistic,adhd200_dx,76,0.005994842503189409,train,0.7589041095890411,0.02258580619318545,0.7504971414367387,0.02368293365828075,0.7476644074006228,0.023385518480010414 +flat_mae,patch,logistic,adhd200_dx,76,0.005994842503189409,test,0.5538461538461539,0.04560701700396552,0.46886446886446886,0.05736867806046821,0.5082046332046332,0.046455993876289896 +flat_mae,patch,logistic,adhd200_dx,77,0.005994842503189409,train,0.7315068493150685,0.021908114979850523,0.7196708463949844,0.0232912380606334,0.7169353361421505,0.022695646239257235 +flat_mae,patch,logistic,adhd200_dx,77,0.005994842503189409,test,0.7076923076923077,0.0500275048608618,0.677124183006536,0.06111047819687928,0.678088803088803,0.05389627049950311 +flat_mae,patch,logistic,adhd200_dx,78,0.005994842503189409,train,0.7643835616438356,0.02221065931320006,0.758493875792454,0.022869609811716696,0.756823594064847,0.022851759583049396 +flat_mae,patch,logistic,adhd200_dx,78,0.005994842503189409,test,0.5692307692307692,0.059257704165438095,0.545,0.06362961991601537,0.5477799227799228,0.060625377137513106 +flat_mae,patch,logistic,adhd200_dx,79,0.005994842503189409,train,0.736986301369863,0.022215563782183315,0.7278150633855331,0.023308010200107757,0.7253770531843439,0.02297865334808946 +flat_mae,patch,logistic,adhd200_dx,79,0.005994842503189409,test,0.6,0.06348624414206806,0.5921814671814671,0.06484062476008548,0.5921814671814671,0.06434023986377421 +flat_mae,patch,logistic,adhd200_dx,80,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adhd200_dx,80,166.81005372000556,test,0.6,0.0606075746628165,0.5953065134099617,0.06137770419848292,0.5965250965250966,0.061576844946997014 +flat_mae,patch,logistic,adhd200_dx,81,0.005994842503189409,train,0.7643835616438356,0.021734175258772078,0.7556513887159049,0.022967637897105424,0.7525187763326616,0.022703169839610893 +flat_mae,patch,logistic,adhd200_dx,81,0.005994842503189409,test,0.6153846153846154,0.0544613211642775,0.5905769715293525,0.059804966626795616,0.5926640926640927,0.05611548040718478 +flat_mae,patch,logistic,adhd200_dx,82,0.005994842503189409,train,0.7178082191780822,0.022612186319842176,0.7063831116595465,0.024024106912998586,0.7040819441900226,0.02351512278307932 +flat_mae,patch,logistic,adhd200_dx,82,0.005994842503189409,test,0.6923076923076923,0.054967756013716194,0.6862934362934363,0.056164106702358045,0.6862934362934363,0.05591368896254493 +flat_mae,patch,logistic,adhd200_dx,83,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adhd200_dx,83,1291.5496650148827,test,0.6,0.06131074020027262,0.5921814671814671,0.06225469873761444,0.5921814671814671,0.06197513059545665 +flat_mae,patch,logistic,adhd200_dx,84,0.005994842503189409,train,0.7397260273972602,0.02269563045960812,0.7303675710142223,0.0236677473948054,0.7278042376503633,0.023299641527674445 +flat_mae,patch,logistic,adhd200_dx,84,0.005994842503189409,test,0.6307692307692307,0.06164019283536567,0.6285714285714286,0.061943213022525125,0.6322393822393823,0.06242084533105582 +flat_mae,patch,logistic,adhd200_dx,85,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adhd200_dx,85,1291.5496650148827,test,0.6,0.06045272983396778,0.588206627680312,0.06262169980838092,0.5878378378378378,0.06169541532519735 +flat_mae,patch,logistic,adhd200_dx,86,0.005994842503189409,train,0.7479452054794521,0.022586378470221272,0.7374429223744292,0.024219925702596377,0.7343683214263906,0.023742372585182876 +flat_mae,patch,logistic,adhd200_dx,86,0.005994842503189409,test,0.5230769230769231,0.05724730943782268,0.47320261437908495,0.06301828353492289,0.48986486486486486,0.05770034684805639 +flat_mae,patch,logistic,adhd200_dx,87,0.005994842503189409,train,0.7205479452054795,0.02330502882532966,0.7101911819653755,0.024386560515931348,0.7079440679001038,0.023968302207005597 +flat_mae,patch,logistic,adhd200_dx,87,0.005994842503189409,test,0.6153846153846154,0.0607692229795516,0.606060606060606,0.06232405681148206,0.6056949806949807,0.06182464459692979 +flat_mae,patch,logistic,adhd200_dx,88,0.005994842503189409,train,0.7205479452054795,0.02322696422570226,0.7101911819653755,0.024451473665403345,0.7079440679001038,0.024072436278364178 +flat_mae,patch,logistic,adhd200_dx,88,0.005994842503189409,test,0.676923076923077,0.05264451735081815,0.6500897205844656,0.060720274376353765,0.6510617760617761,0.05575653872096942 +flat_mae,patch,logistic,adhd200_dx,89,0.046415888336127774,train,0.8410958904109589,0.018842925804674428,0.8371237766972364,0.019422927291929036,0.8348293338218233,0.019510193491784896 +flat_mae,patch,logistic,adhd200_dx,89,0.046415888336127774,test,0.6153846153846154,0.05873209458985132,0.6094688776736361,0.05922455128776054,0.61003861003861,0.05904370801768796 +flat_mae,patch,logistic,adhd200_dx,90,0.005994842503189409,train,0.7095890410958904,0.024367857032796324,0.6988261302777432,0.025608771465977943,0.6968003907919643,0.02512212088227433 +flat_mae,patch,logistic,adhd200_dx,90,0.005994842503189409,test,0.6307692307692307,0.059584327394088435,0.61,0.06472085201494268,0.6105212355212355,0.06149788856627313 +flat_mae,patch,logistic,adhd200_dx,91,0.046415888336127774,train,0.8410958904109589,0.019237958193797915,0.8371237766972364,0.019945274445530917,0.8348293338218233,0.020171946683681677 +flat_mae,patch,logistic,adhd200_dx,91,0.046415888336127774,test,0.5692307692307692,0.05615473971891784,0.5376016260162602,0.061619732450584476,0.5434362934362934,0.057380293324837524 +flat_mae,patch,logistic,adhd200_dx,92,0.005994842503189409,train,0.736986301369863,0.021965085312613562,0.7272387594968239,0.02307168061489656,0.724659583562313,0.02271051462469835 +flat_mae,patch,logistic,adhd200_dx,92,0.005994842503189409,test,0.7076923076923077,0.056908072866654426,0.6888384983623079,0.062345869586531114,0.6867760617760618,0.05938583699833074 +flat_mae,patch,logistic,adhd200_dx,93,0.005994842503189409,train,0.7424657534246575,0.022475550152625045,0.7334855828983347,0.023513536012661217,0.7309488917384136,0.02320315768417121 +flat_mae,patch,logistic,adhd200_dx,93,0.005994842503189409,test,0.6307692307692307,0.05053588332025652,0.587737843551797,0.061186761233571224,0.5974903474903475,0.053061616029203784 +flat_mae,patch,logistic,adhd200_dx,94,0.046415888336127774,train,0.810958904109589,0.01966185222968313,0.8049624793810841,0.020556994030991736,0.8016730780973316,0.020540759725689074 +flat_mae,patch,logistic,adhd200_dx,94,0.046415888336127774,test,0.5846153846153846,0.056459182512154996,0.5501153550371699,0.06363540437686774,0.556949806949807,0.0583276226723968 +flat_mae,patch,logistic,adhd200_dx,95,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adhd200_dx,95,1291.5496650148827,test,0.5538461538461539,0.0575008021554544,0.5321419707123356,0.06085729345999507,0.5342664092664092,0.058545171327462946 +flat_mae,patch,logistic,adhd200_dx,96,0.005994842503189409,train,0.7479452054794521,0.021753123768665433,0.7391561024111359,0.022906275671962174,0.7365207302924833,0.022642133873815886 +flat_mae,patch,logistic,adhd200_dx,96,0.005994842503189409,test,0.6307692307692307,0.06029120653792572,0.6264367816091954,0.06092545572105703,0.627895752895753,0.061078213106392394 +flat_mae,patch,logistic,adhd200_dx,97,0.005994842503189409,train,0.7479452054794521,0.022239806649616976,0.7391561024111359,0.023322873394995433,0.7365207302924833,0.02302702725220748 +flat_mae,patch,logistic,adhd200_dx,97,0.005994842503189409,test,0.5384615384615384,0.05319963518138026,0.4846723044397463,0.061467267066046626,0.5033783783783784,0.05422735714002422 +flat_mae,patch,logistic,adhd200_dx,98,0.005994842503189409,train,0.7178082191780822,0.022132164807904715,0.7057119820898794,0.023447746054687045,0.7033644745679917,0.02287001985250083 +flat_mae,patch,logistic,adhd200_dx,98,0.005994842503189409,test,0.7076923076923077,0.05378633160437345,0.6834145091002307,0.061108399237887544,0.6824324324324325,0.05641554270195684 +flat_mae,patch,logistic,adhd200_dx,99,0.005994842503189409,train,0.7342465753424657,0.023963795799103797,0.7234870080677283,0.025588137064641567,0.7207974598522318,0.025100372174096365 +flat_mae,patch,logistic,adhd200_dx,99,0.005994842503189409,test,0.5846153846153846,0.059634992308981706,0.5644080416976918,0.06267179450839207,0.5656370656370656,0.060452139653714106 +flat_mae,patch,logistic,adhd200_dx,100,0.005994842503189409,train,0.7479452054794521,0.021628879174304165,0.7380328278100231,0.022933801044286956,0.7350857910484215,0.022568488803906283 +flat_mae,patch,logistic,adhd200_dx,100,0.005994842503189409,test,0.6153846153846154,0.055432620221448896,0.5905769715293525,0.0606568042798135,0.5926640926640927,0.05723860296076665 diff --git a/input_space_v3/flat_lr1e-3_1/eval_v2/adhd200_dx__patch__logistic/log.txt b/input_space_v3/flat_lr1e-3_1/eval_v2/adhd200_dx__patch__logistic/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..6da54999b9a7dce9d198f6f7ccadbe9dfb730aa5 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_1/eval_v2/adhd200_dx__patch__logistic/log.txt @@ -0,0 +1,241 @@ +fMRI foundation model logistic probe eval +version: 0.1.dev86+gf97f52698 +sha: bcce2b486277d3a5b520775efd9cdf1a2affce36, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-04-08 21:56:39 +config: +output_root: experiments/input_space_v3/output +name_prefix: eval_logistic +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_1; eval v2 (adhd200_dx patch logistic) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: input_space_v3/flat_lr1e-3_1/eval_v2/adhd200_dx__patch__logistic +model: flat_mae +representation: patch +dataset: adhd200_dx +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/adhd200_dx__patch__logistic +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=True, reg_tokens=0, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: adhd200_dx (flat) +train (n=301): +HFDataset( + dataset=Dataset({ + features: ['sub', 'site', 'gender', 'dx', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 301 +}), + labels=['ADHD' 'Control'], + counts=[131 170] +) + +validation (n=64): +HFDataset( + dataset=Dataset({ + features: ['sub', 'site', 'gender', 'dx', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 64 +}), + labels=['ADHD' 'Control'], + counts=[28 36] +) + +test (n=65): +HFDataset( + dataset=Dataset({ + features: ['sub', 'site', 'gender', 'dx', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 65 +}), + labels=['ADHD' 'Control'], + counts=[28 37] +) + +extracting features for all splits +extract (train) [ 0/151] eta: 0:13:16 time: 5.2728 data: 4.4344 max mem: 2698 +extract (train) [ 20/151] eta: 0:01:02 time: 0.2408 data: 0.0960 max mem: 2851 +extract (train) [ 40/151] eta: 0:00:38 time: 0.1988 data: 0.0705 max mem: 2851 +extract (train) [ 60/151] eta: 0:00:26 time: 0.1843 data: 0.0600 max mem: 2851 +extract (train) [ 80/151] eta: 0:00:19 time: 0.2033 data: 0.0697 max mem: 2851 +extract (train) [100/151] eta: 0:00:12 time: 0.1914 data: 0.0640 max mem: 2851 +extract (train) [120/151] eta: 0:00:07 time: 0.1965 data: 0.0689 max mem: 2851 +extract (train) [140/151] eta: 0:00:02 time: 0.1783 data: 0.0582 max mem: 2851 +extract (train) [150/151] eta: 0:00:00 time: 0.1751 data: 0.0583 max mem: 2851 +extract (train) Total time: 0:00:35 (0.2331 s / it) +extract (validation) [ 0/32] eta: 0:02:37 time: 4.9312 data: 4.7836 max mem: 2851 +extract (validation) [20/32] eta: 0:00:05 time: 0.2051 data: 0.0692 max mem: 2851 +extract (validation) [31/32] eta: 0:00:00 time: 0.1696 data: 0.0502 max mem: 2851 +extract (validation) Total time: 0:00:11 (0.3554 s / it) +extract (test) [ 0/33] eta: 0:02:33 time: 4.6636 data: 4.3942 max mem: 2851 +extract (test) [20/33] eta: 0:00:05 time: 0.2007 data: 0.0659 max mem: 2851 +extract (test) [32/33] eta: 0:00:00 time: 0.1812 data: 0.0586 max mem: 2851 +extract (test) Total time: 0:00:11 (0.3382 s / it) +feature extraction time: 0:00:57 +train features: (301, 768) +validation features: (64, 768) +test features: (65, 768) +evaluating fixed splits +eval results (fixed splits): + +| model | repr | clf | dataset | trial | C | split | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:-----------|:--------|----------:|:--------|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | adhd200_dx | | 0.0059948 | train | 0.73699 | 0.022107 | 0.72474 | 0.023664 | 0.72179 | 0.023047 | +| flat_mae | patch | logistic | adhd200_dx | | 0.0059948 | test | 0.64615 | 0.055189 | 0.61676 | 0.062368 | 0.61969 | 0.057498 | + + +evaluating random splits (n=100) +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 1, "C": 0.005994842503189409, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.057030053324966475, "f1": 0.5565302144249512, "f1_std": 0.05846364318275646, "bacc": 0.5564671814671815, "bacc_std": 0.05758818871724876} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 2, "C": 0.046415888336127774, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.06107731059749181, "f1": 0.6153846153846154, "f1_std": 0.0646001916713054, "bacc": 0.6148648648648649, "bacc_std": 0.0627834935726728} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 3, "C": 0.005994842503189409, "split": "test", "acc": 0.5538461538461539, "acc_std": 0.057277367299254665, "f1": 0.5167905665214048, "f1_std": 0.06237050928721482, "bacc": 0.5255791505791506, "bacc_std": 0.05802576577732097} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 4, "C": 166.81005372000556, "split": "test", "acc": 0.6461538461538462, "acc_std": 0.05888631912321959, "f1": 0.6375757575757576, "f1_std": 0.060965838472192266, "bacc": 0.6370656370656371, "bacc_std": 0.06040203328770341} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 5, "C": 0.005994842503189409, "split": "test", "acc": 0.5538461538461539, "acc_std": 0.060532352345447245, "f1": 0.5500119360229172, "f1_std": 0.06108462540450254, "bacc": 0.5516409266409266, "bacc_std": 0.06178934530054559} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 6, "C": 0.005994842503189409, "split": "test", "acc": 0.7076923076923077, "acc_std": 0.05605491812636824, "f1": 0.7006060606060607, "f1_std": 0.058021802501924034, "bacc": 0.6998069498069499, "bacc_std": 0.05760684942049024} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 7, "C": 0.046415888336127774, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.056394846380009335, "f1": 0.5644080416976918, "f1_std": 0.059206475922165984, "bacc": 0.5656370656370656, "bacc_std": 0.05718639485720542} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 8, "C": 10000.0, "split": "test", "acc": 0.5230769230769231, "acc_std": 0.061997243687538804, "f1": 0.521263958184842, "f1_std": 0.061904911362818234, "bacc": 0.5246138996138996, "bacc_std": 0.06233668231192845} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 9, "C": 0.005994842503189409, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.06175993990860737, "f1": 0.6018132810585641, "f1_std": 0.06449627806797452, "bacc": 0.6013513513513513, "bacc_std": 0.06310811970499651} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 10, "C": 0.3593813663804626, "split": "test", "acc": 0.5076923076923077, "acc_std": 0.06265071768172734, "f1": 0.4980694980694981, "f1_std": 0.0633051524790109, "bacc": 0.4980694980694981, "bacc_std": 0.06305204665354289} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 11, "C": 0.005994842503189409, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.05839659550747719, "f1": 0.5512820512820513, "f1_std": 0.061063217726435706, "bacc": 0.5521235521235521, "bacc_std": 0.05922848616285002} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 12, "C": 0.005994842503189409, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.05730516256677695, "f1": 0.5905769715293525, "f1_std": 0.06376911927964216, "bacc": 0.5926640926640927, "bacc_std": 0.05966650454813879} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 13, "C": 0.000774263682681127, "split": "test", "acc": 0.6, "acc_std": 0.05722159562540318, "f1": 0.5775, "f1_std": 0.061777789960338815, "bacc": 0.5791505791505791, "bacc_std": 0.05871631637500129} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 14, "C": 0.046415888336127774, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.056751833898893295, "f1": 0.5905769715293525, "f1_std": 0.06291956490580695, "bacc": 0.5926640926640927, "bacc_std": 0.05927875561539454} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 15, "C": 0.005994842503189409, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.0601410570705415, "f1": 0.606060606060606, "f1_std": 0.061334677494769466, "bacc": 0.6056949806949807, "bacc_std": 0.06092306413252225} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 16, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.06166242130490362, "f1": 0.5921814671814671, "f1_std": 0.06293219270530465, "bacc": 0.5921814671814671, "bacc_std": 0.06266679919641048} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 17, "C": 0.046415888336127774, "split": "test", "acc": 0.5230769230769231, "acc_std": 0.05912558092337552, "f1": 0.49987589972697943, "f1_std": 0.0626245707761221, "bacc": 0.502895752895753, "bacc_std": 0.05990240558996929} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 18, "C": 0.005994842503189409, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.057991070522581574, "f1": 0.6153846153846154, "f1_std": 0.06119687847692137, "bacc": 0.6148648648648649, "bacc_std": 0.05938303406935956} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 19, "C": 0.005994842503189409, "split": "test", "acc": 0.6615384615384615, "acc_std": 0.05848241732430932, "f1": 0.6474358974358974, "f1_std": 0.06175183841855442, "bacc": 0.6462355212355213, "bacc_std": 0.060207361471745754} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 20, "C": 0.000774263682681127, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.05895561262810378, "f1": 0.6018132810585641, "f1_std": 0.061800283214614844, "bacc": 0.6013513513513513, "bacc_std": 0.06059439258286527} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 21, "C": 0.046415888336127774, "split": "test", "acc": 0.676923076923077, "acc_std": 0.05643022397186452, "f1": 0.6690909090909091, "f1_std": 0.05837607882387025, "bacc": 0.6684362934362934, "bacc_std": 0.0581366076018027} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 22, "C": 0.005994842503189409, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.06466664633278112, "f1": 0.578226387887527, "f1_std": 0.06608254741354343, "bacc": 0.5786679536679536, "bacc_std": 0.06623582228848263} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 23, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.052728183182953955, "f1": 0.5626293995859213, "f1_std": 0.059363276830879816, "bacc": 0.5704633204633205, "bacc_std": 0.05396988089119899} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 24, "C": 0.046415888336127774, "split": "test", "acc": 0.6461538461538462, "acc_std": 0.05057151243360718, "f1": 0.6091503267973856, "f1_std": 0.05819852087188557, "bacc": 0.6153474903474904, "bacc_std": 0.05235163413979055} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 25, "C": 21.54434690031882, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.06236529910570765, "f1": 0.578226387887527, "f1_std": 0.06367101221920407, "bacc": 0.5786679536679536, "bacc_std": 0.06368087931408309} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 26, "C": 0.005994842503189409, "split": "test", "acc": 0.7230769230769231, "acc_std": 0.05205712838204404, "f1": 0.7027439024390244, "f1_std": 0.05971381338807358, "bacc": 0.7002895752895753, "bacc_std": 0.05581980004239406} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 27, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.056649981068219134, "f1": 0.588206627680312, "f1_std": 0.05851296762370158, "bacc": 0.5878378378378378, "bacc_std": 0.05756208618144019} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 28, "C": 0.046415888336127774, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.05523030640474602, "f1": 0.5248538011695907, "f1_std": 0.057016554702592474, "bacc": 0.525096525096525, "bacc_std": 0.05605969797487614} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 29, "C": 0.005994842503189409, "split": "test", "acc": 0.5230769230769231, "acc_std": 0.05906547164654153, "f1": 0.4923154446963971, "f1_std": 0.06284549463893928, "bacc": 0.4985521235521235, "bacc_std": 0.05968707845560607} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 30, "C": 0.000774263682681127, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.060631243532585505, "f1": 0.4484848484848485, "f1_std": 0.061799554288565234, "bacc": 0.4488416988416989, "bacc_std": 0.06121211173775657} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 31, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.0596020253021518, "f1": 0.5775, "f1_std": 0.06458294767552464, "bacc": 0.5791505791505791, "bacc_std": 0.06142982766012953} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 32, "C": 0.3593813663804626, "split": "test", "acc": 0.5230769230769231, "acc_std": 0.06243557626411365, "f1": 0.5189782764382908, "f1_std": 0.06301545602466557, "bacc": 0.5202702702702703, "bacc_std": 0.06324433087962135} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 33, "C": 0.005994842503189409, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.06017671019343066, "f1": 0.6139225469232596, "f1_std": 0.06040977003595826, "bacc": 0.6187258687258688, "bacc_std": 0.06084496760893288} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 34, "C": 1291.5496650148827, "split": "test", "acc": 0.5230769230769231, "acc_std": 0.060998702091148896, "f1": 0.5189782764382908, "f1_std": 0.06162028261225651, "bacc": 0.5202702702702703, "bacc_std": 0.061635576407767796} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 35, "C": 0.005994842503189409, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.05642345393403486, "f1": 0.61, "f1_std": 0.06139348194558014, "bacc": 0.6105212355212355, "bacc_std": 0.058396271529567965} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 36, "C": 0.005994842503189409, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.05499731246795816, "f1": 0.6036585365853658, "f1_std": 0.06092695318057618, "bacc": 0.6061776061776062, "bacc_std": 0.056776369262307703} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 37, "C": 0.000774263682681127, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.05235382580980188, "f1": 0.5834401435529352, "f1_std": 0.060346068917281635, "bacc": 0.5883204633204633, "bacc_std": 0.054720703795302666} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 38, "C": 0.005994842503189409, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.05685997333843323, "f1": 0.5966741126830479, "f1_std": 0.06002274234674323, "bacc": 0.597007722007722, "bacc_std": 0.057711837019269775} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 39, "C": 0.005994842503189409, "split": "test", "acc": 0.6461538461538462, "acc_std": 0.05893232303434893, "f1": 0.6289401836684041, "f1_std": 0.0624022877183475, "bacc": 0.6283783783783784, "bacc_std": 0.06027785430203463} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 40, "C": 0.005994842503189409, "split": "test", "acc": 0.7230769230769231, "acc_std": 0.050488276218375275, "f1": 0.7027439024390244, "f1_std": 0.057814406749156215, "bacc": 0.7002895752895753, "bacc_std": 0.054086873611829435} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 41, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.06099975749297028, "f1": 0.5953065134099617, "f1_std": 0.06173730091792685, "bacc": 0.5965250965250966, "bacc_std": 0.06165636094734389} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 42, "C": 0.005994842503189409, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.06361300153661233, "f1": 0.5810455956075435, "f1_std": 0.06370737080898675, "bacc": 0.583011583011583, "bacc_std": 0.0636243688415284} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 43, "C": 0.005994842503189409, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.058054053571604064, "f1": 0.61, "f1_std": 0.06253380112310643, "bacc": 0.6105212355212355, "bacc_std": 0.059571723255644644} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 44, "C": 0.005994842503189409, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.05844359238722634, "f1": 0.6018132810585641, "f1_std": 0.06086477057653474, "bacc": 0.6013513513513513, "bacc_std": 0.0596477169108376} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 45, "C": 0.005994842503189409, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.0583861538258848, "f1": 0.5376016260162602, "f1_std": 0.06436461001417502, "bacc": 0.5434362934362934, "bacc_std": 0.059904838277729806} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 46, "C": 0.046415888336127774, "split": "test", "acc": 0.6, "acc_std": 0.060507823348642555, "f1": 0.5953065134099617, "f1_std": 0.060825207089236645, "bacc": 0.5965250965250966, "bacc_std": 0.06074034265849366} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 47, "C": 0.005994842503189409, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.05964251690266941, "f1": 0.5125, "f1_std": 0.06294422073578794, "bacc": 0.5164092664092664, "bacc_std": 0.06035136137838817} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 48, "C": 21.54434690031882, "split": "test", "acc": 0.6461538461538462, "acc_std": 0.061546799435145766, "f1": 0.6458185264155414, "f1_std": 0.0617382329566013, "bacc": 0.6544401544401545, "bacc_std": 0.06108288232753081} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 49, "C": 0.005994842503189409, "split": "test", "acc": 0.5538461538461539, "acc_std": 0.05543706063914006, "f1": 0.5250692869740489, "f1_std": 0.05932347239519175, "bacc": 0.5299227799227799, "bacc_std": 0.05613691074492593} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 50, "C": 0.005994842503189409, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.058226052039397916, "f1": 0.6018132810585641, "f1_std": 0.06075063875306767, "bacc": 0.6013513513513513, "bacc_std": 0.05932541001755602} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 51, "C": 0.000774263682681127, "split": "test", "acc": 0.5076923076923077, "acc_std": 0.061636683152641904, "f1": 0.48, "f1_std": 0.06514522175670766, "bacc": 0.48503861003861004, "bacc_std": 0.062411912821212695} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 52, "C": 0.005994842503189409, "split": "test", "acc": 0.6923076923076923, "acc_std": 0.050537756698047116, "f1": 0.6697154471544715, "f1_std": 0.056854284922725935, "bacc": 0.6689189189189189, "bacc_std": 0.053228058595478946} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 53, "C": 0.005994842503189409, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.052787473859332426, "f1": 0.5308740978348035, "f1_std": 0.06241624762346807, "bacc": 0.5482625482625483, "bacc_std": 0.054531797873224715} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 54, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.05950282376075071, "f1": 0.588206627680312, "f1_std": 0.06157724154233597, "bacc": 0.5878378378378378, "bacc_std": 0.06053995159915649} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 55, "C": 0.005994842503189409, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.059442865014932046, "f1": 0.5666666666666667, "f1_std": 0.05986143274299147, "bacc": 0.5694980694980695, "bacc_std": 0.06014335314329599} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 56, "C": 0.046415888336127774, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.05772224864093291, "f1": 0.6235521235521235, "f1_std": 0.05857203279275898, "bacc": 0.6235521235521235, "bacc_std": 0.05828805722293264} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 57, "C": 0.005994842503189409, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.05509191029435862, "f1": 0.5905769715293525, "f1_std": 0.061266105638531625, "bacc": 0.5926640926640927, "bacc_std": 0.0571515634346359} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 58, "C": 0.005994842503189409, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.05844705083645616, "f1": 0.6235521235521235, "f1_std": 0.05939752276613207, "bacc": 0.6235521235521235, "bacc_std": 0.05901740993557954} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 59, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.05855677263393001, "f1": 0.570630081300813, "f1_std": 0.06376628859551649, "bacc": 0.5748069498069498, "bacc_std": 0.05999070547857539} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 60, "C": 0.005994842503189409, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.060519909189324005, "f1": 0.6153846153846154, "f1_std": 0.0635462731011157, "bacc": 0.6148648648648649, "bacc_std": 0.061910714584818} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 61, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.061424016658675196, "f1": 0.5833333333333333, "f1_std": 0.0653390287867694, "bacc": 0.5834942084942085, "bacc_std": 0.06338053402232253} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 62, "C": 0.005994842503189409, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.05706194288178232, "f1": 0.5810455956075435, "f1_std": 0.05744929462852472, "bacc": 0.583011583011583, "bacc_std": 0.057952981920473726} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 63, "C": 0.005994842503189409, "split": "test", "acc": 0.6461538461538462, "acc_std": 0.057362594248647016, "f1": 0.6289401836684041, "f1_std": 0.0607991165525109, "bacc": 0.6283783783783784, "bacc_std": 0.05880371294892321} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 64, "C": 0.005994842503189409, "split": "test", "acc": 0.676923076923077, "acc_std": 0.05358569092761005, "f1": 0.6690909090909091, "f1_std": 0.05483491903885424, "bacc": 0.6684362934362934, "bacc_std": 0.05431984728253862} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 65, "C": 0.005994842503189409, "split": "test", "acc": 0.6923076923076923, "acc_std": 0.05564812527079278, "f1": 0.6794871794871795, "f1_std": 0.05880017755853895, "bacc": 0.6776061776061776, "bacc_std": 0.057362836908692066} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 66, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.060611479764892236, "f1": 0.588206627680312, "f1_std": 0.062026929240961155, "bacc": 0.5878378378378378, "bacc_std": 0.06134073130477672} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 67, "C": 0.046415888336127774, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.05783779808718486, "f1": 0.6153846153846154, "f1_std": 0.06136336365480444, "bacc": 0.6148648648648649, "bacc_std": 0.05935220008420243} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 68, "C": 0.000774263682681127, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.05274822636464078, "f1": 0.5751633986928104, "f1_std": 0.060910793706564985, "bacc": 0.583976833976834, "bacc_std": 0.05470302695296367} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 69, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.05670130603882838, "f1": 0.570630081300813, "f1_std": 0.06277919195560008, "bacc": 0.5748069498069498, "bacc_std": 0.058238041429629045} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 70, "C": 0.005994842503189409, "split": "test", "acc": 0.5538461538461539, "acc_std": 0.06067338888131431, "f1": 0.5321419707123356, "f1_std": 0.0645414462802145, "bacc": 0.5342664092664092, "bacc_std": 0.062156289621645065} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 71, "C": 0.005994842503189409, "split": "test", "acc": 0.6615384615384615, "acc_std": 0.05699454972385388, "f1": 0.6474358974358974, "f1_std": 0.06059926701905896, "bacc": 0.6462355212355213, "bacc_std": 0.05900700227304202} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 72, "C": 0.005994842503189409, "split": "test", "acc": 0.6461538461538462, "acc_std": 0.05891942949144733, "f1": 0.6289401836684041, "f1_std": 0.06282707331491111, "bacc": 0.6283783783783784, "bacc_std": 0.060672395975667905} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 73, "C": 0.000774263682681127, "split": "test", "acc": 0.5538461538461539, "acc_std": 0.061154765353517514, "f1": 0.5250692869740489, "f1_std": 0.06612794524507659, "bacc": 0.5299227799227799, "bacc_std": 0.06248451917665427} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 74, "C": 0.005994842503189409, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.06151700395132982, "f1": 0.6235521235521235, "f1_std": 0.06294434749507762, "bacc": 0.6235521235521235, "bacc_std": 0.06234699624319913} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 75, "C": 21.54434690031882, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.06174706183269301, "f1": 0.4532564287430906, "f1_std": 0.06195589714709461, "bacc": 0.4531853281853282, "bacc_std": 0.06233319939539225} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 76, "C": 0.005994842503189409, "split": "test", "acc": 0.5538461538461539, "acc_std": 0.04560701700396552, "f1": 0.46886446886446886, "f1_std": 0.05736867806046821, "bacc": 0.5082046332046332, "bacc_std": 0.046455993876289896} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 77, "C": 0.005994842503189409, "split": "test", "acc": 0.7076923076923077, "acc_std": 0.0500275048608618, "f1": 0.677124183006536, "f1_std": 0.06111047819687928, "bacc": 0.678088803088803, "bacc_std": 0.05389627049950311} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 78, "C": 0.005994842503189409, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.059257704165438095, "f1": 0.545, "f1_std": 0.06362961991601537, "bacc": 0.5477799227799228, "bacc_std": 0.060625377137513106} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 79, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.06348624414206806, "f1": 0.5921814671814671, "f1_std": 0.06484062476008548, "bacc": 0.5921814671814671, "bacc_std": 0.06434023986377421} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 80, "C": 166.81005372000556, "split": "test", "acc": 0.6, "acc_std": 0.0606075746628165, "f1": 0.5953065134099617, "f1_std": 0.06137770419848292, "bacc": 0.5965250965250966, "bacc_std": 0.061576844946997014} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 81, "C": 0.005994842503189409, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.0544613211642775, "f1": 0.5905769715293525, "f1_std": 0.059804966626795616, "bacc": 0.5926640926640927, "bacc_std": 0.05611548040718478} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 82, "C": 0.005994842503189409, "split": "test", "acc": 0.6923076923076923, "acc_std": 0.054967756013716194, "f1": 0.6862934362934363, "f1_std": 0.056164106702358045, "bacc": 0.6862934362934363, "bacc_std": 0.05591368896254493} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 83, "C": 1291.5496650148827, "split": "test", "acc": 0.6, "acc_std": 0.06131074020027262, "f1": 0.5921814671814671, "f1_std": 0.06225469873761444, "bacc": 0.5921814671814671, "bacc_std": 0.06197513059545665} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 84, "C": 0.005994842503189409, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.06164019283536567, "f1": 0.6285714285714286, "f1_std": 0.061943213022525125, "bacc": 0.6322393822393823, "bacc_std": 0.06242084533105582} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 85, "C": 1291.5496650148827, "split": "test", "acc": 0.6, "acc_std": 0.06045272983396778, "f1": 0.588206627680312, "f1_std": 0.06262169980838092, "bacc": 0.5878378378378378, "bacc_std": 0.06169541532519735} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 86, "C": 0.005994842503189409, "split": "test", "acc": 0.5230769230769231, "acc_std": 0.05724730943782268, "f1": 0.47320261437908495, "f1_std": 0.06301828353492289, "bacc": 0.48986486486486486, "bacc_std": 0.05770034684805639} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 87, "C": 0.005994842503189409, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.0607692229795516, "f1": 0.606060606060606, "f1_std": 0.06232405681148206, "bacc": 0.6056949806949807, "bacc_std": 0.06182464459692979} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 88, "C": 0.005994842503189409, "split": "test", "acc": 0.676923076923077, "acc_std": 0.05264451735081815, "f1": 0.6500897205844656, "f1_std": 0.060720274376353765, "bacc": 0.6510617760617761, "bacc_std": 0.05575653872096942} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 89, "C": 0.046415888336127774, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.05873209458985132, "f1": 0.6094688776736361, "f1_std": 0.05922455128776054, "bacc": 0.61003861003861, "bacc_std": 0.05904370801768796} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 90, "C": 0.005994842503189409, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.059584327394088435, "f1": 0.61, "f1_std": 0.06472085201494268, "bacc": 0.6105212355212355, "bacc_std": 0.06149788856627313} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 91, "C": 0.046415888336127774, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.05615473971891784, "f1": 0.5376016260162602, "f1_std": 0.061619732450584476, "bacc": 0.5434362934362934, "bacc_std": 0.057380293324837524} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 92, "C": 0.005994842503189409, "split": "test", "acc": 0.7076923076923077, "acc_std": 0.056908072866654426, "f1": 0.6888384983623079, "f1_std": 0.062345869586531114, "bacc": 0.6867760617760618, "bacc_std": 0.05938583699833074} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 93, "C": 0.005994842503189409, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.05053588332025652, "f1": 0.587737843551797, "f1_std": 0.061186761233571224, "bacc": 0.5974903474903475, "bacc_std": 0.053061616029203784} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 94, "C": 0.046415888336127774, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.056459182512154996, "f1": 0.5501153550371699, "f1_std": 0.06363540437686774, "bacc": 0.556949806949807, "bacc_std": 0.0583276226723968} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 95, "C": 1291.5496650148827, "split": "test", "acc": 0.5538461538461539, "acc_std": 0.0575008021554544, "f1": 0.5321419707123356, "f1_std": 0.06085729345999507, "bacc": 0.5342664092664092, "bacc_std": 0.058545171327462946} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 96, "C": 0.005994842503189409, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.06029120653792572, "f1": 0.6264367816091954, "f1_std": 0.06092545572105703, "bacc": 0.627895752895753, "bacc_std": 0.061078213106392394} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 97, "C": 0.005994842503189409, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.05319963518138026, "f1": 0.4846723044397463, "f1_std": 0.061467267066046626, "bacc": 0.5033783783783784, "bacc_std": 0.05422735714002422} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 98, "C": 0.005994842503189409, "split": "test", "acc": 0.7076923076923077, "acc_std": 0.05378633160437345, "f1": 0.6834145091002307, "f1_std": 0.061108399237887544, "bacc": 0.6824324324324325, "bacc_std": 0.05641554270195684} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 99, "C": 0.005994842503189409, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.059634992308981706, "f1": 0.5644080416976918, "f1_std": 0.06267179450839207, "bacc": 0.5656370656370656, "bacc_std": 0.060452139653714106} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 100, "C": 0.005994842503189409, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.055432620221448896, "f1": 0.5905769715293525, "f1_std": 0.0606568042798135, "bacc": 0.5926640926640927, "bacc_std": 0.05723860296076665} +eval results (random splits): + +| model | repr | clf | dataset | split | n_trials | C | C_std | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:-----------|:--------|-----------:|-------:|--------:|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | adhd200_dx | train | 100 | 155.66 | 1026.5 | 0.77923 | 0.086929 | 0.77079 | 0.090917 | 0.76859 | 0.091383 | +| flat_mae | patch | logistic | adhd200_dx | test | 100 | 155.66 | 1026.5 | 0.60523 | 0.053124 | 0.5867 | 0.056388 | 0.58909 | 0.053904 | + + +done! total time: 0:04:56 diff --git a/input_space_v3/flat_lr1e-3_1/eval_v2/adni_ad_vs_cn__patch__attn/config.yaml b/input_space_v3/flat_lr1e-3_1/eval_v2/adni_ad_vs_cn__patch__attn/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..c388f6486483705652002ce4a983c530102bdb82 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_1/eval_v2/adni_ad_vs_cn__patch__attn/config.yaml @@ -0,0 +1,98 @@ +output_root: experiments/input_space_v3/output +name_prefix: eval_probe +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_1; eval v2 (adni_ad_vs_cn patch attn) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +dataset_kwargs: {} +classifier_kwargs: + embed_dim: null + dropout: 0.0 + xavier_init: true + norm: true +lr_scale_grid: +- 0.02 +- 0.023 +- 0.028 +- 0.033 +- 0.038 +- 0.045 +- 0.053 +- 0.062 +- 0.074 +- 0.087 +- 0.1 +- 0.12 +- 0.14 +- 0.17 +- 0.2 +- 0.23 +- 0.27 +- 0.32 +- 0.38 +- 0.44 +- 0.52 +- 0.61 +- 0.72 +- 0.85 +- 1 +- 1.2 +- 1.4 +- 1.6 +- 1.9 +- 2.3 +- 2.7 +- 3.1 +- 3.7 +- 4.3 +- 5.1 +- 6 +- 7.1 +- 8.3 +- 9.8 +- 12 +- 14 +- 16 +- 19 +- 22 +- 26 +- 31 +- 36 +- 43 +- 50 +wd_scale_grid: +- 1.0 +num_workers: 8 +prefetch_factor: null +balanced_sampling: false +epochs: 20 +steps_per_epoch: 200 +batch_size: 4 +accum_iter: 4 +lr: 0.0003 +warmup_epochs: 5 +no_decay: false +weight_decay: 0.05 +clip_grad: 1.0 +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +early_stopping: true +amp: true +device: cuda +seed: 4466 +debug: false +wandb: false +wandb_entity: null +wandb_project: fMRI-fm-eval +name: input_space_v3/flat_lr1e-3_1/eval_v2/adni_ad_vs_cn__patch__attn +base_lr: 3.0e-05 +model: flat_mae +representation: patch +classifier: attn +dataset: adni_ad_vs_cn +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/adni_ad_vs_cn__patch__attn +remote_dir: null diff --git a/input_space_v3/flat_lr1e-3_1/eval_v2/adni_ad_vs_cn__patch__attn/eval_log.json b/input_space_v3/flat_lr1e-3_1/eval_v2/adni_ad_vs_cn__patch__attn/eval_log.json new file mode 100644 index 0000000000000000000000000000000000000000..58e25a62a2ccf5e403a8df0683279361b5b9ddaa --- /dev/null +++ b/input_space_v3/flat_lr1e-3_1/eval_v2/adni_ad_vs_cn__patch__attn/eval_log.json @@ -0,0 +1 @@ +{"eval/epoch": 3, "eval/id_best": 23, "eval/lr_best": 0.00025499999999999996, "eval/wd_best": 0.05, "eval/train/loss": 0.3775363862514496, "eval/train/acc": 0.8353658536585366, "eval/train/acc_std": 0.020288735068313614, "eval/train/f1": 0.7729230769230769, "eval/train/f1_std": 0.02729139864647517, "eval/train/bacc": 0.7753919387385523, "eval/train/bacc_std": 0.02859064756993785, "eval/validation/loss": 0.5280576944351196, "eval/validation/acc": 0.7560975609756098, "eval/validation/acc_std": 0.06598188059103473, "eval/validation/f1": 0.6893939393939394, "eval/validation/f1_std": 0.08020635986334625, "eval/validation/bacc": 0.7032258064516128, "eval/validation/bacc_std": 0.08557345148078968, "eval/test/loss": 0.6293800473213196, "eval/test/acc": 0.6097560975609756, "eval/test/acc_std": 0.07080709187199699, "eval/test/f1": 0.5030303030303029, "eval/test/f1_std": 0.07855479531321212, "eval/test/bacc": 0.5104166666666666, "eval/test/bacc_std": 0.08867365679465587} diff --git a/input_space_v3/flat_lr1e-3_1/eval_v2/adni_ad_vs_cn__patch__attn/eval_log_best.json b/input_space_v3/flat_lr1e-3_1/eval_v2/adni_ad_vs_cn__patch__attn/eval_log_best.json new file mode 100644 index 0000000000000000000000000000000000000000..3c607cf7389cd0b87d7193dd053c63ddde6e0606 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_1/eval_v2/adni_ad_vs_cn__patch__attn/eval_log_best.json @@ -0,0 +1 @@ +{"eval/best/epoch": 3, "eval/best/id_best": 23, "eval/best/lr_best": 0.00025499999999999996, "eval/best/wd_best": 0.05, "eval/best/train/loss": 0.3775363862514496, "eval/best/train/acc": 0.8353658536585366, "eval/best/train/acc_std": 0.020288735068313614, "eval/best/train/f1": 0.7729230769230769, "eval/best/train/f1_std": 0.02729139864647517, "eval/best/train/bacc": 0.7753919387385523, "eval/best/train/bacc_std": 0.02859064756993785, "eval/best/validation/loss": 0.5280576944351196, "eval/best/validation/acc": 0.7560975609756098, "eval/best/validation/acc_std": 0.06598188059103473, "eval/best/validation/f1": 0.6893939393939394, "eval/best/validation/f1_std": 0.08020635986334625, "eval/best/validation/bacc": 0.7032258064516128, "eval/best/validation/bacc_std": 0.08557345148078968, "eval/best/test/loss": 0.6293800473213196, "eval/best/test/acc": 0.6097560975609756, "eval/best/test/acc_std": 0.07080709187199699, "eval/best/test/f1": 0.5030303030303029, "eval/best/test/f1_std": 0.07855479531321212, "eval/best/test/bacc": 0.5104166666666666, "eval/best/test/bacc_std": 0.08867365679465587} diff --git a/input_space_v3/flat_lr1e-3_1/eval_v2/adni_ad_vs_cn__patch__attn/eval_log_last.json b/input_space_v3/flat_lr1e-3_1/eval_v2/adni_ad_vs_cn__patch__attn/eval_log_last.json new file mode 100644 index 0000000000000000000000000000000000000000..b8952e8925528a88f769a147fffc3a66b6a6d952 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_1/eval_v2/adni_ad_vs_cn__patch__attn/eval_log_last.json @@ -0,0 +1 @@ +{"eval/last/epoch": 19, "eval/last/id_best": 36, "eval/last/lr_best": 0.0021299999999999995, "eval/last/wd_best": 0.05, "eval/last/train/loss": 3.984906288678758e-05, "eval/last/train/acc": 1.0, "eval/last/train/acc_std": 0.0, "eval/last/train/f1": 1.0, "eval/last/train/f1_std": 0.0, "eval/last/train/bacc": 1.0, "eval/last/train/bacc_std": 0.0, "eval/last/validation/loss": 2.4606077671051025, "eval/last/validation/acc": 0.7804878048780488, "eval/last/validation/acc_std": 0.060087008101037995, "eval/last/validation/f1": 0.6917293233082706, "eval/last/validation/f1_std": 0.08601083578073733, "eval/last/validation/bacc": 0.685483870967742, "eval/last/validation/bacc_std": 0.08563186768830702, "eval/last/test/loss": 2.5194590091705322, "eval/last/test/acc": 0.7317073170731707, "eval/last/test/acc_std": 0.05428851911366736, "eval/last/test/f1": 0.5512437810945273, "eval/last/test/f1_std": 0.08349137958485817, "eval/last/test/bacc": 0.5486111111111112, "eval/last/test/bacc_std": 0.07235784408278512} diff --git a/input_space_v3/flat_lr1e-3_1/eval_v2/adni_ad_vs_cn__patch__attn/eval_table.csv b/input_space_v3/flat_lr1e-3_1/eval_v2/adni_ad_vs_cn__patch__attn/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..9bd17ebe0067d7b089bb670b1dd614459fdc1eb7 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_1/eval_v2/adni_ad_vs_cn__patch__attn/eval_table.csv @@ -0,0 +1,4 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std,bacc,bacc_std +flat_mae,patch,attn,adni_ad_vs_cn,best,3,0.00025499999999999996,0.05,23,"[0.85, 1.0]",train,0.3775363862514496,0.8353658536585366,0.020288735068313614,0.7729230769230769,0.02729139864647517,0.7753919387385523,0.02859064756993785 +flat_mae,patch,attn,adni_ad_vs_cn,best,3,0.00025499999999999996,0.05,23,"[0.85, 1.0]",validation,0.5280576944351196,0.7560975609756098,0.06598188059103473,0.6893939393939394,0.08020635986334625,0.7032258064516128,0.08557345148078968 +flat_mae,patch,attn,adni_ad_vs_cn,best,3,0.00025499999999999996,0.05,23,"[0.85, 1.0]",test,0.6293800473213196,0.6097560975609756,0.07080709187199699,0.5030303030303029,0.07855479531321212,0.5104166666666666,0.08867365679465587 diff --git a/input_space_v3/flat_lr1e-3_1/eval_v2/adni_ad_vs_cn__patch__attn/eval_table_best.csv b/input_space_v3/flat_lr1e-3_1/eval_v2/adni_ad_vs_cn__patch__attn/eval_table_best.csv new file mode 100644 index 0000000000000000000000000000000000000000..9bd17ebe0067d7b089bb670b1dd614459fdc1eb7 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_1/eval_v2/adni_ad_vs_cn__patch__attn/eval_table_best.csv @@ -0,0 +1,4 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std,bacc,bacc_std +flat_mae,patch,attn,adni_ad_vs_cn,best,3,0.00025499999999999996,0.05,23,"[0.85, 1.0]",train,0.3775363862514496,0.8353658536585366,0.020288735068313614,0.7729230769230769,0.02729139864647517,0.7753919387385523,0.02859064756993785 +flat_mae,patch,attn,adni_ad_vs_cn,best,3,0.00025499999999999996,0.05,23,"[0.85, 1.0]",validation,0.5280576944351196,0.7560975609756098,0.06598188059103473,0.6893939393939394,0.08020635986334625,0.7032258064516128,0.08557345148078968 +flat_mae,patch,attn,adni_ad_vs_cn,best,3,0.00025499999999999996,0.05,23,"[0.85, 1.0]",test,0.6293800473213196,0.6097560975609756,0.07080709187199699,0.5030303030303029,0.07855479531321212,0.5104166666666666,0.08867365679465587 diff --git a/input_space_v3/flat_lr1e-3_1/eval_v2/adni_ad_vs_cn__patch__attn/eval_table_last.csv b/input_space_v3/flat_lr1e-3_1/eval_v2/adni_ad_vs_cn__patch__attn/eval_table_last.csv new file mode 100644 index 0000000000000000000000000000000000000000..6d10985c9c29d5d6e9f37977ef8bef6e2781c0ae --- /dev/null +++ b/input_space_v3/flat_lr1e-3_1/eval_v2/adni_ad_vs_cn__patch__attn/eval_table_last.csv @@ -0,0 +1,4 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std,bacc,bacc_std +flat_mae,patch,attn,adni_ad_vs_cn,last,19,0.0021299999999999995,0.05,36,"[7.1, 1.0]",train,3.984906288678758e-05,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,attn,adni_ad_vs_cn,last,19,0.0021299999999999995,0.05,36,"[7.1, 1.0]",validation,2.4606077671051025,0.7804878048780488,0.060087008101037995,0.6917293233082706,0.08601083578073733,0.685483870967742,0.08563186768830702 +flat_mae,patch,attn,adni_ad_vs_cn,last,19,0.0021299999999999995,0.05,36,"[7.1, 1.0]",test,2.5194590091705322,0.7317073170731707,0.05428851911366736,0.5512437810945273,0.08349137958485817,0.5486111111111112,0.07235784408278512 diff --git a/input_space_v3/flat_lr1e-3_1/eval_v2/adni_ad_vs_cn__patch__attn/log.txt b/input_space_v3/flat_lr1e-3_1/eval_v2/adni_ad_vs_cn__patch__attn/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..f996bbbd6420b392bbf7525c9a9eaa1d045f9e17 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_1/eval_v2/adni_ad_vs_cn__patch__attn/log.txt @@ -0,0 +1,1196 @@ +fMRI foundation model probe eval +version: 0.1.dev95+g65be98d36 +sha: 28a47a6a336052f679e36c7962a91fe73a2e9637, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-04-24 07:19:05 +config: +output_root: experiments/input_space_v3/output +name_prefix: eval_probe +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_1; eval v2 (adni_ad_vs_cn patch attn) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +dataset_kwargs: {} +classifier_kwargs: + embed_dim: null + dropout: 0.0 + xavier_init: true + norm: true +lr_scale_grid: +- 0.02 +- 0.023 +- 0.028 +- 0.033 +- 0.038 +- 0.045 +- 0.053 +- 0.062 +- 0.074 +- 0.087 +- 0.1 +- 0.12 +- 0.14 +- 0.17 +- 0.2 +- 0.23 +- 0.27 +- 0.32 +- 0.38 +- 0.44 +- 0.52 +- 0.61 +- 0.72 +- 0.85 +- 1 +- 1.2 +- 1.4 +- 1.6 +- 1.9 +- 2.3 +- 2.7 +- 3.1 +- 3.7 +- 4.3 +- 5.1 +- 6 +- 7.1 +- 8.3 +- 9.8 +- 12 +- 14 +- 16 +- 19 +- 22 +- 26 +- 31 +- 36 +- 43 +- 50 +wd_scale_grid: +- 1.0 +num_workers: 8 +prefetch_factor: null +balanced_sampling: false +epochs: 20 +steps_per_epoch: 200 +batch_size: 4 +accum_iter: 4 +lr: 0.0003 +warmup_epochs: 5 +no_decay: false +weight_decay: 0.05 +clip_grad: 1.0 +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +early_stopping: true +amp: true +device: cuda +seed: 4466 +debug: false +wandb: false +wandb_entity: null +wandb_project: fMRI-fm-eval +name: input_space_v3/flat_lr1e-3_1/eval_v2/adni_ad_vs_cn__patch__attn +base_lr: 3.0e-05 +model: flat_mae +representation: patch +classifier: attn +dataset: adni_ad_vs_cn +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/adni_ad_vs_cn__patch__attn +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=True, reg_tokens=0, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: adni_ad_vs_cn (flat) +train (n=328): +ADNIDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'bold', 'mean', 'std'], + num_rows: 525 +}), + labels=[0 1], + counts=[251 77] +) + +validation (n=41): +ADNIDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'bold', 'mean', 'std'], + num_rows: 66 +}), + labels=[0 1], + counts=[31 10] +) + +test (n=41): +ADNIDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'bold', 'mean', 'std'], + num_rows: 66 +}), + labels=[0 1], + counts=[32 9] +) + +running backbone on example batch to get embedding dim +embedding feature dim (patch): 768 +initializing sweep of classifier heads +classifiers: +ModuleList( + (0-48): 49 x AttnPoolClassifier( + (kv): Linear(in_features=768, out_features=1536, bias=True) + (linear): Linear(in_features=768, out_features=2, bias=True) + ) +) +classifier params (train): 58.0M (58.0M) +setting up optimizer +total batch size: 16 = 4 bs per gpu x 4 accum +lr: 3.00e-04 +full schedule: epochs = 20 (steps = 4000) (decay = True) +warmup: epochs = 5 (steps = 1000) +start training for 20 epochs +train: [0] [ 0/800] eta: 0:55:03 lr: nan time: 4.1293 data: 3.4717 max mem: 24352 +train: [0] [ 20/800] eta: 0:08:00 lr: 0.000001 loss: 0.6490 (0.6497) grad: 0.7173 (0.6287) time: 0.4400 data: 0.0048 max mem: 25051 +train: [0] [ 40/800] eta: 0:06:35 lr: 0.000003 loss: 0.6490 (0.6577) grad: 0.5431 (0.5428) time: 0.4212 data: 0.0029 max mem: 25051 +train: [0] [ 60/800] eta: 0:06:02 lr: 0.000004 loss: 0.6490 (0.6602) grad: 0.4914 (0.4806) time: 0.4244 data: 0.0033 max mem: 25051 +train: [0] [ 80/800] eta: 0:05:39 lr: 0.000006 loss: 0.6436 (0.6338) grad: 0.4484 (0.4721) time: 0.4162 data: 0.0029 max mem: 25051 +train: [0] [100/800] eta: 0:05:44 lr: 0.000007 loss: 0.6156 (0.6493) grad: 0.4391 (0.4710) time: 0.5787 data: 0.1710 max mem: 25051 +train: [0] [120/800] eta: 0:05:25 lr: 0.000009 loss: 0.6138 (0.6580) grad: 0.3642 (0.4540) time: 0.4068 data: 0.0023 max mem: 25051 +train: [0] [140/800] eta: 0:05:09 lr: 0.000010 loss: 0.6020 (0.6448) grad: 0.3642 (0.4439) time: 0.4103 data: 0.0033 max mem: 25051 +train: [0] [160/800] eta: 0:04:54 lr: 0.000012 loss: 0.6089 (0.6473) grad: 0.3067 (0.4260) time: 0.4058 data: 0.0030 max mem: 25051 +train: [0] [180/800] eta: 0:04:56 lr: 0.000013 loss: 0.5992 (0.6411) grad: 0.2934 (0.4198) time: 0.6224 data: 0.1746 max mem: 25051 +train: [0] [200/800] eta: 0:04:43 lr: 0.000015 loss: 0.5752 (0.6247) grad: 0.2848 (0.4118) time: 0.4130 data: 0.0027 max mem: 25051 +train: [0] [220/800] eta: 0:04:30 lr: 0.000016 loss: 0.5639 (0.6213) grad: 0.2917 (0.4110) time: 0.4161 data: 0.0034 max mem: 25051 +train: [0] [240/800] eta: 0:04:19 lr: 0.000018 loss: 0.5362 (0.6105) grad: 0.3168 (0.4010) time: 0.4130 data: 0.0029 max mem: 25051 +train: [0] [260/800] eta: 0:04:15 lr: 0.000019 loss: 0.5639 (0.6127) grad: 0.3240 (0.3989) time: 0.6095 data: 0.1722 max mem: 25051 +train: [0] [280/800] eta: 0:04:03 lr: 0.000021 loss: 0.5602 (0.6055) grad: 0.3240 (0.3918) time: 0.4086 data: 0.0027 max mem: 25051 +train: [0] [300/800] eta: 0:03:52 lr: 0.000022 loss: 0.5786 (0.6044) grad: 0.3168 (0.3901) time: 0.4199 data: 0.0032 max mem: 25051 +train: [0] [320/800] eta: 0:03:42 lr: 0.000024 loss: 0.5795 (0.6006) grad: 0.2904 (0.3841) time: 0.4177 data: 0.0031 max mem: 25051 +train: [0] [340/800] eta: 0:03:36 lr: 0.000025 loss: 0.5400 (0.5976) grad: 0.2827 (0.3773) time: 0.5802 data: 0.1741 max mem: 25051 +train: [0] [360/800] eta: 0:03:25 lr: 0.000027 loss: 0.5298 (0.5930) grad: 0.2839 (0.3767) time: 0.4083 data: 0.0026 max mem: 25051 +train: [0] [380/800] eta: 0:03:14 lr: 0.000028 loss: 0.5298 (0.5941) grad: 0.2839 (0.3755) time: 0.4131 data: 0.0030 max mem: 25051 +train: [0] [400/800] eta: 0:03:04 lr: 0.000030 loss: 0.5013 (0.5897) grad: 0.2862 (0.3724) time: 0.4095 data: 0.0030 max mem: 25051 +train: [0] [420/800] eta: 0:02:58 lr: 0.000031 loss: 0.5013 (0.5870) grad: 0.3064 (0.3703) time: 0.6241 data: 0.1791 max mem: 25051 +train: [0] [440/800] eta: 0:02:48 lr: 0.000033 loss: 0.5033 (0.5847) grad: 0.2862 (0.3656) time: 0.4315 data: 0.0024 max mem: 25051 +train: [0] [460/800] eta: 0:02:37 lr: 0.000034 loss: 0.4887 (0.5832) grad: 0.2803 (0.3617) time: 0.4113 data: 0.0033 max mem: 25051 +train: [0] [480/800] eta: 0:02:27 lr: 0.000036 loss: 0.4657 (0.5764) grad: 0.2735 (0.3576) time: 0.4074 data: 0.0029 max mem: 25051 +train: [0] [500/800] eta: 0:02:20 lr: 0.000037 loss: 0.4657 (0.5727) grad: 0.2279 (0.3527) time: 0.5818 data: 0.1783 max mem: 25051 +train: [0] [520/800] eta: 0:02:10 lr: 0.000039 loss: 0.4653 (0.5750) grad: 0.2115 (0.3475) time: 0.4055 data: 0.0018 max mem: 25051 +train: [0] [540/800] eta: 0:02:00 lr: 0.000040 loss: 0.4792 (0.5731) grad: 0.1996 (0.3422) time: 0.4058 data: 0.0027 max mem: 25051 +train: [0] [560/800] eta: 0:01:50 lr: 0.000042 loss: 0.5352 (0.5730) grad: 0.2129 (0.3397) time: 0.4050 data: 0.0030 max mem: 25051 +train: [0] [580/800] eta: 0:01:42 lr: 0.000043 loss: 0.5279 (0.5696) grad: 0.2246 (0.3402) time: 0.5682 data: 0.1718 max mem: 25051 +train: [0] [600/800] eta: 0:01:32 lr: 0.000045 loss: 0.4882 (0.5638) grad: 0.2315 (0.3373) time: 0.4327 data: 0.0035 max mem: 25051 +train: [0] [620/800] eta: 0:01:23 lr: 0.000046 loss: 0.4835 (0.5637) grad: 0.2315 (0.3338) time: 0.4186 data: 0.0033 max mem: 25051 +train: [0] [640/800] eta: 0:01:13 lr: 0.000048 loss: 0.4882 (0.5635) grad: 0.2277 (0.3301) time: 0.4169 data: 0.0032 max mem: 25051 +train: [0] [660/800] eta: 0:01:05 lr: 0.000049 loss: 0.5036 (0.5635) grad: 0.2162 (0.3279) time: 0.6069 data: 0.1752 max mem: 25051 +train: [0] [680/800] eta: 0:00:55 lr: 0.000051 loss: 0.5198 (0.5601) grad: 0.2130 (0.3257) time: 0.4140 data: 0.0025 max mem: 25051 +train: [0] [700/800] eta: 0:00:46 lr: 0.000052 loss: 0.5198 (0.5560) grad: 0.2162 (0.3233) time: 0.4131 data: 0.0032 max mem: 25051 +train: [0] [720/800] eta: 0:00:36 lr: 0.000054 loss: 0.4755 (0.5548) grad: 0.2209 (0.3199) time: 0.4158 data: 0.0031 max mem: 25051 +train: [0] [740/800] eta: 0:00:27 lr: 0.000055 loss: 0.3882 (0.5501) grad: 0.2130 (0.3172) time: 0.5771 data: 0.1729 max mem: 25051 +train: [0] [760/800] eta: 0:00:18 lr: 0.000057 loss: 0.3891 (0.5464) grad: 0.1953 (0.3141) time: 0.4313 data: 0.0023 max mem: 25051 +train: [0] [780/800] eta: 0:00:09 lr: 0.000058 loss: 0.4675 (0.5487) grad: 0.1851 (0.3138) time: 0.4167 data: 0.0031 max mem: 25051 +train: [0] [799/800] eta: 0:00:00 lr: 0.000060 loss: 0.4982 (0.5477) grad: 0.1953 (0.3118) time: 0.4207 data: 0.0031 max mem: 25051 +train: [0] Total time: 0:06:08 (0.4609 s / it) +train: [0] Summary: lr: 0.000060 loss: 0.4982 (0.5477) grad: 0.1953 (0.3118) +eval (validation): [0] [ 0/11] eta: 0:00:39 time: 3.6260 data: 3.4031 max mem: 25051 +eval (validation): [0] [10/11] eta: 0:00:00 time: 0.5707 data: 0.3120 max mem: 25051 +eval (validation): [0] Total time: 0:00:06 (0.5858 s / it) +cv: [0] best hparam: (5.1, 1.0) (034) ('034_lr5.1e+00_wd1.0e+00') loss: 0.495 acc: 0.805 f1: 0.655 bacc: 0.634 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/adni_ad_vs_cn__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/adni_ad_vs_cn__patch__attn/checkpoint-best.pth +train: [1] [ 0/800] eta: 0:46:55 lr: nan time: 3.5190 data: 3.1564 max mem: 25051 +train: [1] [ 20/800] eta: 0:07:19 lr: 0.000061 loss: 0.5365 (0.6055) grad: 0.3404 (0.3272) time: 0.4153 data: 0.0032 max mem: 25051 +train: [1] [ 40/800] eta: 0:06:13 lr: 0.000063 loss: 0.4996 (0.5292) grad: 0.2732 (0.2880) time: 0.4160 data: 0.0027 max mem: 25051 +train: [1] [ 60/800] eta: 0:05:46 lr: 0.000064 loss: 0.5123 (0.5612) grad: 0.2732 (0.2838) time: 0.4192 data: 0.0032 max mem: 25051 +train: [1] [ 80/800] eta: 0:05:27 lr: 0.000066 loss: 0.4996 (0.5368) grad: 0.2502 (0.2781) time: 0.4136 data: 0.0028 max mem: 25051 +train: [1] [100/800] eta: 0:05:39 lr: 0.000067 loss: 0.4923 (0.5178) grad: 0.2470 (0.2708) time: 0.6096 data: 0.1769 max mem: 25051 +train: [1] [120/800] eta: 0:05:22 lr: 0.000069 loss: 0.5070 (0.5368) grad: 0.2502 (0.2642) time: 0.4195 data: 0.0023 max mem: 25051 +train: [1] [140/800] eta: 0:05:07 lr: 0.000070 loss: 0.5070 (0.5290) grad: 0.2470 (0.2625) time: 0.4118 data: 0.0031 max mem: 25051 +train: [1] [160/800] eta: 0:04:53 lr: 0.000072 loss: 0.5070 (0.5304) grad: 0.2514 (0.2668) time: 0.4121 data: 0.0031 max mem: 25051 +train: [1] [180/800] eta: 0:04:54 lr: 0.000073 loss: 0.5283 (0.5205) grad: 0.2514 (0.2694) time: 0.5986 data: 0.1764 max mem: 25051 +train: [1] [200/800] eta: 0:04:41 lr: 0.000075 loss: 0.5394 (0.5404) grad: 0.3129 (0.2778) time: 0.4192 data: 0.0025 max mem: 25051 +train: [1] [220/800] eta: 0:04:28 lr: 0.000076 loss: 0.5116 (0.5241) grad: 0.3166 (0.2812) time: 0.4133 data: 0.0032 max mem: 25051 +train: [1] [240/800] eta: 0:04:17 lr: 0.000078 loss: 0.5116 (0.5222) grad: 0.3129 (0.2809) time: 0.4082 data: 0.0029 max mem: 25051 +train: [1] [260/800] eta: 0:04:12 lr: 0.000079 loss: 0.4280 (0.5113) grad: 0.3108 (0.2793) time: 0.5791 data: 0.1741 max mem: 25051 +train: [1] [280/800] eta: 0:04:01 lr: 0.000081 loss: 0.3173 (0.5123) grad: 0.2527 (0.2770) time: 0.4074 data: 0.0030 max mem: 25051 +train: [1] [300/800] eta: 0:03:50 lr: 0.000082 loss: 0.3173 (0.5046) grad: 0.2070 (0.2714) time: 0.4093 data: 0.0027 max mem: 25051 +train: [1] [320/800] eta: 0:03:39 lr: 0.000084 loss: 0.4280 (0.5109) grad: 0.2121 (0.2713) time: 0.4068 data: 0.0031 max mem: 25051 +train: [1] [340/800] eta: 0:03:33 lr: 0.000085 loss: 0.4716 (0.5093) grad: 0.2222 (0.2693) time: 0.5887 data: 0.1740 max mem: 25051 +train: [1] [360/800] eta: 0:03:23 lr: 0.000087 loss: 0.4821 (0.5093) grad: 0.2225 (0.2702) time: 0.4163 data: 0.0028 max mem: 25051 +train: [1] [380/800] eta: 0:03:13 lr: 0.000088 loss: 0.5098 (0.5093) grad: 0.2249 (0.2737) time: 0.4253 data: 0.0030 max mem: 25051 +train: [1] [400/800] eta: 0:03:03 lr: 0.000090 loss: 0.4502 (0.5028) grad: 0.2249 (0.2717) time: 0.4231 data: 0.0031 max mem: 25051 +train: [1] [420/800] eta: 0:02:56 lr: 0.000091 loss: 0.4385 (0.5034) grad: 0.2811 (0.2751) time: 0.6044 data: 0.1773 max mem: 25051 +train: [1] [440/800] eta: 0:02:46 lr: 0.000093 loss: 0.4215 (0.5020) grad: 0.2877 (0.2772) time: 0.4095 data: 0.0022 max mem: 25051 +train: [1] [460/800] eta: 0:02:36 lr: 0.000094 loss: 0.4218 (0.5006) grad: 0.2958 (0.2781) time: 0.4185 data: 0.0033 max mem: 25051 +train: [1] [480/800] eta: 0:02:26 lr: 0.000096 loss: 0.4385 (0.5000) grad: 0.3019 (0.2781) time: 0.4159 data: 0.0032 max mem: 25051 +train: [1] [500/800] eta: 0:02:19 lr: 0.000097 loss: 0.4175 (0.5026) grad: 0.2832 (0.2772) time: 0.5806 data: 0.1731 max mem: 25051 +train: [1] [520/800] eta: 0:02:09 lr: 0.000099 loss: 0.3825 (0.4969) grad: 0.2420 (0.2751) time: 0.4176 data: 0.0022 max mem: 25051 +train: [1] [540/800] eta: 0:01:59 lr: 0.000100 loss: 0.3825 (0.4986) grad: 0.2408 (0.2753) time: 0.4152 data: 0.0032 max mem: 25051 +train: [1] [560/800] eta: 0:01:50 lr: 0.000102 loss: 0.3712 (0.4946) grad: 0.2420 (0.2754) time: 0.4150 data: 0.0032 max mem: 25051 +train: [1] [580/800] eta: 0:01:41 lr: 0.000103 loss: 0.3944 (0.4991) grad: 0.2360 (0.2735) time: 0.6023 data: 0.1843 max mem: 25051 +train: [1] [600/800] eta: 0:01:32 lr: 0.000105 loss: 0.3939 (0.4906) grad: 0.2360 (0.2722) time: 0.4229 data: 0.0028 max mem: 25051 +train: [1] [620/800] eta: 0:01:22 lr: 0.000106 loss: 0.4152 (0.4904) grad: 0.2440 (0.2728) time: 0.4122 data: 0.0032 max mem: 25051 +train: [1] [640/800] eta: 0:01:13 lr: 0.000108 loss: 0.4152 (0.4923) grad: 0.2436 (0.2727) time: 0.4193 data: 0.0035 max mem: 25051 +train: [1] [660/800] eta: 0:01:04 lr: 0.000109 loss: 0.3939 (0.4881) grad: 0.2436 (0.2723) time: 0.5775 data: 0.1730 max mem: 25051 +train: [1] [680/800] eta: 0:00:55 lr: 0.000111 loss: 0.4096 (0.4893) grad: 0.2778 (0.2728) time: 0.4098 data: 0.0025 max mem: 25051 +train: [1] [700/800] eta: 0:00:46 lr: 0.000112 loss: 0.4028 (0.4882) grad: 0.2885 (0.2745) time: 0.4265 data: 0.0025 max mem: 25051 +train: [1] [720/800] eta: 0:00:36 lr: 0.000114 loss: 0.4074 (0.4884) grad: 0.2778 (0.2741) time: 0.4319 data: 0.0035 max mem: 25051 +train: [1] [740/800] eta: 0:00:27 lr: 0.000115 loss: 0.4028 (0.4838) grad: 0.2778 (0.2740) time: 0.5997 data: 0.1839 max mem: 25051 +train: [1] [760/800] eta: 0:00:18 lr: 0.000117 loss: 0.3824 (0.4789) grad: 0.2843 (0.2755) time: 0.4386 data: 0.0021 max mem: 25051 +train: [1] [780/800] eta: 0:00:09 lr: 0.000118 loss: 0.3641 (0.4791) grad: 0.2676 (0.2751) time: 0.4262 data: 0.0031 max mem: 25051 +train: [1] [799/800] eta: 0:00:00 lr: 0.000120 loss: 0.3425 (0.4793) grad: 0.2440 (0.2740) time: 0.4255 data: 0.0033 max mem: 25051 +train: [1] Total time: 0:06:08 (0.4612 s / it) +train: [1] Summary: lr: 0.000120 loss: 0.3425 (0.4793) grad: 0.2440 (0.2740) +eval (validation): [1] [ 0/11] eta: 0:00:40 time: 3.7012 data: 3.4440 max mem: 25051 +eval (validation): [1] [10/11] eta: 0:00:00 time: 0.5781 data: 0.3138 max mem: 25051 +eval (validation): [1] Total time: 0:00:06 (0.5919 s / it) +cv: [1] best hparam: (6, 1.0) (035) ('035_lr6.0e+00_wd1.0e+00') loss: 0.605 acc: 0.683 f1: 0.641 bacc: 0.689 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/adni_ad_vs_cn__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/adni_ad_vs_cn__patch__attn/checkpoint-best.pth +train: [2] [ 0/800] eta: 0:49:53 lr: nan time: 3.7416 data: 3.3600 max mem: 25051 +train: [2] [ 20/800] eta: 0:07:51 lr: 0.000121 loss: 0.3984 (0.3869) grad: 0.2567 (0.2464) time: 0.4470 data: 0.0077 max mem: 25051 +train: [2] [ 40/800] eta: 0:06:38 lr: 0.000123 loss: 0.3984 (0.4261) grad: 0.2859 (0.2892) time: 0.4394 data: 0.0030 max mem: 25051 +train: [2] [ 60/800] eta: 0:06:05 lr: 0.000124 loss: 0.3984 (0.4230) grad: 0.2859 (0.2952) time: 0.4347 data: 0.0029 max mem: 25051 +train: [2] [ 80/800] eta: 0:05:44 lr: 0.000126 loss: 0.3578 (0.4019) grad: 0.2613 (0.2808) time: 0.4269 data: 0.0029 max mem: 25051 +train: [2] [100/800] eta: 0:05:52 lr: 0.000127 loss: 0.3486 (0.3820) grad: 0.2613 (0.2801) time: 0.6063 data: 0.1765 max mem: 25051 +train: [2] [120/800] eta: 0:05:33 lr: 0.000129 loss: 0.3578 (0.3905) grad: 0.2467 (0.2831) time: 0.4258 data: 0.0025 max mem: 25051 +WARNING: classifier 46 (36, 1.0) diverged (loss=13.88 > 13.86) at step 434. Freezing. +train: [2] [140/800] eta: 0:05:17 lr: 0.000130 loss: 0.3989 (0.4269) grad: 0.2722 (0.2925) time: 0.4224 data: 0.0030 max mem: 25051 +train: [2] [160/800] eta: 0:05:03 lr: 0.000132 loss: 0.4162 (0.4430) grad: 0.2852 (0.2953) time: 0.4228 data: 0.0030 max mem: 25051 +train: [2] [180/800] eta: 0:05:02 lr: 0.000133 loss: 0.4408 (0.4494) grad: 0.3149 (0.3006) time: 0.6101 data: 0.1787 max mem: 25051 +train: [2] [200/800] eta: 0:04:49 lr: 0.000135 loss: 0.4453 (0.4513) grad: 0.3149 (0.2961) time: 0.4223 data: 0.0027 max mem: 25051 +train: [2] [220/800] eta: 0:04:36 lr: 0.000136 loss: 0.4162 (0.4341) grad: 0.3323 (0.3136) time: 0.4244 data: 0.0031 max mem: 25051 +WARNING: classifier 48 (50, 1.0) diverged (loss=14.69 > 13.86) at step 459. Freezing. +train: [2] [240/800] eta: 0:04:24 lr: 0.000138 loss: 0.3856 (0.4438) grad: 0.2991 (0.3111) time: 0.4209 data: 0.0031 max mem: 25051 +train: [2] [260/800] eta: 0:04:20 lr: 0.000139 loss: 0.3856 (0.4419) grad: 0.2553 (0.3018) time: 0.6057 data: 0.1836 max mem: 25051 +train: [2] [280/800] eta: 0:04:09 lr: 0.000141 loss: 0.3150 (0.4294) grad: 0.2549 (0.2967) time: 0.4359 data: 0.0032 max mem: 25051 +train: [2] [300/800] eta: 0:03:57 lr: 0.000142 loss: 0.3293 (0.4234) grad: 0.2133 (0.2867) time: 0.4305 data: 0.0029 max mem: 25051 +train: [2] [320/800] eta: 0:03:46 lr: 0.000144 loss: 0.3293 (0.4268) grad: 0.2020 (0.2833) time: 0.4180 data: 0.0033 max mem: 25051 +train: [2] [340/800] eta: 0:03:40 lr: 0.000145 loss: 0.2851 (0.4246) grad: 0.2133 (0.2815) time: 0.5855 data: 0.1735 max mem: 25051 +train: [2] [360/800] eta: 0:03:29 lr: 0.000147 loss: 0.4287 (0.4306) grad: 0.2133 (0.2793) time: 0.4438 data: 0.0120 max mem: 25051 +train: [2] [380/800] eta: 0:03:19 lr: 0.000148 loss: 0.4287 (0.4304) grad: 0.2489 (0.2801) time: 0.4214 data: 0.0026 max mem: 25051 +train: [2] [400/800] eta: 0:03:08 lr: 0.000150 loss: 0.3637 (0.4207) grad: 0.2548 (0.2806) time: 0.4176 data: 0.0031 max mem: 25051 +train: [2] [420/800] eta: 0:03:01 lr: 0.000151 loss: 0.3637 (0.4177) grad: 0.2725 (0.2848) time: 0.5957 data: 0.1769 max mem: 25051 +train: [2] [440/800] eta: 0:02:50 lr: 0.000153 loss: 0.3485 (0.4182) grad: 0.2799 (0.2840) time: 0.4200 data: 0.0021 max mem: 25051 +train: [2] [460/800] eta: 0:02:40 lr: 0.000154 loss: 0.4101 (0.4209) grad: 0.3216 (0.2866) time: 0.4379 data: 0.0034 max mem: 25051 +train: [2] [480/800] eta: 0:02:30 lr: 0.000156 loss: 0.4101 (0.4159) grad: 0.3216 (0.2881) time: 0.4208 data: 0.0033 max mem: 25051 +train: [2] [500/800] eta: 0:02:22 lr: 0.000157 loss: 0.4138 (0.4206) grad: 0.2969 (0.2908) time: 0.5891 data: 0.1721 max mem: 25051 +WARNING: classifier 47 (43, 1.0) diverged (loss=14.55 > 13.86) at step 527. Freezing. +train: [2] [520/800] eta: 0:02:12 lr: 0.000159 loss: 0.4575 (0.4232) grad: 0.3322 (0.2958) time: 0.4122 data: 0.0025 max mem: 25051 +train: [2] [540/800] eta: 0:02:02 lr: 0.000160 loss: 0.3247 (0.4201) grad: 0.2862 (0.2946) time: 0.4259 data: 0.0032 max mem: 25051 +train: [2] [560/800] eta: 0:01:52 lr: 0.000162 loss: 0.3821 (0.4174) grad: 0.2862 (0.2949) time: 0.4198 data: 0.0035 max mem: 25051 +train: [2] [580/800] eta: 0:01:44 lr: 0.000163 loss: 0.4005 (0.4212) grad: 0.2725 (0.2928) time: 0.6026 data: 0.1793 max mem: 25051 +train: [2] [600/800] eta: 0:01:34 lr: 0.000165 loss: 0.3326 (0.4178) grad: 0.2627 (0.2907) time: 0.4192 data: 0.0028 max mem: 25051 +train: [2] [620/800] eta: 0:01:24 lr: 0.000166 loss: 0.3326 (0.4161) grad: 0.2572 (0.2905) time: 0.4139 data: 0.0032 max mem: 25051 +train: [2] [640/800] eta: 0:01:15 lr: 0.000168 loss: 0.3111 (0.4127) grad: 0.2399 (0.2891) time: 0.4197 data: 0.0033 max mem: 25051 +train: [2] [660/800] eta: 0:01:06 lr: 0.000169 loss: 0.3111 (0.4131) grad: 0.2356 (0.2896) time: 0.5851 data: 0.1780 max mem: 25051 +train: [2] [680/800] eta: 0:00:56 lr: 0.000171 loss: 0.3581 (0.4157) grad: 0.2421 (0.2891) time: 0.4225 data: 0.0028 max mem: 25051 +train: [2] [700/800] eta: 0:00:46 lr: 0.000172 loss: 0.3890 (0.4170) grad: 0.2421 (0.2879) time: 0.4099 data: 0.0028 max mem: 25051 +train: [2] [720/800] eta: 0:00:37 lr: 0.000174 loss: 0.3919 (0.4159) grad: 0.2356 (0.2858) time: 0.4126 data: 0.0031 max mem: 25051 +train: [2] [740/800] eta: 0:00:28 lr: 0.000175 loss: 0.3706 (0.4137) grad: 0.2304 (0.2857) time: 0.5909 data: 0.1824 max mem: 25051 +train: [2] [760/800] eta: 0:00:18 lr: 0.000177 loss: 0.3260 (0.4081) grad: 0.2304 (0.2848) time: 0.4320 data: 0.0024 max mem: 25051 +train: [2] [780/800] eta: 0:00:09 lr: 0.000178 loss: 0.3260 (0.4088) grad: 0.2406 (0.2856) time: 0.4226 data: 0.0030 max mem: 25051 +train: [2] [799/800] eta: 0:00:00 lr: 0.000180 loss: 0.2688 (0.4120) grad: 0.2413 (0.2853) time: 0.4318 data: 0.0032 max mem: 25051 +train: [2] Total time: 0:06:14 (0.4681 s / it) +train: [2] Summary: lr: 0.000180 loss: 0.2688 (0.4120) grad: 0.2413 (0.2853) +eval (validation): [2] [ 0/11] eta: 0:00:38 time: 3.4779 data: 3.2444 max mem: 25051 +eval (validation): [2] [10/11] eta: 0:00:00 time: 0.5747 data: 0.2970 max mem: 25051 +eval (validation): [2] Total time: 0:00:06 (0.5900 s / it) +cv: [2] best hparam: (31, 1.0) (045) ('045_lr3.1e+01_wd1.0e+00') loss: 5.987 acc: 0.634 f1: 0.611 bacc: 0.690 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/adni_ad_vs_cn__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/adni_ad_vs_cn__patch__attn/checkpoint-best.pth +train: [3] [ 0/800] eta: 0:49:24 lr: nan time: 3.7051 data: 3.3606 max mem: 25051 +train: [3] [ 20/800] eta: 0:07:37 lr: 0.000181 loss: 0.4846 (0.3772) grad: 0.3061 (0.2944) time: 0.4299 data: 0.0026 max mem: 25051 +train: [3] [ 40/800] eta: 0:06:30 lr: 0.000183 loss: 0.4106 (0.4137) grad: 0.2997 (0.3253) time: 0.4375 data: 0.0025 max mem: 25051 +train: [3] [ 60/800] eta: 0:05:59 lr: 0.000184 loss: 0.4106 (0.4027) grad: 0.2871 (0.3007) time: 0.4287 data: 0.0034 max mem: 25051 +train: [3] [ 80/800] eta: 0:05:36 lr: 0.000186 loss: 0.3683 (0.3791) grad: 0.2707 (0.2973) time: 0.4097 data: 0.0029 max mem: 25051 +WARNING: classifier 45 (31, 1.0) diverged (loss=16.25 > 13.86) at step 621. Freezing. +train: [3] [100/800] eta: 0:05:49 lr: 0.000187 loss: 0.3861 (0.4002) grad: 0.2484 (0.2813) time: 0.6305 data: 0.1837 max mem: 25051 +train: [3] [120/800] eta: 0:05:30 lr: 0.000189 loss: 0.2951 (0.4038) grad: 0.2318 (0.2707) time: 0.4205 data: 0.0027 max mem: 25051 +train: [3] [140/800] eta: 0:05:16 lr: 0.000190 loss: 0.3861 (0.4148) grad: 0.2078 (0.2593) time: 0.4358 data: 0.0036 max mem: 25051 +train: [3] [160/800] eta: 0:05:01 lr: 0.000192 loss: 0.3828 (0.4083) grad: 0.1934 (0.2515) time: 0.4182 data: 0.0030 max mem: 25051 +train: [3] [180/800] eta: 0:05:04 lr: 0.000193 loss: 0.3239 (0.4053) grad: 0.2078 (0.2516) time: 0.6500 data: 0.1817 max mem: 25051 +train: [3] [200/800] eta: 0:04:50 lr: 0.000195 loss: 0.3580 (0.4019) grad: 0.2228 (0.2571) time: 0.4222 data: 0.0028 max mem: 25051 +train: [3] [220/800] eta: 0:04:37 lr: 0.000196 loss: 0.3229 (0.3987) grad: 0.2271 (0.2567) time: 0.4181 data: 0.0030 max mem: 25051 +train: [3] [240/800] eta: 0:04:25 lr: 0.000198 loss: 0.3342 (0.3950) grad: 0.2289 (0.2555) time: 0.4161 data: 0.0029 max mem: 25051 +train: [3] [260/800] eta: 0:04:21 lr: 0.000199 loss: 0.3213 (0.3874) grad: 0.2327 (0.2514) time: 0.6168 data: 0.1733 max mem: 25051 +train: [3] [280/800] eta: 0:04:09 lr: 0.000201 loss: 0.3287 (0.3915) grad: 0.2158 (0.2467) time: 0.4209 data: 0.0029 max mem: 25051 +train: [3] [300/800] eta: 0:03:57 lr: 0.000202 loss: 0.3213 (0.3892) grad: 0.2155 (0.2481) time: 0.4217 data: 0.0032 max mem: 25051 +train: [3] [320/800] eta: 0:03:46 lr: 0.000204 loss: 0.3287 (0.3897) grad: 0.2155 (0.2503) time: 0.4153 data: 0.0030 max mem: 25051 +train: [3] [340/800] eta: 0:03:40 lr: 0.000205 loss: 0.3403 (0.3889) grad: 0.2155 (0.2495) time: 0.6106 data: 0.1870 max mem: 25051 +train: [3] [360/800] eta: 0:03:29 lr: 0.000207 loss: 0.3403 (0.3904) grad: 0.2334 (0.2528) time: 0.4140 data: 0.0025 max mem: 25051 +train: [3] [380/800] eta: 0:03:18 lr: 0.000208 loss: 0.3494 (0.3912) grad: 0.2494 (0.2523) time: 0.4166 data: 0.0030 max mem: 25051 +train: [3] [400/800] eta: 0:03:08 lr: 0.000210 loss: 0.3494 (0.3969) grad: 0.2555 (0.2538) time: 0.4169 data: 0.0031 max mem: 25051 +train: [3] [420/800] eta: 0:03:00 lr: 0.000211 loss: 0.3096 (0.3969) grad: 0.2660 (0.2595) time: 0.5897 data: 0.1801 max mem: 25051 +train: [3] [440/800] eta: 0:02:50 lr: 0.000213 loss: 0.3041 (0.3938) grad: 0.2682 (0.2627) time: 0.4099 data: 0.0023 max mem: 25051 +train: [3] [460/800] eta: 0:02:39 lr: 0.000214 loss: 0.2607 (0.3883) grad: 0.2861 (0.2643) time: 0.4107 data: 0.0032 max mem: 25051 +train: [3] [480/800] eta: 0:02:29 lr: 0.000216 loss: 0.3041 (0.4005) grad: 0.2861 (0.2693) time: 0.4153 data: 0.0030 max mem: 25051 +train: [3] [500/800] eta: 0:02:21 lr: 0.000217 loss: 0.3430 (0.4005) grad: 0.3118 (0.2747) time: 0.5829 data: 0.1756 max mem: 25051 +train: [3] [520/800] eta: 0:02:11 lr: 0.000219 loss: 0.3430 (0.3974) grad: 0.2615 (0.2715) time: 0.4235 data: 0.0025 max mem: 25051 +train: [3] [540/800] eta: 0:02:01 lr: 0.000220 loss: 0.3430 (0.3976) grad: 0.2553 (0.2726) time: 0.4122 data: 0.0029 max mem: 25051 +train: [3] [560/800] eta: 0:01:52 lr: 0.000222 loss: 0.3430 (0.3999) grad: 0.3056 (0.2775) time: 0.4260 data: 0.0033 max mem: 25051 +train: [3] [580/800] eta: 0:01:43 lr: 0.000223 loss: 0.2750 (0.3973) grad: 0.2901 (0.2784) time: 0.6080 data: 0.1863 max mem: 25051 +train: [3] [600/800] eta: 0:01:34 lr: 0.000225 loss: 0.3552 (0.4042) grad: 0.3072 (0.2805) time: 0.4142 data: 0.0028 max mem: 25051 +train: [3] [620/800] eta: 0:01:24 lr: 0.000226 loss: 0.4518 (0.4067) grad: 0.2974 (0.2802) time: 0.4146 data: 0.0028 max mem: 25051 +train: [3] [640/800] eta: 0:01:14 lr: 0.000228 loss: 0.3750 (0.4034) grad: 0.2913 (0.2809) time: 0.4135 data: 0.0029 max mem: 25051 +train: [3] [660/800] eta: 0:01:05 lr: 0.000229 loss: 0.3977 (0.4012) grad: 0.2956 (0.2822) time: 0.5787 data: 0.1735 max mem: 25051 +train: [3] [680/800] eta: 0:00:56 lr: 0.000231 loss: 0.3625 (0.3980) grad: 0.2654 (0.2794) time: 0.4285 data: 0.0026 max mem: 25051 +train: [3] [700/800] eta: 0:00:46 lr: 0.000232 loss: 0.3434 (0.4002) grad: 0.2453 (0.2768) time: 0.4168 data: 0.0026 max mem: 25051 +WARNING: classifier 44 (26, 1.0) diverged (loss=27.00 > 13.86) at step 778. Freezing. +train: [3] [720/800] eta: 0:00:37 lr: 0.000234 loss: 0.3498 (0.4026) grad: 0.2635 (0.2805) time: 0.4151 data: 0.0033 max mem: 25051 +train: [3] [740/800] eta: 0:00:28 lr: 0.000235 loss: 0.3530 (0.4036) grad: 0.2108 (0.2792) time: 0.5911 data: 0.1760 max mem: 25051 +train: [3] [760/800] eta: 0:00:18 lr: 0.000237 loss: 0.3962 (0.4058) grad: 0.2054 (0.2763) time: 0.4191 data: 0.0025 max mem: 25051 +train: [3] [780/800] eta: 0:00:09 lr: 0.000238 loss: 0.3812 (0.4032) grad: 0.2078 (0.2748) time: 0.4139 data: 0.0035 max mem: 25051 +train: [3] [799/800] eta: 0:00:00 lr: 0.000240 loss: 0.3962 (0.4045) grad: 0.1876 (0.2731) time: 0.4194 data: 0.0034 max mem: 25051 +train: [3] Total time: 0:06:12 (0.4657 s / it) +train: [3] Summary: lr: 0.000240 loss: 0.3962 (0.4045) grad: 0.1876 (0.2731) +eval (validation): [3] [ 0/11] eta: 0:00:37 time: 3.4260 data: 3.1961 max mem: 25051 +eval (validation): [3] [10/11] eta: 0:00:00 time: 0.5648 data: 0.2927 max mem: 25051 +eval (validation): [3] Total time: 0:00:06 (0.5800 s / it) +cv: [3] best hparam: (0.85, 1.0) (023) ('023_lr8.5e-01_wd1.0e+00') loss: 0.528 acc: 0.756 f1: 0.689 bacc: 0.703 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/adni_ad_vs_cn__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/adni_ad_vs_cn__patch__attn/checkpoint-best.pth +train: [4] [ 0/800] eta: 0:49:47 lr: nan time: 3.7341 data: 3.3972 max mem: 25051 +train: [4] [ 20/800] eta: 0:07:37 lr: 0.000241 loss: 0.2083 (0.2384) grad: 0.1456 (0.1840) time: 0.4296 data: 0.0028 max mem: 25051 +train: [4] [ 40/800] eta: 0:06:22 lr: 0.000243 loss: 0.2062 (0.2567) grad: 0.2194 (0.2478) time: 0.4143 data: 0.0026 max mem: 25051 +train: [4] [ 60/800] eta: 0:05:50 lr: 0.000244 loss: 0.2083 (0.2567) grad: 0.2194 (0.2386) time: 0.4135 data: 0.0031 max mem: 25051 +train: [4] [ 80/800] eta: 0:05:27 lr: 0.000246 loss: 0.2675 (0.2890) grad: 0.2244 (0.2582) time: 0.3995 data: 0.0029 max mem: 25051 +train: [4] [100/800] eta: 0:05:35 lr: 0.000247 loss: 0.2714 (0.2865) grad: 0.2244 (0.2542) time: 0.5795 data: 0.1764 max mem: 25051 +train: [4] [120/800] eta: 0:05:18 lr: 0.000249 loss: 0.2726 (0.3006) grad: 0.2231 (0.2514) time: 0.4107 data: 0.0021 max mem: 25051 +train: [4] [140/800] eta: 0:05:03 lr: 0.000250 loss: 0.3055 (0.3086) grad: 0.2480 (0.2567) time: 0.4092 data: 0.0027 max mem: 25051 +train: [4] [160/800] eta: 0:04:50 lr: 0.000252 loss: 0.2774 (0.3194) grad: 0.2480 (0.2580) time: 0.4087 data: 0.0029 max mem: 25051 +WARNING: classifier 42 (19, 1.0) diverged (loss=16.39 > 13.86) at step 843. Freezing. +train: [4] [180/800] eta: 0:04:49 lr: 0.000253 loss: 0.3069 (0.3219) grad: 0.2102 (0.2615) time: 0.5798 data: 0.1762 max mem: 25051 +train: [4] [200/800] eta: 0:04:37 lr: 0.000255 loss: 0.3254 (0.3226) grad: 0.2102 (0.2550) time: 0.4132 data: 0.0025 max mem: 25051 +train: [4] [220/800] eta: 0:04:24 lr: 0.000256 loss: 0.3254 (0.3349) grad: 0.2008 (0.2503) time: 0.4041 data: 0.0030 max mem: 25051 +train: [4] [240/800] eta: 0:04:13 lr: 0.000258 loss: 0.3069 (0.3254) grad: 0.1975 (0.2449) time: 0.4044 data: 0.0031 max mem: 25051 +train: [4] [260/800] eta: 0:04:09 lr: 0.000259 loss: 0.3023 (0.3202) grad: 0.1975 (0.2402) time: 0.5861 data: 0.1747 max mem: 25051 +train: [4] [280/800] eta: 0:03:59 lr: 0.000261 loss: 0.3023 (0.3220) grad: 0.1972 (0.2399) time: 0.4187 data: 0.0037 max mem: 25051 +train: [4] [300/800] eta: 0:03:48 lr: 0.000262 loss: 0.2418 (0.3231) grad: 0.1944 (0.2365) time: 0.4066 data: 0.0030 max mem: 25051 +train: [4] [320/800] eta: 0:03:37 lr: 0.000264 loss: 0.2773 (0.3223) grad: 0.1940 (0.2346) time: 0.4029 data: 0.0029 max mem: 25051 +train: [4] [340/800] eta: 0:03:32 lr: 0.000265 loss: 0.2773 (0.3212) grad: 0.1940 (0.2323) time: 0.5946 data: 0.1819 max mem: 25051 +train: [4] [360/800] eta: 0:03:21 lr: 0.000267 loss: 0.3019 (0.3234) grad: 0.1940 (0.2317) time: 0.4226 data: 0.0030 max mem: 25051 +train: [4] [380/800] eta: 0:03:11 lr: 0.000268 loss: 0.3019 (0.3251) grad: 0.1933 (0.2284) time: 0.4162 data: 0.0030 max mem: 25051 +train: [4] [400/800] eta: 0:03:01 lr: 0.000270 loss: 0.3122 (0.3264) grad: 0.1933 (0.2273) time: 0.4048 data: 0.0030 max mem: 25051 +train: [4] [420/800] eta: 0:02:55 lr: 0.000271 loss: 0.3370 (0.3245) grad: 0.1933 (0.2249) time: 0.6117 data: 0.1757 max mem: 25051 +train: [4] [440/800] eta: 0:02:45 lr: 0.000273 loss: 0.3122 (0.3260) grad: 0.1850 (0.2220) time: 0.4208 data: 0.0024 max mem: 25051 +train: [4] [460/800] eta: 0:02:35 lr: 0.000274 loss: 0.2563 (0.3231) grad: 0.1850 (0.2206) time: 0.4143 data: 0.0030 max mem: 25051 +train: [4] [480/800] eta: 0:02:25 lr: 0.000276 loss: 0.2448 (0.3239) grad: 0.1829 (0.2206) time: 0.4082 data: 0.0031 max mem: 25051 +train: [4] [500/800] eta: 0:02:18 lr: 0.000277 loss: 0.3007 (0.3257) grad: 0.1806 (0.2194) time: 0.6131 data: 0.1857 max mem: 25051 +train: [4] [520/800] eta: 0:02:08 lr: 0.000279 loss: 0.3083 (0.3296) grad: 0.1906 (0.2195) time: 0.4151 data: 0.0021 max mem: 25051 +train: [4] [540/800] eta: 0:01:59 lr: 0.000280 loss: 0.4074 (0.3321) grad: 0.1906 (0.2175) time: 0.4112 data: 0.0031 max mem: 25051 +train: [4] [560/800] eta: 0:01:49 lr: 0.000282 loss: 0.4107 (0.3335) grad: 0.1869 (0.2153) time: 0.4126 data: 0.0031 max mem: 25051 +train: [4] [580/800] eta: 0:01:41 lr: 0.000283 loss: 0.4107 (0.3360) grad: 0.1790 (0.2155) time: 0.5990 data: 0.1740 max mem: 25051 +train: [4] [600/800] eta: 0:01:32 lr: 0.000285 loss: 0.3116 (0.3355) grad: 0.1281 (0.2158) time: 0.4138 data: 0.0031 max mem: 25051 +train: [4] [620/800] eta: 0:01:22 lr: 0.000286 loss: 0.2984 (0.3345) grad: 0.1878 (0.2171) time: 0.4118 data: 0.0030 max mem: 25051 +train: [4] [640/800] eta: 0:01:13 lr: 0.000288 loss: 0.2477 (0.3324) grad: 0.2189 (0.2196) time: 0.4151 data: 0.0030 max mem: 25051 +train: [4] [660/800] eta: 0:01:04 lr: 0.000289 loss: 0.2440 (0.3313) grad: 0.2189 (0.2190) time: 0.6028 data: 0.1799 max mem: 25051 +train: [4] [680/800] eta: 0:00:55 lr: 0.000291 loss: 0.2440 (0.3323) grad: 0.2107 (0.2174) time: 0.4160 data: 0.0030 max mem: 25051 +train: [4] [700/800] eta: 0:00:45 lr: 0.000292 loss: 0.2758 (0.3349) grad: 0.2093 (0.2177) time: 0.4125 data: 0.0026 max mem: 25051 +train: [4] [720/800] eta: 0:00:36 lr: 0.000294 loss: 0.3144 (0.3337) grad: 0.1947 (0.2177) time: 0.4129 data: 0.0031 max mem: 25051 +train: [4] [740/800] eta: 0:00:27 lr: 0.000295 loss: 0.3255 (0.3333) grad: 0.1735 (0.2163) time: 0.5733 data: 0.1788 max mem: 25051 +train: [4] [760/800] eta: 0:00:18 lr: 0.000297 loss: 0.2825 (0.3324) grad: 0.1757 (0.2147) time: 0.4069 data: 0.0027 max mem: 25051 +train: [4] [780/800] eta: 0:00:09 lr: 0.000298 loss: 0.2611 (0.3307) grad: 0.1807 (0.2168) time: 0.4169 data: 0.0029 max mem: 25051 +train: [4] [799/800] eta: 0:00:00 lr: 0.000300 loss: 0.2730 (0.3312) grad: 0.1830 (0.2168) time: 0.4027 data: 0.0031 max mem: 25051 +train: [4] Total time: 0:06:05 (0.4572 s / it) +train: [4] Summary: lr: 0.000300 loss: 0.2730 (0.3312) grad: 0.1830 (0.2168) +eval (validation): [4] [ 0/11] eta: 0:00:39 time: 3.5740 data: 3.3472 max mem: 25051 +eval (validation): [4] [10/11] eta: 0:00:00 time: 0.5758 data: 0.3050 max mem: 25051 +eval (validation): [4] Total time: 0:00:06 (0.5898 s / it) +cv: [4] best hparam: (1.9, 1.0) (028) ('028_lr1.9e+00_wd1.0e+00') loss: 1.528 acc: 0.756 f1: 0.644 bacc: 0.635 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/adni_ad_vs_cn__patch__attn/checkpoint-last.pth +train: [5] [ 0/800] eta: 0:49:06 lr: nan time: 3.6829 data: 3.3512 max mem: 25051 +train: [5] [ 20/800] eta: 0:07:30 lr: 0.000300 loss: 0.2251 (0.2502) grad: 0.2643 (0.2670) time: 0.4228 data: 0.0021 max mem: 25051 +train: [5] [ 40/800] eta: 0:06:19 lr: 0.000300 loss: 0.2155 (0.2697) grad: 0.2012 (0.2249) time: 0.4170 data: 0.0028 max mem: 25051 +train: [5] [ 60/800] eta: 0:05:48 lr: 0.000300 loss: 0.3417 (0.3350) grad: 0.1936 (0.2044) time: 0.4127 data: 0.0032 max mem: 25051 +train: [5] [ 80/800] eta: 0:05:27 lr: 0.000300 loss: 0.3346 (0.3294) grad: 0.2228 (0.2292) time: 0.4050 data: 0.0029 max mem: 25051 +train: [5] [100/800] eta: 0:05:40 lr: 0.000300 loss: 0.3346 (0.3191) grad: 0.1936 (0.2306) time: 0.6179 data: 0.1848 max mem: 25051 +train: [5] [120/800] eta: 0:05:22 lr: 0.000300 loss: 0.3417 (0.3277) grad: 0.2347 (0.2319) time: 0.4088 data: 0.0026 max mem: 25051 +train: [5] [140/800] eta: 0:05:07 lr: 0.000300 loss: 0.2941 (0.3207) grad: 0.2540 (0.2269) time: 0.4116 data: 0.0033 max mem: 25051 +train: [5] [160/800] eta: 0:04:53 lr: 0.000300 loss: 0.2941 (0.3279) grad: 0.2091 (0.2229) time: 0.4089 data: 0.0032 max mem: 25051 +train: [5] [180/800] eta: 0:04:52 lr: 0.000300 loss: 0.2943 (0.3336) grad: 0.1816 (0.2259) time: 0.5855 data: 0.1835 max mem: 25051 +train: [5] [200/800] eta: 0:04:39 lr: 0.000300 loss: 0.2943 (0.3373) grad: 0.1816 (0.2279) time: 0.4136 data: 0.0023 max mem: 25051 +train: [5] [220/800] eta: 0:04:27 lr: 0.000300 loss: 0.3135 (0.3339) grad: 0.1663 (0.2226) time: 0.4076 data: 0.0033 max mem: 25051 +train: [5] [240/800] eta: 0:04:15 lr: 0.000300 loss: 0.2382 (0.3210) grad: 0.1629 (0.2213) time: 0.4077 data: 0.0035 max mem: 25051 +train: [5] [260/800] eta: 0:04:12 lr: 0.000300 loss: 0.2631 (0.3256) grad: 0.2057 (0.2267) time: 0.6105 data: 0.1815 max mem: 25051 +train: [5] [280/800] eta: 0:04:01 lr: 0.000300 loss: 0.2670 (0.3230) grad: 0.2057 (0.2276) time: 0.4079 data: 0.0030 max mem: 25051 +train: [5] [300/800] eta: 0:03:50 lr: 0.000300 loss: 0.2942 (0.3269) grad: 0.1921 (0.2237) time: 0.4128 data: 0.0031 max mem: 25051 +train: [5] [320/800] eta: 0:03:39 lr: 0.000299 loss: 0.3185 (0.3274) grad: 0.1826 (0.2195) time: 0.4045 data: 0.0029 max mem: 25051 +train: [5] [340/800] eta: 0:03:34 lr: 0.000299 loss: 0.3249 (0.3259) grad: 0.1650 (0.2181) time: 0.6042 data: 0.1770 max mem: 25051 +train: [5] [360/800] eta: 0:03:23 lr: 0.000299 loss: 0.3315 (0.3237) grad: 0.1587 (0.2150) time: 0.4041 data: 0.0024 max mem: 25051 +train: [5] [380/800] eta: 0:03:13 lr: 0.000299 loss: 0.3315 (0.3296) grad: 0.1650 (0.2160) time: 0.4140 data: 0.0031 max mem: 25051 +train: [5] [400/800] eta: 0:03:03 lr: 0.000299 loss: 0.3057 (0.3276) grad: 0.1544 (0.2129) time: 0.4197 data: 0.0031 max mem: 25051 +train: [5] [420/800] eta: 0:02:56 lr: 0.000299 loss: 0.2956 (0.3290) grad: 0.1566 (0.2106) time: 0.5998 data: 0.1814 max mem: 25051 +train: [5] [440/800] eta: 0:02:46 lr: 0.000299 loss: 0.3057 (0.3283) grad: 0.1532 (0.2080) time: 0.4031 data: 0.0024 max mem: 25051 +train: [5] [460/800] eta: 0:02:36 lr: 0.000299 loss: 0.3025 (0.3311) grad: 0.1491 (0.2085) time: 0.4040 data: 0.0030 max mem: 25051 +train: [5] [480/800] eta: 0:02:26 lr: 0.000299 loss: 0.3074 (0.3321) grad: 0.1794 (0.2117) time: 0.4059 data: 0.0032 max mem: 25051 +train: [5] [500/800] eta: 0:02:18 lr: 0.000299 loss: 0.3202 (0.3324) grad: 0.1944 (0.2116) time: 0.5789 data: 0.1777 max mem: 25051 +train: [5] [520/800] eta: 0:02:08 lr: 0.000299 loss: 0.3586 (0.3328) grad: 0.2224 (0.2134) time: 0.4154 data: 0.0030 max mem: 25051 +train: [5] [540/800] eta: 0:01:59 lr: 0.000299 loss: 0.3367 (0.3304) grad: 0.1944 (0.2103) time: 0.4009 data: 0.0031 max mem: 25051 +train: [5] [560/800] eta: 0:01:49 lr: 0.000298 loss: 0.3319 (0.3291) grad: 0.1706 (0.2082) time: 0.4076 data: 0.0031 max mem: 25051 +train: [5] [580/800] eta: 0:01:41 lr: 0.000298 loss: 0.3002 (0.3294) grad: 0.1617 (0.2080) time: 0.6038 data: 0.1785 max mem: 25051 +train: [5] [600/800] eta: 0:01:31 lr: 0.000298 loss: 0.2817 (0.3300) grad: 0.1583 (0.2068) time: 0.4080 data: 0.0028 max mem: 25051 +train: [5] [620/800] eta: 0:01:22 lr: 0.000298 loss: 0.2710 (0.3268) grad: 0.1583 (0.2054) time: 0.4096 data: 0.0027 max mem: 25051 +train: [5] [640/800] eta: 0:01:13 lr: 0.000298 loss: 0.2710 (0.3267) grad: 0.1576 (0.2028) time: 0.4118 data: 0.0030 max mem: 25051 +train: [5] [660/800] eta: 0:01:04 lr: 0.000298 loss: 0.2602 (0.3270) grad: 0.1464 (0.2025) time: 0.6051 data: 0.1793 max mem: 25051 +train: [5] [680/800] eta: 0:00:55 lr: 0.000298 loss: 0.2407 (0.3244) grad: 0.1464 (0.2023) time: 0.4242 data: 0.0035 max mem: 25051 +train: [5] [700/800] eta: 0:00:45 lr: 0.000298 loss: 0.2761 (0.3235) grad: 0.1339 (0.2010) time: 0.4094 data: 0.0032 max mem: 25051 +train: [5] [720/800] eta: 0:00:36 lr: 0.000297 loss: 0.2621 (0.3235) grad: 0.1322 (0.1989) time: 0.4184 data: 0.0034 max mem: 25051 +train: [5] [740/800] eta: 0:00:27 lr: 0.000297 loss: 0.2621 (0.3215) grad: 0.1318 (0.1978) time: 0.5751 data: 0.1767 max mem: 25051 +train: [5] [760/800] eta: 0:00:18 lr: 0.000297 loss: 0.2731 (0.3212) grad: 0.1322 (0.1983) time: 0.4116 data: 0.0026 max mem: 25051 +train: [5] [780/800] eta: 0:00:09 lr: 0.000297 loss: 0.2720 (0.3203) grad: 0.1586 (0.1981) time: 0.4058 data: 0.0029 max mem: 25051 +train: [5] [799/800] eta: 0:00:00 lr: 0.000297 loss: 0.2720 (0.3204) grad: 0.1588 (0.1970) time: 0.4079 data: 0.0033 max mem: 25051 +train: [5] Total time: 0:06:05 (0.4570 s / it) +train: [5] Summary: lr: 0.000297 loss: 0.2720 (0.3204) grad: 0.1588 (0.1970) +eval (validation): [5] [ 0/11] eta: 0:00:38 time: 3.5050 data: 3.2807 max mem: 25051 +eval (validation): [5] [10/11] eta: 0:00:00 time: 0.5661 data: 0.2999 max mem: 25051 +eval (validation): [5] Total time: 0:00:06 (0.5805 s / it) +cv: [5] best hparam: (2.3, 1.0) (029) ('029_lr2.3e+00_wd1.0e+00') loss: 2.170 acc: 0.732 f1: 0.648 bacc: 0.653 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/adni_ad_vs_cn__patch__attn/checkpoint-last.pth +train: [6] [ 0/800] eta: 0:48:22 lr: nan time: 3.6283 data: 3.2506 max mem: 25051 +train: [6] [ 20/800] eta: 0:07:44 lr: 0.000297 loss: 0.3215 (0.3143) grad: 0.1543 (0.1736) time: 0.4437 data: 0.0026 max mem: 25051 +train: [6] [ 40/800] eta: 0:06:23 lr: 0.000296 loss: 0.2547 (0.2796) grad: 0.1530 (0.1648) time: 0.4096 data: 0.0027 max mem: 25051 +train: [6] [ 60/800] eta: 0:05:50 lr: 0.000296 loss: 0.2547 (0.2865) grad: 0.1543 (0.1722) time: 0.4094 data: 0.0032 max mem: 25051 +train: [6] [ 80/800] eta: 0:05:27 lr: 0.000296 loss: 0.2547 (0.2859) grad: 0.1478 (0.1600) time: 0.3985 data: 0.0029 max mem: 25051 +train: [6] [100/800] eta: 0:05:41 lr: 0.000296 loss: 0.2738 (0.3015) grad: 0.1478 (0.1654) time: 0.6201 data: 0.1715 max mem: 25051 +train: [6] [120/800] eta: 0:05:21 lr: 0.000296 loss: 0.2967 (0.3035) grad: 0.1654 (0.1734) time: 0.4021 data: 0.0033 max mem: 25051 +train: [6] [140/800] eta: 0:05:07 lr: 0.000296 loss: 0.2967 (0.3020) grad: 0.1654 (0.1753) time: 0.4162 data: 0.0031 max mem: 25051 +train: [6] [160/800] eta: 0:04:53 lr: 0.000295 loss: 0.2633 (0.2923) grad: 0.1926 (0.1805) time: 0.4046 data: 0.0031 max mem: 25051 +train: [6] [180/800] eta: 0:04:53 lr: 0.000295 loss: 0.2422 (0.2967) grad: 0.2045 (0.1801) time: 0.6013 data: 0.1739 max mem: 25051 +train: [6] [200/800] eta: 0:04:40 lr: 0.000295 loss: 0.2422 (0.2950) grad: 0.1594 (0.1736) time: 0.4135 data: 0.0033 max mem: 25051 +train: [6] [220/800] eta: 0:04:28 lr: 0.000295 loss: 0.2533 (0.2909) grad: 0.1594 (0.1761) time: 0.4133 data: 0.0034 max mem: 25051 +train: [6] [240/800] eta: 0:04:16 lr: 0.000295 loss: 0.2916 (0.2904) grad: 0.1069 (0.1745) time: 0.4011 data: 0.0032 max mem: 25051 +train: [6] [260/800] eta: 0:04:12 lr: 0.000294 loss: 0.2547 (0.2846) grad: 0.1140 (0.1769) time: 0.5773 data: 0.1771 max mem: 25051 +train: [6] [280/800] eta: 0:04:00 lr: 0.000294 loss: 0.2561 (0.2845) grad: 0.1700 (0.1790) time: 0.4097 data: 0.0030 max mem: 25051 +train: [6] [300/800] eta: 0:03:49 lr: 0.000294 loss: 0.2561 (0.2870) grad: 0.1898 (0.1851) time: 0.4167 data: 0.0033 max mem: 25051 +train: [6] [320/800] eta: 0:03:39 lr: 0.000294 loss: 0.2443 (0.2828) grad: 0.2105 (0.1855) time: 0.4084 data: 0.0032 max mem: 25051 +train: [6] [340/800] eta: 0:03:34 lr: 0.000293 loss: 0.2494 (0.2838) grad: 0.2191 (0.1856) time: 0.6242 data: 0.1880 max mem: 25051 +train: [6] [360/800] eta: 0:03:23 lr: 0.000293 loss: 0.2494 (0.2852) grad: 0.1742 (0.1824) time: 0.4132 data: 0.0028 max mem: 25051 +train: [6] [380/800] eta: 0:03:13 lr: 0.000293 loss: 0.2610 (0.2849) grad: 0.1676 (0.1809) time: 0.4174 data: 0.0030 max mem: 25051 +train: [6] [400/800] eta: 0:03:03 lr: 0.000293 loss: 0.2657 (0.2865) grad: 0.1545 (0.1808) time: 0.4142 data: 0.0032 max mem: 25051 +train: [6] [420/800] eta: 0:02:56 lr: 0.000292 loss: 0.2610 (0.2838) grad: 0.1417 (0.1788) time: 0.5858 data: 0.1812 max mem: 25051 +train: [6] [440/800] eta: 0:02:46 lr: 0.000292 loss: 0.2610 (0.2854) grad: 0.1264 (0.1768) time: 0.4207 data: 0.0026 max mem: 25051 +train: [6] [460/800] eta: 0:02:36 lr: 0.000292 loss: 0.2709 (0.2864) grad: 0.1369 (0.1771) time: 0.4285 data: 0.0031 max mem: 25051 +train: [6] [480/800] eta: 0:02:27 lr: 0.000292 loss: 0.2761 (0.2889) grad: 0.1635 (0.1807) time: 0.4199 data: 0.0032 max mem: 25051 +train: [6] [500/800] eta: 0:02:19 lr: 0.000291 loss: 0.2949 (0.2908) grad: 0.1635 (0.1810) time: 0.5849 data: 0.1778 max mem: 25051 +train: [6] [520/800] eta: 0:02:09 lr: 0.000291 loss: 0.3339 (0.2923) grad: 0.1635 (0.1788) time: 0.4159 data: 0.0033 max mem: 25051 +train: [6] [540/800] eta: 0:01:59 lr: 0.000291 loss: 0.3185 (0.2912) grad: 0.1607 (0.1795) time: 0.4186 data: 0.0024 max mem: 25051 +train: [6] [560/800] eta: 0:01:50 lr: 0.000291 loss: 0.3185 (0.2927) grad: 0.1557 (0.1800) time: 0.4225 data: 0.0034 max mem: 25051 +train: [6] [580/800] eta: 0:01:42 lr: 0.000290 loss: 0.3072 (0.2921) grad: 0.1530 (0.1800) time: 0.6129 data: 0.1818 max mem: 25051 +train: [6] [600/800] eta: 0:01:32 lr: 0.000290 loss: 0.3072 (0.2940) grad: 0.1819 (0.1811) time: 0.4166 data: 0.0032 max mem: 25051 +train: [6] [620/800] eta: 0:01:23 lr: 0.000290 loss: 0.3033 (0.2913) grad: 0.1819 (0.1824) time: 0.4183 data: 0.0031 max mem: 25051 +train: [6] [640/800] eta: 0:01:13 lr: 0.000290 loss: 0.2638 (0.2919) grad: 0.2011 (0.1846) time: 0.4243 data: 0.0033 max mem: 25051 +train: [6] [660/800] eta: 0:01:05 lr: 0.000289 loss: 0.2638 (0.2926) grad: 0.2076 (0.1852) time: 0.5925 data: 0.1859 max mem: 25051 +train: [6] [680/800] eta: 0:00:55 lr: 0.000289 loss: 0.2168 (0.2924) grad: 0.2133 (0.1872) time: 0.4517 data: 0.0028 max mem: 25051 +train: [6] [700/800] eta: 0:00:46 lr: 0.000289 loss: 0.2269 (0.2908) grad: 0.1969 (0.1866) time: 0.4292 data: 0.0025 max mem: 25051 +train: [6] [720/800] eta: 0:00:37 lr: 0.000288 loss: 0.2125 (0.2882) grad: 0.1877 (0.1856) time: 0.4361 data: 0.0034 max mem: 25051 +train: [6] [740/800] eta: 0:00:28 lr: 0.000288 loss: 0.2125 (0.2868) grad: 0.1868 (0.1847) time: 0.6271 data: 0.1949 max mem: 25051 +train: [6] [760/800] eta: 0:00:18 lr: 0.000288 loss: 0.2172 (0.2866) grad: 0.1494 (0.1837) time: 0.4579 data: 0.0031 max mem: 25051 +train: [6] [780/800] eta: 0:00:09 lr: 0.000287 loss: 0.2277 (0.2871) grad: 0.1252 (0.1826) time: 0.4351 data: 0.0033 max mem: 25051 +train: [6] [799/800] eta: 0:00:00 lr: 0.000287 loss: 0.2391 (0.2861) grad: 0.1252 (0.1830) time: 0.4430 data: 0.0031 max mem: 25051 +train: [6] Total time: 0:06:12 (0.4657 s / it) +train: [6] Summary: lr: 0.000287 loss: 0.2391 (0.2861) grad: 0.1252 (0.1830) +eval (validation): [6] [ 0/11] eta: 0:00:40 time: 3.6576 data: 3.4179 max mem: 25051 +eval (validation): [6] [10/11] eta: 0:00:00 time: 0.6069 data: 0.3204 max mem: 25051 +eval (validation): [6] Total time: 0:00:06 (0.6211 s / it) +cv: [6] best hparam: (2.3, 1.0) (029) ('029_lr2.3e+00_wd1.0e+00') loss: 2.318 acc: 0.732 f1: 0.648 bacc: 0.653 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/adni_ad_vs_cn__patch__attn/checkpoint-last.pth +train: [7] [ 0/800] eta: 0:53:44 lr: nan time: 4.0308 data: 3.6656 max mem: 25051 +train: [7] [ 20/800] eta: 0:07:52 lr: 0.000287 loss: 0.2073 (0.2069) grad: 0.1014 (0.1367) time: 0.4346 data: 0.0140 max mem: 25051 +train: [7] [ 40/800] eta: 0:06:33 lr: 0.000286 loss: 0.2308 (0.2827) grad: 0.1583 (0.1658) time: 0.4256 data: 0.0023 max mem: 25051 +train: [7] [ 60/800] eta: 0:06:14 lr: 0.000286 loss: 0.2411 (0.2758) grad: 0.1520 (0.1567) time: 0.4807 data: 0.0028 max mem: 25051 +train: [7] [ 80/800] eta: 0:05:51 lr: 0.000286 loss: 0.2411 (0.2715) grad: 0.1583 (0.1591) time: 0.4368 data: 0.0029 max mem: 25051 +train: [7] [100/800] eta: 0:06:00 lr: 0.000285 loss: 0.2885 (0.2788) grad: 0.1520 (0.1516) time: 0.6205 data: 0.1925 max mem: 25051 +train: [7] [120/800] eta: 0:05:44 lr: 0.000285 loss: 0.2855 (0.2942) grad: 0.1160 (0.1475) time: 0.4667 data: 0.0023 max mem: 25051 +train: [7] [140/800] eta: 0:05:27 lr: 0.000285 loss: 0.2855 (0.2947) grad: 0.1160 (0.1497) time: 0.4288 data: 0.0032 max mem: 25051 +train: [7] [160/800] eta: 0:05:12 lr: 0.000284 loss: 0.2885 (0.2965) grad: 0.1146 (0.1479) time: 0.4295 data: 0.0030 max mem: 25051 +train: [7] [180/800] eta: 0:05:09 lr: 0.000284 loss: 0.2855 (0.2988) grad: 0.1126 (0.1429) time: 0.5932 data: 0.1820 max mem: 25051 +train: [7] [200/800] eta: 0:04:54 lr: 0.000284 loss: 0.2652 (0.2947) grad: 0.1146 (0.1462) time: 0.4096 data: 0.0043 max mem: 25051 +train: [7] [220/800] eta: 0:04:40 lr: 0.000283 loss: 0.2754 (0.2933) grad: 0.1088 (0.1466) time: 0.4087 data: 0.0028 max mem: 25051 +train: [7] [240/800] eta: 0:04:27 lr: 0.000283 loss: 0.2326 (0.2871) grad: 0.1126 (0.1486) time: 0.4146 data: 0.0029 max mem: 25051 +train: [7] [260/800] eta: 0:04:22 lr: 0.000283 loss: 0.2321 (0.2843) grad: 0.1338 (0.1518) time: 0.5941 data: 0.1777 max mem: 25051 +train: [7] [280/800] eta: 0:04:10 lr: 0.000282 loss: 0.2170 (0.2796) grad: 0.1504 (0.1539) time: 0.4171 data: 0.0028 max mem: 25051 +train: [7] [300/800] eta: 0:03:58 lr: 0.000282 loss: 0.2153 (0.2772) grad: 0.1504 (0.1526) time: 0.4177 data: 0.0028 max mem: 25051 +train: [7] [320/800] eta: 0:03:47 lr: 0.000282 loss: 0.2153 (0.2755) grad: 0.1384 (0.1498) time: 0.4220 data: 0.0029 max mem: 25051 +train: [7] [340/800] eta: 0:03:41 lr: 0.000281 loss: 0.2170 (0.2742) grad: 0.1174 (0.1482) time: 0.5907 data: 0.1790 max mem: 25051 +train: [7] [360/800] eta: 0:03:30 lr: 0.000281 loss: 0.2229 (0.2719) grad: 0.1326 (0.1499) time: 0.4236 data: 0.0025 max mem: 25051 +train: [7] [380/800] eta: 0:03:19 lr: 0.000280 loss: 0.2155 (0.2682) grad: 0.1326 (0.1494) time: 0.4229 data: 0.0027 max mem: 25051 +train: [7] [400/800] eta: 0:03:08 lr: 0.000280 loss: 0.2010 (0.2649) grad: 0.1182 (0.1474) time: 0.4277 data: 0.0030 max mem: 25051 +train: [7] [420/800] eta: 0:03:01 lr: 0.000280 loss: 0.2090 (0.2644) grad: 0.1182 (0.1463) time: 0.6074 data: 0.1910 max mem: 25051 +train: [7] [440/800] eta: 0:02:51 lr: 0.000279 loss: 0.2090 (0.2626) grad: 0.1140 (0.1454) time: 0.4112 data: 0.0021 max mem: 25051 +train: [7] [460/800] eta: 0:02:40 lr: 0.000279 loss: 0.2156 (0.2651) grad: 0.1182 (0.1459) time: 0.4063 data: 0.0025 max mem: 25051 +train: [7] [480/800] eta: 0:02:30 lr: 0.000278 loss: 0.2370 (0.2656) grad: 0.1226 (0.1462) time: 0.4185 data: 0.0030 max mem: 25051 +train: [7] [500/800] eta: 0:02:22 lr: 0.000278 loss: 0.2482 (0.2653) grad: 0.1586 (0.1470) time: 0.6183 data: 0.1851 max mem: 25051 +train: [7] [520/800] eta: 0:02:12 lr: 0.000278 loss: 0.2370 (0.2620) grad: 0.1517 (0.1472) time: 0.4325 data: 0.0017 max mem: 25051 +train: [7] [540/800] eta: 0:02:02 lr: 0.000277 loss: 0.2094 (0.2621) grad: 0.1300 (0.1468) time: 0.4303 data: 0.0031 max mem: 25051 +train: [7] [560/800] eta: 0:01:53 lr: 0.000277 loss: 0.2308 (0.2627) grad: 0.1440 (0.1469) time: 0.4244 data: 0.0032 max mem: 25051 +train: [7] [580/800] eta: 0:01:44 lr: 0.000276 loss: 0.2308 (0.2636) grad: 0.1440 (0.1495) time: 0.5911 data: 0.1834 max mem: 25051 +train: [7] [600/800] eta: 0:01:34 lr: 0.000276 loss: 0.2440 (0.2638) grad: 0.1350 (0.1488) time: 0.4309 data: 0.0057 max mem: 25051 +train: [7] [620/800] eta: 0:01:24 lr: 0.000275 loss: 0.2440 (0.2629) grad: 0.1386 (0.1501) time: 0.4191 data: 0.0029 max mem: 25051 +train: [7] [640/800] eta: 0:01:15 lr: 0.000275 loss: 0.2379 (0.2626) grad: 0.1340 (0.1505) time: 0.4177 data: 0.0032 max mem: 25051 +train: [7] [660/800] eta: 0:01:06 lr: 0.000275 loss: 0.2379 (0.2641) grad: 0.1377 (0.1514) time: 0.5955 data: 0.1849 max mem: 25051 +train: [7] [680/800] eta: 0:00:56 lr: 0.000274 loss: 0.1976 (0.2620) grad: 0.1504 (0.1521) time: 0.4447 data: 0.0026 max mem: 25051 +train: [7] [700/800] eta: 0:00:47 lr: 0.000274 loss: 0.2428 (0.2612) grad: 0.1492 (0.1530) time: 0.4294 data: 0.0028 max mem: 25051 +train: [7] [720/800] eta: 0:00:37 lr: 0.000273 loss: 0.2428 (0.2608) grad: 0.1539 (0.1531) time: 0.4295 data: 0.0029 max mem: 25051 +train: [7] [740/800] eta: 0:00:28 lr: 0.000273 loss: 0.2407 (0.2619) grad: 0.1492 (0.1529) time: 0.5960 data: 0.1772 max mem: 25051 +train: [7] [760/800] eta: 0:00:18 lr: 0.000272 loss: 0.2467 (0.2621) grad: 0.1239 (0.1523) time: 0.4318 data: 0.0023 max mem: 25051 +train: [7] [780/800] eta: 0:00:09 lr: 0.000272 loss: 0.2489 (0.2626) grad: 0.1277 (0.1533) time: 0.4233 data: 0.0030 max mem: 25051 +train: [7] [799/800] eta: 0:00:00 lr: 0.000271 loss: 0.2708 (0.2633) grad: 0.1106 (0.1526) time: 0.4227 data: 0.0032 max mem: 25051 +train: [7] Total time: 0:06:16 (0.4709 s / it) +train: [7] Summary: lr: 0.000271 loss: 0.2708 (0.2633) grad: 0.1106 (0.1526) +eval (validation): [7] [ 0/11] eta: 0:00:38 time: 3.5083 data: 3.2701 max mem: 25051 +eval (validation): [7] [10/11] eta: 0:00:00 time: 0.5867 data: 0.2988 max mem: 25051 +eval (validation): [7] Total time: 0:00:06 (0.6007 s / it) +cv: [7] best hparam: (2.3, 1.0) (029) ('029_lr2.3e+00_wd1.0e+00') loss: 2.404 acc: 0.732 f1: 0.648 bacc: 0.653 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/adni_ad_vs_cn__patch__attn/checkpoint-last.pth +train: [8] [ 0/800] eta: 0:47:14 lr: nan time: 3.5433 data: 3.2100 max mem: 25051 +train: [8] [ 20/800] eta: 0:07:20 lr: 0.000271 loss: 0.2233 (0.2355) grad: 0.1728 (0.1751) time: 0.4162 data: 0.0032 max mem: 25051 +train: [8] [ 40/800] eta: 0:06:12 lr: 0.000270 loss: 0.1896 (0.2328) grad: 0.1936 (0.1993) time: 0.4102 data: 0.0022 max mem: 25051 +train: [8] [ 60/800] eta: 0:05:44 lr: 0.000270 loss: 0.2394 (0.2465) grad: 0.1936 (0.1902) time: 0.4169 data: 0.0029 max mem: 25051 +train: [8] [ 80/800] eta: 0:05:25 lr: 0.000270 loss: 0.2515 (0.2563) grad: 0.1755 (0.1881) time: 0.4113 data: 0.0030 max mem: 25051 +train: [8] [100/800] eta: 0:05:38 lr: 0.000269 loss: 0.2522 (0.2597) grad: 0.1603 (0.1750) time: 0.6106 data: 0.1793 max mem: 25051 +train: [8] [120/800] eta: 0:05:22 lr: 0.000269 loss: 0.2466 (0.2498) grad: 0.1526 (0.1751) time: 0.4251 data: 0.0023 max mem: 25051 +train: [8] [140/800] eta: 0:05:07 lr: 0.000268 loss: 0.2466 (0.2493) grad: 0.1405 (0.1822) time: 0.4148 data: 0.0032 max mem: 25051 +train: [8] [160/800] eta: 0:04:53 lr: 0.000268 loss: 0.2294 (0.2541) grad: 0.1405 (0.1784) time: 0.4129 data: 0.0030 max mem: 25051 +train: [8] [180/800] eta: 0:04:53 lr: 0.000267 loss: 0.2294 (0.2547) grad: 0.1304 (0.1730) time: 0.5871 data: 0.1788 max mem: 25051 +train: [8] [200/800] eta: 0:04:40 lr: 0.000267 loss: 0.2589 (0.2547) grad: 0.1304 (0.1713) time: 0.4182 data: 0.0063 max mem: 25051 +train: [8] [220/800] eta: 0:04:29 lr: 0.000266 loss: 0.2613 (0.2530) grad: 0.1250 (0.1696) time: 0.4315 data: 0.0029 max mem: 25051 +train: [8] [240/800] eta: 0:04:18 lr: 0.000266 loss: 0.2172 (0.2499) grad: 0.1250 (0.1677) time: 0.4206 data: 0.0029 max mem: 25051 +train: [8] [260/800] eta: 0:04:14 lr: 0.000265 loss: 0.2118 (0.2520) grad: 0.1250 (0.1670) time: 0.5873 data: 0.1798 max mem: 25051 +train: [8] [280/800] eta: 0:04:03 lr: 0.000265 loss: 0.1996 (0.2495) grad: 0.1241 (0.1663) time: 0.4394 data: 0.0028 max mem: 25051 +train: [8] [300/800] eta: 0:03:52 lr: 0.000264 loss: 0.1857 (0.2488) grad: 0.1269 (0.1683) time: 0.4173 data: 0.0030 max mem: 25051 +train: [8] [320/800] eta: 0:03:41 lr: 0.000264 loss: 0.1920 (0.2492) grad: 0.1269 (0.1665) time: 0.4191 data: 0.0032 max mem: 25051 +train: [8] [340/800] eta: 0:03:36 lr: 0.000263 loss: 0.1920 (0.2459) grad: 0.1241 (0.1631) time: 0.6187 data: 0.1790 max mem: 25051 +train: [8] [360/800] eta: 0:03:26 lr: 0.000263 loss: 0.1868 (0.2438) grad: 0.1269 (0.1615) time: 0.4164 data: 0.0026 max mem: 25051 +train: [8] [380/800] eta: 0:03:15 lr: 0.000262 loss: 0.1920 (0.2441) grad: 0.1425 (0.1638) time: 0.4193 data: 0.0031 max mem: 25051 +train: [8] [400/800] eta: 0:03:05 lr: 0.000262 loss: 0.2035 (0.2481) grad: 0.1494 (0.1651) time: 0.4125 data: 0.0032 max mem: 25051 +train: [8] [420/800] eta: 0:02:58 lr: 0.000261 loss: 0.2348 (0.2469) grad: 0.1549 (0.1664) time: 0.6227 data: 0.1785 max mem: 25051 +train: [8] [440/800] eta: 0:02:48 lr: 0.000260 loss: 0.2348 (0.2484) grad: 0.1758 (0.1676) time: 0.4222 data: 0.0029 max mem: 25051 +train: [8] [460/800] eta: 0:02:38 lr: 0.000260 loss: 0.2360 (0.2490) grad: 0.1603 (0.1651) time: 0.4197 data: 0.0031 max mem: 25051 +train: [8] [480/800] eta: 0:02:28 lr: 0.000259 loss: 0.2360 (0.2534) grad: 0.1090 (0.1637) time: 0.4200 data: 0.0030 max mem: 25051 +train: [8] [500/800] eta: 0:02:20 lr: 0.000259 loss: 0.2360 (0.2522) grad: 0.0961 (0.1620) time: 0.5838 data: 0.1749 max mem: 25051 +train: [8] [520/800] eta: 0:02:10 lr: 0.000258 loss: 0.2360 (0.2512) grad: 0.0919 (0.1619) time: 0.4114 data: 0.0028 max mem: 25051 +train: [8] [540/800] eta: 0:02:00 lr: 0.000258 loss: 0.2510 (0.2533) grad: 0.1060 (0.1624) time: 0.4236 data: 0.0030 max mem: 25051 +train: [8] [560/800] eta: 0:01:51 lr: 0.000257 loss: 0.2020 (0.2509) grad: 0.1626 (0.1625) time: 0.4067 data: 0.0033 max mem: 25051 +train: [8] [580/800] eta: 0:01:42 lr: 0.000257 loss: 0.2293 (0.2537) grad: 0.1692 (0.1645) time: 0.5822 data: 0.1800 max mem: 25051 +train: [8] [600/800] eta: 0:01:33 lr: 0.000256 loss: 0.2293 (0.2528) grad: 0.1591 (0.1632) time: 0.4495 data: 0.0033 max mem: 25051 +train: [8] [620/800] eta: 0:01:23 lr: 0.000256 loss: 0.1852 (0.2526) grad: 0.1591 (0.1631) time: 0.4180 data: 0.0030 max mem: 25051 +train: [8] [640/800] eta: 0:01:14 lr: 0.000255 loss: 0.2337 (0.2523) grad: 0.1497 (0.1623) time: 0.4168 data: 0.0031 max mem: 25051 +train: [8] [660/800] eta: 0:01:05 lr: 0.000254 loss: 0.1999 (0.2512) grad: 0.1158 (0.1621) time: 0.5876 data: 0.1818 max mem: 25051 +train: [8] [680/800] eta: 0:00:55 lr: 0.000254 loss: 0.2143 (0.2502) grad: 0.1158 (0.1616) time: 0.4165 data: 0.0028 max mem: 25051 +train: [8] [700/800] eta: 0:00:46 lr: 0.000253 loss: 0.2143 (0.2499) grad: 0.1072 (0.1605) time: 0.4168 data: 0.0022 max mem: 25051 +train: [8] [720/800] eta: 0:00:37 lr: 0.000253 loss: 0.2143 (0.2500) grad: 0.1072 (0.1618) time: 0.4165 data: 0.0032 max mem: 25051 +train: [8] [740/800] eta: 0:00:28 lr: 0.000252 loss: 0.2236 (0.2509) grad: 0.1522 (0.1627) time: 0.5995 data: 0.1769 max mem: 25051 +train: [8] [760/800] eta: 0:00:18 lr: 0.000252 loss: 0.2567 (0.2522) grad: 0.1522 (0.1625) time: 0.4240 data: 0.0025 max mem: 25051 +train: [8] [780/800] eta: 0:00:09 lr: 0.000251 loss: 0.2236 (0.2508) grad: 0.1522 (0.1615) time: 0.4113 data: 0.0030 max mem: 25051 +train: [8] [799/800] eta: 0:00:00 lr: 0.000250 loss: 0.2236 (0.2506) grad: 0.1273 (0.1603) time: 0.4180 data: 0.0030 max mem: 25051 +train: [8] Total time: 0:06:10 (0.4635 s / it) +train: [8] Summary: lr: 0.000250 loss: 0.2236 (0.2506) grad: 0.1273 (0.1603) +eval (validation): [8] [ 0/11] eta: 0:00:39 time: 3.5614 data: 3.2931 max mem: 25051 +eval (validation): [8] [10/11] eta: 0:00:00 time: 0.5848 data: 0.3010 max mem: 25051 +eval (validation): [8] Total time: 0:00:06 (0.5984 s / it) +cv: [8] best hparam: (2.3, 1.0) (029) ('029_lr2.3e+00_wd1.0e+00') loss: 2.479 acc: 0.732 f1: 0.648 bacc: 0.653 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/adni_ad_vs_cn__patch__attn/checkpoint-last.pth +train: [9] [ 0/800] eta: 0:46:52 lr: nan time: 3.5158 data: 3.1842 max mem: 25051 +train: [9] [ 20/800] eta: 0:07:26 lr: 0.000250 loss: 0.1974 (0.2576) grad: 0.1143 (0.1289) time: 0.4250 data: 0.0052 max mem: 25051 +train: [9] [ 40/800] eta: 0:06:18 lr: 0.000249 loss: 0.1974 (0.2520) grad: 0.1143 (0.1287) time: 0.4204 data: 0.0024 max mem: 25051 +train: [9] [ 60/800] eta: 0:05:48 lr: 0.000249 loss: 0.1974 (0.2298) grad: 0.1150 (0.1242) time: 0.4151 data: 0.0023 max mem: 25051 +train: [9] [ 80/800] eta: 0:05:29 lr: 0.000248 loss: 0.2079 (0.2475) grad: 0.1268 (0.1349) time: 0.4158 data: 0.0029 max mem: 25051 +train: [9] [100/800] eta: 0:05:42 lr: 0.000248 loss: 0.2202 (0.2467) grad: 0.1309 (0.1320) time: 0.6174 data: 0.1793 max mem: 25051 +train: [9] [120/800] eta: 0:05:24 lr: 0.000247 loss: 0.2238 (0.2585) grad: 0.1313 (0.1413) time: 0.4190 data: 0.0028 max mem: 25051 +train: [9] [140/800] eta: 0:05:09 lr: 0.000246 loss: 0.2117 (0.2495) grad: 0.1309 (0.1415) time: 0.4175 data: 0.0032 max mem: 25051 +train: [9] [160/800] eta: 0:04:55 lr: 0.000246 loss: 0.2117 (0.2508) grad: 0.1112 (0.1378) time: 0.4085 data: 0.0028 max mem: 25051 +train: [9] [180/800] eta: 0:04:54 lr: 0.000245 loss: 0.2242 (0.2523) grad: 0.1280 (0.1389) time: 0.5823 data: 0.1774 max mem: 25051 +train: [9] [200/800] eta: 0:04:40 lr: 0.000244 loss: 0.2170 (0.2494) grad: 0.1280 (0.1380) time: 0.4082 data: 0.0016 max mem: 25051 +train: [9] [220/800] eta: 0:04:28 lr: 0.000244 loss: 0.2726 (0.2609) grad: 0.1438 (0.1395) time: 0.4087 data: 0.0027 max mem: 25051 +train: [9] [240/800] eta: 0:04:16 lr: 0.000243 loss: 0.2442 (0.2568) grad: 0.1508 (0.1411) time: 0.4095 data: 0.0030 max mem: 25051 +train: [9] [260/800] eta: 0:04:13 lr: 0.000243 loss: 0.2456 (0.2642) grad: 0.1438 (0.1410) time: 0.5927 data: 0.1845 max mem: 25051 +train: [9] [280/800] eta: 0:04:01 lr: 0.000242 loss: 0.2589 (0.2626) grad: 0.1481 (0.1448) time: 0.4130 data: 0.0026 max mem: 25051 +train: [9] [300/800] eta: 0:03:50 lr: 0.000241 loss: 0.1920 (0.2568) grad: 0.1131 (0.1430) time: 0.4166 data: 0.0030 max mem: 25051 +train: [9] [320/800] eta: 0:03:40 lr: 0.000241 loss: 0.2005 (0.2581) grad: 0.0961 (0.1421) time: 0.4133 data: 0.0028 max mem: 25051 +train: [9] [340/800] eta: 0:03:35 lr: 0.000240 loss: 0.1896 (0.2580) grad: 0.0961 (0.1422) time: 0.6200 data: 0.1804 max mem: 25051 +train: [9] [360/800] eta: 0:03:24 lr: 0.000240 loss: 0.1817 (0.2544) grad: 0.0927 (0.1402) time: 0.4068 data: 0.0025 max mem: 25051 +train: [9] [380/800] eta: 0:03:14 lr: 0.000239 loss: 0.2197 (0.2521) grad: 0.0927 (0.1386) time: 0.4184 data: 0.0030 max mem: 25051 +train: [9] [400/800] eta: 0:03:03 lr: 0.000238 loss: 0.2115 (0.2534) grad: 0.1076 (0.1396) time: 0.4136 data: 0.0029 max mem: 25051 +train: [9] [420/800] eta: 0:02:57 lr: 0.000238 loss: 0.2068 (0.2514) grad: 0.1076 (0.1392) time: 0.5963 data: 0.1796 max mem: 25051 +train: [9] [440/800] eta: 0:02:47 lr: 0.000237 loss: 0.2068 (0.2490) grad: 0.0859 (0.1355) time: 0.4282 data: 0.0031 max mem: 25051 +train: [9] [460/800] eta: 0:02:37 lr: 0.000236 loss: 0.2121 (0.2525) grad: 0.0859 (0.1342) time: 0.4139 data: 0.0031 max mem: 25051 +train: [9] [480/800] eta: 0:02:27 lr: 0.000236 loss: 0.2068 (0.2515) grad: 0.0859 (0.1343) time: 0.4122 data: 0.0031 max mem: 25051 +train: [9] [500/800] eta: 0:02:19 lr: 0.000235 loss: 0.2121 (0.2515) grad: 0.0983 (0.1362) time: 0.5976 data: 0.1931 max mem: 25051 +train: [9] [520/800] eta: 0:02:09 lr: 0.000234 loss: 0.2446 (0.2531) grad: 0.1441 (0.1373) time: 0.4219 data: 0.0018 max mem: 25051 +train: [9] [540/800] eta: 0:02:00 lr: 0.000234 loss: 0.2446 (0.2522) grad: 0.1840 (0.1389) time: 0.4139 data: 0.0024 max mem: 25051 +train: [9] [560/800] eta: 0:01:50 lr: 0.000233 loss: 0.1972 (0.2495) grad: 0.1691 (0.1383) time: 0.4298 data: 0.0031 max mem: 25051 +train: [9] [580/800] eta: 0:01:42 lr: 0.000232 loss: 0.1984 (0.2518) grad: 0.0997 (0.1362) time: 0.5827 data: 0.1789 max mem: 25051 +train: [9] [600/800] eta: 0:01:32 lr: 0.000232 loss: 0.1972 (0.2521) grad: 0.1176 (0.1365) time: 0.4335 data: 0.0033 max mem: 25051 +train: [9] [620/800] eta: 0:01:23 lr: 0.000231 loss: 0.1984 (0.2510) grad: 0.0913 (0.1361) time: 0.4079 data: 0.0028 max mem: 25051 +train: [9] [640/800] eta: 0:01:13 lr: 0.000230 loss: 0.2314 (0.2504) grad: 0.0991 (0.1367) time: 0.4161 data: 0.0032 max mem: 25051 +train: [9] [660/800] eta: 0:01:05 lr: 0.000230 loss: 0.2054 (0.2499) grad: 0.1263 (0.1365) time: 0.5886 data: 0.1841 max mem: 25051 +train: [9] [680/800] eta: 0:00:55 lr: 0.000229 loss: 0.2215 (0.2495) grad: 0.1093 (0.1355) time: 0.4071 data: 0.0024 max mem: 25051 +train: [9] [700/800] eta: 0:00:46 lr: 0.000228 loss: 0.2354 (0.2504) grad: 0.1205 (0.1360) time: 0.4225 data: 0.0030 max mem: 25051 +train: [9] [720/800] eta: 0:00:36 lr: 0.000228 loss: 0.2215 (0.2502) grad: 0.0967 (0.1354) time: 0.4192 data: 0.0032 max mem: 25051 +train: [9] [740/800] eta: 0:00:27 lr: 0.000227 loss: 0.2103 (0.2502) grad: 0.1393 (0.1382) time: 0.5891 data: 0.1811 max mem: 25051 +train: [9] [760/800] eta: 0:00:18 lr: 0.000226 loss: 0.2053 (0.2492) grad: 0.1463 (0.1403) time: 0.4098 data: 0.0023 max mem: 25051 +train: [9] [780/800] eta: 0:00:09 lr: 0.000226 loss: 0.2085 (0.2503) grad: 0.1463 (0.1409) time: 0.4060 data: 0.0027 max mem: 25051 +train: [9] [799/800] eta: 0:00:00 lr: 0.000225 loss: 0.2098 (0.2494) grad: 0.1452 (0.1408) time: 0.4053 data: 0.0029 max mem: 25051 +train: [9] Total time: 0:06:08 (0.4603 s / it) +train: [9] Summary: lr: 0.000225 loss: 0.2098 (0.2494) grad: 0.1452 (0.1408) +eval (validation): [9] [ 0/11] eta: 0:00:38 time: 3.5264 data: 3.2954 max mem: 25051 +eval (validation): [9] [10/11] eta: 0:00:00 time: 0.5788 data: 0.3044 max mem: 25051 +eval (validation): [9] Total time: 0:00:06 (0.5925 s / it) +cv: [9] best hparam: (2.3, 1.0) (029) ('029_lr2.3e+00_wd1.0e+00') loss: 2.516 acc: 0.732 f1: 0.648 bacc: 0.653 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/adni_ad_vs_cn__patch__attn/checkpoint-last.pth +train: [10] [ 0/800] eta: 0:49:55 lr: nan time: 3.7449 data: 3.4149 max mem: 25051 +train: [10] [ 20/800] eta: 0:07:44 lr: 0.000224 loss: 0.1711 (0.1789) grad: 0.1085 (0.1333) time: 0.4377 data: 0.0026 max mem: 25051 +train: [10] [ 40/800] eta: 0:06:26 lr: 0.000224 loss: 0.1717 (0.1982) grad: 0.0935 (0.1179) time: 0.4171 data: 0.0024 max mem: 25051 +train: [10] [ 60/800] eta: 0:05:53 lr: 0.000223 loss: 0.2123 (0.2534) grad: 0.1277 (0.1593) time: 0.4153 data: 0.0031 max mem: 25051 +train: [10] [ 80/800] eta: 0:05:32 lr: 0.000222 loss: 0.2163 (0.2471) grad: 0.1421 (0.1705) time: 0.4153 data: 0.0029 max mem: 25051 +train: [10] [100/800] eta: 0:05:44 lr: 0.000222 loss: 0.2163 (0.2353) grad: 0.1277 (0.1573) time: 0.6162 data: 0.1774 max mem: 25051 +train: [10] [120/800] eta: 0:05:27 lr: 0.000221 loss: 0.2426 (0.2410) grad: 0.1359 (0.1557) time: 0.4216 data: 0.0029 max mem: 25051 +train: [10] [140/800] eta: 0:05:11 lr: 0.000220 loss: 0.2090 (0.2343) grad: 0.1225 (0.1504) time: 0.4164 data: 0.0031 max mem: 25051 +train: [10] [160/800] eta: 0:04:57 lr: 0.000220 loss: 0.1852 (0.2301) grad: 0.1168 (0.1539) time: 0.4106 data: 0.0029 max mem: 25051 +train: [10] [180/800] eta: 0:04:57 lr: 0.000219 loss: 0.1861 (0.2314) grad: 0.1192 (0.1541) time: 0.6058 data: 0.1790 max mem: 25051 +train: [10] [200/800] eta: 0:04:44 lr: 0.000218 loss: 0.1969 (0.2299) grad: 0.1175 (0.1524) time: 0.4139 data: 0.0027 max mem: 25051 +train: [10] [220/800] eta: 0:04:31 lr: 0.000217 loss: 0.2033 (0.2326) grad: 0.1099 (0.1467) time: 0.4238 data: 0.0030 max mem: 25051 +train: [10] [240/800] eta: 0:04:20 lr: 0.000217 loss: 0.2171 (0.2346) grad: 0.1007 (0.1468) time: 0.4149 data: 0.0029 max mem: 25051 +train: [10] [260/800] eta: 0:04:17 lr: 0.000216 loss: 0.2023 (0.2324) grad: 0.0951 (0.1442) time: 0.6251 data: 0.1833 max mem: 25051 +train: [10] [280/800] eta: 0:04:05 lr: 0.000215 loss: 0.2023 (0.2347) grad: 0.0951 (0.1412) time: 0.4236 data: 0.0027 max mem: 25051 +train: [10] [300/800] eta: 0:03:54 lr: 0.000215 loss: 0.2023 (0.2356) grad: 0.1007 (0.1410) time: 0.4256 data: 0.0032 max mem: 25051 +train: [10] [320/800] eta: 0:03:44 lr: 0.000214 loss: 0.2000 (0.2339) grad: 0.0896 (0.1365) time: 0.4211 data: 0.0030 max mem: 25051 +train: [10] [340/800] eta: 0:03:38 lr: 0.000213 loss: 0.2260 (0.2340) grad: 0.0889 (0.1367) time: 0.5970 data: 0.1833 max mem: 25051 +train: [10] [360/800] eta: 0:03:27 lr: 0.000213 loss: 0.1782 (0.2308) grad: 0.0992 (0.1365) time: 0.4348 data: 0.0029 max mem: 25051 +train: [10] [380/800] eta: 0:03:17 lr: 0.000212 loss: 0.1782 (0.2298) grad: 0.0785 (0.1356) time: 0.4271 data: 0.0031 max mem: 25051 +train: [10] [400/800] eta: 0:03:06 lr: 0.000211 loss: 0.1946 (0.2339) grad: 0.1017 (0.1340) time: 0.4200 data: 0.0029 max mem: 25051 +train: [10] [420/800] eta: 0:03:00 lr: 0.000210 loss: 0.2088 (0.2350) grad: 0.1017 (0.1343) time: 0.6319 data: 0.1793 max mem: 25051 +train: [10] [440/800] eta: 0:02:50 lr: 0.000210 loss: 0.2161 (0.2342) grad: 0.1050 (0.1338) time: 0.4282 data: 0.0024 max mem: 25051 +train: [10] [460/800] eta: 0:02:39 lr: 0.000209 loss: 0.2105 (0.2327) grad: 0.0700 (0.1321) time: 0.4153 data: 0.0031 max mem: 25051 +train: [10] [480/800] eta: 0:02:29 lr: 0.000208 loss: 0.1900 (0.2328) grad: 0.1142 (0.1353) time: 0.4246 data: 0.0031 max mem: 25051 +train: [10] [500/800] eta: 0:02:22 lr: 0.000207 loss: 0.1825 (0.2312) grad: 0.1147 (0.1368) time: 0.5911 data: 0.1814 max mem: 25051 +train: [10] [520/800] eta: 0:02:11 lr: 0.000207 loss: 0.1847 (0.2331) grad: 0.1181 (0.1380) time: 0.4180 data: 0.0026 max mem: 25051 +train: [10] [540/800] eta: 0:02:01 lr: 0.000206 loss: 0.1776 (0.2315) grad: 0.1603 (0.1411) time: 0.4094 data: 0.0029 max mem: 25051 +train: [10] [560/800] eta: 0:01:52 lr: 0.000205 loss: 0.2111 (0.2308) grad: 0.1603 (0.1414) time: 0.4443 data: 0.0031 max mem: 25051 +train: [10] [580/800] eta: 0:01:43 lr: 0.000205 loss: 0.2143 (0.2311) grad: 0.1634 (0.1434) time: 0.5860 data: 0.1767 max mem: 25051 +train: [10] [600/800] eta: 0:01:34 lr: 0.000204 loss: 0.2098 (0.2316) grad: 0.1603 (0.1438) time: 0.4167 data: 0.0027 max mem: 25051 +train: [10] [620/800] eta: 0:01:24 lr: 0.000203 loss: 0.2098 (0.2308) grad: 0.1536 (0.1450) time: 0.4109 data: 0.0024 max mem: 25051 +train: [10] [640/800] eta: 0:01:14 lr: 0.000202 loss: 0.1986 (0.2309) grad: 0.1384 (0.1436) time: 0.4155 data: 0.0031 max mem: 25051 +train: [10] [660/800] eta: 0:01:05 lr: 0.000202 loss: 0.1945 (0.2317) grad: 0.1341 (0.1430) time: 0.5826 data: 0.1756 max mem: 25051 +train: [10] [680/800] eta: 0:00:56 lr: 0.000201 loss: 0.1947 (0.2311) grad: 0.1206 (0.1428) time: 0.4474 data: 0.0029 max mem: 25051 +train: [10] [700/800] eta: 0:00:46 lr: 0.000200 loss: 0.1947 (0.2303) grad: 0.1023 (0.1432) time: 0.4290 data: 0.0030 max mem: 25051 +train: [10] [720/800] eta: 0:00:37 lr: 0.000199 loss: 0.1972 (0.2308) grad: 0.0876 (0.1414) time: 0.4278 data: 0.0032 max mem: 25051 +train: [10] [740/800] eta: 0:00:28 lr: 0.000199 loss: 0.2146 (0.2320) grad: 0.1022 (0.1413) time: 0.5925 data: 0.1787 max mem: 25051 +train: [10] [760/800] eta: 0:00:18 lr: 0.000198 loss: 0.2266 (0.2315) grad: 0.1040 (0.1417) time: 0.4305 data: 0.0023 max mem: 25051 +train: [10] [780/800] eta: 0:00:09 lr: 0.000197 loss: 0.2305 (0.2324) grad: 0.1060 (0.1426) time: 0.4182 data: 0.0028 max mem: 25051 +train: [10] [799/800] eta: 0:00:00 lr: 0.000196 loss: 0.2364 (0.2328) grad: 0.1161 (0.1414) time: 0.4122 data: 0.0033 max mem: 25051 +train: [10] Total time: 0:06:13 (0.4674 s / it) +train: [10] Summary: lr: 0.000196 loss: 0.2364 (0.2328) grad: 0.1161 (0.1414) +eval (validation): [10] [ 0/11] eta: 0:00:39 time: 3.5560 data: 3.2738 max mem: 25051 +eval (validation): [10] [10/11] eta: 0:00:00 time: 0.5763 data: 0.2987 max mem: 25051 +eval (validation): [10] Total time: 0:00:06 (0.5908 s / it) +cv: [10] best hparam: (0.23, 1.0) (015) ('015_lr2.3e-01_wd1.0e+00') loss: 0.583 acc: 0.756 f1: 0.669 bacc: 0.669 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/adni_ad_vs_cn__patch__attn/checkpoint-last.pth +train: [11] [ 0/800] eta: 0:47:49 lr: nan time: 3.5873 data: 3.2535 max mem: 25051 +train: [11] [ 20/800] eta: 0:07:36 lr: 0.000196 loss: 0.1771 (0.2217) grad: 0.1884 (0.2072) time: 0.4350 data: 0.0033 max mem: 25051 +train: [11] [ 40/800] eta: 0:06:22 lr: 0.000195 loss: 0.1771 (0.2139) grad: 0.1837 (0.1795) time: 0.4178 data: 0.0028 max mem: 25051 +train: [11] [ 60/800] eta: 0:05:50 lr: 0.000194 loss: 0.2007 (0.2196) grad: 0.1329 (0.1527) time: 0.4143 data: 0.0032 max mem: 25051 +train: [11] [ 80/800] eta: 0:05:31 lr: 0.000193 loss: 0.2007 (0.2276) grad: 0.1308 (0.1404) time: 0.4206 data: 0.0029 max mem: 25051 +train: [11] [100/800] eta: 0:05:44 lr: 0.000193 loss: 0.2102 (0.2264) grad: 0.1074 (0.1384) time: 0.6171 data: 0.1960 max mem: 25051 +train: [11] [120/800] eta: 0:05:25 lr: 0.000192 loss: 0.2144 (0.2250) grad: 0.1013 (0.1376) time: 0.4137 data: 0.0024 max mem: 25051 +train: [11] [140/800] eta: 0:05:10 lr: 0.000191 loss: 0.2302 (0.2311) grad: 0.1066 (0.1413) time: 0.4148 data: 0.0031 max mem: 25051 +train: [11] [160/800] eta: 0:04:55 lr: 0.000190 loss: 0.2013 (0.2254) grad: 0.1294 (0.1465) time: 0.4041 data: 0.0030 max mem: 25051 +train: [11] [180/800] eta: 0:04:56 lr: 0.000190 loss: 0.1956 (0.2249) grad: 0.1294 (0.1491) time: 0.6062 data: 0.1796 max mem: 25051 +train: [11] [200/800] eta: 0:04:42 lr: 0.000189 loss: 0.1943 (0.2265) grad: 0.1424 (0.1478) time: 0.4148 data: 0.0030 max mem: 25051 +train: [11] [220/800] eta: 0:04:30 lr: 0.000188 loss: 0.1943 (0.2281) grad: 0.1424 (0.1453) time: 0.4137 data: 0.0031 max mem: 25051 +train: [11] [240/800] eta: 0:04:18 lr: 0.000187 loss: 0.1943 (0.2235) grad: 0.1372 (0.1429) time: 0.4211 data: 0.0029 max mem: 25051 +train: [11] [260/800] eta: 0:04:14 lr: 0.000187 loss: 0.1943 (0.2239) grad: 0.1083 (0.1383) time: 0.5837 data: 0.1762 max mem: 25051 +train: [11] [280/800] eta: 0:04:03 lr: 0.000186 loss: 0.1801 (0.2220) grad: 0.0802 (0.1334) time: 0.4117 data: 0.0029 max mem: 25051 +train: [11] [300/800] eta: 0:03:51 lr: 0.000185 loss: 0.1894 (0.2215) grad: 0.0835 (0.1328) time: 0.4108 data: 0.0031 max mem: 25051 +train: [11] [320/800] eta: 0:03:41 lr: 0.000184 loss: 0.2208 (0.2266) grad: 0.0804 (0.1328) time: 0.4170 data: 0.0030 max mem: 25051 +train: [11] [340/800] eta: 0:03:36 lr: 0.000184 loss: 0.2390 (0.2311) grad: 0.1304 (0.1357) time: 0.6157 data: 0.1801 max mem: 25051 +train: [11] [360/800] eta: 0:03:25 lr: 0.000183 loss: 0.2390 (0.2295) grad: 0.1382 (0.1364) time: 0.4324 data: 0.0028 max mem: 25051 +train: [11] [380/800] eta: 0:03:15 lr: 0.000182 loss: 0.2619 (0.2324) grad: 0.1349 (0.1349) time: 0.4251 data: 0.0031 max mem: 25051 +train: [11] [400/800] eta: 0:03:05 lr: 0.000181 loss: 0.2228 (0.2342) grad: 0.1349 (0.1360) time: 0.4289 data: 0.0030 max mem: 25051 +train: [11] [420/800] eta: 0:02:59 lr: 0.000181 loss: 0.2228 (0.2335) grad: 0.1180 (0.1352) time: 0.6649 data: 0.1955 max mem: 25051 +train: [11] [440/800] eta: 0:02:49 lr: 0.000180 loss: 0.2228 (0.2328) grad: 0.1112 (0.1349) time: 0.4393 data: 0.0025 max mem: 25051 +train: [11] [460/800] eta: 0:02:39 lr: 0.000179 loss: 0.2189 (0.2316) grad: 0.1198 (0.1343) time: 0.4375 data: 0.0034 max mem: 25051 +train: [11] [480/800] eta: 0:02:29 lr: 0.000178 loss: 0.1843 (0.2304) grad: 0.1180 (0.1340) time: 0.4243 data: 0.0032 max mem: 25051 +train: [11] [500/800] eta: 0:02:22 lr: 0.000177 loss: 0.1815 (0.2289) grad: 0.1236 (0.1334) time: 0.6090 data: 0.1997 max mem: 25051 +train: [11] [520/800] eta: 0:02:12 lr: 0.000177 loss: 0.1843 (0.2269) grad: 0.1096 (0.1322) time: 0.4294 data: 0.0018 max mem: 25051 +train: [11] [540/800] eta: 0:02:02 lr: 0.000176 loss: 0.1843 (0.2272) grad: 0.1099 (0.1323) time: 0.4278 data: 0.0024 max mem: 25051 +train: [11] [560/800] eta: 0:01:52 lr: 0.000175 loss: 0.1893 (0.2261) grad: 0.0954 (0.1310) time: 0.4274 data: 0.0031 max mem: 25051 +train: [11] [580/800] eta: 0:01:44 lr: 0.000174 loss: 0.1887 (0.2251) grad: 0.1099 (0.1334) time: 0.6105 data: 0.1885 max mem: 25051 +train: [11] [600/800] eta: 0:01:34 lr: 0.000174 loss: 0.1887 (0.2248) grad: 0.1291 (0.1342) time: 0.4303 data: 0.0035 max mem: 25051 +train: [11] [620/800] eta: 0:01:24 lr: 0.000173 loss: 0.1859 (0.2253) grad: 0.1493 (0.1344) time: 0.4302 data: 0.0018 max mem: 25051 +train: [11] [640/800] eta: 0:01:15 lr: 0.000172 loss: 0.1859 (0.2244) grad: 0.1512 (0.1338) time: 0.4303 data: 0.0031 max mem: 25051 +train: [11] [660/800] eta: 0:01:06 lr: 0.000171 loss: 0.1801 (0.2237) grad: 0.1198 (0.1349) time: 0.5911 data: 0.1815 max mem: 25051 +train: [11] [680/800] eta: 0:00:56 lr: 0.000170 loss: 0.1778 (0.2230) grad: 0.1198 (0.1346) time: 0.4148 data: 0.0025 max mem: 25051 +train: [11] [700/800] eta: 0:00:47 lr: 0.000170 loss: 0.1798 (0.2242) grad: 0.1198 (0.1363) time: 0.4288 data: 0.0026 max mem: 25051 +train: [11] [720/800] eta: 0:00:37 lr: 0.000169 loss: 0.1833 (0.2237) grad: 0.1289 (0.1369) time: 0.4320 data: 0.0031 max mem: 25051 +train: [11] [740/800] eta: 0:00:28 lr: 0.000168 loss: 0.2081 (0.2237) grad: 0.1140 (0.1359) time: 0.6072 data: 0.1862 max mem: 25051 +train: [11] [760/800] eta: 0:00:18 lr: 0.000167 loss: 0.2377 (0.2248) grad: 0.1117 (0.1358) time: 0.4386 data: 0.0024 max mem: 25051 +train: [11] [780/800] eta: 0:00:09 lr: 0.000167 loss: 0.2377 (0.2256) grad: 0.1052 (0.1349) time: 0.4320 data: 0.0030 max mem: 25051 +train: [11] [799/800] eta: 0:00:00 lr: 0.000166 loss: 0.2377 (0.2262) grad: 0.0983 (0.1349) time: 0.4319 data: 0.0030 max mem: 25051 +train: [11] Total time: 0:06:16 (0.4706 s / it) +train: [11] Summary: lr: 0.000166 loss: 0.2377 (0.2262) grad: 0.0983 (0.1349) +eval (validation): [11] [ 0/11] eta: 0:00:39 time: 3.5775 data: 3.3543 max mem: 25051 +eval (validation): [11] [10/11] eta: 0:00:00 time: 0.5929 data: 0.3153 max mem: 25051 +eval (validation): [11] Total time: 0:00:06 (0.6064 s / it) +cv: [11] best hparam: (2.3, 1.0) (029) ('029_lr2.3e+00_wd1.0e+00') loss: 2.581 acc: 0.732 f1: 0.648 bacc: 0.653 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/adni_ad_vs_cn__patch__attn/checkpoint-last.pth +train: [12] [ 0/800] eta: 0:50:50 lr: nan time: 3.8129 data: 3.4647 max mem: 25051 +train: [12] [ 20/800] eta: 0:07:30 lr: 0.000165 loss: 0.1684 (0.1981) grad: 0.1252 (0.1298) time: 0.4163 data: 0.0020 max mem: 25051 +train: [12] [ 40/800] eta: 0:06:24 lr: 0.000164 loss: 0.1989 (0.2369) grad: 0.0974 (0.1205) time: 0.4305 data: 0.0027 max mem: 25051 +train: [12] [ 60/800] eta: 0:05:58 lr: 0.000163 loss: 0.2438 (0.2462) grad: 0.1178 (0.1220) time: 0.4383 data: 0.0034 max mem: 25051 +train: [12] [ 80/800] eta: 0:05:39 lr: 0.000163 loss: 0.2438 (0.2517) grad: 0.1102 (0.1191) time: 0.4364 data: 0.0030 max mem: 25051 +train: [12] [100/800] eta: 0:05:54 lr: 0.000162 loss: 0.2144 (0.2393) grad: 0.0947 (0.1165) time: 0.6473 data: 0.1864 max mem: 25051 +train: [12] [120/800] eta: 0:05:34 lr: 0.000161 loss: 0.2330 (0.2380) grad: 0.1065 (0.1225) time: 0.4186 data: 0.0028 max mem: 25051 +train: [12] [140/800] eta: 0:05:18 lr: 0.000160 loss: 0.2296 (0.2363) grad: 0.0947 (0.1270) time: 0.4254 data: 0.0030 max mem: 25051 +train: [12] [160/800] eta: 0:05:04 lr: 0.000160 loss: 0.2330 (0.2431) grad: 0.0973 (0.1244) time: 0.4215 data: 0.0029 max mem: 25051 +train: [12] [180/800] eta: 0:05:06 lr: 0.000159 loss: 0.2386 (0.2507) grad: 0.1065 (0.1331) time: 0.6431 data: 0.2116 max mem: 25051 +train: [12] [200/800] eta: 0:04:52 lr: 0.000158 loss: 0.2386 (0.2459) grad: 0.1030 (0.1370) time: 0.4307 data: 0.0026 max mem: 25051 +train: [12] [220/800] eta: 0:04:40 lr: 0.000157 loss: 0.2692 (0.2479) grad: 0.1077 (0.1449) time: 0.4358 data: 0.0030 max mem: 25051 +train: [12] [240/800] eta: 0:04:27 lr: 0.000156 loss: 0.2423 (0.2501) grad: 0.1658 (0.1485) time: 0.4270 data: 0.0029 max mem: 25051 +train: [12] [260/800] eta: 0:04:24 lr: 0.000156 loss: 0.2052 (0.2481) grad: 0.1202 (0.1453) time: 0.6222 data: 0.1864 max mem: 25051 +train: [12] [280/800] eta: 0:04:11 lr: 0.000155 loss: 0.2423 (0.2493) grad: 0.1065 (0.1424) time: 0.4243 data: 0.0027 max mem: 25051 +train: [12] [300/800] eta: 0:04:00 lr: 0.000154 loss: 0.2159 (0.2488) grad: 0.1063 (0.1408) time: 0.4329 data: 0.0030 max mem: 25051 +train: [12] [320/800] eta: 0:03:49 lr: 0.000153 loss: 0.2159 (0.2462) grad: 0.1063 (0.1410) time: 0.4332 data: 0.0030 max mem: 25051 +train: [12] [340/800] eta: 0:03:43 lr: 0.000152 loss: 0.2224 (0.2469) grad: 0.1169 (0.1434) time: 0.6097 data: 0.1791 max mem: 25051 +train: [12] [360/800] eta: 0:03:32 lr: 0.000152 loss: 0.1872 (0.2425) grad: 0.1407 (0.1441) time: 0.4254 data: 0.0028 max mem: 25051 +train: [12] [380/800] eta: 0:03:21 lr: 0.000151 loss: 0.2224 (0.2443) grad: 0.1407 (0.1432) time: 0.4266 data: 0.0029 max mem: 25051 +train: [12] [400/800] eta: 0:03:10 lr: 0.000150 loss: 0.1934 (0.2409) grad: 0.1392 (0.1434) time: 0.4264 data: 0.0029 max mem: 25051 +train: [12] [420/800] eta: 0:03:03 lr: 0.000149 loss: 0.1794 (0.2397) grad: 0.0996 (0.1440) time: 0.6232 data: 0.1799 max mem: 25051 +train: [12] [440/800] eta: 0:02:53 lr: 0.000149 loss: 0.2072 (0.2389) grad: 0.0877 (0.1441) time: 0.4328 data: 0.0025 max mem: 25051 +train: [12] [460/800] eta: 0:02:42 lr: 0.000148 loss: 0.2029 (0.2380) grad: 0.0872 (0.1428) time: 0.4224 data: 0.0030 max mem: 25051 +train: [12] [480/800] eta: 0:02:32 lr: 0.000147 loss: 0.2033 (0.2370) grad: 0.1454 (0.1454) time: 0.4268 data: 0.0029 max mem: 25051 +train: [12] [500/800] eta: 0:02:24 lr: 0.000146 loss: 0.2033 (0.2354) grad: 0.1454 (0.1447) time: 0.6021 data: 0.1828 max mem: 25051 +train: [12] [520/800] eta: 0:02:14 lr: 0.000145 loss: 0.1856 (0.2333) grad: 0.1231 (0.1433) time: 0.4188 data: 0.0017 max mem: 25051 +train: [12] [540/800] eta: 0:02:04 lr: 0.000145 loss: 0.1856 (0.2328) grad: 0.1469 (0.1433) time: 0.4211 data: 0.0028 max mem: 25051 +train: [12] [560/800] eta: 0:01:54 lr: 0.000144 loss: 0.1905 (0.2336) grad: 0.0907 (0.1443) time: 0.4300 data: 0.0029 max mem: 25051 +train: [12] [580/800] eta: 0:01:45 lr: 0.000143 loss: 0.2016 (0.2337) grad: 0.0907 (0.1434) time: 0.6036 data: 0.1813 max mem: 25051 +train: [12] [600/800] eta: 0:01:35 lr: 0.000142 loss: 0.1905 (0.2320) grad: 0.0907 (0.1419) time: 0.4366 data: 0.0030 max mem: 25051 +train: [12] [620/800] eta: 0:01:25 lr: 0.000141 loss: 0.2036 (0.2325) grad: 0.0891 (0.1398) time: 0.4169 data: 0.0027 max mem: 25051 +train: [12] [640/800] eta: 0:01:15 lr: 0.000141 loss: 0.2036 (0.2325) grad: 0.0891 (0.1391) time: 0.4231 data: 0.0030 max mem: 25051 +train: [12] [660/800] eta: 0:01:07 lr: 0.000140 loss: 0.2036 (0.2338) grad: 0.0940 (0.1398) time: 0.6167 data: 0.1824 max mem: 25051 +train: [12] [680/800] eta: 0:00:57 lr: 0.000139 loss: 0.2178 (0.2328) grad: 0.0986 (0.1395) time: 0.4197 data: 0.0023 max mem: 25051 +train: [12] [700/800] eta: 0:00:47 lr: 0.000138 loss: 0.2073 (0.2319) grad: 0.1036 (0.1401) time: 0.4172 data: 0.0028 max mem: 25051 +train: [12] [720/800] eta: 0:00:37 lr: 0.000138 loss: 0.2013 (0.2312) grad: 0.1238 (0.1391) time: 0.4246 data: 0.0030 max mem: 25051 +train: [12] [740/800] eta: 0:00:28 lr: 0.000137 loss: 0.2013 (0.2322) grad: 0.1025 (0.1385) time: 0.5972 data: 0.1809 max mem: 25051 +train: [12] [760/800] eta: 0:00:19 lr: 0.000136 loss: 0.2002 (0.2316) grad: 0.0994 (0.1373) time: 0.4507 data: 0.0024 max mem: 25051 +train: [12] [780/800] eta: 0:00:09 lr: 0.000135 loss: 0.1994 (0.2321) grad: 0.0976 (0.1372) time: 0.4245 data: 0.0029 max mem: 25051 +train: [12] [799/800] eta: 0:00:00 lr: 0.000134 loss: 0.1994 (0.2329) grad: 0.0994 (0.1370) time: 0.4252 data: 0.0035 max mem: 25051 +train: [12] Total time: 0:06:19 (0.4746 s / it) +train: [12] Summary: lr: 0.000134 loss: 0.1994 (0.2329) grad: 0.0994 (0.1370) +eval (validation): [12] [ 0/11] eta: 0:00:39 time: 3.6085 data: 3.3448 max mem: 25051 +eval (validation): [12] [10/11] eta: 0:00:00 time: 0.5857 data: 0.3051 max mem: 25051 +eval (validation): [12] Total time: 0:00:06 (0.5997 s / it) +cv: [12] best hparam: (7.1, 1.0) (036) ('036_lr7.1e+00_wd1.0e+00') loss: 2.415 acc: 0.756 f1: 0.669 bacc: 0.669 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/adni_ad_vs_cn__patch__attn/checkpoint-last.pth +train: [13] [ 0/800] eta: 0:49:42 lr: nan time: 3.7287 data: 3.4014 max mem: 25051 +train: [13] [ 20/800] eta: 0:07:28 lr: 0.000134 loss: 0.2903 (0.2865) grad: 0.0999 (0.1048) time: 0.4174 data: 0.0020 max mem: 25051 +train: [13] [ 40/800] eta: 0:06:19 lr: 0.000133 loss: 0.2632 (0.2614) grad: 0.0999 (0.1025) time: 0.4192 data: 0.0026 max mem: 25051 +train: [13] [ 60/800] eta: 0:05:49 lr: 0.000132 loss: 0.2162 (0.2357) grad: 0.1103 (0.1252) time: 0.4161 data: 0.0032 max mem: 25051 +train: [13] [ 80/800] eta: 0:05:29 lr: 0.000131 loss: 0.2105 (0.2318) grad: 0.0999 (0.1224) time: 0.4159 data: 0.0029 max mem: 25051 +train: [13] [100/800] eta: 0:05:42 lr: 0.000130 loss: 0.2162 (0.2361) grad: 0.1262 (0.1610) time: 0.6145 data: 0.1771 max mem: 25051 +train: [13] [120/800] eta: 0:05:24 lr: 0.000130 loss: 0.2021 (0.2308) grad: 0.1844 (0.1618) time: 0.4180 data: 0.0028 max mem: 25051 +train: [13] [140/800] eta: 0:05:10 lr: 0.000129 loss: 0.2512 (0.2357) grad: 0.1844 (0.1633) time: 0.4248 data: 0.0030 max mem: 25051 +train: [13] [160/800] eta: 0:04:56 lr: 0.000128 loss: 0.2021 (0.2353) grad: 0.1844 (0.1627) time: 0.4145 data: 0.0028 max mem: 25051 +train: [13] [180/800] eta: 0:04:57 lr: 0.000127 loss: 0.2021 (0.2353) grad: 0.1113 (0.1540) time: 0.6163 data: 0.1746 max mem: 25051 +train: [13] [200/800] eta: 0:04:44 lr: 0.000127 loss: 0.1982 (0.2354) grad: 0.1125 (0.1531) time: 0.4242 data: 0.0032 max mem: 25051 +train: [13] [220/800] eta: 0:04:32 lr: 0.000126 loss: 0.1923 (0.2341) grad: 0.1135 (0.1538) time: 0.4269 data: 0.0033 max mem: 25051 +train: [13] [240/800] eta: 0:04:20 lr: 0.000125 loss: 0.1812 (0.2296) grad: 0.1200 (0.1527) time: 0.4191 data: 0.0029 max mem: 25051 +train: [13] [260/800] eta: 0:04:17 lr: 0.000124 loss: 0.1797 (0.2257) grad: 0.1378 (0.1567) time: 0.6114 data: 0.1962 max mem: 25051 +train: [13] [280/800] eta: 0:04:05 lr: 0.000124 loss: 0.1812 (0.2268) grad: 0.1365 (0.1549) time: 0.4123 data: 0.0028 max mem: 25051 +train: [13] [300/800] eta: 0:03:54 lr: 0.000123 loss: 0.1812 (0.2232) grad: 0.1200 (0.1501) time: 0.4102 data: 0.0024 max mem: 25051 +train: [13] [320/800] eta: 0:03:43 lr: 0.000122 loss: 0.1918 (0.2246) grad: 0.1217 (0.1529) time: 0.4098 data: 0.0029 max mem: 25051 +train: [13] [340/800] eta: 0:03:37 lr: 0.000121 loss: 0.2084 (0.2241) grad: 0.1080 (0.1504) time: 0.5947 data: 0.1800 max mem: 25051 +train: [13] [360/800] eta: 0:03:26 lr: 0.000120 loss: 0.2035 (0.2251) grad: 0.1080 (0.1503) time: 0.4305 data: 0.0026 max mem: 25051 +train: [13] [380/800] eta: 0:03:16 lr: 0.000120 loss: 0.2354 (0.2309) grad: 0.1208 (0.1517) time: 0.4182 data: 0.0028 max mem: 25051 +train: [13] [400/800] eta: 0:03:05 lr: 0.000119 loss: 0.2226 (0.2287) grad: 0.1682 (0.1520) time: 0.4187 data: 0.0030 max mem: 25051 +train: [13] [420/800] eta: 0:02:59 lr: 0.000118 loss: 0.2257 (0.2284) grad: 0.1682 (0.1512) time: 0.6085 data: 0.1759 max mem: 25051 +train: [13] [440/800] eta: 0:02:48 lr: 0.000117 loss: 0.1991 (0.2259) grad: 0.1602 (0.1501) time: 0.4145 data: 0.0023 max mem: 25051 +train: [13] [460/800] eta: 0:02:38 lr: 0.000117 loss: 0.1954 (0.2237) grad: 0.1278 (0.1487) time: 0.4218 data: 0.0032 max mem: 25051 +train: [13] [480/800] eta: 0:02:28 lr: 0.000116 loss: 0.1883 (0.2227) grad: 0.1228 (0.1480) time: 0.4316 data: 0.0031 max mem: 25051 +train: [13] [500/800] eta: 0:02:21 lr: 0.000115 loss: 0.1833 (0.2233) grad: 0.1093 (0.1458) time: 0.6236 data: 0.1839 max mem: 25051 +train: [13] [520/800] eta: 0:02:11 lr: 0.000114 loss: 0.1946 (0.2248) grad: 0.1093 (0.1462) time: 0.4152 data: 0.0023 max mem: 25051 +train: [13] [540/800] eta: 0:02:01 lr: 0.000114 loss: 0.2100 (0.2248) grad: 0.0974 (0.1460) time: 0.4214 data: 0.0032 max mem: 25051 +train: [13] [560/800] eta: 0:01:51 lr: 0.000113 loss: 0.2100 (0.2237) grad: 0.1117 (0.1456) time: 0.4196 data: 0.0029 max mem: 25051 +train: [13] [580/800] eta: 0:01:43 lr: 0.000112 loss: 0.2100 (0.2229) grad: 0.1157 (0.1449) time: 0.6129 data: 0.1766 max mem: 25051 +train: [13] [600/800] eta: 0:01:33 lr: 0.000111 loss: 0.2128 (0.2227) grad: 0.1117 (0.1435) time: 0.4112 data: 0.0027 max mem: 25051 +train: [13] [620/800] eta: 0:01:24 lr: 0.000110 loss: 0.2156 (0.2235) grad: 0.1157 (0.1430) time: 0.4222 data: 0.0029 max mem: 25051 +train: [13] [640/800] eta: 0:01:14 lr: 0.000110 loss: 0.2216 (0.2231) grad: 0.1203 (0.1432) time: 0.4244 data: 0.0031 max mem: 25051 +train: [13] [660/800] eta: 0:01:05 lr: 0.000109 loss: 0.2216 (0.2216) grad: 0.0976 (0.1427) time: 0.5929 data: 0.1844 max mem: 25051 +train: [13] [680/800] eta: 0:00:56 lr: 0.000108 loss: 0.2191 (0.2218) grad: 0.0976 (0.1425) time: 0.4130 data: 0.0024 max mem: 25051 +train: [13] [700/800] eta: 0:00:46 lr: 0.000107 loss: 0.1937 (0.2214) grad: 0.0874 (0.1417) time: 0.4050 data: 0.0027 max mem: 25051 +train: [13] [720/800] eta: 0:00:37 lr: 0.000107 loss: 0.1937 (0.2206) grad: 0.1172 (0.1415) time: 0.4072 data: 0.0030 max mem: 25051 +train: [13] [740/800] eta: 0:00:28 lr: 0.000106 loss: 0.2066 (0.2215) grad: 0.1089 (0.1404) time: 0.5865 data: 0.1770 max mem: 25051 +train: [13] [760/800] eta: 0:00:18 lr: 0.000105 loss: 0.2023 (0.2214) grad: 0.1089 (0.1404) time: 0.4159 data: 0.0023 max mem: 25051 +train: [13] [780/800] eta: 0:00:09 lr: 0.000104 loss: 0.1975 (0.2203) grad: 0.1078 (0.1396) time: 0.4201 data: 0.0026 max mem: 25051 +train: [13] [799/800] eta: 0:00:00 lr: 0.000104 loss: 0.1997 (0.2207) grad: 0.1063 (0.1400) time: 0.4283 data: 0.0030 max mem: 25051 +train: [13] Total time: 0:06:12 (0.4651 s / it) +train: [13] Summary: lr: 0.000104 loss: 0.1997 (0.2207) grad: 0.1063 (0.1400) +eval (validation): [13] [ 0/11] eta: 0:00:38 time: 3.4575 data: 3.2097 max mem: 25051 +eval (validation): [13] [10/11] eta: 0:00:00 time: 0.5826 data: 0.2939 max mem: 25051 +eval (validation): [13] Total time: 0:00:06 (0.5965 s / it) +cv: [13] best hparam: (7.1, 1.0) (036) ('036_lr7.1e+00_wd1.0e+00') loss: 2.428 acc: 0.780 f1: 0.692 bacc: 0.685 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/adni_ad_vs_cn__patch__attn/checkpoint-last.pth +train: [14] [ 0/800] eta: 0:50:28 lr: nan time: 3.7850 data: 3.4068 max mem: 25051 +train: [14] [ 20/800] eta: 0:07:38 lr: 0.000103 loss: 0.1810 (0.1788) grad: 0.0875 (0.1025) time: 0.4278 data: 0.0024 max mem: 25051 +train: [14] [ 40/800] eta: 0:06:23 lr: 0.000102 loss: 0.1457 (0.1817) grad: 0.0981 (0.1172) time: 0.4185 data: 0.0028 max mem: 25051 +train: [14] [ 60/800] eta: 0:05:54 lr: 0.000101 loss: 0.1810 (0.1931) grad: 0.1194 (0.1421) time: 0.4255 data: 0.0033 max mem: 25051 +train: [14] [ 80/800] eta: 0:05:33 lr: 0.000101 loss: 0.1810 (0.2035) grad: 0.1194 (0.1452) time: 0.4131 data: 0.0030 max mem: 25051 +train: [14] [100/800] eta: 0:05:47 lr: 0.000100 loss: 0.1800 (0.2021) grad: 0.1299 (0.1350) time: 0.6332 data: 0.1777 max mem: 25051 +train: [14] [120/800] eta: 0:05:28 lr: 0.000099 loss: 0.1833 (0.1997) grad: 0.1299 (0.1349) time: 0.4184 data: 0.0029 max mem: 25051 +train: [14] [140/800] eta: 0:05:13 lr: 0.000099 loss: 0.1814 (0.2028) grad: 0.1299 (0.1434) time: 0.4266 data: 0.0032 max mem: 25051 +train: [14] [160/800] eta: 0:04:59 lr: 0.000098 loss: 0.1587 (0.2011) grad: 0.1299 (0.1467) time: 0.4168 data: 0.0030 max mem: 25051 +train: [14] [180/800] eta: 0:05:01 lr: 0.000097 loss: 0.1631 (0.2020) grad: 0.1370 (0.1425) time: 0.6261 data: 0.1734 max mem: 25051 +train: [14] [200/800] eta: 0:04:47 lr: 0.000096 loss: 0.1755 (0.2029) grad: 0.1069 (0.1419) time: 0.4187 data: 0.0029 max mem: 25051 +train: [14] [220/800] eta: 0:04:34 lr: 0.000096 loss: 0.1798 (0.2106) grad: 0.1069 (0.1444) time: 0.4132 data: 0.0030 max mem: 25051 +train: [14] [240/800] eta: 0:04:21 lr: 0.000095 loss: 0.1940 (0.2119) grad: 0.1370 (0.1467) time: 0.4098 data: 0.0028 max mem: 25051 +train: [14] [260/800] eta: 0:04:18 lr: 0.000094 loss: 0.2255 (0.2149) grad: 0.1516 (0.1475) time: 0.6175 data: 0.1792 max mem: 25051 +train: [14] [280/800] eta: 0:04:07 lr: 0.000093 loss: 0.2264 (0.2171) grad: 0.1524 (0.1497) time: 0.4320 data: 0.0028 max mem: 25051 +train: [14] [300/800] eta: 0:03:56 lr: 0.000093 loss: 0.2287 (0.2203) grad: 0.1366 (0.1473) time: 0.4249 data: 0.0030 max mem: 25051 +train: [14] [320/800] eta: 0:03:45 lr: 0.000092 loss: 0.2057 (0.2176) grad: 0.1178 (0.1481) time: 0.4293 data: 0.0029 max mem: 25051 +train: [14] [340/800] eta: 0:03:40 lr: 0.000091 loss: 0.1879 (0.2179) grad: 0.1366 (0.1478) time: 0.6223 data: 0.1757 max mem: 25051 +train: [14] [360/800] eta: 0:03:29 lr: 0.000090 loss: 0.1879 (0.2181) grad: 0.1150 (0.1465) time: 0.4182 data: 0.0026 max mem: 25051 +train: [14] [380/800] eta: 0:03:18 lr: 0.000090 loss: 0.1868 (0.2180) grad: 0.1530 (0.1487) time: 0.4181 data: 0.0032 max mem: 25051 +train: [14] [400/800] eta: 0:03:07 lr: 0.000089 loss: 0.2009 (0.2189) grad: 0.1446 (0.1474) time: 0.4226 data: 0.0030 max mem: 25051 +train: [14] [420/800] eta: 0:03:01 lr: 0.000088 loss: 0.1868 (0.2171) grad: 0.1044 (0.1446) time: 0.6128 data: 0.1783 max mem: 25051 +train: [14] [440/800] eta: 0:02:50 lr: 0.000088 loss: 0.1887 (0.2175) grad: 0.1032 (0.1427) time: 0.4299 data: 0.0023 max mem: 25051 +train: [14] [460/800] eta: 0:02:40 lr: 0.000087 loss: 0.1730 (0.2160) grad: 0.0717 (0.1416) time: 0.4190 data: 0.0030 max mem: 25051 +train: [14] [480/800] eta: 0:02:30 lr: 0.000086 loss: 0.1723 (0.2173) grad: 0.0717 (0.1425) time: 0.4260 data: 0.0030 max mem: 25051 +train: [14] [500/800] eta: 0:02:22 lr: 0.000085 loss: 0.1887 (0.2172) grad: 0.1003 (0.1419) time: 0.6124 data: 0.1800 max mem: 25051 +train: [14] [520/800] eta: 0:02:12 lr: 0.000085 loss: 0.1796 (0.2178) grad: 0.1003 (0.1410) time: 0.4217 data: 0.0025 max mem: 25051 +train: [14] [540/800] eta: 0:02:02 lr: 0.000084 loss: 0.1916 (0.2163) grad: 0.1003 (0.1399) time: 0.4231 data: 0.0030 max mem: 25051 +train: [14] [560/800] eta: 0:01:52 lr: 0.000083 loss: 0.1916 (0.2150) grad: 0.0929 (0.1382) time: 0.4286 data: 0.0033 max mem: 25051 +train: [14] [580/800] eta: 0:01:44 lr: 0.000083 loss: 0.1931 (0.2151) grad: 0.0888 (0.1377) time: 0.5901 data: 0.1812 max mem: 25051 +train: [14] [600/800] eta: 0:01:34 lr: 0.000082 loss: 0.1984 (0.2165) grad: 0.0888 (0.1369) time: 0.4135 data: 0.0030 max mem: 25051 +train: [14] [620/800] eta: 0:01:24 lr: 0.000081 loss: 0.1984 (0.2157) grad: 0.0930 (0.1374) time: 0.4187 data: 0.0027 max mem: 25051 +train: [14] [640/800] eta: 0:01:15 lr: 0.000081 loss: 0.1982 (0.2145) grad: 0.1054 (0.1365) time: 0.4122 data: 0.0032 max mem: 25051 +train: [14] [660/800] eta: 0:01:06 lr: 0.000080 loss: 0.1982 (0.2149) grad: 0.0799 (0.1350) time: 0.6130 data: 0.1783 max mem: 25051 +train: [14] [680/800] eta: 0:00:56 lr: 0.000079 loss: 0.1982 (0.2167) grad: 0.0799 (0.1345) time: 0.4273 data: 0.0031 max mem: 25051 +train: [14] [700/800] eta: 0:00:47 lr: 0.000078 loss: 0.1982 (0.2152) grad: 0.0799 (0.1330) time: 0.4207 data: 0.0026 max mem: 25051 +train: [14] [720/800] eta: 0:00:37 lr: 0.000078 loss: 0.2128 (0.2157) grad: 0.0735 (0.1332) time: 0.4130 data: 0.0029 max mem: 25051 +train: [14] [740/800] eta: 0:00:28 lr: 0.000077 loss: 0.1914 (0.2162) grad: 0.0880 (0.1343) time: 0.5877 data: 0.1781 max mem: 25051 +train: [14] [760/800] eta: 0:00:18 lr: 0.000076 loss: 0.1891 (0.2161) grad: 0.1005 (0.1336) time: 0.4409 data: 0.0032 max mem: 25051 +train: [14] [780/800] eta: 0:00:09 lr: 0.000076 loss: 0.1946 (0.2175) grad: 0.1050 (0.1335) time: 0.4138 data: 0.0029 max mem: 25051 +train: [14] [799/800] eta: 0:00:00 lr: 0.000075 loss: 0.1946 (0.2168) grad: 0.1090 (0.1332) time: 0.4203 data: 0.0031 max mem: 25051 +train: [14] Total time: 0:06:15 (0.4690 s / it) +train: [14] Summary: lr: 0.000075 loss: 0.1946 (0.2168) grad: 0.1090 (0.1332) +eval (validation): [14] [ 0/11] eta: 0:00:40 time: 3.6723 data: 3.4047 max mem: 25051 +eval (validation): [14] [10/11] eta: 0:00:00 time: 0.6027 data: 0.3105 max mem: 25051 +eval (validation): [14] Total time: 0:00:06 (0.6174 s / it) +cv: [14] best hparam: (7.1, 1.0) (036) ('036_lr7.1e+00_wd1.0e+00') loss: 2.438 acc: 0.780 f1: 0.692 bacc: 0.685 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/adni_ad_vs_cn__patch__attn/checkpoint-last.pth +train: [15] [ 0/800] eta: 0:47:05 lr: nan time: 3.5318 data: 3.1974 max mem: 25051 +train: [15] [ 20/800] eta: 0:07:26 lr: 0.000074 loss: 0.2016 (0.2077) grad: 0.0869 (0.1041) time: 0.4249 data: 0.0030 max mem: 25051 +train: [15] [ 40/800] eta: 0:06:16 lr: 0.000074 loss: 0.2240 (0.2223) grad: 0.0869 (0.1165) time: 0.4143 data: 0.0026 max mem: 25051 +train: [15] [ 60/800] eta: 0:05:47 lr: 0.000073 loss: 0.2240 (0.2133) grad: 0.0869 (0.1058) time: 0.4153 data: 0.0028 max mem: 25051 +train: [15] [ 80/800] eta: 0:05:27 lr: 0.000072 loss: 0.2240 (0.2238) grad: 0.0814 (0.1009) time: 0.4126 data: 0.0029 max mem: 25051 +train: [15] [100/800] eta: 0:05:42 lr: 0.000072 loss: 0.2088 (0.2157) grad: 0.0934 (0.1107) time: 0.6263 data: 0.1995 max mem: 25051 +train: [15] [120/800] eta: 0:05:24 lr: 0.000071 loss: 0.1998 (0.2199) grad: 0.0938 (0.1153) time: 0.4189 data: 0.0023 max mem: 25051 +train: [15] [140/800] eta: 0:05:10 lr: 0.000070 loss: 0.2071 (0.2199) grad: 0.1264 (0.1245) time: 0.4246 data: 0.0032 max mem: 25051 +train: [15] [160/800] eta: 0:04:56 lr: 0.000070 loss: 0.2088 (0.2250) grad: 0.1336 (0.1259) time: 0.4222 data: 0.0031 max mem: 25051 +train: [15] [180/800] eta: 0:04:57 lr: 0.000069 loss: 0.2122 (0.2238) grad: 0.1278 (0.1225) time: 0.6030 data: 0.1805 max mem: 25051 +train: [15] [200/800] eta: 0:04:44 lr: 0.000068 loss: 0.2220 (0.2240) grad: 0.1086 (0.1187) time: 0.4256 data: 0.0023 max mem: 25051 +train: [15] [220/800] eta: 0:04:32 lr: 0.000068 loss: 0.2227 (0.2300) grad: 0.1010 (0.1224) time: 0.4206 data: 0.0034 max mem: 25051 +train: [15] [240/800] eta: 0:04:20 lr: 0.000067 loss: 0.2191 (0.2310) grad: 0.1010 (0.1275) time: 0.4173 data: 0.0031 max mem: 25051 +train: [15] [260/800] eta: 0:04:17 lr: 0.000066 loss: 0.2191 (0.2271) grad: 0.1178 (0.1252) time: 0.6131 data: 0.1865 max mem: 25051 +train: [15] [280/800] eta: 0:04:05 lr: 0.000066 loss: 0.2191 (0.2303) grad: 0.1206 (0.1250) time: 0.4272 data: 0.0034 max mem: 25051 +train: [15] [300/800] eta: 0:03:54 lr: 0.000065 loss: 0.1933 (0.2270) grad: 0.1206 (0.1252) time: 0.4242 data: 0.0031 max mem: 25051 +train: [15] [320/800] eta: 0:03:43 lr: 0.000064 loss: 0.1933 (0.2283) grad: 0.1178 (0.1272) time: 0.4107 data: 0.0032 max mem: 25051 +train: [15] [340/800] eta: 0:03:38 lr: 0.000064 loss: 0.2030 (0.2279) grad: 0.1019 (0.1244) time: 0.6034 data: 0.1815 max mem: 25051 +train: [15] [360/800] eta: 0:03:27 lr: 0.000063 loss: 0.2030 (0.2300) grad: 0.1049 (0.1271) time: 0.4175 data: 0.0026 max mem: 25051 +train: [15] [380/800] eta: 0:03:16 lr: 0.000063 loss: 0.2071 (0.2291) grad: 0.1014 (0.1265) time: 0.4104 data: 0.0031 max mem: 25051 +train: [15] [400/800] eta: 0:03:06 lr: 0.000062 loss: 0.2071 (0.2282) grad: 0.0952 (0.1281) time: 0.4198 data: 0.0031 max mem: 25051 +train: [15] [420/800] eta: 0:02:59 lr: 0.000061 loss: 0.1970 (0.2258) grad: 0.1309 (0.1286) time: 0.6210 data: 0.1767 max mem: 25051 +train: [15] [440/800] eta: 0:02:49 lr: 0.000061 loss: 0.1812 (0.2276) grad: 0.1271 (0.1280) time: 0.4099 data: 0.0022 max mem: 25051 +train: [15] [460/800] eta: 0:02:39 lr: 0.000060 loss: 0.1930 (0.2272) grad: 0.1271 (0.1276) time: 0.4220 data: 0.0032 max mem: 25051 +train: [15] [480/800] eta: 0:02:29 lr: 0.000059 loss: 0.1930 (0.2269) grad: 0.1009 (0.1285) time: 0.4200 data: 0.0033 max mem: 25051 +train: [15] [500/800] eta: 0:02:21 lr: 0.000059 loss: 0.2114 (0.2269) grad: 0.0975 (0.1280) time: 0.6310 data: 0.1930 max mem: 25051 +train: [15] [520/800] eta: 0:02:11 lr: 0.000058 loss: 0.2114 (0.2249) grad: 0.0901 (0.1281) time: 0.4200 data: 0.0021 max mem: 25051 +train: [15] [540/800] eta: 0:02:01 lr: 0.000057 loss: 0.1812 (0.2238) grad: 0.0878 (0.1271) time: 0.4287 data: 0.0032 max mem: 25051 +train: [15] [560/800] eta: 0:01:52 lr: 0.000057 loss: 0.1812 (0.2228) grad: 0.0975 (0.1278) time: 0.4103 data: 0.0031 max mem: 25051 +train: [15] [580/800] eta: 0:01:43 lr: 0.000056 loss: 0.1840 (0.2242) grad: 0.0878 (0.1271) time: 0.5893 data: 0.1851 max mem: 25051 +train: [15] [600/800] eta: 0:01:33 lr: 0.000056 loss: 0.2050 (0.2241) grad: 0.0878 (0.1256) time: 0.4126 data: 0.0029 max mem: 25051 +train: [15] [620/800] eta: 0:01:24 lr: 0.000055 loss: 0.2246 (0.2243) grad: 0.0903 (0.1266) time: 0.4110 data: 0.0024 max mem: 25051 +train: [15] [640/800] eta: 0:01:14 lr: 0.000054 loss: 0.2271 (0.2242) grad: 0.0903 (0.1273) time: 0.4204 data: 0.0033 max mem: 25051 +train: [15] [660/800] eta: 0:01:05 lr: 0.000054 loss: 0.2114 (0.2239) grad: 0.1063 (0.1269) time: 0.6068 data: 0.1826 max mem: 25051 +train: [15] [680/800] eta: 0:00:56 lr: 0.000053 loss: 0.2271 (0.2260) grad: 0.1200 (0.1283) time: 0.4160 data: 0.0028 max mem: 25051 +train: [15] [700/800] eta: 0:00:46 lr: 0.000053 loss: 0.2271 (0.2275) grad: 0.1200 (0.1280) time: 0.4252 data: 0.0032 max mem: 25051 +train: [15] [720/800] eta: 0:00:37 lr: 0.000052 loss: 0.2459 (0.2265) grad: 0.1093 (0.1287) time: 0.4347 data: 0.0031 max mem: 25051 +train: [15] [740/800] eta: 0:00:28 lr: 0.000051 loss: 0.2638 (0.2266) grad: 0.1093 (0.1297) time: 0.5922 data: 0.1877 max mem: 25051 +train: [15] [760/800] eta: 0:00:18 lr: 0.000051 loss: 0.2040 (0.2262) grad: 0.1036 (0.1288) time: 0.4286 data: 0.0025 max mem: 25051 +train: [15] [780/800] eta: 0:00:09 lr: 0.000050 loss: 0.2205 (0.2269) grad: 0.1063 (0.1295) time: 0.4230 data: 0.0031 max mem: 25051 +train: [15] [799/800] eta: 0:00:00 lr: 0.000050 loss: 0.2205 (0.2265) grad: 0.0934 (0.1291) time: 0.4268 data: 0.0034 max mem: 25051 +train: [15] Total time: 0:06:13 (0.4667 s / it) +train: [15] Summary: lr: 0.000050 loss: 0.2205 (0.2265) grad: 0.0934 (0.1291) +eval (validation): [15] [ 0/11] eta: 0:00:39 time: 3.6092 data: 3.3365 max mem: 25051 +eval (validation): [15] [10/11] eta: 0:00:00 time: 0.5934 data: 0.3047 max mem: 25051 +eval (validation): [15] Total time: 0:00:06 (0.6076 s / it) +cv: [15] best hparam: (7.1, 1.0) (036) ('036_lr7.1e+00_wd1.0e+00') loss: 2.446 acc: 0.780 f1: 0.692 bacc: 0.685 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/adni_ad_vs_cn__patch__attn/checkpoint-last.pth +train: [16] [ 0/800] eta: 0:52:16 lr: nan time: 3.9203 data: 3.5872 max mem: 25051 +train: [16] [ 20/800] eta: 0:07:38 lr: 0.000049 loss: 0.2073 (0.2280) grad: 0.1171 (0.1331) time: 0.4214 data: 0.0031 max mem: 25051 +train: [16] [ 40/800] eta: 0:06:27 lr: 0.000048 loss: 0.2073 (0.2350) grad: 0.1171 (0.1363) time: 0.4278 data: 0.0027 max mem: 25051 +train: [16] [ 60/800] eta: 0:05:58 lr: 0.000048 loss: 0.2073 (0.2304) grad: 0.1180 (0.1313) time: 0.4327 data: 0.0030 max mem: 25051 +train: [16] [ 80/800] eta: 0:05:40 lr: 0.000047 loss: 0.2039 (0.2216) grad: 0.1171 (0.1238) time: 0.4374 data: 0.0029 max mem: 25051 +train: [16] [100/800] eta: 0:05:56 lr: 0.000047 loss: 0.2202 (0.2262) grad: 0.1029 (0.1174) time: 0.6586 data: 0.1856 max mem: 25051 +train: [16] [120/800] eta: 0:05:39 lr: 0.000046 loss: 0.2039 (0.2219) grad: 0.0894 (0.1154) time: 0.4500 data: 0.0024 max mem: 25051 +train: [16] [140/800] eta: 0:05:23 lr: 0.000046 loss: 0.2039 (0.2202) grad: 0.0842 (0.1116) time: 0.4368 data: 0.0034 max mem: 25051 +train: [16] [160/800] eta: 0:05:09 lr: 0.000045 loss: 0.2142 (0.2209) grad: 0.0791 (0.1108) time: 0.4291 data: 0.0032 max mem: 25051 +train: [16] [180/800] eta: 0:05:09 lr: 0.000045 loss: 0.1915 (0.2172) grad: 0.0791 (0.1116) time: 0.6233 data: 0.1919 max mem: 25051 +train: [16] [200/800] eta: 0:04:55 lr: 0.000044 loss: 0.1945 (0.2181) grad: 0.0842 (0.1116) time: 0.4328 data: 0.0027 max mem: 25051 +train: [16] [220/800] eta: 0:04:43 lr: 0.000043 loss: 0.2099 (0.2182) grad: 0.1040 (0.1139) time: 0.4514 data: 0.0053 max mem: 25051 +train: [16] [240/800] eta: 0:04:31 lr: 0.000043 loss: 0.2015 (0.2185) grad: 0.1219 (0.1185) time: 0.4388 data: 0.0029 max mem: 25051 +train: [16] [260/800] eta: 0:04:28 lr: 0.000042 loss: 0.2099 (0.2171) grad: 0.1219 (0.1188) time: 0.6639 data: 0.1866 max mem: 25051 +train: [16] [280/800] eta: 0:04:16 lr: 0.000042 loss: 0.2099 (0.2176) grad: 0.1277 (0.1197) time: 0.4380 data: 0.0029 max mem: 25051 +train: [16] [300/800] eta: 0:04:05 lr: 0.000041 loss: 0.1859 (0.2149) grad: 0.1212 (0.1196) time: 0.4585 data: 0.0033 max mem: 25051 +train: [16] [320/800] eta: 0:03:54 lr: 0.000041 loss: 0.1827 (0.2144) grad: 0.1100 (0.1196) time: 0.4342 data: 0.0030 max mem: 25051 +train: [16] [340/800] eta: 0:03:48 lr: 0.000040 loss: 0.1700 (0.2128) grad: 0.1036 (0.1191) time: 0.6450 data: 0.1980 max mem: 25051 +train: [16] [360/800] eta: 0:03:37 lr: 0.000040 loss: 0.1658 (0.2099) grad: 0.1036 (0.1195) time: 0.4459 data: 0.0024 max mem: 25051 +train: [16] [380/800] eta: 0:03:26 lr: 0.000039 loss: 0.1700 (0.2090) grad: 0.0863 (0.1181) time: 0.4422 data: 0.0030 max mem: 25051 +train: [16] [400/800] eta: 0:03:15 lr: 0.000039 loss: 0.1700 (0.2107) grad: 0.0875 (0.1176) time: 0.4372 data: 0.0031 max mem: 25051 +train: [16] [420/800] eta: 0:03:08 lr: 0.000038 loss: 0.1768 (0.2114) grad: 0.0856 (0.1164) time: 0.6378 data: 0.1827 max mem: 25051 +train: [16] [440/800] eta: 0:02:57 lr: 0.000038 loss: 0.1791 (0.2128) grad: 0.0980 (0.1178) time: 0.4173 data: 0.0021 max mem: 25051 +train: [16] [460/800] eta: 0:02:46 lr: 0.000037 loss: 0.1846 (0.2113) grad: 0.1000 (0.1181) time: 0.4251 data: 0.0031 max mem: 25051 +train: [16] [480/800] eta: 0:02:36 lr: 0.000036 loss: 0.1846 (0.2107) grad: 0.1140 (0.1223) time: 0.4445 data: 0.0034 max mem: 25051 +train: [16] [500/800] eta: 0:02:27 lr: 0.000036 loss: 0.1992 (0.2137) grad: 0.1164 (0.1223) time: 0.6204 data: 0.1930 max mem: 25051 +train: [16] [520/800] eta: 0:02:17 lr: 0.000035 loss: 0.1995 (0.2131) grad: 0.1164 (0.1217) time: 0.4730 data: 0.0031 max mem: 25051 +train: [16] [540/800] eta: 0:02:07 lr: 0.000035 loss: 0.2042 (0.2127) grad: 0.1164 (0.1216) time: 0.4319 data: 0.0031 max mem: 25051 +train: [16] [560/800] eta: 0:01:57 lr: 0.000034 loss: 0.1995 (0.2124) grad: 0.1111 (0.1217) time: 0.4352 data: 0.0034 max mem: 25051 +train: [16] [580/800] eta: 0:01:48 lr: 0.000034 loss: 0.2120 (0.2128) grad: 0.0901 (0.1202) time: 0.6765 data: 0.2114 max mem: 25051 +train: [16] [600/800] eta: 0:01:38 lr: 0.000033 loss: 0.2060 (0.2137) grad: 0.1204 (0.1235) time: 0.4663 data: 0.0045 max mem: 25051 +train: [16] [620/800] eta: 0:01:28 lr: 0.000033 loss: 0.2060 (0.2127) grad: 0.1020 (0.1223) time: 0.4557 data: 0.0036 max mem: 25051 +train: [16] [640/800] eta: 0:01:18 lr: 0.000032 loss: 0.2060 (0.2130) grad: 0.0817 (0.1219) time: 0.4539 data: 0.0030 max mem: 25051 +train: [16] [660/800] eta: 0:01:09 lr: 0.000032 loss: 0.1936 (0.2124) grad: 0.1020 (0.1209) time: 0.6513 data: 0.1852 max mem: 25051 +train: [16] [680/800] eta: 0:00:59 lr: 0.000031 loss: 0.1682 (0.2112) grad: 0.0813 (0.1206) time: 0.4874 data: 0.0034 max mem: 25051 +train: [16] [700/800] eta: 0:00:49 lr: 0.000031 loss: 0.1901 (0.2124) grad: 0.0894 (0.1201) time: 0.4540 data: 0.0032 max mem: 25051 +train: [16] [720/800] eta: 0:00:39 lr: 0.000031 loss: 0.1937 (0.2128) grad: 0.0894 (0.1203) time: 0.4333 data: 0.0029 max mem: 25051 +train: [16] [740/800] eta: 0:00:29 lr: 0.000030 loss: 0.1945 (0.2129) grad: 0.1061 (0.1211) time: 0.6253 data: 0.1952 max mem: 25051 +train: [16] [760/800] eta: 0:00:19 lr: 0.000030 loss: 0.1974 (0.2132) grad: 0.1061 (0.1217) time: 0.4652 data: 0.0026 max mem: 25051 +train: [16] [780/800] eta: 0:00:09 lr: 0.000029 loss: 0.2042 (0.2146) grad: 0.1338 (0.1220) time: 0.4476 data: 0.0031 max mem: 25051 +train: [16] [799/800] eta: 0:00:00 lr: 0.000029 loss: 0.1972 (0.2132) grad: 0.1126 (0.1215) time: 0.4443 data: 0.0032 max mem: 25051 +train: [16] Total time: 0:06:34 (0.4934 s / it) +train: [16] Summary: lr: 0.000029 loss: 0.1972 (0.2132) grad: 0.1126 (0.1215) +eval (validation): [16] [ 0/11] eta: 0:00:41 time: 3.7723 data: 3.4772 max mem: 25051 +eval (validation): [16] [10/11] eta: 0:00:00 time: 0.6187 data: 0.3175 max mem: 25051 +eval (validation): [16] Total time: 0:00:06 (0.6325 s / it) +cv: [16] best hparam: (7.1, 1.0) (036) ('036_lr7.1e+00_wd1.0e+00') loss: 2.453 acc: 0.780 f1: 0.692 bacc: 0.685 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/adni_ad_vs_cn__patch__attn/checkpoint-last.pth +train: [17] [ 0/800] eta: 0:48:10 lr: nan time: 3.6130 data: 3.2851 max mem: 25051 +train: [17] [ 20/800] eta: 0:07:42 lr: 0.000028 loss: 0.1641 (0.1819) grad: 0.1162 (0.1271) time: 0.4422 data: 0.0032 max mem: 25051 +train: [17] [ 40/800] eta: 0:06:29 lr: 0.000028 loss: 0.1768 (0.2233) grad: 0.1162 (0.1328) time: 0.4280 data: 0.0026 max mem: 25051 +train: [17] [ 60/800] eta: 0:05:59 lr: 0.000027 loss: 0.2168 (0.2257) grad: 0.1162 (0.1283) time: 0.4290 data: 0.0031 max mem: 25051 +train: [17] [ 80/800] eta: 0:05:39 lr: 0.000027 loss: 0.2168 (0.2284) grad: 0.1162 (0.1275) time: 0.4324 data: 0.0030 max mem: 25051 +train: [17] [100/800] eta: 0:05:52 lr: 0.000026 loss: 0.2316 (0.2352) grad: 0.1170 (0.1263) time: 0.6331 data: 0.1906 max mem: 25051 +train: [17] [120/800] eta: 0:05:33 lr: 0.000026 loss: 0.2168 (0.2268) grad: 0.1170 (0.1255) time: 0.4185 data: 0.0022 max mem: 25051 +train: [17] [140/800] eta: 0:05:16 lr: 0.000026 loss: 0.1843 (0.2205) grad: 0.1336 (0.1290) time: 0.4210 data: 0.0033 max mem: 25051 +train: [17] [160/800] eta: 0:05:02 lr: 0.000025 loss: 0.2251 (0.2260) grad: 0.1199 (0.1236) time: 0.4254 data: 0.0031 max mem: 25051 +train: [17] [180/800] eta: 0:05:03 lr: 0.000025 loss: 0.1695 (0.2238) grad: 0.1203 (0.1268) time: 0.6244 data: 0.1814 max mem: 25051 +train: [17] [200/800] eta: 0:04:50 lr: 0.000024 loss: 0.1844 (0.2212) grad: 0.1203 (0.1273) time: 0.4246 data: 0.0025 max mem: 25051 +train: [17] [220/800] eta: 0:04:38 lr: 0.000024 loss: 0.1844 (0.2175) grad: 0.1203 (0.1294) time: 0.4449 data: 0.0031 max mem: 25051 +train: [17] [240/800] eta: 0:04:26 lr: 0.000023 loss: 0.1805 (0.2197) grad: 0.1308 (0.1277) time: 0.4208 data: 0.0030 max mem: 25051 +train: [17] [260/800] eta: 0:04:22 lr: 0.000023 loss: 0.1844 (0.2194) grad: 0.1096 (0.1262) time: 0.6093 data: 0.1798 max mem: 25051 +train: [17] [280/800] eta: 0:04:10 lr: 0.000023 loss: 0.1904 (0.2176) grad: 0.1108 (0.1266) time: 0.4410 data: 0.0031 max mem: 25051 +train: [17] [300/800] eta: 0:03:59 lr: 0.000022 loss: 0.1912 (0.2192) grad: 0.0997 (0.1229) time: 0.4280 data: 0.0030 max mem: 25051 +train: [17] [320/800] eta: 0:03:48 lr: 0.000022 loss: 0.1897 (0.2169) grad: 0.0901 (0.1228) time: 0.4258 data: 0.0033 max mem: 25051 +train: [17] [340/800] eta: 0:03:42 lr: 0.000021 loss: 0.1897 (0.2165) grad: 0.1093 (0.1250) time: 0.6109 data: 0.1751 max mem: 25051 +train: [17] [360/800] eta: 0:03:31 lr: 0.000021 loss: 0.2024 (0.2174) grad: 0.1019 (0.1267) time: 0.4296 data: 0.0029 max mem: 25051 +train: [17] [380/800] eta: 0:03:20 lr: 0.000021 loss: 0.1949 (0.2161) grad: 0.1549 (0.1305) time: 0.4326 data: 0.0033 max mem: 25051 +train: [17] [400/800] eta: 0:03:10 lr: 0.000020 loss: 0.2163 (0.2177) grad: 0.1549 (0.1314) time: 0.4260 data: 0.0030 max mem: 25051 +train: [17] [420/800] eta: 0:03:03 lr: 0.000020 loss: 0.2159 (0.2166) grad: 0.1141 (0.1308) time: 0.6325 data: 0.1859 max mem: 25051 +train: [17] [440/800] eta: 0:02:52 lr: 0.000019 loss: 0.2058 (0.2179) grad: 0.1141 (0.1303) time: 0.4209 data: 0.0022 max mem: 25051 +train: [17] [460/800] eta: 0:02:42 lr: 0.000019 loss: 0.2046 (0.2181) grad: 0.1046 (0.1309) time: 0.4238 data: 0.0030 max mem: 25051 +train: [17] [480/800] eta: 0:02:32 lr: 0.000019 loss: 0.2046 (0.2194) grad: 0.0962 (0.1304) time: 0.4276 data: 0.0031 max mem: 25051 +train: [17] [500/800] eta: 0:02:24 lr: 0.000018 loss: 0.2058 (0.2192) grad: 0.0945 (0.1290) time: 0.6024 data: 0.1782 max mem: 25051 +train: [17] [520/800] eta: 0:02:14 lr: 0.000018 loss: 0.1855 (0.2182) grad: 0.0816 (0.1280) time: 0.4440 data: 0.0022 max mem: 25051 +train: [17] [540/800] eta: 0:02:04 lr: 0.000017 loss: 0.2015 (0.2184) grad: 0.0771 (0.1260) time: 0.4418 data: 0.0028 max mem: 25051 +train: [17] [560/800] eta: 0:01:54 lr: 0.000017 loss: 0.1913 (0.2199) grad: 0.0945 (0.1271) time: 0.4274 data: 0.0031 max mem: 25051 +train: [17] [580/800] eta: 0:01:45 lr: 0.000017 loss: 0.1884 (0.2180) grad: 0.0977 (0.1266) time: 0.5962 data: 0.1800 max mem: 25051 +train: [17] [600/800] eta: 0:01:35 lr: 0.000016 loss: 0.1903 (0.2192) grad: 0.0977 (0.1261) time: 0.4393 data: 0.0032 max mem: 25051 +train: [17] [620/800] eta: 0:01:25 lr: 0.000016 loss: 0.1903 (0.2197) grad: 0.1016 (0.1255) time: 0.4289 data: 0.0035 max mem: 25051 +train: [17] [640/800] eta: 0:01:16 lr: 0.000016 loss: 0.1903 (0.2186) grad: 0.1016 (0.1254) time: 0.4227 data: 0.0031 max mem: 25051 +train: [17] [660/800] eta: 0:01:07 lr: 0.000015 loss: 0.1962 (0.2187) grad: 0.0895 (0.1240) time: 0.5942 data: 0.1777 max mem: 25051 +train: [17] [680/800] eta: 0:00:57 lr: 0.000015 loss: 0.1853 (0.2169) grad: 0.1037 (0.1240) time: 0.4187 data: 0.0028 max mem: 25051 +train: [17] [700/800] eta: 0:00:47 lr: 0.000015 loss: 0.1748 (0.2174) grad: 0.0998 (0.1234) time: 0.4105 data: 0.0029 max mem: 25051 +train: [17] [720/800] eta: 0:00:37 lr: 0.000014 loss: 0.1878 (0.2179) grad: 0.0949 (0.1235) time: 0.4406 data: 0.0034 max mem: 25051 +train: [17] [740/800] eta: 0:00:28 lr: 0.000014 loss: 0.1954 (0.2172) grad: 0.0998 (0.1228) time: 0.6035 data: 0.1908 max mem: 25051 +train: [17] [760/800] eta: 0:00:19 lr: 0.000014 loss: 0.1980 (0.2172) grad: 0.0883 (0.1222) time: 0.4248 data: 0.0020 max mem: 25051 +train: [17] [780/800] eta: 0:00:09 lr: 0.000013 loss: 0.2022 (0.2175) grad: 0.1013 (0.1239) time: 0.4206 data: 0.0029 max mem: 25051 +train: [17] [799/800] eta: 0:00:00 lr: 0.000013 loss: 0.1894 (0.2167) grad: 0.1013 (0.1233) time: 0.4236 data: 0.0030 max mem: 25051 +train: [17] Total time: 0:06:19 (0.4740 s / it) +train: [17] Summary: lr: 0.000013 loss: 0.1894 (0.2167) grad: 0.1013 (0.1233) +eval (validation): [17] [ 0/11] eta: 0:00:40 time: 3.7015 data: 3.4687 max mem: 25051 +eval (validation): [17] [10/11] eta: 0:00:00 time: 0.6031 data: 0.3166 max mem: 25051 +eval (validation): [17] Total time: 0:00:06 (0.6156 s / it) +cv: [17] best hparam: (7.1, 1.0) (036) ('036_lr7.1e+00_wd1.0e+00') loss: 2.459 acc: 0.780 f1: 0.692 bacc: 0.685 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/adni_ad_vs_cn__patch__attn/checkpoint-last.pth +train: [18] [ 0/800] eta: 0:49:45 lr: nan time: 3.7318 data: 3.3571 max mem: 25051 +train: [18] [ 20/800] eta: 0:07:27 lr: 0.000013 loss: 0.2282 (0.2180) grad: 0.2032 (0.1983) time: 0.4163 data: 0.0023 max mem: 25051 +train: [18] [ 40/800] eta: 0:06:17 lr: 0.000012 loss: 0.2200 (0.2147) grad: 0.1565 (0.1606) time: 0.4153 data: 0.0022 max mem: 25051 +train: [18] [ 60/800] eta: 0:05:48 lr: 0.000012 loss: 0.2131 (0.2059) grad: 0.1565 (0.1504) time: 0.4175 data: 0.0032 max mem: 25051 +train: [18] [ 80/800] eta: 0:05:29 lr: 0.000012 loss: 0.2178 (0.2127) grad: 0.1194 (0.1409) time: 0.4165 data: 0.0029 max mem: 25051 +train: [18] [100/800] eta: 0:05:41 lr: 0.000011 loss: 0.2168 (0.2139) grad: 0.1095 (0.1395) time: 0.6092 data: 0.1750 max mem: 25051 +train: [18] [120/800] eta: 0:05:24 lr: 0.000011 loss: 0.1992 (0.2084) grad: 0.1095 (0.1363) time: 0.4247 data: 0.0021 max mem: 25051 +train: [18] [140/800] eta: 0:05:10 lr: 0.000011 loss: 0.2168 (0.2106) grad: 0.1092 (0.1365) time: 0.4278 data: 0.0031 max mem: 25051 +train: [18] [160/800] eta: 0:04:57 lr: 0.000011 loss: 0.2098 (0.2156) grad: 0.1092 (0.1377) time: 0.4266 data: 0.0029 max mem: 25051 +train: [18] [180/800] eta: 0:04:58 lr: 0.000010 loss: 0.2220 (0.2177) grad: 0.1092 (0.1380) time: 0.6095 data: 0.1773 max mem: 25051 +train: [18] [200/800] eta: 0:04:45 lr: 0.000010 loss: 0.2282 (0.2149) grad: 0.1060 (0.1369) time: 0.4325 data: 0.0026 max mem: 25051 +train: [18] [220/800] eta: 0:04:33 lr: 0.000010 loss: 0.2205 (0.2155) grad: 0.0990 (0.1346) time: 0.4281 data: 0.0033 max mem: 25051 +train: [18] [240/800] eta: 0:04:22 lr: 0.000009 loss: 0.1916 (0.2130) grad: 0.0990 (0.1327) time: 0.4289 data: 0.0031 max mem: 25051 +train: [18] [260/800] eta: 0:04:19 lr: 0.000009 loss: 0.1916 (0.2123) grad: 0.1060 (0.1319) time: 0.6321 data: 0.1856 max mem: 25051 +train: [18] [280/800] eta: 0:04:08 lr: 0.000009 loss: 0.1985 (0.2142) grad: 0.1208 (0.1342) time: 0.4320 data: 0.0029 max mem: 25051 +train: [18] [300/800] eta: 0:03:56 lr: 0.000009 loss: 0.1917 (0.2139) grad: 0.1249 (0.1332) time: 0.4237 data: 0.0032 max mem: 25051 +train: [18] [320/800] eta: 0:03:45 lr: 0.000008 loss: 0.2006 (0.2143) grad: 0.1073 (0.1306) time: 0.4288 data: 0.0031 max mem: 25051 +train: [18] [340/800] eta: 0:03:40 lr: 0.000008 loss: 0.2084 (0.2136) grad: 0.0920 (0.1304) time: 0.5987 data: 0.1830 max mem: 25051 +train: [18] [360/800] eta: 0:03:28 lr: 0.000008 loss: 0.2084 (0.2126) grad: 0.0891 (0.1297) time: 0.4179 data: 0.0025 max mem: 25051 +train: [18] [380/800] eta: 0:03:18 lr: 0.000008 loss: 0.2064 (0.2098) grad: 0.0913 (0.1290) time: 0.4383 data: 0.0031 max mem: 25051 +train: [18] [400/800] eta: 0:03:08 lr: 0.000007 loss: 0.2011 (0.2119) grad: 0.1123 (0.1281) time: 0.4295 data: 0.0031 max mem: 25051 +train: [18] [420/800] eta: 0:03:01 lr: 0.000007 loss: 0.1823 (0.2133) grad: 0.0913 (0.1274) time: 0.6139 data: 0.1767 max mem: 25051 +train: [18] [440/800] eta: 0:02:50 lr: 0.000007 loss: 0.1696 (0.2110) grad: 0.0913 (0.1259) time: 0.4193 data: 0.0021 max mem: 25051 +train: [18] [460/800] eta: 0:02:40 lr: 0.000007 loss: 0.1801 (0.2126) grad: 0.1156 (0.1279) time: 0.4266 data: 0.0029 max mem: 25051 +train: [18] [480/800] eta: 0:02:30 lr: 0.000006 loss: 0.1700 (0.2119) grad: 0.1156 (0.1291) time: 0.4314 data: 0.0031 max mem: 25051 +train: [18] [500/800] eta: 0:02:23 lr: 0.000006 loss: 0.1700 (0.2115) grad: 0.1210 (0.1288) time: 0.6253 data: 0.1758 max mem: 25051 +train: [18] [520/800] eta: 0:02:13 lr: 0.000006 loss: 0.1927 (0.2109) grad: 0.1254 (0.1284) time: 0.4216 data: 0.0022 max mem: 25051 +train: [18] [540/800] eta: 0:02:03 lr: 0.000006 loss: 0.1744 (0.2101) grad: 0.1162 (0.1284) time: 0.4231 data: 0.0031 max mem: 25051 +train: [18] [560/800] eta: 0:01:53 lr: 0.000006 loss: 0.2111 (0.2105) grad: 0.1162 (0.1281) time: 0.4172 data: 0.0030 max mem: 25051 +train: [18] [580/800] eta: 0:01:44 lr: 0.000005 loss: 0.1934 (0.2105) grad: 0.1127 (0.1278) time: 0.5884 data: 0.1779 max mem: 25051 +train: [18] [600/800] eta: 0:01:34 lr: 0.000005 loss: 0.2116 (0.2129) grad: 0.1127 (0.1285) time: 0.4197 data: 0.0030 max mem: 25051 +train: [18] [620/800] eta: 0:01:24 lr: 0.000005 loss: 0.2052 (0.2122) grad: 0.1127 (0.1290) time: 0.4161 data: 0.0023 max mem: 25051 +train: [18] [640/800] eta: 0:01:15 lr: 0.000005 loss: 0.2007 (0.2125) grad: 0.0886 (0.1292) time: 0.4336 data: 0.0030 max mem: 25051 +train: [18] [660/800] eta: 0:01:06 lr: 0.000005 loss: 0.1999 (0.2125) grad: 0.1075 (0.1292) time: 0.5956 data: 0.1833 max mem: 25051 +train: [18] [680/800] eta: 0:00:56 lr: 0.000004 loss: 0.1857 (0.2116) grad: 0.0781 (0.1285) time: 0.4252 data: 0.0028 max mem: 25051 +train: [18] [700/800] eta: 0:00:47 lr: 0.000004 loss: 0.1857 (0.2119) grad: 0.0797 (0.1293) time: 0.4285 data: 0.0030 max mem: 25051 +train: [18] [720/800] eta: 0:00:37 lr: 0.000004 loss: 0.1948 (0.2126) grad: 0.1038 (0.1298) time: 0.4188 data: 0.0031 max mem: 25051 +train: [18] [740/800] eta: 0:00:28 lr: 0.000004 loss: 0.1947 (0.2115) grad: 0.0815 (0.1298) time: 0.5971 data: 0.1784 max mem: 25051 +train: [18] [760/800] eta: 0:00:18 lr: 0.000004 loss: 0.2148 (0.2136) grad: 0.1309 (0.1299) time: 0.4234 data: 0.0032 max mem: 25051 +train: [18] [780/800] eta: 0:00:09 lr: 0.000003 loss: 0.2064 (0.2131) grad: 0.1309 (0.1302) time: 0.4193 data: 0.0030 max mem: 25051 +train: [18] [799/800] eta: 0:00:00 lr: 0.000003 loss: 0.1768 (0.2121) grad: 0.1149 (0.1297) time: 0.4238 data: 0.0030 max mem: 25051 +train: [18] Total time: 0:06:15 (0.4700 s / it) +train: [18] Summary: lr: 0.000003 loss: 0.1768 (0.2121) grad: 0.1149 (0.1297) +eval (validation): [18] [ 0/11] eta: 0:00:39 time: 3.5577 data: 3.2795 max mem: 25051 +eval (validation): [18] [10/11] eta: 0:00:00 time: 0.5936 data: 0.3003 max mem: 25051 +eval (validation): [18] Total time: 0:00:06 (0.6072 s / it) +cv: [18] best hparam: (7.1, 1.0) (036) ('036_lr7.1e+00_wd1.0e+00') loss: 2.461 acc: 0.780 f1: 0.692 bacc: 0.685 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/adni_ad_vs_cn__patch__attn/checkpoint-last.pth +train: [19] [ 0/800] eta: 0:48:36 lr: nan time: 3.6455 data: 3.3100 max mem: 25051 +train: [19] [ 20/800] eta: 0:07:25 lr: 0.000003 loss: 0.1995 (0.2241) grad: 0.1208 (0.1193) time: 0.4177 data: 0.0029 max mem: 25051 +train: [19] [ 40/800] eta: 0:06:22 lr: 0.000003 loss: 0.1995 (0.2195) grad: 0.1061 (0.1193) time: 0.4321 data: 0.0027 max mem: 25051 +train: [19] [ 60/800] eta: 0:05:53 lr: 0.000003 loss: 0.1995 (0.2113) grad: 0.1197 (0.1215) time: 0.4261 data: 0.0032 max mem: 25051 +train: [19] [ 80/800] eta: 0:05:34 lr: 0.000003 loss: 0.1995 (0.2120) grad: 0.1116 (0.1109) time: 0.4219 data: 0.0029 max mem: 25051 +train: [19] [100/800] eta: 0:05:42 lr: 0.000003 loss: 0.2146 (0.2137) grad: 0.1116 (0.1157) time: 0.5894 data: 0.1746 max mem: 25051 +train: [19] [120/800] eta: 0:05:24 lr: 0.000002 loss: 0.1969 (0.2098) grad: 0.0845 (0.1066) time: 0.4177 data: 0.0024 max mem: 25051 +train: [19] [140/800] eta: 0:05:10 lr: 0.000002 loss: 0.1995 (0.2136) grad: 0.0816 (0.1127) time: 0.4324 data: 0.0031 max mem: 25051 +train: [19] [160/800] eta: 0:04:57 lr: 0.000002 loss: 0.1991 (0.2123) grad: 0.0987 (0.1179) time: 0.4235 data: 0.0031 max mem: 25051 +train: [19] [180/800] eta: 0:05:00 lr: 0.000002 loss: 0.1991 (0.2218) grad: 0.0969 (0.1188) time: 0.6371 data: 0.1791 max mem: 25051 +train: [19] [200/800] eta: 0:04:46 lr: 0.000002 loss: 0.2163 (0.2187) grad: 0.1108 (0.1180) time: 0.4173 data: 0.0025 max mem: 25051 +train: [19] [220/800] eta: 0:04:33 lr: 0.000002 loss: 0.2189 (0.2232) grad: 0.1066 (0.1209) time: 0.4202 data: 0.0034 max mem: 25051 +train: [19] [240/800] eta: 0:04:21 lr: 0.000002 loss: 0.2163 (0.2204) grad: 0.1084 (0.1237) time: 0.4152 data: 0.0031 max mem: 25051 +train: [19] [260/800] eta: 0:04:17 lr: 0.000001 loss: 0.1769 (0.2184) grad: 0.1247 (0.1235) time: 0.5992 data: 0.1809 max mem: 25051 +train: [19] [280/800] eta: 0:04:06 lr: 0.000001 loss: 0.1769 (0.2164) grad: 0.1126 (0.1210) time: 0.4321 data: 0.0032 max mem: 25051 +train: [19] [300/800] eta: 0:03:55 lr: 0.000001 loss: 0.1769 (0.2152) grad: 0.1126 (0.1226) time: 0.4224 data: 0.0031 max mem: 25051 +train: [19] [320/800] eta: 0:03:44 lr: 0.000001 loss: 0.1792 (0.2144) grad: 0.1005 (0.1199) time: 0.4252 data: 0.0031 max mem: 25051 +train: [19] [340/800] eta: 0:03:38 lr: 0.000001 loss: 0.1835 (0.2150) grad: 0.0996 (0.1219) time: 0.6037 data: 0.1798 max mem: 25051 +train: [19] [360/800] eta: 0:03:28 lr: 0.000001 loss: 0.1930 (0.2152) grad: 0.0959 (0.1199) time: 0.4452 data: 0.0025 max mem: 25051 +train: [19] [380/800] eta: 0:03:17 lr: 0.000001 loss: 0.1972 (0.2148) grad: 0.0851 (0.1199) time: 0.4201 data: 0.0030 max mem: 25051 +train: [19] [400/800] eta: 0:03:07 lr: 0.000001 loss: 0.1972 (0.2148) grad: 0.0951 (0.1191) time: 0.4209 data: 0.0032 max mem: 25051 +train: [19] [420/800] eta: 0:03:00 lr: 0.000001 loss: 0.1972 (0.2169) grad: 0.0951 (0.1219) time: 0.6006 data: 0.1822 max mem: 25051 +train: [19] [440/800] eta: 0:02:50 lr: 0.000001 loss: 0.2125 (0.2184) grad: 0.1006 (0.1210) time: 0.4385 data: 0.0028 max mem: 25051 +train: [19] [460/800] eta: 0:02:40 lr: 0.000001 loss: 0.1836 (0.2175) grad: 0.1199 (0.1225) time: 0.4265 data: 0.0031 max mem: 25051 +train: [19] [480/800] eta: 0:02:30 lr: 0.000001 loss: 0.1724 (0.2143) grad: 0.1315 (0.1255) time: 0.4246 data: 0.0031 max mem: 25051 +train: [19] [500/800] eta: 0:02:22 lr: 0.000000 loss: 0.1836 (0.2163) grad: 0.1257 (0.1255) time: 0.6026 data: 0.1883 max mem: 25051 +train: [19] [520/800] eta: 0:02:12 lr: 0.000000 loss: 0.1734 (0.2178) grad: 0.1339 (0.1278) time: 0.4403 data: 0.0017 max mem: 25051 +train: [19] [540/800] eta: 0:02:02 lr: 0.000000 loss: 0.1650 (0.2181) grad: 0.1339 (0.1284) time: 0.4223 data: 0.0029 max mem: 25051 +train: [19] [560/800] eta: 0:01:52 lr: 0.000000 loss: 0.2066 (0.2169) grad: 0.1257 (0.1291) time: 0.4201 data: 0.0032 max mem: 25051 +train: [19] [580/800] eta: 0:01:44 lr: 0.000000 loss: 0.2200 (0.2177) grad: 0.1235 (0.1298) time: 0.6258 data: 0.1889 max mem: 25051 +train: [19] [600/800] eta: 0:01:34 lr: 0.000000 loss: 0.2200 (0.2192) grad: 0.1235 (0.1306) time: 0.4200 data: 0.0027 max mem: 25051 +train: [19] [620/800] eta: 0:01:24 lr: 0.000000 loss: 0.1765 (0.2168) grad: 0.1235 (0.1310) time: 0.4180 data: 0.0029 max mem: 25051 +train: [19] [640/800] eta: 0:01:15 lr: 0.000000 loss: 0.1883 (0.2164) grad: 0.1101 (0.1311) time: 0.4243 data: 0.0030 max mem: 25051 +train: [19] [660/800] eta: 0:01:06 lr: 0.000000 loss: 0.1745 (0.2156) grad: 0.1101 (0.1306) time: 0.6146 data: 0.1800 max mem: 25051 +train: [19] [680/800] eta: 0:00:56 lr: 0.000000 loss: 0.1883 (0.2163) grad: 0.0940 (0.1292) time: 0.4279 data: 0.0031 max mem: 25051 +train: [19] [700/800] eta: 0:00:47 lr: 0.000000 loss: 0.2143 (0.2162) grad: 0.0963 (0.1308) time: 0.4257 data: 0.0029 max mem: 25051 +train: [19] [720/800] eta: 0:00:37 lr: 0.000000 loss: 0.2176 (0.2176) grad: 0.0869 (0.1293) time: 0.4198 data: 0.0032 max mem: 25051 +train: [19] [740/800] eta: 0:00:28 lr: 0.000000 loss: 0.2143 (0.2161) grad: 0.0844 (0.1289) time: 0.5880 data: 0.1798 max mem: 25051 +train: [19] [760/800] eta: 0:00:18 lr: 0.000000 loss: 0.2083 (0.2173) grad: 0.0962 (0.1287) time: 0.4103 data: 0.0023 max mem: 25051 +train: [19] [780/800] eta: 0:00:09 lr: 0.000000 loss: 0.2085 (0.2176) grad: 0.0773 (0.1285) time: 0.4142 data: 0.0028 max mem: 25051 +train: [19] [799/800] eta: 0:00:00 lr: 0.000000 loss: 0.2085 (0.2186) grad: 0.1195 (0.1306) time: 0.4214 data: 0.0030 max mem: 25051 +train: [19] Total time: 0:06:15 (0.4695 s / it) +train: [19] Summary: lr: 0.000000 loss: 0.2085 (0.2186) grad: 0.1195 (0.1306) +eval (validation): [19] [ 0/11] eta: 0:00:40 time: 3.6896 data: 3.4591 max mem: 25051 +eval (validation): [19] [10/11] eta: 0:00:00 time: 0.6102 data: 0.3273 max mem: 25051 +eval (validation): [19] Total time: 0:00:06 (0.6241 s / it) +cv: [19] best hparam: (7.1, 1.0) (036) ('036_lr7.1e+00_wd1.0e+00') loss: 2.461 acc: 0.780 f1: 0.692 bacc: 0.685 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/adni_ad_vs_cn__patch__attn/checkpoint-last.pth +evaluating last checkpoint: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/adni_ad_vs_cn__patch__attn/checkpoint-last.pth +eval model info: +{"score": 0.685483870967742, "hparam": [7.1, 1.0], "hparam_id": 36, "epoch": 19, "is_best": false, "best_score": 0.7032258064516128} +eval (train): [20] [ 0/82] eta: 0:05:14 time: 3.8311 data: 3.5909 max mem: 25051 +eval (train): [20] [20/82] eta: 0:00:34 time: 0.3881 data: 0.0248 max mem: 25051 +eval (train): [20] [40/82] eta: 0:00:19 time: 0.3901 data: 0.0472 max mem: 25051 +eval (train): [20] [60/82] eta: 0:00:10 time: 0.4221 data: 0.0369 max mem: 25051 +eval (train): [20] [80/82] eta: 0:00:00 time: 0.3347 data: 0.0114 max mem: 25051 +eval (train): [20] [81/82] eta: 0:00:00 time: 0.3363 data: 0.0171 max mem: 25051 +eval (train): [20] Total time: 0:00:35 (0.4283 s / it) +eval (validation): [20] [ 0/11] eta: 0:00:39 time: 3.6088 data: 3.3769 max mem: 25051 +eval (validation): [20] [10/11] eta: 0:00:00 time: 0.6352 data: 0.3545 max mem: 25051 +eval (validation): [20] Total time: 0:00:07 (0.6448 s / it) +eval (test): [20] [ 0/11] eta: 0:00:41 time: 3.7661 data: 3.5393 max mem: 25051 +eval (test): [20] [10/11] eta: 0:00:00 time: 0.6475 data: 0.3663 max mem: 25051 +eval (test): [20] Total time: 0:00:07 (0.6563 s / it) +evaluating best checkpoint: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/adni_ad_vs_cn__patch__attn/checkpoint-best.pth +eval model info: +{"score": 0.7032258064516128, "hparam": [0.85, 1.0], "hparam_id": 23, "epoch": 3, "is_best": true, "best_score": 0.7032258064516128} +eval (train): [20] [ 0/82] eta: 0:05:03 time: 3.7009 data: 3.4229 max mem: 25051 +eval (train): [20] [20/82] eta: 0:00:35 time: 0.4108 data: 0.0035 max mem: 25051 +eval (train): [20] [40/82] eta: 0:00:19 time: 0.3593 data: 0.0036 max mem: 25051 +eval (train): [20] [60/82] eta: 0:00:10 time: 0.4401 data: 0.0291 max mem: 25051 +eval (train): [20] [80/82] eta: 0:00:00 time: 0.3410 data: 0.0194 max mem: 25051 +eval (train): [20] [81/82] eta: 0:00:00 time: 0.3424 data: 0.0196 max mem: 25051 +eval (train): [20] Total time: 0:00:35 (0.4291 s / it) +eval (validation): [20] [ 0/11] eta: 0:00:42 time: 3.8786 data: 3.6452 max mem: 25051 +eval (validation): [20] [10/11] eta: 0:00:00 time: 0.6666 data: 0.3806 max mem: 25051 +eval (validation): [20] Total time: 0:00:07 (0.6749 s / it) +eval (test): [20] [ 0/11] eta: 0:00:41 time: 3.7366 data: 3.4613 max mem: 25051 +eval (test): [20] [10/11] eta: 0:00:00 time: 0.6462 data: 0.3571 max mem: 25051 +eval (test): [20] Total time: 0:00:07 (0.6559 s / it) +eval results: + +| model | repr | clf | dataset | ckpt | epoch | lr | wd | hparam_id | hparam | split | loss | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:------|:--------------|:-------|--------:|---------:|-----:|------------:|:------------|:-----------|--------:|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | attn | adni_ad_vs_cn | best | 3 | 0.000255 | 0.05 | 23 | [0.85, 1.0] | train | 0.37754 | 0.83537 | 0.020289 | 0.77292 | 0.027291 | 0.77539 | 0.028591 | +| flat_mae | patch | attn | adni_ad_vs_cn | best | 3 | 0.000255 | 0.05 | 23 | [0.85, 1.0] | validation | 0.52806 | 0.7561 | 0.065982 | 0.68939 | 0.080206 | 0.70323 | 0.085573 | +| flat_mae | patch | attn | adni_ad_vs_cn | best | 3 | 0.000255 | 0.05 | 23 | [0.85, 1.0] | test | 0.62938 | 0.60976 | 0.070807 | 0.50303 | 0.078555 | 0.51042 | 0.088674 | + + +done! total time: 2:10:32 diff --git a/input_space_v3/flat_lr1e-3_1/eval_v2/adni_ad_vs_cn__patch__attn/train_log.json b/input_space_v3/flat_lr1e-3_1/eval_v2/adni_ad_vs_cn__patch__attn/train_log.json new file mode 100644 index 0000000000000000000000000000000000000000..98f3b58eef3d9d67ea6034d823423e3afa764357 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_1/eval_v2/adni_ad_vs_cn__patch__attn/train_log.json @@ -0,0 +1,20 @@ +{"epoch": 0, "train/lr": 2.987987987987988e-05, "train/loss": 0.5476695947349072, "train/grad": 0.3117578808218241, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.62927734375, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.6257861328125, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.6207275390625, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.6161328125, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.61220703125, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.6072705078125, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.60259033203125, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.5979443359375, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.5930859375, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.58879638671875, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.5852587890625, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.5810498046875, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.577626953125, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.57358154296875, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.57056640625, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.56794921875, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.56516357421875, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.562215576171875, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.559197998046875, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.556739501953125, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.553905029296875, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.55103515625, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.548153076171875, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.545113525390625, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.541986083984375, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.5387005615234375, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.53608642578125, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.5338177490234375, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.5314776611328125, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.5297616577148437, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.5290542602539062, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.5282049560546875, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.5246466064453125, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.5199697875976562, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.5147377014160156, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.5117366027832031, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.5094672393798828, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.5095022583007812, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.5096868896484374, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.5052595138549805, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.5007895660400391, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.4995399475097656, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.4982039642333984, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.49669235229492187, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.49500518798828125, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.49356592178344727, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.4936090087890625, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.4960666751861572, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.4968674993515015, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.06325193441938609, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.0620206611789763, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.06013419549446553, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.05844132112339139, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.05691596610005945, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.055043338402174416, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.053222089791670445, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.051528066634200516, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.04972736635711044, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.048216738027986136, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.04700463825138286, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.04556587358005345, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.04445751399500295, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.0431922182883136, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.042229733478743585, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.04145125700393692, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.04060022886376828, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.039720736290328205, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.03887308464385569, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.0381839836249128, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.037428866932168604, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.03676036238204688, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.03610487012658268, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.03551196052227169, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.034995745765045286, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.03454786795657128, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.03432425135979429, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.03427608337020502, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.034417488786857575, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.034782731423620136, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.03500792094273493, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.03501694349804893, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.03488683232339099, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.03449769509024918, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.03367546834051609, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.033225824558176104, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.03313061324646696, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.03312684795819223, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.03327552840812132, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.03352116514928639, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.03337049396010116, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.03341085912659764, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.033554438028950244, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.03363385787699372, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.033544329444412144, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.03357006025500595, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.033818053579889235, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.034544312946964056, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.035311593138612804, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.5959054231643677, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.5905928015708923, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.5837975740432739, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.5785714387893677, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.5748135447502136, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.5710076689720154, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.5681111216545105, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.5666158199310303, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.5656831860542297, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.5649954676628113, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.5647875070571899, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.5644333362579346, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.5637775659561157, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.5627405047416687, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.5620678067207336, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.5609498620033264, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.559991717338562, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.5588011145591736, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.557036280632019, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.5554506182670593, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.5531774163246155, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.5505574941635132, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.5472429990768433, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.5440823435783386, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.5407214164733887, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.5378610491752625, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.5353466272354126, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.5332742929458618, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.529485285282135, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.5282170176506042, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.5347958207130432, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.5505196452140808, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.5569019317626953, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.5206374526023865, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.4953780174255371, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.49052271246910095, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.49147340655326843, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.5014033317565918, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.5158696174621582, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.5406739115715027, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.570695161819458, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.5995467305183411, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.6230772137641907, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.6313625574111938, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.6433320045471191, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.6575998663902283, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.6805278658866882, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.7234535813331604, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.6886900663375854, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.7560975609756098, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.7560975609756098, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.7560975609756098, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.7560975609756098, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.7560975609756098, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.7560975609756098, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.7560975609756098, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.7560975609756098, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.7560975609756098, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.7560975609756098, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.7560975609756098, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.7560975609756098, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.7560975609756098, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.7560975609756098, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.7560975609756098, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.7560975609756098, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.7560975609756098, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.7560975609756098, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.7804878048780488, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.7317073170731707, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.7317073170731707, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.6585365853658537, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.6585365853658537, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.7317073170731707, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.8048780487804879, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.7804878048780488, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.8048780487804879, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.7560975609756098, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.7560975609756098, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.7560975609756098, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.7560975609756098, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.7560975609756098, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.7560975609756098, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.7560975609756098, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.7560975609756098, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.7560975609756098, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.7560975609756098, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.7560975609756098, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.7560975609756098, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.4305555555555556, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.4305555555555556, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.4305555555555556, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.4305555555555556, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.4305555555555556, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.4305555555555556, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.4305555555555556, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.4305555555555556, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.4305555555555556, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.4305555555555556, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.4305555555555556, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.4305555555555556, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.4305555555555556, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.4305555555555556, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.4305555555555556, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.4305555555555556, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.5119047619047619, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.5119047619047619, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.5886287625418061, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.5512437810945273, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.5918552036199095, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.5370967741935484, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.5651515151515152, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.5918552036199095, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.6554621848739496, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.5886287625418061, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.6095238095238095, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.4305555555555556, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.4305555555555556, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.4305555555555556, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.4305555555555556, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.4305555555555556, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.4305555555555556, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.4305555555555556, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.4305555555555556, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.4305555555555556, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.4305555555555556, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.4305555555555556, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.4305555555555556, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.5, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.5, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.5, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.5, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.5, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.5, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.5, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.5, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.5, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.5, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.5, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.5, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.5, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.5, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.5, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.5, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.5, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.5, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.5, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.5, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.5, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.5, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.5, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.5, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.5, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.5, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.5338709677419355, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.5338709677419355, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.5838709677419355, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.5516129032258065, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.5854838709677419, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.5370967741935484, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.5709677419354839, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.5854838709677419, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.6338709677419355, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.5838709677419355, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.6, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.5, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.5, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.5, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.5, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.5, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.5, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.5, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.5, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.5, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.5, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.5, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.5, "id_best": 34, "lr_best": 0.0015299999999999997, "wd_best": 0.05, "train/loss_best": 0.5147377014160156, "validation/loss_best": 0.4953780174255371, "validation/acc_best": 0.8048780487804879, "validation/f1_best": 0.6554621848739496, "validation/bacc_best": 0.6338709677419355} +{"epoch": 1, "train/lr": 8.993993993993998e-05, "train/loss": 0.4792527974396944, "train/grad": 0.2739703590422869, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.56874267578125, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.5654248046875, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.561685791015625, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.5588720703125, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.556728515625, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.55434814453125, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.552305908203125, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.550255126953125, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.547816162109375, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.5453369140625, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.543076171875, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.539715576171875, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.53671875, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.532681884765625, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.528961181640625, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.5257073974609375, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.52197509765625, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.517769775390625, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.5132379150390625, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.5090533447265625, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.50392333984375, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.4987060546875, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.4931231689453125, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.487431640625, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.48227508544921877, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.4772711181640625, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.47437759399414064, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.4724364471435547, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.47149101257324216, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.4724375152587891, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.4746678924560547, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.47733322143554685, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.4798695373535156, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.47363624572753904, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.4599843406677246, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.44807814598083495, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.4402203273773193, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.4322731399536133, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.4180843037366867, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.3996797755360603, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.3895133973658085, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.3880456367135048, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.3887041102349758, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.35351525962352753, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.3220151424407959, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.3491385032236576, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.34386528328061106, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.394601092338562, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.38627602115273474, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.03679731858428568, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.03558688207762316, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.034238569852896035, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.033434608490206304, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.03292810067534447, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.032502110567875206, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.032230651122517884, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.032060529987793414, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.03194921178044751, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.03188117907848209, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.031827057101763784, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.0317545700375922, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.03169214267283678, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.03160677104024216, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.03153983203228563, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.03147960539674386, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.03144354332238436, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.03143917249049991, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.031489639976061884, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.031590872234664856, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.031774675876367835, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.03204513776348904, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.032458493914455176, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.03298803808167577, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.03353257686831057, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.03411798543529585, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.03468768871854991, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.03519785968586803, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0357365292054601, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.035991706741042434, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.035737443116959186, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.035131136917043476, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.034034768594428895, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.033405765071511266, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.03341122065437958, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.03223738052649423, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.031077765063382685, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.030460759762208908, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.02974073217017576, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.029029909698292614, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.029583639206830412, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.030544253119733186, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.032871089165564624, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.032540709795430306, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.032649878470692784, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.04043670765197021, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.04454658553560876, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.05514576979912818, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.05869687361526303, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.565779447555542, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.5654213428497314, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.5647491216659546, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.564382016658783, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.5636328458786011, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.56293785572052, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.5623437762260437, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.5611622929573059, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.5600048899650574, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.5586423873901367, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.5575801134109497, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.555715024471283, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.5539270043373108, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.5514807105064392, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.5488460063934326, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.5467352271080017, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.543616771697998, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.5400885343551636, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.5358107089996338, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.5316172242164612, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.5270181894302368, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.5231130123138428, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.5205320715904236, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.5207297801971436, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.5264270305633545, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.5360190272331238, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.5403785705566406, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.5367079973220825, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.527604341506958, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.5234991312026978, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.5241052508354187, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.5251006484031677, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.5275429487228394, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.5330333113670349, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.554225742816925, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.6049025654792786, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.6183961033821106, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.6621610522270203, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.7149508595466614, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.8807563781738281, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.9269306659698486, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.93067866563797, "validation/loss_042_lr1.9e+01_wd1.0e+00": 1.190624475479126, "validation/loss_043_lr2.2e+01_wd1.0e+00": 1.1179229021072388, "validation/loss_044_lr2.6e+01_wd1.0e+00": 1.8646913766860962, "validation/loss_045_lr3.1e+01_wd1.0e+00": 1.3192695379257202, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.719837188720703, "validation/loss_047_lr4.3e+01_wd1.0e+00": 1.9728895425796509, "validation/loss_048_lr5.0e+01_wd1.0e+00": 2.7711520195007324, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.7560975609756098, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.7560975609756098, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.7560975609756098, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.7560975609756098, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.7560975609756098, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.7560975609756098, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.7560975609756098, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.7560975609756098, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.7560975609756098, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.7560975609756098, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.7560975609756098, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.7804878048780488, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.8048780487804879, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.7317073170731707, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.6829268292682927, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.6829268292682927, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.7073170731707317, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.7073170731707317, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.7073170731707317, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.7073170731707317, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.7073170731707317, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.7073170731707317, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.7073170731707317, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.7073170731707317, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.7317073170731707, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.6829268292682927, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.6829268292682927, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.6829268292682927, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.6585365853658537, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.6341463414634146, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.6585365853658537, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.6585365853658537, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.6585365853658537, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.6829268292682927, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.6341463414634146, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.7073170731707317, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.7317073170731707, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.7073170731707317, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.7317073170731707, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.4305555555555556, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.4305555555555556, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.4305555555555556, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.4305555555555556, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.4305555555555556, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.4305555555555556, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.4305555555555556, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.4305555555555556, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.4305555555555556, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.4305555555555556, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.4305555555555556, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.5275288092189501, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.6095238095238095, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.5512437810945273, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.5176470588235295, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.5547201336675021, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.603225806451613, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.603225806451613, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.5729166666666666, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.5340909090909092, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.5340909090909092, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.5340909090909092, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.5729166666666666, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.5729166666666666, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.6479313036690086, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.6410774410774411, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.6259649122807017, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.6259649122807017, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.6057692307692308, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.5858585858585859, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.6057692307692308, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.6057692307692308, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.6057692307692308, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.6072218128224024, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.5998698763825634, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.5729166666666666, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.4972129319955407, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.4831932773109243, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.4225352112676056, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.5, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.5, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.5, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.5, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.5, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.5, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.5, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.5, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.5, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.5, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.5, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.5, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.5, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.5, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.5, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.5, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.5, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.5, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.5, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.5, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.5, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.55, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.6, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.5516129032258065, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.5193548387096775, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.5532258064516129, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.603225806451613, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.603225806451613, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.5693548387096774, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.535483870967742, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.535483870967742, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.535483870967742, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.5693548387096774, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.5693548387096774, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.6532258064516129, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.6887096774193548, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.6548387096774193, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.6548387096774193, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.6387096774193548, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.6225806451612903, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.6387096774193548, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.6387096774193548, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.6387096774193548, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.6209677419354839, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.6564516129032258, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.5693548387096774, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.5177419354838709, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.5016129032258064, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.4838709677419355, "id_best": 35, "lr_best": 0.0018, "wd_best": 0.05, "train/loss_best": 0.44807814598083495, "validation/loss_best": 0.6049025654792786, "validation/acc_best": 0.6829268292682927, "validation/f1_best": 0.6410774410774411, "validation/bacc_best": 0.6887096774193548} +{"epoch": 2, "train/lr": 0.00014999999999999988, "train/loss": 0.4120488431304693, "train/grad": 0.28532596047967673, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.535369873046875, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.533948974609375, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.531783447265625, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.529818115234375, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.52786376953125, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.525401611328125, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.52261962890625, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.519876708984375, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.516436767578125, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.5130810546875, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.509920654296875, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.505472412109375, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.5016107177734375, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.495977783203125, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.490777587890625, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.48590087890625, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.4799395751953125, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.4734539794921875, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.46665374755859373, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.4602787780761719, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.45217376708984375, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.44470733642578125, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.4389611053466797, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.4361455535888672, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.4345113754272461, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.43023807525634766, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.42361257553100584, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.4165357208251953, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.4080053901672363, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.40030837059020996, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.3935677981376648, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.38433429002761843, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.3646529227495193, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.33785943493247034, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.3047123302519321, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.2481963086128235, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.1898783737421036, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.15361774027347563, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.10541750773787499, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.1154753278195858, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.06923979476094246, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.08385886907577515, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.15757533475756647, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.15012509375810623, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.26951723769307134, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.3169255182147026, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.7892082554101943, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.5431386929750442, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.8017075650393963, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.030155934621579946, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.03008491257438436, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.030017044185660778, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.02997723866486922, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.02994095776928589, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.029912202118430285, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.02988695029169321, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.029862947301007806, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.029873261742759494, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.02989398536970839, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.029930119474884123, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.030022531882859766, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.030139371582772582, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.030314725728239865, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.030450294066686184, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.030573051462415606, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.030739111844450235, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.030937202386558057, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.03108945084735751, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.03108450965490192, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.031014003618620337, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.03136310287751257, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.03257280028657988, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.03420748068019748, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.03555235788226128, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0361169767472893, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.035814745433162896, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.03515805621631443, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.034192477783653884, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.032776862909086046, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.031399360438808796, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.02991801124298945, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.02743306928081438, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.025875539029948415, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.02463154797675088, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.02403262292733416, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.02090272274130257, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.017258754332524405, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.015436708449342404, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.02008102399733616, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.017438883314462146, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.017497166913053662, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.03064610842174261, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.039146829768240465, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.061599140659114655, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.05125216755194884, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0235508743301034, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.04120814057714597, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.038326068216308184, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.5628046989440918, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.5620120763778687, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.5606421232223511, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.5595335960388184, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.558301568031311, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.5566859245300293, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.5549853444099426, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.5531260371208191, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.5509379506111145, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.548635721206665, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.5465211868286133, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.5436676144599915, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.5410650968551636, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.5372368693351746, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.5325726270675659, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.5271141529083252, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.5209274291992188, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.5168854594230652, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.5216054916381836, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.5399308204650879, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.5730566382408142, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.6060266494750977, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.6339176297187805, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.648824155330658, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.6475793123245239, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.6111542582511902, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.5734759569168091, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.5554620027542114, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.5469558835029602, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.5462477803230286, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.5592859983444214, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.5813853740692139, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.6439175605773926, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.7813146710395813, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.9932215809822083, "validation/loss_035_lr6.0e+00_wd1.0e+00": 1.286612629890442, "validation/loss_036_lr7.1e+00_wd1.0e+00": 1.8573098182678223, "validation/loss_037_lr8.3e+00_wd1.0e+00": 1.8136980533599854, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.3629331588745117, "validation/loss_039_lr1.2e+01_wd1.0e+00": 1.8692902326583862, "validation/loss_040_lr1.4e+01_wd1.0e+00": 1.2293134927749634, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.0454647541046143, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.668015241622925, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.317460536956787, "validation/loss_044_lr2.6e+01_wd1.0e+00": 4.12923002243042, "validation/loss_045_lr3.1e+01_wd1.0e+00": 5.987327575683594, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.6931472420692444, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.7560975609756098, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.7560975609756098, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.7560975609756098, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.7560975609756098, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.7560975609756098, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.7560975609756098, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.7560975609756098, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.8048780487804879, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.6829268292682927, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.7073170731707317, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.5853658536585366, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.5365853658536586, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.6097560975609756, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.6097560975609756, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.6097560975609756, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.5853658536585366, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.5609756097560976, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.6585365853658537, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.7317073170731707, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.6829268292682927, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.6585365853658537, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.6829268292682927, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.7073170731707317, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.6829268292682927, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.7073170731707317, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.6829268292682927, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.6585365853658537, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.6829268292682927, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.6341463414634146, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.7317073170731707, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.7317073170731707, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.7317073170731707, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.6829268292682927, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.7560975609756098, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.7073170731707317, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.6341463414634146, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.7560975609756098, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.7560975609756098, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.7560975609756098, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.4305555555555556, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.4305555555555556, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.4305555555555556, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.4305555555555556, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.4305555555555556, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.4305555555555556, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.4305555555555556, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.6095238095238095, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.5176470588235295, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.603225806451613, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.5108771929824562, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.4754208754208754, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.5794871794871794, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.5794871794871794, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.5661375661375662, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.5306397306397306, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.4698275862068966, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.5370967741935484, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.5918552036199095, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.5547201336675021, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.5370967741935484, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.6072218128224024, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.6272727272727273, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.5839188134270101, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.6272727272727273, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.5547201336675021, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.4564393939393939, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.5839188134270101, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.44343891402714936, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.5512437810945273, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.5918552036199095, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.5512437810945273, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.4696517412935323, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.6693548387096775, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.6272727272727273, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.6110056925996206, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.4305555555555556, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.4305555555555556, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.4305555555555556, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.5, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.5, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.5, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.5, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.5, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.5, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.5, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.5, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.5, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.5, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.5, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.5, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.5, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.5, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.5, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.5, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.5, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.6, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.5193548387096775, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.603225806451613, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.5225806451612903, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.4903225806451613, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.6403225806451613, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.6403225806451613, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.6064516129032258, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.5564516129032258, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.4725806451612903, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.5370967741935484, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.5854838709677419, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.5532258064516129, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.5370967741935484, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.6209677419354839, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.6370967741935484, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.5870967741935484, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.6370967741935484, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.5532258064516129, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.4693548387096774, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.5870967741935484, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.45322580645161287, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.5516129032258065, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.5854838709677419, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.5516129032258065, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.4854838709677419, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.6693548387096775, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.6370967741935484, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.6903225806451614, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.5, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.5, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.5, "id_best": 45, "lr_best": 0.0093, "wd_best": 0.05, "train/loss_best": 0.3169255182147026, "validation/loss_best": 5.987327575683594, "validation/acc_best": 0.6341463414634146, "validation/f1_best": 0.6110056925996206, "validation/bacc_best": 0.6903225806451614} +{"epoch": 3, "train/lr": 0.0002100600600600602, "train/loss": 0.4045325054973364, "train/grad": 0.2730969450995326, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.555447998046875, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.55300537109375, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.549462890625, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.545960693359375, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.542867431640625, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.538690185546875, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.534429931640625, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.529952392578125, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.52462158203125, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.5190814208984375, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.51389404296875, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.5065679931640625, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.49991424560546877, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.4908660888671875, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.4829998779296875, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.4759382629394531, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.4676103210449219, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.4589935302734375, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.4523357391357422, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.4489034271240234, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.4471018981933594, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.44600765228271483, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.4434161376953125, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.43713132858276366, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.42800814628601075, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.4111438465118408, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.3904110908508301, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.3690076744556427, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.33670246362686157, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.2965097126364708, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.24340769946575164, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.1866102996468544, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.1249704922735691, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.0618352797627449, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.06640972286462783, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.04957504808902741, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.004729547947645188, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.0006212374567985535, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.0006362484395503998, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.0428525422513485, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.6267743265628815, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.22487469002604485, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.13716094240546226, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.3749754031002521, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.6103631903231144, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.7950943897664547, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.69140625, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.69140625, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.69140625, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.02880671849939972, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.02873477680841461, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.028625088308472185, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.02853330855257809, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.02845899486215785, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.02837086614686996, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.028297203194815667, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.028236061399802566, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.028188336761668323, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.028150110782589763, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.02814680230803788, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.028166855298914016, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.02824323966866359, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.028458668880630283, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.02877729556290433, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.029167138184420766, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.029602412269450724, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.029936950451228767, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.03027225028956309, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.030700703067705035, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.03128520157188177, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.03210888484027237, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.03234886677702889, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.03169403651263565, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.030618146574124695, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.02907240100670606, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.028013876099139454, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.02741396467667073, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.02630196466110647, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.024817229884210975, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.02185853021219373, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.01852183132432401, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.015591911870578769, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.01101005011361849, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.012206896154639253, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.008985725873417323, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.002135969577675496, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.00023644731299555133, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0002182067268768151, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.006851477908869583, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.07745054162166154, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0409484283023221, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.02516457329162433, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.06424210730235581, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.07069569627437998, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.016237441207463447, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.5591528415679932, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.5578680038452148, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.5560415983200073, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.5540242791175842, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.552475094795227, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.5500584840774536, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.5471706986427307, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.5444962978363037, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.5408809185028076, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.537550151348114, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.5343602895736694, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.5297125577926636, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.5252494812011719, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.5191128849983215, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.5140659809112549, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.5101970434188843, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.5060566067695618, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.5044165849685669, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.5120522975921631, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.5168626308441162, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.5126292109489441, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.5099731087684631, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.5145303010940552, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.5280576944351196, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.5514608025550842, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.5878968834877014, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.6362127065658569, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.6781284809112549, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.7756367325782776, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.9539182782173157, "validation/loss_030_lr2.7e+00_wd1.0e+00": 1.4747192859649658, "validation/loss_031_lr3.1e+00_wd1.0e+00": 1.7945020198822021, "validation/loss_032_lr3.7e+00_wd1.0e+00": 1.840986728668213, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.6480956077575684, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.0642738342285156, "validation/loss_035_lr6.0e+00_wd1.0e+00": 1.7299705743789673, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.2401516437530518, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.0837249755859375, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.631756544113159, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.6219325065612793, "validation/loss_040_lr1.4e+01_wd1.0e+00": 5.178646087646484, "validation/loss_041_lr1.6e+01_wd1.0e+00": 4.9809160232543945, "validation/loss_042_lr1.9e+01_wd1.0e+00": 4.089223384857178, "validation/loss_043_lr2.2e+01_wd1.0e+00": 4.7580037117004395, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.6931472420692444, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.7560975609756098, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.7560975609756098, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.7560975609756098, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.7804878048780488, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.7804878048780488, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.8048780487804879, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.8048780487804879, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.7317073170731707, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.7560975609756098, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.7317073170731707, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.7317073170731707, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.7317073170731707, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.7073170731707317, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.7560975609756098, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.7560975609756098, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.6829268292682927, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.6829268292682927, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.7317073170731707, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.7317073170731707, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.7317073170731707, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.6829268292682927, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.6585365853658537, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.7073170731707317, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.6829268292682927, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.7073170731707317, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.7560975609756098, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.7073170731707317, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.7073170731707317, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.6097560975609756, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.7073170731707317, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.7073170731707317, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.6097560975609756, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.7317073170731707, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.7073170731707317, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.7560975609756098, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.7560975609756098, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.7560975609756098, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.7560975609756098, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.7560975609756098, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.4305555555555556, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.4305555555555556, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.4305555555555556, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.5275288092189501, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.5275288092189501, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.6095238095238095, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.6095238095238095, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.5512437810945273, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.6117424242424243, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.6232247284878863, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.6232247284878863, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.6232247284878863, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.5729166666666666, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.6893939393939394, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.6893939393939394, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.6259649122807017, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.6259649122807017, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.6676492262343405, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.6676492262343405, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.6676492262343405, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.6072218128224024, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.5370967741935484, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.646551724137931, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.5547201336675021, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.603225806451613, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.6893939393939394, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.5729166666666666, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.603225806451613, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.4305555555555556, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.4831932773109243, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.4831932773109243, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.47096774193548385, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.6676492262343405, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.603225806451613, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.4305555555555556, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.4305555555555556, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.4305555555555556, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.4305555555555556, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.4305555555555556, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.5, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.5, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.5, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.5, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.5, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.5, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.5, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.5, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.5, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.5, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.5, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.5, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.5, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.55, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.55, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.6, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.6, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.5516129032258065, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.6016129032258064, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.6193548387096774, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.6193548387096774, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.6193548387096774, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.5693548387096774, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.7032258064516128, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.7032258064516128, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.6548387096774193, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.6548387096774193, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.6870967741935483, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.6870967741935483, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.6870967741935483, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.6209677419354839, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.5370967741935484, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.6709677419354838, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.5532258064516129, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.603225806451613, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.7032258064516128, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.5693548387096774, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.603225806451613, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.43709677419354837, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.5016129032258064, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.5016129032258064, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.47096774193548385, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.6870967741935483, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.603225806451613, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.5, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.5, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.5, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.5, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.5, "id_best": 23, "lr_best": 0.00025499999999999996, "wd_best": 0.05, "train/loss_best": 0.43713132858276366, "validation/loss_best": 0.5280576944351196, "validation/acc_best": 0.7560975609756098, "validation/f1_best": 0.6893939393939394, "validation/bacc_best": 0.7032258064516128} +{"epoch": 4, "train/lr": 0.0002701201201201201, "train/loss": 0.3311793905496597, "train/grad": 0.216820236928761, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.496710205078125, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.49339599609375, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.488448486328125, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.4839306640625, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.48001220703125, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.4751080322265625, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.4702490234375, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.46532958984375, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.459844970703125, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.45434661865234377, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.44921722412109377, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.441893310546875, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.4351422119140625, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.42616790771484375, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.4191679382324219, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.41317771911621093, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.4058502197265625, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.39790977478027345, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.39016036987304686, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.3816741943359375, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.36930299758911134, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.35917547702789304, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.35036386966705324, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.3371951138973236, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.31468073070049285, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.2775646927952766, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.23377362981438637, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.18985138773918153, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.12059730693697929, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.06511836692690849, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.019131523221731186, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.0037627197802066804, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.0021405568718910217, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.022093820124864577, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.013336826711893082, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.000535518079996109, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.00030190214514732363, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.0002694632112979889, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.0002396000921726227, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.0001654103398323059, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.16736901864409448, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.23108072623610496, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.7315477049350738, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.03342428907752037, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.69140625, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.69140625, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.69140625, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.69140625, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.69140625, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.03109474005177617, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.03098927960731089, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.030849337736144664, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.03074997349176556, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.03066239818930626, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.0305922694504261, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.03053822748363018, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.03050998367834836, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.03053563104942441, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.030586157548241316, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.030648506998550148, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.030806895883288235, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.030971509222872555, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.031196393815334886, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.031398255375679585, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.03159463863354176, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.03195347335422412, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.032675291101913896, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.033548096781596544, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.034278581591788676, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.0347106101969257, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.03472480352502316, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.03426487443968654, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.03317759174387902, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.03172057142481208, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.030766952701378615, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.03004240244394168, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.02768235347000882, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.02136611447960604, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.012881123676052084, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.005783665544549876, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0012962330794516674, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.001119478209755016, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.007543591988421667, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.00461915673569365, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.00016341791380000359, "train/grad_036_lr7.1e+00_wd1.0e+00": 9.811650701067264e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 8.76673739458056e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 8.540524363979784e-05, "train/grad_039_lr1.2e+01_wd1.0e+00": 6.671668537933329e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.020943723539037992, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.048579966438840605, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.021296794626156444, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.014424606540382898, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.5547549724578857, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.5528081655502319, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.5498469471931458, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.5469428300857544, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.5444300770759583, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.5406306982040405, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.5367299318313599, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.5322391390800476, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.5272812843322754, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.5221980214118958, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.5180112719535828, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.5144819617271423, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.514562726020813, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.5171836614608765, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.5156714916229248, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.5096114277839661, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.5034549236297607, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.5049632787704468, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.5110296607017517, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.5167357325553894, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.5277462601661682, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.56203293800354, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.6303370594978333, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.6758447885513306, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.6844568848609924, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.7630833983421326, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.9513382315635681, "validation/loss_027_lr1.6e+00_wd1.0e+00": 1.1448928117752075, "validation/loss_028_lr1.9e+00_wd1.0e+00": 1.5277601480484009, "validation/loss_029_lr2.3e+00_wd1.0e+00": 1.8373559713363647, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.2358736991882324, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.2727198600769043, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.207961082458496, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.8563168048858643, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.470668315887451, "validation/loss_035_lr6.0e+00_wd1.0e+00": 1.8978009223937988, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.291118621826172, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.1924543380737305, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.74588942527771, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.5600438117980957, "validation/loss_040_lr1.4e+01_wd1.0e+00": 4.7086992263793945, "validation/loss_041_lr1.6e+01_wd1.0e+00": 8.541969299316406, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_043_lr2.2e+01_wd1.0e+00": 4.708595275878906, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.6931472420692444, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.7560975609756098, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.7560975609756098, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.7560975609756098, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.7560975609756098, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.7560975609756098, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.8048780487804879, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.7804878048780488, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.7560975609756098, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.7560975609756098, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.7804878048780488, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.7317073170731707, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.8048780487804879, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.8048780487804879, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.7804878048780488, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.7073170731707317, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.7073170731707317, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.6829268292682927, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.7073170731707317, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.7560975609756098, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.6829268292682927, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.6585365853658537, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.6341463414634146, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.6585365853658537, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.6829268292682927, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.6585365853658537, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.7073170731707317, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.7073170731707317, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.7073170731707317, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.6341463414634146, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.7073170731707317, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.6585365853658537, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.6829268292682927, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.7560975609756098, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.7560975609756098, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.7560975609756098, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.7560975609756098, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.7560975609756098, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.7560975609756098, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.7560975609756098, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.4305555555555556, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.4305555555555556, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.4305555555555556, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.4305555555555556, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.4305555555555556, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.6095238095238095, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.5886287625418061, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.569327731092437, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.569327731092437, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.6328358208955224, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.5918552036199095, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.6554621848739496, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.6554621848739496, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.5886287625418061, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.5340909090909092, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.603225806451613, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.5839188134270101, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.603225806451613, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.6440972222222222, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.5547201336675021, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.5370967741935484, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.48621553884711777, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.5370967741935484, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.5839188134270101, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.5017361111111112, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.603225806451613, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.5729166666666666, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.603225806451613, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.48621553884711777, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.4831932773109243, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.39705882352941174, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.5176470588235295, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.4305555555555556, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.6117424242424243, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.4305555555555556, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.4305555555555556, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.4305555555555556, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.4305555555555556, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.4305555555555556, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.5, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.5, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.5, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.5, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.5, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.5, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.5, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.5, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.5, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.5, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.5, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.5, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.5, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.5, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.5, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.6, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.5838709677419355, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.567741935483871, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.567741935483871, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.6177419354838709, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.5854838709677419, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.6338709677419355, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.6338709677419355, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.5838709677419355, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.535483870967742, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.603225806451613, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.5870967741935484, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.603225806451613, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.635483870967742, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.5532258064516129, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.5370967741935484, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.48709677419354835, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.5370967741935484, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.5870967741935484, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.5032258064516129, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.603225806451613, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.5693548387096774, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.603225806451613, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.48709677419354835, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.5016129032258064, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.43548387096774194, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.5193548387096775, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.5, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.6016129032258064, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.5, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.5, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.5, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.5, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.5, "id_best": 28, "lr_best": 0.00057, "wd_best": 0.05, "train/loss_best": 0.12059730693697929, "validation/loss_best": 1.5277601480484009, "validation/acc_best": 0.7560975609756098, "validation/f1_best": 0.6440972222222222, "validation/bacc_best": 0.635483870967742} +{"epoch": 5, "train/lr": 0.00029891323817685334, "train/loss": 0.32039565350860355, "train/grad": 0.19702390119433402, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.51598876953125, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.5127276611328125, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.5076617431640625, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.5033197021484375, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.4993048095703125, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.4942218017578125, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.488955078125, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.4836077880859375, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.4771969604492188, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.47095916748046873, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.465565185546875, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.45833099365234375, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.45192718505859375, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.4422874450683594, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.43300270080566405, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.42513145446777345, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.4173699188232422, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.41102210998535155, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.4060977840423584, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.4030406951904297, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.39700904846191404, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.37795003890991213, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.3394883340597153, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.28789823457598684, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.23486770153045655, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.15985680297017096, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.08035727798938751, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.045235519856214525, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0074568261206150056, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0029143904149532317, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0008419105410575867, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.000604054480791092, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.000401342511177063, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.0001906217634677887, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.00028499945998191836, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.00023207008838653563, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.00017635330557823182, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.00016207665205001832, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.00017365843057632447, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.00013227373361587524, "train/loss_040_lr1.4e+01_wd1.0e+00": 9.96813178062439e-06, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.3469012576341629, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.69140625, "train/loss_043_lr2.2e+01_wd1.0e+00": 8.621782064437866e-05, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.69140625, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.69140625, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.69140625, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.69140625, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.69140625, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.03141386785311624, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.031248324746266008, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.031031945606227965, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.030850306891370565, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.030720377042889595, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.03059111994225532, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.030500198437366635, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.03045207931427285, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.03043091237777844, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.03045369163621217, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.030488688957411796, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.03054610191611573, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.030649368530139328, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.031021365027409046, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.031429759678430855, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.031853809971362355, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.032524238228797915, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.03344457037979737, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.03467706807889044, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.0358054878260009, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.03660957171581686, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.03566445875912905, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.03406568492995575, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.03230899185640737, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.03031083392444998, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.025588432044023647, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.016963253733702003, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.011857891808758722, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0023963652378006374, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.000911809619392443, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.00028618599357287165, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.00019825158918138186, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.00012765224582835799, "train/grad_033_lr4.3e+00_wd1.0e+00": 8.234295592899344e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 9.2863378945367e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 7.767122744098743e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 6.076791016084826e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 5.4577750667021974e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 5.593976334466788e-05, "train/grad_039_lr1.2e+01_wd1.0e+00": 4.931187408033111e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 1.2107406247499592e-05, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.058832681926303226, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0, "train/grad_043_lr2.2e+01_wd1.0e+00": 6.264877828732029e-05, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.5503843426704407, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.5482605695724487, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.5444614887237549, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.5412697196006775, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.5381169319152832, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.5336761474609375, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.5292530655860901, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.5246169567108154, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.5196036100387573, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.5153623819351196, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.5120255351066589, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.5091183185577393, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.508354127407074, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.5103415250778198, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.5109041929244995, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.5121678709983826, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.518298864364624, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.5319498777389526, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.55097496509552, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.5695434212684631, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.5985237956047058, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.6498282551765442, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.7213733196258545, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.8663809895515442, "validation/loss_024_lr1.0e+00_wd1.0e+00": 1.0959877967834473, "validation/loss_025_lr1.2e+00_wd1.0e+00": 1.3773729801177979, "validation/loss_026_lr1.4e+00_wd1.0e+00": 1.6586546897888184, "validation/loss_027_lr1.6e+00_wd1.0e+00": 1.9129908084869385, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.0599751472473145, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.1695775985717773, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.4262301921844482, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.4318974018096924, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.3224923610687256, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.8780462741851807, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.5768959522247314, "validation/loss_035_lr6.0e+00_wd1.0e+00": 1.9786618947982788, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.3330483436584473, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.245830535888672, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.781902313232422, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.5063366889953613, "validation/loss_040_lr1.4e+01_wd1.0e+00": 4.166045188903809, "validation/loss_041_lr1.6e+01_wd1.0e+00": 9.372255325317383, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.81147837638855, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.6931472420692444, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.7804878048780488, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.8048780487804879, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.8048780487804879, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.8048780487804879, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.7804878048780488, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.7804878048780488, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.7560975609756098, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.7317073170731707, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.6829268292682927, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.6829268292682927, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.6585365853658537, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.6341463414634146, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.6341463414634146, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.6341463414634146, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.6585365853658537, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.6585365853658537, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.6585365853658537, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.7073170731707317, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.7073170731707317, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.7317073170731707, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.6341463414634146, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.6341463414634146, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.6585365853658537, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.6829268292682927, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.6585365853658537, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.7317073170731707, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.7073170731707317, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.7073170731707317, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.6341463414634146, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.7073170731707317, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.6341463414634146, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.6341463414634146, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.7560975609756098, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.7317073170731707, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.7560975609756098, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.7560975609756098, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.7560975609756098, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.7560975609756098, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.7560975609756098, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.5275288092189501, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.6095238095238095, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.6095238095238095, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.6095238095238095, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.5886287625418061, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.5886287625418061, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.6117424242424243, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.5918552036199095, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.5547201336675021, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.5547201336675021, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.5651515151515152, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.5467943994104643, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.5467943994104643, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.5467943994104643, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.5651515151515152, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.5651515151515152, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.5651515151515152, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.5729166666666666, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.603225806451613, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.6479313036690086, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.48621553884711777, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.48621553884711777, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.5370967741935484, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.5839188134270101, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.5017361111111112, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.6479313036690086, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.5729166666666666, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.603225806451613, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.48621553884711777, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.4831932773109243, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.3880597014925373, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.5199063231850116, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.4305555555555556, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.5918552036199095, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.4305555555555556, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.4305555555555556, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.4305555555555556, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.4305555555555556, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.4305555555555556, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.5, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.5, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.5, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.5, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.5, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.5, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.5, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.5, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.5, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.5, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.55, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.6, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.6, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.6, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.5838709677419355, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.5838709677419355, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.6016129032258064, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.5854838709677419, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.5532258064516129, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.5532258064516129, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.5709677419354839, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.5548387096774194, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.5548387096774194, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.5548387096774194, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.5709677419354839, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.5709677419354839, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.5709677419354839, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.5693548387096774, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.603225806451613, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.6532258064516129, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.48709677419354835, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.48709677419354835, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.5370967741935484, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.5870967741935484, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.5032258064516129, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.6532258064516129, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.5693548387096774, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.603225806451613, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.48709677419354835, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.5016129032258064, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.41935483870967744, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.5209677419354839, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.5, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.5854838709677419, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.5, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.5, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.5, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.5, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.5, "id_best": 29, "lr_best": 0.0006899999999999999, "wd_best": 0.05, "train/loss_best": 0.0029143904149532317, "validation/loss_best": 2.1695775985717773, "validation/acc_best": 0.7317073170731707, "validation/f1_best": 0.6479313036690086, "validation/bacc_best": 0.6532258064516129} +{"epoch": 6, "train/lr": 0.0002924170901991409, "train/loss": 0.2861354997754097, "train/grad": 0.18303241591900588, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.4971380615234375, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.4926727294921875, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.486168212890625, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.4804815673828125, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.475496826171875, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.4690081787109375, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.46248779296875, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.45589996337890626, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.44797607421875, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.440487060546875, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.43391204833984376, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.4249595642089844, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.4169879913330078, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.4066531372070312, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.39709625244140623, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.388125, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.3765541076660156, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.36399365425109864, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.3508287000656128, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.33562530994415285, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.30705914735794065, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.2637476894259453, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.21094315752387047, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.1438117055594921, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.06463250264525414, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.019205075055360794, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.006100174784660339, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0027212023735046385, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0014813756942749024, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0009267103672027588, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.00043197736144065855, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.00032564252614974976, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.0002460618317127228, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.00015196844935417176, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.00016264155507087708, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.0001622295379638672, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.00013483867049217225, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.00012409687042236328, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.00012629702687263488, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.00011393919587135315, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.6651153564453126e-05, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.2469120991230011, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.69140625, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.0001128910481929779, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.69140625, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.69140625, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.69140625, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.69140625, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.69140625, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.030494955498725176, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.030448424047790468, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.030373861715197563, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.03032796412240714, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.03028406604891643, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.03024184631416574, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.030217512231320142, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.03021433955989778, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.03027534197550267, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.030425838420633226, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.03064484532456845, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.031056966544128956, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.03148846905678511, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.03216030110605061, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.03287561648525297, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.03354480440961197, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.03407130701467395, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.0344806830631569, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.035333302502986046, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.03587960820645094, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.03525315979728475, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.033357462675776335, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.032008132967166605, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.02856559104984626, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.017116649197996592, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.006672819256491494, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.002265060227509821, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.001041901821463398, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0005658174377458636, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0003380382233990531, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0001455538117352262, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.00010933824297353568, "train/grad_032_lr3.7e+00_wd1.0e+00": 8.338476543030993e-05, "train/grad_033_lr4.3e+00_wd1.0e+00": 5.5467248355114404e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 6.296544949520922e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 5.707349291469654e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 4.7437008831821e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 4.352861792540352e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 4.3885911691177173e-05, "train/grad_039_lr1.2e+01_wd1.0e+00": 4.428296589992442e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 1.923694791871759e-05, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.03884078278297526, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0, "train/grad_043_lr2.2e+01_wd1.0e+00": 8.441635209816668e-05, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.5461666584014893, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.5434805750846863, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.5391080975532532, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.5353596210479736, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.5315186381340027, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.526880145072937, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.5220579504966736, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.5174885988235474, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.5123777389526367, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.5089542269706726, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.507476806640625, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.5076888203620911, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.5093689560890198, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.5108963847160339, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.5168821811676025, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.5297961235046387, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.5575066208839417, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.5924937725067139, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.6310670375823975, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.6708641648292542, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.719352126121521, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.7799175381660461, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.9449172616004944, "validation/loss_023_lr8.5e-01_wd1.0e+00": 1.2121388912200928, "validation/loss_024_lr1.0e+00_wd1.0e+00": 1.5211892127990723, "validation/loss_025_lr1.2e+00_wd1.0e+00": 1.8131126165390015, "validation/loss_026_lr1.4e+00_wd1.0e+00": 1.9733057022094727, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.1117613315582275, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.251216411590576, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.3179829120635986, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.523252010345459, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.537374258041382, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.3970882892608643, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.8872249126434326, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.635042190551758, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.0249900817871094, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.357379913330078, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.289255380630493, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.7982616424560547, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.4989757537841797, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.748838424682617, "validation/loss_041_lr1.6e+01_wd1.0e+00": 12.012300491333008, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.103130340576172, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.6931472420692444, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.7804878048780488, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.8048780487804879, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.8048780487804879, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.8048780487804879, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.8048780487804879, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.7804878048780488, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.7560975609756098, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.7804878048780488, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.7560975609756098, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.7560975609756098, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.7317073170731707, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.7317073170731707, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.6585365853658537, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.6585365853658537, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.7073170731707317, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.6585365853658537, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.6585365853658537, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.6585365853658537, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.6829268292682927, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.7317073170731707, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.6829268292682927, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.7317073170731707, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.6341463414634146, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.6341463414634146, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.6585365853658537, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.6829268292682927, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.6585365853658537, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.7317073170731707, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.7073170731707317, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.7073170731707317, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.6341463414634146, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.7073170731707317, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.6585365853658537, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.7317073170731707, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.7560975609756098, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.7317073170731707, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.7560975609756098, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.7560975609756098, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.7560975609756098, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.7560975609756098, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.7560975609756098, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.5275288092189501, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.6095238095238095, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.6095238095238095, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.6095238095238095, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.6095238095238095, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.5886287625418061, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.569327731092437, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.5886287625418061, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.5119047619047619, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.5119047619047619, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.4225352112676056, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.4225352112676056, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.39705882352941174, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.4564393939393939, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.603225806451613, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.5651515151515152, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.5651515151515152, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.5651515151515152, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.5839188134270101, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.6232247284878863, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.5839188134270101, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.6479313036690086, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.48621553884711777, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.48621553884711777, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.5370967741935484, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.5839188134270101, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.5017361111111112, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.6479313036690086, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.5729166666666666, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.603225806451613, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.48621553884711777, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.4831932773109243, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.4564393939393939, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.5512437810945273, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.4305555555555556, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.5918552036199095, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.4305555555555556, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.4305555555555556, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.4305555555555556, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.4305555555555556, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.4305555555555556, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.5, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.5, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.5, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.5, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.5, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.5, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.5, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.5, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.55, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.6, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.6, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.6, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.6, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.5838709677419355, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.567741935483871, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.5838709677419355, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.5338709677419355, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.5338709677419355, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.4838709677419355, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.4838709677419355, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.43548387096774194, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.4693548387096774, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.603225806451613, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.5709677419354839, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.5709677419354839, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.5709677419354839, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.5870967741935484, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.6193548387096774, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.5870967741935484, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.6532258064516129, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.48709677419354835, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.48709677419354835, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.5370967741935484, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.5870967741935484, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.5032258064516129, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.6532258064516129, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.5693548387096774, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.603225806451613, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.48709677419354835, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.5016129032258064, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.4693548387096774, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.5516129032258065, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.5, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.5854838709677419, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.5, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.5, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.5, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.5, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.5, "id_best": 29, "lr_best": 0.0006899999999999999, "wd_best": 0.05, "train/loss_best": 0.0009267103672027588, "validation/loss_best": 2.3179829120635986, "validation/acc_best": 0.7317073170731707, "validation/f1_best": 0.6479313036690086, "validation/bacc_best": 0.6532258064516129} +{"epoch": 7, "train/lr": 0.00027969249556793234, "train/loss": 0.26334647964686153, "train/grad": 0.15263787472620607, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.4995477294921875, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.4941033935546875, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.4859027099609375, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.47822021484375, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.471343994140625, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.4625, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.4533538818359375, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.444119873046875, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.4331097412109375, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.4226751708984375, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.4135101318359375, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.40161376953125, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.3917594528198242, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.3789017105102539, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.3680119514465332, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.3588279342651367, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.3481737565994263, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.3331497836112976, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.30793570041656493, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.2731828552484512, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.21965030804276467, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.16356879338622093, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.09391658559441567, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.03369816869497299, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.009607900381088257, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.003724664747714996, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.0021920865774154663, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0012688934803009033, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0007820577919483185, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0005077916383743286, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.00024457097053527834, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.0001972918212413788, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.00018112361431121826, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.00010209396481513977, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.00013690873980522157, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.00012146309018135071, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.00010472640395164489, "train/loss_037_lr8.3e+00_wd1.0e+00": 9.842634201049804e-05, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.00011002764105796814, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.0001015414297580719, "train/loss_040_lr1.4e+01_wd1.0e+00": 4.362642765045166e-05, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.005034250319004059, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.69140625, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.00020321562886238098, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.69140625, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.69140625, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.69140625, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.69140625, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.69140625, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.027364880789536982, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.027310978551395238, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.027262556196656077, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.027223603092133997, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.02720037112245336, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.027182424748316406, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.02718911722302437, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.027230536034330725, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.027350954804569484, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.027567455002572388, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.02786127959378064, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.028379290679004042, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.028898976708296685, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.029700389963109045, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.03036754884524271, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.03104306714143604, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.03228247093735263, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.0337161339004524, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.03450282744131982, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.03447557367151603, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.03372660416644067, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.0313947559625376, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.023204070085193963, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.011142720128118526, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0036164320065290665, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0014377741093630902, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0008427493124327157, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0005124603703370667, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.00029774503494991224, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.00018823544334736653, "train/grad_030_lr2.7e+00_wd1.0e+00": 9.633644455334434e-05, "train/grad_031_lr3.1e+00_wd1.0e+00": 7.433829546243942e-05, "train/grad_032_lr3.7e+00_wd1.0e+00": 6.199996643317718e-05, "train/grad_033_lr4.3e+00_wd1.0e+00": 4.5381000630868585e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 4.999802232305228e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 4.6225998587487994e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 3.8596541970719044e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 3.519018751831027e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 3.770049017475685e-05, "train/grad_039_lr1.2e+01_wd1.0e+00": 4.0388766676642264e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 3.910325803031226e-05, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.009548884011351426, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.00010948056010107621, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.5423792004585266, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.5394057035446167, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.5343758463859558, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.529840886592865, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.5257393717765808, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.5206781625747681, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.5156102776527405, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.51090008020401, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.5063811540603638, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.5033073425292969, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.5021438598632812, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.5024834871292114, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.5055054426193237, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.5146077871322632, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.5271122455596924, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.5418716073036194, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.5616244077682495, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.5903550982475281, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.646784782409668, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.7187491655349731, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.8391167521476746, "validation/loss_021_lr6.1e-01_wd1.0e+00": 1.0130705833435059, "validation/loss_022_lr7.2e-01_wd1.0e+00": 1.2842636108398438, "validation/loss_023_lr8.5e-01_wd1.0e+00": 1.5783350467681885, "validation/loss_024_lr1.0e+00_wd1.0e+00": 1.8273601531982422, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.0030105113983154, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.142591953277588, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.251744508743286, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.370479106903076, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.4036929607391357, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.5826826095581055, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.6026713848114014, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.4426751136779785, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.892016887664795, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.6710455417633057, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.0597596168518066, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.372171401977539, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.315178394317627, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.8120720386505127, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.471628189086914, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.4513907432556152, "validation/loss_041_lr1.6e+01_wd1.0e+00": 8.865138053894043, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.718125581741333, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.6931472420692444, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.8048780487804879, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.8048780487804879, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.8048780487804879, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.7804878048780488, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.7560975609756098, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.7560975609756098, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.7317073170731707, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.7317073170731707, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.7073170731707317, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.7073170731707317, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.7073170731707317, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.6585365853658537, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.6585365853658537, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.6585365853658537, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.6585365853658537, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.6585365853658537, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.6829268292682927, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.6585365853658537, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.6829268292682927, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.6829268292682927, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.7317073170731707, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.6829268292682927, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.7317073170731707, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.6341463414634146, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.6341463414634146, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.6585365853658537, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.6585365853658537, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.6585365853658537, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.7317073170731707, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.7073170731707317, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.7073170731707317, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.6341463414634146, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.7073170731707317, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.6585365853658537, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.7317073170731707, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.7560975609756098, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.7317073170731707, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.7560975609756098, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.7560975609756098, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.7560975609756098, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.7560975609756098, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.7560975609756098, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.6095238095238095, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.6095238095238095, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.6095238095238095, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.5886287625418061, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.569327731092437, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.569327731092437, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.5918552036199095, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.5918552036199095, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.5729166666666666, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.5729166666666666, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.5729166666666666, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.5651515151515152, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.5876436781609196, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.5876436781609196, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.5651515151515152, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.5651515151515152, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.5839188134270101, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.5651515151515152, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.5839188134270101, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.5839188134270101, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.6232247284878863, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.5839188134270101, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.6479313036690086, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.48621553884711777, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.48621553884711777, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.5370967741935484, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.5370967741935484, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.5017361111111112, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.6479313036690086, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.5729166666666666, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.603225806451613, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.48621553884711777, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.4831932773109243, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.4564393939393939, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.6232247284878863, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.4305555555555556, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.5918552036199095, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.4305555555555556, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.4305555555555556, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.4305555555555556, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.4305555555555556, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.4305555555555556, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.5, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.5, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.5, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.5, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.5, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.5, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.5, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.6, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.6, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.6, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.5838709677419355, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.567741935483871, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.567741935483871, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.5854838709677419, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.5854838709677419, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.5693548387096774, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.5693548387096774, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.5693548387096774, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.5709677419354839, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.6048387096774194, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.6048387096774194, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.5709677419354839, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.5709677419354839, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.5870967741935484, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.5709677419354839, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.5870967741935484, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.5870967741935484, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.6193548387096774, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.5870967741935484, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.6532258064516129, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.48709677419354835, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.48709677419354835, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.5370967741935484, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.5370967741935484, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.5032258064516129, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.6532258064516129, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.5693548387096774, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.603225806451613, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.48709677419354835, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.5016129032258064, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.4693548387096774, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.6193548387096774, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.5, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.5854838709677419, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.5, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.5, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.5, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.5, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.5, "id_best": 29, "lr_best": 0.0006899999999999999, "wd_best": 0.05, "train/loss_best": 0.0005077916383743286, "validation/loss_best": 2.4036929607391357, "validation/acc_best": 0.7317073170731707, "validation/f1_best": 0.6479313036690086, "validation/bacc_best": 0.6532258064516129} +{"epoch": 8, "train/lr": 0.0002612959497061927, "train/loss": 0.25060004003345965, "train/grad": 0.16027330826967956, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.490616455078125, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.485450439453125, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.4775439453125, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.4702392578125, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.46349365234375, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.45492095947265626, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.44605712890625, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.4369207763671875, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.4260148620605469, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.41527862548828126, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.40569290161132815, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.3923398208618164, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.38082744598388674, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.3654958724975586, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.35180403709411623, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.33874600410461425, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.32076537132263183, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.2923737502098083, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.24736753597855568, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.19914537966251372, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.13950470864772796, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.07952457875013351, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.032148414999246595, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.009127915799617768, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.003758545219898224, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.0017885930836200714, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.00115048810839653, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0007592593133449554, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.00044326171278953554, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0003029096126556396, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.000168771892786026, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.00013095349073410033, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.00012063562870025635, "train/loss_033_lr4.3e+00_wd1.0e+00": 8.439958095550537e-05, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.00010491028428077698, "train/loss_035_lr6.0e+00_wd1.0e+00": 9.558990597724915e-05, "train/loss_036_lr7.1e+00_wd1.0e+00": 8.064299821853637e-05, "train/loss_037_lr8.3e+00_wd1.0e+00": 7.669523358345032e-05, "train/loss_038_lr9.8e+00_wd1.0e+00": 8.002281188964843e-05, "train/loss_039_lr1.2e+01_wd1.0e+00": 9.03920829296112e-05, "train/loss_040_lr1.4e+01_wd1.0e+00": 5.5855363607406614e-05, "train/loss_041_lr1.6e+01_wd1.0e+00": 7.312685251235962e-05, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.69140625, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.00019985973834991456, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.69140625, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.69140625, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.69140625, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.69140625, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.69140625, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.03176085304701701, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.03162315356079489, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.031462580573279414, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.0313388382573612, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.03125525292940438, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.031184198155533523, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.03114880289649591, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.03117536476114765, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.03127660748781636, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.03148824763251468, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.03176071424037218, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.0321749289194122, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.03264328919816762, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.033650201614946126, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.03474479535594582, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.035634775042999535, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.03629949355963617, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.036244822200387716, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.03533493250142783, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.03373945389641449, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.029213713555363938, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.02150891938363202, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.011437692489998881, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.003826094032410765, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0015882181077904534, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0007868254290406185, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0005174177264598256, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0003399045417609159, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.00020138586361099443, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.00013415516164059227, "train/grad_030_lr2.7e+00_wd1.0e+00": 7.395967403681425e-05, "train/grad_031_lr3.1e+00_wd1.0e+00": 5.686247167204783e-05, "train/grad_032_lr3.7e+00_wd1.0e+00": 5.087892250003279e-05, "train/grad_033_lr4.3e+00_wd1.0e+00": 3.747547741838275e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 4.250233892662436e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 3.980985524094649e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 3.294635614565777e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 3.101363099403898e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 3.151191373262918e-05, "train/grad_039_lr1.2e+01_wd1.0e+00": 3.615793013523216e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 5.141987664330043e-05, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0003831583694565111, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.00012177860103292914, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.5393972396850586, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.5357868671417236, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.5304960012435913, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.5257152915000916, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.5213015675544739, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.5163738131523132, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.5116984248161316, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.5080874562263489, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.505143404006958, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.5051342844963074, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.5073649287223816, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.5151919722557068, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.5268136262893677, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.5408555269241333, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.54827481508255, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.557947039604187, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.5835543274879456, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.6351622343063354, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.7201328873634338, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.8287003040313721, "validation/loss_020_lr5.2e-01_wd1.0e+00": 1.0251123905181885, "validation/loss_021_lr6.1e-01_wd1.0e+00": 1.295677900314331, "validation/loss_022_lr7.2e-01_wd1.0e+00": 1.5839130878448486, "validation/loss_023_lr8.5e-01_wd1.0e+00": 1.809255838394165, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.0041117668151855, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.143956422805786, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.271463632583618, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.3560798168182373, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.4657368659973145, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.4791347980499268, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.62644624710083, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.6409571170806885, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.485633373260498, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.892690420150757, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.7039361000061035, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.0837137699127197, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.3787894248962402, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.330508232116699, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.818751335144043, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.4428224563598633, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.1915974617004395, "validation/loss_041_lr1.6e+01_wd1.0e+00": 9.587221145629883, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.545197010040283, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.6931472420692444, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.8048780487804879, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.8048780487804879, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.8048780487804879, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.8048780487804879, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.7804878048780488, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.7804878048780488, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.7804878048780488, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.7804878048780488, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.7560975609756098, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.7317073170731707, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.7073170731707317, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.6829268292682927, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.6585365853658537, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.6341463414634146, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.6829268292682927, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.6829268292682927, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.6829268292682927, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.6829268292682927, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.7073170731707317, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.6829268292682927, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.6829268292682927, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.7073170731707317, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.6829268292682927, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.7317073170731707, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.6341463414634146, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.6341463414634146, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.6585365853658537, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.6585365853658537, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.6829268292682927, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.7317073170731707, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.7073170731707317, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.7073170731707317, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.6341463414634146, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.7073170731707317, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.6585365853658537, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.7073170731707317, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.7560975609756098, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.7317073170731707, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.7560975609756098, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.7560975609756098, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.7560975609756098, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.7560975609756098, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.7560975609756098, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.6095238095238095, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.6095238095238095, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.6095238095238095, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.6095238095238095, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.5886287625418061, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.5886287625418061, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.5886287625418061, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.5886287625418061, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.6117424242424243, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.5918552036199095, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.5729166666666666, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.5839188134270101, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.5651515151515152, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.5467943994104643, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.5839188134270101, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.5839188134270101, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.5839188134270101, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.5839188134270101, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.603225806451613, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.5839188134270101, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.5839188134270101, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.603225806451613, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.5839188134270101, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.6479313036690086, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.48621553884711777, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.48621553884711777, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.5370967741935484, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.5370967741935484, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.5547201336675021, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.6479313036690086, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.5729166666666666, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.603225806451613, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.48621553884711777, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.4831932773109243, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.4564393939393939, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.5729166666666666, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.4305555555555556, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.5918552036199095, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.4305555555555556, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.4305555555555556, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.4305555555555556, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.4305555555555556, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.4305555555555556, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.5, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.5, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.5, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.5, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.5, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.5, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.6, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.6, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.6, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.6, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.5838709677419355, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.5838709677419355, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.5838709677419355, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.5838709677419355, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.6016129032258064, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.5854838709677419, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.5693548387096774, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.5870967741935484, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.5709677419354839, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.5548387096774194, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.5870967741935484, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.5870967741935484, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.5870967741935484, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.5870967741935484, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.603225806451613, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.5870967741935484, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.5870967741935484, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.603225806451613, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.5870967741935484, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.6532258064516129, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.48709677419354835, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.48709677419354835, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.5370967741935484, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.5370967741935484, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.5532258064516129, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.6532258064516129, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.5693548387096774, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.603225806451613, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.48709677419354835, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.5016129032258064, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.4693548387096774, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.5693548387096774, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.5, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.5854838709677419, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.5, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.5, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.5, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.5, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.5, "id_best": 29, "lr_best": 0.0006899999999999999, "wd_best": 0.05, "train/loss_best": 0.0003029096126556396, "validation/loss_best": 2.4791347980499268, "validation/acc_best": 0.7317073170731707, "validation/f1_best": 0.6479313036690086, "validation/bacc_best": 0.6532258064516129} +{"epoch": 9, "train/lr": 0.00023803200426111704, "train/loss": 0.24935668397694827, "train/grad": 0.1407682789117098, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.4952276611328125, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.489632568359375, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.4813287353515625, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.47388946533203125, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.46721893310546875, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.458829345703125, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.4501416015625, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.4416206359863281, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.4313241577148437, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.42165618896484375, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.4130369567871094, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.40137069702148437, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.39071035385131836, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.37602863311767576, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.3619571590423584, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.3472977924346924, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.32464524745941165, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.28734643161296847, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.22986554548144342, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.17000633463263512, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.09451045855879783, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.038736788034439085, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.012361256033182144, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.004659628868103028, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.0022161577641963957, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.0012102581560611725, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.0008054313063621521, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.00056025430560112, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0003393703699111938, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.00023841172456741334, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.00015026524662971495, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.00012033075094223023, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.00011315315961837768, "train/loss_033_lr4.3e+00_wd1.0e+00": 7.306069135665894e-05, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.00010046795010566711, "train/loss_035_lr6.0e+00_wd1.0e+00": 9.109482169151307e-05, "train/loss_036_lr7.1e+00_wd1.0e+00": 7.678568363189697e-05, "train/loss_037_lr8.3e+00_wd1.0e+00": 7.303088903427125e-05, "train/loss_038_lr9.8e+00_wd1.0e+00": 7.752358913421632e-05, "train/loss_039_lr1.2e+01_wd1.0e+00": 8.256390690803528e-05, "train/loss_040_lr1.4e+01_wd1.0e+00": 8.941978216171264e-05, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.5000998973846436e-05, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.69140625, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.00020510300993919372, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.69140625, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.69140625, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.69140625, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.69140625, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.69140625, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.028655526351649314, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.028620500213000923, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.028593913270160556, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.02859226244967431, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.028610807105433195, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.028670553090050815, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.02877792010549456, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.02891674644779414, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.029156994710210712, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.029432916827499867, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.02971454508136958, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.03008472374640405, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.030378190325573085, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.030740331853739918, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.030965215708129108, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.031077538272365927, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.03127715681446716, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.031825882906559855, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.03127639389596879, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.02818384617799893, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.020698166020447387, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.01098574606818147, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.004102861928840866, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0017159373989852611, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0008750079284072853, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0005047573718911736, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0003501565119950101, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0002524967895169539, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.00016120474067065515, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.00010862195968002198, "train/grad_030_lr2.7e+00_wd1.0e+00": 5.9715231125210266e-05, "train/grad_031_lr3.1e+00_wd1.0e+00": 4.667769004640831e-05, "train/grad_032_lr3.7e+00_wd1.0e+00": 4.175085046199456e-05, "train/grad_033_lr4.3e+00_wd1.0e+00": 3.3479200728265826e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 3.801299272367942e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 3.393330742369471e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 2.8483419027907077e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 2.6617220477476167e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 2.818350023858329e-05, "train/grad_039_lr1.2e+01_wd1.0e+00": 3.2447201699596915e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 5.9884873474570496e-05, "train/grad_041_lr1.6e+01_wd1.0e+00": 9.343070713415788e-06, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.00011041484753505415, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.5353690981864929, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.5317709445953369, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.5259670615196228, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.5207284092903137, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.5163962841033936, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.5111854076385498, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.5067461729049683, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.5035176873207092, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.501441240310669, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.5017655491828918, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.5035049319267273, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.5080002546310425, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.5155661106109619, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.5332672595977783, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.5550270080566406, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.5817079544067383, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.6260358095169067, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.6938821077346802, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.7988688945770264, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.9452612996101379, "validation/loss_020_lr5.2e-01_wd1.0e+00": 1.2250078916549683, "validation/loss_021_lr6.1e-01_wd1.0e+00": 1.5246591567993164, "validation/loss_022_lr7.2e-01_wd1.0e+00": 1.7830219268798828, "validation/loss_023_lr8.5e-01_wd1.0e+00": 1.9672586917877197, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.1424994468688965, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.2433252334594727, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.357398509979248, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.4248976707458496, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.5228569507598877, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.5155253410339355, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.6603786945343018, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.681245803833008, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.516930103302002, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.8932855129241943, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.732023000717163, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.104919910430908, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.38354754447937, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.3457348346710205, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.8209433555603027, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.440803050994873, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.0048561096191406, "validation/loss_041_lr1.6e+01_wd1.0e+00": 8.558793067932129, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.4691123962402344, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.6931472420692444, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.7804878048780488, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.8048780487804879, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.8048780487804879, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.7804878048780488, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.7560975609756098, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.7804878048780488, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.7560975609756098, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.7560975609756098, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.7560975609756098, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.7560975609756098, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.6829268292682927, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.6829268292682927, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.7073170731707317, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.7073170731707317, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.6829268292682927, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.7073170731707317, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.7073170731707317, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.6829268292682927, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.6829268292682927, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.6829268292682927, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.6829268292682927, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.7073170731707317, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.6829268292682927, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.7317073170731707, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.6341463414634146, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.6341463414634146, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.6585365853658537, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.6585365853658537, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.6829268292682927, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.7317073170731707, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.7317073170731707, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.7073170731707317, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.6585365853658537, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.7073170731707317, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.6585365853658537, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.7073170731707317, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.7560975609756098, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.7317073170731707, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.7560975609756098, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.7560975609756098, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.7560975609756098, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.7560975609756098, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.7560975609756098, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.5275288092189501, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.6095238095238095, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.6095238095238095, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.5886287625418061, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.569327731092437, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.569327731092437, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.569327731092437, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.6328358208955224, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.6117424242424243, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.6117424242424243, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.6117424242424243, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.6117424242424243, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.4696517412935323, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.4696517412935323, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.5729166666666666, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.5729166666666666, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.5547201336675021, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.603225806451613, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.603225806451613, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.5839188134270101, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.5839188134270101, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.5839188134270101, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.5839188134270101, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.603225806451613, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.5839188134270101, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.6479313036690086, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.48621553884711777, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.48621553884711777, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.5370967741935484, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.5370967741935484, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.5547201336675021, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.6479313036690086, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.6232247284878863, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.603225806451613, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.5017361111111112, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.4831932773109243, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.4564393939393939, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.5729166666666666, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.4305555555555556, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.5918552036199095, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.4305555555555556, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.4305555555555556, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.4305555555555556, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.4305555555555556, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.4305555555555556, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.5, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.5, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.5, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.5, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.55, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.6, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.6, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.5838709677419355, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.567741935483871, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.567741935483871, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.567741935483871, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.6177419354838709, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.6016129032258064, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.6016129032258064, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.6016129032258064, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.6016129032258064, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.4854838709677419, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.4854838709677419, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.5693548387096774, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.5693548387096774, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.5532258064516129, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.603225806451613, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.603225806451613, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.5870967741935484, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.5870967741935484, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.5870967741935484, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.5870967741935484, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.603225806451613, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.5870967741935484, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.6532258064516129, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.48709677419354835, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.48709677419354835, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.5370967741935484, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.5370967741935484, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.5532258064516129, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.6532258064516129, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.6193548387096774, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.603225806451613, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.5032258064516129, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.5016129032258064, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.4693548387096774, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.5693548387096774, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.5, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.5854838709677419, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.5, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.5, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.5, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.5, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.5, "id_best": 29, "lr_best": 0.0006899999999999999, "wd_best": 0.05, "train/loss_best": 0.00023841172456741334, "validation/loss_best": 2.5155253410339355, "validation/acc_best": 0.7317073170731707, "validation/f1_best": 0.6479313036690086, "validation/bacc_best": 0.6532258064516129} +{"epoch": 10, "train/lr": 0.00021091808096876188, "train/loss": 0.23277125891298056, "train/grad": 0.14143084084615112, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.4811871337890625, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.4749072265625, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.46552734375, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.45701324462890625, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.44905059814453124, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.43896240234375, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.4284577941894531, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.41774978637695315, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.4051052093505859, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.3929575347900391, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.3818767547607422, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.3661071014404297, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.3512509155273438, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.33023550987243655, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.3106034231185913, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.2904284596443176, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.2579244750738144, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.21107837423682213, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.1563245539367199, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.10510727301239968, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.04979403033852577, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.020226189345121385, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.007288454174995422, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.0030378323793411256, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.0015738740563392638, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.0009036299586296082, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.0006230773031711579, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.00045593366026878355, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.00029153481125831604, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.00021323785185813903, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.00011805966496467591, "train/loss_031_lr3.1e+00_wd1.0e+00": 9.35719907283783e-05, "train/loss_032_lr3.7e+00_wd1.0e+00": 9.563207626342774e-05, "train/loss_033_lr4.3e+00_wd1.0e+00": 7.519021630287171e-05, "train/loss_034_lr5.1e+00_wd1.0e+00": 8.795544505119324e-05, "train/loss_035_lr6.0e+00_wd1.0e+00": 8.195355534553528e-05, "train/loss_036_lr7.1e+00_wd1.0e+00": 6.459236145019532e-05, "train/loss_037_lr8.3e+00_wd1.0e+00": 6.426349282264709e-05, "train/loss_038_lr9.8e+00_wd1.0e+00": 6.54524564743042e-05, "train/loss_039_lr1.2e+01_wd1.0e+00": 7.009178400039672e-05, "train/loss_040_lr1.4e+01_wd1.0e+00": 8.700743317604065e-05, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.0869055986404418e-05, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.69140625, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.00017689019441604614, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.69140625, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.69140625, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.69140625, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.69140625, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.69140625, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.028753163851797582, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.028681393566075714, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.028602950205095113, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.028553747453261166, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.028527628008741885, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.028518833939451725, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.02854093780275434, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.028611782495863734, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.02875716006848961, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.02895852049579844, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.029204671911429614, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.029640204252209514, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.030167292812839152, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.031145981678273527, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.03217161863576621, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.033003606635611506, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.03326138529460877, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.03188817023765296, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.03016107714618556, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.026262202635989523, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.016384427011362276, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.007832719706057105, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.002937683242271305, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.001314048194035422, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0006898673019713897, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.00039888248974421, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.00028261828426366263, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0002046294760384626, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.00012545391962703433, "train/grad_029_lr2.3e+00_wd1.0e+00": 8.552878626687744e-05, "train/grad_030_lr2.7e+00_wd1.0e+00": 4.824187038138916e-05, "train/grad_031_lr3.1e+00_wd1.0e+00": 3.9267659510073827e-05, "train/grad_032_lr3.7e+00_wd1.0e+00": 3.6704955850837e-05, "train/grad_033_lr4.3e+00_wd1.0e+00": 3.0362238801728837e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 3.385261182074828e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 3.0387392787361022e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 2.5748549099944284e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 2.3436949902588822e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 2.4855608929783558e-05, "train/grad_039_lr1.2e+01_wd1.0e+00": 2.957999408181422e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 6.712856906165409e-05, "train/grad_041_lr1.6e+01_wd1.0e+00": 8.382739591786448e-06, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.00010614988263796477, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.5328271389007568, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.5290660858154297, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.523133397102356, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.5179261565208435, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.5136019587516785, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.5091714859008789, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.5053014755249023, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.5026243925094604, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.5013954639434814, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.5017887353897095, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.5041109323501587, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.5107365846633911, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.5194910764694214, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.5359694361686707, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.5558629035949707, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.5831575393676758, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.6419920325279236, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.7376339435577393, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.8916338682174683, "validation/loss_019_lr4.4e-01_wd1.0e+00": 1.08882474899292, "validation/loss_020_lr5.2e-01_wd1.0e+00": 1.4259755611419678, "validation/loss_021_lr6.1e-01_wd1.0e+00": 1.7318496704101562, "validation/loss_022_lr7.2e-01_wd1.0e+00": 1.9374154806137085, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.079643487930298, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.2339916229248047, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.312284469604492, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.417703866958618, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.4831316471099854, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.5673515796661377, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.548959493637085, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.6851117610931396, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.709064483642578, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.5445406436920166, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.8957738876342773, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.752253293991089, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.120582103729248, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.395059585571289, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.3575985431671143, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.83317232131958, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.447396993637085, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.8380141258239746, "validation/loss_041_lr1.6e+01_wd1.0e+00": 7.697149276733398, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.4254603385925293, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.6931472420692444, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.8048780487804879, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.8048780487804879, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.8048780487804879, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.7804878048780488, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.7804878048780488, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.7560975609756098, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.7560975609756098, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.7317073170731707, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.7317073170731707, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.7073170731707317, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.7560975609756098, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.7317073170731707, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.7073170731707317, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.7073170731707317, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.6829268292682927, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.7073170731707317, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.7073170731707317, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.7073170731707317, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.6829268292682927, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.6829268292682927, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.6829268292682927, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.6829268292682927, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.7073170731707317, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.6829268292682927, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.7317073170731707, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.6341463414634146, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.6341463414634146, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.6585365853658537, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.6585365853658537, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.6829268292682927, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.7317073170731707, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.7317073170731707, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.7073170731707317, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.6585365853658537, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.7073170731707317, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.6585365853658537, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.7073170731707317, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.7560975609756098, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.7317073170731707, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.7560975609756098, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.7560975609756098, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.7560975609756098, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.7560975609756098, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.7560975609756098, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.6095238095238095, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.6095238095238095, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.6095238095238095, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.5886287625418061, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.5886287625418061, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.569327731092437, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.6117424242424243, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.5918552036199095, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.5918552036199095, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.5729166666666666, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.6693548387096775, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.6479313036690086, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.6272727272727273, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.603225806451613, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.5547201336675021, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.603225806451613, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.603225806451613, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.603225806451613, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.5839188134270101, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.5839188134270101, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.5839188134270101, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.5839188134270101, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.603225806451613, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.5839188134270101, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.6479313036690086, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.48621553884711777, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.48621553884711777, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.5370967741935484, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.5370967741935484, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.5547201336675021, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.6479313036690086, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.6232247284878863, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.603225806451613, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.5017361111111112, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.4831932773109243, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.4564393939393939, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.5729166666666666, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.4305555555555556, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.5918552036199095, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.4305555555555556, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.4305555555555556, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.4305555555555556, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.4305555555555556, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.4305555555555556, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.5, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.5, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.5, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.5, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.5, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.6, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.6, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.6, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.5838709677419355, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.5838709677419355, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.567741935483871, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.6016129032258064, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.5854838709677419, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.5854838709677419, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.5693548387096774, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.6693548387096775, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.6532258064516129, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.6370967741935484, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.603225806451613, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.5532258064516129, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.603225806451613, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.603225806451613, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.603225806451613, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.5870967741935484, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.5870967741935484, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.5870967741935484, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.5870967741935484, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.603225806451613, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.5870967741935484, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.6532258064516129, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.48709677419354835, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.48709677419354835, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.5370967741935484, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.5370967741935484, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.5532258064516129, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.6532258064516129, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.6193548387096774, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.603225806451613, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.5032258064516129, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.5016129032258064, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.4693548387096774, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.5693548387096774, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.5, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.5854838709677419, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.5, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.5, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.5, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.5, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.5, "id_best": 15, "lr_best": 6.9e-05, "wd_best": 0.05, "train/loss_best": 0.2904284596443176, "validation/loss_best": 0.5831575393676758, "validation/acc_best": 0.7560975609756098, "validation/f1_best": 0.6693548387096775, "validation/bacc_best": 0.6693548387096775} +{"epoch": 11, "train/lr": 0.00018113997589164516, "train/loss": 0.22624137740582229, "train/grad": 0.13490496966987847, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.4631573486328125, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.4573309326171875, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.44883819580078127, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.44125457763671877, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.43413055419921875, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.4252783203125, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.41609298706054687, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.40679840087890623, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.3955726623535156, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.3849846649169922, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.37517719268798827, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.3612850379943848, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.3483133888244629, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.32875767707824705, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.30887952327728274, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.2857797944545746, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.2446258246898651, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.18172382727265357, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.11456858113408089, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.06625342905521393, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.027345714569091798, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.010808037519454956, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.004364304095506668, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.0020152536034584046, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.0011032851040363313, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.00066480353474617, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.0004792550206184387, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0003647300601005554, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.00023050695657730102, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.00016749635338783264, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.00010538697242736816, "train/loss_031_lr3.1e+00_wd1.0e+00": 8.876562118530273e-05, "train/loss_032_lr3.7e+00_wd1.0e+00": 8.414790034294128e-05, "train/loss_033_lr4.3e+00_wd1.0e+00": 7.024779915809631e-05, "train/loss_034_lr5.1e+00_wd1.0e+00": 7.86551833152771e-05, "train/loss_035_lr6.0e+00_wd1.0e+00": 7.511988282203674e-05, "train/loss_036_lr7.1e+00_wd1.0e+00": 6.208479404449462e-05, "train/loss_037_lr8.3e+00_wd1.0e+00": 5.9786438941955564e-05, "train/loss_038_lr9.8e+00_wd1.0e+00": 6.326571106910705e-05, "train/loss_039_lr1.2e+01_wd1.0e+00": 7.235050201416015e-05, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.00011510297656059266, "train/loss_041_lr1.6e+01_wd1.0e+00": 8.324384689331054e-06, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.69140625, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.0001607424020767212, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.69140625, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.69140625, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.69140625, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.69140625, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.69140625, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.029395122500136494, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.029348893631249665, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.02930489796679467, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.029276826549321414, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.02926568160764873, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.029262372464872895, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.029275979220401496, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.02930754599161446, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.02938075045123696, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.02947329842019826, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.029602264291606843, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.029823773293755948, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.03011244211345911, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.030571436514146625, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.030993105752859264, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.031264773139264436, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.031152629328425975, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.029394377111457287, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.025639439704827963, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.019584313298109918, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.010192927629104816, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.004445675288734492, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.001887722150349873, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.000898013165606244, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0005085323221464932, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0003100449834892061, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0002261010463371349, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.00017129199883129332, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0001072763804859278, "train/grad_029_lr2.3e+00_wd1.0e+00": 7.395554753657052e-05, "train/grad_030_lr2.7e+00_wd1.0e+00": 4.2870131605923236e-05, "train/grad_031_lr3.1e+00_wd1.0e+00": 3.413967257529294e-05, "train/grad_032_lr3.7e+00_wd1.0e+00": 3.264850611230941e-05, "train/grad_033_lr4.3e+00_wd1.0e+00": 2.8024660326764206e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 3.1566048699005476e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 2.7533436619933126e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 2.312358708309148e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 2.1627103189985065e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 2.3003840749424852e-05, "train/grad_039_lr1.2e+01_wd1.0e+00": 2.7510757388142792e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 7.228756879852582e-05, "train/grad_041_lr1.6e+01_wd1.0e+00": 1.0944783799869268e-05, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0, "train/grad_043_lr2.2e+01_wd1.0e+00": 9.461845555392756e-05, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.530662477016449, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.5265858173370361, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.5205023288726807, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.5153275728225708, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.5110959410667419, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.5065813064575195, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.5029270052909851, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.500799298286438, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.500563383102417, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.5029391050338745, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.5070556402206421, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.5158827900886536, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.5266913771629333, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.5467939376831055, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.5735877156257629, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.6086594462394714, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.6818661093711853, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.8030869960784912, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.9896177053451538, "validation/loss_019_lr4.4e-01_wd1.0e+00": 1.2211260795593262, "validation/loss_020_lr5.2e-01_wd1.0e+00": 1.5733656883239746, "validation/loss_021_lr6.1e-01_wd1.0e+00": 1.8571453094482422, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.041135787963867, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.158599853515625, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.3072097301483154, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.372859001159668, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.473442316055298, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.5323548316955566, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.60976243019104, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.5809245109558105, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.7108757495880127, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.732206106185913, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.5691211223602295, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.8972856998443604, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.7762789726257324, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.1390631198883057, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.407477617263794, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.378751039505005, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.847081184387207, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.4456470012664795, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.7158334255218506, "validation/loss_041_lr1.6e+01_wd1.0e+00": 6.972153186798096, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.4072937965393066, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.6931472420692444, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.8048780487804879, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.8048780487804879, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.8048780487804879, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.7804878048780488, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.7560975609756098, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.7317073170731707, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.7317073170731707, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.7317073170731707, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.7317073170731707, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.7317073170731707, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.6829268292682927, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.7073170731707317, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.7073170731707317, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.7073170731707317, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.6829268292682927, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.7073170731707317, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.7073170731707317, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.6829268292682927, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.6829268292682927, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.6829268292682927, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.6829268292682927, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.7073170731707317, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.6829268292682927, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.7317073170731707, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.6341463414634146, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.6341463414634146, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.6585365853658537, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.6585365853658537, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.6829268292682927, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.7317073170731707, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.7317073170731707, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.7073170731707317, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.6585365853658537, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.6829268292682927, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.6585365853658537, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.7073170731707317, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.7560975609756098, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.7317073170731707, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.7560975609756098, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.7560975609756098, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.7560975609756098, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.7560975609756098, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.7560975609756098, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.6095238095238095, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.6095238095238095, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.6095238095238095, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.5886287625418061, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.569327731092437, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.569327731092437, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.569327731092437, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.5918552036199095, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.5918552036199095, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.5918552036199095, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.5918552036199095, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.5918552036199095, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.5176470588235295, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.5729166666666666, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.5729166666666666, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.5729166666666666, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.5547201336675021, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.603225806451613, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.603225806451613, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.5839188134270101, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.5839188134270101, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.5839188134270101, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.5839188134270101, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.603225806451613, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.5839188134270101, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.6479313036690086, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.48621553884711777, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.48621553884711777, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.5370967741935484, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.5370967741935484, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.5547201336675021, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.6479313036690086, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.6232247284878863, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.603225806451613, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.5017361111111112, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.4696517412935323, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.4564393939393939, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.5729166666666666, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.4305555555555556, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.5918552036199095, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.4305555555555556, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.4305555555555556, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.4305555555555556, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.4305555555555556, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.4305555555555556, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.5, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.5, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.5, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.5, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.6, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.6, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.6, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.5838709677419355, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.567741935483871, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.567741935483871, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.567741935483871, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.5854838709677419, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.5854838709677419, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.5854838709677419, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.5854838709677419, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.5854838709677419, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.5193548387096775, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.5693548387096774, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.5693548387096774, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.5693548387096774, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.5532258064516129, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.603225806451613, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.603225806451613, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.5870967741935484, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.5870967741935484, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.5870967741935484, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.5870967741935484, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.603225806451613, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.5870967741935484, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.6532258064516129, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.48709677419354835, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.48709677419354835, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.5370967741935484, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.5370967741935484, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.5532258064516129, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.6532258064516129, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.6193548387096774, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.603225806451613, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.5032258064516129, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.4854838709677419, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.4693548387096774, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.5693548387096774, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.5, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.5854838709677419, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.5, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.5, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.5, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.5, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.5, "id_best": 29, "lr_best": 0.0006899999999999999, "wd_best": 0.05, "train/loss_best": 0.00016749635338783264, "validation/loss_best": 2.5809245109558105, "validation/acc_best": 0.7317073170731707, "validation/f1_best": 0.6479313036690086, "validation/bacc_best": 0.6532258064516129} +{"epoch": 12, "train/lr": 0.0001499999999999999, "train/loss": 0.23293486800044774, "train/grad": 0.13695627415552736, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.48603515625, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.48020263671875, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.4712530517578125, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.46318145751953127, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.45575531005859377, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.446279296875, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.436304931640625, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.42631820678710936, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.4142543029785156, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.4026449584960938, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.39238914489746096, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.37793243408203125, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.3646378517150879, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.3450504207611084, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.3243843030929565, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.2994911026954651, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.2562862250208855, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.19378046691417694, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.12271246016025543, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.0660331705212593, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.022402731925249098, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.008590086698532104, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.0036839589476585386, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.0017959652841091156, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.0010432857275009155, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.0006499575078487397, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.0004738853871822357, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.00036668702960014344, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.00023876607418060302, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.00017571240663528443, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.00010283336043357849, "train/loss_031_lr3.1e+00_wd1.0e+00": 8.175820112228393e-05, "train/loss_032_lr3.7e+00_wd1.0e+00": 8.269935846328735e-05, "train/loss_033_lr4.3e+00_wd1.0e+00": 6.500229239463806e-05, "train/loss_034_lr5.1e+00_wd1.0e+00": 8.196249604225158e-05, "train/loss_035_lr6.0e+00_wd1.0e+00": 7.240816950798034e-05, "train/loss_036_lr7.1e+00_wd1.0e+00": 6.084278225898743e-05, "train/loss_037_lr8.3e+00_wd1.0e+00": 5.758747458457947e-05, "train/loss_038_lr9.8e+00_wd1.0e+00": 6.213620305061341e-05, "train/loss_039_lr1.2e+01_wd1.0e+00": 6.657987833023072e-05, "train/loss_040_lr1.4e+01_wd1.0e+00": 9.913578629493714e-05, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.1227726936340332e-05, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.69140625, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.00017918780446052551, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.69140625, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.69140625, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.69140625, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.69140625, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.69140625, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.02828980209538713, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.028251571299042554, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.02822880754712969, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.02824477379443124, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.028302118382416665, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.028400650636758656, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.028576370065566153, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.02880117642460391, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.029137985354755074, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.02951048329938203, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.029900347362272442, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.030467543872073292, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.031052163229323925, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.031909218439832326, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.032659249869175254, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.033204310873989014, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.033480475218966604, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.0321820236579515, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.026990771293640137, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.018870101256179623, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.007988369290833361, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.0031903411257371774, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0014155438324087298, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0007101481709105428, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0004133926349459216, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0002582057311337849, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.00018949897596030497, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.00014500932195915083, "train/grad_028_lr1.9e+00_wd1.0e+00": 9.12105128463736e-05, "train/grad_029_lr2.3e+00_wd1.0e+00": 6.302124293597444e-05, "train/grad_030_lr2.7e+00_wd1.0e+00": 3.756189822752276e-05, "train/grad_031_lr3.1e+00_wd1.0e+00": 3.03755458003252e-05, "train/grad_032_lr3.7e+00_wd1.0e+00": 2.9440568994232308e-05, "train/grad_033_lr4.3e+00_wd1.0e+00": 2.628562561767467e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 2.8482705141641417e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 2.5010311645701222e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 2.103600459236077e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 1.948576915310696e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 2.1085642041498433e-05, "train/grad_039_lr1.2e+01_wd1.0e+00": 2.4328717299795243e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 6.958631349515798e-05, "train/grad_041_lr1.6e+01_wd1.0e+00": 1.5954338351943275e-05, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0, "train/grad_043_lr2.2e+01_wd1.0e+00": 8.552563342391295e-05, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.5291513800621033, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.5250893831253052, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.5191829204559326, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.5139455795288086, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.5102056264877319, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.5058474540710449, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.5031605958938599, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.5022419095039368, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.5037215352058411, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.5080332159996033, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.513751745223999, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.5245610475540161, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.5376589894294739, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.5602796077728271, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.5899748206138611, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.6332274079322815, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.7241252660751343, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.8721821308135986, "validation/loss_018_lr3.8e-01_wd1.0e+00": 1.099353551864624, "validation/loss_019_lr4.4e-01_wd1.0e+00": 1.3567646741867065, "validation/loss_020_lr5.2e-01_wd1.0e+00": 1.698127031326294, "validation/loss_021_lr6.1e-01_wd1.0e+00": 1.9679691791534424, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.123345375061035, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.221046209335327, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.3654797077178955, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.4202520847320557, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.516618013381958, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.571448802947998, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.641836166381836, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.6065614223480225, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.729081630706787, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.7532284259796143, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.5874857902526855, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.900477409362793, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.799114227294922, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.1532034873962402, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.4149529933929443, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.3928496837615967, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.862828016281128, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.45157527923584, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.631019353866577, "validation/loss_041_lr1.6e+01_wd1.0e+00": 6.422966003417969, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.3983798027038574, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.6931472420692444, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.8048780487804879, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.8048780487804879, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.8048780487804879, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.7804878048780488, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.7804878048780488, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.7560975609756098, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.7317073170731707, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.7560975609756098, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.7317073170731707, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.7317073170731707, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.7073170731707317, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.7073170731707317, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.6829268292682927, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.6585365853658537, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.6829268292682927, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.7073170731707317, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.7073170731707317, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.7073170731707317, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.6829268292682927, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.6829268292682927, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.6829268292682927, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.6829268292682927, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.7073170731707317, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.6829268292682927, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.7317073170731707, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.6585365853658537, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.6341463414634146, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.6585365853658537, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.6585365853658537, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.6829268292682927, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.7317073170731707, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.7560975609756098, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.7073170731707317, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.6585365853658537, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.6829268292682927, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.6585365853658537, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.7073170731707317, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.7560975609756098, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.7317073170731707, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.7560975609756098, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.7560975609756098, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.7560975609756098, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.7560975609756098, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.7560975609756098, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.6095238095238095, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.6095238095238095, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.6095238095238095, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.5886287625418061, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.5886287625418061, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.569327731092437, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.569327731092437, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.5512437810945273, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.6117424242424243, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.5918552036199095, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.5918552036199095, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.5729166666666666, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.5729166666666666, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.5547201336675021, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.5017361111111112, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.5176470588235295, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.603225806451613, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.603225806451613, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.603225806451613, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.5839188134270101, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.5839188134270101, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.5839188134270101, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.5839188134270101, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.603225806451613, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.5839188134270101, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.6479313036690086, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.5370967741935484, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.48621553884711777, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.5370967741935484, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.5370967741935484, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.5547201336675021, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.6479313036690086, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.6693548387096775, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.603225806451613, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.5017361111111112, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.4696517412935323, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.4564393939393939, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.5729166666666666, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.4305555555555556, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.5918552036199095, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.4305555555555556, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.4305555555555556, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.4305555555555556, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.4305555555555556, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.4305555555555556, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.5, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.5, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.5, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.5, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.6, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.6, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.6, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.5838709677419355, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.5838709677419355, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.567741935483871, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.567741935483871, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.5516129032258065, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.6016129032258064, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.5854838709677419, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.5854838709677419, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.5693548387096774, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.5693548387096774, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.5532258064516129, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.5032258064516129, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.5193548387096775, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.603225806451613, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.603225806451613, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.603225806451613, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.5870967741935484, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.5870967741935484, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.5870967741935484, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.5870967741935484, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.603225806451613, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.5870967741935484, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.6532258064516129, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.5370967741935484, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.48709677419354835, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.5370967741935484, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.5370967741935484, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.5532258064516129, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.6532258064516129, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.6693548387096775, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.603225806451613, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.5032258064516129, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.4854838709677419, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.4693548387096774, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.5693548387096774, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.5, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.5854838709677419, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.5, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.5, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.5, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.5, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.5, "id_best": 36, "lr_best": 0.0021299999999999995, "wd_best": 0.05, "train/loss_best": 6.084278225898743e-05, "validation/loss_best": 2.4149529933929443, "validation/acc_best": 0.7560975609756098, "validation/f1_best": 0.6693548387096775, "validation/bacc_best": 0.6693548387096775} +{"epoch": 13, "train/lr": 0.00011886002410835478, "train/loss": 0.22067260168492794, "train/grad": 0.1399815903045237, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.4681219482421875, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.4619317626953125, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.452562255859375, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.44396636962890623, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.4359014892578125, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.4256170654296875, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.41471435546875, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.4036468505859375, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.3903472900390625, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.3775604629516602, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.36604618072509765, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.3500639343261719, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.33538601875305174, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.3140862035751343, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.29043652534484865, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.25879682421684264, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.20197358280420302, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.13411372527480125, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.07501061707735061, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.03779461458325386, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.013572788089513779, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.005662402510643006, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.0025688621401786806, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.001312754601240158, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.0008051325380802154, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.0005134141445159912, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.0003817556798458099, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.00030973851680755616, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.00020384833216667176, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.00015204861760139465, "train/loss_030_lr2.7e+00_wd1.0e+00": 9.268641471862793e-05, "train/loss_031_lr3.1e+00_wd1.0e+00": 7.69573450088501e-05, "train/loss_032_lr3.7e+00_wd1.0e+00": 7.724121212959289e-05, "train/loss_033_lr4.3e+00_wd1.0e+00": 5.9743374586105346e-05, "train/loss_034_lr5.1e+00_wd1.0e+00": 7.443845272064208e-05, "train/loss_035_lr6.0e+00_wd1.0e+00": 6.723791360855103e-05, "train/loss_036_lr7.1e+00_wd1.0e+00": 4.9986988306045535e-05, "train/loss_037_lr8.3e+00_wd1.0e+00": 4.929766058921814e-05, "train/loss_038_lr9.8e+00_wd1.0e+00": 5.4544657468795774e-05, "train/loss_039_lr1.2e+01_wd1.0e+00": 5.8601796627044675e-05, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.00012362316250801085, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.5010237693786622e-05, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.69140625, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.0001600387692451477, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.69140625, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.69140625, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.69140625, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.69140625, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.69140625, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.030555209699086844, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.03048948851414025, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.03043074885616079, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.030392151256091893, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.030395994742866604, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.030423146220855415, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.03050786760635674, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.030622820479329675, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.03085776220774278, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.03113057532114908, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.03142292325384915, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.03188057306222618, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.0322984797693789, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.032861007796600464, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.03339369454188272, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.03352661431767046, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.03252177524380386, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.029235776083078237, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.02137333476450294, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.012603632675018161, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.0051675133849494155, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.0023167241958435623, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0011121087063656887, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0005884309099201346, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.00035795042899735565, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.00022676756549117272, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.00016883966502973636, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0001310128781278763, "train/grad_028_lr1.9e+00_wd1.0e+00": 8.570041499751824e-05, "train/grad_029_lr2.3e+00_wd1.0e+00": 5.956993622248774e-05, "train/grad_030_lr2.7e+00_wd1.0e+00": 3.554754527613113e-05, "train/grad_031_lr3.1e+00_wd1.0e+00": 2.870641378194705e-05, "train/grad_032_lr3.7e+00_wd1.0e+00": 2.759543497404593e-05, "train/grad_033_lr4.3e+00_wd1.0e+00": 2.421789328622026e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 2.794620056874919e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 2.3773680696876907e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 1.966489920391723e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 1.8457182504789672e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 1.9480727027030297e-05, "train/grad_039_lr1.2e+01_wd1.0e+00": 2.3139154450291244e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 6.846647909085846e-05, "train/grad_041_lr1.6e+01_wd1.0e+00": 2.019675416613283e-05, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0, "train/grad_043_lr2.2e+01_wd1.0e+00": 8.104966985683859e-05, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.5278104543685913, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.523475706577301, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.5176312327384949, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.5128504037857056, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.5089820623397827, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.5052695274353027, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.502716064453125, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.5022805333137512, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.504618763923645, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.5092278718948364, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.5156810283660889, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.527991771697998, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.5420470833778381, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.5670474171638489, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.5997845530509949, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.6494067311286926, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.7501238584518433, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.9078493714332581, "validation/loss_018_lr3.8e-01_wd1.0e+00": 1.1528152227401733, "validation/loss_019_lr4.4e-01_wd1.0e+00": 1.4321948289871216, "validation/loss_020_lr5.2e-01_wd1.0e+00": 1.783251166343689, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.042234420776367, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.180173635482788, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.2683939933776855, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.408585786819458, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.4547512531280518, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.54892897605896, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.59720516204834, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.6605801582336426, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.6203455924987793, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.744758367538452, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.7735695838928223, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.609022617340088, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.906113624572754, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.8174469470977783, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.1719601154327393, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.428474187850952, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.404820203781128, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.872926712036133, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.4596400260925293, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.584474802017212, "validation/loss_041_lr1.6e+01_wd1.0e+00": 6.015454292297363, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.3902127742767334, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.6931472420692444, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.8048780487804879, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.8048780487804879, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.8048780487804879, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.7804878048780488, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.7804878048780488, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.7560975609756098, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.7560975609756098, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.7317073170731707, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.7317073170731707, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.7073170731707317, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.7073170731707317, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.7073170731707317, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.6829268292682927, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.6829268292682927, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.7073170731707317, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.7073170731707317, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.7073170731707317, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.7073170731707317, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.6829268292682927, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.6829268292682927, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.6829268292682927, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.6829268292682927, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.7073170731707317, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.6829268292682927, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.7317073170731707, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.6585365853658537, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.6341463414634146, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.6585365853658537, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.6585365853658537, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.6829268292682927, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.7317073170731707, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.7804878048780488, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.7073170731707317, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.6585365853658537, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.6829268292682927, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.6585365853658537, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.7073170731707317, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.7560975609756098, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.7317073170731707, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.7560975609756098, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.7560975609756098, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.7560975609756098, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.7560975609756098, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.7560975609756098, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.6095238095238095, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.6095238095238095, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.6095238095238095, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.5886287625418061, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.5886287625418061, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.569327731092437, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.569327731092437, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.6117424242424243, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.5918552036199095, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.5918552036199095, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.5729166666666666, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.5729166666666666, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.603225806451613, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.5547201336675021, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.5547201336675021, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.5729166666666666, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.603225806451613, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.603225806451613, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.603225806451613, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.5839188134270101, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.5839188134270101, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.5839188134270101, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.5839188134270101, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.603225806451613, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.5839188134270101, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.6479313036690086, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.5370967741935484, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.48621553884711777, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.5370967741935484, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.5370967741935484, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.5547201336675021, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.6479313036690086, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.6917293233082706, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.603225806451613, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.5017361111111112, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.4696517412935323, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.4564393939393939, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.5729166666666666, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.4305555555555556, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.5918552036199095, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.4305555555555556, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.4305555555555556, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.4305555555555556, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.4305555555555556, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.4305555555555556, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.5, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.5, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.5, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.5, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.6, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.6, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.6, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.5838709677419355, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.5838709677419355, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.567741935483871, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.567741935483871, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.6016129032258064, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.5854838709677419, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.5854838709677419, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.5693548387096774, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.5693548387096774, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.603225806451613, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.5532258064516129, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.5532258064516129, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.5693548387096774, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.603225806451613, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.603225806451613, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.603225806451613, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.5870967741935484, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.5870967741935484, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.5870967741935484, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.5870967741935484, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.603225806451613, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.5870967741935484, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.6532258064516129, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.5370967741935484, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.48709677419354835, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.5370967741935484, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.5370967741935484, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.5532258064516129, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.6532258064516129, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.685483870967742, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.603225806451613, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.5032258064516129, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.4854838709677419, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.4693548387096774, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.5693548387096774, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.5, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.5854838709677419, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.5, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.5, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.5, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.5, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.5, "id_best": 36, "lr_best": 0.0021299999999999995, "wd_best": 0.05, "train/loss_best": 4.9986988306045535e-05, "validation/loss_best": 2.428474187850952, "validation/acc_best": 0.7804878048780488, "validation/f1_best": 0.6917293233082706, "validation/bacc_best": 0.685483870967742} +{"epoch": 14, "train/lr": 8.9081919031238e-05, "train/loss": 0.21682547546923162, "train/grad": 0.13316985009238125, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.4578302001953125, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.451507568359375, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.44206146240234373, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.4333843994140625, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.42560028076171874, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.4156101989746094, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.40524322509765626, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.39476890563964845, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.3823140716552734, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.37042476654052736, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.3596377944946289, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.3440947151184082, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.32888895988464356, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.30560725688934326, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.27985889434814454, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.24744462132453918, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.19485631927847863, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.12750087231397628, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.06187404975295067, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.02703761965036392, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.009723606705665588, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.004412327855825424, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.002201912850141525, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.0011775912344455719, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.000710882991552353, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.00045116648077964783, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.0003377649188041687, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0002618217468261719, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0001618926227092743, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0001208643615245819, "train/loss_030_lr2.7e+00_wd1.0e+00": 8.619427680969238e-05, "train/loss_031_lr3.1e+00_wd1.0e+00": 6.854921579360962e-05, "train/loss_032_lr3.7e+00_wd1.0e+00": 6.968319416046142e-05, "train/loss_033_lr4.3e+00_wd1.0e+00": 5.959764122962952e-05, "train/loss_034_lr5.1e+00_wd1.0e+00": 6.812065839767456e-05, "train/loss_035_lr6.0e+00_wd1.0e+00": 6.390079855918885e-05, "train/loss_036_lr7.1e+00_wd1.0e+00": 4.884600639343262e-05, "train/loss_037_lr8.3e+00_wd1.0e+00": 4.8023760318756106e-05, "train/loss_038_lr9.8e+00_wd1.0e+00": 5.012616515159607e-05, "train/loss_039_lr1.2e+01_wd1.0e+00": 5.678147077560425e-05, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.00010557606816291809, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.7713159322738648e-05, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.69140625, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.00016194775700569152, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.69140625, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.69140625, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.69140625, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.69140625, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.69140625, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.031134012185502796, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.030993536254391073, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.030795244572218508, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.030641863502096384, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.030525518201757224, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.030392296300269663, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.03028763640904799, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.030205740672536195, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.030132642253302037, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.03010038358392194, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.03009087990503758, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.03015345811843872, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.030276341687422246, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.030541323076467963, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.030815771457273513, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.030795868157874794, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.029365103819873183, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.025641900193877517, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.017995164624881, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.010082678470644169, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.004047124555218034, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.0018644391415000427, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0009109302271099295, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0004932419080068939, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.00030343221200382684, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.00019616868569755753, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.00014826727569925425, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.00011623089743352466, "train/grad_028_lr1.9e+00_wd1.0e+00": 7.473796119938925e-05, "train/grad_029_lr2.3e+00_wd1.0e+00": 5.260487035229744e-05, "train/grad_030_lr2.7e+00_wd1.0e+00": 3.082427051595005e-05, "train/grad_031_lr3.1e+00_wd1.0e+00": 2.526790609863383e-05, "train/grad_032_lr3.7e+00_wd1.0e+00": 2.4657248393396002e-05, "train/grad_033_lr4.3e+00_wd1.0e+00": 2.285425375816885e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 2.5483631413862896e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 2.154177068177887e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 1.778271828243305e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 1.64396060222316e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 1.7575452719711393e-05, "train/grad_039_lr1.2e+01_wd1.0e+00": 2.0525467082279647e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 6.367280516172081e-05, "train/grad_041_lr1.6e+01_wd1.0e+00": 2.5332772822624903e-05, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0, "train/grad_043_lr2.2e+01_wd1.0e+00": 7.373238964021311e-05, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.5268188118934631, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.5225468873977661, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.5166002511978149, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.5119401216506958, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.5080030560493469, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.5042285919189453, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.5021698474884033, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.5019630789756775, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.5041321516036987, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.5088727474212646, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.5158331990242004, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.528188943862915, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.5433521866798401, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.5705158114433289, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.6071597337722778, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.6642436385154724, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.7727306485176086, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.9407209753990173, "validation/loss_018_lr3.8e-01_wd1.0e+00": 1.202480435371399, "validation/loss_019_lr4.4e-01_wd1.0e+00": 1.4982514381408691, "validation/loss_020_lr5.2e-01_wd1.0e+00": 1.8457645177841187, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.09580659866333, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.221515655517578, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.3015553951263428, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.437476634979248, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.4801700115203857, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.5754261016845703, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.625661611557007, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.676605701446533, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.631749153137207, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.7576563358306885, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.783029794692993, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.6232142448425293, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.911283016204834, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.8356025218963623, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.182441234588623, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.4378128051757812, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.4151337146759033, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.881455421447754, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.466984510421753, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.5447750091552734, "validation/loss_041_lr1.6e+01_wd1.0e+00": 5.728935718536377, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.400954484939575, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.6931472420692444, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.8048780487804879, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.8048780487804879, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.8048780487804879, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.7804878048780488, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.7804878048780488, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.7560975609756098, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.7317073170731707, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.7317073170731707, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.7317073170731707, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.7073170731707317, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.7073170731707317, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.7073170731707317, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.6829268292682927, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.6829268292682927, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.6829268292682927, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.7073170731707317, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.7073170731707317, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.7073170731707317, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.6829268292682927, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.6829268292682927, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.6829268292682927, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.6829268292682927, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.7073170731707317, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.6829268292682927, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.7317073170731707, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.6585365853658537, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.6341463414634146, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.6585365853658537, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.6585365853658537, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.6829268292682927, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.7317073170731707, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.7804878048780488, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.7073170731707317, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.6585365853658537, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.6829268292682927, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.6585365853658537, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.7073170731707317, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.7560975609756098, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.7073170731707317, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.7560975609756098, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.7560975609756098, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.7560975609756098, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.7560975609756098, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.7560975609756098, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.6095238095238095, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.6095238095238095, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.6095238095238095, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.5886287625418061, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.5886287625418061, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.569327731092437, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.569327731092437, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.6117424242424243, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.5918552036199095, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.5918552036199095, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.5918552036199095, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.5729166666666666, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.5729166666666666, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.5729166666666666, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.5547201336675021, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.5547201336675021, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.5547201336675021, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.603225806451613, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.603225806451613, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.603225806451613, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.5839188134270101, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.5839188134270101, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.5839188134270101, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.5839188134270101, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.603225806451613, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.5839188134270101, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.6479313036690086, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.5370967741935484, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.48621553884711777, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.5370967741935484, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.5370967741935484, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.5547201336675021, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.6479313036690086, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.6917293233082706, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.603225806451613, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.5017361111111112, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.4696517412935323, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.4564393939393939, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.5729166666666666, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.4305555555555556, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.5729166666666666, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.4305555555555556, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.4305555555555556, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.4305555555555556, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.4305555555555556, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.4305555555555556, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.5, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.5, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.5, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.6, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.6, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.6, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.5838709677419355, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.5838709677419355, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.567741935483871, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.567741935483871, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.6016129032258064, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.5854838709677419, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.5854838709677419, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.5854838709677419, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.5693548387096774, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.5693548387096774, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.5693548387096774, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.5532258064516129, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.5532258064516129, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.5532258064516129, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.603225806451613, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.603225806451613, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.603225806451613, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.5870967741935484, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.5870967741935484, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.5870967741935484, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.5870967741935484, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.603225806451613, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.5870967741935484, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.6532258064516129, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.5370967741935484, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.48709677419354835, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.5370967741935484, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.5370967741935484, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.5532258064516129, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.6532258064516129, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.685483870967742, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.603225806451613, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.5032258064516129, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.4854838709677419, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.4693548387096774, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.5693548387096774, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.5, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.5693548387096774, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.5, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.5, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.5, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.5, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.5, "id_best": 36, "lr_best": 0.0021299999999999995, "wd_best": 0.05, "train/loss_best": 4.884600639343262e-05, "validation/loss_best": 2.4378128051757812, "validation/acc_best": 0.7804878048780488, "validation/f1_best": 0.6917293233082706, "validation/bacc_best": 0.685483870967742} +{"epoch": 15, "train/lr": 6.196799573888289e-05, "train/loss": 0.2265280006080866, "train/grad": 0.1290927573479712, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.48637451171875, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.480457763671875, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.4715069580078125, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.463248291015625, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.45562469482421875, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.4458631896972656, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.4357838439941406, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.42534332275390624, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.4130957794189453, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.40116104125976565, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.3902407455444336, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.3744975471496582, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.3592444896697998, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.3357133626937866, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.30845395565032957, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.2707385057210922, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.20346832767128945, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.1251138387620449, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.060197003036737445, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.026069717854261397, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.00925238847732544, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.00409762978553772, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.0020010088384151458, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.0010802361369132995, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.0006631180644035339, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.0004236641526222229, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.00031936392188072207, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.00025316938757896423, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.00016640082001686095, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.00012358322739601136, "train/loss_030_lr2.7e+00_wd1.0e+00": 7.740721106529236e-05, "train/loss_031_lr3.1e+00_wd1.0e+00": 5.924314260482788e-05, "train/loss_032_lr3.7e+00_wd1.0e+00": 6.692826747894286e-05, "train/loss_033_lr4.3e+00_wd1.0e+00": 4.991039633750915e-05, "train/loss_034_lr5.1e+00_wd1.0e+00": 6.515741348266602e-05, "train/loss_035_lr6.0e+00_wd1.0e+00": 5.2841603755950926e-05, "train/loss_036_lr7.1e+00_wd1.0e+00": 4.6433359384536745e-05, "train/loss_037_lr8.3e+00_wd1.0e+00": 4.168584942817688e-05, "train/loss_038_lr9.8e+00_wd1.0e+00": 4.717066884040833e-05, "train/loss_039_lr1.2e+01_wd1.0e+00": 5.0942450761795045e-05, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.0001120944321155548, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.0066519975662232e-05, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.69140625, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.00015746161341667175, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.69140625, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.69140625, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.69140625, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.69140625, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.69140625, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.030053777084685863, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.029915647003799676, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.02976458233781159, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.02963079118169844, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.029542839026544244, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.029443244389258324, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.02937773790676147, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.029337921743281186, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.02936119312653318, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.029434408652596177, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.02954245691653341, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.029757729179691522, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.03000273054232821, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.030360132639762016, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.03059821928618476, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.030237309210933747, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.0279708719055634, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.023504927216563373, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.01571982407942414, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.008339262219378725, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.0033199177062488163, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.0015622388913106987, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0008007406897195323, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.00044234485272681923, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0002740287980304856, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0001791411809699639, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0001362668109823062, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.00010870883455027069, "train/grad_028_lr1.9e+00_wd1.0e+00": 7.129902635369945e-05, "train/grad_029_lr2.3e+00_wd1.0e+00": 4.979705595815176e-05, "train/grad_030_lr2.7e+00_wd1.0e+00": 2.9971826596693062e-05, "train/grad_031_lr3.1e+00_wd1.0e+00": 2.4237375454276845e-05, "train/grad_032_lr3.7e+00_wd1.0e+00": 2.3854531768847664e-05, "train/grad_033_lr4.3e+00_wd1.0e+00": 2.1368673244523962e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 2.460734295027578e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 2.0377189081273172e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 1.7055349450458833e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 1.5549120846571895e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 1.66608523272771e-05, "train/grad_039_lr1.2e+01_wd1.0e+00": 1.9564987738363016e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 5.9091212309354546e-05, "train/grad_041_lr1.6e+01_wd1.0e+00": 3.05652990936304e-05, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0, "train/grad_043_lr2.2e+01_wd1.0e+00": 7.046750283734582e-05, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.5258966684341431, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.5217782258987427, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.515784502029419, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.5108033418655396, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.5071157217025757, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.5034891963005066, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.5014482140541077, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.5011470317840576, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.5035397410392761, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.5087823867797852, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.5156718492507935, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.52858966588974, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.5441004633903503, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.5729089379310608, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.6127867102622986, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.6755476593971252, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.7913671135902405, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.9683700203895569, "validation/loss_018_lr3.8e-01_wd1.0e+00": 1.2477076053619385, "validation/loss_019_lr4.4e-01_wd1.0e+00": 1.5513100624084473, "validation/loss_020_lr5.2e-01_wd1.0e+00": 1.8989075422286987, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.1443135738372803, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.255204677581787, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.3275563716888428, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.4654321670532227, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.5014994144439697, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.5940163135528564, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.643409252166748, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.694596767425537, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.647520065307617, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.766810417175293, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.800001859664917, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.634483814239502, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.9142649173736572, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.8491263389587402, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.190645456314087, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.445887804031372, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.4278550148010254, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.8943276405334473, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.4796435832977295, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.520932197570801, "validation/loss_041_lr1.6e+01_wd1.0e+00": 5.540992259979248, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.4065101146698, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.6931472420692444, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.8048780487804879, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.8048780487804879, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.8048780487804879, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.7804878048780488, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.7804878048780488, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.7560975609756098, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.7317073170731707, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.7317073170731707, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.7073170731707317, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.7073170731707317, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.7073170731707317, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.6585365853658537, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.6829268292682927, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.6829268292682927, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.6829268292682927, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.7073170731707317, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.7073170731707317, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.7073170731707317, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.6829268292682927, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.6829268292682927, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.6829268292682927, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.6829268292682927, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.7073170731707317, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.6829268292682927, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.7317073170731707, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.6585365853658537, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.6341463414634146, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.6585365853658537, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.6585365853658537, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.6829268292682927, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.7317073170731707, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.7804878048780488, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.7073170731707317, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.6585365853658537, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.6829268292682927, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.6585365853658537, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.7073170731707317, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.7560975609756098, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.7073170731707317, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.7560975609756098, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.7560975609756098, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.7560975609756098, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.7560975609756098, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.7560975609756098, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.6095238095238095, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.6095238095238095, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.6095238095238095, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.5886287625418061, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.5886287625418061, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.569327731092437, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.569327731092437, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.6117424242424243, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.5918552036199095, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.5918552036199095, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.5729166666666666, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.5729166666666666, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.603225806451613, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.5370967741935484, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.5547201336675021, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.5547201336675021, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.5547201336675021, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.603225806451613, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.603225806451613, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.603225806451613, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.5839188134270101, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.5839188134270101, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.5839188134270101, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.5839188134270101, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.603225806451613, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.5839188134270101, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.6479313036690086, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.5370967741935484, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.48621553884711777, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.5370967741935484, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.5370967741935484, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.5547201336675021, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.6479313036690086, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.6917293233082706, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.603225806451613, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.5017361111111112, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.4696517412935323, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.4564393939393939, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.5729166666666666, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.4305555555555556, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.5729166666666666, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.4305555555555556, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.4305555555555556, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.4305555555555556, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.4305555555555556, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.4305555555555556, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.5, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.5, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.5, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.6, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.6, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.6, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.5838709677419355, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.5838709677419355, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.567741935483871, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.567741935483871, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.6016129032258064, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.5854838709677419, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.5854838709677419, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.5693548387096774, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.5693548387096774, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.603225806451613, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.5370967741935484, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.5532258064516129, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.5532258064516129, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.5532258064516129, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.603225806451613, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.603225806451613, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.603225806451613, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.5870967741935484, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.5870967741935484, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.5870967741935484, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.5870967741935484, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.603225806451613, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.5870967741935484, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.6532258064516129, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.5370967741935484, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.48709677419354835, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.5370967741935484, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.5370967741935484, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.5532258064516129, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.6532258064516129, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.685483870967742, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.603225806451613, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.5032258064516129, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.4854838709677419, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.4693548387096774, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.5693548387096774, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.5, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.5693548387096774, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.5, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.5, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.5, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.5, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.5, "id_best": 36, "lr_best": 0.0021299999999999995, "wd_best": 0.05, "train/loss_best": 4.6433359384536745e-05, "validation/loss_best": 2.445887804031372, "validation/acc_best": 0.7804878048780488, "validation/f1_best": 0.6917293233082706, "validation/bacc_best": 0.685483870967742} +{"epoch": 16, "train/lr": 3.870405029380728e-05, "train/loss": 0.21323550071567296, "train/grad": 0.12150037394836545, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.4661907958984375, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.4589907836914062, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.44795684814453124, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.43802642822265625, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.4287603759765625, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.41684051513671877, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.40460693359375, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.39223838806152345, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.3773589324951172, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.36296337127685546, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.34996915817260743, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.33133319854736326, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.3137166309356689, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.28698833465576173, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.25676610708236697, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.21796259582042693, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.16157826110720636, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.10083472177386284, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.04909376621246338, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.02151194542646408, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.0077020637691020966, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.003453257381916046, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.001730034351348877, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.0009545291960239411, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.000603020191192627, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.00038358673453330993, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.000288873165845871, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.00023264452815055847, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.00015235036611557006, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0001158517599105835, "train/loss_030_lr2.7e+00_wd1.0e+00": 7.369145750999451e-05, "train/loss_031_lr3.1e+00_wd1.0e+00": 5.8307945728302e-05, "train/loss_032_lr3.7e+00_wd1.0e+00": 6.37868046760559e-05, "train/loss_033_lr4.3e+00_wd1.0e+00": 5.4897218942642214e-05, "train/loss_034_lr5.1e+00_wd1.0e+00": 5.486726760864258e-05, "train/loss_035_lr6.0e+00_wd1.0e+00": 5.381539463996887e-05, "train/loss_036_lr7.1e+00_wd1.0e+00": 4.286721348762512e-05, "train/loss_037_lr8.3e+00_wd1.0e+00": 4.166528582572937e-05, "train/loss_038_lr9.8e+00_wd1.0e+00": 4.301860928535461e-05, "train/loss_039_lr1.2e+01_wd1.0e+00": 4.6300888061523435e-05, "train/loss_040_lr1.4e+01_wd1.0e+00": 9.061813354492187e-05, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.0433982610702516e-05, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.69140625, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.00014367282390594481, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.69140625, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.69140625, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.69140625, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.69140625, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.69140625, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.027787531963549553, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.027700951730366796, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.027597938601393254, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.027507260635029524, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.02744164538104087, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.027376622480805964, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.02733333863085136, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.0273306322703138, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.027385788920801134, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.027492111446335912, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.027653424537274988, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.02793548519955948, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.028273912952281533, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.02877663234481588, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.029186322931200267, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.029233774365857244, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.027783898289781065, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.022936684521846475, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.014474484156817197, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.007506967566150706, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.0029936326852475757, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.0014001329713209999, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.000715127037401544, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.000400619156735047, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0002476018179277162, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0001590916139048204, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0001202008516247588, "train/grad_027_lr1.6e+00_wd1.0e+00": 9.576898567047465e-05, "train/grad_028_lr1.9e+00_wd1.0e+00": 6.220819630243568e-05, "train/grad_029_lr2.3e+00_wd1.0e+00": 4.5158534044276165e-05, "train/grad_030_lr2.7e+00_wd1.0e+00": 2.7945705573984016e-05, "train/grad_031_lr3.1e+00_wd1.0e+00": 2.2761792572509875e-05, "train/grad_032_lr3.7e+00_wd1.0e+00": 2.2598869234116136e-05, "train/grad_033_lr4.3e+00_wd1.0e+00": 2.1212794459870567e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 2.3196119100248326e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 1.9346121893022427e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 1.6120331123659072e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 1.4665226572105894e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 1.5326178230452568e-05, "train/grad_039_lr1.2e+01_wd1.0e+00": 1.864380410324884e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 5.7320156096096755e-05, "train/grad_041_lr1.6e+01_wd1.0e+00": 3.397479261481804e-05, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0, "train/grad_043_lr2.2e+01_wd1.0e+00": 6.470677105198775e-05, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.5254716873168945, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.5211899280548096, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.5151216387748718, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.5102505683898926, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.5065581798553467, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.5030527710914612, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.5011778473854065, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.5010365843772888, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.5037919282913208, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.5091549158096313, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.5164880752563477, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.5296220779418945, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.5455272793769836, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.5750493407249451, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.6165741682052612, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.6818021535873413, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.801459789276123, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.9830644130706787, "validation/loss_018_lr3.8e-01_wd1.0e+00": 1.2708461284637451, "validation/loss_019_lr4.4e-01_wd1.0e+00": 1.580024003982544, "validation/loss_020_lr5.2e-01_wd1.0e+00": 1.9226495027542114, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.1635470390319824, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.2722396850585938, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.3440089225769043, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.480942964553833, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.515197277069092, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.606146812438965, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.651352643966675, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.707519054412842, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.650555372238159, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.7763454914093018, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.804202079772949, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.6439614295959473, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.9210855960845947, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.859856605529785, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.1979589462280273, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.4531476497650146, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.436307191848755, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.8999741077423096, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.4813828468322754, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.50945782661438, "validation/loss_041_lr1.6e+01_wd1.0e+00": 5.455573081970215, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.412749767303467, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.6931472420692444, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.8048780487804879, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.8048780487804879, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.8048780487804879, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.7804878048780488, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.7804878048780488, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.7560975609756098, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.7317073170731707, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.7317073170731707, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.7073170731707317, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.7073170731707317, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.7073170731707317, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.6829268292682927, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.6829268292682927, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.6829268292682927, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.6829268292682927, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.7073170731707317, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.7073170731707317, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.7073170731707317, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.6829268292682927, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.6829268292682927, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.6829268292682927, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.6829268292682927, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.7073170731707317, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.6829268292682927, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.7317073170731707, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.6585365853658537, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.6341463414634146, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.6341463414634146, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.6585365853658537, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.6829268292682927, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.7317073170731707, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.7804878048780488, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.7073170731707317, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.6585365853658537, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.6829268292682927, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.6585365853658537, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.7073170731707317, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.7560975609756098, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.7073170731707317, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.7560975609756098, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.7560975609756098, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.7560975609756098, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.7560975609756098, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.7560975609756098, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.6095238095238095, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.6095238095238095, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.6095238095238095, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.5886287625418061, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.5886287625418061, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.569327731092437, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.569327731092437, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.6117424242424243, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.5918552036199095, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.5918552036199095, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.5729166666666666, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.5729166666666666, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.603225806451613, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.5547201336675021, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.5547201336675021, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.5547201336675021, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.5547201336675021, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.603225806451613, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.603225806451613, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.603225806451613, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.5839188134270101, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.5839188134270101, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.5839188134270101, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.5839188134270101, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.603225806451613, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.5839188134270101, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.6479313036690086, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.5370967741935484, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.48621553884711777, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.48621553884711777, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.5370967741935484, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.5547201336675021, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.6479313036690086, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.6917293233082706, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.603225806451613, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.5017361111111112, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.4696517412935323, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.4564393939393939, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.5729166666666666, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.4305555555555556, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.5729166666666666, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.4305555555555556, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.4305555555555556, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.4305555555555556, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.4305555555555556, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.4305555555555556, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.5, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.5, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.5, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.6, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.6, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.6, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.5838709677419355, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.5838709677419355, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.567741935483871, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.567741935483871, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.6016129032258064, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.5854838709677419, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.5854838709677419, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.5693548387096774, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.5693548387096774, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.603225806451613, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.5532258064516129, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.5532258064516129, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.5532258064516129, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.5532258064516129, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.603225806451613, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.603225806451613, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.603225806451613, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.5870967741935484, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.5870967741935484, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.5870967741935484, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.5870967741935484, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.603225806451613, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.5870967741935484, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.6532258064516129, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.5370967741935484, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.48709677419354835, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.48709677419354835, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.5370967741935484, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.5532258064516129, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.6532258064516129, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.685483870967742, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.603225806451613, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.5032258064516129, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.4854838709677419, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.4693548387096774, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.5693548387096774, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.5, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.5693548387096774, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.5, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.5, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.5, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.5, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.5, "id_best": 36, "lr_best": 0.0021299999999999995, "wd_best": 0.05, "train/loss_best": 4.286721348762512e-05, "validation/loss_best": 2.4531476497650146, "validation/acc_best": 0.7804878048780488, "validation/f1_best": 0.6917293233082706, "validation/bacc_best": 0.685483870967742} +{"epoch": 17, "train/lr": 2.030750443206766e-05, "train/loss": 0.21673958867788315, "train/grad": 0.12331810869276523, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.47124267578125, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.46382965087890626, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.4528662109375, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.4430438232421875, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.43414520263671874, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.42309127807617186, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.411890869140625, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.4006813049316406, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.3874632263183594, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.3748926544189453, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.36323991775512693, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.34663795471191405, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.330384635925293, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.3051867341995239, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.27546671628952024, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.2350075364112854, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.17035796508193016, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.09980936199426652, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.04622928589582443, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.020324569046497345, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.007428163290023803, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.0033683623373508454, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.001703188568353653, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.0009349586069583893, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.0005922499299049378, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.0003910622000694275, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.0002934299409389496, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0002374039590358734, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.00015477284789085387, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0001153111457824707, "train/loss_030_lr2.7e+00_wd1.0e+00": 7.140502333641052e-05, "train/loss_031_lr3.1e+00_wd1.0e+00": 5.7964175939559934e-05, "train/loss_032_lr3.7e+00_wd1.0e+00": 5.902186036109924e-05, "train/loss_033_lr4.3e+00_wd1.0e+00": 4.515737295150757e-05, "train/loss_034_lr5.1e+00_wd1.0e+00": 6.547465920448304e-05, "train/loss_035_lr6.0e+00_wd1.0e+00": 5.340993404388428e-05, "train/loss_036_lr7.1e+00_wd1.0e+00": 4.1844546794891356e-05, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.917381167411804e-05, "train/loss_038_lr9.8e+00_wd1.0e+00": 4.201129078865051e-05, "train/loss_039_lr1.2e+01_wd1.0e+00": 4.697740077972412e-05, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.00010887473821640015, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.3229271173477174e-05, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.69140625, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.0001375773549079895, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.69140625, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.69140625, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.69140625, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.69140625, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.69140625, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.027999136664438994, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.027904520819429308, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.02779087295755744, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.027723313013557346, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.0276857968326658, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.027695227079093457, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.02775423588231206, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.027867755433544517, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.028068877265322954, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.028292028070427477, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.02852554155746475, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.028849212925415486, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.029122399678453804, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.029456360603217036, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.02960828408366069, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.02935592128429562, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.02779300125548616, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.02291094555403106, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.014298938583233394, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.007334813992056297, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.00292092054420209, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.0013602065300801769, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0006878823948136414, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.00038211181159567784, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.00023871080362368956, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.00015648144650185714, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.00011970824655691104, "train/grad_027_lr1.6e+00_wd1.0e+00": 9.573075500156847e-05, "train/grad_028_lr1.9e+00_wd1.0e+00": 6.318836870832457e-05, "train/grad_029_lr2.3e+00_wd1.0e+00": 4.505792343479698e-05, "train/grad_030_lr2.7e+00_wd1.0e+00": 2.7931928127600258e-05, "train/grad_031_lr3.1e+00_wd1.0e+00": 2.229591255371588e-05, "train/grad_032_lr3.7e+00_wd1.0e+00": 2.202049281095242e-05, "train/grad_033_lr4.3e+00_wd1.0e+00": 2.060144395500174e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 2.230061121736071e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 1.936221226856105e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 1.589222200379936e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 1.4103810162851004e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 1.4970110946705972e-05, "train/grad_039_lr1.2e+01_wd1.0e+00": 1.7804083079795418e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 5.5489465373241845e-05, "train/grad_041_lr1.6e+01_wd1.0e+00": 3.453591168871635e-05, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0, "train/grad_043_lr2.2e+01_wd1.0e+00": 6.164686139186415e-05, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.5251482725143433, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.5211275815963745, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.5148898363113403, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.5100687146186829, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.5063609480857849, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.5029109716415405, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.5012624263763428, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.5012478828430176, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.5040937662124634, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.5095978379249573, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.5167282819747925, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.5306723713874817, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.5469468235969543, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.5770602226257324, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.6200326681137085, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.6870677471160889, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.8094214200973511, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.9960256218910217, "validation/loss_018_lr3.8e-01_wd1.0e+00": 1.2886320352554321, "validation/loss_019_lr4.4e-01_wd1.0e+00": 1.59856379032135, "validation/loss_020_lr5.2e-01_wd1.0e+00": 1.9404057264328003, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.1808505058288574, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.2856321334838867, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.3547794818878174, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.488609790802002, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.5222971439361572, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.6142518520355225, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.6571414470672607, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.7115979194641113, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.6573410034179688, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.779714345932007, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.8095591068267822, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.648649215698242, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.9226789474487305, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.864689826965332, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.2035703659057617, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.4587175846099854, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.440983772277832, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.911841869354248, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.487610101699829, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.507188320159912, "validation/loss_041_lr1.6e+01_wd1.0e+00": 5.404976844787598, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.415203094482422, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.6931472420692444, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.8048780487804879, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.8048780487804879, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.8048780487804879, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.7804878048780488, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.7804878048780488, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.7560975609756098, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.7317073170731707, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.7317073170731707, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.7073170731707317, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.7073170731707317, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.7073170731707317, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.6829268292682927, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.6829268292682927, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.6585365853658537, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.6829268292682927, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.7073170731707317, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.7073170731707317, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.7073170731707317, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.6829268292682927, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.6829268292682927, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.6829268292682927, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.6829268292682927, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.7073170731707317, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.6829268292682927, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.7317073170731707, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.6585365853658537, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.6341463414634146, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.6341463414634146, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.6585365853658537, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.6829268292682927, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.7317073170731707, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.7804878048780488, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.7073170731707317, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.6585365853658537, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.6829268292682927, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.6585365853658537, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.7073170731707317, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.7560975609756098, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.7073170731707317, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.7560975609756098, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.7560975609756098, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.7560975609756098, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.7560975609756098, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.7560975609756098, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.6095238095238095, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.6095238095238095, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.6095238095238095, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.5886287625418061, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.5886287625418061, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.569327731092437, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.569327731092437, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.6117424242424243, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.5918552036199095, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.5918552036199095, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.5729166666666666, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.5729166666666666, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.5729166666666666, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.5547201336675021, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.5547201336675021, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.5017361111111112, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.5547201336675021, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.603225806451613, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.603225806451613, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.603225806451613, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.5839188134270101, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.5839188134270101, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.5839188134270101, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.5839188134270101, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.603225806451613, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.5839188134270101, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.6479313036690086, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.5370967741935484, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.48621553884711777, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.48621553884711777, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.5370967741935484, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.5547201336675021, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.6479313036690086, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.6917293233082706, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.603225806451613, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.5017361111111112, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.4696517412935323, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.4564393939393939, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.5729166666666666, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.4305555555555556, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.5729166666666666, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.4305555555555556, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.4305555555555556, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.4305555555555556, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.4305555555555556, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.4305555555555556, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.5, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.5, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.5, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.6, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.6, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.6, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.5838709677419355, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.5838709677419355, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.567741935483871, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.567741935483871, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.6016129032258064, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.5854838709677419, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.5854838709677419, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.5693548387096774, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.5693548387096774, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.5693548387096774, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.5532258064516129, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.5532258064516129, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.5032258064516129, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.5532258064516129, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.603225806451613, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.603225806451613, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.603225806451613, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.5870967741935484, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.5870967741935484, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.5870967741935484, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.5870967741935484, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.603225806451613, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.5870967741935484, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.6532258064516129, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.5370967741935484, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.48709677419354835, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.48709677419354835, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.5370967741935484, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.5532258064516129, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.6532258064516129, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.685483870967742, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.603225806451613, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.5032258064516129, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.4854838709677419, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.4693548387096774, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.5693548387096774, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.5, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.5693548387096774, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.5, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.5, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.5, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.5, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.5, "id_best": 36, "lr_best": 0.0021299999999999995, "wd_best": 0.05, "train/loss_best": 4.1844546794891356e-05, "validation/loss_best": 2.4587175846099854, "validation/acc_best": 0.7804878048780488, "validation/f1_best": 0.6917293233082706, "validation/bacc_best": 0.685483870967742} +{"epoch": 18, "train/lr": 7.5829098008590064e-06, "train/loss": 0.21210804857313634, "train/grad": 0.12971090698614718, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.4712579345703125, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.4633477783203125, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.450963134765625, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.439613037109375, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.42906036376953127, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.4157905578613281, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.40179885864257814, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.38797233581542967, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.3717548370361328, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.3564731979370117, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.3428392028808594, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.3241554069519043, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.3068570804595947, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.2813852596282959, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.2526681900024414, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.21488166511058807, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.15806396096944808, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.09678283035755157, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.04529469788074494, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.019294633269309996, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.006832724511623383, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.0030370603501796724, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.0015170842409133912, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.0008466754853725433, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.0005413086712360382, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.00035442084074020384, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.00026832133531570437, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.00021749913692474366, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.00014131054282188416, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.00010525450110435486, "train/loss_030_lr2.7e+00_wd1.0e+00": 6.284669041633606e-05, "train/loss_031_lr3.1e+00_wd1.0e+00": 5.118235945701599e-05, "train/loss_032_lr3.7e+00_wd1.0e+00": 5.4431557655334475e-05, "train/loss_033_lr4.3e+00_wd1.0e+00": 4.493415355682373e-05, "train/loss_034_lr5.1e+00_wd1.0e+00": 5.6231915950775144e-05, "train/loss_035_lr6.0e+00_wd1.0e+00": 4.62089478969574e-05, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.660157322883606e-05, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.65661084651947e-05, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.858044743537903e-05, "train/loss_039_lr1.2e+01_wd1.0e+00": 4.4050663709640504e-05, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.00010058104991912842, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.9063820838928223e-05, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.69140625, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.00013917699456214905, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.69140625, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.69140625, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.69140625, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.69140625, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.69140625, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.02967356703709811, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.029576659437734635, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.029447491480968892, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.029362761504016816, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.029305375323165208, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.029273233287967743, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.029282787705305964, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.029342006978113205, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.02947091659763828, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.029633749679196627, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.029815395881887526, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.030101782171986998, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.030376784775871784, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.030771969652269037, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.03109883127268404, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.03103680409025401, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.02960839615436271, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.024590123711386695, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.014874070954392664, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.007336440999060869, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.002886890328809386, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.0013568353539449164, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0007006673991963908, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0003946523480135511, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.00024941380553173076, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.00016484040074828953, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.00012621705006495175, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.00010093536986005347, "train/grad_028_lr1.9e+00_wd1.0e+00": 6.521740286189015e-05, "train/grad_029_lr2.3e+00_wd1.0e+00": 4.603332395163307e-05, "train/grad_030_lr2.7e+00_wd1.0e+00": 2.690416337827628e-05, "train/grad_031_lr3.1e+00_wd1.0e+00": 2.1878939128328058e-05, "train/grad_032_lr3.7e+00_wd1.0e+00": 2.1848576518550545e-05, "train/grad_033_lr4.3e+00_wd1.0e+00": 2.0215077838656726e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 2.230090017405928e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 1.9029146062621294e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 1.5176436596675557e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 1.3871422905822329e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 1.472415813736916e-05, "train/grad_039_lr1.2e+01_wd1.0e+00": 1.7296816961334115e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 5.57685913663164e-05, "train/grad_041_lr1.6e+01_wd1.0e+00": 3.274200809174631e-05, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0, "train/grad_043_lr2.2e+01_wd1.0e+00": 5.8512189204975585e-05, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.5251632332801819, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.5209915041923523, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.5149248242378235, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.5100945830345154, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.5064950585365295, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.5031265020370483, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.5014484524726868, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.5011085867881775, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.5042420029640198, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.5098037719726562, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.517370343208313, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.5310574769973755, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.5478308796882629, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.5784265398979187, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.6210488080978394, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.6895123720169067, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.8121321797370911, "validation/loss_017_lr3.2e-01_wd1.0e+00": 1.0005563497543335, "validation/loss_018_lr3.8e-01_wd1.0e+00": 1.2945058345794678, "validation/loss_019_lr4.4e-01_wd1.0e+00": 1.6050039529800415, "validation/loss_020_lr5.2e-01_wd1.0e+00": 1.9473493099212646, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.187851667404175, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.2910661697387695, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.3589982986450195, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.4944820404052734, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.5246620178222656, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.6174261569976807, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.661949634552002, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.7141098976135254, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.6580662727355957, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.782694101333618, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.809890031814575, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.6525399684906006, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.924008369445801, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.867575168609619, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.205362558364868, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.4605531692504883, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.4442617893218994, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.9150450229644775, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.4931161403656006, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.504871129989624, "validation/loss_041_lr1.6e+01_wd1.0e+00": 5.376593112945557, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.419428586959839, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.6931472420692444, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.8048780487804879, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.8048780487804879, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.8048780487804879, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.7804878048780488, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.7804878048780488, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.7560975609756098, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.7317073170731707, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.7317073170731707, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.7317073170731707, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.7073170731707317, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.7073170731707317, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.6829268292682927, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.6829268292682927, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.6585365853658537, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.6829268292682927, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.7073170731707317, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.7073170731707317, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.7073170731707317, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.6829268292682927, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.6829268292682927, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.6829268292682927, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.6829268292682927, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.7073170731707317, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.6829268292682927, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.7317073170731707, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.6585365853658537, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.6341463414634146, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.6341463414634146, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.6585365853658537, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.6829268292682927, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.7317073170731707, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.7804878048780488, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.7073170731707317, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.6585365853658537, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.6829268292682927, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.6585365853658537, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.7073170731707317, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.7560975609756098, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.7073170731707317, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.7560975609756098, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.7560975609756098, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.7560975609756098, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.7560975609756098, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.7560975609756098, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.6095238095238095, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.6095238095238095, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.6095238095238095, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.5886287625418061, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.5886287625418061, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.569327731092437, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.569327731092437, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.6117424242424243, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.5918552036199095, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.5918552036199095, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.5918552036199095, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.5729166666666666, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.5729166666666666, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.5547201336675021, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.5547201336675021, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.5017361111111112, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.5547201336675021, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.603225806451613, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.603225806451613, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.603225806451613, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.5839188134270101, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.5839188134270101, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.5839188134270101, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.5839188134270101, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.603225806451613, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.5839188134270101, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.6479313036690086, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.5370967741935484, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.48621553884711777, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.48621553884711777, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.5370967741935484, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.5547201336675021, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.6479313036690086, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.6917293233082706, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.603225806451613, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.5017361111111112, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.4696517412935323, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.4564393939393939, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.5729166666666666, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.4305555555555556, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.5729166666666666, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.4305555555555556, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.4305555555555556, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.4305555555555556, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.4305555555555556, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.4305555555555556, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.5, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.5, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.5, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.6, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.6, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.6, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.5838709677419355, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.5838709677419355, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.567741935483871, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.567741935483871, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.6016129032258064, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.5854838709677419, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.5854838709677419, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.5854838709677419, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.5693548387096774, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.5693548387096774, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.5532258064516129, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.5532258064516129, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.5032258064516129, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.5532258064516129, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.603225806451613, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.603225806451613, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.603225806451613, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.5870967741935484, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.5870967741935484, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.5870967741935484, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.5870967741935484, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.603225806451613, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.5870967741935484, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.6532258064516129, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.5370967741935484, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.48709677419354835, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.48709677419354835, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.5370967741935484, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.5532258064516129, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.6532258064516129, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.685483870967742, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.603225806451613, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.5032258064516129, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.4854838709677419, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.4693548387096774, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.5693548387096774, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.5, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.5693548387096774, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.5, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.5, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.5, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.5, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.5, "id_best": 36, "lr_best": 0.0021299999999999995, "wd_best": 0.05, "train/loss_best": 3.660157322883606e-05, "validation/loss_best": 2.4605531692504883, "validation/acc_best": 0.7804878048780488, "validation/f1_best": 0.6917293233082706, "validation/bacc_best": 0.685483870967742} +{"epoch": 19, "train/lr": 1.0867618231465446e-06, "train/loss": 0.21856728829443456, "train/grad": 0.13056347344070673, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.4703863525390625, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.463538818359375, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.453504638671875, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.44451812744140623, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.4364556884765625, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.42653732299804686, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.4161073303222656, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.4057490539550781, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.39345909118652345, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.38134033203125, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.36992431640625, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.3536800765991211, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.3375343608856201, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.31230195045471193, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.2823499202728271, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.24217937767505646, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.17971318319439888, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.10737591028213501, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.048525199592113495, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.02032997667789459, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.007307814210653305, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.0033612507581710816, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.0017013484239578247, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.0009292902052402496, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.0005794002115726471, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.0003861282765865326, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.0002919788658618927, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0002421170473098755, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.00015685781836509704, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.00011665388941764832, "train/loss_030_lr2.7e+00_wd1.0e+00": 7.37278163433075e-05, "train/loss_031_lr3.1e+00_wd1.0e+00": 5.779758095741272e-05, "train/loss_032_lr3.7e+00_wd1.0e+00": 6.0549676418304444e-05, "train/loss_033_lr4.3e+00_wd1.0e+00": 5.231529474258423e-05, "train/loss_034_lr5.1e+00_wd1.0e+00": 5.9647858142852785e-05, "train/loss_035_lr6.0e+00_wd1.0e+00": 5.0510913133621216e-05, "train/loss_036_lr7.1e+00_wd1.0e+00": 4.158094525337219e-05, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.956958651542663e-05, "train/loss_038_lr9.8e+00_wd1.0e+00": 4.377633333206177e-05, "train/loss_039_lr1.2e+01_wd1.0e+00": 4.4215768575668335e-05, "train/loss_040_lr1.4e+01_wd1.0e+00": 8.064985275268554e-05, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.5664269924163818e-05, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.69140625, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.00014600813388824464, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.69140625, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.69140625, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.69140625, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.69140625, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.69140625, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.030439419236499815, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.030330509718041868, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.03021073729963973, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.030113208214752375, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.03004907780792564, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.030005924121942373, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.02999830790096894, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.030027757443021982, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.030134011923801152, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.030259112175554038, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.03040703160688281, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.03061309979762882, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.03079796998295933, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.030942165413871407, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.03083708971273154, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.03016639861976728, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.028031492503359914, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.023000809457153083, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.014137947144336067, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.007101473977090791, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.002842168938659597, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.001339193880048697, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.000688295457039203, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0003857132643861405, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.00024321137063452626, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0001595225780238252, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.00012134010116369609, "train/grad_027_lr1.6e+00_wd1.0e+00": 9.812420922571619e-05, "train/grad_028_lr1.9e+00_wd1.0e+00": 6.320259637504933e-05, "train/grad_029_lr2.3e+00_wd1.0e+00": 4.4972986609082e-05, "train/grad_030_lr2.7e+00_wd1.0e+00": 2.7201966470329354e-05, "train/grad_031_lr3.1e+00_wd1.0e+00": 2.18773287338081e-05, "train/grad_032_lr3.7e+00_wd1.0e+00": 2.1764230446024158e-05, "train/grad_033_lr4.3e+00_wd1.0e+00": 1.9971206461377734e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 2.250614104241322e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 1.8666273673488833e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 1.5239787896916824e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 1.3903473646905695e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 1.4414297477287618e-05, "train/grad_039_lr1.2e+01_wd1.0e+00": 1.701036623217078e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 5.359541458496153e-05, "train/grad_041_lr1.6e+01_wd1.0e+00": 3.3824688193072265e-05, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0, "train/grad_043_lr2.2e+01_wd1.0e+00": 5.969471297703421e-05, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.5252082347869873, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.5210484862327576, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.5148407220840454, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.5101311206817627, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.5065104365348816, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.5030250549316406, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.5012351870536804, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.5016971826553345, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.5042541027069092, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.5099882483482361, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.5174533724784851, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.5313495397567749, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.547942578792572, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.5783341526985168, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.6217203140258789, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.6897637248039246, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.8123149275779724, "validation/loss_017_lr3.2e-01_wd1.0e+00": 1.001240849494934, "validation/loss_018_lr3.8e-01_wd1.0e+00": 1.2943373918533325, "validation/loss_019_lr4.4e-01_wd1.0e+00": 1.6056691408157349, "validation/loss_020_lr5.2e-01_wd1.0e+00": 1.9467724561691284, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.1882548332214355, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.2908389568328857, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.359523057937622, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.4951939582824707, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.527564764022827, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.618389129638672, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.6618690490722656, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.713878631591797, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.6576602458953857, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.7828269004821777, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.8127129077911377, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.6526026725769043, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.924610137939453, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.8684871196746826, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.206099271774292, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.4606077671051025, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.4449408054351807, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.914945363998413, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.4932284355163574, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.5039315223693848, "validation/loss_041_lr1.6e+01_wd1.0e+00": 5.376598834991455, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.421149730682373, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.6931472420692444, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.6931472420692444, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.8048780487804879, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.8048780487804879, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.8048780487804879, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.7804878048780488, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.7804878048780488, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.7560975609756098, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.7560975609756098, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.7317073170731707, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.7317073170731707, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.7317073170731707, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.7073170731707317, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.7073170731707317, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.6829268292682927, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.6829268292682927, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.6585365853658537, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.6829268292682927, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.7073170731707317, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.7073170731707317, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.7073170731707317, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.6829268292682927, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.6829268292682927, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.6829268292682927, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.6829268292682927, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.7073170731707317, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.6829268292682927, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.7317073170731707, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.6585365853658537, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.6341463414634146, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.6341463414634146, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.6585365853658537, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.6829268292682927, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.7317073170731707, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.7804878048780488, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.7073170731707317, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.6585365853658537, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.6829268292682927, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.6585365853658537, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.7073170731707317, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.7560975609756098, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.7073170731707317, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.7560975609756098, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.7560975609756098, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.7560975609756098, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.7560975609756098, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.7560975609756098, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.4305555555555556, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.6095238095238095, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.6095238095238095, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.6095238095238095, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.5886287625418061, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.5886287625418061, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.569327731092437, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.569327731092437, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.6117424242424243, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.5918552036199095, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.5918552036199095, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.5918552036199095, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.5729166666666666, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.5729166666666666, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.5547201336675021, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.5547201336675021, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.5017361111111112, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.5547201336675021, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.603225806451613, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.603225806451613, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.603225806451613, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.5839188134270101, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.5839188134270101, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.5839188134270101, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.5839188134270101, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.603225806451613, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.5839188134270101, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.6479313036690086, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.5370967741935484, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.48621553884711777, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.48621553884711777, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.5370967741935484, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.5547201336675021, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.6479313036690086, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.6917293233082706, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.603225806451613, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.5017361111111112, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.4696517412935323, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.4564393939393939, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.5729166666666666, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.4305555555555556, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.5729166666666666, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.4305555555555556, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.4305555555555556, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.4305555555555556, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.4305555555555556, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.4305555555555556, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.5, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.5, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.5, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.6, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.6, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.6, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.5838709677419355, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.5838709677419355, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.567741935483871, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.567741935483871, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.6016129032258064, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.5854838709677419, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.5854838709677419, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.5854838709677419, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.5693548387096774, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.5693548387096774, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.5532258064516129, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.5532258064516129, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.5032258064516129, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.5532258064516129, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.603225806451613, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.603225806451613, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.603225806451613, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.5870967741935484, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.5870967741935484, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.5870967741935484, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.5870967741935484, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.603225806451613, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.5870967741935484, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.6532258064516129, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.5370967741935484, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.48709677419354835, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.48709677419354835, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.5370967741935484, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.5532258064516129, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.6532258064516129, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.685483870967742, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.603225806451613, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.5032258064516129, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.4854838709677419, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.4693548387096774, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.5693548387096774, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.5, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.5693548387096774, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.5, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.5, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.5, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.5, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.5, "id_best": 36, "lr_best": 0.0021299999999999995, "wd_best": 0.05, "train/loss_best": 4.158094525337219e-05, "validation/loss_best": 2.4606077671051025, "validation/acc_best": 0.7804878048780488, "validation/f1_best": 0.6917293233082706, "validation/bacc_best": 0.685483870967742} diff --git a/input_space_v3/flat_lr1e-3_1/eval_v2/adni_ad_vs_cn__patch__logistic/config.yaml b/input_space_v3/flat_lr1e-3_1/eval_v2/adni_ad_vs_cn__patch__logistic/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..2d3dce6618328816783fcea0a65ba214c519bf23 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_1/eval_v2/adni_ad_vs_cn__patch__logistic/config.yaml @@ -0,0 +1,30 @@ +output_root: experiments/input_space_v3/output +name_prefix: eval_logistic +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_1; eval v2 (adni_ad_vs_cn patch logistic) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: input_space_v3/flat_lr1e-3_1/eval_v2/adni_ad_vs_cn__patch__logistic +model: flat_mae +representation: patch +dataset: adni_ad_vs_cn +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/adni_ad_vs_cn__patch__logistic +remote_dir: null diff --git a/input_space_v3/flat_lr1e-3_1/eval_v2/adni_ad_vs_cn__patch__logistic/eval_table.csv b/input_space_v3/flat_lr1e-3_1/eval_v2/adni_ad_vs_cn__patch__logistic/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..1ce1c8e23efc04de3085ad25cc07fbde8fe6b7b8 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_1/eval_v2/adni_ad_vs_cn__patch__logistic/eval_table.csv @@ -0,0 +1,203 @@ +model,repr,clf,dataset,trial,C,split,acc,acc_std,f1,f1_std,bacc,bacc_std +flat_mae,patch,logistic,adni_ad_vs_cn,,0.046415888336127774,train,0.8943089430894309,0.01315477414417864,0.8326335988835263,0.023979673612274988,0.795732452922475,0.025646056267428857 +flat_mae,patch,logistic,adni_ad_vs_cn,,0.046415888336127774,test,0.7073170731707317,0.052426294541097734,0.4831932773109243,0.07352405771758995,0.4930555555555556,0.06124936854045875 +flat_mae,patch,logistic,adni_ad_vs_cn,1,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,1,166.81005372000556,test,0.7560975609756098,0.06515722074056064,0.6693548387096775,0.08803415619871047,0.6693548387096775,0.08953103967650945 +flat_mae,patch,logistic,adni_ad_vs_cn,2,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,2,1291.5496650148827,test,0.5609756097560976,0.07416910754471685,0.4698275862068966,0.07829002134488994,0.4725806451612903,0.08771713234580747 +flat_mae,patch,logistic,adni_ad_vs_cn,3,0.005994842503189409,train,0.8373983739837398,0.013431654363641807,0.705397061954439,0.031123628716263767,0.6713986358780508,0.026071276582384492 +flat_mae,patch,logistic,adni_ad_vs_cn,3,0.005994842503189409,test,0.7073170731707317,0.033612694126248586,0.4142857142857143,0.011738306189410555,0.46774193548387094,0.0222277493415515 +flat_mae,patch,logistic,adni_ad_vs_cn,4,0.046415888336127774,train,0.8997289972899729,0.014242288499639022,0.8412164912484736,0.02552434561314673,0.805119566110609,0.026988984573936545 +flat_mae,patch,logistic,adni_ad_vs_cn,4,0.046415888336127774,test,0.9024390243902439,0.04474771636817422,0.8677419354838709,0.06160546677306388,0.8677419354838709,0.06727208672581347 +flat_mae,patch,logistic,adni_ad_vs_cn,5,0.046415888336127774,train,0.9024390243902439,0.013572243211705847,0.8463069233617179,0.02405558684746694,0.8109335195989811,0.026292388326261223 +flat_mae,patch,logistic,adni_ad_vs_cn,5,0.046415888336127774,test,0.7317073170731707,0.038890012542428784,0.4972129319955407,0.07400447039176034,0.5177419354838709,0.05207380738137465 +flat_mae,patch,logistic,adni_ad_vs_cn,6,0.046415888336127774,train,0.8970189701897019,0.013185930316370527,0.8343179884677191,0.024724054823019634,0.7952584435861616,0.026728710250658778 +flat_mae,patch,logistic,adni_ad_vs_cn,6,0.046415888336127774,test,0.7804878048780488,0.04044590838461307,0.5886287625418061,0.09571751245706862,0.5838709677419355,0.06846762027421843 +flat_mae,patch,logistic,adni_ad_vs_cn,7,0.3593813663804626,train,0.9728997289972899,0.008520247625787214,0.9608013937282229,0.012794038233014882,0.9459076341523543,0.017305257461486992 +flat_mae,patch,logistic,adni_ad_vs_cn,7,0.3593813663804626,test,0.7317073170731707,0.06668096416188503,0.6479313036690086,0.08370977998850171,0.6532258064516129,0.08666487531834224 +flat_mae,patch,logistic,adni_ad_vs_cn,8,0.046415888336127774,train,0.8970189701897019,0.013538857094847357,0.8343179884677191,0.024883253640590637,0.7952584435861616,0.026212149165642414 +flat_mae,patch,logistic,adni_ad_vs_cn,8,0.046415888336127774,test,0.7560975609756098,0.046104425866434214,0.569327731092437,0.08794904797292388,0.567741935483871,0.06707625453912046 +flat_mae,patch,logistic,adni_ad_vs_cn,9,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,9,21.54434690031882,test,0.7317073170731707,0.06859105551808536,0.6676492262343405,0.08106773095033465,0.6870967741935483,0.08777337814229258 +flat_mae,patch,logistic,adni_ad_vs_cn,10,0.3593813663804626,train,0.9728997289972899,0.008173067929028093,0.9604552469135802,0.012509677782689138,0.9418604651162791,0.017534081777973026 +flat_mae,patch,logistic,adni_ad_vs_cn,10,0.3593813663804626,test,0.7560975609756098,0.0544354181863531,0.6117424242424243,0.09227366159043424,0.6016129032258064,0.07936655538993802 +flat_mae,patch,logistic,adni_ad_vs_cn,11,0.046415888336127774,train,0.8997289972899729,0.01410872070325627,0.8428467833834041,0.024774401257237354,0.8091667351466842,0.02690545403296342 +flat_mae,patch,logistic,adni_ad_vs_cn,11,0.046415888336127774,test,0.7560975609756098,0.04478513711982098,0.569327731092437,0.08593076971213748,0.567741935483871,0.06454589764830765 +flat_mae,patch,logistic,adni_ad_vs_cn,12,0.046415888336127774,train,0.8970189701897019,0.013757608387523018,0.8394182317911132,0.02358752963428593,0.8073999506943874,0.025592448631837773 +flat_mae,patch,logistic,adni_ad_vs_cn,12,0.046415888336127774,test,0.7317073170731707,0.058513084713497,0.5918552036199095,0.09090050300189824,0.5854838709677419,0.08131503535008414 +flat_mae,patch,logistic,adni_ad_vs_cn,13,0.046415888336127774,train,0.8997289972899729,0.013955782855806622,0.8428467833834041,0.024033310837936223,0.8091667351466842,0.025688512444422006 +flat_mae,patch,logistic,adni_ad_vs_cn,13,0.046415888336127774,test,0.7560975609756098,0.05297830474212248,0.6117424242424243,0.09154118185961335,0.6016129032258064,0.0790807761540565 +flat_mae,patch,logistic,adni_ad_vs_cn,14,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,14,2.782559402207126,test,0.7560975609756098,0.06587849576789148,0.6893939393939394,0.08022474946105645,0.7032258064516128,0.0855511031413346 +flat_mae,patch,logistic,adni_ad_vs_cn,15,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,15,2.782559402207126,test,0.7317073170731707,0.060457329065346954,0.6232247284878863,0.08746409539628443,0.6193548387096774,0.08706508384043236 +flat_mae,patch,logistic,adni_ad_vs_cn,16,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,16,21.54434690031882,test,0.7073170731707317,0.06355592140584998,0.5729166666666666,0.0882387013628753,0.5693548387096774,0.08194757156201489 +flat_mae,patch,logistic,adni_ad_vs_cn,17,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,17,21.54434690031882,test,0.6341463414634146,0.06545679876423556,0.48621553884711777,0.07825069210182156,0.48709677419354835,0.0747229998150018 +flat_mae,patch,logistic,adni_ad_vs_cn,18,0.005994842503189409,train,0.8184281842818428,0.013918146195398967,0.664367847300471,0.03241846009047367,0.6387952995315966,0.02556664942874246 +flat_mae,patch,logistic,adni_ad_vs_cn,18,0.005994842503189409,test,0.8292682926829268,0.03574528169693307,0.6800445930880714,0.09742890175980444,0.65,0.07327782747871281 +flat_mae,patch,logistic,adni_ad_vs_cn,19,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,19,1291.5496650148827,test,0.7804878048780488,0.06328624902680995,0.7119437939110069,0.08170162845182061,0.7193548387096774,0.08583050469326219 +flat_mae,patch,logistic,adni_ad_vs_cn,20,0.3593813663804626,train,0.975609756097561,0.007798572806935563,0.9645665510802881,0.011828236204535292,0.9476744186046512,0.01673065910325125 +flat_mae,patch,logistic,adni_ad_vs_cn,20,0.3593813663804626,test,0.6829268292682927,0.06954126905888364,0.5839188134270101,0.08116368898010201,0.5870967741935484,0.08374118991665719 +flat_mae,patch,logistic,adni_ad_vs_cn,21,0.3593813663804626,train,0.981029810298103,0.006942433577590784,0.9726796763445977,0.010351487740876648,0.9593023255813953,0.014893941803087169 +flat_mae,patch,logistic,adni_ad_vs_cn,21,0.3593813663804626,test,0.8292682926829268,0.0535663065453145,0.7402714932126697,0.09223826412467516,0.717741935483871,0.08717811130398902 +flat_mae,patch,logistic,adni_ad_vs_cn,22,0.046415888336127774,train,0.8915989159891599,0.013635649943834535,0.8292299148463532,0.0242487913983376,0.7957720437176432,0.02603092386322289 +flat_mae,patch,logistic,adni_ad_vs_cn,22,0.046415888336127774,test,0.8048780487804879,0.04140380219746612,0.6554621848739496,0.09106376774598174,0.6338709677419355,0.07195598319229343 +flat_mae,patch,logistic,adni_ad_vs_cn,23,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,23,21.54434690031882,test,0.7073170731707317,0.06703246658480198,0.646551724137931,0.07565502867621048,0.6709677419354838,0.0844464299525905 +flat_mae,patch,logistic,adni_ad_vs_cn,24,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,24,2.782559402207126,test,0.6341463414634146,0.0735514485646662,0.5684210526315789,0.07897570504552442,0.5887096774193548,0.09052166055799517 +flat_mae,patch,logistic,adni_ad_vs_cn,25,0.046415888336127774,train,0.8970189701897019,0.013214064351442846,0.8394182317911132,0.022796585925185336,0.8073999506943874,0.024959267833635453 +flat_mae,patch,logistic,adni_ad_vs_cn,25,0.046415888336127774,test,0.7804878048780488,0.058989628949645836,0.6917293233082706,0.08394913966393933,0.685483870967742,0.08423795541294912 +flat_mae,patch,logistic,adni_ad_vs_cn,26,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,26,2.782559402207126,test,0.6829268292682927,0.06894246624967622,0.5839188134270101,0.08537130341765903,0.5870967741935484,0.08817039009727896 +flat_mae,patch,logistic,adni_ad_vs_cn,27,0.3593813663804626,train,0.975609756097561,0.007471666110306775,0.9645665510802881,0.011311687454200029,0.9476744186046512,0.016029330201762754 +flat_mae,patch,logistic,adni_ad_vs_cn,27,0.3593813663804626,test,0.7560975609756098,0.05260463921202205,0.6117424242424243,0.08767482136925565,0.6016129032258064,0.07527863026661616 +flat_mae,patch,logistic,adni_ad_vs_cn,28,10000.0,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,28,10000.0,test,0.7073170731707317,0.06438083818960755,0.6272727272727273,0.08016920158524264,0.6370967741935484,0.0865428625315276 +flat_mae,patch,logistic,adni_ad_vs_cn,29,0.3593813663804626,train,0.975609756097561,0.0076671911237503445,0.9645665510802881,0.011612570065511894,0.9476744186046512,0.016448799561999246 +flat_mae,patch,logistic,adni_ad_vs_cn,29,0.3593813663804626,test,0.7804878048780488,0.06161182237811127,0.7119437939110069,0.07968144367447959,0.7193548387096774,0.08398900992225782 +flat_mae,patch,logistic,adni_ad_vs_cn,30,0.046415888336127774,train,0.9024390243902439,0.013312883385501337,0.8446969696969697,0.02395394744920863,0.8068863505629058,0.02610098193901376 +flat_mae,patch,logistic,adni_ad_vs_cn,30,0.046415888336127774,test,0.7804878048780488,0.050243902439024386,0.6328358208955224,0.09830568285539709,0.6177419354838709,0.07942186102279813 +flat_mae,patch,logistic,adni_ad_vs_cn,31,0.046415888336127774,train,0.9024390243902439,0.01392842571445379,0.8463069233617179,0.025069113118698742,0.8109335195989811,0.02764571478238745 +flat_mae,patch,logistic,adni_ad_vs_cn,31,0.046415888336127774,test,0.7073170731707317,0.054151263234891965,0.5340909090909092,0.08344762194521764,0.535483870967742,0.07044882209703383 +flat_mae,patch,logistic,adni_ad_vs_cn,32,0.3593813663804626,train,0.983739837398374,0.006297300649956612,0.9768796992481203,0.009156028590685374,0.9691634481058427,0.012619029837098927 +flat_mae,patch,logistic,adni_ad_vs_cn,32,0.3593813663804626,test,0.6341463414634146,0.07172364174557003,0.5467943994104643,0.0818822938227026,0.5548387096774194,0.0889289149527431 +flat_mae,patch,logistic,adni_ad_vs_cn,33,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,33,21.54434690031882,test,0.6585365853658537,0.06888530328686417,0.6203703703703703,0.06995988598780206,0.6725806451612903,0.08096175944997869 +flat_mae,patch,logistic,adni_ad_vs_cn,34,0.046415888336127774,train,0.8943089430894309,0.013744838546103083,0.8326335988835263,0.024987105129309843,0.79753882816994,0.027084218354260406 +flat_mae,patch,logistic,adni_ad_vs_cn,34,0.046415888336127774,test,0.6829268292682927,0.06576527040312172,0.5547201336675021,0.08772111916923223,0.5532258064516129,0.08439668363221713 +flat_mae,patch,logistic,adni_ad_vs_cn,35,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,35,21.54434690031882,test,0.7317073170731707,0.056580655817430374,0.5918552036199095,0.08652895550745775,0.5854838709677419,0.07780222959710703 +flat_mae,patch,logistic,adni_ad_vs_cn,36,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,36,166.81005372000556,test,0.7073170731707317,0.0643953434787715,0.603225806451613,0.08147511668477317,0.603225806451613,0.08340816630303881 +flat_mae,patch,logistic,adni_ad_vs_cn,37,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,37,1291.5496650148827,test,0.5853658536585366,0.07290910952028593,0.4863669859985261,0.07600678844975386,0.4887096774193548,0.08292034535177133 +flat_mae,patch,logistic,adni_ad_vs_cn,38,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,38,2.782559402207126,test,0.6829268292682927,0.07056732791586351,0.6072218128224024,0.08106557793297316,0.6209677419354839,0.08784478145884676 +flat_mae,patch,logistic,adni_ad_vs_cn,39,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,39,166.81005372000556,test,0.6341463414634146,0.07053413955210441,0.5199063231850116,0.08220560265527836,0.5209677419354839,0.08569173577192014 +flat_mae,patch,logistic,adni_ad_vs_cn,40,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,40,2.782559402207126,test,0.5853658536585366,0.07495672358414526,0.5108771929824562,0.07684993483535087,0.5225806451612903,0.08738993934337708 +flat_mae,patch,logistic,adni_ad_vs_cn,41,0.3593813663804626,train,0.975609756097561,0.007884202436286444,0.9645665510802881,0.011967142454230495,0.9476744186046512,0.016914364529009837 +flat_mae,patch,logistic,adni_ad_vs_cn,41,0.3593813663804626,test,0.7560975609756098,0.06430859568425995,0.6893939393939394,0.07795158247576858,0.7032258064516128,0.0842231820300035 +flat_mae,patch,logistic,adni_ad_vs_cn,42,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,42,2.782559402207126,test,0.6829268292682927,0.07249502639404916,0.6072218128224024,0.0822553501609299,0.6209677419354839,0.0893328152665902 +flat_mae,patch,logistic,adni_ad_vs_cn,43,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,43,21.54434690031882,test,0.7317073170731707,0.06571808990581307,0.6479313036690086,0.08326368998639433,0.6532258064516129,0.08779642965014701 +flat_mae,patch,logistic,adni_ad_vs_cn,44,0.046415888336127774,train,0.8997289972899729,0.013403366651195762,0.8395369336545807,0.0248129868510246,0.8010723970745337,0.026833372512988795 +flat_mae,patch,logistic,adni_ad_vs_cn,44,0.046415888336127774,test,0.8536585365853658,0.04670967961929116,0.7670454545454546,0.08716572322220954,0.7338709677419355,0.08417058863804706 +flat_mae,patch,logistic,adni_ad_vs_cn,45,0.046415888336127774,train,0.8915989159891599,0.014177974993608816,0.825597882597599,0.026394604377145827,0.7876777056454927,0.02824781825024379 +flat_mae,patch,logistic,adni_ad_vs_cn,45,0.046415888336127774,test,0.8048780487804879,0.0540173369838287,0.7152777777777778,0.08361425902776974,0.7016129032258065,0.08186764088667532 +flat_mae,patch,logistic,adni_ad_vs_cn,46,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,46,1291.5496650148827,test,0.8048780487804879,0.05924921905272777,0.7354838709677419,0.08104807341190313,0.7354838709677419,0.08507103746394837 +flat_mae,patch,logistic,adni_ad_vs_cn,47,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,47,2.782559402207126,test,0.7317073170731707,0.06355217729195817,0.6232247284878863,0.0875626902848416,0.6193548387096774,0.08629315491281735 +flat_mae,patch,logistic,adni_ad_vs_cn,48,0.046415888336127774,train,0.9024390243902439,0.013405602061860623,0.8463069233617179,0.023764960938614046,0.8109335195989811,0.026203571117965226 +flat_mae,patch,logistic,adni_ad_vs_cn,48,0.046415888336127774,test,0.7073170731707317,0.0613622667531333,0.5729166666666666,0.08814433639264842,0.5693548387096774,0.0836171152737366 +flat_mae,patch,logistic,adni_ad_vs_cn,49,0.3593813663804626,train,0.978319783197832,0.0071952602582413,0.9686411149825784,0.010801353072518428,0.9534883720930232,0.015436343228436228 +flat_mae,patch,logistic,adni_ad_vs_cn,49,0.3593813663804626,test,0.7073170731707317,0.056119274694765145,0.5340909090909092,0.08723935507128132,0.535483870967742,0.07319931842935679 +flat_mae,patch,logistic,adni_ad_vs_cn,50,0.046415888336127774,train,0.8970189701897019,0.014152959234558378,0.8394182317911132,0.024537535284881527,0.8073999506943874,0.026607938062269697 +flat_mae,patch,logistic,adni_ad_vs_cn,50,0.046415888336127774,test,0.7560975609756098,0.06370507596999357,0.6693548387096775,0.08417992824356524,0.6693548387096775,0.08346240007840076 +flat_mae,patch,logistic,adni_ad_vs_cn,51,0.046415888336127774,train,0.8997289972899729,0.013675924536759318,0.8444297580930026,0.02334593989882821,0.8132139041827595,0.025330093901179015 +flat_mae,patch,logistic,adni_ad_vs_cn,51,0.046415888336127774,test,0.6097560975609756,0.06753973426759641,0.47096774193548385,0.07536868643673575,0.47096774193548385,0.07576051999015014 +flat_mae,patch,logistic,adni_ad_vs_cn,52,0.046415888336127774,train,0.9051490514905149,0.013357191072962375,0.851341551849166,0.023609199010242374,0.8167474730873532,0.026326871774579437 +flat_mae,patch,logistic,adni_ad_vs_cn,52,0.046415888336127774,test,0.7317073170731707,0.061126369723305735,0.6232247284878863,0.08456889738255485,0.6193548387096774,0.0828768701673808 +flat_mae,patch,logistic,adni_ad_vs_cn,53,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,53,2.782559402207126,test,0.7317073170731707,0.06739832494824974,0.6479313036690086,0.08671539994701721,0.6532258064516129,0.08989287525634185 +flat_mae,patch,logistic,adni_ad_vs_cn,54,0.046415888336127774,train,0.8970189701897019,0.013023336865761462,0.8360690235690236,0.023187041436093424,0.7993056126222369,0.024628980461373445 +flat_mae,patch,logistic,adni_ad_vs_cn,54,0.046415888336127774,test,0.7804878048780488,0.060134511130559315,0.7119437939110069,0.07946344060293192,0.7193548387096774,0.0853743958771245 +flat_mae,patch,logistic,adni_ad_vs_cn,55,0.046415888336127774,train,0.8997289972899729,0.014176834303049427,0.8428467833834041,0.024773967207890046,0.8091667351466842,0.02662371708560874 +flat_mae,patch,logistic,adni_ad_vs_cn,55,0.046415888336127774,test,0.7804878048780488,0.05940996817755268,0.6917293233082706,0.08639004208542186,0.685483870967742,0.08578346866592629 +flat_mae,patch,logistic,adni_ad_vs_cn,56,0.3593813663804626,train,0.9701897018970189,0.008175123647153577,0.9570680628272251,0.01213825950515203,0.9441408497000575,0.015834299851369537 +flat_mae,patch,logistic,adni_ad_vs_cn,56,0.3593813663804626,test,0.8048780487804879,0.06227514698644415,0.7354838709677419,0.08433290093213709,0.7354838709677419,0.08757381996811907 +flat_mae,patch,logistic,adni_ad_vs_cn,57,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,57,166.81005372000556,test,0.7073170731707317,0.0685339813757553,0.603225806451613,0.08847928655173226,0.603225806451613,0.08791437419686635 +flat_mae,patch,logistic,adni_ad_vs_cn,58,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,58,2.782559402207126,test,0.7317073170731707,0.06495793724361838,0.6232247284878863,0.08773730146357786,0.6193548387096774,0.08542786107875554 +flat_mae,patch,logistic,adni_ad_vs_cn,59,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,59,2.782559402207126,test,0.7560975609756098,0.06287838937257563,0.6693548387096775,0.08366079782021439,0.6693548387096775,0.08390836635168468 +flat_mae,patch,logistic,adni_ad_vs_cn,60,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,60,21.54434690031882,test,0.7073170731707317,0.07121849314339432,0.646551724137931,0.08181657172321756,0.6709677419354838,0.08994362646528863 +flat_mae,patch,logistic,adni_ad_vs_cn,61,0.046415888336127774,train,0.8970189701897019,0.014040974444800914,0.8394182317911132,0.02443051514811686,0.8073999506943874,0.026303647267148258 +flat_mae,patch,logistic,adni_ad_vs_cn,61,0.046415888336127774,test,0.6585365853658537,0.06329286620585334,0.5017361111111112,0.08145833201221855,0.5032258064516129,0.07500108157388706 +flat_mae,patch,logistic,adni_ad_vs_cn,62,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,62,166.81005372000556,test,0.6341463414634146,0.07159358825923892,0.5199063231850116,0.08129254222076338,0.5209677419354839,0.08325896432504232 +flat_mae,patch,logistic,adni_ad_vs_cn,63,0.046415888336127774,train,0.9105691056910569,0.01336657345576092,0.8612481626234888,0.02287364556935075,0.8283753800640973,0.025527059119816377 +flat_mae,patch,logistic,adni_ad_vs_cn,63,0.046415888336127774,test,0.7804878048780488,0.05259703929437669,0.6660633484162897,0.08475897715141065,0.6516129032258065,0.07795550907011545 +flat_mae,patch,logistic,adni_ad_vs_cn,64,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,64,166.81005372000556,test,0.6829268292682927,0.0688536369370036,0.6072218128224024,0.08065086590216966,0.6209677419354839,0.08893858349285129 +flat_mae,patch,logistic,adni_ad_vs_cn,65,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,65,166.81005372000556,test,0.7317073170731707,0.07131673951408386,0.6676492262343405,0.08277045710287861,0.6870967741935483,0.08866024869258493 +flat_mae,patch,logistic,adni_ad_vs_cn,66,0.3593813663804626,train,0.981029810298103,0.006823122799498731,0.9726796763445977,0.010189879915428824,0.9593023255813953,0.014637978564040841 +flat_mae,patch,logistic,adni_ad_vs_cn,66,0.3593813663804626,test,0.6829268292682927,0.06443034597494353,0.5547201336675021,0.08702290870940191,0.5532258064516129,0.0837075619099954 +flat_mae,patch,logistic,adni_ad_vs_cn,67,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,67,21.54434690031882,test,0.7317073170731707,0.06340073018306168,0.6232247284878863,0.09144406430218113,0.6193548387096774,0.08887898980244908 +flat_mae,patch,logistic,adni_ad_vs_cn,68,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,68,2.782559402207126,test,0.5853658536585366,0.06657805731354324,0.4558938329430133,0.07210662424128757,0.45483870967741935,0.07476544272321495 +flat_mae,patch,logistic,adni_ad_vs_cn,69,0.3593813663804626,train,0.967479674796748,0.00900520597337912,0.9525462962962963,0.013736492522335891,0.9342797271756101,0.018267825439386855 +flat_mae,patch,logistic,adni_ad_vs_cn,69,0.3593813663804626,test,0.7317073170731707,0.06645075287760997,0.6479313036690086,0.08529793288714195,0.6532258064516129,0.08801130018024544 +flat_mae,patch,logistic,adni_ad_vs_cn,70,0.046415888336127774,train,0.9051490514905149,0.013592643351849919,0.849799383613421,0.024796951458646226,0.8127003040512779,0.027318315830695314 +flat_mae,patch,logistic,adni_ad_vs_cn,70,0.046415888336127774,test,0.8292682926829268,0.03634274019691994,0.6800445930880714,0.09828328728543555,0.65,0.07450261740368588 +flat_mae,patch,logistic,adni_ad_vs_cn,71,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,71,21.54434690031882,test,0.5609756097560976,0.06653620985517382,0.40483870967741936,0.05861580892879866,0.40483870967741936,0.06139833741779247 +flat_mae,patch,logistic,adni_ad_vs_cn,72,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,72,166.81005372000556,test,0.6097560975609756,0.06015271067892623,0.4305555555555556,0.06351100364018782,0.43709677419354837,0.06115945442664469 +flat_mae,patch,logistic,adni_ad_vs_cn,73,0.046415888336127774,train,0.8970189701897019,0.013090228728904172,0.8360690235690236,0.0238404654108807,0.7993056126222369,0.025802127192699018 +flat_mae,patch,logistic,adni_ad_vs_cn,73,0.046415888336127774,test,0.7804878048780488,0.05663099505948771,0.6660633484162897,0.08968484878563565,0.6516129032258065,0.08147808576505443 +flat_mae,patch,logistic,adni_ad_vs_cn,74,0.005994842503189409,train,0.8292682926829268,0.013783192503571665,0.6844055877601445,0.03360170013280626,0.6539567754129345,0.027056866337417915 +flat_mae,patch,logistic,adni_ad_vs_cn,74,0.005994842503189409,test,0.7317073170731707,0.02680992650920385,0.4225352112676056,0.009132940949010071,0.4838709677419355,0.01772914494963481 +flat_mae,patch,logistic,adni_ad_vs_cn,75,0.046415888336127774,train,0.907859078590786,0.013078517784559688,0.8577551020408163,0.02218880374164146,0.8266085956118004,0.02494447898113027 +flat_mae,patch,logistic,adni_ad_vs_cn,75,0.046415888336127774,test,0.7560975609756098,0.05997046665576459,0.6440972222222222,0.089672091373048,0.635483870967742,0.08562253750152346 +flat_mae,patch,logistic,adni_ad_vs_cn,76,0.3593813663804626,train,0.981029810298103,0.006873697265893914,0.9729123189697663,0.010067285908437886,0.9633494946174705,0.013862098656190763 +flat_mae,patch,logistic,adni_ad_vs_cn,76,0.3593813663804626,test,0.6585365853658537,0.06526419105563433,0.5651515151515152,0.07903395197028419,0.5709677419354839,0.0839293133905066 +flat_mae,patch,logistic,adni_ad_vs_cn,77,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,77,2.782559402207126,test,0.8292682926829268,0.050914562582102474,0.7402714932126697,0.08707617304855449,0.717741935483871,0.08279121339616144 +flat_mae,patch,logistic,adni_ad_vs_cn,78,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,78,2.782559402207126,test,0.6829268292682927,0.0742845150291179,0.6072218128224024,0.08322149551173999,0.6209677419354839,0.08916571017475126 +flat_mae,patch,logistic,adni_ad_vs_cn,79,0.3593813663804626,train,0.9728997289972899,0.00838540192071173,0.9608013937282229,0.012588973328125039,0.9459076341523543,0.016965935195875748 +flat_mae,patch,logistic,adni_ad_vs_cn,79,0.3593813663804626,test,0.7804878048780488,0.06605481472597623,0.7410526315789474,0.070629114778351,0.7870967741935484,0.07326995429146282 +flat_mae,patch,logistic,adni_ad_vs_cn,80,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,80,2.782559402207126,test,0.7317073170731707,0.06054039806393282,0.5918552036199095,0.09250033007801402,0.5854838709677419,0.08206741188591514 +flat_mae,patch,logistic,adni_ad_vs_cn,81,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,81,21.54434690031882,test,0.6829268292682927,0.05941807831741083,0.5176470588235295,0.08159289863990833,0.5193548387096775,0.07284185048515708 +flat_mae,patch,logistic,adni_ad_vs_cn,82,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,82,2.782559402207126,test,0.6585365853658537,0.059312961186100716,0.5017361111111112,0.07892151995114707,0.5032258064516129,0.07348055615735764 +flat_mae,patch,logistic,adni_ad_vs_cn,83,0.3593813663804626,train,0.9728997289972899,0.007792332208161614,0.9608013937282229,0.011661791671068691,0.9459076341523543,0.01586693713514841 +flat_mae,patch,logistic,adni_ad_vs_cn,83,0.3593813663804626,test,0.7804878048780488,0.054211430884532855,0.6660633484162897,0.08974645928826613,0.6516129032258065,0.08163921920488298 +flat_mae,patch,logistic,adni_ad_vs_cn,84,0.046415888336127774,train,0.8997289972899729,0.013160248764032973,0.8378060515342671,0.02441790240393755,0.7970252280384584,0.026258705320700827 +flat_mae,patch,logistic,adni_ad_vs_cn,84,0.046415888336127774,test,0.7560975609756098,0.056394041563403205,0.6117424242424243,0.09422002694866369,0.6016129032258064,0.0810377162611078 +flat_mae,patch,logistic,adni_ad_vs_cn,85,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,85,166.81005372000556,test,0.8536585365853658,0.05301815207768281,0.8136363636363637,0.06626184003472495,0.8354838709677419,0.07026852020899634 +flat_mae,patch,logistic,adni_ad_vs_cn,86,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,86,166.81005372000556,test,0.6585365853658537,0.06989498368835037,0.5876436781609196,0.07937872967426757,0.6048387096774194,0.08857187390494986 +flat_mae,patch,logistic,adni_ad_vs_cn,87,0.046415888336127774,train,0.8943089430894309,0.013232149614411083,0.8308632543926662,0.02397260279650031,0.7934916591338648,0.025626683626490548 +flat_mae,patch,logistic,adni_ad_vs_cn,87,0.046415888336127774,test,0.8048780487804879,0.04203426267401966,0.6554621848739496,0.09628466855319083,0.6338709677419355,0.07450442416100506 +flat_mae,patch,logistic,adni_ad_vs_cn,88,0.3593813663804626,train,0.9728997289972899,0.008324361619043097,0.9608013937282229,0.012512301257846385,0.9459076341523543,0.016988609088099585 +flat_mae,patch,logistic,adni_ad_vs_cn,88,0.3593813663804626,test,0.7073170731707317,0.0655260323544876,0.603225806451613,0.08655025004224037,0.603225806451613,0.08804815273946674 +flat_mae,patch,logistic,adni_ad_vs_cn,89,0.046415888336127774,train,0.8915989159891599,0.013544205748593847,0.8292299148463532,0.024128136502523056,0.7957720437176432,0.025742696539170384 +flat_mae,patch,logistic,adni_ad_vs_cn,89,0.046415888336127774,test,0.7317073170731707,0.05917093278070916,0.5918552036199095,0.09071309694933379,0.5854838709677419,0.0810339743885422 +flat_mae,patch,logistic,adni_ad_vs_cn,90,0.046415888336127774,train,0.907859078590786,0.01367923218081881,0.8548454276194002,0.02430089074758205,0.81851425753965,0.026749349887215074 +flat_mae,patch,logistic,adni_ad_vs_cn,90,0.046415888336127774,test,0.8048780487804879,0.060087661522328285,0.7354838709677419,0.08020331566824455,0.7354838709677419,0.08181907523188102 +flat_mae,patch,logistic,adni_ad_vs_cn,91,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,91,2.782559402207126,test,0.6585365853658537,0.07108793391710033,0.5370967741935484,0.08476688889466748,0.5370967741935484,0.08488491321286161 +flat_mae,patch,logistic,adni_ad_vs_cn,92,0.3593813663804626,train,0.986449864498645,0.005866439424590431,0.9808134274809954,0.008421457730391263,0.9749774015942148,0.011124155409484615 +flat_mae,patch,logistic,adni_ad_vs_cn,92,0.3593813663804626,test,0.6585365853658537,0.07091272044059192,0.5370967741935484,0.08645184894296147,0.5370967741935484,0.08721515252744225 +flat_mae,patch,logistic,adni_ad_vs_cn,93,0.046415888336127774,train,0.9132791327913279,0.012423071644015748,0.8647732478240953,0.021516270622148614,0.8301421645163941,0.02426373053651609 +flat_mae,patch,logistic,adni_ad_vs_cn,93,0.046415888336127774,test,0.6585365853658537,0.07544149649376211,0.5876436781609196,0.08415153984134682,0.6048387096774194,0.09395774040657903 +flat_mae,patch,logistic,adni_ad_vs_cn,94,0.3593813663804626,train,0.981029810298103,0.0070317365145335054,0.9729123189697663,0.010253500889576786,0.9633494946174705,0.01370340488086221 +flat_mae,patch,logistic,adni_ad_vs_cn,94,0.3593813663804626,test,0.6341463414634146,0.0702210498056816,0.5199063231850116,0.08006364729766992,0.5209677419354839,0.08169757248949555 +flat_mae,patch,logistic,adni_ad_vs_cn,95,0.046415888336127774,train,0.9024390243902439,0.013745166619347141,0.850862223818933,0.022948751879812185,0.8230750267072069,0.02566292572540467 +flat_mae,patch,logistic,adni_ad_vs_cn,95,0.046415888336127774,test,0.7804878048780488,0.05387177143260957,0.6660633484162897,0.0877702711754316,0.6516129032258065,0.08079938646597408 +flat_mae,patch,logistic,adni_ad_vs_cn,96,0.3593813663804626,train,0.978319783197832,0.007178910382748355,0.9686411149825784,0.010799253659931249,0.9534883720930232,0.015401267042058927 +flat_mae,patch,logistic,adni_ad_vs_cn,96,0.3593813663804626,test,0.7073170731707317,0.058972684468191615,0.5729166666666666,0.0854977489043364,0.5693548387096774,0.07984730817171277 +flat_mae,patch,logistic,adni_ad_vs_cn,97,0.046415888336127774,train,0.8861788617886179,0.013313818975838176,0.816877776727479,0.02428496975597056,0.7800969677048237,0.02520213140963851 +flat_mae,patch,logistic,adni_ad_vs_cn,97,0.046415888336127774,test,0.8048780487804879,0.04971485617448502,0.6893939393939394,0.0906084807522974,0.667741935483871,0.08111138934693328 +flat_mae,patch,logistic,adni_ad_vs_cn,98,0.046415888336127774,train,0.8970189701897019,0.013883449526459193,0.8394182317911132,0.023824412465347857,0.8073999506943874,0.025544736564989956 +flat_mae,patch,logistic,adni_ad_vs_cn,98,0.046415888336127774,test,0.7560975609756098,0.055315868701129686,0.6117424242424243,0.09512647865405739,0.6016129032258064,0.08111358385592474 +flat_mae,patch,logistic,adni_ad_vs_cn,99,0.046415888336127774,train,0.9105691056910569,0.01303746804540142,0.8612481626234888,0.02231344426249228,0.8283753800640973,0.024771338409605118 +flat_mae,patch,logistic,adni_ad_vs_cn,99,0.046415888336127774,test,0.8048780487804879,0.05022398373819231,0.6893939393939394,0.09415223515022882,0.667741935483871,0.08252877976872348 +flat_mae,patch,logistic,adni_ad_vs_cn,100,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,100,166.81005372000556,test,0.6829268292682927,0.06589671582449683,0.5839188134270101,0.08042563182654325,0.5870967741935484,0.08440446175038074 diff --git a/input_space_v3/flat_lr1e-3_1/eval_v2/adni_ad_vs_cn__patch__logistic/log.txt b/input_space_v3/flat_lr1e-3_1/eval_v2/adni_ad_vs_cn__patch__logistic/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..b7a035b9d2c30c451c52928dd3ab2cb0e59c8d51 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_1/eval_v2/adni_ad_vs_cn__patch__logistic/log.txt @@ -0,0 +1,240 @@ +fMRI foundation model logistic probe eval +version: 0.1.dev86+gf97f52698 +sha: bcce2b486277d3a5b520775efd9cdf1a2affce36, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-04-08 21:56:54 +config: +output_root: experiments/input_space_v3/output +name_prefix: eval_logistic +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_1; eval v2 (adni_ad_vs_cn patch logistic) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: input_space_v3/flat_lr1e-3_1/eval_v2/adni_ad_vs_cn__patch__logistic +model: flat_mae +representation: patch +dataset: adni_ad_vs_cn +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/adni_ad_vs_cn__patch__logistic +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=True, reg_tokens=0, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: adni_ad_vs_cn (flat) +train (n=328): +ADNIDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'bold', 'mean', 'std'], + num_rows: 525 +}), + labels=[0 1], + counts=[251 77] +) + +validation (n=41): +ADNIDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'bold', 'mean', 'std'], + num_rows: 66 +}), + labels=[0 1], + counts=[31 10] +) + +test (n=41): +ADNIDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'bold', 'mean', 'std'], + num_rows: 66 +}), + labels=[0 1], + counts=[32 9] +) + +extracting features for all splits +extract (train) [ 0/164] eta: 0:14:00 time: 5.1222 data: 4.0133 max mem: 2698 +extract (train) [ 20/164] eta: 0:01:06 time: 0.2304 data: 0.0810 max mem: 2851 +extract (train) [ 40/164] eta: 0:00:41 time: 0.1936 data: 0.0644 max mem: 2851 +extract (train) [ 60/164] eta: 0:00:29 time: 0.1996 data: 0.0677 max mem: 2851 +extract (train) [ 80/164] eta: 0:00:22 time: 0.1968 data: 0.0653 max mem: 2851 +extract (train) [100/164] eta: 0:00:16 time: 0.1979 data: 0.0677 max mem: 2851 +extract (train) [120/164] eta: 0:00:10 time: 0.1846 data: 0.0595 max mem: 2851 +extract (train) [140/164] eta: 0:00:05 time: 0.1907 data: 0.0611 max mem: 2851 +extract (train) [160/164] eta: 0:00:00 time: 0.1711 data: 0.0528 max mem: 2851 +extract (train) [163/164] eta: 0:00:00 time: 0.1696 data: 0.0520 max mem: 2851 +extract (train) Total time: 0:00:37 (0.2278 s / it) +extract (validation) [ 0/21] eta: 0:01:28 time: 4.2132 data: 4.0724 max mem: 2851 +extract (validation) [20/21] eta: 0:00:00 time: 0.1771 data: 0.0525 max mem: 2851 +extract (validation) Total time: 0:00:08 (0.3847 s / it) +extract (test) [ 0/21] eta: 0:01:29 time: 4.2608 data: 4.1023 max mem: 2851 +extract (test) [20/21] eta: 0:00:00 time: 0.1787 data: 0.0548 max mem: 2851 +extract (test) Total time: 0:00:08 (0.3896 s / it) +feature extraction time: 0:00:53 +train features: (328, 768) +validation features: (41, 768) +test features: (41, 768) +evaluating fixed splits +eval results (fixed splits): + +| model | repr | clf | dataset | trial | C | split | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:--------------|:--------|---------:|:--------|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | adni_ad_vs_cn | | 0.046416 | train | 0.89431 | 0.013155 | 0.83263 | 0.02398 | 0.79573 | 0.025646 | +| flat_mae | patch | logistic | adni_ad_vs_cn | | 0.046416 | test | 0.70732 | 0.052426 | 0.48319 | 0.073524 | 0.49306 | 0.061249 | + + +evaluating random splits (n=100) +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 1, "C": 166.81005372000556, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.06515722074056064, "f1": 0.6693548387096775, "f1_std": 0.08803415619871047, "bacc": 0.6693548387096775, "bacc_std": 0.08953103967650945} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 2, "C": 1291.5496650148827, "split": "test", "acc": 0.5609756097560976, "acc_std": 0.07416910754471685, "f1": 0.4698275862068966, "f1_std": 0.07829002134488994, "bacc": 0.4725806451612903, "bacc_std": 0.08771713234580747} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 3, "C": 0.005994842503189409, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.033612694126248586, "f1": 0.4142857142857143, "f1_std": 0.011738306189410555, "bacc": 0.46774193548387094, "bacc_std": 0.0222277493415515} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 4, "C": 0.046415888336127774, "split": "test", "acc": 0.9024390243902439, "acc_std": 0.04474771636817422, "f1": 0.8677419354838709, "f1_std": 0.06160546677306388, "bacc": 0.8677419354838709, "bacc_std": 0.06727208672581347} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 5, "C": 0.046415888336127774, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.038890012542428784, "f1": 0.4972129319955407, "f1_std": 0.07400447039176034, "bacc": 0.5177419354838709, "bacc_std": 0.05207380738137465} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 6, "C": 0.046415888336127774, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.04044590838461307, "f1": 0.5886287625418061, "f1_std": 0.09571751245706862, "bacc": 0.5838709677419355, "bacc_std": 0.06846762027421843} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 7, "C": 0.3593813663804626, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.06668096416188503, "f1": 0.6479313036690086, "f1_std": 0.08370977998850171, "bacc": 0.6532258064516129, "bacc_std": 0.08666487531834224} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 8, "C": 0.046415888336127774, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.046104425866434214, "f1": 0.569327731092437, "f1_std": 0.08794904797292388, "bacc": 0.567741935483871, "bacc_std": 0.06707625453912046} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 9, "C": 21.54434690031882, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.06859105551808536, "f1": 0.6676492262343405, "f1_std": 0.08106773095033465, "bacc": 0.6870967741935483, "bacc_std": 0.08777337814229258} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 10, "C": 0.3593813663804626, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.0544354181863531, "f1": 0.6117424242424243, "f1_std": 0.09227366159043424, "bacc": 0.6016129032258064, "bacc_std": 0.07936655538993802} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 11, "C": 0.046415888336127774, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.04478513711982098, "f1": 0.569327731092437, "f1_std": 0.08593076971213748, "bacc": 0.567741935483871, "bacc_std": 0.06454589764830765} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 12, "C": 0.046415888336127774, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.058513084713497, "f1": 0.5918552036199095, "f1_std": 0.09090050300189824, "bacc": 0.5854838709677419, "bacc_std": 0.08131503535008414} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 13, "C": 0.046415888336127774, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.05297830474212248, "f1": 0.6117424242424243, "f1_std": 0.09154118185961335, "bacc": 0.6016129032258064, "bacc_std": 0.0790807761540565} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 14, "C": 2.782559402207126, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.06587849576789148, "f1": 0.6893939393939394, "f1_std": 0.08022474946105645, "bacc": 0.7032258064516128, "bacc_std": 0.0855511031413346} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 15, "C": 2.782559402207126, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.060457329065346954, "f1": 0.6232247284878863, "f1_std": 0.08746409539628443, "bacc": 0.6193548387096774, "bacc_std": 0.08706508384043236} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 16, "C": 21.54434690031882, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.06355592140584998, "f1": 0.5729166666666666, "f1_std": 0.0882387013628753, "bacc": 0.5693548387096774, "bacc_std": 0.08194757156201489} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 17, "C": 21.54434690031882, "split": "test", "acc": 0.6341463414634146, "acc_std": 0.06545679876423556, "f1": 0.48621553884711777, "f1_std": 0.07825069210182156, "bacc": 0.48709677419354835, "bacc_std": 0.0747229998150018} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 18, "C": 0.005994842503189409, "split": "test", "acc": 0.8292682926829268, "acc_std": 0.03574528169693307, "f1": 0.6800445930880714, "f1_std": 0.09742890175980444, "bacc": 0.65, "bacc_std": 0.07327782747871281} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 19, "C": 1291.5496650148827, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.06328624902680995, "f1": 0.7119437939110069, "f1_std": 0.08170162845182061, "bacc": 0.7193548387096774, "bacc_std": 0.08583050469326219} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 20, "C": 0.3593813663804626, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.06954126905888364, "f1": 0.5839188134270101, "f1_std": 0.08116368898010201, "bacc": 0.5870967741935484, "bacc_std": 0.08374118991665719} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 21, "C": 0.3593813663804626, "split": "test", "acc": 0.8292682926829268, "acc_std": 0.0535663065453145, "f1": 0.7402714932126697, "f1_std": 0.09223826412467516, "bacc": 0.717741935483871, "bacc_std": 0.08717811130398902} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 22, "C": 0.046415888336127774, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.04140380219746612, "f1": 0.6554621848739496, "f1_std": 0.09106376774598174, "bacc": 0.6338709677419355, "bacc_std": 0.07195598319229343} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 23, "C": 21.54434690031882, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.06703246658480198, "f1": 0.646551724137931, "f1_std": 0.07565502867621048, "bacc": 0.6709677419354838, "bacc_std": 0.0844464299525905} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 24, "C": 2.782559402207126, "split": "test", "acc": 0.6341463414634146, "acc_std": 0.0735514485646662, "f1": 0.5684210526315789, "f1_std": 0.07897570504552442, "bacc": 0.5887096774193548, "bacc_std": 0.09052166055799517} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 25, "C": 0.046415888336127774, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.058989628949645836, "f1": 0.6917293233082706, "f1_std": 0.08394913966393933, "bacc": 0.685483870967742, "bacc_std": 0.08423795541294912} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 26, "C": 2.782559402207126, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.06894246624967622, "f1": 0.5839188134270101, "f1_std": 0.08537130341765903, "bacc": 0.5870967741935484, "bacc_std": 0.08817039009727896} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 27, "C": 0.3593813663804626, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.05260463921202205, "f1": 0.6117424242424243, "f1_std": 0.08767482136925565, "bacc": 0.6016129032258064, "bacc_std": 0.07527863026661616} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 28, "C": 10000.0, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.06438083818960755, "f1": 0.6272727272727273, "f1_std": 0.08016920158524264, "bacc": 0.6370967741935484, "bacc_std": 0.0865428625315276} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 29, "C": 0.3593813663804626, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.06161182237811127, "f1": 0.7119437939110069, "f1_std": 0.07968144367447959, "bacc": 0.7193548387096774, "bacc_std": 0.08398900992225782} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 30, "C": 0.046415888336127774, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.050243902439024386, "f1": 0.6328358208955224, "f1_std": 0.09830568285539709, "bacc": 0.6177419354838709, "bacc_std": 0.07942186102279813} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 31, "C": 0.046415888336127774, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.054151263234891965, "f1": 0.5340909090909092, "f1_std": 0.08344762194521764, "bacc": 0.535483870967742, "bacc_std": 0.07044882209703383} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 32, "C": 0.3593813663804626, "split": "test", "acc": 0.6341463414634146, "acc_std": 0.07172364174557003, "f1": 0.5467943994104643, "f1_std": 0.0818822938227026, "bacc": 0.5548387096774194, "bacc_std": 0.0889289149527431} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 33, "C": 21.54434690031882, "split": "test", "acc": 0.6585365853658537, "acc_std": 0.06888530328686417, "f1": 0.6203703703703703, "f1_std": 0.06995988598780206, "bacc": 0.6725806451612903, "bacc_std": 0.08096175944997869} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 34, "C": 0.046415888336127774, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.06576527040312172, "f1": 0.5547201336675021, "f1_std": 0.08772111916923223, "bacc": 0.5532258064516129, "bacc_std": 0.08439668363221713} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 35, "C": 21.54434690031882, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.056580655817430374, "f1": 0.5918552036199095, "f1_std": 0.08652895550745775, "bacc": 0.5854838709677419, "bacc_std": 0.07780222959710703} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 36, "C": 166.81005372000556, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.0643953434787715, "f1": 0.603225806451613, "f1_std": 0.08147511668477317, "bacc": 0.603225806451613, "bacc_std": 0.08340816630303881} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 37, "C": 1291.5496650148827, "split": "test", "acc": 0.5853658536585366, "acc_std": 0.07290910952028593, "f1": 0.4863669859985261, "f1_std": 0.07600678844975386, "bacc": 0.4887096774193548, "bacc_std": 0.08292034535177133} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 38, "C": 2.782559402207126, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.07056732791586351, "f1": 0.6072218128224024, "f1_std": 0.08106557793297316, "bacc": 0.6209677419354839, "bacc_std": 0.08784478145884676} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 39, "C": 166.81005372000556, "split": "test", "acc": 0.6341463414634146, "acc_std": 0.07053413955210441, "f1": 0.5199063231850116, "f1_std": 0.08220560265527836, "bacc": 0.5209677419354839, "bacc_std": 0.08569173577192014} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 40, "C": 2.782559402207126, "split": "test", "acc": 0.5853658536585366, "acc_std": 0.07495672358414526, "f1": 0.5108771929824562, "f1_std": 0.07684993483535087, "bacc": 0.5225806451612903, "bacc_std": 0.08738993934337708} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 41, "C": 0.3593813663804626, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.06430859568425995, "f1": 0.6893939393939394, "f1_std": 0.07795158247576858, "bacc": 0.7032258064516128, "bacc_std": 0.0842231820300035} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 42, "C": 2.782559402207126, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.07249502639404916, "f1": 0.6072218128224024, "f1_std": 0.0822553501609299, "bacc": 0.6209677419354839, "bacc_std": 0.0893328152665902} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 43, "C": 21.54434690031882, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.06571808990581307, "f1": 0.6479313036690086, "f1_std": 0.08326368998639433, "bacc": 0.6532258064516129, "bacc_std": 0.08779642965014701} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 44, "C": 0.046415888336127774, "split": "test", "acc": 0.8536585365853658, "acc_std": 0.04670967961929116, "f1": 0.7670454545454546, "f1_std": 0.08716572322220954, "bacc": 0.7338709677419355, "bacc_std": 0.08417058863804706} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 45, "C": 0.046415888336127774, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.0540173369838287, "f1": 0.7152777777777778, "f1_std": 0.08361425902776974, "bacc": 0.7016129032258065, "bacc_std": 0.08186764088667532} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 46, "C": 1291.5496650148827, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.05924921905272777, "f1": 0.7354838709677419, "f1_std": 0.08104807341190313, "bacc": 0.7354838709677419, "bacc_std": 0.08507103746394837} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 47, "C": 2.782559402207126, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.06355217729195817, "f1": 0.6232247284878863, "f1_std": 0.0875626902848416, "bacc": 0.6193548387096774, "bacc_std": 0.08629315491281735} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 48, "C": 0.046415888336127774, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.0613622667531333, "f1": 0.5729166666666666, "f1_std": 0.08814433639264842, "bacc": 0.5693548387096774, "bacc_std": 0.0836171152737366} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 49, "C": 0.3593813663804626, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.056119274694765145, "f1": 0.5340909090909092, "f1_std": 0.08723935507128132, "bacc": 0.535483870967742, "bacc_std": 0.07319931842935679} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 50, "C": 0.046415888336127774, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.06370507596999357, "f1": 0.6693548387096775, "f1_std": 0.08417992824356524, "bacc": 0.6693548387096775, "bacc_std": 0.08346240007840076} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 51, "C": 0.046415888336127774, "split": "test", "acc": 0.6097560975609756, "acc_std": 0.06753973426759641, "f1": 0.47096774193548385, "f1_std": 0.07536868643673575, "bacc": 0.47096774193548385, "bacc_std": 0.07576051999015014} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 52, "C": 0.046415888336127774, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.061126369723305735, "f1": 0.6232247284878863, "f1_std": 0.08456889738255485, "bacc": 0.6193548387096774, "bacc_std": 0.0828768701673808} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 53, "C": 2.782559402207126, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.06739832494824974, "f1": 0.6479313036690086, "f1_std": 0.08671539994701721, "bacc": 0.6532258064516129, "bacc_std": 0.08989287525634185} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 54, "C": 0.046415888336127774, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.060134511130559315, "f1": 0.7119437939110069, "f1_std": 0.07946344060293192, "bacc": 0.7193548387096774, "bacc_std": 0.0853743958771245} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 55, "C": 0.046415888336127774, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.05940996817755268, "f1": 0.6917293233082706, "f1_std": 0.08639004208542186, "bacc": 0.685483870967742, "bacc_std": 0.08578346866592629} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 56, "C": 0.3593813663804626, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.06227514698644415, "f1": 0.7354838709677419, "f1_std": 0.08433290093213709, "bacc": 0.7354838709677419, "bacc_std": 0.08757381996811907} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 57, "C": 166.81005372000556, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.0685339813757553, "f1": 0.603225806451613, "f1_std": 0.08847928655173226, "bacc": 0.603225806451613, "bacc_std": 0.08791437419686635} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 58, "C": 2.782559402207126, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.06495793724361838, "f1": 0.6232247284878863, "f1_std": 0.08773730146357786, "bacc": 0.6193548387096774, "bacc_std": 0.08542786107875554} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 59, "C": 2.782559402207126, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.06287838937257563, "f1": 0.6693548387096775, "f1_std": 0.08366079782021439, "bacc": 0.6693548387096775, "bacc_std": 0.08390836635168468} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 60, "C": 21.54434690031882, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.07121849314339432, "f1": 0.646551724137931, "f1_std": 0.08181657172321756, "bacc": 0.6709677419354838, "bacc_std": 0.08994362646528863} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 61, "C": 0.046415888336127774, "split": "test", "acc": 0.6585365853658537, "acc_std": 0.06329286620585334, "f1": 0.5017361111111112, "f1_std": 0.08145833201221855, "bacc": 0.5032258064516129, "bacc_std": 0.07500108157388706} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 62, "C": 166.81005372000556, "split": "test", "acc": 0.6341463414634146, "acc_std": 0.07159358825923892, "f1": 0.5199063231850116, "f1_std": 0.08129254222076338, "bacc": 0.5209677419354839, "bacc_std": 0.08325896432504232} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 63, "C": 0.046415888336127774, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.05259703929437669, "f1": 0.6660633484162897, "f1_std": 0.08475897715141065, "bacc": 0.6516129032258065, "bacc_std": 0.07795550907011545} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 64, "C": 166.81005372000556, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.0688536369370036, "f1": 0.6072218128224024, "f1_std": 0.08065086590216966, "bacc": 0.6209677419354839, "bacc_std": 0.08893858349285129} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 65, "C": 166.81005372000556, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.07131673951408386, "f1": 0.6676492262343405, "f1_std": 0.08277045710287861, "bacc": 0.6870967741935483, "bacc_std": 0.08866024869258493} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 66, "C": 0.3593813663804626, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.06443034597494353, "f1": 0.5547201336675021, "f1_std": 0.08702290870940191, "bacc": 0.5532258064516129, "bacc_std": 0.0837075619099954} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 67, "C": 21.54434690031882, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.06340073018306168, "f1": 0.6232247284878863, "f1_std": 0.09144406430218113, "bacc": 0.6193548387096774, "bacc_std": 0.08887898980244908} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 68, "C": 2.782559402207126, "split": "test", "acc": 0.5853658536585366, "acc_std": 0.06657805731354324, "f1": 0.4558938329430133, "f1_std": 0.07210662424128757, "bacc": 0.45483870967741935, "bacc_std": 0.07476544272321495} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 69, "C": 0.3593813663804626, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.06645075287760997, "f1": 0.6479313036690086, "f1_std": 0.08529793288714195, "bacc": 0.6532258064516129, "bacc_std": 0.08801130018024544} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 70, "C": 0.046415888336127774, "split": "test", "acc": 0.8292682926829268, "acc_std": 0.03634274019691994, "f1": 0.6800445930880714, "f1_std": 0.09828328728543555, "bacc": 0.65, "bacc_std": 0.07450261740368588} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 71, "C": 21.54434690031882, "split": "test", "acc": 0.5609756097560976, "acc_std": 0.06653620985517382, "f1": 0.40483870967741936, "f1_std": 0.05861580892879866, "bacc": 0.40483870967741936, "bacc_std": 0.06139833741779247} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 72, "C": 166.81005372000556, "split": "test", "acc": 0.6097560975609756, "acc_std": 0.06015271067892623, "f1": 0.4305555555555556, "f1_std": 0.06351100364018782, "bacc": 0.43709677419354837, "bacc_std": 0.06115945442664469} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 73, "C": 0.046415888336127774, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.05663099505948771, "f1": 0.6660633484162897, "f1_std": 0.08968484878563565, "bacc": 0.6516129032258065, "bacc_std": 0.08147808576505443} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 74, "C": 0.005994842503189409, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.02680992650920385, "f1": 0.4225352112676056, "f1_std": 0.009132940949010071, "bacc": 0.4838709677419355, "bacc_std": 0.01772914494963481} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 75, "C": 0.046415888336127774, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.05997046665576459, "f1": 0.6440972222222222, "f1_std": 0.089672091373048, "bacc": 0.635483870967742, "bacc_std": 0.08562253750152346} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 76, "C": 0.3593813663804626, "split": "test", "acc": 0.6585365853658537, "acc_std": 0.06526419105563433, "f1": 0.5651515151515152, "f1_std": 0.07903395197028419, "bacc": 0.5709677419354839, "bacc_std": 0.0839293133905066} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 77, "C": 2.782559402207126, "split": "test", "acc": 0.8292682926829268, "acc_std": 0.050914562582102474, "f1": 0.7402714932126697, "f1_std": 0.08707617304855449, "bacc": 0.717741935483871, "bacc_std": 0.08279121339616144} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 78, "C": 2.782559402207126, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.0742845150291179, "f1": 0.6072218128224024, "f1_std": 0.08322149551173999, "bacc": 0.6209677419354839, "bacc_std": 0.08916571017475126} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 79, "C": 0.3593813663804626, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.06605481472597623, "f1": 0.7410526315789474, "f1_std": 0.070629114778351, "bacc": 0.7870967741935484, "bacc_std": 0.07326995429146282} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 80, "C": 2.782559402207126, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.06054039806393282, "f1": 0.5918552036199095, "f1_std": 0.09250033007801402, "bacc": 0.5854838709677419, "bacc_std": 0.08206741188591514} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 81, "C": 21.54434690031882, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.05941807831741083, "f1": 0.5176470588235295, "f1_std": 0.08159289863990833, "bacc": 0.5193548387096775, "bacc_std": 0.07284185048515708} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 82, "C": 2.782559402207126, "split": "test", "acc": 0.6585365853658537, "acc_std": 0.059312961186100716, "f1": 0.5017361111111112, "f1_std": 0.07892151995114707, "bacc": 0.5032258064516129, "bacc_std": 0.07348055615735764} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 83, "C": 0.3593813663804626, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.054211430884532855, "f1": 0.6660633484162897, "f1_std": 0.08974645928826613, "bacc": 0.6516129032258065, "bacc_std": 0.08163921920488298} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 84, "C": 0.046415888336127774, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.056394041563403205, "f1": 0.6117424242424243, "f1_std": 0.09422002694866369, "bacc": 0.6016129032258064, "bacc_std": 0.0810377162611078} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 85, "C": 166.81005372000556, "split": "test", "acc": 0.8536585365853658, "acc_std": 0.05301815207768281, "f1": 0.8136363636363637, "f1_std": 0.06626184003472495, "bacc": 0.8354838709677419, "bacc_std": 0.07026852020899634} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 86, "C": 166.81005372000556, "split": "test", "acc": 0.6585365853658537, "acc_std": 0.06989498368835037, "f1": 0.5876436781609196, "f1_std": 0.07937872967426757, "bacc": 0.6048387096774194, "bacc_std": 0.08857187390494986} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 87, "C": 0.046415888336127774, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.04203426267401966, "f1": 0.6554621848739496, "f1_std": 0.09628466855319083, "bacc": 0.6338709677419355, "bacc_std": 0.07450442416100506} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 88, "C": 0.3593813663804626, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.0655260323544876, "f1": 0.603225806451613, "f1_std": 0.08655025004224037, "bacc": 0.603225806451613, "bacc_std": 0.08804815273946674} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 89, "C": 0.046415888336127774, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.05917093278070916, "f1": 0.5918552036199095, "f1_std": 0.09071309694933379, "bacc": 0.5854838709677419, "bacc_std": 0.0810339743885422} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 90, "C": 0.046415888336127774, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.060087661522328285, "f1": 0.7354838709677419, "f1_std": 0.08020331566824455, "bacc": 0.7354838709677419, "bacc_std": 0.08181907523188102} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 91, "C": 2.782559402207126, "split": "test", "acc": 0.6585365853658537, "acc_std": 0.07108793391710033, "f1": 0.5370967741935484, "f1_std": 0.08476688889466748, "bacc": 0.5370967741935484, "bacc_std": 0.08488491321286161} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 92, "C": 0.3593813663804626, "split": "test", "acc": 0.6585365853658537, "acc_std": 0.07091272044059192, "f1": 0.5370967741935484, "f1_std": 0.08645184894296147, "bacc": 0.5370967741935484, "bacc_std": 0.08721515252744225} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 93, "C": 0.046415888336127774, "split": "test", "acc": 0.6585365853658537, "acc_std": 0.07544149649376211, "f1": 0.5876436781609196, "f1_std": 0.08415153984134682, "bacc": 0.6048387096774194, "bacc_std": 0.09395774040657903} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 94, "C": 0.3593813663804626, "split": "test", "acc": 0.6341463414634146, "acc_std": 0.0702210498056816, "f1": 0.5199063231850116, "f1_std": 0.08006364729766992, "bacc": 0.5209677419354839, "bacc_std": 0.08169757248949555} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 95, "C": 0.046415888336127774, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.05387177143260957, "f1": 0.6660633484162897, "f1_std": 0.0877702711754316, "bacc": 0.6516129032258065, "bacc_std": 0.08079938646597408} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 96, "C": 0.3593813663804626, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.058972684468191615, "f1": 0.5729166666666666, "f1_std": 0.0854977489043364, "bacc": 0.5693548387096774, "bacc_std": 0.07984730817171277} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 97, "C": 0.046415888336127774, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.04971485617448502, "f1": 0.6893939393939394, "f1_std": 0.0906084807522974, "bacc": 0.667741935483871, "bacc_std": 0.08111138934693328} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 98, "C": 0.046415888336127774, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.055315868701129686, "f1": 0.6117424242424243, "f1_std": 0.09512647865405739, "bacc": 0.6016129032258064, "bacc_std": 0.08111358385592474} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 99, "C": 0.046415888336127774, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.05022398373819231, "f1": 0.6893939393939394, "f1_std": 0.09415223515022882, "bacc": 0.667741935483871, "bacc_std": 0.08252877976872348} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 100, "C": 166.81005372000556, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.06589671582449683, "f1": 0.5839188134270101, "f1_std": 0.08042563182654325, "bacc": 0.5870967741935484, "bacc_std": 0.08440446175038074} +eval results (random splits): + +| model | repr | clf | dataset | split | n_trials | C | C_std | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:--------------|:--------|-----------:|-------:|--------:|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | adni_ad_vs_cn | train | 100 | 172.94 | 1024.9 | 0.95634 | 0.050375 | 0.93041 | 0.083452 | 0.915 | 0.097936 | +| flat_mae | patch | logistic | adni_ad_vs_cn | test | 100 | 172.94 | 1024.9 | 0.72488 | 0.067763 | 0.61173 | 0.086161 | 0.61315 | 0.083254 | + + +done! total time: 0:05:06 diff --git a/input_space_v3/flat_lr1e-3_1/eval_v2/hcpya_task21__patch__attn/config.yaml b/input_space_v3/flat_lr1e-3_1/eval_v2/hcpya_task21__patch__attn/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..759b53108f3f100f65a2a2e690439b04f4b4c8ed --- /dev/null +++ b/input_space_v3/flat_lr1e-3_1/eval_v2/hcpya_task21__patch__attn/config.yaml @@ -0,0 +1,96 @@ +output_root: experiments/input_space_v3/output +name_prefix: eval_probe +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_1; eval v2 (hcpya_task21 patch attn) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +dataset_kwargs: {} +classifier_kwargs: + embed_dim: null + dropout: 0.0 + xavier_init: true + norm: true +lr_scale_grid: +- 0.02 +- 0.023 +- 0.028 +- 0.033 +- 0.038 +- 0.045 +- 0.053 +- 0.062 +- 0.074 +- 0.087 +- 0.1 +- 0.12 +- 0.14 +- 0.17 +- 0.2 +- 0.23 +- 0.27 +- 0.32 +- 0.38 +- 0.44 +- 0.52 +- 0.61 +- 0.72 +- 0.85 +- 1 +- 1.2 +- 1.4 +- 1.6 +- 1.9 +- 2.3 +- 2.7 +- 3.1 +- 3.7 +- 4.3 +- 5.1 +- 6 +- 7.1 +- 8.3 +- 9.8 +- 12 +- 14 +- 16 +- 19 +- 22 +- 26 +- 31 +- 36 +- 43 +- 50 +wd_scale_grid: +- 1.0 +num_workers: 8 +prefetch_factor: null +balanced_sampling: false +epochs: 20 +steps_per_epoch: 200 +batch_size: 64 +accum_iter: 2 +lr: 0.0003 +warmup_epochs: 5 +no_decay: false +weight_decay: 0.05 +clip_grad: 1.0 +metrics: +- acc +- f1 +cv_metric: acc +early_stopping: true +amp: true +device: cuda +seed: 4466 +debug: false +wandb: false +wandb_entity: null +wandb_project: fMRI-fm-eval +name: input_space_v3/flat_lr1e-3_1/eval_v2/hcpya_task21__patch__attn +model: flat_mae +representation: patch +classifier: attn +dataset: hcpya_task21 +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/hcpya_task21__patch__attn +remote_dir: null diff --git a/input_space_v3/flat_lr1e-3_1/eval_v2/hcpya_task21__patch__attn/eval_log.json b/input_space_v3/flat_lr1e-3_1/eval_v2/hcpya_task21__patch__attn/eval_log.json new file mode 100644 index 0000000000000000000000000000000000000000..9a3a5b7cc8cd8108712623f7e09ecc001e9c5472 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_1/eval_v2/hcpya_task21__patch__attn/eval_log.json @@ -0,0 +1 @@ +{"eval/epoch": 6, "eval/id_best": 29, "eval/lr_best": 0.0006899999999999999, "eval/wd_best": 0.05, "eval/train/loss": 0.009245019406080246, "eval/train/acc": 0.9978419916837729, "eval/train/acc_std": 0.0003241048510502608, "eval/train/f1": 0.997777991962027, "eval/train/f1_std": 0.00035988629098860866, "eval/validation/loss": 0.0239899680018425, "eval/validation/acc": 0.9928075396825397, "eval/validation/acc_std": 0.0013337749462061035, "eval/validation/f1": 0.991433429258681, "eval/validation/f1_std": 0.0017508155140758207, "eval/test/loss": 0.03400512412190437, "eval/test/acc": 0.9898809523809524, "eval/test/acc_std": 0.0013061241946853838, "eval/test/f1": 0.9875128178751948, "eval/test/f1_std": 0.0017798350252151167} diff --git a/input_space_v3/flat_lr1e-3_1/eval_v2/hcpya_task21__patch__attn/eval_log_best.json b/input_space_v3/flat_lr1e-3_1/eval_v2/hcpya_task21__patch__attn/eval_log_best.json new file mode 100644 index 0000000000000000000000000000000000000000..9a2daf3065851fd461391b4d0285e1a884890292 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_1/eval_v2/hcpya_task21__patch__attn/eval_log_best.json @@ -0,0 +1 @@ +{"eval/best/epoch": 6, "eval/best/id_best": 29, "eval/best/lr_best": 0.0006899999999999999, "eval/best/wd_best": 0.05, "eval/best/train/loss": 0.009245019406080246, "eval/best/train/acc": 0.9978419916837729, "eval/best/train/acc_std": 0.0003241048510502608, "eval/best/train/f1": 0.997777991962027, "eval/best/train/f1_std": 0.00035988629098860866, "eval/best/validation/loss": 0.0239899680018425, "eval/best/validation/acc": 0.9928075396825397, "eval/best/validation/acc_std": 0.0013337749462061035, "eval/best/validation/f1": 0.991433429258681, "eval/best/validation/f1_std": 0.0017508155140758207, "eval/best/test/loss": 0.03400512412190437, "eval/best/test/acc": 0.9898809523809524, "eval/best/test/acc_std": 0.0013061241946853838, "eval/best/test/f1": 0.9875128178751948, "eval/best/test/f1_std": 0.0017798350252151167} diff --git a/input_space_v3/flat_lr1e-3_1/eval_v2/hcpya_task21__patch__attn/eval_log_last.json b/input_space_v3/flat_lr1e-3_1/eval_v2/hcpya_task21__patch__attn/eval_log_last.json new file mode 100644 index 0000000000000000000000000000000000000000..7b346f70cde58a872148dd6306539bcfd6214e4d --- /dev/null +++ b/input_space_v3/flat_lr1e-3_1/eval_v2/hcpya_task21__patch__attn/eval_log_last.json @@ -0,0 +1 @@ +{"eval/last/epoch": 19, "eval/last/id_best": 29, "eval/last/lr_best": 0.0006899999999999999, "eval/last/wd_best": 0.05, "eval/last/train/loss": 0.0003940816386602819, "eval/last/train/acc": 1.0, "eval/last/train/acc_std": 0.0, "eval/last/train/f1": 1.0, "eval/last/train/f1_std": 0.0, "eval/last/validation/loss": 0.026755208149552345, "eval/last/validation/acc": 0.9920634920634921, "eval/last/validation/acc_std": 0.0014538868173273488, "eval/last/validation/f1": 0.9894658055361347, "eval/last/validation/f1_std": 0.002095601610933988, "eval/last/test/loss": 0.04119957983493805, "eval/last/test/acc": 0.9908730158730159, "eval/last/test/acc_std": 0.0012073577524927724, "eval/last/test/f1": 0.9882455953952981, "eval/last/test/f1_std": 0.0017165835441958091} diff --git a/input_space_v3/flat_lr1e-3_1/eval_v2/hcpya_task21__patch__attn/eval_table.csv b/input_space_v3/flat_lr1e-3_1/eval_v2/hcpya_task21__patch__attn/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..da106ab88aa46852815a4edcd580af0c69f43a36 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_1/eval_v2/hcpya_task21__patch__attn/eval_table.csv @@ -0,0 +1,4 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,patch,attn,hcpya_task21,best,6,0.0006899999999999999,0.05,29,"[2.3, 1.0]",train,0.009245019406080246,0.9978419916837729,0.0003241048510502608,0.997777991962027,0.00035988629098860866 +flat_mae,patch,attn,hcpya_task21,best,6,0.0006899999999999999,0.05,29,"[2.3, 1.0]",validation,0.0239899680018425,0.9928075396825397,0.0013337749462061035,0.991433429258681,0.0017508155140758207 +flat_mae,patch,attn,hcpya_task21,best,6,0.0006899999999999999,0.05,29,"[2.3, 1.0]",test,0.03400512412190437,0.9898809523809524,0.0013061241946853838,0.9875128178751948,0.0017798350252151167 diff --git a/input_space_v3/flat_lr1e-3_1/eval_v2/hcpya_task21__patch__attn/eval_table_best.csv b/input_space_v3/flat_lr1e-3_1/eval_v2/hcpya_task21__patch__attn/eval_table_best.csv new file mode 100644 index 0000000000000000000000000000000000000000..da106ab88aa46852815a4edcd580af0c69f43a36 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_1/eval_v2/hcpya_task21__patch__attn/eval_table_best.csv @@ -0,0 +1,4 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,patch,attn,hcpya_task21,best,6,0.0006899999999999999,0.05,29,"[2.3, 1.0]",train,0.009245019406080246,0.9978419916837729,0.0003241048510502608,0.997777991962027,0.00035988629098860866 +flat_mae,patch,attn,hcpya_task21,best,6,0.0006899999999999999,0.05,29,"[2.3, 1.0]",validation,0.0239899680018425,0.9928075396825397,0.0013337749462061035,0.991433429258681,0.0017508155140758207 +flat_mae,patch,attn,hcpya_task21,best,6,0.0006899999999999999,0.05,29,"[2.3, 1.0]",test,0.03400512412190437,0.9898809523809524,0.0013061241946853838,0.9875128178751948,0.0017798350252151167 diff --git a/input_space_v3/flat_lr1e-3_1/eval_v2/hcpya_task21__patch__attn/eval_table_last.csv b/input_space_v3/flat_lr1e-3_1/eval_v2/hcpya_task21__patch__attn/eval_table_last.csv new file mode 100644 index 0000000000000000000000000000000000000000..5fb1ab38ce46c7f74e1bee3c9c41165ea0928d3e --- /dev/null +++ b/input_space_v3/flat_lr1e-3_1/eval_v2/hcpya_task21__patch__attn/eval_table_last.csv @@ -0,0 +1,4 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,patch,attn,hcpya_task21,last,19,0.0006899999999999999,0.05,29,"[2.3, 1.0]",train,0.0003940816386602819,1.0,0.0,1.0,0.0 +flat_mae,patch,attn,hcpya_task21,last,19,0.0006899999999999999,0.05,29,"[2.3, 1.0]",validation,0.026755208149552345,0.9920634920634921,0.0014538868173273488,0.9894658055361347,0.002095601610933988 +flat_mae,patch,attn,hcpya_task21,last,19,0.0006899999999999999,0.05,29,"[2.3, 1.0]",test,0.04119957983493805,0.9908730158730159,0.0012073577524927724,0.9882455953952981,0.0017165835441958091 diff --git a/input_space_v3/flat_lr1e-3_1/eval_v2/hcpya_task21__patch__attn/log.txt b/input_space_v3/flat_lr1e-3_1/eval_v2/hcpya_task21__patch__attn/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..dd5f01c628c1ff6e1fd6561d5295cbd58603439b --- /dev/null +++ b/input_space_v3/flat_lr1e-3_1/eval_v2/hcpya_task21__patch__attn/log.txt @@ -0,0 +1,883 @@ +fMRI foundation model probe eval +version: 0.1.dev86+gf97f52698 +sha: bcce2b486277d3a5b520775efd9cdf1a2affce36, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-04-08 20:31:09 +config: +output_root: experiments/input_space_v3/output +name_prefix: eval_probe +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_1; eval v2 (hcpya_task21 patch attn) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +dataset_kwargs: {} +classifier_kwargs: + embed_dim: null + dropout: 0.0 + xavier_init: true + norm: true +lr_scale_grid: +- 0.02 +- 0.023 +- 0.028 +- 0.033 +- 0.038 +- 0.045 +- 0.053 +- 0.062 +- 0.074 +- 0.087 +- 0.1 +- 0.12 +- 0.14 +- 0.17 +- 0.2 +- 0.23 +- 0.27 +- 0.32 +- 0.38 +- 0.44 +- 0.52 +- 0.61 +- 0.72 +- 0.85 +- 1 +- 1.2 +- 1.4 +- 1.6 +- 1.9 +- 2.3 +- 2.7 +- 3.1 +- 3.7 +- 4.3 +- 5.1 +- 6 +- 7.1 +- 8.3 +- 9.8 +- 12 +- 14 +- 16 +- 19 +- 22 +- 26 +- 31 +- 36 +- 43 +- 50 +wd_scale_grid: +- 1.0 +num_workers: 8 +prefetch_factor: null +balanced_sampling: false +epochs: 20 +steps_per_epoch: 200 +batch_size: 64 +accum_iter: 2 +lr: 0.0003 +warmup_epochs: 5 +no_decay: false +weight_decay: 0.05 +clip_grad: 1.0 +metrics: +- acc +- f1 +cv_metric: acc +early_stopping: true +amp: true +device: cuda +seed: 4466 +debug: false +wandb: false +wandb_entity: null +wandb_project: fMRI-fm-eval +name: input_space_v3/flat_lr1e-3_1/eval_v2/hcpya_task21__patch__attn +model: flat_mae +representation: patch +classifier: attn +dataset: hcpya_task21 +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/hcpya_task21__patch__attn +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=True, reg_tokens=0, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: hcpya_task21 (flat) +train (n=18999): +HFDataset( + dataset=Dataset({ + features: ['sub', 'task', 'cond', 'cond_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 18999 +}), + labels=[ 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20], + counts=[ 832 1248 3201 1660 832 832 832 832 832 1248 1247 1243 832 416 + 416 416 416 416 416 416 416] +) + +validation (n=4032): +HFDataset( + dataset=Dataset({ + features: ['sub', 'task', 'cond', 'cond_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 4032 +}), + labels=[ 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20], + counts=[176 264 688 352 176 176 176 176 176 264 264 264 176 88 88 88 88 88 + 88 88 88] +) + +test (n=5040): +HFDataset( + dataset=Dataset({ + features: ['sub', 'task', 'cond', 'cond_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 5040 +}), + labels=[ 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20], + counts=[220 330 860 440 220 220 220 220 220 330 330 330 220 110 110 110 110 110 + 110 110 110] +) + +running backbone on example batch to get embedding dim +embedding feature dim (patch): 768 +initializing sweep of classifier heads +classifiers: +ModuleList( + (0-48): 49 x AttnPoolClassifier( + (kv): Linear(in_features=768, out_features=1536, bias=True) + (linear): Linear(in_features=768, out_features=21, bias=True) + ) +) +classifier params (train): 58.7M (58.7M) +setting up optimizer +total batch size: 128 = 64 bs per gpu x 2 accum +lr: 3.00e-04 +full schedule: epochs = 20 (steps = 4000) (decay = True) +warmup: epochs = 5 (steps = 1000) +start training for 20 epochs +train: [0] [ 0/400] eta: 0:32:58 lr: nan time: 4.9453 data: 4.3461 max mem: 21740 +train: [0] [ 20/400] eta: 0:04:22 lr: 0.000003 loss: 3.0710 (3.0762) grad: 0.2600 (0.2695) time: 0.4787 data: 0.0035 max mem: 22446 +train: [0] [ 40/400] eta: 0:03:30 lr: 0.000006 loss: 3.0239 (3.0298) grad: 0.2604 (0.2670) time: 0.4733 data: 0.0027 max mem: 22446 +train: [0] [ 60/400] eta: 0:03:05 lr: 0.000009 loss: 2.9050 (2.9706) grad: 0.2604 (0.2627) time: 0.4613 data: 0.0034 max mem: 22446 +train: [0] [ 80/400] eta: 0:02:47 lr: 0.000012 loss: 2.7826 (2.9065) grad: 0.2451 (0.2560) time: 0.4538 data: 0.0033 max mem: 22446 +train: [0] [100/400] eta: 0:02:32 lr: 0.000015 loss: 2.6260 (2.8378) grad: 0.2291 (0.2514) time: 0.4533 data: 0.0032 max mem: 22446 +train: [0] [120/400] eta: 0:02:20 lr: 0.000018 loss: 2.5174 (2.7686) grad: 0.2293 (0.2469) time: 0.4575 data: 0.0033 max mem: 22446 +train: [0] [140/400] eta: 0:02:08 lr: 0.000021 loss: 2.3484 (2.7017) grad: 0.2274 (0.2451) time: 0.4582 data: 0.0033 max mem: 22446 +train: [0] [160/400] eta: 0:01:57 lr: 0.000024 loss: 2.2599 (2.6417) grad: 0.2166 (0.2406) time: 0.4657 data: 0.0032 max mem: 22446 +train: [0] [180/400] eta: 0:01:47 lr: 0.000027 loss: 2.1568 (2.5816) grad: 0.2035 (0.2364) time: 0.4547 data: 0.0032 max mem: 22446 +train: [0] [200/400] eta: 0:01:36 lr: 0.000030 loss: 2.0773 (2.5243) grad: 0.1990 (0.2333) time: 0.4585 data: 0.0033 max mem: 22446 +train: [0] [220/400] eta: 0:01:26 lr: 0.000033 loss: 1.9640 (2.4703) grad: 0.1974 (0.2297) time: 0.4587 data: 0.0033 max mem: 22446 +train: [0] [240/400] eta: 0:01:16 lr: 0.000036 loss: 1.8783 (2.4163) grad: 0.1977 (0.2276) time: 0.4706 data: 0.0033 max mem: 22446 +train: [0] [260/400] eta: 0:01:07 lr: 0.000039 loss: 1.8020 (2.3679) grad: 0.1986 (0.2253) time: 0.4820 data: 0.0034 max mem: 22446 +train: [0] [280/400] eta: 0:00:57 lr: 0.000042 loss: 1.7661 (2.3246) grad: 0.1838 (0.2221) time: 0.4791 data: 0.0035 max mem: 22446 +train: [0] [300/400] eta: 0:00:49 lr: 0.000045 loss: 1.7267 (2.2825) grad: 0.1728 (0.2189) time: 0.6406 data: 0.1779 max mem: 22446 +train: [0] [320/400] eta: 0:00:39 lr: 0.000048 loss: 1.6648 (2.2413) grad: 0.1709 (0.2161) time: 0.4794 data: 0.0033 max mem: 22446 +train: [0] [340/400] eta: 0:00:29 lr: 0.000051 loss: 1.5866 (2.2024) grad: 0.1789 (0.2142) time: 0.4689 data: 0.0034 max mem: 22446 +train: [0] [360/400] eta: 0:00:19 lr: 0.000054 loss: 1.5582 (2.1661) grad: 0.1774 (0.2119) time: 0.4935 data: 0.0036 max mem: 22446 +train: [0] [380/400] eta: 0:00:09 lr: 0.000057 loss: 1.5294 (2.1313) grad: 0.1705 (0.2096) time: 0.5181 data: 0.0038 max mem: 22446 +train: [0] [399/400] eta: 0:00:00 lr: 0.000060 loss: 1.4753 (2.0967) grad: 0.1659 (0.2077) time: 0.4960 data: 0.0035 max mem: 22446 +train: [0] Total time: 0:03:16 (0.4913 s / it) +train: [0] Summary: lr: 0.000060 loss: 1.4753 (2.0967) grad: 0.1659 (0.2077) +eval (validation): [0] [ 0/63] eta: 0:03:37 time: 3.4550 data: 3.1337 max mem: 22446 +eval (validation): [0] [20/63] eta: 0:00:24 time: 0.4203 data: 0.0038 max mem: 22446 +eval (validation): [0] [40/63] eta: 0:00:10 time: 0.3612 data: 0.0032 max mem: 22446 +eval (validation): [0] [60/63] eta: 0:00:01 time: 0.3477 data: 0.0033 max mem: 22446 +eval (validation): [0] [62/63] eta: 0:00:00 time: 0.3463 data: 0.0033 max mem: 22446 +eval (validation): [0] Total time: 0:00:26 (0.4280 s / it) +cv: [0] best hparam: (26, 1.0) (044) ('044_lr2.6e+01_wd1.0e+00') loss: 0.044 acc: 0.986 f1: 0.985 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/hcpya_task21__patch__attn/checkpoint-best.pth +train: [1] [ 0/400] eta: 0:22:44 lr: nan time: 3.4114 data: 3.0019 max mem: 22446 +train: [1] [ 20/400] eta: 0:03:55 lr: 0.000063 loss: 1.4152 (1.4255) grad: 0.1625 (0.1690) time: 0.4805 data: 0.0032 max mem: 22446 +train: [1] [ 40/400] eta: 0:03:17 lr: 0.000066 loss: 1.4072 (1.4014) grad: 0.1654 (0.1677) time: 0.4738 data: 0.0033 max mem: 22446 +train: [1] [ 60/400] eta: 0:02:57 lr: 0.000069 loss: 1.3588 (1.3820) grad: 0.1620 (0.1645) time: 0.4656 data: 0.0036 max mem: 22446 +train: [1] [ 80/400] eta: 0:02:42 lr: 0.000072 loss: 1.3282 (1.3654) grad: 0.1518 (0.1624) time: 0.4701 data: 0.0033 max mem: 22446 +train: [1] [100/400] eta: 0:02:29 lr: 0.000075 loss: 1.3096 (1.3536) grad: 0.1575 (0.1619) time: 0.4552 data: 0.0034 max mem: 22446 +train: [1] [120/400] eta: 0:02:18 lr: 0.000078 loss: 1.2830 (1.3357) grad: 0.1500 (0.1604) time: 0.4678 data: 0.0035 max mem: 22446 +train: [1] [140/400] eta: 0:02:06 lr: 0.000081 loss: 1.2370 (1.3203) grad: 0.1483 (0.1589) time: 0.4564 data: 0.0035 max mem: 22446 +train: [1] [160/400] eta: 0:01:56 lr: 0.000084 loss: 1.2121 (1.3043) grad: 0.1466 (0.1577) time: 0.4551 data: 0.0035 max mem: 22446 +train: [1] [180/400] eta: 0:01:45 lr: 0.000087 loss: 1.1875 (1.2904) grad: 0.1466 (0.1570) time: 0.4505 data: 0.0034 max mem: 22446 +train: [1] [200/400] eta: 0:01:35 lr: 0.000090 loss: 1.1491 (1.2763) grad: 0.1465 (0.1563) time: 0.4568 data: 0.0033 max mem: 22446 +train: [1] [220/400] eta: 0:01:25 lr: 0.000093 loss: 1.1196 (1.2610) grad: 0.1496 (0.1564) time: 0.4534 data: 0.0035 max mem: 22446 +train: [1] [240/400] eta: 0:01:15 lr: 0.000096 loss: 1.0985 (1.2472) grad: 0.1496 (0.1554) time: 0.4548 data: 0.0034 max mem: 22446 +train: [1] [260/400] eta: 0:01:06 lr: 0.000099 loss: 1.0911 (1.2348) grad: 0.1450 (0.1544) time: 0.4536 data: 0.0033 max mem: 22446 +train: [1] [280/400] eta: 0:00:56 lr: 0.000102 loss: 1.0573 (1.2214) grad: 0.1373 (0.1538) time: 0.4524 data: 0.0034 max mem: 22446 +train: [1] [300/400] eta: 0:00:48 lr: 0.000105 loss: 1.0374 (1.2088) grad: 0.1357 (0.1525) time: 0.6380 data: 0.1755 max mem: 22446 +train: [1] [320/400] eta: 0:00:38 lr: 0.000108 loss: 1.0148 (1.1967) grad: 0.1358 (0.1517) time: 0.4602 data: 0.0030 max mem: 22446 +train: [1] [340/400] eta: 0:00:28 lr: 0.000111 loss: 0.9904 (1.1839) grad: 0.1376 (0.1508) time: 0.4528 data: 0.0035 max mem: 22446 +train: [1] [360/400] eta: 0:00:19 lr: 0.000114 loss: 0.9896 (1.1739) grad: 0.1374 (0.1499) time: 0.4562 data: 0.0034 max mem: 22446 +train: [1] [380/400] eta: 0:00:09 lr: 0.000117 loss: 0.9767 (1.1631) grad: 0.1388 (0.1495) time: 0.4531 data: 0.0034 max mem: 22446 +train: [1] [399/400] eta: 0:00:00 lr: 0.000120 loss: 0.9503 (1.1531) grad: 0.1339 (0.1486) time: 0.4544 data: 0.0034 max mem: 22446 +train: [1] Total time: 0:03:10 (0.4758 s / it) +train: [1] Summary: lr: 0.000120 loss: 0.9503 (1.1531) grad: 0.1339 (0.1486) +eval (validation): [1] [ 0/63] eta: 0:03:28 time: 3.3018 data: 2.9976 max mem: 22446 +eval (validation): [1] [20/63] eta: 0:00:22 time: 0.3808 data: 0.0031 max mem: 22446 +eval (validation): [1] [40/63] eta: 0:00:10 time: 0.3583 data: 0.0032 max mem: 22446 +eval (validation): [1] [60/63] eta: 0:00:01 time: 0.3383 data: 0.0032 max mem: 22446 +eval (validation): [1] [62/63] eta: 0:00:00 time: 0.3355 data: 0.0032 max mem: 22446 +eval (validation): [1] Total time: 0:00:25 (0.4087 s / it) +cv: [1] best hparam: (5.1, 1.0) (034) ('034_lr5.1e+00_wd1.0e+00') loss: 0.033 acc: 0.990 f1: 0.989 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/hcpya_task21__patch__attn/checkpoint-best.pth +train: [2] [ 0/400] eta: 0:22:56 lr: nan time: 3.4413 data: 3.0406 max mem: 22446 +train: [2] [ 20/400] eta: 0:03:55 lr: 0.000123 loss: 0.8891 (0.9061) grad: 0.1413 (0.1409) time: 0.4788 data: 0.0019 max mem: 22446 +train: [2] [ 40/400] eta: 0:03:15 lr: 0.000126 loss: 0.9147 (0.9120) grad: 0.1357 (0.1394) time: 0.4599 data: 0.0037 max mem: 22446 +train: [2] [ 60/400] eta: 0:02:55 lr: 0.000129 loss: 0.9045 (0.9017) grad: 0.1384 (0.1410) time: 0.4602 data: 0.0036 max mem: 22446 +train: [2] [ 80/400] eta: 0:02:42 lr: 0.000132 loss: 0.8790 (0.8982) grad: 0.1467 (0.1448) time: 0.4879 data: 0.0039 max mem: 22446 +train: [2] [100/400] eta: 0:02:28 lr: 0.000135 loss: 0.8790 (0.8929) grad: 0.1490 (0.1491) time: 0.4471 data: 0.0035 max mem: 22446 +train: [2] [120/400] eta: 0:02:16 lr: 0.000138 loss: 0.8754 (0.8925) grad: 0.1605 (0.1549) time: 0.4492 data: 0.0037 max mem: 22446 +train: [2] [140/400] eta: 0:02:05 lr: 0.000141 loss: 0.8703 (0.8903) grad: 0.1803 (0.1607) time: 0.4584 data: 0.0036 max mem: 22446 +train: [2] [160/400] eta: 0:01:54 lr: 0.000144 loss: 0.8890 (0.8925) grad: 0.1860 (0.1666) time: 0.4424 data: 0.0034 max mem: 22446 +train: [2] [180/400] eta: 0:01:44 lr: 0.000147 loss: 0.8565 (0.8871) grad: 0.1880 (0.1680) time: 0.4430 data: 0.0034 max mem: 22446 +train: [2] [200/400] eta: 0:01:34 lr: 0.000150 loss: 0.8185 (0.8782) grad: 0.1603 (0.1674) time: 0.4432 data: 0.0034 max mem: 22446 +train: [2] [220/400] eta: 0:01:24 lr: 0.000153 loss: 0.8224 (0.8792) grad: 0.1801 (0.1705) time: 0.4432 data: 0.0035 max mem: 22446 +train: [2] [240/400] eta: 0:01:14 lr: 0.000156 loss: 0.8404 (0.8743) grad: 0.1932 (0.1721) time: 0.4367 data: 0.0034 max mem: 22446 +train: [2] [260/400] eta: 0:01:05 lr: 0.000159 loss: 0.8402 (0.8725) grad: 0.2011 (0.1790) time: 0.4497 data: 0.0034 max mem: 22446 +train: [2] [280/400] eta: 0:00:55 lr: 0.000162 loss: 0.8325 (0.8679) grad: 0.2002 (0.1794) time: 0.4459 data: 0.0034 max mem: 22446 +train: [2] [300/400] eta: 0:00:47 lr: 0.000165 loss: 0.7720 (0.8608) grad: 0.1832 (0.1796) time: 0.6219 data: 0.1729 max mem: 22446 +train: [2] [320/400] eta: 0:00:37 lr: 0.000168 loss: 0.7561 (0.8584) grad: 0.1910 (0.1846) time: 0.4335 data: 0.0029 max mem: 22446 +train: [2] [340/400] eta: 0:00:28 lr: 0.000171 loss: 0.8064 (0.8552) grad: 0.2276 (0.1873) time: 0.4456 data: 0.0035 max mem: 22446 +train: [2] [360/400] eta: 0:00:18 lr: 0.000174 loss: 0.8375 (0.8544) grad: 0.1983 (0.1879) time: 0.4525 data: 0.0035 max mem: 22446 +train: [2] [380/400] eta: 0:00:09 lr: 0.000177 loss: 0.7614 (0.8493) grad: 0.2021 (0.1915) time: 0.4689 data: 0.0035 max mem: 22446 +train: [2] [399/400] eta: 0:00:00 lr: 0.000180 loss: 0.7241 (0.8428) grad: 0.2468 (0.1948) time: 0.4661 data: 0.0034 max mem: 22446 +train: [2] Total time: 0:03:07 (0.4695 s / it) +train: [2] Summary: lr: 0.000180 loss: 0.7241 (0.8428) grad: 0.2468 (0.1948) +eval (validation): [2] [ 0/63] eta: 0:03:28 time: 3.3128 data: 3.0131 max mem: 22446 +eval (validation): [2] [20/63] eta: 0:00:21 time: 0.3694 data: 0.0025 max mem: 22446 +eval (validation): [2] [40/63] eta: 0:00:09 time: 0.3244 data: 0.0032 max mem: 22446 +eval (validation): [2] [60/63] eta: 0:00:01 time: 0.3223 data: 0.0031 max mem: 22446 +eval (validation): [2] [62/63] eta: 0:00:00 time: 0.3223 data: 0.0031 max mem: 22446 +eval (validation): [2] Total time: 0:00:24 (0.3891 s / it) +cv: [2] best hparam: (5.1, 1.0) (034) ('034_lr5.1e+00_wd1.0e+00') loss: 0.031 acc: 0.991 f1: 0.989 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/hcpya_task21__patch__attn/checkpoint-best.pth +train: [3] [ 0/400] eta: 0:22:06 lr: nan time: 3.3166 data: 2.9702 max mem: 22446 +train: [3] [ 20/400] eta: 0:03:41 lr: 0.000183 loss: 0.6780 (0.6985) grad: 0.1902 (0.2111) time: 0.4451 data: 0.0040 max mem: 22446 +train: [3] [ 40/400] eta: 0:03:15 lr: 0.000186 loss: 0.6962 (0.7183) grad: 0.1924 (0.2098) time: 0.5002 data: 0.0034 max mem: 22446 +train: [3] [ 60/400] eta: 0:02:59 lr: 0.000189 loss: 0.7226 (0.7337) grad: 0.2187 (0.2254) time: 0.5004 data: 0.0038 max mem: 22446 +train: [3] [ 80/400] eta: 0:02:44 lr: 0.000192 loss: 0.7608 (0.7507) grad: 0.2485 (0.2349) time: 0.4683 data: 0.0035 max mem: 22446 +train: [3] [100/400] eta: 0:02:32 lr: 0.000195 loss: 0.6823 (0.7359) grad: 0.2292 (0.2368) time: 0.4913 data: 0.0038 max mem: 22446 +train: [3] [120/400] eta: 0:02:20 lr: 0.000198 loss: 0.6867 (0.7421) grad: 0.2307 (0.2397) time: 0.4607 data: 0.0033 max mem: 22446 +train: [3] [140/400] eta: 0:02:08 lr: 0.000201 loss: 0.7908 (0.7532) grad: 0.2584 (0.2403) time: 0.4602 data: 0.0034 max mem: 22446 +train: [3] [160/400] eta: 0:01:57 lr: 0.000204 loss: 0.7177 (0.7558) grad: 0.2672 (0.2485) time: 0.4644 data: 0.0033 max mem: 22446 +train: [3] [180/400] eta: 0:01:47 lr: 0.000207 loss: 0.7411 (0.7623) grad: 0.2735 (0.2491) time: 0.4638 data: 0.0034 max mem: 22446 +train: [3] [200/400] eta: 0:01:37 lr: 0.000210 loss: 0.7757 (0.7725) grad: 0.2328 (0.2504) time: 0.4747 data: 0.0034 max mem: 22446 +train: [3] [220/400] eta: 0:01:27 lr: 0.000213 loss: 0.7245 (0.7654) grad: 0.2640 (0.2521) time: 0.4681 data: 0.0034 max mem: 22446 +train: [3] [240/400] eta: 0:01:17 lr: 0.000216 loss: 0.7384 (0.7771) grad: 0.2910 (0.2602) time: 0.4678 data: 0.0034 max mem: 22446 +train: [3] [260/400] eta: 0:01:07 lr: 0.000219 loss: 0.7747 (0.7780) grad: 0.3172 (0.2663) time: 0.4682 data: 0.0034 max mem: 22446 +train: [3] [280/400] eta: 0:00:57 lr: 0.000222 loss: 0.7405 (0.7761) grad: 0.3218 (0.2716) time: 0.4667 data: 0.0034 max mem: 22446 +train: [3] [300/400] eta: 0:00:49 lr: 0.000225 loss: 0.7617 (0.7775) grad: 0.3373 (0.2873) time: 0.6294 data: 0.1775 max mem: 22446 +train: [3] [320/400] eta: 0:00:39 lr: 0.000228 loss: 0.6743 (0.7726) grad: 0.3101 (0.2875) time: 0.4522 data: 0.0031 max mem: 22446 +train: [3] [340/400] eta: 0:00:29 lr: 0.000231 loss: 0.6328 (0.7635) grad: 0.2920 (0.2892) time: 0.4650 data: 0.0033 max mem: 22446 +train: [3] [360/400] eta: 0:00:19 lr: 0.000234 loss: 0.6127 (0.7559) grad: 0.3140 (0.2917) time: 0.4839 data: 0.0034 max mem: 22446 +train: [3] [380/400] eta: 0:00:09 lr: 0.000237 loss: 0.6466 (0.7542) grad: 0.3309 (0.2946) time: 0.4618 data: 0.0033 max mem: 22446 +train: [3] [399/400] eta: 0:00:00 lr: 0.000240 loss: 0.6465 (0.7497) grad: 0.3309 (0.2954) time: 0.4616 data: 0.0037 max mem: 22446 +train: [3] Total time: 0:03:14 (0.4852 s / it) +train: [3] Summary: lr: 0.000240 loss: 0.6465 (0.7497) grad: 0.3309 (0.2954) +eval (validation): [3] [ 0/63] eta: 0:03:22 time: 3.2111 data: 2.9568 max mem: 22446 +eval (validation): [3] [20/63] eta: 0:00:20 time: 0.3466 data: 0.0030 max mem: 22446 +eval (validation): [3] [40/63] eta: 0:00:09 time: 0.3454 data: 0.0030 max mem: 22446 +eval (validation): [3] [60/63] eta: 0:00:01 time: 0.3411 data: 0.0030 max mem: 22446 +eval (validation): [3] [62/63] eta: 0:00:00 time: 0.3410 data: 0.0031 max mem: 22446 +eval (validation): [3] Total time: 0:00:24 (0.3933 s / it) +cv: [3] best hparam: (1.2, 1.0) (025) ('025_lr1.2e+00_wd1.0e+00') loss: 0.035 acc: 0.990 f1: 0.988 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [4] [ 0/400] eta: 0:22:34 lr: nan time: 3.3867 data: 3.0240 max mem: 22446 +train: [4] [ 20/400] eta: 0:03:50 lr: 0.000243 loss: 0.8378 (0.8441) grad: 0.3027 (0.3708) time: 0.4663 data: 0.0033 max mem: 22446 +train: [4] [ 40/400] eta: 0:03:17 lr: 0.000246 loss: 0.8269 (0.8254) grad: 0.3038 (0.3492) time: 0.4868 data: 0.0034 max mem: 22446 +train: [4] [ 60/400] eta: 0:03:00 lr: 0.000249 loss: 0.7128 (0.7563) grad: 0.3246 (0.3774) time: 0.4962 data: 0.0040 max mem: 22446 +train: [4] [ 80/400] eta: 0:02:47 lr: 0.000252 loss: 0.5724 (0.7259) grad: 0.3170 (0.3778) time: 0.5018 data: 0.0036 max mem: 22446 +train: [4] [100/400] eta: 0:02:34 lr: 0.000255 loss: 0.6118 (0.7169) grad: 0.3170 (0.3775) time: 0.4749 data: 0.0034 max mem: 22446 +train: [4] [120/400] eta: 0:02:21 lr: 0.000258 loss: 0.6241 (0.7207) grad: 0.3789 (0.3949) time: 0.4677 data: 0.0034 max mem: 22446 +train: [4] [140/400] eta: 0:02:10 lr: 0.000261 loss: 0.6138 (0.7205) grad: 0.4014 (0.3927) time: 0.4721 data: 0.0033 max mem: 22446 +train: [4] [160/400] eta: 0:01:59 lr: 0.000264 loss: 0.7092 (0.7323) grad: 0.3751 (0.3897) time: 0.4722 data: 0.0033 max mem: 22446 +train: [4] [180/400] eta: 0:01:48 lr: 0.000267 loss: 0.7658 (0.7361) grad: 0.3751 (0.3894) time: 0.4701 data: 0.0033 max mem: 22446 +train: [4] [200/400] eta: 0:01:38 lr: 0.000270 loss: 0.7243 (0.7411) grad: 0.3798 (0.3905) time: 0.4703 data: 0.0034 max mem: 22446 +train: [4] [220/400] eta: 0:01:28 lr: 0.000273 loss: 0.7243 (0.7455) grad: 0.4184 (0.3943) time: 0.4666 data: 0.0034 max mem: 22446 +train: [4] [240/400] eta: 0:01:18 lr: 0.000276 loss: 0.5972 (0.7452) grad: 0.3822 (0.3921) time: 0.4718 data: 0.0034 max mem: 22446 +train: [4] [260/400] eta: 0:01:08 lr: 0.000279 loss: 0.6127 (0.7691) grad: 0.3764 (0.3942) time: 0.4720 data: 0.0035 max mem: 22446 +train: [4] [280/400] eta: 0:00:58 lr: 0.000282 loss: 0.9244 (0.7799) grad: 0.5095 (0.4101) time: 0.4755 data: 0.0034 max mem: 22446 +train: [4] [300/400] eta: 0:00:49 lr: 0.000285 loss: 0.7798 (0.7852) grad: 0.5096 (0.4154) time: 0.6670 data: 0.1801 max mem: 22446 +train: [4] [320/400] eta: 0:00:39 lr: 0.000288 loss: 0.5886 (0.7704) grad: 0.4123 (0.4124) time: 0.4761 data: 0.0030 max mem: 22446 +train: [4] [340/400] eta: 0:00:29 lr: 0.000291 loss: 0.5042 (0.7604) grad: 0.4144 (0.4128) time: 0.4692 data: 0.0035 max mem: 22446 +train: [4] [360/400] eta: 0:00:19 lr: 0.000294 loss: 0.5621 (0.7672) grad: 0.4272 (0.4150) time: 0.4684 data: 0.0034 max mem: 22446 +train: [4] [380/400] eta: 0:00:09 lr: 0.000297 loss: 0.7891 (0.7825) grad: 0.4751 (0.4226) time: 0.4740 data: 0.0034 max mem: 22446 +train: [4] [399/400] eta: 0:00:00 lr: 0.000300 loss: 0.7891 (0.7903) grad: 0.4754 (0.4247) time: 0.4735 data: 0.0034 max mem: 22446 +train: [4] Total time: 0:03:16 (0.4922 s / it) +train: [4] Summary: lr: 0.000300 loss: 0.7891 (0.7903) grad: 0.4754 (0.4247) +eval (validation): [4] [ 0/63] eta: 0:03:30 time: 3.3461 data: 3.0653 max mem: 22446 +eval (validation): [4] [20/63] eta: 0:00:22 time: 0.3864 data: 0.0024 max mem: 22446 +eval (validation): [4] [40/63] eta: 0:00:10 time: 0.4040 data: 0.0038 max mem: 22446 +eval (validation): [4] [60/63] eta: 0:00:01 time: 0.3555 data: 0.0034 max mem: 22446 +eval (validation): [4] [62/63] eta: 0:00:00 time: 0.3402 data: 0.0032 max mem: 22446 +eval (validation): [4] Total time: 0:00:27 (0.4308 s / it) +cv: [4] best hparam: (7.1, 1.0) (036) ('036_lr7.1e+00_wd1.0e+00') loss: 0.039 acc: 0.990 f1: 0.987 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [5] [ 0/400] eta: 0:22:32 lr: nan time: 3.3802 data: 3.0261 max mem: 22446 +train: [5] [ 20/400] eta: 0:03:49 lr: 0.000300 loss: 0.6475 (0.6297) grad: 0.3982 (0.4021) time: 0.4647 data: 0.0036 max mem: 22446 +train: [5] [ 40/400] eta: 0:03:13 lr: 0.000300 loss: 0.6646 (0.6755) grad: 0.4056 (0.4618) time: 0.4682 data: 0.0028 max mem: 22446 +train: [5] [ 60/400] eta: 0:02:54 lr: 0.000300 loss: 0.8032 (0.7355) grad: 0.4364 (0.4619) time: 0.4599 data: 0.0034 max mem: 22446 +train: [5] [ 80/400] eta: 0:02:43 lr: 0.000300 loss: 0.6456 (0.7089) grad: 0.4211 (0.4462) time: 0.5020 data: 0.0033 max mem: 22446 +train: [5] [100/400] eta: 0:02:32 lr: 0.000300 loss: 0.6456 (0.7866) grad: 0.4053 (0.4470) time: 0.5002 data: 0.0036 max mem: 22446 +train: [5] [120/400] eta: 0:02:22 lr: 0.000300 loss: 1.0453 (0.8125) grad: 0.4448 (0.4479) time: 0.5088 data: 0.0037 max mem: 22446 +train: [5] [140/400] eta: 0:02:12 lr: 0.000300 loss: 0.8746 (0.8132) grad: 0.4667 (0.4544) time: 0.5147 data: 0.0037 max mem: 22446 +train: [5] [160/400] eta: 0:02:01 lr: 0.000299 loss: 0.7441 (0.8311) grad: 0.5005 (0.4602) time: 0.4722 data: 0.0033 max mem: 22446 +train: [5] [180/400] eta: 0:01:49 lr: 0.000299 loss: 0.6039 (0.8202) grad: 0.4766 (0.4669) time: 0.4609 data: 0.0033 max mem: 22446 +train: [5] [200/400] eta: 0:01:39 lr: 0.000299 loss: 0.5289 (0.8024) grad: 0.4092 (0.4572) time: 0.4615 data: 0.0031 max mem: 22446 +train: [5] [220/400] eta: 0:01:28 lr: 0.000299 loss: 0.5410 (0.7984) grad: 0.3645 (0.4575) time: 0.4548 data: 0.0032 max mem: 22446 +train: [5] [240/400] eta: 0:01:18 lr: 0.000299 loss: 0.5544 (0.7817) grad: 0.4316 (0.4546) time: 0.4530 data: 0.0033 max mem: 22446 +train: [5] [260/400] eta: 0:01:08 lr: 0.000299 loss: 0.6995 (0.8116) grad: 0.4826 (0.4648) time: 0.4540 data: 0.0033 max mem: 22446 +train: [5] [280/400] eta: 0:00:58 lr: 0.000298 loss: 0.8838 (0.8204) grad: 0.5474 (0.4691) time: 0.4570 data: 0.0034 max mem: 22446 +train: [5] [300/400] eta: 0:00:49 lr: 0.000298 loss: 0.8424 (0.8191) grad: 0.4947 (0.4709) time: 0.6199 data: 0.1805 max mem: 22446 +train: [5] [320/400] eta: 0:00:39 lr: 0.000298 loss: 0.6614 (0.8088) grad: 0.4594 (0.4686) time: 0.4471 data: 0.0034 max mem: 22446 +train: [5] [340/400] eta: 0:00:29 lr: 0.000298 loss: 0.6431 (0.8115) grad: 0.4324 (0.4672) time: 0.4462 data: 0.0034 max mem: 22446 +train: [5] [360/400] eta: 0:00:19 lr: 0.000297 loss: 0.6542 (0.8080) grad: 0.4384 (0.4688) time: 0.4557 data: 0.0033 max mem: 22446 +train: [5] [380/400] eta: 0:00:09 lr: 0.000297 loss: 0.6542 (0.8001) grad: 0.4359 (0.4681) time: 0.4568 data: 0.0033 max mem: 22446 +train: [5] [399/400] eta: 0:00:00 lr: 0.000297 loss: 0.6743 (0.7897) grad: 0.3896 (0.4655) time: 0.4598 data: 0.0032 max mem: 22446 +train: [5] Total time: 0:03:13 (0.4835 s / it) +train: [5] Summary: lr: 0.000297 loss: 0.6743 (0.7897) grad: 0.3896 (0.4655) +eval (validation): [5] [ 0/63] eta: 0:03:19 time: 3.1710 data: 2.9238 max mem: 22446 +eval (validation): [5] [20/63] eta: 0:00:19 time: 0.3269 data: 0.0039 max mem: 22446 +eval (validation): [5] [40/63] eta: 0:00:09 time: 0.3738 data: 0.0027 max mem: 22446 +eval (validation): [5] [60/63] eta: 0:00:01 time: 0.3202 data: 0.0032 max mem: 22446 +eval (validation): [5] [62/63] eta: 0:00:00 time: 0.3179 data: 0.0029 max mem: 22446 +eval (validation): [5] Total time: 0:00:24 (0.3878 s / it) +cv: [5] best hparam: (4.3, 1.0) (033) ('033_lr4.3e+00_wd1.0e+00') loss: 0.027 acc: 0.991 f1: 0.990 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [6] [ 0/400] eta: 0:21:41 lr: nan time: 3.2544 data: 2.9069 max mem: 22446 +train: [6] [ 20/400] eta: 0:03:35 lr: 0.000296 loss: 0.6270 (0.6590) grad: 0.3864 (0.4169) time: 0.4332 data: 0.0035 max mem: 22446 +train: [6] [ 40/400] eta: 0:03:03 lr: 0.000296 loss: 0.4722 (0.5799) grad: 0.3680 (0.3908) time: 0.4494 data: 0.0030 max mem: 22446 +train: [6] [ 60/400] eta: 0:02:47 lr: 0.000296 loss: 0.4725 (0.5781) grad: 0.3680 (0.4135) time: 0.4577 data: 0.0035 max mem: 22446 +train: [6] [ 80/400] eta: 0:02:34 lr: 0.000295 loss: 0.6116 (0.6066) grad: 0.4189 (0.4062) time: 0.4545 data: 0.0034 max mem: 22446 +train: [6] [100/400] eta: 0:02:23 lr: 0.000295 loss: 0.5158 (0.5810) grad: 0.3792 (0.3995) time: 0.4640 data: 0.0036 max mem: 22446 +train: [6] [120/400] eta: 0:02:15 lr: 0.000295 loss: 0.4521 (0.5819) grad: 0.3792 (0.3979) time: 0.5063 data: 0.0034 max mem: 22446 +train: [6] [140/400] eta: 0:02:05 lr: 0.000294 loss: 0.4305 (0.5797) grad: 0.4325 (0.4084) time: 0.4736 data: 0.0036 max mem: 22446 +train: [6] [160/400] eta: 0:01:55 lr: 0.000294 loss: 0.4296 (0.5701) grad: 0.4264 (0.4054) time: 0.4745 data: 0.0033 max mem: 22446 +train: [6] [180/400] eta: 0:01:45 lr: 0.000293 loss: 0.4828 (0.5819) grad: 0.3535 (0.4039) time: 0.4765 data: 0.0035 max mem: 22446 +train: [6] [200/400] eta: 0:01:35 lr: 0.000293 loss: 0.4881 (0.6173) grad: 0.3701 (0.4087) time: 0.4498 data: 0.0033 max mem: 22446 +train: [6] [220/400] eta: 0:01:25 lr: 0.000292 loss: 0.4646 (0.6108) grad: 0.3881 (0.4090) time: 0.4644 data: 0.0034 max mem: 22446 +train: [6] [240/400] eta: 0:01:15 lr: 0.000292 loss: 0.4400 (0.5961) grad: 0.3472 (0.4012) time: 0.4494 data: 0.0034 max mem: 22446 +train: [6] [260/400] eta: 0:01:06 lr: 0.000291 loss: 0.4191 (0.5917) grad: 0.3003 (0.3978) time: 0.4396 data: 0.0034 max mem: 22446 +train: [6] [280/400] eta: 0:00:56 lr: 0.000291 loss: 0.6004 (0.6007) grad: 0.3471 (0.3977) time: 0.4173 data: 0.0035 max mem: 22446 +train: [6] [300/400] eta: 0:00:47 lr: 0.000290 loss: 0.4873 (0.5893) grad: 0.3384 (0.3914) time: 0.5953 data: 0.1779 max mem: 22446 +train: [6] [320/400] eta: 0:00:38 lr: 0.000290 loss: 0.3931 (0.5759) grad: 0.2793 (0.3866) time: 0.4767 data: 0.0027 max mem: 22446 +train: [6] [340/400] eta: 0:00:28 lr: 0.000289 loss: 0.3580 (0.5685) grad: 0.2845 (0.3825) time: 0.4778 data: 0.0034 max mem: 22446 +train: [6] [360/400] eta: 0:00:19 lr: 0.000288 loss: 0.3580 (0.5611) grad: 0.3014 (0.3783) time: 0.4531 data: 0.0034 max mem: 22446 +train: [6] [380/400] eta: 0:00:09 lr: 0.000288 loss: 0.4437 (0.5551) grad: 0.2977 (0.3735) time: 0.4622 data: 0.0033 max mem: 22446 +train: [6] [399/400] eta: 0:00:00 lr: 0.000287 loss: 0.3452 (0.5445) grad: 0.2696 (0.3682) time: 0.4555 data: 0.0033 max mem: 22446 +train: [6] Total time: 0:03:09 (0.4738 s / it) +train: [6] Summary: lr: 0.000287 loss: 0.3452 (0.5445) grad: 0.2696 (0.3682) +eval (validation): [6] [ 0/63] eta: 0:03:20 time: 3.1883 data: 2.9400 max mem: 22446 +eval (validation): [6] [20/63] eta: 0:00:20 time: 0.3490 data: 0.0035 max mem: 22446 +eval (validation): [6] [40/63] eta: 0:00:09 time: 0.3387 data: 0.0028 max mem: 22446 +eval (validation): [6] [60/63] eta: 0:00:01 time: 0.3268 data: 0.0030 max mem: 22446 +eval (validation): [6] [62/63] eta: 0:00:00 time: 0.3267 data: 0.0029 max mem: 22446 +eval (validation): [6] Total time: 0:00:24 (0.3868 s / it) +cv: [6] best hparam: (2.3, 1.0) (029) ('029_lr2.3e+00_wd1.0e+00') loss: 0.024 acc: 0.993 f1: 0.991 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/hcpya_task21__patch__attn/checkpoint-best.pth +train: [7] [ 0/400] eta: 0:22:23 lr: nan time: 3.3595 data: 2.9504 max mem: 22446 +train: [7] [ 20/400] eta: 0:03:49 lr: 0.000286 loss: 0.2523 (0.3927) grad: 0.2390 (0.2868) time: 0.4660 data: 0.0030 max mem: 22446 +train: [7] [ 40/400] eta: 0:03:11 lr: 0.000286 loss: 0.2734 (0.3864) grad: 0.2390 (0.2665) time: 0.4583 data: 0.0034 max mem: 22446 +train: [7] [ 60/400] eta: 0:02:52 lr: 0.000285 loss: 0.3641 (0.4277) grad: 0.2673 (0.2777) time: 0.4565 data: 0.0035 max mem: 22446 +train: [7] [ 80/400] eta: 0:02:38 lr: 0.000284 loss: 0.3476 (0.3855) grad: 0.3172 (0.2847) time: 0.4628 data: 0.0036 max mem: 22446 +train: [7] [100/400] eta: 0:02:26 lr: 0.000284 loss: 0.2387 (0.3765) grad: 0.2982 (0.2873) time: 0.4597 data: 0.0034 max mem: 22446 +train: [7] [120/400] eta: 0:02:15 lr: 0.000283 loss: 0.2484 (0.3601) grad: 0.2730 (0.2867) time: 0.4665 data: 0.0036 max mem: 22446 +train: [7] [140/400] eta: 0:02:05 lr: 0.000282 loss: 0.2829 (0.3688) grad: 0.2660 (0.2899) time: 0.4611 data: 0.0035 max mem: 22446 +train: [7] [160/400] eta: 0:01:55 lr: 0.000282 loss: 0.3207 (0.3668) grad: 0.2943 (0.2925) time: 0.4711 data: 0.0035 max mem: 22446 +train: [7] [180/400] eta: 0:01:45 lr: 0.000281 loss: 0.3076 (0.3680) grad: 0.2929 (0.2903) time: 0.4679 data: 0.0035 max mem: 22446 +train: [7] [200/400] eta: 0:01:35 lr: 0.000280 loss: 0.2714 (0.3639) grad: 0.2572 (0.2910) time: 0.4778 data: 0.0035 max mem: 22446 +train: [7] [220/400] eta: 0:01:26 lr: 0.000279 loss: 0.2618 (0.3685) grad: 0.2850 (0.2919) time: 0.4724 data: 0.0034 max mem: 22446 +train: [7] [240/400] eta: 0:01:16 lr: 0.000278 loss: 0.3319 (0.3766) grad: 0.3327 (0.3001) time: 0.4764 data: 0.0034 max mem: 22446 +train: [7] [260/400] eta: 0:01:06 lr: 0.000278 loss: 0.3685 (0.3720) grad: 0.3327 (0.3005) time: 0.4771 data: 0.0033 max mem: 22446 +train: [7] [280/400] eta: 0:00:57 lr: 0.000277 loss: 0.3685 (0.3843) grad: 0.2925 (0.3038) time: 0.4545 data: 0.0035 max mem: 22446 +train: [7] [300/400] eta: 0:00:48 lr: 0.000276 loss: 0.2975 (0.3863) grad: 0.2810 (0.3022) time: 0.6166 data: 0.1740 max mem: 22446 +train: [7] [320/400] eta: 0:00:38 lr: 0.000275 loss: 0.3309 (0.3892) grad: 0.2721 (0.3005) time: 0.4635 data: 0.0031 max mem: 22446 +train: [7] [340/400] eta: 0:00:29 lr: 0.000274 loss: 0.2851 (0.3810) grad: 0.2447 (0.2974) time: 0.4918 data: 0.0031 max mem: 22446 +train: [7] [360/400] eta: 0:00:19 lr: 0.000273 loss: 0.2097 (0.3721) grad: 0.2063 (0.2927) time: 0.4609 data: 0.0037 max mem: 22446 +train: [7] [380/400] eta: 0:00:09 lr: 0.000272 loss: 0.2097 (0.3650) grad: 0.2296 (0.2897) time: 0.4760 data: 0.0032 max mem: 22446 +train: [7] [399/400] eta: 0:00:00 lr: 0.000271 loss: 0.2241 (0.3608) grad: 0.1977 (0.2890) time: 0.4905 data: 0.0034 max mem: 22446 +train: [7] Total time: 0:03:13 (0.4838 s / it) +train: [7] Summary: lr: 0.000271 loss: 0.2241 (0.3608) grad: 0.1977 (0.2890) +eval (validation): [7] [ 0/63] eta: 0:03:23 time: 3.2258 data: 2.9814 max mem: 22446 +eval (validation): [7] [20/63] eta: 0:00:22 time: 0.3761 data: 0.0030 max mem: 22446 +eval (validation): [7] [40/63] eta: 0:00:10 time: 0.3934 data: 0.0034 max mem: 22446 +eval (validation): [7] [60/63] eta: 0:00:01 time: 0.3839 data: 0.0035 max mem: 22446 +eval (validation): [7] [62/63] eta: 0:00:00 time: 0.3778 data: 0.0034 max mem: 22446 +eval (validation): [7] Total time: 0:00:27 (0.4326 s / it) +cv: [7] best hparam: (3.7, 1.0) (032) ('032_lr3.7e+00_wd1.0e+00') loss: 0.026 acc: 0.993 f1: 0.991 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [8] [ 0/400] eta: 0:22:23 lr: nan time: 3.3575 data: 3.0008 max mem: 22446 +train: [8] [ 20/400] eta: 0:03:52 lr: 0.000270 loss: 0.2016 (0.2444) grad: 0.2533 (0.2691) time: 0.4748 data: 0.0026 max mem: 22446 +train: [8] [ 40/400] eta: 0:03:18 lr: 0.000270 loss: 0.2016 (0.2505) grad: 0.2398 (0.2346) time: 0.4860 data: 0.0031 max mem: 22446 +train: [8] [ 60/400] eta: 0:03:00 lr: 0.000269 loss: 0.1850 (0.2420) grad: 0.1864 (0.2244) time: 0.4886 data: 0.0035 max mem: 22446 +train: [8] [ 80/400] eta: 0:02:48 lr: 0.000268 loss: 0.1678 (0.2382) grad: 0.2020 (0.2204) time: 0.5156 data: 0.0038 max mem: 22446 +train: [8] [100/400] eta: 0:02:35 lr: 0.000267 loss: 0.2095 (0.2441) grad: 0.2021 (0.2147) time: 0.4763 data: 0.0034 max mem: 22446 +train: [8] [120/400] eta: 0:02:22 lr: 0.000266 loss: 0.2403 (0.2527) grad: 0.2180 (0.2181) time: 0.4661 data: 0.0033 max mem: 22446 +train: [8] [140/400] eta: 0:02:10 lr: 0.000265 loss: 0.2351 (0.2536) grad: 0.2341 (0.2240) time: 0.4586 data: 0.0035 max mem: 22446 +train: [8] [160/400] eta: 0:01:59 lr: 0.000264 loss: 0.1905 (0.2514) grad: 0.2294 (0.2194) time: 0.4642 data: 0.0040 max mem: 22446 +train: [8] [180/400] eta: 0:01:48 lr: 0.000263 loss: 0.1729 (0.2531) grad: 0.1819 (0.2167) time: 0.4720 data: 0.0025 max mem: 22446 +train: [8] [200/400] eta: 0:01:37 lr: 0.000262 loss: 0.1687 (0.2489) grad: 0.2085 (0.2145) time: 0.4534 data: 0.0034 max mem: 22446 +train: [8] [220/400] eta: 0:01:27 lr: 0.000260 loss: 0.2011 (0.2515) grad: 0.1978 (0.2127) time: 0.4503 data: 0.0034 max mem: 22446 +train: [8] [240/400] eta: 0:01:17 lr: 0.000259 loss: 0.2251 (0.2580) grad: 0.1818 (0.2129) time: 0.4339 data: 0.0034 max mem: 22446 +train: [8] [260/400] eta: 0:01:07 lr: 0.000258 loss: 0.2158 (0.2575) grad: 0.1987 (0.2127) time: 0.4690 data: 0.0035 max mem: 22446 +train: [8] [280/400] eta: 0:00:57 lr: 0.000257 loss: 0.1839 (0.2608) grad: 0.1987 (0.2134) time: 0.4924 data: 0.0035 max mem: 22446 +train: [8] [300/400] eta: 0:00:49 lr: 0.000256 loss: 0.2491 (0.2671) grad: 0.2346 (0.2153) time: 0.6407 data: 0.1742 max mem: 22446 +train: [8] [320/400] eta: 0:00:39 lr: 0.000255 loss: 0.2009 (0.2649) grad: 0.2346 (0.2146) time: 0.4722 data: 0.0028 max mem: 22446 +train: [8] [340/400] eta: 0:00:29 lr: 0.000254 loss: 0.1644 (0.2608) grad: 0.1841 (0.2120) time: 0.4608 data: 0.0031 max mem: 22446 +train: [8] [360/400] eta: 0:00:19 lr: 0.000253 loss: 0.1575 (0.2552) grad: 0.1598 (0.2082) time: 0.4757 data: 0.0034 max mem: 22446 +train: [8] [380/400] eta: 0:00:09 lr: 0.000252 loss: 0.1332 (0.2494) grad: 0.1315 (0.2050) time: 0.4886 data: 0.0034 max mem: 22446 +train: [8] [399/400] eta: 0:00:00 lr: 0.000250 loss: 0.1513 (0.2475) grad: 0.1569 (0.2038) time: 0.4823 data: 0.0033 max mem: 22446 +train: [8] Total time: 0:03:15 (0.4885 s / it) +train: [8] Summary: lr: 0.000250 loss: 0.1513 (0.2475) grad: 0.1569 (0.2038) +eval (validation): [8] [ 0/63] eta: 0:03:21 time: 3.1957 data: 2.9571 max mem: 22446 +eval (validation): [8] [20/63] eta: 0:00:20 time: 0.3453 data: 0.0031 max mem: 22446 +eval (validation): [8] [40/63] eta: 0:00:09 time: 0.3553 data: 0.0036 max mem: 22446 +eval (validation): [8] [60/63] eta: 0:00:01 time: 0.3493 data: 0.0029 max mem: 22446 +eval (validation): [8] [62/63] eta: 0:00:00 time: 0.3468 data: 0.0031 max mem: 22446 +eval (validation): [8] Total time: 0:00:25 (0.3988 s / it) +cv: [8] best hparam: (1.9, 1.0) (028) ('028_lr1.9e+00_wd1.0e+00') loss: 0.026 acc: 0.993 f1: 0.990 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [9] [ 0/400] eta: 0:23:19 lr: nan time: 3.4997 data: 3.0777 max mem: 22446 +train: [9] [ 20/400] eta: 0:04:05 lr: 0.000249 loss: 0.1960 (0.2113) grad: 0.1865 (0.2010) time: 0.5041 data: 0.0029 max mem: 22446 +train: [9] [ 40/400] eta: 0:03:23 lr: 0.000248 loss: 0.1648 (0.1964) grad: 0.1692 (0.1757) time: 0.4809 data: 0.0033 max mem: 22446 +train: [9] [ 60/400] eta: 0:03:03 lr: 0.000247 loss: 0.1542 (0.1808) grad: 0.1416 (0.1661) time: 0.4848 data: 0.0035 max mem: 22446 +train: [9] [ 80/400] eta: 0:02:46 lr: 0.000246 loss: 0.1656 (0.1897) grad: 0.1347 (0.1651) time: 0.4612 data: 0.0033 max mem: 22446 +train: [9] [100/400] eta: 0:02:32 lr: 0.000244 loss: 0.1656 (0.1833) grad: 0.1542 (0.1652) time: 0.4657 data: 0.0034 max mem: 22446 +train: [9] [120/400] eta: 0:02:20 lr: 0.000243 loss: 0.1677 (0.1889) grad: 0.1705 (0.1665) time: 0.4628 data: 0.0035 max mem: 22446 +train: [9] [140/400] eta: 0:02:08 lr: 0.000242 loss: 0.1841 (0.1856) grad: 0.1535 (0.1641) time: 0.4589 data: 0.0033 max mem: 22446 +train: [9] [160/400] eta: 0:01:57 lr: 0.000241 loss: 0.1541 (0.1823) grad: 0.1549 (0.1624) time: 0.4522 data: 0.0033 max mem: 22446 +train: [9] [180/400] eta: 0:01:46 lr: 0.000240 loss: 0.1278 (0.1780) grad: 0.1549 (0.1622) time: 0.4493 data: 0.0033 max mem: 22446 +train: [9] [200/400] eta: 0:01:36 lr: 0.000238 loss: 0.1460 (0.1766) grad: 0.1567 (0.1625) time: 0.4432 data: 0.0034 max mem: 22446 +train: [9] [220/400] eta: 0:01:26 lr: 0.000237 loss: 0.1460 (0.1753) grad: 0.1391 (0.1615) time: 0.4502 data: 0.0034 max mem: 22446 +train: [9] [240/400] eta: 0:01:16 lr: 0.000236 loss: 0.1435 (0.1739) grad: 0.1322 (0.1593) time: 0.4495 data: 0.0033 max mem: 22446 +train: [9] [260/400] eta: 0:01:06 lr: 0.000234 loss: 0.1481 (0.1756) grad: 0.1556 (0.1613) time: 0.4562 data: 0.0033 max mem: 22446 +train: [9] [280/400] eta: 0:00:56 lr: 0.000233 loss: 0.2109 (0.1774) grad: 0.1730 (0.1634) time: 0.4510 data: 0.0034 max mem: 22446 +train: [9] [300/400] eta: 0:00:48 lr: 0.000232 loss: 0.1575 (0.1762) grad: 0.1532 (0.1631) time: 0.6177 data: 0.1844 max mem: 22446 +train: [9] [320/400] eta: 0:00:38 lr: 0.000230 loss: 0.1178 (0.1739) grad: 0.1452 (0.1622) time: 0.4476 data: 0.0036 max mem: 22446 +train: [9] [340/400] eta: 0:00:28 lr: 0.000229 loss: 0.1302 (0.1732) grad: 0.1464 (0.1620) time: 0.4570 data: 0.0033 max mem: 22446 +train: [9] [360/400] eta: 0:00:19 lr: 0.000228 loss: 0.1365 (0.1717) grad: 0.1525 (0.1615) time: 0.4550 data: 0.0034 max mem: 22446 +train: [9] [380/400] eta: 0:00:09 lr: 0.000226 loss: 0.1325 (0.1690) grad: 0.1322 (0.1582) time: 0.4651 data: 0.0035 max mem: 22446 +train: [9] [399/400] eta: 0:00:00 lr: 0.000225 loss: 0.1144 (0.1683) grad: 0.0985 (0.1565) time: 0.4844 data: 0.0034 max mem: 22446 +train: [9] Total time: 0:03:11 (0.4776 s / it) +train: [9] Summary: lr: 0.000225 loss: 0.1144 (0.1683) grad: 0.0985 (0.1565) +eval (validation): [9] [ 0/63] eta: 0:04:29 time: 4.2764 data: 3.9605 max mem: 22446 +eval (validation): [9] [20/63] eta: 0:00:26 time: 0.4315 data: 0.0030 max mem: 22446 +eval (validation): [9] [40/63] eta: 0:00:11 time: 0.4115 data: 0.0034 max mem: 22446 +eval (validation): [9] [60/63] eta: 0:00:01 time: 0.3769 data: 0.0032 max mem: 22446 +eval (validation): [9] [62/63] eta: 0:00:00 time: 0.3744 data: 0.0033 max mem: 22446 +eval (validation): [9] Total time: 0:00:29 (0.4713 s / it) +cv: [9] best hparam: (0.85, 1.0) (023) ('023_lr8.5e-01_wd1.0e+00') loss: 0.026 acc: 0.992 f1: 0.991 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [10] [ 0/400] eta: 0:23:41 lr: nan time: 3.5538 data: 3.1351 max mem: 22446 +train: [10] [ 20/400] eta: 0:03:53 lr: 0.000224 loss: 0.1518 (0.1716) grad: 0.1458 (0.1430) time: 0.4682 data: 0.0024 max mem: 22446 +train: [10] [ 40/400] eta: 0:03:16 lr: 0.000222 loss: 0.1324 (0.1485) grad: 0.1159 (0.1160) time: 0.4718 data: 0.0030 max mem: 22446 +train: [10] [ 60/400] eta: 0:02:56 lr: 0.000221 loss: 0.1156 (0.1396) grad: 0.0880 (0.1105) time: 0.4617 data: 0.0034 max mem: 22446 +train: [10] [ 80/400] eta: 0:02:40 lr: 0.000220 loss: 0.1124 (0.1349) grad: 0.1079 (0.1184) time: 0.4560 data: 0.0033 max mem: 22446 +train: [10] [100/400] eta: 0:02:27 lr: 0.000218 loss: 0.1082 (0.1315) grad: 0.1016 (0.1126) time: 0.4533 data: 0.0034 max mem: 22446 +train: [10] [120/400] eta: 0:02:16 lr: 0.000217 loss: 0.1175 (0.1295) grad: 0.1016 (0.1112) time: 0.4613 data: 0.0035 max mem: 22446 +train: [10] [140/400] eta: 0:02:05 lr: 0.000215 loss: 0.1340 (0.1322) grad: 0.1178 (0.1141) time: 0.4469 data: 0.0035 max mem: 22446 +train: [10] [160/400] eta: 0:01:54 lr: 0.000214 loss: 0.1282 (0.1334) grad: 0.1311 (0.1190) time: 0.4495 data: 0.0034 max mem: 22446 +train: [10] [180/400] eta: 0:01:44 lr: 0.000213 loss: 0.1227 (0.1354) grad: 0.1362 (0.1208) time: 0.4580 data: 0.0034 max mem: 22446 +train: [10] [200/400] eta: 0:01:34 lr: 0.000211 loss: 0.1240 (0.1355) grad: 0.1346 (0.1222) time: 0.4560 data: 0.0034 max mem: 22446 +train: [10] [220/400] eta: 0:01:25 lr: 0.000210 loss: 0.1176 (0.1355) grad: 0.1129 (0.1207) time: 0.4631 data: 0.0034 max mem: 22446 +train: [10] [240/400] eta: 0:01:15 lr: 0.000208 loss: 0.1176 (0.1367) grad: 0.1225 (0.1220) time: 0.4609 data: 0.0034 max mem: 22446 +train: [10] [260/400] eta: 0:01:06 lr: 0.000207 loss: 0.1251 (0.1361) grad: 0.1255 (0.1226) time: 0.4777 data: 0.0034 max mem: 22446 +train: [10] [280/400] eta: 0:00:56 lr: 0.000205 loss: 0.1162 (0.1347) grad: 0.1255 (0.1212) time: 0.4794 data: 0.0034 max mem: 22446 +train: [10] [300/400] eta: 0:00:48 lr: 0.000204 loss: 0.1041 (0.1344) grad: 0.1141 (0.1202) time: 0.6589 data: 0.1788 max mem: 22446 +train: [10] [320/400] eta: 0:00:38 lr: 0.000202 loss: 0.1041 (0.1335) grad: 0.1141 (0.1197) time: 0.4710 data: 0.0032 max mem: 22446 +train: [10] [340/400] eta: 0:00:28 lr: 0.000201 loss: 0.0955 (0.1320) grad: 0.1068 (0.1189) time: 0.4614 data: 0.0031 max mem: 22446 +train: [10] [360/400] eta: 0:00:19 lr: 0.000199 loss: 0.0914 (0.1313) grad: 0.0911 (0.1168) time: 0.4610 data: 0.0035 max mem: 22446 +train: [10] [380/400] eta: 0:00:09 lr: 0.000198 loss: 0.0970 (0.1308) grad: 0.0800 (0.1150) time: 0.4572 data: 0.0033 max mem: 22446 +train: [10] [399/400] eta: 0:00:00 lr: 0.000196 loss: 0.1068 (0.1296) grad: 0.0602 (0.1124) time: 0.4531 data: 0.0033 max mem: 22446 +train: [10] Total time: 0:03:11 (0.4794 s / it) +train: [10] Summary: lr: 0.000196 loss: 0.1068 (0.1296) grad: 0.0602 (0.1124) +eval (validation): [10] [ 0/63] eta: 0:03:28 time: 3.3049 data: 3.0559 max mem: 22446 +eval (validation): [10] [20/63] eta: 0:00:21 time: 0.3643 data: 0.0038 max mem: 22446 +eval (validation): [10] [40/63] eta: 0:00:10 time: 0.3637 data: 0.0032 max mem: 22446 +eval (validation): [10] [60/63] eta: 0:00:01 time: 0.3471 data: 0.0033 max mem: 22446 +eval (validation): [10] [62/63] eta: 0:00:00 time: 0.3382 data: 0.0032 max mem: 22446 +eval (validation): [10] Total time: 0:00:25 (0.4079 s / it) +cv: [10] best hparam: (3.1, 1.0) (031) ('031_lr3.1e+00_wd1.0e+00') loss: 0.026 acc: 0.992 f1: 0.989 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [11] [ 0/400] eta: 0:22:39 lr: nan time: 3.3997 data: 3.0498 max mem: 22446 +train: [11] [ 20/400] eta: 0:04:00 lr: 0.000195 loss: 0.1126 (0.1094) grad: 0.0752 (0.0825) time: 0.4957 data: 0.0035 max mem: 22446 +train: [11] [ 40/400] eta: 0:03:22 lr: 0.000193 loss: 0.1126 (0.1083) grad: 0.0766 (0.0794) time: 0.4854 data: 0.0033 max mem: 22446 +train: [11] [ 60/400] eta: 0:03:02 lr: 0.000192 loss: 0.1133 (0.1124) grad: 0.0813 (0.0852) time: 0.4815 data: 0.0036 max mem: 22446 +train: [11] [ 80/400] eta: 0:02:47 lr: 0.000190 loss: 0.1133 (0.1143) grad: 0.1040 (0.0926) time: 0.4865 data: 0.0036 max mem: 22446 +train: [11] [100/400] eta: 0:02:33 lr: 0.000189 loss: 0.0997 (0.1102) grad: 0.1077 (0.0885) time: 0.4697 data: 0.0035 max mem: 22446 +train: [11] [120/400] eta: 0:02:22 lr: 0.000187 loss: 0.0948 (0.1083) grad: 0.0772 (0.0881) time: 0.4871 data: 0.0038 max mem: 22446 +train: [11] [140/400] eta: 0:02:11 lr: 0.000186 loss: 0.1081 (0.1111) grad: 0.0891 (0.0915) time: 0.4798 data: 0.0034 max mem: 22446 +train: [11] [160/400] eta: 0:02:00 lr: 0.000184 loss: 0.1136 (0.1104) grad: 0.0889 (0.0917) time: 0.4779 data: 0.0034 max mem: 22446 +train: [11] [180/400] eta: 0:01:49 lr: 0.000183 loss: 0.0969 (0.1103) grad: 0.0856 (0.0913) time: 0.4824 data: 0.0034 max mem: 22446 +train: [11] [200/400] eta: 0:01:39 lr: 0.000181 loss: 0.0922 (0.1087) grad: 0.0728 (0.0902) time: 0.4690 data: 0.0033 max mem: 22446 +train: [11] [220/400] eta: 0:01:28 lr: 0.000180 loss: 0.0862 (0.1074) grad: 0.0730 (0.0897) time: 0.4586 data: 0.0035 max mem: 22446 +train: [11] [240/400] eta: 0:01:18 lr: 0.000178 loss: 0.0912 (0.1067) grad: 0.0782 (0.0890) time: 0.4649 data: 0.0035 max mem: 22446 +train: [11] [260/400] eta: 0:01:08 lr: 0.000177 loss: 0.1083 (0.1079) grad: 0.0782 (0.0891) time: 0.4600 data: 0.0035 max mem: 22446 +train: [11] [280/400] eta: 0:00:58 lr: 0.000175 loss: 0.1083 (0.1080) grad: 0.0802 (0.0890) time: 0.4426 data: 0.0034 max mem: 22446 +train: [11] [300/400] eta: 0:00:49 lr: 0.000174 loss: 0.0993 (0.1075) grad: 0.0796 (0.0887) time: 0.6198 data: 0.1786 max mem: 22446 +train: [11] [320/400] eta: 0:00:39 lr: 0.000172 loss: 0.0939 (0.1073) grad: 0.0792 (0.0878) time: 0.4472 data: 0.0030 max mem: 22446 +train: [11] [340/400] eta: 0:00:29 lr: 0.000170 loss: 0.0892 (0.1063) grad: 0.0515 (0.0863) time: 0.4748 data: 0.0033 max mem: 22446 +train: [11] [360/400] eta: 0:00:19 lr: 0.000169 loss: 0.0892 (0.1053) grad: 0.0581 (0.0851) time: 0.4779 data: 0.0039 max mem: 22446 +train: [11] [380/400] eta: 0:00:09 lr: 0.000167 loss: 0.0846 (0.1043) grad: 0.0601 (0.0840) time: 0.4609 data: 0.0036 max mem: 22446 +train: [11] [399/400] eta: 0:00:00 lr: 0.000166 loss: 0.0924 (0.1039) grad: 0.0658 (0.0834) time: 0.4549 data: 0.0033 max mem: 22446 +train: [11] Total time: 0:03:14 (0.4865 s / it) +train: [11] Summary: lr: 0.000166 loss: 0.0924 (0.1039) grad: 0.0658 (0.0834) +eval (validation): [11] [ 0/63] eta: 0:03:14 time: 3.0870 data: 2.8291 max mem: 22446 +eval (validation): [11] [20/63] eta: 0:00:20 time: 0.3420 data: 0.0042 max mem: 22446 +eval (validation): [11] [40/63] eta: 0:00:09 time: 0.3413 data: 0.0028 max mem: 22446 +eval (validation): [11] [60/63] eta: 0:00:01 time: 0.3270 data: 0.0031 max mem: 22446 +eval (validation): [11] [62/63] eta: 0:00:00 time: 0.3252 data: 0.0031 max mem: 22446 +eval (validation): [11] Total time: 0:00:24 (0.3843 s / it) +cv: [11] best hparam: (5.1, 1.0) (034) ('034_lr5.1e+00_wd1.0e+00') loss: 0.034 acc: 0.992 f1: 0.991 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [12] [ 0/400] eta: 0:22:47 lr: nan time: 3.4191 data: 3.0011 max mem: 22446 +train: [12] [ 20/400] eta: 0:04:08 lr: 0.000164 loss: 0.0901 (0.0982) grad: 0.0603 (0.0724) time: 0.5150 data: 0.0035 max mem: 22446 +train: [12] [ 40/400] eta: 0:03:20 lr: 0.000163 loss: 0.0867 (0.0931) grad: 0.0603 (0.0724) time: 0.4544 data: 0.0034 max mem: 22446 +train: [12] [ 60/400] eta: 0:02:57 lr: 0.000161 loss: 0.0820 (0.0931) grad: 0.0740 (0.0737) time: 0.4511 data: 0.0034 max mem: 22446 +train: [12] [ 80/400] eta: 0:02:41 lr: 0.000160 loss: 0.0804 (0.0907) grad: 0.0523 (0.0680) time: 0.4554 data: 0.0033 max mem: 22446 +train: [12] [100/400] eta: 0:02:29 lr: 0.000158 loss: 0.0909 (0.0918) grad: 0.0508 (0.0664) time: 0.4667 data: 0.0035 max mem: 22446 +train: [12] [120/400] eta: 0:02:17 lr: 0.000156 loss: 0.0983 (0.0948) grad: 0.0596 (0.0674) time: 0.4579 data: 0.0033 max mem: 22446 +train: [12] [140/400] eta: 0:02:06 lr: 0.000155 loss: 0.0955 (0.0944) grad: 0.0596 (0.0663) time: 0.4623 data: 0.0034 max mem: 22446 +train: [12] [160/400] eta: 0:01:56 lr: 0.000153 loss: 0.0784 (0.0931) grad: 0.0458 (0.0644) time: 0.4574 data: 0.0033 max mem: 22446 +train: [12] [180/400] eta: 0:01:45 lr: 0.000152 loss: 0.0820 (0.0930) grad: 0.0442 (0.0642) time: 0.4573 data: 0.0033 max mem: 22446 +train: [12] [200/400] eta: 0:01:35 lr: 0.000150 loss: 0.0776 (0.0921) grad: 0.0442 (0.0638) time: 0.4589 data: 0.0033 max mem: 22446 +train: [12] [220/400] eta: 0:01:25 lr: 0.000149 loss: 0.0776 (0.0925) grad: 0.0701 (0.0649) time: 0.4494 data: 0.0033 max mem: 22446 +train: [12] [240/400] eta: 0:01:16 lr: 0.000147 loss: 0.0898 (0.0928) grad: 0.0661 (0.0644) time: 0.4673 data: 0.0034 max mem: 22446 +train: [12] [260/400] eta: 0:01:06 lr: 0.000145 loss: 0.0869 (0.0920) grad: 0.0477 (0.0639) time: 0.4600 data: 0.0033 max mem: 22446 +train: [12] [280/400] eta: 0:00:56 lr: 0.000144 loss: 0.0810 (0.0914) grad: 0.0628 (0.0641) time: 0.4551 data: 0.0034 max mem: 22446 +train: [12] [300/400] eta: 0:00:48 lr: 0.000142 loss: 0.0880 (0.0916) grad: 0.0634 (0.0634) time: 0.6225 data: 0.1775 max mem: 22446 +train: [12] [320/400] eta: 0:00:38 lr: 0.000141 loss: 0.0882 (0.0913) grad: 0.0460 (0.0630) time: 0.4561 data: 0.0030 max mem: 22446 +train: [12] [340/400] eta: 0:00:28 lr: 0.000139 loss: 0.0815 (0.0912) grad: 0.0453 (0.0628) time: 0.4605 data: 0.0039 max mem: 22446 +train: [12] [360/400] eta: 0:00:19 lr: 0.000138 loss: 0.0841 (0.0908) grad: 0.0453 (0.0625) time: 0.4746 data: 0.0030 max mem: 22446 +train: [12] [380/400] eta: 0:00:09 lr: 0.000136 loss: 0.0812 (0.0908) grad: 0.0548 (0.0629) time: 0.4940 data: 0.0036 max mem: 22446 +train: [12] [399/400] eta: 0:00:00 lr: 0.000134 loss: 0.0812 (0.0907) grad: 0.0483 (0.0625) time: 0.4844 data: 0.0035 max mem: 22446 +train: [12] Total time: 0:03:12 (0.4807 s / it) +train: [12] Summary: lr: 0.000134 loss: 0.0812 (0.0907) grad: 0.0483 (0.0625) +eval (validation): [12] [ 0/63] eta: 0:03:34 time: 3.3989 data: 3.1382 max mem: 22446 +eval (validation): [12] [20/63] eta: 0:00:20 time: 0.3375 data: 0.0028 max mem: 22446 +eval (validation): [12] [40/63] eta: 0:00:09 time: 0.3440 data: 0.0036 max mem: 22446 +eval (validation): [12] [60/63] eta: 0:00:01 time: 0.3381 data: 0.0023 max mem: 22446 +eval (validation): [12] [62/63] eta: 0:00:00 time: 0.3372 data: 0.0025 max mem: 22446 +eval (validation): [12] Total time: 0:00:24 (0.3919 s / it) +cv: [12] best hparam: (2.3, 1.0) (029) ('029_lr2.3e+00_wd1.0e+00') loss: 0.026 acc: 0.992 f1: 0.990 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [13] [ 0/400] eta: 0:22:40 lr: nan time: 3.4003 data: 3.0056 max mem: 22446 +train: [13] [ 20/400] eta: 0:03:45 lr: 0.000133 loss: 0.0881 (0.0856) grad: 0.0403 (0.0565) time: 0.4522 data: 0.0039 max mem: 22446 +train: [13] [ 40/400] eta: 0:03:07 lr: 0.000131 loss: 0.0751 (0.0816) grad: 0.0403 (0.0524) time: 0.4445 data: 0.0032 max mem: 22446 +train: [13] [ 60/400] eta: 0:02:48 lr: 0.000130 loss: 0.0724 (0.0814) grad: 0.0468 (0.0551) time: 0.4448 data: 0.0034 max mem: 22446 +train: [13] [ 80/400] eta: 0:02:35 lr: 0.000128 loss: 0.0760 (0.0812) grad: 0.0451 (0.0517) time: 0.4544 data: 0.0035 max mem: 22446 +train: [13] [100/400] eta: 0:02:24 lr: 0.000127 loss: 0.0760 (0.0806) grad: 0.0396 (0.0517) time: 0.4737 data: 0.0036 max mem: 22446 +train: [13] [120/400] eta: 0:02:14 lr: 0.000125 loss: 0.0724 (0.0800) grad: 0.0420 (0.0511) time: 0.4578 data: 0.0034 max mem: 22446 +train: [13] [140/400] eta: 0:02:03 lr: 0.000124 loss: 0.0721 (0.0803) grad: 0.0427 (0.0524) time: 0.4543 data: 0.0034 max mem: 22446 +train: [13] [160/400] eta: 0:01:53 lr: 0.000122 loss: 0.0738 (0.0798) grad: 0.0390 (0.0514) time: 0.4597 data: 0.0034 max mem: 22446 +train: [13] [180/400] eta: 0:01:43 lr: 0.000120 loss: 0.0802 (0.0805) grad: 0.0390 (0.0508) time: 0.4645 data: 0.0034 max mem: 22446 +train: [13] [200/400] eta: 0:01:34 lr: 0.000119 loss: 0.0835 (0.0811) grad: 0.0461 (0.0520) time: 0.4638 data: 0.0035 max mem: 22446 +train: [13] [220/400] eta: 0:01:24 lr: 0.000117 loss: 0.0772 (0.0812) grad: 0.0561 (0.0527) time: 0.4616 data: 0.0034 max mem: 22446 +train: [13] [240/400] eta: 0:01:15 lr: 0.000116 loss: 0.0737 (0.0807) grad: 0.0422 (0.0519) time: 0.4566 data: 0.0034 max mem: 22446 +train: [13] [260/400] eta: 0:01:05 lr: 0.000114 loss: 0.0716 (0.0806) grad: 0.0413 (0.0516) time: 0.4597 data: 0.0034 max mem: 22446 +train: [13] [280/400] eta: 0:00:56 lr: 0.000113 loss: 0.0703 (0.0801) grad: 0.0441 (0.0518) time: 0.4556 data: 0.0034 max mem: 22446 +train: [13] [300/400] eta: 0:00:48 lr: 0.000111 loss: 0.0754 (0.0799) grad: 0.0481 (0.0523) time: 0.6688 data: 0.1826 max mem: 22446 +train: [13] [320/400] eta: 0:00:38 lr: 0.000110 loss: 0.0776 (0.0800) grad: 0.0483 (0.0524) time: 0.4654 data: 0.0026 max mem: 22446 +train: [13] [340/400] eta: 0:00:28 lr: 0.000108 loss: 0.0767 (0.0797) grad: 0.0478 (0.0525) time: 0.4781 data: 0.0031 max mem: 22446 +train: [13] [360/400] eta: 0:00:19 lr: 0.000107 loss: 0.0649 (0.0792) grad: 0.0406 (0.0519) time: 0.5117 data: 0.0037 max mem: 22446 +train: [13] [380/400] eta: 0:00:09 lr: 0.000105 loss: 0.0704 (0.0792) grad: 0.0415 (0.0517) time: 0.4651 data: 0.0035 max mem: 22446 +train: [13] [399/400] eta: 0:00:00 lr: 0.000104 loss: 0.0757 (0.0793) grad: 0.0468 (0.0516) time: 0.4678 data: 0.0035 max mem: 22446 +train: [13] Total time: 0:03:12 (0.4807 s / it) +train: [13] Summary: lr: 0.000104 loss: 0.0757 (0.0793) grad: 0.0468 (0.0516) +eval (validation): [13] [ 0/63] eta: 0:03:30 time: 3.3405 data: 3.0935 max mem: 22446 +eval (validation): [13] [20/63] eta: 0:00:20 time: 0.3289 data: 0.0042 max mem: 22446 +eval (validation): [13] [40/63] eta: 0:00:09 time: 0.3498 data: 0.0030 max mem: 22446 +eval (validation): [13] [60/63] eta: 0:00:01 time: 0.3313 data: 0.0034 max mem: 22446 +eval (validation): [13] [62/63] eta: 0:00:00 time: 0.3316 data: 0.0034 max mem: 22446 +eval (validation): [13] Total time: 0:00:24 (0.3872 s / it) +cv: [13] best hparam: (2.3, 1.0) (029) ('029_lr2.3e+00_wd1.0e+00') loss: 0.027 acc: 0.992 f1: 0.990 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [14] [ 0/400] eta: 0:26:38 lr: nan time: 3.9962 data: 3.6512 max mem: 22446 +train: [14] [ 20/400] eta: 0:03:55 lr: 0.000102 loss: 0.0798 (0.0787) grad: 0.0384 (0.0439) time: 0.4519 data: 0.0029 max mem: 22446 +train: [14] [ 40/400] eta: 0:03:13 lr: 0.000101 loss: 0.0725 (0.0770) grad: 0.0384 (0.0455) time: 0.4494 data: 0.0026 max mem: 22446 +train: [14] [ 60/400] eta: 0:02:52 lr: 0.000099 loss: 0.0711 (0.0755) grad: 0.0402 (0.0461) time: 0.4480 data: 0.0035 max mem: 22446 +train: [14] [ 80/400] eta: 0:02:37 lr: 0.000098 loss: 0.0676 (0.0749) grad: 0.0415 (0.0468) time: 0.4495 data: 0.0035 max mem: 22446 +train: [14] [100/400] eta: 0:02:27 lr: 0.000096 loss: 0.0651 (0.0744) grad: 0.0409 (0.0450) time: 0.4805 data: 0.0035 max mem: 22446 +train: [14] [120/400] eta: 0:02:15 lr: 0.000095 loss: 0.0721 (0.0758) grad: 0.0382 (0.0442) time: 0.4573 data: 0.0035 max mem: 22446 +train: [14] [140/400] eta: 0:02:06 lr: 0.000093 loss: 0.0782 (0.0768) grad: 0.0413 (0.0441) time: 0.4814 data: 0.0036 max mem: 22446 +train: [14] [160/400] eta: 0:01:56 lr: 0.000092 loss: 0.0637 (0.0759) grad: 0.0379 (0.0437) time: 0.4965 data: 0.0036 max mem: 22446 +train: [14] [180/400] eta: 0:01:47 lr: 0.000090 loss: 0.0637 (0.0750) grad: 0.0361 (0.0430) time: 0.5113 data: 0.0040 max mem: 22446 +train: [14] [200/400] eta: 0:01:37 lr: 0.000089 loss: 0.0666 (0.0752) grad: 0.0380 (0.0426) time: 0.4812 data: 0.0035 max mem: 22446 +train: [14] [220/400] eta: 0:01:27 lr: 0.000088 loss: 0.0720 (0.0749) grad: 0.0380 (0.0424) time: 0.4635 data: 0.0033 max mem: 22446 +train: [14] [240/400] eta: 0:01:17 lr: 0.000086 loss: 0.0722 (0.0746) grad: 0.0375 (0.0421) time: 0.4628 data: 0.0033 max mem: 22446 +train: [14] [260/400] eta: 0:01:07 lr: 0.000085 loss: 0.0690 (0.0740) grad: 0.0367 (0.0419) time: 0.4735 data: 0.0034 max mem: 22446 +train: [14] [280/400] eta: 0:00:57 lr: 0.000083 loss: 0.0745 (0.0748) grad: 0.0402 (0.0420) time: 0.4659 data: 0.0033 max mem: 22446 +train: [14] [300/400] eta: 0:00:49 lr: 0.000082 loss: 0.0780 (0.0750) grad: 0.0387 (0.0420) time: 0.6342 data: 0.1801 max mem: 22446 +train: [14] [320/400] eta: 0:00:39 lr: 0.000081 loss: 0.0729 (0.0748) grad: 0.0373 (0.0416) time: 0.4632 data: 0.0034 max mem: 22446 +train: [14] [340/400] eta: 0:00:29 lr: 0.000079 loss: 0.0755 (0.0752) grad: 0.0355 (0.0414) time: 0.4561 data: 0.0034 max mem: 22446 +train: [14] [360/400] eta: 0:00:19 lr: 0.000078 loss: 0.0772 (0.0753) grad: 0.0373 (0.0413) time: 0.4607 data: 0.0037 max mem: 22446 +train: [14] [380/400] eta: 0:00:09 lr: 0.000076 loss: 0.0750 (0.0755) grad: 0.0399 (0.0413) time: 0.4563 data: 0.0034 max mem: 22446 +train: [14] [399/400] eta: 0:00:00 lr: 0.000075 loss: 0.0749 (0.0755) grad: 0.0391 (0.0412) time: 0.4671 data: 0.0034 max mem: 22446 +train: [14] Total time: 0:03:13 (0.4847 s / it) +train: [14] Summary: lr: 0.000075 loss: 0.0749 (0.0755) grad: 0.0391 (0.0412) +eval (validation): [14] [ 0/63] eta: 0:03:26 time: 3.2712 data: 2.9781 max mem: 22446 +eval (validation): [14] [20/63] eta: 0:00:22 time: 0.3899 data: 0.0031 max mem: 22446 +eval (validation): [14] [40/63] eta: 0:00:10 time: 0.3663 data: 0.0035 max mem: 22446 +eval (validation): [14] [60/63] eta: 0:00:01 time: 0.3650 data: 0.0036 max mem: 22446 +eval (validation): [14] [62/63] eta: 0:00:00 time: 0.3653 data: 0.0035 max mem: 22446 +eval (validation): [14] Total time: 0:00:26 (0.4227 s / it) +cv: [14] best hparam: (0.85, 1.0) (023) ('023_lr8.5e-01_wd1.0e+00') loss: 0.025 acc: 0.992 f1: 0.990 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [15] [ 0/400] eta: 0:28:26 lr: nan time: 4.2667 data: 3.8552 max mem: 22446 +train: [15] [ 20/400] eta: 0:04:16 lr: 0.000074 loss: 0.0681 (0.0782) grad: 0.0369 (0.0397) time: 0.4963 data: 0.0022 max mem: 22446 +train: [15] [ 40/400] eta: 0:03:28 lr: 0.000072 loss: 0.0778 (0.0774) grad: 0.0389 (0.0409) time: 0.4778 data: 0.0032 max mem: 22446 +train: [15] [ 60/400] eta: 0:03:04 lr: 0.000071 loss: 0.0649 (0.0725) grad: 0.0374 (0.0394) time: 0.4670 data: 0.0035 max mem: 22446 +train: [15] [ 80/400] eta: 0:02:48 lr: 0.000070 loss: 0.0628 (0.0713) grad: 0.0349 (0.0386) time: 0.4772 data: 0.0034 max mem: 22446 +train: [15] [100/400] eta: 0:02:34 lr: 0.000068 loss: 0.0627 (0.0700) grad: 0.0353 (0.0384) time: 0.4624 data: 0.0033 max mem: 22446 +train: [15] [120/400] eta: 0:02:21 lr: 0.000067 loss: 0.0625 (0.0698) grad: 0.0357 (0.0385) time: 0.4667 data: 0.0033 max mem: 22446 +train: [15] [140/400] eta: 0:02:09 lr: 0.000066 loss: 0.0663 (0.0700) grad: 0.0369 (0.0383) time: 0.4585 data: 0.0033 max mem: 22446 +train: [15] [160/400] eta: 0:01:58 lr: 0.000064 loss: 0.0667 (0.0695) grad: 0.0378 (0.0385) time: 0.4671 data: 0.0034 max mem: 22446 +train: [15] [180/400] eta: 0:01:48 lr: 0.000063 loss: 0.0634 (0.0699) grad: 0.0377 (0.0384) time: 0.4673 data: 0.0034 max mem: 22446 +train: [15] [200/400] eta: 0:01:37 lr: 0.000062 loss: 0.0802 (0.0706) grad: 0.0361 (0.0383) time: 0.4615 data: 0.0033 max mem: 22446 +train: [15] [220/400] eta: 0:01:27 lr: 0.000061 loss: 0.0696 (0.0701) grad: 0.0349 (0.0383) time: 0.4668 data: 0.0033 max mem: 22446 +train: [15] [240/400] eta: 0:01:17 lr: 0.000059 loss: 0.0659 (0.0700) grad: 0.0376 (0.0385) time: 0.4751 data: 0.0033 max mem: 22446 +train: [15] [260/400] eta: 0:01:07 lr: 0.000058 loss: 0.0640 (0.0702) grad: 0.0368 (0.0382) time: 0.4620 data: 0.0034 max mem: 22446 +train: [15] [280/400] eta: 0:00:57 lr: 0.000057 loss: 0.0640 (0.0703) grad: 0.0355 (0.0382) time: 0.4548 data: 0.0035 max mem: 22446 +train: [15] [300/400] eta: 0:00:48 lr: 0.000056 loss: 0.0653 (0.0703) grad: 0.0354 (0.0381) time: 0.5952 data: 0.1672 max mem: 22446 +train: [15] [320/400] eta: 0:00:38 lr: 0.000054 loss: 0.0684 (0.0702) grad: 0.0362 (0.0382) time: 0.4546 data: 0.0033 max mem: 22446 +train: [15] [340/400] eta: 0:00:29 lr: 0.000053 loss: 0.0684 (0.0703) grad: 0.0383 (0.0384) time: 0.4644 data: 0.0032 max mem: 22446 +train: [15] [360/400] eta: 0:00:19 lr: 0.000052 loss: 0.0670 (0.0704) grad: 0.0391 (0.0385) time: 0.4725 data: 0.0035 max mem: 22446 +train: [15] [380/400] eta: 0:00:09 lr: 0.000051 loss: 0.0625 (0.0700) grad: 0.0374 (0.0384) time: 0.4610 data: 0.0034 max mem: 22446 +train: [15] [399/400] eta: 0:00:00 lr: 0.000050 loss: 0.0680 (0.0703) grad: 0.0368 (0.0383) time: 0.4453 data: 0.0033 max mem: 22446 +train: [15] Total time: 0:03:13 (0.4825 s / it) +train: [15] Summary: lr: 0.000050 loss: 0.0680 (0.0703) grad: 0.0368 (0.0383) +eval (validation): [15] [ 0/63] eta: 0:03:19 time: 3.1677 data: 2.9385 max mem: 22446 +eval (validation): [15] [20/63] eta: 0:00:19 time: 0.3146 data: 0.0041 max mem: 22446 +eval (validation): [15] [40/63] eta: 0:00:09 time: 0.3484 data: 0.0032 max mem: 22446 +eval (validation): [15] [60/63] eta: 0:00:01 time: 0.3283 data: 0.0033 max mem: 22446 +eval (validation): [15] [62/63] eta: 0:00:00 time: 0.3256 data: 0.0033 max mem: 22446 +eval (validation): [15] Total time: 0:00:23 (0.3793 s / it) +cv: [15] best hparam: (5.1, 1.0) (034) ('034_lr5.1e+00_wd1.0e+00') loss: 0.032 acc: 0.992 f1: 0.991 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [16] [ 0/400] eta: 0:22:22 lr: nan time: 3.3550 data: 2.9627 max mem: 22446 +train: [16] [ 20/400] eta: 0:03:56 lr: 0.000048 loss: 0.0648 (0.0711) grad: 0.0340 (0.0359) time: 0.4861 data: 0.0030 max mem: 22446 +train: [16] [ 40/400] eta: 0:03:13 lr: 0.000047 loss: 0.0667 (0.0704) grad: 0.0340 (0.0370) time: 0.4476 data: 0.0031 max mem: 22446 +train: [16] [ 60/400] eta: 0:02:53 lr: 0.000046 loss: 0.0671 (0.0697) grad: 0.0337 (0.0364) time: 0.4538 data: 0.0033 max mem: 22446 +train: [16] [ 80/400] eta: 0:02:39 lr: 0.000045 loss: 0.0710 (0.0702) grad: 0.0341 (0.0366) time: 0.4594 data: 0.0033 max mem: 22446 +train: [16] [100/400] eta: 0:02:26 lr: 0.000044 loss: 0.0704 (0.0704) grad: 0.0354 (0.0365) time: 0.4502 data: 0.0033 max mem: 22446 +train: [16] [120/400] eta: 0:02:15 lr: 0.000043 loss: 0.0625 (0.0700) grad: 0.0365 (0.0370) time: 0.4523 data: 0.0034 max mem: 22446 +train: [16] [140/400] eta: 0:02:04 lr: 0.000042 loss: 0.0637 (0.0701) grad: 0.0375 (0.0374) time: 0.4546 data: 0.0032 max mem: 22446 +train: [16] [160/400] eta: 0:01:53 lr: 0.000041 loss: 0.0680 (0.0696) grad: 0.0373 (0.0374) time: 0.4448 data: 0.0033 max mem: 22446 +train: [16] [180/400] eta: 0:01:44 lr: 0.000040 loss: 0.0680 (0.0698) grad: 0.0351 (0.0370) time: 0.4784 data: 0.0034 max mem: 22446 +train: [16] [200/400] eta: 0:01:34 lr: 0.000039 loss: 0.0713 (0.0707) grad: 0.0368 (0.0375) time: 0.4451 data: 0.0034 max mem: 22446 +train: [16] [220/400] eta: 0:01:24 lr: 0.000038 loss: 0.0647 (0.0705) grad: 0.0376 (0.0373) time: 0.4552 data: 0.0033 max mem: 22446 +train: [16] [240/400] eta: 0:01:15 lr: 0.000036 loss: 0.0624 (0.0702) grad: 0.0333 (0.0370) time: 0.4642 data: 0.0033 max mem: 22446 +train: [16] [260/400] eta: 0:01:05 lr: 0.000035 loss: 0.0701 (0.0705) grad: 0.0337 (0.0370) time: 0.4535 data: 0.0033 max mem: 22446 +train: [16] [280/400] eta: 0:00:56 lr: 0.000034 loss: 0.0662 (0.0703) grad: 0.0377 (0.0374) time: 0.4536 data: 0.0033 max mem: 22446 +train: [16] [300/400] eta: 0:00:47 lr: 0.000033 loss: 0.0638 (0.0702) grad: 0.0408 (0.0377) time: 0.6245 data: 0.1739 max mem: 22446 +train: [16] [320/400] eta: 0:00:38 lr: 0.000032 loss: 0.0664 (0.0701) grad: 0.0372 (0.0377) time: 0.4478 data: 0.0044 max mem: 22446 +train: [16] [340/400] eta: 0:00:28 lr: 0.000031 loss: 0.0713 (0.0704) grad: 0.0364 (0.0378) time: 0.4512 data: 0.0034 max mem: 22446 +train: [16] [360/400] eta: 0:00:18 lr: 0.000031 loss: 0.0695 (0.0703) grad: 0.0350 (0.0378) time: 0.4619 data: 0.0033 max mem: 22446 +train: [16] [380/400] eta: 0:00:09 lr: 0.000030 loss: 0.0639 (0.0698) grad: 0.0359 (0.0377) time: 0.4564 data: 0.0032 max mem: 22446 +train: [16] [399/400] eta: 0:00:00 lr: 0.000029 loss: 0.0604 (0.0698) grad: 0.0383 (0.0379) time: 0.4484 data: 0.0033 max mem: 22446 +train: [16] Total time: 0:03:08 (0.4720 s / it) +train: [16] Summary: lr: 0.000029 loss: 0.0604 (0.0698) grad: 0.0383 (0.0379) +eval (validation): [16] [ 0/63] eta: 0:03:25 time: 3.2631 data: 3.0286 max mem: 22446 +eval (validation): [16] [20/63] eta: 0:00:20 time: 0.3314 data: 0.0046 max mem: 22446 +eval (validation): [16] [40/63] eta: 0:00:09 time: 0.3254 data: 0.0029 max mem: 22446 +eval (validation): [16] [60/63] eta: 0:00:01 time: 0.3127 data: 0.0030 max mem: 22446 +eval (validation): [16] [62/63] eta: 0:00:00 time: 0.3142 data: 0.0030 max mem: 22446 +eval (validation): [16] Total time: 0:00:23 (0.3734 s / it) +cv: [16] best hparam: (1.2, 1.0) (025) ('025_lr1.2e+00_wd1.0e+00') loss: 0.025 acc: 0.992 f1: 0.990 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [17] [ 0/400] eta: 0:21:33 lr: nan time: 3.2336 data: 2.8660 max mem: 22446 +train: [17] [ 20/400] eta: 0:03:40 lr: 0.000028 loss: 0.0603 (0.0669) grad: 0.0357 (0.0379) time: 0.4477 data: 0.0085 max mem: 22446 +train: [17] [ 40/400] eta: 0:03:11 lr: 0.000027 loss: 0.0663 (0.0701) grad: 0.0377 (0.0386) time: 0.4827 data: 0.0030 max mem: 22446 +train: [17] [ 60/400] eta: 0:02:52 lr: 0.000026 loss: 0.0718 (0.0720) grad: 0.0392 (0.0384) time: 0.4528 data: 0.0033 max mem: 22446 +train: [17] [ 80/400] eta: 0:02:37 lr: 0.000025 loss: 0.0755 (0.0728) grad: 0.0378 (0.0380) time: 0.4438 data: 0.0031 max mem: 22446 +train: [17] [100/400] eta: 0:02:24 lr: 0.000024 loss: 0.0700 (0.0716) grad: 0.0364 (0.0378) time: 0.4506 data: 0.0033 max mem: 22446 +train: [17] [120/400] eta: 0:02:13 lr: 0.000023 loss: 0.0651 (0.0713) grad: 0.0350 (0.0373) time: 0.4469 data: 0.0034 max mem: 22446 +train: [17] [140/400] eta: 0:02:03 lr: 0.000023 loss: 0.0667 (0.0711) grad: 0.0334 (0.0374) time: 0.4519 data: 0.0034 max mem: 22446 +train: [17] [160/400] eta: 0:01:53 lr: 0.000022 loss: 0.0673 (0.0705) grad: 0.0358 (0.0374) time: 0.4602 data: 0.0033 max mem: 22446 +train: [17] [180/400] eta: 0:01:43 lr: 0.000021 loss: 0.0673 (0.0699) grad: 0.0364 (0.0373) time: 0.4609 data: 0.0034 max mem: 22446 +train: [17] [200/400] eta: 0:01:33 lr: 0.000020 loss: 0.0603 (0.0693) grad: 0.0361 (0.0372) time: 0.4467 data: 0.0033 max mem: 22446 +train: [17] [220/400] eta: 0:01:24 lr: 0.000019 loss: 0.0610 (0.0691) grad: 0.0329 (0.0370) time: 0.4573 data: 0.0033 max mem: 22446 +train: [17] [240/400] eta: 0:01:14 lr: 0.000019 loss: 0.0655 (0.0692) grad: 0.0335 (0.0371) time: 0.4564 data: 0.0033 max mem: 22446 +train: [17] [260/400] eta: 0:01:05 lr: 0.000018 loss: 0.0655 (0.0695) grad: 0.0362 (0.0371) time: 0.4515 data: 0.0032 max mem: 22446 +train: [17] [280/400] eta: 0:00:55 lr: 0.000017 loss: 0.0658 (0.0692) grad: 0.0343 (0.0369) time: 0.4565 data: 0.0033 max mem: 22446 +train: [17] [300/400] eta: 0:00:47 lr: 0.000016 loss: 0.0616 (0.0693) grad: 0.0347 (0.0370) time: 0.6297 data: 0.1757 max mem: 22446 +train: [17] [320/400] eta: 0:00:38 lr: 0.000016 loss: 0.0604 (0.0692) grad: 0.0389 (0.0372) time: 0.4956 data: 0.0035 max mem: 22446 +train: [17] [340/400] eta: 0:00:28 lr: 0.000015 loss: 0.0604 (0.0691) grad: 0.0344 (0.0370) time: 0.4565 data: 0.0035 max mem: 22446 +train: [17] [360/400] eta: 0:00:19 lr: 0.000014 loss: 0.0627 (0.0688) grad: 0.0331 (0.0369) time: 0.4669 data: 0.0035 max mem: 22446 +train: [17] [380/400] eta: 0:00:09 lr: 0.000014 loss: 0.0627 (0.0689) grad: 0.0353 (0.0368) time: 0.4592 data: 0.0034 max mem: 22446 +train: [17] [399/400] eta: 0:00:00 lr: 0.000013 loss: 0.0626 (0.0688) grad: 0.0357 (0.0369) time: 0.4750 data: 0.0036 max mem: 22446 +train: [17] Total time: 0:03:09 (0.4747 s / it) +train: [17] Summary: lr: 0.000013 loss: 0.0626 (0.0688) grad: 0.0357 (0.0369) +eval (validation): [17] [ 0/63] eta: 0:03:26 time: 3.2750 data: 3.0251 max mem: 22446 +eval (validation): [17] [20/63] eta: 0:00:22 time: 0.3823 data: 0.0348 max mem: 22446 +eval (validation): [17] [40/63] eta: 0:00:10 time: 0.3612 data: 0.0032 max mem: 22446 +eval (validation): [17] [60/63] eta: 0:00:01 time: 0.3522 data: 0.0033 max mem: 22446 +eval (validation): [17] [62/63] eta: 0:00:00 time: 0.3526 data: 0.0034 max mem: 22446 +eval (validation): [17] Total time: 0:00:26 (0.4143 s / it) +cv: [17] best hparam: (0.85, 1.0) (023) ('023_lr8.5e-01_wd1.0e+00') loss: 0.024 acc: 0.992 f1: 0.990 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [18] [ 0/400] eta: 0:21:29 lr: nan time: 3.2236 data: 2.8885 max mem: 22446 +train: [18] [ 20/400] eta: 0:03:38 lr: 0.000012 loss: 0.0621 (0.0679) grad: 0.0337 (0.0358) time: 0.4430 data: 0.0034 max mem: 22446 +train: [18] [ 40/400] eta: 0:03:03 lr: 0.000012 loss: 0.0633 (0.0703) grad: 0.0364 (0.0367) time: 0.4427 data: 0.0030 max mem: 22446 +train: [18] [ 60/400] eta: 0:02:45 lr: 0.000011 loss: 0.0641 (0.0695) grad: 0.0370 (0.0367) time: 0.4406 data: 0.0035 max mem: 22446 +train: [18] [ 80/400] eta: 0:02:32 lr: 0.000011 loss: 0.0665 (0.0701) grad: 0.0362 (0.0368) time: 0.4406 data: 0.0034 max mem: 22446 +train: [18] [100/400] eta: 0:02:21 lr: 0.000010 loss: 0.0644 (0.0702) grad: 0.0365 (0.0369) time: 0.4522 data: 0.0034 max mem: 22446 +train: [18] [120/400] eta: 0:02:11 lr: 0.000009 loss: 0.0620 (0.0685) grad: 0.0363 (0.0367) time: 0.4596 data: 0.0035 max mem: 22446 +train: [18] [140/400] eta: 0:02:01 lr: 0.000009 loss: 0.0664 (0.0686) grad: 0.0352 (0.0367) time: 0.4503 data: 0.0034 max mem: 22446 +train: [18] [160/400] eta: 0:01:51 lr: 0.000008 loss: 0.0657 (0.0686) grad: 0.0347 (0.0366) time: 0.4615 data: 0.0033 max mem: 22446 +train: [18] [180/400] eta: 0:01:42 lr: 0.000008 loss: 0.0616 (0.0680) grad: 0.0353 (0.0369) time: 0.4552 data: 0.0033 max mem: 22446 +train: [18] [200/400] eta: 0:01:32 lr: 0.000007 loss: 0.0624 (0.0679) grad: 0.0367 (0.0370) time: 0.4596 data: 0.0034 max mem: 22446 +train: [18] [220/400] eta: 0:01:23 lr: 0.000007 loss: 0.0624 (0.0675) grad: 0.0359 (0.0369) time: 0.4603 data: 0.0033 max mem: 22446 +train: [18] [240/400] eta: 0:01:14 lr: 0.000006 loss: 0.0635 (0.0672) grad: 0.0347 (0.0368) time: 0.4558 data: 0.0033 max mem: 22446 +train: [18] [260/400] eta: 0:01:04 lr: 0.000006 loss: 0.0635 (0.0676) grad: 0.0345 (0.0366) time: 0.4651 data: 0.0034 max mem: 22446 +train: [18] [280/400] eta: 0:00:55 lr: 0.000006 loss: 0.0685 (0.0677) grad: 0.0383 (0.0368) time: 0.4581 data: 0.0034 max mem: 22446 +train: [18] [300/400] eta: 0:00:47 lr: 0.000005 loss: 0.0652 (0.0673) grad: 0.0383 (0.0369) time: 0.6556 data: 0.1818 max mem: 22446 +train: [18] [320/400] eta: 0:00:38 lr: 0.000005 loss: 0.0618 (0.0673) grad: 0.0361 (0.0370) time: 0.4656 data: 0.0031 max mem: 22446 +train: [18] [340/400] eta: 0:00:28 lr: 0.000004 loss: 0.0636 (0.0674) grad: 0.0354 (0.0369) time: 0.5096 data: 0.0035 max mem: 22446 +train: [18] [360/400] eta: 0:00:19 lr: 0.000004 loss: 0.0615 (0.0672) grad: 0.0354 (0.0371) time: 0.4586 data: 0.0035 max mem: 22446 +train: [18] [380/400] eta: 0:00:09 lr: 0.000004 loss: 0.0613 (0.0667) grad: 0.0348 (0.0370) time: 0.4454 data: 0.0035 max mem: 22446 +train: [18] [399/400] eta: 0:00:00 lr: 0.000003 loss: 0.0579 (0.0665) grad: 0.0337 (0.0369) time: 0.4612 data: 0.0030 max mem: 22446 +train: [18] Total time: 0:03:09 (0.4742 s / it) +train: [18] Summary: lr: 0.000003 loss: 0.0579 (0.0665) grad: 0.0337 (0.0369) +eval (validation): [18] [ 0/63] eta: 0:03:23 time: 3.2230 data: 2.9301 max mem: 22446 +eval (validation): [18] [20/63] eta: 0:00:20 time: 0.3515 data: 0.0045 max mem: 22446 +eval (validation): [18] [40/63] eta: 0:00:09 time: 0.3365 data: 0.0030 max mem: 22446 +eval (validation): [18] [60/63] eta: 0:00:01 time: 0.3308 data: 0.0032 max mem: 22446 +eval (validation): [18] [62/63] eta: 0:00:00 time: 0.3300 data: 0.0031 max mem: 22446 +eval (validation): [18] Total time: 0:00:24 (0.3889 s / it) +cv: [18] best hparam: (2.3, 1.0) (029) ('029_lr2.3e+00_wd1.0e+00') loss: 0.027 acc: 0.992 f1: 0.989 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [19] [ 0/400] eta: 0:22:18 lr: nan time: 3.3461 data: 2.9908 max mem: 22446 +train: [19] [ 20/400] eta: 0:03:45 lr: 0.000003 loss: 0.0680 (0.0669) grad: 0.0340 (0.0340) time: 0.4550 data: 0.0028 max mem: 22446 +train: [19] [ 40/400] eta: 0:03:13 lr: 0.000003 loss: 0.0680 (0.0657) grad: 0.0349 (0.0356) time: 0.4783 data: 0.0034 max mem: 22446 +train: [19] [ 60/400] eta: 0:02:54 lr: 0.000002 loss: 0.0660 (0.0658) grad: 0.0352 (0.0353) time: 0.4619 data: 0.0033 max mem: 22446 +train: [19] [ 80/400] eta: 0:02:39 lr: 0.000002 loss: 0.0662 (0.0670) grad: 0.0353 (0.0366) time: 0.4553 data: 0.0033 max mem: 22446 +train: [19] [100/400] eta: 0:02:29 lr: 0.000002 loss: 0.0671 (0.0680) grad: 0.0383 (0.0365) time: 0.5036 data: 0.0036 max mem: 22446 +train: [19] [120/400] eta: 0:02:19 lr: 0.000002 loss: 0.0639 (0.0672) grad: 0.0354 (0.0364) time: 0.4897 data: 0.0036 max mem: 22446 +train: [19] [140/400] eta: 0:02:08 lr: 0.000001 loss: 0.0613 (0.0666) grad: 0.0353 (0.0365) time: 0.4779 data: 0.0033 max mem: 22446 +train: [19] [160/400] eta: 0:01:58 lr: 0.000001 loss: 0.0615 (0.0668) grad: 0.0332 (0.0363) time: 0.4799 data: 0.0033 max mem: 22446 +train: [19] [180/400] eta: 0:01:47 lr: 0.000001 loss: 0.0616 (0.0670) grad: 0.0332 (0.0364) time: 0.4705 data: 0.0033 max mem: 22446 +train: [19] [200/400] eta: 0:01:38 lr: 0.000001 loss: 0.0640 (0.0671) grad: 0.0353 (0.0364) time: 0.4914 data: 0.0034 max mem: 22446 +train: [19] [220/400] eta: 0:01:28 lr: 0.000001 loss: 0.0657 (0.0674) grad: 0.0353 (0.0364) time: 0.5016 data: 0.0037 max mem: 22446 +train: [19] [240/400] eta: 0:01:18 lr: 0.000001 loss: 0.0661 (0.0671) grad: 0.0340 (0.0362) time: 0.5091 data: 0.0036 max mem: 22446 +train: [19] [260/400] eta: 0:01:08 lr: 0.000000 loss: 0.0616 (0.0669) grad: 0.0342 (0.0361) time: 0.4874 data: 0.0035 max mem: 22446 +train: [19] [280/400] eta: 0:00:59 lr: 0.000000 loss: 0.0625 (0.0674) grad: 0.0358 (0.0363) time: 0.5166 data: 0.0036 max mem: 22446 +train: [19] [300/400] eta: 0:00:50 lr: 0.000000 loss: 0.0656 (0.0673) grad: 0.0388 (0.0364) time: 0.6605 data: 0.1840 max mem: 22446 +train: [19] [320/400] eta: 0:00:40 lr: 0.000000 loss: 0.0649 (0.0671) grad: 0.0388 (0.0365) time: 0.5076 data: 0.0028 max mem: 22446 +train: [19] [340/400] eta: 0:00:30 lr: 0.000000 loss: 0.0589 (0.0668) grad: 0.0386 (0.0365) time: 0.4736 data: 0.0034 max mem: 22446 +train: [19] [360/400] eta: 0:00:20 lr: 0.000000 loss: 0.0662 (0.0668) grad: 0.0354 (0.0365) time: 0.4623 data: 0.0033 max mem: 22446 +train: [19] [380/400] eta: 0:00:09 lr: 0.000000 loss: 0.0662 (0.0667) grad: 0.0360 (0.0365) time: 0.4681 data: 0.0034 max mem: 22446 +train: [19] [399/400] eta: 0:00:00 lr: 0.000000 loss: 0.0612 (0.0665) grad: 0.0326 (0.0366) time: 0.4661 data: 0.0033 max mem: 22446 +train: [19] Total time: 0:03:19 (0.4983 s / it) +train: [19] Summary: lr: 0.000000 loss: 0.0612 (0.0665) grad: 0.0326 (0.0366) +eval (validation): [19] [ 0/63] eta: 0:03:30 time: 3.3461 data: 3.0910 max mem: 22446 +eval (validation): [19] [20/63] eta: 0:00:21 time: 0.3563 data: 0.0026 max mem: 22446 +eval (validation): [19] [40/63] eta: 0:00:10 time: 0.3692 data: 0.0029 max mem: 22446 +eval (validation): [19] [60/63] eta: 0:00:01 time: 0.3353 data: 0.0033 max mem: 22446 +eval (validation): [19] [62/63] eta: 0:00:00 time: 0.3387 data: 0.0031 max mem: 22446 +eval (validation): [19] Total time: 0:00:25 (0.4053 s / it) +cv: [19] best hparam: (2.3, 1.0) (029) ('029_lr2.3e+00_wd1.0e+00') loss: 0.027 acc: 0.992 f1: 0.989 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +evaluating last checkpoint: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +eval model info: +{"score": 0.9920634920634921, "hparam": [2.3, 1.0], "hparam_id": 29, "epoch": 19, "is_best": false, "best_score": 0.9928075396825397} +eval (train): [20] [ 0/297] eta: 0:15:26 time: 3.1188 data: 2.8535 max mem: 22446 +eval (train): [20] [ 20/297] eta: 0:02:27 time: 0.4046 data: 0.0089 max mem: 22446 +eval (train): [20] [ 40/297] eta: 0:01:57 time: 0.3737 data: 0.0034 max mem: 22446 +eval (train): [20] [ 60/297] eta: 0:01:42 time: 0.3825 data: 0.0035 max mem: 22446 +eval (train): [20] [ 80/297] eta: 0:01:31 time: 0.3849 data: 0.0038 max mem: 22446 +eval (train): [20] [100/297] eta: 0:01:19 time: 0.3379 data: 0.0032 max mem: 22446 +eval (train): [20] [120/297] eta: 0:01:10 time: 0.3570 data: 0.0040 max mem: 22446 +eval (train): [20] [140/297] eta: 0:01:01 time: 0.3553 data: 0.0030 max mem: 22446 +eval (train): [20] [160/297] eta: 0:00:52 time: 0.3539 data: 0.0033 max mem: 22446 +eval (train): [20] [180/297] eta: 0:00:44 time: 0.3478 data: 0.0032 max mem: 22446 +eval (train): [20] [200/297] eta: 0:00:36 time: 0.3595 data: 0.0032 max mem: 22446 +eval (train): [20] [220/297] eta: 0:00:29 time: 0.3804 data: 0.0037 max mem: 22446 +eval (train): [20] [240/297] eta: 0:00:21 time: 0.4089 data: 0.0036 max mem: 22446 +eval (train): [20] [260/297] eta: 0:00:14 time: 0.3838 data: 0.0037 max mem: 22446 +eval (train): [20] [280/297] eta: 0:00:06 time: 0.3554 data: 0.0035 max mem: 22446 +eval (train): [20] [296/297] eta: 0:00:00 time: 0.3375 data: 0.0030 max mem: 22446 +eval (train): [20] Total time: 0:01:52 (0.3792 s / it) +eval (validation): [20] [ 0/63] eta: 0:03:23 time: 3.2316 data: 2.9772 max mem: 22446 +eval (validation): [20] [20/63] eta: 0:00:22 time: 0.3873 data: 0.0032 max mem: 22446 +eval (validation): [20] [40/63] eta: 0:00:10 time: 0.4059 data: 0.0030 max mem: 22446 +eval (validation): [20] [60/63] eta: 0:00:01 time: 0.3311 data: 0.0032 max mem: 22446 +eval (validation): [20] [62/63] eta: 0:00:00 time: 0.3308 data: 0.0032 max mem: 22446 +eval (validation): [20] Total time: 0:00:26 (0.4221 s / it) +eval (test): [20] [ 0/79] eta: 0:04:10 time: 3.1771 data: 2.8741 max mem: 22446 +eval (test): [20] [20/79] eta: 0:00:34 time: 0.4639 data: 0.0040 max mem: 22446 +eval (test): [20] [40/79] eta: 0:00:19 time: 0.4217 data: 0.0033 max mem: 22446 +eval (test): [20] [60/79] eta: 0:00:09 time: 0.4293 data: 0.0039 max mem: 22446 +eval (test): [20] [78/79] eta: 0:00:00 time: 0.3407 data: 0.0032 max mem: 22446 +eval (test): [20] Total time: 0:00:35 (0.4535 s / it) +evaluating best checkpoint: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/hcpya_task21__patch__attn/checkpoint-best.pth +eval model info: +{"score": 0.9928075396825397, "hparam": [2.3, 1.0], "hparam_id": 29, "epoch": 6, "is_best": true, "best_score": 0.9928075396825397} +eval (train): [20] [ 0/297] eta: 0:15:15 time: 3.0809 data: 2.8363 max mem: 22446 +eval (train): [20] [ 20/297] eta: 0:02:34 time: 0.4313 data: 0.0323 max mem: 22446 +eval (train): [20] [ 40/297] eta: 0:01:59 time: 0.3701 data: 0.0028 max mem: 22446 +eval (train): [20] [ 60/297] eta: 0:01:41 time: 0.3541 data: 0.0031 max mem: 22446 +eval (train): [20] [ 80/297] eta: 0:01:29 time: 0.3625 data: 0.0030 max mem: 22446 +eval (train): [20] [100/297] eta: 0:01:21 time: 0.4134 data: 0.0034 max mem: 22446 +eval (train): [20] [120/297] eta: 0:01:12 time: 0.4023 data: 0.0035 max mem: 22446 +eval (train): [20] [140/297] eta: 0:01:03 time: 0.3775 data: 0.0036 max mem: 22446 +eval (train): [20] [160/297] eta: 0:00:55 time: 0.3879 data: 0.0036 max mem: 22446 +eval (train): [20] [180/297] eta: 0:00:46 time: 0.3580 data: 0.0035 max mem: 22446 +eval (train): [20] [200/297] eta: 0:00:38 time: 0.4004 data: 0.0033 max mem: 22446 +eval (train): [20] [220/297] eta: 0:00:30 time: 0.3784 data: 0.0037 max mem: 22446 +eval (train): [20] [240/297] eta: 0:00:22 time: 0.3582 data: 0.0034 max mem: 22446 +eval (train): [20] [260/297] eta: 0:00:14 time: 0.3515 data: 0.0033 max mem: 22446 +eval (train): [20] [280/297] eta: 0:00:06 time: 0.3763 data: 0.0034 max mem: 22446 +eval (train): [20] [296/297] eta: 0:00:00 time: 0.3583 data: 0.0034 max mem: 22446 +eval (train): [20] Total time: 0:01:55 (0.3890 s / it) +eval (validation): [20] [ 0/63] eta: 0:02:54 time: 2.7768 data: 2.5396 max mem: 22446 +eval (validation): [20] [20/63] eta: 0:00:20 time: 0.3561 data: 0.0030 max mem: 22446 +eval (validation): [20] [40/63] eta: 0:00:09 time: 0.3684 data: 0.0031 max mem: 22446 +eval (validation): [20] [60/63] eta: 0:00:01 time: 0.3485 data: 0.0036 max mem: 22446 +eval (validation): [20] [62/63] eta: 0:00:00 time: 0.3404 data: 0.0035 max mem: 22446 +eval (validation): [20] Total time: 0:00:25 (0.3997 s / it) +eval (test): [20] [ 0/79] eta: 0:03:59 time: 3.0336 data: 2.7633 max mem: 22446 +eval (test): [20] [20/79] eta: 0:00:26 time: 0.3214 data: 0.0206 max mem: 22446 +eval (test): [20] [40/79] eta: 0:00:14 time: 0.3076 data: 0.0146 max mem: 22446 +eval (test): [20] [60/79] eta: 0:00:06 time: 0.3203 data: 0.0034 max mem: 22446 +eval (test): [20] [78/79] eta: 0:00:00 time: 0.2809 data: 0.0028 max mem: 22446 +eval (test): [20] Total time: 0:00:27 (0.3456 s / it) +eval results: + +| model | repr | clf | dataset | ckpt | epoch | lr | wd | hparam_id | hparam | split | loss | acc | acc_std | f1 | f1_std | +|:---------|:-------|:------|:-------------|:-------|--------:|--------:|-----:|------------:|:-----------|:-----------|---------:|--------:|----------:|--------:|-----------:| +| flat_mae | patch | attn | hcpya_task21 | best | 6 | 0.00069 | 0.05 | 29 | [2.3, 1.0] | train | 0.009245 | 0.99784 | 0.0003241 | 0.99778 | 0.00035989 | +| flat_mae | patch | attn | hcpya_task21 | best | 6 | 0.00069 | 0.05 | 29 | [2.3, 1.0] | validation | 0.02399 | 0.99281 | 0.0013338 | 0.99143 | 0.0017508 | +| flat_mae | patch | attn | hcpya_task21 | best | 6 | 0.00069 | 0.05 | 29 | [2.3, 1.0] | test | 0.034005 | 0.98988 | 0.0013061 | 0.98751 | 0.0017798 | + + +done! total time: 1:20:35 diff --git a/input_space_v3/flat_lr1e-3_1/eval_v2/hcpya_task21__patch__attn/train_log.json b/input_space_v3/flat_lr1e-3_1/eval_v2/hcpya_task21__patch__attn/train_log.json new file mode 100644 index 0000000000000000000000000000000000000000..92b6c5578c190e7791bafd0f30dc59837a92e74e --- /dev/null +++ b/input_space_v3/flat_lr1e-3_1/eval_v2/hcpya_task21__patch__attn/train_log.json @@ -0,0 +1,20 @@ +{"epoch": 0, "train/lr": 2.987987987987988e-05, "train/loss": 2.0966553872823717, "train/grad": 0.2077255731076002, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.06048583984375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.057403564453125, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.0522314453125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.04710693359375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.042052001953125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.035093994140625, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.02701904296875, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.0182373046875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.0065625, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.994068603515625, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.9818603515625, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.9633941650390625, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.9454638671875, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.9193218994140624, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.8940667724609375, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.8697430419921877, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.838621826171875, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.801387939453125, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.759041748046875, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.7186968994140623, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.667480773925781, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.6128805541992186, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.549777374267578, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.479903259277344, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.404718322753906, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.312898864746094, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.229693489074707, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.1542013931274413, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.0530590057373046, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.9363663482666016, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.8350488567352294, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.7453336143493652, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.628406175971031, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.5295742054283619, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.4208818055316805, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.3221408233232796, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.2269409214146436, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.1451027160696685, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.0646347641199827, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.9744817996583879, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.9108753450214863, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.8596771847084165, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.7984582456294447, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.7507222189567984, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.7006496367417276, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.6523612577095628, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.6155325334426016, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.5764308657310903, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.5460237528290599, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.03901119539514184, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.038947773268446326, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.038843868989497425, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.038740194169804454, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.03863741303794086, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.038494977178052066, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.038333222502842546, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.0381540971621871, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.03791746941395104, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.03766332488507032, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.03741345198825002, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.03703599452972412, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.0366689167637378, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.03613511157222092, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.03562417195178568, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.03514117863029242, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.03454469623044133, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.033883228907361625, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.03319938903674483, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.03262101913802326, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.03196899300441146, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.03135215817950666, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.03071042618714273, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.03005386349745095, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.029380475645884873, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0285795119125396, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.02786319169215858, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.02721573574934155, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.026363239600323142, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.025404231804423034, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.02459618516266346, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.023886049930006266, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.022918108319863677, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.02207153259078041, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.02108275700127706, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.020110247910488398, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.019213496861048042, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.01851363666821271, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.01782190000638366, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.016877182617317885, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.015983537769061515, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.015306850957567803, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.014567299422924406, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.014194851944339462, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.014015146010788158, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.013876756662211847, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.013927515463437885, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.014040666232467629, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0141275492857676, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.018503189086914, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.009321451187134, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.9942071437835693, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.979034900665283, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.9641473293304443, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.943598985671997, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.920652389526367, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.8950812816619873, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.861902952194214, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.8268015384674072, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.7928178310394287, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.742347478866577, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.693963050842285, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.6250905990600586, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.5603504180908203, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.4991331100463867, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.422207832336426, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.331789493560791, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.22959041595459, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.1327216625213623, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.010390043258667, "validation/loss_021_lr6.1e-01_wd1.0e+00": 1.8813339471817017, "validation/loss_022_lr7.2e-01_wd1.0e+00": 1.7352927923202515, "validation/loss_023_lr8.5e-01_wd1.0e+00": 1.5792790651321411, "validation/loss_024_lr1.0e+00_wd1.0e+00": 1.4208989143371582, "validation/loss_025_lr1.2e+00_wd1.0e+00": 1.2431310415267944, "validation/loss_026_lr1.4e+00_wd1.0e+00": 1.097353219985962, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.976220965385437, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.8261236548423767, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.6596654057502747, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.5130503177642822, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.3847552239894867, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.2473190873861313, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.16673552989959717, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.10561386495828629, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.07504246383905411, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.06419315189123154, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.059846144169569016, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.05937527120113373, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.061670515686273575, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.05521756410598755, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.04760684072971344, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.04347512871026993, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.04328972101211548, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.043780241161584854, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.047902897000312805, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.06077585369348526, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.09102167934179306, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.15008707344532013, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.05257936507936508, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.07862103174603174, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.14012896825396826, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.2003968253968254, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.23511904761904762, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.24950396825396826, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.25223214285714285, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.23809523809523808, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.2204861111111111, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.2078373015873016, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.2021329365079365, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.19295634920634921, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.1892361111111111, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.19246031746031747, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.20262896825396826, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.21651785714285715, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.25992063492063494, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.3239087301587302, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.3812003968253968, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.419890873015873, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.4774305555555556, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.5310019841269841, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.5629960317460317, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.6096230158730159, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.6661706349206349, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.736359126984127, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.7998511904761905, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.8482142857142857, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.8821924603174603, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.8943452380952381, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9002976190476191, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9099702380952381, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9456845238095238, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.970734126984127, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9769345238095238, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9796626984126984, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9796626984126984, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9794146825396826, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9781746031746031, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9774305555555556, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9796626984126984, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9831349206349206, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9851190476190477, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9851190476190477, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.986359126984127, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.984375, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9826388888888888, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9737103174603174, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.957093253968254, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.02878655565284319, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.038875537970971055, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.05726782333057158, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.0713778298475865, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.08125743181135728, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.08223763537929835, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.08418419562904497, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.07380354074010535, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.06402992320192002, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.05712517673399534, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.052048518836831405, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.04195390309649305, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.03742495064816377, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.04014092083141777, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.04972160079468314, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.06113191452430472, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.0961977797634644, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.13365370905865415, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.16797668447894087, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.19661845499464428, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.2596635424474797, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.30010157886413286, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.3283615391432905, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.39475059979552446, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.48872703943875545, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.6129774255379127, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.7265837543147177, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.8054238581764909, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.8582773060439195, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.872114460629019, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.8775317072283616, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.8925476694346353, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.939656386492265, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9668780912854392, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.973750632140689, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9767404547746965, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9772659811947997, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9767662860583215, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.976045741117102, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9763037554155263, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9779433810043227, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9817893238874779, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9835952664385882, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9833763559712493, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9845637618111984, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9829954469249762, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9816483202604115, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9694002982309419, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9415435028792063, "id_best": 44, "lr_best": 0.0078, "wd_best": 0.05, "train/loss_best": 0.7006496367417276, "validation/loss_best": 0.043780241161584854, "validation/acc_best": 0.986359126984127, "validation/f1_best": 0.9845637618111984} +{"epoch": 1, "train/lr": 8.993993993993998e-05, "train/loss": 1.153138576745987, "train/grad": 0.14863873180001974, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.942730712890625, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.92319580078125, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.89129150390625, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.8602508544921874, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.830130615234375, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.7891070556640627, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.74423828125, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.6958843994140627, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.6343353271484373, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.5712451171875, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.5110549926757812, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.423451232910156, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.340639343261719, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.2240638732910156, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.1153309631347654, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.0133831787109373, "train/loss_016_lr2.7e-01_wd1.0e+00": 1.8876115417480468, "train/loss_017_lr3.2e-01_wd1.0e+00": 1.7453421020507813, "train/loss_018_lr3.8e-01_wd1.0e+00": 1.594155387878418, "train/loss_019_lr4.4e-01_wd1.0e+00": 1.4614645385742187, "train/loss_020_lr5.2e-01_wd1.0e+00": 1.3073292064666748, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.1577437686920167, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.000505256652832, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.8441686975955963, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.699066407084465, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.5510518792271614, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.44147003669291734, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.35938850946724415, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.2711511676944792, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.1935010656900704, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.14451959638856351, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.11327518512494862, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.08667193248867988, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.07322378142736852, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.06456786645576358, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.06008062779903412, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.05712130053900182, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.055339702405035496, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.054102895064279434, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.05357772110030055, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.054079287415370346, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.05501321949996054, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.05736271289177239, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.05766476904042065, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.06081273500807583, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.06979417515918612, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.08745286838151514, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.10631356661207975, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.16853495332412421, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.036266887690871955, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.03587474221363664, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.03523954216390848, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.034626837195828555, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.03403444197960198, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.0332431463804096, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.03239696848206222, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.03152326822280884, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.030494430121034383, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.029549776958301664, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.0287535503692925, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.027761629596352578, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.026974372481927276, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.02604537275619805, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.025299210641533135, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.02465328318066895, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.023879529256373645, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.022986370511353015, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.02199424020946026, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.021081547932699323, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.01999193137977272, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.01891307080630213, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.017736029671505095, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.01644831584766507, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.015075698648579418, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.013474247597623617, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.012146727212239057, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.011136349374428391, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.010055800166446716, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.009021168644540011, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.008283642008900643, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.007759909478481859, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.007231531613506377, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.007009896346135065, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.006801602247287519, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.006698985809925943, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0066287196334451435, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.006646186332800425, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.006720201577991247, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.006827116993372328, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.006945278935745591, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0072993691705050875, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.007704320114571601, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.007927814913273323, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.008474997895245907, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.009682235410291468, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.010972716285687056, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.014156120830157305, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.02104091744753532, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.8466644287109375, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.8148818016052246, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.7638089656829834, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.714749574661255, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.6676597595214844, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.604968547821045, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.5371391773223877, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.4652907848358154, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.375014066696167, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.2829551696777344, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.195364475250244, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.0676991939544678, "validation/loss_012_lr1.4e-01_wd1.0e+00": 1.9477756023406982, "validation/loss_013_lr1.7e-01_wd1.0e+00": 1.7807590961456299, "validation/loss_014_lr2.0e-01_wd1.0e+00": 1.6295515298843384, "validation/loss_015_lr2.3e-01_wd1.0e+00": 1.4937520027160645, "validation/loss_016_lr2.7e-01_wd1.0e+00": 1.3352469205856323, "validation/loss_017_lr3.2e-01_wd1.0e+00": 1.169255256652832, "validation/loss_018_lr3.8e-01_wd1.0e+00": 1.0066415071487427, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.8714826703071594, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.7159239649772644, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.559445321559906, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.3941182792186737, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.25837570428848267, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.1662498116493225, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.10157328844070435, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.0767279863357544, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.06559836864471436, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.05688327178359032, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.050158239901065826, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.04550613835453987, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.04206572845578194, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.03811463713645935, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.0355028361082077, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.03332561254501343, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.032289355993270874, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.03196569159626961, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.03078751266002655, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.029846595600247383, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.032018743455410004, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.03773852437734604, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.04364754259586334, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.05623650178313255, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.052137088030576706, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.058636374771595, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.13721412420272827, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.10778142511844635, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.1790206879377365, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.281474232673645, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.21949404761904762, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.21031746031746032, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.20287698412698413, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.1984126984126984, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.20089285714285715, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.20535714285714285, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.22023809523809523, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.25049603174603174, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.3033234126984127, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.35540674603174605, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.4000496031746032, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.47098214285714285, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.5290178571428571, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.5704365079365079, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.6148313492063492, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.6604662698412699, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.7152777777777778, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.7842261904761905, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.8462301587301587, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.8792162698412699, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9079861111111112, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9201388888888888, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9365079365079365, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9627976190476191, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9756944444444444, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9801587301587301, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9826388888888888, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9833829365079365, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9846230158730159, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9856150793650794, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9858630952380952, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9868551587301587, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9885912698412699, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9898313492063492, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9903273809523809, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9900793650793651, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9893353174603174, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9893353174603174, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9893353174603174, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.988343253968254, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9858630952380952, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9848710317460317, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9828869047619048, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9831349206349206, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9846230158730159, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9732142857142857, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9806547619047619, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9781746031746031, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9734623015873016, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.06409818844309673, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.05912407185796186, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.05202512738482877, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.046649609903941465, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.04806314053514918, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.05109931409784242, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.06211494579959268, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.08538538542098321, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.11903238978245552, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.14967750529056512, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.18559923947844825, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.2575707531521908, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.29910119416533554, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.3341994422577438, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.40972448135937045, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.48733826757129367, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.5868469900827903, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.7050142206662647, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.8025093649446172, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.8542650823787296, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.8935636350956306, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9078010441295952, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9281265909946994, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9587906313797083, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9727832284502562, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9772982447175215, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9804017936992855, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9809887626152567, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9819397387403916, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9834718605053719, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9834862632531359, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9845637321320889, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.987022937080716, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9882486699523408, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9887021002601298, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9887834612080717, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9886186132411454, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9883768777783718, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9875767113514924, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9865456429607307, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9844631426990273, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9827890874093854, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9801561767966056, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.980652188783464, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9805410652483334, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9700590455418775, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9791834206318083, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9711950686913822, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9674085777045975, "id_best": 34, "lr_best": 0.0015299999999999997, "wd_best": 0.05, "train/loss_best": 0.06456786645576358, "validation/loss_best": 0.03332561254501343, "validation/acc_best": 0.9903273809523809, "validation/f1_best": 0.9887021002601298} +{"epoch": 2, "train/lr": 0.00014999999999999988, "train/loss": 0.8428211367130279, "train/grad": 0.19475476507097483, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.72923828125, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.684482421875, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.6137420654296877, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.547119140625, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.4838717651367186, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.400037841796875, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.3095489501953126, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.213359680175781, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.0924954223632812, "train/loss_009_lr8.7e-02_wd1.0e+00": 1.9702597045898438, "train/loss_010_lr1.0e-01_wd1.0e+00": 1.856070327758789, "train/loss_011_lr1.2e-01_wd1.0e+00": 1.6957601165771485, "train/loss_012_lr1.4e-01_wd1.0e+00": 1.5529117584228516, "train/loss_013_lr1.7e-01_wd1.0e+00": 1.36778564453125, "train/loss_014_lr2.0e-01_wd1.0e+00": 1.2120687866210937, "train/loss_015_lr2.3e-01_wd1.0e+00": 1.0788734817504884, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.9261736297607421, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.7631560599803925, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.6007578921318054, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.47147626280784605, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.34147836893796923, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.24107385128736497, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.16562002738937737, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.11742956596426665, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.08939696450717748, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.07296712447889149, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.06562280850484967, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.06128955217078328, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.05712005318142474, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.05349379302933812, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.05103276233188808, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.04934374686330557, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.047679154491052034, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.046771331494674086, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.04535014295950532, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.044546686420217155, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.044083702685311435, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.044232226610183716, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.04520206172950566, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.048267256608232854, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.05262793506495655, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.0539366829674691, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.06522162023931742, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.10545526704750956, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.13577319545671343, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.3414170778915286, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.4434661801345646, "train/loss_047_lr4.3e+01_wd1.0e+00": 1.0402285403665155, "train/loss_048_lr5.0e+01_wd1.0e+00": 1.7589197740145028, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.03257442029193044, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.0317315583024174, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.03046481216326356, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.029380448190495373, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.028474394334480166, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.027461814135313033, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.026586093213409184, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.025844200775027276, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.02508187915198505, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.024392427373677493, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.02375541511923075, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.022793100867420434, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.02184463690035045, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.020484238304197787, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.019264139477163555, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.018209388041868807, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.01703592932317406, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.015806505922228098, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.014468186404556035, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.01325523192062974, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.01177895767148584, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.010368989778216929, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.008997265733778476, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.007910676400642842, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.00713924125302583, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0066339222469832745, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0064650526572950185, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0063877015368780125, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.006310637262067757, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.006234981123125181, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.006216638667974621, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.006235010483069345, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.006300596560176928, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.006362687283544801, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.006339112739369739, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.00634093920030864, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.006331148303579539, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0062149026693077754, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.006427961281442549, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.006851080672058743, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.007772826242799056, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.007887374291967716, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.009546586287178797, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.014514009899903613, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.01871780672838213, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.03338511203895905, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.04045948847771797, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.07565845395110343, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.10045481825033037, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.6029067039489746, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.545362949371338, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.4553375244140625, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.3710594177246094, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.291154623031616, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.185124158859253, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.070382595062256, "validation/loss_007_lr6.2e-02_wd1.0e+00": 1.9487173557281494, "validation/loss_008_lr7.4e-02_wd1.0e+00": 1.7978394031524658, "validation/loss_009_lr8.7e-02_wd1.0e+00": 1.6486198902130127, "validation/loss_010_lr1.0e-01_wd1.0e+00": 1.5142110586166382, "validation/loss_011_lr1.2e-01_wd1.0e+00": 1.334823727607727, "validation/loss_012_lr1.4e-01_wd1.0e+00": 1.1840051412582397, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.9993659257888794, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.8479108214378357, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.7153297662734985, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.5548100471496582, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.3840525150299072, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.2474627047777176, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.16630958020687103, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.10657978802919388, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.07941748201847076, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.06519056111574173, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.056389547884464264, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.050422992557287216, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.04547388106584549, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.04261074215173721, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.041608549654483795, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.040939316153526306, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.038210298866033554, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.03555932641029358, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.034441471099853516, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.03249678760766983, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.032395441085100174, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.03086899220943451, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.030724486336112022, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.03376031294465065, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.03892165794968605, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.03842594847083092, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.038790687918663025, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.0470723882317543, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.072759248316288, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.05522630363702774, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.32656461000442505, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.4978023171424866, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.7977632880210876, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.6793530583381653, "validation/loss_047_lr4.3e+01_wd1.0e+00": 2.8468146324157715, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.0506534576416016, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.19593253968253968, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.20610119047619047, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.2435515873015873, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.29712301587301587, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.34523809523809523, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.39384920634920634, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.45163690476190477, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.5205853174603174, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.5577876984126984, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.5992063492063492, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.644593253968254, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.7336309523809523, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.8015873015873016, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.8534226190476191, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.8854166666666666, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.90625, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9213789682539683, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9417162698412699, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9642857142857143, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9747023809523809, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9791666666666666, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9821428571428571, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9836309523809523, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9846230158730159, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9858630952380952, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9866071428571429, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9871031746031746, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9868551587301587, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9875992063492064, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9878472222222222, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9885912698412699, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9888392857142857, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9895833333333334, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9893353174603174, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9913194444444444, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9913194444444444, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9908234126984127, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9880952380952381, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9875992063492064, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9893353174603174, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9875992063492064, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9831349206349206, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9856150793650794, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9618055555555556, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9660218253968254, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9702380952380952, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9719742063492064, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9543650793650794, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9670138888888888, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.04500273983747384, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.05443377727420992, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.0853666291068131, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.11899219349897663, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.14218965773686362, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.1781947478543373, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.23924246055704299, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.2980367703006171, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.3267946331519894, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.3768205247681542, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.459249612566342, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.6223515724033164, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.7257238849093123, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.8044998169709847, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.858557100767298, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.8897583668920754, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9098865452785444, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9359418880512502, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9606350086895583, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9710732535126855, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9758855115077905, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9791426244693222, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9803152293006503, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9816447523309129, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9831213861021436, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9836582137957269, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9852762576201899, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9856045294404181, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9868761963851606, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9870994079324171, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9877195554025517, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9875851642650803, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9880435580643995, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9872076508766903, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.989063731315161, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9895714593111845, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9887769068025379, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9852716880086133, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9840295126982463, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9866952785669868, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9857639677552757, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9743035783279813, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9842048886944743, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9474836622741211, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9557241313988434, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9712180505111909, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.967467867111392, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9080420051899929, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9600630604295082, "id_best": 34, "lr_best": 0.0015299999999999997, "wd_best": 0.05, "train/loss_best": 0.04535014295950532, "validation/loss_best": 0.03086899220943451, "validation/acc_best": 0.9913194444444444, "validation/f1_best": 0.989063731315161} +{"epoch": 3, "train/lr": 0.0002100600600600602, "train/loss": 0.7497048810124397, "train/grad": 0.2954022202640772, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.477738037109375, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.4080075073242186, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.29844482421875, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.195154266357422, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.096982421875, "train/loss_005_lr4.5e-02_wd1.0e+00": 1.9673719787597657, "train/loss_006_lr5.3e-02_wd1.0e+00": 1.8297728729248046, "train/loss_007_lr6.2e-02_wd1.0e+00": 1.6879539489746094, "train/loss_008_lr7.4e-02_wd1.0e+00": 1.5196170043945312, "train/loss_009_lr8.7e-02_wd1.0e+00": 1.3617977142333983, "train/loss_010_lr1.0e-01_wd1.0e+00": 1.226047534942627, "train/loss_011_lr1.2e-01_wd1.0e+00": 1.0506847858428956, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.9036211252212525, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.7157952213287353, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.5575206124782562, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.42947698950767516, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.3023908363282681, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.20060851246118547, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.13534723941236734, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.10221775269135833, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.08144636552780866, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.07108723991550506, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.06428925178945065, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.059324833182618025, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.055419645449146626, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.05157360388897359, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.04845401939004659, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.04597192188724875, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.04307341197505593, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.04031364106573165, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.03870669750496745, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.037696329988539216, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.03647823296487331, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.03550306670367718, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.035113484552130106, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.03405702921561897, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.034501358568668365, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.0383845682349056, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.038808610858395695, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.0450941363722086, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.07322294674813748, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.16615471556782724, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.30463373445905745, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.30163242128677664, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.5883527435641736, "train/loss_045_lr3.1e+01_wd1.0e+00": 1.1613696518726646, "train/loss_046_lr3.6e+01_wd1.0e+00": 1.832514059478417, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.3701779738068582, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.5356333041097967, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.027924633836373686, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.027113207401707768, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.026129125859588386, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.025433995313942432, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.024890014752745628, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.024233028991147876, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.023512003291398288, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.022684694174677132, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.02155096606351435, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.02034814028069377, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.01923793103545904, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.01777915489859879, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.01661496756132692, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.015227224277332425, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.01396845224313438, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.01272837644442916, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.011138446009717883, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.009402101077139378, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.007974780690856277, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.0071186455781571565, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.006548674156656489, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.006309335853438824, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.006190039644134231, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.006112231703591533, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.00603850937797688, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.005912563280435279, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.005769115725997836, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.005659765887830872, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.005542878615378868, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0054579865344567225, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.005472067072114442, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.005500229227764066, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.00549367340230674, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.005465196486038621, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.005564039589080494, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.00558227842047927, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.005720408866509387, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.006523269427852938, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.00690677266480634, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.008641511866662767, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.011686183549572888, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.020085059760313016, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.03027436699889222, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.03105284897016742, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.052762978493678926, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.08041113138344028, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.10171250391742954, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.12069927586581096, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.1662787603400648, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.3294713497161865, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.246060848236084, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.114809036254883, "validation/loss_003_lr3.3e-02_wd1.0e+00": 1.9915541410446167, "validation/loss_004_lr3.8e-02_wd1.0e+00": 1.8755418062210083, "validation/loss_005_lr4.5e-02_wd1.0e+00": 1.725144386291504, "validation/loss_006_lr5.3e-02_wd1.0e+00": 1.569920301437378, "validation/loss_007_lr6.2e-02_wd1.0e+00": 1.4162119626998901, "validation/loss_008_lr7.4e-02_wd1.0e+00": 1.2421674728393555, "validation/loss_009_lr8.7e-02_wd1.0e+00": 1.0863468647003174, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.9555087089538574, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.7845606803894043, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.634020209312439, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.43548786640167236, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.2923344671726227, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.20288468897342682, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.13037490844726562, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.08967199921607971, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.07108156383037567, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.061718519777059555, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.054358746856451035, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.049134060740470886, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.04485764726996422, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.04126841574907303, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.03824076056480408, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.035423457622528076, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.03353816643357277, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.03304913267493248, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.03438262268900871, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.037217870354652405, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.04452575370669365, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.05190734565258026, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.0555059015750885, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.06162171810865402, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.06848292052745819, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.08712780475616455, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.08783357590436935, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.07108478993177414, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.07851412147283554, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.1403726190328598, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.252577543258667, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.21010364592075348, "validation/loss_042_lr1.9e+01_wd1.0e+00": 1.1913678646087646, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.4575117528438568, "validation/loss_044_lr2.6e+01_wd1.0e+00": 1.8403733968734741, "validation/loss_045_lr3.1e+01_wd1.0e+00": 1.0465264320373535, "validation/loss_046_lr3.6e+01_wd1.0e+00": 2.2233119010925293, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.914480686187744, "validation/loss_048_lr5.0e+01_wd1.0e+00": 7.232217788696289, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.33209325396825395, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.3759920634920635, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.43427579365079366, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.5086805555555556, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.5493551587301587, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.5835813492063492, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.6299603174603174, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.691468253968254, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.7683531746031746, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.828125, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.8623511904761905, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.8936011904761905, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9089781746031746, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9288194444444444, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9516369047619048, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9692460317460317, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9764384920634921, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.980406746031746, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9831349206349206, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9841269841269841, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9856150793650794, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9868551587301587, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9871031746031746, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9878472222222222, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9888392857142857, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9898313492063492, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9898313492063492, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9898313492063492, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9890873015873016, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9878472222222222, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9848710317460317, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9838789682539683, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.980406746031746, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9791666666666666, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9776785714285714, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9764384920634921, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9756944444444444, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9809027777777778, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9809027777777778, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9724702380952381, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9685019841269841, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9796626984126984, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9637896825396826, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9774305555555556, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9603174603174603, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9818948412698413, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9737103174603174, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.96875, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9568452380952381, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.1364243011603236, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.16514224175711892, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.21768215507723468, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.2905687745127781, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.3203422998423989, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.3568410205530193, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.4387070567761618, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.5598697121387887, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.6885710645894283, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.7719184315281415, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.8265951423710115, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.8715112743566373, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.8959797955393098, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9191472744658252, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9474881404721375, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9666339240254991, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9737650163438516, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9779892267066027, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9809731497725894, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9820120851330225, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9830664469936333, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9839648676168566, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9845025666636034, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9854112517953617, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9866760495181187, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9881723893788293, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.98773132496404, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.98818035043069, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9876525606329516, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9872652100855133, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9852033852370833, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9845236880076493, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9807265369676046, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9792268214484781, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9760587860602546, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9771766533570495, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9737422735581911, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.97135567927515, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9718757965169511, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9639118483934821, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9550945956460423, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9767314432114127, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9570157546205662, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9725524615120249, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9551758567645766, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9785672142405976, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9650791294016049, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9548661752297934, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9449762993329862, "id_best": 25, "lr_best": 0.00035999999999999997, "wd_best": 0.05, "train/loss_best": 0.05157360388897359, "validation/loss_best": 0.035423457622528076, "validation/acc_best": 0.9898313492063492, "validation/f1_best": 0.9881723893788293} +{"epoch": 4, "train/lr": 0.0002701201201201201, "train/loss": 0.7902768900990487, "train/grad": 0.42471771873533726, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.189902038574219, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.092648468017578, "train/loss_002_lr2.8e-02_wd1.0e+00": 1.9403997802734374, "train/loss_003_lr3.3e-02_wd1.0e+00": 1.8000648498535157, "train/loss_004_lr3.8e-02_wd1.0e+00": 1.6712100982666016, "train/loss_005_lr4.5e-02_wd1.0e+00": 1.5096611785888672, "train/loss_006_lr5.3e-02_wd1.0e+00": 1.3498818588256836, "train/loss_007_lr6.2e-02_wd1.0e+00": 1.197141227722168, "train/loss_008_lr7.4e-02_wd1.0e+00": 1.0279016304016113, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.874751558303833, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.7408058452606201, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.5609425771236419, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.4156191974878311, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.2647170288860798, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.17679567329585552, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.12811056114733219, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.09578032681718468, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.07854919224977493, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.06893101743422449, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.06333160964772105, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.05844977111555636, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.05460268179886043, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.05115772309713065, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.048012699065729976, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.045229251869022845, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.04241085190325975, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.0404448473174125, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.03894021757878363, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.03726669673807919, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.034860022077336905, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.03307833430357277, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.03193986785598099, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.03237057888880372, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.034263249663636086, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.03330377164296806, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.03495236269198358, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.038132369723170995, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.047864761026576164, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.07689563883468509, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.12780065828934312, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.29317827661521734, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.3693702453933656, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.5170272164419294, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.8830442661698907, "train/loss_044_lr2.6e+01_wd1.0e+00": 1.2541779135446995, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.3990656010992826, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.4520464944653213, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.64687528998591, "train/loss_048_lr5.0e+01_wd1.0e+00": 6.719660948524251, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.025434382036328317, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.02490831049159169, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.02415621674619615, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.023431130573153495, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.022684381110593677, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.021610524542629718, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.02040878134779632, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.0191719324933365, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.01778755764942616, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.016601312663406132, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.01562893399503082, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.014254241175949573, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.012803818425163626, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.010678452735301108, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.008885648988652975, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.0076163205388002095, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.006664489007089287, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.006214973666938022, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.006008783156867139, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.005909061854472384, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.005830254660104402, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.005779576362692751, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.005734426224953495, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0056948799354722725, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.005654496544739231, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.005626559417578392, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0056493154080817475, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0056840303607168605, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.005715778714220505, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.005598707590543199, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.005495040038076695, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.005443222260073526, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.005669908860290888, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0060006820669514125, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0058935922477394345, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.006052910513681127, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.006921732175105717, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.00901428285476868, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.012289557573894853, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.017761016517561075, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.030499710886506364, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.034772416089135734, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.042191838249940945, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.07052309315026975, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.08279050315115494, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.1147453475050255, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.1656295051511259, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.16369881156551266, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.2430430747234465, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.032965660095215, "validation/loss_001_lr2.3e-02_wd1.0e+00": 1.9217101335525513, "validation/loss_002_lr2.8e-02_wd1.0e+00": 1.7499630451202393, "validation/loss_003_lr3.3e-02_wd1.0e+00": 1.5955214500427246, "validation/loss_004_lr3.8e-02_wd1.0e+00": 1.4580274820327759, "validation/loss_005_lr4.5e-02_wd1.0e+00": 1.291603684425354, "validation/loss_006_lr5.3e-02_wd1.0e+00": 1.1329292058944702, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.9850839972496033, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.8203505873680115, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.6644385457038879, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.5229602456092834, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.34594810009002686, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.23342002928256989, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.13746331632137299, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.09383746236562729, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.07567628473043442, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.06372903287410736, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.05566583201289177, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.04985005035996437, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.04604977369308472, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.042777322232723236, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.040403641760349274, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.03908596560359001, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.03854599967598915, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.0384659618139267, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.04014776647090912, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.04315096512436867, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.04458935186266899, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.04136628657579422, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.03775113448500633, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.03695837780833244, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.037343431264162064, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.03735937550663948, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.0419539175927639, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.04408721253275871, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.0466223880648613, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.03873681277036667, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.07920288294553757, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.15983633697032928, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.413985937833786, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.29873862862586975, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.5068196058273315, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.5413253903388977, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.9727049469947815, "validation/loss_044_lr2.6e+01_wd1.0e+00": 1.3496434688568115, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.405062675476074, "validation/loss_046_lr3.6e+01_wd1.0e+00": 7.159502983093262, "validation/loss_047_lr4.3e+01_wd1.0e+00": 5.067311763763428, "validation/loss_048_lr5.0e+01_wd1.0e+00": 9.243906021118164, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.4880952380952381, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.5384424603174603, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.5776289682539683, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.6240079365079365, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.6775793650793651, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.7497519841269841, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.8216765873015873, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.8598710317460317, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.8859126984126984, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9020337301587301, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9164186507936508, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9444444444444444, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9702380952380952, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9784226190476191, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.980406746031746, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9816468253968254, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.984375, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.984375, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9853670634920635, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9866071428571429, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9871031746031746, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9873511904761905, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9880952380952381, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9875992063492064, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9873511904761905, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.986359126984127, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9858630952380952, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9851190476190477, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.986359126984127, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9875992063492064, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9880952380952381, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9878472222222222, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9878472222222222, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.986359126984127, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9868551587301587, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9861111111111112, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9900793650793651, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9831349206349206, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9769345238095238, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9689980158730159, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9776785714285714, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9784226190476191, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9794146825396826, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9781746031746031, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.982390873015873, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9754464285714286, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9580853174603174, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9719742063492064, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9697420634920635, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.2737380099074682, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.30732427815995456, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.3393621755116978, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.4213059373234361, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.5231579126663168, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.6543049692422697, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.7633020348213403, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.8225429406482955, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.8607075252516219, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.8853390169273606, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9058649997572482, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9392941085614672, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9663326745483626, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9749212476874257, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9770784182058433, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9788205466296528, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9821554406967837, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9825175043717306, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9832323333082637, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9844152383423347, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9848585142620978, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9855779867949948, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9863062303010819, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9858238086585464, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9856970844263114, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9839066974512446, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9838532806508556, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9830122140286722, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9843500851957966, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9852985991608856, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9855894042126037, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9844907570842766, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9848614619545214, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9836853522151975, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9849638581844923, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.984778372974468, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9865921116940088, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9771765881067632, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9736898458450554, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9700738893496981, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9767384080582564, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9733186038680811, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9742363777967594, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9755006603509111, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9778319017119922, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9698015715256939, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9479898864788464, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9639658278560018, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9633094264301618, "id_best": 36, "lr_best": 0.0021299999999999995, "wd_best": 0.05, "train/loss_best": 0.038132369723170995, "validation/loss_best": 0.03873681277036667, "validation/acc_best": 0.9900793650793651, "validation/f1_best": 0.9865921116940088} +{"epoch": 5, "train/lr": 0.00029891323817685334, "train/loss": 0.7897174493223429, "train/grad": 0.465504214912653, "train/loss_000_lr2.0e-02_wd1.0e+00": 1.8963662719726562, "train/loss_001_lr2.3e-02_wd1.0e+00": 1.7740263366699218, "train/loss_002_lr2.8e-02_wd1.0e+00": 1.590113754272461, "train/loss_003_lr3.3e-02_wd1.0e+00": 1.4301889801025391, "train/loss_004_lr3.8e-02_wd1.0e+00": 1.2920027923583985, "train/loss_005_lr4.5e-02_wd1.0e+00": 1.1289593505859374, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.9748941802978516, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.8280630207061768, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.6572171783447266, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.49615162014961245, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.36796595454216, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.23660460501909256, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.1608504468202591, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.10621390219777822, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.08493784751743078, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.07487530682235956, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.06738172782585025, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.061581012830138206, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.05701718737371266, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.05369323102757335, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.05025924740359187, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.04724582139402628, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.044274214906618, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.041404068451374766, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.038538343040272593, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.035286684054881334, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.03251928431913256, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.03025643895380199, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.02752793318592012, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.025349660320207478, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.02364982838742435, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.022316832207143308, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.020528693227097394, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.019633318101987242, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.02209699500352144, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.02592390738427639, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.03948387268930673, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.06961400422267616, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.15562425647862255, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.27514218183234335, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.35854018496349455, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.46715819980949164, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.43469051987864077, "train/loss_043_lr2.2e+01_wd1.0e+00": 1.1255291991122067, "train/loss_044_lr2.6e+01_wd1.0e+00": 1.5823956283554435, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.8363794446457176, "train/loss_046_lr3.6e+01_wd1.0e+00": 4.349708135724068, "train/loss_047_lr4.3e+01_wd1.0e+00": 5.996476955423131, "train/loss_048_lr5.0e+01_wd1.0e+00": 7.159497283129022, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.023831758508458735, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.023189597791060806, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.022067790972068905, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.02091969427652657, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.019815941425040364, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.01843670948408544, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.017143793259747325, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.016003644871525467, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.01479270386043936, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.013522655400447548, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.01213755112607032, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.010114309703931212, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.008478368310024962, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.006960884520085528, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.006334968461887911, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.006091413576505147, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.005923933897865936, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.005808345197001472, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.0057212050765519966, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.005648968701134436, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.005561036767321639, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.005486060215625912, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.005420236018835567, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0053837131947511805, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.005325654214830138, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.00521276323357597, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.005073232972063124, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.004939778550469782, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.004729741122573614, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.004596885211067274, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.004477708020131104, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0043878876986855175, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0042460051777743505, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.004351654493475508, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.004811103427709895, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.005130978181987302, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.007490306670842983, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.011109708580625011, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.018001491688946773, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.028180529670850073, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0331801706456528, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.039938219878917665, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.03599484772917909, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.07442358519133939, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0982639854075795, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.13450030440865846, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.17063462460622264, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.2188072966686561, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.24587325809275, "validation/loss_000_lr2.0e-02_wd1.0e+00": 1.7509527206420898, "validation/loss_001_lr2.3e-02_wd1.0e+00": 1.6201674938201904, "validation/loss_002_lr2.8e-02_wd1.0e+00": 1.4288369417190552, "validation/loss_003_lr3.3e-02_wd1.0e+00": 1.2674839496612549, "validation/loss_004_lr3.8e-02_wd1.0e+00": 1.131542444229126, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.9731124043464661, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.8215511441230774, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.6718390583992004, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.49292948842048645, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.3392481207847595, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.23808595538139343, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.14483825862407684, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.0990784540772438, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.07307421416044235, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.06177588179707527, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.05519365891814232, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.04946449398994446, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.04494006559252739, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.04130253940820694, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.038833048194646835, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.03639891743659973, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.0342591293156147, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.032186463475227356, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.030583538115024567, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.029822364449501038, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.02890431135892868, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.028106043115258217, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.02777061052620411, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.028745464980602264, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.03019241988658905, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.03203244134783745, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.030625851824879646, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.02863883227109909, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.026544908061623573, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.02944614365696907, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.0370463952422142, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.10284806787967682, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.08804710954427719, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.2543671131134033, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.37821507453918457, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.5194220542907715, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.48125162720680237, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.6620033979415894, "validation/loss_043_lr2.2e+01_wd1.0e+00": 1.2849411964416504, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.4691414833068848, "validation/loss_045_lr3.1e+01_wd1.0e+00": 4.499453067779541, "validation/loss_046_lr3.6e+01_wd1.0e+00": 5.036466598510742, "validation/loss_047_lr4.3e+01_wd1.0e+00": 5.844730377197266, "validation/loss_048_lr5.0e+01_wd1.0e+00": 8.430780410766602, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.5825892857142857, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.6207837301587301, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.6956845238095238, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.7646329365079365, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.8194444444444444, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.8583829365079365, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.8876488095238095, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.9017857142857143, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9176587301587301, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9407242063492064, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9662698412698413, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9776785714285714, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9791666666666666, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.984375, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.984375, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.984375, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9846230158730159, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9866071428571429, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9880952380952381, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9885912698412699, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9885912698412699, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9895833333333334, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9898313492063492, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9903273809523809, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9908234126984127, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9900793650793651, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9905753968253969, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9905753968253969, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9895833333333334, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9895833333333334, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.988343253968254, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9893353174603174, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9900793650793651, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9910714285714286, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9905753968253969, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9880952380952381, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9828869047619048, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9858630952380952, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9781746031746031, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9809027777777778, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9747023809523809, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9791666666666666, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9809027777777778, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9789186507936508, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9747023809523809, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.970734126984127, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9744543650793651, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9754464285714286, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9689980158730159, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.3458120181688442, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.4149762854356447, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.5534144258409872, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.677444753834167, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.7622865204362896, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.8204271719290507, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.8632326794457015, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.883577272342067, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9051610822139361, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9342785239206334, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9625771693464916, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9745020578438474, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9755951356961593, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9824778592594544, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9821236345109199, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9821236409515096, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9821818465379221, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9840273987472786, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9862740869578337, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9870088923970732, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9868218181194051, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9879621733975441, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.988186782091183, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9886405523049516, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.989239677920545, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9884338142795406, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9887912134021833, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9886708317754239, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9880972733801682, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.988422357925583, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9864538796549462, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9875252527034122, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9889177212291691, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9899369818054973, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9884764091104445, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9856887494781958, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9827934486638367, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9801633721714506, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9719233592768742, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9753651817281951, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9731908938707066, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9767408248149339, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9798569498526748, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9747188545194564, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.973831367127499, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9685211474817648, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9741455693301311, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9719392024206596, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9693560817135166, "id_best": 33, "lr_best": 0.00129, "wd_best": 0.05, "train/loss_best": 0.019633318101987242, "validation/loss_best": 0.026544908061623573, "validation/acc_best": 0.9910714285714286, "validation/f1_best": 0.9899369818054973} +{"epoch": 6, "train/lr": 0.0002924170901991409, "train/loss": 0.5445079519599676, "train/grad": 0.3681759437918663, "train/loss_000_lr2.0e-02_wd1.0e+00": 1.6363575744628907, "train/loss_001_lr2.3e-02_wd1.0e+00": 1.501180191040039, "train/loss_002_lr2.8e-02_wd1.0e+00": 1.3081113815307617, "train/loss_003_lr3.3e-02_wd1.0e+00": 1.1490352058410644, "train/loss_004_lr3.8e-02_wd1.0e+00": 1.0158636093139648, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.8588209056854248, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.7039057302474976, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.548525025844574, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.37910486936569215, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.2567678186297417, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.18037163734436035, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.11636097192764282, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.08973584920167924, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.07353198504075407, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.0655294460337609, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.06055336490273475, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.05596539672464132, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.05181580126285553, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.04803783167153597, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.04500841522589326, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.041698968643322586, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.03860033977776766, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.03537334363907576, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.03227903268299997, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.02947555359452963, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.026755109606310726, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.024753101151436568, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.023216507313773036, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.021578829912468792, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.01959440065547824, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.017930149277672173, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.0161355225648731, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.015472848042845726, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.013979144589975477, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.014481443874537946, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.020123219955712555, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.04077359045855701, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.06947003027424216, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.09386227119714022, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.1914700175076723, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.18241777596995234, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.24726921131834387, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.233208193378523, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.7576153857819736, "train/loss_044_lr2.6e+01_wd1.0e+00": 1.2573915331345051, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.467039361642674, "train/loss_046_lr3.6e+01_wd1.0e+00": 1.8333438293635844, "train/loss_047_lr4.3e+01_wd1.0e+00": 4.2021396413818, "train/loss_048_lr5.0e+01_wd1.0e+00": 4.568858659751713, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.022344510462135078, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.021409191070124508, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.01989372075535357, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.018545668930746616, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.01741941477637738, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.016180186942219735, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.01508418590761721, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.013969562319107353, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.012275003637187183, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.010429757409729063, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.008888001032173633, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.00719361407100223, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.006450628456659615, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.006093813949264586, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.005948719774605707, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.005865101984818466, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.0057797370199114085, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.005690509217092767, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.0055761282626190225, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.005482758878206369, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.005377624947577715, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.005269433111825492, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0051389317336725075, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0050015513185644525, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.004878446607617662, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.004812655313580763, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.004724713798423181, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.004649749449927185, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.004555851909135527, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.004357489746071224, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.004181014736968791, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0039806820647208955, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.003985592996905325, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.00386290310696495, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0039948154611283825, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.005347201264685282, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.008293608191913791, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.012173819391198321, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.013749685478119939, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.021099171701750984, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0197596818853724, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.028315795178201805, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.026077286176778288, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.061083743205277256, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.09368744472717613, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.11189623054274399, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.09902947715846239, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.18138157517900028, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.18863870410233352, "validation/loss_000_lr2.0e-02_wd1.0e+00": 1.5177303552627563, "validation/loss_001_lr2.3e-02_wd1.0e+00": 1.380936861038208, "validation/loss_002_lr2.8e-02_wd1.0e+00": 1.1896376609802246, "validation/loss_003_lr3.3e-02_wd1.0e+00": 1.034674048423767, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.9046832919120789, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.74819016456604, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.5890629291534424, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.4317970275878906, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.28116124868392944, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.18324604630470276, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.12443827092647552, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.08453541994094849, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.06877007335424423, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.05722876265645027, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.05080264061689377, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.046496350318193436, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.042555175721645355, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.039116762578487396, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.036207109689712524, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.03419744595885277, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.03218769654631615, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.030658939853310585, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.029179558157920837, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.028212852776050568, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.02738773450255394, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.026567691937088966, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.02569660358130932, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.02508443221449852, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.02443019673228264, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.0239899680018425, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.024440331384539604, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.026287393644452095, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.029637660831212997, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.034418027848005295, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.03472186252474785, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.05727618932723999, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.09010762721300125, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.13075797259807587, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.126137837767601, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.28485482931137085, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.2291198968887329, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.31854012608528137, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.4331144690513611, "validation/loss_043_lr2.2e+01_wd1.0e+00": 1.0309315919876099, "validation/loss_044_lr2.6e+01_wd1.0e+00": 1.7050389051437378, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.610304832458496, "validation/loss_046_lr3.6e+01_wd1.0e+00": 1.600020170211792, "validation/loss_047_lr4.3e+01_wd1.0e+00": 4.701565265655518, "validation/loss_048_lr5.0e+01_wd1.0e+00": 4.304730415344238, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.6597222222222222, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.7130456349206349, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.7904265873015873, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.8531746031746031, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.8836805555555556, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.9069940476190477, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9181547619047619, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.9375, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9610615079365079, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9742063492063492, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9786706349206349, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9813988095238095, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9848710317460317, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9853670634920635, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9858630952380952, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.986359126984127, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9880952380952381, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9895833333333334, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9898313492063492, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9905753968253969, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9900793650793651, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9903273809523809, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9905753968253969, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9910714285714286, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9910714285714286, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9908234126984127, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9915674603174603, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9915674603174603, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9923115079365079, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9928075396825397, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9913194444444444, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9913194444444444, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9908234126984127, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9903273809523809, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9866071428571429, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9861111111111112, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.984375, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9878472222222222, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9816468253968254, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9858630952380952, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.986359126984127, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9833829365079365, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9853670634920635, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.984375, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9779265873015873, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9856150793650794, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9779265873015873, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9801587301587301, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.4885921071909235, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.5973009073166254, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.732533382112966, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.8220898477263148, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.8642928964791904, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.8959119528420929, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.9094158315574441, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9316652184330527, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9578322434903054, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9706897184045967, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9753929090190636, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9788024821610961, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9823968649282807, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9829721878662838, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9837390204528366, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9844610493086103, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9863659296780793, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9879824366538783, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9882497542530062, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9891517645885108, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9882181065442902, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9889363535811623, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9891200940978467, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9895137480440296, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9898850235306019, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9893454636912745, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.990474718007057, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9900371638228174, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9908511489133376, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.991433429258681, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9904577528203374, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9888736964057216, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9895991226269119, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9888395446022002, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9886652728384727, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9804551204161892, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9834700884072696, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9802788159051946, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9864116432843967, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9791975337151237, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9829899614950558, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9865242426313973, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9787353789258252, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9826615491822056, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9820683603760844, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9747418011569952, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9851362230754481, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9749308688177275, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9782260154838731, "id_best": 29, "lr_best": 0.0006899999999999999, "wd_best": 0.05, "train/loss_best": 0.01959440065547824, "validation/loss_best": 0.0239899680018425, "validation/acc_best": 0.9928075396825397, "validation/f1_best": 0.991433429258681} +{"epoch": 7, "train/lr": 0.00027969249556793234, "train/loss": 0.36079940989613535, "train/grad": 0.28897621225565673, "train/loss_000_lr2.0e-02_wd1.0e+00": 1.4225511169433593, "train/loss_001_lr2.3e-02_wd1.0e+00": 1.2860889434814453, "train/loss_002_lr2.8e-02_wd1.0e+00": 1.0982893371582032, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.9465482330322266, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.817706937789917, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.6590059041976929, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.49829936504364014, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.35379412174224856, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.22987060874700546, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.15179693311452866, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.1107049598544836, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.08445797584950925, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.07306507868692279, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.0640111987479031, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.058567819073796275, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.054639186104759575, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.05073301996104419, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.04693485535681248, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.0433724747877568, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.04053839008323848, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.03732471544295549, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.034369519958272574, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.03130563208833337, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.028354877270758153, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.025574314603582025, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.02251934280619025, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.019993183091282844, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.01770397729240358, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.014740849509835244, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.011461478359997272, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.00860379872843623, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.007595974439755082, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.006537968572229147, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.008199370494112372, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.007897575795650482, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.025438467022031546, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.03887386883608997, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.054444445027038456, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.061924924571067096, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.09402155448682606, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.08384857297874987, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.11358004635199904, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.16217954097315668, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.32824538215063515, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.6980934500228614, "train/loss_045_lr3.1e+01_wd1.0e+00": 1.1865901789441704, "train/loss_046_lr3.6e+01_wd1.0e+00": 1.0794425621815025, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.4889828399196268, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.890346559518948, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.021061453092843293, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.019955562613904475, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.018347328510135413, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.017068876791745423, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.01606741357129067, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.014929010048508645, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.013682120721787214, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.012064130534417928, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.010022085434757173, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.008208398998249322, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.007023731132503599, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.006321506613167003, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.006081611553672701, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.0059057910612318664, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.005787033180822619, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.005684617458609864, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.005560251236020121, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.005416302006342449, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.005265836396429222, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.0051481417301693, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.005009918051655404, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.004870208291540621, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.004691801229928388, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.004515126938204048, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.004353840025141835, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.004171437931581749, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.004008575610459957, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0038237014440528584, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.003504478105933231, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0030546108747421387, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0025878000355078258, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0024394022931892322, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.002237149384316126, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0023450154435960256, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0028500807176328634, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.005855987345839111, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.007344970212917401, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.01157171994836605, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.011032365075210653, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.016099930938611524, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.014027978331945124, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.016775662969980145, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.02249917444278724, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.03899681543791959, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.05737943180414649, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.07244179039881113, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0844086442439911, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.13273432614751018, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.1552952575449938, "validation/loss_000_lr2.0e-02_wd1.0e+00": 1.3324933052062988, "validation/loss_001_lr2.3e-02_wd1.0e+00": 1.1973499059677124, "validation/loss_002_lr2.8e-02_wd1.0e+00": 1.0131828784942627, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.8637317419052124, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.7343237996101379, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.57110995054245, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.4099901020526886, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.2799775004386902, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.17493318021297455, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.1122175008058548, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.08457254618406296, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.06644363701343536, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.05749063193798065, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.04985376447439194, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.045188773423433304, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.04205704480409622, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.03924597054719925, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.03694135695695877, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.03510988876223564, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.03370630368590355, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.03237243741750717, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.031267501413822174, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.029901620000600815, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.02839551866054535, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.026768522337079048, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.025350093841552734, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.02470429055392742, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.024828463792800903, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.02485605888068676, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.02382688596844673, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.02487797662615776, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.025114906951785088, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.02607310749590397, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.033198583871126175, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.037916772067546844, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.0633644312620163, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.08309956640005112, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.10866177082061768, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.1841554194688797, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.22471460700035095, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.2486375868320465, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.5905216932296753, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.30955439805984497, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.9243038296699524, "validation/loss_044_lr2.6e+01_wd1.0e+00": 1.2159143686294556, "validation/loss_045_lr3.1e+01_wd1.0e+00": 1.4425599575042725, "validation/loss_046_lr3.6e+01_wd1.0e+00": 1.8081120252609253, "validation/loss_047_lr4.3e+01_wd1.0e+00": 4.107192516326904, "validation/loss_048_lr5.0e+01_wd1.0e+00": 5.955713748931885, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.7348710317460317, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.7919146825396826, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.8568948412698413, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.8893849206349206, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9069940476190477, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.9188988095238095, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9387400793650794, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.9623015873015873, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9744543650793651, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9799107142857143, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9821428571428571, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9841269841269841, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9851190476190477, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.986359126984127, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.988343253968254, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9878472222222222, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.988343253968254, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9890873015873016, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9890873015873016, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9890873015873016, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9900793650793651, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9893353174603174, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9903273809523809, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9905753968253969, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9923115079365079, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9918154761904762, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9923115079365079, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9913194444444444, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9913194444444444, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9918154761904762, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9915674603174603, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9925595238095238, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9915674603174603, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9918154761904762, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9875992063492064, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9890873015873016, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9871031746031746, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9861111111111112, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9875992063492064, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.988343253968254, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9789186507936508, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9878472222222222, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9831349206349206, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9838789682539683, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9866071428571429, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9871031746031746, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9791666666666666, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9717261904761905, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.6323680972274437, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.7273839043968364, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.82528136983509, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.8723363735568768, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.8953066879426665, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.9094536789673994, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.9331183363488775, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9588813062571899, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9706006066295397, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.976771521506946, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9797891043565414, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9819421351195988, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.982747813196274, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9840219798872576, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9861837968183057, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.985989016776507, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9867202130183562, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.987632005653478, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9876363705437996, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9879594324920605, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9888624122545974, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.988498277761436, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9894797744086044, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9897067907806633, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9911638781977243, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9906261458666724, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9910330574904691, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9899641188776214, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9896391385796558, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9895308199148354, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9892556044676859, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9902449015436633, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9905669415103179, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9894438281180553, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9888619800064037, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9843087351802938, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9865938456217636, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9849961618717196, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9814705319484021, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9854621743056017, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9861172202219454, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9705455083376794, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9853686307213179, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9789183617510331, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9824649850293784, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9843573695452925, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9853851031262744, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9748945987060642, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9672916218557971, "id_best": 32, "lr_best": 0.0011099999999999999, "wd_best": 0.05, "train/loss_best": 0.006537968572229147, "validation/loss_best": 0.02607310749590397, "validation/acc_best": 0.9925595238095238, "validation/f1_best": 0.9905669415103179} +{"epoch": 8, "train/lr": 0.0002612959497061927, "train/loss": 0.247497472204268, "train/grad": 0.20384810773655773, "train/loss_000_lr2.0e-02_wd1.0e+00": 1.2490495681762694, "train/loss_001_lr2.3e-02_wd1.0e+00": 1.1164219665527344, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.9360908699035645, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.7879049205780029, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.6572946691513062, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.494036021232605, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.34547808051109313, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.23560876101255418, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.14838578641414643, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.10258243381977081, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.08328597381711006, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.06974729516543449, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.06255507522262632, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.05596136838197708, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.051561058638617395, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.04823923695832491, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.044688511807471513, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.041133212065324186, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.037664724308997394, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.03475043593905866, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.03145121497102082, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.028450218560174108, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.025431423028931022, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.02245063342154026, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.019566641645506023, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.016353929406031965, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.013590511567890644, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.01125165498815477, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.008167473506182433, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.004993571005761623, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0031740552000701426, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.002695607878267765, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.0029911489225924017, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.0035829171165823936, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.006527105644345284, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.020299397287890316, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.030337411109358073, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.031245503732934596, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.050670242318883535, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.05967647115699947, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.055568632325157526, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.07378065780736506, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.09131140841171145, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.1294250958971679, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.3148140591196716, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.4347205921076238, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.699931602170691, "train/loss_047_lr4.3e+01_wd1.0e+00": 1.5334717848710715, "train/loss_048_lr5.0e+01_wd1.0e+00": 1.7990054204780608, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.019479651292786, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.018318305970169604, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.016751309381797908, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.015562139027751982, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.014591362988576294, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.013323714509606361, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.0116778320283629, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.009912255078088492, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.00797040430130437, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.006631555687636137, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.006079345941543579, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.005762248419923708, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.005609972319798544, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.005467580342083238, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.005359030083054677, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.005276878007571213, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.005160423136549071, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.005032026478438638, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.00487769757892238, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.004720265559735708, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.004521604357578326, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.004326086963847047, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.00413649848633213, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0039565552028216185, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0037322510291414803, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.003428097168143722, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0031022219495207537, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.002777719985024305, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0022501088050194086, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0015810202119973837, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0011127683619906747, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0009911948610215405, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0009074997455377343, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.001063019431160228, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0017835774760840196, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.004591090915417908, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.005539615319847684, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.007905994665275626, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.009948887733252986, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.011125692003612707, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.010851213724840134, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.012937997280489744, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.012384368861481379, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.02226096265026714, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.037218030882091364, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.04816269359255856, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0550140422925367, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.09355155607467858, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.09932625541647036, "validation/loss_000_lr2.0e-02_wd1.0e+00": 1.1886571645736694, "validation/loss_001_lr2.3e-02_wd1.0e+00": 1.0578831434249878, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.879659116268158, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.7306545972824097, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.5970465540885925, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.4316600263118744, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.2924063801765442, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.1940706968307495, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.11834171414375305, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.08406244963407516, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.06926963478326797, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.05781476944684982, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.0514245443046093, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.04563092067837715, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.04179102182388306, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.03910430893301964, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.036733511835336685, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.03478911146521568, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.033208515495061874, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.032218705862760544, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.031025517731904984, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.030250655487179756, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.02937905676662922, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.02822457253932953, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.02683471329510212, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.02585461549460888, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.025423740968108177, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.025394370779395103, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.025908850133419037, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.02758045308291912, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.02799699455499649, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.028059765696525574, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.02934800088405609, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.03327092528343201, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.05510970577597618, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.05585649237036705, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.0856776311993599, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.15270675718784332, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.23433203995227814, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.2298963963985443, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.3077322244644165, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.3144889771938324, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.3520036041736603, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.8657209277153015, "validation/loss_044_lr2.6e+01_wd1.0e+00": 1.0796257257461548, "validation/loss_045_lr3.1e+01_wd1.0e+00": 1.630927324295044, "validation/loss_046_lr3.6e+01_wd1.0e+00": 1.4564728736877441, "validation/loss_047_lr4.3e+01_wd1.0e+00": 2.5436949729919434, "validation/loss_048_lr5.0e+01_wd1.0e+00": 2.395937442779541, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.8003472222222222, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.8435019841269841, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.8794642857142857, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.902281746031746, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9122023809523809, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.9310515873015873, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9585813492063492, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.972718253968254, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9799107142857143, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.982390873015873, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9846230158730159, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9853670634920635, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9853670634920635, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9866071428571429, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9880952380952381, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9890873015873016, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9893353174603174, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9890873015873016, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9898313492063492, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9900793650793651, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9900793650793651, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9905753968253969, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9900793650793651, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9900793650793651, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9905753968253969, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9915674603174603, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9918154761904762, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9918154761904762, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9928075396825397, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9915674603174603, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9915674603174603, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9913194444444444, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9910714285714286, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9905753968253969, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.988343253968254, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9888392857142857, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9885912698412699, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.986359126984127, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.982390873015873, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9853670634920635, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9853670634920635, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9871031746031746, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9861111111111112, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.984375, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9878472222222222, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.984375, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.986359126984127, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9811507936507936, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9816468253968254, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.7382753750382111, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.8021478718378818, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.8544520086505637, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.8862195710792329, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.8997654802380148, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.9238236574029566, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.9553303008670491, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9693840810961503, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9771275789624009, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.980857475201577, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.982745276733659, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9833310484478865, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9833310484478865, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9849955314770993, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9861710879743371, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9876605964066156, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9879336091314269, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9874394331414116, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.988028523428067, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9883380777329859, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.988341300779589, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9891072604138744, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9883798490210713, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9884358083850164, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9887962063190352, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9896569053934537, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9897616645621861, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9897616645621861, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9904212081455229, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9888381875494606, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9892890875743515, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.988717604182485, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9884314335430011, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9880285681861712, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9859839823464795, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9864840690150795, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9864076890615749, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9835654527071344, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9774174092602466, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9838194107999347, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9812902975423698, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9870042416172486, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9846453632105, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9824889803685143, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9850494275607204, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9834410191018059, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9838468542528028, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9780673042909924, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9778806774336063, "id_best": 28, "lr_best": 0.00057, "wd_best": 0.05, "train/loss_best": 0.008167473506182433, "validation/loss_best": 0.025908850133419037, "validation/acc_best": 0.9928075396825397, "validation/f1_best": 0.9904212081455229} +{"epoch": 9, "train/lr": 0.00023803200426111704, "train/loss": 0.168290438875556, "train/grad": 0.1564932614006102, "train/loss_000_lr2.0e-02_wd1.0e+00": 1.1330756378173827, "train/loss_001_lr2.3e-02_wd1.0e+00": 1.0043200302124022, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.8275127506256104, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.6775783967971801, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.5425695991516113, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.38314217805862427, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.2588197475671768, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.1723574534058571, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.11072756886482239, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.08507793378084898, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.07355723448097706, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.06423694242723287, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.05861901470459998, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.053040970116853714, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.0489791411254555, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.04575776415877044, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.042282867329195145, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.03872931797988713, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.03529126530513167, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.032373777916654946, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.029155844058841467, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.026088616317138075, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.022918104846030473, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.01964454281143844, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.01643384702503681, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.01278369328007102, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.009775787470862269, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.00746048322878778, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.005198678467422724, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0038359546195715667, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.002728425674140453, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.002230557007715106, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.002103685466572642, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.0005200250912457704, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.0028141716960817576, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.010180381936952471, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.011781798200681806, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.024338059546425938, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.02517415389418602, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.021650982927531003, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.05048189212568104, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.03933321627788246, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.039856209652498364, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.1171525690332055, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.1611757834814489, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.2243043528776616, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.3000951506290585, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.6062643073406071, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.7627008619997651, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.018582305377349256, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.01747219352517277, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.016042096563614903, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.01493056386243552, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.013917743912898003, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.012309077770914882, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.010402278716210276, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.008604286361951381, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.006929190239170566, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.006235206688288599, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.005972703815205023, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.005806283145211637, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.005716010922915302, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.005629089252906851, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.005545470495999325, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.005466101682686713, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.005371046484506223, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.005244034074712545, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.0050944011844694615, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.004945464291376993, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.004764167995890602, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.004569023229996674, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0043361045868368815, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.004053235300525557, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.003721156718820566, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0032490832199982833, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0027900722772756124, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.002346717193577206, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0017983689735046938, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0013517064900224795, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.001069923524009937, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0009488925057576126, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0006092849270589795, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0003440752432766203, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0013076894153687135, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0031453513991010597, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0037318770781939394, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.006163027622422046, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0066449093718998755, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.004950351844604886, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.010037476184516132, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.007838863631356443, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.009710574474441926, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.018352192847889606, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.023324870053628363, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.031752064399312746, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.03937349525572963, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.06067830884694009, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.06914046311243315, "validation/loss_000_lr2.0e-02_wd1.0e+00": 1.0773608684539795, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.9507046341896057, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.7751397490501404, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.6235039830207825, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.4870256781578064, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.33319661021232605, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.21988944709300995, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.1415960043668747, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.0913509875535965, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.07088048756122589, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.06093854457139969, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.05237244814634323, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.04737627133727074, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.04247334599494934, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.03922702372074127, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.036899980157613754, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.03453006222844124, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.03251089155673981, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.030829375609755516, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.02951245754957199, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.028254326432943344, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.027262048795819283, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.0265799593180418, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.025909630581736565, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.025622457265853882, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.025490252301096916, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.02556668408215046, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.025727592408657074, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.025290586054325104, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.0265070628374815, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.027267063036561012, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.028593717142939568, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.03128577768802643, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.0334431417286396, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.03829194977879524, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.057168178260326385, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.07269106805324554, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.13074132800102234, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.17122626304626465, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.22771674394607544, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.2074929177761078, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.3185969889163971, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.29382339119911194, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.7636459469795227, "validation/loss_044_lr2.6e+01_wd1.0e+00": 1.1232792139053345, "validation/loss_045_lr3.1e+01_wd1.0e+00": 1.083046555519104, "validation/loss_046_lr3.6e+01_wd1.0e+00": 1.383691430091858, "validation/loss_047_lr4.3e+01_wd1.0e+00": 2.115351676940918, "validation/loss_048_lr5.0e+01_wd1.0e+00": 2.451096534729004, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.8392857142857143, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.8715277777777778, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.9017857142857143, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.9161706349206349, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9283234126984127, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.9496527777777778, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9694940476190477, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.9766865079365079, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.980406746031746, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9838789682539683, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.984375, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9853670634920635, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9866071428571429, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9875992063492064, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9888392857142857, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9898313492063492, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9900793650793651, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9898313492063492, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9893353174603174, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9903273809523809, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9910714285714286, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9918154761904762, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9918154761904762, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9923115079365079, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9913194444444444, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9908234126984127, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9905753968253969, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9898313492063492, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9913194444444444, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9910714285714286, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9910714285714286, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9918154761904762, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9915674603174603, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9908234126984127, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9908234126984127, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9908234126984127, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9893353174603174, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9888392857142857, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.988343253968254, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9898313492063492, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9890873015873016, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9861111111111112, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9861111111111112, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9858630952380952, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9853670634920635, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9885912698412699, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9851190476190477, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9828869047619048, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9826388888888888, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.797265841072545, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.8465748035640689, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.887802702563057, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.9062612265732076, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.920838709363576, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.9455932325659524, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.9662417675637551, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9738677934171275, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9779131737089855, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9817588004635486, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9821233498694901, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9839720866397134, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9852031347878839, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.986131053307096, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9867141293869957, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9878904337975214, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9880694610970063, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9878860740017217, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9870334424420173, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9884487094121138, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9889874089111741, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.989977048212237, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.990336001181103, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9906085222158474, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9897579244284962, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.989079737597671, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9881768718991895, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9868216726713399, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9881679111838021, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9881661008156257, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.987986124702305, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9887912135968078, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9887886902928964, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9883418751416185, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9893720457593027, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9884269175107464, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9878891407576592, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.986833324721931, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9867171055035481, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9893588473326191, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9872450604456124, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9858318492056245, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9836503256153131, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9847203804770992, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9820822743024148, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.987050930757718, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9852886114399728, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9793471647461205, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.978993134973022, "id_best": 23, "lr_best": 0.00025499999999999996, "wd_best": 0.05, "train/loss_best": 0.01964454281143844, "validation/loss_best": 0.025909630581736565, "validation/acc_best": 0.9923115079365079, "validation/f1_best": 0.9906085222158474} +{"epoch": 10, "train/lr": 0.00021091808096876188, "train/loss": 0.12955174010246992, "train/grad": 0.11243265945464373, "train/loss_000_lr2.0e-02_wd1.0e+00": 1.0367803764343262, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.9118696784973145, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.7368105506896973, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.5839556360244751, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.4486885619163513, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.3051025259494782, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.20260388433933257, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.1337536282837391, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.09355311837047338, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.07701453475281596, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.06863865051418543, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.06106417456641793, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.05621658371761441, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.051025748159736393, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.047173664057627324, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.04400620088912546, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.040443395357578994, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.036796622751280664, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.03315247228369117, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.030161592420190574, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.026735961847007276, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.023506109761074187, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.020202778978273273, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.01686253594234586, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.013538915924727916, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.009783226624131202, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.006843953290954232, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.004690065141767263, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0025948509480804207, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0022203421220183374, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0020923635084182024, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.0022360781487077474, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.0003794725611805916, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.00022630428895354271, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.0005418175552040339, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.0017011651769280433, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.0013000594172626733, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.003264234410598874, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.01224586240015924, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.012920627072453499, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.011354608666151763, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.011370245879516006, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.025508734267205, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.0639969861228019, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.03824852372519672, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.12885069442912936, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.1924746853671968, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.36666944082826375, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.34686313633807003, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.017575151245109735, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.0165498671727255, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.015273047834634781, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.014234457788988948, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.013130617379210889, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.011349661585409194, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.00949413558235392, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.007722672879463061, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.006484383592614904, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.006032761470414698, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.005834800993907266, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.0056507986923679705, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.005526351915905252, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.005375815167790279, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.00525895792467054, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.005147998633910902, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.005016220172692556, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.004871655534661841, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.0047180055142962375, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.0045823311223648485, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.004414264163788175, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.00421952260658145, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.003982105905670323, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.003661609935006709, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.003271535773674259, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.002733999071533617, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.002204348291888891, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0017019233201790484, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0010981879268501871, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0008624559664667686, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0006975321697427717, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0005484228748673559, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.00016366346533004618, "train/grad_033_lr4.3e+00_wd1.0e+00": 9.551616689634556e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0003176913822738925, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0012457697633483633, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0010868963823409666, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0030665822229741222, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.004137908893995163, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.004123212669826188, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.004244821116935543, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0035287309718776212, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.005808832627857321, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.011164650975937116, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.00949530401528766, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.020612186120420442, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.022849316161448457, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.040210940442277264, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.042258066508633806, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.9916724562644958, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.8675406575202942, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.6920281052589417, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.5374553203582764, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.4034789502620697, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.2680254876613617, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.17252330482006073, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.1110546737909317, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.0780135989189148, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.0636538565158844, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.0559990219771862, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.049046143889427185, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.04460093006491661, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.04026956856250763, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.03744698315858841, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.03537697345018387, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.03347862884402275, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.03186565637588501, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.03034047782421112, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.02940911427140236, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.02841120772063732, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.02765542082488537, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.02689531072974205, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.02617591992020607, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.025709521025419235, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.02498883754014969, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.024440113455057144, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.024602500721812248, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.024648023769259453, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.024991475045681, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.025013327598571777, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.02640569768846035, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.028010331094264984, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.032690443098545074, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.03399785980582237, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.05325182154774666, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.06461244076490402, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.14644771814346313, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.11954191327095032, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.21349050104618073, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.22112107276916504, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.31340041756629944, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.23065051436424255, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.4950025677680969, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.7736644148826599, "validation/loss_045_lr3.1e+01_wd1.0e+00": 1.0671141147613525, "validation/loss_046_lr3.6e+01_wd1.0e+00": 1.3504927158355713, "validation/loss_047_lr4.3e+01_wd1.0e+00": 1.5983444452285767, "validation/loss_048_lr5.0e+01_wd1.0e+00": 2.16957688331604, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.8616071428571429, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.8834325396825397, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.9060019841269841, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.9201388888888888, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9377480158730159, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.9630456349206349, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9734623015873016, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.9796626984126984, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9831349206349206, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9846230158730159, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9846230158730159, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9861111111111112, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9875992063492064, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9885912698412699, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9890873015873016, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9890873015873016, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9893353174603174, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9898313492063492, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9903273809523809, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9908234126984127, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9908234126984127, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9900793650793651, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9895833333333334, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9900793650793651, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9908234126984127, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9910714285714286, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9918154761904762, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9915674603174603, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9915674603174603, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9918154761904762, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9923115079365079, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9915674603174603, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9908234126984127, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9893353174603174, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9910714285714286, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9880952380952381, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9898313492063492, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9880952380952381, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9868551587301587, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9873511904761905, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9903273809523809, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9871031746031746, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9871031746031746, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9875992063492064, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9848710317460317, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9856150793650794, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9836309523809523, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.8325916076367127, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.864159121696749, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.8937162926141985, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.910333361147017, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.9318711271668874, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.9590115438839811, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.9706828290960943, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9770682794469016, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9815310051879057, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9827039898724628, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9827039963130524, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9841083926020188, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9855439711017973, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9864786817255679, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.987258727981246, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9869041351003915, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.98745598033083, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9881926016269325, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9887212858004213, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9891720786102921, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9893567966239568, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9880012337194212, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9873890412603039, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9878389409143105, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9884669287018399, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9890056053607087, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9891748363832212, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.988940760958351, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9895286821058152, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9890784746129526, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.988571777829087, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9893328618753012, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9890980701783789, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9883418751416185, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9903413510077066, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9867864621650733, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9893560180064669, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9876070648289745, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9871843834584555, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9873489557252995, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9856075893017087, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9849100358233727, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9888754945519045, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9852896731903689, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.98621748518987, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9859527223294238, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9806681002139774, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9857005509579254, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9812149984911022, "id_best": 31, "lr_best": 0.0009299999999999999, "wd_best": 0.05, "train/loss_best": 0.0022360781487077474, "validation/loss_best": 0.02640569768846035, "validation/acc_best": 0.9923115079365079, "validation/f1_best": 0.9893328618753012} +{"epoch": 11, "train/lr": 0.00018113997589164516, "train/loss": 0.10386005472391843, "train/grad": 0.08335046291351318, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.9559172248840332, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.8335606288909913, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.6588301134109497, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.5050591945648193, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.3761419248580933, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.2511365407705307, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.16360924944281577, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.11017818287014962, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.08301501229405403, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.0710446535423398, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.06446018149144947, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.058184609385207295, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.05383042238652706, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.049007892124354836, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.04526208026334643, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.042089988831430676, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.038587348237633705, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.034861789532005784, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.031169824665412307, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.02811463379301131, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.024518602415919303, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.02103350835852325, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.01746153119020164, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.013755878498777747, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.010263239787891508, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.006631794786080718, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.0040729216299951075, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0025980375241488217, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.001503311265259981, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.000845176950097084, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0005971239134669304, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.0004290154669433832, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.000281610582023859, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.00018922493793070317, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.00010950351133942604, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.0006948565691709519, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.0002620426192879677, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.00411648784764111, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.0033628132473677397, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.007191108157858252, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.010400955062359572, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.002747692987322807, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.008149783881381155, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.02348029921762645, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.014718256201595068, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.09010484350845217, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.11190752669237554, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.13756135085597634, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.11609280640259385, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.016916313879191874, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.015898161130025984, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.014556785258464515, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.013339090687222778, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.011939565315842629, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.009978150574024767, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.008178542065434159, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.006751052689505741, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.006013645845232531, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.005758361374028027, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.00562821970845107, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.005494745888281614, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.0053860935068223625, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.005242206825932953, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.005121418246417307, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.00500258352374658, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.0048712819878710435, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.004722151154128369, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.004556547869578935, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.004408871064515552, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.004202563774088048, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.003950408429082017, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.003638797393650748, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.003246844976383727, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0027890689730338636, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.002166650192120869, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0015514284184428107, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0010792993089307856, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0006640801928642759, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0003668442397247418, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0002688472956651822, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.00022942610512700413, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.00011529794890975609, "train/grad_033_lr4.3e+00_wd1.0e+00": 8.160575819772475e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 6.0848175741341494e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0005539861215257247, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.00019268112903808533, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0018834067804418544, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.001996537115810003, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0032853451749821436, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0022225315542053646, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0018228217644071778, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.003337569779177885, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0038116623410684096, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0019669048174071634, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.020707497855951676, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.015614509933302354, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.021859780863786274, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.02238257581780056, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.925529420375824, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.8030509948730469, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.6260624527931213, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.4704605042934418, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.3434554636478424, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.2240164577960968, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.1410464495420456, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.09378473460674286, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.07006531953811646, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.05884747952222824, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.052558526396751404, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.04658275097608566, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.04262543097138405, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.038869909942150116, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.036227986216545105, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.03429663926362991, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.032545141875743866, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.030937697738409042, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.029624242335557938, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.028639931231737137, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.027699870988726616, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.02686871774494648, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.026126351207494736, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.025541098788380623, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.02532590553164482, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.025349242612719536, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.02513619139790535, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.025358255952596664, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.02591775543987751, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.026239072903990746, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.02659621648490429, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.02733333595097065, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.028528835624456406, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.03274910897016525, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.03402849659323692, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.04620934650301933, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.056709613651037216, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.11407174170017242, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.11269884556531906, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.2310885637998581, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.21514856815338135, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.23134160041809082, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.2105860561132431, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.4803469181060791, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.6247725486755371, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.950176477432251, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.9228951334953308, "validation/loss_047_lr4.3e+01_wd1.0e+00": 1.8115484714508057, "validation/loss_048_lr5.0e+01_wd1.0e+00": 1.321213722229004, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.8690476190476191, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.8898809523809523, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.9099702380952381, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.9265873015873016, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9471726190476191, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.9689980158730159, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9766865079365079, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.980406746031746, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9848710317460317, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9851190476190477, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9861111111111112, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9873511904761905, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9885912698412699, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9895833333333334, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9900793650793651, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9895833333333334, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9895833333333334, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9900793650793651, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9905753968253969, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9910714285714286, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9915674603174603, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9918154761904762, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9913194444444444, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9918154761904762, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9910714285714286, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9905753968253969, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9908234126984127, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9913194444444444, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9915674603174603, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9915674603174603, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9918154761904762, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9918154761904762, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9918154761904762, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9905753968253969, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9910714285714286, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9910714285714286, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9903273809523809, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9908234126984127, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.988343253968254, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9858630952380952, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9873511904761905, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9890873015873016, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9871031746031746, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9890873015873016, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9873511904761905, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.986359126984127, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9838789682539683, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9873511904761905, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.8431649366533746, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.8730662420205827, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.8995696097876932, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.9193810710741395, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.9425925182427345, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.9655549587581567, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.9732324560099695, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9782288762091792, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9828377882850787, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9831486415704698, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9842769821279966, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9854588283301399, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9868874357081238, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.987611811454201, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.988433191653946, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9873510465950123, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9875291914107613, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9885858373859089, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9889898714875395, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9893597546726479, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9895313484856393, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9897100315911518, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9889801207565615, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.98930899579605, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9883558799090383, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9878158532683443, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9881347336682605, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9886675372795937, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9888355431932183, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.989012831732842, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9889216914898304, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9888769802121017, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9894146067430202, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9879318284094898, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9905222183312178, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9891240452438749, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9893643029401576, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9884496591695043, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9872314984685372, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9855513575216318, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9840308349296869, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9851843400057373, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9868704917759362, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9854970199135722, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.98722949929355, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9859713433152693, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9830799530884291, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.982212732366374, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9861247840228293, "id_best": 34, "lr_best": 0.0015299999999999997, "wd_best": 0.05, "train/loss_best": 0.00010950351133942604, "validation/loss_best": 0.03402849659323692, "validation/acc_best": 0.9920634920634921, "validation/f1_best": 0.9905222183312178} +{"epoch": 12, "train/lr": 0.0001499999999999999, "train/loss": 0.09071999164298176, "train/grad": 0.06248374133370817, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.9084611701965332, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.7863535690307617, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.6090736198425293, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.4542155027389526, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.3318734931945801, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.2187948089838028, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.14056836500763892, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.09868929896503686, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.07796390747651458, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.06793865346349776, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.061968533881008626, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.056001835176721214, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.05171417131088674, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.046921513061970475, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.04320794650353491, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.0401325320918113, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.03673057938925922, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.03318358754739165, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.029614183204248547, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.02658868067897856, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.023018885860219596, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.019584912015125154, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.015912455674260854, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.012191267386078834, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.008643335839733481, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.0052418208215385675, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.003134897341951728, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.001987069630995393, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0011657043360173702, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0006932180281728506, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.00048602933995425704, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.00035537220537662506, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.0002590095903724432, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.00018072488717734813, "train/loss_034_lr5.1e+00_wd1.0e+00": 8.734575472772121e-05, "train/loss_035_lr6.0e+00_wd1.0e+00": 4.483153112232685e-05, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.77846772223711e-05, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.002640559608116746, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.0011022120621055364, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.0014920697640627622, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.0006892083398997783, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.009137065429240466, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.00025318843312561513, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.0077941142767667775, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.003957768436521292, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.047143014781177044, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.030024964455515148, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.037661182284355166, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.09037369247525931, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.01644327288027853, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.015521291494369507, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.014272686457261444, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.012999020330607892, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.011504123932681978, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.009570099951233715, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.0077099524368532, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.0064821257954463364, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.005973643772304058, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.005786530929617584, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.005676121599972248, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.005555055478471332, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.005448195013450459, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.005296809829305857, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.005159225382376462, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.005026232863310724, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.00486478788574459, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.0046902330103330316, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.004489873773127329, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.004309765686630271, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.0040749301815230865, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.003788918370992178, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.003403049972548615, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.00291791634139372, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.002368930329394061, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.001692623749258928, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0011432715499540792, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0007779578313420643, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0004612255026950152, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0002658608303681831, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.00018688937854676623, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.00013914410154029612, "train/grad_032_lr3.7e+00_wd1.0e+00": 9.997843976634613e-05, "train/grad_033_lr4.3e+00_wd1.0e+00": 7.246948391639307e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 4.40275001341206e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 4.635938892324276e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 2.964266141803229e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0010488945469444033, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.000588723897116803, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0010673021620781979, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0008387822172703593, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0013728142701731445, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0006304217829111383, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0020556502685665935, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0019047109508055391, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.008412349128226401, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.008145452236292445, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.011396795901422598, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.013561099886262392, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.8749666213989258, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.7528628706932068, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.574644923210144, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.4200074076652527, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.30152150988578796, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.19375406205654144, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.120761439204216, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.08393628150224686, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.06511053442955017, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.05565272644162178, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.050043635070323944, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.04465467110276222, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.04117815941572189, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.03763444349169731, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.03540365397930145, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.03375678509473801, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.03230574354529381, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.03115803934633732, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.03036642074584961, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.029995715245604515, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.0298360213637352, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.029759356752038002, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.0293052326887846, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.028205128386616707, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.026941843330860138, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.025964591652154922, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.025635765865445137, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.02578047104179859, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.025911657139658928, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.02634834684431553, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.026500776410102844, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.027220450341701508, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.028354249894618988, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.03266342729330063, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.03342859819531441, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.044572241604328156, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.05441131442785263, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.09147621691226959, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.10181157290935516, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.19924023747444153, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.18964453041553497, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.24571958184242249, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.20928922295570374, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.4434097409248352, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.5244818925857544, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.7977356910705566, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.7123409509658813, "validation/loss_047_lr4.3e+01_wd1.0e+00": 1.3162198066711426, "validation/loss_048_lr5.0e+01_wd1.0e+00": 1.329080581665039, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.8826884920634921, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.9020337301587301, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.9171626984126984, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.9365079365079365, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9590773809523809, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.9714781746031746, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9784226190476191, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.9818948412698413, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9846230158730159, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9853670634920635, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9858630952380952, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9871031746031746, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9885912698412699, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9890873015873016, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9890873015873016, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9888392857142857, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9898313492063492, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9900793650793651, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9903273809523809, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9908234126984127, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9905753968253969, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9908234126984127, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9900793650793651, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9903273809523809, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9903273809523809, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9910714285714286, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9913194444444444, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9913194444444444, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9915674603174603, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9923115079365079, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9915674603174603, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9905753968253969, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9923115079365079, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9918154761904762, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9905753968253969, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9908234126984127, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9908234126984127, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9885912698412699, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.988343253968254, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9871031746031746, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9885912698412699, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9875992063492064, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9903273809523809, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9885912698412699, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9878472222222222, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9875992063492064, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.984375, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.8634562960049995, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.8888569766829372, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.9080168716106201, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.9299816870678328, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.9555716218939591, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.9679747895565113, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.9754117095493833, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9804936600138345, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9827039963130524, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9836067429252603, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9843714556547076, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9845524467768824, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9863251464178161, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9869036433193075, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9869049125634772, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9867735673747768, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9880391174010066, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9882196705504224, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9887704218644789, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9892642193428254, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9887618023205014, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9889821595253117, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.988083016626326, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.988309310114982, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9880113315727524, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9884008889099485, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9887068630887261, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9887070166475349, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9888867706648428, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9897845255125275, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9892885476336316, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9886943064052874, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.989594324932017, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9879318284094898, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9907019128505349, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9898090592184242, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9890062005829502, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9888604113641749, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9893434221304453, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9871182815170686, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9871214424647777, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9858325781838094, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9864506881922058, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9862432481609744, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9900095769272452, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9877639763660712, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9850040115171713, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9872351812779809, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9841727103439724, "id_best": 29, "lr_best": 0.0006899999999999999, "wd_best": 0.05, "train/loss_best": 0.0006932180281728506, "validation/loss_best": 0.02634834684431553, "validation/acc_best": 0.9923115079365079, "validation/f1_best": 0.9897845255125275} +{"epoch": 13, "train/lr": 0.00011886002410835478, "train/loss": 0.07925309162586927, "train/grad": 0.05164648325182498, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.8551219367980957, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.7326245212554932, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.5532610154151917, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.4007427287101746, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.28763537168502806, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.18627377688884736, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.11927744634449482, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.08726478602737188, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.07105346877127885, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.06265585554763675, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.057500920370221136, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.05215630408376455, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.04812808766961098, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.043629796020686624, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.0399766531214118, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.03699704731814563, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.03362889508716762, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.030177962770685553, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.026682187085971237, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.023641855455935, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.020089494744315744, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.016787947351112963, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.013365431595593691, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.00997877917252481, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.006882563615217805, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.0039890542440116404, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.0023375989310443403, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0015039020869880915, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0009070674795657397, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.000564309572800994, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0003982586693018675, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.0003006498422473669, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.00022430049255490304, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.00016666313633322715, "train/loss_034_lr5.1e+00_wd1.0e+00": 8.914685808122159e-05, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.2221459075808526e-05, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.3594767078757286e-05, "train/loss_037_lr8.3e+00_wd1.0e+00": 8.586319163441658e-06, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.000175693454220891, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.00029955890029668806, "train/loss_040_lr1.4e+01_wd1.0e+00": 8.61012376844883e-05, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.00039753541350364687, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.2349961325526238e-05, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.0013148864544928075, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.003040041634812951, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.005503103351220489, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.004977315692231059, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.011529927253723144, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.03000488310121, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.015953462482430042, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.015039151860401034, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.013750193314626813, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.012352653462439776, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.010832541696727276, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008998908591456712, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.0072269278462044895, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.0062452467286493625, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.005832528977189213, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.005645668829092756, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.005531380762113259, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.0053976869588950645, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.005283454039890785, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.005139601828996092, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.004992709030630067, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.004858293313591275, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.004682100533100311, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.0044805607649323065, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.00426376599658397, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.004063307261822047, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.00380379044538131, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.0035031649655138607, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.003100888325352571, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.002607513682451099, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0020417154549431872, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.001369928937529039, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0008825056056593894, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0005915062147505523, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.00035551752517676505, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.00022256427399042878, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0001615755125499163, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.00012299610267859861, "train/grad_032_lr3.7e+00_wd1.0e+00": 9.048822863746864e-05, "train/grad_033_lr4.3e+00_wd1.0e+00": 6.848711716799016e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 4.259887232365145e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 2.030176633061487e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 2.2129946750190087e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 1.1477017270299581e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 8.324890389108152e-05, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0003299898134314378, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0002141202873015239, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.00038925853481019056, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.00033840780611071126, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0014395239022276705, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0018406355540944983, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.004634564029661023, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0018574089105996272, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0051816923126521705, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.011666086836598444, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.8369233012199402, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.7150231003761292, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.5358299612998962, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.38387659192085266, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.27272942662239075, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.17269906401634216, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.10786749422550201, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.077699214220047, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.061805251985788345, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.053450413048267365, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.04831719771027565, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.0433853417634964, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.040039755403995514, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.03665795549750328, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.034489940851926804, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.032952651381492615, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.03138945624232292, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.03002455271780491, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.02896251156926155, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.02807696722447872, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.027120692655444145, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.026420461013913155, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.025611432269215584, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.025042414665222168, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.024827908724546432, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.024968182668089867, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.025298459455370903, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.02552028000354767, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.025989225134253502, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.026573309674859047, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.026574961841106415, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.02742653898894787, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.028500832617282867, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.03264661878347397, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.03314535319805145, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.04357955977320671, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.05324940383434296, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.0899730920791626, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.09354406595230103, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.17536714673042297, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.16608135402202606, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.21083703637123108, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.17752404510974884, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.33793318271636963, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.49056220054626465, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.9546063542366028, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.6602864265441895, "validation/loss_047_lr4.3e+01_wd1.0e+00": 1.136868953704834, "validation/loss_048_lr5.0e+01_wd1.0e+00": 1.0309478044509888, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.888640873015873, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.9057539682539683, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.9201388888888888, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.9404761904761905, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9627976190476191, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.972718253968254, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9796626984126984, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.9833829365079365, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9848710317460317, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9858630952380952, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9858630952380952, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9878472222222222, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9890873015873016, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9898313492063492, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9900793650793651, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9900793650793651, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9905753968253969, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9915674603174603, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9913194444444444, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9915674603174603, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9918154761904762, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9915674603174603, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9918154761904762, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9915674603174603, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9913194444444444, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9905753968253969, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9908234126984127, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9913194444444444, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9913194444444444, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9923115079365079, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9918154761904762, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9913194444444444, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9905753968253969, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9913194444444444, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9910714285714286, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9905753968253969, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9910714285714286, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9878472222222222, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9890873015873016, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9888392857142857, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9900793650793651, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9895833333333334, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9908234126984127, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9851190476190477, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9885912698412699, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9866071428571429, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9856150793650794, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.8714816891741639, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.8936744686739269, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.910528188313426, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.9349066627809011, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.9593566611769168, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.9692747880293905, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.9767500561596572, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9816666327904964, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.982615395695555, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9841027213605155, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9841027213605155, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9860000756916502, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9869004293848102, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9878993492263781, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9877117931029504, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9880893304398577, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9889115446036107, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9897995239604308, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9896203501862709, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9898876291850495, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9901249184336718, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.989850841894536, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9902640794470395, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9894196752328106, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.988823576168361, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9880573224120839, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9881338466975441, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9888517051938434, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9891975823292735, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9896425837908784, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9889186866926368, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.988339354410851, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9895936442998728, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9879318284094898, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9905222183312178, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9894606644738682, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9893643029401576, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9888560940182656, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9894682955057587, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9864717693310887, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.988143651125024, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9871357665948091, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9875949293891559, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9877472239098333, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9903230750118934, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9844642109299623, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9876349090891575, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.98483190116684, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9853248259046088, "id_best": 29, "lr_best": 0.0006899999999999999, "wd_best": 0.05, "train/loss_best": 0.000564309572800994, "validation/loss_best": 0.026573309674859047, "validation/acc_best": 0.9923115079365079, "validation/f1_best": 0.9896425837908784} +{"epoch": 14, "train/lr": 8.9081919031238e-05, "train/loss": 0.07546807253733277, "train/grad": 0.041242266921326515, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.8271468734741211, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.7053953313827515, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.5265342426300049, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.37757999062538145, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.27072258591651915, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.1749463601410389, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.11418029211461544, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.08674339067190885, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.0720923119597137, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.06413835722953082, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.05906119492836297, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.053655274379998445, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.049604738540947435, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.04485988277941942, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.041060930090025066, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.0379062370955944, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.03427018630318344, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.030462377974763512, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.026594168059527874, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.023398374589160085, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.01968632448464632, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.01614942466840148, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.012440901948139071, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.008913586558774113, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.005804028445854783, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.003201460773125291, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.0019050930719822646, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0012727747205644846, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0007975258585065603, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0005111622717231513, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0003671485744416714, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.00027861911803483963, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.00021382934413850308, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.00015695453621447086, "train/loss_034_lr5.1e+00_wd1.0e+00": 8.038108237087726e-05, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.5331098586320878e-05, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.172740012407303e-05, "train/loss_037_lr8.3e+00_wd1.0e+00": 4.504742100834847e-06, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.946751192212105e-06, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.8475729525089266e-06, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.0006658436823636293, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.0004633698891848326, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.329554408788681e-06, "train/loss_043_lr2.2e+01_wd1.0e+00": 5.640089511871338e-07, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.00046983608976006505, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.002423047190532088, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.00016803301870822905, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.0013279915135353804, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.00023393887095153333, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.016000965032726525, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.015080886036157608, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.013723734891973436, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.012201692773960531, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.010632885172963142, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008720533619634808, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.006972240961622447, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.00618494936148636, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.005883489295374602, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.00575244703097269, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.005667188700754195, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.005553898821235634, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.00543560108228121, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.005272196241130587, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.0051096668333048, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.004964782949246, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.004769170725121512, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.0045394098326505625, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.004288206318888115, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.004051600107850391, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.003741389378410531, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.0034127173689194024, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0029877474838576746, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.002480288648221176, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0018915773338085272, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.001190558526359382, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0007427813327467447, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0005040110533263941, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.00031331662014508763, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.000199464310167059, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.00014524208107332014, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0001105330673044591, "train/grad_032_lr3.7e+00_wd1.0e+00": 8.324300801291428e-05, "train/grad_033_lr4.3e+00_wd1.0e+00": 6.348705396590048e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 3.9830028094769434e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 1.9833114329617098e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 1.3367989958351228e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 6.890708022577698e-06, "train/grad_038_lr9.8e+00_wd1.0e+00": 5.456531820467018e-06, "train/grad_039_lr1.2e+01_wd1.0e+00": 5.624203258542393e-06, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0001027289850487542, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0003218289509047096, "train/grad_042_lr1.9e+01_wd1.0e+00": 7.078084827648009e-06, "train/grad_043_lr2.2e+01_wd1.0e+00": 2.772860551651648e-06, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.00038521118431351307, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0012650230628167322, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0004695675499153725, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.001915900350749382, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0004324667061759936, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.8094784617424011, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.6876042485237122, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.5079231858253479, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.358964204788208, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.2531169354915619, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.158400297164917, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.09993728995323181, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.07394012063741684, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.05964691564440727, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.05196642875671387, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.047233130782842636, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.04239775985479355, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.039286572486162186, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.03618185594677925, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.034102436155080795, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.0325520895421505, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.031252700835466385, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.02986917831003666, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.028817206621170044, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.028001317754387856, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.0271419920027256, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.026408985257148743, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.025676283985376358, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.025019580498337746, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.024745531380176544, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.024862466380000114, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.024991195648908615, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.025405924767255783, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.02585633471608162, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.02648383192718029, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.026638658717274666, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.027376707643270493, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.02841106429696083, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.03260086476802826, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.03295503929257393, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.042814239859580994, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.052146390080451965, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.08770232647657394, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.09104850143194199, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.1698388010263443, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.17386505007743835, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.21268251538276672, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.16774605214595795, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.31912684440612793, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.4536929130554199, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.7579091191291809, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.6354343891143799, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.9958449602127075, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.8372960090637207, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.8936011904761905, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.9079861111111112, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.9236111111111112, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.9454365079365079, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9637896825396826, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.9734623015873016, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9801587301587301, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.9833829365079365, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.984375, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9858630952380952, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.986359126984127, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9878472222222222, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9893353174603174, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9895833333333334, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9900793650793651, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9903273809523809, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9898313492063492, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9900793650793651, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9905753968253969, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9903273809523809, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9905753968253969, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9898313492063492, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9903273809523809, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9920634920634921, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9918154761904762, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9915674603174603, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9915674603174603, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9918154761904762, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9918154761904762, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9918154761904762, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9918154761904762, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9918154761904762, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9905753968253969, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9913194444444444, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9913194444444444, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9903273809523809, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9910714285714286, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9878472222222222, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9888392857142857, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9875992063492064, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9900793650793651, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9905753968253969, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9905753968253969, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9888392857142857, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.988343253968254, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9868551587301587, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9873511904761905, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.8782069014616584, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.8963948489391989, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.9146893203939539, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.9408092856023709, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.9600585286262644, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.9703122083992779, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.9778388434069187, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.981350187208264, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.982166084028398, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9840573755036226, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9843838089122295, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9854578846261306, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9871716601844537, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9869930869117266, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9880378007570253, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9885965646782047, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9884086270087377, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9885448989214473, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9889946256738863, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9888232332276112, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.988955762850231, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9881996747654391, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9886052911864628, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9896849280988178, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9894449890302414, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9889428441630811, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9888864283717387, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9893796572395226, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9893796316507609, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9890637380299863, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9892885476336316, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9887990276902585, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9890532518001448, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9879318284094898, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9905222183312178, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9894606644738682, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9895440331903006, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9886302271932026, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9894682955057587, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9864717693310887, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9879695099130222, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9860711132661796, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9876534026109349, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9890135068200931, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9901913050824828, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9867719137755528, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9867255098161485, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9853673142086488, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9864395820405308, "id_best": 23, "lr_best": 0.00025499999999999996, "wd_best": 0.05, "train/loss_best": 0.008913586558774113, "validation/loss_best": 0.025019580498337746, "validation/acc_best": 0.9920634920634921, "validation/f1_best": 0.9896849280988178} +{"epoch": 15, "train/lr": 6.196799573888289e-05, "train/loss": 0.07031990582123399, "train/grad": 0.0382596430182457, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.7996567535400391, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.6771830368041992, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.49676992893218996, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.3499062025547028, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.24771342992782594, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.15696573302149772, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.10211572851985692, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.078303413502872, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.06520382695831359, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.057863301457837225, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.05314913942478597, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.04801614994183183, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.044214156549423934, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.03977027198299766, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.03620991440489888, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.03321322722360492, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.029932101015001534, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.026497811721637846, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.02307466679252684, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.02019659030251205, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.01690204952843487, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.013638852955773472, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.010282343486323953, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.007087963931262493, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.004503451371565461, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.002516420027241111, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.0015567031502723694, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0010638090316206217, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0006832543294876814, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.00044565778225660326, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.00031903021037578584, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.0002459745667874813, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.00018882672302424907, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.00013973258435726166, "train/loss_034_lr5.1e+00_wd1.0e+00": 7.096697576344014e-05, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.1220985800027848e-05, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.0906178504228592e-05, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.7556234747171404e-06, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.596043050289154e-06, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.9581615924835205e-06, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.5776773691177367e-05, "train/loss_041_lr1.6e+01_wd1.0e+00": 5.021225661039352e-07, "train/loss_042_lr1.9e+01_wd1.0e+00": 4.672175273299217e-06, "train/loss_043_lr2.2e+01_wd1.0e+00": 9.752158075571061e-07, "train/loss_044_lr2.6e+01_wd1.0e+00": 1.9581615924835205e-06, "train/loss_045_lr3.1e+01_wd1.0e+00": 5.291402339935302e-07, "train/loss_046_lr3.6e+01_wd1.0e+00": 7.354654371738434e-08, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.0, "train/loss_048_lr5.0e+01_wd1.0e+00": 9.062699973583222e-08, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.01569703159388155, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.014809200763702393, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.013447884325869382, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.011869012529496103, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.010267010182142258, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008348297942429781, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.006778698393609375, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.006137105543748475, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.005862239198759198, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.0057206848246278245, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.00562840195663739, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.005496125621721149, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.005368606153060682, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.005187829296046402, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.005022162506647874, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.00486437880404992, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.004677131233329419, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.004473280482343398, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.0042435949292848815, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.004026014433329692, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.0037185919130570256, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.003358659029472619, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.002888169877987821, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.002302187104069162, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0016753677922679345, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0010292958524041752, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0006530582505001803, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0004501078510656953, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.00028526245950160955, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.00018540143597874702, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.00013503158438652463, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.00010381593305055503, "train/grad_032_lr3.7e+00_wd1.0e+00": 7.886191718057489e-05, "train/grad_033_lr4.3e+00_wd1.0e+00": 6.0713828057714634e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 3.798626695868279e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 1.7553787532946787e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 1.355611438084381e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 5.941187157075548e-06, "train/grad_038_lr9.8e+00_wd1.0e+00": 4.513607654863477e-06, "train/grad_039_lr1.2e+01_wd1.0e+00": 4.912004579047584e-06, "train/grad_040_lr1.4e+01_wd1.0e+00": 9.468821211525827e-05, "train/grad_041_lr1.6e+01_wd1.0e+00": 2.1523617735264586e-06, "train/grad_042_lr1.9e+01_wd1.0e+00": 9.390859674501604e-06, "train/grad_043_lr2.2e+01_wd1.0e+00": 3.566645774298965e-06, "train/grad_044_lr2.6e+01_wd1.0e+00": 7.66393749879344e-06, "train/grad_045_lr3.1e+01_wd1.0e+00": 6.346737041440846e-06, "train/grad_046_lr3.6e+01_wd1.0e+00": 1.1730686813060322e-05, "train/grad_047_lr4.3e+01_wd1.0e+00": 9.672444115140873e-08, "train/grad_048_lr5.0e+01_wd1.0e+00": 9.495434349594543e-07, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.7908896207809448, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.6690374612808228, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.48914676904678345, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.3425288498401642, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.24030961096286774, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.1491967737674713, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.09493617713451385, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.0714232549071312, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.0583002008497715, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.0509992390871048, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.04644292965531349, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.04182024672627449, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.038730375468730927, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.035589322447776794, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.0334809273481369, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.03193635493516922, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.030345894396305084, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.028886383399367332, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.02758548967540264, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.02650752104818821, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.025571106001734734, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.02472906932234764, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.024115754291415215, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.023799585178494453, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.023752611130475998, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.02405359596014023, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.02444230578839779, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.02502504549920559, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.025712626054883003, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.026488780975341797, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.026701493188738823, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.02747396193444729, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.028409764170646667, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.03230913728475571, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.03245904669165611, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.04258392006158829, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.05139194801449776, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.08659368753433228, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.08990570902824402, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.1662680059671402, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.15741895139217377, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.20572902262210846, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.1614621877670288, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.30731266736984253, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.4403459131717682, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.7155886292457581, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.5969103574752808, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.942577600479126, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.7756367325782776, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.8948412698412699, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.908234126984127, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.9248511904761905, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.9489087301587301, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9660218253968254, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.9749503968253969, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9806547619047619, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.9841269841269841, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9851190476190477, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9861111111111112, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9861111111111112, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.988343253968254, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9900793650793651, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9903273809523809, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9900793650793651, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9905753968253969, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9910714285714286, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9913194444444444, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9915674603174603, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9915674603174603, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9918154761904762, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9918154761904762, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9915674603174603, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9918154761904762, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9913194444444444, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9918154761904762, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9913194444444444, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9915674603174603, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9913194444444444, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9915674603174603, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9918154761904762, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9918154761904762, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9915674603174603, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9908234126984127, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9910714285714286, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9913194444444444, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9905753968253969, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9910714285714286, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9878472222222222, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9890873015873016, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9875992063492064, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9900793650793651, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9908234126984127, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9910714285714286, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9888392857142857, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9885912698412699, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9868551587301587, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9878472222222222, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.8800765930616631, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.8971412592945134, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.9164994572280314, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.9448209199637899, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.9624008839453365, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.9718582966162869, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.9786486664388528, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9822500116636945, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.983108334941569, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9842817730635673, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9842047572091778, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9867120807516256, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9884345478438257, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9886135751433106, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9880756128319492, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9891382715369232, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9897141210775047, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9898931572752422, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9901175485317909, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9902182095192639, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9905839598632753, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9905839598632753, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9893719752058477, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9895513562592965, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9887831240574426, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9895844229608584, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9890219092063158, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9891998993868929, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9888360879741528, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9890612674852507, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9892860732722671, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9891175434749054, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.988873533611148, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.988285256482885, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9905222029706874, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.989190029856405, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9895440331903006, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9888099722518611, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9894682955057587, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9865188982498452, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9882752458639303, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9860711132661796, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9876534026109349, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9891933071631006, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9905499278866027, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9867719137755528, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9869045321133292, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9853673142086488, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9867987648269654, "id_best": 34, "lr_best": 0.0015299999999999997, "wd_best": 0.05, "train/loss_best": 7.096697576344014e-05, "validation/loss_best": 0.03245904669165611, "validation/acc_best": 0.9920634920634921, "validation/f1_best": 0.9905222029706874} +{"epoch": 16, "train/lr": 3.870405029380728e-05, "train/loss": 0.0697546773776412, "train/grad": 0.03785446299239993, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.7886191177368164, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.6665453100204468, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.48656177043914794, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.3419340169429779, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.24231243789196014, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.15397028416395186, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.10215657882392407, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.07995129764080047, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.06744688380509616, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.060313073713332416, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.055524288322776554, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.05028722738847136, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.04630415081046522, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.04163945145905018, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.03795271886512637, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.03489035000093281, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.03135035753250122, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.027588626248762012, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.0237630754429847, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.020540386848151685, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.016895509315654634, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.013456291705369949, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.009960660263895988, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.006761937430128455, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.004218746358528733, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.0023624007496982815, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.001477208249270916, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0010246056597679853, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0006692017428576946, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.00044599108397960665, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.00032620249316096307, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.00025447857566177843, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.00019472472369670867, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.00014453946612775326, "train/loss_034_lr5.1e+00_wd1.0e+00": 7.548193447291851e-05, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.2438550367951392e-05, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.2242831289768218e-05, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.8091279566287994e-06, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.5745201855897902e-06, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.1012389808893202e-06, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.251824527978897e-06, "train/loss_041_lr1.6e+01_wd1.0e+00": 6.654392927885055e-07, "train/loss_042_lr1.9e+01_wd1.0e+00": 5.914680659770966e-06, "train/loss_043_lr2.2e+01_wd1.0e+00": 1.7547234892845153e-06, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.1917355954647063e-06, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.093760460615158e-07, "train/loss_046_lr3.6e+01_wd1.0e+00": 5.780626088380814e-07, "train/loss_047_lr4.3e+01_wd1.0e+00": 5.094334483146667e-09, "train/loss_048_lr5.0e+01_wd1.0e+00": 5.2480027079582216e-08, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.015711809801869096, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.014814249305054546, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.013411816461011767, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.011801533987745643, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.010230687810108066, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008377132962923497, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.006851644191192463, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.006229810484219342, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.005936883416725322, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.00577036811679136, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.00563261876872275, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.00545326026796829, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.0052872105146525425, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.005064371643820778, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.004859644391981419, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.004677632347156759, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.004455726479936857, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.0041946140339132396, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.003921972727548564, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.003682949668436777, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.0033759604627266525, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.0030180870297772345, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.002554398871579906, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.002010463661426911, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0014376010518753902, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0008733391157147708, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0005630242728693702, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.00039489262702772975, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0002588025722889142, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.00016923628837957948, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0001245858276161016, "train/grad_031_lr3.1e+00_wd1.0e+00": 9.570558583845923e-05, "train/grad_032_lr3.7e+00_wd1.0e+00": 7.269165888374119e-05, "train/grad_033_lr4.3e+00_wd1.0e+00": 5.750465280385697e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 3.5548488312606705e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 1.842603895882533e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 1.2997494961826117e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 7.632969626348226e-06, "train/grad_038_lr9.8e+00_wd1.0e+00": 4.967057657645004e-06, "train/grad_039_lr1.2e+01_wd1.0e+00": 5.1902149716810264e-06, "train/grad_040_lr1.4e+01_wd1.0e+00": 4.954358474875276e-06, "train/grad_041_lr1.6e+01_wd1.0e+00": 2.3865541326231365e-06, "train/grad_042_lr1.9e+01_wd1.0e+00": 1.1601565661428488e-05, "train/grad_043_lr2.2e+01_wd1.0e+00": 3.4467896637585587e-06, "train/grad_044_lr2.6e+01_wd1.0e+00": 8.132999464883236e-06, "train/grad_045_lr3.1e+01_wd1.0e+00": 1.0577196925940942e-06, "train/grad_046_lr3.6e+01_wd1.0e+00": 1.9068057676893848e-06, "train/grad_047_lr4.3e+01_wd1.0e+00": 1.8916529982661063e-08, "train/grad_048_lr5.0e+01_wd1.0e+00": 2.8328522312553767e-07, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.7794039845466614, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.6574668884277344, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.4774734377861023, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.3325633704662323, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.232484832406044, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.1435030698776245, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.09200724214315414, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.06987771391868591, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.057375289499759674, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.05034441128373146, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.045909687876701355, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.041413262486457825, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.03836992010474205, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.0353749543428421, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.03336178511381149, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.03180837258696556, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.0303663220256567, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.02904132567346096, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.027927670627832413, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.026987049728631973, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.02606990933418274, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.025458835065364838, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.024920832365751266, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.02466457337141037, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.024791760370135307, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.02509850077331066, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.025322621688246727, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.025620432570576668, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.026241665706038475, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.02668432891368866, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.027014538645744324, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.027703292667865753, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.028619864955544472, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.03241283446550369, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.03246758505702019, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.0423755943775177, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.05114619806408882, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.08552096784114838, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.088826484978199, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.16360439360141754, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.15492713451385498, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.20073558390140533, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.15800802409648895, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.29872551560401917, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.4251314103603363, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.6908950805664062, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.5770214200019836, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.9098459482192993, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.7390255331993103, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.8973214285714286, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.9094742063492064, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.9250992063492064, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.9516369047619048, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9680059523809523, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.9756944444444444, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9806547619047619, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.9841269841269841, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9853670634920635, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9861111111111112, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9868551587301587, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9888392857142857, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9898313492063492, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9900793650793651, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9903273809523809, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9905753968253969, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9908234126984127, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9910714285714286, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9915674603174603, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9918154761904762, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9918154761904762, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9913194444444444, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9913194444444444, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9918154761904762, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9915674603174603, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9918154761904762, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9915674603174603, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9918154761904762, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9918154761904762, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9915674603174603, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9918154761904762, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9910714285714286, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9913194444444444, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9913194444444444, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9905753968253969, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9913194444444444, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9880952380952381, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9893353174603174, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9878472222222222, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9905753968253969, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9905753968253969, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9910714285714286, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9888392857142857, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9888392857142857, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9868551587301587, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9880952380952381, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.8832166698602746, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.8994396391324395, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.91752242940629, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.9476812782939762, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.9643007948204392, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.9725347157777231, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.9783332430407732, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9822519842833701, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9832890485224324, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9842817730635673, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9847418064750406, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9870700860127917, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9882541861046763, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9880756128319492, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9882559758505229, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9891382737205893, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.98953506256836, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9897158927978147, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9901283983077488, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9900304138022058, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9900294425628511, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9895802965710865, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9892555890877265, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9893642482228324, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9889885920246775, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9897094071706617, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9893806692642344, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9891999556833708, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9895569457791463, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9892409997491184, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9894658055361347, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9885734294286012, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9890532518001448, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.988464959318461, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9905222183312178, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9894606644738682, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9895440331903006, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9888099722518611, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9896466312763476, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9866982109754593, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9884545917978129, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9862501119267719, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9883840684440406, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9890133345214994, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9905499278866027, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9867719137755528, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9870847289326997, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9853673142086488, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9870216869097133, "id_best": 25, "lr_best": 0.00035999999999999997, "wd_best": 0.05, "train/loss_best": 0.0023624007496982815, "validation/loss_best": 0.02509850077331066, "validation/acc_best": 0.9920634920634921, "validation/f1_best": 0.9897094071706617} +{"epoch": 17, "train/lr": 2.030750443206766e-05, "train/loss": 0.0688353724218905, "train/grad": 0.036851740377023816, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.7804482173919678, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.65850350856781, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.47904349088668824, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.33587178587913513, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.23755949556827546, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.15010529935359954, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.09995909698307515, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.07856678832322359, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.06645178351551294, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.059414365785196425, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.05477254778146744, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.04961789201945067, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.04574558277614415, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.04130954585969448, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.037779435096308586, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.03478058862499893, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.03140999390743673, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.02788106326945126, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.0242076603602618, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.021026635812595486, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.017319065080955626, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.013724088547751307, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.01005662627518177, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.006666360870003701, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.004054622584953904, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.0022341217007488014, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.0013943234737962484, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0009725104831159115, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0006399642582982779, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0004208651278167963, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.00030711966566741465, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.0002388837467879057, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.00018394246697425842, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.0001378676388412714, "train/loss_034_lr5.1e+00_wd1.0e+00": 7.4704485014081e-05, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.1513551473617554e-05, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.1793551966547966e-05, "train/loss_037_lr8.3e+00_wd1.0e+00": 6.1426777392625805e-06, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.775166019797325e-06, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.5272462517023088e-06, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.2591650485992434e-06, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.0241474956274033e-06, "train/loss_042_lr1.9e+01_wd1.0e+00": 4.187282174825669e-06, "train/loss_043_lr2.2e+01_wd1.0e+00": 7.092393934726715e-07, "train/loss_044_lr2.6e+01_wd1.0e+00": 1.0716915130615235e-06, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.785399556159973e-07, "train/loss_046_lr3.6e+01_wd1.0e+00": 1.627206802368164e-07, "train/loss_047_lr4.3e+01_wd1.0e+00": 9.313225746154786e-11, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.9820948839187625e-08, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.015139517248608172, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.01427392997778952, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.012963715344667434, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.011448802193626761, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.00992108471924439, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008019284375477583, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.006579951932653785, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.006002187206177041, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.005736109737772495, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.0055984884069766845, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.005504756671725773, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.005373732100706547, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.005253410913865082, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.005079956664412748, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.0049158366397023204, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.004758481833850965, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.004561167698702775, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.004330534164619166, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.0040696878309245225, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.0038156827772036195, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.0034772749347030184, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.0030815640421496936, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0025876960408641025, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0020111195854042307, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0013985895117002655, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0008460923434722645, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0005493514591762505, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.00038610558848631624, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.00025493106112662645, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.00016878210941285944, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.00012540972428269016, "train/grad_031_lr3.1e+00_wd1.0e+00": 9.652279628426186e-05, "train/grad_032_lr3.7e+00_wd1.0e+00": 7.43623580365238e-05, "train/grad_033_lr4.3e+00_wd1.0e+00": 5.829323212310555e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 3.7605051772402476e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 1.775275899713602e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 1.2519036847539536e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 6.522503771985293e-06, "train/grad_038_lr9.8e+00_wd1.0e+00": 4.773433622851258e-06, "train/grad_039_lr1.2e+01_wd1.0e+00": 4.680354902582333e-06, "train/grad_040_lr1.4e+01_wd1.0e+00": 3.963056756989644e-06, "train/grad_041_lr1.6e+01_wd1.0e+00": 2.2011624762566697e-06, "train/grad_042_lr1.9e+01_wd1.0e+00": 1.155756627244817e-05, "train/grad_043_lr2.2e+01_wd1.0e+00": 4.229586888887091e-06, "train/grad_044_lr2.6e+01_wd1.0e+00": 4.873590696629038e-06, "train/grad_045_lr3.1e+01_wd1.0e+00": 1.0023350863119336e-06, "train/grad_046_lr3.6e+01_wd1.0e+00": 6.651277309681997e-06, "train/grad_047_lr4.3e+01_wd1.0e+00": 2.0417746645520093e-08, "train/grad_048_lr5.0e+01_wd1.0e+00": 3.578143228612207e-07, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.7733875513076782, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.6513552069664001, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.4714645445346832, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.32750779390335083, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.22850927710533142, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.14066791534423828, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.09057119488716125, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.06918397545814514, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.05693048611283302, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.0500202551484108, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.04572884365916252, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.041257232427597046, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.0382310226559639, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.03526521846652031, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.03315172344446182, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.03169630467891693, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.03029784932732582, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.028934825211763382, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.02776842936873436, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.02682899683713913, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.02585880644619465, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.025109335780143738, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.024529365822672844, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.024263035506010056, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.024474652484059334, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.024773916229605675, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.02508436143398285, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.02560085989534855, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.02608475647866726, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.02682526595890522, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.026976721361279488, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.027576861903071404, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.028601018711924553, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.03246312215924263, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.03255899250507355, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.042264074087142944, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.050882987678050995, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.08534204959869385, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.0883711576461792, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.16309066116809845, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.1539536565542221, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.19999876618385315, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.15647514164447784, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.2948865294456482, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.41972967982292175, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.6749634742736816, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.5650193691253662, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.8914619088172913, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.7191146612167358, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.8970734126984127, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.9107142857142857, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.9283234126984127, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.9521329365079365, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9672619047619048, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.9759424603174603, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9811507936507936, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.9838789682539683, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9848710317460317, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9861111111111112, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9871031746031746, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9888392857142857, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9900793650793651, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9898313492063492, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9903273809523809, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9900793650793651, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9905753968253969, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9913194444444444, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9910714285714286, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9915674603174603, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9918154761904762, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9913194444444444, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9913194444444444, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9920634920634921, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9915674603174603, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9915674603174603, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9915674603174603, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9915674603174603, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9918154761904762, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9915674603174603, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9915674603174603, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9908234126984127, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9915674603174603, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9913194444444444, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9905753968253969, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9913194444444444, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9878472222222222, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9893353174603174, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9880952380952381, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9900793650793651, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9905753968253969, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9910714285714286, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9888392857142857, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9890873015873016, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9868551587301587, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9880952380952381, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.8827765325230859, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.9006840912147589, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.9212957449491355, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.948288710515085, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.9636598890690602, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.9723536886072934, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.979104924835358, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9820690829077964, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9829275835013741, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9842363906485755, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9849207599954614, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9870682623551271, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.988433191653946, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9878952293425849, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9886322503343385, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9884078581931061, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.988990827411534, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9895298746548459, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.989082115822238, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9894861786453798, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9900294425628511, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9893058793702805, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9891785042043124, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9897300131578705, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9888622256439297, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9888864283717387, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.989201298482583, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9891998993868929, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9895569457791463, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9890612674852507, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9894658055361347, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9885734294286012, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9895974345477173, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.988285256482885, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9905222029706874, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9896407371802075, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9895440331903006, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9888099722518611, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9896466312763476, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9865621086278467, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9884545917978129, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9864740962061689, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9876534026109349, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9890133345214994, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9905499278866027, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9867719137755528, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9872637231379547, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9853673142086488, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9870216869097133, "id_best": 23, "lr_best": 0.00025499999999999996, "wd_best": 0.05, "train/loss_best": 0.006666360870003701, "validation/loss_best": 0.024263035506010056, "validation/acc_best": 0.9920634920634921, "validation/f1_best": 0.9897300131578705} +{"epoch": 18, "train/lr": 7.5829098008590064e-06, "train/loss": 0.06646024856716394, "train/grad": 0.03691962170414627, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.7671766662597657, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.6462540340423584, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.46842519283294676, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.3268061923980713, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.2298569732904434, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.14364886909723282, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.09482250150293112, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.07412800310179592, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.06220693170093, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.05532631862908602, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.05074063556268811, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.04579985905438662, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.042135511757805943, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.03786173261702061, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.03450023414567113, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.03164993947371841, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.028462592819705604, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.02511737962253392, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.02169580779969692, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.01870648850686848, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.015293354354798793, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.01203632310964167, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.008732762979343533, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.005774350399151445, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.0035307137761265038, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.0019656565878540277, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.0012321170791983603, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0008593402616679668, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0005626662820577621, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0003704941924661398, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.00027307656593620775, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.00021003889851272105, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.0001585131511092186, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.00012172242626547814, "train/loss_034_lr5.1e+00_wd1.0e+00": 5.938502959907055e-05, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.931527629494667e-05, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.134626567363739e-05, "train/loss_037_lr8.3e+00_wd1.0e+00": 5.937991663813591e-06, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.4719612449407575e-06, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.4303717762231826e-06, "train/loss_040_lr1.4e+01_wd1.0e+00": 4.93563711643219e-07, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.2934394180774688e-06, "train/loss_042_lr1.9e+01_wd1.0e+00": 4.688277840614319e-06, "train/loss_043_lr2.2e+01_wd1.0e+00": 5.690101534128189e-07, "train/loss_044_lr2.6e+01_wd1.0e+00": 1.0893773287534714e-06, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.715977072715759e-08, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.0443461835384368e-07, "train/loss_047_lr4.3e+01_wd1.0e+00": 9.313225746154785e-12, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.7939677238464354e-11, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.015403007781133056, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.01451771215070039, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.013134988681413233, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.011542448452673852, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.009987872960045933, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008054774310439826, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.006542144919512794, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.005962350926129147, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.005707241014461033, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.005567229127627797, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.0054572428279789165, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.0053029765409883115, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.005178434351983015, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.004983266705530696, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.004813183087098878, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.004638586103974376, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.004434169045416638, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.00420056165457936, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.003937761843844783, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.0036829651618609204, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.0033350679733848664, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.0029401679231523302, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0024304090451187223, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.001855601921924972, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.001282966848630167, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0007704465319693554, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0004996695085628744, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0003533295108718448, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.00023413857269133587, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0001556554674561994, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.00011672319618810434, "train/grad_031_lr3.1e+00_wd1.0e+00": 9.032259384866848e-05, "train/grad_032_lr3.7e+00_wd1.0e+00": 6.981228953009122e-05, "train/grad_033_lr4.3e+00_wd1.0e+00": 5.437598000867183e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 3.356146886630995e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 1.6309983574913643e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 1.2497130979702842e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 6.696687464810919e-06, "train/grad_038_lr9.8e+00_wd1.0e+00": 5.577299097502743e-06, "train/grad_039_lr1.2e+01_wd1.0e+00": 3.975062541568874e-06, "train/grad_040_lr1.4e+01_wd1.0e+00": 2.9376714944062743e-06, "train/grad_041_lr1.6e+01_wd1.0e+00": 2.495552535662692e-06, "train/grad_042_lr1.9e+01_wd1.0e+00": 1.0915266673956017e-05, "train/grad_043_lr2.2e+01_wd1.0e+00": 3.3215353744373346e-06, "train/grad_044_lr2.6e+01_wd1.0e+00": 4.0835213884256095e-06, "train/grad_045_lr3.1e+01_wd1.0e+00": 1.0806918277426937e-06, "train/grad_046_lr3.6e+01_wd1.0e+00": 1.695602476412801e-06, "train/grad_047_lr4.3e+01_wd1.0e+00": 4.6735699808336924e-08, "train/grad_048_lr5.0e+01_wd1.0e+00": 3.2040383659237834e-07, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.7710426449775696, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.6490727663040161, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.46916264295578003, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.3255779445171356, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.2269735336303711, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.1395084708929062, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.08996088802814484, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.06891074776649475, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.056745145469903946, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.049884893000125885, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.04557633772492409, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.041096098721027374, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.03817968815565109, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.035152267664670944, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.03319892659783363, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.03169160708785057, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.030268918722867966, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.02889988198876381, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.02766362391412258, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.026821734383702278, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.02579582668840885, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.02518213726580143, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.024608273059129715, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.024411343038082123, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.024528054520487785, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.02495017647743225, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.025228144600987434, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.025659503415226936, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.026162365451455116, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.026782669126987457, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.026935240253806114, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.027622228488326073, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.028574874624609947, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.032483600080013275, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.032587602734565735, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.04219047352671623, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.05075189098715782, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.08519227057695389, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.08819616585969925, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.16264231503009796, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.15365110337734222, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.19838203489780426, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.1558404117822647, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.29415163397789, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.4173322916030884, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.6713178157806396, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.5610054731369019, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.884009838104248, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.7138333916664124, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.8980654761904762, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.9112103174603174, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.9278273809523809, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.9523809523809523, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9675099206349206, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.9764384920634921, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9813988095238095, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.984375, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9848710317460317, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9861111111111112, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9871031746031746, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9888392857142857, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9900793650793651, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9900793650793651, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9900793650793651, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9900793650793651, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9905753968253969, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9910714285714286, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9915674603174603, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9915674603174603, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9915674603174603, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9913194444444444, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9910714285714286, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9915674603174603, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9913194444444444, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9915674603174603, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9915674603174603, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9915674603174603, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9918154761904762, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9915674603174603, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9908234126984127, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9915674603174603, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9913194444444444, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9905753968253969, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9913194444444444, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9878472222222222, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9893353174603174, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9878472222222222, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9903273809523809, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9905753968253969, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9913194444444444, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9888392857142857, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9890873015873016, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9868551587301587, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9880952380952381, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.8843173078880068, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.9008649248591044, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.9204080405721139, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.9485614298303486, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.9639299844646616, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.9733273070615199, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.9792865729113083, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9824308896385555, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9826136594003132, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9842817730635673, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9849207599954614, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9867139250140726, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.988433191653946, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9880756128319492, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9880880151775125, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9880439860548539, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.988990827411534, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9893507804809917, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9894753384307987, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9894861786453798, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9894852074060251, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9893058793702805, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9886342690474864, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9888200130660064, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9883180428963572, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9888392274593765, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.989201298482583, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9891999556833708, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9895569457791463, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9894658055361347, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9894658055361347, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9885734294286012, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9895974345477173, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.988285256482885, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9905222183312178, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9896407371802075, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9895440331903006, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9888099722518611, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9896466312763476, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9863771378941839, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9884545917978129, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9862945796124695, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9882043296731786, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9890133345214994, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.990773932333247, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9867719137755528, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9872637231379547, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9853673142086488, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9870216869097133, "id_best": 29, "lr_best": 0.0006899999999999999, "wd_best": 0.05, "train/loss_best": 0.0003704941924661398, "validation/loss_best": 0.026782669126987457, "validation/acc_best": 0.9920634920634921, "validation/f1_best": 0.9894658055361347} +{"epoch": 19, "train/lr": 1.0867618231465446e-06, "train/loss": 0.0664803858846426, "train/grad": 0.036554265711456535, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.7691228580474854, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.6474486827850342, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.4686204218864441, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.32643784761428835, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.22926862061023712, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.14341976329684258, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.09497549254447221, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.07445927001535893, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.06271194056607783, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.05586139878258109, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.05129793616011739, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.0462403516471386, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.04241223787888884, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.03791311836801469, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.03431438746862114, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.031278400951996445, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.027937944969162343, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.02447498810477555, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.021057256124913694, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.01812153834849596, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.014838808476924896, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.011716417651623488, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.008546492671594024, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.005685950955376029, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.003474411368370056, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.001944587817415595, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.0012257603462785482, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0008603724371641874, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0005708806030452251, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.00038066619075834753, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0002805626578629017, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.0002189354319125414, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.00016901595517992973, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.00013164976611733435, "train/loss_034_lr5.1e+00_wd1.0e+00": 6.919215433299541e-05, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.8580006435513497e-05, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.1918200179934501e-05, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.298224717378616e-06, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.3035874366760252e-06, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.832915633916855e-06, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.7908494919538499e-06, "train/loss_041_lr1.6e+01_wd1.0e+00": 7.370207458734512e-07, "train/loss_042_lr1.9e+01_wd1.0e+00": 5.267858505249023e-06, "train/loss_043_lr2.2e+01_wd1.0e+00": 1.7965678125619888e-06, "train/loss_044_lr2.6e+01_wd1.0e+00": 1.5075504779815674e-06, "train/loss_045_lr3.1e+01_wd1.0e+00": 1.3814307749271394e-07, "train/loss_046_lr3.6e+01_wd1.0e+00": 6.368663161993027e-07, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.548339009284973e-09, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.635883331298828e-08, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.015137041290290653, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.014248023619875311, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.012886407524347306, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.011336158658377827, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.009798605325631798, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.007925670139957219, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.006526380854193121, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.005991091445321217, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.0057487170328386124, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.005615745457471348, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.005508699734928086, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.005357863507815637, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.005218245832948014, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.005016827863873914, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.004830915751226712, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.004655026788532269, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.004435371479776223, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.004184221324248938, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.003913334178359946, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.0036546657899452837, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.0033052485658117805, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.0029118890943937003, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.002413413639005739, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0018434253374289256, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0012632371939980658, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0007628468440452707, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0004943564932455047, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.00035176864450932045, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.00023338388369211315, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.00015527883336744709, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.00011534254224670803, "train/grad_031_lr3.1e+00_wd1.0e+00": 8.91521266566997e-05, "train/grad_032_lr3.7e+00_wd1.0e+00": 6.816942806608494e-05, "train/grad_033_lr4.3e+00_wd1.0e+00": 5.369194629793128e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 3.5303478067021385e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 1.699277912898367e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 1.2105287750842075e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 6.048018232446713e-06, "train/grad_038_lr9.8e+00_wd1.0e+00": 5.652187869745149e-06, "train/grad_039_lr1.2e+01_wd1.0e+00": 3.969667508837379e-06, "train/grad_040_lr1.4e+01_wd1.0e+00": 2.9609082379124557e-06, "train/grad_041_lr1.6e+01_wd1.0e+00": 2.0508132260680077e-06, "train/grad_042_lr1.9e+01_wd1.0e+00": 1.0065243282875532e-05, "train/grad_043_lr2.2e+01_wd1.0e+00": 4.101972599232201e-06, "train/grad_044_lr2.6e+01_wd1.0e+00": 4.798129324050358e-06, "train/grad_045_lr3.1e+01_wd1.0e+00": 7.452944710479289e-07, "train/grad_046_lr3.6e+01_wd1.0e+00": 2.7471211889320968e-06, "train/grad_047_lr4.3e+01_wd1.0e+00": 1.58581292953522e-08, "train/grad_048_lr5.0e+01_wd1.0e+00": 2.3405682227398546e-07, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.7706839442253113, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.648738443851471, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.46886885166168213, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.3252515494823456, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.2268320471048355, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.13937903940677643, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.08988510817289352, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.06887318193912506, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.056737493723630905, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.04987131431698799, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.04556649178266525, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.04110291227698326, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.03815128654241562, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.035116467624902725, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.03317802771925926, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.0317096970975399, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.030204882845282555, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.02892216481268406, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.027656786143779755, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.026817528530955315, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.025819744914770126, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.025159569457173347, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.024575715884566307, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.02440723404288292, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.02456624060869217, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.024899980053305626, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.025211049243807793, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.025690047070384026, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.026205999776721, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.026755208149552345, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.02696203999221325, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.027682412415742874, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.02863769419491291, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.03250867873430252, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.03262145072221756, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.04220598563551903, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.05077435448765755, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.085175059735775, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.08816699683666229, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.16274838149547577, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.15361417829990387, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.19813191890716553, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.15549777448177338, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.2941870391368866, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.4170188903808594, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.6707132458686829, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.5604243278503418, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.881187915802002, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.7131558656692505, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.8988095238095238, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.9107142857142857, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.9278273809523809, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.9523809523809523, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9672619047619048, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.9764384920634921, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9813988095238095, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.984375, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9848710317460317, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9861111111111112, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9871031746031746, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9885912698412699, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9900793650793651, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9900793650793651, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9900793650793651, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9900793650793651, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9905753968253969, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9910714285714286, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9915674603174603, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9915674603174603, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9915674603174603, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9913194444444444, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9910714285714286, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9913194444444444, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9915674603174603, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9913194444444444, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9915674603174603, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9915674603174603, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9918154761904762, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9915674603174603, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9918154761904762, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9908234126984127, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9915674603174603, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9913194444444444, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9905753968253969, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9913194444444444, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9875992063492064, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9893353174603174, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9880952380952381, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9903273809523809, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9905753968253969, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9913194444444444, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9888392857142857, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9890873015873016, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9868551587301587, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9880952380952381, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.8851112462036786, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.9003183457850867, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.9204080405721139, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.9486512131286436, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.9636576112810127, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.9736022509350798, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.9792865729113083, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9824308896385555, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9826136594003132, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9842817730635673, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9849207599954614, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9865349560966126, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.988433191653946, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9880756128319492, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9880880151775125, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9880439860548539, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.988990827411534, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9893507804809917, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9894753384307987, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9894861786453798, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9894852074060251, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9893058793702805, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9886342690474864, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9886406850302615, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9886688309820719, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9886598847456992, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.989201298482583, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9891999556833708, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9895569457791463, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9894658055361347, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9894658055361347, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9885734294286012, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9890532518001448, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.988285256482885, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9905222029706874, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9896407371802075, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9895440331903006, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9888099722518611, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9896466312763476, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9861978174050081, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9884545917978129, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9864740962061689, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9882043296731786, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9890133345214994, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.990773932333247, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9867719137755528, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9872637231379547, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9853673142086488, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9870216869097133, "id_best": 29, "lr_best": 0.0006899999999999999, "wd_best": 0.05, "train/loss_best": 0.00038066619075834753, "validation/loss_best": 0.026755208149552345, "validation/acc_best": 0.9920634920634921, "validation/f1_best": 0.9894658055361347} diff --git a/input_space_v3/flat_lr1e-3_1/eval_v2/nsd_cococlip__patch__attn/config.yaml b/input_space_v3/flat_lr1e-3_1/eval_v2/nsd_cococlip__patch__attn/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..de42a8db40e835ec5abf8fbc2062c51696ca9b84 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_1/eval_v2/nsd_cococlip__patch__attn/config.yaml @@ -0,0 +1,96 @@ +output_root: experiments/input_space_v3/output +name_prefix: eval_probe +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_1; eval v2 (nsd_cococlip patch attn) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +dataset_kwargs: {} +classifier_kwargs: + embed_dim: null + dropout: 0.0 + xavier_init: true + norm: true +lr_scale_grid: +- 0.02 +- 0.023 +- 0.028 +- 0.033 +- 0.038 +- 0.045 +- 0.053 +- 0.062 +- 0.074 +- 0.087 +- 0.1 +- 0.12 +- 0.14 +- 0.17 +- 0.2 +- 0.23 +- 0.27 +- 0.32 +- 0.38 +- 0.44 +- 0.52 +- 0.61 +- 0.72 +- 0.85 +- 1 +- 1.2 +- 1.4 +- 1.6 +- 1.9 +- 2.3 +- 2.7 +- 3.1 +- 3.7 +- 4.3 +- 5.1 +- 6 +- 7.1 +- 8.3 +- 9.8 +- 12 +- 14 +- 16 +- 19 +- 22 +- 26 +- 31 +- 36 +- 43 +- 50 +wd_scale_grid: +- 1.0 +num_workers: 8 +prefetch_factor: null +balanced_sampling: false +epochs: 20 +steps_per_epoch: 200 +batch_size: 64 +accum_iter: 2 +lr: 0.0003 +warmup_epochs: 5 +no_decay: false +weight_decay: 0.05 +clip_grad: 1.0 +metrics: +- acc +- f1 +cv_metric: acc +early_stopping: true +amp: true +device: cuda +seed: 4466 +debug: false +wandb: false +wandb_entity: null +wandb_project: fMRI-fm-eval +name: input_space_v3/flat_lr1e-3_1/eval_v2/nsd_cococlip__patch__attn +model: flat_mae +representation: patch +classifier: attn +dataset: nsd_cococlip +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/nsd_cococlip__patch__attn +remote_dir: null diff --git a/input_space_v3/flat_lr1e-3_1/eval_v2/nsd_cococlip__patch__attn/eval_log.json b/input_space_v3/flat_lr1e-3_1/eval_v2/nsd_cococlip__patch__attn/eval_log.json new file mode 100644 index 0000000000000000000000000000000000000000..a9f97d8a54fab15020a1f8c186e450b243861306 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_1/eval_v2/nsd_cococlip__patch__attn/eval_log.json @@ -0,0 +1 @@ +{"eval/epoch": 5, "eval/id_best": 25, "eval/lr_best": 0.00035999999999999997, "eval/wd_best": 0.05, "eval/train/loss": 2.0998287200927734, "eval/train/acc": 0.36270321767724883, "eval/train/acc_std": 0.0022714047755210804, "eval/train/f1": 0.29767350355874467, "eval/train/f1_std": 0.002460141564741038, "eval/validation/loss": 2.3558778762817383, "eval/validation/acc": 0.290328534514581, "eval/validation/acc_std": 0.005529181629477793, "eval/validation/f1": 0.22030143677357192, "eval/validation/f1_std": 0.005243067074592791, "eval/test/loss": 2.2803070545196533, "eval/test/acc": 0.3057513914656772, "eval/test/acc_std": 0.0054496469491390614, "eval/test/f1": 0.23490195569136108, "eval/test/f1_std": 0.005192870077843104, "eval/testid/loss": 2.3014211654663086, "eval/testid/acc": 0.29959514170040485, "eval/testid/acc_std": 0.005505681827001186, "eval/testid/f1": 0.23657613292046645, "eval/testid/f1_std": 0.005149382365278941} diff --git a/input_space_v3/flat_lr1e-3_1/eval_v2/nsd_cococlip__patch__attn/eval_log_best.json b/input_space_v3/flat_lr1e-3_1/eval_v2/nsd_cococlip__patch__attn/eval_log_best.json new file mode 100644 index 0000000000000000000000000000000000000000..595f0f5407a776f016d664770ba79e2cd0cdfcbb --- /dev/null +++ b/input_space_v3/flat_lr1e-3_1/eval_v2/nsd_cococlip__patch__attn/eval_log_best.json @@ -0,0 +1 @@ +{"eval/best/epoch": 5, "eval/best/id_best": 25, "eval/best/lr_best": 0.00035999999999999997, "eval/best/wd_best": 0.05, "eval/best/train/loss": 2.0998287200927734, "eval/best/train/acc": 0.36270321767724883, "eval/best/train/acc_std": 0.0022714047755210804, "eval/best/train/f1": 0.29767350355874467, "eval/best/train/f1_std": 0.002460141564741038, "eval/best/validation/loss": 2.3558778762817383, "eval/best/validation/acc": 0.290328534514581, "eval/best/validation/acc_std": 0.005529181629477793, "eval/best/validation/f1": 0.22030143677357192, "eval/best/validation/f1_std": 0.005243067074592791, "eval/best/test/loss": 2.2803070545196533, "eval/best/test/acc": 0.3057513914656772, "eval/best/test/acc_std": 0.0054496469491390614, "eval/best/test/f1": 0.23490195569136108, "eval/best/test/f1_std": 0.005192870077843104, "eval/best/testid/loss": 2.3014211654663086, "eval/best/testid/acc": 0.29959514170040485, "eval/best/testid/acc_std": 0.005505681827001186, "eval/best/testid/f1": 0.23657613292046645, "eval/best/testid/f1_std": 0.005149382365278941} diff --git a/input_space_v3/flat_lr1e-3_1/eval_v2/nsd_cococlip__patch__attn/eval_log_last.json b/input_space_v3/flat_lr1e-3_1/eval_v2/nsd_cococlip__patch__attn/eval_log_last.json new file mode 100644 index 0000000000000000000000000000000000000000..520839b4e14084fc18294ee74e22ce7545acd2ee --- /dev/null +++ b/input_space_v3/flat_lr1e-3_1/eval_v2/nsd_cococlip__patch__attn/eval_log_last.json @@ -0,0 +1 @@ +{"eval/last/epoch": 19, "eval/last/id_best": 18, "eval/last/lr_best": 0.00011399999999999999, "eval/last/wd_best": 0.05, "eval/last/train/loss": 2.0616867542266846, "eval/last/train/acc": 0.379267955376625, "eval/last/train/acc_std": 0.002376399811294904, "eval/last/train/f1": 0.32109350214137533, "eval/last/train/f1_std": 0.0025465955686408944, "eval/last/validation/loss": 2.3812315464019775, "eval/last/validation/acc": 0.2851605758582503, "eval/last/validation/acc_std": 0.005368994923606133, "eval/last/validation/f1": 0.22485967984522437, "eval/last/validation/f1_std": 0.005189941709734747, "eval/last/test/loss": 2.265471935272217, "eval/last/test/acc": 0.3092764378478664, "eval/last/test/acc_std": 0.0055326397318310894, "eval/last/test/f1": 0.2400697155868646, "eval/last/test/f1_std": 0.0055795276941791256, "eval/last/testid/loss": 2.271428346633911, "eval/last/testid/acc": 0.3051860420281473, "eval/last/testid/acc_std": 0.00562020757108842, "eval/last/testid/f1": 0.24529111299439962, "eval/last/testid/f1_std": 0.005587048858616305} diff --git a/input_space_v3/flat_lr1e-3_1/eval_v2/nsd_cococlip__patch__attn/eval_table.csv b/input_space_v3/flat_lr1e-3_1/eval_v2/nsd_cococlip__patch__attn/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..915fdedc641f68f2b19930eb431b82f12f5fa692 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_1/eval_v2/nsd_cococlip__patch__attn/eval_table.csv @@ -0,0 +1,5 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,patch,attn,nsd_cococlip,best,5,0.00035999999999999997,0.05,25,"[1.2, 1.0]",train,2.0998287200927734,0.36270321767724883,0.0022714047755210804,0.29767350355874467,0.002460141564741038 +flat_mae,patch,attn,nsd_cococlip,best,5,0.00035999999999999997,0.05,25,"[1.2, 1.0]",validation,2.3558778762817383,0.290328534514581,0.005529181629477793,0.22030143677357192,0.005243067074592791 +flat_mae,patch,attn,nsd_cococlip,best,5,0.00035999999999999997,0.05,25,"[1.2, 1.0]",test,2.2803070545196533,0.3057513914656772,0.0054496469491390614,0.23490195569136108,0.005192870077843104 +flat_mae,patch,attn,nsd_cococlip,best,5,0.00035999999999999997,0.05,25,"[1.2, 1.0]",testid,2.3014211654663086,0.29959514170040485,0.005505681827001186,0.23657613292046645,0.005149382365278941 diff --git a/input_space_v3/flat_lr1e-3_1/eval_v2/nsd_cococlip__patch__attn/eval_table_best.csv b/input_space_v3/flat_lr1e-3_1/eval_v2/nsd_cococlip__patch__attn/eval_table_best.csv new file mode 100644 index 0000000000000000000000000000000000000000..915fdedc641f68f2b19930eb431b82f12f5fa692 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_1/eval_v2/nsd_cococlip__patch__attn/eval_table_best.csv @@ -0,0 +1,5 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,patch,attn,nsd_cococlip,best,5,0.00035999999999999997,0.05,25,"[1.2, 1.0]",train,2.0998287200927734,0.36270321767724883,0.0022714047755210804,0.29767350355874467,0.002460141564741038 +flat_mae,patch,attn,nsd_cococlip,best,5,0.00035999999999999997,0.05,25,"[1.2, 1.0]",validation,2.3558778762817383,0.290328534514581,0.005529181629477793,0.22030143677357192,0.005243067074592791 +flat_mae,patch,attn,nsd_cococlip,best,5,0.00035999999999999997,0.05,25,"[1.2, 1.0]",test,2.2803070545196533,0.3057513914656772,0.0054496469491390614,0.23490195569136108,0.005192870077843104 +flat_mae,patch,attn,nsd_cococlip,best,5,0.00035999999999999997,0.05,25,"[1.2, 1.0]",testid,2.3014211654663086,0.29959514170040485,0.005505681827001186,0.23657613292046645,0.005149382365278941 diff --git a/input_space_v3/flat_lr1e-3_1/eval_v2/nsd_cococlip__patch__attn/eval_table_last.csv b/input_space_v3/flat_lr1e-3_1/eval_v2/nsd_cococlip__patch__attn/eval_table_last.csv new file mode 100644 index 0000000000000000000000000000000000000000..205982206a117d89bf6aebfe3111f7fab222af30 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_1/eval_v2/nsd_cococlip__patch__attn/eval_table_last.csv @@ -0,0 +1,5 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,patch,attn,nsd_cococlip,last,19,0.00011399999999999999,0.05,18,"[0.38, 1.0]",train,2.0616867542266846,0.379267955376625,0.002376399811294904,0.32109350214137533,0.0025465955686408944 +flat_mae,patch,attn,nsd_cococlip,last,19,0.00011399999999999999,0.05,18,"[0.38, 1.0]",validation,2.3812315464019775,0.2851605758582503,0.005368994923606133,0.22485967984522437,0.005189941709734747 +flat_mae,patch,attn,nsd_cococlip,last,19,0.00011399999999999999,0.05,18,"[0.38, 1.0]",test,2.265471935272217,0.3092764378478664,0.0055326397318310894,0.2400697155868646,0.0055795276941791256 +flat_mae,patch,attn,nsd_cococlip,last,19,0.00011399999999999999,0.05,18,"[0.38, 1.0]",testid,2.271428346633911,0.3051860420281473,0.00562020757108842,0.24529111299439962,0.005587048858616305 diff --git a/input_space_v3/flat_lr1e-3_1/eval_v2/nsd_cococlip__patch__attn/log.txt b/input_space_v3/flat_lr1e-3_1/eval_v2/nsd_cococlip__patch__attn/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..757bad07b3277fd13d58603439a0f6fbdb33d676 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_1/eval_v2/nsd_cococlip__patch__attn/log.txt @@ -0,0 +1,963 @@ +fMRI foundation model probe eval +version: 0.1.dev86+gf97f52698 +sha: bcce2b486277d3a5b520775efd9cdf1a2affce36, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-04-08 20:31:09 +config: +output_root: experiments/input_space_v3/output +name_prefix: eval_probe +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_1; eval v2 (nsd_cococlip patch attn) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +dataset_kwargs: {} +classifier_kwargs: + embed_dim: null + dropout: 0.0 + xavier_init: true + norm: true +lr_scale_grid: +- 0.02 +- 0.023 +- 0.028 +- 0.033 +- 0.038 +- 0.045 +- 0.053 +- 0.062 +- 0.074 +- 0.087 +- 0.1 +- 0.12 +- 0.14 +- 0.17 +- 0.2 +- 0.23 +- 0.27 +- 0.32 +- 0.38 +- 0.44 +- 0.52 +- 0.61 +- 0.72 +- 0.85 +- 1 +- 1.2 +- 1.4 +- 1.6 +- 1.9 +- 2.3 +- 2.7 +- 3.1 +- 3.7 +- 4.3 +- 5.1 +- 6 +- 7.1 +- 8.3 +- 9.8 +- 12 +- 14 +- 16 +- 19 +- 22 +- 26 +- 31 +- 36 +- 43 +- 50 +wd_scale_grid: +- 1.0 +num_workers: 8 +prefetch_factor: null +balanced_sampling: false +epochs: 20 +steps_per_epoch: 200 +batch_size: 64 +accum_iter: 2 +lr: 0.0003 +warmup_epochs: 5 +no_decay: false +weight_decay: 0.05 +clip_grad: 1.0 +metrics: +- acc +- f1 +cv_metric: acc +early_stopping: true +amp: true +device: cuda +seed: 4466 +debug: false +wandb: false +wandb_entity: null +wandb_project: fMRI-fm-eval +name: input_space_v3/flat_lr1e-3_1/eval_v2/nsd_cococlip__patch__attn +model: flat_mae +representation: patch +classifier: attn +dataset: nsd_cococlip +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/nsd_cococlip__patch__attn +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=True, reg_tokens=0, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: nsd_cococlip (flat) +train (n=32539): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'run', 'trial_id', 'nsd_id', 'category_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 32539 +}), + labels=[ 3 4 5 6 10 11 17 18 19 20 22 23 25 30 31 33 36 37 38 53 55 59 61 74], + counts=[1286 1180 1639 1868 834 824 1026 1042 913 1853 1503 2092 1001 1410 + 794 1241 1904 1872 2267 1428 889 904 1447 1322] +) + +validation (n=5418): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'run', 'trial_id', 'nsd_id', 'category_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 5418 +}), + labels=[ 3 4 5 6 10 11 17 18 19 20 22 23 25 30 31 33 36 37 38 53 55 59 61 74], + counts=[197 161 276 345 126 142 143 185 112 295 285 387 169 250 159 193 316 334 + 343 215 172 141 226 246] +) + +test (n=5390): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'run', 'trial_id', 'nsd_id', 'category_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 5390 +}), + labels=[ 3 4 5 6 10 11 17 18 19 20 22 23 25 30 31 33 36 37 38 53 55 59 61 74], + counts=[202 172 274 298 144 180 134 182 186 293 218 343 165 185 140 177 346 333 + 345 271 165 140 251 246] +) + +testid (n=5187): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'run', 'trial_id', 'nsd_id', 'category_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 5187 +}), + labels=[ 3 4 5 6 10 11 17 18 19 20 22 23 25 30 31 33 36 37 38 53 55 59 61 74], + counts=[197 159 267 273 123 153 175 184 139 310 215 386 153 230 118 192 330 306 + 349 223 143 127 249 186] +) + +running backbone on example batch to get embedding dim +embedding feature dim (patch): 768 +initializing sweep of classifier heads +classifiers: +ModuleList( + (0-48): 49 x AttnPoolClassifier( + (kv): Linear(in_features=768, out_features=1536, bias=True) + (linear): Linear(in_features=768, out_features=24, bias=True) + ) +) +classifier params (train): 58.8M (58.8M) +setting up optimizer +total batch size: 128 = 64 bs per gpu x 2 accum +lr: 3.00e-04 +full schedule: epochs = 20 (steps = 4000) (decay = True) +warmup: epochs = 5 (steps = 1000) +start training for 20 epochs +train: [0] [ 0/400] eta: 0:30:25 lr: nan time: 4.5629 data: 4.0176 max mem: 21740 +train: [0] [ 20/400] eta: 0:03:55 lr: 0.000003 loss: 3.1974 (3.1957) grad: 0.1924 (0.1895) time: 0.4231 data: 0.0041 max mem: 22448 +train: [0] [ 40/400] eta: 0:03:04 lr: 0.000006 loss: 3.1927 (3.1911) grad: 0.1883 (0.1894) time: 0.3981 data: 0.0034 max mem: 22448 +train: [0] [ 60/400] eta: 0:02:47 lr: 0.000009 loss: 3.1806 (3.1877) grad: 0.1797 (0.1869) time: 0.4570 data: 0.0043 max mem: 22448 +train: [0] [ 80/400] eta: 0:02:34 lr: 0.000012 loss: 3.1690 (3.1817) grad: 0.1772 (0.1842) time: 0.4458 data: 0.0041 max mem: 22448 +train: [0] [100/400] eta: 0:02:22 lr: 0.000015 loss: 3.1637 (3.1811) grad: 0.1694 (0.1818) time: 0.4549 data: 0.0041 max mem: 22448 +train: [0] [120/400] eta: 0:02:11 lr: 0.000018 loss: 3.1765 (3.1786) grad: 0.1623 (0.1787) time: 0.4443 data: 0.0042 max mem: 22448 +train: [0] [140/400] eta: 0:02:01 lr: 0.000021 loss: 3.1574 (3.1765) grad: 0.1663 (0.1781) time: 0.4451 data: 0.0041 max mem: 22448 +train: [0] [160/400] eta: 0:01:51 lr: 0.000024 loss: 3.1559 (3.1725) grad: 0.1794 (0.1787) time: 0.4408 data: 0.0042 max mem: 22448 +train: [0] [180/400] eta: 0:01:41 lr: 0.000027 loss: 3.1406 (3.1700) grad: 0.1718 (0.1780) time: 0.4470 data: 0.0043 max mem: 22448 +train: [0] [200/400] eta: 0:01:32 lr: 0.000030 loss: 3.1551 (3.1696) grad: 0.1621 (0.1762) time: 0.4730 data: 0.0042 max mem: 22448 +train: [0] [220/400] eta: 0:01:23 lr: 0.000033 loss: 3.1569 (3.1683) grad: 0.1621 (0.1750) time: 0.4540 data: 0.0041 max mem: 22448 +train: [0] [240/400] eta: 0:01:13 lr: 0.000036 loss: 3.1497 (3.1667) grad: 0.1643 (0.1742) time: 0.4501 data: 0.0041 max mem: 22448 +train: [0] [260/400] eta: 0:01:04 lr: 0.000039 loss: 3.1359 (3.1640) grad: 0.1597 (0.1730) time: 0.4481 data: 0.0041 max mem: 22448 +train: [0] [280/400] eta: 0:00:55 lr: 0.000042 loss: 3.1259 (3.1607) grad: 0.1594 (0.1723) time: 0.4433 data: 0.0042 max mem: 22448 +train: [0] [300/400] eta: 0:00:45 lr: 0.000045 loss: 3.1038 (3.1561) grad: 0.1617 (0.1719) time: 0.4392 data: 0.0041 max mem: 22448 +train: [0] [320/400] eta: 0:00:36 lr: 0.000048 loss: 3.0939 (3.1526) grad: 0.1689 (0.1722) time: 0.4476 data: 0.0042 max mem: 22448 +train: [0] [340/400] eta: 0:00:27 lr: 0.000051 loss: 3.1021 (3.1494) grad: 0.1707 (0.1720) time: 0.4473 data: 0.0042 max mem: 22448 +train: [0] [360/400] eta: 0:00:18 lr: 0.000054 loss: 3.0848 (3.1455) grad: 0.1702 (0.1726) time: 0.4516 data: 0.0040 max mem: 22448 +train: [0] [380/400] eta: 0:00:09 lr: 0.000057 loss: 3.0745 (3.1419) grad: 0.1839 (0.1731) time: 0.4563 data: 0.0041 max mem: 22448 +train: [0] [399/400] eta: 0:00:00 lr: 0.000060 loss: 3.0757 (3.1393) grad: 0.1891 (0.1736) time: 0.4601 data: 0.0040 max mem: 22448 +train: [0] Total time: 0:03:02 (0.4569 s / it) +train: [0] Summary: lr: 0.000060 loss: 3.0757 (3.1393) grad: 0.1891 (0.1736) +eval (validation): [0] [ 0/85] eta: 0:04:34 time: 3.2351 data: 2.9948 max mem: 22448 +eval (validation): [0] [20/85] eta: 0:00:32 time: 0.3653 data: 0.0068 max mem: 22448 +eval (validation): [0] [40/85] eta: 0:00:19 time: 0.3465 data: 0.0033 max mem: 22448 +eval (validation): [0] [60/85] eta: 0:00:09 time: 0.3411 data: 0.0043 max mem: 22448 +eval (validation): [0] [80/85] eta: 0:00:01 time: 0.3417 data: 0.0043 max mem: 22448 +eval (validation): [0] [84/85] eta: 0:00:00 time: 0.3307 data: 0.0042 max mem: 22448 +eval (validation): [0] Total time: 0:00:32 (0.3846 s / it) +cv: [0] best hparam: (31, 1.0) (045) ('045_lr3.1e+01_wd1.0e+00') loss: 2.555 acc: 0.236 f1: 0.158 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/nsd_cococlip__patch__attn/checkpoint-best.pth +train: [1] [ 0/400] eta: 0:24:01 lr: nan time: 3.6034 data: 3.2132 max mem: 22448 +train: [1] [ 20/400] eta: 0:03:57 lr: 0.000063 loss: 3.0218 (3.0304) grad: 0.1771 (0.1772) time: 0.4758 data: 0.0028 max mem: 22448 +train: [1] [ 40/400] eta: 0:03:14 lr: 0.000066 loss: 3.0381 (3.0295) grad: 0.1728 (0.1728) time: 0.4520 data: 0.0040 max mem: 22448 +train: [1] [ 60/400] eta: 0:02:55 lr: 0.000069 loss: 3.0083 (3.0171) grad: 0.1694 (0.1734) time: 0.4635 data: 0.0042 max mem: 22448 +train: [1] [ 80/400] eta: 0:02:38 lr: 0.000072 loss: 3.0080 (3.0182) grad: 0.1796 (0.1762) time: 0.4361 data: 0.0040 max mem: 22448 +train: [1] [100/400] eta: 0:02:27 lr: 0.000075 loss: 3.0000 (3.0123) grad: 0.1815 (0.1784) time: 0.4756 data: 0.0044 max mem: 22448 +train: [1] [120/400] eta: 0:02:16 lr: 0.000078 loss: 2.9988 (3.0107) grad: 0.1857 (0.1797) time: 0.4564 data: 0.0043 max mem: 22448 +train: [1] [140/400] eta: 0:02:05 lr: 0.000081 loss: 2.9998 (3.0094) grad: 0.1857 (0.1812) time: 0.4520 data: 0.0039 max mem: 22448 +train: [1] [160/400] eta: 0:01:54 lr: 0.000084 loss: 2.9908 (3.0092) grad: 0.1844 (0.1812) time: 0.4372 data: 0.0039 max mem: 22448 +train: [1] [180/400] eta: 0:01:44 lr: 0.000087 loss: 3.0068 (3.0091) grad: 0.1812 (0.1820) time: 0.4506 data: 0.0041 max mem: 22448 +train: [1] [200/400] eta: 0:01:34 lr: 0.000090 loss: 2.9841 (3.0063) grad: 0.1821 (0.1827) time: 0.4485 data: 0.0040 max mem: 22448 +train: [1] [220/400] eta: 0:01:24 lr: 0.000093 loss: 2.9428 (2.9985) grad: 0.1987 (0.1848) time: 0.4395 data: 0.0040 max mem: 22448 +train: [1] [240/400] eta: 0:01:14 lr: 0.000096 loss: 2.9360 (2.9952) grad: 0.1987 (0.1849) time: 0.4467 data: 0.0042 max mem: 22448 +train: [1] [260/400] eta: 0:01:04 lr: 0.000099 loss: 2.9606 (2.9940) grad: 0.1896 (0.1858) time: 0.4435 data: 0.0040 max mem: 22448 +train: [1] [280/400] eta: 0:00:55 lr: 0.000102 loss: 2.9569 (2.9905) grad: 0.1871 (0.1859) time: 0.4431 data: 0.0042 max mem: 22448 +train: [1] [300/400] eta: 0:00:46 lr: 0.000105 loss: 2.9389 (2.9891) grad: 0.1862 (0.1863) time: 0.4482 data: 0.0042 max mem: 22448 +train: [1] [320/400] eta: 0:00:36 lr: 0.000108 loss: 2.9168 (2.9840) grad: 0.1926 (0.1869) time: 0.4347 data: 0.0040 max mem: 22448 +train: [1] [340/400] eta: 0:00:27 lr: 0.000111 loss: 2.9040 (2.9797) grad: 0.1963 (0.1876) time: 0.4402 data: 0.0039 max mem: 22448 +train: [1] [360/400] eta: 0:00:18 lr: 0.000114 loss: 2.9096 (2.9778) grad: 0.1945 (0.1880) time: 0.4415 data: 0.0040 max mem: 22448 +train: [1] [380/400] eta: 0:00:09 lr: 0.000117 loss: 2.9097 (2.9744) grad: 0.1956 (0.1891) time: 0.4435 data: 0.0042 max mem: 22448 +train: [1] [399/400] eta: 0:00:00 lr: 0.000120 loss: 2.9097 (2.9727) grad: 0.2100 (0.1905) time: 0.4389 data: 0.0041 max mem: 22448 +train: [1] Total time: 0:03:02 (0.4566 s / it) +train: [1] Summary: lr: 0.000120 loss: 2.9097 (2.9727) grad: 0.2100 (0.1905) +eval (validation): [1] [ 0/85] eta: 0:04:27 time: 3.1421 data: 2.9121 max mem: 22448 +eval (validation): [1] [20/85] eta: 0:00:31 time: 0.3503 data: 0.0052 max mem: 22448 +eval (validation): [1] [40/85] eta: 0:00:18 time: 0.3216 data: 0.0036 max mem: 22448 +eval (validation): [1] [60/85] eta: 0:00:09 time: 0.3265 data: 0.0041 max mem: 22448 +eval (validation): [1] [80/85] eta: 0:00:01 time: 0.3434 data: 0.0041 max mem: 22448 +eval (validation): [1] [84/85] eta: 0:00:00 time: 0.3363 data: 0.0040 max mem: 22448 +eval (validation): [1] Total time: 0:00:31 (0.3709 s / it) +cv: [1] best hparam: (14, 1.0) (040) ('040_lr1.4e+01_wd1.0e+00') loss: 2.472 acc: 0.255 f1: 0.184 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/nsd_cococlip__patch__attn/checkpoint-best.pth +train: [2] [ 0/400] eta: 0:22:35 lr: nan time: 3.3877 data: 2.9891 max mem: 22448 +train: [2] [ 20/400] eta: 0:03:53 lr: 0.000123 loss: 2.9387 (2.9364) grad: 0.2688 (0.2770) time: 0.4760 data: 0.0046 max mem: 22448 +train: [2] [ 40/400] eta: 0:03:10 lr: 0.000126 loss: 2.9790 (2.9763) grad: 0.3094 (0.3627) time: 0.4422 data: 0.0040 max mem: 22448 +train: [2] [ 60/400] eta: 0:02:52 lr: 0.000129 loss: 3.1040 (3.1286) grad: 0.6774 (0.6115) time: 0.4635 data: 0.0043 max mem: 22448 +WARNING: classifier 48 (50, 1.0) diverged (loss=71.13 > 63.56) at step 438. Freezing. +train: [2] [ 80/400] eta: 0:02:37 lr: 0.000132 loss: 3.5589 (3.2836) grad: 1.1607 (0.8041) time: 0.4363 data: 0.0041 max mem: 22448 +train: [2] [100/400] eta: 0:02:25 lr: 0.000135 loss: 2.9410 (3.1979) grad: 0.2188 (0.6844) time: 0.4640 data: 0.0045 max mem: 22448 +train: [2] [120/400] eta: 0:02:14 lr: 0.000138 loss: 2.8566 (3.1426) grad: 0.2105 (0.6061) time: 0.4517 data: 0.0044 max mem: 22448 +train: [2] [140/400] eta: 0:02:03 lr: 0.000141 loss: 2.8790 (3.1094) grad: 0.2153 (0.5517) time: 0.4400 data: 0.0044 max mem: 22448 +train: [2] [160/400] eta: 0:01:52 lr: 0.000144 loss: 2.8790 (3.0788) grad: 0.2233 (0.5111) time: 0.4378 data: 0.0041 max mem: 22448 +train: [2] [180/400] eta: 0:01:42 lr: 0.000147 loss: 2.8366 (3.0519) grad: 0.2207 (0.4789) time: 0.4502 data: 0.0042 max mem: 22448 +train: [2] [200/400] eta: 0:01:32 lr: 0.000150 loss: 2.8412 (3.0309) grad: 0.2171 (0.4526) time: 0.4390 data: 0.0041 max mem: 22448 +train: [2] [220/400] eta: 0:01:23 lr: 0.000153 loss: 2.8596 (3.0176) grad: 0.2233 (0.4341) time: 0.4369 data: 0.0038 max mem: 22448 +train: [2] [240/400] eta: 0:01:13 lr: 0.000156 loss: 2.9593 (3.0240) grad: 0.3331 (0.4576) time: 0.4465 data: 0.0041 max mem: 22448 +WARNING: classifier 47 (43, 1.0) diverged (loss=89.97 > 63.56) at step 525. Freezing. +train: [2] [260/400] eta: 0:01:04 lr: 0.000159 loss: 2.9796 (3.0461) grad: 0.6004 (0.4945) time: 0.4419 data: 0.0040 max mem: 22448 +train: [2] [280/400] eta: 0:00:54 lr: 0.000162 loss: 2.8884 (3.0317) grad: 0.2366 (0.4762) time: 0.4389 data: 0.0042 max mem: 22448 +train: [2] [300/400] eta: 0:00:45 lr: 0.000165 loss: 2.8278 (3.0193) grad: 0.2348 (0.4597) time: 0.4410 data: 0.0043 max mem: 22448 +train: [2] [320/400] eta: 0:00:36 lr: 0.000168 loss: 2.8192 (3.0073) grad: 0.2147 (0.4442) time: 0.4434 data: 0.0039 max mem: 22448 +train: [2] [340/400] eta: 0:00:27 lr: 0.000171 loss: 2.8220 (2.9987) grad: 0.2144 (0.4312) time: 0.4450 data: 0.0042 max mem: 22448 +train: [2] [360/400] eta: 0:00:18 lr: 0.000174 loss: 2.8273 (2.9915) grad: 0.2255 (0.4209) time: 0.4393 data: 0.0039 max mem: 22448 +train: [2] [380/400] eta: 0:00:09 lr: 0.000177 loss: 2.9206 (2.9917) grad: 0.3090 (0.4255) time: 0.4442 data: 0.0041 max mem: 22448 +WARNING: classifier 46 (36, 1.0) diverged (loss=65.82 > 63.56) at step 595. Freezing. +train: [2] [399/400] eta: 0:00:00 lr: 0.000180 loss: 2.9703 (3.0024) grad: 0.4133 (0.4415) time: 0.4349 data: 0.0039 max mem: 22448 +train: [2] Total time: 0:03:01 (0.4533 s / it) +train: [2] Summary: lr: 0.000180 loss: 2.9703 (3.0024) grad: 0.4133 (0.4415) +eval (validation): [2] [ 0/85] eta: 0:04:32 time: 3.2061 data: 2.9259 max mem: 22448 +eval (validation): [2] [20/85] eta: 0:00:31 time: 0.3436 data: 0.0034 max mem: 22448 +eval (validation): [2] [40/85] eta: 0:00:18 time: 0.3338 data: 0.0035 max mem: 22448 +eval (validation): [2] [60/85] eta: 0:00:09 time: 0.3322 data: 0.0039 max mem: 22448 +eval (validation): [2] [80/85] eta: 0:00:01 time: 0.3276 data: 0.0037 max mem: 22448 +eval (validation): [2] [84/85] eta: 0:00:00 time: 0.3153 data: 0.0036 max mem: 22448 +eval (validation): [2] Total time: 0:00:31 (0.3693 s / it) +cv: [2] best hparam: (2.7, 1.0) (030) ('030_lr2.7e+00_wd1.0e+00') loss: 2.433 acc: 0.267 f1: 0.189 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/nsd_cococlip__patch__attn/checkpoint-best.pth +train: [3] [ 0/400] eta: 0:22:35 lr: nan time: 3.3884 data: 3.0557 max mem: 22448 +train: [3] [ 20/400] eta: 0:03:45 lr: 0.000183 loss: 2.7842 (2.8061) grad: 0.2140 (0.2148) time: 0.4528 data: 0.0031 max mem: 22448 +train: [3] [ 40/400] eta: 0:03:05 lr: 0.000186 loss: 2.8140 (2.8292) grad: 0.2205 (0.2221) time: 0.4368 data: 0.0041 max mem: 22448 +train: [3] [ 60/400] eta: 0:02:48 lr: 0.000189 loss: 2.8217 (2.8234) grad: 0.2260 (0.2227) time: 0.4500 data: 0.0042 max mem: 22448 +train: [3] [ 80/400] eta: 0:02:33 lr: 0.000192 loss: 2.8203 (2.8227) grad: 0.2185 (0.2206) time: 0.4367 data: 0.0039 max mem: 22448 +train: [3] [100/400] eta: 0:02:22 lr: 0.000195 loss: 2.7906 (2.8164) grad: 0.2118 (0.2192) time: 0.4613 data: 0.0041 max mem: 22448 +train: [3] [120/400] eta: 0:02:12 lr: 0.000198 loss: 2.7856 (2.8128) grad: 0.2159 (0.2194) time: 0.4494 data: 0.0040 max mem: 22448 +train: [3] [140/400] eta: 0:02:01 lr: 0.000201 loss: 2.7983 (2.8124) grad: 0.2232 (0.2214) time: 0.4495 data: 0.0043 max mem: 22448 +train: [3] [160/400] eta: 0:01:51 lr: 0.000204 loss: 2.8147 (2.8157) grad: 0.2348 (0.2224) time: 0.4314 data: 0.0040 max mem: 22448 +train: [3] [180/400] eta: 0:01:41 lr: 0.000207 loss: 2.7968 (2.8128) grad: 0.2278 (0.2230) time: 0.4573 data: 0.0042 max mem: 22448 +train: [3] [200/400] eta: 0:01:32 lr: 0.000210 loss: 2.7875 (2.8128) grad: 0.2283 (0.2238) time: 0.4399 data: 0.0042 max mem: 22448 +train: [3] [220/400] eta: 0:01:22 lr: 0.000213 loss: 2.8026 (2.8123) grad: 0.2378 (0.2250) time: 0.4291 data: 0.0041 max mem: 22448 +train: [3] [240/400] eta: 0:01:13 lr: 0.000216 loss: 2.7980 (2.8103) grad: 0.2381 (0.2266) time: 0.4344 data: 0.0040 max mem: 22448 +train: [3] [260/400] eta: 0:01:03 lr: 0.000219 loss: 2.8017 (2.8111) grad: 0.2461 (0.2301) time: 0.4304 data: 0.0040 max mem: 22448 +train: [3] [280/400] eta: 0:00:54 lr: 0.000222 loss: 2.8377 (2.8212) grad: 0.3023 (0.2545) time: 0.4393 data: 0.0040 max mem: 22448 +train: [3] [300/400] eta: 0:00:45 lr: 0.000225 loss: 3.2676 (2.8902) grad: 0.9114 (0.3434) time: 0.4319 data: 0.0041 max mem: 22448 +WARNING: classifier 45 (31, 1.0) diverged (loss=73.41 > 63.56) at step 752. Freezing. +WARNING: classifier 44 (26, 1.0) diverged (loss=65.56 > 63.56) at step 757. Freezing. +train: [3] [320/400] eta: 0:00:36 lr: 0.000228 loss: 3.6470 (2.9429) grad: 1.4599 (0.4033) time: 0.4333 data: 0.0042 max mem: 22448 +train: [3] [340/400] eta: 0:00:26 lr: 0.000231 loss: 2.8273 (2.9353) grad: 0.2478 (0.3938) time: 0.4289 data: 0.0041 max mem: 22448 +train: [3] [360/400] eta: 0:00:17 lr: 0.000234 loss: 2.8273 (2.9316) grad: 0.2351 (0.3851) time: 0.4275 data: 0.0039 max mem: 22448 +train: [3] [380/400] eta: 0:00:08 lr: 0.000237 loss: 2.8437 (2.9273) grad: 0.2500 (0.3848) time: 0.4281 data: 0.0040 max mem: 22448 +train: [3] [399/400] eta: 0:00:00 lr: 0.000240 loss: 2.9357 (2.9406) grad: 0.5717 (0.4166) time: 0.4307 data: 0.0041 max mem: 22448 +train: [3] Total time: 0:02:58 (0.4466 s / it) +train: [3] Summary: lr: 0.000240 loss: 2.9357 (2.9406) grad: 0.5717 (0.4166) +eval (validation): [3] [ 0/85] eta: 0:04:31 time: 3.1972 data: 2.9182 max mem: 22448 +eval (validation): [3] [20/85] eta: 0:00:31 time: 0.3514 data: 0.0047 max mem: 22448 +eval (validation): [3] [40/85] eta: 0:00:18 time: 0.3278 data: 0.0036 max mem: 22448 +eval (validation): [3] [60/85] eta: 0:00:09 time: 0.3314 data: 0.0041 max mem: 22448 +eval (validation): [3] [80/85] eta: 0:00:01 time: 0.3368 data: 0.0040 max mem: 22448 +eval (validation): [3] [84/85] eta: 0:00:00 time: 0.3298 data: 0.0039 max mem: 22448 +eval (validation): [3] Total time: 0:00:31 (0.3728 s / it) +cv: [3] best hparam: (4.3, 1.0) (033) ('033_lr4.3e+00_wd1.0e+00') loss: 2.437 acc: 0.269 f1: 0.187 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/nsd_cococlip__patch__attn/checkpoint-best.pth +train: [4] [ 0/400] eta: 0:22:16 lr: nan time: 3.3408 data: 3.0141 max mem: 22448 +train: [4] [ 20/400] eta: 0:03:45 lr: 0.000243 loss: 3.6855 (3.6602) grad: 1.4620 (1.5265) time: 0.4560 data: 0.0029 max mem: 22448 +WARNING: classifier 43 (22, 1.0) diverged (loss=74.00 > 63.56) at step 816. Freezing. +train: [4] [ 40/400] eta: 0:03:05 lr: 0.000246 loss: 3.6855 (3.5431) grad: 1.3886 (1.2699) time: 0.4314 data: 0.0040 max mem: 22448 +train: [4] [ 60/400] eta: 0:02:47 lr: 0.000249 loss: 2.8264 (3.2899) grad: 0.2097 (0.9167) time: 0.4458 data: 0.0042 max mem: 22448 +train: [4] [ 80/400] eta: 0:02:32 lr: 0.000252 loss: 2.7539 (3.1598) grad: 0.2023 (0.7379) time: 0.4270 data: 0.0039 max mem: 22448 +train: [4] [100/400] eta: 0:02:21 lr: 0.000255 loss: 2.7906 (3.0922) grad: 0.2041 (0.6331) time: 0.4475 data: 0.0041 max mem: 22448 +train: [4] [120/400] eta: 0:02:10 lr: 0.000258 loss: 2.7945 (3.0363) grad: 0.2113 (0.5636) time: 0.4491 data: 0.0042 max mem: 22448 +train: [4] [140/400] eta: 0:01:59 lr: 0.000261 loss: 2.7438 (2.9959) grad: 0.2150 (0.5156) time: 0.4290 data: 0.0042 max mem: 22448 +train: [4] [160/400] eta: 0:01:49 lr: 0.000264 loss: 2.7673 (2.9689) grad: 0.2319 (0.4798) time: 0.4238 data: 0.0039 max mem: 22448 +train: [4] [180/400] eta: 0:01:40 lr: 0.000267 loss: 2.7692 (2.9492) grad: 0.2319 (0.4523) time: 0.4421 data: 0.0039 max mem: 22448 +train: [4] [200/400] eta: 0:01:30 lr: 0.000270 loss: 2.7456 (2.9273) grad: 0.2255 (0.4290) time: 0.4283 data: 0.0040 max mem: 22448 +train: [4] [220/400] eta: 0:01:21 lr: 0.000273 loss: 2.7456 (2.9151) grad: 0.2294 (0.4114) time: 0.4325 data: 0.0041 max mem: 22448 +train: [4] [240/400] eta: 0:01:11 lr: 0.000276 loss: 2.7720 (2.9037) grad: 0.2294 (0.3961) time: 0.4347 data: 0.0040 max mem: 22448 +train: [4] [260/400] eta: 0:01:02 lr: 0.000279 loss: 2.7855 (2.8946) grad: 0.2223 (0.3832) time: 0.4340 data: 0.0040 max mem: 22448 +train: [4] [280/400] eta: 0:00:53 lr: 0.000282 loss: 2.7855 (2.8872) grad: 0.2258 (0.3726) time: 0.4331 data: 0.0040 max mem: 22448 +train: [4] [300/400] eta: 0:00:44 lr: 0.000285 loss: 2.7814 (2.8798) grad: 0.2280 (0.3628) time: 0.4341 data: 0.0041 max mem: 22448 +train: [4] [320/400] eta: 0:00:35 lr: 0.000288 loss: 2.7706 (2.8722) grad: 0.2139 (0.3532) time: 0.4425 data: 0.0040 max mem: 22448 +train: [4] [340/400] eta: 0:00:26 lr: 0.000291 loss: 2.7615 (2.8664) grad: 0.2130 (0.3455) time: 0.4347 data: 0.0040 max mem: 22448 +train: [4] [360/400] eta: 0:00:17 lr: 0.000294 loss: 2.7615 (2.8618) grad: 0.2272 (0.3390) time: 0.4335 data: 0.0040 max mem: 22448 +train: [4] [380/400] eta: 0:00:08 lr: 0.000297 loss: 2.7670 (2.8568) grad: 0.2316 (0.3334) time: 0.4358 data: 0.0040 max mem: 22448 +train: [4] [399/400] eta: 0:00:00 lr: 0.000300 loss: 2.7629 (2.8507) grad: 0.2268 (0.3281) time: 0.4260 data: 0.0039 max mem: 22448 +train: [4] Total time: 0:02:57 (0.4436 s / it) +train: [4] Summary: lr: 0.000300 loss: 2.7629 (2.8507) grad: 0.2268 (0.3281) +eval (validation): [4] [ 0/85] eta: 0:04:37 time: 3.2601 data: 3.0321 max mem: 22448 +eval (validation): [4] [20/85] eta: 0:00:31 time: 0.3531 data: 0.0038 max mem: 22448 +eval (validation): [4] [40/85] eta: 0:00:18 time: 0.3225 data: 0.0036 max mem: 22448 +eval (validation): [4] [60/85] eta: 0:00:09 time: 0.3307 data: 0.0042 max mem: 22448 +eval (validation): [4] [80/85] eta: 0:00:01 time: 0.3453 data: 0.0041 max mem: 22448 +eval (validation): [4] [84/85] eta: 0:00:00 time: 0.3329 data: 0.0040 max mem: 22448 +eval (validation): [4] Total time: 0:00:31 (0.3741 s / it) +cv: [4] best hparam: (1.9, 1.0) (028) ('028_lr1.9e+00_wd1.0e+00') loss: 2.428 acc: 0.275 f1: 0.220 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/nsd_cococlip__patch__attn/checkpoint-best.pth +train: [5] [ 0/400] eta: 0:22:42 lr: nan time: 3.4064 data: 3.0750 max mem: 22448 +train: [5] [ 20/400] eta: 0:03:46 lr: 0.000300 loss: 2.6751 (2.6728) grad: 0.2416 (0.2407) time: 0.4548 data: 0.0034 max mem: 22448 +train: [5] [ 40/400] eta: 0:03:06 lr: 0.000300 loss: 2.6928 (2.7090) grad: 0.2359 (0.2402) time: 0.4358 data: 0.0041 max mem: 22448 +train: [5] [ 60/400] eta: 0:02:48 lr: 0.000300 loss: 2.7436 (2.7170) grad: 0.2359 (0.2407) time: 0.4509 data: 0.0047 max mem: 22448 +train: [5] [ 80/400] eta: 0:02:34 lr: 0.000300 loss: 2.7363 (2.7089) grad: 0.2339 (0.2381) time: 0.4373 data: 0.0041 max mem: 22448 +train: [5] [100/400] eta: 0:02:22 lr: 0.000300 loss: 2.7313 (2.7165) grad: 0.2349 (0.2408) time: 0.4541 data: 0.0043 max mem: 22448 +train: [5] [120/400] eta: 0:02:11 lr: 0.000300 loss: 2.6905 (2.7084) grad: 0.2402 (0.2392) time: 0.4485 data: 0.0044 max mem: 22448 +train: [5] [140/400] eta: 0:02:01 lr: 0.000300 loss: 2.6643 (2.7032) grad: 0.2246 (0.2368) time: 0.4494 data: 0.0044 max mem: 22448 +train: [5] [160/400] eta: 0:01:51 lr: 0.000299 loss: 2.6773 (2.7015) grad: 0.2226 (0.2363) time: 0.4308 data: 0.0042 max mem: 22448 +train: [5] [180/400] eta: 0:01:41 lr: 0.000299 loss: 2.7019 (2.7041) grad: 0.2317 (0.2358) time: 0.4388 data: 0.0042 max mem: 22448 +train: [5] [200/400] eta: 0:01:31 lr: 0.000299 loss: 2.7025 (2.7034) grad: 0.2324 (0.2358) time: 0.4339 data: 0.0042 max mem: 22448 +train: [5] [220/400] eta: 0:01:21 lr: 0.000299 loss: 2.6687 (2.7016) grad: 0.2327 (0.2350) time: 0.4260 data: 0.0040 max mem: 22448 +train: [5] [240/400] eta: 0:01:12 lr: 0.000299 loss: 2.6734 (2.7008) grad: 0.2294 (0.2345) time: 0.4309 data: 0.0039 max mem: 22448 +train: [5] [260/400] eta: 0:01:03 lr: 0.000299 loss: 2.6570 (2.6968) grad: 0.2239 (0.2339) time: 0.4416 data: 0.0042 max mem: 22448 +train: [5] [280/400] eta: 0:00:54 lr: 0.000298 loss: 2.6566 (2.6981) grad: 0.2312 (0.2342) time: 0.4438 data: 0.0044 max mem: 22448 +train: [5] [300/400] eta: 0:00:45 lr: 0.000298 loss: 2.6566 (2.6941) grad: 0.2312 (0.2338) time: 0.4329 data: 0.0043 max mem: 22448 +train: [5] [320/400] eta: 0:00:35 lr: 0.000298 loss: 2.6597 (2.6938) grad: 0.2339 (0.2341) time: 0.4308 data: 0.0041 max mem: 22448 +train: [5] [340/400] eta: 0:00:26 lr: 0.000298 loss: 2.6725 (2.6917) grad: 0.2384 (0.2341) time: 0.4330 data: 0.0040 max mem: 22448 +train: [5] [360/400] eta: 0:00:17 lr: 0.000297 loss: 2.6712 (2.6920) grad: 0.2350 (0.2343) time: 0.4372 data: 0.0040 max mem: 22448 +train: [5] [380/400] eta: 0:00:08 lr: 0.000297 loss: 2.6691 (2.6921) grad: 0.2350 (0.2344) time: 0.4385 data: 0.0041 max mem: 22448 +train: [5] [399/400] eta: 0:00:00 lr: 0.000297 loss: 2.6291 (2.6886) grad: 0.2281 (0.2337) time: 0.4284 data: 0.0039 max mem: 22448 +train: [5] Total time: 0:02:58 (0.4465 s / it) +train: [5] Summary: lr: 0.000297 loss: 2.6291 (2.6886) grad: 0.2281 (0.2337) +eval (validation): [5] [ 0/85] eta: 0:04:31 time: 3.1897 data: 2.9180 max mem: 22448 +eval (validation): [5] [20/85] eta: 0:00:30 time: 0.3360 data: 0.0053 max mem: 22448 +eval (validation): [5] [40/85] eta: 0:00:17 time: 0.3209 data: 0.0033 max mem: 22448 +eval (validation): [5] [60/85] eta: 0:00:09 time: 0.3493 data: 0.0042 max mem: 22448 +eval (validation): [5] [80/85] eta: 0:00:01 time: 0.3386 data: 0.0039 max mem: 22448 +eval (validation): [5] [84/85] eta: 0:00:00 time: 0.3297 data: 0.0037 max mem: 22448 +eval (validation): [5] Total time: 0:00:31 (0.3715 s / it) +cv: [5] best hparam: (1.2, 1.0) (025) ('025_lr1.2e+00_wd1.0e+00') loss: 2.356 acc: 0.290 f1: 0.220 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/nsd_cococlip__patch__attn/checkpoint-best.pth +train: [6] [ 0/400] eta: 0:22:34 lr: nan time: 3.3855 data: 3.0423 max mem: 22448 +train: [6] [ 20/400] eta: 0:03:48 lr: 0.000296 loss: 2.6211 (2.6064) grad: 0.2246 (0.2272) time: 0.4622 data: 0.0039 max mem: 22448 +train: [6] [ 40/400] eta: 0:03:09 lr: 0.000296 loss: 2.6314 (2.6321) grad: 0.2301 (0.2318) time: 0.4452 data: 0.0039 max mem: 22448 +train: [6] [ 60/400] eta: 0:02:49 lr: 0.000296 loss: 2.6280 (2.6289) grad: 0.2301 (0.2328) time: 0.4405 data: 0.0041 max mem: 22448 +train: [6] [ 80/400] eta: 0:02:33 lr: 0.000295 loss: 2.5880 (2.6129) grad: 0.2283 (0.2330) time: 0.4298 data: 0.0040 max mem: 22448 +train: [6] [100/400] eta: 0:02:23 lr: 0.000295 loss: 2.5880 (2.6108) grad: 0.2298 (0.2325) time: 0.4627 data: 0.0041 max mem: 22448 +train: [6] [120/400] eta: 0:02:11 lr: 0.000295 loss: 2.6066 (2.6147) grad: 0.2337 (0.2337) time: 0.4364 data: 0.0041 max mem: 22448 +train: [6] [140/400] eta: 0:02:01 lr: 0.000294 loss: 2.6224 (2.6224) grad: 0.2357 (0.2348) time: 0.4402 data: 0.0043 max mem: 22448 +train: [6] [160/400] eta: 0:01:50 lr: 0.000294 loss: 2.6452 (2.6264) grad: 0.2384 (0.2350) time: 0.4291 data: 0.0042 max mem: 22448 +train: [6] [180/400] eta: 0:01:41 lr: 0.000293 loss: 2.6081 (2.6246) grad: 0.2402 (0.2358) time: 0.4469 data: 0.0041 max mem: 22448 +train: [6] [200/400] eta: 0:01:31 lr: 0.000293 loss: 2.6107 (2.6255) grad: 0.2368 (0.2357) time: 0.4415 data: 0.0042 max mem: 22448 +train: [6] [220/400] eta: 0:01:22 lr: 0.000292 loss: 2.6219 (2.6231) grad: 0.2400 (0.2366) time: 0.4343 data: 0.0040 max mem: 22448 +train: [6] [240/400] eta: 0:01:12 lr: 0.000292 loss: 2.6352 (2.6256) grad: 0.2471 (0.2375) time: 0.4302 data: 0.0040 max mem: 22448 +train: [6] [260/400] eta: 0:01:03 lr: 0.000291 loss: 2.6352 (2.6214) grad: 0.2397 (0.2377) time: 0.4304 data: 0.0040 max mem: 22448 +train: [6] [280/400] eta: 0:00:54 lr: 0.000291 loss: 2.6147 (2.6214) grad: 0.2373 (0.2376) time: 0.4324 data: 0.0039 max mem: 22448 +train: [6] [300/400] eta: 0:00:44 lr: 0.000290 loss: 2.6407 (2.6227) grad: 0.2298 (0.2376) time: 0.4398 data: 0.0041 max mem: 22448 +train: [6] [320/400] eta: 0:00:35 lr: 0.000290 loss: 2.6611 (2.6242) grad: 0.2363 (0.2380) time: 0.4353 data: 0.0041 max mem: 22448 +train: [6] [340/400] eta: 0:00:26 lr: 0.000289 loss: 2.6611 (2.6260) grad: 0.2408 (0.2382) time: 0.4333 data: 0.0041 max mem: 22448 +train: [6] [360/400] eta: 0:00:17 lr: 0.000288 loss: 2.6046 (2.6240) grad: 0.2409 (0.2383) time: 0.4383 data: 0.0043 max mem: 22448 +train: [6] [380/400] eta: 0:00:08 lr: 0.000288 loss: 2.6046 (2.6261) grad: 0.2423 (0.2385) time: 0.4427 data: 0.0041 max mem: 22448 +train: [6] [399/400] eta: 0:00:00 lr: 0.000287 loss: 2.6276 (2.6266) grad: 0.2301 (0.2380) time: 0.4391 data: 0.0040 max mem: 22448 +train: [6] Total time: 0:02:58 (0.4472 s / it) +train: [6] Summary: lr: 0.000287 loss: 2.6276 (2.6266) grad: 0.2301 (0.2380) +eval (validation): [6] [ 0/85] eta: 0:04:32 time: 3.2079 data: 2.9370 max mem: 22448 +eval (validation): [6] [20/85] eta: 0:00:32 time: 0.3669 data: 0.0035 max mem: 22448 +eval (validation): [6] [40/85] eta: 0:00:19 time: 0.3432 data: 0.0039 max mem: 22448 +eval (validation): [6] [60/85] eta: 0:00:09 time: 0.3396 data: 0.0042 max mem: 22448 +eval (validation): [6] [80/85] eta: 0:00:01 time: 0.3253 data: 0.0038 max mem: 22448 +eval (validation): [6] [84/85] eta: 0:00:00 time: 0.3198 data: 0.0037 max mem: 22448 +eval (validation): [6] Total time: 0:00:32 (0.3795 s / it) +cv: [6] best hparam: (0.72, 1.0) (022) ('022_lr7.2e-01_wd1.0e+00') loss: 2.373 acc: 0.284 f1: 0.222 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [7] [ 0/400] eta: 0:23:05 lr: nan time: 3.4650 data: 3.0913 max mem: 22448 +train: [7] [ 20/400] eta: 0:03:49 lr: 0.000286 loss: 2.5294 (2.5332) grad: 0.2255 (0.2312) time: 0.4611 data: 0.0028 max mem: 22448 +train: [7] [ 40/400] eta: 0:03:09 lr: 0.000286 loss: 2.5287 (2.5414) grad: 0.2312 (0.2355) time: 0.4449 data: 0.0042 max mem: 22448 +train: [7] [ 60/400] eta: 0:02:50 lr: 0.000285 loss: 2.5220 (2.5298) grad: 0.2389 (0.2389) time: 0.4476 data: 0.0043 max mem: 22448 +train: [7] [ 80/400] eta: 0:02:34 lr: 0.000284 loss: 2.5220 (2.5432) grad: 0.2407 (0.2374) time: 0.4298 data: 0.0042 max mem: 22448 +train: [7] [100/400] eta: 0:02:22 lr: 0.000284 loss: 2.5337 (2.5358) grad: 0.2313 (0.2370) time: 0.4489 data: 0.0042 max mem: 22448 +train: [7] [120/400] eta: 0:02:12 lr: 0.000283 loss: 2.5183 (2.5351) grad: 0.2402 (0.2389) time: 0.4501 data: 0.0044 max mem: 22448 +train: [7] [140/400] eta: 0:02:01 lr: 0.000282 loss: 2.5113 (2.5402) grad: 0.2420 (0.2397) time: 0.4329 data: 0.0042 max mem: 22448 +train: [7] [160/400] eta: 0:01:50 lr: 0.000282 loss: 2.5605 (2.5432) grad: 0.2398 (0.2396) time: 0.4308 data: 0.0042 max mem: 22448 +train: [7] [180/400] eta: 0:01:40 lr: 0.000281 loss: 2.5960 (2.5506) grad: 0.2428 (0.2407) time: 0.4352 data: 0.0042 max mem: 22448 +train: [7] [200/400] eta: 0:01:31 lr: 0.000280 loss: 2.5939 (2.5493) grad: 0.2471 (0.2411) time: 0.4344 data: 0.0043 max mem: 22448 +train: [7] [220/400] eta: 0:01:21 lr: 0.000279 loss: 2.5299 (2.5488) grad: 0.2426 (0.2422) time: 0.4283 data: 0.0040 max mem: 22448 +train: [7] [240/400] eta: 0:01:12 lr: 0.000278 loss: 2.5962 (2.5531) grad: 0.2527 (0.2432) time: 0.4347 data: 0.0041 max mem: 22448 +train: [7] [260/400] eta: 0:01:03 lr: 0.000278 loss: 2.5745 (2.5525) grad: 0.2433 (0.2424) time: 0.4301 data: 0.0042 max mem: 22448 +train: [7] [280/400] eta: 0:00:53 lr: 0.000277 loss: 2.5220 (2.5510) grad: 0.2334 (0.2420) time: 0.4336 data: 0.0042 max mem: 22448 +train: [7] [300/400] eta: 0:00:44 lr: 0.000276 loss: 2.4769 (2.5505) grad: 0.2409 (0.2422) time: 0.4409 data: 0.0041 max mem: 22448 +train: [7] [320/400] eta: 0:00:35 lr: 0.000275 loss: 2.5421 (2.5518) grad: 0.2463 (0.2422) time: 0.4281 data: 0.0042 max mem: 22448 +train: [7] [340/400] eta: 0:00:26 lr: 0.000274 loss: 2.5329 (2.5492) grad: 0.2352 (0.2417) time: 0.4284 data: 0.0039 max mem: 22448 +train: [7] [360/400] eta: 0:00:17 lr: 0.000273 loss: 2.5193 (2.5506) grad: 0.2409 (0.2424) time: 0.4287 data: 0.0040 max mem: 22448 +train: [7] [380/400] eta: 0:00:08 lr: 0.000272 loss: 2.5357 (2.5502) grad: 0.2470 (0.2431) time: 0.4244 data: 0.0042 max mem: 22448 +train: [7] [399/400] eta: 0:00:00 lr: 0.000271 loss: 2.5974 (2.5524) grad: 0.2515 (0.2437) time: 0.4406 data: 0.0041 max mem: 22448 +train: [7] Total time: 0:02:57 (0.4446 s / it) +train: [7] Summary: lr: 0.000271 loss: 2.5974 (2.5524) grad: 0.2515 (0.2437) +eval (validation): [7] [ 0/85] eta: 0:04:39 time: 3.2927 data: 3.0588 max mem: 22448 +eval (validation): [7] [20/85] eta: 0:00:30 time: 0.3276 data: 0.0039 max mem: 22448 +eval (validation): [7] [40/85] eta: 0:00:17 time: 0.3238 data: 0.0033 max mem: 22448 +eval (validation): [7] [60/85] eta: 0:00:09 time: 0.3444 data: 0.0042 max mem: 22448 +eval (validation): [7] [80/85] eta: 0:00:01 time: 0.3480 data: 0.0042 max mem: 22448 +eval (validation): [7] [84/85] eta: 0:00:00 time: 0.3337 data: 0.0040 max mem: 22448 +eval (validation): [7] Total time: 0:00:31 (0.3734 s / it) +cv: [7] best hparam: (0.72, 1.0) (022) ('022_lr7.2e-01_wd1.0e+00') loss: 2.381 acc: 0.279 f1: 0.220 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [8] [ 0/400] eta: 0:23:36 lr: nan time: 3.5417 data: 3.1581 max mem: 22448 +train: [8] [ 20/400] eta: 0:03:50 lr: 0.000270 loss: 2.4135 (2.4351) grad: 0.2288 (0.2339) time: 0.4602 data: 0.0034 max mem: 22448 +train: [8] [ 40/400] eta: 0:03:11 lr: 0.000270 loss: 2.4428 (2.4597) grad: 0.2390 (0.2394) time: 0.4508 data: 0.0042 max mem: 22448 +train: [8] [ 60/400] eta: 0:02:50 lr: 0.000269 loss: 2.4681 (2.4679) grad: 0.2418 (0.2388) time: 0.4377 data: 0.0043 max mem: 22448 +train: [8] [ 80/400] eta: 0:02:34 lr: 0.000268 loss: 2.4952 (2.4762) grad: 0.2402 (0.2413) time: 0.4249 data: 0.0041 max mem: 22448 +train: [8] [100/400] eta: 0:02:22 lr: 0.000267 loss: 2.5005 (2.4761) grad: 0.2533 (0.2449) time: 0.4462 data: 0.0043 max mem: 22448 +train: [8] [120/400] eta: 0:02:11 lr: 0.000266 loss: 2.4784 (2.4779) grad: 0.2638 (0.2481) time: 0.4443 data: 0.0043 max mem: 22448 +train: [8] [140/400] eta: 0:02:00 lr: 0.000265 loss: 2.4723 (2.4839) grad: 0.2584 (0.2493) time: 0.4390 data: 0.0043 max mem: 22448 +train: [8] [160/400] eta: 0:01:50 lr: 0.000264 loss: 2.4969 (2.4842) grad: 0.2590 (0.2519) time: 0.4376 data: 0.0041 max mem: 22448 +train: [8] [180/400] eta: 0:01:40 lr: 0.000263 loss: 2.4778 (2.4821) grad: 0.2558 (0.2515) time: 0.4365 data: 0.0040 max mem: 22448 +train: [8] [200/400] eta: 0:01:31 lr: 0.000262 loss: 2.4797 (2.4854) grad: 0.2497 (0.2514) time: 0.4489 data: 0.0041 max mem: 22448 +train: [8] [220/400] eta: 0:01:22 lr: 0.000260 loss: 2.5162 (2.4868) grad: 0.2497 (0.2512) time: 0.4357 data: 0.0040 max mem: 22448 +train: [8] [240/400] eta: 0:01:12 lr: 0.000259 loss: 2.5080 (2.4863) grad: 0.2494 (0.2512) time: 0.4342 data: 0.0041 max mem: 22448 +train: [8] [260/400] eta: 0:01:03 lr: 0.000258 loss: 2.5120 (2.4894) grad: 0.2477 (0.2514) time: 0.4347 data: 0.0040 max mem: 22448 +train: [8] [280/400] eta: 0:00:54 lr: 0.000257 loss: 2.5041 (2.4882) grad: 0.2483 (0.2512) time: 0.4311 data: 0.0042 max mem: 22448 +train: [8] [300/400] eta: 0:00:45 lr: 0.000256 loss: 2.4762 (2.4882) grad: 0.2485 (0.2511) time: 0.4371 data: 0.0042 max mem: 22448 +train: [8] [320/400] eta: 0:00:35 lr: 0.000255 loss: 2.4842 (2.4878) grad: 0.2433 (0.2503) time: 0.4454 data: 0.0042 max mem: 22448 +train: [8] [340/400] eta: 0:00:26 lr: 0.000254 loss: 2.4880 (2.4875) grad: 0.2433 (0.2506) time: 0.4392 data: 0.0041 max mem: 22448 +train: [8] [360/400] eta: 0:00:17 lr: 0.000253 loss: 2.4670 (2.4875) grad: 0.2528 (0.2504) time: 0.4336 data: 0.0040 max mem: 22448 +train: [8] [380/400] eta: 0:00:08 lr: 0.000252 loss: 2.4670 (2.4887) grad: 0.2461 (0.2502) time: 0.4391 data: 0.0041 max mem: 22448 +train: [8] [399/400] eta: 0:00:00 lr: 0.000250 loss: 2.5281 (2.4893) grad: 0.2505 (0.2510) time: 0.4316 data: 0.0040 max mem: 22448 +train: [8] Total time: 0:02:59 (0.4475 s / it) +train: [8] Summary: lr: 0.000250 loss: 2.5281 (2.4893) grad: 0.2505 (0.2510) +eval (validation): [8] [ 0/85] eta: 0:04:37 time: 3.2628 data: 2.9852 max mem: 22448 +eval (validation): [8] [20/85] eta: 0:00:31 time: 0.3416 data: 0.0027 max mem: 22448 +eval (validation): [8] [40/85] eta: 0:00:18 time: 0.3367 data: 0.0036 max mem: 22448 +eval (validation): [8] [60/85] eta: 0:00:09 time: 0.3579 data: 0.0045 max mem: 22448 +eval (validation): [8] [80/85] eta: 0:00:01 time: 0.3278 data: 0.0041 max mem: 22448 +eval (validation): [8] [84/85] eta: 0:00:00 time: 0.3237 data: 0.0040 max mem: 22448 +eval (validation): [8] Total time: 0:00:32 (0.3769 s / it) +cv: [8] best hparam: (0.44, 1.0) (019) ('019_lr4.4e-01_wd1.0e+00') loss: 2.409 acc: 0.274 f1: 0.214 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [9] [ 0/400] eta: 0:22:53 lr: nan time: 3.4344 data: 3.0539 max mem: 22448 +train: [9] [ 20/400] eta: 0:03:45 lr: 0.000249 loss: 2.4252 (2.4408) grad: 0.2554 (0.2609) time: 0.4509 data: 0.0040 max mem: 22448 +train: [9] [ 40/400] eta: 0:03:09 lr: 0.000248 loss: 2.4595 (2.4573) grad: 0.2519 (0.2545) time: 0.4570 data: 0.0043 max mem: 22448 +train: [9] [ 60/400] eta: 0:02:50 lr: 0.000247 loss: 2.4452 (2.4466) grad: 0.2448 (0.2515) time: 0.4482 data: 0.0044 max mem: 22448 +train: [9] [ 80/400] eta: 0:02:35 lr: 0.000246 loss: 2.4452 (2.4569) grad: 0.2489 (0.2530) time: 0.4361 data: 0.0042 max mem: 22448 +train: [9] [100/400] eta: 0:02:22 lr: 0.000244 loss: 2.4461 (2.4551) grad: 0.2520 (0.2522) time: 0.4403 data: 0.0042 max mem: 22448 +train: [9] [120/400] eta: 0:02:12 lr: 0.000243 loss: 2.4139 (2.4526) grad: 0.2455 (0.2516) time: 0.4490 data: 0.0042 max mem: 22448 +train: [9] [140/400] eta: 0:02:01 lr: 0.000242 loss: 2.4309 (2.4534) grad: 0.2532 (0.2527) time: 0.4432 data: 0.0042 max mem: 22448 +train: [9] [160/400] eta: 0:01:51 lr: 0.000241 loss: 2.4409 (2.4501) grad: 0.2543 (0.2533) time: 0.4420 data: 0.0041 max mem: 22448 +train: [9] [180/400] eta: 0:01:41 lr: 0.000240 loss: 2.4180 (2.4526) grad: 0.2543 (0.2537) time: 0.4367 data: 0.0039 max mem: 22448 +train: [9] [200/400] eta: 0:01:31 lr: 0.000238 loss: 2.4164 (2.4492) grad: 0.2579 (0.2544) time: 0.4412 data: 0.0040 max mem: 22448 +train: [9] [220/400] eta: 0:01:22 lr: 0.000237 loss: 2.4164 (2.4462) grad: 0.2579 (0.2550) time: 0.4405 data: 0.0042 max mem: 22448 +train: [9] [240/400] eta: 0:01:12 lr: 0.000236 loss: 2.4668 (2.4498) grad: 0.2543 (0.2547) time: 0.4383 data: 0.0044 max mem: 22448 +train: [9] [260/400] eta: 0:01:03 lr: 0.000234 loss: 2.4668 (2.4486) grad: 0.2513 (0.2542) time: 0.4459 data: 0.0040 max mem: 22448 +train: [9] [280/400] eta: 0:00:54 lr: 0.000233 loss: 2.4325 (2.4471) grad: 0.2501 (0.2543) time: 0.4368 data: 0.0041 max mem: 22448 +train: [9] [300/400] eta: 0:00:45 lr: 0.000232 loss: 2.4194 (2.4473) grad: 0.2561 (0.2546) time: 0.4370 data: 0.0039 max mem: 22448 +train: [9] [320/400] eta: 0:00:36 lr: 0.000230 loss: 2.4194 (2.4486) grad: 0.2547 (0.2547) time: 0.4317 data: 0.0041 max mem: 22448 +train: [9] [340/400] eta: 0:00:27 lr: 0.000229 loss: 2.3992 (2.4464) grad: 0.2493 (0.2548) time: 0.4417 data: 0.0041 max mem: 22448 +train: [9] [360/400] eta: 0:00:18 lr: 0.000228 loss: 2.4355 (2.4471) grad: 0.2566 (0.2554) time: 0.4365 data: 0.0042 max mem: 22448 +train: [9] [380/400] eta: 0:00:08 lr: 0.000226 loss: 2.4335 (2.4462) grad: 0.2621 (0.2553) time: 0.4318 data: 0.0040 max mem: 22448 +train: [9] [399/400] eta: 0:00:00 lr: 0.000225 loss: 2.4470 (2.4468) grad: 0.2622 (0.2558) time: 0.4322 data: 0.0041 max mem: 22448 +train: [9] Total time: 0:02:59 (0.4487 s / it) +train: [9] Summary: lr: 0.000225 loss: 2.4470 (2.4468) grad: 0.2622 (0.2558) +eval (validation): [9] [ 0/85] eta: 0:04:26 time: 3.1325 data: 2.8971 max mem: 22448 +eval (validation): [9] [20/85] eta: 0:00:31 time: 0.3451 data: 0.0049 max mem: 22448 +eval (validation): [9] [40/85] eta: 0:00:18 time: 0.3501 data: 0.0033 max mem: 22448 +eval (validation): [9] [60/85] eta: 0:00:09 time: 0.3425 data: 0.0042 max mem: 22448 +eval (validation): [9] [80/85] eta: 0:00:01 time: 0.3331 data: 0.0039 max mem: 22448 +eval (validation): [9] [84/85] eta: 0:00:00 time: 0.3266 data: 0.0037 max mem: 22448 +eval (validation): [9] Total time: 0:00:32 (0.3768 s / it) +cv: [9] best hparam: (0.52, 1.0) (020) ('020_lr5.2e-01_wd1.0e+00') loss: 2.381 acc: 0.282 f1: 0.220 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [10] [ 0/400] eta: 0:23:18 lr: nan time: 3.4954 data: 3.1204 max mem: 22448 +train: [10] [ 20/400] eta: 0:03:43 lr: 0.000224 loss: 2.3616 (2.3920) grad: 0.2597 (0.2632) time: 0.4428 data: 0.0033 max mem: 22448 +train: [10] [ 40/400] eta: 0:03:09 lr: 0.000222 loss: 2.3512 (2.3794) grad: 0.2597 (0.2590) time: 0.4592 data: 0.0043 max mem: 22448 +train: [10] [ 60/400] eta: 0:02:49 lr: 0.000221 loss: 2.3571 (2.3945) grad: 0.2511 (0.2556) time: 0.4402 data: 0.0045 max mem: 22448 +train: [10] [ 80/400] eta: 0:02:34 lr: 0.000220 loss: 2.3571 (2.3793) grad: 0.2438 (0.2523) time: 0.4412 data: 0.0039 max mem: 22448 +train: [10] [100/400] eta: 0:02:22 lr: 0.000218 loss: 2.3472 (2.3751) grad: 0.2472 (0.2523) time: 0.4458 data: 0.0041 max mem: 22448 +train: [10] [120/400] eta: 0:02:12 lr: 0.000217 loss: 2.3756 (2.3786) grad: 0.2505 (0.2534) time: 0.4488 data: 0.0041 max mem: 22448 +train: [10] [140/400] eta: 0:02:01 lr: 0.000215 loss: 2.3756 (2.3802) grad: 0.2541 (0.2536) time: 0.4472 data: 0.0044 max mem: 22448 +train: [10] [160/400] eta: 0:01:51 lr: 0.000214 loss: 2.3429 (2.3825) grad: 0.2533 (0.2541) time: 0.4396 data: 0.0043 max mem: 22448 +train: [10] [180/400] eta: 0:01:41 lr: 0.000213 loss: 2.3770 (2.3846) grad: 0.2533 (0.2545) time: 0.4464 data: 0.0042 max mem: 22448 +train: [10] [200/400] eta: 0:01:32 lr: 0.000211 loss: 2.4144 (2.3855) grad: 0.2524 (0.2548) time: 0.4452 data: 0.0043 max mem: 22448 +train: [10] [220/400] eta: 0:01:22 lr: 0.000210 loss: 2.4024 (2.3852) grad: 0.2581 (0.2548) time: 0.4461 data: 0.0042 max mem: 22448 +train: [10] [240/400] eta: 0:01:13 lr: 0.000208 loss: 2.3927 (2.3858) grad: 0.2523 (0.2547) time: 0.4360 data: 0.0042 max mem: 22448 +train: [10] [260/400] eta: 0:01:03 lr: 0.000207 loss: 2.3913 (2.3846) grad: 0.2511 (0.2544) time: 0.4338 data: 0.0040 max mem: 22448 +train: [10] [280/400] eta: 0:00:54 lr: 0.000205 loss: 2.3943 (2.3842) grad: 0.2516 (0.2543) time: 0.4299 data: 0.0041 max mem: 22448 +train: [10] [300/400] eta: 0:00:45 lr: 0.000204 loss: 2.3490 (2.3803) grad: 0.2512 (0.2538) time: 0.4321 data: 0.0041 max mem: 22448 +train: [10] [320/400] eta: 0:00:36 lr: 0.000202 loss: 2.3486 (2.3785) grad: 0.2523 (0.2544) time: 0.4403 data: 0.0041 max mem: 22448 +train: [10] [340/400] eta: 0:00:27 lr: 0.000201 loss: 2.3740 (2.3787) grad: 0.2596 (0.2545) time: 0.4420 data: 0.0040 max mem: 22448 +train: [10] [360/400] eta: 0:00:18 lr: 0.000199 loss: 2.3684 (2.3781) grad: 0.2536 (0.2543) time: 0.4365 data: 0.0041 max mem: 22448 +train: [10] [380/400] eta: 0:00:08 lr: 0.000198 loss: 2.3425 (2.3768) grad: 0.2519 (0.2541) time: 0.4446 data: 0.0042 max mem: 22448 +train: [10] [399/400] eta: 0:00:00 lr: 0.000196 loss: 2.3573 (2.3783) grad: 0.2537 (0.2543) time: 0.4387 data: 0.0041 max mem: 22448 +train: [10] Total time: 0:02:59 (0.4497 s / it) +train: [10] Summary: lr: 0.000196 loss: 2.3573 (2.3783) grad: 0.2537 (0.2543) +eval (validation): [10] [ 0/85] eta: 0:04:34 time: 3.2303 data: 3.0017 max mem: 22448 +eval (validation): [10] [20/85] eta: 0:00:31 time: 0.3483 data: 0.0038 max mem: 22448 +eval (validation): [10] [40/85] eta: 0:00:19 time: 0.3688 data: 0.0038 max mem: 22448 +eval (validation): [10] [60/85] eta: 0:00:09 time: 0.3366 data: 0.0041 max mem: 22448 +eval (validation): [10] [80/85] eta: 0:00:01 time: 0.3379 data: 0.0040 max mem: 22448 +eval (validation): [10] [84/85] eta: 0:00:00 time: 0.3207 data: 0.0037 max mem: 22448 +eval (validation): [10] Total time: 0:00:32 (0.3835 s / it) +cv: [10] best hparam: (0.44, 1.0) (019) ('019_lr4.4e-01_wd1.0e+00') loss: 2.377 acc: 0.285 f1: 0.226 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [11] [ 0/400] eta: 0:21:51 lr: nan time: 3.2795 data: 2.9175 max mem: 22448 +train: [11] [ 20/400] eta: 0:03:40 lr: 0.000195 loss: 2.2831 (2.3210) grad: 0.2413 (0.2473) time: 0.4441 data: 0.0027 max mem: 22448 +train: [11] [ 40/400] eta: 0:03:05 lr: 0.000193 loss: 2.3254 (2.3312) grad: 0.2443 (0.2485) time: 0.4480 data: 0.0041 max mem: 22448 +train: [11] [ 60/400] eta: 0:02:46 lr: 0.000192 loss: 2.3010 (2.3163) grad: 0.2510 (0.2515) time: 0.4379 data: 0.0042 max mem: 22448 +train: [11] [ 80/400] eta: 0:02:32 lr: 0.000190 loss: 2.3038 (2.3273) grad: 0.2512 (0.2526) time: 0.4323 data: 0.0038 max mem: 22448 +train: [11] [100/400] eta: 0:02:20 lr: 0.000189 loss: 2.3306 (2.3233) grad: 0.2482 (0.2525) time: 0.4457 data: 0.0040 max mem: 22448 +train: [11] [120/400] eta: 0:02:10 lr: 0.000187 loss: 2.2526 (2.3117) grad: 0.2535 (0.2526) time: 0.4570 data: 0.0042 max mem: 22448 +train: [11] [140/400] eta: 0:02:00 lr: 0.000186 loss: 2.2803 (2.3124) grad: 0.2538 (0.2532) time: 0.4425 data: 0.0044 max mem: 22448 +train: [11] [160/400] eta: 0:01:50 lr: 0.000184 loss: 2.3132 (2.3175) grad: 0.2597 (0.2538) time: 0.4301 data: 0.0040 max mem: 22448 +train: [11] [180/400] eta: 0:01:40 lr: 0.000183 loss: 2.2940 (2.3192) grad: 0.2654 (0.2556) time: 0.4464 data: 0.0042 max mem: 22448 +train: [11] [200/400] eta: 0:01:31 lr: 0.000181 loss: 2.3551 (2.3222) grad: 0.2654 (0.2562) time: 0.4455 data: 0.0042 max mem: 22448 +train: [11] [220/400] eta: 0:01:22 lr: 0.000180 loss: 2.3717 (2.3288) grad: 0.2574 (0.2562) time: 0.4410 data: 0.0041 max mem: 22448 +train: [11] [240/400] eta: 0:01:12 lr: 0.000178 loss: 2.3639 (2.3298) grad: 0.2510 (0.2568) time: 0.4275 data: 0.0040 max mem: 22448 +train: [11] [260/400] eta: 0:01:03 lr: 0.000177 loss: 2.3290 (2.3293) grad: 0.2650 (0.2578) time: 0.4283 data: 0.0039 max mem: 22448 +train: [11] [280/400] eta: 0:00:53 lr: 0.000175 loss: 2.3182 (2.3292) grad: 0.2671 (0.2582) time: 0.4313 data: 0.0040 max mem: 22448 +train: [11] [300/400] eta: 0:00:44 lr: 0.000174 loss: 2.3552 (2.3341) grad: 0.2619 (0.2582) time: 0.4321 data: 0.0039 max mem: 22448 +train: [11] [320/400] eta: 0:00:35 lr: 0.000172 loss: 2.3929 (2.3363) grad: 0.2585 (0.2590) time: 0.4302 data: 0.0040 max mem: 22448 +train: [11] [340/400] eta: 0:00:26 lr: 0.000170 loss: 2.3559 (2.3375) grad: 0.2585 (0.2596) time: 0.4244 data: 0.0041 max mem: 22448 +train: [11] [360/400] eta: 0:00:17 lr: 0.000169 loss: 2.3405 (2.3370) grad: 0.2561 (0.2599) time: 0.4348 data: 0.0041 max mem: 22448 +train: [11] [380/400] eta: 0:00:08 lr: 0.000167 loss: 2.3306 (2.3352) grad: 0.2569 (0.2597) time: 0.4334 data: 0.0042 max mem: 22448 +train: [11] [399/400] eta: 0:00:00 lr: 0.000166 loss: 2.3384 (2.3383) grad: 0.2569 (0.2595) time: 0.4252 data: 0.0039 max mem: 22448 +train: [11] Total time: 0:02:57 (0.4443 s / it) +train: [11] Summary: lr: 0.000166 loss: 2.3384 (2.3383) grad: 0.2569 (0.2595) +eval (validation): [11] [ 0/85] eta: 0:04:34 time: 3.2239 data: 2.9579 max mem: 22448 +eval (validation): [11] [20/85] eta: 0:00:32 time: 0.3651 data: 0.0047 max mem: 22448 +eval (validation): [11] [40/85] eta: 0:00:19 time: 0.3406 data: 0.0041 max mem: 22448 +eval (validation): [11] [60/85] eta: 0:00:10 time: 0.3592 data: 0.0042 max mem: 22448 +eval (validation): [11] [80/85] eta: 0:00:01 time: 0.3292 data: 0.0038 max mem: 22448 +eval (validation): [11] [84/85] eta: 0:00:00 time: 0.3211 data: 0.0038 max mem: 22448 +eval (validation): [11] Total time: 0:00:32 (0.3836 s / it) +cv: [11] best hparam: (0.44, 1.0) (019) ('019_lr4.4e-01_wd1.0e+00') loss: 2.386 acc: 0.287 f1: 0.228 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [12] [ 0/400] eta: 0:22:17 lr: nan time: 3.3447 data: 2.9704 max mem: 22448 +train: [12] [ 20/400] eta: 0:03:49 lr: 0.000164 loss: 2.2225 (2.2364) grad: 0.2424 (0.2438) time: 0.4663 data: 0.0032 max mem: 22448 +train: [12] [ 40/400] eta: 0:03:09 lr: 0.000163 loss: 2.2334 (2.2496) grad: 0.2464 (0.2471) time: 0.4433 data: 0.0042 max mem: 22448 +train: [12] [ 60/400] eta: 0:02:50 lr: 0.000161 loss: 2.2338 (2.2468) grad: 0.2464 (0.2463) time: 0.4483 data: 0.0042 max mem: 22448 +train: [12] [ 80/400] eta: 0:02:35 lr: 0.000160 loss: 2.2443 (2.2594) grad: 0.2485 (0.2481) time: 0.4389 data: 0.0041 max mem: 22448 +train: [12] [100/400] eta: 0:02:23 lr: 0.000158 loss: 2.2564 (2.2603) grad: 0.2544 (0.2492) time: 0.4517 data: 0.0042 max mem: 22448 +train: [12] [120/400] eta: 0:02:12 lr: 0.000156 loss: 2.2582 (2.2676) grad: 0.2498 (0.2484) time: 0.4539 data: 0.0041 max mem: 22448 +train: [12] [140/400] eta: 0:02:02 lr: 0.000155 loss: 2.2629 (2.2661) grad: 0.2520 (0.2509) time: 0.4419 data: 0.0044 max mem: 22448 +train: [12] [160/400] eta: 0:01:51 lr: 0.000153 loss: 2.2495 (2.2690) grad: 0.2662 (0.2532) time: 0.4342 data: 0.0042 max mem: 22448 +train: [12] [180/400] eta: 0:01:41 lr: 0.000152 loss: 2.2772 (2.2697) grad: 0.2629 (0.2537) time: 0.4431 data: 0.0042 max mem: 22448 +train: [12] [200/400] eta: 0:01:32 lr: 0.000150 loss: 2.2998 (2.2754) grad: 0.2552 (0.2542) time: 0.4375 data: 0.0042 max mem: 22448 +train: [12] [220/400] eta: 0:01:22 lr: 0.000149 loss: 2.3044 (2.2791) grad: 0.2552 (0.2546) time: 0.4387 data: 0.0041 max mem: 22448 +train: [12] [240/400] eta: 0:01:12 lr: 0.000147 loss: 2.2738 (2.2771) grad: 0.2591 (0.2561) time: 0.4322 data: 0.0041 max mem: 22448 +train: [12] [260/400] eta: 0:01:03 lr: 0.000145 loss: 2.2547 (2.2764) grad: 0.2571 (0.2560) time: 0.4239 data: 0.0040 max mem: 22448 +train: [12] [280/400] eta: 0:00:54 lr: 0.000144 loss: 2.2316 (2.2726) grad: 0.2495 (0.2560) time: 0.4257 data: 0.0039 max mem: 22448 +train: [12] [300/400] eta: 0:00:44 lr: 0.000142 loss: 2.2298 (2.2738) grad: 0.2595 (0.2570) time: 0.4245 data: 0.0039 max mem: 22448 +train: [12] [320/400] eta: 0:00:35 lr: 0.000141 loss: 2.2298 (2.2751) grad: 0.2617 (0.2570) time: 0.4317 data: 0.0040 max mem: 22448 +train: [12] [340/400] eta: 0:00:26 lr: 0.000139 loss: 2.2303 (2.2751) grad: 0.2575 (0.2569) time: 0.4369 data: 0.0040 max mem: 22448 +train: [12] [360/400] eta: 0:00:17 lr: 0.000138 loss: 2.2505 (2.2740) grad: 0.2565 (0.2568) time: 0.4347 data: 0.0040 max mem: 22448 +train: [12] [380/400] eta: 0:00:08 lr: 0.000136 loss: 2.2665 (2.2747) grad: 0.2565 (0.2567) time: 0.4326 data: 0.0041 max mem: 22448 +train: [12] [399/400] eta: 0:00:00 lr: 0.000134 loss: 2.2663 (2.2744) grad: 0.2611 (0.2572) time: 0.4348 data: 0.0043 max mem: 22448 +train: [12] Total time: 0:02:58 (0.4463 s / it) +train: [12] Summary: lr: 0.000134 loss: 2.2663 (2.2744) grad: 0.2611 (0.2572) +eval (validation): [12] [ 0/85] eta: 0:04:35 time: 3.2384 data: 2.9729 max mem: 22448 +eval (validation): [12] [20/85] eta: 0:00:32 time: 0.3606 data: 0.0054 max mem: 22448 +eval (validation): [12] [40/85] eta: 0:00:19 time: 0.3681 data: 0.0037 max mem: 22448 +eval (validation): [12] [60/85] eta: 0:00:10 time: 0.3445 data: 0.0043 max mem: 22448 +eval (validation): [12] [80/85] eta: 0:00:01 time: 0.3378 data: 0.0041 max mem: 22448 +eval (validation): [12] [84/85] eta: 0:00:00 time: 0.3270 data: 0.0039 max mem: 22448 +eval (validation): [12] Total time: 0:00:32 (0.3881 s / it) +cv: [12] best hparam: (0.44, 1.0) (019) ('019_lr4.4e-01_wd1.0e+00') loss: 2.401 acc: 0.280 f1: 0.223 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [13] [ 0/400] eta: 0:21:26 lr: nan time: 3.2173 data: 2.8873 max mem: 22448 +train: [13] [ 20/400] eta: 0:03:45 lr: 0.000133 loss: 2.2249 (2.2309) grad: 0.2498 (0.2573) time: 0.4616 data: 0.0047 max mem: 22448 +train: [13] [ 40/400] eta: 0:03:07 lr: 0.000131 loss: 2.2437 (2.2352) grad: 0.2556 (0.2570) time: 0.4455 data: 0.0042 max mem: 22448 +train: [13] [ 60/400] eta: 0:02:47 lr: 0.000130 loss: 2.2497 (2.2388) grad: 0.2561 (0.2579) time: 0.4384 data: 0.0042 max mem: 22448 +train: [13] [ 80/400] eta: 0:02:32 lr: 0.000128 loss: 2.1939 (2.2349) grad: 0.2547 (0.2577) time: 0.4271 data: 0.0039 max mem: 22448 +train: [13] [100/400] eta: 0:02:21 lr: 0.000127 loss: 2.1884 (2.2278) grad: 0.2503 (0.2556) time: 0.4565 data: 0.0043 max mem: 22448 +train: [13] [120/400] eta: 0:02:11 lr: 0.000125 loss: 2.1979 (2.2198) grad: 0.2496 (0.2552) time: 0.4485 data: 0.0044 max mem: 22448 +train: [13] [140/400] eta: 0:02:01 lr: 0.000124 loss: 2.2356 (2.2277) grad: 0.2652 (0.2567) time: 0.4454 data: 0.0042 max mem: 22448 +train: [13] [160/400] eta: 0:01:50 lr: 0.000122 loss: 2.2506 (2.2282) grad: 0.2710 (0.2585) time: 0.4334 data: 0.0040 max mem: 22448 +train: [13] [180/400] eta: 0:01:40 lr: 0.000120 loss: 2.2238 (2.2321) grad: 0.2677 (0.2583) time: 0.4367 data: 0.0040 max mem: 22448 +train: [13] [200/400] eta: 0:01:31 lr: 0.000119 loss: 2.1972 (2.2262) grad: 0.2527 (0.2579) time: 0.4421 data: 0.0042 max mem: 22448 +train: [13] [220/400] eta: 0:01:21 lr: 0.000117 loss: 2.1699 (2.2264) grad: 0.2572 (0.2584) time: 0.4243 data: 0.0041 max mem: 22448 +train: [13] [240/400] eta: 0:01:12 lr: 0.000116 loss: 2.2421 (2.2270) grad: 0.2591 (0.2589) time: 0.4384 data: 0.0041 max mem: 22448 +train: [13] [260/400] eta: 0:01:03 lr: 0.000114 loss: 2.2257 (2.2286) grad: 0.2514 (0.2580) time: 0.4393 data: 0.0039 max mem: 22448 +train: [13] [280/400] eta: 0:00:54 lr: 0.000113 loss: 2.1830 (2.2275) grad: 0.2446 (0.2575) time: 0.4330 data: 0.0041 max mem: 22448 +train: [13] [300/400] eta: 0:00:44 lr: 0.000111 loss: 2.1919 (2.2272) grad: 0.2470 (0.2564) time: 0.4298 data: 0.0039 max mem: 22448 +train: [13] [320/400] eta: 0:00:35 lr: 0.000110 loss: 2.2453 (2.2285) grad: 0.2562 (0.2572) time: 0.4354 data: 0.0040 max mem: 22448 +train: [13] [340/400] eta: 0:00:26 lr: 0.000108 loss: 2.2352 (2.2287) grad: 0.2624 (0.2569) time: 0.4429 data: 0.0040 max mem: 22448 +train: [13] [360/400] eta: 0:00:17 lr: 0.000107 loss: 2.2341 (2.2300) grad: 0.2610 (0.2575) time: 0.4414 data: 0.0041 max mem: 22448 +train: [13] [380/400] eta: 0:00:08 lr: 0.000105 loss: 2.2330 (2.2303) grad: 0.2650 (0.2578) time: 0.4401 data: 0.0040 max mem: 22448 +train: [13] [399/400] eta: 0:00:00 lr: 0.000104 loss: 2.2354 (2.2321) grad: 0.2584 (0.2578) time: 0.4240 data: 0.0040 max mem: 22448 +train: [13] Total time: 0:02:58 (0.4465 s / it) +train: [13] Summary: lr: 0.000104 loss: 2.2354 (2.2321) grad: 0.2584 (0.2578) +eval (validation): [13] [ 0/85] eta: 0:04:31 time: 3.1980 data: 2.9196 max mem: 22448 +eval (validation): [13] [20/85] eta: 0:00:33 time: 0.3755 data: 0.0043 max mem: 22448 +eval (validation): [13] [40/85] eta: 0:00:19 time: 0.3373 data: 0.0039 max mem: 22448 +eval (validation): [13] [60/85] eta: 0:00:09 time: 0.3351 data: 0.0042 max mem: 22448 +eval (validation): [13] [80/85] eta: 0:00:01 time: 0.3204 data: 0.0040 max mem: 22448 +eval (validation): [13] [84/85] eta: 0:00:00 time: 0.3182 data: 0.0038 max mem: 22448 +eval (validation): [13] Total time: 0:00:32 (0.3775 s / it) +cv: [13] best hparam: (0.38, 1.0) (018) ('018_lr3.8e-01_wd1.0e+00') loss: 2.391 acc: 0.284 f1: 0.222 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [14] [ 0/400] eta: 0:22:04 lr: nan time: 3.3104 data: 2.9836 max mem: 22448 +train: [14] [ 20/400] eta: 0:03:41 lr: 0.000102 loss: 2.1209 (2.1364) grad: 0.2435 (0.2444) time: 0.4458 data: 0.0028 max mem: 22448 +train: [14] [ 40/400] eta: 0:03:06 lr: 0.000101 loss: 2.1483 (2.1515) grad: 0.2407 (0.2444) time: 0.4499 data: 0.0042 max mem: 22448 +train: [14] [ 60/400] eta: 0:02:48 lr: 0.000099 loss: 2.1601 (2.1617) grad: 0.2489 (0.2475) time: 0.4492 data: 0.0041 max mem: 22448 +train: [14] [ 80/400] eta: 0:02:33 lr: 0.000098 loss: 2.1601 (2.1703) grad: 0.2444 (0.2459) time: 0.4298 data: 0.0041 max mem: 22448 +train: [14] [100/400] eta: 0:02:22 lr: 0.000096 loss: 2.1832 (2.1755) grad: 0.2467 (0.2480) time: 0.4585 data: 0.0042 max mem: 22448 +train: [14] [120/400] eta: 0:02:11 lr: 0.000095 loss: 2.1557 (2.1697) grad: 0.2505 (0.2489) time: 0.4526 data: 0.0043 max mem: 22448 +train: [14] [140/400] eta: 0:02:01 lr: 0.000093 loss: 2.1340 (2.1685) grad: 0.2576 (0.2505) time: 0.4346 data: 0.0043 max mem: 22448 +train: [14] [160/400] eta: 0:01:50 lr: 0.000092 loss: 2.1424 (2.1688) grad: 0.2554 (0.2510) time: 0.4311 data: 0.0042 max mem: 22448 +train: [14] [180/400] eta: 0:01:41 lr: 0.000090 loss: 2.1464 (2.1662) grad: 0.2524 (0.2513) time: 0.4451 data: 0.0042 max mem: 22448 +train: [14] [200/400] eta: 0:01:31 lr: 0.000089 loss: 2.1358 (2.1660) grad: 0.2527 (0.2520) time: 0.4368 data: 0.0043 max mem: 22448 +train: [14] [220/400] eta: 0:01:22 lr: 0.000088 loss: 2.1684 (2.1672) grad: 0.2578 (0.2526) time: 0.4400 data: 0.0042 max mem: 22448 +train: [14] [240/400] eta: 0:01:12 lr: 0.000086 loss: 2.1688 (2.1715) grad: 0.2582 (0.2530) time: 0.4304 data: 0.0040 max mem: 22448 +train: [14] [260/400] eta: 0:01:03 lr: 0.000085 loss: 2.1963 (2.1733) grad: 0.2582 (0.2531) time: 0.4343 data: 0.0039 max mem: 22448 +train: [14] [280/400] eta: 0:00:54 lr: 0.000083 loss: 2.1963 (2.1730) grad: 0.2572 (0.2529) time: 0.4308 data: 0.0041 max mem: 22448 +train: [14] [300/400] eta: 0:00:44 lr: 0.000082 loss: 2.2029 (2.1778) grad: 0.2567 (0.2531) time: 0.4345 data: 0.0042 max mem: 22448 +train: [14] [320/400] eta: 0:00:35 lr: 0.000081 loss: 2.2029 (2.1794) grad: 0.2587 (0.2536) time: 0.4338 data: 0.0043 max mem: 22448 +train: [14] [340/400] eta: 0:00:26 lr: 0.000079 loss: 2.1900 (2.1797) grad: 0.2642 (0.2542) time: 0.4456 data: 0.0042 max mem: 22448 +train: [14] [360/400] eta: 0:00:17 lr: 0.000078 loss: 2.1876 (2.1804) grad: 0.2602 (0.2543) time: 0.4385 data: 0.0041 max mem: 22448 +train: [14] [380/400] eta: 0:00:08 lr: 0.000076 loss: 2.1844 (2.1792) grad: 0.2526 (0.2542) time: 0.4300 data: 0.0041 max mem: 22448 +train: [14] [399/400] eta: 0:00:00 lr: 0.000075 loss: 2.1437 (2.1795) grad: 0.2549 (0.2547) time: 0.4341 data: 0.0039 max mem: 22448 +train: [14] Total time: 0:02:58 (0.4468 s / it) +train: [14] Summary: lr: 0.000075 loss: 2.1437 (2.1795) grad: 0.2549 (0.2547) +eval (validation): [14] [ 0/85] eta: 0:04:29 time: 3.1750 data: 2.9439 max mem: 22448 +eval (validation): [14] [20/85] eta: 0:00:32 time: 0.3657 data: 0.0050 max mem: 22448 +eval (validation): [14] [40/85] eta: 0:00:19 time: 0.3546 data: 0.0035 max mem: 22448 +eval (validation): [14] [60/85] eta: 0:00:10 time: 0.3504 data: 0.0042 max mem: 22448 +eval (validation): [14] [80/85] eta: 0:00:01 time: 0.3377 data: 0.0039 max mem: 22448 +eval (validation): [14] [84/85] eta: 0:00:00 time: 0.3248 data: 0.0037 max mem: 22448 +eval (validation): [14] Total time: 0:00:32 (0.3865 s / it) +cv: [14] best hparam: (0.38, 1.0) (018) ('018_lr3.8e-01_wd1.0e+00') loss: 2.375 acc: 0.289 f1: 0.228 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [15] [ 0/400] eta: 0:22:03 lr: nan time: 3.3083 data: 2.9350 max mem: 22448 +train: [15] [ 20/400] eta: 0:03:46 lr: 0.000074 loss: 2.1332 (2.1299) grad: 0.2391 (0.2427) time: 0.4616 data: 0.0028 max mem: 22448 +train: [15] [ 40/400] eta: 0:03:08 lr: 0.000072 loss: 2.1279 (2.1281) grad: 0.2412 (0.2438) time: 0.4456 data: 0.0042 max mem: 22448 +train: [15] [ 60/400] eta: 0:02:47 lr: 0.000071 loss: 2.0955 (2.1214) grad: 0.2429 (0.2451) time: 0.4324 data: 0.0041 max mem: 22448 +train: [15] [ 80/400] eta: 0:02:33 lr: 0.000070 loss: 2.0964 (2.1168) grad: 0.2452 (0.2451) time: 0.4391 data: 0.0040 max mem: 22448 +train: [15] [100/400] eta: 0:02:21 lr: 0.000068 loss: 2.0964 (2.1121) grad: 0.2432 (0.2458) time: 0.4452 data: 0.0040 max mem: 22448 +train: [15] [120/400] eta: 0:02:11 lr: 0.000067 loss: 2.1279 (2.1191) grad: 0.2531 (0.2479) time: 0.4506 data: 0.0041 max mem: 22448 +train: [15] [140/400] eta: 0:02:01 lr: 0.000066 loss: 2.1572 (2.1283) grad: 0.2576 (0.2504) time: 0.4449 data: 0.0044 max mem: 22448 +train: [15] [160/400] eta: 0:01:50 lr: 0.000064 loss: 2.1352 (2.1282) grad: 0.2560 (0.2509) time: 0.4359 data: 0.0041 max mem: 22448 +train: [15] [180/400] eta: 0:01:40 lr: 0.000063 loss: 2.1556 (2.1356) grad: 0.2544 (0.2523) time: 0.4330 data: 0.0039 max mem: 22448 +train: [15] [200/400] eta: 0:01:31 lr: 0.000062 loss: 2.1556 (2.1354) grad: 0.2528 (0.2521) time: 0.4433 data: 0.0044 max mem: 22448 +train: [15] [220/400] eta: 0:01:21 lr: 0.000061 loss: 2.1347 (2.1350) grad: 0.2482 (0.2521) time: 0.4320 data: 0.0039 max mem: 22448 +train: [15] [240/400] eta: 0:01:12 lr: 0.000059 loss: 2.1286 (2.1357) grad: 0.2542 (0.2525) time: 0.4379 data: 0.0039 max mem: 22448 +train: [15] [260/400] eta: 0:01:03 lr: 0.000058 loss: 2.1695 (2.1400) grad: 0.2542 (0.2525) time: 0.4406 data: 0.0040 max mem: 22448 +train: [15] [280/400] eta: 0:00:54 lr: 0.000057 loss: 2.1461 (2.1376) grad: 0.2430 (0.2518) time: 0.4329 data: 0.0039 max mem: 22448 +train: [15] [300/400] eta: 0:00:45 lr: 0.000056 loss: 2.1026 (2.1371) grad: 0.2431 (0.2519) time: 0.4403 data: 0.0039 max mem: 22448 +train: [15] [320/400] eta: 0:00:35 lr: 0.000054 loss: 2.1319 (2.1374) grad: 0.2524 (0.2521) time: 0.4350 data: 0.0042 max mem: 22448 +train: [15] [340/400] eta: 0:00:26 lr: 0.000053 loss: 2.1319 (2.1375) grad: 0.2513 (0.2520) time: 0.4302 data: 0.0041 max mem: 22448 +train: [15] [360/400] eta: 0:00:17 lr: 0.000052 loss: 2.1319 (2.1373) grad: 0.2511 (0.2523) time: 0.4320 data: 0.0039 max mem: 22448 +train: [15] [380/400] eta: 0:00:08 lr: 0.000051 loss: 2.0891 (2.1341) grad: 0.2472 (0.2519) time: 0.4390 data: 0.0039 max mem: 22448 +train: [15] [399/400] eta: 0:00:00 lr: 0.000050 loss: 2.1013 (2.1351) grad: 0.2461 (0.2517) time: 0.4332 data: 0.0039 max mem: 22448 +train: [15] Total time: 0:02:58 (0.4467 s / it) +train: [15] Summary: lr: 0.000050 loss: 2.1013 (2.1351) grad: 0.2461 (0.2517) +eval (validation): [15] [ 0/85] eta: 0:04:35 time: 3.2360 data: 2.9990 max mem: 22448 +eval (validation): [15] [20/85] eta: 0:00:31 time: 0.3471 data: 0.0044 max mem: 22448 +eval (validation): [15] [40/85] eta: 0:00:18 time: 0.3512 data: 0.0035 max mem: 22448 +eval (validation): [15] [60/85] eta: 0:00:09 time: 0.3407 data: 0.0041 max mem: 22448 +eval (validation): [15] [80/85] eta: 0:00:01 time: 0.3254 data: 0.0038 max mem: 22448 +eval (validation): [15] [84/85] eta: 0:00:00 time: 0.3178 data: 0.0037 max mem: 22448 +eval (validation): [15] Total time: 0:00:32 (0.3766 s / it) +cv: [15] best hparam: (0.38, 1.0) (018) ('018_lr3.8e-01_wd1.0e+00') loss: 2.389 acc: 0.284 f1: 0.222 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [16] [ 0/400] eta: 0:21:22 lr: nan time: 3.2074 data: 2.8809 max mem: 22448 +train: [16] [ 20/400] eta: 0:03:39 lr: 0.000048 loss: 2.0589 (2.0871) grad: 0.2257 (0.2295) time: 0.4454 data: 0.0035 max mem: 22448 +train: [16] [ 40/400] eta: 0:03:03 lr: 0.000047 loss: 2.0609 (2.0859) grad: 0.2327 (0.2333) time: 0.4414 data: 0.0039 max mem: 22448 +train: [16] [ 60/400] eta: 0:02:45 lr: 0.000046 loss: 2.0604 (2.0783) grad: 0.2397 (0.2364) time: 0.4377 data: 0.0041 max mem: 22448 +train: [16] [ 80/400] eta: 0:02:32 lr: 0.000045 loss: 2.0993 (2.0949) grad: 0.2448 (0.2399) time: 0.4410 data: 0.0039 max mem: 22448 +train: [16] [100/400] eta: 0:02:20 lr: 0.000044 loss: 2.1187 (2.0941) grad: 0.2510 (0.2412) time: 0.4453 data: 0.0042 max mem: 22448 +train: [16] [120/400] eta: 0:02:10 lr: 0.000043 loss: 2.0801 (2.0946) grad: 0.2431 (0.2422) time: 0.4502 data: 0.0041 max mem: 22448 +train: [16] [140/400] eta: 0:02:00 lr: 0.000042 loss: 2.0676 (2.0952) grad: 0.2373 (0.2420) time: 0.4496 data: 0.0043 max mem: 22448 +train: [16] [160/400] eta: 0:01:50 lr: 0.000041 loss: 2.0786 (2.1012) grad: 0.2431 (0.2434) time: 0.4338 data: 0.0041 max mem: 22448 +train: [16] [180/400] eta: 0:01:40 lr: 0.000040 loss: 2.0983 (2.1022) grad: 0.2493 (0.2434) time: 0.4341 data: 0.0041 max mem: 22448 +train: [16] [200/400] eta: 0:01:31 lr: 0.000039 loss: 2.0883 (2.1008) grad: 0.2418 (0.2430) time: 0.4461 data: 0.0043 max mem: 22448 +train: [16] [220/400] eta: 0:01:21 lr: 0.000038 loss: 2.0883 (2.1016) grad: 0.2362 (0.2427) time: 0.4379 data: 0.0043 max mem: 22448 +train: [16] [240/400] eta: 0:01:12 lr: 0.000036 loss: 2.1005 (2.1010) grad: 0.2408 (0.2434) time: 0.4474 data: 0.0042 max mem: 22448 +train: [16] [260/400] eta: 0:01:03 lr: 0.000035 loss: 2.1118 (2.1046) grad: 0.2547 (0.2441) time: 0.4347 data: 0.0041 max mem: 22448 +train: [16] [280/400] eta: 0:00:54 lr: 0.000034 loss: 2.1162 (2.1043) grad: 0.2479 (0.2444) time: 0.4329 data: 0.0041 max mem: 22448 +train: [16] [300/400] eta: 0:00:45 lr: 0.000033 loss: 2.1102 (2.1066) grad: 0.2451 (0.2446) time: 0.4390 data: 0.0041 max mem: 22448 +train: [16] [320/400] eta: 0:00:35 lr: 0.000032 loss: 2.1437 (2.1095) grad: 0.2499 (0.2451) time: 0.4371 data: 0.0041 max mem: 22448 +train: [16] [340/400] eta: 0:00:26 lr: 0.000031 loss: 2.0944 (2.1081) grad: 0.2465 (0.2450) time: 0.4274 data: 0.0040 max mem: 22448 +train: [16] [360/400] eta: 0:00:17 lr: 0.000031 loss: 2.0914 (2.1088) grad: 0.2417 (0.2454) time: 0.4325 data: 0.0041 max mem: 22448 +train: [16] [380/400] eta: 0:00:08 lr: 0.000030 loss: 2.1234 (2.1082) grad: 0.2467 (0.2458) time: 0.4321 data: 0.0041 max mem: 22448 +train: [16] [399/400] eta: 0:00:00 lr: 0.000029 loss: 2.0847 (2.1077) grad: 0.2555 (0.2464) time: 0.4316 data: 0.0041 max mem: 22448 +train: [16] Total time: 0:02:58 (0.4461 s / it) +train: [16] Summary: lr: 0.000029 loss: 2.0847 (2.1077) grad: 0.2555 (0.2464) +eval (validation): [16] [ 0/85] eta: 0:04:37 time: 3.2603 data: 3.0271 max mem: 22448 +eval (validation): [16] [20/85] eta: 0:00:30 time: 0.3371 data: 0.0039 max mem: 22448 +eval (validation): [16] [40/85] eta: 0:00:18 time: 0.3460 data: 0.0032 max mem: 22448 +eval (validation): [16] [60/85] eta: 0:00:09 time: 0.3439 data: 0.0044 max mem: 22448 +eval (validation): [16] [80/85] eta: 0:00:01 time: 0.3282 data: 0.0040 max mem: 22448 +eval (validation): [16] [84/85] eta: 0:00:00 time: 0.3204 data: 0.0039 max mem: 22448 +eval (validation): [16] Total time: 0:00:31 (0.3743 s / it) +cv: [16] best hparam: (0.38, 1.0) (018) ('018_lr3.8e-01_wd1.0e+00') loss: 2.387 acc: 0.285 f1: 0.225 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [17] [ 0/400] eta: 0:21:40 lr: nan time: 3.2514 data: 2.9259 max mem: 22448 +train: [17] [ 20/400] eta: 0:03:41 lr: 0.000028 loss: 2.0590 (2.0455) grad: 0.2273 (0.2334) time: 0.4508 data: 0.0034 max mem: 22448 +train: [17] [ 40/400] eta: 0:03:07 lr: 0.000027 loss: 2.0590 (2.0648) grad: 0.2341 (0.2357) time: 0.4569 data: 0.0039 max mem: 22448 +train: [17] [ 60/400] eta: 0:02:49 lr: 0.000026 loss: 2.0810 (2.0757) grad: 0.2331 (0.2349) time: 0.4470 data: 0.0043 max mem: 22448 +train: [17] [ 80/400] eta: 0:02:34 lr: 0.000025 loss: 2.0497 (2.0621) grad: 0.2303 (0.2355) time: 0.4403 data: 0.0042 max mem: 22448 +train: [17] [100/400] eta: 0:02:23 lr: 0.000024 loss: 2.0528 (2.0710) grad: 0.2330 (0.2359) time: 0.4528 data: 0.0042 max mem: 22448 +train: [17] [120/400] eta: 0:02:12 lr: 0.000023 loss: 2.0743 (2.0692) grad: 0.2383 (0.2364) time: 0.4440 data: 0.0041 max mem: 22448 +train: [17] [140/400] eta: 0:02:01 lr: 0.000023 loss: 2.0574 (2.0689) grad: 0.2382 (0.2364) time: 0.4512 data: 0.0042 max mem: 22448 +train: [17] [160/400] eta: 0:01:51 lr: 0.000022 loss: 2.0683 (2.0679) grad: 0.2400 (0.2373) time: 0.4483 data: 0.0041 max mem: 22448 +train: [17] [180/400] eta: 0:01:41 lr: 0.000021 loss: 2.0615 (2.0666) grad: 0.2370 (0.2367) time: 0.4360 data: 0.0041 max mem: 22448 +train: [17] [200/400] eta: 0:01:32 lr: 0.000020 loss: 2.0524 (2.0679) grad: 0.2360 (0.2366) time: 0.4468 data: 0.0042 max mem: 22448 +train: [17] [220/400] eta: 0:01:22 lr: 0.000019 loss: 2.0800 (2.0702) grad: 0.2397 (0.2374) time: 0.4411 data: 0.0040 max mem: 22448 +train: [17] [240/400] eta: 0:01:13 lr: 0.000019 loss: 2.0960 (2.0693) grad: 0.2386 (0.2380) time: 0.4346 data: 0.0041 max mem: 22448 +train: [17] [260/400] eta: 0:01:03 lr: 0.000018 loss: 2.0248 (2.0696) grad: 0.2414 (0.2382) time: 0.4394 data: 0.0040 max mem: 22448 +train: [17] [280/400] eta: 0:00:54 lr: 0.000017 loss: 2.0637 (2.0706) grad: 0.2418 (0.2382) time: 0.4413 data: 0.0041 max mem: 22448 +train: [17] [300/400] eta: 0:00:45 lr: 0.000016 loss: 2.0992 (2.0717) grad: 0.2389 (0.2382) time: 0.4295 data: 0.0041 max mem: 22448 +train: [17] [320/400] eta: 0:00:36 lr: 0.000016 loss: 2.0788 (2.0706) grad: 0.2296 (0.2375) time: 0.4392 data: 0.0042 max mem: 22448 +train: [17] [340/400] eta: 0:00:27 lr: 0.000015 loss: 2.0341 (2.0700) grad: 0.2302 (0.2379) time: 0.4339 data: 0.0042 max mem: 22448 +train: [17] [360/400] eta: 0:00:18 lr: 0.000014 loss: 2.0668 (2.0704) grad: 0.2401 (0.2382) time: 0.4406 data: 0.0041 max mem: 22448 +train: [17] [380/400] eta: 0:00:08 lr: 0.000014 loss: 2.0675 (2.0697) grad: 0.2429 (0.2389) time: 0.4342 data: 0.0039 max mem: 22448 +train: [17] [399/400] eta: 0:00:00 lr: 0.000013 loss: 2.0416 (2.0684) grad: 0.2379 (0.2386) time: 0.4419 data: 0.0039 max mem: 22448 +train: [17] Total time: 0:02:59 (0.4498 s / it) +train: [17] Summary: lr: 0.000013 loss: 2.0416 (2.0684) grad: 0.2379 (0.2386) +eval (validation): [17] [ 0/85] eta: 0:04:38 time: 3.2806 data: 2.9915 max mem: 22448 +eval (validation): [17] [20/85] eta: 0:00:31 time: 0.3493 data: 0.0040 max mem: 22448 +eval (validation): [17] [40/85] eta: 0:00:19 time: 0.3572 data: 0.0036 max mem: 22448 +eval (validation): [17] [60/85] eta: 0:00:09 time: 0.3485 data: 0.0043 max mem: 22448 +eval (validation): [17] [80/85] eta: 0:00:01 time: 0.3432 data: 0.0042 max mem: 22448 +eval (validation): [17] [84/85] eta: 0:00:00 time: 0.3298 data: 0.0041 max mem: 22448 +eval (validation): [17] Total time: 0:00:32 (0.3861 s / it) +cv: [17] best hparam: (0.38, 1.0) (018) ('018_lr3.8e-01_wd1.0e+00') loss: 2.376 acc: 0.285 f1: 0.225 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [18] [ 0/400] eta: 0:21:23 lr: nan time: 3.2076 data: 2.8394 max mem: 22448 +train: [18] [ 20/400] eta: 0:03:40 lr: 0.000012 loss: 2.0695 (2.0819) grad: 0.2333 (0.2341) time: 0.4485 data: 0.0046 max mem: 22448 +train: [18] [ 40/400] eta: 0:03:05 lr: 0.000012 loss: 2.0604 (2.0568) grad: 0.2333 (0.2336) time: 0.4483 data: 0.0040 max mem: 22448 +train: [18] [ 60/400] eta: 0:02:46 lr: 0.000011 loss: 2.0181 (2.0458) grad: 0.2388 (0.2366) time: 0.4325 data: 0.0042 max mem: 22448 +train: [18] [ 80/400] eta: 0:02:31 lr: 0.000011 loss: 2.0181 (2.0438) grad: 0.2348 (0.2345) time: 0.4265 data: 0.0042 max mem: 22448 +train: [18] [100/400] eta: 0:02:19 lr: 0.000010 loss: 2.0423 (2.0437) grad: 0.2269 (0.2344) time: 0.4368 data: 0.0043 max mem: 22448 +train: [18] [120/400] eta: 0:02:09 lr: 0.000009 loss: 2.0279 (2.0397) grad: 0.2343 (0.2344) time: 0.4384 data: 0.0042 max mem: 22448 +train: [18] [140/400] eta: 0:01:59 lr: 0.000009 loss: 2.0423 (2.0439) grad: 0.2346 (0.2350) time: 0.4486 data: 0.0043 max mem: 22448 +train: [18] [160/400] eta: 0:01:49 lr: 0.000008 loss: 2.0423 (2.0439) grad: 0.2336 (0.2342) time: 0.4440 data: 0.0042 max mem: 22448 +train: [18] [180/400] eta: 0:01:40 lr: 0.000008 loss: 2.0287 (2.0430) grad: 0.2339 (0.2348) time: 0.4297 data: 0.0041 max mem: 22448 +train: [18] [200/400] eta: 0:01:30 lr: 0.000007 loss: 2.0421 (2.0429) grad: 0.2350 (0.2347) time: 0.4423 data: 0.0042 max mem: 22448 +train: [18] [220/400] eta: 0:01:21 lr: 0.000007 loss: 2.0421 (2.0438) grad: 0.2364 (0.2346) time: 0.4410 data: 0.0042 max mem: 22448 +train: [18] [240/400] eta: 0:01:12 lr: 0.000006 loss: 2.0624 (2.0473) grad: 0.2364 (0.2346) time: 0.4328 data: 0.0044 max mem: 22448 +train: [18] [260/400] eta: 0:01:02 lr: 0.000006 loss: 2.0728 (2.0482) grad: 0.2353 (0.2347) time: 0.4351 data: 0.0042 max mem: 22448 +train: [18] [280/400] eta: 0:00:53 lr: 0.000006 loss: 2.0488 (2.0477) grad: 0.2318 (0.2347) time: 0.4365 data: 0.0041 max mem: 22448 +train: [18] [300/400] eta: 0:00:44 lr: 0.000005 loss: 2.0220 (2.0473) grad: 0.2318 (0.2348) time: 0.4350 data: 0.0041 max mem: 22448 +train: [18] [320/400] eta: 0:00:35 lr: 0.000005 loss: 2.0604 (2.0506) grad: 0.2343 (0.2348) time: 0.4316 data: 0.0040 max mem: 22448 +train: [18] [340/400] eta: 0:00:26 lr: 0.000004 loss: 2.0526 (2.0483) grad: 0.2319 (0.2347) time: 0.4298 data: 0.0041 max mem: 22448 +train: [18] [360/400] eta: 0:00:17 lr: 0.000004 loss: 2.0312 (2.0486) grad: 0.2319 (0.2346) time: 0.4318 data: 0.0042 max mem: 22448 +train: [18] [380/400] eta: 0:00:08 lr: 0.000004 loss: 2.0438 (2.0487) grad: 0.2349 (0.2346) time: 0.4361 data: 0.0041 max mem: 22448 +train: [18] [399/400] eta: 0:00:00 lr: 0.000003 loss: 2.0361 (2.0476) grad: 0.2344 (0.2348) time: 0.4412 data: 0.0041 max mem: 22448 +train: [18] Total time: 0:02:57 (0.4446 s / it) +train: [18] Summary: lr: 0.000003 loss: 2.0361 (2.0476) grad: 0.2344 (0.2348) +eval (validation): [18] [ 0/85] eta: 0:04:31 time: 3.1912 data: 2.9622 max mem: 22448 +eval (validation): [18] [20/85] eta: 0:00:31 time: 0.3477 data: 0.0035 max mem: 22448 +eval (validation): [18] [40/85] eta: 0:00:18 time: 0.3504 data: 0.0032 max mem: 22448 +eval (validation): [18] [60/85] eta: 0:00:09 time: 0.3522 data: 0.0044 max mem: 22448 +eval (validation): [18] [80/85] eta: 0:00:01 time: 0.3370 data: 0.0041 max mem: 22448 +eval (validation): [18] [84/85] eta: 0:00:00 time: 0.3272 data: 0.0040 max mem: 22448 +eval (validation): [18] Total time: 0:00:32 (0.3811 s / it) +cv: [18] best hparam: (0.38, 1.0) (018) ('018_lr3.8e-01_wd1.0e+00') loss: 2.382 acc: 0.284 f1: 0.225 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [19] [ 0/400] eta: 0:21:47 lr: nan time: 3.2687 data: 2.9364 max mem: 22448 +train: [19] [ 20/400] eta: 0:03:53 lr: 0.000003 loss: 2.0509 (2.0530) grad: 0.2206 (0.2281) time: 0.4805 data: 0.0033 max mem: 22448 +train: [19] [ 40/400] eta: 0:03:14 lr: 0.000003 loss: 2.0237 (2.0337) grad: 0.2271 (0.2312) time: 0.4622 data: 0.0042 max mem: 22448 +train: [19] [ 60/400] eta: 0:02:53 lr: 0.000002 loss: 2.0470 (2.0519) grad: 0.2286 (0.2310) time: 0.4473 data: 0.0041 max mem: 22448 +train: [19] [ 80/400] eta: 0:02:36 lr: 0.000002 loss: 2.0786 (2.0585) grad: 0.2281 (0.2308) time: 0.4324 data: 0.0042 max mem: 22448 +train: [19] [100/400] eta: 0:02:24 lr: 0.000002 loss: 2.0730 (2.0604) grad: 0.2314 (0.2318) time: 0.4472 data: 0.0043 max mem: 22448 +train: [19] [120/400] eta: 0:02:13 lr: 0.000002 loss: 2.0509 (2.0606) grad: 0.2327 (0.2323) time: 0.4424 data: 0.0042 max mem: 22448 +train: [19] [140/400] eta: 0:02:02 lr: 0.000001 loss: 2.0396 (2.0565) grad: 0.2310 (0.2316) time: 0.4446 data: 0.0041 max mem: 22448 +train: [19] [160/400] eta: 0:01:52 lr: 0.000001 loss: 1.9995 (2.0500) grad: 0.2274 (0.2310) time: 0.4466 data: 0.0041 max mem: 22448 +train: [19] [180/400] eta: 0:01:41 lr: 0.000001 loss: 2.0063 (2.0476) grad: 0.2310 (0.2322) time: 0.4268 data: 0.0039 max mem: 22448 +train: [19] [200/400] eta: 0:01:32 lr: 0.000001 loss: 2.0126 (2.0460) grad: 0.2337 (0.2317) time: 0.4388 data: 0.0040 max mem: 22448 +train: [19] [220/400] eta: 0:01:22 lr: 0.000001 loss: 2.0206 (2.0435) grad: 0.2261 (0.2312) time: 0.4357 data: 0.0040 max mem: 22448 +train: [19] [240/400] eta: 0:01:13 lr: 0.000001 loss: 2.0230 (2.0416) grad: 0.2270 (0.2314) time: 0.4386 data: 0.0041 max mem: 22448 +train: [19] [260/400] eta: 0:01:03 lr: 0.000000 loss: 2.0170 (2.0400) grad: 0.2280 (0.2311) time: 0.4298 data: 0.0041 max mem: 22448 +train: [19] [280/400] eta: 0:00:54 lr: 0.000000 loss: 2.0768 (2.0435) grad: 0.2282 (0.2312) time: 0.4312 data: 0.0040 max mem: 22448 +train: [19] [300/400] eta: 0:00:45 lr: 0.000000 loss: 2.0768 (2.0429) grad: 0.2296 (0.2310) time: 0.4270 data: 0.0041 max mem: 22448 +train: [19] [320/400] eta: 0:00:36 lr: 0.000000 loss: 2.0410 (2.0450) grad: 0.2359 (0.2315) time: 0.4288 data: 0.0040 max mem: 22448 +train: [19] [340/400] eta: 0:00:26 lr: 0.000000 loss: 2.0804 (2.0471) grad: 0.2359 (0.2314) time: 0.4320 data: 0.0040 max mem: 22448 +train: [19] [360/400] eta: 0:00:17 lr: 0.000000 loss: 2.0628 (2.0472) grad: 0.2274 (0.2310) time: 0.4351 data: 0.0040 max mem: 22448 +train: [19] [380/400] eta: 0:00:08 lr: 0.000000 loss: 2.0401 (2.0471) grad: 0.2274 (0.2309) time: 0.4381 data: 0.0041 max mem: 22448 +train: [19] [399/400] eta: 0:00:00 lr: 0.000000 loss: 2.0458 (2.0490) grad: 0.2288 (0.2309) time: 0.4269 data: 0.0040 max mem: 22448 +train: [19] Total time: 0:02:58 (0.4470 s / it) +train: [19] Summary: lr: 0.000000 loss: 2.0458 (2.0490) grad: 0.2288 (0.2309) +eval (validation): [19] [ 0/85] eta: 0:04:32 time: 3.2079 data: 2.9120 max mem: 22448 +eval (validation): [19] [20/85] eta: 0:00:32 time: 0.3567 data: 0.0049 max mem: 22448 +eval (validation): [19] [40/85] eta: 0:00:18 time: 0.3465 data: 0.0040 max mem: 22448 +eval (validation): [19] [60/85] eta: 0:00:09 time: 0.3331 data: 0.0041 max mem: 22448 +eval (validation): [19] [80/85] eta: 0:00:01 time: 0.3322 data: 0.0041 max mem: 22448 +eval (validation): [19] [84/85] eta: 0:00:00 time: 0.3207 data: 0.0040 max mem: 22448 +eval (validation): [19] Total time: 0:00:32 (0.3768 s / it) +cv: [19] best hparam: (0.38, 1.0) (018) ('018_lr3.8e-01_wd1.0e+00') loss: 2.381 acc: 0.285 f1: 0.225 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +evaluating last checkpoint: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +eval model info: +{"score": 0.2851605758582503, "hparam": [0.38, 1.0], "hparam_id": 18, "epoch": 19, "is_best": false, "best_score": 0.290328534514581} +eval (train): [20] [ 0/509] eta: 0:23:56 time: 2.8215 data: 2.5795 max mem: 22448 +eval (train): [20] [ 20/509] eta: 0:03:55 time: 0.3651 data: 0.0040 max mem: 22448 +eval (train): [20] [ 40/509] eta: 0:03:16 time: 0.3515 data: 0.0038 max mem: 22448 +eval (train): [20] [ 60/509] eta: 0:02:57 time: 0.3511 data: 0.0043 max mem: 22448 +eval (train): [20] [ 80/509] eta: 0:02:45 time: 0.3525 data: 0.0043 max mem: 22448 +eval (train): [20] [100/509] eta: 0:02:36 time: 0.3724 data: 0.0044 max mem: 22448 +eval (train): [20] [120/509] eta: 0:02:27 time: 0.3548 data: 0.0045 max mem: 22448 +eval (train): [20] [140/509] eta: 0:02:18 time: 0.3569 data: 0.0044 max mem: 22448 +eval (train): [20] [160/509] eta: 0:02:10 time: 0.3683 data: 0.0043 max mem: 22448 +eval (train): [20] [180/509] eta: 0:02:02 time: 0.3439 data: 0.0048 max mem: 22448 +eval (train): [20] [200/509] eta: 0:01:54 time: 0.3575 data: 0.0043 max mem: 22448 +eval (train): [20] [220/509] eta: 0:01:46 time: 0.3573 data: 0.0044 max mem: 22448 +eval (train): [20] [240/509] eta: 0:01:38 time: 0.3616 data: 0.0044 max mem: 22448 +eval (train): [20] [260/509] eta: 0:01:31 time: 0.3791 data: 0.0044 max mem: 22448 +eval (train): [20] [280/509] eta: 0:01:24 time: 0.3731 data: 0.0043 max mem: 22448 +eval (train): [20] [300/509] eta: 0:01:16 time: 0.3468 data: 0.0043 max mem: 22448 +eval (train): [20] [320/509] eta: 0:01:09 time: 0.3558 data: 0.0043 max mem: 22448 +eval (train): [20] [340/509] eta: 0:01:01 time: 0.3628 data: 0.0045 max mem: 22448 +eval (train): [20] [360/509] eta: 0:00:54 time: 0.3607 data: 0.0044 max mem: 22448 +eval (train): [20] [380/509] eta: 0:00:47 time: 0.3574 data: 0.0043 max mem: 22448 +eval (train): [20] [400/509] eta: 0:00:39 time: 0.3588 data: 0.0041 max mem: 22448 +eval (train): [20] [420/509] eta: 0:00:32 time: 0.3470 data: 0.0040 max mem: 22448 +eval (train): [20] [440/509] eta: 0:00:25 time: 0.3524 data: 0.0041 max mem: 22448 +eval (train): [20] [460/509] eta: 0:00:17 time: 0.3619 data: 0.0045 max mem: 22448 +eval (train): [20] [480/509] eta: 0:00:10 time: 0.3684 data: 0.0041 max mem: 22448 +eval (train): [20] [500/509] eta: 0:00:03 time: 0.3488 data: 0.0043 max mem: 22448 +eval (train): [20] [508/509] eta: 0:00:00 time: 0.3394 data: 0.0037 max mem: 22448 +eval (train): [20] Total time: 0:03:05 (0.3641 s / it) +eval (validation): [20] [ 0/85] eta: 0:04:21 time: 3.0727 data: 2.8018 max mem: 22448 +eval (validation): [20] [20/85] eta: 0:00:34 time: 0.3995 data: 0.0059 max mem: 22448 +eval (validation): [20] [40/85] eta: 0:00:20 time: 0.3691 data: 0.0037 max mem: 22448 +eval (validation): [20] [60/85] eta: 0:00:10 time: 0.3609 data: 0.0044 max mem: 22448 +eval (validation): [20] [80/85] eta: 0:00:02 time: 0.3438 data: 0.0043 max mem: 22448 +eval (validation): [20] [84/85] eta: 0:00:00 time: 0.3332 data: 0.0038 max mem: 22448 +eval (validation): [20] Total time: 0:00:34 (0.4006 s / it) +eval (test): [20] [ 0/85] eta: 0:04:09 time: 2.9302 data: 2.6928 max mem: 22448 +eval (test): [20] [20/85] eta: 0:00:32 time: 0.3740 data: 0.0141 max mem: 22448 +eval (test): [20] [40/85] eta: 0:00:19 time: 0.3883 data: 0.0049 max mem: 22448 +eval (test): [20] [60/85] eta: 0:00:10 time: 0.3629 data: 0.0040 max mem: 22448 +eval (test): [20] [80/85] eta: 0:00:02 time: 0.3556 data: 0.0044 max mem: 22448 +eval (test): [20] [84/85] eta: 0:00:00 time: 0.3256 data: 0.0039 max mem: 22448 +eval (test): [20] Total time: 0:00:34 (0.4000 s / it) +eval (testid): [20] [ 0/82] eta: 0:04:07 time: 3.0161 data: 2.7463 max mem: 22448 +eval (testid): [20] [20/82] eta: 0:00:28 time: 0.3399 data: 0.0135 max mem: 22448 +eval (testid): [20] [40/82] eta: 0:00:17 time: 0.3511 data: 0.0046 max mem: 22448 +eval (testid): [20] [60/82] eta: 0:00:08 time: 0.3427 data: 0.0035 max mem: 22448 +eval (testid): [20] [80/82] eta: 0:00:00 time: 0.3377 data: 0.0039 max mem: 22448 +eval (testid): [20] [81/82] eta: 0:00:00 time: 0.3261 data: 0.0039 max mem: 22448 +eval (testid): [20] Total time: 0:00:30 (0.3761 s / it) +evaluating best checkpoint: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/nsd_cococlip__patch__attn/checkpoint-best.pth +eval model info: +{"score": 0.290328534514581, "hparam": [1.2, 1.0], "hparam_id": 25, "epoch": 5, "is_best": true, "best_score": 0.290328534514581} +eval (train): [20] [ 0/509] eta: 0:25:22 time: 2.9908 data: 2.7265 max mem: 22448 +eval (train): [20] [ 20/509] eta: 0:03:57 time: 0.3599 data: 0.0039 max mem: 22448 +eval (train): [20] [ 40/509] eta: 0:03:24 time: 0.3824 data: 0.0046 max mem: 22448 +eval (train): [20] [ 60/509] eta: 0:03:03 time: 0.3512 data: 0.0042 max mem: 22448 +eval (train): [20] [ 80/509] eta: 0:02:49 time: 0.3586 data: 0.0042 max mem: 22448 +eval (train): [20] [100/509] eta: 0:02:38 time: 0.3591 data: 0.0039 max mem: 22448 +eval (train): [20] [120/509] eta: 0:02:28 time: 0.3513 data: 0.0042 max mem: 22448 +eval (train): [20] [140/509] eta: 0:02:19 time: 0.3480 data: 0.0038 max mem: 22448 +eval (train): [20] [160/509] eta: 0:02:09 time: 0.3367 data: 0.0041 max mem: 22448 +eval (train): [20] [180/509] eta: 0:02:02 time: 0.3651 data: 0.0043 max mem: 22448 +eval (train): [20] [200/509] eta: 0:01:54 time: 0.3627 data: 0.0044 max mem: 22448 +eval (train): [20] [220/509] eta: 0:01:46 time: 0.3451 data: 0.0041 max mem: 22448 +eval (train): [20] [240/509] eta: 0:01:38 time: 0.3615 data: 0.0042 max mem: 22448 +eval (train): [20] [260/509] eta: 0:01:30 time: 0.3368 data: 0.0041 max mem: 22448 +eval (train): [20] [280/509] eta: 0:01:24 time: 0.3908 data: 0.0047 max mem: 22448 +eval (train): [20] [300/509] eta: 0:01:16 time: 0.3416 data: 0.0038 max mem: 22448 +eval (train): [20] [320/509] eta: 0:01:09 time: 0.3914 data: 0.0046 max mem: 22448 +eval (train): [20] [340/509] eta: 0:01:02 time: 0.3827 data: 0.0038 max mem: 22448 +eval (train): [20] [360/509] eta: 0:00:54 time: 0.3703 data: 0.0043 max mem: 22448 +eval (train): [20] [380/509] eta: 0:00:47 time: 0.3563 data: 0.0042 max mem: 22448 +eval (train): [20] [400/509] eta: 0:00:39 time: 0.3525 data: 0.0041 max mem: 22448 +eval (train): [20] [420/509] eta: 0:00:32 time: 0.3673 data: 0.0042 max mem: 22448 +eval (train): [20] [440/509] eta: 0:00:25 time: 0.3491 data: 0.0040 max mem: 22448 +eval (train): [20] [460/509] eta: 0:00:17 time: 0.3769 data: 0.0042 max mem: 22448 +eval (train): [20] [480/509] eta: 0:00:10 time: 0.3474 data: 0.0042 max mem: 22448 +eval (train): [20] [500/509] eta: 0:00:03 time: 0.3640 data: 0.0043 max mem: 22448 +eval (train): [20] [508/509] eta: 0:00:00 time: 0.3501 data: 0.0041 max mem: 22448 +eval (train): [20] Total time: 0:03:06 (0.3660 s / it) +eval (validation): [20] [ 0/85] eta: 0:04:06 time: 2.9020 data: 2.6200 max mem: 22448 +eval (validation): [20] [20/85] eta: 0:00:32 time: 0.3779 data: 0.0033 max mem: 22448 +eval (validation): [20] [40/85] eta: 0:00:19 time: 0.3752 data: 0.0042 max mem: 22448 +eval (validation): [20] [60/85] eta: 0:00:10 time: 0.3651 data: 0.0044 max mem: 22448 +eval (validation): [20] [80/85] eta: 0:00:01 time: 0.3555 data: 0.0041 max mem: 22448 +eval (validation): [20] [84/85] eta: 0:00:00 time: 0.3333 data: 0.0038 max mem: 22448 +eval (validation): [20] Total time: 0:00:33 (0.3987 s / it) +eval (test): [20] [ 0/85] eta: 0:03:57 time: 2.7916 data: 2.5295 max mem: 22448 +eval (test): [20] [20/85] eta: 0:00:28 time: 0.3242 data: 0.0047 max mem: 22448 +eval (test): [20] [40/85] eta: 0:00:18 time: 0.3991 data: 0.0041 max mem: 22448 +eval (test): [20] [60/85] eta: 0:00:09 time: 0.3531 data: 0.0039 max mem: 22448 +eval (test): [20] [80/85] eta: 0:00:01 time: 0.3533 data: 0.0037 max mem: 22448 +eval (test): [20] [84/85] eta: 0:00:00 time: 0.3427 data: 0.0036 max mem: 22448 +eval (test): [20] Total time: 0:00:32 (0.3857 s / it) +eval (testid): [20] [ 0/82] eta: 0:04:12 time: 3.0766 data: 2.8014 max mem: 22448 +eval (testid): [20] [20/82] eta: 0:00:28 time: 0.3307 data: 0.0031 max mem: 22448 +eval (testid): [20] [40/82] eta: 0:00:17 time: 0.3587 data: 0.0039 max mem: 22448 +eval (testid): [20] [60/82] eta: 0:00:08 time: 0.3533 data: 0.0042 max mem: 22448 +eval (testid): [20] [80/82] eta: 0:00:00 time: 0.3327 data: 0.0038 max mem: 22448 +eval (testid): [20] [81/82] eta: 0:00:00 time: 0.3190 data: 0.0036 max mem: 22448 +eval (testid): [20] Total time: 0:00:30 (0.3775 s / it) +eval results: + +| model | repr | clf | dataset | ckpt | epoch | lr | wd | hparam_id | hparam | split | loss | acc | acc_std | f1 | f1_std | +|:---------|:-------|:------|:-------------|:-------|--------:|--------:|-----:|------------:|:-----------|:-----------|-------:|--------:|----------:|--------:|----------:| +| flat_mae | patch | attn | nsd_cococlip | best | 5 | 0.00036 | 0.05 | 25 | [1.2, 1.0] | train | 2.0998 | 0.3627 | 0.0022714 | 0.29767 | 0.0024601 | +| flat_mae | patch | attn | nsd_cococlip | best | 5 | 0.00036 | 0.05 | 25 | [1.2, 1.0] | validation | 2.3559 | 0.29033 | 0.0055292 | 0.2203 | 0.0052431 | +| flat_mae | patch | attn | nsd_cococlip | best | 5 | 0.00036 | 0.05 | 25 | [1.2, 1.0] | test | 2.2803 | 0.30575 | 0.0054496 | 0.2349 | 0.0051929 | +| flat_mae | patch | attn | nsd_cococlip | best | 5 | 0.00036 | 0.05 | 25 | [1.2, 1.0] | testid | 2.3014 | 0.2996 | 0.0055057 | 0.23658 | 0.0051494 | + + +done! total time: 1:22:25 diff --git a/input_space_v3/flat_lr1e-3_1/eval_v2/nsd_cococlip__patch__attn/train_log.json b/input_space_v3/flat_lr1e-3_1/eval_v2/nsd_cococlip__patch__attn/train_log.json new file mode 100644 index 0000000000000000000000000000000000000000..4a6554b844c1f5669290768567d7ee7a1d33dca3 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_1/eval_v2/nsd_cococlip__patch__attn/train_log.json @@ -0,0 +1,20 @@ +{"epoch": 0, "train/lr": 2.987987987987988e-05, "train/loss": 3.1392525470256807, "train/grad": 0.17359873242676258, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.19360107421875, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.19255859375, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.1909130859375, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.189261474609375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.187783203125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.18584228515625, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.18371337890625, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.181453857421875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.178731689453125, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.176112060546875, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.17384521484375, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.17072998046875, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.168177490234375, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.164967041015625, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.1625439453125, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.16045654296875, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.158326416015625, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.15617431640625, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.15421630859375, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.15271240234375, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.1510791015625, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.149761962890625, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.1485400390625, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.14740478515625, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.146630859375, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.145755615234375, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.14532958984375, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.145089111328125, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.1448388671875, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.144833984375, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.144886474609375, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.145123291015625, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.145404052734375, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.145772705078125, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.146199951171875, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.14680419921875, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.14779296875, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.14902587890625, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.1497601318359374, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.1422860717773435, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.127023468017578, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.1105799865722656, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.086874542236328, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.0657582092285156, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.041067810058594, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.0205768585205077, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.0017049407958982, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.9840203094482423, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.97133113861084, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.027100367974489926, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.027015065122395755, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.026876575779169798, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.026743467254564165, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.026614529695361853, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.026444106129929423, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.026261575585231185, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.026069232332520186, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.025834075715392826, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.025607158257626, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.02540309906937182, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.02513365453109145, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.024908571764826776, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.024635793147608637, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.024421856408007443, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.024251816417090594, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.02407415207941085, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.023904330851510166, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.023750313888303936, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.023634170601144432, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.023519253325648606, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.02342578665353358, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.02334461215417832, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.023275155117735268, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.023220549752004445, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.02317090386990458, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.023138488652184607, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.02311717817559838, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.023096681302413345, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.023081476637162267, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.023065019622445105, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.023043730040080847, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.022997189918532966, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.02293068191036582, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.022816135049797594, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.02266861910931766, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.02248365316540003, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.022283222395926713, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.022078154939226807, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0221217227447778, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.022601114423014223, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.023211634363979102, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.023973247497342528, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.024694109451957047, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.025618963013403117, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.02697714526671916, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.02787487059831619, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.02931994715705514, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.030406816843897105, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.181513786315918, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.178419351577759, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1736934185028076, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1693387031555176, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1653382778167725, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1602251529693604, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1551363468170166, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.150207042694092, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1448214054107666, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.140191078186035, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1366617679595947, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.132798910140991, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1302363872528076, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1279921531677246, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.126796007156372, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1261484622955322, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1256918907165527, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.125485897064209, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.125471591949463, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.1256632804870605, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.126112937927246, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.1268835067749023, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.128115653991699, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.1298117637634277, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.131772041320801, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.133997678756714, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.1357598304748535, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.1369524002075195, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.1374404430389404, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.135967493057251, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.133683681488037, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.1315691471099854, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.129345417022705, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.1281473636627197, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.1285927295684814, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.1312577724456787, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.133967399597168, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.13053560256958, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.0935099124908447, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.900132417678833, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.7915408611297607, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.724696159362793, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.6438262462615967, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.637822151184082, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.6028895378112793, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.555043935775757, "validation/loss_046_lr3.6e+01_wd1.0e+00": 2.534088373184204, "validation/loss_047_lr4.3e+01_wd1.0e+00": 2.5894548892974854, "validation/loss_048_lr5.0e+01_wd1.0e+00": 2.6233630180358887, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.053156146179401995, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.056109265411590996, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.05740125507567368, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.057770394979697305, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.05906238464377999, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.05906238464377999, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.061461794019933555, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06256921373200443, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.059616094499815434, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.05887781469176818, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06404577334809892, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06699889258028793, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06847545219638243, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06847545219638243, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06995201181247693, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.07087486157253599, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.07161314138058324, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.07216685123661867, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.0725359911406423, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.07069029162052418, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.067921742340347, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.06570690291620525, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.0592469545957918, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.05204872646733112, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.051125876707272054, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.05094130675526024, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.05094130675526024, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.05057216685123662, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.05278700627537837, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.05998523440383906, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.06736803248431156, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.07216685123661867, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.0754891103728313, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.07511997046880768, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.07216685123661867, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.0710594315245478, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.0695828719084533, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.07807308970099668, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.14802510151347362, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.17792543373938724, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.19638242894056848, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.20487264673311184, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.20616463639719454, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.22093023255813954, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.23569582871908454, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.23421926910299004, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.22148394241417496, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.21982281284606867, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.011239637917098482, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.011523099867572856, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.01079947872301032, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.010689540223432548, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.011022832422476071, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.009503116305200773, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.010345158949662777, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.01137988611235624, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.013678628990398652, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.015057799772066768, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.018620325430799136, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.020620152966172096, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.02035754069285497, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.018456528892482785, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.017027194989768697, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.017407947487671136, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.017277921108316607, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.01711101027611842, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.016982605948750226, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.01682172160411313, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.017082025172177558, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.015747656871881472, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.014898382926717961, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.011978632144688722, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.006434658352140456, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.004518529999939216, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.0040478704681450196, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.004048582995951417, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.0040377247273799, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.006849602194880661, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.009433980121648268, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.011663510162121889, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.014274691801448235, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.01682075830351294, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.023141783622772513, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.01988562101456373, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.015983855801541, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.012655679816820685, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.02104253323120105, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.07273280285541256, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.09469470771325102, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.110927494324065, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.12672753443441045, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.12866154569331079, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.15082574333272905, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.157554646148411, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.15358438684443868, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.1445141313525218, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.14053050736232278, "id_best": 45, "lr_best": 0.0093, "wd_best": 0.05, "train/loss_best": 3.0205768585205077, "validation/loss_best": 2.555043935775757, "validation/acc_best": 0.23569582871908454, "validation/f1_best": 0.157554646148411} +{"epoch": 1, "train/lr": 8.993993993993998e-05, "train/loss": 2.972692084312439, "train/grad": 0.19051498532295227, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.1624755859375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.15859375, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.1534765625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.149310302734375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.145960693359375, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.142247314453125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.1391796875, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.1365966796875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.134334716796875, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.132708740234375, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.13165283203125, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.130694580078125, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.1301513671875, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.12976318359375, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.129608154296875, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.129508056640625, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.129471435546875, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.129322509765625, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.1291748046875, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.129019775390625, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.128839111328125, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.12871337890625, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.12857666015625, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.1285400390625, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.128468017578125, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.128369140625, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.128514404296875, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.128717041015625, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.128582763671875, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.1245343017578127, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.103487854003906, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.0644873046875, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.002059326171875, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.944541015625, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.874072036743164, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.8042467498779295, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.7359197998046874, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.6834075546264646, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.6289421463012697, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.5726789665222167, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.556726894378662, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.54983962059021, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.5421783447265627, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.540228929519653, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.5456554794311526, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.5616772747039795, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.5790791654586793, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.6353693342208864, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.702211604118347, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.023911932669579982, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.02357682291418314, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.023103955751284957, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.022723171771503986, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.022420087112113834, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.022095102020539343, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.02183101129718125, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.021626918273977936, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.021456902357749642, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.02135049202479422, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.021291931588202716, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.02125401355791837, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.02124672676436603, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.021262436541728675, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.02128817998804152, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.021315820976160468, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.021352134463377297, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.02139340650755912, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.021434601116925477, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.02147036904003471, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.021509398105554283, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.021545152766630053, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.02156907676719129, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.021569169545546173, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.021530590457841753, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.021427556327544152, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.02128708693664521, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.02111753570847213, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.020823517055250703, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.020453881192952394, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.020495884823612868, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.02105327425058931, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.022195187178440393, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.023270125240087508, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.02461390966549516, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.026150908078998326, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.02753246801905334, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.028726190472953023, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.030234013791196047, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.032512741070240735, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.033768273079767826, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.03511951974593103, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.03633657794445753, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.03727236486971378, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.038334304532036186, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.04009034143760801, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.042369031915441155, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.04623535017482936, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.05231617502868176, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.142345905303955, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.138617753982544, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1340720653533936, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1311123371124268, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1291990280151367, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.127612829208374, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.126638174057007, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1261322498321533, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1258506774902344, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.125741958618164, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1256821155548096, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1255972385406494, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1254591941833496, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.125235080718994, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1249589920043945, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.124708414077759, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.124450206756592, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.124371290206909, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1245956420898438, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.1251041889190674, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.126009702682495, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.127329111099243, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.1295320987701416, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.1329665184020996, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.1375749111175537, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.143646001815796, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.1480250358581543, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.149927854537964, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.1449010372161865, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.0801501274108887, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.88167142868042, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.7478878498077393, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.6312317848205566, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.5649051666259766, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.541248083114624, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.534132480621338, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.5010387897491455, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.484825611114502, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.4920501708984375, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.479928493499756, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.472128391265869, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.4925520420074463, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.513922691345215, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.5242371559143066, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.7111213207244873, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.72119140625, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.013406991958618, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.02494478225708, "validation/loss_048_lr5.0e+01_wd1.0e+00": 4.058297634124756, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06256921373200443, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06109265411590993, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.058693244739756366, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.059431524547803614, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.062384643779992616, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06404577334809892, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06423034330011074, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06423034330011074, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06423034330011074, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.0636766334440753, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06386120339608711, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06293835363602805, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06533776301218161, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06755260243632337, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06866002214839424, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06976744186046512, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.07032115171650055, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.07069029162052418, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.0710594315245478, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.07124400147655961, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.07013658176448874, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.07069029162052418, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.07198228128460686, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.07142857142857142, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.07475083056478406, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.07585825027685493, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.07733480989294943, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.10465116279069768, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.15337763012181616, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.17792543373938724, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.19730527870062753, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.21853082318198597, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.22554448135843486, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.23145071982281284, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.23938722775932078, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.24640088593576967, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.2454780361757106, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.2484311554078996, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.25489110372831303, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.24787744555186417, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.2368032484311554, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.2368032484311554, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.2203765227021041, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.21520856404577335, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.19785898855666298, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.18567737172388335, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.1511627906976744, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.009235206804642156, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.012542865995436312, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.017365496774206516, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.017316729069042983, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.015577499043777608, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.011796940436641479, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.009285998200256064, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.008201053051706741, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.008099758882862431, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.008293763165389758, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.009238813112403712, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.009255547480686755, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.009724909088656196, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.010445025010696466, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.01237747680721029, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.013260387646674423, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.014759232116007307, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.015151102477684199, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.015940176740943387, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.0168686868024592, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.018093549809959603, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.017784834033796184, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.01551055042559156, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.014617578179023196, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.014696495895067344, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.014910734381706618, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.01637949059256134, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.01819820986296426, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.020975276258047196, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.042195128248331826, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.06919443189684386, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.0930021848006664, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.11609485037452767, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.14390361845818336, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.15260753242822186, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.15866151435464346, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.1698713295815456, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.1792150509483457, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.18696405493547222, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.18708493703187404, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.18430445673202292, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.18195696196999753, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.17204408319361766, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.16776141474379538, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.15854026143796518, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.1371703515955635, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.1291798035155274, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.11554552992387139, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.09422202270919884, "id_best": 40, "lr_best": 0.0042, "wd_best": 0.05, "train/loss_best": 2.556726894378662, "validation/loss_best": 2.472128391265869, "validation/acc_best": 0.25489110372831303, "validation/f1_best": 0.18430445673202292} +{"epoch": 2, "train/lr": 0.00014999999999999988, "train/loss": 3.0023915481567385, "train/grad": 0.4414506637305021, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.137352294921875, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.1357080078125, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.1340283203125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.13324462890625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.13287109375, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.132645263671875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.1325439453125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.132418212890625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.132220458984375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.132161865234375, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.132010498046875, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.13169189453125, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.131409912109375, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.131007080078125, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.13056884765625, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.130234375, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.12987548828125, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.129510498046875, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.12895751953125, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.128707275390625, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.128243408203125, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.12773681640625, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.126875, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.12491943359375, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.11536376953125, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.062544708251953, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.9847590637207033, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.904845733642578, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.7956586837768556, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.671622085571289, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.584020538330078, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.52811653137207, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.4648335075378416, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.426520290374756, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.393260898590088, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.37009407043457, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.3531165885925294, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.3538123416900634, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.35777391910553, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.3598798513412476, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.3722158527374266, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.401365013122559, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.4255001544952393, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.452013475894928, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.5317028188705444, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.6382646024227143, "train/loss_046_lr3.6e+01_wd1.0e+00": 4.02204199552536, "train/loss_047_lr4.3e+01_wd1.0e+00": 4.56293288230896, "train/loss_048_lr5.0e+01_wd1.0e+00": 6.837987537384033, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.021737219584174454, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.021574689792469143, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.02142448167782277, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.02136183639988303, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.021341915000230072, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.021345546329393984, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.021363852112554014, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.021386447842232884, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.021412284090183677, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.021436483869329094, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.021458299141377212, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.021487093372270463, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.02151095315814018, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.021542677441611886, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.021566156800836324, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.02158342064358294, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.021600234699435533, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.021605292786844074, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.021590617937035858, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.02155491105746478, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.021476474478840827, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.021348884678445756, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.021146775470115245, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.020858617261983455, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.020648491154424846, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.021347160558216272, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.02270728333853185, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.023963797562755643, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.025814695712178946, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.028294492587447165, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.03018175756558776, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.031214985474944116, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.032505070148035886, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.03333875220268965, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.034486783538013696, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.035450260089710355, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.036674266923218964, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.036826763497665525, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.037624836936593055, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.03954772385768592, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.04059836266562342, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.04198467749170959, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.04386074660345912, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.04545882765203715, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0503491990827024, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.058289779871702196, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.11616495674476028, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.11244125341996551, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.14899252001196145, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.12800931930542, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.127181053161621, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1265299320220947, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1262731552124023, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.126178741455078, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1261279582977295, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1261496543884277, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1262104511260986, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1263976097106934, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1266093254089355, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.126840591430664, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1272571086883545, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1276707649230957, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1281938552856445, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.128570318222046, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.128714084625244, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.128445625305176, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.127614736557007, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1259946823120117, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.1240620613098145, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.1212477684020996, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.1179709434509277, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.113417625427246, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.099933385848999, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.0093493461608887, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.7557356357574463, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.648585557937622, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.5778677463531494, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.5032684803009033, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.4492805004119873, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.43279767036438, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.429711103439331, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.4304022789001465, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.4399194717407227, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.4554872512817383, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.499126434326172, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.5174288749694824, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.5039687156677246, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.4879446029663086, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.50217604637146, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.5325770378112793, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.5665550231933594, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.577097177505493, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.5393717288970947, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.616180658340454, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.827425241470337, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06478405315614617, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06496862310815799, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06533776301218161, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06533776301218161, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06533776301218161, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06441491325212255, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06626061277224068, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06626061277224068, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06699889258028793, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.0681063122923588, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06847545219638243, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.0681063122923588, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06773717238833518, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06626061277224068, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.0664451827242525, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06607604282022887, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06570690291620525, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.0651531930601698, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06478405315614617, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.06423034330011074, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.06496862310815799, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.06847545219638243, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.07179771133259505, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.08231819859726837, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.11941675895164268, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.17626430417128092, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.20579549649317092, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.23015873015873015, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.25193798449612403, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.26411960132890366, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.26744186046511625, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.26356589147286824, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.2643041712809155, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.25858250276854927, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.2589516426725729, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.25083056478405313, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.24880029531192321, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.25083056478405313, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.24861572535991142, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.24806201550387597, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.24215577703949798, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.2336655592469546, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.2484311554078996, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.2526762643041713, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.23717238833517904, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.21225544481358435, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.01206722125298093, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.011748493171046225, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.011544629954828661, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.011564629577483629, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.011661696509087771, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.011548639709079904, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.01261171822195734, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.012540156097387574, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.012544415244298135, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.012845563081038555, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.012672765706744936, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.012151358606546698, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.011759537218676131, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.01113950586343849, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.010482946957556333, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.010074854931089667, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.009705341467797257, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.008974344205585254, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.008837112619345201, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.008550094357849246, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.00916882529259488, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.011418530689336718, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.013580029086287327, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.018577462776855527, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.04231555441171029, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.08368749394351314, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.11782980726466573, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.14875235448301063, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.17107607422005322, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.18278842053836167, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.1890055313400061, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.1868863372940457, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.19241954070883202, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.191475594586948, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.19459967820310242, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.1854776004328528, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.18792426614831267, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.19108346069934753, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.1944673255380305, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.19532124405629323, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.1757405856281303, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.1724778449138056, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.1888688929203913, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.183633489845854, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.16545113801616526, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.1563482468286309, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 30, "lr_best": 0.00081, "wd_best": 0.05, "train/loss_best": 2.584020538330078, "validation/loss_best": 2.43279767036438, "validation/acc_best": 0.26744186046511625, "validation/f1_best": 0.1890055313400061} +{"epoch": 3, "train/lr": 0.0002100600600600602, "train/loss": 2.940648527145386, "train/grad": 0.4165573710948229, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.1309130859375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.130635986328125, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.1303857421875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.130185546875, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.130068359375, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.129769287109375, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.129427490234375, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.12914306640625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.1287109375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.128232421875, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.127730712890625, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.1271484375, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.12653564453125, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.1257080078125, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.125040283203125, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.12440185546875, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.123470458984375, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.1223681640625, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.120877685546875, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.118922119140625, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.1116552734375, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.07237548828125, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.9694830322265626, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.841422576904297, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.7094075775146482, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.590260009765625, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.52095329284668, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.4708802795410154, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.4181660270690917, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.3690771675109863, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.337549934387207, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.3116180992126463, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.280387420654297, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.264594068527222, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.24884108543396, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.245176079273224, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.246863117218018, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.2679780769348143, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.292057659626007, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.3356265377998353, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.378388812541962, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.4381271529197694, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.516228376626968, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.760014090538025, "train/loss_044_lr2.6e+01_wd1.0e+00": 5.614455050230026, "train/loss_045_lr3.1e+01_wd1.0e+00": 5.424895325899124, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.021261318158358335, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.021269346545450388, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.021290353522635995, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.021310026403516532, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.02132645065896213, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.02134472759440541, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.021361497826874257, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.0213800468435511, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.02140033783391118, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.021419370700605213, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.02143255442380905, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.021448321496136485, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.021456134323962033, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.021456600106321274, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.021441036737523973, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.021413314980454744, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.02135610781610012, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.021257376237772404, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.021095960261300208, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.020888065621256828, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.020615050536580384, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.02097147815860808, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.022600400443188846, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.024949263143353165, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.02762905481271446, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.02968759708106518, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.030721429623663424, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.03156385084614158, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.032569098938256505, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.03381259102374315, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.03473498529754579, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.03560689910314977, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.03685447418130934, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.038004534970968964, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0387810721155256, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.03969095934182405, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0410923882201314, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.041366761960089204, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.041924188258126376, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.04482591588050127, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.04772818148136139, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.05149060733616352, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.05574061894789338, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.11950548399239778, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.15592013977468014, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.15258963635191322, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1259613037109375, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1257717609405518, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.125535011291504, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.125328302383423, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1251015663146973, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.124816417694092, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1244781017303467, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1240811347961426, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1235532760620117, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1230058670043945, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1225554943084717, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1219632625579834, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.121497392654419, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.121062755584717, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1209633350372314, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1210978031158447, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1213741302490234, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1215717792510986, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1207122802734375, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.1159186363220215, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.0731520652770996, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.86676025390625, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.7098333835601807, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.6122663021087646, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.5361194610595703, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.474655866622925, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.446645498275757, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.440399169921875, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.4391086101531982, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.451408863067627, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.438004970550537, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.4363458156585693, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.4359593391418457, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.437253952026367, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.5027077198028564, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.54544734954834, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.546982526779175, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.6020724773406982, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.637118339538574, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.6141722202301025, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.64682674407959, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.733400344848633, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.7100906372070312, "validation/loss_043_lr2.2e+01_wd1.0e+00": 29.811935424804688, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06496862310815799, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06478405315614617, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06478405315614617, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06459948320413436, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06478405315614617, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.0681063122923588, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06718346253229975, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.0681063122923588, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06847545219638243, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06866002214839424, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06773717238833518, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06773717238833518, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06681432262827612, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.06921373200442968, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.09302325581395349, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.1539313399778516, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.18143226282761166, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.2087486157253599, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.22517534145441123, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.24603174603174602, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.2561830933923957, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.26153562200073827, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.26208933185677374, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.25507567368032485, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.2617201919527501, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.2646733111849391, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.26264304171280917, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.26947212993724623, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.2547065337763012, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.2467700258397933, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.25950535252860835, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.24197120708748615, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.23624953857511996, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.22978959025470652, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.2307124400147656, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.22425249169435216, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.2320044296788483, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.07142857142857142, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.010742613025303787, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.010600857995924242, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.010072888323166428, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.00955706226962687, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.009421563317052713, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.009372957998699695, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.009348861480070365, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.010180626286840534, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.010940372692822236, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.011889805374981346, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.012677945087428089, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.015277116069572787, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.01554148903601076, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.015536770910519178, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.016483660468246734, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.016852899312854417, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.017016253809890507, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.017537806539980105, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.01752050341619128, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.01906022477956278, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.04514810714336274, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.08101591243085694, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.10458874326951297, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.12901048997384512, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.14745353922050955, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.17198932295899613, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.1885255055052646, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.19869046996618925, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.20081210682195408, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.1973025620497636, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.20187405424943985, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.19927521357703656, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.18870135829487902, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.18727571335836832, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.1778912244748587, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.17755152361289062, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.1965830321268116, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.1882868923373089, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.17825405589112656, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.17643800866678702, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.16416136583641497, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.16242617388983052, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.17558453571406296, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.013836373635739441, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 33, "lr_best": 0.00129, "wd_best": 0.05, "train/loss_best": 2.264594068527222, "validation/loss_best": 2.437253952026367, "validation/acc_best": 0.26947212993724623, "validation/f1_best": 0.18727571335836832} +{"epoch": 4, "train/lr": 0.0002701201201201201, "train/loss": 2.850741684436798, "train/grad": 0.328072307407856, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.133289794921875, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.133087158203125, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.132724609375, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.132379150390625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.131978759765625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.131444091796875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.1308984375, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.130386962890625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.12962890625, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.12888427734375, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.12822021484375, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.127164306640625, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.126282958984375, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.124942626953125, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.123712158203125, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.122158203125, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.11993408203125, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.11331787109375, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.070218811035156, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.9658912658691405, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.8129348754882812, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.6747506713867186, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.577798309326172, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.4995265197753906, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.43536039352417, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.3797644996643066, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.3389005947113035, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.3095428848266604, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.2782636165618895, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.246368408203125, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.223666887283325, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.205392112731934, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.1908077001571655, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.192573275566101, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.190185458660126, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.198678376674652, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.221239056587219, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.253731529712677, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.311817413568497, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.3729182934761046, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.444008604288101, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.4750084221363067, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.6614712369441986, "train/loss_043_lr2.2e+01_wd1.0e+00": 6.995717487335205, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.021082884138450025, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.021093672728165983, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.021106756869703532, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.02111832447350025, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.021127638234756888, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.021139474334195257, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.021152268890291454, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.021164418677799404, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.021176816639490427, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.021184948743321, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.021187529717572033, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.021180736692622305, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.021156518175266682, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.021094739646650852, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.020998454233631492, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.02088138327933848, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.020679440372623502, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.020395970018580557, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.020698229707777502, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.022239927519112825, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.024966954682022334, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.027561116311699153, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.029338373513892294, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.03072497562505305, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0317318300716579, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.03286057821474969, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.03375536504201591, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.03439378815703094, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.03497509391978383, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.035848121149465444, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0367460738029331, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.03767566076479852, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.03895724492147565, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.04065959273837507, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.04197039000689983, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.04299965972080827, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.044669671319425105, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.044702156521379946, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.04747689737007022, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.051148459687829016, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.05483872372657061, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.05706161906942725, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.06968440670520067, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.12185581505298615, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.126620292663574, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1266911029815674, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.126779317855835, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.126866340637207, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.126915216445923, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.126889705657959, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1267805099487305, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1265764236450195, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1261680126190186, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.125575304031372, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1249184608459473, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.124011278152466, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1231558322906494, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1222610473632812, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.121840000152588, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.121495246887207, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1192474365234375, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.0935943126678467, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.902151107788086, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.727731943130493, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.623401403427124, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.5555269718170166, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.5149765014648438, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.46416974067688, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.4317855834960938, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.422696352005005, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.427333116531372, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.428945779800415, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.42794132232666, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.4117891788482666, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.416766881942749, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.447413206100464, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.486647605895996, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.520268201828003, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.568016767501831, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.595372438430786, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.6172468662261963, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.591059923171997, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.6297266483306885, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.751791477203369, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.9404726028442383, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.904083728790283, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.1434414386749268, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06404577334809892, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06478405315614617, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06404577334809892, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06423034330011074, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06459948320413436, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06423034330011074, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06478405315614617, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06496862310815799, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06441491325212255, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06478405315614617, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06589147286821706, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06829088224437062, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06866002214839424, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06921373200442968, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06921373200442968, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06995201181247693, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.0681063122923588, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.07936507936507936, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.14285714285714285, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.1819859726836471, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.20930232558139536, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.22462163159837578, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.23809523809523808, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.25396825396825395, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.266703580657069, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.2709486895533407, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.2707641196013289, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.2727943890734588, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.2751937984496124, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.2713178294573643, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.260797342192691, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.25101513473606496, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.25212255444813586, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.24529346622369877, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.23864894795127353, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.2294204503506829, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.23588039867109634, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.24031007751937986, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.23034330011074197, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.23920265780730898, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.21982281284606867, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.22683647102251753, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.19582871908453303, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.007594329761978726, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.008323003078905194, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.007640189525100997, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.008438882745714438, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.008808729822547172, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.008645014519086582, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.009249278190453604, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.009532399785920817, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.009964381207005135, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.010817193540116404, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.012219653929032149, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.01344821327415697, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.013464672225508609, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.013439150695519085, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.013251273732699784, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.014087014304634637, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.013477911076485239, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.026143564621186877, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.07220321327824068, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.10436617031892548, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.13057831835217754, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.15003534357000933, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.16528676926300734, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.18587620831245322, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.19672389465861698, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.20617039805142054, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.20983633838220883, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.21607841088599933, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.2204798961325701, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.22097731899799267, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.21791948441128703, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.20542360998368991, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.19572639656759086, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.18625398675592264, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.18236860075812858, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.17137849444967782, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.17609813112442887, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.1898340645694755, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.17776558197773717, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.17409578893364852, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.16661588218030737, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.16351071803473258, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.14634546341550106, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 28, "lr_best": 0.00057, "wd_best": 0.05, "train/loss_best": 2.2782636165618895, "validation/loss_best": 2.42794132232666, "validation/acc_best": 0.2751937984496124, "validation/f1_best": 0.2204798961325701} +{"epoch": 5, "train/lr": 0.00029891323817685334, "train/loss": 2.688588662147522, "train/grad": 0.2336794886738062, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.125609130859375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.125205078125, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.124656982421875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.124158935546875, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.123587646484375, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.122979736328125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.12242431640625, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.12164306640625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.120792236328125, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.119837646484375, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.118948974609375, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.117615966796875, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.116298828125, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.1141259765625, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.110899658203125, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.1022589111328127, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.0444970703125, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.8798524475097658, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.70186164855957, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.5999056243896486, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.5132670974731446, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.4435005378723145, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.3804580688476564, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.3223650550842283, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.2734223079681395, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.2290861797332764, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.194060764312744, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.1681390953063966, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.1429042530059816, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.1257900953292848, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.110765461921692, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.0963827085494997, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.0911774468421935, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.0881576335430143, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.103317866325378, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.122393243312836, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.139835543036461, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.184496678113937, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.232640187740326, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.289329653978348, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.337119481563568, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.436652581691742, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.547174838781357, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.171875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.021378315882757307, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.021389104332774876, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.021405574223026632, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.0214198713703081, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.021433205297216772, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.021450877478346227, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.02146523660980165, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.02147680876310915, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.021484529594890774, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.02148329365067184, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.021471860534511507, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.021435973327606918, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.02138001913204789, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.021249515493400394, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.021063652588054538, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.02089231040328741, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.02152724398765713, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.02395049190148711, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.02698069727048278, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.028919306471943854, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.0303930623549968, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.03159021395258606, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.03261111248284578, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.03384553992189467, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.03466505370102823, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.03544928116723895, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.03631803127937019, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.036890661101788284, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.03737417232245207, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.03853163110092282, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.03989533137530089, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.041186063457280396, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.04236712921410799, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.043635673951357604, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.04577784299850464, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.046868457831442355, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.04832785286009312, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.04852889420464635, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.049621276799589394, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.05250346006825566, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.05455790312960744, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.059099703989923, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.06452815108001232, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1244289875030518, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1241135597229004, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.12359619140625, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.123138189315796, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.122694253921509, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.12210750579834, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.121511220932007, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1208508014678955, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.120008707046509, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1190640926361084, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.118100643157959, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1166417598724365, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1151275634765625, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1124138832092285, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.106557846069336, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.0764410495758057, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.8870387077331543, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.696631669998169, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.5884664058685303, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.5161232948303223, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.4679336547851562, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.441128730773926, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.420684337615967, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.400651693344116, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.3712410926818848, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.3558778762817383, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.359550952911377, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.4054932594299316, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.449552536010742, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.43593692779541, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.438713312149048, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.4588959217071533, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.5555760860443115, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.6127943992614746, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.7127230167388916, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.7696123123168945, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.8501360416412354, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.7826220989227295, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.912100076675415, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.817326545715332, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.783535957336426, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.929976224899292, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.8589305877685547, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06404577334809892, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06496862310815799, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06662975267626431, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06662975267626431, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06995201181247693, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.0873015873015873, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.1421188630490956, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.18014027316352899, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.21114802510151348, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.22831303063861202, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.25396825396825395, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.2589516426725729, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.26707272056109266, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.2731635289774825, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.2853451458102621, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.290328534514581, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.2901439645625692, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.27906976744186046, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.27408637873754155, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.2794389073458841, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.27445551864156514, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.2768549280177187, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.2561830933923957, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.25230712440014763, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.23089700996677742, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.21539313399778517, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.21779254337393872, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.21705426356589147, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.19859726836471023, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.19859726836471023, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.20653377630121816, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.2100406053894426, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.21483942414174972, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.005596403075732063, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.005596564716887675, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.005436172296490433, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.0054346188812401, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.005175756241709612, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.005176113601490496, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.005164262274605987, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.005422175556848786, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.0063913316473579555, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.007172227434293285, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.007546034529678231, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.009120682392736935, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.010503965799152826, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.011997838884216528, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.016276514389380273, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.028933808551575877, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.06498657313003713, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.095886790377237, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.12602471234358448, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.15158611766077626, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.17572936338203504, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.18315352550595684, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.19202637793415142, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.19904173712625817, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.2114306669619017, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.22030143677357192, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.22319213292319953, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.21450959908555914, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.20921666453088061, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.21817278179828156, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.21938009407813533, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.22203039752260323, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.20441219718329218, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.19652098624465683, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.18172966531269527, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.1706386710902478, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.16747241793554254, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.16866981199573713, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.14758763702349736, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.1554614824461926, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.15791837261874522, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.1683079057785546, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.15046014671375593, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 25, "lr_best": 0.00035999999999999997, "wd_best": 0.05, "train/loss_best": 2.2290861797332764, "validation/loss_best": 2.3558778762817383, "validation/acc_best": 0.290328534514581, "validation/f1_best": 0.22030143677357192} +{"epoch": 6, "train/lr": 0.0002924170901991409, "train/loss": 2.6266488289833068, "train/grad": 0.23796417444944382, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.130648193359375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.13013427734375, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.12944580078125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.128577880859375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.127781982421875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.126904296875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.125859375, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.12478271484375, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.123402099609375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.121998291015625, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.12046875, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.1183544921875, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.115870361328125, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.108599853515625, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.071766357421875, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.943399658203125, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.752064971923828, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.625573196411133, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.52510009765625, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.454728012084961, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.3923168563842774, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.334673137664795, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.2755315017700197, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.214400873184204, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.169988193511963, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.131224374771118, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.0999047422409056, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.075185317993164, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.053189926147461, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.032346031665802, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.0117660367488863, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.999115378856659, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.998805458545685, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.000917866230011, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.014578448534012, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.0416960352659226, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.0746104645729067, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.118543807268143, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.1712179732322694, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.2587993586063386, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.308878712058067, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.369790942668915, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.4216028225421904, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.171875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.021343540367670357, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.021347151310183107, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.0213527358090505, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.02135767920408398, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.021360633661970496, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.02136106735095382, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.02135692802257836, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.021346468096598983, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.02132202038541436, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.02128244171384722, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.02122782834805548, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.021111456593498588, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.02095528883859515, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.020653068642131983, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.020856915907934308, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.02272352125030011, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.02580955335870385, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.0283266828302294, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.03036995026282966, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.03161320974119008, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.032066672220826146, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.032857588734477756, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.033870678301900624, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.03493588041514158, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.03548019666224718, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.03646635324694216, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0374279055558145, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.03813721626996994, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.03882157457992434, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.03983147358521819, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.04093492902815342, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.04218323061242699, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.04336290050297976, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.04493119766935706, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.04636810200288892, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.04727138938382268, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.04948397180065513, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.04945164903998375, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.050259446799755095, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.054781819954514505, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.056647829078137875, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.05918163377791643, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.05977683447301388, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1242284774780273, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1239686012268066, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1236178874969482, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1232783794403076, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.122955560684204, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1225404739379883, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1220901012420654, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1215457916259766, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.120790958404541, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1198904514312744, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1188182830810547, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1166586875915527, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.113109588623047, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.095904588699341, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.9732346534729004, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.7558751106262207, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.6323845386505127, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.533540964126587, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.4650585651397705, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.4304020404815674, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.4020626544952393, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.381906747817993, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.372901678085327, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.3771910667419434, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.3875372409820557, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.4030606746673584, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.4160706996917725, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.455145835876465, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.5027718544006348, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.5132460594177246, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.5156142711639404, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.5513579845428467, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.6103227138519287, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.572067975997925, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.640148878097534, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.659817934036255, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.725832462310791, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.6405136585235596, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.669543743133545, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.682940721511841, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.7458813190460205, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.776515245437622, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.7780532836914062, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06496862310815799, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.0664451827242525, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06607604282022887, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.0681063122923588, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06921373200442968, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.0695828719084533, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06902916205241787, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.07419712070874862, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.08877814691768181, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.12919896640826872, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.1729420450350683, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.21188630490956073, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.23624953857511996, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.2606127722406792, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.26965669988925806, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.27906976744186046, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.28349944629014395, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.2836840162421558, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.28165374677002586, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.27464008859357697, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.27205610926541157, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.2707641196013289, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.2631967515688446, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.26208933185677374, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.26135105204872644, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.2563676633444075, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.24363233665559247, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.23385012919896642, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.25101513473606496, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.24307862679955702, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.2412329272794389, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.22849760059062385, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.24916943521594684, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.23458840900701367, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.23440383905500184, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.22259136212624583, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.22997416020671835, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.24197120708748615, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.008536782769856442, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.008111624520829546, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.007958038410731649, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.008875299793186573, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.009454997897724129, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.010455538709413181, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.011755681555517997, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.012227101066678327, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.014680254196424275, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.015568369326513593, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.016737754583978203, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.018219965132237968, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.02282925373255915, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.03286538063165706, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.05933734065281502, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.09179062111206611, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.12992223609843778, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.16413891394149424, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.18806626254079162, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.1995831328086826, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.21035577398974747, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.21878332728229002, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.2218970921043046, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.22504620292157396, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.21946462570901015, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.21835816259568933, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.21499123251446248, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.2079793583391684, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.2099880557062425, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.2066379469783376, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.20985786618975932, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.19826179045631576, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.18778000523905905, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.20373493298695736, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.20406728195771953, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.19208023439635138, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.18605293305821513, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.19576570173887856, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.19639973929366308, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.18681966328675195, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.1759843161001332, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.17547825977339537, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.18245560300261474, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 22, "lr_best": 0.00021599999999999996, "wd_best": 0.05, "train/loss_best": 2.2755315017700197, "validation/loss_best": 2.372901678085327, "validation/acc_best": 0.2836840162421558, "validation/f1_best": 0.2218970921043046} +{"epoch": 7, "train/lr": 0.00027969249556793234, "train/loss": 2.552361829280853, "train/grad": 0.2437257481366396, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.12881103515625, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.128175048828125, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.12723876953125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.12621337890625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.125284423828125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.124122314453125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.122730712890625, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.121239013671875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.1193310546875, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.117166748046875, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.114951171875, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.1108172607421873, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.103201904296875, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.0382861328125, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.835341491699219, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.6868310546875, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.5800079345703124, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.4782462692260743, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.3948053169250487, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.3359613037109375, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.2800434112548826, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.2246502876281737, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.165866298675537, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.1086870050430297, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.0667171335220336, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.025275502204895, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.9907920098304748, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.9672272086143494, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.9437896490097046, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.92415935754776, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.9034856617450715, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.8916118824481964, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.8970257115364075, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.8930695754289628, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.9059598386287688, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.9417305326461791, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.9651867485046386, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.019613890647888, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.0769683796167375, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.150286665558815, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.2108325970172884, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.2456054508686067, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.3171349334716798, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.171875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.020817619273439048, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.02082101708743721, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.020822763121686877, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.02082219279836863, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.020816922802478075, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.020807320214807988, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.020789603269658983, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.020762279559858144, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.020713046863675116, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.02063958377111703, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.020545657710172235, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.02035746168345213, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.02012985685840249, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.020742840371094643, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.023752374947071074, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.026312398333102463, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.02846203887835145, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.03068958081305027, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.03200835034251213, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.03280825475230813, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.03332045423798263, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.034121762234717606, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.035203008046373725, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.036378117362037304, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.03710817604325712, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.038226384073495864, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.03911121169105172, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.040015577860176565, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.04117266023531556, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.04257779762148857, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.04390162751078606, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.04470267334952951, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.04583305055275559, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.04693563347682357, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.04828846976161003, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.050164913833141325, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.051324283704161644, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.05143781958147883, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.05197894487529993, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.05408914448693394, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.05568493694067001, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.055281584542244674, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.057580424901098014, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.124084711074829, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1238443851470947, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.12353253364563, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1232259273529053, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1229283809661865, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1226062774658203, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1221957206726074, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1217575073242188, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1211795806884766, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.120471477508545, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1194519996643066, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.11600399017334, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1027705669403076, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.9446098804473877, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.722900152206421, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.625359535217285, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.5310494899749756, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.462005853652954, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.420713186264038, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.3973588943481445, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.3804659843444824, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.372572898864746, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.3810694217681885, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.400179624557495, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.4047560691833496, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.4203367233276367, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.44008731842041, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.467487096786499, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.5115110874176025, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.5494818687438965, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.5932998657226562, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.6136953830718994, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.641526222229004, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.6847264766693115, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.745887279510498, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.698866128921509, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.7781288623809814, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.838763952255249, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.8389599323272705, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.8488895893096924, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.876149892807007, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.96978759765625, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.0066640377044678, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06441491325212255, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06404577334809892, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06496862310815799, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06570690291620525, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06626061277224068, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.0664451827242525, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06718346253229975, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06829088224437062, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.067921742340347, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06921373200442968, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06902916205241787, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.07050572166851236, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.0769656699889258, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.14451827242524917, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.1925064599483204, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.21631598375784422, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.24178663713547435, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.2574750830564784, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.2698412698412698, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.2751937984496124, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.2779623477297896, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.2777777777777778, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.2794389073458841, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.2757475083056478, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.27260981912144705, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.26799557032115173, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.266703580657069, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.26411960132890366, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.26596530084902176, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.26596530084902176, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.25489110372831303, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.24806201550387597, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.2382798080472499, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.23791066814322628, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.22997416020671835, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.24178663713547435, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.2264673311184939, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.22000738279808046, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.2264673311184939, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.21225544481358435, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.2201919527500923, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.2056109265411591, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.21040974529346623, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.009321046051467786, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.008959540137591824, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.009400666929496024, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.00992939777010006, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.010622977047796281, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.010928213569322392, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.010986430739778971, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.011785135900160443, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.011847477763101452, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.012533282776352982, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.012800694083290579, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.014065333602162932, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.01833997878405529, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.06169319809960785, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.10799993047397548, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.13053849458296413, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.16026795835874566, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.18137383632747062, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.19914982006262028, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.20853899421216007, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.21378473734780187, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.2158085232043303, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.21998855924028118, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.2213012458544837, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.22427083714491602, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.2268057356519669, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.22691816358033864, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.2250409495780992, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.22374688720946892, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.2191066964544605, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.20950682292763134, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.20669989138973213, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.19937945636466026, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.19325510046267483, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.19309422193110792, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.1934680183281273, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.18523405374099358, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.18186792877148705, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.18218163002521479, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.1628255828889418, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.16911483561534704, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.14279105444849582, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.14023515850954307, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 22, "lr_best": 0.00021599999999999996, "wd_best": 0.05, "train/loss_best": 2.165866298675537, "validation/loss_best": 2.3810694217681885, "validation/acc_best": 0.2794389073458841, "validation/f1_best": 0.21998855924028118} +{"epoch": 8, "train/lr": 0.0002612959497061927, "train/loss": 2.4892881047725677, "train/grad": 0.2509524939209223, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.1248388671875, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.124107666015625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.123094482421875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.1219580078125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.121014404296875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.11962158203125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.118299560546875, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.116619873046875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.11457275390625, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.111929931640625, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.10906982421875, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.10049072265625, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.06052001953125, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.8298500061035154, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.663228759765625, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.5718523406982423, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.4784884643554688, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.393228874206543, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.3210029220581054, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.265447540283203, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.209297752380371, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.154127097129822, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.0951972818374633, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.0312209510803223, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.9878764212131501, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.9435279989242553, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.9065213298797608, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.8789090359210967, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.853274382352829, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.8258578151464462, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.7979517167806625, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.779903923869133, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.784189823269844, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.7744258064031602, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.7860173839330673, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.8157453066110611, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.8537877255678177, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.9213426035642625, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.9865056550502778, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.0420779752731324, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.1013022631406786, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.1730779337882997, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.2524953830242156, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.171875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.02151522634550929, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.021519936257973313, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.021522032949142157, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.021523309308104217, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.02151926335413009, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.021508368542417885, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.02148768138606101, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.021452007214538753, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.021388295372016728, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.021292416625656188, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.021164754386991263, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.020914897951297463, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.021146878693252803, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.024438751777634025, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.02757056343369186, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.029432361023500563, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.03145168550312519, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.033155582416802644, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.034108905661851166, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.03483258806169033, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.03520324802957475, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.03582896639592945, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.036742343287914994, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.03780113646760583, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.03863947957754135, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.04016167930327356, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.04129407614469528, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.04212207157164812, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.04336176285520196, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.04462350001558661, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.045999730564653875, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0470300149358809, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.04778725504875183, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.04833725158125162, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.04911380210891366, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.05020002344623208, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.051135511789470914, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.05149981576949358, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.05134105710312724, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.05277072770521045, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.055019896049052476, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.055736988727003334, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.05784900654107332, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1236085891723633, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1232149600982666, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.122633695602417, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.122016668319702, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1214470863342285, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1206612586975098, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1197121143341064, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.118640661239624, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.117051124572754, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1148898601531982, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1116690635681152, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.097604274749756, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.008558750152588, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.73762845993042, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.6192569732666016, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.5396738052368164, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.4762392044067383, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.4377591609954834, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.4173696041107178, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.4085960388183594, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.4096884727478027, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.41743803024292, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.4354476928710938, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.4588193893432617, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.4664688110351562, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.4981160163879395, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.534721612930298, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.558152198791504, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.592139482498169, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.6205673217773438, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.6565134525299072, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.671694278717041, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.734755754470825, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.8038997650146484, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.875764846801758, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.9257874488830566, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.0228078365325928, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.965759038925171, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.004652500152588, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.9961695671081543, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.8512558937072754, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.8602840900421143, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.8159000873565674, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06496862310815799, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06459948320413436, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06570690291620525, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06570690291620525, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06589147286821706, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06866002214839424, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06884459210040605, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06902916205241787, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.07124400147655961, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.07235142118863049, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.082687338501292, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.12993724621631597, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.17571059431524547, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.21188630490956073, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.23385012919896642, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.25193798449612403, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.2643041712809155, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.2724252491694352, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.27353266888150607, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.2705795496493171, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.271686969361388, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.26854928017718716, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.26596530084902176, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.260797342192691, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.25839793281653745, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.25452196382428943, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.2530454042081949, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.24750830564784054, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.24916943521594684, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.24806201550387597, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.24806201550387597, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.2532299741602067, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.24178663713547435, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.23421926910299004, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.22535991140642303, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.2203765227021041, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.2187153931339978, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.23477297895902546, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.21650055370985605, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.2277593207825766, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.21779254337393872, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.22443706164636398, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.008299032601433068, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.009880898268117836, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.010035185451208652, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.011736435514158178, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.011740143690911689, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.012412832147907922, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.014904075688157747, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.016257485852366835, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.01724679753356423, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.019900277750486268, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.021205579956789473, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.030349065774664518, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.05916053244675077, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.095322195750983, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.1314325527041136, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.1590432655562818, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.18215164443237372, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.19629099584306353, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.20961723698753879, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.21365443760399702, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.2123700435190304, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.21551834403092807, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.2147767526297865, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.2152916904176386, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.21032059147299229, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.20908118763678496, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.20884948684619173, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.20820509655589428, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.20063920238993524, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.19797161422935727, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.19743437538520645, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.197302341969288, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.19265052330060475, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.19057667510386897, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.18263376325757386, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.16810728742949665, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.1643760046293683, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.14880373916715786, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.17063114878184496, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.15802282608450507, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.17411084482835468, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.16377930203392232, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.16793304224173564, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 19, "lr_best": 0.00013199999999999998, "wd_best": 0.05, "train/loss_best": 2.265447540283203, "validation/loss_best": 2.4085960388183594, "validation/acc_best": 0.27353266888150607, "validation/f1_best": 0.21365443760399702} +{"epoch": 9, "train/lr": 0.00023803200426111704, "train/loss": 2.446795401573181, "train/grad": 0.25578162468969823, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.123048095703125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.122265625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.120921630859375, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.119708251953125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.118426513671875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.116697998046875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.114837646484375, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.11285400390625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.110028076171875, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.10644287109375, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.101278076171875, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.0725439453125, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.9297467041015626, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.6926890563964845, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.5812132263183596, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.4990462493896484, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.4181234359741213, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.3416443061828613, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.273339729309082, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.219730920791626, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.165560369491577, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.112092957496643, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.050766019821167, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.9846423530578614, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.9380666851997375, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.8869967007637023, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.8463123226165772, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.8158399891853332, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.779349948167801, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.7453036689758301, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.7085095965862274, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.6933101582527161, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.701883156299591, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.7011818182468414, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.718662679195404, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.744099995493889, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.78611891746521, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.840457080602646, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.9248237425088883, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.9977021986246108, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.078287073969841, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.1383841848373413, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.2087890869379043, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.171875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.021399198984727263, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.02140046569518745, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.021398352207615972, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.02139273494016379, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.021383578795939683, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.02136348854750395, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.021329379617236556, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.021279839449562132, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.0211922259721905, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.021061348258517684, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.020891047273762522, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.02085464500822127, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.02288879214785993, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.02675423813983798, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.029101595813408494, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.030713846366852524, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.032311502229422334, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.03357305380515754, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.03455735540948808, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.03526945130899548, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.035684400722384456, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.036339173717424275, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.03733731422573328, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.03857919936068356, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.03956369549036026, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.04101089639589191, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.042306003533303736, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.04333898682147264, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.044530988615006206, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.045716864578425886, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.04691748118028045, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0478821774199605, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0486892076022923, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.050234199333935976, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0511358099617064, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.052283182293176654, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.05263871755450964, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.05176020100712776, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0521954346075654, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.053303299956023696, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.05628518523648381, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.05604205578565598, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.05776566678658128, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1229617595672607, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1225342750549316, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1218864917755127, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1212692260742188, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1206777095794678, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.11979603767395, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.11879825592041, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1175544261932373, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.115541934967041, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.112346887588501, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1058545112609863, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.050727605819702, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.844974994659424, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.652071475982666, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.552778959274292, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.4899203777313232, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.4425196647644043, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.408996343612671, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.387688398361206, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.3782262802124023, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.380936861038208, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.3895018100738525, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.405075788497925, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.4291627407073975, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.4471325874328613, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.497136116027832, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.536630153656006, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.565925359725952, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.597231149673462, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.607921838760376, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.6956374645233154, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.7190065383911133, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.7742204666137695, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.818964958190918, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.8524882793426514, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.865615129470825, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.9174275398254395, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.8360559940338135, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.824589729309082, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.753138303756714, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.746809959411621, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.728060245513916, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.749790668487549, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06441491325212255, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.0651531930601698, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06570690291620525, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06607604282022887, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06736803248431156, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06718346253229975, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06847545219638243, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06995201181247693, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.07069029162052418, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.0725359911406423, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.07751937984496124, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.11184939091915837, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.1598375784422296, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.19582871908453303, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.2277593207825766, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.24363233665559247, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.26005906238464377, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.2739018087855297, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.2763012181616833, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.27999261720191954, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.2822074566260613, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.2763012181616833, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.26854928017718716, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.2707641196013289, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.26596530084902176, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.2622739018087855, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.26005906238464377, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.2513842746400886, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.24880029531192321, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.2547065337763012, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.2368032484311554, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.24012550756736803, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.22960502030269472, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.23735695828719083, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.23385012919896642, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.22868217054263565, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.23015873015873015, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.23089700996677742, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.22665190107050573, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.24031007751937986, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.22683647102251753, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.23126614987080105, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.2262827611664821, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.009801582478945444, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.010880033100577405, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.01156832735041905, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.01271664025679758, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.013774987602580288, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.01422714918386375, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.01567105690471406, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.017188968653457322, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.01861204350627746, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.020344976778810673, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.024617103123555324, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.047868110140777874, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.07924571928062919, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.11224416276324627, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.14462521145437723, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.1637426986231815, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.18396425490778998, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.20070184070795163, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.2045509467535466, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.2152775205618619, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.22028633716332782, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.21737728068377826, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.2114513356506634, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.21905611458615862, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.21931107228867056, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.21862335387823006, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.22098280656221783, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.21470981826508803, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.2161465840771005, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.2210985719231885, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.20776571729151172, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.20931478084616909, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.19628135917965492, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.1993399466279423, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.18781390381161764, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.18382248614923324, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.18632281822291039, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.18176570851195006, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.1736082486950481, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.1878705592515861, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.18171776843934007, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.19817334130154848, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.18687468402398147, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 20, "lr_best": 0.000156, "wd_best": 0.05, "train/loss_best": 2.165560369491577, "validation/loss_best": 2.380936861038208, "validation/acc_best": 0.2822074566260613, "validation/f1_best": 0.22028633716332782} +{"epoch": 10, "train/lr": 0.00021091808096876188, "train/loss": 2.3782557821273804, "train/grad": 0.25431209467351434, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.1226513671875, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.1216357421875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.120184326171875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.1187890625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.11744140625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.115643310546875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.11355224609375, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.11121826171875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.107781982421875, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.10298828125, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.09263671875, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.001746826171875, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.788548889160156, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.6195445251464844, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.5149674224853515, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.43890079498291, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.3623638916015626, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.2855637741088866, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.214009304046631, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.156917915344238, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.0999638748168947, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.0432902860641478, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.9791166257858277, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.906499478816986, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.8545930624008178, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.7934709346294404, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.7432635039091111, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.7036768901348114, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.6608427900075913, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.624696142077446, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.589973088502884, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.5720553779602051, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.572642630338669, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.5632404679059981, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.578085646033287, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.6031397151947022, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.642532199025154, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.7302082163095474, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.7955093955993653, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.852486326098442, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.9254229813814163, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.9885613983869552, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.0529284185171126, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.171875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.02107007267419249, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.021070074094459414, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.021064437767490743, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.02105470335111022, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.021039120173081755, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.021012859181500972, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.020974282883107664, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.02091494747437537, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.020809117672033608, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.02065358860883862, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.020483668688684703, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.0215195940900594, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.024432993391528726, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.027865248899906873, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.030028815688565372, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.031468644104897976, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.032807454634457826, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.03412319491617381, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.035120451413095, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.03576446725055575, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.03624341705814004, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.03687337558716536, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.03792205736041069, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.039152685832232234, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.04003159588202834, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.04127996711060405, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.04220781078562141, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.04324821287766099, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.044776502382010225, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.046528390049934386, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.04819394974038005, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.04909787748008967, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.049437211770564315, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.050874637607485056, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.051756685692816974, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.05218303542584181, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.05247008936479688, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.052066885959357025, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.051205334234982726, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.05151024244725704, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.05343323213979602, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.052185956686735153, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.05226140120998025, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1232495307922363, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1228861808776855, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.122284173965454, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.121659994125366, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.121016502380371, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1200568675994873, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.118835687637329, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.117260217666626, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.114473819732666, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1092867851257324, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.0942187309265137, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.950683832168579, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.73824405670166, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.5969367027282715, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.511540174484253, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.468106508255005, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.433544635772705, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.404876947402954, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.385514974594116, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.3769466876983643, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.3843584060668945, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.3975374698638916, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.4242823123931885, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.463606834411621, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.5114309787750244, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.560042142868042, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.589433431625366, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.653128147125244, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.74638295173645, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.7979214191436768, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.812795877456665, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.880821466445923, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.9353604316711426, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.92293381690979, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.942591905593872, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.9934213161468506, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.0476701259613037, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.926377534866333, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.9415371417999268, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.819498062133789, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.9573380947113037, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.9403693675994873, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.944187641143799, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06441491325212255, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.0651531930601698, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06552233296419344, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.0651531930601698, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06533776301218161, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06589147286821706, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06662975267626431, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.07069029162052418, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.07825765965300849, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.14008859357696568, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.18253968253968253, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.22111480251015134, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.24178663713547435, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.2528608342561831, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.2681801402731635, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.2792543373938723, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.28497600590623845, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.2853451458102621, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.2833148763381321, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.2766703580657069, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.27297895902547065, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.2663344407530454, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.25950535252860835, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.25064599483204136, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.24916943521594684, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.24141749723145073, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.2321889996308601, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.23034330011074197, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.2307124400147656, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.23606496862310816, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.2321889996308601, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.2397563676633444, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.2307124400147656, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.2249907715023994, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.20967146548541898, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.22868217054263565, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.21963824289405684, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.22185308231819859, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.20007382798080472, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.21188630490956073, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.2129937246216316, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.008749434631086149, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.00900715673087247, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.009668608273178496, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.01049574624791477, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.01120962011906138, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.011845001745203636, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.012459806003185641, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.012844062192350918, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.014195849181546226, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.018431922011201543, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.02485294125056565, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.06410073643044566, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.10100549811632153, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.13715239520004557, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.16255598940591723, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.1785074053159176, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.19707677247618807, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.21103702585693493, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.22106068088182176, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.22572017824662227, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.22578388171097974, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.22298128622454408, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.21940808019095084, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.21622409109245377, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.21263835187243166, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.20393018424095097, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.20617325424082647, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.19910826884769803, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.19351201624641967, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.1948100838948437, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.19794146795430811, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.19709535534551895, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.1909337959868261, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.19628433848644058, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.19027949027345636, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.18312131306938237, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.17474099370060617, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.18997794624430694, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.18119700038723516, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.19399823105311467, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.166869651835947, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.1777063781320567, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.16357596739481903, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 19, "lr_best": 0.00013199999999999998, "wd_best": 0.05, "train/loss_best": 2.156917915344238, "validation/loss_best": 2.3769466876983643, "validation/acc_best": 0.2853451458102621, "validation/f1_best": 0.22572017824662227} +{"epoch": 11, "train/lr": 0.00018113997589164516, "train/loss": 2.338337287902832, "train/grad": 0.2594524873048067, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.1266259765625, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.12576416015625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.12421875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.122752685546875, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.121407470703125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.119407958984375, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.11720703125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.114627685546875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.110477294921875, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.10323486328125, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.080697021484375, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.9067617797851564, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.712410583496094, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.5743540954589843, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.476170883178711, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.406382942199707, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.332695426940918, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.254909915924072, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.1843502044677736, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.1279870510101317, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.072463035583496, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.0157135772705077, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.9481576895713806, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.8738233017921448, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.8218086743354798, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.7558129864931107, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.700488619208336, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.6560927629470825, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.6035000634193421, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.5582504332065583, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.510542728304863, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.4793130564689636, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.4832102406024932, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.4616839873790741, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.4819717061519624, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.4958463889360427, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.5455000114440918, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.6142878693342209, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.7075414890050888, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.774954812526703, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.8437177240848541, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.908406955599785, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.9917475843429566, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.171875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.021189012839458884, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.021184793105348945, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.02117675106972456, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.021165314875543118, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.021150545617565512, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.021122725713066757, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.021077865613624455, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.021007764930836857, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.020879674875177442, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.020694634104147555, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.020661994372494517, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.02303611606359482, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.026123161083087324, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.02910154446028173, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.031251598224043844, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.0325126626342535, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.033784704990684984, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.0351351984962821, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.03603258111514151, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.03668024569749832, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.03716544181108475, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.037829443896189335, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.03905712835490704, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.04048353089019656, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.04160179544240236, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0432255319878459, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.04459387369453907, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.045629828702658415, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.046920421067625284, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.04839223138988018, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.04962662545964122, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.050082120317965745, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.05130532028153539, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.05153545966371894, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.052255597971379755, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.05300895230844617, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.053815425280481576, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.05245210491120815, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.05158984076231718, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.051593973096460105, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.05205513620749116, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.05075924491509795, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.051877480521798136, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1229636669158936, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1224448680877686, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1216280460357666, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1208207607269287, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.119985580444336, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1188104152679443, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.117335557937622, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.115466594696045, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.111903429031372, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1036183834075928, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.0690393447875977, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.851684093475342, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.6833548545837402, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.562922477722168, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.4940013885498047, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.4611775875091553, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.4311633110046387, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.40702748298645, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.392275810241699, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.385934352874756, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.3912370204925537, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.407320022583008, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.4335427284240723, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.466958999633789, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.4908523559570312, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.5307819843292236, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.5801541805267334, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.631228446960449, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.708486795425415, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.747591257095337, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.806851863861084, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.86337947845459, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.9272212982177734, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.918665885925293, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.8902299404144287, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.901336908340454, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.959290027618408, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.9403064250946045, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.880448341369629, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.8285648822784424, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.785064458847046, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.7434017658233643, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.856025457382202, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06478405315614617, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06533776301218161, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06496862310815799, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06552233296419344, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06662975267626431, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06681432262827612, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06866002214839424, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06829088224437062, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06866002214839424, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.07511997046880768, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.1020671834625323, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.15743816906607605, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.1939830195644149, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.22868217054263565, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.24473975636766335, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.2606127722406792, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.268733850129199, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.28165374677002586, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.28645256552233295, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.2870062753783684, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.2822074566260613, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.27150239940937615, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.2698412698412698, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.26559616094499816, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.26208933185677374, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.2582133628645257, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.2530454042081949, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.2547065337763012, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.24381690660760427, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.24769287559985234, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.24529346622369877, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.24086378737541528, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.2349575489110373, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.24067921742340348, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.23624953857511996, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.23606496862310816, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.24086378737541528, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.24086378737541528, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.23329641934293097, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.24086378737541528, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.22960502030269472, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.24381690660760427, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.2349575489110373, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.009551475853323286, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.010009861391562817, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.010413693945699892, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.011565087724992923, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.012505940931364035, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.013596653621810255, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.015829511980233326, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.016812745489445547, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.018355791116115388, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.025895623151916142, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.04324360014584736, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.07700838556428073, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.10818672879359177, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.1453094855023793, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.16569946919097533, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.18234358596858355, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.19456489911298017, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.21106470979504496, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.220963283986632, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.22751313919179741, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.2256913267397438, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.21791563393195393, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.21839808796087515, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.21935189933803564, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.21749653230880825, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.2200137577516538, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.21635402933455028, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.21748741421629372, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.2063419272717876, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.20443050348330785, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.20531849933442473, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.20201188129908554, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.1934829126759624, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.20473451624603634, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.20155387635870625, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.20742660919700942, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.20146200310401916, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.20076078617086357, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.1988806745231011, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.19407587481611166, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.19201931667011607, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.2089800741044705, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.1954951707609214, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 19, "lr_best": 0.00013199999999999998, "wd_best": 0.05, "train/loss_best": 2.1279870510101317, "validation/loss_best": 2.385934352874756, "validation/acc_best": 0.2870062753783684, "validation/f1_best": 0.22751313919179741} +{"epoch": 12, "train/lr": 0.0001499999999999999, "train/loss": 2.274397246837616, "train/grad": 0.2572350130230188, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.11953857421875, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.118486328125, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.11664306640625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.114990234375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.113212890625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.110889892578125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.108310546875, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.104859619140625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.099400634765625, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.0878094482421874, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.0399908447265624, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.8077992248535155, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.65103759765625, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.521918411254883, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.4281994247436525, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.3616777229309083, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.2874631118774413, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.209724941253662, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.1386087131500244, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.0820735836029054, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.0243677282333374, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.9656524181365966, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.894717493057251, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.814423882961273, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.7556174075603486, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.679201773405075, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.6146230673789979, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.559169436097145, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.490057309269905, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.4340320527553558, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.3728089213371277, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.3398522698879243, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.3457132840156556, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.326508154273033, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.3333701235055924, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.3461544764041902, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.3909823483228683, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.489866710305214, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.563575754761696, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.6663287806510925, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.717198322415352, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.7952318584918976, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.8721289163827897, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.171875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.021163613037206232, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.02116104982793331, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.021154132792726158, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.02114198262337595, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.02112307379953563, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.021091022514738142, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.021036888007074594, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.020956883849576117, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.020809838413260878, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.020624746046960355, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.020994060318917037, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.024227617476135492, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.027353787422180177, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.03014914614148438, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.032209884086623786, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.03324800205416977, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.03444148707203567, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.0357615789398551, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.03651489932090044, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.0370776392519474, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.037500166269019246, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.03819916210137308, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.039382114205509425, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.040597115959972147, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.04150567730888724, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.042912504374980925, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.04404009286314249, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.04510408172383904, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.046303379889577626, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.047404722031205895, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.049204840511083606, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.04968601729720831, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.05059834867715836, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.051307374760508534, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.051401750277727844, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.052147478014230725, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.05195930136367679, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.051773708909749985, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.050150527898222205, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.050856327712535856, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.04995145719498396, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.05007115021347999, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.04967880867421627, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.123028039932251, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1225478649139404, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.121752977371216, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1209452152252197, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1201179027557373, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1188364028930664, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1172797679901123, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1150877475738525, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1105844974517822, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.0974936485290527, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.032582998275757, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.7880194187164307, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.649775266647339, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.537818670272827, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.480441093444824, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.453601121902466, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.426649808883667, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.408162832260132, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.400857925415039, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.4014551639556885, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.4187071323394775, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.4465975761413574, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.485764980316162, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.527366876602173, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.5526492595672607, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.6011712551116943, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.666283130645752, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.7350926399230957, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.82955265045166, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.8993523120880127, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.999452829360962, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.086117744445801, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.145204544067383, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.1073780059814453, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.1661577224731445, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.131847858428955, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.200368642807007, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.036611795425415, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.03381085395813, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.9071061611175537, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.877070188522339, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.8193790912628174, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.7737696170806885, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06423034330011074, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06423034330011074, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06423034330011074, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06552233296419344, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.0664451827242525, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06921373200442968, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.07087486157253599, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.08102620893318568, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.11572535991140642, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.17128091546696197, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.20191952750092285, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.2307124400147656, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.24510889627168697, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.25950535252860835, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.2661498708010336, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.2751937984496124, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.2777777777777778, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.2798080472499077, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.2722406792174234, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.2643041712809155, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.2591362126245847, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.2593207825765965, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.25599852344038393, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.24916943521594684, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.24898486526393504, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.24584717607973422, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.2355112587670727, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.24529346622369877, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.24289405684754523, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.23791066814322628, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.22960502030269472, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.2412329272794389, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.23126614987080105, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.23385012919896642, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.22978959025470652, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.24012550756736803, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.2277593207825766, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.2410483573274271, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.2355112587670727, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.2456626061277224, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.24031007751937986, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.007807965001176163, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.008200004698801824, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.008959166597209287, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.009026783938741944, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.009201517790577249, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.010468357703926484, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.01196063025926028, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.014436223833193129, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.01733879097446704, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.0292407340961157, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.05001669902882208, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.08672566250193757, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.11502108602435474, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.14723620907732274, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.16656864585339543, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.1827778043406515, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.1943607785657527, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.208404655618035, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.21567400710226378, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.22325925296668944, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.21891111679965125, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.2117600376069192, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.20690907060583796, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.20618854017003027, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.2029127409722111, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.19991636207856409, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.19656435630447736, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.19321921112539533, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.18433567233101208, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.1897331578703261, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.1892767176006478, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.18305918125816703, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.17265138681438782, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.1907082833743563, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.18251278574052102, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.18923782027279112, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.1863875782496466, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.19313005550745585, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.1899588591222318, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.1964340580633277, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.1868367054530001, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.1932730904930644, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.19568185195707213, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 19, "lr_best": 0.00013199999999999998, "wd_best": 0.05, "train/loss_best": 2.0820735836029054, "validation/loss_best": 2.4014551639556885, "validation/acc_best": 0.2798080472499077, "validation/f1_best": 0.22325925296668944} +{"epoch": 13, "train/lr": 0.00011886002410835478, "train/loss": 2.232077159881592, "train/grad": 0.25784493803977965, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.12381591796875, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.12260009765625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.12072998046875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.1188427734375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.11710205078125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.114779052734375, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.111943359375, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.1084228515625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.10223876953125, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.085650634765625, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.0094647216796875, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.7638861083984376, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.6278974914550783, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.5005416870117188, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.4106872940063475, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.3467913246154786, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.2740126419067384, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.1973719692230222, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.126573266983032, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.0675924015045166, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.0071642446517943, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.9439048886299133, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.8661301553249359, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.7832674551010133, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.71897784948349, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.6348071312904358, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.565232065320015, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.5056105399131774, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.426782513856888, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.3619609814882279, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.288198677301407, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.250246069729328, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.245065882205963, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.2141974556446076, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.214751341044903, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.2212110468745232, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.2586641880869864, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.35183451294899, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.456028226017952, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.5399347138404846, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.5931019240617752, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.679953094124794, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.762563568353653, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.171875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.021556347766891124, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.02155057431664318, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.021538919191807507, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.021523326598107816, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.02150000572670251, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.021458984962664546, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.02139782558195293, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.021305448622442782, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.02113640739582479, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.020971595090813935, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.021827468136325478, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.025265414509922268, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.028161779567599295, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.03082614284940064, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.03274582051672041, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.03365715921856463, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.034867613920941946, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.036119967550039295, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.03678412634879351, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.037268687803298235, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.037670675618574026, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.03836201059632003, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.03965368945151568, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.04103814857080579, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.04209309769794345, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.043545594941824674, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.044872647151350975, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.046001330204308036, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.046940347831696275, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.04810298508033156, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.04870357118546963, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.049423084892332554, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.05057234210893512, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.05124015392735601, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.05107506014406681, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.051725009214133026, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.05169431962072849, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.05076687499880791, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.05067068926990032, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.05040245087817311, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.04945884745568037, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.049157758560031656, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.047976838890463114, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1227481365203857, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.122147798538208, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1211466789245605, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1201016902923584, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.119016647338867, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1174204349517822, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.11541748046875, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1127026081085205, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1069087982177734, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.08722186088562, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.9909310340881348, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.7442119121551514, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.623077154159546, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.5189011096954346, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.468508720397949, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.442849636077881, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.414669990539551, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.3973019123077393, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.391291856765747, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.392393112182617, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.408146858215332, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.430074691772461, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.4655728340148926, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.509758949279785, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.539793014526367, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.5921623706817627, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.655459403991699, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.728947639465332, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.81498384475708, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.8962936401367188, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.9802989959716797, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.033097505569458, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.12322998046875, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.161066770553589, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.2489728927612305, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.2312228679656982, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.2887237071990967, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.218155860900879, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.1644885540008545, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.990457057952881, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.9845352172851562, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.9123940467834473, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.837696075439453, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06496862310815799, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06570690291620525, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06607604282022887, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06681432262827612, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06681432262827612, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.0681063122923588, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06866002214839424, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06847545219638243, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.07235142118863049, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.08693244739756367, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.12846068660022147, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.1806939830195644, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.21188630490956073, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.23920265780730898, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.2511997046880768, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.2678110003691399, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.27556293835363604, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.2809154669619786, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.2840531561461794, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.27906976744186046, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.2733480989294943, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.26891842008121075, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.26559616094499816, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.26559616094499816, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.2589516426725729, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.25599852344038393, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.25046142488002954, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.2440014765596161, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.23329641934293097, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.22997416020671835, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.22905131044665927, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.2320044296788483, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.21650055370985605, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.23015873015873015, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.21705426356589147, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.2220376522702104, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.21336286452565523, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.22757475083056478, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.2294204503506829, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.23809523809523808, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.23754152823920266, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.2440014765596161, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.2456626061277224, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.010200696350938832, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.010812391075175126, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.011372519311495667, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.012353263756544367, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.012749272306588025, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.014804763912492904, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.015739975845706355, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.01651779004510148, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.02141600904671889, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.03544151764789109, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.05790140658458206, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.0981425811252138, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.12689767816366762, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.1577448500025108, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.17377494862693454, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.1922110487353542, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.2038385921166587, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.2153593493626836, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.2224864000987996, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.2203764015454769, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.21823554896597822, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.214293044653285, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.2129686929638572, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.21707749450078176, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.21161982428932116, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.2113901711074322, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.20626282539888355, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.19933405878570834, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.1928333582721745, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.19067249466057956, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.19396527640013903, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.1961112412603153, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.18138303771036238, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.19035241788962867, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.1767497570139919, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.18421348884459107, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.17516417030017725, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.17826976251512372, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.1819049387219164, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.1885286299273726, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.17898105021131283, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.19360192103389048, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.1870317605867251, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 18, "lr_best": 0.00011399999999999999, "wd_best": 0.05, "train/loss_best": 2.126573266983032, "validation/loss_best": 2.391291856765747, "validation/acc_best": 0.2840531561461794, "validation/f1_best": 0.2224864000987996} +{"epoch": 14, "train/lr": 8.9081919031238e-05, "train/loss": 2.179529169797897, "train/grad": 0.2547478572279215, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.120513916015625, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.11938720703125, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.117384033203125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.11550537109375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.11371826171875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.11130859375, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.10830078125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.104559326171875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.097313232421875, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.074315185546875, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.97102294921875, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.7238706970214843, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.597687530517578, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.4739501953125, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.3867807006835937, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.3234116363525392, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.248033905029297, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.1683506774902344, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.096998119354248, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.0390727615356443, "train/loss_020_lr5.2e-01_wd1.0e+00": 1.977637948989868, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.912333426475525, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.8317788600921632, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.7434012639522551, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.6740798592567443, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.5849227386713027, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.5082688361406327, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.442562382221222, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.3560822474956513, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.2810447776317597, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.1942051500082016, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.143216211795807, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.1212681910395623, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.0948890092968941, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.0826884338259697, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.0712554594874382, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.0995024451613427, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.2035246145725251, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.302017063498497, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.3924625849723815, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.45540478348732, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.5490113413333892, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.6326387947797776, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.171875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.021108224685303868, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.02110084711574018, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.021088209268637, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.021071241525933145, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.021047204839996992, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.021006620712578295, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.02094454405363649, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.02084983912296593, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.020682596708647905, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.02060371131170541, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.02194053664803505, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.025548558877781034, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.028248108476400375, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.030843924591317774, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.03268628443591297, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.03359441014938056, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.03485625024884939, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.03608229640871286, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.0366901898290962, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.03721797442995012, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.03760586906224489, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.03833691524341702, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.03966370359063148, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.04102779168635607, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.04207339223474264, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0436808468028903, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.04501580864191055, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.04617464434355498, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.04717719037085771, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.04826745286583901, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.04845675721764565, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.04884388711303472, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.048896005228161815, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.04925243701785803, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.049385100565850736, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.049830892123281956, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.049682492781430485, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.04993119869381189, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.04954176720231771, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.04918073646724224, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.049404785241931676, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.04896799750626087, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.04742373855784535, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1221203804016113, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1214866638183594, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1204044818878174, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1193323135375977, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1182336807250977, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.116638422012329, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1145572662353516, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1116323471069336, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.104820489883423, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.0782008171081543, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.957321882247925, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.7178313732147217, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.604858160018921, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.5054709911346436, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.458404779434204, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.4323930740356445, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.402228832244873, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.3837103843688965, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.375002145767212, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.3741626739501953, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.386310577392578, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.4073081016540527, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.443169116973877, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.4855027198791504, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.5143539905548096, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.574490785598755, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.643181800842285, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.7086586952209473, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.8011558055877686, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.884669303894043, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.0026323795318604, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.0883827209472656, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.181647539138794, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.212311029434204, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.3192238807678223, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.348846197128296, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.3920774459838867, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.2905845642089844, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.2168498039245605, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.1823980808258057, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.149928569793701, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.053251266479492, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.9641401767730713, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.0651531930601698, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06552233296419344, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06681432262827612, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06681432262827612, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06718346253229975, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06736803248431156, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06921373200442968, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.0695828719084533, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.07308970099667775, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.09505352528608342, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.1378737541528239, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.18604651162790697, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.21816168327796234, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.2440014765596161, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.25802879291251385, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.2663344407530454, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.27851605758582504, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.2827611664820967, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.28903654485049834, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.2862679955703212, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.27870062753783686, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.27150239940937615, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.2727943890734588, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.2652270210409745, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.26301218161683276, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.25987449243263194, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.25046142488002954, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.24473975636766335, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.23421926910299004, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.2334809892949428, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.22572905131044665, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.2334809892949428, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.22388335179032853, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.22683647102251753, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.2117017349575489, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.21040974529346623, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.21483942414174972, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.21520856404577335, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.22111480251015134, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.21613141380583242, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.21391657438169065, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.21797711332595054, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.22739018087855298, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.010246976285831086, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.01071620059057945, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.01176965428444112, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.011838023063670182, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.01206863878994109, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.01303422816747211, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.014732913823362176, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.016106380347281554, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.021339982768861464, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.03901919817962916, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.0616705350251307, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.10112478086674363, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.13301333543216376, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.16151608302873774, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.1793443905068618, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.19005511262216412, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.20882167749584077, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.2170553924680093, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.22755425244151492, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.22848344660357842, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.22562796366309604, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.2195885864033005, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.22386281813268535, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.21755374756371904, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.21974511776788433, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.2187133901314354, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.20928606286533968, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.20472907003882546, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.1987155774685052, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.19817159711673735, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.1921220425960013, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.19741152443351698, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.1893988175950627, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.19297662294204032, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.17822587216540844, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.18166265212616625, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.18621024908245132, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.18469752915712964, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.19014396968197622, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.18065548717722638, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.17966912485890293, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.18517125851441707, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.18848433715895285, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 18, "lr_best": 0.00011399999999999999, "wd_best": 0.05, "train/loss_best": 2.096998119354248, "validation/loss_best": 2.375002145767212, "validation/acc_best": 0.28903654485049834, "validation/f1_best": 0.22755425244151492} +{"epoch": 15, "train/lr": 6.196799573888289e-05, "train/loss": 2.1351494717597963, "train/grad": 0.2517167708277702, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.115908203125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.114669189453125, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.11280517578125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.11094970703125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.109066162109375, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.10645751953125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.103426513671875, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.099522705078125, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.09124755859375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.06255126953125, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.9410720825195313, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.7020950317382812, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.5821092987060545, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.4595058441162108, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.373599510192871, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.309976005554199, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.2341463470458987, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.1535757541656495, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.080136957168579, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.0191801309585573, "train/loss_020_lr5.2e-01_wd1.0e+00": 1.95629723072052, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.889206190109253, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.8054588735103607, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.7126695382595063, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.641970168352127, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.550105094909668, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.4668363827466964, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.3852898097038269, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.2912880355119705, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.2044690334796906, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.1137764573097229, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.0598143547773362, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.0204559513926506, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.9924644774198532, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.9757721757888794, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.9472719806432724, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.984634969830513, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.0751975896954535, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.1728559723496437, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.245115409195423, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.3138235527276994, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.4048421639204025, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.4994596368074418, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.171875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.021542269894853236, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.021535459477454423, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.021520124822854994, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.02149809910915792, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.021470119822770358, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.02142104648053646, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.02134916295297444, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.021241077394224702, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.021049954774789513, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.021019705329090355, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.0225862137414515, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.026286132717505097, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.02893145615234971, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.03152927200309932, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.033295312700793146, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.03416354419663548, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.03537118467502296, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.03652137720026076, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.03708417965099216, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.03757536586374045, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.037957715578377245, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.038698416091501715, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.03994462177157402, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.04125749142840505, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.04221886597573757, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.043486464824527504, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.04442171839997172, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.04515950545668602, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.04593748165294528, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.04651586560532451, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.04654107805341482, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.046631341725587847, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.04700270405039191, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.04709243591874838, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.04784643746912479, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.047220611814409494, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.04839464275166392, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.048988895788788796, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.048852840159088376, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.04830143503844738, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0488103094138205, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.048245008047670124, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.04698988312855363, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1221940517425537, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1215782165527344, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1205804347991943, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.119572162628174, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1184821128845215, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1169142723083496, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.114837408065796, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1117844581604004, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1042139530181885, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.0717318058013916, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.9354989528656006, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.7028727531433105, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.5936641693115234, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.497896432876587, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.454606533050537, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.430967092514038, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.405540943145752, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.3935608863830566, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.388981819152832, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.3894574642181396, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.4018657207489014, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.425544500350952, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.460318088531494, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.4978139400482178, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.525940418243408, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.581918716430664, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.655017375946045, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.732706069946289, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.837555408477783, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.931422710418701, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.031252145767212, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.106980562210083, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.2092061042785645, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.2381954193115234, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.344125270843506, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.3696107864379883, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.44354248046875, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.348717451095581, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.269558906555176, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.1592655181884766, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.1190786361694336, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.042099952697754, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.9926702976226807, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.0651531930601698, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06570690291620525, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06570690291620525, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06626061277224068, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.0681063122923588, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06884459210040605, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06939830195644149, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06939830195644149, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.07364341085271318, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.09874492432631968, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.14156515319306018, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.18973791066814322, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.22240679217423404, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.2456626061277224, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.2576596530084902, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.2672572905131045, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.27851605758582504, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.2823920265780731, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.2838685861941676, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.2811000369139904, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.2751937984496124, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.271686969361388, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.26836471022517533, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.26854928017718716, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.26245847176079734, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.25950535252860835, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.25101513473606496, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.24307862679955702, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.2351421188630491, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.22831303063861202, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.22554448135843486, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.22997416020671835, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.21853082318198597, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.22720561092654115, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.21114802510151348, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.2129937246216316, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.20764119601328904, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.22683647102251753, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.21557770394979697, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.21797711332595054, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.2129937246216316, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.2187153931339978, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.22388335179032853, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.010514293842800204, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.010878289829078812, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.01099506712050719, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.01160242051096017, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.013179636035279102, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.014510759149215154, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.016374570466027333, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.017611475661930765, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.022458004513916083, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.04128840992408944, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.06555246883632289, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.10664646487572009, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.1384238770281453, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.16561696104766574, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.18084029849769814, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.19424874918237678, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.2087840249611437, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.2159478493340591, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.2224053210159279, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.2237234321059519, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.2209272617230753, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.218616616184543, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.2173603037652757, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.22119276794708778, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.21822165782593628, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.21971570690032652, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.21422191253984454, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.20754035388728923, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.20139981968437817, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.19466169708830314, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.1980234451185067, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.20231261402643566, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.1856181247643958, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.20265121578504453, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.18622249218043554, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.19135393059065778, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.18961894359891907, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.19933773071701574, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.19296210519160603, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.1928183916076446, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.18943985570533073, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.19631654671722273, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.20237167245308738, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 18, "lr_best": 0.00011399999999999999, "wd_best": 0.05, "train/loss_best": 2.080136957168579, "validation/loss_best": 2.388981819152832, "validation/acc_best": 0.2838685861941676, "validation/f1_best": 0.2224053210159279} +{"epoch": 16, "train/lr": 3.870405029380728e-05, "train/loss": 2.1076651859283446, "train/grad": 0.2464498668164015, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.12359375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.1223046875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.120255126953125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.11818359375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.116241455078125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.113494873046875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.110191650390625, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.105814208984375, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.0968426513671874, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.063372802734375, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.9299261474609377, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.698167266845703, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.585662155151367, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.467439727783203, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.383059196472168, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.318958225250244, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.242725429534912, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.162448720932007, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.0887532901763914, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.0262871742248536, "train/loss_020_lr5.2e-01_wd1.0e+00": 1.9596253633499146, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.8908542585372925, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.804825336933136, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.7085251939296722, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.6323000764846802, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.5326217073202133, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.4452099317312241, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.3634140843153, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.2655772370100022, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.1710928750038148, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.0693989396095276, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.0088739836215972, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.9639035686850548, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.9193868732452393, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.8959541606903076, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.8611900222301483, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.8782650089263916, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.9522674888372421, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.0401684293150901, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.1048380747437476, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.1683411064743996, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.2510005182027817, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.3629901045560837, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.171875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.02149168959353119, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.02148289427626878, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.02146387298591435, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.021440499797463416, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.02140856292564422, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.02135780181735754, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.021280997493304313, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.021172279375605285, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.020980080193839967, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.021021618591621518, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.02279845635406673, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.02650598019361496, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.029096836969256402, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.03165896685793996, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.03337897349148989, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.034239865401759745, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.03545991933904588, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.036598655385896565, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.03715798581019044, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.03767307411879301, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.038061509858816865, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.038783647138625386, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.039979657754302025, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.041213514059782026, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.042098452504724264, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.04335175830870867, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.04425062632188201, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.044863570146262646, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.04552657263353467, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.04580023068934679, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.04572028007358313, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.04534308204427361, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.045408221669495104, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.045193210691213605, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.045165405161678794, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.044910735581070185, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.045821791160851714, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.04593579739332199, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.046260426491498946, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.046389474496245385, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.046498557049781085, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.04630096100270748, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.04555173000320792, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.122180223464966, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1215713024139404, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1205756664276123, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.119553804397583, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.11847186088562, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.11684513092041, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.114675521850586, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.111463785171509, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.103288173675537, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.0667765140533447, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.921924114227295, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.694474458694458, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.5877034664154053, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.4938807487487793, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.4513723850250244, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.427492141723633, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.401247262954712, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.3900535106658936, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.386885404586792, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.39180064201355, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.4101109504699707, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.439359426498413, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.4806206226348877, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.5257818698883057, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.5597329139709473, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.626920700073242, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.7047078609466553, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.7889251708984375, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.895838499069214, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.991415500640869, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.1067795753479004, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.2052435874938965, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.3048579692840576, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.3265774250030518, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.441279411315918, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.5022573471069336, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.5627739429473877, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.484809398651123, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.432171583175659, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.320214033126831, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.292787790298462, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.1941676139831543, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.100942373275757, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06459948320413436, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.0651531930601698, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.0651531930601698, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06589147286821706, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.0664451827242525, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06755260243632337, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06847545219638243, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06995201181247693, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.07235142118863049, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.09985234403839055, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.14710225175341454, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.18973791066814322, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.2233296419342931, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.24510889627168697, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.25987449243263194, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.26947212993724623, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.2768549280177187, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.2811000369139904, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.28497600590623845, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.28017718715393136, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.2751937984496124, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.2705795496493171, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.2661498708010336, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.260797342192691, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.2552602436323367, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.2541528239202658, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.24086378737541528, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.23717238833517904, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.22960502030269472, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.22665190107050573, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.22240679217423404, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.22443706164636398, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.21188630490956073, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.21834625322997417, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.20524178663713546, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.2056109265411591, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.21207087486157253, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.21816168327796234, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.20671834625322996, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.21779254337393872, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.20985603543743078, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.2117017349575489, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.21853082318198597, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.009768505204496387, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.010738954911507314, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.010327704591611335, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.011205697431577904, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.01171655340248943, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.013064868953120576, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.014451216382987268, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.0172619028873938, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.02135252547269978, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.041786083583298654, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.0689148389423044, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.10589180885777948, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.13866329551990794, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.16535249906185825, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.18386081335529117, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.19778541860093893, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.20706507247577563, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.2154708522507204, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.2254650534059923, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.22396304244120904, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.22109037513927696, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.21850527388844795, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.21567195895597502, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.21508383778625761, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.2115462046925486, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.21294274981764458, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.201952445169666, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.19944035144032446, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.1956530279937648, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.19286873965305648, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.19111216746306173, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.1924751627646937, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.18024742862801438, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.18924610910738363, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.1808619952168026, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.1792015629673784, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.18205536372910702, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.18861892470366337, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.17929902518179944, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.18850609131822124, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.18232576614917892, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.18548234985425704, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.1916489125445621, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 18, "lr_best": 0.00011399999999999999, "wd_best": 0.05, "train/loss_best": 2.0887532901763914, "validation/loss_best": 2.386885404586792, "validation/acc_best": 0.28497600590623845, "validation/f1_best": 0.2254650534059923} +{"epoch": 17, "train/lr": 2.030750443206766e-05, "train/loss": 2.0684328413009645, "train/grad": 0.2385747741162777, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.119385986328125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.1180810546875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.116112060546875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.114169921875, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.11217041015625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.109530029296875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.10626708984375, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.1020166015625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.0926910400390626, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.056544189453125, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.916445007324219, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.6830560302734376, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.567503662109375, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.4485113525390627, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.365207748413086, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.3021206665039062, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.226778087615967, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.1466569614410402, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.0717005252838137, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.008331365585327, "train/loss_020_lr5.2e-01_wd1.0e+00": 1.9404568576812744, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.8688029718399048, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.7809552025794984, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.6820893824100493, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.6021291363239287, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.4971088951826095, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.4052723306417465, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.3224646073579789, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.2201950252056122, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.1199020713567733, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.0176761278510094, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.9516097000241279, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.8900468608736992, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.8519423267245293, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.8165549299120903, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.7697021198272705, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.7741959223151207, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.8383806133270264, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.9075844094157219, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.9655091762542725, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.0142086231708527, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.0897674658894538, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.2121267220377923, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.171875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.021256073652766647, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.021243858486413955, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.02122162876650691, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.021195012452080844, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.021162266773171724, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.021109152231365443, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.021030024630017578, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.020919269830919802, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.020729490565136077, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.020817135092802346, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.022664316222071646, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.026355556612834334, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.028901397734880447, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.031457521794363855, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.033154642833396794, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.034010951351374386, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.03521787928417325, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.03632235036231577, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.03679727551527321, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.03725686570629477, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.037641590163111686, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.03835206478834152, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.03951428970322013, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.040700923781841994, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.041559600476175546, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.04272218467667699, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.043456200044602156, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.04409260544925928, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.04455227065831423, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.04473648527637124, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.04434704391285777, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0438472998701036, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.04341530757024884, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.042926182057708505, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.04251791441813111, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.04202762492001057, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.042371996380388736, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.04282140674069524, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.042952915616333485, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.043336381036788225, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.04353565553203225, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.04362959252670407, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0434685979411006, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1221816539764404, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1215648651123047, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1205341815948486, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.119490385055542, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.118394374847412, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.11673903465271, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.114509105682373, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1111690998077393, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.102613925933838, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.0637872219085693, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.9146151542663574, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.689323902130127, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.583352565765381, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.490567922592163, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.4478189945220947, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.422943592071533, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.395017623901367, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.381185531616211, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.37577748298645, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.3783161640167236, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.3946521282196045, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.4219634532928467, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.460721492767334, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.504178047180176, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.5368592739105225, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.5976345539093018, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.674624443054199, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.7532801628112793, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.86588191986084, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.9714629650115967, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.0868732929229736, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.173532485961914, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.287071466445923, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.3185670375823975, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.423854112625122, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.5013654232025146, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.5867793560028076, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.509138345718384, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.454916000366211, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.3312389850616455, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.3056931495666504, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.2578470706939697, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.1506762504577637, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.0651531930601698, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06533776301218161, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06570690291620525, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.0664451827242525, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.067921742340347, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.0681063122923588, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06884459210040605, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06939830195644149, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.07475083056478406, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.10428202288667406, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.14820967146548542, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.19158361018826134, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.2249907715023994, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.24603174603174602, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.26005906238464377, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.27002583979328165, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.28183831672203763, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.2838685861941676, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.28497600590623845, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.2842377260981912, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.2794389073458841, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.27113325950535255, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.26947212993724623, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.26651901070505724, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.260797342192691, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.2543373938722776, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.24880029531192321, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.24492432631967515, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.2294204503506829, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.22812846068660023, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.22369878183831673, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.2294204503506829, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.21668512366186785, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.22388335179032853, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.21280915466961978, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.21077888519748986, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.2100406053894426, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.22259136212624583, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.21077888519748986, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.2201919527500923, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.2129937246216316, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.2216685123661868, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.22296050203026946, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.010620552391034961, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.01075281121846996, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.010887780603343661, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.011667125572933765, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.013105497524237503, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.013820135979772786, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.01584373304373139, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.017613649624779296, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.02338259630357262, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.04507497905828702, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.06981372438791052, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.10889381363322552, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.14099217238957573, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.16619733780703075, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.18547810683428545, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.19756924024487518, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.2128486082030495, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.21905466050525102, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.2253797541294229, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.22791665018416266, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.22602347264203007, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.22013682421044314, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.2227007294880562, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.22211280011044435, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.21817766437702193, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.21534325509416652, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.21018913954120447, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.2082504784494952, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.19519435829207088, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.19412387488867058, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.19186280333929248, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.1957128950144783, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.1835052797876583, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.1924441143841863, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.18498476975470549, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.1832162824769886, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.1825204793792314, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.19007449026958814, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.18018173084145597, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.19229973214178386, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.18332771025983433, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.1904504768731874, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.19572395402025713, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 18, "lr_best": 0.00011399999999999999, "wd_best": 0.05, "train/loss_best": 2.0717005252838137, "validation/loss_best": 2.37577748298645, "validation/acc_best": 0.28497600590623845, "validation/f1_best": 0.2253797541294229} +{"epoch": 18, "train/lr": 7.5829098008590064e-06, "train/loss": 2.0476135009527208, "train/grad": 0.23479387588799, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.121533203125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.12022216796875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.118131103515625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.1161328125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.11420166015625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.1113671875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.108155517578125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.103656005859375, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.094072265625, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.05646484375, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.914518127441406, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.6858651733398435, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.571316375732422, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.449413146972656, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.362422676086426, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.2968235206604004, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.2189262199401854, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.137414016723633, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.062536191940308, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.0000856828689577, "train/loss_020_lr5.2e-01_wd1.0e+00": 1.9350634503364563, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.8623430013656617, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.7719384765625, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.6702334904670715, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.5905125141143799, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.4829672634601594, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.3889041775465012, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.304099428653717, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.195373565554619, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.093266746401787, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.9843670335412026, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.9211008194088935, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.852659456729889, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.815135022699833, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.7679643243551254, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.7134984368085862, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.7207361924648285, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.7695174545049668, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.8365916219353676, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.8826538279652596, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.9121811014413833, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.9766708573698998, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.0907770422101022, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.171875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.021362979835830628, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.021350706261582673, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.021329996837303043, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.021303340545855462, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.021269454043358563, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.021216160780750216, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.021139003182761372, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.02102989493403584, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.020840655285865067, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.020948854079470038, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.02283560055308044, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.026534396409988403, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.029063000893220305, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.03162638477049768, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.03330527642741799, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.03414976806379855, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.035358121721073985, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.03643097271211446, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.03692646342329681, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.03739680288359523, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.03780762758105993, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.03849744354374707, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.039608808532357216, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0407471857778728, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.041536451242864134, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.042593728844076396, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.04327688736841082, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0438387318328023, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0440982523187995, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.04400553138926625, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.04355055404826999, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.04294002130627632, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.04250554459169507, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.041822655759751796, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.04126191655173898, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.040351706501096485, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.04033967182040214, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.04052589574828744, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.04099013604223728, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.04113949798047543, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.04135797390714288, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.04175283325836063, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.04162062812596559, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1221752166748047, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.121554374694824, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1205430030822754, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.11948299407959, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.118389368057251, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1167101860046387, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.114457845687866, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.111135244369507, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.10248064994812, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.0628774166107178, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.9123165607452393, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.6882472038269043, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.5828795433044434, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.491055727005005, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.4492738246917725, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.4252986907958984, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.3985579013824463, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.3863887786865234, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.382239580154419, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.385918378829956, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.4029452800750732, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.4307212829589844, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.4705135822296143, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.513669490814209, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.5461583137512207, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.6050679683685303, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.6828665733337402, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.7633438110351562, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.8770241737365723, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.9800310134887695, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.094536304473877, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.1849300861358643, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.299327850341797, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.3375401496887207, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.450749397277832, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.516282558441162, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.6082141399383545, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.5083842277526855, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.4537277221679688, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.3617427349090576, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.3593199253082275, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.2973482608795166, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.2073049545288086, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.0651531930601698, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06552233296419344, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06552233296419344, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06607604282022887, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06736803248431156, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06847545219638243, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06995201181247693, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.0695828719084533, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.07475083056478406, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.10483573274270949, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.1491325212255445, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.19121447028423771, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.22554448135843486, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.2469545957918051, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.2617201919527501, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.2691029900332226, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.27999261720191954, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.28146917681801403, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.2840531561461794, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.2812846068660022, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.27759320782576596, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.26947212993724623, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.27002583979328165, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.26559616094499816, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.26098191214470284, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.25507567368032485, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.2456626061277224, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.24326319675156885, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.22831303063861202, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.2279438907345884, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.21982281284606867, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.2321889996308601, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.2157622739018088, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.22314507198228128, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.20967146548541898, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.21077888519748986, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.20837947582133629, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.22148394241417496, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.21133259505352528, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.21797711332595054, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.20837947582133629, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.2159468438538206, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.21705426356589147, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.010649510282960342, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.01081621622165752, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.010663404147795189, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.011282822179556095, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.012778879002958135, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.014148829817180708, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.016335790902454492, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.017780968974562248, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.023703662113956633, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.04578853284817599, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.07028257630858546, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.10791687337264866, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.14189821727652227, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.16757178508896434, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.18731387158298643, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.19707920380563826, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.21029706820386393, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.21677773872789516, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.22493561114699903, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.22479683797396133, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.22379470206309146, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.21807110736299176, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.22122139778086405, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.21907462816980636, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.2176130437536569, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.21514720344431804, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.20653752523384328, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.2060490641361266, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.19430956499460703, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.19435964507034606, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.1894345960407993, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.20062779266251796, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.18103631367497555, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.19394349306047953, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.18379132668860862, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.18479473219146791, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.18244874153174603, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.19071283619132862, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.18395945610728984, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.19008888230316257, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.1801706987627503, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.18799010210030842, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.19083587636691993, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 18, "lr_best": 0.00011399999999999999, "wd_best": 0.05, "train/loss_best": 2.062536191940308, "validation/loss_best": 2.382239580154419, "validation/acc_best": 0.2840531561461794, "validation/f1_best": 0.22493561114699903} +{"epoch": 19, "train/lr": 1.0867618231465446e-06, "train/loss": 2.0489721584320066, "train/grad": 0.2309134429693222, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.122486572265625, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.12122314453125, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.119241943359375, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.117401123046875, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.1154638671875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.112744140625, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.109505615234375, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.1051611328125, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.0957452392578126, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.058311767578125, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.9161669921875, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.686789245605469, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.5740174865722656, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.4550741958618163, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.3699681854248045, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.3052044486999512, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.2289775657653808, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.1487952709197997, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.0741087436676025, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.011375994682312, "train/loss_020_lr5.2e-01_wd1.0e+00": 1.9454944324493408, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.874033706188202, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.7840852975845336, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.681753042936325, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.6023797047138215, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.4934954631328583, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.3985168808698654, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.3123171281814576, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.2022422820329666, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.105955134034157, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.9905663016438484, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.9193790796399116, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.8543846425414086, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.8117410051822662, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.7692789033055305, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.714619320333004, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.7132822653651237, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.7651525188982486, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.8224761176109314, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.8544754713773728, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.8959356513619423, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.9606774353981018, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.0483832302689553, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.171875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.020980123025365175, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.020967654236592352, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.020946183372288943, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.020919649694114924, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.020884857657365502, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.02082976740319282, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.020749133126810194, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.0206378251966089, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.020450248629786075, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.02056668481323868, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.022452921597287057, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.026121145114302635, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.02861568777821958, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.031120298076421023, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.0327570287976414, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.0336005297023803, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.03482145125977695, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.035948460418730975, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.036495690690353515, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.037012786194682123, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.0374029151070863, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.038103864789009095, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.039206411130726336, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.04033879136666656, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.04105623956769705, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.042088247891515496, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0428070218488574, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.04332016218453646, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.04355265028774738, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.04341765437275171, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.043155983686447144, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.04228644944727421, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.04175546264275908, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.04111249232664704, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.04049598909914494, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.039719930421561, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.039513005185872314, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.03978613629937172, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.03994991121813655, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.04006064860150218, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.04027806872501969, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.04043956097215414, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.04032438827678561, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.122173309326172, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.12154483795166, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.120532751083374, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.11946439743042, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1183676719665527, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.11668062210083, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.114438533782959, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.111081123352051, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1024181842803955, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.0627219676971436, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.911996841430664, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.6879732608795166, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.5826659202575684, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.4908363819122314, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.4489834308624268, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.424801826477051, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.3978912830352783, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.385471820831299, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.3812315464019775, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.3846359252929688, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.401848554611206, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.4295947551727295, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.4696874618530273, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.512906312942505, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.5451459884643555, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.6056506633758545, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.6835832595825195, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.7647385597229004, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.876415729522705, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.9810123443603516, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.0971667766571045, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.188143730163574, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.297769069671631, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.3337626457214355, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.447925567626953, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.518244981765747, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.6027073860168457, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.5147652626037598, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.463287830352783, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.3667361736297607, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.366501569747925, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.306966781616211, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.2190358638763428, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.0651531930601698, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06552233296419344, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06552233296419344, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.0664451827242525, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06755260243632337, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.0681063122923588, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06976744186046512, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06939830195644149, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.07456626061277224, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.10520487264673312, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.1491325212255445, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.19139904023624954, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.22554448135843486, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.24640088593576967, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.26245847176079734, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.2691029900332226, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.2796234772978959, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.27999261720191954, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.2851605758582503, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.2812846068660022, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.27759320782576596, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.26947212993724623, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.26891842008121075, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.2643041712809155, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.2602436323366556, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.25489110372831303, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.2456626061277224, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.24141749723145073, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.23089700996677742, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.2307124400147656, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.2216685123661868, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.23292727943890734, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.21520856404577335, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.2235142118863049, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.21096345514950166, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.21336286452565523, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.21077888519748986, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.2216685123661868, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.21133259505352528, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.21816168327796234, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.2102251753414544, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.21668512366186785, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.21631598375784422, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.010649984942573444, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.010820637106903347, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.010655914078483611, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.011690957887754821, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.012920698145246252, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.013736839116715293, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.01637354382076996, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.017506830729990954, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.023614789246796223, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.04599812454697593, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.07036962564830546, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.10808874247491213, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.1420928411492338, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.16687896338409533, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.18791170464458554, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.19666366111539024, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.21006671256299247, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.2155177935853065, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.22485967984522437, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.22520490384526526, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.2239471951772906, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.21813447638253816, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.22010325789921978, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.21873668681006675, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.2169810078582005, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.21462994083502562, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.2071325589016169, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.20416599148869416, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.19640765573677324, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.1951790296880889, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.18980424593957582, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.20042478754064783, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.18130186484791566, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.19482972517338426, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.1849625915704257, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.18723785796930095, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.18407959542344807, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.19042857948325806, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.1833533186976628, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.18999629774192472, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.18139270054110423, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.18880044304876006, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.19026819137939668, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 18, "lr_best": 0.00011399999999999999, "wd_best": 0.05, "train/loss_best": 2.0741087436676025, "validation/loss_best": 2.3812315464019775, "validation/acc_best": 0.2851605758582503, "validation/f1_best": 0.22485967984522437} diff --git a/input_space_v3/flat_lr1e-3_1/eval_v2/ppmi_dx__patch__attn/config.yaml b/input_space_v3/flat_lr1e-3_1/eval_v2/ppmi_dx__patch__attn/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..eb6b0b2a91b7e5e9752f19aceabb98f089b6c976 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_1/eval_v2/ppmi_dx__patch__attn/config.yaml @@ -0,0 +1,98 @@ +output_root: experiments/input_space_v3/output +name_prefix: eval_probe +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_1; eval v2 (ppmi_dx patch attn) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +dataset_kwargs: {} +classifier_kwargs: + embed_dim: null + dropout: 0.0 + xavier_init: true + norm: true +lr_scale_grid: +- 0.02 +- 0.023 +- 0.028 +- 0.033 +- 0.038 +- 0.045 +- 0.053 +- 0.062 +- 0.074 +- 0.087 +- 0.1 +- 0.12 +- 0.14 +- 0.17 +- 0.2 +- 0.23 +- 0.27 +- 0.32 +- 0.38 +- 0.44 +- 0.52 +- 0.61 +- 0.72 +- 0.85 +- 1 +- 1.2 +- 1.4 +- 1.6 +- 1.9 +- 2.3 +- 2.7 +- 3.1 +- 3.7 +- 4.3 +- 5.1 +- 6 +- 7.1 +- 8.3 +- 9.8 +- 12 +- 14 +- 16 +- 19 +- 22 +- 26 +- 31 +- 36 +- 43 +- 50 +wd_scale_grid: +- 1.0 +num_workers: 8 +prefetch_factor: null +balanced_sampling: false +epochs: 20 +steps_per_epoch: 200 +batch_size: 4 +accum_iter: 4 +lr: 0.0003 +warmup_epochs: 5 +no_decay: false +weight_decay: 0.05 +clip_grad: 1.0 +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +early_stopping: true +amp: true +device: cuda +seed: 4466 +debug: false +wandb: false +wandb_entity: null +wandb_project: fMRI-fm-eval +name: input_space_v3/flat_lr1e-3_1/eval_v2/ppmi_dx__patch__attn +base_lr: 3.0e-05 +model: flat_mae +representation: patch +classifier: attn +dataset: ppmi_dx +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/ppmi_dx__patch__attn +remote_dir: null diff --git a/input_space_v3/flat_lr1e-3_1/eval_v2/ppmi_dx__patch__attn/eval_log.json b/input_space_v3/flat_lr1e-3_1/eval_v2/ppmi_dx__patch__attn/eval_log.json new file mode 100644 index 0000000000000000000000000000000000000000..50a69abad97e980802454e62c8d0d430e758166c --- /dev/null +++ b/input_space_v3/flat_lr1e-3_1/eval_v2/ppmi_dx__patch__attn/eval_log.json @@ -0,0 +1 @@ +{"eval/epoch": 10, "eval/id_best": 19, "eval/lr_best": 0.00013199999999999998, "eval/wd_best": 0.05, "eval/train/loss": 0.4721227288246155, "eval/train/acc": 0.7775377969762419, "eval/train/acc_std": 0.019701765318171735, "eval/train/f1": 0.7666524766476325, "eval/train/f1_std": 0.020403957597703963, "eval/train/bacc": 0.7686773112556673, "eval/train/bacc_std": 0.020512997656709143, "eval/validation/loss": 0.6690674424171448, "eval/validation/acc": 0.6868686868686869, "eval/validation/acc_std": 0.04674812078860053, "eval/validation/f1": 0.6735453675140943, "eval/validation/f1_std": 0.0486870415365517, "eval/validation/bacc": 0.6743589743589744, "eval/validation/bacc_std": 0.04896461204860454, "eval/test/loss": 0.6794328093528748, "eval/test/acc": 0.59, "eval/test/acc_std": 0.044957273048973956, "eval/test/f1": 0.539894512400404, "eval/test/f1_std": 0.04936345405766934, "eval/test/bacc": 0.5407550407550408, "eval/test/bacc_std": 0.047017469378541815} diff --git a/input_space_v3/flat_lr1e-3_1/eval_v2/ppmi_dx__patch__attn/eval_log_best.json b/input_space_v3/flat_lr1e-3_1/eval_v2/ppmi_dx__patch__attn/eval_log_best.json new file mode 100644 index 0000000000000000000000000000000000000000..1288bcebc69e264561356cd4f53f2dddf98d68a0 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_1/eval_v2/ppmi_dx__patch__attn/eval_log_best.json @@ -0,0 +1 @@ +{"eval/best/epoch": 10, "eval/best/id_best": 19, "eval/best/lr_best": 0.00013199999999999998, "eval/best/wd_best": 0.05, "eval/best/train/loss": 0.4721227288246155, "eval/best/train/acc": 0.7775377969762419, "eval/best/train/acc_std": 0.019701765318171735, "eval/best/train/f1": 0.7666524766476325, "eval/best/train/f1_std": 0.020403957597703963, "eval/best/train/bacc": 0.7686773112556673, "eval/best/train/bacc_std": 0.020512997656709143, "eval/best/validation/loss": 0.6690674424171448, "eval/best/validation/acc": 0.6868686868686869, "eval/best/validation/acc_std": 0.04674812078860053, "eval/best/validation/f1": 0.6735453675140943, "eval/best/validation/f1_std": 0.0486870415365517, "eval/best/validation/bacc": 0.6743589743589744, "eval/best/validation/bacc_std": 0.04896461204860454, "eval/best/test/loss": 0.6794328093528748, "eval/best/test/acc": 0.59, "eval/best/test/acc_std": 0.044957273048973956, "eval/best/test/f1": 0.539894512400404, "eval/best/test/f1_std": 0.04936345405766934, "eval/best/test/bacc": 0.5407550407550408, "eval/best/test/bacc_std": 0.047017469378541815} diff --git a/input_space_v3/flat_lr1e-3_1/eval_v2/ppmi_dx__patch__attn/eval_log_last.json b/input_space_v3/flat_lr1e-3_1/eval_v2/ppmi_dx__patch__attn/eval_log_last.json new file mode 100644 index 0000000000000000000000000000000000000000..0453d0dedb520e21ac1c74e17d90ff0d6584a020 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_1/eval_v2/ppmi_dx__patch__attn/eval_log_last.json @@ -0,0 +1 @@ +{"eval/last/epoch": 19, "eval/last/id_best": 5, "eval/last/lr_best": 1.3499999999999998e-05, "eval/last/wd_best": 0.05, "eval/last/train/loss": 0.592566728591919, "eval/last/train/acc": 0.6997840172786177, "eval/last/train/acc_std": 0.01771661436577667, "eval/last/train/f1": 0.6434772010880103, "eval/last/train/f1_std": 0.02316512947349564, "eval/last/train/bacc": 0.6422432485708653, "eval/last/train/bacc_std": 0.020130690624316175, "eval/last/validation/loss": 0.6362319588661194, "eval/last/validation/acc": 0.696969696969697, "eval/last/validation/acc_std": 0.039138873817858265, "eval/last/validation/f1": 0.6413043478260869, "eval/last/validation/f1_std": 0.051767170111456685, "eval/last/validation/bacc": 0.6423076923076924, "eval/last/validation/bacc_std": 0.044231276009731466, "eval/last/test/loss": 0.6528473496437073, "eval/last/test/acc": 0.61, "eval/last/test/acc_std": 0.0370594063632973, "eval/last/test/f1": 0.49942241047362346, "eval/last/test/f1_std": 0.04768442661555211, "eval/last/test/bacc": 0.5231660231660231, "eval/last/test/bacc_std": 0.038854928250301526} diff --git a/input_space_v3/flat_lr1e-3_1/eval_v2/ppmi_dx__patch__attn/eval_table.csv b/input_space_v3/flat_lr1e-3_1/eval_v2/ppmi_dx__patch__attn/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..a4ce7b78ae83d7df6214e049648f47da076eccdd --- /dev/null +++ b/input_space_v3/flat_lr1e-3_1/eval_v2/ppmi_dx__patch__attn/eval_table.csv @@ -0,0 +1,4 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std,bacc,bacc_std +flat_mae,patch,attn,ppmi_dx,best,10,0.00013199999999999998,0.05,19,"[0.44, 1.0]",train,0.4721227288246155,0.7775377969762419,0.019701765318171735,0.7666524766476325,0.020403957597703963,0.7686773112556673,0.020512997656709143 +flat_mae,patch,attn,ppmi_dx,best,10,0.00013199999999999998,0.05,19,"[0.44, 1.0]",validation,0.6690674424171448,0.6868686868686869,0.04674812078860053,0.6735453675140943,0.0486870415365517,0.6743589743589744,0.04896461204860454 +flat_mae,patch,attn,ppmi_dx,best,10,0.00013199999999999998,0.05,19,"[0.44, 1.0]",test,0.6794328093528748,0.59,0.044957273048973956,0.539894512400404,0.04936345405766934,0.5407550407550408,0.047017469378541815 diff --git a/input_space_v3/flat_lr1e-3_1/eval_v2/ppmi_dx__patch__attn/eval_table_best.csv b/input_space_v3/flat_lr1e-3_1/eval_v2/ppmi_dx__patch__attn/eval_table_best.csv new file mode 100644 index 0000000000000000000000000000000000000000..a4ce7b78ae83d7df6214e049648f47da076eccdd --- /dev/null +++ b/input_space_v3/flat_lr1e-3_1/eval_v2/ppmi_dx__patch__attn/eval_table_best.csv @@ -0,0 +1,4 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std,bacc,bacc_std +flat_mae,patch,attn,ppmi_dx,best,10,0.00013199999999999998,0.05,19,"[0.44, 1.0]",train,0.4721227288246155,0.7775377969762419,0.019701765318171735,0.7666524766476325,0.020403957597703963,0.7686773112556673,0.020512997656709143 +flat_mae,patch,attn,ppmi_dx,best,10,0.00013199999999999998,0.05,19,"[0.44, 1.0]",validation,0.6690674424171448,0.6868686868686869,0.04674812078860053,0.6735453675140943,0.0486870415365517,0.6743589743589744,0.04896461204860454 +flat_mae,patch,attn,ppmi_dx,best,10,0.00013199999999999998,0.05,19,"[0.44, 1.0]",test,0.6794328093528748,0.59,0.044957273048973956,0.539894512400404,0.04936345405766934,0.5407550407550408,0.047017469378541815 diff --git a/input_space_v3/flat_lr1e-3_1/eval_v2/ppmi_dx__patch__attn/eval_table_last.csv b/input_space_v3/flat_lr1e-3_1/eval_v2/ppmi_dx__patch__attn/eval_table_last.csv new file mode 100644 index 0000000000000000000000000000000000000000..b82eb8c6c69b61017dd803478a07cbf59cdcfc4c --- /dev/null +++ b/input_space_v3/flat_lr1e-3_1/eval_v2/ppmi_dx__patch__attn/eval_table_last.csv @@ -0,0 +1,4 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std,bacc,bacc_std +flat_mae,patch,attn,ppmi_dx,last,19,1.3499999999999998e-05,0.05,5,"[0.045, 1.0]",train,0.592566728591919,0.6997840172786177,0.01771661436577667,0.6434772010880103,0.02316512947349564,0.6422432485708653,0.020130690624316175 +flat_mae,patch,attn,ppmi_dx,last,19,1.3499999999999998e-05,0.05,5,"[0.045, 1.0]",validation,0.6362319588661194,0.696969696969697,0.039138873817858265,0.6413043478260869,0.051767170111456685,0.6423076923076924,0.044231276009731466 +flat_mae,patch,attn,ppmi_dx,last,19,1.3499999999999998e-05,0.05,5,"[0.045, 1.0]",test,0.6528473496437073,0.61,0.0370594063632973,0.49942241047362346,0.04768442661555211,0.5231660231660231,0.038854928250301526 diff --git a/input_space_v3/flat_lr1e-3_1/eval_v2/ppmi_dx__patch__attn/log.txt b/input_space_v3/flat_lr1e-3_1/eval_v2/ppmi_dx__patch__attn/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..f29b45c69b8bb2d5ad91a36a0e1c77e783d96db5 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_1/eval_v2/ppmi_dx__patch__attn/log.txt @@ -0,0 +1,1224 @@ +fMRI foundation model probe eval +version: 0.1.dev95+g65be98d36 +sha: 28a47a6a336052f679e36c7962a91fe73a2e9637, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-04-24 07:41:35 +config: +output_root: experiments/input_space_v3/output +name_prefix: eval_probe +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_1; eval v2 (ppmi_dx patch attn) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +dataset_kwargs: {} +classifier_kwargs: + embed_dim: null + dropout: 0.0 + xavier_init: true + norm: true +lr_scale_grid: +- 0.02 +- 0.023 +- 0.028 +- 0.033 +- 0.038 +- 0.045 +- 0.053 +- 0.062 +- 0.074 +- 0.087 +- 0.1 +- 0.12 +- 0.14 +- 0.17 +- 0.2 +- 0.23 +- 0.27 +- 0.32 +- 0.38 +- 0.44 +- 0.52 +- 0.61 +- 0.72 +- 0.85 +- 1 +- 1.2 +- 1.4 +- 1.6 +- 1.9 +- 2.3 +- 2.7 +- 3.1 +- 3.7 +- 4.3 +- 5.1 +- 6 +- 7.1 +- 8.3 +- 9.8 +- 12 +- 14 +- 16 +- 19 +- 22 +- 26 +- 31 +- 36 +- 43 +- 50 +wd_scale_grid: +- 1.0 +num_workers: 8 +prefetch_factor: null +balanced_sampling: false +epochs: 20 +steps_per_epoch: 200 +batch_size: 4 +accum_iter: 4 +lr: 0.0003 +warmup_epochs: 5 +no_decay: false +weight_decay: 0.05 +clip_grad: 1.0 +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +early_stopping: true +amp: true +device: cuda +seed: 4466 +debug: false +wandb: false +wandb_entity: null +wandb_project: fMRI-fm-eval +name: input_space_v3/flat_lr1e-3_1/eval_v2/ppmi_dx__patch__attn +base_lr: 3.0e-05 +model: flat_mae +representation: patch +classifier: attn +dataset: ppmi_dx +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/ppmi_dx__patch__attn +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=True, reg_tokens=0, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: ppmi_dx (flat) +train (n=463): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'dir', 'sex', 'age', 'age_bin', 'dx', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 463 +}), + labels=['PD' 'Prodromal'], + counts=[178 285] +) + +validation (n=99): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'dir', 'sex', 'age', 'age_bin', 'dx', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 99 +}), + labels=['PD' 'Prodromal'], + counts=[39 60] +) + +test (n=100): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'dir', 'sex', 'age', 'age_bin', 'dx', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 100 +}), + labels=['PD' 'Prodromal'], + counts=[37 63] +) + +running backbone on example batch to get embedding dim +embedding feature dim (patch): 768 +initializing sweep of classifier heads +classifiers: +ModuleList( + (0-48): 49 x AttnPoolClassifier( + (kv): Linear(in_features=768, out_features=1536, bias=True) + (linear): Linear(in_features=768, out_features=2, bias=True) + ) +) +classifier params (train): 58.0M (58.0M) +setting up optimizer +total batch size: 16 = 4 bs per gpu x 4 accum +lr: 3.00e-04 +full schedule: epochs = 20 (steps = 4000) (decay = True) +warmup: epochs = 5 (steps = 1000) +start training for 20 epochs +train: [0] [ 0/800] eta: 1:02:29 lr: nan time: 4.6863 data: 3.9441 max mem: 24352 +train: [0] [ 20/800] eta: 0:09:56 lr: 0.000001 loss: 0.7062 (0.7209) grad: 0.4802 (0.3952) time: 0.5680 data: 0.0028 max mem: 25051 +train: [0] [ 40/800] eta: 0:08:09 lr: 0.000003 loss: 0.7041 (0.7124) grad: 0.4155 (0.4190) time: 0.5174 data: 0.0032 max mem: 25051 +train: [0] [ 60/800] eta: 0:07:27 lr: 0.000004 loss: 0.7041 (0.7055) grad: 0.3202 (0.3828) time: 0.5264 data: 0.0030 max mem: 25051 +train: [0] [ 80/800] eta: 0:07:01 lr: 0.000006 loss: 0.6998 (0.6964) grad: 0.3202 (0.3719) time: 0.5238 data: 0.0033 max mem: 25051 +train: [0] [100/800] eta: 0:06:38 lr: 0.000007 loss: 0.6873 (0.6966) grad: 0.2514 (0.3484) time: 0.5068 data: 0.0029 max mem: 25051 +train: [0] [120/800] eta: 0:06:48 lr: 0.000009 loss: 0.6839 (0.6933) grad: 0.2514 (0.3425) time: 0.7605 data: 0.2266 max mem: 25051 +train: [0] [140/800] eta: 0:06:27 lr: 0.000010 loss: 0.6839 (0.6953) grad: 0.2504 (0.3326) time: 0.5071 data: 0.0028 max mem: 25051 +train: [0] [160/800] eta: 0:06:09 lr: 0.000012 loss: 0.7014 (0.7010) grad: 0.2531 (0.3235) time: 0.5051 data: 0.0029 max mem: 25051 +train: [0] [180/800] eta: 0:05:53 lr: 0.000013 loss: 0.6839 (0.6967) grad: 0.2629 (0.3320) time: 0.5082 data: 0.0032 max mem: 25051 +train: [0] [200/800] eta: 0:05:38 lr: 0.000015 loss: 0.7111 (0.7004) grad: 0.2641 (0.3326) time: 0.5080 data: 0.0030 max mem: 25051 +train: [0] [220/800] eta: 0:05:23 lr: 0.000016 loss: 0.7111 (0.7029) grad: 0.2641 (0.3276) time: 0.4936 data: 0.0029 max mem: 25051 +train: [0] [240/800] eta: 0:05:20 lr: 0.000018 loss: 0.6734 (0.6936) grad: 0.2929 (0.3253) time: 0.7437 data: 0.2100 max mem: 25051 +train: [0] [260/800] eta: 0:05:07 lr: 0.000019 loss: 0.6517 (0.6863) grad: 0.2929 (0.3269) time: 0.5384 data: 0.0026 max mem: 25051 +train: [0] [280/800] eta: 0:04:55 lr: 0.000021 loss: 0.6517 (0.6898) grad: 0.2804 (0.3333) time: 0.5327 data: 0.0033 max mem: 25051 +train: [0] [300/800] eta: 0:04:41 lr: 0.000022 loss: 0.6228 (0.6875) grad: 0.2804 (0.3303) time: 0.4996 data: 0.0034 max mem: 25051 +train: [0] [320/800] eta: 0:04:29 lr: 0.000024 loss: 0.6529 (0.6863) grad: 0.2804 (0.3263) time: 0.5482 data: 0.0036 max mem: 25051 +train: [0] [340/800] eta: 0:04:17 lr: 0.000025 loss: 0.6759 (0.6891) grad: 0.2081 (0.3176) time: 0.5100 data: 0.0029 max mem: 25051 +train: [0] [360/800] eta: 0:04:10 lr: 0.000027 loss: 0.6529 (0.6856) grad: 0.1758 (0.3097) time: 0.7330 data: 0.2126 max mem: 25051 +train: [0] [380/800] eta: 0:03:57 lr: 0.000028 loss: 0.6759 (0.6853) grad: 0.1970 (0.3075) time: 0.5109 data: 0.0031 max mem: 25051 +train: [0] [400/800] eta: 0:03:44 lr: 0.000030 loss: 0.6753 (0.6850) grad: 0.1935 (0.3059) time: 0.5003 data: 0.0032 max mem: 25051 +train: [0] [420/800] eta: 0:03:32 lr: 0.000031 loss: 0.6709 (0.6860) grad: 0.2483 (0.3104) time: 0.5209 data: 0.0030 max mem: 25051 +train: [0] [440/800] eta: 0:03:21 lr: 0.000033 loss: 0.6672 (0.6800) grad: 0.2511 (0.3089) time: 0.5153 data: 0.0031 max mem: 25051 +train: [0] [460/800] eta: 0:03:12 lr: 0.000034 loss: 0.6443 (0.6773) grad: 0.2502 (0.3089) time: 0.7294 data: 0.2384 max mem: 25051 +train: [0] [480/800] eta: 0:03:01 lr: 0.000036 loss: 0.6204 (0.6755) grad: 0.2483 (0.3065) time: 0.5901 data: 0.0351 max mem: 25051 +train: [0] [500/800] eta: 0:02:49 lr: 0.000037 loss: 0.6167 (0.6757) grad: 0.2419 (0.3074) time: 0.5166 data: 0.0034 max mem: 25051 +train: [0] [520/800] eta: 0:02:37 lr: 0.000039 loss: 0.6372 (0.6729) grad: 0.2309 (0.3041) time: 0.5424 data: 0.0035 max mem: 25051 +train: [0] [540/800] eta: 0:02:26 lr: 0.000040 loss: 0.6167 (0.6709) grad: 0.2130 (0.3005) time: 0.5429 data: 0.0035 max mem: 25051 +train: [0] [560/800] eta: 0:02:14 lr: 0.000042 loss: 0.6422 (0.6712) grad: 0.2130 (0.2977) time: 0.5143 data: 0.0032 max mem: 25051 +train: [0] [580/800] eta: 0:02:04 lr: 0.000043 loss: 0.6422 (0.6744) grad: 0.2113 (0.2967) time: 0.7489 data: 0.2272 max mem: 25051 +train: [0] [600/800] eta: 0:01:53 lr: 0.000045 loss: 0.6422 (0.6710) grad: 0.2373 (0.2954) time: 0.5463 data: 0.0034 max mem: 25051 +train: [0] [620/800] eta: 0:01:41 lr: 0.000046 loss: 0.6422 (0.6691) grad: 0.2542 (0.2936) time: 0.5364 data: 0.0035 max mem: 25051 +train: [0] [640/800] eta: 0:01:30 lr: 0.000048 loss: 0.6356 (0.6691) grad: 0.2415 (0.2907) time: 0.5197 data: 0.0031 max mem: 25051 +train: [0] [660/800] eta: 0:01:18 lr: 0.000049 loss: 0.5853 (0.6667) grad: 0.2415 (0.2923) time: 0.5145 data: 0.0032 max mem: 25051 +train: [0] [680/800] eta: 0:01:07 lr: 0.000051 loss: 0.6313 (0.6667) grad: 0.2415 (0.2925) time: 0.5297 data: 0.0033 max mem: 25051 +train: [0] [700/800] eta: 0:00:56 lr: 0.000052 loss: 0.6274 (0.6668) grad: 0.2790 (0.2923) time: 0.7172 data: 0.2225 max mem: 25051 +train: [0] [720/800] eta: 0:00:45 lr: 0.000054 loss: 0.6207 (0.6661) grad: 0.2790 (0.2907) time: 0.5167 data: 0.0026 max mem: 25051 +train: [0] [740/800] eta: 0:00:33 lr: 0.000055 loss: 0.6207 (0.6642) grad: 0.2483 (0.2918) time: 0.5369 data: 0.0026 max mem: 25051 +train: [0] [760/800] eta: 0:00:22 lr: 0.000057 loss: 0.6207 (0.6621) grad: 0.2915 (0.2935) time: 0.5376 data: 0.0029 max mem: 25051 +train: [0] [780/800] eta: 0:00:11 lr: 0.000058 loss: 0.6357 (0.6626) grad: 0.2840 (0.2932) time: 0.5138 data: 0.0036 max mem: 25051 +train: [0] [799/800] eta: 0:00:00 lr: 0.000060 loss: 0.6357 (0.6615) grad: 0.2879 (0.2923) time: 0.5033 data: 0.0032 max mem: 25051 +train: [0] Total time: 0:07:29 (0.5613 s / it) +train: [0] Summary: lr: 0.000060 loss: 0.6357 (0.6615) grad: 0.2879 (0.2923) +eval (validation): [0] [ 0/25] eta: 0:01:42 time: 4.1047 data: 3.8073 max mem: 25051 +eval (validation): [0] [20/25] eta: 0:00:03 time: 0.4801 data: 0.0897 max mem: 25051 +eval (validation): [0] [24/25] eta: 0:00:00 time: 0.4246 data: 0.0515 max mem: 25051 +eval (validation): [0] Total time: 0:00:15 (0.6184 s / it) +cv: [0] best hparam: (36, 1.0) (046) ('046_lr3.6e+01_wd1.0e+00') loss: 0.695 acc: 0.697 f1: 0.659 bacc: 0.656 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/ppmi_dx__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/ppmi_dx__patch__attn/checkpoint-best.pth +train: [1] [ 0/800] eta: 0:57:47 lr: nan time: 4.3347 data: 3.9498 max mem: 25051 +train: [1] [ 20/800] eta: 0:09:43 lr: 0.000061 loss: 0.7635 (0.8220) grad: 0.2728 (0.2722) time: 0.5689 data: 0.0037 max mem: 25051 +train: [1] [ 40/800] eta: 0:07:58 lr: 0.000063 loss: 0.6838 (0.7216) grad: 0.2728 (0.2657) time: 0.5045 data: 0.0033 max mem: 25051 +train: [1] [ 60/800] eta: 0:07:17 lr: 0.000064 loss: 0.6313 (0.6553) grad: 0.2728 (0.2666) time: 0.5126 data: 0.0037 max mem: 25051 +train: [1] [ 80/800] eta: 0:06:52 lr: 0.000066 loss: 0.6000 (0.6348) grad: 0.2685 (0.2760) time: 0.5159 data: 0.0035 max mem: 25051 +train: [1] [100/800] eta: 0:06:33 lr: 0.000067 loss: 0.5852 (0.6341) grad: 0.2528 (0.2703) time: 0.5223 data: 0.0032 max mem: 25051 +train: [1] [120/800] eta: 0:06:38 lr: 0.000069 loss: 0.5859 (0.6393) grad: 0.2166 (0.2602) time: 0.7068 data: 0.2066 max mem: 25051 +train: [1] [140/800] eta: 0:06:22 lr: 0.000070 loss: 0.6343 (0.6437) grad: 0.2005 (0.2557) time: 0.5395 data: 0.0030 max mem: 25051 +train: [1] [160/800] eta: 0:06:05 lr: 0.000072 loss: 0.6521 (0.6414) grad: 0.1945 (0.2458) time: 0.5039 data: 0.0031 max mem: 25051 +train: [1] [180/800] eta: 0:05:50 lr: 0.000073 loss: 0.6521 (0.6352) grad: 0.1717 (0.2451) time: 0.5251 data: 0.0030 max mem: 25051 +train: [1] [200/800] eta: 0:05:35 lr: 0.000075 loss: 0.6062 (0.6339) grad: 0.1716 (0.2444) time: 0.5092 data: 0.0030 max mem: 25051 +train: [1] [220/800] eta: 0:05:21 lr: 0.000076 loss: 0.5677 (0.6195) grad: 0.1711 (0.2394) time: 0.5065 data: 0.0030 max mem: 25051 +train: [1] [240/800] eta: 0:05:19 lr: 0.000078 loss: 0.5727 (0.6310) grad: 0.1833 (0.2405) time: 0.7331 data: 0.2195 max mem: 25051 +train: [1] [260/800] eta: 0:05:05 lr: 0.000079 loss: 0.5727 (0.6302) grad: 0.1859 (0.2376) time: 0.5219 data: 0.0024 max mem: 25051 +train: [1] [280/800] eta: 0:04:51 lr: 0.000081 loss: 0.5727 (0.6272) grad: 0.2032 (0.2444) time: 0.4976 data: 0.0031 max mem: 25051 +train: [1] [300/800] eta: 0:04:39 lr: 0.000082 loss: 0.6215 (0.6209) grad: 0.2032 (0.2400) time: 0.5188 data: 0.0030 max mem: 25051 +train: [1] [320/800] eta: 0:04:26 lr: 0.000084 loss: 0.5238 (0.6226) grad: 0.1810 (0.2405) time: 0.5181 data: 0.0032 max mem: 25051 +train: [1] [340/800] eta: 0:04:14 lr: 0.000085 loss: 0.6060 (0.6216) grad: 0.1810 (0.2393) time: 0.4998 data: 0.0029 max mem: 25051 +train: [1] [360/800] eta: 0:04:06 lr: 0.000087 loss: 0.6193 (0.6230) grad: 0.1743 (0.2391) time: 0.6981 data: 0.2082 max mem: 25051 +train: [1] [380/800] eta: 0:03:54 lr: 0.000088 loss: 0.6543 (0.6271) grad: 0.2066 (0.2467) time: 0.4981 data: 0.0029 max mem: 25051 +train: [1] [400/800] eta: 0:03:41 lr: 0.000090 loss: 0.6534 (0.6247) grad: 0.2533 (0.2482) time: 0.4975 data: 0.0034 max mem: 25051 +train: [1] [420/800] eta: 0:03:29 lr: 0.000091 loss: 0.6534 (0.6284) grad: 0.2533 (0.2467) time: 0.5069 data: 0.0031 max mem: 25051 +train: [1] [440/800] eta: 0:03:17 lr: 0.000093 loss: 0.6312 (0.6277) grad: 0.2533 (0.2454) time: 0.4912 data: 0.0031 max mem: 25051 +train: [1] [460/800] eta: 0:03:09 lr: 0.000094 loss: 0.5914 (0.6284) grad: 0.2516 (0.2489) time: 0.7220 data: 0.2310 max mem: 25051 +train: [1] [480/800] eta: 0:02:58 lr: 0.000096 loss: 0.6282 (0.6319) grad: 0.2516 (0.2546) time: 0.5984 data: 0.0027 max mem: 25051 +train: [1] [500/800] eta: 0:02:47 lr: 0.000097 loss: 0.5991 (0.6303) grad: 0.2813 (0.2563) time: 0.5158 data: 0.0025 max mem: 25051 +train: [1] [520/800] eta: 0:02:35 lr: 0.000099 loss: 0.5693 (0.6272) grad: 0.2687 (0.2550) time: 0.5125 data: 0.0026 max mem: 25051 +train: [1] [540/800] eta: 0:02:23 lr: 0.000100 loss: 0.6051 (0.6293) grad: 0.2676 (0.2561) time: 0.5035 data: 0.0032 max mem: 25051 +train: [1] [560/800] eta: 0:02:12 lr: 0.000102 loss: 0.6051 (0.6311) grad: 0.2542 (0.2604) time: 0.4990 data: 0.0027 max mem: 25051 +train: [1] [580/800] eta: 0:02:02 lr: 0.000103 loss: 0.6051 (0.6304) grad: 0.2459 (0.2624) time: 0.7041 data: 0.2185 max mem: 25051 +train: [1] [600/800] eta: 0:01:51 lr: 0.000105 loss: 0.6240 (0.6294) grad: 0.2459 (0.2615) time: 0.5384 data: 0.0033 max mem: 25051 +train: [1] [620/800] eta: 0:01:39 lr: 0.000106 loss: 0.6240 (0.6302) grad: 0.2480 (0.2622) time: 0.5262 data: 0.0032 max mem: 25051 +train: [1] [640/800] eta: 0:01:28 lr: 0.000108 loss: 0.5823 (0.6297) grad: 0.2537 (0.2640) time: 0.5626 data: 0.0036 max mem: 25051 +train: [1] [660/800] eta: 0:01:17 lr: 0.000109 loss: 0.5917 (0.6293) grad: 0.2537 (0.2667) time: 0.5090 data: 0.0034 max mem: 25051 +train: [1] [680/800] eta: 0:01:06 lr: 0.000111 loss: 0.6118 (0.6318) grad: 0.2904 (0.2690) time: 0.5184 data: 0.0027 max mem: 25051 +train: [1] [700/800] eta: 0:00:55 lr: 0.000112 loss: 0.5930 (0.6311) grad: 0.2997 (0.2698) time: 0.7586 data: 0.2356 max mem: 25051 +train: [1] [720/800] eta: 0:00:44 lr: 0.000114 loss: 0.5930 (0.6311) grad: 0.3036 (0.2741) time: 0.5460 data: 0.0032 max mem: 25051 +train: [1] [740/800] eta: 0:00:33 lr: 0.000115 loss: 0.5693 (0.6275) grad: 0.3021 (0.2752) time: 0.5233 data: 0.0032 max mem: 25051 +train: [1] [760/800] eta: 0:00:22 lr: 0.000117 loss: 0.5496 (0.6254) grad: 0.3036 (0.2773) time: 0.5635 data: 0.0036 max mem: 25051 +train: [1] [780/800] eta: 0:00:11 lr: 0.000118 loss: 0.5655 (0.6279) grad: 0.3307 (0.2805) time: 0.5604 data: 0.0034 max mem: 25051 +train: [1] [799/800] eta: 0:00:00 lr: 0.000120 loss: 0.5882 (0.6302) grad: 0.3101 (0.2822) time: 0.5161 data: 0.0032 max mem: 25051 +train: [1] Total time: 0:07:25 (0.5569 s / it) +train: [1] Summary: lr: 0.000120 loss: 0.5882 (0.6302) grad: 0.3101 (0.2822) +eval (validation): [1] [ 0/25] eta: 0:01:48 time: 4.3409 data: 4.0571 max mem: 25051 +eval (validation): [1] [20/25] eta: 0:00:02 time: 0.3646 data: 0.0020 max mem: 25051 +eval (validation): [1] [24/25] eta: 0:00:00 time: 0.3664 data: 0.0022 max mem: 25051 +eval (validation): [1] Total time: 0:00:13 (0.5356 s / it) +cv: [1] best hparam: (0.38, 1.0) (018) ('018_lr3.8e-01_wd1.0e+00') loss: 0.650 acc: 0.687 f1: 0.650 bacc: 0.647 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/ppmi_dx__patch__attn/checkpoint-last.pth +train: [2] [ 0/800] eta: 1:01:13 lr: nan time: 4.5921 data: 4.1631 max mem: 25051 +train: [2] [ 20/800] eta: 0:09:29 lr: 0.000121 loss: 0.5157 (0.5847) grad: 0.3612 (0.4219) time: 0.5373 data: 0.0042 max mem: 25051 +train: [2] [ 40/800] eta: 0:07:59 lr: 0.000123 loss: 0.5691 (0.6483) grad: 0.3328 (0.3648) time: 0.5264 data: 0.0027 max mem: 25051 +train: [2] [ 60/800] eta: 0:07:18 lr: 0.000124 loss: 0.6057 (0.6569) grad: 0.3263 (0.3453) time: 0.5160 data: 0.0034 max mem: 25051 +train: [2] [ 80/800] eta: 0:06:56 lr: 0.000126 loss: 0.6057 (0.6639) grad: 0.3263 (0.3498) time: 0.5324 data: 0.0034 max mem: 25051 +train: [2] [100/800] eta: 0:06:37 lr: 0.000127 loss: 0.6196 (0.6546) grad: 0.3304 (0.3727) time: 0.5244 data: 0.0035 max mem: 25051 +train: [2] [120/800] eta: 0:06:42 lr: 0.000129 loss: 0.6196 (0.6669) grad: 0.4022 (0.3976) time: 0.7129 data: 0.2118 max mem: 25051 +train: [2] [140/800] eta: 0:06:24 lr: 0.000130 loss: 0.6698 (0.6678) grad: 0.4195 (0.4091) time: 0.5254 data: 0.0035 max mem: 25051 +train: [2] [160/800] eta: 0:06:08 lr: 0.000132 loss: 0.6858 (0.6640) grad: 0.4565 (0.4117) time: 0.5255 data: 0.0027 max mem: 25051 +train: [2] [180/800] eta: 0:05:53 lr: 0.000133 loss: 0.6312 (0.6509) grad: 0.4075 (0.4118) time: 0.5334 data: 0.0031 max mem: 25051 +train: [2] [200/800] eta: 0:05:40 lr: 0.000135 loss: 0.6064 (0.6390) grad: 0.4045 (0.4157) time: 0.5404 data: 0.0034 max mem: 25051 +train: [2] [220/800] eta: 0:05:26 lr: 0.000136 loss: 0.5684 (0.6477) grad: 0.4034 (0.4153) time: 0.5203 data: 0.0033 max mem: 25051 +train: [2] [240/800] eta: 0:05:28 lr: 0.000138 loss: 0.6064 (0.6481) grad: 0.3670 (0.4086) time: 0.8426 data: 0.3079 max mem: 25051 +train: [2] [260/800] eta: 0:05:14 lr: 0.000139 loss: 0.6531 (0.6483) grad: 0.3485 (0.4002) time: 0.5435 data: 0.0025 max mem: 25051 +train: [2] [280/800] eta: 0:05:00 lr: 0.000141 loss: 0.6531 (0.6368) grad: 0.3134 (0.3930) time: 0.5147 data: 0.0027 max mem: 25051 +train: [2] [300/800] eta: 0:04:46 lr: 0.000142 loss: 0.6531 (0.6375) grad: 0.3092 (0.3891) time: 0.5084 data: 0.0030 max mem: 25051 +train: [2] [320/800] eta: 0:04:33 lr: 0.000144 loss: 0.5979 (0.6362) grad: 0.3081 (0.3900) time: 0.5120 data: 0.0031 max mem: 25051 +train: [2] [340/800] eta: 0:04:20 lr: 0.000145 loss: 0.5979 (0.6434) grad: 0.3439 (0.3935) time: 0.5010 data: 0.0030 max mem: 25051 +train: [2] [360/800] eta: 0:04:13 lr: 0.000147 loss: 0.6725 (0.6440) grad: 0.3702 (0.3918) time: 0.7370 data: 0.2177 max mem: 25051 +train: [2] [380/800] eta: 0:04:00 lr: 0.000148 loss: 0.6725 (0.6450) grad: 0.3702 (0.3915) time: 0.5144 data: 0.0037 max mem: 25051 +train: [2] [400/800] eta: 0:03:47 lr: 0.000150 loss: 0.6886 (0.6465) grad: 0.3448 (0.3912) time: 0.4936 data: 0.0035 max mem: 25051 +train: [2] [420/800] eta: 0:03:34 lr: 0.000151 loss: 0.6725 (0.6485) grad: 0.3437 (0.3900) time: 0.4984 data: 0.0031 max mem: 25051 +train: [2] [440/800] eta: 0:03:22 lr: 0.000153 loss: 0.6474 (0.6454) grad: 0.3691 (0.3927) time: 0.5008 data: 0.0032 max mem: 25051 +train: [2] [460/800] eta: 0:03:13 lr: 0.000154 loss: 0.6474 (0.6459) grad: 0.3710 (0.3935) time: 0.7191 data: 0.2239 max mem: 25051 +train: [2] [480/800] eta: 0:03:01 lr: 0.000156 loss: 0.6206 (0.6409) grad: 0.4016 (0.3936) time: 0.5174 data: 0.0034 max mem: 25051 +train: [2] [500/800] eta: 0:02:49 lr: 0.000157 loss: 0.6206 (0.6421) grad: 0.3722 (0.3911) time: 0.5192 data: 0.0027 max mem: 25051 +train: [2] [520/800] eta: 0:02:38 lr: 0.000159 loss: 0.5896 (0.6422) grad: 0.3511 (0.3894) time: 0.5700 data: 0.0039 max mem: 25051 +train: [2] [540/800] eta: 0:02:26 lr: 0.000160 loss: 0.5868 (0.6391) grad: 0.3413 (0.3911) time: 0.5152 data: 0.0033 max mem: 25051 +train: [2] [560/800] eta: 0:02:14 lr: 0.000162 loss: 0.5868 (0.6346) grad: 0.3374 (0.3910) time: 0.5231 data: 0.0036 max mem: 25051 +train: [2] [580/800] eta: 0:02:04 lr: 0.000163 loss: 0.5857 (0.6360) grad: 0.3647 (0.3909) time: 0.7161 data: 0.2227 max mem: 25051 +train: [2] [600/800] eta: 0:01:52 lr: 0.000165 loss: 0.5781 (0.6328) grad: 0.3724 (0.3928) time: 0.4956 data: 0.0058 max mem: 25051 +train: [2] [620/800] eta: 0:01:41 lr: 0.000166 loss: 0.5781 (0.6308) grad: 0.3774 (0.3927) time: 0.5088 data: 0.0023 max mem: 25051 +train: [2] [640/800] eta: 0:01:29 lr: 0.000168 loss: 0.6210 (0.6339) grad: 0.3680 (0.3916) time: 0.4989 data: 0.0029 max mem: 25051 +train: [2] [660/800] eta: 0:01:18 lr: 0.000169 loss: 0.6433 (0.6363) grad: 0.3774 (0.3931) time: 0.4819 data: 0.0030 max mem: 25051 +train: [2] [680/800] eta: 0:01:06 lr: 0.000171 loss: 0.6543 (0.6380) grad: 0.3820 (0.3976) time: 0.4813 data: 0.0029 max mem: 25051 +train: [2] [700/800] eta: 0:00:56 lr: 0.000172 loss: 0.6568 (0.6408) grad: 0.4348 (0.4002) time: 0.6919 data: 0.1999 max mem: 25051 +train: [2] [720/800] eta: 0:00:44 lr: 0.000174 loss: 0.6568 (0.6425) grad: 0.4489 (0.4017) time: 0.5693 data: 0.0027 max mem: 25051 +train: [2] [740/800] eta: 0:00:33 lr: 0.000175 loss: 0.6332 (0.6437) grad: 0.4421 (0.4038) time: 0.5646 data: 0.0036 max mem: 25051 +train: [2] [760/800] eta: 0:00:22 lr: 0.000177 loss: 0.6332 (0.6440) grad: 0.4421 (0.4060) time: 0.5131 data: 0.0032 max mem: 25051 +train: [2] [780/800] eta: 0:00:11 lr: 0.000178 loss: 0.6272 (0.6445) grad: 0.4890 (0.4120) time: 0.5093 data: 0.0032 max mem: 25051 +train: [2] [799/800] eta: 0:00:00 lr: 0.000180 loss: 0.6332 (0.6456) grad: 0.5431 (0.4195) time: 0.5220 data: 0.0032 max mem: 25051 +train: [2] Total time: 0:07:25 (0.5573 s / it) +train: [2] Summary: lr: 0.000180 loss: 0.6332 (0.6456) grad: 0.5431 (0.4195) +eval (validation): [2] [ 0/25] eta: 0:01:53 time: 4.5433 data: 4.2317 max mem: 25051 +eval (validation): [2] [20/25] eta: 0:00:03 time: 0.4842 data: 0.0123 max mem: 25051 +eval (validation): [2] [24/25] eta: 0:00:00 time: 0.4460 data: 0.0123 max mem: 25051 +eval (validation): [2] Total time: 0:00:15 (0.6338 s / it) +cv: [2] best hparam: (0.2, 1.0) (014) ('014_lr2.0e-01_wd1.0e+00') loss: 0.648 acc: 0.677 f1: 0.636 bacc: 0.635 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/ppmi_dx__patch__attn/checkpoint-last.pth +train: [3] [ 0/800] eta: 0:53:20 lr: nan time: 4.0008 data: 3.6433 max mem: 25051 +train: [3] [ 20/800] eta: 0:08:58 lr: 0.000181 loss: 0.6165 (0.7364) grad: 0.5420 (0.6031) time: 0.5255 data: 0.0036 max mem: 25051 +train: [3] [ 40/800] eta: 0:07:43 lr: 0.000183 loss: 0.5447 (0.6363) grad: 0.5410 (0.5684) time: 0.5241 data: 0.0027 max mem: 25051 +train: [3] [ 60/800] eta: 0:07:10 lr: 0.000184 loss: 0.6165 (0.6489) grad: 0.5420 (0.5503) time: 0.5235 data: 0.0028 max mem: 25051 +train: [3] [ 80/800] eta: 0:06:43 lr: 0.000186 loss: 0.6073 (0.6625) grad: 0.5410 (0.5396) time: 0.4965 data: 0.0018 max mem: 25051 +train: [3] [100/800] eta: 0:06:29 lr: 0.000187 loss: 0.6744 (0.6754) grad: 0.5042 (0.5227) time: 0.5395 data: 0.0029 max mem: 25051 +train: [3] [120/800] eta: 0:06:43 lr: 0.000189 loss: 0.6744 (0.6795) grad: 0.4373 (0.5031) time: 0.7827 data: 0.2651 max mem: 25051 +train: [3] [140/800] eta: 0:06:25 lr: 0.000190 loss: 0.6744 (0.6840) grad: 0.3971 (0.4833) time: 0.5225 data: 0.0032 max mem: 25051 +train: [3] [160/800] eta: 0:06:06 lr: 0.000192 loss: 0.6564 (0.6602) grad: 0.3904 (0.4758) time: 0.4982 data: 0.0028 max mem: 25051 +train: [3] [180/800] eta: 0:05:51 lr: 0.000193 loss: 0.6063 (0.6554) grad: 0.3884 (0.4855) time: 0.5165 data: 0.0033 max mem: 25051 +train: [3] [200/800] eta: 0:05:37 lr: 0.000195 loss: 0.6093 (0.6571) grad: 0.4275 (0.4889) time: 0.5281 data: 0.0035 max mem: 25051 +train: [3] [220/800] eta: 0:05:23 lr: 0.000196 loss: 0.5659 (0.6590) grad: 0.4830 (0.4962) time: 0.5063 data: 0.0033 max mem: 25051 +train: [3] [240/800] eta: 0:05:19 lr: 0.000198 loss: 0.6093 (0.6650) grad: 0.5076 (0.5053) time: 0.7177 data: 0.2023 max mem: 25051 +train: [3] [260/800] eta: 0:05:06 lr: 0.000199 loss: 0.6102 (0.6574) grad: 0.5130 (0.5094) time: 0.5244 data: 0.0035 max mem: 25051 +train: [3] [280/800] eta: 0:04:53 lr: 0.000201 loss: 0.7078 (0.6583) grad: 0.5265 (0.5135) time: 0.5166 data: 0.0024 max mem: 25051 +train: [3] [300/800] eta: 0:04:41 lr: 0.000202 loss: 0.7078 (0.6565) grad: 0.5265 (0.5212) time: 0.5495 data: 0.0033 max mem: 25051 +train: [3] [320/800] eta: 0:04:28 lr: 0.000204 loss: 0.6405 (0.6606) grad: 0.5611 (0.5311) time: 0.5103 data: 0.0028 max mem: 25051 +train: [3] [340/800] eta: 0:04:16 lr: 0.000205 loss: 0.6433 (0.6614) grad: 0.6421 (0.5360) time: 0.5135 data: 0.0029 max mem: 25051 +train: [3] [360/800] eta: 0:04:10 lr: 0.000207 loss: 0.6405 (0.6569) grad: 0.6028 (0.5349) time: 0.7604 data: 0.2445 max mem: 25051 +train: [3] [380/800] eta: 0:03:57 lr: 0.000208 loss: 0.5941 (0.6545) grad: 0.5852 (0.5325) time: 0.5099 data: 0.0028 max mem: 25051 +train: [3] [400/800] eta: 0:03:44 lr: 0.000210 loss: 0.5941 (0.6570) grad: 0.5232 (0.5325) time: 0.5005 data: 0.0031 max mem: 25051 +train: [3] [420/800] eta: 0:03:32 lr: 0.000211 loss: 0.5701 (0.6536) grad: 0.4815 (0.5319) time: 0.5098 data: 0.0031 max mem: 25051 +train: [3] [440/800] eta: 0:03:20 lr: 0.000213 loss: 0.5651 (0.6472) grad: 0.5054 (0.5308) time: 0.4977 data: 0.0028 max mem: 25051 +train: [3] [460/800] eta: 0:03:11 lr: 0.000214 loss: 0.5440 (0.6414) grad: 0.4944 (0.5287) time: 0.7108 data: 0.2184 max mem: 25051 +train: [3] [480/800] eta: 0:02:59 lr: 0.000216 loss: 0.5455 (0.6404) grad: 0.4944 (0.5331) time: 0.5304 data: 0.0026 max mem: 25051 +WARNING: classifier 48 (50, 1.0) diverged (loss=14.29 > 13.86) at step 721. Freezing. +train: [3] [500/800] eta: 0:02:47 lr: 0.000217 loss: 0.5597 (0.6414) grad: 0.4944 (0.5348) time: 0.5088 data: 0.0033 max mem: 25051 +train: [3] [520/800] eta: 0:02:36 lr: 0.000219 loss: 0.5784 (0.6414) grad: 0.4723 (0.5316) time: 0.5161 data: 0.0034 max mem: 25051 +train: [3] [540/800] eta: 0:02:24 lr: 0.000220 loss: 0.6151 (0.6430) grad: 0.4723 (0.5292) time: 0.5105 data: 0.0032 max mem: 25051 +train: [3] [560/800] eta: 0:02:13 lr: 0.000222 loss: 0.6136 (0.6419) grad: 0.4151 (0.5244) time: 0.5470 data: 0.0034 max mem: 25051 +train: [3] [580/800] eta: 0:02:03 lr: 0.000223 loss: 0.6136 (0.6456) grad: 0.4518 (0.5278) time: 0.7076 data: 0.2136 max mem: 25051 +train: [3] [600/800] eta: 0:01:52 lr: 0.000225 loss: 0.6136 (0.6473) grad: 0.4641 (0.5303) time: 0.5265 data: 0.0034 max mem: 25051 +train: [3] [620/800] eta: 0:01:40 lr: 0.000226 loss: 0.6637 (0.6487) grad: 0.4781 (0.5308) time: 0.5329 data: 0.0019 max mem: 25051 +train: [3] [640/800] eta: 0:01:29 lr: 0.000228 loss: 0.7386 (0.6542) grad: 0.5252 (0.5330) time: 0.5533 data: 0.0028 max mem: 25051 +train: [3] [660/800] eta: 0:01:18 lr: 0.000229 loss: 0.6637 (0.6537) grad: 0.5211 (0.5348) time: 0.5110 data: 0.0036 max mem: 25051 +train: [3] [680/800] eta: 0:01:06 lr: 0.000231 loss: 0.6171 (0.6504) grad: 0.5211 (0.5326) time: 0.5007 data: 0.0034 max mem: 25051 +train: [3] [700/800] eta: 0:00:56 lr: 0.000232 loss: 0.6171 (0.6522) grad: 0.5211 (0.5326) time: 0.7431 data: 0.2240 max mem: 25051 +train: [3] [720/800] eta: 0:00:44 lr: 0.000234 loss: 0.5757 (0.6490) grad: 0.5211 (0.5343) time: 0.5073 data: 0.0035 max mem: 25051 +train: [3] [740/800] eta: 0:00:33 lr: 0.000235 loss: 0.5357 (0.6473) grad: 0.5040 (0.5356) time: 0.5106 data: 0.0038 max mem: 25051 +train: [3] [760/800] eta: 0:00:22 lr: 0.000237 loss: 0.6172 (0.6488) grad: 0.5351 (0.5376) time: 0.5122 data: 0.0038 max mem: 25051 +train: [3] [780/800] eta: 0:00:11 lr: 0.000238 loss: 0.5824 (0.6464) grad: 0.5814 (0.5379) time: 0.5133 data: 0.0034 max mem: 25051 +train: [3] [799/800] eta: 0:00:00 lr: 0.000240 loss: 0.6172 (0.6465) grad: 0.5814 (0.5421) time: 0.5023 data: 0.0034 max mem: 25051 +train: [3] Total time: 0:07:24 (0.5551 s / it) +train: [3] Summary: lr: 0.000240 loss: 0.6172 (0.6465) grad: 0.5814 (0.5421) +eval (validation): [3] [ 0/25] eta: 0:01:43 time: 4.1356 data: 3.8693 max mem: 25051 +eval (validation): [3] [20/25] eta: 0:00:03 time: 0.4311 data: 0.0734 max mem: 25051 +eval (validation): [3] [24/25] eta: 0:00:00 time: 0.3815 data: 0.0230 max mem: 25051 +eval (validation): [3] Total time: 0:00:14 (0.5744 s / it) +cv: [3] best hparam: (0.12, 1.0) (011) ('011_lr1.2e-01_wd1.0e+00') loss: 0.646 acc: 0.687 f1: 0.650 bacc: 0.647 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/ppmi_dx__patch__attn/checkpoint-last.pth +train: [4] [ 0/800] eta: 0:57:04 lr: nan time: 4.2806 data: 3.8502 max mem: 25051 +train: [4] [ 20/800] eta: 0:09:02 lr: 0.000241 loss: 0.7761 (0.7024) grad: 0.7786 (0.7475) time: 0.5168 data: 0.0033 max mem: 25051 +WARNING: classifier 46 (36, 1.0) diverged (loss=21.03 > 13.86) at step 807. Freezing. +train: [4] [ 40/800] eta: 0:07:41 lr: 0.000243 loss: 0.6493 (0.6940) grad: 0.6087 (0.6457) time: 0.5135 data: 0.0032 max mem: 25051 +train: [4] [ 60/800] eta: 0:07:03 lr: 0.000244 loss: 0.6493 (0.6546) grad: 0.4752 (0.5643) time: 0.5012 data: 0.0036 max mem: 25051 +train: [4] [ 80/800] eta: 0:06:39 lr: 0.000246 loss: 0.6175 (0.6410) grad: 0.4752 (0.5610) time: 0.5002 data: 0.0037 max mem: 25051 +train: [4] [100/800] eta: 0:06:20 lr: 0.000247 loss: 0.6175 (0.6479) grad: 0.4752 (0.5507) time: 0.4974 data: 0.0036 max mem: 25051 +train: [4] [120/800] eta: 0:06:27 lr: 0.000249 loss: 0.6175 (0.6408) grad: 0.4920 (0.5596) time: 0.7013 data: 0.2063 max mem: 25051 +train: [4] [140/800] eta: 0:06:14 lr: 0.000250 loss: 0.6175 (0.6299) grad: 0.5381 (0.5622) time: 0.5554 data: 0.0032 max mem: 25051 +train: [4] [160/800] eta: 0:06:02 lr: 0.000252 loss: 0.5727 (0.6196) grad: 0.5197 (0.5652) time: 0.5639 data: 0.0028 max mem: 25051 +train: [4] [180/800] eta: 0:05:47 lr: 0.000253 loss: 0.5283 (0.6171) grad: 0.5102 (0.5534) time: 0.5071 data: 0.0032 max mem: 25051 +train: [4] [200/800] eta: 0:05:34 lr: 0.000255 loss: 0.5301 (0.6139) grad: 0.4715 (0.5405) time: 0.5290 data: 0.0030 max mem: 25051 +train: [4] [220/800] eta: 0:05:22 lr: 0.000256 loss: 0.5690 (0.6163) grad: 0.4947 (0.5479) time: 0.5369 data: 0.0031 max mem: 25051 +train: [4] [240/800] eta: 0:05:19 lr: 0.000258 loss: 0.6182 (0.6268) grad: 0.4947 (0.5675) time: 0.7418 data: 0.2285 max mem: 25051 +train: [4] [260/800] eta: 0:05:05 lr: 0.000259 loss: 0.6394 (0.6271) grad: 0.5506 (0.5684) time: 0.5047 data: 0.0033 max mem: 25051 +train: [4] [280/800] eta: 0:04:51 lr: 0.000261 loss: 0.6182 (0.6271) grad: 0.5697 (0.5718) time: 0.5038 data: 0.0033 max mem: 25051 +train: [4] [300/800] eta: 0:04:39 lr: 0.000262 loss: 0.5655 (0.6213) grad: 0.5697 (0.5778) time: 0.5130 data: 0.0036 max mem: 25051 +train: [4] [320/800] eta: 0:04:26 lr: 0.000264 loss: 0.5655 (0.6351) grad: 0.6100 (0.5953) time: 0.5009 data: 0.0035 max mem: 25051 +train: [4] [340/800] eta: 0:04:13 lr: 0.000265 loss: 0.5655 (0.6390) grad: 0.6547 (0.5983) time: 0.4872 data: 0.0029 max mem: 25051 +train: [4] [360/800] eta: 0:04:07 lr: 0.000267 loss: 0.5915 (0.6381) grad: 0.7063 (0.6036) time: 0.7755 data: 0.2816 max mem: 25051 +WARNING: classifier 45 (31, 1.0) diverged (loss=22.11 > 13.86) at step 891. Freezing. +train: [4] [380/800] eta: 0:03:54 lr: 0.000268 loss: 0.6300 (0.6375) grad: 0.6547 (0.6046) time: 0.4898 data: 0.0031 max mem: 25051 +train: [4] [400/800] eta: 0:03:42 lr: 0.000270 loss: 0.6145 (0.6419) grad: 0.5932 (0.6075) time: 0.5087 data: 0.0033 max mem: 25051 +train: [4] [420/800] eta: 0:03:30 lr: 0.000271 loss: 0.6145 (0.6388) grad: 0.5932 (0.6078) time: 0.4872 data: 0.0035 max mem: 25051 +train: [4] [440/800] eta: 0:03:18 lr: 0.000273 loss: 0.6525 (0.6448) grad: 0.5864 (0.6066) time: 0.4962 data: 0.0034 max mem: 25051 +train: [4] [460/800] eta: 0:03:10 lr: 0.000274 loss: 0.6511 (0.6424) grad: 0.6227 (0.6085) time: 0.7857 data: 0.2997 max mem: 25051 +train: [4] [480/800] eta: 0:02:58 lr: 0.000276 loss: 0.5759 (0.6415) grad: 0.6210 (0.6095) time: 0.4999 data: 0.0173 max mem: 25051 +train: [4] [500/800] eta: 0:02:46 lr: 0.000277 loss: 0.5759 (0.6405) grad: 0.6210 (0.6107) time: 0.5052 data: 0.0024 max mem: 25051 +train: [4] [520/800] eta: 0:02:35 lr: 0.000279 loss: 0.5507 (0.6398) grad: 0.5841 (0.6093) time: 0.4957 data: 0.0034 max mem: 25051 +WARNING: classifier 47 (43, 1.0) diverged (loss=16.94 > 13.86) at step 934. Freezing. +train: [4] [540/800] eta: 0:02:23 lr: 0.000280 loss: 0.5600 (0.6424) grad: 0.5806 (0.6098) time: 0.5093 data: 0.0038 max mem: 25051 +train: [4] [560/800] eta: 0:02:12 lr: 0.000282 loss: 0.5683 (0.6427) grad: 0.5799 (0.6088) time: 0.4996 data: 0.0030 max mem: 25051 +train: [4] [580/800] eta: 0:02:02 lr: 0.000283 loss: 0.5810 (0.6396) grad: 0.5315 (0.6054) time: 0.7447 data: 0.2265 max mem: 25051 +WARNING: classifier 44 (26, 1.0) diverged (loss=15.20 > 13.86) at step 948. Freezing. +train: [4] [600/800] eta: 0:01:51 lr: 0.000285 loss: 0.5914 (0.6410) grad: 0.5145 (0.6064) time: 0.5144 data: 0.0045 max mem: 25051 +train: [4] [620/800] eta: 0:01:39 lr: 0.000286 loss: 0.5852 (0.6396) grad: 0.4632 (0.5990) time: 0.5004 data: 0.0037 max mem: 25051 +WARNING: classifier 40 (14, 1.0) diverged (loss=14.10 > 13.86) at step 958. Freezing. +train: [4] [640/800] eta: 0:01:28 lr: 0.000288 loss: 0.5867 (0.6403) grad: 0.4185 (0.5937) time: 0.5137 data: 0.0035 max mem: 25051 +train: [4] [660/800] eta: 0:01:17 lr: 0.000289 loss: 0.5867 (0.6382) grad: 0.3884 (0.5856) time: 0.5032 data: 0.0035 max mem: 25051 +train: [4] [680/800] eta: 0:01:05 lr: 0.000291 loss: 0.5614 (0.6348) grad: 0.3617 (0.5759) time: 0.5019 data: 0.0035 max mem: 25051 +train: [4] [700/800] eta: 0:00:55 lr: 0.000292 loss: 0.5529 (0.6311) grad: 0.3244 (0.5695) time: 0.7023 data: 0.2297 max mem: 25051 +train: [4] [720/800] eta: 0:00:44 lr: 0.000294 loss: 0.5182 (0.6253) grad: 0.2812 (0.5621) time: 0.4998 data: 0.0031 max mem: 25051 +train: [4] [740/800] eta: 0:00:33 lr: 0.000295 loss: 0.4969 (0.6232) grad: 0.2683 (0.5543) time: 0.4861 data: 0.0031 max mem: 25051 +train: [4] [760/800] eta: 0:00:21 lr: 0.000297 loss: 0.4728 (0.6203) grad: 0.3346 (0.5486) time: 0.4850 data: 0.0034 max mem: 25051 +train: [4] [780/800] eta: 0:00:10 lr: 0.000298 loss: 0.4987 (0.6193) grad: 0.3425 (0.5444) time: 0.4883 data: 0.0030 max mem: 25051 +train: [4] [799/800] eta: 0:00:00 lr: 0.000300 loss: 0.5786 (0.6192) grad: 0.3346 (0.5386) time: 0.4978 data: 0.0024 max mem: 25051 +train: [4] Total time: 0:07:17 (0.5467 s / it) +train: [4] Summary: lr: 0.000300 loss: 0.5786 (0.6192) grad: 0.3346 (0.5386) +eval (validation): [4] [ 0/25] eta: 0:01:46 time: 4.2579 data: 3.9527 max mem: 25051 +eval (validation): [4] [20/25] eta: 0:00:02 time: 0.3835 data: 0.0278 max mem: 25051 +eval (validation): [4] [24/25] eta: 0:00:00 time: 0.3833 data: 0.0279 max mem: 25051 +eval (validation): [4] Total time: 0:00:13 (0.5456 s / it) +cv: [4] best hparam: (0.087, 1.0) (009) ('009_lr8.7e-02_wd1.0e+00') loss: 0.645 acc: 0.687 f1: 0.650 bacc: 0.647 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/ppmi_dx__patch__attn/checkpoint-last.pth +train: [5] [ 0/800] eta: 1:00:47 lr: nan time: 4.5589 data: 4.1678 max mem: 25051 +train: [5] [ 20/800] eta: 0:09:15 lr: 0.000300 loss: 0.6268 (0.5982) grad: 0.3178 (0.3009) time: 0.5200 data: 0.0025 max mem: 25051 +train: [5] [ 40/800] eta: 0:07:43 lr: 0.000300 loss: 0.5339 (0.5573) grad: 0.2667 (0.2740) time: 0.5012 data: 0.0028 max mem: 25051 +train: [5] [ 60/800] eta: 0:07:01 lr: 0.000300 loss: 0.5339 (0.5410) grad: 0.2956 (0.3266) time: 0.4865 data: 0.0031 max mem: 25051 +train: [5] [ 80/800] eta: 0:06:37 lr: 0.000300 loss: 0.5143 (0.5472) grad: 0.2956 (0.3542) time: 0.4999 data: 0.0028 max mem: 25051 +train: [5] [100/800] eta: 0:06:20 lr: 0.000300 loss: 0.4928 (0.5201) grad: 0.4375 (0.3859) time: 0.5097 data: 0.0031 max mem: 25051 +train: [5] [120/800] eta: 0:06:28 lr: 0.000300 loss: 0.4928 (0.5200) grad: 0.4475 (0.3774) time: 0.7149 data: 0.2265 max mem: 25051 +train: [5] [140/800] eta: 0:06:08 lr: 0.000300 loss: 0.5335 (0.5443) grad: 0.4328 (0.3778) time: 0.4806 data: 0.0032 max mem: 25051 +train: [5] [160/800] eta: 0:05:52 lr: 0.000300 loss: 0.5335 (0.5429) grad: 0.4096 (0.3818) time: 0.4973 data: 0.0029 max mem: 25051 +train: [5] [180/800] eta: 0:05:38 lr: 0.000300 loss: 0.5371 (0.5341) grad: 0.3594 (0.3784) time: 0.5093 data: 0.0035 max mem: 25051 +train: [5] [200/800] eta: 0:05:24 lr: 0.000300 loss: 0.5948 (0.5383) grad: 0.3594 (0.3803) time: 0.4927 data: 0.0035 max mem: 25051 +train: [5] [220/800] eta: 0:05:11 lr: 0.000300 loss: 0.4871 (0.5409) grad: 0.3767 (0.3836) time: 0.4909 data: 0.0031 max mem: 25051 +train: [5] [240/800] eta: 0:05:08 lr: 0.000300 loss: 0.5088 (0.5411) grad: 0.3551 (0.3834) time: 0.7019 data: 0.2294 max mem: 25051 +train: [5] [260/800] eta: 0:04:55 lr: 0.000300 loss: 0.5489 (0.5420) grad: 0.3551 (0.3814) time: 0.5000 data: 0.0026 max mem: 25051 +train: [5] [280/800] eta: 0:04:42 lr: 0.000300 loss: 0.5204 (0.5400) grad: 0.3860 (0.3899) time: 0.4867 data: 0.0031 max mem: 25051 +train: [5] [300/800] eta: 0:04:28 lr: 0.000300 loss: 0.5204 (0.5453) grad: 0.3860 (0.3919) time: 0.4672 data: 0.0030 max mem: 25051 +train: [5] [320/800] eta: 0:04:16 lr: 0.000299 loss: 0.5376 (0.5434) grad: 0.3724 (0.3904) time: 0.4847 data: 0.0030 max mem: 25051 +WARNING: classifier 38 (9.8, 1.0) diverged (loss=15.18 > 13.86) at step 1081. Freezing. +train: [5] [340/800] eta: 0:04:04 lr: 0.000299 loss: 0.5633 (0.5488) grad: 0.3871 (0.3940) time: 0.4828 data: 0.0030 max mem: 25051 +train: [5] [360/800] eta: 0:03:57 lr: 0.000299 loss: 0.5275 (0.5443) grad: 0.3612 (0.3898) time: 0.6965 data: 0.2064 max mem: 25051 +train: [5] [380/800] eta: 0:03:45 lr: 0.000299 loss: 0.4945 (0.5399) grad: 0.3318 (0.3842) time: 0.4734 data: 0.0028 max mem: 25051 +train: [5] [400/800] eta: 0:03:34 lr: 0.000299 loss: 0.4858 (0.5362) grad: 0.3072 (0.3847) time: 0.5129 data: 0.0030 max mem: 25051 +train: [5] [420/800] eta: 0:03:22 lr: 0.000299 loss: 0.4489 (0.5315) grad: 0.3072 (0.3844) time: 0.5062 data: 0.0031 max mem: 25051 +train: [5] [440/800] eta: 0:03:11 lr: 0.000299 loss: 0.4489 (0.5311) grad: 0.3630 (0.3924) time: 0.4952 data: 0.0032 max mem: 25051 +train: [5] [460/800] eta: 0:03:03 lr: 0.000299 loss: 0.4802 (0.5293) grad: 0.4272 (0.3959) time: 0.6887 data: 0.2153 max mem: 25051 +train: [5] [480/800] eta: 0:02:52 lr: 0.000299 loss: 0.4805 (0.5294) grad: 0.4353 (0.3976) time: 0.4996 data: 0.0080 max mem: 25051 +train: [5] [500/800] eta: 0:02:40 lr: 0.000299 loss: 0.4936 (0.5287) grad: 0.4578 (0.4053) time: 0.5114 data: 0.0033 max mem: 25051 +train: [5] [520/800] eta: 0:02:29 lr: 0.000299 loss: 0.4908 (0.5277) grad: 0.4353 (0.4071) time: 0.5151 data: 0.0029 max mem: 25051 +WARNING: classifier 43 (22, 1.0) diverged (loss=14.52 > 13.86) at step 1135. Freezing. +train: [5] [540/800] eta: 0:02:19 lr: 0.000299 loss: 0.4908 (0.5284) grad: 0.4503 (0.4130) time: 0.5191 data: 0.0033 max mem: 25051 +train: [5] [560/800] eta: 0:02:08 lr: 0.000298 loss: 0.4714 (0.5277) grad: 0.4218 (0.4071) time: 0.4946 data: 0.0032 max mem: 25051 +train: [5] [580/800] eta: 0:01:58 lr: 0.000298 loss: 0.4659 (0.5245) grad: 0.3093 (0.4047) time: 0.7286 data: 0.2287 max mem: 25051 +train: [5] [600/800] eta: 0:01:47 lr: 0.000298 loss: 0.4659 (0.5229) grad: 0.2781 (0.3988) time: 0.5067 data: 0.0040 max mem: 25051 +train: [5] [620/800] eta: 0:01:36 lr: 0.000298 loss: 0.4680 (0.5235) grad: 0.2232 (0.3940) time: 0.4729 data: 0.0024 max mem: 25051 +train: [5] [640/800] eta: 0:01:25 lr: 0.000298 loss: 0.4742 (0.5228) grad: 0.2297 (0.3890) time: 0.5039 data: 0.0034 max mem: 25051 +train: [5] [660/800] eta: 0:01:14 lr: 0.000298 loss: 0.5265 (0.5252) grad: 0.2297 (0.3845) time: 0.4998 data: 0.0030 max mem: 25051 +train: [5] [680/800] eta: 0:01:03 lr: 0.000298 loss: 0.5292 (0.5261) grad: 0.2570 (0.3848) time: 0.4743 data: 0.0034 max mem: 25051 +train: [5] [700/800] eta: 0:00:53 lr: 0.000298 loss: 0.5179 (0.5238) grad: 0.2588 (0.3818) time: 0.6841 data: 0.2028 max mem: 25051 +train: [5] [720/800] eta: 0:00:42 lr: 0.000297 loss: 0.4846 (0.5234) grad: 0.2662 (0.3775) time: 0.5248 data: 0.0024 max mem: 25051 +train: [5] [740/800] eta: 0:00:32 lr: 0.000297 loss: 0.5018 (0.5255) grad: 0.2758 (0.3756) time: 0.5172 data: 0.0036 max mem: 25051 +train: [5] [760/800] eta: 0:00:21 lr: 0.000297 loss: 0.4689 (0.5244) grad: 0.2916 (0.3747) time: 0.5102 data: 0.0034 max mem: 25051 +train: [5] [780/800] eta: 0:00:10 lr: 0.000297 loss: 0.5018 (0.5232) grad: 0.3002 (0.3751) time: 0.4821 data: 0.0035 max mem: 25051 +train: [5] [799/800] eta: 0:00:00 lr: 0.000297 loss: 0.5018 (0.5218) grad: 0.3413 (0.3749) time: 0.5033 data: 0.0032 max mem: 25051 +train: [5] Total time: 0:07:07 (0.5341 s / it) +train: [5] Summary: lr: 0.000297 loss: 0.5018 (0.5218) grad: 0.3413 (0.3749) +eval (validation): [5] [ 0/25] eta: 0:01:50 time: 4.4154 data: 4.1497 max mem: 25051 +eval (validation): [5] [20/25] eta: 0:00:03 time: 0.4647 data: 0.0689 max mem: 25051 +eval (validation): [5] [24/25] eta: 0:00:00 time: 0.4556 data: 0.0689 max mem: 25051 +eval (validation): [5] Total time: 0:00:15 (0.6108 s / it) +cv: [5] best hparam: (6, 1.0) (035) ('035_lr6.0e+00_wd1.0e+00') loss: 2.104 acc: 0.677 f1: 0.655 bacc: 0.653 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/ppmi_dx__patch__attn/checkpoint-last.pth +train: [6] [ 0/800] eta: 0:57:21 lr: nan time: 4.3013 data: 3.9118 max mem: 25051 +train: [6] [ 20/800] eta: 0:09:06 lr: 0.000297 loss: 0.5537 (0.5326) grad: 0.3299 (0.3571) time: 0.5201 data: 0.0023 max mem: 25051 +train: [6] [ 40/800] eta: 0:07:33 lr: 0.000296 loss: 0.5329 (0.5261) grad: 0.3299 (0.3556) time: 0.4874 data: 0.0030 max mem: 25051 +WARNING: classifier 41 (16, 1.0) diverged (loss=16.38 > 13.86) at step 1211. Freezing. +train: [6] [ 60/800] eta: 0:06:57 lr: 0.000296 loss: 0.5137 (0.5262) grad: 0.3157 (0.3534) time: 0.4972 data: 0.0032 max mem: 25051 +train: [6] [ 80/800] eta: 0:06:35 lr: 0.000296 loss: 0.5137 (0.5261) grad: 0.2749 (0.3062) time: 0.5058 data: 0.0034 max mem: 25051 +train: [6] [100/800] eta: 0:06:17 lr: 0.000296 loss: 0.4656 (0.5079) grad: 0.2352 (0.2962) time: 0.4969 data: 0.0039 max mem: 25051 +train: [6] [120/800] eta: 0:06:22 lr: 0.000296 loss: 0.5084 (0.5194) grad: 0.2178 (0.2867) time: 0.6804 data: 0.2193 max mem: 25051 +train: [6] [140/800] eta: 0:06:09 lr: 0.000296 loss: 0.5275 (0.5270) grad: 0.2076 (0.2710) time: 0.5487 data: 0.0037 max mem: 25051 +train: [6] [160/800] eta: 0:05:54 lr: 0.000295 loss: 0.5084 (0.5133) grad: 0.2032 (0.2625) time: 0.5090 data: 0.0034 max mem: 25051 +train: [6] [180/800] eta: 0:05:38 lr: 0.000295 loss: 0.5368 (0.5127) grad: 0.2032 (0.2662) time: 0.4846 data: 0.0032 max mem: 25051 +train: [6] [200/800] eta: 0:05:24 lr: 0.000295 loss: 0.5016 (0.5085) grad: 0.2401 (0.2635) time: 0.4873 data: 0.0034 max mem: 25051 +train: [6] [220/800] eta: 0:05:11 lr: 0.000295 loss: 0.4941 (0.5084) grad: 0.2136 (0.2579) time: 0.5102 data: 0.0031 max mem: 25051 +train: [6] [240/800] eta: 0:05:08 lr: 0.000295 loss: 0.4668 (0.5011) grad: 0.2230 (0.2547) time: 0.6926 data: 0.2200 max mem: 25051 +train: [6] [260/800] eta: 0:04:54 lr: 0.000294 loss: 0.4499 (0.4987) grad: 0.1906 (0.2490) time: 0.4710 data: 0.0026 max mem: 25051 +train: [6] [280/800] eta: 0:04:41 lr: 0.000294 loss: 0.4474 (0.4945) grad: 0.1829 (0.2450) time: 0.5020 data: 0.0030 max mem: 25051 +train: [6] [300/800] eta: 0:04:29 lr: 0.000294 loss: 0.4468 (0.4929) grad: 0.1601 (0.2402) time: 0.5013 data: 0.0033 max mem: 25051 +train: [6] [320/800] eta: 0:04:18 lr: 0.000294 loss: 0.4499 (0.4920) grad: 0.1601 (0.2410) time: 0.5275 data: 0.0032 max mem: 25051 +train: [6] [340/800] eta: 0:04:06 lr: 0.000293 loss: 0.4187 (0.4869) grad: 0.1640 (0.2393) time: 0.4838 data: 0.0032 max mem: 25051 +train: [6] [360/800] eta: 0:04:00 lr: 0.000293 loss: 0.4175 (0.4840) grad: 0.1644 (0.2425) time: 0.7524 data: 0.2354 max mem: 25051 +train: [6] [380/800] eta: 0:03:49 lr: 0.000293 loss: 0.4161 (0.4835) grad: 0.1919 (0.2410) time: 0.5587 data: 0.0032 max mem: 25051 +train: [6] [400/800] eta: 0:03:37 lr: 0.000293 loss: 0.4133 (0.4831) grad: 0.1919 (0.2385) time: 0.4896 data: 0.0036 max mem: 25051 +train: [6] [420/800] eta: 0:03:26 lr: 0.000292 loss: 0.4133 (0.4809) grad: 0.1644 (0.2351) time: 0.5287 data: 0.0039 max mem: 25051 +train: [6] [440/800] eta: 0:03:15 lr: 0.000292 loss: 0.4150 (0.4784) grad: 0.1482 (0.2311) time: 0.5024 data: 0.0033 max mem: 25051 +train: [6] [460/800] eta: 0:03:06 lr: 0.000292 loss: 0.4331 (0.4757) grad: 0.1473 (0.2287) time: 0.6740 data: 0.2131 max mem: 25051 +train: [6] [480/800] eta: 0:02:54 lr: 0.000292 loss: 0.4331 (0.4741) grad: 0.1517 (0.2271) time: 0.5169 data: 0.0029 max mem: 25051 +train: [6] [500/800] eta: 0:02:43 lr: 0.000291 loss: 0.4331 (0.4744) grad: 0.1517 (0.2257) time: 0.4953 data: 0.0029 max mem: 25051 +train: [6] [520/800] eta: 0:02:32 lr: 0.000291 loss: 0.4309 (0.4725) grad: 0.1517 (0.2244) time: 0.5178 data: 0.0038 max mem: 25051 +train: [6] [540/800] eta: 0:02:20 lr: 0.000291 loss: 0.4218 (0.4712) grad: 0.1426 (0.2217) time: 0.5076 data: 0.0028 max mem: 25051 +train: [6] [560/800] eta: 0:02:10 lr: 0.000291 loss: 0.4218 (0.4713) grad: 0.1426 (0.2239) time: 0.5367 data: 0.0034 max mem: 25051 +train: [6] [580/800] eta: 0:02:00 lr: 0.000290 loss: 0.4218 (0.4727) grad: 0.1852 (0.2248) time: 0.6859 data: 0.2121 max mem: 25051 +train: [6] [600/800] eta: 0:01:49 lr: 0.000290 loss: 0.4574 (0.4731) grad: 0.1907 (0.2258) time: 0.5126 data: 0.0062 max mem: 25051 +train: [6] [620/800] eta: 0:01:37 lr: 0.000290 loss: 0.4729 (0.4720) grad: 0.2485 (0.2274) time: 0.4933 data: 0.0030 max mem: 25051 +train: [6] [640/800] eta: 0:01:26 lr: 0.000290 loss: 0.4729 (0.4733) grad: 0.1979 (0.2251) time: 0.4987 data: 0.0034 max mem: 25051 +train: [6] [660/800] eta: 0:01:15 lr: 0.000289 loss: 0.4518 (0.4707) grad: 0.1587 (0.2234) time: 0.5002 data: 0.0031 max mem: 25051 +train: [6] [680/800] eta: 0:01:04 lr: 0.000289 loss: 0.4302 (0.4684) grad: 0.1683 (0.2228) time: 0.4916 data: 0.0030 max mem: 25051 +train: [6] [700/800] eta: 0:00:54 lr: 0.000289 loss: 0.4430 (0.4701) grad: 0.1630 (0.2226) time: 0.6647 data: 0.2031 max mem: 25051 +train: [6] [720/800] eta: 0:00:43 lr: 0.000288 loss: 0.4033 (0.4692) grad: 0.1850 (0.2222) time: 0.4821 data: 0.0031 max mem: 25051 +train: [6] [740/800] eta: 0:00:32 lr: 0.000288 loss: 0.4166 (0.4688) grad: 0.2033 (0.2225) time: 0.4724 data: 0.0031 max mem: 25051 +train: [6] [760/800] eta: 0:00:21 lr: 0.000288 loss: 0.4166 (0.4680) grad: 0.1992 (0.2220) time: 0.4797 data: 0.0032 max mem: 25051 +train: [6] [780/800] eta: 0:00:10 lr: 0.000287 loss: 0.4278 (0.4686) grad: 0.1992 (0.2212) time: 0.4832 data: 0.0032 max mem: 25051 +train: [6] [799/800] eta: 0:00:00 lr: 0.000287 loss: 0.4167 (0.4675) grad: 0.1613 (0.2193) time: 0.4776 data: 0.0027 max mem: 25051 +train: [6] Total time: 0:07:08 (0.5358 s / it) +train: [6] Summary: lr: 0.000287 loss: 0.4167 (0.4675) grad: 0.1613 (0.2193) +eval (validation): [6] [ 0/25] eta: 0:01:44 time: 4.1606 data: 3.8963 max mem: 25051 +eval (validation): [6] [20/25] eta: 0:00:03 time: 0.4764 data: 0.0715 max mem: 25051 +eval (validation): [6] [24/25] eta: 0:00:00 time: 0.4671 data: 0.0716 max mem: 25051 +eval (validation): [6] Total time: 0:00:15 (0.6116 s / it) +cv: [6] best hparam: (0.85, 1.0) (023) ('023_lr8.5e-01_wd1.0e+00') loss: 0.669 acc: 0.667 f1: 0.655 bacc: 0.658 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/ppmi_dx__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/ppmi_dx__patch__attn/checkpoint-best.pth +train: [7] [ 0/800] eta: 0:58:28 lr: nan time: 4.3857 data: 4.0006 max mem: 25051 +train: [7] [ 20/800] eta: 0:09:01 lr: 0.000287 loss: 0.4144 (0.4081) grad: 0.2414 (0.2041) time: 0.5096 data: 0.0096 max mem: 25051 +train: [7] [ 40/800] eta: 0:07:37 lr: 0.000286 loss: 0.4211 (0.4291) grad: 0.1007 (0.1589) time: 0.5055 data: 0.0035 max mem: 25051 +train: [7] [ 60/800] eta: 0:06:58 lr: 0.000286 loss: 0.4283 (0.4469) grad: 0.1007 (0.1403) time: 0.4906 data: 0.0024 max mem: 25051 +train: [7] [ 80/800] eta: 0:06:35 lr: 0.000286 loss: 0.4283 (0.4441) grad: 0.1012 (0.1354) time: 0.5002 data: 0.0032 max mem: 25051 +train: [7] [100/800] eta: 0:06:21 lr: 0.000285 loss: 0.4467 (0.4498) grad: 0.1072 (0.1349) time: 0.5235 data: 0.0038 max mem: 25051 +train: [7] [120/800] eta: 0:06:27 lr: 0.000285 loss: 0.4453 (0.4463) grad: 0.1192 (0.1495) time: 0.6949 data: 0.2185 max mem: 25051 +train: [7] [140/800] eta: 0:06:07 lr: 0.000285 loss: 0.4558 (0.4489) grad: 0.1497 (0.1648) time: 0.4871 data: 0.0033 max mem: 25051 +train: [7] [160/800] eta: 0:05:51 lr: 0.000284 loss: 0.4369 (0.4380) grad: 0.1797 (0.1669) time: 0.4859 data: 0.0028 max mem: 25051 +train: [7] [180/800] eta: 0:05:36 lr: 0.000284 loss: 0.4351 (0.4477) grad: 0.1997 (0.1758) time: 0.4982 data: 0.0036 max mem: 25051 +train: [7] [200/800] eta: 0:05:22 lr: 0.000284 loss: 0.4416 (0.4515) grad: 0.1997 (0.1789) time: 0.4930 data: 0.0035 max mem: 25051 +train: [7] [220/800] eta: 0:05:10 lr: 0.000283 loss: 0.4284 (0.4491) grad: 0.1951 (0.1856) time: 0.4996 data: 0.0032 max mem: 25051 +train: [7] [240/800] eta: 0:05:08 lr: 0.000283 loss: 0.4351 (0.4453) grad: 0.2179 (0.1886) time: 0.7248 data: 0.2532 max mem: 25051 +train: [7] [260/800] eta: 0:04:54 lr: 0.000283 loss: 0.4284 (0.4426) grad: 0.2096 (0.1882) time: 0.4828 data: 0.0021 max mem: 25051 +train: [7] [280/800] eta: 0:04:42 lr: 0.000282 loss: 0.4284 (0.4433) grad: 0.1970 (0.1873) time: 0.5141 data: 0.0031 max mem: 25051 +train: [7] [300/800] eta: 0:04:29 lr: 0.000282 loss: 0.4055 (0.4360) grad: 0.1963 (0.1874) time: 0.4926 data: 0.0037 max mem: 25051 +train: [7] [320/800] eta: 0:04:17 lr: 0.000282 loss: 0.4063 (0.4368) grad: 0.1745 (0.1873) time: 0.5032 data: 0.0036 max mem: 25051 +train: [7] [340/800] eta: 0:04:06 lr: 0.000281 loss: 0.4282 (0.4386) grad: 0.1849 (0.1934) time: 0.5026 data: 0.0036 max mem: 25051 +train: [7] [360/800] eta: 0:04:00 lr: 0.000281 loss: 0.4282 (0.4389) grad: 0.1904 (0.1937) time: 0.7324 data: 0.2490 max mem: 25051 +train: [7] [380/800] eta: 0:03:48 lr: 0.000280 loss: 0.4318 (0.4363) grad: 0.1904 (0.1938) time: 0.4886 data: 0.0029 max mem: 25051 +train: [7] [400/800] eta: 0:03:36 lr: 0.000280 loss: 0.4338 (0.4369) grad: 0.2216 (0.1948) time: 0.4853 data: 0.0030 max mem: 25051 +train: [7] [420/800] eta: 0:03:24 lr: 0.000280 loss: 0.4338 (0.4391) grad: 0.1676 (0.1937) time: 0.4933 data: 0.0024 max mem: 25051 +train: [7] [440/800] eta: 0:03:13 lr: 0.000279 loss: 0.3881 (0.4370) grad: 0.1492 (0.1915) time: 0.5049 data: 0.0035 max mem: 25051 +train: [7] [460/800] eta: 0:03:04 lr: 0.000279 loss: 0.4429 (0.4377) grad: 0.1485 (0.1916) time: 0.6824 data: 0.2167 max mem: 25051 +train: [7] [480/800] eta: 0:02:53 lr: 0.000278 loss: 0.4429 (0.4383) grad: 0.1485 (0.1930) time: 0.5457 data: 0.0027 max mem: 25051 +train: [7] [500/800] eta: 0:02:42 lr: 0.000278 loss: 0.4014 (0.4371) grad: 0.1485 (0.1915) time: 0.4959 data: 0.0032 max mem: 25051 +train: [7] [520/800] eta: 0:02:30 lr: 0.000278 loss: 0.4289 (0.4361) grad: 0.1757 (0.1944) time: 0.4913 data: 0.0034 max mem: 25051 +train: [7] [540/800] eta: 0:02:19 lr: 0.000277 loss: 0.4408 (0.4375) grad: 0.1757 (0.1940) time: 0.4896 data: 0.0031 max mem: 25051 +train: [7] [560/800] eta: 0:02:08 lr: 0.000277 loss: 0.4289 (0.4367) grad: 0.1335 (0.1922) time: 0.4766 data: 0.0029 max mem: 25051 +train: [7] [580/800] eta: 0:01:59 lr: 0.000276 loss: 0.4408 (0.4377) grad: 0.1419 (0.1929) time: 0.7335 data: 0.2685 max mem: 25051 +train: [7] [600/800] eta: 0:01:48 lr: 0.000276 loss: 0.4408 (0.4379) grad: 0.1261 (0.1913) time: 0.5749 data: 0.0157 max mem: 25051 +train: [7] [620/800] eta: 0:01:37 lr: 0.000275 loss: 0.4269 (0.4387) grad: 0.1361 (0.1924) time: 0.4895 data: 0.0029 max mem: 25051 +train: [7] [640/800] eta: 0:01:26 lr: 0.000275 loss: 0.4540 (0.4393) grad: 0.1508 (0.1925) time: 0.4976 data: 0.0028 max mem: 25051 +train: [7] [660/800] eta: 0:01:15 lr: 0.000275 loss: 0.4563 (0.4406) grad: 0.1526 (0.1930) time: 0.5001 data: 0.0030 max mem: 25051 +train: [7] [680/800] eta: 0:01:04 lr: 0.000274 loss: 0.4455 (0.4399) grad: 0.1655 (0.1924) time: 0.4955 data: 0.0031 max mem: 25051 +train: [7] [700/800] eta: 0:00:54 lr: 0.000274 loss: 0.4455 (0.4407) grad: 0.1655 (0.1921) time: 0.7194 data: 0.2109 max mem: 25051 +train: [7] [720/800] eta: 0:00:43 lr: 0.000273 loss: 0.4318 (0.4409) grad: 0.1662 (0.1924) time: 0.5119 data: 0.0026 max mem: 25051 +train: [7] [740/800] eta: 0:00:32 lr: 0.000273 loss: 0.4176 (0.4385) grad: 0.1568 (0.1913) time: 0.4982 data: 0.0033 max mem: 25051 +train: [7] [760/800] eta: 0:00:21 lr: 0.000272 loss: 0.3904 (0.4359) grad: 0.1473 (0.1895) time: 0.4917 data: 0.0029 max mem: 25051 +train: [7] [780/800] eta: 0:00:10 lr: 0.000272 loss: 0.3868 (0.4362) grad: 0.1303 (0.1882) time: 0.4698 data: 0.0032 max mem: 25051 +train: [7] [799/800] eta: 0:00:00 lr: 0.000271 loss: 0.3750 (0.4385) grad: 0.1391 (0.1888) time: 0.4856 data: 0.0031 max mem: 25051 +train: [7] Total time: 0:07:09 (0.5367 s / it) +train: [7] Summary: lr: 0.000271 loss: 0.3750 (0.4385) grad: 0.1391 (0.1888) +eval (validation): [7] [ 0/25] eta: 0:01:44 time: 4.1961 data: 3.9291 max mem: 25051 +eval (validation): [7] [20/25] eta: 0:00:02 time: 0.3967 data: 0.0068 max mem: 25051 +eval (validation): [7] [24/25] eta: 0:00:00 time: 0.3913 data: 0.0064 max mem: 25051 +eval (validation): [7] Total time: 0:00:13 (0.5493 s / it) +cv: [7] best hparam: (1.2, 1.0) (025) ('025_lr1.2e+00_wd1.0e+00') loss: 0.929 acc: 0.636 f1: 0.635 bacc: 0.655 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/ppmi_dx__patch__attn/checkpoint-last.pth +train: [8] [ 0/800] eta: 0:59:31 lr: nan time: 4.4649 data: 4.0555 max mem: 25051 +train: [8] [ 20/800] eta: 0:08:39 lr: 0.000271 loss: 0.4030 (0.4336) grad: 0.2375 (0.2306) time: 0.4756 data: 0.0028 max mem: 25051 +train: [8] [ 40/800] eta: 0:07:20 lr: 0.000270 loss: 0.4224 (0.4556) grad: 0.1956 (0.2356) time: 0.4897 data: 0.0030 max mem: 25051 +train: [8] [ 60/800] eta: 0:07:07 lr: 0.000270 loss: 0.4224 (0.4554) grad: 0.1956 (0.2280) time: 0.5752 data: 0.0040 max mem: 25051 +train: [8] [ 80/800] eta: 0:06:42 lr: 0.000270 loss: 0.4030 (0.4407) grad: 0.1911 (0.2274) time: 0.4991 data: 0.0034 max mem: 25051 +train: [8] [100/800] eta: 0:06:22 lr: 0.000269 loss: 0.4090 (0.4377) grad: 0.1859 (0.2284) time: 0.4996 data: 0.0031 max mem: 25051 +train: [8] [120/800] eta: 0:06:25 lr: 0.000269 loss: 0.4090 (0.4437) grad: 0.1937 (0.2323) time: 0.6713 data: 0.2086 max mem: 25051 +train: [8] [140/800] eta: 0:06:11 lr: 0.000268 loss: 0.4104 (0.4407) grad: 0.2107 (0.2300) time: 0.5367 data: 0.0404 max mem: 25051 +train: [8] [160/800] eta: 0:05:53 lr: 0.000268 loss: 0.4243 (0.4386) grad: 0.1937 (0.2180) time: 0.4806 data: 0.0022 max mem: 25051 +train: [8] [180/800] eta: 0:05:37 lr: 0.000267 loss: 0.4115 (0.4294) grad: 0.1887 (0.2149) time: 0.4771 data: 0.0029 max mem: 25051 +train: [8] [200/800] eta: 0:05:23 lr: 0.000267 loss: 0.3984 (0.4330) grad: 0.1887 (0.2148) time: 0.4886 data: 0.0019 max mem: 25051 +train: [8] [220/800] eta: 0:05:10 lr: 0.000266 loss: 0.4050 (0.4325) grad: 0.1758 (0.2144) time: 0.5056 data: 0.0033 max mem: 25051 +train: [8] [240/800] eta: 0:05:10 lr: 0.000266 loss: 0.4232 (0.4349) grad: 0.1758 (0.2136) time: 0.7551 data: 0.2792 max mem: 25051 +train: [8] [260/800] eta: 0:04:56 lr: 0.000265 loss: 0.4340 (0.4338) grad: 0.1758 (0.2103) time: 0.4957 data: 0.0021 max mem: 25051 +train: [8] [280/800] eta: 0:04:42 lr: 0.000265 loss: 0.4340 (0.4356) grad: 0.1661 (0.2092) time: 0.4666 data: 0.0028 max mem: 25051 +train: [8] [300/800] eta: 0:04:30 lr: 0.000264 loss: 0.4478 (0.4411) grad: 0.1791 (0.2136) time: 0.4935 data: 0.0034 max mem: 25051 +train: [8] [320/800] eta: 0:04:18 lr: 0.000264 loss: 0.4478 (0.4419) grad: 0.1818 (0.2111) time: 0.4993 data: 0.0035 max mem: 25051 +train: [8] [340/800] eta: 0:04:05 lr: 0.000263 loss: 0.4346 (0.4375) grad: 0.1818 (0.2084) time: 0.4725 data: 0.0027 max mem: 25051 +train: [8] [360/800] eta: 0:03:59 lr: 0.000263 loss: 0.4142 (0.4348) grad: 0.1579 (0.2056) time: 0.7364 data: 0.1941 max mem: 25051 +train: [8] [380/800] eta: 0:03:47 lr: 0.000262 loss: 0.4250 (0.4375) grad: 0.1471 (0.2039) time: 0.4976 data: 0.0032 max mem: 25051 +train: [8] [400/800] eta: 0:03:36 lr: 0.000262 loss: 0.4142 (0.4360) grad: 0.1471 (0.2056) time: 0.4962 data: 0.0033 max mem: 25051 +train: [8] [420/800] eta: 0:03:24 lr: 0.000261 loss: 0.4132 (0.4332) grad: 0.1550 (0.2026) time: 0.4981 data: 0.0029 max mem: 25051 +train: [8] [440/800] eta: 0:03:13 lr: 0.000260 loss: 0.3753 (0.4302) grad: 0.1199 (0.1995) time: 0.4897 data: 0.0031 max mem: 25051 +train: [8] [460/800] eta: 0:03:04 lr: 0.000260 loss: 0.3555 (0.4269) grad: 0.1395 (0.1978) time: 0.7051 data: 0.2229 max mem: 25051 +train: [8] [480/800] eta: 0:02:53 lr: 0.000259 loss: 0.3555 (0.4248) grad: 0.1449 (0.1972) time: 0.5280 data: 0.0353 max mem: 25051 +train: [8] [500/800] eta: 0:02:42 lr: 0.000259 loss: 0.3743 (0.4236) grad: 0.1449 (0.1960) time: 0.4740 data: 0.0054 max mem: 25051 +train: [8] [520/800] eta: 0:02:30 lr: 0.000258 loss: 0.3766 (0.4230) grad: 0.1608 (0.1985) time: 0.5004 data: 0.0030 max mem: 25051 +train: [8] [540/800] eta: 0:02:19 lr: 0.000258 loss: 0.3861 (0.4212) grad: 0.1784 (0.1981) time: 0.5069 data: 0.0029 max mem: 25051 +train: [8] [560/800] eta: 0:02:08 lr: 0.000257 loss: 0.3861 (0.4200) grad: 0.1538 (0.1970) time: 0.4995 data: 0.0033 max mem: 25051 +train: [8] [580/800] eta: 0:01:59 lr: 0.000257 loss: 0.3904 (0.4216) grad: 0.1554 (0.1950) time: 0.7168 data: 0.2190 max mem: 25051 +train: [8] [600/800] eta: 0:01:48 lr: 0.000256 loss: 0.3905 (0.4228) grad: 0.1504 (0.1960) time: 0.4838 data: 0.0033 max mem: 25051 +train: [8] [620/800] eta: 0:01:37 lr: 0.000256 loss: 0.3905 (0.4219) grad: 0.1499 (0.1945) time: 0.5094 data: 0.0027 max mem: 25051 +train: [8] [640/800] eta: 0:01:26 lr: 0.000255 loss: 0.3904 (0.4203) grad: 0.1400 (0.1924) time: 0.4943 data: 0.0035 max mem: 25051 +train: [8] [660/800] eta: 0:01:15 lr: 0.000254 loss: 0.3845 (0.4190) grad: 0.1397 (0.1917) time: 0.4716 data: 0.0031 max mem: 25051 +train: [8] [680/800] eta: 0:01:04 lr: 0.000254 loss: 0.3845 (0.4212) grad: 0.1397 (0.1924) time: 0.4876 data: 0.0034 max mem: 25051 +train: [8] [700/800] eta: 0:00:53 lr: 0.000253 loss: 0.3845 (0.4205) grad: 0.1808 (0.1945) time: 0.7060 data: 0.2201 max mem: 25051 +train: [8] [720/800] eta: 0:00:43 lr: 0.000253 loss: 0.4020 (0.4200) grad: 0.1948 (0.1990) time: 0.5007 data: 0.0031 max mem: 25051 +train: [8] [740/800] eta: 0:00:32 lr: 0.000252 loss: 0.4174 (0.4201) grad: 0.2262 (0.1992) time: 0.4922 data: 0.0030 max mem: 25051 +train: [8] [760/800] eta: 0:00:21 lr: 0.000252 loss: 0.4100 (0.4207) grad: 0.2293 (0.2003) time: 0.4894 data: 0.0031 max mem: 25051 +train: [8] [780/800] eta: 0:00:10 lr: 0.000251 loss: 0.4100 (0.4220) grad: 0.2240 (0.2006) time: 0.4880 data: 0.0029 max mem: 25051 +train: [8] [799/800] eta: 0:00:00 lr: 0.000250 loss: 0.3930 (0.4199) grad: 0.1873 (0.1995) time: 0.4702 data: 0.0025 max mem: 25051 +train: [8] Total time: 0:07:06 (0.5334 s / it) +train: [8] Summary: lr: 0.000250 loss: 0.3930 (0.4199) grad: 0.1873 (0.1995) +eval (validation): [8] [ 0/25] eta: 0:01:40 time: 4.0335 data: 3.7100 max mem: 25051 +eval (validation): [8] [20/25] eta: 0:00:03 time: 0.4515 data: 0.0043 max mem: 25051 +eval (validation): [8] [24/25] eta: 0:00:00 time: 0.4183 data: 0.0034 max mem: 25051 +eval (validation): [8] Total time: 0:00:14 (0.5860 s / it) +cv: [8] best hparam: (0.074, 1.0) (008) ('008_lr7.4e-02_wd1.0e+00') loss: 0.636 acc: 0.687 f1: 0.633 bacc: 0.634 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/ppmi_dx__patch__attn/checkpoint-last.pth +train: [9] [ 0/800] eta: 0:55:49 lr: nan time: 4.1866 data: 3.7836 max mem: 25051 +train: [9] [ 20/800] eta: 0:08:26 lr: 0.000250 loss: 0.4077 (0.4165) grad: 0.1497 (0.1638) time: 0.4729 data: 0.0037 max mem: 25051 +train: [9] [ 40/800] eta: 0:07:13 lr: 0.000249 loss: 0.3921 (0.3868) grad: 0.1536 (0.1901) time: 0.4867 data: 0.0019 max mem: 25051 +train: [9] [ 60/800] eta: 0:06:41 lr: 0.000249 loss: 0.3921 (0.4050) grad: 0.1671 (0.2082) time: 0.4876 data: 0.0029 max mem: 25051 +train: [9] [ 80/800] eta: 0:06:25 lr: 0.000248 loss: 0.3921 (0.4050) grad: 0.1497 (0.1896) time: 0.5100 data: 0.0020 max mem: 25051 +train: [9] [100/800] eta: 0:06:09 lr: 0.000248 loss: 0.3765 (0.4104) grad: 0.1536 (0.1866) time: 0.4986 data: 0.0030 max mem: 25051 +train: [9] [120/800] eta: 0:06:16 lr: 0.000247 loss: 0.4061 (0.4181) grad: 0.1545 (0.1886) time: 0.6872 data: 0.2156 max mem: 25051 +train: [9] [140/800] eta: 0:06:00 lr: 0.000246 loss: 0.4082 (0.4160) grad: 0.1545 (0.1930) time: 0.4998 data: 0.0032 max mem: 25051 +train: [9] [160/800] eta: 0:05:46 lr: 0.000246 loss: 0.4333 (0.4305) grad: 0.1665 (0.1898) time: 0.5001 data: 0.0053 max mem: 25051 +train: [9] [180/800] eta: 0:05:32 lr: 0.000245 loss: 0.4377 (0.4350) grad: 0.1665 (0.1947) time: 0.5058 data: 0.0019 max mem: 25051 +train: [9] [200/800] eta: 0:05:20 lr: 0.000244 loss: 0.4371 (0.4326) grad: 0.1875 (0.1979) time: 0.5044 data: 0.0030 max mem: 25051 +train: [9] [220/800] eta: 0:05:06 lr: 0.000244 loss: 0.4468 (0.4302) grad: 0.1947 (0.2010) time: 0.4863 data: 0.0020 max mem: 25051 +train: [9] [240/800] eta: 0:05:05 lr: 0.000243 loss: 0.4184 (0.4259) grad: 0.1957 (0.1998) time: 0.7177 data: 0.2288 max mem: 25051 +train: [9] [260/800] eta: 0:04:52 lr: 0.000243 loss: 0.3917 (0.4251) grad: 0.1947 (0.1985) time: 0.4962 data: 0.0024 max mem: 25051 +train: [9] [280/800] eta: 0:04:38 lr: 0.000242 loss: 0.3770 (0.4241) grad: 0.1967 (0.1988) time: 0.4728 data: 0.0029 max mem: 25051 +train: [9] [300/800] eta: 0:04:26 lr: 0.000241 loss: 0.3734 (0.4237) grad: 0.1740 (0.2017) time: 0.4966 data: 0.0032 max mem: 25051 +train: [9] [320/800] eta: 0:04:14 lr: 0.000241 loss: 0.4085 (0.4245) grad: 0.1559 (0.2009) time: 0.4884 data: 0.0033 max mem: 25051 +train: [9] [340/800] eta: 0:04:02 lr: 0.000240 loss: 0.4101 (0.4239) grad: 0.1695 (0.2027) time: 0.4753 data: 0.0028 max mem: 25051 +train: [9] [360/800] eta: 0:03:58 lr: 0.000240 loss: 0.4168 (0.4244) grad: 0.1628 (0.2019) time: 0.7682 data: 0.2553 max mem: 25051 +train: [9] [380/800] eta: 0:03:46 lr: 0.000239 loss: 0.4156 (0.4229) grad: 0.1695 (0.2057) time: 0.4924 data: 0.0033 max mem: 25051 +train: [9] [400/800] eta: 0:03:34 lr: 0.000238 loss: 0.4156 (0.4234) grad: 0.1628 (0.2030) time: 0.4840 data: 0.0034 max mem: 25051 +train: [9] [420/800] eta: 0:03:22 lr: 0.000238 loss: 0.4156 (0.4234) grad: 0.1424 (0.2023) time: 0.4820 data: 0.0032 max mem: 25051 +train: [9] [440/800] eta: 0:03:10 lr: 0.000237 loss: 0.4156 (0.4233) grad: 0.1424 (0.2019) time: 0.4707 data: 0.0033 max mem: 25051 +train: [9] [460/800] eta: 0:03:02 lr: 0.000236 loss: 0.4306 (0.4261) grad: 0.1424 (0.2035) time: 0.6937 data: 0.2192 max mem: 25051 +train: [9] [480/800] eta: 0:02:51 lr: 0.000236 loss: 0.3869 (0.4223) grad: 0.1836 (0.2043) time: 0.4817 data: 0.0033 max mem: 25051 +train: [9] [500/800] eta: 0:02:40 lr: 0.000235 loss: 0.3526 (0.4192) grad: 0.1836 (0.2028) time: 0.4964 data: 0.0029 max mem: 25051 +train: [9] [520/800] eta: 0:02:28 lr: 0.000234 loss: 0.3451 (0.4157) grad: 0.1915 (0.2055) time: 0.4929 data: 0.0028 max mem: 25051 +train: [9] [540/800] eta: 0:02:17 lr: 0.000234 loss: 0.3502 (0.4154) grad: 0.1915 (0.2064) time: 0.4894 data: 0.0037 max mem: 25051 +train: [9] [560/800] eta: 0:02:07 lr: 0.000233 loss: 0.3540 (0.4146) grad: 0.1882 (0.2071) time: 0.5178 data: 0.0034 max mem: 25051 +train: [9] [580/800] eta: 0:01:57 lr: 0.000232 loss: 0.3502 (0.4108) grad: 0.1886 (0.2064) time: 0.6775 data: 0.2180 max mem: 25051 +train: [9] [600/800] eta: 0:01:47 lr: 0.000232 loss: 0.3542 (0.4098) grad: 0.1886 (0.2062) time: 0.5355 data: 0.0172 max mem: 25051 +train: [9] [620/800] eta: 0:01:36 lr: 0.000231 loss: 0.3754 (0.4101) grad: 0.1977 (0.2068) time: 0.4956 data: 0.0022 max mem: 25051 +train: [9] [640/800] eta: 0:01:25 lr: 0.000230 loss: 0.3877 (0.4117) grad: 0.1978 (0.2066) time: 0.4864 data: 0.0036 max mem: 25051 +train: [9] [660/800] eta: 0:01:14 lr: 0.000230 loss: 0.3949 (0.4097) grad: 0.1869 (0.2057) time: 0.4886 data: 0.0037 max mem: 25051 +train: [9] [680/800] eta: 0:01:03 lr: 0.000229 loss: 0.3979 (0.4086) grad: 0.1763 (0.2050) time: 0.4871 data: 0.0035 max mem: 25051 +train: [9] [700/800] eta: 0:00:53 lr: 0.000228 loss: 0.3911 (0.4092) grad: 0.1654 (0.2056) time: 0.7754 data: 0.3077 max mem: 25051 +train: [9] [720/800] eta: 0:00:42 lr: 0.000228 loss: 0.3349 (0.4085) grad: 0.1404 (0.2036) time: 0.4717 data: 0.0186 max mem: 25051 +train: [9] [740/800] eta: 0:00:31 lr: 0.000227 loss: 0.3349 (0.4058) grad: 0.1404 (0.2028) time: 0.4760 data: 0.0084 max mem: 25051 +train: [9] [760/800] eta: 0:00:21 lr: 0.000226 loss: 0.3341 (0.4043) grad: 0.1404 (0.2013) time: 0.5057 data: 0.0022 max mem: 25051 +train: [9] [780/800] eta: 0:00:10 lr: 0.000226 loss: 0.3341 (0.4055) grad: 0.1324 (0.2007) time: 0.4916 data: 0.0030 max mem: 25051 +train: [9] [799/800] eta: 0:00:00 lr: 0.000225 loss: 0.3777 (0.4075) grad: 0.1670 (0.2020) time: 0.4735 data: 0.0029 max mem: 25051 +train: [9] Total time: 0:07:04 (0.5304 s / it) +train: [9] Summary: lr: 0.000225 loss: 0.3777 (0.4075) grad: 0.1670 (0.2020) +eval (validation): [9] [ 0/25] eta: 0:01:44 time: 4.1977 data: 3.9368 max mem: 25051 +eval (validation): [9] [20/25] eta: 0:00:03 time: 0.4779 data: 0.1073 max mem: 25051 +eval (validation): [9] [24/25] eta: 0:00:00 time: 0.4754 data: 0.1070 max mem: 25051 +eval (validation): [9] Total time: 0:00:15 (0.6156 s / it) +cv: [9] best hparam: (0.062, 1.0) (007) ('007_lr6.2e-02_wd1.0e+00') loss: 0.637 acc: 0.697 f1: 0.641 bacc: 0.642 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/ppmi_dx__patch__attn/checkpoint-last.pth +train: [10] [ 0/800] eta: 0:57:59 lr: nan time: 4.3489 data: 3.9399 max mem: 25051 +train: [10] [ 20/800] eta: 0:08:55 lr: 0.000224 loss: 0.3657 (0.3605) grad: 0.1496 (0.1451) time: 0.5028 data: 0.0036 max mem: 25051 +train: [10] [ 40/800] eta: 0:07:24 lr: 0.000224 loss: 0.3620 (0.3717) grad: 0.1590 (0.1658) time: 0.4790 data: 0.0023 max mem: 25051 +train: [10] [ 60/800] eta: 0:06:48 lr: 0.000223 loss: 0.3657 (0.3884) grad: 0.1787 (0.1787) time: 0.4854 data: 0.0030 max mem: 25051 +train: [10] [ 80/800] eta: 0:06:27 lr: 0.000222 loss: 0.3722 (0.3925) grad: 0.1787 (0.1840) time: 0.4930 data: 0.0020 max mem: 25051 +train: [10] [100/800] eta: 0:06:09 lr: 0.000222 loss: 0.3722 (0.3834) grad: 0.1954 (0.1832) time: 0.4886 data: 0.0028 max mem: 25051 +train: [10] [120/800] eta: 0:06:16 lr: 0.000221 loss: 0.3735 (0.3857) grad: 0.1859 (0.1809) time: 0.6872 data: 0.2117 max mem: 25051 +train: [10] [140/800] eta: 0:06:02 lr: 0.000220 loss: 0.3735 (0.3855) grad: 0.1906 (0.1819) time: 0.5188 data: 0.0035 max mem: 25051 +train: [10] [160/800] eta: 0:05:46 lr: 0.000220 loss: 0.3501 (0.3822) grad: 0.1794 (0.1832) time: 0.4845 data: 0.0031 max mem: 25051 +train: [10] [180/800] eta: 0:05:31 lr: 0.000219 loss: 0.3782 (0.3820) grad: 0.1854 (0.1887) time: 0.4763 data: 0.0031 max mem: 25051 +train: [10] [200/800] eta: 0:05:17 lr: 0.000218 loss: 0.3523 (0.3857) grad: 0.2136 (0.2015) time: 0.4927 data: 0.0032 max mem: 25051 +train: [10] [220/800] eta: 0:05:04 lr: 0.000217 loss: 0.3523 (0.3865) grad: 0.1899 (0.2011) time: 0.4807 data: 0.0031 max mem: 25051 +train: [10] [240/800] eta: 0:05:02 lr: 0.000217 loss: 0.3880 (0.3888) grad: 0.1849 (0.1956) time: 0.6984 data: 0.2238 max mem: 25051 +train: [10] [260/800] eta: 0:04:51 lr: 0.000216 loss: 0.3880 (0.3944) grad: 0.1849 (0.1987) time: 0.5388 data: 0.0031 max mem: 25051 +train: [10] [280/800] eta: 0:04:38 lr: 0.000215 loss: 0.3880 (0.3950) grad: 0.1684 (0.1983) time: 0.4878 data: 0.0033 max mem: 25051 +train: [10] [300/800] eta: 0:04:26 lr: 0.000215 loss: 0.3747 (0.3904) grad: 0.1897 (0.2016) time: 0.4807 data: 0.0032 max mem: 25051 +train: [10] [320/800] eta: 0:04:14 lr: 0.000214 loss: 0.3526 (0.3888) grad: 0.2124 (0.2015) time: 0.4882 data: 0.0030 max mem: 25051 +train: [10] [340/800] eta: 0:04:02 lr: 0.000213 loss: 0.3533 (0.3895) grad: 0.1958 (0.2015) time: 0.5000 data: 0.0029 max mem: 25051 +train: [10] [360/800] eta: 0:03:56 lr: 0.000213 loss: 0.3593 (0.3924) grad: 0.2125 (0.2061) time: 0.7132 data: 0.2109 max mem: 25051 +train: [10] [380/800] eta: 0:03:45 lr: 0.000212 loss: 0.3871 (0.3953) grad: 0.2125 (0.2064) time: 0.5201 data: 0.0036 max mem: 25051 +train: [10] [400/800] eta: 0:03:34 lr: 0.000211 loss: 0.3937 (0.3961) grad: 0.1662 (0.2048) time: 0.4952 data: 0.0035 max mem: 25051 +train: [10] [420/800] eta: 0:03:22 lr: 0.000210 loss: 0.4006 (0.3948) grad: 0.2169 (0.2071) time: 0.5045 data: 0.0033 max mem: 25051 +train: [10] [440/800] eta: 0:03:11 lr: 0.000210 loss: 0.4016 (0.3979) grad: 0.2169 (0.2094) time: 0.5090 data: 0.0034 max mem: 25051 +train: [10] [460/800] eta: 0:03:03 lr: 0.000209 loss: 0.3937 (0.3957) grad: 0.1689 (0.2078) time: 0.6956 data: 0.2183 max mem: 25051 +train: [10] [480/800] eta: 0:02:52 lr: 0.000208 loss: 0.3778 (0.3951) grad: 0.1705 (0.2061) time: 0.5473 data: 0.0034 max mem: 25051 +train: [10] [500/800] eta: 0:02:41 lr: 0.000207 loss: 0.3778 (0.3954) grad: 0.1577 (0.2060) time: 0.5006 data: 0.0033 max mem: 25051 +train: [10] [520/800] eta: 0:02:30 lr: 0.000207 loss: 0.3778 (0.3980) grad: 0.1551 (0.2041) time: 0.4718 data: 0.0033 max mem: 25051 +train: [10] [540/800] eta: 0:02:19 lr: 0.000206 loss: 0.3712 (0.3974) grad: 0.1388 (0.2047) time: 0.5056 data: 0.0036 max mem: 25051 +train: [10] [560/800] eta: 0:02:07 lr: 0.000205 loss: 0.4025 (0.3975) grad: 0.1395 (0.2028) time: 0.4945 data: 0.0032 max mem: 25051 +train: [10] [580/800] eta: 0:01:58 lr: 0.000205 loss: 0.3816 (0.3979) grad: 0.1544 (0.2039) time: 0.6927 data: 0.2163 max mem: 25051 +train: [10] [600/800] eta: 0:01:47 lr: 0.000204 loss: 0.3709 (0.3982) grad: 0.1677 (0.2028) time: 0.4857 data: 0.0031 max mem: 25051 +train: [10] [620/800] eta: 0:01:36 lr: 0.000203 loss: 0.3756 (0.3977) grad: 0.1618 (0.2013) time: 0.4933 data: 0.0028 max mem: 25051 +train: [10] [640/800] eta: 0:01:25 lr: 0.000202 loss: 0.3641 (0.3963) grad: 0.1746 (0.2009) time: 0.4950 data: 0.0033 max mem: 25051 +train: [10] [660/800] eta: 0:01:14 lr: 0.000202 loss: 0.3756 (0.3969) grad: 0.1699 (0.2004) time: 0.5020 data: 0.0035 max mem: 25051 +train: [10] [680/800] eta: 0:01:03 lr: 0.000201 loss: 0.3756 (0.3977) grad: 0.1695 (0.1991) time: 0.4741 data: 0.0030 max mem: 25051 +train: [10] [700/800] eta: 0:00:53 lr: 0.000200 loss: 0.3915 (0.4001) grad: 0.1680 (0.1971) time: 0.7388 data: 0.2226 max mem: 25051 +train: [10] [720/800] eta: 0:00:43 lr: 0.000199 loss: 0.4301 (0.4007) grad: 0.1680 (0.1987) time: 0.5689 data: 0.0289 max mem: 25051 +train: [10] [740/800] eta: 0:00:32 lr: 0.000199 loss: 0.4251 (0.4008) grad: 0.1467 (0.1988) time: 0.5385 data: 0.0033 max mem: 25051 +train: [10] [760/800] eta: 0:00:21 lr: 0.000198 loss: 0.4050 (0.3994) grad: 0.1679 (0.1986) time: 0.4812 data: 0.0020 max mem: 25051 +train: [10] [780/800] eta: 0:00:10 lr: 0.000197 loss: 0.3933 (0.3995) grad: 0.1811 (0.1977) time: 0.5479 data: 0.0396 max mem: 25051 +train: [10] [799/800] eta: 0:00:00 lr: 0.000196 loss: 0.3745 (0.3992) grad: 0.1493 (0.1962) time: 0.4778 data: 0.0017 max mem: 25051 +train: [10] Total time: 0:07:08 (0.5360 s / it) +train: [10] Summary: lr: 0.000196 loss: 0.3745 (0.3992) grad: 0.1493 (0.1962) +eval (validation): [10] [ 0/25] eta: 0:01:46 time: 4.2610 data: 3.9983 max mem: 25051 +eval (validation): [10] [20/25] eta: 0:00:02 time: 0.3836 data: 0.0025 max mem: 25051 +eval (validation): [10] [24/25] eta: 0:00:00 time: 0.3688 data: 0.0023 max mem: 25051 +eval (validation): [10] Total time: 0:00:13 (0.5419 s / it) +cv: [10] best hparam: (0.44, 1.0) (019) ('019_lr4.4e-01_wd1.0e+00') loss: 0.669 acc: 0.687 f1: 0.674 bacc: 0.674 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/ppmi_dx__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/ppmi_dx__patch__attn/checkpoint-best.pth +train: [11] [ 0/800] eta: 0:56:30 lr: nan time: 4.2384 data: 3.8176 max mem: 25051 +train: [11] [ 20/800] eta: 0:09:03 lr: 0.000196 loss: 0.3975 (0.3889) grad: 0.1608 (0.1750) time: 0.5201 data: 0.0032 max mem: 25051 +train: [11] [ 40/800] eta: 0:07:35 lr: 0.000195 loss: 0.3975 (0.4064) grad: 0.1765 (0.2353) time: 0.4957 data: 0.0028 max mem: 25051 +train: [11] [ 60/800] eta: 0:06:57 lr: 0.000194 loss: 0.4096 (0.4071) grad: 0.1713 (0.2061) time: 0.4918 data: 0.0025 max mem: 25051 +train: [11] [ 80/800] eta: 0:06:32 lr: 0.000193 loss: 0.3975 (0.4003) grad: 0.1746 (0.2089) time: 0.4911 data: 0.0026 max mem: 25051 +train: [11] [100/800] eta: 0:06:15 lr: 0.000193 loss: 0.4110 (0.4020) grad: 0.1746 (0.2035) time: 0.4997 data: 0.0026 max mem: 25051 +train: [11] [120/800] eta: 0:06:21 lr: 0.000192 loss: 0.4110 (0.4101) grad: 0.1746 (0.2076) time: 0.6821 data: 0.2075 max mem: 25051 +train: [11] [140/800] eta: 0:06:03 lr: 0.000191 loss: 0.3766 (0.4006) grad: 0.1967 (0.2087) time: 0.4870 data: 0.0036 max mem: 25051 +train: [11] [160/800] eta: 0:05:47 lr: 0.000190 loss: 0.3766 (0.3939) grad: 0.1666 (0.2006) time: 0.4923 data: 0.0026 max mem: 25051 +train: [11] [180/800] eta: 0:05:33 lr: 0.000190 loss: 0.3713 (0.3896) grad: 0.1666 (0.1982) time: 0.5019 data: 0.0036 max mem: 25051 +train: [11] [200/800] eta: 0:05:21 lr: 0.000189 loss: 0.3534 (0.3864) grad: 0.1305 (0.1924) time: 0.5042 data: 0.0031 max mem: 25051 +train: [11] [220/800] eta: 0:05:08 lr: 0.000188 loss: 0.3713 (0.3896) grad: 0.1368 (0.1894) time: 0.4937 data: 0.0035 max mem: 25051 +train: [11] [240/800] eta: 0:05:07 lr: 0.000187 loss: 0.3824 (0.3955) grad: 0.1442 (0.1993) time: 0.7512 data: 0.2424 max mem: 25051 +train: [11] [260/800] eta: 0:04:56 lr: 0.000187 loss: 0.3665 (0.3959) grad: 0.1606 (0.1953) time: 0.5346 data: 0.0025 max mem: 25051 +train: [11] [280/800] eta: 0:04:43 lr: 0.000186 loss: 0.4202 (0.3988) grad: 0.1624 (0.1914) time: 0.4922 data: 0.0026 max mem: 25051 +train: [11] [300/800] eta: 0:04:30 lr: 0.000185 loss: 0.3965 (0.4020) grad: 0.1606 (0.1909) time: 0.4977 data: 0.0035 max mem: 25051 +train: [11] [320/800] eta: 0:04:19 lr: 0.000184 loss: 0.3765 (0.3985) grad: 0.1606 (0.1909) time: 0.5461 data: 0.0040 max mem: 25051 +train: [11] [340/800] eta: 0:04:07 lr: 0.000184 loss: 0.3731 (0.3956) grad: 0.1555 (0.1889) time: 0.4802 data: 0.0031 max mem: 25051 +train: [11] [360/800] eta: 0:04:00 lr: 0.000183 loss: 0.3529 (0.3951) grad: 0.1555 (0.1871) time: 0.7032 data: 0.2075 max mem: 25051 +train: [11] [380/800] eta: 0:03:48 lr: 0.000182 loss: 0.3731 (0.3984) grad: 0.1563 (0.1877) time: 0.4737 data: 0.0031 max mem: 25051 +train: [11] [400/800] eta: 0:03:36 lr: 0.000181 loss: 0.3916 (0.3968) grad: 0.1482 (0.1857) time: 0.5142 data: 0.0037 max mem: 25051 +train: [11] [420/800] eta: 0:03:24 lr: 0.000181 loss: 0.4046 (0.3964) grad: 0.1482 (0.1841) time: 0.4903 data: 0.0033 max mem: 25051 +train: [11] [440/800] eta: 0:03:13 lr: 0.000180 loss: 0.4046 (0.3976) grad: 0.1563 (0.1846) time: 0.4937 data: 0.0031 max mem: 25051 +train: [11] [460/800] eta: 0:03:05 lr: 0.000179 loss: 0.3891 (0.3978) grad: 0.1450 (0.1826) time: 0.7038 data: 0.2171 max mem: 25051 +train: [11] [480/800] eta: 0:02:54 lr: 0.000178 loss: 0.3955 (0.3972) grad: 0.1532 (0.1831) time: 0.5463 data: 0.0047 max mem: 25051 +train: [11] [500/800] eta: 0:02:42 lr: 0.000177 loss: 0.3891 (0.3967) grad: 0.1552 (0.1827) time: 0.4821 data: 0.0030 max mem: 25051 +train: [11] [520/800] eta: 0:02:31 lr: 0.000177 loss: 0.3805 (0.3945) grad: 0.1532 (0.1831) time: 0.4953 data: 0.0033 max mem: 25051 +train: [11] [540/800] eta: 0:02:20 lr: 0.000176 loss: 0.3547 (0.3936) grad: 0.1780 (0.1850) time: 0.4937 data: 0.0031 max mem: 25051 +train: [11] [560/800] eta: 0:02:08 lr: 0.000175 loss: 0.3733 (0.3943) grad: 0.1780 (0.1836) time: 0.4772 data: 0.0028 max mem: 25051 +train: [11] [580/800] eta: 0:01:58 lr: 0.000174 loss: 0.3571 (0.3931) grad: 0.1670 (0.1832) time: 0.6585 data: 0.2012 max mem: 25051 +train: [11] [600/800] eta: 0:01:48 lr: 0.000174 loss: 0.3831 (0.3925) grad: 0.1888 (0.1849) time: 0.5584 data: 0.0055 max mem: 25051 +train: [11] [620/800] eta: 0:01:37 lr: 0.000173 loss: 0.3773 (0.3914) grad: 0.1888 (0.1863) time: 0.5002 data: 0.0031 max mem: 25051 +train: [11] [640/800] eta: 0:01:26 lr: 0.000172 loss: 0.3571 (0.3900) grad: 0.1670 (0.1839) time: 0.5062 data: 0.0034 max mem: 25051 +train: [11] [660/800] eta: 0:01:15 lr: 0.000171 loss: 0.3692 (0.3897) grad: 0.1543 (0.1827) time: 0.5203 data: 0.0036 max mem: 25051 +train: [11] [680/800] eta: 0:01:04 lr: 0.000170 loss: 0.3773 (0.3915) grad: 0.1543 (0.1821) time: 0.5590 data: 0.0039 max mem: 25051 +train: [11] [700/800] eta: 0:00:54 lr: 0.000170 loss: 0.3799 (0.3910) grad: 0.1400 (0.1806) time: 0.7675 data: 0.2168 max mem: 25051 +train: [11] [720/800] eta: 0:00:43 lr: 0.000169 loss: 0.3799 (0.3907) grad: 0.1473 (0.1804) time: 0.4951 data: 0.0027 max mem: 25051 +train: [11] [740/800] eta: 0:00:32 lr: 0.000168 loss: 0.3848 (0.3919) grad: 0.1373 (0.1785) time: 0.4993 data: 0.0028 max mem: 25051 +train: [11] [760/800] eta: 0:00:21 lr: 0.000167 loss: 0.3623 (0.3912) grad: 0.1082 (0.1777) time: 0.5028 data: 0.0034 max mem: 25051 +train: [11] [780/800] eta: 0:00:10 lr: 0.000167 loss: 0.3602 (0.3907) grad: 0.1248 (0.1775) time: 0.4893 data: 0.0032 max mem: 25051 +train: [11] [799/800] eta: 0:00:00 lr: 0.000166 loss: 0.3771 (0.3912) grad: 0.1346 (0.1784) time: 0.4773 data: 0.0032 max mem: 25051 +train: [11] Total time: 0:07:11 (0.5392 s / it) +train: [11] Summary: lr: 0.000166 loss: 0.3771 (0.3912) grad: 0.1346 (0.1784) +eval (validation): [11] [ 0/25] eta: 0:01:44 time: 4.1792 data: 3.8779 max mem: 25051 +eval (validation): [11] [20/25] eta: 0:00:02 time: 0.3800 data: 0.0022 max mem: 25051 +eval (validation): [11] [24/25] eta: 0:00:00 time: 0.3786 data: 0.0023 max mem: 25051 +eval (validation): [11] Total time: 0:00:13 (0.5344 s / it) +cv: [11] best hparam: (6, 1.0) (035) ('035_lr6.0e+00_wd1.0e+00') loss: 2.249 acc: 0.646 f1: 0.616 bacc: 0.614 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/ppmi_dx__patch__attn/checkpoint-last.pth +train: [12] [ 0/800] eta: 0:59:15 lr: nan time: 4.4447 data: 4.0448 max mem: 25051 +train: [12] [ 20/800] eta: 0:09:26 lr: 0.000165 loss: 0.3323 (0.3833) grad: 0.1678 (0.2088) time: 0.5408 data: 0.0050 max mem: 25051 +train: [12] [ 40/800] eta: 0:07:47 lr: 0.000164 loss: 0.3539 (0.3836) grad: 0.1519 (0.1898) time: 0.4968 data: 0.0032 max mem: 25051 +train: [12] [ 60/800] eta: 0:06:57 lr: 0.000163 loss: 0.3559 (0.3799) grad: 0.1480 (0.1704) time: 0.4603 data: 0.0026 max mem: 25051 +train: [12] [ 80/800] eta: 0:06:35 lr: 0.000163 loss: 0.3881 (0.3952) grad: 0.1519 (0.1686) time: 0.5024 data: 0.0037 max mem: 25051 +train: [12] [100/800] eta: 0:06:15 lr: 0.000162 loss: 0.3935 (0.3872) grad: 0.1480 (0.1705) time: 0.4884 data: 0.0032 max mem: 25051 +train: [12] [120/800] eta: 0:06:20 lr: 0.000161 loss: 0.4066 (0.3877) grad: 0.1460 (0.1709) time: 0.6735 data: 0.2104 max mem: 25051 +train: [12] [140/800] eta: 0:06:05 lr: 0.000160 loss: 0.4066 (0.3855) grad: 0.1460 (0.1718) time: 0.5161 data: 0.0034 max mem: 25051 +train: [12] [160/800] eta: 0:05:55 lr: 0.000160 loss: 0.3747 (0.3854) grad: 0.1424 (0.1753) time: 0.5647 data: 0.0037 max mem: 25051 +train: [12] [180/800] eta: 0:05:44 lr: 0.000159 loss: 0.4055 (0.3906) grad: 0.1401 (0.1745) time: 0.5618 data: 0.0038 max mem: 25051 +train: [12] [200/800] eta: 0:05:30 lr: 0.000158 loss: 0.3747 (0.3865) grad: 0.1676 (0.1808) time: 0.5045 data: 0.0035 max mem: 25051 +train: [12] [220/800] eta: 0:05:16 lr: 0.000157 loss: 0.3662 (0.3878) grad: 0.1721 (0.1856) time: 0.4890 data: 0.0036 max mem: 25051 +train: [12] [240/800] eta: 0:05:15 lr: 0.000156 loss: 0.3653 (0.3850) grad: 0.1676 (0.1843) time: 0.7760 data: 0.2409 max mem: 25051 +train: [12] [260/800] eta: 0:05:03 lr: 0.000156 loss: 0.3568 (0.3839) grad: 0.1696 (0.1842) time: 0.5284 data: 0.0026 max mem: 25051 +train: [12] [280/800] eta: 0:04:49 lr: 0.000155 loss: 0.3689 (0.3832) grad: 0.1473 (0.1811) time: 0.4996 data: 0.0039 max mem: 25051 +train: [12] [300/800] eta: 0:04:36 lr: 0.000154 loss: 0.3721 (0.3828) grad: 0.1508 (0.1817) time: 0.4859 data: 0.0029 max mem: 25051 +train: [12] [320/800] eta: 0:04:23 lr: 0.000153 loss: 0.3740 (0.3818) grad: 0.1668 (0.1841) time: 0.4983 data: 0.0032 max mem: 25051 +train: [12] [340/800] eta: 0:04:10 lr: 0.000152 loss: 0.3740 (0.3835) grad: 0.1739 (0.1843) time: 0.4756 data: 0.0030 max mem: 25051 +train: [12] [360/800] eta: 0:04:05 lr: 0.000152 loss: 0.3690 (0.3818) grad: 0.1995 (0.1834) time: 0.7764 data: 0.2129 max mem: 25051 +train: [12] [380/800] eta: 0:03:53 lr: 0.000151 loss: 0.3480 (0.3798) grad: 0.1995 (0.1826) time: 0.5349 data: 0.0029 max mem: 25051 +train: [12] [400/800] eta: 0:03:41 lr: 0.000150 loss: 0.3187 (0.3761) grad: 0.1892 (0.1831) time: 0.5247 data: 0.0022 max mem: 25051 +train: [12] [420/800] eta: 0:03:29 lr: 0.000149 loss: 0.3178 (0.3749) grad: 0.1892 (0.1880) time: 0.4939 data: 0.0028 max mem: 25051 +train: [12] [440/800] eta: 0:03:17 lr: 0.000149 loss: 0.3187 (0.3761) grad: 0.1892 (0.1880) time: 0.4754 data: 0.0030 max mem: 25051 +train: [12] [460/800] eta: 0:03:08 lr: 0.000148 loss: 0.3333 (0.3773) grad: 0.1751 (0.1862) time: 0.6863 data: 0.2212 max mem: 25051 +train: [12] [480/800] eta: 0:02:57 lr: 0.000147 loss: 0.3914 (0.3800) grad: 0.1683 (0.1846) time: 0.5286 data: 0.0034 max mem: 25051 +train: [12] [500/800] eta: 0:02:45 lr: 0.000146 loss: 0.3962 (0.3792) grad: 0.1684 (0.1859) time: 0.4928 data: 0.0036 max mem: 25051 +train: [12] [520/800] eta: 0:02:33 lr: 0.000145 loss: 0.3654 (0.3770) grad: 0.1552 (0.1834) time: 0.5017 data: 0.0039 max mem: 25051 +train: [12] [540/800] eta: 0:02:22 lr: 0.000145 loss: 0.3569 (0.3756) grad: 0.1588 (0.1836) time: 0.4790 data: 0.0034 max mem: 25051 +train: [12] [560/800] eta: 0:02:10 lr: 0.000144 loss: 0.3207 (0.3745) grad: 0.1664 (0.1842) time: 0.5029 data: 0.0031 max mem: 25051 +train: [12] [580/800] eta: 0:02:00 lr: 0.000143 loss: 0.3207 (0.3749) grad: 0.1193 (0.1816) time: 0.6716 data: 0.2056 max mem: 25051 +train: [12] [600/800] eta: 0:01:49 lr: 0.000142 loss: 0.3270 (0.3732) grad: 0.1098 (0.1805) time: 0.5004 data: 0.0031 max mem: 25051 +train: [12] [620/800] eta: 0:01:38 lr: 0.000141 loss: 0.3367 (0.3752) grad: 0.1193 (0.1806) time: 0.4798 data: 0.0031 max mem: 25051 +train: [12] [640/800] eta: 0:01:27 lr: 0.000141 loss: 0.3513 (0.3744) grad: 0.1077 (0.1787) time: 0.5010 data: 0.0034 max mem: 25051 +train: [12] [660/800] eta: 0:01:15 lr: 0.000140 loss: 0.3447 (0.3737) grad: 0.1311 (0.1800) time: 0.4996 data: 0.0033 max mem: 25051 +train: [12] [680/800] eta: 0:01:04 lr: 0.000139 loss: 0.3513 (0.3747) grad: 0.1382 (0.1794) time: 0.4845 data: 0.0032 max mem: 25051 +train: [12] [700/800] eta: 0:00:54 lr: 0.000138 loss: 0.3513 (0.3754) grad: 0.1432 (0.1795) time: 0.7125 data: 0.2320 max mem: 25051 +train: [12] [720/800] eta: 0:00:43 lr: 0.000138 loss: 0.3712 (0.3762) grad: 0.1706 (0.1821) time: 0.5360 data: 0.0036 max mem: 25051 +train: [12] [740/800] eta: 0:00:32 lr: 0.000137 loss: 0.3920 (0.3775) grad: 0.1499 (0.1818) time: 0.5022 data: 0.0033 max mem: 25051 +train: [12] [760/800] eta: 0:00:21 lr: 0.000136 loss: 0.3875 (0.3768) grad: 0.1706 (0.1823) time: 0.4859 data: 0.0034 max mem: 25051 +train: [12] [780/800] eta: 0:00:10 lr: 0.000135 loss: 0.3875 (0.3775) grad: 0.1971 (0.1825) time: 0.5124 data: 0.0034 max mem: 25051 +train: [12] [799/800] eta: 0:00:00 lr: 0.000134 loss: 0.3920 (0.3777) grad: 0.1416 (0.1820) time: 0.5034 data: 0.0033 max mem: 25051 +train: [12] Total time: 0:07:13 (0.5414 s / it) +train: [12] Summary: lr: 0.000134 loss: 0.3920 (0.3777) grad: 0.1416 (0.1820) +eval (validation): [12] [ 0/25] eta: 0:01:46 time: 4.2435 data: 3.9258 max mem: 25051 +eval (validation): [12] [20/25] eta: 0:00:02 time: 0.4144 data: 0.0035 max mem: 25051 +eval (validation): [12] [24/25] eta: 0:00:00 time: 0.3731 data: 0.0022 max mem: 25051 +eval (validation): [12] Total time: 0:00:14 (0.5651 s / it) +cv: [12] best hparam: (0.053, 1.0) (006) ('006_lr5.3e-02_wd1.0e+00') loss: 0.636 acc: 0.697 f1: 0.641 bacc: 0.642 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/ppmi_dx__patch__attn/checkpoint-last.pth +train: [13] [ 0/800] eta: 0:54:29 lr: nan time: 4.0867 data: 3.6812 max mem: 25051 +train: [13] [ 20/800] eta: 0:10:08 lr: 0.000134 loss: 0.3406 (0.3603) grad: 0.1245 (0.1418) time: 0.6141 data: 0.0046 max mem: 25051 +train: [13] [ 40/800] eta: 0:08:28 lr: 0.000133 loss: 0.3351 (0.3508) grad: 0.1793 (0.1751) time: 0.5544 data: 0.0034 max mem: 25051 +train: [13] [ 60/800] eta: 0:07:31 lr: 0.000132 loss: 0.3351 (0.3500) grad: 0.1559 (0.1619) time: 0.4900 data: 0.0035 max mem: 25051 +train: [13] [ 80/800] eta: 0:06:56 lr: 0.000131 loss: 0.3406 (0.3534) grad: 0.1546 (0.1646) time: 0.4814 data: 0.0031 max mem: 25051 +train: [13] [100/800] eta: 0:06:33 lr: 0.000130 loss: 0.3615 (0.3702) grad: 0.1589 (0.1699) time: 0.4929 data: 0.0035 max mem: 25051 +train: [13] [120/800] eta: 0:06:34 lr: 0.000130 loss: 0.3615 (0.3702) grad: 0.1494 (0.1710) time: 0.6740 data: 0.2076 max mem: 25051 +train: [13] [140/800] eta: 0:06:20 lr: 0.000129 loss: 0.3615 (0.3670) grad: 0.1546 (0.1724) time: 0.5547 data: 0.0683 max mem: 25051 +train: [13] [160/800] eta: 0:06:00 lr: 0.000128 loss: 0.3634 (0.3687) grad: 0.1382 (0.1662) time: 0.4717 data: 0.0018 max mem: 25051 +train: [13] [180/800] eta: 0:05:46 lr: 0.000127 loss: 0.3505 (0.3688) grad: 0.1183 (0.1646) time: 0.5258 data: 0.0028 max mem: 25051 +train: [13] [200/800] eta: 0:05:34 lr: 0.000127 loss: 0.3494 (0.3646) grad: 0.1183 (0.1683) time: 0.5458 data: 0.0033 max mem: 25051 +train: [13] [220/800] eta: 0:05:19 lr: 0.000126 loss: 0.3634 (0.3665) grad: 0.1191 (0.1701) time: 0.4804 data: 0.0030 max mem: 25051 +train: [13] [240/800] eta: 0:05:14 lr: 0.000125 loss: 0.3797 (0.3704) grad: 0.1444 (0.1707) time: 0.6790 data: 0.2231 max mem: 25051 +train: [13] [260/800] eta: 0:05:00 lr: 0.000124 loss: 0.3801 (0.3716) grad: 0.1637 (0.1716) time: 0.4891 data: 0.0022 max mem: 25051 +train: [13] [280/800] eta: 0:04:47 lr: 0.000124 loss: 0.3801 (0.3692) grad: 0.1721 (0.1732) time: 0.5051 data: 0.0034 max mem: 25051 +train: [13] [300/800] eta: 0:04:34 lr: 0.000123 loss: 0.3801 (0.3704) grad: 0.1581 (0.1696) time: 0.5030 data: 0.0034 max mem: 25051 +train: [13] [320/800] eta: 0:04:23 lr: 0.000122 loss: 0.3626 (0.3703) grad: 0.1471 (0.1713) time: 0.5289 data: 0.0037 max mem: 25051 +train: [13] [340/800] eta: 0:04:10 lr: 0.000121 loss: 0.3538 (0.3692) grad: 0.1471 (0.1729) time: 0.4761 data: 0.0028 max mem: 25051 +train: [13] [360/800] eta: 0:04:04 lr: 0.000120 loss: 0.3585 (0.3713) grad: 0.1187 (0.1715) time: 0.7487 data: 0.2715 max mem: 25051 +train: [13] [380/800] eta: 0:03:51 lr: 0.000120 loss: 0.3585 (0.3703) grad: 0.1295 (0.1703) time: 0.4734 data: 0.0031 max mem: 25051 +train: [13] [400/800] eta: 0:03:38 lr: 0.000119 loss: 0.3505 (0.3691) grad: 0.1434 (0.1722) time: 0.4781 data: 0.0022 max mem: 25051 +train: [13] [420/800] eta: 0:03:26 lr: 0.000118 loss: 0.3489 (0.3668) grad: 0.1195 (0.1697) time: 0.4792 data: 0.0027 max mem: 25051 +train: [13] [440/800] eta: 0:03:14 lr: 0.000117 loss: 0.3468 (0.3673) grad: 0.1195 (0.1675) time: 0.4902 data: 0.0023 max mem: 25051 +train: [13] [460/800] eta: 0:03:06 lr: 0.000117 loss: 0.3438 (0.3673) grad: 0.1366 (0.1699) time: 0.6761 data: 0.2143 max mem: 25051 +train: [13] [480/800] eta: 0:02:54 lr: 0.000116 loss: 0.3438 (0.3669) grad: 0.1366 (0.1713) time: 0.4726 data: 0.0028 max mem: 25051 +train: [13] [500/800] eta: 0:02:42 lr: 0.000115 loss: 0.4014 (0.3675) grad: 0.1523 (0.1717) time: 0.4804 data: 0.0023 max mem: 25051 +train: [13] [520/800] eta: 0:02:31 lr: 0.000114 loss: 0.3909 (0.3679) grad: 0.1538 (0.1695) time: 0.4919 data: 0.0031 max mem: 25051 +train: [13] [540/800] eta: 0:02:19 lr: 0.000114 loss: 0.3408 (0.3672) grad: 0.1444 (0.1695) time: 0.4755 data: 0.0024 max mem: 25051 +train: [13] [560/800] eta: 0:02:08 lr: 0.000113 loss: 0.3574 (0.3678) grad: 0.1396 (0.1708) time: 0.4675 data: 0.0026 max mem: 25051 +train: [13] [580/800] eta: 0:01:58 lr: 0.000112 loss: 0.3572 (0.3672) grad: 0.1396 (0.1720) time: 0.6816 data: 0.2209 max mem: 25051 +train: [13] [600/800] eta: 0:01:48 lr: 0.000111 loss: 0.3572 (0.3667) grad: 0.1548 (0.1741) time: 0.6314 data: 0.0345 max mem: 25051 +train: [13] [620/800] eta: 0:01:37 lr: 0.000110 loss: 0.3620 (0.3669) grad: 0.1427 (0.1725) time: 0.5289 data: 0.0033 max mem: 25051 +train: [13] [640/800] eta: 0:01:26 lr: 0.000110 loss: 0.3517 (0.3659) grad: 0.1548 (0.1728) time: 0.5165 data: 0.0037 max mem: 25051 +train: [13] [660/800] eta: 0:01:15 lr: 0.000109 loss: 0.3488 (0.3645) grad: 0.1302 (0.1722) time: 0.4905 data: 0.0035 max mem: 25051 +train: [13] [680/800] eta: 0:01:04 lr: 0.000108 loss: 0.3382 (0.3639) grad: 0.1285 (0.1720) time: 0.4869 data: 0.0036 max mem: 25051 +train: [13] [700/800] eta: 0:00:54 lr: 0.000107 loss: 0.3337 (0.3647) grad: 0.1615 (0.1714) time: 0.6782 data: 0.2097 max mem: 25051 +train: [13] [720/800] eta: 0:00:43 lr: 0.000107 loss: 0.3323 (0.3634) grad: 0.1615 (0.1716) time: 0.4928 data: 0.0026 max mem: 25051 +train: [13] [740/800] eta: 0:00:32 lr: 0.000106 loss: 0.3323 (0.3634) grad: 0.1656 (0.1722) time: 0.4827 data: 0.0034 max mem: 25051 +train: [13] [760/800] eta: 0:00:21 lr: 0.000105 loss: 0.3323 (0.3634) grad: 0.1771 (0.1730) time: 0.4791 data: 0.0034 max mem: 25051 +train: [13] [780/800] eta: 0:00:10 lr: 0.000104 loss: 0.3299 (0.3638) grad: 0.1632 (0.1721) time: 0.4873 data: 0.0033 max mem: 25051 +train: [13] [799/800] eta: 0:00:00 lr: 0.000104 loss: 0.3619 (0.3639) grad: 0.1498 (0.1717) time: 0.4635 data: 0.0030 max mem: 25051 +train: [13] Total time: 0:07:08 (0.5353 s / it) +train: [13] Summary: lr: 0.000104 loss: 0.3619 (0.3639) grad: 0.1498 (0.1717) +eval (validation): [13] [ 0/25] eta: 0:01:40 time: 4.0204 data: 3.7198 max mem: 25051 +eval (validation): [13] [20/25] eta: 0:00:03 time: 0.4371 data: 0.0026 max mem: 25051 +eval (validation): [13] [24/25] eta: 0:00:00 time: 0.4108 data: 0.0025 max mem: 25051 +eval (validation): [13] Total time: 0:00:14 (0.5750 s / it) +cv: [13] best hparam: (0.053, 1.0) (006) ('006_lr5.3e-02_wd1.0e+00') loss: 0.636 acc: 0.687 f1: 0.626 bacc: 0.629 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/ppmi_dx__patch__attn/checkpoint-last.pth +train: [14] [ 0/800] eta: 0:55:10 lr: nan time: 4.1385 data: 3.7860 max mem: 25051 +train: [14] [ 20/800] eta: 0:08:18 lr: 0.000103 loss: 0.3755 (0.3958) grad: 0.2036 (0.2237) time: 0.4648 data: 0.0021 max mem: 25051 +train: [14] [ 40/800] eta: 0:07:04 lr: 0.000102 loss: 0.3755 (0.3954) grad: 0.1402 (0.1932) time: 0.4746 data: 0.0029 max mem: 25051 +train: [14] [ 60/800] eta: 0:06:40 lr: 0.000101 loss: 0.3740 (0.3798) grad: 0.1625 (0.2029) time: 0.5037 data: 0.0031 max mem: 25051 +train: [14] [ 80/800] eta: 0:06:22 lr: 0.000101 loss: 0.3493 (0.3637) grad: 0.1658 (0.2005) time: 0.4989 data: 0.0033 max mem: 25051 +train: [14] [100/800] eta: 0:06:06 lr: 0.000100 loss: 0.3288 (0.3605) grad: 0.1767 (0.2059) time: 0.4974 data: 0.0031 max mem: 25051 +train: [14] [120/800] eta: 0:06:12 lr: 0.000099 loss: 0.3288 (0.3724) grad: 0.1767 (0.2006) time: 0.6699 data: 0.2095 max mem: 25051 +train: [14] [140/800] eta: 0:05:56 lr: 0.000099 loss: 0.3191 (0.3629) grad: 0.1658 (0.1891) time: 0.4963 data: 0.0031 max mem: 25051 +train: [14] [160/800] eta: 0:05:44 lr: 0.000098 loss: 0.3343 (0.3614) grad: 0.1239 (0.1874) time: 0.5200 data: 0.0033 max mem: 25051 +train: [14] [180/800] eta: 0:05:32 lr: 0.000097 loss: 0.3343 (0.3626) grad: 0.1239 (0.1854) time: 0.5149 data: 0.0034 max mem: 25051 +train: [14] [200/800] eta: 0:05:20 lr: 0.000096 loss: 0.3343 (0.3625) grad: 0.1423 (0.1934) time: 0.5239 data: 0.0034 max mem: 25051 +train: [14] [220/800] eta: 0:05:07 lr: 0.000096 loss: 0.3497 (0.3644) grad: 0.1592 (0.1896) time: 0.4854 data: 0.0030 max mem: 25051 +train: [14] [240/800] eta: 0:05:04 lr: 0.000095 loss: 0.3587 (0.3645) grad: 0.1541 (0.1863) time: 0.6937 data: 0.2248 max mem: 25051 +train: [14] [260/800] eta: 0:04:51 lr: 0.000094 loss: 0.3497 (0.3648) grad: 0.1592 (0.1850) time: 0.4964 data: 0.0025 max mem: 25051 +train: [14] [280/800] eta: 0:04:39 lr: 0.000093 loss: 0.3691 (0.3652) grad: 0.1276 (0.1833) time: 0.5068 data: 0.0031 max mem: 25051 +train: [14] [300/800] eta: 0:04:27 lr: 0.000093 loss: 0.3483 (0.3656) grad: 0.1202 (0.1836) time: 0.4840 data: 0.0027 max mem: 25051 +train: [14] [320/800] eta: 0:04:14 lr: 0.000092 loss: 0.3424 (0.3635) grad: 0.1526 (0.1872) time: 0.4811 data: 0.0025 max mem: 25051 +train: [14] [340/800] eta: 0:04:02 lr: 0.000091 loss: 0.3232 (0.3612) grad: 0.1526 (0.1863) time: 0.4643 data: 0.0028 max mem: 25051 +train: [14] [360/800] eta: 0:03:58 lr: 0.000090 loss: 0.3232 (0.3590) grad: 0.1549 (0.1869) time: 0.7926 data: 0.2213 max mem: 25051 +train: [14] [380/800] eta: 0:03:46 lr: 0.000090 loss: 0.3293 (0.3588) grad: 0.1530 (0.1856) time: 0.4928 data: 0.0033 max mem: 25051 +train: [14] [400/800] eta: 0:03:34 lr: 0.000089 loss: 0.3455 (0.3615) grad: 0.1530 (0.1887) time: 0.4947 data: 0.0036 max mem: 25051 +train: [14] [420/800] eta: 0:03:23 lr: 0.000088 loss: 0.3455 (0.3595) grad: 0.1712 (0.1933) time: 0.4911 data: 0.0036 max mem: 25051 +train: [14] [440/800] eta: 0:03:12 lr: 0.000088 loss: 0.3455 (0.3606) grad: 0.1712 (0.1923) time: 0.5227 data: 0.0030 max mem: 25051 +train: [14] [460/800] eta: 0:03:03 lr: 0.000087 loss: 0.3484 (0.3611) grad: 0.1541 (0.1890) time: 0.6700 data: 0.2156 max mem: 25051 +train: [14] [480/800] eta: 0:02:53 lr: 0.000086 loss: 0.3358 (0.3600) grad: 0.1278 (0.1876) time: 0.5715 data: 0.0772 max mem: 25051 +train: [14] [500/800] eta: 0:02:42 lr: 0.000085 loss: 0.3358 (0.3595) grad: 0.1188 (0.1860) time: 0.5271 data: 0.0032 max mem: 25051 +train: [14] [520/800] eta: 0:02:30 lr: 0.000085 loss: 0.3415 (0.3604) grad: 0.1278 (0.1842) time: 0.5001 data: 0.0033 max mem: 25051 +train: [14] [540/800] eta: 0:02:19 lr: 0.000084 loss: 0.3415 (0.3603) grad: 0.1442 (0.1844) time: 0.4942 data: 0.0028 max mem: 25051 +train: [14] [560/800] eta: 0:02:08 lr: 0.000083 loss: 0.3618 (0.3620) grad: 0.1442 (0.1836) time: 0.5093 data: 0.0034 max mem: 25051 +train: [14] [580/800] eta: 0:01:59 lr: 0.000083 loss: 0.3756 (0.3625) grad: 0.1549 (0.1839) time: 0.6955 data: 0.2206 max mem: 25051 +train: [14] [600/800] eta: 0:01:48 lr: 0.000082 loss: 0.3692 (0.3613) grad: 0.1846 (0.1846) time: 0.5286 data: 0.0324 max mem: 25051 +train: [14] [620/800] eta: 0:01:37 lr: 0.000081 loss: 0.3627 (0.3613) grad: 0.1876 (0.1875) time: 0.4730 data: 0.0022 max mem: 25051 +train: [14] [640/800] eta: 0:01:26 lr: 0.000081 loss: 0.3550 (0.3619) grad: 0.1898 (0.1887) time: 0.5130 data: 0.0032 max mem: 25051 +train: [14] [660/800] eta: 0:01:15 lr: 0.000080 loss: 0.3534 (0.3623) grad: 0.2115 (0.1896) time: 0.5294 data: 0.0035 max mem: 25051 +train: [14] [680/800] eta: 0:01:04 lr: 0.000079 loss: 0.3460 (0.3612) grad: 0.1888 (0.1891) time: 0.4982 data: 0.0035 max mem: 25051 +train: [14] [700/800] eta: 0:00:54 lr: 0.000078 loss: 0.3316 (0.3606) grad: 0.1834 (0.1884) time: 0.7136 data: 0.2156 max mem: 25051 +train: [14] [720/800] eta: 0:00:43 lr: 0.000078 loss: 0.3271 (0.3609) grad: 0.1834 (0.1891) time: 0.5058 data: 0.0026 max mem: 25051 +train: [14] [740/800] eta: 0:00:32 lr: 0.000077 loss: 0.3271 (0.3635) grad: 0.1834 (0.1898) time: 0.5354 data: 0.0038 max mem: 25051 +train: [14] [760/800] eta: 0:00:21 lr: 0.000076 loss: 0.3655 (0.3649) grad: 0.1771 (0.1890) time: 0.4823 data: 0.0036 max mem: 25051 +train: [14] [780/800] eta: 0:00:10 lr: 0.000076 loss: 0.3682 (0.3646) grad: 0.1853 (0.1897) time: 0.4718 data: 0.0030 max mem: 25051 +train: [14] [799/800] eta: 0:00:00 lr: 0.000075 loss: 0.3827 (0.3654) grad: 0.1962 (0.1916) time: 0.4993 data: 0.0032 max mem: 25051 +train: [14] Total time: 0:07:09 (0.5370 s / it) +train: [14] Summary: lr: 0.000075 loss: 0.3827 (0.3654) grad: 0.1962 (0.1916) +eval (validation): [14] [ 0/25] eta: 0:01:42 time: 4.0948 data: 3.8232 max mem: 25051 +eval (validation): [14] [20/25] eta: 0:00:02 time: 0.4023 data: 0.0268 max mem: 25051 +eval (validation): [14] [24/25] eta: 0:00:00 time: 0.3974 data: 0.0265 max mem: 25051 +eval (validation): [14] Total time: 0:00:13 (0.5501 s / it) +cv: [14] best hparam: (0.053, 1.0) (006) ('006_lr5.3e-02_wd1.0e+00') loss: 0.636 acc: 0.687 f1: 0.626 bacc: 0.629 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/ppmi_dx__patch__attn/checkpoint-last.pth +train: [15] [ 0/800] eta: 0:57:35 lr: nan time: 4.3193 data: 3.8935 max mem: 25051 +train: [15] [ 20/800] eta: 0:08:39 lr: 0.000074 loss: 0.4591 (0.4600) grad: 0.2584 (0.2430) time: 0.4832 data: 0.0035 max mem: 25051 +train: [15] [ 40/800] eta: 0:07:21 lr: 0.000074 loss: 0.3916 (0.4176) grad: 0.1679 (0.2074) time: 0.4904 data: 0.0031 max mem: 25051 +train: [15] [ 60/800] eta: 0:06:45 lr: 0.000073 loss: 0.3799 (0.3949) grad: 0.1351 (0.1832) time: 0.4816 data: 0.0031 max mem: 25051 +train: [15] [ 80/800] eta: 0:06:24 lr: 0.000072 loss: 0.3459 (0.3863) grad: 0.1351 (0.1850) time: 0.4931 data: 0.0032 max mem: 25051 +train: [15] [100/800] eta: 0:06:04 lr: 0.000072 loss: 0.3424 (0.3720) grad: 0.1351 (0.1847) time: 0.4652 data: 0.0031 max mem: 25051 +train: [15] [120/800] eta: 0:06:17 lr: 0.000071 loss: 0.3302 (0.3629) grad: 0.1385 (0.1777) time: 0.7285 data: 0.2165 max mem: 25051 +train: [15] [140/800] eta: 0:06:05 lr: 0.000070 loss: 0.3373 (0.3633) grad: 0.1478 (0.1903) time: 0.5431 data: 0.0036 max mem: 25051 +train: [15] [160/800] eta: 0:05:49 lr: 0.000070 loss: 0.3283 (0.3609) grad: 0.1552 (0.1949) time: 0.4921 data: 0.0034 max mem: 25051 +train: [15] [180/800] eta: 0:05:34 lr: 0.000069 loss: 0.3501 (0.3623) grad: 0.1464 (0.1869) time: 0.4840 data: 0.0032 max mem: 25051 +train: [15] [200/800] eta: 0:05:21 lr: 0.000068 loss: 0.3539 (0.3612) grad: 0.1492 (0.1853) time: 0.5045 data: 0.0035 max mem: 25051 +train: [15] [220/800] eta: 0:05:07 lr: 0.000068 loss: 0.3670 (0.3648) grad: 0.1543 (0.1918) time: 0.4720 data: 0.0031 max mem: 25051 +train: [15] [240/800] eta: 0:05:02 lr: 0.000067 loss: 0.3539 (0.3607) grad: 0.1519 (0.1899) time: 0.6558 data: 0.2016 max mem: 25051 +train: [15] [260/800] eta: 0:04:49 lr: 0.000066 loss: 0.3473 (0.3611) grad: 0.1571 (0.1892) time: 0.4838 data: 0.0027 max mem: 25051 +train: [15] [280/800] eta: 0:04:36 lr: 0.000066 loss: 0.3521 (0.3606) grad: 0.1681 (0.1884) time: 0.4840 data: 0.0032 max mem: 25051 +train: [15] [300/800] eta: 0:04:24 lr: 0.000065 loss: 0.3514 (0.3604) grad: 0.1657 (0.1884) time: 0.4992 data: 0.0033 max mem: 25051 +train: [15] [320/800] eta: 0:04:13 lr: 0.000064 loss: 0.3473 (0.3598) grad: 0.1681 (0.1906) time: 0.4975 data: 0.0033 max mem: 25051 +train: [15] [340/800] eta: 0:04:01 lr: 0.000064 loss: 0.3467 (0.3603) grad: 0.1639 (0.1873) time: 0.4860 data: 0.0032 max mem: 25051 +train: [15] [360/800] eta: 0:03:55 lr: 0.000063 loss: 0.3381 (0.3586) grad: 0.1639 (0.1886) time: 0.7084 data: 0.2159 max mem: 25051 +train: [15] [380/800] eta: 0:03:43 lr: 0.000063 loss: 0.3464 (0.3623) grad: 0.1384 (0.1863) time: 0.4858 data: 0.0032 max mem: 25051 +train: [15] [400/800] eta: 0:03:33 lr: 0.000062 loss: 0.3467 (0.3610) grad: 0.1179 (0.1828) time: 0.5332 data: 0.0024 max mem: 25051 +train: [15] [420/800] eta: 0:03:21 lr: 0.000061 loss: 0.3251 (0.3596) grad: 0.1427 (0.1839) time: 0.4951 data: 0.0036 max mem: 25051 +train: [15] [440/800] eta: 0:03:10 lr: 0.000061 loss: 0.3187 (0.3614) grad: 0.1394 (0.1817) time: 0.4908 data: 0.0034 max mem: 25051 +train: [15] [460/800] eta: 0:03:02 lr: 0.000060 loss: 0.3178 (0.3599) grad: 0.1427 (0.1824) time: 0.7145 data: 0.2280 max mem: 25051 +train: [15] [480/800] eta: 0:02:52 lr: 0.000059 loss: 0.3178 (0.3628) grad: 0.1603 (0.1825) time: 0.5438 data: 0.0462 max mem: 25051 +train: [15] [500/800] eta: 0:02:40 lr: 0.000059 loss: 0.3554 (0.3623) grad: 0.1394 (0.1818) time: 0.4826 data: 0.0027 max mem: 25051 +train: [15] [520/800] eta: 0:02:29 lr: 0.000058 loss: 0.3554 (0.3609) grad: 0.1363 (0.1811) time: 0.5133 data: 0.0033 max mem: 25051 +train: [15] [540/800] eta: 0:02:18 lr: 0.000057 loss: 0.3533 (0.3616) grad: 0.1351 (0.1803) time: 0.4906 data: 0.0030 max mem: 25051 +train: [15] [560/800] eta: 0:02:07 lr: 0.000057 loss: 0.3488 (0.3625) grad: 0.1152 (0.1791) time: 0.4980 data: 0.0031 max mem: 25051 +train: [15] [580/800] eta: 0:01:58 lr: 0.000056 loss: 0.3488 (0.3626) grad: 0.1080 (0.1769) time: 0.6752 data: 0.2090 max mem: 25051 +train: [15] [600/800] eta: 0:01:47 lr: 0.000056 loss: 0.3324 (0.3610) grad: 0.1080 (0.1762) time: 0.5029 data: 0.0032 max mem: 25051 +train: [15] [620/800] eta: 0:01:36 lr: 0.000055 loss: 0.3273 (0.3609) grad: 0.1360 (0.1789) time: 0.5186 data: 0.0031 max mem: 25051 +train: [15] [640/800] eta: 0:01:25 lr: 0.000054 loss: 0.3094 (0.3601) grad: 0.1530 (0.1808) time: 0.5039 data: 0.0034 max mem: 25051 +train: [15] [660/800] eta: 0:01:14 lr: 0.000054 loss: 0.3094 (0.3600) grad: 0.1799 (0.1815) time: 0.5015 data: 0.0030 max mem: 25051 +train: [15] [680/800] eta: 0:01:03 lr: 0.000053 loss: 0.3312 (0.3593) grad: 0.1937 (0.1818) time: 0.5039 data: 0.0033 max mem: 25051 +train: [15] [700/800] eta: 0:00:53 lr: 0.000053 loss: 0.3489 (0.3603) grad: 0.2064 (0.1818) time: 0.7584 data: 0.2935 max mem: 25051 +train: [15] [720/800] eta: 0:00:43 lr: 0.000052 loss: 0.3489 (0.3588) grad: 0.2045 (0.1832) time: 0.5563 data: 0.0221 max mem: 25051 +train: [15] [740/800] eta: 0:00:32 lr: 0.000051 loss: 0.3500 (0.3604) grad: 0.1947 (0.1825) time: 0.5321 data: 0.0028 max mem: 25051 +train: [15] [760/800] eta: 0:00:21 lr: 0.000051 loss: 0.3512 (0.3603) grad: 0.1939 (0.1821) time: 0.4914 data: 0.0034 max mem: 25051 +train: [15] [780/800] eta: 0:00:10 lr: 0.000050 loss: 0.3282 (0.3596) grad: 0.1640 (0.1810) time: 0.5450 data: 0.0036 max mem: 25051 +train: [15] [799/800] eta: 0:00:00 lr: 0.000050 loss: 0.3400 (0.3596) grad: 0.1362 (0.1807) time: 0.4792 data: 0.0033 max mem: 25051 +train: [15] Total time: 0:07:09 (0.5368 s / it) +train: [15] Summary: lr: 0.000050 loss: 0.3400 (0.3596) grad: 0.1362 (0.1807) +eval (validation): [15] [ 0/25] eta: 0:01:42 time: 4.0916 data: 3.7765 max mem: 25051 +eval (validation): [15] [20/25] eta: 0:00:03 time: 0.4415 data: 0.0557 max mem: 25051 +eval (validation): [15] [24/25] eta: 0:00:00 time: 0.3970 data: 0.0361 max mem: 25051 +eval (validation): [15] Total time: 0:00:14 (0.5799 s / it) +cv: [15] best hparam: (0.045, 1.0) (005) ('005_lr4.5e-02_wd1.0e+00') loss: 0.636 acc: 0.687 f1: 0.633 bacc: 0.634 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/ppmi_dx__patch__attn/checkpoint-last.pth +train: [16] [ 0/800] eta: 1:05:07 lr: nan time: 4.8844 data: 4.4401 max mem: 25051 +train: [16] [ 20/800] eta: 0:09:00 lr: 0.000049 loss: 0.3498 (0.3650) grad: 0.1325 (0.1408) time: 0.4837 data: 0.0024 max mem: 25051 +train: [16] [ 40/800] eta: 0:07:40 lr: 0.000048 loss: 0.3211 (0.3471) grad: 0.1325 (0.1411) time: 0.5155 data: 0.0257 max mem: 25051 +train: [16] [ 60/800] eta: 0:06:59 lr: 0.000048 loss: 0.3498 (0.3581) grad: 0.1325 (0.1359) time: 0.4839 data: 0.0018 max mem: 25051 +train: [16] [ 80/800] eta: 0:06:33 lr: 0.000047 loss: 0.3305 (0.3509) grad: 0.1217 (0.1411) time: 0.4885 data: 0.0025 max mem: 25051 +train: [16] [100/800] eta: 0:06:15 lr: 0.000047 loss: 0.3439 (0.3555) grad: 0.1441 (0.1526) time: 0.4919 data: 0.0030 max mem: 25051 +train: [16] [120/800] eta: 0:06:26 lr: 0.000046 loss: 0.3486 (0.3521) grad: 0.1441 (0.1556) time: 0.7285 data: 0.2118 max mem: 25051 +train: [16] [140/800] eta: 0:06:08 lr: 0.000046 loss: 0.3439 (0.3519) grad: 0.1619 (0.1603) time: 0.4999 data: 0.0038 max mem: 25051 +train: [16] [160/800] eta: 0:05:51 lr: 0.000045 loss: 0.3403 (0.3487) grad: 0.1690 (0.1637) time: 0.4878 data: 0.0030 max mem: 25051 +train: [16] [180/800] eta: 0:05:36 lr: 0.000045 loss: 0.3403 (0.3510) grad: 0.1619 (0.1657) time: 0.4845 data: 0.0033 max mem: 25051 +train: [16] [200/800] eta: 0:05:22 lr: 0.000044 loss: 0.3403 (0.3495) grad: 0.1690 (0.1669) time: 0.4917 data: 0.0033 max mem: 25051 +train: [16] [220/800] eta: 0:05:09 lr: 0.000043 loss: 0.3476 (0.3557) grad: 0.1779 (0.1719) time: 0.4898 data: 0.0030 max mem: 25051 +train: [16] [240/800] eta: 0:05:06 lr: 0.000043 loss: 0.3568 (0.3566) grad: 0.1389 (0.1667) time: 0.7145 data: 0.2439 max mem: 25051 +train: [16] [260/800] eta: 0:04:54 lr: 0.000042 loss: 0.3476 (0.3568) grad: 0.1389 (0.1637) time: 0.5041 data: 0.0021 max mem: 25051 +train: [16] [280/800] eta: 0:04:41 lr: 0.000042 loss: 0.3630 (0.3568) grad: 0.1389 (0.1631) time: 0.5067 data: 0.0032 max mem: 25051 +train: [16] [300/800] eta: 0:04:28 lr: 0.000041 loss: 0.3456 (0.3577) grad: 0.1382 (0.1647) time: 0.4695 data: 0.0033 max mem: 25051 +train: [16] [320/800] eta: 0:04:16 lr: 0.000041 loss: 0.3456 (0.3592) grad: 0.1367 (0.1621) time: 0.5049 data: 0.0031 max mem: 25051 +train: [16] [340/800] eta: 0:04:04 lr: 0.000040 loss: 0.3684 (0.3598) grad: 0.1367 (0.1652) time: 0.4849 data: 0.0031 max mem: 25051 +train: [16] [360/800] eta: 0:03:59 lr: 0.000040 loss: 0.3684 (0.3592) grad: 0.1279 (0.1641) time: 0.7325 data: 0.2212 max mem: 25051 +train: [16] [380/800] eta: 0:03:47 lr: 0.000039 loss: 0.3586 (0.3571) grad: 0.1246 (0.1633) time: 0.5011 data: 0.0035 max mem: 25051 +train: [16] [400/800] eta: 0:03:35 lr: 0.000039 loss: 0.3503 (0.3563) grad: 0.1295 (0.1632) time: 0.4907 data: 0.0022 max mem: 25051 +train: [16] [420/800] eta: 0:03:24 lr: 0.000038 loss: 0.3287 (0.3572) grad: 0.1295 (0.1629) time: 0.5060 data: 0.0033 max mem: 25051 +train: [16] [440/800] eta: 0:03:12 lr: 0.000038 loss: 0.3417 (0.3560) grad: 0.1395 (0.1620) time: 0.4695 data: 0.0030 max mem: 25051 +train: [16] [460/800] eta: 0:03:03 lr: 0.000037 loss: 0.3497 (0.3569) grad: 0.1421 (0.1650) time: 0.6800 data: 0.2091 max mem: 25051 +train: [16] [480/800] eta: 0:02:52 lr: 0.000036 loss: 0.3497 (0.3566) grad: 0.1519 (0.1656) time: 0.4778 data: 0.0024 max mem: 25051 +train: [16] [500/800] eta: 0:02:40 lr: 0.000036 loss: 0.3417 (0.3549) grad: 0.1509 (0.1643) time: 0.4940 data: 0.0026 max mem: 25051 +train: [16] [520/800] eta: 0:02:29 lr: 0.000035 loss: 0.3375 (0.3549) grad: 0.1399 (0.1631) time: 0.5167 data: 0.0030 max mem: 25051 +train: [16] [540/800] eta: 0:02:18 lr: 0.000035 loss: 0.3238 (0.3551) grad: 0.1321 (0.1659) time: 0.5051 data: 0.0031 max mem: 25051 +train: [16] [560/800] eta: 0:02:07 lr: 0.000034 loss: 0.3375 (0.3556) grad: 0.1298 (0.1656) time: 0.4872 data: 0.0029 max mem: 25051 +train: [16] [580/800] eta: 0:01:58 lr: 0.000034 loss: 0.3375 (0.3564) grad: 0.1321 (0.1661) time: 0.6746 data: 0.2077 max mem: 25051 +train: [16] [600/800] eta: 0:01:47 lr: 0.000033 loss: 0.3390 (0.3570) grad: 0.1869 (0.1676) time: 0.5021 data: 0.0141 max mem: 25051 +train: [16] [620/800] eta: 0:01:36 lr: 0.000033 loss: 0.3528 (0.3569) grad: 0.1931 (0.1691) time: 0.4987 data: 0.0026 max mem: 25051 +train: [16] [640/800] eta: 0:01:25 lr: 0.000032 loss: 0.3528 (0.3583) grad: 0.2168 (0.1698) time: 0.4738 data: 0.0033 max mem: 25051 +train: [16] [660/800] eta: 0:01:14 lr: 0.000032 loss: 0.3528 (0.3585) grad: 0.1931 (0.1685) time: 0.4903 data: 0.0035 max mem: 25051 +train: [16] [680/800] eta: 0:01:03 lr: 0.000031 loss: 0.3470 (0.3575) grad: 0.1743 (0.1698) time: 0.4786 data: 0.0033 max mem: 25051 +train: [16] [700/800] eta: 0:00:53 lr: 0.000031 loss: 0.3219 (0.3562) grad: 0.1646 (0.1697) time: 0.8024 data: 0.3341 max mem: 25051 +train: [16] [720/800] eta: 0:00:42 lr: 0.000031 loss: 0.3219 (0.3561) grad: 0.1646 (0.1699) time: 0.4843 data: 0.0018 max mem: 25051 +train: [16] [740/800] eta: 0:00:32 lr: 0.000030 loss: 0.3160 (0.3557) grad: 0.1646 (0.1693) time: 0.4968 data: 0.0052 max mem: 25051 +train: [16] [760/800] eta: 0:00:21 lr: 0.000030 loss: 0.3387 (0.3559) grad: 0.1419 (0.1696) time: 0.4823 data: 0.0019 max mem: 25051 +train: [16] [780/800] eta: 0:00:10 lr: 0.000029 loss: 0.3504 (0.3561) grad: 0.1557 (0.1703) time: 0.4964 data: 0.0037 max mem: 25051 +train: [16] [799/800] eta: 0:00:00 lr: 0.000029 loss: 0.3523 (0.3574) grad: 0.1577 (0.1736) time: 0.4758 data: 0.0035 max mem: 25051 +train: [16] Total time: 0:07:05 (0.5319 s / it) +train: [16] Summary: lr: 0.000029 loss: 0.3523 (0.3574) grad: 0.1577 (0.1736) +eval (validation): [16] [ 0/25] eta: 0:02:09 time: 5.2000 data: 4.9324 max mem: 25051 +eval (validation): [16] [20/25] eta: 0:00:03 time: 0.4121 data: 0.0125 max mem: 25051 +eval (validation): [16] [24/25] eta: 0:00:00 time: 0.4073 data: 0.0126 max mem: 25051 +eval (validation): [16] Total time: 0:00:15 (0.6003 s / it) +cv: [16] best hparam: (0.045, 1.0) (005) ('005_lr4.5e-02_wd1.0e+00') loss: 0.636 acc: 0.697 f1: 0.641 bacc: 0.642 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/ppmi_dx__patch__attn/checkpoint-last.pth +train: [17] [ 0/800] eta: 1:00:21 lr: nan time: 4.5268 data: 4.1115 max mem: 25051 +train: [17] [ 20/800] eta: 0:08:56 lr: 0.000028 loss: 0.2597 (0.2901) grad: 0.0940 (0.1160) time: 0.4956 data: 0.0028 max mem: 25051 +train: [17] [ 40/800] eta: 0:07:25 lr: 0.000028 loss: 0.3129 (0.3264) grad: 0.1065 (0.1452) time: 0.4808 data: 0.0022 max mem: 25051 +train: [17] [ 60/800] eta: 0:06:50 lr: 0.000027 loss: 0.3411 (0.3440) grad: 0.1671 (0.1583) time: 0.4872 data: 0.0032 max mem: 25051 +train: [17] [ 80/800] eta: 0:06:28 lr: 0.000027 loss: 0.3285 (0.3432) grad: 0.1671 (0.1622) time: 0.4967 data: 0.0034 max mem: 25051 +train: [17] [100/800] eta: 0:06:09 lr: 0.000026 loss: 0.3411 (0.3436) grad: 0.1689 (0.1646) time: 0.4797 data: 0.0029 max mem: 25051 +train: [17] [120/800] eta: 0:06:17 lr: 0.000026 loss: 0.3411 (0.3514) grad: 0.1799 (0.1677) time: 0.6929 data: 0.2030 max mem: 25051 +train: [17] [140/800] eta: 0:05:58 lr: 0.000026 loss: 0.3315 (0.3485) grad: 0.1689 (0.1678) time: 0.4680 data: 0.0043 max mem: 25051 +train: [17] [160/800] eta: 0:05:41 lr: 0.000025 loss: 0.3461 (0.3523) grad: 0.1689 (0.1706) time: 0.4740 data: 0.0026 max mem: 25051 +train: [17] [180/800] eta: 0:05:27 lr: 0.000025 loss: 0.3315 (0.3491) grad: 0.1730 (0.1685) time: 0.4810 data: 0.0030 max mem: 25051 +train: [17] [200/800] eta: 0:05:15 lr: 0.000024 loss: 0.3272 (0.3485) grad: 0.1689 (0.1730) time: 0.4989 data: 0.0039 max mem: 25051 +train: [17] [220/800] eta: 0:05:03 lr: 0.000024 loss: 0.3534 (0.3540) grad: 0.1395 (0.1681) time: 0.5024 data: 0.0028 max mem: 25051 +train: [17] [240/800] eta: 0:05:01 lr: 0.000023 loss: 0.3528 (0.3550) grad: 0.1298 (0.1659) time: 0.6985 data: 0.2137 max mem: 25051 +train: [17] [260/800] eta: 0:04:48 lr: 0.000023 loss: 0.3534 (0.3548) grad: 0.1073 (0.1617) time: 0.4865 data: 0.0041 max mem: 25051 +train: [17] [280/800] eta: 0:04:37 lr: 0.000023 loss: 0.3528 (0.3527) grad: 0.1073 (0.1588) time: 0.5325 data: 0.0026 max mem: 25051 +train: [17] [300/800] eta: 0:04:25 lr: 0.000022 loss: 0.3335 (0.3492) grad: 0.1231 (0.1610) time: 0.4903 data: 0.0033 max mem: 25051 +train: [17] [320/800] eta: 0:04:13 lr: 0.000022 loss: 0.3335 (0.3507) grad: 0.1176 (0.1579) time: 0.4995 data: 0.0030 max mem: 25051 +train: [17] [340/800] eta: 0:04:01 lr: 0.000021 loss: 0.3176 (0.3511) grad: 0.1397 (0.1566) time: 0.4718 data: 0.0033 max mem: 25051 +train: [17] [360/800] eta: 0:03:55 lr: 0.000021 loss: 0.3196 (0.3505) grad: 0.1464 (0.1595) time: 0.6870 data: 0.2120 max mem: 25051 +train: [17] [380/800] eta: 0:03:43 lr: 0.000021 loss: 0.3279 (0.3500) grad: 0.1464 (0.1616) time: 0.4800 data: 0.0027 max mem: 25051 +train: [17] [400/800] eta: 0:03:32 lr: 0.000020 loss: 0.3279 (0.3487) grad: 0.1630 (0.1636) time: 0.5133 data: 0.0034 max mem: 25051 +train: [17] [420/800] eta: 0:03:21 lr: 0.000020 loss: 0.3312 (0.3509) grad: 0.1797 (0.1626) time: 0.5423 data: 0.0033 max mem: 25051 +train: [17] [440/800] eta: 0:03:10 lr: 0.000019 loss: 0.3349 (0.3515) grad: 0.1830 (0.1658) time: 0.4885 data: 0.0034 max mem: 25051 +train: [17] [460/800] eta: 0:03:03 lr: 0.000019 loss: 0.3309 (0.3508) grad: 0.1830 (0.1666) time: 0.7669 data: 0.2687 max mem: 25051 +train: [17] [480/800] eta: 0:02:52 lr: 0.000019 loss: 0.3312 (0.3518) grad: 0.1830 (0.1680) time: 0.4914 data: 0.0033 max mem: 25051 +train: [17] [500/800] eta: 0:02:40 lr: 0.000018 loss: 0.3160 (0.3507) grad: 0.1967 (0.1683) time: 0.4775 data: 0.0029 max mem: 25051 +train: [17] [520/800] eta: 0:02:29 lr: 0.000018 loss: 0.3170 (0.3519) grad: 0.1967 (0.1723) time: 0.4984 data: 0.0037 max mem: 25051 +train: [17] [540/800] eta: 0:02:18 lr: 0.000017 loss: 0.3170 (0.3518) grad: 0.2014 (0.1755) time: 0.4860 data: 0.0037 max mem: 25051 +train: [17] [560/800] eta: 0:02:07 lr: 0.000017 loss: 0.3223 (0.3514) grad: 0.1887 (0.1742) time: 0.4835 data: 0.0036 max mem: 25051 +train: [17] [580/800] eta: 0:01:57 lr: 0.000017 loss: 0.3228 (0.3501) grad: 0.1887 (0.1749) time: 0.6760 data: 0.2140 max mem: 25051 +train: [17] [600/800] eta: 0:01:47 lr: 0.000016 loss: 0.3277 (0.3494) grad: 0.1887 (0.1756) time: 0.5273 data: 0.0195 max mem: 25051 +train: [17] [620/800] eta: 0:01:36 lr: 0.000016 loss: 0.3427 (0.3513) grad: 0.1514 (0.1767) time: 0.4826 data: 0.0026 max mem: 25051 +train: [17] [640/800] eta: 0:01:25 lr: 0.000016 loss: 0.3548 (0.3532) grad: 0.1914 (0.1785) time: 0.5053 data: 0.0031 max mem: 25051 +train: [17] [660/800] eta: 0:01:14 lr: 0.000015 loss: 0.3835 (0.3557) grad: 0.1878 (0.1779) time: 0.4943 data: 0.0033 max mem: 25051 +train: [17] [680/800] eta: 0:01:03 lr: 0.000015 loss: 0.3841 (0.3547) grad: 0.1867 (0.1772) time: 0.4921 data: 0.0027 max mem: 25051 +train: [17] [700/800] eta: 0:00:53 lr: 0.000015 loss: 0.4098 (0.3574) grad: 0.1523 (0.1764) time: 0.7619 data: 0.2156 max mem: 25051 +train: [17] [720/800] eta: 0:00:42 lr: 0.000014 loss: 0.3743 (0.3573) grad: 0.1506 (0.1768) time: 0.4979 data: 0.0025 max mem: 25051 +train: [17] [740/800] eta: 0:00:32 lr: 0.000014 loss: 0.3401 (0.3586) grad: 0.1453 (0.1758) time: 0.4756 data: 0.0030 max mem: 25051 +train: [17] [760/800] eta: 0:00:21 lr: 0.000014 loss: 0.3401 (0.3576) grad: 0.1418 (0.1738) time: 0.4910 data: 0.0030 max mem: 25051 +train: [17] [780/800] eta: 0:00:10 lr: 0.000013 loss: 0.3320 (0.3574) grad: 0.1253 (0.1731) time: 0.4682 data: 0.0030 max mem: 25051 +train: [17] [799/800] eta: 0:00:00 lr: 0.000013 loss: 0.3464 (0.3583) grad: 0.1196 (0.1716) time: 0.4543 data: 0.0026 max mem: 25051 +train: [17] Total time: 0:07:03 (0.5298 s / it) +train: [17] Summary: lr: 0.000013 loss: 0.3464 (0.3583) grad: 0.1196 (0.1716) +eval (validation): [17] [ 0/25] eta: 0:01:42 time: 4.1051 data: 3.7907 max mem: 25051 +eval (validation): [17] [20/25] eta: 0:00:02 time: 0.3717 data: 0.0029 max mem: 25051 +eval (validation): [17] [24/25] eta: 0:00:00 time: 0.3651 data: 0.0022 max mem: 25051 +eval (validation): [17] Total time: 0:00:13 (0.5258 s / it) +cv: [17] best hparam: (0.045, 1.0) (005) ('005_lr4.5e-02_wd1.0e+00') loss: 0.636 acc: 0.697 f1: 0.641 bacc: 0.642 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/ppmi_dx__patch__attn/checkpoint-last.pth +train: [18] [ 0/800] eta: 0:55:09 lr: nan time: 4.1366 data: 3.7310 max mem: 25051 +train: [18] [ 20/800] eta: 0:08:32 lr: 0.000013 loss: 0.3425 (0.3761) grad: 0.1329 (0.1489) time: 0.4835 data: 0.0033 max mem: 25051 +train: [18] [ 40/800] eta: 0:07:18 lr: 0.000012 loss: 0.3425 (0.3626) grad: 0.1209 (0.1612) time: 0.4914 data: 0.0028 max mem: 25051 +train: [18] [ 60/800] eta: 0:06:45 lr: 0.000012 loss: 0.3620 (0.3714) grad: 0.1329 (0.1620) time: 0.4884 data: 0.0032 max mem: 25051 +train: [18] [ 80/800] eta: 0:06:24 lr: 0.000012 loss: 0.3620 (0.3669) grad: 0.1437 (0.1642) time: 0.4906 data: 0.0033 max mem: 25051 +train: [18] [100/800] eta: 0:06:05 lr: 0.000011 loss: 0.3550 (0.3515) grad: 0.1437 (0.1594) time: 0.4786 data: 0.0028 max mem: 25051 +train: [18] [120/800] eta: 0:06:16 lr: 0.000011 loss: 0.3376 (0.3466) grad: 0.1474 (0.1704) time: 0.7076 data: 0.2179 max mem: 25051 +train: [18] [140/800] eta: 0:06:01 lr: 0.000011 loss: 0.3268 (0.3503) grad: 0.1665 (0.1754) time: 0.5187 data: 0.0033 max mem: 25051 +train: [18] [160/800] eta: 0:05:45 lr: 0.000011 loss: 0.3260 (0.3587) grad: 0.1665 (0.1745) time: 0.4842 data: 0.0035 max mem: 25051 +train: [18] [180/800] eta: 0:05:31 lr: 0.000010 loss: 0.3300 (0.3574) grad: 0.1687 (0.1729) time: 0.4921 data: 0.0034 max mem: 25051 +train: [18] [200/800] eta: 0:05:18 lr: 0.000010 loss: 0.3300 (0.3550) grad: 0.1384 (0.1689) time: 0.4907 data: 0.0034 max mem: 25051 +train: [18] [220/800] eta: 0:05:05 lr: 0.000010 loss: 0.3300 (0.3552) grad: 0.1384 (0.1687) time: 0.4882 data: 0.0034 max mem: 25051 +train: [18] [240/800] eta: 0:05:03 lr: 0.000009 loss: 0.3645 (0.3611) grad: 0.1434 (0.1679) time: 0.7135 data: 0.2160 max mem: 25051 +train: [18] [260/800] eta: 0:04:50 lr: 0.000009 loss: 0.3932 (0.3611) grad: 0.1448 (0.1689) time: 0.4752 data: 0.0025 max mem: 25051 +train: [18] [280/800] eta: 0:04:37 lr: 0.000009 loss: 0.3932 (0.3627) grad: 0.1526 (0.1706) time: 0.4791 data: 0.0030 max mem: 25051 +train: [18] [300/800] eta: 0:04:24 lr: 0.000009 loss: 0.3576 (0.3630) grad: 0.1448 (0.1694) time: 0.4784 data: 0.0027 max mem: 25051 +train: [18] [320/800] eta: 0:04:12 lr: 0.000008 loss: 0.3576 (0.3667) grad: 0.1448 (0.1714) time: 0.4754 data: 0.0032 max mem: 25051 +train: [18] [340/800] eta: 0:04:00 lr: 0.000008 loss: 0.3835 (0.3679) grad: 0.1447 (0.1721) time: 0.4671 data: 0.0030 max mem: 25051 +train: [18] [360/800] eta: 0:03:53 lr: 0.000008 loss: 0.3576 (0.3654) grad: 0.1429 (0.1725) time: 0.6701 data: 0.2077 max mem: 25051 +train: [18] [380/800] eta: 0:03:41 lr: 0.000008 loss: 0.3509 (0.3638) grad: 0.1448 (0.1751) time: 0.4850 data: 0.0030 max mem: 25051 +train: [18] [400/800] eta: 0:03:30 lr: 0.000007 loss: 0.3492 (0.3650) grad: 0.1541 (0.1759) time: 0.5115 data: 0.0028 max mem: 25051 +train: [18] [420/800] eta: 0:03:19 lr: 0.000007 loss: 0.3388 (0.3653) grad: 0.1692 (0.1781) time: 0.4809 data: 0.0033 max mem: 25051 +train: [18] [440/800] eta: 0:03:08 lr: 0.000007 loss: 0.3494 (0.3662) grad: 0.1806 (0.1775) time: 0.4752 data: 0.0029 max mem: 25051 +train: [18] [460/800] eta: 0:02:59 lr: 0.000007 loss: 0.3494 (0.3648) grad: 0.1243 (0.1756) time: 0.6697 data: 0.2140 max mem: 25051 +train: [18] [480/800] eta: 0:02:48 lr: 0.000006 loss: 0.3544 (0.3663) grad: 0.1189 (0.1771) time: 0.4740 data: 0.0037 max mem: 25051 +train: [18] [500/800] eta: 0:02:37 lr: 0.000006 loss: 0.3544 (0.3651) grad: 0.1173 (0.1754) time: 0.4655 data: 0.0033 max mem: 25051 +train: [18] [520/800] eta: 0:02:26 lr: 0.000006 loss: 0.3315 (0.3653) grad: 0.1172 (0.1728) time: 0.4972 data: 0.0022 max mem: 25051 +train: [18] [540/800] eta: 0:02:15 lr: 0.000006 loss: 0.3625 (0.3660) grad: 0.1184 (0.1723) time: 0.4922 data: 0.0033 max mem: 25051 +train: [18] [560/800] eta: 0:02:05 lr: 0.000006 loss: 0.3458 (0.3652) grad: 0.1207 (0.1724) time: 0.4820 data: 0.0033 max mem: 25051 +train: [18] [580/800] eta: 0:01:56 lr: 0.000005 loss: 0.3533 (0.3649) grad: 0.1289 (0.1715) time: 0.7136 data: 0.2357 max mem: 25051 +train: [18] [600/800] eta: 0:01:45 lr: 0.000005 loss: 0.3412 (0.3639) grad: 0.1403 (0.1700) time: 0.4775 data: 0.0034 max mem: 25051 +train: [18] [620/800] eta: 0:01:34 lr: 0.000005 loss: 0.3349 (0.3635) grad: 0.1382 (0.1690) time: 0.5215 data: 0.0026 max mem: 25051 +train: [18] [640/800] eta: 0:01:23 lr: 0.000005 loss: 0.3349 (0.3633) grad: 0.1382 (0.1694) time: 0.4791 data: 0.0031 max mem: 25051 +train: [18] [660/800] eta: 0:01:13 lr: 0.000005 loss: 0.3412 (0.3669) grad: 0.1355 (0.1694) time: 0.4777 data: 0.0033 max mem: 25051 +train: [18] [680/800] eta: 0:01:02 lr: 0.000004 loss: 0.3466 (0.3655) grad: 0.1360 (0.1699) time: 0.4917 data: 0.0034 max mem: 25051 +train: [18] [700/800] eta: 0:00:52 lr: 0.000004 loss: 0.3832 (0.3655) grad: 0.1455 (0.1699) time: 0.6782 data: 0.2055 max mem: 25051 +train: [18] [720/800] eta: 0:00:42 lr: 0.000004 loss: 0.3861 (0.3665) grad: 0.1455 (0.1688) time: 0.4833 data: 0.0028 max mem: 25051 +train: [18] [740/800] eta: 0:00:31 lr: 0.000004 loss: 0.3681 (0.3661) grad: 0.1492 (0.1685) time: 0.4876 data: 0.0028 max mem: 25051 +train: [18] [760/800] eta: 0:00:20 lr: 0.000004 loss: 0.3693 (0.3660) grad: 0.1601 (0.1685) time: 0.4821 data: 0.0033 max mem: 25051 +train: [18] [780/800] eta: 0:00:10 lr: 0.000003 loss: 0.3693 (0.3668) grad: 0.1582 (0.1694) time: 0.4926 data: 0.0034 max mem: 25051 +train: [18] [799/800] eta: 0:00:00 lr: 0.000003 loss: 0.3645 (0.3667) grad: 0.1637 (0.1692) time: 0.4776 data: 0.0028 max mem: 25051 +train: [18] Total time: 0:06:57 (0.5215 s / it) +train: [18] Summary: lr: 0.000003 loss: 0.3645 (0.3667) grad: 0.1637 (0.1692) +eval (validation): [18] [ 0/25] eta: 0:01:44 time: 4.1758 data: 3.8685 max mem: 25051 +eval (validation): [18] [20/25] eta: 0:00:03 time: 0.4510 data: 0.0660 max mem: 25051 +eval (validation): [18] [24/25] eta: 0:00:00 time: 0.4468 data: 0.0654 max mem: 25051 +eval (validation): [18] Total time: 0:00:14 (0.5898 s / it) +cv: [18] best hparam: (0.045, 1.0) (005) ('005_lr4.5e-02_wd1.0e+00') loss: 0.636 acc: 0.697 f1: 0.641 bacc: 0.642 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/ppmi_dx__patch__attn/checkpoint-last.pth +train: [19] [ 0/800] eta: 0:56:18 lr: nan time: 4.2234 data: 3.8283 max mem: 25051 +train: [19] [ 20/800] eta: 0:08:42 lr: 0.000003 loss: 0.3442 (0.3245) grad: 0.1286 (0.1704) time: 0.4923 data: 0.0027 max mem: 25051 +train: [19] [ 40/800] eta: 0:07:23 lr: 0.000003 loss: 0.3327 (0.3259) grad: 0.1286 (0.1797) time: 0.4929 data: 0.0027 max mem: 25051 +train: [19] [ 60/800] eta: 0:06:48 lr: 0.000003 loss: 0.3442 (0.3504) grad: 0.1286 (0.1639) time: 0.4866 data: 0.0029 max mem: 25051 +train: [19] [ 80/800] eta: 0:06:26 lr: 0.000003 loss: 0.3442 (0.3563) grad: 0.1112 (0.1550) time: 0.4910 data: 0.0032 max mem: 25051 +train: [19] [100/800] eta: 0:06:09 lr: 0.000003 loss: 0.3448 (0.3629) grad: 0.1343 (0.1657) time: 0.4920 data: 0.0032 max mem: 25051 +train: [19] [120/800] eta: 0:06:20 lr: 0.000002 loss: 0.3723 (0.3662) grad: 0.1107 (0.1543) time: 0.7183 data: 0.2135 max mem: 25051 +train: [19] [140/800] eta: 0:06:04 lr: 0.000002 loss: 0.3586 (0.3628) grad: 0.1364 (0.1549) time: 0.5042 data: 0.0037 max mem: 25051 +train: [19] [160/800] eta: 0:05:47 lr: 0.000002 loss: 0.3723 (0.3663) grad: 0.1364 (0.1524) time: 0.4861 data: 0.0034 max mem: 25051 +train: [19] [180/800] eta: 0:05:31 lr: 0.000002 loss: 0.3104 (0.3627) grad: 0.1217 (0.1551) time: 0.4683 data: 0.0029 max mem: 25051 +train: [19] [200/800] eta: 0:05:16 lr: 0.000002 loss: 0.3104 (0.3621) grad: 0.1364 (0.1533) time: 0.4661 data: 0.0029 max mem: 25051 +train: [19] [220/800] eta: 0:05:03 lr: 0.000002 loss: 0.3187 (0.3666) grad: 0.1350 (0.1613) time: 0.4653 data: 0.0027 max mem: 25051 +train: [19] [240/800] eta: 0:05:00 lr: 0.000002 loss: 0.3625 (0.3659) grad: 0.1350 (0.1591) time: 0.6845 data: 0.2060 max mem: 25051 +train: [19] [260/800] eta: 0:04:47 lr: 0.000001 loss: 0.3493 (0.3619) grad: 0.1297 (0.1606) time: 0.4955 data: 0.0042 max mem: 25051 +train: [19] [280/800] eta: 0:04:35 lr: 0.000001 loss: 0.3475 (0.3626) grad: 0.1382 (0.1621) time: 0.4793 data: 0.0028 max mem: 25051 +train: [19] [300/800] eta: 0:04:22 lr: 0.000001 loss: 0.3475 (0.3639) grad: 0.1237 (0.1625) time: 0.4701 data: 0.0016 max mem: 25051 +train: [19] [320/800] eta: 0:04:10 lr: 0.000001 loss: 0.3380 (0.3646) grad: 0.1547 (0.1629) time: 0.4753 data: 0.0027 max mem: 25051 +train: [19] [340/800] eta: 0:03:58 lr: 0.000001 loss: 0.3433 (0.3653) grad: 0.1705 (0.1631) time: 0.4764 data: 0.0031 max mem: 25051 +train: [19] [360/800] eta: 0:03:52 lr: 0.000001 loss: 0.3433 (0.3633) grad: 0.1696 (0.1641) time: 0.6770 data: 0.2018 max mem: 25051 +train: [19] [380/800] eta: 0:03:41 lr: 0.000001 loss: 0.3321 (0.3609) grad: 0.1728 (0.1668) time: 0.4917 data: 0.0033 max mem: 25051 +train: [19] [400/800] eta: 0:03:29 lr: 0.000001 loss: 0.3321 (0.3638) grad: 0.1728 (0.1684) time: 0.4940 data: 0.0022 max mem: 25051 +train: [19] [420/800] eta: 0:03:18 lr: 0.000001 loss: 0.3217 (0.3629) grad: 0.1728 (0.1715) time: 0.4793 data: 0.0032 max mem: 25051 +train: [19] [440/800] eta: 0:03:07 lr: 0.000001 loss: 0.3356 (0.3631) grad: 0.1712 (0.1713) time: 0.5049 data: 0.0032 max mem: 25051 +train: [19] [460/800] eta: 0:02:59 lr: 0.000001 loss: 0.3507 (0.3622) grad: 0.1563 (0.1716) time: 0.6673 data: 0.2074 max mem: 25051 +train: [19] [480/800] eta: 0:02:48 lr: 0.000001 loss: 0.3331 (0.3608) grad: 0.1563 (0.1737) time: 0.4881 data: 0.0029 max mem: 25051 +train: [19] [500/800] eta: 0:02:37 lr: 0.000000 loss: 0.3331 (0.3589) grad: 0.1400 (0.1739) time: 0.4879 data: 0.0031 max mem: 25051 +train: [19] [520/800] eta: 0:02:26 lr: 0.000000 loss: 0.3337 (0.3605) grad: 0.1372 (0.1725) time: 0.4890 data: 0.0024 max mem: 25051 +train: [19] [540/800] eta: 0:02:15 lr: 0.000000 loss: 0.3471 (0.3619) grad: 0.1372 (0.1739) time: 0.5009 data: 0.0034 max mem: 25051 +train: [19] [560/800] eta: 0:02:05 lr: 0.000000 loss: 0.3716 (0.3621) grad: 0.1356 (0.1722) time: 0.4919 data: 0.0035 max mem: 25051 +train: [19] [580/800] eta: 0:01:56 lr: 0.000000 loss: 0.3583 (0.3599) grad: 0.1356 (0.1704) time: 0.7171 data: 0.2118 max mem: 25051 +train: [19] [600/800] eta: 0:01:45 lr: 0.000000 loss: 0.3679 (0.3617) grad: 0.1369 (0.1720) time: 0.5275 data: 0.0031 max mem: 25051 +train: [19] [620/800] eta: 0:01:34 lr: 0.000000 loss: 0.3287 (0.3607) grad: 0.1372 (0.1721) time: 0.4906 data: 0.0032 max mem: 25051 +train: [19] [640/800] eta: 0:01:24 lr: 0.000000 loss: 0.3125 (0.3587) grad: 0.1382 (0.1724) time: 0.4819 data: 0.0032 max mem: 25051 +train: [19] [660/800] eta: 0:01:13 lr: 0.000000 loss: 0.3287 (0.3594) grad: 0.1728 (0.1727) time: 0.4616 data: 0.0031 max mem: 25051 +train: [19] [680/800] eta: 0:01:02 lr: 0.000000 loss: 0.3116 (0.3592) grad: 0.1580 (0.1739) time: 0.5080 data: 0.0033 max mem: 25051 +train: [19] [700/800] eta: 0:00:52 lr: 0.000000 loss: 0.3138 (0.3592) grad: 0.1664 (0.1762) time: 0.6618 data: 0.1992 max mem: 25051 +train: [19] [720/800] eta: 0:00:42 lr: 0.000000 loss: 0.3278 (0.3583) grad: 0.1664 (0.1757) time: 0.4866 data: 0.0023 max mem: 25051 +train: [19] [740/800] eta: 0:00:31 lr: 0.000000 loss: 0.3278 (0.3570) grad: 0.1664 (0.1760) time: 0.4849 data: 0.0032 max mem: 25051 +train: [19] [760/800] eta: 0:00:20 lr: 0.000000 loss: 0.3278 (0.3568) grad: 0.1748 (0.1754) time: 0.4713 data: 0.0033 max mem: 25051 +train: [19] [780/800] eta: 0:00:10 lr: 0.000000 loss: 0.3438 (0.3592) grad: 0.1530 (0.1758) time: 0.4624 data: 0.0029 max mem: 25051 +train: [19] [799/800] eta: 0:00:00 lr: 0.000000 loss: 0.3093 (0.3572) grad: 0.1482 (0.1750) time: 0.4636 data: 0.0028 max mem: 25051 +train: [19] Total time: 0:06:56 (0.5208 s / it) +train: [19] Summary: lr: 0.000000 loss: 0.3093 (0.3572) grad: 0.1482 (0.1750) +eval (validation): [19] [ 0/25] eta: 0:01:36 time: 3.8476 data: 3.5850 max mem: 25051 +eval (validation): [19] [20/25] eta: 0:00:03 time: 0.4508 data: 0.0553 max mem: 25051 +eval (validation): [19] [24/25] eta: 0:00:00 time: 0.4452 data: 0.0546 max mem: 25051 +eval (validation): [19] Total time: 0:00:14 (0.5778 s / it) +cv: [19] best hparam: (0.045, 1.0) (005) ('005_lr4.5e-02_wd1.0e+00') loss: 0.636 acc: 0.697 f1: 0.641 bacc: 0.642 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/ppmi_dx__patch__attn/checkpoint-last.pth +evaluating last checkpoint: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/ppmi_dx__patch__attn/checkpoint-last.pth +eval model info: +{"score": 0.6423076923076924, "hparam": [0.045, 1.0], "hparam_id": 5, "epoch": 19, "is_best": false, "best_score": 0.6743589743589744} +eval (train): [20] [ 0/116] eta: 0:08:18 time: 4.2931 data: 3.9706 max mem: 25051 +eval (train): [20] [ 20/116] eta: 0:01:06 time: 0.5154 data: 0.0574 max mem: 25051 +eval (train): [20] [ 40/116] eta: 0:00:41 time: 0.3997 data: 0.0263 max mem: 25051 +eval (train): [20] [ 60/116] eta: 0:00:30 time: 0.5215 data: 0.1539 max mem: 25051 +eval (train): [20] [ 80/116] eta: 0:00:19 time: 0.5129 data: 0.0667 max mem: 25051 +eval (train): [20] [100/116] eta: 0:00:08 time: 0.5024 data: 0.0475 max mem: 25051 +eval (train): [20] [115/116] eta: 0:00:00 time: 0.4000 data: 0.0284 max mem: 25051 +eval (train): [20] Total time: 0:00:59 (0.5099 s / it) +eval (validation): [20] [ 0/25] eta: 0:01:41 time: 4.0730 data: 3.8147 max mem: 25051 +eval (validation): [20] [20/25] eta: 0:00:03 time: 0.4887 data: 0.1072 max mem: 25051 +eval (validation): [20] [24/25] eta: 0:00:00 time: 0.4576 data: 0.0833 max mem: 25051 +eval (validation): [20] Total time: 0:00:15 (0.6157 s / it) +eval (test): [20] [ 0/25] eta: 0:01:49 time: 4.3935 data: 4.0885 max mem: 25051 +eval (test): [20] [20/25] eta: 0:00:03 time: 0.4545 data: 0.0027 max mem: 25051 +eval (test): [20] [24/25] eta: 0:00:00 time: 0.4311 data: 0.0030 max mem: 25051 +eval (test): [20] Total time: 0:00:15 (0.6042 s / it) +evaluating best checkpoint: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/ppmi_dx__patch__attn/checkpoint-best.pth +eval model info: +{"score": 0.6743589743589744, "hparam": [0.44, 1.0], "hparam_id": 19, "epoch": 10, "is_best": true, "best_score": 0.6743589743589744} +eval (train): [20] [ 0/116] eta: 0:08:10 time: 4.2326 data: 3.9196 max mem: 25051 +eval (train): [20] [ 20/116] eta: 0:01:11 time: 0.5696 data: 0.1942 max mem: 25051 +eval (train): [20] [ 40/116] eta: 0:00:49 time: 0.5641 data: 0.1091 max mem: 25051 +eval (train): [20] [ 60/116] eta: 0:00:32 time: 0.4224 data: 0.0026 max mem: 25051 +eval (train): [20] [ 80/116] eta: 0:00:19 time: 0.4353 data: 0.0179 max mem: 25051 +eval (train): [20] [100/116] eta: 0:00:08 time: 0.4822 data: 0.0036 max mem: 25051 +eval (train): [20] [115/116] eta: 0:00:00 time: 0.3942 data: 0.0027 max mem: 25051 +eval (train): [20] Total time: 0:00:59 (0.5113 s / it) +eval (validation): [20] [ 0/25] eta: 0:01:45 time: 4.2091 data: 3.8886 max mem: 25051 +eval (validation): [20] [20/25] eta: 0:00:03 time: 0.4853 data: 0.0415 max mem: 25051 +eval (validation): [20] [24/25] eta: 0:00:00 time: 0.4548 data: 0.0404 max mem: 25051 +eval (validation): [20] Total time: 0:00:15 (0.6155 s / it) +eval (test): [20] [ 0/25] eta: 0:01:46 time: 4.2525 data: 3.9302 max mem: 25051 +eval (test): [20] [20/25] eta: 0:00:03 time: 0.4968 data: 0.0777 max mem: 25051 +eval (test): [20] [24/25] eta: 0:00:00 time: 0.4871 data: 0.0880 max mem: 25051 +eval (test): [20] Total time: 0:00:15 (0.6384 s / it) +eval results: + +| model | repr | clf | dataset | ckpt | epoch | lr | wd | hparam_id | hparam | split | loss | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:------|:----------|:-------|--------:|---------:|-----:|------------:|:------------|:-----------|--------:|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | attn | ppmi_dx | best | 10 | 0.000132 | 0.05 | 19 | [0.44, 1.0] | train | 0.47212 | 0.77754 | 0.019702 | 0.76665 | 0.020404 | 0.76868 | 0.020513 | +| flat_mae | patch | attn | ppmi_dx | best | 10 | 0.000132 | 0.05 | 19 | [0.44, 1.0] | validation | 0.66907 | 0.68687 | 0.046748 | 0.67355 | 0.048687 | 0.67436 | 0.048965 | +| flat_mae | patch | attn | ppmi_dx | best | 10 | 0.000132 | 0.05 | 19 | [0.44, 1.0] | test | 0.67943 | 0.59 | 0.044957 | 0.53989 | 0.049363 | 0.54076 | 0.047017 | + + +done! total time: 2:32:51 diff --git a/input_space_v3/flat_lr1e-3_1/eval_v2/ppmi_dx__patch__attn/train_log.json b/input_space_v3/flat_lr1e-3_1/eval_v2/ppmi_dx__patch__attn/train_log.json new file mode 100644 index 0000000000000000000000000000000000000000..66dd4cfaa61c2a3e03b69b5f66a0ca9be73f8e74 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_1/eval_v2/ppmi_dx__patch__attn/train_log.json @@ -0,0 +1,20 @@ +{"epoch": 0, "train/lr": 2.987987987987988e-05, "train/loss": 0.6615462745726108, "train/grad": 0.29226288065314293, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.691630859375, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.6898583984375, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.6873974609375, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.6852880859375, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.68338623046875, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.681279296875, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.67921630859375, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.67747314453125, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.67556640625, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.67402099609375, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.67277587890625, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.671357421875, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.6702783203125, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.6690185546875, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.6681103515625, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.667509765625, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.6667529296875, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.66592041015625, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.66498779296875, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.66420654296875, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.66306884765625, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.6617578125, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.66013427734375, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.658543701171875, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.65728271484375, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.656556396484375, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.656236572265625, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.65607666015625, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.655504150390625, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.65412353515625, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.6524169921875, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.65066650390625, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.648238525390625, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.6463037109375, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.646656494140625, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.6492108154296875, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.65164794921875, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.6523696899414062, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.6526950073242187, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.6527813720703125, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.651593017578125, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.6504293823242188, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.6484439086914062, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.6466622924804688, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.6431423950195313, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.6391412353515625, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.6396255493164062, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.6472479248046875, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.661175537109375, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.04731854454148561, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.046707240254618226, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.04582242048811167, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.04505766786169261, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.044397282167337834, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.04362131767440587, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.04288937265984714, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.042223549894988534, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.04151042383164168, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.040901440395973626, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.04041257440112531, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.039814240438863634, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.03935454953461885, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.03883290609810501, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.03845935911405832, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.03818049749359489, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.03789895039983094, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.03765459684189409, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.037427948224358264, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.037251678039319815, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.03705033821053803, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.0368618837557733, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.03669177576433867, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.036574918366968634, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.036536758309230206, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.036588861369527874, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.036747789676301185, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.03694467429071665, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.037173660146072506, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.03733937853947282, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.03756400185637176, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.03785054745618254, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.038057831530459225, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.037850139979273084, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.03762815547408536, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.03803909828420728, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.03839104861021042, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0385608105477877, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.03870891067199409, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.03873608626890927, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.03871158331632614, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.03857581364922225, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.038017289210110904, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.03765873382799327, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.03709972267504782, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.03620565878693014, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.03508784515317529, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.035423948341049255, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.03721789238974452, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.6738080978393555, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.671878457069397, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.6696590781211853, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.6682113409042358, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.6672553420066833, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.6664658188819885, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.6660290360450745, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.6656841039657593, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.6653636693954468, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.6649516820907593, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.6643965840339661, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.6637125015258789, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.6629814505577087, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.66201251745224, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.6611518263816833, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.6603327989578247, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.6592078804969788, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.6582088470458984, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.656974732875824, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.6560014486312866, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.6549329161643982, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.6539521813392639, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.6530249118804932, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.6523644328117371, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.6519894003868103, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.6507757306098938, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.6490849852561951, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.6478717923164368, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.646367073059082, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.6431996822357178, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.6457489728927612, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.6561895608901978, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.6798125505447388, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.6993505358695984, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.7183564305305481, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.7589700222015381, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.7976081967353821, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.7944291830062866, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.757286787033081, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.7009417414665222, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.6574180722236633, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.6403964161872864, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.6898728013038635, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.7344881296157837, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.7179641127586365, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.7050555944442749, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.6946465969085693, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.6851619482040405, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.6972098350524902, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.6060606060606061, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.6060606060606061, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.6060606060606061, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.6060606060606061, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.6060606060606061, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.6060606060606061, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.6060606060606061, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.6060606060606061, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.6060606060606061, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.6060606060606061, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.6060606060606061, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.6060606060606061, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.6060606060606061, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.6060606060606061, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.6060606060606061, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.6060606060606061, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.6060606060606061, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.6060606060606061, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.6060606060606061, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.6060606060606061, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.6161616161616161, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.6161616161616161, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.5959595959595959, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.5858585858585859, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.6161616161616161, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.6363636363636364, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.6363636363636364, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.6464646464646465, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.6464646464646465, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.6060606060606061, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.5858585858585859, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.6161616161616161, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.6161616161616161, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.6060606060606061, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.6060606060606061, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.6060606060606061, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.6060606060606061, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.6060606060606061, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.6060606060606061, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.6161616161616161, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.6161616161616161, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.696969696969697, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.5656565656565656, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.5353535353535354, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.5454545454545454, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.5959595959595959, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.696969696969697, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.6565656565656566, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.6363636363636364, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.37735849056603776, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.37735849056603776, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.37735849056603776, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.37735849056603776, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.37735849056603776, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.37735849056603776, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.37735849056603776, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.37735849056603776, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.37735849056603776, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.37735849056603776, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.37735849056603776, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.37735849056603776, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.37735849056603776, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.37735849056603776, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.37735849056603776, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.37735849056603776, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.37735849056603776, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.37735849056603776, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.37735849056603776, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.37735849056603776, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.404746835443038, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.4258241758241758, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.4155844155844156, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.428068197830069, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.5269114688128773, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.5610837438423646, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.5610837438423646, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.577490549932935, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.5853775278209884, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.4849939975990396, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.428068197830069, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.4258241758241758, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.404746835443038, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.37735849056603776, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.37735849056603776, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.37735849056603776, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.37735849056603776, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.37735849056603776, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.37735849056603776, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.404746835443038, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.4258241758241758, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.6477703984819734, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.5640552995391706, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.5349264705882353, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.542466878915477, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.5864661654135339, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.6590909090909091, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.5934782608695652, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.5518108651911469, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.5, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.5, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.5, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.5, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.5, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.5, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.5, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.5, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.5, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.5, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.5, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.5, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.5, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.5, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.5, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.5, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.5, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.5, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.5, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.5, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.5128205128205128, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.5173076923076922, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.5006410256410256, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.4967948717948718, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.5487179487179488, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.5743589743589743, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.5743589743589743, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.5871794871794872, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.5916666666666667, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.5269230769230769, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.4967948717948718, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.5173076923076922, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.5128205128205128, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.5, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.5, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.5, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.5, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.5, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.5, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.5128205128205128, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.5173076923076922, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.6467948717948717, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.5788461538461539, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.5673076923076923, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.5532051282051282, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.5903846153846154, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.6557692307692308, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.6, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.5698717948717948, "id_best": 46, "lr_best": 0.010799999999999999, "wd_best": 0.05, "train/loss_best": 0.6396255493164062, "validation/loss_best": 0.6946465969085693, "validation/acc_best": 0.696969696969697, "validation/f1_best": 0.6590909090909091, "validation/bacc_best": 0.6557692307692308} +{"epoch": 1, "train/lr": 8.993993993993998e-05, "train/loss": 0.6302077403664589, "train/grad": 0.2821962910145521, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.65618896484375, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.65459228515625, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.65255126953125, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.65096923828125, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.64983154296875, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.64854248046875, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.64724609375, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.6460546875, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.6446630859375, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.6432275390625, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.641962890625, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.64000732421875, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.638232421875, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.6357470703125, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.6333642578125, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.63091552734375, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.62833984375, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.62513916015625, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.6219775390625, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.619168701171875, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.6163232421875, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.6137109375, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.610670166015625, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.607305908203125, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.60483154296875, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.603404541015625, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.602635498046875, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.6015692138671875, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.600552978515625, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.6017669677734375, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.604444580078125, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.6072601318359375, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.610625, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.6132806396484375, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.616109619140625, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.617916259765625, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.6193353271484375, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.6201513671875, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.618785400390625, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.619915771484375, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.6204379272460937, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.611640625, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.6153094482421875, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.623460693359375, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.6300675964355469, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.6484803009033203, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.6861043739318847, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.6993960571289063, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.7259658908843994, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.0346170847164467, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.034121802821755406, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.03361112121026963, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.033322307956404985, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.03314835152588785, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.03302671639248729, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.03297031769994646, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.03295270692091435, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.03295657781418413, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.03296847433783114, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.03298638280946761, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.033004287218209354, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.03301959248492494, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.03302478313446045, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.033026267378591004, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.03301872030831873, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.0330097985221073, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.03302297594025731, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.03304915819317102, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.03310087746940553, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.03317535290494561, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.03329875246156007, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.033502259647939354, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.033749310991261154, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.03389294058317319, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.03416217647958547, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.034505588712636384, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.03462983010103926, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.03470337273553014, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.03495351538294926, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.03512159653240815, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.03492798033868894, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.03405543587636203, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.03311012778431177, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.03199687294894829, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.03038766039535403, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.02885857336455956, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.02878075634595007, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.02864303273614496, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.030617001452483236, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.03185518741607666, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.03201941772829741, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.03316572949523106, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.03726266115438193, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.041120095062069595, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.047019521980546417, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.05944316134788096, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.06816622993908822, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.07397912066895515, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.6649537682533264, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.6646442413330078, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.6640937924385071, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.6634027361869812, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.6628437042236328, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.6619676351547241, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.6610923409461975, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.6602099537849426, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.6590812802314758, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.6579781770706177, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.656978189945221, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.6555243730545044, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.6540843844413757, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.6519730091094971, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.6503121256828308, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.6490776538848877, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.6483694314956665, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.6486219167709351, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.6503251194953918, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.6531045436859131, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.6578614115715027, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.663779079914093, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.6685149073600769, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.6643700003623962, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.6560428738594055, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.648732602596283, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.6407526731491089, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.6374989748001099, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.6389452815055847, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.6421077251434326, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.6460856795310974, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.6485720276832581, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.6507008075714111, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.6516994833946228, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.6513227224349976, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.650205671787262, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.6478353142738342, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.6505584716796875, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.6662679314613342, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.7441633343696594, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.7437583804130554, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.7524393200874329, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.780880868434906, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.8201007843017578, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.9137107133865356, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.7577654719352722, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.8154449462890625, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.7552729845046997, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.7580466866493225, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.6060606060606061, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.6060606060606061, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.6060606060606061, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.6060606060606061, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.6060606060606061, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.6060606060606061, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.6060606060606061, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.6060606060606061, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.6060606060606061, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.6060606060606061, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.6060606060606061, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.6060606060606061, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.6060606060606061, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.6161616161616161, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.6060606060606061, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.5858585858585859, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.5959595959595959, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.6565656565656566, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.6868686868686869, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.6363636363636364, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.5757575757575758, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.5555555555555556, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.5454545454545454, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.5454545454545454, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.5757575757575758, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.5959595959595959, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.6363636363636364, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.6666666666666666, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.6666666666666666, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.6767676767676768, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.6464646464646465, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.6161616161616161, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.6060606060606061, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.6060606060606061, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.5959595959595959, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.6060606060606061, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.6060606060606061, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.5858585858585859, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.5454545454545454, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.48484848484848486, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.46464646464646464, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.48484848484848486, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.48484848484848486, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.48484848484848486, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.47474747474747475, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.6161616161616161, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.5454545454545454, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.5555555555555556, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.5252525252525253, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.37735849056603776, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.37735849056603776, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.37735849056603776, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.37735849056603776, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.37735849056603776, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.37735849056603776, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.37735849056603776, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.37735849056603776, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.37735849056603776, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.37735849056603776, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.37735849056603776, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.37735849056603776, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.37735849056603776, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.404746835443038, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.42070517629407356, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.41045751633986927, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.4907407407407407, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.5934782608695652, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.6503361057308876, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.6156169111302847, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.5628679562657696, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.5518518518518518, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.543778801843318, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.542466878915477, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.5657894736842105, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.5805084745762712, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.6115954664341761, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.6220936957779063, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.6158730158730159, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.641628959276018, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.6202739726027398, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.5942622950819672, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.589299010743538, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.589299010743538, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.5769230769230769, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.5855962219598583, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.5814634146341464, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.564344746162928, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.5332634887375589, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.48146246277087396, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.45666356011183595, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.4710319539025668, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.4466849315068493, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.4710319539025668, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.44999999999999996, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.6161224489795918, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.543778801843318, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.5533223954060705, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.5221320735339426, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.5, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.5, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.5, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.5, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.5, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.5, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.5, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.5, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.5, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.5, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.5, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.5, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.5, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.5128205128205128, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.5089743589743589, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.49230769230769234, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.5230769230769231, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.6, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.6474358974358975, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.6147435897435898, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.5647435897435897, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.5615384615384615, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.5576923076923077, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.5532051282051282, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.5692307692307692, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.5814102564102563, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.6102564102564102, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.6217948717948718, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.6173076923076923, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.639102564102564, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.6185897435897436, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.5935897435897436, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.5897435897435896, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.5897435897435896, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.5769230769230769, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.5852564102564103, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.5807692307692307, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.5641025641025641, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.5352564102564102, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.5256410256410257, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.5134615384615384, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.5435897435897435, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.566025641025641, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.5435897435897435, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.5442307692307693, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.642948717948718, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.5576923076923077, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.566025641025641, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.5679487179487179, "id_best": 18, "lr_best": 0.00011399999999999999, "wd_best": 0.05, "train/loss_best": 0.6219775390625, "validation/loss_best": 0.6503251194953918, "validation/acc_best": 0.6868686868686869, "validation/f1_best": 0.6503361057308876, "validation/bacc_best": 0.6474358974358975} +{"epoch": 2, "train/lr": 0.00014999999999999988, "train/loss": 0.6456232324242592, "train/grad": 0.4194521671533585, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.6566650390625, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.65555908203125, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.6538818359375, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.6524169921875, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.6508935546875, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.64905517578125, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.64705810546875, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.644951171875, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.64249267578125, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.6400537109375, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.63786865234375, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.63508056640625, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.632496337890625, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.629447021484375, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.62699951171875, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.625113525390625, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.623026123046875, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.6207421875, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.6180511474609375, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.6155865478515625, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.6124658203125, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.609818115234375, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.6067041015625, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.6029730224609375, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.5994207763671875, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.59609375, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.5948489379882812, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.5954269409179688, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.5974691772460937, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.5984661865234375, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.5982769775390625, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.5976898193359375, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.5976409912109375, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.5991133117675781, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.6011880493164062, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.604718017578125, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.6074151611328125, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.600357666015625, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.5991456604003906, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.6294418334960937, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.6113312911987304, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.5966552734375, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.6024151229858399, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.6235493278503418, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.7000511649250984, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.7624795341491699, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.7429440581798553, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.8594573915004731, "train/loss_048_lr5.0e+01_wd1.0e+00": 1.3305425497889518, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.03336105965077877, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.033350046728737655, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.03334818452596664, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.03333996705245226, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.03333151605911553, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.03335165310185403, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.03336586194112897, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.03339235837571323, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.03344394936226308, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.033504683366045354, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.03358173815533519, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.03372073294129223, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.03386203507892788, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.03410922724287957, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.034377904892899096, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.034655874841846526, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.0349963383609429, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.03534897610545158, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.035691005471162496, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.03604310928843915, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.03650161239784211, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.036771602258086206, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.03676682099699974, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.03661047406028956, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.036351623046211895, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.035935366386547686, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.035618787398561835, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.03551568611059338, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.03522885711863637, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.034154581064358355, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.032584076384082436, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.031003403286449613, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.029230576241388917, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.02810911497566849, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.027422839119099082, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.027581481270026416, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.030347410421818495, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.02951372627634555, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.03291238588513806, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.04269046756438911, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.04434182199183852, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.05140884943306446, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.05258863162714988, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.059462991608306766, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.07606270578689873, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.10548887775279582, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0916334334667772, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.12858954340219497, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.19256315809674562, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.661374568939209, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.6607353687286377, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.6596592664718628, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.6586111783981323, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.6576172709465027, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.6564878821372986, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.6552155613899231, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.6540062427520752, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.6524657607078552, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.6509280204772949, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.6496111750602722, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.6478026509284973, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.6465762853622437, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.6461479663848877, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.6479859948158264, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.6513301730155945, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.6558709740638733, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.6581424474716187, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.6575290560722351, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.6601408123970032, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.6712789535522461, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.6807247400283813, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.6727078557014465, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.6553650498390198, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.6435001492500305, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.6402209401130676, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.6440953016281128, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.6471431255340576, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.6485387086868286, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.6486836671829224, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.6483110189437866, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.6479377150535583, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.6471194624900818, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.6480057835578918, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.6524146199226379, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.6631993651390076, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.6803796291351318, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.7105947732925415, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.7061331868171692, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.6768099069595337, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.6792991161346436, "validation/loss_041_lr1.6e+01_wd1.0e+00": 1.163176417350769, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.9353287816047668, "validation/loss_043_lr2.2e+01_wd1.0e+00": 1.5196644067764282, "validation/loss_044_lr2.6e+01_wd1.0e+00": 1.398764967918396, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.02217960357666, "validation/loss_046_lr3.6e+01_wd1.0e+00": 2.54463529586792, "validation/loss_047_lr4.3e+01_wd1.0e+00": 1.9287972450256348, "validation/loss_048_lr5.0e+01_wd1.0e+00": 2.2023422718048096, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.6060606060606061, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.6060606060606061, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.6060606060606061, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.6060606060606061, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.6060606060606061, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.6060606060606061, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.6060606060606061, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.6060606060606061, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.6161616161616161, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.6060606060606061, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.6060606060606061, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.5757575757575758, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.5959595959595959, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.6464646464646465, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.6767676767676768, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.6161616161616161, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.5757575757575758, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.5757575757575758, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.5656565656565656, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.5656565656565656, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.5959595959595959, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.5858585858585859, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.5959595959595959, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.5959595959595959, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.6161616161616161, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.6262626262626263, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.6363636363636364, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.6363636363636364, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.6363636363636364, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.6262626262626263, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.6262626262626263, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.6464646464646465, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.6464646464646465, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.6565656565656566, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.6262626262626263, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.6161616161616161, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.6060606060606061, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.6161616161616161, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.6161616161616161, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.6464646464646465, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.5656565656565656, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.5252525252525253, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.494949494949495, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.48484848484848486, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.48484848484848486, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.5252525252525253, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.47474747474747475, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.5151515151515151, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.5959595959595959, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.37735849056603776, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.37735849056603776, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.37735849056603776, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.37735849056603776, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.37735849056603776, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.37735849056603776, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.37735849056603776, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.37735849056603776, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.404746835443038, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.42070517629407356, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.42070517629407356, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.40532036613272315, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.4648648648648649, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.577490549932935, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.6363636363636364, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.5900174367916304, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.5628679562657696, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.5657894736842105, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.5540073336825564, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.5567933368037481, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.5925925925925926, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.5856894967847299, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.5925925925925926, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.5888704318936877, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.5900174367916304, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.5762868710237131, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.5610837438423646, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.5610837438423646, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.5610837438423646, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.5533471527862456, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.5533471527862456, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.577490549932935, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.577490549932935, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.5854679802955665, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.5616848151250449, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.5744343891402715, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.4392156862745098, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.404746835443038, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.404746835443038, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.49673202614379086, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.5334794520547945, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.5125196437925615, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.493657937806874, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.4400576688477321, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.45268292682926825, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.5235023041474655, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.4447799827437446, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.5147058823529411, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.5217391304347826, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.5, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.5, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.5, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.5, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.5, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.5, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.5, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.5, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.5128205128205128, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.5089743589743589, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.5089743589743589, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.483974358974359, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.514102564102564, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.5871794871794872, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.6346153846153846, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.5891025641025641, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.5647435897435897, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.5692307692307692, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.5564102564102564, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.5608974358974359, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.6038461538461539, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.608974358974359, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.6038461538461539, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.5948717948717949, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.5891025641025641, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.5794871794871795, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.5743589743589743, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.5743589743589743, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.5743589743589743, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.566025641025641, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.566025641025641, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.5871794871794872, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.5871794871794872, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.5955128205128205, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.5705128205128205, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.5756410256410257, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.5134615384615384, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.5128205128205128, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.5128205128205128, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.5557692307692308, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.533974358974359, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.5858974358974359, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.5294871794871795, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.5705128205128205, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.5615384615384615, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.5634615384615385, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.5487179487179488, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.5461538461538462, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.5365384615384615, "id_best": 14, "lr_best": 5.9999999999999995e-05, "wd_best": 0.05, "train/loss_best": 0.62699951171875, "validation/loss_best": 0.6479859948158264, "validation/acc_best": 0.6767676767676768, "validation/f1_best": 0.6363636363636364, "validation/bacc_best": 0.6346153846153846} +{"epoch": 3, "train/lr": 0.0002100600600600602, "train/loss": 0.646492377370596, "train/grad": 0.5420741948485375, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.645537109375, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.6441064453125, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.642158203125, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.640390625, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.63882568359375, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.6369775390625, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.63520263671875, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.633458251953125, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.6315380859375, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.6295947265625, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.628121337890625, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.626053466796875, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.624332275390625, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.621856689453125, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.61905517578125, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.61545166015625, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.6103521728515625, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.6046453857421875, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.5993109130859375, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.5954779052734375, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.591971435546875, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.5901763916015625, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.5897015380859375, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.5896359252929687, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.5890911865234375, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.5874737548828125, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.584659423828125, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.5819631958007813, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.5789816284179687, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.5750042724609375, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.5711416625976562, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.5683139038085937, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.5655508422851563, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.5633364868164062, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.5673740386962891, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.539036294221878, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.49655977725982664, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.467420065253973, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.4016950131952763, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.4517698433995247, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.44829820916056634, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.45596021667122844, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.6735327410697937, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.6719283410906791, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.844932364076376, "train/loss_045_lr3.1e+01_wd1.0e+00": 1.1339643868803977, "train/loss_046_lr3.6e+01_wd1.0e+00": 1.2992356269061565, "train/loss_047_lr4.3e+01_wd1.0e+00": 1.2643722361326217, "train/loss_048_lr5.0e+01_wd1.0e+00": 1.3126001404225827, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.032352769863791764, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.03232942184433341, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.032288694349117575, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.03226016176398844, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.0322427901532501, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.03221462900284678, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.03220998633652925, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.03220872389152646, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.0321965245436877, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.03220814404077828, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.032240897081792355, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.032355122342705725, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.03251411712262779, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.03281529310625046, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.03307742530480027, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.03325408996548504, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.03340857587754727, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.03360430224332958, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.03384843205101788, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.03413054741919041, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.03458924520760775, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.035091228387318554, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.035449730302207175, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.03544404533226043, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.03467124522197992, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.033149054620880636, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.03225176612846553, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.03135032943915576, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.02981493989471346, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.02802156372461468, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.026865762735251337, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.026506511776242404, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.02644646035740152, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0270718481997028, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.02998915486037731, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.03363371721003205, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.03635456393007189, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.03922604906372726, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.040184694952331484, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.04173869606573135, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0690264975419268, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.06842964094597846, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.10119408788508735, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.11264731474686414, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.13247030552942307, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.15823869596235454, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.19480223154183476, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.18801700561773033, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.1522240509092808, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.6573315262794495, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.6563212275505066, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.6548712849617004, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.6535526514053345, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.6524044871330261, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.6509648561477661, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.6496869325637817, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.6485150456428528, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.6473435759544373, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.6466661095619202, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.6463639736175537, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.6464911699295044, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.647577702999115, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.6513013243675232, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.6543979048728943, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.6535347700119019, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.6477918028831482, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.6402712464332581, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.6354125738143921, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.6341820955276489, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.6343497037887573, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.6349061131477356, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.6357758641242981, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.6371131539344788, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.640326201915741, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.653255820274353, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.6686214804649353, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.6787682771682739, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.6891695857048035, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.6999584436416626, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.7114878296852112, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.7166374921798706, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.7099002003669739, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.6947771310806274, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.6909384727478027, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.9887889623641968, "validation/loss_036_lr7.1e+00_wd1.0e+00": 1.1951764822006226, "validation/loss_037_lr8.3e+00_wd1.0e+00": 1.5362203121185303, "validation/loss_038_lr9.8e+00_wd1.0e+00": 1.5283485651016235, "validation/loss_039_lr1.2e+01_wd1.0e+00": 1.186366081237793, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.753652334213257, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.7163162231445312, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.985889434814453, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.2419357299804688, "validation/loss_044_lr2.6e+01_wd1.0e+00": 4.474057674407959, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1043429374694824, "validation/loss_046_lr3.6e+01_wd1.0e+00": 5.964853763580322, "validation/loss_047_lr4.3e+01_wd1.0e+00": 2.227421760559082, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.6931473016738892, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.6060606060606061, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.6060606060606061, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.6060606060606061, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.6161616161616161, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.6262626262626263, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.5959595959595959, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.5858585858585859, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.6060606060606061, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.6262626262626263, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.6565656565656566, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.6666666666666666, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.6868686868686869, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.6363636363636364, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.5757575757575758, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.5757575757575758, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.5656565656565656, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.5757575757575758, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.6060606060606061, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.6666666666666666, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.6868686868686869, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.6666666666666666, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.6565656565656566, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.6666666666666666, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.6666666666666666, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.6464646464646465, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.6060606060606061, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.6262626262626263, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.6262626262626263, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.6262626262626263, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.6161616161616161, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.6262626262626263, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.6464646464646465, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.6363636363636364, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.6363636363636364, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.5959595959595959, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.5757575757575758, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.6161616161616161, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.5757575757575758, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.5555555555555556, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.6363636363636364, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.6060606060606061, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.5050505050505051, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.6262626262626263, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.6565656565656566, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.4444444444444444, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.5656565656565656, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.43434343434343436, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.5959595959595959, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.3939393939393939, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.37735849056603776, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.37735849056603776, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.37735849056603776, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.404746835443038, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.43094609290041946, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.4155844155844156, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.41045751633986927, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.4849939975990396, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.5442329227323628, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.5934782608695652, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.6158730158730159, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.6503361057308876, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.6071428571428572, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.5595338983050847, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.5595338983050847, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.5508072174738841, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.5595338983050847, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.5855962219598583, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.6329625884732053, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.6449971081550029, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.6158730158730159, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.6008064516129032, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.6158730158730159, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.6158730158730159, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.5853775278209884, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.4975927130774236, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.5114045618247299, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.5114045618247299, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.4982879057663334, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.47750000000000004, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.4982879057663334, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.5378151260504201, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.5305584826132772, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.5305584826132772, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.5520361990950227, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.5736259228876128, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.6142329778506973, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.5722222222222222, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.5301984469370147, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.5773244781783682, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.5601002620485359, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.5017972681524083, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.5114045618247299, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.6075093283582089, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.41558441558441556, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.49947089947089945, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.353544776119403, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.5454545454545454, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.2826086956521739, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.5, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.5, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.5, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.5128205128205128, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.5256410256410257, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.5006410256410256, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.49230769230769234, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.5269230769230769, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.5615384615384615, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.6, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.6173076923076923, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.6474358974358975, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.6057692307692308, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.5602564102564103, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.5602564102564103, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.551923076923077, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.5602564102564103, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.5852564102564103, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.6307692307692307, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.6429487179487179, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.6173076923076923, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.6044871794871794, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.6173076923076923, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.6173076923076923, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.5916666666666667, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.5314102564102564, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.548076923076923, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.548076923076923, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.5435897435897437, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.5307692307692308, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.5435897435897437, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.5692307692307692, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.5608974358974359, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.5608974358974359, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.5544871794871795, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.5871794871794872, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.6294871794871795, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.5826923076923077, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.5301282051282051, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.5833333333333334, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.5628205128205128, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.5108974358974359, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.548076923076923, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.608974358974359, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.5147435897435897, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.5115384615384615, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.5333333333333333, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.55, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.5, "id_best": 11, "lr_best": 3.5999999999999994e-05, "wd_best": 0.05, "train/loss_best": 0.626053466796875, "validation/loss_best": 0.6464911699295044, "validation/acc_best": 0.6868686868686869, "validation/f1_best": 0.6503361057308876, "validation/bacc_best": 0.6474358974358975} +{"epoch": 4, "train/lr": 0.0002701201201201201, "train/loss": 0.6192237711697817, "train/grad": 0.5386236441880464, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.65408935546875, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.65240478515625, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.65, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.64757568359375, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.64552490234375, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.64256591796875, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.639488525390625, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.636365966796875, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.632523193359375, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.628739013671875, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.625224609375, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.620311279296875, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.61616455078125, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.610770263671875, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.6060980224609375, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.6026617431640625, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.5994940185546875, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.5967791748046875, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.5944329833984375, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.59328369140625, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.59230224609375, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.5911611938476562, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.589710693359375, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.588314208984375, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.5873049926757813, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.5851785278320313, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.5801876831054688, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.574643325805664, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.5674684906005859, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.5522551727294922, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.5313615417480468, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.5105882740020752, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.40542901515960694, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.37126987129449845, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.2971785782277584, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.15205016627907753, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.18790960758924485, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.14172451347112655, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.29988177090883256, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.41512718081474304, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.8742239199578762, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.47927157521247865, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.9841047315299511, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.48480187833309174, "train/loss_044_lr2.6e+01_wd1.0e+00": 1.973447822779417, "train/loss_045_lr3.1e+01_wd1.0e+00": 1.3139148551225661, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.8498296990990639, "train/loss_047_lr4.3e+01_wd1.0e+00": 1.075420067757368, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.69140625, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.032547544380649926, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.03255216182209551, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.032559122913517057, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.03257539175916463, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.03258984284941107, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.032618826744146644, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.03264704310335219, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.03268788707908243, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.032730221464298666, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.03277175243012607, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.032825246322900056, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.032956868247129026, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.0331767159467563, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.03365852816496044, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.03416997376363724, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.034570701790507884, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.034925197777338324, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.03533005445729941, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.03593111905734986, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.03656638929620385, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.036966226315125826, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.03673683857545257, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.035950996181927625, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.034888545046560464, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.033833799499552696, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.032683491124771535, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.031705175563693046, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.03054044666700065, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.029276822018437086, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.028232844858430327, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.027332304697483777, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.028716671341098846, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.030149861061945556, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.03299809900810942, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.03358794085215777, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.023695365789099015, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.03449462103948463, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.030212680343247485, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.050446925346404894, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.07723360239014383, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.09326523130897796, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.09773633329261582, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.1623760121325938, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.08832358341147482, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.21691752273240128, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.11957717725860072, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.01782897874712944, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.12168911536689847, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.6548166871070862, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.6537255048751831, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.6519836783409119, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.6503755450248718, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.6489270925521851, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.6472569704055786, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.6457350850105286, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.6445665955543518, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.6441320776939392, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.6450765132904053, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.6469823718070984, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.6506286859512329, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.6528915166854858, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.6532084345817566, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.6500283479690552, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.6458677053451538, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.6428133249282837, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.6440770030021667, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.6540290117263794, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.6659281849861145, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.6731494665145874, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.6754699349403381, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.6745589971542358, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.6710087656974792, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.6654554605484009, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.65628981590271, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.6498988270759583, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.6555338501930237, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.6578353643417358, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.6620402336120605, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.7082169055938721, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.8189976215362549, "validation/loss_032_lr3.7e+00_wd1.0e+00": 1.1676453351974487, "validation/loss_033_lr4.3e+00_wd1.0e+00": 1.5173239707946777, "validation/loss_034_lr5.1e+00_wd1.0e+00": 1.7834084033966064, "validation/loss_035_lr6.0e+00_wd1.0e+00": 1.9316678047180176, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.5427699089050293, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.411226511001587, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.8961551189422607, "validation/loss_039_lr1.2e+01_wd1.0e+00": 5.621851921081543, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_041_lr1.6e+01_wd1.0e+00": 5.515195846557617, "validation/loss_042_lr1.9e+01_wd1.0e+00": 4.991593837738037, "validation/loss_043_lr2.2e+01_wd1.0e+00": 4.1972174644470215, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.6931473016738892, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.6060606060606061, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.6060606060606061, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.6161616161616161, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.6060606060606061, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.6060606060606061, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.5757575757575758, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.5757575757575758, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.6363636363636364, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.6565656565656566, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.6868686868686869, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.6464646464646465, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.5959595959595959, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.5757575757575758, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.5757575757575758, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.5858585858585859, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.5959595959595959, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.6060606060606061, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.6060606060606061, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.5858585858585859, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.5757575757575758, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.5555555555555556, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.5555555555555556, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.5555555555555556, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.5858585858585859, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.6060606060606061, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.6464646464646465, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.6666666666666666, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.6464646464646465, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.6464646464646465, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.6666666666666666, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.6262626262626263, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.6060606060606061, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.6161616161616161, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.5656565656565656, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.6262626262626263, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.6565656565656566, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.6262626262626263, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.5959595959595959, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.5252525252525253, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.5858585858585859, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.6262626262626263, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.6161616161616161, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.5858585858585859, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.3939393939393939, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.37735849056603776, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.37735849056603776, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.404746835443038, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.42070517629407356, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.42070517629407356, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.40532036613272315, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.45231822971548996, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.5610837438423646, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.6008064516129032, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.6503361057308876, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.6202739726027398, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.5769230769230769, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.5595338983050847, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.5595338983050847, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.5682374215508988, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.5769230769230769, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.5855962219598583, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.5855962219598583, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.5716999050332383, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.5657894736842105, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.5518518518518518, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.5518518518518518, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.5518518518518518, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.5774076002082249, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.5925925925925926, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.624390243902439, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.6329625884732053, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.577490549932935, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.577490549932935, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.6090702405169319, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.5884732052578362, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.5718088055894421, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.5942622950819672, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.5075766338924234, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.6162388685175484, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.6243303571428571, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.5114045618247299, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.530360531309298, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.4839747144283021, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.49496080627099664, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.610360599936177, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.6044995794785535, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.5796831314072693, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.2826086956521739, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.5, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.5, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.5128205128205128, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.5089743589743589, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.5089743589743589, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.483974358974359, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.49743589743589745, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.5743589743589743, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.6044871794871794, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.6474358974358975, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.6185897435897436, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.5769230769230769, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.5602564102564103, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.5602564102564103, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.5685897435897436, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.5769230769230769, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.5852564102564103, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.5852564102564103, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.573076923076923, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.5692307692307692, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.5615384615384615, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.5615384615384615, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.5615384615384615, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.582051282051282, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.5942307692307692, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.6230769230769231, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.6307692307692307, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.5871794871794872, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.5871794871794872, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.6128205128205129, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.5884615384615385, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.5717948717948718, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.5935897435897436, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.516025641025641, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.6198717948717949, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.6224358974358974, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.548076923076923, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.5410256410256411, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.48717948717948717, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.5192307692307693, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.5, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.610897435897436, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.6070512820512821, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.5865384615384616, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.5, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.5, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.5, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.5, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.5, "id_best": 9, "lr_best": 2.6099999999999997e-05, "wd_best": 0.05, "train/loss_best": 0.628739013671875, "validation/loss_best": 0.6450765132904053, "validation/acc_best": 0.6868686868686869, "validation/f1_best": 0.6503361057308876, "validation/bacc_best": 0.6474358974358975} +{"epoch": 5, "train/lr": 0.00029891323817685334, "train/loss": 0.521845999956131, "train/grad": 0.3748706861957908, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.645927734375, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.64377197265625, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.64057373046875, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.637718505859375, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.635240478515625, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.6322021484375, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.629364013671875, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.62679931640625, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.623931884765625, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.6211944580078125, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.6183343505859376, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.6136767578125, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.609078369140625, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.6031646728515625, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.597857666015625, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.5931396484375, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.587498779296875, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.582664794921875, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.579168701171875, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.576900634765625, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.5746731567382812, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.5727218627929688, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.5706072998046875, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.5682638549804687, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.5649781799316407, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.5586700439453125, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.5476126098632812, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.5244284820556641, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.47908607482910154, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.3829456728696823, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.21458656072616578, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.1507165886461735, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.12762411132454873, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.04817502349615097, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.07655693128705025, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.0006890255212783814, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.116104676425457, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.06902561932802201, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.6484261690080166, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.6088113813102245, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.69140625, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.7172742722928525, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.21411191076040267, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.7877188451588154, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.69140625, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.69140625, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.69140625, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.69140625, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.69140625, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.03446518791373819, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.0344675669586286, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.0344951085653156, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.03454383126460016, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.03460491419769823, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.03470883261412382, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.03485414533875883, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.03503565248567611, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.03524469428695738, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.03544022908899933, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.035571021321229634, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.035628743725828825, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.03561873785220086, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.035744192274287344, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.03591561740729958, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.03606109825428575, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.03631164907012135, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.03672930042259395, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.0369785068416968, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.03676102296914905, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.03597548009362072, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.03491222081240267, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.03360931872855872, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.03216473079286516, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.03077054119668901, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.029467053599655627, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.028853211281821133, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.028768876977264882, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.029547877516597508, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.030563282663933933, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.025278717983164823, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.022860835358369514, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.024560096552959293, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.008656661863242335, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.019754321943300967, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0002702104041054554, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.024730976318547846, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.02196119990909665, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.03647707259100571, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.1016439024260824, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.13713186818691792, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.05201947705874284, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.1166985631046191, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.6515815854072571, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.6505630016326904, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.6491435170173645, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.6478736400604248, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.6469403505325317, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.645577609539032, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.6442325711250305, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.6430126428604126, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.6412562727928162, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.6397176384925842, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.638437807559967, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.6372602581977844, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.6365544199943542, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.6357621550559998, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.6365604996681213, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.641537070274353, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.6516498327255249, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.6640945672988892, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.6725345849990845, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.6697167158126831, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.6635572910308838, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.6611787676811218, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.6618749499320984, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.6654636859893799, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.6705014109611511, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.6812264919281006, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.7441409230232239, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.7707785367965698, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.7805969715118408, "validation/loss_029_lr2.3e+00_wd1.0e+00": 1.219129204750061, "validation/loss_030_lr2.7e+00_wd1.0e+00": 1.702350378036499, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.2555148601531982, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.1085755825042725, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.0237882137298584, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.3681480884552, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.104295253753662, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.443000555038452, "validation/loss_037_lr8.3e+00_wd1.0e+00": 4.40285587310791, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.6931473016738892, "validation/loss_039_lr1.2e+01_wd1.0e+00": 5.666584014892578, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_041_lr1.6e+01_wd1.0e+00": 13.721431732177734, "validation/loss_042_lr1.9e+01_wd1.0e+00": 7.019399166107178, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.6931473016738892, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.5959595959595959, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.5858585858585859, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.6161616161616161, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.6262626262626263, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.6565656565656566, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.6565656565656566, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.6666666666666666, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.6666666666666666, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.6666666666666666, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.6767676767676768, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.6767676767676768, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.6767676767676768, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.6666666666666666, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.6666666666666666, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.6666666666666666, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.6262626262626263, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.6060606060606061, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.6060606060606061, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.6060606060606061, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.6161616161616161, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.6060606060606061, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.6262626262626263, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.6262626262626263, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.6363636363636364, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.6161616161616161, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.6161616161616161, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.6161616161616161, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.6363636363636364, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.6060606060606061, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.5353535353535354, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.5555555555555556, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.6262626262626263, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.6666666666666666, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.6060606060606061, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.6262626262626263, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.6767676767676768, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.5959595959595959, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.5757575757575758, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.3939393939393939, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.5353535353535354, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.5757575757575758, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.6363636363636364, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.3939393939393939, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.4155844155844156, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.41045751633986927, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.5044783983140148, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.5442329227323628, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.5934782608695652, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.5934782608695652, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.6158730158730159, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.6220936957779063, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.6220936957779063, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.6363636363636364, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.6363636363636364, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.6363636363636364, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.6277771448102997, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.6158730158730159, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.6016339470796245, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.5342657342657342, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.4975927130774236, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.4849939975990396, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.4849939975990396, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.5044783983140148, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.509090909090909, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.5442329227323628, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.5442329227323628, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.5518108651911469, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.5162037037037037, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.5044783983140148, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.46195652173913043, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.505, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.5718088055894421, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.5134615384615384, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.5198412698412699, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.5533471527862456, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.641972602739726, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.576876712328767, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.5616848151250449, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.6547515257192676, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.5729076790336497, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.477112676056338, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.2826086956521739, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.5295454545454545, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.49782608695652175, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.5518108651911469, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.2826086956521739, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.5006410256410256, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.49230769230769234, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.5397435897435897, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.5615384615384615, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.6, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.6, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.6173076923076923, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.6217948717948718, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.6217948717948718, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.6346153846153846, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.6346153846153846, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.6346153846153846, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.6262820512820513, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.6173076923076923, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.6083333333333333, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.5570512820512821, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.5314102564102564, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.5269230769230769, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.5269230769230769, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.5397435897435897, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.5358974358974359, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.5615384615384615, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.5615384615384615, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.5698717948717948, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.5442307692307692, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.5397435897435897, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.5262820512820513, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.551923076923077, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.5717948717948718, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.5134615384615384, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.5211538461538462, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.566025641025641, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.6397435897435897, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.5762820512820512, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.5705128205128205, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.6525641025641026, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.5724358974358974, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.5064102564102564, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.5, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.5358974358974359, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.5, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.5153846153846154, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.5698717948717948, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.5, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.5, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.5, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.5, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.5, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.5, "id_best": 35, "lr_best": 0.0018, "wd_best": 0.05, "train/loss_best": 0.0006890255212783814, "validation/loss_best": 2.104295253753662, "validation/acc_best": 0.6767676767676768, "validation/f1_best": 0.6547515257192676, "validation/bacc_best": 0.6525641025641026} +{"epoch": 6, "train/lr": 0.0002924170901991409, "train/loss": 0.4674825258553028, "train/grad": 0.21933029823005198, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.63073486328125, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.628406982421875, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.625093994140625, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.622276611328125, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.61980224609375, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.61675048828125, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.613726806640625, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.610733642578125, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.60713623046875, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.60374267578125, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.6005242919921875, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.59625, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.592474365234375, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.5884210205078125, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.5852493286132813, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.5823965454101563, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.57822265625, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.5731640625, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.5679095458984375, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.5638296508789062, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.5597357177734374, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.5565403747558594, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.5527757263183594, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.5471721649169922, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.5376752853393555, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.514236421585083, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.46911992073059083, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.3528364086151123, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.1778487603366375, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.05869261518120766, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.007435482144355774, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.003212716430425644, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.0010486401617527008, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.000605979710817337, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.0007236625254154205, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.0003256206214427948, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.006576686799526214, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.2025818707048893, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.69140625, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.02022417426109314, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.69140625, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.7789391326904297, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.020240860134363173, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.69140625, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.69140625, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.69140625, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.69140625, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.69140625, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.69140625, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.03395757131278515, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.033928733225911854, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.033913181298412386, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.03391465846449137, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.033918549213558434, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.03394168865866959, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.03398624529596418, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.0340700914664194, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.034186131516471506, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.03432216026820242, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.034447299824096264, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.034634672938846055, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.034757131328806284, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.03506540846079588, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.03552273797336966, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.03604743334464729, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.03666634442750365, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.0370976401725784, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.03730587393045425, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.037274712156504394, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.03685563180129975, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.03606888609007001, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.03507443438284099, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.03404156015254557, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.033180770948529247, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.03268193817231804, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.03299677435308695, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.03455016460036859, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.027208742392249404, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.014562500734464266, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0021227724980781206, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0010821409706113626, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.00037175368956923196, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.00020234365034411895, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0004475240653596302, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0001141547721272218, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0033023297189935354, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.03977069168993466, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.012546848590631893, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.014303563639468848, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.005018964188164134, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.6493569016456604, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.6481056809425354, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.6461964845657349, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.6446340680122375, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.6433293223381042, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.6417736411094666, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.6403298377990723, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.6389963030815125, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.6376800537109375, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.6365907788276672, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.6363763809204102, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.6372942924499512, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.63798588514328, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.6374151706695557, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.636848509311676, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.6376135945320129, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.6394835710525513, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.6416606903076172, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.6445702910423279, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.6474359035491943, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.6510565280914307, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.656609296798706, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.6639791131019592, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.6694645881652832, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.6774224042892456, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.7188412547111511, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.7599356174468994, "validation/loss_027_lr1.6e+00_wd1.0e+00": 1.0119564533233643, "validation/loss_028_lr1.9e+00_wd1.0e+00": 1.6307023763656616, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.15390944480896, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.102958917617798, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.288773775100708, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.2606966495513916, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.18233585357666, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.020815849304199, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.1579365730285645, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.4104175567626953, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.9898464679718018, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.6931473016738892, "validation/loss_039_lr1.2e+01_wd1.0e+00": 7.448716163635254, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_042_lr1.9e+01_wd1.0e+00": 6.6630473136901855, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.6931473016738892, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.6060606060606061, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.6060606060606061, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.5757575757575758, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.5959595959595959, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.5757575757575758, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.6060606060606061, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.6161616161616161, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.6262626262626263, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.6666666666666666, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.6565656565656566, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.6464646464646465, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.6363636363636364, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.6262626262626263, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.6565656565656566, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.6767676767676768, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.6565656565656566, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.6464646464646465, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.6363636363636364, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.6262626262626263, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.6262626262626263, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.6262626262626263, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.6363636363636364, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.6363636363636364, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.6666666666666666, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.6363636363636364, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.5959595959595959, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.6161616161616161, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.6464646464646465, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.6060606060606061, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.5252525252525253, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.5555555555555556, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.6060606060606061, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.6565656565656566, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.6060606060606061, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.6161616161616161, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.6363636363636364, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.5858585858585859, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.5353535353535354, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.3939393939393939, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.6161616161616161, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.5858585858585859, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.3939393939393939, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.42070517629407356, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.42070517629407356, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.40532036613272315, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.4648648648648649, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.45231822971548996, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.509090909090909, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.5269114688128773, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.5442329227323628, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.6016339470796245, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.5767102615694165, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.5594405594405594, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.5416666666666666, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.5233571893298634, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.5854679802955665, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.6305970149253731, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.6136363636363636, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.6052181838897117, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.5909090909090909, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.5826592229691239, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.5884732052578362, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.6029268292682928, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.6156169111302847, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.6192307692307693, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.6552706552706553, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.6278195488721805, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.5949263502454992, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.5801339285714285, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.6202739726027398, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.5954950235725511, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.49560975609756097, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.525283347863993, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.5601002620485359, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.628968253968254, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.5718088055894421, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.5744343891402715, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.6022321428571429, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.5551780821917809, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.4599146110056926, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.2826086956521739, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.5456521739130434, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.5439838220424671, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.2826086956521739, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.5089743589743589, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.5089743589743589, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.483974358974359, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.514102564102564, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.49743589743589745, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.5358974358974359, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.5487179487179488, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.5615384615384615, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.6083333333333333, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.591025641025641, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.5782051282051281, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.5653846153846154, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.5525641025641026, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.5955128205128205, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.6301282051282051, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.6134615384615385, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.6051282051282052, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.5923076923076923, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.583974358974359, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.5884615384615385, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.6019230769230769, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.6147435897435898, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.6192307692307693, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.6576923076923077, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.6326923076923077, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.6128205128205129, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.5801282051282051, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.6185897435897436, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.5987179487179487, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.49615384615384617, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.5256410256410257, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.5628205128205128, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.6269230769230769, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.5717948717948718, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.5756410256410257, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.6012820512820514, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.5551282051282052, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.47756410256410253, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.5, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.5576923076923077, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.5, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.5, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.5461538461538461, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.5, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.5, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.5, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.5, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.5, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.5, "id_best": 23, "lr_best": 0.00025499999999999996, "wd_best": 0.05, "train/loss_best": 0.5471721649169922, "validation/loss_best": 0.6694645881652832, "validation/acc_best": 0.6666666666666666, "validation/f1_best": 0.6552706552706553, "validation/bacc_best": 0.6576923076923077} +{"epoch": 7, "train/lr": 0.00027969249556793234, "train/loss": 0.4384620568156242, "train/grad": 0.18875474084168672, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.63640380859375, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.63376953125, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.629625244140625, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.626180419921875, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.622813720703125, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.61871337890625, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.61456787109375, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.6101904296875, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.605250244140625, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.600865478515625, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.5973486328125, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.592611083984375, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.588223876953125, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.5829852294921875, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.5790679931640625, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.5755999755859375, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.5714785766601562, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.567860107421875, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.56406494140625, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.5596719360351563, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.552091064453125, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.5414225769042968, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.5251496887207031, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.503013916015625, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.4718929672241211, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.38462178349494935, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.2218957355618477, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.06719183295965195, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.01171871080994606, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0016318127512931825, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0007864987850189209, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.0005822269618511199, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.0005029657483100891, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.00036783844232559206, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.00012712001800537108, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.0002352312207221985, "train/loss_036_lr7.1e+00_wd1.0e+00": 4.2269378900527955e-05, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.0013689465820789337, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.69140625, "train/loss_039_lr1.2e+01_wd1.0e+00": 9.382367134094238e-06, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.69140625, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.69140625, "train/loss_042_lr1.9e+01_wd1.0e+00": 4.0025562047958376e-05, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.69140625, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.69140625, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.69140625, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.69140625, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.69140625, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.69140625, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.031061589368619025, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.031098452606238426, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.031174152810126542, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.03126519178505987, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.031371982372365895, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.031534190573729574, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.03173953016288578, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.03196627783589065, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.032254207548685375, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.032543977922759953, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.03283727108500898, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.033277182327583435, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.03373017037753016, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.03455020680557937, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.03539452499710023, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.036034171120263636, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.03646633171010762, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.03683798984158784, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.037221356038935484, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.03721078197006136, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.036717791836708785, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.03612820585258305, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0358947990834713, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.03627953972667455, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.03703540242742747, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.036344714388251306, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0315117962192744, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.016777646687696688, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0035666846109961626, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0005720613866287749, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0002640555502148345, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.00021170521646126872, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.00019447449170911568, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.00013028751061028743, "train/grad_034_lr5.1e+00_wd1.0e+00": 6.43673474564821e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 8.608172176536754e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 3.0085355786013678e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0010962262035555171, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.00020403223320816552, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0, "train/grad_042_lr1.9e+01_wd1.0e+00": 4.4847512050288156e-05, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.6479434370994568, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.6464831233024597, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.6446906924247742, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.6431620717048645, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.6419934034347534, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.6405279636383057, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.639316201210022, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.6381722092628479, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.6371197700500488, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.6367259621620178, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.6363713145256042, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.6357842087745667, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.6358161568641663, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.639270007610321, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.6462172269821167, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.6536365151405334, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.6606448292732239, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.6666959524154663, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.6778154373168945, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.6895822882652283, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.6969373226165771, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.6915751695632935, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.6778231263160706, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.6926292777061462, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.725772500038147, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.929253876209259, "validation/loss_026_lr1.4e+00_wd1.0e+00": 1.3153260946273804, "validation/loss_027_lr1.6e+00_wd1.0e+00": 1.8315523862838745, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.161004066467285, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.201693058013916, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.23720121383667, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.372596025466919, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.342055082321167, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.263984203338623, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.992551326751709, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.183706045150757, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.2826530933380127, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.8263936042785645, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.6931473016738892, "validation/loss_039_lr1.2e+01_wd1.0e+00": 6.458869934082031, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_042_lr1.9e+01_wd1.0e+00": 5.704562664031982, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.6931473016738892, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.6060606060606061, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.6060606060606061, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.5757575757575758, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.5959595959595959, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.5959595959595959, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.5858585858585859, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.6161616161616161, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.6262626262626263, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.6363636363636364, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.6363636363636364, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.6666666666666666, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.6767676767676768, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.6565656565656566, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.6363636363636364, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.6161616161616161, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.6161616161616161, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.6363636363636364, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.6060606060606061, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.5858585858585859, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.5858585858585859, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.5656565656565656, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.6060606060606061, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.6363636363636364, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.5858585858585859, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.5555555555555556, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.6363636363636364, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.5858585858585859, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.5757575757575758, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.5858585858585859, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.5353535353535354, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.5656565656565656, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.6060606060606061, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.6565656565656566, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.6060606060606061, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.6161616161616161, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.6464646464646465, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.6060606060606061, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.5353535353535354, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.3939393939393939, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.6161616161616161, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.6060606060606061, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.3939393939393939, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.42070517629407356, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.42070517629407356, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.40532036613272315, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.44999999999999996, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.4648648648648649, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.45858343337334934, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.5162037037037037, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.5342657342657342, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.5416666666666666, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.5416666666666666, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.593505039193729, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.6098522167487685, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.6075093283582089, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.6071428571428572, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.5942622950819672, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.5980769230769231, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.6253153910849454, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.5954950235725511, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.5815895268529018, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.5831364896785458, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.5640552995391706, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.6001863932898416, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.6224576271186442, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.5747511786275536, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.5477574750830565, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.6354337152209493, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.5747511786275536, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.5595338983050847, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.564344746162928, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.5037053182214473, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.5385365853658537, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.5601002620485359, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.628968253968254, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.5718088055894421, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.5744343891402715, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.6157258511700122, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.576876712328767, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.4772727272727273, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.2826086956521739, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.553842504743833, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.5601002620485359, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.2826086956521739, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.5089743589743589, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.5089743589743589, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.483974358974359, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.5096153846153846, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.514102564102564, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.5057692307692307, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.5442307692307692, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.5570512820512821, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.5653846153846154, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.5653846153846154, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.6038461538461539, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.6166666666666667, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.608974358974359, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.6057692307692308, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.5935897435897436, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.5980769230769231, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.6282051282051282, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.5987179487179487, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.591025641025641, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.5955128205128206, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.5788461538461539, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.6076923076923078, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.6237179487179487, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.5775641025641025, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.5525641025641026, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.6551282051282051, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.5775641025641025, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.5602564102564103, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.5641025641025641, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.5044871794871795, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.5384615384615384, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.5628205128205128, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.6269230769230769, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.5717948717948718, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.5756410256410257, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.6141025641025641, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.5762820512820512, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.48653846153846153, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.5, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.5621794871794872, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.5, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.5, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.5628205128205128, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.5, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.5, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.5, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.5, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.5, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.5, "id_best": 25, "lr_best": 0.00035999999999999997, "wd_best": 0.05, "train/loss_best": 0.38462178349494935, "validation/loss_best": 0.929253876209259, "validation/acc_best": 0.6363636363636364, "validation/f1_best": 0.6354337152209493, "validation/bacc_best": 0.6551282051282051} +{"epoch": 8, "train/lr": 0.0002612959497061927, "train/loss": 0.4198732943832874, "train/grad": 0.1994880348443985, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.629490966796875, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.626922607421875, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.62324462890625, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.619879150390625, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.616982421875, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.613212890625, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.609400634765625, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.605631103515625, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.6010675048828125, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.59656005859375, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.5927056884765625, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.5875079345703125, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.5829498291015625, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.576939697265625, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.571826171875, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.5672396850585938, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.5606375122070313, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.5528898620605469, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.5451457214355468, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.5376451110839844, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.5262336730957031, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.5101625061035157, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.48279289245605467, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.4426723861694336, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.3697942662239075, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.16675382241606712, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.02557733029127121, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.004924944490194321, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0018417568504810334, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0005741220712661743, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0004489852488040924, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.0004008018970489502, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.0003227865695953369, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.00028112411499023435, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.0001306602358818054, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.00016931265592575072, "train/loss_036_lr7.1e+00_wd1.0e+00": 4.476457834243774e-05, "train/loss_037_lr8.3e+00_wd1.0e+00": 4.919812083244324e-05, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.69140625, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.2262314558029174e-05, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.69140625, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.69140625, "train/loss_042_lr1.9e+01_wd1.0e+00": 6.884500384330749e-05, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.69140625, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.69140625, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.69140625, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.69140625, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.69140625, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.69140625, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.03487374757416546, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.034888128344900904, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.0349528915155679, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.03502734161913395, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.03512906981166452, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.03529429302085191, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.03549273501615971, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.03572521110996604, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.03604520994238555, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.03642078165896237, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.036812123111449185, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.037406528908759354, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.037882788674905896, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.03837496487423778, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.03870670416392386, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.03889128270093352, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.03898633997421712, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.03930044597014785, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.040048334700986746, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.04055658248718828, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.04046801040414721, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.039681604411453006, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.03869066992308944, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.037978987880051135, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0366351708676666, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.030003077671863138, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.007631316719634924, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0016791479039238765, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0007100375492518651, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.00023098207286238902, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.00017331367380393203, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.00015539884032477857, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.00013773814325759303, "train/grad_033_lr4.3e+00_wd1.0e+00": 9.90150206484941e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 5.601147904599202e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 7.080279533511202e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 2.982375117170477e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 4.737416955222784e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0, "train/grad_039_lr1.2e+01_wd1.0e+00": 1.927370877235118e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0, "train/grad_042_lr1.9e+01_wd1.0e+00": 6.459005944332352e-05, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.6459587812423706, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.6446154713630676, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.6428265571594238, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.6412282586097717, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.6400797367095947, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.6387770771980286, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.637636125087738, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.6366583108901978, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.6358561515808105, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.6353884339332581, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.6352583169937134, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.635910153388977, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.6367643475532532, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.6387062668800354, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.6428937315940857, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.6502529978752136, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.6588904857635498, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.6621056795120239, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.6596934199333191, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.6576453447341919, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.6595368981361389, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.6733323931694031, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.7379595637321472, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.8291656970977783, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.9133665561676025, "validation/loss_025_lr1.2e+00_wd1.0e+00": 1.3626266717910767, "validation/loss_026_lr1.4e+00_wd1.0e+00": 1.8316714763641357, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.1412441730499268, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.351257562637329, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.2642343044281006, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.3246288299560547, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.4311206340789795, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.3926949501037598, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.3160083293914795, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.9554245471954346, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.2034757137298584, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.15761137008667, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.546863317489624, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.6931473016738892, "validation/loss_039_lr1.2e+01_wd1.0e+00": 5.80812406539917, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_042_lr1.9e+01_wd1.0e+00": 4.901339530944824, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.6931473016738892, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.5757575757575758, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.5959595959595959, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.5858585858585859, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.6161616161616161, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.6565656565656566, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.6565656565656566, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.6767676767676768, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.6767676767676768, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.6868686868686869, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.6868686868686869, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.6666666666666666, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.6666666666666666, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.6565656565656566, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.6363636363636364, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.6262626262626263, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.6161616161616161, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.6262626262626263, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.6161616161616161, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.6363636363636364, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.6363636363636364, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.6464646464646465, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.6363636363636364, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.5656565656565656, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.5555555555555556, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.6161616161616161, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.5858585858585859, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.6060606060606061, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.5757575757575758, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.5959595959595959, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.5454545454545454, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.5656565656565656, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.6060606060606061, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.6565656565656566, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.5959595959595959, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.6161616161616161, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.6565656565656566, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.5959595959595959, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.5454545454545454, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.3939393939393939, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.6060606060606061, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.6060606060606061, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.3939393939393939, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.40532036613272315, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.4648648648648649, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.47182823682498376, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.5269114688128773, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.5934782608695652, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.5934782608695652, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.6242884250474383, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.6242884250474383, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.6327629532128755, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.6327629532128755, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.6158730158730159, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.6158730158730159, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.6075093283582089, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.5968325791855204, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.5937673283797271, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.5980769230769231, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.6134852801519468, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.6014830508474576, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.6115954664341761, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.6115954664341761, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.6157258511700122, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.6224576271186442, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.5611792598701165, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.5555102040816327, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.6129629629629629, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.5796831314072693, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.589299010743538, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.5595338983050847, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.5769230769230769, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.5117808219178082, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.5385365853658537, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.5601002620485359, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.628968253968254, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.5634920634920635, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.5744343891402715, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.628968253968254, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.5684394071490846, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.48467322151532677, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.2826086956521739, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.5460317460317461, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.5601002620485359, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.2826086956521739, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.483974358974359, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.514102564102564, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.5102564102564102, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.5487179487179488, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.6, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.6, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.6256410256410256, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.6256410256410256, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.6339743589743589, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.6339743589743589, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.6173076923076923, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.6173076923076923, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.608974358974359, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.5967948717948718, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.592948717948718, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.5980769230769231, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.6153846153846154, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.6025641025641025, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.6102564102564102, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.6102564102564102, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.6141025641025641, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.6237179487179487, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.5698717948717948, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.583974358974359, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.625, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.5865384615384616, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.5897435897435896, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.5602564102564103, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.5769230769230769, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.5128205128205128, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.5384615384615384, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.5628205128205128, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.6269230769230769, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.5634615384615385, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.5756410256410257, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.6269230769230769, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.5679487179487179, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.49487179487179483, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.5, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.5538461538461539, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.5, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.5, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.5628205128205128, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.5, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.5, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.5, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.5, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.5, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.5, "id_best": 8, "lr_best": 2.2199999999999998e-05, "wd_best": 0.05, "train/loss_best": 0.6010675048828125, "validation/loss_best": 0.6358561515808105, "validation/acc_best": 0.6868686868686869, "validation/f1_best": 0.6327629532128755, "validation/bacc_best": 0.6339743589743589} +{"epoch": 9, "train/lr": 0.00023803200426111704, "train/loss": 0.40745608299970626, "train/grad": 0.2019690190255642, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.620364990234375, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.61786376953125, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.614306640625, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.611109619140625, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.60836181640625, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.604818115234375, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.60093017578125, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.597047119140625, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.592301025390625, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.587611083984375, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.5835833740234375, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.578172607421875, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.5737078857421875, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.56827880859375, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.5642840576171875, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.5613925170898437, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.557347412109375, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.5507070922851562, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.54140625, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.5312692260742188, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.5133104705810547, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.48666385650634764, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.4456661796569824, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.3649039179086685, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.22391689494252204, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.031919503062963483, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.005597180724143982, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0024579226970672607, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0012068511545658112, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.00046874597668647764, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.00035507306456565856, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.0003353804349899292, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.0002645416557788849, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.00022986263036727905, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.00013096287846565247, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.00016788914799690247, "train/loss_036_lr7.1e+00_wd1.0e+00": 4.418179392814636e-05, "train/loss_037_lr8.3e+00_wd1.0e+00": 4.9986094236373905e-05, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.69140625, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.127481460571289e-05, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.69140625, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.69140625, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.0001281242072582245, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.69140625, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.69140625, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.69140625, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.69140625, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.69140625, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.69140625, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.03485356933902949, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.03487675770651549, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.03493051364086568, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.03500332259107381, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.035077029475942254, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.035183018250390885, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.03528835145290941, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.03541309962980449, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.035598613624461, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.035793919190764426, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.03602066428866237, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.036428222456015645, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.03687567088752985, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.03759584439918399, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.03824762516655028, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.03885619402397424, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.03986841711681336, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.041451337924227116, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.042958250967785716, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.04378836334683001, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.043875758135691285, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.04388631205540151, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.043020820543169976, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.043078613625839354, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0377557317330502, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.010913782475690824, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0019042948533024174, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0008308591050445102, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0004110118599055568, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.00016708282682884601, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.00012929196405821132, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.00012064770438882988, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0001107506389143964, "train/grad_033_lr4.3e+00_wd1.0e+00": 8.391075079089205e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 5.160855015674315e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 6.207983167769271e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 2.9944056608570692e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 4.0474860905206355e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0, "train/grad_039_lr1.2e+01_wd1.0e+00": 2.3201919880305212e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.00010547208771860995, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.6451768279075623, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.643836259841919, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.6421446204185486, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.640778660774231, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.6396257877349854, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.6385249495506287, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.637576699256897, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.6368504166603088, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.6363394856452942, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.6362985372543335, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.6364902257919312, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.6376545429229736, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.6392253041267395, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.6426005363464355, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.6465529799461365, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.6497089862823486, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.6531550288200378, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.6569350361824036, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.6605338454246521, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.6631622314453125, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.6697933077812195, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.7003215551376343, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.7510837316513062, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.8906139135360718, "validation/loss_024_lr1.0e+00_wd1.0e+00": 1.211932897567749, "validation/loss_025_lr1.2e+00_wd1.0e+00": 1.7334449291229248, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.0668399333953857, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.2972023487091064, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.4618191719055176, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.319549322128296, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.38956356048584, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.466813802719116, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.4325015544891357, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.355912446975708, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.9267303943634033, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.2171614170074463, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.0547518730163574, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.3276472091674805, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.6931473016738892, "validation/loss_039_lr1.2e+01_wd1.0e+00": 5.263752460479736, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_042_lr1.9e+01_wd1.0e+00": 4.290250778198242, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.6931473016738892, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.5959595959595959, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.5959595959595959, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.6060606060606061, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.6161616161616161, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.6363636363636364, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.6565656565656566, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.6868686868686869, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.696969696969697, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.6868686868686869, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.6666666666666666, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.6666666666666666, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.6767676767676768, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.6363636363636364, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.6363636363636364, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.6262626262626263, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.6161616161616161, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.5959595959595959, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.6262626262626263, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.6363636363636364, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.6363636363636364, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.6363636363636364, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.6262626262626263, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.6161616161616161, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.5858585858585859, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.6262626262626263, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.6161616161616161, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.6161616161616161, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.5656565656565656, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.5959595959595959, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.5555555555555556, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.5656565656565656, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.6060606060606061, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.6565656565656566, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.5959595959595959, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.6161616161616161, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.6565656565656566, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.5959595959595959, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.5555555555555556, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.3939393939393939, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.6060606060606061, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.5858585858585859, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.3939393939393939, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.4648648648648649, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.4648648648648649, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.509090909090909, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.5269114688128773, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.5610837438423646, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.5934782608695652, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.6327629532128755, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.6413043478260869, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.6327629532128755, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.6158730158730159, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.6158730158730159, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.6305970149253731, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.5968325791855204, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.5968325791855204, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.5937673283797271, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.5853174603174602, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.5634920634920635, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.5985753424657534, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.6071428571428572, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.6071428571428572, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.6192307692307693, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.6162388685175484, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.6129629629629629, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.5858585858585859, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.6224100608184724, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.6014830508474576, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.6014830508474576, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.5471758323582597, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.5769230769230769, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.5198412698412699, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.5385365853658537, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.5601002620485359, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.628968253968254, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.5634920634920635, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.5744343891402715, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.628968253968254, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.5684394071490846, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.4920708955223881, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.2826086956521739, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.5460317460317461, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.5439838220424671, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.2826086956521739, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.514102564102564, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.514102564102564, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.5358974358974359, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.5487179487179488, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.5743589743589743, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.6, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.6339743589743589, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.6423076923076924, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.6339743589743589, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.6173076923076923, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.6173076923076923, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.6301282051282051, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.5967948717948718, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.5967948717948718, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.592948717948718, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.5846153846153845, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.5634615384615385, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.5974358974358974, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.6057692307692308, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.6057692307692308, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.6192307692307693, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.6198717948717949, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.625, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.6134615384615385, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.6333333333333333, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.6025641025641025, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.6025641025641025, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.5474358974358975, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.5769230769230769, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.5211538461538462, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.5384615384615384, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.5628205128205128, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.6269230769230769, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.5634615384615385, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.5756410256410257, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.6269230769230769, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.5679487179487179, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.5032051282051282, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.5, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.5538461538461539, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.5, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.5, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.5461538461538461, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.5, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.5, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.5, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.5, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.5, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.5, "id_best": 7, "lr_best": 1.8599999999999998e-05, "wd_best": 0.05, "train/loss_best": 0.597047119140625, "validation/loss_best": 0.6368504166603088, "validation/acc_best": 0.696969696969697, "validation/f1_best": 0.6413043478260869, "validation/bacc_best": 0.6423076923076924} +{"epoch": 10, "train/lr": 0.00021091808096876188, "train/loss": 0.39919273391366006, "train/grad": 0.1961754548549652, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.6395703125, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.63626220703125, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.63130615234375, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.626895751953125, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.6230712890625, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.6180987548828125, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.6130023193359375, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.6079840087890624, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.601888427734375, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.596046142578125, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.590731201171875, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.5835308837890625, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.577210693359375, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.5684439086914063, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.560343017578125, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.5528689575195312, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.5426747131347657, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.52933837890625, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.5123727416992188, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.4939576721191406, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.4662372589111328, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.43250484466552735, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.3724643516540527, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.2617211127281189, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.08484429642558097, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.0073023103177547455, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.002602158784866333, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0015454526245594026, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0008583760261535644, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0004147359728813171, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.00030670464038848875, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.00029737502336502075, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.00024158895015716553, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.00020160079002380372, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.00011972397565841675, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.0001608163118362427, "train/loss_036_lr7.1e+00_wd1.0e+00": 5.205303430557251e-05, "train/loss_037_lr8.3e+00_wd1.0e+00": 5.757614970207214e-05, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.69140625, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.348276019096374e-05, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.69140625, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.69140625, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.00022479519248008728, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.69140625, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.69140625, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.69140625, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.69140625, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.69140625, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.69140625, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.035286392187699675, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.03528513848781586, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.035298460433259606, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.03532847779802978, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.03536773761268705, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.03543029320891947, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.035531022725626825, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.035663295546546576, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.035917250509373846, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.03623542876914144, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.03659011594951153, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.03715023767203093, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.03763884414918721, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.0383106304705143, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.038884489103220406, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.03939162551891059, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.039975595059804615, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.04053781394381076, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.04127101787365973, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.041713000698946415, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.04203848118428141, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.041943932650610805, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.03957839768379927, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.035237026675604285, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.021318315542303026, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0024480621283873914, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0009074303176748799, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.000520369229489006, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0002808474322773691, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.00013551365505009015, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.00010226755779513041, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.00010101905843839631, "train/grad_032_lr3.7e+00_wd1.0e+00": 9.161201093775162e-05, "train/grad_033_lr4.3e+00_wd1.0e+00": 7.134640848562413e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 4.9573294909350807e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 5.442506005692849e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 3.1167229077091465e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 3.919160960720092e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0, "train/grad_039_lr1.2e+01_wd1.0e+00": 2.96265062152698e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.00014413911146164083, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.6442697644233704, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.6429055333137512, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.6411477327346802, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.6398255825042725, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.6385837197303772, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.6375036835670471, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.6366379261016846, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.6359474658966064, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.6358165740966797, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.6364357471466064, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.6374415159225464, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.639186441898346, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.6407738327980042, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.6438280940055847, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.6483999490737915, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.6534959673881531, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.6572985649108887, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.6557406187057495, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.6568081974983215, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.6690674424171448, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.7022700309753418, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.7331414222717285, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.767214298248291, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.9650439620018005, "validation/loss_024_lr1.0e+00_wd1.0e+00": 1.4949862957000732, "validation/loss_025_lr1.2e+00_wd1.0e+00": 1.9322166442871094, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.1944525241851807, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.397390127182007, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.5424437522888184, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.3586273193359375, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.441891670227051, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.502190113067627, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.468562364578247, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.393214464187622, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.9072043895721436, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.2342305183410645, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.969717264175415, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.1446404457092285, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.6931473016738892, "validation/loss_039_lr1.2e+01_wd1.0e+00": 4.815184593200684, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.8683314323425293, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.6931473016738892, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.5858585858585859, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.5959595959595959, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.6060606060606061, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.6161616161616161, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.6363636363636364, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.6464646464646465, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.6565656565656566, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.6666666666666666, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.6565656565656566, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.6464646464646465, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.6363636363636364, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.6363636363636364, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.6262626262626263, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.6363636363636364, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.6363636363636364, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.6262626262626263, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.6262626262626263, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.5959595959595959, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.6464646464646465, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.6868686868686869, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.6363636363636364, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.6262626262626263, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.6363636363636364, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.6262626262626263, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.6060606060606061, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.6161616161616161, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.6161616161616161, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.5656565656565656, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.6060606060606061, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.5555555555555556, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.5656565656565656, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.6060606060606061, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.6363636363636364, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.6060606060606061, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.6161616161616161, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.6464646464646465, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.5959595959595959, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.5555555555555556, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.3939393939393939, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.5959595959595959, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.5858585858585859, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.3939393939393939, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.4440487604437748, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.4648648648648649, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.509090909090909, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.5269114688128773, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.5518108651911469, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.5688689809630458, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.5767102615694165, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.593505039193729, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.5854679802955665, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.5688689809630458, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.5518108651911469, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.5610837438423646, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.5442329227323628, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.5610837438423646, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.5610837438423646, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.5442329227323628, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.5442329227323628, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.530360531309298, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.6157258511700122, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.6735453675140943, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.6299833887043189, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.6206896551724137, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.6022321428571429, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.5985753424657534, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.5980218636127017, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.5980769230769231, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.5980769230769231, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.5471758323582597, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.5855962219598583, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.5198412698412699, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.5385365853658537, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.5601002620485359, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.6115954664341761, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.5718088055894421, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.5744343891402715, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.6157258511700122, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.5729076790336497, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.5, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.2826086956521739, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.5382462686567164, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.5439838220424671, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.2826086956521739, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.5012820512820513, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.514102564102564, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.5358974358974359, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.5487179487179488, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.5698717948717948, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.5826923076923076, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.591025641025641, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.6038461538461539, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.5955128205128205, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.5826923076923076, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.5698717948717948, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.5743589743589743, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.5615384615384615, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.5743589743589743, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.5743589743589743, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.5615384615384615, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.5615384615384615, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.5410256410256411, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.6141025641025641, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.6743589743589744, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.6371794871794871, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.6288461538461538, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.6012820512820514, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.5974358974358974, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.6032051282051283, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.5980769230769231, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.5980769230769231, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.5474358974358975, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.5852564102564103, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.5211538461538462, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.5384615384615384, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.5628205128205128, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.6102564102564102, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.5717948717948718, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.5756410256410257, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.6141025641025641, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.5724358974358974, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.5076923076923077, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.5, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.5455128205128206, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.5, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.5, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.5461538461538461, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.5, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.5, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.5, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.5, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.5, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.5, "id_best": 19, "lr_best": 0.00013199999999999998, "wd_best": 0.05, "train/loss_best": 0.4939576721191406, "validation/loss_best": 0.6690674424171448, "validation/acc_best": 0.6868686868686869, "validation/f1_best": 0.6735453675140943, "validation/bacc_best": 0.6743589743589744} +{"epoch": 11, "train/lr": 0.00018113997589164516, "train/loss": 0.3912105030566454, "train/grad": 0.17835070744156836, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.62711181640625, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.62394775390625, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.6194140625, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.615321044921875, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.61162841796875, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.607060546875, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.602489013671875, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.5979156494140625, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.5924920654296875, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.5875738525390625, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.583187255859375, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.5775555419921875, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.5726065063476562, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.5657354736328125, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.5585354614257813, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.550723876953125, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.5394415283203124, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.5245918273925781, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.5054605865478515, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.48227142333984374, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.44807378768920897, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.4049361181259155, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.3220651865005493, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.18404160007834436, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.03301177084445953, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.004091280400753021, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.001779661476612091, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0011529897153377533, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.000628027468919754, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.00031481683254241943, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.00025158897042274473, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.00023358136415481566, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.00020674422383308412, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.00017161339521408082, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.00012616723775863648, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.0001247924566268921, "train/loss_036_lr7.1e+00_wd1.0e+00": 4.926532506942749e-05, "train/loss_037_lr8.3e+00_wd1.0e+00": 7.267788052558899e-05, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.69140625, "train/loss_039_lr1.2e+01_wd1.0e+00": 4.106581211090088e-05, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.69140625, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.69140625, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.00022235170006752015, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.69140625, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.69140625, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.69140625, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.69140625, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.69140625, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.69140625, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.03248502428643405, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.0325005161203444, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.03255772450473159, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.03261219921056181, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.0326757682627067, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.03277121908962727, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.03289301151409745, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.03306783158797771, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.03331277841236442, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.03364425002131611, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.03402015907224268, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.034650175217539075, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.035212665349245074, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.03573396374471485, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.03587231955956668, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.03603241404052824, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.036577676278539, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.03742578722536564, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.03816957295872271, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.038915178691968325, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.03972396966069937, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.03952921797521412, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.03689877385739237, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.03131462785648182, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.00997745594533626, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.001388831958975061, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0006047605814092094, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0003925486443404225, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.00021316192543963553, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.00011466010726508103, "train/grad_030_lr2.7e+00_wd1.0e+00": 8.722707578272093e-05, "train/grad_031_lr3.1e+00_wd1.0e+00": 8.471551647744491e-05, "train/grad_032_lr3.7e+00_wd1.0e+00": 8.077708741438983e-05, "train/grad_033_lr4.3e+00_wd1.0e+00": 6.439424284508277e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 4.724838236143114e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 4.973229748884478e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 3.217626826085507e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 4.1392488700608965e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0, "train/grad_039_lr1.2e+01_wd1.0e+00": 3.6721986227195026e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0001618391221990123, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.6438922882080078, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.642621636390686, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.6410040259361267, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.63981032371521, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.6389301419258118, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.6378887295722961, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.6371455192565918, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.6367193460464478, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.6364327073097229, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.6367093324661255, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.6373130679130554, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.6389559507369995, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.6409599781036377, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.6443801522254944, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.6483822464942932, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.652277946472168, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.6560684442520142, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.6597514152526855, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.6660023927688599, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.6819712519645691, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.7195756435394287, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.76614910364151, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.863284170627594, "validation/loss_023_lr8.5e-01_wd1.0e+00": 1.1607927083969116, "validation/loss_024_lr1.0e+00_wd1.0e+00": 1.7146711349487305, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.0553371906280518, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.290156364440918, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.475351572036743, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.6048622131347656, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.392892599105835, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.4849305152893066, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.5279133319854736, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.4948859214782715, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.4236390590667725, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.8933632373809814, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.2489583492279053, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.901038885116577, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.01362943649292, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.6931473016738892, "validation/loss_039_lr1.2e+01_wd1.0e+00": 4.467877388000488, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.585008382797241, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.6931473016738892, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.5858585858585859, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.6060606060606061, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.6060606060606061, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.6161616161616161, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.6262626262626263, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.6363636363636364, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.6464646464646465, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.6666666666666666, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.6666666666666666, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.6666666666666666, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.6565656565656566, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.6565656565656566, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.6363636363636364, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.6464646464646465, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.6464646464646465, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.6262626262626263, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.6161616161616161, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.6262626262626263, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.6363636363636364, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.6161616161616161, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.6363636363636364, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.6363636363636364, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.6161616161616161, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.5959595959595959, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.5959595959595959, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.6060606060606061, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.6161616161616161, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.5656565656565656, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.5959595959595959, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.5555555555555556, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.5656565656565656, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.6060606060606061, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.6363636363636364, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.6060606060606061, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.6161616161616161, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.6464646464646465, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.5959595959595959, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.5555555555555556, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.3939393939393939, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.5858585858585859, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.5959595959595959, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.3939393939393939, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.4440487604437748, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.4711683331050541, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.4975927130774236, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.5162037037037037, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.5233571893298634, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.5416666666666666, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.5594405594405594, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.593505039193729, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.6016339470796245, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.6090702405169319, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.6008064516129032, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.6075093283582089, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.5909090909090909, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.5991902834008097, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.5925925925925926, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.5616848151250449, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.553842504743833, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.5762868710237131, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.5909090909090909, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.553842504743833, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.5844216417910448, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.5909090909090909, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.5980769230769231, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.5864661654135339, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.5864661654135339, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.589299010743538, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.5980769230769231, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.5471758323582597, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.5769230769230769, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.5198412698412699, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.5385365853658537, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.5601002620485359, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.6115954664341761, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.5718088055894421, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.5744343891402715, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.6157258511700122, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.5729076790336497, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.5, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.2826086956521739, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.53048004626952, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.5520361990950227, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.2826086956521739, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.5012820512820513, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.5224358974358974, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.5314102564102564, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.5442307692307692, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.5525641025641026, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.5653846153846154, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.5782051282051281, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.6038461538461539, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.6083333333333333, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.6128205128205129, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.6044871794871794, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.608974358974359, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.5923076923076923, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.6006410256410256, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.5961538461538461, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.5705128205128205, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.5621794871794872, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.5794871794871795, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.5923076923076923, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.5621794871794872, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.5878205128205128, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.5923076923076923, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.5980769230769231, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.5903846153846154, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.5903846153846154, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.5897435897435896, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.5980769230769231, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.5474358974358975, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.5769230769230769, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.5211538461538462, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.5384615384615384, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.5628205128205128, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.6102564102564102, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.5717948717948718, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.5756410256410257, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.6141025641025641, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.5724358974358974, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.5076923076923077, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.5, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.5371794871794873, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.5, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.5, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.5544871794871795, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.5, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.5, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.5, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.5, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.5, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.5, "id_best": 35, "lr_best": 0.0018, "wd_best": 0.05, "train/loss_best": 0.0001247924566268921, "validation/loss_best": 2.2489583492279053, "validation/acc_best": 0.6464646464646465, "validation/f1_best": 0.6157258511700122, "validation/bacc_best": 0.6141025641025641} +{"epoch": 12, "train/lr": 0.0001499999999999999, "train/loss": 0.37768906518816947, "train/grad": 0.18195888437330723, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.61608642578125, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.6129443359375, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.608466796875, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.604312744140625, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.600794677734375, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.596268310546875, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.59145751953125, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.586676025390625, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.580985107421875, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.5756427001953125, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.57080322265625, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.5644757080078125, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.5585205078125, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.549896240234375, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.541070556640625, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.5318533325195313, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.5179100036621094, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.49745513916015627, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.4671198272705078, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.432949390411377, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.3882701587677002, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.32964821100234987, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.23049888759851456, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.10861200422048568, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.014044624865055083, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.002857794314622879, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.0012893077731132507, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0008982555568218232, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0005017237365245819, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0002766084671020508, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.00023283153772354125, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.00022868767380714416, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.00020688682794570924, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.0001673506200313568, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.00011164441704750061, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.00012786462903022767, "train/loss_036_lr7.1e+00_wd1.0e+00": 5.761057138442993e-05, "train/loss_037_lr8.3e+00_wd1.0e+00": 6.38185441493988e-05, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.69140625, "train/loss_039_lr1.2e+01_wd1.0e+00": 4.539534449577331e-05, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.69140625, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.69140625, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.00028012335300445554, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.69140625, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.69140625, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.69140625, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.69140625, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.69140625, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.69140625, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.033300766539759934, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.033328819698654116, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.03341015656013042, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.03349635198246688, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.03357836935669184, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.033720580488443376, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.033876258777454496, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.03407210968900472, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.03435477468185127, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.03469309700652957, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.035047979294322434, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.03557791934814304, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.03605530836619437, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.03660697190556675, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.03703582686837763, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.03749525541905314, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.038379414463415744, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.03966745348647237, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.04077603125479072, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.04139870775863528, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.04118356095161289, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.040504314815625546, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.037566614067181946, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.025027364091947675, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.004998969064617995, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.001017858727282146, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0004794120631777332, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.000318227627685701, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0001839744661538134, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.00010103149958013091, "train/grad_030_lr2.7e+00_wd1.0e+00": 7.630003728081647e-05, "train/grad_031_lr3.1e+00_wd1.0e+00": 7.573499658064975e-05, "train/grad_032_lr3.7e+00_wd1.0e+00": 7.193461599854345e-05, "train/grad_033_lr4.3e+00_wd1.0e+00": 5.693517835425155e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 4.39279382908353e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 4.4929315565696014e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 3.3543621420051295e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 4.428251966828611e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0, "train/grad_039_lr1.2e+01_wd1.0e+00": 4.310097071809737e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.00016758101176264973, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.642960786819458, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.6416537165641785, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.6399539709091187, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.6386969685554504, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.6377482414245605, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.6367408633232117, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.6359980702400208, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.6356993913650513, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.635947585105896, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.6367427110671997, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.6382045745849609, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.6413156390190125, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.6458336710929871, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.6546694040298462, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.6639377474784851, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.6719915866851807, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.6816389560699463, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.692190945148468, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.7032876014709473, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.7273815274238586, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.7645469307899475, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.8087388873100281, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.948095440864563, "validation/loss_023_lr8.5e-01_wd1.0e+00": 1.310627818107605, "validation/loss_024_lr1.0e+00_wd1.0e+00": 1.8914178609848022, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.1384761333465576, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.357086420059204, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.5343596935272217, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.6513850688934326, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.4197216033935547, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.5158798694610596, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.54758620262146, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.5175178050994873, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.4441070556640625, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.8845224380493164, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.2646031379699707, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.8499233722686768, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.9161460399627686, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.6931473016738892, "validation/loss_039_lr1.2e+01_wd1.0e+00": 4.20097017288208, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.4180800914764404, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.6931473016738892, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.5757575757575758, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.6060606060606061, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.6161616161616161, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.6262626262626263, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.6565656565656566, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.6767676767676768, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.696969696969697, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.6868686868686869, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.6767676767676768, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.6565656565656566, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.6565656565656566, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.6464646464646465, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.6262626262626263, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.6060606060606061, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.6060606060606061, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.6161616161616161, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.6161616161616161, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.6262626262626263, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.6565656565656566, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.6565656565656566, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.6363636363636364, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.6161616161616161, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.5959595959595959, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.5959595959595959, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.6060606060606061, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.6161616161616161, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.6161616161616161, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.5656565656565656, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.5959595959595959, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.5555555555555556, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.5656565656565656, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.6060606060606061, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.6363636363636364, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.6060606060606061, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.6161616161616161, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.6464646464646465, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.5858585858585859, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.5555555555555556, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.3939393939393939, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.5858585858585859, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.6060606060606061, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.3939393939393939, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.45231822971548996, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.509090909090909, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.5269114688128773, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.5442329227323628, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.5854679802955665, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.6173913043478261, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.6413043478260869, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.6327629532128755, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.6242884250474383, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.6008064516129032, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.6008064516129032, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.577490549932935, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.5442329227323628, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.509090909090909, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.509090909090909, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.5162037037037037, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.5162037037037037, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.5342657342657342, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.5854679802955665, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.5854679802955665, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.5695652173913044, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.5613339552238805, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.5520361990950227, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.5634920634920635, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.5980218636127017, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.6014830508474576, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.5980769230769231, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.5471758323582597, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.5769230769230769, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.5198412698412699, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.5385365853658537, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.5601002620485359, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.6115954664341761, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.5718088055894421, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.5744343891402715, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.6157258511700122, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.5599999999999999, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.5, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.2826086956521739, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.53048004626952, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.5662285136501517, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.2826086956521739, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.49743589743589745, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.5358974358974359, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.5487179487179488, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.5615384615384615, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.5955128205128205, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.6211538461538462, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.6423076923076924, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.6339743589743589, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.6256410256410256, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.6044871794871794, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.6044871794871794, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.5871794871794872, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.5615384615384615, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.5358974358974359, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.5358974358974359, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.5442307692307692, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.5442307692307692, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.5570512820512821, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.5955128205128205, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.5955128205128205, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.5788461538461538, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.5666666666666667, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.5544871794871795, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.5634615384615385, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.6032051282051283, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.6025641025641025, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.5980769230769231, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.5474358974358975, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.5769230769230769, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.5211538461538462, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.5384615384615384, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.5628205128205128, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.6102564102564102, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.5717948717948718, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.5756410256410257, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.6141025641025641, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.5596153846153846, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.5076923076923077, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.5, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.5371794871794873, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.5, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.5, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.5673076923076923, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.5, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.5, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.5, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.5, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.5, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.5, "id_best": 6, "lr_best": 1.5899999999999997e-05, "wd_best": 0.05, "train/loss_best": 0.59145751953125, "validation/loss_best": 0.6359980702400208, "validation/acc_best": 0.696969696969697, "validation/f1_best": 0.6413043478260869, "validation/bacc_best": 0.6423076923076924} +{"epoch": 13, "train/lr": 0.00011886002410835478, "train/loss": 0.36388186924159527, "train/grad": 0.17169549159705638, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.603287353515625, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.599832763671875, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.59463623046875, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.589993896484375, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.5856689453125, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.5804962158203125, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.5748870849609375, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.5691790771484375, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.562152099609375, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.5552642822265625, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.5487738037109375, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.5399481201171875, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.531949462890625, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.5209426879882812, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.5112139892578125, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.501846923828125, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.4881793212890625, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.4668068695068359, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.4325236129760742, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.39450620651245116, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.34322341918945315, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.27518621683120725, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.1641694849729538, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.05861042350530624, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.00855835661292076, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.002018952667713165, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.0010010437667369843, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0006909532845020294, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.000397244393825531, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0002477802336215973, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.00019129708409309387, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.00018915593624114992, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.00017613887786865234, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.0001405368745326996, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.00010643810033798217, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.00011153042316436768, "train/loss_036_lr7.1e+00_wd1.0e+00": 6.294667720794677e-05, "train/loss_037_lr8.3e+00_wd1.0e+00": 6.553664803504944e-05, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.69140625, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.6313533782958985e-05, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.69140625, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.69140625, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.00028292521834373475, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.69140625, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.69140625, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.69140625, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.69140625, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.69140625, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.69140625, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.03205716205760836, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.03204246016219258, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.0320573739008978, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.032074554557912055, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.03210120071191341, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.03215345555450767, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.03221938587259501, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.0322997062606737, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.03246585166081786, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.03267570157069713, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.03290537224151194, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.03329588358290494, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.03366719282697886, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.03420049455016851, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.034719669092446566, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.03532296286895871, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.03641754717566073, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.037902884148061276, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.03906718974467367, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.03975791865494102, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.039686794858425856, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.03826392420101911, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.032143639002460984, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.01806028940132819, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.003125005941838026, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0007748510249075479, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.00038427760107879295, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.00026213400946289766, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.00015709009454440093, "train/grad_029_lr2.3e+00_wd1.0e+00": 9.196102626447101e-05, "train/grad_030_lr2.7e+00_wd1.0e+00": 6.990015089286316e-05, "train/grad_031_lr3.1e+00_wd1.0e+00": 6.990577120632225e-05, "train/grad_032_lr3.7e+00_wd1.0e+00": 6.595253112664068e-05, "train/grad_033_lr4.3e+00_wd1.0e+00": 5.354299753889791e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 4.215863595845803e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 4.2278917912881295e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 3.295290656808447e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 4.6761424113697105e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0, "train/grad_039_lr1.2e+01_wd1.0e+00": 4.7340528965773565e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.00016086644362673042, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.6425043940544128, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.6413446068763733, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.6397011280059814, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.6383313536643982, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.6374513506889343, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.6364995837211609, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.6360571384429932, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.6358522176742554, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.6363227963447571, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.6373264193534851, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.6386396884918213, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.6412023305892944, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.6441656351089478, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.6492732763290405, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.6558716893196106, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.6637738943099976, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.6724877953529358, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.6726474761962891, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.6775930523872375, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.7054793238639832, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.7511935234069824, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.8131842017173767, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.9869179129600525, "validation/loss_023_lr8.5e-01_wd1.0e+00": 1.4132696390151978, "validation/loss_024_lr1.0e+00_wd1.0e+00": 1.958177924156189, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.199362277984619, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.409130573272705, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.574542999267578, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.6862740516662598, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.4414913654327393, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.5422656536102295, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.5635440349578857, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.536099910736084, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.464662551879883, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.8784360885620117, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.273367166519165, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.8104307651519775, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.8503241539001465, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.6931473016738892, "validation/loss_039_lr1.2e+01_wd1.0e+00": 4.01284122467041, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.30690336227417, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.6931473016738892, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.5858585858585859, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.5959595959595959, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.6161616161616161, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.6363636363636364, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.6565656565656566, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.6666666666666666, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.6868686868686869, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.6767676767676768, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.6767676767676768, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.6565656565656566, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.6464646464646465, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.6565656565656566, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.6464646464646465, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.6363636363636364, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.6262626262626263, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.6363636363636364, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.6161616161616161, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.6363636363636364, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.6262626262626263, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.6262626262626263, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.6464646464646465, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.6161616161616161, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.5858585858585859, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.6060606060606061, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.6060606060606061, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.6161616161616161, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.6161616161616161, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.5656565656565656, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.5757575757575758, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.5555555555555556, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.5656565656565656, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.6060606060606061, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.6363636363636364, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.6060606060606061, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.6161616161616161, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.6363636363636364, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.5858585858585859, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.5555555555555556, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.3939393939393939, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.5858585858585859, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.6060606060606061, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.3939393939393939, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.45858343337334934, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.4907407407407407, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.5269114688128773, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.5518108651911469, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.5854679802955665, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.6016339470796245, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.6257773442263139, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.6173913043478261, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.6173913043478261, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.5934782608695652, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.577490549932935, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.5934782608695652, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.577490549932935, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.5610837438423646, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.5442329227323628, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.5518108651911469, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.5269114688128773, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.5695652173913044, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.5693121693121693, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.5826592229691239, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.6107178968655207, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.5744343891402715, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.5599999999999999, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.5954950235725511, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.5954950235725511, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.5980769230769231, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.5980769230769231, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.5471758323582597, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.5515530629853321, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.5198412698412699, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.5385365853658537, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.5601002620485359, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.6115954664341761, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.5718088055894421, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.5801339285714285, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.6022321428571429, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.5599999999999999, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.5, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.2826086956521739, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.5375413011279481, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.5662285136501517, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.2826086956521739, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.5057692307692307, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.5230769230769231, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.5487179487179488, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.5698717948717948, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.5955128205128205, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.6083333333333333, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.6294871794871795, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.6211538461538462, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.6211538461538462, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.6, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.5871794871794872, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.6, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.5871794871794872, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.5743589743589743, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.5615384615384615, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.5698717948717948, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.5487179487179488, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.5788461538461538, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.575, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.583974358974359, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.6096153846153847, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.5756410256410257, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.5596153846153846, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.5987179487179487, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.5987179487179487, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.5980769230769231, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.5980769230769231, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.5474358974358975, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.5512820512820513, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.5211538461538462, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.5384615384615384, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.5628205128205128, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.6102564102564102, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.5717948717948718, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.5801282051282051, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.6012820512820514, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.5596153846153846, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.5076923076923077, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.5, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.5416666666666666, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.5, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.5, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.5673076923076923, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.5, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.5, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.5, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.5, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.5, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.5, "id_best": 6, "lr_best": 1.5899999999999997e-05, "wd_best": 0.05, "train/loss_best": 0.5748870849609375, "validation/loss_best": 0.6360571384429932, "validation/acc_best": 0.6868686868686869, "validation/f1_best": 0.6257773442263139, "validation/bacc_best": 0.6294871794871795} +{"epoch": 14, "train/lr": 8.9081919031238e-05, "train/loss": 0.3654424412548542, "train/grad": 0.19163000509142875, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.612257080078125, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.608990478515625, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.604322509765625, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.600064697265625, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.59612548828125, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.5912255859375, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.5860113525390624, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.5806884765625, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.5742022705078125, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.5677850341796875, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.561842041015625, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.5534869384765625, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.5458648681640625, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.5349176025390625, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.5238299560546875, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.511881103515625, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.4934782409667969, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.4646261596679688, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.42153839111328123, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.3802623748779297, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.32699477195739746, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.25185125827789306, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.13553147584199907, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.043378684222698215, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.007329394817352295, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.0019147896766662598, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.0009485742449760437, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0006882810592651367, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.00040250048041343687, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.00023996025323867797, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.00017129495739936828, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.00018509820103645324, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.00016195327043533325, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.0001397097110748291, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.0001073339581489563, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.00010648593306541442, "train/loss_036_lr7.1e+00_wd1.0e+00": 4.234269261360169e-05, "train/loss_037_lr8.3e+00_wd1.0e+00": 9.273111820220947e-05, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.69140625, "train/loss_039_lr1.2e+01_wd1.0e+00": 5.163922905921936e-05, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.69140625, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.69140625, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.00028477922081947325, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.69140625, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.69140625, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.69140625, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.69140625, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.69140625, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.69140625, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.035605971016921104, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.03564560132101178, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.03573444017674774, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.035827929200604555, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.03592786771245301, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.03606745667289943, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.03623064779676497, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.03640729796607047, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.03667322114109993, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.036954107559286055, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.037235459322109817, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.037670221314765516, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.03811271312646568, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.03886506744194776, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.03977528209332377, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.04085959577932954, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.042423950070515276, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.04380565247964114, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.04481602355372161, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.04515853344462812, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.043923526052385566, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.04019985327031463, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.031408518864773215, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.01401636969530955, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0026678568619536236, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0006670401906740154, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.00033643042017502013, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0002431419004642521, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.00014404508541701944, "train/grad_029_lr2.3e+00_wd1.0e+00": 8.329150952704367e-05, "train/grad_030_lr2.7e+00_wd1.0e+00": 6.546611588873929e-05, "train/grad_031_lr3.1e+00_wd1.0e+00": 6.451078799727838e-05, "train/grad_032_lr3.7e+00_wd1.0e+00": 6.115030541877786e-05, "train/grad_033_lr4.3e+00_wd1.0e+00": 4.961890258528001e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 4.072767541856592e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 3.862532906850902e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 3.294659101314324e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 4.877829215885754e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0, "train/grad_039_lr1.2e+01_wd1.0e+00": 5.3660826241053174e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.00015823863344621714, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.6423195004463196, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.6410620212554932, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.6394413709640503, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.6382283568382263, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.6372753977775574, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.6362681984901428, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.6357952952384949, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.6357319951057434, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.6361225247383118, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.6369733214378357, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.6382110118865967, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.6402883529663086, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.642536461353302, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.6456522345542908, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.6490939855575562, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.6528957486152649, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.6586908102035522, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.6679432988166809, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.6887128353118896, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.7249906659126282, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.7814640998840332, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.8585408329963684, "validation/loss_022_lr7.2e-01_wd1.0e+00": 1.0595759153366089, "validation/loss_023_lr8.5e-01_wd1.0e+00": 1.51582670211792, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.0463523864746094, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.2428574562072754, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.4484469890594482, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.608334541320801, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.7129287719726562, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.4592490196228027, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.564284563064575, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.5836403369903564, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.5560498237609863, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.4858245849609375, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.8837552070617676, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.2822425365448, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.7852783203125, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.8044121265411377, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.6931473016738892, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.8866283893585205, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.2426095008850098, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.6931473016738892, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.5858585858585859, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.5959595959595959, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.6161616161616161, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.6363636363636364, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.6464646464646465, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.6767676767676768, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.6868686868686869, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.6767676767676768, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.6767676767676768, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.6565656565656566, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.6565656565656566, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.6565656565656566, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.6363636363636364, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.6464646464646465, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.6363636363636364, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.6262626262626263, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.6262626262626263, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.6464646464646465, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.6262626262626263, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.6161616161616161, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.6363636363636364, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.6161616161616161, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.5858585858585859, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.5959595959595959, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.6060606060606061, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.6161616161616161, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.6161616161616161, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.5656565656565656, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.5757575757575758, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.5555555555555556, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.5656565656565656, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.6060606060606061, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.6363636363636364, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.5959595959595959, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.6161616161616161, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.6363636363636364, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.5858585858585859, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.5555555555555556, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.3939393939393939, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.5858585858585859, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.6161616161616161, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.3939393939393939, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.45858343337334934, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.4907407407407407, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.5162037037037037, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.5518108651911469, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.5688689809630458, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.6098522167487685, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.6257773442263139, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.6173913043478261, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.6242884250474383, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.6008064516129032, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.6075093283582089, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.6075093283582089, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.5909090909090909, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.5991902834008097, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.5909090909090909, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.5826592229691239, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.5826592229691239, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.5991902834008097, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.5762868710237131, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.5681818181818182, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.5844216417910448, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.5681818181818182, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.5551780821917809, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.5836837678721615, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.5980218636127017, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.5980769230769231, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.5980769230769231, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.5471758323582597, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.5515530629853321, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.5198412698412699, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.5385365853658537, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.5601002620485359, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.6115954664341761, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.5580357142857143, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.5801339285714285, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.6022321428571429, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.5599999999999999, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.5, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.2826086956521739, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.5375413011279481, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.5801339285714285, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.2826086956521739, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.5057692307692307, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.5230769230769231, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.5442307692307692, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.5698717948717948, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.5826923076923076, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.6166666666666667, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.6294871794871795, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.6211538461538462, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.6256410256410256, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.6044871794871794, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.608974358974359, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.608974358974359, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.5923076923076923, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.6006410256410256, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.5923076923076923, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.583974358974359, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.583974358974359, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.6006410256410256, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.5794871794871795, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.5711538461538461, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.5878205128205128, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.5711538461538461, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.5551282051282052, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.5858974358974358, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.6032051282051283, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.5980769230769231, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.5980769230769231, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.5474358974358975, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.5512820512820513, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.5211538461538462, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.5384615384615384, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.5628205128205128, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.6102564102564102, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.558974358974359, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.5801282051282051, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.6012820512820514, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.5596153846153846, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.5076923076923077, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.5, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.5416666666666666, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.5, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.5, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.5801282051282051, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.5, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.5, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.5, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.5, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.5, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.5, "id_best": 6, "lr_best": 1.5899999999999997e-05, "wd_best": 0.05, "train/loss_best": 0.5860113525390624, "validation/loss_best": 0.6357952952384949, "validation/acc_best": 0.6868686868686869, "validation/f1_best": 0.6257773442263139, "validation/bacc_best": 0.6294871794871795} +{"epoch": 15, "train/lr": 6.196799573888289e-05, "train/loss": 0.35959796100854874, "train/grad": 0.18069978499785067, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.60402099609375, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.600177001953125, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.5944677734375, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.589698486328125, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.5855096435546875, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.5801702880859375, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.5748846435546875, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.5696051025390625, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.5632501220703126, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.55707763671875, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.5514434814453125, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.543558349609375, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.5363055419921875, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.5256924438476562, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.5145001220703125, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.502340087890625, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.4835841369628906, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.4540379333496094, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.4100713348388672, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.36639238357543946, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.30652192115783694, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.22774370074272154, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.11708816260099411, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.029411131143569948, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.005371157377958298, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.0015130738914012909, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.0007641774415969849, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0005514554679393769, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0003578752279281616, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0002252177894115448, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.00017702192068099975, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.00018325716257095337, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.00016789644956588745, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.00012666717171669006, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.0001026645302772522, "train/loss_035_lr6.0e+00_wd1.0e+00": 9.876996278762818e-05, "train/loss_036_lr7.1e+00_wd1.0e+00": 5.466863512992859e-05, "train/loss_037_lr8.3e+00_wd1.0e+00": 8.248627185821534e-05, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.69140625, "train/loss_039_lr1.2e+01_wd1.0e+00": 5.884543061256409e-05, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.69140625, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.69140625, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.0002566009759902954, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.69140625, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.69140625, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.69140625, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.69140625, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.69140625, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.69140625, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.0330379341961816, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.03307995194103569, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.03317213435191661, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.033265664796344935, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.033373265713453296, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.033540165009908376, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.03373578663449735, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.033962035616859794, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.03428514391183853, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.034638470057398084, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.03498982263728976, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.03551632753573358, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.0360384724335745, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.03682671123649925, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.03765552601311356, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.03857270401902497, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.03993127749301493, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.04156577289570123, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.043037941991351546, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.04370080941356719, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.04284915786236525, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.03966232903767377, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.02995092140743509, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.010935979005298578, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0020349983192863874, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0005617339255695697, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.000291685748306918, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.00021163387729757231, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.00013004243336581567, "train/grad_029_lr2.3e+00_wd1.0e+00": 7.967411779645772e-05, "train/grad_030_lr2.7e+00_wd1.0e+00": 6.0543146482814335e-05, "train/grad_031_lr3.1e+00_wd1.0e+00": 6.11549897189434e-05, "train/grad_032_lr3.7e+00_wd1.0e+00": 5.770433896486793e-05, "train/grad_033_lr4.3e+00_wd1.0e+00": 4.6314965868532457e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 3.974525281137176e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 3.680737605463946e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 3.251032253849928e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 4.8639712960891754e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0, "train/grad_039_lr1.2e+01_wd1.0e+00": 5.5020952356201745e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0001446067297274567, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.64192795753479, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.6407346725463867, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.6391388773918152, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.6379885673522949, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.6372320652008057, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.6363098621368408, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.635802149772644, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.6357776522636414, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.6362850666046143, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.6373146176338196, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.6386502385139465, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.6410890817642212, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.6434080600738525, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.6469416618347168, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.6501612663269043, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.6537994146347046, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.6587881445884705, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.6659086346626282, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.6878466606140137, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.7261084318161011, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.7852960228919983, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.8802592158317566, "validation/loss_022_lr7.2e-01_wd1.0e+00": 1.1278437376022339, "validation/loss_023_lr8.5e-01_wd1.0e+00": 1.5874663591384888, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.0860397815704346, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.2712082862854004, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.4735093116760254, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.6324851512908936, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.731267213821411, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.47176456451416, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.582522392272949, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.591458797454834, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.5685112476348877, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.4960100650787354, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.8831422328948975, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.291478157043457, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.769251585006714, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.77528977394104, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.6931473016738892, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.802614212036133, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.2034640312194824, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.6931473016738892, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.5959595959595959, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.6060606060606061, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.6262626262626263, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.6565656565656566, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.6767676767676768, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.6868686868686869, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.6868686868686869, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.6666666666666666, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.6767676767676768, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.6565656565656566, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.6363636363636364, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.6262626262626263, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.6262626262626263, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.6363636363636364, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.6363636363636364, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.6464646464646465, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.6262626262626263, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.6363636363636364, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.6262626262626263, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.6262626262626263, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.6363636363636364, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.6363636363636364, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.5858585858585859, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.6060606060606061, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.6060606060606061, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.6161616161616161, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.6161616161616161, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.5656565656565656, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.5757575757575758, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.5555555555555556, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.5656565656565656, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.6060606060606061, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.6363636363636364, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.6060606060606061, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.6161616161616161, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.6363636363636364, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.5858585858585859, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.5555555555555556, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.3939393939393939, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.5858585858585859, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.6161616161616161, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.3939393939393939, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.4907407407407407, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.509090909090909, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.5442329227323628, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.5934782608695652, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.6173913043478261, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.6327629532128755, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.6327629532128755, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.6158730158730159, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.6305970149253731, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.6136363636363636, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.5968325791855204, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.5826592229691239, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.5826592229691239, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.5909090909090909, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.5968325791855204, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.6107178968655207, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.5884732052578362, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.6022321428571429, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.5826592229691239, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.5826592229691239, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.5909090909090909, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.5844216417910448, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.5375413011279481, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.589299010743538, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.5980218636127017, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.5980769230769231, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.5980769230769231, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.5471758323582597, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.5515530629853321, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.5198412698412699, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.5385365853658537, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.5601002620485359, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.6115954664341761, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.5718088055894421, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.5801339285714285, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.6022321428571429, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.5599999999999999, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.5, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.2826086956521739, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.5375413011279481, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.5801339285714285, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.2826086956521739, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.5230769230769231, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.5358974358974359, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.5615384615384615, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.6, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.6211538461538462, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.6339743589743589, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.6339743589743589, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.6173076923076923, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.6301282051282051, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.6134615384615385, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.5967948717948718, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.583974358974359, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.583974358974359, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.5923076923076923, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.5967948717948718, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.6096153846153847, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.5884615384615385, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.6012820512820514, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.583974358974359, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.583974358974359, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.5923076923076923, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.5878205128205128, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.5416666666666666, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.5897435897435896, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.6032051282051283, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.5980769230769231, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.5980769230769231, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.5474358974358975, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.5512820512820513, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.5211538461538462, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.5384615384615384, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.5628205128205128, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.6102564102564102, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.5717948717948718, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.5801282051282051, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.6012820512820514, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.5596153846153846, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.5076923076923077, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.5, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.5416666666666666, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.5, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.5, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.5801282051282051, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.5, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.5, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.5, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.5, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.5, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.5, "id_best": 5, "lr_best": 1.3499999999999998e-05, "wd_best": 0.05, "train/loss_best": 0.5801702880859375, "validation/loss_best": 0.6363098621368408, "validation/acc_best": 0.6868686868686869, "validation/f1_best": 0.6327629532128755, "validation/bacc_best": 0.6339743589743589} +{"epoch": 16, "train/lr": 3.870405029380728e-05, "train/loss": 0.3574369677901268, "train/grad": 0.17359554471448063, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.6112451171875, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.60760498046875, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.602216796875, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.5974383544921875, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.5930572509765625, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.5872906494140625, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.581163330078125, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.5748870849609375, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.5670941162109375, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.559542236328125, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.55258056640625, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.5429388427734375, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.534029541015625, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.5212503051757813, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.508121337890625, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.49367340087890627, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.4714395141601562, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.4369065856933594, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.3862776184082031, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.3396186447143555, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.2808989524841309, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.20486300110816955, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.10383866548538208, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.025106858611106873, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.004465164542198181, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.0013015711307525636, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.0006744508445262909, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.000515146255493164, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.000313800722360611, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.00019726812839508057, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.00015777796506881713, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.0001659846305847168, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.00013687878847122193, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.00012465447187423706, "train/loss_034_lr5.1e+00_wd1.0e+00": 8.605927228927613e-05, "train/loss_035_lr6.0e+00_wd1.0e+00": 9.269699454307556e-05, "train/loss_036_lr7.1e+00_wd1.0e+00": 6.057232618331909e-05, "train/loss_037_lr8.3e+00_wd1.0e+00": 8.759289979934693e-05, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.69140625, "train/loss_039_lr1.2e+01_wd1.0e+00": 5.024150013923645e-05, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.69140625, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.69140625, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.00024197503924369812, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.69140625, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.69140625, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.69140625, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.69140625, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.69140625, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.69140625, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.03341358252801001, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.03339364619925618, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.033386271130293604, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.03339355477131903, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.03341857462190092, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.03346570826135576, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.03352273176424205, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.03361509601585567, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.03377115306910127, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.03395927643869072, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.03413834886625409, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.03445840499829501, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.03478388687595725, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.035339676532894375, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.03600896040443331, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.03681351814419031, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.038020512824878096, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.039489332395605745, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.04087725770194083, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.04120629494544119, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.04022153858095408, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.03633457589428872, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.025578311765566467, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.009087387032341212, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0017446098048822024, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0005288084309722763, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0002774784961002297, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.00020218337604092085, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.00012055853718266007, "train/grad_029_lr2.3e+00_wd1.0e+00": 7.428605439372405e-05, "train/grad_030_lr2.7e+00_wd1.0e+00": 5.606449904917099e-05, "train/grad_031_lr3.1e+00_wd1.0e+00": 5.7469342773401874e-05, "train/grad_032_lr3.7e+00_wd1.0e+00": 5.384491045788309e-05, "train/grad_033_lr4.3e+00_wd1.0e+00": 4.3561599868553456e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 3.799061701556639e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 3.462934705112275e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 3.154116024688847e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 4.799618803417616e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0, "train/grad_039_lr1.2e+01_wd1.0e+00": 5.4027354967414176e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.00013845163842120202, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.6418850421905518, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.6407268047332764, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.6391562819480896, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.6379371285438538, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.6370914578437805, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.6363106369972229, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.6358298659324646, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.6358953714370728, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.6363168358802795, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.6374588012695312, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.6387883424758911, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.6413000822067261, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.6437270045280457, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.6473046541213989, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.6510569453239441, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.6549551486968994, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.6602826118469238, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.6685646772384644, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.693668782711029, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.7330540418624878, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.7900695204734802, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.8723204731941223, "validation/loss_022_lr7.2e-01_wd1.0e+00": 1.1234990358352661, "validation/loss_023_lr8.5e-01_wd1.0e+00": 1.6262034177780151, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.106961250305176, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.289735794067383, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.4912383556365967, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.6489334106445312, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.7452003955841064, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.4781899452209473, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.591228723526001, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.600938081741333, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.576425313949585, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.5084609985351562, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.886225461959839, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.298494577407837, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.7587645053863525, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.7590723037719727, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.6931473016738892, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.755756378173828, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.190129041671753, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.6931473016738892, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.5858585858585859, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.6060606060606061, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.6262626262626263, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.6565656565656566, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.6666666666666666, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.696969696969697, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.696969696969697, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.6767676767676768, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.6666666666666666, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.6767676767676768, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.6565656565656566, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.6565656565656566, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.6464646464646465, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.6464646464646465, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.6161616161616161, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.6262626262626263, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.6363636363636364, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.6363636363636364, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.6161616161616161, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.6262626262626263, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.6262626262626263, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.5959595959595959, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.5959595959595959, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.6161616161616161, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.5959595959595959, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.6161616161616161, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.6161616161616161, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.5656565656565656, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.5757575757575758, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.5555555555555556, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.5656565656565656, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.6060606060606061, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.6363636363636364, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.5959595959595959, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.6161616161616161, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.6363636363636364, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.5858585858585859, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.5454545454545454, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.3939393939393939, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.5858585858585859, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.6161616161616161, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.3939393939393939, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.47182823682498376, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.509090909090909, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.5442329227323628, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.5854679802955665, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.6016339470796245, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.6413043478260869, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.6413043478260869, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.6242884250474383, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.6158730158730159, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.6305970149253731, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.6075093283582089, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.6075093283582089, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.5991902834008097, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.5991902834008097, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.5613339552238805, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.5762868710237131, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.5909090909090909, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.5844216417910448, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.5681818181818182, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.5826592229691239, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.5884732052578362, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.5580357142857143, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.5729076790336497, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.6044995794785535, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.5864661654135339, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.5980769230769231, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.5980769230769231, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.5471758323582597, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.5515530629853321, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.5198412698412699, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.5385365853658537, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.5601002620485359, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.6115954664341761, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.5580357142857143, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.5801339285714285, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.6022321428571429, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.5599999999999999, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.48467322151532677, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.2826086956521739, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.5375413011279481, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.5801339285714285, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.2826086956521739, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.5102564102564102, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.5358974358974359, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.5615384615384615, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.5955128205128205, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.6083333333333333, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.6423076923076924, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.6423076923076924, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.6256410256410256, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.6173076923076923, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.6301282051282051, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.608974358974359, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.608974358974359, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.6006410256410256, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.6006410256410256, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.5666666666666667, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.5794871794871795, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.5923076923076923, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.5878205128205128, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.5711538461538461, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.583974358974359, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.5884615384615385, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.558974358974359, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.5724358974358974, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.6070512820512821, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.5903846153846154, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.5980769230769231, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.5980769230769231, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.5474358974358975, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.5512820512820513, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.5211538461538462, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.5384615384615384, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.5628205128205128, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.6102564102564102, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.558974358974359, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.5801282051282051, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.6012820512820514, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.5596153846153846, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.49487179487179483, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.5, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.5416666666666666, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.5, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.5, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.5801282051282051, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.5, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.5, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.5, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.5, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.5, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.5, "id_best": 5, "lr_best": 1.3499999999999998e-05, "wd_best": 0.05, "train/loss_best": 0.5872906494140625, "validation/loss_best": 0.6363106369972229, "validation/acc_best": 0.696969696969697, "validation/f1_best": 0.6413043478260869, "validation/bacc_best": 0.6423076923076924} +{"epoch": 17, "train/lr": 2.030750443206766e-05, "train/loss": 0.35825024418532847, "train/grad": 0.1716482412815094, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.5987744140625, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.595814208984375, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.591444091796875, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.58760498046875, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.58423583984375, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.5797235107421875, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.57528076171875, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.5708905029296875, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.5653302001953125, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.5597979736328125, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.5546337890625, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.54718505859375, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.539876708984375, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.5287753295898437, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.5165008544921875, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.502564697265625, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.48077117919921875, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.4481065368652344, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.40403308868408205, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.35980791091918946, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.29852508068084715, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.21569707334041596, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.09611520603299141, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.02137197121977806, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.004258742034435273, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.0013826759159564972, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.0007431881129741669, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0005430805683135986, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.000348132997751236, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.00021041467785835267, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0001585632562637329, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.00015907421708106996, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.0001447734236717224, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.0001236395537853241, "train/loss_034_lr5.1e+00_wd1.0e+00": 9.343057870864869e-05, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.00010075047612190247, "train/loss_036_lr7.1e+00_wd1.0e+00": 6.260201334953308e-05, "train/loss_037_lr8.3e+00_wd1.0e+00": 8.931666612625121e-05, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.69140625, "train/loss_039_lr1.2e+01_wd1.0e+00": 6.279081106185913e-05, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.69140625, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.69140625, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.0002638858556747437, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.69140625, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.69140625, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.69140625, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.69140625, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.69140625, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.69140625, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.03244945811107755, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.03248528050258756, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.03255712683312595, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.0326265869429335, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.03269845531322062, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.03281019353773445, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.032937141335569325, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.033082853648811576, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.033303015702404085, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.033533612764440474, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.03377150841988623, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.03413773528765887, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.034522258951328696, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.03513073508627713, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.03588110161945224, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.0367872515367344, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.03814459489192814, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.039788507707417015, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.041113635627552866, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.041181007958948614, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.039754024529829624, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.03606589780189097, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.02426220227498561, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.007842841751116793, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0015968418920238037, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.00047836198300501567, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.00025760529100807614, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.00018949996934679802, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.00011567537583687226, "train/grad_029_lr2.3e+00_wd1.0e+00": 7.282720591319958e-05, "train/grad_030_lr2.7e+00_wd1.0e+00": 5.574618995979108e-05, "train/grad_031_lr3.1e+00_wd1.0e+00": 5.556423886446282e-05, "train/grad_032_lr3.7e+00_wd1.0e+00": 5.3120434163247406e-05, "train/grad_033_lr4.3e+00_wd1.0e+00": 4.251430927979527e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 3.676342871926863e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 3.369961496673568e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 3.102441522941035e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 4.9125685294484355e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0, "train/grad_039_lr1.2e+01_wd1.0e+00": 5.656687351944356e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0001318286327517626, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.6419298052787781, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.640756368637085, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.6391595602035522, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.6379238367080688, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.637107253074646, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.63630610704422, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.635779082775116, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.6358319520950317, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.6364054679870605, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.6373869776725769, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.6388424038887024, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.6411395072937012, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.6437182426452637, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.6473165154457092, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.6508654952049255, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.6547591686248779, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.6600704193115234, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.6689028739929199, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.695189893245697, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.7350156307220459, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.7933905124664307, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.8775005340576172, "validation/loss_022_lr7.2e-01_wd1.0e+00": 1.1387927532196045, "validation/loss_023_lr8.5e-01_wd1.0e+00": 1.65006422996521, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.1264359951019287, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.3002383708953857, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.5016701221466064, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.657541275024414, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.7525742053985596, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.4839138984680176, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.599045991897583, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.6050832271575928, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.5814125537872314, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.5152664184570312, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.8880703449249268, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.303232431411743, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.7537009716033936, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.7524290084838867, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.6931473016738892, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.7293083667755127, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.18233323097229, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.6931473016738892, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.5757575757575758, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.6060606060606061, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.6262626262626263, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.6565656565656566, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.6666666666666666, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.696969696969697, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.696969696969697, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.6767676767676768, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.6666666666666666, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.6767676767676768, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.6565656565656566, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.6363636363636364, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.6363636363636364, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.6464646464646465, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.6262626262626263, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.6363636363636364, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.6262626262626263, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.6464646464646465, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.6161616161616161, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.6262626262626263, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.6262626262626263, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.6060606060606061, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.6161616161616161, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.6060606060606061, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.5959595959595959, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.6161616161616161, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.6161616161616161, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.5656565656565656, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.5757575757575758, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.5555555555555556, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.5656565656565656, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.6060606060606061, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.6363636363636364, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.5959595959595959, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.6161616161616161, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.6363636363636364, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.5858585858585859, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.5454545454545454, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.3939393939393939, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.5858585858585859, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.6161616161616161, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.3939393939393939, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.45231822971548996, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.509090909090909, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.5442329227323628, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.5854679802955665, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.6016339470796245, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.6413043478260869, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.6413043478260869, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.6242884250474383, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.6158730158730159, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.6305970149253731, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.6075093283582089, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.5909090909090909, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.5909090909090909, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.5991902834008097, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.5762868710237131, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.5909090909090909, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.5826592229691239, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.5991902834008097, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.5681818181818182, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.5937673283797271, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.5937673283797271, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.5718088055894421, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.5980769230769231, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.5954950235725511, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.5864661654135339, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.5980769230769231, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.5980769230769231, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.5471758323582597, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.5515530629853321, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.5198412698412699, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.5385365853658537, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.5601002620485359, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.6115954664341761, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.5580357142857143, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.5801339285714285, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.6022321428571429, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.5599999999999999, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.48467322151532677, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.2826086956521739, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.5375413011279481, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.5801339285714285, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.2826086956521739, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.49743589743589745, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.5358974358974359, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.5615384615384615, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.5955128205128205, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.6083333333333333, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.6423076923076924, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.6423076923076924, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.6256410256410256, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.6173076923076923, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.6301282051282051, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.608974358974359, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.5923076923076923, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.5923076923076923, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.6006410256410256, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.5794871794871795, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.5923076923076923, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.583974358974359, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.6006410256410256, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.5711538461538461, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.592948717948718, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.592948717948718, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.5717948717948718, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.5980769230769231, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.5987179487179487, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.5903846153846154, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.5980769230769231, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.5980769230769231, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.5474358974358975, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.5512820512820513, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.5211538461538462, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.5384615384615384, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.5628205128205128, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.6102564102564102, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.558974358974359, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.5801282051282051, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.6012820512820514, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.5596153846153846, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.49487179487179483, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.5, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.5416666666666666, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.5, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.5, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.5801282051282051, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.5, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.5, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.5, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.5, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.5, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.5, "id_best": 5, "lr_best": 1.3499999999999998e-05, "wd_best": 0.05, "train/loss_best": 0.5797235107421875, "validation/loss_best": 0.63630610704422, "validation/acc_best": 0.696969696969697, "validation/f1_best": 0.6413043478260869, "validation/bacc_best": 0.6423076923076924} +{"epoch": 18, "train/lr": 7.5829098008590064e-06, "train/loss": 0.36674560263752937, "train/grad": 0.169215022996068, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.622724609375, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.61940185546875, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.61467041015625, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.610245361328125, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.6063818359375, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.601317138671875, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.59580078125, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.590255126953125, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.5833477783203125, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.576483154296875, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.5702569580078125, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.561656494140625, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.5538067626953125, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.5425515747070313, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.5311602783203125, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.5186875915527344, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.49923812866210937, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.4689960479736328, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.42577907562255857, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.37831830978393555, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.31138867378234864, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.22964025259017945, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.10503103852272033, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.0220251502096653, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.004360616058111191, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.0013462075591087342, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.0006894947588443756, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0005338972806930542, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0003260062634944916, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.00020498290657997131, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.00016290903091430663, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.00016055673360824586, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.00013996347784996034, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.00011735618114471436, "train/loss_034_lr5.1e+00_wd1.0e+00": 9.753897786140441e-05, "train/loss_035_lr6.0e+00_wd1.0e+00": 9.456366300582886e-05, "train/loss_036_lr7.1e+00_wd1.0e+00": 5.099594593048096e-05, "train/loss_037_lr8.3e+00_wd1.0e+00": 9.694203734397888e-05, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.69140625, "train/loss_039_lr1.2e+01_wd1.0e+00": 6.825998425483704e-05, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.69140625, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.69140625, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.0002639961242675781, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.69140625, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.69140625, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.69140625, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.69140625, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.69140625, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.69140625, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.033158075623214246, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.033149623894132674, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.03316810919437557, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.03320167484693229, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.03323436102364212, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.033299241552595046, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.033363640401512386, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.033467158277053384, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.03361658187350258, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.03379044390516356, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.03395968697965145, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.03422349617118016, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.03448750274023041, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.034931073184125125, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.03550189550034702, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.03617341322358698, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.0371768510947004, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.03826651035808027, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.03896479327697307, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.03880335622467101, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.037314559258520605, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.03347744897007942, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.023268697066232562, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.007459476537187584, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.001513989959785249, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.000460290854498453, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.00024951712426627635, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.00018354649228058406, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0001130450880555145, "train/grad_029_lr2.3e+00_wd1.0e+00": 7.146048830236395e-05, "train/grad_030_lr2.7e+00_wd1.0e+00": 5.528895988391014e-05, "train/grad_031_lr3.1e+00_wd1.0e+00": 5.545234231703944e-05, "train/grad_032_lr3.7e+00_wd1.0e+00": 5.1495326415533784e-05, "train/grad_033_lr4.3e+00_wd1.0e+00": 4.209708189591765e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 3.5736808558795016e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 3.3093174979512694e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 3.1409819039254215e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 4.8061711357831885e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0, "train/grad_039_lr1.2e+01_wd1.0e+00": 5.4945661245753286e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.00013132256045764735, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.6419262886047363, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.6406527757644653, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.6391015648841858, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.6378623247146606, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.6371229290962219, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.6362026333808899, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.6358546018600464, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.6357757449150085, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.6364398002624512, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.6375131011009216, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.6388646364212036, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.6414469480514526, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.6439532041549683, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.6476893424987793, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.6513867378234863, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.6553321480751038, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.660914421081543, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.6697806119918823, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.6961540579795837, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.7365226149559021, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.7948440909385681, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.8792217373847961, "validation/loss_022_lr7.2e-01_wd1.0e+00": 1.142227292060852, "validation/loss_023_lr8.5e-01_wd1.0e+00": 1.65812349319458, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.1290597915649414, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.305290699005127, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.504528045654297, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.6617507934570312, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.7553067207336426, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.4865241050720215, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.6017990112304688, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.6087899208068848, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.5841739177703857, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.517810344696045, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.890298843383789, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.3049840927124023, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.7519161701202393, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.7506794929504395, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.6931473016738892, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.721881866455078, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.178997039794922, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.6931473016738892, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.5757575757575758, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.6060606060606061, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.6262626262626263, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.6565656565656566, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.6666666666666666, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.696969696969697, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.696969696969697, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.6767676767676768, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.6666666666666666, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.6666666666666666, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.6565656565656566, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.6565656565656566, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.6565656565656566, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.6363636363636364, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.6161616161616161, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.6262626262626263, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.6363636363636364, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.6363636363636364, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.6161616161616161, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.6363636363636364, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.6262626262626263, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.6060606060606061, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.5959595959595959, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.6161616161616161, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.5959595959595959, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.6161616161616161, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.6161616161616161, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.5656565656565656, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.5757575757575758, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.5555555555555556, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.5656565656565656, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.6060606060606061, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.6363636363636364, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.5959595959595959, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.6161616161616161, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.6363636363636364, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.5858585858585859, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.5454545454545454, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.3939393939393939, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.5858585858585859, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.6161616161616161, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.3939393939393939, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.45231822971548996, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.509090909090909, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.5442329227323628, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.5854679802955665, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.6016339470796245, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.6413043478260869, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.6413043478260869, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.6242884250474383, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.6158730158730159, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.6158730158730159, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.6075093283582089, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.6075093283582089, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.6075093283582089, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.5844216417910448, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.5613339552238805, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.5762868710237131, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.5909090909090909, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.5844216417910448, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.5681818181818182, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.6022321428571429, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.5884732052578362, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.5718088055894421, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.5729076790336497, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.6044995794785535, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.5864661654135339, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.5980769230769231, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.5980769230769231, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.5471758323582597, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.5515530629853321, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.5198412698412699, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.5385365853658537, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.5601002620485359, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.6115954664341761, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.5580357142857143, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.5801339285714285, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.6022321428571429, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.5599999999999999, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.48467322151532677, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.2826086956521739, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.5375413011279481, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.5801339285714285, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.2826086956521739, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.49743589743589745, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.5358974358974359, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.5615384615384615, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.5955128205128205, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.6083333333333333, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.6423076923076924, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.6423076923076924, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.6256410256410256, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.6173076923076923, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.6173076923076923, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.608974358974359, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.608974358974359, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.608974358974359, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.5878205128205128, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.5666666666666667, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.5794871794871795, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.5923076923076923, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.5878205128205128, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.5711538461538461, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.6012820512820514, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.5884615384615385, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.5717948717948718, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.5724358974358974, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.6070512820512821, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.5903846153846154, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.5980769230769231, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.5980769230769231, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.5474358974358975, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.5512820512820513, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.5211538461538462, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.5384615384615384, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.5628205128205128, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.6102564102564102, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.558974358974359, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.5801282051282051, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.6012820512820514, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.5596153846153846, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.49487179487179483, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.5, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.5416666666666666, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.5, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.5, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.5801282051282051, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.5, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.5, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.5, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.5, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.5, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.5, "id_best": 5, "lr_best": 1.3499999999999998e-05, "wd_best": 0.05, "train/loss_best": 0.601317138671875, "validation/loss_best": 0.6362026333808899, "validation/acc_best": 0.696969696969697, "validation/f1_best": 0.6413043478260869, "validation/bacc_best": 0.6423076923076924} +{"epoch": 19, "train/lr": 1.0867618231465446e-06, "train/loss": 0.3572455137223005, "train/grad": 0.17495374156162144, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.610281982421875, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.606468505859375, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.60086669921875, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.59556396484375, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.590833740234375, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.584501953125, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.577799072265625, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.571153564453125, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.562938232421875, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.5550054931640624, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.5479400634765625, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.5380841064453125, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.5292010498046875, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.5167733764648438, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.5042306518554688, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.49058990478515624, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.4705680847167969, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.4407107543945312, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.4008404541015625, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.35692897796630857, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.29106189727783205, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.2101318897306919, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.10029891327023506, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.02107755735516548, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.004273494631052017, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.0013276585936546326, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.0007089062035083771, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0005187961459159851, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0003217296302318573, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0002038300037384033, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.00014711663126945495, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.0001508842408657074, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.00012932002544403077, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.00011376500129699708, "train/loss_034_lr5.1e+00_wd1.0e+00": 8.172467350959778e-05, "train/loss_035_lr6.0e+00_wd1.0e+00": 9.01728868484497e-05, "train/loss_036_lr7.1e+00_wd1.0e+00": 5.8280378580093385e-05, "train/loss_037_lr8.3e+00_wd1.0e+00": 7.563740015029907e-05, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.69140625, "train/loss_039_lr1.2e+01_wd1.0e+00": 6.323829293251038e-05, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.69140625, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.69140625, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.0002589060366153717, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.69140625, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.69140625, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.69140625, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.69140625, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.69140625, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.69140625, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.03467608722858131, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.034635853730142115, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.034612624919973314, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.03459446219261736, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.03459542417898774, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.03461093324236572, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.03463739150669426, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.03469035354442895, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.034790704171173276, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.034921967699192466, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.035042627900838855, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.03528563479892909, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.035532499393448234, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.035978187690488994, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.03657015199307352, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.03728861761279404, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.03845175647642463, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.03990736248902976, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.04116171998903155, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.041116210920736196, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.03917901494074613, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.034014228847809136, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.02294642724446021, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.007516362046007998, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0015859350419486873, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.00048349337041145193, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0002570342410399462, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.00018897932224717806, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.00011612344029344968, "train/grad_029_lr2.3e+00_wd1.0e+00": 7.179350090154913e-05, "train/grad_030_lr2.7e+00_wd1.0e+00": 5.418156983978406e-05, "train/grad_031_lr3.1e+00_wd1.0e+00": 5.47476557585469e-05, "train/grad_032_lr3.7e+00_wd1.0e+00": 5.216843763264478e-05, "train/grad_033_lr4.3e+00_wd1.0e+00": 4.131500084440631e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 3.6103752238432206e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 3.3939595268748235e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 3.132915618550669e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 4.876595953533069e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0, "train/grad_039_lr1.2e+01_wd1.0e+00": 5.3272270945186054e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.00013178815835090062, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.6418765187263489, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.6406543850898743, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.6390862464904785, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.6378628611564636, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.6370962858200073, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.6362319588661194, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.6358627080917358, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.6357501149177551, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.6363869309425354, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.6375402808189392, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.638881504535675, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.6414198279380798, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.6440187096595764, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.6477574706077576, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.6514447331428528, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.65518718957901, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.6606218814849854, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.6694393754005432, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.6961069107055664, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.7362273931503296, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.7948489189147949, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.8789669275283813, "validation/loss_022_lr7.2e-01_wd1.0e+00": 1.142662763595581, "validation/loss_023_lr8.5e-01_wd1.0e+00": 1.6587755680084229, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.1313695907592773, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.30521297454834, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.5053632259368896, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.6620607376098633, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.7566261291503906, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.4873549938201904, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.602306365966797, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.60898756980896, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.5849967002868652, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.5178935527801514, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.890197992324829, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.3061156272888184, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.751924514770508, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.748594284057617, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.6931473016738892, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.7206451892852783, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.178877592086792, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.6931473016738892, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.6931473016738892, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.5757575757575758, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.6060606060606061, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.6262626262626263, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.6565656565656566, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.6666666666666666, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.696969696969697, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.696969696969697, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.6767676767676768, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.6666666666666666, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.6666666666666666, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.6565656565656566, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.6565656565656566, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.6464646464646465, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.6464646464646465, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.6161616161616161, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.6262626262626263, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.6262626262626263, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.6363636363636364, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.6161616161616161, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.6262626262626263, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.6262626262626263, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.6060606060606061, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.6060606060606061, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.6161616161616161, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.5959595959595959, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.6161616161616161, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.6161616161616161, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.5656565656565656, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.5757575757575758, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.5555555555555556, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.5656565656565656, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.6060606060606061, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.6363636363636364, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.5959595959595959, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.6161616161616161, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.6363636363636364, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.5858585858585859, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.5454545454545454, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.3939393939393939, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.5858585858585859, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.6161616161616161, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.3939393939393939, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.3939393939393939, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.45231822971548996, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.509090909090909, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.5442329227323628, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.5854679802955665, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.6016339470796245, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.6413043478260869, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.6413043478260869, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.6242884250474383, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.6158730158730159, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.6158730158730159, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.6075093283582089, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.6075093283582089, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.5991902834008097, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.5991902834008097, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.5613339552238805, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.5762868710237131, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.5826592229691239, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.5844216417910448, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.5681818181818182, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.5937673283797271, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.5937673283797271, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.5718088055894421, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.5855962219598583, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.6044995794785535, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.5864661654135339, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.5980769230769231, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.5980769230769231, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.5471758323582597, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.5515530629853321, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.5198412698412699, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.5385365853658537, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.5601002620485359, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.6115954664341761, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.5580357142857143, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.5801339285714285, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.6022321428571429, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.5599999999999999, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.48467322151532677, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.2826086956521739, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.5375413011279481, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.5801339285714285, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.2826086956521739, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.2826086956521739, "validation/bacc_000_lr2.0e-02_wd1.0e+00": 0.49743589743589745, "validation/bacc_001_lr2.3e-02_wd1.0e+00": 0.5358974358974359, "validation/bacc_002_lr2.8e-02_wd1.0e+00": 0.5615384615384615, "validation/bacc_003_lr3.3e-02_wd1.0e+00": 0.5955128205128205, "validation/bacc_004_lr3.8e-02_wd1.0e+00": 0.6083333333333333, "validation/bacc_005_lr4.5e-02_wd1.0e+00": 0.6423076923076924, "validation/bacc_006_lr5.3e-02_wd1.0e+00": 0.6423076923076924, "validation/bacc_007_lr6.2e-02_wd1.0e+00": 0.6256410256410256, "validation/bacc_008_lr7.4e-02_wd1.0e+00": 0.6173076923076923, "validation/bacc_009_lr8.7e-02_wd1.0e+00": 0.6173076923076923, "validation/bacc_010_lr1.0e-01_wd1.0e+00": 0.608974358974359, "validation/bacc_011_lr1.2e-01_wd1.0e+00": 0.608974358974359, "validation/bacc_012_lr1.4e-01_wd1.0e+00": 0.6006410256410256, "validation/bacc_013_lr1.7e-01_wd1.0e+00": 0.6006410256410256, "validation/bacc_014_lr2.0e-01_wd1.0e+00": 0.5666666666666667, "validation/bacc_015_lr2.3e-01_wd1.0e+00": 0.5794871794871795, "validation/bacc_016_lr2.7e-01_wd1.0e+00": 0.583974358974359, "validation/bacc_017_lr3.2e-01_wd1.0e+00": 0.5878205128205128, "validation/bacc_018_lr3.8e-01_wd1.0e+00": 0.5711538461538461, "validation/bacc_019_lr4.4e-01_wd1.0e+00": 0.592948717948718, "validation/bacc_020_lr5.2e-01_wd1.0e+00": 0.592948717948718, "validation/bacc_021_lr6.1e-01_wd1.0e+00": 0.5717948717948718, "validation/bacc_022_lr7.2e-01_wd1.0e+00": 0.5852564102564103, "validation/bacc_023_lr8.5e-01_wd1.0e+00": 0.6070512820512821, "validation/bacc_024_lr1.0e+00_wd1.0e+00": 0.5903846153846154, "validation/bacc_025_lr1.2e+00_wd1.0e+00": 0.5980769230769231, "validation/bacc_026_lr1.4e+00_wd1.0e+00": 0.5980769230769231, "validation/bacc_027_lr1.6e+00_wd1.0e+00": 0.5474358974358975, "validation/bacc_028_lr1.9e+00_wd1.0e+00": 0.5512820512820513, "validation/bacc_029_lr2.3e+00_wd1.0e+00": 0.5211538461538462, "validation/bacc_030_lr2.7e+00_wd1.0e+00": 0.5384615384615384, "validation/bacc_031_lr3.1e+00_wd1.0e+00": 0.5628205128205128, "validation/bacc_032_lr3.7e+00_wd1.0e+00": 0.6102564102564102, "validation/bacc_033_lr4.3e+00_wd1.0e+00": 0.558974358974359, "validation/bacc_034_lr5.1e+00_wd1.0e+00": 0.5801282051282051, "validation/bacc_035_lr6.0e+00_wd1.0e+00": 0.6012820512820514, "validation/bacc_036_lr7.1e+00_wd1.0e+00": 0.5596153846153846, "validation/bacc_037_lr8.3e+00_wd1.0e+00": 0.49487179487179483, "validation/bacc_038_lr9.8e+00_wd1.0e+00": 0.5, "validation/bacc_039_lr1.2e+01_wd1.0e+00": 0.5416666666666666, "validation/bacc_040_lr1.4e+01_wd1.0e+00": 0.5, "validation/bacc_041_lr1.6e+01_wd1.0e+00": 0.5, "validation/bacc_042_lr1.9e+01_wd1.0e+00": 0.5801282051282051, "validation/bacc_043_lr2.2e+01_wd1.0e+00": 0.5, "validation/bacc_044_lr2.6e+01_wd1.0e+00": 0.5, "validation/bacc_045_lr3.1e+01_wd1.0e+00": 0.5, "validation/bacc_046_lr3.6e+01_wd1.0e+00": 0.5, "validation/bacc_047_lr4.3e+01_wd1.0e+00": 0.5, "validation/bacc_048_lr5.0e+01_wd1.0e+00": 0.5, "id_best": 5, "lr_best": 1.3499999999999998e-05, "wd_best": 0.05, "train/loss_best": 0.584501953125, "validation/loss_best": 0.6362319588661194, "validation/acc_best": 0.696969696969697, "validation/f1_best": 0.6413043478260869, "validation/bacc_best": 0.6423076923076924} diff --git a/input_space_v3/flat_lr1e-3_1/eval_v2/ppmi_dx__patch__logistic/config.yaml b/input_space_v3/flat_lr1e-3_1/eval_v2/ppmi_dx__patch__logistic/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..e832cbd7923cb348e68ed4b83a514e6d68fb3240 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_1/eval_v2/ppmi_dx__patch__logistic/config.yaml @@ -0,0 +1,30 @@ +output_root: experiments/input_space_v3/output +name_prefix: eval_logistic +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_1; eval v2 (ppmi_dx patch logistic) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: input_space_v3/flat_lr1e-3_1/eval_v2/ppmi_dx__patch__logistic +model: flat_mae +representation: patch +dataset: ppmi_dx +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/ppmi_dx__patch__logistic +remote_dir: null diff --git a/input_space_v3/flat_lr1e-3_1/eval_v2/ppmi_dx__patch__logistic/eval_table.csv b/input_space_v3/flat_lr1e-3_1/eval_v2/ppmi_dx__patch__logistic/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..1e56923d0654057c5d6fa8cefafa81bdb895e569 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_1/eval_v2/ppmi_dx__patch__logistic/eval_table.csv @@ -0,0 +1,203 @@ +model,repr,clf,dataset,trial,C,split,acc,acc_std,f1,f1_std,bacc,bacc_std +flat_mae,patch,logistic,ppmi_dx,,0.3593813663804626,train,0.9181494661921709,0.011064951447822668,0.9118713864950365,0.012138338714686921,0.9042676818272891,0.012907935326269217 +flat_mae,patch,logistic,ppmi_dx,,0.3593813663804626,test,0.66,0.044639798386641484,0.6212121212121212,0.049409768647047506,0.6186186186186187,0.04763897163197838 +flat_mae,patch,logistic,ppmi_dx,1,2.782559402207126,train,0.998220640569395,0.0017880605760429366,0.9981216765874674,0.0018845770403339685,0.9985549132947977,0.001452153242393256 +flat_mae,patch,logistic,ppmi_dx,1,2.782559402207126,test,0.57,0.04722465034280295,0.5459824728117411,0.048481250952047916,0.5462648556876061,0.04855677552170009 +flat_mae,patch,logistic,ppmi_dx,2,0.005994842503189409,train,0.7206405693950177,0.01637064829678318,0.6758045729948596,0.020479722528993462,0.6704934703489617,0.018499232055921726 +flat_mae,patch,logistic,ppmi_dx,2,0.005994842503189409,test,0.68,0.04344607692300882,0.64349376114082,0.04975007092827599,0.6400679117147707,0.04706829817647831 +flat_mae,patch,logistic,ppmi_dx,3,0.005994842503189409,train,0.7473309608540926,0.01661613473210582,0.7072272360407954,0.020951039575510963,0.6991275958038964,0.01923357088880721 +flat_mae,patch,logistic,ppmi_dx,3,0.005994842503189409,test,0.66,0.042418184779643736,0.6155585707824514,0.05009765331277162,0.6137521222410866,0.04647180319063591 +flat_mae,patch,logistic,ppmi_dx,4,0.046415888336127774,train,0.7900355871886121,0.01615959767769297,0.7629404026538549,0.0192865726969072,0.7520739670306145,0.01854682337286981 +flat_mae,patch,logistic,ppmi_dx,4,0.046415888336127774,test,0.66,0.045224855997559564,0.6263736263736264,0.0499203647412052,0.6239388794567062,0.04801732732955611 +flat_mae,patch,logistic,ppmi_dx,5,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,5,166.81005372000556,test,0.56,0.04948932814253997,0.537620849096259,0.05084135870880222,0.5382003395585738,0.0513173291479043 +flat_mae,patch,logistic,ppmi_dx,6,0.3593813663804626,train,0.9092526690391459,0.012093854067850343,0.901781583789952,0.013377594012835435,0.893250909869407,0.014124330542510135 +flat_mae,patch,logistic,ppmi_dx,6,0.3593813663804626,test,0.59,0.04846000825422959,0.5670995670995671,0.050900663241427266,0.5674872665534805,0.051119845077975956 +flat_mae,patch,logistic,ppmi_dx,7,0.046415888336127774,train,0.8078291814946619,0.015187215813642737,0.7869328952356881,0.01763564490123595,0.7769615713979876,0.017529599137634667 +flat_mae,patch,logistic,ppmi_dx,7,0.046415888336127774,test,0.62,0.047312894648288015,0.5924495924495925,0.05031702328969495,0.5916808149405772,0.04955051908728715 +flat_mae,patch,logistic,ppmi_dx,8,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,8,166.81005372000556,test,0.61,0.04701861333557169,0.5983935742971888,0.047115919610913805,0.6039898132427843,0.04779095035607081 +flat_mae,patch,logistic,ppmi_dx,9,0.3593813663804626,train,0.9181494661921709,0.011538997603702675,0.9111248624862487,0.012853392546327756,0.901346071505031,0.013768433840214919 +flat_mae,patch,logistic,ppmi_dx,9,0.3593813663804626,test,0.6,0.045167669853557864,0.570999570999571,0.0480851296459321,0.5704584040747029,0.04727129431711301 +flat_mae,patch,logistic,ppmi_dx,10,2.782559402207126,train,0.994661921708185,0.003149438043986233,0.9943552194132241,0.0033339901002624552,0.993925283665168,0.0036361214844623396 +flat_mae,patch,logistic,ppmi_dx,10,2.782559402207126,test,0.63,0.047540042069817316,0.6161427533976553,0.048594098113166055,0.6201188455008488,0.04955561221768322 +flat_mae,patch,logistic,ppmi_dx,11,2.782559402207126,train,0.99644128113879,0.0025371319512418745,0.9962334964144495,0.002692687140194609,0.9953703703703703,0.0033006207328655835 +flat_mae,patch,logistic,ppmi_dx,11,2.782559402207126,test,0.62,0.04955989911208456,0.6006725514922235,0.05081797583002668,0.6018675721561969,0.050958726738892325 +flat_mae,patch,logistic,ppmi_dx,12,0.005994842503189409,train,0.7402135231316725,0.016249119283327975,0.7025420165020809,0.020122265905173613,0.6950867052023122,0.018725661164615087 +flat_mae,patch,logistic,ppmi_dx,12,0.005994842503189409,test,0.57,0.03631512632499024,0.46081504702194354,0.04394809350323639,0.4902376910016978,0.03688708663502455 +flat_mae,patch,logistic,ppmi_dx,13,0.046415888336127774,train,0.7953736654804271,0.016601769057290647,0.7734021927010473,0.019003980490011462,0.7642367801327339,0.018683344555513504 +flat_mae,patch,logistic,ppmi_dx,13,0.046415888336127774,test,0.66,0.04220379129888688,0.609375,0.05025468714859442,0.6086587436332768,0.045709315195201466 +flat_mae,patch,logistic,ppmi_dx,14,0.046415888336127774,train,0.800711743772242,0.016477728777022575,0.78064012490242,0.018727522929232215,0.7720509526867909,0.018569566762281577 +flat_mae,patch,logistic,ppmi_dx,14,0.046415888336127774,test,0.63,0.04476881057164687,0.5847828526540231,0.0506242815370244,0.5844651952461799,0.0476584391956827 +flat_mae,patch,logistic,ppmi_dx,15,0.005994842503189409,train,0.7241992882562278,0.01537247054470387,0.6769144607761323,0.019824070028468522,0.6716441875401413,0.017722982643938463 +flat_mae,patch,logistic,ppmi_dx,15,0.005994842503189409,test,0.69,0.04072885463648591,0.6343908479773559,0.052756144508267155,0.6328522920203735,0.046518326194705424 +flat_mae,patch,logistic,ppmi_dx,16,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,16,166.81005372000556,test,0.56,0.04869599983571545,0.5555555555555556,0.04837888346661797,0.5687606112054329,0.04999918691923091 +flat_mae,patch,logistic,ppmi_dx,17,0.005994842503189409,train,0.7295373665480427,0.016903680462885068,0.6875585205992509,0.021055110751474843,0.6811978163134232,0.019268612713112712 +flat_mae,patch,logistic,ppmi_dx,17,0.005994842503189409,test,0.62,0.04363220828699827,0.5703301673450927,0.049890256570154994,0.5713073005093379,0.04637235354757133 +flat_mae,patch,logistic,ppmi_dx,18,0.046415888336127774,train,0.8220640569395018,0.015407901036279729,0.8022240990990992,0.017809503735357373,0.7911314493684436,0.01756547948241028 +flat_mae,patch,logistic,ppmi_dx,18,0.046415888336127774,test,0.6,0.04586873008924489,0.5477159656264134,0.051195506583176995,0.5500848896434635,0.047604185612310876 +flat_mae,patch,logistic,ppmi_dx,19,0.3593813663804626,train,0.9234875444839857,0.011321690869088677,0.9180310631268677,0.01231315842166043,0.912639156497538,0.013080622417863964 +flat_mae,patch,logistic,ppmi_dx,19,0.3593813663804626,test,0.59,0.050379880904980315,0.5746446726838883,0.05153584786399316,0.5776740237691002,0.05257351725789684 +flat_mae,patch,logistic,ppmi_dx,20,0.046415888336127774,train,0.8042704626334519,0.0164511913408644,0.7818969531900481,0.019322405717719503,0.7714622136587455,0.019058198613147788 +flat_mae,patch,logistic,ppmi_dx,20,0.046415888336127774,test,0.6,0.04561238428321852,0.5477159656264134,0.05109057467709319,0.5500848896434635,0.04746836520995787 +flat_mae,patch,logistic,ppmi_dx,21,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,21,2.782559402207126,test,0.65,0.04461602850994248,0.6178622120318812,0.04936099984730498,0.615874363327674,0.04769561479162906 +flat_mae,patch,logistic,ppmi_dx,22,0.046415888336127774,train,0.8042704626334519,0.016319927347317593,0.7835191618108471,0.01872683069840713,0.774071397987583,0.018495278538966462 +flat_mae,patch,logistic,ppmi_dx,22,0.046415888336127774,test,0.61,0.04342726793156577,0.5555555555555556,0.04975917802341098,0.5581494057724957,0.045848984255488265 +flat_mae,patch,logistic,ppmi_dx,23,0.046415888336127774,train,0.8096085409252669,0.014413779678382862,0.7896787506776489,0.01676063886160139,0.7801461143224149,0.01678389141713296 +flat_mae,patch,logistic,ppmi_dx,23,0.046415888336127774,test,0.59,0.04830683181497209,0.5464100011063171,0.0528132397813685,0.5471137521222411,0.05044909519657971 +flat_mae,patch,logistic,ppmi_dx,24,0.005994842503189409,train,0.7366548042704626,0.01589846449307042,0.6939178049929345,0.020096497346170823,0.6869781631342324,0.01832231732068055 +flat_mae,patch,logistic,ppmi_dx,24,0.005994842503189409,test,0.62,0.042644666723987895,0.5476190476190476,0.05238424404069358,0.5560271646859083,0.04547055172898811 +flat_mae,patch,logistic,ppmi_dx,25,0.046415888336127774,train,0.8042704626334519,0.015100265612066064,0.7818969531900481,0.01758601165574483,0.7714622136587455,0.017366255719737253 +flat_mae,patch,logistic,ppmi_dx,25,0.046415888336127774,test,0.61,0.0374444441806792,0.5311936530833032,0.04842044205479659,0.5428692699490663,0.04071243579677809 +flat_mae,patch,logistic,ppmi_dx,26,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,26,21.54434690031882,test,0.56,0.05064345564828687,0.537620849096259,0.05180613250937748,0.5382003395585738,0.05197831050059593 +flat_mae,patch,logistic,ppmi_dx,27,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,27,21.54434690031882,test,0.58,0.04648812321442972,0.5543293718166383,0.049016687140385796,0.5543293718166383,0.04887738333817796 +flat_mae,patch,logistic,ppmi_dx,28,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,28,21.54434690031882,test,0.63,0.04844718361267247,0.6093337556752191,0.05194884871096041,0.6099320882852293,0.05241791770264522 +flat_mae,patch,logistic,ppmi_dx,29,0.3593813663804626,train,0.9163701067615658,0.011885121529782003,0.9098630576400051,0.013101027783143841,0.9025101691286662,0.013976594041268626 +flat_mae,patch,logistic,ppmi_dx,29,0.3593813663804626,test,0.6,0.0511022504396822,0.5755517826825127,0.05331479633568266,0.5755517826825127,0.053358757276586226 +flat_mae,patch,logistic,ppmi_dx,30,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,30,1291.5496650148827,test,0.6,0.04824220144230568,0.570999570999571,0.05176844620913562,0.5704584040747029,0.051234603887909916 +flat_mae,patch,logistic,ppmi_dx,31,0.005994842503189409,train,0.7259786476868327,0.016416185728139368,0.6824858757062147,0.020584517404503636,0.6765681866837936,0.01873155807580265 +flat_mae,patch,logistic,ppmi_dx,31,0.005994842503189409,test,0.6,0.04581931470460902,0.5477159656264134,0.05162923878900251,0.5500848896434635,0.047954587870815274 +flat_mae,patch,logistic,ppmi_dx,32,0.3593813663804626,train,0.9163701067615658,0.01156105896407268,0.9100472342265948,0.012679206870336917,0.9033798972382787,0.01353063729472161 +flat_mae,patch,logistic,ppmi_dx,32,0.3593813663804626,test,0.63,0.04854248036513997,0.6129302228266555,0.04969613917010385,0.615025466893039,0.0501935819464046 +flat_mae,patch,logistic,ppmi_dx,33,2.782559402207126,train,0.99644128113879,0.0023525258193648917,0.9962400984799828,0.0024847590985939225,0.9962400984799828,0.0025463467765183627 +flat_mae,patch,logistic,ppmi_dx,33,2.782559402207126,test,0.61,0.048492024086441265,0.6052232007288187,0.048341602003436714,0.6192699490662139,0.04963229370035876 +flat_mae,patch,logistic,ppmi_dx,34,0.046415888336127774,train,0.8096085409252669,0.01593000545816731,0.7901836338070432,0.018121950257053845,0.7810158424320275,0.01798949326614352 +flat_mae,patch,logistic,ppmi_dx,34,0.046415888336127774,test,0.65,0.04842922671280226,0.6266666666666667,0.05163843948784456,0.6260611205432938,0.051366298003115624 +flat_mae,patch,logistic,ppmi_dx,35,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,35,166.81005372000556,test,0.58,0.047173632465605186,0.5495495495495495,0.049728010063455515,0.5492359932088284,0.04888675492373518 +flat_mae,patch,logistic,ppmi_dx,36,0.005994842503189409,train,0.7188612099644128,0.016912796318095204,0.6771524141942991,0.020662619714692868,0.6716575679725969,0.01900306785937127 +flat_mae,patch,logistic,ppmi_dx,36,0.005994842503189409,test,0.65,0.03983614439174554,0.5872154735228211,0.04948768893897405,0.5904074702886248,0.04366223742114046 +flat_mae,patch,logistic,ppmi_dx,37,0.046415888336127774,train,0.8078291814946619,0.01602480315577717,0.785314091680815,0.018946066557659916,0.7743523870691501,0.018663052809824877 +flat_mae,patch,logistic,ppmi_dx,37,0.046415888336127774,test,0.7,0.04328567430455484,0.6657754010695187,0.049527042706808556,0.6612903225806452,0.04737636091576165 +flat_mae,patch,logistic,ppmi_dx,38,0.046415888336127774,train,0.806049822064057,0.014493668888922819,0.7841530921096677,0.016914441534309363,0.7737770284735603,0.016688485191724816 +flat_mae,patch,logistic,ppmi_dx,38,0.046415888336127774,test,0.62,0.046615688346306756,0.5967741935483871,0.048829737830471315,0.5967741935483871,0.04895399281003357 +flat_mae,patch,logistic,ppmi_dx,39,0.046415888336127774,train,0.7829181494661922,0.015337378091703883,0.7562151553077711,0.01854626219893286,0.7462936202098052,0.018066707350860207 +flat_mae,patch,logistic,ppmi_dx,39,0.046415888336127774,test,0.71,0.04326703595117188,0.6791680495630048,0.04943692819561399,0.6744482173174873,0.04771475807387816 +flat_mae,patch,logistic,ppmi_dx,40,0.005994842503189409,train,0.7259786476868327,0.016514324888048645,0.6774448419797257,0.021417751053109953,0.6722195461357311,0.019082830399285065 +flat_mae,patch,logistic,ppmi_dx,40,0.005994842503189409,test,0.67,0.04409769154955846,0.6296711929076422,0.05053933375600651,0.6269100169779287,0.047727161766093214 +flat_mae,patch,logistic,ppmi_dx,41,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,41,21.54434690031882,test,0.72,0.044795910527636346,0.7028862478777589,0.047562497957026356,0.7028862478777589,0.047658043064029314 +flat_mae,patch,logistic,ppmi_dx,42,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,42,166.81005372000556,test,0.67,0.04513206842146723,0.6396986570586308,0.049067685769278155,0.6370967741935484,0.04785896218427989 +flat_mae,patch,logistic,ppmi_dx,43,0.005994842503189409,train,0.7277580071174378,0.01643242663388307,0.6859750419072452,0.020623111804307613,0.6797527296082209,0.018935373602926187 +flat_mae,patch,logistic,ppmi_dx,43,0.005994842503189409,test,0.67,0.04359355915728836,0.6176572818908586,0.05299877590242605,0.616723259762309,0.04788763004961681 +flat_mae,patch,logistic,ppmi_dx,44,0.005994842503189409,train,0.7313167259786477,0.016086867316526327,0.6881942071479223,0.0203003419019956,0.6817731749090131,0.018459869436083746 +flat_mae,patch,logistic,ppmi_dx,44,0.005994842503189409,test,0.71,0.03790358294409645,0.6579785352046232,0.048961024960636354,0.6540747028862479,0.04353592338115061 +flat_mae,patch,logistic,ppmi_dx,45,0.046415888336127774,train,0.806049822064057,0.016123627950165285,0.7830461652883781,0.01890300337974695,0.7720375722543353,0.01841375522099595 +flat_mae,patch,logistic,ppmi_dx,45,0.046415888336127774,test,0.67,0.04210607557110968,0.6176572818908586,0.05275183153537994,0.616723259762309,0.0475479369121876 +flat_mae,patch,logistic,ppmi_dx,46,0.3593813663804626,train,0.9145907473309609,0.011462904136783912,0.9078499692559951,0.012591370206658003,0.9001953543138514,0.013328601672031941 +flat_mae,patch,logistic,ppmi_dx,46,0.3593813663804626,test,0.58,0.04329934872489423,0.5384615384615385,0.04842445535014656,0.5390492359932089,0.04612223855545981 +flat_mae,patch,logistic,ppmi_dx,47,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,47,166.81005372000556,test,0.64,0.04825404024535148,0.6216897856242118,0.050934989277892515,0.6230899830220713,0.051444033699867935 +flat_mae,patch,logistic,ppmi_dx,48,0.046415888336127774,train,0.798932384341637,0.01583143553615308,0.7738994214508232,0.018844629001254064,0.762778312995076,0.018324837059052843 +flat_mae,patch,logistic,ppmi_dx,48,0.046415888336127774,test,0.72,0.04273862421744528,0.7057587221521648,0.044971335367298276,0.7079796264855688,0.04557266058417626 +flat_mae,patch,logistic,ppmi_dx,49,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,49,21.54434690031882,test,0.63,0.04461612264641562,0.5906626839252129,0.05022010635383451,0.5895585738539898,0.0476709310012149 +flat_mae,patch,logistic,ppmi_dx,50,0.046415888336127774,train,0.806049822064057,0.015335313636447504,0.7846932499165247,0.01756071061322649,0.7746467565831727,0.01724494895828865 +flat_mae,patch,logistic,ppmi_dx,50,0.046415888336127774,test,0.62,0.04496966088375584,0.5766488413547237,0.04951057930269233,0.5764006791171477,0.04692339153460689 +flat_mae,patch,logistic,ppmi_dx,51,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,51,166.81005372000556,test,0.58,0.048286495006367974,0.5586380832282472,0.04974940210500168,0.5594227504244482,0.05029281467088384 +flat_mae,patch,logistic,ppmi_dx,52,10000.0,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,52,10000.0,test,0.6,0.04579351919213023,0.5659722222222222,0.04925406011264427,0.565365025466893,0.04806826570016233 +flat_mae,patch,logistic,ppmi_dx,53,0.3593813663804626,train,0.9145907473309609,0.012313514384262212,0.9085893977797959,0.013380987157575188,0.9036742667523014,0.014114958525657625 +flat_mae,patch,logistic,ppmi_dx,53,0.3593813663804626,test,0.64,0.0469640884080592,0.6179966044142615,0.049485775426490075,0.6179966044142615,0.04946046063370554 +flat_mae,patch,logistic,ppmi_dx,54,0.005994842503189409,train,0.7437722419928826,0.016289877669488452,0.7021902967498823,0.020446075199491324,0.6944979661742667,0.018562502954905906 +flat_mae,patch,logistic,ppmi_dx,54,0.005994842503189409,test,0.58,0.04574024048909232,0.5320855614973261,0.04958838864055525,0.533955857385399,0.04709241242656537 +flat_mae,patch,logistic,ppmi_dx,55,0.005994842503189409,train,0.7277580071174378,0.016380530489155134,0.6830862108999237,0.020933920725554743,0.6771435452793835,0.018902010465374982 +flat_mae,patch,logistic,ppmi_dx,55,0.005994842503189409,test,0.67,0.04415746369528032,0.6349153667441089,0.049904255678792676,0.6320033955857385,0.04752474573120637 +flat_mae,patch,logistic,ppmi_dx,56,0.046415888336127774,train,0.800711743772242,0.015507645723907552,0.7773627617430674,0.01833104817593421,0.7668325840291158,0.018026642221179747 +flat_mae,patch,logistic,ppmi_dx,56,0.046415888336127774,test,0.6,0.04722749622836256,0.554367201426025,0.05184764705639123,0.5551782682512734,0.04921557198275155 +flat_mae,patch,logistic,ppmi_dx,57,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,57,1291.5496650148827,test,0.54,0.045391148916941945,0.5066495066495067,0.04736195667403996,0.5067911714770797,0.04680466897804246 +flat_mae,patch,logistic,ppmi_dx,58,2.782559402207126,train,0.99644128113879,0.002445759150026101,0.9962334964144495,0.0025954948211686373,0.9953703703703703,0.003181751486839507 +flat_mae,patch,logistic,ppmi_dx,58,2.782559402207126,test,0.6,0.05059841894763116,0.586606035551881,0.051566613354036284,0.5908319185059423,0.05286090978452304 +flat_mae,patch,logistic,ppmi_dx,59,0.3593813663804626,train,0.9181494661921709,0.01124232126223859,0.9120500782472614,0.012288656125235366,0.9056947120530936,0.013073494993450705 +flat_mae,patch,logistic,ppmi_dx,59,0.3593813663804626,test,0.61,0.04544418994767098,0.584,0.04880134471886391,0.583616298811545,0.0482897077886412 +flat_mae,patch,logistic,ppmi_dx,60,0.046415888336127774,train,0.8042704626334519,0.014858312257548547,0.7824465090090089,0.01715654775369925,0.772331941768358,0.01688062897054609 +flat_mae,patch,logistic,ppmi_dx,60,0.046415888336127774,test,0.62,0.0445647573762048,0.5703301673450927,0.05189641083281955,0.5713073005093379,0.04819611399807796 +flat_mae,patch,logistic,ppmi_dx,61,2.782559402207126,train,0.998220640569395,0.001761116445787707,0.9981184064710746,0.0018659068545066164,0.9976851851851851,0.002291082042899745 +flat_mae,patch,logistic,ppmi_dx,61,2.782559402207126,test,0.62,0.04878309133296085,0.6041666666666667,0.0504087178797371,0.6069609507640068,0.05147683489102075 +flat_mae,patch,logistic,ppmi_dx,62,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,62,2.782559402207126,test,0.62,0.04470892081005758,0.5766488413547237,0.051230962153924295,0.5764006791171477,0.04816240430858508 +flat_mae,patch,logistic,ppmi_dx,63,0.3593813663804626,train,0.9039145907473309,0.012089694464722899,0.8958930801213003,0.013336409741099038,0.887176193534575,0.01381802132618036 +flat_mae,patch,logistic,ppmi_dx,63,0.3593813663804626,test,0.65,0.044012957183084164,0.612789025334661,0.0499307236021549,0.6107809847198642,0.047596035179020786 +flat_mae,patch,logistic,ppmi_dx,64,0.3593813663804626,train,0.9288256227758007,0.010748332540353376,0.9233664230391623,0.01179899303007091,0.9161046885035324,0.012698068589505689 +flat_mae,patch,logistic,ppmi_dx,64,0.3593813663804626,test,0.58,0.04408596602094593,0.5174632352941176,0.04978369394562174,0.5237691001697793,0.045539796534067506 +flat_mae,patch,logistic,ppmi_dx,65,0.005994842503189409,train,0.7313167259786477,0.01604713741345863,0.6910007828572469,0.019684232264955373,0.6843823592378505,0.01814051078558778 +flat_mae,patch,logistic,ppmi_dx,65,0.005994842503189409,test,0.62,0.04364443148902275,0.5634191176470589,0.0497341805791602,0.566213921901528,0.04532692078806033 +flat_mae,patch,logistic,ppmi_dx,66,0.046415888336127774,train,0.8220640569395018,0.014926607515094543,0.8046032960155761,0.016969304642646118,0.7954800899165061,0.017060942575066153 +flat_mae,patch,logistic,ppmi_dx,66,0.046415888336127774,test,0.62,0.047445564597757714,0.5766488413547237,0.05323989017347579,0.5764006791171477,0.05035196169889621 +flat_mae,patch,logistic,ppmi_dx,67,0.005994842503189409,train,0.7259786476868327,0.016723668728206853,0.685325770796975,0.02051133799077469,0.6791773710126312,0.01892261065320525 +flat_mae,patch,logistic,ppmi_dx,67,0.005994842503189409,test,0.63,0.04251672141640275,0.5783475783475784,0.05042489907174505,0.5793718166383701,0.046241978510727685 +flat_mae,patch,logistic,ppmi_dx,68,0.3593813663804626,train,0.9128113879003559,0.011619390929143656,0.9056332863864245,0.0129179940521979,0.8970108113894242,0.013926377619788594 +flat_mae,patch,logistic,ppmi_dx,68,0.3593813663804626,test,0.67,0.04525172261914456,0.6396986570586308,0.04981313171528849,0.6370967741935484,0.04834291719141169 +flat_mae,patch,logistic,ppmi_dx,69,0.3593813663804626,train,0.9074733096085409,0.011779505111397694,0.8995324532453246,0.013127245568540046,0.8900663669449796,0.013919338476027587 +flat_mae,patch,logistic,ppmi_dx,69,0.3593813663804626,test,0.65,0.04852052761460864,0.6266666666666667,0.050694635309452375,0.6260611205432938,0.05054351696289294 +flat_mae,patch,logistic,ppmi_dx,70,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,70,166.81005372000556,test,0.62,0.049178857245771784,0.5924495924495925,0.05254896741665565,0.5916808149405772,0.05163844634223699 +flat_mae,patch,logistic,ppmi_dx,71,0.005994842503189409,train,0.7259786476868327,0.016829007659114725,0.6862429489131538,0.02056776431781668,0.6800470991222436,0.019015255966099615 +flat_mae,patch,logistic,ppmi_dx,71,0.005994842503189409,test,0.68,0.04248242460123951,0.6259934548854604,0.05184213375875312,0.6247877758913413,0.046450884160565614 +flat_mae,patch,logistic,ppmi_dx,72,0.046415888336127774,train,0.8042704626334519,0.01580738854154562,0.7807708129423947,0.018637639082693263,0.7697227574395205,0.01821654058365698 +flat_mae,patch,logistic,ppmi_dx,72,0.046415888336127774,test,0.65,0.04822495619489975,0.6266666666666667,0.05084725711274687,0.6260611205432938,0.050588126733053566 +flat_mae,patch,logistic,ppmi_dx,73,0.046415888336127774,train,0.8238434163701067,0.015695773411092344,0.8054037038980117,0.018096862969007973,0.7951857204024835,0.01808177828176327 +flat_mae,patch,logistic,ppmi_dx,73,0.046415888336127774,test,0.59,0.04853411171536984,0.5670995670995671,0.05095303993970923,0.5674872665534805,0.05112136508990824 +flat_mae,patch,logistic,ppmi_dx,74,0.3593813663804626,train,0.9145907473309609,0.012010926582337215,0.9078499692559951,0.013221062047381328,0.9001953543138514,0.014065697914472352 +flat_mae,patch,logistic,ppmi_dx,74,0.3593813663804626,test,0.54,0.04803586576715361,0.5208333333333334,0.04903229462366983,0.5220713073005093,0.05017417160224676 +flat_mae,patch,logistic,ppmi_dx,75,0.005994842503189409,train,0.7366548042704626,0.01624200379887413,0.6929641934293097,0.02018814489603186,0.68610843502462,0.018285894328086985 +flat_mae,patch,logistic,ppmi_dx,75,0.005994842503189409,test,0.66,0.043411791025019915,0.6155585707824514,0.05114531892880968,0.6137521222410866,0.04766509388303385 +flat_mae,patch,logistic,ppmi_dx,76,0.005994842503189409,train,0.7188612099644128,0.016807485211182683,0.676196449669618,0.020837891576720387,0.6707878398629844,0.01905814830631983 +flat_mae,patch,logistic,ppmi_dx,76,0.005994842503189409,test,0.71,0.04099207240430764,0.6745595331612613,0.048329821382448755,0.6693548387096775,0.04560264171602428 +flat_mae,patch,logistic,ppmi_dx,77,0.3593813663804626,train,0.9199288256227758,0.010294759820456939,0.9136986722085154,0.011359135025007976,0.9062700706486834,0.012255276704280211 +flat_mae,patch,logistic,ppmi_dx,77,0.3593813663804626,test,0.65,0.04188965982196561,0.6011396011396011,0.050306228237410336,0.6005942275042444,0.046290792522531155 +flat_mae,patch,logistic,ppmi_dx,78,0.046415888336127774,train,0.802491103202847,0.015141643685154454,0.7828552333413394,0.017332290121682508,0.7743657675016057,0.017363326244525253 +flat_mae,patch,logistic,ppmi_dx,78,0.046415888336127774,test,0.64,0.041536157742381515,0.5714285714285714,0.05077231471479952,0.5772495755517827,0.04453176264697273 +flat_mae,patch,logistic,ppmi_dx,79,0.005994842503189409,train,0.7241992882562278,0.01650788223575714,0.6737489840938117,0.021698353855014264,0.6690350032113038,0.019162967892985928 +flat_mae,patch,logistic,ppmi_dx,79,0.005994842503189409,test,0.65,0.04328001848428441,0.6011396011396011,0.051311004718037005,0.6005942275042444,0.047111185142446485 +flat_mae,patch,logistic,ppmi_dx,80,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,80,166.81005372000556,test,0.65,0.04900204077382899,0.6368917937545389,0.05013910766868334,0.6413412563667232,0.05094303396519896 +flat_mae,patch,logistic,ppmi_dx,81,0.046415888336127774,train,0.800711743772242,0.015287195865068017,0.778490990990991,0.017700004662834976,0.7685720402483409,0.01747264616163597 +flat_mae,patch,logistic,ppmi_dx,81,0.046415888336127774,test,0.69,0.04321490020814579,0.6521153630344518,0.05007210926986836,0.6481324278438031,0.047131502575524876 +flat_mae,patch,logistic,ppmi_dx,82,0.046415888336127774,train,0.7935943060498221,0.01563572085059234,0.7675864527629234,0.018815349491423685,0.756703596660244,0.018289681513200706 +flat_mae,patch,logistic,ppmi_dx,82,0.046415888336127774,test,0.64,0.04569689705001862,0.5989304812834224,0.052631815012195715,0.597623089983022,0.049675594135949325 +flat_mae,patch,logistic,ppmi_dx,83,0.005994842503189409,train,0.7473309608540926,0.01617091052740595,0.711524002313476,0.01946874513708729,0.7034762363519589,0.01823475809944108 +flat_mae,patch,logistic,ppmi_dx,83,0.005994842503189409,test,0.5,0.049919551280034564,0.46943972835314096,0.05090797057956661,0.46943972835314096,0.050947567462096575 +flat_mae,patch,logistic,ppmi_dx,84,0.3593813663804626,train,0.9199288256227758,0.011664457711938664,0.9135192435925932,0.012885247663054886,0.9054003425390709,0.013872783748994475 +flat_mae,patch,logistic,ppmi_dx,84,0.3593813663804626,test,0.57,0.048472029047688936,0.5305164319248826,0.052403019587527945,0.5309847198641766,0.050763842718247604 +flat_mae,patch,logistic,ppmi_dx,85,0.005994842503189409,train,0.7330960854092526,0.016062994176605293,0.6934991273996509,0.019579989551801444,0.6866971740526654,0.018010134214142257 +flat_mae,patch,logistic,ppmi_dx,85,0.005994842503189409,test,0.63,0.03903214572631129,0.5552350042072365,0.049209447960951995,0.5640916808149405,0.042195067189945666 +flat_mae,patch,logistic,ppmi_dx,86,0.000774263682681127,train,0.6903914590747331,0.015459992239276835,0.6170102769770648,0.021584396074368097,0.6224443374009848,0.01761212701035602 +flat_mae,patch,logistic,ppmi_dx,86,0.000774263682681127,test,0.57,0.03058665722173639,0.4188403838356535,0.03849912047256905,0.47495755517826826,0.030203411748350506 +flat_mae,patch,logistic,ppmi_dx,87,0.046415888336127774,train,0.8078291814946619,0.015913338143588945,0.7864020270270271,0.01872036412082472,0.776091843288375,0.01855223429783164 +flat_mae,patch,logistic,ppmi_dx,87,0.046415888336127774,test,0.61,0.04503268146579771,0.5481404240528328,0.053650766658701075,0.5530560271646858,0.04822666352904696 +flat_mae,patch,logistic,ppmi_dx,88,0.3593813663804626,train,0.9288256227758007,0.010813339279755281,0.9239718614718615,0.011688277900122107,0.9195836009419824,0.012383368961156504 +flat_mae,patch,logistic,ppmi_dx,88,0.3593813663804626,test,0.61,0.04636836852855619,0.568536342515765,0.05121611411553309,0.5683361629881154,0.04902371503535925 +flat_mae,patch,logistic,ppmi_dx,89,2.782559402207126,train,0.994661921708185,0.0031880162763099165,0.9943452231222015,0.003389230762428411,0.9930555555555556,0.0041473730261254 +flat_mae,patch,logistic,ppmi_dx,89,2.782559402207126,test,0.64,0.04633914543881879,0.625,0.04808719306320222,0.6281833616298811,0.04933901810449358 +flat_mae,patch,logistic,ppmi_dx,90,0.005994842503189409,train,0.7295373665480427,0.01630649679164836,0.6894124490983129,0.019849935652158653,0.6829372725326482,0.018294001630323832 +flat_mae,patch,logistic,ppmi_dx,90,0.005994842503189409,test,0.63,0.04407201379560503,0.5783475783475784,0.05104837649481271,0.5793718166383701,0.046970346487666306 +flat_mae,patch,logistic,ppmi_dx,91,2.782559402207126,train,0.994661921708185,0.0030962469790541476,0.9943452231222015,0.0032914562614162948,0.9930555555555556,0.0040279879681213646 +flat_mae,patch,logistic,ppmi_dx,91,2.782559402207126,test,0.66,0.04771540631703769,0.6458333333333333,0.04885103137013177,0.6494057724957556,0.049234130724096464 +flat_mae,patch,logistic,ppmi_dx,92,2.782559402207126,train,0.998220640569395,0.0018901454412654094,0.9981184064710746,0.002002468353723959,0.9976851851851851,0.002458939208312873 +flat_mae,patch,logistic,ppmi_dx,92,2.782559402207126,test,0.6,0.04840649130023782,0.5755517826825127,0.05051458579379349,0.5755517826825127,0.050340552409902255 +flat_mae,patch,logistic,ppmi_dx,93,0.005994842503189409,train,0.7402135231316725,0.016097883551564503,0.701672484002327,0.019758449748826578,0.6942169770926996,0.018336609232940768 +flat_mae,patch,logistic,ppmi_dx,93,0.005994842503189409,test,0.6,0.04467597117019394,0.5604395604395604,0.05035782772831961,0.5602716468590832,0.04818643239543958 +flat_mae,patch,logistic,ppmi_dx,94,0.3593813663804626,train,0.9110320284697508,0.011349300127823786,0.9047806226872874,0.012300887795788517,0.8999143652322843,0.012907568172084135 +flat_mae,patch,logistic,ppmi_dx,94,0.3593813663804626,test,0.67,0.04287003615580467,0.6515679442508711,0.04512405826061534,0.652376910016978,0.04545498137931404 +flat_mae,patch,logistic,ppmi_dx,95,0.005994842503189409,train,0.7384341637010676,0.016202491724604907,0.7000686167374013,0.01997629007405492,0.6927718903874973,0.01854754962968634 +flat_mae,patch,logistic,ppmi_dx,95,0.005994842503189409,test,0.61,0.03702559114990604,0.5215311004784688,0.047803639949767066,0.5377758913412564,0.03958387413505116 +flat_mae,patch,logistic,ppmi_dx,96,0.005994842503189409,train,0.7419928825622776,0.01658950112187835,0.702394647559154,0.020834351289382175,0.6947923356882895,0.01918085873638335 +flat_mae,patch,logistic,ppmi_dx,96,0.005994842503189409,test,0.57,0.04390181773002114,0.5242836596968692,0.04799898063125751,0.5258913412563667,0.045817714750352824 +flat_mae,patch,logistic,ppmi_dx,97,0.046415888336127774,train,0.8149466192170819,0.015198056277983074,0.7937934830160456,0.01761586927331079,0.7827419182187968,0.017351309956552978 +flat_mae,patch,logistic,ppmi_dx,97,0.046415888336127774,test,0.66,0.047348997877463044,0.6263736263736264,0.052551055417661155,0.6239388794567062,0.05048498314970916 +flat_mae,patch,logistic,ppmi_dx,98,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,98,2.782559402207126,test,0.64,0.04859219690444135,0.609375,0.054329714479281935,0.6078098471986417,0.053024487059845096 +flat_mae,patch,logistic,ppmi_dx,99,0.046415888336127774,train,0.7935943060498221,0.015965373858675663,0.7688128572847072,0.018762525341101396,0.758443052879469,0.01830842459545889 +flat_mae,patch,logistic,ppmi_dx,99,0.046415888336127774,test,0.65,0.04409714730002384,0.6224786970121885,0.04813814011602131,0.6209677419354839,0.04743906778182589 +flat_mae,patch,logistic,ppmi_dx,100,0.046415888336127774,train,0.806049822064057,0.014706715598476841,0.7841530921096677,0.01733743537709599,0.7737770284735603,0.01718551942443998 +flat_mae,patch,logistic,ppmi_dx,100,0.046415888336127774,test,0.61,0.04761096932430593,0.5793334052421529,0.0514722941810896,0.5785229202037352,0.05039685349764104 diff --git a/input_space_v3/flat_lr1e-3_1/eval_v2/ppmi_dx__patch__logistic/log.txt b/input_space_v3/flat_lr1e-3_1/eval_v2/ppmi_dx__patch__logistic/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..b77a2a03b99300e463325fe8196ddd55e9ff5106 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_1/eval_v2/ppmi_dx__patch__logistic/log.txt @@ -0,0 +1,247 @@ +fMRI foundation model logistic probe eval +version: 0.1.dev86+gf97f52698 +sha: bcce2b486277d3a5b520775efd9cdf1a2affce36, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-04-08 22:02:22 +config: +output_root: experiments/input_space_v3/output +name_prefix: eval_logistic +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_1; eval v2 (ppmi_dx patch logistic) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: input_space_v3/flat_lr1e-3_1/eval_v2/ppmi_dx__patch__logistic +model: flat_mae +representation: patch +dataset: ppmi_dx +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/eval_v2/ppmi_dx__patch__logistic +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=True, reg_tokens=0, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: ppmi_dx (flat) +train (n=463): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'dir', 'sex', 'age', 'age_bin', 'dx', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 463 +}), + labels=['PD' 'Prodromal'], + counts=[178 285] +) + +validation (n=99): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'dir', 'sex', 'age', 'age_bin', 'dx', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 99 +}), + labels=['PD' 'Prodromal'], + counts=[39 60] +) + +test (n=100): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'dir', 'sex', 'age', 'age_bin', 'dx', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 100 +}), + labels=['PD' 'Prodromal'], + counts=[37 63] +) + +extracting features for all splits +extract (train) [ 0/232] eta: 0:19:27 time: 5.0324 data: 4.0046 max mem: 2698 +extract (train) [ 20/232] eta: 0:01:31 time: 0.2025 data: 0.0692 max mem: 2851 +extract (train) [ 40/232] eta: 0:01:00 time: 0.1906 data: 0.0625 max mem: 2851 +extract (train) [ 60/232] eta: 0:00:45 time: 0.1664 data: 0.0520 max mem: 2851 +extract (train) [ 80/232] eta: 0:00:36 time: 0.1661 data: 0.0509 max mem: 2851 +extract (train) [100/232] eta: 0:00:30 time: 0.1884 data: 0.0640 max mem: 2851 +extract (train) [120/232] eta: 0:00:25 time: 0.1988 data: 0.0682 max mem: 2851 +extract (train) [140/232] eta: 0:00:20 time: 0.1937 data: 0.0665 max mem: 2851 +extract (train) [160/232] eta: 0:00:15 time: 0.1811 data: 0.0603 max mem: 2851 +extract (train) [180/232] eta: 0:00:11 time: 0.1776 data: 0.0589 max mem: 2851 +extract (train) [200/232] eta: 0:00:06 time: 0.2065 data: 0.0726 max mem: 2851 +extract (train) [220/232] eta: 0:00:02 time: 0.1714 data: 0.0550 max mem: 2851 +extract (train) [231/232] eta: 0:00:00 time: 0.1669 data: 0.0539 max mem: 2851 +extract (train) Total time: 0:00:48 (0.2071 s / it) +extract (validation) [ 0/50] eta: 0:03:38 time: 4.3754 data: 4.1290 max mem: 2851 +extract (validation) [20/50] eta: 0:00:13 time: 0.2542 data: 0.0931 max mem: 2851 +extract (validation) [40/50] eta: 0:00:03 time: 0.1679 data: 0.0506 max mem: 2851 +extract (validation) [49/50] eta: 0:00:00 time: 0.1683 data: 0.0525 max mem: 2851 +extract (validation) Total time: 0:00:14 (0.2926 s / it) +extract (test) [ 0/50] eta: 0:03:55 time: 4.7114 data: 4.5178 max mem: 2851 +extract (test) [20/50] eta: 0:00:14 time: 0.2689 data: 0.1028 max mem: 2851 +extract (test) [40/50] eta: 0:00:03 time: 0.1751 data: 0.0545 max mem: 2851 +extract (test) [49/50] eta: 0:00:00 time: 0.1753 data: 0.0562 max mem: 2851 +extract (test) Total time: 0:00:15 (0.3078 s / it) +feature extraction time: 0:01:18 +train features: (463, 768) +validation features: (99, 768) +test features: (100, 768) +evaluating fixed splits +eval results (fixed splits): + +| model | repr | clf | dataset | trial | C | split | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|--------:|:--------|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | ppmi_dx | | 0.35938 | train | 0.91815 | 0.011065 | 0.91187 | 0.012138 | 0.90427 | 0.012908 | +| flat_mae | patch | logistic | ppmi_dx | | 0.35938 | test | 0.66 | 0.04464 | 0.62121 | 0.04941 | 0.61862 | 0.047639 | + + +evaluating random splits (n=100) +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 1, "C": 2.782559402207126, "split": "test", "acc": 0.57, "acc_std": 0.04722465034280295, "f1": 0.5459824728117411, "f1_std": 0.048481250952047916, "bacc": 0.5462648556876061, "bacc_std": 0.04855677552170009} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 2, "C": 0.005994842503189409, "split": "test", "acc": 0.68, "acc_std": 0.04344607692300882, "f1": 0.64349376114082, "f1_std": 0.04975007092827599, "bacc": 0.6400679117147707, "bacc_std": 0.04706829817647831} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 3, "C": 0.005994842503189409, "split": "test", "acc": 0.66, "acc_std": 0.042418184779643736, "f1": 0.6155585707824514, "f1_std": 0.05009765331277162, "bacc": 0.6137521222410866, "bacc_std": 0.04647180319063591} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 4, "C": 0.046415888336127774, "split": "test", "acc": 0.66, "acc_std": 0.045224855997559564, "f1": 0.6263736263736264, "f1_std": 0.0499203647412052, "bacc": 0.6239388794567062, "bacc_std": 0.04801732732955611} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 5, "C": 166.81005372000556, "split": "test", "acc": 0.56, "acc_std": 0.04948932814253997, "f1": 0.537620849096259, "f1_std": 0.05084135870880222, "bacc": 0.5382003395585738, "bacc_std": 0.0513173291479043} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 6, "C": 0.3593813663804626, "split": "test", "acc": 0.59, "acc_std": 0.04846000825422959, "f1": 0.5670995670995671, "f1_std": 0.050900663241427266, "bacc": 0.5674872665534805, "bacc_std": 0.051119845077975956} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 7, "C": 0.046415888336127774, "split": "test", "acc": 0.62, "acc_std": 0.047312894648288015, "f1": 0.5924495924495925, "f1_std": 0.05031702328969495, "bacc": 0.5916808149405772, "bacc_std": 0.04955051908728715} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 8, "C": 166.81005372000556, "split": "test", "acc": 0.61, "acc_std": 0.04701861333557169, "f1": 0.5983935742971888, "f1_std": 0.047115919610913805, "bacc": 0.6039898132427843, "bacc_std": 0.04779095035607081} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 9, "C": 0.3593813663804626, "split": "test", "acc": 0.6, "acc_std": 0.045167669853557864, "f1": 0.570999570999571, "f1_std": 0.0480851296459321, "bacc": 0.5704584040747029, "bacc_std": 0.04727129431711301} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 10, "C": 2.782559402207126, "split": "test", "acc": 0.63, "acc_std": 0.047540042069817316, "f1": 0.6161427533976553, "f1_std": 0.048594098113166055, "bacc": 0.6201188455008488, "bacc_std": 0.04955561221768322} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 11, "C": 2.782559402207126, "split": "test", "acc": 0.62, "acc_std": 0.04955989911208456, "f1": 0.6006725514922235, "f1_std": 0.05081797583002668, "bacc": 0.6018675721561969, "bacc_std": 0.050958726738892325} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 12, "C": 0.005994842503189409, "split": "test", "acc": 0.57, "acc_std": 0.03631512632499024, "f1": 0.46081504702194354, "f1_std": 0.04394809350323639, "bacc": 0.4902376910016978, "bacc_std": 0.03688708663502455} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 13, "C": 0.046415888336127774, "split": "test", "acc": 0.66, "acc_std": 0.04220379129888688, "f1": 0.609375, "f1_std": 0.05025468714859442, "bacc": 0.6086587436332768, "bacc_std": 0.045709315195201466} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 14, "C": 0.046415888336127774, "split": "test", "acc": 0.63, "acc_std": 0.04476881057164687, "f1": 0.5847828526540231, "f1_std": 0.0506242815370244, "bacc": 0.5844651952461799, "bacc_std": 0.0476584391956827} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 15, "C": 0.005994842503189409, "split": "test", "acc": 0.69, "acc_std": 0.04072885463648591, "f1": 0.6343908479773559, "f1_std": 0.052756144508267155, "bacc": 0.6328522920203735, "bacc_std": 0.046518326194705424} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 16, "C": 166.81005372000556, "split": "test", "acc": 0.56, "acc_std": 0.04869599983571545, "f1": 0.5555555555555556, "f1_std": 0.04837888346661797, "bacc": 0.5687606112054329, "bacc_std": 0.04999918691923091} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 17, "C": 0.005994842503189409, "split": "test", "acc": 0.62, "acc_std": 0.04363220828699827, "f1": 0.5703301673450927, "f1_std": 0.049890256570154994, "bacc": 0.5713073005093379, "bacc_std": 0.04637235354757133} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 18, "C": 0.046415888336127774, "split": "test", "acc": 0.6, "acc_std": 0.04586873008924489, "f1": 0.5477159656264134, "f1_std": 0.051195506583176995, "bacc": 0.5500848896434635, "bacc_std": 0.047604185612310876} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 19, "C": 0.3593813663804626, "split": "test", "acc": 0.59, "acc_std": 0.050379880904980315, "f1": 0.5746446726838883, "f1_std": 0.05153584786399316, "bacc": 0.5776740237691002, "bacc_std": 0.05257351725789684} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 20, "C": 0.046415888336127774, "split": "test", "acc": 0.6, "acc_std": 0.04561238428321852, "f1": 0.5477159656264134, "f1_std": 0.05109057467709319, "bacc": 0.5500848896434635, "bacc_std": 0.04746836520995787} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 21, "C": 2.782559402207126, "split": "test", "acc": 0.65, "acc_std": 0.04461602850994248, "f1": 0.6178622120318812, "f1_std": 0.04936099984730498, "bacc": 0.615874363327674, "bacc_std": 0.04769561479162906} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 22, "C": 0.046415888336127774, "split": "test", "acc": 0.61, "acc_std": 0.04342726793156577, "f1": 0.5555555555555556, "f1_std": 0.04975917802341098, "bacc": 0.5581494057724957, "bacc_std": 0.045848984255488265} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 23, "C": 0.046415888336127774, "split": "test", "acc": 0.59, "acc_std": 0.04830683181497209, "f1": 0.5464100011063171, "f1_std": 0.0528132397813685, "bacc": 0.5471137521222411, "bacc_std": 0.05044909519657971} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 24, "C": 0.005994842503189409, "split": "test", "acc": 0.62, "acc_std": 0.042644666723987895, "f1": 0.5476190476190476, "f1_std": 0.05238424404069358, "bacc": 0.5560271646859083, "bacc_std": 0.04547055172898811} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 25, "C": 0.046415888336127774, "split": "test", "acc": 0.61, "acc_std": 0.0374444441806792, "f1": 0.5311936530833032, "f1_std": 0.04842044205479659, "bacc": 0.5428692699490663, "bacc_std": 0.04071243579677809} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 26, "C": 21.54434690031882, "split": "test", "acc": 0.56, "acc_std": 0.05064345564828687, "f1": 0.537620849096259, "f1_std": 0.05180613250937748, "bacc": 0.5382003395585738, "bacc_std": 0.05197831050059593} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 27, "C": 21.54434690031882, "split": "test", "acc": 0.58, "acc_std": 0.04648812321442972, "f1": 0.5543293718166383, "f1_std": 0.049016687140385796, "bacc": 0.5543293718166383, "bacc_std": 0.04887738333817796} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 28, "C": 21.54434690031882, "split": "test", "acc": 0.63, "acc_std": 0.04844718361267247, "f1": 0.6093337556752191, "f1_std": 0.05194884871096041, "bacc": 0.6099320882852293, "bacc_std": 0.05241791770264522} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 29, "C": 0.3593813663804626, "split": "test", "acc": 0.6, "acc_std": 0.0511022504396822, "f1": 0.5755517826825127, "f1_std": 0.05331479633568266, "bacc": 0.5755517826825127, "bacc_std": 0.053358757276586226} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 30, "C": 1291.5496650148827, "split": "test", "acc": 0.6, "acc_std": 0.04824220144230568, "f1": 0.570999570999571, "f1_std": 0.05176844620913562, "bacc": 0.5704584040747029, "bacc_std": 0.051234603887909916} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 31, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.04581931470460902, "f1": 0.5477159656264134, "f1_std": 0.05162923878900251, "bacc": 0.5500848896434635, "bacc_std": 0.047954587870815274} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 32, "C": 0.3593813663804626, "split": "test", "acc": 0.63, "acc_std": 0.04854248036513997, "f1": 0.6129302228266555, "f1_std": 0.04969613917010385, "bacc": 0.615025466893039, "bacc_std": 0.0501935819464046} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 33, "C": 2.782559402207126, "split": "test", "acc": 0.61, "acc_std": 0.048492024086441265, "f1": 0.6052232007288187, "f1_std": 0.048341602003436714, "bacc": 0.6192699490662139, "bacc_std": 0.04963229370035876} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 34, "C": 0.046415888336127774, "split": "test", "acc": 0.65, "acc_std": 0.04842922671280226, "f1": 0.6266666666666667, "f1_std": 0.05163843948784456, "bacc": 0.6260611205432938, "bacc_std": 0.051366298003115624} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 35, "C": 166.81005372000556, "split": "test", "acc": 0.58, "acc_std": 0.047173632465605186, "f1": 0.5495495495495495, "f1_std": 0.049728010063455515, "bacc": 0.5492359932088284, "bacc_std": 0.04888675492373518} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 36, "C": 0.005994842503189409, "split": "test", "acc": 0.65, "acc_std": 0.03983614439174554, "f1": 0.5872154735228211, "f1_std": 0.04948768893897405, "bacc": 0.5904074702886248, "bacc_std": 0.04366223742114046} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 37, "C": 0.046415888336127774, "split": "test", "acc": 0.7, "acc_std": 0.04328567430455484, "f1": 0.6657754010695187, "f1_std": 0.049527042706808556, "bacc": 0.6612903225806452, "bacc_std": 0.04737636091576165} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 38, "C": 0.046415888336127774, "split": "test", "acc": 0.62, "acc_std": 0.046615688346306756, "f1": 0.5967741935483871, "f1_std": 0.048829737830471315, "bacc": 0.5967741935483871, "bacc_std": 0.04895399281003357} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 39, "C": 0.046415888336127774, "split": "test", "acc": 0.71, "acc_std": 0.04326703595117188, "f1": 0.6791680495630048, "f1_std": 0.04943692819561399, "bacc": 0.6744482173174873, "bacc_std": 0.04771475807387816} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 40, "C": 0.005994842503189409, "split": "test", "acc": 0.67, "acc_std": 0.04409769154955846, "f1": 0.6296711929076422, "f1_std": 0.05053933375600651, "bacc": 0.6269100169779287, "bacc_std": 0.047727161766093214} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 41, "C": 21.54434690031882, "split": "test", "acc": 0.72, "acc_std": 0.044795910527636346, "f1": 0.7028862478777589, "f1_std": 0.047562497957026356, "bacc": 0.7028862478777589, "bacc_std": 0.047658043064029314} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 42, "C": 166.81005372000556, "split": "test", "acc": 0.67, "acc_std": 0.04513206842146723, "f1": 0.6396986570586308, "f1_std": 0.049067685769278155, "bacc": 0.6370967741935484, "bacc_std": 0.04785896218427989} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 43, "C": 0.005994842503189409, "split": "test", "acc": 0.67, "acc_std": 0.04359355915728836, "f1": 0.6176572818908586, "f1_std": 0.05299877590242605, "bacc": 0.616723259762309, "bacc_std": 0.04788763004961681} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 44, "C": 0.005994842503189409, "split": "test", "acc": 0.71, "acc_std": 0.03790358294409645, "f1": 0.6579785352046232, "f1_std": 0.048961024960636354, "bacc": 0.6540747028862479, "bacc_std": 0.04353592338115061} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 45, "C": 0.046415888336127774, "split": "test", "acc": 0.67, "acc_std": 0.04210607557110968, "f1": 0.6176572818908586, "f1_std": 0.05275183153537994, "bacc": 0.616723259762309, "bacc_std": 0.0475479369121876} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 46, "C": 0.3593813663804626, "split": "test", "acc": 0.58, "acc_std": 0.04329934872489423, "f1": 0.5384615384615385, "f1_std": 0.04842445535014656, "bacc": 0.5390492359932089, "bacc_std": 0.04612223855545981} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 47, "C": 166.81005372000556, "split": "test", "acc": 0.64, "acc_std": 0.04825404024535148, "f1": 0.6216897856242118, "f1_std": 0.050934989277892515, "bacc": 0.6230899830220713, "bacc_std": 0.051444033699867935} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 48, "C": 0.046415888336127774, "split": "test", "acc": 0.72, "acc_std": 0.04273862421744528, "f1": 0.7057587221521648, "f1_std": 0.044971335367298276, "bacc": 0.7079796264855688, "bacc_std": 0.04557266058417626} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 49, "C": 21.54434690031882, "split": "test", "acc": 0.63, "acc_std": 0.04461612264641562, "f1": 0.5906626839252129, "f1_std": 0.05022010635383451, "bacc": 0.5895585738539898, "bacc_std": 0.0476709310012149} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 50, "C": 0.046415888336127774, "split": "test", "acc": 0.62, "acc_std": 0.04496966088375584, "f1": 0.5766488413547237, "f1_std": 0.04951057930269233, "bacc": 0.5764006791171477, "bacc_std": 0.04692339153460689} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 51, "C": 166.81005372000556, "split": "test", "acc": 0.58, "acc_std": 0.048286495006367974, "f1": 0.5586380832282472, "f1_std": 0.04974940210500168, "bacc": 0.5594227504244482, "bacc_std": 0.05029281467088384} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 52, "C": 10000.0, "split": "test", "acc": 0.6, "acc_std": 0.04579351919213023, "f1": 0.5659722222222222, "f1_std": 0.04925406011264427, "bacc": 0.565365025466893, "bacc_std": 0.04806826570016233} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 53, "C": 0.3593813663804626, "split": "test", "acc": 0.64, "acc_std": 0.0469640884080592, "f1": 0.6179966044142615, "f1_std": 0.049485775426490075, "bacc": 0.6179966044142615, "bacc_std": 0.04946046063370554} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 54, "C": 0.005994842503189409, "split": "test", "acc": 0.58, "acc_std": 0.04574024048909232, "f1": 0.5320855614973261, "f1_std": 0.04958838864055525, "bacc": 0.533955857385399, "bacc_std": 0.04709241242656537} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 55, "C": 0.005994842503189409, "split": "test", "acc": 0.67, "acc_std": 0.04415746369528032, "f1": 0.6349153667441089, "f1_std": 0.049904255678792676, "bacc": 0.6320033955857385, "bacc_std": 0.04752474573120637} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 56, "C": 0.046415888336127774, "split": "test", "acc": 0.6, "acc_std": 0.04722749622836256, "f1": 0.554367201426025, "f1_std": 0.05184764705639123, "bacc": 0.5551782682512734, "bacc_std": 0.04921557198275155} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 57, "C": 1291.5496650148827, "split": "test", "acc": 0.54, "acc_std": 0.045391148916941945, "f1": 0.5066495066495067, "f1_std": 0.04736195667403996, "bacc": 0.5067911714770797, "bacc_std": 0.04680466897804246} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 58, "C": 2.782559402207126, "split": "test", "acc": 0.6, "acc_std": 0.05059841894763116, "f1": 0.586606035551881, "f1_std": 0.051566613354036284, "bacc": 0.5908319185059423, "bacc_std": 0.05286090978452304} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 59, "C": 0.3593813663804626, "split": "test", "acc": 0.61, "acc_std": 0.04544418994767098, "f1": 0.584, "f1_std": 0.04880134471886391, "bacc": 0.583616298811545, "bacc_std": 0.0482897077886412} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 60, "C": 0.046415888336127774, "split": "test", "acc": 0.62, "acc_std": 0.0445647573762048, "f1": 0.5703301673450927, "f1_std": 0.05189641083281955, "bacc": 0.5713073005093379, "bacc_std": 0.04819611399807796} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 61, "C": 2.782559402207126, "split": "test", "acc": 0.62, "acc_std": 0.04878309133296085, "f1": 0.6041666666666667, "f1_std": 0.0504087178797371, "bacc": 0.6069609507640068, "bacc_std": 0.05147683489102075} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 62, "C": 2.782559402207126, "split": "test", "acc": 0.62, "acc_std": 0.04470892081005758, "f1": 0.5766488413547237, "f1_std": 0.051230962153924295, "bacc": 0.5764006791171477, "bacc_std": 0.04816240430858508} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 63, "C": 0.3593813663804626, "split": "test", "acc": 0.65, "acc_std": 0.044012957183084164, "f1": 0.612789025334661, "f1_std": 0.0499307236021549, "bacc": 0.6107809847198642, "bacc_std": 0.047596035179020786} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 64, "C": 0.3593813663804626, "split": "test", "acc": 0.58, "acc_std": 0.04408596602094593, "f1": 0.5174632352941176, "f1_std": 0.04978369394562174, "bacc": 0.5237691001697793, "bacc_std": 0.045539796534067506} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 65, "C": 0.005994842503189409, "split": "test", "acc": 0.62, "acc_std": 0.04364443148902275, "f1": 0.5634191176470589, "f1_std": 0.0497341805791602, "bacc": 0.566213921901528, "bacc_std": 0.04532692078806033} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 66, "C": 0.046415888336127774, "split": "test", "acc": 0.62, "acc_std": 0.047445564597757714, "f1": 0.5766488413547237, "f1_std": 0.05323989017347579, "bacc": 0.5764006791171477, "bacc_std": 0.05035196169889621} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 67, "C": 0.005994842503189409, "split": "test", "acc": 0.63, "acc_std": 0.04251672141640275, "f1": 0.5783475783475784, "f1_std": 0.05042489907174505, "bacc": 0.5793718166383701, "bacc_std": 0.046241978510727685} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 68, "C": 0.3593813663804626, "split": "test", "acc": 0.67, "acc_std": 0.04525172261914456, "f1": 0.6396986570586308, "f1_std": 0.04981313171528849, "bacc": 0.6370967741935484, "bacc_std": 0.04834291719141169} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 69, "C": 0.3593813663804626, "split": "test", "acc": 0.65, "acc_std": 0.04852052761460864, "f1": 0.6266666666666667, "f1_std": 0.050694635309452375, "bacc": 0.6260611205432938, "bacc_std": 0.05054351696289294} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 70, "C": 166.81005372000556, "split": "test", "acc": 0.62, "acc_std": 0.049178857245771784, "f1": 0.5924495924495925, "f1_std": 0.05254896741665565, "bacc": 0.5916808149405772, "bacc_std": 0.05163844634223699} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 71, "C": 0.005994842503189409, "split": "test", "acc": 0.68, "acc_std": 0.04248242460123951, "f1": 0.6259934548854604, "f1_std": 0.05184213375875312, "bacc": 0.6247877758913413, "bacc_std": 0.046450884160565614} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 72, "C": 0.046415888336127774, "split": "test", "acc": 0.65, "acc_std": 0.04822495619489975, "f1": 0.6266666666666667, "f1_std": 0.05084725711274687, "bacc": 0.6260611205432938, "bacc_std": 0.050588126733053566} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 73, "C": 0.046415888336127774, "split": "test", "acc": 0.59, "acc_std": 0.04853411171536984, "f1": 0.5670995670995671, "f1_std": 0.05095303993970923, "bacc": 0.5674872665534805, "bacc_std": 0.05112136508990824} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 74, "C": 0.3593813663804626, "split": "test", "acc": 0.54, "acc_std": 0.04803586576715361, "f1": 0.5208333333333334, "f1_std": 0.04903229462366983, "bacc": 0.5220713073005093, "bacc_std": 0.05017417160224676} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 75, "C": 0.005994842503189409, "split": "test", "acc": 0.66, "acc_std": 0.043411791025019915, "f1": 0.6155585707824514, "f1_std": 0.05114531892880968, "bacc": 0.6137521222410866, "bacc_std": 0.04766509388303385} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 76, "C": 0.005994842503189409, "split": "test", "acc": 0.71, "acc_std": 0.04099207240430764, "f1": 0.6745595331612613, "f1_std": 0.048329821382448755, "bacc": 0.6693548387096775, "bacc_std": 0.04560264171602428} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 77, "C": 0.3593813663804626, "split": "test", "acc": 0.65, "acc_std": 0.04188965982196561, "f1": 0.6011396011396011, "f1_std": 0.050306228237410336, "bacc": 0.6005942275042444, "bacc_std": 0.046290792522531155} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 78, "C": 0.046415888336127774, "split": "test", "acc": 0.64, "acc_std": 0.041536157742381515, "f1": 0.5714285714285714, "f1_std": 0.05077231471479952, "bacc": 0.5772495755517827, "bacc_std": 0.04453176264697273} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 79, "C": 0.005994842503189409, "split": "test", "acc": 0.65, "acc_std": 0.04328001848428441, "f1": 0.6011396011396011, "f1_std": 0.051311004718037005, "bacc": 0.6005942275042444, "bacc_std": 0.047111185142446485} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 80, "C": 166.81005372000556, "split": "test", "acc": 0.65, "acc_std": 0.04900204077382899, "f1": 0.6368917937545389, "f1_std": 0.05013910766868334, "bacc": 0.6413412563667232, "bacc_std": 0.05094303396519896} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 81, "C": 0.046415888336127774, "split": "test", "acc": 0.69, "acc_std": 0.04321490020814579, "f1": 0.6521153630344518, "f1_std": 0.05007210926986836, "bacc": 0.6481324278438031, "bacc_std": 0.047131502575524876} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 82, "C": 0.046415888336127774, "split": "test", "acc": 0.64, "acc_std": 0.04569689705001862, "f1": 0.5989304812834224, "f1_std": 0.052631815012195715, "bacc": 0.597623089983022, "bacc_std": 0.049675594135949325} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 83, "C": 0.005994842503189409, "split": "test", "acc": 0.5, "acc_std": 0.049919551280034564, "f1": 0.46943972835314096, "f1_std": 0.05090797057956661, "bacc": 0.46943972835314096, "bacc_std": 0.050947567462096575} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 84, "C": 0.3593813663804626, "split": "test", "acc": 0.57, "acc_std": 0.048472029047688936, "f1": 0.5305164319248826, "f1_std": 0.052403019587527945, "bacc": 0.5309847198641766, "bacc_std": 0.050763842718247604} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 85, "C": 0.005994842503189409, "split": "test", "acc": 0.63, "acc_std": 0.03903214572631129, "f1": 0.5552350042072365, "f1_std": 0.049209447960951995, "bacc": 0.5640916808149405, "bacc_std": 0.042195067189945666} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 86, "C": 0.000774263682681127, "split": "test", "acc": 0.57, "acc_std": 0.03058665722173639, "f1": 0.4188403838356535, "f1_std": 0.03849912047256905, "bacc": 0.47495755517826826, "bacc_std": 0.030203411748350506} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 87, "C": 0.046415888336127774, "split": "test", "acc": 0.61, "acc_std": 0.04503268146579771, "f1": 0.5481404240528328, "f1_std": 0.053650766658701075, "bacc": 0.5530560271646858, "bacc_std": 0.04822666352904696} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 88, "C": 0.3593813663804626, "split": "test", "acc": 0.61, "acc_std": 0.04636836852855619, "f1": 0.568536342515765, "f1_std": 0.05121611411553309, "bacc": 0.5683361629881154, "bacc_std": 0.04902371503535925} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 89, "C": 2.782559402207126, "split": "test", "acc": 0.64, "acc_std": 0.04633914543881879, "f1": 0.625, "f1_std": 0.04808719306320222, "bacc": 0.6281833616298811, "bacc_std": 0.04933901810449358} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 90, "C": 0.005994842503189409, "split": "test", "acc": 0.63, "acc_std": 0.04407201379560503, "f1": 0.5783475783475784, "f1_std": 0.05104837649481271, "bacc": 0.5793718166383701, "bacc_std": 0.046970346487666306} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 91, "C": 2.782559402207126, "split": "test", "acc": 0.66, "acc_std": 0.04771540631703769, "f1": 0.6458333333333333, "f1_std": 0.04885103137013177, "bacc": 0.6494057724957556, "bacc_std": 0.049234130724096464} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 92, "C": 2.782559402207126, "split": "test", "acc": 0.6, "acc_std": 0.04840649130023782, "f1": 0.5755517826825127, "f1_std": 0.05051458579379349, "bacc": 0.5755517826825127, "bacc_std": 0.050340552409902255} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 93, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.04467597117019394, "f1": 0.5604395604395604, "f1_std": 0.05035782772831961, "bacc": 0.5602716468590832, "bacc_std": 0.04818643239543958} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 94, "C": 0.3593813663804626, "split": "test", "acc": 0.67, "acc_std": 0.04287003615580467, "f1": 0.6515679442508711, "f1_std": 0.04512405826061534, "bacc": 0.652376910016978, "bacc_std": 0.04545498137931404} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 95, "C": 0.005994842503189409, "split": "test", "acc": 0.61, "acc_std": 0.03702559114990604, "f1": 0.5215311004784688, "f1_std": 0.047803639949767066, "bacc": 0.5377758913412564, "bacc_std": 0.03958387413505116} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 96, "C": 0.005994842503189409, "split": "test", "acc": 0.57, "acc_std": 0.04390181773002114, "f1": 0.5242836596968692, "f1_std": 0.04799898063125751, "bacc": 0.5258913412563667, "bacc_std": 0.045817714750352824} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 97, "C": 0.046415888336127774, "split": "test", "acc": 0.66, "acc_std": 0.047348997877463044, "f1": 0.6263736263736264, "f1_std": 0.052551055417661155, "bacc": 0.6239388794567062, "bacc_std": 0.05048498314970916} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 98, "C": 2.782559402207126, "split": "test", "acc": 0.64, "acc_std": 0.04859219690444135, "f1": 0.609375, "f1_std": 0.054329714479281935, "bacc": 0.6078098471986417, "bacc_std": 0.053024487059845096} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 99, "C": 0.046415888336127774, "split": "test", "acc": 0.65, "acc_std": 0.04409714730002384, "f1": 0.6224786970121885, "f1_std": 0.04813814011602131, "bacc": 0.6209677419354839, "bacc_std": 0.04743906778182589} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 100, "C": 0.046415888336127774, "split": "test", "acc": 0.61, "acc_std": 0.04761096932430593, "f1": 0.5793334052421529, "f1_std": 0.0514722941810896, "bacc": 0.5785229202037352, "bacc_std": 0.05039685349764104} +eval results (random splits): + +| model | repr | clf | dataset | split | n_trials | C | C_std | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|-----------:|-------:|--------:|-------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | ppmi_dx | train | 100 | 142.33 | 1012.9 | 0.8606 | 0.1075 | 0.84209 | 0.12421 | 0.83639 | 0.12678 | +| flat_mae | patch | logistic | ppmi_dx | test | 100 | 142.33 | 1012.9 | 0.6252 | 0.041839 | 0.58719 | 0.048234 | 0.58895 | 0.044559 | + + +done! total time: 0:05:36 diff --git a/input_space_v3/flat_lr1e-3_1/pretrain/config.yaml b/input_space_v3/flat_lr1e-3_1/pretrain/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..8afc57ab7eef41755f40f9c3587ace0498c0293b --- /dev/null +++ b/input_space_v3/flat_lr1e-3_1/pretrain/config.yaml @@ -0,0 +1,102 @@ +name: input_space_v3/flat_lr1e-3_1/pretrain +notes: input_space ablation v3 flat_lr1e-3_1; use tube masking and on-disk data (input_space=flat + base_lr=1e-3 seed=5401) +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain +input_space: flat +patch_size: 16 +num_frames: 16 +t_patch_size: 4 +mask_ratio: 0.9 +pred_mask_ratio: null +masking: tube +masking_kwargs: {} +mask_patch_size: null +model: mae_vit_base +model_kwargs: + decoding: attn + pos_embed: sep + target_norm: null + pca_norm_nc: 2 + t_pred_stride: 2 + no_decode_pos: true + mask_drop_scale: false + pred_edge_pad: 0 + gauss_sigma: null + class_token: true + reg_tokens: 0 + no_embed_class: true + head_init_scale: 0.0 + decoder_depth: 4 + drop_path_rate: 0.0 +datasets: + hcp-train: + type: wds + url: /data/fmri-datasets/pretrain/hcpya-all.${input_space}.wds/hcpya-all-${input_space}-{00000..01799}.tar + clipping: random + clipping_kwargs: + oversample: 4.0 + shuffle: true + buffer_size: 2000 + samples_per_epoch: 200000 + hcp-train-subset: + type: arrow + root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/validation + split_range: + - 0 + - 2000 + shuffle: false + hcp-val: + type: arrow + root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/test + split_range: + - 0 + - 2000 + shuffle: false +train_dataset: hcp-train +eval_datasets: +- hcp-train-subset +- hcp-val +val_dataset: null +clip_vmax: 3.0 +normalize: frame +tr_scale: null +crop_scale: null +crop_aspect: null +gray_jitter: null +num_workers: 16 +epochs: 100 +batch_size: 32 +accum_iter: 1 +base_lr: 0.001 +min_lr: 0.0 +warmup_epochs: 5 +weight_decay: 0.05 +betas: +- 0.9 +- 0.95 +clip_grad: 1.0 +amp: true +amp_dtype: float16 +ckpt: null +resume: true +auto_resume: true +start_epoch: 0 +max_checkpoints: 0 +checkpoint_period: null +plot_period: 5 +device: cuda +presend_cuda: false +seed: 5401 +debug: false +wandb: true +wandb_entity: null +wandb_project: fMRI-foundation-model +rank: 0 +world_size: 1 +gpu: 0 +distributed: true +dist_backend: nccl +in_chans: 1 +img_size: +- 224 +- 560 diff --git a/input_space_v3/flat_lr1e-3_1/pretrain/log.json b/input_space_v3/flat_lr1e-3_1/pretrain/log.json new file mode 100644 index 0000000000000000000000000000000000000000..e8a54a26c315baa84bb5aca8012dda88fbf03ae3 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_1/pretrain/log.json @@ -0,0 +1,100 @@ +{"epoch": 0, "train/lr": 1.2502400076802458e-05, "train/grad": 0.05918827326536179, "train/loss": 0.9929688432025909, "eval/hcp-train-subset/loss": 0.9921299190290512, "eval/hcp-val/loss": 0.9906984433051078} +{"epoch": 1, "train/lr": 3.750320010240327e-05, "train/grad": 0.08643446314930915, "train/loss": 0.9875358654117584, "eval/hcp-train-subset/loss": 0.9895215467099221, "eval/hcp-val/loss": 0.9866379037980111} +{"epoch": 2, "train/lr": 6.250400012800409e-05, "train/grad": 0.13588601619312912, "train/loss": 0.9837714320373535, "eval/hcp-train-subset/loss": 0.9839242369897904, "eval/hcp-val/loss": 0.9801209588204661} +{"epoch": 3, "train/lr": 8.75048001536049e-05, "train/grad": 0.19876538398860455, "train/loss": 0.9743550951290131, "eval/hcp-train-subset/loss": 0.9632774956764714, "eval/hcp-val/loss": 0.9606849753087566} +{"epoch": 4, "train/lr": 0.00011250559953918529, "train/grad": 0.25153835915701606, "train/loss": 0.9356088685607911, "eval/hcp-train-subset/loss": 0.9184494335805217, "eval/hcp-val/loss": 0.9129575067950834} +{"epoch": 5, "train/lr": 0.00012498860637884563, "train/grad": 0.1622875796647974, "train/loss": 0.892770802192688, "eval/hcp-train-subset/loss": 0.8805275184492911, "eval/hcp-val/loss": 0.8744441991852175} +{"epoch": 6, "train/lr": 0.0001249202705377922, "train/grad": 0.10130744191072315, "train/loss": 0.8697980627250671, "eval/hcp-train-subset/loss": 0.8679759771593155, "eval/hcp-val/loss": 0.8623736087352999} +{"epoch": 7, "train/lr": 0.0001247836790473516, "train/grad": 0.08313484155607533, "train/loss": 0.8609552175807953, "eval/hcp-train-subset/loss": 0.8621031430459791, "eval/hcp-val/loss": 0.8565207498688852} +{"epoch": 8, "train/lr": 0.000124578981268311, "train/grad": 0.07428935083347606, "train/loss": 0.8549646623039245, "eval/hcp-train-subset/loss": 0.858587194834986, "eval/hcp-val/loss": 0.8529048956209614} +{"epoch": 9, "train/lr": 0.00012430640103468907, "train/grad": 0.06986930098375078, "train/loss": 0.8515365135669708, "eval/hcp-train-subset/loss": 0.8552034410738176, "eval/hcp-val/loss": 0.8503843709345786} +{"epoch": 10, "train/lr": 0.00012396623640896796, "train/grad": 0.06642564091302498, "train/loss": 0.849890394191742, "eval/hcp-train-subset/loss": 0.8541372697199544, "eval/hcp-val/loss": 0.8485986253907604} +{"epoch": 11, "train/lr": 0.0001235588593561712, "train/grad": 0.06524651159470816, "train/loss": 0.8486777857589721, "eval/hcp-train-subset/loss": 0.8515217669548527, "eval/hcp-val/loss": 0.84664610412813} +{"epoch": 12, "train/lr": 0.00012308471533712604, "train/grad": 0.065498447448144, "train/loss": 0.8445446167945861, "eval/hcp-train-subset/loss": 0.8520120141967651, "eval/hcp-val/loss": 0.8460227193370942} +{"epoch": 13, "train/lr": 0.00012254432282135565, "train/grad": 0.06421579502038646, "train/loss": 0.8447173558902741, "eval/hcp-train-subset/loss": 0.8499766059460179, "eval/hcp-val/loss": 0.8446888327598572} +{"epoch": 14, "train/lr": 0.00012193827272014171, "train/grad": 0.06284531338018737, "train/loss": 0.8431001119232178, "eval/hcp-train-subset/loss": 0.84914190923014, "eval/hcp-val/loss": 0.8432932842162347} +{"epoch": 15, "train/lr": 0.00012126722774037197, "train/grad": 0.06313478412993834, "train/loss": 0.8414368620300293, "eval/hcp-train-subset/loss": 0.8482136851356875, "eval/hcp-val/loss": 0.8436122892364379} +{"epoch": 16, "train/lr": 0.00012053192165988122, "train/grad": 0.06498945658007207, "train/loss": 0.8400391171169281, "eval/hcp-train-subset/loss": 0.8478436566168263, "eval/hcp-val/loss": 0.8426969051361084} +{"epoch": 17, "train/lr": 0.00011973315852507104, "train/grad": 0.0644361399717524, "train/loss": 0.8388603707027436, "eval/hcp-train-subset/loss": 0.8458859209091433, "eval/hcp-val/loss": 0.8417230594542718} +{"epoch": 18, "train/lr": 0.00011887181177170142, "train/grad": 0.06442134446022071, "train/loss": 0.83773605260849, "eval/hcp-train-subset/loss": 0.8457485610438932, "eval/hcp-val/loss": 0.8410216175740765} +{"epoch": 19, "train/lr": 0.00011794882326980209, "train/grad": 0.06496212434376052, "train/loss": 0.8358815899181365, "eval/hcp-train-subset/loss": 0.8453317794107622, "eval/hcp-val/loss": 0.8408496639420909} +{"epoch": 20, "train/lr": 0.00011696520229374954, "train/grad": 0.06655993163060973, "train/loss": 0.8355108136081696, "eval/hcp-train-subset/loss": 0.8452288066187212, "eval/hcp-val/loss": 0.8413715381776133} +{"epoch": 21, "train/lr": 0.00011592202441863837, "train/grad": 0.06672464138452588, "train/loss": 0.8356040711307525, "eval/hcp-train-subset/loss": 0.8450446138458867, "eval/hcp-val/loss": 0.8406175980644841} +{"epoch": 22, "train/lr": 0.00011482043034415979, "train/grad": 0.0662221235935548, "train/loss": 0.8357748672771453, "eval/hcp-train-subset/loss": 0.8446697967667733, "eval/hcp-val/loss": 0.8400395329921476} +{"epoch": 23, "train/lr": 0.00011366162464726024, "train/grad": 0.0671542270834082, "train/loss": 0.8335803558063507, "eval/hcp-train-subset/loss": 0.8438299798196361, "eval/hcp-val/loss": 0.8416102201707901} +{"epoch": 24, "train/lr": 0.0001124468744649569, "train/grad": 0.0674696560840572, "train/loss": 0.8330728803634644, "eval/hcp-train-subset/loss": 0.8446507357781933, "eval/hcp-val/loss": 0.8404553532600403} +{"epoch": 25, "train/lr": 0.0001111775081087387, "train/grad": 0.06901710742199733, "train/loss": 0.8329814314079285, "eval/hcp-train-subset/loss": 0.8443768976196167, "eval/hcp-val/loss": 0.840334718265841} +{"epoch": 26, "train/lr": 0.0001098549136120796, "train/grad": 0.07007557242302637, "train/loss": 0.8286457947921753, "eval/hcp-train-subset/loss": 0.842490134700652, "eval/hcp-val/loss": 0.8391403113642046} +{"epoch": 27, "train/lr": 0.00010848053721264312, "train/grad": 0.07062890857090774, "train/loss": 0.8302095539665222, "eval/hcp-train-subset/loss": 0.843563723948694, "eval/hcp-val/loss": 0.83940177963626} +{"epoch": 28, "train/lr": 0.00010705588177084458, "train/grad": 0.07005136467518808, "train/loss": 0.8313083849716186, "eval/hcp-train-subset/loss": 0.8423055227725736, "eval/hcp-val/loss": 0.8391136882766601} +{"epoch": 29, "train/lr": 0.00010558250512649171, "train/grad": 0.07106202407569356, "train/loss": 0.8308209407520294, "eval/hcp-train-subset/loss": 0.8415361479405434, "eval/hcp-val/loss": 0.839051979203378} +{"epoch": 30, "train/lr": 0.00010406201839531515, "train/grad": 0.07026484764983613, "train/loss": 0.8302689732837677, "eval/hcp-train-subset/loss": 0.8427148817046997, "eval/hcp-val/loss": 0.8391120145397801} +{"epoch": 31, "train/lr": 0.00010249608420723018, "train/grad": 0.07262431026976579, "train/loss": 0.8296879758739472, "eval/hcp-train-subset/loss": 0.842633209882244, "eval/hcp-val/loss": 0.8384755936361128} +{"epoch": 32, "train/lr": 0.00010088641488828097, "train/grad": 0.07389799755414836, "train/loss": 0.8282942691707611, "eval/hcp-train-subset/loss": 0.8422023932779988, "eval/hcp-val/loss": 0.8374918785787397} +{"epoch": 33, "train/lr": 9.923477058823526e-05, "train/grad": 0.074779011497588, "train/loss": 0.8278728552627563, "eval/hcp-train-subset/loss": 0.842065574661378, "eval/hcp-val/loss": 0.8379004578436574} +{"epoch": 34, "train/lr": 9.754295735588547e-05, "train/grad": 0.07399195055185165, "train/loss": 0.828330591096878, "eval/hcp-train-subset/loss": 0.840960237287706, "eval/hcp-val/loss": 0.8374566118563375} +{"epoch": 35, "train/lr": 9.581282516416285e-05, "train/grad": 0.07808313538206146, "train/loss": 0.8259139669799804, "eval/hcp-train-subset/loss": 0.8417881948332633, "eval/hcp-val/loss": 0.8382225526917365} +{"epoch": 36, "train/lr": 9.404626588721676e-05, "train/grad": 0.07825824150099113, "train/loss": 0.8249022184181214, "eval/hcp-train-subset/loss": 0.8414575544095808, "eval/hcp-val/loss": 0.8377928570393594} +{"epoch": 37, "train/lr": 9.224521123168153e-05, "train/grad": 0.07674224697470665, "train/loss": 0.8262329187965393, "eval/hcp-train-subset/loss": 0.8418971002101898, "eval/hcp-val/loss": 0.8383183536990997} +{"epoch": 38, "train/lr": 9.041163062437843e-05, "train/grad": 0.08048803252509455, "train/loss": 0.8237208746051788, "eval/hcp-train-subset/loss": 0.8400741238747874, "eval/hcp-val/loss": 0.8379353784745739} +{"epoch": 39, "train/lr": 8.85475290587822e-05, "train/grad": 0.0795553954556997, "train/loss": 0.8249224576854706, "eval/hcp-train-subset/loss": 0.8383492192914409, "eval/hcp-val/loss": 0.8374601198780921} +{"epoch": 40, "train/lr": 8.665494490258622e-05, "train/grad": 0.07970285661021391, "train/loss": 0.8249309525489807, "eval/hcp-train-subset/loss": 0.8401587470885246, "eval/hcp-val/loss": 0.8379610363514193} +{"epoch": 41, "train/lr": 8.473594766877838e-05, "train/grad": 0.0801894052222712, "train/loss": 0.8230879835319519, "eval/hcp-train-subset/loss": 0.8406558978942132, "eval/hcp-val/loss": 0.8378814506915307} +{"epoch": 42, "train/lr": 8.279263575265999e-05, "train/grad": 0.08271710580233348, "train/loss": 0.8229351184082031, "eval/hcp-train-subset/loss": 0.8393751978874207, "eval/hcp-val/loss": 0.8370053931590049} +{"epoch": 43, "train/lr": 8.082713413727944e-05, "train/grad": 0.08239421413772562, "train/loss": 0.8234495847606659, "eval/hcp-train-subset/loss": 0.8389828637723, "eval/hcp-val/loss": 0.8366277958116224} +{"epoch": 44, "train/lr": 7.884159206979602e-05, "train/grad": 0.08259474607129386, "train/loss": 0.8234488940620422, "eval/hcp-train-subset/loss": 0.8389662408059643, "eval/hcp-val/loss": 0.8361711357870409} +{"epoch": 45, "train/lr": 7.683818071130916e-05, "train/grad": 0.08461914609504048, "train/loss": 0.8223505304050446, "eval/hcp-train-subset/loss": 0.8389441899714931, "eval/hcp-val/loss": 0.8369546599926487} +{"epoch": 46, "train/lr": 7.481909076272522e-05, "train/grad": 0.08551212333289455, "train/loss": 0.8220764071750641, "eval/hcp-train-subset/loss": 0.8385918842208001, "eval/hcp-val/loss": 0.8356989458683999} +{"epoch": 47, "train/lr": 7.278653006925963e-05, "train/grad": 0.08458247658451984, "train/loss": 0.8217558120536804, "eval/hcp-train-subset/loss": 0.8363034705961904, "eval/hcp-val/loss": 0.8360912665244071} +{"epoch": 48, "train/lr": 7.074272120618864e-05, "train/grad": 0.08782085147775738, "train/loss": 0.8218074759578705, "eval/hcp-train-subset/loss": 0.8364891227214567, "eval/hcp-val/loss": 0.8352825305154247} +{"epoch": 49, "train/lr": 6.868989904849677e-05, "train/grad": 0.08863332531415821, "train/loss": 0.8208740701961518, "eval/hcp-train-subset/loss": 0.8361696543232087, "eval/hcp-val/loss": 0.8351583701948966} +{"epoch": 50, "train/lr": 6.6630308327075e-05, "train/grad": 0.09162561612191496, "train/loss": 0.8181926302814484, "eval/hcp-train-subset/loss": 0.8361222061418718, "eval/hcp-val/loss": 0.835366545184966} +{"epoch": 51, "train/lr": 6.456620117413798e-05, "train/grad": 0.08864295912293199, "train/loss": 0.8214564589595794, "eval/hcp-train-subset/loss": 0.8362859766329488, "eval/hcp-val/loss": 0.8356587829128388} +{"epoch": 52, "train/lr": 6.249983466055255e-05, "train/grad": 0.09243136079338182, "train/loss": 0.8204797601032257, "eval/hcp-train-subset/loss": 0.8353299748513007, "eval/hcp-val/loss": 0.8351250867689809} +{"epoch": 53, "train/lr": 6.0433468327763305e-05, "train/grad": 0.09267968720680314, "train/loss": 0.8206929054927826, "eval/hcp-train-subset/loss": 0.8356479002583411, "eval/hcp-val/loss": 0.8350481179452711} +{"epoch": 54, "train/lr": 5.83693617170174e-05, "train/grad": 0.09556325646160564, "train/loss": 0.8187564165401459, "eval/hcp-train-subset/loss": 0.8347384497042625, "eval/hcp-val/loss": 0.8345636187061187} +{"epoch": 55, "train/lr": 5.6309771898588165e-05, "train/grad": 0.0967984134897771, "train/loss": 0.8166789912986755, "eval/hcp-train-subset/loss": 0.8355942762667133, "eval/hcp-val/loss": 0.8344885985697469} +{"epoch": 56, "train/lr": 5.4256951003704155e-05, "train/grad": 0.09803778580038137, "train/loss": 0.816890696811676, "eval/hcp-train-subset/loss": 0.8349985153444351, "eval/hcp-val/loss": 0.8341330318681656} +{"epoch": 57, "train/lr": 5.221314376187425e-05, "train/grad": 0.09944536457619745, "train/loss": 0.8167387428569793, "eval/hcp-train-subset/loss": 0.8344313444629792, "eval/hcp-val/loss": 0.834641880566074} +{"epoch": 58, "train/lr": 5.018058504631059e-05, "train/grad": 0.09958522594217854, "train/loss": 0.817336377325058, "eval/hcp-train-subset/loss": 0.8351881907832238, "eval/hcp-val/loss": 0.834782225470389} +{"epoch": 59, "train/lr": 4.816149743012713e-05, "train/grad": 0.09959036470645043, "train/loss": 0.8182291454696655, "eval/hcp-train-subset/loss": 0.8361680671092002, "eval/hcp-val/loss": 0.8332956683251166} +{"epoch": 60, "train/lr": 4.615808875598772e-05, "train/grad": 0.10259796107824648, "train/loss": 0.8158963592624664, "eval/hcp-train-subset/loss": 0.8331548350472604, "eval/hcp-val/loss": 0.8335854488034402} +{"epoch": 61, "train/lr": 4.417254972186445e-05, "train/grad": 0.10255611465824344, "train/loss": 0.8166392568206787, "eval/hcp-train-subset/loss": 0.8314469004831007, "eval/hcp-val/loss": 0.8327904968492447} +{"epoch": 62, "train/lr": 4.220705148553925e-05, "train/grad": 0.10298956617076194, "train/loss": 0.8185492950820923, "eval/hcp-train-subset/loss": 0.8328874053493622, "eval/hcp-val/loss": 0.8334381839921398} +{"epoch": 63, "train/lr": 4.026374329047657e-05, "train/grad": 0.10746201977839809, "train/loss": 0.8162345561027526, "eval/hcp-train-subset/loss": 0.8329646510462607, "eval/hcp-val/loss": 0.8339532104230696} +{"epoch": 64, "train/lr": 3.834475011565652e-05, "train/grad": 0.10928437678279324, "train/loss": 0.8138387530422211, "eval/hcp-train-subset/loss": 0.8319701437027224, "eval/hcp-val/loss": 0.8327077579113745} +{"epoch": 65, "train/lr": 3.6452170351940815e-05, "train/grad": 0.1111544074995083, "train/loss": 0.8130520414924621, "eval/hcp-train-subset/loss": 0.8315751975582492, "eval/hcp-val/loss": 0.833052687106594} +{"epoch": 66, "train/lr": 3.458807350751516e-05, "train/grad": 0.10976299479975939, "train/loss": 0.8155115792751312, "eval/hcp-train-subset/loss": 0.830179670164662, "eval/hcp-val/loss": 0.8324808334150622} +{"epoch": 67, "train/lr": 3.2754497944910164e-05, "train/grad": 0.11114765969795844, "train/loss": 0.8153975456237793, "eval/hcp-train-subset/loss": 0.8315584332712235, "eval/hcp-val/loss": 0.8323470632876119} +{"epoch": 68, "train/lr": 3.0953448652083367e-05, "train/grad": 0.11379729848315691, "train/loss": 0.815397158164978, "eval/hcp-train-subset/loss": 0.831339652499845, "eval/hcp-val/loss": 0.8325808807726829} +{"epoch": 69, "train/lr": 2.9186895049993948e-05, "train/grad": 0.11309180574708651, "train/loss": 0.8147507821083069, "eval/hcp-train-subset/loss": 0.8300857313217656, "eval/hcp-val/loss": 0.8317489902819356} +{"epoch": 70, "train/lr": 2.7456768839068717e-05, "train/grad": 0.11637300148556208, "train/loss": 0.8120452905464173, "eval/hcp-train-subset/loss": 0.8308043527987695, "eval/hcp-val/loss": 0.8314424666666216} +{"epoch": 71, "train/lr": 2.5764961886919063e-05, "train/grad": 0.11897015785047171, "train/loss": 0.8133431961917877, "eval/hcp-train-subset/loss": 0.828442019800986, "eval/hcp-val/loss": 0.8312790759148136} +{"epoch": 72, "train/lr": 2.411332415960724e-05, "train/grad": 0.11750669605589893, "train/loss": 0.8148402929401398, "eval/hcp-train-subset/loss": 0.8256296380873649, "eval/hcp-val/loss": 0.8310690733694261} +{"epoch": 73, "train/lr": 2.2503661698739544e-05, "train/grad": 0.12267351013459689, "train/loss": 0.8107552459049225, "eval/hcp-train-subset/loss": 0.8264283297523376, "eval/hcp-val/loss": 0.8313339794835737} +{"epoch": 74, "train/lr": 2.0937734646583902e-05, "train/grad": 0.12058638094205328, "train/loss": 0.814898381986618, "eval/hcp-train-subset/loss": 0.8258475545913943, "eval/hcp-val/loss": 0.8310053098586297} +{"epoch": 75, "train/lr": 1.9417255321381202e-05, "train/grad": 0.12270904013242113, "train/loss": 0.8136728283786774, "eval/hcp-train-subset/loss": 0.8250523363390276, "eval/hcp-val/loss": 0.8309880322025668} +{"epoch": 76, "train/lr": 1.7943886344950134e-05, "train/grad": 0.12530584074079837, "train/loss": 0.8135763104724884, "eval/hcp-train-subset/loss": 0.8256851482775903, "eval/hcp-val/loss": 0.8305567868294255} +{"epoch": 77, "train/lr": 1.651923882463461e-05, "train/grad": 0.12650547205099644, "train/loss": 0.8123081521701813, "eval/hcp-train-subset/loss": 0.8252428712383393, "eval/hcp-val/loss": 0.8301111392436489} +{"epoch": 78, "train/lr": 1.5144870591581508e-05, "train/grad": 0.12645622388265487, "train/loss": 0.8131512977027893, "eval/hcp-train-subset/loss": 0.8259089675641829, "eval/hcp-val/loss": 0.8307072251073776} +{"epoch": 79, "train/lr": 1.3822284497275662e-05, "train/grad": 0.13148694397645777, "train/loss": 0.8098872527313232, "eval/hcp-train-subset/loss": 0.8248400284397986, "eval/hcp-val/loss": 0.8304543841269708} +{"epoch": 80, "train/lr": 1.2552926770192975e-05, "train/grad": 0.1316617213370858, "train/loss": 0.8112667320537568, "eval/hcp-train-subset/loss": 0.8224094279350773, "eval/hcp-val/loss": 0.8300398991953942} +{"epoch": 81, "train/lr": 1.1338185434371453e-05, "train/grad": 0.13541070847858977, "train/loss": 0.8101442498207092, "eval/hcp-train-subset/loss": 0.8221168421929882, "eval/hcp-val/loss": 0.8293871110485446} +{"epoch": 82, "train/lr": 1.0179388791627326e-05, "train/grad": 0.13431470943602916, "train/loss": 0.810937711315155, "eval/hcp-train-subset/loss": 0.8225122392177582, "eval/hcp-val/loss": 0.8298606151534665} +{"epoch": 83, "train/lr": 9.07780396907607e-06, "train/grad": 0.13297319503694238, "train/loss": 0.8128102447605133, "eval/hcp-train-subset/loss": 0.8215558000149266, "eval/hcp-val/loss": 0.8295864799330311} +{"epoch": 84, "train/lr": 8.034635533547902e-06, "train/grad": 0.1367734780108196, "train/loss": 0.812502010936737, "eval/hcp-train-subset/loss": 0.8209137974246856, "eval/hcp-val/loss": 0.8289313460550001} +{"epoch": 85, "train/lr": 7.051024174411275e-06, "train/grad": 0.13609225850010254, "train/loss": 0.8129409290409089, "eval/hcp-train-subset/loss": 0.8203659759413812, "eval/hcp-val/loss": 0.8287168385521058} +{"epoch": 86, "train/lr": 6.1280454562463606e-06, "train/grad": 0.1403935137002883, "train/loss": 0.8096636202907562, "eval/hcp-train-subset/loss": 0.8195635186087701, "eval/hcp-val/loss": 0.8287464101468364} +{"epoch": 87, "train/lr": 5.266708642730326e-06, "train/grad": 0.14241944419702224, "train/loss": 0.8105250136852264, "eval/hcp-train-subset/loss": 0.8192712183921568, "eval/hcp-val/loss": 0.8284706848282968} +{"epoch": 88, "train/lr": 4.467955593022733e-06, "train/grad": 0.14085762070115326, "train/loss": 0.8131479990291596, "eval/hcp-train-subset/loss": 0.8187609824442095, "eval/hcp-val/loss": 0.8285069619455645} +{"epoch": 89, "train/lr": 3.732659731856291e-06, "train/grad": 0.14256878364643363, "train/loss": 0.8116393257522583, "eval/hcp-train-subset/loss": 0.8184836006933643, "eval/hcp-val/loss": 0.8286462368503693} +{"epoch": 90, "train/lr": 3.0616250944596583e-06, "train/grad": 0.1419861989379616, "train/loss": 0.8128543576908112, "eval/hcp-train-subset/loss": 0.8173224724108173, "eval/hcp-val/loss": 0.828626609617664} +{"epoch": 91, "train/lr": 2.4555854473568305e-06, "train/grad": 0.14416408179406548, "train/loss": 0.8136971681880951, "eval/hcp-train-subset/loss": 0.817156094697214, "eval/hcp-val/loss": 0.8280816030117774} +{"epoch": 92, "train/lr": 1.915203486004091e-06, "train/grad": 0.14429353748714902, "train/loss": 0.8139333023452758, "eval/hcp-train-subset/loss": 0.8167237966291366, "eval/hcp-val/loss": 0.8282202001540891} +{"epoch": 93, "train/lr": 1.4410701101423926e-06, "train/grad": 0.14750944703283053, "train/loss": 0.8117554086589813, "eval/hcp-train-subset/loss": 0.815984800938637, "eval/hcp-val/loss": 0.8275601450474032} +{"epoch": 94, "train/lr": 1.0337037776570775e-06, "train/grad": 0.14833410468047306, "train/loss": 0.8130846704006195, "eval/hcp-train-subset/loss": 0.8157883238407874, "eval/hcp-val/loss": 0.8280747225207667} +{"epoch": 95, "train/lr": 6.935499376518293e-07, "train/grad": 0.1484180090736679, "train/loss": 0.8139602139377594, "eval/hcp-train-subset/loss": 0.8153513794945132, "eval/hcp-val/loss": 0.8276245420978915} +{"epoch": 96, "train/lr": 4.209805433566085e-07, "train/grad": 0.14818024880526942, "train/loss": 0.8144279089927673, "eval/hcp-train-subset/loss": 0.8150702368828558, "eval/hcp-val/loss": 0.827619343996048} +{"epoch": 97, "train/lr": 2.1629364540224422e-07, "train/grad": 0.14771381277088283, "train/loss": 0.8156582881355285, "eval/hcp-train-subset/loss": 0.8149832410197104, "eval/hcp-val/loss": 0.8278578769776129} +{"epoch": 98, "train/lr": 7.971306590647406e-08, "train/grad": 0.14993381041141463, "train/loss": 0.8155630426311493, "eval/hcp-train-subset/loss": 0.8152456562365255, "eval/hcp-val/loss": 0.8275897233716903} +{"epoch": 99, "train/lr": 1.1388153727718725e-08, "train/grad": 0.15090593402053346, "train/loss": 0.813764778213501, "eval/hcp-train-subset/loss": 0.8150549752096976, "eval/hcp-val/loss": 0.8269499742215679} diff --git a/input_space_v3/flat_lr1e-3_1/pretrain/log.txt b/input_space_v3/flat_lr1e-3_1/pretrain/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..dbe6415f78d98e36a014247db0314e14e2012adf --- /dev/null +++ b/input_space_v3/flat_lr1e-3_1/pretrain/log.txt @@ -0,0 +1,8762 @@ +pretraining fmri mae +start: 2026-03-31 13:08:49 +cwd: /data/connor/fmri-fm +sha: ae0eae57a44753a80f371738f3276b064d5077cb, status: clean, branch: dev/clane9 +config: +name: input_space_v3/flat_lr1e-3_1/pretrain +notes: input_space ablation v3 flat_lr1e-3_1; use tube masking and on-disk data (input_space=flat + base_lr=1e-3 seed=5401) +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain +input_space: flat +patch_size: 16 +num_frames: 16 +t_patch_size: 4 +mask_ratio: 0.9 +pred_mask_ratio: null +masking: tube +masking_kwargs: {} +mask_patch_size: null +model: mae_vit_base +model_kwargs: + decoding: attn + pos_embed: sep + target_norm: null + pca_norm_nc: 2 + t_pred_stride: 2 + no_decode_pos: true + mask_drop_scale: false + pred_edge_pad: 0 + gauss_sigma: null + class_token: true + reg_tokens: 0 + no_embed_class: true + head_init_scale: 0.0 + decoder_depth: 4 + drop_path_rate: 0.0 +datasets: + hcp-train: + type: wds + url: /data/fmri-datasets/pretrain/hcpya-all.${input_space}.wds/hcpya-all-${input_space}-{00000..01799}.tar + clipping: random + clipping_kwargs: + oversample: 4.0 + shuffle: true + buffer_size: 2000 + samples_per_epoch: 200000 + hcp-train-subset: + type: arrow + root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/validation + split_range: + - 0 + - 2000 + shuffle: false + hcp-val: + type: arrow + root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/test + split_range: + - 0 + - 2000 + shuffle: false +train_dataset: hcp-train +eval_datasets: +- hcp-train-subset +- hcp-val +val_dataset: null +clip_vmax: 3.0 +normalize: frame +tr_scale: null +crop_scale: null +crop_aspect: null +gray_jitter: null +num_workers: 16 +epochs: 100 +batch_size: 32 +accum_iter: 1 +base_lr: 0.001 +min_lr: 0.0 +warmup_epochs: 5 +weight_decay: 0.05 +betas: +- 0.9 +- 0.95 +clip_grad: 1.0 +amp: true +amp_dtype: float16 +ckpt: null +resume: true +auto_resume: true +start_epoch: 0 +max_checkpoints: 0 +checkpoint_period: null +plot_period: 5 +device: cuda +presend_cuda: false +seed: 5401 +debug: false +wandb: true +wandb_entity: null +wandb_project: fMRI-foundation-model +rank: 0 +world_size: 1 +gpu: 0 +distributed: true +dist_backend: nccl +in_chans: 1 +img_size: +- 224 +- 560 + +train transform: +Compose( + ToTensor() + TemporalCenterCrop(num_frames=16) + Normalize(mode='frame') + Clip(vmax=3.0) + FlatUnmask((224, 560)) +) +val transform: +Compose( + ToTensor() + TemporalCenterCrop(num_frames=16) + Normalize(mode='frame') + Clip(vmax=3.0) + FlatUnmask((224, 560)) +) +mask generator: +TubeMasking( + mask_ratio=0.9 + (patchify): Patchify2D((224, 560), (16, 16), in_chans=1) +) +loading dataset: hcp-train + +type: wds +url: /data/fmri-datasets/pretrain/hcpya-all.${input_space}.wds/hcpya-all-${input_space}-{00000..01799}.tar +clipping: random +clipping_kwargs: + oversample: 4.0 +shuffle: true +buffer_size: 2000 +samples_per_epoch: 200000 + +loading dataset: hcp-train-subset + +type: arrow +root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/validation +split_range: +- 0 +- 2000 +shuffle: false + +split indices: [899, 472, 767, 116, 1265, 1852, 300, 1335, 361, 1560] +loading dataset: hcp-val + +type: arrow +root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/test +split_range: +- 0 +- 2000 +shuffle: false + +split indices: [1075, 1189, 738, 1350, 965, 1964, 1367, 1183, 1619, 1407] +model: +MaskedAutoencoderViT( + decoding=attn, t_pred_stride=2, pred_edge_pad=0, no_decode_pos=True + (encoder): MaskedEncoder( + class_token=True, reg_tokens=0, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) + (pred_patchify): StridedPatchify3D((16, 224, 560), (2, 16, 16), in_chans=1, t_stride=2) + (decoder): MaskedDecoder( + cross_decode=False, class_token=True, no_embed_class=True + (pos_embed): SeparablePosEmbed(512, (4, 14, 35)) + (proj): Linear(in_features=768, out_features=512, bias=True) + (blocks): ModuleList( + (0-3): 4 x Block( + (norm1): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=16 + (q): Linear(in_features=512, out_features=512, bias=True) + (k): Linear(in_features=512, out_features=512, bias=True) + (v): Linear(in_features=512, out_features=512, bias=True) + (proj): Linear(in_features=512, out_features=512, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=512, out_features=2048, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=2048, out_features=512, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (head): Linear(in_features=512, out_features=512, bias=True) + ) +) +num params: 99.7M +total batch size: 32 = 32 bs per gpu x 1 accum x 1 gpus +lr: 1.25e-04 = 1.00e-03 x 32 / 256 +full schedule: epochs = 100 (steps = 625000) +warmup: epochs = 5 (steps = 31250) +start training for 100 epochs +Train: [0] [ 0/6250] eta: 21:51:01 lr: 0.000000 grad: 0.0217 (0.0217) loss: 0.9959 (0.9959) time: 12.5858 data: 9.6939 max mem: 8589 +Train: [0] [ 100/6250] eta: 1:03:02 lr: 0.000000 grad: 0.0126 (0.0157) loss: 0.9962 (0.9962) time: 0.1237 data: 0.0183 max mem: 9394 +Train: [0] [ 200/6250] eta: 0:50:28 lr: 0.000001 grad: 0.0138 (0.0148) loss: 0.9959 (0.9961) time: 0.1122 data: 0.0004 max mem: 9394 +Train: [0] [ 300/6250] eta: 0:42:50 lr: 0.000001 grad: 0.0130 (0.0143) loss: 0.9956 (0.9960) time: 0.2598 data: 0.1509 max mem: 9394 +Train: [0] [ 400/6250] eta: 0:39:19 lr: 0.000002 grad: 0.0128 (0.0140) loss: 0.9959 (0.9960) time: 0.6061 data: 0.4123 max mem: 9394 +Train: [0] [ 500/6250] eta: 0:35:58 lr: 0.000002 grad: 0.0128 (0.0138) loss: 0.9952 (0.9960) time: 0.1667 data: 0.0608 max mem: 9394 +Train: [0] [ 600/6250] eta: 0:32:57 lr: 0.000002 grad: 0.0128 (0.0137) loss: 0.9956 (0.9960) time: 0.2710 data: 0.1556 max mem: 9394 +Train: [0] [ 700/6250] eta: 0:30:30 lr: 0.000003 grad: 0.0135 (0.0136) loss: 0.9958 (0.9960) time: 0.1751 data: 0.0004 max mem: 9394 +Train: [0] [ 800/6250] eta: 0:29:01 lr: 0.000003 grad: 0.0133 (0.0136) loss: 0.9957 (0.9960) time: 0.2456 data: 0.1567 max mem: 9394 +Train: [0] [ 900/6250] eta: 0:28:33 lr: 0.000004 grad: 0.0137 (0.0136) loss: 0.9956 (0.9959) time: 0.5163 data: 0.4068 max mem: 9394 +Train: [0] [1000/6250] eta: 0:26:20 lr: 0.000004 grad: 0.0166 (0.0138) loss: 0.9958 (0.9959) time: 0.1392 data: 0.0533 max mem: 9394 +Train: [0] [1100/6250] eta: 0:24:48 lr: 0.000004 grad: 0.0145 (0.0140) loss: 0.9965 (0.9959) time: 0.0985 data: 0.0002 max mem: 9394 +Train: [0] [1200/6250] eta: 0:23:16 lr: 0.000005 grad: 0.0181 (0.0144) loss: 0.9959 (0.9959) time: 0.0825 data: 0.0002 max mem: 9394 +Train: [0] [1300/6250] eta: 0:21:52 lr: 0.000005 grad: 0.0200 (0.0148) loss: 0.9960 (0.9959) time: 0.1421 data: 0.0634 max mem: 9394 +Train: [0] [1400/6250] eta: 0:20:47 lr: 0.000006 grad: 0.0257 (0.0154) loss: 0.9959 (0.9958) time: 0.1576 data: 0.0243 max mem: 9394 +Train: [0] [1500/6250] eta: 0:19:43 lr: 0.000006 grad: 0.0250 (0.0163) loss: 0.9958 (0.9958) time: 0.1380 data: 0.0589 max mem: 9394 +Train: [0] [1600/6250] eta: 0:18:46 lr: 0.000006 grad: 0.0344 (0.0175) loss: 0.9952 (0.9958) time: 0.1581 data: 0.0790 max mem: 9394 +Train: [0] [1700/6250] eta: 0:17:58 lr: 0.000007 grad: 0.0533 (0.0189) loss: 0.9951 (0.9958) time: 0.2540 data: 0.1365 max mem: 9394 +Train: [0] [1800/6250] eta: 0:17:10 lr: 0.000007 grad: 0.0420 (0.0204) loss: 0.9951 (0.9957) time: 0.0965 data: 0.0054 max mem: 9394 +Train: [0] [1900/6250] eta: 0:16:23 lr: 0.000008 grad: 0.0411 (0.0215) loss: 0.9944 (0.9957) time: 0.1283 data: 0.0430 max mem: 9394 +Train: [0] [2000/6250] eta: 0:15:41 lr: 0.000008 grad: 0.0460 (0.0227) loss: 0.9948 (0.9956) time: 0.1454 data: 0.0677 max mem: 9394 +Train: [0] [2100/6250] eta: 0:15:17 lr: 0.000008 grad: 0.0468 (0.0238) loss: 0.9950 (0.9956) time: 0.1093 data: 0.0263 max mem: 9394 +Train: [0] [2200/6250] eta: 0:14:36 lr: 0.000009 grad: 0.0489 (0.0250) loss: 0.9950 (0.9956) time: 0.1269 data: 0.0448 max mem: 9394 +Train: [0] [2300/6250] eta: 0:14:00 lr: 0.000009 grad: 0.0416 (0.0262) loss: 0.9941 (0.9955) time: 0.1446 data: 0.0661 max mem: 9394 +Train: [0] [2400/6250] eta: 0:13:27 lr: 0.000010 grad: 0.0519 (0.0273) loss: 0.9939 (0.9955) time: 0.1253 data: 0.0430 max mem: 9394 +Train: [0] [2500/6250] eta: 0:13:03 lr: 0.000010 grad: 0.0536 (0.0286) loss: 0.9947 (0.9954) time: 0.4014 data: 0.3005 max mem: 9394 +Train: [0] [2600/6250] eta: 0:12:32 lr: 0.000010 grad: 0.0634 (0.0298) loss: 0.9946 (0.9954) time: 0.1584 data: 0.0788 max mem: 9394 +Train: [0] [2700/6250] eta: 0:12:05 lr: 0.000011 grad: 0.0580 (0.0311) loss: 0.9940 (0.9953) time: 0.1663 data: 0.0489 max mem: 9394 +Train: [0] [2800/6250] eta: 0:11:39 lr: 0.000011 grad: 0.0686 (0.0325) loss: 0.9932 (0.9953) time: 0.1254 data: 0.0373 max mem: 9394 +Train: [0] [2900/6250] eta: 0:11:11 lr: 0.000012 grad: 0.0536 (0.0336) loss: 0.9944 (0.9952) time: 0.1426 data: 0.0638 max mem: 9394 +Train: [0] [3000/6250] eta: 0:10:53 lr: 0.000012 grad: 0.0708 (0.0347) loss: 0.9928 (0.9951) time: 0.5207 data: 0.3381 max mem: 9394 +Train: [0] [3100/6250] eta: 0:10:25 lr: 0.000012 grad: 0.0646 (0.0359) loss: 0.9929 (0.9951) time: 0.1372 data: 0.0622 max mem: 9394 +Train: [0] [3200/6250] eta: 0:09:59 lr: 0.000013 grad: 0.0714 (0.0371) loss: 0.9921 (0.9950) time: 0.1506 data: 0.0647 max mem: 9394 +Train: [0] [3300/6250] eta: 0:09:34 lr: 0.000013 grad: 0.0598 (0.0382) loss: 0.9934 (0.9949) time: 0.1377 data: 0.0604 max mem: 9394 +Train: [0] [3400/6250] eta: 0:09:12 lr: 0.000014 grad: 0.0691 (0.0395) loss: 0.9921 (0.9949) time: 0.0907 data: 0.0002 max mem: 9394 +Train: [0] [3500/6250] eta: 0:08:48 lr: 0.000014 grad: 0.0709 (0.0404) loss: 0.9920 (0.9948) time: 0.1309 data: 0.0490 max mem: 9394 +Train: [0] [3600/6250] eta: 0:08:25 lr: 0.000014 grad: 0.0843 (0.0415) loss: 0.9917 (0.9947) time: 0.1152 data: 0.0380 max mem: 9394 +Train: [0] [3700/6250] eta: 0:08:02 lr: 0.000015 grad: 0.0745 (0.0425) loss: 0.9930 (0.9946) time: 0.1413 data: 0.0616 max mem: 9394 +Train: [0] [3800/6250] eta: 0:07:39 lr: 0.000015 grad: 0.0671 (0.0435) loss: 0.9931 (0.9946) time: 0.1314 data: 0.0551 max mem: 9394 +Train: [0] [3900/6250] eta: 0:07:17 lr: 0.000016 grad: 0.0864 (0.0446) loss: 0.9924 (0.9945) time: 0.1289 data: 0.0470 max mem: 9394 +Train: [0] [4000/6250] eta: 0:06:55 lr: 0.000016 grad: 0.0865 (0.0455) loss: 0.9913 (0.9944) time: 0.1418 data: 0.0628 max mem: 9394 +Train: [0] [4100/6250] eta: 0:06:34 lr: 0.000016 grad: 0.0610 (0.0463) loss: 0.9928 (0.9943) time: 0.1435 data: 0.0652 max mem: 9394 +Train: [0] [4200/6250] eta: 0:06:14 lr: 0.000017 grad: 0.0745 (0.0471) loss: 0.9903 (0.9943) time: 0.1393 data: 0.0602 max mem: 9394 +Train: [0] [4300/6250] eta: 0:05:53 lr: 0.000017 grad: 0.0802 (0.0480) loss: 0.9912 (0.9942) time: 0.1288 data: 0.0457 max mem: 9394 +Train: [0] [4400/6250] eta: 0:05:34 lr: 0.000018 grad: 0.0740 (0.0488) loss: 0.9906 (0.9941) time: 0.1601 data: 0.0810 max mem: 9394 +Train: [0] [4500/6250] eta: 0:05:14 lr: 0.000018 grad: 0.0662 (0.0495) loss: 0.9922 (0.9940) time: 0.1526 data: 0.0689 max mem: 9394 +Train: [0] [4600/6250] eta: 0:04:54 lr: 0.000018 grad: 0.0731 (0.0501) loss: 0.9908 (0.9940) time: 0.1346 data: 0.0499 max mem: 9394 +Train: [0] [4700/6250] eta: 0:04:37 lr: 0.000019 grad: 0.0812 (0.0507) loss: 0.9916 (0.9939) time: 0.1718 data: 0.0837 max mem: 9394 +Train: [0] [4800/6250] eta: 0:04:17 lr: 0.000019 grad: 0.0707 (0.0513) loss: 0.9915 (0.9939) time: 0.1237 data: 0.0360 max mem: 9394 +Train: [0] [4900/6250] eta: 0:03:58 lr: 0.000020 grad: 0.0788 (0.0520) loss: 0.9911 (0.9938) time: 0.1318 data: 0.0567 max mem: 9394 +Train: [0] [5000/6250] eta: 0:03:40 lr: 0.000020 grad: 0.0867 (0.0526) loss: 0.9897 (0.9937) time: 0.1198 data: 0.0443 max mem: 9394 +Train: [0] [5100/6250] eta: 0:03:21 lr: 0.000020 grad: 0.0981 (0.0533) loss: 0.9897 (0.9937) time: 0.1401 data: 0.0627 max mem: 9394 +Train: [0] [5200/6250] eta: 0:03:03 lr: 0.000021 grad: 0.0703 (0.0539) loss: 0.9902 (0.9936) time: 0.1350 data: 0.0585 max mem: 9394 +Train: [0] [5300/6250] eta: 0:02:44 lr: 0.000021 grad: 0.0939 (0.0545) loss: 0.9887 (0.9935) time: 0.1353 data: 0.0553 max mem: 9394 +Train: [0] [5400/6250] eta: 0:02:27 lr: 0.000022 grad: 0.0722 (0.0551) loss: 0.9912 (0.9935) time: 0.0910 data: 0.0048 max mem: 9394 +Train: [0] [5500/6250] eta: 0:02:09 lr: 0.000022 grad: 0.0872 (0.0555) loss: 0.9903 (0.9934) time: 0.1183 data: 0.0119 max mem: 9394 +Train: [0] [5600/6250] eta: 0:01:51 lr: 0.000022 grad: 0.0871 (0.0562) loss: 0.9886 (0.9934) time: 0.1234 data: 0.0404 max mem: 9394 +Train: [0] [5700/6250] eta: 0:01:34 lr: 0.000023 grad: 0.0820 (0.0567) loss: 0.9895 (0.9933) time: 0.1404 data: 0.0658 max mem: 9394 +Train: [0] [5800/6250] eta: 0:01:16 lr: 0.000023 grad: 0.0686 (0.0572) loss: 0.9900 (0.9932) time: 0.1366 data: 0.0506 max mem: 9394 +Train: [0] [5900/6250] eta: 0:00:59 lr: 0.000024 grad: 0.0778 (0.0576) loss: 0.9901 (0.9932) time: 0.1274 data: 0.0498 max mem: 9394 +Train: [0] [6000/6250] eta: 0:00:42 lr: 0.000024 grad: 0.0901 (0.0581) loss: 0.9899 (0.9931) time: 0.1454 data: 0.0677 max mem: 9394 +Train: [0] [6100/6250] eta: 0:00:25 lr: 0.000024 grad: 0.0699 (0.0586) loss: 0.9898 (0.9931) time: 0.1123 data: 0.0266 max mem: 9394 +Train: [0] [6200/6250] eta: 0:00:08 lr: 0.000025 grad: 0.0735 (0.0590) loss: 0.9902 (0.9930) time: 0.1474 data: 0.0666 max mem: 9394 +Train: [0] [6249/6250] eta: 0:00:00 lr: 0.000025 grad: 0.0840 (0.0592) loss: 0.9893 (0.9930) time: 0.1288 data: 0.0423 max mem: 9394 +Train: [0] Total time: 0:17:42 (0.1699 s / it) +Averaged stats: lr: 0.000025 grad: 0.0840 (0.0592) loss: 0.9893 (0.9930) +Eval (hcp-train-subset): [0] [ 0/62] eta: 0:05:02 loss: 0.9911 (0.9911) time: 4.8849 data: 4.8510 max mem: 9394 +Eval (hcp-train-subset): [0] [61/62] eta: 0:00:00 loss: 0.9930 (0.9921) time: 0.1418 data: 0.1119 max mem: 9394 +Eval (hcp-train-subset): [0] Total time: 0:00:14 (0.2359 s / it) +Averaged stats (hcp-train-subset): loss: 0.9930 (0.9921) +Eval (hcp-val): [0] [ 0/62] eta: 0:04:32 loss: 0.9880 (0.9880) time: 4.3874 data: 4.3532 max mem: 9394 +Eval (hcp-val): [0] [61/62] eta: 0:00:00 loss: 0.9909 (0.9907) time: 0.1347 data: 0.1084 max mem: 9394 +Eval (hcp-val): [0] Total time: 0:00:13 (0.2106 s / it) +Averaged stats (hcp-val): loss: 0.9909 (0.9907) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +Train: [1] [ 0/6250] eta: 6:37:44 lr: 0.000025 grad: 0.0832 (0.0832) loss: 0.9882 (0.9882) time: 3.8183 data: 3.5127 max mem: 9394 +Train: [1] [ 100/6250] eta: 0:19:38 lr: 0.000025 grad: 0.0664 (0.0753) loss: 0.9900 (0.9912) time: 0.1309 data: 0.0402 max mem: 9394 +Train: [1] [ 200/6250] eta: 0:16:43 lr: 0.000026 grad: 0.0896 (0.0835) loss: 0.9892 (0.9899) time: 0.1259 data: 0.0412 max mem: 9394 +Train: [1] [ 300/6250] eta: 0:15:44 lr: 0.000026 grad: 0.0776 (0.0863) loss: 0.9902 (0.9896) time: 0.1671 data: 0.0769 max mem: 9394 +Train: [1] [ 400/6250] eta: 0:15:06 lr: 0.000027 grad: 0.0791 (0.0862) loss: 0.9898 (0.9896) time: 0.1372 data: 0.0502 max mem: 9394 +Train: [1] [ 500/6250] eta: 0:14:22 lr: 0.000027 grad: 0.0850 (0.0880) loss: 0.9887 (0.9894) time: 0.1370 data: 0.0572 max mem: 9394 +Train: [1] [ 600/6250] eta: 0:14:00 lr: 0.000027 grad: 0.0854 (0.0893) loss: 0.9898 (0.9894) time: 0.1715 data: 0.0854 max mem: 9394 +Train: [1] [ 700/6250] eta: 0:13:44 lr: 0.000028 grad: 0.0835 (0.0897) loss: 0.9891 (0.9893) time: 0.2006 data: 0.1076 max mem: 9394 +Train: [1] [ 800/6250] eta: 0:13:36 lr: 0.000028 grad: 0.0745 (0.0893) loss: 0.9901 (0.9893) time: 0.1122 data: 0.0367 max mem: 9394 +Train: [1] [ 900/6250] eta: 0:14:00 lr: 0.000029 grad: 0.0876 (0.0881) loss: 0.9880 (0.9893) time: 0.1661 data: 0.0604 max mem: 9394 +Train: [1] [1000/6250] eta: 0:14:30 lr: 0.000029 grad: 0.0806 (0.0879) loss: 0.9882 (0.9893) time: 0.0908 data: 0.0002 max mem: 9394 +Train: [1] [1100/6250] eta: 0:14:14 lr: 0.000029 grad: 0.0714 (0.0874) loss: 0.9903 (0.9893) time: 0.1210 data: 0.0434 max mem: 9394 +Train: [1] [1200/6250] eta: 0:13:55 lr: 0.000030 grad: 0.0749 (0.0868) loss: 0.9899 (0.9893) time: 0.1358 data: 0.0510 max mem: 9394 +Train: [1] [1300/6250] eta: 0:13:27 lr: 0.000030 grad: 0.0680 (0.0859) loss: 0.9908 (0.9894) time: 0.1379 data: 0.0661 max mem: 9394 +Train: [1] [1400/6250] eta: 0:13:20 lr: 0.000031 grad: 0.0777 (0.0856) loss: 0.9895 (0.9894) time: 0.2224 data: 0.1464 max mem: 9394 +Train: [1] [1500/6250] eta: 0:12:53 lr: 0.000031 grad: 0.0728 (0.0855) loss: 0.9891 (0.9893) time: 0.1284 data: 0.0528 max mem: 9394 +Train: [1] [1600/6250] eta: 0:12:28 lr: 0.000031 grad: 0.0845 (0.0855) loss: 0.9890 (0.9893) time: 0.1318 data: 0.0527 max mem: 9394 +Train: [1] [1700/6250] eta: 0:12:04 lr: 0.000032 grad: 0.0738 (0.0853) loss: 0.9903 (0.9893) time: 0.1269 data: 0.0513 max mem: 9394 +Train: [1] [1800/6250] eta: 0:11:42 lr: 0.000032 grad: 0.0848 (0.0849) loss: 0.9876 (0.9893) time: 0.1296 data: 0.0504 max mem: 9394 +Train: [1] [1900/6250] eta: 0:11:20 lr: 0.000033 grad: 0.0692 (0.0847) loss: 0.9880 (0.9893) time: 0.1314 data: 0.0502 max mem: 9394 +Train: [1] [2000/6250] eta: 0:11:01 lr: 0.000033 grad: 0.0810 (0.0845) loss: 0.9890 (0.9892) time: 0.1335 data: 0.0553 max mem: 9394 +Train: [1] [2100/6250] eta: 0:10:59 lr: 0.000033 grad: 0.0776 (0.0844) loss: 0.9872 (0.9892) time: 0.1360 data: 0.0498 max mem: 9394 +Train: [1] [2200/6250] eta: 0:10:38 lr: 0.000034 grad: 0.0702 (0.0842) loss: 0.9902 (0.9891) time: 0.1411 data: 0.0633 max mem: 9394 +Train: [1] [2300/6250] eta: 0:10:21 lr: 0.000034 grad: 0.0754 (0.0841) loss: 0.9890 (0.9891) time: 0.1529 data: 0.0610 max mem: 9394 +Train: [1] [2400/6250] eta: 0:10:00 lr: 0.000035 grad: 0.0799 (0.0840) loss: 0.9874 (0.9891) time: 0.1214 data: 0.0406 max mem: 9394 +Train: [1] [2500/6250] eta: 0:09:47 lr: 0.000035 grad: 0.0834 (0.0840) loss: 0.9862 (0.9891) time: 0.0998 data: 0.0002 max mem: 9394 +Train: [1] [2600/6250] eta: 0:09:28 lr: 0.000035 grad: 0.0820 (0.0841) loss: 0.9878 (0.9890) time: 0.1369 data: 0.0602 max mem: 9394 +Train: [1] [2700/6250] eta: 0:09:09 lr: 0.000036 grad: 0.0794 (0.0841) loss: 0.9897 (0.9890) time: 0.1251 data: 0.0526 max mem: 9394 +Train: [1] [2800/6250] eta: 0:08:53 lr: 0.000036 grad: 0.0733 (0.0840) loss: 0.9897 (0.9889) time: 0.1177 data: 0.0384 max mem: 9394 +Train: [1] [2900/6250] eta: 0:08:40 lr: 0.000037 grad: 0.0709 (0.0837) loss: 0.9888 (0.9889) time: 0.1114 data: 0.0357 max mem: 9394 +Train: [1] [3000/6250] eta: 0:08:23 lr: 0.000037 grad: 0.0795 (0.0838) loss: 0.9887 (0.9889) time: 0.1220 data: 0.0361 max mem: 9394 +Train: [1] [3100/6250] eta: 0:08:09 lr: 0.000037 grad: 0.0797 (0.0837) loss: 0.9875 (0.9889) time: 0.1889 data: 0.1035 max mem: 9394 +Train: [1] [3200/6250] eta: 0:07:50 lr: 0.000038 grad: 0.0771 (0.0837) loss: 0.9880 (0.9889) time: 0.1324 data: 0.0555 max mem: 9394 +Train: [1] [3300/6250] eta: 0:07:33 lr: 0.000038 grad: 0.0727 (0.0837) loss: 0.9885 (0.9888) time: 0.1378 data: 0.0594 max mem: 9394 +Train: [1] [3400/6250] eta: 0:07:16 lr: 0.000039 grad: 0.0764 (0.0837) loss: 0.9878 (0.9888) time: 0.1209 data: 0.0440 max mem: 9394 +Train: [1] [3500/6250] eta: 0:07:00 lr: 0.000039 grad: 0.0836 (0.0837) loss: 0.9874 (0.9887) time: 0.1555 data: 0.0769 max mem: 9394 +Train: [1] [3600/6250] eta: 0:06:43 lr: 0.000039 grad: 0.0785 (0.0839) loss: 0.9863 (0.9886) time: 0.1255 data: 0.0465 max mem: 9394 +Train: [1] [3700/6250] eta: 0:06:27 lr: 0.000040 grad: 0.0757 (0.0840) loss: 0.9880 (0.9886) time: 0.1575 data: 0.0809 max mem: 9394 +Train: [1] [3800/6250] eta: 0:06:11 lr: 0.000040 grad: 0.0797 (0.0840) loss: 0.9874 (0.9885) time: 0.1481 data: 0.0673 max mem: 9394 +Train: [1] [3900/6250] eta: 0:05:55 lr: 0.000041 grad: 0.0881 (0.0841) loss: 0.9868 (0.9885) time: 0.1109 data: 0.0286 max mem: 9394 +Train: [1] [4000/6250] eta: 0:05:39 lr: 0.000041 grad: 0.0827 (0.0842) loss: 0.9868 (0.9885) time: 0.1415 data: 0.0654 max mem: 9394 +Train: [1] [4100/6250] eta: 0:05:23 lr: 0.000041 grad: 0.0887 (0.0844) loss: 0.9863 (0.9884) time: 0.1281 data: 0.0431 max mem: 9394 +Train: [1] [4200/6250] eta: 0:05:07 lr: 0.000042 grad: 0.0805 (0.0845) loss: 0.9868 (0.9884) time: 0.1252 data: 0.0485 max mem: 9394 +Train: [1] [4300/6250] eta: 0:04:52 lr: 0.000042 grad: 0.0785 (0.0846) loss: 0.9866 (0.9883) time: 0.1293 data: 0.0501 max mem: 9394 +Train: [1] [4400/6250] eta: 0:04:36 lr: 0.000043 grad: 0.0834 (0.0847) loss: 0.9877 (0.9883) time: 0.1470 data: 0.0704 max mem: 9394 +Train: [1] [4500/6250] eta: 0:04:21 lr: 0.000043 grad: 0.0926 (0.0848) loss: 0.9863 (0.9882) time: 0.1299 data: 0.0495 max mem: 9394 +Train: [1] [4600/6250] eta: 0:04:06 lr: 0.000043 grad: 0.0800 (0.0847) loss: 0.9875 (0.9882) time: 0.1303 data: 0.0497 max mem: 9394 +Train: [1] [4700/6250] eta: 0:03:51 lr: 0.000044 grad: 0.0781 (0.0847) loss: 0.9855 (0.9882) time: 0.1335 data: 0.0560 max mem: 9394 +Train: [1] [4800/6250] eta: 0:03:36 lr: 0.000044 grad: 0.0825 (0.0847) loss: 0.9874 (0.9881) time: 0.1510 data: 0.0694 max mem: 9394 +Train: [1] [4900/6250] eta: 0:03:21 lr: 0.000045 grad: 0.0804 (0.0847) loss: 0.9868 (0.9881) time: 0.1233 data: 0.0486 max mem: 9394 +Train: [1] [5000/6250] eta: 0:03:05 lr: 0.000045 grad: 0.0884 (0.0848) loss: 0.9849 (0.9880) time: 0.1428 data: 0.0649 max mem: 9394 +Train: [1] [5100/6250] eta: 0:02:50 lr: 0.000045 grad: 0.0775 (0.0848) loss: 0.9875 (0.9880) time: 0.1308 data: 0.0550 max mem: 9394 +Train: [1] [5200/6250] eta: 0:02:35 lr: 0.000046 grad: 0.0837 (0.0850) loss: 0.9865 (0.9880) time: 0.1823 data: 0.0771 max mem: 9394 +Train: [1] [5300/6250] eta: 0:02:21 lr: 0.000046 grad: 0.0790 (0.0851) loss: 0.9854 (0.9879) time: 0.1316 data: 0.0533 max mem: 9394 +Train: [1] [5400/6250] eta: 0:02:05 lr: 0.000047 grad: 0.0900 (0.0853) loss: 0.9849 (0.9879) time: 0.1436 data: 0.0644 max mem: 9394 +Train: [1] [5500/6250] eta: 0:01:51 lr: 0.000047 grad: 0.0872 (0.0855) loss: 0.9853 (0.9878) time: 0.1876 data: 0.1152 max mem: 9394 +Train: [1] [5600/6250] eta: 0:01:36 lr: 0.000047 grad: 0.0854 (0.0856) loss: 0.9863 (0.9878) time: 0.1586 data: 0.0837 max mem: 9394 +Train: [1] [5700/6250] eta: 0:01:21 lr: 0.000048 grad: 0.0872 (0.0857) loss: 0.9866 (0.9878) time: 0.1176 data: 0.0364 max mem: 9394 +Train: [1] [5800/6250] eta: 0:01:06 lr: 0.000048 grad: 0.0984 (0.0858) loss: 0.9849 (0.9877) time: 0.1220 data: 0.0503 max mem: 9394 +Train: [1] [5900/6250] eta: 0:00:51 lr: 0.000049 grad: 0.0887 (0.0860) loss: 0.9865 (0.9877) time: 0.1445 data: 0.0638 max mem: 9394 +Train: [1] [6000/6250] eta: 0:00:36 lr: 0.000049 grad: 0.0926 (0.0861) loss: 0.9843 (0.9876) time: 0.0939 data: 0.0002 max mem: 9394 +Train: [1] [6100/6250] eta: 0:00:22 lr: 0.000049 grad: 0.0948 (0.0863) loss: 0.9866 (0.9876) time: 0.1369 data: 0.0612 max mem: 9394 +Train: [1] [6200/6250] eta: 0:00:07 lr: 0.000050 grad: 0.0752 (0.0864) loss: 0.9851 (0.9876) time: 0.1122 data: 0.0274 max mem: 9394 +Train: [1] [6249/6250] eta: 0:00:00 lr: 0.000050 grad: 0.0892 (0.0864) loss: 0.9851 (0.9875) time: 0.1466 data: 0.0646 max mem: 9394 +Train: [1] Total time: 0:15:24 (0.1479 s / it) +Averaged stats: lr: 0.000050 grad: 0.0892 (0.0864) loss: 0.9851 (0.9875) +Eval (hcp-train-subset): [1] [ 0/62] eta: 0:03:26 loss: 0.9873 (0.9873) time: 3.3236 data: 3.2552 max mem: 9394 +Eval (hcp-train-subset): [1] [61/62] eta: 0:00:00 loss: 0.9882 (0.9895) time: 0.1070 data: 0.0800 max mem: 9394 +Eval (hcp-train-subset): [1] Total time: 0:00:14 (0.2350 s / it) +Averaged stats (hcp-train-subset): loss: 0.9882 (0.9895) +Eval (hcp-val): [1] [ 0/62] eta: 0:04:59 loss: 0.9878 (0.9878) time: 4.8256 data: 4.7967 max mem: 9394 +Eval (hcp-val): [1] [61/62] eta: 0:00:00 loss: 0.9868 (0.9866) time: 0.1206 data: 0.0920 max mem: 9394 +Eval (hcp-val): [1] Total time: 0:00:13 (0.2209 s / it) +Averaged stats (hcp-val): loss: 0.9868 (0.9866) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +Train: [2] [ 0/6250] eta: 6:52:16 lr: 0.000050 grad: 0.0838 (0.0838) loss: 0.9884 (0.9884) time: 3.9578 data: 3.8050 max mem: 9394 +Train: [2] [ 100/6250] eta: 0:19:34 lr: 0.000050 grad: 0.0846 (0.0976) loss: 0.9868 (0.9856) time: 0.1415 data: 0.0623 max mem: 9394 +Train: [2] [ 200/6250] eta: 0:17:00 lr: 0.000051 grad: 0.0916 (0.1018) loss: 0.9840 (0.9855) time: 0.1426 data: 0.0645 max mem: 9394 +Train: [2] [ 300/6250] eta: 0:15:47 lr: 0.000051 grad: 0.0890 (0.0987) loss: 0.9869 (0.9858) time: 0.1423 data: 0.0559 max mem: 9394 +Train: [2] [ 400/6250] eta: 0:14:53 lr: 0.000052 grad: 0.0824 (0.0981) loss: 0.9876 (0.9858) time: 0.1385 data: 0.0535 max mem: 9394 +Train: [2] [ 500/6250] eta: 0:14:06 lr: 0.000052 grad: 0.0895 (0.0976) loss: 0.9860 (0.9857) time: 0.1313 data: 0.0432 max mem: 9394 +Train: [2] [ 600/6250] eta: 0:13:32 lr: 0.000052 grad: 0.0814 (0.0975) loss: 0.9849 (0.9856) time: 0.1276 data: 0.0514 max mem: 9394 +Train: [2] [ 700/6250] eta: 0:13:01 lr: 0.000053 grad: 0.0845 (0.0977) loss: 0.9872 (0.9855) time: 0.1269 data: 0.0471 max mem: 9394 +Train: [2] [ 800/6250] eta: 0:12:43 lr: 0.000053 grad: 0.0881 (0.0974) loss: 0.9874 (0.9855) time: 0.1367 data: 0.0566 max mem: 9394 +Train: [2] [ 900/6250] eta: 0:12:36 lr: 0.000054 grad: 0.0827 (0.0965) loss: 0.9868 (0.9856) time: 0.1646 data: 0.0846 max mem: 9394 +Train: [2] [1000/6250] eta: 0:12:22 lr: 0.000054 grad: 0.0800 (0.0953) loss: 0.9869 (0.9857) time: 0.1631 data: 0.0642 max mem: 9394 +Train: [2] [1100/6250] eta: 0:12:12 lr: 0.000054 grad: 0.0931 (0.0951) loss: 0.9844 (0.9856) time: 0.1598 data: 0.0845 max mem: 9394 +Train: [2] [1200/6250] eta: 0:11:58 lr: 0.000055 grad: 0.0862 (0.0954) loss: 0.9842 (0.9855) time: 0.1399 data: 0.0532 max mem: 9394 +Train: [2] [1300/6250] eta: 0:11:43 lr: 0.000055 grad: 0.0763 (0.0955) loss: 0.9858 (0.9855) time: 0.1366 data: 0.0623 max mem: 9394 +Train: [2] [1400/6250] eta: 0:11:26 lr: 0.000056 grad: 0.0945 (0.0952) loss: 0.9862 (0.9854) time: 0.1281 data: 0.0495 max mem: 9394 +Train: [2] [1500/6250] eta: 0:11:11 lr: 0.000056 grad: 0.0825 (0.0952) loss: 0.9840 (0.9854) time: 0.1342 data: 0.0517 max mem: 9394 +Train: [2] [1600/6250] eta: 0:10:56 lr: 0.000056 grad: 0.0916 (0.0952) loss: 0.9839 (0.9853) time: 0.1528 data: 0.0754 max mem: 9394 +Train: [2] [1700/6250] eta: 0:10:41 lr: 0.000057 grad: 0.0914 (0.0950) loss: 0.9849 (0.9853) time: 0.1417 data: 0.0645 max mem: 9394 +Train: [2] [1800/6250] eta: 0:10:26 lr: 0.000057 grad: 0.0853 (0.0949) loss: 0.9863 (0.9853) time: 0.1419 data: 0.0651 max mem: 9394 +Train: [2] [1900/6250] eta: 0:10:10 lr: 0.000058 grad: 0.0924 (0.0944) loss: 0.9850 (0.9852) time: 0.1338 data: 0.0477 max mem: 9394 +Train: [2] [2000/6250] eta: 0:09:55 lr: 0.000058 grad: 0.0978 (0.0943) loss: 0.9843 (0.9853) time: 0.1268 data: 0.0470 max mem: 9394 +Train: [2] [2100/6250] eta: 0:09:43 lr: 0.000058 grad: 0.0901 (0.0942) loss: 0.9852 (0.9853) time: 0.1220 data: 0.0293 max mem: 9394 +Train: [2] [2200/6250] eta: 0:09:28 lr: 0.000059 grad: 0.0734 (0.0938) loss: 0.9866 (0.9853) time: 0.1512 data: 0.0739 max mem: 9394 +Train: [2] [2300/6250] eta: 0:09:14 lr: 0.000059 grad: 0.0924 (0.0938) loss: 0.9870 (0.9853) time: 0.1459 data: 0.0652 max mem: 9394 +Train: [2] [2400/6250] eta: 0:08:59 lr: 0.000060 grad: 0.0816 (0.0936) loss: 0.9861 (0.9853) time: 0.1377 data: 0.0596 max mem: 9394 +Train: [2] [2500/6250] eta: 0:08:45 lr: 0.000060 grad: 0.0835 (0.0936) loss: 0.9878 (0.9853) time: 0.1421 data: 0.0631 max mem: 9394 +Train: [2] [2600/6250] eta: 0:08:30 lr: 0.000060 grad: 0.0776 (0.0938) loss: 0.9837 (0.9852) time: 0.1424 data: 0.0652 max mem: 9394 +Train: [2] [2700/6250] eta: 0:08:16 lr: 0.000061 grad: 0.0869 (0.0939) loss: 0.9855 (0.9852) time: 0.1364 data: 0.0583 max mem: 9394 +Train: [2] [2800/6250] eta: 0:08:02 lr: 0.000061 grad: 0.0850 (0.0938) loss: 0.9836 (0.9852) time: 0.1370 data: 0.0535 max mem: 9394 +Train: [2] [2900/6250] eta: 0:07:48 lr: 0.000062 grad: 0.0867 (0.0938) loss: 0.9856 (0.9852) time: 0.1030 data: 0.0219 max mem: 9394 +Train: [2] [3000/6250] eta: 0:07:34 lr: 0.000062 grad: 0.0916 (0.0941) loss: 0.9834 (0.9851) time: 0.1527 data: 0.0764 max mem: 9394 +Train: [2] [3100/6250] eta: 0:07:20 lr: 0.000062 grad: 0.1038 (0.0945) loss: 0.9834 (0.9851) time: 0.1030 data: 0.0245 max mem: 9394 +Train: [2] [3200/6250] eta: 0:07:06 lr: 0.000063 grad: 0.1040 (0.0949) loss: 0.9840 (0.9850) time: 0.1452 data: 0.0658 max mem: 9394 +Train: [2] [3300/6250] eta: 0:06:57 lr: 0.000063 grad: 0.1062 (0.0954) loss: 0.9834 (0.9849) time: 0.1010 data: 0.0002 max mem: 9394 +Train: [2] [3400/6250] eta: 0:06:44 lr: 0.000064 grad: 0.0976 (0.0956) loss: 0.9834 (0.9849) time: 0.2635 data: 0.1804 max mem: 9394 +Train: [2] [3500/6250] eta: 0:06:30 lr: 0.000064 grad: 0.1118 (0.0961) loss: 0.9824 (0.9848) time: 0.1202 data: 0.0245 max mem: 9394 +Train: [2] [3600/6250] eta: 0:06:15 lr: 0.000064 grad: 0.1135 (0.0966) loss: 0.9844 (0.9848) time: 0.1378 data: 0.0593 max mem: 9394 +Train: [2] [3700/6250] eta: 0:06:01 lr: 0.000065 grad: 0.0882 (0.0972) loss: 0.9835 (0.9847) time: 0.1459 data: 0.0410 max mem: 9394 +Train: [2] [3800/6250] eta: 0:05:48 lr: 0.000065 grad: 0.1400 (0.0981) loss: 0.9815 (0.9846) time: 0.1497 data: 0.0669 max mem: 9394 +Train: [2] [3900/6250] eta: 0:05:33 lr: 0.000066 grad: 0.1211 (0.0990) loss: 0.9849 (0.9846) time: 0.1367 data: 0.0585 max mem: 9394 +Train: [2] [4000/6250] eta: 0:05:18 lr: 0.000066 grad: 0.1020 (0.0997) loss: 0.9835 (0.9845) time: 0.1407 data: 0.0668 max mem: 9394 +Train: [2] [4100/6250] eta: 0:05:03 lr: 0.000066 grad: 0.1263 (0.1006) loss: 0.9831 (0.9845) time: 0.1379 data: 0.0570 max mem: 9394 +Train: [2] [4200/6250] eta: 0:04:49 lr: 0.000067 grad: 0.1166 (0.1016) loss: 0.9828 (0.9844) time: 0.1355 data: 0.0589 max mem: 9394 +Train: [2] [4300/6250] eta: 0:04:35 lr: 0.000067 grad: 0.1502 (0.1031) loss: 0.9844 (0.9844) time: 0.1398 data: 0.0575 max mem: 9394 +Train: [2] [4400/6250] eta: 0:04:20 lr: 0.000068 grad: 0.1314 (0.1045) loss: 0.9839 (0.9844) time: 0.1386 data: 0.0630 max mem: 9394 +Train: [2] [4500/6250] eta: 0:04:06 lr: 0.000068 grad: 0.1491 (0.1061) loss: 0.9832 (0.9844) time: 0.1358 data: 0.0566 max mem: 9394 +Train: [2] [4600/6250] eta: 0:03:51 lr: 0.000068 grad: 0.1185 (0.1082) loss: 0.9844 (0.9843) time: 0.1198 data: 0.0343 max mem: 9394 +Train: [2] [4700/6250] eta: 0:03:37 lr: 0.000069 grad: 0.1724 (0.1102) loss: 0.9847 (0.9843) time: 0.1386 data: 0.0631 max mem: 9394 +Train: [2] [4800/6250] eta: 0:03:23 lr: 0.000069 grad: 0.2037 (0.1124) loss: 0.9809 (0.9842) time: 0.1418 data: 0.0636 max mem: 9394 +Train: [2] [4900/6250] eta: 0:03:09 lr: 0.000070 grad: 0.1261 (0.1145) loss: 0.9833 (0.9842) time: 0.1335 data: 0.0595 max mem: 9394 +Train: [2] [5000/6250] eta: 0:02:55 lr: 0.000070 grad: 0.1660 (0.1162) loss: 0.9838 (0.9842) time: 0.1143 data: 0.0294 max mem: 9394 +Train: [2] [5100/6250] eta: 0:02:40 lr: 0.000070 grad: 0.1824 (0.1178) loss: 0.9807 (0.9841) time: 0.1533 data: 0.0737 max mem: 9394 +Train: [2] [5200/6250] eta: 0:02:26 lr: 0.000071 grad: 0.2108 (0.1198) loss: 0.9833 (0.9841) time: 0.1259 data: 0.0451 max mem: 9394 +Train: [2] [5300/6250] eta: 0:02:13 lr: 0.000071 grad: 0.2269 (0.1215) loss: 0.9834 (0.9841) time: 0.1880 data: 0.0508 max mem: 9394 +Train: [2] [5400/6250] eta: 0:01:59 lr: 0.000072 grad: 0.1314 (0.1231) loss: 0.9818 (0.9841) time: 0.1497 data: 0.0731 max mem: 9394 +Train: [2] [5500/6250] eta: 0:01:45 lr: 0.000072 grad: 0.1615 (0.1250) loss: 0.9829 (0.9840) time: 0.1382 data: 0.0576 max mem: 9394 +Train: [2] [5600/6250] eta: 0:01:31 lr: 0.000072 grad: 0.1927 (0.1263) loss: 0.9821 (0.9840) time: 0.1515 data: 0.0754 max mem: 9394 +Train: [2] [5700/6250] eta: 0:01:17 lr: 0.000073 grad: 0.1224 (0.1279) loss: 0.9814 (0.9840) time: 0.1359 data: 0.0624 max mem: 9394 +Train: [2] [5800/6250] eta: 0:01:03 lr: 0.000073 grad: 0.1705 (0.1294) loss: 0.9830 (0.9839) time: 0.1330 data: 0.0500 max mem: 9394 +Train: [2] [5900/6250] eta: 0:00:49 lr: 0.000074 grad: 0.1544 (0.1311) loss: 0.9813 (0.9839) time: 0.1323 data: 0.0532 max mem: 9394 +Train: [2] [6000/6250] eta: 0:00:35 lr: 0.000074 grad: 0.2024 (0.1324) loss: 0.9789 (0.9839) time: 0.1503 data: 0.0739 max mem: 9394 +Train: [2] [6100/6250] eta: 0:00:20 lr: 0.000074 grad: 0.1113 (0.1335) loss: 0.9823 (0.9838) time: 0.1412 data: 0.0652 max mem: 9394 +Train: [2] [6200/6250] eta: 0:00:06 lr: 0.000075 grad: 0.1979 (0.1352) loss: 0.9824 (0.9838) time: 0.1514 data: 0.0743 max mem: 9394 +Train: [2] [6249/6250] eta: 0:00:00 lr: 0.000075 grad: 0.2410 (0.1359) loss: 0.9803 (0.9838) time: 0.1273 data: 0.0542 max mem: 9394 +Train: [2] Total time: 0:14:39 (0.1408 s / it) +Averaged stats: lr: 0.000075 grad: 0.2410 (0.1359) loss: 0.9803 (0.9838) +Eval (hcp-train-subset): [2] [ 0/62] eta: 0:03:07 loss: 0.9808 (0.9808) time: 3.0319 data: 2.9299 max mem: 9394 +Eval (hcp-train-subset): [2] [61/62] eta: 0:00:00 loss: 0.9846 (0.9839) time: 0.1367 data: 0.1119 max mem: 9394 +Eval (hcp-train-subset): [2] Total time: 0:00:14 (0.2385 s / it) +Averaged stats (hcp-train-subset): loss: 0.9846 (0.9839) +Eval (hcp-val): [2] [ 0/62] eta: 0:05:29 loss: 0.9767 (0.9767) time: 5.3196 data: 5.2669 max mem: 9394 +Eval (hcp-val): [2] [61/62] eta: 0:00:00 loss: 0.9806 (0.9801) time: 0.1461 data: 0.1187 max mem: 9394 +Eval (hcp-val): [2] Total time: 0:00:13 (0.2241 s / it) +Averaged stats (hcp-val): loss: 0.9806 (0.9801) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +Train: [3] [ 0/6250] eta: 6:26:49 lr: 0.000075 grad: 0.1057 (0.1057) loss: 0.9790 (0.9790) time: 3.7135 data: 3.4436 max mem: 9394 +Train: [3] [ 100/6250] eta: 0:19:35 lr: 0.000075 grad: 0.1673 (0.2366) loss: 0.9801 (0.9817) time: 0.1224 data: 0.0332 max mem: 9394 +Train: [3] [ 200/6250] eta: 0:16:48 lr: 0.000076 grad: 0.1942 (0.2229) loss: 0.9840 (0.9814) time: 0.1419 data: 0.0566 max mem: 9394 +Train: [3] [ 300/6250] eta: 0:15:40 lr: 0.000076 grad: 0.1593 (0.2195) loss: 0.9811 (0.9812) time: 0.1435 data: 0.0646 max mem: 9394 +Train: [3] [ 400/6250] eta: 0:14:49 lr: 0.000077 grad: 0.1739 (0.2119) loss: 0.9797 (0.9808) time: 0.1496 data: 0.0733 max mem: 9394 +Train: [3] [ 500/6250] eta: 0:13:59 lr: 0.000077 grad: 0.1358 (0.2136) loss: 0.9788 (0.9809) time: 0.1268 data: 0.0466 max mem: 9394 +Train: [3] [ 600/6250] eta: 0:13:25 lr: 0.000077 grad: 0.1685 (0.2111) loss: 0.9808 (0.9807) time: 0.1345 data: 0.0556 max mem: 9394 +Train: [3] [ 700/6250] eta: 0:12:53 lr: 0.000078 grad: 0.1685 (0.2127) loss: 0.9810 (0.9808) time: 0.1193 data: 0.0346 max mem: 9394 +Train: [3] [ 800/6250] eta: 0:12:34 lr: 0.000078 grad: 0.1558 (0.2111) loss: 0.9798 (0.9807) time: 0.1421 data: 0.0577 max mem: 9394 +Train: [3] [ 900/6250] eta: 0:12:21 lr: 0.000079 grad: 0.1595 (0.2128) loss: 0.9800 (0.9807) time: 0.1297 data: 0.0441 max mem: 9394 +Train: [3] [1000/6250] eta: 0:12:09 lr: 0.000079 grad: 0.2134 (0.2103) loss: 0.9830 (0.9808) time: 0.1433 data: 0.0645 max mem: 9394 +Train: [3] [1100/6250] eta: 0:11:55 lr: 0.000079 grad: 0.1901 (0.2089) loss: 0.9795 (0.9808) time: 0.1317 data: 0.0541 max mem: 9394 +Train: [3] [1200/6250] eta: 0:11:44 lr: 0.000080 grad: 0.1738 (0.2074) loss: 0.9803 (0.9807) time: 0.1500 data: 0.0714 max mem: 9394 +Train: [3] [1300/6250] eta: 0:11:32 lr: 0.000080 grad: 0.1480 (0.2061) loss: 0.9795 (0.9806) time: 0.1372 data: 0.0636 max mem: 9394 +Train: [3] [1400/6250] eta: 0:11:16 lr: 0.000081 grad: 0.1390 (0.2045) loss: 0.9796 (0.9804) time: 0.1360 data: 0.0556 max mem: 9394 +Train: [3] [1500/6250] eta: 0:11:06 lr: 0.000081 grad: 0.2572 (0.2044) loss: 0.9803 (0.9803) time: 0.1468 data: 0.0717 max mem: 9394 +Train: [3] [1600/6250] eta: 0:10:53 lr: 0.000081 grad: 0.1716 (0.2045) loss: 0.9802 (0.9802) time: 0.1449 data: 0.0619 max mem: 9394 +Train: [3] [1700/6250] eta: 0:10:39 lr: 0.000082 grad: 0.1280 (0.2036) loss: 0.9780 (0.9800) time: 0.1409 data: 0.0630 max mem: 9394 +Train: [3] [1800/6250] eta: 0:10:25 lr: 0.000082 grad: 0.1491 (0.2036) loss: 0.9767 (0.9799) time: 0.1637 data: 0.0841 max mem: 9394 +Train: [3] [1900/6250] eta: 0:10:11 lr: 0.000083 grad: 0.1465 (0.2040) loss: 0.9781 (0.9798) time: 0.1471 data: 0.0713 max mem: 9394 +Train: [3] [2000/6250] eta: 0:09:57 lr: 0.000083 grad: 0.1307 (0.2029) loss: 0.9761 (0.9797) time: 0.1496 data: 0.0720 max mem: 9394 +Train: [3] [2100/6250] eta: 0:09:43 lr: 0.000083 grad: 0.2349 (0.2054) loss: 0.9782 (0.9795) time: 0.1519 data: 0.0747 max mem: 9394 +Train: [3] [2200/6250] eta: 0:09:28 lr: 0.000084 grad: 0.1552 (0.2046) loss: 0.9768 (0.9794) time: 0.0893 data: 0.0035 max mem: 9394 +Train: [3] [2300/6250] eta: 0:09:13 lr: 0.000084 grad: 0.1572 (0.2048) loss: 0.9761 (0.9793) time: 0.1369 data: 0.0551 max mem: 9394 +Train: [3] [2400/6250] eta: 0:08:59 lr: 0.000085 grad: 0.1414 (0.2040) loss: 0.9748 (0.9792) time: 0.1331 data: 0.0542 max mem: 9394 +Train: [3] [2500/6250] eta: 0:08:45 lr: 0.000085 grad: 0.2067 (0.2039) loss: 0.9762 (0.9790) time: 0.1452 data: 0.0651 max mem: 9394 +Train: [3] [2600/6250] eta: 0:08:34 lr: 0.000085 grad: 0.1393 (0.2027) loss: 0.9790 (0.9789) time: 0.1696 data: 0.0905 max mem: 9394 +Train: [3] [2700/6250] eta: 0:08:20 lr: 0.000086 grad: 0.1880 (0.2025) loss: 0.9772 (0.9788) time: 0.1323 data: 0.0552 max mem: 9394 +Train: [3] [2800/6250] eta: 0:08:06 lr: 0.000086 grad: 0.2162 (0.2020) loss: 0.9775 (0.9787) time: 0.1677 data: 0.0910 max mem: 9394 +Train: [3] [2900/6250] eta: 0:07:51 lr: 0.000087 grad: 0.1724 (0.2022) loss: 0.9775 (0.9786) time: 0.1283 data: 0.0455 max mem: 9394 +Train: [3] [3000/6250] eta: 0:07:37 lr: 0.000087 grad: 0.1241 (0.2011) loss: 0.9765 (0.9785) time: 0.1567 data: 0.0825 max mem: 9394 +Train: [3] [3100/6250] eta: 0:07:22 lr: 0.000087 grad: 0.1687 (0.2005) loss: 0.9775 (0.9784) time: 0.1286 data: 0.0473 max mem: 9394 +Train: [3] [3200/6250] eta: 0:07:09 lr: 0.000088 grad: 0.1836 (0.2009) loss: 0.9768 (0.9784) time: 0.1387 data: 0.0551 max mem: 9394 +Train: [3] [3300/6250] eta: 0:06:56 lr: 0.000088 grad: 0.1593 (0.2003) loss: 0.9742 (0.9783) time: 0.0958 data: 0.0147 max mem: 9394 +Train: [3] [3400/6250] eta: 0:06:42 lr: 0.000089 grad: 0.2268 (0.2002) loss: 0.9778 (0.9782) time: 0.1406 data: 0.0632 max mem: 9394 +Train: [3] [3500/6250] eta: 0:06:27 lr: 0.000089 grad: 0.1347 (0.1998) loss: 0.9740 (0.9781) time: 0.1422 data: 0.0624 max mem: 9394 +Train: [3] [3600/6250] eta: 0:06:12 lr: 0.000089 grad: 0.1549 (0.1995) loss: 0.9740 (0.9780) time: 0.1330 data: 0.0549 max mem: 9394 +Train: [3] [3700/6250] eta: 0:05:58 lr: 0.000090 grad: 0.1442 (0.1986) loss: 0.9751 (0.9779) time: 0.1347 data: 0.0561 max mem: 9394 +Train: [3] [3800/6250] eta: 0:05:43 lr: 0.000090 grad: 0.1742 (0.1989) loss: 0.9764 (0.9779) time: 0.1178 data: 0.0341 max mem: 9394 +Train: [3] [3900/6250] eta: 0:05:29 lr: 0.000091 grad: 0.1544 (0.1984) loss: 0.9738 (0.9778) time: 0.1610 data: 0.0834 max mem: 9394 +Train: [3] [4000/6250] eta: 0:05:14 lr: 0.000091 grad: 0.1217 (0.1974) loss: 0.9751 (0.9777) time: 0.1249 data: 0.0485 max mem: 9394 +Train: [3] [4100/6250] eta: 0:05:00 lr: 0.000091 grad: 0.1654 (0.1966) loss: 0.9733 (0.9777) time: 0.1143 data: 0.0327 max mem: 9394 +Train: [3] [4200/6250] eta: 0:04:45 lr: 0.000092 grad: 0.1355 (0.1962) loss: 0.9751 (0.9776) time: 0.1344 data: 0.0568 max mem: 9394 +Train: [3] [4300/6250] eta: 0:04:31 lr: 0.000092 grad: 0.1764 (0.1956) loss: 0.9722 (0.9775) time: 0.1313 data: 0.0530 max mem: 9394 +Train: [3] [4400/6250] eta: 0:04:17 lr: 0.000093 grad: 0.1355 (0.1952) loss: 0.9712 (0.9774) time: 0.1178 data: 0.0321 max mem: 9394 +Train: [3] [4500/6250] eta: 0:04:03 lr: 0.000093 grad: 0.1555 (0.1951) loss: 0.9728 (0.9773) time: 0.1161 data: 0.0315 max mem: 9394 +Train: [3] [4600/6250] eta: 0:03:49 lr: 0.000093 grad: 0.1707 (0.1949) loss: 0.9710 (0.9772) time: 0.1423 data: 0.0592 max mem: 9394 +Train: [3] [4700/6250] eta: 0:03:34 lr: 0.000094 grad: 0.1572 (0.1944) loss: 0.9734 (0.9771) time: 0.1461 data: 0.0716 max mem: 9394 +Train: [3] [4800/6250] eta: 0:03:21 lr: 0.000094 grad: 0.1923 (0.1948) loss: 0.9715 (0.9770) time: 0.1786 data: 0.1001 max mem: 9394 +Train: [3] [4900/6250] eta: 0:03:07 lr: 0.000095 grad: 0.1908 (0.1949) loss: 0.9706 (0.9769) time: 0.1228 data: 0.0394 max mem: 9394 +Train: [3] [5000/6250] eta: 0:02:53 lr: 0.000095 grad: 0.1356 (0.1947) loss: 0.9682 (0.9767) time: 0.1493 data: 0.0703 max mem: 9394 +Train: [3] [5100/6250] eta: 0:02:39 lr: 0.000095 grad: 0.1555 (0.1949) loss: 0.9680 (0.9766) time: 0.1431 data: 0.0691 max mem: 9394 +Train: [3] [5200/6250] eta: 0:02:25 lr: 0.000096 grad: 0.2546 (0.1951) loss: 0.9703 (0.9764) time: 0.1367 data: 0.0575 max mem: 9394 +Train: [3] [5300/6250] eta: 0:02:11 lr: 0.000096 grad: 0.1656 (0.1947) loss: 0.9679 (0.9762) time: 0.1407 data: 0.0637 max mem: 9394 +Train: [3] [5400/6250] eta: 0:01:58 lr: 0.000097 grad: 0.1845 (0.1951) loss: 0.9652 (0.9761) time: 0.1479 data: 0.0715 max mem: 9394 +Train: [3] [5500/6250] eta: 0:01:44 lr: 0.000097 grad: 0.2433 (0.1954) loss: 0.9672 (0.9759) time: 0.1303 data: 0.0518 max mem: 9394 +Train: [3] [5600/6250] eta: 0:01:30 lr: 0.000097 grad: 0.1604 (0.1956) loss: 0.9643 (0.9757) time: 0.1425 data: 0.0624 max mem: 9394 +Train: [3] [5700/6250] eta: 0:01:16 lr: 0.000098 grad: 0.1878 (0.1960) loss: 0.9627 (0.9755) time: 0.1523 data: 0.0731 max mem: 9394 +Train: [3] [5800/6250] eta: 0:01:02 lr: 0.000098 grad: 0.1786 (0.1961) loss: 0.9657 (0.9753) time: 0.1599 data: 0.0823 max mem: 9394 +Train: [3] [5900/6250] eta: 0:00:48 lr: 0.000099 grad: 0.1499 (0.1966) loss: 0.9620 (0.9751) time: 0.1436 data: 0.0694 max mem: 9394 +Train: [3] [6000/6250] eta: 0:00:34 lr: 0.000099 grad: 0.2142 (0.1973) loss: 0.9640 (0.9749) time: 0.1483 data: 0.0741 max mem: 9394 +Train: [3] [6100/6250] eta: 0:00:20 lr: 0.000099 grad: 0.1977 (0.1979) loss: 0.9610 (0.9747) time: 0.1353 data: 0.0555 max mem: 9394 +Train: [3] [6200/6250] eta: 0:00:06 lr: 0.000100 grad: 0.2451 (0.1985) loss: 0.9630 (0.9745) time: 0.1322 data: 0.0523 max mem: 9394 +Train: [3] [6249/6250] eta: 0:00:00 lr: 0.000100 grad: 0.2164 (0.1988) loss: 0.9605 (0.9744) time: 0.1351 data: 0.0585 max mem: 9394 +Train: [3] Total time: 0:14:36 (0.1403 s / it) +Averaged stats: lr: 0.000100 grad: 0.2164 (0.1988) loss: 0.9605 (0.9744) +Eval (hcp-train-subset): [3] [ 0/62] eta: 0:04:18 loss: 0.9620 (0.9620) time: 4.1737 data: 4.1442 max mem: 9394 +Eval (hcp-train-subset): [3] [61/62] eta: 0:00:00 loss: 0.9658 (0.9633) time: 0.1068 data: 0.0821 max mem: 9394 +Eval (hcp-train-subset): [3] Total time: 0:00:12 (0.1973 s / it) +Averaged stats (hcp-train-subset): loss: 0.9658 (0.9633) +Eval (hcp-val): [3] [ 0/62] eta: 0:03:14 loss: 0.9580 (0.9580) time: 3.1380 data: 3.0439 max mem: 9394 +Eval (hcp-val): [3] [61/62] eta: 0:00:00 loss: 0.9609 (0.9607) time: 0.1283 data: 0.1035 max mem: 9394 +Eval (hcp-val): [3] Total time: 0:00:12 (0.2031 s / it) +Averaged stats (hcp-val): loss: 0.9609 (0.9607) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +Train: [4] [ 0/6250] eta: 10:19:21 lr: 0.000100 grad: 0.4190 (0.4190) loss: 0.9582 (0.9582) time: 5.9459 data: 5.8407 max mem: 9394 +Train: [4] [ 100/6250] eta: 0:20:47 lr: 0.000100 grad: 0.2156 (0.2875) loss: 0.9565 (0.9592) time: 0.1542 data: 0.0753 max mem: 9394 +Train: [4] [ 200/6250] eta: 0:17:28 lr: 0.000101 grad: 0.1587 (0.2693) loss: 0.9588 (0.9580) time: 0.1461 data: 0.0643 max mem: 9394 +Train: [4] [ 300/6250] eta: 0:16:03 lr: 0.000101 grad: 0.2371 (0.2583) loss: 0.9592 (0.9576) time: 0.1367 data: 0.0563 max mem: 9394 +Train: [4] [ 400/6250] eta: 0:14:54 lr: 0.000102 grad: 0.2569 (0.2552) loss: 0.9636 (0.9580) time: 0.1197 data: 0.0335 max mem: 9394 +Train: [4] [ 500/6250] eta: 0:14:07 lr: 0.000102 grad: 0.2494 (0.2562) loss: 0.9569 (0.9577) time: 0.1227 data: 0.0345 max mem: 9394 +Train: [4] [ 600/6250] eta: 0:13:29 lr: 0.000102 grad: 0.2258 (0.2603) loss: 0.9577 (0.9577) time: 0.1199 data: 0.0366 max mem: 9394 +Train: [4] [ 700/6250] eta: 0:12:58 lr: 0.000103 grad: 0.2211 (0.2571) loss: 0.9550 (0.9576) time: 0.1266 data: 0.0460 max mem: 9394 +Train: [4] [ 800/6250] eta: 0:12:43 lr: 0.000103 grad: 0.2708 (0.2565) loss: 0.9576 (0.9573) time: 0.1576 data: 0.0741 max mem: 9394 +Train: [4] [ 900/6250] eta: 0:12:33 lr: 0.000104 grad: 0.2509 (0.2534) loss: 0.9540 (0.9571) time: 0.1533 data: 0.0771 max mem: 9394 +Train: [4] [1000/6250] eta: 0:12:19 lr: 0.000104 grad: 0.1964 (0.2534) loss: 0.9517 (0.9569) time: 0.1312 data: 0.0515 max mem: 9394 +Train: [4] [1100/6250] eta: 0:12:05 lr: 0.000104 grad: 0.2154 (0.2553) loss: 0.9542 (0.9567) time: 0.1221 data: 0.0462 max mem: 9394 +Train: [4] [1200/6250] eta: 0:11:53 lr: 0.000105 grad: 0.2575 (0.2565) loss: 0.9569 (0.9565) time: 0.1455 data: 0.0589 max mem: 9394 +Train: [4] [1300/6250] eta: 0:11:42 lr: 0.000105 grad: 0.2579 (0.2580) loss: 0.9518 (0.9561) time: 0.1866 data: 0.1047 max mem: 9394 +Train: [4] [1400/6250] eta: 0:11:31 lr: 0.000106 grad: 0.2268 (0.2581) loss: 0.9503 (0.9557) time: 0.1059 data: 0.0278 max mem: 9394 +Train: [4] [1500/6250] eta: 0:11:16 lr: 0.000106 grad: 0.2695 (0.2605) loss: 0.9485 (0.9552) time: 0.1503 data: 0.0760 max mem: 9394 +Train: [4] [1600/6250] eta: 0:10:58 lr: 0.000106 grad: 0.2141 (0.2620) loss: 0.9500 (0.9548) time: 0.1234 data: 0.0445 max mem: 9394 +Train: [4] [1700/6250] eta: 0:10:43 lr: 0.000107 grad: 0.3067 (0.2653) loss: 0.9437 (0.9544) time: 0.1424 data: 0.0608 max mem: 9394 +Train: [4] [1800/6250] eta: 0:10:28 lr: 0.000107 grad: 0.2506 (0.2654) loss: 0.9480 (0.9539) time: 0.1561 data: 0.0799 max mem: 9394 +Train: [4] [1900/6250] eta: 0:10:13 lr: 0.000108 grad: 0.2752 (0.2674) loss: 0.9442 (0.9535) time: 0.1351 data: 0.0578 max mem: 9394 +Train: [4] [2000/6250] eta: 0:10:00 lr: 0.000108 grad: 0.2877 (0.2679) loss: 0.9415 (0.9530) time: 0.1471 data: 0.0635 max mem: 9394 +Train: [4] [2100/6250] eta: 0:09:44 lr: 0.000108 grad: 0.2628 (0.2675) loss: 0.9422 (0.9525) time: 0.1278 data: 0.0453 max mem: 9394 +Train: [4] [2200/6250] eta: 0:09:30 lr: 0.000109 grad: 0.2351 (0.2682) loss: 0.9422 (0.9520) time: 0.1314 data: 0.0517 max mem: 9394 +Train: [4] [2300/6250] eta: 0:09:16 lr: 0.000109 grad: 0.2511 (0.2691) loss: 0.9416 (0.9515) time: 0.1367 data: 0.0573 max mem: 9394 +Train: [4] [2400/6250] eta: 0:09:01 lr: 0.000110 grad: 0.2921 (0.2694) loss: 0.9394 (0.9510) time: 0.1130 data: 0.0265 max mem: 9394 +Train: [4] [2500/6250] eta: 0:08:47 lr: 0.000110 grad: 0.2577 (0.2705) loss: 0.9365 (0.9505) time: 0.1300 data: 0.0504 max mem: 9394 +Train: [4] [2600/6250] eta: 0:08:33 lr: 0.000110 grad: 0.2569 (0.2707) loss: 0.9400 (0.9500) time: 0.1559 data: 0.0763 max mem: 9394 +Train: [4] [2700/6250] eta: 0:08:18 lr: 0.000111 grad: 0.2813 (0.2716) loss: 0.9364 (0.9495) time: 0.1338 data: 0.0544 max mem: 9394 +Train: [4] [2800/6250] eta: 0:08:04 lr: 0.000111 grad: 0.2454 (0.2714) loss: 0.9357 (0.9490) time: 0.1436 data: 0.0666 max mem: 9394 +Train: [4] [2900/6250] eta: 0:07:49 lr: 0.000112 grad: 0.2936 (0.2723) loss: 0.9355 (0.9486) time: 0.1291 data: 0.0498 max mem: 9394 +Train: [4] [3000/6250] eta: 0:07:35 lr: 0.000112 grad: 0.2090 (0.2730) loss: 0.9335 (0.9481) time: 0.1369 data: 0.0590 max mem: 9394 +Train: [4] [3100/6250] eta: 0:07:20 lr: 0.000112 grad: 0.2455 (0.2725) loss: 0.9326 (0.9477) time: 0.1405 data: 0.0633 max mem: 9394 +Train: [4] [3200/6250] eta: 0:07:06 lr: 0.000113 grad: 0.2625 (0.2720) loss: 0.9345 (0.9472) time: 0.1329 data: 0.0540 max mem: 9394 +Train: [4] [3300/6250] eta: 0:06:53 lr: 0.000113 grad: 0.2548 (0.2723) loss: 0.9334 (0.9467) time: 0.1733 data: 0.0987 max mem: 9394 +Train: [4] [3400/6250] eta: 0:06:38 lr: 0.000114 grad: 0.2469 (0.2718) loss: 0.9294 (0.9463) time: 0.1365 data: 0.0585 max mem: 9394 +Train: [4] [3500/6250] eta: 0:06:23 lr: 0.000114 grad: 0.2123 (0.2713) loss: 0.9318 (0.9458) time: 0.1216 data: 0.0436 max mem: 9394 +Train: [4] [3600/6250] eta: 0:06:08 lr: 0.000114 grad: 0.2733 (0.2705) loss: 0.9296 (0.9454) time: 0.1393 data: 0.0645 max mem: 9394 +Train: [4] [3700/6250] eta: 0:05:54 lr: 0.000115 grad: 0.2514 (0.2703) loss: 0.9306 (0.9450) time: 0.1322 data: 0.0506 max mem: 9394 +Train: [4] [3800/6250] eta: 0:05:40 lr: 0.000115 grad: 0.2516 (0.2705) loss: 0.9283 (0.9447) time: 0.1420 data: 0.0599 max mem: 9394 +Train: [4] [3900/6250] eta: 0:05:25 lr: 0.000116 grad: 0.2368 (0.2700) loss: 0.9280 (0.9442) time: 0.1371 data: 0.0542 max mem: 9394 +Train: [4] [4000/6250] eta: 0:05:11 lr: 0.000116 grad: 0.2530 (0.2699) loss: 0.9279 (0.9438) time: 0.1327 data: 0.0495 max mem: 9394 +Train: [4] [4100/6250] eta: 0:04:57 lr: 0.000116 grad: 0.2135 (0.2693) loss: 0.9262 (0.9435) time: 0.1472 data: 0.0685 max mem: 9394 +Train: [4] [4200/6250] eta: 0:04:43 lr: 0.000117 grad: 0.2101 (0.2685) loss: 0.9281 (0.9431) time: 0.1262 data: 0.0494 max mem: 9394 +Train: [4] [4300/6250] eta: 0:04:29 lr: 0.000117 grad: 0.1743 (0.2676) loss: 0.9232 (0.9426) time: 0.1618 data: 0.0838 max mem: 9394 +Train: [4] [4400/6250] eta: 0:04:14 lr: 0.000118 grad: 0.1954 (0.2671) loss: 0.9245 (0.9422) time: 0.1040 data: 0.0182 max mem: 9394 +Train: [4] [4500/6250] eta: 0:04:00 lr: 0.000118 grad: 0.2110 (0.2668) loss: 0.9233 (0.9419) time: 0.1177 data: 0.0354 max mem: 9394 +Train: [4] [4600/6250] eta: 0:03:47 lr: 0.000118 grad: 0.1908 (0.2656) loss: 0.9233 (0.9415) time: 0.1554 data: 0.0749 max mem: 9394 +Train: [4] [4700/6250] eta: 0:03:33 lr: 0.000119 grad: 0.2214 (0.2651) loss: 0.9237 (0.9411) time: 0.1309 data: 0.0524 max mem: 9394 +Train: [4] [4800/6250] eta: 0:03:19 lr: 0.000119 grad: 0.2221 (0.2642) loss: 0.9209 (0.9407) time: 0.1382 data: 0.0564 max mem: 9394 +Train: [4] [4900/6250] eta: 0:03:05 lr: 0.000120 grad: 0.2164 (0.2631) loss: 0.9217 (0.9403) time: 0.1068 data: 0.0235 max mem: 9394 +Train: [4] [5000/6250] eta: 0:02:52 lr: 0.000120 grad: 0.1793 (0.2620) loss: 0.9196 (0.9399) time: 0.1521 data: 0.0774 max mem: 9394 +Train: [4] [5100/6250] eta: 0:02:38 lr: 0.000120 grad: 0.1961 (0.2613) loss: 0.9238 (0.9395) time: 0.1440 data: 0.0631 max mem: 9394 +Train: [4] [5200/6250] eta: 0:02:24 lr: 0.000121 grad: 0.1952 (0.2606) loss: 0.9151 (0.9392) time: 0.1379 data: 0.0581 max mem: 9394 +Train: [4] [5300/6250] eta: 0:02:11 lr: 0.000121 grad: 0.1872 (0.2592) loss: 0.9187 (0.9388) time: 0.1949 data: 0.1026 max mem: 9394 +Train: [4] [5400/6250] eta: 0:01:57 lr: 0.000122 grad: 0.1885 (0.2583) loss: 0.9162 (0.9385) time: 0.1416 data: 0.0643 max mem: 9394 +Train: [4] [5500/6250] eta: 0:01:43 lr: 0.000122 grad: 0.1747 (0.2577) loss: 0.9161 (0.9381) time: 0.1630 data: 0.0851 max mem: 9394 +Train: [4] [5600/6250] eta: 0:01:29 lr: 0.000122 grad: 0.1667 (0.2568) loss: 0.9173 (0.9377) time: 0.1272 data: 0.0481 max mem: 9394 +Train: [4] [5700/6250] eta: 0:01:16 lr: 0.000123 grad: 0.2588 (0.2565) loss: 0.9160 (0.9374) time: 0.1676 data: 0.0924 max mem: 9394 +Train: [4] [5800/6250] eta: 0:01:02 lr: 0.000123 grad: 0.2009 (0.2556) loss: 0.9196 (0.9370) time: 0.1514 data: 0.0765 max mem: 9394 +Train: [4] [5900/6250] eta: 0:00:48 lr: 0.000124 grad: 0.1624 (0.2545) loss: 0.9196 (0.9367) time: 0.1445 data: 0.0666 max mem: 9394 +Train: [4] [6000/6250] eta: 0:00:34 lr: 0.000124 grad: 0.2052 (0.2538) loss: 0.9154 (0.9364) time: 0.1492 data: 0.0737 max mem: 9394 +Train: [4] [6100/6250] eta: 0:00:20 lr: 0.000124 grad: 0.1954 (0.2529) loss: 0.9143 (0.9361) time: 0.1586 data: 0.0807 max mem: 9394 +Train: [4] [6200/6250] eta: 0:00:06 lr: 0.000125 grad: 0.2344 (0.2520) loss: 0.9183 (0.9358) time: 0.1218 data: 0.0402 max mem: 9394 +Train: [4] [6249/6250] eta: 0:00:00 lr: 0.000125 grad: 0.1773 (0.2515) loss: 0.9161 (0.9356) time: 0.1385 data: 0.0574 max mem: 9394 +Train: [4] Total time: 0:14:27 (0.1388 s / it) +Averaged stats: lr: 0.000125 grad: 0.1773 (0.2515) loss: 0.9161 (0.9356) +Eval (hcp-train-subset): [4] [ 0/62] eta: 0:03:24 loss: 0.9255 (0.9255) time: 3.2916 data: 3.2282 max mem: 9394 +Eval (hcp-train-subset): [4] [61/62] eta: 0:00:00 loss: 0.9184 (0.9184) time: 0.1671 data: 0.1401 max mem: 9394 +Eval (hcp-train-subset): [4] Total time: 0:00:14 (0.2404 s / it) +Averaged stats (hcp-train-subset): loss: 0.9184 (0.9184) +Making plots (hcp-train-subset): example=59 +Eval (hcp-val): [4] [ 0/62] eta: 0:03:14 loss: 0.9100 (0.9100) time: 3.1313 data: 3.0333 max mem: 9394 +Eval (hcp-val): [4] [61/62] eta: 0:00:00 loss: 0.9119 (0.9130) time: 0.1143 data: 0.0881 max mem: 9394 +Eval (hcp-val): [4] Total time: 0:00:12 (0.1978 s / it) +Averaged stats (hcp-val): loss: 0.9119 (0.9130) +Making plots (hcp-val): example=56 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +Train: [5] [ 0/6250] eta: 6:15:08 lr: 0.000125 grad: 0.1278 (0.1278) loss: 0.9041 (0.9041) time: 3.6014 data: 3.4404 max mem: 9394 +Train: [5] [ 100/6250] eta: 0:19:21 lr: 0.000125 grad: 0.2134 (0.2426) loss: 0.9185 (0.9181) time: 0.1199 data: 0.0403 max mem: 9394 +Train: [5] [ 200/6250] eta: 0:16:56 lr: 0.000125 grad: 0.2013 (0.2224) loss: 0.9141 (0.9148) time: 0.1532 data: 0.0764 max mem: 9394 +Train: [5] [ 300/6250] eta: 0:15:31 lr: 0.000125 grad: 0.1995 (0.2150) loss: 0.9155 (0.9148) time: 0.1409 data: 0.0599 max mem: 9394 +Train: [5] [ 400/6250] eta: 0:14:37 lr: 0.000125 grad: 0.1794 (0.2122) loss: 0.9139 (0.9150) time: 0.1406 data: 0.0527 max mem: 9394 +Train: [5] [ 500/6250] eta: 0:13:53 lr: 0.000125 grad: 0.2034 (0.2076) loss: 0.9174 (0.9150) time: 0.1328 data: 0.0438 max mem: 9394 +Train: [5] [ 600/6250] eta: 0:13:20 lr: 0.000125 grad: 0.1772 (0.2033) loss: 0.9137 (0.9150) time: 0.1356 data: 0.0503 max mem: 9394 +Train: [5] [ 700/6250] eta: 0:12:55 lr: 0.000125 grad: 0.1574 (0.1989) loss: 0.9143 (0.9149) time: 0.1273 data: 0.0445 max mem: 9394 +Train: [5] [ 800/6250] eta: 0:12:38 lr: 0.000125 grad: 0.1660 (0.1969) loss: 0.9140 (0.9147) time: 0.1429 data: 0.0637 max mem: 9394 +Train: [5] [ 900/6250] eta: 0:12:28 lr: 0.000125 grad: 0.1719 (0.1951) loss: 0.9120 (0.9145) time: 0.1420 data: 0.0605 max mem: 9394 +Train: [5] [1000/6250] eta: 0:12:16 lr: 0.000125 grad: 0.1787 (0.1952) loss: 0.9100 (0.9141) time: 0.1767 data: 0.0860 max mem: 9394 +Train: [5] [1100/6250] eta: 0:12:06 lr: 0.000125 grad: 0.1460 (0.1932) loss: 0.9091 (0.9137) time: 0.1629 data: 0.0808 max mem: 9394 +Train: [5] [1200/6250] eta: 0:11:52 lr: 0.000125 grad: 0.1485 (0.1917) loss: 0.9099 (0.9133) time: 0.1244 data: 0.0486 max mem: 9394 +Train: [5] [1300/6250] eta: 0:11:41 lr: 0.000125 grad: 0.1673 (0.1907) loss: 0.9081 (0.9128) time: 0.1413 data: 0.0607 max mem: 9394 +Train: [5] [1400/6250] eta: 0:11:24 lr: 0.000125 grad: 0.1742 (0.1898) loss: 0.9066 (0.9124) time: 0.1321 data: 0.0546 max mem: 9394 +Train: [5] [1500/6250] eta: 0:11:09 lr: 0.000125 grad: 0.1760 (0.1884) loss: 0.9073 (0.9119) time: 0.1270 data: 0.0465 max mem: 9394 +Train: [5] [1600/6250] eta: 0:10:56 lr: 0.000125 grad: 0.2071 (0.1881) loss: 0.9052 (0.9114) time: 0.1453 data: 0.0698 max mem: 9394 +Train: [5] [1700/6250] eta: 0:10:40 lr: 0.000125 grad: 0.1908 (0.1873) loss: 0.9063 (0.9109) time: 0.1357 data: 0.0555 max mem: 9394 +Train: [5] [1800/6250] eta: 0:10:25 lr: 0.000125 grad: 0.1669 (0.1870) loss: 0.8998 (0.9103) time: 0.1633 data: 0.0746 max mem: 9394 +Train: [5] [1900/6250] eta: 0:10:16 lr: 0.000125 grad: 0.2314 (0.1873) loss: 0.9012 (0.9098) time: 0.1463 data: 0.0676 max mem: 9394 +Train: [5] [2000/6250] eta: 0:10:01 lr: 0.000125 grad: 0.2056 (0.1878) loss: 0.8976 (0.9092) time: 0.1360 data: 0.0607 max mem: 9394 +Train: [5] [2100/6250] eta: 0:09:45 lr: 0.000125 grad: 0.1993 (0.1876) loss: 0.8929 (0.9086) time: 0.1283 data: 0.0520 max mem: 9394 +Train: [5] [2200/6250] eta: 0:09:30 lr: 0.000125 grad: 0.1758 (0.1874) loss: 0.8909 (0.9079) time: 0.1415 data: 0.0638 max mem: 9394 +Train: [5] [2300/6250] eta: 0:09:15 lr: 0.000125 grad: 0.1802 (0.1874) loss: 0.8927 (0.9074) time: 0.1270 data: 0.0469 max mem: 9394 +Train: [5] [2400/6250] eta: 0:09:00 lr: 0.000125 grad: 0.1864 (0.1874) loss: 0.8894 (0.9067) time: 0.1416 data: 0.0609 max mem: 9394 +Train: [5] [2500/6250] eta: 0:08:45 lr: 0.000125 grad: 0.1790 (0.1869) loss: 0.8953 (0.9061) time: 0.1311 data: 0.0519 max mem: 9394 +Train: [5] [2600/6250] eta: 0:08:30 lr: 0.000125 grad: 0.1714 (0.1867) loss: 0.8926 (0.9055) time: 0.1455 data: 0.0676 max mem: 9394 +Train: [5] [2700/6250] eta: 0:08:16 lr: 0.000125 grad: 0.1660 (0.1862) loss: 0.8883 (0.9049) time: 0.1401 data: 0.0620 max mem: 9394 +Train: [5] [2800/6250] eta: 0:08:01 lr: 0.000125 grad: 0.1725 (0.1860) loss: 0.8898 (0.9043) time: 0.1481 data: 0.0661 max mem: 9394 +Train: [5] [2900/6250] eta: 0:07:47 lr: 0.000125 grad: 0.1882 (0.1855) loss: 0.8909 (0.9037) time: 0.1334 data: 0.0587 max mem: 9394 +Train: [5] [3000/6250] eta: 0:07:33 lr: 0.000125 grad: 0.1316 (0.1852) loss: 0.8890 (0.9032) time: 0.1264 data: 0.0450 max mem: 9394 +Train: [5] [3100/6250] eta: 0:07:19 lr: 0.000125 grad: 0.1823 (0.1850) loss: 0.8912 (0.9028) time: 0.1399 data: 0.0618 max mem: 9394 +Train: [5] [3200/6250] eta: 0:07:05 lr: 0.000125 grad: 0.1889 (0.1844) loss: 0.8863 (0.9024) time: 0.1249 data: 0.0431 max mem: 9394 +Train: [5] [3300/6250] eta: 0:06:51 lr: 0.000125 grad: 0.1593 (0.1839) loss: 0.8897 (0.9019) time: 0.1269 data: 0.0504 max mem: 9394 +Train: [5] [3400/6250] eta: 0:06:37 lr: 0.000125 grad: 0.1312 (0.1829) loss: 0.8833 (0.9015) time: 0.1405 data: 0.0584 max mem: 9394 +Train: [5] [3500/6250] eta: 0:06:22 lr: 0.000125 grad: 0.1221 (0.1825) loss: 0.8804 (0.9011) time: 0.1235 data: 0.0436 max mem: 9394 +Train: [5] [3600/6250] eta: 0:06:08 lr: 0.000125 grad: 0.1900 (0.1819) loss: 0.8844 (0.9006) time: 0.1426 data: 0.0525 max mem: 9394 +Train: [5] [3700/6250] eta: 0:05:54 lr: 0.000125 grad: 0.1299 (0.1809) loss: 0.8848 (0.9002) time: 0.1376 data: 0.0597 max mem: 9394 +Train: [5] [3800/6250] eta: 0:05:40 lr: 0.000125 grad: 0.1475 (0.1805) loss: 0.8871 (0.8999) time: 0.1336 data: 0.0542 max mem: 9394 +Train: [5] [3900/6250] eta: 0:05:26 lr: 0.000125 grad: 0.1386 (0.1796) loss: 0.8848 (0.8995) time: 0.1226 data: 0.0433 max mem: 9394 +Train: [5] [4000/6250] eta: 0:05:12 lr: 0.000125 grad: 0.1230 (0.1787) loss: 0.8849 (0.8991) time: 0.1356 data: 0.0578 max mem: 9394 +Train: [5] [4100/6250] eta: 0:04:57 lr: 0.000125 grad: 0.1405 (0.1780) loss: 0.8864 (0.8988) time: 0.1269 data: 0.0504 max mem: 9394 +Train: [5] [4200/6250] eta: 0:04:43 lr: 0.000125 grad: 0.1336 (0.1772) loss: 0.8850 (0.8985) time: 0.1398 data: 0.0607 max mem: 9394 +Train: [5] [4300/6250] eta: 0:04:29 lr: 0.000125 grad: 0.1424 (0.1764) loss: 0.8839 (0.8982) time: 0.1251 data: 0.0447 max mem: 9394 +Train: [5] [4400/6250] eta: 0:04:15 lr: 0.000125 grad: 0.1608 (0.1762) loss: 0.8806 (0.8979) time: 0.1078 data: 0.0274 max mem: 9394 +Train: [5] [4500/6250] eta: 0:04:01 lr: 0.000125 grad: 0.1251 (0.1754) loss: 0.8853 (0.8976) time: 0.1168 data: 0.0312 max mem: 9394 +Train: [5] [4600/6250] eta: 0:03:47 lr: 0.000125 grad: 0.1167 (0.1747) loss: 0.8845 (0.8972) time: 0.1270 data: 0.0504 max mem: 9394 +Train: [5] [4700/6250] eta: 0:03:33 lr: 0.000125 grad: 0.1691 (0.1741) loss: 0.8833 (0.8969) time: 0.1379 data: 0.0555 max mem: 9394 +Train: [5] [4800/6250] eta: 0:03:19 lr: 0.000125 grad: 0.1243 (0.1731) loss: 0.8833 (0.8967) time: 0.1180 data: 0.0377 max mem: 9394 +Train: [5] [4900/6250] eta: 0:03:05 lr: 0.000125 grad: 0.1069 (0.1723) loss: 0.8834 (0.8964) time: 0.1236 data: 0.0421 max mem: 9394 +Train: [5] [5000/6250] eta: 0:02:52 lr: 0.000125 grad: 0.1616 (0.1717) loss: 0.8758 (0.8961) time: 0.1424 data: 0.0654 max mem: 9394 +Train: [5] [5100/6250] eta: 0:02:38 lr: 0.000125 grad: 0.1098 (0.1707) loss: 0.8838 (0.8958) time: 0.1248 data: 0.0448 max mem: 9394 +Train: [5] [5200/6250] eta: 0:02:24 lr: 0.000125 grad: 0.1269 (0.1698) loss: 0.8829 (0.8956) time: 0.1440 data: 0.0708 max mem: 9394 +Train: [5] [5300/6250] eta: 0:02:10 lr: 0.000125 grad: 0.1270 (0.1692) loss: 0.8833 (0.8953) time: 0.1416 data: 0.0633 max mem: 9394 +Train: [5] [5400/6250] eta: 0:01:56 lr: 0.000125 grad: 0.1152 (0.1685) loss: 0.8794 (0.8950) time: 0.1171 data: 0.0363 max mem: 9394 +Train: [5] [5500/6250] eta: 0:01:43 lr: 0.000125 grad: 0.1167 (0.1676) loss: 0.8807 (0.8948) time: 0.1395 data: 0.0638 max mem: 9394 +Train: [5] [5600/6250] eta: 0:01:29 lr: 0.000125 grad: 0.1056 (0.1669) loss: 0.8745 (0.8945) time: 0.1475 data: 0.0690 max mem: 9394 +Train: [5] [5700/6250] eta: 0:01:15 lr: 0.000125 grad: 0.1197 (0.1662) loss: 0.8813 (0.8943) time: 0.1117 data: 0.0274 max mem: 9394 +Train: [5] [5800/6250] eta: 0:01:01 lr: 0.000125 grad: 0.1189 (0.1656) loss: 0.8748 (0.8940) time: 0.1273 data: 0.0489 max mem: 9394 +Train: [5] [5900/6250] eta: 0:00:48 lr: 0.000125 grad: 0.0991 (0.1650) loss: 0.8742 (0.8937) time: 0.1423 data: 0.0615 max mem: 9394 +Train: [5] [6000/6250] eta: 0:00:34 lr: 0.000125 grad: 0.1130 (0.1642) loss: 0.8779 (0.8934) time: 0.2916 data: 0.1815 max mem: 9394 +Train: [5] [6100/6250] eta: 0:00:20 lr: 0.000125 grad: 0.1249 (0.1635) loss: 0.8759 (0.8932) time: 0.1394 data: 0.0545 max mem: 9394 +Train: [5] [6200/6250] eta: 0:00:06 lr: 0.000125 grad: 0.1031 (0.1627) loss: 0.8749 (0.8929) time: 0.1247 data: 0.0455 max mem: 9394 +Train: [5] [6249/6250] eta: 0:00:00 lr: 0.000125 grad: 0.1062 (0.1623) loss: 0.8784 (0.8928) time: 0.1402 data: 0.0601 max mem: 9394 +Train: [5] Total time: 0:14:25 (0.1385 s / it) +Averaged stats: lr: 0.000125 grad: 0.1062 (0.1623) loss: 0.8784 (0.8928) +Eval (hcp-train-subset): [5] [ 0/62] eta: 0:04:11 loss: 0.8888 (0.8888) time: 4.0617 data: 4.0282 max mem: 9394 +Eval (hcp-train-subset): [5] [61/62] eta: 0:00:00 loss: 0.8816 (0.8805) time: 0.1746 data: 0.1488 max mem: 9394 +Eval (hcp-train-subset): [5] Total time: 0:00:14 (0.2416 s / it) +Averaged stats (hcp-train-subset): loss: 0.8816 (0.8805) +Eval (hcp-val): [5] [ 0/62] eta: 0:03:58 loss: 0.8724 (0.8724) time: 3.8541 data: 3.7779 max mem: 9394 +Eval (hcp-val): [5] [61/62] eta: 0:00:00 loss: 0.8743 (0.8744) time: 0.1249 data: 0.1001 max mem: 9394 +Eval (hcp-val): [5] Total time: 0:00:12 (0.2042 s / it) +Averaged stats (hcp-val): loss: 0.8743 (0.8744) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +Train: [6] [ 0/6250] eta: 9:48:23 lr: 0.000125 grad: 0.1191 (0.1191) loss: 0.8915 (0.8915) time: 5.6486 data: 5.5439 max mem: 9394 +Train: [6] [ 100/6250] eta: 0:20:04 lr: 0.000125 grad: 0.1055 (0.1135) loss: 0.8813 (0.8839) time: 0.1534 data: 0.0702 max mem: 9394 +Train: [6] [ 200/6250] eta: 0:16:54 lr: 0.000125 grad: 0.1119 (0.1145) loss: 0.8801 (0.8815) time: 0.1480 data: 0.0676 max mem: 9394 +Train: [6] [ 300/6250] eta: 0:15:12 lr: 0.000125 grad: 0.1143 (0.1148) loss: 0.8808 (0.8806) time: 0.1188 data: 0.0390 max mem: 9394 +Train: [6] [ 400/6250] eta: 0:14:21 lr: 0.000125 grad: 0.1024 (0.1162) loss: 0.8761 (0.8798) time: 0.1138 data: 0.0293 max mem: 9394 +Train: [6] [ 500/6250] eta: 0:13:41 lr: 0.000125 grad: 0.1140 (0.1174) loss: 0.8809 (0.8789) time: 0.1370 data: 0.0519 max mem: 9394 +Train: [6] [ 600/6250] eta: 0:13:07 lr: 0.000125 grad: 0.1024 (0.1184) loss: 0.8782 (0.8785) time: 0.1336 data: 0.0528 max mem: 9394 +Train: [6] [ 700/6250] eta: 0:12:41 lr: 0.000125 grad: 0.1006 (0.1210) loss: 0.8787 (0.8784) time: 0.1123 data: 0.0280 max mem: 9394 +Train: [6] [ 800/6250] eta: 0:12:31 lr: 0.000125 grad: 0.1128 (0.1201) loss: 0.8766 (0.8781) time: 0.1445 data: 0.0594 max mem: 9394 +Train: [6] [ 900/6250] eta: 0:12:27 lr: 0.000125 grad: 0.0973 (0.1188) loss: 0.8744 (0.8778) time: 0.1610 data: 0.0753 max mem: 9394 +Train: [6] [1000/6250] eta: 0:12:13 lr: 0.000125 grad: 0.1079 (0.1184) loss: 0.8758 (0.8777) time: 0.1452 data: 0.0642 max mem: 9394 +Train: [6] [1100/6250] eta: 0:12:00 lr: 0.000125 grad: 0.0932 (0.1174) loss: 0.8761 (0.8775) time: 0.1448 data: 0.0660 max mem: 9394 +Train: [6] [1200/6250] eta: 0:11:51 lr: 0.000125 grad: 0.0944 (0.1158) loss: 0.8714 (0.8772) time: 0.1329 data: 0.0530 max mem: 9394 +Train: [6] [1300/6250] eta: 0:11:58 lr: 0.000125 grad: 0.1036 (0.1152) loss: 0.8758 (0.8770) time: 0.3532 data: 0.2645 max mem: 9394 +Train: [6] [1400/6250] eta: 0:11:36 lr: 0.000125 grad: 0.0971 (0.1143) loss: 0.8743 (0.8768) time: 0.1416 data: 0.0596 max mem: 9394 +Train: [6] [1500/6250] eta: 0:11:20 lr: 0.000125 grad: 0.0891 (0.1136) loss: 0.8686 (0.8765) time: 0.1365 data: 0.0598 max mem: 9394 +Train: [6] [1600/6250] eta: 0:11:29 lr: 0.000125 grad: 0.1002 (0.1129) loss: 0.8692 (0.8762) time: 0.4252 data: 0.3054 max mem: 9394 +Train: [6] [1700/6250] eta: 0:11:07 lr: 0.000125 grad: 0.0950 (0.1126) loss: 0.8677 (0.8759) time: 0.1191 data: 0.0389 max mem: 9394 +Train: [6] [1800/6250] eta: 0:10:52 lr: 0.000125 grad: 0.1129 (0.1134) loss: 0.8684 (0.8755) time: 0.1434 data: 0.0664 max mem: 9394 +Train: [6] [1900/6250] eta: 0:10:35 lr: 0.000125 grad: 0.0999 (0.1135) loss: 0.8675 (0.8752) time: 0.1045 data: 0.0237 max mem: 9394 +Train: [6] [2000/6250] eta: 0:10:20 lr: 0.000125 grad: 0.1082 (0.1131) loss: 0.8695 (0.8750) time: 0.1691 data: 0.0736 max mem: 9394 +Train: [6] [2100/6250] eta: 0:10:07 lr: 0.000125 grad: 0.0993 (0.1128) loss: 0.8646 (0.8747) time: 0.1520 data: 0.0720 max mem: 9394 +Train: [6] [2200/6250] eta: 0:09:51 lr: 0.000125 grad: 0.0923 (0.1124) loss: 0.8698 (0.8744) time: 0.1238 data: 0.0425 max mem: 9394 +Train: [6] [2300/6250] eta: 0:09:36 lr: 0.000125 grad: 0.0957 (0.1120) loss: 0.8685 (0.8741) time: 0.1531 data: 0.0780 max mem: 9394 +Train: [6] [2400/6250] eta: 0:09:20 lr: 0.000125 grad: 0.1010 (0.1113) loss: 0.8659 (0.8739) time: 0.1440 data: 0.0648 max mem: 9394 +Train: [6] [2500/6250] eta: 0:09:04 lr: 0.000125 grad: 0.0911 (0.1113) loss: 0.8666 (0.8737) time: 0.1472 data: 0.0706 max mem: 9394 +Train: [6] [2600/6250] eta: 0:08:48 lr: 0.000125 grad: 0.0879 (0.1114) loss: 0.8683 (0.8734) time: 0.1354 data: 0.0503 max mem: 9394 +Train: [6] [2700/6250] eta: 0:08:33 lr: 0.000125 grad: 0.1056 (0.1110) loss: 0.8673 (0.8732) time: 0.1130 data: 0.0339 max mem: 9394 +Train: [6] [2800/6250] eta: 0:08:19 lr: 0.000125 grad: 0.1045 (0.1107) loss: 0.8667 (0.8730) time: 0.1966 data: 0.0953 max mem: 9394 +Train: [6] [2900/6250] eta: 0:08:04 lr: 0.000125 grad: 0.1254 (0.1104) loss: 0.8717 (0.8728) time: 0.1306 data: 0.0494 max mem: 9394 +Train: [6] [3000/6250] eta: 0:07:49 lr: 0.000125 grad: 0.0995 (0.1102) loss: 0.8708 (0.8727) time: 0.1353 data: 0.0603 max mem: 9394 +Train: [6] [3100/6250] eta: 0:07:33 lr: 0.000125 grad: 0.0966 (0.1098) loss: 0.8686 (0.8725) time: 0.1238 data: 0.0440 max mem: 9394 +Train: [6] [3200/6250] eta: 0:07:18 lr: 0.000125 grad: 0.0926 (0.1094) loss: 0.8656 (0.8724) time: 0.1320 data: 0.0534 max mem: 9394 +Train: [6] [3300/6250] eta: 0:07:03 lr: 0.000125 grad: 0.0891 (0.1092) loss: 0.8662 (0.8722) time: 0.1456 data: 0.0673 max mem: 9394 +Train: [6] [3400/6250] eta: 0:06:48 lr: 0.000125 grad: 0.0959 (0.1090) loss: 0.8715 (0.8721) time: 0.1520 data: 0.0714 max mem: 9394 +Train: [6] [3500/6250] eta: 0:06:33 lr: 0.000125 grad: 0.0879 (0.1086) loss: 0.8686 (0.8721) time: 0.1187 data: 0.0313 max mem: 9394 +Train: [6] [3600/6250] eta: 0:06:18 lr: 0.000125 grad: 0.0882 (0.1082) loss: 0.8688 (0.8719) time: 0.1302 data: 0.0485 max mem: 9394 +Train: [6] [3700/6250] eta: 0:06:05 lr: 0.000125 grad: 0.0943 (0.1080) loss: 0.8723 (0.8719) time: 0.1319 data: 0.0455 max mem: 9394 +Train: [6] [3800/6250] eta: 0:05:50 lr: 0.000125 grad: 0.0871 (0.1076) loss: 0.8669 (0.8717) time: 0.1443 data: 0.0669 max mem: 9394 +Train: [6] [3900/6250] eta: 0:05:36 lr: 0.000125 grad: 0.0915 (0.1072) loss: 0.8709 (0.8716) time: 0.1325 data: 0.0532 max mem: 9394 +Train: [6] [4000/6250] eta: 0:05:21 lr: 0.000125 grad: 0.1088 (0.1070) loss: 0.8681 (0.8715) time: 0.1409 data: 0.0650 max mem: 9394 +Train: [6] [4100/6250] eta: 0:05:06 lr: 0.000125 grad: 0.0903 (0.1068) loss: 0.8605 (0.8714) time: 0.1561 data: 0.0724 max mem: 9394 +Train: [6] [4200/6250] eta: 0:04:52 lr: 0.000125 grad: 0.0883 (0.1067) loss: 0.8658 (0.8713) time: 0.1423 data: 0.0662 max mem: 9394 +Train: [6] [4300/6250] eta: 0:04:37 lr: 0.000125 grad: 0.0957 (0.1064) loss: 0.8690 (0.8712) time: 0.1366 data: 0.0473 max mem: 9394 +Train: [6] [4400/6250] eta: 0:04:22 lr: 0.000125 grad: 0.0860 (0.1060) loss: 0.8647 (0.8711) time: 0.1538 data: 0.0763 max mem: 9394 +Train: [6] [4500/6250] eta: 0:04:08 lr: 0.000125 grad: 0.0897 (0.1057) loss: 0.8665 (0.8710) time: 0.1497 data: 0.0706 max mem: 9394 +Train: [6] [4600/6250] eta: 0:03:53 lr: 0.000125 grad: 0.0829 (0.1054) loss: 0.8645 (0.8709) time: 0.1344 data: 0.0585 max mem: 9394 +Train: [6] [4700/6250] eta: 0:03:39 lr: 0.000125 grad: 0.0874 (0.1052) loss: 0.8692 (0.8708) time: 0.1215 data: 0.0412 max mem: 9394 +Train: [6] [4800/6250] eta: 0:03:25 lr: 0.000125 grad: 0.0863 (0.1049) loss: 0.8679 (0.8707) time: 0.1228 data: 0.0443 max mem: 9394 +Train: [6] [4900/6250] eta: 0:03:10 lr: 0.000125 grad: 0.0917 (0.1046) loss: 0.8631 (0.8706) time: 0.1452 data: 0.0627 max mem: 9394 +Train: [6] [5000/6250] eta: 0:02:56 lr: 0.000125 grad: 0.0840 (0.1044) loss: 0.8674 (0.8705) time: 0.0925 data: 0.0020 max mem: 9394 +Train: [6] [5100/6250] eta: 0:02:42 lr: 0.000125 grad: 0.0860 (0.1041) loss: 0.8675 (0.8705) time: 0.1268 data: 0.0475 max mem: 9394 +Train: [6] [5200/6250] eta: 0:02:28 lr: 0.000125 grad: 0.0949 (0.1038) loss: 0.8684 (0.8704) time: 0.1097 data: 0.0163 max mem: 9394 +Train: [6] [5300/6250] eta: 0:02:13 lr: 0.000125 grad: 0.0832 (0.1036) loss: 0.8639 (0.8703) time: 0.1464 data: 0.0679 max mem: 9394 +Train: [6] [5400/6250] eta: 0:01:59 lr: 0.000125 grad: 0.0815 (0.1033) loss: 0.8667 (0.8703) time: 0.1116 data: 0.0327 max mem: 9394 +Train: [6] [5500/6250] eta: 0:01:45 lr: 0.000125 grad: 0.0818 (0.1030) loss: 0.8676 (0.8702) time: 0.1374 data: 0.0582 max mem: 9394 +Train: [6] [5600/6250] eta: 0:01:31 lr: 0.000125 grad: 0.0804 (0.1027) loss: 0.8685 (0.8702) time: 0.1223 data: 0.0441 max mem: 9394 +Train: [6] [5700/6250] eta: 0:01:17 lr: 0.000125 grad: 0.0815 (0.1024) loss: 0.8680 (0.8701) time: 0.1343 data: 0.0608 max mem: 9394 +Train: [6] [5800/6250] eta: 0:01:03 lr: 0.000125 grad: 0.0780 (0.1022) loss: 0.8644 (0.8700) time: 0.1493 data: 0.0696 max mem: 9394 +Train: [6] [5900/6250] eta: 0:00:49 lr: 0.000125 grad: 0.0906 (0.1021) loss: 0.8676 (0.8700) time: 0.1477 data: 0.0725 max mem: 9394 +Train: [6] [6000/6250] eta: 0:00:35 lr: 0.000125 grad: 0.0850 (0.1018) loss: 0.8661 (0.8699) time: 0.1708 data: 0.0839 max mem: 9394 +Train: [6] [6100/6250] eta: 0:00:21 lr: 0.000125 grad: 0.0773 (0.1017) loss: 0.8672 (0.8699) time: 0.1578 data: 0.0805 max mem: 9394 +Train: [6] [6200/6250] eta: 0:00:07 lr: 0.000125 grad: 0.0872 (0.1014) loss: 0.8620 (0.8698) time: 0.1309 data: 0.0530 max mem: 9394 +Train: [6] [6249/6250] eta: 0:00:00 lr: 0.000125 grad: 0.0800 (0.1013) loss: 0.8678 (0.8698) time: 0.1546 data: 0.0779 max mem: 9394 +Train: [6] Total time: 0:14:45 (0.1416 s / it) +Averaged stats: lr: 0.000125 grad: 0.0800 (0.1013) loss: 0.8678 (0.8698) +Eval (hcp-train-subset): [6] [ 0/62] eta: 0:04:37 loss: 0.8770 (0.8770) time: 4.4812 data: 4.4480 max mem: 9394 +Eval (hcp-train-subset): [6] [61/62] eta: 0:00:00 loss: 0.8675 (0.8680) time: 0.1260 data: 0.1015 max mem: 9394 +Eval (hcp-train-subset): [6] Total time: 0:00:12 (0.2083 s / it) +Averaged stats (hcp-train-subset): loss: 0.8675 (0.8680) +Eval (hcp-val): [6] [ 0/62] eta: 0:03:12 loss: 0.8588 (0.8588) time: 3.1083 data: 3.0467 max mem: 9394 +Eval (hcp-val): [6] [61/62] eta: 0:00:00 loss: 0.8613 (0.8624) time: 0.1203 data: 0.0939 max mem: 9394 +Eval (hcp-val): [6] Total time: 0:00:12 (0.1965 s / it) +Averaged stats (hcp-val): loss: 0.8613 (0.8624) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +Train: [7] [ 0/6250] eta: 7:54:28 lr: 0.000125 grad: 0.0648 (0.0648) loss: 0.8620 (0.8620) time: 4.5550 data: 4.2383 max mem: 9394 +Train: [7] [ 100/6250] eta: 0:20:43 lr: 0.000125 grad: 0.0785 (0.0903) loss: 0.8696 (0.8778) time: 0.1385 data: 0.0563 max mem: 9394 +Train: [7] [ 200/6250] eta: 0:17:33 lr: 0.000125 grad: 0.0798 (0.0882) loss: 0.8652 (0.8722) time: 0.1493 data: 0.0650 max mem: 9394 +Train: [7] [ 300/6250] eta: 0:15:59 lr: 0.000125 grad: 0.0880 (0.0883) loss: 0.8638 (0.8693) time: 0.1303 data: 0.0454 max mem: 9394 +Train: [7] [ 400/6250] eta: 0:15:01 lr: 0.000125 grad: 0.0820 (0.0872) loss: 0.8617 (0.8681) time: 0.1406 data: 0.0513 max mem: 9394 +Train: [7] [ 500/6250] eta: 0:14:09 lr: 0.000125 grad: 0.0967 (0.0884) loss: 0.8597 (0.8671) time: 0.1248 data: 0.0410 max mem: 9394 +Train: [7] [ 600/6250] eta: 0:13:32 lr: 0.000125 grad: 0.0832 (0.0883) loss: 0.8598 (0.8664) time: 0.1100 data: 0.0149 max mem: 9394 +Train: [7] [ 700/6250] eta: 0:13:03 lr: 0.000125 grad: 0.0749 (0.0874) loss: 0.8627 (0.8662) time: 0.1230 data: 0.0300 max mem: 9394 +Train: [7] [ 800/6250] eta: 0:12:51 lr: 0.000125 grad: 0.0828 (0.0874) loss: 0.8625 (0.8659) time: 0.1294 data: 0.0402 max mem: 9394 +Train: [7] [ 900/6250] eta: 0:12:51 lr: 0.000125 grad: 0.0820 (0.0867) loss: 0.8608 (0.8656) time: 0.1730 data: 0.0945 max mem: 9394 +Train: [7] [1000/6250] eta: 0:12:40 lr: 0.000125 grad: 0.0840 (0.0866) loss: 0.8631 (0.8654) time: 0.1468 data: 0.0581 max mem: 9394 +Train: [7] [1100/6250] eta: 0:12:27 lr: 0.000125 grad: 0.0842 (0.0865) loss: 0.8643 (0.8651) time: 0.1475 data: 0.0690 max mem: 9394 +Train: [7] [1200/6250] eta: 0:12:14 lr: 0.000125 grad: 0.0802 (0.0865) loss: 0.8617 (0.8649) time: 0.1395 data: 0.0642 max mem: 9394 +Train: [7] [1300/6250] eta: 0:11:59 lr: 0.000125 grad: 0.0791 (0.0864) loss: 0.8618 (0.8649) time: 0.1426 data: 0.0545 max mem: 9394 +Train: [7] [1400/6250] eta: 0:11:48 lr: 0.000125 grad: 0.0722 (0.0861) loss: 0.8649 (0.8648) time: 0.1218 data: 0.0383 max mem: 9394 +Train: [7] [1500/6250] eta: 0:11:34 lr: 0.000125 grad: 0.0782 (0.0859) loss: 0.8618 (0.8647) time: 0.1302 data: 0.0312 max mem: 9394 +Train: [7] [1600/6250] eta: 0:11:22 lr: 0.000125 grad: 0.0916 (0.0862) loss: 0.8627 (0.8646) time: 0.1365 data: 0.0580 max mem: 9394 +Train: [7] [1700/6250] eta: 0:11:04 lr: 0.000125 grad: 0.0880 (0.0860) loss: 0.8585 (0.8644) time: 0.1331 data: 0.0520 max mem: 9394 +Train: [7] [1800/6250] eta: 0:10:54 lr: 0.000125 grad: 0.0835 (0.0860) loss: 0.8632 (0.8643) time: 0.1172 data: 0.0174 max mem: 9394 +Train: [7] [1900/6250] eta: 0:10:37 lr: 0.000125 grad: 0.0850 (0.0863) loss: 0.8581 (0.8642) time: 0.1533 data: 0.0742 max mem: 9394 +Train: [7] [2000/6250] eta: 0:10:21 lr: 0.000125 grad: 0.0759 (0.0863) loss: 0.8642 (0.8641) time: 0.1449 data: 0.0636 max mem: 9394 +Train: [7] [2100/6250] eta: 0:10:04 lr: 0.000125 grad: 0.0830 (0.0862) loss: 0.8647 (0.8639) time: 0.1212 data: 0.0382 max mem: 9394 +Train: [7] [2200/6250] eta: 0:09:48 lr: 0.000125 grad: 0.0757 (0.0862) loss: 0.8609 (0.8638) time: 0.1393 data: 0.0583 max mem: 9394 +Train: [7] [2300/6250] eta: 0:09:32 lr: 0.000125 grad: 0.0740 (0.0861) loss: 0.8593 (0.8636) time: 0.1513 data: 0.0774 max mem: 9394 +Train: [7] [2400/6250] eta: 0:09:23 lr: 0.000125 grad: 0.0824 (0.0862) loss: 0.8601 (0.8634) time: 0.2448 data: 0.1650 max mem: 9394 +Train: [7] [2500/6250] eta: 0:09:05 lr: 0.000125 grad: 0.0786 (0.0862) loss: 0.8607 (0.8633) time: 0.1456 data: 0.0644 max mem: 9394 +Train: [7] [2600/6250] eta: 0:08:50 lr: 0.000125 grad: 0.0766 (0.0862) loss: 0.8613 (0.8632) time: 0.1156 data: 0.0413 max mem: 9394 +Train: [7] [2700/6250] eta: 0:08:34 lr: 0.000125 grad: 0.0757 (0.0861) loss: 0.8609 (0.8630) time: 0.1324 data: 0.0533 max mem: 9394 +Train: [7] [2800/6250] eta: 0:08:19 lr: 0.000125 grad: 0.0867 (0.0861) loss: 0.8576 (0.8629) time: 0.1466 data: 0.0674 max mem: 9394 +Train: [7] [2900/6250] eta: 0:08:04 lr: 0.000125 grad: 0.0787 (0.0859) loss: 0.8533 (0.8627) time: 0.1331 data: 0.0511 max mem: 9394 +Train: [7] [3000/6250] eta: 0:07:49 lr: 0.000125 grad: 0.0796 (0.0859) loss: 0.8570 (0.8626) time: 0.1348 data: 0.0559 max mem: 9394 +Train: [7] [3100/6250] eta: 0:07:34 lr: 0.000125 grad: 0.0784 (0.0857) loss: 0.8603 (0.8625) time: 0.1512 data: 0.0643 max mem: 9394 +Train: [7] [3200/6250] eta: 0:07:19 lr: 0.000125 grad: 0.0773 (0.0856) loss: 0.8562 (0.8624) time: 0.1486 data: 0.0687 max mem: 9394 +Train: [7] [3300/6250] eta: 0:07:05 lr: 0.000125 grad: 0.0748 (0.0856) loss: 0.8589 (0.8623) time: 0.1573 data: 0.0821 max mem: 9394 +Train: [7] [3400/6250] eta: 0:06:49 lr: 0.000125 grad: 0.0797 (0.0855) loss: 0.8559 (0.8622) time: 0.1517 data: 0.0706 max mem: 9394 +Train: [7] [3500/6250] eta: 0:06:35 lr: 0.000125 grad: 0.0831 (0.0855) loss: 0.8637 (0.8621) time: 0.1385 data: 0.0564 max mem: 9394 +Train: [7] [3600/6250] eta: 0:06:20 lr: 0.000125 grad: 0.0766 (0.0853) loss: 0.8603 (0.8620) time: 0.1324 data: 0.0520 max mem: 9394 +Train: [7] [3700/6250] eta: 0:06:05 lr: 0.000125 grad: 0.0776 (0.0853) loss: 0.8630 (0.8620) time: 0.1364 data: 0.0558 max mem: 9394 +Train: [7] [3800/6250] eta: 0:05:50 lr: 0.000125 grad: 0.0761 (0.0852) loss: 0.8619 (0.8620) time: 0.1100 data: 0.0283 max mem: 9394 +Train: [7] [3900/6250] eta: 0:05:36 lr: 0.000125 grad: 0.0778 (0.0850) loss: 0.8611 (0.8620) time: 0.0959 data: 0.0177 max mem: 9394 +Train: [7] [4000/6250] eta: 0:05:21 lr: 0.000125 grad: 0.0789 (0.0850) loss: 0.8635 (0.8619) time: 0.1489 data: 0.0684 max mem: 9394 +Train: [7] [4100/6250] eta: 0:05:06 lr: 0.000125 grad: 0.0755 (0.0850) loss: 0.8644 (0.8619) time: 0.1178 data: 0.0345 max mem: 9394 +Train: [7] [4200/6250] eta: 0:04:52 lr: 0.000125 grad: 0.0880 (0.0850) loss: 0.8592 (0.8619) time: 0.1395 data: 0.0543 max mem: 9394 +Train: [7] [4300/6250] eta: 0:04:37 lr: 0.000125 grad: 0.0759 (0.0850) loss: 0.8578 (0.8618) time: 0.1465 data: 0.0681 max mem: 9394 +Train: [7] [4400/6250] eta: 0:04:23 lr: 0.000125 grad: 0.0747 (0.0849) loss: 0.8604 (0.8618) time: 0.1302 data: 0.0462 max mem: 9394 +Train: [7] [4500/6250] eta: 0:04:08 lr: 0.000125 grad: 0.0743 (0.0848) loss: 0.8573 (0.8617) time: 0.1013 data: 0.0191 max mem: 9394 +Train: [7] [4600/6250] eta: 0:03:54 lr: 0.000125 grad: 0.0750 (0.0846) loss: 0.8590 (0.8617) time: 0.1325 data: 0.0536 max mem: 9394 +Train: [7] [4700/6250] eta: 0:03:39 lr: 0.000125 grad: 0.0744 (0.0845) loss: 0.8578 (0.8617) time: 0.1303 data: 0.0525 max mem: 9394 +Train: [7] [4800/6250] eta: 0:03:26 lr: 0.000125 grad: 0.0764 (0.0844) loss: 0.8580 (0.8616) time: 0.0927 data: 0.0002 max mem: 9394 +Train: [7] [4900/6250] eta: 0:03:11 lr: 0.000125 grad: 0.0821 (0.0844) loss: 0.8618 (0.8616) time: 0.1201 data: 0.0423 max mem: 9394 +Train: [7] [5000/6250] eta: 0:02:57 lr: 0.000125 grad: 0.0772 (0.0843) loss: 0.8580 (0.8616) time: 0.1285 data: 0.0490 max mem: 9394 +Train: [7] [5100/6250] eta: 0:02:43 lr: 0.000125 grad: 0.0747 (0.0842) loss: 0.8613 (0.8616) time: 0.0931 data: 0.0002 max mem: 9394 +Train: [7] [5200/6250] eta: 0:02:29 lr: 0.000125 grad: 0.0798 (0.0841) loss: 0.8593 (0.8615) time: 0.1353 data: 0.0553 max mem: 9394 +Train: [7] [5300/6250] eta: 0:02:15 lr: 0.000125 grad: 0.0737 (0.0840) loss: 0.8602 (0.8615) time: 0.1171 data: 0.0287 max mem: 9394 +Train: [7] [5400/6250] eta: 0:02:00 lr: 0.000125 grad: 0.0870 (0.0839) loss: 0.8589 (0.8614) time: 0.1070 data: 0.0296 max mem: 9394 +Train: [7] [5500/6250] eta: 0:01:46 lr: 0.000125 grad: 0.0763 (0.0839) loss: 0.8583 (0.8614) time: 0.1284 data: 0.0481 max mem: 9394 +Train: [7] [5600/6250] eta: 0:01:32 lr: 0.000125 grad: 0.0695 (0.0837) loss: 0.8604 (0.8614) time: 0.1292 data: 0.0509 max mem: 9394 +Train: [7] [5700/6250] eta: 0:01:18 lr: 0.000125 grad: 0.0756 (0.0836) loss: 0.8573 (0.8613) time: 0.1464 data: 0.0734 max mem: 9394 +Train: [7] [5800/6250] eta: 0:01:03 lr: 0.000125 grad: 0.0750 (0.0835) loss: 0.8570 (0.8612) time: 0.1581 data: 0.0823 max mem: 9394 +Train: [7] [5900/6250] eta: 0:00:49 lr: 0.000125 grad: 0.0678 (0.0834) loss: 0.8569 (0.8612) time: 0.1119 data: 0.0283 max mem: 9394 +Train: [7] [6000/6250] eta: 0:00:35 lr: 0.000125 grad: 0.0779 (0.0833) loss: 0.8562 (0.8611) time: 0.1411 data: 0.0620 max mem: 9394 +Train: [7] [6100/6250] eta: 0:00:21 lr: 0.000125 grad: 0.0715 (0.0833) loss: 0.8592 (0.8611) time: 0.1492 data: 0.0655 max mem: 9394 +Train: [7] [6200/6250] eta: 0:00:07 lr: 0.000125 grad: 0.0710 (0.0832) loss: 0.8560 (0.8610) time: 0.1460 data: 0.0633 max mem: 9394 +Train: [7] [6249/6250] eta: 0:00:00 lr: 0.000125 grad: 0.0722 (0.0831) loss: 0.8626 (0.8610) time: 0.1410 data: 0.0621 max mem: 9394 +Train: [7] Total time: 0:14:50 (0.1425 s / it) +Averaged stats: lr: 0.000125 grad: 0.0722 (0.0831) loss: 0.8626 (0.8610) +Eval (hcp-train-subset): [7] [ 0/62] eta: 0:04:06 loss: 0.8711 (0.8711) time: 3.9683 data: 3.9045 max mem: 9394 +Eval (hcp-train-subset): [7] [61/62] eta: 0:00:00 loss: 0.8621 (0.8621) time: 0.1444 data: 0.1196 max mem: 9394 +Eval (hcp-train-subset): [7] Total time: 0:00:13 (0.2201 s / it) +Averaged stats (hcp-train-subset): loss: 0.8621 (0.8621) +Eval (hcp-val): [7] [ 0/62] eta: 0:05:15 loss: 0.8544 (0.8544) time: 5.0937 data: 5.0612 max mem: 9394 +Eval (hcp-val): [7] [61/62] eta: 0:00:00 loss: 0.8566 (0.8565) time: 0.1358 data: 0.1103 max mem: 9394 +Eval (hcp-val): [7] Total time: 0:00:13 (0.2232 s / it) +Averaged stats (hcp-val): loss: 0.8566 (0.8565) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +Train: [8] [ 0/6250] eta: 7:00:28 lr: 0.000125 grad: 0.0558 (0.0558) loss: 0.8887 (0.8887) time: 4.0365 data: 3.7882 max mem: 9394 +Train: [8] [ 100/6250] eta: 0:20:09 lr: 0.000125 grad: 0.0743 (0.0766) loss: 0.8557 (0.8608) time: 0.1468 data: 0.0601 max mem: 9394 +Train: [8] [ 200/6250] eta: 0:17:13 lr: 0.000125 grad: 0.0774 (0.0763) loss: 0.8583 (0.8600) time: 0.1271 data: 0.0382 max mem: 9394 +Train: [8] [ 300/6250] eta: 0:15:45 lr: 0.000125 grad: 0.0716 (0.0760) loss: 0.8526 (0.8601) time: 0.1335 data: 0.0517 max mem: 9394 +Train: [8] [ 400/6250] eta: 0:14:44 lr: 0.000125 grad: 0.0781 (0.0755) loss: 0.8600 (0.8605) time: 0.1244 data: 0.0387 max mem: 9394 +Train: [8] [ 500/6250] eta: 0:14:00 lr: 0.000125 grad: 0.0685 (0.0749) loss: 0.8583 (0.8605) time: 0.1283 data: 0.0495 max mem: 9394 +Train: [8] [ 600/6250] eta: 0:13:29 lr: 0.000125 grad: 0.0720 (0.0750) loss: 0.8655 (0.8603) time: 0.1274 data: 0.0424 max mem: 9394 +Train: [8] [ 700/6250] eta: 0:13:08 lr: 0.000125 grad: 0.0731 (0.0750) loss: 0.8571 (0.8603) time: 0.1671 data: 0.0881 max mem: 9394 +Train: [8] [ 800/6250] eta: 0:13:00 lr: 0.000125 grad: 0.0736 (0.0747) loss: 0.8611 (0.8604) time: 0.1399 data: 0.0626 max mem: 9394 +Train: [8] [ 900/6250] eta: 0:13:01 lr: 0.000125 grad: 0.0700 (0.0743) loss: 0.8592 (0.8603) time: 0.1866 data: 0.1069 max mem: 9394 +Train: [8] [1000/6250] eta: 0:12:52 lr: 0.000125 grad: 0.0695 (0.0742) loss: 0.8580 (0.8604) time: 0.1357 data: 0.0554 max mem: 9394 +Train: [8] [1100/6250] eta: 0:12:39 lr: 0.000125 grad: 0.0642 (0.0740) loss: 0.8604 (0.8603) time: 0.1461 data: 0.0587 max mem: 9394 +Train: [8] [1200/6250] eta: 0:12:25 lr: 0.000125 grad: 0.0718 (0.0740) loss: 0.8565 (0.8601) time: 0.1125 data: 0.0307 max mem: 9394 +Train: [8] [1300/6250] eta: 0:12:08 lr: 0.000125 grad: 0.0764 (0.0744) loss: 0.8569 (0.8600) time: 0.1372 data: 0.0554 max mem: 9394 +Train: [8] [1400/6250] eta: 0:12:01 lr: 0.000125 grad: 0.0754 (0.0744) loss: 0.8553 (0.8597) time: 0.1459 data: 0.0629 max mem: 9394 +Train: [8] [1500/6250] eta: 0:11:54 lr: 0.000125 grad: 0.0669 (0.0742) loss: 0.8527 (0.8595) time: 0.0980 data: 0.0098 max mem: 9394 +Train: [8] [1600/6250] eta: 0:11:36 lr: 0.000125 grad: 0.0683 (0.0739) loss: 0.8545 (0.8594) time: 0.1505 data: 0.0651 max mem: 9394 +Train: [8] [1700/6250] eta: 0:11:26 lr: 0.000125 grad: 0.0687 (0.0742) loss: 0.8591 (0.8593) time: 0.1284 data: 0.0425 max mem: 9394 +Train: [8] [1800/6250] eta: 0:11:07 lr: 0.000125 grad: 0.0696 (0.0742) loss: 0.8523 (0.8591) time: 0.1370 data: 0.0597 max mem: 9394 +Train: [8] [1900/6250] eta: 0:10:48 lr: 0.000125 grad: 0.0710 (0.0742) loss: 0.8523 (0.8589) time: 0.1376 data: 0.0580 max mem: 9394 +Train: [8] [2000/6250] eta: 0:10:53 lr: 0.000125 grad: 0.0663 (0.0741) loss: 0.8522 (0.8588) time: 0.3286 data: 0.2357 max mem: 9394 +Train: [8] [2100/6250] eta: 0:10:31 lr: 0.000125 grad: 0.0796 (0.0742) loss: 0.8567 (0.8587) time: 0.1379 data: 0.0575 max mem: 9394 +Train: [8] [2200/6250] eta: 0:10:13 lr: 0.000125 grad: 0.0697 (0.0742) loss: 0.8580 (0.8586) time: 0.1439 data: 0.0623 max mem: 9394 +Train: [8] [2300/6250] eta: 0:09:55 lr: 0.000125 grad: 0.0670 (0.0741) loss: 0.8602 (0.8585) time: 0.1300 data: 0.0514 max mem: 9394 +Train: [8] [2400/6250] eta: 0:09:38 lr: 0.000125 grad: 0.0692 (0.0741) loss: 0.8546 (0.8584) time: 0.1391 data: 0.0530 max mem: 9394 +Train: [8] [2500/6250] eta: 0:09:26 lr: 0.000125 grad: 0.0694 (0.0740) loss: 0.8579 (0.8583) time: 0.1219 data: 0.0214 max mem: 9394 +Train: [8] [2600/6250] eta: 0:09:09 lr: 0.000125 grad: 0.0765 (0.0739) loss: 0.8553 (0.8582) time: 0.1350 data: 0.0548 max mem: 9394 +Train: [8] [2700/6250] eta: 0:08:53 lr: 0.000125 grad: 0.0708 (0.0739) loss: 0.8502 (0.8580) time: 0.1663 data: 0.0817 max mem: 9394 +Train: [8] [2800/6250] eta: 0:08:36 lr: 0.000125 grad: 0.0708 (0.0740) loss: 0.8538 (0.8579) time: 0.1378 data: 0.0646 max mem: 9394 +Train: [8] [2900/6250] eta: 0:08:20 lr: 0.000125 grad: 0.0652 (0.0740) loss: 0.8541 (0.8578) time: 0.1453 data: 0.0668 max mem: 9394 +Train: [8] [3000/6250] eta: 0:08:03 lr: 0.000125 grad: 0.0676 (0.0739) loss: 0.8522 (0.8577) time: 0.1373 data: 0.0590 max mem: 9394 +Train: [8] [3100/6250] eta: 0:07:47 lr: 0.000125 grad: 0.0762 (0.0740) loss: 0.8541 (0.8576) time: 0.1274 data: 0.0469 max mem: 9394 +Train: [8] [3200/6250] eta: 0:07:31 lr: 0.000125 grad: 0.0695 (0.0740) loss: 0.8552 (0.8575) time: 0.1051 data: 0.0280 max mem: 9394 +Train: [8] [3300/6250] eta: 0:07:15 lr: 0.000125 grad: 0.0718 (0.0741) loss: 0.8550 (0.8574) time: 0.1286 data: 0.0490 max mem: 9394 +Train: [8] [3400/6250] eta: 0:07:00 lr: 0.000125 grad: 0.0775 (0.0742) loss: 0.8470 (0.8572) time: 0.1289 data: 0.0500 max mem: 9394 +Train: [8] [3500/6250] eta: 0:06:44 lr: 0.000125 grad: 0.0753 (0.0744) loss: 0.8526 (0.8571) time: 0.1288 data: 0.0459 max mem: 9394 +Train: [8] [3600/6250] eta: 0:06:29 lr: 0.000125 grad: 0.0731 (0.0744) loss: 0.8519 (0.8570) time: 0.1475 data: 0.0710 max mem: 9394 +Train: [8] [3700/6250] eta: 0:06:13 lr: 0.000125 grad: 0.0713 (0.0746) loss: 0.8492 (0.8568) time: 0.1254 data: 0.0484 max mem: 9394 +Train: [8] [3800/6250] eta: 0:05:58 lr: 0.000125 grad: 0.0690 (0.0747) loss: 0.8474 (0.8567) time: 0.1333 data: 0.0543 max mem: 9394 +Train: [8] [3900/6250] eta: 0:05:43 lr: 0.000125 grad: 0.0714 (0.0748) loss: 0.8556 (0.8566) time: 0.1298 data: 0.0491 max mem: 9394 +Train: [8] [4000/6250] eta: 0:05:28 lr: 0.000125 grad: 0.0689 (0.0747) loss: 0.8521 (0.8565) time: 0.1390 data: 0.0626 max mem: 9394 +Train: [8] [4100/6250] eta: 0:05:12 lr: 0.000125 grad: 0.0674 (0.0746) loss: 0.8543 (0.8564) time: 0.1455 data: 0.0620 max mem: 9394 +Train: [8] [4200/6250] eta: 0:04:57 lr: 0.000125 grad: 0.0704 (0.0746) loss: 0.8514 (0.8563) time: 0.1364 data: 0.0558 max mem: 9394 +Train: [8] [4300/6250] eta: 0:04:43 lr: 0.000125 grad: 0.0687 (0.0745) loss: 0.8513 (0.8562) time: 0.1100 data: 0.0318 max mem: 9394 +Train: [8] [4400/6250] eta: 0:04:28 lr: 0.000125 grad: 0.0683 (0.0745) loss: 0.8492 (0.8561) time: 0.1215 data: 0.0394 max mem: 9394 +Train: [8] [4500/6250] eta: 0:04:13 lr: 0.000125 grad: 0.0628 (0.0747) loss: 0.8556 (0.8561) time: 0.1352 data: 0.0581 max mem: 9394 +Train: [8] [4600/6250] eta: 0:03:58 lr: 0.000125 grad: 0.0890 (0.0749) loss: 0.8469 (0.8560) time: 0.1061 data: 0.0246 max mem: 9394 +Train: [8] [4700/6250] eta: 0:03:43 lr: 0.000125 grad: 0.0670 (0.0748) loss: 0.8570 (0.8559) time: 0.1253 data: 0.0447 max mem: 9394 +Train: [8] [4800/6250] eta: 0:03:28 lr: 0.000125 grad: 0.0721 (0.0747) loss: 0.8546 (0.8558) time: 0.1316 data: 0.0520 max mem: 9394 +Train: [8] [4900/6250] eta: 0:03:14 lr: 0.000125 grad: 0.0642 (0.0746) loss: 0.8554 (0.8558) time: 0.1138 data: 0.0311 max mem: 9394 +Train: [8] [5000/6250] eta: 0:02:59 lr: 0.000125 grad: 0.0753 (0.0746) loss: 0.8506 (0.8557) time: 0.1397 data: 0.0617 max mem: 9394 +Train: [8] [5100/6250] eta: 0:02:45 lr: 0.000125 grad: 0.0699 (0.0746) loss: 0.8557 (0.8557) time: 0.1362 data: 0.0585 max mem: 9394 +Train: [8] [5200/6250] eta: 0:02:30 lr: 0.000124 grad: 0.0771 (0.0745) loss: 0.8545 (0.8556) time: 0.1281 data: 0.0517 max mem: 9394 +Train: [8] [5300/6250] eta: 0:02:16 lr: 0.000124 grad: 0.0649 (0.0745) loss: 0.8518 (0.8556) time: 0.1155 data: 0.0330 max mem: 9394 +Train: [8] [5400/6250] eta: 0:02:01 lr: 0.000124 grad: 0.0673 (0.0744) loss: 0.8537 (0.8556) time: 0.1195 data: 0.0359 max mem: 9394 +Train: [8] [5500/6250] eta: 0:01:47 lr: 0.000124 grad: 0.0675 (0.0744) loss: 0.8496 (0.8555) time: 0.1305 data: 0.0513 max mem: 9394 +Train: [8] [5600/6250] eta: 0:01:33 lr: 0.000124 grad: 0.0706 (0.0744) loss: 0.8497 (0.8554) time: 0.1255 data: 0.0389 max mem: 9394 +Train: [8] [5700/6250] eta: 0:01:18 lr: 0.000124 grad: 0.0651 (0.0743) loss: 0.8515 (0.8553) time: 0.1984 data: 0.0882 max mem: 9394 +Train: [8] [5800/6250] eta: 0:01:04 lr: 0.000124 grad: 0.0698 (0.0743) loss: 0.8481 (0.8552) time: 0.1315 data: 0.0523 max mem: 9394 +Train: [8] [5900/6250] eta: 0:00:50 lr: 0.000124 grad: 0.0706 (0.0743) loss: 0.8522 (0.8551) time: 0.1347 data: 0.0570 max mem: 9394 +Train: [8] [6000/6250] eta: 0:00:35 lr: 0.000124 grad: 0.0727 (0.0743) loss: 0.8474 (0.8551) time: 0.1250 data: 0.0477 max mem: 9394 +Train: [8] [6100/6250] eta: 0:00:21 lr: 0.000124 grad: 0.0708 (0.0743) loss: 0.8554 (0.8550) time: 0.1308 data: 0.0517 max mem: 9394 +Train: [8] [6200/6250] eta: 0:00:07 lr: 0.000124 grad: 0.0706 (0.0743) loss: 0.8510 (0.8550) time: 0.1208 data: 0.0439 max mem: 9394 +Train: [8] [6249/6250] eta: 0:00:00 lr: 0.000124 grad: 0.0704 (0.0743) loss: 0.8565 (0.8550) time: 0.1519 data: 0.0753 max mem: 9394 +Train: [8] Total time: 0:14:58 (0.1437 s / it) +Averaged stats: lr: 0.000124 grad: 0.0704 (0.0743) loss: 0.8565 (0.8550) +Eval (hcp-train-subset): [8] [ 0/62] eta: 0:05:37 loss: 0.8685 (0.8685) time: 5.4483 data: 5.4171 max mem: 9394 +Eval (hcp-train-subset): [8] [61/62] eta: 0:00:00 loss: 0.8580 (0.8586) time: 0.1949 data: 0.1699 max mem: 9394 +Eval (hcp-train-subset): [8] Total time: 0:00:14 (0.2414 s / it) +Averaged stats (hcp-train-subset): loss: 0.8580 (0.8586) +Eval (hcp-val): [8] [ 0/62] eta: 0:05:02 loss: 0.8474 (0.8474) time: 4.8856 data: 4.8555 max mem: 9394 +Eval (hcp-val): [8] [61/62] eta: 0:00:00 loss: 0.8522 (0.8529) time: 0.1068 data: 0.0804 max mem: 9394 +Eval (hcp-val): [8] Total time: 0:00:13 (0.2116 s / it) +Averaged stats (hcp-val): loss: 0.8522 (0.8529) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +Train: [9] [ 0/6250] eta: 9:57:34 lr: 0.000124 grad: 0.0446 (0.0446) loss: 0.8896 (0.8896) time: 5.7367 data: 5.6280 max mem: 9394 +Train: [9] [ 100/6250] eta: 0:20:38 lr: 0.000124 grad: 0.0645 (0.0737) loss: 0.8610 (0.8661) time: 0.1742 data: 0.0924 max mem: 9394 +Train: [9] [ 200/6250] eta: 0:17:13 lr: 0.000124 grad: 0.0675 (0.0738) loss: 0.8482 (0.8598) time: 0.1389 data: 0.0566 max mem: 9394 +Train: [9] [ 300/6250] eta: 0:15:45 lr: 0.000124 grad: 0.0666 (0.0743) loss: 0.8498 (0.8557) time: 0.1263 data: 0.0415 max mem: 9394 +Train: [9] [ 400/6250] eta: 0:14:40 lr: 0.000124 grad: 0.0699 (0.0746) loss: 0.8494 (0.8537) time: 0.1242 data: 0.0379 max mem: 9394 +Train: [9] [ 500/6250] eta: 0:13:56 lr: 0.000124 grad: 0.0750 (0.0740) loss: 0.8499 (0.8529) time: 0.1043 data: 0.0210 max mem: 9394 +Train: [9] [ 600/6250] eta: 0:13:24 lr: 0.000124 grad: 0.0702 (0.0745) loss: 0.8527 (0.8530) time: 0.1199 data: 0.0296 max mem: 9394 +Train: [9] [ 700/6250] eta: 0:12:57 lr: 0.000124 grad: 0.0674 (0.0736) loss: 0.8495 (0.8531) time: 0.1382 data: 0.0510 max mem: 9394 +Train: [9] [ 800/6250] eta: 0:13:09 lr: 0.000124 grad: 0.0705 (0.0739) loss: 0.8523 (0.8531) time: 0.2697 data: 0.1952 max mem: 9394 +Train: [9] [ 900/6250] eta: 0:13:06 lr: 0.000124 grad: 0.0706 (0.0735) loss: 0.8503 (0.8532) time: 0.1846 data: 0.1013 max mem: 9394 +Train: [9] [1000/6250] eta: 0:12:59 lr: 0.000124 grad: 0.0686 (0.0729) loss: 0.8488 (0.8532) time: 0.1515 data: 0.0665 max mem: 9394 +Train: [9] [1100/6250] eta: 0:12:50 lr: 0.000124 grad: 0.0654 (0.0725) loss: 0.8509 (0.8530) time: 0.1574 data: 0.0837 max mem: 9394 +Train: [9] [1200/6250] eta: 0:12:32 lr: 0.000124 grad: 0.0679 (0.0722) loss: 0.8502 (0.8529) time: 0.1517 data: 0.0604 max mem: 9394 +Train: [9] [1300/6250] eta: 0:12:14 lr: 0.000124 grad: 0.0699 (0.0719) loss: 0.8512 (0.8528) time: 0.1372 data: 0.0536 max mem: 9394 +Train: [9] [1400/6250] eta: 0:11:57 lr: 0.000124 grad: 0.0680 (0.0717) loss: 0.8484 (0.8529) time: 0.1415 data: 0.0586 max mem: 9394 +Train: [9] [1500/6250] eta: 0:11:42 lr: 0.000124 grad: 0.0642 (0.0720) loss: 0.8536 (0.8531) time: 0.1375 data: 0.0568 max mem: 9394 +Train: [9] [1600/6250] eta: 0:11:32 lr: 0.000124 grad: 0.0684 (0.0719) loss: 0.8544 (0.8531) time: 0.1675 data: 0.0866 max mem: 9394 +Train: [9] [1700/6250] eta: 0:11:20 lr: 0.000124 grad: 0.0660 (0.0716) loss: 0.8590 (0.8533) time: 0.1166 data: 0.0288 max mem: 9394 +Train: [9] [1800/6250] eta: 0:11:09 lr: 0.000124 grad: 0.0640 (0.0714) loss: 0.8572 (0.8535) time: 0.1025 data: 0.0003 max mem: 9394 +Train: [9] [1900/6250] eta: 0:10:52 lr: 0.000124 grad: 0.0633 (0.0712) loss: 0.8552 (0.8535) time: 0.1493 data: 0.0703 max mem: 9394 +Train: [9] [2000/6250] eta: 0:10:43 lr: 0.000124 grad: 0.0632 (0.0711) loss: 0.8548 (0.8535) time: 0.0926 data: 0.0002 max mem: 9394 +Train: [9] [2100/6250] eta: 0:10:31 lr: 0.000124 grad: 0.0685 (0.0709) loss: 0.8562 (0.8535) time: 0.1622 data: 0.0742 max mem: 9394 +Train: [9] [2200/6250] eta: 0:10:11 lr: 0.000124 grad: 0.0640 (0.0708) loss: 0.8473 (0.8535) time: 0.1469 data: 0.0708 max mem: 9394 +Train: [9] [2300/6250] eta: 0:09:57 lr: 0.000124 grad: 0.0620 (0.0706) loss: 0.8520 (0.8534) time: 0.1950 data: 0.0897 max mem: 9394 +Train: [9] [2400/6250] eta: 0:09:40 lr: 0.000124 grad: 0.0659 (0.0704) loss: 0.8501 (0.8534) time: 0.1446 data: 0.0668 max mem: 9394 +Train: [9] [2500/6250] eta: 0:09:27 lr: 0.000124 grad: 0.0646 (0.0703) loss: 0.8464 (0.8534) time: 0.1319 data: 0.0531 max mem: 9394 +Train: [9] [2600/6250] eta: 0:09:10 lr: 0.000124 grad: 0.0682 (0.0703) loss: 0.8515 (0.8533) time: 0.1462 data: 0.0672 max mem: 9394 +Train: [9] [2700/6250] eta: 0:08:53 lr: 0.000124 grad: 0.0663 (0.0704) loss: 0.8521 (0.8532) time: 0.1298 data: 0.0536 max mem: 9394 +Train: [9] [2800/6250] eta: 0:08:38 lr: 0.000124 grad: 0.0631 (0.0704) loss: 0.8490 (0.8531) time: 0.1266 data: 0.0485 max mem: 9394 +Train: [9] [2900/6250] eta: 0:08:22 lr: 0.000124 grad: 0.0657 (0.0703) loss: 0.8475 (0.8530) time: 0.1204 data: 0.0469 max mem: 9394 +Train: [9] [3000/6250] eta: 0:08:07 lr: 0.000124 grad: 0.0640 (0.0706) loss: 0.8405 (0.8528) time: 0.1809 data: 0.1060 max mem: 9394 +Train: [9] [3100/6250] eta: 0:07:51 lr: 0.000124 grad: 0.0754 (0.0705) loss: 0.8495 (0.8528) time: 0.0980 data: 0.0137 max mem: 9394 +Train: [9] [3200/6250] eta: 0:07:36 lr: 0.000124 grad: 0.0737 (0.0704) loss: 0.8474 (0.8527) time: 0.1264 data: 0.0387 max mem: 9394 +Train: [9] [3300/6250] eta: 0:07:20 lr: 0.000124 grad: 0.0686 (0.0704) loss: 0.8481 (0.8526) time: 0.1371 data: 0.0514 max mem: 9394 +Train: [9] [3400/6250] eta: 0:07:04 lr: 0.000124 grad: 0.0658 (0.0703) loss: 0.8464 (0.8525) time: 0.1053 data: 0.0260 max mem: 9394 +Train: [9] [3500/6250] eta: 0:06:50 lr: 0.000124 grad: 0.0637 (0.0703) loss: 0.8485 (0.8524) time: 0.1020 data: 0.0207 max mem: 9394 +Train: [9] [3600/6250] eta: 0:06:33 lr: 0.000124 grad: 0.0680 (0.0703) loss: 0.8439 (0.8523) time: 0.1364 data: 0.0572 max mem: 9394 +Train: [9] [3700/6250] eta: 0:06:17 lr: 0.000124 grad: 0.0699 (0.0703) loss: 0.8467 (0.8521) time: 0.1390 data: 0.0574 max mem: 9394 +Train: [9] [3800/6250] eta: 0:06:02 lr: 0.000124 grad: 0.0631 (0.0703) loss: 0.8467 (0.8520) time: 0.1807 data: 0.0976 max mem: 9394 +Train: [9] [3900/6250] eta: 0:05:47 lr: 0.000124 grad: 0.0682 (0.0703) loss: 0.8467 (0.8519) time: 0.1561 data: 0.0797 max mem: 9394 +Train: [9] [4000/6250] eta: 0:05:31 lr: 0.000124 grad: 0.0664 (0.0703) loss: 0.8459 (0.8518) time: 0.1148 data: 0.0351 max mem: 9394 +Train: [9] [4100/6250] eta: 0:05:15 lr: 0.000124 grad: 0.0666 (0.0702) loss: 0.8476 (0.8518) time: 0.1312 data: 0.0521 max mem: 9394 +Train: [9] [4200/6250] eta: 0:05:00 lr: 0.000124 grad: 0.0699 (0.0702) loss: 0.8424 (0.8517) time: 0.1296 data: 0.0509 max mem: 9394 +Train: [9] [4300/6250] eta: 0:04:44 lr: 0.000124 grad: 0.0658 (0.0701) loss: 0.8478 (0.8517) time: 0.1385 data: 0.0573 max mem: 9394 +Train: [9] [4400/6250] eta: 0:04:29 lr: 0.000124 grad: 0.0679 (0.0701) loss: 0.8522 (0.8517) time: 0.1020 data: 0.0187 max mem: 9394 +Train: [9] [4500/6250] eta: 0:04:14 lr: 0.000124 grad: 0.0645 (0.0701) loss: 0.8491 (0.8516) time: 0.1505 data: 0.0716 max mem: 9394 +Train: [9] [4600/6250] eta: 0:03:59 lr: 0.000124 grad: 0.0661 (0.0702) loss: 0.8555 (0.8516) time: 0.1235 data: 0.0446 max mem: 9394 +Train: [9] [4700/6250] eta: 0:03:45 lr: 0.000124 grad: 0.0658 (0.0701) loss: 0.8551 (0.8516) time: 0.2656 data: 0.1343 max mem: 9394 +Train: [9] [4800/6250] eta: 0:03:30 lr: 0.000124 grad: 0.0655 (0.0701) loss: 0.8535 (0.8517) time: 0.1392 data: 0.0526 max mem: 9394 +Train: [9] [4900/6250] eta: 0:03:16 lr: 0.000124 grad: 0.0642 (0.0700) loss: 0.8535 (0.8517) time: 0.1323 data: 0.0364 max mem: 9394 +Train: [9] [5000/6250] eta: 0:03:02 lr: 0.000124 grad: 0.0666 (0.0700) loss: 0.8516 (0.8517) time: 0.1909 data: 0.1128 max mem: 9394 +Train: [9] [5100/6250] eta: 0:02:47 lr: 0.000124 grad: 0.0720 (0.0701) loss: 0.8514 (0.8517) time: 0.1353 data: 0.0515 max mem: 9394 +Train: [9] [5200/6250] eta: 0:02:32 lr: 0.000124 grad: 0.0661 (0.0700) loss: 0.8471 (0.8517) time: 0.1429 data: 0.0690 max mem: 9394 +Train: [9] [5300/6250] eta: 0:02:17 lr: 0.000124 grad: 0.0660 (0.0699) loss: 0.8472 (0.8517) time: 0.1452 data: 0.0634 max mem: 9394 +Train: [9] [5400/6250] eta: 0:02:03 lr: 0.000124 grad: 0.0690 (0.0699) loss: 0.8524 (0.8516) time: 0.1348 data: 0.0526 max mem: 9394 +Train: [9] [5500/6250] eta: 0:01:48 lr: 0.000124 grad: 0.0658 (0.0701) loss: 0.8518 (0.8516) time: 0.1440 data: 0.0641 max mem: 9394 +Train: [9] [5600/6250] eta: 0:01:33 lr: 0.000124 grad: 0.0665 (0.0700) loss: 0.8507 (0.8516) time: 0.1284 data: 0.0480 max mem: 9394 +Train: [9] [5700/6250] eta: 0:01:19 lr: 0.000124 grad: 0.0632 (0.0700) loss: 0.8510 (0.8516) time: 0.1301 data: 0.0530 max mem: 9394 +Train: [9] [5800/6250] eta: 0:01:05 lr: 0.000124 grad: 0.0669 (0.0699) loss: 0.8552 (0.8516) time: 0.1581 data: 0.0699 max mem: 9394 +Train: [9] [5900/6250] eta: 0:00:50 lr: 0.000124 grad: 0.0661 (0.0699) loss: 0.8459 (0.8516) time: 0.1438 data: 0.0613 max mem: 9394 +Train: [9] [6000/6250] eta: 0:00:36 lr: 0.000124 grad: 0.0646 (0.0699) loss: 0.8543 (0.8516) time: 0.1414 data: 0.0638 max mem: 9394 +Train: [9] [6100/6250] eta: 0:00:21 lr: 0.000124 grad: 0.0652 (0.0698) loss: 0.8508 (0.8515) time: 0.1499 data: 0.0671 max mem: 9394 +Train: [9] [6200/6250] eta: 0:00:07 lr: 0.000124 grad: 0.0678 (0.0699) loss: 0.8539 (0.8515) time: 0.1437 data: 0.0665 max mem: 9394 +Train: [9] [6249/6250] eta: 0:00:00 lr: 0.000124 grad: 0.0670 (0.0699) loss: 0.8526 (0.8515) time: 0.1205 data: 0.0396 max mem: 9394 +Train: [9] Total time: 0:15:06 (0.1451 s / it) +Averaged stats: lr: 0.000124 grad: 0.0670 (0.0699) loss: 0.8526 (0.8515) +Eval (hcp-train-subset): [9] [ 0/62] eta: 0:05:06 loss: 0.8652 (0.8652) time: 4.9392 data: 4.9102 max mem: 9394 +Eval (hcp-train-subset): [9] [61/62] eta: 0:00:00 loss: 0.8559 (0.8552) time: 0.1539 data: 0.1287 max mem: 9394 +Eval (hcp-train-subset): [9] Total time: 0:00:13 (0.2222 s / it) +Averaged stats (hcp-train-subset): loss: 0.8559 (0.8552) +Making plots (hcp-train-subset): example=29 +Eval (hcp-val): [9] [ 0/62] eta: 0:05:42 loss: 0.8441 (0.8441) time: 5.5180 data: 5.4827 max mem: 9394 +Eval (hcp-val): [9] [61/62] eta: 0:00:00 loss: 0.8503 (0.8504) time: 0.1449 data: 0.1199 max mem: 9394 +Eval (hcp-val): [9] Total time: 0:00:13 (0.2252 s / it) +Averaged stats (hcp-val): loss: 0.8503 (0.8504) +Making plots (hcp-val): example=3 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +Train: [10] [ 0/6250] eta: 10:09:55 lr: 0.000124 grad: 0.0848 (0.0848) loss: 0.8532 (0.8532) time: 5.8553 data: 5.7671 max mem: 9394 +Train: [10] [ 100/6250] eta: 0:21:08 lr: 0.000124 grad: 0.0618 (0.0666) loss: 0.8538 (0.8589) time: 0.1722 data: 0.0923 max mem: 9394 +Train: [10] [ 200/6250] eta: 0:17:49 lr: 0.000124 grad: 0.0671 (0.0697) loss: 0.8529 (0.8571) time: 0.1697 data: 0.0925 max mem: 9394 +Train: [10] [ 300/6250] eta: 0:16:10 lr: 0.000124 grad: 0.0622 (0.0691) loss: 0.8582 (0.8561) time: 0.1484 data: 0.0514 max mem: 9394 +Train: [10] [ 400/6250] eta: 0:15:06 lr: 0.000124 grad: 0.0665 (0.0685) loss: 0.8477 (0.8545) time: 0.1395 data: 0.0628 max mem: 9394 +Train: [10] [ 500/6250] eta: 0:14:14 lr: 0.000124 grad: 0.0670 (0.0687) loss: 0.8449 (0.8531) time: 0.1125 data: 0.0270 max mem: 9394 +Train: [10] [ 600/6250] eta: 0:13:40 lr: 0.000124 grad: 0.0663 (0.0685) loss: 0.8486 (0.8526) time: 0.1379 data: 0.0524 max mem: 9394 +Train: [10] [ 700/6250] eta: 0:13:09 lr: 0.000124 grad: 0.0708 (0.0688) loss: 0.8487 (0.8524) time: 0.1085 data: 0.0246 max mem: 9394 +Train: [10] [ 800/6250] eta: 0:12:56 lr: 0.000124 grad: 0.0635 (0.0685) loss: 0.8535 (0.8524) time: 0.1411 data: 0.0556 max mem: 9394 +Train: [10] [ 900/6250] eta: 0:13:12 lr: 0.000124 grad: 0.0659 (0.0680) loss: 0.8458 (0.8524) time: 0.2592 data: 0.1800 max mem: 9394 +Train: [10] [1000/6250] eta: 0:13:05 lr: 0.000124 grad: 0.0691 (0.0681) loss: 0.8558 (0.8522) time: 0.1621 data: 0.0835 max mem: 9394 +Train: [10] [1100/6250] eta: 0:12:57 lr: 0.000124 grad: 0.0643 (0.0681) loss: 0.8466 (0.8519) time: 0.1592 data: 0.0784 max mem: 9394 +Train: [10] [1200/6250] eta: 0:12:44 lr: 0.000124 grad: 0.0722 (0.0681) loss: 0.8469 (0.8516) time: 0.1423 data: 0.0684 max mem: 9394 +Train: [10] [1300/6250] eta: 0:12:30 lr: 0.000124 grad: 0.0629 (0.0680) loss: 0.8519 (0.8514) time: 0.1716 data: 0.0879 max mem: 9394 +Train: [10] [1400/6250] eta: 0:12:10 lr: 0.000124 grad: 0.0639 (0.0678) loss: 0.8469 (0.8513) time: 0.1390 data: 0.0562 max mem: 9394 +Train: [10] [1500/6250] eta: 0:11:53 lr: 0.000124 grad: 0.0704 (0.0682) loss: 0.8474 (0.8511) time: 0.1362 data: 0.0538 max mem: 9394 +Train: [10] [1600/6250] eta: 0:11:37 lr: 0.000124 grad: 0.0666 (0.0682) loss: 0.8514 (0.8508) time: 0.1067 data: 0.0247 max mem: 9394 +Train: [10] [1700/6250] eta: 0:11:32 lr: 0.000124 grad: 0.0638 (0.0681) loss: 0.8476 (0.8508) time: 0.0978 data: 0.0003 max mem: 9394 +Train: [10] [1800/6250] eta: 0:11:21 lr: 0.000124 grad: 0.0609 (0.0679) loss: 0.8503 (0.8507) time: 0.1522 data: 0.0692 max mem: 9394 +Train: [10] [1900/6250] eta: 0:11:11 lr: 0.000124 grad: 0.0633 (0.0680) loss: 0.8536 (0.8506) time: 0.1009 data: 0.0129 max mem: 9394 +Train: [10] [2000/6250] eta: 0:10:55 lr: 0.000124 grad: 0.0662 (0.0679) loss: 0.8523 (0.8505) time: 0.1318 data: 0.0452 max mem: 9394 +Train: [10] [2100/6250] eta: 0:10:38 lr: 0.000124 grad: 0.0659 (0.0679) loss: 0.8428 (0.8504) time: 0.1674 data: 0.0807 max mem: 9394 +Train: [10] [2200/6250] eta: 0:10:26 lr: 0.000124 grad: 0.0650 (0.0678) loss: 0.8494 (0.8503) time: 0.1258 data: 0.0401 max mem: 9394 +Train: [10] [2300/6250] eta: 0:10:08 lr: 0.000124 grad: 0.0609 (0.0677) loss: 0.8484 (0.8503) time: 0.1271 data: 0.0354 max mem: 9394 +Train: [10] [2400/6250] eta: 0:09:52 lr: 0.000124 grad: 0.0599 (0.0675) loss: 0.8570 (0.8503) time: 0.1315 data: 0.0484 max mem: 9394 +Train: [10] [2500/6250] eta: 0:09:37 lr: 0.000124 grad: 0.0582 (0.0674) loss: 0.8483 (0.8503) time: 0.1145 data: 0.0240 max mem: 9394 +Train: [10] [2600/6250] eta: 0:09:27 lr: 0.000124 grad: 0.0608 (0.0673) loss: 0.8518 (0.8504) time: 0.3596 data: 0.2491 max mem: 9394 +Train: [10] [2700/6250] eta: 0:09:07 lr: 0.000124 grad: 0.0633 (0.0673) loss: 0.8483 (0.8504) time: 0.1307 data: 0.0511 max mem: 9394 +Train: [10] [2800/6250] eta: 0:08:51 lr: 0.000124 grad: 0.0646 (0.0672) loss: 0.8540 (0.8505) time: 0.1179 data: 0.0328 max mem: 9394 +Train: [10] [2900/6250] eta: 0:08:37 lr: 0.000124 grad: 0.0644 (0.0671) loss: 0.8526 (0.8505) time: 0.1310 data: 0.0323 max mem: 9394 +Train: [10] [3000/6250] eta: 0:08:20 lr: 0.000124 grad: 0.0639 (0.0670) loss: 0.8494 (0.8505) time: 0.1417 data: 0.0596 max mem: 9394 +Train: [10] [3100/6250] eta: 0:08:09 lr: 0.000124 grad: 0.0627 (0.0670) loss: 0.8475 (0.8505) time: 0.1009 data: 0.0004 max mem: 9394 +Train: [10] [3200/6250] eta: 0:07:52 lr: 0.000124 grad: 0.0648 (0.0670) loss: 0.8497 (0.8505) time: 0.1262 data: 0.0484 max mem: 9394 +Train: [10] [3300/6250] eta: 0:07:37 lr: 0.000124 grad: 0.0616 (0.0669) loss: 0.8487 (0.8504) time: 0.2112 data: 0.0893 max mem: 9394 +Train: [10] [3400/6250] eta: 0:07:19 lr: 0.000124 grad: 0.0649 (0.0670) loss: 0.8512 (0.8504) time: 0.1187 data: 0.0391 max mem: 9394 +Train: [10] [3500/6250] eta: 0:07:02 lr: 0.000124 grad: 0.0643 (0.0670) loss: 0.8477 (0.8503) time: 0.1261 data: 0.0476 max mem: 9394 +Train: [10] [3600/6250] eta: 0:06:45 lr: 0.000124 grad: 0.0635 (0.0669) loss: 0.8465 (0.8503) time: 0.1357 data: 0.0568 max mem: 9394 +Train: [10] [3700/6250] eta: 0:06:28 lr: 0.000124 grad: 0.0616 (0.0669) loss: 0.8541 (0.8503) time: 0.1212 data: 0.0381 max mem: 9394 +Train: [10] [3800/6250] eta: 0:06:13 lr: 0.000124 grad: 0.0598 (0.0668) loss: 0.8488 (0.8503) time: 0.0908 data: 0.0044 max mem: 9394 +Train: [10] [3900/6250] eta: 0:05:56 lr: 0.000124 grad: 0.0665 (0.0668) loss: 0.8467 (0.8503) time: 0.1250 data: 0.0440 max mem: 9394 +Train: [10] [4000/6250] eta: 0:05:41 lr: 0.000124 grad: 0.0672 (0.0668) loss: 0.8540 (0.8503) time: 0.1333 data: 0.0335 max mem: 9394 +Train: [10] [4100/6250] eta: 0:05:25 lr: 0.000124 grad: 0.0626 (0.0667) loss: 0.8500 (0.8503) time: 0.1292 data: 0.0460 max mem: 9394 +Train: [10] [4200/6250] eta: 0:05:09 lr: 0.000124 grad: 0.0645 (0.0667) loss: 0.8480 (0.8503) time: 0.1481 data: 0.0722 max mem: 9394 +Train: [10] [4300/6250] eta: 0:04:53 lr: 0.000124 grad: 0.0636 (0.0667) loss: 0.8484 (0.8503) time: 0.1334 data: 0.0573 max mem: 9394 +Train: [10] [4400/6250] eta: 0:04:37 lr: 0.000124 grad: 0.0629 (0.0667) loss: 0.8498 (0.8503) time: 0.1432 data: 0.0712 max mem: 9394 +Train: [10] [4500/6250] eta: 0:04:21 lr: 0.000124 grad: 0.0636 (0.0668) loss: 0.8488 (0.8503) time: 0.1312 data: 0.0514 max mem: 9394 +Train: [10] [4600/6250] eta: 0:04:06 lr: 0.000124 grad: 0.0611 (0.0667) loss: 0.8547 (0.8503) time: 0.1289 data: 0.0453 max mem: 9394 +Train: [10] [4700/6250] eta: 0:03:50 lr: 0.000124 grad: 0.0609 (0.0667) loss: 0.8493 (0.8503) time: 0.1185 data: 0.0370 max mem: 9394 +Train: [10] [4800/6250] eta: 0:03:35 lr: 0.000124 grad: 0.0613 (0.0667) loss: 0.8536 (0.8503) time: 0.1263 data: 0.0422 max mem: 9394 +Train: [10] [4900/6250] eta: 0:03:19 lr: 0.000124 grad: 0.0644 (0.0667) loss: 0.8516 (0.8503) time: 0.1361 data: 0.0559 max mem: 9394 +Train: [10] [5000/6250] eta: 0:03:05 lr: 0.000124 grad: 0.0632 (0.0667) loss: 0.8507 (0.8503) time: 0.1201 data: 0.0426 max mem: 9394 +Train: [10] [5100/6250] eta: 0:02:50 lr: 0.000124 grad: 0.0607 (0.0666) loss: 0.8518 (0.8503) time: 0.1279 data: 0.0441 max mem: 9394 +Train: [10] [5200/6250] eta: 0:02:35 lr: 0.000124 grad: 0.0645 (0.0666) loss: 0.8493 (0.8502) time: 0.1297 data: 0.0515 max mem: 9394 +Train: [10] [5300/6250] eta: 0:02:20 lr: 0.000124 grad: 0.0665 (0.0666) loss: 0.8482 (0.8502) time: 0.1263 data: 0.0510 max mem: 9394 +Train: [10] [5400/6250] eta: 0:02:05 lr: 0.000124 grad: 0.0642 (0.0666) loss: 0.8481 (0.8502) time: 0.1606 data: 0.0779 max mem: 9394 +Train: [10] [5500/6250] eta: 0:01:50 lr: 0.000124 grad: 0.0592 (0.0665) loss: 0.8499 (0.8502) time: 0.1432 data: 0.0619 max mem: 9394 +Train: [10] [5600/6250] eta: 0:01:35 lr: 0.000124 grad: 0.0617 (0.0665) loss: 0.8470 (0.8501) time: 0.1383 data: 0.0597 max mem: 9394 +Train: [10] [5700/6250] eta: 0:01:20 lr: 0.000124 grad: 0.0666 (0.0665) loss: 0.8473 (0.8501) time: 0.1314 data: 0.0558 max mem: 9394 +Train: [10] [5800/6250] eta: 0:01:06 lr: 0.000124 grad: 0.0657 (0.0665) loss: 0.8507 (0.8500) time: 0.1240 data: 0.0460 max mem: 9394 +Train: [10] [5900/6250] eta: 0:00:51 lr: 0.000124 grad: 0.0641 (0.0664) loss: 0.8481 (0.8500) time: 0.1326 data: 0.0506 max mem: 9394 +Train: [10] [6000/6250] eta: 0:00:36 lr: 0.000124 grad: 0.0644 (0.0665) loss: 0.8492 (0.8500) time: 0.1301 data: 0.0543 max mem: 9394 +Train: [10] [6100/6250] eta: 0:00:21 lr: 0.000124 grad: 0.0637 (0.0664) loss: 0.8505 (0.8500) time: 0.1080 data: 0.0201 max mem: 9394 +Train: [10] [6200/6250] eta: 0:00:07 lr: 0.000124 grad: 0.0659 (0.0664) loss: 0.8447 (0.8499) time: 0.1471 data: 0.0698 max mem: 9394 +Train: [10] [6249/6250] eta: 0:00:00 lr: 0.000124 grad: 0.0639 (0.0664) loss: 0.8470 (0.8499) time: 0.1553 data: 0.0773 max mem: 9394 +Train: [10] Total time: 0:15:19 (0.1472 s / it) +Averaged stats: lr: 0.000124 grad: 0.0639 (0.0664) loss: 0.8470 (0.8499) +Eval (hcp-train-subset): [10] [ 0/62] eta: 0:05:55 loss: 0.8631 (0.8631) time: 5.7339 data: 5.7029 max mem: 9394 +Eval (hcp-train-subset): [10] [61/62] eta: 0:00:00 loss: 0.8547 (0.8541) time: 0.1735 data: 0.1487 max mem: 9394 +Eval (hcp-train-subset): [10] Total time: 0:00:14 (0.2376 s / it) +Averaged stats (hcp-train-subset): loss: 0.8547 (0.8541) +Eval (hcp-val): [10] [ 0/62] eta: 0:05:52 loss: 0.8451 (0.8451) time: 5.6811 data: 5.6327 max mem: 9394 +Eval (hcp-val): [10] [61/62] eta: 0:00:00 loss: 0.8482 (0.8486) time: 0.1088 data: 0.0819 max mem: 9394 +Eval (hcp-val): [10] Total time: 0:00:12 (0.2097 s / it) +Averaged stats (hcp-val): loss: 0.8482 (0.8486) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +Train: [11] [ 0/6250] eta: 9:47:43 lr: 0.000124 grad: 0.0793 (0.0793) loss: 0.8352 (0.8352) time: 5.6422 data: 5.5239 max mem: 9394 +Train: [11] [ 100/6250] eta: 0:20:17 lr: 0.000124 grad: 0.0627 (0.0758) loss: 0.8476 (0.8500) time: 0.1723 data: 0.0873 max mem: 9394 +Train: [11] [ 200/6250] eta: 0:17:29 lr: 0.000124 grad: 0.0708 (0.0763) loss: 0.8424 (0.8471) time: 0.1536 data: 0.0680 max mem: 9394 +Train: [11] [ 300/6250] eta: 0:16:06 lr: 0.000124 grad: 0.0722 (0.0739) loss: 0.8459 (0.8477) time: 0.1237 data: 0.0330 max mem: 9394 +Train: [11] [ 400/6250] eta: 0:15:11 lr: 0.000124 grad: 0.0669 (0.0727) loss: 0.8394 (0.8474) time: 0.1407 data: 0.0611 max mem: 9394 +Train: [11] [ 500/6250] eta: 0:14:25 lr: 0.000124 grad: 0.0643 (0.0713) loss: 0.8472 (0.8471) time: 0.1237 data: 0.0370 max mem: 9394 +Train: [11] [ 600/6250] eta: 0:13:49 lr: 0.000124 grad: 0.0644 (0.0704) loss: 0.8515 (0.8475) time: 0.1228 data: 0.0386 max mem: 9394 +Train: [11] [ 700/6250] eta: 0:13:22 lr: 0.000124 grad: 0.0625 (0.0698) loss: 0.8484 (0.8478) time: 0.1284 data: 0.0421 max mem: 9394 +Train: [11] [ 800/6250] eta: 0:13:16 lr: 0.000124 grad: 0.0656 (0.0693) loss: 0.8495 (0.8479) time: 0.1903 data: 0.1110 max mem: 9394 +Train: [11] [ 900/6250] eta: 0:13:11 lr: 0.000124 grad: 0.0610 (0.0688) loss: 0.8488 (0.8483) time: 0.1666 data: 0.0838 max mem: 9394 +Train: [11] [1000/6250] eta: 0:13:07 lr: 0.000124 grad: 0.0627 (0.0683) loss: 0.8513 (0.8487) time: 0.1842 data: 0.1030 max mem: 9394 +Train: [11] [1100/6250] eta: 0:12:56 lr: 0.000124 grad: 0.0622 (0.0679) loss: 0.8497 (0.8490) time: 0.1486 data: 0.0679 max mem: 9394 +Train: [11] [1200/6250] eta: 0:12:50 lr: 0.000124 grad: 0.0626 (0.0677) loss: 0.8546 (0.8493) time: 0.1297 data: 0.0485 max mem: 9394 +Train: [11] [1300/6250] eta: 0:12:35 lr: 0.000124 grad: 0.0619 (0.0674) loss: 0.8536 (0.8495) time: 0.1554 data: 0.0763 max mem: 9394 +Train: [11] [1400/6250] eta: 0:12:22 lr: 0.000124 grad: 0.0618 (0.0670) loss: 0.8561 (0.8497) time: 0.1555 data: 0.0791 max mem: 9394 +Train: [11] [1500/6250] eta: 0:12:10 lr: 0.000124 grad: 0.0676 (0.0670) loss: 0.8526 (0.8499) time: 0.1487 data: 0.0551 max mem: 9394 +Train: [11] [1600/6250] eta: 0:11:54 lr: 0.000124 grad: 0.0598 (0.0668) loss: 0.8554 (0.8500) time: 0.1385 data: 0.0556 max mem: 9394 +Train: [11] [1700/6250] eta: 0:11:36 lr: 0.000124 grad: 0.0596 (0.0665) loss: 0.8496 (0.8501) time: 0.1433 data: 0.0652 max mem: 9394 +Train: [11] [1800/6250] eta: 0:11:34 lr: 0.000124 grad: 0.0628 (0.0664) loss: 0.8463 (0.8502) time: 0.2037 data: 0.0596 max mem: 9394 +Train: [11] [1900/6250] eta: 0:11:34 lr: 0.000124 grad: 0.0645 (0.0662) loss: 0.8531 (0.8503) time: 0.2581 data: 0.1525 max mem: 9394 +Train: [11] [2000/6250] eta: 0:11:25 lr: 0.000124 grad: 0.0594 (0.0661) loss: 0.8486 (0.8503) time: 0.1051 data: 0.0002 max mem: 9394 +Train: [11] [2100/6250] eta: 0:11:06 lr: 0.000124 grad: 0.0628 (0.0660) loss: 0.8520 (0.8502) time: 0.1287 data: 0.0417 max mem: 9394 +Train: [11] [2200/6250] eta: 0:10:58 lr: 0.000124 grad: 0.0620 (0.0659) loss: 0.8501 (0.8502) time: 0.0903 data: 0.0003 max mem: 9394 +Train: [11] [2300/6250] eta: 0:10:37 lr: 0.000124 grad: 0.0635 (0.0659) loss: 0.8463 (0.8501) time: 0.1446 data: 0.0654 max mem: 9394 +Train: [11] [2400/6250] eta: 0:10:19 lr: 0.000124 grad: 0.0628 (0.0659) loss: 0.8510 (0.8500) time: 0.1699 data: 0.0944 max mem: 9394 +Train: [11] [2500/6250] eta: 0:09:59 lr: 0.000124 grad: 0.0634 (0.0658) loss: 0.8450 (0.8499) time: 0.1354 data: 0.0529 max mem: 9394 +Train: [11] [2600/6250] eta: 0:09:40 lr: 0.000124 grad: 0.0611 (0.0658) loss: 0.8514 (0.8498) time: 0.1426 data: 0.0643 max mem: 9394 +Train: [11] [2700/6250] eta: 0:09:21 lr: 0.000124 grad: 0.0632 (0.0658) loss: 0.8452 (0.8497) time: 0.1303 data: 0.0502 max mem: 9394 +Train: [11] [2800/6250] eta: 0:09:03 lr: 0.000124 grad: 0.0689 (0.0659) loss: 0.8488 (0.8496) time: 0.1368 data: 0.0523 max mem: 9394 +Train: [11] [2900/6250] eta: 0:08:46 lr: 0.000124 grad: 0.0643 (0.0659) loss: 0.8450 (0.8495) time: 0.1450 data: 0.0563 max mem: 9394 +Train: [11] [3000/6250] eta: 0:08:28 lr: 0.000124 grad: 0.0628 (0.0658) loss: 0.8436 (0.8493) time: 0.1294 data: 0.0510 max mem: 9394 +Train: [11] [3100/6250] eta: 0:08:10 lr: 0.000124 grad: 0.0608 (0.0658) loss: 0.8457 (0.8492) time: 0.1152 data: 0.0297 max mem: 9394 +Train: [11] [3200/6250] eta: 0:07:55 lr: 0.000124 grad: 0.0622 (0.0659) loss: 0.8500 (0.8491) time: 0.1350 data: 0.0583 max mem: 9394 +Train: [11] [3300/6250] eta: 0:07:37 lr: 0.000124 grad: 0.0600 (0.0659) loss: 0.8511 (0.8491) time: 0.1366 data: 0.0498 max mem: 9394 +Train: [11] [3400/6250] eta: 0:07:20 lr: 0.000124 grad: 0.0661 (0.0659) loss: 0.8507 (0.8490) time: 0.1445 data: 0.0589 max mem: 9394 +Train: [11] [3500/6250] eta: 0:07:03 lr: 0.000124 grad: 0.0609 (0.0660) loss: 0.8498 (0.8490) time: 0.1383 data: 0.0511 max mem: 9394 +Train: [11] [3600/6250] eta: 0:06:45 lr: 0.000124 grad: 0.0587 (0.0660) loss: 0.8495 (0.8490) time: 0.1283 data: 0.0411 max mem: 9394 +Train: [11] [3700/6250] eta: 0:06:29 lr: 0.000124 grad: 0.0617 (0.0659) loss: 0.8464 (0.8490) time: 0.1315 data: 0.0475 max mem: 9394 +Train: [11] [3800/6250] eta: 0:06:12 lr: 0.000124 grad: 0.0655 (0.0659) loss: 0.8506 (0.8490) time: 0.1350 data: 0.0552 max mem: 9394 +Train: [11] [3900/6250] eta: 0:05:56 lr: 0.000124 grad: 0.0673 (0.0659) loss: 0.8470 (0.8490) time: 0.1304 data: 0.0479 max mem: 9394 +Train: [11] [4000/6250] eta: 0:05:40 lr: 0.000123 grad: 0.0602 (0.0659) loss: 0.8507 (0.8489) time: 0.1269 data: 0.0465 max mem: 9394 +Train: [11] [4100/6250] eta: 0:05:24 lr: 0.000123 grad: 0.0634 (0.0658) loss: 0.8518 (0.8489) time: 0.1118 data: 0.0333 max mem: 9394 +Train: [11] [4200/6250] eta: 0:05:08 lr: 0.000123 grad: 0.0634 (0.0658) loss: 0.8424 (0.8489) time: 0.1393 data: 0.0640 max mem: 9394 +Train: [11] [4300/6250] eta: 0:04:52 lr: 0.000123 grad: 0.0676 (0.0658) loss: 0.8476 (0.8489) time: 0.1397 data: 0.0615 max mem: 9394 +Train: [11] [4400/6250] eta: 0:04:36 lr: 0.000123 grad: 0.0623 (0.0659) loss: 0.8437 (0.8488) time: 0.1315 data: 0.0560 max mem: 9394 +Train: [11] [4500/6250] eta: 0:04:21 lr: 0.000123 grad: 0.0612 (0.0658) loss: 0.8481 (0.8488) time: 0.1491 data: 0.0697 max mem: 9394 +Train: [11] [4600/6250] eta: 0:04:05 lr: 0.000123 grad: 0.0615 (0.0658) loss: 0.8498 (0.8488) time: 0.1343 data: 0.0557 max mem: 9394 +Train: [11] [4700/6250] eta: 0:03:50 lr: 0.000123 grad: 0.0579 (0.0657) loss: 0.8482 (0.8487) time: 0.2092 data: 0.0518 max mem: 9394 +Train: [11] [4800/6250] eta: 0:03:35 lr: 0.000123 grad: 0.0632 (0.0657) loss: 0.8494 (0.8487) time: 0.1408 data: 0.0593 max mem: 9394 +Train: [11] [4900/6250] eta: 0:03:20 lr: 0.000123 grad: 0.0626 (0.0657) loss: 0.8511 (0.8488) time: 0.1304 data: 0.0497 max mem: 9394 +Train: [11] [5000/6250] eta: 0:03:05 lr: 0.000123 grad: 0.0631 (0.0656) loss: 0.8495 (0.8487) time: 0.1317 data: 0.0560 max mem: 9394 +Train: [11] [5100/6250] eta: 0:02:50 lr: 0.000123 grad: 0.0616 (0.0656) loss: 0.8515 (0.8487) time: 0.1506 data: 0.0584 max mem: 9394 +Train: [11] [5200/6250] eta: 0:02:35 lr: 0.000123 grad: 0.0653 (0.0655) loss: 0.8468 (0.8488) time: 0.1818 data: 0.0721 max mem: 9394 +Train: [11] [5300/6250] eta: 0:02:20 lr: 0.000123 grad: 0.0644 (0.0655) loss: 0.8501 (0.8487) time: 0.1420 data: 0.0626 max mem: 9394 +Train: [11] [5400/6250] eta: 0:02:05 lr: 0.000123 grad: 0.0672 (0.0655) loss: 0.8470 (0.8487) time: 0.1541 data: 0.0795 max mem: 9394 +Train: [11] [5500/6250] eta: 0:01:50 lr: 0.000123 grad: 0.0627 (0.0655) loss: 0.8484 (0.8487) time: 0.1384 data: 0.0601 max mem: 9394 +Train: [11] [5600/6250] eta: 0:01:36 lr: 0.000123 grad: 0.0596 (0.0655) loss: 0.8479 (0.8487) time: 0.1377 data: 0.0543 max mem: 9394 +Train: [11] [5700/6250] eta: 0:01:21 lr: 0.000123 grad: 0.0632 (0.0654) loss: 0.8479 (0.8487) time: 0.1472 data: 0.0687 max mem: 9394 +Train: [11] [5800/6250] eta: 0:01:06 lr: 0.000123 grad: 0.0609 (0.0654) loss: 0.8462 (0.8487) time: 0.1215 data: 0.0350 max mem: 9394 +Train: [11] [5900/6250] eta: 0:00:51 lr: 0.000123 grad: 0.0615 (0.0654) loss: 0.8505 (0.8487) time: 0.1318 data: 0.0553 max mem: 9394 +Train: [11] [6000/6250] eta: 0:00:36 lr: 0.000123 grad: 0.0620 (0.0653) loss: 0.8475 (0.8487) time: 0.1587 data: 0.0809 max mem: 9394 +Train: [11] [6100/6250] eta: 0:00:22 lr: 0.000123 grad: 0.0596 (0.0653) loss: 0.8477 (0.8487) time: 0.1312 data: 0.0548 max mem: 9394 +Train: [11] [6200/6250] eta: 0:00:07 lr: 0.000123 grad: 0.0634 (0.0653) loss: 0.8475 (0.8487) time: 0.1498 data: 0.0720 max mem: 9394 +Train: [11] [6249/6250] eta: 0:00:00 lr: 0.000123 grad: 0.0605 (0.0652) loss: 0.8464 (0.8487) time: 0.1260 data: 0.0468 max mem: 9394 +Train: [11] Total time: 0:15:22 (0.1477 s / it) +Averaged stats: lr: 0.000123 grad: 0.0605 (0.0652) loss: 0.8464 (0.8487) +Eval (hcp-train-subset): [11] [ 0/62] eta: 0:05:33 loss: 0.8552 (0.8552) time: 5.3813 data: 5.3515 max mem: 9394 +Eval (hcp-train-subset): [11] [61/62] eta: 0:00:00 loss: 0.8489 (0.8515) time: 0.1401 data: 0.1139 max mem: 9394 +Eval (hcp-train-subset): [11] Total time: 0:00:14 (0.2262 s / it) +Averaged stats (hcp-train-subset): loss: 0.8489 (0.8515) +Eval (hcp-val): [11] [ 0/62] eta: 0:05:24 loss: 0.8398 (0.8398) time: 5.2351 data: 5.2052 max mem: 9394 +Eval (hcp-val): [11] [61/62] eta: 0:00:00 loss: 0.8455 (0.8466) time: 0.1225 data: 0.0950 max mem: 9394 +Eval (hcp-val): [11] Total time: 0:00:14 (0.2319 s / it) +Averaged stats (hcp-val): loss: 0.8455 (0.8466) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +Train: [12] [ 0/6250] eta: 10:19:55 lr: 0.000123 grad: 0.0749 (0.0749) loss: 0.8518 (0.8518) time: 5.9513 data: 5.8528 max mem: 9394 +Train: [12] [ 100/6250] eta: 0:20:12 lr: 0.000123 grad: 0.0676 (0.0690) loss: 0.8428 (0.8498) time: 0.1625 data: 0.0752 max mem: 9394 +Train: [12] [ 200/6250] eta: 0:17:12 lr: 0.000123 grad: 0.0612 (0.0678) loss: 0.8451 (0.8481) time: 0.1419 data: 0.0585 max mem: 9394 +Train: [12] [ 300/6250] eta: 0:15:58 lr: 0.000123 grad: 0.0650 (0.0673) loss: 0.8424 (0.8471) time: 0.1377 data: 0.0556 max mem: 9394 +Train: [12] [ 400/6250] eta: 0:14:52 lr: 0.000123 grad: 0.0657 (0.0673) loss: 0.8454 (0.8467) time: 0.1298 data: 0.0408 max mem: 9394 +Train: [12] [ 500/6250] eta: 0:14:16 lr: 0.000123 grad: 0.0612 (0.0676) loss: 0.8489 (0.8463) time: 0.1554 data: 0.0608 max mem: 9394 +Train: [12] [ 600/6250] eta: 0:13:41 lr: 0.000123 grad: 0.0657 (0.0675) loss: 0.8484 (0.8460) time: 0.1361 data: 0.0466 max mem: 9394 +Train: [12] [ 700/6250] eta: 0:13:16 lr: 0.000123 grad: 0.0636 (0.0675) loss: 0.8411 (0.8455) time: 0.1173 data: 0.0278 max mem: 9394 +Train: [12] [ 800/6250] eta: 0:12:58 lr: 0.000123 grad: 0.0643 (0.0674) loss: 0.8443 (0.8451) time: 0.1510 data: 0.0721 max mem: 9394 +Train: [12] [ 900/6250] eta: 0:13:02 lr: 0.000123 grad: 0.0616 (0.0672) loss: 0.8430 (0.8449) time: 0.1752 data: 0.0818 max mem: 9394 +Train: [12] [1000/6250] eta: 0:12:42 lr: 0.000123 grad: 0.0643 (0.0670) loss: 0.8433 (0.8448) time: 0.1328 data: 0.0581 max mem: 9394 +Train: [12] [1100/6250] eta: 0:12:32 lr: 0.000123 grad: 0.0653 (0.0667) loss: 0.8432 (0.8450) time: 0.1560 data: 0.0792 max mem: 9394 +Train: [12] [1200/6250] eta: 0:12:19 lr: 0.000123 grad: 0.0636 (0.0667) loss: 0.8454 (0.8448) time: 0.1222 data: 0.0426 max mem: 9394 +Train: [12] [1300/6250] eta: 0:12:06 lr: 0.000123 grad: 0.0640 (0.0667) loss: 0.8375 (0.8445) time: 0.1661 data: 0.0881 max mem: 9394 +Train: [12] [1400/6250] eta: 0:11:55 lr: 0.000123 grad: 0.0658 (0.0666) loss: 0.8418 (0.8443) time: 0.1716 data: 0.0934 max mem: 9394 +Train: [12] [1500/6250] eta: 0:11:37 lr: 0.000123 grad: 0.0680 (0.0666) loss: 0.8439 (0.8442) time: 0.1256 data: 0.0494 max mem: 9394 +Train: [12] [1600/6250] eta: 0:11:22 lr: 0.000123 grad: 0.0615 (0.0667) loss: 0.8415 (0.8440) time: 0.1427 data: 0.0652 max mem: 9394 +Train: [12] [1700/6250] eta: 0:11:06 lr: 0.000123 grad: 0.0641 (0.0666) loss: 0.8452 (0.8441) time: 0.1458 data: 0.0699 max mem: 9394 +Train: [12] [1800/6250] eta: 0:10:52 lr: 0.000123 grad: 0.0609 (0.0665) loss: 0.8431 (0.8441) time: 0.1738 data: 0.0964 max mem: 9394 +Train: [12] [1900/6250] eta: 0:10:37 lr: 0.000123 grad: 0.0640 (0.0665) loss: 0.8535 (0.8442) time: 0.1536 data: 0.0772 max mem: 9394 +Train: [12] [2000/6250] eta: 0:10:21 lr: 0.000123 grad: 0.0646 (0.0664) loss: 0.8428 (0.8442) time: 0.1307 data: 0.0509 max mem: 9394 +Train: [12] [2100/6250] eta: 0:10:06 lr: 0.000123 grad: 0.0635 (0.0664) loss: 0.8469 (0.8443) time: 0.1674 data: 0.0877 max mem: 9394 +Train: [12] [2200/6250] eta: 0:09:52 lr: 0.000123 grad: 0.0610 (0.0663) loss: 0.8479 (0.8444) time: 0.1451 data: 0.0630 max mem: 9394 +Train: [12] [2300/6250] eta: 0:09:38 lr: 0.000123 grad: 0.0618 (0.0662) loss: 0.8452 (0.8445) time: 0.1817 data: 0.0994 max mem: 9394 +Train: [12] [2400/6250] eta: 0:09:22 lr: 0.000123 grad: 0.0628 (0.0661) loss: 0.8497 (0.8445) time: 0.1479 data: 0.0601 max mem: 9394 +Train: [12] [2500/6250] eta: 0:09:09 lr: 0.000123 grad: 0.0628 (0.0660) loss: 0.8448 (0.8446) time: 0.0921 data: 0.0002 max mem: 9394 +Train: [12] [2600/6250] eta: 0:08:56 lr: 0.000123 grad: 0.0614 (0.0659) loss: 0.8448 (0.8446) time: 0.1841 data: 0.0881 max mem: 9394 +Train: [12] [2700/6250] eta: 0:08:41 lr: 0.000123 grad: 0.0604 (0.0659) loss: 0.8458 (0.8447) time: 0.1490 data: 0.0714 max mem: 9394 +Train: [12] [2800/6250] eta: 0:08:25 lr: 0.000123 grad: 0.0610 (0.0658) loss: 0.8439 (0.8447) time: 0.1393 data: 0.0642 max mem: 9394 +Train: [12] [2900/6250] eta: 0:08:10 lr: 0.000123 grad: 0.0591 (0.0656) loss: 0.8478 (0.8448) time: 0.0889 data: 0.0059 max mem: 9394 +Train: [12] [3000/6250] eta: 0:07:55 lr: 0.000123 grad: 0.0604 (0.0656) loss: 0.8426 (0.8448) time: 0.1472 data: 0.0686 max mem: 9394 +Train: [12] [3100/6250] eta: 0:07:40 lr: 0.000123 grad: 0.0651 (0.0655) loss: 0.8440 (0.8448) time: 0.1527 data: 0.0762 max mem: 9394 +Train: [12] [3200/6250] eta: 0:07:25 lr: 0.000123 grad: 0.0604 (0.0656) loss: 0.8457 (0.8449) time: 0.1399 data: 0.0593 max mem: 9394 +Train: [12] [3300/6250] eta: 0:07:10 lr: 0.000123 grad: 0.0612 (0.0655) loss: 0.8451 (0.8449) time: 0.1423 data: 0.0645 max mem: 9394 +Train: [12] [3400/6250] eta: 0:06:54 lr: 0.000123 grad: 0.0638 (0.0655) loss: 0.8475 (0.8450) time: 0.1334 data: 0.0488 max mem: 9394 +Train: [12] [3500/6250] eta: 0:06:39 lr: 0.000123 grad: 0.0663 (0.0656) loss: 0.8487 (0.8451) time: 0.1571 data: 0.0834 max mem: 9394 +Train: [12] [3600/6250] eta: 0:06:23 lr: 0.000123 grad: 0.0630 (0.0655) loss: 0.8500 (0.8451) time: 0.1304 data: 0.0540 max mem: 9394 +Train: [12] [3700/6250] eta: 0:06:08 lr: 0.000123 grad: 0.0627 (0.0655) loss: 0.8456 (0.8452) time: 0.1350 data: 0.0531 max mem: 9394 +Train: [12] [3800/6250] eta: 0:05:53 lr: 0.000123 grad: 0.0638 (0.0655) loss: 0.8470 (0.8452) time: 0.1375 data: 0.0550 max mem: 9394 +Train: [12] [3900/6250] eta: 0:05:38 lr: 0.000123 grad: 0.0633 (0.0655) loss: 0.8471 (0.8452) time: 0.1390 data: 0.0560 max mem: 9394 +Train: [12] [4000/6250] eta: 0:05:23 lr: 0.000123 grad: 0.0656 (0.0654) loss: 0.8462 (0.8452) time: 0.1149 data: 0.0369 max mem: 9394 +Train: [12] [4100/6250] eta: 0:05:09 lr: 0.000123 grad: 0.0621 (0.0654) loss: 0.8464 (0.8452) time: 0.1356 data: 0.0580 max mem: 9394 +Train: [12] [4200/6250] eta: 0:04:54 lr: 0.000123 grad: 0.0620 (0.0655) loss: 0.8428 (0.8452) time: 0.1456 data: 0.0645 max mem: 9394 +Train: [12] [4300/6250] eta: 0:04:39 lr: 0.000123 grad: 0.0637 (0.0655) loss: 0.8455 (0.8452) time: 0.1369 data: 0.0537 max mem: 9394 +Train: [12] [4400/6250] eta: 0:04:24 lr: 0.000123 grad: 0.0613 (0.0655) loss: 0.8426 (0.8452) time: 0.1335 data: 0.0548 max mem: 9394 +Train: [12] [4500/6250] eta: 0:04:10 lr: 0.000123 grad: 0.0604 (0.0655) loss: 0.8416 (0.8452) time: 0.1350 data: 0.0498 max mem: 9394 +Train: [12] [4600/6250] eta: 0:03:55 lr: 0.000123 grad: 0.0641 (0.0655) loss: 0.8456 (0.8452) time: 0.1332 data: 0.0559 max mem: 9394 +Train: [12] [4700/6250] eta: 0:03:41 lr: 0.000123 grad: 0.0628 (0.0655) loss: 0.8409 (0.8451) time: 0.1275 data: 0.0385 max mem: 9394 +Train: [12] [4800/6250] eta: 0:03:27 lr: 0.000123 grad: 0.0635 (0.0655) loss: 0.8446 (0.8452) time: 0.1407 data: 0.0603 max mem: 9394 +Train: [12] [4900/6250] eta: 0:03:13 lr: 0.000123 grad: 0.0614 (0.0655) loss: 0.8449 (0.8451) time: 0.1381 data: 0.0612 max mem: 9394 +Train: [12] [5000/6250] eta: 0:02:58 lr: 0.000123 grad: 0.0629 (0.0655) loss: 0.8433 (0.8451) time: 0.1182 data: 0.0377 max mem: 9394 +Train: [12] [5100/6250] eta: 0:02:44 lr: 0.000123 grad: 0.0633 (0.0655) loss: 0.8461 (0.8451) time: 0.1309 data: 0.0529 max mem: 9394 +Train: [12] [5200/6250] eta: 0:02:29 lr: 0.000123 grad: 0.0647 (0.0655) loss: 0.8421 (0.8451) time: 0.1390 data: 0.0584 max mem: 9394 +Train: [12] [5300/6250] eta: 0:02:15 lr: 0.000123 grad: 0.0636 (0.0655) loss: 0.8421 (0.8450) time: 0.2162 data: 0.1377 max mem: 9394 +Train: [12] [5400/6250] eta: 0:02:01 lr: 0.000123 grad: 0.0663 (0.0655) loss: 0.8458 (0.8450) time: 0.1363 data: 0.0586 max mem: 9394 +Train: [12] [5500/6250] eta: 0:01:47 lr: 0.000123 grad: 0.0620 (0.0655) loss: 0.8423 (0.8450) time: 0.1442 data: 0.0647 max mem: 9394 +Train: [12] [5600/6250] eta: 0:01:32 lr: 0.000123 grad: 0.0644 (0.0655) loss: 0.8396 (0.8450) time: 0.1363 data: 0.0571 max mem: 9394 +Train: [12] [5700/6250] eta: 0:01:18 lr: 0.000123 grad: 0.0609 (0.0655) loss: 0.8450 (0.8449) time: 0.1633 data: 0.0862 max mem: 9394 +Train: [12] [5800/6250] eta: 0:01:04 lr: 0.000123 grad: 0.0640 (0.0655) loss: 0.8401 (0.8448) time: 0.1357 data: 0.0565 max mem: 9394 +Train: [12] [5900/6250] eta: 0:00:49 lr: 0.000123 grad: 0.0634 (0.0655) loss: 0.8426 (0.8448) time: 0.1291 data: 0.0543 max mem: 9394 +Train: [12] [6000/6250] eta: 0:00:35 lr: 0.000123 grad: 0.0633 (0.0655) loss: 0.8386 (0.8447) time: 0.1273 data: 0.0525 max mem: 9394 +Train: [12] [6100/6250] eta: 0:00:21 lr: 0.000123 grad: 0.0652 (0.0655) loss: 0.8367 (0.8447) time: 0.1273 data: 0.0525 max mem: 9394 +Train: [12] [6200/6250] eta: 0:00:07 lr: 0.000123 grad: 0.0654 (0.0655) loss: 0.8375 (0.8446) time: 0.1422 data: 0.0646 max mem: 9394 +Train: [12] [6249/6250] eta: 0:00:00 lr: 0.000123 grad: 0.0683 (0.0655) loss: 0.8372 (0.8445) time: 0.1410 data: 0.0538 max mem: 9394 +Train: [12] Total time: 0:14:52 (0.1428 s / it) +Averaged stats: lr: 0.000123 grad: 0.0683 (0.0655) loss: 0.8372 (0.8445) +Eval (hcp-train-subset): [12] [ 0/62] eta: 0:05:30 loss: 0.8625 (0.8625) time: 5.3373 data: 5.3068 max mem: 9394 +Eval (hcp-train-subset): [12] [61/62] eta: 0:00:00 loss: 0.8514 (0.8520) time: 0.1527 data: 0.1273 max mem: 9394 +Eval (hcp-train-subset): [12] Total time: 0:00:14 (0.2349 s / it) +Averaged stats (hcp-train-subset): loss: 0.8514 (0.8520) +Eval (hcp-val): [12] [ 0/62] eta: 0:05:51 loss: 0.8435 (0.8435) time: 5.6718 data: 5.6420 max mem: 9394 +Eval (hcp-val): [12] [61/62] eta: 0:00:00 loss: 0.8455 (0.8460) time: 0.1352 data: 0.1085 max mem: 9394 +Eval (hcp-val): [12] Total time: 0:00:13 (0.2171 s / it) +Averaged stats (hcp-val): loss: 0.8455 (0.8460) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +Train: [13] [ 0/6250] eta: 8:35:57 lr: 0.000123 grad: 0.0523 (0.0523) loss: 0.8711 (0.8711) time: 4.9531 data: 4.8086 max mem: 9394 +Train: [13] [ 100/6250] eta: 0:19:56 lr: 0.000123 grad: 0.0643 (0.0630) loss: 0.8545 (0.8539) time: 0.1511 data: 0.0692 max mem: 9394 +Train: [13] [ 200/6250] eta: 0:17:30 lr: 0.000123 grad: 0.0704 (0.0673) loss: 0.8379 (0.8493) time: 0.1323 data: 0.0528 max mem: 9394 +Train: [13] [ 300/6250] eta: 0:16:11 lr: 0.000123 grad: 0.0597 (0.0691) loss: 0.8496 (0.8458) time: 0.1414 data: 0.0548 max mem: 9394 +Train: [13] [ 400/6250] eta: 0:15:18 lr: 0.000123 grad: 0.0654 (0.0685) loss: 0.8395 (0.8450) time: 0.1255 data: 0.0482 max mem: 9394 +Train: [13] [ 500/6250] eta: 0:14:32 lr: 0.000123 grad: 0.0648 (0.0685) loss: 0.8435 (0.8447) time: 0.1211 data: 0.0350 max mem: 9394 +Train: [13] [ 600/6250] eta: 0:13:55 lr: 0.000123 grad: 0.0598 (0.0679) loss: 0.8466 (0.8448) time: 0.1407 data: 0.0573 max mem: 9394 +Train: [13] [ 700/6250] eta: 0:13:24 lr: 0.000123 grad: 0.0591 (0.0673) loss: 0.8491 (0.8455) time: 0.1218 data: 0.0320 max mem: 9394 +Train: [13] [ 800/6250] eta: 0:12:58 lr: 0.000123 grad: 0.0630 (0.0668) loss: 0.8445 (0.8459) time: 0.1103 data: 0.0307 max mem: 9394 +Train: [13] [ 900/6250] eta: 0:12:54 lr: 0.000123 grad: 0.0595 (0.0665) loss: 0.8493 (0.8460) time: 0.1772 data: 0.0998 max mem: 9394 +Train: [13] [1000/6250] eta: 0:12:40 lr: 0.000123 grad: 0.0604 (0.0661) loss: 0.8481 (0.8461) time: 0.1601 data: 0.0816 max mem: 9394 +Train: [13] [1100/6250] eta: 0:12:29 lr: 0.000123 grad: 0.0599 (0.0658) loss: 0.8474 (0.8462) time: 0.1539 data: 0.0773 max mem: 9394 +Train: [13] [1200/6250] eta: 0:12:17 lr: 0.000123 grad: 0.0660 (0.0662) loss: 0.8449 (0.8461) time: 0.1497 data: 0.0694 max mem: 9394 +Train: [13] [1300/6250] eta: 0:12:07 lr: 0.000123 grad: 0.0637 (0.0659) loss: 0.8434 (0.8461) time: 0.1629 data: 0.0821 max mem: 9394 +Train: [13] [1400/6250] eta: 0:11:57 lr: 0.000123 grad: 0.0594 (0.0656) loss: 0.8392 (0.8460) time: 0.1748 data: 0.0953 max mem: 9394 +Train: [13] [1500/6250] eta: 0:11:44 lr: 0.000123 grad: 0.0595 (0.0656) loss: 0.8413 (0.8459) time: 0.1365 data: 0.0613 max mem: 9394 +Train: [13] [1600/6250] eta: 0:11:39 lr: 0.000123 grad: 0.0614 (0.0654) loss: 0.8448 (0.8458) time: 0.1786 data: 0.1028 max mem: 9394 +Train: [13] [1700/6250] eta: 0:11:21 lr: 0.000123 grad: 0.0641 (0.0654) loss: 0.8463 (0.8458) time: 0.1441 data: 0.0654 max mem: 9394 +Train: [13] [1800/6250] eta: 0:11:08 lr: 0.000123 grad: 0.0620 (0.0652) loss: 0.8457 (0.8459) time: 0.1613 data: 0.0842 max mem: 9394 +Train: [13] [1900/6250] eta: 0:10:52 lr: 0.000123 grad: 0.0616 (0.0650) loss: 0.8476 (0.8459) time: 0.1440 data: 0.0624 max mem: 9394 +Train: [13] [2000/6250] eta: 0:10:34 lr: 0.000123 grad: 0.0576 (0.0650) loss: 0.8504 (0.8460) time: 0.1082 data: 0.0207 max mem: 9394 +Train: [13] [2100/6250] eta: 0:10:17 lr: 0.000123 grad: 0.0635 (0.0648) loss: 0.8443 (0.8461) time: 0.1236 data: 0.0424 max mem: 9394 +Train: [13] [2200/6250] eta: 0:10:02 lr: 0.000123 grad: 0.0572 (0.0647) loss: 0.8490 (0.8461) time: 0.1866 data: 0.1101 max mem: 9394 +Train: [13] [2300/6250] eta: 0:09:46 lr: 0.000123 grad: 0.0650 (0.0647) loss: 0.8415 (0.8461) time: 0.1460 data: 0.0564 max mem: 9394 +Train: [13] [2400/6250] eta: 0:09:32 lr: 0.000123 grad: 0.0639 (0.0648) loss: 0.8493 (0.8460) time: 0.1703 data: 0.0802 max mem: 9394 +Train: [13] [2500/6250] eta: 0:09:17 lr: 0.000123 grad: 0.0632 (0.0647) loss: 0.8413 (0.8459) time: 0.1429 data: 0.0616 max mem: 9394 +Train: [13] [2600/6250] eta: 0:09:03 lr: 0.000123 grad: 0.0594 (0.0647) loss: 0.8489 (0.8459) time: 0.1943 data: 0.0874 max mem: 9394 +Train: [13] [2700/6250] eta: 0:08:56 lr: 0.000123 grad: 0.0630 (0.0647) loss: 0.8414 (0.8458) time: 0.1478 data: 0.0622 max mem: 9394 +Train: [13] [2800/6250] eta: 0:08:39 lr: 0.000123 grad: 0.0668 (0.0647) loss: 0.8407 (0.8457) time: 0.1478 data: 0.0687 max mem: 9394 +Train: [13] [2900/6250] eta: 0:08:25 lr: 0.000123 grad: 0.0613 (0.0647) loss: 0.8432 (0.8456) time: 0.1504 data: 0.0693 max mem: 9394 +Train: [13] [3000/6250] eta: 0:08:13 lr: 0.000123 grad: 0.0627 (0.0647) loss: 0.8443 (0.8456) time: 0.0797 data: 0.0002 max mem: 9394 +Train: [13] [3100/6250] eta: 0:07:55 lr: 0.000123 grad: 0.0653 (0.0647) loss: 0.8471 (0.8456) time: 0.1418 data: 0.0636 max mem: 9394 +Train: [13] [3200/6250] eta: 0:07:39 lr: 0.000123 grad: 0.0613 (0.0646) loss: 0.8396 (0.8456) time: 0.1469 data: 0.0622 max mem: 9394 +Train: [13] [3300/6250] eta: 0:07:28 lr: 0.000123 grad: 0.0627 (0.0645) loss: 0.8482 (0.8457) time: 0.2552 data: 0.1324 max mem: 9394 +Train: [13] [3400/6250] eta: 0:07:15 lr: 0.000123 grad: 0.0604 (0.0645) loss: 0.8475 (0.8457) time: 0.1375 data: 0.0575 max mem: 9394 +Train: [13] [3500/6250] eta: 0:06:59 lr: 0.000123 grad: 0.0593 (0.0645) loss: 0.8454 (0.8457) time: 0.1355 data: 0.0550 max mem: 9394 +Train: [13] [3600/6250] eta: 0:06:42 lr: 0.000123 grad: 0.0649 (0.0644) loss: 0.8426 (0.8457) time: 0.1374 data: 0.0494 max mem: 9394 +Train: [13] [3700/6250] eta: 0:06:26 lr: 0.000122 grad: 0.0617 (0.0644) loss: 0.8457 (0.8457) time: 0.1419 data: 0.0677 max mem: 9394 +Train: [13] [3800/6250] eta: 0:06:10 lr: 0.000122 grad: 0.0584 (0.0644) loss: 0.8483 (0.8457) time: 0.1268 data: 0.0389 max mem: 9394 +Train: [13] [3900/6250] eta: 0:05:53 lr: 0.000122 grad: 0.0627 (0.0644) loss: 0.8454 (0.8457) time: 0.1397 data: 0.0608 max mem: 9394 +Train: [13] [4000/6250] eta: 0:05:37 lr: 0.000122 grad: 0.0628 (0.0643) loss: 0.8459 (0.8457) time: 0.1342 data: 0.0506 max mem: 9394 +Train: [13] [4100/6250] eta: 0:05:21 lr: 0.000122 grad: 0.0633 (0.0643) loss: 0.8465 (0.8457) time: 0.1347 data: 0.0522 max mem: 9394 +Train: [13] [4200/6250] eta: 0:05:06 lr: 0.000122 grad: 0.0646 (0.0643) loss: 0.8454 (0.8457) time: 0.1365 data: 0.0585 max mem: 9394 +Train: [13] [4300/6250] eta: 0:04:50 lr: 0.000122 grad: 0.0632 (0.0643) loss: 0.8489 (0.8457) time: 0.1424 data: 0.0558 max mem: 9394 +Train: [13] [4400/6250] eta: 0:04:34 lr: 0.000122 grad: 0.0615 (0.0643) loss: 0.8464 (0.8457) time: 0.1192 data: 0.0390 max mem: 9394 +Train: [13] [4500/6250] eta: 0:04:19 lr: 0.000122 grad: 0.0604 (0.0642) loss: 0.8467 (0.8457) time: 0.1268 data: 0.0462 max mem: 9394 +Train: [13] [4600/6250] eta: 0:04:04 lr: 0.000122 grad: 0.0600 (0.0642) loss: 0.8465 (0.8457) time: 0.1566 data: 0.0796 max mem: 9394 +Train: [13] [4700/6250] eta: 0:03:48 lr: 0.000122 grad: 0.0593 (0.0642) loss: 0.8432 (0.8456) time: 0.1345 data: 0.0552 max mem: 9394 +Train: [13] [4800/6250] eta: 0:03:33 lr: 0.000122 grad: 0.0615 (0.0643) loss: 0.8399 (0.8456) time: 0.1307 data: 0.0490 max mem: 9394 +Train: [13] [4900/6250] eta: 0:03:18 lr: 0.000122 grad: 0.0605 (0.0643) loss: 0.8440 (0.8455) time: 0.1503 data: 0.0698 max mem: 9394 +Train: [13] [5000/6250] eta: 0:03:03 lr: 0.000122 grad: 0.0628 (0.0643) loss: 0.8426 (0.8455) time: 0.1546 data: 0.0711 max mem: 9394 +Train: [13] [5100/6250] eta: 0:02:48 lr: 0.000122 grad: 0.0624 (0.0642) loss: 0.8411 (0.8455) time: 0.1020 data: 0.0197 max mem: 9394 +Train: [13] [5200/6250] eta: 0:02:33 lr: 0.000122 grad: 0.0608 (0.0642) loss: 0.8430 (0.8454) time: 0.1412 data: 0.0616 max mem: 9394 +Train: [13] [5300/6250] eta: 0:02:18 lr: 0.000122 grad: 0.0598 (0.0642) loss: 0.8418 (0.8453) time: 0.1150 data: 0.0383 max mem: 9394 +Train: [13] [5400/6250] eta: 0:02:03 lr: 0.000122 grad: 0.0591 (0.0642) loss: 0.8416 (0.8452) time: 0.1382 data: 0.0585 max mem: 9394 +Train: [13] [5500/6250] eta: 0:01:49 lr: 0.000122 grad: 0.0642 (0.0641) loss: 0.8423 (0.8452) time: 0.1556 data: 0.0796 max mem: 9394 +Train: [13] [5600/6250] eta: 0:01:34 lr: 0.000122 grad: 0.0652 (0.0642) loss: 0.8391 (0.8451) time: 0.1097 data: 0.0267 max mem: 9394 +Train: [13] [5700/6250] eta: 0:01:19 lr: 0.000122 grad: 0.0612 (0.0642) loss: 0.8373 (0.8450) time: 0.1391 data: 0.0617 max mem: 9394 +Train: [13] [5800/6250] eta: 0:01:05 lr: 0.000122 grad: 0.0657 (0.0642) loss: 0.8390 (0.8449) time: 0.1436 data: 0.0654 max mem: 9394 +Train: [13] [5900/6250] eta: 0:00:50 lr: 0.000122 grad: 0.0628 (0.0642) loss: 0.8456 (0.8448) time: 0.1340 data: 0.0530 max mem: 9394 +Train: [13] [6000/6250] eta: 0:00:36 lr: 0.000122 grad: 0.0619 (0.0642) loss: 0.8440 (0.8448) time: 0.1395 data: 0.0593 max mem: 9394 +Train: [13] [6100/6250] eta: 0:00:21 lr: 0.000122 grad: 0.0622 (0.0642) loss: 0.8440 (0.8448) time: 0.1280 data: 0.0415 max mem: 9394 +Train: [13] [6200/6250] eta: 0:00:07 lr: 0.000122 grad: 0.0580 (0.0642) loss: 0.8456 (0.8447) time: 0.0864 data: 0.0002 max mem: 9394 +Train: [13] [6249/6250] eta: 0:00:00 lr: 0.000122 grad: 0.0654 (0.0642) loss: 0.8452 (0.8447) time: 0.1485 data: 0.0701 max mem: 9394 +Train: [13] Total time: 0:15:09 (0.1456 s / it) +Averaged stats: lr: 0.000122 grad: 0.0654 (0.0642) loss: 0.8452 (0.8447) +Eval (hcp-train-subset): [13] [ 0/62] eta: 0:04:48 loss: 0.8626 (0.8626) time: 4.6561 data: 4.6263 max mem: 9394 +Eval (hcp-train-subset): [13] [61/62] eta: 0:00:00 loss: 0.8500 (0.8500) time: 0.1595 data: 0.1312 max mem: 9394 +Eval (hcp-train-subset): [13] Total time: 0:00:14 (0.2310 s / it) +Averaged stats (hcp-train-subset): loss: 0.8500 (0.8500) +Eval (hcp-val): [13] [ 0/62] eta: 0:05:34 loss: 0.8413 (0.8413) time: 5.3933 data: 5.3634 max mem: 9394 +Eval (hcp-val): [13] [61/62] eta: 0:00:00 loss: 0.8445 (0.8447) time: 0.1249 data: 0.0996 max mem: 9394 +Eval (hcp-val): [13] Total time: 0:00:13 (0.2187 s / it) +Averaged stats (hcp-val): loss: 0.8445 (0.8447) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +Train: [14] [ 0/6250] eta: 8:39:05 lr: 0.000122 grad: 0.0587 (0.0587) loss: 0.8690 (0.8690) time: 4.9833 data: 4.8894 max mem: 9394 +Train: [14] [ 100/6250] eta: 0:20:06 lr: 0.000122 grad: 0.0686 (0.0692) loss: 0.8521 (0.8514) time: 0.1614 data: 0.0782 max mem: 9394 +Train: [14] [ 200/6250] eta: 0:17:31 lr: 0.000122 grad: 0.0643 (0.0660) loss: 0.8462 (0.8475) time: 0.1405 data: 0.0600 max mem: 9394 +Train: [14] [ 300/6250] eta: 0:16:20 lr: 0.000122 grad: 0.0638 (0.0648) loss: 0.8450 (0.8463) time: 0.1271 data: 0.0406 max mem: 9394 +Train: [14] [ 400/6250] eta: 0:15:20 lr: 0.000122 grad: 0.0620 (0.0651) loss: 0.8373 (0.8447) time: 0.1311 data: 0.0505 max mem: 9394 +pretraining fmri mae +start: 2026-03-31 20:03:56 +cwd: /data/connor/fmri-fm +sha: 7f4cedc35609f6857314e0d1ea6657523f17ddeb, status: has uncommitted changes, branch: dev/clane9 +config: +name: input_space_v3/flat_lr1e-3_1/pretrain +notes: input_space ablation v3 flat_lr1e-3_1; use tube masking and on-disk data (input_space=flat + base_lr=1e-3 seed=5401) +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain +input_space: flat +patch_size: 16 +num_frames: 16 +t_patch_size: 4 +mask_ratio: 0.9 +pred_mask_ratio: null +masking: tube +masking_kwargs: {} +mask_patch_size: null +model: mae_vit_base +model_kwargs: + decoding: attn + pos_embed: sep + target_norm: null + pca_norm_nc: 2 + t_pred_stride: 2 + no_decode_pos: true + mask_drop_scale: false + pred_edge_pad: 0 + gauss_sigma: null + class_token: true + reg_tokens: 0 + no_embed_class: true + head_init_scale: 0.0 + decoder_depth: 4 + drop_path_rate: 0.0 +datasets: + hcp-train: + type: wds + url: /data/fmri-datasets/pretrain/hcpya-all.${input_space}.wds/hcpya-all-${input_space}-{00000..01799}.tar + clipping: random + clipping_kwargs: + oversample: 4.0 + shuffle: true + buffer_size: 2000 + samples_per_epoch: 200000 + hcp-train-subset: + type: arrow + root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/validation + split_range: + - 0 + - 2000 + shuffle: false + hcp-val: + type: arrow + root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/test + split_range: + - 0 + - 2000 + shuffle: false +train_dataset: hcp-train +eval_datasets: +- hcp-train-subset +- hcp-val +val_dataset: null +clip_vmax: 3.0 +normalize: frame +tr_scale: null +crop_scale: null +crop_aspect: null +gray_jitter: null +num_workers: 16 +epochs: 100 +batch_size: 32 +accum_iter: 1 +base_lr: 0.001 +min_lr: 0.0 +warmup_epochs: 5 +weight_decay: 0.05 +betas: +- 0.9 +- 0.95 +clip_grad: 1.0 +amp: true +amp_dtype: float16 +ckpt: null +resume: true +auto_resume: true +start_epoch: 0 +max_checkpoints: 0 +checkpoint_period: null +plot_period: 5 +device: cuda +presend_cuda: false +seed: 5401 +debug: false +wandb: true +wandb_entity: null +wandb_project: fMRI-foundation-model +rank: 0 +world_size: 1 +gpu: 0 +distributed: true +dist_backend: nccl +in_chans: 1 +img_size: +- 224 +- 560 + +train transform: +Compose( + ToTensor() + TemporalCenterCrop(num_frames=16) + Normalize(mode='frame') + Clip(vmax=3.0) + FlatUnmask((224, 560)) +) +val transform: +Compose( + ToTensor() + TemporalCenterCrop(num_frames=16) + Normalize(mode='frame') + Clip(vmax=3.0) + FlatUnmask((224, 560)) +) +mask generator: +TubeMasking( + mask_ratio=0.9 + (patchify): Patchify2D((224, 560), (16, 16), in_chans=1) +) +loading dataset: hcp-train + +type: wds +url: /data/fmri-datasets/pretrain/hcpya-all.${input_space}.wds/hcpya-all-${input_space}-{00000..01799}.tar +clipping: random +clipping_kwargs: + oversample: 4.0 +shuffle: true +buffer_size: 2000 +samples_per_epoch: 200000 + +loading dataset: hcp-train-subset + +type: arrow +root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/validation +split_range: +- 0 +- 2000 +shuffle: false + +split indices: [899, 472, 767, 116, 1265, 1852, 300, 1335, 361, 1560] +loading dataset: hcp-val + +type: arrow +root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/test +split_range: +- 0 +- 2000 +shuffle: false + +split indices: [1075, 1189, 738, 1350, 965, 1964, 1367, 1183, 1619, 1407] +model: +MaskedAutoencoderViT( + decoding=attn, t_pred_stride=2, pred_edge_pad=0, no_decode_pos=True + (encoder): MaskedEncoder( + class_token=True, reg_tokens=0, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) + (pred_patchify): StridedPatchify3D((16, 224, 560), (2, 16, 16), in_chans=1, t_stride=2) + (decoder): MaskedDecoder( + cross_decode=False, class_token=True, no_embed_class=True + (pos_embed): SeparablePosEmbed(512, (4, 14, 35)) + (proj): Linear(in_features=768, out_features=512, bias=True) + (blocks): ModuleList( + (0-3): 4 x Block( + (norm1): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=16 + (q): Linear(in_features=512, out_features=512, bias=True) + (k): Linear(in_features=512, out_features=512, bias=True) + (v): Linear(in_features=512, out_features=512, bias=True) + (proj): Linear(in_features=512, out_features=512, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=512, out_features=2048, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=2048, out_features=512, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (head): Linear(in_features=512, out_features=512, bias=True) + ) +) +num params: 99.7M +total batch size: 32 = 32 bs per gpu x 1 accum x 1 gpus +lr: 1.25e-04 = 1.00e-03 x 32 / 256 +full schedule: epochs = 100 (steps = 625000) +warmup: epochs = 5 (steps = 31250) +loaded model state from checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +loaded optimizer state, resuming training from 14 +start training for 100 epochs +Train: [14] [ 0/6250] eta: 13:20:20 lr: 0.000122 grad: 0.0545 (0.0545) loss: 0.8787 (0.8787) time: 7.6833 data: 6.6721 max mem: 9353 +Train: [14] [ 100/6250] eta: 0:20:21 lr: 0.000122 grad: 0.0604 (0.0649) loss: 0.8550 (0.8545) time: 0.1532 data: 0.0739 max mem: 9390 +Train: [14] [ 200/6250] eta: 0:16:53 lr: 0.000122 grad: 0.0667 (0.0661) loss: 0.8516 (0.8527) time: 0.1557 data: 0.0759 max mem: 9390 +Train: [14] [ 300/6250] eta: 0:15:57 lr: 0.000122 grad: 0.0604 (0.0661) loss: 0.8512 (0.8517) time: 0.1060 data: 0.0272 max mem: 9390 +Train: [14] [ 400/6250] eta: 0:16:05 lr: 0.000122 grad: 0.0602 (0.0659) loss: 0.8495 (0.8502) time: 0.1483 data: 0.0688 max mem: 9390 +Train: [14] [ 500/6250] eta: 0:16:00 lr: 0.000122 grad: 0.0641 (0.0654) loss: 0.8449 (0.8490) time: 0.1155 data: 0.0042 max mem: 9390 +Train: [14] [ 600/6250] eta: 0:15:49 lr: 0.000122 grad: 0.0618 (0.0648) loss: 0.8410 (0.8480) time: 0.2124 data: 0.1269 max mem: 9390 +Train: [14] [ 700/6250] eta: 0:15:29 lr: 0.000122 grad: 0.0577 (0.0642) loss: 0.8435 (0.8474) time: 0.1610 data: 0.0704 max mem: 9390 +Train: [14] [ 800/6250] eta: 0:15:06 lr: 0.000122 grad: 0.0561 (0.0639) loss: 0.8426 (0.8470) time: 0.1442 data: 0.0631 max mem: 9390 +Train: [14] [ 900/6250] eta: 0:14:34 lr: 0.000122 grad: 0.0602 (0.0637) loss: 0.8425 (0.8469) time: 0.1438 data: 0.0586 max mem: 9390 +Train: [14] [1000/6250] eta: 0:14:01 lr: 0.000122 grad: 0.0612 (0.0636) loss: 0.8394 (0.8465) time: 0.1066 data: 0.0303 max mem: 9390 +Train: [14] [1100/6250] eta: 0:13:34 lr: 0.000122 grad: 0.0604 (0.0633) loss: 0.8439 (0.8462) time: 0.1419 data: 0.0649 max mem: 9390 +Train: [14] [1200/6250] eta: 0:13:10 lr: 0.000122 grad: 0.0610 (0.0631) loss: 0.8410 (0.8461) time: 0.1393 data: 0.0530 max mem: 9390 +Train: [14] [1300/6250] eta: 0:12:46 lr: 0.000122 grad: 0.0631 (0.0631) loss: 0.8410 (0.8459) time: 0.1361 data: 0.0580 max mem: 9390 +Train: [14] [1400/6250] eta: 0:12:23 lr: 0.000122 grad: 0.0575 (0.0630) loss: 0.8478 (0.8457) time: 0.1211 data: 0.0460 max mem: 9390 +Train: [14] [1500/6250] eta: 0:12:01 lr: 0.000122 grad: 0.0600 (0.0629) loss: 0.8419 (0.8455) time: 0.1289 data: 0.0500 max mem: 9390 +Train: [14] [1600/6250] eta: 0:11:40 lr: 0.000122 grad: 0.0600 (0.0628) loss: 0.8446 (0.8454) time: 0.1281 data: 0.0458 max mem: 9390 +Train: [14] [1700/6250] eta: 0:11:20 lr: 0.000122 grad: 0.0598 (0.0627) loss: 0.8460 (0.8453) time: 0.1360 data: 0.0650 max mem: 9390 +Train: [14] [1800/6250] eta: 0:10:59 lr: 0.000122 grad: 0.0584 (0.0626) loss: 0.8442 (0.8452) time: 0.1200 data: 0.0426 max mem: 9390 +Train: [14] [1900/6250] eta: 0:10:41 lr: 0.000122 grad: 0.0589 (0.0625) loss: 0.8463 (0.8452) time: 0.1430 data: 0.0648 max mem: 9390 +Train: [14] [2000/6250] eta: 0:10:22 lr: 0.000122 grad: 0.0575 (0.0624) loss: 0.8438 (0.8452) time: 0.1224 data: 0.0465 max mem: 9390 +Train: [14] [2100/6250] eta: 0:10:05 lr: 0.000122 grad: 0.0610 (0.0623) loss: 0.8433 (0.8451) time: 0.1320 data: 0.0517 max mem: 9390 +Train: [14] [2200/6250] eta: 0:09:48 lr: 0.000122 grad: 0.0605 (0.0623) loss: 0.8457 (0.8450) time: 0.1513 data: 0.0771 max mem: 9390 +Train: [14] [2300/6250] eta: 0:09:30 lr: 0.000122 grad: 0.0608 (0.0624) loss: 0.8411 (0.8449) time: 0.1181 data: 0.0373 max mem: 9390 +Train: [14] [2400/6250] eta: 0:09:14 lr: 0.000122 grad: 0.0588 (0.0623) loss: 0.8439 (0.8448) time: 0.1411 data: 0.0634 max mem: 9390 +Train: [14] [2500/6250] eta: 0:08:58 lr: 0.000122 grad: 0.0598 (0.0622) loss: 0.8437 (0.8448) time: 0.1310 data: 0.0539 max mem: 9390 +Train: [14] [2600/6250] eta: 0:08:42 lr: 0.000122 grad: 0.0618 (0.0622) loss: 0.8429 (0.8447) time: 0.1199 data: 0.0421 max mem: 9390 +Train: [14] [2700/6250] eta: 0:08:26 lr: 0.000122 grad: 0.0606 (0.0623) loss: 0.8426 (0.8447) time: 0.1405 data: 0.0614 max mem: 9390 +Train: [14] [2800/6250] eta: 0:08:11 lr: 0.000122 grad: 0.0632 (0.0623) loss: 0.8414 (0.8447) time: 0.1375 data: 0.0586 max mem: 9390 +Train: [14] [2900/6250] eta: 0:07:55 lr: 0.000122 grad: 0.0605 (0.0623) loss: 0.8442 (0.8447) time: 0.1199 data: 0.0409 max mem: 9390 +Train: [14] [3000/6250] eta: 0:07:40 lr: 0.000122 grad: 0.0614 (0.0624) loss: 0.8383 (0.8446) time: 0.1314 data: 0.0542 max mem: 9390 +Train: [14] [3100/6250] eta: 0:07:25 lr: 0.000122 grad: 0.0641 (0.0624) loss: 0.8438 (0.8445) time: 0.1338 data: 0.0545 max mem: 9390 +Train: [14] [3200/6250] eta: 0:07:09 lr: 0.000122 grad: 0.0606 (0.0624) loss: 0.8433 (0.8445) time: 0.1334 data: 0.0536 max mem: 9390 +Train: [14] [3300/6250] eta: 0:06:54 lr: 0.000122 grad: 0.0646 (0.0624) loss: 0.8391 (0.8444) time: 0.1129 data: 0.0330 max mem: 9390 +Train: [14] [3400/6250] eta: 0:06:40 lr: 0.000122 grad: 0.0620 (0.0625) loss: 0.8417 (0.8443) time: 0.1291 data: 0.0521 max mem: 9390 +Train: [14] [3500/6250] eta: 0:06:25 lr: 0.000122 grad: 0.0595 (0.0625) loss: 0.8418 (0.8443) time: 0.1206 data: 0.0377 max mem: 9390 +Train: [14] [3600/6250] eta: 0:06:11 lr: 0.000122 grad: 0.0633 (0.0625) loss: 0.8398 (0.8442) time: 0.1269 data: 0.0508 max mem: 9390 +Train: [14] [3700/6250] eta: 0:05:56 lr: 0.000122 grad: 0.0602 (0.0626) loss: 0.8421 (0.8442) time: 0.1170 data: 0.0394 max mem: 9390 +Train: [14] [3800/6250] eta: 0:05:41 lr: 0.000122 grad: 0.0612 (0.0626) loss: 0.8446 (0.8441) time: 0.1078 data: 0.0295 max mem: 9390 +Train: [14] [3900/6250] eta: 0:05:27 lr: 0.000122 grad: 0.0591 (0.0625) loss: 0.8408 (0.8441) time: 0.1297 data: 0.0519 max mem: 9390 +Train: [14] [4000/6250] eta: 0:05:13 lr: 0.000122 grad: 0.0578 (0.0625) loss: 0.8454 (0.8440) time: 0.1367 data: 0.0580 max mem: 9390 +Train: [14] [4100/6250] eta: 0:04:59 lr: 0.000122 grad: 0.0602 (0.0626) loss: 0.8409 (0.8439) time: 0.1439 data: 0.0702 max mem: 9390 +Train: [14] [4200/6250] eta: 0:04:45 lr: 0.000122 grad: 0.0595 (0.0626) loss: 0.8411 (0.8438) time: 0.1484 data: 0.0715 max mem: 9390 +Train: [14] [4300/6250] eta: 0:04:31 lr: 0.000122 grad: 0.0604 (0.0627) loss: 0.8409 (0.8438) time: 0.1490 data: 0.0690 max mem: 9390 +Train: [14] [4400/6250] eta: 0:04:16 lr: 0.000122 grad: 0.0620 (0.0626) loss: 0.8410 (0.8437) time: 0.1202 data: 0.0325 max mem: 9390 +Train: [14] [4500/6250] eta: 0:04:02 lr: 0.000122 grad: 0.0642 (0.0626) loss: 0.8426 (0.8437) time: 0.1339 data: 0.0609 max mem: 9390 +Train: [14] [4600/6250] eta: 0:03:48 lr: 0.000122 grad: 0.0601 (0.0626) loss: 0.8484 (0.8437) time: 0.1444 data: 0.0659 max mem: 9390 +Train: [14] [4700/6250] eta: 0:03:34 lr: 0.000122 grad: 0.0622 (0.0627) loss: 0.8400 (0.8437) time: 0.1686 data: 0.0965 max mem: 9390 +Train: [14] [4800/6250] eta: 0:03:20 lr: 0.000122 grad: 0.0614 (0.0627) loss: 0.8447 (0.8437) time: 0.1295 data: 0.0457 max mem: 9390 +Train: [14] [4900/6250] eta: 0:03:06 lr: 0.000122 grad: 0.0626 (0.0627) loss: 0.8411 (0.8436) time: 0.1340 data: 0.0587 max mem: 9390 +Train: [14] [5000/6250] eta: 0:02:52 lr: 0.000122 grad: 0.0593 (0.0627) loss: 0.8420 (0.8436) time: 0.1136 data: 0.0360 max mem: 9390 +Train: [14] [5100/6250] eta: 0:02:38 lr: 0.000122 grad: 0.0662 (0.0627) loss: 0.8361 (0.8435) time: 0.1249 data: 0.0438 max mem: 9390 +Train: [14] [5200/6250] eta: 0:02:24 lr: 0.000122 grad: 0.0601 (0.0627) loss: 0.8426 (0.8435) time: 0.1363 data: 0.0565 max mem: 9390 +Train: [14] [5300/6250] eta: 0:02:11 lr: 0.000122 grad: 0.0620 (0.0628) loss: 0.8426 (0.8435) time: 0.1351 data: 0.0589 max mem: 9390 +Train: [14] [5400/6250] eta: 0:01:57 lr: 0.000122 grad: 0.0630 (0.0628) loss: 0.8412 (0.8434) time: 0.1261 data: 0.0497 max mem: 9390 +Train: [14] [5500/6250] eta: 0:01:43 lr: 0.000122 grad: 0.0615 (0.0628) loss: 0.8440 (0.8434) time: 0.1560 data: 0.0810 max mem: 9390 +Train: [14] [5600/6250] eta: 0:01:29 lr: 0.000122 grad: 0.0610 (0.0628) loss: 0.8390 (0.8434) time: 0.1330 data: 0.0558 max mem: 9390 +Train: [14] [5700/6250] eta: 0:01:15 lr: 0.000122 grad: 0.0644 (0.0629) loss: 0.8433 (0.8433) time: 0.1358 data: 0.0567 max mem: 9390 +Train: [14] [5800/6250] eta: 0:01:01 lr: 0.000122 grad: 0.0603 (0.0629) loss: 0.8441 (0.8433) time: 0.1287 data: 0.0462 max mem: 9390 +Train: [14] [5900/6250] eta: 0:00:48 lr: 0.000122 grad: 0.0577 (0.0629) loss: 0.8410 (0.8432) time: 0.1251 data: 0.0436 max mem: 9390 +Train: [14] [6000/6250] eta: 0:00:34 lr: 0.000122 grad: 0.0591 (0.0629) loss: 0.8403 (0.8432) time: 0.1521 data: 0.0716 max mem: 9390 +Train: [14] [6100/6250] eta: 0:00:20 lr: 0.000122 grad: 0.0641 (0.0629) loss: 0.8384 (0.8431) time: 0.1246 data: 0.0461 max mem: 9390 +Train: [14] [6200/6250] eta: 0:00:06 lr: 0.000122 grad: 0.0619 (0.0629) loss: 0.8368 (0.8431) time: 0.1096 data: 0.0309 max mem: 9390 +Train: [14] [6249/6250] eta: 0:00:00 lr: 0.000122 grad: 0.0594 (0.0628) loss: 0.8386 (0.8431) time: 0.1487 data: 0.0705 max mem: 9390 +Train: [14] Total time: 0:14:27 (0.1387 s / it) +Averaged stats: lr: 0.000122 grad: 0.0594 (0.0628) loss: 0.8386 (0.8431) +Eval (hcp-train-subset): [14] [ 0/62] eta: 0:03:48 loss: 0.8597 (0.8597) time: 3.6903 data: 3.6366 max mem: 9390 +Eval (hcp-train-subset): [14] [61/62] eta: 0:00:00 loss: 0.8481 (0.8491) time: 0.1019 data: 0.0732 max mem: 9390 +Eval (hcp-train-subset): [14] Total time: 0:00:13 (0.2097 s / it) +Averaged stats (hcp-train-subset): loss: 0.8481 (0.8491) +Making plots (hcp-train-subset): example=51 +Eval (hcp-val): [14] [ 0/62] eta: 0:03:51 loss: 0.8381 (0.8381) time: 3.7272 data: 3.6357 max mem: 9390 +Eval (hcp-val): [14] [61/62] eta: 0:00:00 loss: 0.8415 (0.8433) time: 0.1118 data: 0.0848 max mem: 9390 +Eval (hcp-val): [14] Total time: 0:00:12 (0.2022 s / it) +Averaged stats (hcp-val): loss: 0.8415 (0.8433) +Making plots (hcp-val): example=54 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +Train: [15] [ 0/6250] eta: 8:46:27 lr: 0.000122 grad: 0.0483 (0.0483) loss: 0.8787 (0.8787) time: 5.0541 data: 4.9389 max mem: 9390 +Train: [15] [ 100/6250] eta: 0:18:48 lr: 0.000122 grad: 0.0665 (0.0710) loss: 0.8467 (0.8507) time: 0.1258 data: 0.0494 max mem: 9390 +Train: [15] [ 200/6250] eta: 0:15:40 lr: 0.000122 grad: 0.0664 (0.0699) loss: 0.8456 (0.8484) time: 0.1127 data: 0.0367 max mem: 9390 +Train: [15] [ 300/6250] eta: 0:14:29 lr: 0.000122 grad: 0.0615 (0.0679) loss: 0.8462 (0.8477) time: 0.1127 data: 0.0311 max mem: 9390 +Train: [15] [ 400/6250] eta: 0:13:43 lr: 0.000122 grad: 0.0570 (0.0665) loss: 0.8396 (0.8470) time: 0.1082 data: 0.0220 max mem: 9390 +Train: [15] [ 500/6250] eta: 0:13:06 lr: 0.000122 grad: 0.0569 (0.0656) loss: 0.8501 (0.8468) time: 0.1271 data: 0.0430 max mem: 9390 +Train: [15] [ 600/6250] eta: 0:12:34 lr: 0.000122 grad: 0.0595 (0.0648) loss: 0.8460 (0.8470) time: 0.1219 data: 0.0402 max mem: 9390 +Train: [15] [ 700/6250] eta: 0:12:11 lr: 0.000122 grad: 0.0591 (0.0645) loss: 0.8414 (0.8468) time: 0.1165 data: 0.0314 max mem: 9390 +Train: [15] [ 800/6250] eta: 0:12:01 lr: 0.000122 grad: 0.0597 (0.0641) loss: 0.8457 (0.8465) time: 0.1338 data: 0.0535 max mem: 9390 +Train: [15] [ 900/6250] eta: 0:11:52 lr: 0.000122 grad: 0.0557 (0.0636) loss: 0.8422 (0.8462) time: 0.1368 data: 0.0592 max mem: 9390 +Train: [15] [1000/6250] eta: 0:11:45 lr: 0.000122 grad: 0.0563 (0.0632) loss: 0.8448 (0.8462) time: 0.1311 data: 0.0552 max mem: 9390 +Train: [15] [1100/6250] eta: 0:11:32 lr: 0.000121 grad: 0.0579 (0.0630) loss: 0.8445 (0.8459) time: 0.1392 data: 0.0584 max mem: 9390 +Train: [15] [1200/6250] eta: 0:11:21 lr: 0.000121 grad: 0.0553 (0.0627) loss: 0.8461 (0.8456) time: 0.1344 data: 0.0595 max mem: 9390 +Train: [15] [1300/6250] eta: 0:11:08 lr: 0.000121 grad: 0.0588 (0.0626) loss: 0.8427 (0.8453) time: 0.1291 data: 0.0567 max mem: 9390 +Train: [15] [1400/6250] eta: 0:10:55 lr: 0.000121 grad: 0.0624 (0.0624) loss: 0.8397 (0.8451) time: 0.1382 data: 0.0524 max mem: 9390 +Train: [15] [1500/6250] eta: 0:10:42 lr: 0.000121 grad: 0.0594 (0.0624) loss: 0.8411 (0.8448) time: 0.1251 data: 0.0467 max mem: 9390 +Train: [15] [1600/6250] eta: 0:10:28 lr: 0.000121 grad: 0.0624 (0.0623) loss: 0.8390 (0.8444) time: 0.1221 data: 0.0395 max mem: 9390 +Train: [15] [1700/6250] eta: 0:10:16 lr: 0.000121 grad: 0.0598 (0.0622) loss: 0.8411 (0.8442) time: 0.1253 data: 0.0463 max mem: 9390 +Train: [15] [1800/6250] eta: 0:10:01 lr: 0.000121 grad: 0.0622 (0.0621) loss: 0.8393 (0.8439) time: 0.0986 data: 0.0194 max mem: 9390 +Train: [15] [1900/6250] eta: 0:09:48 lr: 0.000121 grad: 0.0611 (0.0621) loss: 0.8357 (0.8437) time: 0.1344 data: 0.0619 max mem: 9390 +Train: [15] [2000/6250] eta: 0:09:34 lr: 0.000121 grad: 0.0588 (0.0620) loss: 0.8387 (0.8435) time: 0.1403 data: 0.0598 max mem: 9390 +Train: [15] [2100/6250] eta: 0:09:21 lr: 0.000121 grad: 0.0594 (0.0619) loss: 0.8431 (0.8435) time: 0.1386 data: 0.0638 max mem: 9390 +Train: [15] [2200/6250] eta: 0:09:06 lr: 0.000121 grad: 0.0615 (0.0619) loss: 0.8430 (0.8434) time: 0.1218 data: 0.0449 max mem: 9390 +Train: [15] [2300/6250] eta: 0:08:53 lr: 0.000121 grad: 0.0587 (0.0618) loss: 0.8386 (0.8433) time: 0.1373 data: 0.0630 max mem: 9390 +Train: [15] [2400/6250] eta: 0:08:40 lr: 0.000121 grad: 0.0587 (0.0618) loss: 0.8492 (0.8433) time: 0.1450 data: 0.0665 max mem: 9390 +Train: [15] [2500/6250] eta: 0:08:26 lr: 0.000121 grad: 0.0595 (0.0618) loss: 0.8453 (0.8433) time: 0.1387 data: 0.0615 max mem: 9390 +Train: [15] [2600/6250] eta: 0:08:13 lr: 0.000121 grad: 0.0592 (0.0618) loss: 0.8446 (0.8433) time: 0.1211 data: 0.0442 max mem: 9390 +Train: [15] [2700/6250] eta: 0:07:59 lr: 0.000121 grad: 0.0602 (0.0619) loss: 0.8392 (0.8432) time: 0.1245 data: 0.0416 max mem: 9390 +Train: [15] [2800/6250] eta: 0:07:46 lr: 0.000121 grad: 0.0631 (0.0619) loss: 0.8421 (0.8432) time: 0.1340 data: 0.0587 max mem: 9390 +Train: [15] [2900/6250] eta: 0:07:32 lr: 0.000121 grad: 0.0614 (0.0619) loss: 0.8482 (0.8432) time: 0.1235 data: 0.0456 max mem: 9390 +Train: [15] [3000/6250] eta: 0:07:19 lr: 0.000121 grad: 0.0592 (0.0619) loss: 0.8445 (0.8432) time: 0.1295 data: 0.0525 max mem: 9390 +Train: [15] [3100/6250] eta: 0:07:05 lr: 0.000121 grad: 0.0604 (0.0620) loss: 0.8439 (0.8432) time: 0.1334 data: 0.0556 max mem: 9390 +Train: [15] [3200/6250] eta: 0:06:52 lr: 0.000121 grad: 0.0590 (0.0619) loss: 0.8417 (0.8431) time: 0.1337 data: 0.0581 max mem: 9390 +Train: [15] [3300/6250] eta: 0:06:38 lr: 0.000121 grad: 0.0597 (0.0620) loss: 0.8450 (0.8430) time: 0.1239 data: 0.0462 max mem: 9390 +Train: [15] [3400/6250] eta: 0:06:24 lr: 0.000121 grad: 0.0567 (0.0620) loss: 0.8477 (0.8430) time: 0.1246 data: 0.0503 max mem: 9390 +Train: [15] [3500/6250] eta: 0:06:11 lr: 0.000121 grad: 0.0639 (0.0621) loss: 0.8367 (0.8429) time: 0.1424 data: 0.0645 max mem: 9390 +Train: [15] [3600/6250] eta: 0:05:58 lr: 0.000121 grad: 0.0631 (0.0622) loss: 0.8419 (0.8428) time: 0.1371 data: 0.0592 max mem: 9390 +Train: [15] [3700/6250] eta: 0:05:44 lr: 0.000121 grad: 0.0609 (0.0623) loss: 0.8385 (0.8427) time: 0.1329 data: 0.0544 max mem: 9390 +Train: [15] [3800/6250] eta: 0:05:30 lr: 0.000121 grad: 0.0618 (0.0623) loss: 0.8367 (0.8426) time: 0.1208 data: 0.0332 max mem: 9390 +Train: [15] [3900/6250] eta: 0:05:17 lr: 0.000121 grad: 0.0625 (0.0624) loss: 0.8416 (0.8425) time: 0.1253 data: 0.0493 max mem: 9390 +Train: [15] [4000/6250] eta: 0:05:03 lr: 0.000121 grad: 0.0636 (0.0624) loss: 0.8395 (0.8424) time: 0.1322 data: 0.0527 max mem: 9390 +Train: [15] [4100/6250] eta: 0:04:50 lr: 0.000121 grad: 0.0600 (0.0625) loss: 0.8386 (0.8424) time: 0.1376 data: 0.0596 max mem: 9390 +Train: [15] [4200/6250] eta: 0:04:36 lr: 0.000121 grad: 0.0602 (0.0625) loss: 0.8397 (0.8423) time: 0.1217 data: 0.0349 max mem: 9390 +Train: [15] [4300/6250] eta: 0:04:23 lr: 0.000121 grad: 0.0641 (0.0626) loss: 0.8376 (0.8421) time: 0.1375 data: 0.0625 max mem: 9390 +Train: [15] [4400/6250] eta: 0:04:09 lr: 0.000121 grad: 0.0646 (0.0626) loss: 0.8388 (0.8420) time: 0.1515 data: 0.0785 max mem: 9390 +Train: [15] [4500/6250] eta: 0:03:56 lr: 0.000121 grad: 0.0647 (0.0627) loss: 0.8377 (0.8420) time: 0.1403 data: 0.0569 max mem: 9390 +Train: [15] [4600/6250] eta: 0:03:42 lr: 0.000121 grad: 0.0665 (0.0628) loss: 0.8369 (0.8419) time: 0.1345 data: 0.0568 max mem: 9390 +Train: [15] [4700/6250] eta: 0:03:29 lr: 0.000121 grad: 0.0621 (0.0628) loss: 0.8425 (0.8418) time: 0.1314 data: 0.0539 max mem: 9390 +Train: [15] [4800/6250] eta: 0:03:15 lr: 0.000121 grad: 0.0586 (0.0628) loss: 0.8469 (0.8418) time: 0.1442 data: 0.0717 max mem: 9390 +Train: [15] [4900/6250] eta: 0:03:02 lr: 0.000121 grad: 0.0601 (0.0628) loss: 0.8418 (0.8417) time: 0.1444 data: 0.0665 max mem: 9390 +Train: [15] [5000/6250] eta: 0:02:48 lr: 0.000121 grad: 0.0611 (0.0628) loss: 0.8399 (0.8417) time: 0.1388 data: 0.0518 max mem: 9390 +Train: [15] [5100/6250] eta: 0:02:35 lr: 0.000121 grad: 0.0592 (0.0628) loss: 0.8416 (0.8417) time: 0.1335 data: 0.0489 max mem: 9390 +Train: [15] [5200/6250] eta: 0:02:21 lr: 0.000121 grad: 0.0608 (0.0628) loss: 0.8371 (0.8417) time: 0.1360 data: 0.0561 max mem: 9390 +Train: [15] [5300/6250] eta: 0:02:07 lr: 0.000121 grad: 0.0575 (0.0628) loss: 0.8424 (0.8417) time: 0.1189 data: 0.0361 max mem: 9390 +Train: [15] [5400/6250] eta: 0:01:54 lr: 0.000121 grad: 0.0606 (0.0628) loss: 0.8409 (0.8416) time: 0.1178 data: 0.0422 max mem: 9390 +Train: [15] [5500/6250] eta: 0:01:40 lr: 0.000121 grad: 0.0595 (0.0628) loss: 0.8399 (0.8416) time: 0.1217 data: 0.0413 max mem: 9390 +Train: [15] [5600/6250] eta: 0:01:27 lr: 0.000121 grad: 0.0666 (0.0629) loss: 0.8402 (0.8416) time: 0.1156 data: 0.0388 max mem: 9390 +Train: [15] [5700/6250] eta: 0:01:13 lr: 0.000121 grad: 0.0612 (0.0629) loss: 0.8380 (0.8416) time: 0.1235 data: 0.0453 max mem: 9390 +Train: [15] [5800/6250] eta: 0:01:00 lr: 0.000121 grad: 0.0646 (0.0629) loss: 0.8419 (0.8416) time: 0.1250 data: 0.0473 max mem: 9390 +Train: [15] [5900/6250] eta: 0:00:46 lr: 0.000121 grad: 0.0603 (0.0630) loss: 0.8400 (0.8416) time: 0.1397 data: 0.0608 max mem: 9390 +Train: [15] [6000/6250] eta: 0:00:33 lr: 0.000121 grad: 0.0636 (0.0630) loss: 0.8363 (0.8415) time: 0.1350 data: 0.0504 max mem: 9390 +Train: [15] [6100/6250] eta: 0:00:20 lr: 0.000121 grad: 0.0591 (0.0631) loss: 0.8379 (0.8415) time: 0.1156 data: 0.0436 max mem: 9390 +Train: [15] [6200/6250] eta: 0:00:06 lr: 0.000121 grad: 0.0631 (0.0631) loss: 0.8414 (0.8415) time: 0.1578 data: 0.0809 max mem: 9390 +Train: [15] [6249/6250] eta: 0:00:00 lr: 0.000121 grad: 0.0600 (0.0631) loss: 0.8397 (0.8414) time: 0.1389 data: 0.0591 max mem: 9390 +Train: [15] Total time: 0:14:01 (0.1346 s / it) +Averaged stats: lr: 0.000121 grad: 0.0600 (0.0631) loss: 0.8397 (0.8414) +Eval (hcp-train-subset): [15] [ 0/62] eta: 0:04:44 loss: 0.8578 (0.8578) time: 4.5933 data: 4.5635 max mem: 9390 +Eval (hcp-train-subset): [15] [61/62] eta: 0:00:00 loss: 0.8494 (0.8482) time: 0.1228 data: 0.0963 max mem: 9390 +Eval (hcp-train-subset): [15] Total time: 0:00:13 (0.2150 s / it) +Averaged stats (hcp-train-subset): loss: 0.8494 (0.8482) +Eval (hcp-val): [15] [ 0/62] eta: 0:04:33 loss: 0.8402 (0.8402) time: 4.4060 data: 4.3738 max mem: 9390 +Eval (hcp-val): [15] [61/62] eta: 0:00:00 loss: 0.8425 (0.8436) time: 0.1197 data: 0.0951 max mem: 9390 +Eval (hcp-val): [15] Total time: 0:00:12 (0.2070 s / it) +Averaged stats (hcp-val): loss: 0.8425 (0.8436) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +Train: [16] [ 0/6250] eta: 7:41:09 lr: 0.000121 grad: 0.0577 (0.0577) loss: 0.8492 (0.8492) time: 4.4271 data: 4.1289 max mem: 9390 +Train: [16] [ 100/6250] eta: 0:18:44 lr: 0.000121 grad: 0.0701 (0.0772) loss: 0.8405 (0.8411) time: 0.1478 data: 0.0664 max mem: 9390 +Train: [16] [ 200/6250] eta: 0:15:59 lr: 0.000121 grad: 0.0680 (0.0744) loss: 0.8413 (0.8419) time: 0.1269 data: 0.0447 max mem: 9390 +Train: [16] [ 300/6250] eta: 0:15:01 lr: 0.000121 grad: 0.0594 (0.0719) loss: 0.8442 (0.8425) time: 0.1401 data: 0.0574 max mem: 9390 +Train: [16] [ 400/6250] eta: 0:14:01 lr: 0.000121 grad: 0.0626 (0.0697) loss: 0.8397 (0.8432) time: 0.1129 data: 0.0266 max mem: 9390 +Train: [16] [ 500/6250] eta: 0:13:26 lr: 0.000121 grad: 0.0623 (0.0689) loss: 0.8477 (0.8433) time: 0.1247 data: 0.0428 max mem: 9390 +Train: [16] [ 600/6250] eta: 0:12:54 lr: 0.000121 grad: 0.0597 (0.0682) loss: 0.8483 (0.8435) time: 0.1293 data: 0.0477 max mem: 9390 +Train: [16] [ 700/6250] eta: 0:12:27 lr: 0.000121 grad: 0.0587 (0.0674) loss: 0.8418 (0.8431) time: 0.1227 data: 0.0388 max mem: 9390 +Train: [16] [ 800/6250] eta: 0:12:06 lr: 0.000121 grad: 0.0636 (0.0670) loss: 0.8433 (0.8432) time: 0.1174 data: 0.0245 max mem: 9390 +Train: [16] [ 900/6250] eta: 0:11:57 lr: 0.000121 grad: 0.0636 (0.0667) loss: 0.8428 (0.8433) time: 0.1247 data: 0.0141 max mem: 9390 +Train: [16] [1000/6250] eta: 0:11:47 lr: 0.000121 grad: 0.0620 (0.0664) loss: 0.8457 (0.8433) time: 0.1242 data: 0.0460 max mem: 9390 +Train: [16] [1100/6250] eta: 0:11:35 lr: 0.000121 grad: 0.0607 (0.0661) loss: 0.8424 (0.8432) time: 0.1305 data: 0.0491 max mem: 9390 +Train: [16] [1200/6250] eta: 0:11:24 lr: 0.000121 grad: 0.0625 (0.0661) loss: 0.8401 (0.8432) time: 0.1363 data: 0.0582 max mem: 9390 +Train: [16] [1300/6250] eta: 0:11:10 lr: 0.000121 grad: 0.0654 (0.0660) loss: 0.8389 (0.8431) time: 0.1155 data: 0.0341 max mem: 9390 +Train: [16] [1400/6250] eta: 0:11:00 lr: 0.000121 grad: 0.0619 (0.0659) loss: 0.8387 (0.8430) time: 0.1264 data: 0.0530 max mem: 9390 +Train: [16] [1500/6250] eta: 0:10:46 lr: 0.000121 grad: 0.0656 (0.0659) loss: 0.8355 (0.8427) time: 0.1342 data: 0.0558 max mem: 9390 +Train: [16] [1600/6250] eta: 0:10:33 lr: 0.000121 grad: 0.0670 (0.0661) loss: 0.8376 (0.8425) time: 0.1213 data: 0.0403 max mem: 9390 +Train: [16] [1700/6250] eta: 0:10:20 lr: 0.000121 grad: 0.0610 (0.0660) loss: 0.8429 (0.8424) time: 0.1483 data: 0.0714 max mem: 9390 +Train: [16] [1800/6250] eta: 0:10:05 lr: 0.000121 grad: 0.0614 (0.0661) loss: 0.8432 (0.8423) time: 0.1254 data: 0.0451 max mem: 9390 +Train: [16] [1900/6250] eta: 0:09:52 lr: 0.000121 grad: 0.0620 (0.0659) loss: 0.8331 (0.8423) time: 0.1411 data: 0.0625 max mem: 9390 +Train: [16] [2000/6250] eta: 0:09:38 lr: 0.000121 grad: 0.0627 (0.0658) loss: 0.8433 (0.8422) time: 0.1448 data: 0.0650 max mem: 9390 +Train: [16] [2100/6250] eta: 0:09:24 lr: 0.000121 grad: 0.0585 (0.0657) loss: 0.8402 (0.8421) time: 0.1291 data: 0.0521 max mem: 9390 +Train: [16] [2200/6250] eta: 0:09:12 lr: 0.000121 grad: 0.0608 (0.0656) loss: 0.8437 (0.8421) time: 0.1657 data: 0.0864 max mem: 9390 +Train: [16] [2300/6250] eta: 0:08:57 lr: 0.000121 grad: 0.0583 (0.0654) loss: 0.8402 (0.8421) time: 0.1376 data: 0.0629 max mem: 9390 +Train: [16] [2400/6250] eta: 0:08:45 lr: 0.000121 grad: 0.0603 (0.0652) loss: 0.8374 (0.8420) time: 0.1658 data: 0.0632 max mem: 9390 +Train: [16] [2500/6250] eta: 0:08:31 lr: 0.000121 grad: 0.0591 (0.0652) loss: 0.8438 (0.8420) time: 0.1375 data: 0.0622 max mem: 9390 +Train: [16] [2600/6250] eta: 0:08:18 lr: 0.000121 grad: 0.0596 (0.0651) loss: 0.8403 (0.8418) time: 0.1291 data: 0.0594 max mem: 9390 +Train: [16] [2700/6250] eta: 0:08:04 lr: 0.000121 grad: 0.0643 (0.0651) loss: 0.8417 (0.8417) time: 0.1341 data: 0.0515 max mem: 9390 +Train: [16] [2800/6250] eta: 0:07:50 lr: 0.000121 grad: 0.0647 (0.0650) loss: 0.8348 (0.8416) time: 0.1398 data: 0.0564 max mem: 9390 +Train: [16] [2900/6250] eta: 0:07:37 lr: 0.000121 grad: 0.0648 (0.0650) loss: 0.8378 (0.8415) time: 0.1100 data: 0.0335 max mem: 9390 +Train: [16] [3000/6250] eta: 0:07:22 lr: 0.000121 grad: 0.0615 (0.0650) loss: 0.8405 (0.8414) time: 0.1582 data: 0.0800 max mem: 9390 +Train: [16] [3100/6250] eta: 0:07:08 lr: 0.000121 grad: 0.0624 (0.0650) loss: 0.8371 (0.8413) time: 0.1421 data: 0.0622 max mem: 9390 +Train: [16] [3200/6250] eta: 0:06:55 lr: 0.000121 grad: 0.0625 (0.0650) loss: 0.8397 (0.8412) time: 0.1560 data: 0.0793 max mem: 9390 +Train: [16] [3300/6250] eta: 0:06:41 lr: 0.000121 grad: 0.0604 (0.0650) loss: 0.8375 (0.8411) time: 0.1469 data: 0.0722 max mem: 9390 +Train: [16] [3400/6250] eta: 0:06:27 lr: 0.000121 grad: 0.0644 (0.0650) loss: 0.8385 (0.8410) time: 0.1411 data: 0.0650 max mem: 9390 +Train: [16] [3500/6250] eta: 0:06:13 lr: 0.000120 grad: 0.0601 (0.0650) loss: 0.8380 (0.8410) time: 0.1299 data: 0.0525 max mem: 9390 +Train: [16] [3600/6250] eta: 0:06:00 lr: 0.000120 grad: 0.0631 (0.0649) loss: 0.8406 (0.8409) time: 0.1212 data: 0.0426 max mem: 9390 +Train: [16] [3700/6250] eta: 0:05:46 lr: 0.000120 grad: 0.0599 (0.0649) loss: 0.8399 (0.8409) time: 0.1657 data: 0.0913 max mem: 9390 +Train: [16] [3800/6250] eta: 0:05:32 lr: 0.000120 grad: 0.0618 (0.0649) loss: 0.8417 (0.8409) time: 0.1294 data: 0.0494 max mem: 9390 +Train: [16] [3900/6250] eta: 0:05:19 lr: 0.000120 grad: 0.0610 (0.0648) loss: 0.8382 (0.8409) time: 0.1375 data: 0.0577 max mem: 9390 +Train: [16] [4000/6250] eta: 0:05:05 lr: 0.000120 grad: 0.0639 (0.0648) loss: 0.8409 (0.8408) time: 0.1268 data: 0.0441 max mem: 9390 +Train: [16] [4100/6250] eta: 0:04:51 lr: 0.000120 grad: 0.0613 (0.0648) loss: 0.8432 (0.8408) time: 0.1235 data: 0.0455 max mem: 9390 +Train: [16] [4200/6250] eta: 0:04:38 lr: 0.000120 grad: 0.0620 (0.0648) loss: 0.8377 (0.8407) time: 0.1470 data: 0.0717 max mem: 9390 +Train: [16] [4300/6250] eta: 0:04:24 lr: 0.000120 grad: 0.0596 (0.0647) loss: 0.8425 (0.8408) time: 0.1614 data: 0.0808 max mem: 9390 +Train: [16] [4400/6250] eta: 0:04:10 lr: 0.000120 grad: 0.0603 (0.0647) loss: 0.8422 (0.8408) time: 0.1277 data: 0.0450 max mem: 9390 +Train: [16] [4500/6250] eta: 0:03:57 lr: 0.000120 grad: 0.0607 (0.0647) loss: 0.8388 (0.8407) time: 0.1304 data: 0.0478 max mem: 9390 +Train: [16] [4600/6250] eta: 0:03:43 lr: 0.000120 grad: 0.0704 (0.0648) loss: 0.8363 (0.8406) time: 0.1343 data: 0.0598 max mem: 9390 +Train: [16] [4700/6250] eta: 0:03:30 lr: 0.000120 grad: 0.0597 (0.0648) loss: 0.8393 (0.8405) time: 0.1383 data: 0.0622 max mem: 9390 +Train: [16] [4800/6250] eta: 0:03:16 lr: 0.000120 grad: 0.0642 (0.0648) loss: 0.8329 (0.8404) time: 0.1133 data: 0.0359 max mem: 9390 +Train: [16] [4900/6250] eta: 0:03:02 lr: 0.000120 grad: 0.0613 (0.0648) loss: 0.8369 (0.8404) time: 0.1250 data: 0.0458 max mem: 9390 +Train: [16] [5000/6250] eta: 0:02:49 lr: 0.000120 grad: 0.0662 (0.0648) loss: 0.8382 (0.8403) time: 0.1189 data: 0.0363 max mem: 9390 +Train: [16] [5100/6250] eta: 0:02:35 lr: 0.000120 grad: 0.0629 (0.0648) loss: 0.8346 (0.8402) time: 0.1575 data: 0.0784 max mem: 9390 +Train: [16] [5200/6250] eta: 0:02:21 lr: 0.000120 grad: 0.0590 (0.0649) loss: 0.8377 (0.8402) time: 0.1391 data: 0.0676 max mem: 9390 +Train: [16] [5300/6250] eta: 0:02:08 lr: 0.000120 grad: 0.0633 (0.0649) loss: 0.8417 (0.8402) time: 0.1530 data: 0.0714 max mem: 9390 +Train: [16] [5400/6250] eta: 0:01:54 lr: 0.000120 grad: 0.0614 (0.0648) loss: 0.8401 (0.8401) time: 0.1342 data: 0.0561 max mem: 9390 +Train: [16] [5500/6250] eta: 0:01:41 lr: 0.000120 grad: 0.0612 (0.0649) loss: 0.8363 (0.8401) time: 0.1363 data: 0.0590 max mem: 9390 +Train: [16] [5600/6250] eta: 0:01:27 lr: 0.000120 grad: 0.0620 (0.0649) loss: 0.8358 (0.8401) time: 0.1383 data: 0.0586 max mem: 9390 +Train: [16] [5700/6250] eta: 0:01:14 lr: 0.000120 grad: 0.0593 (0.0649) loss: 0.8380 (0.8401) time: 0.1469 data: 0.0715 max mem: 9390 +Train: [16] [5800/6250] eta: 0:01:00 lr: 0.000120 grad: 0.0630 (0.0649) loss: 0.8458 (0.8401) time: 0.1456 data: 0.0610 max mem: 9390 +Train: [16] [5900/6250] eta: 0:00:47 lr: 0.000120 grad: 0.0663 (0.0649) loss: 0.8352 (0.8401) time: 0.1370 data: 0.0607 max mem: 9390 +Train: [16] [6000/6250] eta: 0:00:33 lr: 0.000120 grad: 0.0626 (0.0649) loss: 0.8436 (0.8401) time: 0.1181 data: 0.0391 max mem: 9390 +Train: [16] [6100/6250] eta: 0:00:20 lr: 0.000120 grad: 0.0609 (0.0649) loss: 0.8449 (0.8401) time: 0.1345 data: 0.0638 max mem: 9390 +Train: [16] [6200/6250] eta: 0:00:06 lr: 0.000120 grad: 0.0599 (0.0650) loss: 0.8378 (0.8401) time: 0.1387 data: 0.0647 max mem: 9390 +Train: [16] [6249/6250] eta: 0:00:00 lr: 0.000120 grad: 0.0646 (0.0650) loss: 0.8351 (0.8400) time: 0.1327 data: 0.0548 max mem: 9390 +Train: [16] Total time: 0:14:05 (0.1353 s / it) +Averaged stats: lr: 0.000120 grad: 0.0646 (0.0650) loss: 0.8351 (0.8400) +Eval (hcp-train-subset): [16] [ 0/62] eta: 0:04:55 loss: 0.8607 (0.8607) time: 4.7721 data: 4.7431 max mem: 9390 +Eval (hcp-train-subset): [16] [61/62] eta: 0:00:00 loss: 0.8467 (0.8478) time: 0.1386 data: 0.1131 max mem: 9390 +Eval (hcp-train-subset): [16] Total time: 0:00:13 (0.2118 s / it) +Averaged stats (hcp-train-subset): loss: 0.8467 (0.8478) +Eval (hcp-val): [16] [ 0/62] eta: 0:04:13 loss: 0.8385 (0.8385) time: 4.0882 data: 4.0570 max mem: 9390 +Eval (hcp-val): [16] [61/62] eta: 0:00:00 loss: 0.8416 (0.8427) time: 0.1624 data: 0.1322 max mem: 9390 +Eval (hcp-val): [16] Total time: 0:00:13 (0.2138 s / it) +Averaged stats (hcp-val): loss: 0.8416 (0.8427) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +Train: [17] [ 0/6250] eta: 9:24:38 lr: 0.000120 grad: 0.1448 (0.1448) loss: 0.8578 (0.8578) time: 5.4206 data: 5.3365 max mem: 9390 +Train: [17] [ 100/6250] eta: 0:17:58 lr: 0.000120 grad: 0.0591 (0.0692) loss: 0.8405 (0.8467) time: 0.1423 data: 0.0614 max mem: 9390 +Train: [17] [ 200/6250] eta: 0:15:43 lr: 0.000120 grad: 0.0569 (0.0656) loss: 0.8459 (0.8471) time: 0.1343 data: 0.0545 max mem: 9390 +Train: [17] [ 300/6250] eta: 0:14:37 lr: 0.000120 grad: 0.0614 (0.0642) loss: 0.8465 (0.8473) time: 0.1214 data: 0.0359 max mem: 9390 +Train: [17] [ 400/6250] eta: 0:13:51 lr: 0.000120 grad: 0.0622 (0.0640) loss: 0.8410 (0.8466) time: 0.1198 data: 0.0361 max mem: 9390 +Train: [17] [ 500/6250] eta: 0:13:15 lr: 0.000120 grad: 0.0629 (0.0637) loss: 0.8372 (0.8455) time: 0.1296 data: 0.0380 max mem: 9390 +Train: [17] [ 600/6250] eta: 0:12:45 lr: 0.000120 grad: 0.0603 (0.0638) loss: 0.8397 (0.8444) time: 0.1255 data: 0.0392 max mem: 9390 +Train: [17] [ 700/6250] eta: 0:12:20 lr: 0.000120 grad: 0.0646 (0.0637) loss: 0.8382 (0.8439) time: 0.1213 data: 0.0396 max mem: 9390 +Train: [17] [ 800/6250] eta: 0:12:00 lr: 0.000120 grad: 0.0609 (0.0637) loss: 0.8429 (0.8431) time: 0.1212 data: 0.0340 max mem: 9390 +Train: [17] [ 900/6250] eta: 0:11:43 lr: 0.000120 grad: 0.0563 (0.0637) loss: 0.8436 (0.8426) time: 0.1474 data: 0.0604 max mem: 9390 +Train: [17] [1000/6250] eta: 0:11:32 lr: 0.000120 grad: 0.0619 (0.0635) loss: 0.8407 (0.8423) time: 0.1452 data: 0.0654 max mem: 9390 +Train: [17] [1100/6250] eta: 0:11:18 lr: 0.000120 grad: 0.0562 (0.0632) loss: 0.8429 (0.8421) time: 0.1521 data: 0.0744 max mem: 9390 +Train: [17] [1200/6250] eta: 0:11:10 lr: 0.000120 grad: 0.0635 (0.0633) loss: 0.8335 (0.8417) time: 0.1491 data: 0.0694 max mem: 9390 +Train: [17] [1300/6250] eta: 0:10:59 lr: 0.000120 grad: 0.0614 (0.0632) loss: 0.8396 (0.8415) time: 0.1502 data: 0.0709 max mem: 9390 +Train: [17] [1400/6250] eta: 0:10:48 lr: 0.000120 grad: 0.0609 (0.0632) loss: 0.8366 (0.8414) time: 0.1290 data: 0.0504 max mem: 9390 +Train: [17] [1500/6250] eta: 0:10:38 lr: 0.000120 grad: 0.0632 (0.0632) loss: 0.8433 (0.8413) time: 0.1605 data: 0.0815 max mem: 9390 +Train: [17] [1600/6250] eta: 0:10:24 lr: 0.000120 grad: 0.0616 (0.0632) loss: 0.8447 (0.8412) time: 0.1236 data: 0.0422 max mem: 9390 +Train: [17] [1700/6250] eta: 0:10:11 lr: 0.000120 grad: 0.0602 (0.0633) loss: 0.8433 (0.8410) time: 0.1296 data: 0.0481 max mem: 9390 +Train: [17] [1800/6250] eta: 0:10:01 lr: 0.000120 grad: 0.0599 (0.0634) loss: 0.8356 (0.8408) time: 0.1476 data: 0.0707 max mem: 9390 +Train: [17] [1900/6250] eta: 0:09:46 lr: 0.000120 grad: 0.0622 (0.0635) loss: 0.8351 (0.8407) time: 0.1262 data: 0.0487 max mem: 9390 +Train: [17] [2000/6250] eta: 0:09:34 lr: 0.000120 grad: 0.0615 (0.0636) loss: 0.8382 (0.8404) time: 0.1595 data: 0.0807 max mem: 9390 +Train: [17] [2100/6250] eta: 0:09:20 lr: 0.000120 grad: 0.0653 (0.0637) loss: 0.8400 (0.8403) time: 0.1310 data: 0.0499 max mem: 9390 +Train: [17] [2200/6250] eta: 0:09:08 lr: 0.000120 grad: 0.0662 (0.0638) loss: 0.8327 (0.8402) time: 0.1236 data: 0.0437 max mem: 9390 +Train: [17] [2300/6250] eta: 0:08:55 lr: 0.000120 grad: 0.0625 (0.0640) loss: 0.8403 (0.8401) time: 0.1436 data: 0.0642 max mem: 9390 +Train: [17] [2400/6250] eta: 0:08:42 lr: 0.000120 grad: 0.0597 (0.0641) loss: 0.8355 (0.8400) time: 0.1525 data: 0.0759 max mem: 9390 +Train: [17] [2500/6250] eta: 0:08:28 lr: 0.000120 grad: 0.0582 (0.0642) loss: 0.8429 (0.8400) time: 0.1473 data: 0.0713 max mem: 9390 +Train: [17] [2600/6250] eta: 0:08:15 lr: 0.000120 grad: 0.0635 (0.0642) loss: 0.8332 (0.8398) time: 0.1546 data: 0.0755 max mem: 9390 +Train: [17] [2700/6250] eta: 0:08:01 lr: 0.000120 grad: 0.0626 (0.0642) loss: 0.8430 (0.8397) time: 0.1539 data: 0.0791 max mem: 9390 +Train: [17] [2800/6250] eta: 0:07:47 lr: 0.000120 grad: 0.0632 (0.0642) loss: 0.8389 (0.8397) time: 0.1377 data: 0.0577 max mem: 9390 +Train: [17] [2900/6250] eta: 0:07:33 lr: 0.000120 grad: 0.0613 (0.0642) loss: 0.8428 (0.8397) time: 0.1276 data: 0.0454 max mem: 9390 +Train: [17] [3000/6250] eta: 0:07:20 lr: 0.000120 grad: 0.0648 (0.0642) loss: 0.8361 (0.8397) time: 0.1520 data: 0.0776 max mem: 9390 +Train: [17] [3100/6250] eta: 0:07:06 lr: 0.000120 grad: 0.0614 (0.0643) loss: 0.8377 (0.8397) time: 0.1296 data: 0.0539 max mem: 9390 +Train: [17] [3200/6250] eta: 0:06:52 lr: 0.000120 grad: 0.0609 (0.0643) loss: 0.8338 (0.8396) time: 0.1457 data: 0.0696 max mem: 9390 +Train: [17] [3300/6250] eta: 0:06:38 lr: 0.000120 grad: 0.0610 (0.0644) loss: 0.8413 (0.8396) time: 0.1518 data: 0.0750 max mem: 9390 +Train: [17] [3400/6250] eta: 0:06:24 lr: 0.000120 grad: 0.0619 (0.0644) loss: 0.8384 (0.8396) time: 0.1317 data: 0.0508 max mem: 9390 +Train: [17] [3500/6250] eta: 0:06:11 lr: 0.000120 grad: 0.0586 (0.0644) loss: 0.8421 (0.8395) time: 0.1263 data: 0.0481 max mem: 9390 +Train: [17] [3600/6250] eta: 0:05:58 lr: 0.000120 grad: 0.0613 (0.0644) loss: 0.8410 (0.8395) time: 0.1279 data: 0.0528 max mem: 9390 +Train: [17] [3700/6250] eta: 0:05:44 lr: 0.000120 grad: 0.0620 (0.0644) loss: 0.8374 (0.8394) time: 0.1322 data: 0.0567 max mem: 9390 +Train: [17] [3800/6250] eta: 0:05:31 lr: 0.000120 grad: 0.0653 (0.0644) loss: 0.8351 (0.8394) time: 0.1420 data: 0.0655 max mem: 9390 +Train: [17] [3900/6250] eta: 0:05:17 lr: 0.000120 grad: 0.0616 (0.0644) loss: 0.8414 (0.8394) time: 0.1394 data: 0.0636 max mem: 9390 +Train: [17] [4000/6250] eta: 0:05:04 lr: 0.000120 grad: 0.0610 (0.0644) loss: 0.8382 (0.8394) time: 0.1387 data: 0.0624 max mem: 9390 +Train: [17] [4100/6250] eta: 0:04:50 lr: 0.000120 grad: 0.0629 (0.0644) loss: 0.8389 (0.8394) time: 0.1254 data: 0.0468 max mem: 9390 +Train: [17] [4200/6250] eta: 0:04:37 lr: 0.000120 grad: 0.0609 (0.0644) loss: 0.8400 (0.8393) time: 0.1001 data: 0.0190 max mem: 9390 +Train: [17] [4300/6250] eta: 0:04:23 lr: 0.000120 grad: 0.0639 (0.0644) loss: 0.8384 (0.8394) time: 0.1375 data: 0.0597 max mem: 9390 +Train: [17] [4400/6250] eta: 0:04:09 lr: 0.000120 grad: 0.0639 (0.0645) loss: 0.8413 (0.8394) time: 0.1404 data: 0.0578 max mem: 9390 +Train: [17] [4500/6250] eta: 0:03:56 lr: 0.000120 grad: 0.0629 (0.0644) loss: 0.8383 (0.8393) time: 0.1046 data: 0.0248 max mem: 9390 +Train: [17] [4600/6250] eta: 0:03:42 lr: 0.000120 grad: 0.0631 (0.0644) loss: 0.8349 (0.8393) time: 0.1485 data: 0.0721 max mem: 9390 +Train: [17] [4700/6250] eta: 0:03:29 lr: 0.000120 grad: 0.0613 (0.0644) loss: 0.8392 (0.8393) time: 0.1503 data: 0.0651 max mem: 9390 +Train: [17] [4800/6250] eta: 0:03:15 lr: 0.000120 grad: 0.0658 (0.0644) loss: 0.8281 (0.8393) time: 0.1365 data: 0.0649 max mem: 9390 +Train: [17] [4900/6250] eta: 0:03:02 lr: 0.000119 grad: 0.0576 (0.0644) loss: 0.8416 (0.8392) time: 0.1277 data: 0.0495 max mem: 9390 +Train: [17] [5000/6250] eta: 0:02:48 lr: 0.000119 grad: 0.0613 (0.0644) loss: 0.8435 (0.8392) time: 0.1243 data: 0.0477 max mem: 9390 +Train: [17] [5100/6250] eta: 0:02:35 lr: 0.000119 grad: 0.0602 (0.0644) loss: 0.8401 (0.8392) time: 0.1336 data: 0.0572 max mem: 9390 +Train: [17] [5200/6250] eta: 0:02:21 lr: 0.000119 grad: 0.0586 (0.0643) loss: 0.8399 (0.8392) time: 0.1329 data: 0.0541 max mem: 9390 +Train: [17] [5300/6250] eta: 0:02:07 lr: 0.000119 grad: 0.0646 (0.0644) loss: 0.8365 (0.8392) time: 0.1283 data: 0.0530 max mem: 9390 +Train: [17] [5400/6250] eta: 0:01:54 lr: 0.000119 grad: 0.0586 (0.0644) loss: 0.8387 (0.8391) time: 0.1388 data: 0.0595 max mem: 9390 +Train: [17] [5500/6250] eta: 0:01:40 lr: 0.000119 grad: 0.0635 (0.0644) loss: 0.8322 (0.8390) time: 0.1260 data: 0.0470 max mem: 9390 +Train: [17] [5600/6250] eta: 0:01:27 lr: 0.000119 grad: 0.0584 (0.0644) loss: 0.8369 (0.8390) time: 0.1395 data: 0.0576 max mem: 9390 +Train: [17] [5700/6250] eta: 0:01:14 lr: 0.000119 grad: 0.0636 (0.0644) loss: 0.8416 (0.8390) time: 0.1666 data: 0.0884 max mem: 9390 +Train: [17] [5800/6250] eta: 0:01:00 lr: 0.000119 grad: 0.0605 (0.0644) loss: 0.8399 (0.8390) time: 0.1214 data: 0.0430 max mem: 9390 +Train: [17] [5900/6250] eta: 0:00:47 lr: 0.000119 grad: 0.0621 (0.0644) loss: 0.8403 (0.8389) time: 0.1443 data: 0.0660 max mem: 9390 +Train: [17] [6000/6250] eta: 0:00:33 lr: 0.000119 grad: 0.0632 (0.0644) loss: 0.8379 (0.8389) time: 0.1276 data: 0.0476 max mem: 9390 +Train: [17] [6100/6250] eta: 0:00:20 lr: 0.000119 grad: 0.0621 (0.0644) loss: 0.8376 (0.8389) time: 0.1346 data: 0.0555 max mem: 9390 +Train: [17] [6200/6250] eta: 0:00:06 lr: 0.000119 grad: 0.0588 (0.0644) loss: 0.8373 (0.8389) time: 0.1422 data: 0.0672 max mem: 9390 +Train: [17] [6249/6250] eta: 0:00:00 lr: 0.000119 grad: 0.0645 (0.0644) loss: 0.8375 (0.8389) time: 0.0981 data: 0.0153 max mem: 9390 +Train: [17] Total time: 0:14:06 (0.1354 s / it) +Averaged stats: lr: 0.000119 grad: 0.0645 (0.0644) loss: 0.8375 (0.8389) +Eval (hcp-train-subset): [17] [ 0/62] eta: 0:04:30 loss: 0.8539 (0.8539) time: 4.3630 data: 4.3243 max mem: 9390 +Eval (hcp-train-subset): [17] [61/62] eta: 0:00:00 loss: 0.8445 (0.8459) time: 0.0964 data: 0.0716 max mem: 9390 +Eval (hcp-train-subset): [17] Total time: 0:00:12 (0.1985 s / it) +Averaged stats (hcp-train-subset): loss: 0.8445 (0.8459) +Eval (hcp-val): [17] [ 0/62] eta: 0:04:29 loss: 0.8370 (0.8370) time: 4.3414 data: 4.3113 max mem: 9390 +Eval (hcp-val): [17] [61/62] eta: 0:00:00 loss: 0.8421 (0.8417) time: 0.1131 data: 0.0886 max mem: 9390 +Eval (hcp-val): [17] Total time: 0:00:11 (0.1885 s / it) +Averaged stats (hcp-val): loss: 0.8421 (0.8417) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +Train: [18] [ 0/6250] eta: 7:41:45 lr: 0.000119 grad: 0.1132 (0.1132) loss: 0.8193 (0.8193) time: 4.4330 data: 4.3238 max mem: 9390 +Train: [18] [ 100/6250] eta: 0:18:15 lr: 0.000119 grad: 0.0623 (0.0683) loss: 0.8442 (0.8471) time: 0.1410 data: 0.0560 max mem: 9390 +Train: [18] [ 200/6250] eta: 0:15:34 lr: 0.000119 grad: 0.0604 (0.0660) loss: 0.8423 (0.8458) time: 0.1274 data: 0.0404 max mem: 9390 +Train: [18] [ 300/6250] eta: 0:14:37 lr: 0.000119 grad: 0.0662 (0.0658) loss: 0.8368 (0.8436) time: 0.1369 data: 0.0595 max mem: 9390 +Train: [18] [ 400/6250] eta: 0:14:01 lr: 0.000119 grad: 0.0666 (0.0656) loss: 0.8362 (0.8416) time: 0.1373 data: 0.0606 max mem: 9390 +Train: [18] [ 500/6250] eta: 0:13:27 lr: 0.000119 grad: 0.0610 (0.0653) loss: 0.8395 (0.8409) time: 0.1305 data: 0.0454 max mem: 9390 +Train: [18] [ 600/6250] eta: 0:12:56 lr: 0.000119 grad: 0.0592 (0.0647) loss: 0.8454 (0.8410) time: 0.1383 data: 0.0521 max mem: 9390 +Train: [18] [ 700/6250] eta: 0:12:29 lr: 0.000119 grad: 0.0636 (0.0643) loss: 0.8384 (0.8412) time: 0.1373 data: 0.0451 max mem: 9390 +Train: [18] [ 800/6250] eta: 0:12:03 lr: 0.000119 grad: 0.0595 (0.0639) loss: 0.8431 (0.8414) time: 0.1188 data: 0.0377 max mem: 9390 +Train: [18] [ 900/6250] eta: 0:11:50 lr: 0.000119 grad: 0.0591 (0.0635) loss: 0.8421 (0.8415) time: 0.1439 data: 0.0650 max mem: 9390 +Train: [18] [1000/6250] eta: 0:11:46 lr: 0.000119 grad: 0.0577 (0.0632) loss: 0.8414 (0.8416) time: 0.1513 data: 0.0666 max mem: 9390 +Train: [18] [1100/6250] eta: 0:11:30 lr: 0.000119 grad: 0.0579 (0.0631) loss: 0.8424 (0.8415) time: 0.1059 data: 0.0231 max mem: 9390 +Train: [18] [1200/6250] eta: 0:11:17 lr: 0.000119 grad: 0.0567 (0.0630) loss: 0.8464 (0.8415) time: 0.1405 data: 0.0566 max mem: 9390 +Train: [18] [1300/6250] eta: 0:11:05 lr: 0.000119 grad: 0.0600 (0.0628) loss: 0.8422 (0.8414) time: 0.1419 data: 0.0637 max mem: 9390 +Train: [18] [1400/6250] eta: 0:10:55 lr: 0.000119 grad: 0.0561 (0.0628) loss: 0.8422 (0.8413) time: 0.1344 data: 0.0547 max mem: 9390 +Train: [18] [1500/6250] eta: 0:10:46 lr: 0.000119 grad: 0.0604 (0.0629) loss: 0.8419 (0.8411) time: 0.1529 data: 0.0765 max mem: 9390 +Train: [18] [1600/6250] eta: 0:10:34 lr: 0.000119 grad: 0.0590 (0.0628) loss: 0.8444 (0.8410) time: 0.1305 data: 0.0511 max mem: 9390 +Train: [18] [1700/6250] eta: 0:10:21 lr: 0.000119 grad: 0.0606 (0.0628) loss: 0.8393 (0.8408) time: 0.1305 data: 0.0523 max mem: 9390 +Train: [18] [1800/6250] eta: 0:10:08 lr: 0.000119 grad: 0.0642 (0.0629) loss: 0.8372 (0.8407) time: 0.1560 data: 0.0772 max mem: 9390 +Train: [18] [1900/6250] eta: 0:09:55 lr: 0.000119 grad: 0.0650 (0.0630) loss: 0.8378 (0.8405) time: 0.1418 data: 0.0672 max mem: 9390 +Train: [18] [2000/6250] eta: 0:09:41 lr: 0.000119 grad: 0.0622 (0.0632) loss: 0.8347 (0.8404) time: 0.1503 data: 0.0759 max mem: 9390 +Train: [18] [2100/6250] eta: 0:09:27 lr: 0.000119 grad: 0.0636 (0.0635) loss: 0.8387 (0.8402) time: 0.1276 data: 0.0503 max mem: 9390 +Train: [18] [2200/6250] eta: 0:09:14 lr: 0.000119 grad: 0.0630 (0.0636) loss: 0.8356 (0.8401) time: 0.1394 data: 0.0656 max mem: 9390 +Train: [18] [2300/6250] eta: 0:09:00 lr: 0.000119 grad: 0.0647 (0.0638) loss: 0.8398 (0.8399) time: 0.1358 data: 0.0591 max mem: 9390 +Train: [18] [2400/6250] eta: 0:08:45 lr: 0.000119 grad: 0.0618 (0.0638) loss: 0.8377 (0.8398) time: 0.1278 data: 0.0472 max mem: 9390 +Train: [18] [2500/6250] eta: 0:08:32 lr: 0.000119 grad: 0.0646 (0.0639) loss: 0.8365 (0.8397) time: 0.1485 data: 0.0711 max mem: 9390 +Train: [18] [2600/6250] eta: 0:08:17 lr: 0.000119 grad: 0.0649 (0.0639) loss: 0.8344 (0.8396) time: 0.1353 data: 0.0531 max mem: 9390 +Train: [18] [2700/6250] eta: 0:08:04 lr: 0.000119 grad: 0.0593 (0.0640) loss: 0.8369 (0.8395) time: 0.1464 data: 0.0663 max mem: 9390 +Train: [18] [2800/6250] eta: 0:07:50 lr: 0.000119 grad: 0.0631 (0.0640) loss: 0.8381 (0.8393) time: 0.1291 data: 0.0505 max mem: 9390 +Train: [18] [2900/6250] eta: 0:07:35 lr: 0.000119 grad: 0.0671 (0.0642) loss: 0.8373 (0.8392) time: 0.1262 data: 0.0503 max mem: 9390 +Train: [18] [3000/6250] eta: 0:07:22 lr: 0.000119 grad: 0.0639 (0.0643) loss: 0.8328 (0.8391) time: 0.1364 data: 0.0591 max mem: 9390 +Train: [18] [3100/6250] eta: 0:07:08 lr: 0.000119 grad: 0.0662 (0.0644) loss: 0.8329 (0.8390) time: 0.1385 data: 0.0551 max mem: 9390 +Train: [18] [3200/6250] eta: 0:06:54 lr: 0.000119 grad: 0.0623 (0.0644) loss: 0.8364 (0.8388) time: 0.1290 data: 0.0509 max mem: 9390 +Train: [18] [3300/6250] eta: 0:06:41 lr: 0.000119 grad: 0.0590 (0.0645) loss: 0.8400 (0.8388) time: 0.1394 data: 0.0642 max mem: 9390 +Train: [18] [3400/6250] eta: 0:06:27 lr: 0.000119 grad: 0.0616 (0.0644) loss: 0.8422 (0.8388) time: 0.1268 data: 0.0477 max mem: 9390 +Train: [18] [3500/6250] eta: 0:06:13 lr: 0.000119 grad: 0.0621 (0.0644) loss: 0.8408 (0.8387) time: 0.1208 data: 0.0428 max mem: 9390 +Train: [18] [3600/6250] eta: 0:06:00 lr: 0.000119 grad: 0.0630 (0.0645) loss: 0.8440 (0.8386) time: 0.1341 data: 0.0554 max mem: 9390 +Train: [18] [3700/6250] eta: 0:05:46 lr: 0.000119 grad: 0.0640 (0.0645) loss: 0.8383 (0.8386) time: 0.1202 data: 0.0416 max mem: 9390 +Train: [18] [3800/6250] eta: 0:05:32 lr: 0.000119 grad: 0.0719 (0.0645) loss: 0.8292 (0.8385) time: 0.1326 data: 0.0561 max mem: 9390 +Train: [18] [3900/6250] eta: 0:05:18 lr: 0.000119 grad: 0.0659 (0.0645) loss: 0.8396 (0.8385) time: 0.1500 data: 0.0745 max mem: 9390 +Train: [18] [4000/6250] eta: 0:05:05 lr: 0.000119 grad: 0.0601 (0.0645) loss: 0.8391 (0.8385) time: 0.1600 data: 0.0743 max mem: 9390 +Train: [18] [4100/6250] eta: 0:04:51 lr: 0.000119 grad: 0.0614 (0.0645) loss: 0.8378 (0.8384) time: 0.1173 data: 0.0405 max mem: 9390 +Train: [18] [4200/6250] eta: 0:04:38 lr: 0.000119 grad: 0.0631 (0.0645) loss: 0.8353 (0.8384) time: 0.1415 data: 0.0516 max mem: 9390 +Train: [18] [4300/6250] eta: 0:04:24 lr: 0.000119 grad: 0.0642 (0.0645) loss: 0.8367 (0.8383) time: 0.1431 data: 0.0615 max mem: 9390 +Train: [18] [4400/6250] eta: 0:04:11 lr: 0.000119 grad: 0.0589 (0.0645) loss: 0.8383 (0.8383) time: 0.1341 data: 0.0538 max mem: 9390 +Train: [18] [4500/6250] eta: 0:03:57 lr: 0.000119 grad: 0.0644 (0.0645) loss: 0.8360 (0.8383) time: 0.1298 data: 0.0482 max mem: 9390 +Train: [18] [4600/6250] eta: 0:03:43 lr: 0.000119 grad: 0.0617 (0.0645) loss: 0.8359 (0.8382) time: 0.1433 data: 0.0685 max mem: 9390 +Train: [18] [4700/6250] eta: 0:03:30 lr: 0.000119 grad: 0.0626 (0.0645) loss: 0.8425 (0.8382) time: 0.1332 data: 0.0548 max mem: 9390 +Train: [18] [4800/6250] eta: 0:03:16 lr: 0.000119 grad: 0.0617 (0.0645) loss: 0.8353 (0.8382) time: 0.1336 data: 0.0568 max mem: 9390 +Train: [18] [4900/6250] eta: 0:03:02 lr: 0.000119 grad: 0.0595 (0.0645) loss: 0.8358 (0.8381) time: 0.1045 data: 0.0239 max mem: 9390 +Train: [18] [5000/6250] eta: 0:02:49 lr: 0.000119 grad: 0.0626 (0.0645) loss: 0.8292 (0.8380) time: 0.1291 data: 0.0509 max mem: 9390 +Train: [18] [5100/6250] eta: 0:02:35 lr: 0.000119 grad: 0.0598 (0.0646) loss: 0.8368 (0.8380) time: 0.1173 data: 0.0378 max mem: 9390 +Train: [18] [5200/6250] eta: 0:02:22 lr: 0.000119 grad: 0.0636 (0.0645) loss: 0.8361 (0.8380) time: 0.1432 data: 0.0659 max mem: 9390 +Train: [18] [5300/6250] eta: 0:02:08 lr: 0.000119 grad: 0.0585 (0.0645) loss: 0.8397 (0.8379) time: 0.1232 data: 0.0432 max mem: 9390 +Train: [18] [5400/6250] eta: 0:01:54 lr: 0.000119 grad: 0.0597 (0.0645) loss: 0.8446 (0.8379) time: 0.1360 data: 0.0601 max mem: 9390 +Train: [18] [5500/6250] eta: 0:01:41 lr: 0.000119 grad: 0.0624 (0.0645) loss: 0.8375 (0.8379) time: 0.1634 data: 0.0752 max mem: 9390 +Train: [18] [5600/6250] eta: 0:01:27 lr: 0.000119 grad: 0.0633 (0.0645) loss: 0.8403 (0.8379) time: 0.1304 data: 0.0518 max mem: 9390 +Train: [18] [5700/6250] eta: 0:01:14 lr: 0.000119 grad: 0.0618 (0.0645) loss: 0.8375 (0.8378) time: 0.1353 data: 0.0569 max mem: 9390 +Train: [18] [5800/6250] eta: 0:01:00 lr: 0.000118 grad: 0.0602 (0.0645) loss: 0.8334 (0.8378) time: 0.1070 data: 0.0264 max mem: 9390 +Train: [18] [5900/6250] eta: 0:00:47 lr: 0.000118 grad: 0.0612 (0.0645) loss: 0.8346 (0.8377) time: 0.1370 data: 0.0622 max mem: 9390 +Train: [18] [6000/6250] eta: 0:00:33 lr: 0.000118 grad: 0.0640 (0.0645) loss: 0.8332 (0.8377) time: 0.1292 data: 0.0478 max mem: 9390 +Train: [18] [6100/6250] eta: 0:00:20 lr: 0.000118 grad: 0.0624 (0.0645) loss: 0.8346 (0.8377) time: 0.1248 data: 0.0456 max mem: 9390 +Train: [18] [6200/6250] eta: 0:00:06 lr: 0.000118 grad: 0.0609 (0.0644) loss: 0.8383 (0.8377) time: 0.1333 data: 0.0577 max mem: 9390 +Train: [18] [6249/6250] eta: 0:00:00 lr: 0.000118 grad: 0.0618 (0.0644) loss: 0.8367 (0.8377) time: 0.1199 data: 0.0374 max mem: 9390 +Train: [18] Total time: 0:14:05 (0.1352 s / it) +Averaged stats: lr: 0.000118 grad: 0.0618 (0.0644) loss: 0.8367 (0.8377) +Eval (hcp-train-subset): [18] [ 0/62] eta: 0:03:41 loss: 0.8570 (0.8570) time: 3.5654 data: 3.5034 max mem: 9390 +Eval (hcp-train-subset): [18] [61/62] eta: 0:00:00 loss: 0.8446 (0.8457) time: 0.1935 data: 0.1674 max mem: 9390 +Eval (hcp-train-subset): [18] Total time: 0:00:14 (0.2279 s / it) +Averaged stats (hcp-train-subset): loss: 0.8446 (0.8457) +Eval (hcp-val): [18] [ 0/62] eta: 0:03:16 loss: 0.8368 (0.8368) time: 3.1744 data: 3.0901 max mem: 9390 +Eval (hcp-val): [18] [61/62] eta: 0:00:00 loss: 0.8413 (0.8410) time: 0.1429 data: 0.1160 max mem: 9390 +Eval (hcp-val): [18] Total time: 0:00:12 (0.2032 s / it) +Averaged stats (hcp-val): loss: 0.8413 (0.8410) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +Train: [19] [ 0/6250] eta: 9:54:30 lr: 0.000118 grad: 0.0805 (0.0805) loss: 0.7666 (0.7666) time: 5.7073 data: 5.6166 max mem: 9390 +Train: [19] [ 100/6250] eta: 0:18:59 lr: 0.000118 grad: 0.0615 (0.0724) loss: 0.8311 (0.8331) time: 0.1284 data: 0.0510 max mem: 9390 +Train: [19] [ 200/6250] eta: 0:16:18 lr: 0.000118 grad: 0.0604 (0.0707) loss: 0.8364 (0.8344) time: 0.1237 data: 0.0449 max mem: 9390 +Train: [19] [ 300/6250] eta: 0:15:03 lr: 0.000118 grad: 0.0591 (0.0683) loss: 0.8398 (0.8349) time: 0.1326 data: 0.0471 max mem: 9390 +Train: [19] [ 400/6250] eta: 0:14:18 lr: 0.000118 grad: 0.0582 (0.0663) loss: 0.8379 (0.8360) time: 0.1283 data: 0.0473 max mem: 9390 +Train: [19] [ 500/6250] eta: 0:13:31 lr: 0.000118 grad: 0.0614 (0.0653) loss: 0.8421 (0.8371) time: 0.1242 data: 0.0397 max mem: 9390 +Train: [19] [ 600/6250] eta: 0:13:04 lr: 0.000118 grad: 0.0573 (0.0645) loss: 0.8395 (0.8379) time: 0.1311 data: 0.0543 max mem: 9390 +Train: [19] [ 700/6250] eta: 0:12:37 lr: 0.000118 grad: 0.0642 (0.0643) loss: 0.8389 (0.8381) time: 0.1284 data: 0.0420 max mem: 9390 +Train: [19] [ 800/6250] eta: 0:12:17 lr: 0.000118 grad: 0.0614 (0.0642) loss: 0.8389 (0.8384) time: 0.1412 data: 0.0581 max mem: 9390 +Train: [19] [ 900/6250] eta: 0:12:09 lr: 0.000118 grad: 0.0615 (0.0639) loss: 0.8404 (0.8386) time: 0.1618 data: 0.0757 max mem: 9390 +Train: [19] [1000/6250] eta: 0:11:59 lr: 0.000118 grad: 0.0581 (0.0639) loss: 0.8401 (0.8388) time: 0.1306 data: 0.0445 max mem: 9390 +Train: [19] [1100/6250] eta: 0:11:47 lr: 0.000118 grad: 0.0674 (0.0640) loss: 0.8346 (0.8387) time: 0.1480 data: 0.0694 max mem: 9390 +Train: [19] [1200/6250] eta: 0:11:31 lr: 0.000118 grad: 0.0639 (0.0640) loss: 0.8392 (0.8387) time: 0.1298 data: 0.0527 max mem: 9390 +Train: [19] [1300/6250] eta: 0:11:19 lr: 0.000118 grad: 0.0707 (0.0640) loss: 0.8365 (0.8386) time: 0.1155 data: 0.0414 max mem: 9390 +Train: [19] [1400/6250] eta: 0:11:08 lr: 0.000118 grad: 0.0587 (0.0640) loss: 0.8401 (0.8386) time: 0.1270 data: 0.0446 max mem: 9390 +Train: [19] [1500/6250] eta: 0:10:55 lr: 0.000118 grad: 0.0609 (0.0640) loss: 0.8427 (0.8387) time: 0.1556 data: 0.0757 max mem: 9390 +Train: [19] [1600/6250] eta: 0:10:41 lr: 0.000118 grad: 0.0621 (0.0639) loss: 0.8366 (0.8386) time: 0.1465 data: 0.0660 max mem: 9390 +Train: [19] [1700/6250] eta: 0:10:27 lr: 0.000118 grad: 0.0629 (0.0639) loss: 0.8396 (0.8386) time: 0.1250 data: 0.0487 max mem: 9390 +Train: [19] [1800/6250] eta: 0:10:11 lr: 0.000118 grad: 0.0601 (0.0640) loss: 0.8364 (0.8386) time: 0.1339 data: 0.0531 max mem: 9390 +Train: [19] [1900/6250] eta: 0:09:57 lr: 0.000118 grad: 0.0626 (0.0639) loss: 0.8312 (0.8386) time: 0.1394 data: 0.0624 max mem: 9390 +Train: [19] [2000/6250] eta: 0:09:43 lr: 0.000118 grad: 0.0601 (0.0640) loss: 0.8373 (0.8385) time: 0.1352 data: 0.0557 max mem: 9390 +Train: [19] [2100/6250] eta: 0:09:29 lr: 0.000118 grad: 0.0644 (0.0641) loss: 0.8323 (0.8384) time: 0.1086 data: 0.0298 max mem: 9390 +Train: [19] [2200/6250] eta: 0:09:15 lr: 0.000118 grad: 0.0616 (0.0641) loss: 0.8388 (0.8384) time: 0.1470 data: 0.0710 max mem: 9390 +Train: [19] [2300/6250] eta: 0:09:01 lr: 0.000118 grad: 0.0583 (0.0641) loss: 0.8460 (0.8384) time: 0.1454 data: 0.0639 max mem: 9390 +Train: [19] [2400/6250] eta: 0:08:47 lr: 0.000118 grad: 0.0646 (0.0641) loss: 0.8343 (0.8384) time: 0.1390 data: 0.0599 max mem: 9390 +Train: [19] [2500/6250] eta: 0:08:34 lr: 0.000118 grad: 0.0702 (0.0643) loss: 0.8397 (0.8384) time: 0.1361 data: 0.0578 max mem: 9390 +Train: [19] [2600/6250] eta: 0:08:19 lr: 0.000118 grad: 0.0614 (0.0644) loss: 0.8414 (0.8384) time: 0.1276 data: 0.0519 max mem: 9390 +Train: [19] [2700/6250] eta: 0:08:04 lr: 0.000118 grad: 0.0635 (0.0643) loss: 0.8347 (0.8384) time: 0.1148 data: 0.0311 max mem: 9390 +Train: [19] [2800/6250] eta: 0:07:50 lr: 0.000118 grad: 0.0609 (0.0644) loss: 0.8439 (0.8384) time: 0.1454 data: 0.0709 max mem: 9390 +Train: [19] [2900/6250] eta: 0:07:36 lr: 0.000118 grad: 0.0617 (0.0644) loss: 0.8409 (0.8385) time: 0.1273 data: 0.0527 max mem: 9390 +Train: [19] [3000/6250] eta: 0:07:22 lr: 0.000118 grad: 0.0647 (0.0643) loss: 0.8387 (0.8385) time: 0.1255 data: 0.0398 max mem: 9390 +Train: [19] [3100/6250] eta: 0:07:09 lr: 0.000118 grad: 0.0623 (0.0643) loss: 0.8411 (0.8385) time: 0.1513 data: 0.0746 max mem: 9390 +Train: [19] [3200/6250] eta: 0:06:56 lr: 0.000118 grad: 0.0623 (0.0644) loss: 0.8445 (0.8386) time: 0.1355 data: 0.0498 max mem: 9390 +Train: [19] [3300/6250] eta: 0:06:42 lr: 0.000118 grad: 0.0585 (0.0643) loss: 0.8387 (0.8386) time: 0.1328 data: 0.0495 max mem: 9390 +Train: [19] [3400/6250] eta: 0:06:29 lr: 0.000118 grad: 0.0633 (0.0643) loss: 0.8355 (0.8386) time: 0.1345 data: 0.0594 max mem: 9390 +Train: [19] [3500/6250] eta: 0:06:15 lr: 0.000118 grad: 0.0644 (0.0644) loss: 0.8364 (0.8385) time: 0.1154 data: 0.0346 max mem: 9390 +Train: [19] [3600/6250] eta: 0:06:01 lr: 0.000118 grad: 0.0630 (0.0644) loss: 0.8345 (0.8384) time: 0.1353 data: 0.0556 max mem: 9390 +Train: [19] [3700/6250] eta: 0:05:48 lr: 0.000118 grad: 0.0648 (0.0644) loss: 0.8371 (0.8383) time: 0.1322 data: 0.0562 max mem: 9390 +Train: [19] [3800/6250] eta: 0:05:34 lr: 0.000118 grad: 0.0599 (0.0645) loss: 0.8354 (0.8382) time: 0.1365 data: 0.0566 max mem: 9390 +Train: [19] [3900/6250] eta: 0:05:20 lr: 0.000118 grad: 0.0638 (0.0645) loss: 0.8313 (0.8381) time: 0.1133 data: 0.0314 max mem: 9390 +Train: [19] [4000/6250] eta: 0:05:06 lr: 0.000118 grad: 0.0675 (0.0646) loss: 0.8308 (0.8379) time: 0.1448 data: 0.0617 max mem: 9390 +Train: [19] [4100/6250] eta: 0:04:53 lr: 0.000118 grad: 0.0630 (0.0646) loss: 0.8278 (0.8378) time: 0.1207 data: 0.0391 max mem: 9390 +Train: [19] [4200/6250] eta: 0:04:39 lr: 0.000118 grad: 0.0650 (0.0646) loss: 0.8387 (0.8377) time: 0.1218 data: 0.0482 max mem: 9390 +Train: [19] [4300/6250] eta: 0:04:25 lr: 0.000118 grad: 0.0604 (0.0647) loss: 0.8343 (0.8376) time: 0.1251 data: 0.0519 max mem: 9390 +Train: [19] [4400/6250] eta: 0:04:11 lr: 0.000118 grad: 0.0623 (0.0646) loss: 0.8337 (0.8375) time: 0.1226 data: 0.0421 max mem: 9390 +Train: [19] [4500/6250] eta: 0:03:57 lr: 0.000118 grad: 0.0634 (0.0646) loss: 0.8346 (0.8374) time: 0.1452 data: 0.0689 max mem: 9390 +Train: [19] [4600/6250] eta: 0:03:44 lr: 0.000118 grad: 0.0646 (0.0646) loss: 0.8296 (0.8373) time: 0.1484 data: 0.0731 max mem: 9390 +Train: [19] [4700/6250] eta: 0:03:30 lr: 0.000118 grad: 0.0618 (0.0646) loss: 0.8274 (0.8371) time: 0.1239 data: 0.0463 max mem: 9390 +Train: [19] [4800/6250] eta: 0:03:16 lr: 0.000118 grad: 0.0642 (0.0646) loss: 0.8314 (0.8370) time: 0.1555 data: 0.0549 max mem: 9390 +Train: [19] [4900/6250] eta: 0:03:04 lr: 0.000118 grad: 0.0594 (0.0646) loss: 0.8399 (0.8369) time: 0.1408 data: 0.0583 max mem: 9390 +Train: [19] [5000/6250] eta: 0:02:50 lr: 0.000118 grad: 0.0612 (0.0646) loss: 0.8314 (0.8368) time: 0.0970 data: 0.0206 max mem: 9390 +Train: [19] [5100/6250] eta: 0:02:36 lr: 0.000118 grad: 0.0595 (0.0646) loss: 0.8367 (0.8367) time: 0.1314 data: 0.0544 max mem: 9390 +Train: [19] [5200/6250] eta: 0:02:22 lr: 0.000118 grad: 0.0616 (0.0646) loss: 0.8333 (0.8367) time: 0.1198 data: 0.0409 max mem: 9390 +Train: [19] [5300/6250] eta: 0:02:08 lr: 0.000118 grad: 0.0655 (0.0646) loss: 0.8312 (0.8366) time: 0.1338 data: 0.0532 max mem: 9390 +Train: [19] [5400/6250] eta: 0:01:55 lr: 0.000118 grad: 0.0688 (0.0647) loss: 0.8329 (0.8365) time: 0.1238 data: 0.0425 max mem: 9390 +Train: [19] [5500/6250] eta: 0:01:41 lr: 0.000118 grad: 0.0646 (0.0647) loss: 0.8354 (0.8364) time: 0.1404 data: 0.0622 max mem: 9390 +Train: [19] [5600/6250] eta: 0:01:28 lr: 0.000118 grad: 0.0678 (0.0648) loss: 0.8362 (0.8363) time: 0.1385 data: 0.0622 max mem: 9390 +Train: [19] [5700/6250] eta: 0:01:14 lr: 0.000118 grad: 0.0630 (0.0649) loss: 0.8315 (0.8362) time: 0.1400 data: 0.0662 max mem: 9390 +Train: [19] [5800/6250] eta: 0:01:01 lr: 0.000118 grad: 0.0636 (0.0649) loss: 0.8341 (0.8362) time: 0.1447 data: 0.0668 max mem: 9390 +Train: [19] [5900/6250] eta: 0:00:47 lr: 0.000118 grad: 0.0662 (0.0649) loss: 0.8283 (0.8361) time: 0.1261 data: 0.0430 max mem: 9390 +Train: [19] [6000/6250] eta: 0:00:33 lr: 0.000118 grad: 0.0644 (0.0649) loss: 0.8352 (0.8360) time: 0.1340 data: 0.0595 max mem: 9390 +Train: [19] [6100/6250] eta: 0:00:20 lr: 0.000117 grad: 0.0643 (0.0649) loss: 0.8322 (0.8360) time: 0.1337 data: 0.0542 max mem: 9390 +Train: [19] [6200/6250] eta: 0:00:06 lr: 0.000117 grad: 0.0622 (0.0650) loss: 0.8291 (0.8359) time: 0.1312 data: 0.0533 max mem: 9390 +Train: [19] [6249/6250] eta: 0:00:00 lr: 0.000117 grad: 0.0639 (0.0650) loss: 0.8325 (0.8359) time: 0.1610 data: 0.0791 max mem: 9390 +Train: [19] Total time: 0:14:09 (0.1360 s / it) +Averaged stats: lr: 0.000117 grad: 0.0639 (0.0650) loss: 0.8325 (0.8359) +Eval (hcp-train-subset): [19] [ 0/62] eta: 0:03:25 loss: 0.8551 (0.8551) time: 3.3164 data: 3.2315 max mem: 9390 +Eval (hcp-train-subset): [19] [61/62] eta: 0:00:00 loss: 0.8440 (0.8453) time: 0.1334 data: 0.1069 max mem: 9390 +Eval (hcp-train-subset): [19] Total time: 0:00:13 (0.2219 s / it) +Averaged stats (hcp-train-subset): loss: 0.8440 (0.8453) +Making plots (hcp-train-subset): example=22 +Eval (hcp-val): [19] [ 0/62] eta: 0:03:06 loss: 0.8364 (0.8364) time: 3.0130 data: 2.8874 max mem: 9390 +Eval (hcp-val): [19] [61/62] eta: 0:00:00 loss: 0.8399 (0.8408) time: 0.1499 data: 0.1250 max mem: 9390 +Eval (hcp-val): [19] Total time: 0:00:13 (0.2204 s / it) +Averaged stats (hcp-val): loss: 0.8399 (0.8408) +Making plots (hcp-val): example=26 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +Train: [20] [ 0/6250] eta: 8:26:51 lr: 0.000117 grad: 0.0521 (0.0521) loss: 0.8595 (0.8595) time: 4.8658 data: 4.7805 max mem: 9390 +Train: [20] [ 100/6250] eta: 0:18:57 lr: 0.000117 grad: 0.0668 (0.0755) loss: 0.8368 (0.8417) time: 0.1565 data: 0.0785 max mem: 9390 +Train: [20] [ 200/6250] eta: 0:16:20 lr: 0.000117 grad: 0.0638 (0.0744) loss: 0.8457 (0.8398) time: 0.1434 data: 0.0606 max mem: 9390 +Train: [20] [ 300/6250] eta: 0:15:06 lr: 0.000117 grad: 0.0639 (0.0709) loss: 0.8327 (0.8399) time: 0.1336 data: 0.0569 max mem: 9390 +Train: [20] [ 400/6250] eta: 0:14:17 lr: 0.000117 grad: 0.0664 (0.0697) loss: 0.8331 (0.8393) time: 0.1341 data: 0.0531 max mem: 9390 +Train: [20] [ 500/6250] eta: 0:13:36 lr: 0.000117 grad: 0.0649 (0.0697) loss: 0.8396 (0.8387) time: 0.1161 data: 0.0352 max mem: 9390 +Train: [20] [ 600/6250] eta: 0:13:04 lr: 0.000117 grad: 0.0650 (0.0690) loss: 0.8396 (0.8382) time: 0.1037 data: 0.0206 max mem: 9390 +Train: [20] [ 700/6250] eta: 0:12:38 lr: 0.000117 grad: 0.0648 (0.0685) loss: 0.8394 (0.8378) time: 0.1092 data: 0.0282 max mem: 9390 +Train: [20] [ 800/6250] eta: 0:12:14 lr: 0.000117 grad: 0.0642 (0.0680) loss: 0.8348 (0.8376) time: 0.1159 data: 0.0353 max mem: 9390 +Train: [20] [ 900/6250] eta: 0:11:51 lr: 0.000117 grad: 0.0642 (0.0676) loss: 0.8306 (0.8375) time: 0.1322 data: 0.0470 max mem: 9390 +Train: [20] [1000/6250] eta: 0:11:35 lr: 0.000117 grad: 0.0653 (0.0675) loss: 0.8299 (0.8372) time: 0.1342 data: 0.0533 max mem: 9390 +Train: [20] [1100/6250] eta: 0:11:19 lr: 0.000117 grad: 0.0632 (0.0672) loss: 0.8324 (0.8372) time: 0.1306 data: 0.0539 max mem: 9390 +Train: [20] [1200/6250] eta: 0:11:03 lr: 0.000117 grad: 0.0608 (0.0669) loss: 0.8324 (0.8370) time: 0.1188 data: 0.0396 max mem: 9390 +Train: [20] [1300/6250] eta: 0:10:51 lr: 0.000117 grad: 0.0643 (0.0668) loss: 0.8345 (0.8368) time: 0.1315 data: 0.0522 max mem: 9390 +Train: [20] [1400/6250] eta: 0:10:37 lr: 0.000117 grad: 0.0627 (0.0667) loss: 0.8322 (0.8367) time: 0.1258 data: 0.0410 max mem: 9390 +Train: [20] [1500/6250] eta: 0:10:28 lr: 0.000117 grad: 0.0667 (0.0665) loss: 0.8326 (0.8365) time: 0.1508 data: 0.0701 max mem: 9390 +Train: [20] [1600/6250] eta: 0:10:17 lr: 0.000117 grad: 0.0635 (0.0663) loss: 0.8326 (0.8364) time: 0.1045 data: 0.0270 max mem: 9390 +Train: [20] [1700/6250] eta: 0:10:04 lr: 0.000117 grad: 0.0592 (0.0662) loss: 0.8345 (0.8363) time: 0.1425 data: 0.0665 max mem: 9390 +Train: [20] [1800/6250] eta: 0:09:55 lr: 0.000117 grad: 0.0646 (0.0661) loss: 0.8392 (0.8363) time: 0.1856 data: 0.1058 max mem: 9390 +Train: [20] [1900/6250] eta: 0:09:41 lr: 0.000117 grad: 0.0653 (0.0661) loss: 0.8356 (0.8363) time: 0.1322 data: 0.0523 max mem: 9390 +Train: [20] [2000/6250] eta: 0:09:28 lr: 0.000117 grad: 0.0623 (0.0662) loss: 0.8425 (0.8364) time: 0.1445 data: 0.0670 max mem: 9390 +Train: [20] [2100/6250] eta: 0:09:16 lr: 0.000117 grad: 0.0680 (0.0662) loss: 0.8331 (0.8364) time: 0.1256 data: 0.0397 max mem: 9390 +Train: [20] [2200/6250] eta: 0:09:05 lr: 0.000117 grad: 0.0664 (0.0663) loss: 0.8312 (0.8365) time: 0.1356 data: 0.0592 max mem: 9390 +Train: [20] [2300/6250] eta: 0:08:52 lr: 0.000117 grad: 0.0633 (0.0662) loss: 0.8341 (0.8365) time: 0.1408 data: 0.0604 max mem: 9390 +Train: [20] [2400/6250] eta: 0:08:38 lr: 0.000117 grad: 0.0649 (0.0661) loss: 0.8344 (0.8364) time: 0.1202 data: 0.0374 max mem: 9390 +Train: [20] [2500/6250] eta: 0:08:25 lr: 0.000117 grad: 0.0617 (0.0661) loss: 0.8299 (0.8364) time: 0.1394 data: 0.0652 max mem: 9390 +Train: [20] [2600/6250] eta: 0:08:11 lr: 0.000117 grad: 0.0596 (0.0661) loss: 0.8359 (0.8364) time: 0.1397 data: 0.0614 max mem: 9390 +Train: [20] [2700/6250] eta: 0:07:58 lr: 0.000117 grad: 0.0627 (0.0660) loss: 0.8394 (0.8363) time: 0.1261 data: 0.0487 max mem: 9390 +Train: [20] [2800/6250] eta: 0:07:44 lr: 0.000117 grad: 0.0685 (0.0661) loss: 0.8331 (0.8363) time: 0.1211 data: 0.0450 max mem: 9390 +Train: [20] [2900/6250] eta: 0:07:31 lr: 0.000117 grad: 0.0597 (0.0661) loss: 0.8360 (0.8363) time: 0.1530 data: 0.0661 max mem: 9390 +Train: [20] [3000/6250] eta: 0:07:18 lr: 0.000117 grad: 0.0627 (0.0660) loss: 0.8389 (0.8363) time: 0.1173 data: 0.0413 max mem: 9390 +Train: [20] [3100/6250] eta: 0:07:05 lr: 0.000117 grad: 0.0590 (0.0660) loss: 0.8424 (0.8364) time: 0.1241 data: 0.0480 max mem: 9390 +Train: [20] [3200/6250] eta: 0:06:52 lr: 0.000117 grad: 0.0658 (0.0662) loss: 0.8332 (0.8363) time: 0.1596 data: 0.0782 max mem: 9390 +Train: [20] [3300/6250] eta: 0:06:38 lr: 0.000117 grad: 0.0589 (0.0661) loss: 0.8375 (0.8363) time: 0.1267 data: 0.0440 max mem: 9390 +Train: [20] [3400/6250] eta: 0:06:24 lr: 0.000117 grad: 0.0611 (0.0661) loss: 0.8362 (0.8363) time: 0.1544 data: 0.0723 max mem: 9390 +Train: [20] [3500/6250] eta: 0:06:11 lr: 0.000117 grad: 0.0628 (0.0660) loss: 0.8361 (0.8364) time: 0.1362 data: 0.0562 max mem: 9390 +Train: [20] [3600/6250] eta: 0:05:58 lr: 0.000117 grad: 0.0613 (0.0659) loss: 0.8391 (0.8364) time: 0.1476 data: 0.0749 max mem: 9390 +Train: [20] [3700/6250] eta: 0:05:44 lr: 0.000117 grad: 0.0651 (0.0659) loss: 0.8338 (0.8363) time: 0.1275 data: 0.0566 max mem: 9390 +Train: [20] [3800/6250] eta: 0:05:31 lr: 0.000117 grad: 0.0613 (0.0659) loss: 0.8368 (0.8363) time: 0.1340 data: 0.0473 max mem: 9390 +Train: [20] [3900/6250] eta: 0:05:17 lr: 0.000117 grad: 0.0645 (0.0659) loss: 0.8304 (0.8363) time: 0.1373 data: 0.0613 max mem: 9390 +Train: [20] [4000/6250] eta: 0:05:04 lr: 0.000117 grad: 0.0691 (0.0659) loss: 0.8373 (0.8364) time: 0.1588 data: 0.0858 max mem: 9390 +Train: [20] [4100/6250] eta: 0:04:50 lr: 0.000117 grad: 0.0604 (0.0658) loss: 0.8387 (0.8364) time: 0.1164 data: 0.0383 max mem: 9390 +Train: [20] [4200/6250] eta: 0:04:36 lr: 0.000117 grad: 0.0614 (0.0657) loss: 0.8361 (0.8364) time: 0.1273 data: 0.0480 max mem: 9390 +Train: [20] [4300/6250] eta: 0:04:23 lr: 0.000117 grad: 0.0627 (0.0657) loss: 0.8358 (0.8365) time: 0.1296 data: 0.0532 max mem: 9390 +Train: [20] [4400/6250] eta: 0:04:10 lr: 0.000117 grad: 0.0656 (0.0657) loss: 0.8332 (0.8365) time: 0.1280 data: 0.0510 max mem: 9390 +Train: [20] [4500/6250] eta: 0:03:56 lr: 0.000117 grad: 0.0604 (0.0657) loss: 0.8426 (0.8365) time: 0.1370 data: 0.0617 max mem: 9390 +Train: [20] [4600/6250] eta: 0:03:43 lr: 0.000117 grad: 0.0632 (0.0657) loss: 0.8397 (0.8365) time: 0.1300 data: 0.0505 max mem: 9390 +Train: [20] [4700/6250] eta: 0:03:30 lr: 0.000117 grad: 0.0642 (0.0657) loss: 0.8305 (0.8364) time: 0.1196 data: 0.0376 max mem: 9390 +Train: [20] [4800/6250] eta: 0:03:16 lr: 0.000117 grad: 0.0663 (0.0658) loss: 0.8333 (0.8363) time: 0.1414 data: 0.0610 max mem: 9390 +Train: [20] [4900/6250] eta: 0:03:02 lr: 0.000117 grad: 0.0602 (0.0659) loss: 0.8336 (0.8362) time: 0.1334 data: 0.0582 max mem: 9390 +Train: [20] [5000/6250] eta: 0:02:49 lr: 0.000117 grad: 0.0669 (0.0659) loss: 0.8324 (0.8362) time: 0.1156 data: 0.0387 max mem: 9390 +Train: [20] [5100/6250] eta: 0:02:35 lr: 0.000117 grad: 0.0717 (0.0660) loss: 0.8324 (0.8361) time: 0.1606 data: 0.0865 max mem: 9390 +Train: [20] [5200/6250] eta: 0:02:22 lr: 0.000117 grad: 0.0696 (0.0661) loss: 0.8330 (0.8360) time: 0.1230 data: 0.0444 max mem: 9390 +Train: [20] [5300/6250] eta: 0:02:08 lr: 0.000117 grad: 0.0607 (0.0661) loss: 0.8356 (0.8359) time: 0.1262 data: 0.0491 max mem: 9390 +Train: [20] [5400/6250] eta: 0:01:55 lr: 0.000117 grad: 0.0723 (0.0662) loss: 0.8325 (0.8359) time: 0.1309 data: 0.0573 max mem: 9390 +Train: [20] [5500/6250] eta: 0:01:41 lr: 0.000117 grad: 0.0637 (0.0663) loss: 0.8333 (0.8358) time: 0.1275 data: 0.0522 max mem: 9390 +Train: [20] [5600/6250] eta: 0:01:27 lr: 0.000117 grad: 0.0602 (0.0664) loss: 0.8375 (0.8357) time: 0.1316 data: 0.0525 max mem: 9390 +Train: [20] [5700/6250] eta: 0:01:14 lr: 0.000117 grad: 0.0627 (0.0664) loss: 0.8377 (0.8357) time: 0.1210 data: 0.0382 max mem: 9390 +Train: [20] [5800/6250] eta: 0:01:00 lr: 0.000117 grad: 0.0673 (0.0664) loss: 0.8355 (0.8357) time: 0.1412 data: 0.0598 max mem: 9390 +Train: [20] [5900/6250] eta: 0:00:47 lr: 0.000117 grad: 0.0636 (0.0665) loss: 0.8301 (0.8356) time: 0.1302 data: 0.0524 max mem: 9390 +Train: [20] [6000/6250] eta: 0:00:33 lr: 0.000116 grad: 0.0650 (0.0665) loss: 0.8362 (0.8356) time: 0.1277 data: 0.0476 max mem: 9390 +Train: [20] [6100/6250] eta: 0:00:20 lr: 0.000116 grad: 0.0660 (0.0665) loss: 0.8317 (0.8355) time: 0.1383 data: 0.0607 max mem: 9390 +Train: [20] [6200/6250] eta: 0:00:06 lr: 0.000116 grad: 0.0643 (0.0666) loss: 0.8346 (0.8355) time: 0.1309 data: 0.0513 max mem: 9390 +Train: [20] [6249/6250] eta: 0:00:00 lr: 0.000116 grad: 0.0642 (0.0666) loss: 0.8309 (0.8355) time: 0.1219 data: 0.0444 max mem: 9390 +Train: [20] Total time: 0:14:07 (0.1356 s / it) +Averaged stats: lr: 0.000116 grad: 0.0642 (0.0666) loss: 0.8309 (0.8355) +Eval (hcp-train-subset): [20] [ 0/62] eta: 0:04:31 loss: 0.8580 (0.8580) time: 4.3779 data: 4.3471 max mem: 9390 +Eval (hcp-train-subset): [20] [61/62] eta: 0:00:00 loss: 0.8462 (0.8452) time: 0.1177 data: 0.0928 max mem: 9390 +Eval (hcp-train-subset): [20] Total time: 0:00:13 (0.2200 s / it) +Averaged stats (hcp-train-subset): loss: 0.8462 (0.8452) +Eval (hcp-val): [20] [ 0/62] eta: 0:03:38 loss: 0.8390 (0.8390) time: 3.5287 data: 3.4466 max mem: 9390 +Eval (hcp-val): [20] [61/62] eta: 0:00:00 loss: 0.8392 (0.8414) time: 0.1363 data: 0.1100 max mem: 9390 +Eval (hcp-val): [20] Total time: 0:00:13 (0.2114 s / it) +Averaged stats (hcp-val): loss: 0.8392 (0.8414) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +Train: [21] [ 0/6250] eta: 7:50:28 lr: 0.000116 grad: 0.0794 (0.0794) loss: 0.8321 (0.8321) time: 4.5165 data: 4.3922 max mem: 9390 +Train: [21] [ 100/6250] eta: 0:18:34 lr: 0.000116 grad: 0.0668 (0.0748) loss: 0.8379 (0.8413) time: 0.1380 data: 0.0588 max mem: 9390 +Train: [21] [ 200/6250] eta: 0:15:56 lr: 0.000116 grad: 0.0575 (0.0726) loss: 0.8452 (0.8382) time: 0.1274 data: 0.0484 max mem: 9390 +Train: [21] [ 300/6250] eta: 0:14:53 lr: 0.000116 grad: 0.0667 (0.0714) loss: 0.8274 (0.8377) time: 0.1295 data: 0.0530 max mem: 9390 +Train: [21] [ 400/6250] eta: 0:13:59 lr: 0.000116 grad: 0.0635 (0.0711) loss: 0.8376 (0.8365) time: 0.1198 data: 0.0394 max mem: 9390 +Train: [21] [ 500/6250] eta: 0:13:22 lr: 0.000116 grad: 0.0633 (0.0709) loss: 0.8440 (0.8365) time: 0.1344 data: 0.0528 max mem: 9390 +Train: [21] [ 600/6250] eta: 0:12:48 lr: 0.000116 grad: 0.0590 (0.0697) loss: 0.8392 (0.8368) time: 0.1229 data: 0.0456 max mem: 9390 +Train: [21] [ 700/6250] eta: 0:12:25 lr: 0.000116 grad: 0.0568 (0.0688) loss: 0.8422 (0.8371) time: 0.1240 data: 0.0413 max mem: 9390 +Train: [21] [ 800/6250] eta: 0:12:05 lr: 0.000116 grad: 0.0618 (0.0680) loss: 0.8371 (0.8373) time: 0.1409 data: 0.0613 max mem: 9390 +Train: [21] [ 900/6250] eta: 0:12:10 lr: 0.000116 grad: 0.0624 (0.0675) loss: 0.8391 (0.8375) time: 0.1581 data: 0.0754 max mem: 9390 +Train: [21] [1000/6250] eta: 0:12:12 lr: 0.000116 grad: 0.0667 (0.0670) loss: 0.8387 (0.8376) time: 0.1735 data: 0.0943 max mem: 9390 +Train: [21] [1100/6250] eta: 0:12:02 lr: 0.000116 grad: 0.0585 (0.0667) loss: 0.8416 (0.8375) time: 0.1397 data: 0.0604 max mem: 9390 +Train: [21] [1200/6250] eta: 0:11:47 lr: 0.000116 grad: 0.0624 (0.0664) loss: 0.8395 (0.8376) time: 0.1335 data: 0.0536 max mem: 9390 +Train: [21] [1300/6250] eta: 0:11:37 lr: 0.000116 grad: 0.0648 (0.0663) loss: 0.8356 (0.8375) time: 0.1939 data: 0.1166 max mem: 9390 +Train: [21] [1400/6250] eta: 0:11:23 lr: 0.000116 grad: 0.0640 (0.0662) loss: 0.8401 (0.8375) time: 0.1152 data: 0.0370 max mem: 9390 +Train: [21] [1500/6250] eta: 0:11:09 lr: 0.000116 grad: 0.0683 (0.0663) loss: 0.8367 (0.8373) time: 0.1411 data: 0.0574 max mem: 9390 +Train: [21] [1600/6250] eta: 0:10:56 lr: 0.000116 grad: 0.0664 (0.0664) loss: 0.8371 (0.8371) time: 0.1486 data: 0.0737 max mem: 9390 +Train: [21] [1700/6250] eta: 0:10:41 lr: 0.000116 grad: 0.0617 (0.0663) loss: 0.8333 (0.8369) time: 0.1353 data: 0.0535 max mem: 9390 +Train: [21] [1800/6250] eta: 0:10:26 lr: 0.000116 grad: 0.0609 (0.0663) loss: 0.8377 (0.8368) time: 0.1350 data: 0.0555 max mem: 9390 +Train: [21] [1900/6250] eta: 0:10:12 lr: 0.000116 grad: 0.0598 (0.0663) loss: 0.8374 (0.8367) time: 0.1452 data: 0.0680 max mem: 9390 +Train: [21] [2000/6250] eta: 0:09:57 lr: 0.000116 grad: 0.0702 (0.0669) loss: 0.8327 (0.8367) time: 0.1379 data: 0.0589 max mem: 9390 +Train: [21] [2100/6250] eta: 0:09:43 lr: 0.000116 grad: 0.0633 (0.0670) loss: 0.8330 (0.8366) time: 0.1529 data: 0.0781 max mem: 9390 +Train: [21] [2200/6250] eta: 0:09:27 lr: 0.000116 grad: 0.0625 (0.0670) loss: 0.8326 (0.8365) time: 0.1292 data: 0.0399 max mem: 9390 +Train: [21] [2300/6250] eta: 0:09:13 lr: 0.000116 grad: 0.0631 (0.0669) loss: 0.8385 (0.8364) time: 0.1419 data: 0.0644 max mem: 9390 +Train: [21] [2400/6250] eta: 0:08:58 lr: 0.000116 grad: 0.0658 (0.0668) loss: 0.8384 (0.8364) time: 0.1251 data: 0.0355 max mem: 9390 +Train: [21] [2500/6250] eta: 0:08:44 lr: 0.000116 grad: 0.0685 (0.0669) loss: 0.8401 (0.8364) time: 0.1540 data: 0.0779 max mem: 9390 +Train: [21] [2600/6250] eta: 0:08:30 lr: 0.000116 grad: 0.0648 (0.0670) loss: 0.8348 (0.8363) time: 0.1292 data: 0.0537 max mem: 9390 +Train: [21] [2700/6250] eta: 0:08:14 lr: 0.000116 grad: 0.0635 (0.0669) loss: 0.8329 (0.8363) time: 0.1245 data: 0.0459 max mem: 9390 +Train: [21] [2800/6250] eta: 0:08:01 lr: 0.000116 grad: 0.0622 (0.0668) loss: 0.8383 (0.8364) time: 0.1487 data: 0.0700 max mem: 9390 +Train: [21] [2900/6250] eta: 0:07:47 lr: 0.000116 grad: 0.0607 (0.0667) loss: 0.8418 (0.8364) time: 0.1311 data: 0.0521 max mem: 9390 +Train: [21] [3000/6250] eta: 0:07:33 lr: 0.000116 grad: 0.0622 (0.0666) loss: 0.8348 (0.8363) time: 0.1399 data: 0.0613 max mem: 9390 +Train: [21] [3100/6250] eta: 0:07:18 lr: 0.000116 grad: 0.0628 (0.0665) loss: 0.8263 (0.8363) time: 0.1405 data: 0.0469 max mem: 9390 +Train: [21] [3200/6250] eta: 0:07:04 lr: 0.000116 grad: 0.0653 (0.0665) loss: 0.8376 (0.8363) time: 0.1475 data: 0.0760 max mem: 9390 +Train: [21] [3300/6250] eta: 0:06:50 lr: 0.000116 grad: 0.0635 (0.0665) loss: 0.8318 (0.8363) time: 0.1463 data: 0.0691 max mem: 9390 +Train: [21] [3400/6250] eta: 0:06:36 lr: 0.000116 grad: 0.0618 (0.0664) loss: 0.8392 (0.8363) time: 0.1357 data: 0.0549 max mem: 9390 +Train: [21] [3500/6250] eta: 0:06:22 lr: 0.000116 grad: 0.0659 (0.0665) loss: 0.8362 (0.8363) time: 0.1590 data: 0.0828 max mem: 9390 +Train: [21] [3600/6250] eta: 0:06:07 lr: 0.000116 grad: 0.0599 (0.0665) loss: 0.8369 (0.8362) time: 0.1291 data: 0.0536 max mem: 9390 +Train: [21] [3700/6250] eta: 0:05:53 lr: 0.000116 grad: 0.0645 (0.0666) loss: 0.8382 (0.8362) time: 0.1340 data: 0.0538 max mem: 9390 +Train: [21] [3800/6250] eta: 0:05:39 lr: 0.000116 grad: 0.0623 (0.0667) loss: 0.8385 (0.8362) time: 0.1355 data: 0.0527 max mem: 9390 +Train: [21] [3900/6250] eta: 0:05:25 lr: 0.000116 grad: 0.0673 (0.0667) loss: 0.8325 (0.8361) time: 0.1317 data: 0.0503 max mem: 9390 +Train: [21] [4000/6250] eta: 0:05:10 lr: 0.000116 grad: 0.0670 (0.0668) loss: 0.8290 (0.8360) time: 0.1440 data: 0.0603 max mem: 9390 +Train: [21] [4100/6250] eta: 0:04:57 lr: 0.000116 grad: 0.0657 (0.0668) loss: 0.8372 (0.8359) time: 0.1271 data: 0.0491 max mem: 9390 +Train: [21] [4200/6250] eta: 0:04:43 lr: 0.000116 grad: 0.0650 (0.0668) loss: 0.8384 (0.8359) time: 0.1357 data: 0.0494 max mem: 9390 +Train: [21] [4300/6250] eta: 0:04:29 lr: 0.000116 grad: 0.0652 (0.0668) loss: 0.8321 (0.8358) time: 0.1424 data: 0.0667 max mem: 9390 +Train: [21] [4400/6250] eta: 0:04:15 lr: 0.000116 grad: 0.0644 (0.0668) loss: 0.8364 (0.8358) time: 0.1463 data: 0.0696 max mem: 9390 +Train: [21] [4500/6250] eta: 0:04:01 lr: 0.000116 grad: 0.0652 (0.0668) loss: 0.8346 (0.8358) time: 0.1464 data: 0.0701 max mem: 9390 +Train: [21] [4600/6250] eta: 0:03:47 lr: 0.000116 grad: 0.0669 (0.0668) loss: 0.8379 (0.8358) time: 0.1538 data: 0.0724 max mem: 9390 +Train: [21] [4700/6250] eta: 0:03:33 lr: 0.000116 grad: 0.0630 (0.0668) loss: 0.8342 (0.8358) time: 0.1255 data: 0.0485 max mem: 9390 +Train: [21] [4800/6250] eta: 0:03:19 lr: 0.000116 grad: 0.0671 (0.0668) loss: 0.8321 (0.8358) time: 0.1379 data: 0.0650 max mem: 9390 +Train: [21] [4900/6250] eta: 0:03:05 lr: 0.000116 grad: 0.0666 (0.0668) loss: 0.8370 (0.8358) time: 0.1532 data: 0.0777 max mem: 9390 +Train: [21] [5000/6250] eta: 0:02:52 lr: 0.000116 grad: 0.0619 (0.0667) loss: 0.8367 (0.8358) time: 0.1300 data: 0.0522 max mem: 9390 +Train: [21] [5100/6250] eta: 0:02:38 lr: 0.000116 grad: 0.0600 (0.0667) loss: 0.8438 (0.8358) time: 0.1342 data: 0.0539 max mem: 9390 +Train: [21] [5200/6250] eta: 0:02:24 lr: 0.000116 grad: 0.0647 (0.0667) loss: 0.8359 (0.8358) time: 0.1257 data: 0.0510 max mem: 9390 +Train: [21] [5300/6250] eta: 0:02:10 lr: 0.000116 grad: 0.0632 (0.0667) loss: 0.8304 (0.8358) time: 0.1408 data: 0.0658 max mem: 9390 +Train: [21] [5400/6250] eta: 0:01:56 lr: 0.000116 grad: 0.0633 (0.0668) loss: 0.8380 (0.8358) time: 0.1138 data: 0.0324 max mem: 9390 +Train: [21] [5500/6250] eta: 0:01:42 lr: 0.000116 grad: 0.0673 (0.0668) loss: 0.8370 (0.8358) time: 0.1348 data: 0.0525 max mem: 9390 +Train: [21] [5600/6250] eta: 0:01:29 lr: 0.000115 grad: 0.0625 (0.0668) loss: 0.8380 (0.8358) time: 0.1509 data: 0.0768 max mem: 9390 +Train: [21] [5700/6250] eta: 0:01:15 lr: 0.000115 grad: 0.0704 (0.0668) loss: 0.8370 (0.8357) time: 0.1349 data: 0.0606 max mem: 9390 +Train: [21] [5800/6250] eta: 0:01:01 lr: 0.000115 grad: 0.0610 (0.0668) loss: 0.8369 (0.8357) time: 0.1309 data: 0.0546 max mem: 9390 +Train: [21] [5900/6250] eta: 0:00:47 lr: 0.000115 grad: 0.0610 (0.0668) loss: 0.8327 (0.8356) time: 0.1448 data: 0.0606 max mem: 9390 +Train: [21] [6000/6250] eta: 0:00:34 lr: 0.000115 grad: 0.0667 (0.0668) loss: 0.8291 (0.8356) time: 0.1222 data: 0.0431 max mem: 9390 +Train: [21] [6100/6250] eta: 0:00:20 lr: 0.000115 grad: 0.0631 (0.0668) loss: 0.8375 (0.8356) time: 0.1209 data: 0.0369 max mem: 9390 +Train: [21] [6200/6250] eta: 0:00:06 lr: 0.000115 grad: 0.0647 (0.0667) loss: 0.8367 (0.8356) time: 0.1394 data: 0.0616 max mem: 9390 +Train: [21] [6249/6250] eta: 0:00:00 lr: 0.000115 grad: 0.0596 (0.0667) loss: 0.8402 (0.8356) time: 0.1461 data: 0.0702 max mem: 9390 +Train: [21] Total time: 0:14:17 (0.1371 s / it) +Averaged stats: lr: 0.000115 grad: 0.0596 (0.0667) loss: 0.8402 (0.8356) +Eval (hcp-train-subset): [21] [ 0/62] eta: 0:03:42 loss: 0.8573 (0.8573) time: 3.5945 data: 3.5242 max mem: 9390 +Eval (hcp-train-subset): [21] [61/62] eta: 0:00:00 loss: 0.8457 (0.8450) time: 0.1408 data: 0.1159 max mem: 9390 +Eval (hcp-train-subset): [21] Total time: 0:00:13 (0.2157 s / it) +Averaged stats (hcp-train-subset): loss: 0.8457 (0.8450) +Eval (hcp-val): [21] [ 0/62] eta: 0:03:04 loss: 0.8398 (0.8398) time: 2.9814 data: 2.9108 max mem: 9390 +Eval (hcp-val): [21] [61/62] eta: 0:00:00 loss: 0.8403 (0.8406) time: 0.0947 data: 0.0701 max mem: 9390 +Eval (hcp-val): [21] Total time: 0:00:13 (0.2109 s / it) +Averaged stats (hcp-val): loss: 0.8403 (0.8406) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +Train: [22] [ 0/6250] eta: 7:58:38 lr: 0.000115 grad: 0.0419 (0.0419) loss: 0.8672 (0.8672) time: 4.5950 data: 4.3857 max mem: 9390 +Train: [22] [ 100/6250] eta: 0:18:36 lr: 0.000115 grad: 0.0688 (0.0678) loss: 0.8358 (0.8402) time: 0.1461 data: 0.0698 max mem: 9390 +Train: [22] [ 200/6250] eta: 0:15:58 lr: 0.000115 grad: 0.0642 (0.0685) loss: 0.8451 (0.8389) time: 0.1375 data: 0.0606 max mem: 9390 +Train: [22] [ 300/6250] eta: 0:14:54 lr: 0.000115 grad: 0.0589 (0.0669) loss: 0.8538 (0.8402) time: 0.1256 data: 0.0395 max mem: 9390 +Train: [22] [ 400/6250] eta: 0:13:54 lr: 0.000115 grad: 0.0614 (0.0662) loss: 0.8468 (0.8409) time: 0.1226 data: 0.0357 max mem: 9390 +Train: [22] [ 500/6250] eta: 0:13:17 lr: 0.000115 grad: 0.0577 (0.0662) loss: 0.8413 (0.8408) time: 0.1332 data: 0.0495 max mem: 9390 +Train: [22] [ 600/6250] eta: 0:12:44 lr: 0.000115 grad: 0.0583 (0.0658) loss: 0.8379 (0.8406) time: 0.1167 data: 0.0215 max mem: 9390 +Train: [22] [ 700/6250] eta: 0:12:23 lr: 0.000115 grad: 0.0645 (0.0656) loss: 0.8366 (0.8404) time: 0.1377 data: 0.0556 max mem: 9390 +Train: [22] [ 800/6250] eta: 0:12:13 lr: 0.000115 grad: 0.0601 (0.0652) loss: 0.8379 (0.8402) time: 0.1275 data: 0.0508 max mem: 9390 +Train: [22] [ 900/6250] eta: 0:12:19 lr: 0.000115 grad: 0.0598 (0.0649) loss: 0.8376 (0.8402) time: 0.1692 data: 0.0832 max mem: 9390 +Train: [22] [1000/6250] eta: 0:12:15 lr: 0.000115 grad: 0.0603 (0.0648) loss: 0.8379 (0.8401) time: 0.1684 data: 0.0849 max mem: 9390 +Train: [22] [1100/6250] eta: 0:12:06 lr: 0.000115 grad: 0.0609 (0.0646) loss: 0.8377 (0.8401) time: 0.1502 data: 0.0725 max mem: 9390 +Train: [22] [1200/6250] eta: 0:11:52 lr: 0.000115 grad: 0.0592 (0.0645) loss: 0.8395 (0.8400) time: 0.1229 data: 0.0424 max mem: 9390 +Train: [22] [1300/6250] eta: 0:11:36 lr: 0.000115 grad: 0.0653 (0.0644) loss: 0.8293 (0.8397) time: 0.1387 data: 0.0595 max mem: 9390 +Train: [22] [1400/6250] eta: 0:11:18 lr: 0.000115 grad: 0.0631 (0.0646) loss: 0.8372 (0.8395) time: 0.1429 data: 0.0661 max mem: 9390 +Train: [22] [1500/6250] eta: 0:11:03 lr: 0.000115 grad: 0.0634 (0.0646) loss: 0.8356 (0.8393) time: 0.1577 data: 0.0809 max mem: 9390 +Train: [22] [1600/6250] eta: 0:10:48 lr: 0.000115 grad: 0.0631 (0.0647) loss: 0.8392 (0.8391) time: 0.1491 data: 0.0690 max mem: 9390 +Train: [22] [1700/6250] eta: 0:10:34 lr: 0.000115 grad: 0.0674 (0.0648) loss: 0.8309 (0.8389) time: 0.1583 data: 0.0823 max mem: 9390 +Train: [22] [1800/6250] eta: 0:10:21 lr: 0.000115 grad: 0.0594 (0.0649) loss: 0.8391 (0.8388) time: 0.1315 data: 0.0513 max mem: 9390 +Train: [22] [1900/6250] eta: 0:10:06 lr: 0.000115 grad: 0.0642 (0.0650) loss: 0.8351 (0.8386) time: 0.1368 data: 0.0637 max mem: 9390 +Train: [22] [2000/6250] eta: 0:09:53 lr: 0.000115 grad: 0.0632 (0.0651) loss: 0.8389 (0.8385) time: 0.1364 data: 0.0603 max mem: 9390 +Train: [22] [2100/6250] eta: 0:09:38 lr: 0.000115 grad: 0.0649 (0.0651) loss: 0.8345 (0.8383) time: 0.1281 data: 0.0514 max mem: 9390 +Train: [22] [2200/6250] eta: 0:09:23 lr: 0.000115 grad: 0.0681 (0.0652) loss: 0.8303 (0.8382) time: 0.1387 data: 0.0572 max mem: 9390 +Train: [22] [2300/6250] eta: 0:09:09 lr: 0.000115 grad: 0.0649 (0.0653) loss: 0.8365 (0.8380) time: 0.1310 data: 0.0571 max mem: 9390 +Train: [22] [2400/6250] eta: 0:08:55 lr: 0.000115 grad: 0.0629 (0.0653) loss: 0.8384 (0.8380) time: 0.1483 data: 0.0651 max mem: 9390 +Train: [22] [2500/6250] eta: 0:08:40 lr: 0.000115 grad: 0.0712 (0.0653) loss: 0.8322 (0.8379) time: 0.1264 data: 0.0505 max mem: 9390 +Train: [22] [2600/6250] eta: 0:08:26 lr: 0.000115 grad: 0.0661 (0.0654) loss: 0.8362 (0.8378) time: 0.1270 data: 0.0530 max mem: 9390 +Train: [22] [2700/6250] eta: 0:08:12 lr: 0.000115 grad: 0.0658 (0.0655) loss: 0.8289 (0.8377) time: 0.1419 data: 0.0648 max mem: 9390 +Train: [22] [2800/6250] eta: 0:07:58 lr: 0.000115 grad: 0.0621 (0.0655) loss: 0.8388 (0.8377) time: 0.1202 data: 0.0394 max mem: 9390 +Train: [22] [2900/6250] eta: 0:07:45 lr: 0.000115 grad: 0.0629 (0.0656) loss: 0.8396 (0.8376) time: 0.1242 data: 0.0369 max mem: 9390 +Train: [22] [3000/6250] eta: 0:07:30 lr: 0.000115 grad: 0.0633 (0.0656) loss: 0.8392 (0.8376) time: 0.1247 data: 0.0470 max mem: 9390 +Train: [22] [3100/6250] eta: 0:07:16 lr: 0.000115 grad: 0.0652 (0.0657) loss: 0.8369 (0.8375) time: 0.1342 data: 0.0579 max mem: 9390 +Train: [22] [3200/6250] eta: 0:07:02 lr: 0.000115 grad: 0.0653 (0.0658) loss: 0.8347 (0.8374) time: 0.1413 data: 0.0622 max mem: 9390 +Train: [22] [3300/6250] eta: 0:06:48 lr: 0.000115 grad: 0.0688 (0.0658) loss: 0.8319 (0.8373) time: 0.1268 data: 0.0463 max mem: 9390 +Train: [22] [3400/6250] eta: 0:06:34 lr: 0.000115 grad: 0.0673 (0.0659) loss: 0.8361 (0.8371) time: 0.1340 data: 0.0539 max mem: 9390 +Train: [22] [3500/6250] eta: 0:06:20 lr: 0.000115 grad: 0.0683 (0.0659) loss: 0.8318 (0.8369) time: 0.1312 data: 0.0448 max mem: 9390 +Train: [22] [3600/6250] eta: 0:06:06 lr: 0.000115 grad: 0.0621 (0.0659) loss: 0.8322 (0.8369) time: 0.1399 data: 0.0686 max mem: 9390 +Train: [22] [3700/6250] eta: 0:05:52 lr: 0.000115 grad: 0.0651 (0.0660) loss: 0.8345 (0.8368) time: 0.1455 data: 0.0696 max mem: 9390 +Train: [22] [3800/6250] eta: 0:05:38 lr: 0.000115 grad: 0.0651 (0.0660) loss: 0.8387 (0.8367) time: 0.1254 data: 0.0490 max mem: 9390 +Train: [22] [3900/6250] eta: 0:05:24 lr: 0.000115 grad: 0.0687 (0.0660) loss: 0.8307 (0.8367) time: 0.1255 data: 0.0467 max mem: 9390 +Train: [22] [4000/6250] eta: 0:05:10 lr: 0.000115 grad: 0.0649 (0.0660) loss: 0.8308 (0.8366) time: 0.1304 data: 0.0514 max mem: 9390 +Train: [22] [4100/6250] eta: 0:04:56 lr: 0.000115 grad: 0.0717 (0.0660) loss: 0.8300 (0.8365) time: 0.1359 data: 0.0590 max mem: 9390 +Train: [22] [4200/6250] eta: 0:04:43 lr: 0.000115 grad: 0.0628 (0.0660) loss: 0.8366 (0.8364) time: 0.1435 data: 0.0629 max mem: 9390 +Train: [22] [4300/6250] eta: 0:04:29 lr: 0.000115 grad: 0.0655 (0.0660) loss: 0.8357 (0.8364) time: 0.1397 data: 0.0572 max mem: 9390 +Train: [22] [4400/6250] eta: 0:04:15 lr: 0.000115 grad: 0.0625 (0.0660) loss: 0.8282 (0.8362) time: 0.1441 data: 0.0667 max mem: 9390 +Train: [22] [4500/6250] eta: 0:04:01 lr: 0.000115 grad: 0.0622 (0.0661) loss: 0.8364 (0.8361) time: 0.1331 data: 0.0586 max mem: 9390 +Train: [22] [4600/6250] eta: 0:03:47 lr: 0.000115 grad: 0.0666 (0.0661) loss: 0.8267 (0.8360) time: 0.1293 data: 0.0475 max mem: 9390 +Train: [22] [4700/6250] eta: 0:03:33 lr: 0.000115 grad: 0.0597 (0.0662) loss: 0.8356 (0.8360) time: 0.1415 data: 0.0621 max mem: 9390 +Train: [22] [4800/6250] eta: 0:03:19 lr: 0.000115 grad: 0.0575 (0.0661) loss: 0.8412 (0.8360) time: 0.1274 data: 0.0509 max mem: 9390 +Train: [22] [4900/6250] eta: 0:03:05 lr: 0.000114 grad: 0.0629 (0.0661) loss: 0.8346 (0.8360) time: 0.1382 data: 0.0452 max mem: 9390 +Train: [22] [5000/6250] eta: 0:02:51 lr: 0.000114 grad: 0.0622 (0.0661) loss: 0.8324 (0.8360) time: 0.1280 data: 0.0485 max mem: 9390 +Train: [22] [5100/6250] eta: 0:02:37 lr: 0.000114 grad: 0.0622 (0.0660) loss: 0.8425 (0.8360) time: 0.1547 data: 0.0764 max mem: 9390 +Train: [22] [5200/6250] eta: 0:02:23 lr: 0.000114 grad: 0.0623 (0.0661) loss: 0.8379 (0.8360) time: 0.1067 data: 0.0222 max mem: 9390 +Train: [22] [5300/6250] eta: 0:02:09 lr: 0.000114 grad: 0.0628 (0.0662) loss: 0.8398 (0.8360) time: 0.1306 data: 0.0533 max mem: 9390 +Train: [22] [5400/6250] eta: 0:01:56 lr: 0.000114 grad: 0.0607 (0.0662) loss: 0.8397 (0.8360) time: 0.1334 data: 0.0513 max mem: 9390 +Train: [22] [5500/6250] eta: 0:01:42 lr: 0.000114 grad: 0.0632 (0.0661) loss: 0.8405 (0.8360) time: 0.1251 data: 0.0452 max mem: 9390 +Train: [22] [5600/6250] eta: 0:01:28 lr: 0.000114 grad: 0.0654 (0.0661) loss: 0.8356 (0.8360) time: 0.1422 data: 0.0585 max mem: 9390 +Train: [22] [5700/6250] eta: 0:01:15 lr: 0.000114 grad: 0.0627 (0.0661) loss: 0.8352 (0.8360) time: 0.1490 data: 0.0654 max mem: 9390 +Train: [22] [5800/6250] eta: 0:01:01 lr: 0.000114 grad: 0.0637 (0.0661) loss: 0.8365 (0.8359) time: 0.1314 data: 0.0519 max mem: 9390 +Train: [22] [5900/6250] eta: 0:00:47 lr: 0.000114 grad: 0.0640 (0.0661) loss: 0.8333 (0.8359) time: 0.1027 data: 0.0239 max mem: 9390 +Train: [22] [6000/6250] eta: 0:00:34 lr: 0.000114 grad: 0.0666 (0.0662) loss: 0.8333 (0.8359) time: 0.1412 data: 0.0628 max mem: 9390 +Train: [22] [6100/6250] eta: 0:00:20 lr: 0.000114 grad: 0.0643 (0.0662) loss: 0.8385 (0.8358) time: 0.1375 data: 0.0580 max mem: 9390 +Train: [22] [6200/6250] eta: 0:00:06 lr: 0.000114 grad: 0.0651 (0.0662) loss: 0.8353 (0.8358) time: 0.1194 data: 0.0385 max mem: 9390 +Train: [22] [6249/6250] eta: 0:00:00 lr: 0.000114 grad: 0.0637 (0.0662) loss: 0.8343 (0.8358) time: 0.1442 data: 0.0711 max mem: 9390 +Train: [22] Total time: 0:14:15 (0.1369 s / it) +Averaged stats: lr: 0.000114 grad: 0.0637 (0.0662) loss: 0.8343 (0.8358) +Eval (hcp-train-subset): [22] [ 0/62] eta: 0:04:13 loss: 0.8556 (0.8556) time: 4.0936 data: 4.0437 max mem: 9390 +Eval (hcp-train-subset): [22] [61/62] eta: 0:00:00 loss: 0.8430 (0.8447) time: 0.1882 data: 0.1637 max mem: 9390 +Eval (hcp-train-subset): [22] Total time: 0:00:13 (0.2226 s / it) +Averaged stats (hcp-train-subset): loss: 0.8430 (0.8447) +Eval (hcp-val): [22] [ 0/62] eta: 0:04:19 loss: 0.8346 (0.8346) time: 4.1864 data: 4.1548 max mem: 9390 +Eval (hcp-val): [22] [61/62] eta: 0:00:00 loss: 0.8404 (0.8400) time: 0.1267 data: 0.0996 max mem: 9390 +Eval (hcp-val): [22] Total time: 0:00:13 (0.2104 s / it) +Averaged stats (hcp-val): loss: 0.8404 (0.8400) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +Train: [23] [ 0/6250] eta: 8:29:31 lr: 0.000114 grad: 0.1198 (0.1198) loss: 0.8633 (0.8633) time: 4.8914 data: 4.8031 max mem: 9390 +Train: [23] [ 100/6250] eta: 0:18:36 lr: 0.000114 grad: 0.0659 (0.0752) loss: 0.8411 (0.8389) time: 0.1195 data: 0.0377 max mem: 9390 +Train: [23] [ 200/6250] eta: 0:16:13 lr: 0.000114 grad: 0.0641 (0.0731) loss: 0.8267 (0.8356) time: 0.1459 data: 0.0636 max mem: 9390 +Train: [23] [ 300/6250] eta: 0:15:00 lr: 0.000114 grad: 0.0654 (0.0713) loss: 0.8366 (0.8352) time: 0.1338 data: 0.0455 max mem: 9390 +Train: [23] [ 400/6250] eta: 0:14:15 lr: 0.000114 grad: 0.0639 (0.0706) loss: 0.8339 (0.8344) time: 0.1241 data: 0.0432 max mem: 9390 +Train: [23] [ 500/6250] eta: 0:13:29 lr: 0.000114 grad: 0.0662 (0.0702) loss: 0.8340 (0.8337) time: 0.1168 data: 0.0258 max mem: 9390 +Train: [23] [ 600/6250] eta: 0:12:55 lr: 0.000114 grad: 0.0690 (0.0703) loss: 0.8288 (0.8330) time: 0.1188 data: 0.0288 max mem: 9390 +Train: [23] [ 700/6250] eta: 0:12:29 lr: 0.000114 grad: 0.0644 (0.0707) loss: 0.8333 (0.8329) time: 0.1131 data: 0.0299 max mem: 9390 +Train: [23] [ 800/6250] eta: 0:12:12 lr: 0.000114 grad: 0.0648 (0.0702) loss: 0.8306 (0.8328) time: 0.1530 data: 0.0757 max mem: 9390 +Train: [23] [ 900/6250] eta: 0:12:14 lr: 0.000114 grad: 0.0613 (0.0698) loss: 0.8312 (0.8329) time: 0.1872 data: 0.1049 max mem: 9390 +Train: [23] [1000/6250] eta: 0:12:21 lr: 0.000114 grad: 0.0619 (0.0693) loss: 0.8373 (0.8333) time: 0.1590 data: 0.0804 max mem: 9390 +Train: [23] [1100/6250] eta: 0:12:17 lr: 0.000114 grad: 0.0641 (0.0691) loss: 0.8324 (0.8335) time: 0.1424 data: 0.0627 max mem: 9390 +Train: [23] [1200/6250] eta: 0:12:11 lr: 0.000114 grad: 0.0665 (0.0688) loss: 0.8373 (0.8336) time: 0.1470 data: 0.0706 max mem: 9390 +Train: [23] [1300/6250] eta: 0:11:59 lr: 0.000114 grad: 0.0635 (0.0686) loss: 0.8270 (0.8337) time: 0.1575 data: 0.0722 max mem: 9390 +Train: [23] [1400/6250] eta: 0:11:46 lr: 0.000114 grad: 0.0654 (0.0685) loss: 0.8325 (0.8337) time: 0.1547 data: 0.0754 max mem: 9390 +Train: [23] [1500/6250] eta: 0:11:30 lr: 0.000114 grad: 0.0637 (0.0684) loss: 0.8318 (0.8337) time: 0.1357 data: 0.0524 max mem: 9390 +Train: [23] [1600/6250] eta: 0:11:16 lr: 0.000114 grad: 0.0661 (0.0684) loss: 0.8304 (0.8336) time: 0.1286 data: 0.0502 max mem: 9390 +Train: [23] [1700/6250] eta: 0:11:00 lr: 0.000114 grad: 0.0629 (0.0682) loss: 0.8298 (0.8337) time: 0.1275 data: 0.0447 max mem: 9390 +Train: [23] [1800/6250] eta: 0:10:43 lr: 0.000114 grad: 0.0659 (0.0681) loss: 0.8286 (0.8337) time: 0.1262 data: 0.0528 max mem: 9390 +Train: [23] [1900/6250] eta: 0:10:31 lr: 0.000114 grad: 0.0631 (0.0680) loss: 0.8371 (0.8337) time: 0.1528 data: 0.0717 max mem: 9390 +Train: [23] [2000/6250] eta: 0:10:15 lr: 0.000114 grad: 0.0640 (0.0679) loss: 0.8280 (0.8337) time: 0.1358 data: 0.0651 max mem: 9390 +Train: [23] [2100/6250] eta: 0:10:01 lr: 0.000114 grad: 0.0601 (0.0677) loss: 0.8335 (0.8337) time: 0.1474 data: 0.0633 max mem: 9390 +Train: [23] [2200/6250] eta: 0:09:46 lr: 0.000114 grad: 0.0652 (0.0677) loss: 0.8313 (0.8336) time: 0.1466 data: 0.0717 max mem: 9390 +Train: [23] [2300/6250] eta: 0:09:31 lr: 0.000114 grad: 0.0647 (0.0678) loss: 0.8313 (0.8336) time: 0.1487 data: 0.0748 max mem: 9390 +Train: [23] [2400/6250] eta: 0:09:15 lr: 0.000114 grad: 0.0643 (0.0677) loss: 0.8385 (0.8336) time: 0.1218 data: 0.0406 max mem: 9390 +Train: [23] [2500/6250] eta: 0:09:01 lr: 0.000114 grad: 0.0627 (0.0676) loss: 0.8360 (0.8336) time: 0.1636 data: 0.0869 max mem: 9390 +Train: [23] [2600/6250] eta: 0:08:46 lr: 0.000114 grad: 0.0673 (0.0675) loss: 0.8295 (0.8336) time: 0.1431 data: 0.0617 max mem: 9390 +Train: [23] [2700/6250] eta: 0:08:30 lr: 0.000114 grad: 0.0674 (0.0675) loss: 0.8357 (0.8336) time: 0.1277 data: 0.0439 max mem: 9390 +Train: [23] [2800/6250] eta: 0:08:15 lr: 0.000114 grad: 0.0649 (0.0674) loss: 0.8299 (0.8336) time: 0.0966 data: 0.0192 max mem: 9390 +Train: [23] [2900/6250] eta: 0:08:00 lr: 0.000114 grad: 0.0611 (0.0673) loss: 0.8316 (0.8336) time: 0.1385 data: 0.0630 max mem: 9390 +Train: [23] [3000/6250] eta: 0:07:44 lr: 0.000114 grad: 0.0629 (0.0672) loss: 0.8397 (0.8337) time: 0.1318 data: 0.0566 max mem: 9390 +Train: [23] [3100/6250] eta: 0:07:29 lr: 0.000114 grad: 0.0647 (0.0671) loss: 0.8343 (0.8337) time: 0.1279 data: 0.0501 max mem: 9390 +Train: [23] [3200/6250] eta: 0:07:14 lr: 0.000114 grad: 0.0634 (0.0671) loss: 0.8327 (0.8337) time: 0.1377 data: 0.0567 max mem: 9390 +Train: [23] [3300/6250] eta: 0:07:00 lr: 0.000114 grad: 0.0659 (0.0670) loss: 0.8374 (0.8337) time: 0.1327 data: 0.0581 max mem: 9390 +Train: [23] [3400/6250] eta: 0:06:45 lr: 0.000114 grad: 0.0645 (0.0670) loss: 0.8324 (0.8337) time: 0.1198 data: 0.0390 max mem: 9390 +Train: [23] [3500/6250] eta: 0:06:30 lr: 0.000114 grad: 0.0628 (0.0669) loss: 0.8347 (0.8337) time: 0.1556 data: 0.0815 max mem: 9390 +Train: [23] [3600/6250] eta: 0:06:15 lr: 0.000114 grad: 0.0638 (0.0670) loss: 0.8303 (0.8337) time: 0.1225 data: 0.0449 max mem: 9390 +Train: [23] [3700/6250] eta: 0:06:01 lr: 0.000114 grad: 0.0622 (0.0670) loss: 0.8322 (0.8336) time: 0.1356 data: 0.0537 max mem: 9390 +Train: [23] [3800/6250] eta: 0:05:47 lr: 0.000114 grad: 0.0667 (0.0670) loss: 0.8341 (0.8336) time: 0.1227 data: 0.0451 max mem: 9390 +Train: [23] [3900/6250] eta: 0:05:32 lr: 0.000114 grad: 0.0670 (0.0671) loss: 0.8359 (0.8336) time: 0.1134 data: 0.0390 max mem: 9390 +Train: [23] [4000/6250] eta: 0:05:17 lr: 0.000113 grad: 0.0644 (0.0672) loss: 0.8305 (0.8336) time: 0.1270 data: 0.0502 max mem: 9390 +Train: [23] [4100/6250] eta: 0:05:03 lr: 0.000113 grad: 0.0686 (0.0672) loss: 0.8329 (0.8335) time: 0.1316 data: 0.0581 max mem: 9390 +Train: [23] [4200/6250] eta: 0:04:48 lr: 0.000113 grad: 0.0654 (0.0673) loss: 0.8392 (0.8334) time: 0.1341 data: 0.0616 max mem: 9390 +Train: [23] [4300/6250] eta: 0:04:34 lr: 0.000113 grad: 0.0668 (0.0673) loss: 0.8295 (0.8334) time: 0.1685 data: 0.0861 max mem: 9390 +Train: [23] [4400/6250] eta: 0:04:19 lr: 0.000113 grad: 0.0717 (0.0673) loss: 0.8292 (0.8334) time: 0.1237 data: 0.0474 max mem: 9390 +Train: [23] [4500/6250] eta: 0:04:06 lr: 0.000113 grad: 0.0652 (0.0673) loss: 0.8334 (0.8334) time: 0.1477 data: 0.0581 max mem: 9390 +Train: [23] [4600/6250] eta: 0:03:51 lr: 0.000113 grad: 0.0647 (0.0673) loss: 0.8378 (0.8334) time: 0.1307 data: 0.0546 max mem: 9390 +Train: [23] [4700/6250] eta: 0:03:37 lr: 0.000113 grad: 0.0619 (0.0673) loss: 0.8365 (0.8334) time: 0.1277 data: 0.0499 max mem: 9390 +Train: [23] [4800/6250] eta: 0:03:23 lr: 0.000113 grad: 0.0624 (0.0673) loss: 0.8355 (0.8334) time: 0.1396 data: 0.0610 max mem: 9390 +Train: [23] [4900/6250] eta: 0:03:08 lr: 0.000113 grad: 0.0615 (0.0672) loss: 0.8359 (0.8335) time: 0.1316 data: 0.0573 max mem: 9390 +Train: [23] [5000/6250] eta: 0:02:54 lr: 0.000113 grad: 0.0670 (0.0672) loss: 0.8348 (0.8335) time: 0.1241 data: 0.0446 max mem: 9390 +Train: [23] [5100/6250] eta: 0:02:40 lr: 0.000113 grad: 0.0642 (0.0672) loss: 0.8364 (0.8335) time: 0.1454 data: 0.0562 max mem: 9390 +Train: [23] [5200/6250] eta: 0:02:26 lr: 0.000113 grad: 0.0688 (0.0673) loss: 0.8306 (0.8335) time: 0.1049 data: 0.0277 max mem: 9390 +Train: [23] [5300/6250] eta: 0:02:12 lr: 0.000113 grad: 0.0632 (0.0672) loss: 0.8343 (0.8335) time: 0.1360 data: 0.0578 max mem: 9390 +Train: [23] [5400/6250] eta: 0:01:58 lr: 0.000113 grad: 0.0639 (0.0672) loss: 0.8292 (0.8335) time: 0.1186 data: 0.0416 max mem: 9390 +Train: [23] [5500/6250] eta: 0:01:44 lr: 0.000113 grad: 0.0631 (0.0672) loss: 0.8344 (0.8335) time: 0.1739 data: 0.0959 max mem: 9390 +Train: [23] [5600/6250] eta: 0:01:30 lr: 0.000113 grad: 0.0635 (0.0672) loss: 0.8358 (0.8335) time: 0.1453 data: 0.0623 max mem: 9390 +Train: [23] [5700/6250] eta: 0:01:16 lr: 0.000113 grad: 0.0595 (0.0671) loss: 0.8353 (0.8335) time: 0.1425 data: 0.0621 max mem: 9390 +Train: [23] [5800/6250] eta: 0:01:02 lr: 0.000113 grad: 0.0693 (0.0671) loss: 0.8306 (0.8335) time: 0.1371 data: 0.0601 max mem: 9390 +Train: [23] [5900/6250] eta: 0:00:48 lr: 0.000113 grad: 0.0607 (0.0671) loss: 0.8337 (0.8335) time: 0.1179 data: 0.0415 max mem: 9390 +Train: [23] [6000/6250] eta: 0:00:34 lr: 0.000113 grad: 0.0638 (0.0671) loss: 0.8332 (0.8335) time: 0.1332 data: 0.0581 max mem: 9390 +Train: [23] [6100/6250] eta: 0:00:20 lr: 0.000113 grad: 0.0675 (0.0672) loss: 0.8376 (0.8335) time: 0.1331 data: 0.0544 max mem: 9390 +Train: [23] [6200/6250] eta: 0:00:06 lr: 0.000113 grad: 0.0640 (0.0671) loss: 0.8384 (0.8336) time: 0.1361 data: 0.0545 max mem: 9390 +Train: [23] [6249/6250] eta: 0:00:00 lr: 0.000113 grad: 0.0645 (0.0672) loss: 0.8309 (0.8336) time: 0.1525 data: 0.0741 max mem: 9390 +Train: [23] Total time: 0:14:29 (0.1392 s / it) +Averaged stats: lr: 0.000113 grad: 0.0645 (0.0672) loss: 0.8309 (0.8336) +Eval (hcp-train-subset): [23] [ 0/62] eta: 0:05:40 loss: 0.8589 (0.8589) time: 5.4920 data: 5.4620 max mem: 9390 +Eval (hcp-train-subset): [23] [61/62] eta: 0:00:00 loss: 0.8434 (0.8438) time: 0.1236 data: 0.0990 max mem: 9390 +Eval (hcp-train-subset): [23] Total time: 0:00:13 (0.2152 s / it) +Averaged stats (hcp-train-subset): loss: 0.8434 (0.8438) +Eval (hcp-val): [23] [ 0/62] eta: 0:05:22 loss: 0.8345 (0.8345) time: 5.1985 data: 5.1655 max mem: 9390 +Eval (hcp-val): [23] [61/62] eta: 0:00:00 loss: 0.8412 (0.8416) time: 0.1220 data: 0.0968 max mem: 9390 +Eval (hcp-val): [23] Total time: 0:00:13 (0.2188 s / it) +Averaged stats (hcp-val): loss: 0.8412 (0.8416) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +Train: [24] [ 0/6250] eta: 9:30:36 lr: 0.000113 grad: 0.1215 (0.1215) loss: 0.8027 (0.8027) time: 5.4778 data: 5.3898 max mem: 9390 +Train: [24] [ 100/6250] eta: 0:17:43 lr: 0.000113 grad: 0.0610 (0.0686) loss: 0.8406 (0.8451) time: 0.1422 data: 0.0509 max mem: 9390 +Train: [24] [ 200/6250] eta: 0:16:01 lr: 0.000113 grad: 0.0656 (0.0669) loss: 0.8304 (0.8424) time: 0.1612 data: 0.0859 max mem: 9390 +Train: [24] [ 300/6250] eta: 0:14:51 lr: 0.000113 grad: 0.0671 (0.0662) loss: 0.8390 (0.8404) time: 0.1337 data: 0.0540 max mem: 9390 +Train: [24] [ 400/6250] eta: 0:14:06 lr: 0.000113 grad: 0.0629 (0.0663) loss: 0.8313 (0.8385) time: 0.1172 data: 0.0339 max mem: 9390 +Train: [24] [ 500/6250] eta: 0:13:30 lr: 0.000113 grad: 0.0658 (0.0659) loss: 0.8368 (0.8382) time: 0.1096 data: 0.0272 max mem: 9390 +Train: [24] [ 600/6250] eta: 0:13:02 lr: 0.000113 grad: 0.0630 (0.0660) loss: 0.8342 (0.8378) time: 0.1115 data: 0.0195 max mem: 9390 +Train: [24] [ 700/6250] eta: 0:12:36 lr: 0.000113 grad: 0.0685 (0.0667) loss: 0.8313 (0.8373) time: 0.1256 data: 0.0379 max mem: 9390 +Train: [24] [ 800/6250] eta: 0:12:16 lr: 0.000113 grad: 0.0618 (0.0667) loss: 0.8330 (0.8372) time: 0.1479 data: 0.0665 max mem: 9390 +Train: [24] [ 900/6250] eta: 0:12:08 lr: 0.000113 grad: 0.0602 (0.0664) loss: 0.8395 (0.8373) time: 0.1680 data: 0.0913 max mem: 9390 +Train: [24] [1000/6250] eta: 0:12:11 lr: 0.000113 grad: 0.0653 (0.0664) loss: 0.8347 (0.8372) time: 0.1736 data: 0.0984 max mem: 9390 +Train: [24] [1100/6250] eta: 0:12:24 lr: 0.000113 grad: 0.0611 (0.0664) loss: 0.8347 (0.8370) time: 0.1555 data: 0.0741 max mem: 9390 +Train: [24] [1200/6250] eta: 0:12:11 lr: 0.000113 grad: 0.0636 (0.0663) loss: 0.8313 (0.8368) time: 0.1496 data: 0.0720 max mem: 9390 +Train: [24] [1300/6250] eta: 0:12:01 lr: 0.000113 grad: 0.0629 (0.0662) loss: 0.8364 (0.8365) time: 0.1711 data: 0.0938 max mem: 9390 +Train: [24] [1400/6250] eta: 0:11:46 lr: 0.000113 grad: 0.0644 (0.0663) loss: 0.8329 (0.8363) time: 0.1581 data: 0.0843 max mem: 9390 +Train: [24] [1500/6250] eta: 0:11:31 lr: 0.000113 grad: 0.0672 (0.0663) loss: 0.8264 (0.8361) time: 0.1444 data: 0.0629 max mem: 9390 +Train: [24] [1600/6250] eta: 0:11:14 lr: 0.000113 grad: 0.0660 (0.0664) loss: 0.8370 (0.8358) time: 0.1336 data: 0.0571 max mem: 9390 +Train: [24] [1700/6250] eta: 0:10:57 lr: 0.000113 grad: 0.0637 (0.0665) loss: 0.8334 (0.8356) time: 0.1319 data: 0.0542 max mem: 9390 +Train: [24] [1800/6250] eta: 0:10:41 lr: 0.000113 grad: 0.0654 (0.0665) loss: 0.8329 (0.8354) time: 0.1164 data: 0.0375 max mem: 9390 +Train: [24] [1900/6250] eta: 0:10:29 lr: 0.000113 grad: 0.0676 (0.0667) loss: 0.8317 (0.8350) time: 0.1832 data: 0.0472 max mem: 9390 +Train: [24] [2000/6250] eta: 0:10:15 lr: 0.000113 grad: 0.0653 (0.0666) loss: 0.8335 (0.8349) time: 0.1609 data: 0.0829 max mem: 9390 +Train: [24] [2100/6250] eta: 0:10:00 lr: 0.000113 grad: 0.0617 (0.0668) loss: 0.8325 (0.8346) time: 0.1407 data: 0.0611 max mem: 9390 +Train: [24] [2200/6250] eta: 0:09:44 lr: 0.000113 grad: 0.0702 (0.0668) loss: 0.8294 (0.8345) time: 0.1229 data: 0.0430 max mem: 9390 +Train: [24] [2300/6250] eta: 0:09:32 lr: 0.000113 grad: 0.0645 (0.0668) loss: 0.8299 (0.8343) time: 0.2177 data: 0.1224 max mem: 9390 +Train: [24] [2400/6250] eta: 0:09:18 lr: 0.000113 grad: 0.0668 (0.0669) loss: 0.8298 (0.8342) time: 0.1449 data: 0.0696 max mem: 9390 +Train: [24] [2500/6250] eta: 0:09:01 lr: 0.000113 grad: 0.0656 (0.0669) loss: 0.8287 (0.8341) time: 0.1269 data: 0.0485 max mem: 9390 +Train: [24] [2600/6250] eta: 0:08:48 lr: 0.000113 grad: 0.0624 (0.0669) loss: 0.8393 (0.8341) time: 0.1604 data: 0.0766 max mem: 9390 +Train: [24] [2700/6250] eta: 0:08:33 lr: 0.000113 grad: 0.0647 (0.0669) loss: 0.8295 (0.8340) time: 0.1131 data: 0.0365 max mem: 9390 +Train: [24] [2800/6250] eta: 0:08:17 lr: 0.000113 grad: 0.0618 (0.0669) loss: 0.8343 (0.8339) time: 0.1435 data: 0.0674 max mem: 9390 +Train: [24] [2900/6250] eta: 0:08:02 lr: 0.000112 grad: 0.0661 (0.0669) loss: 0.8316 (0.8339) time: 0.1439 data: 0.0637 max mem: 9390 +Train: [24] [3000/6250] eta: 0:07:46 lr: 0.000112 grad: 0.0607 (0.0669) loss: 0.8316 (0.8338) time: 0.1300 data: 0.0482 max mem: 9390 +Train: [24] [3100/6250] eta: 0:07:32 lr: 0.000112 grad: 0.0651 (0.0669) loss: 0.8355 (0.8338) time: 0.1475 data: 0.0690 max mem: 9390 +Train: [24] [3200/6250] eta: 0:07:16 lr: 0.000112 grad: 0.0651 (0.0669) loss: 0.8312 (0.8337) time: 0.1290 data: 0.0506 max mem: 9390 +Train: [24] [3300/6250] eta: 0:07:01 lr: 0.000112 grad: 0.0636 (0.0669) loss: 0.8337 (0.8337) time: 0.1339 data: 0.0557 max mem: 9390 +Train: [24] [3400/6250] eta: 0:06:46 lr: 0.000112 grad: 0.0644 (0.0669) loss: 0.8347 (0.8338) time: 0.1269 data: 0.0536 max mem: 9390 +Train: [24] [3500/6250] eta: 0:06:31 lr: 0.000112 grad: 0.0680 (0.0668) loss: 0.8315 (0.8337) time: 0.1429 data: 0.0637 max mem: 9390 +Train: [24] [3600/6250] eta: 0:06:16 lr: 0.000112 grad: 0.0670 (0.0668) loss: 0.8363 (0.8337) time: 0.1392 data: 0.0658 max mem: 9390 +Train: [24] [3700/6250] eta: 0:06:01 lr: 0.000112 grad: 0.0700 (0.0669) loss: 0.8373 (0.8338) time: 0.1459 data: 0.0544 max mem: 9390 +Train: [24] [3800/6250] eta: 0:05:47 lr: 0.000112 grad: 0.0617 (0.0669) loss: 0.8315 (0.8337) time: 0.1221 data: 0.0438 max mem: 9390 +Train: [24] [3900/6250] eta: 0:05:32 lr: 0.000112 grad: 0.0628 (0.0669) loss: 0.8392 (0.8337) time: 0.1347 data: 0.0564 max mem: 9390 +Train: [24] [4000/6250] eta: 0:05:17 lr: 0.000112 grad: 0.0654 (0.0670) loss: 0.8335 (0.8337) time: 0.1244 data: 0.0472 max mem: 9390 +Train: [24] [4100/6250] eta: 0:05:03 lr: 0.000112 grad: 0.0630 (0.0670) loss: 0.8350 (0.8338) time: 0.1423 data: 0.0654 max mem: 9390 +Train: [24] [4200/6250] eta: 0:04:48 lr: 0.000112 grad: 0.0623 (0.0670) loss: 0.8397 (0.8338) time: 0.1243 data: 0.0460 max mem: 9390 +Train: [24] [4300/6250] eta: 0:04:34 lr: 0.000112 grad: 0.0666 (0.0670) loss: 0.8372 (0.8338) time: 0.1332 data: 0.0603 max mem: 9390 +Train: [24] [4400/6250] eta: 0:04:19 lr: 0.000112 grad: 0.0730 (0.0670) loss: 0.8302 (0.8338) time: 0.1361 data: 0.0599 max mem: 9390 +Train: [24] [4500/6250] eta: 0:04:05 lr: 0.000112 grad: 0.0655 (0.0670) loss: 0.8290 (0.8338) time: 0.1218 data: 0.0429 max mem: 9390 +Train: [24] [4600/6250] eta: 0:03:50 lr: 0.000112 grad: 0.0650 (0.0670) loss: 0.8314 (0.8338) time: 0.1368 data: 0.0592 max mem: 9390 +Train: [24] [4700/6250] eta: 0:03:36 lr: 0.000112 grad: 0.0661 (0.0671) loss: 0.8331 (0.8337) time: 0.1345 data: 0.0581 max mem: 9390 +Train: [24] [4800/6250] eta: 0:03:22 lr: 0.000112 grad: 0.0614 (0.0671) loss: 0.8347 (0.8337) time: 0.1467 data: 0.0738 max mem: 9390 +Train: [24] [4900/6250] eta: 0:03:08 lr: 0.000112 grad: 0.0625 (0.0671) loss: 0.8374 (0.8337) time: 0.1437 data: 0.0605 max mem: 9390 +Train: [24] [5000/6250] eta: 0:02:54 lr: 0.000112 grad: 0.0641 (0.0671) loss: 0.8327 (0.8337) time: 0.1360 data: 0.0543 max mem: 9390 +Train: [24] [5100/6250] eta: 0:02:40 lr: 0.000112 grad: 0.0647 (0.0671) loss: 0.8341 (0.8337) time: 0.1476 data: 0.0704 max mem: 9390 +Train: [24] [5200/6250] eta: 0:02:26 lr: 0.000112 grad: 0.0622 (0.0671) loss: 0.8351 (0.8337) time: 0.1461 data: 0.0713 max mem: 9390 +Train: [24] [5300/6250] eta: 0:02:12 lr: 0.000112 grad: 0.0693 (0.0671) loss: 0.8265 (0.8337) time: 0.1438 data: 0.0700 max mem: 9390 +Train: [24] [5400/6250] eta: 0:01:58 lr: 0.000112 grad: 0.0646 (0.0671) loss: 0.8329 (0.8336) time: 0.1744 data: 0.0964 max mem: 9390 +Train: [24] [5500/6250] eta: 0:01:44 lr: 0.000112 grad: 0.0665 (0.0671) loss: 0.8339 (0.8336) time: 0.1468 data: 0.0685 max mem: 9390 +Train: [24] [5600/6250] eta: 0:01:30 lr: 0.000112 grad: 0.0623 (0.0672) loss: 0.8362 (0.8336) time: 0.1201 data: 0.0452 max mem: 9390 +Train: [24] [5700/6250] eta: 0:01:16 lr: 0.000112 grad: 0.0617 (0.0672) loss: 0.8375 (0.8335) time: 0.1497 data: 0.0674 max mem: 9390 +Train: [24] [5800/6250] eta: 0:01:02 lr: 0.000112 grad: 0.0685 (0.0673) loss: 0.8255 (0.8334) time: 0.1359 data: 0.0596 max mem: 9390 +Train: [24] [5900/6250] eta: 0:00:48 lr: 0.000112 grad: 0.0650 (0.0673) loss: 0.8288 (0.8334) time: 0.1519 data: 0.0782 max mem: 9390 +Train: [24] [6000/6250] eta: 0:00:34 lr: 0.000112 grad: 0.0699 (0.0673) loss: 0.8278 (0.8333) time: 0.1408 data: 0.0550 max mem: 9390 +Train: [24] [6100/6250] eta: 0:00:20 lr: 0.000112 grad: 0.0670 (0.0674) loss: 0.8325 (0.8332) time: 0.1552 data: 0.0759 max mem: 9390 +Train: [24] [6200/6250] eta: 0:00:06 lr: 0.000112 grad: 0.0700 (0.0674) loss: 0.8234 (0.8331) time: 0.1352 data: 0.0584 max mem: 9390 +Train: [24] [6249/6250] eta: 0:00:00 lr: 0.000112 grad: 0.0679 (0.0675) loss: 0.8277 (0.8331) time: 0.1296 data: 0.0562 max mem: 9390 +Train: [24] Total time: 0:14:30 (0.1393 s / it) +Averaged stats: lr: 0.000112 grad: 0.0679 (0.0675) loss: 0.8277 (0.8331) +Eval (hcp-train-subset): [24] [ 0/62] eta: 0:03:03 loss: 0.8546 (0.8546) time: 2.9562 data: 2.8845 max mem: 9390 +Eval (hcp-train-subset): [24] [61/62] eta: 0:00:00 loss: 0.8461 (0.8447) time: 0.1720 data: 0.1474 max mem: 9390 +Eval (hcp-train-subset): [24] Total time: 0:00:13 (0.2219 s / it) +Averaged stats (hcp-train-subset): loss: 0.8461 (0.8447) +Making plots (hcp-train-subset): example=19 +Eval (hcp-val): [24] [ 0/62] eta: 0:05:14 loss: 0.8355 (0.8355) time: 5.0801 data: 5.0500 max mem: 9390 +Eval (hcp-val): [24] [61/62] eta: 0:00:00 loss: 0.8395 (0.8405) time: 0.1374 data: 0.1107 max mem: 9390 +Eval (hcp-val): [24] Total time: 0:00:13 (0.2114 s / it) +Averaged stats (hcp-val): loss: 0.8395 (0.8405) +Making plots (hcp-val): example=54 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +Train: [25] [ 0/6250] eta: 5:33:04 lr: 0.000112 grad: 0.0437 (0.0437) loss: 0.8671 (0.8671) time: 3.1975 data: 2.9653 max mem: 9390 +Train: [25] [ 100/6250] eta: 0:18:01 lr: 0.000112 grad: 0.0658 (0.0836) loss: 0.8442 (0.8421) time: 0.1236 data: 0.0438 max mem: 9390 +Train: [25] [ 200/6250] eta: 0:15:49 lr: 0.000112 grad: 0.0691 (0.0791) loss: 0.8448 (0.8424) time: 0.1352 data: 0.0535 max mem: 9390 +Train: [25] [ 300/6250] eta: 0:14:49 lr: 0.000112 grad: 0.0623 (0.0747) loss: 0.8420 (0.8420) time: 0.1474 data: 0.0688 max mem: 9390 +Train: [25] [ 400/6250] eta: 0:14:10 lr: 0.000112 grad: 0.0600 (0.0722) loss: 0.8358 (0.8411) time: 0.1459 data: 0.0642 max mem: 9390 +Train: [25] [ 500/6250] eta: 0:13:33 lr: 0.000112 grad: 0.0630 (0.0708) loss: 0.8413 (0.8399) time: 0.1367 data: 0.0596 max mem: 9390 +Train: [25] [ 600/6250] eta: 0:13:04 lr: 0.000112 grad: 0.0624 (0.0700) loss: 0.8277 (0.8386) time: 0.1138 data: 0.0326 max mem: 9390 +Train: [25] [ 700/6250] eta: 0:12:41 lr: 0.000112 grad: 0.0632 (0.0692) loss: 0.8374 (0.8380) time: 0.1183 data: 0.0331 max mem: 9390 +Train: [25] [ 800/6250] eta: 0:12:20 lr: 0.000112 grad: 0.0627 (0.0687) loss: 0.8430 (0.8376) time: 0.1271 data: 0.0452 max mem: 9390 +Train: [25] [ 900/6250] eta: 0:12:11 lr: 0.000112 grad: 0.0625 (0.0687) loss: 0.8355 (0.8371) time: 0.1591 data: 0.0816 max mem: 9390 +Train: [25] [1000/6250] eta: 0:12:16 lr: 0.000112 grad: 0.0607 (0.0686) loss: 0.8328 (0.8368) time: 0.1917 data: 0.1101 max mem: 9390 +Train: [25] [1100/6250] eta: 0:12:18 lr: 0.000112 grad: 0.0634 (0.0684) loss: 0.8352 (0.8366) time: 0.1747 data: 0.1009 max mem: 9390 +Train: [25] [1200/6250] eta: 0:12:06 lr: 0.000112 grad: 0.0683 (0.0683) loss: 0.8311 (0.8364) time: 0.1133 data: 0.0276 max mem: 9390 +Train: [25] [1300/6250] eta: 0:11:55 lr: 0.000112 grad: 0.0646 (0.0682) loss: 0.8317 (0.8362) time: 0.1595 data: 0.0804 max mem: 9390 +Train: [25] [1400/6250] eta: 0:11:40 lr: 0.000112 grad: 0.0683 (0.0684) loss: 0.8344 (0.8359) time: 0.1460 data: 0.0660 max mem: 9390 +Train: [25] [1500/6250] eta: 0:11:29 lr: 0.000112 grad: 0.0671 (0.0684) loss: 0.8314 (0.8357) time: 0.1832 data: 0.1009 max mem: 9390 +Train: [25] [1600/6250] eta: 0:11:11 lr: 0.000111 grad: 0.0636 (0.0684) loss: 0.8340 (0.8355) time: 0.0942 data: 0.0136 max mem: 9390 +Train: [25] [1700/6250] eta: 0:10:54 lr: 0.000111 grad: 0.0666 (0.0685) loss: 0.8382 (0.8354) time: 0.1123 data: 0.0297 max mem: 9390 +Train: [25] [1800/6250] eta: 0:10:37 lr: 0.000111 grad: 0.0679 (0.0684) loss: 0.8296 (0.8352) time: 0.1159 data: 0.0264 max mem: 9390 +Train: [25] [1900/6250] eta: 0:10:23 lr: 0.000111 grad: 0.0656 (0.0684) loss: 0.8338 (0.8350) time: 0.1672 data: 0.0850 max mem: 9390 +Train: [25] [2000/6250] eta: 0:10:10 lr: 0.000111 grad: 0.0618 (0.0684) loss: 0.8291 (0.8350) time: 0.1324 data: 0.0523 max mem: 9390 +Train: [25] [2100/6250] eta: 0:09:56 lr: 0.000111 grad: 0.0638 (0.0684) loss: 0.8330 (0.8348) time: 0.1669 data: 0.0898 max mem: 9390 +Train: [25] [2200/6250] eta: 0:09:41 lr: 0.000111 grad: 0.0678 (0.0685) loss: 0.8315 (0.8348) time: 0.1687 data: 0.0909 max mem: 9390 +Train: [25] [2300/6250] eta: 0:09:26 lr: 0.000111 grad: 0.0633 (0.0684) loss: 0.8318 (0.8348) time: 0.1462 data: 0.0662 max mem: 9390 +Train: [25] [2400/6250] eta: 0:09:12 lr: 0.000111 grad: 0.0708 (0.0684) loss: 0.8291 (0.8346) time: 0.1339 data: 0.0498 max mem: 9390 +Train: [25] [2500/6250] eta: 0:08:58 lr: 0.000111 grad: 0.0664 (0.0685) loss: 0.8367 (0.8345) time: 0.1546 data: 0.0523 max mem: 9390 +Train: [25] [2600/6250] eta: 0:08:44 lr: 0.000111 grad: 0.0685 (0.0685) loss: 0.8337 (0.8344) time: 0.0895 data: 0.0002 max mem: 9390 +Train: [25] [2700/6250] eta: 0:08:29 lr: 0.000111 grad: 0.0699 (0.0687) loss: 0.8359 (0.8344) time: 0.1327 data: 0.0553 max mem: 9390 +Train: [25] [2800/6250] eta: 0:08:14 lr: 0.000111 grad: 0.0631 (0.0688) loss: 0.8380 (0.8343) time: 0.1475 data: 0.0707 max mem: 9390 +Train: [25] [2900/6250] eta: 0:07:59 lr: 0.000111 grad: 0.0643 (0.0688) loss: 0.8314 (0.8343) time: 0.1350 data: 0.0578 max mem: 9390 +Train: [25] [3000/6250] eta: 0:07:44 lr: 0.000111 grad: 0.0696 (0.0689) loss: 0.8301 (0.8342) time: 0.1294 data: 0.0494 max mem: 9390 +Train: [25] [3100/6250] eta: 0:07:29 lr: 0.000111 grad: 0.0670 (0.0688) loss: 0.8291 (0.8342) time: 0.1487 data: 0.0699 max mem: 9390 +Train: [25] [3200/6250] eta: 0:07:13 lr: 0.000111 grad: 0.0667 (0.0688) loss: 0.8355 (0.8341) time: 0.1156 data: 0.0360 max mem: 9390 +Train: [25] [3300/6250] eta: 0:06:59 lr: 0.000111 grad: 0.0638 (0.0688) loss: 0.8342 (0.8342) time: 0.1477 data: 0.0646 max mem: 9390 +Train: [25] [3400/6250] eta: 0:06:43 lr: 0.000111 grad: 0.0652 (0.0688) loss: 0.8325 (0.8341) time: 0.1334 data: 0.0583 max mem: 9390 +Train: [25] [3500/6250] eta: 0:06:29 lr: 0.000111 grad: 0.0693 (0.0688) loss: 0.8334 (0.8341) time: 0.1166 data: 0.0372 max mem: 9390 +Train: [25] [3600/6250] eta: 0:06:14 lr: 0.000111 grad: 0.0700 (0.0688) loss: 0.8302 (0.8340) time: 0.1251 data: 0.0461 max mem: 9390 +Train: [25] [3700/6250] eta: 0:05:59 lr: 0.000111 grad: 0.0645 (0.0688) loss: 0.8336 (0.8339) time: 0.1318 data: 0.0579 max mem: 9390 +Train: [25] [3800/6250] eta: 0:05:44 lr: 0.000111 grad: 0.0678 (0.0688) loss: 0.8280 (0.8338) time: 0.1237 data: 0.0448 max mem: 9390 +Train: [25] [3900/6250] eta: 0:05:29 lr: 0.000111 grad: 0.0698 (0.0688) loss: 0.8278 (0.8337) time: 0.1281 data: 0.0457 max mem: 9390 +Train: [25] [4000/6250] eta: 0:05:14 lr: 0.000111 grad: 0.0634 (0.0688) loss: 0.8343 (0.8337) time: 0.1395 data: 0.0592 max mem: 9390 +Train: [25] [4100/6250] eta: 0:05:00 lr: 0.000111 grad: 0.0647 (0.0687) loss: 0.8319 (0.8336) time: 0.1269 data: 0.0528 max mem: 9390 +Train: [25] [4200/6250] eta: 0:04:46 lr: 0.000111 grad: 0.0652 (0.0687) loss: 0.8323 (0.8335) time: 0.1536 data: 0.0686 max mem: 9390 +Train: [25] [4300/6250] eta: 0:04:32 lr: 0.000111 grad: 0.0687 (0.0687) loss: 0.8281 (0.8335) time: 0.1469 data: 0.0696 max mem: 9390 +Train: [25] [4400/6250] eta: 0:04:18 lr: 0.000111 grad: 0.0638 (0.0687) loss: 0.8373 (0.8334) time: 0.1364 data: 0.0594 max mem: 9390 +Train: [25] [4500/6250] eta: 0:04:04 lr: 0.000111 grad: 0.0680 (0.0687) loss: 0.8269 (0.8334) time: 0.1358 data: 0.0593 max mem: 9390 +Train: [25] [4600/6250] eta: 0:03:50 lr: 0.000111 grad: 0.0691 (0.0687) loss: 0.8355 (0.8334) time: 0.1248 data: 0.0460 max mem: 9390 +Train: [25] [4700/6250] eta: 0:03:35 lr: 0.000111 grad: 0.0633 (0.0687) loss: 0.8304 (0.8334) time: 0.1467 data: 0.0693 max mem: 9390 +Train: [25] [4800/6250] eta: 0:03:21 lr: 0.000111 grad: 0.0677 (0.0687) loss: 0.8317 (0.8334) time: 0.1288 data: 0.0414 max mem: 9390 +Train: [25] [4900/6250] eta: 0:03:07 lr: 0.000111 grad: 0.0677 (0.0687) loss: 0.8307 (0.8334) time: 0.1531 data: 0.0686 max mem: 9390 +Train: [25] [5000/6250] eta: 0:02:53 lr: 0.000111 grad: 0.0672 (0.0687) loss: 0.8321 (0.8333) time: 0.1335 data: 0.0572 max mem: 9390 +Train: [25] [5100/6250] eta: 0:02:39 lr: 0.000111 grad: 0.0664 (0.0687) loss: 0.8309 (0.8333) time: 0.1364 data: 0.0591 max mem: 9390 +Train: [25] [5200/6250] eta: 0:02:25 lr: 0.000111 grad: 0.0702 (0.0687) loss: 0.8321 (0.8333) time: 0.1250 data: 0.0506 max mem: 9390 +Train: [25] [5300/6250] eta: 0:02:11 lr: 0.000111 grad: 0.0705 (0.0687) loss: 0.8276 (0.8333) time: 0.1155 data: 0.0268 max mem: 9390 +Train: [25] [5400/6250] eta: 0:01:57 lr: 0.000111 grad: 0.0674 (0.0687) loss: 0.8296 (0.8332) time: 0.1249 data: 0.0501 max mem: 9390 +Train: [25] [5500/6250] eta: 0:01:43 lr: 0.000111 grad: 0.0650 (0.0688) loss: 0.8293 (0.8332) time: 0.1284 data: 0.0460 max mem: 9390 +Train: [25] [5600/6250] eta: 0:01:29 lr: 0.000111 grad: 0.0727 (0.0688) loss: 0.8283 (0.8332) time: 0.1248 data: 0.0483 max mem: 9390 +Train: [25] [5700/6250] eta: 0:01:15 lr: 0.000111 grad: 0.0680 (0.0688) loss: 0.8288 (0.8332) time: 0.1536 data: 0.0784 max mem: 9390 +Train: [25] [5800/6250] eta: 0:01:02 lr: 0.000111 grad: 0.0716 (0.0688) loss: 0.8330 (0.8331) time: 0.1336 data: 0.0547 max mem: 9390 +Train: [25] [5900/6250] eta: 0:00:48 lr: 0.000111 grad: 0.0656 (0.0689) loss: 0.8314 (0.8331) time: 0.1471 data: 0.0748 max mem: 9390 +Train: [25] [6000/6250] eta: 0:00:34 lr: 0.000111 grad: 0.0703 (0.0689) loss: 0.8378 (0.8331) time: 0.1311 data: 0.0513 max mem: 9390 +Train: [25] [6100/6250] eta: 0:00:20 lr: 0.000111 grad: 0.0672 (0.0689) loss: 0.8293 (0.8330) time: 0.1351 data: 0.0495 max mem: 9390 +Train: [25] [6200/6250] eta: 0:00:06 lr: 0.000111 grad: 0.0696 (0.0690) loss: 0.8298 (0.8330) time: 0.1557 data: 0.0780 max mem: 9390 +Train: [25] [6249/6250] eta: 0:00:00 lr: 0.000111 grad: 0.0634 (0.0690) loss: 0.8313 (0.8330) time: 0.1422 data: 0.0632 max mem: 9390 +Train: [25] Total time: 0:14:27 (0.1388 s / it) +Averaged stats: lr: 0.000111 grad: 0.0634 (0.0690) loss: 0.8313 (0.8330) +Eval (hcp-train-subset): [25] [ 0/62] eta: 0:04:52 loss: 0.8540 (0.8540) time: 4.7102 data: 4.6799 max mem: 9390 +Eval (hcp-train-subset): [25] [61/62] eta: 0:00:00 loss: 0.8439 (0.8444) time: 0.1085 data: 0.0821 max mem: 9390 +Eval (hcp-train-subset): [25] Total time: 0:00:12 (0.1989 s / it) +Averaged stats (hcp-train-subset): loss: 0.8439 (0.8444) +Eval (hcp-val): [25] [ 0/62] eta: 0:05:10 loss: 0.8332 (0.8332) time: 5.0100 data: 4.9809 max mem: 9390 +Eval (hcp-val): [25] [61/62] eta: 0:00:00 loss: 0.8394 (0.8403) time: 0.1361 data: 0.1089 max mem: 9390 +Eval (hcp-val): [25] Total time: 0:00:12 (0.2084 s / it) +Averaged stats (hcp-val): loss: 0.8394 (0.8403) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +Train: [26] [ 0/6250] eta: 7:19:11 lr: 0.000111 grad: 0.1972 (0.1972) loss: 0.8285 (0.8285) time: 4.2163 data: 3.9606 max mem: 9390 +Train: [26] [ 100/6250] eta: 0:20:24 lr: 0.000111 grad: 0.0671 (0.0755) loss: 0.8339 (0.8411) time: 0.1374 data: 0.0496 max mem: 9390 +Train: [26] [ 200/6250] eta: 0:17:14 lr: 0.000110 grad: 0.0698 (0.0749) loss: 0.8230 (0.8331) time: 0.1244 data: 0.0413 max mem: 9390 +Train: [26] [ 300/6250] eta: 0:15:49 lr: 0.000110 grad: 0.0632 (0.0721) loss: 0.8284 (0.8315) time: 0.1688 data: 0.0896 max mem: 9390 +Train: [26] [ 400/6250] eta: 0:15:05 lr: 0.000110 grad: 0.0662 (0.0711) loss: 0.8274 (0.8310) time: 0.1405 data: 0.0566 max mem: 9390 +Train: [26] [ 500/6250] eta: 0:14:24 lr: 0.000110 grad: 0.0616 (0.0699) loss: 0.8314 (0.8314) time: 0.1382 data: 0.0578 max mem: 9390 +Train: [26] [ 600/6250] eta: 0:13:53 lr: 0.000110 grad: 0.0660 (0.0698) loss: 0.8334 (0.8314) time: 0.1405 data: 0.0597 max mem: 9390 +Train: [26] [ 700/6250] eta: 0:13:17 lr: 0.000110 grad: 0.0705 (0.0696) loss: 0.8298 (0.8309) time: 0.1224 data: 0.0284 max mem: 9390 +Train: [26] [ 800/6250] eta: 0:12:53 lr: 0.000110 grad: 0.0681 (0.0697) loss: 0.8297 (0.8304) time: 0.1020 data: 0.0105 max mem: 9390 +Train: [26] [ 900/6250] eta: 0:12:31 lr: 0.000110 grad: 0.0648 (0.0699) loss: 0.8276 (0.8297) time: 0.1377 data: 0.0528 max mem: 9390 +Train: [26] [1000/6250] eta: 0:12:09 lr: 0.000110 grad: 0.0670 (0.0698) loss: 0.8319 (0.8294) time: 0.1333 data: 0.0592 max mem: 9390 +Train: [26] [1100/6250] eta: 0:11:53 lr: 0.000110 grad: 0.0656 (0.0701) loss: 0.8303 (0.8291) time: 0.1335 data: 0.0553 max mem: 9390 +Train: [26] [1200/6250] eta: 0:11:45 lr: 0.000110 grad: 0.0693 (0.0702) loss: 0.8257 (0.8289) time: 0.1498 data: 0.0779 max mem: 9390 +Train: [26] [1300/6250] eta: 0:11:53 lr: 0.000110 grad: 0.0671 (0.0702) loss: 0.8313 (0.8288) time: 0.2647 data: 0.1865 max mem: 9390 +Train: [26] [1400/6250] eta: 0:11:36 lr: 0.000110 grad: 0.0626 (0.0701) loss: 0.8311 (0.8287) time: 0.1616 data: 0.0855 max mem: 9390 +Train: [26] [1500/6250] eta: 0:11:23 lr: 0.000110 grad: 0.0651 (0.0700) loss: 0.8320 (0.8287) time: 0.1466 data: 0.0660 max mem: 9390 +Train: [26] [1600/6250] eta: 0:11:14 lr: 0.000110 grad: 0.0674 (0.0699) loss: 0.8259 (0.8287) time: 0.1719 data: 0.0991 max mem: 9390 +Train: [26] [1700/6250] eta: 0:11:01 lr: 0.000110 grad: 0.0675 (0.0698) loss: 0.8297 (0.8288) time: 0.1425 data: 0.0620 max mem: 9390 +Train: [26] [1800/6250] eta: 0:10:45 lr: 0.000110 grad: 0.0703 (0.0697) loss: 0.8280 (0.8287) time: 0.1431 data: 0.0609 max mem: 9390 +Train: [26] [1900/6250] eta: 0:10:28 lr: 0.000110 grad: 0.0676 (0.0697) loss: 0.8268 (0.8285) time: 0.1287 data: 0.0509 max mem: 9390 +Train: [26] [2000/6250] eta: 0:10:09 lr: 0.000110 grad: 0.0681 (0.0697) loss: 0.8302 (0.8285) time: 0.1177 data: 0.0326 max mem: 9390 +Train: [26] [2100/6250] eta: 0:09:53 lr: 0.000110 grad: 0.0654 (0.0696) loss: 0.8309 (0.8286) time: 0.1266 data: 0.0493 max mem: 9390 +Train: [26] [2200/6250] eta: 0:09:39 lr: 0.000110 grad: 0.0665 (0.0695) loss: 0.8188 (0.8285) time: 0.1665 data: 0.0904 max mem: 9390 +Train: [26] [2300/6250] eta: 0:09:23 lr: 0.000110 grad: 0.0674 (0.0695) loss: 0.8258 (0.8285) time: 0.1480 data: 0.0724 max mem: 9390 +Train: [26] [2400/6250] eta: 0:09:08 lr: 0.000110 grad: 0.0678 (0.0695) loss: 0.8231 (0.8284) time: 0.1415 data: 0.0671 max mem: 9390 +Train: [26] [2500/6250] eta: 0:08:56 lr: 0.000110 grad: 0.0715 (0.0695) loss: 0.8277 (0.8284) time: 0.1704 data: 0.0838 max mem: 9390 +Train: [26] [2600/6250] eta: 0:08:41 lr: 0.000110 grad: 0.0681 (0.0695) loss: 0.8243 (0.8283) time: 0.1262 data: 0.0476 max mem: 9390 +Train: [26] [2700/6250] eta: 0:08:28 lr: 0.000110 grad: 0.0647 (0.0696) loss: 0.8353 (0.8283) time: 0.1336 data: 0.0576 max mem: 9390 +Train: [26] [2800/6250] eta: 0:08:12 lr: 0.000110 grad: 0.0720 (0.0696) loss: 0.8230 (0.8282) time: 0.1491 data: 0.0704 max mem: 9390 +Train: [26] [2900/6250] eta: 0:07:58 lr: 0.000110 grad: 0.0676 (0.0696) loss: 0.8226 (0.8282) time: 0.1521 data: 0.0779 max mem: 9390 +Train: [26] [3000/6250] eta: 0:07:42 lr: 0.000110 grad: 0.0707 (0.0696) loss: 0.8300 (0.8281) time: 0.1153 data: 0.0292 max mem: 9390 +Train: [26] [3100/6250] eta: 0:07:28 lr: 0.000110 grad: 0.0644 (0.0697) loss: 0.8296 (0.8280) time: 0.1516 data: 0.0676 max mem: 9390 +Train: [26] [3200/6250] eta: 0:07:14 lr: 0.000110 grad: 0.0652 (0.0698) loss: 0.8255 (0.8279) time: 0.1366 data: 0.0622 max mem: 9390 +Train: [26] [3300/6250] eta: 0:06:59 lr: 0.000110 grad: 0.0663 (0.0699) loss: 0.8260 (0.8279) time: 0.1345 data: 0.0582 max mem: 9390 +Train: [26] [3400/6250] eta: 0:06:45 lr: 0.000110 grad: 0.0661 (0.0699) loss: 0.8316 (0.8278) time: 0.1420 data: 0.0581 max mem: 9390 +Train: [26] [3500/6250] eta: 0:06:31 lr: 0.000110 grad: 0.0746 (0.0700) loss: 0.8239 (0.8277) time: 0.1618 data: 0.0765 max mem: 9390 +Train: [26] [3600/6250] eta: 0:06:17 lr: 0.000110 grad: 0.0689 (0.0700) loss: 0.8325 (0.8277) time: 0.1234 data: 0.0451 max mem: 9390 +Train: [26] [3700/6250] eta: 0:06:02 lr: 0.000110 grad: 0.0684 (0.0701) loss: 0.8244 (0.8276) time: 0.1268 data: 0.0485 max mem: 9390 +Train: [26] [3800/6250] eta: 0:05:48 lr: 0.000110 grad: 0.0662 (0.0701) loss: 0.8248 (0.8276) time: 0.1611 data: 0.0881 max mem: 9390 +Train: [26] [3900/6250] eta: 0:05:33 lr: 0.000110 grad: 0.0700 (0.0701) loss: 0.8300 (0.8277) time: 0.1256 data: 0.0451 max mem: 9390 +Train: [26] [4000/6250] eta: 0:05:18 lr: 0.000110 grad: 0.0684 (0.0701) loss: 0.8264 (0.8277) time: 0.1090 data: 0.0294 max mem: 9390 +Train: [26] [4100/6250] eta: 0:05:04 lr: 0.000110 grad: 0.0706 (0.0700) loss: 0.8309 (0.8277) time: 0.1305 data: 0.0469 max mem: 9390 +Train: [26] [4200/6250] eta: 0:04:49 lr: 0.000110 grad: 0.0682 (0.0701) loss: 0.8253 (0.8277) time: 0.1293 data: 0.0546 max mem: 9390 +Train: [26] [4300/6250] eta: 0:04:35 lr: 0.000110 grad: 0.0715 (0.0701) loss: 0.8251 (0.8277) time: 0.1390 data: 0.0585 max mem: 9390 +Train: [26] [4400/6250] eta: 0:04:20 lr: 0.000110 grad: 0.0656 (0.0701) loss: 0.8320 (0.8278) time: 0.1058 data: 0.0267 max mem: 9390 +Train: [26] [4500/6250] eta: 0:04:06 lr: 0.000110 grad: 0.0674 (0.0701) loss: 0.8317 (0.8278) time: 0.1218 data: 0.0456 max mem: 9390 +Train: [26] [4600/6250] eta: 0:03:52 lr: 0.000110 grad: 0.0703 (0.0702) loss: 0.8335 (0.8279) time: 0.1422 data: 0.0656 max mem: 9390 +Train: [26] [4700/6250] eta: 0:03:37 lr: 0.000110 grad: 0.0655 (0.0701) loss: 0.8382 (0.8280) time: 0.1453 data: 0.0679 max mem: 9390 +Train: [26] [4800/6250] eta: 0:03:23 lr: 0.000109 grad: 0.0668 (0.0701) loss: 0.8314 (0.8281) time: 0.1454 data: 0.0666 max mem: 9390 +Train: [26] [4900/6250] eta: 0:03:09 lr: 0.000109 grad: 0.0670 (0.0702) loss: 0.8263 (0.8281) time: 0.1409 data: 0.0671 max mem: 9390 +Train: [26] [5000/6250] eta: 0:02:54 lr: 0.000109 grad: 0.0638 (0.0702) loss: 0.8319 (0.8281) time: 0.1497 data: 0.0611 max mem: 9390 +Train: [26] [5100/6250] eta: 0:02:40 lr: 0.000109 grad: 0.0657 (0.0701) loss: 0.8298 (0.8282) time: 0.1195 data: 0.0412 max mem: 9390 +Train: [26] [5200/6250] eta: 0:02:26 lr: 0.000109 grad: 0.0641 (0.0701) loss: 0.8277 (0.8283) time: 0.1461 data: 0.0618 max mem: 9390 +Train: [26] [5300/6250] eta: 0:02:12 lr: 0.000109 grad: 0.0692 (0.0701) loss: 0.8305 (0.8283) time: 0.1290 data: 0.0518 max mem: 9390 +Train: [26] [5400/6250] eta: 0:01:58 lr: 0.000109 grad: 0.0594 (0.0700) loss: 0.8380 (0.8284) time: 0.1318 data: 0.0499 max mem: 9390 +Train: [26] [5500/6250] eta: 0:01:44 lr: 0.000109 grad: 0.0632 (0.0700) loss: 0.8358 (0.8285) time: 0.1296 data: 0.0517 max mem: 9390 +Train: [26] [5600/6250] eta: 0:01:30 lr: 0.000109 grad: 0.0677 (0.0700) loss: 0.8302 (0.8285) time: 0.1595 data: 0.0809 max mem: 9390 +Train: [26] [5700/6250] eta: 0:01:16 lr: 0.000109 grad: 0.0684 (0.0700) loss: 0.8318 (0.8286) time: 0.1144 data: 0.0407 max mem: 9390 +Train: [26] [5800/6250] eta: 0:01:02 lr: 0.000109 grad: 0.0679 (0.0699) loss: 0.8297 (0.8286) time: 0.1297 data: 0.0528 max mem: 9390 +Train: [26] [5900/6250] eta: 0:00:48 lr: 0.000109 grad: 0.0675 (0.0699) loss: 0.8271 (0.8287) time: 0.1339 data: 0.0561 max mem: 9390 +Train: [26] [6000/6250] eta: 0:00:34 lr: 0.000109 grad: 0.0721 (0.0700) loss: 0.8293 (0.8287) time: 0.1026 data: 0.0228 max mem: 9390 +Train: [26] [6100/6250] eta: 0:00:20 lr: 0.000109 grad: 0.0698 (0.0700) loss: 0.8230 (0.8287) time: 0.1296 data: 0.0563 max mem: 9390 +Train: [26] [6200/6250] eta: 0:00:06 lr: 0.000109 grad: 0.0701 (0.0700) loss: 0.8321 (0.8286) time: 0.1377 data: 0.0602 max mem: 9390 +Train: [26] [6249/6250] eta: 0:00:00 lr: 0.000109 grad: 0.0709 (0.0701) loss: 0.8283 (0.8286) time: 0.1218 data: 0.0413 max mem: 9390 +Train: [26] Total time: 0:14:28 (0.1390 s / it) +Averaged stats: lr: 0.000109 grad: 0.0709 (0.0701) loss: 0.8283 (0.8286) +Eval (hcp-train-subset): [26] [ 0/62] eta: 0:05:10 loss: 0.8563 (0.8563) time: 5.0025 data: 4.9708 max mem: 9390 +Eval (hcp-train-subset): [26] [61/62] eta: 0:00:00 loss: 0.8389 (0.8425) time: 0.1220 data: 0.0973 max mem: 9390 +Eval (hcp-train-subset): [26] Total time: 0:00:12 (0.1970 s / it) +Averaged stats (hcp-train-subset): loss: 0.8389 (0.8425) +Eval (hcp-val): [26] [ 0/62] eta: 0:04:16 loss: 0.8366 (0.8366) time: 4.1396 data: 4.1085 max mem: 9390 +Eval (hcp-val): [26] [61/62] eta: 0:00:00 loss: 0.8396 (0.8391) time: 0.1424 data: 0.1155 max mem: 9390 +Eval (hcp-val): [26] Total time: 0:00:12 (0.2043 s / it) +Averaged stats (hcp-val): loss: 0.8396 (0.8391) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +Train: [27] [ 0/6250] eta: 7:20:31 lr: 0.000109 grad: 0.0903 (0.0903) loss: 0.8212 (0.8212) time: 4.2291 data: 3.9756 max mem: 9390 +Train: [27] [ 100/6250] eta: 0:19:14 lr: 0.000109 grad: 0.0758 (0.0793) loss: 0.8347 (0.8362) time: 0.1551 data: 0.0741 max mem: 9390 +Train: [27] [ 200/6250] eta: 0:16:26 lr: 0.000109 grad: 0.0702 (0.0776) loss: 0.8302 (0.8329) time: 0.1246 data: 0.0432 max mem: 9390 +Train: [27] [ 300/6250] eta: 0:15:37 lr: 0.000109 grad: 0.0715 (0.0765) loss: 0.8279 (0.8314) time: 0.1570 data: 0.0801 max mem: 9390 +Train: [27] [ 400/6250] eta: 0:14:55 lr: 0.000109 grad: 0.0641 (0.0756) loss: 0.8342 (0.8309) time: 0.1516 data: 0.0774 max mem: 9390 +Train: [27] [ 500/6250] eta: 0:14:24 lr: 0.000109 grad: 0.0729 (0.0751) loss: 0.8294 (0.8306) time: 0.1320 data: 0.0490 max mem: 9390 +Train: [27] [ 600/6250] eta: 0:13:54 lr: 0.000109 grad: 0.0724 (0.0748) loss: 0.8310 (0.8307) time: 0.1344 data: 0.0537 max mem: 9390 +Train: [27] [ 700/6250] eta: 0:13:26 lr: 0.000109 grad: 0.0657 (0.0742) loss: 0.8267 (0.8310) time: 0.1332 data: 0.0460 max mem: 9390 +Train: [27] [ 800/6250] eta: 0:13:01 lr: 0.000109 grad: 0.0661 (0.0736) loss: 0.8282 (0.8311) time: 0.1326 data: 0.0451 max mem: 9390 +Train: [27] [ 900/6250] eta: 0:12:36 lr: 0.000109 grad: 0.0648 (0.0731) loss: 0.8279 (0.8309) time: 0.1384 data: 0.0569 max mem: 9390 +Train: [27] [1000/6250] eta: 0:12:15 lr: 0.000109 grad: 0.0672 (0.0726) loss: 0.8229 (0.8309) time: 0.1277 data: 0.0445 max mem: 9390 +Train: [27] [1100/6250] eta: 0:11:55 lr: 0.000109 grad: 0.0618 (0.0723) loss: 0.8331 (0.8308) time: 0.1231 data: 0.0423 max mem: 9390 +Train: [27] [1200/6250] eta: 0:11:39 lr: 0.000109 grad: 0.0663 (0.0719) loss: 0.8300 (0.8308) time: 0.1447 data: 0.0600 max mem: 9390 +Train: [27] [1300/6250] eta: 0:11:28 lr: 0.000109 grad: 0.0667 (0.0716) loss: 0.8311 (0.8308) time: 0.1236 data: 0.0430 max mem: 9390 +Train: [27] [1400/6250] eta: 0:11:20 lr: 0.000109 grad: 0.0703 (0.0715) loss: 0.8248 (0.8306) time: 0.1823 data: 0.1083 max mem: 9390 +Train: [27] [1500/6250] eta: 0:11:13 lr: 0.000109 grad: 0.0659 (0.0713) loss: 0.8260 (0.8305) time: 0.1374 data: 0.0589 max mem: 9390 +Train: [27] [1600/6250] eta: 0:11:02 lr: 0.000109 grad: 0.0658 (0.0713) loss: 0.8348 (0.8304) time: 0.1667 data: 0.0956 max mem: 9390 +Train: [27] [1700/6250] eta: 0:10:49 lr: 0.000109 grad: 0.0684 (0.0712) loss: 0.8308 (0.8305) time: 0.1474 data: 0.0679 max mem: 9390 +Train: [27] [1800/6250] eta: 0:10:38 lr: 0.000109 grad: 0.0685 (0.0712) loss: 0.8279 (0.8304) time: 0.1413 data: 0.0641 max mem: 9390 +Train: [27] [1900/6250] eta: 0:10:25 lr: 0.000109 grad: 0.0630 (0.0711) loss: 0.8374 (0.8303) time: 0.1382 data: 0.0607 max mem: 9390 +Train: [27] [2000/6250] eta: 0:10:10 lr: 0.000109 grad: 0.0663 (0.0710) loss: 0.8312 (0.8304) time: 0.1178 data: 0.0396 max mem: 9390 +Train: [27] [2100/6250] eta: 0:09:54 lr: 0.000109 grad: 0.0665 (0.0711) loss: 0.8286 (0.8303) time: 0.1436 data: 0.0659 max mem: 9390 +Train: [27] [2200/6250] eta: 0:09:38 lr: 0.000109 grad: 0.0666 (0.0709) loss: 0.8320 (0.8303) time: 0.1178 data: 0.0374 max mem: 9390 +Train: [27] [2300/6250] eta: 0:09:22 lr: 0.000109 grad: 0.0659 (0.0708) loss: 0.8326 (0.8304) time: 0.1414 data: 0.0659 max mem: 9390 +Train: [27] [2400/6250] eta: 0:09:08 lr: 0.000109 grad: 0.0706 (0.0707) loss: 0.8249 (0.8304) time: 0.1547 data: 0.0719 max mem: 9390 +Train: [27] [2500/6250] eta: 0:08:53 lr: 0.000109 grad: 0.0704 (0.0708) loss: 0.8269 (0.8303) time: 0.1174 data: 0.0364 max mem: 9390 +Train: [27] [2600/6250] eta: 0:08:37 lr: 0.000109 grad: 0.0663 (0.0708) loss: 0.8284 (0.8302) time: 0.1253 data: 0.0457 max mem: 9390 +Train: [27] [2700/6250] eta: 0:08:23 lr: 0.000109 grad: 0.0715 (0.0708) loss: 0.8310 (0.8302) time: 0.1407 data: 0.0606 max mem: 9390 +Train: [27] [2800/6250] eta: 0:08:08 lr: 0.000109 grad: 0.0616 (0.0708) loss: 0.8307 (0.8302) time: 0.1355 data: 0.0588 max mem: 9390 +Train: [27] [2900/6250] eta: 0:07:55 lr: 0.000109 grad: 0.0663 (0.0708) loss: 0.8269 (0.8302) time: 0.1399 data: 0.0608 max mem: 9390 +Train: [27] [3000/6250] eta: 0:07:40 lr: 0.000109 grad: 0.0626 (0.0707) loss: 0.8308 (0.8301) time: 0.1463 data: 0.0720 max mem: 9390 +Train: [27] [3100/6250] eta: 0:07:25 lr: 0.000108 grad: 0.0639 (0.0707) loss: 0.8362 (0.8301) time: 0.1569 data: 0.0792 max mem: 9390 +Train: [27] [3200/6250] eta: 0:07:11 lr: 0.000108 grad: 0.0684 (0.0707) loss: 0.8260 (0.8300) time: 0.1347 data: 0.0468 max mem: 9390 +Train: [27] [3300/6250] eta: 0:06:56 lr: 0.000108 grad: 0.0668 (0.0707) loss: 0.8331 (0.8298) time: 0.1418 data: 0.0611 max mem: 9390 +Train: [27] [3400/6250] eta: 0:06:42 lr: 0.000108 grad: 0.0682 (0.0707) loss: 0.8229 (0.8298) time: 0.1316 data: 0.0466 max mem: 9390 +Train: [27] [3500/6250] eta: 0:06:28 lr: 0.000108 grad: 0.0649 (0.0707) loss: 0.8309 (0.8298) time: 0.1323 data: 0.0523 max mem: 9390 +Train: [27] [3600/6250] eta: 0:06:13 lr: 0.000108 grad: 0.0651 (0.0707) loss: 0.8265 (0.8297) time: 0.1423 data: 0.0577 max mem: 9390 +Train: [27] [3700/6250] eta: 0:05:59 lr: 0.000108 grad: 0.0683 (0.0707) loss: 0.8243 (0.8297) time: 0.1452 data: 0.0680 max mem: 9390 +Train: [27] [3800/6250] eta: 0:05:44 lr: 0.000108 grad: 0.0666 (0.0707) loss: 0.8363 (0.8297) time: 0.1476 data: 0.0701 max mem: 9390 +Train: [27] [3900/6250] eta: 0:05:29 lr: 0.000108 grad: 0.0720 (0.0707) loss: 0.8286 (0.8297) time: 0.1186 data: 0.0421 max mem: 9390 +Train: [27] [4000/6250] eta: 0:05:15 lr: 0.000108 grad: 0.0684 (0.0707) loss: 0.8285 (0.8297) time: 0.1301 data: 0.0551 max mem: 9390 +Train: [27] [4100/6250] eta: 0:05:00 lr: 0.000108 grad: 0.0689 (0.0707) loss: 0.8315 (0.8297) time: 0.1507 data: 0.0709 max mem: 9390 +Train: [27] [4200/6250] eta: 0:04:46 lr: 0.000108 grad: 0.0699 (0.0706) loss: 0.8315 (0.8298) time: 0.1265 data: 0.0507 max mem: 9390 +Train: [27] [4300/6250] eta: 0:04:32 lr: 0.000108 grad: 0.0688 (0.0706) loss: 0.8319 (0.8298) time: 0.1464 data: 0.0693 max mem: 9390 +Train: [27] [4400/6250] eta: 0:04:17 lr: 0.000108 grad: 0.0642 (0.0706) loss: 0.8314 (0.8298) time: 0.1288 data: 0.0544 max mem: 9390 +Train: [27] [4500/6250] eta: 0:04:03 lr: 0.000108 grad: 0.0705 (0.0706) loss: 0.8273 (0.8298) time: 0.1293 data: 0.0482 max mem: 9390 +Train: [27] [4600/6250] eta: 0:03:49 lr: 0.000108 grad: 0.0679 (0.0707) loss: 0.8306 (0.8298) time: 0.1291 data: 0.0512 max mem: 9390 +Train: [27] [4700/6250] eta: 0:03:35 lr: 0.000108 grad: 0.0705 (0.0706) loss: 0.8291 (0.8298) time: 0.1381 data: 0.0598 max mem: 9390 +Train: [27] [4800/6250] eta: 0:03:21 lr: 0.000108 grad: 0.0675 (0.0706) loss: 0.8302 (0.8298) time: 0.1012 data: 0.0199 max mem: 9390 +Train: [27] [4900/6250] eta: 0:03:06 lr: 0.000108 grad: 0.0672 (0.0706) loss: 0.8309 (0.8298) time: 0.1307 data: 0.0422 max mem: 9390 +Train: [27] [5000/6250] eta: 0:02:52 lr: 0.000108 grad: 0.0685 (0.0706) loss: 0.8328 (0.8298) time: 0.1348 data: 0.0627 max mem: 9390 +Train: [27] [5100/6250] eta: 0:02:38 lr: 0.000108 grad: 0.0702 (0.0706) loss: 0.8298 (0.8298) time: 0.1453 data: 0.0620 max mem: 9390 +Train: [27] [5200/6250] eta: 0:02:24 lr: 0.000108 grad: 0.0678 (0.0705) loss: 0.8250 (0.8298) time: 0.1386 data: 0.0546 max mem: 9390 +Train: [27] [5300/6250] eta: 0:02:11 lr: 0.000108 grad: 0.0744 (0.0706) loss: 0.8304 (0.8299) time: 0.1373 data: 0.0592 max mem: 9390 +Train: [27] [5400/6250] eta: 0:01:57 lr: 0.000108 grad: 0.0696 (0.0706) loss: 0.8320 (0.8299) time: 0.1278 data: 0.0503 max mem: 9390 +Train: [27] [5500/6250] eta: 0:01:43 lr: 0.000108 grad: 0.0712 (0.0706) loss: 0.8272 (0.8300) time: 0.1187 data: 0.0399 max mem: 9390 +Train: [27] [5600/6250] eta: 0:01:29 lr: 0.000108 grad: 0.0677 (0.0705) loss: 0.8327 (0.8300) time: 0.1341 data: 0.0610 max mem: 9390 +Train: [27] [5700/6250] eta: 0:01:15 lr: 0.000108 grad: 0.0679 (0.0705) loss: 0.8361 (0.8301) time: 0.1442 data: 0.0634 max mem: 9390 +Train: [27] [5800/6250] eta: 0:01:02 lr: 0.000108 grad: 0.0733 (0.0705) loss: 0.8294 (0.8301) time: 0.1466 data: 0.0605 max mem: 9390 +Train: [27] [5900/6250] eta: 0:00:48 lr: 0.000108 grad: 0.0685 (0.0706) loss: 0.8316 (0.8301) time: 0.1428 data: 0.0648 max mem: 9390 +Train: [27] [6000/6250] eta: 0:00:34 lr: 0.000108 grad: 0.0665 (0.0706) loss: 0.8306 (0.8302) time: 0.1286 data: 0.0494 max mem: 9390 +Train: [27] [6100/6250] eta: 0:00:20 lr: 0.000108 grad: 0.0718 (0.0706) loss: 0.8288 (0.8302) time: 0.1139 data: 0.0326 max mem: 9390 +Train: [27] [6200/6250] eta: 0:00:06 lr: 0.000108 grad: 0.0656 (0.0706) loss: 0.8299 (0.8302) time: 0.1376 data: 0.0517 max mem: 9390 +Train: [27] [6249/6250] eta: 0:00:00 lr: 0.000108 grad: 0.0698 (0.0706) loss: 0.8228 (0.8302) time: 0.1373 data: 0.0588 max mem: 9390 +Train: [27] Total time: 0:14:27 (0.1388 s / it) +Averaged stats: lr: 0.000108 grad: 0.0698 (0.0706) loss: 0.8228 (0.8302) +Eval (hcp-train-subset): [27] [ 0/62] eta: 0:04:30 loss: 0.8543 (0.8543) time: 4.3573 data: 4.3268 max mem: 9390 +Eval (hcp-train-subset): [27] [61/62] eta: 0:00:00 loss: 0.8441 (0.8436) time: 0.1101 data: 0.0852 max mem: 9390 +Eval (hcp-train-subset): [27] Total time: 0:00:12 (0.2003 s / it) +Averaged stats (hcp-train-subset): loss: 0.8441 (0.8436) +Eval (hcp-val): [27] [ 0/62] eta: 0:05:06 loss: 0.8361 (0.8361) time: 4.9379 data: 4.8952 max mem: 9390 +Eval (hcp-val): [27] [61/62] eta: 0:00:00 loss: 0.8384 (0.8394) time: 0.1210 data: 0.0959 max mem: 9390 +Eval (hcp-val): [27] Total time: 0:00:12 (0.2042 s / it) +Averaged stats (hcp-val): loss: 0.8384 (0.8394) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +Train: [28] [ 0/6250] eta: 8:09:13 lr: 0.000108 grad: 0.0624 (0.0624) loss: 0.8584 (0.8584) time: 4.6965 data: 4.5304 max mem: 9390 +Train: [28] [ 100/6250] eta: 0:19:41 lr: 0.000108 grad: 0.0792 (0.0789) loss: 0.8249 (0.8378) time: 0.1633 data: 0.0886 max mem: 9390 +Train: [28] [ 200/6250] eta: 0:17:08 lr: 0.000108 grad: 0.0673 (0.0750) loss: 0.8276 (0.8323) time: 0.1878 data: 0.1070 max mem: 9390 +Train: [28] [ 300/6250] eta: 0:15:27 lr: 0.000108 grad: 0.0646 (0.0733) loss: 0.8365 (0.8315) time: 0.1577 data: 0.0767 max mem: 9390 +Train: [28] [ 400/6250] eta: 0:14:46 lr: 0.000108 grad: 0.0622 (0.0718) loss: 0.8387 (0.8321) time: 0.1426 data: 0.0666 max mem: 9390 +Train: [28] [ 500/6250] eta: 0:14:19 lr: 0.000108 grad: 0.0696 (0.0714) loss: 0.8275 (0.8321) time: 0.1625 data: 0.0840 max mem: 9390 +Train: [28] [ 600/6250] eta: 0:13:51 lr: 0.000108 grad: 0.0628 (0.0709) loss: 0.8376 (0.8323) time: 0.1228 data: 0.0414 max mem: 9390 +Train: [28] [ 700/6250] eta: 0:13:31 lr: 0.000108 grad: 0.0634 (0.0703) loss: 0.8402 (0.8326) time: 0.1456 data: 0.0667 max mem: 9390 +Train: [28] [ 800/6250] eta: 0:13:04 lr: 0.000108 grad: 0.0639 (0.0697) loss: 0.8389 (0.8329) time: 0.1322 data: 0.0487 max mem: 9390 +Train: [28] [ 900/6250] eta: 0:12:41 lr: 0.000108 grad: 0.0621 (0.0693) loss: 0.8332 (0.8330) time: 0.1416 data: 0.0621 max mem: 9390 +Train: [28] [1000/6250] eta: 0:12:14 lr: 0.000108 grad: 0.0642 (0.0691) loss: 0.8353 (0.8331) time: 0.1221 data: 0.0352 max mem: 9390 +Train: [28] [1100/6250] eta: 0:11:53 lr: 0.000108 grad: 0.0642 (0.0690) loss: 0.8330 (0.8331) time: 0.1270 data: 0.0452 max mem: 9390 +Train: [28] [1200/6250] eta: 0:11:36 lr: 0.000108 grad: 0.0649 (0.0692) loss: 0.8312 (0.8329) time: 0.1393 data: 0.0628 max mem: 9390 +Train: [28] [1300/6250] eta: 0:11:23 lr: 0.000107 grad: 0.0679 (0.0692) loss: 0.8274 (0.8326) time: 0.1490 data: 0.0720 max mem: 9390 +Train: [28] [1400/6250] eta: 0:11:07 lr: 0.000107 grad: 0.0739 (0.0694) loss: 0.8198 (0.8321) time: 0.1363 data: 0.0577 max mem: 9390 +Train: [28] [1500/6250] eta: 0:10:55 lr: 0.000107 grad: 0.0702 (0.0695) loss: 0.8267 (0.8318) time: 0.1448 data: 0.0655 max mem: 9390 +Train: [28] [1600/6250] eta: 0:10:49 lr: 0.000107 grad: 0.0704 (0.0696) loss: 0.8265 (0.8315) time: 0.1628 data: 0.0810 max mem: 9390 +Train: [28] [1700/6250] eta: 0:10:40 lr: 0.000107 grad: 0.0726 (0.0698) loss: 0.8239 (0.8312) time: 0.1494 data: 0.0721 max mem: 9390 +Train: [28] [1800/6250] eta: 0:10:30 lr: 0.000107 grad: 0.0701 (0.0700) loss: 0.8245 (0.8310) time: 0.1645 data: 0.0878 max mem: 9390 +Train: [28] [1900/6250] eta: 0:10:19 lr: 0.000107 grad: 0.0702 (0.0701) loss: 0.8283 (0.8308) time: 0.1757 data: 0.0917 max mem: 9390 +Train: [28] [2000/6250] eta: 0:10:05 lr: 0.000107 grad: 0.0663 (0.0702) loss: 0.8339 (0.8308) time: 0.1490 data: 0.0693 max mem: 9390 +Train: [28] [2100/6250] eta: 0:09:50 lr: 0.000107 grad: 0.0653 (0.0702) loss: 0.8288 (0.8307) time: 0.1332 data: 0.0588 max mem: 9390 +Train: [28] [2200/6250] eta: 0:09:34 lr: 0.000107 grad: 0.0704 (0.0702) loss: 0.8213 (0.8306) time: 0.1213 data: 0.0336 max mem: 9390 +Train: [28] [2300/6250] eta: 0:09:19 lr: 0.000107 grad: 0.0693 (0.0703) loss: 0.8264 (0.8304) time: 0.1348 data: 0.0525 max mem: 9390 +Train: [28] [2400/6250] eta: 0:09:03 lr: 0.000107 grad: 0.0700 (0.0704) loss: 0.8293 (0.8303) time: 0.1113 data: 0.0303 max mem: 9390 +Train: [28] [2500/6250] eta: 0:08:51 lr: 0.000107 grad: 0.0695 (0.0704) loss: 0.8307 (0.8302) time: 0.2000 data: 0.1193 max mem: 9390 +Train: [28] [2600/6250] eta: 0:08:35 lr: 0.000107 grad: 0.0698 (0.0704) loss: 0.8249 (0.8301) time: 0.1520 data: 0.0698 max mem: 9390 +Train: [28] [2700/6250] eta: 0:08:20 lr: 0.000107 grad: 0.0666 (0.0704) loss: 0.8266 (0.8302) time: 0.1461 data: 0.0657 max mem: 9390 +Train: [28] [2800/6250] eta: 0:08:07 lr: 0.000107 grad: 0.0698 (0.0704) loss: 0.8298 (0.8302) time: 0.1931 data: 0.1123 max mem: 9390 +Train: [28] [2900/6250] eta: 0:07:51 lr: 0.000107 grad: 0.0693 (0.0704) loss: 0.8326 (0.8302) time: 0.1304 data: 0.0517 max mem: 9390 +Train: [28] [3000/6250] eta: 0:07:36 lr: 0.000107 grad: 0.0662 (0.0703) loss: 0.8323 (0.8303) time: 0.1486 data: 0.0698 max mem: 9390 +Train: [28] [3100/6250] eta: 0:07:20 lr: 0.000107 grad: 0.0661 (0.0703) loss: 0.8322 (0.8303) time: 0.1103 data: 0.0269 max mem: 9390 +Train: [28] [3200/6250] eta: 0:07:05 lr: 0.000107 grad: 0.0660 (0.0702) loss: 0.8358 (0.8304) time: 0.1269 data: 0.0492 max mem: 9390 +Train: [28] [3300/6250] eta: 0:06:50 lr: 0.000107 grad: 0.0649 (0.0702) loss: 0.8286 (0.8305) time: 0.1233 data: 0.0451 max mem: 9390 +Train: [28] [3400/6250] eta: 0:06:36 lr: 0.000107 grad: 0.0647 (0.0702) loss: 0.8319 (0.8305) time: 0.1317 data: 0.0493 max mem: 9390 +Train: [28] [3500/6250] eta: 0:06:21 lr: 0.000107 grad: 0.0648 (0.0701) loss: 0.8278 (0.8306) time: 0.1160 data: 0.0283 max mem: 9390 +Train: [28] [3600/6250] eta: 0:06:07 lr: 0.000107 grad: 0.0669 (0.0701) loss: 0.8284 (0.8306) time: 0.1327 data: 0.0564 max mem: 9390 +Train: [28] [3700/6250] eta: 0:05:52 lr: 0.000107 grad: 0.0692 (0.0701) loss: 0.8341 (0.8307) time: 0.1270 data: 0.0524 max mem: 9390 +Train: [28] [3800/6250] eta: 0:05:38 lr: 0.000107 grad: 0.0675 (0.0701) loss: 0.8323 (0.8307) time: 0.1374 data: 0.0606 max mem: 9390 +Train: [28] [3900/6250] eta: 0:05:24 lr: 0.000107 grad: 0.0695 (0.0701) loss: 0.8308 (0.8308) time: 0.1369 data: 0.0606 max mem: 9390 +Train: [28] [4000/6250] eta: 0:05:10 lr: 0.000107 grad: 0.0713 (0.0701) loss: 0.8307 (0.8309) time: 0.1293 data: 0.0412 max mem: 9390 +Train: [28] [4100/6250] eta: 0:04:56 lr: 0.000107 grad: 0.0645 (0.0700) loss: 0.8391 (0.8309) time: 0.1442 data: 0.0626 max mem: 9390 +Train: [28] [4200/6250] eta: 0:04:42 lr: 0.000107 grad: 0.0655 (0.0700) loss: 0.8328 (0.8310) time: 0.1461 data: 0.0655 max mem: 9390 +Train: [28] [4300/6250] eta: 0:04:29 lr: 0.000107 grad: 0.0695 (0.0700) loss: 0.8354 (0.8310) time: 0.1326 data: 0.0498 max mem: 9390 +Train: [28] [4400/6250] eta: 0:04:14 lr: 0.000107 grad: 0.0691 (0.0699) loss: 0.8274 (0.8310) time: 0.1399 data: 0.0689 max mem: 9390 +Train: [28] [4500/6250] eta: 0:04:00 lr: 0.000107 grad: 0.0638 (0.0699) loss: 0.8318 (0.8310) time: 0.1199 data: 0.0405 max mem: 9390 +Train: [28] [4600/6250] eta: 0:03:47 lr: 0.000107 grad: 0.0676 (0.0699) loss: 0.8368 (0.8311) time: 0.1504 data: 0.0687 max mem: 9390 +Train: [28] [4700/6250] eta: 0:03:34 lr: 0.000107 grad: 0.0656 (0.0698) loss: 0.8334 (0.8311) time: 0.1021 data: 0.0158 max mem: 9390 +Train: [28] [4800/6250] eta: 0:03:20 lr: 0.000107 grad: 0.0692 (0.0698) loss: 0.8313 (0.8312) time: 0.1261 data: 0.0450 max mem: 9390 +Train: [28] [4900/6250] eta: 0:03:06 lr: 0.000107 grad: 0.0693 (0.0699) loss: 0.8314 (0.8312) time: 0.1357 data: 0.0493 max mem: 9390 +Train: [28] [5000/6250] eta: 0:02:52 lr: 0.000107 grad: 0.0692 (0.0699) loss: 0.8288 (0.8312) time: 0.1231 data: 0.0429 max mem: 9390 +Train: [28] [5100/6250] eta: 0:02:39 lr: 0.000107 grad: 0.0667 (0.0700) loss: 0.8376 (0.8312) time: 0.1493 data: 0.0700 max mem: 9390 +Train: [28] [5200/6250] eta: 0:02:25 lr: 0.000107 grad: 0.0643 (0.0700) loss: 0.8354 (0.8312) time: 0.1504 data: 0.0654 max mem: 9390 +Train: [28] [5300/6250] eta: 0:02:11 lr: 0.000107 grad: 0.0674 (0.0700) loss: 0.8333 (0.8312) time: 0.1313 data: 0.0549 max mem: 9390 +Train: [28] [5400/6250] eta: 0:01:57 lr: 0.000107 grad: 0.0669 (0.0700) loss: 0.8341 (0.8313) time: 0.1325 data: 0.0432 max mem: 9390 +Train: [28] [5500/6250] eta: 0:01:44 lr: 0.000107 grad: 0.0632 (0.0699) loss: 0.8348 (0.8313) time: 0.1373 data: 0.0548 max mem: 9390 +Train: [28] [5600/6250] eta: 0:01:30 lr: 0.000106 grad: 0.0735 (0.0699) loss: 0.8287 (0.8313) time: 0.1417 data: 0.0646 max mem: 9390 +Train: [28] [5700/6250] eta: 0:01:16 lr: 0.000106 grad: 0.0695 (0.0699) loss: 0.8320 (0.8313) time: 0.1425 data: 0.0655 max mem: 9390 +Train: [28] [5800/6250] eta: 0:01:02 lr: 0.000106 grad: 0.0647 (0.0699) loss: 0.8324 (0.8313) time: 0.1376 data: 0.0530 max mem: 9390 +Train: [28] [5900/6250] eta: 0:00:48 lr: 0.000106 grad: 0.0658 (0.0699) loss: 0.8338 (0.8313) time: 0.1665 data: 0.0867 max mem: 9390 +Train: [28] [6000/6250] eta: 0:00:34 lr: 0.000106 grad: 0.0694 (0.0700) loss: 0.8254 (0.8313) time: 0.1491 data: 0.0668 max mem: 9390 +Train: [28] [6100/6250] eta: 0:00:20 lr: 0.000106 grad: 0.0669 (0.0700) loss: 0.8338 (0.8313) time: 0.1472 data: 0.0700 max mem: 9390 +Train: [28] [6200/6250] eta: 0:00:06 lr: 0.000106 grad: 0.0718 (0.0700) loss: 0.8314 (0.8313) time: 0.1337 data: 0.0599 max mem: 9390 +Train: [28] [6249/6250] eta: 0:00:00 lr: 0.000106 grad: 0.0657 (0.0701) loss: 0.8359 (0.8313) time: 0.1348 data: 0.0591 max mem: 9390 +Train: [28] Total time: 0:14:36 (0.1403 s / it) +Averaged stats: lr: 0.000106 grad: 0.0657 (0.0701) loss: 0.8359 (0.8313) +Eval (hcp-train-subset): [28] [ 0/62] eta: 0:03:07 loss: 0.8538 (0.8538) time: 3.0175 data: 2.9586 max mem: 9390 +Eval (hcp-train-subset): [28] [61/62] eta: 0:00:00 loss: 0.8418 (0.8423) time: 0.1312 data: 0.1064 max mem: 9390 +Eval (hcp-train-subset): [28] Total time: 0:00:12 (0.2051 s / it) +Averaged stats (hcp-train-subset): loss: 0.8418 (0.8423) +Eval (hcp-val): [28] [ 0/62] eta: 0:04:58 loss: 0.8346 (0.8346) time: 4.8097 data: 4.7805 max mem: 9390 +Eval (hcp-val): [28] [61/62] eta: 0:00:00 loss: 0.8383 (0.8391) time: 0.1202 data: 0.0949 max mem: 9390 +Eval (hcp-val): [28] Total time: 0:00:12 (0.1992 s / it) +Averaged stats (hcp-val): loss: 0.8383 (0.8391) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +Train: [29] [ 0/6250] eta: 11:20:33 lr: 0.000106 grad: 0.1601 (0.1601) loss: 0.8660 (0.8660) time: 6.5333 data: 6.4386 max mem: 9390 +Train: [29] [ 100/6250] eta: 0:20:37 lr: 0.000106 grad: 0.0684 (0.0729) loss: 0.8316 (0.8377) time: 0.1500 data: 0.0695 max mem: 9390 +Train: [29] [ 200/6250] eta: 0:17:29 lr: 0.000106 grad: 0.0694 (0.0731) loss: 0.8246 (0.8326) time: 0.1544 data: 0.0704 max mem: 9390 +Train: [29] [ 300/6250] eta: 0:16:14 lr: 0.000106 grad: 0.0693 (0.0739) loss: 0.8241 (0.8299) time: 0.1250 data: 0.0399 max mem: 9390 +Train: [29] [ 400/6250] eta: 0:15:08 lr: 0.000106 grad: 0.0693 (0.0735) loss: 0.8263 (0.8288) time: 0.1331 data: 0.0489 max mem: 9390 +Train: [29] [ 500/6250] eta: 0:14:22 lr: 0.000106 grad: 0.0627 (0.0728) loss: 0.8302 (0.8292) time: 0.1343 data: 0.0530 max mem: 9390 +Train: [29] [ 600/6250] eta: 0:14:13 lr: 0.000106 grad: 0.0593 (0.0720) loss: 0.8411 (0.8303) time: 0.1540 data: 0.0746 max mem: 9390 +Train: [29] [ 700/6250] eta: 0:13:52 lr: 0.000106 grad: 0.0652 (0.0714) loss: 0.8328 (0.8308) time: 0.1045 data: 0.0144 max mem: 9390 +Train: [29] [ 800/6250] eta: 0:13:34 lr: 0.000106 grad: 0.0675 (0.0708) loss: 0.8291 (0.8313) time: 0.1541 data: 0.0749 max mem: 9390 +Train: [29] [ 900/6250] eta: 0:13:11 lr: 0.000106 grad: 0.0656 (0.0704) loss: 0.8353 (0.8318) time: 0.1340 data: 0.0501 max mem: 9390 +Train: [29] [1000/6250] eta: 0:12:47 lr: 0.000106 grad: 0.0587 (0.0700) loss: 0.8395 (0.8321) time: 0.1281 data: 0.0545 max mem: 9390 +Train: [29] [1100/6250] eta: 0:12:23 lr: 0.000106 grad: 0.0672 (0.0699) loss: 0.8277 (0.8320) time: 0.1236 data: 0.0400 max mem: 9390 +Train: [29] [1200/6250] eta: 0:12:01 lr: 0.000106 grad: 0.0700 (0.0697) loss: 0.8279 (0.8318) time: 0.1280 data: 0.0405 max mem: 9390 +Train: [29] [1300/6250] eta: 0:11:41 lr: 0.000106 grad: 0.0658 (0.0697) loss: 0.8275 (0.8318) time: 0.1346 data: 0.0469 max mem: 9390 +Train: [29] [1400/6250] eta: 0:11:22 lr: 0.000106 grad: 0.0623 (0.0697) loss: 0.8370 (0.8319) time: 0.1160 data: 0.0373 max mem: 9390 +Train: [29] [1500/6250] eta: 0:11:06 lr: 0.000106 grad: 0.0735 (0.0698) loss: 0.8239 (0.8315) time: 0.1466 data: 0.0695 max mem: 9390 +Train: [29] [1600/6250] eta: 0:10:51 lr: 0.000106 grad: 0.0675 (0.0698) loss: 0.8298 (0.8315) time: 0.1436 data: 0.0721 max mem: 9390 +Train: [29] [1700/6250] eta: 0:10:42 lr: 0.000106 grad: 0.0686 (0.0700) loss: 0.8281 (0.8314) time: 0.1932 data: 0.1152 max mem: 9390 +Train: [29] [1800/6250] eta: 0:10:33 lr: 0.000106 grad: 0.0664 (0.0699) loss: 0.8338 (0.8314) time: 0.1600 data: 0.0802 max mem: 9390 +Train: [29] [1900/6250] eta: 0:10:21 lr: 0.000106 grad: 0.0672 (0.0699) loss: 0.8261 (0.8314) time: 0.1348 data: 0.0583 max mem: 9390 +Train: [29] [2000/6250] eta: 0:10:10 lr: 0.000106 grad: 0.0686 (0.0699) loss: 0.8331 (0.8314) time: 0.1717 data: 0.0938 max mem: 9390 +Train: [29] [2100/6250] eta: 0:09:58 lr: 0.000106 grad: 0.0688 (0.0702) loss: 0.8308 (0.8313) time: 0.1571 data: 0.0846 max mem: 9390 +Train: [29] [2200/6250] eta: 0:09:43 lr: 0.000106 grad: 0.0671 (0.0702) loss: 0.8290 (0.8312) time: 0.1421 data: 0.0607 max mem: 9390 +Train: [29] [2300/6250] eta: 0:09:28 lr: 0.000106 grad: 0.0636 (0.0702) loss: 0.8377 (0.8312) time: 0.1429 data: 0.0677 max mem: 9390 +Train: [29] [2400/6250] eta: 0:09:13 lr: 0.000106 grad: 0.0624 (0.0701) loss: 0.8318 (0.8312) time: 0.1504 data: 0.0524 max mem: 9390 +Train: [29] [2500/6250] eta: 0:08:56 lr: 0.000106 grad: 0.0655 (0.0702) loss: 0.8311 (0.8312) time: 0.1496 data: 0.0732 max mem: 9390 +Train: [29] [2600/6250] eta: 0:08:40 lr: 0.000106 grad: 0.0688 (0.0703) loss: 0.8295 (0.8312) time: 0.1293 data: 0.0503 max mem: 9390 +Train: [29] [2700/6250] eta: 0:08:26 lr: 0.000106 grad: 0.0642 (0.0702) loss: 0.8282 (0.8312) time: 0.1426 data: 0.0541 max mem: 9390 +Train: [29] [2800/6250] eta: 0:08:13 lr: 0.000106 grad: 0.0646 (0.0701) loss: 0.8330 (0.8312) time: 0.0992 data: 0.0004 max mem: 9390 +Train: [29] [2900/6250] eta: 0:08:01 lr: 0.000106 grad: 0.0723 (0.0702) loss: 0.8352 (0.8312) time: 0.1490 data: 0.0565 max mem: 9390 +Train: [29] [3000/6250] eta: 0:07:47 lr: 0.000106 grad: 0.0748 (0.0703) loss: 0.8335 (0.8312) time: 0.1829 data: 0.1002 max mem: 9390 +Train: [29] [3100/6250] eta: 0:07:35 lr: 0.000106 grad: 0.0656 (0.0704) loss: 0.8325 (0.8312) time: 0.1061 data: 0.0063 max mem: 9390 +Train: [29] [3200/6250] eta: 0:07:20 lr: 0.000106 grad: 0.0686 (0.0704) loss: 0.8301 (0.8312) time: 0.1424 data: 0.0666 max mem: 9390 +Train: [29] [3300/6250] eta: 0:07:06 lr: 0.000106 grad: 0.0702 (0.0704) loss: 0.8303 (0.8312) time: 0.1464 data: 0.0628 max mem: 9390 +Train: [29] [3400/6250] eta: 0:06:52 lr: 0.000106 grad: 0.0691 (0.0704) loss: 0.8328 (0.8312) time: 0.1214 data: 0.0413 max mem: 9390 +Train: [29] [3500/6250] eta: 0:06:37 lr: 0.000105 grad: 0.0669 (0.0704) loss: 0.8338 (0.8312) time: 0.1313 data: 0.0533 max mem: 9390 +Train: [29] [3600/6250] eta: 0:06:22 lr: 0.000105 grad: 0.0636 (0.0704) loss: 0.8371 (0.8313) time: 0.1499 data: 0.0730 max mem: 9390 +Train: [29] [3700/6250] eta: 0:06:08 lr: 0.000105 grad: 0.0692 (0.0704) loss: 0.8333 (0.8313) time: 0.1509 data: 0.0747 max mem: 9390 +Train: [29] [3800/6250] eta: 0:05:53 lr: 0.000105 grad: 0.0653 (0.0704) loss: 0.8323 (0.8313) time: 0.1410 data: 0.0632 max mem: 9390 +Train: [29] [3900/6250] eta: 0:05:38 lr: 0.000105 grad: 0.0669 (0.0705) loss: 0.8350 (0.8313) time: 0.1574 data: 0.0800 max mem: 9390 +Train: [29] [4000/6250] eta: 0:05:24 lr: 0.000105 grad: 0.0680 (0.0705) loss: 0.8384 (0.8314) time: 0.1496 data: 0.0695 max mem: 9390 +Train: [29] [4100/6250] eta: 0:05:11 lr: 0.000105 grad: 0.0651 (0.0705) loss: 0.8389 (0.8315) time: 0.0936 data: 0.0002 max mem: 9390 +Train: [29] [4200/6250] eta: 0:04:57 lr: 0.000105 grad: 0.0708 (0.0705) loss: 0.8273 (0.8314) time: 0.1684 data: 0.0851 max mem: 9390 +Train: [29] [4300/6250] eta: 0:04:42 lr: 0.000105 grad: 0.0660 (0.0705) loss: 0.8314 (0.8314) time: 0.1429 data: 0.0654 max mem: 9390 +Train: [29] [4400/6250] eta: 0:04:27 lr: 0.000105 grad: 0.0682 (0.0705) loss: 0.8334 (0.8315) time: 0.1403 data: 0.0523 max mem: 9390 +Train: [29] [4500/6250] eta: 0:04:13 lr: 0.000105 grad: 0.0661 (0.0704) loss: 0.8322 (0.8315) time: 0.1628 data: 0.0746 max mem: 9390 +Train: [29] [4600/6250] eta: 0:03:59 lr: 0.000105 grad: 0.0679 (0.0704) loss: 0.8331 (0.8316) time: 0.1421 data: 0.0559 max mem: 9390 +Train: [29] [4700/6250] eta: 0:03:45 lr: 0.000105 grad: 0.0658 (0.0704) loss: 0.8373 (0.8316) time: 0.1305 data: 0.0455 max mem: 9390 +Train: [29] [4800/6250] eta: 0:03:30 lr: 0.000105 grad: 0.0707 (0.0704) loss: 0.8304 (0.8316) time: 0.1767 data: 0.0966 max mem: 9390 +Train: [29] [4900/6250] eta: 0:03:15 lr: 0.000105 grad: 0.0654 (0.0704) loss: 0.8315 (0.8316) time: 0.1580 data: 0.0804 max mem: 9390 +Train: [29] [5000/6250] eta: 0:03:01 lr: 0.000105 grad: 0.0701 (0.0704) loss: 0.8321 (0.8316) time: 0.1427 data: 0.0501 max mem: 9390 +Train: [29] [5100/6250] eta: 0:02:46 lr: 0.000105 grad: 0.0709 (0.0705) loss: 0.8271 (0.8315) time: 0.1312 data: 0.0509 max mem: 9390 +Train: [29] [5200/6250] eta: 0:02:32 lr: 0.000105 grad: 0.0714 (0.0705) loss: 0.8302 (0.8315) time: 0.1333 data: 0.0530 max mem: 9390 +Train: [29] [5300/6250] eta: 0:02:17 lr: 0.000105 grad: 0.0706 (0.0705) loss: 0.8304 (0.8315) time: 0.0987 data: 0.0151 max mem: 9390 +Train: [29] [5400/6250] eta: 0:02:03 lr: 0.000105 grad: 0.0696 (0.0706) loss: 0.8337 (0.8314) time: 0.1466 data: 0.0639 max mem: 9390 +Train: [29] [5500/6250] eta: 0:01:48 lr: 0.000105 grad: 0.0687 (0.0706) loss: 0.8320 (0.8314) time: 0.1059 data: 0.0265 max mem: 9390 +Train: [29] [5600/6250] eta: 0:01:34 lr: 0.000105 grad: 0.0729 (0.0707) loss: 0.8205 (0.8313) time: 0.1466 data: 0.0721 max mem: 9390 +Train: [29] [5700/6250] eta: 0:01:19 lr: 0.000105 grad: 0.0700 (0.0707) loss: 0.8360 (0.8312) time: 0.1456 data: 0.0530 max mem: 9390 +Train: [29] [5800/6250] eta: 0:01:05 lr: 0.000105 grad: 0.0712 (0.0708) loss: 0.8256 (0.8311) time: 0.1408 data: 0.0661 max mem: 9390 +Train: [29] [5900/6250] eta: 0:00:50 lr: 0.000105 grad: 0.0749 (0.0709) loss: 0.8244 (0.8311) time: 0.1327 data: 0.0555 max mem: 9390 +Train: [29] [6000/6250] eta: 0:00:36 lr: 0.000105 grad: 0.0696 (0.0709) loss: 0.8317 (0.8310) time: 0.1435 data: 0.0615 max mem: 9390 +Train: [29] [6100/6250] eta: 0:00:21 lr: 0.000105 grad: 0.0718 (0.0709) loss: 0.8342 (0.8310) time: 0.1251 data: 0.0482 max mem: 9390 +Train: [29] [6200/6250] eta: 0:00:07 lr: 0.000105 grad: 0.0712 (0.0710) loss: 0.8313 (0.8309) time: 0.1432 data: 0.0615 max mem: 9390 +Train: [29] [6249/6250] eta: 0:00:00 lr: 0.000105 grad: 0.0731 (0.0711) loss: 0.8235 (0.8308) time: 0.1597 data: 0.0719 max mem: 9390 +Train: [29] Total time: 0:15:12 (0.1460 s / it) +Averaged stats: lr: 0.000105 grad: 0.0731 (0.0711) loss: 0.8235 (0.8308) +Eval (hcp-train-subset): [29] [ 0/62] eta: 0:04:55 loss: 0.8515 (0.8515) time: 4.7615 data: 4.7243 max mem: 9390 +Eval (hcp-train-subset): [29] [61/62] eta: 0:00:00 loss: 0.8423 (0.8415) time: 0.1183 data: 0.0914 max mem: 9390 +Eval (hcp-train-subset): [29] Total time: 0:00:12 (0.2065 s / it) +Averaged stats (hcp-train-subset): loss: 0.8423 (0.8415) +Making plots (hcp-train-subset): example=43 +Eval (hcp-val): [29] [ 0/62] eta: 0:05:18 loss: 0.8362 (0.8362) time: 5.1427 data: 5.1133 max mem: 9390 +Eval (hcp-val): [29] [61/62] eta: 0:00:00 loss: 0.8384 (0.8391) time: 0.1202 data: 0.0953 max mem: 9390 +Eval (hcp-val): [29] Total time: 0:00:12 (0.2015 s / it) +Averaged stats (hcp-val): loss: 0.8384 (0.8391) +Making plots (hcp-val): example=11 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +Train: [30] [ 0/6250] eta: 9:06:42 lr: 0.000105 grad: 0.0838 (0.0838) loss: 0.8504 (0.8504) time: 5.2485 data: 5.1548 max mem: 9390 +Train: [30] [ 100/6250] eta: 0:20:40 lr: 0.000105 grad: 0.0656 (0.0732) loss: 0.8390 (0.8430) time: 0.1534 data: 0.0695 max mem: 9390 +Train: [30] [ 200/6250] eta: 0:17:57 lr: 0.000105 grad: 0.0619 (0.0708) loss: 0.8387 (0.8416) time: 0.1436 data: 0.0591 max mem: 9390 +Train: [30] [ 300/6250] eta: 0:16:55 lr: 0.000105 grad: 0.0708 (0.0707) loss: 0.8292 (0.8382) time: 0.1511 data: 0.0683 max mem: 9390 +Train: [30] [ 400/6250] eta: 0:16:06 lr: 0.000105 grad: 0.0630 (0.0703) loss: 0.8366 (0.8367) time: 0.1258 data: 0.0413 max mem: 9390 +Train: [30] [ 500/6250] eta: 0:15:24 lr: 0.000105 grad: 0.0698 (0.0699) loss: 0.8318 (0.8357) time: 0.1294 data: 0.0500 max mem: 9390 +Train: [30] [ 600/6250] eta: 0:14:58 lr: 0.000105 grad: 0.0644 (0.0695) loss: 0.8328 (0.8348) time: 0.1690 data: 0.0923 max mem: 9390 +Train: [30] [ 700/6250] eta: 0:14:32 lr: 0.000105 grad: 0.0642 (0.0694) loss: 0.8291 (0.8339) time: 0.1463 data: 0.0702 max mem: 9390 +Train: [30] [ 800/6250] eta: 0:14:03 lr: 0.000105 grad: 0.0654 (0.0692) loss: 0.8291 (0.8333) time: 0.1247 data: 0.0517 max mem: 9390 +Train: [30] [ 900/6250] eta: 0:13:39 lr: 0.000105 grad: 0.0692 (0.0693) loss: 0.8321 (0.8328) time: 0.1453 data: 0.0662 max mem: 9390 +Train: [30] [1000/6250] eta: 0:13:15 lr: 0.000105 grad: 0.0664 (0.0691) loss: 0.8369 (0.8324) time: 0.1373 data: 0.0580 max mem: 9390 +Train: [30] [1100/6250] eta: 0:12:48 lr: 0.000105 grad: 0.0683 (0.0691) loss: 0.8246 (0.8322) time: 0.1326 data: 0.0561 max mem: 9390 +Train: [30] [1200/6250] eta: 0:12:25 lr: 0.000105 grad: 0.0682 (0.0689) loss: 0.8279 (0.8319) time: 0.1313 data: 0.0480 max mem: 9390 +Train: [30] [1300/6250] eta: 0:12:02 lr: 0.000105 grad: 0.0622 (0.0689) loss: 0.8320 (0.8316) time: 0.1149 data: 0.0345 max mem: 9390 +Train: [30] [1400/6250] eta: 0:11:39 lr: 0.000104 grad: 0.0644 (0.0689) loss: 0.8273 (0.8314) time: 0.1213 data: 0.0373 max mem: 9390 +Train: [30] [1500/6250] eta: 0:11:19 lr: 0.000104 grad: 0.0694 (0.0688) loss: 0.8264 (0.8311) time: 0.1267 data: 0.0469 max mem: 9390 +Train: [30] [1600/6250] eta: 0:11:00 lr: 0.000104 grad: 0.0638 (0.0688) loss: 0.8307 (0.8309) time: 0.1217 data: 0.0397 max mem: 9390 +Train: [30] [1700/6250] eta: 0:10:41 lr: 0.000104 grad: 0.0641 (0.0689) loss: 0.8286 (0.8306) time: 0.1138 data: 0.0328 max mem: 9390 +Train: [30] [1800/6250] eta: 0:10:23 lr: 0.000104 grad: 0.0687 (0.0690) loss: 0.8289 (0.8305) time: 0.1182 data: 0.0397 max mem: 9390 +Train: [30] [1900/6250] eta: 0:10:10 lr: 0.000104 grad: 0.0668 (0.0690) loss: 0.8322 (0.8304) time: 0.1167 data: 0.0304 max mem: 9390 +Train: [30] [2000/6250] eta: 0:09:58 lr: 0.000104 grad: 0.0685 (0.0690) loss: 0.8352 (0.8304) time: 0.1618 data: 0.0824 max mem: 9390 +Train: [30] [2100/6250] eta: 0:09:45 lr: 0.000104 grad: 0.0714 (0.0692) loss: 0.8341 (0.8304) time: 0.1369 data: 0.0604 max mem: 9390 +Train: [30] [2200/6250] eta: 0:09:29 lr: 0.000104 grad: 0.0679 (0.0692) loss: 0.8283 (0.8304) time: 0.1196 data: 0.0431 max mem: 9390 +Train: [30] [2300/6250] eta: 0:09:15 lr: 0.000104 grad: 0.0694 (0.0693) loss: 0.8308 (0.8303) time: 0.1891 data: 0.1125 max mem: 9390 +Train: [30] [2400/6250] eta: 0:08:58 lr: 0.000104 grad: 0.0657 (0.0693) loss: 0.8314 (0.8304) time: 0.1429 data: 0.0634 max mem: 9390 +Train: [30] [2500/6250] eta: 0:08:43 lr: 0.000104 grad: 0.0647 (0.0693) loss: 0.8300 (0.8304) time: 0.1351 data: 0.0574 max mem: 9390 +Train: [30] [2600/6250] eta: 0:08:27 lr: 0.000104 grad: 0.0616 (0.0692) loss: 0.8307 (0.8304) time: 0.1169 data: 0.0270 max mem: 9390 +Train: [30] [2700/6250] eta: 0:08:12 lr: 0.000104 grad: 0.0689 (0.0693) loss: 0.8289 (0.8303) time: 0.1286 data: 0.0476 max mem: 9390 +Train: [30] [2800/6250] eta: 0:07:59 lr: 0.000104 grad: 0.0663 (0.0694) loss: 0.8294 (0.8302) time: 0.1418 data: 0.0626 max mem: 9390 +Train: [30] [2900/6250] eta: 0:07:45 lr: 0.000104 grad: 0.0690 (0.0694) loss: 0.8258 (0.8302) time: 0.1371 data: 0.0638 max mem: 9390 +Train: [30] [3000/6250] eta: 0:07:33 lr: 0.000104 grad: 0.0678 (0.0695) loss: 0.8300 (0.8301) time: 0.1833 data: 0.0931 max mem: 9390 +Train: [30] [3100/6250] eta: 0:07:20 lr: 0.000104 grad: 0.0698 (0.0695) loss: 0.8224 (0.8301) time: 0.1710 data: 0.0808 max mem: 9390 +Train: [30] [3200/6250] eta: 0:07:07 lr: 0.000104 grad: 0.0702 (0.0696) loss: 0.8269 (0.8300) time: 0.1376 data: 0.0519 max mem: 9390 +Train: [30] [3300/6250] eta: 0:06:53 lr: 0.000104 grad: 0.0688 (0.0696) loss: 0.8245 (0.8299) time: 0.1363 data: 0.0586 max mem: 9390 +Train: [30] [3400/6250] eta: 0:06:40 lr: 0.000104 grad: 0.0728 (0.0697) loss: 0.8302 (0.8298) time: 0.1708 data: 0.0851 max mem: 9390 +Train: [30] [3500/6250] eta: 0:06:26 lr: 0.000104 grad: 0.0674 (0.0697) loss: 0.8233 (0.8298) time: 0.1491 data: 0.0722 max mem: 9390 +Train: [30] [3600/6250] eta: 0:06:11 lr: 0.000104 grad: 0.0701 (0.0697) loss: 0.8282 (0.8297) time: 0.1445 data: 0.0658 max mem: 9390 +Train: [30] [3700/6250] eta: 0:05:57 lr: 0.000104 grad: 0.0689 (0.0698) loss: 0.8240 (0.8297) time: 0.1290 data: 0.0449 max mem: 9390 +Train: [30] [3800/6250] eta: 0:05:45 lr: 0.000104 grad: 0.0678 (0.0698) loss: 0.8275 (0.8297) time: 0.2288 data: 0.1422 max mem: 9390 +Train: [30] [3900/6250] eta: 0:05:30 lr: 0.000104 grad: 0.0653 (0.0699) loss: 0.8264 (0.8297) time: 0.1304 data: 0.0540 max mem: 9390 +Train: [30] [4000/6250] eta: 0:05:16 lr: 0.000104 grad: 0.0758 (0.0699) loss: 0.8200 (0.8296) time: 0.1369 data: 0.0586 max mem: 9390 +Train: [30] [4100/6250] eta: 0:05:02 lr: 0.000104 grad: 0.0723 (0.0699) loss: 0.8263 (0.8296) time: 0.0951 data: 0.0024 max mem: 9390 +Train: [30] [4200/6250] eta: 0:04:49 lr: 0.000104 grad: 0.0666 (0.0699) loss: 0.8310 (0.8296) time: 0.1770 data: 0.0852 max mem: 9390 +Train: [30] [4300/6250] eta: 0:04:36 lr: 0.000104 grad: 0.0647 (0.0699) loss: 0.8287 (0.8296) time: 0.1100 data: 0.0186 max mem: 9390 +Train: [30] [4400/6250] eta: 0:04:21 lr: 0.000104 grad: 0.0720 (0.0699) loss: 0.8236 (0.8295) time: 0.1435 data: 0.0616 max mem: 9390 +Train: [30] [4500/6250] eta: 0:04:07 lr: 0.000104 grad: 0.0699 (0.0699) loss: 0.8353 (0.8296) time: 0.1418 data: 0.0609 max mem: 9390 +Train: [30] [4600/6250] eta: 0:03:53 lr: 0.000104 grad: 0.0657 (0.0699) loss: 0.8318 (0.8296) time: 0.1314 data: 0.0463 max mem: 9390 +Train: [30] [4700/6250] eta: 0:03:39 lr: 0.000104 grad: 0.0700 (0.0700) loss: 0.8242 (0.8296) time: 0.1064 data: 0.0211 max mem: 9390 +Train: [30] [4800/6250] eta: 0:03:25 lr: 0.000104 grad: 0.0661 (0.0700) loss: 0.8294 (0.8296) time: 0.1491 data: 0.0741 max mem: 9390 +Train: [30] [4900/6250] eta: 0:03:12 lr: 0.000104 grad: 0.0679 (0.0700) loss: 0.8346 (0.8297) time: 0.0875 data: 0.0002 max mem: 9390 +Train: [30] [5000/6250] eta: 0:02:57 lr: 0.000104 grad: 0.0684 (0.0699) loss: 0.8330 (0.8297) time: 0.1733 data: 0.0704 max mem: 9390 +Train: [30] [5100/6250] eta: 0:02:43 lr: 0.000104 grad: 0.0693 (0.0699) loss: 0.8269 (0.8297) time: 0.1344 data: 0.0558 max mem: 9390 +Train: [30] [5200/6250] eta: 0:02:29 lr: 0.000104 grad: 0.0678 (0.0699) loss: 0.8362 (0.8298) time: 0.1394 data: 0.0630 max mem: 9390 +Train: [30] [5300/6250] eta: 0:02:15 lr: 0.000104 grad: 0.0701 (0.0699) loss: 0.8281 (0.8298) time: 0.0873 data: 0.0002 max mem: 9390 +Train: [30] [5400/6250] eta: 0:02:01 lr: 0.000103 grad: 0.0681 (0.0700) loss: 0.8327 (0.8299) time: 0.1464 data: 0.0614 max mem: 9390 +Train: [30] [5500/6250] eta: 0:01:46 lr: 0.000103 grad: 0.0702 (0.0700) loss: 0.8357 (0.8300) time: 0.1579 data: 0.0819 max mem: 9390 +Train: [30] [5600/6250] eta: 0:01:32 lr: 0.000103 grad: 0.0703 (0.0700) loss: 0.8255 (0.8300) time: 0.1394 data: 0.0645 max mem: 9390 +Train: [30] [5700/6250] eta: 0:01:18 lr: 0.000103 grad: 0.0684 (0.0701) loss: 0.8327 (0.8300) time: 0.1440 data: 0.0580 max mem: 9390 +Train: [30] [5800/6250] eta: 0:01:04 lr: 0.000103 grad: 0.0667 (0.0701) loss: 0.8325 (0.8301) time: 0.1257 data: 0.0272 max mem: 9390 +Train: [30] [5900/6250] eta: 0:00:49 lr: 0.000103 grad: 0.0738 (0.0701) loss: 0.8337 (0.8301) time: 0.1434 data: 0.0659 max mem: 9390 +Train: [30] [6000/6250] eta: 0:00:35 lr: 0.000103 grad: 0.0688 (0.0702) loss: 0.8331 (0.8302) time: 0.1669 data: 0.0869 max mem: 9390 +Train: [30] [6100/6250] eta: 0:00:21 lr: 0.000103 grad: 0.0712 (0.0703) loss: 0.8366 (0.8302) time: 0.1298 data: 0.0478 max mem: 9390 +Train: [30] [6200/6250] eta: 0:00:07 lr: 0.000103 grad: 0.0664 (0.0703) loss: 0.8303 (0.8303) time: 0.1470 data: 0.0659 max mem: 9390 +Train: [30] [6249/6250] eta: 0:00:00 lr: 0.000103 grad: 0.0683 (0.0703) loss: 0.8387 (0.8303) time: 0.1239 data: 0.0480 max mem: 9390 +Train: [30] Total time: 0:15:00 (0.1441 s / it) +Averaged stats: lr: 0.000103 grad: 0.0683 (0.0703) loss: 0.8387 (0.8303) +Eval (hcp-train-subset): [30] [ 0/62] eta: 0:03:29 loss: 0.8573 (0.8573) time: 3.3813 data: 3.3097 max mem: 9390 +Eval (hcp-train-subset): [30] [61/62] eta: 0:00:00 loss: 0.8423 (0.8427) time: 0.1049 data: 0.0785 max mem: 9390 +Eval (hcp-train-subset): [30] Total time: 0:00:12 (0.1975 s / it) +Averaged stats (hcp-train-subset): loss: 0.8423 (0.8427) +Eval (hcp-val): [30] [ 0/62] eta: 0:03:18 loss: 0.8369 (0.8369) time: 3.2090 data: 3.1538 max mem: 9390 +Eval (hcp-val): [30] [61/62] eta: 0:00:00 loss: 0.8383 (0.8391) time: 0.1439 data: 0.1189 max mem: 9390 +Eval (hcp-val): [30] Total time: 0:00:12 (0.2062 s / it) +Averaged stats (hcp-val): loss: 0.8383 (0.8391) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +Train: [31] [ 0/6250] eta: 9:51:12 lr: 0.000103 grad: 0.0933 (0.0933) loss: 0.8459 (0.8459) time: 5.6755 data: 5.5814 max mem: 9390 +Train: [31] [ 100/6250] eta: 0:20:37 lr: 0.000103 grad: 0.0716 (0.0866) loss: 0.8373 (0.8361) time: 0.1575 data: 0.0759 max mem: 9390 +Train: [31] [ 200/6250] eta: 0:18:34 lr: 0.000103 grad: 0.0676 (0.0802) loss: 0.8282 (0.8353) time: 0.1764 data: 0.0903 max mem: 9390 +Train: [31] [ 300/6250] eta: 0:17:08 lr: 0.000103 grad: 0.0660 (0.0772) loss: 0.8262 (0.8344) time: 0.1476 data: 0.0654 max mem: 9390 +Train: [31] [ 400/6250] eta: 0:16:06 lr: 0.000103 grad: 0.0715 (0.0757) loss: 0.8269 (0.8336) time: 0.1290 data: 0.0465 max mem: 9390 +Train: [31] [ 500/6250] eta: 0:15:10 lr: 0.000103 grad: 0.0692 (0.0749) loss: 0.8263 (0.8327) time: 0.1196 data: 0.0407 max mem: 9390 +Train: [31] [ 600/6250] eta: 0:14:32 lr: 0.000103 grad: 0.0690 (0.0738) loss: 0.8299 (0.8321) time: 0.1446 data: 0.0626 max mem: 9390 +Train: [31] [ 700/6250] eta: 0:14:01 lr: 0.000103 grad: 0.0679 (0.0732) loss: 0.8305 (0.8321) time: 0.1726 data: 0.0953 max mem: 9390 +Train: [31] [ 800/6250] eta: 0:13:46 lr: 0.000103 grad: 0.0689 (0.0728) loss: 0.8319 (0.8318) time: 0.1435 data: 0.0660 max mem: 9390 +Train: [31] [ 900/6250] eta: 0:13:26 lr: 0.000103 grad: 0.0722 (0.0727) loss: 0.8251 (0.8317) time: 0.1360 data: 0.0576 max mem: 9390 +Train: [31] [1000/6250] eta: 0:13:11 lr: 0.000103 grad: 0.0670 (0.0723) loss: 0.8356 (0.8318) time: 0.1406 data: 0.0559 max mem: 9390 +Train: [31] [1100/6250] eta: 0:12:49 lr: 0.000103 grad: 0.0689 (0.0722) loss: 0.8291 (0.8318) time: 0.1290 data: 0.0466 max mem: 9390 +Train: [31] [1200/6250] eta: 0:12:23 lr: 0.000103 grad: 0.0603 (0.0720) loss: 0.8362 (0.8317) time: 0.1226 data: 0.0468 max mem: 9390 +Train: [31] [1300/6250] eta: 0:12:00 lr: 0.000103 grad: 0.0715 (0.0717) loss: 0.8358 (0.8317) time: 0.1159 data: 0.0348 max mem: 9390 +Train: [31] [1400/6250] eta: 0:11:38 lr: 0.000103 grad: 0.0643 (0.0715) loss: 0.8369 (0.8319) time: 0.1201 data: 0.0385 max mem: 9390 +Train: [31] [1500/6250] eta: 0:11:17 lr: 0.000103 grad: 0.0685 (0.0715) loss: 0.8335 (0.8318) time: 0.1290 data: 0.0483 max mem: 9390 +Train: [31] [1600/6250] eta: 0:10:59 lr: 0.000103 grad: 0.0697 (0.0715) loss: 0.8325 (0.8317) time: 0.1292 data: 0.0442 max mem: 9390 +Train: [31] [1700/6250] eta: 0:10:41 lr: 0.000103 grad: 0.0724 (0.0715) loss: 0.8299 (0.8316) time: 0.1242 data: 0.0453 max mem: 9390 +Train: [31] [1800/6250] eta: 0:10:22 lr: 0.000103 grad: 0.0723 (0.0716) loss: 0.8313 (0.8316) time: 0.1166 data: 0.0364 max mem: 9390 +Train: [31] [1900/6250] eta: 0:10:09 lr: 0.000103 grad: 0.0738 (0.0716) loss: 0.8312 (0.8315) time: 0.1416 data: 0.0675 max mem: 9390 +Train: [31] [2000/6250] eta: 0:09:57 lr: 0.000103 grad: 0.0735 (0.0717) loss: 0.8316 (0.8314) time: 0.1575 data: 0.0810 max mem: 9390 +Train: [31] [2100/6250] eta: 0:09:48 lr: 0.000103 grad: 0.0703 (0.0716) loss: 0.8342 (0.8314) time: 0.1807 data: 0.1053 max mem: 9390 +Train: [31] [2200/6250] eta: 0:09:33 lr: 0.000103 grad: 0.0680 (0.0717) loss: 0.8345 (0.8313) time: 0.1563 data: 0.0757 max mem: 9390 +Train: [31] [2300/6250] eta: 0:09:19 lr: 0.000103 grad: 0.0706 (0.0719) loss: 0.8355 (0.8313) time: 0.1337 data: 0.0588 max mem: 9390 +Train: [31] [2400/6250] eta: 0:09:04 lr: 0.000103 grad: 0.0721 (0.0719) loss: 0.8336 (0.8313) time: 0.1250 data: 0.0434 max mem: 9390 +Train: [31] [2500/6250] eta: 0:08:49 lr: 0.000103 grad: 0.0688 (0.0719) loss: 0.8326 (0.8313) time: 0.1137 data: 0.0321 max mem: 9390 +Train: [31] [2600/6250] eta: 0:08:33 lr: 0.000103 grad: 0.0713 (0.0718) loss: 0.8279 (0.8313) time: 0.1299 data: 0.0503 max mem: 9390 +Train: [31] [2700/6250] eta: 0:08:19 lr: 0.000103 grad: 0.0750 (0.0719) loss: 0.8299 (0.8312) time: 0.1458 data: 0.0662 max mem: 9390 +Train: [31] [2800/6250] eta: 0:08:05 lr: 0.000103 grad: 0.0711 (0.0718) loss: 0.8283 (0.8312) time: 0.1788 data: 0.0969 max mem: 9390 +Train: [31] [2900/6250] eta: 0:07:51 lr: 0.000103 grad: 0.0694 (0.0718) loss: 0.8309 (0.8311) time: 0.1177 data: 0.0331 max mem: 9390 +Train: [31] [3000/6250] eta: 0:07:38 lr: 0.000103 grad: 0.0663 (0.0719) loss: 0.8363 (0.8311) time: 0.1638 data: 0.0905 max mem: 9390 +Train: [31] [3100/6250] eta: 0:07:24 lr: 0.000103 grad: 0.0708 (0.0718) loss: 0.8272 (0.8311) time: 0.1790 data: 0.1014 max mem: 9390 +Train: [31] [3200/6250] eta: 0:07:11 lr: 0.000102 grad: 0.0738 (0.0718) loss: 0.8289 (0.8310) time: 0.1447 data: 0.0593 max mem: 9390 +Train: [31] [3300/6250] eta: 0:06:58 lr: 0.000102 grad: 0.0727 (0.0718) loss: 0.8309 (0.8310) time: 0.1517 data: 0.0746 max mem: 9390 +Train: [31] [3400/6250] eta: 0:06:44 lr: 0.000102 grad: 0.0686 (0.0718) loss: 0.8281 (0.8310) time: 0.1446 data: 0.0696 max mem: 9390 +Train: [31] [3500/6250] eta: 0:06:29 lr: 0.000102 grad: 0.0713 (0.0718) loss: 0.8262 (0.8310) time: 0.1558 data: 0.0738 max mem: 9390 +Train: [31] [3600/6250] eta: 0:06:15 lr: 0.000102 grad: 0.0723 (0.0719) loss: 0.8263 (0.8309) time: 0.1336 data: 0.0575 max mem: 9390 +Train: [31] [3700/6250] eta: 0:06:01 lr: 0.000102 grad: 0.0686 (0.0718) loss: 0.8311 (0.8308) time: 0.1484 data: 0.0723 max mem: 9390 +Train: [31] [3800/6250] eta: 0:05:47 lr: 0.000102 grad: 0.0715 (0.0718) loss: 0.8256 (0.8308) time: 0.1362 data: 0.0445 max mem: 9390 +Train: [31] [3900/6250] eta: 0:05:33 lr: 0.000102 grad: 0.0766 (0.0719) loss: 0.8232 (0.8308) time: 0.1452 data: 0.0567 max mem: 9390 +Train: [31] [4000/6250] eta: 0:05:19 lr: 0.000102 grad: 0.0717 (0.0719) loss: 0.8282 (0.8307) time: 0.1290 data: 0.0479 max mem: 9390 +Train: [31] [4100/6250] eta: 0:05:04 lr: 0.000102 grad: 0.0694 (0.0720) loss: 0.8250 (0.8306) time: 0.1219 data: 0.0411 max mem: 9390 +Train: [31] [4200/6250] eta: 0:04:50 lr: 0.000102 grad: 0.0728 (0.0720) loss: 0.8269 (0.8304) time: 0.1403 data: 0.0486 max mem: 9390 +Train: [31] [4300/6250] eta: 0:04:36 lr: 0.000102 grad: 0.0711 (0.0721) loss: 0.8202 (0.8303) time: 0.1287 data: 0.0453 max mem: 9390 +Train: [31] [4400/6250] eta: 0:04:22 lr: 0.000102 grad: 0.0699 (0.0723) loss: 0.8267 (0.8302) time: 0.1395 data: 0.0620 max mem: 9390 +Train: [31] [4500/6250] eta: 0:04:07 lr: 0.000102 grad: 0.0736 (0.0723) loss: 0.8263 (0.8301) time: 0.1355 data: 0.0559 max mem: 9390 +Train: [31] [4600/6250] eta: 0:03:53 lr: 0.000102 grad: 0.0668 (0.0723) loss: 0.8307 (0.8300) time: 0.1480 data: 0.0663 max mem: 9390 +Train: [31] [4700/6250] eta: 0:03:40 lr: 0.000102 grad: 0.0714 (0.0724) loss: 0.8286 (0.8300) time: 0.1798 data: 0.0895 max mem: 9390 +Train: [31] [4800/6250] eta: 0:03:25 lr: 0.000102 grad: 0.0713 (0.0724) loss: 0.8285 (0.8299) time: 0.1343 data: 0.0488 max mem: 9390 +Train: [31] [4900/6250] eta: 0:03:11 lr: 0.000102 grad: 0.0735 (0.0725) loss: 0.8263 (0.8299) time: 0.1462 data: 0.0682 max mem: 9390 +Train: [31] [5000/6250] eta: 0:02:57 lr: 0.000102 grad: 0.0712 (0.0725) loss: 0.8239 (0.8298) time: 0.1508 data: 0.0765 max mem: 9390 +Train: [31] [5100/6250] eta: 0:02:43 lr: 0.000102 grad: 0.0722 (0.0725) loss: 0.8296 (0.8298) time: 0.1392 data: 0.0569 max mem: 9390 +Train: [31] [5200/6250] eta: 0:02:28 lr: 0.000102 grad: 0.0711 (0.0725) loss: 0.8300 (0.8298) time: 0.1292 data: 0.0515 max mem: 9390 +Train: [31] [5300/6250] eta: 0:02:14 lr: 0.000102 grad: 0.0716 (0.0725) loss: 0.8324 (0.8297) time: 0.1350 data: 0.0553 max mem: 9390 +Train: [31] [5400/6250] eta: 0:02:00 lr: 0.000102 grad: 0.0700 (0.0725) loss: 0.8330 (0.8297) time: 0.0825 data: 0.0002 max mem: 9390 +Train: [31] [5500/6250] eta: 0:01:46 lr: 0.000102 grad: 0.0720 (0.0725) loss: 0.8272 (0.8297) time: 0.1513 data: 0.0683 max mem: 9390 +Train: [31] [5600/6250] eta: 0:01:32 lr: 0.000102 grad: 0.0756 (0.0726) loss: 0.8252 (0.8297) time: 0.1454 data: 0.0689 max mem: 9390 +Train: [31] [5700/6250] eta: 0:01:18 lr: 0.000102 grad: 0.0679 (0.0726) loss: 0.8307 (0.8297) time: 0.1530 data: 0.0765 max mem: 9390 +Train: [31] [5800/6250] eta: 0:01:03 lr: 0.000102 grad: 0.0694 (0.0726) loss: 0.8323 (0.8297) time: 0.1427 data: 0.0654 max mem: 9390 +Train: [31] [5900/6250] eta: 0:00:49 lr: 0.000102 grad: 0.0675 (0.0726) loss: 0.8321 (0.8297) time: 0.1243 data: 0.0442 max mem: 9390 +Train: [31] [6000/6250] eta: 0:00:35 lr: 0.000102 grad: 0.0720 (0.0726) loss: 0.8307 (0.8297) time: 0.1284 data: 0.0510 max mem: 9390 +Train: [31] [6100/6250] eta: 0:00:21 lr: 0.000102 grad: 0.0744 (0.0726) loss: 0.8298 (0.8297) time: 0.1239 data: 0.0453 max mem: 9390 +Train: [31] [6200/6250] eta: 0:00:07 lr: 0.000102 grad: 0.0729 (0.0726) loss: 0.8314 (0.8297) time: 0.1186 data: 0.0411 max mem: 9390 +Train: [31] [6249/6250] eta: 0:00:00 lr: 0.000102 grad: 0.0729 (0.0726) loss: 0.8324 (0.8297) time: 0.1538 data: 0.0683 max mem: 9390 +Train: [31] Total time: 0:14:53 (0.1429 s / it) +Averaged stats: lr: 0.000102 grad: 0.0729 (0.0726) loss: 0.8324 (0.8297) +Eval (hcp-train-subset): [31] [ 0/62] eta: 0:04:20 loss: 0.8528 (0.8528) time: 4.2002 data: 4.1701 max mem: 9390 +Eval (hcp-train-subset): [31] [61/62] eta: 0:00:00 loss: 0.8408 (0.8426) time: 0.1285 data: 0.1019 max mem: 9390 +Eval (hcp-train-subset): [31] Total time: 0:00:12 (0.2036 s / it) +Averaged stats (hcp-train-subset): loss: 0.8408 (0.8426) +Eval (hcp-val): [31] [ 0/62] eta: 0:04:41 loss: 0.8336 (0.8336) time: 4.5407 data: 4.5115 max mem: 9390 +Eval (hcp-val): [31] [61/62] eta: 0:00:00 loss: 0.8377 (0.8385) time: 0.1207 data: 0.0943 max mem: 9390 +Eval (hcp-val): [31] Total time: 0:00:12 (0.2027 s / it) +Averaged stats (hcp-val): loss: 0.8377 (0.8385) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +Train: [32] [ 0/6250] eta: 10:08:08 lr: 0.000102 grad: 0.1389 (0.1389) loss: 0.8306 (0.8306) time: 5.8381 data: 5.7510 max mem: 9390 +Train: [32] [ 100/6250] eta: 0:20:41 lr: 0.000102 grad: 0.0703 (0.0771) loss: 0.8347 (0.8403) time: 0.1408 data: 0.0425 max mem: 9390 +Train: [32] [ 200/6250] eta: 0:17:43 lr: 0.000102 grad: 0.0648 (0.0746) loss: 0.8418 (0.8383) time: 0.1542 data: 0.0710 max mem: 9390 +Train: [32] [ 300/6250] eta: 0:16:45 lr: 0.000102 grad: 0.0677 (0.0729) loss: 0.8356 (0.8376) time: 0.1609 data: 0.0683 max mem: 9390 +Train: [32] [ 400/6250] eta: 0:16:02 lr: 0.000102 grad: 0.0673 (0.0716) loss: 0.8286 (0.8368) time: 0.1359 data: 0.0555 max mem: 9390 +Train: [32] [ 500/6250] eta: 0:15:11 lr: 0.000102 grad: 0.0643 (0.0713) loss: 0.8354 (0.8363) time: 0.1379 data: 0.0575 max mem: 9390 +Train: [32] [ 600/6250] eta: 0:14:37 lr: 0.000102 grad: 0.0709 (0.0713) loss: 0.8300 (0.8356) time: 0.1622 data: 0.0758 max mem: 9390 +Train: [32] [ 700/6250] eta: 0:14:06 lr: 0.000102 grad: 0.0663 (0.0709) loss: 0.8301 (0.8348) time: 0.1432 data: 0.0585 max mem: 9390 +Train: [32] [ 800/6250] eta: 0:13:56 lr: 0.000101 grad: 0.0738 (0.0713) loss: 0.8264 (0.8338) time: 0.1568 data: 0.0745 max mem: 9390 +Train: [32] [ 900/6250] eta: 0:13:41 lr: 0.000101 grad: 0.0732 (0.0716) loss: 0.8269 (0.8329) time: 0.1479 data: 0.0681 max mem: 9390 +Train: [32] [1000/6250] eta: 0:13:23 lr: 0.000101 grad: 0.0694 (0.0718) loss: 0.8302 (0.8323) time: 0.1524 data: 0.0709 max mem: 9390 +Train: [32] [1100/6250] eta: 0:13:00 lr: 0.000101 grad: 0.0714 (0.0723) loss: 0.8305 (0.8319) time: 0.1333 data: 0.0549 max mem: 9390 +Train: [32] [1200/6250] eta: 0:12:37 lr: 0.000101 grad: 0.0690 (0.0726) loss: 0.8267 (0.8314) time: 0.1308 data: 0.0475 max mem: 9390 +Train: [32] [1300/6250] eta: 0:12:12 lr: 0.000101 grad: 0.0745 (0.0727) loss: 0.8224 (0.8309) time: 0.1269 data: 0.0395 max mem: 9390 +Train: [32] [1400/6250] eta: 0:11:51 lr: 0.000101 grad: 0.0663 (0.0726) loss: 0.8303 (0.8306) time: 0.1257 data: 0.0399 max mem: 9390 +Train: [32] [1500/6250] eta: 0:11:29 lr: 0.000101 grad: 0.0677 (0.0726) loss: 0.8284 (0.8302) time: 0.1228 data: 0.0417 max mem: 9390 +Train: [32] [1600/6250] eta: 0:11:09 lr: 0.000101 grad: 0.0712 (0.0727) loss: 0.8201 (0.8299) time: 0.1199 data: 0.0444 max mem: 9390 +Train: [32] [1700/6250] eta: 0:10:51 lr: 0.000101 grad: 0.0712 (0.0727) loss: 0.8268 (0.8296) time: 0.1476 data: 0.0712 max mem: 9390 +Train: [32] [1800/6250] eta: 0:10:34 lr: 0.000101 grad: 0.0729 (0.0727) loss: 0.8224 (0.8295) time: 0.1403 data: 0.0600 max mem: 9390 +Train: [32] [1900/6250] eta: 0:10:23 lr: 0.000101 grad: 0.0729 (0.0728) loss: 0.8291 (0.8293) time: 0.1822 data: 0.1062 max mem: 9390 +Train: [32] [2000/6250] eta: 0:10:12 lr: 0.000101 grad: 0.0698 (0.0729) loss: 0.8283 (0.8291) time: 0.1443 data: 0.0683 max mem: 9390 +Train: [32] [2100/6250] eta: 0:09:59 lr: 0.000101 grad: 0.0741 (0.0730) loss: 0.8234 (0.8290) time: 0.1356 data: 0.0539 max mem: 9390 +Train: [32] [2200/6250] eta: 0:09:45 lr: 0.000101 grad: 0.0677 (0.0730) loss: 0.8266 (0.8289) time: 0.1420 data: 0.0674 max mem: 9390 +Train: [32] [2300/6250] eta: 0:09:31 lr: 0.000101 grad: 0.0763 (0.0730) loss: 0.8283 (0.8288) time: 0.1395 data: 0.0640 max mem: 9390 +Train: [32] [2400/6250] eta: 0:09:17 lr: 0.000101 grad: 0.0710 (0.0730) loss: 0.8247 (0.8288) time: 0.1337 data: 0.0548 max mem: 9390 +Train: [32] [2500/6250] eta: 0:09:00 lr: 0.000101 grad: 0.0731 (0.0730) loss: 0.8285 (0.8286) time: 0.1187 data: 0.0397 max mem: 9390 +Train: [32] [2600/6250] eta: 0:08:45 lr: 0.000101 grad: 0.0750 (0.0731) loss: 0.8292 (0.8285) time: 0.1112 data: 0.0324 max mem: 9390 +Train: [32] [2700/6250] eta: 0:08:29 lr: 0.000101 grad: 0.0705 (0.0731) loss: 0.8296 (0.8286) time: 0.1427 data: 0.0626 max mem: 9390 +Train: [32] [2800/6250] eta: 0:08:15 lr: 0.000101 grad: 0.0770 (0.0732) loss: 0.8254 (0.8285) time: 0.1237 data: 0.0435 max mem: 9390 +Train: [32] [2900/6250] eta: 0:08:00 lr: 0.000101 grad: 0.0739 (0.0732) loss: 0.8289 (0.8285) time: 0.1392 data: 0.0628 max mem: 9390 +Train: [32] [3000/6250] eta: 0:07:47 lr: 0.000101 grad: 0.0737 (0.0733) loss: 0.8340 (0.8286) time: 0.1615 data: 0.0804 max mem: 9390 +Train: [32] [3100/6250] eta: 0:07:33 lr: 0.000101 grad: 0.0699 (0.0733) loss: 0.8268 (0.8286) time: 0.1431 data: 0.0632 max mem: 9390 +Train: [32] [3200/6250] eta: 0:07:20 lr: 0.000101 grad: 0.0736 (0.0733) loss: 0.8291 (0.8286) time: 0.1609 data: 0.0598 max mem: 9390 +Train: [32] [3300/6250] eta: 0:07:06 lr: 0.000101 grad: 0.0751 (0.0734) loss: 0.8283 (0.8286) time: 0.1523 data: 0.0783 max mem: 9390 +Train: [32] [3400/6250] eta: 0:06:51 lr: 0.000101 grad: 0.0708 (0.0734) loss: 0.8301 (0.8285) time: 0.1390 data: 0.0614 max mem: 9390 +Train: [32] [3500/6250] eta: 0:06:36 lr: 0.000101 grad: 0.0751 (0.0735) loss: 0.8179 (0.8284) time: 0.1369 data: 0.0604 max mem: 9390 +Train: [32] [3600/6250] eta: 0:06:22 lr: 0.000101 grad: 0.0716 (0.0735) loss: 0.8218 (0.8283) time: 0.1474 data: 0.0710 max mem: 9390 +Train: [32] [3700/6250] eta: 0:06:08 lr: 0.000101 grad: 0.0746 (0.0736) loss: 0.8229 (0.8282) time: 0.1602 data: 0.0811 max mem: 9390 +Train: [32] [3800/6250] eta: 0:05:53 lr: 0.000101 grad: 0.0732 (0.0737) loss: 0.8267 (0.8282) time: 0.1716 data: 0.0884 max mem: 9390 +Train: [32] [3900/6250] eta: 0:05:39 lr: 0.000101 grad: 0.0731 (0.0737) loss: 0.8205 (0.8281) time: 0.1522 data: 0.0716 max mem: 9390 +Train: [32] [4000/6250] eta: 0:05:24 lr: 0.000101 grad: 0.0744 (0.0738) loss: 0.8261 (0.8280) time: 0.1511 data: 0.0666 max mem: 9390 +Train: [32] [4100/6250] eta: 0:05:10 lr: 0.000101 grad: 0.0710 (0.0738) loss: 0.8212 (0.8279) time: 0.1472 data: 0.0639 max mem: 9390 +Train: [32] [4200/6250] eta: 0:04:56 lr: 0.000101 grad: 0.0729 (0.0738) loss: 0.8193 (0.8279) time: 0.1338 data: 0.0590 max mem: 9390 +Train: [32] [4300/6250] eta: 0:04:41 lr: 0.000101 grad: 0.0813 (0.0738) loss: 0.8217 (0.8279) time: 0.1525 data: 0.0628 max mem: 9390 +Train: [32] [4400/6250] eta: 0:04:27 lr: 0.000101 grad: 0.0709 (0.0738) loss: 0.8270 (0.8279) time: 0.1486 data: 0.0734 max mem: 9390 +Train: [32] [4500/6250] eta: 0:04:13 lr: 0.000101 grad: 0.0726 (0.0738) loss: 0.8245 (0.8279) time: 0.1318 data: 0.0493 max mem: 9390 +Train: [32] [4600/6250] eta: 0:03:58 lr: 0.000101 grad: 0.0726 (0.0738) loss: 0.8329 (0.8279) time: 0.1708 data: 0.0939 max mem: 9390 +Train: [32] [4700/6250] eta: 0:03:44 lr: 0.000100 grad: 0.0693 (0.0738) loss: 0.8253 (0.8279) time: 0.1080 data: 0.0213 max mem: 9390 +Train: [32] [4800/6250] eta: 0:03:30 lr: 0.000100 grad: 0.0765 (0.0738) loss: 0.8297 (0.8279) time: 0.1631 data: 0.0790 max mem: 9390 +Train: [32] [4900/6250] eta: 0:03:16 lr: 0.000100 grad: 0.0678 (0.0738) loss: 0.8263 (0.8279) time: 0.1623 data: 0.0805 max mem: 9390 +Train: [32] [5000/6250] eta: 0:03:01 lr: 0.000100 grad: 0.0726 (0.0738) loss: 0.8256 (0.8279) time: 0.1484 data: 0.0648 max mem: 9390 +Train: [32] [5100/6250] eta: 0:02:47 lr: 0.000100 grad: 0.0747 (0.0739) loss: 0.8261 (0.8279) time: 0.1440 data: 0.0694 max mem: 9390 +Train: [32] [5200/6250] eta: 0:02:32 lr: 0.000100 grad: 0.0694 (0.0740) loss: 0.8299 (0.8279) time: 0.1333 data: 0.0524 max mem: 9390 +Train: [32] [5300/6250] eta: 0:02:18 lr: 0.000100 grad: 0.0698 (0.0740) loss: 0.8306 (0.8280) time: 0.1534 data: 0.0684 max mem: 9390 +Train: [32] [5400/6250] eta: 0:02:03 lr: 0.000100 grad: 0.0687 (0.0739) loss: 0.8291 (0.8280) time: 0.1651 data: 0.0783 max mem: 9390 +Train: [32] [5500/6250] eta: 0:01:49 lr: 0.000100 grad: 0.0704 (0.0739) loss: 0.8298 (0.8280) time: 0.1264 data: 0.0472 max mem: 9390 +Train: [32] [5600/6250] eta: 0:01:34 lr: 0.000100 grad: 0.0732 (0.0739) loss: 0.8336 (0.8281) time: 0.1508 data: 0.0724 max mem: 9390 +Train: [32] [5700/6250] eta: 0:01:19 lr: 0.000100 grad: 0.0707 (0.0739) loss: 0.8349 (0.8281) time: 0.1646 data: 0.0897 max mem: 9390 +Train: [32] [5800/6250] eta: 0:01:05 lr: 0.000100 grad: 0.0718 (0.0739) loss: 0.8324 (0.8282) time: 0.1648 data: 0.0644 max mem: 9390 +Train: [32] [5900/6250] eta: 0:00:51 lr: 0.000100 grad: 0.0765 (0.0739) loss: 0.8271 (0.8282) time: 0.1457 data: 0.0604 max mem: 9390 +Train: [32] [6000/6250] eta: 0:00:36 lr: 0.000100 grad: 0.0715 (0.0739) loss: 0.8294 (0.8283) time: 0.1310 data: 0.0522 max mem: 9390 +Train: [32] [6100/6250] eta: 0:00:21 lr: 0.000100 grad: 0.0734 (0.0739) loss: 0.8295 (0.8283) time: 0.1605 data: 0.0833 max mem: 9390 +Train: [32] [6200/6250] eta: 0:00:07 lr: 0.000100 grad: 0.0724 (0.0739) loss: 0.8302 (0.8283) time: 0.1392 data: 0.0602 max mem: 9390 +Train: [32] [6249/6250] eta: 0:00:00 lr: 0.000100 grad: 0.0705 (0.0739) loss: 0.8277 (0.8283) time: 0.1630 data: 0.0780 max mem: 9390 +Train: [32] Total time: 0:15:19 (0.1471 s / it) +Averaged stats: lr: 0.000100 grad: 0.0705 (0.0739) loss: 0.8277 (0.8283) +Eval (hcp-train-subset): [32] [ 0/62] eta: 0:05:27 loss: 0.8534 (0.8534) time: 5.2769 data: 5.2475 max mem: 9390 +Eval (hcp-train-subset): [32] [61/62] eta: 0:00:00 loss: 0.8410 (0.8422) time: 0.1238 data: 0.0989 max mem: 9390 +Eval (hcp-train-subset): [32] Total time: 0:00:13 (0.2103 s / it) +Averaged stats (hcp-train-subset): loss: 0.8410 (0.8422) +Eval (hcp-val): [32] [ 0/62] eta: 0:03:33 loss: 0.8364 (0.8364) time: 3.4491 data: 3.3781 max mem: 9390 +Eval (hcp-val): [32] [61/62] eta: 0:00:00 loss: 0.8362 (0.8375) time: 0.1203 data: 0.0940 max mem: 9390 +Eval (hcp-val): [32] Total time: 0:00:12 (0.2017 s / it) +Averaged stats (hcp-val): loss: 0.8362 (0.8375) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +Train: [33] [ 0/6250] eta: 7:36:41 lr: 0.000100 grad: 0.0881 (0.0881) loss: 0.8414 (0.8414) time: 4.3842 data: 4.1182 max mem: 9390 +Train: [33] [ 100/6250] eta: 0:21:07 lr: 0.000100 grad: 0.0708 (0.0865) loss: 0.8264 (0.8281) time: 0.1529 data: 0.0653 max mem: 9390 +Train: [33] [ 200/6250] eta: 0:18:09 lr: 0.000100 grad: 0.0670 (0.0815) loss: 0.8323 (0.8275) time: 0.1620 data: 0.0805 max mem: 9390 +Train: [33] [ 300/6250] eta: 0:16:35 lr: 0.000100 grad: 0.0707 (0.0783) loss: 0.8288 (0.8285) time: 0.1329 data: 0.0492 max mem: 9390 +Train: [33] [ 400/6250] eta: 0:15:43 lr: 0.000100 grad: 0.0719 (0.0773) loss: 0.8285 (0.8284) time: 0.1486 data: 0.0649 max mem: 9390 +Train: [33] [ 500/6250] eta: 0:14:56 lr: 0.000100 grad: 0.0693 (0.0765) loss: 0.8288 (0.8282) time: 0.1103 data: 0.0306 max mem: 9390 +Train: [33] [ 600/6250] eta: 0:14:17 lr: 0.000100 grad: 0.0729 (0.0763) loss: 0.8233 (0.8280) time: 0.1294 data: 0.0486 max mem: 9390 +Train: [33] [ 700/6250] eta: 0:13:47 lr: 0.000100 grad: 0.0725 (0.0762) loss: 0.8275 (0.8279) time: 0.1301 data: 0.0405 max mem: 9390 +Train: [33] [ 800/6250] eta: 0:13:15 lr: 0.000100 grad: 0.0707 (0.0757) loss: 0.8237 (0.8275) time: 0.1248 data: 0.0455 max mem: 9390 +Train: [33] [ 900/6250] eta: 0:13:14 lr: 0.000100 grad: 0.0669 (0.0753) loss: 0.8336 (0.8276) time: 0.1429 data: 0.0620 max mem: 9390 +Train: [33] [1000/6250] eta: 0:12:56 lr: 0.000100 grad: 0.0683 (0.0750) loss: 0.8321 (0.8277) time: 0.1454 data: 0.0707 max mem: 9390 +Train: [33] [1100/6250] eta: 0:12:41 lr: 0.000100 grad: 0.0665 (0.0751) loss: 0.8325 (0.8280) time: 0.1429 data: 0.0629 max mem: 9390 +Train: [33] [1200/6250] eta: 0:12:23 lr: 0.000100 grad: 0.0717 (0.0747) loss: 0.8268 (0.8281) time: 0.1446 data: 0.0647 max mem: 9390 +Train: [33] [1300/6250] eta: 0:12:04 lr: 0.000100 grad: 0.0715 (0.0745) loss: 0.8286 (0.8282) time: 0.1255 data: 0.0437 max mem: 9390 +Train: [33] [1400/6250] eta: 0:11:44 lr: 0.000100 grad: 0.0774 (0.0746) loss: 0.8252 (0.8282) time: 0.1551 data: 0.0753 max mem: 9390 +Train: [33] [1500/6250] eta: 0:11:22 lr: 0.000100 grad: 0.0721 (0.0746) loss: 0.8258 (0.8282) time: 0.1206 data: 0.0346 max mem: 9390 +Train: [33] [1600/6250] eta: 0:11:03 lr: 0.000100 grad: 0.0752 (0.0748) loss: 0.8287 (0.8282) time: 0.1419 data: 0.0603 max mem: 9390 +Train: [33] [1700/6250] eta: 0:10:43 lr: 0.000100 grad: 0.0727 (0.0748) loss: 0.8304 (0.8283) time: 0.1334 data: 0.0531 max mem: 9390 +Train: [33] [1800/6250] eta: 0:10:25 lr: 0.000100 grad: 0.0694 (0.0746) loss: 0.8273 (0.8282) time: 0.1286 data: 0.0480 max mem: 9390 +Train: [33] [1900/6250] eta: 0:10:07 lr: 0.000100 grad: 0.0716 (0.0745) loss: 0.8247 (0.8282) time: 0.1333 data: 0.0572 max mem: 9390 +Train: [33] [2000/6250] eta: 0:09:50 lr: 0.000100 grad: 0.0726 (0.0745) loss: 0.8226 (0.8281) time: 0.1392 data: 0.0523 max mem: 9390 +Train: [33] [2100/6250] eta: 0:09:36 lr: 0.000100 grad: 0.0718 (0.0744) loss: 0.8309 (0.8282) time: 0.1245 data: 0.0371 max mem: 9390 +Train: [33] [2200/6250] eta: 0:09:22 lr: 0.000099 grad: 0.0702 (0.0743) loss: 0.8318 (0.8282) time: 0.1479 data: 0.0727 max mem: 9390 +Train: [33] [2300/6250] eta: 0:09:10 lr: 0.000099 grad: 0.0727 (0.0743) loss: 0.8222 (0.8282) time: 0.1432 data: 0.0620 max mem: 9390 +Train: [33] [2400/6250] eta: 0:08:54 lr: 0.000099 grad: 0.0688 (0.0743) loss: 0.8288 (0.8282) time: 0.1251 data: 0.0465 max mem: 9390 +Train: [33] [2500/6250] eta: 0:08:40 lr: 0.000099 grad: 0.0709 (0.0743) loss: 0.8271 (0.8282) time: 0.1351 data: 0.0578 max mem: 9390 +Train: [33] [2600/6250] eta: 0:08:24 lr: 0.000099 grad: 0.0690 (0.0743) loss: 0.8296 (0.8282) time: 0.1374 data: 0.0603 max mem: 9390 +Train: [33] [2700/6250] eta: 0:08:09 lr: 0.000099 grad: 0.0721 (0.0743) loss: 0.8251 (0.8282) time: 0.1372 data: 0.0585 max mem: 9390 +Train: [33] [2800/6250] eta: 0:07:54 lr: 0.000099 grad: 0.0761 (0.0743) loss: 0.8311 (0.8281) time: 0.1201 data: 0.0435 max mem: 9390 +Train: [33] [2900/6250] eta: 0:07:41 lr: 0.000099 grad: 0.0774 (0.0743) loss: 0.8276 (0.8281) time: 0.1552 data: 0.0802 max mem: 9390 +Train: [33] [3000/6250] eta: 0:07:29 lr: 0.000099 grad: 0.0709 (0.0743) loss: 0.8291 (0.8281) time: 0.1479 data: 0.0710 max mem: 9390 +Train: [33] [3100/6250] eta: 0:07:17 lr: 0.000099 grad: 0.0726 (0.0743) loss: 0.8265 (0.8280) time: 0.1701 data: 0.0806 max mem: 9390 +Train: [33] [3200/6250] eta: 0:07:04 lr: 0.000099 grad: 0.0752 (0.0742) loss: 0.8207 (0.8279) time: 0.1571 data: 0.0755 max mem: 9390 +Train: [33] [3300/6250] eta: 0:06:51 lr: 0.000099 grad: 0.0722 (0.0742) loss: 0.8240 (0.8278) time: 0.1485 data: 0.0635 max mem: 9390 +Train: [33] [3400/6250] eta: 0:06:37 lr: 0.000099 grad: 0.0705 (0.0742) loss: 0.8270 (0.8278) time: 0.1466 data: 0.0650 max mem: 9390 +Train: [33] [3500/6250] eta: 0:06:24 lr: 0.000099 grad: 0.0715 (0.0743) loss: 0.8250 (0.8277) time: 0.1469 data: 0.0712 max mem: 9390 +Train: [33] [3600/6250] eta: 0:06:10 lr: 0.000099 grad: 0.0735 (0.0743) loss: 0.8225 (0.8277) time: 0.1305 data: 0.0478 max mem: 9390 +Train: [33] [3700/6250] eta: 0:05:56 lr: 0.000099 grad: 0.0727 (0.0743) loss: 0.8249 (0.8276) time: 0.1419 data: 0.0651 max mem: 9390 +Train: [33] [3800/6250] eta: 0:05:43 lr: 0.000099 grad: 0.0691 (0.0744) loss: 0.8304 (0.8277) time: 0.1596 data: 0.0728 max mem: 9390 +Train: [33] [3900/6250] eta: 0:05:29 lr: 0.000099 grad: 0.0730 (0.0745) loss: 0.8272 (0.8277) time: 0.1123 data: 0.0344 max mem: 9390 +Train: [33] [4000/6250] eta: 0:05:15 lr: 0.000099 grad: 0.0755 (0.0746) loss: 0.8216 (0.8276) time: 0.1331 data: 0.0561 max mem: 9390 +Train: [33] [4100/6250] eta: 0:05:01 lr: 0.000099 grad: 0.0796 (0.0746) loss: 0.8253 (0.8276) time: 0.1477 data: 0.0694 max mem: 9390 +Train: [33] [4200/6250] eta: 0:04:48 lr: 0.000099 grad: 0.0745 (0.0746) loss: 0.8267 (0.8275) time: 0.0955 data: 0.0107 max mem: 9390 +Train: [33] [4300/6250] eta: 0:04:34 lr: 0.000099 grad: 0.0789 (0.0747) loss: 0.8254 (0.8275) time: 0.1605 data: 0.0711 max mem: 9390 +Train: [33] [4400/6250] eta: 0:04:20 lr: 0.000099 grad: 0.0714 (0.0748) loss: 0.8279 (0.8275) time: 0.1482 data: 0.0710 max mem: 9390 +Train: [33] [4500/6250] eta: 0:04:06 lr: 0.000099 grad: 0.0742 (0.0748) loss: 0.8270 (0.8274) time: 0.1137 data: 0.0325 max mem: 9390 +Train: [33] [4600/6250] eta: 0:03:52 lr: 0.000099 grad: 0.0739 (0.0748) loss: 0.8266 (0.8274) time: 0.1357 data: 0.0542 max mem: 9390 +Train: [33] [4700/6250] eta: 0:03:39 lr: 0.000099 grad: 0.0715 (0.0748) loss: 0.8179 (0.8274) time: 0.1541 data: 0.0753 max mem: 9390 +Train: [33] [4800/6250] eta: 0:03:24 lr: 0.000099 grad: 0.0734 (0.0748) loss: 0.8271 (0.8274) time: 0.1488 data: 0.0694 max mem: 9390 +Train: [33] [4900/6250] eta: 0:03:10 lr: 0.000099 grad: 0.0724 (0.0748) loss: 0.8311 (0.8274) time: 0.1400 data: 0.0514 max mem: 9390 +Train: [33] [5000/6250] eta: 0:02:57 lr: 0.000099 grad: 0.0714 (0.0748) loss: 0.8330 (0.8275) time: 0.1573 data: 0.0677 max mem: 9390 +Train: [33] [5100/6250] eta: 0:02:43 lr: 0.000099 grad: 0.0697 (0.0749) loss: 0.8327 (0.8275) time: 0.1522 data: 0.0713 max mem: 9390 +Train: [33] [5200/6250] eta: 0:02:29 lr: 0.000099 grad: 0.0740 (0.0749) loss: 0.8292 (0.8276) time: 0.1681 data: 0.0643 max mem: 9390 +Train: [33] [5300/6250] eta: 0:02:14 lr: 0.000099 grad: 0.0729 (0.0749) loss: 0.8304 (0.8276) time: 0.1117 data: 0.0175 max mem: 9390 +Train: [33] [5400/6250] eta: 0:02:01 lr: 0.000099 grad: 0.0693 (0.0749) loss: 0.8273 (0.8276) time: 0.1459 data: 0.0569 max mem: 9390 +Train: [33] [5500/6250] eta: 0:01:46 lr: 0.000099 grad: 0.0747 (0.0750) loss: 0.8253 (0.8276) time: 0.1037 data: 0.0186 max mem: 9390 +Train: [33] [5600/6250] eta: 0:01:32 lr: 0.000099 grad: 0.0705 (0.0749) loss: 0.8304 (0.8276) time: 0.1554 data: 0.0780 max mem: 9390 +Train: [33] [5700/6250] eta: 0:01:18 lr: 0.000099 grad: 0.0713 (0.0749) loss: 0.8253 (0.8277) time: 0.1477 data: 0.0683 max mem: 9390 +Train: [33] [5800/6250] eta: 0:01:04 lr: 0.000099 grad: 0.0686 (0.0749) loss: 0.8290 (0.8277) time: 0.1680 data: 0.0864 max mem: 9390 +Train: [33] [5900/6250] eta: 0:00:49 lr: 0.000098 grad: 0.0725 (0.0748) loss: 0.8337 (0.8278) time: 0.1199 data: 0.0417 max mem: 9390 +Train: [33] [6000/6250] eta: 0:00:35 lr: 0.000098 grad: 0.0747 (0.0748) loss: 0.8305 (0.8278) time: 0.1485 data: 0.0689 max mem: 9390 +Train: [33] [6100/6250] eta: 0:00:21 lr: 0.000098 grad: 0.0706 (0.0748) loss: 0.8330 (0.8279) time: 0.1406 data: 0.0664 max mem: 9390 +Train: [33] [6200/6250] eta: 0:00:07 lr: 0.000098 grad: 0.0729 (0.0748) loss: 0.8309 (0.8279) time: 0.1585 data: 0.0832 max mem: 9390 +Train: [33] [6249/6250] eta: 0:00:00 lr: 0.000098 grad: 0.0702 (0.0748) loss: 0.8304 (0.8279) time: 0.1307 data: 0.0554 max mem: 9390 +Train: [33] Total time: 0:14:57 (0.1436 s / it) +Averaged stats: lr: 0.000098 grad: 0.0702 (0.0748) loss: 0.8304 (0.8279) +Eval (hcp-train-subset): [33] [ 0/62] eta: 0:03:23 loss: 0.8543 (0.8543) time: 3.2778 data: 3.1927 max mem: 9390 +Eval (hcp-train-subset): [33] [61/62] eta: 0:00:00 loss: 0.8413 (0.8421) time: 0.1278 data: 0.1018 max mem: 9390 +Eval (hcp-train-subset): [33] Total time: 0:00:12 (0.2070 s / it) +Averaged stats (hcp-train-subset): loss: 0.8413 (0.8421) +Eval (hcp-val): [33] [ 0/62] eta: 0:05:19 loss: 0.8354 (0.8354) time: 5.1534 data: 5.1237 max mem: 9390 +Eval (hcp-val): [33] [61/62] eta: 0:00:00 loss: 0.8372 (0.8379) time: 0.1222 data: 0.0958 max mem: 9390 +Eval (hcp-val): [33] Total time: 0:00:12 (0.2043 s / it) +Averaged stats (hcp-val): loss: 0.8372 (0.8379) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +Train: [34] [ 0/6250] eta: 7:24:35 lr: 0.000098 grad: 0.0815 (0.0815) loss: 0.8569 (0.8569) time: 4.2680 data: 4.0109 max mem: 9390 +Train: [34] [ 100/6250] eta: 0:20:58 lr: 0.000098 grad: 0.0651 (0.0756) loss: 0.8356 (0.8381) time: 0.1489 data: 0.0572 max mem: 9390 +Train: [34] [ 200/6250] eta: 0:18:00 lr: 0.000098 grad: 0.0624 (0.0709) loss: 0.8336 (0.8373) time: 0.1561 data: 0.0765 max mem: 9390 +Train: [34] [ 300/6250] eta: 0:16:19 lr: 0.000098 grad: 0.0637 (0.0690) loss: 0.8378 (0.8372) time: 0.1363 data: 0.0559 max mem: 9390 +Train: [34] [ 400/6250] eta: 0:15:20 lr: 0.000098 grad: 0.0633 (0.0688) loss: 0.8282 (0.8358) time: 0.1431 data: 0.0601 max mem: 9390 +Train: [34] [ 500/6250] eta: 0:14:41 lr: 0.000098 grad: 0.0684 (0.0690) loss: 0.8281 (0.8348) time: 0.1515 data: 0.0649 max mem: 9390 +Train: [34] [ 600/6250] eta: 0:14:03 lr: 0.000098 grad: 0.0748 (0.0699) loss: 0.8275 (0.8337) time: 0.1415 data: 0.0620 max mem: 9390 +Train: [34] [ 700/6250] eta: 0:13:31 lr: 0.000098 grad: 0.0687 (0.0703) loss: 0.8306 (0.8328) time: 0.1442 data: 0.0677 max mem: 9390 +Train: [34] [ 800/6250] eta: 0:13:11 lr: 0.000098 grad: 0.0661 (0.0704) loss: 0.8306 (0.8325) time: 0.1502 data: 0.0694 max mem: 9390 +Train: [34] [ 900/6250] eta: 0:12:58 lr: 0.000098 grad: 0.0708 (0.0705) loss: 0.8278 (0.8321) time: 0.1602 data: 0.0846 max mem: 9390 +Train: [34] [1000/6250] eta: 0:12:41 lr: 0.000098 grad: 0.0733 (0.0706) loss: 0.8285 (0.8319) time: 0.1430 data: 0.0660 max mem: 9390 +Train: [34] [1100/6250] eta: 0:12:22 lr: 0.000098 grad: 0.0690 (0.0704) loss: 0.8294 (0.8319) time: 0.1483 data: 0.0679 max mem: 9390 +Train: [34] [1200/6250] eta: 0:12:12 lr: 0.000098 grad: 0.0691 (0.0704) loss: 0.8303 (0.8318) time: 0.1328 data: 0.0510 max mem: 9390 +Train: [34] [1300/6250] eta: 0:11:56 lr: 0.000098 grad: 0.0646 (0.0705) loss: 0.8318 (0.8318) time: 0.1615 data: 0.0799 max mem: 9390 +Train: [34] [1400/6250] eta: 0:11:39 lr: 0.000098 grad: 0.0670 (0.0704) loss: 0.8342 (0.8317) time: 0.1339 data: 0.0561 max mem: 9390 +Train: [34] [1500/6250] eta: 0:11:23 lr: 0.000098 grad: 0.0720 (0.0706) loss: 0.8297 (0.8316) time: 0.1420 data: 0.0632 max mem: 9390 +Train: [34] [1600/6250] eta: 0:11:05 lr: 0.000098 grad: 0.0686 (0.0707) loss: 0.8272 (0.8316) time: 0.1447 data: 0.0653 max mem: 9390 +Train: [34] [1700/6250] eta: 0:10:45 lr: 0.000098 grad: 0.0673 (0.0706) loss: 0.8312 (0.8316) time: 0.1182 data: 0.0378 max mem: 9390 +Train: [34] [1800/6250] eta: 0:10:25 lr: 0.000098 grad: 0.0688 (0.0705) loss: 0.8315 (0.8315) time: 0.1094 data: 0.0170 max mem: 9390 +Train: [34] [1900/6250] eta: 0:10:08 lr: 0.000098 grad: 0.0712 (0.0706) loss: 0.8333 (0.8313) time: 0.1373 data: 0.0604 max mem: 9390 +Train: [34] [2000/6250] eta: 0:09:55 lr: 0.000098 grad: 0.0680 (0.0706) loss: 0.8338 (0.8313) time: 0.1502 data: 0.0713 max mem: 9390 +Train: [34] [2100/6250] eta: 0:09:44 lr: 0.000098 grad: 0.0728 (0.0708) loss: 0.8328 (0.8313) time: 0.1551 data: 0.0740 max mem: 9390 +Train: [34] [2200/6250] eta: 0:09:33 lr: 0.000098 grad: 0.0658 (0.0709) loss: 0.8325 (0.8313) time: 0.1620 data: 0.0804 max mem: 9390 +Train: [34] [2300/6250] eta: 0:09:18 lr: 0.000098 grad: 0.0728 (0.0710) loss: 0.8293 (0.8312) time: 0.1362 data: 0.0584 max mem: 9390 +Train: [34] [2400/6250] eta: 0:09:04 lr: 0.000098 grad: 0.0741 (0.0711) loss: 0.8290 (0.8312) time: 0.1735 data: 0.0940 max mem: 9390 +Train: [34] [2500/6250] eta: 0:08:48 lr: 0.000098 grad: 0.0699 (0.0712) loss: 0.8340 (0.8312) time: 0.1428 data: 0.0648 max mem: 9390 +Train: [34] [2600/6250] eta: 0:08:32 lr: 0.000098 grad: 0.0718 (0.0713) loss: 0.8326 (0.8312) time: 0.1412 data: 0.0621 max mem: 9390 +Train: [34] [2700/6250] eta: 0:08:18 lr: 0.000098 grad: 0.0688 (0.0714) loss: 0.8359 (0.8312) time: 0.1002 data: 0.0216 max mem: 9390 +Train: [34] [2800/6250] eta: 0:08:03 lr: 0.000098 grad: 0.0731 (0.0715) loss: 0.8299 (0.8311) time: 0.1499 data: 0.0740 max mem: 9390 +Train: [34] [2900/6250] eta: 0:07:51 lr: 0.000098 grad: 0.0714 (0.0716) loss: 0.8264 (0.8311) time: 0.2151 data: 0.1297 max mem: 9390 +Train: [34] [3000/6250] eta: 0:07:37 lr: 0.000098 grad: 0.0695 (0.0716) loss: 0.8311 (0.8310) time: 0.1443 data: 0.0687 max mem: 9390 +Train: [34] [3100/6250] eta: 0:07:22 lr: 0.000098 grad: 0.0680 (0.0717) loss: 0.8296 (0.8309) time: 0.1470 data: 0.0659 max mem: 9390 +Train: [34] [3200/6250] eta: 0:07:08 lr: 0.000098 grad: 0.0732 (0.0717) loss: 0.8306 (0.8309) time: 0.1509 data: 0.0741 max mem: 9390 +Train: [34] [3300/6250] eta: 0:06:54 lr: 0.000097 grad: 0.0719 (0.0718) loss: 0.8312 (0.8309) time: 0.1682 data: 0.0851 max mem: 9390 +Train: [34] [3400/6250] eta: 0:06:40 lr: 0.000097 grad: 0.0709 (0.0719) loss: 0.8286 (0.8308) time: 0.1695 data: 0.0855 max mem: 9390 +Train: [34] [3500/6250] eta: 0:06:25 lr: 0.000097 grad: 0.0700 (0.0719) loss: 0.8266 (0.8308) time: 0.1262 data: 0.0454 max mem: 9390 +Train: [34] [3600/6250] eta: 0:06:11 lr: 0.000097 grad: 0.0745 (0.0720) loss: 0.8307 (0.8307) time: 0.1078 data: 0.0306 max mem: 9390 +Train: [34] [3700/6250] eta: 0:05:57 lr: 0.000097 grad: 0.0717 (0.0722) loss: 0.8292 (0.8306) time: 0.1307 data: 0.0526 max mem: 9390 +Train: [34] [3800/6250] eta: 0:05:42 lr: 0.000097 grad: 0.0732 (0.0723) loss: 0.8262 (0.8306) time: 0.1421 data: 0.0641 max mem: 9390 +Train: [34] [3900/6250] eta: 0:05:29 lr: 0.000097 grad: 0.0749 (0.0724) loss: 0.8296 (0.8305) time: 0.2116 data: 0.1330 max mem: 9390 +Train: [34] [4000/6250] eta: 0:05:15 lr: 0.000097 grad: 0.0738 (0.0725) loss: 0.8244 (0.8305) time: 0.1454 data: 0.0658 max mem: 9390 +Train: [34] [4100/6250] eta: 0:05:02 lr: 0.000097 grad: 0.0790 (0.0727) loss: 0.8289 (0.8304) time: 0.1095 data: 0.0252 max mem: 9390 +Train: [34] [4200/6250] eta: 0:04:47 lr: 0.000097 grad: 0.0732 (0.0727) loss: 0.8278 (0.8303) time: 0.1354 data: 0.0611 max mem: 9390 +Train: [34] [4300/6250] eta: 0:04:34 lr: 0.000097 grad: 0.0757 (0.0728) loss: 0.8240 (0.8302) time: 0.1503 data: 0.0682 max mem: 9390 +Train: [34] [4400/6250] eta: 0:04:20 lr: 0.000097 grad: 0.0761 (0.0729) loss: 0.8182 (0.8301) time: 0.1599 data: 0.0804 max mem: 9390 +Train: [34] [4500/6250] eta: 0:04:06 lr: 0.000097 grad: 0.0709 (0.0730) loss: 0.8297 (0.8300) time: 0.1394 data: 0.0621 max mem: 9390 +Train: [34] [4600/6250] eta: 0:03:52 lr: 0.000097 grad: 0.0760 (0.0730) loss: 0.8249 (0.8299) time: 0.1403 data: 0.0638 max mem: 9390 +Train: [34] [4700/6250] eta: 0:03:38 lr: 0.000097 grad: 0.0727 (0.0731) loss: 0.8226 (0.8299) time: 0.1526 data: 0.0678 max mem: 9390 +Train: [34] [4800/6250] eta: 0:03:25 lr: 0.000097 grad: 0.0747 (0.0732) loss: 0.8262 (0.8298) time: 0.1860 data: 0.1054 max mem: 9390 +Train: [34] [4900/6250] eta: 0:03:10 lr: 0.000097 grad: 0.0697 (0.0732) loss: 0.8249 (0.8297) time: 0.1402 data: 0.0675 max mem: 9390 +Train: [34] [5000/6250] eta: 0:02:56 lr: 0.000097 grad: 0.0740 (0.0733) loss: 0.8297 (0.8296) time: 0.1569 data: 0.0804 max mem: 9390 +Train: [34] [5100/6250] eta: 0:02:42 lr: 0.000097 grad: 0.0699 (0.0733) loss: 0.8296 (0.8295) time: 0.1661 data: 0.0859 max mem: 9390 +Train: [34] [5200/6250] eta: 0:02:28 lr: 0.000097 grad: 0.0751 (0.0734) loss: 0.8208 (0.8294) time: 0.1866 data: 0.1035 max mem: 9390 +Train: [34] [5300/6250] eta: 0:02:14 lr: 0.000097 grad: 0.0763 (0.0735) loss: 0.8246 (0.8293) time: 0.1649 data: 0.0814 max mem: 9390 +Train: [34] [5400/6250] eta: 0:02:00 lr: 0.000097 grad: 0.0763 (0.0735) loss: 0.8280 (0.8292) time: 0.1533 data: 0.0754 max mem: 9390 +Train: [34] [5500/6250] eta: 0:01:46 lr: 0.000097 grad: 0.0716 (0.0736) loss: 0.8274 (0.8291) time: 0.1628 data: 0.0880 max mem: 9390 +Train: [34] [5600/6250] eta: 0:01:32 lr: 0.000097 grad: 0.0796 (0.0736) loss: 0.8238 (0.8291) time: 0.1657 data: 0.0770 max mem: 9390 +Train: [34] [5700/6250] eta: 0:01:18 lr: 0.000097 grad: 0.0758 (0.0737) loss: 0.8250 (0.8290) time: 0.1557 data: 0.0762 max mem: 9390 +Train: [34] [5800/6250] eta: 0:01:04 lr: 0.000097 grad: 0.0752 (0.0737) loss: 0.8210 (0.8289) time: 0.1544 data: 0.0699 max mem: 9390 +Train: [34] [5900/6250] eta: 0:00:49 lr: 0.000097 grad: 0.0745 (0.0738) loss: 0.8262 (0.8288) time: 0.1264 data: 0.0430 max mem: 9390 +Train: [34] [6000/6250] eta: 0:00:35 lr: 0.000097 grad: 0.0734 (0.0738) loss: 0.8263 (0.8287) time: 0.1408 data: 0.0613 max mem: 9390 +Train: [34] [6100/6250] eta: 0:00:21 lr: 0.000097 grad: 0.0778 (0.0739) loss: 0.8232 (0.8286) time: 0.1635 data: 0.0906 max mem: 9390 +Train: [34] [6200/6250] eta: 0:00:07 lr: 0.000097 grad: 0.0756 (0.0740) loss: 0.8180 (0.8284) time: 0.1479 data: 0.0677 max mem: 9390 +Train: [34] [6249/6250] eta: 0:00:00 lr: 0.000097 grad: 0.0799 (0.0740) loss: 0.8131 (0.8283) time: 0.1215 data: 0.0451 max mem: 9390 +Train: [34] Total time: 0:14:56 (0.1434 s / it) +Averaged stats: lr: 0.000097 grad: 0.0799 (0.0740) loss: 0.8131 (0.8283) +Eval (hcp-train-subset): [34] [ 0/62] eta: 0:04:36 loss: 0.8518 (0.8518) time: 4.4621 data: 4.4295 max mem: 9390 +Eval (hcp-train-subset): [34] [61/62] eta: 0:00:00 loss: 0.8417 (0.8410) time: 0.1135 data: 0.0872 max mem: 9390 +Eval (hcp-train-subset): [34] Total time: 0:00:11 (0.1923 s / it) +Averaged stats (hcp-train-subset): loss: 0.8417 (0.8410) +Making plots (hcp-train-subset): example=47 +Eval (hcp-val): [34] [ 0/62] eta: 0:04:26 loss: 0.8325 (0.8325) time: 4.2977 data: 4.2675 max mem: 9390 +Eval (hcp-val): [34] [61/62] eta: 0:00:00 loss: 0.8359 (0.8375) time: 0.1315 data: 0.1062 max mem: 9390 +Eval (hcp-val): [34] Total time: 0:00:13 (0.2127 s / it) +Averaged stats (hcp-val): loss: 0.8359 (0.8375) +Making plots (hcp-val): example=37 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +Train: [35] [ 0/6250] eta: 9:07:43 lr: 0.000097 grad: 0.0553 (0.0553) loss: 0.8624 (0.8624) time: 5.2581 data: 5.1547 max mem: 9390 +Train: [35] [ 100/6250] eta: 0:20:29 lr: 0.000097 grad: 0.0674 (0.0866) loss: 0.8327 (0.8384) time: 0.1500 data: 0.0606 max mem: 9390 +Train: [35] [ 200/6250] eta: 0:17:59 lr: 0.000097 grad: 0.0673 (0.0818) loss: 0.8363 (0.8367) time: 0.1416 data: 0.0549 max mem: 9390 +Train: [35] [ 300/6250] eta: 0:16:41 lr: 0.000097 grad: 0.0703 (0.0799) loss: 0.8321 (0.8349) time: 0.1475 data: 0.0704 max mem: 9390 +Train: [35] [ 400/6250] eta: 0:15:42 lr: 0.000097 grad: 0.0757 (0.0782) loss: 0.8342 (0.8341) time: 0.1332 data: 0.0527 max mem: 9390 +Train: [35] [ 500/6250] eta: 0:14:55 lr: 0.000097 grad: 0.0697 (0.0770) loss: 0.8314 (0.8334) time: 0.1185 data: 0.0356 max mem: 9390 +Train: [35] [ 600/6250] eta: 0:14:17 lr: 0.000097 grad: 0.0681 (0.0765) loss: 0.8236 (0.8325) time: 0.1369 data: 0.0530 max mem: 9390 +Train: [35] [ 700/6250] eta: 0:13:44 lr: 0.000096 grad: 0.0728 (0.0761) loss: 0.8284 (0.8319) time: 0.1375 data: 0.0539 max mem: 9390 +Train: [35] [ 800/6250] eta: 0:13:19 lr: 0.000096 grad: 0.0711 (0.0757) loss: 0.8272 (0.8312) time: 0.1463 data: 0.0637 max mem: 9390 +Train: [35] [ 900/6250] eta: 0:12:59 lr: 0.000096 grad: 0.0735 (0.0754) loss: 0.8290 (0.8308) time: 0.1792 data: 0.0968 max mem: 9390 +Train: [35] [1000/6250] eta: 0:12:47 lr: 0.000096 grad: 0.0657 (0.0751) loss: 0.8277 (0.8306) time: 0.1373 data: 0.0557 max mem: 9390 +Train: [35] [1100/6250] eta: 0:12:28 lr: 0.000096 grad: 0.0782 (0.0752) loss: 0.8284 (0.8301) time: 0.1388 data: 0.0587 max mem: 9390 +Train: [35] [1200/6250] eta: 0:12:15 lr: 0.000096 grad: 0.0730 (0.0751) loss: 0.8282 (0.8299) time: 0.1451 data: 0.0682 max mem: 9390 +Train: [35] [1300/6250] eta: 0:11:58 lr: 0.000096 grad: 0.0765 (0.0751) loss: 0.8219 (0.8294) time: 0.1432 data: 0.0682 max mem: 9390 +Train: [35] [1400/6250] eta: 0:11:41 lr: 0.000096 grad: 0.0782 (0.0751) loss: 0.8266 (0.8291) time: 0.1579 data: 0.0800 max mem: 9390 +Train: [35] [1500/6250] eta: 0:11:19 lr: 0.000096 grad: 0.0732 (0.0751) loss: 0.8296 (0.8289) time: 0.1182 data: 0.0352 max mem: 9390 +Train: [35] [1600/6250] eta: 0:11:00 lr: 0.000096 grad: 0.0782 (0.0753) loss: 0.8255 (0.8286) time: 0.1158 data: 0.0358 max mem: 9390 +Train: [35] [1700/6250] eta: 0:10:41 lr: 0.000096 grad: 0.0820 (0.0755) loss: 0.8251 (0.8283) time: 0.1277 data: 0.0506 max mem: 9390 +Train: [35] [1800/6250] eta: 0:10:22 lr: 0.000096 grad: 0.0760 (0.0756) loss: 0.8264 (0.8279) time: 0.1068 data: 0.0274 max mem: 9390 +Train: [35] [1900/6250] eta: 0:10:03 lr: 0.000096 grad: 0.0741 (0.0758) loss: 0.8325 (0.8277) time: 0.0981 data: 0.0162 max mem: 9390 +Train: [35] [2000/6250] eta: 0:09:49 lr: 0.000096 grad: 0.0712 (0.0759) loss: 0.8236 (0.8274) time: 0.1670 data: 0.0883 max mem: 9390 +Train: [35] [2100/6250] eta: 0:09:33 lr: 0.000096 grad: 0.0759 (0.0761) loss: 0.8222 (0.8273) time: 0.1511 data: 0.0768 max mem: 9390 +Train: [35] [2200/6250] eta: 0:09:20 lr: 0.000096 grad: 0.0725 (0.0760) loss: 0.8295 (0.8273) time: 0.1541 data: 0.0827 max mem: 9390 +Train: [35] [2300/6250] eta: 0:09:07 lr: 0.000096 grad: 0.0762 (0.0760) loss: 0.8213 (0.8272) time: 0.1372 data: 0.0652 max mem: 9390 +Train: [35] [2400/6250] eta: 0:08:53 lr: 0.000096 grad: 0.0748 (0.0760) loss: 0.8290 (0.8272) time: 0.1621 data: 0.0843 max mem: 9390 +Train: [35] [2500/6250] eta: 0:08:37 lr: 0.000096 grad: 0.0722 (0.0760) loss: 0.8278 (0.8272) time: 0.1289 data: 0.0479 max mem: 9390 +Train: [35] [2600/6250] eta: 0:08:22 lr: 0.000096 grad: 0.0732 (0.0760) loss: 0.8266 (0.8272) time: 0.1496 data: 0.0702 max mem: 9390 +Train: [35] [2700/6250] eta: 0:08:08 lr: 0.000096 grad: 0.0768 (0.0760) loss: 0.8273 (0.8272) time: 0.1180 data: 0.0354 max mem: 9390 +Train: [35] [2800/6250] eta: 0:07:55 lr: 0.000096 grad: 0.0710 (0.0760) loss: 0.8323 (0.8272) time: 0.1232 data: 0.0304 max mem: 9390 +Train: [35] [2900/6250] eta: 0:07:42 lr: 0.000096 grad: 0.0717 (0.0760) loss: 0.8286 (0.8273) time: 0.1364 data: 0.0452 max mem: 9390 +Train: [35] [3000/6250] eta: 0:07:29 lr: 0.000096 grad: 0.0747 (0.0762) loss: 0.8200 (0.8272) time: 0.1634 data: 0.0816 max mem: 9390 +Train: [35] [3100/6250] eta: 0:07:17 lr: 0.000096 grad: 0.0734 (0.0763) loss: 0.8317 (0.8272) time: 0.1464 data: 0.0580 max mem: 9390 +Train: [35] [3200/6250] eta: 0:07:04 lr: 0.000096 grad: 0.0784 (0.0764) loss: 0.8258 (0.8271) time: 0.1480 data: 0.0619 max mem: 9390 +Train: [35] [3300/6250] eta: 0:06:50 lr: 0.000096 grad: 0.0798 (0.0765) loss: 0.8184 (0.8271) time: 0.1332 data: 0.0567 max mem: 9390 +Train: [35] [3400/6250] eta: 0:06:36 lr: 0.000096 grad: 0.0720 (0.0765) loss: 0.8202 (0.8270) time: 0.1427 data: 0.0647 max mem: 9390 +Train: [35] [3500/6250] eta: 0:06:22 lr: 0.000096 grad: 0.0730 (0.0765) loss: 0.8289 (0.8270) time: 0.1305 data: 0.0490 max mem: 9390 +Train: [35] [3600/6250] eta: 0:06:09 lr: 0.000096 grad: 0.0725 (0.0765) loss: 0.8266 (0.8270) time: 0.1407 data: 0.0579 max mem: 9390 +Train: [35] [3700/6250] eta: 0:05:56 lr: 0.000096 grad: 0.0714 (0.0765) loss: 0.8288 (0.8270) time: 0.1451 data: 0.0551 max mem: 9390 +Train: [35] [3800/6250] eta: 0:05:42 lr: 0.000096 grad: 0.0735 (0.0766) loss: 0.8263 (0.8270) time: 0.1532 data: 0.0771 max mem: 9390 +Train: [35] [3900/6250] eta: 0:05:29 lr: 0.000096 grad: 0.0757 (0.0766) loss: 0.8226 (0.8269) time: 0.1471 data: 0.0663 max mem: 9390 +Train: [35] [4000/6250] eta: 0:05:15 lr: 0.000096 grad: 0.0754 (0.0767) loss: 0.8282 (0.8268) time: 0.1460 data: 0.0712 max mem: 9390 +Train: [35] [4100/6250] eta: 0:05:01 lr: 0.000096 grad: 0.0794 (0.0768) loss: 0.8237 (0.8267) time: 0.1541 data: 0.0790 max mem: 9390 +Train: [35] [4200/6250] eta: 0:04:47 lr: 0.000096 grad: 0.0763 (0.0769) loss: 0.8247 (0.8267) time: 0.1242 data: 0.0490 max mem: 9390 +Train: [35] [4300/6250] eta: 0:04:33 lr: 0.000095 grad: 0.0742 (0.0768) loss: 0.8299 (0.8267) time: 0.1359 data: 0.0565 max mem: 9390 +Train: [35] [4400/6250] eta: 0:04:20 lr: 0.000095 grad: 0.0694 (0.0768) loss: 0.8322 (0.8268) time: 0.1935 data: 0.1067 max mem: 9390 +Train: [35] [4500/6250] eta: 0:04:05 lr: 0.000095 grad: 0.0741 (0.0767) loss: 0.8256 (0.8268) time: 0.1389 data: 0.0624 max mem: 9390 +Train: [35] [4600/6250] eta: 0:03:51 lr: 0.000095 grad: 0.0734 (0.0767) loss: 0.8253 (0.8268) time: 0.1501 data: 0.0716 max mem: 9390 +Train: [35] [4700/6250] eta: 0:03:37 lr: 0.000095 grad: 0.0742 (0.0767) loss: 0.8243 (0.8268) time: 0.1367 data: 0.0558 max mem: 9390 +Train: [35] [4800/6250] eta: 0:03:23 lr: 0.000095 grad: 0.0754 (0.0768) loss: 0.8320 (0.8268) time: 0.1679 data: 0.0894 max mem: 9390 +Train: [35] [4900/6250] eta: 0:03:09 lr: 0.000095 grad: 0.0758 (0.0769) loss: 0.8235 (0.8268) time: 0.1459 data: 0.0684 max mem: 9390 +Train: [35] [5000/6250] eta: 0:02:55 lr: 0.000095 grad: 0.0757 (0.0770) loss: 0.8237 (0.8267) time: 0.1531 data: 0.0700 max mem: 9390 +Train: [35] [5100/6250] eta: 0:02:41 lr: 0.000095 grad: 0.0744 (0.0770) loss: 0.8275 (0.8267) time: 0.1507 data: 0.0581 max mem: 9390 +Train: [35] [5200/6250] eta: 0:02:27 lr: 0.000095 grad: 0.0807 (0.0772) loss: 0.8245 (0.8266) time: 0.1349 data: 0.0596 max mem: 9390 +Train: [35] [5300/6250] eta: 0:02:13 lr: 0.000095 grad: 0.0741 (0.0772) loss: 0.8268 (0.8265) time: 0.1245 data: 0.0476 max mem: 9390 +Train: [35] [5400/6250] eta: 0:01:59 lr: 0.000095 grad: 0.0757 (0.0773) loss: 0.8225 (0.8265) time: 0.1133 data: 0.0367 max mem: 9390 +Train: [35] [5500/6250] eta: 0:01:45 lr: 0.000095 grad: 0.0789 (0.0774) loss: 0.8334 (0.8264) time: 0.1639 data: 0.0905 max mem: 9390 +Train: [35] [5600/6250] eta: 0:01:31 lr: 0.000095 grad: 0.0767 (0.0775) loss: 0.8300 (0.8263) time: 0.1371 data: 0.0572 max mem: 9390 +Train: [35] [5700/6250] eta: 0:01:17 lr: 0.000095 grad: 0.0772 (0.0776) loss: 0.8192 (0.8263) time: 0.1251 data: 0.0452 max mem: 9390 +Train: [35] [5800/6250] eta: 0:01:03 lr: 0.000095 grad: 0.0764 (0.0777) loss: 0.8266 (0.8262) time: 0.1520 data: 0.0667 max mem: 9390 +Train: [35] [5900/6250] eta: 0:00:49 lr: 0.000095 grad: 0.0802 (0.0778) loss: 0.8233 (0.8261) time: 0.1413 data: 0.0648 max mem: 9390 +Train: [35] [6000/6250] eta: 0:00:35 lr: 0.000095 grad: 0.0786 (0.0778) loss: 0.8213 (0.8261) time: 0.1509 data: 0.0654 max mem: 9390 +Train: [35] [6100/6250] eta: 0:00:21 lr: 0.000095 grad: 0.0759 (0.0779) loss: 0.8236 (0.8260) time: 0.1450 data: 0.0654 max mem: 9390 +Train: [35] [6200/6250] eta: 0:00:07 lr: 0.000095 grad: 0.0753 (0.0780) loss: 0.8269 (0.8259) time: 0.1472 data: 0.0682 max mem: 9390 +Train: [35] [6249/6250] eta: 0:00:00 lr: 0.000095 grad: 0.0839 (0.0781) loss: 0.8237 (0.8259) time: 0.1575 data: 0.0738 max mem: 9390 +Train: [35] Total time: 0:14:53 (0.1429 s / it) +Averaged stats: lr: 0.000095 grad: 0.0839 (0.0781) loss: 0.8237 (0.8259) +Eval (hcp-train-subset): [35] [ 0/62] eta: 0:04:09 loss: 0.8524 (0.8524) time: 4.0164 data: 3.9470 max mem: 9390 +Eval (hcp-train-subset): [35] [61/62] eta: 0:00:00 loss: 0.8401 (0.8418) time: 0.1198 data: 0.0946 max mem: 9390 +Eval (hcp-train-subset): [35] Total time: 0:00:13 (0.2113 s / it) +Averaged stats (hcp-train-subset): loss: 0.8401 (0.8418) +Eval (hcp-val): [35] [ 0/62] eta: 0:03:29 loss: 0.8379 (0.8379) time: 3.3729 data: 3.2930 max mem: 9390 +Eval (hcp-val): [35] [61/62] eta: 0:00:00 loss: 0.8365 (0.8382) time: 0.1302 data: 0.1036 max mem: 9390 +Eval (hcp-val): [35] Total time: 0:00:12 (0.2078 s / it) +Averaged stats (hcp-val): loss: 0.8365 (0.8382) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +Train: [36] [ 0/6250] eta: 8:58:57 lr: 0.000095 grad: 0.0782 (0.0782) loss: 0.8630 (0.8630) time: 5.1740 data: 5.0530 max mem: 9390 +Train: [36] [ 100/6250] eta: 0:19:38 lr: 0.000095 grad: 0.0806 (0.0824) loss: 0.8404 (0.8402) time: 0.1488 data: 0.0650 max mem: 9390 +Train: [36] [ 200/6250] eta: 0:17:21 lr: 0.000095 grad: 0.0773 (0.0811) loss: 0.8293 (0.8359) time: 0.1833 data: 0.0865 max mem: 9390 +Train: [36] [ 300/6250] eta: 0:16:36 lr: 0.000095 grad: 0.0752 (0.0803) loss: 0.8343 (0.8334) time: 0.1802 data: 0.0928 max mem: 9390 +Train: [36] [ 400/6250] eta: 0:15:53 lr: 0.000095 grad: 0.0748 (0.0797) loss: 0.8288 (0.8320) time: 0.1582 data: 0.0645 max mem: 9390 +Train: [36] [ 500/6250] eta: 0:15:14 lr: 0.000095 grad: 0.0805 (0.0797) loss: 0.8278 (0.8308) time: 0.1421 data: 0.0608 max mem: 9390 +Train: [36] [ 600/6250] eta: 0:14:32 lr: 0.000095 grad: 0.0762 (0.0797) loss: 0.8247 (0.8294) time: 0.1361 data: 0.0551 max mem: 9390 +Train: [36] [ 700/6250] eta: 0:14:09 lr: 0.000095 grad: 0.0739 (0.0795) loss: 0.8179 (0.8286) time: 0.1609 data: 0.0787 max mem: 9390 +Train: [36] [ 800/6250] eta: 0:13:42 lr: 0.000095 grad: 0.0757 (0.0793) loss: 0.8219 (0.8280) time: 0.1421 data: 0.0561 max mem: 9390 +Train: [36] [ 900/6250] eta: 0:13:19 lr: 0.000095 grad: 0.0725 (0.0789) loss: 0.8243 (0.8279) time: 0.1241 data: 0.0428 max mem: 9390 +Train: [36] [1000/6250] eta: 0:13:05 lr: 0.000095 grad: 0.0763 (0.0786) loss: 0.8218 (0.8277) time: 0.1805 data: 0.0989 max mem: 9390 +Train: [36] [1100/6250] eta: 0:12:48 lr: 0.000095 grad: 0.0738 (0.0785) loss: 0.8267 (0.8274) time: 0.1488 data: 0.0555 max mem: 9390 +Train: [36] [1200/6250] eta: 0:12:31 lr: 0.000095 grad: 0.0752 (0.0783) loss: 0.8206 (0.8272) time: 0.1552 data: 0.0710 max mem: 9390 +Train: [36] [1300/6250] eta: 0:12:17 lr: 0.000095 grad: 0.0766 (0.0783) loss: 0.8189 (0.8271) time: 0.1433 data: 0.0614 max mem: 9390 +Train: [36] [1400/6250] eta: 0:11:57 lr: 0.000095 grad: 0.0773 (0.0784) loss: 0.8243 (0.8268) time: 0.1219 data: 0.0383 max mem: 9390 +Train: [36] [1500/6250] eta: 0:11:37 lr: 0.000095 grad: 0.0729 (0.0785) loss: 0.8313 (0.8267) time: 0.1256 data: 0.0424 max mem: 9390 +Train: [36] [1600/6250] eta: 0:11:15 lr: 0.000094 grad: 0.0746 (0.0784) loss: 0.8257 (0.8266) time: 0.1149 data: 0.0341 max mem: 9390 +Train: [36] [1700/6250] eta: 0:10:56 lr: 0.000094 grad: 0.0752 (0.0784) loss: 0.8283 (0.8265) time: 0.1309 data: 0.0552 max mem: 9390 +Train: [36] [1800/6250] eta: 0:10:35 lr: 0.000094 grad: 0.0765 (0.0784) loss: 0.8200 (0.8264) time: 0.1270 data: 0.0515 max mem: 9390 +Train: [36] [1900/6250] eta: 0:10:15 lr: 0.000094 grad: 0.0747 (0.0783) loss: 0.8280 (0.8264) time: 0.1143 data: 0.0341 max mem: 9390 +Train: [36] [2000/6250] eta: 0:09:56 lr: 0.000094 grad: 0.0744 (0.0783) loss: 0.8227 (0.8264) time: 0.1295 data: 0.0464 max mem: 9390 +Train: [36] [2100/6250] eta: 0:09:39 lr: 0.000094 grad: 0.0818 (0.0784) loss: 0.8272 (0.8265) time: 0.1358 data: 0.0567 max mem: 9390 +Train: [36] [2200/6250] eta: 0:09:26 lr: 0.000094 grad: 0.0769 (0.0784) loss: 0.8253 (0.8265) time: 0.1585 data: 0.0826 max mem: 9390 +Train: [36] [2300/6250] eta: 0:09:12 lr: 0.000094 grad: 0.0777 (0.0785) loss: 0.8245 (0.8264) time: 0.1491 data: 0.0715 max mem: 9390 +Train: [36] [2400/6250] eta: 0:08:57 lr: 0.000094 grad: 0.0723 (0.0785) loss: 0.8292 (0.8264) time: 0.1268 data: 0.0511 max mem: 9390 +Train: [36] [2500/6250] eta: 0:08:41 lr: 0.000094 grad: 0.0809 (0.0787) loss: 0.8225 (0.8264) time: 0.1167 data: 0.0348 max mem: 9390 +Train: [36] [2600/6250] eta: 0:08:27 lr: 0.000094 grad: 0.0756 (0.0788) loss: 0.8228 (0.8263) time: 0.1452 data: 0.0689 max mem: 9390 +Train: [36] [2700/6250] eta: 0:08:11 lr: 0.000094 grad: 0.0743 (0.0789) loss: 0.8291 (0.8263) time: 0.1263 data: 0.0470 max mem: 9390 +Train: [36] [2800/6250] eta: 0:07:56 lr: 0.000094 grad: 0.0722 (0.0789) loss: 0.8230 (0.8262) time: 0.1070 data: 0.0212 max mem: 9390 +Train: [36] [2900/6250] eta: 0:07:44 lr: 0.000094 grad: 0.0755 (0.0789) loss: 0.8248 (0.8262) time: 0.1511 data: 0.0727 max mem: 9390 +Train: [36] [3000/6250] eta: 0:07:31 lr: 0.000094 grad: 0.0738 (0.0789) loss: 0.8311 (0.8262) time: 0.1411 data: 0.0637 max mem: 9390 +Train: [36] [3100/6250] eta: 0:07:16 lr: 0.000094 grad: 0.0732 (0.0790) loss: 0.8275 (0.8262) time: 0.1282 data: 0.0464 max mem: 9390 +Train: [36] [3200/6250] eta: 0:07:02 lr: 0.000094 grad: 0.0744 (0.0789) loss: 0.8185 (0.8261) time: 0.1393 data: 0.0629 max mem: 9390 +Train: [36] [3300/6250] eta: 0:06:49 lr: 0.000094 grad: 0.0749 (0.0789) loss: 0.8208 (0.8260) time: 0.1430 data: 0.0664 max mem: 9390 +Train: [36] [3400/6250] eta: 0:06:35 lr: 0.000094 grad: 0.0751 (0.0789) loss: 0.8231 (0.8259) time: 0.1401 data: 0.0590 max mem: 9390 +Train: [36] [3500/6250] eta: 0:06:22 lr: 0.000094 grad: 0.0748 (0.0789) loss: 0.8258 (0.8258) time: 0.1228 data: 0.0378 max mem: 9390 +Train: [36] [3600/6250] eta: 0:06:09 lr: 0.000094 grad: 0.0730 (0.0789) loss: 0.8296 (0.8258) time: 0.1539 data: 0.0783 max mem: 9390 +Train: [36] [3700/6250] eta: 0:05:55 lr: 0.000094 grad: 0.0758 (0.0788) loss: 0.8271 (0.8258) time: 0.1530 data: 0.0751 max mem: 9390 +Train: [36] [3800/6250] eta: 0:05:42 lr: 0.000094 grad: 0.0739 (0.0788) loss: 0.8218 (0.8257) time: 0.1524 data: 0.0714 max mem: 9390 +Train: [36] [3900/6250] eta: 0:05:28 lr: 0.000094 grad: 0.0787 (0.0788) loss: 0.8190 (0.8256) time: 0.1459 data: 0.0646 max mem: 9390 +Train: [36] [4000/6250] eta: 0:05:14 lr: 0.000094 grad: 0.0770 (0.0788) loss: 0.8211 (0.8255) time: 0.1201 data: 0.0427 max mem: 9390 +Train: [36] [4100/6250] eta: 0:05:01 lr: 0.000094 grad: 0.0720 (0.0787) loss: 0.8227 (0.8254) time: 0.1544 data: 0.0706 max mem: 9390 +Train: [36] [4200/6250] eta: 0:04:48 lr: 0.000094 grad: 0.0749 (0.0787) loss: 0.8242 (0.8254) time: 0.1338 data: 0.0450 max mem: 9390 +Train: [36] [4300/6250] eta: 0:04:34 lr: 0.000094 grad: 0.0780 (0.0787) loss: 0.8254 (0.8253) time: 0.1422 data: 0.0654 max mem: 9390 +Train: [36] [4400/6250] eta: 0:04:20 lr: 0.000094 grad: 0.0742 (0.0788) loss: 0.8258 (0.8252) time: 0.1292 data: 0.0448 max mem: 9390 +Train: [36] [4500/6250] eta: 0:04:06 lr: 0.000094 grad: 0.0789 (0.0787) loss: 0.8235 (0.8251) time: 0.1388 data: 0.0524 max mem: 9390 +Train: [36] [4600/6250] eta: 0:03:52 lr: 0.000094 grad: 0.0760 (0.0787) loss: 0.8253 (0.8251) time: 0.1584 data: 0.0561 max mem: 9390 +Train: [36] [4700/6250] eta: 0:03:38 lr: 0.000094 grad: 0.0753 (0.0787) loss: 0.8141 (0.8250) time: 0.1514 data: 0.0752 max mem: 9390 +Train: [36] [4800/6250] eta: 0:03:24 lr: 0.000094 grad: 0.0751 (0.0787) loss: 0.8185 (0.8250) time: 0.1340 data: 0.0563 max mem: 9390 +Train: [36] [4900/6250] eta: 0:03:10 lr: 0.000094 grad: 0.0780 (0.0787) loss: 0.8261 (0.8249) time: 0.1611 data: 0.0815 max mem: 9390 +Train: [36] [5000/6250] eta: 0:02:56 lr: 0.000094 grad: 0.0760 (0.0787) loss: 0.8220 (0.8249) time: 0.1427 data: 0.0600 max mem: 9390 +Train: [36] [5100/6250] eta: 0:02:42 lr: 0.000093 grad: 0.0724 (0.0787) loss: 0.8243 (0.8248) time: 0.1488 data: 0.0751 max mem: 9390 +Train: [36] [5200/6250] eta: 0:02:28 lr: 0.000093 grad: 0.0775 (0.0786) loss: 0.8264 (0.8249) time: 0.1625 data: 0.0816 max mem: 9390 +Train: [36] [5300/6250] eta: 0:02:14 lr: 0.000093 grad: 0.0761 (0.0785) loss: 0.8246 (0.8249) time: 0.1295 data: 0.0518 max mem: 9390 +Train: [36] [5400/6250] eta: 0:02:00 lr: 0.000093 grad: 0.0733 (0.0785) loss: 0.8269 (0.8249) time: 0.1373 data: 0.0518 max mem: 9390 +Train: [36] [5500/6250] eta: 0:01:46 lr: 0.000093 grad: 0.0734 (0.0785) loss: 0.8266 (0.8250) time: 0.1377 data: 0.0522 max mem: 9390 +Train: [36] [5600/6250] eta: 0:01:32 lr: 0.000093 grad: 0.0770 (0.0784) loss: 0.8186 (0.8249) time: 0.1606 data: 0.0715 max mem: 9390 +Train: [36] [5700/6250] eta: 0:01:18 lr: 0.000093 grad: 0.0703 (0.0784) loss: 0.8271 (0.8250) time: 0.1548 data: 0.0692 max mem: 9390 +Train: [36] [5800/6250] eta: 0:01:04 lr: 0.000093 grad: 0.0770 (0.0784) loss: 0.8255 (0.8250) time: 0.1269 data: 0.0480 max mem: 9390 +Train: [36] [5900/6250] eta: 0:00:49 lr: 0.000093 grad: 0.0678 (0.0784) loss: 0.8255 (0.8250) time: 0.1178 data: 0.0403 max mem: 9390 +Train: [36] [6000/6250] eta: 0:00:35 lr: 0.000093 grad: 0.0758 (0.0783) loss: 0.8203 (0.8249) time: 0.1407 data: 0.0614 max mem: 9390 +Train: [36] [6100/6250] eta: 0:00:21 lr: 0.000093 grad: 0.0719 (0.0783) loss: 0.8299 (0.8249) time: 0.1732 data: 0.0866 max mem: 9390 +Train: [36] [6200/6250] eta: 0:00:07 lr: 0.000093 grad: 0.0750 (0.0783) loss: 0.8141 (0.8249) time: 0.1393 data: 0.0628 max mem: 9390 +Train: [36] [6249/6250] eta: 0:00:00 lr: 0.000093 grad: 0.0710 (0.0783) loss: 0.8250 (0.8249) time: 0.1334 data: 0.0496 max mem: 9390 +Train: [36] Total time: 0:14:57 (0.1437 s / it) +Averaged stats: lr: 0.000093 grad: 0.0710 (0.0783) loss: 0.8250 (0.8249) +Eval (hcp-train-subset): [36] [ 0/62] eta: 0:03:39 loss: 0.8531 (0.8531) time: 3.5374 data: 3.4730 max mem: 9390 +Eval (hcp-train-subset): [36] [61/62] eta: 0:00:00 loss: 0.8391 (0.8415) time: 0.1241 data: 0.0994 max mem: 9390 +Eval (hcp-train-subset): [36] Total time: 0:00:12 (0.1965 s / it) +Averaged stats (hcp-train-subset): loss: 0.8391 (0.8415) +Eval (hcp-val): [36] [ 0/62] eta: 0:03:08 loss: 0.8330 (0.8330) time: 3.0441 data: 2.9754 max mem: 9390 +Eval (hcp-val): [36] [61/62] eta: 0:00:00 loss: 0.8363 (0.8378) time: 0.1230 data: 0.0977 max mem: 9390 +Eval (hcp-val): [36] Total time: 0:00:13 (0.2180 s / it) +Averaged stats (hcp-val): loss: 0.8363 (0.8378) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +Train: [37] [ 0/6250] eta: 10:23:40 lr: 0.000093 grad: 0.2037 (0.2037) loss: 0.8231 (0.8231) time: 5.9873 data: 5.8927 max mem: 9390 +Train: [37] [ 100/6250] eta: 0:19:57 lr: 0.000093 grad: 0.0752 (0.0818) loss: 0.8293 (0.8379) time: 0.1756 data: 0.0859 max mem: 9390 +Train: [37] [ 200/6250] eta: 0:17:36 lr: 0.000093 grad: 0.0756 (0.0795) loss: 0.8249 (0.8321) time: 0.1512 data: 0.0671 max mem: 9390 +Train: [37] [ 300/6250] eta: 0:16:31 lr: 0.000093 grad: 0.0677 (0.0780) loss: 0.8313 (0.8310) time: 0.1625 data: 0.0790 max mem: 9390 +Train: [37] [ 400/6250] eta: 0:15:33 lr: 0.000093 grad: 0.0717 (0.0770) loss: 0.8207 (0.8302) time: 0.1309 data: 0.0479 max mem: 9390 +Train: [37] [ 500/6250] eta: 0:14:49 lr: 0.000093 grad: 0.0675 (0.0760) loss: 0.8355 (0.8301) time: 0.1443 data: 0.0598 max mem: 9390 +Train: [37] [ 600/6250] eta: 0:14:06 lr: 0.000093 grad: 0.0687 (0.0757) loss: 0.8305 (0.8304) time: 0.1298 data: 0.0398 max mem: 9390 +Train: [37] [ 700/6250] eta: 0:13:41 lr: 0.000093 grad: 0.0671 (0.0755) loss: 0.8292 (0.8305) time: 0.1170 data: 0.0372 max mem: 9390 +Train: [37] [ 800/6250] eta: 0:13:11 lr: 0.000093 grad: 0.0691 (0.0750) loss: 0.8347 (0.8308) time: 0.1439 data: 0.0573 max mem: 9390 +Train: [37] [ 900/6250] eta: 0:12:49 lr: 0.000093 grad: 0.0696 (0.0745) loss: 0.8303 (0.8311) time: 0.1318 data: 0.0561 max mem: 9390 +Train: [37] [1000/6250] eta: 0:12:28 lr: 0.000093 grad: 0.0658 (0.0743) loss: 0.8354 (0.8311) time: 0.1098 data: 0.0307 max mem: 9390 +Train: [37] [1100/6250] eta: 0:12:17 lr: 0.000093 grad: 0.0666 (0.0740) loss: 0.8268 (0.8310) time: 0.2013 data: 0.1240 max mem: 9390 +Train: [37] [1200/6250] eta: 0:12:06 lr: 0.000093 grad: 0.0699 (0.0738) loss: 0.8314 (0.8309) time: 0.1524 data: 0.0705 max mem: 9390 +Train: [37] [1300/6250] eta: 0:11:50 lr: 0.000093 grad: 0.0709 (0.0739) loss: 0.8290 (0.8308) time: 0.1527 data: 0.0726 max mem: 9390 +Train: [37] [1400/6250] eta: 0:11:40 lr: 0.000093 grad: 0.0732 (0.0740) loss: 0.8297 (0.8307) time: 0.1424 data: 0.0629 max mem: 9390 +Train: [37] [1500/6250] eta: 0:11:26 lr: 0.000093 grad: 0.0764 (0.0739) loss: 0.8291 (0.8306) time: 0.1606 data: 0.0844 max mem: 9390 +Train: [37] [1600/6250] eta: 0:11:07 lr: 0.000093 grad: 0.0724 (0.0739) loss: 0.8331 (0.8306) time: 0.1249 data: 0.0403 max mem: 9390 +Train: [37] [1700/6250] eta: 0:10:48 lr: 0.000093 grad: 0.0755 (0.0739) loss: 0.8230 (0.8305) time: 0.1262 data: 0.0436 max mem: 9390 +Train: [37] [1800/6250] eta: 0:10:29 lr: 0.000093 grad: 0.0704 (0.0740) loss: 0.8267 (0.8305) time: 0.1168 data: 0.0357 max mem: 9390 +Train: [37] [1900/6250] eta: 0:10:10 lr: 0.000093 grad: 0.0757 (0.0740) loss: 0.8289 (0.8304) time: 0.1210 data: 0.0398 max mem: 9390 +Train: [37] [2000/6250] eta: 0:09:52 lr: 0.000093 grad: 0.0740 (0.0740) loss: 0.8324 (0.8304) time: 0.1311 data: 0.0491 max mem: 9390 +Train: [37] [2100/6250] eta: 0:09:33 lr: 0.000093 grad: 0.0721 (0.0739) loss: 0.8306 (0.8304) time: 0.1227 data: 0.0412 max mem: 9390 +Train: [37] [2200/6250] eta: 0:09:18 lr: 0.000093 grad: 0.0749 (0.0740) loss: 0.8288 (0.8303) time: 0.1530 data: 0.0750 max mem: 9390 +Train: [37] [2300/6250] eta: 0:09:03 lr: 0.000092 grad: 0.0684 (0.0740) loss: 0.8257 (0.8303) time: 0.1357 data: 0.0638 max mem: 9390 +Train: [37] [2400/6250] eta: 0:08:49 lr: 0.000092 grad: 0.0740 (0.0739) loss: 0.8263 (0.8302) time: 0.1233 data: 0.0429 max mem: 9390 +Train: [37] [2500/6250] eta: 0:08:34 lr: 0.000092 grad: 0.0690 (0.0739) loss: 0.8292 (0.8301) time: 0.1304 data: 0.0395 max mem: 9390 +Train: [37] [2600/6250] eta: 0:08:19 lr: 0.000092 grad: 0.0748 (0.0740) loss: 0.8286 (0.8300) time: 0.1180 data: 0.0355 max mem: 9390 +Train: [37] [2700/6250] eta: 0:08:06 lr: 0.000092 grad: 0.0711 (0.0740) loss: 0.8272 (0.8299) time: 0.1584 data: 0.0775 max mem: 9390 +Train: [37] [2800/6250] eta: 0:07:53 lr: 0.000092 grad: 0.0757 (0.0741) loss: 0.8328 (0.8298) time: 0.1458 data: 0.0573 max mem: 9390 +Train: [37] [2900/6250] eta: 0:07:40 lr: 0.000092 grad: 0.0734 (0.0741) loss: 0.8232 (0.8297) time: 0.1400 data: 0.0564 max mem: 9390 +Train: [37] [3000/6250] eta: 0:07:27 lr: 0.000092 grad: 0.0706 (0.0742) loss: 0.8261 (0.8295) time: 0.1591 data: 0.0872 max mem: 9390 +Train: [37] [3100/6250] eta: 0:07:14 lr: 0.000092 grad: 0.0766 (0.0743) loss: 0.8279 (0.8294) time: 0.1503 data: 0.0660 max mem: 9390 +Train: [37] [3200/6250] eta: 0:07:01 lr: 0.000092 grad: 0.0729 (0.0744) loss: 0.8220 (0.8292) time: 0.1267 data: 0.0527 max mem: 9390 +Train: [37] [3300/6250] eta: 0:06:48 lr: 0.000092 grad: 0.0773 (0.0746) loss: 0.8276 (0.8290) time: 0.1701 data: 0.0892 max mem: 9390 +Train: [37] [3400/6250] eta: 0:06:35 lr: 0.000092 grad: 0.0716 (0.0747) loss: 0.8261 (0.8288) time: 0.1652 data: 0.0832 max mem: 9390 +Train: [37] [3500/6250] eta: 0:06:23 lr: 0.000092 grad: 0.0791 (0.0748) loss: 0.8224 (0.8287) time: 0.2090 data: 0.0967 max mem: 9390 +Train: [37] [3600/6250] eta: 0:06:09 lr: 0.000092 grad: 0.0807 (0.0750) loss: 0.8223 (0.8285) time: 0.1286 data: 0.0464 max mem: 9390 +Train: [37] [3700/6250] eta: 0:05:55 lr: 0.000092 grad: 0.0823 (0.0752) loss: 0.8235 (0.8284) time: 0.1324 data: 0.0521 max mem: 9390 +Train: [37] [3800/6250] eta: 0:05:42 lr: 0.000092 grad: 0.0764 (0.0753) loss: 0.8181 (0.8282) time: 0.1353 data: 0.0545 max mem: 9390 +Train: [37] [3900/6250] eta: 0:05:29 lr: 0.000092 grad: 0.0747 (0.0754) loss: 0.8185 (0.8281) time: 0.1460 data: 0.0716 max mem: 9390 +Train: [37] [4000/6250] eta: 0:05:16 lr: 0.000092 grad: 0.0891 (0.0755) loss: 0.8214 (0.8279) time: 0.1732 data: 0.0908 max mem: 9390 +Train: [37] [4100/6250] eta: 0:05:02 lr: 0.000092 grad: 0.0745 (0.0757) loss: 0.8226 (0.8278) time: 0.1447 data: 0.0690 max mem: 9390 +Train: [37] [4200/6250] eta: 0:04:48 lr: 0.000092 grad: 0.0730 (0.0758) loss: 0.8228 (0.8276) time: 0.1448 data: 0.0621 max mem: 9390 +Train: [37] [4300/6250] eta: 0:04:33 lr: 0.000092 grad: 0.0793 (0.0759) loss: 0.8209 (0.8275) time: 0.1420 data: 0.0608 max mem: 9390 +Train: [37] [4400/6250] eta: 0:04:20 lr: 0.000092 grad: 0.0760 (0.0759) loss: 0.8193 (0.8274) time: 0.1671 data: 0.0930 max mem: 9390 +Train: [37] [4500/6250] eta: 0:04:06 lr: 0.000092 grad: 0.0799 (0.0760) loss: 0.8233 (0.8272) time: 0.1314 data: 0.0574 max mem: 9390 +Train: [37] [4600/6250] eta: 0:03:52 lr: 0.000092 grad: 0.0761 (0.0760) loss: 0.8175 (0.8271) time: 0.1583 data: 0.0788 max mem: 9390 +Train: [37] [4700/6250] eta: 0:03:39 lr: 0.000092 grad: 0.0791 (0.0761) loss: 0.8230 (0.8270) time: 0.2328 data: 0.1297 max mem: 9390 +Train: [37] [4800/6250] eta: 0:03:25 lr: 0.000092 grad: 0.0761 (0.0762) loss: 0.8204 (0.8269) time: 0.1182 data: 0.0391 max mem: 9390 +Train: [37] [4900/6250] eta: 0:03:11 lr: 0.000092 grad: 0.0785 (0.0762) loss: 0.8187 (0.8268) time: 0.1689 data: 0.0872 max mem: 9390 +Train: [37] [5000/6250] eta: 0:02:56 lr: 0.000092 grad: 0.0716 (0.0763) loss: 0.8230 (0.8267) time: 0.1128 data: 0.0365 max mem: 9390 +Train: [37] [5100/6250] eta: 0:02:42 lr: 0.000092 grad: 0.0739 (0.0763) loss: 0.8217 (0.8266) time: 0.1462 data: 0.0620 max mem: 9390 +Train: [37] [5200/6250] eta: 0:02:28 lr: 0.000092 grad: 0.0740 (0.0764) loss: 0.8256 (0.8265) time: 0.1552 data: 0.0819 max mem: 9390 +Train: [37] [5300/6250] eta: 0:02:14 lr: 0.000092 grad: 0.0766 (0.0764) loss: 0.8250 (0.8265) time: 0.1540 data: 0.0765 max mem: 9390 +Train: [37] [5400/6250] eta: 0:02:00 lr: 0.000092 grad: 0.0747 (0.0765) loss: 0.8237 (0.8264) time: 0.1860 data: 0.1111 max mem: 9390 +Train: [37] [5500/6250] eta: 0:01:46 lr: 0.000092 grad: 0.0752 (0.0765) loss: 0.8264 (0.8264) time: 0.1632 data: 0.0812 max mem: 9390 +Train: [37] [5600/6250] eta: 0:01:32 lr: 0.000092 grad: 0.0763 (0.0766) loss: 0.8276 (0.8263) time: 0.1583 data: 0.0720 max mem: 9390 +Train: [37] [5700/6250] eta: 0:01:18 lr: 0.000091 grad: 0.0816 (0.0766) loss: 0.8228 (0.8263) time: 0.1641 data: 0.0795 max mem: 9390 +Train: [37] [5800/6250] eta: 0:01:04 lr: 0.000091 grad: 0.0711 (0.0767) loss: 0.8187 (0.8263) time: 0.1403 data: 0.0616 max mem: 9390 +Train: [37] [5900/6250] eta: 0:00:49 lr: 0.000091 grad: 0.0718 (0.0767) loss: 0.8263 (0.8262) time: 0.1513 data: 0.0712 max mem: 9390 +Train: [37] [6000/6250] eta: 0:00:35 lr: 0.000091 grad: 0.0770 (0.0767) loss: 0.8248 (0.8263) time: 0.1484 data: 0.0732 max mem: 9390 +Train: [37] [6100/6250] eta: 0:00:21 lr: 0.000091 grad: 0.0768 (0.0767) loss: 0.8263 (0.8263) time: 0.1521 data: 0.0753 max mem: 9390 +Train: [37] [6200/6250] eta: 0:00:07 lr: 0.000091 grad: 0.0760 (0.0768) loss: 0.8228 (0.8262) time: 0.1156 data: 0.0408 max mem: 9390 +Train: [37] [6249/6250] eta: 0:00:00 lr: 0.000091 grad: 0.0740 (0.0767) loss: 0.8209 (0.8262) time: 0.1353 data: 0.0524 max mem: 9390 +Train: [37] Total time: 0:14:55 (0.1432 s / it) +Averaged stats: lr: 0.000091 grad: 0.0740 (0.0767) loss: 0.8209 (0.8262) +Eval (hcp-train-subset): [37] [ 0/62] eta: 0:04:24 loss: 0.8550 (0.8550) time: 4.2738 data: 4.2445 max mem: 9390 +Eval (hcp-train-subset): [37] [61/62] eta: 0:00:00 loss: 0.8419 (0.8419) time: 0.1183 data: 0.0919 max mem: 9390 +Eval (hcp-train-subset): [37] Total time: 0:00:12 (0.1991 s / it) +Averaged stats (hcp-train-subset): loss: 0.8419 (0.8419) +Eval (hcp-val): [37] [ 0/62] eta: 0:05:23 loss: 0.8375 (0.8375) time: 5.2247 data: 5.1929 max mem: 9390 +Eval (hcp-val): [37] [61/62] eta: 0:00:00 loss: 0.8354 (0.8383) time: 0.1007 data: 0.0741 max mem: 9390 +Eval (hcp-val): [37] Total time: 0:00:13 (0.2179 s / it) +Averaged stats (hcp-val): loss: 0.8354 (0.8383) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +Train: [38] [ 0/6250] eta: 9:44:40 lr: 0.000091 grad: 0.0730 (0.0730) loss: 0.8568 (0.8568) time: 5.6128 data: 5.5139 max mem: 9390 +Train: [38] [ 100/6250] eta: 0:20:03 lr: 0.000091 grad: 0.0777 (0.0827) loss: 0.8329 (0.8376) time: 0.1535 data: 0.0642 max mem: 9390 +Train: [38] [ 200/6250] eta: 0:18:00 lr: 0.000091 grad: 0.0773 (0.0817) loss: 0.8331 (0.8336) time: 0.1629 data: 0.0769 max mem: 9390 +Train: [38] [ 300/6250] eta: 0:16:45 lr: 0.000091 grad: 0.0721 (0.0805) loss: 0.8310 (0.8310) time: 0.1644 data: 0.0825 max mem: 9390 +Train: [38] [ 400/6250] eta: 0:15:52 lr: 0.000091 grad: 0.0728 (0.0795) loss: 0.8281 (0.8300) time: 0.1256 data: 0.0424 max mem: 9390 +Train: [38] [ 500/6250] eta: 0:15:04 lr: 0.000091 grad: 0.0677 (0.0784) loss: 0.8247 (0.8297) time: 0.1344 data: 0.0593 max mem: 9390 +Train: [38] [ 600/6250] eta: 0:14:22 lr: 0.000091 grad: 0.0716 (0.0777) loss: 0.8229 (0.8297) time: 0.1234 data: 0.0388 max mem: 9390 +Train: [38] [ 700/6250] eta: 0:13:48 lr: 0.000091 grad: 0.0721 (0.0773) loss: 0.8268 (0.8299) time: 0.1270 data: 0.0465 max mem: 9390 +Train: [38] [ 800/6250] eta: 0:13:21 lr: 0.000091 grad: 0.0700 (0.0769) loss: 0.8273 (0.8295) time: 0.1367 data: 0.0517 max mem: 9390 +Train: [38] [ 900/6250] eta: 0:12:55 lr: 0.000091 grad: 0.0730 (0.0765) loss: 0.8287 (0.8294) time: 0.1445 data: 0.0624 max mem: 9390 +Train: [38] [1000/6250] eta: 0:12:31 lr: 0.000091 grad: 0.0731 (0.0764) loss: 0.8277 (0.8294) time: 0.1241 data: 0.0452 max mem: 9390 +Train: [38] [1100/6250] eta: 0:12:18 lr: 0.000091 grad: 0.0705 (0.0762) loss: 0.8256 (0.8291) time: 0.1632 data: 0.0668 max mem: 9390 +Train: [38] [1200/6250] eta: 0:12:08 lr: 0.000091 grad: 0.0777 (0.0766) loss: 0.8211 (0.8289) time: 0.2082 data: 0.1362 max mem: 9390 +Train: [38] [1300/6250] eta: 0:11:56 lr: 0.000091 grad: 0.0723 (0.0767) loss: 0.8224 (0.8284) time: 0.1389 data: 0.0614 max mem: 9390 +Train: [38] [1400/6250] eta: 0:11:39 lr: 0.000091 grad: 0.0815 (0.0769) loss: 0.8214 (0.8281) time: 0.1350 data: 0.0513 max mem: 9390 +Train: [38] [1500/6250] eta: 0:11:29 lr: 0.000091 grad: 0.0739 (0.0770) loss: 0.8179 (0.8278) time: 0.1485 data: 0.0637 max mem: 9390 +Train: [38] [1600/6250] eta: 0:11:14 lr: 0.000091 grad: 0.0770 (0.0772) loss: 0.8209 (0.8276) time: 0.1352 data: 0.0564 max mem: 9390 +Train: [38] [1700/6250] eta: 0:10:55 lr: 0.000091 grad: 0.0717 (0.0772) loss: 0.8257 (0.8274) time: 0.1389 data: 0.0613 max mem: 9390 +Train: [38] [1800/6250] eta: 0:10:36 lr: 0.000091 grad: 0.0792 (0.0773) loss: 0.8301 (0.8272) time: 0.1213 data: 0.0405 max mem: 9390 +Train: [38] [1900/6250] eta: 0:10:18 lr: 0.000091 grad: 0.0800 (0.0773) loss: 0.8237 (0.8270) time: 0.1075 data: 0.0221 max mem: 9390 +Train: [38] [2000/6250] eta: 0:09:59 lr: 0.000091 grad: 0.0766 (0.0773) loss: 0.8250 (0.8269) time: 0.1254 data: 0.0464 max mem: 9390 +Train: [38] [2100/6250] eta: 0:09:41 lr: 0.000091 grad: 0.0799 (0.0773) loss: 0.8220 (0.8268) time: 0.1310 data: 0.0516 max mem: 9390 +Train: [38] [2200/6250] eta: 0:09:22 lr: 0.000091 grad: 0.0745 (0.0775) loss: 0.8264 (0.8267) time: 0.1067 data: 0.0175 max mem: 9390 +Train: [38] [2300/6250] eta: 0:09:05 lr: 0.000091 grad: 0.0775 (0.0776) loss: 0.8216 (0.8264) time: 0.1177 data: 0.0375 max mem: 9390 +Train: [38] [2400/6250] eta: 0:08:48 lr: 0.000091 grad: 0.0784 (0.0778) loss: 0.8250 (0.8262) time: 0.1262 data: 0.0542 max mem: 9390 +Train: [38] [2500/6250] eta: 0:08:34 lr: 0.000091 grad: 0.0795 (0.0780) loss: 0.8219 (0.8261) time: 0.1293 data: 0.0534 max mem: 9390 +Train: [38] [2600/6250] eta: 0:08:20 lr: 0.000091 grad: 0.0747 (0.0781) loss: 0.8262 (0.8260) time: 0.1316 data: 0.0534 max mem: 9390 +Train: [38] [2700/6250] eta: 0:08:05 lr: 0.000091 grad: 0.0819 (0.0782) loss: 0.8159 (0.8259) time: 0.1361 data: 0.0610 max mem: 9390 +Train: [38] [2800/6250] eta: 0:07:49 lr: 0.000091 grad: 0.0757 (0.0784) loss: 0.8303 (0.8258) time: 0.1329 data: 0.0536 max mem: 9390 +Train: [38] [2900/6250] eta: 0:07:35 lr: 0.000090 grad: 0.0803 (0.0784) loss: 0.8226 (0.8257) time: 0.1414 data: 0.0625 max mem: 9390 +Train: [38] [3000/6250] eta: 0:07:23 lr: 0.000090 grad: 0.0824 (0.0786) loss: 0.8275 (0.8256) time: 0.1560 data: 0.0694 max mem: 9390 +Train: [38] [3100/6250] eta: 0:07:10 lr: 0.000090 grad: 0.0742 (0.0788) loss: 0.8251 (0.8255) time: 0.1318 data: 0.0546 max mem: 9390 +Train: [38] [3200/6250] eta: 0:06:58 lr: 0.000090 grad: 0.0802 (0.0788) loss: 0.8222 (0.8254) time: 0.1392 data: 0.0634 max mem: 9390 +Train: [38] [3300/6250] eta: 0:06:45 lr: 0.000090 grad: 0.0840 (0.0789) loss: 0.8211 (0.8254) time: 0.1308 data: 0.0541 max mem: 9390 +Train: [38] [3400/6250] eta: 0:06:32 lr: 0.000090 grad: 0.0777 (0.0790) loss: 0.8252 (0.8253) time: 0.1474 data: 0.0667 max mem: 9390 +Train: [38] [3500/6250] eta: 0:06:18 lr: 0.000090 grad: 0.0765 (0.0790) loss: 0.8265 (0.8253) time: 0.1533 data: 0.0785 max mem: 9390 +Train: [38] [3600/6250] eta: 0:06:04 lr: 0.000090 grad: 0.0775 (0.0791) loss: 0.8190 (0.8252) time: 0.1458 data: 0.0716 max mem: 9390 +Train: [38] [3700/6250] eta: 0:05:52 lr: 0.000090 grad: 0.0810 (0.0793) loss: 0.8179 (0.8251) time: 0.1581 data: 0.0677 max mem: 9390 +Train: [38] [3800/6250] eta: 0:05:39 lr: 0.000090 grad: 0.0850 (0.0795) loss: 0.8165 (0.8249) time: 0.1304 data: 0.0521 max mem: 9390 +Train: [38] [3900/6250] eta: 0:05:25 lr: 0.000090 grad: 0.0789 (0.0796) loss: 0.8217 (0.8248) time: 0.1465 data: 0.0670 max mem: 9390 +Train: [38] [4000/6250] eta: 0:05:11 lr: 0.000090 grad: 0.0775 (0.0796) loss: 0.8228 (0.8247) time: 0.1348 data: 0.0510 max mem: 9390 +Train: [38] [4100/6250] eta: 0:04:57 lr: 0.000090 grad: 0.0777 (0.0797) loss: 0.8203 (0.8246) time: 0.1296 data: 0.0492 max mem: 9390 +Train: [38] [4200/6250] eta: 0:04:43 lr: 0.000090 grad: 0.0810 (0.0798) loss: 0.8167 (0.8244) time: 0.1116 data: 0.0252 max mem: 9390 +Train: [38] [4300/6250] eta: 0:04:30 lr: 0.000090 grad: 0.0830 (0.0800) loss: 0.8181 (0.8243) time: 0.1396 data: 0.0623 max mem: 9390 +Train: [38] [4400/6250] eta: 0:04:16 lr: 0.000090 grad: 0.0790 (0.0800) loss: 0.8225 (0.8241) time: 0.1232 data: 0.0416 max mem: 9390 +Train: [38] [4500/6250] eta: 0:04:03 lr: 0.000090 grad: 0.0791 (0.0800) loss: 0.8200 (0.8241) time: 0.1553 data: 0.0609 max mem: 9390 +Train: [38] [4600/6250] eta: 0:03:49 lr: 0.000090 grad: 0.0766 (0.0801) loss: 0.8247 (0.8240) time: 0.1474 data: 0.0643 max mem: 9390 +Train: [38] [4700/6250] eta: 0:03:36 lr: 0.000090 grad: 0.0850 (0.0801) loss: 0.8200 (0.8240) time: 0.1188 data: 0.0281 max mem: 9390 +Train: [38] [4800/6250] eta: 0:03:22 lr: 0.000090 grad: 0.0773 (0.0802) loss: 0.8219 (0.8239) time: 0.1604 data: 0.0825 max mem: 9390 +Train: [38] [4900/6250] eta: 0:03:08 lr: 0.000090 grad: 0.0812 (0.0801) loss: 0.8217 (0.8239) time: 0.1482 data: 0.0613 max mem: 9390 +Train: [38] [5000/6250] eta: 0:02:54 lr: 0.000090 grad: 0.0760 (0.0802) loss: 0.8247 (0.8239) time: 0.1275 data: 0.0449 max mem: 9390 +Train: [38] [5100/6250] eta: 0:02:41 lr: 0.000090 grad: 0.0763 (0.0802) loss: 0.8179 (0.8238) time: 0.1421 data: 0.0604 max mem: 9390 +Train: [38] [5200/6250] eta: 0:02:27 lr: 0.000090 grad: 0.0823 (0.0803) loss: 0.8230 (0.8238) time: 0.1501 data: 0.0668 max mem: 9390 +Train: [38] [5300/6250] eta: 0:02:13 lr: 0.000090 grad: 0.0764 (0.0803) loss: 0.8246 (0.8238) time: 0.1252 data: 0.0442 max mem: 9390 +Train: [38] [5400/6250] eta: 0:01:59 lr: 0.000090 grad: 0.0838 (0.0803) loss: 0.8242 (0.8237) time: 0.1508 data: 0.0506 max mem: 9390 +Train: [38] [5500/6250] eta: 0:01:45 lr: 0.000090 grad: 0.0833 (0.0804) loss: 0.8266 (0.8237) time: 0.1371 data: 0.0592 max mem: 9390 +Train: [38] [5600/6250] eta: 0:01:31 lr: 0.000090 grad: 0.0825 (0.0804) loss: 0.8175 (0.8237) time: 0.1317 data: 0.0527 max mem: 9390 +Train: [38] [5700/6250] eta: 0:01:17 lr: 0.000090 grad: 0.0873 (0.0805) loss: 0.8271 (0.8236) time: 0.1498 data: 0.0713 max mem: 9390 +Train: [38] [5800/6250] eta: 0:01:03 lr: 0.000090 grad: 0.0835 (0.0805) loss: 0.8225 (0.8236) time: 0.1285 data: 0.0489 max mem: 9390 +Train: [38] [5900/6250] eta: 0:00:48 lr: 0.000090 grad: 0.0764 (0.0805) loss: 0.8321 (0.8236) time: 0.1365 data: 0.0602 max mem: 9390 +Train: [38] [6000/6250] eta: 0:00:34 lr: 0.000090 grad: 0.0771 (0.0805) loss: 0.8255 (0.8236) time: 0.1387 data: 0.0577 max mem: 9390 +Train: [38] [6100/6250] eta: 0:00:21 lr: 0.000090 grad: 0.0743 (0.0805) loss: 0.8317 (0.8236) time: 0.1605 data: 0.0853 max mem: 9390 +Train: [38] [6200/6250] eta: 0:00:06 lr: 0.000089 grad: 0.0747 (0.0805) loss: 0.8303 (0.8237) time: 0.1355 data: 0.0559 max mem: 9390 +Train: [38] [6249/6250] eta: 0:00:00 lr: 0.000089 grad: 0.0837 (0.0805) loss: 0.8265 (0.8237) time: 0.1320 data: 0.0536 max mem: 9390 +Train: [38] Total time: 0:14:41 (0.1410 s / it) +Averaged stats: lr: 0.000089 grad: 0.0837 (0.0805) loss: 0.8265 (0.8237) +Eval (hcp-train-subset): [38] [ 0/62] eta: 0:03:29 loss: 0.8545 (0.8545) time: 3.3821 data: 3.3138 max mem: 9390 +Eval (hcp-train-subset): [38] [61/62] eta: 0:00:00 loss: 0.8395 (0.8401) time: 0.1317 data: 0.1070 max mem: 9390 +Eval (hcp-train-subset): [38] Total time: 0:00:13 (0.2209 s / it) +Averaged stats (hcp-train-subset): loss: 0.8395 (0.8401) +Eval (hcp-val): [38] [ 0/62] eta: 0:05:22 loss: 0.8329 (0.8329) time: 5.2078 data: 5.1784 max mem: 9390 +Eval (hcp-val): [38] [61/62] eta: 0:00:00 loss: 0.8370 (0.8379) time: 0.1212 data: 0.0965 max mem: 9390 +Eval (hcp-val): [38] Total time: 0:00:13 (0.2115 s / it) +Averaged stats (hcp-val): loss: 0.8370 (0.8379) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +Train: [39] [ 0/6250] eta: 10:20:32 lr: 0.000089 grad: 0.0760 (0.0760) loss: 0.8392 (0.8392) time: 5.9571 data: 5.8584 max mem: 9390 +Train: [39] [ 100/6250] eta: 0:20:44 lr: 0.000089 grad: 0.0780 (0.0790) loss: 0.8366 (0.8410) time: 0.1433 data: 0.0548 max mem: 9390 +Train: [39] [ 200/6250] eta: 0:17:35 lr: 0.000089 grad: 0.0676 (0.0805) loss: 0.8303 (0.8351) time: 0.1277 data: 0.0451 max mem: 9390 +Train: [39] [ 300/6250] eta: 0:16:14 lr: 0.000089 grad: 0.0751 (0.0791) loss: 0.8246 (0.8334) time: 0.1536 data: 0.0649 max mem: 9390 +Train: [39] [ 400/6250] eta: 0:15:28 lr: 0.000089 grad: 0.0645 (0.0775) loss: 0.8347 (0.8324) time: 0.1242 data: 0.0414 max mem: 9390 +Train: [39] [ 500/6250] eta: 0:14:44 lr: 0.000089 grad: 0.0708 (0.0763) loss: 0.8289 (0.8322) time: 0.1511 data: 0.0688 max mem: 9390 +Train: [39] [ 600/6250] eta: 0:14:01 lr: 0.000089 grad: 0.0731 (0.0757) loss: 0.8342 (0.8322) time: 0.1180 data: 0.0395 max mem: 9390 +Train: [39] [ 700/6250] eta: 0:13:31 lr: 0.000089 grad: 0.0664 (0.0751) loss: 0.8342 (0.8323) time: 0.1208 data: 0.0353 max mem: 9390 +Train: [39] [ 800/6250] eta: 0:13:08 lr: 0.000089 grad: 0.0702 (0.0747) loss: 0.8350 (0.8323) time: 0.1193 data: 0.0357 max mem: 9390 +Train: [39] [ 900/6250] eta: 0:12:53 lr: 0.000089 grad: 0.0737 (0.0746) loss: 0.8281 (0.8320) time: 0.1592 data: 0.0788 max mem: 9390 +Train: [39] [1000/6250] eta: 0:12:29 lr: 0.000089 grad: 0.0754 (0.0747) loss: 0.8288 (0.8315) time: 0.1299 data: 0.0532 max mem: 9390 +Train: [39] [1100/6250] eta: 0:12:09 lr: 0.000089 grad: 0.0732 (0.0749) loss: 0.8254 (0.8312) time: 0.1341 data: 0.0532 max mem: 9390 +Train: [39] [1200/6250] eta: 0:11:50 lr: 0.000089 grad: 0.0696 (0.0748) loss: 0.8245 (0.8306) time: 0.1165 data: 0.0303 max mem: 9390 +Train: [39] [1300/6250] eta: 0:11:41 lr: 0.000089 grad: 0.0781 (0.0750) loss: 0.8188 (0.8301) time: 0.1717 data: 0.0955 max mem: 9390 +Train: [39] [1400/6250] eta: 0:11:25 lr: 0.000089 grad: 0.0784 (0.0754) loss: 0.8264 (0.8296) time: 0.1310 data: 0.0550 max mem: 9390 +Train: [39] [1500/6250] eta: 0:11:15 lr: 0.000089 grad: 0.0724 (0.0757) loss: 0.8208 (0.8291) time: 0.1487 data: 0.0672 max mem: 9390 +Train: [39] [1600/6250] eta: 0:11:03 lr: 0.000089 grad: 0.0735 (0.0757) loss: 0.8255 (0.8287) time: 0.1508 data: 0.0733 max mem: 9390 +Train: [39] [1700/6250] eta: 0:10:51 lr: 0.000089 grad: 0.0749 (0.0760) loss: 0.8262 (0.8283) time: 0.1602 data: 0.0784 max mem: 9390 +Train: [39] [1800/6250] eta: 0:10:36 lr: 0.000089 grad: 0.0775 (0.0763) loss: 0.8185 (0.8280) time: 0.1406 data: 0.0565 max mem: 9390 +Train: [39] [1900/6250] eta: 0:10:20 lr: 0.000089 grad: 0.0777 (0.0766) loss: 0.8217 (0.8278) time: 0.1399 data: 0.0625 max mem: 9390 +Train: [39] [2000/6250] eta: 0:10:03 lr: 0.000089 grad: 0.0752 (0.0769) loss: 0.8243 (0.8276) time: 0.1312 data: 0.0521 max mem: 9390 +Train: [39] [2100/6250] eta: 0:09:45 lr: 0.000089 grad: 0.0763 (0.0770) loss: 0.8240 (0.8275) time: 0.1181 data: 0.0363 max mem: 9390 +Train: [39] [2200/6250] eta: 0:09:28 lr: 0.000089 grad: 0.0719 (0.0773) loss: 0.8152 (0.8273) time: 0.1218 data: 0.0464 max mem: 9390 +Train: [39] [2300/6250] eta: 0:09:11 lr: 0.000089 grad: 0.0777 (0.0774) loss: 0.8220 (0.8271) time: 0.1246 data: 0.0485 max mem: 9390 +Train: [39] [2400/6250] eta: 0:08:53 lr: 0.000089 grad: 0.0769 (0.0775) loss: 0.8237 (0.8270) time: 0.1108 data: 0.0372 max mem: 9390 +Train: [39] [2500/6250] eta: 0:08:36 lr: 0.000089 grad: 0.0721 (0.0777) loss: 0.8282 (0.8270) time: 0.1294 data: 0.0494 max mem: 9390 +Train: [39] [2600/6250] eta: 0:08:20 lr: 0.000089 grad: 0.0719 (0.0778) loss: 0.8278 (0.8270) time: 0.1004 data: 0.0240 max mem: 9390 +Train: [39] [2700/6250] eta: 0:08:04 lr: 0.000089 grad: 0.0771 (0.0778) loss: 0.8232 (0.8269) time: 0.1110 data: 0.0282 max mem: 9390 +Train: [39] [2800/6250] eta: 0:07:50 lr: 0.000089 grad: 0.0764 (0.0780) loss: 0.8220 (0.8268) time: 0.1244 data: 0.0417 max mem: 9390 +Train: [39] [2900/6250] eta: 0:07:36 lr: 0.000089 grad: 0.0742 (0.0780) loss: 0.8238 (0.8267) time: 0.1373 data: 0.0613 max mem: 9390 +Train: [39] [3000/6250] eta: 0:07:21 lr: 0.000089 grad: 0.0736 (0.0780) loss: 0.8240 (0.8266) time: 0.1385 data: 0.0582 max mem: 9390 +Train: [39] [3100/6250] eta: 0:07:07 lr: 0.000089 grad: 0.0760 (0.0781) loss: 0.8252 (0.8266) time: 0.1394 data: 0.0565 max mem: 9390 +Train: [39] [3200/6250] eta: 0:06:55 lr: 0.000089 grad: 0.0766 (0.0781) loss: 0.8279 (0.8265) time: 0.1564 data: 0.0724 max mem: 9390 +Train: [39] [3300/6250] eta: 0:06:43 lr: 0.000088 grad: 0.0745 (0.0782) loss: 0.8180 (0.8264) time: 0.1466 data: 0.0635 max mem: 9390 +Train: [39] [3400/6250] eta: 0:06:31 lr: 0.000088 grad: 0.0747 (0.0782) loss: 0.8279 (0.8263) time: 0.1513 data: 0.0699 max mem: 9390 +Train: [39] [3500/6250] eta: 0:06:18 lr: 0.000088 grad: 0.0829 (0.0783) loss: 0.8195 (0.8262) time: 0.1497 data: 0.0617 max mem: 9390 +Train: [39] [3600/6250] eta: 0:06:05 lr: 0.000088 grad: 0.0779 (0.0784) loss: 0.8137 (0.8261) time: 0.1514 data: 0.0663 max mem: 9390 +Train: [39] [3700/6250] eta: 0:05:53 lr: 0.000088 grad: 0.0807 (0.0785) loss: 0.8273 (0.8260) time: 0.1468 data: 0.0588 max mem: 9390 +Train: [39] [3800/6250] eta: 0:05:40 lr: 0.000088 grad: 0.0792 (0.0785) loss: 0.8192 (0.8260) time: 0.1540 data: 0.0791 max mem: 9390 +Train: [39] [3900/6250] eta: 0:05:26 lr: 0.000088 grad: 0.0718 (0.0785) loss: 0.8308 (0.8260) time: 0.1133 data: 0.0362 max mem: 9390 +Train: [39] [4000/6250] eta: 0:05:12 lr: 0.000088 grad: 0.0768 (0.0785) loss: 0.8239 (0.8260) time: 0.1338 data: 0.0529 max mem: 9390 +Train: [39] [4100/6250] eta: 0:04:59 lr: 0.000088 grad: 0.0738 (0.0785) loss: 0.8280 (0.8260) time: 0.1454 data: 0.0684 max mem: 9390 +Train: [39] [4200/6250] eta: 0:04:45 lr: 0.000088 grad: 0.0737 (0.0785) loss: 0.8291 (0.8260) time: 0.1467 data: 0.0720 max mem: 9390 +Train: [39] [4300/6250] eta: 0:04:31 lr: 0.000088 grad: 0.0764 (0.0786) loss: 0.8246 (0.8260) time: 0.1589 data: 0.0613 max mem: 9390 +Train: [39] [4400/6250] eta: 0:04:18 lr: 0.000088 grad: 0.0758 (0.0786) loss: 0.8243 (0.8260) time: 0.1540 data: 0.0735 max mem: 9390 +Train: [39] [4500/6250] eta: 0:04:04 lr: 0.000088 grad: 0.0779 (0.0786) loss: 0.8201 (0.8260) time: 0.1753 data: 0.0872 max mem: 9390 +Train: [39] [4600/6250] eta: 0:03:50 lr: 0.000088 grad: 0.0726 (0.0786) loss: 0.8280 (0.8260) time: 0.1391 data: 0.0613 max mem: 9390 +Train: [39] [4700/6250] eta: 0:03:36 lr: 0.000088 grad: 0.0811 (0.0786) loss: 0.8289 (0.8259) time: 0.1450 data: 0.0650 max mem: 9390 +Train: [39] [4800/6250] eta: 0:03:23 lr: 0.000088 grad: 0.0823 (0.0786) loss: 0.8213 (0.8259) time: 0.1242 data: 0.0429 max mem: 9390 +Train: [39] [4900/6250] eta: 0:03:09 lr: 0.000088 grad: 0.0842 (0.0787) loss: 0.8160 (0.8258) time: 0.1744 data: 0.0977 max mem: 9390 +Train: [39] [5000/6250] eta: 0:02:55 lr: 0.000088 grad: 0.0761 (0.0787) loss: 0.8207 (0.8256) time: 0.1481 data: 0.0522 max mem: 9390 +Train: [39] [5100/6250] eta: 0:02:41 lr: 0.000088 grad: 0.0796 (0.0788) loss: 0.8218 (0.8255) time: 0.1388 data: 0.0625 max mem: 9390 +Train: [39] [5200/6250] eta: 0:02:27 lr: 0.000088 grad: 0.0811 (0.0789) loss: 0.8207 (0.8254) time: 0.1936 data: 0.1027 max mem: 9390 +Train: [39] [5300/6250] eta: 0:02:14 lr: 0.000088 grad: 0.0762 (0.0789) loss: 0.8228 (0.8253) time: 0.1880 data: 0.1024 max mem: 9390 +Train: [39] [5400/6250] eta: 0:01:59 lr: 0.000088 grad: 0.0739 (0.0790) loss: 0.8269 (0.8253) time: 0.1449 data: 0.0705 max mem: 9390 +Train: [39] [5500/6250] eta: 0:01:46 lr: 0.000088 grad: 0.0749 (0.0790) loss: 0.8281 (0.8253) time: 0.1357 data: 0.0525 max mem: 9390 +Train: [39] [5600/6250] eta: 0:01:32 lr: 0.000088 grad: 0.0769 (0.0790) loss: 0.8245 (0.8253) time: 0.1886 data: 0.0706 max mem: 9390 +Train: [39] [5700/6250] eta: 0:01:18 lr: 0.000088 grad: 0.0807 (0.0790) loss: 0.8198 (0.8252) time: 0.1406 data: 0.0474 max mem: 9390 +Train: [39] [5800/6250] eta: 0:01:03 lr: 0.000088 grad: 0.0792 (0.0792) loss: 0.8215 (0.8251) time: 0.1405 data: 0.0659 max mem: 9390 +Train: [39] [5900/6250] eta: 0:00:49 lr: 0.000088 grad: 0.0807 (0.0793) loss: 0.8182 (0.8250) time: 0.1314 data: 0.0557 max mem: 9390 +Train: [39] [6000/6250] eta: 0:00:35 lr: 0.000088 grad: 0.0801 (0.0794) loss: 0.8262 (0.8250) time: 0.1202 data: 0.0298 max mem: 9390 +Train: [39] [6100/6250] eta: 0:00:21 lr: 0.000088 grad: 0.0819 (0.0795) loss: 0.8220 (0.8250) time: 0.1789 data: 0.0716 max mem: 9390 +Train: [39] [6200/6250] eta: 0:00:07 lr: 0.000088 grad: 0.0820 (0.0795) loss: 0.8206 (0.8249) time: 0.1589 data: 0.0761 max mem: 9390 +Train: [39] [6249/6250] eta: 0:00:00 lr: 0.000088 grad: 0.0800 (0.0796) loss: 0.8214 (0.8249) time: 0.1605 data: 0.0776 max mem: 9390 +Train: [39] Total time: 0:14:53 (0.1430 s / it) +Averaged stats: lr: 0.000088 grad: 0.0800 (0.0796) loss: 0.8214 (0.8249) +Eval (hcp-train-subset): [39] [ 0/62] eta: 0:04:13 loss: 0.8504 (0.8504) time: 4.0926 data: 4.0535 max mem: 9390 +Eval (hcp-train-subset): [39] [61/62] eta: 0:00:00 loss: 0.8383 (0.8383) time: 0.1216 data: 0.0951 max mem: 9390 +Eval (hcp-train-subset): [39] Total time: 0:00:12 (0.2026 s / it) +Averaged stats (hcp-train-subset): loss: 0.8383 (0.8383) +Making plots (hcp-train-subset): example=57 +Eval (hcp-val): [39] [ 0/62] eta: 0:04:42 loss: 0.8388 (0.8388) time: 4.5601 data: 4.5295 max mem: 9390 +Eval (hcp-val): [39] [61/62] eta: 0:00:00 loss: 0.8368 (0.8375) time: 0.1259 data: 0.0996 max mem: 9390 +Eval (hcp-val): [39] Total time: 0:00:12 (0.1979 s / it) +Averaged stats (hcp-val): loss: 0.8368 (0.8375) +Making plots (hcp-val): example=51 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +Train: [40] [ 0/6250] eta: 10:57:28 lr: 0.000088 grad: 0.0783 (0.0783) loss: 0.8445 (0.8445) time: 6.3118 data: 6.2043 max mem: 9390 +Train: [40] [ 100/6250] eta: 0:20:24 lr: 0.000088 grad: 0.0769 (0.0823) loss: 0.8338 (0.8366) time: 0.1465 data: 0.0628 max mem: 9390 +Train: [40] [ 200/6250] eta: 0:17:29 lr: 0.000088 grad: 0.0746 (0.0821) loss: 0.8356 (0.8340) time: 0.1231 data: 0.0359 max mem: 9390 +Train: [40] [ 300/6250] eta: 0:16:28 lr: 0.000088 grad: 0.0720 (0.0821) loss: 0.8322 (0.8331) time: 0.1646 data: 0.0866 max mem: 9390 +Train: [40] [ 400/6250] eta: 0:15:29 lr: 0.000087 grad: 0.0775 (0.0813) loss: 0.8258 (0.8318) time: 0.1229 data: 0.0443 max mem: 9390 +Train: [40] [ 500/6250] eta: 0:14:43 lr: 0.000087 grad: 0.0719 (0.0806) loss: 0.8272 (0.8305) time: 0.1417 data: 0.0543 max mem: 9390 +Train: [40] [ 600/6250] eta: 0:14:08 lr: 0.000087 grad: 0.0700 (0.0801) loss: 0.8335 (0.8299) time: 0.1144 data: 0.0303 max mem: 9390 +Train: [40] [ 700/6250] eta: 0:13:36 lr: 0.000087 grad: 0.0784 (0.0799) loss: 0.8218 (0.8287) time: 0.1260 data: 0.0422 max mem: 9390 +Train: [40] [ 800/6250] eta: 0:13:10 lr: 0.000087 grad: 0.0709 (0.0795) loss: 0.8278 (0.8284) time: 0.1481 data: 0.0708 max mem: 9390 +Train: [40] [ 900/6250] eta: 0:12:48 lr: 0.000087 grad: 0.0697 (0.0789) loss: 0.8314 (0.8285) time: 0.1403 data: 0.0611 max mem: 9390 +Train: [40] [1000/6250] eta: 0:12:29 lr: 0.000087 grad: 0.0719 (0.0786) loss: 0.8309 (0.8284) time: 0.1438 data: 0.0669 max mem: 9390 +Train: [40] [1100/6250] eta: 0:12:09 lr: 0.000087 grad: 0.0756 (0.0787) loss: 0.8239 (0.8280) time: 0.1224 data: 0.0483 max mem: 9390 +Train: [40] [1200/6250] eta: 0:12:05 lr: 0.000087 grad: 0.0752 (0.0787) loss: 0.8240 (0.8275) time: 0.2543 data: 0.1687 max mem: 9390 +Train: [40] [1300/6250] eta: 0:11:45 lr: 0.000087 grad: 0.0767 (0.0787) loss: 0.8234 (0.8269) time: 0.1197 data: 0.0467 max mem: 9390 +Train: [40] [1400/6250] eta: 0:11:30 lr: 0.000087 grad: 0.0750 (0.0787) loss: 0.8228 (0.8266) time: 0.1402 data: 0.0680 max mem: 9390 +Train: [40] [1500/6250] eta: 0:11:19 lr: 0.000087 grad: 0.0771 (0.0787) loss: 0.8221 (0.8264) time: 0.1614 data: 0.0845 max mem: 9390 +Train: [40] [1600/6250] eta: 0:11:06 lr: 0.000087 grad: 0.0764 (0.0786) loss: 0.8226 (0.8262) time: 0.1413 data: 0.0680 max mem: 9390 +Train: [40] [1700/6250] eta: 0:10:54 lr: 0.000087 grad: 0.0761 (0.0786) loss: 0.8194 (0.8261) time: 0.1687 data: 0.0884 max mem: 9390 +Train: [40] [1800/6250] eta: 0:10:42 lr: 0.000087 grad: 0.0790 (0.0786) loss: 0.8246 (0.8258) time: 0.1511 data: 0.0815 max mem: 9390 +Train: [40] [1900/6250] eta: 0:10:26 lr: 0.000087 grad: 0.0781 (0.0787) loss: 0.8206 (0.8258) time: 0.1358 data: 0.0552 max mem: 9390 +Train: [40] [2000/6250] eta: 0:10:08 lr: 0.000087 grad: 0.0752 (0.0787) loss: 0.8191 (0.8256) time: 0.1296 data: 0.0481 max mem: 9390 +Train: [40] [2100/6250] eta: 0:09:50 lr: 0.000087 grad: 0.0751 (0.0787) loss: 0.8246 (0.8255) time: 0.1360 data: 0.0528 max mem: 9390 +Train: [40] [2200/6250] eta: 0:09:33 lr: 0.000087 grad: 0.0689 (0.0787) loss: 0.8280 (0.8256) time: 0.1494 data: 0.0739 max mem: 9390 +Train: [40] [2300/6250] eta: 0:09:14 lr: 0.000087 grad: 0.0774 (0.0787) loss: 0.8242 (0.8255) time: 0.1144 data: 0.0398 max mem: 9390 +Train: [40] [2400/6250] eta: 0:08:57 lr: 0.000087 grad: 0.0754 (0.0787) loss: 0.8232 (0.8255) time: 0.1282 data: 0.0513 max mem: 9390 +Train: [40] [2500/6250] eta: 0:08:39 lr: 0.000087 grad: 0.0778 (0.0787) loss: 0.8152 (0.8254) time: 0.1153 data: 0.0357 max mem: 9390 +Train: [40] [2600/6250] eta: 0:08:24 lr: 0.000087 grad: 0.0714 (0.0787) loss: 0.8300 (0.8254) time: 0.1379 data: 0.0587 max mem: 9390 +Train: [40] [2700/6250] eta: 0:08:08 lr: 0.000087 grad: 0.0759 (0.0787) loss: 0.8244 (0.8253) time: 0.1362 data: 0.0614 max mem: 9390 +Train: [40] [2800/6250] eta: 0:07:53 lr: 0.000087 grad: 0.0716 (0.0786) loss: 0.8259 (0.8253) time: 0.1223 data: 0.0447 max mem: 9390 +Train: [40] [2900/6250] eta: 0:07:38 lr: 0.000087 grad: 0.0775 (0.0786) loss: 0.8188 (0.8252) time: 0.1381 data: 0.0622 max mem: 9390 +Train: [40] [3000/6250] eta: 0:07:23 lr: 0.000087 grad: 0.0772 (0.0786) loss: 0.8220 (0.8252) time: 0.1245 data: 0.0524 max mem: 9390 +Train: [40] [3100/6250] eta: 0:07:07 lr: 0.000087 grad: 0.0791 (0.0787) loss: 0.8207 (0.8251) time: 0.1096 data: 0.0282 max mem: 9390 +Train: [40] [3200/6250] eta: 0:06:54 lr: 0.000087 grad: 0.0839 (0.0788) loss: 0.8246 (0.8250) time: 0.1222 data: 0.0432 max mem: 9390 +Train: [40] [3300/6250] eta: 0:06:41 lr: 0.000087 grad: 0.0822 (0.0790) loss: 0.8225 (0.8250) time: 0.1546 data: 0.0745 max mem: 9390 +Train: [40] [3400/6250] eta: 0:06:29 lr: 0.000087 grad: 0.0794 (0.0790) loss: 0.8207 (0.8249) time: 0.1485 data: 0.0694 max mem: 9390 +Train: [40] [3500/6250] eta: 0:06:15 lr: 0.000087 grad: 0.0821 (0.0791) loss: 0.8202 (0.8248) time: 0.1468 data: 0.0668 max mem: 9390 +Train: [40] [3600/6250] eta: 0:06:03 lr: 0.000087 grad: 0.0801 (0.0792) loss: 0.8278 (0.8247) time: 0.1493 data: 0.0705 max mem: 9390 +Train: [40] [3700/6250] eta: 0:05:49 lr: 0.000086 grad: 0.0762 (0.0793) loss: 0.8319 (0.8247) time: 0.1375 data: 0.0566 max mem: 9390 +Train: [40] [3800/6250] eta: 0:05:36 lr: 0.000086 grad: 0.0775 (0.0793) loss: 0.8245 (0.8247) time: 0.1599 data: 0.0677 max mem: 9390 +Train: [40] [3900/6250] eta: 0:05:23 lr: 0.000086 grad: 0.0868 (0.0794) loss: 0.8161 (0.8246) time: 0.1482 data: 0.0577 max mem: 9390 +Train: [40] [4000/6250] eta: 0:05:10 lr: 0.000086 grad: 0.0748 (0.0795) loss: 0.8243 (0.8246) time: 0.1515 data: 0.0651 max mem: 9390 +Train: [40] [4100/6250] eta: 0:04:56 lr: 0.000086 grad: 0.0816 (0.0795) loss: 0.8225 (0.8246) time: 0.1450 data: 0.0683 max mem: 9390 +Train: [40] [4200/6250] eta: 0:04:42 lr: 0.000086 grad: 0.0801 (0.0795) loss: 0.8160 (0.8246) time: 0.1330 data: 0.0553 max mem: 9390 +Train: [40] [4300/6250] eta: 0:04:29 lr: 0.000086 grad: 0.0823 (0.0795) loss: 0.8240 (0.8246) time: 0.1498 data: 0.0677 max mem: 9390 +Train: [40] [4400/6250] eta: 0:04:16 lr: 0.000086 grad: 0.0799 (0.0796) loss: 0.8235 (0.8246) time: 0.1305 data: 0.0506 max mem: 9390 +Train: [40] [4500/6250] eta: 0:04:02 lr: 0.000086 grad: 0.0807 (0.0796) loss: 0.8282 (0.8246) time: 0.1401 data: 0.0655 max mem: 9390 +Train: [40] [4600/6250] eta: 0:03:48 lr: 0.000086 grad: 0.0784 (0.0797) loss: 0.8252 (0.8246) time: 0.1317 data: 0.0518 max mem: 9390 +Train: [40] [4700/6250] eta: 0:03:34 lr: 0.000086 grad: 0.0742 (0.0796) loss: 0.8259 (0.8246) time: 0.1651 data: 0.0885 max mem: 9390 +Train: [40] [4800/6250] eta: 0:03:20 lr: 0.000086 grad: 0.0765 (0.0796) loss: 0.8277 (0.8247) time: 0.1274 data: 0.0498 max mem: 9390 +Train: [40] [4900/6250] eta: 0:03:07 lr: 0.000086 grad: 0.0750 (0.0796) loss: 0.8246 (0.8247) time: 0.1372 data: 0.0479 max mem: 9390 +Train: [40] [5000/6250] eta: 0:02:53 lr: 0.000086 grad: 0.0764 (0.0795) loss: 0.8236 (0.8247) time: 0.1324 data: 0.0540 max mem: 9390 +Train: [40] [5100/6250] eta: 0:02:39 lr: 0.000086 grad: 0.0788 (0.0795) loss: 0.8234 (0.8248) time: 0.1395 data: 0.0625 max mem: 9390 +Train: [40] [5200/6250] eta: 0:02:25 lr: 0.000086 grad: 0.0699 (0.0795) loss: 0.8277 (0.8248) time: 0.1406 data: 0.0636 max mem: 9390 +Train: [40] [5300/6250] eta: 0:02:11 lr: 0.000086 grad: 0.0754 (0.0795) loss: 0.8289 (0.8248) time: 0.1495 data: 0.0748 max mem: 9390 +Train: [40] [5400/6250] eta: 0:01:57 lr: 0.000086 grad: 0.0751 (0.0795) loss: 0.8311 (0.8248) time: 0.1460 data: 0.0694 max mem: 9390 +Train: [40] [5500/6250] eta: 0:01:44 lr: 0.000086 grad: 0.0781 (0.0795) loss: 0.8279 (0.8249) time: 0.1518 data: 0.0646 max mem: 9390 +Train: [40] [5600/6250] eta: 0:01:30 lr: 0.000086 grad: 0.0760 (0.0795) loss: 0.8270 (0.8249) time: 0.1271 data: 0.0465 max mem: 9390 +Train: [40] [5700/6250] eta: 0:01:16 lr: 0.000086 grad: 0.0773 (0.0795) loss: 0.8242 (0.8249) time: 0.1337 data: 0.0626 max mem: 9390 +Train: [40] [5800/6250] eta: 0:01:02 lr: 0.000086 grad: 0.0803 (0.0796) loss: 0.8238 (0.8249) time: 0.1230 data: 0.0421 max mem: 9390 +Train: [40] [5900/6250] eta: 0:00:48 lr: 0.000086 grad: 0.0834 (0.0797) loss: 0.8257 (0.8249) time: 0.1524 data: 0.0788 max mem: 9390 +Train: [40] [6000/6250] eta: 0:00:34 lr: 0.000086 grad: 0.0762 (0.0797) loss: 0.8300 (0.8249) time: 0.1283 data: 0.0509 max mem: 9390 +Train: [40] [6100/6250] eta: 0:00:20 lr: 0.000086 grad: 0.0794 (0.0797) loss: 0.8230 (0.8249) time: 0.1473 data: 0.0669 max mem: 9390 +Train: [40] [6200/6250] eta: 0:00:06 lr: 0.000086 grad: 0.0780 (0.0797) loss: 0.8243 (0.8249) time: 0.1504 data: 0.0617 max mem: 9390 +Train: [40] [6249/6250] eta: 0:00:00 lr: 0.000086 grad: 0.0765 (0.0797) loss: 0.8222 (0.8249) time: 0.1233 data: 0.0273 max mem: 9390 +Train: [40] Total time: 0:14:34 (0.1400 s / it) +Averaged stats: lr: 0.000086 grad: 0.0765 (0.0797) loss: 0.8222 (0.8249) +Eval (hcp-train-subset): [40] [ 0/62] eta: 0:04:34 loss: 0.8519 (0.8519) time: 4.4217 data: 4.3812 max mem: 9390 +Eval (hcp-train-subset): [40] [61/62] eta: 0:00:00 loss: 0.8419 (0.8402) time: 0.1057 data: 0.0791 max mem: 9390 +Eval (hcp-train-subset): [40] Total time: 0:00:13 (0.2098 s / it) +Averaged stats (hcp-train-subset): loss: 0.8419 (0.8402) +Eval (hcp-val): [40] [ 0/62] eta: 0:04:24 loss: 0.8332 (0.8332) time: 4.2713 data: 4.2413 max mem: 9390 +Eval (hcp-val): [40] [61/62] eta: 0:00:00 loss: 0.8368 (0.8380) time: 0.1276 data: 0.1008 max mem: 9390 +Eval (hcp-val): [40] Total time: 0:00:12 (0.1981 s / it) +Averaged stats (hcp-val): loss: 0.8368 (0.8380) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +Train: [41] [ 0/6250] eta: 8:41:51 lr: 0.000086 grad: 0.0554 (0.0554) loss: 0.8415 (0.8415) time: 5.0098 data: 4.8798 max mem: 9390 +Train: [41] [ 100/6250] eta: 0:19:45 lr: 0.000086 grad: 0.0742 (0.0819) loss: 0.8335 (0.8353) time: 0.1485 data: 0.0586 max mem: 9390 +Train: [41] [ 200/6250] eta: 0:17:49 lr: 0.000086 grad: 0.0803 (0.0807) loss: 0.8296 (0.8311) time: 0.1603 data: 0.0796 max mem: 9390 +Train: [41] [ 300/6250] eta: 0:16:39 lr: 0.000086 grad: 0.0751 (0.0810) loss: 0.8216 (0.8291) time: 0.1517 data: 0.0605 max mem: 9390 +Train: [41] [ 400/6250] eta: 0:15:44 lr: 0.000086 grad: 0.0727 (0.0797) loss: 0.8260 (0.8281) time: 0.1365 data: 0.0528 max mem: 9390 +Train: [41] [ 500/6250] eta: 0:15:02 lr: 0.000086 grad: 0.0743 (0.0789) loss: 0.8172 (0.8273) time: 0.1257 data: 0.0405 max mem: 9390 +Train: [41] [ 600/6250] eta: 0:14:25 lr: 0.000086 grad: 0.0729 (0.0785) loss: 0.8258 (0.8270) time: 0.1323 data: 0.0549 max mem: 9390 +Train: [41] [ 700/6250] eta: 0:13:55 lr: 0.000085 grad: 0.0745 (0.0780) loss: 0.8238 (0.8268) time: 0.1219 data: 0.0408 max mem: 9390 +Train: [41] [ 800/6250] eta: 0:13:30 lr: 0.000085 grad: 0.0732 (0.0776) loss: 0.8324 (0.8269) time: 0.1392 data: 0.0560 max mem: 9390 +Train: [41] [ 900/6250] eta: 0:13:04 lr: 0.000085 grad: 0.0729 (0.0770) loss: 0.8328 (0.8270) time: 0.1181 data: 0.0292 max mem: 9390 +Train: [41] [1000/6250] eta: 0:12:43 lr: 0.000085 grad: 0.0720 (0.0765) loss: 0.8326 (0.8272) time: 0.1185 data: 0.0420 max mem: 9390 +Train: [41] [1100/6250] eta: 0:12:26 lr: 0.000085 grad: 0.0716 (0.0763) loss: 0.8235 (0.8273) time: 0.1585 data: 0.0706 max mem: 9390 +Train: [41] [1200/6250] eta: 0:12:10 lr: 0.000085 grad: 0.0717 (0.0763) loss: 0.8203 (0.8272) time: 0.1429 data: 0.0638 max mem: 9390 +Train: [41] [1300/6250] eta: 0:11:53 lr: 0.000085 grad: 0.0756 (0.0763) loss: 0.8280 (0.8272) time: 0.1506 data: 0.0774 max mem: 9390 +Train: [41] [1400/6250] eta: 0:11:41 lr: 0.000085 grad: 0.0751 (0.0764) loss: 0.8289 (0.8272) time: 0.1226 data: 0.0429 max mem: 9390 +Train: [41] [1500/6250] eta: 0:11:26 lr: 0.000085 grad: 0.0820 (0.0765) loss: 0.8164 (0.8271) time: 0.1473 data: 0.0660 max mem: 9390 +Train: [41] [1600/6250] eta: 0:11:14 lr: 0.000085 grad: 0.0773 (0.0765) loss: 0.8243 (0.8269) time: 0.1566 data: 0.0807 max mem: 9390 +Train: [41] [1700/6250] eta: 0:10:59 lr: 0.000085 grad: 0.0757 (0.0766) loss: 0.8243 (0.8267) time: 0.1555 data: 0.0688 max mem: 9390 +Train: [41] [1800/6250] eta: 0:10:47 lr: 0.000085 grad: 0.0764 (0.0768) loss: 0.8260 (0.8266) time: 0.1496 data: 0.0689 max mem: 9390 +Train: [41] [1900/6250] eta: 0:10:31 lr: 0.000085 grad: 0.0824 (0.0769) loss: 0.8200 (0.8264) time: 0.1312 data: 0.0561 max mem: 9390 +Train: [41] [2000/6250] eta: 0:10:13 lr: 0.000085 grad: 0.0851 (0.0771) loss: 0.8177 (0.8262) time: 0.1294 data: 0.0510 max mem: 9390 +Train: [41] [2100/6250] eta: 0:09:54 lr: 0.000085 grad: 0.0780 (0.0772) loss: 0.8307 (0.8261) time: 0.1194 data: 0.0362 max mem: 9390 +Train: [41] [2200/6250] eta: 0:09:36 lr: 0.000085 grad: 0.0781 (0.0774) loss: 0.8209 (0.8260) time: 0.1178 data: 0.0373 max mem: 9390 +Train: [41] [2300/6250] eta: 0:09:17 lr: 0.000085 grad: 0.0744 (0.0775) loss: 0.8209 (0.8259) time: 0.1280 data: 0.0446 max mem: 9390 +Train: [41] [2400/6250] eta: 0:08:59 lr: 0.000085 grad: 0.0797 (0.0777) loss: 0.8213 (0.8258) time: 0.1129 data: 0.0307 max mem: 9390 +Train: [41] [2500/6250] eta: 0:08:42 lr: 0.000085 grad: 0.0792 (0.0778) loss: 0.8213 (0.8257) time: 0.1260 data: 0.0491 max mem: 9390 +Train: [41] [2600/6250] eta: 0:08:27 lr: 0.000085 grad: 0.0782 (0.0779) loss: 0.8246 (0.8255) time: 0.1353 data: 0.0585 max mem: 9390 +Train: [41] [2700/6250] eta: 0:08:12 lr: 0.000085 grad: 0.0772 (0.0780) loss: 0.8194 (0.8255) time: 0.1333 data: 0.0557 max mem: 9390 +Train: [41] [2800/6250] eta: 0:07:58 lr: 0.000085 grad: 0.0786 (0.0781) loss: 0.8245 (0.8254) time: 0.1278 data: 0.0522 max mem: 9390 +Train: [41] [2900/6250] eta: 0:07:43 lr: 0.000085 grad: 0.0794 (0.0783) loss: 0.8186 (0.8253) time: 0.1188 data: 0.0382 max mem: 9390 +Train: [41] [3000/6250] eta: 0:07:29 lr: 0.000085 grad: 0.0807 (0.0785) loss: 0.8189 (0.8251) time: 0.1194 data: 0.0442 max mem: 9390 +Train: [41] [3100/6250] eta: 0:07:14 lr: 0.000085 grad: 0.0844 (0.0786) loss: 0.8186 (0.8250) time: 0.1254 data: 0.0466 max mem: 9390 +Train: [41] [3200/6250] eta: 0:06:58 lr: 0.000085 grad: 0.0737 (0.0787) loss: 0.8222 (0.8249) time: 0.1257 data: 0.0492 max mem: 9390 +Train: [41] [3300/6250] eta: 0:06:44 lr: 0.000085 grad: 0.0825 (0.0788) loss: 0.8253 (0.8248) time: 0.1337 data: 0.0445 max mem: 9390 +Train: [41] [3400/6250] eta: 0:06:30 lr: 0.000085 grad: 0.0836 (0.0789) loss: 0.8194 (0.8247) time: 0.1421 data: 0.0604 max mem: 9390 +Train: [41] [3500/6250] eta: 0:06:17 lr: 0.000085 grad: 0.0830 (0.0790) loss: 0.8151 (0.8246) time: 0.1544 data: 0.0694 max mem: 9390 +Train: [41] [3600/6250] eta: 0:06:03 lr: 0.000085 grad: 0.0827 (0.0791) loss: 0.8267 (0.8245) time: 0.1282 data: 0.0488 max mem: 9390 +Train: [41] [3700/6250] eta: 0:05:50 lr: 0.000085 grad: 0.0789 (0.0792) loss: 0.8286 (0.8244) time: 0.1381 data: 0.0590 max mem: 9390 +Train: [41] [3800/6250] eta: 0:05:36 lr: 0.000085 grad: 0.0823 (0.0793) loss: 0.8180 (0.8242) time: 0.1424 data: 0.0652 max mem: 9390 +Train: [41] [3900/6250] eta: 0:05:23 lr: 0.000084 grad: 0.0787 (0.0794) loss: 0.8132 (0.8241) time: 0.1277 data: 0.0517 max mem: 9390 +Train: [41] [4000/6250] eta: 0:05:10 lr: 0.000084 grad: 0.0865 (0.0795) loss: 0.8177 (0.8239) time: 0.1613 data: 0.0832 max mem: 9390 +Train: [41] [4100/6250] eta: 0:04:56 lr: 0.000084 grad: 0.0792 (0.0796) loss: 0.8228 (0.8239) time: 0.1418 data: 0.0628 max mem: 9390 +Train: [41] [4200/6250] eta: 0:04:43 lr: 0.000084 grad: 0.0802 (0.0797) loss: 0.8233 (0.8238) time: 0.1513 data: 0.0746 max mem: 9390 +Train: [41] [4300/6250] eta: 0:04:29 lr: 0.000084 grad: 0.0829 (0.0798) loss: 0.8186 (0.8238) time: 0.1359 data: 0.0541 max mem: 9390 +Train: [41] [4400/6250] eta: 0:04:15 lr: 0.000084 grad: 0.0776 (0.0798) loss: 0.8210 (0.8237) time: 0.1409 data: 0.0622 max mem: 9390 +Train: [41] [4500/6250] eta: 0:04:02 lr: 0.000084 grad: 0.0804 (0.0798) loss: 0.8176 (0.8237) time: 0.1450 data: 0.0623 max mem: 9390 +Train: [41] [4600/6250] eta: 0:03:48 lr: 0.000084 grad: 0.0849 (0.0799) loss: 0.8182 (0.8236) time: 0.1513 data: 0.0699 max mem: 9390 +Train: [41] [4700/6250] eta: 0:03:35 lr: 0.000084 grad: 0.0761 (0.0799) loss: 0.8205 (0.8236) time: 0.1483 data: 0.0703 max mem: 9390 +Train: [41] [4800/6250] eta: 0:03:21 lr: 0.000084 grad: 0.0772 (0.0799) loss: 0.8257 (0.8235) time: 0.1374 data: 0.0593 max mem: 9390 +Train: [41] [4900/6250] eta: 0:03:07 lr: 0.000084 grad: 0.0767 (0.0800) loss: 0.8199 (0.8234) time: 0.1186 data: 0.0253 max mem: 9390 +Train: [41] [5000/6250] eta: 0:02:53 lr: 0.000084 grad: 0.0768 (0.0800) loss: 0.8221 (0.8234) time: 0.1478 data: 0.0653 max mem: 9390 +Train: [41] [5100/6250] eta: 0:02:40 lr: 0.000084 grad: 0.0762 (0.0800) loss: 0.8266 (0.8234) time: 0.1521 data: 0.0610 max mem: 9390 +Train: [41] [5200/6250] eta: 0:02:26 lr: 0.000084 grad: 0.0755 (0.0800) loss: 0.8266 (0.8234) time: 0.1391 data: 0.0622 max mem: 9390 +Train: [41] [5300/6250] eta: 0:02:12 lr: 0.000084 grad: 0.0736 (0.0800) loss: 0.8185 (0.8234) time: 0.1461 data: 0.0695 max mem: 9390 +Train: [41] [5400/6250] eta: 0:01:58 lr: 0.000084 grad: 0.0792 (0.0800) loss: 0.8241 (0.8234) time: 0.1392 data: 0.0455 max mem: 9390 +Train: [41] [5500/6250] eta: 0:01:44 lr: 0.000084 grad: 0.0775 (0.0801) loss: 0.8203 (0.8233) time: 0.1681 data: 0.0932 max mem: 9390 +Train: [41] [5600/6250] eta: 0:01:30 lr: 0.000084 grad: 0.0808 (0.0801) loss: 0.8173 (0.8233) time: 0.1318 data: 0.0522 max mem: 9390 +Train: [41] [5700/6250] eta: 0:01:16 lr: 0.000084 grad: 0.0751 (0.0801) loss: 0.8235 (0.8232) time: 0.1222 data: 0.0399 max mem: 9390 +Train: [41] [5800/6250] eta: 0:01:02 lr: 0.000084 grad: 0.0790 (0.0801) loss: 0.8244 (0.8232) time: 0.1523 data: 0.0790 max mem: 9390 +Train: [41] [5900/6250] eta: 0:00:48 lr: 0.000084 grad: 0.0775 (0.0802) loss: 0.8189 (0.8232) time: 0.1341 data: 0.0548 max mem: 9390 +Train: [41] [6000/6250] eta: 0:00:34 lr: 0.000084 grad: 0.0798 (0.0802) loss: 0.8215 (0.8231) time: 0.1281 data: 0.0506 max mem: 9390 +Train: [41] [6100/6250] eta: 0:00:20 lr: 0.000084 grad: 0.0731 (0.0802) loss: 0.8267 (0.8231) time: 0.1272 data: 0.0511 max mem: 9390 +Train: [41] [6200/6250] eta: 0:00:06 lr: 0.000084 grad: 0.0789 (0.0802) loss: 0.8225 (0.8231) time: 0.1618 data: 0.0825 max mem: 9390 +Train: [41] [6249/6250] eta: 0:00:00 lr: 0.000084 grad: 0.0811 (0.0802) loss: 0.8278 (0.8231) time: 0.1707 data: 0.0882 max mem: 9390 +Train: [41] Total time: 0:14:38 (0.1405 s / it) +Averaged stats: lr: 0.000084 grad: 0.0811 (0.0802) loss: 0.8278 (0.8231) +Eval (hcp-train-subset): [41] [ 0/62] eta: 0:03:40 loss: 0.8475 (0.8475) time: 3.5556 data: 3.4579 max mem: 9390 +Eval (hcp-train-subset): [41] [61/62] eta: 0:00:00 loss: 0.8385 (0.8407) time: 0.1082 data: 0.0833 max mem: 9390 +Eval (hcp-train-subset): [41] Total time: 0:00:13 (0.2098 s / it) +Averaged stats (hcp-train-subset): loss: 0.8385 (0.8407) +Eval (hcp-val): [41] [ 0/62] eta: 0:03:36 loss: 0.8344 (0.8344) time: 3.4933 data: 3.4171 max mem: 9390 +Eval (hcp-val): [41] [61/62] eta: 0:00:00 loss: 0.8366 (0.8379) time: 0.1242 data: 0.0995 max mem: 9390 +Eval (hcp-val): [41] Total time: 0:00:12 (0.2076 s / it) +Averaged stats (hcp-val): loss: 0.8366 (0.8379) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +Train: [42] [ 0/6250] eta: 9:42:35 lr: 0.000084 grad: 0.1215 (0.1215) loss: 0.8332 (0.8332) time: 5.5929 data: 5.4948 max mem: 9390 +Train: [42] [ 100/6250] eta: 0:20:57 lr: 0.000084 grad: 0.0702 (0.0814) loss: 0.8390 (0.8445) time: 0.1806 data: 0.0923 max mem: 9390 +Train: [42] [ 200/6250] eta: 0:17:41 lr: 0.000084 grad: 0.0691 (0.0786) loss: 0.8373 (0.8389) time: 0.1556 data: 0.0735 max mem: 9390 +Train: [42] [ 300/6250] eta: 0:16:08 lr: 0.000084 grad: 0.0738 (0.0772) loss: 0.8294 (0.8372) time: 0.1212 data: 0.0406 max mem: 9390 +Train: [42] [ 400/6250] eta: 0:15:29 lr: 0.000084 grad: 0.0687 (0.0763) loss: 0.8307 (0.8356) time: 0.1609 data: 0.0753 max mem: 9390 +Train: [42] [ 500/6250] eta: 0:14:46 lr: 0.000084 grad: 0.0745 (0.0766) loss: 0.8257 (0.8341) time: 0.1317 data: 0.0483 max mem: 9390 +Train: [42] [ 600/6250] eta: 0:14:08 lr: 0.000084 grad: 0.0753 (0.0770) loss: 0.8335 (0.8334) time: 0.1300 data: 0.0450 max mem: 9390 +Train: [42] [ 700/6250] eta: 0:13:35 lr: 0.000084 grad: 0.0780 (0.0773) loss: 0.8326 (0.8326) time: 0.1262 data: 0.0454 max mem: 9390 +Train: [42] [ 800/6250] eta: 0:13:09 lr: 0.000084 grad: 0.0839 (0.0776) loss: 0.8250 (0.8321) time: 0.1265 data: 0.0411 max mem: 9390 +Train: [42] [ 900/6250] eta: 0:12:45 lr: 0.000083 grad: 0.0770 (0.0777) loss: 0.8317 (0.8315) time: 0.1346 data: 0.0538 max mem: 9390 +Train: [42] [1000/6250] eta: 0:12:24 lr: 0.000083 grad: 0.0769 (0.0778) loss: 0.8282 (0.8307) time: 0.1325 data: 0.0478 max mem: 9390 +Train: [42] [1100/6250] eta: 0:12:02 lr: 0.000083 grad: 0.0851 (0.0783) loss: 0.8220 (0.8301) time: 0.1334 data: 0.0453 max mem: 9390 +Train: [42] [1200/6250] eta: 0:11:43 lr: 0.000083 grad: 0.0791 (0.0784) loss: 0.8195 (0.8294) time: 0.1274 data: 0.0480 max mem: 9390 +Train: [42] [1300/6250] eta: 0:11:27 lr: 0.000083 grad: 0.0803 (0.0787) loss: 0.8187 (0.8288) time: 0.1377 data: 0.0633 max mem: 9390 +Train: [42] [1400/6250] eta: 0:11:10 lr: 0.000083 grad: 0.0823 (0.0791) loss: 0.8170 (0.8281) time: 0.1322 data: 0.0542 max mem: 9390 +Train: [42] [1500/6250] eta: 0:11:06 lr: 0.000083 grad: 0.0789 (0.0793) loss: 0.8262 (0.8276) time: 0.1569 data: 0.0759 max mem: 9390 +Train: [42] [1600/6250] eta: 0:10:53 lr: 0.000083 grad: 0.0828 (0.0797) loss: 0.8208 (0.8271) time: 0.1430 data: 0.0655 max mem: 9390 +Train: [42] [1700/6250] eta: 0:10:42 lr: 0.000083 grad: 0.0790 (0.0798) loss: 0.8231 (0.8267) time: 0.1581 data: 0.0734 max mem: 9390 +Train: [42] [1800/6250] eta: 0:10:29 lr: 0.000083 grad: 0.0830 (0.0801) loss: 0.8224 (0.8264) time: 0.1133 data: 0.0343 max mem: 9390 +Train: [42] [1900/6250] eta: 0:10:14 lr: 0.000083 grad: 0.0780 (0.0802) loss: 0.8190 (0.8260) time: 0.1300 data: 0.0499 max mem: 9390 +Train: [42] [2000/6250] eta: 0:09:59 lr: 0.000083 grad: 0.0770 (0.0805) loss: 0.8214 (0.8257) time: 0.1381 data: 0.0565 max mem: 9390 +Train: [42] [2100/6250] eta: 0:09:43 lr: 0.000083 grad: 0.0862 (0.0806) loss: 0.8190 (0.8254) time: 0.1424 data: 0.0632 max mem: 9390 +Train: [42] [2200/6250] eta: 0:09:26 lr: 0.000083 grad: 0.0772 (0.0807) loss: 0.8271 (0.8253) time: 0.1343 data: 0.0552 max mem: 9390 +Train: [42] [2300/6250] eta: 0:09:09 lr: 0.000083 grad: 0.0774 (0.0810) loss: 0.8179 (0.8252) time: 0.1164 data: 0.0385 max mem: 9390 +Train: [42] [2400/6250] eta: 0:08:52 lr: 0.000083 grad: 0.0847 (0.0812) loss: 0.8251 (0.8250) time: 0.1160 data: 0.0416 max mem: 9390 +Train: [42] [2500/6250] eta: 0:08:35 lr: 0.000083 grad: 0.0842 (0.0813) loss: 0.8214 (0.8247) time: 0.0996 data: 0.0182 max mem: 9390 +Train: [42] [2600/6250] eta: 0:08:20 lr: 0.000083 grad: 0.0816 (0.0814) loss: 0.8214 (0.8245) time: 0.1178 data: 0.0395 max mem: 9390 +Train: [42] [2700/6250] eta: 0:08:08 lr: 0.000083 grad: 0.0782 (0.0815) loss: 0.8245 (0.8244) time: 0.1579 data: 0.0806 max mem: 9390 +Train: [42] [2800/6250] eta: 0:07:57 lr: 0.000083 grad: 0.0775 (0.0815) loss: 0.8234 (0.8244) time: 0.2317 data: 0.1542 max mem: 9390 +Train: [42] [2900/6250] eta: 0:07:42 lr: 0.000083 grad: 0.0833 (0.0816) loss: 0.8191 (0.8243) time: 0.1281 data: 0.0532 max mem: 9390 +Train: [42] [3000/6250] eta: 0:07:28 lr: 0.000083 grad: 0.0789 (0.0817) loss: 0.8279 (0.8242) time: 0.1298 data: 0.0523 max mem: 9390 +Train: [42] [3100/6250] eta: 0:07:14 lr: 0.000083 grad: 0.0820 (0.0819) loss: 0.8209 (0.8241) time: 0.1439 data: 0.0703 max mem: 9390 +Train: [42] [3200/6250] eta: 0:07:00 lr: 0.000083 grad: 0.0767 (0.0819) loss: 0.8224 (0.8240) time: 0.1239 data: 0.0510 max mem: 9390 +Train: [42] [3300/6250] eta: 0:06:45 lr: 0.000083 grad: 0.0867 (0.0820) loss: 0.8132 (0.8238) time: 0.1259 data: 0.0477 max mem: 9390 +Train: [42] [3400/6250] eta: 0:06:31 lr: 0.000083 grad: 0.0830 (0.0821) loss: 0.8172 (0.8236) time: 0.1511 data: 0.0743 max mem: 9390 +Train: [42] [3500/6250] eta: 0:06:17 lr: 0.000083 grad: 0.0839 (0.0822) loss: 0.8218 (0.8234) time: 0.1198 data: 0.0279 max mem: 9390 +Train: [42] [3600/6250] eta: 0:06:03 lr: 0.000083 grad: 0.0822 (0.0823) loss: 0.8156 (0.8233) time: 0.1252 data: 0.0461 max mem: 9390 +Train: [42] [3700/6250] eta: 0:05:51 lr: 0.000083 grad: 0.0816 (0.0823) loss: 0.8184 (0.8232) time: 0.1498 data: 0.0690 max mem: 9390 +Train: [42] [3800/6250] eta: 0:05:40 lr: 0.000083 grad: 0.0805 (0.0824) loss: 0.8252 (0.8231) time: 0.2816 data: 0.1859 max mem: 9390 +Train: [42] [3900/6250] eta: 0:05:25 lr: 0.000083 grad: 0.0824 (0.0825) loss: 0.8171 (0.8231) time: 0.1248 data: 0.0464 max mem: 9390 +Train: [42] [4000/6250] eta: 0:05:11 lr: 0.000083 grad: 0.0781 (0.0825) loss: 0.8226 (0.8230) time: 0.1666 data: 0.0777 max mem: 9390 +Train: [42] [4100/6250] eta: 0:04:58 lr: 0.000082 grad: 0.0780 (0.0824) loss: 0.8276 (0.8230) time: 0.1521 data: 0.0715 max mem: 9390 +Train: [42] [4200/6250] eta: 0:04:46 lr: 0.000082 grad: 0.0800 (0.0824) loss: 0.8314 (0.8230) time: 0.1519 data: 0.0461 max mem: 9390 +Train: [42] [4300/6250] eta: 0:04:32 lr: 0.000082 grad: 0.0773 (0.0824) loss: 0.8224 (0.8230) time: 0.1535 data: 0.0748 max mem: 9390 +Train: [42] [4400/6250] eta: 0:04:18 lr: 0.000082 grad: 0.0813 (0.0824) loss: 0.8177 (0.8230) time: 0.1409 data: 0.0650 max mem: 9390 +Train: [42] [4500/6250] eta: 0:04:04 lr: 0.000082 grad: 0.0810 (0.0824) loss: 0.8188 (0.8230) time: 0.1263 data: 0.0465 max mem: 9390 +Train: [42] [4600/6250] eta: 0:03:51 lr: 0.000082 grad: 0.0805 (0.0824) loss: 0.8309 (0.8230) time: 0.2030 data: 0.1159 max mem: 9390 +Train: [42] [4700/6250] eta: 0:03:36 lr: 0.000082 grad: 0.0784 (0.0825) loss: 0.8218 (0.8230) time: 0.1344 data: 0.0495 max mem: 9390 +Train: [42] [4800/6250] eta: 0:03:23 lr: 0.000082 grad: 0.0830 (0.0825) loss: 0.8160 (0.8230) time: 0.2029 data: 0.1021 max mem: 9390 +Train: [42] [4900/6250] eta: 0:03:09 lr: 0.000082 grad: 0.0810 (0.0825) loss: 0.8202 (0.8230) time: 0.2333 data: 0.1436 max mem: 9390 +Train: [42] [5000/6250] eta: 0:02:55 lr: 0.000082 grad: 0.0827 (0.0825) loss: 0.8247 (0.8229) time: 0.1395 data: 0.0581 max mem: 9390 +Train: [42] [5100/6250] eta: 0:02:41 lr: 0.000082 grad: 0.0765 (0.0825) loss: 0.8223 (0.8229) time: 0.1508 data: 0.0688 max mem: 9390 +Train: [42] [5200/6250] eta: 0:02:27 lr: 0.000082 grad: 0.0854 (0.0825) loss: 0.8240 (0.8229) time: 0.1339 data: 0.0556 max mem: 9390 +Train: [42] [5300/6250] eta: 0:02:13 lr: 0.000082 grad: 0.0785 (0.0825) loss: 0.8273 (0.8229) time: 0.1385 data: 0.0578 max mem: 9390 +Train: [42] [5400/6250] eta: 0:01:59 lr: 0.000082 grad: 0.0834 (0.0825) loss: 0.8186 (0.8229) time: 0.1622 data: 0.0782 max mem: 9390 +Train: [42] [5500/6250] eta: 0:01:45 lr: 0.000082 grad: 0.0835 (0.0825) loss: 0.8286 (0.8229) time: 0.1338 data: 0.0447 max mem: 9390 +Train: [42] [5600/6250] eta: 0:01:31 lr: 0.000082 grad: 0.0797 (0.0826) loss: 0.8216 (0.8230) time: 0.1242 data: 0.0477 max mem: 9390 +Train: [42] [5700/6250] eta: 0:01:17 lr: 0.000082 grad: 0.0805 (0.0825) loss: 0.8188 (0.8230) time: 0.1441 data: 0.0609 max mem: 9390 +Train: [42] [5800/6250] eta: 0:01:03 lr: 0.000082 grad: 0.0842 (0.0826) loss: 0.8243 (0.8231) time: 0.1070 data: 0.0131 max mem: 9390 +Train: [42] [5900/6250] eta: 0:00:49 lr: 0.000082 grad: 0.0781 (0.0826) loss: 0.8210 (0.8231) time: 0.1402 data: 0.0597 max mem: 9390 +Train: [42] [6000/6250] eta: 0:00:35 lr: 0.000082 grad: 0.0808 (0.0826) loss: 0.8186 (0.8230) time: 0.1342 data: 0.0558 max mem: 9390 +Train: [42] [6100/6250] eta: 0:00:21 lr: 0.000082 grad: 0.0783 (0.0827) loss: 0.8133 (0.8230) time: 0.1202 data: 0.0247 max mem: 9390 +Train: [42] [6200/6250] eta: 0:00:07 lr: 0.000082 grad: 0.0825 (0.0827) loss: 0.8199 (0.8229) time: 0.1318 data: 0.0521 max mem: 9390 +Train: [42] [6249/6250] eta: 0:00:00 lr: 0.000082 grad: 0.0823 (0.0827) loss: 0.8230 (0.8229) time: 0.1998 data: 0.1231 max mem: 9390 +Train: [42] Total time: 0:14:53 (0.1429 s / it) +Averaged stats: lr: 0.000082 grad: 0.0823 (0.0827) loss: 0.8230 (0.8229) +Eval (hcp-train-subset): [42] [ 0/62] eta: 0:04:41 loss: 0.8504 (0.8504) time: 4.5338 data: 4.5037 max mem: 9390 +Eval (hcp-train-subset): [42] [61/62] eta: 0:00:00 loss: 0.8409 (0.8394) time: 0.1212 data: 0.0952 max mem: 9390 +Eval (hcp-train-subset): [42] Total time: 0:00:12 (0.2074 s / it) +Averaged stats (hcp-train-subset): loss: 0.8409 (0.8394) +Eval (hcp-val): [42] [ 0/62] eta: 0:03:13 loss: 0.8360 (0.8360) time: 3.1247 data: 3.0708 max mem: 9390 +Eval (hcp-val): [42] [61/62] eta: 0:00:00 loss: 0.8369 (0.8370) time: 0.1055 data: 0.0792 max mem: 9390 +Eval (hcp-val): [42] Total time: 0:00:13 (0.2109 s / it) +Averaged stats (hcp-val): loss: 0.8369 (0.8370) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +Train: [43] [ 0/6250] eta: 8:08:42 lr: 0.000082 grad: 0.1294 (0.1294) loss: 0.8275 (0.8275) time: 4.6916 data: 4.4730 max mem: 9390 +Train: [43] [ 100/6250] eta: 0:20:51 lr: 0.000082 grad: 0.0831 (0.0878) loss: 0.8176 (0.8318) time: 0.1564 data: 0.0617 max mem: 9390 +Train: [43] [ 200/6250] eta: 0:17:48 lr: 0.000082 grad: 0.0762 (0.0855) loss: 0.8232 (0.8249) time: 0.1304 data: 0.0386 max mem: 9390 +Train: [43] [ 300/6250] eta: 0:16:16 lr: 0.000082 grad: 0.0758 (0.0840) loss: 0.8238 (0.8235) time: 0.1213 data: 0.0327 max mem: 9390 +Train: [43] [ 400/6250] eta: 0:15:28 lr: 0.000082 grad: 0.0785 (0.0831) loss: 0.8261 (0.8235) time: 0.1325 data: 0.0515 max mem: 9390 +Train: [43] [ 500/6250] eta: 0:14:45 lr: 0.000082 grad: 0.0778 (0.0828) loss: 0.8273 (0.8232) time: 0.1253 data: 0.0439 max mem: 9390 +Train: [43] [ 600/6250] eta: 0:14:07 lr: 0.000082 grad: 0.0782 (0.0828) loss: 0.8253 (0.8232) time: 0.1155 data: 0.0315 max mem: 9390 +Train: [43] [ 700/6250] eta: 0:13:35 lr: 0.000082 grad: 0.0782 (0.0824) loss: 0.8279 (0.8237) time: 0.1378 data: 0.0552 max mem: 9390 +Train: [43] [ 800/6250] eta: 0:13:12 lr: 0.000082 grad: 0.0788 (0.0820) loss: 0.8297 (0.8240) time: 0.1311 data: 0.0549 max mem: 9390 +Train: [43] [ 900/6250] eta: 0:12:50 lr: 0.000082 grad: 0.0770 (0.0817) loss: 0.8275 (0.8243) time: 0.1222 data: 0.0445 max mem: 9390 +Train: [43] [1000/6250] eta: 0:12:30 lr: 0.000081 grad: 0.0703 (0.0814) loss: 0.8332 (0.8248) time: 0.1415 data: 0.0629 max mem: 9390 +Train: [43] [1100/6250] eta: 0:12:13 lr: 0.000081 grad: 0.0817 (0.0812) loss: 0.8237 (0.8249) time: 0.1223 data: 0.0490 max mem: 9390 +Train: [43] [1200/6250] eta: 0:11:53 lr: 0.000081 grad: 0.0783 (0.0812) loss: 0.8248 (0.8251) time: 0.1254 data: 0.0438 max mem: 9390 +Train: [43] [1300/6250] eta: 0:11:44 lr: 0.000081 grad: 0.0746 (0.0810) loss: 0.8272 (0.8252) time: 0.1747 data: 0.0940 max mem: 9390 +Train: [43] [1400/6250] eta: 0:11:31 lr: 0.000081 grad: 0.0739 (0.0810) loss: 0.8297 (0.8253) time: 0.1211 data: 0.0441 max mem: 9390 +Train: [43] [1500/6250] eta: 0:11:22 lr: 0.000081 grad: 0.0729 (0.0808) loss: 0.8256 (0.8253) time: 0.1419 data: 0.0657 max mem: 9390 +Train: [43] [1600/6250] eta: 0:11:09 lr: 0.000081 grad: 0.0795 (0.0808) loss: 0.8248 (0.8252) time: 0.1569 data: 0.0766 max mem: 9390 +Train: [43] [1700/6250] eta: 0:10:54 lr: 0.000081 grad: 0.0854 (0.0808) loss: 0.8159 (0.8250) time: 0.1408 data: 0.0599 max mem: 9390 +Train: [43] [1800/6250] eta: 0:10:42 lr: 0.000081 grad: 0.0797 (0.0809) loss: 0.8309 (0.8251) time: 0.1599 data: 0.0795 max mem: 9390 +Train: [43] [1900/6250] eta: 0:10:26 lr: 0.000081 grad: 0.0802 (0.0810) loss: 0.8299 (0.8250) time: 0.1451 data: 0.0691 max mem: 9390 +Train: [43] [2000/6250] eta: 0:10:10 lr: 0.000081 grad: 0.0806 (0.0810) loss: 0.8268 (0.8250) time: 0.1153 data: 0.0250 max mem: 9390 +Train: [43] [2100/6250] eta: 0:09:54 lr: 0.000081 grad: 0.0813 (0.0810) loss: 0.8209 (0.8250) time: 0.1021 data: 0.0206 max mem: 9390 +Train: [43] [2200/6250] eta: 0:09:36 lr: 0.000081 grad: 0.0816 (0.0810) loss: 0.8230 (0.8250) time: 0.1272 data: 0.0418 max mem: 9390 +Train: [43] [2300/6250] eta: 0:09:19 lr: 0.000081 grad: 0.0838 (0.0809) loss: 0.8262 (0.8250) time: 0.1137 data: 0.0284 max mem: 9390 +Train: [43] [2400/6250] eta: 0:09:01 lr: 0.000081 grad: 0.0817 (0.0810) loss: 0.8277 (0.8251) time: 0.1279 data: 0.0462 max mem: 9390 +Train: [43] [2500/6250] eta: 0:08:44 lr: 0.000081 grad: 0.0817 (0.0811) loss: 0.8264 (0.8251) time: 0.1284 data: 0.0456 max mem: 9390 +Train: [43] [2600/6250] eta: 0:08:31 lr: 0.000081 grad: 0.0762 (0.0811) loss: 0.8198 (0.8250) time: 0.1250 data: 0.0416 max mem: 9390 +Train: [43] [2700/6250] eta: 0:08:20 lr: 0.000081 grad: 0.0804 (0.0812) loss: 0.8213 (0.8249) time: 0.1528 data: 0.0672 max mem: 9390 +Train: [43] [2800/6250] eta: 0:08:05 lr: 0.000081 grad: 0.0726 (0.0812) loss: 0.8287 (0.8249) time: 0.1199 data: 0.0403 max mem: 9390 +Train: [43] [2900/6250] eta: 0:07:52 lr: 0.000081 grad: 0.0792 (0.0813) loss: 0.8258 (0.8248) time: 0.1433 data: 0.0700 max mem: 9390 +Train: [43] [3000/6250] eta: 0:07:38 lr: 0.000081 grad: 0.0757 (0.0814) loss: 0.8258 (0.8248) time: 0.1350 data: 0.0611 max mem: 9390 +Train: [43] [3100/6250] eta: 0:07:24 lr: 0.000081 grad: 0.0788 (0.0814) loss: 0.8256 (0.8248) time: 0.1258 data: 0.0437 max mem: 9390 +Train: [43] [3200/6250] eta: 0:07:09 lr: 0.000081 grad: 0.0785 (0.0814) loss: 0.8225 (0.8248) time: 0.1585 data: 0.0703 max mem: 9390 +Train: [43] [3300/6250] eta: 0:06:54 lr: 0.000081 grad: 0.0816 (0.0814) loss: 0.8271 (0.8248) time: 0.1311 data: 0.0533 max mem: 9390 +Train: [43] [3400/6250] eta: 0:06:39 lr: 0.000081 grad: 0.0825 (0.0814) loss: 0.8229 (0.8249) time: 0.1333 data: 0.0544 max mem: 9390 +Train: [43] [3500/6250] eta: 0:06:25 lr: 0.000081 grad: 0.0776 (0.0813) loss: 0.8239 (0.8249) time: 0.1590 data: 0.0790 max mem: 9390 +Train: [43] [3600/6250] eta: 0:06:11 lr: 0.000081 grad: 0.0818 (0.0813) loss: 0.8256 (0.8249) time: 0.1420 data: 0.0625 max mem: 9390 +Train: [43] [3700/6250] eta: 0:05:59 lr: 0.000081 grad: 0.0827 (0.0814) loss: 0.8224 (0.8249) time: 0.1788 data: 0.0914 max mem: 9390 +Train: [43] [3800/6250] eta: 0:05:46 lr: 0.000081 grad: 0.0825 (0.0814) loss: 0.8207 (0.8249) time: 0.1377 data: 0.0542 max mem: 9390 +Train: [43] [3900/6250] eta: 0:05:33 lr: 0.000081 grad: 0.0769 (0.0814) loss: 0.8229 (0.8249) time: 0.1595 data: 0.0773 max mem: 9390 +Train: [43] [4000/6250] eta: 0:05:20 lr: 0.000081 grad: 0.0790 (0.0814) loss: 0.8235 (0.8248) time: 0.1304 data: 0.0373 max mem: 9390 +Train: [43] [4100/6250] eta: 0:05:06 lr: 0.000081 grad: 0.0810 (0.0814) loss: 0.8172 (0.8247) time: 0.1507 data: 0.0608 max mem: 9390 +Train: [43] [4200/6250] eta: 0:04:53 lr: 0.000080 grad: 0.0847 (0.0815) loss: 0.8196 (0.8246) time: 0.1375 data: 0.0529 max mem: 9390 +Train: [43] [4300/6250] eta: 0:04:39 lr: 0.000080 grad: 0.0856 (0.0816) loss: 0.8179 (0.8244) time: 0.1413 data: 0.0573 max mem: 9390 +Train: [43] [4400/6250] eta: 0:04:25 lr: 0.000080 grad: 0.0813 (0.0816) loss: 0.8149 (0.8243) time: 0.1654 data: 0.0837 max mem: 9390 +Train: [43] [4500/6250] eta: 0:04:11 lr: 0.000080 grad: 0.0804 (0.0816) loss: 0.8222 (0.8242) time: 0.1330 data: 0.0577 max mem: 9390 +Train: [43] [4600/6250] eta: 0:03:57 lr: 0.000080 grad: 0.0802 (0.0817) loss: 0.8185 (0.8242) time: 0.1120 data: 0.0114 max mem: 9390 +Train: [43] [4700/6250] eta: 0:03:44 lr: 0.000080 grad: 0.0866 (0.0818) loss: 0.8160 (0.8241) time: 0.0991 data: 0.0003 max mem: 9390 +Train: [43] [4800/6250] eta: 0:03:29 lr: 0.000080 grad: 0.0807 (0.0820) loss: 0.8220 (0.8240) time: 0.1311 data: 0.0544 max mem: 9390 +Train: [43] [4900/6250] eta: 0:03:14 lr: 0.000080 grad: 0.0864 (0.0821) loss: 0.8203 (0.8239) time: 0.1472 data: 0.0641 max mem: 9390 +Train: [43] [5000/6250] eta: 0:03:00 lr: 0.000080 grad: 0.0787 (0.0821) loss: 0.8231 (0.8239) time: 0.1490 data: 0.0693 max mem: 9390 +Train: [43] [5100/6250] eta: 0:02:46 lr: 0.000080 grad: 0.0762 (0.0821) loss: 0.8233 (0.8238) time: 0.1483 data: 0.0715 max mem: 9390 +Train: [43] [5200/6250] eta: 0:02:31 lr: 0.000080 grad: 0.0813 (0.0821) loss: 0.8230 (0.8238) time: 0.1541 data: 0.0704 max mem: 9390 +Train: [43] [5300/6250] eta: 0:02:17 lr: 0.000080 grad: 0.0815 (0.0822) loss: 0.8139 (0.8237) time: 0.1872 data: 0.1102 max mem: 9390 +Train: [43] [5400/6250] eta: 0:02:02 lr: 0.000080 grad: 0.0804 (0.0822) loss: 0.8190 (0.8237) time: 0.1355 data: 0.0535 max mem: 9390 +Train: [43] [5500/6250] eta: 0:01:48 lr: 0.000080 grad: 0.0755 (0.0822) loss: 0.8246 (0.8237) time: 0.0969 data: 0.0100 max mem: 9390 +Train: [43] [5600/6250] eta: 0:01:34 lr: 0.000080 grad: 0.0847 (0.0822) loss: 0.8201 (0.8236) time: 0.1492 data: 0.0685 max mem: 9390 +Train: [43] [5700/6250] eta: 0:01:19 lr: 0.000080 grad: 0.0815 (0.0823) loss: 0.8230 (0.8235) time: 0.1568 data: 0.0754 max mem: 9390 +Train: [43] [5800/6250] eta: 0:01:05 lr: 0.000080 grad: 0.0797 (0.0823) loss: 0.8208 (0.8235) time: 0.1608 data: 0.0756 max mem: 9390 +Train: [43] [5900/6250] eta: 0:00:50 lr: 0.000080 grad: 0.0831 (0.0823) loss: 0.8187 (0.8235) time: 0.1380 data: 0.0620 max mem: 9390 +Train: [43] [6000/6250] eta: 0:00:36 lr: 0.000080 grad: 0.0816 (0.0823) loss: 0.8200 (0.8235) time: 0.1349 data: 0.0584 max mem: 9390 +Train: [43] [6100/6250] eta: 0:00:21 lr: 0.000080 grad: 0.0810 (0.0824) loss: 0.8244 (0.8235) time: 0.1686 data: 0.0923 max mem: 9390 +Train: [43] [6200/6250] eta: 0:00:07 lr: 0.000080 grad: 0.0831 (0.0824) loss: 0.8252 (0.8234) time: 0.1509 data: 0.0657 max mem: 9390 +Train: [43] [6249/6250] eta: 0:00:00 lr: 0.000080 grad: 0.0777 (0.0824) loss: 0.8279 (0.8234) time: 0.1604 data: 0.0845 max mem: 9390 +Train: [43] Total time: 0:15:14 (0.1463 s / it) +Averaged stats: lr: 0.000080 grad: 0.0777 (0.0824) loss: 0.8279 (0.8234) +Eval (hcp-train-subset): [43] [ 0/62] eta: 0:04:59 loss: 0.8483 (0.8483) time: 4.8280 data: 4.7951 max mem: 9390 +Eval (hcp-train-subset): [43] [61/62] eta: 0:00:00 loss: 0.8372 (0.8390) time: 0.1255 data: 0.1006 max mem: 9390 +Eval (hcp-train-subset): [43] Total time: 0:00:13 (0.2116 s / it) +Averaged stats (hcp-train-subset): loss: 0.8372 (0.8390) +Eval (hcp-val): [43] [ 0/62] eta: 0:03:29 loss: 0.8336 (0.8336) time: 3.3772 data: 3.3232 max mem: 9390 +Eval (hcp-val): [43] [61/62] eta: 0:00:00 loss: 0.8357 (0.8366) time: 0.1264 data: 0.1016 max mem: 9390 +Eval (hcp-val): [43] Total time: 0:00:12 (0.2042 s / it) +Averaged stats (hcp-val): loss: 0.8357 (0.8366) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +Train: [44] [ 0/6250] eta: 7:53:05 lr: 0.000080 grad: 0.0992 (0.0992) loss: 0.8634 (0.8634) time: 4.5417 data: 4.3025 max mem: 9390 +Train: [44] [ 100/6250] eta: 0:21:20 lr: 0.000080 grad: 0.0837 (0.1017) loss: 0.8280 (0.8322) time: 0.1568 data: 0.0650 max mem: 9390 +Train: [44] [ 200/6250] eta: 0:18:03 lr: 0.000080 grad: 0.0856 (0.0968) loss: 0.8156 (0.8276) time: 0.1376 data: 0.0572 max mem: 9390 +Train: [44] [ 300/6250] eta: 0:16:44 lr: 0.000080 grad: 0.0796 (0.0918) loss: 0.8238 (0.8274) time: 0.1597 data: 0.0774 max mem: 9390 +Train: [44] [ 400/6250] eta: 0:15:38 lr: 0.000080 grad: 0.0767 (0.0888) loss: 0.8224 (0.8266) time: 0.1223 data: 0.0334 max mem: 9390 +Train: [44] [ 500/6250] eta: 0:14:56 lr: 0.000080 grad: 0.0819 (0.0875) loss: 0.8265 (0.8259) time: 0.1477 data: 0.0668 max mem: 9390 +Train: [44] [ 600/6250] eta: 0:14:11 lr: 0.000080 grad: 0.0845 (0.0873) loss: 0.8184 (0.8249) time: 0.1116 data: 0.0214 max mem: 9390 +Train: [44] [ 700/6250] eta: 0:13:41 lr: 0.000080 grad: 0.0802 (0.0864) loss: 0.8168 (0.8246) time: 0.1179 data: 0.0293 max mem: 9390 +Train: [44] [ 800/6250] eta: 0:13:21 lr: 0.000080 grad: 0.0785 (0.0856) loss: 0.8262 (0.8244) time: 0.1461 data: 0.0627 max mem: 9390 +Train: [44] [ 900/6250] eta: 0:12:58 lr: 0.000080 grad: 0.0768 (0.0849) loss: 0.8238 (0.8242) time: 0.1335 data: 0.0461 max mem: 9390 +Train: [44] [1000/6250] eta: 0:12:50 lr: 0.000080 grad: 0.0810 (0.0845) loss: 0.8207 (0.8242) time: 0.1708 data: 0.0830 max mem: 9390 +Train: [44] [1100/6250] eta: 0:12:27 lr: 0.000079 grad: 0.0744 (0.0839) loss: 0.8299 (0.8244) time: 0.1288 data: 0.0474 max mem: 9390 +Train: [44] [1200/6250] eta: 0:12:07 lr: 0.000079 grad: 0.0799 (0.0836) loss: 0.8227 (0.8242) time: 0.1385 data: 0.0638 max mem: 9390 +Train: [44] [1300/6250] eta: 0:11:50 lr: 0.000079 grad: 0.0821 (0.0835) loss: 0.8187 (0.8241) time: 0.1496 data: 0.0689 max mem: 9390 +Train: [44] [1400/6250] eta: 0:11:35 lr: 0.000079 grad: 0.0811 (0.0833) loss: 0.8259 (0.8241) time: 0.1589 data: 0.0838 max mem: 9390 +Train: [44] [1500/6250] eta: 0:11:20 lr: 0.000079 grad: 0.0821 (0.0831) loss: 0.8214 (0.8241) time: 0.1408 data: 0.0627 max mem: 9390 +Train: [44] [1600/6250] eta: 0:11:11 lr: 0.000079 grad: 0.0842 (0.0831) loss: 0.8210 (0.8239) time: 0.1288 data: 0.0531 max mem: 9390 +Train: [44] [1700/6250] eta: 0:10:55 lr: 0.000079 grad: 0.0753 (0.0829) loss: 0.8251 (0.8240) time: 0.1418 data: 0.0634 max mem: 9390 +Train: [44] [1800/6250] eta: 0:10:44 lr: 0.000079 grad: 0.0762 (0.0829) loss: 0.8303 (0.8240) time: 0.1280 data: 0.0520 max mem: 9390 +Train: [44] [1900/6250] eta: 0:10:29 lr: 0.000079 grad: 0.0801 (0.0829) loss: 0.8256 (0.8240) time: 0.1555 data: 0.0804 max mem: 9390 +Train: [44] [2000/6250] eta: 0:10:13 lr: 0.000079 grad: 0.0822 (0.0829) loss: 0.8209 (0.8241) time: 0.1107 data: 0.0284 max mem: 9390 +Train: [44] [2100/6250] eta: 0:09:56 lr: 0.000079 grad: 0.0847 (0.0828) loss: 0.8245 (0.8242) time: 0.1356 data: 0.0545 max mem: 9390 +Train: [44] [2200/6250] eta: 0:09:38 lr: 0.000079 grad: 0.0769 (0.0828) loss: 0.8276 (0.8242) time: 0.1199 data: 0.0435 max mem: 9390 +Train: [44] [2300/6250] eta: 0:09:20 lr: 0.000079 grad: 0.0737 (0.0826) loss: 0.8272 (0.8242) time: 0.1154 data: 0.0318 max mem: 9390 +Train: [44] [2400/6250] eta: 0:09:02 lr: 0.000079 grad: 0.0815 (0.0826) loss: 0.8219 (0.8243) time: 0.1347 data: 0.0503 max mem: 9390 +Train: [44] [2500/6250] eta: 0:08:45 lr: 0.000079 grad: 0.0751 (0.0826) loss: 0.8252 (0.8243) time: 0.1137 data: 0.0333 max mem: 9390 +Train: [44] [2600/6250] eta: 0:08:28 lr: 0.000079 grad: 0.0785 (0.0826) loss: 0.8283 (0.8242) time: 0.1375 data: 0.0555 max mem: 9390 +Train: [44] [2700/6250] eta: 0:08:14 lr: 0.000079 grad: 0.0808 (0.0826) loss: 0.8165 (0.8241) time: 0.1979 data: 0.1206 max mem: 9390 +Train: [44] [2800/6250] eta: 0:07:59 lr: 0.000079 grad: 0.0785 (0.0825) loss: 0.8225 (0.8241) time: 0.1083 data: 0.0288 max mem: 9390 +Train: [44] [2900/6250] eta: 0:07:44 lr: 0.000079 grad: 0.0810 (0.0826) loss: 0.8219 (0.8240) time: 0.1206 data: 0.0284 max mem: 9390 +Train: [44] [3000/6250] eta: 0:07:30 lr: 0.000079 grad: 0.0810 (0.0825) loss: 0.8237 (0.8240) time: 0.1396 data: 0.0622 max mem: 9390 +Train: [44] [3100/6250] eta: 0:07:17 lr: 0.000079 grad: 0.0765 (0.0824) loss: 0.8281 (0.8240) time: 0.1506 data: 0.0764 max mem: 9390 +Train: [44] [3200/6250] eta: 0:07:02 lr: 0.000079 grad: 0.0770 (0.0824) loss: 0.8244 (0.8240) time: 0.1519 data: 0.0743 max mem: 9390 +Train: [44] [3300/6250] eta: 0:06:47 lr: 0.000079 grad: 0.0763 (0.0823) loss: 0.8226 (0.8241) time: 0.1307 data: 0.0507 max mem: 9390 +Train: [44] [3400/6250] eta: 0:06:33 lr: 0.000079 grad: 0.0793 (0.0822) loss: 0.8214 (0.8241) time: 0.1370 data: 0.0577 max mem: 9390 +Train: [44] [3500/6250] eta: 0:06:19 lr: 0.000079 grad: 0.0853 (0.0822) loss: 0.8248 (0.8241) time: 0.1694 data: 0.0937 max mem: 9390 +Train: [44] [3600/6250] eta: 0:06:05 lr: 0.000079 grad: 0.0744 (0.0822) loss: 0.8254 (0.8240) time: 0.1422 data: 0.0615 max mem: 9390 +Train: [44] [3700/6250] eta: 0:05:52 lr: 0.000079 grad: 0.0757 (0.0821) loss: 0.8277 (0.8240) time: 0.1536 data: 0.0680 max mem: 9390 +Train: [44] [3800/6250] eta: 0:05:39 lr: 0.000079 grad: 0.0743 (0.0821) loss: 0.8267 (0.8241) time: 0.1403 data: 0.0523 max mem: 9390 +Train: [44] [3900/6250] eta: 0:05:26 lr: 0.000079 grad: 0.0771 (0.0820) loss: 0.8202 (0.8241) time: 0.1467 data: 0.0612 max mem: 9390 +Train: [44] [4000/6250] eta: 0:05:13 lr: 0.000079 grad: 0.0752 (0.0820) loss: 0.8248 (0.8241) time: 0.1551 data: 0.0718 max mem: 9390 +Train: [44] [4100/6250] eta: 0:04:59 lr: 0.000079 grad: 0.0799 (0.0820) loss: 0.8183 (0.8241) time: 0.1616 data: 0.0729 max mem: 9390 +Train: [44] [4200/6250] eta: 0:04:46 lr: 0.000078 grad: 0.0781 (0.0820) loss: 0.8336 (0.8240) time: 0.1461 data: 0.0651 max mem: 9390 +Train: [44] [4300/6250] eta: 0:04:32 lr: 0.000078 grad: 0.0908 (0.0820) loss: 0.8232 (0.8240) time: 0.1453 data: 0.0662 max mem: 9390 +Train: [44] [4400/6250] eta: 0:04:18 lr: 0.000078 grad: 0.0840 (0.0821) loss: 0.8183 (0.8239) time: 0.1406 data: 0.0564 max mem: 9390 +Train: [44] [4500/6250] eta: 0:04:04 lr: 0.000078 grad: 0.0783 (0.0821) loss: 0.8267 (0.8239) time: 0.1508 data: 0.0732 max mem: 9390 +Train: [44] [4600/6250] eta: 0:03:50 lr: 0.000078 grad: 0.0819 (0.0821) loss: 0.8220 (0.8238) time: 0.1610 data: 0.0794 max mem: 9390 +Train: [44] [4700/6250] eta: 0:03:36 lr: 0.000078 grad: 0.0783 (0.0821) loss: 0.8251 (0.8238) time: 0.1576 data: 0.0736 max mem: 9390 +Train: [44] [4800/6250] eta: 0:03:22 lr: 0.000078 grad: 0.0765 (0.0821) loss: 0.8232 (0.8238) time: 0.1512 data: 0.0731 max mem: 9390 +Train: [44] [4900/6250] eta: 0:03:08 lr: 0.000078 grad: 0.0756 (0.0821) loss: 0.8284 (0.8238) time: 0.1287 data: 0.0498 max mem: 9390 +Train: [44] [5000/6250] eta: 0:02:54 lr: 0.000078 grad: 0.0803 (0.0821) loss: 0.8232 (0.8238) time: 0.1695 data: 0.0883 max mem: 9390 +Train: [44] [5100/6250] eta: 0:02:40 lr: 0.000078 grad: 0.0791 (0.0821) loss: 0.8249 (0.8238) time: 0.1274 data: 0.0403 max mem: 9390 +Train: [44] [5200/6250] eta: 0:02:26 lr: 0.000078 grad: 0.0810 (0.0821) loss: 0.8259 (0.8239) time: 0.1279 data: 0.0482 max mem: 9390 +Train: [44] [5300/6250] eta: 0:02:13 lr: 0.000078 grad: 0.0822 (0.0822) loss: 0.8220 (0.8239) time: 0.1496 data: 0.0684 max mem: 9390 +Train: [44] [5400/6250] eta: 0:01:59 lr: 0.000078 grad: 0.0810 (0.0822) loss: 0.8249 (0.8239) time: 0.1636 data: 0.0745 max mem: 9390 +Train: [44] [5500/6250] eta: 0:01:45 lr: 0.000078 grad: 0.0850 (0.0823) loss: 0.8203 (0.8238) time: 0.1505 data: 0.0684 max mem: 9390 +Train: [44] [5600/6250] eta: 0:01:31 lr: 0.000078 grad: 0.0851 (0.0824) loss: 0.8158 (0.8237) time: 0.1456 data: 0.0682 max mem: 9390 +Train: [44] [5700/6250] eta: 0:01:17 lr: 0.000078 grad: 0.0823 (0.0824) loss: 0.8117 (0.8237) time: 0.1738 data: 0.0852 max mem: 9390 +Train: [44] [5800/6250] eta: 0:01:03 lr: 0.000078 grad: 0.0875 (0.0824) loss: 0.8192 (0.8236) time: 0.1274 data: 0.0359 max mem: 9390 +Train: [44] [5900/6250] eta: 0:00:49 lr: 0.000078 grad: 0.0775 (0.0825) loss: 0.8195 (0.8236) time: 0.1305 data: 0.0515 max mem: 9390 +Train: [44] [6000/6250] eta: 0:00:35 lr: 0.000078 grad: 0.0837 (0.0825) loss: 0.8187 (0.8235) time: 0.1671 data: 0.0616 max mem: 9390 +Train: [44] [6100/6250] eta: 0:00:21 lr: 0.000078 grad: 0.0822 (0.0826) loss: 0.8178 (0.8235) time: 0.1016 data: 0.0224 max mem: 9390 +Train: [44] [6200/6250] eta: 0:00:07 lr: 0.000078 grad: 0.0742 (0.0826) loss: 0.8235 (0.8235) time: 0.1354 data: 0.0558 max mem: 9390 +Train: [44] [6249/6250] eta: 0:00:00 lr: 0.000078 grad: 0.0850 (0.0826) loss: 0.8229 (0.8234) time: 0.2798 data: 0.2021 max mem: 9390 +Train: [44] Total time: 0:14:48 (0.1421 s / it) +Averaged stats: lr: 0.000078 grad: 0.0850 (0.0826) loss: 0.8229 (0.8234) +Eval (hcp-train-subset): [44] [ 0/62] eta: 0:03:27 loss: 0.8494 (0.8494) time: 3.3480 data: 3.2759 max mem: 9390 +Eval (hcp-train-subset): [44] [61/62] eta: 0:00:00 loss: 0.8377 (0.8390) time: 0.1090 data: 0.0843 max mem: 9390 +Eval (hcp-train-subset): [44] Total time: 0:00:11 (0.1927 s / it) +Averaged stats (hcp-train-subset): loss: 0.8377 (0.8390) +Making plots (hcp-train-subset): example=30 +Eval (hcp-val): [44] [ 0/62] eta: 0:04:47 loss: 0.8350 (0.8350) time: 4.6340 data: 4.6017 max mem: 9390 +Eval (hcp-val): [44] [61/62] eta: 0:00:00 loss: 0.8350 (0.8362) time: 0.1208 data: 0.0961 max mem: 9390 +Eval (hcp-val): [44] Total time: 0:00:12 (0.2005 s / it) +Averaged stats (hcp-val): loss: 0.8350 (0.8362) +Making plots (hcp-val): example=33 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +Train: [45] [ 0/6250] eta: 7:59:49 lr: 0.000078 grad: 0.0984 (0.0984) loss: 0.8589 (0.8589) time: 4.6063 data: 4.4375 max mem: 9390 +Train: [45] [ 100/6250] eta: 0:19:50 lr: 0.000078 grad: 0.0832 (0.0893) loss: 0.8333 (0.8359) time: 0.1536 data: 0.0566 max mem: 9390 +Train: [45] [ 200/6250] eta: 0:17:19 lr: 0.000078 grad: 0.0754 (0.0836) loss: 0.8358 (0.8347) time: 0.1357 data: 0.0551 max mem: 9390 +Train: [45] [ 300/6250] eta: 0:16:05 lr: 0.000078 grad: 0.0813 (0.0827) loss: 0.8285 (0.8330) time: 0.1276 data: 0.0419 max mem: 9390 +Train: [45] [ 400/6250] eta: 0:15:15 lr: 0.000078 grad: 0.0807 (0.0825) loss: 0.8241 (0.8312) time: 0.1513 data: 0.0723 max mem: 9390 +Train: [45] [ 500/6250] eta: 0:14:33 lr: 0.000078 grad: 0.0749 (0.0824) loss: 0.8256 (0.8296) time: 0.1321 data: 0.0496 max mem: 9390 +Train: [45] [ 600/6250] eta: 0:13:58 lr: 0.000078 grad: 0.0819 (0.0825) loss: 0.8272 (0.8286) time: 0.1316 data: 0.0521 max mem: 9390 +Train: [45] [ 700/6250] eta: 0:13:23 lr: 0.000078 grad: 0.0824 (0.0829) loss: 0.8239 (0.8275) time: 0.1059 data: 0.0129 max mem: 9390 +Train: [45] [ 800/6250] eta: 0:12:52 lr: 0.000078 grad: 0.0822 (0.0828) loss: 0.8218 (0.8269) time: 0.1123 data: 0.0284 max mem: 9390 +Train: [45] [ 900/6250] eta: 0:12:26 lr: 0.000078 grad: 0.0798 (0.0826) loss: 0.8286 (0.8269) time: 0.1214 data: 0.0352 max mem: 9390 +Train: [45] [1000/6250] eta: 0:12:04 lr: 0.000078 grad: 0.0746 (0.0826) loss: 0.8308 (0.8267) time: 0.1111 data: 0.0297 max mem: 9390 +Train: [45] [1100/6250] eta: 0:11:48 lr: 0.000077 grad: 0.0811 (0.0824) loss: 0.8222 (0.8265) time: 0.1211 data: 0.0455 max mem: 9390 +Train: [45] [1200/6250] eta: 0:11:33 lr: 0.000077 grad: 0.0786 (0.0824) loss: 0.8221 (0.8260) time: 0.1349 data: 0.0528 max mem: 9390 +Train: [45] [1300/6250] eta: 0:11:15 lr: 0.000077 grad: 0.0805 (0.0826) loss: 0.8227 (0.8255) time: 0.1254 data: 0.0483 max mem: 9390 +Train: [45] [1400/6250] eta: 0:10:58 lr: 0.000077 grad: 0.0800 (0.0825) loss: 0.8228 (0.8253) time: 0.1177 data: 0.0289 max mem: 9390 +Train: [45] [1500/6250] eta: 0:10:47 lr: 0.000077 grad: 0.0839 (0.0827) loss: 0.8142 (0.8249) time: 0.1263 data: 0.0467 max mem: 9390 +Train: [45] [1600/6250] eta: 0:10:39 lr: 0.000077 grad: 0.0788 (0.0827) loss: 0.8201 (0.8245) time: 0.1776 data: 0.1041 max mem: 9390 +Train: [45] [1700/6250] eta: 0:10:27 lr: 0.000077 grad: 0.0801 (0.0828) loss: 0.8208 (0.8242) time: 0.1404 data: 0.0632 max mem: 9390 +Train: [45] [1800/6250] eta: 0:10:12 lr: 0.000077 grad: 0.0815 (0.0830) loss: 0.8193 (0.8239) time: 0.1297 data: 0.0544 max mem: 9390 +Train: [45] [1900/6250] eta: 0:10:00 lr: 0.000077 grad: 0.0823 (0.0831) loss: 0.8154 (0.8236) time: 0.1253 data: 0.0410 max mem: 9390 +Train: [45] [2000/6250] eta: 0:09:47 lr: 0.000077 grad: 0.0832 (0.0831) loss: 0.8188 (0.8235) time: 0.1699 data: 0.0785 max mem: 9390 +Train: [45] [2100/6250] eta: 0:09:33 lr: 0.000077 grad: 0.0867 (0.0832) loss: 0.8126 (0.8234) time: 0.1312 data: 0.0410 max mem: 9390 +Train: [45] [2200/6250] eta: 0:09:20 lr: 0.000077 grad: 0.0823 (0.0832) loss: 0.8185 (0.8233) time: 0.1301 data: 0.0448 max mem: 9390 +Train: [45] [2300/6250] eta: 0:09:05 lr: 0.000077 grad: 0.0864 (0.0833) loss: 0.8175 (0.8231) time: 0.1062 data: 0.0264 max mem: 9390 +Train: [45] [2400/6250] eta: 0:08:49 lr: 0.000077 grad: 0.0876 (0.0834) loss: 0.8195 (0.8229) time: 0.1237 data: 0.0337 max mem: 9390 +Train: [45] [2500/6250] eta: 0:08:32 lr: 0.000077 grad: 0.0831 (0.0835) loss: 0.8160 (0.8229) time: 0.1106 data: 0.0280 max mem: 9390 +Train: [45] [2600/6250] eta: 0:08:16 lr: 0.000077 grad: 0.0796 (0.0835) loss: 0.8243 (0.8228) time: 0.1223 data: 0.0465 max mem: 9390 +Train: [45] [2700/6250] eta: 0:08:00 lr: 0.000077 grad: 0.0850 (0.0836) loss: 0.8218 (0.8228) time: 0.1363 data: 0.0585 max mem: 9390 +Train: [45] [2800/6250] eta: 0:07:44 lr: 0.000077 grad: 0.0818 (0.0836) loss: 0.8193 (0.8228) time: 0.1324 data: 0.0588 max mem: 9390 +Train: [45] [2900/6250] eta: 0:07:30 lr: 0.000077 grad: 0.0788 (0.0837) loss: 0.8209 (0.8227) time: 0.1380 data: 0.0575 max mem: 9390 +Train: [45] [3000/6250] eta: 0:07:17 lr: 0.000077 grad: 0.0802 (0.0837) loss: 0.8256 (0.8227) time: 0.1476 data: 0.0607 max mem: 9390 +Train: [45] [3100/6250] eta: 0:07:03 lr: 0.000077 grad: 0.0831 (0.0838) loss: 0.8244 (0.8227) time: 0.1291 data: 0.0502 max mem: 9390 +Train: [45] [3200/6250] eta: 0:06:49 lr: 0.000077 grad: 0.0854 (0.0838) loss: 0.8204 (0.8227) time: 0.1182 data: 0.0409 max mem: 9390 +Train: [45] [3300/6250] eta: 0:06:35 lr: 0.000077 grad: 0.0770 (0.0839) loss: 0.8246 (0.8227) time: 0.1521 data: 0.0813 max mem: 9390 +Train: [45] [3400/6250] eta: 0:06:21 lr: 0.000077 grad: 0.0810 (0.0839) loss: 0.8200 (0.8227) time: 0.1269 data: 0.0501 max mem: 9390 +Train: [45] [3500/6250] eta: 0:06:07 lr: 0.000077 grad: 0.0904 (0.0840) loss: 0.8187 (0.8226) time: 0.1191 data: 0.0378 max mem: 9390 +Train: [45] [3600/6250] eta: 0:05:53 lr: 0.000077 grad: 0.0851 (0.0842) loss: 0.8219 (0.8226) time: 0.1122 data: 0.0274 max mem: 9390 +Train: [45] [3700/6250] eta: 0:05:39 lr: 0.000077 grad: 0.0848 (0.0842) loss: 0.8164 (0.8225) time: 0.1215 data: 0.0437 max mem: 9390 +Train: [45] [3800/6250] eta: 0:05:25 lr: 0.000077 grad: 0.0839 (0.0842) loss: 0.8237 (0.8225) time: 0.1241 data: 0.0493 max mem: 9390 +Train: [45] [3900/6250] eta: 0:05:12 lr: 0.000077 grad: 0.0848 (0.0842) loss: 0.8162 (0.8225) time: 0.1230 data: 0.0462 max mem: 9390 +Train: [45] [4000/6250] eta: 0:05:00 lr: 0.000077 grad: 0.0840 (0.0842) loss: 0.8211 (0.8226) time: 0.1183 data: 0.0354 max mem: 9390 +Train: [45] [4100/6250] eta: 0:04:48 lr: 0.000077 grad: 0.0851 (0.0842) loss: 0.8213 (0.8226) time: 0.1472 data: 0.0596 max mem: 9390 +Train: [45] [4200/6250] eta: 0:04:35 lr: 0.000076 grad: 0.0812 (0.0843) loss: 0.8252 (0.8225) time: 0.1333 data: 0.0491 max mem: 9390 +Train: [45] [4300/6250] eta: 0:04:22 lr: 0.000076 grad: 0.0812 (0.0843) loss: 0.8245 (0.8226) time: 0.1399 data: 0.0551 max mem: 9390 +Train: [45] [4400/6250] eta: 0:04:09 lr: 0.000076 grad: 0.0842 (0.0843) loss: 0.8168 (0.8225) time: 0.1435 data: 0.0491 max mem: 9390 +Train: [45] [4500/6250] eta: 0:03:57 lr: 0.000076 grad: 0.0830 (0.0844) loss: 0.8188 (0.8224) time: 0.1565 data: 0.0733 max mem: 9390 +Train: [45] [4600/6250] eta: 0:03:44 lr: 0.000076 grad: 0.0820 (0.0844) loss: 0.8157 (0.8224) time: 0.1739 data: 0.0921 max mem: 9390 +Train: [45] [4700/6250] eta: 0:03:30 lr: 0.000076 grad: 0.0784 (0.0844) loss: 0.8227 (0.8224) time: 0.1390 data: 0.0598 max mem: 9390 +Train: [45] [4800/6250] eta: 0:03:17 lr: 0.000076 grad: 0.0817 (0.0843) loss: 0.8198 (0.8224) time: 0.1471 data: 0.0726 max mem: 9390 +Train: [45] [4900/6250] eta: 0:03:04 lr: 0.000076 grad: 0.0791 (0.0844) loss: 0.8255 (0.8224) time: 0.1463 data: 0.0623 max mem: 9390 +Train: [45] [5000/6250] eta: 0:02:50 lr: 0.000076 grad: 0.0836 (0.0843) loss: 0.8250 (0.8224) time: 0.1655 data: 0.0759 max mem: 9390 +Train: [45] [5100/6250] eta: 0:02:37 lr: 0.000076 grad: 0.0782 (0.0843) loss: 0.8280 (0.8224) time: 0.1599 data: 0.0551 max mem: 9390 +Train: [45] [5200/6250] eta: 0:02:23 lr: 0.000076 grad: 0.0792 (0.0843) loss: 0.8259 (0.8225) time: 0.1331 data: 0.0435 max mem: 9390 +Train: [45] [5300/6250] eta: 0:02:10 lr: 0.000076 grad: 0.0815 (0.0843) loss: 0.8271 (0.8225) time: 0.1443 data: 0.0639 max mem: 9390 +Train: [45] [5400/6250] eta: 0:01:56 lr: 0.000076 grad: 0.0863 (0.0843) loss: 0.8222 (0.8225) time: 0.1206 data: 0.0432 max mem: 9390 +Train: [45] [5500/6250] eta: 0:01:43 lr: 0.000076 grad: 0.0843 (0.0844) loss: 0.8202 (0.8225) time: 0.1539 data: 0.0736 max mem: 9390 +Train: [45] [5600/6250] eta: 0:01:29 lr: 0.000076 grad: 0.0843 (0.0844) loss: 0.8229 (0.8225) time: 0.1388 data: 0.0675 max mem: 9390 +Train: [45] [5700/6250] eta: 0:01:15 lr: 0.000076 grad: 0.0852 (0.0844) loss: 0.8177 (0.8225) time: 0.1463 data: 0.0655 max mem: 9390 +Train: [45] [5800/6250] eta: 0:01:01 lr: 0.000076 grad: 0.0821 (0.0844) loss: 0.8262 (0.8225) time: 0.1470 data: 0.0628 max mem: 9390 +Train: [45] [5900/6250] eta: 0:00:48 lr: 0.000076 grad: 0.0901 (0.0845) loss: 0.8174 (0.8224) time: 0.1435 data: 0.0690 max mem: 9390 +Train: [45] [6000/6250] eta: 0:00:34 lr: 0.000076 grad: 0.0866 (0.0846) loss: 0.8173 (0.8224) time: 0.1354 data: 0.0572 max mem: 9390 +Train: [45] [6100/6250] eta: 0:00:20 lr: 0.000076 grad: 0.0873 (0.0846) loss: 0.8223 (0.8224) time: 0.1685 data: 0.0905 max mem: 9390 +Train: [45] [6200/6250] eta: 0:00:06 lr: 0.000076 grad: 0.0782 (0.0846) loss: 0.8204 (0.8224) time: 0.1498 data: 0.0623 max mem: 9390 +Train: [45] [6249/6250] eta: 0:00:00 lr: 0.000076 grad: 0.0817 (0.0846) loss: 0.8242 (0.8224) time: 0.1692 data: 0.0874 max mem: 9390 +Train: [45] Total time: 0:14:29 (0.1392 s / it) +Averaged stats: lr: 0.000076 grad: 0.0817 (0.0846) loss: 0.8242 (0.8224) +Eval (hcp-train-subset): [45] [ 0/62] eta: 0:03:35 loss: 0.8444 (0.8444) time: 3.4688 data: 3.3989 max mem: 9390 +Eval (hcp-train-subset): [45] [61/62] eta: 0:00:00 loss: 0.8369 (0.8389) time: 0.1108 data: 0.0860 max mem: 9390 +Eval (hcp-train-subset): [45] Total time: 0:00:13 (0.2123 s / it) +Averaged stats (hcp-train-subset): loss: 0.8369 (0.8389) +Eval (hcp-val): [45] [ 0/62] eta: 0:03:33 loss: 0.8340 (0.8340) time: 3.4467 data: 3.3778 max mem: 9390 +Eval (hcp-val): [45] [61/62] eta: 0:00:00 loss: 0.8370 (0.8370) time: 0.1269 data: 0.1005 max mem: 9390 +Eval (hcp-val): [45] Total time: 0:00:12 (0.2000 s / it) +Averaged stats (hcp-val): loss: 0.8370 (0.8370) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +Train: [46] [ 0/6250] eta: 7:26:03 lr: 0.000076 grad: 0.2086 (0.2086) loss: 0.8287 (0.8287) time: 4.2822 data: 4.0058 max mem: 9390 +Train: [46] [ 100/6250] eta: 0:20:14 lr: 0.000076 grad: 0.0826 (0.0919) loss: 0.8363 (0.8382) time: 0.1467 data: 0.0571 max mem: 9390 +Train: [46] [ 200/6250] eta: 0:17:25 lr: 0.000076 grad: 0.0774 (0.0879) loss: 0.8372 (0.8376) time: 0.1389 data: 0.0503 max mem: 9390 +Train: [46] [ 300/6250] eta: 0:16:00 lr: 0.000076 grad: 0.0818 (0.0857) loss: 0.8298 (0.8356) time: 0.1388 data: 0.0583 max mem: 9390 +Train: [46] [ 400/6250] eta: 0:15:11 lr: 0.000076 grad: 0.0838 (0.0850) loss: 0.8187 (0.8327) time: 0.1285 data: 0.0449 max mem: 9390 +Train: [46] [ 500/6250] eta: 0:14:32 lr: 0.000076 grad: 0.0786 (0.0847) loss: 0.8254 (0.8305) time: 0.1387 data: 0.0602 max mem: 9390 +Train: [46] [ 600/6250] eta: 0:13:50 lr: 0.000076 grad: 0.0791 (0.0841) loss: 0.8248 (0.8289) time: 0.1287 data: 0.0500 max mem: 9390 +Train: [46] [ 700/6250] eta: 0:13:21 lr: 0.000076 grad: 0.0800 (0.0844) loss: 0.8219 (0.8276) time: 0.1176 data: 0.0338 max mem: 9390 +Train: [46] [ 800/6250] eta: 0:12:52 lr: 0.000076 grad: 0.0824 (0.0841) loss: 0.8210 (0.8267) time: 0.1225 data: 0.0353 max mem: 9390 +Train: [46] [ 900/6250] eta: 0:12:29 lr: 0.000076 grad: 0.0825 (0.0841) loss: 0.8182 (0.8258) time: 0.1294 data: 0.0472 max mem: 9390 +Train: [46] [1000/6250] eta: 0:12:07 lr: 0.000076 grad: 0.0833 (0.0841) loss: 0.8222 (0.8251) time: 0.1261 data: 0.0470 max mem: 9390 +Train: [46] [1100/6250] eta: 0:11:46 lr: 0.000075 grad: 0.0818 (0.0841) loss: 0.8206 (0.8247) time: 0.1329 data: 0.0543 max mem: 9390 +Train: [46] [1200/6250] eta: 0:11:28 lr: 0.000075 grad: 0.0848 (0.0843) loss: 0.8163 (0.8241) time: 0.1162 data: 0.0355 max mem: 9390 +Train: [46] [1300/6250] eta: 0:11:12 lr: 0.000075 grad: 0.0875 (0.0846) loss: 0.8159 (0.8236) time: 0.1324 data: 0.0566 max mem: 9390 +Train: [46] [1400/6250] eta: 0:10:57 lr: 0.000075 grad: 0.0821 (0.0847) loss: 0.8159 (0.8231) time: 0.1208 data: 0.0437 max mem: 9390 +Train: [46] [1500/6250] eta: 0:10:42 lr: 0.000075 grad: 0.0802 (0.0847) loss: 0.8170 (0.8228) time: 0.1296 data: 0.0534 max mem: 9390 +Train: [46] [1600/6250] eta: 0:10:27 lr: 0.000075 grad: 0.0810 (0.0847) loss: 0.8167 (0.8226) time: 0.1163 data: 0.0370 max mem: 9390 +Train: [46] [1700/6250] eta: 0:10:20 lr: 0.000075 grad: 0.0833 (0.0847) loss: 0.8209 (0.8224) time: 0.1609 data: 0.0845 max mem: 9390 +Train: [46] [1800/6250] eta: 0:10:09 lr: 0.000075 grad: 0.0816 (0.0847) loss: 0.8188 (0.8222) time: 0.1526 data: 0.0712 max mem: 9390 +Train: [46] [1900/6250] eta: 0:09:56 lr: 0.000075 grad: 0.0890 (0.0850) loss: 0.8182 (0.8220) time: 0.1519 data: 0.0737 max mem: 9390 +Train: [46] [2000/6250] eta: 0:09:45 lr: 0.000075 grad: 0.0826 (0.0853) loss: 0.8233 (0.8219) time: 0.1459 data: 0.0654 max mem: 9390 +Train: [46] [2100/6250] eta: 0:09:32 lr: 0.000075 grad: 0.0751 (0.0853) loss: 0.8243 (0.8219) time: 0.1319 data: 0.0490 max mem: 9390 +Train: [46] [2200/6250] eta: 0:09:20 lr: 0.000075 grad: 0.0848 (0.0853) loss: 0.8187 (0.8219) time: 0.1442 data: 0.0593 max mem: 9390 +Train: [46] [2300/6250] eta: 0:09:05 lr: 0.000075 grad: 0.0785 (0.0852) loss: 0.8266 (0.8219) time: 0.1230 data: 0.0430 max mem: 9390 +Train: [46] [2400/6250] eta: 0:08:49 lr: 0.000075 grad: 0.0838 (0.0850) loss: 0.8165 (0.8219) time: 0.1082 data: 0.0268 max mem: 9390 +Train: [46] [2500/6250] eta: 0:08:33 lr: 0.000075 grad: 0.0757 (0.0850) loss: 0.8290 (0.8219) time: 0.1078 data: 0.0209 max mem: 9390 +Train: [46] [2600/6250] eta: 0:08:16 lr: 0.000075 grad: 0.0786 (0.0849) loss: 0.8257 (0.8219) time: 0.1064 data: 0.0290 max mem: 9390 +Train: [46] [2700/6250] eta: 0:08:00 lr: 0.000075 grad: 0.0796 (0.0848) loss: 0.8280 (0.8220) time: 0.1064 data: 0.0269 max mem: 9390 +Train: [46] [2800/6250] eta: 0:07:44 lr: 0.000075 grad: 0.0792 (0.0847) loss: 0.8169 (0.8220) time: 0.1229 data: 0.0405 max mem: 9390 +Train: [46] [2900/6250] eta: 0:07:28 lr: 0.000075 grad: 0.0769 (0.0846) loss: 0.8248 (0.8221) time: 0.1162 data: 0.0324 max mem: 9390 +Train: [46] [3000/6250] eta: 0:07:13 lr: 0.000075 grad: 0.0808 (0.0845) loss: 0.8225 (0.8222) time: 0.1249 data: 0.0520 max mem: 9390 +Train: [46] [3100/6250] eta: 0:06:58 lr: 0.000075 grad: 0.0818 (0.0845) loss: 0.8272 (0.8223) time: 0.1132 data: 0.0373 max mem: 9390 +Train: [46] [3200/6250] eta: 0:06:44 lr: 0.000075 grad: 0.0837 (0.0845) loss: 0.8222 (0.8223) time: 0.1246 data: 0.0413 max mem: 9390 +Train: [46] [3300/6250] eta: 0:06:30 lr: 0.000075 grad: 0.0854 (0.0845) loss: 0.8231 (0.8223) time: 0.1271 data: 0.0491 max mem: 9390 +Train: [46] [3400/6250] eta: 0:06:16 lr: 0.000075 grad: 0.0775 (0.0845) loss: 0.8295 (0.8223) time: 0.1229 data: 0.0444 max mem: 9390 +Train: [46] [3500/6250] eta: 0:06:03 lr: 0.000075 grad: 0.0794 (0.0845) loss: 0.8228 (0.8223) time: 0.1259 data: 0.0470 max mem: 9390 +Train: [46] [3600/6250] eta: 0:05:50 lr: 0.000075 grad: 0.0854 (0.0846) loss: 0.8154 (0.8223) time: 0.1164 data: 0.0412 max mem: 9390 +Train: [46] [3700/6250] eta: 0:05:36 lr: 0.000075 grad: 0.0804 (0.0846) loss: 0.8245 (0.8224) time: 0.1471 data: 0.0699 max mem: 9390 +Train: [46] [3800/6250] eta: 0:05:22 lr: 0.000075 grad: 0.0826 (0.0846) loss: 0.8155 (0.8223) time: 0.1307 data: 0.0445 max mem: 9390 +Train: [46] [3900/6250] eta: 0:05:09 lr: 0.000075 grad: 0.0844 (0.0847) loss: 0.8204 (0.8222) time: 0.1330 data: 0.0534 max mem: 9390 +Train: [46] [4000/6250] eta: 0:04:55 lr: 0.000075 grad: 0.0862 (0.0848) loss: 0.8230 (0.8222) time: 0.1410 data: 0.0658 max mem: 9390 +Train: [46] [4100/6250] eta: 0:04:43 lr: 0.000075 grad: 0.0866 (0.0850) loss: 0.8212 (0.8221) time: 0.1726 data: 0.0649 max mem: 9390 +Train: [46] [4200/6250] eta: 0:04:30 lr: 0.000074 grad: 0.0843 (0.0851) loss: 0.8225 (0.8220) time: 0.1461 data: 0.0692 max mem: 9390 +Train: [46] [4300/6250] eta: 0:04:17 lr: 0.000074 grad: 0.0885 (0.0852) loss: 0.8136 (0.8219) time: 0.1320 data: 0.0533 max mem: 9390 +Train: [46] [4400/6250] eta: 0:04:04 lr: 0.000074 grad: 0.0859 (0.0852) loss: 0.8241 (0.8219) time: 0.1466 data: 0.0662 max mem: 9390 +Train: [46] [4500/6250] eta: 0:03:51 lr: 0.000074 grad: 0.0834 (0.0853) loss: 0.8223 (0.8219) time: 0.1356 data: 0.0533 max mem: 9390 +Train: [46] [4600/6250] eta: 0:03:38 lr: 0.000074 grad: 0.0872 (0.0854) loss: 0.8228 (0.8218) time: 0.1222 data: 0.0467 max mem: 9390 +Train: [46] [4700/6250] eta: 0:03:26 lr: 0.000074 grad: 0.0835 (0.0854) loss: 0.8275 (0.8218) time: 0.1097 data: 0.0324 max mem: 9390 +Train: [46] [4800/6250] eta: 0:03:13 lr: 0.000074 grad: 0.0849 (0.0854) loss: 0.8240 (0.8219) time: 0.1654 data: 0.0859 max mem: 9390 +Train: [46] [4900/6250] eta: 0:03:00 lr: 0.000074 grad: 0.0830 (0.0854) loss: 0.8241 (0.8219) time: 0.1423 data: 0.0551 max mem: 9390 +Train: [46] [5000/6250] eta: 0:02:47 lr: 0.000074 grad: 0.0842 (0.0854) loss: 0.8239 (0.8220) time: 0.1381 data: 0.0547 max mem: 9390 +Train: [46] [5100/6250] eta: 0:02:33 lr: 0.000074 grad: 0.0854 (0.0853) loss: 0.8205 (0.8221) time: 0.1329 data: 0.0567 max mem: 9390 +Train: [46] [5200/6250] eta: 0:02:20 lr: 0.000074 grad: 0.0906 (0.0853) loss: 0.8256 (0.8221) time: 0.1552 data: 0.0758 max mem: 9390 +Train: [46] [5300/6250] eta: 0:02:07 lr: 0.000074 grad: 0.0830 (0.0854) loss: 0.8190 (0.8221) time: 0.1278 data: 0.0457 max mem: 9390 +Train: [46] [5400/6250] eta: 0:01:53 lr: 0.000074 grad: 0.0848 (0.0854) loss: 0.8215 (0.8221) time: 0.1360 data: 0.0530 max mem: 9390 +Train: [46] [5500/6250] eta: 0:01:40 lr: 0.000074 grad: 0.0834 (0.0854) loss: 0.8180 (0.8221) time: 0.1459 data: 0.0714 max mem: 9390 +Train: [46] [5600/6250] eta: 0:01:27 lr: 0.000074 grad: 0.0859 (0.0854) loss: 0.8255 (0.8221) time: 0.1376 data: 0.0580 max mem: 9390 +Train: [46] [5700/6250] eta: 0:01:14 lr: 0.000074 grad: 0.0816 (0.0854) loss: 0.8214 (0.8221) time: 0.1527 data: 0.0766 max mem: 9390 +Train: [46] [5800/6250] eta: 0:01:00 lr: 0.000074 grad: 0.0819 (0.0854) loss: 0.8241 (0.8221) time: 0.1504 data: 0.0820 max mem: 9390 +Train: [46] [5900/6250] eta: 0:00:47 lr: 0.000074 grad: 0.0863 (0.0854) loss: 0.8215 (0.8221) time: 0.1335 data: 0.0536 max mem: 9390 +Train: [46] [6000/6250] eta: 0:00:33 lr: 0.000074 grad: 0.0770 (0.0854) loss: 0.8304 (0.8221) time: 0.1413 data: 0.0645 max mem: 9390 +Train: [46] [6100/6250] eta: 0:00:20 lr: 0.000074 grad: 0.0869 (0.0854) loss: 0.8216 (0.8221) time: 0.1454 data: 0.0680 max mem: 9390 +Train: [46] [6200/6250] eta: 0:00:06 lr: 0.000074 grad: 0.0941 (0.0855) loss: 0.8197 (0.8221) time: 0.1304 data: 0.0503 max mem: 9390 +Train: [46] [6249/6250] eta: 0:00:00 lr: 0.000074 grad: 0.0884 (0.0855) loss: 0.8155 (0.8221) time: 0.1471 data: 0.0731 max mem: 9390 +Train: [46] Total time: 0:14:09 (0.1360 s / it) +Averaged stats: lr: 0.000074 grad: 0.0884 (0.0855) loss: 0.8155 (0.8221) +Eval (hcp-train-subset): [46] [ 0/62] eta: 0:03:31 loss: 0.8484 (0.8484) time: 3.4063 data: 3.3297 max mem: 9390 +Eval (hcp-train-subset): [46] [61/62] eta: 0:00:00 loss: 0.8388 (0.8386) time: 0.1225 data: 0.0958 max mem: 9390 +Eval (hcp-train-subset): [46] Total time: 0:00:12 (0.1962 s / it) +Averaged stats (hcp-train-subset): loss: 0.8388 (0.8386) +Eval (hcp-val): [46] [ 0/62] eta: 0:03:41 loss: 0.8328 (0.8328) time: 3.5723 data: 3.5171 max mem: 9390 +Eval (hcp-val): [46] [61/62] eta: 0:00:00 loss: 0.8340 (0.8357) time: 0.1206 data: 0.0957 max mem: 9390 +Eval (hcp-val): [46] Total time: 0:00:11 (0.1909 s / it) +Averaged stats (hcp-val): loss: 0.8340 (0.8357) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +Train: [47] [ 0/6250] eta: 7:32:11 lr: 0.000074 grad: 0.0828 (0.0828) loss: 0.8553 (0.8553) time: 4.3410 data: 4.0208 max mem: 9390 +Train: [47] [ 100/6250] eta: 0:20:10 lr: 0.000074 grad: 0.0791 (0.0891) loss: 0.8318 (0.8347) time: 0.1390 data: 0.0489 max mem: 9390 +Train: [47] [ 200/6250] eta: 0:17:41 lr: 0.000074 grad: 0.0767 (0.0848) loss: 0.8240 (0.8310) time: 0.1537 data: 0.0663 max mem: 9390 +Train: [47] [ 300/6250] eta: 0:16:31 lr: 0.000074 grad: 0.0795 (0.0832) loss: 0.8344 (0.8304) time: 0.1696 data: 0.0863 max mem: 9390 +Train: [47] [ 400/6250] eta: 0:15:28 lr: 0.000074 grad: 0.0784 (0.0830) loss: 0.8168 (0.8287) time: 0.1280 data: 0.0430 max mem: 9390 +Train: [47] [ 500/6250] eta: 0:14:43 lr: 0.000074 grad: 0.0784 (0.0825) loss: 0.8202 (0.8273) time: 0.1329 data: 0.0480 max mem: 9390 +Train: [47] [ 600/6250] eta: 0:14:03 lr: 0.000074 grad: 0.0798 (0.0824) loss: 0.8230 (0.8261) time: 0.1392 data: 0.0529 max mem: 9390 +Train: [47] [ 700/6250] eta: 0:13:25 lr: 0.000074 grad: 0.0780 (0.0818) loss: 0.8227 (0.8255) time: 0.1293 data: 0.0519 max mem: 9390 +Train: [47] [ 800/6250] eta: 0:12:57 lr: 0.000074 grad: 0.0773 (0.0816) loss: 0.8198 (0.8253) time: 0.1306 data: 0.0462 max mem: 9390 +Train: [47] [ 900/6250] eta: 0:12:35 lr: 0.000074 grad: 0.0751 (0.0814) loss: 0.8272 (0.8255) time: 0.1413 data: 0.0639 max mem: 9390 +Train: [47] [1000/6250] eta: 0:12:14 lr: 0.000073 grad: 0.0792 (0.0813) loss: 0.8232 (0.8254) time: 0.1254 data: 0.0479 max mem: 9390 +Train: [47] [1100/6250] eta: 0:11:53 lr: 0.000073 grad: 0.0774 (0.0811) loss: 0.8259 (0.8253) time: 0.1219 data: 0.0448 max mem: 9390 +Train: [47] [1200/6250] eta: 0:11:37 lr: 0.000073 grad: 0.0803 (0.0810) loss: 0.8141 (0.8250) time: 0.1398 data: 0.0669 max mem: 9390 +Train: [47] [1300/6250] eta: 0:11:19 lr: 0.000073 grad: 0.0782 (0.0810) loss: 0.8192 (0.8247) time: 0.1332 data: 0.0576 max mem: 9390 +Train: [47] [1400/6250] eta: 0:11:08 lr: 0.000073 grad: 0.0804 (0.0810) loss: 0.8183 (0.8245) time: 0.1306 data: 0.0545 max mem: 9390 +Train: [47] [1500/6250] eta: 0:10:56 lr: 0.000073 grad: 0.0748 (0.0811) loss: 0.8282 (0.8244) time: 0.1627 data: 0.0823 max mem: 9390 +Train: [47] [1600/6250] eta: 0:10:39 lr: 0.000073 grad: 0.0811 (0.0813) loss: 0.8212 (0.8243) time: 0.1436 data: 0.0702 max mem: 9390 +Train: [47] [1700/6250] eta: 0:10:22 lr: 0.000073 grad: 0.0766 (0.0812) loss: 0.8259 (0.8242) time: 0.1221 data: 0.0445 max mem: 9390 +Train: [47] [1800/6250] eta: 0:10:15 lr: 0.000073 grad: 0.0803 (0.0814) loss: 0.8288 (0.8241) time: 0.1695 data: 0.0962 max mem: 9390 +Train: [47] [1900/6250] eta: 0:10:02 lr: 0.000073 grad: 0.0773 (0.0814) loss: 0.8227 (0.8240) time: 0.1298 data: 0.0533 max mem: 9390 +Train: [47] [2000/6250] eta: 0:09:52 lr: 0.000073 grad: 0.0819 (0.0815) loss: 0.8200 (0.8239) time: 0.1707 data: 0.0892 max mem: 9390 +Train: [47] [2100/6250] eta: 0:09:39 lr: 0.000073 grad: 0.0823 (0.0816) loss: 0.8228 (0.8238) time: 0.1323 data: 0.0488 max mem: 9390 +Train: [47] [2200/6250] eta: 0:09:25 lr: 0.000073 grad: 0.0767 (0.0817) loss: 0.8207 (0.8237) time: 0.1290 data: 0.0511 max mem: 9390 +Train: [47] [2300/6250] eta: 0:09:10 lr: 0.000073 grad: 0.0792 (0.0818) loss: 0.8194 (0.8236) time: 0.1347 data: 0.0557 max mem: 9390 +Train: [47] [2400/6250] eta: 0:08:55 lr: 0.000073 grad: 0.0773 (0.0818) loss: 0.8241 (0.8235) time: 0.1188 data: 0.0412 max mem: 9390 +Train: [47] [2500/6250] eta: 0:08:40 lr: 0.000073 grad: 0.0826 (0.0818) loss: 0.8165 (0.8233) time: 0.1343 data: 0.0547 max mem: 9390 +Train: [47] [2600/6250] eta: 0:08:23 lr: 0.000073 grad: 0.0810 (0.0819) loss: 0.8243 (0.8233) time: 0.0986 data: 0.0115 max mem: 9390 +Train: [47] [2700/6250] eta: 0:08:06 lr: 0.000073 grad: 0.0800 (0.0819) loss: 0.8313 (0.8233) time: 0.1154 data: 0.0337 max mem: 9390 +Train: [47] [2800/6250] eta: 0:07:50 lr: 0.000073 grad: 0.0852 (0.0820) loss: 0.8276 (0.8234) time: 0.1079 data: 0.0303 max mem: 9390 +Train: [47] [2900/6250] eta: 0:07:35 lr: 0.000073 grad: 0.0883 (0.0821) loss: 0.8187 (0.8234) time: 0.1233 data: 0.0473 max mem: 9390 +Train: [47] [3000/6250] eta: 0:07:22 lr: 0.000073 grad: 0.0794 (0.0822) loss: 0.8215 (0.8234) time: 0.1590 data: 0.0847 max mem: 9390 +Train: [47] [3100/6250] eta: 0:07:08 lr: 0.000073 grad: 0.0831 (0.0823) loss: 0.8192 (0.8234) time: 0.1157 data: 0.0381 max mem: 9390 +Train: [47] [3200/6250] eta: 0:06:54 lr: 0.000073 grad: 0.0806 (0.0823) loss: 0.8198 (0.8234) time: 0.1181 data: 0.0314 max mem: 9390 +Train: [47] [3300/6250] eta: 0:06:40 lr: 0.000073 grad: 0.0830 (0.0824) loss: 0.8237 (0.8233) time: 0.1280 data: 0.0580 max mem: 9390 +Train: [47] [3400/6250] eta: 0:06:26 lr: 0.000073 grad: 0.0850 (0.0826) loss: 0.8260 (0.8233) time: 0.1214 data: 0.0404 max mem: 9390 +Train: [47] [3500/6250] eta: 0:06:12 lr: 0.000073 grad: 0.0814 (0.0826) loss: 0.8207 (0.8233) time: 0.1355 data: 0.0508 max mem: 9390 +Train: [47] [3600/6250] eta: 0:05:58 lr: 0.000073 grad: 0.0832 (0.0827) loss: 0.8266 (0.8233) time: 0.1194 data: 0.0446 max mem: 9390 +Train: [47] [3700/6250] eta: 0:05:45 lr: 0.000073 grad: 0.0870 (0.0828) loss: 0.8190 (0.8232) time: 0.1542 data: 0.0775 max mem: 9390 +Train: [47] [3800/6250] eta: 0:05:30 lr: 0.000073 grad: 0.0845 (0.0829) loss: 0.8191 (0.8232) time: 0.1235 data: 0.0421 max mem: 9390 +Train: [47] [3900/6250] eta: 0:05:16 lr: 0.000073 grad: 0.0865 (0.0830) loss: 0.8234 (0.8231) time: 0.1222 data: 0.0454 max mem: 9390 +Train: [47] [4000/6250] eta: 0:05:02 lr: 0.000073 grad: 0.0864 (0.0832) loss: 0.8185 (0.8231) time: 0.1096 data: 0.0314 max mem: 9390 +Train: [47] [4100/6250] eta: 0:04:48 lr: 0.000072 grad: 0.0817 (0.0833) loss: 0.8239 (0.8230) time: 0.1212 data: 0.0325 max mem: 9390 +Train: [47] [4200/6250] eta: 0:04:34 lr: 0.000072 grad: 0.0765 (0.0833) loss: 0.8248 (0.8231) time: 0.1218 data: 0.0430 max mem: 9390 +Train: [47] [4300/6250] eta: 0:04:21 lr: 0.000072 grad: 0.0848 (0.0834) loss: 0.8203 (0.8230) time: 0.1638 data: 0.0843 max mem: 9390 +Train: [47] [4400/6250] eta: 0:04:08 lr: 0.000072 grad: 0.0873 (0.0835) loss: 0.8183 (0.8230) time: 0.1918 data: 0.1123 max mem: 9390 +Train: [47] [4500/6250] eta: 0:03:55 lr: 0.000072 grad: 0.0850 (0.0836) loss: 0.8183 (0.8229) time: 0.1433 data: 0.0565 max mem: 9390 +Train: [47] [4600/6250] eta: 0:03:42 lr: 0.000072 grad: 0.0869 (0.0836) loss: 0.8204 (0.8229) time: 0.1041 data: 0.0209 max mem: 9390 +Train: [47] [4700/6250] eta: 0:03:28 lr: 0.000072 grad: 0.0885 (0.0837) loss: 0.8225 (0.8228) time: 0.1395 data: 0.0618 max mem: 9390 +Train: [47] [4800/6250] eta: 0:03:15 lr: 0.000072 grad: 0.0832 (0.0838) loss: 0.8238 (0.8228) time: 0.1752 data: 0.0894 max mem: 9390 +Train: [47] [4900/6250] eta: 0:03:02 lr: 0.000072 grad: 0.0880 (0.0839) loss: 0.8202 (0.8227) time: 0.1681 data: 0.0964 max mem: 9390 +Train: [47] [5000/6250] eta: 0:02:48 lr: 0.000072 grad: 0.0889 (0.0840) loss: 0.8141 (0.8226) time: 0.1176 data: 0.0345 max mem: 9390 +Train: [47] [5100/6250] eta: 0:02:34 lr: 0.000072 grad: 0.0831 (0.0841) loss: 0.8214 (0.8225) time: 0.1307 data: 0.0520 max mem: 9390 +Train: [47] [5200/6250] eta: 0:02:21 lr: 0.000072 grad: 0.0866 (0.0841) loss: 0.8179 (0.8224) time: 0.1192 data: 0.0317 max mem: 9390 +Train: [47] [5300/6250] eta: 0:02:08 lr: 0.000072 grad: 0.0863 (0.0842) loss: 0.8145 (0.8223) time: 0.1390 data: 0.0559 max mem: 9390 +Train: [47] [5400/6250] eta: 0:01:54 lr: 0.000072 grad: 0.0812 (0.0843) loss: 0.8207 (0.8222) time: 0.1533 data: 0.0726 max mem: 9390 +Train: [47] [5500/6250] eta: 0:01:41 lr: 0.000072 grad: 0.0872 (0.0844) loss: 0.8185 (0.8221) time: 0.1411 data: 0.0538 max mem: 9390 +Train: [47] [5600/6250] eta: 0:01:28 lr: 0.000072 grad: 0.0839 (0.0844) loss: 0.8236 (0.8221) time: 0.1522 data: 0.0711 max mem: 9390 +Train: [47] [5700/6250] eta: 0:01:14 lr: 0.000072 grad: 0.0862 (0.0845) loss: 0.8149 (0.8220) time: 0.1469 data: 0.0641 max mem: 9390 +Train: [47] [5800/6250] eta: 0:01:01 lr: 0.000072 grad: 0.0860 (0.0845) loss: 0.8206 (0.8219) time: 0.1407 data: 0.0603 max mem: 9390 +Train: [47] [5900/6250] eta: 0:00:47 lr: 0.000072 grad: 0.0781 (0.0845) loss: 0.8159 (0.8219) time: 0.1403 data: 0.0648 max mem: 9390 +Train: [47] [6000/6250] eta: 0:00:33 lr: 0.000072 grad: 0.0851 (0.0845) loss: 0.8249 (0.8219) time: 0.1183 data: 0.0369 max mem: 9390 +Train: [47] [6100/6250] eta: 0:00:20 lr: 0.000072 grad: 0.0837 (0.0845) loss: 0.8137 (0.8218) time: 0.1613 data: 0.0800 max mem: 9390 +Train: [47] [6200/6250] eta: 0:00:06 lr: 0.000072 grad: 0.0856 (0.0846) loss: 0.8162 (0.8218) time: 0.1445 data: 0.0650 max mem: 9390 +Train: [47] [6249/6250] eta: 0:00:00 lr: 0.000072 grad: 0.0829 (0.0846) loss: 0.8223 (0.8218) time: 0.1327 data: 0.0565 max mem: 9390 +Train: [47] Total time: 0:14:14 (0.1368 s / it) +Averaged stats: lr: 0.000072 grad: 0.0829 (0.0846) loss: 0.8223 (0.8218) +Eval (hcp-train-subset): [47] [ 0/62] eta: 0:03:11 loss: 0.8505 (0.8505) time: 3.0877 data: 2.9977 max mem: 9390 +Eval (hcp-train-subset): [47] [61/62] eta: 0:00:00 loss: 0.8340 (0.8363) time: 0.1140 data: 0.0892 max mem: 9390 +Eval (hcp-train-subset): [47] Total time: 0:00:11 (0.1913 s / it) +Averaged stats (hcp-train-subset): loss: 0.8340 (0.8363) +Eval (hcp-val): [47] [ 0/62] eta: 0:05:50 loss: 0.8319 (0.8319) time: 5.6477 data: 5.6159 max mem: 9390 +Eval (hcp-val): [47] [61/62] eta: 0:00:00 loss: 0.8326 (0.8361) time: 0.1047 data: 0.0801 max mem: 9390 +Eval (hcp-val): [47] Total time: 0:00:12 (0.2072 s / it) +Averaged stats (hcp-val): loss: 0.8326 (0.8361) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +Train: [48] [ 0/6250] eta: 8:31:43 lr: 0.000072 grad: 0.0696 (0.0696) loss: 0.8582 (0.8582) time: 4.9125 data: 4.7885 max mem: 9390 +Train: [48] [ 100/6250] eta: 0:19:54 lr: 0.000072 grad: 0.0834 (0.0940) loss: 0.8295 (0.8286) time: 0.1400 data: 0.0535 max mem: 9390 +Train: [48] [ 200/6250] eta: 0:17:18 lr: 0.000072 grad: 0.0792 (0.0905) loss: 0.8270 (0.8293) time: 0.1515 data: 0.0651 max mem: 9390 +Train: [48] [ 300/6250] eta: 0:16:06 lr: 0.000072 grad: 0.0763 (0.0878) loss: 0.8301 (0.8284) time: 0.1467 data: 0.0654 max mem: 9390 +Train: [48] [ 400/6250] eta: 0:15:10 lr: 0.000072 grad: 0.0753 (0.0862) loss: 0.8319 (0.8275) time: 0.1250 data: 0.0279 max mem: 9390 +Train: [48] [ 500/6250] eta: 0:14:28 lr: 0.000072 grad: 0.0786 (0.0850) loss: 0.8267 (0.8269) time: 0.1412 data: 0.0541 max mem: 9390 +Train: [48] [ 600/6250] eta: 0:13:46 lr: 0.000072 grad: 0.0852 (0.0845) loss: 0.8249 (0.8271) time: 0.1117 data: 0.0243 max mem: 9390 +Train: [48] [ 700/6250] eta: 0:13:17 lr: 0.000072 grad: 0.0780 (0.0838) loss: 0.8327 (0.8273) time: 0.1380 data: 0.0553 max mem: 9390 +Train: [48] [ 800/6250] eta: 0:12:46 lr: 0.000072 grad: 0.0779 (0.0834) loss: 0.8303 (0.8273) time: 0.0988 data: 0.0124 max mem: 9390 +Train: [48] [ 900/6250] eta: 0:12:25 lr: 0.000071 grad: 0.0868 (0.0833) loss: 0.8228 (0.8270) time: 0.1294 data: 0.0435 max mem: 9390 +Train: [48] [1000/6250] eta: 0:12:06 lr: 0.000071 grad: 0.0796 (0.0835) loss: 0.8192 (0.8266) time: 0.1294 data: 0.0535 max mem: 9390 +Train: [48] [1100/6250] eta: 0:11:48 lr: 0.000071 grad: 0.0767 (0.0835) loss: 0.8252 (0.8264) time: 0.1178 data: 0.0392 max mem: 9390 +Train: [48] [1200/6250] eta: 0:11:29 lr: 0.000071 grad: 0.0792 (0.0835) loss: 0.8213 (0.8261) time: 0.1194 data: 0.0339 max mem: 9390 +Train: [48] [1300/6250] eta: 0:11:12 lr: 0.000071 grad: 0.0807 (0.0836) loss: 0.8232 (0.8258) time: 0.1210 data: 0.0429 max mem: 9390 +Train: [48] [1400/6250] eta: 0:11:00 lr: 0.000071 grad: 0.0823 (0.0837) loss: 0.8211 (0.8256) time: 0.1424 data: 0.0595 max mem: 9390 +Train: [48] [1500/6250] eta: 0:10:49 lr: 0.000071 grad: 0.0870 (0.0839) loss: 0.8206 (0.8255) time: 0.1315 data: 0.0515 max mem: 9390 +Train: [48] [1600/6250] eta: 0:10:37 lr: 0.000071 grad: 0.0823 (0.0839) loss: 0.8192 (0.8253) time: 0.1558 data: 0.0708 max mem: 9390 +Train: [48] [1700/6250] eta: 0:10:23 lr: 0.000071 grad: 0.0827 (0.0842) loss: 0.8222 (0.8251) time: 0.1390 data: 0.0623 max mem: 9390 +Train: [48] [1800/6250] eta: 0:10:11 lr: 0.000071 grad: 0.0789 (0.0842) loss: 0.8241 (0.8248) time: 0.1943 data: 0.1205 max mem: 9390 +Train: [48] [1900/6250] eta: 0:10:00 lr: 0.000071 grad: 0.0842 (0.0843) loss: 0.8187 (0.8246) time: 0.1444 data: 0.0666 max mem: 9390 +Train: [48] [2000/6250] eta: 0:09:47 lr: 0.000071 grad: 0.0829 (0.0844) loss: 0.8227 (0.8245) time: 0.1349 data: 0.0571 max mem: 9390 +Train: [48] [2100/6250] eta: 0:09:36 lr: 0.000071 grad: 0.0873 (0.0847) loss: 0.8226 (0.8243) time: 0.1333 data: 0.0444 max mem: 9390 +Train: [48] [2200/6250] eta: 0:09:23 lr: 0.000071 grad: 0.0814 (0.0850) loss: 0.8265 (0.8242) time: 0.1155 data: 0.0355 max mem: 9390 +Train: [48] [2300/6250] eta: 0:09:09 lr: 0.000071 grad: 0.0883 (0.0851) loss: 0.8213 (0.8241) time: 0.1292 data: 0.0416 max mem: 9390 +Train: [48] [2400/6250] eta: 0:08:54 lr: 0.000071 grad: 0.0883 (0.0852) loss: 0.8161 (0.8239) time: 0.1376 data: 0.0541 max mem: 9390 +Train: [48] [2500/6250] eta: 0:08:39 lr: 0.000071 grad: 0.0876 (0.0853) loss: 0.8189 (0.8237) time: 0.1398 data: 0.0618 max mem: 9390 +Train: [48] [2600/6250] eta: 0:08:23 lr: 0.000071 grad: 0.0889 (0.0854) loss: 0.8171 (0.8237) time: 0.1335 data: 0.0567 max mem: 9390 +Train: [48] [2700/6250] eta: 0:08:07 lr: 0.000071 grad: 0.0888 (0.0855) loss: 0.8221 (0.8235) time: 0.0938 data: 0.0112 max mem: 9390 +Train: [48] [2800/6250] eta: 0:07:51 lr: 0.000071 grad: 0.0788 (0.0855) loss: 0.8238 (0.8235) time: 0.1057 data: 0.0251 max mem: 9390 +Train: [48] [2900/6250] eta: 0:07:37 lr: 0.000071 grad: 0.0863 (0.0856) loss: 0.8233 (0.8235) time: 0.1597 data: 0.0852 max mem: 9390 +Train: [48] [3000/6250] eta: 0:07:24 lr: 0.000071 grad: 0.0881 (0.0857) loss: 0.8240 (0.8235) time: 0.1463 data: 0.0735 max mem: 9390 +Train: [48] [3100/6250] eta: 0:07:11 lr: 0.000071 grad: 0.0823 (0.0858) loss: 0.8218 (0.8235) time: 0.1499 data: 0.0721 max mem: 9390 +Train: [48] [3200/6250] eta: 0:06:59 lr: 0.000071 grad: 0.0828 (0.0858) loss: 0.8228 (0.8235) time: 0.1453 data: 0.0715 max mem: 9390 +Train: [48] [3300/6250] eta: 0:06:46 lr: 0.000071 grad: 0.0831 (0.0859) loss: 0.8211 (0.8235) time: 0.1488 data: 0.0676 max mem: 9390 +Train: [48] [3400/6250] eta: 0:06:32 lr: 0.000071 grad: 0.0841 (0.0859) loss: 0.8254 (0.8235) time: 0.1235 data: 0.0428 max mem: 9390 +Train: [48] [3500/6250] eta: 0:06:19 lr: 0.000071 grad: 0.0864 (0.0859) loss: 0.8166 (0.8234) time: 0.1388 data: 0.0610 max mem: 9390 +Train: [48] [3600/6250] eta: 0:06:04 lr: 0.000071 grad: 0.0825 (0.0859) loss: 0.8223 (0.8234) time: 0.1240 data: 0.0458 max mem: 9390 +Train: [48] [3700/6250] eta: 0:05:51 lr: 0.000071 grad: 0.0814 (0.0860) loss: 0.8226 (0.8234) time: 0.1553 data: 0.0732 max mem: 9390 +Train: [48] [3800/6250] eta: 0:05:37 lr: 0.000071 grad: 0.0924 (0.0860) loss: 0.8187 (0.8233) time: 0.1577 data: 0.0804 max mem: 9390 +Train: [48] [3900/6250] eta: 0:05:22 lr: 0.000070 grad: 0.0799 (0.0861) loss: 0.8204 (0.8232) time: 0.1167 data: 0.0364 max mem: 9390 +Train: [48] [4000/6250] eta: 0:05:09 lr: 0.000070 grad: 0.0875 (0.0861) loss: 0.8202 (0.8232) time: 0.1432 data: 0.0700 max mem: 9390 +Train: [48] [4100/6250] eta: 0:04:55 lr: 0.000070 grad: 0.0853 (0.0862) loss: 0.8203 (0.8231) time: 0.1697 data: 0.0880 max mem: 9390 +Train: [48] [4200/6250] eta: 0:04:41 lr: 0.000070 grad: 0.0869 (0.0863) loss: 0.8207 (0.8231) time: 0.1353 data: 0.0598 max mem: 9390 +Train: [48] [4300/6250] eta: 0:04:27 lr: 0.000070 grad: 0.0817 (0.0863) loss: 0.8295 (0.8231) time: 0.1434 data: 0.0552 max mem: 9390 +Train: [48] [4400/6250] eta: 0:04:15 lr: 0.000070 grad: 0.0849 (0.0864) loss: 0.8193 (0.8230) time: 0.1364 data: 0.0489 max mem: 9390 +Train: [48] [4500/6250] eta: 0:04:01 lr: 0.000070 grad: 0.0895 (0.0865) loss: 0.8202 (0.8229) time: 0.1342 data: 0.0553 max mem: 9390 +Train: [48] [4600/6250] eta: 0:03:47 lr: 0.000070 grad: 0.0861 (0.0865) loss: 0.8240 (0.8229) time: 0.1476 data: 0.0634 max mem: 9390 +Train: [48] [4700/6250] eta: 0:03:33 lr: 0.000070 grad: 0.0931 (0.0866) loss: 0.8151 (0.8228) time: 0.1658 data: 0.0844 max mem: 9390 +Train: [48] [4800/6250] eta: 0:03:20 lr: 0.000070 grad: 0.0897 (0.0866) loss: 0.8158 (0.8228) time: 0.1625 data: 0.0861 max mem: 9390 +Train: [48] [4900/6250] eta: 0:03:06 lr: 0.000070 grad: 0.0847 (0.0867) loss: 0.8231 (0.8227) time: 0.1465 data: 0.0664 max mem: 9390 +Train: [48] [5000/6250] eta: 0:02:52 lr: 0.000070 grad: 0.0913 (0.0867) loss: 0.8152 (0.8226) time: 0.1422 data: 0.0668 max mem: 9390 +Train: [48] [5100/6250] eta: 0:02:38 lr: 0.000070 grad: 0.0831 (0.0868) loss: 0.8236 (0.8226) time: 0.1395 data: 0.0609 max mem: 9390 +Train: [48] [5200/6250] eta: 0:02:25 lr: 0.000070 grad: 0.0860 (0.0869) loss: 0.8201 (0.8225) time: 0.1213 data: 0.0410 max mem: 9390 +Train: [48] [5300/6250] eta: 0:02:11 lr: 0.000070 grad: 0.0966 (0.0870) loss: 0.8168 (0.8224) time: 0.1194 data: 0.0381 max mem: 9390 +Train: [48] [5400/6250] eta: 0:01:57 lr: 0.000070 grad: 0.0879 (0.0871) loss: 0.8209 (0.8224) time: 0.1695 data: 0.0863 max mem: 9390 +Train: [48] [5500/6250] eta: 0:01:43 lr: 0.000070 grad: 0.0860 (0.0872) loss: 0.8141 (0.8223) time: 0.1498 data: 0.0628 max mem: 9390 +Train: [48] [5600/6250] eta: 0:01:29 lr: 0.000070 grad: 0.0921 (0.0873) loss: 0.8237 (0.8222) time: 0.1276 data: 0.0529 max mem: 9390 +Train: [48] [5700/6250] eta: 0:01:15 lr: 0.000070 grad: 0.0937 (0.0874) loss: 0.8195 (0.8221) time: 0.1334 data: 0.0534 max mem: 9390 +Train: [48] [5800/6250] eta: 0:01:02 lr: 0.000070 grad: 0.0857 (0.0875) loss: 0.8180 (0.8220) time: 0.1510 data: 0.0598 max mem: 9390 +Train: [48] [5900/6250] eta: 0:00:48 lr: 0.000070 grad: 0.0901 (0.0876) loss: 0.8166 (0.8220) time: 0.1585 data: 0.0823 max mem: 9390 +Train: [48] [6000/6250] eta: 0:00:34 lr: 0.000070 grad: 0.0835 (0.0876) loss: 0.8211 (0.8219) time: 0.1535 data: 0.0792 max mem: 9390 +Train: [48] [6100/6250] eta: 0:00:20 lr: 0.000070 grad: 0.0862 (0.0877) loss: 0.8249 (0.8219) time: 0.1544 data: 0.0733 max mem: 9390 +Train: [48] [6200/6250] eta: 0:00:06 lr: 0.000070 grad: 0.0959 (0.0878) loss: 0.8137 (0.8218) time: 0.1250 data: 0.0483 max mem: 9390 +Train: [48] [6249/6250] eta: 0:00:00 lr: 0.000070 grad: 0.0943 (0.0878) loss: 0.8197 (0.8218) time: 0.1312 data: 0.0527 max mem: 9390 +Train: [48] Total time: 0:14:31 (0.1394 s / it) +Averaged stats: lr: 0.000070 grad: 0.0943 (0.0878) loss: 0.8197 (0.8218) +Eval (hcp-train-subset): [48] [ 0/62] eta: 0:04:27 loss: 0.8527 (0.8527) time: 4.3173 data: 4.2881 max mem: 9390 +Eval (hcp-train-subset): [48] [61/62] eta: 0:00:00 loss: 0.8342 (0.8365) time: 0.1157 data: 0.0905 max mem: 9390 +Eval (hcp-train-subset): [48] Total time: 0:00:12 (0.1943 s / it) +Averaged stats (hcp-train-subset): loss: 0.8342 (0.8365) +Eval (hcp-val): [48] [ 0/62] eta: 0:04:13 loss: 0.8338 (0.8338) time: 4.0828 data: 4.0479 max mem: 9390 +Eval (hcp-val): [48] [61/62] eta: 0:00:00 loss: 0.8337 (0.8353) time: 0.1215 data: 0.0947 max mem: 9390 +Eval (hcp-val): [48] Total time: 0:00:12 (0.2045 s / it) +Averaged stats (hcp-val): loss: 0.8337 (0.8353) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +Train: [49] [ 0/6250] eta: 7:25:36 lr: 0.000070 grad: 0.0548 (0.0548) loss: 0.8818 (0.8818) time: 4.2779 data: 3.9788 max mem: 9390 +Train: [49] [ 100/6250] eta: 0:19:48 lr: 0.000070 grad: 0.0911 (0.1061) loss: 0.8200 (0.8272) time: 0.1478 data: 0.0630 max mem: 9390 +Train: [49] [ 200/6250] eta: 0:17:38 lr: 0.000070 grad: 0.0799 (0.1031) loss: 0.8134 (0.8218) time: 0.1499 data: 0.0622 max mem: 9390 +Train: [49] [ 300/6250] eta: 0:16:06 lr: 0.000070 grad: 0.0817 (0.0983) loss: 0.8284 (0.8227) time: 0.1315 data: 0.0435 max mem: 9390 +Train: [49] [ 400/6250] eta: 0:15:21 lr: 0.000070 grad: 0.0765 (0.0945) loss: 0.8261 (0.8233) time: 0.1260 data: 0.0457 max mem: 9390 +Train: [49] [ 500/6250] eta: 0:14:40 lr: 0.000070 grad: 0.0822 (0.0926) loss: 0.8290 (0.8238) time: 0.1304 data: 0.0419 max mem: 9390 +Train: [49] [ 600/6250] eta: 0:14:02 lr: 0.000070 grad: 0.0781 (0.0909) loss: 0.8253 (0.8239) time: 0.1440 data: 0.0525 max mem: 9390 +Train: [49] [ 700/6250] eta: 0:13:29 lr: 0.000069 grad: 0.0808 (0.0898) loss: 0.8234 (0.8241) time: 0.1228 data: 0.0387 max mem: 9390 +Train: [49] [ 800/6250] eta: 0:13:03 lr: 0.000069 grad: 0.0841 (0.0893) loss: 0.8259 (0.8242) time: 0.1231 data: 0.0357 max mem: 9390 +Train: [49] [ 900/6250] eta: 0:12:39 lr: 0.000069 grad: 0.0809 (0.0885) loss: 0.8228 (0.8244) time: 0.1272 data: 0.0425 max mem: 9390 +Train: [49] [1000/6250] eta: 0:12:17 lr: 0.000069 grad: 0.0760 (0.0880) loss: 0.8274 (0.8245) time: 0.1157 data: 0.0345 max mem: 9390 +Train: [49] [1100/6250] eta: 0:11:55 lr: 0.000069 grad: 0.0806 (0.0875) loss: 0.8262 (0.8244) time: 0.1186 data: 0.0332 max mem: 9390 +Train: [49] [1200/6250] eta: 0:11:38 lr: 0.000069 grad: 0.0842 (0.0870) loss: 0.8212 (0.8244) time: 0.1512 data: 0.0749 max mem: 9390 +Train: [49] [1300/6250] eta: 0:11:23 lr: 0.000069 grad: 0.0871 (0.0870) loss: 0.8232 (0.8244) time: 0.1404 data: 0.0538 max mem: 9390 +Train: [49] [1400/6250] eta: 0:11:08 lr: 0.000069 grad: 0.0833 (0.0867) loss: 0.8253 (0.8244) time: 0.1588 data: 0.0842 max mem: 9390 +Train: [49] [1500/6250] eta: 0:10:54 lr: 0.000069 grad: 0.0812 (0.0866) loss: 0.8226 (0.8243) time: 0.1589 data: 0.0829 max mem: 9390 +Train: [49] [1600/6250] eta: 0:10:38 lr: 0.000069 grad: 0.0875 (0.0865) loss: 0.8286 (0.8244) time: 0.1312 data: 0.0545 max mem: 9390 +Train: [49] [1700/6250] eta: 0:10:22 lr: 0.000069 grad: 0.0780 (0.0863) loss: 0.8285 (0.8244) time: 0.1436 data: 0.0570 max mem: 9390 +Train: [49] [1800/6250] eta: 0:10:10 lr: 0.000069 grad: 0.0851 (0.0862) loss: 0.8268 (0.8245) time: 0.1488 data: 0.0615 max mem: 9390 +Train: [49] [1900/6250] eta: 0:10:01 lr: 0.000069 grad: 0.0818 (0.0861) loss: 0.8242 (0.8244) time: 0.1547 data: 0.0712 max mem: 9390 +Train: [49] [2000/6250] eta: 0:09:45 lr: 0.000069 grad: 0.0815 (0.0861) loss: 0.8329 (0.8246) time: 0.1268 data: 0.0562 max mem: 9390 +Train: [49] [2100/6250] eta: 0:09:31 lr: 0.000069 grad: 0.0799 (0.0860) loss: 0.8272 (0.8248) time: 0.1461 data: 0.0677 max mem: 9390 +Train: [49] [2200/6250] eta: 0:09:17 lr: 0.000069 grad: 0.0805 (0.0860) loss: 0.8239 (0.8249) time: 0.1512 data: 0.0650 max mem: 9390 +Train: [49] [2300/6250] eta: 0:09:04 lr: 0.000069 grad: 0.0791 (0.0860) loss: 0.8287 (0.8249) time: 0.1413 data: 0.0553 max mem: 9390 +Train: [49] [2400/6250] eta: 0:08:51 lr: 0.000069 grad: 0.0835 (0.0862) loss: 0.8244 (0.8250) time: 0.1415 data: 0.0555 max mem: 9390 +Train: [49] [2500/6250] eta: 0:08:37 lr: 0.000069 grad: 0.0810 (0.0863) loss: 0.8275 (0.8249) time: 0.1256 data: 0.0370 max mem: 9390 +Train: [49] [2600/6250] eta: 0:08:21 lr: 0.000069 grad: 0.0830 (0.0864) loss: 0.8203 (0.8248) time: 0.1188 data: 0.0442 max mem: 9390 +Train: [49] [2700/6250] eta: 0:08:06 lr: 0.000069 grad: 0.0962 (0.0865) loss: 0.8135 (0.8246) time: 0.1303 data: 0.0456 max mem: 9390 +Train: [49] [2800/6250] eta: 0:07:49 lr: 0.000069 grad: 0.0905 (0.0867) loss: 0.8255 (0.8244) time: 0.1075 data: 0.0243 max mem: 9390 +Train: [49] [2900/6250] eta: 0:07:34 lr: 0.000069 grad: 0.0881 (0.0867) loss: 0.8229 (0.8243) time: 0.1379 data: 0.0602 max mem: 9390 +Train: [49] [3000/6250] eta: 0:07:20 lr: 0.000069 grad: 0.0824 (0.0868) loss: 0.8278 (0.8241) time: 0.1393 data: 0.0632 max mem: 9390 +Train: [49] [3100/6250] eta: 0:07:08 lr: 0.000069 grad: 0.0830 (0.0869) loss: 0.8186 (0.8240) time: 0.1432 data: 0.0720 max mem: 9390 +Train: [49] [3200/6250] eta: 0:06:56 lr: 0.000069 grad: 0.0824 (0.0870) loss: 0.8264 (0.8238) time: 0.1316 data: 0.0461 max mem: 9390 +Train: [49] [3300/6250] eta: 0:06:42 lr: 0.000069 grad: 0.0787 (0.0870) loss: 0.8266 (0.8238) time: 0.1379 data: 0.0629 max mem: 9390 +Train: [49] [3400/6250] eta: 0:06:28 lr: 0.000069 grad: 0.0839 (0.0870) loss: 0.8194 (0.8236) time: 0.1244 data: 0.0444 max mem: 9390 +Train: [49] [3500/6250] eta: 0:06:14 lr: 0.000069 grad: 0.0858 (0.0871) loss: 0.8235 (0.8235) time: 0.1240 data: 0.0486 max mem: 9390 +Train: [49] [3600/6250] eta: 0:06:00 lr: 0.000069 grad: 0.0906 (0.0871) loss: 0.8146 (0.8234) time: 0.1350 data: 0.0584 max mem: 9390 +Train: [49] [3700/6250] eta: 0:05:47 lr: 0.000069 grad: 0.0796 (0.0872) loss: 0.8220 (0.8233) time: 0.1297 data: 0.0506 max mem: 9390 +Train: [49] [3800/6250] eta: 0:05:33 lr: 0.000068 grad: 0.0833 (0.0873) loss: 0.8214 (0.8232) time: 0.1277 data: 0.0498 max mem: 9390 +Train: [49] [3900/6250] eta: 0:05:18 lr: 0.000068 grad: 0.0841 (0.0873) loss: 0.8213 (0.8231) time: 0.1178 data: 0.0400 max mem: 9390 +Train: [49] [4000/6250] eta: 0:05:04 lr: 0.000068 grad: 0.0909 (0.0874) loss: 0.8186 (0.8229) time: 0.1267 data: 0.0399 max mem: 9390 +Train: [49] [4100/6250] eta: 0:04:50 lr: 0.000068 grad: 0.0915 (0.0875) loss: 0.8188 (0.8228) time: 0.1262 data: 0.0485 max mem: 9390 +Train: [49] [4200/6250] eta: 0:04:36 lr: 0.000068 grad: 0.0879 (0.0876) loss: 0.8137 (0.8227) time: 0.1069 data: 0.0329 max mem: 9390 +Train: [49] [4300/6250] eta: 0:04:22 lr: 0.000068 grad: 0.0837 (0.0877) loss: 0.8198 (0.8226) time: 0.1265 data: 0.0484 max mem: 9390 +Train: [49] [4400/6250] eta: 0:04:08 lr: 0.000068 grad: 0.0900 (0.0878) loss: 0.8148 (0.8224) time: 0.1339 data: 0.0574 max mem: 9390 +Train: [49] [4500/6250] eta: 0:03:54 lr: 0.000068 grad: 0.0884 (0.0879) loss: 0.8148 (0.8223) time: 0.1180 data: 0.0385 max mem: 9390 +Train: [49] [4600/6250] eta: 0:03:41 lr: 0.000068 grad: 0.0905 (0.0880) loss: 0.8136 (0.8222) time: 0.1317 data: 0.0544 max mem: 9390 +Train: [49] [4700/6250] eta: 0:03:28 lr: 0.000068 grad: 0.0874 (0.0880) loss: 0.8173 (0.8221) time: 0.1383 data: 0.0625 max mem: 9390 +Train: [49] [4800/6250] eta: 0:03:14 lr: 0.000068 grad: 0.0935 (0.0882) loss: 0.8129 (0.8219) time: 0.1258 data: 0.0511 max mem: 9390 +Train: [49] [4900/6250] eta: 0:03:01 lr: 0.000068 grad: 0.0860 (0.0883) loss: 0.8160 (0.8218) time: 0.1416 data: 0.0594 max mem: 9390 +Train: [49] [5000/6250] eta: 0:02:48 lr: 0.000068 grad: 0.0859 (0.0883) loss: 0.8197 (0.8218) time: 0.1759 data: 0.1068 max mem: 9390 +Train: [49] [5100/6250] eta: 0:02:34 lr: 0.000068 grad: 0.0883 (0.0883) loss: 0.8144 (0.8217) time: 0.1312 data: 0.0567 max mem: 9390 +Train: [49] [5200/6250] eta: 0:02:21 lr: 0.000068 grad: 0.0833 (0.0884) loss: 0.8158 (0.8216) time: 0.1530 data: 0.0682 max mem: 9390 +Train: [49] [5300/6250] eta: 0:02:08 lr: 0.000068 grad: 0.0883 (0.0884) loss: 0.8183 (0.8215) time: 0.0894 data: 0.0026 max mem: 9390 +Train: [49] [5400/6250] eta: 0:01:54 lr: 0.000068 grad: 0.0885 (0.0884) loss: 0.8106 (0.8214) time: 0.1207 data: 0.0396 max mem: 9390 +Train: [49] [5500/6250] eta: 0:01:41 lr: 0.000068 grad: 0.0866 (0.0884) loss: 0.8161 (0.8213) time: 0.1214 data: 0.0399 max mem: 9390 +Train: [49] [5600/6250] eta: 0:01:27 lr: 0.000068 grad: 0.0930 (0.0885) loss: 0.8104 (0.8212) time: 0.1638 data: 0.0804 max mem: 9390 +Train: [49] [5700/6250] eta: 0:01:14 lr: 0.000068 grad: 0.0883 (0.0885) loss: 0.8118 (0.8211) time: 0.1119 data: 0.0345 max mem: 9390 +Train: [49] [5800/6250] eta: 0:01:00 lr: 0.000068 grad: 0.0874 (0.0885) loss: 0.8131 (0.8210) time: 0.1310 data: 0.0572 max mem: 9390 +Train: [49] [5900/6250] eta: 0:00:47 lr: 0.000068 grad: 0.0862 (0.0885) loss: 0.8197 (0.8210) time: 0.1363 data: 0.0611 max mem: 9390 +Train: [49] [6000/6250] eta: 0:00:33 lr: 0.000068 grad: 0.0856 (0.0886) loss: 0.8203 (0.8209) time: 0.1510 data: 0.0554 max mem: 9390 +Train: [49] [6100/6250] eta: 0:00:20 lr: 0.000068 grad: 0.0886 (0.0886) loss: 0.8199 (0.8209) time: 0.1310 data: 0.0477 max mem: 9390 +Train: [49] [6200/6250] eta: 0:00:06 lr: 0.000068 grad: 0.0925 (0.0886) loss: 0.8206 (0.8209) time: 0.1486 data: 0.0729 max mem: 9390 +Train: [49] [6249/6250] eta: 0:00:00 lr: 0.000068 grad: 0.0866 (0.0886) loss: 0.8197 (0.8209) time: 0.1552 data: 0.0733 max mem: 9390 +Train: [49] Total time: 0:14:14 (0.1367 s / it) +Averaged stats: lr: 0.000068 grad: 0.0866 (0.0886) loss: 0.8197 (0.8209) +Eval (hcp-train-subset): [49] [ 0/62] eta: 0:04:22 loss: 0.8450 (0.8450) time: 4.2346 data: 4.2022 max mem: 9390 +Eval (hcp-train-subset): [49] [61/62] eta: 0:00:00 loss: 0.8363 (0.8362) time: 0.1011 data: 0.0763 max mem: 9390 +Eval (hcp-train-subset): [49] Total time: 0:00:12 (0.1980 s / it) +Averaged stats (hcp-train-subset): loss: 0.8363 (0.8362) +Making plots (hcp-train-subset): example=30 +Eval (hcp-val): [49] [ 0/62] eta: 0:05:25 loss: 0.8347 (0.8347) time: 5.2473 data: 5.2171 max mem: 9390 +Eval (hcp-val): [49] [61/62] eta: 0:00:00 loss: 0.8333 (0.8352) time: 0.1250 data: 0.0999 max mem: 9390 +Eval (hcp-val): [49] Total time: 0:00:12 (0.2008 s / it) +Averaged stats (hcp-val): loss: 0.8333 (0.8352) +Making plots (hcp-val): example=2 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +Train: [50] [ 0/6250] eta: 10:37:32 lr: 0.000068 grad: 0.0782 (0.0782) loss: 0.8399 (0.8399) time: 6.1203 data: 5.9877 max mem: 9390 +Train: [50] [ 100/6250] eta: 0:20:01 lr: 0.000068 grad: 0.0865 (0.1095) loss: 0.8253 (0.8327) time: 0.1489 data: 0.0523 max mem: 9390 +Train: [50] [ 200/6250] eta: 0:17:14 lr: 0.000068 grad: 0.0791 (0.1008) loss: 0.8198 (0.8294) time: 0.1410 data: 0.0536 max mem: 9390 +Train: [50] [ 300/6250] eta: 0:15:59 lr: 0.000068 grad: 0.0827 (0.0976) loss: 0.8221 (0.8265) time: 0.1435 data: 0.0610 max mem: 9390 +Train: [50] [ 400/6250] eta: 0:15:02 lr: 0.000068 grad: 0.0788 (0.0952) loss: 0.8228 (0.8248) time: 0.1515 data: 0.0652 max mem: 9390 +Train: [50] [ 500/6250] eta: 0:14:14 lr: 0.000067 grad: 0.0866 (0.0936) loss: 0.8107 (0.8239) time: 0.1245 data: 0.0447 max mem: 9390 +Train: [50] [ 600/6250] eta: 0:13:45 lr: 0.000067 grad: 0.0799 (0.0922) loss: 0.8194 (0.8230) time: 0.1490 data: 0.0669 max mem: 9390 +Train: [50] [ 700/6250] eta: 0:13:13 lr: 0.000067 grad: 0.0845 (0.0914) loss: 0.8179 (0.8226) time: 0.1293 data: 0.0503 max mem: 9390 +Train: [50] [ 800/6250] eta: 0:12:46 lr: 0.000067 grad: 0.0840 (0.0909) loss: 0.8203 (0.8224) time: 0.1275 data: 0.0425 max mem: 9390 +Train: [50] [ 900/6250] eta: 0:12:25 lr: 0.000067 grad: 0.0903 (0.0905) loss: 0.8188 (0.8221) time: 0.1175 data: 0.0348 max mem: 9390 +Train: [50] [1000/6250] eta: 0:12:04 lr: 0.000067 grad: 0.0833 (0.0899) loss: 0.8142 (0.8221) time: 0.1229 data: 0.0433 max mem: 9390 +Train: [50] [1100/6250] eta: 0:11:45 lr: 0.000067 grad: 0.0880 (0.0899) loss: 0.8148 (0.8218) time: 0.1528 data: 0.0727 max mem: 9390 +Train: [50] [1200/6250] eta: 0:11:24 lr: 0.000067 grad: 0.0876 (0.0899) loss: 0.8196 (0.8214) time: 0.1305 data: 0.0511 max mem: 9390 +Train: [50] [1300/6250] eta: 0:11:09 lr: 0.000067 grad: 0.0875 (0.0903) loss: 0.8147 (0.8209) time: 0.1146 data: 0.0309 max mem: 9390 +Train: [50] [1400/6250] eta: 0:10:55 lr: 0.000067 grad: 0.0817 (0.0901) loss: 0.8172 (0.8206) time: 0.1476 data: 0.0653 max mem: 9390 +Train: [50] [1500/6250] eta: 0:10:39 lr: 0.000067 grad: 0.0829 (0.0901) loss: 0.8179 (0.8201) time: 0.1351 data: 0.0592 max mem: 9390 +Train: [50] [1600/6250] eta: 0:10:23 lr: 0.000067 grad: 0.0878 (0.0904) loss: 0.8169 (0.8197) time: 0.1230 data: 0.0408 max mem: 9390 +Train: [50] [1700/6250] eta: 0:10:08 lr: 0.000067 grad: 0.0864 (0.0904) loss: 0.8121 (0.8194) time: 0.1245 data: 0.0477 max mem: 9390 +Train: [50] [1800/6250] eta: 0:09:55 lr: 0.000067 grad: 0.0910 (0.0904) loss: 0.8169 (0.8193) time: 0.1608 data: 0.0807 max mem: 9390 +Train: [50] [1900/6250] eta: 0:09:46 lr: 0.000067 grad: 0.0876 (0.0905) loss: 0.8099 (0.8189) time: 0.1543 data: 0.0597 max mem: 9390 +Train: [50] [2000/6250] eta: 0:09:35 lr: 0.000067 grad: 0.0869 (0.0906) loss: 0.8138 (0.8188) time: 0.1602 data: 0.0844 max mem: 9390 +Train: [50] [2100/6250] eta: 0:09:23 lr: 0.000067 grad: 0.0836 (0.0905) loss: 0.8070 (0.8186) time: 0.1280 data: 0.0395 max mem: 9390 +Train: [50] [2200/6250] eta: 0:09:10 lr: 0.000067 grad: 0.0871 (0.0905) loss: 0.8160 (0.8184) time: 0.1405 data: 0.0601 max mem: 9390 +Train: [50] [2300/6250] eta: 0:08:58 lr: 0.000067 grad: 0.0890 (0.0904) loss: 0.8123 (0.8183) time: 0.1286 data: 0.0498 max mem: 9390 +Train: [50] [2400/6250] eta: 0:08:44 lr: 0.000067 grad: 0.0852 (0.0905) loss: 0.8169 (0.8182) time: 0.1470 data: 0.0678 max mem: 9390 +Train: [50] [2500/6250] eta: 0:08:29 lr: 0.000067 grad: 0.0868 (0.0906) loss: 0.8166 (0.8182) time: 0.1317 data: 0.0516 max mem: 9390 +Train: [50] [2600/6250] eta: 0:08:15 lr: 0.000067 grad: 0.0872 (0.0906) loss: 0.8147 (0.8181) time: 0.1262 data: 0.0490 max mem: 9390 +Train: [50] [2700/6250] eta: 0:08:00 lr: 0.000067 grad: 0.0893 (0.0906) loss: 0.8270 (0.8182) time: 0.1192 data: 0.0393 max mem: 9390 +Train: [50] [2800/6250] eta: 0:07:45 lr: 0.000067 grad: 0.0848 (0.0907) loss: 0.8187 (0.8181) time: 0.1274 data: 0.0441 max mem: 9390 +Train: [50] [2900/6250] eta: 0:07:30 lr: 0.000067 grad: 0.0869 (0.0907) loss: 0.8234 (0.8182) time: 0.1099 data: 0.0251 max mem: 9390 +Train: [50] [3000/6250] eta: 0:07:14 lr: 0.000067 grad: 0.0900 (0.0907) loss: 0.8222 (0.8182) time: 0.1230 data: 0.0401 max mem: 9390 +Train: [50] [3100/6250] eta: 0:06:59 lr: 0.000067 grad: 0.0923 (0.0907) loss: 0.8110 (0.8181) time: 0.1083 data: 0.0266 max mem: 9390 +Train: [50] [3200/6250] eta: 0:06:46 lr: 0.000067 grad: 0.0903 (0.0908) loss: 0.8239 (0.8181) time: 0.1387 data: 0.0605 max mem: 9390 +Train: [50] [3300/6250] eta: 0:06:32 lr: 0.000067 grad: 0.0858 (0.0909) loss: 0.8210 (0.8181) time: 0.1431 data: 0.0612 max mem: 9390 +Train: [50] [3400/6250] eta: 0:06:18 lr: 0.000067 grad: 0.0912 (0.0910) loss: 0.8209 (0.8180) time: 0.1434 data: 0.0662 max mem: 9390 +Train: [50] [3500/6250] eta: 0:06:05 lr: 0.000067 grad: 0.0909 (0.0910) loss: 0.8242 (0.8180) time: 0.1268 data: 0.0496 max mem: 9390 +Train: [50] [3600/6250] eta: 0:05:51 lr: 0.000066 grad: 0.0906 (0.0911) loss: 0.8199 (0.8180) time: 0.1016 data: 0.0241 max mem: 9390 +Train: [50] [3700/6250] eta: 0:05:37 lr: 0.000066 grad: 0.0931 (0.0911) loss: 0.8161 (0.8180) time: 0.1294 data: 0.0497 max mem: 9390 +Train: [50] [3800/6250] eta: 0:05:24 lr: 0.000066 grad: 0.0925 (0.0912) loss: 0.8200 (0.8180) time: 0.1351 data: 0.0562 max mem: 9390 +Train: [50] [3900/6250] eta: 0:05:10 lr: 0.000066 grad: 0.0904 (0.0912) loss: 0.8133 (0.8180) time: 0.1301 data: 0.0540 max mem: 9390 +Train: [50] [4000/6250] eta: 0:04:57 lr: 0.000066 grad: 0.0994 (0.0912) loss: 0.8153 (0.8180) time: 0.1399 data: 0.0627 max mem: 9390 +Train: [50] [4100/6250] eta: 0:04:44 lr: 0.000066 grad: 0.0923 (0.0913) loss: 0.8201 (0.8180) time: 0.1332 data: 0.0592 max mem: 9390 +Train: [50] [4200/6250] eta: 0:04:31 lr: 0.000066 grad: 0.0890 (0.0913) loss: 0.8195 (0.8180) time: 0.1492 data: 0.0593 max mem: 9390 +Train: [50] [4300/6250] eta: 0:04:17 lr: 0.000066 grad: 0.0841 (0.0914) loss: 0.8175 (0.8180) time: 0.1260 data: 0.0385 max mem: 9390 +Train: [50] [4400/6250] eta: 0:04:04 lr: 0.000066 grad: 0.0885 (0.0913) loss: 0.8133 (0.8180) time: 0.1243 data: 0.0507 max mem: 9390 +Train: [50] [4500/6250] eta: 0:03:50 lr: 0.000066 grad: 0.0924 (0.0914) loss: 0.8176 (0.8180) time: 0.1363 data: 0.0582 max mem: 9390 +Train: [50] [4600/6250] eta: 0:03:37 lr: 0.000066 grad: 0.0914 (0.0914) loss: 0.8200 (0.8180) time: 0.1310 data: 0.0534 max mem: 9390 +Train: [50] [4700/6250] eta: 0:03:24 lr: 0.000066 grad: 0.0937 (0.0914) loss: 0.8147 (0.8180) time: 0.1338 data: 0.0547 max mem: 9390 +Train: [50] [4800/6250] eta: 0:03:10 lr: 0.000066 grad: 0.0883 (0.0914) loss: 0.8215 (0.8181) time: 0.1247 data: 0.0492 max mem: 9390 +Train: [50] [4900/6250] eta: 0:02:57 lr: 0.000066 grad: 0.0928 (0.0914) loss: 0.8154 (0.8181) time: 0.1276 data: 0.0517 max mem: 9390 +Train: [50] [5000/6250] eta: 0:02:44 lr: 0.000066 grad: 0.0882 (0.0914) loss: 0.8193 (0.8181) time: 0.1493 data: 0.0732 max mem: 9390 +Train: [50] [5100/6250] eta: 0:02:31 lr: 0.000066 grad: 0.0867 (0.0914) loss: 0.8210 (0.8181) time: 0.1448 data: 0.0636 max mem: 9390 +Train: [50] [5200/6250] eta: 0:02:18 lr: 0.000066 grad: 0.0883 (0.0914) loss: 0.8223 (0.8181) time: 0.1422 data: 0.0511 max mem: 9390 +Train: [50] [5300/6250] eta: 0:02:05 lr: 0.000066 grad: 0.0930 (0.0915) loss: 0.8198 (0.8181) time: 0.1424 data: 0.0618 max mem: 9390 +Train: [50] [5400/6250] eta: 0:01:52 lr: 0.000066 grad: 0.0869 (0.0915) loss: 0.8162 (0.8181) time: 0.1378 data: 0.0639 max mem: 9390 +Train: [50] [5500/6250] eta: 0:01:39 lr: 0.000066 grad: 0.0876 (0.0914) loss: 0.8119 (0.8181) time: 0.1490 data: 0.0638 max mem: 9390 +Train: [50] [5600/6250] eta: 0:01:26 lr: 0.000066 grad: 0.0891 (0.0914) loss: 0.8184 (0.8182) time: 0.1342 data: 0.0506 max mem: 9390 +Train: [50] [5700/6250] eta: 0:01:13 lr: 0.000066 grad: 0.0822 (0.0915) loss: 0.8221 (0.8182) time: 0.1382 data: 0.0546 max mem: 9390 +Train: [50] [5800/6250] eta: 0:01:00 lr: 0.000066 grad: 0.0943 (0.0915) loss: 0.8202 (0.8182) time: 0.0858 data: 0.0003 max mem: 9390 +Train: [50] [5900/6250] eta: 0:00:46 lr: 0.000066 grad: 0.0931 (0.0915) loss: 0.8166 (0.8182) time: 0.1171 data: 0.0406 max mem: 9390 +Train: [50] [6000/6250] eta: 0:00:33 lr: 0.000066 grad: 0.0989 (0.0916) loss: 0.8174 (0.8182) time: 0.1649 data: 0.0476 max mem: 9390 +Train: [50] [6100/6250] eta: 0:00:19 lr: 0.000066 grad: 0.0923 (0.0916) loss: 0.8190 (0.8182) time: 0.1204 data: 0.0399 max mem: 9390 +Train: [50] [6200/6250] eta: 0:00:06 lr: 0.000066 grad: 0.0900 (0.0916) loss: 0.8178 (0.8182) time: 0.1431 data: 0.0684 max mem: 9390 +Train: [50] [6249/6250] eta: 0:00:00 lr: 0.000066 grad: 0.0944 (0.0916) loss: 0.8179 (0.8182) time: 0.1809 data: 0.1006 max mem: 9390 +Train: [50] Total time: 0:14:00 (0.1345 s / it) +Averaged stats: lr: 0.000066 grad: 0.0944 (0.0916) loss: 0.8179 (0.8182) +Eval (hcp-train-subset): [50] [ 0/62] eta: 0:03:25 loss: 0.8518 (0.8518) time: 3.3072 data: 3.2173 max mem: 9390 +Eval (hcp-train-subset): [50] [61/62] eta: 0:00:00 loss: 0.8334 (0.8361) time: 0.1260 data: 0.1011 max mem: 9390 +Eval (hcp-train-subset): [50] Total time: 0:00:11 (0.1912 s / it) +Averaged stats (hcp-train-subset): loss: 0.8334 (0.8361) +Eval (hcp-val): [50] [ 0/62] eta: 0:05:50 loss: 0.8354 (0.8354) time: 5.6453 data: 5.6163 max mem: 9390 +Eval (hcp-val): [50] [61/62] eta: 0:00:00 loss: 0.8341 (0.8354) time: 0.1099 data: 0.0851 max mem: 9390 +Eval (hcp-val): [50] Total time: 0:00:13 (0.2101 s / it) +Averaged stats (hcp-val): loss: 0.8341 (0.8354) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +Train: [51] [ 0/6250] eta: 9:48:07 lr: 0.000066 grad: 0.0468 (0.0468) loss: 0.8717 (0.8717) time: 5.6461 data: 5.5513 max mem: 9390 +Train: [51] [ 100/6250] eta: 0:20:10 lr: 0.000066 grad: 0.0862 (0.0949) loss: 0.8239 (0.8352) time: 0.1620 data: 0.0685 max mem: 9390 +Train: [51] [ 200/6250] eta: 0:17:32 lr: 0.000066 grad: 0.0854 (0.0944) loss: 0.8108 (0.8263) time: 0.1462 data: 0.0622 max mem: 9390 +Train: [51] [ 300/6250] eta: 0:16:17 lr: 0.000065 grad: 0.0919 (0.0941) loss: 0.8173 (0.8217) time: 0.1540 data: 0.0720 max mem: 9390 +Train: [51] [ 400/6250] eta: 0:15:15 lr: 0.000065 grad: 0.0887 (0.0930) loss: 0.8135 (0.8197) time: 0.1331 data: 0.0408 max mem: 9390 +Train: [51] [ 500/6250] eta: 0:14:27 lr: 0.000065 grad: 0.0867 (0.0923) loss: 0.8182 (0.8190) time: 0.1237 data: 0.0376 max mem: 9390 +Train: [51] [ 600/6250] eta: 0:13:53 lr: 0.000065 grad: 0.0846 (0.0918) loss: 0.8155 (0.8181) time: 0.1341 data: 0.0495 max mem: 9390 +Train: [51] [ 700/6250] eta: 0:13:23 lr: 0.000065 grad: 0.0832 (0.0908) loss: 0.8211 (0.8183) time: 0.1226 data: 0.0422 max mem: 9390 +Train: [51] [ 800/6250] eta: 0:13:01 lr: 0.000065 grad: 0.0824 (0.0902) loss: 0.8215 (0.8183) time: 0.1055 data: 0.0196 max mem: 9390 +Train: [51] [ 900/6250] eta: 0:12:44 lr: 0.000065 grad: 0.0834 (0.0894) loss: 0.8182 (0.8185) time: 0.1429 data: 0.0653 max mem: 9390 +Train: [51] [1000/6250] eta: 0:12:23 lr: 0.000065 grad: 0.0806 (0.0886) loss: 0.8255 (0.8189) time: 0.1346 data: 0.0597 max mem: 9390 +Train: [51] [1100/6250] eta: 0:12:06 lr: 0.000065 grad: 0.0793 (0.0881) loss: 0.8209 (0.8192) time: 0.1651 data: 0.0843 max mem: 9390 +Train: [51] [1200/6250] eta: 0:11:49 lr: 0.000065 grad: 0.0831 (0.0877) loss: 0.8274 (0.8195) time: 0.1393 data: 0.0596 max mem: 9390 +Train: [51] [1300/6250] eta: 0:11:29 lr: 0.000065 grad: 0.0866 (0.0876) loss: 0.8211 (0.8196) time: 0.1170 data: 0.0361 max mem: 9390 +Train: [51] [1400/6250] eta: 0:11:17 lr: 0.000065 grad: 0.0829 (0.0875) loss: 0.8199 (0.8197) time: 0.0856 data: 0.0002 max mem: 9390 +Train: [51] [1500/6250] eta: 0:11:03 lr: 0.000065 grad: 0.0903 (0.0875) loss: 0.8189 (0.8197) time: 0.1502 data: 0.0729 max mem: 9390 +Train: [51] [1600/6250] eta: 0:10:45 lr: 0.000065 grad: 0.0901 (0.0878) loss: 0.8162 (0.8195) time: 0.1362 data: 0.0612 max mem: 9390 +Train: [51] [1700/6250] eta: 0:10:27 lr: 0.000065 grad: 0.0902 (0.0878) loss: 0.8184 (0.8195) time: 0.1098 data: 0.0331 max mem: 9390 +Train: [51] [1800/6250] eta: 0:10:13 lr: 0.000065 grad: 0.0837 (0.0877) loss: 0.8203 (0.8195) time: 0.1415 data: 0.0681 max mem: 9390 +Train: [51] [1900/6250] eta: 0:09:57 lr: 0.000065 grad: 0.0864 (0.0878) loss: 0.8209 (0.8195) time: 0.1327 data: 0.0584 max mem: 9390 +Train: [51] [2000/6250] eta: 0:09:43 lr: 0.000065 grad: 0.0820 (0.0878) loss: 0.8244 (0.8196) time: 0.1445 data: 0.0582 max mem: 9390 +Train: [51] [2100/6250] eta: 0:09:31 lr: 0.000065 grad: 0.0864 (0.0878) loss: 0.8222 (0.8196) time: 0.1291 data: 0.0577 max mem: 9390 +Train: [51] [2200/6250] eta: 0:09:17 lr: 0.000065 grad: 0.0794 (0.0877) loss: 0.8230 (0.8197) time: 0.1478 data: 0.0715 max mem: 9390 +Train: [51] [2300/6250] eta: 0:09:06 lr: 0.000065 grad: 0.0818 (0.0877) loss: 0.8222 (0.8199) time: 0.1486 data: 0.0662 max mem: 9390 +Train: [51] [2400/6250] eta: 0:08:54 lr: 0.000065 grad: 0.0865 (0.0877) loss: 0.8176 (0.8199) time: 0.1135 data: 0.0362 max mem: 9390 +Train: [51] [2500/6250] eta: 0:08:41 lr: 0.000065 grad: 0.0879 (0.0877) loss: 0.8196 (0.8199) time: 0.1560 data: 0.0807 max mem: 9390 +Train: [51] [2600/6250] eta: 0:08:27 lr: 0.000065 grad: 0.0877 (0.0878) loss: 0.8209 (0.8199) time: 0.1306 data: 0.0487 max mem: 9390 +Train: [51] [2700/6250] eta: 0:08:13 lr: 0.000065 grad: 0.0894 (0.0878) loss: 0.8209 (0.8199) time: 0.1479 data: 0.0718 max mem: 9390 +Train: [51] [2800/6250] eta: 0:07:57 lr: 0.000065 grad: 0.0836 (0.0879) loss: 0.8171 (0.8199) time: 0.1351 data: 0.0531 max mem: 9390 +Train: [51] [2900/6250] eta: 0:07:40 lr: 0.000065 grad: 0.0879 (0.0879) loss: 0.8216 (0.8200) time: 0.1202 data: 0.0348 max mem: 9390 +Train: [51] [3000/6250] eta: 0:07:25 lr: 0.000065 grad: 0.0867 (0.0880) loss: 0.8148 (0.8200) time: 0.1128 data: 0.0375 max mem: 9390 +Train: [51] [3100/6250] eta: 0:07:10 lr: 0.000065 grad: 0.0849 (0.0879) loss: 0.8212 (0.8201) time: 0.1305 data: 0.0493 max mem: 9390 +Train: [51] [3200/6250] eta: 0:06:56 lr: 0.000065 grad: 0.0867 (0.0880) loss: 0.8272 (0.8201) time: 0.1472 data: 0.0634 max mem: 9390 +Train: [51] [3300/6250] eta: 0:06:42 lr: 0.000065 grad: 0.0878 (0.0880) loss: 0.8229 (0.8202) time: 0.1335 data: 0.0607 max mem: 9390 +Train: [51] [3400/6250] eta: 0:06:28 lr: 0.000064 grad: 0.0824 (0.0880) loss: 0.8264 (0.8203) time: 0.1390 data: 0.0586 max mem: 9390 +Train: [51] [3500/6250] eta: 0:06:15 lr: 0.000064 grad: 0.0809 (0.0879) loss: 0.8261 (0.8204) time: 0.1377 data: 0.0581 max mem: 9390 +Train: [51] [3600/6250] eta: 0:06:02 lr: 0.000064 grad: 0.0916 (0.0880) loss: 0.8246 (0.8205) time: 0.1504 data: 0.0752 max mem: 9390 +Train: [51] [3700/6250] eta: 0:05:48 lr: 0.000064 grad: 0.0869 (0.0880) loss: 0.8219 (0.8206) time: 0.1434 data: 0.0625 max mem: 9390 +Train: [51] [3800/6250] eta: 0:05:35 lr: 0.000064 grad: 0.0816 (0.0879) loss: 0.8241 (0.8207) time: 0.1607 data: 0.0736 max mem: 9390 +Train: [51] [3900/6250] eta: 0:05:21 lr: 0.000064 grad: 0.0880 (0.0879) loss: 0.8224 (0.8208) time: 0.1264 data: 0.0421 max mem: 9390 +Train: [51] [4000/6250] eta: 0:05:07 lr: 0.000064 grad: 0.0853 (0.0880) loss: 0.8265 (0.8209) time: 0.1368 data: 0.0598 max mem: 9390 +Train: [51] [4100/6250] eta: 0:04:52 lr: 0.000064 grad: 0.0892 (0.0881) loss: 0.8174 (0.8209) time: 0.1166 data: 0.0395 max mem: 9390 +Train: [51] [4200/6250] eta: 0:04:39 lr: 0.000064 grad: 0.0902 (0.0881) loss: 0.8191 (0.8210) time: 0.1383 data: 0.0609 max mem: 9390 +Train: [51] [4300/6250] eta: 0:04:25 lr: 0.000064 grad: 0.0848 (0.0881) loss: 0.8263 (0.8211) time: 0.1284 data: 0.0438 max mem: 9390 +Train: [51] [4400/6250] eta: 0:04:11 lr: 0.000064 grad: 0.0880 (0.0881) loss: 0.8267 (0.8211) time: 0.1474 data: 0.0678 max mem: 9390 +Train: [51] [4500/6250] eta: 0:03:57 lr: 0.000064 grad: 0.0857 (0.0881) loss: 0.8255 (0.8212) time: 0.1350 data: 0.0476 max mem: 9390 +Train: [51] [4600/6250] eta: 0:03:44 lr: 0.000064 grad: 0.0834 (0.0881) loss: 0.8215 (0.8213) time: 0.1466 data: 0.0632 max mem: 9390 +Train: [51] [4700/6250] eta: 0:03:30 lr: 0.000064 grad: 0.0874 (0.0882) loss: 0.8175 (0.8213) time: 0.1277 data: 0.0481 max mem: 9390 +Train: [51] [4800/6250] eta: 0:03:16 lr: 0.000064 grad: 0.0843 (0.0882) loss: 0.8200 (0.8213) time: 0.1175 data: 0.0402 max mem: 9390 +Train: [51] [4900/6250] eta: 0:03:02 lr: 0.000064 grad: 0.0877 (0.0883) loss: 0.8265 (0.8213) time: 0.1251 data: 0.0480 max mem: 9390 +Train: [51] [5000/6250] eta: 0:02:48 lr: 0.000064 grad: 0.0937 (0.0883) loss: 0.8206 (0.8213) time: 0.1232 data: 0.0443 max mem: 9390 +Train: [51] [5100/6250] eta: 0:02:35 lr: 0.000064 grad: 0.0891 (0.0883) loss: 0.8217 (0.8213) time: 0.1476 data: 0.0644 max mem: 9390 +Train: [51] [5200/6250] eta: 0:02:22 lr: 0.000064 grad: 0.0863 (0.0884) loss: 0.8243 (0.8213) time: 0.1485 data: 0.0729 max mem: 9390 +Train: [51] [5300/6250] eta: 0:02:08 lr: 0.000064 grad: 0.0837 (0.0884) loss: 0.8271 (0.8214) time: 0.1481 data: 0.0693 max mem: 9390 +Train: [51] [5400/6250] eta: 0:01:55 lr: 0.000064 grad: 0.0836 (0.0884) loss: 0.8191 (0.8214) time: 0.1445 data: 0.0664 max mem: 9390 +Train: [51] [5500/6250] eta: 0:01:41 lr: 0.000064 grad: 0.0866 (0.0885) loss: 0.8245 (0.8214) time: 0.1363 data: 0.0493 max mem: 9390 +Train: [51] [5600/6250] eta: 0:01:28 lr: 0.000064 grad: 0.0865 (0.0885) loss: 0.8288 (0.8214) time: 0.1240 data: 0.0419 max mem: 9390 +Train: [51] [5700/6250] eta: 0:01:14 lr: 0.000064 grad: 0.0880 (0.0885) loss: 0.8184 (0.8214) time: 0.1406 data: 0.0648 max mem: 9390 +Train: [51] [5800/6250] eta: 0:01:01 lr: 0.000064 grad: 0.0853 (0.0885) loss: 0.8204 (0.8214) time: 0.1339 data: 0.0554 max mem: 9390 +Train: [51] [5900/6250] eta: 0:00:47 lr: 0.000064 grad: 0.0859 (0.0885) loss: 0.8284 (0.8214) time: 0.1445 data: 0.0584 max mem: 9390 +Train: [51] [6000/6250] eta: 0:00:33 lr: 0.000064 grad: 0.0840 (0.0885) loss: 0.8248 (0.8215) time: 0.1500 data: 0.0636 max mem: 9390 +Train: [51] [6100/6250] eta: 0:00:20 lr: 0.000064 grad: 0.0840 (0.0885) loss: 0.8211 (0.8215) time: 0.1343 data: 0.0470 max mem: 9390 +Train: [51] [6200/6250] eta: 0:00:06 lr: 0.000064 grad: 0.0897 (0.0886) loss: 0.8180 (0.8215) time: 0.1500 data: 0.0636 max mem: 9390 +Train: [51] [6249/6250] eta: 0:00:00 lr: 0.000064 grad: 0.0919 (0.0886) loss: 0.8207 (0.8215) time: 0.1382 data: 0.0641 max mem: 9390 +Train: [51] Total time: 0:14:17 (0.1372 s / it) +Averaged stats: lr: 0.000064 grad: 0.0919 (0.0886) loss: 0.8207 (0.8215) +Eval (hcp-train-subset): [51] [ 0/62] eta: 0:03:35 loss: 0.8509 (0.8509) time: 3.4749 data: 3.4104 max mem: 9390 +Eval (hcp-train-subset): [51] [61/62] eta: 0:00:00 loss: 0.8347 (0.8363) time: 0.1175 data: 0.0925 max mem: 9390 +Eval (hcp-train-subset): [51] Total time: 0:00:11 (0.1925 s / it) +Averaged stats (hcp-train-subset): loss: 0.8347 (0.8363) +Eval (hcp-val): [51] [ 0/62] eta: 0:04:25 loss: 0.8311 (0.8311) time: 4.2877 data: 4.2455 max mem: 9390 +Eval (hcp-val): [51] [61/62] eta: 0:00:00 loss: 0.8346 (0.8357) time: 0.1243 data: 0.0978 max mem: 9390 +Eval (hcp-val): [51] Total time: 0:00:12 (0.2097 s / it) +Averaged stats (hcp-val): loss: 0.8346 (0.8357) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +Train: [52] [ 0/6250] eta: 10:06:41 lr: 0.000064 grad: 0.1526 (0.1526) loss: 0.8323 (0.8323) time: 5.8242 data: 5.7057 max mem: 9390 +Train: [52] [ 100/6250] eta: 0:19:40 lr: 0.000063 grad: 0.0955 (0.1098) loss: 0.8277 (0.8328) time: 0.1337 data: 0.0453 max mem: 9390 +Train: [52] [ 200/6250] eta: 0:17:29 lr: 0.000063 grad: 0.0984 (0.1045) loss: 0.8186 (0.8293) time: 0.1536 data: 0.0688 max mem: 9390 +Train: [52] [ 300/6250] eta: 0:16:19 lr: 0.000063 grad: 0.0926 (0.1001) loss: 0.8322 (0.8280) time: 0.1628 data: 0.0822 max mem: 9390 +Train: [52] [ 400/6250] eta: 0:15:26 lr: 0.000063 grad: 0.0855 (0.0973) loss: 0.8268 (0.8277) time: 0.1396 data: 0.0544 max mem: 9390 +Train: [52] [ 500/6250] eta: 0:14:40 lr: 0.000063 grad: 0.0891 (0.0958) loss: 0.8216 (0.8269) time: 0.1325 data: 0.0504 max mem: 9390 +Train: [52] [ 600/6250] eta: 0:14:01 lr: 0.000063 grad: 0.0846 (0.0944) loss: 0.8215 (0.8264) time: 0.1032 data: 0.0166 max mem: 9390 +Train: [52] [ 700/6250] eta: 0:13:32 lr: 0.000063 grad: 0.0908 (0.0938) loss: 0.8206 (0.8258) time: 0.1486 data: 0.0663 max mem: 9390 +Train: [52] [ 800/6250] eta: 0:13:02 lr: 0.000063 grad: 0.0902 (0.0934) loss: 0.8206 (0.8253) time: 0.1346 data: 0.0483 max mem: 9390 +Train: [52] [ 900/6250] eta: 0:12:36 lr: 0.000063 grad: 0.0895 (0.0931) loss: 0.8241 (0.8249) time: 0.1342 data: 0.0532 max mem: 9390 +Train: [52] [1000/6250] eta: 0:12:18 lr: 0.000063 grad: 0.0888 (0.0928) loss: 0.8183 (0.8243) time: 0.1283 data: 0.0507 max mem: 9390 +Train: [52] [1100/6250] eta: 0:12:02 lr: 0.000063 grad: 0.0881 (0.0924) loss: 0.8162 (0.8239) time: 0.1464 data: 0.0714 max mem: 9390 +Train: [52] [1200/6250] eta: 0:11:38 lr: 0.000063 grad: 0.0871 (0.0923) loss: 0.8140 (0.8233) time: 0.1179 data: 0.0399 max mem: 9390 +Train: [52] [1300/6250] eta: 0:11:22 lr: 0.000063 grad: 0.0909 (0.0921) loss: 0.8154 (0.8229) time: 0.1395 data: 0.0605 max mem: 9390 +Train: [52] [1400/6250] eta: 0:11:04 lr: 0.000063 grad: 0.0879 (0.0919) loss: 0.8169 (0.8228) time: 0.1373 data: 0.0488 max mem: 9390 +Train: [52] [1500/6250] eta: 0:10:48 lr: 0.000063 grad: 0.0904 (0.0919) loss: 0.8179 (0.8223) time: 0.1389 data: 0.0591 max mem: 9390 +Train: [52] [1600/6250] eta: 0:10:34 lr: 0.000063 grad: 0.0887 (0.0919) loss: 0.8171 (0.8221) time: 0.1431 data: 0.0593 max mem: 9390 +Train: [52] [1700/6250] eta: 0:10:25 lr: 0.000063 grad: 0.0873 (0.0919) loss: 0.8192 (0.8218) time: 0.2000 data: 0.1271 max mem: 9390 +Train: [52] [1800/6250] eta: 0:10:08 lr: 0.000063 grad: 0.0893 (0.0919) loss: 0.8195 (0.8216) time: 0.1291 data: 0.0443 max mem: 9390 +Train: [52] [1900/6250] eta: 0:09:52 lr: 0.000063 grad: 0.0862 (0.0917) loss: 0.8204 (0.8213) time: 0.1324 data: 0.0503 max mem: 9390 +Train: [52] [2000/6250] eta: 0:09:36 lr: 0.000063 grad: 0.0832 (0.0917) loss: 0.8145 (0.8211) time: 0.1167 data: 0.0418 max mem: 9390 +Train: [52] [2100/6250] eta: 0:09:27 lr: 0.000063 grad: 0.0822 (0.0916) loss: 0.8234 (0.8210) time: 0.1453 data: 0.0599 max mem: 9390 +Train: [52] [2200/6250] eta: 0:09:15 lr: 0.000063 grad: 0.0935 (0.0915) loss: 0.8190 (0.8210) time: 0.1448 data: 0.0688 max mem: 9390 +Train: [52] [2300/6250] eta: 0:09:02 lr: 0.000063 grad: 0.0898 (0.0915) loss: 0.8186 (0.8209) time: 0.1667 data: 0.0849 max mem: 9390 +Train: [52] [2400/6250] eta: 0:08:49 lr: 0.000063 grad: 0.0866 (0.0915) loss: 0.8191 (0.8209) time: 0.1113 data: 0.0299 max mem: 9390 +Train: [52] [2500/6250] eta: 0:08:36 lr: 0.000063 grad: 0.0875 (0.0913) loss: 0.8214 (0.8209) time: 0.1353 data: 0.0556 max mem: 9390 +Train: [52] [2600/6250] eta: 0:08:22 lr: 0.000063 grad: 0.0842 (0.0913) loss: 0.8216 (0.8209) time: 0.1172 data: 0.0304 max mem: 9390 +Train: [52] [2700/6250] eta: 0:08:06 lr: 0.000063 grad: 0.0945 (0.0914) loss: 0.8153 (0.8208) time: 0.1249 data: 0.0459 max mem: 9390 +Train: [52] [2800/6250] eta: 0:07:51 lr: 0.000063 grad: 0.0844 (0.0913) loss: 0.8256 (0.8207) time: 0.1279 data: 0.0498 max mem: 9390 +Train: [52] [2900/6250] eta: 0:07:36 lr: 0.000063 grad: 0.0899 (0.0914) loss: 0.8195 (0.8207) time: 0.1438 data: 0.0654 max mem: 9390 +Train: [52] [3000/6250] eta: 0:07:20 lr: 0.000063 grad: 0.0902 (0.0914) loss: 0.8159 (0.8206) time: 0.1110 data: 0.0228 max mem: 9390 +Train: [52] [3100/6250] eta: 0:07:05 lr: 0.000063 grad: 0.0954 (0.0915) loss: 0.8226 (0.8206) time: 0.1272 data: 0.0474 max mem: 9390 +Train: [52] [3200/6250] eta: 0:06:50 lr: 0.000062 grad: 0.0896 (0.0915) loss: 0.8184 (0.8205) time: 0.1223 data: 0.0458 max mem: 9390 +Train: [52] [3300/6250] eta: 0:06:36 lr: 0.000062 grad: 0.0901 (0.0915) loss: 0.8202 (0.8205) time: 0.1247 data: 0.0473 max mem: 9390 +Train: [52] [3400/6250] eta: 0:06:22 lr: 0.000062 grad: 0.0961 (0.0915) loss: 0.8134 (0.8205) time: 0.1500 data: 0.0725 max mem: 9390 +Train: [52] [3500/6250] eta: 0:06:08 lr: 0.000062 grad: 0.0859 (0.0915) loss: 0.8276 (0.8205) time: 0.1521 data: 0.0677 max mem: 9390 +Train: [52] [3600/6250] eta: 0:05:54 lr: 0.000062 grad: 0.0905 (0.0916) loss: 0.8214 (0.8205) time: 0.1257 data: 0.0462 max mem: 9390 +Train: [52] [3700/6250] eta: 0:05:39 lr: 0.000062 grad: 0.0913 (0.0917) loss: 0.8189 (0.8205) time: 0.1173 data: 0.0366 max mem: 9390 +Train: [52] [3800/6250] eta: 0:05:26 lr: 0.000062 grad: 0.0943 (0.0918) loss: 0.8256 (0.8204) time: 0.1349 data: 0.0568 max mem: 9390 +Train: [52] [3900/6250] eta: 0:05:12 lr: 0.000062 grad: 0.0905 (0.0918) loss: 0.8178 (0.8203) time: 0.1160 data: 0.0392 max mem: 9390 +Train: [52] [4000/6250] eta: 0:04:58 lr: 0.000062 grad: 0.0851 (0.0918) loss: 0.8252 (0.8203) time: 0.1218 data: 0.0417 max mem: 9390 +Train: [52] [4100/6250] eta: 0:04:45 lr: 0.000062 grad: 0.0911 (0.0919) loss: 0.8218 (0.8203) time: 0.1486 data: 0.0657 max mem: 9390 +Train: [52] [4200/6250] eta: 0:04:32 lr: 0.000062 grad: 0.0881 (0.0918) loss: 0.8236 (0.8203) time: 0.1229 data: 0.0418 max mem: 9390 +Train: [52] [4300/6250] eta: 0:04:18 lr: 0.000062 grad: 0.0863 (0.0918) loss: 0.8191 (0.8203) time: 0.1217 data: 0.0418 max mem: 9390 +Train: [52] [4400/6250] eta: 0:04:05 lr: 0.000062 grad: 0.0892 (0.0919) loss: 0.8170 (0.8203) time: 0.1368 data: 0.0622 max mem: 9390 +Train: [52] [4500/6250] eta: 0:03:52 lr: 0.000062 grad: 0.0920 (0.0919) loss: 0.8199 (0.8203) time: 0.1306 data: 0.0490 max mem: 9390 +Train: [52] [4600/6250] eta: 0:03:38 lr: 0.000062 grad: 0.0888 (0.0919) loss: 0.8246 (0.8203) time: 0.1318 data: 0.0489 max mem: 9390 +Train: [52] [4700/6250] eta: 0:03:25 lr: 0.000062 grad: 0.0920 (0.0919) loss: 0.8190 (0.8203) time: 0.1434 data: 0.0703 max mem: 9390 +Train: [52] [4800/6250] eta: 0:03:11 lr: 0.000062 grad: 0.0937 (0.0919) loss: 0.8187 (0.8203) time: 0.1270 data: 0.0473 max mem: 9390 +Train: [52] [4900/6250] eta: 0:02:58 lr: 0.000062 grad: 0.0820 (0.0919) loss: 0.8262 (0.8203) time: 0.1290 data: 0.0509 max mem: 9390 +Train: [52] [5000/6250] eta: 0:02:45 lr: 0.000062 grad: 0.0857 (0.0919) loss: 0.8189 (0.8204) time: 0.1404 data: 0.0561 max mem: 9390 +Train: [52] [5100/6250] eta: 0:02:31 lr: 0.000062 grad: 0.0902 (0.0919) loss: 0.8202 (0.8204) time: 0.1325 data: 0.0611 max mem: 9390 +Train: [52] [5200/6250] eta: 0:02:18 lr: 0.000062 grad: 0.0885 (0.0919) loss: 0.8210 (0.8204) time: 0.1025 data: 0.0309 max mem: 9390 +Train: [52] [5300/6250] eta: 0:02:05 lr: 0.000062 grad: 0.0953 (0.0919) loss: 0.8166 (0.8204) time: 0.1394 data: 0.0629 max mem: 9390 +Train: [52] [5400/6250] eta: 0:01:52 lr: 0.000062 grad: 0.0910 (0.0920) loss: 0.8255 (0.8204) time: 0.1462 data: 0.0668 max mem: 9390 +Train: [52] [5500/6250] eta: 0:01:39 lr: 0.000062 grad: 0.0938 (0.0921) loss: 0.8157 (0.8204) time: 0.1328 data: 0.0557 max mem: 9390 +Train: [52] [5600/6250] eta: 0:01:26 lr: 0.000062 grad: 0.0899 (0.0921) loss: 0.8213 (0.8204) time: 0.1464 data: 0.0621 max mem: 9390 +Train: [52] [5700/6250] eta: 0:01:12 lr: 0.000062 grad: 0.0870 (0.0921) loss: 0.8255 (0.8204) time: 0.1321 data: 0.0478 max mem: 9390 +Train: [52] [5800/6250] eta: 0:00:59 lr: 0.000062 grad: 0.0948 (0.0922) loss: 0.8199 (0.8204) time: 0.1314 data: 0.0521 max mem: 9390 +Train: [52] [5900/6250] eta: 0:00:46 lr: 0.000062 grad: 0.0885 (0.0924) loss: 0.8198 (0.8204) time: 0.1351 data: 0.0516 max mem: 9390 +Train: [52] [6000/6250] eta: 0:00:33 lr: 0.000062 grad: 0.0934 (0.0924) loss: 0.8176 (0.8205) time: 0.1150 data: 0.0329 max mem: 9390 +Train: [52] [6100/6250] eta: 0:00:19 lr: 0.000062 grad: 0.0860 (0.0924) loss: 0.8203 (0.8205) time: 0.1465 data: 0.0657 max mem: 9390 +Train: [52] [6200/6250] eta: 0:00:06 lr: 0.000061 grad: 0.0953 (0.0924) loss: 0.8161 (0.8205) time: 0.1445 data: 0.0680 max mem: 9390 +Train: [52] [6249/6250] eta: 0:00:00 lr: 0.000061 grad: 0.0913 (0.0924) loss: 0.8219 (0.8205) time: 0.1262 data: 0.0477 max mem: 9390 +Train: [52] Total time: 0:13:59 (0.1344 s / it) +Averaged stats: lr: 0.000061 grad: 0.0913 (0.0924) loss: 0.8219 (0.8205) +Eval (hcp-train-subset): [52] [ 0/62] eta: 0:04:39 loss: 0.8437 (0.8437) time: 4.5086 data: 4.4800 max mem: 9390 +Eval (hcp-train-subset): [52] [61/62] eta: 0:00:00 loss: 0.8337 (0.8353) time: 0.1387 data: 0.1121 max mem: 9390 +Eval (hcp-train-subset): [52] Total time: 0:00:12 (0.2072 s / it) +Averaged stats (hcp-train-subset): loss: 0.8337 (0.8353) +Eval (hcp-val): [52] [ 0/62] eta: 0:03:55 loss: 0.8333 (0.8333) time: 3.7914 data: 3.7068 max mem: 9390 +Eval (hcp-val): [52] [61/62] eta: 0:00:00 loss: 0.8353 (0.8351) time: 0.1037 data: 0.0790 max mem: 9390 +Eval (hcp-val): [52] Total time: 0:00:12 (0.1977 s / it) +Averaged stats (hcp-val): loss: 0.8353 (0.8351) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +Train: [53] [ 0/6250] eta: 9:16:41 lr: 0.000061 grad: 0.0936 (0.0936) loss: 0.8545 (0.8545) time: 5.3443 data: 5.2376 max mem: 9390 +Train: [53] [ 100/6250] eta: 0:20:33 lr: 0.000061 grad: 0.0806 (0.0848) loss: 0.8284 (0.8367) time: 0.1340 data: 0.0397 max mem: 9390 +Train: [53] [ 200/6250] eta: 0:17:53 lr: 0.000061 grad: 0.0887 (0.0861) loss: 0.8247 (0.8326) time: 0.1510 data: 0.0751 max mem: 9390 +Train: [53] [ 300/6250] eta: 0:16:33 lr: 0.000061 grad: 0.0915 (0.0884) loss: 0.8165 (0.8300) time: 0.1222 data: 0.0371 max mem: 9390 +Train: [53] [ 400/6250] eta: 0:15:29 lr: 0.000061 grad: 0.0880 (0.0882) loss: 0.8201 (0.8280) time: 0.1167 data: 0.0235 max mem: 9390 +Train: [53] [ 500/6250] eta: 0:14:42 lr: 0.000061 grad: 0.0842 (0.0878) loss: 0.8246 (0.8273) time: 0.1372 data: 0.0568 max mem: 9390 +Train: [53] [ 600/6250] eta: 0:14:04 lr: 0.000061 grad: 0.0871 (0.0876) loss: 0.8298 (0.8271) time: 0.1196 data: 0.0306 max mem: 9390 +Train: [53] [ 700/6250] eta: 0:13:30 lr: 0.000061 grad: 0.0833 (0.0873) loss: 0.8266 (0.8268) time: 0.1205 data: 0.0405 max mem: 9390 +Train: [53] [ 800/6250] eta: 0:13:00 lr: 0.000061 grad: 0.0788 (0.0872) loss: 0.8286 (0.8265) time: 0.1141 data: 0.0279 max mem: 9390 +Train: [53] [ 900/6250] eta: 0:12:35 lr: 0.000061 grad: 0.0824 (0.0870) loss: 0.8298 (0.8263) time: 0.1143 data: 0.0302 max mem: 9390 +Train: [53] [1000/6250] eta: 0:12:14 lr: 0.000061 grad: 0.0823 (0.0868) loss: 0.8299 (0.8261) time: 0.1465 data: 0.0687 max mem: 9390 +Train: [53] [1100/6250] eta: 0:11:52 lr: 0.000061 grad: 0.0849 (0.0868) loss: 0.8223 (0.8259) time: 0.1244 data: 0.0453 max mem: 9390 +Train: [53] [1200/6250] eta: 0:11:35 lr: 0.000061 grad: 0.0834 (0.0867) loss: 0.8253 (0.8258) time: 0.1222 data: 0.0481 max mem: 9390 +Train: [53] [1300/6250] eta: 0:11:15 lr: 0.000061 grad: 0.0886 (0.0868) loss: 0.8199 (0.8257) time: 0.1058 data: 0.0270 max mem: 9390 +Train: [53] [1400/6250] eta: 0:10:59 lr: 0.000061 grad: 0.0894 (0.0870) loss: 0.8201 (0.8255) time: 0.1339 data: 0.0557 max mem: 9390 +Train: [53] [1500/6250] eta: 0:10:44 lr: 0.000061 grad: 0.0867 (0.0871) loss: 0.8201 (0.8254) time: 0.1308 data: 0.0434 max mem: 9390 +Train: [53] [1600/6250] eta: 0:10:31 lr: 0.000061 grad: 0.0871 (0.0873) loss: 0.8154 (0.8251) time: 0.1412 data: 0.0594 max mem: 9390 +Train: [53] [1700/6250] eta: 0:10:16 lr: 0.000061 grad: 0.0921 (0.0876) loss: 0.8185 (0.8248) time: 0.1248 data: 0.0418 max mem: 9390 +Train: [53] [1800/6250] eta: 0:10:01 lr: 0.000061 grad: 0.0906 (0.0879) loss: 0.8164 (0.8244) time: 0.1275 data: 0.0504 max mem: 9390 +Train: [53] [1900/6250] eta: 0:09:53 lr: 0.000061 grad: 0.0927 (0.0883) loss: 0.8236 (0.8240) time: 0.2234 data: 0.1346 max mem: 9390 +Train: [53] [2000/6250] eta: 0:09:40 lr: 0.000061 grad: 0.0960 (0.0886) loss: 0.8161 (0.8237) time: 0.0906 data: 0.0004 max mem: 9390 +Train: [53] [2100/6250] eta: 0:09:27 lr: 0.000061 grad: 0.0924 (0.0888) loss: 0.8098 (0.8235) time: 0.1456 data: 0.0694 max mem: 9390 +Train: [53] [2200/6250] eta: 0:09:18 lr: 0.000061 grad: 0.0913 (0.0890) loss: 0.8205 (0.8233) time: 0.1497 data: 0.0672 max mem: 9390 +Train: [53] [2300/6250] eta: 0:09:05 lr: 0.000061 grad: 0.0900 (0.0891) loss: 0.8192 (0.8231) time: 0.1432 data: 0.0712 max mem: 9390 +Train: [53] [2400/6250] eta: 0:08:54 lr: 0.000061 grad: 0.0903 (0.0893) loss: 0.8205 (0.8229) time: 0.1543 data: 0.0704 max mem: 9390 +Train: [53] [2500/6250] eta: 0:08:41 lr: 0.000061 grad: 0.0905 (0.0895) loss: 0.8181 (0.8228) time: 0.1428 data: 0.0611 max mem: 9390 +Train: [53] [2600/6250] eta: 0:08:28 lr: 0.000061 grad: 0.0945 (0.0897) loss: 0.8142 (0.8226) time: 0.1344 data: 0.0555 max mem: 9390 +Train: [53] [2700/6250] eta: 0:08:14 lr: 0.000061 grad: 0.0864 (0.0900) loss: 0.8199 (0.8224) time: 0.1423 data: 0.0663 max mem: 9390 +Train: [53] [2800/6250] eta: 0:07:59 lr: 0.000061 grad: 0.0938 (0.0902) loss: 0.8178 (0.8223) time: 0.1407 data: 0.0630 max mem: 9390 +Train: [53] [2900/6250] eta: 0:07:43 lr: 0.000061 grad: 0.0914 (0.0904) loss: 0.8182 (0.8222) time: 0.1152 data: 0.0306 max mem: 9390 +Train: [53] [3000/6250] eta: 0:07:28 lr: 0.000060 grad: 0.0903 (0.0904) loss: 0.8182 (0.8222) time: 0.1252 data: 0.0463 max mem: 9390 +Train: [53] [3100/6250] eta: 0:07:12 lr: 0.000060 grad: 0.0915 (0.0906) loss: 0.8230 (0.8221) time: 0.1230 data: 0.0431 max mem: 9390 +Train: [53] [3200/6250] eta: 0:06:57 lr: 0.000060 grad: 0.0945 (0.0908) loss: 0.8187 (0.8221) time: 0.1368 data: 0.0613 max mem: 9390 +Train: [53] [3300/6250] eta: 0:06:43 lr: 0.000060 grad: 0.0925 (0.0909) loss: 0.8178 (0.8220) time: 0.1297 data: 0.0519 max mem: 9390 +Train: [53] [3400/6250] eta: 0:06:28 lr: 0.000060 grad: 0.0943 (0.0911) loss: 0.8151 (0.8220) time: 0.1314 data: 0.0523 max mem: 9390 +Train: [53] [3500/6250] eta: 0:06:15 lr: 0.000060 grad: 0.0881 (0.0912) loss: 0.8209 (0.8219) time: 0.1239 data: 0.0463 max mem: 9390 +Train: [53] [3600/6250] eta: 0:06:01 lr: 0.000060 grad: 0.0930 (0.0913) loss: 0.8172 (0.8218) time: 0.1179 data: 0.0313 max mem: 9390 +Train: [53] [3700/6250] eta: 0:05:46 lr: 0.000060 grad: 0.0959 (0.0915) loss: 0.8132 (0.8217) time: 0.1288 data: 0.0454 max mem: 9390 +Train: [53] [3800/6250] eta: 0:05:32 lr: 0.000060 grad: 0.0928 (0.0916) loss: 0.8180 (0.8216) time: 0.1137 data: 0.0393 max mem: 9390 +Train: [53] [3900/6250] eta: 0:05:18 lr: 0.000060 grad: 0.0939 (0.0916) loss: 0.8244 (0.8216) time: 0.1312 data: 0.0480 max mem: 9390 +Train: [53] [4000/6250] eta: 0:05:04 lr: 0.000060 grad: 0.0905 (0.0917) loss: 0.8170 (0.8215) time: 0.1277 data: 0.0516 max mem: 9390 +Train: [53] [4100/6250] eta: 0:04:50 lr: 0.000060 grad: 0.0904 (0.0918) loss: 0.8192 (0.8215) time: 0.1181 data: 0.0445 max mem: 9390 +Train: [53] [4200/6250] eta: 0:04:36 lr: 0.000060 grad: 0.0875 (0.0918) loss: 0.8257 (0.8214) time: 0.1206 data: 0.0394 max mem: 9390 +Train: [53] [4300/6250] eta: 0:04:22 lr: 0.000060 grad: 0.0859 (0.0918) loss: 0.8202 (0.8213) time: 0.1331 data: 0.0570 max mem: 9390 +Train: [53] [4400/6250] eta: 0:04:08 lr: 0.000060 grad: 0.0924 (0.0919) loss: 0.8160 (0.8212) time: 0.1198 data: 0.0422 max mem: 9390 +Train: [53] [4500/6250] eta: 0:03:54 lr: 0.000060 grad: 0.0960 (0.0919) loss: 0.8201 (0.8212) time: 0.1287 data: 0.0515 max mem: 9390 +Train: [53] [4600/6250] eta: 0:03:40 lr: 0.000060 grad: 0.0883 (0.0920) loss: 0.8217 (0.8211) time: 0.1530 data: 0.0705 max mem: 9390 +Train: [53] [4700/6250] eta: 0:03:27 lr: 0.000060 grad: 0.0890 (0.0920) loss: 0.8240 (0.8211) time: 0.1297 data: 0.0491 max mem: 9390 +Train: [53] [4800/6250] eta: 0:03:14 lr: 0.000060 grad: 0.0938 (0.0920) loss: 0.8214 (0.8211) time: 0.1269 data: 0.0491 max mem: 9390 +Train: [53] [4900/6250] eta: 0:03:00 lr: 0.000060 grad: 0.0936 (0.0920) loss: 0.8160 (0.8211) time: 0.1208 data: 0.0351 max mem: 9390 +Train: [53] [5000/6250] eta: 0:02:47 lr: 0.000060 grad: 0.0914 (0.0920) loss: 0.8233 (0.8211) time: 0.1342 data: 0.0469 max mem: 9390 +Train: [53] [5100/6250] eta: 0:02:33 lr: 0.000060 grad: 0.0916 (0.0921) loss: 0.8246 (0.8210) time: 0.1421 data: 0.0641 max mem: 9390 +Train: [53] [5200/6250] eta: 0:02:20 lr: 0.000060 grad: 0.0952 (0.0921) loss: 0.8179 (0.8210) time: 0.1316 data: 0.0532 max mem: 9390 +Train: [53] [5300/6250] eta: 0:02:06 lr: 0.000060 grad: 0.0946 (0.0922) loss: 0.8224 (0.8210) time: 0.1183 data: 0.0410 max mem: 9390 +Train: [53] [5400/6250] eta: 0:01:53 lr: 0.000060 grad: 0.0850 (0.0922) loss: 0.8188 (0.8210) time: 0.1433 data: 0.0566 max mem: 9390 +Train: [53] [5500/6250] eta: 0:01:39 lr: 0.000060 grad: 0.0951 (0.0923) loss: 0.8180 (0.8210) time: 0.1492 data: 0.0682 max mem: 9390 +Train: [53] [5600/6250] eta: 0:01:26 lr: 0.000060 grad: 0.0885 (0.0923) loss: 0.8204 (0.8210) time: 0.1483 data: 0.0723 max mem: 9390 +Train: [53] [5700/6250] eta: 0:01:13 lr: 0.000060 grad: 0.0909 (0.0924) loss: 0.8204 (0.8209) time: 0.1298 data: 0.0447 max mem: 9390 +Train: [53] [5800/6250] eta: 0:01:00 lr: 0.000060 grad: 0.0859 (0.0925) loss: 0.8239 (0.8209) time: 0.1185 data: 0.0289 max mem: 9390 +Train: [53] [5900/6250] eta: 0:00:46 lr: 0.000060 grad: 0.0887 (0.0925) loss: 0.8171 (0.8209) time: 0.1424 data: 0.0550 max mem: 9390 +Train: [53] [6000/6250] eta: 0:00:33 lr: 0.000059 grad: 0.0966 (0.0926) loss: 0.8196 (0.8208) time: 0.1314 data: 0.0554 max mem: 9390 +Train: [53] [6100/6250] eta: 0:00:20 lr: 0.000059 grad: 0.0858 (0.0926) loss: 0.8189 (0.8208) time: 0.1915 data: 0.1132 max mem: 9390 +Train: [53] [6200/6250] eta: 0:00:06 lr: 0.000059 grad: 0.0970 (0.0926) loss: 0.8203 (0.8207) time: 0.1411 data: 0.0666 max mem: 9390 +Train: [53] [6249/6250] eta: 0:00:00 lr: 0.000059 grad: 0.0912 (0.0927) loss: 0.8256 (0.8207) time: 0.1503 data: 0.0659 max mem: 9390 +Train: [53] Total time: 0:14:03 (0.1349 s / it) +Averaged stats: lr: 0.000059 grad: 0.0912 (0.0927) loss: 0.8256 (0.8207) +Eval (hcp-train-subset): [53] [ 0/62] eta: 0:03:39 loss: 0.8446 (0.8446) time: 3.5341 data: 3.4685 max mem: 9390 +Eval (hcp-train-subset): [53] [61/62] eta: 0:00:00 loss: 0.8350 (0.8356) time: 0.1260 data: 0.0994 max mem: 9390 +Eval (hcp-train-subset): [53] Total time: 0:00:12 (0.2048 s / it) +Averaged stats (hcp-train-subset): loss: 0.8350 (0.8356) +Eval (hcp-val): [53] [ 0/62] eta: 0:04:34 loss: 0.8311 (0.8311) time: 4.4275 data: 4.3986 max mem: 9390 +Eval (hcp-val): [53] [61/62] eta: 0:00:00 loss: 0.8347 (0.8350) time: 0.1239 data: 0.0969 max mem: 9390 +Eval (hcp-val): [53] Total time: 0:00:12 (0.1981 s / it) +Averaged stats (hcp-val): loss: 0.8347 (0.8350) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +Train: [54] [ 0/6250] eta: 10:33:36 lr: 0.000059 grad: 0.1623 (0.1623) loss: 0.8376 (0.8376) time: 6.0826 data: 5.9875 max mem: 9390 +Train: [54] [ 100/6250] eta: 0:20:56 lr: 0.000059 grad: 0.0996 (0.1203) loss: 0.8126 (0.8258) time: 0.1296 data: 0.0362 max mem: 9390 +Train: [54] [ 200/6250] eta: 0:17:44 lr: 0.000059 grad: 0.0884 (0.1168) loss: 0.8228 (0.8227) time: 0.1456 data: 0.0573 max mem: 9390 +Train: [54] [ 300/6250] eta: 0:16:22 lr: 0.000059 grad: 0.0975 (0.1098) loss: 0.8249 (0.8231) time: 0.1274 data: 0.0391 max mem: 9390 +Train: [54] [ 400/6250] eta: 0:15:18 lr: 0.000059 grad: 0.0877 (0.1053) loss: 0.8232 (0.8236) time: 0.1128 data: 0.0297 max mem: 9390 +Train: [54] [ 500/6250] eta: 0:14:36 lr: 0.000059 grad: 0.0894 (0.1026) loss: 0.8254 (0.8236) time: 0.1561 data: 0.0732 max mem: 9390 +Train: [54] [ 600/6250] eta: 0:13:50 lr: 0.000059 grad: 0.0814 (0.1008) loss: 0.8285 (0.8239) time: 0.1190 data: 0.0362 max mem: 9390 +Train: [54] [ 700/6250] eta: 0:13:19 lr: 0.000059 grad: 0.0891 (0.0990) loss: 0.8254 (0.8243) time: 0.1291 data: 0.0451 max mem: 9390 +Train: [54] [ 800/6250] eta: 0:12:51 lr: 0.000059 grad: 0.0867 (0.0981) loss: 0.8308 (0.8245) time: 0.1358 data: 0.0489 max mem: 9390 +Train: [54] [ 900/6250] eta: 0:12:31 lr: 0.000059 grad: 0.0896 (0.0972) loss: 0.8256 (0.8246) time: 0.1297 data: 0.0451 max mem: 9390 +Train: [54] [1000/6250] eta: 0:12:09 lr: 0.000059 grad: 0.0874 (0.0967) loss: 0.8218 (0.8244) time: 0.1147 data: 0.0337 max mem: 9390 +Train: [54] [1100/6250] eta: 0:11:51 lr: 0.000059 grad: 0.0953 (0.0962) loss: 0.8172 (0.8241) time: 0.1464 data: 0.0700 max mem: 9390 +Train: [54] [1200/6250] eta: 0:11:34 lr: 0.000059 grad: 0.0886 (0.0957) loss: 0.8274 (0.8239) time: 0.1357 data: 0.0566 max mem: 9390 +Train: [54] [1300/6250] eta: 0:11:18 lr: 0.000059 grad: 0.0854 (0.0953) loss: 0.8256 (0.8237) time: 0.1046 data: 0.0277 max mem: 9390 +Train: [54] [1400/6250] eta: 0:11:01 lr: 0.000059 grad: 0.0861 (0.0948) loss: 0.8208 (0.8236) time: 0.1313 data: 0.0415 max mem: 9390 +Train: [54] [1500/6250] eta: 0:10:48 lr: 0.000059 grad: 0.0960 (0.0947) loss: 0.8175 (0.8233) time: 0.1102 data: 0.0304 max mem: 9390 +Train: [54] [1600/6250] eta: 0:10:36 lr: 0.000059 grad: 0.0866 (0.0945) loss: 0.8271 (0.8232) time: 0.1391 data: 0.0632 max mem: 9390 +Train: [54] [1700/6250] eta: 0:10:24 lr: 0.000059 grad: 0.0903 (0.0943) loss: 0.8282 (0.8233) time: 0.1873 data: 0.1031 max mem: 9390 +Train: [54] [1800/6250] eta: 0:10:10 lr: 0.000059 grad: 0.0913 (0.0940) loss: 0.8267 (0.8233) time: 0.1368 data: 0.0500 max mem: 9390 +Train: [54] [1900/6250] eta: 0:09:57 lr: 0.000059 grad: 0.0945 (0.0938) loss: 0.8218 (0.8233) time: 0.1477 data: 0.0721 max mem: 9390 +Train: [54] [2000/6250] eta: 0:09:41 lr: 0.000059 grad: 0.0894 (0.0937) loss: 0.8207 (0.8233) time: 0.1272 data: 0.0451 max mem: 9390 +Train: [54] [2100/6250] eta: 0:09:26 lr: 0.000059 grad: 0.0888 (0.0936) loss: 0.8209 (0.8231) time: 0.1353 data: 0.0590 max mem: 9390 +Train: [54] [2200/6250] eta: 0:09:13 lr: 0.000059 grad: 0.0883 (0.0936) loss: 0.8219 (0.8230) time: 0.1407 data: 0.0499 max mem: 9390 +Train: [54] [2300/6250] eta: 0:09:02 lr: 0.000059 grad: 0.0911 (0.0936) loss: 0.8125 (0.8229) time: 0.1651 data: 0.0851 max mem: 9390 +Train: [54] [2400/6250] eta: 0:08:50 lr: 0.000059 grad: 0.0956 (0.0936) loss: 0.8188 (0.8227) time: 0.1526 data: 0.0778 max mem: 9390 +Train: [54] [2500/6250] eta: 0:08:37 lr: 0.000059 grad: 0.0893 (0.0936) loss: 0.8229 (0.8225) time: 0.1419 data: 0.0626 max mem: 9390 +Train: [54] [2600/6250] eta: 0:08:25 lr: 0.000059 grad: 0.0988 (0.0937) loss: 0.8162 (0.8223) time: 0.1498 data: 0.0697 max mem: 9390 +Train: [54] [2700/6250] eta: 0:08:11 lr: 0.000059 grad: 0.0921 (0.0938) loss: 0.8161 (0.8220) time: 0.1318 data: 0.0395 max mem: 9390 +Train: [54] [2800/6250] eta: 0:07:57 lr: 0.000058 grad: 0.0958 (0.0938) loss: 0.8137 (0.8218) time: 0.1466 data: 0.0670 max mem: 9390 +Train: [54] [2900/6250] eta: 0:07:42 lr: 0.000058 grad: 0.0882 (0.0938) loss: 0.8187 (0.8217) time: 0.1202 data: 0.0376 max mem: 9390 +Train: [54] [3000/6250] eta: 0:07:27 lr: 0.000058 grad: 0.0933 (0.0938) loss: 0.8193 (0.8216) time: 0.1264 data: 0.0442 max mem: 9390 +Train: [54] [3100/6250] eta: 0:07:11 lr: 0.000058 grad: 0.0915 (0.0939) loss: 0.8178 (0.8215) time: 0.1306 data: 0.0485 max mem: 9390 +Train: [54] [3200/6250] eta: 0:06:56 lr: 0.000058 grad: 0.0935 (0.0939) loss: 0.8175 (0.8214) time: 0.1155 data: 0.0269 max mem: 9390 +Train: [54] [3300/6250] eta: 0:06:40 lr: 0.000058 grad: 0.0961 (0.0939) loss: 0.8217 (0.8214) time: 0.1094 data: 0.0335 max mem: 9390 +Train: [54] [3400/6250] eta: 0:06:26 lr: 0.000058 grad: 0.0911 (0.0940) loss: 0.8189 (0.8213) time: 0.1077 data: 0.0182 max mem: 9390 +Train: [54] [3500/6250] eta: 0:06:11 lr: 0.000058 grad: 0.0938 (0.0941) loss: 0.8179 (0.8212) time: 0.1102 data: 0.0319 max mem: 9390 +Train: [54] [3600/6250] eta: 0:05:59 lr: 0.000058 grad: 0.0930 (0.0941) loss: 0.8138 (0.8212) time: 0.2702 data: 0.1900 max mem: 9390 +Train: [54] [3700/6250] eta: 0:05:44 lr: 0.000058 grad: 0.0869 (0.0941) loss: 0.8201 (0.8212) time: 0.1168 data: 0.0379 max mem: 9390 +Train: [54] [3800/6250] eta: 0:05:30 lr: 0.000058 grad: 0.0991 (0.0942) loss: 0.8117 (0.8210) time: 0.1210 data: 0.0378 max mem: 9390 +Train: [54] [3900/6250] eta: 0:05:15 lr: 0.000058 grad: 0.0916 (0.0943) loss: 0.8216 (0.8209) time: 0.1323 data: 0.0578 max mem: 9390 +Train: [54] [4000/6250] eta: 0:05:02 lr: 0.000058 grad: 0.0938 (0.0943) loss: 0.8190 (0.8208) time: 0.1232 data: 0.0452 max mem: 9390 +Train: [54] [4100/6250] eta: 0:04:49 lr: 0.000058 grad: 0.0936 (0.0943) loss: 0.8192 (0.8207) time: 0.1919 data: 0.1048 max mem: 9390 +Train: [54] [4200/6250] eta: 0:04:35 lr: 0.000058 grad: 0.0961 (0.0943) loss: 0.8136 (0.8206) time: 0.1363 data: 0.0582 max mem: 9390 +Train: [54] [4300/6250] eta: 0:04:22 lr: 0.000058 grad: 0.0952 (0.0943) loss: 0.8183 (0.8205) time: 0.1461 data: 0.0628 max mem: 9390 +Train: [54] [4400/6250] eta: 0:04:08 lr: 0.000058 grad: 0.0961 (0.0944) loss: 0.8168 (0.8204) time: 0.1377 data: 0.0609 max mem: 9390 +Train: [54] [4500/6250] eta: 0:03:55 lr: 0.000058 grad: 0.0982 (0.0944) loss: 0.8120 (0.8203) time: 0.1243 data: 0.0413 max mem: 9390 +Train: [54] [4600/6250] eta: 0:03:41 lr: 0.000058 grad: 0.0921 (0.0944) loss: 0.8174 (0.8202) time: 0.1230 data: 0.0399 max mem: 9390 +Train: [54] [4700/6250] eta: 0:03:28 lr: 0.000058 grad: 0.0902 (0.0945) loss: 0.8184 (0.8201) time: 0.1353 data: 0.0590 max mem: 9390 +Train: [54] [4800/6250] eta: 0:03:14 lr: 0.000058 grad: 0.0927 (0.0946) loss: 0.8168 (0.8200) time: 0.1539 data: 0.0755 max mem: 9390 +Train: [54] [4900/6250] eta: 0:03:01 lr: 0.000058 grad: 0.0949 (0.0946) loss: 0.8132 (0.8199) time: 0.1389 data: 0.0506 max mem: 9390 +Train: [54] [5000/6250] eta: 0:02:47 lr: 0.000058 grad: 0.1024 (0.0948) loss: 0.8171 (0.8198) time: 0.1382 data: 0.0628 max mem: 9390 +Train: [54] [5100/6250] eta: 0:02:34 lr: 0.000058 grad: 0.0953 (0.0948) loss: 0.8142 (0.8197) time: 0.1412 data: 0.0649 max mem: 9390 +Train: [54] [5200/6250] eta: 0:02:20 lr: 0.000058 grad: 0.0977 (0.0949) loss: 0.8208 (0.8196) time: 0.1439 data: 0.0697 max mem: 9390 +Train: [54] [5300/6250] eta: 0:02:07 lr: 0.000058 grad: 0.0931 (0.0950) loss: 0.8117 (0.8195) time: 0.1245 data: 0.0483 max mem: 9390 +Train: [54] [5400/6250] eta: 0:01:54 lr: 0.000058 grad: 0.0963 (0.0951) loss: 0.8072 (0.8194) time: 0.1314 data: 0.0506 max mem: 9390 +Train: [54] [5500/6250] eta: 0:01:40 lr: 0.000058 grad: 0.0959 (0.0952) loss: 0.8142 (0.8193) time: 0.1434 data: 0.0642 max mem: 9390 +Train: [54] [5600/6250] eta: 0:01:27 lr: 0.000058 grad: 0.0978 (0.0952) loss: 0.8164 (0.8192) time: 0.1344 data: 0.0595 max mem: 9390 +Train: [54] [5700/6250] eta: 0:01:13 lr: 0.000058 grad: 0.0940 (0.0952) loss: 0.8161 (0.8191) time: 0.1551 data: 0.0669 max mem: 9390 +Train: [54] [5800/6250] eta: 0:01:00 lr: 0.000057 grad: 0.0944 (0.0953) loss: 0.8186 (0.8191) time: 0.1572 data: 0.0678 max mem: 9390 +Train: [54] [5900/6250] eta: 0:00:47 lr: 0.000057 grad: 0.0932 (0.0953) loss: 0.8202 (0.8190) time: 0.1502 data: 0.0594 max mem: 9390 +Train: [54] [6000/6250] eta: 0:00:33 lr: 0.000057 grad: 0.1001 (0.0954) loss: 0.8196 (0.8189) time: 0.1656 data: 0.0791 max mem: 9390 +Train: [54] [6100/6250] eta: 0:00:20 lr: 0.000057 grad: 0.0928 (0.0955) loss: 0.8171 (0.8189) time: 0.1421 data: 0.0610 max mem: 9390 +Train: [54] [6200/6250] eta: 0:00:06 lr: 0.000057 grad: 0.1024 (0.0956) loss: 0.8185 (0.8188) time: 0.1513 data: 0.0681 max mem: 9390 +Train: [54] [6249/6250] eta: 0:00:00 lr: 0.000057 grad: 0.0949 (0.0956) loss: 0.8179 (0.8188) time: 0.1283 data: 0.0431 max mem: 9390 +Train: [54] Total time: 0:14:11 (0.1362 s / it) +Averaged stats: lr: 0.000057 grad: 0.0949 (0.0956) loss: 0.8179 (0.8188) +Eval (hcp-train-subset): [54] [ 0/62] eta: 0:03:16 loss: 0.8457 (0.8457) time: 3.1678 data: 3.0922 max mem: 9390 +Eval (hcp-train-subset): [54] [61/62] eta: 0:00:00 loss: 0.8313 (0.8347) time: 0.1069 data: 0.0819 max mem: 9390 +Eval (hcp-train-subset): [54] Total time: 0:00:11 (0.1926 s / it) +Averaged stats (hcp-train-subset): loss: 0.8313 (0.8347) +Making plots (hcp-train-subset): example=18 +Eval (hcp-val): [54] [ 0/62] eta: 0:03:08 loss: 0.8304 (0.8304) time: 3.0350 data: 2.9661 max mem: 9390 +Eval (hcp-val): [54] [61/62] eta: 0:00:00 loss: 0.8330 (0.8346) time: 0.1097 data: 0.0845 max mem: 9390 +Eval (hcp-val): [54] Total time: 0:00:12 (0.1960 s / it) +Averaged stats (hcp-val): loss: 0.8330 (0.8346) +Making plots (hcp-val): example=24 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +Train: [55] [ 0/6250] eta: 6:39:58 lr: 0.000057 grad: 0.0560 (0.0560) loss: 0.8716 (0.8716) time: 3.8398 data: 3.5385 max mem: 9390 +Train: [55] [ 100/6250] eta: 0:20:37 lr: 0.000057 grad: 0.0839 (0.0981) loss: 0.8377 (0.8377) time: 0.1528 data: 0.0593 max mem: 9390 +Train: [55] [ 200/6250] eta: 0:17:46 lr: 0.000057 grad: 0.0863 (0.0966) loss: 0.8421 (0.8355) time: 0.1494 data: 0.0688 max mem: 9390 +Train: [55] [ 300/6250] eta: 0:16:12 lr: 0.000057 grad: 0.0907 (0.0963) loss: 0.8222 (0.8316) time: 0.1321 data: 0.0416 max mem: 9390 +Train: [55] [ 400/6250] eta: 0:15:26 lr: 0.000057 grad: 0.0949 (0.0966) loss: 0.8210 (0.8289) time: 0.1662 data: 0.0819 max mem: 9390 +Train: [55] [ 500/6250] eta: 0:14:41 lr: 0.000057 grad: 0.0856 (0.0977) loss: 0.8278 (0.8273) time: 0.1378 data: 0.0569 max mem: 9390 +Train: [55] [ 600/6250] eta: 0:14:12 lr: 0.000057 grad: 0.0916 (0.0970) loss: 0.8195 (0.8259) time: 0.1291 data: 0.0529 max mem: 9390 +Train: [55] [ 700/6250] eta: 0:13:42 lr: 0.000057 grad: 0.0845 (0.0963) loss: 0.8213 (0.8250) time: 0.1187 data: 0.0272 max mem: 9390 +Train: [55] [ 800/6250] eta: 0:13:16 lr: 0.000057 grad: 0.0909 (0.0959) loss: 0.8238 (0.8242) time: 0.1316 data: 0.0515 max mem: 9390 +Train: [55] [ 900/6250] eta: 0:12:50 lr: 0.000057 grad: 0.0902 (0.0955) loss: 0.8223 (0.8237) time: 0.1373 data: 0.0550 max mem: 9390 +Train: [55] [1000/6250] eta: 0:12:24 lr: 0.000057 grad: 0.0872 (0.0954) loss: 0.8159 (0.8233) time: 0.1243 data: 0.0402 max mem: 9390 +Train: [55] [1100/6250] eta: 0:12:02 lr: 0.000057 grad: 0.0930 (0.0953) loss: 0.8116 (0.8227) time: 0.1251 data: 0.0454 max mem: 9390 +Train: [55] [1200/6250] eta: 0:11:40 lr: 0.000057 grad: 0.0935 (0.0955) loss: 0.8225 (0.8222) time: 0.1058 data: 0.0290 max mem: 9390 +Train: [55] [1300/6250] eta: 0:11:23 lr: 0.000057 grad: 0.0932 (0.0954) loss: 0.8184 (0.8217) time: 0.1577 data: 0.0784 max mem: 9390 +Train: [55] [1400/6250] eta: 0:11:03 lr: 0.000057 grad: 0.0956 (0.0955) loss: 0.8156 (0.8211) time: 0.1085 data: 0.0298 max mem: 9390 +Train: [55] [1500/6250] eta: 0:10:46 lr: 0.000057 grad: 0.0952 (0.0957) loss: 0.8138 (0.8206) time: 0.1355 data: 0.0507 max mem: 9390 +Train: [55] [1600/6250] eta: 0:10:31 lr: 0.000057 grad: 0.0972 (0.0958) loss: 0.8119 (0.8201) time: 0.1363 data: 0.0564 max mem: 9390 +Train: [55] [1700/6250] eta: 0:10:15 lr: 0.000057 grad: 0.0970 (0.0959) loss: 0.8160 (0.8198) time: 0.1243 data: 0.0432 max mem: 9390 +Train: [55] [1800/6250] eta: 0:09:59 lr: 0.000057 grad: 0.0917 (0.0958) loss: 0.8202 (0.8195) time: 0.1326 data: 0.0511 max mem: 9390 +Train: [55] [1900/6250] eta: 0:09:43 lr: 0.000057 grad: 0.0997 (0.0959) loss: 0.8104 (0.8192) time: 0.1096 data: 0.0238 max mem: 9390 +Train: [55] [2000/6250] eta: 0:09:28 lr: 0.000057 grad: 0.0981 (0.0961) loss: 0.8056 (0.8188) time: 0.1271 data: 0.0477 max mem: 9390 +Train: [55] [2100/6250] eta: 0:09:14 lr: 0.000057 grad: 0.0914 (0.0962) loss: 0.8156 (0.8185) time: 0.1349 data: 0.0359 max mem: 9390 +Train: [55] [2200/6250] eta: 0:08:59 lr: 0.000057 grad: 0.1027 (0.0964) loss: 0.8109 (0.8181) time: 0.1016 data: 0.0184 max mem: 9390 +Train: [55] [2300/6250] eta: 0:08:46 lr: 0.000057 grad: 0.0915 (0.0963) loss: 0.8161 (0.8179) time: 0.1888 data: 0.1140 max mem: 9390 +Train: [55] [2400/6250] eta: 0:08:37 lr: 0.000057 grad: 0.0932 (0.0963) loss: 0.8095 (0.8177) time: 0.1454 data: 0.0757 max mem: 9390 +Train: [55] [2500/6250] eta: 0:08:25 lr: 0.000057 grad: 0.0917 (0.0963) loss: 0.8113 (0.8176) time: 0.1390 data: 0.0659 max mem: 9390 +Train: [55] [2600/6250] eta: 0:08:15 lr: 0.000056 grad: 0.0939 (0.0964) loss: 0.8121 (0.8174) time: 0.1603 data: 0.0835 max mem: 9390 +Train: [55] [2700/6250] eta: 0:08:03 lr: 0.000056 grad: 0.0952 (0.0964) loss: 0.8149 (0.8172) time: 0.1197 data: 0.0337 max mem: 9390 +Train: [55] [2800/6250] eta: 0:07:50 lr: 0.000056 grad: 0.0963 (0.0965) loss: 0.8103 (0.8170) time: 0.1337 data: 0.0521 max mem: 9390 +Train: [55] [2900/6250] eta: 0:07:35 lr: 0.000056 grad: 0.0935 (0.0965) loss: 0.8186 (0.8170) time: 0.1301 data: 0.0476 max mem: 9390 +Train: [55] [3000/6250] eta: 0:07:21 lr: 0.000056 grad: 0.1009 (0.0965) loss: 0.8113 (0.8170) time: 0.1289 data: 0.0486 max mem: 9390 +Train: [55] [3100/6250] eta: 0:07:06 lr: 0.000056 grad: 0.0917 (0.0964) loss: 0.8171 (0.8170) time: 0.1237 data: 0.0439 max mem: 9390 +Train: [55] [3200/6250] eta: 0:06:52 lr: 0.000056 grad: 0.1010 (0.0964) loss: 0.8162 (0.8169) time: 0.1418 data: 0.0638 max mem: 9390 +Train: [55] [3300/6250] eta: 0:06:37 lr: 0.000056 grad: 0.0918 (0.0964) loss: 0.8176 (0.8169) time: 0.1245 data: 0.0471 max mem: 9390 +Train: [55] [3400/6250] eta: 0:06:22 lr: 0.000056 grad: 0.0921 (0.0964) loss: 0.8159 (0.8169) time: 0.1290 data: 0.0476 max mem: 9390 +Train: [55] [3500/6250] eta: 0:06:08 lr: 0.000056 grad: 0.0938 (0.0963) loss: 0.8224 (0.8170) time: 0.1216 data: 0.0381 max mem: 9390 +Train: [55] [3600/6250] eta: 0:05:53 lr: 0.000056 grad: 0.1007 (0.0963) loss: 0.8148 (0.8169) time: 0.1167 data: 0.0384 max mem: 9390 +Train: [55] [3700/6250] eta: 0:05:39 lr: 0.000056 grad: 0.0929 (0.0964) loss: 0.8182 (0.8169) time: 0.1137 data: 0.0385 max mem: 9390 +Train: [55] [3800/6250] eta: 0:05:25 lr: 0.000056 grad: 0.0953 (0.0964) loss: 0.8154 (0.8169) time: 0.1336 data: 0.0590 max mem: 9390 +Train: [55] [3900/6250] eta: 0:05:11 lr: 0.000056 grad: 0.0974 (0.0965) loss: 0.8122 (0.8169) time: 0.1197 data: 0.0410 max mem: 9390 +Train: [55] [4000/6250] eta: 0:04:57 lr: 0.000056 grad: 0.0926 (0.0965) loss: 0.8206 (0.8169) time: 0.1214 data: 0.0452 max mem: 9390 +Train: [55] [4100/6250] eta: 0:04:43 lr: 0.000056 grad: 0.0981 (0.0964) loss: 0.8245 (0.8169) time: 0.1222 data: 0.0450 max mem: 9390 +Train: [55] [4200/6250] eta: 0:04:29 lr: 0.000056 grad: 0.0988 (0.0965) loss: 0.8188 (0.8168) time: 0.1243 data: 0.0484 max mem: 9390 +Train: [55] [4300/6250] eta: 0:04:16 lr: 0.000056 grad: 0.0963 (0.0966) loss: 0.8152 (0.8168) time: 0.1161 data: 0.0322 max mem: 9390 +Train: [55] [4400/6250] eta: 0:04:02 lr: 0.000056 grad: 0.0928 (0.0966) loss: 0.8190 (0.8168) time: 0.1267 data: 0.0505 max mem: 9390 +Train: [55] [4500/6250] eta: 0:03:49 lr: 0.000056 grad: 0.0983 (0.0966) loss: 0.8148 (0.8168) time: 0.1256 data: 0.0484 max mem: 9390 +Train: [55] [4600/6250] eta: 0:03:35 lr: 0.000056 grad: 0.0975 (0.0967) loss: 0.8189 (0.8168) time: 0.1183 data: 0.0437 max mem: 9390 +Train: [55] [4700/6250] eta: 0:03:22 lr: 0.000056 grad: 0.0915 (0.0967) loss: 0.8181 (0.8168) time: 0.1120 data: 0.0275 max mem: 9390 +Train: [55] [4800/6250] eta: 0:03:08 lr: 0.000056 grad: 0.0984 (0.0967) loss: 0.8148 (0.8168) time: 0.1227 data: 0.0459 max mem: 9390 +Train: [55] [4900/6250] eta: 0:02:55 lr: 0.000056 grad: 0.0972 (0.0967) loss: 0.8134 (0.8168) time: 0.1223 data: 0.0468 max mem: 9390 +Train: [55] [5000/6250] eta: 0:02:42 lr: 0.000056 grad: 0.0941 (0.0967) loss: 0.8112 (0.8167) time: 0.0994 data: 0.0158 max mem: 9390 +Train: [55] [5100/6250] eta: 0:02:29 lr: 0.000056 grad: 0.0950 (0.0967) loss: 0.8137 (0.8167) time: 0.1307 data: 0.0552 max mem: 9390 +Train: [55] [5200/6250] eta: 0:02:16 lr: 0.000056 grad: 0.0966 (0.0967) loss: 0.8212 (0.8167) time: 0.1318 data: 0.0557 max mem: 9390 +Train: [55] [5300/6250] eta: 0:02:03 lr: 0.000056 grad: 0.0918 (0.0966) loss: 0.8160 (0.8167) time: 0.1129 data: 0.0379 max mem: 9390 +Train: [55] [5400/6250] eta: 0:01:50 lr: 0.000056 grad: 0.0980 (0.0966) loss: 0.8146 (0.8168) time: 0.1627 data: 0.0862 max mem: 9390 +Train: [55] [5500/6250] eta: 0:01:37 lr: 0.000056 grad: 0.1004 (0.0966) loss: 0.8133 (0.8168) time: 0.1275 data: 0.0503 max mem: 9390 +Train: [55] [5600/6250] eta: 0:01:24 lr: 0.000055 grad: 0.0950 (0.0966) loss: 0.8178 (0.8168) time: 0.1266 data: 0.0512 max mem: 9390 +Train: [55] [5700/6250] eta: 0:01:11 lr: 0.000055 grad: 0.0948 (0.0966) loss: 0.8151 (0.8167) time: 0.1326 data: 0.0365 max mem: 9390 +Train: [55] [5800/6250] eta: 0:00:58 lr: 0.000055 grad: 0.0932 (0.0966) loss: 0.8193 (0.8167) time: 0.1382 data: 0.0572 max mem: 9390 +Train: [55] [5900/6250] eta: 0:00:45 lr: 0.000055 grad: 0.0971 (0.0966) loss: 0.8149 (0.8167) time: 0.1475 data: 0.0692 max mem: 9390 +Train: [55] [6000/6250] eta: 0:00:32 lr: 0.000055 grad: 0.0919 (0.0967) loss: 0.8187 (0.8167) time: 0.1511 data: 0.0711 max mem: 9390 +Train: [55] [6100/6250] eta: 0:00:19 lr: 0.000055 grad: 0.0947 (0.0967) loss: 0.8189 (0.8167) time: 0.1391 data: 0.0553 max mem: 9390 +Train: [55] [6200/6250] eta: 0:00:06 lr: 0.000055 grad: 0.0952 (0.0968) loss: 0.8125 (0.8167) time: 0.1350 data: 0.0530 max mem: 9390 +Train: [55] [6249/6250] eta: 0:00:00 lr: 0.000055 grad: 0.0939 (0.0968) loss: 0.8134 (0.8167) time: 0.1376 data: 0.0556 max mem: 9390 +Train: [55] Total time: 0:13:46 (0.1322 s / it) +Averaged stats: lr: 0.000055 grad: 0.0939 (0.0968) loss: 0.8134 (0.8167) +Eval (hcp-train-subset): [55] [ 0/62] eta: 0:03:02 loss: 0.8496 (0.8496) time: 2.9396 data: 2.8670 max mem: 9390 +Eval (hcp-train-subset): [55] [61/62] eta: 0:00:00 loss: 0.8330 (0.8356) time: 0.1220 data: 0.0973 max mem: 9390 +Eval (hcp-train-subset): [55] Total time: 0:00:12 (0.1961 s / it) +Averaged stats (hcp-train-subset): loss: 0.8330 (0.8356) +Eval (hcp-val): [55] [ 0/62] eta: 0:04:45 loss: 0.8318 (0.8318) time: 4.6006 data: 4.5715 max mem: 9390 +Eval (hcp-val): [55] [61/62] eta: 0:00:00 loss: 0.8337 (0.8345) time: 0.1414 data: 0.1159 max mem: 9390 +Eval (hcp-val): [55] Total time: 0:00:12 (0.2096 s / it) +Averaged stats (hcp-val): loss: 0.8337 (0.8345) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +Train: [56] [ 0/6250] eta: 7:36:49 lr: 0.000055 grad: 0.3182 (0.3182) loss: 0.8312 (0.8312) time: 4.3855 data: 4.0733 max mem: 9390 +Train: [56] [ 100/6250] eta: 0:20:06 lr: 0.000055 grad: 0.1071 (0.1146) loss: 0.8211 (0.8341) time: 0.1590 data: 0.0690 max mem: 9390 +Train: [56] [ 200/6250] eta: 0:17:36 lr: 0.000055 grad: 0.0974 (0.1095) loss: 0.8123 (0.8289) time: 0.1349 data: 0.0471 max mem: 9390 +Train: [56] [ 300/6250] eta: 0:16:19 lr: 0.000055 grad: 0.0947 (0.1086) loss: 0.8227 (0.8262) time: 0.1394 data: 0.0581 max mem: 9390 +Train: [56] [ 400/6250] eta: 0:15:31 lr: 0.000055 grad: 0.0921 (0.1065) loss: 0.8286 (0.8258) time: 0.1420 data: 0.0576 max mem: 9390 +Train: [56] [ 500/6250] eta: 0:14:45 lr: 0.000055 grad: 0.0875 (0.1043) loss: 0.8263 (0.8250) time: 0.1233 data: 0.0313 max mem: 9390 +Train: [56] [ 600/6250] eta: 0:14:05 lr: 0.000055 grad: 0.0891 (0.1024) loss: 0.8163 (0.8242) time: 0.1286 data: 0.0461 max mem: 9390 +Train: [56] [ 700/6250] eta: 0:13:39 lr: 0.000055 grad: 0.0906 (0.1013) loss: 0.8120 (0.8228) time: 0.1391 data: 0.0568 max mem: 9390 +Train: [56] [ 800/6250] eta: 0:13:14 lr: 0.000055 grad: 0.0923 (0.1007) loss: 0.8184 (0.8218) time: 0.1322 data: 0.0537 max mem: 9390 +Train: [56] [ 900/6250] eta: 0:12:57 lr: 0.000055 grad: 0.0908 (0.1000) loss: 0.8241 (0.8214) time: 0.1511 data: 0.0676 max mem: 9390 +Train: [56] [1000/6250] eta: 0:12:30 lr: 0.000055 grad: 0.0899 (0.0990) loss: 0.8199 (0.8213) time: 0.1130 data: 0.0367 max mem: 9390 +Train: [56] [1100/6250] eta: 0:12:09 lr: 0.000055 grad: 0.0906 (0.0985) loss: 0.8174 (0.8209) time: 0.1384 data: 0.0581 max mem: 9390 +Train: [56] [1200/6250] eta: 0:11:50 lr: 0.000055 grad: 0.0916 (0.0984) loss: 0.8093 (0.8203) time: 0.1496 data: 0.0662 max mem: 9390 +Train: [56] [1300/6250] eta: 0:11:35 lr: 0.000055 grad: 0.0934 (0.0982) loss: 0.8191 (0.8198) time: 0.1604 data: 0.0746 max mem: 9390 +Train: [56] [1400/6250] eta: 0:11:20 lr: 0.000055 grad: 0.0964 (0.0981) loss: 0.8109 (0.8194) time: 0.1235 data: 0.0463 max mem: 9390 +Train: [56] [1500/6250] eta: 0:11:01 lr: 0.000055 grad: 0.0941 (0.0979) loss: 0.8189 (0.8190) time: 0.1272 data: 0.0477 max mem: 9390 +Train: [56] [1600/6250] eta: 0:10:48 lr: 0.000055 grad: 0.0944 (0.0981) loss: 0.8132 (0.8186) time: 0.1341 data: 0.0402 max mem: 9390 +Train: [56] [1700/6250] eta: 0:10:35 lr: 0.000055 grad: 0.0916 (0.0980) loss: 0.8102 (0.8183) time: 0.1422 data: 0.0584 max mem: 9390 +Train: [56] [1800/6250] eta: 0:10:21 lr: 0.000055 grad: 0.0918 (0.0980) loss: 0.8155 (0.8182) time: 0.1327 data: 0.0504 max mem: 9390 +Train: [56] [1900/6250] eta: 0:10:06 lr: 0.000055 grad: 0.0899 (0.0979) loss: 0.8162 (0.8181) time: 0.1148 data: 0.0301 max mem: 9390 +Train: [56] [2000/6250] eta: 0:09:50 lr: 0.000055 grad: 0.0974 (0.0978) loss: 0.8153 (0.8180) time: 0.1403 data: 0.0651 max mem: 9390 +Train: [56] [2100/6250] eta: 0:09:36 lr: 0.000055 grad: 0.0945 (0.0977) loss: 0.8216 (0.8180) time: 0.1664 data: 0.0856 max mem: 9390 +Train: [56] [2200/6250] eta: 0:09:21 lr: 0.000055 grad: 0.1012 (0.0977) loss: 0.8181 (0.8178) time: 0.1318 data: 0.0545 max mem: 9390 +Train: [56] [2300/6250] eta: 0:09:06 lr: 0.000055 grad: 0.0897 (0.0976) loss: 0.8222 (0.8178) time: 0.1412 data: 0.0614 max mem: 9390 +Train: [56] [2400/6250] eta: 0:08:54 lr: 0.000054 grad: 0.0946 (0.0976) loss: 0.8181 (0.8178) time: 0.1424 data: 0.0686 max mem: 9390 +Train: [56] [2500/6250] eta: 0:08:42 lr: 0.000054 grad: 0.0854 (0.0974) loss: 0.8246 (0.8179) time: 0.1577 data: 0.0868 max mem: 9390 +Train: [56] [2600/6250] eta: 0:08:29 lr: 0.000054 grad: 0.0930 (0.0974) loss: 0.8118 (0.8179) time: 0.1497 data: 0.0717 max mem: 9390 +Train: [56] [2700/6250] eta: 0:08:17 lr: 0.000054 grad: 0.0946 (0.0974) loss: 0.8108 (0.8178) time: 0.1479 data: 0.0720 max mem: 9390 +Train: [56] [2800/6250] eta: 0:08:03 lr: 0.000054 grad: 0.0967 (0.0975) loss: 0.8191 (0.8177) time: 0.1395 data: 0.0607 max mem: 9390 +Train: [56] [2900/6250] eta: 0:07:48 lr: 0.000054 grad: 0.0907 (0.0975) loss: 0.8176 (0.8178) time: 0.1279 data: 0.0515 max mem: 9390 +Train: [56] [3000/6250] eta: 0:07:32 lr: 0.000054 grad: 0.0962 (0.0976) loss: 0.8138 (0.8177) time: 0.1198 data: 0.0394 max mem: 9390 +Train: [56] [3100/6250] eta: 0:07:17 lr: 0.000054 grad: 0.0935 (0.0977) loss: 0.8141 (0.8176) time: 0.1280 data: 0.0444 max mem: 9390 +Train: [56] [3200/6250] eta: 0:07:01 lr: 0.000054 grad: 0.1012 (0.0979) loss: 0.8170 (0.8175) time: 0.1381 data: 0.0571 max mem: 9390 +Train: [56] [3300/6250] eta: 0:06:46 lr: 0.000054 grad: 0.0930 (0.0979) loss: 0.8176 (0.8175) time: 0.0999 data: 0.0215 max mem: 9390 +Train: [56] [3400/6250] eta: 0:06:31 lr: 0.000054 grad: 0.0935 (0.0979) loss: 0.8165 (0.8175) time: 0.1165 data: 0.0385 max mem: 9390 +Train: [56] [3500/6250] eta: 0:06:16 lr: 0.000054 grad: 0.0961 (0.0980) loss: 0.8145 (0.8175) time: 0.1348 data: 0.0498 max mem: 9390 +Train: [56] [3600/6250] eta: 0:06:02 lr: 0.000054 grad: 0.0934 (0.0981) loss: 0.8187 (0.8174) time: 0.1354 data: 0.0571 max mem: 9390 +Train: [56] [3700/6250] eta: 0:05:48 lr: 0.000054 grad: 0.0936 (0.0981) loss: 0.8184 (0.8173) time: 0.1363 data: 0.0587 max mem: 9390 +Train: [56] [3800/6250] eta: 0:05:34 lr: 0.000054 grad: 0.0945 (0.0981) loss: 0.8161 (0.8172) time: 0.1323 data: 0.0505 max mem: 9390 +Train: [56] [3900/6250] eta: 0:05:20 lr: 0.000054 grad: 0.0931 (0.0981) loss: 0.8114 (0.8171) time: 0.1323 data: 0.0561 max mem: 9390 +Train: [56] [4000/6250] eta: 0:05:06 lr: 0.000054 grad: 0.0990 (0.0982) loss: 0.8160 (0.8170) time: 0.1468 data: 0.0704 max mem: 9390 +Train: [56] [4100/6250] eta: 0:04:53 lr: 0.000054 grad: 0.0993 (0.0982) loss: 0.8134 (0.8170) time: 0.1385 data: 0.0630 max mem: 9390 +Train: [56] [4200/6250] eta: 0:04:39 lr: 0.000054 grad: 0.0959 (0.0982) loss: 0.8174 (0.8170) time: 0.1140 data: 0.0379 max mem: 9390 +Train: [56] [4300/6250] eta: 0:04:25 lr: 0.000054 grad: 0.0961 (0.0982) loss: 0.8219 (0.8170) time: 0.1214 data: 0.0459 max mem: 9390 +Train: [56] [4400/6250] eta: 0:04:11 lr: 0.000054 grad: 0.0944 (0.0981) loss: 0.8197 (0.8170) time: 0.1335 data: 0.0539 max mem: 9390 +Train: [56] [4500/6250] eta: 0:03:57 lr: 0.000054 grad: 0.0913 (0.0981) loss: 0.8161 (0.8170) time: 0.1262 data: 0.0453 max mem: 9390 +Train: [56] [4600/6250] eta: 0:03:43 lr: 0.000054 grad: 0.0923 (0.0981) loss: 0.8166 (0.8170) time: 0.1273 data: 0.0464 max mem: 9390 +Train: [56] [4700/6250] eta: 0:03:29 lr: 0.000054 grad: 0.0989 (0.0981) loss: 0.8095 (0.8169) time: 0.1094 data: 0.0298 max mem: 9390 +Train: [56] [4800/6250] eta: 0:03:15 lr: 0.000054 grad: 0.1019 (0.0980) loss: 0.8149 (0.8169) time: 0.1280 data: 0.0519 max mem: 9390 +Train: [56] [4900/6250] eta: 0:03:02 lr: 0.000054 grad: 0.0924 (0.0980) loss: 0.8208 (0.8169) time: 0.1197 data: 0.0394 max mem: 9390 +Train: [56] [5000/6250] eta: 0:02:48 lr: 0.000054 grad: 0.0902 (0.0980) loss: 0.8150 (0.8170) time: 0.1266 data: 0.0472 max mem: 9390 +Train: [56] [5100/6250] eta: 0:02:34 lr: 0.000054 grad: 0.0989 (0.0980) loss: 0.8185 (0.8170) time: 0.0902 data: 0.0094 max mem: 9390 +Train: [56] [5200/6250] eta: 0:02:21 lr: 0.000054 grad: 0.1005 (0.0979) loss: 0.8186 (0.8171) time: 0.1256 data: 0.0481 max mem: 9390 +Train: [56] [5300/6250] eta: 0:02:07 lr: 0.000054 grad: 0.0933 (0.0979) loss: 0.8242 (0.8171) time: 0.1577 data: 0.0671 max mem: 9390 +Train: [56] [5400/6250] eta: 0:01:54 lr: 0.000054 grad: 0.0945 (0.0979) loss: 0.8157 (0.8170) time: 0.1461 data: 0.0675 max mem: 9390 +Train: [56] [5500/6250] eta: 0:01:40 lr: 0.000053 grad: 0.0870 (0.0979) loss: 0.8210 (0.8171) time: 0.1156 data: 0.0382 max mem: 9390 +Train: [56] [5600/6250] eta: 0:01:27 lr: 0.000053 grad: 0.0950 (0.0979) loss: 0.8167 (0.8171) time: 0.1625 data: 0.0836 max mem: 9390 +Train: [56] [5700/6250] eta: 0:01:13 lr: 0.000053 grad: 0.0963 (0.0979) loss: 0.8112 (0.8171) time: 0.1166 data: 0.0358 max mem: 9390 +Train: [56] [5800/6250] eta: 0:01:00 lr: 0.000053 grad: 0.0913 (0.0979) loss: 0.8189 (0.8171) time: 0.1119 data: 0.0351 max mem: 9390 +Train: [56] [5900/6250] eta: 0:00:47 lr: 0.000053 grad: 0.0987 (0.0979) loss: 0.8139 (0.8170) time: 0.1283 data: 0.0475 max mem: 9390 +Train: [56] [6000/6250] eta: 0:00:33 lr: 0.000053 grad: 0.0926 (0.0979) loss: 0.8193 (0.8170) time: 0.1263 data: 0.0500 max mem: 9390 +Train: [56] [6100/6250] eta: 0:00:20 lr: 0.000053 grad: 0.0995 (0.0979) loss: 0.8111 (0.8170) time: 0.1321 data: 0.0542 max mem: 9390 +Train: [56] [6200/6250] eta: 0:00:06 lr: 0.000053 grad: 0.1011 (0.0980) loss: 0.8145 (0.8169) time: 0.1553 data: 0.0698 max mem: 9390 +Train: [56] [6249/6250] eta: 0:00:00 lr: 0.000053 grad: 0.0941 (0.0980) loss: 0.8112 (0.8169) time: 0.1422 data: 0.0616 max mem: 9390 +Train: [56] Total time: 0:14:06 (0.1355 s / it) +Averaged stats: lr: 0.000053 grad: 0.0941 (0.0980) loss: 0.8112 (0.8169) +Eval (hcp-train-subset): [56] [ 0/62] eta: 0:04:44 loss: 0.8430 (0.8430) time: 4.5889 data: 4.5585 max mem: 9390 +Eval (hcp-train-subset): [56] [61/62] eta: 0:00:00 loss: 0.8335 (0.8350) time: 0.1146 data: 0.0898 max mem: 9390 +Eval (hcp-train-subset): [56] Total time: 0:00:12 (0.2075 s / it) +Averaged stats (hcp-train-subset): loss: 0.8335 (0.8350) +Eval (hcp-val): [56] [ 0/62] eta: 0:04:51 loss: 0.8323 (0.8323) time: 4.6971 data: 4.6672 max mem: 9390 +Eval (hcp-val): [56] [61/62] eta: 0:00:00 loss: 0.8326 (0.8341) time: 0.1140 data: 0.0887 max mem: 9390 +Eval (hcp-val): [56] Total time: 0:00:12 (0.2017 s / it) +Averaged stats (hcp-val): loss: 0.8326 (0.8341) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +Train: [57] [ 0/6250] eta: 8:01:18 lr: 0.000053 grad: 0.0595 (0.0595) loss: 0.8566 (0.8566) time: 4.6206 data: 4.3903 max mem: 9390 +Train: [57] [ 100/6250] eta: 0:20:26 lr: 0.000053 grad: 0.1044 (0.1223) loss: 0.8190 (0.8271) time: 0.1533 data: 0.0586 max mem: 9390 +Train: [57] [ 200/6250] eta: 0:17:50 lr: 0.000053 grad: 0.0940 (0.1143) loss: 0.8129 (0.8218) time: 0.1605 data: 0.0734 max mem: 9390 +Train: [57] [ 300/6250] eta: 0:16:24 lr: 0.000053 grad: 0.1047 (0.1090) loss: 0.8111 (0.8203) time: 0.1385 data: 0.0520 max mem: 9390 +Train: [57] [ 400/6250] eta: 0:15:23 lr: 0.000053 grad: 0.0941 (0.1067) loss: 0.8152 (0.8183) time: 0.1334 data: 0.0486 max mem: 9390 +Train: [57] [ 500/6250] eta: 0:14:36 lr: 0.000053 grad: 0.0934 (0.1051) loss: 0.8104 (0.8175) time: 0.1263 data: 0.0405 max mem: 9390 +Train: [57] [ 600/6250] eta: 0:13:55 lr: 0.000053 grad: 0.0894 (0.1035) loss: 0.8132 (0.8173) time: 0.0990 data: 0.0100 max mem: 9390 +Train: [57] [ 700/6250] eta: 0:13:24 lr: 0.000053 grad: 0.0862 (0.1022) loss: 0.8198 (0.8177) time: 0.1189 data: 0.0388 max mem: 9390 +Train: [57] [ 800/6250] eta: 0:12:59 lr: 0.000053 grad: 0.0898 (0.1011) loss: 0.8209 (0.8179) time: 0.1371 data: 0.0538 max mem: 9390 +Train: [57] [ 900/6250] eta: 0:12:32 lr: 0.000053 grad: 0.0904 (0.1000) loss: 0.8154 (0.8183) time: 0.1352 data: 0.0573 max mem: 9390 +Train: [57] [1000/6250] eta: 0:12:19 lr: 0.000053 grad: 0.0909 (0.0994) loss: 0.8212 (0.8186) time: 0.1880 data: 0.1039 max mem: 9390 +Train: [57] [1100/6250] eta: 0:12:04 lr: 0.000053 grad: 0.0953 (0.0994) loss: 0.8167 (0.8185) time: 0.1545 data: 0.0742 max mem: 9390 +Train: [57] [1200/6250] eta: 0:11:46 lr: 0.000053 grad: 0.0948 (0.0992) loss: 0.8183 (0.8184) time: 0.1196 data: 0.0422 max mem: 9390 +Train: [57] [1300/6250] eta: 0:11:31 lr: 0.000053 grad: 0.0934 (0.0991) loss: 0.8196 (0.8181) time: 0.1451 data: 0.0590 max mem: 9390 +Train: [57] [1400/6250] eta: 0:11:17 lr: 0.000053 grad: 0.0961 (0.0986) loss: 0.8135 (0.8181) time: 0.1156 data: 0.0318 max mem: 9390 +Train: [57] [1500/6250] eta: 0:11:04 lr: 0.000053 grad: 0.0947 (0.0986) loss: 0.8130 (0.8179) time: 0.1593 data: 0.0839 max mem: 9390 +Train: [57] [1600/6250] eta: 0:10:48 lr: 0.000053 grad: 0.0956 (0.0987) loss: 0.8170 (0.8177) time: 0.1405 data: 0.0654 max mem: 9390 +Train: [57] [1700/6250] eta: 0:10:30 lr: 0.000053 grad: 0.0989 (0.0987) loss: 0.8157 (0.8177) time: 0.1178 data: 0.0421 max mem: 9390 +Train: [57] [1800/6250] eta: 0:10:16 lr: 0.000053 grad: 0.0960 (0.0985) loss: 0.8164 (0.8177) time: 0.1322 data: 0.0513 max mem: 9390 +Train: [57] [1900/6250] eta: 0:10:01 lr: 0.000053 grad: 0.0877 (0.0985) loss: 0.8202 (0.8178) time: 0.1338 data: 0.0520 max mem: 9390 +Train: [57] [2000/6250] eta: 0:09:48 lr: 0.000053 grad: 0.0947 (0.0983) loss: 0.8211 (0.8178) time: 0.1375 data: 0.0554 max mem: 9390 +Train: [57] [2100/6250] eta: 0:09:33 lr: 0.000053 grad: 0.0925 (0.0983) loss: 0.8183 (0.8177) time: 0.1290 data: 0.0507 max mem: 9390 +Train: [57] [2200/6250] eta: 0:09:20 lr: 0.000053 grad: 0.0928 (0.0982) loss: 0.8180 (0.8178) time: 0.1777 data: 0.1015 max mem: 9390 +Train: [57] [2300/6250] eta: 0:09:06 lr: 0.000052 grad: 0.0963 (0.0981) loss: 0.8151 (0.8179) time: 0.1601 data: 0.0736 max mem: 9390 +Train: [57] [2400/6250] eta: 0:08:52 lr: 0.000052 grad: 0.0917 (0.0980) loss: 0.8208 (0.8179) time: 0.1470 data: 0.0721 max mem: 9390 +Train: [57] [2500/6250] eta: 0:08:40 lr: 0.000052 grad: 0.0884 (0.0979) loss: 0.8231 (0.8181) time: 0.1322 data: 0.0551 max mem: 9390 +Train: [57] [2600/6250] eta: 0:08:27 lr: 0.000052 grad: 0.0957 (0.0978) loss: 0.8152 (0.8181) time: 0.1418 data: 0.0625 max mem: 9390 +Train: [57] [2700/6250] eta: 0:08:14 lr: 0.000052 grad: 0.0912 (0.0977) loss: 0.8174 (0.8181) time: 0.1527 data: 0.0767 max mem: 9390 +Train: [57] [2800/6250] eta: 0:08:01 lr: 0.000052 grad: 0.0875 (0.0977) loss: 0.8166 (0.8182) time: 0.1161 data: 0.0249 max mem: 9390 +Train: [57] [2900/6250] eta: 0:07:47 lr: 0.000052 grad: 0.0932 (0.0977) loss: 0.8200 (0.8183) time: 0.1324 data: 0.0551 max mem: 9390 +Train: [57] [3000/6250] eta: 0:07:33 lr: 0.000052 grad: 0.1026 (0.0977) loss: 0.8142 (0.8183) time: 0.1337 data: 0.0547 max mem: 9390 +Train: [57] [3100/6250] eta: 0:07:18 lr: 0.000052 grad: 0.0907 (0.0977) loss: 0.8207 (0.8183) time: 0.1238 data: 0.0382 max mem: 9390 +Train: [57] [3200/6250] eta: 0:07:03 lr: 0.000052 grad: 0.0942 (0.0977) loss: 0.8216 (0.8183) time: 0.1262 data: 0.0456 max mem: 9390 +Train: [57] [3300/6250] eta: 0:06:48 lr: 0.000052 grad: 0.0994 (0.0978) loss: 0.8154 (0.8183) time: 0.1101 data: 0.0327 max mem: 9390 +Train: [57] [3400/6250] eta: 0:06:33 lr: 0.000052 grad: 0.0988 (0.0978) loss: 0.8183 (0.8182) time: 0.1171 data: 0.0363 max mem: 9390 +Train: [57] [3500/6250] eta: 0:06:18 lr: 0.000052 grad: 0.0919 (0.0978) loss: 0.8204 (0.8181) time: 0.1126 data: 0.0347 max mem: 9390 +Train: [57] [3600/6250] eta: 0:06:03 lr: 0.000052 grad: 0.0925 (0.0978) loss: 0.8159 (0.8180) time: 0.1265 data: 0.0479 max mem: 9390 +Train: [57] [3700/6250] eta: 0:05:48 lr: 0.000052 grad: 0.0964 (0.0978) loss: 0.8119 (0.8179) time: 0.1391 data: 0.0618 max mem: 9390 +Train: [57] [3800/6250] eta: 0:05:33 lr: 0.000052 grad: 0.0941 (0.0979) loss: 0.8207 (0.8179) time: 0.1212 data: 0.0440 max mem: 9390 +Train: [57] [3900/6250] eta: 0:05:19 lr: 0.000052 grad: 0.0979 (0.0979) loss: 0.8156 (0.8178) time: 0.1463 data: 0.0630 max mem: 9390 +Train: [57] [4000/6250] eta: 0:05:05 lr: 0.000052 grad: 0.1004 (0.0980) loss: 0.8131 (0.8178) time: 0.1340 data: 0.0520 max mem: 9390 +Train: [57] [4100/6250] eta: 0:04:52 lr: 0.000052 grad: 0.0996 (0.0981) loss: 0.8036 (0.8176) time: 0.1284 data: 0.0477 max mem: 9390 +Train: [57] [4200/6250] eta: 0:04:38 lr: 0.000052 grad: 0.0988 (0.0982) loss: 0.8124 (0.8175) time: 0.1146 data: 0.0370 max mem: 9390 +Train: [57] [4300/6250] eta: 0:04:23 lr: 0.000052 grad: 0.0929 (0.0983) loss: 0.8153 (0.8175) time: 0.1221 data: 0.0417 max mem: 9390 +Train: [57] [4400/6250] eta: 0:04:10 lr: 0.000052 grad: 0.0997 (0.0985) loss: 0.8104 (0.8174) time: 0.1422 data: 0.0676 max mem: 9390 +Train: [57] [4500/6250] eta: 0:03:56 lr: 0.000052 grad: 0.1075 (0.0986) loss: 0.8102 (0.8173) time: 0.1487 data: 0.0758 max mem: 9390 +Train: [57] [4600/6250] eta: 0:03:42 lr: 0.000052 grad: 0.0968 (0.0987) loss: 0.8094 (0.8172) time: 0.1207 data: 0.0385 max mem: 9390 +Train: [57] [4700/6250] eta: 0:03:29 lr: 0.000052 grad: 0.1060 (0.0988) loss: 0.8090 (0.8170) time: 0.1056 data: 0.0319 max mem: 9390 +Train: [57] [4800/6250] eta: 0:03:15 lr: 0.000052 grad: 0.0929 (0.0989) loss: 0.8191 (0.8170) time: 0.1430 data: 0.0527 max mem: 9390 +Train: [57] [4900/6250] eta: 0:03:01 lr: 0.000052 grad: 0.1002 (0.0990) loss: 0.8154 (0.8169) time: 0.1181 data: 0.0409 max mem: 9390 +Train: [57] [5000/6250] eta: 0:02:48 lr: 0.000052 grad: 0.0973 (0.0990) loss: 0.8177 (0.8168) time: 0.1654 data: 0.0876 max mem: 9390 +Train: [57] [5100/6250] eta: 0:02:35 lr: 0.000052 grad: 0.1017 (0.0991) loss: 0.8138 (0.8168) time: 0.1468 data: 0.0678 max mem: 9390 +Train: [57] [5200/6250] eta: 0:02:21 lr: 0.000052 grad: 0.1009 (0.0991) loss: 0.8181 (0.8167) time: 0.1578 data: 0.0840 max mem: 9390 +Train: [57] [5300/6250] eta: 0:02:08 lr: 0.000052 grad: 0.0947 (0.0991) loss: 0.8195 (0.8167) time: 0.1267 data: 0.0486 max mem: 9390 +Train: [57] [5400/6250] eta: 0:01:54 lr: 0.000051 grad: 0.1017 (0.0992) loss: 0.8175 (0.8167) time: 0.1353 data: 0.0540 max mem: 9390 +Train: [57] [5500/6250] eta: 0:01:41 lr: 0.000051 grad: 0.0883 (0.0991) loss: 0.8228 (0.8167) time: 0.1388 data: 0.0596 max mem: 9390 +Train: [57] [5600/6250] eta: 0:01:27 lr: 0.000051 grad: 0.0925 (0.0991) loss: 0.8171 (0.8166) time: 0.1194 data: 0.0448 max mem: 9390 +Train: [57] [5700/6250] eta: 0:01:14 lr: 0.000051 grad: 0.0919 (0.0992) loss: 0.8162 (0.8166) time: 0.1333 data: 0.0571 max mem: 9390 +Train: [57] [5800/6250] eta: 0:01:00 lr: 0.000051 grad: 0.0989 (0.0994) loss: 0.8155 (0.8166) time: 0.1541 data: 0.0755 max mem: 9390 +Train: [57] [5900/6250] eta: 0:00:47 lr: 0.000051 grad: 0.0997 (0.0994) loss: 0.8176 (0.8166) time: 0.1232 data: 0.0468 max mem: 9390 +Train: [57] [6000/6250] eta: 0:00:33 lr: 0.000051 grad: 0.0992 (0.0995) loss: 0.8156 (0.8166) time: 0.1309 data: 0.0564 max mem: 9390 +Train: [57] [6100/6250] eta: 0:00:20 lr: 0.000051 grad: 0.0983 (0.0994) loss: 0.8229 (0.8167) time: 0.1248 data: 0.0451 max mem: 9390 +Train: [57] [6200/6250] eta: 0:00:06 lr: 0.000051 grad: 0.0964 (0.0995) loss: 0.8194 (0.8167) time: 0.1199 data: 0.0402 max mem: 9390 +Train: [57] [6249/6250] eta: 0:00:00 lr: 0.000051 grad: 0.0953 (0.0994) loss: 0.8119 (0.8167) time: 0.1330 data: 0.0568 max mem: 9390 +Train: [57] Total time: 0:14:07 (0.1356 s / it) +Averaged stats: lr: 0.000051 grad: 0.0953 (0.0994) loss: 0.8119 (0.8167) +Eval (hcp-train-subset): [57] [ 0/62] eta: 0:03:51 loss: 0.8488 (0.8488) time: 3.7412 data: 3.6474 max mem: 9390 +Eval (hcp-train-subset): [57] [61/62] eta: 0:00:00 loss: 0.8344 (0.8344) time: 0.1221 data: 0.0969 max mem: 9390 +Eval (hcp-train-subset): [57] Total time: 0:00:11 (0.1933 s / it) +Averaged stats (hcp-train-subset): loss: 0.8344 (0.8344) +Eval (hcp-val): [57] [ 0/62] eta: 0:06:25 loss: 0.8309 (0.8309) time: 6.2130 data: 6.1819 max mem: 9390 +Eval (hcp-val): [57] [61/62] eta: 0:00:00 loss: 0.8329 (0.8346) time: 0.1255 data: 0.1007 max mem: 9390 +Eval (hcp-val): [57] Total time: 0:00:13 (0.2252 s / it) +Averaged stats (hcp-val): loss: 0.8329 (0.8346) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +Train: [58] [ 0/6250] eta: 7:08:41 lr: 0.000051 grad: 0.0959 (0.0959) loss: 0.8726 (0.8726) time: 4.1154 data: 3.7717 max mem: 9390 +Train: [58] [ 100/6250] eta: 0:20:49 lr: 0.000051 grad: 0.0997 (0.1106) loss: 0.8140 (0.8222) time: 0.1665 data: 0.0669 max mem: 9390 +Train: [58] [ 200/6250] eta: 0:18:17 lr: 0.000051 grad: 0.0900 (0.1072) loss: 0.8205 (0.8184) time: 0.1373 data: 0.0520 max mem: 9390 +Train: [58] [ 300/6250] eta: 0:16:53 lr: 0.000051 grad: 0.0972 (0.1082) loss: 0.8180 (0.8176) time: 0.1461 data: 0.0588 max mem: 9390 +Train: [58] [ 400/6250] eta: 0:16:01 lr: 0.000051 grad: 0.0900 (0.1077) loss: 0.8134 (0.8169) time: 0.1646 data: 0.0788 max mem: 9390 +Train: [58] [ 500/6250] eta: 0:15:08 lr: 0.000051 grad: 0.0982 (0.1067) loss: 0.8193 (0.8160) time: 0.1227 data: 0.0417 max mem: 9390 +Train: [58] [ 600/6250] eta: 0:14:35 lr: 0.000051 grad: 0.1079 (0.1062) loss: 0.8119 (0.8160) time: 0.1597 data: 0.0701 max mem: 9390 +Train: [58] [ 700/6250] eta: 0:13:59 lr: 0.000051 grad: 0.0932 (0.1052) loss: 0.8162 (0.8160) time: 0.1465 data: 0.0640 max mem: 9390 +Train: [58] [ 800/6250] eta: 0:13:26 lr: 0.000051 grad: 0.0962 (0.1047) loss: 0.8151 (0.8158) time: 0.1223 data: 0.0428 max mem: 9390 +Train: [58] [ 900/6250] eta: 0:12:57 lr: 0.000051 grad: 0.0895 (0.1039) loss: 0.8207 (0.8160) time: 0.1413 data: 0.0578 max mem: 9390 +Train: [58] [1000/6250] eta: 0:12:34 lr: 0.000051 grad: 0.0905 (0.1032) loss: 0.8180 (0.8162) time: 0.1343 data: 0.0540 max mem: 9390 +Train: [58] [1100/6250] eta: 0:12:12 lr: 0.000051 grad: 0.0936 (0.1024) loss: 0.8154 (0.8162) time: 0.1205 data: 0.0439 max mem: 9390 +Train: [58] [1200/6250] eta: 0:11:54 lr: 0.000051 grad: 0.0917 (0.1020) loss: 0.8201 (0.8164) time: 0.1300 data: 0.0422 max mem: 9390 +Train: [58] [1300/6250] eta: 0:11:37 lr: 0.000051 grad: 0.0963 (0.1014) loss: 0.8196 (0.8167) time: 0.1390 data: 0.0678 max mem: 9390 +Train: [58] [1400/6250] eta: 0:11:22 lr: 0.000051 grad: 0.0986 (0.1011) loss: 0.8128 (0.8169) time: 0.1512 data: 0.0719 max mem: 9390 +Train: [58] [1500/6250] eta: 0:11:04 lr: 0.000051 grad: 0.0899 (0.1007) loss: 0.8222 (0.8171) time: 0.1479 data: 0.0705 max mem: 9390 +Train: [58] [1600/6250] eta: 0:10:45 lr: 0.000051 grad: 0.0949 (0.1005) loss: 0.8236 (0.8172) time: 0.1180 data: 0.0393 max mem: 9390 +Train: [58] [1700/6250] eta: 0:10:34 lr: 0.000051 grad: 0.0941 (0.1003) loss: 0.8137 (0.8172) time: 0.1553 data: 0.0634 max mem: 9390 +Train: [58] [1800/6250] eta: 0:10:18 lr: 0.000051 grad: 0.0905 (0.1002) loss: 0.8184 (0.8170) time: 0.1319 data: 0.0537 max mem: 9390 +Train: [58] [1900/6250] eta: 0:10:02 lr: 0.000051 grad: 0.0926 (0.1001) loss: 0.8155 (0.8170) time: 0.1208 data: 0.0412 max mem: 9390 +Train: [58] [2000/6250] eta: 0:09:49 lr: 0.000051 grad: 0.0976 (0.1001) loss: 0.8173 (0.8170) time: 0.0986 data: 0.0172 max mem: 9390 +Train: [58] [2100/6250] eta: 0:09:36 lr: 0.000051 grad: 0.0947 (0.0999) loss: 0.8189 (0.8171) time: 0.1367 data: 0.0573 max mem: 9390 +Train: [58] [2200/6250] eta: 0:09:21 lr: 0.000050 grad: 0.0976 (0.0998) loss: 0.8170 (0.8171) time: 0.1322 data: 0.0581 max mem: 9390 +Train: [58] [2300/6250] eta: 0:09:06 lr: 0.000050 grad: 0.0934 (0.0997) loss: 0.8126 (0.8171) time: 0.1381 data: 0.0538 max mem: 9390 +Train: [58] [2400/6250] eta: 0:08:51 lr: 0.000050 grad: 0.0882 (0.0995) loss: 0.8198 (0.8171) time: 0.1394 data: 0.0620 max mem: 9390 +Train: [58] [2500/6250] eta: 0:08:39 lr: 0.000050 grad: 0.0900 (0.0994) loss: 0.8188 (0.8172) time: 0.1456 data: 0.0673 max mem: 9390 +Train: [58] [2600/6250] eta: 0:08:26 lr: 0.000050 grad: 0.0931 (0.0993) loss: 0.8242 (0.8172) time: 0.1517 data: 0.0766 max mem: 9390 +Train: [58] [2700/6250] eta: 0:08:13 lr: 0.000050 grad: 0.0978 (0.0993) loss: 0.8187 (0.8172) time: 0.1444 data: 0.0693 max mem: 9390 +Train: [58] [2800/6250] eta: 0:08:01 lr: 0.000050 grad: 0.0976 (0.0992) loss: 0.8186 (0.8172) time: 0.1572 data: 0.0815 max mem: 9390 +Train: [58] [2900/6250] eta: 0:07:47 lr: 0.000050 grad: 0.0948 (0.0993) loss: 0.8190 (0.8172) time: 0.1461 data: 0.0651 max mem: 9390 +Train: [58] [3000/6250] eta: 0:07:32 lr: 0.000050 grad: 0.0957 (0.0994) loss: 0.8106 (0.8172) time: 0.1132 data: 0.0341 max mem: 9390 +Train: [58] [3100/6250] eta: 0:07:19 lr: 0.000050 grad: 0.0971 (0.0996) loss: 0.8175 (0.8172) time: 0.1387 data: 0.0621 max mem: 9390 +Train: [58] [3200/6250] eta: 0:07:03 lr: 0.000050 grad: 0.0963 (0.0995) loss: 0.8161 (0.8172) time: 0.1433 data: 0.0636 max mem: 9390 +Train: [58] [3300/6250] eta: 0:06:48 lr: 0.000050 grad: 0.0946 (0.0996) loss: 0.8161 (0.8172) time: 0.1034 data: 0.0175 max mem: 9390 +Train: [58] [3400/6250] eta: 0:06:33 lr: 0.000050 grad: 0.0938 (0.0995) loss: 0.8195 (0.8172) time: 0.1033 data: 0.0256 max mem: 9390 +Train: [58] [3500/6250] eta: 0:06:18 lr: 0.000050 grad: 0.0940 (0.0995) loss: 0.8147 (0.8172) time: 0.1090 data: 0.0291 max mem: 9390 +Train: [58] [3600/6250] eta: 0:06:03 lr: 0.000050 grad: 0.0880 (0.0994) loss: 0.8197 (0.8172) time: 0.1126 data: 0.0303 max mem: 9390 +Train: [58] [3700/6250] eta: 0:05:49 lr: 0.000050 grad: 0.0947 (0.0994) loss: 0.8200 (0.8172) time: 0.1216 data: 0.0390 max mem: 9390 +Train: [58] [3800/6250] eta: 0:05:34 lr: 0.000050 grad: 0.0992 (0.0994) loss: 0.8182 (0.8172) time: 0.1337 data: 0.0580 max mem: 9390 +Train: [58] [3900/6250] eta: 0:05:20 lr: 0.000050 grad: 0.0969 (0.0994) loss: 0.8190 (0.8172) time: 0.1319 data: 0.0580 max mem: 9390 +Train: [58] [4000/6250] eta: 0:05:06 lr: 0.000050 grad: 0.0977 (0.0995) loss: 0.8246 (0.8172) time: 0.1522 data: 0.0707 max mem: 9390 +Train: [58] [4100/6250] eta: 0:04:52 lr: 0.000050 grad: 0.1018 (0.0994) loss: 0.8197 (0.8173) time: 0.1242 data: 0.0516 max mem: 9390 +Train: [58] [4200/6250] eta: 0:04:38 lr: 0.000050 grad: 0.1024 (0.0995) loss: 0.8142 (0.8173) time: 0.1267 data: 0.0484 max mem: 9390 +Train: [58] [4300/6250] eta: 0:04:24 lr: 0.000050 grad: 0.0995 (0.0994) loss: 0.8183 (0.8173) time: 0.1366 data: 0.0600 max mem: 9390 +Train: [58] [4400/6250] eta: 0:04:10 lr: 0.000050 grad: 0.0937 (0.0994) loss: 0.8181 (0.8173) time: 0.1445 data: 0.0558 max mem: 9390 +Train: [58] [4500/6250] eta: 0:03:57 lr: 0.000050 grad: 0.0963 (0.0994) loss: 0.8221 (0.8173) time: 0.1404 data: 0.0633 max mem: 9390 +Train: [58] [4600/6250] eta: 0:03:43 lr: 0.000050 grad: 0.1039 (0.0995) loss: 0.8281 (0.8174) time: 0.1436 data: 0.0696 max mem: 9390 +Train: [58] [4700/6250] eta: 0:03:29 lr: 0.000050 grad: 0.0967 (0.0995) loss: 0.8201 (0.8173) time: 0.1390 data: 0.0599 max mem: 9390 +Train: [58] [4800/6250] eta: 0:03:15 lr: 0.000050 grad: 0.0941 (0.0995) loss: 0.8193 (0.8174) time: 0.1241 data: 0.0468 max mem: 9390 +Train: [58] [4900/6250] eta: 0:03:01 lr: 0.000050 grad: 0.0932 (0.0994) loss: 0.8148 (0.8174) time: 0.1360 data: 0.0601 max mem: 9390 +Train: [58] [5000/6250] eta: 0:02:48 lr: 0.000050 grad: 0.0976 (0.0995) loss: 0.8168 (0.8174) time: 0.1312 data: 0.0524 max mem: 9390 +Train: [58] [5100/6250] eta: 0:02:34 lr: 0.000050 grad: 0.0935 (0.0994) loss: 0.8236 (0.8175) time: 0.1354 data: 0.0538 max mem: 9390 +Train: [58] [5200/6250] eta: 0:02:21 lr: 0.000050 grad: 0.0938 (0.0994) loss: 0.8212 (0.8175) time: 0.1411 data: 0.0613 max mem: 9390 +Train: [58] [5300/6250] eta: 0:02:07 lr: 0.000049 grad: 0.0998 (0.0995) loss: 0.8155 (0.8175) time: 0.1262 data: 0.0470 max mem: 9390 +Train: [58] [5400/6250] eta: 0:01:54 lr: 0.000049 grad: 0.0998 (0.0995) loss: 0.8200 (0.8174) time: 0.1452 data: 0.0633 max mem: 9390 +Train: [58] [5500/6250] eta: 0:01:40 lr: 0.000049 grad: 0.0975 (0.0995) loss: 0.8162 (0.8174) time: 0.1180 data: 0.0417 max mem: 9390 +Train: [58] [5600/6250] eta: 0:01:27 lr: 0.000049 grad: 0.1026 (0.0996) loss: 0.8156 (0.8174) time: 0.1426 data: 0.0674 max mem: 9390 +Train: [58] [5700/6250] eta: 0:01:13 lr: 0.000049 grad: 0.0942 (0.0996) loss: 0.8127 (0.8174) time: 0.1463 data: 0.0677 max mem: 9390 +Train: [58] [5800/6250] eta: 0:01:00 lr: 0.000049 grad: 0.0923 (0.0996) loss: 0.8192 (0.8174) time: 0.1210 data: 0.0429 max mem: 9390 +Train: [58] [5900/6250] eta: 0:00:47 lr: 0.000049 grad: 0.0957 (0.0996) loss: 0.8161 (0.8174) time: 0.1533 data: 0.0752 max mem: 9390 +Train: [58] [6000/6250] eta: 0:00:33 lr: 0.000049 grad: 0.0940 (0.0996) loss: 0.8160 (0.8174) time: 0.1157 data: 0.0317 max mem: 9390 +Train: [58] [6100/6250] eta: 0:00:20 lr: 0.000049 grad: 0.0969 (0.0996) loss: 0.8135 (0.8174) time: 0.1285 data: 0.0489 max mem: 9390 +Train: [58] [6200/6250] eta: 0:00:06 lr: 0.000049 grad: 0.0961 (0.0996) loss: 0.8172 (0.8174) time: 0.1368 data: 0.0608 max mem: 9390 +Train: [58] [6249/6250] eta: 0:00:00 lr: 0.000049 grad: 0.0939 (0.0996) loss: 0.8161 (0.8173) time: 0.1436 data: 0.0634 max mem: 9390 +Train: [58] Total time: 0:14:05 (0.1353 s / it) +Averaged stats: lr: 0.000049 grad: 0.0939 (0.0996) loss: 0.8161 (0.8173) +Eval (hcp-train-subset): [58] [ 0/62] eta: 0:05:30 loss: 0.8467 (0.8467) time: 5.3383 data: 5.3091 max mem: 9390 +Eval (hcp-train-subset): [58] [61/62] eta: 0:00:00 loss: 0.8334 (0.8352) time: 0.1099 data: 0.0851 max mem: 9390 +Eval (hcp-train-subset): [58] Total time: 0:00:12 (0.2014 s / it) +Averaged stats (hcp-train-subset): loss: 0.8334 (0.8352) +Eval (hcp-val): [58] [ 0/62] eta: 0:04:35 loss: 0.8311 (0.8311) time: 4.4477 data: 4.4182 max mem: 9390 +Eval (hcp-val): [58] [61/62] eta: 0:00:00 loss: 0.8330 (0.8348) time: 0.1193 data: 0.0926 max mem: 9390 +Eval (hcp-val): [58] Total time: 0:00:12 (0.2024 s / it) +Averaged stats (hcp-val): loss: 0.8330 (0.8348) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +Train: [59] [ 0/6250] eta: 10:48:06 lr: 0.000049 grad: 0.4063 (0.4063) loss: 0.7922 (0.7922) time: 6.2218 data: 6.1250 max mem: 9390 +Train: [59] [ 100/6250] eta: 0:20:30 lr: 0.000049 grad: 0.1039 (0.1258) loss: 0.8223 (0.8278) time: 0.1694 data: 0.0695 max mem: 9390 +Train: [59] [ 200/6250] eta: 0:17:44 lr: 0.000049 grad: 0.0972 (0.1141) loss: 0.8188 (0.8246) time: 0.1543 data: 0.0583 max mem: 9390 +Train: [59] [ 300/6250] eta: 0:16:52 lr: 0.000049 grad: 0.0974 (0.1107) loss: 0.8216 (0.8227) time: 0.1514 data: 0.0666 max mem: 9390 +Train: [59] [ 400/6250] eta: 0:15:57 lr: 0.000049 grad: 0.0915 (0.1078) loss: 0.8220 (0.8208) time: 0.1461 data: 0.0686 max mem: 9390 +Train: [59] [ 500/6250] eta: 0:15:09 lr: 0.000049 grad: 0.0876 (0.1056) loss: 0.8206 (0.8199) time: 0.1295 data: 0.0425 max mem: 9390 +Train: [59] [ 600/6250] eta: 0:14:32 lr: 0.000049 grad: 0.0940 (0.1035) loss: 0.8204 (0.8202) time: 0.1410 data: 0.0651 max mem: 9390 +Train: [59] [ 700/6250] eta: 0:14:02 lr: 0.000049 grad: 0.0867 (0.1015) loss: 0.8214 (0.8205) time: 0.1481 data: 0.0612 max mem: 9390 +Train: [59] [ 800/6250] eta: 0:13:35 lr: 0.000049 grad: 0.0844 (0.1000) loss: 0.8274 (0.8209) time: 0.1374 data: 0.0564 max mem: 9390 +Train: [59] [ 900/6250] eta: 0:13:14 lr: 0.000049 grad: 0.0894 (0.0988) loss: 0.8220 (0.8210) time: 0.1520 data: 0.0700 max mem: 9390 +Train: [59] [1000/6250] eta: 0:12:54 lr: 0.000049 grad: 0.0918 (0.0979) loss: 0.8152 (0.8213) time: 0.1175 data: 0.0331 max mem: 9390 +Train: [59] [1100/6250] eta: 0:12:35 lr: 0.000049 grad: 0.0904 (0.0971) loss: 0.8208 (0.8215) time: 0.1330 data: 0.0561 max mem: 9390 +Train: [59] [1200/6250] eta: 0:12:16 lr: 0.000049 grad: 0.0896 (0.0966) loss: 0.8221 (0.8216) time: 0.1494 data: 0.0676 max mem: 9390 +Train: [59] [1300/6250] eta: 0:11:57 lr: 0.000049 grad: 0.0910 (0.0964) loss: 0.8197 (0.8215) time: 0.1384 data: 0.0636 max mem: 9390 +Train: [59] [1400/6250] eta: 0:11:42 lr: 0.000049 grad: 0.0960 (0.0962) loss: 0.8177 (0.8214) time: 0.1449 data: 0.0697 max mem: 9390 +Train: [59] [1500/6250] eta: 0:11:22 lr: 0.000049 grad: 0.0917 (0.0960) loss: 0.8198 (0.8213) time: 0.1107 data: 0.0318 max mem: 9390 +Train: [59] [1600/6250] eta: 0:11:04 lr: 0.000049 grad: 0.0927 (0.0959) loss: 0.8198 (0.8211) time: 0.1239 data: 0.0459 max mem: 9390 +Train: [59] [1700/6250] eta: 0:10:49 lr: 0.000049 grad: 0.0927 (0.0959) loss: 0.8188 (0.8208) time: 0.1356 data: 0.0553 max mem: 9390 +Train: [59] [1800/6250] eta: 0:10:34 lr: 0.000049 grad: 0.0977 (0.0960) loss: 0.8148 (0.8206) time: 0.1467 data: 0.0694 max mem: 9390 +Train: [59] [1900/6250] eta: 0:10:18 lr: 0.000049 grad: 0.0936 (0.0961) loss: 0.8158 (0.8203) time: 0.1346 data: 0.0566 max mem: 9390 +Train: [59] [2000/6250] eta: 0:10:03 lr: 0.000049 grad: 0.0927 (0.0961) loss: 0.8176 (0.8201) time: 0.1295 data: 0.0490 max mem: 9390 +Train: [59] [2100/6250] eta: 0:09:49 lr: 0.000048 grad: 0.1004 (0.0963) loss: 0.8152 (0.8198) time: 0.1414 data: 0.0513 max mem: 9390 +Train: [59] [2200/6250] eta: 0:09:34 lr: 0.000048 grad: 0.0978 (0.0965) loss: 0.8188 (0.8197) time: 0.1443 data: 0.0605 max mem: 9390 +Train: [59] [2300/6250] eta: 0:09:20 lr: 0.000048 grad: 0.1010 (0.0967) loss: 0.8132 (0.8195) time: 0.1767 data: 0.1000 max mem: 9390 +Train: [59] [2400/6250] eta: 0:09:05 lr: 0.000048 grad: 0.0988 (0.0968) loss: 0.8173 (0.8194) time: 0.1361 data: 0.0548 max mem: 9390 +Train: [59] [2500/6250] eta: 0:08:51 lr: 0.000048 grad: 0.0937 (0.0970) loss: 0.8165 (0.8192) time: 0.1458 data: 0.0678 max mem: 9390 +Train: [59] [2600/6250] eta: 0:08:38 lr: 0.000048 grad: 0.0982 (0.0974) loss: 0.8173 (0.8190) time: 0.1372 data: 0.0596 max mem: 9390 +Train: [59] [2700/6250] eta: 0:08:25 lr: 0.000048 grad: 0.0953 (0.0975) loss: 0.8155 (0.8189) time: 0.1420 data: 0.0629 max mem: 9390 +Train: [59] [2800/6250] eta: 0:08:11 lr: 0.000048 grad: 0.0956 (0.0978) loss: 0.8178 (0.8187) time: 0.1448 data: 0.0673 max mem: 9390 +Train: [59] [2900/6250] eta: 0:07:58 lr: 0.000048 grad: 0.0965 (0.0979) loss: 0.8155 (0.8186) time: 0.1586 data: 0.0708 max mem: 9390 +Train: [59] [3000/6250] eta: 0:07:44 lr: 0.000048 grad: 0.0966 (0.0981) loss: 0.8155 (0.8185) time: 0.1459 data: 0.0680 max mem: 9390 +Train: [59] [3100/6250] eta: 0:07:29 lr: 0.000048 grad: 0.1010 (0.0984) loss: 0.8198 (0.8184) time: 0.1519 data: 0.0736 max mem: 9390 +Train: [59] [3200/6250] eta: 0:07:13 lr: 0.000048 grad: 0.1014 (0.0985) loss: 0.8167 (0.8183) time: 0.1311 data: 0.0534 max mem: 9390 +Train: [59] [3300/6250] eta: 0:06:57 lr: 0.000048 grad: 0.0960 (0.0986) loss: 0.8165 (0.8182) time: 0.1144 data: 0.0306 max mem: 9390 +Train: [59] [3400/6250] eta: 0:06:42 lr: 0.000048 grad: 0.0948 (0.0987) loss: 0.8176 (0.8181) time: 0.1370 data: 0.0588 max mem: 9390 +Train: [59] [3500/6250] eta: 0:06:26 lr: 0.000048 grad: 0.1036 (0.0989) loss: 0.8092 (0.8180) time: 0.1173 data: 0.0293 max mem: 9390 +Train: [59] [3600/6250] eta: 0:06:10 lr: 0.000048 grad: 0.1010 (0.0990) loss: 0.8168 (0.8179) time: 0.1248 data: 0.0438 max mem: 9390 +Train: [59] [3700/6250] eta: 0:05:55 lr: 0.000048 grad: 0.1046 (0.0990) loss: 0.8179 (0.8178) time: 0.1327 data: 0.0573 max mem: 9390 +Train: [59] [3800/6250] eta: 0:05:40 lr: 0.000048 grad: 0.1061 (0.0992) loss: 0.8144 (0.8177) time: 0.1253 data: 0.0380 max mem: 9390 +Train: [59] [3900/6250] eta: 0:05:26 lr: 0.000048 grad: 0.1019 (0.0993) loss: 0.8184 (0.8177) time: 0.1441 data: 0.0611 max mem: 9390 +Train: [59] [4000/6250] eta: 0:05:11 lr: 0.000048 grad: 0.0962 (0.0993) loss: 0.8171 (0.8176) time: 0.1118 data: 0.0354 max mem: 9390 +Train: [59] [4100/6250] eta: 0:04:57 lr: 0.000048 grad: 0.1019 (0.0994) loss: 0.8176 (0.8176) time: 0.1295 data: 0.0511 max mem: 9390 +Train: [59] [4200/6250] eta: 0:04:43 lr: 0.000048 grad: 0.0945 (0.0994) loss: 0.8154 (0.8176) time: 0.1566 data: 0.0740 max mem: 9390 +Train: [59] [4300/6250] eta: 0:04:29 lr: 0.000048 grad: 0.0938 (0.0994) loss: 0.8171 (0.8175) time: 0.0840 data: 0.0051 max mem: 9390 +Train: [59] [4400/6250] eta: 0:04:15 lr: 0.000048 grad: 0.0970 (0.0994) loss: 0.8169 (0.8175) time: 0.1032 data: 0.0241 max mem: 9390 +Train: [59] [4500/6250] eta: 0:04:00 lr: 0.000048 grad: 0.0975 (0.0994) loss: 0.8204 (0.8176) time: 0.1265 data: 0.0510 max mem: 9390 +Train: [59] [4600/6250] eta: 0:03:46 lr: 0.000048 grad: 0.1070 (0.0995) loss: 0.8184 (0.8176) time: 0.1188 data: 0.0389 max mem: 9390 +Train: [59] [4700/6250] eta: 0:03:32 lr: 0.000048 grad: 0.0959 (0.0996) loss: 0.8116 (0.8175) time: 0.1330 data: 0.0553 max mem: 9390 +Train: [59] [4800/6250] eta: 0:03:18 lr: 0.000048 grad: 0.0976 (0.0995) loss: 0.8239 (0.8176) time: 0.1300 data: 0.0524 max mem: 9390 +Train: [59] [4900/6250] eta: 0:03:04 lr: 0.000048 grad: 0.0970 (0.0995) loss: 0.8223 (0.8176) time: 0.1227 data: 0.0446 max mem: 9390 +Train: [59] [5000/6250] eta: 0:02:50 lr: 0.000048 grad: 0.0977 (0.0995) loss: 0.8245 (0.8176) time: 0.1202 data: 0.0399 max mem: 9390 +Train: [59] [5100/6250] eta: 0:02:36 lr: 0.000048 grad: 0.0916 (0.0995) loss: 0.8207 (0.8177) time: 0.1010 data: 0.0176 max mem: 9390 +Train: [59] [5200/6250] eta: 0:02:23 lr: 0.000047 grad: 0.0953 (0.0995) loss: 0.8266 (0.8178) time: 0.1404 data: 0.0632 max mem: 9390 +Train: [59] [5300/6250] eta: 0:02:09 lr: 0.000047 grad: 0.0944 (0.0995) loss: 0.8219 (0.8178) time: 0.1394 data: 0.0534 max mem: 9390 +Train: [59] [5400/6250] eta: 0:01:55 lr: 0.000047 grad: 0.0934 (0.0994) loss: 0.8172 (0.8179) time: 0.1395 data: 0.0589 max mem: 9390 +Train: [59] [5500/6250] eta: 0:01:42 lr: 0.000047 grad: 0.0883 (0.0995) loss: 0.8251 (0.8180) time: 0.1573 data: 0.0794 max mem: 9390 +Train: [59] [5600/6250] eta: 0:01:28 lr: 0.000047 grad: 0.1034 (0.0994) loss: 0.8187 (0.8180) time: 0.1291 data: 0.0495 max mem: 9390 +Train: [59] [5700/6250] eta: 0:01:15 lr: 0.000047 grad: 0.0942 (0.0995) loss: 0.8219 (0.8181) time: 0.1362 data: 0.0561 max mem: 9390 +Train: [59] [5800/6250] eta: 0:01:01 lr: 0.000047 grad: 0.0953 (0.0995) loss: 0.8149 (0.8182) time: 0.1505 data: 0.0759 max mem: 9390 +Train: [59] [5900/6250] eta: 0:00:47 lr: 0.000047 grad: 0.0997 (0.0995) loss: 0.8202 (0.8182) time: 0.1251 data: 0.0507 max mem: 9390 +Train: [59] [6000/6250] eta: 0:00:34 lr: 0.000047 grad: 0.1015 (0.0995) loss: 0.8204 (0.8182) time: 0.1311 data: 0.0524 max mem: 9390 +Train: [59] [6100/6250] eta: 0:00:20 lr: 0.000047 grad: 0.1001 (0.0995) loss: 0.8201 (0.8182) time: 0.1398 data: 0.0637 max mem: 9390 +Train: [59] [6200/6250] eta: 0:00:06 lr: 0.000047 grad: 0.1069 (0.0996) loss: 0.8172 (0.8182) time: 0.1408 data: 0.0604 max mem: 9390 +Train: [59] [6249/6250] eta: 0:00:00 lr: 0.000047 grad: 0.0969 (0.0996) loss: 0.8165 (0.8182) time: 0.1425 data: 0.0570 max mem: 9390 +Train: [59] Total time: 0:14:20 (0.1376 s / it) +Averaged stats: lr: 0.000047 grad: 0.0969 (0.0996) loss: 0.8165 (0.8182) +Eval (hcp-train-subset): [59] [ 0/62] eta: 0:03:54 loss: 0.8416 (0.8416) time: 3.7763 data: 3.6774 max mem: 9390 +Eval (hcp-train-subset): [59] [61/62] eta: 0:00:00 loss: 0.8354 (0.8362) time: 0.0928 data: 0.0664 max mem: 9390 +Eval (hcp-train-subset): [59] Total time: 0:00:13 (0.2128 s / it) +Averaged stats (hcp-train-subset): loss: 0.8354 (0.8362) +Making plots (hcp-train-subset): example=57 +Eval (hcp-val): [59] [ 0/62] eta: 0:05:47 loss: 0.8312 (0.8312) time: 5.6062 data: 5.5762 max mem: 9390 +Eval (hcp-val): [59] [61/62] eta: 0:00:00 loss: 0.8316 (0.8333) time: 0.1117 data: 0.0868 max mem: 9390 +Eval (hcp-val): [59] Total time: 0:00:12 (0.2062 s / it) +Averaged stats (hcp-val): loss: 0.8316 (0.8333) +Making plots (hcp-val): example=41 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +Train: [60] [ 0/6250] eta: 10:46:00 lr: 0.000047 grad: 0.1632 (0.1632) loss: 0.8853 (0.8853) time: 6.2016 data: 6.1038 max mem: 9390 +Train: [60] [ 100/6250] eta: 0:20:34 lr: 0.000047 grad: 0.0958 (0.1200) loss: 0.8122 (0.8224) time: 0.1597 data: 0.0598 max mem: 9390 +Train: [60] [ 200/6250] eta: 0:17:40 lr: 0.000047 grad: 0.0916 (0.1121) loss: 0.8247 (0.8198) time: 0.1501 data: 0.0685 max mem: 9390 +Train: [60] [ 300/6250] eta: 0:16:21 lr: 0.000047 grad: 0.0932 (0.1075) loss: 0.8219 (0.8196) time: 0.1500 data: 0.0676 max mem: 9390 +Train: [60] [ 400/6250] eta: 0:15:24 lr: 0.000047 grad: 0.0904 (0.1045) loss: 0.8231 (0.8199) time: 0.1421 data: 0.0558 max mem: 9390 +Train: [60] [ 500/6250] eta: 0:14:37 lr: 0.000047 grad: 0.0906 (0.1026) loss: 0.8206 (0.8205) time: 0.1241 data: 0.0377 max mem: 9390 +Train: [60] [ 600/6250] eta: 0:14:06 lr: 0.000047 grad: 0.0906 (0.1015) loss: 0.8258 (0.8210) time: 0.1524 data: 0.0697 max mem: 9390 +Train: [60] [ 700/6250] eta: 0:13:36 lr: 0.000047 grad: 0.0952 (0.1008) loss: 0.8169 (0.8211) time: 0.1431 data: 0.0539 max mem: 9390 +Train: [60] [ 800/6250] eta: 0:13:14 lr: 0.000047 grad: 0.0960 (0.1009) loss: 0.8110 (0.8208) time: 0.1391 data: 0.0609 max mem: 9390 +Train: [60] [ 900/6250] eta: 0:12:53 lr: 0.000047 grad: 0.0902 (0.1006) loss: 0.8181 (0.8205) time: 0.1338 data: 0.0584 max mem: 9390 +Train: [60] [1000/6250] eta: 0:12:32 lr: 0.000047 grad: 0.1033 (0.1005) loss: 0.8175 (0.8202) time: 0.1363 data: 0.0584 max mem: 9390 +Train: [60] [1100/6250] eta: 0:12:13 lr: 0.000047 grad: 0.0865 (0.0999) loss: 0.8231 (0.8201) time: 0.0945 data: 0.0189 max mem: 9390 +Train: [60] [1200/6250] eta: 0:11:55 lr: 0.000047 grad: 0.0999 (0.0997) loss: 0.8183 (0.8199) time: 0.1323 data: 0.0544 max mem: 9390 +Train: [60] [1300/6250] eta: 0:11:36 lr: 0.000047 grad: 0.0956 (0.0996) loss: 0.8186 (0.8197) time: 0.1044 data: 0.0280 max mem: 9390 +Train: [60] [1400/6250] eta: 0:11:23 lr: 0.000047 grad: 0.1007 (0.0996) loss: 0.8063 (0.8193) time: 0.1412 data: 0.0582 max mem: 9390 +Train: [60] [1500/6250] eta: 0:11:26 lr: 0.000047 grad: 0.0945 (0.0995) loss: 0.8245 (0.8192) time: 0.2955 data: 0.2009 max mem: 9390 +Train: [60] [1600/6250] eta: 0:11:02 lr: 0.000047 grad: 0.0977 (0.0994) loss: 0.8140 (0.8190) time: 0.1209 data: 0.0379 max mem: 9390 +Train: [60] [1700/6250] eta: 0:10:46 lr: 0.000047 grad: 0.0950 (0.0995) loss: 0.8232 (0.8188) time: 0.1313 data: 0.0582 max mem: 9390 +Train: [60] [1800/6250] eta: 0:10:31 lr: 0.000047 grad: 0.0900 (0.0994) loss: 0.8224 (0.8187) time: 0.1375 data: 0.0635 max mem: 9390 +Train: [60] [1900/6250] eta: 0:10:18 lr: 0.000047 grad: 0.0977 (0.0993) loss: 0.8149 (0.8186) time: 0.1602 data: 0.0802 max mem: 9390 +Train: [60] [2000/6250] eta: 0:10:05 lr: 0.000047 grad: 0.0898 (0.0993) loss: 0.8201 (0.8183) time: 0.1668 data: 0.0796 max mem: 9390 +Train: [60] [2100/6250] eta: 0:09:51 lr: 0.000046 grad: 0.0934 (0.0993) loss: 0.8184 (0.8181) time: 0.1006 data: 0.0122 max mem: 9390 +Train: [60] [2200/6250] eta: 0:09:36 lr: 0.000046 grad: 0.0961 (0.0993) loss: 0.8164 (0.8180) time: 0.1543 data: 0.0632 max mem: 9390 +Train: [60] [2300/6250] eta: 0:09:22 lr: 0.000046 grad: 0.0994 (0.0994) loss: 0.8116 (0.8178) time: 0.1051 data: 0.0200 max mem: 9390 +Train: [60] [2400/6250] eta: 0:09:08 lr: 0.000046 grad: 0.0926 (0.0994) loss: 0.8136 (0.8177) time: 0.1569 data: 0.0744 max mem: 9390 +Train: [60] [2500/6250] eta: 0:08:54 lr: 0.000046 grad: 0.0968 (0.0994) loss: 0.8103 (0.8175) time: 0.1443 data: 0.0649 max mem: 9390 +Train: [60] [2600/6250] eta: 0:08:42 lr: 0.000046 grad: 0.1026 (0.0995) loss: 0.8098 (0.8174) time: 0.1413 data: 0.0678 max mem: 9390 +Train: [60] [2700/6250] eta: 0:08:27 lr: 0.000046 grad: 0.0977 (0.0995) loss: 0.8205 (0.8173) time: 0.1153 data: 0.0436 max mem: 9390 +Train: [60] [2800/6250] eta: 0:08:12 lr: 0.000046 grad: 0.0961 (0.0995) loss: 0.8141 (0.8173) time: 0.1600 data: 0.0750 max mem: 9390 +Train: [60] [2900/6250] eta: 0:07:58 lr: 0.000046 grad: 0.1005 (0.0996) loss: 0.8181 (0.8173) time: 0.1210 data: 0.0471 max mem: 9390 +Train: [60] [3000/6250] eta: 0:07:44 lr: 0.000046 grad: 0.1055 (0.0997) loss: 0.8120 (0.8172) time: 0.1658 data: 0.0842 max mem: 9390 +Train: [60] [3100/6250] eta: 0:07:30 lr: 0.000046 grad: 0.1058 (0.0998) loss: 0.8117 (0.8172) time: 0.1423 data: 0.0613 max mem: 9390 +Train: [60] [3200/6250] eta: 0:07:15 lr: 0.000046 grad: 0.1010 (0.0999) loss: 0.8118 (0.8171) time: 0.1352 data: 0.0628 max mem: 9390 +Train: [60] [3300/6250] eta: 0:06:59 lr: 0.000046 grad: 0.0996 (0.1001) loss: 0.8149 (0.8171) time: 0.1177 data: 0.0340 max mem: 9390 +Train: [60] [3400/6250] eta: 0:06:43 lr: 0.000046 grad: 0.0990 (0.1002) loss: 0.8185 (0.8171) time: 0.1214 data: 0.0405 max mem: 9390 +Train: [60] [3500/6250] eta: 0:06:28 lr: 0.000046 grad: 0.0960 (0.1003) loss: 0.8203 (0.8171) time: 0.1348 data: 0.0525 max mem: 9390 +Train: [60] [3600/6250] eta: 0:06:12 lr: 0.000046 grad: 0.0984 (0.1004) loss: 0.8142 (0.8170) time: 0.1061 data: 0.0262 max mem: 9390 +Train: [60] [3700/6250] eta: 0:05:57 lr: 0.000046 grad: 0.0997 (0.1004) loss: 0.8158 (0.8169) time: 0.1258 data: 0.0444 max mem: 9390 +Train: [60] [3800/6250] eta: 0:05:42 lr: 0.000046 grad: 0.0985 (0.1005) loss: 0.8173 (0.8168) time: 0.1325 data: 0.0599 max mem: 9390 +Train: [60] [3900/6250] eta: 0:05:27 lr: 0.000046 grad: 0.1027 (0.1006) loss: 0.8137 (0.8168) time: 0.1261 data: 0.0514 max mem: 9390 +Train: [60] [4000/6250] eta: 0:05:13 lr: 0.000046 grad: 0.0987 (0.1007) loss: 0.8152 (0.8167) time: 0.0900 data: 0.0002 max mem: 9390 +Train: [60] [4100/6250] eta: 0:04:59 lr: 0.000046 grad: 0.1033 (0.1008) loss: 0.8183 (0.8167) time: 0.1331 data: 0.0565 max mem: 9390 +Train: [60] [4200/6250] eta: 0:04:44 lr: 0.000046 grad: 0.0982 (0.1009) loss: 0.8230 (0.8166) time: 0.1430 data: 0.0695 max mem: 9390 +Train: [60] [4300/6250] eta: 0:04:30 lr: 0.000046 grad: 0.0970 (0.1010) loss: 0.8169 (0.8166) time: 0.1304 data: 0.0509 max mem: 9390 +Train: [60] [4400/6250] eta: 0:04:15 lr: 0.000046 grad: 0.1012 (0.1010) loss: 0.8146 (0.8167) time: 0.1393 data: 0.0465 max mem: 9390 +Train: [60] [4500/6250] eta: 0:04:01 lr: 0.000046 grad: 0.1063 (0.1011) loss: 0.8098 (0.8166) time: 0.1254 data: 0.0441 max mem: 9390 +Train: [60] [4600/6250] eta: 0:03:47 lr: 0.000046 grad: 0.1057 (0.1012) loss: 0.8130 (0.8166) time: 0.1253 data: 0.0465 max mem: 9390 +Train: [60] [4700/6250] eta: 0:03:33 lr: 0.000046 grad: 0.0977 (0.1013) loss: 0.8149 (0.8166) time: 0.1319 data: 0.0536 max mem: 9390 +Train: [60] [4800/6250] eta: 0:03:19 lr: 0.000046 grad: 0.1063 (0.1014) loss: 0.8119 (0.8165) time: 0.1251 data: 0.0512 max mem: 9390 +Train: [60] [4900/6250] eta: 0:03:05 lr: 0.000046 grad: 0.1063 (0.1015) loss: 0.8121 (0.8165) time: 0.1328 data: 0.0543 max mem: 9390 +Train: [60] [5000/6250] eta: 0:02:51 lr: 0.000046 grad: 0.1055 (0.1016) loss: 0.8113 (0.8165) time: 0.1221 data: 0.0463 max mem: 9390 +Train: [60] [5100/6250] eta: 0:02:37 lr: 0.000046 grad: 0.1106 (0.1017) loss: 0.8068 (0.8164) time: 0.1432 data: 0.0675 max mem: 9390 +Train: [60] [5200/6250] eta: 0:02:23 lr: 0.000045 grad: 0.1002 (0.1018) loss: 0.8148 (0.8164) time: 0.1379 data: 0.0627 max mem: 9390 +Train: [60] [5300/6250] eta: 0:02:10 lr: 0.000045 grad: 0.0994 (0.1018) loss: 0.8124 (0.8163) time: 0.1282 data: 0.0512 max mem: 9390 +Train: [60] [5400/6250] eta: 0:01:56 lr: 0.000045 grad: 0.1035 (0.1019) loss: 0.8154 (0.8163) time: 0.1199 data: 0.0465 max mem: 9390 +Train: [60] [5500/6250] eta: 0:01:42 lr: 0.000045 grad: 0.1016 (0.1020) loss: 0.8171 (0.8163) time: 0.1596 data: 0.0831 max mem: 9390 +Train: [60] [5600/6250] eta: 0:01:28 lr: 0.000045 grad: 0.1069 (0.1021) loss: 0.8156 (0.8163) time: 0.1183 data: 0.0424 max mem: 9390 +Train: [60] [5700/6250] eta: 0:01:15 lr: 0.000045 grad: 0.1063 (0.1022) loss: 0.8088 (0.8162) time: 0.1378 data: 0.0653 max mem: 9390 +Train: [60] [5800/6250] eta: 0:01:01 lr: 0.000045 grad: 0.0968 (0.1022) loss: 0.8133 (0.8162) time: 0.1589 data: 0.0746 max mem: 9390 +Train: [60] [5900/6250] eta: 0:00:47 lr: 0.000045 grad: 0.1079 (0.1023) loss: 0.8129 (0.8161) time: 0.1481 data: 0.0668 max mem: 9390 +Train: [60] [6000/6250] eta: 0:00:34 lr: 0.000045 grad: 0.1083 (0.1024) loss: 0.8106 (0.8160) time: 0.1340 data: 0.0546 max mem: 9390 +Train: [60] [6100/6250] eta: 0:00:20 lr: 0.000045 grad: 0.0975 (0.1025) loss: 0.8176 (0.8160) time: 0.1230 data: 0.0449 max mem: 9390 +Train: [60] [6200/6250] eta: 0:00:06 lr: 0.000045 grad: 0.1061 (0.1026) loss: 0.8149 (0.8159) time: 0.1316 data: 0.0529 max mem: 9390 +Train: [60] [6249/6250] eta: 0:00:00 lr: 0.000045 grad: 0.1126 (0.1026) loss: 0.8108 (0.8159) time: 0.1559 data: 0.0628 max mem: 9390 +Train: [60] Total time: 0:14:19 (0.1376 s / it) +Averaged stats: lr: 0.000045 grad: 0.1126 (0.1026) loss: 0.8108 (0.8159) +Eval (hcp-train-subset): [60] [ 0/62] eta: 0:04:42 loss: 0.8458 (0.8458) time: 4.5561 data: 4.5251 max mem: 9390 +Eval (hcp-train-subset): [60] [61/62] eta: 0:00:00 loss: 0.8310 (0.8332) time: 0.1031 data: 0.0780 max mem: 9390 +Eval (hcp-train-subset): [60] Total time: 0:00:12 (0.2073 s / it) +Averaged stats (hcp-train-subset): loss: 0.8310 (0.8332) +Eval (hcp-val): [60] [ 0/62] eta: 0:04:47 loss: 0.8311 (0.8311) time: 4.6369 data: 4.6070 max mem: 9390 +Eval (hcp-val): [60] [61/62] eta: 0:00:00 loss: 0.8326 (0.8336) time: 0.1296 data: 0.1029 max mem: 9390 +Eval (hcp-val): [60] Total time: 0:00:12 (0.2035 s / it) +Averaged stats (hcp-val): loss: 0.8326 (0.8336) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +Train: [61] [ 0/6250] eta: 7:00:11 lr: 0.000045 grad: 0.3312 (0.3312) loss: 0.8747 (0.8747) time: 4.0338 data: 3.8320 max mem: 9390 +Train: [61] [ 100/6250] eta: 0:20:48 lr: 0.000045 grad: 0.0983 (0.1235) loss: 0.8200 (0.8286) time: 0.1380 data: 0.0475 max mem: 9390 +Train: [61] [ 200/6250] eta: 0:17:56 lr: 0.000045 grad: 0.1072 (0.1177) loss: 0.8224 (0.8259) time: 0.1478 data: 0.0674 max mem: 9390 +Train: [61] [ 300/6250] eta: 0:16:32 lr: 0.000045 grad: 0.0974 (0.1181) loss: 0.8198 (0.8218) time: 0.1531 data: 0.0709 max mem: 9390 +Train: [61] [ 400/6250] eta: 0:15:32 lr: 0.000045 grad: 0.0992 (0.1154) loss: 0.8129 (0.8198) time: 0.1469 data: 0.0611 max mem: 9390 +Train: [61] [ 500/6250] eta: 0:14:48 lr: 0.000045 grad: 0.0978 (0.1132) loss: 0.8139 (0.8187) time: 0.1095 data: 0.0156 max mem: 9390 +Train: [61] [ 600/6250] eta: 0:14:11 lr: 0.000045 grad: 0.1008 (0.1109) loss: 0.8194 (0.8188) time: 0.1387 data: 0.0588 max mem: 9390 +Train: [61] [ 700/6250] eta: 0:13:42 lr: 0.000045 grad: 0.0979 (0.1091) loss: 0.8213 (0.8191) time: 0.1408 data: 0.0639 max mem: 9390 +Train: [61] [ 800/6250] eta: 0:13:11 lr: 0.000045 grad: 0.0929 (0.1074) loss: 0.8180 (0.8192) time: 0.1187 data: 0.0350 max mem: 9390 +Train: [61] [ 900/6250] eta: 0:12:50 lr: 0.000045 grad: 0.0919 (0.1062) loss: 0.8257 (0.8195) time: 0.1356 data: 0.0504 max mem: 9390 +Train: [61] [1000/6250] eta: 0:12:31 lr: 0.000045 grad: 0.0972 (0.1052) loss: 0.8229 (0.8196) time: 0.1364 data: 0.0535 max mem: 9390 +Train: [61] [1100/6250] eta: 0:12:14 lr: 0.000045 grad: 0.0952 (0.1044) loss: 0.8151 (0.8195) time: 0.1346 data: 0.0558 max mem: 9390 +Train: [61] [1200/6250] eta: 0:11:59 lr: 0.000045 grad: 0.0912 (0.1040) loss: 0.8196 (0.8192) time: 0.1215 data: 0.0371 max mem: 9390 +Train: [61] [1300/6250] eta: 0:11:41 lr: 0.000045 grad: 0.0924 (0.1036) loss: 0.8222 (0.8191) time: 0.1165 data: 0.0383 max mem: 9390 +Train: [61] [1400/6250] eta: 0:11:24 lr: 0.000045 grad: 0.1017 (0.1033) loss: 0.8161 (0.8189) time: 0.1231 data: 0.0452 max mem: 9390 +Train: [61] [1500/6250] eta: 0:11:09 lr: 0.000045 grad: 0.1013 (0.1030) loss: 0.8183 (0.8187) time: 0.1401 data: 0.0613 max mem: 9390 +Train: [61] [1600/6250] eta: 0:10:56 lr: 0.000045 grad: 0.1027 (0.1029) loss: 0.8115 (0.8186) time: 0.1741 data: 0.0996 max mem: 9390 +Train: [61] [1700/6250] eta: 0:10:38 lr: 0.000045 grad: 0.0919 (0.1027) loss: 0.8209 (0.8184) time: 0.1192 data: 0.0446 max mem: 9390 +Train: [61] [1800/6250] eta: 0:10:24 lr: 0.000045 grad: 0.0962 (0.1026) loss: 0.8185 (0.8182) time: 0.1380 data: 0.0625 max mem: 9390 +Train: [61] [1900/6250] eta: 0:10:11 lr: 0.000045 grad: 0.1074 (0.1028) loss: 0.8093 (0.8180) time: 0.1588 data: 0.0823 max mem: 9390 +Train: [61] [2000/6250] eta: 0:09:55 lr: 0.000045 grad: 0.1056 (0.1026) loss: 0.8137 (0.8178) time: 0.1528 data: 0.0786 max mem: 9390 +Train: [61] [2100/6250] eta: 0:09:41 lr: 0.000044 grad: 0.1043 (0.1028) loss: 0.8147 (0.8175) time: 0.1597 data: 0.0774 max mem: 9390 +Train: [61] [2200/6250] eta: 0:09:27 lr: 0.000044 grad: 0.1013 (0.1027) loss: 0.8113 (0.8174) time: 0.1503 data: 0.0699 max mem: 9390 +Train: [61] [2300/6250] eta: 0:09:13 lr: 0.000044 grad: 0.0972 (0.1026) loss: 0.8128 (0.8172) time: 0.1327 data: 0.0548 max mem: 9390 +Train: [61] [2400/6250] eta: 0:08:58 lr: 0.000044 grad: 0.1006 (0.1026) loss: 0.8101 (0.8171) time: 0.1274 data: 0.0512 max mem: 9390 +Train: [61] [2500/6250] eta: 0:08:43 lr: 0.000044 grad: 0.1022 (0.1026) loss: 0.8169 (0.8169) time: 0.1332 data: 0.0571 max mem: 9390 +Train: [61] [2600/6250] eta: 0:08:31 lr: 0.000044 grad: 0.0998 (0.1026) loss: 0.8171 (0.8167) time: 0.1743 data: 0.1030 max mem: 9390 +Train: [61] [2700/6250] eta: 0:08:18 lr: 0.000044 grad: 0.0976 (0.1026) loss: 0.8161 (0.8167) time: 0.1504 data: 0.0683 max mem: 9390 +Train: [61] [2800/6250] eta: 0:08:04 lr: 0.000044 grad: 0.0997 (0.1026) loss: 0.8169 (0.8165) time: 0.1423 data: 0.0670 max mem: 9390 +Train: [61] [2900/6250] eta: 0:07:51 lr: 0.000044 grad: 0.1032 (0.1027) loss: 0.8158 (0.8165) time: 0.1668 data: 0.0905 max mem: 9390 +Train: [61] [3000/6250] eta: 0:07:38 lr: 0.000044 grad: 0.0949 (0.1026) loss: 0.8082 (0.8164) time: 0.1519 data: 0.0765 max mem: 9390 +Train: [61] [3100/6250] eta: 0:07:23 lr: 0.000044 grad: 0.0942 (0.1027) loss: 0.8156 (0.8164) time: 0.1320 data: 0.0527 max mem: 9390 +Train: [61] [3200/6250] eta: 0:07:09 lr: 0.000044 grad: 0.0975 (0.1028) loss: 0.8136 (0.8163) time: 0.1415 data: 0.0676 max mem: 9390 +Train: [61] [3300/6250] eta: 0:06:53 lr: 0.000044 grad: 0.1040 (0.1029) loss: 0.8094 (0.8162) time: 0.1414 data: 0.0622 max mem: 9390 +Train: [61] [3400/6250] eta: 0:06:38 lr: 0.000044 grad: 0.1004 (0.1029) loss: 0.8144 (0.8161) time: 0.1207 data: 0.0403 max mem: 9390 +Train: [61] [3500/6250] eta: 0:06:22 lr: 0.000044 grad: 0.1012 (0.1029) loss: 0.8154 (0.8160) time: 0.1300 data: 0.0533 max mem: 9390 +Train: [61] [3600/6250] eta: 0:06:07 lr: 0.000044 grad: 0.1095 (0.1030) loss: 0.8105 (0.8159) time: 0.1260 data: 0.0403 max mem: 9390 +Train: [61] [3700/6250] eta: 0:05:52 lr: 0.000044 grad: 0.1046 (0.1031) loss: 0.8040 (0.8159) time: 0.1180 data: 0.0409 max mem: 9390 +Train: [61] [3800/6250] eta: 0:05:37 lr: 0.000044 grad: 0.0955 (0.1031) loss: 0.8217 (0.8159) time: 0.1230 data: 0.0418 max mem: 9390 +Train: [61] [3900/6250] eta: 0:05:23 lr: 0.000044 grad: 0.0926 (0.1031) loss: 0.8183 (0.8159) time: 0.1268 data: 0.0492 max mem: 9390 +Train: [61] [4000/6250] eta: 0:05:08 lr: 0.000044 grad: 0.0993 (0.1031) loss: 0.8174 (0.8159) time: 0.1396 data: 0.0570 max mem: 9390 +Train: [61] [4100/6250] eta: 0:04:54 lr: 0.000044 grad: 0.0982 (0.1032) loss: 0.8096 (0.8158) time: 0.1112 data: 0.0328 max mem: 9390 +Train: [61] [4200/6250] eta: 0:04:40 lr: 0.000044 grad: 0.0970 (0.1032) loss: 0.8119 (0.8158) time: 0.1070 data: 0.0258 max mem: 9390 +Train: [61] [4300/6250] eta: 0:04:26 lr: 0.000044 grad: 0.1065 (0.1032) loss: 0.8120 (0.8158) time: 0.1484 data: 0.0663 max mem: 9390 +Train: [61] [4400/6250] eta: 0:04:12 lr: 0.000044 grad: 0.0994 (0.1031) loss: 0.8136 (0.8158) time: 0.1361 data: 0.0600 max mem: 9390 +Train: [61] [4500/6250] eta: 0:03:58 lr: 0.000044 grad: 0.0999 (0.1032) loss: 0.8065 (0.8157) time: 0.1211 data: 0.0344 max mem: 9390 +Train: [61] [4600/6250] eta: 0:03:44 lr: 0.000044 grad: 0.0974 (0.1031) loss: 0.8231 (0.8157) time: 0.1226 data: 0.0446 max mem: 9390 +Train: [61] [4700/6250] eta: 0:03:30 lr: 0.000044 grad: 0.0978 (0.1031) loss: 0.8171 (0.8157) time: 0.1275 data: 0.0514 max mem: 9390 +Train: [61] [4800/6250] eta: 0:03:16 lr: 0.000044 grad: 0.0951 (0.1031) loss: 0.8240 (0.8158) time: 0.1290 data: 0.0507 max mem: 9390 +Train: [61] [4900/6250] eta: 0:03:02 lr: 0.000044 grad: 0.0959 (0.1030) loss: 0.8179 (0.8158) time: 0.1212 data: 0.0395 max mem: 9390 +Train: [61] [5000/6250] eta: 0:02:49 lr: 0.000044 grad: 0.0949 (0.1029) loss: 0.8142 (0.8159) time: 0.1154 data: 0.0415 max mem: 9390 +Train: [61] [5100/6250] eta: 0:02:35 lr: 0.000044 grad: 0.1009 (0.1029) loss: 0.8257 (0.8160) time: 0.1399 data: 0.0614 max mem: 9390 +Train: [61] [5200/6250] eta: 0:02:21 lr: 0.000044 grad: 0.0966 (0.1028) loss: 0.8165 (0.8161) time: 0.1208 data: 0.0418 max mem: 9390 +Train: [61] [5300/6250] eta: 0:02:08 lr: 0.000043 grad: 0.0996 (0.1028) loss: 0.8188 (0.8161) time: 0.1363 data: 0.0585 max mem: 9390 +Train: [61] [5400/6250] eta: 0:01:54 lr: 0.000043 grad: 0.1000 (0.1027) loss: 0.8196 (0.8162) time: 0.1495 data: 0.0754 max mem: 9390 +Train: [61] [5500/6250] eta: 0:01:41 lr: 0.000043 grad: 0.0987 (0.1027) loss: 0.8152 (0.8162) time: 0.0874 data: 0.0027 max mem: 9390 +Train: [61] [5600/6250] eta: 0:01:28 lr: 0.000043 grad: 0.0983 (0.1027) loss: 0.8150 (0.8163) time: 0.1915 data: 0.1030 max mem: 9390 +Train: [61] [5700/6250] eta: 0:01:14 lr: 0.000043 grad: 0.0957 (0.1026) loss: 0.8204 (0.8163) time: 0.1505 data: 0.0716 max mem: 9390 +Train: [61] [5800/6250] eta: 0:01:00 lr: 0.000043 grad: 0.0967 (0.1026) loss: 0.8298 (0.8164) time: 0.1320 data: 0.0532 max mem: 9390 +Train: [61] [5900/6250] eta: 0:00:47 lr: 0.000043 grad: 0.0989 (0.1026) loss: 0.8235 (0.8165) time: 0.1703 data: 0.0939 max mem: 9390 +Train: [61] [6000/6250] eta: 0:00:33 lr: 0.000043 grad: 0.0986 (0.1026) loss: 0.8174 (0.8165) time: 0.1186 data: 0.0361 max mem: 9390 +Train: [61] [6100/6250] eta: 0:00:20 lr: 0.000043 grad: 0.0969 (0.1026) loss: 0.8199 (0.8166) time: 0.1400 data: 0.0606 max mem: 9390 +Train: [61] [6200/6250] eta: 0:00:06 lr: 0.000043 grad: 0.0957 (0.1026) loss: 0.8215 (0.8166) time: 0.1539 data: 0.0773 max mem: 9390 +Train: [61] [6249/6250] eta: 0:00:00 lr: 0.000043 grad: 0.0990 (0.1026) loss: 0.8143 (0.8166) time: 0.1453 data: 0.0611 max mem: 9390 +Train: [61] Total time: 0:14:13 (0.1366 s / it) +Averaged stats: lr: 0.000043 grad: 0.0990 (0.1026) loss: 0.8143 (0.8166) +Eval (hcp-train-subset): [61] [ 0/62] eta: 0:04:31 loss: 0.8425 (0.8425) time: 4.3743 data: 4.3437 max mem: 9390 +Eval (hcp-train-subset): [61] [61/62] eta: 0:00:00 loss: 0.8305 (0.8314) time: 0.1181 data: 0.0930 max mem: 9390 +Eval (hcp-train-subset): [61] Total time: 0:00:12 (0.1992 s / it) +Averaged stats (hcp-train-subset): loss: 0.8305 (0.8314) +Eval (hcp-val): [61] [ 0/62] eta: 0:03:27 loss: 0.8272 (0.8272) time: 3.3438 data: 3.2468 max mem: 9390 +Eval (hcp-val): [61] [61/62] eta: 0:00:00 loss: 0.8326 (0.8328) time: 0.1203 data: 0.0953 max mem: 9390 +Eval (hcp-val): [61] Total time: 0:00:12 (0.1939 s / it) +Averaged stats (hcp-val): loss: 0.8326 (0.8328) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +Train: [62] [ 0/6250] eta: 9:24:55 lr: 0.000043 grad: 0.1202 (0.1202) loss: 0.8224 (0.8224) time: 5.4233 data: 5.3315 max mem: 9390 +Train: [62] [ 100/6250] eta: 0:19:30 lr: 0.000043 grad: 0.1200 (0.1293) loss: 0.8209 (0.8285) time: 0.1370 data: 0.0464 max mem: 9390 +Train: [62] [ 200/6250] eta: 0:17:32 lr: 0.000043 grad: 0.0934 (0.1198) loss: 0.8257 (0.8280) time: 0.1808 data: 0.0852 max mem: 9390 +Train: [62] [ 300/6250] eta: 0:16:43 lr: 0.000043 grad: 0.1129 (0.1179) loss: 0.8128 (0.8262) time: 0.1859 data: 0.0883 max mem: 9390 +Train: [62] [ 400/6250] eta: 0:15:42 lr: 0.000043 grad: 0.0985 (0.1152) loss: 0.8213 (0.8250) time: 0.1249 data: 0.0434 max mem: 9390 +Train: [62] [ 500/6250] eta: 0:14:59 lr: 0.000043 grad: 0.0987 (0.1137) loss: 0.8219 (0.8236) time: 0.1341 data: 0.0502 max mem: 9390 +Train: [62] [ 600/6250] eta: 0:14:28 lr: 0.000043 grad: 0.0994 (0.1119) loss: 0.8128 (0.8224) time: 0.1474 data: 0.0725 max mem: 9390 +Train: [62] [ 700/6250] eta: 0:13:56 lr: 0.000043 grad: 0.0952 (0.1106) loss: 0.8135 (0.8215) time: 0.1314 data: 0.0489 max mem: 9390 +Train: [62] [ 800/6250] eta: 0:13:34 lr: 0.000043 grad: 0.0927 (0.1095) loss: 0.8307 (0.8210) time: 0.1230 data: 0.0439 max mem: 9390 +Train: [62] [ 900/6250] eta: 0:13:11 lr: 0.000043 grad: 0.0889 (0.1083) loss: 0.8230 (0.8210) time: 0.1444 data: 0.0630 max mem: 9390 +Train: [62] [1000/6250] eta: 0:12:51 lr: 0.000043 grad: 0.0996 (0.1075) loss: 0.8201 (0.8210) time: 0.1472 data: 0.0566 max mem: 9390 +Train: [62] [1100/6250] eta: 0:12:37 lr: 0.000043 grad: 0.0969 (0.1069) loss: 0.8151 (0.8209) time: 0.1621 data: 0.0760 max mem: 9390 +Train: [62] [1200/6250] eta: 0:12:19 lr: 0.000043 grad: 0.1026 (0.1066) loss: 0.8201 (0.8207) time: 0.1223 data: 0.0351 max mem: 9390 +Train: [62] [1300/6250] eta: 0:12:05 lr: 0.000043 grad: 0.0975 (0.1061) loss: 0.8186 (0.8205) time: 0.1537 data: 0.0702 max mem: 9390 +Train: [62] [1400/6250] eta: 0:11:47 lr: 0.000043 grad: 0.1012 (0.1056) loss: 0.8190 (0.8204) time: 0.1364 data: 0.0595 max mem: 9390 +Train: [62] [1500/6250] eta: 0:11:30 lr: 0.000043 grad: 0.1057 (0.1054) loss: 0.8205 (0.8202) time: 0.1415 data: 0.0624 max mem: 9390 +Train: [62] [1600/6250] eta: 0:11:11 lr: 0.000043 grad: 0.0956 (0.1052) loss: 0.8063 (0.8199) time: 0.1307 data: 0.0515 max mem: 9390 +Train: [62] [1700/6250] eta: 0:10:55 lr: 0.000043 grad: 0.1006 (0.1050) loss: 0.8167 (0.8198) time: 0.1401 data: 0.0571 max mem: 9390 +Train: [62] [1800/6250] eta: 0:10:39 lr: 0.000043 grad: 0.0955 (0.1047) loss: 0.8212 (0.8198) time: 0.1271 data: 0.0509 max mem: 9390 +Train: [62] [1900/6250] eta: 0:10:24 lr: 0.000043 grad: 0.0989 (0.1046) loss: 0.8138 (0.8197) time: 0.1331 data: 0.0532 max mem: 9390 +Train: [62] [2000/6250] eta: 0:10:09 lr: 0.000043 grad: 0.0973 (0.1044) loss: 0.8103 (0.8196) time: 0.1325 data: 0.0510 max mem: 9390 +Train: [62] [2100/6250] eta: 0:09:52 lr: 0.000043 grad: 0.0943 (0.1042) loss: 0.8173 (0.8196) time: 0.1491 data: 0.0677 max mem: 9390 +Train: [62] [2200/6250] eta: 0:09:37 lr: 0.000042 grad: 0.1024 (0.1042) loss: 0.8169 (0.8195) time: 0.1455 data: 0.0583 max mem: 9390 +Train: [62] [2300/6250] eta: 0:09:22 lr: 0.000042 grad: 0.1101 (0.1042) loss: 0.8169 (0.8194) time: 0.1350 data: 0.0581 max mem: 9390 +Train: [62] [2400/6250] eta: 0:09:07 lr: 0.000042 grad: 0.1035 (0.1041) loss: 0.8221 (0.8193) time: 0.1607 data: 0.0830 max mem: 9390 +Train: [62] [2500/6250] eta: 0:08:51 lr: 0.000042 grad: 0.0991 (0.1040) loss: 0.8210 (0.8194) time: 0.1175 data: 0.0371 max mem: 9390 +Train: [62] [2600/6250] eta: 0:08:37 lr: 0.000042 grad: 0.1118 (0.1040) loss: 0.8078 (0.8193) time: 0.1377 data: 0.0556 max mem: 9390 +Train: [62] [2700/6250] eta: 0:08:22 lr: 0.000042 grad: 0.0989 (0.1039) loss: 0.8226 (0.8193) time: 0.1518 data: 0.0678 max mem: 9390 +Train: [62] [2800/6250] eta: 0:08:10 lr: 0.000042 grad: 0.0961 (0.1038) loss: 0.8215 (0.8193) time: 0.1390 data: 0.0668 max mem: 9390 +Train: [62] [2900/6250] eta: 0:07:57 lr: 0.000042 grad: 0.0998 (0.1036) loss: 0.8225 (0.8194) time: 0.1353 data: 0.0668 max mem: 9390 +Train: [62] [3000/6250] eta: 0:07:44 lr: 0.000042 grad: 0.0990 (0.1035) loss: 0.8152 (0.8193) time: 0.1458 data: 0.0691 max mem: 9390 +Train: [62] [3100/6250] eta: 0:07:30 lr: 0.000042 grad: 0.1010 (0.1034) loss: 0.8187 (0.8194) time: 0.1487 data: 0.0712 max mem: 9390 +Train: [62] [3200/6250] eta: 0:07:16 lr: 0.000042 grad: 0.0978 (0.1034) loss: 0.8264 (0.8194) time: 0.1395 data: 0.0586 max mem: 9390 +Train: [62] [3300/6250] eta: 0:07:02 lr: 0.000042 grad: 0.1012 (0.1034) loss: 0.8239 (0.8195) time: 0.1415 data: 0.0644 max mem: 9390 +Train: [62] [3400/6250] eta: 0:06:46 lr: 0.000042 grad: 0.1021 (0.1034) loss: 0.8131 (0.8194) time: 0.1183 data: 0.0412 max mem: 9390 +Train: [62] [3500/6250] eta: 0:06:30 lr: 0.000042 grad: 0.1014 (0.1034) loss: 0.8144 (0.8194) time: 0.1270 data: 0.0448 max mem: 9390 +Train: [62] [3600/6250] eta: 0:06:15 lr: 0.000042 grad: 0.1024 (0.1035) loss: 0.8177 (0.8193) time: 0.1262 data: 0.0456 max mem: 9390 +Train: [62] [3700/6250] eta: 0:05:59 lr: 0.000042 grad: 0.1008 (0.1035) loss: 0.8119 (0.8192) time: 0.0978 data: 0.0178 max mem: 9390 +Train: [62] [3800/6250] eta: 0:05:44 lr: 0.000042 grad: 0.0999 (0.1035) loss: 0.8198 (0.8192) time: 0.1433 data: 0.0644 max mem: 9390 +Train: [62] [3900/6250] eta: 0:05:29 lr: 0.000042 grad: 0.0944 (0.1035) loss: 0.8163 (0.8191) time: 0.1114 data: 0.0315 max mem: 9390 +Train: [62] [4000/6250] eta: 0:05:14 lr: 0.000042 grad: 0.1030 (0.1035) loss: 0.8106 (0.8190) time: 0.1287 data: 0.0544 max mem: 9390 +Train: [62] [4100/6250] eta: 0:04:59 lr: 0.000042 grad: 0.1008 (0.1034) loss: 0.8163 (0.8189) time: 0.1224 data: 0.0413 max mem: 9390 +Train: [62] [4200/6250] eta: 0:04:45 lr: 0.000042 grad: 0.1014 (0.1035) loss: 0.8085 (0.8188) time: 0.1345 data: 0.0583 max mem: 9390 +Train: [62] [4300/6250] eta: 0:04:30 lr: 0.000042 grad: 0.0989 (0.1034) loss: 0.8111 (0.8187) time: 0.1192 data: 0.0448 max mem: 9390 +Train: [62] [4400/6250] eta: 0:04:15 lr: 0.000042 grad: 0.1003 (0.1035) loss: 0.8223 (0.8186) time: 0.1094 data: 0.0321 max mem: 9390 +Train: [62] [4500/6250] eta: 0:04:01 lr: 0.000042 grad: 0.1029 (0.1034) loss: 0.8155 (0.8186) time: 0.0950 data: 0.0144 max mem: 9390 +Train: [62] [4600/6250] eta: 0:03:47 lr: 0.000042 grad: 0.1013 (0.1034) loss: 0.8187 (0.8186) time: 0.1292 data: 0.0433 max mem: 9390 +Train: [62] [4700/6250] eta: 0:03:33 lr: 0.000042 grad: 0.1022 (0.1034) loss: 0.8168 (0.8185) time: 0.0922 data: 0.0124 max mem: 9390 +Train: [62] [4800/6250] eta: 0:03:18 lr: 0.000042 grad: 0.0973 (0.1034) loss: 0.8136 (0.8184) time: 0.1176 data: 0.0409 max mem: 9390 +Train: [62] [4900/6250] eta: 0:03:04 lr: 0.000042 grad: 0.1097 (0.1033) loss: 0.8165 (0.8184) time: 0.1106 data: 0.0312 max mem: 9390 +Train: [62] [5000/6250] eta: 0:02:50 lr: 0.000042 grad: 0.1062 (0.1033) loss: 0.8136 (0.8184) time: 0.1230 data: 0.0454 max mem: 9390 +Train: [62] [5100/6250] eta: 0:02:36 lr: 0.000042 grad: 0.1040 (0.1033) loss: 0.8101 (0.8184) time: 0.1252 data: 0.0529 max mem: 9390 +Train: [62] [5200/6250] eta: 0:02:23 lr: 0.000042 grad: 0.0980 (0.1033) loss: 0.8198 (0.8183) time: 0.1284 data: 0.0503 max mem: 9390 +Train: [62] [5300/6250] eta: 0:02:09 lr: 0.000042 grad: 0.1016 (0.1033) loss: 0.8180 (0.8183) time: 0.1502 data: 0.0726 max mem: 9390 +Train: [62] [5400/6250] eta: 0:01:56 lr: 0.000041 grad: 0.0987 (0.1033) loss: 0.8165 (0.8183) time: 0.1343 data: 0.0513 max mem: 9390 +Train: [62] [5500/6250] eta: 0:01:42 lr: 0.000041 grad: 0.1001 (0.1032) loss: 0.8231 (0.8183) time: 0.1358 data: 0.0600 max mem: 9390 +Train: [62] [5600/6250] eta: 0:01:28 lr: 0.000041 grad: 0.0975 (0.1032) loss: 0.8205 (0.8183) time: 0.1326 data: 0.0583 max mem: 9390 +Train: [62] [5700/6250] eta: 0:01:14 lr: 0.000041 grad: 0.0989 (0.1032) loss: 0.8197 (0.8184) time: 0.1264 data: 0.0533 max mem: 9390 +Train: [62] [5800/6250] eta: 0:01:01 lr: 0.000041 grad: 0.1037 (0.1032) loss: 0.8217 (0.8184) time: 0.1407 data: 0.0583 max mem: 9390 +Train: [62] [5900/6250] eta: 0:00:47 lr: 0.000041 grad: 0.0956 (0.1032) loss: 0.8214 (0.8184) time: 0.1631 data: 0.0766 max mem: 9390 +Train: [62] [6000/6250] eta: 0:00:34 lr: 0.000041 grad: 0.0977 (0.1031) loss: 0.8188 (0.8185) time: 0.1956 data: 0.0712 max mem: 9390 +Train: [62] [6100/6250] eta: 0:00:20 lr: 0.000041 grad: 0.1017 (0.1031) loss: 0.8174 (0.8185) time: 0.1353 data: 0.0603 max mem: 9390 +Train: [62] [6200/6250] eta: 0:00:06 lr: 0.000041 grad: 0.0921 (0.1030) loss: 0.8214 (0.8185) time: 0.1243 data: 0.0459 max mem: 9390 +Train: [62] [6249/6250] eta: 0:00:00 lr: 0.000041 grad: 0.0948 (0.1030) loss: 0.8190 (0.8185) time: 0.1293 data: 0.0527 max mem: 9390 +Train: [62] Total time: 0:14:21 (0.1378 s / it) +Averaged stats: lr: 0.000041 grad: 0.0948 (0.1030) loss: 0.8190 (0.8185) +Eval (hcp-train-subset): [62] [ 0/62] eta: 0:03:52 loss: 0.8442 (0.8442) time: 3.7481 data: 3.6483 max mem: 9390 +Eval (hcp-train-subset): [62] [61/62] eta: 0:00:00 loss: 0.8306 (0.8329) time: 0.1207 data: 0.0938 max mem: 9390 +Eval (hcp-train-subset): [62] Total time: 0:00:12 (0.1974 s / it) +Averaged stats (hcp-train-subset): loss: 0.8306 (0.8329) +Eval (hcp-val): [62] [ 0/62] eta: 0:03:39 loss: 0.8304 (0.8304) time: 3.5375 data: 3.4789 max mem: 9390 +Eval (hcp-val): [62] [61/62] eta: 0:00:00 loss: 0.8319 (0.8334) time: 0.1139 data: 0.0853 max mem: 9390 +Eval (hcp-val): [62] Total time: 0:00:12 (0.2026 s / it) +Averaged stats (hcp-val): loss: 0.8319 (0.8334) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +Train: [63] [ 0/6250] eta: 9:14:08 lr: 0.000041 grad: 0.1101 (0.1101) loss: 0.8537 (0.8537) time: 5.3197 data: 5.2073 max mem: 9390 +Train: [63] [ 100/6250] eta: 0:19:32 lr: 0.000041 grad: 0.0943 (0.1450) loss: 0.8295 (0.8303) time: 0.1470 data: 0.0443 max mem: 9390 +Train: [63] [ 200/6250] eta: 0:17:05 lr: 0.000041 grad: 0.1045 (0.1350) loss: 0.8246 (0.8258) time: 0.1598 data: 0.0635 max mem: 9390 +Train: [63] [ 300/6250] eta: 0:15:50 lr: 0.000041 grad: 0.1014 (0.1268) loss: 0.8227 (0.8236) time: 0.1464 data: 0.0572 max mem: 9390 +Train: [63] [ 400/6250] eta: 0:15:00 lr: 0.000041 grad: 0.1027 (0.1225) loss: 0.8139 (0.8217) time: 0.1357 data: 0.0489 max mem: 9390 +Train: [63] [ 500/6250] eta: 0:14:24 lr: 0.000041 grad: 0.0982 (0.1190) loss: 0.8220 (0.8213) time: 0.1427 data: 0.0574 max mem: 9390 +Train: [63] [ 600/6250] eta: 0:13:43 lr: 0.000041 grad: 0.1023 (0.1167) loss: 0.8175 (0.8212) time: 0.1194 data: 0.0360 max mem: 9390 +Train: [63] [ 700/6250] eta: 0:13:15 lr: 0.000041 grad: 0.0941 (0.1146) loss: 0.8256 (0.8210) time: 0.1053 data: 0.0239 max mem: 9390 +Train: [63] [ 800/6250] eta: 0:12:51 lr: 0.000041 grad: 0.1026 (0.1132) loss: 0.8135 (0.8208) time: 0.1186 data: 0.0371 max mem: 9390 +Train: [63] [ 900/6250] eta: 0:12:30 lr: 0.000041 grad: 0.0988 (0.1120) loss: 0.8217 (0.8207) time: 0.1012 data: 0.0088 max mem: 9390 +Train: [63] [1000/6250] eta: 0:12:07 lr: 0.000041 grad: 0.1005 (0.1113) loss: 0.8173 (0.8208) time: 0.1272 data: 0.0484 max mem: 9390 +Train: [63] [1100/6250] eta: 0:11:53 lr: 0.000041 grad: 0.0991 (0.1105) loss: 0.8232 (0.8206) time: 0.1331 data: 0.0430 max mem: 9390 +Train: [63] [1200/6250] eta: 0:11:37 lr: 0.000041 grad: 0.1029 (0.1101) loss: 0.8169 (0.8205) time: 0.1314 data: 0.0457 max mem: 9390 +Train: [63] [1300/6250] eta: 0:11:24 lr: 0.000041 grad: 0.0973 (0.1095) loss: 0.8217 (0.8204) time: 0.1457 data: 0.0664 max mem: 9390 +Train: [63] [1400/6250] eta: 0:11:06 lr: 0.000041 grad: 0.1012 (0.1089) loss: 0.8229 (0.8204) time: 0.1209 data: 0.0476 max mem: 9390 +Train: [63] [1500/6250] eta: 0:10:50 lr: 0.000041 grad: 0.1007 (0.1086) loss: 0.8181 (0.8201) time: 0.1205 data: 0.0435 max mem: 9390 +Train: [63] [1600/6250] eta: 0:10:36 lr: 0.000041 grad: 0.1050 (0.1086) loss: 0.8130 (0.8198) time: 0.1434 data: 0.0531 max mem: 9390 +Train: [63] [1700/6250] eta: 0:10:22 lr: 0.000041 grad: 0.1053 (0.1084) loss: 0.8184 (0.8196) time: 0.1335 data: 0.0576 max mem: 9390 +Train: [63] [1800/6250] eta: 0:10:06 lr: 0.000041 grad: 0.1080 (0.1084) loss: 0.8191 (0.8194) time: 0.1327 data: 0.0562 max mem: 9390 +Train: [63] [1900/6250] eta: 0:09:52 lr: 0.000041 grad: 0.1041 (0.1082) loss: 0.8211 (0.8192) time: 0.1455 data: 0.0469 max mem: 9390 +Train: [63] [2000/6250] eta: 0:09:37 lr: 0.000041 grad: 0.1049 (0.1081) loss: 0.8144 (0.8190) time: 0.1008 data: 0.0208 max mem: 9390 +Train: [63] [2100/6250] eta: 0:09:23 lr: 0.000041 grad: 0.1023 (0.1081) loss: 0.8183 (0.8188) time: 0.1396 data: 0.0567 max mem: 9390 +Train: [63] [2200/6250] eta: 0:09:09 lr: 0.000041 grad: 0.1050 (0.1081) loss: 0.8179 (0.8186) time: 0.1494 data: 0.0655 max mem: 9390 +Train: [63] [2300/6250] eta: 0:08:56 lr: 0.000041 grad: 0.1025 (0.1079) loss: 0.8159 (0.8184) time: 0.1610 data: 0.0789 max mem: 9390 +Train: [63] [2400/6250] eta: 0:08:41 lr: 0.000040 grad: 0.1032 (0.1078) loss: 0.8096 (0.8182) time: 0.1277 data: 0.0490 max mem: 9390 +Train: [63] [2500/6250] eta: 0:08:27 lr: 0.000040 grad: 0.0962 (0.1076) loss: 0.8179 (0.8181) time: 0.1271 data: 0.0469 max mem: 9390 +Train: [63] [2600/6250] eta: 0:08:14 lr: 0.000040 grad: 0.1030 (0.1075) loss: 0.8168 (0.8180) time: 0.1370 data: 0.0596 max mem: 9390 +Train: [63] [2700/6250] eta: 0:08:00 lr: 0.000040 grad: 0.1013 (0.1074) loss: 0.8157 (0.8179) time: 0.1297 data: 0.0533 max mem: 9390 +Train: [63] [2800/6250] eta: 0:07:46 lr: 0.000040 grad: 0.0976 (0.1074) loss: 0.8134 (0.8178) time: 0.1240 data: 0.0434 max mem: 9390 +Train: [63] [2900/6250] eta: 0:07:37 lr: 0.000040 grad: 0.1064 (0.1075) loss: 0.8152 (0.8177) time: 0.1494 data: 0.0687 max mem: 9390 +Train: [63] [3000/6250] eta: 0:07:24 lr: 0.000040 grad: 0.0987 (0.1075) loss: 0.8124 (0.8176) time: 0.1151 data: 0.0336 max mem: 9390 +Train: [63] [3100/6250] eta: 0:07:12 lr: 0.000040 grad: 0.1098 (0.1075) loss: 0.8169 (0.8174) time: 0.1450 data: 0.0704 max mem: 9390 +Train: [63] [3200/6250] eta: 0:06:59 lr: 0.000040 grad: 0.1088 (0.1076) loss: 0.8140 (0.8173) time: 0.1379 data: 0.0572 max mem: 9390 +Train: [63] [3300/6250] eta: 0:06:46 lr: 0.000040 grad: 0.1086 (0.1078) loss: 0.8149 (0.8173) time: 0.1270 data: 0.0493 max mem: 9390 +Train: [63] [3400/6250] eta: 0:06:32 lr: 0.000040 grad: 0.0955 (0.1078) loss: 0.8261 (0.8172) time: 0.1309 data: 0.0491 max mem: 9390 +Train: [63] [3500/6250] eta: 0:06:18 lr: 0.000040 grad: 0.1039 (0.1078) loss: 0.8140 (0.8171) time: 0.1277 data: 0.0507 max mem: 9390 +Train: [63] [3600/6250] eta: 0:06:03 lr: 0.000040 grad: 0.1040 (0.1078) loss: 0.8138 (0.8171) time: 0.1328 data: 0.0537 max mem: 9390 +Train: [63] [3700/6250] eta: 0:05:48 lr: 0.000040 grad: 0.1018 (0.1078) loss: 0.8142 (0.8170) time: 0.1043 data: 0.0259 max mem: 9390 +Train: [63] [3800/6250] eta: 0:05:33 lr: 0.000040 grad: 0.0996 (0.1077) loss: 0.8227 (0.8169) time: 0.1110 data: 0.0254 max mem: 9390 +Train: [63] [3900/6250] eta: 0:05:19 lr: 0.000040 grad: 0.0981 (0.1077) loss: 0.8137 (0.8169) time: 0.1282 data: 0.0467 max mem: 9390 +Train: [63] [4000/6250] eta: 0:05:05 lr: 0.000040 grad: 0.1030 (0.1077) loss: 0.8212 (0.8169) time: 0.1446 data: 0.0667 max mem: 9390 +Train: [63] [4100/6250] eta: 0:04:50 lr: 0.000040 grad: 0.1054 (0.1077) loss: 0.8120 (0.8168) time: 0.1335 data: 0.0576 max mem: 9390 +Train: [63] [4200/6250] eta: 0:04:36 lr: 0.000040 grad: 0.1013 (0.1076) loss: 0.8175 (0.8168) time: 0.1230 data: 0.0436 max mem: 9390 +Train: [63] [4300/6250] eta: 0:04:22 lr: 0.000040 grad: 0.1019 (0.1076) loss: 0.8165 (0.8168) time: 0.1239 data: 0.0477 max mem: 9390 +Train: [63] [4400/6250] eta: 0:04:08 lr: 0.000040 grad: 0.1026 (0.1075) loss: 0.8176 (0.8168) time: 0.1502 data: 0.0708 max mem: 9390 +Train: [63] [4500/6250] eta: 0:03:54 lr: 0.000040 grad: 0.1052 (0.1075) loss: 0.8178 (0.8168) time: 0.1185 data: 0.0392 max mem: 9390 +Train: [63] [4600/6250] eta: 0:03:40 lr: 0.000040 grad: 0.1033 (0.1074) loss: 0.8223 (0.8168) time: 0.1218 data: 0.0393 max mem: 9390 +Train: [63] [4700/6250] eta: 0:03:26 lr: 0.000040 grad: 0.1112 (0.1075) loss: 0.8107 (0.8168) time: 0.1360 data: 0.0570 max mem: 9390 +Train: [63] [4800/6250] eta: 0:03:13 lr: 0.000040 grad: 0.1034 (0.1074) loss: 0.8144 (0.8167) time: 0.1361 data: 0.0571 max mem: 9390 +Train: [63] [4900/6250] eta: 0:02:59 lr: 0.000040 grad: 0.1029 (0.1075) loss: 0.8082 (0.8166) time: 0.1228 data: 0.0484 max mem: 9390 +Train: [63] [5000/6250] eta: 0:02:46 lr: 0.000040 grad: 0.1016 (0.1076) loss: 0.8144 (0.8165) time: 0.1154 data: 0.0365 max mem: 9390 +Train: [63] [5100/6250] eta: 0:02:32 lr: 0.000040 grad: 0.0996 (0.1076) loss: 0.8200 (0.8165) time: 0.1223 data: 0.0415 max mem: 9390 +Train: [63] [5200/6250] eta: 0:02:19 lr: 0.000040 grad: 0.1027 (0.1076) loss: 0.8150 (0.8165) time: 0.1283 data: 0.0457 max mem: 9390 +Train: [63] [5300/6250] eta: 0:02:06 lr: 0.000040 grad: 0.1035 (0.1076) loss: 0.8142 (0.8164) time: 0.1390 data: 0.0644 max mem: 9390 +Train: [63] [5400/6250] eta: 0:01:52 lr: 0.000040 grad: 0.1055 (0.1077) loss: 0.8137 (0.8163) time: 0.1398 data: 0.0625 max mem: 9390 +Train: [63] [5500/6250] eta: 0:01:39 lr: 0.000040 grad: 0.1071 (0.1077) loss: 0.8137 (0.8163) time: 0.1718 data: 0.0951 max mem: 9390 +Train: [63] [5600/6250] eta: 0:01:26 lr: 0.000039 grad: 0.1038 (0.1077) loss: 0.8122 (0.8163) time: 0.1458 data: 0.0595 max mem: 9390 +Train: [63] [5700/6250] eta: 0:01:13 lr: 0.000039 grad: 0.1041 (0.1076) loss: 0.8127 (0.8162) time: 0.1512 data: 0.0767 max mem: 9390 +Train: [63] [5800/6250] eta: 0:01:00 lr: 0.000039 grad: 0.1019 (0.1076) loss: 0.8142 (0.8162) time: 0.1462 data: 0.0610 max mem: 9390 +Train: [63] [5900/6250] eta: 0:00:46 lr: 0.000039 grad: 0.0975 (0.1076) loss: 0.8188 (0.8162) time: 0.1345 data: 0.0592 max mem: 9390 +Train: [63] [6000/6250] eta: 0:00:33 lr: 0.000039 grad: 0.1043 (0.1076) loss: 0.8157 (0.8162) time: 0.1314 data: 0.0570 max mem: 9390 +Train: [63] [6100/6250] eta: 0:00:20 lr: 0.000039 grad: 0.1077 (0.1075) loss: 0.8150 (0.8162) time: 0.1349 data: 0.0604 max mem: 9390 +Train: [63] [6200/6250] eta: 0:00:06 lr: 0.000039 grad: 0.1004 (0.1075) loss: 0.8179 (0.8163) time: 0.1173 data: 0.0440 max mem: 9390 +Train: [63] [6249/6250] eta: 0:00:00 lr: 0.000039 grad: 0.1010 (0.1075) loss: 0.8185 (0.8162) time: 0.1395 data: 0.0616 max mem: 9390 +Train: [63] Total time: 0:13:58 (0.1342 s / it) +Averaged stats: lr: 0.000039 grad: 0.1010 (0.1075) loss: 0.8185 (0.8162) +Eval (hcp-train-subset): [63] [ 0/62] eta: 0:04:08 loss: 0.8475 (0.8475) time: 4.0136 data: 3.9753 max mem: 9390 +Eval (hcp-train-subset): [63] [61/62] eta: 0:00:00 loss: 0.8331 (0.8330) time: 0.1050 data: 0.0786 max mem: 9390 +Eval (hcp-train-subset): [63] Total time: 0:00:11 (0.1792 s / it) +Averaged stats (hcp-train-subset): loss: 0.8331 (0.8330) +Eval (hcp-val): [63] [ 0/62] eta: 0:03:52 loss: 0.8322 (0.8322) time: 3.7483 data: 3.6919 max mem: 9390 +Eval (hcp-val): [63] [61/62] eta: 0:00:00 loss: 0.8320 (0.8340) time: 0.1431 data: 0.1160 max mem: 9390 +Eval (hcp-val): [63] Total time: 0:00:12 (0.2097 s / it) +Averaged stats (hcp-val): loss: 0.8320 (0.8340) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +Train: [64] [ 0/6250] eta: 10:44:03 lr: 0.000039 grad: 0.0685 (0.0685) loss: 0.8328 (0.8328) time: 6.1830 data: 6.0664 max mem: 9390 +Train: [64] [ 100/6250] eta: 0:20:21 lr: 0.000039 grad: 0.1107 (0.1128) loss: 0.8276 (0.8343) time: 0.1475 data: 0.0537 max mem: 9390 +Train: [64] [ 200/6250] eta: 0:17:58 lr: 0.000039 grad: 0.1019 (0.1105) loss: 0.8280 (0.8285) time: 0.1681 data: 0.0857 max mem: 9390 +Train: [64] [ 300/6250] eta: 0:16:27 lr: 0.000039 grad: 0.0933 (0.1102) loss: 0.8271 (0.8242) time: 0.1303 data: 0.0397 max mem: 9390 +Train: [64] [ 400/6250] eta: 0:15:25 lr: 0.000039 grad: 0.0983 (0.1093) loss: 0.8160 (0.8223) time: 0.1277 data: 0.0404 max mem: 9390 +Train: [64] [ 500/6250] eta: 0:14:44 lr: 0.000039 grad: 0.0934 (0.1084) loss: 0.8211 (0.8215) time: 0.1276 data: 0.0414 max mem: 9390 +Train: [64] [ 600/6250] eta: 0:14:18 lr: 0.000039 grad: 0.0947 (0.1078) loss: 0.8227 (0.8212) time: 0.1392 data: 0.0542 max mem: 9390 +Train: [64] [ 700/6250] eta: 0:14:04 lr: 0.000039 grad: 0.1014 (0.1071) loss: 0.8126 (0.8205) time: 0.2077 data: 0.1269 max mem: 9390 +Train: [64] [ 800/6250] eta: 0:13:41 lr: 0.000039 grad: 0.1011 (0.1072) loss: 0.8078 (0.8198) time: 0.1417 data: 0.0640 max mem: 9390 +Train: [64] [ 900/6250] eta: 0:13:20 lr: 0.000039 grad: 0.0980 (0.1067) loss: 0.8163 (0.8196) time: 0.1537 data: 0.0672 max mem: 9390 +Train: [64] [1000/6250] eta: 0:12:58 lr: 0.000039 grad: 0.1023 (0.1065) loss: 0.8144 (0.8193) time: 0.1208 data: 0.0411 max mem: 9390 +Train: [64] [1100/6250] eta: 0:12:43 lr: 0.000039 grad: 0.1073 (0.1062) loss: 0.8086 (0.8188) time: 0.1354 data: 0.0566 max mem: 9390 +Train: [64] [1200/6250] eta: 0:12:28 lr: 0.000039 grad: 0.1030 (0.1059) loss: 0.8123 (0.8185) time: 0.1607 data: 0.0785 max mem: 9390 +Train: [64] [1300/6250] eta: 0:12:20 lr: 0.000039 grad: 0.1026 (0.1059) loss: 0.8145 (0.8181) time: 0.0833 data: 0.0002 max mem: 9390 +Train: [64] [1400/6250] eta: 0:11:56 lr: 0.000039 grad: 0.1076 (0.1059) loss: 0.8127 (0.8177) time: 0.1341 data: 0.0501 max mem: 9390 +Train: [64] [1500/6250] eta: 0:11:41 lr: 0.000039 grad: 0.1041 (0.1061) loss: 0.8102 (0.8173) time: 0.1182 data: 0.0375 max mem: 9390 +Train: [64] [1600/6250] eta: 0:11:25 lr: 0.000039 grad: 0.1029 (0.1063) loss: 0.8159 (0.8169) time: 0.1456 data: 0.0549 max mem: 9390 +Train: [64] [1700/6250] eta: 0:11:13 lr: 0.000039 grad: 0.1048 (0.1065) loss: 0.8115 (0.8164) time: 0.1542 data: 0.0625 max mem: 9390 +Train: [64] [1800/6250] eta: 0:10:58 lr: 0.000039 grad: 0.1042 (0.1068) loss: 0.8135 (0.8161) time: 0.1095 data: 0.0240 max mem: 9390 +Train: [64] [1900/6250] eta: 0:10:38 lr: 0.000039 grad: 0.1027 (0.1067) loss: 0.8141 (0.8159) time: 0.1280 data: 0.0513 max mem: 9390 +Train: [64] [2000/6250] eta: 0:10:21 lr: 0.000039 grad: 0.1062 (0.1068) loss: 0.8153 (0.8157) time: 0.1243 data: 0.0447 max mem: 9390 +Train: [64] [2100/6250] eta: 0:10:06 lr: 0.000039 grad: 0.1062 (0.1070) loss: 0.8102 (0.8156) time: 0.1551 data: 0.0720 max mem: 9390 +Train: [64] [2200/6250] eta: 0:09:53 lr: 0.000039 grad: 0.1037 (0.1071) loss: 0.8093 (0.8155) time: 0.1174 data: 0.0317 max mem: 9390 +Train: [64] [2300/6250] eta: 0:09:35 lr: 0.000039 grad: 0.1119 (0.1072) loss: 0.8097 (0.8153) time: 0.1285 data: 0.0443 max mem: 9390 +Train: [64] [2400/6250] eta: 0:09:19 lr: 0.000039 grad: 0.1040 (0.1073) loss: 0.8080 (0.8152) time: 0.1289 data: 0.0494 max mem: 9390 +Train: [64] [2500/6250] eta: 0:09:02 lr: 0.000039 grad: 0.0982 (0.1073) loss: 0.8168 (0.8152) time: 0.1287 data: 0.0498 max mem: 9390 +Train: [64] [2600/6250] eta: 0:08:46 lr: 0.000039 grad: 0.1031 (0.1075) loss: 0.8129 (0.8151) time: 0.1304 data: 0.0476 max mem: 9390 +Train: [64] [2700/6250] eta: 0:08:30 lr: 0.000038 grad: 0.1098 (0.1075) loss: 0.8103 (0.8151) time: 0.1277 data: 0.0485 max mem: 9390 +Train: [64] [2800/6250] eta: 0:08:15 lr: 0.000038 grad: 0.1006 (0.1076) loss: 0.8109 (0.8151) time: 0.1266 data: 0.0468 max mem: 9390 +Train: [64] [2900/6250] eta: 0:08:00 lr: 0.000038 grad: 0.1067 (0.1076) loss: 0.8157 (0.8151) time: 0.1454 data: 0.0598 max mem: 9390 +Train: [64] [3000/6250] eta: 0:07:48 lr: 0.000038 grad: 0.1021 (0.1078) loss: 0.8138 (0.8151) time: 0.1528 data: 0.0781 max mem: 9390 +Train: [64] [3100/6250] eta: 0:07:33 lr: 0.000038 grad: 0.1023 (0.1079) loss: 0.8166 (0.8151) time: 0.1485 data: 0.0718 max mem: 9390 +Train: [64] [3200/6250] eta: 0:07:20 lr: 0.000038 grad: 0.1190 (0.1081) loss: 0.8163 (0.8151) time: 0.1418 data: 0.0559 max mem: 9390 +Train: [64] [3300/6250] eta: 0:07:05 lr: 0.000038 grad: 0.1064 (0.1081) loss: 0.8147 (0.8149) time: 0.1582 data: 0.0736 max mem: 9390 +Train: [64] [3400/6250] eta: 0:06:51 lr: 0.000038 grad: 0.1153 (0.1083) loss: 0.8125 (0.8147) time: 0.1265 data: 0.0464 max mem: 9390 +Train: [64] [3500/6250] eta: 0:06:36 lr: 0.000038 grad: 0.1073 (0.1084) loss: 0.8145 (0.8146) time: 0.1317 data: 0.0517 max mem: 9390 +Train: [64] [3600/6250] eta: 0:06:20 lr: 0.000038 grad: 0.1109 (0.1086) loss: 0.8109 (0.8144) time: 0.1322 data: 0.0555 max mem: 9390 +Train: [64] [3700/6250] eta: 0:06:04 lr: 0.000038 grad: 0.1052 (0.1087) loss: 0.8115 (0.8143) time: 0.1264 data: 0.0460 max mem: 9390 +Train: [64] [3800/6250] eta: 0:05:49 lr: 0.000038 grad: 0.1119 (0.1088) loss: 0.8101 (0.8142) time: 0.1242 data: 0.0401 max mem: 9390 +Train: [64] [3900/6250] eta: 0:05:33 lr: 0.000038 grad: 0.1053 (0.1088) loss: 0.8137 (0.8142) time: 0.1020 data: 0.0183 max mem: 9390 +Train: [64] [4000/6250] eta: 0:05:18 lr: 0.000038 grad: 0.1111 (0.1088) loss: 0.8097 (0.8142) time: 0.1204 data: 0.0315 max mem: 9390 +Train: [64] [4100/6250] eta: 0:05:03 lr: 0.000038 grad: 0.1055 (0.1089) loss: 0.8153 (0.8141) time: 0.1114 data: 0.0142 max mem: 9390 +Train: [64] [4200/6250] eta: 0:04:48 lr: 0.000038 grad: 0.1023 (0.1089) loss: 0.8126 (0.8140) time: 0.1167 data: 0.0368 max mem: 9390 +Train: [64] [4300/6250] eta: 0:04:34 lr: 0.000038 grad: 0.1087 (0.1090) loss: 0.8172 (0.8140) time: 0.1196 data: 0.0449 max mem: 9390 +Train: [64] [4400/6250] eta: 0:04:19 lr: 0.000038 grad: 0.1062 (0.1091) loss: 0.8205 (0.8139) time: 0.1261 data: 0.0510 max mem: 9390 +Train: [64] [4500/6250] eta: 0:04:05 lr: 0.000038 grad: 0.1101 (0.1092) loss: 0.8138 (0.8139) time: 0.1323 data: 0.0581 max mem: 9390 +Train: [64] [4600/6250] eta: 0:03:50 lr: 0.000038 grad: 0.1077 (0.1093) loss: 0.8086 (0.8138) time: 0.1203 data: 0.0435 max mem: 9390 +Train: [64] [4700/6250] eta: 0:03:36 lr: 0.000038 grad: 0.1088 (0.1094) loss: 0.8192 (0.8137) time: 0.1224 data: 0.0473 max mem: 9390 +Train: [64] [4800/6250] eta: 0:03:21 lr: 0.000038 grad: 0.1114 (0.1095) loss: 0.8168 (0.8136) time: 0.1071 data: 0.0328 max mem: 9390 +Train: [64] [4900/6250] eta: 0:03:07 lr: 0.000038 grad: 0.1087 (0.1096) loss: 0.8061 (0.8136) time: 0.1276 data: 0.0518 max mem: 9390 +Train: [64] [5000/6250] eta: 0:02:53 lr: 0.000038 grad: 0.1092 (0.1096) loss: 0.8094 (0.8135) time: 0.1211 data: 0.0428 max mem: 9390 +Train: [64] [5100/6250] eta: 0:02:39 lr: 0.000038 grad: 0.1083 (0.1096) loss: 0.8095 (0.8134) time: 0.1480 data: 0.0640 max mem: 9390 +Train: [64] [5200/6250] eta: 0:02:25 lr: 0.000038 grad: 0.1059 (0.1097) loss: 0.8140 (0.8134) time: 0.1096 data: 0.0373 max mem: 9390 +Train: [64] [5300/6250] eta: 0:02:11 lr: 0.000038 grad: 0.1091 (0.1098) loss: 0.8159 (0.8134) time: 0.1515 data: 0.0702 max mem: 9390 +Train: [64] [5400/6250] eta: 0:01:57 lr: 0.000038 grad: 0.1066 (0.1097) loss: 0.8186 (0.8134) time: 0.1433 data: 0.0671 max mem: 9390 +Train: [64] [5500/6250] eta: 0:01:44 lr: 0.000038 grad: 0.1008 (0.1097) loss: 0.8170 (0.8134) time: 0.1269 data: 0.0456 max mem: 9390 +Train: [64] [5600/6250] eta: 0:01:30 lr: 0.000038 grad: 0.1021 (0.1096) loss: 0.8157 (0.8134) time: 0.1288 data: 0.0451 max mem: 9390 +Train: [64] [5700/6250] eta: 0:01:16 lr: 0.000038 grad: 0.1092 (0.1095) loss: 0.8139 (0.8135) time: 0.1510 data: 0.0752 max mem: 9390 +Train: [64] [5800/6250] eta: 0:01:02 lr: 0.000038 grad: 0.0988 (0.1095) loss: 0.8181 (0.8135) time: 0.1572 data: 0.0796 max mem: 9390 +Train: [64] [5900/6250] eta: 0:00:48 lr: 0.000037 grad: 0.0980 (0.1094) loss: 0.8188 (0.8136) time: 0.1609 data: 0.0821 max mem: 9390 +Train: [64] [6000/6250] eta: 0:00:34 lr: 0.000037 grad: 0.1063 (0.1094) loss: 0.8139 (0.8137) time: 0.1495 data: 0.0638 max mem: 9390 +Train: [64] [6100/6250] eta: 0:00:20 lr: 0.000037 grad: 0.1047 (0.1093) loss: 0.8195 (0.8137) time: 0.1610 data: 0.0754 max mem: 9390 +Train: [64] [6200/6250] eta: 0:00:06 lr: 0.000037 grad: 0.1101 (0.1093) loss: 0.8130 (0.8138) time: 0.1225 data: 0.0452 max mem: 9390 +Train: [64] [6249/6250] eta: 0:00:00 lr: 0.000037 grad: 0.1045 (0.1093) loss: 0.8249 (0.8138) time: 0.1414 data: 0.0651 max mem: 9390 +Train: [64] Total time: 0:14:32 (0.1396 s / it) +Averaged stats: lr: 0.000037 grad: 0.1045 (0.1093) loss: 0.8249 (0.8138) +Eval (hcp-train-subset): [64] [ 0/62] eta: 0:03:20 loss: 0.8427 (0.8427) time: 3.2330 data: 3.1485 max mem: 9390 +Eval (hcp-train-subset): [64] [61/62] eta: 0:00:00 loss: 0.8317 (0.8320) time: 0.1055 data: 0.0809 max mem: 9390 +Eval (hcp-train-subset): [64] Total time: 0:00:11 (0.1837 s / it) +Averaged stats (hcp-train-subset): loss: 0.8317 (0.8320) +Making plots (hcp-train-subset): example=28 +Eval (hcp-val): [64] [ 0/62] eta: 0:04:33 loss: 0.8288 (0.8288) time: 4.4131 data: 4.3805 max mem: 9390 +Eval (hcp-val): [64] [61/62] eta: 0:00:00 loss: 0.8316 (0.8327) time: 0.1135 data: 0.0866 max mem: 9390 +Eval (hcp-val): [64] Total time: 0:00:12 (0.2000 s / it) +Averaged stats (hcp-val): loss: 0.8316 (0.8327) +Making plots (hcp-val): example=50 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +Train: [65] [ 0/6250] eta: 10:50:54 lr: 0.000037 grad: 0.0711 (0.0711) loss: 0.8638 (0.8638) time: 6.2488 data: 6.1574 max mem: 9390 +Train: [65] [ 100/6250] eta: 0:20:00 lr: 0.000037 grad: 0.1121 (0.1252) loss: 0.8261 (0.8333) time: 0.1526 data: 0.0658 max mem: 9390 +Train: [65] [ 200/6250] eta: 0:17:52 lr: 0.000037 grad: 0.1132 (0.1224) loss: 0.8160 (0.8253) time: 0.1587 data: 0.0703 max mem: 9390 +Train: [65] [ 300/6250] eta: 0:16:31 lr: 0.000037 grad: 0.1107 (0.1187) loss: 0.8115 (0.8226) time: 0.1351 data: 0.0494 max mem: 9390 +Train: [65] [ 400/6250] eta: 0:15:41 lr: 0.000037 grad: 0.1016 (0.1159) loss: 0.8158 (0.8214) time: 0.1411 data: 0.0586 max mem: 9390 +Train: [65] [ 500/6250] eta: 0:14:59 lr: 0.000037 grad: 0.1189 (0.1153) loss: 0.8069 (0.8204) time: 0.1595 data: 0.0713 max mem: 9390 +Train: [65] [ 600/6250] eta: 0:14:15 lr: 0.000037 grad: 0.1070 (0.1146) loss: 0.8086 (0.8198) time: 0.1349 data: 0.0551 max mem: 9390 +Train: [65] [ 700/6250] eta: 0:13:44 lr: 0.000037 grad: 0.1018 (0.1138) loss: 0.8154 (0.8193) time: 0.1302 data: 0.0529 max mem: 9390 +Train: [65] [ 800/6250] eta: 0:13:18 lr: 0.000037 grad: 0.1044 (0.1130) loss: 0.8177 (0.8191) time: 0.1291 data: 0.0461 max mem: 9390 +Train: [65] [ 900/6250] eta: 0:12:52 lr: 0.000037 grad: 0.1033 (0.1125) loss: 0.8222 (0.8189) time: 0.1309 data: 0.0479 max mem: 9390 +Train: [65] [1000/6250] eta: 0:12:30 lr: 0.000037 grad: 0.1043 (0.1119) loss: 0.8170 (0.8186) time: 0.1301 data: 0.0509 max mem: 9390 +Train: [65] [1100/6250] eta: 0:12:05 lr: 0.000037 grad: 0.0942 (0.1112) loss: 0.8178 (0.8185) time: 0.1138 data: 0.0332 max mem: 9390 +Train: [65] [1200/6250] eta: 0:11:43 lr: 0.000037 grad: 0.0963 (0.1107) loss: 0.8194 (0.8183) time: 0.1127 data: 0.0351 max mem: 9390 +Train: [65] [1300/6250] eta: 0:11:24 lr: 0.000037 grad: 0.1040 (0.1104) loss: 0.8170 (0.8181) time: 0.1330 data: 0.0488 max mem: 9390 +Train: [65] [1400/6250] eta: 0:11:07 lr: 0.000037 grad: 0.0999 (0.1100) loss: 0.8179 (0.8179) time: 0.1367 data: 0.0551 max mem: 9390 +Train: [65] [1500/6250] eta: 0:10:52 lr: 0.000037 grad: 0.0972 (0.1097) loss: 0.8191 (0.8178) time: 0.1131 data: 0.0336 max mem: 9390 +Train: [65] [1600/6250] eta: 0:10:37 lr: 0.000037 grad: 0.0970 (0.1093) loss: 0.8183 (0.8179) time: 0.1294 data: 0.0417 max mem: 9390 +Train: [65] [1700/6250] eta: 0:10:22 lr: 0.000037 grad: 0.0989 (0.1091) loss: 0.8150 (0.8177) time: 0.1317 data: 0.0532 max mem: 9390 +Train: [65] [1800/6250] eta: 0:10:08 lr: 0.000037 grad: 0.1046 (0.1089) loss: 0.8153 (0.8178) time: 0.1462 data: 0.0684 max mem: 9390 +Train: [65] [1900/6250] eta: 0:09:54 lr: 0.000037 grad: 0.1086 (0.1088) loss: 0.8127 (0.8177) time: 0.1270 data: 0.0543 max mem: 9390 +Train: [65] [2000/6250] eta: 0:09:39 lr: 0.000037 grad: 0.1146 (0.1087) loss: 0.8052 (0.8176) time: 0.1243 data: 0.0440 max mem: 9390 +Train: [65] [2100/6250] eta: 0:09:26 lr: 0.000037 grad: 0.1110 (0.1088) loss: 0.8129 (0.8174) time: 0.1587 data: 0.0735 max mem: 9390 +Train: [65] [2200/6250] eta: 0:09:13 lr: 0.000037 grad: 0.1107 (0.1090) loss: 0.8115 (0.8173) time: 0.1338 data: 0.0485 max mem: 9390 +Train: [65] [2300/6250] eta: 0:09:01 lr: 0.000037 grad: 0.1039 (0.1089) loss: 0.8170 (0.8171) time: 0.1622 data: 0.0920 max mem: 9390 +Train: [65] [2400/6250] eta: 0:08:46 lr: 0.000037 grad: 0.1127 (0.1090) loss: 0.8044 (0.8170) time: 0.1154 data: 0.0254 max mem: 9390 +Train: [65] [2500/6250] eta: 0:08:32 lr: 0.000037 grad: 0.1076 (0.1091) loss: 0.8101 (0.8167) time: 0.1385 data: 0.0544 max mem: 9390 +Train: [65] [2600/6250] eta: 0:08:19 lr: 0.000037 grad: 0.1096 (0.1091) loss: 0.8124 (0.8165) time: 0.1023 data: 0.0247 max mem: 9390 +Train: [65] [2700/6250] eta: 0:08:05 lr: 0.000037 grad: 0.1132 (0.1093) loss: 0.8174 (0.8163) time: 0.1559 data: 0.0603 max mem: 9390 +Train: [65] [2800/6250] eta: 0:07:53 lr: 0.000037 grad: 0.1099 (0.1094) loss: 0.8137 (0.8161) time: 0.1226 data: 0.0408 max mem: 9390 +Train: [65] [2900/6250] eta: 0:07:39 lr: 0.000037 grad: 0.1115 (0.1094) loss: 0.8058 (0.8158) time: 0.1472 data: 0.0609 max mem: 9390 +Train: [65] [3000/6250] eta: 0:07:28 lr: 0.000036 grad: 0.1054 (0.1096) loss: 0.8171 (0.8156) time: 0.2073 data: 0.1381 max mem: 9390 +Train: [65] [3100/6250] eta: 0:07:13 lr: 0.000036 grad: 0.1092 (0.1097) loss: 0.8119 (0.8154) time: 0.1255 data: 0.0498 max mem: 9390 +Train: [65] [3200/6250] eta: 0:07:01 lr: 0.000036 grad: 0.1048 (0.1097) loss: 0.8125 (0.8153) time: 0.1465 data: 0.0694 max mem: 9390 +Train: [65] [3300/6250] eta: 0:06:48 lr: 0.000036 grad: 0.1103 (0.1097) loss: 0.8097 (0.8152) time: 0.1691 data: 0.0899 max mem: 9390 +Train: [65] [3400/6250] eta: 0:06:35 lr: 0.000036 grad: 0.1112 (0.1098) loss: 0.8107 (0.8151) time: 0.1357 data: 0.0515 max mem: 9390 +Train: [65] [3500/6250] eta: 0:06:22 lr: 0.000036 grad: 0.1117 (0.1099) loss: 0.8109 (0.8151) time: 0.1523 data: 0.0734 max mem: 9390 +Train: [65] [3600/6250] eta: 0:06:08 lr: 0.000036 grad: 0.1100 (0.1099) loss: 0.8124 (0.8150) time: 0.1285 data: 0.0531 max mem: 9390 +Train: [65] [3700/6250] eta: 0:05:54 lr: 0.000036 grad: 0.1070 (0.1099) loss: 0.8204 (0.8150) time: 0.1324 data: 0.0527 max mem: 9390 +Train: [65] [3800/6250] eta: 0:05:39 lr: 0.000036 grad: 0.1094 (0.1099) loss: 0.8103 (0.8149) time: 0.1425 data: 0.0641 max mem: 9390 +Train: [65] [3900/6250] eta: 0:05:24 lr: 0.000036 grad: 0.1088 (0.1099) loss: 0.8118 (0.8149) time: 0.1227 data: 0.0392 max mem: 9390 +Train: [65] [4000/6250] eta: 0:05:09 lr: 0.000036 grad: 0.1130 (0.1100) loss: 0.8099 (0.8149) time: 0.1286 data: 0.0455 max mem: 9390 +Train: [65] [4100/6250] eta: 0:04:55 lr: 0.000036 grad: 0.1094 (0.1100) loss: 0.8096 (0.8148) time: 0.1264 data: 0.0431 max mem: 9390 +Train: [65] [4200/6250] eta: 0:04:40 lr: 0.000036 grad: 0.1139 (0.1101) loss: 0.8065 (0.8147) time: 0.1054 data: 0.0278 max mem: 9390 +Train: [65] [4300/6250] eta: 0:04:26 lr: 0.000036 grad: 0.1066 (0.1102) loss: 0.8126 (0.8145) time: 0.1125 data: 0.0362 max mem: 9390 +Train: [65] [4400/6250] eta: 0:04:11 lr: 0.000036 grad: 0.1096 (0.1103) loss: 0.8127 (0.8144) time: 0.1207 data: 0.0436 max mem: 9390 +Train: [65] [4500/6250] eta: 0:03:57 lr: 0.000036 grad: 0.1093 (0.1104) loss: 0.8057 (0.8143) time: 0.1146 data: 0.0312 max mem: 9390 +Train: [65] [4600/6250] eta: 0:03:43 lr: 0.000036 grad: 0.1120 (0.1105) loss: 0.8068 (0.8142) time: 0.1316 data: 0.0576 max mem: 9390 +Train: [65] [4700/6250] eta: 0:03:29 lr: 0.000036 grad: 0.1047 (0.1106) loss: 0.8171 (0.8141) time: 0.1130 data: 0.0374 max mem: 9390 +Train: [65] [4800/6250] eta: 0:03:15 lr: 0.000036 grad: 0.1035 (0.1107) loss: 0.8192 (0.8140) time: 0.1053 data: 0.0221 max mem: 9390 +Train: [65] [4900/6250] eta: 0:03:01 lr: 0.000036 grad: 0.1129 (0.1108) loss: 0.8093 (0.8139) time: 0.1242 data: 0.0442 max mem: 9390 +Train: [65] [5000/6250] eta: 0:02:47 lr: 0.000036 grad: 0.1104 (0.1108) loss: 0.8063 (0.8137) time: 0.1259 data: 0.0463 max mem: 9390 +Train: [65] [5100/6250] eta: 0:02:33 lr: 0.000036 grad: 0.1066 (0.1109) loss: 0.8096 (0.8136) time: 0.1283 data: 0.0471 max mem: 9390 +Train: [65] [5200/6250] eta: 0:02:20 lr: 0.000036 grad: 0.1180 (0.1109) loss: 0.8094 (0.8135) time: 0.1284 data: 0.0423 max mem: 9390 +Train: [65] [5300/6250] eta: 0:02:06 lr: 0.000036 grad: 0.1077 (0.1110) loss: 0.8086 (0.8135) time: 0.1396 data: 0.0625 max mem: 9390 +Train: [65] [5400/6250] eta: 0:01:53 lr: 0.000036 grad: 0.1110 (0.1110) loss: 0.8101 (0.8134) time: 0.1283 data: 0.0517 max mem: 9390 +Train: [65] [5500/6250] eta: 0:01:40 lr: 0.000036 grad: 0.1120 (0.1111) loss: 0.8109 (0.8133) time: 0.1008 data: 0.0232 max mem: 9390 +Train: [65] [5600/6250] eta: 0:01:26 lr: 0.000036 grad: 0.1082 (0.1111) loss: 0.8117 (0.8132) time: 0.1577 data: 0.0726 max mem: 9390 +Train: [65] [5700/6250] eta: 0:01:13 lr: 0.000036 grad: 0.1109 (0.1111) loss: 0.8089 (0.8132) time: 0.1488 data: 0.0739 max mem: 9390 +Train: [65] [5800/6250] eta: 0:01:00 lr: 0.000036 grad: 0.1027 (0.1111) loss: 0.8110 (0.8131) time: 0.1471 data: 0.0650 max mem: 9390 +Train: [65] [5900/6250] eta: 0:00:46 lr: 0.000036 grad: 0.1139 (0.1111) loss: 0.8076 (0.8131) time: 0.1531 data: 0.0716 max mem: 9390 +Train: [65] [6000/6250] eta: 0:00:33 lr: 0.000036 grad: 0.1140 (0.1112) loss: 0.8098 (0.8131) time: 0.1036 data: 0.0276 max mem: 9390 +Train: [65] [6100/6250] eta: 0:00:20 lr: 0.000036 grad: 0.1032 (0.1112) loss: 0.8180 (0.8131) time: 0.1339 data: 0.0562 max mem: 9390 +Train: [65] [6200/6250] eta: 0:00:06 lr: 0.000036 grad: 0.1077 (0.1112) loss: 0.8086 (0.8131) time: 0.1519 data: 0.0682 max mem: 9390 +Train: [65] [6249/6250] eta: 0:00:00 lr: 0.000036 grad: 0.1062 (0.1112) loss: 0.8122 (0.8131) time: 0.1215 data: 0.0458 max mem: 9390 +Train: [65] Total time: 0:14:01 (0.1346 s / it) +Averaged stats: lr: 0.000036 grad: 0.1062 (0.1112) loss: 0.8122 (0.8131) +Eval (hcp-train-subset): [65] [ 0/62] eta: 0:03:20 loss: 0.8421 (0.8421) time: 3.2369 data: 3.1666 max mem: 9390 +Eval (hcp-train-subset): [65] [61/62] eta: 0:00:00 loss: 0.8331 (0.8316) time: 0.1059 data: 0.0808 max mem: 9390 +Eval (hcp-train-subset): [65] Total time: 0:00:11 (0.1872 s / it) +Averaged stats (hcp-train-subset): loss: 0.8331 (0.8316) +Eval (hcp-val): [65] [ 0/62] eta: 0:04:00 loss: 0.8331 (0.8331) time: 3.8814 data: 3.8187 max mem: 9390 +Eval (hcp-val): [65] [61/62] eta: 0:00:00 loss: 0.8319 (0.8331) time: 0.1105 data: 0.0859 max mem: 9390 +Eval (hcp-val): [65] Total time: 0:00:11 (0.1895 s / it) +Averaged stats (hcp-val): loss: 0.8319 (0.8331) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +Train: [66] [ 0/6250] eta: 7:18:32 lr: 0.000036 grad: 0.2672 (0.2672) loss: 0.8437 (0.8437) time: 4.2100 data: 4.0196 max mem: 9390 +Train: [66] [ 100/6250] eta: 0:19:26 lr: 0.000035 grad: 0.0992 (0.1227) loss: 0.8154 (0.8240) time: 0.1516 data: 0.0475 max mem: 9390 +Train: [66] [ 200/6250] eta: 0:17:08 lr: 0.000035 grad: 0.0969 (0.1176) loss: 0.8244 (0.8228) time: 0.1392 data: 0.0501 max mem: 9390 +Train: [66] [ 300/6250] eta: 0:16:05 lr: 0.000035 grad: 0.1228 (0.1158) loss: 0.8197 (0.8219) time: 0.1421 data: 0.0546 max mem: 9390 +Train: [66] [ 400/6250] eta: 0:15:16 lr: 0.000035 grad: 0.1083 (0.1144) loss: 0.8262 (0.8214) time: 0.1303 data: 0.0464 max mem: 9390 +Train: [66] [ 500/6250] eta: 0:14:31 lr: 0.000035 grad: 0.1042 (0.1131) loss: 0.8157 (0.8206) time: 0.1354 data: 0.0469 max mem: 9390 +Train: [66] [ 600/6250] eta: 0:13:59 lr: 0.000035 grad: 0.1033 (0.1122) loss: 0.8195 (0.8206) time: 0.1341 data: 0.0460 max mem: 9390 +Train: [66] [ 700/6250] eta: 0:13:32 lr: 0.000035 grad: 0.0989 (0.1112) loss: 0.8202 (0.8205) time: 0.1317 data: 0.0515 max mem: 9390 +Train: [66] [ 800/6250] eta: 0:13:03 lr: 0.000035 grad: 0.0981 (0.1104) loss: 0.8236 (0.8204) time: 0.1293 data: 0.0429 max mem: 9390 +Train: [66] [ 900/6250] eta: 0:12:42 lr: 0.000035 grad: 0.1080 (0.1102) loss: 0.8205 (0.8202) time: 0.1516 data: 0.0764 max mem: 9390 +Train: [66] [1000/6250] eta: 0:12:26 lr: 0.000035 grad: 0.1003 (0.1095) loss: 0.8185 (0.8204) time: 0.1263 data: 0.0362 max mem: 9390 +Train: [66] [1100/6250] eta: 0:12:06 lr: 0.000035 grad: 0.0997 (0.1089) loss: 0.8224 (0.8206) time: 0.1244 data: 0.0474 max mem: 9390 +Train: [66] [1200/6250] eta: 0:11:47 lr: 0.000035 grad: 0.1065 (0.1087) loss: 0.8211 (0.8205) time: 0.1209 data: 0.0293 max mem: 9390 +Train: [66] [1300/6250] eta: 0:11:29 lr: 0.000035 grad: 0.0967 (0.1084) loss: 0.8181 (0.8203) time: 0.1291 data: 0.0466 max mem: 9390 +Train: [66] [1400/6250] eta: 0:11:17 lr: 0.000035 grad: 0.1098 (0.1083) loss: 0.8184 (0.8202) time: 0.1568 data: 0.0698 max mem: 9390 +Train: [66] [1500/6250] eta: 0:11:03 lr: 0.000035 grad: 0.1021 (0.1084) loss: 0.8206 (0.8200) time: 0.1263 data: 0.0488 max mem: 9390 +Train: [66] [1600/6250] eta: 0:10:48 lr: 0.000035 grad: 0.0990 (0.1083) loss: 0.8186 (0.8198) time: 0.1316 data: 0.0509 max mem: 9390 +Train: [66] [1700/6250] eta: 0:10:35 lr: 0.000035 grad: 0.1042 (0.1083) loss: 0.8102 (0.8196) time: 0.1174 data: 0.0435 max mem: 9390 +Train: [66] [1800/6250] eta: 0:10:20 lr: 0.000035 grad: 0.1048 (0.1083) loss: 0.8167 (0.8195) time: 0.1229 data: 0.0486 max mem: 9390 +Train: [66] [1900/6250] eta: 0:10:09 lr: 0.000035 grad: 0.1065 (0.1081) loss: 0.8132 (0.8194) time: 0.1525 data: 0.0729 max mem: 9390 +Train: [66] [2000/6250] eta: 0:09:58 lr: 0.000035 grad: 0.1042 (0.1081) loss: 0.8156 (0.8193) time: 0.1502 data: 0.0735 max mem: 9390 +Train: [66] [2100/6250] eta: 0:09:41 lr: 0.000035 grad: 0.1054 (0.1083) loss: 0.8148 (0.8190) time: 0.1316 data: 0.0463 max mem: 9390 +Train: [66] [2200/6250] eta: 0:09:29 lr: 0.000035 grad: 0.1048 (0.1085) loss: 0.8183 (0.8187) time: 0.1653 data: 0.0886 max mem: 9390 +Train: [66] [2300/6250] eta: 0:09:14 lr: 0.000035 grad: 0.1063 (0.1086) loss: 0.8095 (0.8185) time: 0.1352 data: 0.0535 max mem: 9390 +Train: [66] [2400/6250] eta: 0:09:02 lr: 0.000035 grad: 0.1120 (0.1089) loss: 0.8094 (0.8181) time: 0.1488 data: 0.0700 max mem: 9390 +Train: [66] [2500/6250] eta: 0:08:52 lr: 0.000035 grad: 0.1112 (0.1090) loss: 0.8040 (0.8179) time: 0.2373 data: 0.1352 max mem: 9390 +Train: [66] [2600/6250] eta: 0:08:37 lr: 0.000035 grad: 0.1083 (0.1091) loss: 0.8169 (0.8177) time: 0.1397 data: 0.0678 max mem: 9390 +Train: [66] [2700/6250] eta: 0:08:22 lr: 0.000035 grad: 0.1078 (0.1092) loss: 0.8093 (0.8175) time: 0.1361 data: 0.0572 max mem: 9390 +Train: [66] [2800/6250] eta: 0:08:09 lr: 0.000035 grad: 0.1138 (0.1093) loss: 0.8064 (0.8173) time: 0.1621 data: 0.0874 max mem: 9390 +Train: [66] [2900/6250] eta: 0:07:54 lr: 0.000035 grad: 0.1075 (0.1093) loss: 0.8116 (0.8172) time: 0.1244 data: 0.0496 max mem: 9390 +Train: [66] [3000/6250] eta: 0:07:40 lr: 0.000035 grad: 0.1033 (0.1094) loss: 0.8190 (0.8171) time: 0.1386 data: 0.0536 max mem: 9390 +Train: [66] [3100/6250] eta: 0:07:29 lr: 0.000035 grad: 0.1047 (0.1095) loss: 0.8123 (0.8170) time: 0.1744 data: 0.0958 max mem: 9390 +Train: [66] [3200/6250] eta: 0:07:15 lr: 0.000035 grad: 0.1028 (0.1094) loss: 0.8117 (0.8169) time: 0.1407 data: 0.0596 max mem: 9390 +Train: [66] [3300/6250] eta: 0:07:02 lr: 0.000035 grad: 0.1063 (0.1094) loss: 0.8112 (0.8168) time: 0.1688 data: 0.0908 max mem: 9390 +Train: [66] [3400/6250] eta: 0:06:48 lr: 0.000035 grad: 0.0999 (0.1095) loss: 0.8225 (0.8166) time: 0.1540 data: 0.0744 max mem: 9390 +Train: [66] [3500/6250] eta: 0:06:34 lr: 0.000034 grad: 0.1112 (0.1094) loss: 0.8175 (0.8166) time: 0.1615 data: 0.0839 max mem: 9390 +Train: [66] [3600/6250] eta: 0:06:19 lr: 0.000034 grad: 0.1027 (0.1093) loss: 0.8199 (0.8165) time: 0.1073 data: 0.0317 max mem: 9390 +Train: [66] [3700/6250] eta: 0:06:04 lr: 0.000034 grad: 0.1093 (0.1093) loss: 0.8132 (0.8165) time: 0.1336 data: 0.0520 max mem: 9390 +Train: [66] [3800/6250] eta: 0:05:49 lr: 0.000034 grad: 0.1031 (0.1093) loss: 0.8196 (0.8164) time: 0.1344 data: 0.0552 max mem: 9390 +Train: [66] [3900/6250] eta: 0:05:34 lr: 0.000034 grad: 0.1086 (0.1093) loss: 0.8156 (0.8163) time: 0.1134 data: 0.0288 max mem: 9390 +Train: [66] [4000/6250] eta: 0:05:18 lr: 0.000034 grad: 0.1090 (0.1092) loss: 0.8150 (0.8163) time: 0.1259 data: 0.0444 max mem: 9390 +Train: [66] [4100/6250] eta: 0:05:03 lr: 0.000034 grad: 0.1029 (0.1091) loss: 0.8076 (0.8162) time: 0.1322 data: 0.0523 max mem: 9390 +Train: [66] [4200/6250] eta: 0:04:48 lr: 0.000034 grad: 0.1027 (0.1091) loss: 0.8149 (0.8161) time: 0.1160 data: 0.0372 max mem: 9390 +Train: [66] [4300/6250] eta: 0:04:33 lr: 0.000034 grad: 0.1057 (0.1090) loss: 0.8175 (0.8161) time: 0.1287 data: 0.0493 max mem: 9390 +Train: [66] [4400/6250] eta: 0:04:18 lr: 0.000034 grad: 0.1052 (0.1090) loss: 0.8157 (0.8160) time: 0.1195 data: 0.0381 max mem: 9390 +Train: [66] [4500/6250] eta: 0:04:04 lr: 0.000034 grad: 0.1101 (0.1090) loss: 0.8195 (0.8160) time: 0.1372 data: 0.0585 max mem: 9390 +Train: [66] [4600/6250] eta: 0:03:50 lr: 0.000034 grad: 0.1075 (0.1091) loss: 0.8176 (0.8161) time: 0.1469 data: 0.0653 max mem: 9390 +Train: [66] [4700/6250] eta: 0:03:36 lr: 0.000034 grad: 0.1100 (0.1091) loss: 0.8176 (0.8161) time: 0.1311 data: 0.0538 max mem: 9390 +Train: [66] [4800/6250] eta: 0:03:21 lr: 0.000034 grad: 0.1068 (0.1092) loss: 0.8133 (0.8160) time: 0.1299 data: 0.0404 max mem: 9390 +Train: [66] [4900/6250] eta: 0:03:07 lr: 0.000034 grad: 0.1073 (0.1092) loss: 0.8235 (0.8160) time: 0.1337 data: 0.0592 max mem: 9390 +Train: [66] [5000/6250] eta: 0:02:53 lr: 0.000034 grad: 0.1040 (0.1092) loss: 0.8204 (0.8160) time: 0.1284 data: 0.0486 max mem: 9390 +Train: [66] [5100/6250] eta: 0:02:39 lr: 0.000034 grad: 0.1076 (0.1093) loss: 0.8138 (0.8160) time: 0.1101 data: 0.0333 max mem: 9390 +Train: [66] [5200/6250] eta: 0:02:25 lr: 0.000034 grad: 0.1080 (0.1093) loss: 0.8154 (0.8159) time: 0.1348 data: 0.0533 max mem: 9390 +Train: [66] [5300/6250] eta: 0:02:11 lr: 0.000034 grad: 0.1026 (0.1093) loss: 0.8112 (0.8159) time: 0.1571 data: 0.0733 max mem: 9390 +Train: [66] [5400/6250] eta: 0:01:58 lr: 0.000034 grad: 0.1043 (0.1093) loss: 0.8159 (0.8159) time: 0.1248 data: 0.0432 max mem: 9390 +Train: [66] [5500/6250] eta: 0:01:44 lr: 0.000034 grad: 0.1071 (0.1094) loss: 0.8147 (0.8159) time: 0.1549 data: 0.0637 max mem: 9390 +Train: [66] [5600/6250] eta: 0:01:30 lr: 0.000034 grad: 0.1075 (0.1094) loss: 0.8146 (0.8158) time: 0.2455 data: 0.1671 max mem: 9390 +Train: [66] [5700/6250] eta: 0:01:16 lr: 0.000034 grad: 0.1125 (0.1095) loss: 0.8074 (0.8158) time: 0.1665 data: 0.0807 max mem: 9390 +Train: [66] [5800/6250] eta: 0:01:02 lr: 0.000034 grad: 0.1044 (0.1095) loss: 0.8155 (0.8157) time: 0.1465 data: 0.0664 max mem: 9390 +Train: [66] [5900/6250] eta: 0:00:48 lr: 0.000034 grad: 0.1088 (0.1096) loss: 0.8087 (0.8157) time: 0.1193 data: 0.0319 max mem: 9390 +Train: [66] [6000/6250] eta: 0:00:34 lr: 0.000034 grad: 0.1052 (0.1097) loss: 0.8140 (0.8156) time: 0.1420 data: 0.0593 max mem: 9390 +Train: [66] [6100/6250] eta: 0:00:20 lr: 0.000034 grad: 0.1128 (0.1097) loss: 0.8150 (0.8155) time: 0.1771 data: 0.0953 max mem: 9390 +Train: [66] [6200/6250] eta: 0:00:06 lr: 0.000034 grad: 0.1106 (0.1097) loss: 0.8219 (0.8155) time: 0.1470 data: 0.0722 max mem: 9390 +Train: [66] [6249/6250] eta: 0:00:00 lr: 0.000034 grad: 0.1078 (0.1098) loss: 0.8188 (0.8155) time: 0.1313 data: 0.0524 max mem: 9390 +Train: [66] Total time: 0:14:36 (0.1402 s / it) +Averaged stats: lr: 0.000034 grad: 0.1078 (0.1098) loss: 0.8188 (0.8155) +Eval (hcp-train-subset): [66] [ 0/62] eta: 0:03:15 loss: 0.8409 (0.8409) time: 3.1594 data: 3.0897 max mem: 9390 +Eval (hcp-train-subset): [66] [61/62] eta: 0:00:00 loss: 0.8290 (0.8302) time: 0.1046 data: 0.0798 max mem: 9390 +Eval (hcp-train-subset): [66] Total time: 0:00:11 (0.1834 s / it) +Averaged stats (hcp-train-subset): loss: 0.8290 (0.8302) +Eval (hcp-val): [66] [ 0/62] eta: 0:03:48 loss: 0.8262 (0.8262) time: 3.6904 data: 3.6046 max mem: 9390 +Eval (hcp-val): [66] [61/62] eta: 0:00:00 loss: 0.8308 (0.8325) time: 0.1169 data: 0.0916 max mem: 9390 +Eval (hcp-val): [66] Total time: 0:00:12 (0.2042 s / it) +Averaged stats (hcp-val): loss: 0.8308 (0.8325) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +Train: [67] [ 0/6250] eta: 7:39:04 lr: 0.000034 grad: 0.2928 (0.2928) loss: 0.8019 (0.8019) time: 4.4071 data: 4.1690 max mem: 9390 +Train: [67] [ 100/6250] eta: 0:19:52 lr: 0.000034 grad: 0.1069 (0.1267) loss: 0.8233 (0.8267) time: 0.1376 data: 0.0501 max mem: 9390 +Train: [67] [ 200/6250] eta: 0:16:47 lr: 0.000034 grad: 0.0963 (0.1170) loss: 0.8240 (0.8264) time: 0.1506 data: 0.0651 max mem: 9390 +Train: [67] [ 300/6250] eta: 0:15:36 lr: 0.000034 grad: 0.0972 (0.1155) loss: 0.8247 (0.8247) time: 0.1437 data: 0.0607 max mem: 9390 +Train: [67] [ 400/6250] eta: 0:14:38 lr: 0.000034 grad: 0.0968 (0.1127) loss: 0.8301 (0.8240) time: 0.1257 data: 0.0438 max mem: 9390 +Train: [67] [ 500/6250] eta: 0:14:02 lr: 0.000034 grad: 0.1101 (0.1112) loss: 0.8227 (0.8241) time: 0.1299 data: 0.0488 max mem: 9390 +Train: [67] [ 600/6250] eta: 0:13:34 lr: 0.000033 grad: 0.1074 (0.1100) loss: 0.8258 (0.8238) time: 0.1330 data: 0.0436 max mem: 9390 +Train: [67] [ 700/6250] eta: 0:13:07 lr: 0.000033 grad: 0.1107 (0.1095) loss: 0.8224 (0.8234) time: 0.1276 data: 0.0443 max mem: 9390 +Train: [67] [ 800/6250] eta: 0:12:45 lr: 0.000033 grad: 0.0998 (0.1085) loss: 0.8240 (0.8232) time: 0.1197 data: 0.0387 max mem: 9390 +Train: [67] [ 900/6250] eta: 0:12:28 lr: 0.000033 grad: 0.1009 (0.1084) loss: 0.8220 (0.8229) time: 0.1500 data: 0.0721 max mem: 9390 +Train: [67] [1000/6250] eta: 0:12:10 lr: 0.000033 grad: 0.1068 (0.1087) loss: 0.8238 (0.8226) time: 0.1468 data: 0.0623 max mem: 9390 +Train: [67] [1100/6250] eta: 0:11:57 lr: 0.000033 grad: 0.1034 (0.1085) loss: 0.8212 (0.8223) time: 0.1666 data: 0.0936 max mem: 9390 +Train: [67] [1200/6250] eta: 0:11:40 lr: 0.000033 grad: 0.1033 (0.1083) loss: 0.8132 (0.8218) time: 0.1441 data: 0.0538 max mem: 9390 +Train: [67] [1300/6250] eta: 0:11:26 lr: 0.000033 grad: 0.1027 (0.1083) loss: 0.8180 (0.8214) time: 0.1415 data: 0.0657 max mem: 9390 +Train: [67] [1400/6250] eta: 0:11:12 lr: 0.000033 grad: 0.0988 (0.1083) loss: 0.8183 (0.8211) time: 0.1484 data: 0.0660 max mem: 9390 +Train: [67] [1500/6250] eta: 0:10:59 lr: 0.000033 grad: 0.1055 (0.1081) loss: 0.8123 (0.8208) time: 0.1579 data: 0.0779 max mem: 9390 +Train: [67] [1600/6250] eta: 0:10:50 lr: 0.000033 grad: 0.1091 (0.1082) loss: 0.8117 (0.8203) time: 0.1624 data: 0.0825 max mem: 9390 +Train: [67] [1700/6250] eta: 0:10:37 lr: 0.000033 grad: 0.1063 (0.1081) loss: 0.8218 (0.8201) time: 0.1389 data: 0.0600 max mem: 9390 +Train: [67] [1800/6250] eta: 0:10:21 lr: 0.000033 grad: 0.1091 (0.1080) loss: 0.8178 (0.8198) time: 0.1321 data: 0.0555 max mem: 9390 +Train: [67] [1900/6250] eta: 0:10:05 lr: 0.000033 grad: 0.1009 (0.1080) loss: 0.8154 (0.8196) time: 0.1416 data: 0.0640 max mem: 9390 +Train: [67] [2000/6250] eta: 0:09:51 lr: 0.000033 grad: 0.1117 (0.1083) loss: 0.8190 (0.8192) time: 0.1234 data: 0.0489 max mem: 9390 +Train: [67] [2100/6250] eta: 0:09:37 lr: 0.000033 grad: 0.1164 (0.1086) loss: 0.8085 (0.8188) time: 0.1521 data: 0.0662 max mem: 9390 +Train: [67] [2200/6250] eta: 0:09:22 lr: 0.000033 grad: 0.1071 (0.1088) loss: 0.8110 (0.8184) time: 0.1411 data: 0.0601 max mem: 9390 +Train: [67] [2300/6250] eta: 0:09:09 lr: 0.000033 grad: 0.1091 (0.1089) loss: 0.8110 (0.8181) time: 0.1621 data: 0.0799 max mem: 9390 +Train: [67] [2400/6250] eta: 0:08:55 lr: 0.000033 grad: 0.1142 (0.1091) loss: 0.8066 (0.8177) time: 0.1234 data: 0.0511 max mem: 9390 +Train: [67] [2500/6250] eta: 0:08:41 lr: 0.000033 grad: 0.1119 (0.1092) loss: 0.8146 (0.8175) time: 0.1476 data: 0.0698 max mem: 9390 +Train: [67] [2600/6250] eta: 0:08:27 lr: 0.000033 grad: 0.1170 (0.1094) loss: 0.8115 (0.8174) time: 0.1320 data: 0.0524 max mem: 9390 +Train: [67] [2700/6250] eta: 0:08:14 lr: 0.000033 grad: 0.1030 (0.1095) loss: 0.8095 (0.8172) time: 0.1426 data: 0.0641 max mem: 9390 +Train: [67] [2800/6250] eta: 0:08:02 lr: 0.000033 grad: 0.1030 (0.1096) loss: 0.8140 (0.8171) time: 0.1337 data: 0.0570 max mem: 9390 +Train: [67] [2900/6250] eta: 0:07:49 lr: 0.000033 grad: 0.1095 (0.1095) loss: 0.8116 (0.8170) time: 0.2010 data: 0.0993 max mem: 9390 +Train: [67] [3000/6250] eta: 0:07:38 lr: 0.000033 grad: 0.1071 (0.1098) loss: 0.8175 (0.8168) time: 0.1023 data: 0.0002 max mem: 9390 +Train: [67] [3100/6250] eta: 0:07:25 lr: 0.000033 grad: 0.1066 (0.1099) loss: 0.8153 (0.8167) time: 0.1373 data: 0.0510 max mem: 9390 +Train: [67] [3200/6250] eta: 0:07:12 lr: 0.000033 grad: 0.1111 (0.1101) loss: 0.8091 (0.8165) time: 0.1395 data: 0.0600 max mem: 9390 +Train: [67] [3300/6250] eta: 0:06:59 lr: 0.000033 grad: 0.1147 (0.1102) loss: 0.8077 (0.8163) time: 0.1936 data: 0.1189 max mem: 9390 +Train: [67] [3400/6250] eta: 0:06:45 lr: 0.000033 grad: 0.1064 (0.1102) loss: 0.8180 (0.8162) time: 0.1448 data: 0.0697 max mem: 9390 +Train: [67] [3500/6250] eta: 0:06:31 lr: 0.000033 grad: 0.1137 (0.1103) loss: 0.8145 (0.8160) time: 0.1364 data: 0.0542 max mem: 9390 +Train: [67] [3600/6250] eta: 0:06:16 lr: 0.000033 grad: 0.1245 (0.1104) loss: 0.8108 (0.8158) time: 0.1450 data: 0.0664 max mem: 9390 +Train: [67] [3700/6250] eta: 0:06:02 lr: 0.000033 grad: 0.1122 (0.1104) loss: 0.8164 (0.8158) time: 0.1472 data: 0.0664 max mem: 9390 +Train: [67] [3800/6250] eta: 0:05:46 lr: 0.000033 grad: 0.1031 (0.1104) loss: 0.8113 (0.8157) time: 0.1202 data: 0.0400 max mem: 9390 +Train: [67] [3900/6250] eta: 0:05:31 lr: 0.000033 grad: 0.1042 (0.1104) loss: 0.8196 (0.8157) time: 0.1325 data: 0.0499 max mem: 9390 +Train: [67] [4000/6250] eta: 0:05:16 lr: 0.000032 grad: 0.1046 (0.1104) loss: 0.8154 (0.8156) time: 0.1075 data: 0.0233 max mem: 9390 +Train: [67] [4100/6250] eta: 0:05:01 lr: 0.000032 grad: 0.1039 (0.1104) loss: 0.8186 (0.8156) time: 0.1184 data: 0.0380 max mem: 9390 +Train: [67] [4200/6250] eta: 0:04:46 lr: 0.000032 grad: 0.1057 (0.1105) loss: 0.8179 (0.8156) time: 0.1212 data: 0.0354 max mem: 9390 +Train: [67] [4300/6250] eta: 0:04:32 lr: 0.000032 grad: 0.1102 (0.1105) loss: 0.8099 (0.8155) time: 0.1229 data: 0.0439 max mem: 9390 +Train: [67] [4400/6250] eta: 0:04:17 lr: 0.000032 grad: 0.1047 (0.1106) loss: 0.8103 (0.8154) time: 0.1450 data: 0.0667 max mem: 9390 +Train: [67] [4500/6250] eta: 0:04:03 lr: 0.000032 grad: 0.1066 (0.1106) loss: 0.8148 (0.8154) time: 0.1133 data: 0.0327 max mem: 9390 +Train: [67] [4600/6250] eta: 0:03:49 lr: 0.000032 grad: 0.1026 (0.1106) loss: 0.8204 (0.8154) time: 0.1171 data: 0.0361 max mem: 9390 +Train: [67] [4700/6250] eta: 0:03:35 lr: 0.000032 grad: 0.1083 (0.1106) loss: 0.8086 (0.8154) time: 0.1245 data: 0.0409 max mem: 9390 +Train: [67] [4800/6250] eta: 0:03:20 lr: 0.000032 grad: 0.1050 (0.1106) loss: 0.8184 (0.8155) time: 0.1220 data: 0.0367 max mem: 9390 +Train: [67] [4900/6250] eta: 0:03:06 lr: 0.000032 grad: 0.1081 (0.1107) loss: 0.8204 (0.8154) time: 0.1212 data: 0.0433 max mem: 9390 +Train: [67] [5000/6250] eta: 0:02:52 lr: 0.000032 grad: 0.1091 (0.1107) loss: 0.8177 (0.8155) time: 0.1406 data: 0.0614 max mem: 9390 +Train: [67] [5100/6250] eta: 0:02:38 lr: 0.000032 grad: 0.1068 (0.1108) loss: 0.8147 (0.8155) time: 0.1346 data: 0.0575 max mem: 9390 +Train: [67] [5200/6250] eta: 0:02:24 lr: 0.000032 grad: 0.1114 (0.1108) loss: 0.8147 (0.8155) time: 0.1395 data: 0.0632 max mem: 9390 +Train: [67] [5300/6250] eta: 0:02:10 lr: 0.000032 grad: 0.1136 (0.1108) loss: 0.8158 (0.8155) time: 0.1410 data: 0.0565 max mem: 9390 +Train: [67] [5400/6250] eta: 0:01:56 lr: 0.000032 grad: 0.1117 (0.1108) loss: 0.8162 (0.8156) time: 0.1259 data: 0.0431 max mem: 9390 +Train: [67] [5500/6250] eta: 0:01:43 lr: 0.000032 grad: 0.1065 (0.1109) loss: 0.8171 (0.8155) time: 0.1569 data: 0.0826 max mem: 9390 +Train: [67] [5600/6250] eta: 0:01:29 lr: 0.000032 grad: 0.1069 (0.1109) loss: 0.8172 (0.8155) time: 0.1291 data: 0.0476 max mem: 9390 +Train: [67] [5700/6250] eta: 0:01:15 lr: 0.000032 grad: 0.1060 (0.1109) loss: 0.8195 (0.8155) time: 0.1438 data: 0.0677 max mem: 9390 +Train: [67] [5800/6250] eta: 0:01:01 lr: 0.000032 grad: 0.1072 (0.1110) loss: 0.8133 (0.8155) time: 0.1309 data: 0.0548 max mem: 9390 +Train: [67] [5900/6250] eta: 0:00:48 lr: 0.000032 grad: 0.1022 (0.1109) loss: 0.8193 (0.8155) time: 0.1683 data: 0.0831 max mem: 9390 +Train: [67] [6000/6250] eta: 0:00:34 lr: 0.000032 grad: 0.1162 (0.1110) loss: 0.8066 (0.8155) time: 0.2236 data: 0.1503 max mem: 9390 +Train: [67] [6100/6250] eta: 0:00:20 lr: 0.000032 grad: 0.1143 (0.1111) loss: 0.8137 (0.8154) time: 0.1237 data: 0.0450 max mem: 9390 +Train: [67] [6200/6250] eta: 0:00:06 lr: 0.000032 grad: 0.1121 (0.1111) loss: 0.8104 (0.8154) time: 0.1762 data: 0.0908 max mem: 9390 +Train: [67] [6249/6250] eta: 0:00:00 lr: 0.000032 grad: 0.1149 (0.1111) loss: 0.8086 (0.8154) time: 0.1200 data: 0.0402 max mem: 9390 +Train: [67] Total time: 0:14:24 (0.1382 s / it) +Averaged stats: lr: 0.000032 grad: 0.1149 (0.1111) loss: 0.8086 (0.8154) +Eval (hcp-train-subset): [67] [ 0/62] eta: 0:05:50 loss: 0.8369 (0.8369) time: 5.6476 data: 5.6139 max mem: 9390 +Eval (hcp-train-subset): [67] [61/62] eta: 0:00:00 loss: 0.8314 (0.8316) time: 0.1165 data: 0.0914 max mem: 9390 +Eval (hcp-train-subset): [67] Total time: 0:00:12 (0.1975 s / it) +Averaged stats (hcp-train-subset): loss: 0.8314 (0.8316) +Eval (hcp-val): [67] [ 0/62] eta: 0:04:18 loss: 0.8281 (0.8281) time: 4.1719 data: 4.1273 max mem: 9390 +Eval (hcp-val): [67] [61/62] eta: 0:00:00 loss: 0.8311 (0.8323) time: 0.1233 data: 0.0984 max mem: 9390 +Eval (hcp-val): [67] Total time: 0:00:12 (0.1966 s / it) +Averaged stats (hcp-val): loss: 0.8311 (0.8323) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +Train: [68] [ 0/6250] eta: 9:13:09 lr: 0.000032 grad: 0.0943 (0.0943) loss: 0.8172 (0.8172) time: 5.3104 data: 5.1598 max mem: 9390 +Train: [68] [ 100/6250] eta: 0:19:43 lr: 0.000032 grad: 0.1066 (0.1261) loss: 0.8321 (0.8334) time: 0.1342 data: 0.0424 max mem: 9390 +Train: [68] [ 200/6250] eta: 0:17:01 lr: 0.000032 grad: 0.1115 (0.1222) loss: 0.8186 (0.8283) time: 0.1400 data: 0.0440 max mem: 9390 +Train: [68] [ 300/6250] eta: 0:15:38 lr: 0.000032 grad: 0.0997 (0.1240) loss: 0.8222 (0.8246) time: 0.1350 data: 0.0478 max mem: 9390 +Train: [68] [ 400/6250] eta: 0:14:44 lr: 0.000032 grad: 0.1031 (0.1217) loss: 0.8185 (0.8223) time: 0.1257 data: 0.0414 max mem: 9390 +Train: [68] [ 500/6250] eta: 0:14:06 lr: 0.000032 grad: 0.1038 (0.1211) loss: 0.8169 (0.8207) time: 0.1192 data: 0.0293 max mem: 9390 +Train: [68] [ 600/6250] eta: 0:13:38 lr: 0.000032 grad: 0.1113 (0.1200) loss: 0.8162 (0.8198) time: 0.1307 data: 0.0410 max mem: 9390 +Train: [68] [ 700/6250] eta: 0:13:06 lr: 0.000032 grad: 0.1041 (0.1190) loss: 0.8222 (0.8196) time: 0.1102 data: 0.0197 max mem: 9390 +Train: [68] [ 800/6250] eta: 0:12:38 lr: 0.000032 grad: 0.1087 (0.1181) loss: 0.8250 (0.8196) time: 0.1314 data: 0.0486 max mem: 9390 +Train: [68] [ 900/6250] eta: 0:12:22 lr: 0.000032 grad: 0.1024 (0.1172) loss: 0.8261 (0.8196) time: 0.1462 data: 0.0613 max mem: 9390 +Train: [68] [1000/6250] eta: 0:12:03 lr: 0.000032 grad: 0.1107 (0.1165) loss: 0.8147 (0.8195) time: 0.1271 data: 0.0479 max mem: 9390 +Train: [68] [1100/6250] eta: 0:11:53 lr: 0.000032 grad: 0.1041 (0.1160) loss: 0.8214 (0.8193) time: 0.2260 data: 0.1366 max mem: 9390 +Train: [68] [1200/6250] eta: 0:11:33 lr: 0.000032 grad: 0.1085 (0.1155) loss: 0.8212 (0.8192) time: 0.0988 data: 0.0253 max mem: 9390 +Train: [68] [1300/6250] eta: 0:11:19 lr: 0.000031 grad: 0.1069 (0.1152) loss: 0.8188 (0.8190) time: 0.0869 data: 0.0002 max mem: 9390 +Train: [68] [1400/6250] eta: 0:11:01 lr: 0.000031 grad: 0.1146 (0.1152) loss: 0.8129 (0.8185) time: 0.1269 data: 0.0432 max mem: 9390 +Train: [68] [1500/6250] eta: 0:10:49 lr: 0.000031 grad: 0.1114 (0.1152) loss: 0.8111 (0.8181) time: 0.1288 data: 0.0493 max mem: 9390 +Train: [68] [1600/6250] eta: 0:10:41 lr: 0.000031 grad: 0.1081 (0.1151) loss: 0.8198 (0.8178) time: 0.1162 data: 0.0249 max mem: 9390 +Train: [68] [1700/6250] eta: 0:10:26 lr: 0.000031 grad: 0.1212 (0.1153) loss: 0.8024 (0.8172) time: 0.1301 data: 0.0445 max mem: 9390 +Train: [68] [1800/6250] eta: 0:10:09 lr: 0.000031 grad: 0.1158 (0.1151) loss: 0.8161 (0.8170) time: 0.1293 data: 0.0459 max mem: 9390 +Train: [68] [1900/6250] eta: 0:09:54 lr: 0.000031 grad: 0.1034 (0.1149) loss: 0.8109 (0.8168) time: 0.1522 data: 0.0681 max mem: 9390 +Train: [68] [2000/6250] eta: 0:09:41 lr: 0.000031 grad: 0.1079 (0.1148) loss: 0.8126 (0.8165) time: 0.1181 data: 0.0391 max mem: 9390 +Train: [68] [2100/6250] eta: 0:09:27 lr: 0.000031 grad: 0.1081 (0.1148) loss: 0.8209 (0.8163) time: 0.1090 data: 0.0243 max mem: 9390 +Train: [68] [2200/6250] eta: 0:09:12 lr: 0.000031 grad: 0.1089 (0.1148) loss: 0.8126 (0.8161) time: 0.1240 data: 0.0426 max mem: 9390 +Train: [68] [2300/6250] eta: 0:08:59 lr: 0.000031 grad: 0.1096 (0.1151) loss: 0.8128 (0.8160) time: 0.1289 data: 0.0417 max mem: 9390 +Train: [68] [2400/6250] eta: 0:08:46 lr: 0.000031 grad: 0.1049 (0.1150) loss: 0.8199 (0.8159) time: 0.1372 data: 0.0493 max mem: 9390 +Train: [68] [2500/6250] eta: 0:08:31 lr: 0.000031 grad: 0.1077 (0.1150) loss: 0.8120 (0.8158) time: 0.1255 data: 0.0469 max mem: 9390 +Train: [68] [2600/6250] eta: 0:08:18 lr: 0.000031 grad: 0.1153 (0.1150) loss: 0.8121 (0.8158) time: 0.1531 data: 0.0711 max mem: 9390 +Train: [68] [2700/6250] eta: 0:08:05 lr: 0.000031 grad: 0.1074 (0.1148) loss: 0.8137 (0.8157) time: 0.1417 data: 0.0658 max mem: 9390 +Train: [68] [2800/6250] eta: 0:07:50 lr: 0.000031 grad: 0.1128 (0.1149) loss: 0.8143 (0.8156) time: 0.1321 data: 0.0534 max mem: 9390 +Train: [68] [2900/6250] eta: 0:07:37 lr: 0.000031 grad: 0.1063 (0.1149) loss: 0.8120 (0.8155) time: 0.1250 data: 0.0430 max mem: 9390 +Train: [68] [3000/6250] eta: 0:07:24 lr: 0.000031 grad: 0.1090 (0.1149) loss: 0.8159 (0.8154) time: 0.1393 data: 0.0521 max mem: 9390 +Train: [68] [3100/6250] eta: 0:07:10 lr: 0.000031 grad: 0.1087 (0.1149) loss: 0.8165 (0.8153) time: 0.1068 data: 0.0293 max mem: 9390 +Train: [68] [3200/6250] eta: 0:06:58 lr: 0.000031 grad: 0.1134 (0.1149) loss: 0.8059 (0.8151) time: 0.1482 data: 0.0664 max mem: 9390 +Train: [68] [3300/6250] eta: 0:06:45 lr: 0.000031 grad: 0.1139 (0.1150) loss: 0.8091 (0.8151) time: 0.1260 data: 0.0457 max mem: 9390 +Train: [68] [3400/6250] eta: 0:06:30 lr: 0.000031 grad: 0.1127 (0.1151) loss: 0.8114 (0.8150) time: 0.1304 data: 0.0523 max mem: 9390 +Train: [68] [3500/6250] eta: 0:06:18 lr: 0.000031 grad: 0.1125 (0.1151) loss: 0.8152 (0.8149) time: 0.1533 data: 0.0740 max mem: 9390 +Train: [68] [3600/6250] eta: 0:06:05 lr: 0.000031 grad: 0.1093 (0.1151) loss: 0.8202 (0.8149) time: 0.1503 data: 0.0687 max mem: 9390 +Train: [68] [3700/6250] eta: 0:05:51 lr: 0.000031 grad: 0.1190 (0.1150) loss: 0.8123 (0.8149) time: 0.1299 data: 0.0471 max mem: 9390 +Train: [68] [3800/6250] eta: 0:05:37 lr: 0.000031 grad: 0.1113 (0.1150) loss: 0.8168 (0.8150) time: 0.1338 data: 0.0587 max mem: 9390 +Train: [68] [3900/6250] eta: 0:05:24 lr: 0.000031 grad: 0.1012 (0.1150) loss: 0.8151 (0.8150) time: 0.1410 data: 0.0617 max mem: 9390 +Train: [68] [4000/6250] eta: 0:05:10 lr: 0.000031 grad: 0.1115 (0.1148) loss: 0.8121 (0.8151) time: 0.1305 data: 0.0447 max mem: 9390 +Train: [68] [4100/6250] eta: 0:04:55 lr: 0.000031 grad: 0.1107 (0.1148) loss: 0.8171 (0.8152) time: 0.1235 data: 0.0419 max mem: 9390 +Train: [68] [4200/6250] eta: 0:04:41 lr: 0.000031 grad: 0.1058 (0.1146) loss: 0.8206 (0.8152) time: 0.1332 data: 0.0576 max mem: 9390 +Train: [68] [4300/6250] eta: 0:04:26 lr: 0.000031 grad: 0.1064 (0.1145) loss: 0.8177 (0.8153) time: 0.1178 data: 0.0386 max mem: 9390 +Train: [68] [4400/6250] eta: 0:04:12 lr: 0.000031 grad: 0.1002 (0.1144) loss: 0.8145 (0.8154) time: 0.1344 data: 0.0508 max mem: 9390 +Train: [68] [4500/6250] eta: 0:03:58 lr: 0.000031 grad: 0.1054 (0.1142) loss: 0.8137 (0.8154) time: 0.1415 data: 0.0689 max mem: 9390 +Train: [68] [4600/6250] eta: 0:03:44 lr: 0.000031 grad: 0.1052 (0.1142) loss: 0.8157 (0.8154) time: 0.1117 data: 0.0361 max mem: 9390 +Train: [68] [4700/6250] eta: 0:03:30 lr: 0.000031 grad: 0.1104 (0.1141) loss: 0.8174 (0.8155) time: 0.1344 data: 0.0530 max mem: 9390 +Train: [68] [4800/6250] eta: 0:03:16 lr: 0.000030 grad: 0.1050 (0.1140) loss: 0.8124 (0.8155) time: 0.0965 data: 0.0187 max mem: 9390 +Train: [68] [4900/6250] eta: 0:03:02 lr: 0.000030 grad: 0.1139 (0.1139) loss: 0.8182 (0.8156) time: 0.1062 data: 0.0211 max mem: 9390 +Train: [68] [5000/6250] eta: 0:02:48 lr: 0.000030 grad: 0.1057 (0.1139) loss: 0.8193 (0.8156) time: 0.1167 data: 0.0371 max mem: 9390 +Train: [68] [5100/6250] eta: 0:02:35 lr: 0.000030 grad: 0.1143 (0.1140) loss: 0.8168 (0.8155) time: 0.1329 data: 0.0457 max mem: 9390 +Train: [68] [5200/6250] eta: 0:02:21 lr: 0.000030 grad: 0.1065 (0.1139) loss: 0.8165 (0.8156) time: 0.1203 data: 0.0333 max mem: 9390 +Train: [68] [5300/6250] eta: 0:02:07 lr: 0.000030 grad: 0.1054 (0.1139) loss: 0.8213 (0.8156) time: 0.1347 data: 0.0567 max mem: 9390 +Train: [68] [5400/6250] eta: 0:01:54 lr: 0.000030 grad: 0.1052 (0.1139) loss: 0.8184 (0.8156) time: 0.1198 data: 0.0403 max mem: 9390 +Train: [68] [5500/6250] eta: 0:01:41 lr: 0.000030 grad: 0.1058 (0.1139) loss: 0.8165 (0.8156) time: 0.1497 data: 0.0589 max mem: 9390 +Train: [68] [5600/6250] eta: 0:01:27 lr: 0.000030 grad: 0.1070 (0.1138) loss: 0.8129 (0.8157) time: 0.1323 data: 0.0554 max mem: 9390 +Train: [68] [5700/6250] eta: 0:01:14 lr: 0.000030 grad: 0.1101 (0.1138) loss: 0.8142 (0.8157) time: 0.1457 data: 0.0724 max mem: 9390 +Train: [68] [5800/6250] eta: 0:01:00 lr: 0.000030 grad: 0.1059 (0.1137) loss: 0.8195 (0.8157) time: 0.1201 data: 0.0436 max mem: 9390 +Train: [68] [5900/6250] eta: 0:00:47 lr: 0.000030 grad: 0.1071 (0.1137) loss: 0.8162 (0.8156) time: 0.1612 data: 0.0630 max mem: 9390 +Train: [68] [6000/6250] eta: 0:00:33 lr: 0.000030 grad: 0.1089 (0.1137) loss: 0.8113 (0.8156) time: 0.1159 data: 0.0308 max mem: 9390 +Train: [68] [6100/6250] eta: 0:00:20 lr: 0.000030 grad: 0.1110 (0.1137) loss: 0.8143 (0.8155) time: 0.0934 data: 0.0019 max mem: 9390 +Train: [68] [6200/6250] eta: 0:00:06 lr: 0.000030 grad: 0.1084 (0.1138) loss: 0.8199 (0.8154) time: 0.1147 data: 0.0405 max mem: 9390 +Train: [68] [6249/6250] eta: 0:00:00 lr: 0.000030 grad: 0.1131 (0.1138) loss: 0.8093 (0.8154) time: 0.1516 data: 0.0746 max mem: 9390 +Train: [68] Total time: 0:14:10 (0.1360 s / it) +Averaged stats: lr: 0.000030 grad: 0.1131 (0.1138) loss: 0.8093 (0.8154) +Eval (hcp-train-subset): [68] [ 0/62] eta: 0:03:13 loss: 0.8445 (0.8445) time: 3.1245 data: 3.0534 max mem: 9390 +Eval (hcp-train-subset): [68] [61/62] eta: 0:00:00 loss: 0.8334 (0.8313) time: 0.1178 data: 0.0925 max mem: 9390 +Eval (hcp-train-subset): [68] Total time: 0:00:12 (0.2066 s / it) +Averaged stats (hcp-train-subset): loss: 0.8334 (0.8313) +Eval (hcp-val): [68] [ 0/62] eta: 0:03:52 loss: 0.8324 (0.8324) time: 3.7444 data: 3.6640 max mem: 9390 +Eval (hcp-val): [68] [61/62] eta: 0:00:00 loss: 0.8308 (0.8326) time: 0.1220 data: 0.0971 max mem: 9390 +Eval (hcp-val): [68] Total time: 0:00:12 (0.1982 s / it) +Averaged stats (hcp-val): loss: 0.8308 (0.8326) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +Train: [69] [ 0/6250] eta: 10:38:25 lr: 0.000030 grad: 0.3247 (0.3247) loss: 0.7563 (0.7563) time: 6.1289 data: 6.0278 max mem: 9390 +Train: [69] [ 100/6250] eta: 0:20:11 lr: 0.000030 grad: 0.1198 (0.1345) loss: 0.8207 (0.8204) time: 0.1226 data: 0.0212 max mem: 9390 +Train: [69] [ 200/6250] eta: 0:17:25 lr: 0.000030 grad: 0.1021 (0.1252) loss: 0.8184 (0.8206) time: 0.1339 data: 0.0447 max mem: 9390 +Train: [69] [ 300/6250] eta: 0:15:57 lr: 0.000030 grad: 0.1065 (0.1186) loss: 0.8202 (0.8203) time: 0.1350 data: 0.0574 max mem: 9390 +Train: [69] [ 400/6250] eta: 0:14:52 lr: 0.000030 grad: 0.1066 (0.1153) loss: 0.8246 (0.8208) time: 0.1242 data: 0.0388 max mem: 9390 +Train: [69] [ 500/6250] eta: 0:14:09 lr: 0.000030 grad: 0.1040 (0.1146) loss: 0.8212 (0.8202) time: 0.1344 data: 0.0485 max mem: 9390 +Train: [69] [ 600/6250] eta: 0:13:33 lr: 0.000030 grad: 0.1081 (0.1141) loss: 0.8198 (0.8196) time: 0.1272 data: 0.0409 max mem: 9390 +Train: [69] [ 700/6250] eta: 0:13:10 lr: 0.000030 grad: 0.1087 (0.1136) loss: 0.8174 (0.8191) time: 0.1480 data: 0.0645 max mem: 9390 +Train: [69] [ 800/6250] eta: 0:12:48 lr: 0.000030 grad: 0.1072 (0.1132) loss: 0.8205 (0.8189) time: 0.1435 data: 0.0543 max mem: 9390 +Train: [69] [ 900/6250] eta: 0:12:28 lr: 0.000030 grad: 0.1128 (0.1128) loss: 0.8195 (0.8188) time: 0.1351 data: 0.0459 max mem: 9390 +Train: [69] [1000/6250] eta: 0:12:09 lr: 0.000030 grad: 0.1086 (0.1130) loss: 0.8134 (0.8183) time: 0.1240 data: 0.0382 max mem: 9390 +Train: [69] [1100/6250] eta: 0:11:51 lr: 0.000030 grad: 0.1054 (0.1127) loss: 0.8103 (0.8178) time: 0.1266 data: 0.0468 max mem: 9390 +Train: [69] [1200/6250] eta: 0:11:33 lr: 0.000030 grad: 0.1138 (0.1128) loss: 0.8047 (0.8172) time: 0.1260 data: 0.0401 max mem: 9390 +Train: [69] [1300/6250] eta: 0:11:19 lr: 0.000030 grad: 0.1054 (0.1128) loss: 0.8103 (0.8168) time: 0.1278 data: 0.0409 max mem: 9390 +Train: [69] [1400/6250] eta: 0:11:05 lr: 0.000030 grad: 0.1058 (0.1126) loss: 0.8142 (0.8165) time: 0.1227 data: 0.0371 max mem: 9390 +Train: [69] [1500/6250] eta: 0:10:50 lr: 0.000030 grad: 0.1098 (0.1128) loss: 0.8139 (0.8162) time: 0.1167 data: 0.0386 max mem: 9390 +Train: [69] [1600/6250] eta: 0:10:35 lr: 0.000030 grad: 0.1200 (0.1130) loss: 0.8003 (0.8158) time: 0.1396 data: 0.0634 max mem: 9390 +Train: [69] [1700/6250] eta: 0:10:26 lr: 0.000030 grad: 0.1130 (0.1132) loss: 0.8146 (0.8155) time: 0.1906 data: 0.0800 max mem: 9390 +Train: [69] [1800/6250] eta: 0:10:11 lr: 0.000030 grad: 0.1030 (0.1133) loss: 0.8159 (0.8152) time: 0.1019 data: 0.0200 max mem: 9390 +Train: [69] [1900/6250] eta: 0:09:56 lr: 0.000030 grad: 0.1108 (0.1134) loss: 0.8188 (0.8149) time: 0.1481 data: 0.0718 max mem: 9390 +Train: [69] [2000/6250] eta: 0:09:42 lr: 0.000030 grad: 0.1065 (0.1136) loss: 0.8156 (0.8147) time: 0.1566 data: 0.0698 max mem: 9390 +Train: [69] [2100/6250] eta: 0:09:29 lr: 0.000029 grad: 0.1059 (0.1136) loss: 0.8129 (0.8145) time: 0.1469 data: 0.0662 max mem: 9390 +Train: [69] [2200/6250] eta: 0:09:19 lr: 0.000029 grad: 0.1091 (0.1137) loss: 0.8107 (0.8143) time: 0.0952 data: 0.0004 max mem: 9390 +Train: [69] [2300/6250] eta: 0:09:04 lr: 0.000029 grad: 0.1093 (0.1137) loss: 0.8164 (0.8142) time: 0.1320 data: 0.0502 max mem: 9390 +Train: [69] [2400/6250] eta: 0:08:51 lr: 0.000029 grad: 0.1119 (0.1138) loss: 0.8135 (0.8141) time: 0.1488 data: 0.0696 max mem: 9390 +Train: [69] [2500/6250] eta: 0:08:38 lr: 0.000029 grad: 0.1088 (0.1137) loss: 0.8075 (0.8141) time: 0.1452 data: 0.0614 max mem: 9390 +Train: [69] [2600/6250] eta: 0:08:24 lr: 0.000029 grad: 0.1127 (0.1138) loss: 0.8064 (0.8140) time: 0.1454 data: 0.0656 max mem: 9390 +Train: [69] [2700/6250] eta: 0:08:10 lr: 0.000029 grad: 0.1082 (0.1137) loss: 0.8152 (0.8139) time: 0.1590 data: 0.0845 max mem: 9390 +Train: [69] [2800/6250] eta: 0:07:59 lr: 0.000029 grad: 0.1051 (0.1136) loss: 0.8135 (0.8140) time: 0.1261 data: 0.0393 max mem: 9390 +Train: [69] [2900/6250] eta: 0:07:45 lr: 0.000029 grad: 0.1106 (0.1136) loss: 0.8196 (0.8139) time: 0.1252 data: 0.0453 max mem: 9390 +Train: [69] [3000/6250] eta: 0:07:31 lr: 0.000029 grad: 0.1107 (0.1136) loss: 0.8140 (0.8139) time: 0.1523 data: 0.0657 max mem: 9390 +Train: [69] [3100/6250] eta: 0:07:16 lr: 0.000029 grad: 0.1138 (0.1136) loss: 0.8153 (0.8139) time: 0.1375 data: 0.0529 max mem: 9390 +Train: [69] [3200/6250] eta: 0:07:02 lr: 0.000029 grad: 0.1042 (0.1136) loss: 0.8219 (0.8140) time: 0.1409 data: 0.0642 max mem: 9390 +Train: [69] [3300/6250] eta: 0:06:50 lr: 0.000029 grad: 0.1039 (0.1137) loss: 0.8149 (0.8140) time: 0.1338 data: 0.0585 max mem: 9390 +Train: [69] [3400/6250] eta: 0:06:36 lr: 0.000029 grad: 0.1152 (0.1137) loss: 0.8160 (0.8141) time: 0.1516 data: 0.0778 max mem: 9390 +Train: [69] [3500/6250] eta: 0:06:22 lr: 0.000029 grad: 0.1173 (0.1136) loss: 0.8149 (0.8141) time: 0.1612 data: 0.0779 max mem: 9390 +Train: [69] [3600/6250] eta: 0:06:09 lr: 0.000029 grad: 0.1105 (0.1136) loss: 0.8129 (0.8141) time: 0.1290 data: 0.0528 max mem: 9390 +Train: [69] [3700/6250] eta: 0:05:55 lr: 0.000029 grad: 0.1057 (0.1136) loss: 0.8186 (0.8141) time: 0.1413 data: 0.0628 max mem: 9390 +Train: [69] [3800/6250] eta: 0:05:42 lr: 0.000029 grad: 0.1127 (0.1136) loss: 0.8067 (0.8141) time: 0.1807 data: 0.0988 max mem: 9390 +Train: [69] [3900/6250] eta: 0:05:28 lr: 0.000029 grad: 0.1153 (0.1137) loss: 0.8163 (0.8140) time: 0.1186 data: 0.0323 max mem: 9390 +Train: [69] [4000/6250] eta: 0:05:14 lr: 0.000029 grad: 0.1079 (0.1137) loss: 0.8152 (0.8141) time: 0.1664 data: 0.0918 max mem: 9390 +Train: [69] [4100/6250] eta: 0:04:59 lr: 0.000029 grad: 0.1060 (0.1136) loss: 0.8199 (0.8142) time: 0.1236 data: 0.0387 max mem: 9390 +Train: [69] [4200/6250] eta: 0:04:44 lr: 0.000029 grad: 0.1142 (0.1136) loss: 0.8135 (0.8142) time: 0.1354 data: 0.0516 max mem: 9390 +Train: [69] [4300/6250] eta: 0:04:30 lr: 0.000029 grad: 0.1126 (0.1136) loss: 0.8111 (0.8143) time: 0.1168 data: 0.0360 max mem: 9390 +Train: [69] [4400/6250] eta: 0:04:15 lr: 0.000029 grad: 0.1063 (0.1135) loss: 0.8172 (0.8143) time: 0.1356 data: 0.0567 max mem: 9390 +Train: [69] [4500/6250] eta: 0:04:01 lr: 0.000029 grad: 0.1103 (0.1134) loss: 0.8217 (0.8144) time: 0.1024 data: 0.0247 max mem: 9390 +Train: [69] [4600/6250] eta: 0:03:47 lr: 0.000029 grad: 0.1123 (0.1134) loss: 0.8153 (0.8145) time: 0.1194 data: 0.0415 max mem: 9390 +Train: [69] [4700/6250] eta: 0:03:33 lr: 0.000029 grad: 0.1086 (0.1133) loss: 0.8100 (0.8145) time: 0.1297 data: 0.0525 max mem: 9390 +Train: [69] [4800/6250] eta: 0:03:18 lr: 0.000029 grad: 0.1104 (0.1132) loss: 0.8179 (0.8146) time: 0.1189 data: 0.0392 max mem: 9390 +Train: [69] [4900/6250] eta: 0:03:04 lr: 0.000029 grad: 0.1072 (0.1132) loss: 0.8102 (0.8146) time: 0.1214 data: 0.0403 max mem: 9390 +Train: [69] [5000/6250] eta: 0:02:50 lr: 0.000029 grad: 0.1109 (0.1131) loss: 0.8161 (0.8146) time: 0.1352 data: 0.0603 max mem: 9390 +Train: [69] [5100/6250] eta: 0:02:37 lr: 0.000029 grad: 0.1112 (0.1130) loss: 0.8134 (0.8147) time: 0.1036 data: 0.0247 max mem: 9390 +Train: [69] [5200/6250] eta: 0:02:23 lr: 0.000029 grad: 0.1072 (0.1130) loss: 0.8189 (0.8147) time: 0.1135 data: 0.0307 max mem: 9390 +Train: [69] [5300/6250] eta: 0:02:09 lr: 0.000029 grad: 0.1040 (0.1130) loss: 0.8199 (0.8147) time: 0.1266 data: 0.0479 max mem: 9390 +Train: [69] [5400/6250] eta: 0:01:55 lr: 0.000029 grad: 0.1105 (0.1129) loss: 0.8145 (0.8148) time: 0.1412 data: 0.0553 max mem: 9390 +Train: [69] [5500/6250] eta: 0:01:41 lr: 0.000029 grad: 0.1147 (0.1129) loss: 0.8123 (0.8148) time: 0.1435 data: 0.0645 max mem: 9390 +Train: [69] [5600/6250] eta: 0:01:28 lr: 0.000028 grad: 0.1065 (0.1128) loss: 0.8155 (0.8148) time: 0.2022 data: 0.1241 max mem: 9390 +Train: [69] [5700/6250] eta: 0:01:14 lr: 0.000028 grad: 0.1078 (0.1128) loss: 0.8138 (0.8149) time: 0.1440 data: 0.0704 max mem: 9390 +Train: [69] [5800/6250] eta: 0:01:01 lr: 0.000028 grad: 0.1173 (0.1129) loss: 0.8169 (0.8149) time: 0.1181 data: 0.0381 max mem: 9390 +Train: [69] [5900/6250] eta: 0:00:47 lr: 0.000028 grad: 0.1155 (0.1129) loss: 0.8077 (0.8148) time: 0.1434 data: 0.0698 max mem: 9390 +Train: [69] [6000/6250] eta: 0:00:34 lr: 0.000028 grad: 0.1181 (0.1130) loss: 0.8147 (0.8148) time: 0.1115 data: 0.0348 max mem: 9390 +Train: [69] [6100/6250] eta: 0:00:20 lr: 0.000028 grad: 0.1082 (0.1130) loss: 0.8172 (0.8148) time: 0.1214 data: 0.0424 max mem: 9390 +Train: [69] [6200/6250] eta: 0:00:06 lr: 0.000028 grad: 0.1215 (0.1131) loss: 0.8124 (0.8147) time: 0.1338 data: 0.0597 max mem: 9390 +Train: [69] [6249/6250] eta: 0:00:00 lr: 0.000028 grad: 0.1092 (0.1131) loss: 0.8140 (0.8148) time: 0.1394 data: 0.0642 max mem: 9390 +Train: [69] Total time: 0:14:17 (0.1373 s / it) +Averaged stats: lr: 0.000028 grad: 0.1092 (0.1131) loss: 0.8140 (0.8148) +Eval (hcp-train-subset): [69] [ 0/62] eta: 0:04:26 loss: 0.8389 (0.8389) time: 4.2964 data: 4.2624 max mem: 9390 +Eval (hcp-train-subset): [69] [61/62] eta: 0:00:00 loss: 0.8298 (0.8301) time: 0.1163 data: 0.0892 max mem: 9390 +Eval (hcp-train-subset): [69] Total time: 0:00:12 (0.2015 s / it) +Averaged stats (hcp-train-subset): loss: 0.8298 (0.8301) +Making plots (hcp-train-subset): example=58 +Eval (hcp-val): [69] [ 0/62] eta: 0:03:37 loss: 0.8291 (0.8291) time: 3.5064 data: 3.4197 max mem: 9390 +Eval (hcp-val): [69] [61/62] eta: 0:00:00 loss: 0.8321 (0.8317) time: 0.1096 data: 0.0830 max mem: 9390 +Eval (hcp-val): [69] Total time: 0:00:12 (0.2016 s / it) +Averaged stats (hcp-val): loss: 0.8321 (0.8317) +Making plots (hcp-val): example=47 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +Train: [70] [ 0/6250] eta: 10:26:06 lr: 0.000028 grad: 0.1170 (0.1170) loss: 0.8055 (0.8055) time: 6.0106 data: 5.9152 max mem: 9390 +Train: [70] [ 100/6250] eta: 0:19:54 lr: 0.000028 grad: 0.1132 (0.1248) loss: 0.8178 (0.8217) time: 0.1678 data: 0.0747 max mem: 9390 +Train: [70] [ 200/6250] eta: 0:16:41 lr: 0.000028 grad: 0.1262 (0.1240) loss: 0.8172 (0.8160) time: 0.1432 data: 0.0563 max mem: 9390 +Train: [70] [ 300/6250] eta: 0:15:28 lr: 0.000028 grad: 0.1114 (0.1235) loss: 0.8146 (0.8147) time: 0.1466 data: 0.0610 max mem: 9390 +Train: [70] [ 400/6250] eta: 0:14:27 lr: 0.000028 grad: 0.1138 (0.1224) loss: 0.8120 (0.8142) time: 0.1202 data: 0.0363 max mem: 9390 +Train: [70] [ 500/6250] eta: 0:13:42 lr: 0.000028 grad: 0.1164 (0.1214) loss: 0.8109 (0.8140) time: 0.1055 data: 0.0183 max mem: 9390 +Train: [70] [ 600/6250] eta: 0:13:19 lr: 0.000028 grad: 0.1149 (0.1207) loss: 0.8146 (0.8129) time: 0.1119 data: 0.0263 max mem: 9390 +Train: [70] [ 700/6250] eta: 0:12:58 lr: 0.000028 grad: 0.1095 (0.1204) loss: 0.8098 (0.8121) time: 0.1115 data: 0.0220 max mem: 9390 +Train: [70] [ 800/6250] eta: 0:12:36 lr: 0.000028 grad: 0.1073 (0.1197) loss: 0.8074 (0.8119) time: 0.1258 data: 0.0374 max mem: 9390 +Train: [70] [ 900/6250] eta: 0:12:18 lr: 0.000028 grad: 0.1120 (0.1194) loss: 0.8183 (0.8119) time: 0.1367 data: 0.0570 max mem: 9390 +Train: [70] [1000/6250] eta: 0:11:59 lr: 0.000028 grad: 0.1175 (0.1188) loss: 0.8114 (0.8121) time: 0.0994 data: 0.0162 max mem: 9390 +Train: [70] [1100/6250] eta: 0:11:44 lr: 0.000028 grad: 0.1041 (0.1183) loss: 0.8168 (0.8121) time: 0.1349 data: 0.0591 max mem: 9390 +Train: [70] [1200/6250] eta: 0:11:28 lr: 0.000028 grad: 0.1181 (0.1177) loss: 0.8072 (0.8121) time: 0.1150 data: 0.0366 max mem: 9390 +Train: [70] [1300/6250] eta: 0:11:12 lr: 0.000028 grad: 0.1087 (0.1174) loss: 0.8119 (0.8120) time: 0.1134 data: 0.0319 max mem: 9390 +Train: [70] [1400/6250] eta: 0:10:57 lr: 0.000028 grad: 0.1061 (0.1170) loss: 0.8154 (0.8121) time: 0.1337 data: 0.0493 max mem: 9390 +Train: [70] [1500/6250] eta: 0:10:42 lr: 0.000028 grad: 0.1118 (0.1166) loss: 0.8151 (0.8122) time: 0.1331 data: 0.0505 max mem: 9390 +Train: [70] [1600/6250] eta: 0:10:26 lr: 0.000028 grad: 0.1119 (0.1163) loss: 0.8200 (0.8122) time: 0.1303 data: 0.0522 max mem: 9390 +Train: [70] [1700/6250] eta: 0:10:14 lr: 0.000028 grad: 0.1091 (0.1161) loss: 0.8081 (0.8122) time: 0.1494 data: 0.0549 max mem: 9390 +Train: [70] [1800/6250] eta: 0:10:00 lr: 0.000028 grad: 0.1099 (0.1158) loss: 0.8154 (0.8124) time: 0.1309 data: 0.0516 max mem: 9390 +Train: [70] [1900/6250] eta: 0:09:47 lr: 0.000028 grad: 0.1049 (0.1157) loss: 0.8162 (0.8125) time: 0.1386 data: 0.0588 max mem: 9390 +Train: [70] [2000/6250] eta: 0:09:35 lr: 0.000028 grad: 0.1100 (0.1156) loss: 0.8106 (0.8126) time: 0.1491 data: 0.0670 max mem: 9390 +Train: [70] [2100/6250] eta: 0:09:23 lr: 0.000028 grad: 0.1177 (0.1157) loss: 0.8060 (0.8125) time: 0.1549 data: 0.0640 max mem: 9390 +Train: [70] [2200/6250] eta: 0:09:12 lr: 0.000028 grad: 0.1138 (0.1158) loss: 0.8129 (0.8125) time: 0.1534 data: 0.0657 max mem: 9390 +Train: [70] [2300/6250] eta: 0:08:58 lr: 0.000028 grad: 0.1121 (0.1159) loss: 0.8190 (0.8125) time: 0.1287 data: 0.0546 max mem: 9390 +Train: [70] [2400/6250] eta: 0:08:45 lr: 0.000028 grad: 0.1207 (0.1160) loss: 0.8024 (0.8125) time: 0.1257 data: 0.0419 max mem: 9390 +Train: [70] [2500/6250] eta: 0:08:33 lr: 0.000028 grad: 0.1109 (0.1161) loss: 0.8100 (0.8124) time: 0.1618 data: 0.0751 max mem: 9390 +Train: [70] [2600/6250] eta: 0:08:20 lr: 0.000028 grad: 0.1146 (0.1161) loss: 0.8027 (0.8124) time: 0.1444 data: 0.0442 max mem: 9390 +Train: [70] [2700/6250] eta: 0:08:07 lr: 0.000028 grad: 0.1108 (0.1162) loss: 0.8127 (0.8123) time: 0.1408 data: 0.0712 max mem: 9390 +Train: [70] [2800/6250] eta: 0:07:53 lr: 0.000028 grad: 0.1208 (0.1165) loss: 0.8081 (0.8122) time: 0.1341 data: 0.0515 max mem: 9390 +Train: [70] [2900/6250] eta: 0:07:39 lr: 0.000028 grad: 0.1166 (0.1165) loss: 0.8146 (0.8122) time: 0.1478 data: 0.0727 max mem: 9390 +Train: [70] [3000/6250] eta: 0:07:26 lr: 0.000027 grad: 0.1127 (0.1166) loss: 0.8121 (0.8121) time: 0.1002 data: 0.0002 max mem: 9390 +Train: [70] [3100/6250] eta: 0:07:12 lr: 0.000027 grad: 0.1109 (0.1165) loss: 0.8158 (0.8121) time: 0.1344 data: 0.0557 max mem: 9390 +Train: [70] [3200/6250] eta: 0:07:00 lr: 0.000027 grad: 0.1103 (0.1165) loss: 0.8102 (0.8120) time: 0.1791 data: 0.0974 max mem: 9390 +Train: [70] [3300/6250] eta: 0:06:49 lr: 0.000027 grad: 0.1154 (0.1165) loss: 0.8119 (0.8120) time: 0.1464 data: 0.0680 max mem: 9390 +Train: [70] [3400/6250] eta: 0:06:35 lr: 0.000027 grad: 0.1165 (0.1165) loss: 0.8142 (0.8120) time: 0.1295 data: 0.0537 max mem: 9390 +Train: [70] [3500/6250] eta: 0:06:22 lr: 0.000027 grad: 0.1161 (0.1165) loss: 0.8143 (0.8121) time: 0.1755 data: 0.0853 max mem: 9390 +Train: [70] [3600/6250] eta: 0:06:09 lr: 0.000027 grad: 0.1135 (0.1165) loss: 0.8124 (0.8120) time: 0.1432 data: 0.0701 max mem: 9390 +Train: [70] [3700/6250] eta: 0:05:55 lr: 0.000027 grad: 0.1061 (0.1165) loss: 0.8123 (0.8120) time: 0.1406 data: 0.0628 max mem: 9390 +Train: [70] [3800/6250] eta: 0:05:42 lr: 0.000027 grad: 0.1117 (0.1165) loss: 0.8141 (0.8120) time: 0.1300 data: 0.0553 max mem: 9390 +Train: [70] [3900/6250] eta: 0:05:27 lr: 0.000027 grad: 0.1180 (0.1165) loss: 0.8082 (0.8120) time: 0.1272 data: 0.0490 max mem: 9390 +Train: [70] [4000/6250] eta: 0:05:12 lr: 0.000027 grad: 0.1116 (0.1164) loss: 0.8148 (0.8120) time: 0.1167 data: 0.0377 max mem: 9390 +Train: [70] [4100/6250] eta: 0:04:58 lr: 0.000027 grad: 0.1129 (0.1165) loss: 0.8129 (0.8120) time: 0.1390 data: 0.0579 max mem: 9390 +Train: [70] [4200/6250] eta: 0:04:43 lr: 0.000027 grad: 0.1189 (0.1165) loss: 0.8115 (0.8120) time: 0.1416 data: 0.0582 max mem: 9390 +Train: [70] [4300/6250] eta: 0:04:28 lr: 0.000027 grad: 0.1113 (0.1166) loss: 0.8060 (0.8119) time: 0.1223 data: 0.0401 max mem: 9390 +Train: [70] [4400/6250] eta: 0:04:14 lr: 0.000027 grad: 0.1132 (0.1165) loss: 0.8136 (0.8120) time: 0.1122 data: 0.0303 max mem: 9390 +Train: [70] [4500/6250] eta: 0:03:59 lr: 0.000027 grad: 0.1066 (0.1165) loss: 0.8161 (0.8120) time: 0.1379 data: 0.0636 max mem: 9390 +Train: [70] [4600/6250] eta: 0:03:45 lr: 0.000027 grad: 0.1123 (0.1165) loss: 0.8107 (0.8120) time: 0.1387 data: 0.0606 max mem: 9390 +Train: [70] [4700/6250] eta: 0:03:31 lr: 0.000027 grad: 0.1126 (0.1165) loss: 0.8096 (0.8120) time: 0.1232 data: 0.0444 max mem: 9390 +Train: [70] [4800/6250] eta: 0:03:17 lr: 0.000027 grad: 0.1120 (0.1166) loss: 0.8126 (0.8120) time: 0.1282 data: 0.0567 max mem: 9390 +Train: [70] [4900/6250] eta: 0:03:03 lr: 0.000027 grad: 0.1174 (0.1166) loss: 0.8103 (0.8119) time: 0.1022 data: 0.0188 max mem: 9390 +Train: [70] [5000/6250] eta: 0:02:49 lr: 0.000027 grad: 0.1095 (0.1166) loss: 0.8117 (0.8119) time: 0.1210 data: 0.0400 max mem: 9390 +Train: [70] [5100/6250] eta: 0:02:35 lr: 0.000027 grad: 0.1058 (0.1166) loss: 0.8108 (0.8119) time: 0.1168 data: 0.0413 max mem: 9390 +Train: [70] [5200/6250] eta: 0:02:21 lr: 0.000027 grad: 0.1050 (0.1166) loss: 0.8122 (0.8120) time: 0.1057 data: 0.0249 max mem: 9390 +Train: [70] [5300/6250] eta: 0:02:08 lr: 0.000027 grad: 0.1166 (0.1167) loss: 0.8126 (0.8119) time: 0.1151 data: 0.0374 max mem: 9390 +Train: [70] [5400/6250] eta: 0:01:54 lr: 0.000027 grad: 0.1143 (0.1167) loss: 0.8047 (0.8118) time: 0.1444 data: 0.0684 max mem: 9390 +Train: [70] [5500/6250] eta: 0:01:41 lr: 0.000027 grad: 0.1133 (0.1167) loss: 0.8119 (0.8118) time: 0.1502 data: 0.0640 max mem: 9390 +Train: [70] [5600/6250] eta: 0:01:27 lr: 0.000027 grad: 0.1133 (0.1167) loss: 0.8037 (0.8118) time: 0.1455 data: 0.0646 max mem: 9390 +Train: [70] [5700/6250] eta: 0:01:14 lr: 0.000027 grad: 0.1115 (0.1167) loss: 0.8177 (0.8118) time: 0.1541 data: 0.0789 max mem: 9390 +Train: [70] [5800/6250] eta: 0:01:00 lr: 0.000027 grad: 0.1095 (0.1166) loss: 0.8138 (0.8118) time: 0.1071 data: 0.0286 max mem: 9390 +Train: [70] [5900/6250] eta: 0:00:47 lr: 0.000027 grad: 0.1070 (0.1166) loss: 0.8149 (0.8118) time: 0.1591 data: 0.0755 max mem: 9390 +Train: [70] [6000/6250] eta: 0:00:33 lr: 0.000027 grad: 0.1133 (0.1165) loss: 0.8027 (0.8119) time: 0.1321 data: 0.0585 max mem: 9390 +Train: [70] [6100/6250] eta: 0:00:20 lr: 0.000027 grad: 0.1062 (0.1165) loss: 0.8102 (0.8119) time: 0.1192 data: 0.0451 max mem: 9390 +Train: [70] [6200/6250] eta: 0:00:06 lr: 0.000027 grad: 0.1026 (0.1164) loss: 0.8167 (0.8120) time: 0.1490 data: 0.0678 max mem: 9390 +Train: [70] [6249/6250] eta: 0:00:00 lr: 0.000027 grad: 0.1046 (0.1164) loss: 0.8205 (0.8120) time: 0.1219 data: 0.0430 max mem: 9390 +Train: [70] Total time: 0:14:13 (0.1366 s / it) +Averaged stats: lr: 0.000027 grad: 0.1046 (0.1164) loss: 0.8205 (0.8120) +Eval (hcp-train-subset): [70] [ 0/62] eta: 0:03:57 loss: 0.8413 (0.8413) time: 3.8292 data: 3.7695 max mem: 9390 +Eval (hcp-train-subset): [70] [61/62] eta: 0:00:00 loss: 0.8304 (0.8308) time: 0.0711 data: 0.0463 max mem: 9390 +Eval (hcp-train-subset): [70] Total time: 0:00:11 (0.1902 s / it) +Averaged stats (hcp-train-subset): loss: 0.8304 (0.8308) +Eval (hcp-val): [70] [ 0/62] eta: 0:04:13 loss: 0.8277 (0.8277) time: 4.0915 data: 4.0362 max mem: 9390 +Eval (hcp-val): [70] [61/62] eta: 0:00:00 loss: 0.8292 (0.8314) time: 0.1045 data: 0.0798 max mem: 9390 +Eval (hcp-val): [70] Total time: 0:00:11 (0.1911 s / it) +Averaged stats (hcp-val): loss: 0.8292 (0.8314) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +Train: [71] [ 0/6250] eta: 7:31:26 lr: 0.000027 grad: 0.0801 (0.0801) loss: 0.8615 (0.8615) time: 4.3338 data: 4.0893 max mem: 9390 +Train: [71] [ 100/6250] eta: 0:19:53 lr: 0.000027 grad: 0.1118 (0.1371) loss: 0.8296 (0.8326) time: 0.1627 data: 0.0566 max mem: 9390 +Train: [71] [ 200/6250] eta: 0:17:18 lr: 0.000027 grad: 0.1159 (0.1305) loss: 0.8189 (0.8254) time: 0.1433 data: 0.0552 max mem: 9390 +Train: [71] [ 300/6250] eta: 0:15:59 lr: 0.000027 grad: 0.1208 (0.1299) loss: 0.8161 (0.8212) time: 0.1505 data: 0.0740 max mem: 9390 +Train: [71] [ 400/6250] eta: 0:15:03 lr: 0.000026 grad: 0.1127 (0.1285) loss: 0.8133 (0.8190) time: 0.1273 data: 0.0329 max mem: 9390 +Train: [71] [ 500/6250] eta: 0:14:14 lr: 0.000026 grad: 0.1204 (0.1266) loss: 0.8106 (0.8175) time: 0.1242 data: 0.0393 max mem: 9390 +Train: [71] [ 600/6250] eta: 0:13:38 lr: 0.000026 grad: 0.1131 (0.1244) loss: 0.8153 (0.8174) time: 0.1363 data: 0.0562 max mem: 9390 +Train: [71] [ 700/6250] eta: 0:13:11 lr: 0.000026 grad: 0.1112 (0.1229) loss: 0.8134 (0.8172) time: 0.1222 data: 0.0291 max mem: 9390 +Train: [71] [ 800/6250] eta: 0:12:50 lr: 0.000026 grad: 0.1101 (0.1222) loss: 0.8148 (0.8169) time: 0.1256 data: 0.0421 max mem: 9390 +Train: [71] [ 900/6250] eta: 0:12:32 lr: 0.000026 grad: 0.1109 (0.1214) loss: 0.8102 (0.8167) time: 0.1456 data: 0.0608 max mem: 9390 +Train: [71] [1000/6250] eta: 0:12:11 lr: 0.000026 grad: 0.1058 (0.1207) loss: 0.8172 (0.8165) time: 0.1383 data: 0.0578 max mem: 9390 +Train: [71] [1100/6250] eta: 0:11:54 lr: 0.000026 grad: 0.1186 (0.1204) loss: 0.8097 (0.8163) time: 0.1229 data: 0.0432 max mem: 9390 +Train: [71] [1200/6250] eta: 0:11:42 lr: 0.000026 grad: 0.1087 (0.1199) loss: 0.8183 (0.8162) time: 0.1462 data: 0.0609 max mem: 9390 +Train: [71] [1300/6250] eta: 0:11:26 lr: 0.000026 grad: 0.1132 (0.1195) loss: 0.8123 (0.8161) time: 0.1369 data: 0.0524 max mem: 9390 +Train: [71] [1400/6250] eta: 0:11:11 lr: 0.000026 grad: 0.1110 (0.1191) loss: 0.8112 (0.8159) time: 0.1380 data: 0.0630 max mem: 9390 +Train: [71] [1500/6250] eta: 0:10:56 lr: 0.000026 grad: 0.1072 (0.1187) loss: 0.8170 (0.8158) time: 0.1340 data: 0.0601 max mem: 9390 +Train: [71] [1600/6250] eta: 0:10:41 lr: 0.000026 grad: 0.1075 (0.1184) loss: 0.8148 (0.8156) time: 0.1438 data: 0.0565 max mem: 9390 +Train: [71] [1700/6250] eta: 0:10:26 lr: 0.000026 grad: 0.1056 (0.1180) loss: 0.8201 (0.8156) time: 0.1488 data: 0.0710 max mem: 9390 +Train: [71] [1800/6250] eta: 0:10:10 lr: 0.000026 grad: 0.1111 (0.1179) loss: 0.8130 (0.8155) time: 0.1133 data: 0.0293 max mem: 9390 +Train: [71] [1900/6250] eta: 0:09:57 lr: 0.000026 grad: 0.1203 (0.1177) loss: 0.8157 (0.8155) time: 0.1379 data: 0.0528 max mem: 9390 +Train: [71] [2000/6250] eta: 0:09:45 lr: 0.000026 grad: 0.1140 (0.1177) loss: 0.8127 (0.8154) time: 0.1320 data: 0.0499 max mem: 9390 +Train: [71] [2100/6250] eta: 0:09:29 lr: 0.000026 grad: 0.1172 (0.1177) loss: 0.8130 (0.8153) time: 0.1121 data: 0.0286 max mem: 9390 +Train: [71] [2200/6250] eta: 0:09:14 lr: 0.000026 grad: 0.1158 (0.1177) loss: 0.8174 (0.8152) time: 0.1297 data: 0.0475 max mem: 9390 +Train: [71] [2300/6250] eta: 0:09:01 lr: 0.000026 grad: 0.1162 (0.1176) loss: 0.8128 (0.8152) time: 0.1679 data: 0.0885 max mem: 9390 +Train: [71] [2400/6250] eta: 0:08:48 lr: 0.000026 grad: 0.1140 (0.1176) loss: 0.8173 (0.8151) time: 0.1146 data: 0.0342 max mem: 9390 +Train: [71] [2500/6250] eta: 0:08:36 lr: 0.000026 grad: 0.1111 (0.1175) loss: 0.8188 (0.8151) time: 0.1444 data: 0.0569 max mem: 9390 +Train: [71] [2600/6250] eta: 0:08:23 lr: 0.000026 grad: 0.1138 (0.1174) loss: 0.8148 (0.8152) time: 0.1440 data: 0.0659 max mem: 9390 +Train: [71] [2700/6250] eta: 0:08:08 lr: 0.000026 grad: 0.1102 (0.1174) loss: 0.8179 (0.8151) time: 0.1333 data: 0.0515 max mem: 9390 +Train: [71] [2800/6250] eta: 0:07:54 lr: 0.000026 grad: 0.1270 (0.1174) loss: 0.8078 (0.8151) time: 0.1484 data: 0.0684 max mem: 9390 +Train: [71] [2900/6250] eta: 0:07:41 lr: 0.000026 grad: 0.1171 (0.1174) loss: 0.8170 (0.8151) time: 0.1207 data: 0.0344 max mem: 9390 +Train: [71] [3000/6250] eta: 0:07:26 lr: 0.000026 grad: 0.1155 (0.1175) loss: 0.8186 (0.8150) time: 0.1216 data: 0.0383 max mem: 9390 +Train: [71] [3100/6250] eta: 0:07:13 lr: 0.000026 grad: 0.1156 (0.1174) loss: 0.8145 (0.8149) time: 0.1452 data: 0.0619 max mem: 9390 +Train: [71] [3200/6250] eta: 0:06:59 lr: 0.000026 grad: 0.1156 (0.1175) loss: 0.8127 (0.8149) time: 0.1549 data: 0.0753 max mem: 9390 +Train: [71] [3300/6250] eta: 0:06:45 lr: 0.000026 grad: 0.1144 (0.1174) loss: 0.8149 (0.8149) time: 0.1232 data: 0.0481 max mem: 9390 +Train: [71] [3400/6250] eta: 0:06:32 lr: 0.000026 grad: 0.1145 (0.1175) loss: 0.8120 (0.8149) time: 0.1974 data: 0.1251 max mem: 9390 +Train: [71] [3500/6250] eta: 0:06:21 lr: 0.000026 grad: 0.1134 (0.1175) loss: 0.8162 (0.8149) time: 0.1265 data: 0.0553 max mem: 9390 +Train: [71] [3600/6250] eta: 0:06:07 lr: 0.000026 grad: 0.1161 (0.1176) loss: 0.8113 (0.8148) time: 0.1313 data: 0.0500 max mem: 9390 +Train: [71] [3700/6250] eta: 0:05:54 lr: 0.000026 grad: 0.1172 (0.1175) loss: 0.8154 (0.8148) time: 0.1578 data: 0.0690 max mem: 9390 +Train: [71] [3800/6250] eta: 0:05:40 lr: 0.000026 grad: 0.1068 (0.1175) loss: 0.8148 (0.8148) time: 0.1260 data: 0.0484 max mem: 9390 +Train: [71] [3900/6250] eta: 0:05:26 lr: 0.000026 grad: 0.1138 (0.1174) loss: 0.8123 (0.8148) time: 0.1245 data: 0.0446 max mem: 9390 +Train: [71] [4000/6250] eta: 0:05:12 lr: 0.000026 grad: 0.1175 (0.1174) loss: 0.8172 (0.8148) time: 0.1328 data: 0.0538 max mem: 9390 +Train: [71] [4100/6250] eta: 0:04:57 lr: 0.000026 grad: 0.1156 (0.1174) loss: 0.8168 (0.8148) time: 0.1305 data: 0.0536 max mem: 9390 +Train: [71] [4200/6250] eta: 0:04:43 lr: 0.000025 grad: 0.1165 (0.1174) loss: 0.8077 (0.8147) time: 0.1378 data: 0.0566 max mem: 9390 +Train: [71] [4300/6250] eta: 0:04:28 lr: 0.000025 grad: 0.1143 (0.1174) loss: 0.8170 (0.8147) time: 0.1129 data: 0.0318 max mem: 9390 +Train: [71] [4400/6250] eta: 0:04:14 lr: 0.000025 grad: 0.1159 (0.1174) loss: 0.8137 (0.8146) time: 0.1194 data: 0.0408 max mem: 9390 +Train: [71] [4500/6250] eta: 0:03:59 lr: 0.000025 grad: 0.1232 (0.1176) loss: 0.8165 (0.8146) time: 0.1244 data: 0.0480 max mem: 9390 +Train: [71] [4600/6250] eta: 0:03:46 lr: 0.000025 grad: 0.1177 (0.1177) loss: 0.8170 (0.8145) time: 0.1571 data: 0.0756 max mem: 9390 +Train: [71] [4700/6250] eta: 0:03:33 lr: 0.000025 grad: 0.1215 (0.1178) loss: 0.8112 (0.8144) time: 0.1665 data: 0.0884 max mem: 9390 +Train: [71] [4800/6250] eta: 0:03:19 lr: 0.000025 grad: 0.1181 (0.1180) loss: 0.8111 (0.8143) time: 0.1323 data: 0.0553 max mem: 9390 +Train: [71] [4900/6250] eta: 0:03:05 lr: 0.000025 grad: 0.1167 (0.1182) loss: 0.8090 (0.8141) time: 0.1231 data: 0.0424 max mem: 9390 +Train: [71] [5000/6250] eta: 0:02:51 lr: 0.000025 grad: 0.1137 (0.1183) loss: 0.8067 (0.8140) time: 0.1291 data: 0.0544 max mem: 9390 +Train: [71] [5100/6250] eta: 0:02:37 lr: 0.000025 grad: 0.1135 (0.1184) loss: 0.8089 (0.8139) time: 0.1396 data: 0.0513 max mem: 9390 +Train: [71] [5200/6250] eta: 0:02:23 lr: 0.000025 grad: 0.1169 (0.1186) loss: 0.8046 (0.8138) time: 0.1355 data: 0.0512 max mem: 9390 +Train: [71] [5300/6250] eta: 0:02:10 lr: 0.000025 grad: 0.1213 (0.1187) loss: 0.8086 (0.8137) time: 0.1280 data: 0.0465 max mem: 9390 +Train: [71] [5400/6250] eta: 0:01:56 lr: 0.000025 grad: 0.1220 (0.1188) loss: 0.8089 (0.8136) time: 0.1574 data: 0.0811 max mem: 9390 +Train: [71] [5500/6250] eta: 0:01:42 lr: 0.000025 grad: 0.1248 (0.1188) loss: 0.8081 (0.8136) time: 0.1375 data: 0.0586 max mem: 9390 +Train: [71] [5600/6250] eta: 0:01:29 lr: 0.000025 grad: 0.1154 (0.1188) loss: 0.8118 (0.8135) time: 0.1324 data: 0.0438 max mem: 9390 +Train: [71] [5700/6250] eta: 0:01:15 lr: 0.000025 grad: 0.1135 (0.1188) loss: 0.8144 (0.8135) time: 0.1343 data: 0.0565 max mem: 9390 +Train: [71] [5800/6250] eta: 0:01:01 lr: 0.000025 grad: 0.1244 (0.1189) loss: 0.8095 (0.8135) time: 0.1373 data: 0.0599 max mem: 9390 +Train: [71] [5900/6250] eta: 0:00:47 lr: 0.000025 grad: 0.1128 (0.1189) loss: 0.8116 (0.8134) time: 0.1300 data: 0.0545 max mem: 9390 +Train: [71] [6000/6250] eta: 0:00:34 lr: 0.000025 grad: 0.1170 (0.1189) loss: 0.8126 (0.8134) time: 0.1355 data: 0.0451 max mem: 9390 +Train: [71] [6100/6250] eta: 0:00:20 lr: 0.000025 grad: 0.1173 (0.1189) loss: 0.8147 (0.8134) time: 0.1304 data: 0.0534 max mem: 9390 +Train: [71] [6200/6250] eta: 0:00:06 lr: 0.000025 grad: 0.1150 (0.1189) loss: 0.8124 (0.8133) time: 0.1548 data: 0.0768 max mem: 9390 +Train: [71] [6249/6250] eta: 0:00:00 lr: 0.000025 grad: 0.1267 (0.1190) loss: 0.8139 (0.8133) time: 0.1215 data: 0.0472 max mem: 9390 +Train: [71] Total time: 0:14:19 (0.1376 s / it) +Averaged stats: lr: 0.000025 grad: 0.1267 (0.1190) loss: 0.8139 (0.8133) +Eval (hcp-train-subset): [71] [ 0/62] eta: 0:04:06 loss: 0.8381 (0.8381) time: 3.9688 data: 3.8941 max mem: 9390 +Eval (hcp-train-subset): [71] [61/62] eta: 0:00:00 loss: 0.8291 (0.8284) time: 0.1246 data: 0.0938 max mem: 9390 +Eval (hcp-train-subset): [71] Total time: 0:00:12 (0.1986 s / it) +Averaged stats (hcp-train-subset): loss: 0.8291 (0.8284) +Eval (hcp-val): [71] [ 0/62] eta: 0:03:27 loss: 0.8310 (0.8310) time: 3.3534 data: 3.2890 max mem: 9390 +Eval (hcp-val): [71] [61/62] eta: 0:00:00 loss: 0.8302 (0.8313) time: 0.0826 data: 0.0575 max mem: 9390 +Eval (hcp-val): [71] Total time: 0:00:11 (0.1893 s / it) +Averaged stats (hcp-val): loss: 0.8302 (0.8313) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +Train: [72] [ 0/6250] eta: 9:19:05 lr: 0.000025 grad: 0.0990 (0.0990) loss: 0.8546 (0.8546) time: 5.3672 data: 5.2385 max mem: 9390 +Train: [72] [ 100/6250] eta: 0:19:52 lr: 0.000025 grad: 0.1115 (0.1409) loss: 0.8226 (0.8249) time: 0.1387 data: 0.0499 max mem: 9390 +Train: [72] [ 200/6250] eta: 0:16:55 lr: 0.000025 grad: 0.1120 (0.1293) loss: 0.8196 (0.8229) time: 0.1471 data: 0.0678 max mem: 9390 +Train: [72] [ 300/6250] eta: 0:15:38 lr: 0.000025 grad: 0.1085 (0.1253) loss: 0.8231 (0.8213) time: 0.1346 data: 0.0541 max mem: 9390 +Train: [72] [ 400/6250] eta: 0:14:34 lr: 0.000025 grad: 0.1122 (0.1236) loss: 0.8126 (0.8203) time: 0.1297 data: 0.0503 max mem: 9390 +Train: [72] [ 500/6250] eta: 0:13:45 lr: 0.000025 grad: 0.1064 (0.1228) loss: 0.8202 (0.8197) time: 0.1199 data: 0.0354 max mem: 9390 +Train: [72] [ 600/6250] eta: 0:13:13 lr: 0.000025 grad: 0.1103 (0.1219) loss: 0.8159 (0.8195) time: 0.1301 data: 0.0468 max mem: 9390 +Train: [72] [ 700/6250] eta: 0:12:48 lr: 0.000025 grad: 0.1081 (0.1207) loss: 0.8205 (0.8194) time: 0.1274 data: 0.0329 max mem: 9390 +Train: [72] [ 800/6250] eta: 0:12:22 lr: 0.000025 grad: 0.1090 (0.1197) loss: 0.8119 (0.8195) time: 0.1269 data: 0.0387 max mem: 9390 +Train: [72] [ 900/6250] eta: 0:12:03 lr: 0.000025 grad: 0.1180 (0.1192) loss: 0.8224 (0.8193) time: 0.1179 data: 0.0391 max mem: 9390 +Train: [72] [1000/6250] eta: 0:11:45 lr: 0.000025 grad: 0.1144 (0.1189) loss: 0.8171 (0.8192) time: 0.1226 data: 0.0443 max mem: 9390 +Train: [72] [1100/6250] eta: 0:11:32 lr: 0.000025 grad: 0.1123 (0.1187) loss: 0.8129 (0.8191) time: 0.1348 data: 0.0570 max mem: 9390 +Train: [72] [1200/6250] eta: 0:11:13 lr: 0.000025 grad: 0.1083 (0.1183) loss: 0.8156 (0.8189) time: 0.1170 data: 0.0317 max mem: 9390 +Train: [72] [1300/6250] eta: 0:10:56 lr: 0.000025 grad: 0.1123 (0.1178) loss: 0.8174 (0.8189) time: 0.1274 data: 0.0474 max mem: 9390 +Train: [72] [1400/6250] eta: 0:10:42 lr: 0.000025 grad: 0.1149 (0.1178) loss: 0.8140 (0.8185) time: 0.1457 data: 0.0596 max mem: 9390 +Train: [72] [1500/6250] eta: 0:10:31 lr: 0.000025 grad: 0.1144 (0.1175) loss: 0.8148 (0.8183) time: 0.1198 data: 0.0450 max mem: 9390 +Train: [72] [1600/6250] eta: 0:10:17 lr: 0.000025 grad: 0.1132 (0.1174) loss: 0.8133 (0.8180) time: 0.1155 data: 0.0382 max mem: 9390 +Train: [72] [1700/6250] eta: 0:10:03 lr: 0.000024 grad: 0.1150 (0.1173) loss: 0.8133 (0.8179) time: 0.1467 data: 0.0635 max mem: 9390 +Train: [72] [1800/6250] eta: 0:09:49 lr: 0.000024 grad: 0.1084 (0.1172) loss: 0.8132 (0.8177) time: 0.1134 data: 0.0385 max mem: 9390 +Train: [72] [1900/6250] eta: 0:09:37 lr: 0.000024 grad: 0.1088 (0.1170) loss: 0.8160 (0.8176) time: 0.1289 data: 0.0493 max mem: 9390 +Train: [72] [2000/6250] eta: 0:09:25 lr: 0.000024 grad: 0.1221 (0.1169) loss: 0.8101 (0.8175) time: 0.1342 data: 0.0552 max mem: 9390 +Train: [72] [2100/6250] eta: 0:09:12 lr: 0.000024 grad: 0.1117 (0.1168) loss: 0.8111 (0.8174) time: 0.1508 data: 0.0598 max mem: 9390 +Train: [72] [2200/6250] eta: 0:09:02 lr: 0.000024 grad: 0.1185 (0.1168) loss: 0.8141 (0.8172) time: 0.1276 data: 0.0424 max mem: 9390 +Train: [72] [2300/6250] eta: 0:08:49 lr: 0.000024 grad: 0.1175 (0.1168) loss: 0.8071 (0.8169) time: 0.1266 data: 0.0421 max mem: 9390 +Train: [72] [2400/6250] eta: 0:08:35 lr: 0.000024 grad: 0.1149 (0.1169) loss: 0.8125 (0.8167) time: 0.1326 data: 0.0557 max mem: 9390 +Train: [72] [2500/6250] eta: 0:08:21 lr: 0.000024 grad: 0.1194 (0.1170) loss: 0.8071 (0.8165) time: 0.1352 data: 0.0553 max mem: 9390 +Train: [72] [2600/6250] eta: 0:08:08 lr: 0.000024 grad: 0.1133 (0.1171) loss: 0.8118 (0.8162) time: 0.1388 data: 0.0579 max mem: 9390 +Train: [72] [2700/6250] eta: 0:07:55 lr: 0.000024 grad: 0.1169 (0.1171) loss: 0.8051 (0.8160) time: 0.1380 data: 0.0540 max mem: 9390 +Train: [72] [2800/6250] eta: 0:07:41 lr: 0.000024 grad: 0.1146 (0.1172) loss: 0.8066 (0.8158) time: 0.1256 data: 0.0455 max mem: 9390 +Train: [72] [2900/6250] eta: 0:07:28 lr: 0.000024 grad: 0.1102 (0.1173) loss: 0.8138 (0.8156) time: 0.1436 data: 0.0671 max mem: 9390 +Train: [72] [3000/6250] eta: 0:07:15 lr: 0.000024 grad: 0.1168 (0.1173) loss: 0.8069 (0.8154) time: 0.1343 data: 0.0413 max mem: 9390 +Train: [72] [3100/6250] eta: 0:07:03 lr: 0.000024 grad: 0.1158 (0.1173) loss: 0.8105 (0.8152) time: 0.1446 data: 0.0708 max mem: 9390 +Train: [72] [3200/6250] eta: 0:06:49 lr: 0.000024 grad: 0.1234 (0.1175) loss: 0.8022 (0.8149) time: 0.1131 data: 0.0331 max mem: 9390 +Train: [72] [3300/6250] eta: 0:06:35 lr: 0.000024 grad: 0.1165 (0.1176) loss: 0.8129 (0.8148) time: 0.1336 data: 0.0569 max mem: 9390 +Train: [72] [3400/6250] eta: 0:06:22 lr: 0.000024 grad: 0.1104 (0.1176) loss: 0.8131 (0.8146) time: 0.1303 data: 0.0488 max mem: 9390 +Train: [72] [3500/6250] eta: 0:06:09 lr: 0.000024 grad: 0.1187 (0.1178) loss: 0.8121 (0.8145) time: 0.1393 data: 0.0614 max mem: 9390 +Train: [72] [3600/6250] eta: 0:05:57 lr: 0.000024 grad: 0.1135 (0.1178) loss: 0.8114 (0.8144) time: 0.1369 data: 0.0578 max mem: 9390 +Train: [72] [3700/6250] eta: 0:05:44 lr: 0.000024 grad: 0.1106 (0.1177) loss: 0.8113 (0.8143) time: 0.1757 data: 0.0863 max mem: 9390 +Train: [72] [3800/6250] eta: 0:05:30 lr: 0.000024 grad: 0.1099 (0.1177) loss: 0.8165 (0.8143) time: 0.1422 data: 0.0662 max mem: 9390 +Train: [72] [3900/6250] eta: 0:05:18 lr: 0.000024 grad: 0.1093 (0.1177) loss: 0.8128 (0.8143) time: 0.1654 data: 0.0847 max mem: 9390 +Train: [72] [4000/6250] eta: 0:05:05 lr: 0.000024 grad: 0.1206 (0.1178) loss: 0.8064 (0.8142) time: 0.1743 data: 0.0989 max mem: 9390 +Train: [72] [4100/6250] eta: 0:04:52 lr: 0.000024 grad: 0.1154 (0.1178) loss: 0.8117 (0.8142) time: 0.1453 data: 0.0651 max mem: 9390 +Train: [72] [4200/6250] eta: 0:04:38 lr: 0.000024 grad: 0.1098 (0.1177) loss: 0.8166 (0.8142) time: 0.1399 data: 0.0617 max mem: 9390 +Train: [72] [4300/6250] eta: 0:04:24 lr: 0.000024 grad: 0.1075 (0.1177) loss: 0.8174 (0.8142) time: 0.1032 data: 0.0250 max mem: 9390 +Train: [72] [4400/6250] eta: 0:04:10 lr: 0.000024 grad: 0.1201 (0.1176) loss: 0.8148 (0.8143) time: 0.1372 data: 0.0580 max mem: 9390 +Train: [72] [4500/6250] eta: 0:03:56 lr: 0.000024 grad: 0.1144 (0.1176) loss: 0.8131 (0.8143) time: 0.1199 data: 0.0333 max mem: 9390 +Train: [72] [4600/6250] eta: 0:03:41 lr: 0.000024 grad: 0.1129 (0.1177) loss: 0.8160 (0.8144) time: 0.1267 data: 0.0433 max mem: 9390 +Train: [72] [4700/6250] eta: 0:03:27 lr: 0.000024 grad: 0.1104 (0.1176) loss: 0.8156 (0.8144) time: 0.1117 data: 0.0280 max mem: 9390 +Train: [72] [4800/6250] eta: 0:03:13 lr: 0.000024 grad: 0.1199 (0.1176) loss: 0.8159 (0.8144) time: 0.1144 data: 0.0374 max mem: 9390 +Train: [72] [4900/6250] eta: 0:03:00 lr: 0.000024 grad: 0.1182 (0.1176) loss: 0.8096 (0.8144) time: 0.1291 data: 0.0458 max mem: 9390 +Train: [72] [5000/6250] eta: 0:02:46 lr: 0.000024 grad: 0.1161 (0.1176) loss: 0.8109 (0.8144) time: 0.1226 data: 0.0445 max mem: 9390 +Train: [72] [5100/6250] eta: 0:02:32 lr: 0.000024 grad: 0.1093 (0.1176) loss: 0.8185 (0.8145) time: 0.1238 data: 0.0443 max mem: 9390 +Train: [72] [5200/6250] eta: 0:02:19 lr: 0.000024 grad: 0.1138 (0.1176) loss: 0.8123 (0.8144) time: 0.1241 data: 0.0456 max mem: 9390 +Train: [72] [5300/6250] eta: 0:02:05 lr: 0.000024 grad: 0.1134 (0.1176) loss: 0.8188 (0.8144) time: 0.1203 data: 0.0417 max mem: 9390 +Train: [72] [5400/6250] eta: 0:01:52 lr: 0.000024 grad: 0.1142 (0.1176) loss: 0.8144 (0.8145) time: 0.1255 data: 0.0427 max mem: 9390 +Train: [72] [5500/6250] eta: 0:01:39 lr: 0.000023 grad: 0.1098 (0.1176) loss: 0.8161 (0.8145) time: 0.1537 data: 0.0724 max mem: 9390 +Train: [72] [5600/6250] eta: 0:01:26 lr: 0.000023 grad: 0.1097 (0.1175) loss: 0.8193 (0.8146) time: 0.1474 data: 0.0667 max mem: 9390 +Train: [72] [5700/6250] eta: 0:01:12 lr: 0.000023 grad: 0.1188 (0.1175) loss: 0.8141 (0.8147) time: 0.1159 data: 0.0360 max mem: 9390 +Train: [72] [5800/6250] eta: 0:00:59 lr: 0.000023 grad: 0.1161 (0.1175) loss: 0.8208 (0.8147) time: 0.1381 data: 0.0606 max mem: 9390 +Train: [72] [5900/6250] eta: 0:00:46 lr: 0.000023 grad: 0.1119 (0.1174) loss: 0.8190 (0.8148) time: 0.1103 data: 0.0222 max mem: 9390 +Train: [72] [6000/6250] eta: 0:00:33 lr: 0.000023 grad: 0.1124 (0.1174) loss: 0.8125 (0.8148) time: 0.1517 data: 0.0600 max mem: 9390 +Train: [72] [6100/6250] eta: 0:00:19 lr: 0.000023 grad: 0.1192 (0.1175) loss: 0.8181 (0.8148) time: 0.1382 data: 0.0599 max mem: 9390 +Train: [72] [6200/6250] eta: 0:00:06 lr: 0.000023 grad: 0.1253 (0.1175) loss: 0.8158 (0.8148) time: 0.1184 data: 0.0426 max mem: 9390 +Train: [72] [6249/6250] eta: 0:00:00 lr: 0.000023 grad: 0.1146 (0.1175) loss: 0.8175 (0.8148) time: 0.1348 data: 0.0538 max mem: 9390 +Train: [72] Total time: 0:13:55 (0.1337 s / it) +Averaged stats: lr: 0.000023 grad: 0.1146 (0.1175) loss: 0.8175 (0.8148) +Eval (hcp-train-subset): [72] [ 0/62] eta: 0:05:05 loss: 0.8365 (0.8365) time: 4.9194 data: 4.8887 max mem: 9390 +Eval (hcp-train-subset): [72] [61/62] eta: 0:00:00 loss: 0.8252 (0.8256) time: 0.1210 data: 0.0945 max mem: 9390 +Eval (hcp-train-subset): [72] Total time: 0:00:12 (0.2000 s / it) +Averaged stats (hcp-train-subset): loss: 0.8252 (0.8256) +Eval (hcp-val): [72] [ 0/62] eta: 0:03:30 loss: 0.8252 (0.8252) time: 3.3938 data: 3.3287 max mem: 9390 +Eval (hcp-val): [72] [61/62] eta: 0:00:00 loss: 0.8304 (0.8311) time: 0.1108 data: 0.0858 max mem: 9390 +Eval (hcp-val): [72] Total time: 0:00:12 (0.1974 s / it) +Averaged stats (hcp-val): loss: 0.8304 (0.8311) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +Train: [73] [ 0/6250] eta: 7:47:19 lr: 0.000023 grad: 0.0868 (0.0868) loss: 0.8594 (0.8594) time: 4.4864 data: 4.2146 max mem: 9390 +Train: [73] [ 100/6250] eta: 0:19:39 lr: 0.000023 grad: 0.1257 (0.1380) loss: 0.8208 (0.8371) time: 0.1506 data: 0.0596 max mem: 9390 +Train: [73] [ 200/6250] eta: 0:16:43 lr: 0.000023 grad: 0.1243 (0.1328) loss: 0.8266 (0.8289) time: 0.1375 data: 0.0488 max mem: 9390 +Train: [73] [ 300/6250] eta: 0:15:31 lr: 0.000023 grad: 0.1121 (0.1304) loss: 0.8088 (0.8241) time: 0.1312 data: 0.0468 max mem: 9390 +Train: [73] [ 400/6250] eta: 0:14:34 lr: 0.000023 grad: 0.1286 (0.1298) loss: 0.8080 (0.8203) time: 0.1155 data: 0.0282 max mem: 9390 +Train: [73] [ 500/6250] eta: 0:13:51 lr: 0.000023 grad: 0.1280 (0.1289) loss: 0.8071 (0.8178) time: 0.1286 data: 0.0438 max mem: 9390 +Train: [73] [ 600/6250] eta: 0:13:12 lr: 0.000023 grad: 0.1137 (0.1281) loss: 0.8113 (0.8166) time: 0.1141 data: 0.0182 max mem: 9390 +Train: [73] [ 700/6250] eta: 0:12:41 lr: 0.000023 grad: 0.1189 (0.1272) loss: 0.8112 (0.8158) time: 0.1247 data: 0.0415 max mem: 9390 +Train: [73] [ 800/6250] eta: 0:12:14 lr: 0.000023 grad: 0.1137 (0.1265) loss: 0.8164 (0.8153) time: 0.1195 data: 0.0312 max mem: 9390 +Train: [73] [ 900/6250] eta: 0:11:55 lr: 0.000023 grad: 0.1203 (0.1255) loss: 0.8068 (0.8151) time: 0.1333 data: 0.0482 max mem: 9390 +Train: [73] [1000/6250] eta: 0:11:35 lr: 0.000023 grad: 0.1182 (0.1251) loss: 0.8106 (0.8149) time: 0.1243 data: 0.0444 max mem: 9390 +Train: [73] [1100/6250] eta: 0:11:18 lr: 0.000023 grad: 0.1147 (0.1247) loss: 0.8128 (0.8145) time: 0.1288 data: 0.0506 max mem: 9390 +Train: [73] [1200/6250] eta: 0:11:05 lr: 0.000023 grad: 0.1141 (0.1242) loss: 0.8092 (0.8143) time: 0.1684 data: 0.0933 max mem: 9390 +Train: [73] [1300/6250] eta: 0:10:46 lr: 0.000023 grad: 0.1190 (0.1240) loss: 0.8092 (0.8140) time: 0.1169 data: 0.0323 max mem: 9390 +Train: [73] [1400/6250] eta: 0:10:36 lr: 0.000023 grad: 0.1251 (0.1240) loss: 0.8077 (0.8136) time: 0.1367 data: 0.0595 max mem: 9390 +Train: [73] [1500/6250] eta: 0:10:21 lr: 0.000023 grad: 0.1210 (0.1239) loss: 0.8130 (0.8132) time: 0.1299 data: 0.0500 max mem: 9390 +Train: [73] [1600/6250] eta: 0:10:09 lr: 0.000023 grad: 0.1201 (0.1240) loss: 0.8110 (0.8129) time: 0.1400 data: 0.0614 max mem: 9390 +Train: [73] [1700/6250] eta: 0:09:56 lr: 0.000023 grad: 0.1136 (0.1238) loss: 0.8136 (0.8126) time: 0.1306 data: 0.0509 max mem: 9390 +Train: [73] [1800/6250] eta: 0:09:43 lr: 0.000023 grad: 0.1181 (0.1239) loss: 0.8073 (0.8123) time: 0.0867 data: 0.0002 max mem: 9390 +Train: [73] [1900/6250] eta: 0:09:31 lr: 0.000023 grad: 0.1197 (0.1238) loss: 0.8093 (0.8122) time: 0.1325 data: 0.0599 max mem: 9390 +Train: [73] [2000/6250] eta: 0:09:20 lr: 0.000023 grad: 0.1152 (0.1236) loss: 0.8065 (0.8121) time: 0.0812 data: 0.0034 max mem: 9390 +Train: [73] [2100/6250] eta: 0:09:09 lr: 0.000023 grad: 0.1165 (0.1236) loss: 0.8066 (0.8120) time: 0.1320 data: 0.0478 max mem: 9390 +Train: [73] [2200/6250] eta: 0:08:56 lr: 0.000023 grad: 0.1159 (0.1235) loss: 0.8182 (0.8120) time: 0.1277 data: 0.0514 max mem: 9390 +Train: [73] [2300/6250] eta: 0:08:43 lr: 0.000023 grad: 0.1211 (0.1235) loss: 0.8130 (0.8119) time: 0.1548 data: 0.0764 max mem: 9390 +Train: [73] [2400/6250] eta: 0:08:30 lr: 0.000023 grad: 0.1254 (0.1233) loss: 0.8096 (0.8118) time: 0.1280 data: 0.0482 max mem: 9390 +Train: [73] [2500/6250] eta: 0:08:17 lr: 0.000023 grad: 0.1151 (0.1230) loss: 0.8058 (0.8118) time: 0.1487 data: 0.0702 max mem: 9390 +Train: [73] [2600/6250] eta: 0:08:04 lr: 0.000023 grad: 0.1159 (0.1228) loss: 0.8143 (0.8118) time: 0.1281 data: 0.0506 max mem: 9390 +Train: [73] [2700/6250] eta: 0:07:52 lr: 0.000023 grad: 0.1169 (0.1226) loss: 0.8069 (0.8119) time: 0.1364 data: 0.0594 max mem: 9390 +Train: [73] [2800/6250] eta: 0:07:41 lr: 0.000023 grad: 0.1196 (0.1225) loss: 0.8108 (0.8119) time: 0.1603 data: 0.0763 max mem: 9390 +Train: [73] [2900/6250] eta: 0:07:28 lr: 0.000023 grad: 0.1262 (0.1224) loss: 0.8062 (0.8119) time: 0.1201 data: 0.0352 max mem: 9390 +Train: [73] [3000/6250] eta: 0:07:16 lr: 0.000023 grad: 0.1153 (0.1223) loss: 0.8139 (0.8120) time: 0.1394 data: 0.0602 max mem: 9390 +Train: [73] [3100/6250] eta: 0:07:03 lr: 0.000023 grad: 0.1230 (0.1224) loss: 0.8044 (0.8119) time: 0.1334 data: 0.0606 max mem: 9390 +Train: [73] [3200/6250] eta: 0:06:50 lr: 0.000022 grad: 0.1153 (0.1223) loss: 0.8060 (0.8120) time: 0.1461 data: 0.0674 max mem: 9390 +Train: [73] [3300/6250] eta: 0:06:38 lr: 0.000022 grad: 0.1262 (0.1222) loss: 0.8076 (0.8120) time: 0.1712 data: 0.0905 max mem: 9390 +Train: [73] [3400/6250] eta: 0:06:24 lr: 0.000022 grad: 0.1170 (0.1222) loss: 0.8117 (0.8120) time: 0.1231 data: 0.0473 max mem: 9390 +Train: [73] [3500/6250] eta: 0:06:12 lr: 0.000022 grad: 0.1134 (0.1221) loss: 0.8058 (0.8119) time: 0.1483 data: 0.0675 max mem: 9390 +Train: [73] [3600/6250] eta: 0:05:58 lr: 0.000022 grad: 0.1182 (0.1221) loss: 0.8086 (0.8119) time: 0.1495 data: 0.0618 max mem: 9390 +Train: [73] [3700/6250] eta: 0:05:46 lr: 0.000022 grad: 0.1199 (0.1220) loss: 0.8097 (0.8119) time: 0.1761 data: 0.1000 max mem: 9390 +Train: [73] [3800/6250] eta: 0:05:33 lr: 0.000022 grad: 0.1194 (0.1220) loss: 0.8160 (0.8120) time: 0.1211 data: 0.0436 max mem: 9390 +Train: [73] [3900/6250] eta: 0:05:20 lr: 0.000022 grad: 0.1154 (0.1220) loss: 0.8156 (0.8120) time: 0.1443 data: 0.0644 max mem: 9390 +Train: [73] [4000/6250] eta: 0:05:07 lr: 0.000022 grad: 0.1211 (0.1219) loss: 0.8064 (0.8119) time: 0.1274 data: 0.0486 max mem: 9390 +Train: [73] [4100/6250] eta: 0:04:54 lr: 0.000022 grad: 0.1249 (0.1219) loss: 0.8063 (0.8119) time: 0.1648 data: 0.0748 max mem: 9390 +Train: [73] [4200/6250] eta: 0:04:41 lr: 0.000022 grad: 0.1182 (0.1219) loss: 0.8153 (0.8119) time: 0.1533 data: 0.0732 max mem: 9390 +Train: [73] [4300/6250] eta: 0:04:27 lr: 0.000022 grad: 0.1140 (0.1220) loss: 0.8109 (0.8118) time: 0.1383 data: 0.0639 max mem: 9390 +Train: [73] [4400/6250] eta: 0:04:13 lr: 0.000022 grad: 0.1129 (0.1219) loss: 0.8098 (0.8118) time: 0.1183 data: 0.0352 max mem: 9390 +Train: [73] [4500/6250] eta: 0:03:59 lr: 0.000022 grad: 0.1193 (0.1219) loss: 0.8149 (0.8119) time: 0.1118 data: 0.0356 max mem: 9390 +Train: [73] [4600/6250] eta: 0:03:45 lr: 0.000022 grad: 0.1145 (0.1219) loss: 0.8108 (0.8118) time: 0.1223 data: 0.0353 max mem: 9390 +Train: [73] [4700/6250] eta: 0:03:30 lr: 0.000022 grad: 0.1224 (0.1220) loss: 0.8070 (0.8118) time: 0.1147 data: 0.0360 max mem: 9390 +Train: [73] [4800/6250] eta: 0:03:16 lr: 0.000022 grad: 0.1191 (0.1220) loss: 0.8121 (0.8118) time: 0.1089 data: 0.0270 max mem: 9390 +Train: [73] [4900/6250] eta: 0:03:02 lr: 0.000022 grad: 0.1258 (0.1220) loss: 0.8113 (0.8117) time: 0.1310 data: 0.0455 max mem: 9390 +Train: [73] [5000/6250] eta: 0:02:48 lr: 0.000022 grad: 0.1146 (0.1220) loss: 0.8112 (0.8117) time: 0.1106 data: 0.0306 max mem: 9390 +Train: [73] [5100/6250] eta: 0:02:34 lr: 0.000022 grad: 0.1271 (0.1220) loss: 0.8027 (0.8116) time: 0.1334 data: 0.0547 max mem: 9390 +Train: [73] [5200/6250] eta: 0:02:20 lr: 0.000022 grad: 0.1190 (0.1221) loss: 0.8033 (0.8115) time: 0.0860 data: 0.0002 max mem: 9390 +Train: [73] [5300/6250] eta: 0:02:07 lr: 0.000022 grad: 0.1232 (0.1222) loss: 0.8052 (0.8114) time: 0.1352 data: 0.0608 max mem: 9390 +Train: [73] [5400/6250] eta: 0:01:53 lr: 0.000022 grad: 0.1200 (0.1222) loss: 0.8099 (0.8113) time: 0.1287 data: 0.0439 max mem: 9390 +Train: [73] [5500/6250] eta: 0:01:40 lr: 0.000022 grad: 0.1271 (0.1223) loss: 0.8003 (0.8112) time: 0.1225 data: 0.0394 max mem: 9390 +Train: [73] [5600/6250] eta: 0:01:26 lr: 0.000022 grad: 0.1187 (0.1224) loss: 0.8106 (0.8110) time: 0.1615 data: 0.0797 max mem: 9390 +Train: [73] [5700/6250] eta: 0:01:13 lr: 0.000022 grad: 0.1274 (0.1225) loss: 0.7998 (0.8109) time: 0.1353 data: 0.0560 max mem: 9390 +Train: [73] [5800/6250] eta: 0:01:00 lr: 0.000022 grad: 0.1145 (0.1226) loss: 0.8098 (0.8109) time: 0.1274 data: 0.0494 max mem: 9390 +Train: [73] [5900/6250] eta: 0:00:46 lr: 0.000022 grad: 0.1191 (0.1225) loss: 0.8034 (0.8108) time: 0.1251 data: 0.0456 max mem: 9390 +Train: [73] [6000/6250] eta: 0:00:33 lr: 0.000022 grad: 0.1189 (0.1225) loss: 0.8052 (0.8108) time: 0.1338 data: 0.0623 max mem: 9390 +Train: [73] [6100/6250] eta: 0:00:20 lr: 0.000022 grad: 0.1249 (0.1225) loss: 0.8094 (0.8108) time: 0.1519 data: 0.0718 max mem: 9390 +Train: [73] [6200/6250] eta: 0:00:06 lr: 0.000022 grad: 0.1237 (0.1226) loss: 0.8130 (0.8108) time: 0.1373 data: 0.0543 max mem: 9390 +Train: [73] [6249/6250] eta: 0:00:00 lr: 0.000022 grad: 0.1230 (0.1227) loss: 0.8071 (0.8108) time: 0.1430 data: 0.0448 max mem: 9390 +Train: [73] Total time: 0:14:04 (0.1351 s / it) +Averaged stats: lr: 0.000022 grad: 0.1230 (0.1227) loss: 0.8071 (0.8108) +Eval (hcp-train-subset): [73] [ 0/62] eta: 0:03:05 loss: 0.8400 (0.8400) time: 2.9892 data: 2.9151 max mem: 9390 +Eval (hcp-train-subset): [73] [61/62] eta: 0:00:00 loss: 0.8239 (0.8264) time: 0.1153 data: 0.0904 max mem: 9390 +Eval (hcp-train-subset): [73] Total time: 0:00:11 (0.1834 s / it) +Averaged stats (hcp-train-subset): loss: 0.8239 (0.8264) +Eval (hcp-val): [73] [ 0/62] eta: 0:05:21 loss: 0.8283 (0.8283) time: 5.1859 data: 5.1572 max mem: 9390 +Eval (hcp-val): [73] [61/62] eta: 0:00:00 loss: 0.8298 (0.8313) time: 0.1119 data: 0.0855 max mem: 9390 +Eval (hcp-val): [73] Total time: 0:00:11 (0.1906 s / it) +Averaged stats (hcp-val): loss: 0.8298 (0.8313) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +Train: [74] [ 0/6250] eta: 8:35:59 lr: 0.000022 grad: 0.1686 (0.1686) loss: 0.8543 (0.8543) time: 4.9535 data: 4.7749 max mem: 9390 +Train: [74] [ 100/6250] eta: 0:19:45 lr: 0.000022 grad: 0.1200 (0.1444) loss: 0.8134 (0.8174) time: 0.1419 data: 0.0523 max mem: 9390 +Train: [74] [ 200/6250] eta: 0:16:42 lr: 0.000022 grad: 0.1145 (0.1333) loss: 0.8224 (0.8188) time: 0.1381 data: 0.0454 max mem: 9390 +Train: [74] [ 300/6250] eta: 0:15:46 lr: 0.000022 grad: 0.1182 (0.1305) loss: 0.8183 (0.8186) time: 0.1518 data: 0.0699 max mem: 9390 +Train: [74] [ 400/6250] eta: 0:15:01 lr: 0.000022 grad: 0.1094 (0.1280) loss: 0.8197 (0.8183) time: 0.1364 data: 0.0500 max mem: 9390 +Train: [74] [ 500/6250] eta: 0:14:18 lr: 0.000022 grad: 0.1102 (0.1257) loss: 0.8234 (0.8183) time: 0.1334 data: 0.0496 max mem: 9390 +Train: [74] [ 600/6250] eta: 0:13:39 lr: 0.000022 grad: 0.1178 (0.1234) loss: 0.8175 (0.8187) time: 0.1321 data: 0.0540 max mem: 9390 +Train: [74] [ 700/6250] eta: 0:13:06 lr: 0.000022 grad: 0.1078 (0.1221) loss: 0.8180 (0.8187) time: 0.1248 data: 0.0459 max mem: 9390 +Train: [74] [ 800/6250] eta: 0:12:39 lr: 0.000022 grad: 0.1131 (0.1208) loss: 0.8185 (0.8187) time: 0.1308 data: 0.0505 max mem: 9390 +Train: [74] [ 900/6250] eta: 0:12:11 lr: 0.000021 grad: 0.1078 (0.1201) loss: 0.8247 (0.8189) time: 0.1131 data: 0.0276 max mem: 9390 +Train: [74] [1000/6250] eta: 0:11:50 lr: 0.000021 grad: 0.1158 (0.1196) loss: 0.8231 (0.8192) time: 0.1117 data: 0.0347 max mem: 9390 +Train: [74] [1100/6250] eta: 0:11:31 lr: 0.000021 grad: 0.1160 (0.1192) loss: 0.8164 (0.8192) time: 0.1248 data: 0.0497 max mem: 9390 +Train: [74] [1200/6250] eta: 0:11:15 lr: 0.000021 grad: 0.1170 (0.1189) loss: 0.8187 (0.8192) time: 0.1120 data: 0.0322 max mem: 9390 +Train: [74] [1300/6250] eta: 0:11:00 lr: 0.000021 grad: 0.1107 (0.1188) loss: 0.8192 (0.8191) time: 0.1292 data: 0.0513 max mem: 9390 +Train: [74] [1400/6250] eta: 0:10:46 lr: 0.000021 grad: 0.1161 (0.1186) loss: 0.8140 (0.8191) time: 0.1193 data: 0.0385 max mem: 9390 +Train: [74] [1500/6250] eta: 0:10:35 lr: 0.000021 grad: 0.1137 (0.1183) loss: 0.8226 (0.8191) time: 0.1560 data: 0.0777 max mem: 9390 +Train: [74] [1600/6250] eta: 0:10:19 lr: 0.000021 grad: 0.1117 (0.1181) loss: 0.8174 (0.8191) time: 0.1310 data: 0.0571 max mem: 9390 +Train: [74] [1700/6250] eta: 0:10:05 lr: 0.000021 grad: 0.1107 (0.1180) loss: 0.8192 (0.8191) time: 0.1383 data: 0.0602 max mem: 9390 +Train: [74] [1800/6250] eta: 0:09:52 lr: 0.000021 grad: 0.1107 (0.1179) loss: 0.8196 (0.8190) time: 0.1417 data: 0.0487 max mem: 9390 +Train: [74] [1900/6250] eta: 0:09:41 lr: 0.000021 grad: 0.1124 (0.1179) loss: 0.8157 (0.8189) time: 0.1120 data: 0.0312 max mem: 9390 +Train: [74] [2000/6250] eta: 0:09:28 lr: 0.000021 grad: 0.1178 (0.1180) loss: 0.8190 (0.8188) time: 0.1509 data: 0.0611 max mem: 9390 +Train: [74] [2100/6250] eta: 0:09:16 lr: 0.000021 grad: 0.1165 (0.1182) loss: 0.8138 (0.8186) time: 0.1007 data: 0.0192 max mem: 9390 +Train: [74] [2200/6250] eta: 0:09:01 lr: 0.000021 grad: 0.1172 (0.1182) loss: 0.8092 (0.8184) time: 0.1202 data: 0.0434 max mem: 9390 +Train: [74] [2300/6250] eta: 0:08:47 lr: 0.000021 grad: 0.1189 (0.1184) loss: 0.8111 (0.8183) time: 0.1317 data: 0.0529 max mem: 9390 +Train: [74] [2400/6250] eta: 0:08:34 lr: 0.000021 grad: 0.1175 (0.1184) loss: 0.8145 (0.8182) time: 0.1442 data: 0.0502 max mem: 9390 +Train: [74] [2500/6250] eta: 0:08:20 lr: 0.000021 grad: 0.1155 (0.1184) loss: 0.8089 (0.8180) time: 0.1363 data: 0.0599 max mem: 9390 +Train: [74] [2600/6250] eta: 0:08:06 lr: 0.000021 grad: 0.1166 (0.1185) loss: 0.8161 (0.8179) time: 0.1307 data: 0.0420 max mem: 9390 +Train: [74] [2700/6250] eta: 0:07:54 lr: 0.000021 grad: 0.1187 (0.1186) loss: 0.8118 (0.8177) time: 0.1422 data: 0.0697 max mem: 9390 +Train: [74] [2800/6250] eta: 0:07:41 lr: 0.000021 grad: 0.1128 (0.1186) loss: 0.8174 (0.8176) time: 0.1431 data: 0.0618 max mem: 9390 +Train: [74] [2900/6250] eta: 0:07:29 lr: 0.000021 grad: 0.1157 (0.1186) loss: 0.8126 (0.8175) time: 0.1255 data: 0.0375 max mem: 9390 +Train: [74] [3000/6250] eta: 0:07:16 lr: 0.000021 grad: 0.1210 (0.1186) loss: 0.8099 (0.8174) time: 0.1541 data: 0.0782 max mem: 9390 +Train: [74] [3100/6250] eta: 0:07:03 lr: 0.000021 grad: 0.1167 (0.1187) loss: 0.8130 (0.8173) time: 0.1356 data: 0.0565 max mem: 9390 +Train: [74] [3200/6250] eta: 0:06:49 lr: 0.000021 grad: 0.1108 (0.1187) loss: 0.8140 (0.8172) time: 0.1197 data: 0.0406 max mem: 9390 +Train: [74] [3300/6250] eta: 0:06:35 lr: 0.000021 grad: 0.1169 (0.1187) loss: 0.8166 (0.8171) time: 0.1338 data: 0.0544 max mem: 9390 +Train: [74] [3400/6250] eta: 0:06:22 lr: 0.000021 grad: 0.1194 (0.1187) loss: 0.8096 (0.8169) time: 0.1254 data: 0.0264 max mem: 9390 +Train: [74] [3500/6250] eta: 0:06:09 lr: 0.000021 grad: 0.1165 (0.1188) loss: 0.8039 (0.8167) time: 0.1340 data: 0.0510 max mem: 9390 +Train: [74] [3600/6250] eta: 0:05:56 lr: 0.000021 grad: 0.1210 (0.1188) loss: 0.8164 (0.8166) time: 0.1198 data: 0.0442 max mem: 9390 +Train: [74] [3700/6250] eta: 0:05:42 lr: 0.000021 grad: 0.1162 (0.1188) loss: 0.8110 (0.8165) time: 0.1271 data: 0.0465 max mem: 9390 +Train: [74] [3800/6250] eta: 0:05:30 lr: 0.000021 grad: 0.1198 (0.1189) loss: 0.8178 (0.8165) time: 0.1464 data: 0.0594 max mem: 9390 +Train: [74] [3900/6250] eta: 0:05:17 lr: 0.000021 grad: 0.1278 (0.1191) loss: 0.8111 (0.8164) time: 0.1365 data: 0.0586 max mem: 9390 +Train: [74] [4000/6250] eta: 0:05:04 lr: 0.000021 grad: 0.1183 (0.1191) loss: 0.8147 (0.8164) time: 0.1612 data: 0.0713 max mem: 9390 +Train: [74] [4100/6250] eta: 0:04:52 lr: 0.000021 grad: 0.1185 (0.1192) loss: 0.8127 (0.8163) time: 0.1484 data: 0.0670 max mem: 9390 +Train: [74] [4200/6250] eta: 0:04:38 lr: 0.000021 grad: 0.1208 (0.1193) loss: 0.8184 (0.8163) time: 0.1225 data: 0.0467 max mem: 9390 +Train: [74] [4300/6250] eta: 0:04:25 lr: 0.000021 grad: 0.1194 (0.1195) loss: 0.8118 (0.8161) time: 0.1384 data: 0.0622 max mem: 9390 +Train: [74] [4400/6250] eta: 0:04:11 lr: 0.000021 grad: 0.1291 (0.1197) loss: 0.8083 (0.8160) time: 0.1277 data: 0.0488 max mem: 9390 +Train: [74] [4500/6250] eta: 0:03:57 lr: 0.000021 grad: 0.1193 (0.1198) loss: 0.8158 (0.8159) time: 0.1075 data: 0.0238 max mem: 9390 +Train: [74] [4600/6250] eta: 0:03:43 lr: 0.000021 grad: 0.1153 (0.1199) loss: 0.8075 (0.8158) time: 0.1232 data: 0.0426 max mem: 9390 +Train: [74] [4700/6250] eta: 0:03:28 lr: 0.000021 grad: 0.1120 (0.1199) loss: 0.8161 (0.8157) time: 0.1135 data: 0.0265 max mem: 9390 +Train: [74] [4800/6250] eta: 0:03:14 lr: 0.000021 grad: 0.1239 (0.1200) loss: 0.8143 (0.8156) time: 0.1166 data: 0.0395 max mem: 9390 +Train: [74] [4900/6250] eta: 0:03:00 lr: 0.000020 grad: 0.1213 (0.1200) loss: 0.8153 (0.8156) time: 0.1042 data: 0.0226 max mem: 9390 +Train: [74] [5000/6250] eta: 0:02:46 lr: 0.000020 grad: 0.1230 (0.1201) loss: 0.8139 (0.8155) time: 0.1023 data: 0.0229 max mem: 9390 +Train: [74] [5100/6250] eta: 0:02:33 lr: 0.000020 grad: 0.1186 (0.1202) loss: 0.8118 (0.8155) time: 0.1018 data: 0.0195 max mem: 9390 +Train: [74] [5200/6250] eta: 0:02:19 lr: 0.000020 grad: 0.1190 (0.1202) loss: 0.8125 (0.8155) time: 0.1212 data: 0.0351 max mem: 9390 +Train: [74] [5300/6250] eta: 0:02:06 lr: 0.000020 grad: 0.1134 (0.1202) loss: 0.8145 (0.8154) time: 0.1274 data: 0.0503 max mem: 9390 +Train: [74] [5400/6250] eta: 0:01:52 lr: 0.000020 grad: 0.1232 (0.1203) loss: 0.8169 (0.8154) time: 0.1051 data: 0.0162 max mem: 9390 +Train: [74] [5500/6250] eta: 0:01:39 lr: 0.000020 grad: 0.1191 (0.1203) loss: 0.8133 (0.8154) time: 0.1351 data: 0.0556 max mem: 9390 +Train: [74] [5600/6250] eta: 0:01:25 lr: 0.000020 grad: 0.1282 (0.1203) loss: 0.8084 (0.8153) time: 0.1571 data: 0.0750 max mem: 9390 +Train: [74] [5700/6250] eta: 0:01:12 lr: 0.000020 grad: 0.1212 (0.1204) loss: 0.8057 (0.8153) time: 0.1559 data: 0.0841 max mem: 9390 +Train: [74] [5800/6250] eta: 0:00:59 lr: 0.000020 grad: 0.1168 (0.1204) loss: 0.8125 (0.8152) time: 0.1791 data: 0.0919 max mem: 9390 +Train: [74] [5900/6250] eta: 0:00:46 lr: 0.000020 grad: 0.1213 (0.1204) loss: 0.8103 (0.8152) time: 0.1337 data: 0.0584 max mem: 9390 +Train: [74] [6000/6250] eta: 0:00:33 lr: 0.000020 grad: 0.1196 (0.1205) loss: 0.8143 (0.8151) time: 0.1137 data: 0.0305 max mem: 9390 +Train: [74] [6100/6250] eta: 0:00:19 lr: 0.000020 grad: 0.1219 (0.1206) loss: 0.8131 (0.8150) time: 0.1470 data: 0.0644 max mem: 9390 +Train: [74] [6200/6250] eta: 0:00:06 lr: 0.000020 grad: 0.1141 (0.1206) loss: 0.8135 (0.8149) time: 0.1480 data: 0.0637 max mem: 9390 +Train: [74] [6249/6250] eta: 0:00:00 lr: 0.000020 grad: 0.1116 (0.1206) loss: 0.8195 (0.8149) time: 0.1211 data: 0.0462 max mem: 9390 +Train: [74] Total time: 0:13:58 (0.1342 s / it) +Averaged stats: lr: 0.000020 grad: 0.1116 (0.1206) loss: 0.8195 (0.8149) +Eval (hcp-train-subset): [74] [ 0/62] eta: 0:04:41 loss: 0.8333 (0.8333) time: 4.5452 data: 4.4822 max mem: 9390 +Eval (hcp-train-subset): [74] [61/62] eta: 0:00:00 loss: 0.8243 (0.8258) time: 0.1082 data: 0.0832 max mem: 9390 +Eval (hcp-train-subset): [74] Total time: 0:00:12 (0.2088 s / it) +Averaged stats (hcp-train-subset): loss: 0.8243 (0.8258) +Making plots (hcp-train-subset): example=29 +Eval (hcp-val): [74] [ 0/62] eta: 0:03:24 loss: 0.8336 (0.8336) time: 3.2925 data: 3.2244 max mem: 9390 +Eval (hcp-val): [74] [61/62] eta: 0:00:00 loss: 0.8299 (0.8310) time: 0.1118 data: 0.0854 max mem: 9390 +Eval (hcp-val): [74] Total time: 0:00:12 (0.2082 s / it) +Averaged stats (hcp-val): loss: 0.8299 (0.8310) +Making plots (hcp-val): example=14 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +Train: [75] [ 0/6250] eta: 7:57:16 lr: 0.000020 grad: 0.0710 (0.0710) loss: 0.8696 (0.8696) time: 4.5818 data: 4.2378 max mem: 9390 +Train: [75] [ 100/6250] eta: 0:19:16 lr: 0.000020 grad: 0.1352 (0.1425) loss: 0.8099 (0.8227) time: 0.1520 data: 0.0539 max mem: 9390 +Train: [75] [ 200/6250] eta: 0:16:58 lr: 0.000020 grad: 0.1254 (0.1403) loss: 0.8181 (0.8190) time: 0.1540 data: 0.0669 max mem: 9390 +Train: [75] [ 300/6250] eta: 0:15:38 lr: 0.000020 grad: 0.1218 (0.1369) loss: 0.8133 (0.8174) time: 0.1328 data: 0.0491 max mem: 9390 +Train: [75] [ 400/6250] eta: 0:14:42 lr: 0.000020 grad: 0.1232 (0.1345) loss: 0.8195 (0.8167) time: 0.1320 data: 0.0449 max mem: 9390 +Train: [75] [ 500/6250] eta: 0:14:00 lr: 0.000020 grad: 0.1221 (0.1325) loss: 0.8180 (0.8170) time: 0.1381 data: 0.0565 max mem: 9390 +Train: [75] [ 600/6250] eta: 0:13:21 lr: 0.000020 grad: 0.1111 (0.1306) loss: 0.8208 (0.8172) time: 0.1308 data: 0.0489 max mem: 9390 +Train: [75] [ 700/6250] eta: 0:12:48 lr: 0.000020 grad: 0.1141 (0.1284) loss: 0.8124 (0.8175) time: 0.1230 data: 0.0435 max mem: 9390 +Train: [75] [ 800/6250] eta: 0:12:21 lr: 0.000020 grad: 0.1148 (0.1268) loss: 0.8180 (0.8176) time: 0.1287 data: 0.0454 max mem: 9390 +Train: [75] [ 900/6250] eta: 0:12:00 lr: 0.000020 grad: 0.1119 (0.1252) loss: 0.8103 (0.8176) time: 0.1209 data: 0.0410 max mem: 9390 +Train: [75] [1000/6250] eta: 0:11:48 lr: 0.000020 grad: 0.1102 (0.1240) loss: 0.8144 (0.8177) time: 0.1306 data: 0.0475 max mem: 9390 +Train: [75] [1100/6250] eta: 0:11:35 lr: 0.000020 grad: 0.1089 (0.1232) loss: 0.8198 (0.8177) time: 0.1057 data: 0.0209 max mem: 9390 +Train: [75] [1200/6250] eta: 0:11:20 lr: 0.000020 grad: 0.1135 (0.1226) loss: 0.8161 (0.8177) time: 0.1109 data: 0.0390 max mem: 9390 +Train: [75] [1300/6250] eta: 0:11:07 lr: 0.000020 grad: 0.1116 (0.1221) loss: 0.8162 (0.8173) time: 0.1337 data: 0.0550 max mem: 9390 +Train: [75] [1400/6250] eta: 0:10:58 lr: 0.000020 grad: 0.1186 (0.1220) loss: 0.8198 (0.8171) time: 0.1040 data: 0.0211 max mem: 9390 +Train: [75] [1500/6250] eta: 0:10:42 lr: 0.000020 grad: 0.1128 (0.1216) loss: 0.8160 (0.8168) time: 0.1364 data: 0.0517 max mem: 9390 +Train: [75] [1600/6250] eta: 0:10:28 lr: 0.000020 grad: 0.1165 (0.1214) loss: 0.8080 (0.8165) time: 0.1431 data: 0.0612 max mem: 9390 +Train: [75] [1700/6250] eta: 0:10:16 lr: 0.000020 grad: 0.1106 (0.1213) loss: 0.8182 (0.8162) time: 0.1351 data: 0.0597 max mem: 9390 +Train: [75] [1800/6250] eta: 0:10:02 lr: 0.000020 grad: 0.1155 (0.1212) loss: 0.8171 (0.8160) time: 0.1387 data: 0.0612 max mem: 9390 +Train: [75] [1900/6250] eta: 0:09:52 lr: 0.000020 grad: 0.1139 (0.1212) loss: 0.8079 (0.8158) time: 0.1909 data: 0.0990 max mem: 9390 +Train: [75] [2000/6250] eta: 0:09:37 lr: 0.000020 grad: 0.1176 (0.1211) loss: 0.8079 (0.8156) time: 0.1409 data: 0.0622 max mem: 9390 +Train: [75] [2100/6250] eta: 0:09:23 lr: 0.000020 grad: 0.1118 (0.1212) loss: 0.8045 (0.8154) time: 0.1338 data: 0.0520 max mem: 9390 +Train: [75] [2200/6250] eta: 0:09:10 lr: 0.000020 grad: 0.1175 (0.1213) loss: 0.8147 (0.8152) time: 0.1258 data: 0.0369 max mem: 9390 +Train: [75] [2300/6250] eta: 0:08:56 lr: 0.000020 grad: 0.1187 (0.1213) loss: 0.8163 (0.8150) time: 0.1375 data: 0.0618 max mem: 9390 +Train: [75] [2400/6250] eta: 0:08:42 lr: 0.000020 grad: 0.1183 (0.1214) loss: 0.8150 (0.8148) time: 0.1339 data: 0.0573 max mem: 9390 +Train: [75] [2500/6250] eta: 0:08:28 lr: 0.000020 grad: 0.1190 (0.1215) loss: 0.8090 (0.8147) time: 0.1371 data: 0.0633 max mem: 9390 +Train: [75] [2600/6250] eta: 0:08:14 lr: 0.000020 grad: 0.1267 (0.1216) loss: 0.8148 (0.8146) time: 0.1399 data: 0.0634 max mem: 9390 +Train: [75] [2700/6250] eta: 0:08:00 lr: 0.000020 grad: 0.1231 (0.1216) loss: 0.8080 (0.8144) time: 0.1156 data: 0.0355 max mem: 9390 +Train: [75] [2800/6250] eta: 0:07:46 lr: 0.000019 grad: 0.1168 (0.1216) loss: 0.8117 (0.8143) time: 0.1423 data: 0.0518 max mem: 9390 +Train: [75] [2900/6250] eta: 0:07:33 lr: 0.000019 grad: 0.1197 (0.1216) loss: 0.8053 (0.8142) time: 0.1521 data: 0.0666 max mem: 9390 +Train: [75] [3000/6250] eta: 0:07:21 lr: 0.000019 grad: 0.1192 (0.1216) loss: 0.8141 (0.8141) time: 0.1395 data: 0.0628 max mem: 9390 +Train: [75] [3100/6250] eta: 0:07:07 lr: 0.000019 grad: 0.1237 (0.1218) loss: 0.8083 (0.8140) time: 0.1265 data: 0.0488 max mem: 9390 +Train: [75] [3200/6250] eta: 0:06:53 lr: 0.000019 grad: 0.1265 (0.1219) loss: 0.8135 (0.8139) time: 0.1337 data: 0.0555 max mem: 9390 +Train: [75] [3300/6250] eta: 0:06:39 lr: 0.000019 grad: 0.1202 (0.1219) loss: 0.8117 (0.8139) time: 0.1223 data: 0.0444 max mem: 9390 +Train: [75] [3400/6250] eta: 0:06:25 lr: 0.000019 grad: 0.1192 (0.1220) loss: 0.8116 (0.8138) time: 0.1281 data: 0.0466 max mem: 9390 +Train: [75] [3500/6250] eta: 0:06:11 lr: 0.000019 grad: 0.1160 (0.1221) loss: 0.8047 (0.8137) time: 0.1509 data: 0.0750 max mem: 9390 +Train: [75] [3600/6250] eta: 0:05:57 lr: 0.000019 grad: 0.1220 (0.1223) loss: 0.8182 (0.8136) time: 0.1131 data: 0.0370 max mem: 9390 +Train: [75] [3700/6250] eta: 0:05:43 lr: 0.000019 grad: 0.1207 (0.1223) loss: 0.8020 (0.8136) time: 0.1350 data: 0.0586 max mem: 9390 +Train: [75] [3800/6250] eta: 0:05:31 lr: 0.000019 grad: 0.1166 (0.1224) loss: 0.8129 (0.8135) time: 0.1923 data: 0.1240 max mem: 9390 +Train: [75] [3900/6250] eta: 0:05:18 lr: 0.000019 grad: 0.1201 (0.1224) loss: 0.8094 (0.8134) time: 0.1555 data: 0.0717 max mem: 9390 +Train: [75] [4000/6250] eta: 0:05:05 lr: 0.000019 grad: 0.1250 (0.1224) loss: 0.8126 (0.8134) time: 0.1443 data: 0.0685 max mem: 9390 +Train: [75] [4100/6250] eta: 0:04:52 lr: 0.000019 grad: 0.1142 (0.1224) loss: 0.8147 (0.8134) time: 0.1534 data: 0.0704 max mem: 9390 +Train: [75] [4200/6250] eta: 0:04:39 lr: 0.000019 grad: 0.1189 (0.1224) loss: 0.8111 (0.8134) time: 0.1314 data: 0.0500 max mem: 9390 +Train: [75] [4300/6250] eta: 0:04:25 lr: 0.000019 grad: 0.1156 (0.1223) loss: 0.8176 (0.8134) time: 0.1422 data: 0.0652 max mem: 9390 +Train: [75] [4400/6250] eta: 0:04:11 lr: 0.000019 grad: 0.1151 (0.1223) loss: 0.8139 (0.8134) time: 0.1249 data: 0.0426 max mem: 9390 +Train: [75] [4500/6250] eta: 0:03:57 lr: 0.000019 grad: 0.1188 (0.1223) loss: 0.8155 (0.8134) time: 0.1271 data: 0.0491 max mem: 9390 +Train: [75] [4600/6250] eta: 0:03:43 lr: 0.000019 grad: 0.1192 (0.1223) loss: 0.8169 (0.8134) time: 0.1077 data: 0.0336 max mem: 9390 +Train: [75] [4700/6250] eta: 0:03:29 lr: 0.000019 grad: 0.1206 (0.1223) loss: 0.8142 (0.8134) time: 0.1193 data: 0.0461 max mem: 9390 +Train: [75] [4800/6250] eta: 0:03:15 lr: 0.000019 grad: 0.1238 (0.1223) loss: 0.8110 (0.8134) time: 0.0985 data: 0.0141 max mem: 9390 +Train: [75] [4900/6250] eta: 0:03:01 lr: 0.000019 grad: 0.1194 (0.1223) loss: 0.8087 (0.8134) time: 0.1245 data: 0.0435 max mem: 9390 +Train: [75] [5000/6250] eta: 0:02:47 lr: 0.000019 grad: 0.1225 (0.1223) loss: 0.8056 (0.8134) time: 0.1082 data: 0.0317 max mem: 9390 +Train: [75] [5100/6250] eta: 0:02:33 lr: 0.000019 grad: 0.1208 (0.1222) loss: 0.8111 (0.8134) time: 0.1203 data: 0.0395 max mem: 9390 +Train: [75] [5200/6250] eta: 0:02:20 lr: 0.000019 grad: 0.1163 (0.1222) loss: 0.8182 (0.8134) time: 0.1249 data: 0.0442 max mem: 9390 +Train: [75] [5300/6250] eta: 0:02:06 lr: 0.000019 grad: 0.1212 (0.1222) loss: 0.8099 (0.8134) time: 0.1433 data: 0.0668 max mem: 9390 +Train: [75] [5400/6250] eta: 0:01:52 lr: 0.000019 grad: 0.1233 (0.1222) loss: 0.8112 (0.8135) time: 0.1194 data: 0.0332 max mem: 9390 +Train: [75] [5500/6250] eta: 0:01:39 lr: 0.000019 grad: 0.1084 (0.1222) loss: 0.8184 (0.8135) time: 0.1097 data: 0.0246 max mem: 9390 +Train: [75] [5600/6250] eta: 0:01:25 lr: 0.000019 grad: 0.1209 (0.1222) loss: 0.8124 (0.8135) time: 0.1265 data: 0.0407 max mem: 9390 +Train: [75] [5700/6250] eta: 0:01:12 lr: 0.000019 grad: 0.1249 (0.1223) loss: 0.8071 (0.8135) time: 0.1108 data: 0.0332 max mem: 9390 +Train: [75] [5800/6250] eta: 0:00:59 lr: 0.000019 grad: 0.1156 (0.1223) loss: 0.8162 (0.8135) time: 0.1113 data: 0.0298 max mem: 9390 +Train: [75] [5900/6250] eta: 0:00:46 lr: 0.000019 grad: 0.1284 (0.1224) loss: 0.8107 (0.8136) time: 0.1286 data: 0.0459 max mem: 9390 +Train: [75] [6000/6250] eta: 0:00:32 lr: 0.000019 grad: 0.1237 (0.1226) loss: 0.8159 (0.8136) time: 0.1431 data: 0.0563 max mem: 9390 +Train: [75] [6100/6250] eta: 0:00:19 lr: 0.000019 grad: 0.1244 (0.1226) loss: 0.8151 (0.8136) time: 0.1205 data: 0.0388 max mem: 9390 +Train: [75] [6200/6250] eta: 0:00:06 lr: 0.000019 grad: 0.1184 (0.1227) loss: 0.8226 (0.8136) time: 0.1431 data: 0.0486 max mem: 9390 +Train: [75] [6249/6250] eta: 0:00:00 lr: 0.000019 grad: 0.1151 (0.1227) loss: 0.8171 (0.8137) time: 0.1414 data: 0.0602 max mem: 9390 +Train: [75] Total time: 0:13:50 (0.1329 s / it) +Averaged stats: lr: 0.000019 grad: 0.1151 (0.1227) loss: 0.8171 (0.8137) +Eval (hcp-train-subset): [75] [ 0/62] eta: 0:03:44 loss: 0.8361 (0.8361) time: 3.6278 data: 3.5295 max mem: 9390 +Eval (hcp-train-subset): [75] [61/62] eta: 0:00:00 loss: 0.8241 (0.8251) time: 0.1294 data: 0.1043 max mem: 9390 +Eval (hcp-train-subset): [75] Total time: 0:00:13 (0.2155 s / it) +Averaged stats (hcp-train-subset): loss: 0.8241 (0.8251) +Eval (hcp-val): [75] [ 0/62] eta: 0:03:21 loss: 0.8275 (0.8275) time: 3.2569 data: 3.2018 max mem: 9390 +Eval (hcp-val): [75] [61/62] eta: 0:00:00 loss: 0.8297 (0.8310) time: 0.1191 data: 0.0925 max mem: 9390 +Eval (hcp-val): [75] Total time: 0:00:12 (0.1998 s / it) +Averaged stats (hcp-val): loss: 0.8297 (0.8310) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +Train: [76] [ 0/6250] eta: 10:54:14 lr: 0.000019 grad: 0.1688 (0.1688) loss: 0.7744 (0.7744) time: 6.2807 data: 6.1828 max mem: 9390 +Train: [76] [ 100/6250] eta: 0:20:20 lr: 0.000019 grad: 0.1138 (0.1404) loss: 0.8309 (0.8228) time: 0.1529 data: 0.0642 max mem: 9390 +Train: [76] [ 200/6250] eta: 0:17:02 lr: 0.000019 grad: 0.1239 (0.1337) loss: 0.8126 (0.8214) time: 0.1475 data: 0.0525 max mem: 9390 +Train: [76] [ 300/6250] eta: 0:15:44 lr: 0.000019 grad: 0.1252 (0.1335) loss: 0.8107 (0.8189) time: 0.1102 data: 0.0250 max mem: 9390 +Train: [76] [ 400/6250] eta: 0:14:48 lr: 0.000019 grad: 0.1154 (0.1331) loss: 0.8159 (0.8175) time: 0.1231 data: 0.0436 max mem: 9390 +Train: [76] [ 500/6250] eta: 0:13:55 lr: 0.000019 grad: 0.1227 (0.1312) loss: 0.8118 (0.8165) time: 0.1027 data: 0.0121 max mem: 9390 +Train: [76] [ 600/6250] eta: 0:13:19 lr: 0.000019 grad: 0.1236 (0.1299) loss: 0.8168 (0.8164) time: 0.1109 data: 0.0237 max mem: 9390 +Train: [76] [ 700/6250] eta: 0:12:47 lr: 0.000019 grad: 0.1222 (0.1289) loss: 0.8160 (0.8158) time: 0.1229 data: 0.0431 max mem: 9390 +Train: [76] [ 800/6250] eta: 0:12:18 lr: 0.000018 grad: 0.1143 (0.1280) loss: 0.8207 (0.8157) time: 0.1143 data: 0.0279 max mem: 9390 +Train: [76] [ 900/6250] eta: 0:11:53 lr: 0.000018 grad: 0.1176 (0.1275) loss: 0.8186 (0.8156) time: 0.1254 data: 0.0451 max mem: 9390 +Train: [76] [1000/6250] eta: 0:11:29 lr: 0.000018 grad: 0.1152 (0.1271) loss: 0.8120 (0.8153) time: 0.1150 data: 0.0404 max mem: 9390 +Train: [76] [1100/6250] eta: 0:11:13 lr: 0.000018 grad: 0.1126 (0.1264) loss: 0.8206 (0.8155) time: 0.1223 data: 0.0412 max mem: 9390 +Train: [76] [1200/6250] eta: 0:11:02 lr: 0.000018 grad: 0.1207 (0.1258) loss: 0.8119 (0.8153) time: 0.1316 data: 0.0515 max mem: 9390 +Train: [76] [1300/6250] eta: 0:10:49 lr: 0.000018 grad: 0.1133 (0.1252) loss: 0.8098 (0.8151) time: 0.1286 data: 0.0514 max mem: 9390 +Train: [76] [1400/6250] eta: 0:10:34 lr: 0.000018 grad: 0.1181 (0.1248) loss: 0.8152 (0.8150) time: 0.1121 data: 0.0328 max mem: 9390 +Train: [76] [1500/6250] eta: 0:10:21 lr: 0.000018 grad: 0.1117 (0.1245) loss: 0.8162 (0.8149) time: 0.1255 data: 0.0428 max mem: 9390 +Train: [76] [1600/6250] eta: 0:10:09 lr: 0.000018 grad: 0.1140 (0.1243) loss: 0.8086 (0.8147) time: 0.1286 data: 0.0504 max mem: 9390 +Train: [76] [1700/6250] eta: 0:09:55 lr: 0.000018 grad: 0.1114 (0.1240) loss: 0.8218 (0.8147) time: 0.1225 data: 0.0450 max mem: 9390 +Train: [76] [1800/6250] eta: 0:09:42 lr: 0.000018 grad: 0.1197 (0.1237) loss: 0.8088 (0.8146) time: 0.1255 data: 0.0450 max mem: 9390 +Train: [76] [1900/6250] eta: 0:09:28 lr: 0.000018 grad: 0.1194 (0.1234) loss: 0.8134 (0.8144) time: 0.1167 data: 0.0387 max mem: 9390 +Train: [76] [2000/6250] eta: 0:09:16 lr: 0.000018 grad: 0.1195 (0.1232) loss: 0.8100 (0.8144) time: 0.1378 data: 0.0561 max mem: 9390 +Train: [76] [2100/6250] eta: 0:09:02 lr: 0.000018 grad: 0.1092 (0.1228) loss: 0.8202 (0.8145) time: 0.1198 data: 0.0409 max mem: 9390 +Train: [76] [2200/6250] eta: 0:08:49 lr: 0.000018 grad: 0.1148 (0.1227) loss: 0.8148 (0.8146) time: 0.1311 data: 0.0513 max mem: 9390 +Train: [76] [2300/6250] eta: 0:08:36 lr: 0.000018 grad: 0.1154 (0.1225) loss: 0.8178 (0.8146) time: 0.1198 data: 0.0338 max mem: 9390 +Train: [76] [2400/6250] eta: 0:08:23 lr: 0.000018 grad: 0.1200 (0.1225) loss: 0.8096 (0.8145) time: 0.1235 data: 0.0406 max mem: 9390 +Train: [76] [2500/6250] eta: 0:08:10 lr: 0.000018 grad: 0.1132 (0.1225) loss: 0.8169 (0.8146) time: 0.1464 data: 0.0735 max mem: 9390 +Train: [76] [2600/6250] eta: 0:07:57 lr: 0.000018 grad: 0.1169 (0.1226) loss: 0.8141 (0.8145) time: 0.1284 data: 0.0577 max mem: 9390 +Train: [76] [2700/6250] eta: 0:07:45 lr: 0.000018 grad: 0.1265 (0.1227) loss: 0.8149 (0.8145) time: 0.1383 data: 0.0611 max mem: 9390 +Train: [76] [2800/6250] eta: 0:07:33 lr: 0.000018 grad: 0.1222 (0.1228) loss: 0.8114 (0.8146) time: 0.1469 data: 0.0650 max mem: 9390 +Train: [76] [2900/6250] eta: 0:07:20 lr: 0.000018 grad: 0.1220 (0.1231) loss: 0.8165 (0.8145) time: 0.1267 data: 0.0455 max mem: 9390 +Train: [76] [3000/6250] eta: 0:07:07 lr: 0.000018 grad: 0.1194 (0.1232) loss: 0.8182 (0.8145) time: 0.1288 data: 0.0488 max mem: 9390 +Train: [76] [3100/6250] eta: 0:06:54 lr: 0.000018 grad: 0.1170 (0.1233) loss: 0.8147 (0.8145) time: 0.1449 data: 0.0693 max mem: 9390 +Train: [76] [3200/6250] eta: 0:06:42 lr: 0.000018 grad: 0.1084 (0.1234) loss: 0.8153 (0.8144) time: 0.1512 data: 0.0694 max mem: 9390 +Train: [76] [3300/6250] eta: 0:06:30 lr: 0.000018 grad: 0.1229 (0.1236) loss: 0.8118 (0.8144) time: 0.1185 data: 0.0387 max mem: 9390 +Train: [76] [3400/6250] eta: 0:06:18 lr: 0.000018 grad: 0.1166 (0.1236) loss: 0.8204 (0.8144) time: 0.1223 data: 0.0430 max mem: 9390 +Train: [76] [3500/6250] eta: 0:06:05 lr: 0.000018 grad: 0.1267 (0.1236) loss: 0.8128 (0.8144) time: 0.1447 data: 0.0714 max mem: 9390 +Train: [76] [3600/6250] eta: 0:05:52 lr: 0.000018 grad: 0.1210 (0.1237) loss: 0.8090 (0.8143) time: 0.1165 data: 0.0330 max mem: 9390 +Train: [76] [3700/6250] eta: 0:05:38 lr: 0.000018 grad: 0.1229 (0.1238) loss: 0.8152 (0.8142) time: 0.1388 data: 0.0575 max mem: 9390 +Train: [76] [3800/6250] eta: 0:05:26 lr: 0.000018 grad: 0.1220 (0.1238) loss: 0.8188 (0.8142) time: 0.1475 data: 0.0724 max mem: 9390 +Train: [76] [3900/6250] eta: 0:05:13 lr: 0.000018 grad: 0.1235 (0.1239) loss: 0.8163 (0.8141) time: 0.1488 data: 0.0710 max mem: 9390 +Train: [76] [4000/6250] eta: 0:05:01 lr: 0.000018 grad: 0.1200 (0.1239) loss: 0.8147 (0.8141) time: 0.1404 data: 0.0654 max mem: 9390 +Train: [76] [4100/6250] eta: 0:04:48 lr: 0.000018 grad: 0.1199 (0.1238) loss: 0.8109 (0.8141) time: 0.1441 data: 0.0666 max mem: 9390 +Train: [76] [4200/6250] eta: 0:04:35 lr: 0.000018 grad: 0.1118 (0.1237) loss: 0.8201 (0.8142) time: 0.1879 data: 0.1038 max mem: 9390 +Train: [76] [4300/6250] eta: 0:04:23 lr: 0.000018 grad: 0.1119 (0.1237) loss: 0.8210 (0.8142) time: 0.1342 data: 0.0597 max mem: 9390 +Train: [76] [4400/6250] eta: 0:04:09 lr: 0.000018 grad: 0.1208 (0.1236) loss: 0.8128 (0.8142) time: 0.1401 data: 0.0618 max mem: 9390 +Train: [76] [4500/6250] eta: 0:03:57 lr: 0.000018 grad: 0.1314 (0.1237) loss: 0.8121 (0.8142) time: 0.1516 data: 0.0715 max mem: 9390 +Train: [76] [4600/6250] eta: 0:03:43 lr: 0.000018 grad: 0.1333 (0.1238) loss: 0.8094 (0.8142) time: 0.1397 data: 0.0571 max mem: 9390 +Train: [76] [4700/6250] eta: 0:03:29 lr: 0.000018 grad: 0.1291 (0.1239) loss: 0.8146 (0.8142) time: 0.1172 data: 0.0387 max mem: 9390 +Train: [76] [4800/6250] eta: 0:03:15 lr: 0.000018 grad: 0.1197 (0.1240) loss: 0.8151 (0.8143) time: 0.1213 data: 0.0409 max mem: 9390 +Train: [76] [4900/6250] eta: 0:03:01 lr: 0.000018 grad: 0.1291 (0.1241) loss: 0.8113 (0.8142) time: 0.1189 data: 0.0379 max mem: 9390 +Train: [76] [5000/6250] eta: 0:02:47 lr: 0.000018 grad: 0.1250 (0.1242) loss: 0.8140 (0.8142) time: 0.1196 data: 0.0373 max mem: 9390 +Train: [76] [5100/6250] eta: 0:02:33 lr: 0.000017 grad: 0.1278 (0.1242) loss: 0.8099 (0.8142) time: 0.1130 data: 0.0262 max mem: 9390 +Train: [76] [5200/6250] eta: 0:02:20 lr: 0.000017 grad: 0.1221 (0.1243) loss: 0.8135 (0.8142) time: 0.1305 data: 0.0540 max mem: 9390 +Train: [76] [5300/6250] eta: 0:02:06 lr: 0.000017 grad: 0.1323 (0.1244) loss: 0.8070 (0.8142) time: 0.1415 data: 0.0607 max mem: 9390 +Train: [76] [5400/6250] eta: 0:01:53 lr: 0.000017 grad: 0.1305 (0.1245) loss: 0.8167 (0.8142) time: 0.1233 data: 0.0276 max mem: 9390 +Train: [76] [5500/6250] eta: 0:01:39 lr: 0.000017 grad: 0.1267 (0.1246) loss: 0.8080 (0.8141) time: 0.1252 data: 0.0494 max mem: 9390 +Train: [76] [5600/6250] eta: 0:01:26 lr: 0.000017 grad: 0.1235 (0.1248) loss: 0.8127 (0.8140) time: 0.1281 data: 0.0499 max mem: 9390 +Train: [76] [5700/6250] eta: 0:01:13 lr: 0.000017 grad: 0.1257 (0.1249) loss: 0.8087 (0.8140) time: 0.1250 data: 0.0486 max mem: 9390 +Train: [76] [5800/6250] eta: 0:00:59 lr: 0.000017 grad: 0.1281 (0.1250) loss: 0.8115 (0.8139) time: 0.1321 data: 0.0483 max mem: 9390 +Train: [76] [5900/6250] eta: 0:00:46 lr: 0.000017 grad: 0.1272 (0.1251) loss: 0.8018 (0.8139) time: 0.1600 data: 0.0754 max mem: 9390 +Train: [76] [6000/6250] eta: 0:00:33 lr: 0.000017 grad: 0.1265 (0.1251) loss: 0.8128 (0.8138) time: 0.1050 data: 0.0279 max mem: 9390 +Train: [76] [6100/6250] eta: 0:00:19 lr: 0.000017 grad: 0.1234 (0.1252) loss: 0.8109 (0.8137) time: 0.1621 data: 0.0837 max mem: 9390 +Train: [76] [6200/6250] eta: 0:00:06 lr: 0.000017 grad: 0.1347 (0.1253) loss: 0.8072 (0.8136) time: 0.1537 data: 0.0704 max mem: 9390 +Train: [76] [6249/6250] eta: 0:00:00 lr: 0.000017 grad: 0.1216 (0.1253) loss: 0.8112 (0.8136) time: 0.1260 data: 0.0395 max mem: 9390 +Train: [76] Total time: 0:14:00 (0.1344 s / it) +Averaged stats: lr: 0.000017 grad: 0.1216 (0.1253) loss: 0.8112 (0.8136) +Eval (hcp-train-subset): [76] [ 0/62] eta: 0:03:06 loss: 0.8368 (0.8368) time: 3.0122 data: 2.9293 max mem: 9390 +Eval (hcp-train-subset): [76] [61/62] eta: 0:00:00 loss: 0.8218 (0.8257) time: 0.0994 data: 0.0747 max mem: 9390 +Eval (hcp-train-subset): [76] Total time: 0:00:11 (0.1914 s / it) +Averaged stats (hcp-train-subset): loss: 0.8218 (0.8257) +Eval (hcp-val): [76] [ 0/62] eta: 0:03:38 loss: 0.8278 (0.8278) time: 3.5227 data: 3.4301 max mem: 9390 +Eval (hcp-val): [76] [61/62] eta: 0:00:00 loss: 0.8299 (0.8306) time: 0.1002 data: 0.0755 max mem: 9390 +Eval (hcp-val): [76] Total time: 0:00:12 (0.2009 s / it) +Averaged stats (hcp-val): loss: 0.8299 (0.8306) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +Train: [77] [ 0/6250] eta: 9:22:18 lr: 0.000017 grad: 0.2491 (0.2491) loss: 0.8337 (0.8337) time: 5.3982 data: 5.2110 max mem: 9390 +Train: [77] [ 100/6250] eta: 0:20:31 lr: 0.000017 grad: 0.1586 (0.1726) loss: 0.7963 (0.8190) time: 0.1586 data: 0.0612 max mem: 9390 +Train: [77] [ 200/6250] eta: 0:17:38 lr: 0.000017 grad: 0.1263 (0.1568) loss: 0.8177 (0.8164) time: 0.1530 data: 0.0602 max mem: 9390 +Train: [77] [ 300/6250] eta: 0:16:16 lr: 0.000017 grad: 0.1228 (0.1456) loss: 0.8112 (0.8170) time: 0.1427 data: 0.0575 max mem: 9390 +Train: [77] [ 400/6250] eta: 0:15:18 lr: 0.000017 grad: 0.1275 (0.1408) loss: 0.8216 (0.8168) time: 0.1323 data: 0.0515 max mem: 9390 +Train: [77] [ 500/6250] eta: 0:14:29 lr: 0.000017 grad: 0.1190 (0.1373) loss: 0.8099 (0.8166) time: 0.1237 data: 0.0377 max mem: 9390 +Train: [77] [ 600/6250] eta: 0:13:43 lr: 0.000017 grad: 0.1084 (0.1347) loss: 0.8195 (0.8165) time: 0.1206 data: 0.0297 max mem: 9390 +Train: [77] [ 700/6250] eta: 0:13:08 lr: 0.000017 grad: 0.1200 (0.1332) loss: 0.8108 (0.8158) time: 0.1267 data: 0.0454 max mem: 9390 +Train: [77] [ 800/6250] eta: 0:12:37 lr: 0.000017 grad: 0.1172 (0.1325) loss: 0.8149 (0.8150) time: 0.1272 data: 0.0449 max mem: 9390 +Train: [77] [ 900/6250] eta: 0:12:12 lr: 0.000017 grad: 0.1299 (0.1323) loss: 0.8094 (0.8142) time: 0.1148 data: 0.0321 max mem: 9390 +Train: [77] [1000/6250] eta: 0:11:47 lr: 0.000017 grad: 0.1254 (0.1320) loss: 0.8089 (0.8137) time: 0.1119 data: 0.0360 max mem: 9390 +Train: [77] [1100/6250] eta: 0:11:28 lr: 0.000017 grad: 0.1198 (0.1316) loss: 0.8037 (0.8131) time: 0.1129 data: 0.0201 max mem: 9390 +Train: [77] [1200/6250] eta: 0:11:11 lr: 0.000017 grad: 0.1335 (0.1317) loss: 0.7978 (0.8126) time: 0.1228 data: 0.0433 max mem: 9390 +Train: [77] [1300/6250] eta: 0:11:00 lr: 0.000017 grad: 0.1279 (0.1319) loss: 0.8101 (0.8122) time: 0.1310 data: 0.0389 max mem: 9390 +Train: [77] [1400/6250] eta: 0:10:49 lr: 0.000017 grad: 0.1200 (0.1318) loss: 0.8116 (0.8120) time: 0.1400 data: 0.0655 max mem: 9390 +Train: [77] [1500/6250] eta: 0:10:35 lr: 0.000017 grad: 0.1215 (0.1317) loss: 0.8113 (0.8118) time: 0.1401 data: 0.0675 max mem: 9390 +Train: [77] [1600/6250] eta: 0:10:22 lr: 0.000017 grad: 0.1199 (0.1315) loss: 0.8067 (0.8115) time: 0.1472 data: 0.0710 max mem: 9390 +Train: [77] [1700/6250] eta: 0:10:11 lr: 0.000017 grad: 0.1203 (0.1314) loss: 0.8069 (0.8112) time: 0.1421 data: 0.0535 max mem: 9390 +Train: [77] [1800/6250] eta: 0:09:56 lr: 0.000017 grad: 0.1218 (0.1312) loss: 0.8092 (0.8112) time: 0.1390 data: 0.0594 max mem: 9390 +Train: [77] [1900/6250] eta: 0:09:44 lr: 0.000017 grad: 0.1254 (0.1311) loss: 0.8072 (0.8111) time: 0.1381 data: 0.0580 max mem: 9390 +Train: [77] [2000/6250] eta: 0:09:33 lr: 0.000017 grad: 0.1233 (0.1309) loss: 0.8099 (0.8110) time: 0.1266 data: 0.0446 max mem: 9390 +Train: [77] [2100/6250] eta: 0:09:23 lr: 0.000017 grad: 0.1374 (0.1309) loss: 0.8067 (0.8109) time: 0.1228 data: 0.0486 max mem: 9390 +Train: [77] [2200/6250] eta: 0:09:09 lr: 0.000017 grad: 0.1203 (0.1306) loss: 0.8159 (0.8110) time: 0.1334 data: 0.0559 max mem: 9390 +Train: [77] [2300/6250] eta: 0:08:55 lr: 0.000017 grad: 0.1197 (0.1304) loss: 0.8067 (0.8110) time: 0.1261 data: 0.0482 max mem: 9390 +Train: [77] [2400/6250] eta: 0:08:42 lr: 0.000017 grad: 0.1237 (0.1302) loss: 0.8123 (0.8110) time: 0.1439 data: 0.0661 max mem: 9390 +Train: [77] [2500/6250] eta: 0:08:30 lr: 0.000017 grad: 0.1265 (0.1299) loss: 0.8118 (0.8111) time: 0.1646 data: 0.0927 max mem: 9390 +Train: [77] [2600/6250] eta: 0:08:23 lr: 0.000017 grad: 0.1163 (0.1297) loss: 0.8128 (0.8113) time: 0.0815 data: 0.0002 max mem: 9390 +Train: [77] [2700/6250] eta: 0:08:06 lr: 0.000017 grad: 0.1157 (0.1294) loss: 0.8184 (0.8114) time: 0.1306 data: 0.0513 max mem: 9390 +Train: [77] [2800/6250] eta: 0:07:51 lr: 0.000017 grad: 0.1275 (0.1293) loss: 0.8188 (0.8115) time: 0.1235 data: 0.0443 max mem: 9390 +Train: [77] [2900/6250] eta: 0:07:38 lr: 0.000017 grad: 0.1183 (0.1290) loss: 0.8171 (0.8116) time: 0.1294 data: 0.0443 max mem: 9390 +Train: [77] [3000/6250] eta: 0:07:25 lr: 0.000017 grad: 0.1208 (0.1289) loss: 0.8139 (0.8117) time: 0.1386 data: 0.0582 max mem: 9390 +Train: [77] [3100/6250] eta: 0:07:11 lr: 0.000017 grad: 0.1154 (0.1287) loss: 0.8161 (0.8118) time: 0.1532 data: 0.0685 max mem: 9390 +Train: [77] [3200/6250] eta: 0:06:57 lr: 0.000017 grad: 0.1215 (0.1285) loss: 0.8119 (0.8118) time: 0.1497 data: 0.0729 max mem: 9390 +Train: [77] [3300/6250] eta: 0:06:43 lr: 0.000016 grad: 0.1209 (0.1283) loss: 0.8128 (0.8118) time: 0.1294 data: 0.0524 max mem: 9390 +Train: [77] [3400/6250] eta: 0:06:29 lr: 0.000016 grad: 0.1142 (0.1281) loss: 0.8126 (0.8119) time: 0.1485 data: 0.0712 max mem: 9390 +Train: [77] [3500/6250] eta: 0:06:15 lr: 0.000016 grad: 0.1216 (0.1280) loss: 0.8206 (0.8120) time: 0.1327 data: 0.0545 max mem: 9390 +Train: [77] [3600/6250] eta: 0:06:01 lr: 0.000016 grad: 0.1226 (0.1278) loss: 0.8183 (0.8120) time: 0.1472 data: 0.0683 max mem: 9390 +Train: [77] [3700/6250] eta: 0:05:48 lr: 0.000016 grad: 0.1226 (0.1277) loss: 0.8183 (0.8121) time: 0.1530 data: 0.0781 max mem: 9390 +Train: [77] [3800/6250] eta: 0:05:35 lr: 0.000016 grad: 0.1182 (0.1275) loss: 0.8165 (0.8122) time: 0.1316 data: 0.0505 max mem: 9390 +Train: [77] [3900/6250] eta: 0:05:21 lr: 0.000016 grad: 0.1201 (0.1275) loss: 0.8184 (0.8123) time: 0.1399 data: 0.0672 max mem: 9390 +Train: [77] [4000/6250] eta: 0:05:08 lr: 0.000016 grad: 0.1197 (0.1274) loss: 0.8203 (0.8124) time: 0.1955 data: 0.1263 max mem: 9390 +Train: [77] [4100/6250] eta: 0:04:56 lr: 0.000016 grad: 0.1190 (0.1273) loss: 0.8144 (0.8124) time: 0.2101 data: 0.1370 max mem: 9390 +Train: [77] [4200/6250] eta: 0:04:42 lr: 0.000016 grad: 0.1159 (0.1272) loss: 0.8159 (0.8124) time: 0.1613 data: 0.0823 max mem: 9390 +Train: [77] [4300/6250] eta: 0:04:29 lr: 0.000016 grad: 0.1147 (0.1271) loss: 0.8193 (0.8125) time: 0.1581 data: 0.0784 max mem: 9390 +Train: [77] [4400/6250] eta: 0:04:15 lr: 0.000016 grad: 0.1170 (0.1270) loss: 0.8156 (0.8126) time: 0.1324 data: 0.0499 max mem: 9390 +Train: [77] [4500/6250] eta: 0:04:02 lr: 0.000016 grad: 0.1165 (0.1268) loss: 0.8117 (0.8126) time: 0.1525 data: 0.0760 max mem: 9390 +Train: [77] [4600/6250] eta: 0:03:47 lr: 0.000016 grad: 0.1231 (0.1268) loss: 0.8156 (0.8127) time: 0.1331 data: 0.0458 max mem: 9390 +Train: [77] [4700/6250] eta: 0:03:33 lr: 0.000016 grad: 0.1202 (0.1268) loss: 0.8167 (0.8127) time: 0.1091 data: 0.0259 max mem: 9390 +Train: [77] [4800/6250] eta: 0:03:19 lr: 0.000016 grad: 0.1155 (0.1267) loss: 0.8120 (0.8126) time: 0.1118 data: 0.0300 max mem: 9390 +Train: [77] [4900/6250] eta: 0:03:04 lr: 0.000016 grad: 0.1234 (0.1267) loss: 0.8061 (0.8126) time: 0.1059 data: 0.0297 max mem: 9390 +Train: [77] [5000/6250] eta: 0:02:50 lr: 0.000016 grad: 0.1210 (0.1267) loss: 0.8098 (0.8125) time: 0.1201 data: 0.0377 max mem: 9390 +Train: [77] [5100/6250] eta: 0:02:36 lr: 0.000016 grad: 0.1168 (0.1267) loss: 0.8124 (0.8125) time: 0.1207 data: 0.0413 max mem: 9390 +Train: [77] [5200/6250] eta: 0:02:22 lr: 0.000016 grad: 0.1295 (0.1267) loss: 0.8126 (0.8125) time: 0.1293 data: 0.0472 max mem: 9390 +Train: [77] [5300/6250] eta: 0:02:08 lr: 0.000016 grad: 0.1174 (0.1266) loss: 0.8131 (0.8124) time: 0.1157 data: 0.0401 max mem: 9390 +Train: [77] [5400/6250] eta: 0:01:55 lr: 0.000016 grad: 0.1195 (0.1266) loss: 0.8107 (0.8124) time: 0.1205 data: 0.0442 max mem: 9390 +Train: [77] [5500/6250] eta: 0:01:41 lr: 0.000016 grad: 0.1201 (0.1266) loss: 0.8129 (0.8124) time: 0.1321 data: 0.0515 max mem: 9390 +Train: [77] [5600/6250] eta: 0:01:27 lr: 0.000016 grad: 0.1283 (0.1267) loss: 0.8086 (0.8123) time: 0.1215 data: 0.0436 max mem: 9390 +Train: [77] [5700/6250] eta: 0:01:13 lr: 0.000016 grad: 0.1177 (0.1267) loss: 0.8161 (0.8123) time: 0.1059 data: 0.0212 max mem: 9390 +Train: [77] [5800/6250] eta: 0:01:00 lr: 0.000016 grad: 0.1189 (0.1267) loss: 0.8110 (0.8123) time: 0.1271 data: 0.0478 max mem: 9390 +Train: [77] [5900/6250] eta: 0:00:46 lr: 0.000016 grad: 0.1205 (0.1266) loss: 0.8113 (0.8123) time: 0.1419 data: 0.0665 max mem: 9390 +Train: [77] [6000/6250] eta: 0:00:33 lr: 0.000016 grad: 0.1209 (0.1266) loss: 0.8150 (0.8123) time: 0.1441 data: 0.0672 max mem: 9390 +Train: [77] [6100/6250] eta: 0:00:20 lr: 0.000016 grad: 0.1217 (0.1265) loss: 0.8123 (0.8123) time: 0.1337 data: 0.0567 max mem: 9390 +Train: [77] [6200/6250] eta: 0:00:06 lr: 0.000016 grad: 0.1238 (0.1265) loss: 0.8094 (0.8123) time: 0.1315 data: 0.0542 max mem: 9390 +Train: [77] [6249/6250] eta: 0:00:00 lr: 0.000016 grad: 0.1320 (0.1265) loss: 0.8161 (0.8123) time: 0.1568 data: 0.0827 max mem: 9390 +Train: [77] Total time: 0:14:04 (0.1352 s / it) +Averaged stats: lr: 0.000016 grad: 0.1320 (0.1265) loss: 0.8161 (0.8123) +Eval (hcp-train-subset): [77] [ 0/62] eta: 0:04:31 loss: 0.8330 (0.8330) time: 4.3767 data: 4.3448 max mem: 9390 +Eval (hcp-train-subset): [77] [61/62] eta: 0:00:00 loss: 0.8243 (0.8252) time: 0.1312 data: 0.1061 max mem: 9390 +Eval (hcp-train-subset): [77] Total time: 0:00:12 (0.2037 s / it) +Averaged stats (hcp-train-subset): loss: 0.8243 (0.8252) +Eval (hcp-val): [77] [ 0/62] eta: 0:04:07 loss: 0.8257 (0.8257) time: 3.9950 data: 3.9361 max mem: 9390 +Eval (hcp-val): [77] [61/62] eta: 0:00:00 loss: 0.8290 (0.8301) time: 0.1249 data: 0.1002 max mem: 9390 +Eval (hcp-val): [77] Total time: 0:00:13 (0.2133 s / it) +Averaged stats (hcp-val): loss: 0.8290 (0.8301) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +Train: [78] [ 0/6250] eta: 8:41:24 lr: 0.000016 grad: 0.0891 (0.0891) loss: 0.8471 (0.8471) time: 5.0056 data: 4.8830 max mem: 9390 +Train: [78] [ 100/6250] eta: 0:20:50 lr: 0.000016 grad: 0.1347 (0.1688) loss: 0.8283 (0.8187) time: 0.1351 data: 0.0272 max mem: 9390 +Train: [78] [ 200/6250] eta: 0:17:48 lr: 0.000016 grad: 0.1219 (0.1523) loss: 0.8196 (0.8168) time: 0.1390 data: 0.0412 max mem: 9390 +Train: [78] [ 300/6250] eta: 0:16:48 lr: 0.000016 grad: 0.1237 (0.1439) loss: 0.8136 (0.8170) time: 0.1531 data: 0.0605 max mem: 9390 +Train: [78] [ 400/6250] eta: 0:16:14 lr: 0.000016 grad: 0.1139 (0.1384) loss: 0.8224 (0.8172) time: 0.1557 data: 0.0545 max mem: 9390 +Train: [78] [ 500/6250] eta: 0:15:43 lr: 0.000016 grad: 0.1123 (0.1349) loss: 0.8178 (0.8174) time: 0.1478 data: 0.0541 max mem: 9390 +Train: [78] [ 600/6250] eta: 0:16:10 lr: 0.000016 grad: 0.1189 (0.1324) loss: 0.8154 (0.8176) time: 0.2404 data: 0.1558 max mem: 9390 +Train: [78] [ 700/6250] eta: 0:16:24 lr: 0.000016 grad: 0.1171 (0.1307) loss: 0.8177 (0.8180) time: 0.2488 data: 0.1505 max mem: 9390 +Train: [78] [ 800/6250] eta: 0:16:49 lr: 0.000016 grad: 0.1218 (0.1297) loss: 0.8216 (0.8181) time: 0.2793 data: 0.1698 max mem: 9390 +Train: [78] [ 900/6250] eta: 0:16:58 lr: 0.000016 grad: 0.1223 (0.1292) loss: 0.8140 (0.8179) time: 0.2634 data: 0.1613 max mem: 9390 +Train: [78] [1000/6250] eta: 0:17:10 lr: 0.000016 grad: 0.1326 (0.1292) loss: 0.8113 (0.8175) time: 0.1578 data: 0.0337 max mem: 9390 +Train: [78] [1100/6250] eta: 0:17:29 lr: 0.000016 grad: 0.1269 (0.1289) loss: 0.8112 (0.8169) time: 0.1268 data: 0.0006 max mem: 9390 +Train: [78] [1200/6250] eta: 0:17:27 lr: 0.000016 grad: 0.1197 (0.1288) loss: 0.8110 (0.8162) time: 0.4040 data: 0.2955 max mem: 9390 +Train: [78] [1300/6250] eta: 0:17:16 lr: 0.000016 grad: 0.1215 (0.1287) loss: 0.8035 (0.8159) time: 0.3706 data: 0.2642 max mem: 9390 +Train: [78] [1400/6250] eta: 0:17:02 lr: 0.000016 grad: 0.1241 (0.1286) loss: 0.8095 (0.8155) time: 0.1906 data: 0.1046 max mem: 9390 +Train: [78] [1500/6250] eta: 0:16:40 lr: 0.000015 grad: 0.1210 (0.1285) loss: 0.8116 (0.8151) time: 0.2601 data: 0.1450 max mem: 9390 +Train: [78] [1600/6250] eta: 0:16:13 lr: 0.000015 grad: 0.1209 (0.1283) loss: 0.8171 (0.8149) time: 0.1307 data: 0.0094 max mem: 9390 +Train: [78] [1700/6250] eta: 0:15:54 lr: 0.000015 grad: 0.1210 (0.1281) loss: 0.8124 (0.8147) time: 0.2416 data: 0.1479 max mem: 9390 +Train: [78] [1800/6250] eta: 0:15:31 lr: 0.000015 grad: 0.1206 (0.1279) loss: 0.8090 (0.8145) time: 0.1871 data: 0.0912 max mem: 9390 +Train: [78] [1900/6250] eta: 0:15:04 lr: 0.000015 grad: 0.1246 (0.1277) loss: 0.8103 (0.8143) time: 0.1506 data: 0.0547 max mem: 9390 +Train: [78] [2000/6250] eta: 0:14:43 lr: 0.000015 grad: 0.1241 (0.1276) loss: 0.8145 (0.8141) time: 0.1078 data: 0.0003 max mem: 9390 +Train: [78] [2100/6250] eta: 0:14:17 lr: 0.000015 grad: 0.1232 (0.1274) loss: 0.8095 (0.8139) time: 0.1942 data: 0.0696 max mem: 9390 +Train: [78] [2200/6250] eta: 0:14:01 lr: 0.000015 grad: 0.1202 (0.1273) loss: 0.8136 (0.8138) time: 0.2330 data: 0.1354 max mem: 9390 +Train: [78] [2300/6250] eta: 0:13:37 lr: 0.000015 grad: 0.1206 (0.1271) loss: 0.8116 (0.8137) time: 0.2667 data: 0.1502 max mem: 9390 +Train: [78] [2400/6250] eta: 0:13:16 lr: 0.000015 grad: 0.1204 (0.1270) loss: 0.8161 (0.8136) time: 0.2633 data: 0.1813 max mem: 9390 +Train: [78] [2500/6250] eta: 0:12:51 lr: 0.000015 grad: 0.1211 (0.1271) loss: 0.8104 (0.8135) time: 0.1943 data: 0.1066 max mem: 9390 +Train: [78] [2600/6250] eta: 0:12:27 lr: 0.000015 grad: 0.1237 (0.1270) loss: 0.8072 (0.8135) time: 0.1817 data: 0.0934 max mem: 9390 +Train: [78] [2700/6250] eta: 0:12:05 lr: 0.000015 grad: 0.1189 (0.1270) loss: 0.8201 (0.8135) time: 0.1566 data: 0.0577 max mem: 9390 +Train: [78] [2800/6250] eta: 0:11:48 lr: 0.000015 grad: 0.1209 (0.1270) loss: 0.8204 (0.8136) time: 0.3986 data: 0.2956 max mem: 9390 +Train: [78] [2900/6250] eta: 0:11:25 lr: 0.000015 grad: 0.1179 (0.1269) loss: 0.8151 (0.8136) time: 0.2175 data: 0.1348 max mem: 9390 +Train: [78] [3000/6250] eta: 0:11:04 lr: 0.000015 grad: 0.1228 (0.1269) loss: 0.8124 (0.8136) time: 0.1190 data: 0.0050 max mem: 9390 +Train: [78] [3100/6250] eta: 0:10:47 lr: 0.000015 grad: 0.1279 (0.1271) loss: 0.8148 (0.8136) time: 0.3319 data: 0.2372 max mem: 9390 +Train: [78] [3200/6250] eta: 0:10:23 lr: 0.000015 grad: 0.1237 (0.1272) loss: 0.8138 (0.8134) time: 0.1756 data: 0.0883 max mem: 9390 +Train: [78] [3300/6250] eta: 0:10:02 lr: 0.000015 grad: 0.1200 (0.1272) loss: 0.8155 (0.8133) time: 0.1507 data: 0.0569 max mem: 9390 +Train: [78] [3400/6250] eta: 0:09:41 lr: 0.000015 grad: 0.1240 (0.1271) loss: 0.8102 (0.8133) time: 0.2645 data: 0.1653 max mem: 9390 +Train: [78] [3500/6250] eta: 0:09:19 lr: 0.000015 grad: 0.1289 (0.1272) loss: 0.8145 (0.8132) time: 0.1502 data: 0.0473 max mem: 9390 +Train: [78] [3600/6250] eta: 0:08:58 lr: 0.000015 grad: 0.1281 (0.1273) loss: 0.8150 (0.8131) time: 0.1255 data: 0.0003 max mem: 9390 +Train: [78] [3700/6250] eta: 0:08:37 lr: 0.000015 grad: 0.1241 (0.1273) loss: 0.8137 (0.8131) time: 0.1884 data: 0.1002 max mem: 9390 +Train: [78] [3800/6250] eta: 0:08:17 lr: 0.000015 grad: 0.1170 (0.1273) loss: 0.8140 (0.8131) time: 0.1577 data: 0.0797 max mem: 9390 +Train: [78] [3900/6250] eta: 0:07:55 lr: 0.000015 grad: 0.1210 (0.1273) loss: 0.8091 (0.8131) time: 0.1947 data: 0.0943 max mem: 9390 +Train: [78] [4000/6250] eta: 0:07:35 lr: 0.000015 grad: 0.1174 (0.1273) loss: 0.8219 (0.8131) time: 0.2159 data: 0.1331 max mem: 9390 +Train: [78] [4100/6250] eta: 0:07:13 lr: 0.000015 grad: 0.1235 (0.1273) loss: 0.8170 (0.8131) time: 0.1585 data: 0.0757 max mem: 9390 +Train: [78] [4200/6250] eta: 0:06:51 lr: 0.000015 grad: 0.1216 (0.1272) loss: 0.8169 (0.8132) time: 0.1613 data: 0.0752 max mem: 9390 +Train: [78] [4300/6250] eta: 0:06:30 lr: 0.000015 grad: 0.1185 (0.1271) loss: 0.8234 (0.8132) time: 0.1801 data: 0.0996 max mem: 9390 +Train: [78] [4400/6250] eta: 0:06:09 lr: 0.000015 grad: 0.1252 (0.1271) loss: 0.8161 (0.8132) time: 0.1749 data: 0.0789 max mem: 9390 +Train: [78] [4500/6250] eta: 0:05:48 lr: 0.000015 grad: 0.1203 (0.1271) loss: 0.8172 (0.8133) time: 0.1700 data: 0.0754 max mem: 9390 +Train: [78] [4600/6250] eta: 0:05:27 lr: 0.000015 grad: 0.1318 (0.1271) loss: 0.8133 (0.8133) time: 0.2280 data: 0.0811 max mem: 9390 +Train: [78] [4700/6250] eta: 0:05:06 lr: 0.000015 grad: 0.1194 (0.1271) loss: 0.8133 (0.8133) time: 0.1807 data: 0.0841 max mem: 9390 +Train: [78] [4800/6250] eta: 0:04:45 lr: 0.000015 grad: 0.1264 (0.1270) loss: 0.8135 (0.8133) time: 0.1624 data: 0.0718 max mem: 9390 +Train: [78] [4900/6250] eta: 0:04:25 lr: 0.000015 grad: 0.1158 (0.1270) loss: 0.8165 (0.8133) time: 0.1686 data: 0.0770 max mem: 9390 +Train: [78] [5000/6250] eta: 0:04:05 lr: 0.000015 grad: 0.1217 (0.1269) loss: 0.8130 (0.8133) time: 0.1557 data: 0.0684 max mem: 9390 +Train: [78] [5100/6250] eta: 0:03:44 lr: 0.000015 grad: 0.1195 (0.1269) loss: 0.8172 (0.8134) time: 0.1815 data: 0.1018 max mem: 9390 +Train: [78] [5200/6250] eta: 0:03:24 lr: 0.000015 grad: 0.1210 (0.1268) loss: 0.8191 (0.8134) time: 0.2023 data: 0.1186 max mem: 9390 +Train: [78] [5300/6250] eta: 0:03:04 lr: 0.000015 grad: 0.1246 (0.1268) loss: 0.8128 (0.8134) time: 0.1267 data: 0.0319 max mem: 9390 +Train: [78] [5400/6250] eta: 0:02:45 lr: 0.000015 grad: 0.1233 (0.1267) loss: 0.8055 (0.8134) time: 0.1648 data: 0.0605 max mem: 9390 +Train: [78] [5500/6250] eta: 0:02:25 lr: 0.000015 grad: 0.1293 (0.1267) loss: 0.8098 (0.8134) time: 0.1633 data: 0.0703 max mem: 9390 +Train: [78] [5600/6250] eta: 0:02:05 lr: 0.000015 grad: 0.1152 (0.1267) loss: 0.8116 (0.8134) time: 0.1988 data: 0.1064 max mem: 9390 +Train: [78] [5700/6250] eta: 0:01:46 lr: 0.000015 grad: 0.1271 (0.1267) loss: 0.8084 (0.8134) time: 0.2963 data: 0.2022 max mem: 9390 +Train: [78] [5800/6250] eta: 0:01:27 lr: 0.000015 grad: 0.1216 (0.1266) loss: 0.8091 (0.8133) time: 0.1232 data: 0.0210 max mem: 9390 +Train: [78] [5900/6250] eta: 0:01:08 lr: 0.000015 grad: 0.1256 (0.1266) loss: 0.8081 (0.8133) time: 0.2049 data: 0.1246 max mem: 9390 +Train: [78] [6000/6250] eta: 0:00:48 lr: 0.000015 grad: 0.1269 (0.1265) loss: 0.8090 (0.8132) time: 0.1688 data: 0.0775 max mem: 9390 +Train: [78] [6100/6250] eta: 0:00:29 lr: 0.000015 grad: 0.1181 (0.1265) loss: 0.8058 (0.8132) time: 0.1750 data: 0.0776 max mem: 9390 +Train: [78] [6200/6250] eta: 0:00:09 lr: 0.000014 grad: 0.1195 (0.1265) loss: 0.8145 (0.8132) time: 0.2428 data: 0.1324 max mem: 9390 +Train: [78] [6249/6250] eta: 0:00:00 lr: 0.000014 grad: 0.1191 (0.1265) loss: 0.8117 (0.8132) time: 0.1112 data: 0.0003 max mem: 9390 +Train: [78] Total time: 0:20:25 (0.1961 s / it) +Averaged stats: lr: 0.000014 grad: 0.1191 (0.1265) loss: 0.8117 (0.8132) +Eval (hcp-train-subset): [78] [ 0/62] eta: 0:05:59 loss: 0.8366 (0.8366) time: 5.7914 data: 5.7179 max mem: 9390 +Eval (hcp-train-subset): [78] [61/62] eta: 0:00:00 loss: 0.8274 (0.8259) time: 0.1120 data: 0.0847 max mem: 9390 +Eval (hcp-train-subset): [78] Total time: 0:00:16 (0.2696 s / it) +Averaged stats (hcp-train-subset): loss: 0.8274 (0.8259) +Eval (hcp-val): [78] [ 0/62] eta: 0:04:58 loss: 0.8245 (0.8245) time: 4.8091 data: 4.7361 max mem: 9390 +Eval (hcp-val): [78] [61/62] eta: 0:00:00 loss: 0.8310 (0.8307) time: 0.1382 data: 0.1111 max mem: 9390 +Eval (hcp-val): [78] Total time: 0:00:15 (0.2522 s / it) +Averaged stats (hcp-val): loss: 0.8310 (0.8307) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +Train: [79] [ 0/6250] eta: 10:36:01 lr: 0.000014 grad: 0.2020 (0.2020) loss: 0.8428 (0.8428) time: 6.1059 data: 5.9179 max mem: 9390 +Train: [79] [ 100/6250] eta: 0:26:59 lr: 0.000014 grad: 0.1596 (0.1627) loss: 0.8115 (0.8204) time: 0.2457 data: 0.1429 max mem: 9390 +Train: [79] [ 200/6250] eta: 0:22:32 lr: 0.000014 grad: 0.1280 (0.1580) loss: 0.8105 (0.8141) time: 0.1857 data: 0.0814 max mem: 9390 +Train: [79] [ 300/6250] eta: 0:20:49 lr: 0.000014 grad: 0.1233 (0.1526) loss: 0.8091 (0.8115) time: 0.1566 data: 0.0675 max mem: 9390 +Train: [79] [ 400/6250] eta: 0:19:58 lr: 0.000014 grad: 0.1303 (0.1487) loss: 0.8087 (0.8109) time: 0.1576 data: 0.0543 max mem: 9390 +Train: [79] [ 500/6250] eta: 0:19:03 lr: 0.000014 grad: 0.1343 (0.1460) loss: 0.8042 (0.8102) time: 0.1939 data: 0.0933 max mem: 9390 +Train: [79] [ 600/6250] eta: 0:18:20 lr: 0.000014 grad: 0.1155 (0.1440) loss: 0.8144 (0.8101) time: 0.1473 data: 0.0548 max mem: 9390 +Train: [79] [ 700/6250] eta: 0:17:49 lr: 0.000014 grad: 0.1162 (0.1415) loss: 0.8204 (0.8107) time: 0.1346 data: 0.0180 max mem: 9390 +Train: [79] [ 800/6250] eta: 0:17:15 lr: 0.000014 grad: 0.1084 (0.1396) loss: 0.8221 (0.8113) time: 0.1696 data: 0.0665 max mem: 9390 +Train: [79] [ 900/6250] eta: 0:16:48 lr: 0.000014 grad: 0.1163 (0.1380) loss: 0.8101 (0.8116) time: 0.2030 data: 0.1071 max mem: 9390 +Train: [79] [1000/6250] eta: 0:16:30 lr: 0.000014 grad: 0.1191 (0.1366) loss: 0.8200 (0.8120) time: 0.2976 data: 0.2110 max mem: 9390 +Train: [79] [1100/6250] eta: 0:16:20 lr: 0.000014 grad: 0.1180 (0.1358) loss: 0.8202 (0.8121) time: 0.1909 data: 0.0849 max mem: 9390 +Train: [79] [1200/6250] eta: 0:16:24 lr: 0.000014 grad: 0.1225 (0.1350) loss: 0.8111 (0.8122) time: 0.3542 data: 0.2602 max mem: 9390 +Train: [79] [1300/6250] eta: 0:16:29 lr: 0.000014 grad: 0.1154 (0.1343) loss: 0.8092 (0.8123) time: 0.1349 data: 0.0005 max mem: 9390 +Train: [79] [1400/6250] eta: 0:16:16 lr: 0.000014 grad: 0.1224 (0.1337) loss: 0.8127 (0.8124) time: 0.1093 data: 0.0002 max mem: 9390 +Train: [79] [1500/6250] eta: 0:15:55 lr: 0.000014 grad: 0.1321 (0.1336) loss: 0.8043 (0.8122) time: 0.2124 data: 0.0997 max mem: 9390 +Train: [79] [1600/6250] eta: 0:15:27 lr: 0.000014 grad: 0.1271 (0.1335) loss: 0.8073 (0.8121) time: 0.1261 data: 0.0347 max mem: 9390 +Train: [79] [1700/6250] eta: 0:15:31 lr: 0.000014 grad: 0.1253 (0.1330) loss: 0.8071 (0.8120) time: 0.2863 data: 0.1791 max mem: 9390 +Train: [79] [1800/6250] eta: 0:15:03 lr: 0.000014 grad: 0.1270 (0.1326) loss: 0.8111 (0.8119) time: 0.1646 data: 0.0640 max mem: 9390 +Train: [79] [1900/6250] eta: 0:14:39 lr: 0.000014 grad: 0.1250 (0.1323) loss: 0.8111 (0.8117) time: 0.2153 data: 0.1297 max mem: 9390 +Train: [79] [2000/6250] eta: 0:14:16 lr: 0.000014 grad: 0.1206 (0.1318) loss: 0.8008 (0.8116) time: 0.1570 data: 0.0646 max mem: 9390 +Train: [79] [2100/6250] eta: 0:13:50 lr: 0.000014 grad: 0.1239 (0.1317) loss: 0.8056 (0.8114) time: 0.1535 data: 0.0531 max mem: 9390 +Train: [79] [2200/6250] eta: 0:13:37 lr: 0.000014 grad: 0.1257 (0.1314) loss: 0.8113 (0.8114) time: 0.4095 data: 0.3086 max mem: 9390 +Train: [79] [2300/6250] eta: 0:13:12 lr: 0.000014 grad: 0.1271 (0.1311) loss: 0.8027 (0.8113) time: 0.2418 data: 0.1354 max mem: 9390 +Train: [79] [2400/6250] eta: 0:12:54 lr: 0.000014 grad: 0.1324 (0.1311) loss: 0.7990 (0.8111) time: 0.2776 data: 0.1551 max mem: 9390 +Train: [79] [2500/6250] eta: 0:12:30 lr: 0.000014 grad: 0.1275 (0.1310) loss: 0.8104 (0.8111) time: 0.1431 data: 0.0439 max mem: 9390 +Train: [79] [2600/6250] eta: 0:12:21 lr: 0.000014 grad: 0.1281 (0.1309) loss: 0.8111 (0.8110) time: 0.1276 data: 0.0006 max mem: 9390 +Train: [79] [2700/6250] eta: 0:11:56 lr: 0.000014 grad: 0.1293 (0.1309) loss: 0.8104 (0.8109) time: 0.1653 data: 0.0733 max mem: 9390 +Train: [79] [2800/6250] eta: 0:11:36 lr: 0.000014 grad: 0.1226 (0.1308) loss: 0.8129 (0.8108) time: 0.2316 data: 0.0605 max mem: 9390 +Train: [79] [2900/6250] eta: 0:11:12 lr: 0.000014 grad: 0.1235 (0.1309) loss: 0.8077 (0.8107) time: 0.2012 data: 0.1115 max mem: 9390 +Train: [79] [3000/6250] eta: 0:10:53 lr: 0.000014 grad: 0.1256 (0.1309) loss: 0.8077 (0.8106) time: 0.1240 data: 0.0329 max mem: 9390 +Train: [79] [3100/6250] eta: 0:10:31 lr: 0.000014 grad: 0.1225 (0.1309) loss: 0.8094 (0.8105) time: 0.2052 data: 0.1113 max mem: 9390 +Train: [79] [3200/6250] eta: 0:10:11 lr: 0.000014 grad: 0.1252 (0.1309) loss: 0.8087 (0.8104) time: 0.2231 data: 0.1415 max mem: 9390 +Train: [79] [3300/6250] eta: 0:09:50 lr: 0.000014 grad: 0.1222 (0.1309) loss: 0.8042 (0.8102) time: 0.2110 data: 0.1213 max mem: 9390 +Train: [79] [3400/6250] eta: 0:09:28 lr: 0.000014 grad: 0.1252 (0.1309) loss: 0.8156 (0.8102) time: 0.1528 data: 0.0506 max mem: 9390 +Train: [79] [3500/6250] eta: 0:09:09 lr: 0.000014 grad: 0.1279 (0.1310) loss: 0.8111 (0.8101) time: 0.2409 data: 0.1645 max mem: 9390 +Train: [79] [3600/6250] eta: 0:08:47 lr: 0.000014 grad: 0.1226 (0.1310) loss: 0.8132 (0.8101) time: 0.1971 data: 0.0989 max mem: 9390 +Train: [79] [3700/6250] eta: 0:08:30 lr: 0.000014 grad: 0.1245 (0.1311) loss: 0.8101 (0.8101) time: 0.1335 data: 0.0117 max mem: 9390 +Train: [79] [3800/6250] eta: 0:08:07 lr: 0.000014 grad: 0.1281 (0.1311) loss: 0.8074 (0.8101) time: 0.1839 data: 0.0960 max mem: 9390 +Train: [79] [3900/6250] eta: 0:07:46 lr: 0.000014 grad: 0.1255 (0.1311) loss: 0.8121 (0.8101) time: 0.1352 data: 0.0453 max mem: 9390 +Train: [79] [4000/6250] eta: 0:07:27 lr: 0.000014 grad: 0.1227 (0.1310) loss: 0.8123 (0.8101) time: 0.2704 data: 0.1816 max mem: 9390 +Train: [79] [4100/6250] eta: 0:07:07 lr: 0.000014 grad: 0.1232 (0.1309) loss: 0.8148 (0.8102) time: 0.1953 data: 0.1041 max mem: 9390 +Train: [79] [4200/6250] eta: 0:06:47 lr: 0.000014 grad: 0.1292 (0.1309) loss: 0.8118 (0.8103) time: 0.2063 data: 0.1048 max mem: 9390 +Train: [79] [4300/6250] eta: 0:06:26 lr: 0.000014 grad: 0.1247 (0.1308) loss: 0.8194 (0.8103) time: 0.2125 data: 0.1303 max mem: 9390 +Train: [79] [4400/6250] eta: 0:06:07 lr: 0.000014 grad: 0.1357 (0.1308) loss: 0.8069 (0.8104) time: 0.3023 data: 0.1805 max mem: 9390 +Train: [79] [4500/6250] eta: 0:05:46 lr: 0.000014 grad: 0.1338 (0.1309) loss: 0.8013 (0.8104) time: 0.1871 data: 0.0953 max mem: 9390 +Train: [79] [4600/6250] eta: 0:05:26 lr: 0.000014 grad: 0.1308 (0.1310) loss: 0.8032 (0.8103) time: 0.1472 data: 0.0547 max mem: 9390 +Train: [79] [4700/6250] eta: 0:05:05 lr: 0.000013 grad: 0.1313 (0.1310) loss: 0.8101 (0.8103) time: 0.1704 data: 0.0860 max mem: 9390 +Train: [79] [4800/6250] eta: 0:04:45 lr: 0.000013 grad: 0.1349 (0.1310) loss: 0.8099 (0.8103) time: 0.1753 data: 0.0887 max mem: 9390 +Train: [79] [4900/6250] eta: 0:04:25 lr: 0.000013 grad: 0.1244 (0.1310) loss: 0.8167 (0.8103) time: 0.2042 data: 0.1240 max mem: 9390 +Train: [79] [5000/6250] eta: 0:04:06 lr: 0.000013 grad: 0.1335 (0.1310) loss: 0.8045 (0.8103) time: 0.3319 data: 0.2464 max mem: 9390 +Train: [79] [5100/6250] eta: 0:03:46 lr: 0.000013 grad: 0.1267 (0.1310) loss: 0.8089 (0.8103) time: 0.2709 data: 0.1871 max mem: 9390 +Train: [79] [5200/6250] eta: 0:03:26 lr: 0.000013 grad: 0.1314 (0.1311) loss: 0.8070 (0.8103) time: 0.2623 data: 0.1567 max mem: 9390 +Train: [79] [5300/6250] eta: 0:03:06 lr: 0.000013 grad: 0.1241 (0.1311) loss: 0.8111 (0.8103) time: 0.1697 data: 0.0827 max mem: 9390 +Train: [79] [5400/6250] eta: 0:02:46 lr: 0.000013 grad: 0.1330 (0.1312) loss: 0.8096 (0.8103) time: 0.1890 data: 0.0953 max mem: 9390 +Train: [79] [5500/6250] eta: 0:02:27 lr: 0.000013 grad: 0.1348 (0.1313) loss: 0.8067 (0.8102) time: 0.1882 data: 0.0994 max mem: 9390 +Train: [79] [5600/6250] eta: 0:02:08 lr: 0.000013 grad: 0.1262 (0.1314) loss: 0.8040 (0.8102) time: 0.1859 data: 0.1002 max mem: 9390 +Train: [79] [5700/6250] eta: 0:01:48 lr: 0.000013 grad: 0.1273 (0.1314) loss: 0.8064 (0.8101) time: 0.2068 data: 0.1207 max mem: 9390 +Train: [79] [5800/6250] eta: 0:01:28 lr: 0.000013 grad: 0.1358 (0.1314) loss: 0.8065 (0.8101) time: 0.1773 data: 0.0954 max mem: 9390 +Train: [79] [5900/6250] eta: 0:01:09 lr: 0.000013 grad: 0.1293 (0.1315) loss: 0.8094 (0.8100) time: 0.3737 data: 0.2669 max mem: 9390 +Train: [79] [6000/6250] eta: 0:00:49 lr: 0.000013 grad: 0.1252 (0.1315) loss: 0.8153 (0.8100) time: 0.1818 data: 0.0770 max mem: 9390 +Train: [79] [6100/6250] eta: 0:00:29 lr: 0.000013 grad: 0.1308 (0.1314) loss: 0.8111 (0.8100) time: 0.2031 data: 0.1142 max mem: 9390 +Train: [79] [6200/6250] eta: 0:00:09 lr: 0.000013 grad: 0.1338 (0.1315) loss: 0.7999 (0.8099) time: 0.1724 data: 0.0848 max mem: 9390 +Train: [79] [6249/6250] eta: 0:00:00 lr: 0.000013 grad: 0.1214 (0.1315) loss: 0.8069 (0.8099) time: 0.1658 data: 0.0669 max mem: 9390 +Train: [79] Total time: 0:20:50 (0.2001 s / it) +Averaged stats: lr: 0.000013 grad: 0.1214 (0.1315) loss: 0.8069 (0.8099) +Eval (hcp-train-subset): [79] [ 0/62] eta: 0:04:13 loss: 0.8341 (0.8341) time: 4.0845 data: 3.9837 max mem: 9390 +Eval (hcp-train-subset): [79] [61/62] eta: 0:00:00 loss: 0.8234 (0.8248) time: 0.1105 data: 0.0835 max mem: 9390 +Eval (hcp-train-subset): [79] Total time: 0:00:17 (0.2742 s / it) +Averaged stats (hcp-train-subset): loss: 0.8234 (0.8248) +Making plots (hcp-train-subset): example=49 +Eval (hcp-val): [79] [ 0/62] eta: 0:04:34 loss: 0.8294 (0.8294) time: 4.4324 data: 4.3404 max mem: 9390 +Eval (hcp-val): [79] [61/62] eta: 0:00:00 loss: 0.8288 (0.8305) time: 0.1453 data: 0.1199 max mem: 9390 +Eval (hcp-val): [79] Total time: 0:00:17 (0.2771 s / it) +Averaged stats (hcp-val): loss: 0.8288 (0.8305) +Making plots (hcp-val): example=37 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +Train: [80] [ 0/6250] eta: 9:58:20 lr: 0.000013 grad: 0.3526 (0.3526) loss: 0.7815 (0.7815) time: 5.7441 data: 5.3286 max mem: 9390 +Train: [80] [ 100/6250] eta: 0:23:45 lr: 0.000013 grad: 0.1431 (0.1531) loss: 0.8195 (0.8330) time: 0.1569 data: 0.0425 max mem: 9390 +Train: [80] [ 200/6250] eta: 0:21:34 lr: 0.000013 grad: 0.1348 (0.1448) loss: 0.8149 (0.8284) time: 0.1985 data: 0.0932 max mem: 9390 +Train: [80] [ 300/6250] eta: 0:20:26 lr: 0.000013 grad: 0.1105 (0.1386) loss: 0.8318 (0.8263) time: 0.1693 data: 0.0771 max mem: 9390 +Train: [80] [ 400/6250] eta: 0:19:33 lr: 0.000013 grad: 0.1266 (0.1350) loss: 0.8217 (0.8248) time: 0.1634 data: 0.0884 max mem: 9390 +Train: [80] [ 500/6250] eta: 0:18:53 lr: 0.000013 grad: 0.1194 (0.1329) loss: 0.8180 (0.8235) time: 0.1750 data: 0.0695 max mem: 9390 +Train: [80] [ 600/6250] eta: 0:18:09 lr: 0.000013 grad: 0.1236 (0.1319) loss: 0.8224 (0.8225) time: 0.1672 data: 0.0651 max mem: 9390 +Train: [80] [ 700/6250] eta: 0:17:34 lr: 0.000013 grad: 0.1243 (0.1313) loss: 0.8215 (0.8219) time: 0.1749 data: 0.0811 max mem: 9390 +Train: [80] [ 800/6250] eta: 0:17:16 lr: 0.000013 grad: 0.1139 (0.1306) loss: 0.8161 (0.8215) time: 0.1340 data: 0.0275 max mem: 9390 +Train: [80] [ 900/6250] eta: 0:17:10 lr: 0.000013 grad: 0.1225 (0.1304) loss: 0.8129 (0.8206) time: 0.2846 data: 0.1878 max mem: 9390 +Train: [80] [1000/6250] eta: 0:16:52 lr: 0.000013 grad: 0.1148 (0.1297) loss: 0.8128 (0.8200) time: 0.1827 data: 0.0768 max mem: 9390 +Train: [80] [1100/6250] eta: 0:17:07 lr: 0.000013 grad: 0.1267 (0.1294) loss: 0.8139 (0.8194) time: 0.2807 data: 0.1579 max mem: 9390 +Train: [80] [1200/6250] eta: 0:16:45 lr: 0.000013 grad: 0.1300 (0.1291) loss: 0.8141 (0.8191) time: 0.2161 data: 0.1285 max mem: 9390 +Train: [80] [1300/6250] eta: 0:16:32 lr: 0.000013 grad: 0.1310 (0.1291) loss: 0.8125 (0.8186) time: 0.2992 data: 0.1978 max mem: 9390 +Train: [80] [1400/6250] eta: 0:16:23 lr: 0.000013 grad: 0.1243 (0.1291) loss: 0.8104 (0.8180) time: 0.3278 data: 0.2110 max mem: 9390 +Train: [80] [1500/6250] eta: 0:15:57 lr: 0.000013 grad: 0.1252 (0.1292) loss: 0.8110 (0.8174) time: 0.2349 data: 0.1226 max mem: 9390 +Train: [80] [1600/6250] eta: 0:15:28 lr: 0.000013 grad: 0.1215 (0.1293) loss: 0.8158 (0.8170) time: 0.1747 data: 0.0900 max mem: 9390 +Train: [80] [1700/6250] eta: 0:15:12 lr: 0.000013 grad: 0.1317 (0.1294) loss: 0.8083 (0.8165) time: 0.3126 data: 0.2180 max mem: 9390 +Train: [80] [1800/6250] eta: 0:14:55 lr: 0.000013 grad: 0.1402 (0.1297) loss: 0.8041 (0.8162) time: 0.1315 data: 0.0397 max mem: 9390 +Train: [80] [1900/6250] eta: 0:14:37 lr: 0.000013 grad: 0.1282 (0.1298) loss: 0.8078 (0.8160) time: 0.2675 data: 0.1586 max mem: 9390 +Train: [80] [2000/6250] eta: 0:14:19 lr: 0.000013 grad: 0.1265 (0.1300) loss: 0.8118 (0.8158) time: 0.2085 data: 0.1133 max mem: 9390 +Train: [80] [2100/6250] eta: 0:13:52 lr: 0.000013 grad: 0.1374 (0.1302) loss: 0.8047 (0.8154) time: 0.1494 data: 0.0586 max mem: 9390 +Train: [80] [2200/6250] eta: 0:13:31 lr: 0.000013 grad: 0.1356 (0.1304) loss: 0.8059 (0.8151) time: 0.1911 data: 0.1054 max mem: 9390 +Train: [80] [2300/6250] eta: 0:13:12 lr: 0.000013 grad: 0.1283 (0.1305) loss: 0.8130 (0.8148) time: 0.2110 data: 0.1321 max mem: 9390 +Train: [80] [2400/6250] eta: 0:12:57 lr: 0.000013 grad: 0.1334 (0.1306) loss: 0.8051 (0.8146) time: 0.3315 data: 0.2373 max mem: 9390 +Train: [80] [2500/6250] eta: 0:12:39 lr: 0.000013 grad: 0.1344 (0.1308) loss: 0.8110 (0.8144) time: 0.1794 data: 0.0695 max mem: 9390 +Train: [80] [2600/6250] eta: 0:12:14 lr: 0.000013 grad: 0.1279 (0.1309) loss: 0.8091 (0.8143) time: 0.1811 data: 0.0944 max mem: 9390 +Train: [80] [2700/6250] eta: 0:11:52 lr: 0.000013 grad: 0.1267 (0.1309) loss: 0.8085 (0.8142) time: 0.2210 data: 0.1246 max mem: 9390 +Train: [80] [2800/6250] eta: 0:11:33 lr: 0.000013 grad: 0.1266 (0.1309) loss: 0.8199 (0.8141) time: 0.2690 data: 0.1916 max mem: 9390 +Train: [80] [2900/6250] eta: 0:11:08 lr: 0.000013 grad: 0.1244 (0.1309) loss: 0.8114 (0.8141) time: 0.1221 data: 0.0117 max mem: 9390 +Train: [80] [3000/6250] eta: 0:10:46 lr: 0.000013 grad: 0.1371 (0.1310) loss: 0.8119 (0.8139) time: 0.2256 data: 0.1155 max mem: 9390 +Train: [80] [3100/6250] eta: 0:10:25 lr: 0.000013 grad: 0.1282 (0.1311) loss: 0.8135 (0.8138) time: 0.1765 data: 0.0812 max mem: 9390 +Train: [80] [3200/6250] eta: 0:10:06 lr: 0.000013 grad: 0.1208 (0.1311) loss: 0.8139 (0.8138) time: 0.1111 data: 0.0003 max mem: 9390 +Train: [80] [3300/6250] eta: 0:09:44 lr: 0.000013 grad: 0.1231 (0.1310) loss: 0.8062 (0.8136) time: 0.1762 data: 0.0824 max mem: 9390 +Train: [80] [3400/6250] eta: 0:09:25 lr: 0.000012 grad: 0.1207 (0.1309) loss: 0.8125 (0.8136) time: 0.2012 data: 0.1142 max mem: 9390 +Train: [80] [3500/6250] eta: 0:09:04 lr: 0.000012 grad: 0.1227 (0.1310) loss: 0.8069 (0.8135) time: 0.1880 data: 0.0993 max mem: 9390 +Train: [80] [3600/6250] eta: 0:08:45 lr: 0.000012 grad: 0.1212 (0.1309) loss: 0.8139 (0.8135) time: 0.1796 data: 0.0657 max mem: 9390 +Train: [80] [3700/6250] eta: 0:08:24 lr: 0.000012 grad: 0.1231 (0.1308) loss: 0.8034 (0.8133) time: 0.1825 data: 0.0959 max mem: 9390 +Train: [80] [3800/6250] eta: 0:08:04 lr: 0.000012 grad: 0.1261 (0.1308) loss: 0.8019 (0.8133) time: 0.1505 data: 0.0698 max mem: 9390 +Train: [80] [3900/6250] eta: 0:07:46 lr: 0.000012 grad: 0.1263 (0.1307) loss: 0.8099 (0.8131) time: 0.2553 data: 0.1409 max mem: 9390 +Train: [80] [4000/6250] eta: 0:07:26 lr: 0.000012 grad: 0.1245 (0.1307) loss: 0.8102 (0.8130) time: 0.1799 data: 0.0924 max mem: 9390 +Train: [80] [4100/6250] eta: 0:07:08 lr: 0.000012 grad: 0.1309 (0.1307) loss: 0.8049 (0.8128) time: 0.3412 data: 0.2604 max mem: 9390 +Train: [80] [4200/6250] eta: 0:06:47 lr: 0.000012 grad: 0.1308 (0.1308) loss: 0.8025 (0.8126) time: 0.1980 data: 0.1230 max mem: 9390 +Train: [80] [4300/6250] eta: 0:06:27 lr: 0.000012 grad: 0.1317 (0.1308) loss: 0.8099 (0.8125) time: 0.1886 data: 0.1084 max mem: 9390 +Train: [80] [4400/6250] eta: 0:06:06 lr: 0.000012 grad: 0.1249 (0.1308) loss: 0.8110 (0.8124) time: 0.1684 data: 0.0776 max mem: 9390 +Train: [80] [4500/6250] eta: 0:05:46 lr: 0.000012 grad: 0.1353 (0.1309) loss: 0.8076 (0.8122) time: 0.1906 data: 0.1006 max mem: 9390 +Train: [80] [4600/6250] eta: 0:05:26 lr: 0.000012 grad: 0.1318 (0.1309) loss: 0.8037 (0.8121) time: 0.1797 data: 0.1006 max mem: 9390 +Train: [80] [4700/6250] eta: 0:05:06 lr: 0.000012 grad: 0.1266 (0.1309) loss: 0.8032 (0.8120) time: 0.1813 data: 0.0759 max mem: 9390 +Train: [80] [4800/6250] eta: 0:04:45 lr: 0.000012 grad: 0.1294 (0.1309) loss: 0.8056 (0.8118) time: 0.1822 data: 0.0927 max mem: 9390 +Train: [80] [4900/6250] eta: 0:04:25 lr: 0.000012 grad: 0.1306 (0.1310) loss: 0.8055 (0.8118) time: 0.1591 data: 0.0741 max mem: 9390 +Train: [80] [5000/6250] eta: 0:04:04 lr: 0.000012 grad: 0.1277 (0.1310) loss: 0.8051 (0.8117) time: 0.1716 data: 0.0854 max mem: 9390 +Train: [80] [5100/6250] eta: 0:03:44 lr: 0.000012 grad: 0.1216 (0.1310) loss: 0.8040 (0.8116) time: 0.1970 data: 0.1113 max mem: 9390 +Train: [80] [5200/6250] eta: 0:03:24 lr: 0.000012 grad: 0.1224 (0.1310) loss: 0.8123 (0.8115) time: 0.1596 data: 0.0748 max mem: 9390 +Train: [80] [5300/6250] eta: 0:03:06 lr: 0.000012 grad: 0.1289 (0.1310) loss: 0.8097 (0.8114) time: 0.2632 data: 0.1782 max mem: 9390 +Train: [80] [5400/6250] eta: 0:02:46 lr: 0.000012 grad: 0.1251 (0.1311) loss: 0.8068 (0.8114) time: 0.1687 data: 0.0744 max mem: 9390 +Train: [80] [5500/6250] eta: 0:02:27 lr: 0.000012 grad: 0.1266 (0.1312) loss: 0.8128 (0.8114) time: 0.1985 data: 0.0841 max mem: 9390 +Train: [80] [5600/6250] eta: 0:02:08 lr: 0.000012 grad: 0.1253 (0.1312) loss: 0.8105 (0.8114) time: 0.3365 data: 0.2225 max mem: 9390 +Train: [80] [5700/6250] eta: 0:01:48 lr: 0.000012 grad: 0.1331 (0.1312) loss: 0.8092 (0.8114) time: 0.0933 data: 0.0002 max mem: 9390 +Train: [80] [5800/6250] eta: 0:01:28 lr: 0.000012 grad: 0.1301 (0.1312) loss: 0.8132 (0.8113) time: 0.1923 data: 0.0895 max mem: 9390 +Train: [80] [5900/6250] eta: 0:01:09 lr: 0.000012 grad: 0.1213 (0.1313) loss: 0.8147 (0.8113) time: 0.2261 data: 0.1199 max mem: 9390 +Train: [80] [6000/6250] eta: 0:00:49 lr: 0.000012 grad: 0.1321 (0.1314) loss: 0.8176 (0.8113) time: 0.1069 data: 0.0006 max mem: 9390 +Train: [80] [6100/6250] eta: 0:00:29 lr: 0.000012 grad: 0.1316 (0.1314) loss: 0.8101 (0.8113) time: 0.1431 data: 0.0003 max mem: 9390 +Train: [80] [6200/6250] eta: 0:00:09 lr: 0.000012 grad: 0.1350 (0.1316) loss: 0.8094 (0.8113) time: 0.3801 data: 0.2608 max mem: 9390 +Train: [80] [6249/6250] eta: 0:00:00 lr: 0.000012 grad: 0.1389 (0.1317) loss: 0.8083 (0.8113) time: 0.1985 data: 0.1037 max mem: 9390 +Train: [80] Total time: 0:20:51 (0.2002 s / it) +Averaged stats: lr: 0.000012 grad: 0.1389 (0.1317) loss: 0.8083 (0.8113) +Eval (hcp-train-subset): [80] [ 0/62] eta: 0:04:19 loss: 0.8297 (0.8297) time: 4.1875 data: 4.1184 max mem: 9390 +Eval (hcp-train-subset): [80] [61/62] eta: 0:00:00 loss: 0.8212 (0.8224) time: 0.1325 data: 0.1059 max mem: 9390 +Eval (hcp-train-subset): [80] Total time: 0:00:15 (0.2443 s / it) +Averaged stats (hcp-train-subset): loss: 0.8212 (0.8224) +Eval (hcp-val): [80] [ 0/62] eta: 0:06:36 loss: 0.8281 (0.8281) time: 6.3882 data: 6.3554 max mem: 9390 +Eval (hcp-val): [80] [61/62] eta: 0:00:00 loss: 0.8293 (0.8300) time: 0.1522 data: 0.1264 max mem: 9390 +Eval (hcp-val): [80] Total time: 0:00:15 (0.2528 s / it) +Averaged stats (hcp-val): loss: 0.8293 (0.8300) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +Train: [81] [ 0/6250] eta: 8:25:33 lr: 0.000012 grad: 0.0876 (0.0876) loss: 0.8776 (0.8776) time: 4.8533 data: 4.6956 max mem: 9390 +Train: [81] [ 100/6250] eta: 0:26:13 lr: 0.000012 grad: 0.1347 (0.1571) loss: 0.8177 (0.8248) time: 0.2034 data: 0.0959 max mem: 9390 +Train: [81] [ 200/6250] eta: 0:22:58 lr: 0.000012 grad: 0.1334 (0.1516) loss: 0.8202 (0.8199) time: 0.1534 data: 0.0562 max mem: 9390 +Train: [81] [ 300/6250] eta: 0:20:57 lr: 0.000012 grad: 0.1509 (0.1486) loss: 0.8160 (0.8184) time: 0.1654 data: 0.0698 max mem: 9390 +Train: [81] [ 400/6250] eta: 0:19:28 lr: 0.000012 grad: 0.1286 (0.1466) loss: 0.8076 (0.8169) time: 0.1626 data: 0.0615 max mem: 9390 +Train: [81] [ 500/6250] eta: 0:18:49 lr: 0.000012 grad: 0.1329 (0.1451) loss: 0.8126 (0.8159) time: 0.1757 data: 0.0711 max mem: 9390 +Train: [81] [ 600/6250] eta: 0:18:07 lr: 0.000012 grad: 0.1436 (0.1440) loss: 0.8086 (0.8154) time: 0.1866 data: 0.0908 max mem: 9390 +Train: [81] [ 700/6250] eta: 0:17:35 lr: 0.000012 grad: 0.1229 (0.1429) loss: 0.8127 (0.8149) time: 0.1804 data: 0.0788 max mem: 9390 +Train: [81] [ 800/6250] eta: 0:17:01 lr: 0.000012 grad: 0.1422 (0.1419) loss: 0.8082 (0.8144) time: 0.1422 data: 0.0429 max mem: 9390 +Train: [81] [ 900/6250] eta: 0:16:37 lr: 0.000012 grad: 0.1355 (0.1406) loss: 0.8084 (0.8144) time: 0.1952 data: 0.1069 max mem: 9390 +Train: [81] [1000/6250] eta: 0:16:14 lr: 0.000012 grad: 0.1289 (0.1399) loss: 0.8159 (0.8145) time: 0.1829 data: 0.0902 max mem: 9390 +Train: [81] [1100/6250] eta: 0:16:00 lr: 0.000012 grad: 0.1336 (0.1390) loss: 0.8128 (0.8144) time: 0.2474 data: 0.1681 max mem: 9390 +Train: [81] [1200/6250] eta: 0:15:59 lr: 0.000012 grad: 0.1219 (0.1379) loss: 0.8160 (0.8144) time: 0.2639 data: 0.1846 max mem: 9390 +pretraining fmri mae +start: 2026-04-01 13:10:38 +cwd: /data/connor/fmri-fm +sha: 7f4cedc35609f6857314e0d1ea6657523f17ddeb, status: has uncommitted changes, branch: dev/clane9 +config: +name: input_space_v3/flat_lr1e-3_1/pretrain +notes: input_space ablation v3 flat_lr1e-3_1; use tube masking and on-disk data (input_space=flat + base_lr=1e-3 seed=5401) +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain +input_space: flat +patch_size: 16 +num_frames: 16 +t_patch_size: 4 +mask_ratio: 0.9 +pred_mask_ratio: null +masking: tube +masking_kwargs: {} +mask_patch_size: null +model: mae_vit_base +model_kwargs: + decoding: attn + pos_embed: sep + target_norm: null + pca_norm_nc: 2 + t_pred_stride: 2 + no_decode_pos: true + mask_drop_scale: false + pred_edge_pad: 0 + gauss_sigma: null + class_token: true + reg_tokens: 0 + no_embed_class: true + head_init_scale: 0.0 + decoder_depth: 4 + drop_path_rate: 0.0 +datasets: + hcp-train: + type: wds + url: /data/fmri-datasets/pretrain/hcpya-all.${input_space}.wds/hcpya-all-${input_space}-{00000..01799}.tar + clipping: random + clipping_kwargs: + oversample: 4.0 + shuffle: true + buffer_size: 2000 + samples_per_epoch: 200000 + hcp-train-subset: + type: arrow + root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/validation + split_range: + - 0 + - 2000 + shuffle: false + hcp-val: + type: arrow + root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/test + split_range: + - 0 + - 2000 + shuffle: false +train_dataset: hcp-train +eval_datasets: +- hcp-train-subset +- hcp-val +val_dataset: null +clip_vmax: 3.0 +normalize: frame +tr_scale: null +crop_scale: null +crop_aspect: null +gray_jitter: null +num_workers: 16 +epochs: 100 +batch_size: 32 +accum_iter: 1 +base_lr: 0.001 +min_lr: 0.0 +warmup_epochs: 5 +weight_decay: 0.05 +betas: +- 0.9 +- 0.95 +clip_grad: 1.0 +amp: true +amp_dtype: float16 +ckpt: null +resume: true +auto_resume: true +start_epoch: 0 +max_checkpoints: 0 +checkpoint_period: null +plot_period: 5 +device: cuda +presend_cuda: false +seed: 5401 +debug: false +wandb: true +wandb_entity: null +wandb_project: fMRI-foundation-model +rank: 0 +world_size: 1 +gpu: 0 +distributed: true +dist_backend: nccl +in_chans: 1 +img_size: +- 224 +- 560 + +train transform: +Compose( + ToTensor() + TemporalCenterCrop(num_frames=16) + Normalize(mode='frame') + Clip(vmax=3.0) + FlatUnmask((224, 560)) +) +val transform: +Compose( + ToTensor() + TemporalCenterCrop(num_frames=16) + Normalize(mode='frame') + Clip(vmax=3.0) + FlatUnmask((224, 560)) +) +mask generator: +TubeMasking( + mask_ratio=0.9 + (patchify): Patchify2D((224, 560), (16, 16), in_chans=1) +) +loading dataset: hcp-train + +type: wds +url: /data/fmri-datasets/pretrain/hcpya-all.${input_space}.wds/hcpya-all-${input_space}-{00000..01799}.tar +clipping: random +clipping_kwargs: + oversample: 4.0 +shuffle: true +buffer_size: 2000 +samples_per_epoch: 200000 + +loading dataset: hcp-train-subset + +type: arrow +root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/validation +split_range: +- 0 +- 2000 +shuffle: false + +split indices: [899, 472, 767, 116, 1265, 1852, 300, 1335, 361, 1560] +loading dataset: hcp-val + +type: arrow +root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/test +split_range: +- 0 +- 2000 +shuffle: false + +split indices: [1075, 1189, 738, 1350, 965, 1964, 1367, 1183, 1619, 1407] +model: +MaskedAutoencoderViT( + decoding=attn, t_pred_stride=2, pred_edge_pad=0, no_decode_pos=True + (encoder): MaskedEncoder( + class_token=True, reg_tokens=0, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) + (pred_patchify): StridedPatchify3D((16, 224, 560), (2, 16, 16), in_chans=1, t_stride=2) + (decoder): MaskedDecoder( + cross_decode=False, class_token=True, no_embed_class=True + (pos_embed): SeparablePosEmbed(512, (4, 14, 35)) + (proj): Linear(in_features=768, out_features=512, bias=True) + (blocks): ModuleList( + (0-3): 4 x Block( + (norm1): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=16 + (q): Linear(in_features=512, out_features=512, bias=True) + (k): Linear(in_features=512, out_features=512, bias=True) + (v): Linear(in_features=512, out_features=512, bias=True) + (proj): Linear(in_features=512, out_features=512, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=512, out_features=2048, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=2048, out_features=512, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (head): Linear(in_features=512, out_features=512, bias=True) + ) +) +num params: 99.7M +total batch size: 32 = 32 bs per gpu x 1 accum x 1 gpus +lr: 1.25e-04 = 1.00e-03 x 32 / 256 +full schedule: epochs = 100 (steps = 625000) +warmup: epochs = 5 (steps = 31250) +loaded model state from checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +loaded optimizer state, resuming training from 81 +start training for 100 epochs +Train: [81] [ 0/6250] eta: 1 day, 16:07:32 lr: 0.000012 grad: 0.3147 (0.3147) loss: 0.8486 (0.8486) time: 23.1123 data: 19.9766 max mem: 9353 +Train: [81] [ 100/6250] eta: 1:59:06 lr: 0.000012 grad: 0.1671 (0.1945) loss: 0.8114 (0.8051) time: 0.6165 data: 0.5212 max mem: 9390 +Train: [81] [ 200/6250] eta: 1:35:10 lr: 0.000012 grad: 0.1340 (0.1723) loss: 0.8055 (0.8027) time: 0.1315 data: 0.0003 max mem: 9390 +Train: [81] [ 300/6250] eta: 1:21:44 lr: 0.000012 grad: 0.1269 (0.1598) loss: 0.8117 (0.8049) time: 1.7273 data: 1.6117 max mem: 9390 +Train: [81] [ 400/6250] eta: 1:20:48 lr: 0.000012 grad: 0.1323 (0.1539) loss: 0.8054 (0.8067) time: 0.2800 data: 0.1613 max mem: 9390 +Train: [81] [ 500/6250] eta: 1:16:08 lr: 0.000012 grad: 0.1418 (0.1506) loss: 0.8071 (0.8075) time: 0.5146 data: 0.3993 max mem: 9390 +Train: [81] [ 600/6250] eta: 1:13:23 lr: 0.000012 grad: 0.1337 (0.1488) loss: 0.8057 (0.8075) time: 0.6972 data: 0.6026 max mem: 9390 +Train: [81] [ 700/6250] eta: 1:13:32 lr: 0.000012 grad: 0.1299 (0.1475) loss: 0.8134 (0.8077) time: 0.4713 data: 0.3206 max mem: 9390 +Train: [81] [ 800/6250] eta: 1:10:39 lr: 0.000012 grad: 0.1312 (0.1460) loss: 0.8079 (0.8079) time: 0.7097 data: 0.5773 max mem: 9390 +Train: [81] [ 900/6250] eta: 1:05:15 lr: 0.000012 grad: 0.1321 (0.1444) loss: 0.8097 (0.8085) time: 0.1726 data: 0.0728 max mem: 9390 +Train: [81] [1000/6250] eta: 1:00:49 lr: 0.000012 grad: 0.1294 (0.1433) loss: 0.8129 (0.8091) time: 0.2347 data: 0.1403 max mem: 9390 +Train: [81] [1100/6250] eta: 0:56:26 lr: 0.000012 grad: 0.1215 (0.1421) loss: 0.8172 (0.8096) time: 0.3035 data: 0.2103 max mem: 9390 +Train: [81] [1200/6250] eta: 0:52:05 lr: 0.000012 grad: 0.1246 (0.1411) loss: 0.8087 (0.8098) time: 0.1011 data: 0.0002 max mem: 9390 +Train: [81] [1300/6250] eta: 0:49:11 lr: 0.000012 grad: 0.1246 (0.1402) loss: 0.8147 (0.8101) time: 0.1214 data: 0.0005 max mem: 9390 +Train: [81] [1400/6250] eta: 0:45:54 lr: 0.000012 grad: 0.1298 (0.1394) loss: 0.8074 (0.8102) time: 0.2011 data: 0.1099 max mem: 9390 +Train: [81] [1500/6250] eta: 0:42:54 lr: 0.000012 grad: 0.1345 (0.1389) loss: 0.8113 (0.8101) time: 0.1478 data: 0.0550 max mem: 9390 +Train: [81] [1600/6250] eta: 0:40:14 lr: 0.000012 grad: 0.1260 (0.1385) loss: 0.8074 (0.8100) time: 0.1647 data: 0.0613 max mem: 9390 +Train: [81] [1700/6250] eta: 0:37:58 lr: 0.000012 grad: 0.1337 (0.1386) loss: 0.8077 (0.8100) time: 0.2080 data: 0.1119 max mem: 9390 +Train: [81] [1800/6250] eta: 0:35:56 lr: 0.000012 grad: 0.1411 (0.1384) loss: 0.8082 (0.8100) time: 0.1131 data: 0.0003 max mem: 9390 +Train: [81] [1900/6250] eta: 0:34:56 lr: 0.000012 grad: 0.1304 (0.1382) loss: 0.8135 (0.8100) time: 0.3940 data: 0.2774 max mem: 9390 +Train: [81] [2000/6250] eta: 0:33:13 lr: 0.000012 grad: 0.1262 (0.1379) loss: 0.8080 (0.8100) time: 0.1697 data: 0.0703 max mem: 9390 +Train: [81] [2100/6250] eta: 0:32:57 lr: 0.000012 grad: 0.1332 (0.1376) loss: 0.8054 (0.8100) time: 0.8825 data: 0.7724 max mem: 9390 +Train: [81] [2200/6250] eta: 0:32:09 lr: 0.000012 grad: 0.1377 (0.1375) loss: 0.8172 (0.8100) time: 0.1363 data: 0.0004 max mem: 9390 +Train: [81] [2300/6250] eta: 0:31:28 lr: 0.000011 grad: 0.1318 (0.1373) loss: 0.8037 (0.8100) time: 0.2328 data: 0.1443 max mem: 9390 +Train: [81] [2400/6250] eta: 0:30:12 lr: 0.000011 grad: 0.1236 (0.1372) loss: 0.8065 (0.8100) time: 0.5602 data: 0.4544 max mem: 9390 +Train: [81] [2500/6250] eta: 0:29:38 lr: 0.000011 grad: 0.1231 (0.1369) loss: 0.8115 (0.8101) time: 1.4431 data: 1.3346 max mem: 9390 +Train: [81] [2600/6250] eta: 0:28:39 lr: 0.000011 grad: 0.1320 (0.1368) loss: 0.8183 (0.8102) time: 0.1052 data: 0.0003 max mem: 9390 +Train: [81] [2700/6250] eta: 0:27:44 lr: 0.000011 grad: 0.1234 (0.1365) loss: 0.8160 (0.8103) time: 0.9045 data: 0.7772 max mem: 9390 +Train: [81] [2800/6250] eta: 0:26:55 lr: 0.000011 grad: 0.1306 (0.1363) loss: 0.8114 (0.8104) time: 0.1214 data: 0.0003 max mem: 9390 +Train: [81] [2900/6250] eta: 0:26:12 lr: 0.000011 grad: 0.1286 (0.1361) loss: 0.8126 (0.8105) time: 0.6866 data: 0.5573 max mem: 9390 +Train: [81] [3000/6250] eta: 0:25:25 lr: 0.000011 grad: 0.1219 (0.1360) loss: 0.8114 (0.8106) time: 0.1524 data: 0.0331 max mem: 9390 +Train: [81] [3100/6250] eta: 0:24:37 lr: 0.000011 grad: 0.1373 (0.1361) loss: 0.8102 (0.8105) time: 1.3778 data: 1.2777 max mem: 9390 +Train: [81] [3200/6250] eta: 0:23:40 lr: 0.000011 grad: 0.1286 (0.1360) loss: 0.8145 (0.8106) time: 0.1604 data: 0.0746 max mem: 9390 +Train: [81] [3300/6250] eta: 0:22:36 lr: 0.000011 grad: 0.1227 (0.1359) loss: 0.8123 (0.8107) time: 0.5346 data: 0.4452 max mem: 9390 +Train: [81] [3400/6250] eta: 0:21:28 lr: 0.000011 grad: 0.1286 (0.1358) loss: 0.8115 (0.8107) time: 0.1645 data: 0.0780 max mem: 9390 +Train: [81] [3500/6250] eta: 0:20:20 lr: 0.000011 grad: 0.1332 (0.1357) loss: 0.8162 (0.8108) time: 0.1622 data: 0.0728 max mem: 9390 +Train: [81] [3600/6250] eta: 0:19:15 lr: 0.000011 grad: 0.1335 (0.1355) loss: 0.8080 (0.8108) time: 0.1243 data: 0.0445 max mem: 9390 +Train: [81] [3700/6250] eta: 0:18:11 lr: 0.000011 grad: 0.1266 (0.1355) loss: 0.8139 (0.8108) time: 0.1490 data: 0.0654 max mem: 9390 +Train: [81] [3800/6250] eta: 0:17:11 lr: 0.000011 grad: 0.1288 (0.1355) loss: 0.8090 (0.8108) time: 0.1548 data: 0.0727 max mem: 9390 +Train: [81] [3900/6250] eta: 0:16:12 lr: 0.000011 grad: 0.1260 (0.1354) loss: 0.8061 (0.8108) time: 0.1401 data: 0.0597 max mem: 9390 +Train: [81] [4000/6250] eta: 0:15:16 lr: 0.000011 grad: 0.1281 (0.1353) loss: 0.8107 (0.8109) time: 0.1353 data: 0.0418 max mem: 9390 +Train: [81] [4100/6250] eta: 0:14:22 lr: 0.000011 grad: 0.1306 (0.1353) loss: 0.8121 (0.8108) time: 0.1588 data: 0.0711 max mem: 9390 +Train: [81] [4200/6250] eta: 0:13:30 lr: 0.000011 grad: 0.1335 (0.1352) loss: 0.8180 (0.8109) time: 0.1437 data: 0.0622 max mem: 9390 +Train: [81] [4300/6250] eta: 0:12:39 lr: 0.000011 grad: 0.1308 (0.1351) loss: 0.8108 (0.8109) time: 0.1346 data: 0.0520 max mem: 9390 +Train: [81] [4400/6250] eta: 0:11:50 lr: 0.000011 grad: 0.1270 (0.1351) loss: 0.8132 (0.8109) time: 0.1573 data: 0.0761 max mem: 9390 +Train: [81] [4500/6250] eta: 0:11:02 lr: 0.000011 grad: 0.1354 (0.1351) loss: 0.8055 (0.8109) time: 0.1576 data: 0.0763 max mem: 9390 +Train: [81] [4600/6250] eta: 0:10:16 lr: 0.000011 grad: 0.1376 (0.1352) loss: 0.8087 (0.8109) time: 0.1486 data: 0.0623 max mem: 9390 +Train: [81] [4700/6250] eta: 0:09:31 lr: 0.000011 grad: 0.1284 (0.1352) loss: 0.8080 (0.8108) time: 0.1573 data: 0.0754 max mem: 9390 +Train: [81] [4800/6250] eta: 0:08:48 lr: 0.000011 grad: 0.1377 (0.1353) loss: 0.8083 (0.8107) time: 0.1548 data: 0.0758 max mem: 9390 +Train: [81] [4900/6250] eta: 0:08:06 lr: 0.000011 grad: 0.1277 (0.1353) loss: 0.8098 (0.8107) time: 0.1624 data: 0.0772 max mem: 9390 +Train: [81] [5000/6250] eta: 0:07:24 lr: 0.000011 grad: 0.1452 (0.1354) loss: 0.7970 (0.8105) time: 0.1575 data: 0.0708 max mem: 9390 +Train: [81] [5100/6250] eta: 0:06:44 lr: 0.000011 grad: 0.1452 (0.1355) loss: 0.8058 (0.8104) time: 0.1578 data: 0.0746 max mem: 9390 +Train: [81] [5200/6250] eta: 0:06:05 lr: 0.000011 grad: 0.1389 (0.1356) loss: 0.8053 (0.8103) time: 0.1594 data: 0.0627 max mem: 9390 +Train: [81] [5300/6250] eta: 0:05:27 lr: 0.000011 grad: 0.1335 (0.1357) loss: 0.8071 (0.8102) time: 0.1724 data: 0.0858 max mem: 9390 +Train: [81] [5400/6250] eta: 0:04:49 lr: 0.000011 grad: 0.1320 (0.1356) loss: 0.8089 (0.8103) time: 0.1532 data: 0.0708 max mem: 9390 +Train: [81] [5500/6250] eta: 0:04:13 lr: 0.000011 grad: 0.1297 (0.1356) loss: 0.8096 (0.8103) time: 0.1559 data: 0.0677 max mem: 9390 +Train: [81] [5600/6250] eta: 0:03:37 lr: 0.000011 grad: 0.1316 (0.1355) loss: 0.8149 (0.8103) time: 0.1483 data: 0.0552 max mem: 9390 +Train: [81] [5700/6250] eta: 0:03:02 lr: 0.000011 grad: 0.1313 (0.1354) loss: 0.8084 (0.8103) time: 0.1556 data: 0.0670 max mem: 9390 +Train: [81] [5800/6250] eta: 0:02:27 lr: 0.000011 grad: 0.1224 (0.1354) loss: 0.8126 (0.8103) time: 0.1521 data: 0.0542 max mem: 9390 +Train: [81] [5900/6250] eta: 0:01:53 lr: 0.000011 grad: 0.1296 (0.1354) loss: 0.8082 (0.8103) time: 0.1502 data: 0.0757 max mem: 9390 +Train: [81] [6000/6250] eta: 0:01:20 lr: 0.000011 grad: 0.1325 (0.1354) loss: 0.8104 (0.8102) time: 0.1421 data: 0.0627 max mem: 9390 +Train: [81] [6100/6250] eta: 0:00:47 lr: 0.000011 grad: 0.1305 (0.1354) loss: 0.8082 (0.8102) time: 0.1524 data: 0.0566 max mem: 9390 +Train: [81] [6200/6250] eta: 0:00:15 lr: 0.000011 grad: 0.1462 (0.1354) loss: 0.8034 (0.8102) time: 0.1408 data: 0.0553 max mem: 9390 +Train: [81] [6249/6250] eta: 0:00:00 lr: 0.000011 grad: 0.1344 (0.1354) loss: 0.8056 (0.8101) time: 0.1260 data: 0.0397 max mem: 9390 +Train: [81] Total time: 0:32:59 (0.3168 s / it) +Averaged stats: lr: 0.000011 grad: 0.1344 (0.1354) loss: 0.8056 (0.8101) +Eval (hcp-train-subset): [81] [ 0/62] eta: 0:03:08 loss: 0.8341 (0.8341) time: 3.0475 data: 2.9572 max mem: 9390 +Eval (hcp-train-subset): [81] [61/62] eta: 0:00:00 loss: 0.8199 (0.8221) time: 0.1335 data: 0.1042 max mem: 9390 +Eval (hcp-train-subset): [81] Total time: 0:00:12 (0.1996 s / it) +Averaged stats (hcp-train-subset): loss: 0.8199 (0.8221) +Eval (hcp-val): [81] [ 0/62] eta: 0:02:45 loss: 0.8246 (0.8246) time: 2.6730 data: 2.6154 max mem: 9390 +Eval (hcp-val): [81] [61/62] eta: 0:00:00 loss: 0.8276 (0.8294) time: 0.1149 data: 0.0887 max mem: 9390 +Eval (hcp-val): [81] Total time: 0:00:12 (0.1959 s / it) +Averaged stats (hcp-val): loss: 0.8276 (0.8294) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +Train: [82] [ 0/6250] eta: 7:33:42 lr: 0.000011 grad: 0.0835 (0.0835) loss: 0.8324 (0.8324) time: 4.3556 data: 4.1609 max mem: 9390 +Train: [82] [ 100/6250] eta: 0:21:33 lr: 0.000011 grad: 0.1865 (0.1898) loss: 0.7972 (0.8136) time: 0.1686 data: 0.0755 max mem: 9390 +Train: [82] [ 200/6250] eta: 0:18:33 lr: 0.000011 grad: 0.1421 (0.1708) loss: 0.8106 (0.8112) time: 0.1414 data: 0.0456 max mem: 9390 +Train: [82] [ 300/6250] eta: 0:17:06 lr: 0.000011 grad: 0.1311 (0.1607) loss: 0.8183 (0.8112) time: 0.1557 data: 0.0663 max mem: 9390 +Train: [82] [ 400/6250] eta: 0:16:21 lr: 0.000011 grad: 0.1379 (0.1554) loss: 0.8063 (0.8112) time: 0.1490 data: 0.0681 max mem: 9390 +Train: [82] [ 500/6250] eta: 0:15:37 lr: 0.000011 grad: 0.1370 (0.1523) loss: 0.8111 (0.8108) time: 0.1533 data: 0.0572 max mem: 9390 +Train: [82] [ 600/6250] eta: 0:15:07 lr: 0.000011 grad: 0.1309 (0.1503) loss: 0.8070 (0.8102) time: 0.1578 data: 0.0627 max mem: 9390 +Train: [82] [ 700/6250] eta: 0:14:34 lr: 0.000011 grad: 0.1295 (0.1482) loss: 0.8124 (0.8100) time: 0.1186 data: 0.0287 max mem: 9390 +Train: [82] [ 800/6250] eta: 0:14:04 lr: 0.000011 grad: 0.1321 (0.1463) loss: 0.8116 (0.8102) time: 0.1408 data: 0.0487 max mem: 9390 +Train: [82] [ 900/6250] eta: 0:13:37 lr: 0.000011 grad: 0.1309 (0.1449) loss: 0.8064 (0.8102) time: 0.1360 data: 0.0485 max mem: 9390 +Train: [82] [1000/6250] eta: 0:13:09 lr: 0.000011 grad: 0.1388 (0.1441) loss: 0.7983 (0.8099) time: 0.1215 data: 0.0371 max mem: 9390 +Train: [82] [1100/6250] eta: 0:12:43 lr: 0.000011 grad: 0.1232 (0.1427) loss: 0.8096 (0.8098) time: 0.1298 data: 0.0451 max mem: 9390 +Train: [82] [1200/6250] eta: 0:12:16 lr: 0.000011 grad: 0.1326 (0.1421) loss: 0.8104 (0.8097) time: 0.1244 data: 0.0435 max mem: 9390 +Train: [82] [1300/6250] eta: 0:11:54 lr: 0.000011 grad: 0.1267 (0.1413) loss: 0.8048 (0.8099) time: 0.1491 data: 0.0716 max mem: 9390 +Train: [82] [1400/6250] eta: 0:11:30 lr: 0.000010 grad: 0.1277 (0.1406) loss: 0.8056 (0.8097) time: 0.1295 data: 0.0477 max mem: 9390 +Train: [82] [1500/6250] eta: 0:11:09 lr: 0.000010 grad: 0.1260 (0.1398) loss: 0.8109 (0.8098) time: 0.1228 data: 0.0395 max mem: 9390 +Train: [82] [1600/6250] eta: 0:10:51 lr: 0.000010 grad: 0.1248 (0.1391) loss: 0.8130 (0.8100) time: 0.1253 data: 0.0472 max mem: 9390 +Train: [82] [1700/6250] eta: 0:10:30 lr: 0.000010 grad: 0.1218 (0.1386) loss: 0.8041 (0.8101) time: 0.1076 data: 0.0279 max mem: 9390 +Train: [82] [1800/6250] eta: 0:10:13 lr: 0.000010 grad: 0.1254 (0.1381) loss: 0.8077 (0.8102) time: 0.1205 data: 0.0342 max mem: 9390 +Train: [82] [1900/6250] eta: 0:10:01 lr: 0.000010 grad: 0.1337 (0.1379) loss: 0.8074 (0.8103) time: 0.1547 data: 0.0742 max mem: 9390 +Train: [82] [2000/6250] eta: 0:10:15 lr: 0.000010 grad: 0.1233 (0.1378) loss: 0.8108 (0.8102) time: 0.1880 data: 0.1005 max mem: 9390 +Train: [82] [2100/6250] eta: 0:10:10 lr: 0.000010 grad: 0.1257 (0.1376) loss: 0.8115 (0.8102) time: 0.2228 data: 0.0990 max mem: 9390 +Train: [82] [2200/6250] eta: 0:10:11 lr: 0.000010 grad: 0.1275 (0.1376) loss: 0.8121 (0.8102) time: 0.2989 data: 0.1925 max mem: 9390 +Train: [82] [2300/6250] eta: 0:10:12 lr: 0.000010 grad: 0.1277 (0.1376) loss: 0.8049 (0.8102) time: 0.2420 data: 0.1584 max mem: 9390 +Train: [82] [2400/6250] eta: 0:10:30 lr: 0.000010 grad: 0.1389 (0.1374) loss: 0.8098 (0.8101) time: 0.6002 data: 0.5029 max mem: 9390 +Train: [82] [2500/6250] eta: 0:10:34 lr: 0.000010 grad: 0.1218 (0.1371) loss: 0.8072 (0.8102) time: 0.4524 data: 0.3772 max mem: 9390 +Train: [82] [2600/6250] eta: 0:10:56 lr: 0.000010 grad: 0.1266 (0.1369) loss: 0.8059 (0.8100) time: 0.3032 data: 0.1438 max mem: 9390 +Train: [82] [2700/6250] eta: 0:10:40 lr: 0.000010 grad: 0.1248 (0.1367) loss: 0.8079 (0.8100) time: 0.1876 data: 0.0992 max mem: 9390 +Train: [82] [2800/6250] eta: 0:10:22 lr: 0.000010 grad: 0.1334 (0.1366) loss: 0.8087 (0.8099) time: 0.1040 data: 0.0002 max mem: 9390 +Train: [82] [2900/6250] eta: 0:10:01 lr: 0.000010 grad: 0.1238 (0.1364) loss: 0.8072 (0.8099) time: 0.1480 data: 0.0505 max mem: 9390 +Train: [82] [3000/6250] eta: 0:09:44 lr: 0.000010 grad: 0.1292 (0.1362) loss: 0.8078 (0.8099) time: 0.1245 data: 0.0399 max mem: 9390 +Train: [82] [3100/6250] eta: 0:09:28 lr: 0.000010 grad: 0.1296 (0.1360) loss: 0.8122 (0.8100) time: 0.3335 data: 0.2291 max mem: 9390 +Train: [82] [3200/6250] eta: 0:09:06 lr: 0.000010 grad: 0.1256 (0.1358) loss: 0.8159 (0.8102) time: 0.1580 data: 0.0692 max mem: 9390 +Train: [82] [3300/6250] eta: 0:08:50 lr: 0.000010 grad: 0.1336 (0.1357) loss: 0.8088 (0.8102) time: 0.1700 data: 0.0748 max mem: 9390 +Train: [82] [3400/6250] eta: 0:08:31 lr: 0.000010 grad: 0.1335 (0.1356) loss: 0.8104 (0.8102) time: 0.1479 data: 0.0498 max mem: 9390 +Train: [82] [3500/6250] eta: 0:08:11 lr: 0.000010 grad: 0.1326 (0.1356) loss: 0.8029 (0.8102) time: 0.1512 data: 0.0604 max mem: 9390 +Train: [82] [3600/6250] eta: 0:07:53 lr: 0.000010 grad: 0.1293 (0.1355) loss: 0.8121 (0.8102) time: 0.1898 data: 0.1033 max mem: 9390 +Train: [82] [3700/6250] eta: 0:07:37 lr: 0.000010 grad: 0.1404 (0.1354) loss: 0.8037 (0.8102) time: 0.3104 data: 0.2230 max mem: 9390 +Train: [82] [3800/6250] eta: 0:07:18 lr: 0.000010 grad: 0.1280 (0.1353) loss: 0.8139 (0.8103) time: 0.2131 data: 0.1261 max mem: 9390 +Train: [82] [3900/6250] eta: 0:07:02 lr: 0.000010 grad: 0.1340 (0.1352) loss: 0.8088 (0.8104) time: 0.1017 data: 0.0002 max mem: 9390 +Train: [82] [4000/6250] eta: 0:06:45 lr: 0.000010 grad: 0.1330 (0.1351) loss: 0.8104 (0.8104) time: 0.2394 data: 0.1579 max mem: 9390 +Train: [82] [4100/6250] eta: 0:06:27 lr: 0.000010 grad: 0.1270 (0.1350) loss: 0.8077 (0.8104) time: 0.3042 data: 0.2096 max mem: 9390 +Train: [82] [4200/6250] eta: 0:06:08 lr: 0.000010 grad: 0.1221 (0.1349) loss: 0.8147 (0.8104) time: 0.2261 data: 0.1336 max mem: 9390 +Train: [82] [4300/6250] eta: 0:05:52 lr: 0.000010 grad: 0.1230 (0.1348) loss: 0.8166 (0.8104) time: 0.0962 data: 0.0002 max mem: 9390 +Train: [82] [4400/6250] eta: 0:05:36 lr: 0.000010 grad: 0.1308 (0.1347) loss: 0.8122 (0.8104) time: 0.2162 data: 0.1237 max mem: 9390 +Train: [82] [4500/6250] eta: 0:05:18 lr: 0.000010 grad: 0.1304 (0.1347) loss: 0.8094 (0.8103) time: 0.2951 data: 0.2023 max mem: 9390 +Train: [82] [4600/6250] eta: 0:05:00 lr: 0.000010 grad: 0.1218 (0.1347) loss: 0.8055 (0.8103) time: 0.1575 data: 0.0720 max mem: 9390 +Train: [82] [4700/6250] eta: 0:04:41 lr: 0.000010 grad: 0.1247 (0.1347) loss: 0.8103 (0.8103) time: 0.1582 data: 0.0728 max mem: 9390 +Train: [82] [4800/6250] eta: 0:04:25 lr: 0.000010 grad: 0.1357 (0.1347) loss: 0.8101 (0.8104) time: 0.2859 data: 0.1974 max mem: 9390 +Train: [82] [4900/6250] eta: 0:04:06 lr: 0.000010 grad: 0.1301 (0.1346) loss: 0.8145 (0.8104) time: 0.2048 data: 0.1166 max mem: 9390 +Train: [82] [5000/6250] eta: 0:03:47 lr: 0.000010 grad: 0.1346 (0.1347) loss: 0.8113 (0.8104) time: 0.2145 data: 0.1108 max mem: 9390 +Train: [82] [5100/6250] eta: 0:03:31 lr: 0.000010 grad: 0.1310 (0.1347) loss: 0.8062 (0.8105) time: 0.1260 data: 0.0305 max mem: 9390 +Train: [82] [5200/6250] eta: 0:03:12 lr: 0.000010 grad: 0.1304 (0.1347) loss: 0.8113 (0.8105) time: 0.1535 data: 0.0652 max mem: 9390 +Train: [82] [5300/6250] eta: 0:02:56 lr: 0.000010 grad: 0.1299 (0.1347) loss: 0.8138 (0.8105) time: 0.4020 data: 0.3022 max mem: 9390 +Train: [82] [5400/6250] eta: 0:02:38 lr: 0.000010 grad: 0.1255 (0.1346) loss: 0.8130 (0.8106) time: 0.0870 data: 0.0002 max mem: 9390 +Train: [82] [5500/6250] eta: 0:02:19 lr: 0.000010 grad: 0.1277 (0.1347) loss: 0.8092 (0.8106) time: 0.2149 data: 0.1322 max mem: 9390 +Train: [82] [5600/6250] eta: 0:02:01 lr: 0.000010 grad: 0.1220 (0.1346) loss: 0.8127 (0.8107) time: 0.2073 data: 0.1305 max mem: 9390 +Train: [82] [5700/6250] eta: 0:01:42 lr: 0.000010 grad: 0.1253 (0.1346) loss: 0.8153 (0.8107) time: 0.2118 data: 0.1362 max mem: 9390 +Train: [82] [5800/6250] eta: 0:01:23 lr: 0.000010 grad: 0.1349 (0.1345) loss: 0.8081 (0.8108) time: 0.1642 data: 0.0802 max mem: 9390 +Train: [82] [5900/6250] eta: 0:01:05 lr: 0.000010 grad: 0.1292 (0.1344) loss: 0.8071 (0.8109) time: 0.1114 data: 0.0194 max mem: 9390 +Train: [82] [6000/6250] eta: 0:00:46 lr: 0.000010 grad: 0.1252 (0.1344) loss: 0.8176 (0.8109) time: 0.1535 data: 0.0732 max mem: 9390 +Train: [82] [6100/6250] eta: 0:00:27 lr: 0.000010 grad: 0.1288 (0.1343) loss: 0.8093 (0.8109) time: 0.1709 data: 0.0863 max mem: 9390 +Train: [82] [6200/6250] eta: 0:00:09 lr: 0.000010 grad: 0.1268 (0.1343) loss: 0.8116 (0.8109) time: 0.2093 data: 0.1339 max mem: 9390 +Train: [82] [6249/6250] eta: 0:00:00 lr: 0.000010 grad: 0.1319 (0.1343) loss: 0.8065 (0.8109) time: 0.1854 data: 0.1021 max mem: 9390 +Train: [82] Total time: 0:19:26 (0.1867 s / it) +Averaged stats: lr: 0.000010 grad: 0.1319 (0.1343) loss: 0.8065 (0.8109) +Eval (hcp-train-subset): [82] [ 0/62] eta: 0:05:12 loss: 0.8309 (0.8309) time: 5.0449 data: 5.0155 max mem: 9390 +Eval (hcp-train-subset): [82] [61/62] eta: 0:00:00 loss: 0.8204 (0.8225) time: 0.1399 data: 0.1123 max mem: 9390 +Eval (hcp-train-subset): [82] Total time: 0:00:15 (0.2507 s / it) +Averaged stats (hcp-train-subset): loss: 0.8204 (0.8225) +Eval (hcp-val): [82] [ 0/62] eta: 0:04:01 loss: 0.8274 (0.8274) time: 3.9002 data: 3.8425 max mem: 9390 +Eval (hcp-val): [82] [61/62] eta: 0:00:00 loss: 0.8287 (0.8299) time: 0.1417 data: 0.1163 max mem: 9390 +Eval (hcp-val): [82] Total time: 0:00:15 (0.2504 s / it) +Averaged stats (hcp-val): loss: 0.8287 (0.8299) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +Train: [83] [ 0/6250] eta: 11:29:24 lr: 0.000010 grad: 0.1692 (0.1692) loss: 0.8670 (0.8670) time: 6.6182 data: 6.4695 max mem: 9390 +Train: [83] [ 100/6250] eta: 0:25:12 lr: 0.000010 grad: 0.1273 (0.1369) loss: 0.8220 (0.8252) time: 0.1925 data: 0.0962 max mem: 9390 +Train: [83] [ 200/6250] eta: 0:22:04 lr: 0.000010 grad: 0.1427 (0.1420) loss: 0.8111 (0.8186) time: 0.1678 data: 0.0740 max mem: 9390 +Train: [83] [ 300/6250] eta: 0:20:32 lr: 0.000010 grad: 0.1340 (0.1428) loss: 0.7979 (0.8156) time: 0.1597 data: 0.0672 max mem: 9390 +Train: [83] [ 400/6250] eta: 0:19:04 lr: 0.000010 grad: 0.1321 (0.1423) loss: 0.8082 (0.8138) time: 0.1641 data: 0.0736 max mem: 9390 +Train: [83] [ 500/6250] eta: 0:18:34 lr: 0.000010 grad: 0.1295 (0.1418) loss: 0.8031 (0.8122) time: 0.1839 data: 0.0956 max mem: 9390 +Train: [83] [ 600/6250] eta: 0:18:06 lr: 0.000010 grad: 0.1301 (0.1406) loss: 0.8163 (0.8115) time: 0.1797 data: 0.0939 max mem: 9390 +Train: [83] [ 700/6250] eta: 0:18:26 lr: 0.000009 grad: 0.1293 (0.1393) loss: 0.8188 (0.8114) time: 0.3380 data: 0.2110 max mem: 9390 +Train: [83] [ 800/6250] eta: 0:18:55 lr: 0.000009 grad: 0.1225 (0.1377) loss: 0.8149 (0.8119) time: 0.3427 data: 0.2482 max mem: 9390 +Train: [83] [ 900/6250] eta: 0:19:16 lr: 0.000009 grad: 0.1241 (0.1368) loss: 0.8141 (0.8122) time: 0.1275 data: 0.0046 max mem: 9390 +Train: [83] [1000/6250] eta: 0:18:56 lr: 0.000009 grad: 0.1192 (0.1361) loss: 0.8191 (0.8126) time: 0.0985 data: 0.0002 max mem: 9390 +Train: [83] [1100/6250] eta: 0:18:19 lr: 0.000009 grad: 0.1225 (0.1355) loss: 0.8135 (0.8126) time: 0.1527 data: 0.0005 max mem: 9390 +Train: [83] [1200/6250] eta: 0:18:08 lr: 0.000009 grad: 0.1283 (0.1355) loss: 0.8089 (0.8126) time: 0.1618 data: 0.0429 max mem: 9390 +Train: [83] [1300/6250] eta: 0:18:12 lr: 0.000009 grad: 0.1349 (0.1353) loss: 0.8074 (0.8125) time: 0.0988 data: 0.0002 max mem: 9390 +Train: [83] [1400/6250] eta: 0:17:34 lr: 0.000009 grad: 0.1319 (0.1351) loss: 0.8113 (0.8123) time: 0.1358 data: 0.0379 max mem: 9390 +Train: [83] [1500/6250] eta: 0:17:14 lr: 0.000009 grad: 0.1257 (0.1350) loss: 0.8099 (0.8124) time: 0.1065 data: 0.0003 max mem: 9390 +Train: [83] [1600/6250] eta: 0:16:54 lr: 0.000009 grad: 0.1268 (0.1349) loss: 0.8069 (0.8122) time: 0.1287 data: 0.0412 max mem: 9390 +Train: [83] [1700/6250] eta: 0:16:53 lr: 0.000009 grad: 0.1307 (0.1348) loss: 0.8062 (0.8120) time: 0.4735 data: 0.3779 max mem: 9390 +Train: [83] [1800/6250] eta: 0:16:45 lr: 0.000009 grad: 0.1316 (0.1346) loss: 0.8124 (0.8119) time: 0.1342 data: 0.0318 max mem: 9390 +Train: [83] [1900/6250] eta: 0:16:11 lr: 0.000009 grad: 0.1318 (0.1344) loss: 0.8091 (0.8118) time: 0.1663 data: 0.0746 max mem: 9390 +Train: [83] [2000/6250] eta: 0:16:01 lr: 0.000009 grad: 0.1308 (0.1342) loss: 0.8144 (0.8119) time: 0.2191 data: 0.1282 max mem: 9390 +Train: [83] [2100/6250] eta: 0:15:27 lr: 0.000009 grad: 0.1312 (0.1340) loss: 0.8093 (0.8119) time: 0.1836 data: 0.0950 max mem: 9390 +Train: [83] [2200/6250] eta: 0:15:05 lr: 0.000009 grad: 0.1271 (0.1338) loss: 0.8135 (0.8120) time: 0.1061 data: 0.0002 max mem: 9390 +Train: [83] [2300/6250] eta: 0:15:03 lr: 0.000009 grad: 0.1343 (0.1337) loss: 0.8147 (0.8119) time: 0.3300 data: 0.2420 max mem: 9390 +Train: [83] [2400/6250] eta: 0:14:50 lr: 0.000009 grad: 0.1344 (0.1338) loss: 0.8063 (0.8118) time: 0.4140 data: 0.3258 max mem: 9390 +Train: [83] [2500/6250] eta: 0:14:29 lr: 0.000009 grad: 0.1315 (0.1337) loss: 0.8060 (0.8117) time: 0.5225 data: 0.4276 max mem: 9390 +Train: [83] [2600/6250] eta: 0:13:57 lr: 0.000009 grad: 0.1362 (0.1337) loss: 0.8092 (0.8117) time: 0.1105 data: 0.0003 max mem: 9390 +Train: [83] [2700/6250] eta: 0:13:33 lr: 0.000009 grad: 0.1277 (0.1336) loss: 0.8116 (0.8116) time: 0.1427 data: 0.0474 max mem: 9390 +Train: [83] [2800/6250] eta: 0:13:13 lr: 0.000009 grad: 0.1270 (0.1334) loss: 0.8119 (0.8116) time: 0.1237 data: 0.0286 max mem: 9390 +Train: [83] [2900/6250] eta: 0:13:01 lr: 0.000009 grad: 0.1279 (0.1333) loss: 0.8156 (0.8117) time: 0.1538 data: 0.0658 max mem: 9390 +Train: [83] [3000/6250] eta: 0:12:34 lr: 0.000009 grad: 0.1268 (0.1332) loss: 0.8192 (0.8118) time: 0.2625 data: 0.1676 max mem: 9390 +Train: [83] [3100/6250] eta: 0:12:08 lr: 0.000009 grad: 0.1247 (0.1331) loss: 0.8149 (0.8119) time: 0.1020 data: 0.0002 max mem: 9390 +Train: [83] [3200/6250] eta: 0:11:39 lr: 0.000009 grad: 0.1267 (0.1330) loss: 0.8138 (0.8120) time: 0.1949 data: 0.0973 max mem: 9390 +Train: [83] [3300/6250] eta: 0:11:18 lr: 0.000009 grad: 0.1220 (0.1329) loss: 0.8167 (0.8121) time: 0.2652 data: 0.1715 max mem: 9390 +Train: [83] [3400/6250] eta: 0:10:51 lr: 0.000009 grad: 0.1260 (0.1329) loss: 0.8204 (0.8122) time: 0.1821 data: 0.0871 max mem: 9390 +Train: [83] [3500/6250] eta: 0:10:29 lr: 0.000009 grad: 0.1295 (0.1328) loss: 0.8174 (0.8122) time: 0.0969 data: 0.0002 max mem: 9390 +Train: [83] [3600/6250] eta: 0:10:04 lr: 0.000009 grad: 0.1260 (0.1328) loss: 0.8153 (0.8122) time: 0.1216 data: 0.0356 max mem: 9390 +Train: [83] [3700/6250] eta: 0:09:38 lr: 0.000009 grad: 0.1317 (0.1328) loss: 0.8144 (0.8123) time: 0.1139 data: 0.0239 max mem: 9390 +Train: [83] [3800/6250] eta: 0:09:18 lr: 0.000009 grad: 0.1331 (0.1328) loss: 0.8124 (0.8123) time: 0.6818 data: 0.5556 max mem: 9390 +Train: [83] [3900/6250] eta: 0:08:55 lr: 0.000009 grad: 0.1234 (0.1327) loss: 0.8198 (0.8124) time: 0.1274 data: 0.0319 max mem: 9390 +Train: [83] [4000/6250] eta: 0:08:32 lr: 0.000009 grad: 0.1249 (0.1327) loss: 0.8162 (0.8125) time: 0.1282 data: 0.0475 max mem: 9390 +Train: [83] [4100/6250] eta: 0:08:09 lr: 0.000009 grad: 0.1235 (0.1326) loss: 0.8159 (0.8126) time: 0.0999 data: 0.0002 max mem: 9390 +Train: [83] [4200/6250] eta: 0:07:46 lr: 0.000009 grad: 0.1244 (0.1326) loss: 0.8131 (0.8126) time: 0.5289 data: 0.4368 max mem: 9390 +Train: [83] [4300/6250] eta: 0:07:21 lr: 0.000009 grad: 0.1259 (0.1326) loss: 0.8184 (0.8127) time: 0.3161 data: 0.2263 max mem: 9390 +Train: [83] [4400/6250] eta: 0:06:57 lr: 0.000009 grad: 0.1333 (0.1326) loss: 0.8171 (0.8128) time: 0.2706 data: 0.1854 max mem: 9390 +Train: [83] [4500/6250] eta: 0:06:37 lr: 0.000009 grad: 0.1347 (0.1325) loss: 0.8158 (0.8129) time: 0.6052 data: 0.5092 max mem: 9390 +Train: [83] [4600/6250] eta: 0:06:17 lr: 0.000009 grad: 0.1267 (0.1326) loss: 0.8152 (0.8129) time: 0.5963 data: 0.4911 max mem: 9390 +Train: [83] [4700/6250] eta: 0:05:51 lr: 0.000009 grad: 0.1276 (0.1327) loss: 0.8152 (0.8129) time: 0.1573 data: 0.0780 max mem: 9390 +Train: [83] [4800/6250] eta: 0:05:27 lr: 0.000009 grad: 0.1340 (0.1327) loss: 0.8033 (0.8128) time: 0.1679 data: 0.0709 max mem: 9390 +Train: [83] [4900/6250] eta: 0:05:06 lr: 0.000009 grad: 0.1248 (0.1327) loss: 0.8129 (0.8128) time: 0.2035 data: 0.1162 max mem: 9390 +Train: [83] [5000/6250] eta: 0:04:41 lr: 0.000009 grad: 0.1336 (0.1328) loss: 0.8111 (0.8128) time: 0.2056 data: 0.1184 max mem: 9390 +Train: [83] [5100/6250] eta: 0:04:21 lr: 0.000009 grad: 0.1273 (0.1329) loss: 0.8101 (0.8127) time: 0.0917 data: 0.0002 max mem: 9390 +Train: [83] [5200/6250] eta: 0:03:57 lr: 0.000009 grad: 0.1308 (0.1329) loss: 0.8086 (0.8127) time: 0.1477 data: 0.0583 max mem: 9390 +Train: [83] [5300/6250] eta: 0:03:33 lr: 0.000009 grad: 0.1354 (0.1329) loss: 0.8051 (0.8127) time: 0.2147 data: 0.1336 max mem: 9390 +Train: [83] [5400/6250] eta: 0:03:10 lr: 0.000009 grad: 0.1281 (0.1329) loss: 0.8095 (0.8127) time: 0.2259 data: 0.1428 max mem: 9390 +Train: [83] [5500/6250] eta: 0:02:47 lr: 0.000009 grad: 0.1300 (0.1329) loss: 0.8192 (0.8127) time: 0.1821 data: 0.0962 max mem: 9390 +Train: [83] [5600/6250] eta: 0:02:24 lr: 0.000009 grad: 0.1245 (0.1329) loss: 0.8158 (0.8127) time: 0.1669 data: 0.0837 max mem: 9390 +Train: [83] [5700/6250] eta: 0:02:03 lr: 0.000009 grad: 0.1258 (0.1329) loss: 0.8096 (0.8128) time: 1.0868 data: 0.9725 max mem: 9390 +Train: [83] [5800/6250] eta: 0:01:40 lr: 0.000009 grad: 0.1194 (0.1329) loss: 0.8196 (0.8128) time: 0.2010 data: 0.1186 max mem: 9390 +Train: [83] [5900/6250] eta: 0:01:19 lr: 0.000009 grad: 0.1318 (0.1329) loss: 0.8141 (0.8128) time: 0.2446 data: 0.1481 max mem: 9390 +Train: [83] [6000/6250] eta: 0:00:56 lr: 0.000009 grad: 0.1207 (0.1329) loss: 0.8138 (0.8128) time: 0.1090 data: 0.0002 max mem: 9390 +Train: [83] [6100/6250] eta: 0:00:34 lr: 0.000009 grad: 0.1339 (0.1329) loss: 0.8125 (0.8128) time: 0.1260 data: 0.0003 max mem: 9390 +Train: [83] [6200/6250] eta: 0:00:11 lr: 0.000009 grad: 0.1350 (0.1330) loss: 0.8075 (0.8128) time: 0.1437 data: 0.0508 max mem: 9390 +Train: [83] [6249/6250] eta: 0:00:00 lr: 0.000009 grad: 0.1288 (0.1330) loss: 0.8130 (0.8128) time: 0.1369 data: 0.0499 max mem: 9390 +Train: [83] Total time: 0:23:56 (0.2299 s / it) +Averaged stats: lr: 0.000009 grad: 0.1288 (0.1330) loss: 0.8130 (0.8128) +Eval (hcp-train-subset): [83] [ 0/62] eta: 0:03:09 loss: 0.8298 (0.8298) time: 3.0564 data: 2.9915 max mem: 9390 +Eval (hcp-train-subset): [83] [61/62] eta: 0:00:00 loss: 0.8220 (0.8216) time: 0.1337 data: 0.1086 max mem: 9390 +Eval (hcp-train-subset): [83] Total time: 0:00:13 (0.2180 s / it) +Averaged stats (hcp-train-subset): loss: 0.8220 (0.8216) +Eval (hcp-val): [83] [ 0/62] eta: 0:03:20 loss: 0.8244 (0.8244) time: 3.2267 data: 3.1461 max mem: 9390 +Eval (hcp-val): [83] [61/62] eta: 0:00:00 loss: 0.8290 (0.8296) time: 0.1148 data: 0.0883 max mem: 9390 +Eval (hcp-val): [83] Total time: 0:00:13 (0.2236 s / it) +Averaged stats (hcp-val): loss: 0.8290 (0.8296) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +Train: [84] [ 0/6250] eta: 12:02:41 lr: 0.000009 grad: 0.3106 (0.3106) loss: 0.7737 (0.7737) time: 6.9379 data: 6.8300 max mem: 9390 +Train: [84] [ 100/6250] eta: 0:23:34 lr: 0.000009 grad: 0.1241 (0.1778) loss: 0.8286 (0.8169) time: 0.1617 data: 0.0748 max mem: 9390 +Train: [84] [ 200/6250] eta: 0:20:55 lr: 0.000009 grad: 0.1446 (0.1694) loss: 0.8085 (0.8146) time: 0.2037 data: 0.1108 max mem: 9390 +Train: [84] [ 300/6250] eta: 0:19:36 lr: 0.000008 grad: 0.1580 (0.1626) loss: 0.8136 (0.8128) time: 0.1522 data: 0.0476 max mem: 9390 +Train: [84] [ 400/6250] eta: 0:18:23 lr: 0.000008 grad: 0.1463 (0.1603) loss: 0.8031 (0.8118) time: 0.1588 data: 0.0728 max mem: 9390 +Train: [84] [ 500/6250] eta: 0:17:28 lr: 0.000008 grad: 0.1431 (0.1578) loss: 0.8110 (0.8109) time: 0.1475 data: 0.0607 max mem: 9390 +Train: [84] [ 600/6250] eta: 0:17:08 lr: 0.000008 grad: 0.1413 (0.1549) loss: 0.8055 (0.8107) time: 0.1808 data: 0.0984 max mem: 9390 +Train: [84] [ 700/6250] eta: 0:17:08 lr: 0.000008 grad: 0.1306 (0.1524) loss: 0.8166 (0.8108) time: 0.1402 data: 0.0258 max mem: 9390 +Train: [84] [ 800/6250] eta: 0:18:19 lr: 0.000008 grad: 0.1338 (0.1505) loss: 0.8110 (0.8110) time: 0.1795 data: 0.0905 max mem: 9390 +Train: [84] [ 900/6250] eta: 0:17:57 lr: 0.000008 grad: 0.1257 (0.1488) loss: 0.8182 (0.8111) time: 0.1718 data: 0.0812 max mem: 9390 +Train: [84] [1000/6250] eta: 0:17:27 lr: 0.000008 grad: 0.1302 (0.1472) loss: 0.8153 (0.8114) time: 0.2050 data: 0.1247 max mem: 9390 +Train: [84] [1100/6250] eta: 0:17:00 lr: 0.000008 grad: 0.1235 (0.1458) loss: 0.8170 (0.8117) time: 0.1679 data: 0.0809 max mem: 9390 +Train: [84] [1200/6250] eta: 0:16:28 lr: 0.000008 grad: 0.1192 (0.1444) loss: 0.8180 (0.8121) time: 0.1481 data: 0.0633 max mem: 9390 +Train: [84] [1300/6250] eta: 0:16:02 lr: 0.000008 grad: 0.1292 (0.1433) loss: 0.8163 (0.8123) time: 0.1275 data: 0.0408 max mem: 9390 +Train: [84] [1400/6250] eta: 0:15:31 lr: 0.000008 grad: 0.1268 (0.1424) loss: 0.8082 (0.8125) time: 0.1616 data: 0.0718 max mem: 9390 +Train: [84] [1500/6250] eta: 0:15:46 lr: 0.000008 grad: 0.1292 (0.1416) loss: 0.8156 (0.8126) time: 0.5312 data: 0.4140 max mem: 9390 +Train: [84] [1600/6250] eta: 0:16:06 lr: 0.000008 grad: 0.1217 (0.1410) loss: 0.8180 (0.8127) time: 0.1142 data: 0.0003 max mem: 9390 +Train: [84] [1700/6250] eta: 0:16:02 lr: 0.000008 grad: 0.1397 (0.1407) loss: 0.8104 (0.8127) time: 0.4980 data: 0.3737 max mem: 9390 +Train: [84] [1800/6250] eta: 0:15:31 lr: 0.000008 grad: 0.1246 (0.1402) loss: 0.8117 (0.8129) time: 0.1618 data: 0.0726 max mem: 9390 +Train: [84] [1900/6250] eta: 0:15:14 lr: 0.000008 grad: 0.1281 (0.1397) loss: 0.8193 (0.8129) time: 0.1236 data: 0.0191 max mem: 9390 +Train: [84] [2000/6250] eta: 0:14:52 lr: 0.000008 grad: 0.1314 (0.1395) loss: 0.8111 (0.8129) time: 0.1964 data: 0.0967 max mem: 9390 +Train: [84] [2100/6250] eta: 0:14:29 lr: 0.000008 grad: 0.1387 (0.1395) loss: 0.8132 (0.8129) time: 0.1116 data: 0.0172 max mem: 9390 +Train: [84] [2200/6250] eta: 0:14:09 lr: 0.000008 grad: 0.1275 (0.1393) loss: 0.8149 (0.8129) time: 0.1918 data: 0.1100 max mem: 9390 +Train: [84] [2300/6250] eta: 0:13:47 lr: 0.000008 grad: 0.1322 (0.1392) loss: 0.8171 (0.8129) time: 0.1175 data: 0.0003 max mem: 9390 +Train: [84] [2400/6250] eta: 0:13:28 lr: 0.000008 grad: 0.1403 (0.1392) loss: 0.8111 (0.8129) time: 0.0972 data: 0.0003 max mem: 9390 +Train: [84] [2500/6250] eta: 0:13:15 lr: 0.000008 grad: 0.1312 (0.1391) loss: 0.8128 (0.8127) time: 0.5402 data: 0.4312 max mem: 9390 +Train: [84] [2600/6250] eta: 0:13:01 lr: 0.000008 grad: 0.1348 (0.1390) loss: 0.8129 (0.8127) time: 0.1230 data: 0.0139 max mem: 9390 +Train: [84] [2700/6250] eta: 0:12:41 lr: 0.000008 grad: 0.1364 (0.1389) loss: 0.8069 (0.8125) time: 0.1237 data: 0.0002 max mem: 9390 +Train: [84] [2800/6250] eta: 0:12:15 lr: 0.000008 grad: 0.1386 (0.1389) loss: 0.8081 (0.8124) time: 0.1366 data: 0.0448 max mem: 9390 +Train: [84] [2900/6250] eta: 0:12:11 lr: 0.000008 grad: 0.1358 (0.1389) loss: 0.8046 (0.8123) time: 0.1609 data: 0.0671 max mem: 9390 +Train: [84] [3000/6250] eta: 0:11:49 lr: 0.000008 grad: 0.1309 (0.1388) loss: 0.8149 (0.8123) time: 0.1092 data: 0.0002 max mem: 9390 +Train: [84] [3100/6250] eta: 0:11:27 lr: 0.000008 grad: 0.1327 (0.1387) loss: 0.8079 (0.8123) time: 0.2107 data: 0.1280 max mem: 9390 +Train: [84] [3200/6250] eta: 0:11:01 lr: 0.000008 grad: 0.1404 (0.1386) loss: 0.8088 (0.8122) time: 0.1437 data: 0.0316 max mem: 9390 +Train: [84] [3300/6250] eta: 0:10:49 lr: 0.000008 grad: 0.1291 (0.1385) loss: 0.8137 (0.8122) time: 0.6939 data: 0.5914 max mem: 9390 +Train: [84] [3400/6250] eta: 0:10:24 lr: 0.000008 grad: 0.1173 (0.1383) loss: 0.8169 (0.8123) time: 0.1441 data: 0.0485 max mem: 9390 +Train: [84] [3500/6250] eta: 0:10:10 lr: 0.000008 grad: 0.1313 (0.1381) loss: 0.8124 (0.8124) time: 0.2758 data: 0.1896 max mem: 9390 +Train: [84] [3600/6250] eta: 0:09:46 lr: 0.000008 grad: 0.1221 (0.1379) loss: 0.8188 (0.8125) time: 0.1312 data: 0.0168 max mem: 9390 +Train: [84] [3700/6250] eta: 0:09:29 lr: 0.000008 grad: 0.1332 (0.1379) loss: 0.8164 (0.8124) time: 0.5326 data: 0.4421 max mem: 9390 +Train: [84] [3800/6250] eta: 0:09:04 lr: 0.000008 grad: 0.1269 (0.1379) loss: 0.8155 (0.8125) time: 0.1712 data: 0.0516 max mem: 9390 +Train: [84] [3900/6250] eta: 0:09:00 lr: 0.000008 grad: 0.1264 (0.1378) loss: 0.8141 (0.8125) time: 0.1220 data: 0.0206 max mem: 9390 +Train: [84] [4000/6250] eta: 0:08:41 lr: 0.000008 grad: 0.1347 (0.1378) loss: 0.8080 (0.8124) time: 0.1111 data: 0.0002 max mem: 9390 +Train: [84] [4100/6250] eta: 0:08:27 lr: 0.000008 grad: 0.1252 (0.1377) loss: 0.8135 (0.8125) time: 0.2106 data: 0.1181 max mem: 9390 +Train: [84] [4200/6250] eta: 0:08:00 lr: 0.000008 grad: 0.1271 (0.1376) loss: 0.8214 (0.8126) time: 0.1160 data: 0.0003 max mem: 9390 +Train: [84] [4300/6250] eta: 0:07:36 lr: 0.000008 grad: 0.1307 (0.1376) loss: 0.8170 (0.8126) time: 0.1010 data: 0.0002 max mem: 9390 +Train: [84] [4400/6250] eta: 0:07:18 lr: 0.000008 grad: 0.1301 (0.1376) loss: 0.8177 (0.8127) time: 0.5474 data: 0.4374 max mem: 9390 +Train: [84] [4500/6250] eta: 0:06:52 lr: 0.000008 grad: 0.1365 (0.1374) loss: 0.8169 (0.8127) time: 0.2145 data: 0.1278 max mem: 9390 +Train: [84] [4600/6250] eta: 0:06:25 lr: 0.000008 grad: 0.1286 (0.1373) loss: 0.8136 (0.8128) time: 0.1277 data: 0.0384 max mem: 9390 +Train: [84] [4700/6250] eta: 0:05:59 lr: 0.000008 grad: 0.1328 (0.1372) loss: 0.8112 (0.8128) time: 0.1311 data: 0.0503 max mem: 9390 +Train: [84] [4800/6250] eta: 0:05:34 lr: 0.000008 grad: 0.1357 (0.1371) loss: 0.8125 (0.8129) time: 0.1668 data: 0.0869 max mem: 9390 +Train: [84] [4900/6250] eta: 0:05:10 lr: 0.000008 grad: 0.1301 (0.1371) loss: 0.8165 (0.8129) time: 0.1784 data: 0.0997 max mem: 9390 +Train: [84] [5000/6250] eta: 0:04:45 lr: 0.000008 grad: 0.1318 (0.1370) loss: 0.8155 (0.8129) time: 0.1749 data: 0.0923 max mem: 9390 +Train: [84] [5100/6250] eta: 0:04:21 lr: 0.000008 grad: 0.1349 (0.1369) loss: 0.8123 (0.8129) time: 0.1359 data: 0.0436 max mem: 9390 +Train: [84] [5200/6250] eta: 0:03:57 lr: 0.000008 grad: 0.1343 (0.1368) loss: 0.8130 (0.8129) time: 0.1437 data: 0.0541 max mem: 9390 +Train: [84] [5300/6250] eta: 0:03:33 lr: 0.000008 grad: 0.1297 (0.1368) loss: 0.8159 (0.8129) time: 0.1757 data: 0.0905 max mem: 9390 +Train: [84] [5400/6250] eta: 0:03:10 lr: 0.000008 grad: 0.1244 (0.1367) loss: 0.8167 (0.8129) time: 0.1846 data: 0.1047 max mem: 9390 +Train: [84] [5500/6250] eta: 0:02:46 lr: 0.000008 grad: 0.1337 (0.1366) loss: 0.8080 (0.8129) time: 0.1459 data: 0.0591 max mem: 9390 +Train: [84] [5600/6250] eta: 0:02:23 lr: 0.000008 grad: 0.1350 (0.1366) loss: 0.8099 (0.8129) time: 0.1386 data: 0.0570 max mem: 9390 +Train: [84] [5700/6250] eta: 0:02:01 lr: 0.000008 grad: 0.1367 (0.1366) loss: 0.8115 (0.8129) time: 0.1395 data: 0.0638 max mem: 9390 +Train: [84] [5800/6250] eta: 0:01:38 lr: 0.000008 grad: 0.1360 (0.1365) loss: 0.8080 (0.8128) time: 0.1845 data: 0.1010 max mem: 9390 +Train: [84] [5900/6250] eta: 0:01:16 lr: 0.000008 grad: 0.1379 (0.1366) loss: 0.8074 (0.8128) time: 0.1345 data: 0.0530 max mem: 9390 +Train: [84] [6000/6250] eta: 0:00:54 lr: 0.000008 grad: 0.1333 (0.1366) loss: 0.8045 (0.8127) time: 0.1375 data: 0.0498 max mem: 9390 +Train: [84] [6100/6250] eta: 0:00:32 lr: 0.000008 grad: 0.1351 (0.1367) loss: 0.8085 (0.8126) time: 0.1647 data: 0.0724 max mem: 9390 +Train: [84] [6200/6250] eta: 0:00:10 lr: 0.000008 grad: 0.1348 (0.1367) loss: 0.8136 (0.8125) time: 0.2029 data: 0.1269 max mem: 9390 +Train: [84] [6249/6250] eta: 0:00:00 lr: 0.000008 grad: 0.1398 (0.1368) loss: 0.8036 (0.8125) time: 0.1498 data: 0.0608 max mem: 9390 +Train: [84] Total time: 0:22:29 (0.2159 s / it) +Averaged stats: lr: 0.000008 grad: 0.1398 (0.1368) loss: 0.8036 (0.8125) +Eval (hcp-train-subset): [84] [ 0/62] eta: 0:05:05 loss: 0.8267 (0.8267) time: 4.9261 data: 4.8983 max mem: 9390 +Eval (hcp-train-subset): [84] [61/62] eta: 0:00:00 loss: 0.8191 (0.8209) time: 0.1430 data: 0.1177 max mem: 9390 +Eval (hcp-train-subset): [84] Total time: 0:00:12 (0.2095 s / it) +Averaged stats (hcp-train-subset): loss: 0.8191 (0.8209) +Making plots (hcp-train-subset): example=11 +Eval (hcp-val): [84] [ 0/62] eta: 0:03:15 loss: 0.8253 (0.8253) time: 3.1600 data: 3.0869 max mem: 9390 +Eval (hcp-val): [84] [61/62] eta: 0:00:00 loss: 0.8283 (0.8289) time: 0.1192 data: 0.0942 max mem: 9390 +Eval (hcp-val): [84] Total time: 0:00:13 (0.2155 s / it) +Averaged stats (hcp-val): loss: 0.8283 (0.8289) +Making plots (hcp-val): example=20 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +Train: [85] [ 0/6250] eta: 9:29:31 lr: 0.000008 grad: 0.1208 (0.1208) loss: 0.8516 (0.8516) time: 5.4675 data: 5.3540 max mem: 9390 +Train: [85] [ 100/6250] eta: 0:21:19 lr: 0.000008 grad: 0.1280 (0.1528) loss: 0.8111 (0.8169) time: 0.1443 data: 0.0530 max mem: 9390 +Train: [85] [ 200/6250] eta: 0:18:56 lr: 0.000008 grad: 0.1279 (0.1465) loss: 0.8149 (0.8147) time: 0.1720 data: 0.0757 max mem: 9390 +Train: [85] [ 300/6250] eta: 0:17:40 lr: 0.000007 grad: 0.1360 (0.1469) loss: 0.8143 (0.8141) time: 0.1645 data: 0.0800 max mem: 9390 +Train: [85] [ 400/6250] eta: 0:16:56 lr: 0.000007 grad: 0.1473 (0.1470) loss: 0.7995 (0.8123) time: 0.1863 data: 0.1008 max mem: 9390 +Train: [85] [ 500/6250] eta: 0:16:16 lr: 0.000007 grad: 0.1384 (0.1455) loss: 0.8124 (0.8122) time: 0.1589 data: 0.0612 max mem: 9390 +Train: [85] [ 600/6250] eta: 0:15:42 lr: 0.000007 grad: 0.1289 (0.1442) loss: 0.8152 (0.8130) time: 0.1499 data: 0.0567 max mem: 9390 +Train: [85] [ 700/6250] eta: 0:16:12 lr: 0.000007 grad: 0.1365 (0.1430) loss: 0.8187 (0.8131) time: 0.3188 data: 0.2347 max mem: 9390 +Train: [85] [ 800/6250] eta: 0:16:03 lr: 0.000007 grad: 0.1281 (0.1424) loss: 0.8129 (0.8131) time: 0.1142 data: 0.0002 max mem: 9390 +Train: [85] [ 900/6250] eta: 0:16:46 lr: 0.000007 grad: 0.1344 (0.1417) loss: 0.8158 (0.8134) time: 0.1069 data: 0.0173 max mem: 9390 +Train: [85] [1000/6250] eta: 0:16:52 lr: 0.000007 grad: 0.1288 (0.1409) loss: 0.8186 (0.8137) time: 0.0927 data: 0.0002 max mem: 9390 +Train: [85] [1100/6250] eta: 0:16:21 lr: 0.000007 grad: 0.1318 (0.1402) loss: 0.8180 (0.8140) time: 0.1641 data: 0.0722 max mem: 9390 +Train: [85] [1200/6250] eta: 0:15:53 lr: 0.000007 grad: 0.1281 (0.1395) loss: 0.8181 (0.8142) time: 0.1390 data: 0.0228 max mem: 9390 +Train: [85] [1300/6250] eta: 0:15:43 lr: 0.000007 grad: 0.1222 (0.1389) loss: 0.8174 (0.8144) time: 0.2230 data: 0.1318 max mem: 9390 +Train: [85] [1400/6250] eta: 0:15:35 lr: 0.000007 grad: 0.1305 (0.1383) loss: 0.8158 (0.8147) time: 0.1560 data: 0.0655 max mem: 9390 +Train: [85] [1500/6250] eta: 0:15:21 lr: 0.000007 grad: 0.1340 (0.1380) loss: 0.8123 (0.8147) time: 0.1024 data: 0.0002 max mem: 9390 +Train: [85] [1600/6250] eta: 0:14:55 lr: 0.000007 grad: 0.1269 (0.1378) loss: 0.8168 (0.8147) time: 0.1909 data: 0.0982 max mem: 9390 +Train: [85] [1700/6250] eta: 0:14:36 lr: 0.000007 grad: 0.1240 (0.1372) loss: 0.8120 (0.8148) time: 0.2373 data: 0.1444 max mem: 9390 +Train: [85] [1800/6250] eta: 0:14:08 lr: 0.000007 grad: 0.1275 (0.1370) loss: 0.8230 (0.8148) time: 0.1032 data: 0.0006 max mem: 9390 +Train: [85] [1900/6250] eta: 0:14:01 lr: 0.000007 grad: 0.1209 (0.1365) loss: 0.8186 (0.8149) time: 0.1045 data: 0.0003 max mem: 9390 +Train: [85] [2000/6250] eta: 0:13:39 lr: 0.000007 grad: 0.1274 (0.1362) loss: 0.8184 (0.8150) time: 0.2673 data: 0.1778 max mem: 9390 +Train: [85] [2100/6250] eta: 0:13:17 lr: 0.000007 grad: 0.1282 (0.1359) loss: 0.8180 (0.8150) time: 0.2367 data: 0.1393 max mem: 9390 +Train: [85] [2200/6250] eta: 0:12:54 lr: 0.000007 grad: 0.1291 (0.1356) loss: 0.8162 (0.8152) time: 0.1423 data: 0.0542 max mem: 9390 +Train: [85] [2300/6250] eta: 0:12:28 lr: 0.000007 grad: 0.1335 (0.1354) loss: 0.8088 (0.8152) time: 0.1455 data: 0.0596 max mem: 9390 +Train: [85] [2400/6250] eta: 0:12:13 lr: 0.000007 grad: 0.1232 (0.1352) loss: 0.8130 (0.8153) time: 0.2548 data: 0.1631 max mem: 9390 +Train: [85] [2500/6250] eta: 0:11:49 lr: 0.000007 grad: 0.1294 (0.1350) loss: 0.8117 (0.8152) time: 0.2045 data: 0.1212 max mem: 9390 +Train: [85] [2600/6250] eta: 0:11:36 lr: 0.000007 grad: 0.1292 (0.1349) loss: 0.8122 (0.8151) time: 0.3509 data: 0.2530 max mem: 9390 +Train: [85] [2700/6250] eta: 0:11:13 lr: 0.000007 grad: 0.1265 (0.1349) loss: 0.8154 (0.8151) time: 0.2331 data: 0.1522 max mem: 9390 +Train: [85] [2800/6250] eta: 0:10:51 lr: 0.000007 grad: 0.1346 (0.1350) loss: 0.8077 (0.8149) time: 0.1141 data: 0.0170 max mem: 9390 +Train: [85] [2900/6250] eta: 0:10:37 lr: 0.000007 grad: 0.1304 (0.1350) loss: 0.8108 (0.8148) time: 0.0908 data: 0.0053 max mem: 9390 +Train: [85] [3000/6250] eta: 0:10:16 lr: 0.000007 grad: 0.1358 (0.1350) loss: 0.8169 (0.8147) time: 0.2607 data: 0.1692 max mem: 9390 +Train: [85] [3100/6250] eta: 0:09:53 lr: 0.000007 grad: 0.1316 (0.1352) loss: 0.8104 (0.8145) time: 0.1244 data: 0.0362 max mem: 9390 +Train: [85] [3200/6250] eta: 0:09:32 lr: 0.000007 grad: 0.1320 (0.1354) loss: 0.8042 (0.8144) time: 0.2247 data: 0.1463 max mem: 9390 +Train: [85] [3300/6250] eta: 0:09:12 lr: 0.000007 grad: 0.1403 (0.1356) loss: 0.8042 (0.8142) time: 0.1392 data: 0.0572 max mem: 9390 +Train: [85] [3400/6250] eta: 0:08:49 lr: 0.000007 grad: 0.1316 (0.1357) loss: 0.8096 (0.8141) time: 0.1450 data: 0.0642 max mem: 9390 +Train: [85] [3500/6250] eta: 0:08:28 lr: 0.000007 grad: 0.1408 (0.1358) loss: 0.8130 (0.8140) time: 0.1519 data: 0.0765 max mem: 9390 +Train: [85] [3600/6250] eta: 0:08:07 lr: 0.000007 grad: 0.1355 (0.1359) loss: 0.8122 (0.8138) time: 0.1520 data: 0.0738 max mem: 9390 +Train: [85] [3700/6250] eta: 0:07:46 lr: 0.000007 grad: 0.1381 (0.1360) loss: 0.8079 (0.8137) time: 0.1678 data: 0.0929 max mem: 9390 +Train: [85] [3800/6250] eta: 0:07:26 lr: 0.000007 grad: 0.1281 (0.1361) loss: 0.8135 (0.8136) time: 0.1645 data: 0.0779 max mem: 9390 +Train: [85] [3900/6250] eta: 0:07:07 lr: 0.000007 grad: 0.1262 (0.1363) loss: 0.8102 (0.8136) time: 0.1633 data: 0.0824 max mem: 9390 +Train: [85] [4000/6250] eta: 0:06:47 lr: 0.000007 grad: 0.1398 (0.1363) loss: 0.8082 (0.8134) time: 0.1522 data: 0.0739 max mem: 9390 +Train: [85] [4100/6250] eta: 0:06:27 lr: 0.000007 grad: 0.1390 (0.1362) loss: 0.8074 (0.8134) time: 0.1634 data: 0.0806 max mem: 9390 +Train: [85] [4200/6250] eta: 0:06:07 lr: 0.000007 grad: 0.1405 (0.1363) loss: 0.8140 (0.8134) time: 0.1281 data: 0.0408 max mem: 9390 +Train: [85] [4300/6250] eta: 0:05:48 lr: 0.000007 grad: 0.1275 (0.1363) loss: 0.8143 (0.8133) time: 0.1398 data: 0.0545 max mem: 9390 +Train: [85] [4400/6250] eta: 0:05:29 lr: 0.000007 grad: 0.1361 (0.1364) loss: 0.8105 (0.8133) time: 0.1655 data: 0.0780 max mem: 9390 +Train: [85] [4500/6250] eta: 0:05:10 lr: 0.000007 grad: 0.1300 (0.1364) loss: 0.8095 (0.8133) time: 0.1592 data: 0.0736 max mem: 9390 +Train: [85] [4600/6250] eta: 0:04:52 lr: 0.000007 grad: 0.1293 (0.1364) loss: 0.8124 (0.8132) time: 0.1560 data: 0.0686 max mem: 9390 +Train: [85] [4700/6250] eta: 0:04:33 lr: 0.000007 grad: 0.1254 (0.1363) loss: 0.8148 (0.8133) time: 0.1482 data: 0.0554 max mem: 9390 +Train: [85] [4800/6250] eta: 0:04:14 lr: 0.000007 grad: 0.1345 (0.1363) loss: 0.8147 (0.8132) time: 0.1354 data: 0.0507 max mem: 9390 +Train: [85] [4900/6250] eta: 0:03:56 lr: 0.000007 grad: 0.1331 (0.1362) loss: 0.8112 (0.8132) time: 0.1425 data: 0.0522 max mem: 9390 +Train: [85] [5000/6250] eta: 0:03:38 lr: 0.000007 grad: 0.1284 (0.1362) loss: 0.8174 (0.8132) time: 0.1494 data: 0.0552 max mem: 9390 +Train: [85] [5100/6250] eta: 0:03:20 lr: 0.000007 grad: 0.1294 (0.1362) loss: 0.8114 (0.8132) time: 0.1302 data: 0.0444 max mem: 9390 +Train: [85] [5200/6250] eta: 0:03:01 lr: 0.000007 grad: 0.1313 (0.1361) loss: 0.8120 (0.8132) time: 0.1280 data: 0.0457 max mem: 9390 +Train: [85] [5300/6250] eta: 0:02:44 lr: 0.000007 grad: 0.1297 (0.1362) loss: 0.8119 (0.8132) time: 0.1315 data: 0.0501 max mem: 9390 +Train: [85] [5400/6250] eta: 0:02:26 lr: 0.000007 grad: 0.1330 (0.1362) loss: 0.8104 (0.8131) time: 0.1258 data: 0.0373 max mem: 9390 +Train: [85] [5500/6250] eta: 0:02:08 lr: 0.000007 grad: 0.1353 (0.1361) loss: 0.8093 (0.8131) time: 0.1670 data: 0.0717 max mem: 9390 +Train: [85] [5600/6250] eta: 0:01:51 lr: 0.000007 grad: 0.1422 (0.1362) loss: 0.8140 (0.8130) time: 0.2244 data: 0.1420 max mem: 9390 +Train: [85] [5700/6250] eta: 0:01:34 lr: 0.000007 grad: 0.1314 (0.1361) loss: 0.8149 (0.8130) time: 0.1396 data: 0.0540 max mem: 9390 +Train: [85] [5800/6250] eta: 0:01:16 lr: 0.000007 grad: 0.1368 (0.1362) loss: 0.8149 (0.8130) time: 0.1662 data: 0.0883 max mem: 9390 +Train: [85] [5900/6250] eta: 0:00:59 lr: 0.000007 grad: 0.1393 (0.1362) loss: 0.8084 (0.8130) time: 0.1311 data: 0.0520 max mem: 9390 +Train: [85] [6000/6250] eta: 0:00:42 lr: 0.000007 grad: 0.1289 (0.1362) loss: 0.8145 (0.8129) time: 0.1391 data: 0.0616 max mem: 9390 +Train: [85] [6100/6250] eta: 0:00:25 lr: 0.000007 grad: 0.1273 (0.1362) loss: 0.8128 (0.8129) time: 0.1327 data: 0.0556 max mem: 9390 +Train: [85] [6200/6250] eta: 0:00:08 lr: 0.000007 grad: 0.1325 (0.1361) loss: 0.8103 (0.8129) time: 0.1460 data: 0.0642 max mem: 9390 +Train: [85] [6249/6250] eta: 0:00:00 lr: 0.000007 grad: 0.1361 (0.1361) loss: 0.8096 (0.8129) time: 0.1504 data: 0.0723 max mem: 9390 +Train: [85] Total time: 0:17:43 (0.1702 s / it) +Averaged stats: lr: 0.000007 grad: 0.1361 (0.1361) loss: 0.8096 (0.8129) +Eval (hcp-train-subset): [85] [ 0/62] eta: 0:04:11 loss: 0.8268 (0.8268) time: 4.0518 data: 4.0052 max mem: 9390 +Eval (hcp-train-subset): [85] [61/62] eta: 0:00:00 loss: 0.8177 (0.8204) time: 0.1497 data: 0.1228 max mem: 9390 +Eval (hcp-train-subset): [85] Total time: 0:00:13 (0.2168 s / it) +Averaged stats (hcp-train-subset): loss: 0.8177 (0.8204) +Eval (hcp-val): [85] [ 0/62] eta: 0:04:25 loss: 0.8234 (0.8234) time: 4.2853 data: 4.2409 max mem: 9390 +Eval (hcp-val): [85] [61/62] eta: 0:00:00 loss: 0.8279 (0.8287) time: 0.1248 data: 0.0982 max mem: 9390 +Eval (hcp-val): [85] Total time: 0:00:13 (0.2121 s / it) +Averaged stats (hcp-val): loss: 0.8279 (0.8287) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +Train: [86] [ 0/6250] eta: 8:05:50 lr: 0.000007 grad: 0.1745 (0.1745) loss: 0.8405 (0.8405) time: 4.6640 data: 4.4869 max mem: 9390 +Train: [86] [ 100/6250] eta: 0:19:35 lr: 0.000007 grad: 0.1451 (0.1682) loss: 0.8142 (0.8211) time: 0.1441 data: 0.0578 max mem: 9390 +Train: [86] [ 200/6250] eta: 0:17:51 lr: 0.000007 grad: 0.1372 (0.1633) loss: 0.8181 (0.8186) time: 0.1705 data: 0.0827 max mem: 9390 +Train: [86] [ 300/6250] eta: 0:16:52 lr: 0.000007 grad: 0.1530 (0.1595) loss: 0.8091 (0.8169) time: 0.1495 data: 0.0656 max mem: 9390 +Train: [86] [ 400/6250] eta: 0:16:15 lr: 0.000007 grad: 0.1458 (0.1582) loss: 0.8108 (0.8142) time: 0.1495 data: 0.0568 max mem: 9390 +Train: [86] [ 500/6250] eta: 0:16:02 lr: 0.000007 grad: 0.1489 (0.1581) loss: 0.8058 (0.8116) time: 0.1994 data: 0.1078 max mem: 9390 +Train: [86] [ 600/6250] eta: 0:15:45 lr: 0.000006 grad: 0.1443 (0.1572) loss: 0.8087 (0.8099) time: 0.1723 data: 0.0735 max mem: 9390 +Train: [86] [ 700/6250] eta: 0:15:59 lr: 0.000006 grad: 0.1409 (0.1560) loss: 0.8066 (0.8091) time: 0.2262 data: 0.1327 max mem: 9390 +Train: [86] [ 800/6250] eta: 0:15:40 lr: 0.000006 grad: 0.1434 (0.1547) loss: 0.8108 (0.8091) time: 0.1243 data: 0.0259 max mem: 9390 +Train: [86] [ 900/6250] eta: 0:16:03 lr: 0.000006 grad: 0.1358 (0.1529) loss: 0.8122 (0.8094) time: 0.1265 data: 0.0222 max mem: 9390 +Train: [86] [1000/6250] eta: 0:15:48 lr: 0.000006 grad: 0.1320 (0.1519) loss: 0.8065 (0.8094) time: 0.1501 data: 0.0535 max mem: 9390 +Train: [86] [1100/6250] eta: 0:15:33 lr: 0.000006 grad: 0.1377 (0.1511) loss: 0.8112 (0.8096) time: 0.1691 data: 0.0651 max mem: 9390 +Train: [86] [1200/6250] eta: 0:15:05 lr: 0.000006 grad: 0.1308 (0.1500) loss: 0.8109 (0.8096) time: 0.0989 data: 0.0002 max mem: 9390 +Train: [86] [1300/6250] eta: 0:14:51 lr: 0.000006 grad: 0.1396 (0.1489) loss: 0.8198 (0.8099) time: 0.1229 data: 0.0384 max mem: 9390 +Train: [86] [1400/6250] eta: 0:14:29 lr: 0.000006 grad: 0.1303 (0.1482) loss: 0.8115 (0.8101) time: 0.1205 data: 0.0216 max mem: 9390 +Train: [86] [1500/6250] eta: 0:14:20 lr: 0.000006 grad: 0.1365 (0.1475) loss: 0.8069 (0.8102) time: 0.2198 data: 0.1324 max mem: 9390 +Train: [86] [1600/6250] eta: 0:13:58 lr: 0.000006 grad: 0.1270 (0.1467) loss: 0.8123 (0.8103) time: 0.1416 data: 0.0053 max mem: 9390 +Train: [86] [1700/6250] eta: 0:13:36 lr: 0.000006 grad: 0.1295 (0.1461) loss: 0.8133 (0.8104) time: 0.1976 data: 0.1191 max mem: 9390 +Train: [86] [1800/6250] eta: 0:13:11 lr: 0.000006 grad: 0.1298 (0.1457) loss: 0.8157 (0.8104) time: 0.1952 data: 0.1066 max mem: 9390 +Train: [86] [1900/6250] eta: 0:12:48 lr: 0.000006 grad: 0.1299 (0.1451) loss: 0.8127 (0.8103) time: 0.1530 data: 0.0661 max mem: 9390 +Train: [86] [2000/6250] eta: 0:12:39 lr: 0.000006 grad: 0.1279 (0.1448) loss: 0.8127 (0.8104) time: 0.2652 data: 0.1763 max mem: 9390 +Train: [86] [2100/6250] eta: 0:12:08 lr: 0.000006 grad: 0.1423 (0.1447) loss: 0.8129 (0.8104) time: 0.1289 data: 0.0429 max mem: 9390 +Train: [86] [2200/6250] eta: 0:11:58 lr: 0.000006 grad: 0.1360 (0.1444) loss: 0.8165 (0.8104) time: 0.3965 data: 0.3092 max mem: 9390 +Train: [86] [2300/6250] eta: 0:11:31 lr: 0.000006 grad: 0.1394 (0.1443) loss: 0.8092 (0.8103) time: 0.1446 data: 0.0654 max mem: 9390 +Train: [86] [2400/6250] eta: 0:11:18 lr: 0.000006 grad: 0.1307 (0.1441) loss: 0.8149 (0.8102) time: 0.2215 data: 0.1283 max mem: 9390 +Train: [86] [2500/6250] eta: 0:10:59 lr: 0.000006 grad: 0.1321 (0.1439) loss: 0.8079 (0.8102) time: 0.2274 data: 0.1320 max mem: 9390 +Train: [86] [2600/6250] eta: 0:10:42 lr: 0.000006 grad: 0.1354 (0.1437) loss: 0.8067 (0.8102) time: 0.0915 data: 0.0002 max mem: 9390 +Train: [86] [2700/6250] eta: 0:10:32 lr: 0.000006 grad: 0.1372 (0.1435) loss: 0.8053 (0.8102) time: 0.2161 data: 0.1087 max mem: 9390 +Train: [86] [2800/6250] eta: 0:10:14 lr: 0.000006 grad: 0.1439 (0.1436) loss: 0.8138 (0.8100) time: 0.2327 data: 0.1502 max mem: 9390 +Train: [86] [2900/6250] eta: 0:09:49 lr: 0.000006 grad: 0.1424 (0.1436) loss: 0.8073 (0.8099) time: 0.1220 data: 0.0394 max mem: 9390 +Train: [86] [3000/6250] eta: 0:09:30 lr: 0.000006 grad: 0.1383 (0.1434) loss: 0.8153 (0.8098) time: 0.1070 data: 0.0142 max mem: 9390 +Train: [86] [3100/6250] eta: 0:09:08 lr: 0.000006 grad: 0.1350 (0.1433) loss: 0.8097 (0.8098) time: 0.1402 data: 0.0632 max mem: 9390 +Train: [86] [3200/6250] eta: 0:08:50 lr: 0.000006 grad: 0.1329 (0.1432) loss: 0.8113 (0.8098) time: 0.1763 data: 0.0775 max mem: 9390 +Train: [86] [3300/6250] eta: 0:08:33 lr: 0.000006 grad: 0.1372 (0.1431) loss: 0.8104 (0.8098) time: 0.1543 data: 0.0669 max mem: 9390 +Train: [86] [3400/6250] eta: 0:08:20 lr: 0.000006 grad: 0.1347 (0.1429) loss: 0.8093 (0.8097) time: 0.1292 data: 0.0002 max mem: 9390 +Train: [86] [3500/6250] eta: 0:08:04 lr: 0.000006 grad: 0.1306 (0.1427) loss: 0.8074 (0.8097) time: 0.1891 data: 0.1121 max mem: 9390 +Train: [86] [3600/6250] eta: 0:07:47 lr: 0.000006 grad: 0.1320 (0.1426) loss: 0.8082 (0.8097) time: 0.2131 data: 0.1064 max mem: 9390 +Train: [86] [3700/6250] eta: 0:07:47 lr: 0.000006 grad: 0.1361 (0.1424) loss: 0.8125 (0.8096) time: 0.8809 data: 0.7807 max mem: 9390 +Train: [86] [3800/6250] eta: 0:07:41 lr: 0.000006 grad: 0.1306 (0.1423) loss: 0.8124 (0.8096) time: 0.5659 data: 0.4723 max mem: 9390 +Train: [86] [3900/6250] eta: 0:07:20 lr: 0.000006 grad: 0.1311 (0.1422) loss: 0.8086 (0.8097) time: 0.1936 data: 0.1127 max mem: 9390 +Train: [86] [4000/6250] eta: 0:07:02 lr: 0.000006 grad: 0.1362 (0.1420) loss: 0.8113 (0.8097) time: 0.1652 data: 0.0728 max mem: 9390 +Train: [86] [4100/6250] eta: 0:06:44 lr: 0.000006 grad: 0.1344 (0.1418) loss: 0.8142 (0.8097) time: 0.2387 data: 0.1265 max mem: 9390 +Train: [86] [4200/6250] eta: 0:06:24 lr: 0.000006 grad: 0.1341 (0.1417) loss: 0.8191 (0.8097) time: 0.1933 data: 0.1180 max mem: 9390 +Train: [86] [4300/6250] eta: 0:06:11 lr: 0.000006 grad: 0.1361 (0.1416) loss: 0.8097 (0.8097) time: 0.7773 data: 0.6532 max mem: 9390 +Train: [86] [4400/6250] eta: 0:05:51 lr: 0.000006 grad: 0.1341 (0.1415) loss: 0.8084 (0.8097) time: 0.1980 data: 0.1048 max mem: 9390 +Train: [86] [4500/6250] eta: 0:05:34 lr: 0.000006 grad: 0.1339 (0.1415) loss: 0.8126 (0.8097) time: 0.4753 data: 0.3821 max mem: 9390 +Train: [86] [4600/6250] eta: 0:05:17 lr: 0.000006 grad: 0.1321 (0.1414) loss: 0.8083 (0.8097) time: 0.5103 data: 0.3812 max mem: 9390 +Train: [86] [4700/6250] eta: 0:04:59 lr: 0.000006 grad: 0.1484 (0.1414) loss: 0.7993 (0.8097) time: 0.1116 data: 0.0003 max mem: 9390 +Train: [86] [4800/6250] eta: 0:04:43 lr: 0.000006 grad: 0.1376 (0.1413) loss: 0.8113 (0.8096) time: 0.1090 data: 0.0003 max mem: 9390 +Train: [86] [4900/6250] eta: 0:04:26 lr: 0.000006 grad: 0.1325 (0.1413) loss: 0.8024 (0.8096) time: 0.2817 data: 0.1987 max mem: 9390 +Train: [86] [5000/6250] eta: 0:04:09 lr: 0.000006 grad: 0.1319 (0.1412) loss: 0.8122 (0.8096) time: 0.2932 data: 0.1967 max mem: 9390 +Train: [86] [5100/6250] eta: 0:03:52 lr: 0.000006 grad: 0.1366 (0.1411) loss: 0.8051 (0.8096) time: 0.6477 data: 0.5561 max mem: 9390 +Train: [86] [5200/6250] eta: 0:03:35 lr: 0.000006 grad: 0.1433 (0.1410) loss: 0.8076 (0.8096) time: 0.2407 data: 0.1462 max mem: 9390 +Train: [86] [5300/6250] eta: 0:03:18 lr: 0.000006 grad: 0.1341 (0.1410) loss: 0.8169 (0.8096) time: 0.8423 data: 0.7348 max mem: 9390 +Train: [86] [5400/6250] eta: 0:03:00 lr: 0.000006 grad: 0.1353 (0.1408) loss: 0.8155 (0.8096) time: 0.3085 data: 0.1877 max mem: 9390 +Train: [86] [5500/6250] eta: 0:02:42 lr: 0.000006 grad: 0.1289 (0.1407) loss: 0.8052 (0.8096) time: 0.1255 data: 0.0348 max mem: 9390 +Train: [86] [5600/6250] eta: 0:02:23 lr: 0.000006 grad: 0.1380 (0.1406) loss: 0.8129 (0.8096) time: 0.3094 data: 0.1657 max mem: 9390 +Train: [86] [5700/6250] eta: 0:02:00 lr: 0.000006 grad: 0.1448 (0.1406) loss: 0.8081 (0.8096) time: 0.1014 data: 0.0087 max mem: 9390 +Train: [86] [5800/6250] eta: 0:01:38 lr: 0.000006 grad: 0.1365 (0.1406) loss: 0.8094 (0.8096) time: 0.1446 data: 0.0656 max mem: 9390 +Train: [86] [5900/6250] eta: 0:01:16 lr: 0.000006 grad: 0.1243 (0.1406) loss: 0.8160 (0.8096) time: 0.1797 data: 0.0924 max mem: 9390 +Train: [86] [6000/6250] eta: 0:00:53 lr: 0.000006 grad: 0.1407 (0.1405) loss: 0.8087 (0.8096) time: 0.1571 data: 0.0646 max mem: 9390 +Train: [86] [6100/6250] eta: 0:00:32 lr: 0.000006 grad: 0.1355 (0.1405) loss: 0.8099 (0.8097) time: 0.1613 data: 0.0873 max mem: 9390 +Train: [86] [6200/6250] eta: 0:00:10 lr: 0.000006 grad: 0.1314 (0.1404) loss: 0.8094 (0.8097) time: 0.1632 data: 0.0808 max mem: 9390 +Train: [86] [6249/6250] eta: 0:00:00 lr: 0.000006 grad: 0.1280 (0.1404) loss: 0.8156 (0.8097) time: 0.1632 data: 0.0793 max mem: 9390 +Train: [86] Total time: 0:22:24 (0.2152 s / it) +Averaged stats: lr: 0.000006 grad: 0.1280 (0.1404) loss: 0.8156 (0.8097) +Eval (hcp-train-subset): [86] [ 0/62] eta: 0:03:29 loss: 0.8253 (0.8253) time: 3.3747 data: 3.2983 max mem: 9390 +Eval (hcp-train-subset): [86] [61/62] eta: 0:00:00 loss: 0.8178 (0.8196) time: 0.0868 data: 0.0615 max mem: 9390 +Eval (hcp-train-subset): [86] Total time: 0:00:13 (0.2203 s / it) +Averaged stats (hcp-train-subset): loss: 0.8178 (0.8196) +Eval (hcp-val): [86] [ 0/62] eta: 0:05:16 loss: 0.8248 (0.8248) time: 5.1051 data: 5.0756 max mem: 9390 +Eval (hcp-val): [86] [61/62] eta: 0:00:00 loss: 0.8290 (0.8287) time: 0.1295 data: 0.1043 max mem: 9390 +Eval (hcp-val): [86] Total time: 0:00:14 (0.2294 s / it) +Averaged stats (hcp-val): loss: 0.8290 (0.8287) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +Train: [87] [ 0/6250] eta: 8:24:54 lr: 0.000006 grad: 0.1221 (0.1221) loss: 0.8578 (0.8578) time: 4.8471 data: 4.5553 max mem: 9390 +Train: [87] [ 100/6250] eta: 0:23:03 lr: 0.000006 grad: 0.1578 (0.1729) loss: 0.8091 (0.8106) time: 0.2129 data: 0.1230 max mem: 9390 +Train: [87] [ 200/6250] eta: 0:20:51 lr: 0.000006 grad: 0.1384 (0.1671) loss: 0.8133 (0.8092) time: 0.2422 data: 0.1210 max mem: 9390 +Train: [87] [ 300/6250] eta: 0:19:35 lr: 0.000006 grad: 0.1373 (0.1617) loss: 0.8068 (0.8101) time: 0.2622 data: 0.1488 max mem: 9390 +Train: [87] [ 400/6250] eta: 0:20:51 lr: 0.000006 grad: 0.1321 (0.1563) loss: 0.8186 (0.8110) time: 0.2266 data: 0.1225 max mem: 9390 +Train: [87] [ 500/6250] eta: 0:22:12 lr: 0.000006 grad: 0.1445 (0.1534) loss: 0.8116 (0.8116) time: 0.1174 data: 0.0196 max mem: 9390 +Train: [87] [ 600/6250] eta: 0:24:14 lr: 0.000006 grad: 0.1333 (0.1510) loss: 0.8154 (0.8116) time: 0.7220 data: 0.6172 max mem: 9390 +Train: [87] [ 700/6250] eta: 0:23:15 lr: 0.000006 grad: 0.1294 (0.1488) loss: 0.8158 (0.8120) time: 0.2583 data: 0.1627 max mem: 9390 +Train: [87] [ 800/6250] eta: 0:22:55 lr: 0.000006 grad: 0.1347 (0.1475) loss: 0.8084 (0.8118) time: 0.1947 data: 0.0452 max mem: 9390 +Train: [87] [ 900/6250] eta: 0:23:27 lr: 0.000006 grad: 0.1392 (0.1462) loss: 0.8089 (0.8118) time: 0.1831 data: 0.0680 max mem: 9390 +Train: [87] [1000/6250] eta: 0:23:08 lr: 0.000006 grad: 0.1248 (0.1449) loss: 0.8222 (0.8123) time: 0.2466 data: 0.0978 max mem: 9390 +Train: [87] [1100/6250] eta: 0:22:38 lr: 0.000006 grad: 0.1271 (0.1437) loss: 0.8189 (0.8125) time: 0.5999 data: 0.4908 max mem: 9390 +Train: [87] [1200/6250] eta: 0:21:55 lr: 0.000006 grad: 0.1304 (0.1429) loss: 0.8187 (0.8127) time: 0.1216 data: 0.0210 max mem: 9390 +Train: [87] [1300/6250] eta: 0:21:04 lr: 0.000006 grad: 0.1258 (0.1422) loss: 0.8176 (0.8128) time: 0.1165 data: 0.0002 max mem: 9390 +Train: [87] [1400/6250] eta: 0:22:06 lr: 0.000005 grad: 0.1232 (0.1416) loss: 0.8164 (0.8130) time: 0.1078 data: 0.0003 max mem: 9390 +Train: [87] [1500/6250] eta: 0:22:06 lr: 0.000005 grad: 0.1260 (0.1412) loss: 0.8170 (0.8132) time: 0.6937 data: 0.6097 max mem: 9390 +Train: [87] [1600/6250] eta: 0:21:37 lr: 0.000005 grad: 0.1284 (0.1409) loss: 0.8201 (0.8133) time: 0.1395 data: 0.0503 max mem: 9390 +Train: [87] [1700/6250] eta: 0:20:52 lr: 0.000005 grad: 0.1349 (0.1406) loss: 0.8190 (0.8134) time: 0.0958 data: 0.0002 max mem: 9390 +Train: [87] [1800/6250] eta: 0:20:47 lr: 0.000005 grad: 0.1317 (0.1405) loss: 0.8206 (0.8135) time: 0.1006 data: 0.0002 max mem: 9390 +Train: [87] [1900/6250] eta: 0:20:28 lr: 0.000005 grad: 0.1280 (0.1401) loss: 0.8159 (0.8135) time: 0.3354 data: 0.2313 max mem: 9390 +Train: [87] [2000/6250] eta: 0:19:57 lr: 0.000005 grad: 0.1352 (0.1397) loss: 0.8095 (0.8136) time: 0.2887 data: 0.1940 max mem: 9390 +Train: [87] [2100/6250] eta: 0:19:43 lr: 0.000005 grad: 0.1334 (0.1395) loss: 0.8143 (0.8137) time: 0.1061 data: 0.0002 max mem: 9390 +Train: [87] [2200/6250] eta: 0:19:12 lr: 0.000005 grad: 0.1348 (0.1392) loss: 0.8097 (0.8137) time: 0.1012 data: 0.0002 max mem: 9390 +Train: [87] [2300/6250] eta: 0:18:27 lr: 0.000005 grad: 0.1295 (0.1390) loss: 0.8151 (0.8138) time: 0.1842 data: 0.0795 max mem: 9390 +pretraining fmri mae +start: 2026-04-01 15:51:20 +cwd: /data/connor/fmri-fm +sha: 7f4cedc35609f6857314e0d1ea6657523f17ddeb, status: has uncommitted changes, branch: dev/clane9 +config: +name: input_space_v3/flat_lr1e-3_1/pretrain +notes: input_space ablation v3 flat_lr1e-3_1; use tube masking and on-disk data (input_space=flat + base_lr=1e-3 seed=5401) +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain +input_space: flat +patch_size: 16 +num_frames: 16 +t_patch_size: 4 +mask_ratio: 0.9 +pred_mask_ratio: null +masking: tube +masking_kwargs: {} +mask_patch_size: null +model: mae_vit_base +model_kwargs: + decoding: attn + pos_embed: sep + target_norm: null + pca_norm_nc: 2 + t_pred_stride: 2 + no_decode_pos: true + mask_drop_scale: false + pred_edge_pad: 0 + gauss_sigma: null + class_token: true + reg_tokens: 0 + no_embed_class: true + head_init_scale: 0.0 + decoder_depth: 4 + drop_path_rate: 0.0 +datasets: + hcp-train: + type: wds + url: /data/fmri-datasets/pretrain/hcpya-all.${input_space}.wds/hcpya-all-${input_space}-{00000..01799}.tar + clipping: random + clipping_kwargs: + oversample: 4.0 + shuffle: true + buffer_size: 2000 + samples_per_epoch: 200000 + hcp-train-subset: + type: arrow + root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/validation + split_range: + - 0 + - 2000 + shuffle: false + hcp-val: + type: arrow + root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/test + split_range: + - 0 + - 2000 + shuffle: false +train_dataset: hcp-train +eval_datasets: +- hcp-train-subset +- hcp-val +val_dataset: null +clip_vmax: 3.0 +normalize: frame +tr_scale: null +crop_scale: null +crop_aspect: null +gray_jitter: null +num_workers: 16 +epochs: 100 +batch_size: 32 +accum_iter: 1 +base_lr: 0.001 +min_lr: 0.0 +warmup_epochs: 5 +weight_decay: 0.05 +betas: +- 0.9 +- 0.95 +clip_grad: 1.0 +amp: true +amp_dtype: float16 +ckpt: null +resume: true +auto_resume: true +start_epoch: 0 +max_checkpoints: 0 +checkpoint_period: null +plot_period: 5 +device: cuda +presend_cuda: false +seed: 5401 +debug: false +wandb: true +wandb_entity: null +wandb_project: fMRI-foundation-model +rank: 0 +world_size: 1 +gpu: 0 +distributed: true +dist_backend: nccl +in_chans: 1 +img_size: +- 224 +- 560 + +train transform: +Compose( + ToTensor() + TemporalCenterCrop(num_frames=16) + Normalize(mode='frame') + Clip(vmax=3.0) + FlatUnmask((224, 560)) +) +val transform: +Compose( + ToTensor() + TemporalCenterCrop(num_frames=16) + Normalize(mode='frame') + Clip(vmax=3.0) + FlatUnmask((224, 560)) +) +mask generator: +TubeMasking( + mask_ratio=0.9 + (patchify): Patchify2D((224, 560), (16, 16), in_chans=1) +) +loading dataset: hcp-train + +type: wds +url: /data/fmri-datasets/pretrain/hcpya-all.${input_space}.wds/hcpya-all-${input_space}-{00000..01799}.tar +clipping: random +clipping_kwargs: + oversample: 4.0 +shuffle: true +buffer_size: 2000 +samples_per_epoch: 200000 + +loading dataset: hcp-train-subset + +type: arrow +root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/validation +split_range: +- 0 +- 2000 +shuffle: false + +split indices: [899, 472, 767, 116, 1265, 1852, 300, 1335, 361, 1560] +loading dataset: hcp-val + +type: arrow +root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/test +split_range: +- 0 +- 2000 +shuffle: false + +split indices: [1075, 1189, 738, 1350, 965, 1964, 1367, 1183, 1619, 1407] +model: +MaskedAutoencoderViT( + decoding=attn, t_pred_stride=2, pred_edge_pad=0, no_decode_pos=True + (encoder): MaskedEncoder( + class_token=True, reg_tokens=0, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) + (pred_patchify): StridedPatchify3D((16, 224, 560), (2, 16, 16), in_chans=1, t_stride=2) + (decoder): MaskedDecoder( + cross_decode=False, class_token=True, no_embed_class=True + (pos_embed): SeparablePosEmbed(512, (4, 14, 35)) + (proj): Linear(in_features=768, out_features=512, bias=True) + (blocks): ModuleList( + (0-3): 4 x Block( + (norm1): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=16 + (q): Linear(in_features=512, out_features=512, bias=True) + (k): Linear(in_features=512, out_features=512, bias=True) + (v): Linear(in_features=512, out_features=512, bias=True) + (proj): Linear(in_features=512, out_features=512, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=512, out_features=2048, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=2048, out_features=512, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (head): Linear(in_features=512, out_features=512, bias=True) + ) +) +num params: 99.7M +total batch size: 32 = 32 bs per gpu x 1 accum x 1 gpus +lr: 1.25e-04 = 1.00e-03 x 32 / 256 +full schedule: epochs = 100 (steps = 625000) +warmup: epochs = 5 (steps = 31250) +loaded model state from checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +loaded optimizer state, resuming training from 87 +start training for 100 epochs +Train: [87] [ 0/6250] eta: 13:04:07 lr: 0.000006 grad: 0.0924 (0.0924) loss: 0.8454 (0.8454) time: 7.5275 data: 6.5735 max mem: 9353 +Train: [87] [ 100/6250] eta: 0:21:01 lr: 0.000006 grad: 0.1593 (0.2039) loss: 0.8233 (0.8153) time: 0.1512 data: 0.0743 max mem: 9390 +Train: [87] [ 200/6250] eta: 0:18:12 lr: 0.000006 grad: 0.1610 (0.1843) loss: 0.8027 (0.8142) time: 0.1612 data: 0.0762 max mem: 9390 +Train: [87] [ 300/6250] eta: 0:16:53 lr: 0.000006 grad: 0.1403 (0.1763) loss: 0.8147 (0.8128) time: 0.1423 data: 0.0551 max mem: 9390 +Train: [87] [ 400/6250] eta: 0:16:00 lr: 0.000006 grad: 0.1456 (0.1699) loss: 0.8010 (0.8127) time: 0.1474 data: 0.0417 max mem: 9390 +Train: [87] [ 500/6250] eta: 0:15:18 lr: 0.000006 grad: 0.1461 (0.1659) loss: 0.8049 (0.8122) time: 0.1360 data: 0.0446 max mem: 9390 +Train: [87] [ 600/6250] eta: 0:14:49 lr: 0.000006 grad: 0.1448 (0.1625) loss: 0.8070 (0.8119) time: 0.1396 data: 0.0517 max mem: 9390 +Train: [87] [ 700/6250] eta: 0:14:22 lr: 0.000006 grad: 0.1318 (0.1601) loss: 0.8110 (0.8117) time: 0.1453 data: 0.0529 max mem: 9390 +Train: [87] [ 800/6250] eta: 0:14:08 lr: 0.000006 grad: 0.1496 (0.1586) loss: 0.8069 (0.8116) time: 0.1496 data: 0.0627 max mem: 9390 +Train: [87] [ 900/6250] eta: 0:13:55 lr: 0.000006 grad: 0.1325 (0.1567) loss: 0.8126 (0.8115) time: 0.1654 data: 0.0806 max mem: 9390 +Train: [87] [1000/6250] eta: 0:13:40 lr: 0.000006 grad: 0.1353 (0.1555) loss: 0.8152 (0.8115) time: 0.1632 data: 0.0738 max mem: 9390 +Train: [87] [1100/6250] eta: 0:13:26 lr: 0.000006 grad: 0.1406 (0.1545) loss: 0.8200 (0.8116) time: 0.1847 data: 0.1027 max mem: 9390 +Train: [87] [1200/6250] eta: 0:13:10 lr: 0.000006 grad: 0.1390 (0.1535) loss: 0.8124 (0.8116) time: 0.1619 data: 0.0761 max mem: 9390 +Train: [87] [1300/6250] eta: 0:12:55 lr: 0.000006 grad: 0.1398 (0.1525) loss: 0.8123 (0.8116) time: 0.1561 data: 0.0716 max mem: 9390 +Train: [87] [1400/6250] eta: 0:12:40 lr: 0.000005 grad: 0.1365 (0.1518) loss: 0.8159 (0.8116) time: 0.1590 data: 0.0720 max mem: 9390 +Train: [87] [1500/6250] eta: 0:12:25 lr: 0.000005 grad: 0.1415 (0.1510) loss: 0.8094 (0.8116) time: 0.1624 data: 0.0732 max mem: 9390 +Train: [87] [1600/6250] eta: 0:12:09 lr: 0.000005 grad: 0.1318 (0.1503) loss: 0.8178 (0.8117) time: 0.1537 data: 0.0748 max mem: 9390 +Train: [87] [1700/6250] eta: 0:11:52 lr: 0.000005 grad: 0.1344 (0.1498) loss: 0.8136 (0.8117) time: 0.1723 data: 0.0845 max mem: 9390 +Train: [87] [1800/6250] eta: 0:11:35 lr: 0.000005 grad: 0.1362 (0.1492) loss: 0.8085 (0.8116) time: 0.1548 data: 0.0767 max mem: 9390 +Train: [87] [1900/6250] eta: 0:11:16 lr: 0.000005 grad: 0.1381 (0.1486) loss: 0.8077 (0.8115) time: 0.1424 data: 0.0618 max mem: 9390 +Train: [87] [2000/6250] eta: 0:10:59 lr: 0.000005 grad: 0.1330 (0.1481) loss: 0.8124 (0.8114) time: 0.1372 data: 0.0539 max mem: 9390 +Train: [87] [2100/6250] eta: 0:10:42 lr: 0.000005 grad: 0.1396 (0.1478) loss: 0.8067 (0.8113) time: 0.1488 data: 0.0663 max mem: 9390 +Train: [87] [2200/6250] eta: 0:10:50 lr: 0.000005 grad: 0.1388 (0.1476) loss: 0.8120 (0.8112) time: 0.2600 data: 0.1770 max mem: 9390 +Train: [87] [2300/6250] eta: 0:10:42 lr: 0.000005 grad: 0.1377 (0.1474) loss: 0.8133 (0.8111) time: 0.1163 data: 0.0159 max mem: 9390 +Train: [87] [2400/6250] eta: 0:10:30 lr: 0.000005 grad: 0.1415 (0.1473) loss: 0.8091 (0.8111) time: 0.1851 data: 0.0989 max mem: 9390 +Train: [87] [2500/6250] eta: 0:10:16 lr: 0.000005 grad: 0.1415 (0.1471) loss: 0.8097 (0.8110) time: 0.1636 data: 0.0656 max mem: 9390 +Train: [87] [2600/6250] eta: 0:10:01 lr: 0.000005 grad: 0.1454 (0.1471) loss: 0.8005 (0.8108) time: 0.1769 data: 0.0803 max mem: 9390 +Train: [87] [2700/6250] eta: 0:09:46 lr: 0.000005 grad: 0.1362 (0.1469) loss: 0.8080 (0.8106) time: 0.1843 data: 0.0989 max mem: 9390 +Train: [87] [2800/6250] eta: 0:09:32 lr: 0.000005 grad: 0.1420 (0.1467) loss: 0.8003 (0.8105) time: 0.1390 data: 0.0520 max mem: 9390 +Train: [87] [2900/6250] eta: 0:09:16 lr: 0.000005 grad: 0.1333 (0.1465) loss: 0.8160 (0.8105) time: 0.1746 data: 0.0913 max mem: 9390 +Train: [87] [3000/6250] eta: 0:09:00 lr: 0.000005 grad: 0.1354 (0.1464) loss: 0.8057 (0.8105) time: 0.1699 data: 0.0668 max mem: 9390 +Train: [87] [3100/6250] eta: 0:08:45 lr: 0.000005 grad: 0.1452 (0.1463) loss: 0.8087 (0.8104) time: 0.1861 data: 0.0963 max mem: 9390 +Train: [87] [3200/6250] eta: 0:08:29 lr: 0.000005 grad: 0.1305 (0.1461) loss: 0.8106 (0.8104) time: 0.1522 data: 0.0584 max mem: 9390 +Train: [87] [3300/6250] eta: 0:08:13 lr: 0.000005 grad: 0.1407 (0.1459) loss: 0.8123 (0.8105) time: 0.1658 data: 0.0730 max mem: 9390 +Train: [87] [3400/6250] eta: 0:07:57 lr: 0.000005 grad: 0.1321 (0.1458) loss: 0.8087 (0.8104) time: 0.1790 data: 0.0890 max mem: 9390 +Train: [87] [3500/6250] eta: 0:07:41 lr: 0.000005 grad: 0.1384 (0.1457) loss: 0.8140 (0.8104) time: 0.1751 data: 0.0836 max mem: 9390 +Train: [87] [3600/6250] eta: 0:07:25 lr: 0.000005 grad: 0.1404 (0.1455) loss: 0.8049 (0.8104) time: 0.1816 data: 0.0957 max mem: 9390 +Train: [87] [3700/6250] eta: 0:07:09 lr: 0.000005 grad: 0.1346 (0.1454) loss: 0.8122 (0.8104) time: 0.1643 data: 0.0741 max mem: 9390 +Train: [87] [3800/6250] eta: 0:06:53 lr: 0.000005 grad: 0.1322 (0.1452) loss: 0.8162 (0.8104) time: 0.1860 data: 0.1003 max mem: 9390 +Train: [87] [3900/6250] eta: 0:06:36 lr: 0.000005 grad: 0.1377 (0.1450) loss: 0.8143 (0.8104) time: 0.1791 data: 0.0891 max mem: 9390 +Train: [87] [4000/6250] eta: 0:06:19 lr: 0.000005 grad: 0.1311 (0.1448) loss: 0.8145 (0.8104) time: 0.1732 data: 0.0836 max mem: 9390 +Train: [87] [4100/6250] eta: 0:06:03 lr: 0.000005 grad: 0.1360 (0.1447) loss: 0.8064 (0.8104) time: 0.1665 data: 0.0777 max mem: 9390 +Train: [87] [4200/6250] eta: 0:05:46 lr: 0.000005 grad: 0.1315 (0.1446) loss: 0.8093 (0.8104) time: 0.1762 data: 0.0756 max mem: 9390 +Train: [87] [4300/6250] eta: 0:05:29 lr: 0.000005 grad: 0.1338 (0.1444) loss: 0.8206 (0.8104) time: 0.1686 data: 0.0797 max mem: 9390 +Train: [87] [4400/6250] eta: 0:05:13 lr: 0.000005 grad: 0.1306 (0.1442) loss: 0.8096 (0.8104) time: 0.1856 data: 0.0917 max mem: 9390 +Train: [87] [4500/6250] eta: 0:04:56 lr: 0.000005 grad: 0.1373 (0.1441) loss: 0.8134 (0.8105) time: 0.1816 data: 0.0936 max mem: 9390 +Train: [87] [4600/6250] eta: 0:04:39 lr: 0.000005 grad: 0.1335 (0.1439) loss: 0.8045 (0.8104) time: 0.1754 data: 0.0863 max mem: 9390 +Train: [87] [4700/6250] eta: 0:04:22 lr: 0.000005 grad: 0.1423 (0.1439) loss: 0.8109 (0.8105) time: 0.1750 data: 0.0852 max mem: 9390 +Train: [87] [4800/6250] eta: 0:04:05 lr: 0.000005 grad: 0.1462 (0.1438) loss: 0.8081 (0.8105) time: 0.1417 data: 0.0444 max mem: 9390 +Train: [87] [4900/6250] eta: 0:03:48 lr: 0.000005 grad: 0.1295 (0.1437) loss: 0.8122 (0.8105) time: 0.1606 data: 0.0705 max mem: 9390 +Train: [87] [5000/6250] eta: 0:03:31 lr: 0.000005 grad: 0.1383 (0.1436) loss: 0.8047 (0.8105) time: 0.1499 data: 0.0600 max mem: 9390 +Train: [87] [5100/6250] eta: 0:03:14 lr: 0.000005 grad: 0.1412 (0.1436) loss: 0.8127 (0.8105) time: 0.1894 data: 0.0953 max mem: 9390 +Train: [87] [5200/6250] eta: 0:02:57 lr: 0.000005 grad: 0.1270 (0.1435) loss: 0.8229 (0.8105) time: 0.1699 data: 0.0843 max mem: 9390 +Train: [87] [5300/6250] eta: 0:02:41 lr: 0.000005 grad: 0.1346 (0.1435) loss: 0.8096 (0.8104) time: 0.2086 data: 0.1171 max mem: 9390 +Train: [87] [5400/6250] eta: 0:02:24 lr: 0.000005 grad: 0.1242 (0.1433) loss: 0.8101 (0.8105) time: 0.1608 data: 0.0633 max mem: 9390 +Train: [87] [5500/6250] eta: 0:02:07 lr: 0.000005 grad: 0.1380 (0.1432) loss: 0.8072 (0.8104) time: 0.1719 data: 0.0791 max mem: 9390 +Train: [87] [5600/6250] eta: 0:01:50 lr: 0.000005 grad: 0.1337 (0.1431) loss: 0.8126 (0.8104) time: 0.1742 data: 0.0897 max mem: 9390 +Train: [87] [5700/6250] eta: 0:01:33 lr: 0.000005 grad: 0.1359 (0.1430) loss: 0.8127 (0.8105) time: 0.1885 data: 0.1022 max mem: 9390 +Train: [87] [5800/6250] eta: 0:01:16 lr: 0.000005 grad: 0.1309 (0.1429) loss: 0.8109 (0.8105) time: 0.1543 data: 0.0667 max mem: 9390 +Train: [87] [5900/6250] eta: 0:00:59 lr: 0.000005 grad: 0.1308 (0.1427) loss: 0.8086 (0.8105) time: 0.2014 data: 0.1035 max mem: 9390 +Train: [87] [6000/6250] eta: 0:00:42 lr: 0.000005 grad: 0.1439 (0.1426) loss: 0.8095 (0.8105) time: 0.1949 data: 0.1053 max mem: 9390 +Train: [87] [6100/6250] eta: 0:00:25 lr: 0.000005 grad: 0.1392 (0.1425) loss: 0.8102 (0.8105) time: 0.1628 data: 0.0825 max mem: 9390 +Train: [87] [6200/6250] eta: 0:00:08 lr: 0.000005 grad: 0.1427 (0.1425) loss: 0.8057 (0.8105) time: 0.2037 data: 0.1118 max mem: 9390 +Train: [87] [6249/6250] eta: 0:00:00 lr: 0.000005 grad: 0.1367 (0.1424) loss: 0.8142 (0.8105) time: 0.2564 data: 0.1710 max mem: 9390 +Train: [87] Total time: 0:17:56 (0.1722 s / it) +Averaged stats: lr: 0.000005 grad: 0.1367 (0.1424) loss: 0.8142 (0.8105) +Eval (hcp-train-subset): [87] [ 0/62] eta: 0:05:29 loss: 0.8249 (0.8249) time: 5.3119 data: 5.2786 max mem: 9390 +Eval (hcp-train-subset): [87] [61/62] eta: 0:00:00 loss: 0.8170 (0.8193) time: 0.1460 data: 0.1137 max mem: 9390 +Eval (hcp-train-subset): [87] Total time: 0:00:16 (0.2660 s / it) +Averaged stats (hcp-train-subset): loss: 0.8170 (0.8193) +Eval (hcp-val): [87] [ 0/62] eta: 0:04:10 loss: 0.8216 (0.8216) time: 4.0393 data: 3.9250 max mem: 9390 +Eval (hcp-val): [87] [61/62] eta: 0:00:00 loss: 0.8265 (0.8285) time: 0.1523 data: 0.1246 max mem: 9390 +Eval (hcp-val): [87] Total time: 0:00:14 (0.2343 s / it) +Averaged stats (hcp-val): loss: 0.8265 (0.8285) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +Train: [88] [ 0/6250] eta: 6:44:02 lr: 0.000005 grad: 0.0622 (0.0622) loss: 0.8803 (0.8803) time: 3.8787 data: 3.7320 max mem: 9390 +Train: [88] [ 100/6250] eta: 0:22:31 lr: 0.000005 grad: 0.1412 (0.1662) loss: 0.8258 (0.8272) time: 0.1725 data: 0.0787 max mem: 9390 +Train: [88] [ 200/6250] eta: 0:20:30 lr: 0.000005 grad: 0.1341 (0.1581) loss: 0.8244 (0.8251) time: 0.1876 data: 0.0972 max mem: 9390 +Train: [88] [ 300/6250] eta: 0:19:06 lr: 0.000005 grad: 0.1356 (0.1533) loss: 0.8282 (0.8247) time: 0.1769 data: 0.0753 max mem: 9390 +Train: [88] [ 400/6250] eta: 0:18:11 lr: 0.000005 grad: 0.1435 (0.1527) loss: 0.8131 (0.8237) time: 0.1697 data: 0.0705 max mem: 9390 +Train: [88] [ 500/6250] eta: 0:17:31 lr: 0.000005 grad: 0.1392 (0.1512) loss: 0.8125 (0.8225) time: 0.1663 data: 0.0665 max mem: 9390 +Train: [88] [ 600/6250] eta: 0:17:04 lr: 0.000005 grad: 0.1319 (0.1487) loss: 0.8185 (0.8215) time: 0.1796 data: 0.0815 max mem: 9390 +Train: [88] [ 700/6250] eta: 0:16:35 lr: 0.000005 grad: 0.1363 (0.1473) loss: 0.8138 (0.8203) time: 0.1709 data: 0.0662 max mem: 9390 +Train: [88] [ 800/6250] eta: 0:16:30 lr: 0.000005 grad: 0.1381 (0.1464) loss: 0.8075 (0.8194) time: 0.2103 data: 0.1120 max mem: 9390 +Train: [88] [ 900/6250] eta: 0:16:07 lr: 0.000005 grad: 0.1367 (0.1463) loss: 0.8125 (0.8185) time: 0.1482 data: 0.0598 max mem: 9390 +Train: [88] [1000/6250] eta: 0:15:45 lr: 0.000005 grad: 0.1346 (0.1456) loss: 0.8089 (0.8182) time: 0.1739 data: 0.0758 max mem: 9390 +Train: [88] [1100/6250] eta: 0:15:23 lr: 0.000005 grad: 0.1330 (0.1448) loss: 0.8178 (0.8180) time: 0.1622 data: 0.0660 max mem: 9390 +Train: [88] [1200/6250] eta: 0:15:03 lr: 0.000005 grad: 0.1353 (0.1442) loss: 0.8126 (0.8177) time: 0.1875 data: 0.0923 max mem: 9390 +Train: [88] [1300/6250] eta: 0:14:46 lr: 0.000005 grad: 0.1347 (0.1436) loss: 0.8183 (0.8175) time: 0.1667 data: 0.0726 max mem: 9390 +Train: [88] [1400/6250] eta: 0:14:28 lr: 0.000005 grad: 0.1328 (0.1431) loss: 0.8122 (0.8173) time: 0.1735 data: 0.0762 max mem: 9390 +Train: [88] [1500/6250] eta: 0:14:11 lr: 0.000005 grad: 0.1264 (0.1432) loss: 0.8153 (0.8168) time: 0.1742 data: 0.0907 max mem: 9390 +Train: [88] [1600/6250] eta: 0:13:53 lr: 0.000005 grad: 0.1491 (0.1430) loss: 0.8040 (0.8165) time: 0.1787 data: 0.0873 max mem: 9390 +Train: [88] [1700/6250] eta: 0:13:32 lr: 0.000005 grad: 0.1278 (0.1425) loss: 0.8209 (0.8163) time: 0.1559 data: 0.0628 max mem: 9390 +Train: [88] [1800/6250] eta: 0:13:15 lr: 0.000005 grad: 0.1276 (0.1420) loss: 0.8121 (0.8164) time: 0.1967 data: 0.1094 max mem: 9390 +Train: [88] [1900/6250] eta: 0:12:55 lr: 0.000005 grad: 0.1374 (0.1417) loss: 0.8193 (0.8162) time: 0.1708 data: 0.0804 max mem: 9390 +Train: [88] [2000/6250] eta: 0:12:36 lr: 0.000005 grad: 0.1340 (0.1416) loss: 0.8117 (0.8159) time: 0.1780 data: 0.0817 max mem: 9390 +Train: [88] [2100/6250] eta: 0:12:17 lr: 0.000005 grad: 0.1288 (0.1415) loss: 0.8181 (0.8157) time: 0.1746 data: 0.0838 max mem: 9390 +Train: [88] [2200/6250] eta: 0:11:58 lr: 0.000005 grad: 0.1340 (0.1414) loss: 0.8186 (0.8156) time: 0.1719 data: 0.0723 max mem: 9390 +Train: [88] [2300/6250] eta: 0:11:39 lr: 0.000005 grad: 0.1242 (0.1413) loss: 0.8193 (0.8154) time: 0.1645 data: 0.0685 max mem: 9390 +Train: [88] [2400/6250] eta: 0:11:21 lr: 0.000005 grad: 0.1347 (0.1413) loss: 0.8102 (0.8151) time: 0.1631 data: 0.0690 max mem: 9390 +Train: [88] [2500/6250] eta: 0:11:02 lr: 0.000005 grad: 0.1332 (0.1412) loss: 0.8143 (0.8150) time: 0.1691 data: 0.0807 max mem: 9390 +Train: [88] [2600/6250] eta: 0:10:45 lr: 0.000005 grad: 0.1518 (0.1412) loss: 0.8107 (0.8149) time: 0.1825 data: 0.1005 max mem: 9390 +Train: [88] [2700/6250] eta: 0:10:27 lr: 0.000005 grad: 0.1384 (0.1411) loss: 0.8155 (0.8148) time: 0.1889 data: 0.0971 max mem: 9390 +Train: [88] [2800/6250] eta: 0:10:09 lr: 0.000005 grad: 0.1365 (0.1411) loss: 0.8109 (0.8147) time: 0.1740 data: 0.0800 max mem: 9390 +Train: [88] [2900/6250] eta: 0:09:51 lr: 0.000004 grad: 0.1307 (0.1410) loss: 0.8084 (0.8146) time: 0.1627 data: 0.0691 max mem: 9390 +Train: [88] [3000/6250] eta: 0:09:34 lr: 0.000004 grad: 0.1357 (0.1409) loss: 0.8090 (0.8144) time: 0.1782 data: 0.0851 max mem: 9390 +Train: [88] [3100/6250] eta: 0:09:17 lr: 0.000004 grad: 0.1442 (0.1409) loss: 0.8032 (0.8142) time: 0.1806 data: 0.0850 max mem: 9390 +Train: [88] [3200/6250] eta: 0:09:00 lr: 0.000004 grad: 0.1393 (0.1409) loss: 0.8058 (0.8141) time: 0.1937 data: 0.0997 max mem: 9390 +Train: [88] [3300/6250] eta: 0:08:42 lr: 0.000004 grad: 0.1387 (0.1409) loss: 0.8106 (0.8139) time: 0.1653 data: 0.0751 max mem: 9390 +Train: [88] [3400/6250] eta: 0:08:24 lr: 0.000004 grad: 0.1319 (0.1410) loss: 0.8188 (0.8138) time: 0.1145 data: 0.0112 max mem: 9390 +Train: [88] [3500/6250] eta: 0:08:07 lr: 0.000004 grad: 0.1439 (0.1411) loss: 0.8106 (0.8136) time: 0.1957 data: 0.0986 max mem: 9390 +Train: [88] [3600/6250] eta: 0:07:49 lr: 0.000004 grad: 0.1446 (0.1411) loss: 0.8088 (0.8134) time: 0.1432 data: 0.0470 max mem: 9390 +Train: [88] [3700/6250] eta: 0:07:32 lr: 0.000004 grad: 0.1417 (0.1411) loss: 0.8030 (0.8132) time: 0.1748 data: 0.0794 max mem: 9390 +Train: [88] [3800/6250] eta: 0:07:14 lr: 0.000004 grad: 0.1376 (0.1410) loss: 0.8126 (0.8131) time: 0.2087 data: 0.1131 max mem: 9390 +Train: [88] [3900/6250] eta: 0:06:56 lr: 0.000004 grad: 0.1303 (0.1409) loss: 0.8176 (0.8130) time: 0.1719 data: 0.0757 max mem: 9390 +Train: [88] [4000/6250] eta: 0:06:39 lr: 0.000004 grad: 0.1328 (0.1409) loss: 0.8140 (0.8130) time: 0.1823 data: 0.0854 max mem: 9390 +Train: [88] [4100/6250] eta: 0:06:21 lr: 0.000004 grad: 0.1278 (0.1408) loss: 0.8093 (0.8130) time: 0.1709 data: 0.0763 max mem: 9390 +Train: [88] [4200/6250] eta: 0:06:03 lr: 0.000004 grad: 0.1333 (0.1406) loss: 0.8123 (0.8130) time: 0.1783 data: 0.0941 max mem: 9390 +Train: [88] [4300/6250] eta: 0:05:46 lr: 0.000004 grad: 0.1304 (0.1406) loss: 0.8098 (0.8129) time: 0.1884 data: 0.0896 max mem: 9390 +Train: [88] [4400/6250] eta: 0:05:28 lr: 0.000004 grad: 0.1302 (0.1404) loss: 0.8162 (0.8130) time: 0.1941 data: 0.1072 max mem: 9390 +Train: [88] [4500/6250] eta: 0:05:11 lr: 0.000004 grad: 0.1264 (0.1404) loss: 0.8197 (0.8130) time: 0.2110 data: 0.1206 max mem: 9390 +pretraining fmri mae +start: 2026-04-02 10:08:19 +cwd: /data/connor/fmri-fm +sha: 7f4cedc35609f6857314e0d1ea6657523f17ddeb, status: has uncommitted changes, branch: dev/clane9 +config: +name: input_space_v3/flat_lr1e-3_1/pretrain +notes: input_space ablation v3 flat_lr1e-3_1; use tube masking and on-disk data (input_space=flat + base_lr=1e-3 seed=5401) +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain +input_space: flat +patch_size: 16 +num_frames: 16 +t_patch_size: 4 +mask_ratio: 0.9 +pred_mask_ratio: null +masking: tube +masking_kwargs: {} +mask_patch_size: null +model: mae_vit_base +model_kwargs: + decoding: attn + pos_embed: sep + target_norm: null + pca_norm_nc: 2 + t_pred_stride: 2 + no_decode_pos: true + mask_drop_scale: false + pred_edge_pad: 0 + gauss_sigma: null + class_token: true + reg_tokens: 0 + no_embed_class: true + head_init_scale: 0.0 + decoder_depth: 4 + drop_path_rate: 0.0 +datasets: + hcp-train: + type: wds + url: /data/fmri-datasets/pretrain/hcpya-all.${input_space}.wds/hcpya-all-${input_space}-{00000..01799}.tar + clipping: random + clipping_kwargs: + oversample: 4.0 + shuffle: true + buffer_size: 2000 + samples_per_epoch: 200000 + hcp-train-subset: + type: arrow + root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/validation + split_range: + - 0 + - 2000 + shuffle: false + hcp-val: + type: arrow + root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/test + split_range: + - 0 + - 2000 + shuffle: false +train_dataset: hcp-train +eval_datasets: +- hcp-train-subset +- hcp-val +val_dataset: null +clip_vmax: 3.0 +normalize: frame +tr_scale: null +crop_scale: null +crop_aspect: null +gray_jitter: null +num_workers: 16 +epochs: 100 +batch_size: 32 +accum_iter: 1 +base_lr: 0.001 +min_lr: 0.0 +warmup_epochs: 5 +weight_decay: 0.05 +betas: +- 0.9 +- 0.95 +clip_grad: 1.0 +amp: true +amp_dtype: float16 +ckpt: null +resume: true +auto_resume: true +start_epoch: 0 +max_checkpoints: 0 +checkpoint_period: null +plot_period: 5 +device: cuda +presend_cuda: false +seed: 5401 +debug: false +wandb: true +wandb_entity: null +wandb_project: fMRI-foundation-model +rank: 0 +world_size: 1 +gpu: 0 +distributed: true +dist_backend: nccl +in_chans: 1 +img_size: +- 224 +- 560 + +train transform: +Compose( + ToTensor() + TemporalCenterCrop(num_frames=16) + Normalize(mode='frame') + Clip(vmax=3.0) + FlatUnmask((224, 560)) +) +val transform: +Compose( + ToTensor() + TemporalCenterCrop(num_frames=16) + Normalize(mode='frame') + Clip(vmax=3.0) + FlatUnmask((224, 560)) +) +mask generator: +TubeMasking( + mask_ratio=0.9 + (patchify): Patchify2D((224, 560), (16, 16), in_chans=1) +) +loading dataset: hcp-train + +type: wds +url: /data/fmri-datasets/pretrain/hcpya-all.${input_space}.wds/hcpya-all-${input_space}-{00000..01799}.tar +clipping: random +clipping_kwargs: + oversample: 4.0 +shuffle: true +buffer_size: 2000 +samples_per_epoch: 200000 + +loading dataset: hcp-train-subset + +type: arrow +root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/validation +split_range: +- 0 +- 2000 +shuffle: false + +split indices: [899, 472, 767, 116, 1265, 1852, 300, 1335, 361, 1560] +loading dataset: hcp-val + +type: arrow +root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/test +split_range: +- 0 +- 2000 +shuffle: false + +split indices: [1075, 1189, 738, 1350, 965, 1964, 1367, 1183, 1619, 1407] +model: +MaskedAutoencoderViT( + decoding=attn, t_pred_stride=2, pred_edge_pad=0, no_decode_pos=True + (encoder): MaskedEncoder( + class_token=True, reg_tokens=0, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) + (pred_patchify): StridedPatchify3D((16, 224, 560), (2, 16, 16), in_chans=1, t_stride=2) + (decoder): MaskedDecoder( + cross_decode=False, class_token=True, no_embed_class=True + (pos_embed): SeparablePosEmbed(512, (4, 14, 35)) + (proj): Linear(in_features=768, out_features=512, bias=True) + (blocks): ModuleList( + (0-3): 4 x Block( + (norm1): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=16 + (q): Linear(in_features=512, out_features=512, bias=True) + (k): Linear(in_features=512, out_features=512, bias=True) + (v): Linear(in_features=512, out_features=512, bias=True) + (proj): Linear(in_features=512, out_features=512, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=512, out_features=2048, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=2048, out_features=512, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (head): Linear(in_features=512, out_features=512, bias=True) + ) +) +num params: 99.7M +total batch size: 32 = 32 bs per gpu x 1 accum x 1 gpus +lr: 1.25e-04 = 1.00e-03 x 32 / 256 +full schedule: epochs = 100 (steps = 625000) +warmup: epochs = 5 (steps = 31250) +loaded model state from checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +loaded optimizer state, resuming training from 88 +start training for 100 epochs +Train: [88] [ 0/6250] eta: 9:48:11 lr: 0.000005 grad: 0.1929 (0.1929) loss: 0.8562 (0.8562) time: 5.6467 data: 4.3557 max mem: 9353 +Train: [88] [ 100/6250] eta: 0:22:00 lr: 0.000005 grad: 0.1862 (0.2097) loss: 0.8130 (0.8186) time: 0.1569 data: 0.0638 max mem: 9390 +Train: [88] [ 200/6250] eta: 0:19:10 lr: 0.000005 grad: 0.1545 (0.1920) loss: 0.8136 (0.8152) time: 0.1445 data: 0.0453 max mem: 9390 +Train: [88] [ 300/6250] eta: 0:18:18 lr: 0.000005 grad: 0.1575 (0.1844) loss: 0.8215 (0.8141) time: 0.1521 data: 0.0468 max mem: 9390 +Train: [88] [ 400/6250] eta: 0:17:36 lr: 0.000005 grad: 0.1441 (0.1773) loss: 0.8129 (0.8133) time: 0.1395 data: 0.0301 max mem: 9390 +Train: [88] [ 500/6250] eta: 0:16:57 lr: 0.000005 grad: 0.1383 (0.1717) loss: 0.8045 (0.8123) time: 0.1602 data: 0.0614 max mem: 9390 +Train: [88] [ 600/6250] eta: 0:16:32 lr: 0.000005 grad: 0.1290 (0.1669) loss: 0.8102 (0.8118) time: 0.1540 data: 0.0429 max mem: 9390 +Train: [88] [ 700/6250] eta: 0:16:08 lr: 0.000005 grad: 0.1403 (0.1630) loss: 0.8073 (0.8118) time: 0.1771 data: 0.0792 max mem: 9390 +Train: [88] [ 800/6250] eta: 0:15:42 lr: 0.000005 grad: 0.1273 (0.1603) loss: 0.8096 (0.8116) time: 0.1771 data: 0.0853 max mem: 9390 +Train: [88] [ 900/6250] eta: 0:15:20 lr: 0.000005 grad: 0.1356 (0.1580) loss: 0.8085 (0.8117) time: 0.1666 data: 0.0637 max mem: 9390 +Train: [88] [1000/6250] eta: 0:14:54 lr: 0.000005 grad: 0.1324 (0.1556) loss: 0.8152 (0.8120) time: 0.1349 data: 0.0396 max mem: 9390 +Train: [88] [1100/6250] eta: 0:14:30 lr: 0.000005 grad: 0.1258 (0.1537) loss: 0.8151 (0.8122) time: 0.1422 data: 0.0554 max mem: 9390 +Train: [88] [1200/6250] eta: 0:14:05 lr: 0.000005 grad: 0.1239 (0.1521) loss: 0.8186 (0.8123) time: 0.1567 data: 0.0679 max mem: 9390 +Train: [88] [1300/6250] eta: 0:13:45 lr: 0.000005 grad: 0.1301 (0.1508) loss: 0.8114 (0.8125) time: 0.1491 data: 0.0557 max mem: 9390 +Train: [88] [1400/6250] eta: 0:13:26 lr: 0.000005 grad: 0.1405 (0.1499) loss: 0.8112 (0.8126) time: 0.1582 data: 0.0693 max mem: 9390 +Train: [88] [1500/6250] eta: 0:13:06 lr: 0.000005 grad: 0.1332 (0.1491) loss: 0.8187 (0.8128) time: 0.1544 data: 0.0581 max mem: 9390 +Train: [88] [1600/6250] eta: 0:12:48 lr: 0.000005 grad: 0.1363 (0.1484) loss: 0.8136 (0.8127) time: 0.1715 data: 0.0786 max mem: 9390 +Train: [88] [1700/6250] eta: 0:12:28 lr: 0.000005 grad: 0.1410 (0.1478) loss: 0.8065 (0.8127) time: 0.1449 data: 0.0579 max mem: 9390 +Train: [88] [1800/6250] eta: 0:12:10 lr: 0.000005 grad: 0.1335 (0.1471) loss: 0.8124 (0.8128) time: 0.1741 data: 0.0895 max mem: 9390 +Train: [88] [1900/6250] eta: 0:11:50 lr: 0.000005 grad: 0.1352 (0.1467) loss: 0.8143 (0.8128) time: 0.1643 data: 0.0767 max mem: 9390 +Train: [88] [2000/6250] eta: 0:11:31 lr: 0.000005 grad: 0.1345 (0.1464) loss: 0.8121 (0.8129) time: 0.1495 data: 0.0584 max mem: 9390 +Train: [88] [2100/6250] eta: 0:11:12 lr: 0.000005 grad: 0.1428 (0.1460) loss: 0.8100 (0.8129) time: 0.1582 data: 0.0697 max mem: 9390 +Train: [88] [2200/6250] eta: 0:10:55 lr: 0.000005 grad: 0.1343 (0.1458) loss: 0.8109 (0.8129) time: 0.1431 data: 0.0552 max mem: 9390 +Train: [88] [2300/6250] eta: 0:10:37 lr: 0.000005 grad: 0.1323 (0.1455) loss: 0.8145 (0.8130) time: 0.1668 data: 0.0785 max mem: 9390 +Train: [88] [2400/6250] eta: 0:10:19 lr: 0.000005 grad: 0.1331 (0.1453) loss: 0.8110 (0.8129) time: 0.1477 data: 0.0564 max mem: 9390 +Train: [88] [2500/6250] eta: 0:10:02 lr: 0.000005 grad: 0.1306 (0.1450) loss: 0.8123 (0.8129) time: 0.1588 data: 0.0694 max mem: 9390 +Train: [88] [2600/6250] eta: 0:09:46 lr: 0.000005 grad: 0.1407 (0.1449) loss: 0.8101 (0.8129) time: 0.1702 data: 0.0964 max mem: 9390 +Train: [88] [2700/6250] eta: 0:09:29 lr: 0.000005 grad: 0.1292 (0.1446) loss: 0.8188 (0.8130) time: 0.1511 data: 0.0669 max mem: 9390 +Train: [88] [2800/6250] eta: 0:09:12 lr: 0.000005 grad: 0.1317 (0.1444) loss: 0.8107 (0.8130) time: 0.1295 data: 0.0354 max mem: 9390 +Train: [88] [2900/6250] eta: 0:08:56 lr: 0.000004 grad: 0.1358 (0.1441) loss: 0.8176 (0.8131) time: 0.1408 data: 0.0500 max mem: 9390 +Train: [88] [3000/6250] eta: 0:08:39 lr: 0.000004 grad: 0.1418 (0.1440) loss: 0.8085 (0.8132) time: 0.1556 data: 0.0663 max mem: 9390 +Train: [88] [3100/6250] eta: 0:08:23 lr: 0.000004 grad: 0.1271 (0.1440) loss: 0.8123 (0.8132) time: 0.1528 data: 0.0717 max mem: 9390 +Train: [88] [3200/6250] eta: 0:08:06 lr: 0.000004 grad: 0.1265 (0.1438) loss: 0.8114 (0.8132) time: 0.1332 data: 0.0420 max mem: 9390 +Train: [88] [3300/6250] eta: 0:07:50 lr: 0.000004 grad: 0.1342 (0.1437) loss: 0.8118 (0.8132) time: 0.1383 data: 0.0489 max mem: 9390 +Train: [88] [3400/6250] eta: 0:07:34 lr: 0.000004 grad: 0.1358 (0.1435) loss: 0.8099 (0.8131) time: 0.1620 data: 0.0756 max mem: 9390 +Train: [88] [3500/6250] eta: 0:07:17 lr: 0.000004 grad: 0.1284 (0.1433) loss: 0.8116 (0.8131) time: 0.1531 data: 0.0728 max mem: 9390 +Train: [88] [3600/6250] eta: 0:07:01 lr: 0.000004 grad: 0.1303 (0.1431) loss: 0.8091 (0.8131) time: 0.1429 data: 0.0540 max mem: 9390 +Train: [88] [3700/6250] eta: 0:06:45 lr: 0.000004 grad: 0.1308 (0.1429) loss: 0.8161 (0.8131) time: 0.1328 data: 0.0473 max mem: 9390 +Train: [88] [3800/6250] eta: 0:06:29 lr: 0.000004 grad: 0.1316 (0.1427) loss: 0.8144 (0.8131) time: 0.1529 data: 0.0705 max mem: 9390 +Train: [88] [3900/6250] eta: 0:06:14 lr: 0.000004 grad: 0.1320 (0.1425) loss: 0.8139 (0.8130) time: 0.1521 data: 0.0634 max mem: 9390 +Train: [88] [4000/6250] eta: 0:05:58 lr: 0.000004 grad: 0.1268 (0.1422) loss: 0.8115 (0.8131) time: 0.1563 data: 0.0773 max mem: 9390 +Train: [88] [4100/6250] eta: 0:05:42 lr: 0.000004 grad: 0.1324 (0.1420) loss: 0.8168 (0.8131) time: 0.1522 data: 0.0715 max mem: 9390 +Train: [88] [4200/6250] eta: 0:05:26 lr: 0.000004 grad: 0.1332 (0.1418) loss: 0.8151 (0.8132) time: 0.1491 data: 0.0609 max mem: 9390 +Train: [88] [4300/6250] eta: 0:05:10 lr: 0.000004 grad: 0.1374 (0.1416) loss: 0.8141 (0.8133) time: 0.1664 data: 0.0808 max mem: 9390 +Train: [88] [4400/6250] eta: 0:04:54 lr: 0.000004 grad: 0.1373 (0.1415) loss: 0.8138 (0.8133) time: 0.1646 data: 0.0854 max mem: 9390 +Train: [88] [4500/6250] eta: 0:04:38 lr: 0.000004 grad: 0.1356 (0.1415) loss: 0.8145 (0.8133) time: 0.1727 data: 0.0902 max mem: 9390 +Train: [88] [4600/6250] eta: 0:04:22 lr: 0.000004 grad: 0.1356 (0.1414) loss: 0.8133 (0.8133) time: 0.1588 data: 0.0676 max mem: 9390 +Train: [88] [4700/6250] eta: 0:04:06 lr: 0.000004 grad: 0.1361 (0.1414) loss: 0.8120 (0.8133) time: 0.1511 data: 0.0666 max mem: 9390 +Train: [88] [4800/6250] eta: 0:03:50 lr: 0.000004 grad: 0.1318 (0.1413) loss: 0.8156 (0.8133) time: 0.1646 data: 0.0702 max mem: 9390 +Train: [88] [4900/6250] eta: 0:03:35 lr: 0.000004 grad: 0.1394 (0.1413) loss: 0.8137 (0.8132) time: 0.1639 data: 0.0810 max mem: 9390 +Train: [88] [5000/6250] eta: 0:03:19 lr: 0.000004 grad: 0.1342 (0.1413) loss: 0.8179 (0.8132) time: 0.1593 data: 0.0669 max mem: 9390 +Train: [88] [5100/6250] eta: 0:03:03 lr: 0.000004 grad: 0.1330 (0.1413) loss: 0.8095 (0.8132) time: 0.1683 data: 0.0788 max mem: 9390 +Train: [88] [5200/6250] eta: 0:02:47 lr: 0.000004 grad: 0.1314 (0.1413) loss: 0.8136 (0.8132) time: 0.1495 data: 0.0604 max mem: 9390 +Train: [88] [5300/6250] eta: 0:02:31 lr: 0.000004 grad: 0.1348 (0.1412) loss: 0.8160 (0.8132) time: 0.1605 data: 0.0756 max mem: 9390 +Train: [88] [5400/6250] eta: 0:02:15 lr: 0.000004 grad: 0.1300 (0.1411) loss: 0.8132 (0.8132) time: 0.1736 data: 0.0844 max mem: 9390 +Train: [88] [5500/6250] eta: 0:01:59 lr: 0.000004 grad: 0.1321 (0.1411) loss: 0.8109 (0.8132) time: 0.1562 data: 0.0720 max mem: 9390 +Train: [88] [5600/6250] eta: 0:01:43 lr: 0.000004 grad: 0.1409 (0.1411) loss: 0.8161 (0.8132) time: 0.1698 data: 0.0839 max mem: 9390 +Train: [88] [5700/6250] eta: 0:01:27 lr: 0.000004 grad: 0.1492 (0.1411) loss: 0.8134 (0.8132) time: 0.1461 data: 0.0612 max mem: 9390 +Train: [88] [5800/6250] eta: 0:01:11 lr: 0.000004 grad: 0.1464 (0.1411) loss: 0.8171 (0.8131) time: 0.1648 data: 0.0767 max mem: 9390 +Train: [88] [5900/6250] eta: 0:00:55 lr: 0.000004 grad: 0.1375 (0.1411) loss: 0.8064 (0.8131) time: 0.1444 data: 0.0552 max mem: 9390 +Train: [88] [6000/6250] eta: 0:00:39 lr: 0.000004 grad: 0.1340 (0.1410) loss: 0.8159 (0.8131) time: 0.1598 data: 0.0748 max mem: 9390 +Train: [88] [6100/6250] eta: 0:00:23 lr: 0.000004 grad: 0.1355 (0.1410) loss: 0.8109 (0.8131) time: 0.1525 data: 0.0656 max mem: 9390 +Train: [88] [6200/6250] eta: 0:00:07 lr: 0.000004 grad: 0.1348 (0.1409) loss: 0.8157 (0.8132) time: 0.1441 data: 0.0528 max mem: 9390 +Train: [88] [6249/6250] eta: 0:00:00 lr: 0.000004 grad: 0.1287 (0.1409) loss: 0.8109 (0.8131) time: 0.1603 data: 0.0779 max mem: 9390 +Train: [88] Total time: 0:16:38 (0.1597 s / it) +Averaged stats: lr: 0.000004 grad: 0.1287 (0.1409) loss: 0.8109 (0.8131) +Eval (hcp-train-subset): [88] [ 0/62] eta: 0:05:18 loss: 0.8257 (0.8257) time: 5.1444 data: 5.1147 max mem: 9390 +Eval (hcp-train-subset): [88] [61/62] eta: 0:00:00 loss: 0.8160 (0.8188) time: 0.1120 data: 0.0821 max mem: 9390 +Eval (hcp-train-subset): [88] Total time: 0:00:12 (0.2071 s / it) +Averaged stats (hcp-train-subset): loss: 0.8160 (0.8188) +Eval (hcp-val): [88] [ 0/62] eta: 0:05:28 loss: 0.8228 (0.8228) time: 5.2909 data: 5.2619 max mem: 9390 +Eval (hcp-val): [88] [61/62] eta: 0:00:00 loss: 0.8266 (0.8285) time: 0.1007 data: 0.0683 max mem: 9390 +Eval (hcp-val): [88] Total time: 0:00:12 (0.2085 s / it) +Averaged stats (hcp-val): loss: 0.8266 (0.8285) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +Train: [89] [ 0/6250] eta: 8:06:25 lr: 0.000004 grad: 0.2069 (0.2069) loss: 0.8091 (0.8091) time: 4.6697 data: 4.5319 max mem: 9390 +Train: [89] [ 100/6250] eta: 0:20:05 lr: 0.000004 grad: 0.1378 (0.1535) loss: 0.8327 (0.8209) time: 0.1311 data: 0.0455 max mem: 9390 +Train: [89] [ 200/6250] eta: 0:18:12 lr: 0.000004 grad: 0.1725 (0.1583) loss: 0.8186 (0.8200) time: 0.1714 data: 0.0755 max mem: 9390 +Train: [89] [ 300/6250] eta: 0:17:22 lr: 0.000004 grad: 0.1584 (0.1602) loss: 0.8000 (0.8180) time: 0.1865 data: 0.0946 max mem: 9390 +Train: [89] [ 400/6250] eta: 0:16:51 lr: 0.000004 grad: 0.1461 (0.1593) loss: 0.8130 (0.8163) time: 0.1851 data: 0.0864 max mem: 9390 +Train: [89] [ 500/6250] eta: 0:16:22 lr: 0.000004 grad: 0.1441 (0.1574) loss: 0.8130 (0.8149) time: 0.1659 data: 0.0693 max mem: 9390 +Train: [89] [ 600/6250] eta: 0:15:52 lr: 0.000004 grad: 0.1478 (0.1568) loss: 0.8104 (0.8137) time: 0.1384 data: 0.0404 max mem: 9390 +Train: [89] [ 700/6250] eta: 0:15:31 lr: 0.000004 grad: 0.1468 (0.1559) loss: 0.8072 (0.8132) time: 0.1660 data: 0.0724 max mem: 9390 +Train: [89] [ 800/6250] eta: 0:15:12 lr: 0.000004 grad: 0.1372 (0.1543) loss: 0.8129 (0.8131) time: 0.1660 data: 0.0757 max mem: 9390 +Train: [89] [ 900/6250] eta: 0:14:59 lr: 0.000004 grad: 0.1389 (0.1536) loss: 0.8149 (0.8131) time: 0.1521 data: 0.0624 max mem: 9390 +Train: [89] [1000/6250] eta: 0:14:39 lr: 0.000004 grad: 0.1372 (0.1529) loss: 0.8147 (0.8129) time: 0.1628 data: 0.0673 max mem: 9390 +Train: [89] [1100/6250] eta: 0:14:22 lr: 0.000004 grad: 0.1317 (0.1520) loss: 0.8085 (0.8128) time: 0.1731 data: 0.0915 max mem: 9390 +Train: [89] [1200/6250] eta: 0:14:06 lr: 0.000004 grad: 0.1488 (0.1512) loss: 0.8053 (0.8126) time: 0.1782 data: 0.0917 max mem: 9390 +Train: [89] [1300/6250] eta: 0:13:48 lr: 0.000004 grad: 0.1368 (0.1503) loss: 0.8036 (0.8125) time: 0.1729 data: 0.0830 max mem: 9390 +Train: [89] [1400/6250] eta: 0:13:29 lr: 0.000004 grad: 0.1300 (0.1496) loss: 0.8132 (0.8124) time: 0.1646 data: 0.0768 max mem: 9390 +Train: [89] [1500/6250] eta: 0:13:09 lr: 0.000004 grad: 0.1395 (0.1490) loss: 0.8112 (0.8123) time: 0.2065 data: 0.1262 max mem: 9390 +Train: [89] [1600/6250] eta: 0:12:49 lr: 0.000004 grad: 0.1404 (0.1486) loss: 0.8098 (0.8122) time: 0.1380 data: 0.0469 max mem: 9390 +Train: [89] [1700/6250] eta: 0:12:32 lr: 0.000004 grad: 0.1467 (0.1482) loss: 0.8127 (0.8122) time: 0.1782 data: 0.0979 max mem: 9390 +Train: [89] [1800/6250] eta: 0:12:14 lr: 0.000004 grad: 0.1458 (0.1481) loss: 0.8095 (0.8120) time: 0.1348 data: 0.0340 max mem: 9390 +Train: [89] [1900/6250] eta: 0:11:56 lr: 0.000004 grad: 0.1320 (0.1479) loss: 0.8150 (0.8119) time: 0.1573 data: 0.0718 max mem: 9390 +Train: [89] [2000/6250] eta: 0:11:38 lr: 0.000004 grad: 0.1355 (0.1477) loss: 0.8143 (0.8118) time: 0.1520 data: 0.0652 max mem: 9390 +Train: [89] [2100/6250] eta: 0:11:22 lr: 0.000004 grad: 0.1317 (0.1474) loss: 0.8123 (0.8117) time: 0.1612 data: 0.0702 max mem: 9390 +Train: [89] [2200/6250] eta: 0:11:05 lr: 0.000004 grad: 0.1272 (0.1470) loss: 0.8129 (0.8118) time: 0.1594 data: 0.0745 max mem: 9390 +Train: [89] [2300/6250] eta: 0:10:49 lr: 0.000004 grad: 0.1410 (0.1466) loss: 0.8098 (0.8118) time: 0.1670 data: 0.0783 max mem: 9390 +Train: [89] [2400/6250] eta: 0:10:32 lr: 0.000004 grad: 0.1403 (0.1465) loss: 0.8179 (0.8117) time: 0.1658 data: 0.0719 max mem: 9390 +Train: [89] [2500/6250] eta: 0:10:14 lr: 0.000004 grad: 0.1417 (0.1465) loss: 0.8130 (0.8116) time: 0.1356 data: 0.0477 max mem: 9390 +Train: [89] [2600/6250] eta: 0:09:58 lr: 0.000004 grad: 0.1467 (0.1464) loss: 0.8092 (0.8115) time: 0.1397 data: 0.0506 max mem: 9390 +Train: [89] [2700/6250] eta: 0:09:41 lr: 0.000004 grad: 0.1505 (0.1463) loss: 0.8017 (0.8114) time: 0.1595 data: 0.0746 max mem: 9390 +Train: [89] [2800/6250] eta: 0:09:25 lr: 0.000004 grad: 0.1362 (0.1462) loss: 0.8100 (0.8112) time: 0.1655 data: 0.0735 max mem: 9390 +Train: [89] [2900/6250] eta: 0:09:09 lr: 0.000004 grad: 0.1485 (0.1461) loss: 0.8038 (0.8111) time: 0.1505 data: 0.0585 max mem: 9390 +Train: [89] [3000/6250] eta: 0:08:52 lr: 0.000004 grad: 0.1392 (0.1459) loss: 0.8109 (0.8110) time: 0.1344 data: 0.0433 max mem: 9390 +Train: [89] [3100/6250] eta: 0:08:36 lr: 0.000004 grad: 0.1384 (0.1457) loss: 0.8076 (0.8109) time: 0.1643 data: 0.0743 max mem: 9390 +Train: [89] [3200/6250] eta: 0:08:19 lr: 0.000004 grad: 0.1385 (0.1456) loss: 0.8078 (0.8108) time: 0.1631 data: 0.0816 max mem: 9390 +Train: [89] [3300/6250] eta: 0:08:03 lr: 0.000004 grad: 0.1435 (0.1456) loss: 0.8069 (0.8107) time: 0.1782 data: 0.0959 max mem: 9390 +Train: [89] [3400/6250] eta: 0:07:46 lr: 0.000004 grad: 0.1328 (0.1454) loss: 0.8104 (0.8107) time: 0.1686 data: 0.0848 max mem: 9390 +Train: [89] [3500/6250] eta: 0:07:29 lr: 0.000004 grad: 0.1480 (0.1454) loss: 0.8084 (0.8106) time: 0.1588 data: 0.0782 max mem: 9390 +Train: [89] [3600/6250] eta: 0:07:13 lr: 0.000004 grad: 0.1334 (0.1453) loss: 0.8161 (0.8106) time: 0.1799 data: 0.0944 max mem: 9390 +Train: [89] [3700/6250] eta: 0:06:57 lr: 0.000004 grad: 0.1336 (0.1451) loss: 0.8149 (0.8106) time: 0.1596 data: 0.0712 max mem: 9390 +Train: [89] [3800/6250] eta: 0:06:40 lr: 0.000004 grad: 0.1366 (0.1451) loss: 0.8065 (0.8105) time: 0.1724 data: 0.0859 max mem: 9390 +Train: [89] [3900/6250] eta: 0:06:24 lr: 0.000004 grad: 0.1465 (0.1451) loss: 0.8102 (0.8105) time: 0.1782 data: 0.0900 max mem: 9390 +Train: [89] [4000/6250] eta: 0:06:08 lr: 0.000004 grad: 0.1407 (0.1450) loss: 0.8001 (0.8104) time: 0.1625 data: 0.0798 max mem: 9390 +Train: [89] [4100/6250] eta: 0:05:51 lr: 0.000004 grad: 0.1343 (0.1449) loss: 0.8042 (0.8104) time: 0.1702 data: 0.0835 max mem: 9390 +Train: [89] [4200/6250] eta: 0:05:35 lr: 0.000004 grad: 0.1352 (0.1448) loss: 0.8104 (0.8104) time: 0.1579 data: 0.0727 max mem: 9390 +Train: [89] [4300/6250] eta: 0:05:19 lr: 0.000004 grad: 0.1461 (0.1447) loss: 0.8095 (0.8104) time: 0.1757 data: 0.0925 max mem: 9390 +Train: [89] [4400/6250] eta: 0:05:03 lr: 0.000004 grad: 0.1358 (0.1448) loss: 0.8179 (0.8104) time: 0.1465 data: 0.0578 max mem: 9390 +Train: [89] [4500/6250] eta: 0:04:46 lr: 0.000004 grad: 0.1397 (0.1447) loss: 0.8086 (0.8104) time: 0.1505 data: 0.0661 max mem: 9390 +Train: [89] [4600/6250] eta: 0:04:30 lr: 0.000004 grad: 0.1404 (0.1448) loss: 0.8126 (0.8104) time: 0.1490 data: 0.0666 max mem: 9390 +Train: [89] [4700/6250] eta: 0:04:14 lr: 0.000004 grad: 0.1408 (0.1446) loss: 0.8059 (0.8105) time: 0.2248 data: 0.1445 max mem: 9390 +Train: [89] [4800/6250] eta: 0:03:57 lr: 0.000004 grad: 0.1294 (0.1446) loss: 0.8137 (0.8105) time: 0.1333 data: 0.0431 max mem: 9390 +Train: [89] [4900/6250] eta: 0:03:40 lr: 0.000004 grad: 0.1370 (0.1445) loss: 0.8154 (0.8106) time: 0.1438 data: 0.0618 max mem: 9390 +Train: [89] [5000/6250] eta: 0:03:24 lr: 0.000004 grad: 0.1289 (0.1444) loss: 0.8194 (0.8107) time: 0.1733 data: 0.0861 max mem: 9390 +Train: [89] [5100/6250] eta: 0:03:08 lr: 0.000004 grad: 0.1366 (0.1442) loss: 0.8200 (0.8108) time: 0.1494 data: 0.0643 max mem: 9390 +Train: [89] [5200/6250] eta: 0:02:51 lr: 0.000003 grad: 0.1285 (0.1440) loss: 0.8167 (0.8109) time: 0.1258 data: 0.0463 max mem: 9390 +Train: [89] [5300/6250] eta: 0:02:34 lr: 0.000003 grad: 0.1307 (0.1438) loss: 0.8132 (0.8111) time: 0.1456 data: 0.0609 max mem: 9390 +Train: [89] [5400/6250] eta: 0:02:18 lr: 0.000003 grad: 0.1273 (0.1436) loss: 0.8208 (0.8112) time: 0.1671 data: 0.0672 max mem: 9390 +Train: [89] [5500/6250] eta: 0:02:02 lr: 0.000003 grad: 0.1250 (0.1434) loss: 0.8128 (0.8113) time: 0.1688 data: 0.0772 max mem: 9390 +Train: [89] [5600/6250] eta: 0:01:45 lr: 0.000003 grad: 0.1376 (0.1433) loss: 0.8088 (0.8113) time: 0.1569 data: 0.0681 max mem: 9390 +Train: [89] [5700/6250] eta: 0:01:29 lr: 0.000003 grad: 0.1322 (0.1432) loss: 0.8146 (0.8114) time: 0.1542 data: 0.0591 max mem: 9390 +Train: [89] [5800/6250] eta: 0:01:13 lr: 0.000003 grad: 0.1321 (0.1430) loss: 0.8162 (0.8115) time: 0.1618 data: 0.0726 max mem: 9390 +Train: [89] [5900/6250] eta: 0:00:56 lr: 0.000003 grad: 0.1315 (0.1429) loss: 0.8167 (0.8115) time: 0.1415 data: 0.0380 max mem: 9390 +Train: [89] [6000/6250] eta: 0:00:40 lr: 0.000003 grad: 0.1341 (0.1428) loss: 0.8099 (0.8116) time: 0.1418 data: 0.0496 max mem: 9390 +Train: [89] [6100/6250] eta: 0:00:24 lr: 0.000003 grad: 0.1299 (0.1426) loss: 0.8072 (0.8116) time: 0.1391 data: 0.0304 max mem: 9390 +Train: [89] [6200/6250] eta: 0:00:08 lr: 0.000003 grad: 0.1410 (0.1426) loss: 0.8080 (0.8116) time: 0.1522 data: 0.0575 max mem: 9390 +Train: [89] [6249/6250] eta: 0:00:00 lr: 0.000003 grad: 0.1357 (0.1426) loss: 0.8137 (0.8116) time: 0.1304 data: 0.0388 max mem: 9390 +Train: [89] Total time: 0:16:59 (0.1630 s / it) +Averaged stats: lr: 0.000003 grad: 0.1357 (0.1426) loss: 0.8137 (0.8116) +Eval (hcp-train-subset): [89] [ 0/62] eta: 0:05:32 loss: 0.8240 (0.8240) time: 5.3631 data: 5.3338 max mem: 9390 +Eval (hcp-train-subset): [89] [61/62] eta: 0:00:00 loss: 0.8170 (0.8185) time: 0.1290 data: 0.1022 max mem: 9390 +Eval (hcp-train-subset): [89] Total time: 0:00:13 (0.2202 s / it) +Averaged stats (hcp-train-subset): loss: 0.8170 (0.8185) +Making plots (hcp-train-subset): example=47 +Eval (hcp-val): [89] [ 0/62] eta: 0:05:37 loss: 0.8258 (0.8258) time: 5.4469 data: 5.4176 max mem: 9390 +Eval (hcp-val): [89] [61/62] eta: 0:00:00 loss: 0.8282 (0.8286) time: 0.1180 data: 0.0928 max mem: 9390 +Eval (hcp-val): [89] Total time: 0:00:14 (0.2311 s / it) +Averaged stats (hcp-val): loss: 0.8282 (0.8286) +Making plots (hcp-val): example=35 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +Train: [90] [ 0/6250] eta: 6:49:37 lr: 0.000003 grad: 0.2320 (0.2320) loss: 0.8005 (0.8005) time: 3.9323 data: 3.6664 max mem: 9390 +Train: [90] [ 100/6250] eta: 0:21:45 lr: 0.000003 grad: 0.1464 (0.1952) loss: 0.8159 (0.8041) time: 0.1937 data: 0.1008 max mem: 9390 +Train: [90] [ 200/6250] eta: 0:19:14 lr: 0.000003 grad: 0.1396 (0.1804) loss: 0.8092 (0.8039) time: 0.1652 data: 0.0669 max mem: 9390 +Train: [90] [ 300/6250] eta: 0:18:09 lr: 0.000003 grad: 0.1440 (0.1712) loss: 0.8147 (0.8050) time: 0.1752 data: 0.0722 max mem: 9390 +Train: [90] [ 400/6250] eta: 0:17:30 lr: 0.000003 grad: 0.1483 (0.1648) loss: 0.8126 (0.8063) time: 0.1642 data: 0.0733 max mem: 9390 +Train: [90] [ 500/6250] eta: 0:17:04 lr: 0.000003 grad: 0.1431 (0.1631) loss: 0.8093 (0.8063) time: 0.1792 data: 0.0950 max mem: 9390 +Train: [90] [ 600/6250] eta: 0:16:24 lr: 0.000003 grad: 0.1329 (0.1603) loss: 0.8155 (0.8071) time: 0.1385 data: 0.0460 max mem: 9390 +Train: [90] [ 700/6250] eta: 0:15:59 lr: 0.000003 grad: 0.1354 (0.1576) loss: 0.8195 (0.8081) time: 0.1819 data: 0.0891 max mem: 9390 +Train: [90] [ 800/6250] eta: 0:15:37 lr: 0.000003 grad: 0.1480 (0.1552) loss: 0.8142 (0.8091) time: 0.1631 data: 0.0724 max mem: 9390 +Train: [90] [ 900/6250] eta: 0:15:20 lr: 0.000003 grad: 0.1427 (0.1541) loss: 0.8174 (0.8099) time: 0.1690 data: 0.0772 max mem: 9390 +Train: [90] [1000/6250] eta: 0:14:53 lr: 0.000003 grad: 0.1385 (0.1533) loss: 0.8117 (0.8104) time: 0.1464 data: 0.0553 max mem: 9390 +Train: [90] [1100/6250] eta: 0:14:30 lr: 0.000003 grad: 0.1398 (0.1525) loss: 0.8074 (0.8106) time: 0.1738 data: 0.0882 max mem: 9390 +Train: [90] [1200/6250] eta: 0:14:09 lr: 0.000003 grad: 0.1293 (0.1515) loss: 0.8148 (0.8106) time: 0.1658 data: 0.0756 max mem: 9390 +Train: [90] [1300/6250] eta: 0:13:48 lr: 0.000003 grad: 0.1303 (0.1503) loss: 0.8201 (0.8109) time: 0.1646 data: 0.0643 max mem: 9390 +Train: [90] [1400/6250] eta: 0:13:30 lr: 0.000003 grad: 0.1339 (0.1494) loss: 0.8170 (0.8112) time: 0.1580 data: 0.0684 max mem: 9390 +Train: [90] [1500/6250] eta: 0:13:11 lr: 0.000003 grad: 0.1389 (0.1489) loss: 0.8119 (0.8113) time: 0.1626 data: 0.0693 max mem: 9390 +Train: [90] [1600/6250] eta: 0:12:53 lr: 0.000003 grad: 0.1355 (0.1486) loss: 0.8171 (0.8115) time: 0.1686 data: 0.0771 max mem: 9390 +Train: [90] [1700/6250] eta: 0:12:36 lr: 0.000003 grad: 0.1326 (0.1479) loss: 0.8150 (0.8117) time: 0.1689 data: 0.0731 max mem: 9390 +Train: [90] [1800/6250] eta: 0:12:18 lr: 0.000003 grad: 0.1450 (0.1477) loss: 0.8100 (0.8118) time: 0.1719 data: 0.0867 max mem: 9390 +Train: [90] [1900/6250] eta: 0:12:00 lr: 0.000003 grad: 0.1387 (0.1475) loss: 0.8163 (0.8120) time: 0.1674 data: 0.0713 max mem: 9390 +Train: [90] [2000/6250] eta: 0:11:43 lr: 0.000003 grad: 0.1354 (0.1470) loss: 0.8187 (0.8122) time: 0.1546 data: 0.0628 max mem: 9390 +Train: [90] [2100/6250] eta: 0:11:26 lr: 0.000003 grad: 0.1405 (0.1467) loss: 0.8130 (0.8123) time: 0.1581 data: 0.0630 max mem: 9390 +Train: [90] [2200/6250] eta: 0:11:09 lr: 0.000003 grad: 0.1335 (0.1463) loss: 0.8150 (0.8124) time: 0.1585 data: 0.0632 max mem: 9390 +Train: [90] [2300/6250] eta: 0:10:52 lr: 0.000003 grad: 0.1387 (0.1457) loss: 0.8165 (0.8126) time: 0.1455 data: 0.0596 max mem: 9390 +Train: [90] [2400/6250] eta: 0:10:36 lr: 0.000003 grad: 0.1359 (0.1454) loss: 0.8145 (0.8127) time: 0.2021 data: 0.1089 max mem: 9390 +Train: [90] [2500/6250] eta: 0:10:18 lr: 0.000003 grad: 0.1455 (0.1451) loss: 0.8095 (0.8128) time: 0.1556 data: 0.0728 max mem: 9390 +Train: [90] [2600/6250] eta: 0:10:01 lr: 0.000003 grad: 0.1449 (0.1451) loss: 0.8102 (0.8127) time: 0.1534 data: 0.0557 max mem: 9390 +Train: [90] [2700/6250] eta: 0:09:44 lr: 0.000003 grad: 0.1383 (0.1450) loss: 0.8129 (0.8127) time: 0.1506 data: 0.0620 max mem: 9390 +Train: [90] [2800/6250] eta: 0:09:26 lr: 0.000003 grad: 0.1381 (0.1448) loss: 0.8120 (0.8127) time: 0.1477 data: 0.0495 max mem: 9390 +Train: [90] [2900/6250] eta: 0:09:10 lr: 0.000003 grad: 0.1376 (0.1446) loss: 0.8119 (0.8127) time: 0.1771 data: 0.0859 max mem: 9390 +Train: [90] [3000/6250] eta: 0:08:53 lr: 0.000003 grad: 0.1330 (0.1445) loss: 0.8186 (0.8127) time: 0.1527 data: 0.0617 max mem: 9390 +Train: [90] [3100/6250] eta: 0:08:37 lr: 0.000003 grad: 0.1333 (0.1443) loss: 0.8180 (0.8128) time: 0.1707 data: 0.0785 max mem: 9390 +Train: [90] [3200/6250] eta: 0:08:20 lr: 0.000003 grad: 0.1311 (0.1441) loss: 0.8093 (0.8128) time: 0.1623 data: 0.0812 max mem: 9390 +Train: [90] [3300/6250] eta: 0:08:04 lr: 0.000003 grad: 0.1507 (0.1441) loss: 0.8081 (0.8128) time: 0.1683 data: 0.0783 max mem: 9390 +Train: [90] [3400/6250] eta: 0:07:47 lr: 0.000003 grad: 0.1320 (0.1440) loss: 0.8141 (0.8128) time: 0.1639 data: 0.0750 max mem: 9390 +Train: [90] [3500/6250] eta: 0:07:31 lr: 0.000003 grad: 0.1518 (0.1441) loss: 0.8030 (0.8127) time: 0.1832 data: 0.0938 max mem: 9390 +Train: [90] [3600/6250] eta: 0:07:14 lr: 0.000003 grad: 0.1375 (0.1442) loss: 0.8133 (0.8127) time: 0.1689 data: 0.0862 max mem: 9390 +Train: [90] [3700/6250] eta: 0:06:58 lr: 0.000003 grad: 0.1361 (0.1441) loss: 0.8085 (0.8126) time: 0.1764 data: 0.0927 max mem: 9390 +Train: [90] [3800/6250] eta: 0:06:41 lr: 0.000003 grad: 0.1376 (0.1441) loss: 0.8104 (0.8126) time: 0.1566 data: 0.0655 max mem: 9390 +Train: [90] [3900/6250] eta: 0:06:25 lr: 0.000003 grad: 0.1472 (0.1440) loss: 0.8145 (0.8125) time: 0.1700 data: 0.0804 max mem: 9390 +Train: [90] [4000/6250] eta: 0:06:08 lr: 0.000003 grad: 0.1302 (0.1438) loss: 0.8187 (0.8126) time: 0.1767 data: 0.0862 max mem: 9390 +Train: [90] [4100/6250] eta: 0:05:52 lr: 0.000003 grad: 0.1356 (0.1436) loss: 0.8137 (0.8126) time: 0.1733 data: 0.0914 max mem: 9390 +Train: [90] [4200/6250] eta: 0:05:35 lr: 0.000003 grad: 0.1355 (0.1435) loss: 0.8087 (0.8125) time: 0.1558 data: 0.0699 max mem: 9390 +Train: [90] [4300/6250] eta: 0:05:19 lr: 0.000003 grad: 0.1411 (0.1433) loss: 0.8085 (0.8126) time: 0.1345 data: 0.0455 max mem: 9390 +Train: [90] [4400/6250] eta: 0:05:02 lr: 0.000003 grad: 0.1271 (0.1432) loss: 0.8199 (0.8127) time: 0.1660 data: 0.0799 max mem: 9390 +Train: [90] [4500/6250] eta: 0:04:46 lr: 0.000003 grad: 0.1368 (0.1431) loss: 0.8136 (0.8127) time: 0.1672 data: 0.0859 max mem: 9390 +Train: [90] [4600/6250] eta: 0:04:29 lr: 0.000003 grad: 0.1265 (0.1429) loss: 0.8203 (0.8128) time: 0.1434 data: 0.0584 max mem: 9390 +Train: [90] [4700/6250] eta: 0:04:13 lr: 0.000003 grad: 0.1317 (0.1427) loss: 0.8172 (0.8128) time: 0.1603 data: 0.0716 max mem: 9390 +Train: [90] [4800/6250] eta: 0:03:56 lr: 0.000003 grad: 0.1291 (0.1425) loss: 0.8226 (0.8129) time: 0.1593 data: 0.0789 max mem: 9390 +Train: [90] [4900/6250] eta: 0:03:40 lr: 0.000003 grad: 0.1338 (0.1425) loss: 0.8092 (0.8129) time: 0.1538 data: 0.0640 max mem: 9390 +Train: [90] [5000/6250] eta: 0:03:23 lr: 0.000003 grad: 0.1335 (0.1425) loss: 0.8166 (0.8129) time: 0.1600 data: 0.0674 max mem: 9390 +Train: [90] [5100/6250] eta: 0:03:07 lr: 0.000003 grad: 0.1409 (0.1424) loss: 0.8079 (0.8129) time: 0.1523 data: 0.0565 max mem: 9390 +Train: [90] [5200/6250] eta: 0:02:51 lr: 0.000003 grad: 0.1404 (0.1424) loss: 0.8178 (0.8129) time: 0.1639 data: 0.0730 max mem: 9390 +Train: [90] [5300/6250] eta: 0:02:34 lr: 0.000003 grad: 0.1346 (0.1423) loss: 0.8151 (0.8129) time: 0.1618 data: 0.0772 max mem: 9390 +Train: [90] [5400/6250] eta: 0:02:18 lr: 0.000003 grad: 0.1359 (0.1423) loss: 0.8174 (0.8129) time: 0.1672 data: 0.0813 max mem: 9390 +Train: [90] [5500/6250] eta: 0:02:02 lr: 0.000003 grad: 0.1325 (0.1422) loss: 0.8094 (0.8129) time: 0.1731 data: 0.0953 max mem: 9390 +Train: [90] [5600/6250] eta: 0:01:46 lr: 0.000003 grad: 0.1382 (0.1422) loss: 0.8076 (0.8129) time: 0.1545 data: 0.0709 max mem: 9390 +Train: [90] [5700/6250] eta: 0:01:29 lr: 0.000003 grad: 0.1379 (0.1422) loss: 0.8161 (0.8128) time: 0.1925 data: 0.1030 max mem: 9390 +Train: [90] [5800/6250] eta: 0:01:13 lr: 0.000003 grad: 0.1366 (0.1422) loss: 0.8128 (0.8128) time: 0.1700 data: 0.0822 max mem: 9390 +Train: [90] [5900/6250] eta: 0:00:57 lr: 0.000003 grad: 0.1354 (0.1422) loss: 0.8127 (0.8128) time: 0.1702 data: 0.0850 max mem: 9390 +Train: [90] [6000/6250] eta: 0:00:40 lr: 0.000003 grad: 0.1337 (0.1421) loss: 0.8115 (0.8128) time: 0.1706 data: 0.0791 max mem: 9390 +Train: [90] [6100/6250] eta: 0:00:24 lr: 0.000003 grad: 0.1367 (0.1421) loss: 0.8202 (0.8128) time: 0.1731 data: 0.0912 max mem: 9390 +Train: [90] [6200/6250] eta: 0:00:08 lr: 0.000003 grad: 0.1351 (0.1420) loss: 0.8174 (0.8129) time: 0.1424 data: 0.0608 max mem: 9390 +Train: [90] [6249/6250] eta: 0:00:00 lr: 0.000003 grad: 0.1320 (0.1420) loss: 0.8160 (0.8129) time: 0.1672 data: 0.0736 max mem: 9390 +Train: [90] Total time: 0:17:04 (0.1639 s / it) +Averaged stats: lr: 0.000003 grad: 0.1320 (0.1420) loss: 0.8160 (0.8129) +Eval (hcp-train-subset): [90] [ 0/62] eta: 0:04:01 loss: 0.8257 (0.8257) time: 3.8923 data: 3.8301 max mem: 9390 +Eval (hcp-train-subset): [90] [61/62] eta: 0:00:00 loss: 0.8153 (0.8173) time: 0.1292 data: 0.1036 max mem: 9390 +Eval (hcp-train-subset): [90] Total time: 0:00:14 (0.2323 s / it) +Averaged stats (hcp-train-subset): loss: 0.8153 (0.8173) +Eval (hcp-val): [90] [ 0/62] eta: 0:03:23 loss: 0.8233 (0.8233) time: 3.2834 data: 3.2512 max mem: 9390 +Eval (hcp-val): [90] [61/62] eta: 0:00:00 loss: 0.8276 (0.8286) time: 0.1347 data: 0.1076 max mem: 9390 +Eval (hcp-val): [90] Total time: 0:00:14 (0.2274 s / it) +Averaged stats (hcp-val): loss: 0.8276 (0.8286) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +Train: [91] [ 0/6250] eta: 8:06:17 lr: 0.000003 grad: 0.1459 (0.1459) loss: 0.8495 (0.8495) time: 4.6683 data: 4.4203 max mem: 9390 +Train: [91] [ 100/6250] eta: 0:21:03 lr: 0.000003 grad: 0.1927 (0.1962) loss: 0.8126 (0.8149) time: 0.1335 data: 0.0490 max mem: 9390 +Train: [91] [ 200/6250] eta: 0:19:19 lr: 0.000003 grad: 0.1634 (0.1936) loss: 0.8059 (0.8105) time: 0.1965 data: 0.0986 max mem: 9390 +Train: [91] [ 300/6250] eta: 0:18:09 lr: 0.000003 grad: 0.1501 (0.1817) loss: 0.8152 (0.8119) time: 0.1710 data: 0.0786 max mem: 9390 +Train: [91] [ 400/6250] eta: 0:17:21 lr: 0.000003 grad: 0.1422 (0.1741) loss: 0.8152 (0.8130) time: 0.1598 data: 0.0603 max mem: 9390 +Train: [91] [ 500/6250] eta: 0:16:44 lr: 0.000003 grad: 0.1523 (0.1685) loss: 0.8150 (0.8139) time: 0.1447 data: 0.0510 max mem: 9390 +Train: [91] [ 600/6250] eta: 0:16:12 lr: 0.000003 grad: 0.1444 (0.1652) loss: 0.8174 (0.8143) time: 0.1682 data: 0.0712 max mem: 9390 +Train: [91] [ 700/6250] eta: 0:15:43 lr: 0.000003 grad: 0.1398 (0.1620) loss: 0.8187 (0.8149) time: 0.1487 data: 0.0440 max mem: 9390 +Train: [91] [ 800/6250] eta: 0:15:32 lr: 0.000003 grad: 0.1534 (0.1594) loss: 0.8141 (0.8154) time: 0.1705 data: 0.0789 max mem: 9390 +Train: [91] [ 900/6250] eta: 0:15:20 lr: 0.000003 grad: 0.1284 (0.1572) loss: 0.8203 (0.8156) time: 0.1868 data: 0.0933 max mem: 9390 +Train: [91] [1000/6250] eta: 0:14:58 lr: 0.000003 grad: 0.1320 (0.1556) loss: 0.8144 (0.8156) time: 0.1560 data: 0.0680 max mem: 9390 +Train: [91] [1100/6250] eta: 0:14:40 lr: 0.000003 grad: 0.1307 (0.1540) loss: 0.8177 (0.8158) time: 0.1902 data: 0.1004 max mem: 9390 +Train: [91] [1200/6250] eta: 0:14:20 lr: 0.000003 grad: 0.1438 (0.1531) loss: 0.8146 (0.8157) time: 0.1464 data: 0.0668 max mem: 9390 +Train: [91] [1300/6250] eta: 0:14:02 lr: 0.000003 grad: 0.1387 (0.1522) loss: 0.8148 (0.8156) time: 0.1818 data: 0.0989 max mem: 9390 +Train: [91] [1400/6250] eta: 0:13:46 lr: 0.000003 grad: 0.1324 (0.1514) loss: 0.8178 (0.8156) time: 0.1847 data: 0.0899 max mem: 9390 +Train: [91] [1500/6250] eta: 0:13:26 lr: 0.000003 grad: 0.1391 (0.1507) loss: 0.8159 (0.8155) time: 0.1528 data: 0.0663 max mem: 9390 +Train: [91] [1600/6250] eta: 0:13:08 lr: 0.000003 grad: 0.1309 (0.1499) loss: 0.8205 (0.8156) time: 0.1867 data: 0.1009 max mem: 9390 +Train: [91] [1700/6250] eta: 0:12:49 lr: 0.000003 grad: 0.1328 (0.1493) loss: 0.8204 (0.8155) time: 0.1663 data: 0.0755 max mem: 9390 +Train: [91] [1800/6250] eta: 0:12:31 lr: 0.000003 grad: 0.1447 (0.1490) loss: 0.8119 (0.8154) time: 0.1833 data: 0.0951 max mem: 9390 +Train: [91] [1900/6250] eta: 0:12:14 lr: 0.000003 grad: 0.1320 (0.1485) loss: 0.8145 (0.8153) time: 0.1923 data: 0.1065 max mem: 9390 +Train: [91] [2000/6250] eta: 0:11:57 lr: 0.000003 grad: 0.1332 (0.1480) loss: 0.8196 (0.8153) time: 0.1806 data: 0.0934 max mem: 9390 +Train: [91] [2100/6250] eta: 0:11:39 lr: 0.000003 grad: 0.1310 (0.1475) loss: 0.8151 (0.8151) time: 0.1624 data: 0.0732 max mem: 9390 +Train: [91] [2200/6250] eta: 0:11:21 lr: 0.000003 grad: 0.1414 (0.1470) loss: 0.8105 (0.8150) time: 0.1761 data: 0.0866 max mem: 9390 +Train: [91] [2300/6250] eta: 0:11:03 lr: 0.000003 grad: 0.1289 (0.1467) loss: 0.8134 (0.8149) time: 0.1659 data: 0.0809 max mem: 9390 +Train: [91] [2400/6250] eta: 0:10:45 lr: 0.000003 grad: 0.1380 (0.1465) loss: 0.8136 (0.8148) time: 0.1695 data: 0.0793 max mem: 9390 +Train: [91] [2500/6250] eta: 0:10:27 lr: 0.000003 grad: 0.1348 (0.1463) loss: 0.8137 (0.8148) time: 0.1571 data: 0.0684 max mem: 9390 +Train: [91] [2600/6250] eta: 0:10:10 lr: 0.000003 grad: 0.1418 (0.1460) loss: 0.8059 (0.8146) time: 0.1544 data: 0.0594 max mem: 9390 +Train: [91] [2700/6250] eta: 0:09:53 lr: 0.000002 grad: 0.1320 (0.1458) loss: 0.8133 (0.8146) time: 0.1787 data: 0.0854 max mem: 9390 +Train: [91] [2800/6250] eta: 0:09:36 lr: 0.000002 grad: 0.1353 (0.1456) loss: 0.8134 (0.8145) time: 0.1651 data: 0.0835 max mem: 9390 +Train: [91] [2900/6250] eta: 0:09:19 lr: 0.000002 grad: 0.1329 (0.1456) loss: 0.8163 (0.8145) time: 0.1469 data: 0.0584 max mem: 9390 +Train: [91] [3000/6250] eta: 0:09:02 lr: 0.000002 grad: 0.1474 (0.1455) loss: 0.8071 (0.8144) time: 0.1800 data: 0.0946 max mem: 9390 +Train: [91] [3100/6250] eta: 0:08:45 lr: 0.000002 grad: 0.1344 (0.1454) loss: 0.8130 (0.8144) time: 0.1736 data: 0.0863 max mem: 9390 +Train: [91] [3200/6250] eta: 0:08:28 lr: 0.000002 grad: 0.1358 (0.1453) loss: 0.8130 (0.8143) time: 0.1595 data: 0.0756 max mem: 9390 +Train: [91] [3300/6250] eta: 0:08:11 lr: 0.000002 grad: 0.1351 (0.1452) loss: 0.8127 (0.8143) time: 0.1770 data: 0.0935 max mem: 9390 +Train: [91] [3400/6250] eta: 0:07:54 lr: 0.000002 grad: 0.1338 (0.1451) loss: 0.8074 (0.8142) time: 0.1476 data: 0.0620 max mem: 9390 +Train: [91] [3500/6250] eta: 0:07:38 lr: 0.000002 grad: 0.1361 (0.1450) loss: 0.8111 (0.8141) time: 0.1886 data: 0.1082 max mem: 9390 +Train: [91] [3600/6250] eta: 0:07:22 lr: 0.000002 grad: 0.1346 (0.1450) loss: 0.8149 (0.8141) time: 0.2436 data: 0.1490 max mem: 9390 +Train: [91] [3700/6250] eta: 0:07:04 lr: 0.000002 grad: 0.1384 (0.1450) loss: 0.8087 (0.8139) time: 0.1598 data: 0.0794 max mem: 9390 +Train: [91] [3800/6250] eta: 0:06:49 lr: 0.000002 grad: 0.1347 (0.1450) loss: 0.8090 (0.8139) time: 0.1542 data: 0.0607 max mem: 9390 +Train: [91] [3900/6250] eta: 0:06:31 lr: 0.000002 grad: 0.1442 (0.1450) loss: 0.8134 (0.8138) time: 0.1400 data: 0.0590 max mem: 9390 +Train: [91] [4000/6250] eta: 0:06:14 lr: 0.000002 grad: 0.1414 (0.1451) loss: 0.8193 (0.8137) time: 0.1820 data: 0.0982 max mem: 9390 +Train: [91] [4100/6250] eta: 0:05:57 lr: 0.000002 grad: 0.1371 (0.1450) loss: 0.8119 (0.8137) time: 0.1944 data: 0.0945 max mem: 9390 +Train: [91] [4200/6250] eta: 0:05:41 lr: 0.000002 grad: 0.1436 (0.1450) loss: 0.8071 (0.8136) time: 0.1935 data: 0.1003 max mem: 9390 +Train: [91] [4300/6250] eta: 0:05:24 lr: 0.000002 grad: 0.1408 (0.1450) loss: 0.8118 (0.8135) time: 0.1597 data: 0.0688 max mem: 9390 +Train: [91] [4400/6250] eta: 0:05:06 lr: 0.000002 grad: 0.1363 (0.1449) loss: 0.8139 (0.8135) time: 0.1529 data: 0.0599 max mem: 9390 +Train: [91] [4500/6250] eta: 0:04:50 lr: 0.000002 grad: 0.1367 (0.1447) loss: 0.8182 (0.8135) time: 0.1462 data: 0.0591 max mem: 9390 +Train: [91] [4600/6250] eta: 0:04:32 lr: 0.000002 grad: 0.1362 (0.1447) loss: 0.8156 (0.8135) time: 0.1597 data: 0.0490 max mem: 9390 +Train: [91] [4700/6250] eta: 0:04:16 lr: 0.000002 grad: 0.1385 (0.1446) loss: 0.8159 (0.8135) time: 0.1482 data: 0.0572 max mem: 9390 +Train: [91] [4800/6250] eta: 0:03:59 lr: 0.000002 grad: 0.1382 (0.1445) loss: 0.8160 (0.8135) time: 0.1513 data: 0.0596 max mem: 9390 +Train: [91] [4900/6250] eta: 0:03:42 lr: 0.000002 grad: 0.1395 (0.1444) loss: 0.8201 (0.8135) time: 0.1590 data: 0.0652 max mem: 9390 +Train: [91] [5000/6250] eta: 0:03:26 lr: 0.000002 grad: 0.1355 (0.1443) loss: 0.8088 (0.8136) time: 0.1668 data: 0.0788 max mem: 9390 +Train: [91] [5100/6250] eta: 0:03:09 lr: 0.000002 grad: 0.1385 (0.1442) loss: 0.8057 (0.8136) time: 0.1618 data: 0.0702 max mem: 9390 +Train: [91] [5200/6250] eta: 0:02:52 lr: 0.000002 grad: 0.1444 (0.1442) loss: 0.8131 (0.8136) time: 0.1571 data: 0.0671 max mem: 9390 +Train: [91] [5300/6250] eta: 0:02:36 lr: 0.000002 grad: 0.1371 (0.1442) loss: 0.8140 (0.8136) time: 0.1774 data: 0.0975 max mem: 9390 +Train: [91] [5400/6250] eta: 0:02:20 lr: 0.000002 grad: 0.1411 (0.1441) loss: 0.8067 (0.8137) time: 0.1739 data: 0.0905 max mem: 9390 +Train: [91] [5500/6250] eta: 0:02:03 lr: 0.000002 grad: 0.1298 (0.1440) loss: 0.8177 (0.8138) time: 0.1681 data: 0.0813 max mem: 9390 +Train: [91] [5600/6250] eta: 0:01:47 lr: 0.000002 grad: 0.1376 (0.1440) loss: 0.8144 (0.8138) time: 0.1538 data: 0.0661 max mem: 9390 +Train: [91] [5700/6250] eta: 0:01:30 lr: 0.000002 grad: 0.1483 (0.1440) loss: 0.8163 (0.8138) time: 0.1523 data: 0.0502 max mem: 9390 +Train: [91] [5800/6250] eta: 0:01:14 lr: 0.000002 grad: 0.1402 (0.1440) loss: 0.8151 (0.8138) time: 0.1500 data: 0.0689 max mem: 9390 +Train: [91] [5900/6250] eta: 0:00:57 lr: 0.000002 grad: 0.1502 (0.1441) loss: 0.8094 (0.8138) time: 0.2141 data: 0.1214 max mem: 9390 +Train: [91] [6000/6250] eta: 0:00:41 lr: 0.000002 grad: 0.1449 (0.1441) loss: 0.8115 (0.8137) time: 0.1621 data: 0.0791 max mem: 9390 +Train: [91] [6100/6250] eta: 0:00:24 lr: 0.000002 grad: 0.1454 (0.1442) loss: 0.8118 (0.8137) time: 0.1831 data: 0.0860 max mem: 9390 +Train: [91] [6200/6250] eta: 0:00:08 lr: 0.000002 grad: 0.1442 (0.1442) loss: 0.8106 (0.8137) time: 0.1922 data: 0.1083 max mem: 9390 +Train: [91] [6249/6250] eta: 0:00:00 lr: 0.000002 grad: 0.1406 (0.1442) loss: 0.8064 (0.8137) time: 0.1591 data: 0.0796 max mem: 9390 +Train: [91] Total time: 0:17:15 (0.1657 s / it) +Averaged stats: lr: 0.000002 grad: 0.1406 (0.1442) loss: 0.8064 (0.8137) +Eval (hcp-train-subset): [91] [ 0/62] eta: 0:05:04 loss: 0.8237 (0.8237) time: 4.9065 data: 4.8383 max mem: 9390 +Eval (hcp-train-subset): [91] [61/62] eta: 0:00:00 loss: 0.8153 (0.8172) time: 0.1443 data: 0.1187 max mem: 9390 +Eval (hcp-train-subset): [91] Total time: 0:00:14 (0.2399 s / it) +Averaged stats (hcp-train-subset): loss: 0.8153 (0.8172) +Eval (hcp-val): [91] [ 0/62] eta: 0:03:57 loss: 0.8250 (0.8250) time: 3.8370 data: 3.7764 max mem: 9390 +Eval (hcp-val): [91] [61/62] eta: 0:00:00 loss: 0.8275 (0.8281) time: 0.1457 data: 0.1193 max mem: 9390 +Eval (hcp-val): [91] Total time: 0:00:14 (0.2358 s / it) +Averaged stats (hcp-val): loss: 0.8275 (0.8281) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +Train: [92] [ 0/6250] eta: 12:10:46 lr: 0.000002 grad: 0.1452 (0.1452) loss: 0.8198 (0.8198) time: 7.0154 data: 6.8966 max mem: 9390 +Train: [92] [ 100/6250] eta: 0:22:50 lr: 0.000002 grad: 0.1583 (0.1800) loss: 0.8229 (0.8247) time: 0.2147 data: 0.1167 max mem: 9390 +Train: [92] [ 200/6250] eta: 0:19:45 lr: 0.000002 grad: 0.1360 (0.1684) loss: 0.8258 (0.8224) time: 0.1613 data: 0.0660 max mem: 9390 +Train: [92] [ 300/6250] eta: 0:18:27 lr: 0.000002 grad: 0.1525 (0.1637) loss: 0.8162 (0.8202) time: 0.1403 data: 0.0497 max mem: 9390 +Train: [92] [ 400/6250] eta: 0:17:46 lr: 0.000002 grad: 0.1539 (0.1615) loss: 0.8145 (0.8187) time: 0.1671 data: 0.0602 max mem: 9390 +Train: [92] [ 500/6250] eta: 0:17:02 lr: 0.000002 grad: 0.1471 (0.1592) loss: 0.8135 (0.8176) time: 0.1509 data: 0.0552 max mem: 9390 +Train: [92] [ 600/6250] eta: 0:16:31 lr: 0.000002 grad: 0.1441 (0.1573) loss: 0.8114 (0.8166) time: 0.1601 data: 0.0745 max mem: 9390 +Train: [92] [ 700/6250] eta: 0:16:07 lr: 0.000002 grad: 0.1393 (0.1548) loss: 0.8095 (0.8163) time: 0.1838 data: 0.0865 max mem: 9390 +Train: [92] [ 800/6250] eta: 0:15:46 lr: 0.000002 grad: 0.1440 (0.1534) loss: 0.8128 (0.8159) time: 0.1578 data: 0.0641 max mem: 9390 +Train: [92] [ 900/6250] eta: 0:15:31 lr: 0.000002 grad: 0.1450 (0.1521) loss: 0.8070 (0.8157) time: 0.1865 data: 0.0907 max mem: 9390 +Train: [92] [1000/6250] eta: 0:15:08 lr: 0.000002 grad: 0.1387 (0.1510) loss: 0.8127 (0.8153) time: 0.1601 data: 0.0627 max mem: 9390 +Train: [92] [1100/6250] eta: 0:14:45 lr: 0.000002 grad: 0.1304 (0.1501) loss: 0.8099 (0.8151) time: 0.1440 data: 0.0537 max mem: 9390 +Train: [92] [1200/6250] eta: 0:14:26 lr: 0.000002 grad: 0.1337 (0.1495) loss: 0.8180 (0.8151) time: 0.1739 data: 0.0854 max mem: 9390 +Train: [92] [1300/6250] eta: 0:14:06 lr: 0.000002 grad: 0.1377 (0.1488) loss: 0.8091 (0.8150) time: 0.1525 data: 0.0683 max mem: 9390 +Train: [92] [1400/6250] eta: 0:13:48 lr: 0.000002 grad: 0.1424 (0.1483) loss: 0.8104 (0.8148) time: 0.1655 data: 0.0786 max mem: 9390 +Train: [92] [1500/6250] eta: 0:13:29 lr: 0.000002 grad: 0.1361 (0.1479) loss: 0.8076 (0.8148) time: 0.1729 data: 0.0816 max mem: 9390 +Train: [92] [1600/6250] eta: 0:13:11 lr: 0.000002 grad: 0.1404 (0.1476) loss: 0.8133 (0.8147) time: 0.1521 data: 0.0698 max mem: 9390 +Train: [92] [1700/6250] eta: 0:12:53 lr: 0.000002 grad: 0.1369 (0.1472) loss: 0.8154 (0.8146) time: 0.1682 data: 0.0807 max mem: 9390 +Train: [92] [1800/6250] eta: 0:12:34 lr: 0.000002 grad: 0.1363 (0.1467) loss: 0.8130 (0.8146) time: 0.1656 data: 0.0799 max mem: 9390 +Train: [92] [1900/6250] eta: 0:12:17 lr: 0.000002 grad: 0.1339 (0.1462) loss: 0.8189 (0.8146) time: 0.1524 data: 0.0642 max mem: 9390 +Train: [92] [2000/6250] eta: 0:11:57 lr: 0.000002 grad: 0.1466 (0.1460) loss: 0.8143 (0.8145) time: 0.1227 data: 0.0381 max mem: 9390 +Train: [92] [2100/6250] eta: 0:11:39 lr: 0.000002 grad: 0.1415 (0.1457) loss: 0.8082 (0.8144) time: 0.1534 data: 0.0693 max mem: 9390 +Train: [92] [2200/6250] eta: 0:11:22 lr: 0.000002 grad: 0.1353 (0.1454) loss: 0.8177 (0.8144) time: 0.1454 data: 0.0576 max mem: 9390 +Train: [92] [2300/6250] eta: 0:11:05 lr: 0.000002 grad: 0.1378 (0.1451) loss: 0.8136 (0.8145) time: 0.1793 data: 0.0942 max mem: 9390 +Train: [92] [2400/6250] eta: 0:10:47 lr: 0.000002 grad: 0.1294 (0.1448) loss: 0.8109 (0.8145) time: 0.1593 data: 0.0749 max mem: 9390 +Train: [92] [2500/6250] eta: 0:10:30 lr: 0.000002 grad: 0.1296 (0.1447) loss: 0.8191 (0.8145) time: 0.1611 data: 0.0789 max mem: 9390 +Train: [92] [2600/6250] eta: 0:10:13 lr: 0.000002 grad: 0.1460 (0.1446) loss: 0.8122 (0.8144) time: 0.1589 data: 0.0640 max mem: 9390 +Train: [92] [2700/6250] eta: 0:09:56 lr: 0.000002 grad: 0.1426 (0.1445) loss: 0.8120 (0.8144) time: 0.1517 data: 0.0658 max mem: 9390 +Train: [92] [2800/6250] eta: 0:09:37 lr: 0.000002 grad: 0.1418 (0.1444) loss: 0.8138 (0.8142) time: 0.1469 data: 0.0604 max mem: 9390 +Train: [92] [2900/6250] eta: 0:09:20 lr: 0.000002 grad: 0.1399 (0.1443) loss: 0.8177 (0.8142) time: 0.1676 data: 0.0806 max mem: 9390 +Train: [92] [3000/6250] eta: 0:09:03 lr: 0.000002 grad: 0.1294 (0.1442) loss: 0.8189 (0.8142) time: 0.1514 data: 0.0604 max mem: 9390 +Train: [92] [3100/6250] eta: 0:08:46 lr: 0.000002 grad: 0.1394 (0.1441) loss: 0.8123 (0.8141) time: 0.1644 data: 0.0788 max mem: 9390 +Train: [92] [3200/6250] eta: 0:08:29 lr: 0.000002 grad: 0.1443 (0.1440) loss: 0.8128 (0.8142) time: 0.1715 data: 0.0840 max mem: 9390 +Train: [92] [3300/6250] eta: 0:08:12 lr: 0.000002 grad: 0.1323 (0.1440) loss: 0.8192 (0.8141) time: 0.1936 data: 0.1113 max mem: 9390 +Train: [92] [3400/6250] eta: 0:07:55 lr: 0.000002 grad: 0.1454 (0.1440) loss: 0.8149 (0.8141) time: 0.1551 data: 0.0711 max mem: 9390 +Train: [92] [3500/6250] eta: 0:07:38 lr: 0.000002 grad: 0.1364 (0.1440) loss: 0.8133 (0.8141) time: 0.1731 data: 0.0892 max mem: 9390 +Train: [92] [3600/6250] eta: 0:07:21 lr: 0.000002 grad: 0.1391 (0.1440) loss: 0.8207 (0.8141) time: 0.1589 data: 0.0694 max mem: 9390 +Train: [92] [3700/6250] eta: 0:07:04 lr: 0.000002 grad: 0.1434 (0.1440) loss: 0.8126 (0.8140) time: 0.1514 data: 0.0671 max mem: 9390 +Train: [92] [3800/6250] eta: 0:06:47 lr: 0.000002 grad: 0.1414 (0.1440) loss: 0.8147 (0.8140) time: 0.1681 data: 0.0823 max mem: 9390 +Train: [92] [3900/6250] eta: 0:06:31 lr: 0.000002 grad: 0.1557 (0.1442) loss: 0.8071 (0.8139) time: 0.1606 data: 0.0712 max mem: 9390 +Train: [92] [4000/6250] eta: 0:06:14 lr: 0.000002 grad: 0.1530 (0.1443) loss: 0.8131 (0.8138) time: 0.1583 data: 0.0725 max mem: 9390 +Train: [92] [4100/6250] eta: 0:05:57 lr: 0.000002 grad: 0.1491 (0.1444) loss: 0.8124 (0.8137) time: 0.1442 data: 0.0646 max mem: 9390 +Train: [92] [4200/6250] eta: 0:05:41 lr: 0.000002 grad: 0.1422 (0.1445) loss: 0.8060 (0.8137) time: 0.1699 data: 0.0852 max mem: 9390 +Train: [92] [4300/6250] eta: 0:05:24 lr: 0.000002 grad: 0.1386 (0.1445) loss: 0.8103 (0.8136) time: 0.1658 data: 0.0831 max mem: 9390 +Train: [92] [4400/6250] eta: 0:05:07 lr: 0.000002 grad: 0.1416 (0.1446) loss: 0.8115 (0.8135) time: 0.1498 data: 0.0574 max mem: 9390 +Train: [92] [4500/6250] eta: 0:04:50 lr: 0.000002 grad: 0.1481 (0.1447) loss: 0.8096 (0.8134) time: 0.1558 data: 0.0710 max mem: 9390 +Train: [92] [4600/6250] eta: 0:04:34 lr: 0.000002 grad: 0.1397 (0.1448) loss: 0.8151 (0.8134) time: 0.1394 data: 0.0558 max mem: 9390 +Train: [92] [4700/6250] eta: 0:04:17 lr: 0.000002 grad: 0.1371 (0.1447) loss: 0.8083 (0.8134) time: 0.1682 data: 0.0857 max mem: 9390 +Train: [92] [4800/6250] eta: 0:04:00 lr: 0.000002 grad: 0.1333 (0.1447) loss: 0.8146 (0.8134) time: 0.1608 data: 0.0706 max mem: 9390 +Train: [92] [4900/6250] eta: 0:03:44 lr: 0.000002 grad: 0.1395 (0.1446) loss: 0.8165 (0.8135) time: 0.1734 data: 0.0845 max mem: 9390 +Train: [92] [5000/6250] eta: 0:03:27 lr: 0.000002 grad: 0.1417 (0.1446) loss: 0.8137 (0.8135) time: 0.1575 data: 0.0677 max mem: 9390 +Train: [92] [5100/6250] eta: 0:03:10 lr: 0.000002 grad: 0.1358 (0.1445) loss: 0.8158 (0.8135) time: 0.1566 data: 0.0680 max mem: 9390 +Train: [92] [5200/6250] eta: 0:02:54 lr: 0.000002 grad: 0.1371 (0.1446) loss: 0.8191 (0.8136) time: 0.1447 data: 0.0568 max mem: 9390 +Train: [92] [5300/6250] eta: 0:02:37 lr: 0.000002 grad: 0.1419 (0.1447) loss: 0.8132 (0.8136) time: 0.1579 data: 0.0687 max mem: 9390 +Train: [92] [5400/6250] eta: 0:02:20 lr: 0.000002 grad: 0.1426 (0.1447) loss: 0.8151 (0.8136) time: 0.1654 data: 0.0804 max mem: 9390 +Train: [92] [5500/6250] eta: 0:02:04 lr: 0.000002 grad: 0.1411 (0.1447) loss: 0.8106 (0.8136) time: 0.1623 data: 0.0832 max mem: 9390 +Train: [92] [5600/6250] eta: 0:01:47 lr: 0.000002 grad: 0.1343 (0.1447) loss: 0.8143 (0.8137) time: 0.1530 data: 0.0641 max mem: 9390 +Train: [92] [5700/6250] eta: 0:01:31 lr: 0.000002 grad: 0.1469 (0.1446) loss: 0.8161 (0.8137) time: 0.1690 data: 0.0846 max mem: 9390 +Train: [92] [5800/6250] eta: 0:01:14 lr: 0.000002 grad: 0.1445 (0.1446) loss: 0.8110 (0.8137) time: 0.1622 data: 0.0767 max mem: 9390 +Train: [92] [5900/6250] eta: 0:00:57 lr: 0.000002 grad: 0.1430 (0.1445) loss: 0.8150 (0.8138) time: 0.1425 data: 0.0616 max mem: 9390 +Train: [92] [6000/6250] eta: 0:00:41 lr: 0.000002 grad: 0.1249 (0.1444) loss: 0.8232 (0.8139) time: 0.1794 data: 0.0939 max mem: 9390 +Train: [92] [6100/6250] eta: 0:00:24 lr: 0.000002 grad: 0.1387 (0.1443) loss: 0.8154 (0.8139) time: 0.1658 data: 0.0790 max mem: 9390 +Train: [92] [6200/6250] eta: 0:00:08 lr: 0.000002 grad: 0.1417 (0.1443) loss: 0.8119 (0.8139) time: 0.1428 data: 0.0535 max mem: 9390 +Train: [92] [6249/6250] eta: 0:00:00 lr: 0.000002 grad: 0.1348 (0.1443) loss: 0.8189 (0.8139) time: 0.1501 data: 0.0671 max mem: 9390 +Train: [92] Total time: 0:17:20 (0.1664 s / it) +Averaged stats: lr: 0.000002 grad: 0.1348 (0.1443) loss: 0.8189 (0.8139) +Eval (hcp-train-subset): [92] [ 0/62] eta: 0:05:43 loss: 0.8220 (0.8220) time: 5.5388 data: 5.5023 max mem: 9390 +Eval (hcp-train-subset): [92] [61/62] eta: 0:00:00 loss: 0.8146 (0.8167) time: 0.1251 data: 0.0985 max mem: 9390 +Eval (hcp-train-subset): [92] Total time: 0:00:14 (0.2282 s / it) +Averaged stats (hcp-train-subset): loss: 0.8146 (0.8167) +Eval (hcp-val): [92] [ 0/62] eta: 0:04:22 loss: 0.8233 (0.8233) time: 4.2412 data: 4.1917 max mem: 9390 +Eval (hcp-val): [92] [61/62] eta: 0:00:00 loss: 0.8271 (0.8282) time: 0.1326 data: 0.1051 max mem: 9390 +Eval (hcp-val): [92] Total time: 0:00:14 (0.2392 s / it) +Averaged stats (hcp-val): loss: 0.8271 (0.8282) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +Train: [93] [ 0/6250] eta: 7:32:06 lr: 0.000002 grad: 0.0864 (0.0864) loss: 0.8594 (0.8594) time: 4.3403 data: 4.0191 max mem: 9390 +Train: [93] [ 100/6250] eta: 0:22:11 lr: 0.000002 grad: 0.1518 (0.1824) loss: 0.8196 (0.8149) time: 0.1835 data: 0.0965 max mem: 9390 +Train: [93] [ 200/6250] eta: 0:19:55 lr: 0.000002 grad: 0.1652 (0.1717) loss: 0.8079 (0.8153) time: 0.1666 data: 0.0792 max mem: 9390 +Train: [93] [ 300/6250] eta: 0:18:41 lr: 0.000002 grad: 0.1500 (0.1689) loss: 0.8186 (0.8137) time: 0.1811 data: 0.0920 max mem: 9390 +Train: [93] [ 400/6250] eta: 0:17:51 lr: 0.000002 grad: 0.1438 (0.1637) loss: 0.8188 (0.8145) time: 0.1830 data: 0.0964 max mem: 9390 +Train: [93] [ 500/6250] eta: 0:17:13 lr: 0.000002 grad: 0.1424 (0.1611) loss: 0.8173 (0.8144) time: 0.1672 data: 0.0685 max mem: 9390 +Train: [93] [ 600/6250] eta: 0:16:37 lr: 0.000002 grad: 0.1590 (0.1609) loss: 0.8066 (0.8129) time: 0.1505 data: 0.0524 max mem: 9390 +Train: [93] [ 700/6250] eta: 0:16:16 lr: 0.000002 grad: 0.1540 (0.1601) loss: 0.8038 (0.8124) time: 0.1630 data: 0.0672 max mem: 9390 +Train: [93] [ 800/6250] eta: 0:16:03 lr: 0.000002 grad: 0.1422 (0.1587) loss: 0.8118 (0.8121) time: 0.2014 data: 0.0939 max mem: 9390 +Train: [93] [ 900/6250] eta: 0:15:48 lr: 0.000002 grad: 0.1431 (0.1573) loss: 0.8161 (0.8121) time: 0.1637 data: 0.0777 max mem: 9390 +Train: [93] [1000/6250] eta: 0:15:26 lr: 0.000002 grad: 0.1413 (0.1561) loss: 0.8132 (0.8121) time: 0.1697 data: 0.0748 max mem: 9390 +Train: [93] [1100/6250] eta: 0:15:07 lr: 0.000002 grad: 0.1485 (0.1552) loss: 0.8095 (0.8120) time: 0.2077 data: 0.1179 max mem: 9390 +Train: [93] [1200/6250] eta: 0:14:45 lr: 0.000002 grad: 0.1399 (0.1545) loss: 0.8082 (0.8119) time: 0.1337 data: 0.0461 max mem: 9390 +Train: [93] [1300/6250] eta: 0:14:29 lr: 0.000002 grad: 0.1459 (0.1539) loss: 0.8109 (0.8118) time: 0.1996 data: 0.1150 max mem: 9390 +Train: [93] [1400/6250] eta: 0:14:10 lr: 0.000002 grad: 0.1433 (0.1534) loss: 0.8156 (0.8119) time: 0.1689 data: 0.0737 max mem: 9390 +Train: [93] [1500/6250] eta: 0:13:51 lr: 0.000002 grad: 0.1400 (0.1529) loss: 0.8100 (0.8118) time: 0.1767 data: 0.0844 max mem: 9390 +Train: [93] [1600/6250] eta: 0:13:33 lr: 0.000002 grad: 0.1436 (0.1527) loss: 0.8081 (0.8117) time: 0.1846 data: 0.0990 max mem: 9390 +Train: [93] [1700/6250] eta: 0:13:14 lr: 0.000002 grad: 0.1419 (0.1522) loss: 0.8130 (0.8117) time: 0.1714 data: 0.0820 max mem: 9390 +Train: [93] [1800/6250] eta: 0:12:56 lr: 0.000002 grad: 0.1376 (0.1518) loss: 0.8120 (0.8116) time: 0.1869 data: 0.0979 max mem: 9390 +Train: [93] [1900/6250] eta: 0:12:37 lr: 0.000002 grad: 0.1386 (0.1514) loss: 0.8137 (0.8117) time: 0.1886 data: 0.1047 max mem: 9390 +Train: [93] [2000/6250] eta: 0:12:18 lr: 0.000002 grad: 0.1427 (0.1511) loss: 0.8118 (0.8117) time: 0.1653 data: 0.0795 max mem: 9390 +Train: [93] [2100/6250] eta: 0:12:01 lr: 0.000002 grad: 0.1388 (0.1508) loss: 0.8124 (0.8117) time: 0.1813 data: 0.0963 max mem: 9390 +Train: [93] [2200/6250] eta: 0:11:45 lr: 0.000002 grad: 0.1350 (0.1505) loss: 0.8156 (0.8117) time: 0.2043 data: 0.1176 max mem: 9390 +Train: [93] [2300/6250] eta: 0:11:27 lr: 0.000001 grad: 0.1377 (0.1501) loss: 0.8144 (0.8117) time: 0.1926 data: 0.1012 max mem: 9390 +Train: [93] [2400/6250] eta: 0:11:12 lr: 0.000001 grad: 0.1424 (0.1498) loss: 0.8058 (0.8117) time: 0.1715 data: 0.0887 max mem: 9390 +Train: [93] [2500/6250] eta: 0:10:56 lr: 0.000001 grad: 0.1393 (0.1496) loss: 0.8148 (0.8117) time: 0.1434 data: 0.0682 max mem: 9390 +Train: [93] [2600/6250] eta: 0:10:40 lr: 0.000001 grad: 0.1355 (0.1493) loss: 0.8149 (0.8118) time: 0.1201 data: 0.0296 max mem: 9390 +Train: [93] [2700/6250] eta: 0:10:19 lr: 0.000001 grad: 0.1347 (0.1490) loss: 0.8184 (0.8118) time: 0.1487 data: 0.0655 max mem: 9390 +Train: [93] [2800/6250] eta: 0:10:02 lr: 0.000001 grad: 0.1367 (0.1488) loss: 0.8153 (0.8118) time: 0.1545 data: 0.0727 max mem: 9390 +Train: [93] [2900/6250] eta: 0:09:43 lr: 0.000001 grad: 0.1431 (0.1485) loss: 0.8165 (0.8119) time: 0.1701 data: 0.0747 max mem: 9390 +Train: [93] [3000/6250] eta: 0:09:26 lr: 0.000001 grad: 0.1347 (0.1481) loss: 0.8169 (0.8119) time: 0.1800 data: 0.0854 max mem: 9390 +Train: [93] [3100/6250] eta: 0:09:07 lr: 0.000001 grad: 0.1434 (0.1479) loss: 0.8125 (0.8120) time: 0.1661 data: 0.0729 max mem: 9390 +Train: [93] [3200/6250] eta: 0:08:48 lr: 0.000001 grad: 0.1375 (0.1478) loss: 0.8125 (0.8120) time: 0.1678 data: 0.0730 max mem: 9390 +Train: [93] [3300/6250] eta: 0:08:30 lr: 0.000001 grad: 0.1378 (0.1476) loss: 0.8156 (0.8120) time: 0.1467 data: 0.0498 max mem: 9390 +Train: [93] [3400/6250] eta: 0:08:11 lr: 0.000001 grad: 0.1367 (0.1474) loss: 0.8106 (0.8121) time: 0.1402 data: 0.0492 max mem: 9390 +Train: [93] [3500/6250] eta: 0:07:52 lr: 0.000001 grad: 0.1440 (0.1474) loss: 0.8146 (0.8121) time: 0.1275 data: 0.0260 max mem: 9390 +Train: [93] [3600/6250] eta: 0:07:34 lr: 0.000001 grad: 0.1410 (0.1473) loss: 0.8133 (0.8121) time: 0.1629 data: 0.0676 max mem: 9390 +Train: [93] [3700/6250] eta: 0:07:16 lr: 0.000001 grad: 0.1423 (0.1473) loss: 0.8028 (0.8121) time: 0.1466 data: 0.0495 max mem: 9390 +Train: [93] [3800/6250] eta: 0:06:58 lr: 0.000001 grad: 0.1341 (0.1474) loss: 0.8157 (0.8121) time: 0.1867 data: 0.0972 max mem: 9390 +Train: [93] [3900/6250] eta: 0:06:41 lr: 0.000001 grad: 0.1452 (0.1474) loss: 0.8097 (0.8120) time: 0.1519 data: 0.0596 max mem: 9390 +Train: [93] [4000/6250] eta: 0:06:23 lr: 0.000001 grad: 0.1347 (0.1473) loss: 0.8151 (0.8120) time: 0.1827 data: 0.0960 max mem: 9390 +Train: [93] [4100/6250] eta: 0:06:06 lr: 0.000001 grad: 0.1479 (0.1474) loss: 0.8115 (0.8119) time: 0.1578 data: 0.0685 max mem: 9390 +Train: [93] [4200/6250] eta: 0:05:49 lr: 0.000001 grad: 0.1347 (0.1473) loss: 0.8134 (0.8119) time: 0.1546 data: 0.0632 max mem: 9390 +Train: [93] [4300/6250] eta: 0:05:31 lr: 0.000001 grad: 0.1430 (0.1474) loss: 0.8055 (0.8118) time: 0.1652 data: 0.0700 max mem: 9390 +Train: [93] [4400/6250] eta: 0:05:14 lr: 0.000001 grad: 0.1473 (0.1475) loss: 0.8077 (0.8118) time: 0.1754 data: 0.0822 max mem: 9390 +Train: [93] [4500/6250] eta: 0:04:57 lr: 0.000001 grad: 0.1467 (0.1475) loss: 0.8092 (0.8117) time: 0.1754 data: 0.0834 max mem: 9390 +Train: [93] [4600/6250] eta: 0:04:40 lr: 0.000001 grad: 0.1477 (0.1476) loss: 0.8139 (0.8117) time: 0.1828 data: 0.0890 max mem: 9390 +Train: [93] [4700/6250] eta: 0:04:22 lr: 0.000001 grad: 0.1513 (0.1477) loss: 0.8090 (0.8117) time: 0.1604 data: 0.0649 max mem: 9390 +Train: [93] [4800/6250] eta: 0:04:05 lr: 0.000001 grad: 0.1534 (0.1478) loss: 0.8123 (0.8116) time: 0.1610 data: 0.0757 max mem: 9390 +Train: [93] [4900/6250] eta: 0:03:48 lr: 0.000001 grad: 0.1419 (0.1478) loss: 0.8070 (0.8116) time: 0.1762 data: 0.0919 max mem: 9390 +Train: [93] [5000/6250] eta: 0:03:31 lr: 0.000001 grad: 0.1472 (0.1479) loss: 0.8082 (0.8115) time: 0.1584 data: 0.0712 max mem: 9390 +Train: [93] [5100/6250] eta: 0:03:14 lr: 0.000001 grad: 0.1495 (0.1479) loss: 0.8080 (0.8115) time: 0.1948 data: 0.1079 max mem: 9390 +Train: [93] [5200/6250] eta: 0:02:57 lr: 0.000001 grad: 0.1419 (0.1479) loss: 0.8127 (0.8115) time: 0.1408 data: 0.0534 max mem: 9390 +Train: [93] [5300/6250] eta: 0:02:40 lr: 0.000001 grad: 0.1353 (0.1478) loss: 0.8186 (0.8115) time: 0.1424 data: 0.0538 max mem: 9390 +Train: [93] [5400/6250] eta: 0:02:23 lr: 0.000001 grad: 0.1442 (0.1479) loss: 0.8116 (0.8115) time: 0.1506 data: 0.0663 max mem: 9390 +Train: [93] [5500/6250] eta: 0:02:06 lr: 0.000001 grad: 0.1414 (0.1478) loss: 0.8171 (0.8116) time: 0.1655 data: 0.0802 max mem: 9390 +Train: [93] [5600/6250] eta: 0:01:49 lr: 0.000001 grad: 0.1493 (0.1478) loss: 0.8127 (0.8116) time: 0.1800 data: 0.0975 max mem: 9390 +Train: [93] [5700/6250] eta: 0:01:32 lr: 0.000001 grad: 0.1418 (0.1477) loss: 0.8126 (0.8116) time: 0.1606 data: 0.0753 max mem: 9390 +Train: [93] [5800/6250] eta: 0:01:15 lr: 0.000001 grad: 0.1411 (0.1476) loss: 0.8157 (0.8117) time: 0.1581 data: 0.0726 max mem: 9390 +Train: [93] [5900/6250] eta: 0:00:58 lr: 0.000001 grad: 0.1408 (0.1476) loss: 0.8100 (0.8117) time: 0.1633 data: 0.0835 max mem: 9390 +Train: [93] [6000/6250] eta: 0:00:42 lr: 0.000001 grad: 0.1427 (0.1475) loss: 0.8091 (0.8117) time: 0.1641 data: 0.0822 max mem: 9390 +Train: [93] [6100/6250] eta: 0:00:25 lr: 0.000001 grad: 0.1384 (0.1475) loss: 0.8118 (0.8117) time: 0.1731 data: 0.0827 max mem: 9390 +Train: [93] [6200/6250] eta: 0:00:08 lr: 0.000001 grad: 0.1414 (0.1475) loss: 0.8091 (0.8118) time: 0.1603 data: 0.0826 max mem: 9390 +Train: [93] [6249/6250] eta: 0:00:00 lr: 0.000001 grad: 0.1367 (0.1475) loss: 0.8130 (0.8118) time: 0.1916 data: 0.1097 max mem: 9390 +Train: [93] Total time: 0:17:37 (0.1692 s / it) +Averaged stats: lr: 0.000001 grad: 0.1367 (0.1475) loss: 0.8130 (0.8118) +Eval (hcp-train-subset): [93] [ 0/62] eta: 0:05:43 loss: 0.8205 (0.8205) time: 5.5420 data: 5.5118 max mem: 9390 +Eval (hcp-train-subset): [93] [61/62] eta: 0:00:00 loss: 0.8140 (0.8160) time: 0.1782 data: 0.1532 max mem: 9390 +Eval (hcp-train-subset): [93] Total time: 0:00:15 (0.2552 s / it) +Averaged stats (hcp-train-subset): loss: 0.8140 (0.8160) +Eval (hcp-val): [93] [ 0/62] eta: 0:04:20 loss: 0.8235 (0.8235) time: 4.1965 data: 4.1321 max mem: 9390 +Eval (hcp-val): [93] [61/62] eta: 0:00:00 loss: 0.8279 (0.8276) time: 0.1040 data: 0.0792 max mem: 9390 +Eval (hcp-val): [93] Total time: 0:00:13 (0.2241 s / it) +Averaged stats (hcp-val): loss: 0.8279 (0.8276) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +Train: [94] [ 0/6250] eta: 6:34:09 lr: 0.000001 grad: 0.0812 (0.0812) loss: 0.8639 (0.8639) time: 3.7839 data: 3.6298 max mem: 9390 +Train: [94] [ 100/6250] eta: 0:21:32 lr: 0.000001 grad: 0.1687 (0.2095) loss: 0.8060 (0.8074) time: 0.1629 data: 0.0660 max mem: 9390 +Train: [94] [ 200/6250] eta: 0:19:35 lr: 0.000001 grad: 0.1399 (0.1955) loss: 0.8077 (0.8079) time: 0.1778 data: 0.0799 max mem: 9390 +Train: [94] [ 300/6250] eta: 0:18:13 lr: 0.000001 grad: 0.1465 (0.1818) loss: 0.8208 (0.8107) time: 0.1654 data: 0.0804 max mem: 9390 +Train: [94] [ 400/6250] eta: 0:17:29 lr: 0.000001 grad: 0.1603 (0.1756) loss: 0.8127 (0.8116) time: 0.1703 data: 0.0793 max mem: 9390 +Train: [94] [ 500/6250] eta: 0:16:57 lr: 0.000001 grad: 0.1569 (0.1726) loss: 0.8051 (0.8112) time: 0.1379 data: 0.0412 max mem: 9390 +Train: [94] [ 600/6250] eta: 0:16:30 lr: 0.000001 grad: 0.1576 (0.1697) loss: 0.8088 (0.8111) time: 0.1714 data: 0.0748 max mem: 9390 +Train: [94] [ 700/6250] eta: 0:16:04 lr: 0.000001 grad: 0.1666 (0.1688) loss: 0.8008 (0.8105) time: 0.1793 data: 0.0838 max mem: 9390 +Train: [94] [ 800/6250] eta: 0:15:56 lr: 0.000001 grad: 0.1496 (0.1680) loss: 0.8139 (0.8100) time: 0.1912 data: 0.1064 max mem: 9390 +Train: [94] [ 900/6250] eta: 0:15:38 lr: 0.000001 grad: 0.1466 (0.1670) loss: 0.8038 (0.8093) time: 0.1629 data: 0.0732 max mem: 9390 +Train: [94] [1000/6250] eta: 0:15:14 lr: 0.000001 grad: 0.1486 (0.1659) loss: 0.8038 (0.8090) time: 0.1546 data: 0.0677 max mem: 9390 +Train: [94] [1100/6250] eta: 0:14:51 lr: 0.000001 grad: 0.1476 (0.1651) loss: 0.8056 (0.8088) time: 0.1597 data: 0.0675 max mem: 9390 +Train: [94] [1200/6250] eta: 0:14:31 lr: 0.000001 grad: 0.1504 (0.1643) loss: 0.7969 (0.8086) time: 0.1780 data: 0.0864 max mem: 9390 +Train: [94] [1300/6250] eta: 0:14:15 lr: 0.000001 grad: 0.1451 (0.1632) loss: 0.8045 (0.8086) time: 0.1668 data: 0.0743 max mem: 9390 +Train: [94] [1400/6250] eta: 0:13:55 lr: 0.000001 grad: 0.1415 (0.1620) loss: 0.8152 (0.8088) time: 0.1811 data: 0.0945 max mem: 9390 +Train: [94] [1500/6250] eta: 0:13:35 lr: 0.000001 grad: 0.1406 (0.1609) loss: 0.8101 (0.8089) time: 0.1766 data: 0.0901 max mem: 9390 +Train: [94] [1600/6250] eta: 0:13:16 lr: 0.000001 grad: 0.1346 (0.1601) loss: 0.8130 (0.8091) time: 0.1524 data: 0.0601 max mem: 9390 +Train: [94] [1700/6250] eta: 0:12:56 lr: 0.000001 grad: 0.1372 (0.1593) loss: 0.8164 (0.8092) time: 0.1544 data: 0.0742 max mem: 9390 +Train: [94] [1800/6250] eta: 0:12:36 lr: 0.000001 grad: 0.1533 (0.1586) loss: 0.8120 (0.8094) time: 0.1653 data: 0.0717 max mem: 9390 +Train: [94] [1900/6250] eta: 0:12:18 lr: 0.000001 grad: 0.1399 (0.1578) loss: 0.8178 (0.8096) time: 0.1574 data: 0.0683 max mem: 9390 +Train: [94] [2000/6250] eta: 0:11:59 lr: 0.000001 grad: 0.1449 (0.1571) loss: 0.8144 (0.8099) time: 0.1455 data: 0.0587 max mem: 9390 +Train: [94] [2100/6250] eta: 0:11:41 lr: 0.000001 grad: 0.1330 (0.1563) loss: 0.8155 (0.8101) time: 0.1677 data: 0.0828 max mem: 9390 +Train: [94] [2200/6250] eta: 0:11:23 lr: 0.000001 grad: 0.1408 (0.1556) loss: 0.8140 (0.8103) time: 0.1452 data: 0.0568 max mem: 9390 +Train: [94] [2300/6250] eta: 0:11:06 lr: 0.000001 grad: 0.1477 (0.1550) loss: 0.8099 (0.8104) time: 0.1429 data: 0.0546 max mem: 9390 +Train: [94] [2400/6250] eta: 0:10:49 lr: 0.000001 grad: 0.1391 (0.1545) loss: 0.8165 (0.8106) time: 0.1751 data: 0.0907 max mem: 9390 +Train: [94] [2500/6250] eta: 0:10:31 lr: 0.000001 grad: 0.1250 (0.1539) loss: 0.8158 (0.8107) time: 0.1653 data: 0.0862 max mem: 9390 +Train: [94] [2600/6250] eta: 0:10:13 lr: 0.000001 grad: 0.1361 (0.1536) loss: 0.8065 (0.8107) time: 0.1624 data: 0.0760 max mem: 9390 +Train: [94] [2700/6250] eta: 0:09:56 lr: 0.000001 grad: 0.1273 (0.1530) loss: 0.8211 (0.8108) time: 0.1517 data: 0.0600 max mem: 9390 +Train: [94] [2800/6250] eta: 0:09:40 lr: 0.000001 grad: 0.1395 (0.1526) loss: 0.8052 (0.8109) time: 0.1633 data: 0.0742 max mem: 9390 +Train: [94] [2900/6250] eta: 0:09:23 lr: 0.000001 grad: 0.1386 (0.1523) loss: 0.8206 (0.8111) time: 0.1711 data: 0.0905 max mem: 9390 +Train: [94] [3000/6250] eta: 0:09:06 lr: 0.000001 grad: 0.1346 (0.1519) loss: 0.8143 (0.8112) time: 0.1583 data: 0.0717 max mem: 9390 +Train: [94] [3100/6250] eta: 0:08:49 lr: 0.000001 grad: 0.1448 (0.1517) loss: 0.8163 (0.8113) time: 0.1652 data: 0.0817 max mem: 9390 +Train: [94] [3200/6250] eta: 0:08:32 lr: 0.000001 grad: 0.1396 (0.1515) loss: 0.8190 (0.8114) time: 0.1753 data: 0.0862 max mem: 9390 +Train: [94] [3300/6250] eta: 0:08:15 lr: 0.000001 grad: 0.1372 (0.1513) loss: 0.8171 (0.8115) time: 0.1737 data: 0.0867 max mem: 9390 +Train: [94] [3400/6250] eta: 0:07:58 lr: 0.000001 grad: 0.1445 (0.1511) loss: 0.8144 (0.8115) time: 0.1936 data: 0.1085 max mem: 9390 +Train: [94] [3500/6250] eta: 0:07:41 lr: 0.000001 grad: 0.1392 (0.1509) loss: 0.8168 (0.8115) time: 0.1615 data: 0.0696 max mem: 9390 +Train: [94] [3600/6250] eta: 0:07:24 lr: 0.000001 grad: 0.1512 (0.1509) loss: 0.8144 (0.8115) time: 0.1678 data: 0.0813 max mem: 9390 +Train: [94] [3700/6250] eta: 0:07:07 lr: 0.000001 grad: 0.1369 (0.1507) loss: 0.8188 (0.8116) time: 0.1682 data: 0.0803 max mem: 9390 +Train: [94] [3800/6250] eta: 0:06:50 lr: 0.000001 grad: 0.1392 (0.1506) loss: 0.8157 (0.8117) time: 0.2002 data: 0.1127 max mem: 9390 +Train: [94] [3900/6250] eta: 0:06:33 lr: 0.000001 grad: 0.1357 (0.1505) loss: 0.8154 (0.8117) time: 0.1625 data: 0.0707 max mem: 9390 +Train: [94] [4000/6250] eta: 0:06:17 lr: 0.000001 grad: 0.1425 (0.1504) loss: 0.8126 (0.8118) time: 0.1518 data: 0.0675 max mem: 9390 +Train: [94] [4100/6250] eta: 0:06:00 lr: 0.000001 grad: 0.1355 (0.1503) loss: 0.8096 (0.8119) time: 0.1541 data: 0.0693 max mem: 9390 +Train: [94] [4200/6250] eta: 0:05:43 lr: 0.000001 grad: 0.1367 (0.1501) loss: 0.8149 (0.8119) time: 0.1540 data: 0.0597 max mem: 9390 +Train: [94] [4300/6250] eta: 0:05:26 lr: 0.000001 grad: 0.1428 (0.1500) loss: 0.8143 (0.8120) time: 0.1588 data: 0.0722 max mem: 9390 +Train: [94] [4400/6250] eta: 0:05:09 lr: 0.000001 grad: 0.1346 (0.1498) loss: 0.8173 (0.8121) time: 0.1534 data: 0.0700 max mem: 9390 +Train: [94] [4500/6250] eta: 0:04:52 lr: 0.000001 grad: 0.1387 (0.1497) loss: 0.8137 (0.8122) time: 0.1755 data: 0.0926 max mem: 9390 +Train: [94] [4600/6250] eta: 0:04:35 lr: 0.000001 grad: 0.1421 (0.1496) loss: 0.8188 (0.8123) time: 0.1600 data: 0.0748 max mem: 9390 +Train: [94] [4700/6250] eta: 0:04:18 lr: 0.000001 grad: 0.1377 (0.1495) loss: 0.8151 (0.8123) time: 0.1758 data: 0.0832 max mem: 9390 +Train: [94] [4800/6250] eta: 0:04:02 lr: 0.000001 grad: 0.1461 (0.1493) loss: 0.8171 (0.8124) time: 0.1550 data: 0.0693 max mem: 9390 +Train: [94] [4900/6250] eta: 0:03:45 lr: 0.000001 grad: 0.1312 (0.1491) loss: 0.8216 (0.8125) time: 0.1774 data: 0.0914 max mem: 9390 +Train: [94] [5000/6250] eta: 0:03:28 lr: 0.000001 grad: 0.1362 (0.1489) loss: 0.8212 (0.8126) time: 0.1507 data: 0.0667 max mem: 9390 +Train: [94] [5100/6250] eta: 0:03:11 lr: 0.000001 grad: 0.1430 (0.1489) loss: 0.8160 (0.8127) time: 0.1594 data: 0.0725 max mem: 9390 +Train: [94] [5200/6250] eta: 0:02:55 lr: 0.000001 grad: 0.1395 (0.1489) loss: 0.8158 (0.8127) time: 0.1610 data: 0.0730 max mem: 9390 +Train: [94] [5300/6250] eta: 0:02:38 lr: 0.000001 grad: 0.1378 (0.1489) loss: 0.8147 (0.8127) time: 0.1820 data: 0.1022 max mem: 9390 +Train: [94] [5400/6250] eta: 0:02:22 lr: 0.000001 grad: 0.1371 (0.1488) loss: 0.8186 (0.8127) time: 0.1677 data: 0.0811 max mem: 9390 +Train: [94] [5500/6250] eta: 0:02:05 lr: 0.000001 grad: 0.1397 (0.1487) loss: 0.8163 (0.8128) time: 0.1632 data: 0.0851 max mem: 9390 +Train: [94] [5600/6250] eta: 0:01:48 lr: 0.000001 grad: 0.1424 (0.1486) loss: 0.8174 (0.8129) time: 0.1577 data: 0.0757 max mem: 9390 +Train: [94] [5700/6250] eta: 0:01:31 lr: 0.000001 grad: 0.1355 (0.1486) loss: 0.8134 (0.8129) time: 0.1530 data: 0.0647 max mem: 9390 +Train: [94] [5800/6250] eta: 0:01:15 lr: 0.000001 grad: 0.1336 (0.1485) loss: 0.8164 (0.8129) time: 0.1540 data: 0.0611 max mem: 9390 +Train: [94] [5900/6250] eta: 0:00:58 lr: 0.000001 grad: 0.1408 (0.1484) loss: 0.8129 (0.8130) time: 0.1736 data: 0.0841 max mem: 9390 +Train: [94] [6000/6250] eta: 0:00:41 lr: 0.000001 grad: 0.1444 (0.1484) loss: 0.8163 (0.8130) time: 0.1775 data: 0.0926 max mem: 9390 +Train: [94] [6100/6250] eta: 0:00:25 lr: 0.000001 grad: 0.1377 (0.1483) loss: 0.8193 (0.8130) time: 0.1361 data: 0.0432 max mem: 9390 +Train: [94] [6200/6250] eta: 0:00:08 lr: 0.000001 grad: 0.1546 (0.1483) loss: 0.8087 (0.8131) time: 0.1673 data: 0.0781 max mem: 9390 +Train: [94] [6249/6250] eta: 0:00:00 lr: 0.000001 grad: 0.1462 (0.1483) loss: 0.8146 (0.8131) time: 0.1647 data: 0.0748 max mem: 9390 +Train: [94] Total time: 0:17:31 (0.1682 s / it) +Averaged stats: lr: 0.000001 grad: 0.1462 (0.1483) loss: 0.8146 (0.8131) +Eval (hcp-train-subset): [94] [ 0/62] eta: 0:05:03 loss: 0.8231 (0.8231) time: 4.8980 data: 4.8659 max mem: 9390 +Eval (hcp-train-subset): [94] [61/62] eta: 0:00:00 loss: 0.8131 (0.8158) time: 0.1167 data: 0.0920 max mem: 9390 +Eval (hcp-train-subset): [94] Total time: 0:00:15 (0.2426 s / it) +Averaged stats (hcp-train-subset): loss: 0.8131 (0.8158) +Making plots (hcp-train-subset): example=9 +Eval (hcp-val): [94] [ 0/62] eta: 0:04:08 loss: 0.8238 (0.8238) time: 4.0115 data: 3.9421 max mem: 9390 +Eval (hcp-val): [94] [61/62] eta: 0:00:00 loss: 0.8262 (0.8281) time: 0.1316 data: 0.1048 max mem: 9390 +Eval (hcp-val): [94] Total time: 0:00:14 (0.2278 s / it) +Averaged stats (hcp-val): loss: 0.8262 (0.8281) +Making plots (hcp-val): example=58 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +Train: [95] [ 0/6250] eta: 7:17:43 lr: 0.000001 grad: 0.2492 (0.2492) loss: 0.8378 (0.8378) time: 4.2022 data: 4.0234 max mem: 9390 +Train: [95] [ 100/6250] eta: 0:22:16 lr: 0.000001 grad: 0.1608 (0.2156) loss: 0.8183 (0.8124) time: 0.1644 data: 0.0710 max mem: 9390 +Train: [95] [ 200/6250] eta: 0:19:34 lr: 0.000001 grad: 0.1464 (0.1869) loss: 0.8152 (0.8155) time: 0.1500 data: 0.0601 max mem: 9390 +Train: [95] [ 300/6250] eta: 0:18:23 lr: 0.000001 grad: 0.1616 (0.1776) loss: 0.8113 (0.8161) time: 0.1732 data: 0.0807 max mem: 9390 +Train: [95] [ 400/6250] eta: 0:17:29 lr: 0.000001 grad: 0.1540 (0.1736) loss: 0.8127 (0.8153) time: 0.1513 data: 0.0505 max mem: 9390 +Train: [95] [ 500/6250] eta: 0:16:59 lr: 0.000001 grad: 0.1455 (0.1698) loss: 0.8160 (0.8145) time: 0.1735 data: 0.0804 max mem: 9390 +Train: [95] [ 600/6250] eta: 0:16:24 lr: 0.000001 grad: 0.1306 (0.1657) loss: 0.8181 (0.8143) time: 0.1633 data: 0.0720 max mem: 9390 +Train: [95] [ 700/6250] eta: 0:16:00 lr: 0.000001 grad: 0.1455 (0.1628) loss: 0.8198 (0.8147) time: 0.1800 data: 0.0960 max mem: 9390 +Train: [95] [ 800/6250] eta: 0:15:41 lr: 0.000001 grad: 0.1407 (0.1606) loss: 0.8128 (0.8148) time: 0.1963 data: 0.1027 max mem: 9390 +Train: [95] [ 900/6250] eta: 0:15:21 lr: 0.000001 grad: 0.1473 (0.1596) loss: 0.8097 (0.8147) time: 0.1682 data: 0.0809 max mem: 9390 +Train: [95] [1000/6250] eta: 0:15:01 lr: 0.000001 grad: 0.1383 (0.1584) loss: 0.8187 (0.8145) time: 0.1613 data: 0.0746 max mem: 9390 +Train: [95] [1100/6250] eta: 0:14:40 lr: 0.000001 grad: 0.1288 (0.1570) loss: 0.8227 (0.8145) time: 0.1445 data: 0.0534 max mem: 9390 +Train: [95] [1200/6250] eta: 0:14:27 lr: 0.000001 grad: 0.1385 (0.1562) loss: 0.8066 (0.8144) time: 0.2036 data: 0.1236 max mem: 9390 +Train: [95] [1300/6250] eta: 0:14:26 lr: 0.000001 grad: 0.1354 (0.1553) loss: 0.8123 (0.8142) time: 0.2017 data: 0.1176 max mem: 9390 +Train: [95] [1400/6250] eta: 0:14:24 lr: 0.000001 grad: 0.1342 (0.1544) loss: 0.8178 (0.8143) time: 0.2006 data: 0.1131 max mem: 9390 +Train: [95] [1500/6250] eta: 0:14:00 lr: 0.000001 grad: 0.1381 (0.1540) loss: 0.8179 (0.8144) time: 0.1378 data: 0.0573 max mem: 9390 +Train: [95] [1600/6250] eta: 0:13:46 lr: 0.000001 grad: 0.1398 (0.1536) loss: 0.8211 (0.8143) time: 0.1630 data: 0.0731 max mem: 9390 +Train: [95] [1700/6250] eta: 0:13:25 lr: 0.000001 grad: 0.1392 (0.1531) loss: 0.8124 (0.8143) time: 0.1886 data: 0.0839 max mem: 9390 +Train: [95] [1800/6250] eta: 0:13:04 lr: 0.000001 grad: 0.1502 (0.1527) loss: 0.8082 (0.8143) time: 0.1786 data: 0.0832 max mem: 9390 +Train: [95] [1900/6250] eta: 0:12:47 lr: 0.000001 grad: 0.1418 (0.1525) loss: 0.8160 (0.8144) time: 0.1977 data: 0.0976 max mem: 9390 +Train: [95] [2000/6250] eta: 0:12:24 lr: 0.000001 grad: 0.1358 (0.1521) loss: 0.8185 (0.8144) time: 0.1703 data: 0.0782 max mem: 9390 +Train: [95] [2100/6250] eta: 0:12:06 lr: 0.000001 grad: 0.1345 (0.1518) loss: 0.8208 (0.8145) time: 0.1424 data: 0.0486 max mem: 9390 +Train: [95] [2200/6250] eta: 0:11:46 lr: 0.000001 grad: 0.1373 (0.1514) loss: 0.8119 (0.8145) time: 0.1566 data: 0.0502 max mem: 9390 +Train: [95] [2300/6250] eta: 0:11:26 lr: 0.000001 grad: 0.1321 (0.1512) loss: 0.8135 (0.8144) time: 0.1485 data: 0.0490 max mem: 9390 +Train: [95] [2400/6250] eta: 0:11:05 lr: 0.000001 grad: 0.1404 (0.1511) loss: 0.8188 (0.8144) time: 0.1443 data: 0.0555 max mem: 9390 +Train: [95] [2500/6250] eta: 0:10:47 lr: 0.000001 grad: 0.1388 (0.1510) loss: 0.8119 (0.8144) time: 0.1860 data: 0.1030 max mem: 9390 +Train: [95] [2600/6250] eta: 0:10:28 lr: 0.000001 grad: 0.1453 (0.1506) loss: 0.8144 (0.8144) time: 0.1491 data: 0.0562 max mem: 9390 +Train: [95] [2700/6250] eta: 0:10:10 lr: 0.000001 grad: 0.1482 (0.1504) loss: 0.8119 (0.8144) time: 0.1868 data: 0.0968 max mem: 9390 +Train: [95] [2800/6250] eta: 0:09:52 lr: 0.000001 grad: 0.1327 (0.1501) loss: 0.8148 (0.8144) time: 0.1538 data: 0.0663 max mem: 9390 +Train: [95] [2900/6250] eta: 0:09:34 lr: 0.000001 grad: 0.1379 (0.1499) loss: 0.8141 (0.8144) time: 0.1657 data: 0.0767 max mem: 9390 +Train: [95] [3000/6250] eta: 0:09:16 lr: 0.000001 grad: 0.1448 (0.1497) loss: 0.8185 (0.8144) time: 0.1585 data: 0.0634 max mem: 9390 +Train: [95] [3100/6250] eta: 0:08:58 lr: 0.000001 grad: 0.1441 (0.1495) loss: 0.8114 (0.8144) time: 0.1823 data: 0.0929 max mem: 9390 +Train: [95] [3200/6250] eta: 0:08:41 lr: 0.000001 grad: 0.1427 (0.1493) loss: 0.8178 (0.8144) time: 0.1537 data: 0.0497 max mem: 9390 +Train: [95] [3300/6250] eta: 0:08:24 lr: 0.000001 grad: 0.1458 (0.1493) loss: 0.8126 (0.8143) time: 0.1418 data: 0.0600 max mem: 9390 +Train: [95] [3400/6250] eta: 0:08:07 lr: 0.000001 grad: 0.1384 (0.1490) loss: 0.8094 (0.8142) time: 0.1591 data: 0.0736 max mem: 9390 +Train: [95] [3500/6250] eta: 0:07:50 lr: 0.000001 grad: 0.1384 (0.1489) loss: 0.8146 (0.8142) time: 0.1714 data: 0.0873 max mem: 9390 +Train: [95] [3600/6250] eta: 0:07:32 lr: 0.000001 grad: 0.1426 (0.1488) loss: 0.8168 (0.8141) time: 0.1651 data: 0.0812 max mem: 9390 +Train: [95] [3700/6250] eta: 0:07:15 lr: 0.000001 grad: 0.1411 (0.1486) loss: 0.8108 (0.8141) time: 0.1834 data: 0.1015 max mem: 9390 +Train: [95] [3800/6250] eta: 0:06:58 lr: 0.000001 grad: 0.1411 (0.1485) loss: 0.8174 (0.8140) time: 0.1583 data: 0.0649 max mem: 9390 +Train: [95] [3900/6250] eta: 0:06:41 lr: 0.000001 grad: 0.1403 (0.1484) loss: 0.8182 (0.8140) time: 0.1824 data: 0.0957 max mem: 9390 +Train: [95] [4000/6250] eta: 0:06:24 lr: 0.000001 grad: 0.1362 (0.1484) loss: 0.8130 (0.8139) time: 0.1684 data: 0.0893 max mem: 9390 +Train: [95] [4100/6250] eta: 0:06:07 lr: 0.000001 grad: 0.1403 (0.1484) loss: 0.8125 (0.8138) time: 0.1847 data: 0.0977 max mem: 9390 +Train: [95] [4200/6250] eta: 0:05:49 lr: 0.000001 grad: 0.1479 (0.1484) loss: 0.8158 (0.8138) time: 0.1609 data: 0.0753 max mem: 9390 +Train: [95] [4300/6250] eta: 0:05:32 lr: 0.000001 grad: 0.1378 (0.1484) loss: 0.8185 (0.8137) time: 0.1600 data: 0.0748 max mem: 9390 +Train: [95] [4400/6250] eta: 0:05:15 lr: 0.000001 grad: 0.1401 (0.1484) loss: 0.8134 (0.8137) time: 0.1670 data: 0.0817 max mem: 9390 +Train: [95] [4500/6250] eta: 0:04:57 lr: 0.000001 grad: 0.1379 (0.1483) loss: 0.8117 (0.8137) time: 0.1721 data: 0.0867 max mem: 9390 +Train: [95] [4600/6250] eta: 0:04:40 lr: 0.000001 grad: 0.1460 (0.1483) loss: 0.8128 (0.8137) time: 0.1740 data: 0.0895 max mem: 9390 +Train: [95] [4700/6250] eta: 0:04:23 lr: 0.000001 grad: 0.1344 (0.1483) loss: 0.8152 (0.8137) time: 0.2113 data: 0.1235 max mem: 9390 +Train: [95] [4800/6250] eta: 0:04:06 lr: 0.000001 grad: 0.1364 (0.1482) loss: 0.8137 (0.8137) time: 0.1918 data: 0.1096 max mem: 9390 +Train: [95] [4900/6250] eta: 0:03:49 lr: 0.000001 grad: 0.1351 (0.1480) loss: 0.8146 (0.8138) time: 0.1684 data: 0.0889 max mem: 9390 +Train: [95] [5000/6250] eta: 0:03:32 lr: 0.000001 grad: 0.1419 (0.1480) loss: 0.8133 (0.8138) time: 0.1682 data: 0.0863 max mem: 9390 +Train: [95] [5100/6250] eta: 0:03:15 lr: 0.000001 grad: 0.1449 (0.1480) loss: 0.8105 (0.8138) time: 0.1799 data: 0.0915 max mem: 9390 +Train: [95] [5200/6250] eta: 0:02:58 lr: 0.000001 grad: 0.1372 (0.1480) loss: 0.8187 (0.8139) time: 0.1897 data: 0.1024 max mem: 9390 +Train: [95] [5300/6250] eta: 0:02:41 lr: 0.000001 grad: 0.1437 (0.1480) loss: 0.8177 (0.8139) time: 0.1532 data: 0.0689 max mem: 9390 +Train: [95] [5400/6250] eta: 0:02:24 lr: 0.000001 grad: 0.1505 (0.1480) loss: 0.8182 (0.8140) time: 0.1711 data: 0.0805 max mem: 9390 +Train: [95] [5500/6250] eta: 0:02:07 lr: 0.000001 grad: 0.1469 (0.1481) loss: 0.8148 (0.8140) time: 0.1331 data: 0.0467 max mem: 9390 +Train: [95] [5600/6250] eta: 0:01:50 lr: 0.000001 grad: 0.1441 (0.1481) loss: 0.8175 (0.8140) time: 0.1447 data: 0.0542 max mem: 9390 +Train: [95] [5700/6250] eta: 0:01:33 lr: 0.000001 grad: 0.1503 (0.1481) loss: 0.8128 (0.8141) time: 0.1700 data: 0.0815 max mem: 9390 +Train: [95] [5800/6250] eta: 0:01:16 lr: 0.000001 grad: 0.1399 (0.1482) loss: 0.8148 (0.8141) time: 0.1550 data: 0.0670 max mem: 9390 +Train: [95] [5900/6250] eta: 0:00:59 lr: 0.000001 grad: 0.1486 (0.1483) loss: 0.8118 (0.8140) time: 0.1520 data: 0.0718 max mem: 9390 +Train: [95] [6000/6250] eta: 0:00:42 lr: 0.000001 grad: 0.1483 (0.1484) loss: 0.8093 (0.8140) time: 0.1746 data: 0.0774 max mem: 9390 +Train: [95] [6100/6250] eta: 0:00:25 lr: 0.000001 grad: 0.1573 (0.1484) loss: 0.8107 (0.8140) time: 0.1584 data: 0.0764 max mem: 9390 +Train: [95] [6200/6250] eta: 0:00:08 lr: 0.000001 grad: 0.1477 (0.1484) loss: 0.8138 (0.8140) time: 0.1329 data: 0.0415 max mem: 9390 +Train: [95] [6249/6250] eta: 0:00:00 lr: 0.000001 grad: 0.1346 (0.1484) loss: 0.8146 (0.8140) time: 0.1254 data: 0.0403 max mem: 9390 +Train: [95] Total time: 0:17:44 (0.1704 s / it) +Averaged stats: lr: 0.000001 grad: 0.1346 (0.1484) loss: 0.8146 (0.8140) +Eval (hcp-train-subset): [95] [ 0/62] eta: 0:06:18 loss: 0.8227 (0.8227) time: 6.1053 data: 6.0479 max mem: 9390 +Eval (hcp-train-subset): [95] [61/62] eta: 0:00:00 loss: 0.8139 (0.8154) time: 0.1327 data: 0.1076 max mem: 9390 +Eval (hcp-train-subset): [95] Total time: 0:00:14 (0.2399 s / it) +Averaged stats (hcp-train-subset): loss: 0.8139 (0.8154) +Eval (hcp-val): [95] [ 0/62] eta: 0:05:13 loss: 0.8236 (0.8236) time: 5.0607 data: 5.0300 max mem: 9390 +Eval (hcp-val): [95] [61/62] eta: 0:00:00 loss: 0.8270 (0.8276) time: 0.1438 data: 0.1183 max mem: 9390 +Eval (hcp-val): [95] Total time: 0:00:14 (0.2268 s / it) +Averaged stats (hcp-val): loss: 0.8270 (0.8276) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +Train: [96] [ 0/6250] eta: 6:28:37 lr: 0.000001 grad: 0.0935 (0.0935) loss: 0.8545 (0.8545) time: 3.7307 data: 3.5240 max mem: 9390 +Train: [96] [ 100/6250] eta: 0:23:25 lr: 0.000001 grad: 0.1879 (0.2142) loss: 0.8145 (0.8116) time: 0.1581 data: 0.0698 max mem: 9390 +Train: [96] [ 200/6250] eta: 0:20:04 lr: 0.000001 grad: 0.1532 (0.1979) loss: 0.8131 (0.8088) time: 0.1779 data: 0.0874 max mem: 9390 +Train: [96] [ 300/6250] eta: 0:18:48 lr: 0.000001 grad: 0.1397 (0.1879) loss: 0.8210 (0.8106) time: 0.1466 data: 0.0630 max mem: 9390 +Train: [96] [ 400/6250] eta: 0:17:57 lr: 0.000001 grad: 0.1354 (0.1783) loss: 0.8220 (0.8131) time: 0.1672 data: 0.0785 max mem: 9390 +Train: [96] [ 500/6250] eta: 0:17:14 lr: 0.000001 grad: 0.1384 (0.1715) loss: 0.8229 (0.8151) time: 0.1616 data: 0.0733 max mem: 9390 +Train: [96] [ 600/6250] eta: 0:16:43 lr: 0.000001 grad: 0.1314 (0.1686) loss: 0.8213 (0.8158) time: 0.1604 data: 0.0599 max mem: 9390 +Train: [96] [ 700/6250] eta: 0:16:25 lr: 0.000001 grad: 0.1536 (0.1664) loss: 0.8182 (0.8160) time: 0.1806 data: 0.0889 max mem: 9390 +Train: [96] [ 800/6250] eta: 0:16:04 lr: 0.000001 grad: 0.1551 (0.1648) loss: 0.8132 (0.8157) time: 0.1592 data: 0.0673 max mem: 9390 +Train: [96] [ 900/6250] eta: 0:15:48 lr: 0.000001 grad: 0.1480 (0.1634) loss: 0.8137 (0.8155) time: 0.1751 data: 0.0815 max mem: 9390 +Train: [96] [1000/6250] eta: 0:15:25 lr: 0.000001 grad: 0.1409 (0.1618) loss: 0.8132 (0.8155) time: 0.1640 data: 0.0774 max mem: 9390 +Train: [96] [1100/6250] eta: 0:15:05 lr: 0.000000 grad: 0.1424 (0.1604) loss: 0.8107 (0.8154) time: 0.1686 data: 0.0833 max mem: 9390 +Train: [96] [1200/6250] eta: 0:14:43 lr: 0.000000 grad: 0.1411 (0.1595) loss: 0.8169 (0.8153) time: 0.1723 data: 0.0842 max mem: 9390 +Train: [96] [1300/6250] eta: 0:14:24 lr: 0.000000 grad: 0.1364 (0.1585) loss: 0.8133 (0.8153) time: 0.1832 data: 0.1009 max mem: 9390 +Train: [96] [1400/6250] eta: 0:14:06 lr: 0.000000 grad: 0.1486 (0.1575) loss: 0.8174 (0.8153) time: 0.1868 data: 0.0997 max mem: 9390 +Train: [96] [1500/6250] eta: 0:13:49 lr: 0.000000 grad: 0.1473 (0.1566) loss: 0.8076 (0.8153) time: 0.1821 data: 0.0939 max mem: 9390 +Train: [96] [1600/6250] eta: 0:13:36 lr: 0.000000 grad: 0.1369 (0.1559) loss: 0.8200 (0.8154) time: 0.2182 data: 0.1332 max mem: 9390 +Train: [96] [1700/6250] eta: 0:13:17 lr: 0.000000 grad: 0.1457 (0.1555) loss: 0.8132 (0.8152) time: 0.1680 data: 0.0900 max mem: 9390 +Train: [96] [1800/6250] eta: 0:13:02 lr: 0.000000 grad: 0.1337 (0.1549) loss: 0.8249 (0.8152) time: 0.1747 data: 0.0896 max mem: 9390 +Train: [96] [1900/6250] eta: 0:12:45 lr: 0.000000 grad: 0.1358 (0.1546) loss: 0.8161 (0.8150) time: 0.1935 data: 0.1049 max mem: 9390 +Train: [96] [2000/6250] eta: 0:12:28 lr: 0.000000 grad: 0.1510 (0.1544) loss: 0.8157 (0.8148) time: 0.1409 data: 0.0591 max mem: 9390 +Train: [96] [2100/6250] eta: 0:12:13 lr: 0.000000 grad: 0.1431 (0.1541) loss: 0.8166 (0.8147) time: 0.1870 data: 0.0965 max mem: 9390 +Train: [96] [2200/6250] eta: 0:11:56 lr: 0.000000 grad: 0.1555 (0.1539) loss: 0.8089 (0.8146) time: 0.1672 data: 0.0773 max mem: 9390 +Train: [96] [2300/6250] eta: 0:11:38 lr: 0.000000 grad: 0.1384 (0.1537) loss: 0.8121 (0.8143) time: 0.1831 data: 0.1002 max mem: 9390 +Train: [96] [2400/6250] eta: 0:11:21 lr: 0.000000 grad: 0.1523 (0.1537) loss: 0.8084 (0.8140) time: 0.1618 data: 0.0750 max mem: 9390 +Train: [96] [2500/6250] eta: 0:11:05 lr: 0.000000 grad: 0.1457 (0.1537) loss: 0.7986 (0.8138) time: 0.1815 data: 0.0974 max mem: 9390 +Train: [96] [2600/6250] eta: 0:10:47 lr: 0.000000 grad: 0.1440 (0.1534) loss: 0.8106 (0.8136) time: 0.1536 data: 0.0596 max mem: 9390 +Train: [96] [2700/6250] eta: 0:10:31 lr: 0.000000 grad: 0.1370 (0.1531) loss: 0.8143 (0.8136) time: 0.1509 data: 0.0656 max mem: 9390 +Train: [96] [2800/6250] eta: 0:10:12 lr: 0.000000 grad: 0.1381 (0.1529) loss: 0.8154 (0.8136) time: 0.1824 data: 0.0960 max mem: 9390 +Train: [96] [2900/6250] eta: 0:09:55 lr: 0.000000 grad: 0.1406 (0.1527) loss: 0.8107 (0.8136) time: 0.1797 data: 0.0945 max mem: 9390 +Train: [96] [3000/6250] eta: 0:09:37 lr: 0.000000 grad: 0.1413 (0.1525) loss: 0.8172 (0.8135) time: 0.1982 data: 0.1071 max mem: 9390 +Train: [96] [3100/6250] eta: 0:09:20 lr: 0.000000 grad: 0.1360 (0.1523) loss: 0.8137 (0.8136) time: 0.2013 data: 0.1190 max mem: 9390 +Train: [96] [3200/6250] eta: 0:09:02 lr: 0.000000 grad: 0.1374 (0.1521) loss: 0.8205 (0.8136) time: 0.1934 data: 0.1068 max mem: 9390 +Train: [96] [3300/6250] eta: 0:08:44 lr: 0.000000 grad: 0.1309 (0.1518) loss: 0.8150 (0.8136) time: 0.1775 data: 0.0854 max mem: 9390 +Train: [96] [3400/6250] eta: 0:08:26 lr: 0.000000 grad: 0.1455 (0.1516) loss: 0.8149 (0.8136) time: 0.1754 data: 0.0818 max mem: 9390 +Train: [96] [3500/6250] eta: 0:08:09 lr: 0.000000 grad: 0.1404 (0.1514) loss: 0.8164 (0.8137) time: 0.1994 data: 0.1052 max mem: 9390 +Train: [96] [3600/6250] eta: 0:07:51 lr: 0.000000 grad: 0.1447 (0.1512) loss: 0.8149 (0.8137) time: 0.1985 data: 0.1089 max mem: 9390 +Train: [96] [3700/6250] eta: 0:07:33 lr: 0.000000 grad: 0.1336 (0.1511) loss: 0.8130 (0.8136) time: 0.1824 data: 0.0853 max mem: 9390 +Train: [96] [3800/6250] eta: 0:07:15 lr: 0.000000 grad: 0.1430 (0.1509) loss: 0.8192 (0.8137) time: 0.1801 data: 0.0975 max mem: 9390 +Train: [96] [3900/6250] eta: 0:06:58 lr: 0.000000 grad: 0.1390 (0.1508) loss: 0.8158 (0.8137) time: 0.2109 data: 0.1190 max mem: 9390 +Train: [96] [4000/6250] eta: 0:06:41 lr: 0.000000 grad: 0.1383 (0.1506) loss: 0.8191 (0.8138) time: 0.1807 data: 0.0651 max mem: 9390 +Train: [96] [4100/6250] eta: 0:06:23 lr: 0.000000 grad: 0.1403 (0.1505) loss: 0.8156 (0.8138) time: 0.1625 data: 0.0742 max mem: 9390 +Train: [96] [4200/6250] eta: 0:06:05 lr: 0.000000 grad: 0.1357 (0.1502) loss: 0.8187 (0.8139) time: 0.1918 data: 0.1025 max mem: 9390 +Train: [96] [4300/6250] eta: 0:05:48 lr: 0.000000 grad: 0.1382 (0.1500) loss: 0.8190 (0.8139) time: 0.1545 data: 0.0456 max mem: 9390 +Train: [96] [4400/6250] eta: 0:05:30 lr: 0.000000 grad: 0.1467 (0.1499) loss: 0.8182 (0.8139) time: 0.1859 data: 0.0938 max mem: 9390 +Train: [96] [4500/6250] eta: 0:05:12 lr: 0.000000 grad: 0.1383 (0.1499) loss: 0.8075 (0.8139) time: 0.1768 data: 0.0892 max mem: 9390 +Train: [96] [4600/6250] eta: 0:04:54 lr: 0.000000 grad: 0.1455 (0.1498) loss: 0.8136 (0.8139) time: 0.1770 data: 0.0892 max mem: 9390 +Train: [96] [4700/6250] eta: 0:04:36 lr: 0.000000 grad: 0.1441 (0.1497) loss: 0.8151 (0.8139) time: 0.1735 data: 0.0837 max mem: 9390 +Train: [96] [4800/6250] eta: 0:04:19 lr: 0.000000 grad: 0.1369 (0.1496) loss: 0.8157 (0.8139) time: 0.1712 data: 0.0895 max mem: 9390 +Train: [96] [4900/6250] eta: 0:04:01 lr: 0.000000 grad: 0.1335 (0.1496) loss: 0.8130 (0.8140) time: 0.1977 data: 0.1139 max mem: 9390 +Train: [96] [5000/6250] eta: 0:03:43 lr: 0.000000 grad: 0.1380 (0.1495) loss: 0.8184 (0.8140) time: 0.1672 data: 0.0772 max mem: 9390 +Train: [96] [5100/6250] eta: 0:03:25 lr: 0.000000 grad: 0.1395 (0.1494) loss: 0.8152 (0.8140) time: 0.1823 data: 0.1001 max mem: 9390 +Train: [96] [5200/6250] eta: 0:03:08 lr: 0.000000 grad: 0.1293 (0.1493) loss: 0.8129 (0.8141) time: 0.2141 data: 0.1143 max mem: 9390 +Train: [96] [5300/6250] eta: 0:02:50 lr: 0.000000 grad: 0.1448 (0.1492) loss: 0.8092 (0.8141) time: 0.1417 data: 0.0609 max mem: 9390 +Train: [96] [5400/6250] eta: 0:02:32 lr: 0.000000 grad: 0.1374 (0.1491) loss: 0.8152 (0.8141) time: 0.1603 data: 0.0626 max mem: 9390 +Train: [96] [5500/6250] eta: 0:02:14 lr: 0.000000 grad: 0.1301 (0.1491) loss: 0.8182 (0.8142) time: 0.2000 data: 0.1061 max mem: 9390 +Train: [96] [5600/6250] eta: 0:01:56 lr: 0.000000 grad: 0.1365 (0.1489) loss: 0.8168 (0.8142) time: 0.2233 data: 0.0801 max mem: 9390 +Train: [96] [5700/6250] eta: 0:01:38 lr: 0.000000 grad: 0.1374 (0.1488) loss: 0.8113 (0.8143) time: 0.1719 data: 0.0789 max mem: 9390 +Train: [96] [5800/6250] eta: 0:01:20 lr: 0.000000 grad: 0.1334 (0.1487) loss: 0.8164 (0.8143) time: 0.1756 data: 0.0859 max mem: 9390 +Train: [96] [5900/6250] eta: 0:01:02 lr: 0.000000 grad: 0.1447 (0.1486) loss: 0.8141 (0.8143) time: 0.1880 data: 0.0946 max mem: 9390 +Train: [96] [6000/6250] eta: 0:00:44 lr: 0.000000 grad: 0.1387 (0.1485) loss: 0.8158 (0.8144) time: 0.1683 data: 0.0830 max mem: 9390 +Train: [96] [6100/6250] eta: 0:00:26 lr: 0.000000 grad: 0.1456 (0.1484) loss: 0.8162 (0.8144) time: 0.1561 data: 0.0792 max mem: 9390 +Train: [96] [6200/6250] eta: 0:00:08 lr: 0.000000 grad: 0.1327 (0.1482) loss: 0.8171 (0.8144) time: 0.1703 data: 0.0818 max mem: 9390 +Train: [96] [6249/6250] eta: 0:00:00 lr: 0.000000 grad: 0.1386 (0.1482) loss: 0.8190 (0.8144) time: 0.1554 data: 0.0711 max mem: 9390 +Train: [96] Total time: 0:18:47 (0.1804 s / it) +Averaged stats: lr: 0.000000 grad: 0.1386 (0.1482) loss: 0.8190 (0.8144) +Eval (hcp-train-subset): [96] [ 0/62] eta: 0:05:36 loss: 0.8193 (0.8193) time: 5.4280 data: 5.3867 max mem: 9390 +Eval (hcp-train-subset): [96] [61/62] eta: 0:00:00 loss: 0.8129 (0.8151) time: 0.1503 data: 0.1243 max mem: 9390 +Eval (hcp-train-subset): [96] Total time: 0:00:14 (0.2307 s / it) +Averaged stats (hcp-train-subset): loss: 0.8129 (0.8151) +Eval (hcp-val): [96] [ 0/62] eta: 0:04:35 loss: 0.8227 (0.8227) time: 4.4491 data: 4.4200 max mem: 9390 +Eval (hcp-val): [96] [61/62] eta: 0:00:00 loss: 0.8266 (0.8276) time: 0.1226 data: 0.0948 max mem: 9390 +Eval (hcp-val): [96] Total time: 0:00:13 (0.2129 s / it) +Averaged stats (hcp-val): loss: 0.8266 (0.8276) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +Train: [97] [ 0/6250] eta: 6:58:01 lr: 0.000000 grad: 0.5210 (0.5210) loss: 0.7731 (0.7731) time: 4.0130 data: 3.8527 max mem: 9390 +Train: [97] [ 100/6250] eta: 0:22:21 lr: 0.000000 grad: 0.1652 (0.1666) loss: 0.8158 (0.8145) time: 0.1690 data: 0.0795 max mem: 9390 +Train: [97] [ 200/6250] eta: 0:19:41 lr: 0.000000 grad: 0.1854 (0.1843) loss: 0.8088 (0.8088) time: 0.1931 data: 0.1003 max mem: 9390 +Train: [97] [ 300/6250] eta: 0:18:53 lr: 0.000000 grad: 0.1699 (0.1843) loss: 0.8127 (0.8082) time: 0.1824 data: 0.1068 max mem: 9390 +Train: [97] [ 400/6250] eta: 0:18:26 lr: 0.000000 grad: 0.1539 (0.1794) loss: 0.8005 (0.8089) time: 0.1923 data: 0.0840 max mem: 9390 +Train: [97] [ 500/6250] eta: 0:17:49 lr: 0.000000 grad: 0.1581 (0.1752) loss: 0.8105 (0.8091) time: 0.1661 data: 0.0796 max mem: 9390 +Train: [97] [ 600/6250] eta: 0:17:15 lr: 0.000000 grad: 0.1488 (0.1714) loss: 0.8132 (0.8099) time: 0.1565 data: 0.0769 max mem: 9390 +Train: [97] [ 700/6250] eta: 0:16:42 lr: 0.000000 grad: 0.1349 (0.1673) loss: 0.8189 (0.8109) time: 0.1661 data: 0.0782 max mem: 9390 +Train: [97] [ 800/6250] eta: 0:16:21 lr: 0.000000 grad: 0.1312 (0.1638) loss: 0.8197 (0.8118) time: 0.2001 data: 0.1136 max mem: 9390 +Train: [97] [ 900/6250] eta: 0:15:52 lr: 0.000000 grad: 0.1390 (0.1615) loss: 0.8163 (0.8126) time: 0.1597 data: 0.0671 max mem: 9390 +Train: [97] [1000/6250] eta: 0:15:25 lr: 0.000000 grad: 0.1317 (0.1595) loss: 0.8245 (0.8136) time: 0.1681 data: 0.0722 max mem: 9390 +Train: [97] [1100/6250] eta: 0:15:02 lr: 0.000000 grad: 0.1473 (0.1575) loss: 0.8178 (0.8145) time: 0.1680 data: 0.0663 max mem: 9390 +Train: [97] [1200/6250] eta: 0:14:53 lr: 0.000000 grad: 0.1316 (0.1555) loss: 0.8240 (0.8152) time: 0.1838 data: 0.0874 max mem: 9390 +Train: [97] [1300/6250] eta: 0:14:34 lr: 0.000000 grad: 0.1282 (0.1537) loss: 0.8258 (0.8158) time: 0.1757 data: 0.0699 max mem: 9390 +Train: [97] [1400/6250] eta: 0:14:13 lr: 0.000000 grad: 0.1300 (0.1525) loss: 0.8227 (0.8161) time: 0.1832 data: 0.0973 max mem: 9390 +Train: [97] [1500/6250] eta: 0:13:53 lr: 0.000000 grad: 0.1356 (0.1514) loss: 0.8177 (0.8164) time: 0.1740 data: 0.0828 max mem: 9390 +Train: [97] [1600/6250] eta: 0:13:35 lr: 0.000000 grad: 0.1344 (0.1505) loss: 0.8208 (0.8166) time: 0.1657 data: 0.0642 max mem: 9390 +Train: [97] [1700/6250] eta: 0:13:16 lr: 0.000000 grad: 0.1285 (0.1496) loss: 0.8190 (0.8168) time: 0.1614 data: 0.0655 max mem: 9390 +Train: [97] [1800/6250] eta: 0:12:58 lr: 0.000000 grad: 0.1242 (0.1490) loss: 0.8228 (0.8170) time: 0.1724 data: 0.0758 max mem: 9390 +Train: [97] [1900/6250] eta: 0:12:39 lr: 0.000000 grad: 0.1440 (0.1484) loss: 0.8195 (0.8170) time: 0.1518 data: 0.0564 max mem: 9390 +Train: [97] [2000/6250] eta: 0:12:20 lr: 0.000000 grad: 0.1307 (0.1479) loss: 0.8173 (0.8170) time: 0.1589 data: 0.0618 max mem: 9390 +Train: [97] [2100/6250] eta: 0:12:02 lr: 0.000000 grad: 0.1437 (0.1476) loss: 0.8148 (0.8169) time: 0.1854 data: 0.0929 max mem: 9390 +Train: [97] [2200/6250] eta: 0:11:44 lr: 0.000000 grad: 0.1433 (0.1474) loss: 0.8114 (0.8168) time: 0.1595 data: 0.0562 max mem: 9390 +Train: [97] [2300/6250] eta: 0:11:27 lr: 0.000000 grad: 0.1360 (0.1473) loss: 0.8153 (0.8168) time: 0.1686 data: 0.0779 max mem: 9390 +Train: [97] [2400/6250] eta: 0:11:09 lr: 0.000000 grad: 0.1375 (0.1471) loss: 0.8157 (0.8167) time: 0.1800 data: 0.0826 max mem: 9390 +Train: [97] [2500/6250] eta: 0:10:50 lr: 0.000000 grad: 0.1361 (0.1468) loss: 0.8154 (0.8167) time: 0.1746 data: 0.0927 max mem: 9390 +Train: [97] [2600/6250] eta: 0:10:32 lr: 0.000000 grad: 0.1441 (0.1465) loss: 0.8135 (0.8168) time: 0.1681 data: 0.0670 max mem: 9390 +Train: [97] [2700/6250] eta: 0:10:13 lr: 0.000000 grad: 0.1321 (0.1464) loss: 0.8184 (0.8168) time: 0.1624 data: 0.0746 max mem: 9390 +Train: [97] [2800/6250] eta: 0:09:55 lr: 0.000000 grad: 0.1314 (0.1463) loss: 0.8161 (0.8167) time: 0.1529 data: 0.0493 max mem: 9390 +Train: [97] [2900/6250] eta: 0:09:36 lr: 0.000000 grad: 0.1350 (0.1462) loss: 0.8148 (0.8167) time: 0.1551 data: 0.0689 max mem: 9390 +Train: [97] [3000/6250] eta: 0:09:19 lr: 0.000000 grad: 0.1351 (0.1461) loss: 0.8205 (0.8167) time: 0.1719 data: 0.0803 max mem: 9390 +Train: [97] [3100/6250] eta: 0:09:00 lr: 0.000000 grad: 0.1397 (0.1460) loss: 0.8194 (0.8167) time: 0.1583 data: 0.0682 max mem: 9390 +Train: [97] [3200/6250] eta: 0:08:42 lr: 0.000000 grad: 0.1437 (0.1459) loss: 0.8110 (0.8166) time: 0.1610 data: 0.0723 max mem: 9390 +Train: [97] [3300/6250] eta: 0:08:25 lr: 0.000000 grad: 0.1404 (0.1460) loss: 0.8150 (0.8166) time: 0.1803 data: 0.0953 max mem: 9390 +Train: [97] [3400/6250] eta: 0:08:08 lr: 0.000000 grad: 0.1387 (0.1459) loss: 0.8169 (0.8166) time: 0.1780 data: 0.0837 max mem: 9390 +Train: [97] [3500/6250] eta: 0:07:50 lr: 0.000000 grad: 0.1483 (0.1459) loss: 0.8162 (0.8165) time: 0.1776 data: 0.0943 max mem: 9390 +Train: [97] [3600/6250] eta: 0:07:33 lr: 0.000000 grad: 0.1400 (0.1458) loss: 0.8202 (0.8165) time: 0.1876 data: 0.1091 max mem: 9390 +Train: [97] [3700/6250] eta: 0:07:16 lr: 0.000000 grad: 0.1450 (0.1458) loss: 0.8121 (0.8164) time: 0.1701 data: 0.0748 max mem: 9390 +Train: [97] [3800/6250] eta: 0:06:58 lr: 0.000000 grad: 0.1431 (0.1458) loss: 0.8148 (0.8164) time: 0.1468 data: 0.0541 max mem: 9390 +Train: [97] [3900/6250] eta: 0:06:40 lr: 0.000000 grad: 0.1418 (0.1458) loss: 0.8105 (0.8163) time: 0.1643 data: 0.0749 max mem: 9390 +Train: [97] [4000/6250] eta: 0:06:23 lr: 0.000000 grad: 0.1460 (0.1459) loss: 0.8128 (0.8162) time: 0.1685 data: 0.0778 max mem: 9390 +Train: [97] [4100/6250] eta: 0:06:06 lr: 0.000000 grad: 0.1476 (0.1459) loss: 0.8143 (0.8162) time: 0.1547 data: 0.0713 max mem: 9390 +Train: [97] [4200/6250] eta: 0:05:48 lr: 0.000000 grad: 0.1437 (0.1459) loss: 0.8103 (0.8161) time: 0.1605 data: 0.0737 max mem: 9390 +Train: [97] [4300/6250] eta: 0:05:31 lr: 0.000000 grad: 0.1414 (0.1460) loss: 0.8148 (0.8161) time: 0.1713 data: 0.0882 max mem: 9390 +Train: [97] [4400/6250] eta: 0:05:14 lr: 0.000000 grad: 0.1456 (0.1461) loss: 0.8198 (0.8161) time: 0.1542 data: 0.0689 max mem: 9390 +Train: [97] [4500/6250] eta: 0:04:57 lr: 0.000000 grad: 0.1570 (0.1462) loss: 0.8111 (0.8161) time: 0.1747 data: 0.0895 max mem: 9390 +Train: [97] [4600/6250] eta: 0:04:40 lr: 0.000000 grad: 0.1347 (0.1462) loss: 0.8174 (0.8161) time: 0.1644 data: 0.0753 max mem: 9390 +Train: [97] [4700/6250] eta: 0:04:22 lr: 0.000000 grad: 0.1446 (0.1462) loss: 0.8174 (0.8161) time: 0.1670 data: 0.0747 max mem: 9390 +Train: [97] [4800/6250] eta: 0:04:05 lr: 0.000000 grad: 0.1396 (0.1462) loss: 0.8167 (0.8161) time: 0.1627 data: 0.0724 max mem: 9390 +Train: [97] [4900/6250] eta: 0:03:48 lr: 0.000000 grad: 0.1429 (0.1463) loss: 0.8169 (0.8161) time: 0.1900 data: 0.1010 max mem: 9390 +Train: [97] [5000/6250] eta: 0:03:31 lr: 0.000000 grad: 0.1384 (0.1464) loss: 0.8187 (0.8160) time: 0.1853 data: 0.1010 max mem: 9390 +Train: [97] [5100/6250] eta: 0:03:14 lr: 0.000000 grad: 0.1547 (0.1464) loss: 0.8093 (0.8160) time: 0.1786 data: 0.0967 max mem: 9390 +Train: [97] [5200/6250] eta: 0:02:57 lr: 0.000000 grad: 0.1462 (0.1465) loss: 0.8141 (0.8160) time: 0.1567 data: 0.0534 max mem: 9390 +Train: [97] [5300/6250] eta: 0:02:40 lr: 0.000000 grad: 0.1500 (0.1466) loss: 0.8115 (0.8160) time: 0.1604 data: 0.0707 max mem: 9390 +Train: [97] [5400/6250] eta: 0:02:23 lr: 0.000000 grad: 0.1544 (0.1467) loss: 0.8121 (0.8159) time: 0.1670 data: 0.0827 max mem: 9390 +Train: [97] [5500/6250] eta: 0:02:06 lr: 0.000000 grad: 0.1524 (0.1468) loss: 0.8149 (0.8159) time: 0.1550 data: 0.0674 max mem: 9390 +Train: [97] [5600/6250] eta: 0:01:49 lr: 0.000000 grad: 0.1474 (0.1470) loss: 0.8146 (0.8159) time: 0.1616 data: 0.0753 max mem: 9390 +Train: [97] [5700/6250] eta: 0:01:32 lr: 0.000000 grad: 0.1516 (0.1471) loss: 0.8135 (0.8159) time: 0.1812 data: 0.0897 max mem: 9390 +Train: [97] [5800/6250] eta: 0:01:15 lr: 0.000000 grad: 0.1568 (0.1472) loss: 0.8128 (0.8159) time: 0.1631 data: 0.0684 max mem: 9390 +Train: [97] [5900/6250] eta: 0:00:58 lr: 0.000000 grad: 0.1520 (0.1474) loss: 0.8144 (0.8158) time: 0.1602 data: 0.0726 max mem: 9390 +Train: [97] [6000/6250] eta: 0:00:42 lr: 0.000000 grad: 0.1537 (0.1476) loss: 0.8159 (0.8157) time: 0.1737 data: 0.0963 max mem: 9390 +Train: [97] [6100/6250] eta: 0:00:25 lr: 0.000000 grad: 0.1405 (0.1476) loss: 0.8130 (0.8157) time: 0.1650 data: 0.0733 max mem: 9390 +Train: [97] [6200/6250] eta: 0:00:08 lr: 0.000000 grad: 0.1539 (0.1477) loss: 0.8159 (0.8157) time: 0.1683 data: 0.0815 max mem: 9390 +Train: [97] [6249/6250] eta: 0:00:00 lr: 0.000000 grad: 0.1384 (0.1477) loss: 0.8128 (0.8157) time: 0.1575 data: 0.0686 max mem: 9390 +Train: [97] Total time: 0:17:38 (0.1693 s / it) +Averaged stats: lr: 0.000000 grad: 0.1384 (0.1477) loss: 0.8128 (0.8157) +Eval (hcp-train-subset): [97] [ 0/62] eta: 0:05:42 loss: 0.8224 (0.8224) time: 5.5285 data: 5.4979 max mem: 9390 +Eval (hcp-train-subset): [97] [61/62] eta: 0:00:00 loss: 0.8118 (0.8150) time: 0.1509 data: 0.1248 max mem: 9390 +Eval (hcp-train-subset): [97] Total time: 0:00:14 (0.2414 s / it) +Averaged stats (hcp-train-subset): loss: 0.8118 (0.8150) +Eval (hcp-val): [97] [ 0/62] eta: 0:04:14 loss: 0.8219 (0.8219) time: 4.1037 data: 4.0507 max mem: 9390 +Eval (hcp-val): [97] [61/62] eta: 0:00:00 loss: 0.8258 (0.8279) time: 0.1450 data: 0.1199 max mem: 9390 +Eval (hcp-val): [97] Total time: 0:00:13 (0.2144 s / it) +Averaged stats (hcp-val): loss: 0.8258 (0.8279) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +Train: [98] [ 0/6250] eta: 10:10:48 lr: 0.000000 grad: 0.2361 (0.2361) loss: 0.8008 (0.8008) time: 5.8637 data: 5.7725 max mem: 9390 +Train: [98] [ 100/6250] eta: 0:21:53 lr: 0.000000 grad: 0.1727 (0.2116) loss: 0.8220 (0.8163) time: 0.1828 data: 0.0876 max mem: 9390 +Train: [98] [ 200/6250] eta: 0:19:30 lr: 0.000000 grad: 0.1879 (0.2045) loss: 0.8098 (0.8122) time: 0.1598 data: 0.0745 max mem: 9390 +Train: [98] [ 300/6250] eta: 0:18:18 lr: 0.000000 grad: 0.1707 (0.1978) loss: 0.8055 (0.8114) time: 0.1580 data: 0.0613 max mem: 9390 +Train: [98] [ 400/6250] eta: 0:17:43 lr: 0.000000 grad: 0.1516 (0.1917) loss: 0.8163 (0.8118) time: 0.1534 data: 0.0591 max mem: 9390 +Train: [98] [ 500/6250] eta: 0:17:06 lr: 0.000000 grad: 0.1416 (0.1871) loss: 0.8166 (0.8124) time: 0.1618 data: 0.0639 max mem: 9390 +Train: [98] [ 600/6250] eta: 0:16:38 lr: 0.000000 grad: 0.1504 (0.1828) loss: 0.8162 (0.8126) time: 0.1723 data: 0.0693 max mem: 9390 +Train: [98] [ 700/6250] eta: 0:16:17 lr: 0.000000 grad: 0.1384 (0.1793) loss: 0.8165 (0.8127) time: 0.1911 data: 0.0966 max mem: 9390 +Train: [98] [ 800/6250] eta: 0:15:51 lr: 0.000000 grad: 0.1505 (0.1761) loss: 0.8163 (0.8130) time: 0.1647 data: 0.0766 max mem: 9390 +Train: [98] [ 900/6250] eta: 0:15:35 lr: 0.000000 grad: 0.1402 (0.1731) loss: 0.8162 (0.8135) time: 0.1697 data: 0.0727 max mem: 9390 +Train: [98] [1000/6250] eta: 0:15:13 lr: 0.000000 grad: 0.1413 (0.1705) loss: 0.8165 (0.8140) time: 0.1660 data: 0.0694 max mem: 9390 +Train: [98] [1100/6250] eta: 0:14:50 lr: 0.000000 grad: 0.1396 (0.1681) loss: 0.8199 (0.8143) time: 0.1553 data: 0.0636 max mem: 9390 +Train: [98] [1200/6250] eta: 0:14:30 lr: 0.000000 grad: 0.1411 (0.1664) loss: 0.8139 (0.8144) time: 0.1435 data: 0.0593 max mem: 9390 +Train: [98] [1300/6250] eta: 0:14:09 lr: 0.000000 grad: 0.1301 (0.1648) loss: 0.8192 (0.8147) time: 0.1639 data: 0.0819 max mem: 9390 +Train: [98] [1400/6250] eta: 0:13:49 lr: 0.000000 grad: 0.1391 (0.1637) loss: 0.8226 (0.8149) time: 0.1446 data: 0.0555 max mem: 9390 +Train: [98] [1500/6250] eta: 0:13:29 lr: 0.000000 grad: 0.1421 (0.1627) loss: 0.8169 (0.8150) time: 0.1473 data: 0.0607 max mem: 9390 +Train: [98] [1600/6250] eta: 0:13:10 lr: 0.000000 grad: 0.1429 (0.1614) loss: 0.8197 (0.8152) time: 0.1542 data: 0.0611 max mem: 9390 +Train: [98] [1700/6250] eta: 0:12:50 lr: 0.000000 grad: 0.1327 (0.1606) loss: 0.8207 (0.8152) time: 0.1701 data: 0.0838 max mem: 9390 +Train: [98] [1800/6250] eta: 0:12:30 lr: 0.000000 grad: 0.1465 (0.1599) loss: 0.8100 (0.8151) time: 0.1505 data: 0.0674 max mem: 9390 +Train: [98] [1900/6250] eta: 0:12:13 lr: 0.000000 grad: 0.1407 (0.1592) loss: 0.8171 (0.8151) time: 0.1604 data: 0.0654 max mem: 9390 +Train: [98] [2000/6250] eta: 0:11:55 lr: 0.000000 grad: 0.1382 (0.1585) loss: 0.8201 (0.8150) time: 0.1738 data: 0.0963 max mem: 9390 +Train: [98] [2100/6250] eta: 0:11:37 lr: 0.000000 grad: 0.1418 (0.1579) loss: 0.8109 (0.8150) time: 0.1595 data: 0.0769 max mem: 9390 +Train: [98] [2200/6250] eta: 0:11:20 lr: 0.000000 grad: 0.1291 (0.1573) loss: 0.8167 (0.8149) time: 0.1868 data: 0.1041 max mem: 9390 +Train: [98] [2300/6250] eta: 0:11:02 lr: 0.000000 grad: 0.1333 (0.1566) loss: 0.8137 (0.8149) time: 0.1427 data: 0.0421 max mem: 9390 +Train: [98] [2400/6250] eta: 0:10:45 lr: 0.000000 grad: 0.1463 (0.1561) loss: 0.8123 (0.8147) time: 0.1423 data: 0.0559 max mem: 9390 +Train: [98] [2500/6250] eta: 0:10:27 lr: 0.000000 grad: 0.1447 (0.1557) loss: 0.8179 (0.8147) time: 0.1543 data: 0.0614 max mem: 9390 +Train: [98] [2600/6250] eta: 0:10:10 lr: 0.000000 grad: 0.1447 (0.1555) loss: 0.8119 (0.8147) time: 0.1567 data: 0.0719 max mem: 9390 +Train: [98] [2700/6250] eta: 0:09:53 lr: 0.000000 grad: 0.1399 (0.1554) loss: 0.8178 (0.8147) time: 0.1573 data: 0.0706 max mem: 9390 +Train: [98] [2800/6250] eta: 0:09:37 lr: 0.000000 grad: 0.1384 (0.1550) loss: 0.8170 (0.8148) time: 0.1999 data: 0.0610 max mem: 9390 +Train: [98] [2900/6250] eta: 0:09:20 lr: 0.000000 grad: 0.1418 (0.1547) loss: 0.8208 (0.8149) time: 0.1582 data: 0.0691 max mem: 9390 +Train: [98] [3000/6250] eta: 0:09:02 lr: 0.000000 grad: 0.1383 (0.1544) loss: 0.8165 (0.8150) time: 0.1729 data: 0.0825 max mem: 9390 +Train: [98] [3100/6250] eta: 0:08:45 lr: 0.000000 grad: 0.1381 (0.1541) loss: 0.8188 (0.8151) time: 0.1662 data: 0.0640 max mem: 9390 +Train: [98] [3200/6250] eta: 0:08:29 lr: 0.000000 grad: 0.1463 (0.1539) loss: 0.8140 (0.8152) time: 0.1700 data: 0.0787 max mem: 9390 +Train: [98] [3300/6250] eta: 0:08:12 lr: 0.000000 grad: 0.1612 (0.1538) loss: 0.8231 (0.8153) time: 0.1570 data: 0.0631 max mem: 9390 +Train: [98] [3400/6250] eta: 0:07:54 lr: 0.000000 grad: 0.1490 (0.1536) loss: 0.8194 (0.8154) time: 0.1635 data: 0.0753 max mem: 9390 +Train: [98] [3500/6250] eta: 0:07:38 lr: 0.000000 grad: 0.1372 (0.1535) loss: 0.8203 (0.8155) time: 0.1781 data: 0.0900 max mem: 9390 +Train: [98] [3600/6250] eta: 0:07:22 lr: 0.000000 grad: 0.1408 (0.1533) loss: 0.8195 (0.8155) time: 0.2496 data: 0.1638 max mem: 9390 +Train: [98] [3700/6250] eta: 0:07:05 lr: 0.000000 grad: 0.1464 (0.1530) loss: 0.8173 (0.8156) time: 0.1860 data: 0.0896 max mem: 9390 +Train: [98] [3800/6250] eta: 0:06:48 lr: 0.000000 grad: 0.1410 (0.1527) loss: 0.8162 (0.8157) time: 0.1648 data: 0.0734 max mem: 9390 +Train: [98] [3900/6250] eta: 0:06:31 lr: 0.000000 grad: 0.1327 (0.1524) loss: 0.8195 (0.8158) time: 0.1784 data: 0.0893 max mem: 9390 +Train: [98] [4000/6250] eta: 0:06:15 lr: 0.000000 grad: 0.1405 (0.1522) loss: 0.8122 (0.8158) time: 0.1695 data: 0.0851 max mem: 9390 +Train: [98] [4100/6250] eta: 0:05:58 lr: 0.000000 grad: 0.1535 (0.1519) loss: 0.8226 (0.8159) time: 0.1646 data: 0.0714 max mem: 9390 +Train: [98] [4200/6250] eta: 0:05:41 lr: 0.000000 grad: 0.1374 (0.1516) loss: 0.8148 (0.8159) time: 0.1907 data: 0.0950 max mem: 9390 +Train: [98] [4300/6250] eta: 0:05:24 lr: 0.000000 grad: 0.1325 (0.1514) loss: 0.8194 (0.8159) time: 0.1594 data: 0.0719 max mem: 9390 +Train: [98] [4400/6250] eta: 0:05:07 lr: 0.000000 grad: 0.1426 (0.1512) loss: 0.8171 (0.8160) time: 0.1414 data: 0.0433 max mem: 9390 +Train: [98] [4500/6250] eta: 0:04:51 lr: 0.000000 grad: 0.1338 (0.1509) loss: 0.8177 (0.8160) time: 0.1517 data: 0.0590 max mem: 9390 +Train: [98] [4600/6250] eta: 0:04:34 lr: 0.000000 grad: 0.1449 (0.1507) loss: 0.8201 (0.8160) time: 0.1747 data: 0.0885 max mem: 9390 +Train: [98] [4700/6250] eta: 0:04:17 lr: 0.000000 grad: 0.1348 (0.1505) loss: 0.8172 (0.8160) time: 0.1785 data: 0.0955 max mem: 9390 +Train: [98] [4800/6250] eta: 0:04:01 lr: 0.000000 grad: 0.1459 (0.1504) loss: 0.8146 (0.8161) time: 0.1641 data: 0.0778 max mem: 9390 +Train: [98] [4900/6250] eta: 0:03:44 lr: 0.000000 grad: 0.1375 (0.1503) loss: 0.8195 (0.8161) time: 0.1805 data: 0.0967 max mem: 9390 +Train: [98] [5000/6250] eta: 0:03:28 lr: 0.000000 grad: 0.1411 (0.1503) loss: 0.8166 (0.8160) time: 0.1661 data: 0.0784 max mem: 9390 +Train: [98] [5100/6250] eta: 0:03:11 lr: 0.000000 grad: 0.1401 (0.1503) loss: 0.8175 (0.8160) time: 0.1748 data: 0.0957 max mem: 9390 +Train: [98] [5200/6250] eta: 0:02:54 lr: 0.000000 grad: 0.1502 (0.1503) loss: 0.8128 (0.8160) time: 0.1576 data: 0.0692 max mem: 9390 +Train: [98] [5300/6250] eta: 0:02:38 lr: 0.000000 grad: 0.1508 (0.1502) loss: 0.8161 (0.8159) time: 0.1580 data: 0.0746 max mem: 9390 +Train: [98] [5400/6250] eta: 0:02:21 lr: 0.000000 grad: 0.1386 (0.1502) loss: 0.8132 (0.8159) time: 0.1485 data: 0.0623 max mem: 9390 +Train: [98] [5500/6250] eta: 0:02:04 lr: 0.000000 grad: 0.1355 (0.1502) loss: 0.8160 (0.8158) time: 0.1568 data: 0.0653 max mem: 9390 +Train: [98] [5600/6250] eta: 0:01:48 lr: 0.000000 grad: 0.1520 (0.1502) loss: 0.8112 (0.8158) time: 0.1514 data: 0.0696 max mem: 9390 +Train: [98] [5700/6250] eta: 0:01:31 lr: 0.000000 grad: 0.1388 (0.1501) loss: 0.8108 (0.8158) time: 0.2048 data: 0.1124 max mem: 9390 +Train: [98] [5800/6250] eta: 0:01:15 lr: 0.000000 grad: 0.1395 (0.1501) loss: 0.8125 (0.8157) time: 0.1860 data: 0.1038 max mem: 9390 +Train: [98] [5900/6250] eta: 0:00:58 lr: 0.000000 grad: 0.1455 (0.1500) loss: 0.8093 (0.8157) time: 0.1503 data: 0.0692 max mem: 9390 +Train: [98] [6000/6250] eta: 0:00:41 lr: 0.000000 grad: 0.1464 (0.1499) loss: 0.8159 (0.8157) time: 0.1572 data: 0.0654 max mem: 9390 +Train: [98] [6100/6250] eta: 0:00:24 lr: 0.000000 grad: 0.1601 (0.1499) loss: 0.8099 (0.8156) time: 0.1404 data: 0.0589 max mem: 9390 +Train: [98] [6200/6250] eta: 0:00:08 lr: 0.000000 grad: 0.1422 (0.1499) loss: 0.8092 (0.8156) time: 0.1608 data: 0.0638 max mem: 9390 +Train: [98] [6249/6250] eta: 0:00:00 lr: 0.000000 grad: 0.1422 (0.1499) loss: 0.8151 (0.8156) time: 0.1766 data: 0.0766 max mem: 9390 +Train: [98] Total time: 0:17:27 (0.1676 s / it) +Averaged stats: lr: 0.000000 grad: 0.1422 (0.1499) loss: 0.8151 (0.8156) +Eval (hcp-train-subset): [98] [ 0/62] eta: 0:05:47 loss: 0.8209 (0.8209) time: 5.5969 data: 5.5658 max mem: 9390 +Eval (hcp-train-subset): [98] [61/62] eta: 0:00:00 loss: 0.8146 (0.8152) time: 0.1595 data: 0.1344 max mem: 9390 +Eval (hcp-train-subset): [98] Total time: 0:00:14 (0.2362 s / it) +Averaged stats (hcp-train-subset): loss: 0.8146 (0.8152) +Eval (hcp-val): [98] [ 0/62] eta: 0:05:51 loss: 0.8223 (0.8223) time: 5.6707 data: 5.6421 max mem: 9390 +Eval (hcp-val): [98] [61/62] eta: 0:00:00 loss: 0.8262 (0.8276) time: 0.1323 data: 0.1055 max mem: 9390 +Eval (hcp-val): [98] Total time: 0:00:13 (0.2226 s / it) +Averaged stats (hcp-val): loss: 0.8262 (0.8276) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +Train: [99] [ 0/6250] eta: 8:50:38 lr: 0.000000 grad: 0.1899 (0.1899) loss: 0.8326 (0.8326) time: 5.0941 data: 4.9807 max mem: 9390 +Train: [99] [ 100/6250] eta: 0:21:53 lr: 0.000000 grad: 0.1739 (0.1953) loss: 0.8295 (0.8266) time: 0.1695 data: 0.0713 max mem: 9390 +Train: [99] [ 200/6250] eta: 0:19:35 lr: 0.000000 grad: 0.1500 (0.1844) loss: 0.8243 (0.8223) time: 0.1860 data: 0.0919 max mem: 9390 +Train: [99] [ 300/6250] eta: 0:18:23 lr: 0.000000 grad: 0.1414 (0.1756) loss: 0.8147 (0.8192) time: 0.1613 data: 0.0552 max mem: 9390 +Train: [99] [ 400/6250] eta: 0:17:36 lr: 0.000000 grad: 0.1315 (0.1689) loss: 0.8152 (0.8180) time: 0.1561 data: 0.0547 max mem: 9390 +Train: [99] [ 500/6250] eta: 0:17:00 lr: 0.000000 grad: 0.1377 (0.1646) loss: 0.8136 (0.8176) time: 0.1714 data: 0.0663 max mem: 9390 +Train: [99] [ 600/6250] eta: 0:16:29 lr: 0.000000 grad: 0.1378 (0.1614) loss: 0.8203 (0.8173) time: 0.1778 data: 0.0626 max mem: 9390 +Train: [99] [ 700/6250] eta: 0:16:13 lr: 0.000000 grad: 0.1462 (0.1592) loss: 0.8155 (0.8169) time: 0.1784 data: 0.0870 max mem: 9390 +Train: [99] [ 800/6250] eta: 0:16:03 lr: 0.000000 grad: 0.1390 (0.1579) loss: 0.8106 (0.8165) time: 0.1916 data: 0.1019 max mem: 9390 +Train: [99] [ 900/6250] eta: 0:15:52 lr: 0.000000 grad: 0.1436 (0.1566) loss: 0.8125 (0.8162) time: 0.1782 data: 0.0810 max mem: 9390 +Train: [99] [1000/6250] eta: 0:15:35 lr: 0.000000 grad: 0.1339 (0.1558) loss: 0.8213 (0.8160) time: 0.1625 data: 0.0778 max mem: 9390 +Train: [99] [1100/6250] eta: 0:15:11 lr: 0.000000 grad: 0.1380 (0.1548) loss: 0.8174 (0.8159) time: 0.1695 data: 0.0835 max mem: 9390 +Train: [99] [1200/6250] eta: 0:14:49 lr: 0.000000 grad: 0.1396 (0.1540) loss: 0.8149 (0.8157) time: 0.1738 data: 0.0818 max mem: 9390 +Train: [99] [1300/6250] eta: 0:14:32 lr: 0.000000 grad: 0.1405 (0.1533) loss: 0.8158 (0.8156) time: 0.2039 data: 0.1176 max mem: 9390 +Train: [99] [1400/6250] eta: 0:14:13 lr: 0.000000 grad: 0.1512 (0.1530) loss: 0.8146 (0.8155) time: 0.1920 data: 0.1012 max mem: 9390 +Train: [99] [1500/6250] eta: 0:13:50 lr: 0.000000 grad: 0.1381 (0.1523) loss: 0.8159 (0.8154) time: 0.1577 data: 0.0720 max mem: 9390 +Train: [99] [1600/6250] eta: 0:13:32 lr: 0.000000 grad: 0.1403 (0.1521) loss: 0.8175 (0.8153) time: 0.1848 data: 0.0953 max mem: 9390 +Train: [99] [1700/6250] eta: 0:13:12 lr: 0.000000 grad: 0.1440 (0.1518) loss: 0.8114 (0.8151) time: 0.1833 data: 0.0976 max mem: 9390 +Train: [99] [1800/6250] eta: 0:12:52 lr: 0.000000 grad: 0.1437 (0.1515) loss: 0.8122 (0.8150) time: 0.1479 data: 0.0488 max mem: 9390 +Train: [99] [1900/6250] eta: 0:12:33 lr: 0.000000 grad: 0.1520 (0.1516) loss: 0.8155 (0.8148) time: 0.1705 data: 0.0881 max mem: 9390 +Train: [99] [2000/6250] eta: 0:12:17 lr: 0.000000 grad: 0.1411 (0.1515) loss: 0.8161 (0.8146) time: 0.2041 data: 0.1074 max mem: 9390 +Train: [99] [2100/6250] eta: 0:11:56 lr: 0.000000 grad: 0.1510 (0.1516) loss: 0.8122 (0.8145) time: 0.1681 data: 0.0839 max mem: 9390 +Train: [99] [2200/6250] eta: 0:11:37 lr: 0.000000 grad: 0.1477 (0.1515) loss: 0.8115 (0.8144) time: 0.1790 data: 0.0898 max mem: 9390 +Train: [99] [2300/6250] eta: 0:11:18 lr: 0.000000 grad: 0.1421 (0.1516) loss: 0.8135 (0.8143) time: 0.1412 data: 0.0536 max mem: 9390 +Train: [99] [2400/6250] eta: 0:11:00 lr: 0.000000 grad: 0.1454 (0.1514) loss: 0.8191 (0.8143) time: 0.1636 data: 0.0818 max mem: 9390 +Train: [99] [2500/6250] eta: 0:10:42 lr: 0.000000 grad: 0.1515 (0.1513) loss: 0.8189 (0.8143) time: 0.1760 data: 0.0962 max mem: 9390 +Train: [99] [2600/6250] eta: 0:10:24 lr: 0.000000 grad: 0.1390 (0.1513) loss: 0.8204 (0.8143) time: 0.1639 data: 0.0693 max mem: 9390 +Train: [99] [2700/6250] eta: 0:10:06 lr: 0.000000 grad: 0.1508 (0.1512) loss: 0.8124 (0.8142) time: 0.1518 data: 0.0613 max mem: 9390 +Train: [99] [2800/6250] eta: 0:09:50 lr: 0.000000 grad: 0.1486 (0.1513) loss: 0.8091 (0.8142) time: 0.2028 data: 0.1141 max mem: 9390 +Train: [99] [2900/6250] eta: 0:09:32 lr: 0.000000 grad: 0.1497 (0.1514) loss: 0.8144 (0.8141) time: 0.1810 data: 0.0979 max mem: 9390 +Train: [99] [3000/6250] eta: 0:09:14 lr: 0.000000 grad: 0.1480 (0.1516) loss: 0.8144 (0.8141) time: 0.1654 data: 0.0747 max mem: 9390 +Train: [99] [3100/6250] eta: 0:08:57 lr: 0.000000 grad: 0.1580 (0.1517) loss: 0.8144 (0.8141) time: 0.1853 data: 0.0966 max mem: 9390 +Train: [99] [3200/6250] eta: 0:08:39 lr: 0.000000 grad: 0.1586 (0.1517) loss: 0.8137 (0.8141) time: 0.1674 data: 0.0814 max mem: 9390 +Train: [99] [3300/6250] eta: 0:08:22 lr: 0.000000 grad: 0.1521 (0.1519) loss: 0.8111 (0.8141) time: 0.1633 data: 0.0777 max mem: 9390 +Train: [99] [3400/6250] eta: 0:08:05 lr: 0.000000 grad: 0.1537 (0.1519) loss: 0.8149 (0.8141) time: 0.1836 data: 0.0858 max mem: 9390 +Train: [99] [3500/6250] eta: 0:07:48 lr: 0.000000 grad: 0.1501 (0.1519) loss: 0.8147 (0.8142) time: 0.1537 data: 0.0630 max mem: 9390 +Train: [99] [3600/6250] eta: 0:07:31 lr: 0.000000 grad: 0.1551 (0.1519) loss: 0.8073 (0.8141) time: 0.1732 data: 0.0849 max mem: 9390 +Train: [99] [3700/6250] eta: 0:07:14 lr: 0.000000 grad: 0.1475 (0.1518) loss: 0.8150 (0.8142) time: 0.1808 data: 0.0891 max mem: 9390 +Train: [99] [3800/6250] eta: 0:06:57 lr: 0.000000 grad: 0.1547 (0.1519) loss: 0.8210 (0.8141) time: 0.1886 data: 0.1092 max mem: 9390 +Train: [99] [3900/6250] eta: 0:06:40 lr: 0.000000 grad: 0.1492 (0.1520) loss: 0.8115 (0.8140) time: 0.1672 data: 0.0708 max mem: 9390 +Train: [99] [4000/6250] eta: 0:06:23 lr: 0.000000 grad: 0.1497 (0.1521) loss: 0.8142 (0.8139) time: 0.1429 data: 0.0524 max mem: 9390 +Train: [99] [4100/6250] eta: 0:06:06 lr: 0.000000 grad: 0.1462 (0.1520) loss: 0.8129 (0.8139) time: 0.1843 data: 0.0990 max mem: 9390 +Train: [99] [4200/6250] eta: 0:05:49 lr: 0.000000 grad: 0.1516 (0.1521) loss: 0.8083 (0.8138) time: 0.1717 data: 0.0774 max mem: 9390 +Train: [99] [4300/6250] eta: 0:05:32 lr: 0.000000 grad: 0.1539 (0.1521) loss: 0.8081 (0.8137) time: 0.2068 data: 0.1240 max mem: 9390 +Train: [99] [4400/6250] eta: 0:05:15 lr: 0.000000 grad: 0.1508 (0.1522) loss: 0.8113 (0.8137) time: 0.1732 data: 0.0851 max mem: 9390 +Train: [99] [4500/6250] eta: 0:04:57 lr: 0.000000 grad: 0.1402 (0.1521) loss: 0.8177 (0.8137) time: 0.1850 data: 0.1020 max mem: 9390 +Train: [99] [4600/6250] eta: 0:04:40 lr: 0.000000 grad: 0.1459 (0.1520) loss: 0.8150 (0.8137) time: 0.1469 data: 0.0605 max mem: 9390 +Train: [99] [4700/6250] eta: 0:04:23 lr: 0.000000 grad: 0.1404 (0.1519) loss: 0.8153 (0.8137) time: 0.1701 data: 0.0827 max mem: 9390 +Train: [99] [4800/6250] eta: 0:04:07 lr: 0.000000 grad: 0.1432 (0.1518) loss: 0.8084 (0.8138) time: 0.1964 data: 0.0350 max mem: 9390 +Train: [99] [4900/6250] eta: 0:03:50 lr: 0.000000 grad: 0.1438 (0.1516) loss: 0.8203 (0.8138) time: 0.1459 data: 0.0390 max mem: 9390 +Train: [99] [5000/6250] eta: 0:03:32 lr: 0.000000 grad: 0.1431 (0.1514) loss: 0.8158 (0.8138) time: 0.1430 data: 0.0618 max mem: 9390 +Train: [99] [5100/6250] eta: 0:03:16 lr: 0.000000 grad: 0.1412 (0.1514) loss: 0.8134 (0.8138) time: 0.1667 data: 0.0756 max mem: 9390 +Train: [99] [5200/6250] eta: 0:02:59 lr: 0.000000 grad: 0.1454 (0.1514) loss: 0.8193 (0.8138) time: 0.2251 data: 0.1364 max mem: 9390 +Train: [99] [5300/6250] eta: 0:02:42 lr: 0.000000 grad: 0.1446 (0.1512) loss: 0.8153 (0.8139) time: 0.1837 data: 0.0273 max mem: 9390 +Train: [99] [5400/6250] eta: 0:02:25 lr: 0.000000 grad: 0.1461 (0.1512) loss: 0.8136 (0.8139) time: 0.1945 data: 0.0360 max mem: 9390 +Train: [99] [5500/6250] eta: 0:02:08 lr: 0.000000 grad: 0.1460 (0.1513) loss: 0.8063 (0.8139) time: 0.1364 data: 0.0548 max mem: 9390 +Train: [99] [5600/6250] eta: 0:01:51 lr: 0.000000 grad: 0.1459 (0.1512) loss: 0.8133 (0.8139) time: 0.1820 data: 0.0940 max mem: 9390 +Train: [99] [5700/6250] eta: 0:01:34 lr: 0.000000 grad: 0.1377 (0.1511) loss: 0.8188 (0.8139) time: 0.1875 data: 0.0428 max mem: 9390 +Train: [99] [5800/6250] eta: 0:01:17 lr: 0.000000 grad: 0.1476 (0.1510) loss: 0.8091 (0.8139) time: 0.1666 data: 0.0816 max mem: 9390 +Train: [99] [5900/6250] eta: 0:01:00 lr: 0.000000 grad: 0.1440 (0.1511) loss: 0.8091 (0.8138) time: 0.1804 data: 0.0951 max mem: 9390 +Train: [99] [6000/6250] eta: 0:00:43 lr: 0.000000 grad: 0.1488 (0.1510) loss: 0.8132 (0.8138) time: 0.1783 data: 0.0761 max mem: 9390 +Train: [99] [6100/6250] eta: 0:00:25 lr: 0.000000 grad: 0.1466 (0.1509) loss: 0.8185 (0.8138) time: 0.1755 data: 0.0821 max mem: 9390 +Train: [99] [6200/6250] eta: 0:00:08 lr: 0.000000 grad: 0.1397 (0.1509) loss: 0.8083 (0.8138) time: 0.1620 data: 0.0612 max mem: 9390 +Train: [99] [6249/6250] eta: 0:00:00 lr: 0.000000 grad: 0.1527 (0.1509) loss: 0.8079 (0.8138) time: 0.1507 data: 0.0359 max mem: 9390 +Train: [99] Total time: 0:18:05 (0.1736 s / it) +Averaged stats: lr: 0.000000 grad: 0.1527 (0.1509) loss: 0.8079 (0.8138) +Eval (hcp-train-subset): [99] [ 0/62] eta: 0:10:50 loss: 0.8204 (0.8204) time: 10.4871 data: 10.3235 max mem: 9390 +Eval (hcp-train-subset): [99] [61/62] eta: 0:00:00 loss: 0.8124 (0.8151) time: 0.1047 data: 0.0770 max mem: 9390 +Eval (hcp-train-subset): [99] Total time: 0:00:17 (0.2805 s / it) +Averaged stats (hcp-train-subset): loss: 0.8124 (0.8151) +Making plots (hcp-train-subset): example=60 +Eval (hcp-val): [99] [ 0/62] eta: 0:05:23 loss: 0.8216 (0.8216) time: 5.2098 data: 5.1763 max mem: 9390 +Eval (hcp-val): [99] [61/62] eta: 0:00:00 loss: 0.8259 (0.8269) time: 0.1339 data: 0.1064 max mem: 9390 +Eval (hcp-val): [99] Total time: 0:00:14 (0.2264 s / it) +Averaged stats (hcp-val): loss: 0.8259 (0.8269) +Making plots (hcp-val): example=54 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_1/pretrain/checkpoint-last.pth +done! training time: 3:37:12 diff --git a/input_space_v3/flat_lr1e-3_2/eval_v2/aabc_age__patch__logistic/config.yaml b/input_space_v3/flat_lr1e-3_2/eval_v2/aabc_age__patch__logistic/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..250e9c13b27c804bfbd552fb604a430534c56b3c --- /dev/null +++ b/input_space_v3/flat_lr1e-3_2/eval_v2/aabc_age__patch__logistic/config.yaml @@ -0,0 +1,30 @@ +output_root: experiments/input_space_v3/output +name_prefix: eval_logistic +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_2; eval v2 (aabc_age patch logistic) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: input_space_v3/flat_lr1e-3_2/eval_v2/aabc_age__patch__logistic +model: flat_mae +representation: patch +dataset: aabc_age +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/eval_v2/aabc_age__patch__logistic +remote_dir: null diff --git a/input_space_v3/flat_lr1e-3_2/eval_v2/aabc_age__patch__logistic/eval_table.csv b/input_space_v3/flat_lr1e-3_2/eval_v2/aabc_age__patch__logistic/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..55dbbc94f3ba7e145d209db4ac89c756eb5239d7 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_2/eval_v2/aabc_age__patch__logistic/eval_table.csv @@ -0,0 +1,203 @@ +model,repr,clf,dataset,trial,C,split,acc,acc_std,f1,f1_std,bacc,bacc_std +flat_mae,patch,logistic,aabc_age,,0.005994842503189409,train,0.6889763779527559,0.020610685192411434,0.6868861349572553,0.020769231625125117,0.6900928896699943,0.02051354798293114 +flat_mae,patch,logistic,aabc_age,,0.005994842503189409,test,0.4230769230769231,0.05958043640631431,0.37677585419520904,0.06147710369013507,0.41277472527472525,0.05975546447304462 +flat_mae,patch,logistic,aabc_age,1,0.046415888336127774,train,0.8503937007874016,0.015699490149300464,0.8508896806336781,0.015738607121492915,0.8508637504818859,0.015776005669657936 +flat_mae,patch,logistic,aabc_age,1,0.046415888336127774,test,0.5,0.06495263408481762,0.5022986690728626,0.06401918308124008,0.4981684981684981,0.06466939680232973 +flat_mae,patch,logistic,aabc_age,2,0.000774263682681127,train,0.5551181102362205,0.020965029014167445,0.5467251426167158,0.021711849180200627,0.5551005343419213,0.02097205106108466 +flat_mae,patch,logistic,aabc_age,2,0.000774263682681127,test,0.5384615384615384,0.06622959661250868,0.521166439672382,0.06748429116720692,0.5322802197802198,0.06572204511421993 +flat_mae,patch,logistic,aabc_age,3,0.3593813663804626,train,0.9862204724409449,0.005180934827246073,0.9862222044986548,0.005174324277824971,0.9864898137475091,0.005101258333363456 +flat_mae,patch,logistic,aabc_age,3,0.3593813663804626,test,0.5576923076923077,0.06083174729768939,0.535212201591512,0.06396087785750536,0.5542582417582418,0.06052859709360721 +flat_mae,patch,logistic,aabc_age,4,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,4,2.782559402207126,test,0.46153846153846156,0.06398266222257994,0.4563746438746439,0.06379934216882066,0.46543040293040294,0.06457739540900713 +flat_mae,patch,logistic,aabc_age,5,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,5,21.54434690031882,test,0.5192307692307693,0.063986222629489,0.511904761904762,0.06483166241679016,0.5233516483516484,0.06411880989192921 +flat_mae,patch,logistic,aabc_age,6,0.3593813663804626,train,0.9881889763779528,0.00480458704449334,0.9881633491703268,0.004799602456744345,0.9885559294499884,0.004670719524840383 +flat_mae,patch,logistic,aabc_age,6,0.3593813663804626,test,0.5961538461538461,0.06861619307905913,0.5977911044477761,0.0686794006069846,0.5961538461538461,0.06880589973403901 +flat_mae,patch,logistic,aabc_age,7,0.046415888336127774,train,0.8543307086614174,0.015068911909763508,0.8547451128473762,0.015096784166307954,0.8555810776598662,0.015076816408142612 +flat_mae,patch,logistic,aabc_age,7,0.046415888336127774,test,0.5384615384615384,0.06040205529635286,0.5212754107490949,0.062374903375770605,0.5350274725274725,0.06025307111581183 +flat_mae,patch,logistic,aabc_age,8,0.005994842503189409,train,0.6889763779527559,0.020596739558759306,0.6847184065934067,0.021211046488938363,0.6884605352241799,0.02062828445315086 +flat_mae,patch,logistic,aabc_age,8,0.005994842503189409,test,0.5384615384615384,0.06719330940207043,0.5432150377802551,0.06624322172596296,0.5428113553113554,0.067401492351096 +flat_mae,patch,logistic,aabc_age,9,0.3593813663804626,train,0.9822834645669292,0.005828552345483813,0.9821581707223324,0.00586384016672429,0.9821900011315927,0.0058842940746702595 +flat_mae,patch,logistic,aabc_age,9,0.3593813663804626,test,0.46153846153846156,0.05753232947579337,0.43649509803921566,0.05370691897130668,0.4548992673992674,0.05665445745602652 +flat_mae,patch,logistic,aabc_age,10,0.000774263682681127,train,0.5649606299212598,0.020110141802971115,0.5570880203773952,0.020736060478424224,0.5643608946487172,0.02004346663351043 +flat_mae,patch,logistic,aabc_age,10,0.000774263682681127,test,0.4423076923076923,0.06790395235597212,0.43885281385281383,0.06881048350570582,0.4375,0.06758184320530562 +flat_mae,patch,logistic,aabc_age,11,0.046415888336127774,train,0.8582677165354331,0.01565615472363382,0.8583713643912959,0.015703620841230396,0.8597809169353401,0.0156260509702282 +flat_mae,patch,logistic,aabc_age,11,0.046415888336127774,test,0.6538461538461539,0.06308883564809191,0.6645707915273132,0.060852286423575264,0.6556776556776557,0.06269125946576747 +flat_mae,patch,logistic,aabc_age,12,0.046415888336127774,train,0.8543307086614174,0.015372213995060259,0.8541879389560505,0.01544621722665105,0.8551635630978022,0.015299136979734276 +flat_mae,patch,logistic,aabc_age,12,0.046415888336127774,test,0.46153846153846156,0.05926286592889775,0.4645551879422847,0.05888618411444918,0.46863553113553114,0.059976603054857316 +flat_mae,patch,logistic,aabc_age,13,0.005994842503189409,train,0.6673228346456693,0.019444943268408826,0.6621500327150157,0.020115018685138226,0.66765613102693,0.019416954742484466 +flat_mae,patch,logistic,aabc_age,13,0.005994842503189409,test,0.4423076923076923,0.058748032826187006,0.426327423332868,0.05872159198317128,0.440018315018315,0.058612488028017266 +flat_mae,patch,logistic,aabc_age,14,0.046415888336127774,train,0.8622047244094488,0.014017840240197126,0.8620204864451333,0.014125508700252969,0.8633280525672771,0.013930258508025218 +flat_mae,patch,logistic,aabc_age,14,0.046415888336127774,test,0.6153846153846154,0.06625747697005879,0.6112599469496022,0.06759744033722095,0.614010989010989,0.06638519482426172 +flat_mae,patch,logistic,aabc_age,15,0.005994842503189409,train,0.6988188976377953,0.02034361762876889,0.695604013681333,0.020932298678378643,0.6993938307098923,0.020388720953641432 +flat_mae,patch,logistic,aabc_age,15,0.005994842503189409,test,0.5576923076923077,0.06189469010118633,0.5543661502582042,0.06347107788883607,0.55746336996337,0.06214223111174439 +flat_mae,patch,logistic,aabc_age,16,0.000774263682681127,train,0.5551181102362205,0.020797120655043928,0.5456683235235467,0.021162808737385855,0.5532100312818261,0.0206480613554492 +flat_mae,patch,logistic,aabc_age,16,0.000774263682681127,test,0.40384615384615385,0.06464532273474463,0.40710640981538815,0.06495271903837098,0.4017857142857143,0.06466464860758304 +flat_mae,patch,logistic,aabc_age,17,0.000774263682681127,train,0.5748031496062992,0.021583972346065596,0.5706755210814713,0.022087113433499565,0.5747914465015564,0.021533578562254393 +flat_mae,patch,logistic,aabc_age,17,0.000774263682681127,test,0.4423076923076923,0.0569367966834107,0.40585967432950193,0.05606384328738315,0.43704212454212454,0.05581974517000805 +flat_mae,patch,logistic,aabc_age,18,0.046415888336127774,train,0.8484251968503937,0.01455909291248508,0.8483521567400975,0.014631331495030164,0.8498178663147861,0.014489774849376592 +flat_mae,patch,logistic,aabc_age,18,0.046415888336127774,test,0.4807692307692308,0.06697747568041595,0.47440734452618993,0.06686059755333632,0.47870879120879123,0.06689663536116403 +flat_mae,patch,logistic,aabc_age,19,0.046415888336127774,train,0.8405511811023622,0.01621306497016995,0.840684390504691,0.016223573276143016,0.8411682544127321,0.016101382480751023 +flat_mae,patch,logistic,aabc_age,19,0.046415888336127774,test,0.46153846153846156,0.06687278171955495,0.46484949832775924,0.06728004813532251,0.46130952380952384,0.06690638541110107 +flat_mae,patch,logistic,aabc_age,20,0.3593813663804626,train,0.9803149606299213,0.006236492627084603,0.9803596095712532,0.006223404107761961,0.9803914399805136,0.006226087227190432 +flat_mae,patch,logistic,aabc_age,20,0.3593813663804626,test,0.4230769230769231,0.06146490796578649,0.40805860805860805,0.0613028920251184,0.4194139194139194,0.061034557230863797 +flat_mae,patch,logistic,aabc_age,21,0.3593813663804626,train,0.984251968503937,0.0054519513889567835,0.9842139348094329,0.005463769675561586,0.984473684715251,0.005378816680196757 +flat_mae,patch,logistic,aabc_age,21,0.3593813663804626,test,0.5,0.06110998669098841,0.4870564717641179,0.061648919946218364,0.5038919413919414,0.0615890212280158 +flat_mae,patch,logistic,aabc_age,22,0.046415888336127774,train,0.8484251968503937,0.016725039654778198,0.8482521919453261,0.016926100793292747,0.8483624990170487,0.016771999508223556 +flat_mae,patch,logistic,aabc_age,22,0.046415888336127774,test,0.4807692307692308,0.06665392383146079,0.49312659846547313,0.06520609821902562,0.48214285714285715,0.06689336966748917 +flat_mae,patch,logistic,aabc_age,23,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,23,21.54434690031882,test,0.5192307692307693,0.060711316122494356,0.5118131868131868,0.06322442086667492,0.5173992673992673,0.06071077130448087 +flat_mae,patch,logistic,aabc_age,24,0.046415888336127774,train,0.8523622047244095,0.015877723347640166,0.8523802654186912,0.01602391378994445,0.8532650286062806,0.015827198129962323 +flat_mae,patch,logistic,aabc_age,24,0.046415888336127774,test,0.40384615384615385,0.06545358353545767,0.3959096459096459,0.0641687618769873,0.4001831501831502,0.06501728555619767 +flat_mae,patch,logistic,aabc_age,25,0.046415888336127774,train,0.8523622047244095,0.015818873631631494,0.8526106271806101,0.015823955556949265,0.8530974473953229,0.015749228119323763 +flat_mae,patch,logistic,aabc_age,25,0.046415888336127774,test,0.46153846153846156,0.06607118046148384,0.44928506997472517,0.06643311347532785,0.4608516483516484,0.06588956534461872 +flat_mae,patch,logistic,aabc_age,26,0.005994842503189409,train,0.6830708661417323,0.02046301228973251,0.6786609255547134,0.021051351627626558,0.6835499742035217,0.020393831122473716 +flat_mae,patch,logistic,aabc_age,26,0.005994842503189409,test,0.4807692307692308,0.06232396511149571,0.4721068208971435,0.0634727125359779,0.48168498168498164,0.06248924912566559 +flat_mae,patch,logistic,aabc_age,27,0.3593813663804626,train,0.9921259842519685,0.003929323208793303,0.9920990736487192,0.003929076795899212,0.9923706196333255,0.003825373417122102 +flat_mae,patch,logistic,aabc_age,27,0.3593813663804626,test,0.4230769230769231,0.06547984016058395,0.41288819875776395,0.06612227205288701,0.42124542124542125,0.06545608374900794 +flat_mae,patch,logistic,aabc_age,28,0.046415888336127774,train,0.84251968503937,0.016295311260431287,0.8429523553737697,0.016324049211698548,0.8435019246666117,0.01616228396840791 +flat_mae,patch,logistic,aabc_age,28,0.046415888336127774,test,0.5,0.06863788868630509,0.5021739130434782,0.06872229272051981,0.4983974358974359,0.06865062573492668 +flat_mae,patch,logistic,aabc_age,29,0.046415888336127774,train,0.860236220472441,0.015918414408848468,0.8609158998090735,0.015939123409863223,0.861729438097083,0.015830650982621017 +flat_mae,patch,logistic,aabc_age,29,0.046415888336127774,test,0.46153846153846156,0.06356751058808945,0.4741666666666667,0.06214503896692466,0.46565934065934067,0.06391037550598608 +flat_mae,patch,logistic,aabc_age,30,0.046415888336127774,train,0.844488188976378,0.016323384924879746,0.8448656221977813,0.016335219507983653,0.8453504724879121,0.016318298060475016 +flat_mae,patch,logistic,aabc_age,30,0.046415888336127774,test,0.5,0.07028875355090346,0.5016419184161119,0.06938436171591134,0.4981684981684981,0.07000502692543974 +flat_mae,patch,logistic,aabc_age,31,9.999999999999999e-05,train,0.49015748031496065,0.019961058561301745,0.46167531350421004,0.020386302072055936,0.48715102831091567,0.019825647531615694 +flat_mae,patch,logistic,aabc_age,31,9.999999999999999e-05,test,0.5769230769230769,0.05665021660523566,0.5213107575536418,0.05917780345821021,0.5661630036630036,0.055764187285479834 +flat_mae,patch,logistic,aabc_age,32,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,32,21.54434690031882,test,0.4807692307692308,0.06793090598663969,0.4768892397924656,0.06864669813996178,0.47756410256410253,0.06809926636110422 +flat_mae,patch,logistic,aabc_age,33,0.046415888336127774,train,0.8484251968503937,0.015935974473202615,0.8480280211593114,0.016011468669796206,0.8480949444656485,0.015903591205540753 +flat_mae,patch,logistic,aabc_age,33,0.046415888336127774,test,0.5,0.06886461935432858,0.5011104032843163,0.06962108356956767,0.5013736263736264,0.06911747518678502 +flat_mae,patch,logistic,aabc_age,34,0.046415888336127774,train,0.8523622047244095,0.015104403953352078,0.8520638081560336,0.015316247378714896,0.8533150152765018,0.015012922287970474 +flat_mae,patch,logistic,aabc_age,34,0.046415888336127774,test,0.4807692307692308,0.065811041590802,0.4973557692307692,0.06615096673639582,0.48511904761904767,0.06597789925212175 +flat_mae,patch,logistic,aabc_age,35,0.3593813663804626,train,0.984251968503937,0.005735477337711352,0.984222833779121,0.005718831848230622,0.984473684715251,0.0056525287360697386 +flat_mae,patch,logistic,aabc_age,35,0.3593813663804626,test,0.4230769230769231,0.05773900674074923,0.41682870370370373,0.05868627390957786,0.4210164835164835,0.05757396886003308 +flat_mae,patch,logistic,aabc_age,36,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,36,2.782559402207126,test,0.6538461538461539,0.05966181814509761,0.6480952380952381,0.06196166129532926,0.6584249084249084,0.059776367729725194 +flat_mae,patch,logistic,aabc_age,37,0.046415888336127774,train,0.8622047244094488,0.016574941552155612,0.8630405877441167,0.01650878691494247,0.8636955804591198,0.016446761241316263 +flat_mae,patch,logistic,aabc_age,37,0.046415888336127774,test,0.4230769230769231,0.06420662835144325,0.40714285714285714,0.06358330503665229,0.41666666666666663,0.06369792290360621 +flat_mae,patch,logistic,aabc_age,38,9.999999999999999e-05,train,0.4940944881889764,0.01952177810035859,0.466495119538631,0.020210035951876697,0.4918859766891899,0.019404480837866202 +flat_mae,patch,logistic,aabc_age,38,9.999999999999999e-05,test,0.4807692307692308,0.058399714273435745,0.4279086779086779,0.04863287374984417,0.4697802197802198,0.056899604817416925 +flat_mae,patch,logistic,aabc_age,39,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,39,166.81005372000556,test,0.5,0.059967496126785015,0.47820137951716896,0.059337402519638524,0.49221611721611724,0.0593133148566444 +flat_mae,patch,logistic,aabc_age,40,0.005994842503189409,train,0.6889763779527559,0.019168579364910412,0.6871255644683397,0.019237227597535676,0.6898482946514023,0.019108215793725736 +flat_mae,patch,logistic,aabc_age,40,0.005994842503189409,test,0.46153846153846156,0.05912802027013156,0.42714094184682416,0.06423195262901674,0.4592490842490842,0.058950673871782606 +flat_mae,patch,logistic,aabc_age,41,0.046415888336127774,train,0.8503937007874016,0.014756630290017957,0.850352974675453,0.014831309047447111,0.8512988862442437,0.014743258050394404 +flat_mae,patch,logistic,aabc_age,41,0.046415888336127774,test,0.4230769230769231,0.05705415002874865,0.39380293619424056,0.05958762145555237,0.4251373626373627,0.05760164211328507 +flat_mae,patch,logistic,aabc_age,42,0.005994842503189409,train,0.6850393700787402,0.02010399638980621,0.6827285244900168,0.020404869797969783,0.6861511990088015,0.020090989209338182 +flat_mae,patch,logistic,aabc_age,42,0.005994842503189409,test,0.4807692307692308,0.06301895788772167,0.4610240334378265,0.06866354537446055,0.48489010989010994,0.06350038763659414 +flat_mae,patch,logistic,aabc_age,43,0.005994842503189409,train,0.6732283464566929,0.019286794820832957,0.6690570041315342,0.019746990200275944,0.6742896138967258,0.019290914111328886 +flat_mae,patch,logistic,aabc_age,43,0.005994842503189409,test,0.5192307692307693,0.06842799523984594,0.5198704646921963,0.06891152135255656,0.5162545787545787,0.06862311065002075 +flat_mae,patch,logistic,aabc_age,44,0.005994842503189409,train,0.6614173228346457,0.019050592860858088,0.6591292787617999,0.019177998730917502,0.6631630845683357,0.018976532312967503 +flat_mae,patch,logistic,aabc_age,44,0.005994842503189409,test,0.5,0.07173128479913705,0.4926708074534162,0.07303247824378957,0.4967948717948718,0.07172594454710449 +flat_mae,patch,logistic,aabc_age,45,0.005994842503189409,train,0.6673228346456693,0.02012100076311672,0.6631111300608804,0.020564219128120096,0.6679736722485514,0.020159486305677127 +flat_mae,patch,logistic,aabc_age,45,0.005994842503189409,test,0.46153846153846156,0.06014774708407573,0.4542378917378917,0.060532151796343976,0.46382783882783885,0.06048260015026484 +flat_mae,patch,logistic,aabc_age,46,0.005994842503189409,train,0.6751968503937008,0.020415663241702707,0.6710818865101094,0.02087954357775536,0.6750003356419103,0.0204808549116831 +flat_mae,patch,logistic,aabc_age,46,0.005994842503189409,test,0.5961538461538461,0.06455375953283035,0.5942509332454985,0.06678017285639148,0.5991300366300366,0.06464045229360398 +flat_mae,patch,logistic,aabc_age,47,0.005994842503189409,train,0.6830708661417323,0.019837130564259984,0.6799555754218318,0.020274554923932642,0.6850053415012591,0.019780265741585666 +flat_mae,patch,logistic,aabc_age,47,0.005994842503189409,test,0.5,0.06722482811278062,0.4966183574879227,0.0685144972523331,0.4981684981684981,0.06725434663528654 +flat_mae,patch,logistic,aabc_age,48,0.005994842503189409,train,0.6988188976377953,0.021167332628650712,0.6943063955773644,0.021885118474675235,0.6995114252506286,0.02120117216669093 +flat_mae,patch,logistic,aabc_age,48,0.005994842503189409,test,0.40384615384615385,0.0640872532997238,0.39479166666666665,0.06689389378824258,0.4017857142857143,0.06418370178325516 +flat_mae,patch,logistic,aabc_age,49,0.046415888336127774,train,0.8582677165354331,0.014961357213983612,0.8581382445434029,0.01510707816770364,0.8585431175187815,0.014940583335899621 +flat_mae,patch,logistic,aabc_age,49,0.046415888336127774,test,0.40384615384615385,0.06179676558434423,0.39457556935817806,0.06223201609202196,0.39743589743589747,0.061458532403512664 +flat_mae,patch,logistic,aabc_age,50,0.046415888336127774,train,0.8523622047244095,0.014952546510788546,0.8528342619021301,0.014956637819090539,0.8524447437517861,0.014925753468038693 +flat_mae,patch,logistic,aabc_age,50,0.046415888336127774,test,0.4230769230769231,0.0626210543643601,0.4258832565284178,0.06341875762668599,0.4226190476190476,0.06270810193119868 +flat_mae,patch,logistic,aabc_age,51,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,51,166.81005372000556,test,0.4423076923076923,0.06586083364401049,0.44073539363861947,0.06590658494703676,0.4391025641025641,0.06560286322964723 +flat_mae,patch,logistic,aabc_age,52,0.000774263682681127,train,0.5728346456692913,0.020175595867516206,0.5649945523905566,0.021040380032258832,0.5713375713718548,0.02012936789520636 +flat_mae,patch,logistic,aabc_age,52,0.000774263682681127,test,0.46153846153846156,0.06439219696194406,0.46390307056067925,0.06503837165006317,0.4626831501831502,0.06460284288474365 +flat_mae,patch,logistic,aabc_age,53,0.005994842503189409,train,0.6791338582677166,0.020018438087816108,0.6764402896802668,0.020397382447672835,0.6805379476743851,0.019963167620062477 +flat_mae,patch,logistic,aabc_age,53,0.005994842503189409,test,0.5192307692307693,0.06320272398818445,0.4936507936507937,0.06472340149781383,0.5128205128205129,0.06248438073155845 +flat_mae,patch,logistic,aabc_age,54,0.046415888336127774,train,0.8543307086614174,0.015127488478984727,0.8546659824005369,0.015188735073195283,0.8566189303955396,0.015011167451768443 +flat_mae,patch,logistic,aabc_age,54,0.046415888336127774,test,0.46153846153846156,0.06508115098104636,0.46330484330484323,0.0644486427154609,0.46565934065934067,0.06553625580685964 +flat_mae,patch,logistic,aabc_age,55,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,55,21.54434690031882,test,0.5769230769230769,0.06280457149908303,0.5788461538461538,0.06139689299486092,0.5812728937728938,0.06310715210594338 +flat_mae,patch,logistic,aabc_age,56,0.005994842503189409,train,0.6732283464566929,0.021093647204405045,0.6707763117659228,0.021485892490025825,0.6734017211717163,0.021126382263971483 +flat_mae,patch,logistic,aabc_age,56,0.005994842503189409,test,0.46153846153846156,0.06530016038836017,0.4549107142857143,0.06628142427395155,0.4581043956043956,0.06522336271557556 +flat_mae,patch,logistic,aabc_age,57,0.046415888336127774,train,0.8562992125984252,0.0150575903770177,0.8567722733839812,0.015118500885144076,0.8568945163783662,0.01502639076134177 +flat_mae,patch,logistic,aabc_age,57,0.046415888336127774,test,0.5192307692307693,0.06208597779735175,0.5130240130240129,0.05982349240456816,0.5171703296703296,0.06182705192992116 +flat_mae,patch,logistic,aabc_age,58,0.046415888336127774,train,0.8582677165354331,0.015126537595374535,0.8585646908672393,0.01517486135052582,0.8585931041890028,0.015150578378700257 +flat_mae,patch,logistic,aabc_age,58,0.046415888336127774,test,0.5,0.06058545727430053,0.48113341983484714,0.06686716661848811,0.49793956043956045,0.060349940145765 +flat_mae,patch,logistic,aabc_age,59,0.046415888336127774,train,0.844488188976378,0.01569206343925841,0.8439151395405718,0.01588446163344567,0.8452005124772483,0.015606519744895053 +flat_mae,patch,logistic,aabc_age,59,0.046415888336127774,test,0.5,0.07049372585284015,0.49870247568523435,0.07079376091927915,0.4983974358974359,0.07048245248376149 +flat_mae,patch,logistic,aabc_age,60,0.046415888336127774,train,0.8661417322834646,0.014616830891253076,0.8667766020259645,0.014549201145667524,0.867510270642457,0.014492341737947277 +flat_mae,patch,logistic,aabc_age,60,0.046415888336127774,test,0.4423076923076923,0.06145392029420603,0.4302808302808303,0.06518143974352124,0.44459706959706957,0.06203208067025528 +flat_mae,patch,logistic,aabc_age,61,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,61,2.782559402207126,test,0.46153846153846156,0.06851418675706696,0.46652740937223697,0.06808041354702377,0.4626831501831502,0.06877757052817476 +flat_mae,patch,logistic,aabc_age,62,0.046415888336127774,train,0.84251968503937,0.01565556317074914,0.8435224012031598,0.015656510735280776,0.8443545749910336,0.015566681859068811 +flat_mae,patch,logistic,aabc_age,62,0.046415888336127774,test,0.5576923076923077,0.05965204827921104,0.5309202124084157,0.06108001199998092,0.5512820512820513,0.05911508708673211 +flat_mae,patch,logistic,aabc_age,63,0.000774263682681127,train,0.5649606299212598,0.020131890437463267,0.5585797059540363,0.02065035797237223,0.5644108813189384,0.020200076961081292 +flat_mae,patch,logistic,aabc_age,63,0.000774263682681127,test,0.4423076923076923,0.0582899303167482,0.41254076698155645,0.06068207948150631,0.440018315018315,0.057811500651997895 +flat_mae,patch,logistic,aabc_age,64,0.3593813663804626,train,0.9862204724409449,0.005191681992102726,0.9861172003396281,0.005237715602430068,0.9862722458663302,0.0051925798526705706 +flat_mae,patch,logistic,aabc_age,64,0.3593813663804626,test,0.4230769230769231,0.06492526427230313,0.42913205308015967,0.06466349331266225,0.42719780219780223,0.06537100846888429 +flat_mae,patch,logistic,aabc_age,65,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,65,21.54434690031882,test,0.46153846153846156,0.07229885379696575,0.4612250712250712,0.07148587535577662,0.4610805860805861,0.0724099441260941 +flat_mae,patch,logistic,aabc_age,66,0.005994842503189409,train,0.6771653543307087,0.020015361993464702,0.6748850813771539,0.020389935221003977,0.6784042241013908,0.020054488327903353 +flat_mae,patch,logistic,aabc_age,66,0.005994842503189409,test,0.4423076923076923,0.059633694458694236,0.4464127826196792,0.060002917487599935,0.44459706959706957,0.060086369976294754 +flat_mae,patch,logistic,aabc_age,67,0.046415888336127774,train,0.8543307086614174,0.015912497004402608,0.853988181942345,0.015953079236891786,0.8535406145891071,0.015987304408520114 +flat_mae,patch,logistic,aabc_age,67,0.046415888336127774,test,0.5576923076923077,0.06315533353443836,0.5411519607843137,0.06669566600566844,0.5528846153846154,0.06300436794157975 +flat_mae,patch,logistic,aabc_age,68,0.046415888336127774,train,0.8464566929133859,0.016189567588549048,0.8467337235821619,0.01615382235168554,0.8469814524280335,0.01614156099998251 +flat_mae,patch,logistic,aabc_age,68,0.046415888336127774,test,0.5384615384615384,0.061658764619783535,0.519655172413793,0.06545475822202458,0.5393772893772893,0.0618001817464826 +flat_mae,patch,logistic,aabc_age,69,0.046415888336127774,train,0.8562992125984252,0.01589316732704767,0.8559720567574568,0.015989101915976328,0.8574972333516818,0.01585503786104 +flat_mae,patch,logistic,aabc_age,69,0.046415888336127774,test,0.5,0.06551366224558357,0.5088743784395958,0.06320002246245965,0.5073260073260073,0.06589549714558184 +flat_mae,patch,logistic,aabc_age,70,0.3593813663804626,train,0.9940944881889764,0.0034038410174782405,0.9941230964369745,0.003394335908806511,0.9943867486655836,0.003256606953827682 +flat_mae,patch,logistic,aabc_age,70,0.3593813663804626,test,0.5192307692307693,0.06596452112565722,0.5166666666666667,0.06730729106993083,0.5251831501831501,0.06606899378889165 +flat_mae,patch,logistic,aabc_age,71,0.046415888336127774,train,0.8622047244094488,0.015446611447032977,0.8623521090829656,0.015452860396683811,0.8629928901453617,0.015382232138418632 +flat_mae,patch,logistic,aabc_age,71,0.046415888336127774,test,0.4807692307692308,0.0692046531937603,0.48833333333333334,0.06845878149180999,0.48511904761904756,0.0696456038898842 +flat_mae,patch,logistic,aabc_age,72,0.046415888336127774,train,0.8503937007874016,0.015246676914079153,0.8512540031930321,0.015233223129057609,0.8517663874765291,0.01518478344096408 +flat_mae,patch,logistic,aabc_age,72,0.046415888336127774,test,0.5384615384615384,0.06278431191376717,0.5262326415977532,0.0648947412402049,0.5322802197802198,0.06255211310721301 +flat_mae,patch,logistic,aabc_age,73,0.046415888336127774,train,0.8622047244094488,0.015058278503982546,0.8628895859420361,0.015025413146561735,0.8635279992481621,0.015015452677324733 +flat_mae,patch,logistic,aabc_age,73,0.046415888336127774,test,0.5384615384615384,0.06437311495487913,0.5332324680150767,0.06453694780079018,0.5366300366300366,0.06438301138570883 +flat_mae,patch,logistic,aabc_age,74,0.005994842503189409,train,0.687007874015748,0.020058982095947073,0.6843416338676459,0.02026953716683907,0.6875146243975228,0.01995542969800017 +flat_mae,patch,logistic,aabc_age,74,0.005994842503189409,test,0.46153846153846156,0.06650982042539096,0.45248847926267277,0.0674040453539751,0.4581043956043956,0.06632842495862071 +flat_mae,patch,logistic,aabc_age,75,0.005994842503189409,train,0.6811023622047244,0.019433440954119637,0.6767053045346199,0.019701183874057296,0.6816514397120002,0.019359390805867797 +flat_mae,patch,logistic,aabc_age,75,0.005994842503189409,test,0.5192307692307693,0.06686269380218843,0.5121510673234811,0.0695561140216728,0.5203754578754579,0.06720695319351098 +flat_mae,patch,logistic,aabc_age,76,0.046415888336127774,train,0.8484251968503937,0.015880544838997472,0.8486869297381082,0.01592652546241984,0.849332743882207,0.01592833576072909 +flat_mae,patch,logistic,aabc_age,76,0.046415888336127774,test,0.5384615384615384,0.06339875682427774,0.5332493368700265,0.06440000710093323,0.5425824175824177,0.0636742448879188 +flat_mae,patch,logistic,aabc_age,77,0.046415888336127774,train,0.844488188976378,0.016040558674779555,0.8447360663633043,0.016061722701884638,0.8460031761314489,0.01589033392063439 +flat_mae,patch,logistic,aabc_age,77,0.046415888336127774,test,0.5192307692307693,0.06792547255989616,0.5178328113110722,0.06865095560275412,0.5190018315018315,0.06840033560403395 +flat_mae,patch,logistic,aabc_age,78,0.3593813663804626,train,0.9862204724409449,0.0050368226829188055,0.9861259002247865,0.0050569615940994446,0.9862722458663301,0.005029753864182065 +flat_mae,patch,logistic,aabc_age,78,0.3593813663804626,test,0.4807692307692308,0.06661405221620076,0.4846703296703297,0.06559811094924423,0.4819139194139194,0.06669932097617383 +flat_mae,patch,logistic,aabc_age,79,0.3593813663804626,train,0.9862204724409449,0.005265077961634736,0.9861092082735721,0.00529832583292172,0.9862722458663302,0.005245036566611998 +flat_mae,patch,logistic,aabc_age,79,0.3593813663804626,test,0.4423076923076923,0.06877740443595372,0.4286819502336744,0.06585219232168535,0.4386446886446887,0.06804973938439084 +flat_mae,patch,logistic,aabc_age,80,0.005994842503189409,train,0.6791338582677166,0.020971244361891832,0.6759517453146027,0.021565893594054465,0.6796852973499632,0.02100153805850289 +flat_mae,patch,logistic,aabc_age,80,0.005994842503189409,test,0.5,0.05878799287702273,0.48099529780564265,0.06252255687498927,0.5022893772893773,0.05920955489616655 +flat_mae,patch,logistic,aabc_age,81,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,81,2.782559402207126,test,0.5192307692307693,0.0666249326964368,0.5208741782954677,0.0676424704182074,0.5235805860805861,0.06688628974389411 +flat_mae,patch,logistic,aabc_age,82,0.046415888336127774,train,0.8622047244094488,0.015152675381170886,0.8632015232211016,0.01505576679558461,0.8631604713563193,0.01509303772337093 +flat_mae,patch,logistic,aabc_age,82,0.046415888336127774,test,0.4807692307692308,0.06879417891983622,0.47630059654516177,0.0702567787586907,0.48031135531135527,0.06880264689280871 +flat_mae,patch,logistic,aabc_age,83,0.3593813663804626,train,0.9901574803149606,0.004219539502010516,0.9901657833355795,0.004214112117485341,0.9903045039308462,0.00417005252545957 +flat_mae,patch,logistic,aabc_age,83,0.3593813663804626,test,0.40384615384615385,0.06356699862042779,0.40613553113553114,0.06227358675249944,0.40613553113553114,0.06393528343466984 +flat_mae,patch,logistic,aabc_age,84,0.3593813663804626,train,0.9940944881889764,0.0032719259482755386,0.9941230636559877,0.003257139449017087,0.9943867486655837,0.003122138065992552 +flat_mae,patch,logistic,aabc_age,84,0.3593813663804626,test,0.5961538461538461,0.062245208460823404,0.5833752269236141,0.06707436489376908,0.5931776556776557,0.06223610114653921 +flat_mae,patch,logistic,aabc_age,85,0.046415888336127774,train,0.8464566929133859,0.016524595248431858,0.8466382443521429,0.016565213406097325,0.8480193051637069,0.01639216913421711 +flat_mae,patch,logistic,aabc_age,85,0.046415888336127774,test,0.5,0.05674900619519263,0.48223886328725035,0.05873094179180368,0.4965659340659341,0.056407223505892244 +flat_mae,patch,logistic,aabc_age,86,0.005994842503189409,train,0.6791338582677166,0.020727426305559557,0.6755016760228768,0.02122078258927024,0.6794677294687843,0.020679715267252242 +flat_mae,patch,logistic,aabc_age,86,0.005994842503189409,test,0.5769230769230769,0.058055510571282616,0.54158215010142,0.060911496064142874,0.5677655677655679,0.05792118831166016 +flat_mae,patch,logistic,aabc_age,87,0.000774263682681127,train,0.5826771653543307,0.020474939278207326,0.5749665053228478,0.021305075709696995,0.5819533256359455,0.02044160531846456 +flat_mae,patch,logistic,aabc_age,87,0.000774263682681127,test,0.46153846153846156,0.06532639942273308,0.45896551724137935,0.06632191540661098,0.4624542124542125,0.06552811466720483 +flat_mae,patch,logistic,aabc_age,88,0.005994842503189409,train,0.6791338582677166,0.01894253197539957,0.6745837175189677,0.0195821591643853,0.6813582325288796,0.018852327553243682 +flat_mae,patch,logistic,aabc_age,88,0.005994842503189409,test,0.5384615384615384,0.06482927054600125,0.5318438003220611,0.06741926439826032,0.5412087912087913,0.0648591182521864 +flat_mae,patch,logistic,aabc_age,89,0.046415888336127774,train,0.8503937007874016,0.014970122868873113,0.8507266361746846,0.015020731594361774,0.8516664141360865,0.014890084338543282 +flat_mae,patch,logistic,aabc_age,89,0.046415888336127774,test,0.4807692307692308,0.0671287291119782,0.4833380084151473,0.06796790405137601,0.48076923076923084,0.06701428840373991 +flat_mae,patch,logistic,aabc_age,90,0.000774263682681127,train,0.5531496062992126,0.02074428054067795,0.54559309334569,0.020930407231760182,0.5517789980225897,0.02072894630295423 +flat_mae,patch,logistic,aabc_age,90,0.000774263682681127,test,0.5192307692307693,0.057423733831061446,0.4854898299698077,0.06051120920740761,0.5155677655677656,0.05705978623543791 +flat_mae,patch,logistic,aabc_age,91,0.005994842503189409,train,0.6811023622047244,0.02117613258735368,0.6778963404508247,0.021580279937586835,0.682286522155243,0.02104586594620383 +flat_mae,patch,logistic,aabc_age,91,0.005994842503189409,test,0.46153846153846156,0.0632370738949305,0.4502595966411756,0.0664542163762603,0.4610805860805861,0.06325945859839123 +flat_mae,patch,logistic,aabc_age,92,0.046415888336127774,train,0.8464566929133859,0.01602287912534172,0.8465746509380536,0.01605726864960495,0.8473166148499489,0.016053809510726665 +flat_mae,patch,logistic,aabc_age,92,0.046415888336127774,test,0.6346153846153846,0.053722536674523876,0.6111748047544855,0.06479647095090908,0.6357600732600732,0.054051628363868696 +flat_mae,patch,logistic,aabc_age,93,0.046415888336127774,train,0.8523622047244095,0.015909282218583017,0.8532436489386601,0.015852736519131782,0.853297394076208,0.015863429608376237 +flat_mae,patch,logistic,aabc_age,93,0.046415888336127774,test,0.36538461538461536,0.05903638182255266,0.358124966820619,0.05341295982957303,0.36149267399267404,0.0584542460872325 +flat_mae,patch,logistic,aabc_age,94,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,94,2.782559402207126,test,0.5,0.06503476539558802,0.495,0.06637590711210078,0.5,0.06515775453503532 +flat_mae,patch,logistic,aabc_age,95,0.046415888336127774,train,0.8484251968503937,0.015393736532572243,0.8486440659520051,0.015475075365271693,0.8493827305524282,0.01534436341485699 +flat_mae,patch,logistic,aabc_age,95,0.046415888336127774,test,0.5192307692307693,0.06271862354711692,0.5038961038961038,0.06292346288352726,0.5157967032967032,0.06223336180154213 +flat_mae,patch,logistic,aabc_age,96,0.046415888336127774,train,0.8405511811023622,0.016761392003307014,0.8406604703440969,0.01688489691513284,0.840900699861332,0.01679720271173797 +flat_mae,patch,logistic,aabc_age,96,0.046415888336127774,test,0.5192307692307693,0.06760895217499811,0.508801785975699,0.06702220410909783,0.5130494505494505,0.0673800212470026 +flat_mae,patch,logistic,aabc_age,97,0.005994842503189409,train,0.6791338582677166,0.020137746784526088,0.6772795933797225,0.020340195800402177,0.6798852440308484,0.020220308063626423 +flat_mae,patch,logistic,aabc_age,97,0.005994842503189409,test,0.38461538461538464,0.05910846513730139,0.3692505720823799,0.05631197047697535,0.3807234432234432,0.058382527838171584 +flat_mae,patch,logistic,aabc_age,98,0.3593813663804626,train,0.984251968503937,0.005777676761735417,0.9844106102957562,0.005718172142127078,0.9846912525964299,0.0056397036352570425 +flat_mae,patch,logistic,aabc_age,98,0.3593813663804626,test,0.5192307692307693,0.06200167014356722,0.5016420361247947,0.06737422210034157,0.5176282051282052,0.062048232703861686 +flat_mae,patch,logistic,aabc_age,99,9.999999999999999e-05,train,0.5059055118110236,0.019654550798803166,0.48243545788903464,0.019946827826097416,0.5026597223953708,0.01949450142061004 +flat_mae,patch,logistic,aabc_age,99,9.999999999999999e-05,test,0.4230769230769231,0.062168636378100064,0.3941770434227331,0.05938720264522627,0.41781135531135527,0.0612532388929042 +flat_mae,patch,logistic,aabc_age,100,0.005994842503189409,train,0.6988188976377953,0.01964431062159931,0.6958784381808278,0.02009462276781568,0.7007992113374083,0.01952530244961361 +flat_mae,patch,logistic,aabc_age,100,0.005994842503189409,test,0.4230769230769231,0.06264585348273166,0.4177777777777778,0.06208568350949185,0.42536630036630035,0.06318038689483824 diff --git a/input_space_v3/flat_lr1e-3_2/eval_v2/aabc_age__patch__logistic/log.txt b/input_space_v3/flat_lr1e-3_2/eval_v2/aabc_age__patch__logistic/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..b9bab8479b6308aad81376afe6bdf89d4c03bb37 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_2/eval_v2/aabc_age__patch__logistic/log.txt @@ -0,0 +1,245 @@ +fMRI foundation model logistic probe eval +version: 0.1.dev86+gf97f52698 +sha: bcce2b486277d3a5b520775efd9cdf1a2affce36, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-04-08 22:09:29 +config: +output_root: experiments/input_space_v3/output +name_prefix: eval_logistic +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_2; eval v2 (aabc_age patch logistic) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: input_space_v3/flat_lr1e-3_2/eval_v2/aabc_age__patch__logistic +model: flat_mae +representation: patch +dataset: aabc_age +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/eval_v2/aabc_age__patch__logistic +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=True, reg_tokens=0, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: aabc_age (flat) +train (n=455): +HFDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'segment', 'bold', 'mean', 'std'], + num_rows: 471 +}), + labels=[0 1 2 3], + counts=[110 127 109 109] +) + +validation (n=53): +HFDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'segment', 'bold', 'mean', 'std'], + num_rows: 58 +}), + labels=[0 1 2 3], + counts=[14 13 12 14] +) + +test (n=52): +HFDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'segment', 'bold', 'mean', 'std'], + num_rows: 55 +}), + labels=[0 1 2 3], + counts=[13 13 12 14] +) + +extracting features for all splits +extract (train) [ 0/228] eta: 0:25:03 time: 6.5921 data: 5.6312 max mem: 3205 +extract (train) [ 20/228] eta: 0:02:10 time: 0.3305 data: 0.1323 max mem: 3393 +extract (train) [ 40/228] eta: 0:01:23 time: 0.2525 data: 0.0895 max mem: 3393 +extract (train) [ 60/228] eta: 0:01:04 time: 0.2549 data: 0.0945 max mem: 3393 +extract (train) [ 80/228] eta: 0:00:51 time: 0.2550 data: 0.0886 max mem: 3393 +extract (train) [100/228] eta: 0:00:43 time: 0.2745 data: 0.1019 max mem: 3393 +extract (train) [120/228] eta: 0:00:35 time: 0.2826 data: 0.1083 max mem: 3393 +extract (train) [140/228] eta: 0:00:27 time: 0.2584 data: 0.0956 max mem: 3393 +extract (train) [160/228] eta: 0:00:20 time: 0.2350 data: 0.0841 max mem: 3393 +extract (train) [180/228] eta: 0:00:14 time: 0.2660 data: 0.0908 max mem: 3393 +extract (train) [200/228] eta: 0:00:08 time: 0.2462 data: 0.0862 max mem: 3393 +extract (train) [220/228] eta: 0:00:02 time: 0.2067 data: 0.0731 max mem: 3393 +extract (train) [227/228] eta: 0:00:00 time: 0.2120 data: 0.0760 max mem: 3393 +extract (train) Total time: 0:01:05 (0.2892 s / it) +extract (validation) [ 0/27] eta: 0:02:44 time: 6.1027 data: 5.9394 max mem: 3393 +extract (validation) [20/27] eta: 0:00:03 time: 0.2231 data: 0.0758 max mem: 3393 +extract (validation) [26/27] eta: 0:00:00 time: 0.1918 data: 0.0637 max mem: 3393 +extract (validation) Total time: 0:00:12 (0.4482 s / it) +extract (test) [ 0/26] eta: 0:02:17 time: 5.2716 data: 5.0860 max mem: 3393 +extract (test) [20/26] eta: 0:00:02 time: 0.2217 data: 0.0769 max mem: 3393 +extract (test) [25/26] eta: 0:00:00 time: 0.2040 data: 0.0690 max mem: 3393 +extract (test) Total time: 0:00:11 (0.4334 s / it) +feature extraction time: 0:01:29 +train features: (455, 768) +validation features: (53, 768) +test features: (52, 768) +evaluating fixed splits +eval results (fixed splits): + +| model | repr | clf | dataset | trial | C | split | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|----------:|:--------|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | aabc_age | | 0.0059948 | train | 0.68898 | 0.020611 | 0.68689 | 0.020769 | 0.69009 | 0.020514 | +| flat_mae | patch | logistic | aabc_age | | 0.0059948 | test | 0.42308 | 0.05958 | 0.37678 | 0.061477 | 0.41277 | 0.059755 | + + +evaluating random splits (n=100) +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 1, "C": 0.046415888336127774, "split": "test", "acc": 0.5, "acc_std": 0.06495263408481762, "f1": 0.5022986690728626, "f1_std": 0.06401918308124008, "bacc": 0.4981684981684981, "bacc_std": 0.06466939680232973} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 2, "C": 0.000774263682681127, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.06622959661250868, "f1": 0.521166439672382, "f1_std": 0.06748429116720692, "bacc": 0.5322802197802198, "bacc_std": 0.06572204511421993} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 3, "C": 0.3593813663804626, "split": "test", "acc": 0.5576923076923077, "acc_std": 0.06083174729768939, "f1": 0.535212201591512, "f1_std": 0.06396087785750536, "bacc": 0.5542582417582418, "bacc_std": 0.06052859709360721} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 4, "C": 2.782559402207126, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.06398266222257994, "f1": 0.4563746438746439, "f1_std": 0.06379934216882066, "bacc": 0.46543040293040294, "bacc_std": 0.06457739540900713} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 5, "C": 21.54434690031882, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.063986222629489, "f1": 0.511904761904762, "f1_std": 0.06483166241679016, "bacc": 0.5233516483516484, "bacc_std": 0.06411880989192921} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 6, "C": 0.3593813663804626, "split": "test", "acc": 0.5961538461538461, "acc_std": 0.06861619307905913, "f1": 0.5977911044477761, "f1_std": 0.0686794006069846, "bacc": 0.5961538461538461, "bacc_std": 0.06880589973403901} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 7, "C": 0.046415888336127774, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.06040205529635286, "f1": 0.5212754107490949, "f1_std": 0.062374903375770605, "bacc": 0.5350274725274725, "bacc_std": 0.06025307111581183} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 8, "C": 0.005994842503189409, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.06719330940207043, "f1": 0.5432150377802551, "f1_std": 0.06624322172596296, "bacc": 0.5428113553113554, "bacc_std": 0.067401492351096} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 9, "C": 0.3593813663804626, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.05753232947579337, "f1": 0.43649509803921566, "f1_std": 0.05370691897130668, "bacc": 0.4548992673992674, "bacc_std": 0.05665445745602652} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 10, "C": 0.000774263682681127, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.06790395235597212, "f1": 0.43885281385281383, "f1_std": 0.06881048350570582, "bacc": 0.4375, "bacc_std": 0.06758184320530562} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 11, "C": 0.046415888336127774, "split": "test", "acc": 0.6538461538461539, "acc_std": 0.06308883564809191, "f1": 0.6645707915273132, "f1_std": 0.060852286423575264, "bacc": 0.6556776556776557, "bacc_std": 0.06269125946576747} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 12, "C": 0.046415888336127774, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.05926286592889775, "f1": 0.4645551879422847, "f1_std": 0.05888618411444918, "bacc": 0.46863553113553114, "bacc_std": 0.059976603054857316} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 13, "C": 0.005994842503189409, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.058748032826187006, "f1": 0.426327423332868, "f1_std": 0.05872159198317128, "bacc": 0.440018315018315, "bacc_std": 0.058612488028017266} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 14, "C": 0.046415888336127774, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.06625747697005879, "f1": 0.6112599469496022, "f1_std": 0.06759744033722095, "bacc": 0.614010989010989, "bacc_std": 0.06638519482426172} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 15, "C": 0.005994842503189409, "split": "test", "acc": 0.5576923076923077, "acc_std": 0.06189469010118633, "f1": 0.5543661502582042, "f1_std": 0.06347107788883607, "bacc": 0.55746336996337, "bacc_std": 0.06214223111174439} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 16, "C": 0.000774263682681127, "split": "test", "acc": 0.40384615384615385, "acc_std": 0.06464532273474463, "f1": 0.40710640981538815, "f1_std": 0.06495271903837098, "bacc": 0.4017857142857143, "bacc_std": 0.06466464860758304} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 17, "C": 0.000774263682681127, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.0569367966834107, "f1": 0.40585967432950193, "f1_std": 0.05606384328738315, "bacc": 0.43704212454212454, "bacc_std": 0.05581974517000805} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 18, "C": 0.046415888336127774, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.06697747568041595, "f1": 0.47440734452618993, "f1_std": 0.06686059755333632, "bacc": 0.47870879120879123, "bacc_std": 0.06689663536116403} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 19, "C": 0.046415888336127774, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.06687278171955495, "f1": 0.46484949832775924, "f1_std": 0.06728004813532251, "bacc": 0.46130952380952384, "bacc_std": 0.06690638541110107} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 20, "C": 0.3593813663804626, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.06146490796578649, "f1": 0.40805860805860805, "f1_std": 0.0613028920251184, "bacc": 0.4194139194139194, "bacc_std": 0.061034557230863797} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 21, "C": 0.3593813663804626, "split": "test", "acc": 0.5, "acc_std": 0.06110998669098841, "f1": 0.4870564717641179, "f1_std": 0.061648919946218364, "bacc": 0.5038919413919414, "bacc_std": 0.0615890212280158} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 22, "C": 0.046415888336127774, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.06665392383146079, "f1": 0.49312659846547313, "f1_std": 0.06520609821902562, "bacc": 0.48214285714285715, "bacc_std": 0.06689336966748917} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 23, "C": 21.54434690031882, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.060711316122494356, "f1": 0.5118131868131868, "f1_std": 0.06322442086667492, "bacc": 0.5173992673992673, "bacc_std": 0.06071077130448087} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 24, "C": 0.046415888336127774, "split": "test", "acc": 0.40384615384615385, "acc_std": 0.06545358353545767, "f1": 0.3959096459096459, "f1_std": 0.0641687618769873, "bacc": 0.4001831501831502, "bacc_std": 0.06501728555619767} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 25, "C": 0.046415888336127774, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.06607118046148384, "f1": 0.44928506997472517, "f1_std": 0.06643311347532785, "bacc": 0.4608516483516484, "bacc_std": 0.06588956534461872} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 26, "C": 0.005994842503189409, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.06232396511149571, "f1": 0.4721068208971435, "f1_std": 0.0634727125359779, "bacc": 0.48168498168498164, "bacc_std": 0.06248924912566559} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 27, "C": 0.3593813663804626, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.06547984016058395, "f1": 0.41288819875776395, "f1_std": 0.06612227205288701, "bacc": 0.42124542124542125, "bacc_std": 0.06545608374900794} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 28, "C": 0.046415888336127774, "split": "test", "acc": 0.5, "acc_std": 0.06863788868630509, "f1": 0.5021739130434782, "f1_std": 0.06872229272051981, "bacc": 0.4983974358974359, "bacc_std": 0.06865062573492668} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 29, "C": 0.046415888336127774, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.06356751058808945, "f1": 0.4741666666666667, "f1_std": 0.06214503896692466, "bacc": 0.46565934065934067, "bacc_std": 0.06391037550598608} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 30, "C": 0.046415888336127774, "split": "test", "acc": 0.5, "acc_std": 0.07028875355090346, "f1": 0.5016419184161119, "f1_std": 0.06938436171591134, "bacc": 0.4981684981684981, "bacc_std": 0.07000502692543974} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 31, "C": 9.999999999999999e-05, "split": "test", "acc": 0.5769230769230769, "acc_std": 0.05665021660523566, "f1": 0.5213107575536418, "f1_std": 0.05917780345821021, "bacc": 0.5661630036630036, "bacc_std": 0.055764187285479834} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 32, "C": 21.54434690031882, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.06793090598663969, "f1": 0.4768892397924656, "f1_std": 0.06864669813996178, "bacc": 0.47756410256410253, "bacc_std": 0.06809926636110422} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 33, "C": 0.046415888336127774, "split": "test", "acc": 0.5, "acc_std": 0.06886461935432858, "f1": 0.5011104032843163, "f1_std": 0.06962108356956767, "bacc": 0.5013736263736264, "bacc_std": 0.06911747518678502} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 34, "C": 0.046415888336127774, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.065811041590802, "f1": 0.4973557692307692, "f1_std": 0.06615096673639582, "bacc": 0.48511904761904767, "bacc_std": 0.06597789925212175} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 35, "C": 0.3593813663804626, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.05773900674074923, "f1": 0.41682870370370373, "f1_std": 0.05868627390957786, "bacc": 0.4210164835164835, "bacc_std": 0.05757396886003308} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 36, "C": 2.782559402207126, "split": "test", "acc": 0.6538461538461539, "acc_std": 0.05966181814509761, "f1": 0.6480952380952381, "f1_std": 0.06196166129532926, "bacc": 0.6584249084249084, "bacc_std": 0.059776367729725194} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 37, "C": 0.046415888336127774, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.06420662835144325, "f1": 0.40714285714285714, "f1_std": 0.06358330503665229, "bacc": 0.41666666666666663, "bacc_std": 0.06369792290360621} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 38, "C": 9.999999999999999e-05, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.058399714273435745, "f1": 0.4279086779086779, "f1_std": 0.04863287374984417, "bacc": 0.4697802197802198, "bacc_std": 0.056899604817416925} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 39, "C": 166.81005372000556, "split": "test", "acc": 0.5, "acc_std": 0.059967496126785015, "f1": 0.47820137951716896, "f1_std": 0.059337402519638524, "bacc": 0.49221611721611724, "bacc_std": 0.0593133148566444} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 40, "C": 0.005994842503189409, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.05912802027013156, "f1": 0.42714094184682416, "f1_std": 0.06423195262901674, "bacc": 0.4592490842490842, "bacc_std": 0.058950673871782606} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 41, "C": 0.046415888336127774, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.05705415002874865, "f1": 0.39380293619424056, "f1_std": 0.05958762145555237, "bacc": 0.4251373626373627, "bacc_std": 0.05760164211328507} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 42, "C": 0.005994842503189409, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.06301895788772167, "f1": 0.4610240334378265, "f1_std": 0.06866354537446055, "bacc": 0.48489010989010994, "bacc_std": 0.06350038763659414} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 43, "C": 0.005994842503189409, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.06842799523984594, "f1": 0.5198704646921963, "f1_std": 0.06891152135255656, "bacc": 0.5162545787545787, "bacc_std": 0.06862311065002075} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 44, "C": 0.005994842503189409, "split": "test", "acc": 0.5, "acc_std": 0.07173128479913705, "f1": 0.4926708074534162, "f1_std": 0.07303247824378957, "bacc": 0.4967948717948718, "bacc_std": 0.07172594454710449} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 45, "C": 0.005994842503189409, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.06014774708407573, "f1": 0.4542378917378917, "f1_std": 0.060532151796343976, "bacc": 0.46382783882783885, "bacc_std": 0.06048260015026484} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 46, "C": 0.005994842503189409, "split": "test", "acc": 0.5961538461538461, "acc_std": 0.06455375953283035, "f1": 0.5942509332454985, "f1_std": 0.06678017285639148, "bacc": 0.5991300366300366, "bacc_std": 0.06464045229360398} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 47, "C": 0.005994842503189409, "split": "test", "acc": 0.5, "acc_std": 0.06722482811278062, "f1": 0.4966183574879227, "f1_std": 0.0685144972523331, "bacc": 0.4981684981684981, "bacc_std": 0.06725434663528654} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 48, "C": 0.005994842503189409, "split": "test", "acc": 0.40384615384615385, "acc_std": 0.0640872532997238, "f1": 0.39479166666666665, "f1_std": 0.06689389378824258, "bacc": 0.4017857142857143, "bacc_std": 0.06418370178325516} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 49, "C": 0.046415888336127774, "split": "test", "acc": 0.40384615384615385, "acc_std": 0.06179676558434423, "f1": 0.39457556935817806, "f1_std": 0.06223201609202196, "bacc": 0.39743589743589747, "bacc_std": 0.061458532403512664} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 50, "C": 0.046415888336127774, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.0626210543643601, "f1": 0.4258832565284178, "f1_std": 0.06341875762668599, "bacc": 0.4226190476190476, "bacc_std": 0.06270810193119868} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 51, "C": 166.81005372000556, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.06586083364401049, "f1": 0.44073539363861947, "f1_std": 0.06590658494703676, "bacc": 0.4391025641025641, "bacc_std": 0.06560286322964723} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 52, "C": 0.000774263682681127, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.06439219696194406, "f1": 0.46390307056067925, "f1_std": 0.06503837165006317, "bacc": 0.4626831501831502, "bacc_std": 0.06460284288474365} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 53, "C": 0.005994842503189409, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.06320272398818445, "f1": 0.4936507936507937, "f1_std": 0.06472340149781383, "bacc": 0.5128205128205129, "bacc_std": 0.06248438073155845} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 54, "C": 0.046415888336127774, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.06508115098104636, "f1": 0.46330484330484323, "f1_std": 0.0644486427154609, "bacc": 0.46565934065934067, "bacc_std": 0.06553625580685964} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 55, "C": 21.54434690031882, "split": "test", "acc": 0.5769230769230769, "acc_std": 0.06280457149908303, "f1": 0.5788461538461538, "f1_std": 0.06139689299486092, "bacc": 0.5812728937728938, "bacc_std": 0.06310715210594338} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 56, "C": 0.005994842503189409, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.06530016038836017, "f1": 0.4549107142857143, "f1_std": 0.06628142427395155, "bacc": 0.4581043956043956, "bacc_std": 0.06522336271557556} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 57, "C": 0.046415888336127774, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.06208597779735175, "f1": 0.5130240130240129, "f1_std": 0.05982349240456816, "bacc": 0.5171703296703296, "bacc_std": 0.06182705192992116} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 58, "C": 0.046415888336127774, "split": "test", "acc": 0.5, "acc_std": 0.06058545727430053, "f1": 0.48113341983484714, "f1_std": 0.06686716661848811, "bacc": 0.49793956043956045, "bacc_std": 0.060349940145765} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 59, "C": 0.046415888336127774, "split": "test", "acc": 0.5, "acc_std": 0.07049372585284015, "f1": 0.49870247568523435, "f1_std": 0.07079376091927915, "bacc": 0.4983974358974359, "bacc_std": 0.07048245248376149} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 60, "C": 0.046415888336127774, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.06145392029420603, "f1": 0.4302808302808303, "f1_std": 0.06518143974352124, "bacc": 0.44459706959706957, "bacc_std": 0.06203208067025528} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 61, "C": 2.782559402207126, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.06851418675706696, "f1": 0.46652740937223697, "f1_std": 0.06808041354702377, "bacc": 0.4626831501831502, "bacc_std": 0.06877757052817476} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 62, "C": 0.046415888336127774, "split": "test", "acc": 0.5576923076923077, "acc_std": 0.05965204827921104, "f1": 0.5309202124084157, "f1_std": 0.06108001199998092, "bacc": 0.5512820512820513, "bacc_std": 0.05911508708673211} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 63, "C": 0.000774263682681127, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.0582899303167482, "f1": 0.41254076698155645, "f1_std": 0.06068207948150631, "bacc": 0.440018315018315, "bacc_std": 0.057811500651997895} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 64, "C": 0.3593813663804626, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.06492526427230313, "f1": 0.42913205308015967, "f1_std": 0.06466349331266225, "bacc": 0.42719780219780223, "bacc_std": 0.06537100846888429} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 65, "C": 21.54434690031882, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.07229885379696575, "f1": 0.4612250712250712, "f1_std": 0.07148587535577662, "bacc": 0.4610805860805861, "bacc_std": 0.0724099441260941} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 66, "C": 0.005994842503189409, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.059633694458694236, "f1": 0.4464127826196792, "f1_std": 0.060002917487599935, "bacc": 0.44459706959706957, "bacc_std": 0.060086369976294754} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 67, "C": 0.046415888336127774, "split": "test", "acc": 0.5576923076923077, "acc_std": 0.06315533353443836, "f1": 0.5411519607843137, "f1_std": 0.06669566600566844, "bacc": 0.5528846153846154, "bacc_std": 0.06300436794157975} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 68, "C": 0.046415888336127774, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.061658764619783535, "f1": 0.519655172413793, "f1_std": 0.06545475822202458, "bacc": 0.5393772893772893, "bacc_std": 0.0618001817464826} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 69, "C": 0.046415888336127774, "split": "test", "acc": 0.5, "acc_std": 0.06551366224558357, "f1": 0.5088743784395958, "f1_std": 0.06320002246245965, "bacc": 0.5073260073260073, "bacc_std": 0.06589549714558184} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 70, "C": 0.3593813663804626, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.06596452112565722, "f1": 0.5166666666666667, "f1_std": 0.06730729106993083, "bacc": 0.5251831501831501, "bacc_std": 0.06606899378889165} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 71, "C": 0.046415888336127774, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.0692046531937603, "f1": 0.48833333333333334, "f1_std": 0.06845878149180999, "bacc": 0.48511904761904756, "bacc_std": 0.0696456038898842} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 72, "C": 0.046415888336127774, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.06278431191376717, "f1": 0.5262326415977532, "f1_std": 0.0648947412402049, "bacc": 0.5322802197802198, "bacc_std": 0.06255211310721301} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 73, "C": 0.046415888336127774, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.06437311495487913, "f1": 0.5332324680150767, "f1_std": 0.06453694780079018, "bacc": 0.5366300366300366, "bacc_std": 0.06438301138570883} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 74, "C": 0.005994842503189409, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.06650982042539096, "f1": 0.45248847926267277, "f1_std": 0.0674040453539751, "bacc": 0.4581043956043956, "bacc_std": 0.06632842495862071} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 75, "C": 0.005994842503189409, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.06686269380218843, "f1": 0.5121510673234811, "f1_std": 0.0695561140216728, "bacc": 0.5203754578754579, "bacc_std": 0.06720695319351098} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 76, "C": 0.046415888336127774, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.06339875682427774, "f1": 0.5332493368700265, "f1_std": 0.06440000710093323, "bacc": 0.5425824175824177, "bacc_std": 0.0636742448879188} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 77, "C": 0.046415888336127774, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.06792547255989616, "f1": 0.5178328113110722, "f1_std": 0.06865095560275412, "bacc": 0.5190018315018315, "bacc_std": 0.06840033560403395} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 78, "C": 0.3593813663804626, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.06661405221620076, "f1": 0.4846703296703297, "f1_std": 0.06559811094924423, "bacc": 0.4819139194139194, "bacc_std": 0.06669932097617383} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 79, "C": 0.3593813663804626, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.06877740443595372, "f1": 0.4286819502336744, "f1_std": 0.06585219232168535, "bacc": 0.4386446886446887, "bacc_std": 0.06804973938439084} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 80, "C": 0.005994842503189409, "split": "test", "acc": 0.5, "acc_std": 0.05878799287702273, "f1": 0.48099529780564265, "f1_std": 0.06252255687498927, "bacc": 0.5022893772893773, "bacc_std": 0.05920955489616655} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 81, "C": 2.782559402207126, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.0666249326964368, "f1": 0.5208741782954677, "f1_std": 0.0676424704182074, "bacc": 0.5235805860805861, "bacc_std": 0.06688628974389411} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 82, "C": 0.046415888336127774, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.06879417891983622, "f1": 0.47630059654516177, "f1_std": 0.0702567787586907, "bacc": 0.48031135531135527, "bacc_std": 0.06880264689280871} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 83, "C": 0.3593813663804626, "split": "test", "acc": 0.40384615384615385, "acc_std": 0.06356699862042779, "f1": 0.40613553113553114, "f1_std": 0.06227358675249944, "bacc": 0.40613553113553114, "bacc_std": 0.06393528343466984} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 84, "C": 0.3593813663804626, "split": "test", "acc": 0.5961538461538461, "acc_std": 0.062245208460823404, "f1": 0.5833752269236141, "f1_std": 0.06707436489376908, "bacc": 0.5931776556776557, "bacc_std": 0.06223610114653921} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 85, "C": 0.046415888336127774, "split": "test", "acc": 0.5, "acc_std": 0.05674900619519263, "f1": 0.48223886328725035, "f1_std": 0.05873094179180368, "bacc": 0.4965659340659341, "bacc_std": 0.056407223505892244} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 86, "C": 0.005994842503189409, "split": "test", "acc": 0.5769230769230769, "acc_std": 0.058055510571282616, "f1": 0.54158215010142, "f1_std": 0.060911496064142874, "bacc": 0.5677655677655679, "bacc_std": 0.05792118831166016} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 87, "C": 0.000774263682681127, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.06532639942273308, "f1": 0.45896551724137935, "f1_std": 0.06632191540661098, "bacc": 0.4624542124542125, "bacc_std": 0.06552811466720483} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 88, "C": 0.005994842503189409, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.06482927054600125, "f1": 0.5318438003220611, "f1_std": 0.06741926439826032, "bacc": 0.5412087912087913, "bacc_std": 0.0648591182521864} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 89, "C": 0.046415888336127774, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.0671287291119782, "f1": 0.4833380084151473, "f1_std": 0.06796790405137601, "bacc": 0.48076923076923084, "bacc_std": 0.06701428840373991} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 90, "C": 0.000774263682681127, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.057423733831061446, "f1": 0.4854898299698077, "f1_std": 0.06051120920740761, "bacc": 0.5155677655677656, "bacc_std": 0.05705978623543791} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 91, "C": 0.005994842503189409, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.0632370738949305, "f1": 0.4502595966411756, "f1_std": 0.0664542163762603, "bacc": 0.4610805860805861, "bacc_std": 0.06325945859839123} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 92, "C": 0.046415888336127774, "split": "test", "acc": 0.6346153846153846, "acc_std": 0.053722536674523876, "f1": 0.6111748047544855, "f1_std": 0.06479647095090908, "bacc": 0.6357600732600732, "bacc_std": 0.054051628363868696} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 93, "C": 0.046415888336127774, "split": "test", "acc": 0.36538461538461536, "acc_std": 0.05903638182255266, "f1": 0.358124966820619, "f1_std": 0.05341295982957303, "bacc": 0.36149267399267404, "bacc_std": 0.0584542460872325} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 94, "C": 2.782559402207126, "split": "test", "acc": 0.5, "acc_std": 0.06503476539558802, "f1": 0.495, "f1_std": 0.06637590711210078, "bacc": 0.5, "bacc_std": 0.06515775453503532} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 95, "C": 0.046415888336127774, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.06271862354711692, "f1": 0.5038961038961038, "f1_std": 0.06292346288352726, "bacc": 0.5157967032967032, "bacc_std": 0.06223336180154213} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 96, "C": 0.046415888336127774, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.06760895217499811, "f1": 0.508801785975699, "f1_std": 0.06702220410909783, "bacc": 0.5130494505494505, "bacc_std": 0.0673800212470026} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 97, "C": 0.005994842503189409, "split": "test", "acc": 0.38461538461538464, "acc_std": 0.05910846513730139, "f1": 0.3692505720823799, "f1_std": 0.05631197047697535, "bacc": 0.3807234432234432, "bacc_std": 0.058382527838171584} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 98, "C": 0.3593813663804626, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.06200167014356722, "f1": 0.5016420361247947, "f1_std": 0.06737422210034157, "bacc": 0.5176282051282052, "bacc_std": 0.062048232703861686} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 99, "C": 9.999999999999999e-05, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.062168636378100064, "f1": 0.3941770434227331, "f1_std": 0.05938720264522627, "bacc": 0.41781135531135527, "bacc_std": 0.0612532388929042} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 100, "C": 0.005994842503189409, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.06264585348273166, "f1": 0.4177777777777778, "f1_std": 0.06208568350949185, "bacc": 0.42536630036630035, "bacc_std": 0.06318038689483824} +eval results (random splits): + +| model | repr | clf | dataset | split | n_trials | C | C_std | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|-----------:|-------:|--------:|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | aabc_age | train | 100 | 4.6229 | 23.757 | 0.81585 | 0.14564 | 0.81378 | 0.14922 | 0.81628 | 0.14589 | +| flat_mae | patch | logistic | aabc_age | test | 100 | 4.6229 | 23.757 | 0.49154 | 0.057939 | 0.48266 | 0.058549 | 0.4906 | 0.058302 | + + +done! total time: 0:06:05 diff --git a/input_space_v3/flat_lr1e-3_2/eval_v2/aabc_sex__patch__logistic/config.yaml b/input_space_v3/flat_lr1e-3_2/eval_v2/aabc_sex__patch__logistic/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..8367c7bf799c903b278e968fe39e66e69362ae17 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_2/eval_v2/aabc_sex__patch__logistic/config.yaml @@ -0,0 +1,30 @@ +output_root: experiments/input_space_v3/output +name_prefix: eval_logistic +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_2; eval v2 (aabc_sex patch logistic) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: input_space_v3/flat_lr1e-3_2/eval_v2/aabc_sex__patch__logistic +model: flat_mae +representation: patch +dataset: aabc_sex +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/eval_v2/aabc_sex__patch__logistic +remote_dir: null diff --git a/input_space_v3/flat_lr1e-3_2/eval_v2/aabc_sex__patch__logistic/eval_table.csv b/input_space_v3/flat_lr1e-3_2/eval_v2/aabc_sex__patch__logistic/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..90f18594f16e41068559476753738fd08bb07804 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_2/eval_v2/aabc_sex__patch__logistic/eval_table.csv @@ -0,0 +1,203 @@ +model,repr,clf,dataset,trial,C,split,acc,acc_std,f1,f1_std,bacc,bacc_std +flat_mae,patch,logistic,aabc_sex,,0.046415888336127774,train,0.9489603024574669,0.009634768841197914,0.9475747398557507,0.009916994816244432,0.9462529274004684,0.010150416948130002 +flat_mae,patch,logistic,aabc_sex,,0.046415888336127774,test,0.9090909090909091,0.03929965406867286,0.905982905982906,0.04055637514814348,0.9090909090909091,0.04013147298526362 +flat_mae,patch,logistic,aabc_sex,1,0.046415888336127774,train,0.947069943289225,0.009713261414192004,0.945455884519075,0.010054561930449585,0.9433013863243354,0.010445258805549602 +flat_mae,patch,logistic,aabc_sex,1,0.046415888336127774,test,0.8727272727272727,0.04426067037617888,0.8683760683760684,0.046357898012057336,0.8661684782608696,0.046921319742068535 +flat_mae,patch,logistic,aabc_sex,2,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,2,2.782559402207126,test,0.9272727272727272,0.03658975153448534,0.9252717391304348,0.037673466685692936,0.9252717391304348,0.03781879751570675 +flat_mae,patch,logistic,aabc_sex,3,0.046415888336127774,train,0.945179584120983,0.00996115898403116,0.943691387252473,0.010263306700685072,0.9428837304727571,0.010542141551575988 +flat_mae,patch,logistic,aabc_sex,3,0.046415888336127774,test,0.8181818181818182,0.05155787889385147,0.8106060606060606,0.05449808092685692,0.8070652173913043,0.054488233100118716 +flat_mae,patch,logistic,aabc_sex,4,0.046415888336127774,train,0.9489603024574669,0.009743898461821457,0.947507690272219,0.010062515813540313,0.9461517043289662,0.010420304375942022 +flat_mae,patch,logistic,aabc_sex,4,0.046415888336127774,test,0.8545454545454545,0.0484127023834253,0.8533333333333333,0.04830948583179534,0.8627717391304348,0.04582675701400831 +flat_mae,patch,logistic,aabc_sex,5,0.046415888336127774,train,0.9584120982986768,0.008907631559130092,0.9573099157789711,0.009139780022409573,0.9567543011225417,0.009227307446565908 +flat_mae,patch,logistic,aabc_sex,5,0.046415888336127774,test,0.8727272727272727,0.04405344612743115,0.8663658451926415,0.04752002354087049,0.8600543478260869,0.04824681716422976 +flat_mae,patch,logistic,aabc_sex,6,0.046415888336127774,train,0.945179584120983,0.009603187560946622,0.9436193710331242,0.009931590743992079,0.942275564934494,0.01040112122575312 +flat_mae,patch,logistic,aabc_sex,6,0.046415888336127774,test,0.9454545454545454,0.030464720145665536,0.9435897435897436,0.031856996515590215,0.9408967391304348,0.03345344386828878 +flat_mae,patch,logistic,aabc_sex,7,0.046415888336127774,train,0.947069943289225,0.010265955697208602,0.9455280964989703,0.010602013591872107,0.9439095518625986,0.010891710236730795 +flat_mae,patch,logistic,aabc_sex,7,0.046415888336127774,test,0.8363636363636363,0.04913667899991302,0.8343927735028438,0.04940928192654683,0.8410326086956521,0.04852533304257399 +flat_mae,patch,logistic,aabc_sex,8,0.005994842503189409,train,0.9224952741020794,0.011260941758491235,0.9199682662681501,0.011684850471413011,0.9171942319528708,0.01196882684691904 +flat_mae,patch,logistic,aabc_sex,8,0.005994842503189409,test,0.8181818181818182,0.05039704831970658,0.8131793478260869,0.05207898850767568,0.8131793478260869,0.05251532660302583 +flat_mae,patch,logistic,aabc_sex,9,0.046415888336127774,train,0.945179584120983,0.00988901790504155,0.9435455084069022,0.010233716613818736,0.9416673993962308,0.010625909761330855 +flat_mae,patch,logistic,aabc_sex,9,0.046415888336127774,test,0.9090909090909091,0.03866232710520776,0.905982905982906,0.04030850357587018,0.9035326086956521,0.04111424322522534 +flat_mae,patch,logistic,aabc_sex,10,0.046415888336127774,train,0.9395085066162571,0.010374348294385733,0.9376638680217999,0.010765733689126396,0.9355491075353908,0.011215726249547826 +flat_mae,patch,logistic,aabc_sex,10,0.046415888336127774,test,0.8727272727272727,0.04497161639291759,0.8711943793911007,0.0452538409623905,0.8783967391304348,0.043895105956963616 +flat_mae,patch,logistic,aabc_sex,11,0.046415888336127774,train,0.947069943289225,0.009994846460617239,0.9455985191279309,0.010296060627391794,0.9445177174008617,0.010526698413997716 +flat_mae,patch,logistic,aabc_sex,11,0.046415888336127774,test,0.9272727272727272,0.03654456805799537,0.9252717391304348,0.037494148921764246,0.9252717391304348,0.03743085630396134 +flat_mae,patch,logistic,aabc_sex,12,0.3593813663804626,train,0.994328922495274,0.003308688043423599,0.9941822314276811,0.0033978617095069123,0.99388170813916,0.003636273784096473 +flat_mae,patch,logistic,aabc_sex,12,0.3593813663804626,test,0.7636363636363637,0.057234319011649576,0.7555555555555555,0.059949400405274966,0.7540760869565217,0.059762772694239845 +flat_mae,patch,logistic,aabc_sex,13,0.046415888336127774,train,0.947069943289225,0.009625155719704697,0.9455985191279309,0.009922154698233168,0.9445177174008617,0.010209573697937548 +flat_mae,patch,logistic,aabc_sex,13,0.046415888336127774,test,0.8909090909090909,0.04123673240175019,0.8879076086956521,0.04248939819823548,0.8879076086956521,0.04267870149782034 +flat_mae,patch,logistic,aabc_sex,14,0.046415888336127774,train,0.9489603024574669,0.009159496150129454,0.9475747398557507,0.009428370243074006,0.9467598698672295,0.009632078279470655 +flat_mae,patch,logistic,aabc_sex,14,0.046415888336127774,test,0.8909090909090909,0.042125526702938676,0.8879076086956521,0.04344073935425481,0.8879076086956521,0.043563628064686236 +flat_mae,patch,logistic,aabc_sex,15,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,15,166.81005372000556,test,0.8181818181818182,0.04852855000192416,0.8106060606060606,0.05128818303706811,0.8070652173913043,0.05137415476088575 +flat_mae,patch,logistic,aabc_sex,16,0.3593813663804626,train,0.994328922495274,0.0033071475726207896,0.9941822314276811,0.003396108894579857,0.99388170813916,0.0036103519255005637 +flat_mae,patch,logistic,aabc_sex,16,0.3593813663804626,test,0.8909090909090909,0.04137310980426819,0.8863636363636364,0.04409836968745209,0.8817934782608696,0.04545949364657925 +flat_mae,patch,logistic,aabc_sex,17,0.046415888336127774,train,0.947069943289225,0.009675315473814446,0.9456671655368724,0.009947314294710196,0.9451258829391249,0.010126420651487692 +flat_mae,patch,logistic,aabc_sex,17,0.046415888336127774,test,0.8727272727272727,0.041365310655425196,0.8639095086603039,0.04673459971200336,0.8539402173913043,0.04712889609968627 +flat_mae,patch,logistic,aabc_sex,18,0.005994842503189409,train,0.9130434782608695,0.012462465184521885,0.9102702144606035,0.01292992020012634,0.9078079662358216,0.013215827356259433 +flat_mae,patch,logistic,aabc_sex,18,0.005994842503189409,test,0.9090909090909091,0.03702375382247779,0.9079959852793577,0.03716064950145421,0.9157608695652174,0.03505598188283607 +flat_mae,patch,logistic,aabc_sex,19,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,19,21.54434690031882,test,0.8727272727272727,0.04295644536442821,0.8699763593380614,0.04372141722662848,0.8722826086956521,0.043372580122950255 +flat_mae,patch,logistic,aabc_sex,20,0.046415888336127774,train,0.9546313799621928,0.009560427531190014,0.9534289990316049,0.009837180242253765,0.9528781617280695,0.010085909010521862 +flat_mae,patch,logistic,aabc_sex,20,0.046415888336127774,test,0.9272727272727272,0.03269272924450552,0.9242424242424243,0.03485450048439878,0.9191576086956521,0.036971846447023296 +flat_mae,patch,logistic,aabc_sex,21,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,21,21.54434690031882,test,0.8363636363636363,0.04914527629201182,0.8281846581048247,0.05363818827395226,0.8226902173913043,0.053742046353846926 +flat_mae,patch,logistic,aabc_sex,22,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,22,166.81005372000556,test,0.9272727272727272,0.034764168881429185,0.9260752688172043,0.03511102367777514,0.9313858695652174,0.03339806958094755 +flat_mae,patch,logistic,aabc_sex,23,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,23,21.54434690031882,test,0.8181818181818182,0.05121730079598537,0.8166666666666667,0.05143330982040317,0.8254076086956521,0.050717267457166065 +flat_mae,patch,logistic,aabc_sex,24,0.046415888336127774,train,0.9508506616257089,0.01010487139235879,0.9494843391902215,0.010415657905264082,0.9483938567953341,0.010700559760159553 +flat_mae,patch,logistic,aabc_sex,24,0.046415888336127774,test,0.8545454545454545,0.0477372837985448,0.8484848484848485,0.05072225093312138,0.8444293478260869,0.05120056934869412 +flat_mae,patch,logistic,aabc_sex,25,0.005994842503189409,train,0.9054820415879017,0.012918501563585502,0.9025997937840624,0.013377886041997038,0.9006638529851403,0.013625230403607622 +flat_mae,patch,logistic,aabc_sex,25,0.005994842503189409,test,0.9272727272727272,0.03218005131256536,0.9252717391304348,0.03323151323042152,0.9252717391304348,0.03389648207304361 +flat_mae,patch,logistic,aabc_sex,26,0.046415888336127774,train,0.9621928166351607,0.007878395637468113,0.9612386060552771,0.00807555236963011,0.9612386060552771,0.008134327527871875 +flat_mae,patch,logistic,aabc_sex,26,0.046415888336127774,test,0.8181818181818182,0.04847866021114616,0.8106060606060606,0.051597052806010305,0.8070652173913043,0.05156378485539002 +flat_mae,patch,logistic,aabc_sex,27,0.046415888336127774,train,0.943289224952741,0.009928655846102866,0.9416372462488967,0.010273386544754503,0.9400334124681262,0.01072191227829336 +flat_mae,patch,logistic,aabc_sex,27,0.046415888336127774,test,0.8727272727272727,0.04300788319051432,0.8683760683760684,0.044962123539242956,0.8661684782608696,0.04537478201255267 +flat_mae,patch,logistic,aabc_sex,28,0.005994842503189409,train,0.9149338374291115,0.01233366052573379,0.9122807017543859,0.012807654555768018,0.9100501187021894,0.013181695619817066 +flat_mae,patch,logistic,aabc_sex,28,0.005994842503189409,test,0.8363636363636363,0.046010792840932846,0.8250265111346766,0.05203977459923469,0.8165760869565217,0.05163356176171513 +flat_mae,patch,logistic,aabc_sex,29,0.046415888336127774,train,0.941398865784499,0.010970242061323791,0.9398080346491953,0.011295898080298324,0.9390075910782849,0.011566954016059882 +flat_mae,patch,logistic,aabc_sex,29,0.046415888336127774,test,0.8545454545454545,0.04845656144535471,0.8505434782608696,0.0498346362948025,0.8505434782608696,0.049933839882689346 +flat_mae,patch,logistic,aabc_sex,30,0.046415888336127774,train,0.9508506616257089,0.00948531749382498,0.9494189467490438,0.009790140451424956,0.9477856912570708,0.010058261717881213 +flat_mae,patch,logistic,aabc_sex,30,0.046415888336127774,test,0.8909090909090909,0.04324827422152814,0.8879076086956521,0.044573852583238524,0.8879076086956521,0.044640715869438 +flat_mae,patch,logistic,aabc_sex,31,0.046415888336127774,train,0.945179584120983,0.010184792071012971,0.9435455084069022,0.010532056076727981,0.9416673993962308,0.010846520701678564 +flat_mae,patch,logistic,aabc_sex,31,0.046415888336127774,test,0.8545454545454545,0.04710296791898423,0.8521505376344086,0.04755799431647121,0.8566576086956521,0.046560219757889904 +flat_mae,patch,logistic,aabc_sex,32,0.046415888336127774,train,0.943289224952741,0.010273001368806949,0.9417126990656403,0.010602321513238635,0.9406415780063895,0.01093751865966404 +flat_mae,patch,logistic,aabc_sex,32,0.046415888336127774,test,0.9090909090909091,0.03553722759944205,0.9045470322804582,0.0386887816089132,0.8974184782608696,0.04034603166378916 +flat_mae,patch,logistic,aabc_sex,33,0.046415888336127774,train,0.947069943289225,0.009470326636162159,0.9455985191279309,0.009748763188981087,0.9445177174008617,0.009948413847178672 +flat_mae,patch,logistic,aabc_sex,33,0.046415888336127774,test,0.8909090909090909,0.04172180197846898,0.8879076086956521,0.04303168741071197,0.8879076086956521,0.043335012213441305 +flat_mae,patch,logistic,aabc_sex,34,0.046415888336127774,train,0.9546313799621928,0.009520944786167452,0.9533701592525121,0.009802858873930497,0.9522699961898062,0.010011927276036382 +flat_mae,patch,logistic,aabc_sex,34,0.046415888336127774,test,0.8909090909090909,0.04206919133408832,0.8863636363636364,0.044706754052448595,0.8817934782608696,0.04581491792929106 +flat_mae,patch,logistic,aabc_sex,35,0.005994842503189409,train,0.9130434782608695,0.01243076444334187,0.9102702144606035,0.012920891001731561,0.9078079662358216,0.01328399049489258 +flat_mae,patch,logistic,aabc_sex,35,0.005994842503189409,test,0.9090909090909091,0.03775972755189567,0.905982905982906,0.039296576147445396,0.9035326086956521,0.03988512298375757 +flat_mae,patch,logistic,aabc_sex,36,0.046415888336127774,train,0.945179584120983,0.009367069021529359,0.9435455084069022,0.009692351317625454,0.9416673993962308,0.010041371298903227 +flat_mae,patch,logistic,aabc_sex,36,0.046415888336127774,test,0.8909090909090909,0.04101964858757244,0.8891129032258065,0.041468349270263626,0.8940217391304348,0.040510718160778836 +flat_mae,patch,logistic,aabc_sex,37,0.046415888336127774,train,0.9546313799621928,0.009241729917284032,0.9533701592525121,0.009524489493023328,0.9522699961898062,0.009776970465865748 +flat_mae,patch,logistic,aabc_sex,37,0.046415888336127774,test,0.7454545454545455,0.059154092094885945,0.7348484848484849,0.06290017157784876,0.7323369565217391,0.062117807030826505 +flat_mae,patch,logistic,aabc_sex,38,0.000774263682681127,train,0.8809073724007561,0.013761907704457626,0.8771929824561404,0.014302144703565584,0.8751648641519387,0.01459411158575613 +flat_mae,patch,logistic,aabc_sex,38,0.000774263682681127,test,0.8727272727272727,0.04094582593082015,0.8639095086603039,0.046127049310700156,0.8539402173913043,0.04664858670147762 +flat_mae,patch,logistic,aabc_sex,39,0.046415888336127774,train,0.9508506616257089,0.008919502237414122,0.9495480822842386,0.009168969938785295,0.9490020223335971,0.009349984920183463 +flat_mae,patch,logistic,aabc_sex,39,0.046415888336127774,test,0.8545454545454545,0.046470109472435746,0.8505434782608696,0.04783956222507828,0.8505434782608696,0.04789976345478235 +flat_mae,patch,logistic,aabc_sex,40,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,40,166.81005372000556,test,0.8545454545454545,0.046133632700186326,0.8484848484848485,0.04883630542169441,0.8444293478260869,0.04918407135265216 +flat_mae,patch,logistic,aabc_sex,41,0.005994842503189409,train,0.9130434782608695,0.01246564871259849,0.9101456339359566,0.012972370940059376,0.9071998006975586,0.0133008236453848 +flat_mae,patch,logistic,aabc_sex,41,0.005994842503189409,test,0.8909090909090909,0.04268359856873433,0.8879076086956521,0.04402556638984178,0.8879076086956521,0.04416115309771717 +flat_mae,patch,logistic,aabc_sex,42,0.046415888336127774,train,0.947069943289225,0.009555468480980754,0.9455985191279309,0.009851478064014945,0.9445177174008617,0.01014346958013646 +flat_mae,patch,logistic,aabc_sex,42,0.046415888336127774,test,0.8545454545454545,0.04868850560976785,0.8521505376344086,0.04936857149554626,0.8566576086956521,0.048745620982467014 +flat_mae,patch,logistic,aabc_sex,43,0.046415888336127774,train,0.943289224952741,0.009900574550220281,0.9416372462488967,0.010226194979800159,0.9400334124681262,0.01057251978226379 +flat_mae,patch,logistic,aabc_sex,43,0.046415888336127774,test,0.9636363636363636,0.02447731957453102,0.9630376344086022,0.024630179752562296,0.96875,0.021035196509362586 +flat_mae,patch,logistic,aabc_sex,44,0.046415888336127774,train,0.9565217391304348,0.008558367263007075,0.9553414450623061,0.008821695862491461,0.9545121486561741,0.009172185694155722 +flat_mae,patch,logistic,aabc_sex,44,0.046415888336127774,test,0.8363636363636363,0.04821088660019495,0.8307692307692308,0.05072551162789429,0.8288043478260869,0.05089046168546734 +flat_mae,patch,logistic,aabc_sex,45,0.046415888336127774,train,0.945179584120983,0.010008214864014304,0.943691387252473,0.010318642002687537,0.9428837304727571,0.010634716185317696 +flat_mae,patch,logistic,aabc_sex,45,0.046415888336127774,test,0.9636363636363636,0.02440745042735182,0.9630376344086022,0.024547986237309635,0.96875,0.02097515271100547 +flat_mae,patch,logistic,aabc_sex,46,0.046415888336127774,train,0.9489603024574669,0.010002823347777037,0.947507690272219,0.010321808208111767,0.9461517043289662,0.010624415312074307 +flat_mae,patch,logistic,aabc_sex,46,0.046415888336127774,test,0.9090909090909091,0.037355986830307615,0.9071259709557582,0.03807730881761385,0.9096467391304348,0.03764147254145621 +flat_mae,patch,logistic,aabc_sex,47,0.046415888336127774,train,0.945179584120983,0.009765585217283467,0.9436193710331242,0.010084922407421502,0.942275564934494,0.010422500920602394 +flat_mae,patch,logistic,aabc_sex,47,0.046415888336127774,test,0.8545454545454545,0.04475558601268496,0.84593837535014,0.049115168407924445,0.8383152173913043,0.04931960134450676 +flat_mae,patch,logistic,aabc_sex,48,0.046415888336127774,train,0.9376181474480151,0.010664367717757296,0.935672514619883,0.01106394367973303,0.9333069550690232,0.011478101040615439 +flat_mae,patch,logistic,aabc_sex,48,0.046415888336127774,test,0.9636363636363636,0.02420889802947778,0.9626358695652174,0.024842128203414998,0.9626358695652174,0.02485694163569818 +flat_mae,patch,logistic,aabc_sex,49,0.3593813663804626,train,0.9924385633270322,0.003628433998982546,0.9922381665052675,0.0037301307583891535,0.9916395556727923,0.004031838553672643 +flat_mae,patch,logistic,aabc_sex,49,0.3593813663804626,test,0.8181818181818182,0.049444704903307934,0.8151881720430108,0.05011833100584977,0.8192934782608696,0.049735144358315775 +flat_mae,patch,logistic,aabc_sex,50,0.046415888336127774,train,0.947069943289225,0.009708321539062289,0.9455280964989703,0.01003088281110607,0.9439095518625986,0.010409987502788438 +flat_mae,patch,logistic,aabc_sex,50,0.046415888336127774,test,0.8909090909090909,0.04323965122450144,0.8879076086956521,0.04435367947873587,0.8879076086956521,0.044255169712690424 +flat_mae,patch,logistic,aabc_sex,51,0.046415888336127774,train,0.943289224952741,0.010004086486046022,0.9417862487895061,0.01030509805652496,0.9412497435446525,0.010602029944503237 +flat_mae,patch,logistic,aabc_sex,51,0.046415888336127774,test,0.9272727272727272,0.03467991058735746,0.9242424242424243,0.03692372011134154,0.9191576086956521,0.03889490047200075 +flat_mae,patch,logistic,aabc_sex,52,0.046415888336127774,train,0.9508506616257089,0.009316948089743189,0.9494843391902215,0.00960263605498813,0.9483938567953341,0.009907765893747382 +flat_mae,patch,logistic,aabc_sex,52,0.046415888336127774,test,0.9090909090909091,0.03813961303742643,0.9071259709557582,0.03892950847312275,0.9096467391304348,0.03852719403760353 +flat_mae,patch,logistic,aabc_sex,53,0.005994842503189409,train,0.9130434782608695,0.01300946223374002,0.9103918102813374,0.013462630562802322,0.9084161317740849,0.013674053172698021 +flat_mae,patch,logistic,aabc_sex,53,0.005994842503189409,test,0.8545454545454545,0.04590022956783727,0.8484848484848485,0.04876026578485079,0.8444293478260869,0.04915378549737187 +flat_mae,patch,logistic,aabc_sex,54,0.046415888336127774,train,0.9508506616257089,0.009253307935453595,0.9493518927677125,0.009592600278912301,0.9471775257188078,0.010046620663576642 +flat_mae,patch,logistic,aabc_sex,54,0.046415888336127774,test,0.8363636363636363,0.05027000157003416,0.8343927735028438,0.05054279930158628,0.8410326086956521,0.04924854913021658 +flat_mae,patch,logistic,aabc_sex,55,0.3593813663804626,train,0.9924385633270322,0.003940052718307678,0.9922381665052675,0.004051461999653356,0.9916395556727923,0.0043937486670029245 +flat_mae,patch,logistic,aabc_sex,55,0.3593813663804626,test,0.8545454545454545,0.04848748326174342,0.8521505376344086,0.04917158697323246,0.8566576086956521,0.04877027897253205 +flat_mae,patch,logistic,aabc_sex,56,0.046415888336127774,train,0.9603024574669187,0.008765133766321109,0.9591726479895037,0.009047937740614605,0.9577801225123832,0.009435459278917212 +flat_mae,patch,logistic,aabc_sex,56,0.046415888336127774,test,0.8363636363636363,0.04967416476024631,0.8307692307692308,0.05200060609016469,0.8288043478260869,0.05239560900929229 +flat_mae,patch,logistic,aabc_sex,57,0.046415888336127774,train,0.945179584120983,0.009694941374285258,0.9436193710331242,0.010011197750062307,0.942275564934494,0.010342841978575929 +flat_mae,patch,logistic,aabc_sex,57,0.046415888336127774,test,0.8909090909090909,0.04059802543747033,0.8863636363636364,0.04319418705336951,0.8817934782608696,0.044147461605876286 +flat_mae,patch,logistic,aabc_sex,58,0.046415888336127774,train,0.9508506616257089,0.0092844805322457,0.9494189467490438,0.009593642454781727,0.9477856912570708,0.009953812377649612 +flat_mae,patch,logistic,aabc_sex,58,0.046415888336127774,test,0.8,0.05297990886932187,0.795677136102668,0.054041794647281365,0.7975543478260869,0.05382640879522031 +flat_mae,patch,logistic,aabc_sex,59,0.005994842503189409,train,0.9092627599243857,0.012293888611224173,0.9062389223679547,0.01283285765750282,0.9033236613030862,0.013300287448544128 +flat_mae,patch,logistic,aabc_sex,59,0.005994842503189409,test,0.9090909090909091,0.037484542268659354,0.9071259709557582,0.03820229752403159,0.9096467391304348,0.03772852986274875 +flat_mae,patch,logistic,aabc_sex,60,0.046415888336127774,train,0.9489603024574669,0.009296308213878463,0.9474389216202193,0.009614477289710707,0.9455435387907032,0.009992322077460689 +flat_mae,patch,logistic,aabc_sex,60,0.046415888336127774,test,0.8545454545454545,0.04784962671598914,0.84593837535014,0.05265936801278922,0.8383152173913043,0.05269466990949716 +flat_mae,patch,logistic,aabc_sex,61,0.046415888336127774,train,0.945179584120983,0.009708590235157048,0.9436193710331242,0.0100277359908934,0.942275564934494,0.01036529794909999 +flat_mae,patch,logistic,aabc_sex,61,0.046415888336127774,test,0.9454545454545454,0.030904277700106335,0.9442755825734549,0.03146511125105942,0.9470108695652174,0.03062991631746194 +flat_mae,patch,logistic,aabc_sex,62,0.046415888336127774,train,0.943289224952741,0.010004465825051524,0.9416372462488967,0.010362952770801051,0.9400334124681262,0.0108190621995739 +flat_mae,patch,logistic,aabc_sex,62,0.046415888336127774,test,0.9454545454545454,0.02778741019399355,0.9435897435897436,0.029062852015867845,0.9408967391304348,0.030442408060635518 +flat_mae,patch,logistic,aabc_sex,63,0.046415888336127774,train,0.9376181474480151,0.011198599397744681,0.935672514619883,0.011625771690770342,0.9333069550690232,0.012052373694987736 +flat_mae,patch,logistic,aabc_sex,63,0.046415888336127774,test,0.9272727272727272,0.033829734097254,0.9252717391304348,0.03487657627072886,0.9252717391304348,0.03526266212674039 +flat_mae,patch,logistic,aabc_sex,64,0.3593813663804626,train,0.996219281663516,0.0024954201710125413,0.9961190832526338,0.0025659688497241618,0.9955156950672646,0.002959814507770482 +flat_mae,patch,logistic,aabc_sex,64,0.3593813663804626,test,0.8545454545454545,0.047591582004446416,0.8505434782608696,0.04900973213814301,0.8505434782608696,0.049167542243266374 +flat_mae,patch,logistic,aabc_sex,65,0.046415888336127774,train,0.947069943289225,0.009868121001872121,0.945455884519075,0.01022283702417133,0.9433013863243354,0.010580062147658203 +flat_mae,patch,logistic,aabc_sex,65,0.046415888336127774,test,0.9090909090909091,0.03826477568013747,0.9045470322804582,0.041497043154271794,0.8974184782608696,0.043090696607070364 +flat_mae,patch,logistic,aabc_sex,66,0.046415888336127774,train,0.945179584120983,0.009607943458376808,0.9436193710331242,0.009910761376462192,0.942275564934494,0.010207703544465188 +flat_mae,patch,logistic,aabc_sex,66,0.046415888336127774,test,0.9272727272727272,0.03387241008976564,0.9242424242424243,0.036035130249407944,0.9191576086956521,0.037935072911987194 +flat_mae,patch,logistic,aabc_sex,67,0.3593813663804626,train,0.994328922495274,0.0033948135003653702,0.9941822314276811,0.0034864208873863095,0.99388170813916,0.003722456659192379 +flat_mae,patch,logistic,aabc_sex,67,0.3593813663804626,test,0.9272727272727272,0.03620465245661299,0.9252717391304348,0.037264874439083016,0.9252717391304348,0.03738539108560116 +flat_mae,patch,logistic,aabc_sex,68,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,68,2.782559402207126,test,0.9090909090909091,0.03697913640048427,0.9045470322804582,0.03996583746575895,0.8974184782608696,0.04160381275281441 +flat_mae,patch,logistic,aabc_sex,69,0.046415888336127774,train,0.945179584120983,0.009898888121144056,0.9436193710331242,0.010210711711967848,0.942275564934494,0.010496202974395703 +flat_mae,patch,logistic,aabc_sex,69,0.046415888336127774,test,0.9636363636363636,0.025858074174230382,0.9626358695652174,0.026631317943634693,0.9626358695652174,0.026926550632376582 +flat_mae,patch,logistic,aabc_sex,70,0.3593813663804626,train,0.994328922495274,0.0033510048856196985,0.9941822314276811,0.003440257937258071,0.99388170813916,0.0036342636578965194 +flat_mae,patch,logistic,aabc_sex,70,0.3593813663804626,test,0.8727272727272727,0.044686322717544434,0.8699763593380614,0.04555789248750382,0.8722826086956521,0.04521669921345348 +flat_mae,patch,logistic,aabc_sex,71,0.046415888336127774,train,0.9527410207939508,0.008700388288597734,0.9514580924590283,0.008947555980521594,0.9506360092617017,0.009137851912799366 +flat_mae,patch,logistic,aabc_sex,71,0.046415888336127774,test,0.8727272727272727,0.04338411942383776,0.8663658451926415,0.046612304611181876,0.8600543478260869,0.047130065240854065 +flat_mae,patch,logistic,aabc_sex,72,0.005994842503189409,train,0.9035916824196597,0.013001645198325624,0.900308545034642,0.013614499982250743,0.8972053694422463,0.014086107809061934 +flat_mae,patch,logistic,aabc_sex,72,0.005994842503189409,test,0.9454545454545454,0.030134442554976427,0.9435897435897436,0.0314911311008407,0.9408967391304348,0.03280960466904634 +flat_mae,patch,logistic,aabc_sex,73,0.046415888336127774,train,0.943289224952741,0.009879664474394236,0.9416372462488967,0.01021073591170539,0.9400334124681262,0.010530895328950062 +flat_mae,patch,logistic,aabc_sex,73,0.046415888336127774,test,0.9272727272727272,0.03342101086056718,0.9242424242424243,0.035540376484034374,0.9191576086956521,0.03725583146313884 +flat_mae,patch,logistic,aabc_sex,74,0.046415888336127774,train,0.947069943289225,0.009400234408304863,0.9455280964989703,0.009715205013171017,0.9439095518625986,0.010098831740918125 +flat_mae,patch,logistic,aabc_sex,74,0.046415888336127774,test,0.8727272727272727,0.04654447442149876,0.8699763593380614,0.047472654440359224,0.8722826086956521,0.04711054185814096 +flat_mae,patch,logistic,aabc_sex,75,0.046415888336127774,train,0.947069943289225,0.009589060743454473,0.9455280964989703,0.009914577181843671,0.9439095518625986,0.010267778925482522 +flat_mae,patch,logistic,aabc_sex,75,0.046415888336127774,test,0.8727272727272727,0.042933413753496526,0.8699763593380614,0.043927472476089656,0.8722826086956521,0.043963116327614335 +flat_mae,patch,logistic,aabc_sex,76,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,76,21.54434690031882,test,0.8545454545454545,0.04480984248433677,0.84593837535014,0.0492725353999537,0.8383152173913043,0.049525103920143775 +flat_mae,patch,logistic,aabc_sex,77,0.3593813663804626,train,0.994328922495274,0.003256993943543512,0.9941822314276811,0.003345139290608214,0.99388170813916,0.003571995446211909 +flat_mae,patch,logistic,aabc_sex,77,0.3593813663804626,test,0.8727272727272727,0.04530132722044557,0.8663658451926415,0.048700449815947025,0.8600543478260869,0.04937443774954454 +flat_mae,patch,logistic,aabc_sex,78,0.3593813663804626,train,0.994328922495274,0.0032167226119328082,0.9941822314276811,0.0033024484467446672,0.99388170813916,0.003488862355075004 +flat_mae,patch,logistic,aabc_sex,78,0.3593813663804626,test,0.9454545454545454,0.03048209879761298,0.9435897435897436,0.03186813051360379,0.9408967391304348,0.033220203165154207 +flat_mae,patch,logistic,aabc_sex,79,0.046415888336127774,train,0.941398865784499,0.01008672624672322,0.9397310517940294,0.010422045724085805,0.9383994255400216,0.010764190921157843 +flat_mae,patch,logistic,aabc_sex,79,0.046415888336127774,test,0.9454545454545454,0.029875134081098896,0.9427282193682749,0.03248839899225682,0.9347826086956521,0.03572026901000955 +flat_mae,patch,logistic,aabc_sex,80,0.046415888336127774,train,0.9489603024574669,0.00942459299036538,0.947507690272219,0.009746965709987232,0.9461517043289662,0.010153202713354265 +flat_mae,patch,logistic,aabc_sex,80,0.046415888336127774,test,0.8727272727272727,0.0463533535834221,0.8683760683760684,0.048386851332055204,0.8661684782608696,0.048866110843547694 +flat_mae,patch,logistic,aabc_sex,81,0.046415888336127774,train,0.9395085066162571,0.00965652823546856,0.9377463959988231,0.009960203333979617,0.936157273073654,0.010180670247618949 +flat_mae,patch,logistic,aabc_sex,81,0.046415888336127774,test,0.9454545454545454,0.032853795835891576,0.9442755825734549,0.0333650414797964,0.9470108695652174,0.03209975143277161 +flat_mae,patch,logistic,aabc_sex,82,0.3593813663804626,train,0.994328922495274,0.0033447094396099252,0.9941822314276811,0.003433239457470417,0.99388170813916,0.003613018732951055 +flat_mae,patch,logistic,aabc_sex,82,0.3593813663804626,test,0.8545454545454545,0.04423042593636641,0.84593837535014,0.04841159693018112,0.8383152173913043,0.048776578278426956 +flat_mae,patch,logistic,aabc_sex,83,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,83,166.81005372000556,test,0.8363636363636363,0.048241815132442155,0.8250265111346766,0.05416128083129135,0.8165760869565217,0.053122104248750336 +flat_mae,patch,logistic,aabc_sex,84,0.046415888336127774,train,0.947069943289225,0.010255835963217202,0.9455985191279309,0.010562315990842713,0.9445177174008617,0.010741160088677594 +flat_mae,patch,logistic,aabc_sex,84,0.046415888336127774,test,0.8363636363636363,0.050634323445107855,0.8307692307692308,0.05285238509723649,0.8288043478260869,0.053238752964047016 +flat_mae,patch,logistic,aabc_sex,85,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,85,2.782559402207126,test,0.8545454545454545,0.04540842751358162,0.84593837535014,0.04988941381768201,0.8383152173913043,0.0501507220510753 +flat_mae,patch,logistic,aabc_sex,86,0.046415888336127774,train,0.947069943289225,0.00957681850634643,0.9455985191279309,0.009864398586203348,0.9445177174008617,0.010120433988619216 +flat_mae,patch,logistic,aabc_sex,86,0.046415888336127774,test,0.9454545454545454,0.03236198157158598,0.9435897435897436,0.03378656628725523,0.9408967391304348,0.035160367853775805 +flat_mae,patch,logistic,aabc_sex,87,0.046415888336127774,train,0.947069943289225,0.009801517938358444,0.9455985191279309,0.01009825735772143,0.9445177174008617,0.010361741208832858 +flat_mae,patch,logistic,aabc_sex,87,0.046415888336127774,test,0.9454545454545454,0.029020369022150952,0.9427282193682749,0.031580762545316436,0.9347826086956521,0.034698267309093526 +flat_mae,patch,logistic,aabc_sex,88,0.3593813663804626,train,0.994328922495274,0.0032325893489971555,0.9941893034853195,0.003310334277880403,0.9944898736774231,0.00319763877121477 +flat_mae,patch,logistic,aabc_sex,88,0.3593813663804626,test,0.8909090909090909,0.04108324948722718,0.8863636363636364,0.04358167475898493,0.8817934782608696,0.0447661475622878 +flat_mae,patch,logistic,aabc_sex,89,0.046415888336127774,train,0.9546313799621928,0.009455178978647743,0.9534289990316049,0.009721811401385316,0.9528781617280695,0.009931385344502627 +flat_mae,patch,logistic,aabc_sex,89,0.046415888336127774,test,0.8909090909090909,0.03940266383577856,0.884453781512605,0.04362209950132576,0.8756793478260869,0.04497025005347213 +flat_mae,patch,logistic,aabc_sex,90,0.046415888336127774,train,0.945179584120983,0.01010149359314841,0.9434697855750487,0.010470403707819816,0.9410592338579677,0.010896099990631802 +flat_mae,patch,logistic,aabc_sex,90,0.046415888336127774,test,0.8727272727272727,0.046580952372906034,0.8683760683760684,0.04878424686803953,0.8661684782608696,0.04935393121695989 +flat_mae,patch,logistic,aabc_sex,91,0.046415888336127774,train,0.9527410207939508,0.009508141315181996,0.951396009511314,0.009824075810593524,0.9500278437234386,0.010220441863467229 +flat_mae,patch,logistic,aabc_sex,91,0.046415888336127774,test,0.9090909090909091,0.039783945430909524,0.905982905982906,0.04141461136454477,0.9035326086956521,0.04192449505135774 +flat_mae,patch,logistic,aabc_sex,92,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,92,2.782559402207126,test,0.9090909090909091,0.03795109510718645,0.9045470322804582,0.041034562652099586,0.8974184782608696,0.04273976405756128 +flat_mae,patch,logistic,aabc_sex,93,0.046415888336127774,train,0.9508506616257089,0.009341052553644731,0.9494843391902215,0.009630832745068721,0.9483938567953341,0.009914350938103082 +flat_mae,patch,logistic,aabc_sex,93,0.046415888336127774,test,0.9090909090909091,0.03702132510319822,0.9027925061859314,0.042028994844589294,0.8913043478260869,0.04426462784078048 +flat_mae,patch,logistic,aabc_sex,94,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,94,21.54434690031882,test,0.8545454545454545,0.04616257294059621,0.8484848484848485,0.048686409064739616,0.8444293478260869,0.048720655005097264 +flat_mae,patch,logistic,aabc_sex,95,0.046415888336127774,train,0.9489603024574669,0.009339120455713413,0.9474389216202193,0.009667722648033741,0.9455435387907032,0.010064085014157332 +flat_mae,patch,logistic,aabc_sex,95,0.046415888336127774,test,0.9090909090909091,0.03858618773988331,0.9071259709557582,0.039310523325167386,0.9096467391304348,0.03882445226517596 +flat_mae,patch,logistic,aabc_sex,96,0.005994842503189409,train,0.9073724007561437,0.012501144561862226,0.904218013856813,0.01304816065043848,0.9010815088367186,0.013429402778106595 +flat_mae,patch,logistic,aabc_sex,96,0.005994842503189409,test,0.9090909090909091,0.039017266785847736,0.905982905982906,0.04069436110218064,0.9035326086956521,0.04149131685556947 +flat_mae,patch,logistic,aabc_sex,97,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,97,166.81005372000556,test,0.8363636363636363,0.04907365353297406,0.8343927735028438,0.049611127645771746,0.8410326086956521,0.049372924823587606 +flat_mae,patch,logistic,aabc_sex,98,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,98,21.54434690031882,test,0.8727272727272727,0.04406004918159189,0.8683760683760684,0.04613919707544321,0.8661684782608696,0.04696631266417225 +flat_mae,patch,logistic,aabc_sex,99,0.046415888336127774,train,0.945179584120983,0.010175963360260009,0.943691387252473,0.010472057691731618,0.9428837304727571,0.010679452880922351 +flat_mae,patch,logistic,aabc_sex,99,0.046415888336127774,test,0.9454545454545454,0.029617484226396186,0.9442755825734549,0.030115618077526687,0.9470108695652174,0.029036771087723418 +flat_mae,patch,logistic,aabc_sex,100,0.046415888336127774,train,0.947069943289225,0.009743898461821459,0.9455985191279309,0.010054942526849695,0.9445177174008617,0.010418791183651924 +flat_mae,patch,logistic,aabc_sex,100,0.046415888336127774,test,0.8909090909090909,0.04169263367166121,0.89,0.041622177712185376,0.9001358695652174,0.03865481307778437 diff --git a/input_space_v3/flat_lr1e-3_2/eval_v2/aabc_sex__patch__logistic/log.txt b/input_space_v3/flat_lr1e-3_2/eval_v2/aabc_sex__patch__logistic/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..6d367b50ba04575abcfdc28f16e578c899043147 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_2/eval_v2/aabc_sex__patch__logistic/log.txt @@ -0,0 +1,245 @@ +fMRI foundation model logistic probe eval +version: 0.1.dev86+gf97f52698 +sha: bcce2b486277d3a5b520775efd9cdf1a2affce36, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-04-08 22:09:30 +config: +output_root: experiments/input_space_v3/output +name_prefix: eval_logistic +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_2; eval v2 (aabc_sex patch logistic) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: input_space_v3/flat_lr1e-3_2/eval_v2/aabc_sex__patch__logistic +model: flat_mae +representation: patch +dataset: aabc_sex +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/eval_v2/aabc_sex__patch__logistic +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=True, reg_tokens=0, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: aabc_sex (flat) +train (n=471): +HFDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'segment', 'bold', 'mean', 'std'], + num_rows: 471 +}), + labels=[0 1], + counts=[269 202] +) + +validation (n=58): +HFDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'segment', 'bold', 'mean', 'std'], + num_rows: 58 +}), + labels=[0 1], + counts=[36 22] +) + +test (n=55): +HFDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'segment', 'bold', 'mean', 'std'], + num_rows: 55 +}), + labels=[0 1], + counts=[33 22] +) + +extracting features for all splits +extract (train) [ 0/236] eta: 0:23:38 time: 6.0109 data: 4.9394 max mem: 3205 +extract (train) [ 20/236] eta: 0:01:52 time: 0.2485 data: 0.0874 max mem: 3393 +extract (train) [ 40/236] eta: 0:01:14 time: 0.2266 data: 0.0724 max mem: 3393 +extract (train) [ 60/236] eta: 0:00:58 time: 0.2300 data: 0.0789 max mem: 3393 +extract (train) [ 80/236] eta: 0:00:47 time: 0.2192 data: 0.0734 max mem: 3393 +extract (train) [100/236] eta: 0:00:39 time: 0.2541 data: 0.0913 max mem: 3393 +extract (train) [120/236] eta: 0:00:33 time: 0.2438 data: 0.0884 max mem: 3393 +extract (train) [140/236] eta: 0:00:26 time: 0.2400 data: 0.0831 max mem: 3393 +extract (train) [160/236] eta: 0:00:20 time: 0.2228 data: 0.0743 max mem: 3393 +extract (train) [180/236] eta: 0:00:14 time: 0.2240 data: 0.0748 max mem: 3393 +extract (train) [200/236] eta: 0:00:09 time: 0.2173 data: 0.0716 max mem: 3393 +extract (train) [220/236] eta: 0:00:04 time: 0.1993 data: 0.0623 max mem: 3393 +extract (train) [235/236] eta: 0:00:00 time: 0.1952 data: 0.0622 max mem: 3393 +extract (train) Total time: 0:00:59 (0.2535 s / it) +extract (validation) [ 0/29] eta: 0:02:29 time: 5.1633 data: 4.9848 max mem: 3393 +extract (validation) [20/29] eta: 0:00:04 time: 0.2262 data: 0.0736 max mem: 3393 +extract (validation) [28/29] eta: 0:00:00 time: 0.1941 data: 0.0578 max mem: 3393 +extract (validation) Total time: 0:00:11 (0.3982 s / it) +extract (test) [ 0/28] eta: 0:02:19 time: 4.9778 data: 4.8197 max mem: 3393 +extract (test) [20/28] eta: 0:00:03 time: 0.2249 data: 0.0742 max mem: 3393 +extract (test) [27/28] eta: 0:00:00 time: 0.1954 data: 0.0612 max mem: 3393 +extract (test) Total time: 0:00:11 (0.3979 s / it) +feature extraction time: 0:01:22 +train features: (471, 768) +validation features: (58, 768) +test features: (55, 768) +evaluating fixed splits +eval results (fixed splits): + +| model | repr | clf | dataset | trial | C | split | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|---------:|:--------|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | aabc_sex | | 0.046416 | train | 0.94896 | 0.0096348 | 0.94757 | 0.009917 | 0.94625 | 0.01015 | +| flat_mae | patch | logistic | aabc_sex | | 0.046416 | test | 0.90909 | 0.0393 | 0.90598 | 0.040556 | 0.90909 | 0.040131 | + + +evaluating random splits (n=100) +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 1, "C": 0.046415888336127774, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.04426067037617888, "f1": 0.8683760683760684, "f1_std": 0.046357898012057336, "bacc": 0.8661684782608696, "bacc_std": 0.046921319742068535} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 2, "C": 2.782559402207126, "split": "test", "acc": 0.9272727272727272, "acc_std": 0.03658975153448534, "f1": 0.9252717391304348, "f1_std": 0.037673466685692936, "bacc": 0.9252717391304348, "bacc_std": 0.03781879751570675} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 3, "C": 0.046415888336127774, "split": "test", "acc": 0.8181818181818182, "acc_std": 0.05155787889385147, "f1": 0.8106060606060606, "f1_std": 0.05449808092685692, "bacc": 0.8070652173913043, "bacc_std": 0.054488233100118716} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 4, "C": 0.046415888336127774, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.0484127023834253, "f1": 0.8533333333333333, "f1_std": 0.04830948583179534, "bacc": 0.8627717391304348, "bacc_std": 0.04582675701400831} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 5, "C": 0.046415888336127774, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.04405344612743115, "f1": 0.8663658451926415, "f1_std": 0.04752002354087049, "bacc": 0.8600543478260869, "bacc_std": 0.04824681716422976} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 6, "C": 0.046415888336127774, "split": "test", "acc": 0.9454545454545454, "acc_std": 0.030464720145665536, "f1": 0.9435897435897436, "f1_std": 0.031856996515590215, "bacc": 0.9408967391304348, "bacc_std": 0.03345344386828878} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 7, "C": 0.046415888336127774, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.04913667899991302, "f1": 0.8343927735028438, "f1_std": 0.04940928192654683, "bacc": 0.8410326086956521, "bacc_std": 0.04852533304257399} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 8, "C": 0.005994842503189409, "split": "test", "acc": 0.8181818181818182, "acc_std": 0.05039704831970658, "f1": 0.8131793478260869, "f1_std": 0.05207898850767568, "bacc": 0.8131793478260869, "bacc_std": 0.05251532660302583} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 9, "C": 0.046415888336127774, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.03866232710520776, "f1": 0.905982905982906, "f1_std": 0.04030850357587018, "bacc": 0.9035326086956521, "bacc_std": 0.04111424322522534} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 10, "C": 0.046415888336127774, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.04497161639291759, "f1": 0.8711943793911007, "f1_std": 0.0452538409623905, "bacc": 0.8783967391304348, "bacc_std": 0.043895105956963616} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 11, "C": 0.046415888336127774, "split": "test", "acc": 0.9272727272727272, "acc_std": 0.03654456805799537, "f1": 0.9252717391304348, "f1_std": 0.037494148921764246, "bacc": 0.9252717391304348, "bacc_std": 0.03743085630396134} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 12, "C": 0.3593813663804626, "split": "test", "acc": 0.7636363636363637, "acc_std": 0.057234319011649576, "f1": 0.7555555555555555, "f1_std": 0.059949400405274966, "bacc": 0.7540760869565217, "bacc_std": 0.059762772694239845} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 13, "C": 0.046415888336127774, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.04123673240175019, "f1": 0.8879076086956521, "f1_std": 0.04248939819823548, "bacc": 0.8879076086956521, "bacc_std": 0.04267870149782034} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 14, "C": 0.046415888336127774, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.042125526702938676, "f1": 0.8879076086956521, "f1_std": 0.04344073935425481, "bacc": 0.8879076086956521, "bacc_std": 0.043563628064686236} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 15, "C": 166.81005372000556, "split": "test", "acc": 0.8181818181818182, "acc_std": 0.04852855000192416, "f1": 0.8106060606060606, "f1_std": 0.05128818303706811, "bacc": 0.8070652173913043, "bacc_std": 0.05137415476088575} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 16, "C": 0.3593813663804626, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.04137310980426819, "f1": 0.8863636363636364, "f1_std": 0.04409836968745209, "bacc": 0.8817934782608696, "bacc_std": 0.04545949364657925} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 17, "C": 0.046415888336127774, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.041365310655425196, "f1": 0.8639095086603039, "f1_std": 0.04673459971200336, "bacc": 0.8539402173913043, "bacc_std": 0.04712889609968627} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 18, "C": 0.005994842503189409, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.03702375382247779, "f1": 0.9079959852793577, "f1_std": 0.03716064950145421, "bacc": 0.9157608695652174, "bacc_std": 0.03505598188283607} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 19, "C": 21.54434690031882, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.04295644536442821, "f1": 0.8699763593380614, "f1_std": 0.04372141722662848, "bacc": 0.8722826086956521, "bacc_std": 0.043372580122950255} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 20, "C": 0.046415888336127774, "split": "test", "acc": 0.9272727272727272, "acc_std": 0.03269272924450552, "f1": 0.9242424242424243, "f1_std": 0.03485450048439878, "bacc": 0.9191576086956521, "bacc_std": 0.036971846447023296} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 21, "C": 21.54434690031882, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.04914527629201182, "f1": 0.8281846581048247, "f1_std": 0.05363818827395226, "bacc": 0.8226902173913043, "bacc_std": 0.053742046353846926} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 22, "C": 166.81005372000556, "split": "test", "acc": 0.9272727272727272, "acc_std": 0.034764168881429185, "f1": 0.9260752688172043, "f1_std": 0.03511102367777514, "bacc": 0.9313858695652174, "bacc_std": 0.03339806958094755} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 23, "C": 21.54434690031882, "split": "test", "acc": 0.8181818181818182, "acc_std": 0.05121730079598537, "f1": 0.8166666666666667, "f1_std": 0.05143330982040317, "bacc": 0.8254076086956521, "bacc_std": 0.050717267457166065} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 24, "C": 0.046415888336127774, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.0477372837985448, "f1": 0.8484848484848485, "f1_std": 0.05072225093312138, "bacc": 0.8444293478260869, "bacc_std": 0.05120056934869412} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 25, "C": 0.005994842503189409, "split": "test", "acc": 0.9272727272727272, "acc_std": 0.03218005131256536, "f1": 0.9252717391304348, "f1_std": 0.03323151323042152, "bacc": 0.9252717391304348, "bacc_std": 0.03389648207304361} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 26, "C": 0.046415888336127774, "split": "test", "acc": 0.8181818181818182, "acc_std": 0.04847866021114616, "f1": 0.8106060606060606, "f1_std": 0.051597052806010305, "bacc": 0.8070652173913043, "bacc_std": 0.05156378485539002} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 27, "C": 0.046415888336127774, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.04300788319051432, "f1": 0.8683760683760684, "f1_std": 0.044962123539242956, "bacc": 0.8661684782608696, "bacc_std": 0.04537478201255267} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 28, "C": 0.005994842503189409, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.046010792840932846, "f1": 0.8250265111346766, "f1_std": 0.05203977459923469, "bacc": 0.8165760869565217, "bacc_std": 0.05163356176171513} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 29, "C": 0.046415888336127774, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.04845656144535471, "f1": 0.8505434782608696, "f1_std": 0.0498346362948025, "bacc": 0.8505434782608696, "bacc_std": 0.049933839882689346} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 30, "C": 0.046415888336127774, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.04324827422152814, "f1": 0.8879076086956521, "f1_std": 0.044573852583238524, "bacc": 0.8879076086956521, "bacc_std": 0.044640715869438} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 31, "C": 0.046415888336127774, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.04710296791898423, "f1": 0.8521505376344086, "f1_std": 0.04755799431647121, "bacc": 0.8566576086956521, "bacc_std": 0.046560219757889904} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 32, "C": 0.046415888336127774, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.03553722759944205, "f1": 0.9045470322804582, "f1_std": 0.0386887816089132, "bacc": 0.8974184782608696, "bacc_std": 0.04034603166378916} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 33, "C": 0.046415888336127774, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.04172180197846898, "f1": 0.8879076086956521, "f1_std": 0.04303168741071197, "bacc": 0.8879076086956521, "bacc_std": 0.043335012213441305} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 34, "C": 0.046415888336127774, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.04206919133408832, "f1": 0.8863636363636364, "f1_std": 0.044706754052448595, "bacc": 0.8817934782608696, "bacc_std": 0.04581491792929106} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 35, "C": 0.005994842503189409, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.03775972755189567, "f1": 0.905982905982906, "f1_std": 0.039296576147445396, "bacc": 0.9035326086956521, "bacc_std": 0.03988512298375757} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 36, "C": 0.046415888336127774, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.04101964858757244, "f1": 0.8891129032258065, "f1_std": 0.041468349270263626, "bacc": 0.8940217391304348, "bacc_std": 0.040510718160778836} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 37, "C": 0.046415888336127774, "split": "test", "acc": 0.7454545454545455, "acc_std": 0.059154092094885945, "f1": 0.7348484848484849, "f1_std": 0.06290017157784876, "bacc": 0.7323369565217391, "bacc_std": 0.062117807030826505} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 38, "C": 0.000774263682681127, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.04094582593082015, "f1": 0.8639095086603039, "f1_std": 0.046127049310700156, "bacc": 0.8539402173913043, "bacc_std": 0.04664858670147762} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 39, "C": 0.046415888336127774, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.046470109472435746, "f1": 0.8505434782608696, "f1_std": 0.04783956222507828, "bacc": 0.8505434782608696, "bacc_std": 0.04789976345478235} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 40, "C": 166.81005372000556, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.046133632700186326, "f1": 0.8484848484848485, "f1_std": 0.04883630542169441, "bacc": 0.8444293478260869, "bacc_std": 0.04918407135265216} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 41, "C": 0.005994842503189409, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.04268359856873433, "f1": 0.8879076086956521, "f1_std": 0.04402556638984178, "bacc": 0.8879076086956521, "bacc_std": 0.04416115309771717} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 42, "C": 0.046415888336127774, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.04868850560976785, "f1": 0.8521505376344086, "f1_std": 0.04936857149554626, "bacc": 0.8566576086956521, "bacc_std": 0.048745620982467014} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 43, "C": 0.046415888336127774, "split": "test", "acc": 0.9636363636363636, "acc_std": 0.02447731957453102, "f1": 0.9630376344086022, "f1_std": 0.024630179752562296, "bacc": 0.96875, "bacc_std": 0.021035196509362586} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 44, "C": 0.046415888336127774, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.04821088660019495, "f1": 0.8307692307692308, "f1_std": 0.05072551162789429, "bacc": 0.8288043478260869, "bacc_std": 0.05089046168546734} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 45, "C": 0.046415888336127774, "split": "test", "acc": 0.9636363636363636, "acc_std": 0.02440745042735182, "f1": 0.9630376344086022, "f1_std": 0.024547986237309635, "bacc": 0.96875, "bacc_std": 0.02097515271100547} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 46, "C": 0.046415888336127774, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.037355986830307615, "f1": 0.9071259709557582, "f1_std": 0.03807730881761385, "bacc": 0.9096467391304348, "bacc_std": 0.03764147254145621} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 47, "C": 0.046415888336127774, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.04475558601268496, "f1": 0.84593837535014, "f1_std": 0.049115168407924445, "bacc": 0.8383152173913043, "bacc_std": 0.04931960134450676} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 48, "C": 0.046415888336127774, "split": "test", "acc": 0.9636363636363636, "acc_std": 0.02420889802947778, "f1": 0.9626358695652174, "f1_std": 0.024842128203414998, "bacc": 0.9626358695652174, "bacc_std": 0.02485694163569818} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 49, "C": 0.3593813663804626, "split": "test", "acc": 0.8181818181818182, "acc_std": 0.049444704903307934, "f1": 0.8151881720430108, "f1_std": 0.05011833100584977, "bacc": 0.8192934782608696, "bacc_std": 0.049735144358315775} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 50, "C": 0.046415888336127774, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.04323965122450144, "f1": 0.8879076086956521, "f1_std": 0.04435367947873587, "bacc": 0.8879076086956521, "bacc_std": 0.044255169712690424} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 51, "C": 0.046415888336127774, "split": "test", "acc": 0.9272727272727272, "acc_std": 0.03467991058735746, "f1": 0.9242424242424243, "f1_std": 0.03692372011134154, "bacc": 0.9191576086956521, "bacc_std": 0.03889490047200075} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 52, "C": 0.046415888336127774, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.03813961303742643, "f1": 0.9071259709557582, "f1_std": 0.03892950847312275, "bacc": 0.9096467391304348, "bacc_std": 0.03852719403760353} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 53, "C": 0.005994842503189409, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.04590022956783727, "f1": 0.8484848484848485, "f1_std": 0.04876026578485079, "bacc": 0.8444293478260869, "bacc_std": 0.04915378549737187} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 54, "C": 0.046415888336127774, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.05027000157003416, "f1": 0.8343927735028438, "f1_std": 0.05054279930158628, "bacc": 0.8410326086956521, "bacc_std": 0.04924854913021658} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 55, "C": 0.3593813663804626, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.04848748326174342, "f1": 0.8521505376344086, "f1_std": 0.04917158697323246, "bacc": 0.8566576086956521, "bacc_std": 0.04877027897253205} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 56, "C": 0.046415888336127774, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.04967416476024631, "f1": 0.8307692307692308, "f1_std": 0.05200060609016469, "bacc": 0.8288043478260869, "bacc_std": 0.05239560900929229} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 57, "C": 0.046415888336127774, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.04059802543747033, "f1": 0.8863636363636364, "f1_std": 0.04319418705336951, "bacc": 0.8817934782608696, "bacc_std": 0.044147461605876286} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 58, "C": 0.046415888336127774, "split": "test", "acc": 0.8, "acc_std": 0.05297990886932187, "f1": 0.795677136102668, "f1_std": 0.054041794647281365, "bacc": 0.7975543478260869, "bacc_std": 0.05382640879522031} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 59, "C": 0.005994842503189409, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.037484542268659354, "f1": 0.9071259709557582, "f1_std": 0.03820229752403159, "bacc": 0.9096467391304348, "bacc_std": 0.03772852986274875} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 60, "C": 0.046415888336127774, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.04784962671598914, "f1": 0.84593837535014, "f1_std": 0.05265936801278922, "bacc": 0.8383152173913043, "bacc_std": 0.05269466990949716} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 61, "C": 0.046415888336127774, "split": "test", "acc": 0.9454545454545454, "acc_std": 0.030904277700106335, "f1": 0.9442755825734549, "f1_std": 0.03146511125105942, "bacc": 0.9470108695652174, "bacc_std": 0.03062991631746194} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 62, "C": 0.046415888336127774, "split": "test", "acc": 0.9454545454545454, "acc_std": 0.02778741019399355, "f1": 0.9435897435897436, "f1_std": 0.029062852015867845, "bacc": 0.9408967391304348, "bacc_std": 0.030442408060635518} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 63, "C": 0.046415888336127774, "split": "test", "acc": 0.9272727272727272, "acc_std": 0.033829734097254, "f1": 0.9252717391304348, "f1_std": 0.03487657627072886, "bacc": 0.9252717391304348, "bacc_std": 0.03526266212674039} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 64, "C": 0.3593813663804626, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.047591582004446416, "f1": 0.8505434782608696, "f1_std": 0.04900973213814301, "bacc": 0.8505434782608696, "bacc_std": 0.049167542243266374} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 65, "C": 0.046415888336127774, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.03826477568013747, "f1": 0.9045470322804582, "f1_std": 0.041497043154271794, "bacc": 0.8974184782608696, "bacc_std": 0.043090696607070364} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 66, "C": 0.046415888336127774, "split": "test", "acc": 0.9272727272727272, "acc_std": 0.03387241008976564, "f1": 0.9242424242424243, "f1_std": 0.036035130249407944, "bacc": 0.9191576086956521, "bacc_std": 0.037935072911987194} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 67, "C": 0.3593813663804626, "split": "test", "acc": 0.9272727272727272, "acc_std": 0.03620465245661299, "f1": 0.9252717391304348, "f1_std": 0.037264874439083016, "bacc": 0.9252717391304348, "bacc_std": 0.03738539108560116} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 68, "C": 2.782559402207126, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.03697913640048427, "f1": 0.9045470322804582, "f1_std": 0.03996583746575895, "bacc": 0.8974184782608696, "bacc_std": 0.04160381275281441} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 69, "C": 0.046415888336127774, "split": "test", "acc": 0.9636363636363636, "acc_std": 0.025858074174230382, "f1": 0.9626358695652174, "f1_std": 0.026631317943634693, "bacc": 0.9626358695652174, "bacc_std": 0.026926550632376582} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 70, "C": 0.3593813663804626, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.044686322717544434, "f1": 0.8699763593380614, "f1_std": 0.04555789248750382, "bacc": 0.8722826086956521, "bacc_std": 0.04521669921345348} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 71, "C": 0.046415888336127774, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.04338411942383776, "f1": 0.8663658451926415, "f1_std": 0.046612304611181876, "bacc": 0.8600543478260869, "bacc_std": 0.047130065240854065} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 72, "C": 0.005994842503189409, "split": "test", "acc": 0.9454545454545454, "acc_std": 0.030134442554976427, "f1": 0.9435897435897436, "f1_std": 0.0314911311008407, "bacc": 0.9408967391304348, "bacc_std": 0.03280960466904634} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 73, "C": 0.046415888336127774, "split": "test", "acc": 0.9272727272727272, "acc_std": 0.03342101086056718, "f1": 0.9242424242424243, "f1_std": 0.035540376484034374, "bacc": 0.9191576086956521, "bacc_std": 0.03725583146313884} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 74, "C": 0.046415888336127774, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.04654447442149876, "f1": 0.8699763593380614, "f1_std": 0.047472654440359224, "bacc": 0.8722826086956521, "bacc_std": 0.04711054185814096} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 75, "C": 0.046415888336127774, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.042933413753496526, "f1": 0.8699763593380614, "f1_std": 0.043927472476089656, "bacc": 0.8722826086956521, "bacc_std": 0.043963116327614335} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 76, "C": 21.54434690031882, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.04480984248433677, "f1": 0.84593837535014, "f1_std": 0.0492725353999537, "bacc": 0.8383152173913043, "bacc_std": 0.049525103920143775} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 77, "C": 0.3593813663804626, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.04530132722044557, "f1": 0.8663658451926415, "f1_std": 0.048700449815947025, "bacc": 0.8600543478260869, "bacc_std": 0.04937443774954454} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 78, "C": 0.3593813663804626, "split": "test", "acc": 0.9454545454545454, "acc_std": 0.03048209879761298, "f1": 0.9435897435897436, "f1_std": 0.03186813051360379, "bacc": 0.9408967391304348, "bacc_std": 0.033220203165154207} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 79, "C": 0.046415888336127774, "split": "test", "acc": 0.9454545454545454, "acc_std": 0.029875134081098896, "f1": 0.9427282193682749, "f1_std": 0.03248839899225682, "bacc": 0.9347826086956521, "bacc_std": 0.03572026901000955} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 80, "C": 0.046415888336127774, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.0463533535834221, "f1": 0.8683760683760684, "f1_std": 0.048386851332055204, "bacc": 0.8661684782608696, "bacc_std": 0.048866110843547694} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 81, "C": 0.046415888336127774, "split": "test", "acc": 0.9454545454545454, "acc_std": 0.032853795835891576, "f1": 0.9442755825734549, "f1_std": 0.0333650414797964, "bacc": 0.9470108695652174, "bacc_std": 0.03209975143277161} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 82, "C": 0.3593813663804626, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.04423042593636641, "f1": 0.84593837535014, "f1_std": 0.04841159693018112, "bacc": 0.8383152173913043, "bacc_std": 0.048776578278426956} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 83, "C": 166.81005372000556, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.048241815132442155, "f1": 0.8250265111346766, "f1_std": 0.05416128083129135, "bacc": 0.8165760869565217, "bacc_std": 0.053122104248750336} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 84, "C": 0.046415888336127774, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.050634323445107855, "f1": 0.8307692307692308, "f1_std": 0.05285238509723649, "bacc": 0.8288043478260869, "bacc_std": 0.053238752964047016} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 85, "C": 2.782559402207126, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.04540842751358162, "f1": 0.84593837535014, "f1_std": 0.04988941381768201, "bacc": 0.8383152173913043, "bacc_std": 0.0501507220510753} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 86, "C": 0.046415888336127774, "split": "test", "acc": 0.9454545454545454, "acc_std": 0.03236198157158598, "f1": 0.9435897435897436, "f1_std": 0.03378656628725523, "bacc": 0.9408967391304348, "bacc_std": 0.035160367853775805} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 87, "C": 0.046415888336127774, "split": "test", "acc": 0.9454545454545454, "acc_std": 0.029020369022150952, "f1": 0.9427282193682749, "f1_std": 0.031580762545316436, "bacc": 0.9347826086956521, "bacc_std": 0.034698267309093526} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 88, "C": 0.3593813663804626, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.04108324948722718, "f1": 0.8863636363636364, "f1_std": 0.04358167475898493, "bacc": 0.8817934782608696, "bacc_std": 0.0447661475622878} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 89, "C": 0.046415888336127774, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.03940266383577856, "f1": 0.884453781512605, "f1_std": 0.04362209950132576, "bacc": 0.8756793478260869, "bacc_std": 0.04497025005347213} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 90, "C": 0.046415888336127774, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.046580952372906034, "f1": 0.8683760683760684, "f1_std": 0.04878424686803953, "bacc": 0.8661684782608696, "bacc_std": 0.04935393121695989} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 91, "C": 0.046415888336127774, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.039783945430909524, "f1": 0.905982905982906, "f1_std": 0.04141461136454477, "bacc": 0.9035326086956521, "bacc_std": 0.04192449505135774} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 92, "C": 2.782559402207126, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.03795109510718645, "f1": 0.9045470322804582, "f1_std": 0.041034562652099586, "bacc": 0.8974184782608696, "bacc_std": 0.04273976405756128} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 93, "C": 0.046415888336127774, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.03702132510319822, "f1": 0.9027925061859314, "f1_std": 0.042028994844589294, "bacc": 0.8913043478260869, "bacc_std": 0.04426462784078048} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 94, "C": 21.54434690031882, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.04616257294059621, "f1": 0.8484848484848485, "f1_std": 0.048686409064739616, "bacc": 0.8444293478260869, "bacc_std": 0.048720655005097264} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 95, "C": 0.046415888336127774, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.03858618773988331, "f1": 0.9071259709557582, "f1_std": 0.039310523325167386, "bacc": 0.9096467391304348, "bacc_std": 0.03882445226517596} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 96, "C": 0.005994842503189409, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.039017266785847736, "f1": 0.905982905982906, "f1_std": 0.04069436110218064, "bacc": 0.9035326086956521, "bacc_std": 0.04149131685556947} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 97, "C": 166.81005372000556, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.04907365353297406, "f1": 0.8343927735028438, "f1_std": 0.049611127645771746, "bacc": 0.8410326086956521, "bacc_std": 0.049372924823587606} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 98, "C": 21.54434690031882, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.04406004918159189, "f1": 0.8683760683760684, "f1_std": 0.04613919707544321, "bacc": 0.8661684782608696, "bacc_std": 0.04696631266417225} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 99, "C": 0.046415888336127774, "split": "test", "acc": 0.9454545454545454, "acc_std": 0.029617484226396186, "f1": 0.9442755825734549, "f1_std": 0.030115618077526687, "bacc": 0.9470108695652174, "bacc_std": 0.029036771087723418} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 100, "C": 0.046415888336127774, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.04169263367166121, "f1": 0.89, "f1_std": 0.041622177712185376, "bacc": 0.9001358695652174, "bacc_std": 0.03865481307778437} +eval results (random splits): + +| model | repr | clf | dataset | split | n_trials | C | C_std | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|-----------:|-------:|--------:|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | aabc_sex | train | 100 | 9.8138 | 36.558 | 0.95633 | 0.027823 | 0.95505 | 0.028687 | 0.9539 | 0.029411 | +| flat_mae | patch | logistic | aabc_sex | test | 100 | 9.8138 | 36.558 | 0.884 | 0.044294 | 0.87996 | 0.045936 | 0.87855 | 0.046376 | + + +done! total time: 0:05:17 diff --git a/input_space_v3/flat_lr1e-3_2/eval_v2/abide_dx__patch__logistic/config.yaml b/input_space_v3/flat_lr1e-3_2/eval_v2/abide_dx__patch__logistic/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..76284b8baa68ae666f22e7db24899b37ce34d3ba --- /dev/null +++ b/input_space_v3/flat_lr1e-3_2/eval_v2/abide_dx__patch__logistic/config.yaml @@ -0,0 +1,30 @@ +output_root: experiments/input_space_v3/output +name_prefix: eval_logistic +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_2; eval v2 (abide_dx patch logistic) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: input_space_v3/flat_lr1e-3_2/eval_v2/abide_dx__patch__logistic +model: flat_mae +representation: patch +dataset: abide_dx +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/eval_v2/abide_dx__patch__logistic +remote_dir: null diff --git a/input_space_v3/flat_lr1e-3_2/eval_v2/abide_dx__patch__logistic/eval_table.csv b/input_space_v3/flat_lr1e-3_2/eval_v2/abide_dx__patch__logistic/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..ed92aa84184b1fa3495863e7787ad076948355de --- /dev/null +++ b/input_space_v3/flat_lr1e-3_2/eval_v2/abide_dx__patch__logistic/eval_table.csv @@ -0,0 +1,203 @@ +model,repr,clf,dataset,trial,C,split,acc,acc_std,f1,f1_std,bacc,bacc_std +flat_mae,patch,logistic,abide_dx,,0.046415888336127774,train,0.8005698005698005,0.015135735942204957,0.7964391347213362,0.015553122782824245,0.7943807866570358,0.015503522557056152 +flat_mae,patch,logistic,abide_dx,,0.046415888336127774,test,0.5725806451612904,0.04165275660979222,0.5599598259122867,0.04392239763703516,0.5625818277035873,0.04229868889774645 +flat_mae,patch,logistic,abide_dx,1,0.3593813663804626,train,0.9116809116809117,0.011188400554951,0.9105769230769231,0.011350859754252592,0.9098560354374308,0.011435380329817505 +flat_mae,patch,logistic,abide_dx,1,0.3593813663804626,test,0.6451612903225806,0.045380871710111674,0.6418067226890756,0.04618173543016353,0.6418067226890756,0.04611709623332376 +flat_mae,patch,logistic,abide_dx,2,0.3593813663804626,train,0.896011396011396,0.011571464180867377,0.8947450577663671,0.011735543249442567,0.8941675895164267,0.011825460524242165 +flat_mae,patch,logistic,abide_dx,2,0.3593813663804626,test,0.6048387096774194,0.04422985028923001,0.5989703649924097,0.04476767538051069,0.5987394957983193,0.044454694117810716 +flat_mae,patch,logistic,abide_dx,3,0.046415888336127774,train,0.8005698005698005,0.015305934711919445,0.7972370766488414,0.015645537179714883,0.7957918050941306,0.015663654683110623 +flat_mae,patch,logistic,abide_dx,3,0.046415888336127774,test,0.5564516129032258,0.042795994420009725,0.5498646953996436,0.04368686176032741,0.5498949579831933,0.043201848663059185 +flat_mae,patch,logistic,abide_dx,4,0.3593813663804626,train,0.9031339031339032,0.010849638768501426,0.9017939433838051,0.011055234483626622,0.9006275378368402,0.01123678631913283 +flat_mae,patch,logistic,abide_dx,4,0.3593813663804626,test,0.6451612903225806,0.043429239635975676,0.6405797101449275,0.0442846982350728,0.6402310924369747,0.04406619712793694 +flat_mae,patch,logistic,abide_dx,5,0.005994842503189409,train,0.7150997150997151,0.016589804748029645,0.7053020444145921,0.017445177479343873,0.7038021410114433,0.017021439166233783 +flat_mae,patch,logistic,abide_dx,5,0.005994842503189409,test,0.5806451612903226,0.04235491241425423,0.5766806722689075,0.04256677407590462,0.5766806722689075,0.04258038346716384 +flat_mae,patch,logistic,abide_dx,6,0.000774263682681127,train,0.6581196581196581,0.016757605896386536,0.6362851344933294,0.018576688464820947,0.639719453672942,0.017279177129259835 +flat_mae,patch,logistic,abide_dx,6,0.000774263682681127,test,0.5403225806451613,0.04337361584545201,0.5096774193548387,0.046320158372624584,0.5210084033613446,0.04355449471336164 +flat_mae,patch,logistic,abide_dx,7,0.046415888336127774,train,0.8062678062678063,0.014835071621171094,0.8031748649651589,0.015135426894710702,0.8018456995201181,0.015135765077516287 +flat_mae,patch,logistic,abide_dx,7,0.046415888336127774,test,0.5806451612903226,0.042263835483806834,0.5643243243243243,0.04395852873752037,0.5672268907563025,0.04247835032639005 +flat_mae,patch,logistic,abide_dx,8,2.782559402207126,train,0.9914529914529915,0.003457398483353139,0.9913621262458472,0.0034945995088533745,0.9913621262458472,0.0035297247463911465 +flat_mae,patch,logistic,abide_dx,8,2.782559402207126,test,0.6209677419354839,0.043679956566131634,0.6167554415729598,0.0443807138656965,0.6165966386554622,0.04423414740075194 +flat_mae,patch,logistic,abide_dx,9,10000.0,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,9,10000.0,test,0.6693548387096774,0.04288045417992187,0.6630211440312852,0.04385637413700832,0.6622899159663866,0.04331793699729449 +flat_mae,patch,logistic,abide_dx,10,0.046415888336127774,train,0.7792022792022792,0.015706665105591794,0.7762229996113055,0.015974401864303316,0.7755260243632337,0.01601106890282944 +flat_mae,patch,logistic,abide_dx,10,0.046415888336127774,test,0.6290322580645161,0.04627673173533388,0.6255252100840336,0.04703007790126472,0.6255252100840336,0.0470293708829508 +flat_mae,patch,logistic,abide_dx,11,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,11,166.81005372000556,test,0.4838709677419355,0.04272754170297172,0.4700854700854701,0.04400789389981201,0.4726890756302521,0.04295621708412636 +flat_mae,patch,logistic,abide_dx,12,0.046415888336127774,train,0.782051282051282,0.01523202234611007,0.7781578213588624,0.015605563734107337,0.7766334440753045,0.015575389332046346 +flat_mae,patch,logistic,abide_dx,12,0.046415888336127774,test,0.6129032258064516,0.043516965964356655,0.6063492063492064,0.04427446826553449,0.60609243697479,0.04379038295588903 +flat_mae,patch,logistic,abide_dx,13,0.046415888336127774,train,0.7977207977207977,0.01500495882622507,0.7946387368976201,0.015307698431918561,0.7935031376891841,0.0153430693548703 +flat_mae,patch,logistic,abide_dx,13,0.046415888336127774,test,0.5725806451612904,0.04315218815253425,0.5662332519305657,0.0437882806329679,0.5661764705882353,0.04345613011631512 +flat_mae,patch,logistic,abide_dx,14,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,14,21.54434690031882,test,0.5483870967741935,0.04501206914113465,0.5386659580122243,0.04641350983167062,0.539390756302521,0.045577590729553544 +flat_mae,patch,logistic,abide_dx,15,2.782559402207126,train,0.9857549857549858,0.004565898398613306,0.9855949175914374,0.004618579585625391,0.9853082318198597,0.004672561074441697 +flat_mae,patch,logistic,abide_dx,15,2.782559402207126,test,0.6532258064516129,0.04094745179535325,0.6532032520325204,0.04111235087034635,0.6601890756302521,0.04090618150677673 +flat_mae,patch,logistic,abide_dx,16,0.3593813663804626,train,0.9031339031339032,0.011092139549081616,0.9019230769230769,0.01127106282401706,0.901218161683278,0.01141795508369141 +flat_mae,patch,logistic,abide_dx,16,0.3593813663804626,test,0.5403225806451613,0.04400851303512714,0.5366764995083579,0.04435664694246206,0.5367647058823529,0.04440147421585783 +flat_mae,patch,logistic,abide_dx,17,0.046415888336127774,train,0.7991452991452992,0.015099300913526004,0.7958641569203293,0.015391773816038143,0.794499815430048,0.015381220161905445 +flat_mae,patch,logistic,abide_dx,17,0.046415888336127774,test,0.5967741935483871,0.043931836331939936,0.5915678524374176,0.0446668756210075,0.5913865546218487,0.04447806207521965 +flat_mae,patch,logistic,abide_dx,18,0.005994842503189409,train,0.7022792022792023,0.016876066392082993,0.6925304759849029,0.017519708468038287,0.6912882982650425,0.01712258132684765 +flat_mae,patch,logistic,abide_dx,18,0.005994842503189409,test,0.6048387096774194,0.044420877524443646,0.5953379953379954,0.04618211311235825,0.5955882352941176,0.04521340547489632 +flat_mae,patch,logistic,abide_dx,19,0.005994842503189409,train,0.7236467236467237,0.016488911099636346,0.7147465167522642,0.017321432054084446,0.713030638612034,0.016978788422846173 +flat_mae,patch,logistic,abide_dx,19,0.005994842503189409,test,0.5645161290322581,0.0409759040637269,0.5334448160535117,0.046184939754892566,0.5446428571428572,0.04191543542138331 +flat_mae,patch,logistic,abide_dx,20,0.046415888336127774,train,0.7962962962962963,0.014578851448392828,0.7923313232449654,0.015061388069038834,0.7904392764857882,0.015117462593059117 +flat_mae,patch,logistic,abide_dx,20,0.046415888336127774,test,0.6209677419354839,0.04196585748663989,0.6137071651090342,0.04308436587515701,0.6134453781512605,0.04254195221231739 +flat_mae,patch,logistic,abide_dx,21,0.046415888336127774,train,0.7934472934472935,0.015071732389847936,0.7900730691733882,0.015417538895732956,0.7887412329272794,0.015462865858744334 +flat_mae,patch,logistic,abide_dx,21,0.046415888336127774,test,0.5887096774193549,0.046357756883924545,0.5841388834089565,0.04685648569844466,0.5840336134453781,0.046633614403162056 +flat_mae,patch,logistic,abide_dx,22,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,22,166.81005372000556,test,0.5564516129032258,0.044128265886573065,0.5498646953996436,0.044910212042651096,0.5498949579831933,0.04453267589661029 +flat_mae,patch,logistic,abide_dx,23,2.782559402207126,train,0.9943019943019943,0.002780187427342185,0.9942447694628451,0.0028065102293116984,0.9945367294204503,0.0026912309712759605 +flat_mae,patch,logistic,abide_dx,23,2.782559402207126,test,0.6048387096774194,0.04464281587630023,0.5953379953379954,0.045918930265819016,0.5955882352941176,0.04511747228600106 +flat_mae,patch,logistic,abide_dx,24,2.782559402207126,train,0.99002849002849,0.003694789843117643,0.9899194830504128,0.0037362455957271135,0.9897748246585456,0.0037949946702676013 +flat_mae,patch,logistic,abide_dx,24,2.782559402207126,test,0.5887096774193549,0.043257523270049766,0.5841388834089565,0.0436973802592238,0.5840336134453781,0.04358540411021984 +flat_mae,patch,logistic,abide_dx,25,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,25,21.54434690031882,test,0.6129032258064516,0.043471913139979786,0.6092436974789917,0.04384659777622353,0.6092436974789917,0.04381843689442414 +flat_mae,patch,logistic,abide_dx,26,0.005994842503189409,train,0.7094017094017094,0.016026900868491272,0.7015306122448979,0.01664938114752212,0.7001107419712072,0.016421436075754706 +flat_mae,patch,logistic,abide_dx,26,0.005994842503189409,test,0.5483870967741935,0.04729499822856712,0.5386659580122243,0.04845194040278796,0.539390756302521,0.0477171002411806 +flat_mae,patch,logistic,abide_dx,27,0.3593813663804626,train,0.9088319088319088,0.01083520806224602,0.9080678032690277,0.010899285791778604,0.9090439276485788,0.010823128572606129 +flat_mae,patch,logistic,abide_dx,27,0.3593813663804626,test,0.5806451612903226,0.04204096844859469,0.5694444444444444,0.04323237864363919,0.5703781512605042,0.0422986770528742 +flat_mae,patch,logistic,abide_dx,28,0.3593813663804626,train,0.915954415954416,0.010677975641735126,0.9150356428534796,0.01081932395545302,0.9149132521225545,0.010962194714345758 +flat_mae,patch,logistic,abide_dx,28,0.3593813663804626,test,0.6209677419354839,0.04424149741648043,0.6153389215233318,0.0449901356553834,0.6150210084033614,0.044689242967816976 +flat_mae,patch,logistic,abide_dx,29,0.3593813663804626,train,0.9116809116809117,0.01055573972026,0.9108932783018868,0.010627877119978,0.9116279069767441,0.010578581344596286 +flat_mae,patch,logistic,abide_dx,29,0.3593813663804626,test,0.6612903225806451,0.04200925273432707,0.6539994685091681,0.04343170359673055,0.6533613445378151,0.04283413653533314 +flat_mae,patch,logistic,abide_dx,30,0.005994842503189409,train,0.6951566951566952,0.017613998995375413,0.6856628724472715,0.018412893400011888,0.6845330380214101,0.018008749001128064 +flat_mae,patch,logistic,abide_dx,30,0.005994842503189409,test,0.6129032258064516,0.042646634472626684,0.6063492063492064,0.04344640282154357,0.60609243697479,0.0429358948937272 +flat_mae,patch,logistic,abide_dx,31,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,31,166.81005372000556,test,0.7096774193548387,0.04103759285161778,0.7077769049489395,0.04111972729558379,0.7085084033613445,0.04095937674351609 +flat_mae,patch,logistic,abide_dx,32,2.782559402207126,train,0.99002849002849,0.0037545609744646714,0.9899194830504128,0.0037969960361098226,0.9897748246585456,0.0038648574049877397 +flat_mae,patch,logistic,abide_dx,32,2.782559402207126,test,0.6370967741935484,0.04318499517810298,0.6342182890855457,0.043508039262596485,0.634453781512605,0.043423034354682866 +flat_mae,patch,logistic,abide_dx,33,0.005994842503189409,train,0.717948717948718,0.016803190562830705,0.7094589510121152,0.01752782007345626,0.7078626799557033,0.017169496855184357 +flat_mae,patch,logistic,abide_dx,33,0.005994842503189409,test,0.6290322580645161,0.040607368502415246,0.6169755573462261,0.043071536750848925,0.6176470588235294,0.041653139996521316 +flat_mae,patch,logistic,abide_dx,34,10000.0,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,34,10000.0,test,0.6209677419354839,0.04188857177523967,0.6203504657677024,0.04194170570732389,0.6228991596638656,0.04204135028958175 +flat_mae,patch,logistic,abide_dx,35,2.782559402207126,train,0.9886039886039886,0.003889305259323274,0.9884895389256902,0.003927013838028048,0.9887781469176818,0.003875703523050404 +flat_mae,patch,logistic,abide_dx,35,2.782559402207126,test,0.6129032258064516,0.042620326085443694,0.607905138339921,0.04339476313915318,0.6076680672268908,0.043139486111764797 +flat_mae,patch,logistic,abide_dx,36,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,36,1291.5496650148827,test,0.5887096774193549,0.038530688338109575,0.5649122807017544,0.042628136716165374,0.5714285714285714,0.0395002857610746 +flat_mae,patch,logistic,abide_dx,37,0.005994842503189409,train,0.7108262108262108,0.016584950525215077,0.7013573522724177,0.0175636736888626,0.6999261720191953,0.01715980574357012 +flat_mae,patch,logistic,abide_dx,37,0.005994842503189409,test,0.6209677419354839,0.04242016434895436,0.6118548118548119,0.044027531724373056,0.6118697478991597,0.04318793980188522 +flat_mae,patch,logistic,abide_dx,38,2.782559402207126,train,0.9943019943019943,0.0028838594204816962,0.9942414174972314,0.0029146229885505747,0.9942414174972314,0.002934657778517315 +flat_mae,patch,logistic,abide_dx,38,2.782559402207126,test,0.6290322580645161,0.04595783707662607,0.6266038229903116,0.04618460631138327,0.6271008403361344,0.04627585486689761 +flat_mae,patch,logistic,abide_dx,39,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,39,21.54434690031882,test,0.6209677419354839,0.04110658463954901,0.6153389215233318,0.04191545438842352,0.6150210084033614,0.041589842982686934 +flat_mae,patch,logistic,abide_dx,40,0.3593813663804626,train,0.9188034188034188,0.010127802012325462,0.9180113227727884,0.010215588578672457,0.9183831672203765,0.010222357089633094 +flat_mae,patch,logistic,abide_dx,40,0.3593813663804626,test,0.5806451612903226,0.04253033134466744,0.5716183895827798,0.04406559294537991,0.571953781512605,0.0431878712299396 +flat_mae,patch,logistic,abide_dx,41,2.782559402207126,train,0.9928774928774928,0.002998194817854629,0.9927996307502949,0.003032295523786234,0.9926541159099298,0.0031323733007409867 +flat_mae,patch,logistic,abide_dx,41,2.782559402207126,test,0.5725806451612904,0.04699032379859912,0.5703170970905524,0.0474372139854626,0.5709033613445378,0.047495560001866464 +flat_mae,patch,logistic,abide_dx,42,0.3593813663804626,train,0.9074074074074074,0.010923056116567862,0.906338327390959,0.011049808442760316,0.9059800664451827,0.011073848500480406 +flat_mae,patch,logistic,abide_dx,42,0.3593813663804626,test,0.5806451612903226,0.046377458171301296,0.5788923719958203,0.04640215930543763,0.5798319327731092,0.0465880779747691 +flat_mae,patch,logistic,abide_dx,43,2.782559402207126,train,0.99002849002849,0.003655953419544819,0.98993121507736,0.003688233091795033,0.9903654485049834,0.003549081729858938 +flat_mae,patch,logistic,abide_dx,43,2.782559402207126,test,0.5645161290322581,0.0432927352579925,0.5603991596638656,0.04368837948451462,0.5603991596638656,0.043572272394039734 +flat_mae,patch,logistic,abide_dx,44,0.005994842503189409,train,0.7108262108262108,0.01612097909044872,0.7025641025641025,0.01672342651325589,0.7011074197120708,0.016441712577430094 +flat_mae,patch,logistic,abide_dx,44,0.005994842503189409,test,0.6048387096774194,0.03979087829940008,0.5819745442036464,0.04379538195208709,0.5877100840336134,0.040675551338134955 +flat_mae,patch,logistic,abide_dx,45,0.005994842503189409,train,0.7165242165242165,0.016414701439775057,0.7087070117749109,0.0170205547577657,0.7071613141380584,0.01677534442089073 +flat_mae,patch,logistic,abide_dx,45,0.005994842503189409,test,0.6048387096774194,0.04271891954870755,0.5880957223239103,0.045384065770027814,0.5908613445378151,0.043489616654063444 +flat_mae,patch,logistic,abide_dx,46,0.3593813663804626,train,0.9045584045584045,0.011030636691517173,0.9035720216580594,0.011139364411642219,0.9036913990402362,0.01116785507095209 +flat_mae,patch,logistic,abide_dx,46,0.3593813663804626,test,0.5403225806451613,0.04438994212091788,0.5400533610984577,0.04445779674040261,0.5430672268907563,0.044319943907581705 +flat_mae,patch,logistic,abide_dx,47,0.005994842503189409,train,0.6908831908831908,0.016805451094811755,0.6840821659287217,0.01737583864496715,0.6830195644149133,0.01719715408098568 +flat_mae,patch,logistic,abide_dx,47,0.005994842503189409,test,0.5887096774193549,0.04013992176697529,0.5712833028269271,0.0416758479169066,0.5745798319327731,0.04033486532656347 +flat_mae,patch,logistic,abide_dx,48,0.005994842503189409,train,0.7037037037037037,0.016739892224515045,0.6953862329664462,0.017460788971007387,0.6940568475452196,0.01715206687544508 +flat_mae,patch,logistic,abide_dx,48,0.005994842503189409,test,0.6048387096774194,0.04303405652284774,0.5907590759075907,0.04595525670341774,0.592436974789916,0.04415127633597407 +flat_mae,patch,logistic,abide_dx,49,0.046415888336127774,train,0.7905982905982906,0.015887307733684165,0.7859911446613922,0.016368756037301004,0.7837947582133629,0.01630120800949684 +flat_mae,patch,logistic,abide_dx,49,0.046415888336127774,test,0.5645161290322581,0.043743324152474165,0.5588932806324111,0.04462596568689296,0.5588235294117647,0.044314300107912034 +flat_mae,patch,logistic,abide_dx,50,0.005994842503189409,train,0.7264957264957265,0.015804932600737127,0.7182632252238693,0.01661278869420449,0.7165005537098561,0.01630609638062864 +flat_mae,patch,logistic,abide_dx,50,0.005994842503189409,test,0.5564516129032258,0.04569927261094662,0.5406479423452549,0.04708027788314506,0.54359243697479,0.045848651355045865 +flat_mae,patch,logistic,abide_dx,51,0.3593813663804626,train,0.9002849002849003,0.011103822212934754,0.8989728702888957,0.011275748903849272,0.8980435585086748,0.011368837057847732 +flat_mae,patch,logistic,abide_dx,51,0.3593813663804626,test,0.5645161290322581,0.044485391445160255,0.5528846153846154,0.046055715627909236,0.5540966386554622,0.044935542581315116 +flat_mae,patch,logistic,abide_dx,52,2.782559402207126,train,0.9914529914529915,0.0035661686879228664,0.9913621262458472,0.003604316593607686,0.9913621262458472,0.003620958858465366 +flat_mae,patch,logistic,abide_dx,52,2.782559402207126,test,0.5887096774193549,0.04594077024220916,0.5865315462569467,0.04607414614281558,0.5871848739495797,0.04595140314305561 +flat_mae,patch,logistic,abide_dx,53,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,53,21.54434690031882,test,0.6129032258064516,0.042958259633737776,0.6063492063492064,0.04390823704278879,0.60609243697479,0.043339235037765024 +flat_mae,patch,logistic,abide_dx,54,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,54,1291.5496650148827,test,0.5725806451612904,0.04490501885092669,0.5678306043269548,0.04537263399095966,0.5677521008403361,0.04521059654984247 +flat_mae,patch,logistic,abide_dx,55,2.782559402207126,train,0.9971509971509972,0.0021012897720250256,0.9971207087486158,0.002123693529309765,0.9971207087486158,0.002139547641810153 +flat_mae,patch,logistic,abide_dx,55,2.782559402207126,test,0.5806451612903226,0.04190923185743606,0.5778999738151349,0.04203865579369361,0.5782563025210083,0.0420588431526411 +flat_mae,patch,logistic,abide_dx,56,0.005994842503189409,train,0.7094017094017094,0.016745550530008375,0.7000427289559892,0.017455586599307703,0.6986341823551125,0.01707810676905128 +flat_mae,patch,logistic,abide_dx,56,0.005994842503189409,test,0.6693548387096774,0.04049587278722571,0.6630211440312852,0.041631539956333175,0.6622899159663866,0.04118103348657382 +flat_mae,patch,logistic,abide_dx,57,0.005994842503189409,train,0.7122507122507122,0.015907963255576998,0.7029834865152442,0.01662425521602418,0.7015134736064969,0.016263425701657695 +flat_mae,patch,logistic,abide_dx,57,0.005994842503189409,test,0.6370967741935484,0.0426444536567125,0.6217205613178767,0.04564456764081239,0.6234243697478992,0.04361511603791241 +flat_mae,patch,logistic,abide_dx,58,2.782559402207126,train,0.9957264957264957,0.0024022754180219714,0.9956848064617256,0.002422930490643147,0.9961240310077519,0.0021788079372757224 +flat_mae,patch,logistic,abide_dx,58,2.782559402207126,test,0.5725806451612904,0.04708986637365252,0.5703170970905524,0.047165470494662576,0.5709033613445378,0.04713445916564135 +flat_mae,patch,logistic,abide_dx,59,0.005994842503189409,train,0.7094017094017094,0.017305525288464824,0.6990821678321678,0.018226237854477023,0.6977482465854559,0.017762255361797687 +flat_mae,patch,logistic,abide_dx,59,0.005994842503189409,test,0.6129032258064516,0.04425338543872955,0.6092436974789917,0.044478329993598416,0.6092436974789917,0.04434971241752527 +flat_mae,patch,logistic,abide_dx,60,2.782559402207126,train,0.9871794871794872,0.004450695983171695,0.9870469879839183,0.0044960227708617665,0.9871908453303803,0.004475721833937922 +flat_mae,patch,logistic,abide_dx,60,2.782559402207126,test,0.6048387096774194,0.04406780734414531,0.6017043592264831,0.04425903587179414,0.601890756302521,0.04411209722745683 +flat_mae,patch,logistic,abide_dx,61,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,61,21.54434690031882,test,0.6290322580645161,0.042474403138317254,0.6227513227513227,0.043466926363572786,0.6223739495798319,0.04296793611727676 +flat_mae,patch,logistic,abide_dx,62,10000.0,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,62,10000.0,test,0.5806451612903226,0.04235390203617498,0.5802083333333333,0.04255313101011645,0.5829831932773109,0.04280784747087481 +flat_mae,patch,logistic,abide_dx,63,2.782559402207126,train,0.9985754985754985,0.0013587414016675583,0.998559926150059,0.0013743882703974762,0.9984126984126984,0.001514026133286713 +flat_mae,patch,logistic,abide_dx,63,2.782559402207126,test,0.5564516129032258,0.04597618484999688,0.5541026479241582,0.04641089129230344,0.5546218487394958,0.04659276055877711 +flat_mae,patch,logistic,abide_dx,64,0.3593813663804626,train,0.9017094017094017,0.011393650396452399,0.9006935745433746,0.011543577383093112,0.900812107788852,0.011721230965417377 +flat_mae,patch,logistic,abide_dx,64,0.3593813663804626,test,0.6854838709677419,0.0395791433056287,0.6779220779220779,0.04097307937754979,0.6769957983193278,0.040259411780579915 +flat_mae,patch,logistic,abide_dx,65,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,65,21.54434690031882,test,0.5967741935483871,0.04429882386752255,0.5880946053680574,0.0458424551489954,0.5882352941176471,0.04505724184744904 +flat_mae,patch,logistic,abide_dx,66,0.3593813663804626,train,0.9074074074074074,0.010507333785442776,0.9062798459563544,0.01065832931018916,0.9056847545219637,0.010783610995716947 +flat_mae,patch,logistic,abide_dx,66,0.3593813663804626,test,0.5645161290322581,0.04384466419718592,0.5634941329856584,0.04392768648258941,0.5651260504201681,0.04405948390627233 +flat_mae,patch,logistic,abide_dx,67,2.782559402207126,train,0.99002849002849,0.003431149360663138,0.9899194830504128,0.0034702790548951546,0.9897748246585456,0.00355493769764756 +flat_mae,patch,logistic,abide_dx,67,2.782559402207126,test,0.6129032258064516,0.043816768584151976,0.607905138339921,0.044458670027939136,0.6076680672268908,0.044130399517458604 +flat_mae,patch,logistic,abide_dx,68,2.782559402207126,train,0.9928774928774928,0.0030704519374254646,0.9927952559531508,0.003109189438699059,0.9923588039867111,0.003300146062772881 +flat_mae,patch,logistic,abide_dx,68,2.782559402207126,test,0.5967741935483871,0.0437263508253735,0.5941345902068604,0.043953905193948775,0.5945378151260504,0.04398122459854946 +flat_mae,patch,logistic,abide_dx,69,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,69,21.54434690031882,test,0.6129032258064516,0.04365362135777835,0.6025641025641025,0.044872008138034845,0.6029411764705883,0.04401274135826547 +flat_mae,patch,logistic,abide_dx,70,2.782559402207126,train,0.99002849002849,0.003679441681192899,0.989913358334411,0.0037246022817677992,0.9894795127353266,0.003863655244558233 +flat_mae,patch,logistic,abide_dx,70,2.782559402207126,test,0.6129032258064516,0.043290932522985416,0.6112852664576802,0.04346888274875316,0.6123949579831933,0.043605842527199096 +flat_mae,patch,logistic,abide_dx,71,2.782559402207126,train,0.9914529914529915,0.0034390426561932835,0.9913621262458472,0.0034754241151384196,0.9913621262458472,0.0034893712792212995 +flat_mae,patch,logistic,abide_dx,71,2.782559402207126,test,0.6129032258064516,0.04272597389121953,0.6045708211533352,0.04412504238579045,0.6045168067226891,0.04343681313180054 +flat_mae,patch,logistic,abide_dx,72,0.000774263682681127,train,0.6723646723646723,0.017002236752188787,0.6562486693634235,0.018226420326027476,0.6570690291620525,0.017398531949319535 +flat_mae,patch,logistic,abide_dx,72,0.000774263682681127,test,0.5483870967741935,0.040512491489679496,0.5203094777562862,0.04462739321884685,0.529936974789916,0.04127783916503874 +flat_mae,patch,logistic,abide_dx,73,2.782559402207126,train,0.9957264957264957,0.002515156449246971,0.995679778450177,0.0025436552735776715,0.9955334071613142,0.00263179930159416 +flat_mae,patch,logistic,abide_dx,73,2.782559402207126,test,0.6290322580645161,0.04158743907058393,0.6210470369386127,0.04290946528693738,0.6207983193277311,0.042186734690205216 +flat_mae,patch,logistic,abide_dx,74,0.005994842503189409,train,0.7279202279202279,0.016259228058479708,0.7195893450559747,0.01696778752919762,0.7177925433739387,0.01665990741723625 +flat_mae,patch,logistic,abide_dx,74,0.005994842503189409,test,0.6048387096774194,0.043612855506749995,0.5931704050887178,0.04535691620441678,0.5940126050420168,0.044111914130814736 +flat_mae,patch,logistic,abide_dx,75,2.782559402207126,train,0.9871794871794872,0.004260820683979985,0.9870544193851771,0.004299164250652304,0.9874861572535991,0.0042044098071230985 +flat_mae,patch,logistic,abide_dx,75,2.782559402207126,test,0.6129032258064516,0.04289561841358959,0.6112852664576802,0.0430521963077633,0.6123949579831933,0.04322001258864824 +flat_mae,patch,logistic,abide_dx,76,0.3593813663804626,train,0.9088319088319088,0.011446327666911477,0.9080678032690277,0.011517528339850619,0.9090439276485788,0.011449793480757283 +flat_mae,patch,logistic,abide_dx,76,0.3593813663804626,test,0.6290322580645161,0.04350586633808437,0.6191239316239316,0.04503150020139368,0.6192226890756303,0.044037697403367555 +flat_mae,patch,logistic,abide_dx,77,0.3593813663804626,train,0.896011396011396,0.011523972120144386,0.8948746089543054,0.011634720618613925,0.8947582133628644,0.011616866555816938 +flat_mae,patch,logistic,abide_dx,77,0.3593813663804626,test,0.5725806451612904,0.04509687514410225,0.5691904293674206,0.04545602382431249,0.569327731092437,0.045490003505035514 +flat_mae,patch,logistic,abide_dx,78,0.046415888336127774,train,0.7891737891737892,0.015287356124548021,0.7851559592049431,0.015644260609274006,0.7833887043189369,0.015589497594740416 +flat_mae,patch,logistic,abide_dx,78,0.046415888336127774,test,0.6370967741935484,0.04257906888578025,0.6283716283716283,0.04373121065831221,0.6281512605042017,0.04301881502212462 +flat_mae,patch,logistic,abide_dx,79,0.3593813663804626,train,0.8931623931623932,0.011874707785644246,0.8919944612544233,0.012011849811254336,0.8918789221114802,0.012057917253273435 +flat_mae,patch,logistic,abide_dx,79,0.3593813663804626,test,0.5645161290322581,0.04352817930192201,0.5503626107977437,0.045659587183641805,0.5525210084033614,0.04417928880692354 +flat_mae,patch,logistic,abide_dx,80,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,80,1291.5496650148827,test,0.6612903225806451,0.043117690983567554,0.6580882352941176,0.043413423330055316,0.6580882352941176,0.04333112347196611 +flat_mae,patch,logistic,abide_dx,81,2.782559402207126,train,0.9957264957264957,0.002352772722609954,0.9956771535718905,0.002382881979901872,0.9952380952380953,0.002621661033765363 +flat_mae,patch,logistic,abide_dx,81,2.782559402207126,test,0.6290322580645161,0.04057114035568467,0.6266038229903116,0.04083634946943174,0.6271008403361344,0.04088693005547031 +flat_mae,patch,logistic,abide_dx,82,0.005994842503189409,train,0.698005698005698,0.0168013647680578,0.6879528985507246,0.01768935003596822,0.6868217054263566,0.01725759172863738 +flat_mae,patch,logistic,abide_dx,82,0.005994842503189409,test,0.5967741935483871,0.04300164554119738,0.5880946053680574,0.04401951930521276,0.5882352941176471,0.04336643983228027 +flat_mae,patch,logistic,abide_dx,83,0.3593813663804626,train,0.9102564102564102,0.010340222607360844,0.9093289158874289,0.010461213215159063,0.9094499815430048,0.010559179297183733 +flat_mae,patch,logistic,abide_dx,83,0.3593813663804626,test,0.6451612903225806,0.04554124441391506,0.6356837606837606,0.04729232917201183,0.6355042016806722,0.04622300487615161 +flat_mae,patch,logistic,abide_dx,84,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,84,21.54434690031882,test,0.532258064516129,0.04421337852721553,0.5303030303030303,0.04418800636694227,0.5309873949579832,0.04428371978789664 +flat_mae,patch,logistic,abide_dx,85,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,85,1291.5496650148827,test,0.5645161290322581,0.046243361590124994,0.5616653574234092,0.0465373164096626,0.5619747899159664,0.04645945438284653 +flat_mae,patch,logistic,abide_dx,86,2.782559402207126,train,0.9957264957264957,0.0025409703629332907,0.995679778450177,0.002569623925674123,0.9955334071613142,0.002650709824226794 +flat_mae,patch,logistic,abide_dx,86,2.782559402207126,test,0.5967741935483871,0.04255270344219429,0.5860042735042735,0.04444575809164514,0.5866596638655462,0.0432525618125357 +flat_mae,patch,logistic,abide_dx,87,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,87,166.81005372000556,test,0.5887096774193549,0.048369510244904754,0.5884687967723043,0.04835842117023393,0.5919117647058824,0.04826592975675732 +flat_mae,patch,logistic,abide_dx,88,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,88,21.54434690031882,test,0.5645161290322581,0.04312293971009369,0.5603991596638656,0.04373941911555416,0.5603991596638656,0.04375081681069906 +flat_mae,patch,logistic,abide_dx,89,2.782559402207126,train,0.9886039886039886,0.0037858209787888304,0.9884895389256902,0.003821344210068286,0.9887781469176818,0.00374664360038156 +flat_mae,patch,logistic,abide_dx,89,2.782559402207126,test,0.6129032258064516,0.04511609489672713,0.6092436974789917,0.04565612737296109,0.6092436974789917,0.04556472503989574 +flat_mae,patch,logistic,abide_dx,90,0.3593813663804626,train,0.9102564102564102,0.010680599342343555,0.9091635430038512,0.010829478873248857,0.9085640457733482,0.010929953987730166 +flat_mae,patch,logistic,abide_dx,90,0.3593813663804626,test,0.6370967741935484,0.04045623012183878,0.6160990712074303,0.04401773241224558,0.6202731092436975,0.04127240175724774 +flat_mae,patch,logistic,abide_dx,91,0.000774263682681127,train,0.6695156695156695,0.016416836238257532,0.6509259259259259,0.017859565463388627,0.6527131782945736,0.016857917131205536 +flat_mae,patch,logistic,abide_dx,91,0.000774263682681127,test,0.532258064516129,0.04398962546786833,0.5170561375235025,0.045495749621677066,0.5199579831932774,0.04421747123601648 +flat_mae,patch,logistic,abide_dx,92,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,92,1291.5496650148827,test,0.5967741935483871,0.0413576693711923,0.5941345902068604,0.0416384799999713,0.5945378151260504,0.041624885301074284 +flat_mae,patch,logistic,abide_dx,93,2.782559402207126,train,0.9914529914529915,0.0034686021745720646,0.9913671541942677,0.003500996699353552,0.9916574381690662,0.003392364158979407 +flat_mae,patch,logistic,abide_dx,93,2.782559402207126,test,0.6209677419354839,0.043569561757706314,0.6179613241560145,0.043730628423791405,0.618172268907563,0.04372007610766682 +flat_mae,patch,logistic,abide_dx,94,0.3593813663804626,train,0.9116809116809117,0.010830249658990973,0.910844360686632,0.010921765751578643,0.9113325950535253,0.0109110889051469 +flat_mae,patch,logistic,abide_dx,94,0.3593813663804626,test,0.5564516129032258,0.042909104011572684,0.5498646953996436,0.04367009114610589,0.5498949579831933,0.043329941889343554 +flat_mae,patch,logistic,abide_dx,95,2.782559402207126,train,0.9985754985754985,0.0014059735247365429,0.998559926150059,0.001422187239310965,0.9984126984126984,0.001566656213277868 +flat_mae,patch,logistic,abide_dx,95,2.782559402207126,test,0.6209677419354839,0.042334979866433885,0.6118548118548119,0.0435045121891998,0.6118697478991597,0.04274527874615104 +flat_mae,patch,logistic,abide_dx,96,2.782559402207126,train,0.99002849002849,0.003773164130899276,0.9899254350986032,0.003810749654564032,0.9900701365817646,0.0037683617666148875 +flat_mae,patch,logistic,abide_dx,96,2.782559402207126,test,0.5806451612903226,0.04590289710398487,0.5788923719958203,0.046011434179817394,0.5798319327731092,0.04603789469600443 +flat_mae,patch,logistic,abide_dx,97,0.3593813663804626,train,0.9088319088319088,0.011188211931898067,0.9078626799557032,0.011300656615667688,0.9078626799557032,0.011315145542356016 +flat_mae,patch,logistic,abide_dx,97,0.3593813663804626,test,0.6451612903225806,0.044208294572999185,0.6418067226890756,0.04480904571556057,0.6418067226890756,0.044810564576004 +flat_mae,patch,logistic,abide_dx,98,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,98,1291.5496650148827,test,0.6693548387096774,0.044715597406327766,0.6630211440312852,0.045978269510422456,0.6622899159663866,0.045436297303196496 +flat_mae,patch,logistic,abide_dx,99,0.3593813663804626,train,0.8988603988603988,0.011130474398203152,0.8976926345347398,0.011264643782130407,0.8973421926910299,0.011311531777107711 +flat_mae,patch,logistic,abide_dx,99,0.3593813663804626,test,0.5887096774193549,0.04354653221856164,0.5841388834089565,0.04404852969831584,0.5840336134453781,0.04381053475451205 +flat_mae,patch,logistic,abide_dx,100,0.046415888336127774,train,0.7877492877492878,0.01617335531858442,0.78378970563005,0.01661204757341727,0.7820967146548542,0.01658082708618828 +flat_mae,patch,logistic,abide_dx,100,0.046415888336127774,test,0.6532258064516129,0.04355168446297979,0.63853298081486,0.046632474399592914,0.6397058823529411,0.04467562162719097 diff --git a/input_space_v3/flat_lr1e-3_2/eval_v2/abide_dx__patch__logistic/log.txt b/input_space_v3/flat_lr1e-3_2/eval_v2/abide_dx__patch__logistic/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..50d879c293d7a57ee1eb2f11428d20a0b36253e2 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_2/eval_v2/abide_dx__patch__logistic/log.txt @@ -0,0 +1,252 @@ +fMRI foundation model logistic probe eval +version: 0.1.dev86+gf97f52698 +sha: bcce2b486277d3a5b520775efd9cdf1a2affce36, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-04-08 22:02:48 +config: +output_root: experiments/input_space_v3/output +name_prefix: eval_logistic +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_2; eval v2 (abide_dx patch logistic) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: input_space_v3/flat_lr1e-3_2/eval_v2/abide_dx__patch__logistic +model: flat_mae +representation: patch +dataset: abide_dx +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/eval_v2/abide_dx__patch__logistic +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=True, reg_tokens=0, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: abide_dx (flat) +train (n=578): +HFDataset( + dataset=Dataset({ + features: ['sub', 'site', 'dataset', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 578 +}), + labels=['Autism' 'Control'], + counts=[260 318] +) + +validation (n=124): +HFDataset( + dataset=Dataset({ + features: ['sub', 'site', 'dataset', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 124 +}), + labels=['Autism' 'Control'], + counts=[54 70] +) + +test (n=124): +HFDataset( + dataset=Dataset({ + features: ['sub', 'site', 'dataset', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 124 +}), + labels=['Autism' 'Control'], + counts=[57 67] +) + +extracting features for all splits +extract (train) [ 0/289] eta: 0:25:46 time: 5.3515 data: 4.1795 max mem: 2698 +extract (train) [ 20/289] eta: 0:02:02 time: 0.2114 data: 0.0722 max mem: 2851 +extract (train) [ 40/289] eta: 0:01:23 time: 0.2047 data: 0.0675 max mem: 2851 +extract (train) [ 60/289] eta: 0:01:06 time: 0.1998 data: 0.0673 max mem: 2851 +extract (train) [ 80/289] eta: 0:00:55 time: 0.1899 data: 0.0621 max mem: 2851 +extract (train) [100/289] eta: 0:00:47 time: 0.1983 data: 0.0668 max mem: 2851 +extract (train) [120/289] eta: 0:00:41 time: 0.1978 data: 0.0663 max mem: 2851 +extract (train) [140/289] eta: 0:00:35 time: 0.1891 data: 0.0618 max mem: 2851 +extract (train) [160/289] eta: 0:00:29 time: 0.1952 data: 0.0654 max mem: 2851 +extract (train) [180/289] eta: 0:00:24 time: 0.1829 data: 0.0573 max mem: 2851 +extract (train) [200/289] eta: 0:00:19 time: 0.1907 data: 0.0627 max mem: 2851 +extract (train) [220/289] eta: 0:00:15 time: 0.1865 data: 0.0593 max mem: 2851 +extract (train) [240/289] eta: 0:00:10 time: 0.1908 data: 0.0626 max mem: 2851 +extract (train) [260/289] eta: 0:00:06 time: 0.2024 data: 0.0689 max mem: 2851 +extract (train) [280/289] eta: 0:00:01 time: 0.1785 data: 0.0569 max mem: 2851 +extract (train) [288/289] eta: 0:00:00 time: 0.1758 data: 0.0542 max mem: 2851 +extract (train) Total time: 0:01:01 (0.2130 s / it) +extract (validation) [ 0/62] eta: 0:04:21 time: 4.2234 data: 3.9724 max mem: 2851 +extract (validation) [20/62] eta: 0:00:18 time: 0.2623 data: 0.0926 max mem: 2851 +extract (validation) [40/62] eta: 0:00:07 time: 0.1831 data: 0.0573 max mem: 2851 +extract (validation) [60/62] eta: 0:00:00 time: 0.1695 data: 0.0512 max mem: 2851 +extract (validation) [61/62] eta: 0:00:00 time: 0.1701 data: 0.0514 max mem: 2851 +extract (validation) Total time: 0:00:16 (0.2739 s / it) +extract (test) [ 0/62] eta: 0:04:28 time: 4.3366 data: 4.0901 max mem: 2851 +extract (test) [20/62] eta: 0:00:19 time: 0.2684 data: 0.0923 max mem: 2851 +extract (test) [40/62] eta: 0:00:07 time: 0.1924 data: 0.0612 max mem: 2851 +extract (test) [60/62] eta: 0:00:00 time: 0.1682 data: 0.0515 max mem: 2851 +extract (test) [61/62] eta: 0:00:00 time: 0.1685 data: 0.0515 max mem: 2851 +extract (test) Total time: 0:00:17 (0.2808 s / it) +feature extraction time: 0:01:36 +train features: (578, 768) +validation features: (124, 768) +test features: (124, 768) +evaluating fixed splits +eval results (fixed splits): + +| model | repr | clf | dataset | trial | C | split | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|---------:|:--------|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | abide_dx | | 0.046416 | train | 0.80057 | 0.015136 | 0.79644 | 0.015553 | 0.79438 | 0.015504 | +| flat_mae | patch | logistic | abide_dx | | 0.046416 | test | 0.57258 | 0.041653 | 0.55996 | 0.043922 | 0.56258 | 0.042299 | + + +evaluating random splits (n=100) +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 1, "C": 0.3593813663804626, "split": "test", "acc": 0.6451612903225806, "acc_std": 0.045380871710111674, "f1": 0.6418067226890756, "f1_std": 0.04618173543016353, "bacc": 0.6418067226890756, "bacc_std": 0.04611709623332376} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 2, "C": 0.3593813663804626, "split": "test", "acc": 0.6048387096774194, "acc_std": 0.04422985028923001, "f1": 0.5989703649924097, "f1_std": 0.04476767538051069, "bacc": 0.5987394957983193, "bacc_std": 0.044454694117810716} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 3, "C": 0.046415888336127774, "split": "test", "acc": 0.5564516129032258, "acc_std": 0.042795994420009725, "f1": 0.5498646953996436, "f1_std": 0.04368686176032741, "bacc": 0.5498949579831933, "bacc_std": 0.043201848663059185} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 4, "C": 0.3593813663804626, "split": "test", "acc": 0.6451612903225806, "acc_std": 0.043429239635975676, "f1": 0.6405797101449275, "f1_std": 0.0442846982350728, "bacc": 0.6402310924369747, "bacc_std": 0.04406619712793694} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 5, "C": 0.005994842503189409, "split": "test", "acc": 0.5806451612903226, "acc_std": 0.04235491241425423, "f1": 0.5766806722689075, "f1_std": 0.04256677407590462, "bacc": 0.5766806722689075, "bacc_std": 0.04258038346716384} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 6, "C": 0.000774263682681127, "split": "test", "acc": 0.5403225806451613, "acc_std": 0.04337361584545201, "f1": 0.5096774193548387, "f1_std": 0.046320158372624584, "bacc": 0.5210084033613446, "bacc_std": 0.04355449471336164} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 7, "C": 0.046415888336127774, "split": "test", "acc": 0.5806451612903226, "acc_std": 0.042263835483806834, "f1": 0.5643243243243243, "f1_std": 0.04395852873752037, "bacc": 0.5672268907563025, "bacc_std": 0.04247835032639005} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 8, "C": 2.782559402207126, "split": "test", "acc": 0.6209677419354839, "acc_std": 0.043679956566131634, "f1": 0.6167554415729598, "f1_std": 0.0443807138656965, "bacc": 0.6165966386554622, "bacc_std": 0.04423414740075194} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 9, "C": 10000.0, "split": "test", "acc": 0.6693548387096774, "acc_std": 0.04288045417992187, "f1": 0.6630211440312852, "f1_std": 0.04385637413700832, "bacc": 0.6622899159663866, "bacc_std": 0.04331793699729449} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 10, "C": 0.046415888336127774, "split": "test", "acc": 0.6290322580645161, "acc_std": 0.04627673173533388, "f1": 0.6255252100840336, "f1_std": 0.04703007790126472, "bacc": 0.6255252100840336, "bacc_std": 0.0470293708829508} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 11, "C": 166.81005372000556, "split": "test", "acc": 0.4838709677419355, "acc_std": 0.04272754170297172, "f1": 0.4700854700854701, "f1_std": 0.04400789389981201, "bacc": 0.4726890756302521, "bacc_std": 0.04295621708412636} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 12, "C": 0.046415888336127774, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.043516965964356655, "f1": 0.6063492063492064, "f1_std": 0.04427446826553449, "bacc": 0.60609243697479, "bacc_std": 0.04379038295588903} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 13, "C": 0.046415888336127774, "split": "test", "acc": 0.5725806451612904, "acc_std": 0.04315218815253425, "f1": 0.5662332519305657, "f1_std": 0.0437882806329679, "bacc": 0.5661764705882353, "bacc_std": 0.04345613011631512} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 14, "C": 21.54434690031882, "split": "test", "acc": 0.5483870967741935, "acc_std": 0.04501206914113465, "f1": 0.5386659580122243, "f1_std": 0.04641350983167062, "bacc": 0.539390756302521, "bacc_std": 0.045577590729553544} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 15, "C": 2.782559402207126, "split": "test", "acc": 0.6532258064516129, "acc_std": 0.04094745179535325, "f1": 0.6532032520325204, "f1_std": 0.04111235087034635, "bacc": 0.6601890756302521, "bacc_std": 0.04090618150677673} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 16, "C": 0.3593813663804626, "split": "test", "acc": 0.5403225806451613, "acc_std": 0.04400851303512714, "f1": 0.5366764995083579, "f1_std": 0.04435664694246206, "bacc": 0.5367647058823529, "bacc_std": 0.04440147421585783} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 17, "C": 0.046415888336127774, "split": "test", "acc": 0.5967741935483871, "acc_std": 0.043931836331939936, "f1": 0.5915678524374176, "f1_std": 0.0446668756210075, "bacc": 0.5913865546218487, "bacc_std": 0.04447806207521965} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 18, "C": 0.005994842503189409, "split": "test", "acc": 0.6048387096774194, "acc_std": 0.044420877524443646, "f1": 0.5953379953379954, "f1_std": 0.04618211311235825, "bacc": 0.5955882352941176, "bacc_std": 0.04521340547489632} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 19, "C": 0.005994842503189409, "split": "test", "acc": 0.5645161290322581, "acc_std": 0.0409759040637269, "f1": 0.5334448160535117, "f1_std": 0.046184939754892566, "bacc": 0.5446428571428572, "bacc_std": 0.04191543542138331} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 20, "C": 0.046415888336127774, "split": "test", "acc": 0.6209677419354839, "acc_std": 0.04196585748663989, "f1": 0.6137071651090342, "f1_std": 0.04308436587515701, "bacc": 0.6134453781512605, "bacc_std": 0.04254195221231739} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 21, "C": 0.046415888336127774, "split": "test", "acc": 0.5887096774193549, "acc_std": 0.046357756883924545, "f1": 0.5841388834089565, "f1_std": 0.04685648569844466, "bacc": 0.5840336134453781, "bacc_std": 0.046633614403162056} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 22, "C": 166.81005372000556, "split": "test", "acc": 0.5564516129032258, "acc_std": 0.044128265886573065, "f1": 0.5498646953996436, "f1_std": 0.044910212042651096, "bacc": 0.5498949579831933, "bacc_std": 0.04453267589661029} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 23, "C": 2.782559402207126, "split": "test", "acc": 0.6048387096774194, "acc_std": 0.04464281587630023, "f1": 0.5953379953379954, "f1_std": 0.045918930265819016, "bacc": 0.5955882352941176, "bacc_std": 0.04511747228600106} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 24, "C": 2.782559402207126, "split": "test", "acc": 0.5887096774193549, "acc_std": 0.043257523270049766, "f1": 0.5841388834089565, "f1_std": 0.0436973802592238, "bacc": 0.5840336134453781, "bacc_std": 0.04358540411021984} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 25, "C": 21.54434690031882, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.043471913139979786, "f1": 0.6092436974789917, "f1_std": 0.04384659777622353, "bacc": 0.6092436974789917, "bacc_std": 0.04381843689442414} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 26, "C": 0.005994842503189409, "split": "test", "acc": 0.5483870967741935, "acc_std": 0.04729499822856712, "f1": 0.5386659580122243, "f1_std": 0.04845194040278796, "bacc": 0.539390756302521, "bacc_std": 0.0477171002411806} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 27, "C": 0.3593813663804626, "split": "test", "acc": 0.5806451612903226, "acc_std": 0.04204096844859469, "f1": 0.5694444444444444, "f1_std": 0.04323237864363919, "bacc": 0.5703781512605042, "bacc_std": 0.0422986770528742} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 28, "C": 0.3593813663804626, "split": "test", "acc": 0.6209677419354839, "acc_std": 0.04424149741648043, "f1": 0.6153389215233318, "f1_std": 0.0449901356553834, "bacc": 0.6150210084033614, "bacc_std": 0.044689242967816976} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 29, "C": 0.3593813663804626, "split": "test", "acc": 0.6612903225806451, "acc_std": 0.04200925273432707, "f1": 0.6539994685091681, "f1_std": 0.04343170359673055, "bacc": 0.6533613445378151, "bacc_std": 0.04283413653533314} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 30, "C": 0.005994842503189409, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.042646634472626684, "f1": 0.6063492063492064, "f1_std": 0.04344640282154357, "bacc": 0.60609243697479, "bacc_std": 0.0429358948937272} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 31, "C": 166.81005372000556, "split": "test", "acc": 0.7096774193548387, "acc_std": 0.04103759285161778, "f1": 0.7077769049489395, "f1_std": 0.04111972729558379, "bacc": 0.7085084033613445, "bacc_std": 0.04095937674351609} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 32, "C": 2.782559402207126, "split": "test", "acc": 0.6370967741935484, "acc_std": 0.04318499517810298, "f1": 0.6342182890855457, "f1_std": 0.043508039262596485, "bacc": 0.634453781512605, "bacc_std": 0.043423034354682866} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 33, "C": 0.005994842503189409, "split": "test", "acc": 0.6290322580645161, "acc_std": 0.040607368502415246, "f1": 0.6169755573462261, "f1_std": 0.043071536750848925, "bacc": 0.6176470588235294, "bacc_std": 0.041653139996521316} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 34, "C": 10000.0, "split": "test", "acc": 0.6209677419354839, "acc_std": 0.04188857177523967, "f1": 0.6203504657677024, "f1_std": 0.04194170570732389, "bacc": 0.6228991596638656, "bacc_std": 0.04204135028958175} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 35, "C": 2.782559402207126, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.042620326085443694, "f1": 0.607905138339921, "f1_std": 0.04339476313915318, "bacc": 0.6076680672268908, "bacc_std": 0.043139486111764797} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 36, "C": 1291.5496650148827, "split": "test", "acc": 0.5887096774193549, "acc_std": 0.038530688338109575, "f1": 0.5649122807017544, "f1_std": 0.042628136716165374, "bacc": 0.5714285714285714, "bacc_std": 0.0395002857610746} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 37, "C": 0.005994842503189409, "split": "test", "acc": 0.6209677419354839, "acc_std": 0.04242016434895436, "f1": 0.6118548118548119, "f1_std": 0.044027531724373056, "bacc": 0.6118697478991597, "bacc_std": 0.04318793980188522} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 38, "C": 2.782559402207126, "split": "test", "acc": 0.6290322580645161, "acc_std": 0.04595783707662607, "f1": 0.6266038229903116, "f1_std": 0.04618460631138327, "bacc": 0.6271008403361344, "bacc_std": 0.04627585486689761} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 39, "C": 21.54434690031882, "split": "test", "acc": 0.6209677419354839, "acc_std": 0.04110658463954901, "f1": 0.6153389215233318, "f1_std": 0.04191545438842352, "bacc": 0.6150210084033614, "bacc_std": 0.041589842982686934} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 40, "C": 0.3593813663804626, "split": "test", "acc": 0.5806451612903226, "acc_std": 0.04253033134466744, "f1": 0.5716183895827798, "f1_std": 0.04406559294537991, "bacc": 0.571953781512605, "bacc_std": 0.0431878712299396} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 41, "C": 2.782559402207126, "split": "test", "acc": 0.5725806451612904, "acc_std": 0.04699032379859912, "f1": 0.5703170970905524, "f1_std": 0.0474372139854626, "bacc": 0.5709033613445378, "bacc_std": 0.047495560001866464} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 42, "C": 0.3593813663804626, "split": "test", "acc": 0.5806451612903226, "acc_std": 0.046377458171301296, "f1": 0.5788923719958203, "f1_std": 0.04640215930543763, "bacc": 0.5798319327731092, "bacc_std": 0.0465880779747691} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 43, "C": 2.782559402207126, "split": "test", "acc": 0.5645161290322581, "acc_std": 0.0432927352579925, "f1": 0.5603991596638656, "f1_std": 0.04368837948451462, "bacc": 0.5603991596638656, "bacc_std": 0.043572272394039734} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 44, "C": 0.005994842503189409, "split": "test", "acc": 0.6048387096774194, "acc_std": 0.03979087829940008, "f1": 0.5819745442036464, "f1_std": 0.04379538195208709, "bacc": 0.5877100840336134, "bacc_std": 0.040675551338134955} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 45, "C": 0.005994842503189409, "split": "test", "acc": 0.6048387096774194, "acc_std": 0.04271891954870755, "f1": 0.5880957223239103, "f1_std": 0.045384065770027814, "bacc": 0.5908613445378151, "bacc_std": 0.043489616654063444} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 46, "C": 0.3593813663804626, "split": "test", "acc": 0.5403225806451613, "acc_std": 0.04438994212091788, "f1": 0.5400533610984577, "f1_std": 0.04445779674040261, "bacc": 0.5430672268907563, "bacc_std": 0.044319943907581705} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 47, "C": 0.005994842503189409, "split": "test", "acc": 0.5887096774193549, "acc_std": 0.04013992176697529, "f1": 0.5712833028269271, "f1_std": 0.0416758479169066, "bacc": 0.5745798319327731, "bacc_std": 0.04033486532656347} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 48, "C": 0.005994842503189409, "split": "test", "acc": 0.6048387096774194, "acc_std": 0.04303405652284774, "f1": 0.5907590759075907, "f1_std": 0.04595525670341774, "bacc": 0.592436974789916, "bacc_std": 0.04415127633597407} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 49, "C": 0.046415888336127774, "split": "test", "acc": 0.5645161290322581, "acc_std": 0.043743324152474165, "f1": 0.5588932806324111, "f1_std": 0.04462596568689296, "bacc": 0.5588235294117647, "bacc_std": 0.044314300107912034} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 50, "C": 0.005994842503189409, "split": "test", "acc": 0.5564516129032258, "acc_std": 0.04569927261094662, "f1": 0.5406479423452549, "f1_std": 0.04708027788314506, "bacc": 0.54359243697479, "bacc_std": 0.045848651355045865} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 51, "C": 0.3593813663804626, "split": "test", "acc": 0.5645161290322581, "acc_std": 0.044485391445160255, "f1": 0.5528846153846154, "f1_std": 0.046055715627909236, "bacc": 0.5540966386554622, "bacc_std": 0.044935542581315116} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 52, "C": 2.782559402207126, "split": "test", "acc": 0.5887096774193549, "acc_std": 0.04594077024220916, "f1": 0.5865315462569467, "f1_std": 0.04607414614281558, "bacc": 0.5871848739495797, "bacc_std": 0.04595140314305561} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 53, "C": 21.54434690031882, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.042958259633737776, "f1": 0.6063492063492064, "f1_std": 0.04390823704278879, "bacc": 0.60609243697479, "bacc_std": 0.043339235037765024} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 54, "C": 1291.5496650148827, "split": "test", "acc": 0.5725806451612904, "acc_std": 0.04490501885092669, "f1": 0.5678306043269548, "f1_std": 0.04537263399095966, "bacc": 0.5677521008403361, "bacc_std": 0.04521059654984247} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 55, "C": 2.782559402207126, "split": "test", "acc": 0.5806451612903226, "acc_std": 0.04190923185743606, "f1": 0.5778999738151349, "f1_std": 0.04203865579369361, "bacc": 0.5782563025210083, "bacc_std": 0.0420588431526411} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 56, "C": 0.005994842503189409, "split": "test", "acc": 0.6693548387096774, "acc_std": 0.04049587278722571, "f1": 0.6630211440312852, "f1_std": 0.041631539956333175, "bacc": 0.6622899159663866, "bacc_std": 0.04118103348657382} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 57, "C": 0.005994842503189409, "split": "test", "acc": 0.6370967741935484, "acc_std": 0.0426444536567125, "f1": 0.6217205613178767, "f1_std": 0.04564456764081239, "bacc": 0.6234243697478992, "bacc_std": 0.04361511603791241} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 58, "C": 2.782559402207126, "split": "test", "acc": 0.5725806451612904, "acc_std": 0.04708986637365252, "f1": 0.5703170970905524, "f1_std": 0.047165470494662576, "bacc": 0.5709033613445378, "bacc_std": 0.04713445916564135} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 59, "C": 0.005994842503189409, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.04425338543872955, "f1": 0.6092436974789917, "f1_std": 0.044478329993598416, "bacc": 0.6092436974789917, "bacc_std": 0.04434971241752527} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 60, "C": 2.782559402207126, "split": "test", "acc": 0.6048387096774194, "acc_std": 0.04406780734414531, "f1": 0.6017043592264831, "f1_std": 0.04425903587179414, "bacc": 0.601890756302521, "bacc_std": 0.04411209722745683} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 61, "C": 21.54434690031882, "split": "test", "acc": 0.6290322580645161, "acc_std": 0.042474403138317254, "f1": 0.6227513227513227, "f1_std": 0.043466926363572786, "bacc": 0.6223739495798319, "bacc_std": 0.04296793611727676} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 62, "C": 10000.0, "split": "test", "acc": 0.5806451612903226, "acc_std": 0.04235390203617498, "f1": 0.5802083333333333, "f1_std": 0.04255313101011645, "bacc": 0.5829831932773109, "bacc_std": 0.04280784747087481} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 63, "C": 2.782559402207126, "split": "test", "acc": 0.5564516129032258, "acc_std": 0.04597618484999688, "f1": 0.5541026479241582, "f1_std": 0.04641089129230344, "bacc": 0.5546218487394958, "bacc_std": 0.04659276055877711} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 64, "C": 0.3593813663804626, "split": "test", "acc": 0.6854838709677419, "acc_std": 0.0395791433056287, "f1": 0.6779220779220779, "f1_std": 0.04097307937754979, "bacc": 0.6769957983193278, "bacc_std": 0.040259411780579915} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 65, "C": 21.54434690031882, "split": "test", "acc": 0.5967741935483871, "acc_std": 0.04429882386752255, "f1": 0.5880946053680574, "f1_std": 0.0458424551489954, "bacc": 0.5882352941176471, "bacc_std": 0.04505724184744904} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 66, "C": 0.3593813663804626, "split": "test", "acc": 0.5645161290322581, "acc_std": 0.04384466419718592, "f1": 0.5634941329856584, "f1_std": 0.04392768648258941, "bacc": 0.5651260504201681, "bacc_std": 0.04405948390627233} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 67, "C": 2.782559402207126, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.043816768584151976, "f1": 0.607905138339921, "f1_std": 0.044458670027939136, "bacc": 0.6076680672268908, "bacc_std": 0.044130399517458604} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 68, "C": 2.782559402207126, "split": "test", "acc": 0.5967741935483871, "acc_std": 0.0437263508253735, "f1": 0.5941345902068604, "f1_std": 0.043953905193948775, "bacc": 0.5945378151260504, "bacc_std": 0.04398122459854946} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 69, "C": 21.54434690031882, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.04365362135777835, "f1": 0.6025641025641025, "f1_std": 0.044872008138034845, "bacc": 0.6029411764705883, "bacc_std": 0.04401274135826547} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 70, "C": 2.782559402207126, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.043290932522985416, "f1": 0.6112852664576802, "f1_std": 0.04346888274875316, "bacc": 0.6123949579831933, "bacc_std": 0.043605842527199096} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 71, "C": 2.782559402207126, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.04272597389121953, "f1": 0.6045708211533352, "f1_std": 0.04412504238579045, "bacc": 0.6045168067226891, "bacc_std": 0.04343681313180054} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 72, "C": 0.000774263682681127, "split": "test", "acc": 0.5483870967741935, "acc_std": 0.040512491489679496, "f1": 0.5203094777562862, "f1_std": 0.04462739321884685, "bacc": 0.529936974789916, "bacc_std": 0.04127783916503874} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 73, "C": 2.782559402207126, "split": "test", "acc": 0.6290322580645161, "acc_std": 0.04158743907058393, "f1": 0.6210470369386127, "f1_std": 0.04290946528693738, "bacc": 0.6207983193277311, "bacc_std": 0.042186734690205216} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 74, "C": 0.005994842503189409, "split": "test", "acc": 0.6048387096774194, "acc_std": 0.043612855506749995, "f1": 0.5931704050887178, "f1_std": 0.04535691620441678, "bacc": 0.5940126050420168, "bacc_std": 0.044111914130814736} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 75, "C": 2.782559402207126, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.04289561841358959, "f1": 0.6112852664576802, "f1_std": 0.0430521963077633, "bacc": 0.6123949579831933, "bacc_std": 0.04322001258864824} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 76, "C": 0.3593813663804626, "split": "test", "acc": 0.6290322580645161, "acc_std": 0.04350586633808437, "f1": 0.6191239316239316, "f1_std": 0.04503150020139368, "bacc": 0.6192226890756303, "bacc_std": 0.044037697403367555} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 77, "C": 0.3593813663804626, "split": "test", "acc": 0.5725806451612904, "acc_std": 0.04509687514410225, "f1": 0.5691904293674206, "f1_std": 0.04545602382431249, "bacc": 0.569327731092437, "bacc_std": 0.045490003505035514} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 78, "C": 0.046415888336127774, "split": "test", "acc": 0.6370967741935484, "acc_std": 0.04257906888578025, "f1": 0.6283716283716283, "f1_std": 0.04373121065831221, "bacc": 0.6281512605042017, "bacc_std": 0.04301881502212462} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 79, "C": 0.3593813663804626, "split": "test", "acc": 0.5645161290322581, "acc_std": 0.04352817930192201, "f1": 0.5503626107977437, "f1_std": 0.045659587183641805, "bacc": 0.5525210084033614, "bacc_std": 0.04417928880692354} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 80, "C": 1291.5496650148827, "split": "test", "acc": 0.6612903225806451, "acc_std": 0.043117690983567554, "f1": 0.6580882352941176, "f1_std": 0.043413423330055316, "bacc": 0.6580882352941176, "bacc_std": 0.04333112347196611} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 81, "C": 2.782559402207126, "split": "test", "acc": 0.6290322580645161, "acc_std": 0.04057114035568467, "f1": 0.6266038229903116, "f1_std": 0.04083634946943174, "bacc": 0.6271008403361344, "bacc_std": 0.04088693005547031} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 82, "C": 0.005994842503189409, "split": "test", "acc": 0.5967741935483871, "acc_std": 0.04300164554119738, "f1": 0.5880946053680574, "f1_std": 0.04401951930521276, "bacc": 0.5882352941176471, "bacc_std": 0.04336643983228027} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 83, "C": 0.3593813663804626, "split": "test", "acc": 0.6451612903225806, "acc_std": 0.04554124441391506, "f1": 0.6356837606837606, "f1_std": 0.04729232917201183, "bacc": 0.6355042016806722, "bacc_std": 0.04622300487615161} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 84, "C": 21.54434690031882, "split": "test", "acc": 0.532258064516129, "acc_std": 0.04421337852721553, "f1": 0.5303030303030303, "f1_std": 0.04418800636694227, "bacc": 0.5309873949579832, "bacc_std": 0.04428371978789664} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 85, "C": 1291.5496650148827, "split": "test", "acc": 0.5645161290322581, "acc_std": 0.046243361590124994, "f1": 0.5616653574234092, "f1_std": 0.0465373164096626, "bacc": 0.5619747899159664, "bacc_std": 0.04645945438284653} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 86, "C": 2.782559402207126, "split": "test", "acc": 0.5967741935483871, "acc_std": 0.04255270344219429, "f1": 0.5860042735042735, "f1_std": 0.04444575809164514, "bacc": 0.5866596638655462, "bacc_std": 0.0432525618125357} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 87, "C": 166.81005372000556, "split": "test", "acc": 0.5887096774193549, "acc_std": 0.048369510244904754, "f1": 0.5884687967723043, "f1_std": 0.04835842117023393, "bacc": 0.5919117647058824, "bacc_std": 0.04826592975675732} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 88, "C": 21.54434690031882, "split": "test", "acc": 0.5645161290322581, "acc_std": 0.04312293971009369, "f1": 0.5603991596638656, "f1_std": 0.04373941911555416, "bacc": 0.5603991596638656, "bacc_std": 0.04375081681069906} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 89, "C": 2.782559402207126, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.04511609489672713, "f1": 0.6092436974789917, "f1_std": 0.04565612737296109, "bacc": 0.6092436974789917, "bacc_std": 0.04556472503989574} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 90, "C": 0.3593813663804626, "split": "test", "acc": 0.6370967741935484, "acc_std": 0.04045623012183878, "f1": 0.6160990712074303, "f1_std": 0.04401773241224558, "bacc": 0.6202731092436975, "bacc_std": 0.04127240175724774} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 91, "C": 0.000774263682681127, "split": "test", "acc": 0.532258064516129, "acc_std": 0.04398962546786833, "f1": 0.5170561375235025, "f1_std": 0.045495749621677066, "bacc": 0.5199579831932774, "bacc_std": 0.04421747123601648} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 92, "C": 1291.5496650148827, "split": "test", "acc": 0.5967741935483871, "acc_std": 0.0413576693711923, "f1": 0.5941345902068604, "f1_std": 0.0416384799999713, "bacc": 0.5945378151260504, "bacc_std": 0.041624885301074284} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 93, "C": 2.782559402207126, "split": "test", "acc": 0.6209677419354839, "acc_std": 0.043569561757706314, "f1": 0.6179613241560145, "f1_std": 0.043730628423791405, "bacc": 0.618172268907563, "bacc_std": 0.04372007610766682} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 94, "C": 0.3593813663804626, "split": "test", "acc": 0.5564516129032258, "acc_std": 0.042909104011572684, "f1": 0.5498646953996436, "f1_std": 0.04367009114610589, "bacc": 0.5498949579831933, "bacc_std": 0.043329941889343554} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 95, "C": 2.782559402207126, "split": "test", "acc": 0.6209677419354839, "acc_std": 0.042334979866433885, "f1": 0.6118548118548119, "f1_std": 0.0435045121891998, "bacc": 0.6118697478991597, "bacc_std": 0.04274527874615104} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 96, "C": 2.782559402207126, "split": "test", "acc": 0.5806451612903226, "acc_std": 0.04590289710398487, "f1": 0.5788923719958203, "f1_std": 0.046011434179817394, "bacc": 0.5798319327731092, "bacc_std": 0.04603789469600443} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 97, "C": 0.3593813663804626, "split": "test", "acc": 0.6451612903225806, "acc_std": 0.044208294572999185, "f1": 0.6418067226890756, "f1_std": 0.04480904571556057, "bacc": 0.6418067226890756, "bacc_std": 0.044810564576004} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 98, "C": 1291.5496650148827, "split": "test", "acc": 0.6693548387096774, "acc_std": 0.044715597406327766, "f1": 0.6630211440312852, "f1_std": 0.045978269510422456, "bacc": 0.6622899159663866, "bacc_std": 0.045436297303196496} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 99, "C": 0.3593813663804626, "split": "test", "acc": 0.5887096774193549, "acc_std": 0.04354653221856164, "f1": 0.5841388834089565, "f1_std": 0.04404852969831584, "bacc": 0.5840336134453781, "bacc_std": 0.04381053475451205} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 100, "C": 0.046415888336127774, "split": "test", "acc": 0.6532258064516129, "acc_std": 0.04355168446297979, "f1": 0.63853298081486, "f1_std": 0.046632474399592914, "bacc": 0.6397058823529411, "bacc_std": 0.04467562162719097} +eval results (random splits): + +| model | repr | clf | dataset | split | n_trials | C | C_std | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|-----------:|-------:|--------:|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | abide_dx | train | 100 | 386.91 | 1726.7 | 0.89625 | 0.11648 | 0.89355 | 0.12037 | 0.89318 | 0.12078 | +| flat_mae | patch | logistic | abide_dx | test | 100 | 386.91 | 1726.7 | 0.60048 | 0.037711 | 0.59293 | 0.03938 | 0.59397 | 0.038525 | + + +done! total time: 0:06:24 diff --git a/input_space_v3/flat_lr1e-3_2/eval_v2/adhd200_dx__patch__logistic/config.yaml b/input_space_v3/flat_lr1e-3_2/eval_v2/adhd200_dx__patch__logistic/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..35271a5278a6e8513ba068f375a110ea244c27e0 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_2/eval_v2/adhd200_dx__patch__logistic/config.yaml @@ -0,0 +1,30 @@ +output_root: experiments/input_space_v3/output +name_prefix: eval_logistic +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_2; eval v2 (adhd200_dx patch logistic) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: input_space_v3/flat_lr1e-3_2/eval_v2/adhd200_dx__patch__logistic +model: flat_mae +representation: patch +dataset: adhd200_dx +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/eval_v2/adhd200_dx__patch__logistic +remote_dir: null diff --git a/input_space_v3/flat_lr1e-3_2/eval_v2/adhd200_dx__patch__logistic/eval_table.csv b/input_space_v3/flat_lr1e-3_2/eval_v2/adhd200_dx__patch__logistic/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..c59afb852a7ed4e40d17178f77d4c0979033887d --- /dev/null +++ b/input_space_v3/flat_lr1e-3_2/eval_v2/adhd200_dx__patch__logistic/eval_table.csv @@ -0,0 +1,203 @@ +model,repr,clf,dataset,trial,C,split,acc,acc_std,f1,f1_std,bacc,bacc_std +flat_mae,patch,logistic,adhd200_dx,,0.005994842503189409,train,0.7534246575342466,0.02177477920830142,0.7413059913059913,0.02334351717994827,0.7377877511143677,0.022682821905326032 +flat_mae,patch,logistic,adhd200_dx,,0.005994842503189409,test,0.6307692307692307,0.059097840848032754,0.61,0.06405595528070906,0.6105212355212355,0.06130023778880736 +flat_mae,patch,logistic,adhd200_dx,1,0.005994842503189409,train,0.7397260273972602,0.021943204464720315,0.7265917602996255,0.02358386767896961,0.7234994199181779,0.022855996359773246 +flat_mae,patch,logistic,adhd200_dx,1,0.005994842503189409,test,0.6307692307692307,0.05894250734060804,0.6153846153846154,0.061603974574624375,0.6148648648648649,0.06021561682277206 +flat_mae,patch,logistic,adhd200_dx,2,0.005994842503189409,train,0.7315068493150685,0.023420067803177326,0.7190013826043238,0.025065201982982153,0.7162178665201197,0.02437516174594273 +flat_mae,patch,logistic,adhd200_dx,2,0.005994842503189409,test,0.6615384615384615,0.05408022968334686,0.6366869918699187,0.05969321755407053,0.6375482625482626,0.05588518590094086 +flat_mae,patch,logistic,adhd200_dx,3,0.005994842503189409,train,0.7726027397260274,0.022088026694345984,0.7628552865384465,0.023586379076825825,0.759082860108689,0.023251626631862355 +flat_mae,patch,logistic,adhd200_dx,3,0.005994842503189409,test,0.5846153846153846,0.05894918080143068,0.5699583435432491,0.061629831029543114,0.5699806949806949,0.060299441986599596 +flat_mae,patch,logistic,adhd200_dx,4,0.005994842503189409,train,0.7561643835616438,0.02179615209618518,0.7468536917981687,0.02315741018185824,0.7438022836905416,0.022830755213295945 +flat_mae,patch,logistic,adhd200_dx,4,0.005994842503189409,test,0.6153846153846154,0.058965889246873536,0.606060606060606,0.06106753965820011,0.6056949806949807,0.0604302455925058 +flat_mae,patch,logistic,adhd200_dx,5,0.005994842503189409,train,0.7753424657534247,0.02126718147919597,0.767984496124031,0.022508257421521193,0.7650973926848629,0.02243749304024331 +flat_mae,patch,logistic,adhd200_dx,5,0.005994842503189409,test,0.5230769230769231,0.062289448421184335,0.5189782764382908,0.0629660314164797,0.5202702702702703,0.06365376187269381 +flat_mae,patch,logistic,adhd200_dx,6,0.005994842503189409,train,0.7589041095890411,0.020421272378258092,0.7488584474885844,0.021620445624595617,0.7455119985345301,0.021221057717484604 +flat_mae,patch,logistic,adhd200_dx,6,0.005994842503189409,test,0.6461538461538462,0.058195540608757666,0.6289401836684041,0.06253118357978447,0.6283783783783784,0.05997326096916544 +flat_mae,patch,logistic,adhd200_dx,7,0.005994842503189409,train,0.7506849315068493,0.02241294093121123,0.7417205153925708,0.023682180379437735,0.7389479147585027,0.02339954162943178 +flat_mae,patch,logistic,adhd200_dx,7,0.005994842503189409,test,0.6615384615384615,0.05473751026111618,0.6474358974358974,0.05793048083082731,0.6462355212355213,0.056518194715923294 +flat_mae,patch,logistic,adhd200_dx,8,0.005994842503189409,train,0.7506849315068493,0.02235723876010952,0.7432776064491695,0.02345848636646431,0.7411003236245954,0.023360303206666964 +flat_mae,patch,logistic,adhd200_dx,8,0.005994842503189409,test,0.6153846153846154,0.06082428664730764,0.5905769715293525,0.06678012138586842,0.5926640926640927,0.06258889817433187 +flat_mae,patch,logistic,adhd200_dx,9,0.005994842503189409,train,0.7780821917808219,0.021795887612860054,0.7705809775818855,0.022810544121156573,0.7675245771508823,0.022654446549280633 +flat_mae,patch,logistic,adhd200_dx,9,0.005994842503189409,test,0.5692307692307692,0.061250487741084235,0.5512820512820513,0.06427367783625362,0.5521235521235521,0.062391303932445435 +flat_mae,patch,logistic,adhd200_dx,10,0.005994842503189409,train,0.7534246575342466,0.022656788843314953,0.7458531905675558,0.02357512838385368,0.7435275080906149,0.023410712841864186 +flat_mae,patch,logistic,adhd200_dx,10,0.005994842503189409,test,0.5384615384615384,0.05807225860025517,0.5192307692307693,0.06049564307801839,0.5207528957528957,0.05888729549029609 +flat_mae,patch,logistic,adhd200_dx,11,0.005994842503189409,train,0.7643835616438356,0.02048765584526821,0.7521789932419629,0.022381918942309446,0.7482139586004762,0.02174723506498849 +flat_mae,patch,logistic,adhd200_dx,11,0.005994842503189409,test,0.5230769230769231,0.06047728117617009,0.4923154446963971,0.06387574247309044,0.4985521235521235,0.06092600840259674 +flat_mae,patch,logistic,adhd200_dx,12,0.005994842503189409,train,0.7561643835616438,0.020667156655753097,0.7473969875817451,0.02184041054421327,0.7445197533125725,0.02159684531863594 +flat_mae,patch,logistic,adhd200_dx,12,0.005994842503189409,test,0.5846153846153846,0.0570011938004333,0.5644080416976918,0.06198901346314867,0.5656370656370656,0.05903868831409257 +flat_mae,patch,logistic,adhd200_dx,13,0.005994842503189409,train,0.7534246575342466,0.022680443603447547,0.7448266219239373,0.02379163025698952,0.7420925688465531,0.02356156858478572 +flat_mae,patch,logistic,adhd200_dx,13,0.005994842503189409,test,0.6307692307692307,0.05837645630635329,0.6198830409356726,0.06020869626809582,0.6192084942084942,0.059438170571788095 +flat_mae,patch,logistic,adhd200_dx,14,0.000774263682681127,train,0.6794520547945205,0.022700289950143903,0.6624137358597956,0.024290711293322925,0.66149172620138,0.023388721238300592 +flat_mae,patch,logistic,adhd200_dx,14,0.000774263682681127,test,0.5846153846153846,0.06060381771714956,0.5644080416976918,0.06405068894389736,0.5656370656370656,0.06180517511227803 +flat_mae,patch,logistic,adhd200_dx,15,0.005994842503189409,train,0.7315068493150685,0.022758545768941003,0.7190013826043238,0.024534752509356113,0.7162178665201197,0.023875594222126633 +flat_mae,patch,logistic,adhd200_dx,15,0.005994842503189409,test,0.6,0.05889687306474542,0.599146110056926,0.05890847049780926,0.6052123552123552,0.05910914783705134 +flat_mae,patch,logistic,adhd200_dx,16,0.005994842503189409,train,0.7671232876712328,0.020581525072966345,0.7597363876433645,0.021571211562444473,0.7570983696647737,0.021423018599271208 +flat_mae,patch,logistic,adhd200_dx,16,0.005994842503189409,test,0.5846153846153846,0.062264182339181684,0.578226387887527,0.06308873927466953,0.5786679536679536,0.06319487123244827 +flat_mae,patch,logistic,adhd200_dx,17,0.005994842503189409,train,0.7753424657534247,0.019165196453820397,0.7648787078934138,0.020558478826349827,0.7607925749526775,0.020163327009141443 +flat_mae,patch,logistic,adhd200_dx,17,0.005994842503189409,test,0.5538461538461539,0.05728298693081547,0.5167905665214048,0.06341598226193546,0.5255791505791506,0.05860371717089946 +flat_mae,patch,logistic,adhd200_dx,18,0.005994842503189409,train,0.726027397260274,0.023298501268989857,0.7125622125622125,0.025093879502123887,0.709928558344019,0.0243132075189523 +flat_mae,patch,logistic,adhd200_dx,18,0.005994842503189409,test,0.6307692307692307,0.06039061018748335,0.6235521235521235,0.061506940769785357,0.6235521235521235,0.06117754172597732 +flat_mae,patch,logistic,adhd200_dx,19,0.005994842503189409,train,0.7424657534246575,0.0240996716838094,0.7298084798084798,0.025999614514166467,0.7266440740062282,0.025222246478274445 +flat_mae,patch,logistic,adhd200_dx,19,0.005994842503189409,test,0.7230769230769231,0.05704970530808766,0.7075,0.061867771549056545,0.7046332046332047,0.059577119481288715 +flat_mae,patch,logistic,adhd200_dx,20,0.046415888336127774,train,0.8136986301369863,0.019059209675303328,0.8083456881640722,0.019855287110620314,0.8055352018074128,0.019893062095514814 +flat_mae,patch,logistic,adhd200_dx,20,0.046415888336127774,test,0.6,0.05584343286441872,0.5833333333333333,0.05939518106483849,0.5834942084942085,0.05754575150529048 +flat_mae,patch,logistic,adhd200_dx,21,0.005994842503189409,train,0.7452054794520548,0.0220312264101757,0.734283634314163,0.023377169454495233,0.7312236673383403,0.022862631930314604 +flat_mae,patch,logistic,adhd200_dx,21,0.005994842503189409,test,0.6615384615384615,0.05912126540990678,0.6575670498084292,0.05970301337656005,0.6592664092664093,0.059881181016699085 +flat_mae,patch,logistic,adhd200_dx,22,0.005994842503189409,train,0.7452054794520548,0.02295059842572913,0.734283634314163,0.024479863480040002,0.7312236673383403,0.02399352466669183 +flat_mae,patch,logistic,adhd200_dx,22,0.005994842503189409,test,0.5846153846153846,0.061056970195608753,0.578226387887527,0.06235933400563895,0.5786679536679536,0.062420509064024694 +flat_mae,patch,logistic,adhd200_dx,23,0.005994842503189409,train,0.7424657534246575,0.0215485406914208,0.7311128526645768,0.022966281569990973,0.72807901325029,0.022392997210420942 +flat_mae,patch,logistic,adhd200_dx,23,0.005994842503189409,test,0.6153846153846154,0.05144463560512776,0.5751633986928104,0.06014826755001408,0.583976833976834,0.053668820095225486 +flat_mae,patch,logistic,adhd200_dx,24,0.005994842503189409,train,0.7452054794520548,0.023043671935875025,0.7330129541218018,0.024718946273593428,0.7297887280942785,0.024049746101494233 +flat_mae,patch,logistic,adhd200_dx,24,0.005994842503189409,test,0.5846153846153846,0.056974147568210794,0.5501153550371699,0.06349020861166332,0.556949806949807,0.05827987583466787 +flat_mae,patch,logistic,adhd200_dx,25,0.000774263682681127,train,0.6575342465753424,0.022087949893404003,0.6259908680290845,0.025500868881282432,0.6305947365207303,0.02308262555818167 +flat_mae,patch,logistic,adhd200_dx,25,0.000774263682681127,test,0.6153846153846154,0.05349738477266709,0.5751633986928104,0.06185897132333864,0.583976833976834,0.05539811962744256 +flat_mae,patch,logistic,adhd200_dx,26,0.3593813663804626,train,0.9534246575342465,0.011065780218182435,0.9524597574336697,0.011347985213501846,0.95084569823533,0.011761062483010386 +flat_mae,patch,logistic,adhd200_dx,26,0.3593813663804626,test,0.5846153846153846,0.06119265145191844,0.5810455956075435,0.06153964511728402,0.583011583011583,0.06170853629571692 +flat_mae,patch,logistic,adhd200_dx,27,0.005994842503189409,train,0.7287671232876712,0.022799011017124827,0.7184102863822326,0.024133337918462686,0.7159430909201929,0.023735596450061593 +flat_mae,patch,logistic,adhd200_dx,27,0.005994842503189409,test,0.6153846153846154,0.05757741174449635,0.606060606060606,0.05885276147833077,0.6056949806949807,0.05803047228270683 +flat_mae,patch,logistic,adhd200_dx,28,0.046415888336127774,train,0.8301369863013699,0.018937654573444512,0.8255796029103466,0.019620179769839912,0.822968187091653,0.019698303406908615 +flat_mae,patch,logistic,adhd200_dx,28,0.046415888336127774,test,0.5692307692307692,0.05664734883626518,0.5512820512820513,0.05885866272963064,0.5521235521235521,0.057365803430973646 +flat_mae,patch,logistic,adhd200_dx,29,0.3593813663804626,train,0.9643835616438357,0.009671620932103712,0.9635865519649449,0.00995859997189448,0.9612719057214386,0.010642874851680403 +flat_mae,patch,logistic,adhd200_dx,29,0.3593813663804626,test,0.5076923076923077,0.06070396495243737,0.5047619047619047,0.061250041522727554,0.5067567567567568,0.06145650089676941 +flat_mae,patch,logistic,adhd200_dx,30,0.005994842503189409,train,0.726027397260274,0.022474713214999057,0.7164740243599304,0.023967095017325152,0.7142333760762044,0.023631833222061426 +flat_mae,patch,logistic,adhd200_dx,30,0.005994842503189409,test,0.5846153846153846,0.059290032290378145,0.5699583435432491,0.06178904549839272,0.5699806949806949,0.06044961320880358 +flat_mae,patch,logistic,adhd200_dx,31,0.005994842503189409,train,0.7397260273972602,0.022066494981943564,0.7279303878414111,0.023432997853301038,0.7249343591622397,0.022873925993937703 +flat_mae,patch,logistic,adhd200_dx,31,0.005994842503189409,test,0.6,0.058537109051392984,0.5775,0.06365588266787665,0.5791505791505791,0.06054490047232745 +flat_mae,patch,logistic,adhd200_dx,32,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adhd200_dx,32,2.782559402207126,test,0.5538461538461539,0.060355483418644114,0.5469838981014179,0.061088827618924584,0.5472972972972974,0.06120753335672655 +flat_mae,patch,logistic,adhd200_dx,33,0.046415888336127774,train,0.8493150684931506,0.017842538900278638,0.8442216514444901,0.018812564331841388,0.8399584783537889,0.019005458151864645 +flat_mae,patch,logistic,adhd200_dx,33,0.046415888336127774,test,0.5846153846153846,0.06012669857606357,0.5810455956075435,0.06078300300090024,0.583011583011583,0.06123524531523332 +flat_mae,patch,logistic,adhd200_dx,34,0.046415888336127774,train,0.8164383561643835,0.019974135273897374,0.8116832613332717,0.02071406182057597,0.809397325517494,0.0207634458788847 +flat_mae,patch,logistic,adhd200_dx,34,0.046415888336127774,test,0.5846153846153846,0.06133162162091336,0.5830363506771205,0.06197959950036834,0.5873552123552124,0.06267626955224453 +flat_mae,patch,logistic,adhd200_dx,35,0.005994842503189409,train,0.7452054794520548,0.021945188377535108,0.7316622002988118,0.023786904284550017,0.7283537888502167,0.022978036772343367 +flat_mae,patch,logistic,adhd200_dx,35,0.005994842503189409,test,0.5230769230769231,0.057014678894714954,0.4923154446963971,0.0608245198098326,0.4985521235521235,0.05760879708376629 +flat_mae,patch,logistic,adhd200_dx,36,0.000774263682681127,train,0.684931506849315,0.0239431684660658,0.6714259994207391,0.025509833371168245,0.6699334432435733,0.024858303320786312 +flat_mae,patch,logistic,adhd200_dx,36,0.000774263682681127,test,0.5230769230769231,0.05560244343530534,0.4923154446963971,0.05952932449781949,0.4985521235521235,0.0562998671589309 +flat_mae,patch,logistic,adhd200_dx,37,0.000774263682681127,train,0.6794520547945205,0.02182328659639212,0.6534388314059647,0.024908377970615864,0.6550344996031019,0.022994198612536636 +flat_mae,patch,logistic,adhd200_dx,37,0.000774263682681127,test,0.6153846153846154,0.048326463770813156,0.5656241646618552,0.060577168715194606,0.5796332046332047,0.051047202560797644 +flat_mae,patch,logistic,adhd200_dx,38,0.005994842503189409,train,0.7424657534246575,0.02232299177348091,0.732337889284154,0.023578706508888953,0.7295139524943518,0.0231696811539343 +flat_mae,patch,logistic,adhd200_dx,38,0.005994842503189409,test,0.5384615384615384,0.05815155876657347,0.5248538011695907,0.05989667755854438,0.525096525096525,0.05872059650388699 +flat_mae,patch,logistic,adhd200_dx,39,0.005994842503189409,train,0.7726027397260274,0.020980537854450677,0.7617212386248339,0.02280003417885627,0.7576479208646272,0.022287402029586848 +flat_mae,patch,logistic,adhd200_dx,39,0.005994842503189409,test,0.6307692307692307,0.05786921798791258,0.61,0.06224133442202154,0.6105212355212355,0.05941162162010358 +flat_mae,patch,logistic,adhd200_dx,40,0.000774263682681127,train,0.663013698630137,0.022625824657952914,0.6379698247707828,0.02498948270943597,0.6397539231849545,0.023349510835830856 +flat_mae,patch,logistic,adhd200_dx,40,0.000774263682681127,test,0.6615384615384615,0.048211604584042285,0.6130952380952381,0.06007641908921364,0.6245173745173745,0.05100462526170923 +flat_mae,patch,logistic,adhd200_dx,41,0.005994842503189409,train,0.7561643835616438,0.020805884959303307,0.7457122952038764,0.0223698473368044,0.7423673444464798,0.021979803532467843 +flat_mae,patch,logistic,adhd200_dx,41,0.005994842503189409,test,0.6461538461538462,0.05597371318795402,0.6289401836684041,0.059686489002563105,0.6283783783783784,0.057572793377780034 +flat_mae,patch,logistic,adhd200_dx,42,0.046415888336127774,train,0.8493150684931506,0.018144592205637355,0.8445353096515887,0.01893031687708631,0.8406759479758198,0.01898299394599047 +flat_mae,patch,logistic,adhd200_dx,42,0.046415888336127774,test,0.5692307692307692,0.06315605542842355,0.5608108108108107,0.06353841110614689,0.5608108108108107,0.06313109393233973 +flat_mae,patch,logistic,adhd200_dx,43,0.005994842503189409,train,0.7506849315068493,0.0214373160936381,0.7399979647590196,0.0230018153466418,0.73679550589241,0.022537582070231273 +flat_mae,patch,logistic,adhd200_dx,43,0.005994842503189409,test,0.6461538461538462,0.06240652370692852,0.6407113674597452,0.0629750619025757,0.6414092664092663,0.06284490731781295 +flat_mae,patch,logistic,adhd200_dx,44,0.3593813663804626,train,0.9506849315068493,0.010832546886976652,0.9495391705069125,0.011157507755355423,0.9469835745252488,0.011646237776967803 +flat_mae,patch,logistic,adhd200_dx,44,0.3593813663804626,test,0.676923076923077,0.0547599300659561,0.6612062546537603,0.05916536798016416,0.6597490347490347,0.05691862080474488 +flat_mae,patch,logistic,adhd200_dx,45,0.046415888336127774,train,0.8383561643835616,0.019290143054562628,0.8332287867171588,0.020239906074967513,0.8295322708676803,0.02042859087878961 +flat_mae,patch,logistic,adhd200_dx,45,0.046415888336127774,test,0.47692307692307695,0.061365572523396694,0.4666988416988417,0.062556501737144,0.4666988416988417,0.06201304402500115 +flat_mae,patch,logistic,adhd200_dx,46,0.3593813663804626,train,0.947945205479452,0.011001238777719469,0.9466903427653375,0.011367110097575813,0.9438389204371985,0.011982255017444748 +flat_mae,patch,logistic,adhd200_dx,46,0.3593813663804626,test,0.6,0.05639676855067655,0.599905303030303,0.056491723085260584,0.6095559845559846,0.056457784057814674 +flat_mae,patch,logistic,adhd200_dx,47,0.005994842503189409,train,0.7506849315068493,0.021627046722433502,0.7399979647590196,0.023096383966555487,0.73679550589241,0.02259791015177233 +flat_mae,patch,logistic,adhd200_dx,47,0.005994842503189409,test,0.5692307692307692,0.05665833654981159,0.5376016260162602,0.06119665957552759,0.5434362934362934,0.057363646967686005 +flat_mae,patch,logistic,adhd200_dx,48,0.046415888336127774,train,0.8027397260273973,0.019706427858198476,0.7974472807991121,0.020351495653020833,0.7951089943213042,0.02031360977119916 +flat_mae,patch,logistic,adhd200_dx,48,0.046415888336127774,test,0.6923076923076923,0.054970167272265315,0.6904761904761905,0.055486948035640145,0.6949806949806949,0.055714538364641186 +flat_mae,patch,logistic,adhd200_dx,49,0.005994842503189409,train,0.7534246575342466,0.022256243934459876,0.7431506849315068,0.023868185078510167,0.7399401599804604,0.023420214304501114 +flat_mae,patch,logistic,adhd200_dx,49,0.005994842503189409,test,0.5692307692307692,0.060494029242269,0.5565302144249512,0.06263942839932318,0.5564671814671815,0.061605363608883495 +flat_mae,patch,logistic,adhd200_dx,50,0.046415888336127774,train,0.8136986301369863,0.02140887131690948,0.8087002096436059,0.022203944227733488,0.8062526714294437,0.022265320784612293 +flat_mae,patch,logistic,adhd200_dx,50,0.046415888336127774,test,0.6615384615384615,0.05866332785908893,0.6515594541910331,0.060761411796487905,0.6505791505791505,0.060007433524804046 +flat_mae,patch,logistic,adhd200_dx,51,0.005994842503189409,train,0.7424657534246575,0.022192338230780716,0.7334855828983347,0.023527563429037113,0.7309488917384136,0.0232811218710848 +flat_mae,patch,logistic,adhd200_dx,51,0.005994842503189409,test,0.6,0.059402141694301074,0.5953065134099617,0.06019669395954965,0.5965250965250966,0.06057435794005852 +flat_mae,patch,logistic,adhd200_dx,52,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adhd200_dx,52,21.54434690031882,test,0.5538461538461539,0.06067068153262444,0.5381034060279344,0.06227076379630303,0.5386100386100386,0.06103541025983018 +flat_mae,patch,logistic,adhd200_dx,53,0.046415888336127774,train,0.8301369863013699,0.01984751856642314,0.8249210868354273,0.02079214449178521,0.8215332478475912,0.02087884261264684 +flat_mae,patch,logistic,adhd200_dx,53,0.046415888336127774,test,0.5846153846153846,0.059846936913998915,0.5578231292517006,0.06485177547968979,0.5612934362934363,0.061374970631221513 +flat_mae,patch,logistic,adhd200_dx,54,0.000774263682681127,train,0.6904109589041096,0.023089822566961536,0.680590727102355,0.024210749483800902,0.6790926299077975,0.023921405886091134 +flat_mae,patch,logistic,adhd200_dx,54,0.000774263682681127,test,0.49230769230769234,0.061449165982948854,0.48000000000000004,0.06322073269872715,0.48021235521235517,0.062390273345522204 +flat_mae,patch,logistic,adhd200_dx,55,0.005994842503189409,train,0.7452054794520548,0.023758246970642286,0.7371233417745046,0.024800863605816226,0.7348110154484948,0.024588740097042795 +flat_mae,patch,logistic,adhd200_dx,55,0.005994842503189409,test,0.5846153846153846,0.06010687916600664,0.578226387887527,0.06073980886754974,0.5786679536679536,0.06078583819527776 +flat_mae,patch,logistic,adhd200_dx,56,0.005994842503189409,train,0.7534246575342466,0.02095279703307177,0.7413059913059913,0.022694733376917152,0.7377877511143677,0.022089655407812023 +flat_mae,patch,logistic,adhd200_dx,56,0.005994842503189409,test,0.6461538461538462,0.06112552997071832,0.6407113674597452,0.062384316205707085,0.6414092664092663,0.06245842620068136 +flat_mae,patch,logistic,adhd200_dx,57,0.046415888336127774,train,0.8328767123287671,0.019163908656859237,0.8279113625648279,0.019969541511308978,0.8246779019356415,0.020034985909659905 +flat_mae,patch,logistic,adhd200_dx,57,0.046415888336127774,test,0.5076923076923077,0.06083860499705893,0.48,0.06338333171181566,0.48503861003861004,0.06106514003504446 +flat_mae,patch,logistic,adhd200_dx,58,0.005994842503189409,train,0.7534246575342466,0.02198549753150102,0.7453488372093022,0.023082313452841608,0.742810038468584,0.022904203122227282 +flat_mae,patch,logistic,adhd200_dx,58,0.005994842503189409,test,0.6307692307692307,0.05962783988994427,0.6235521235521235,0.060761126416081467,0.6235521235521235,0.06030415097305269 +flat_mae,patch,logistic,adhd200_dx,59,0.046415888336127774,train,0.8465753424657534,0.01851907589189213,0.8412254536415611,0.019568784591531108,0.8368138242657386,0.019742610583911187 +flat_mae,patch,logistic,adhd200_dx,59,0.046415888336127774,test,0.6,0.06083984991169938,0.5833333333333333,0.06365456070958665,0.5834942084942085,0.06187489303401872 +flat_mae,patch,logistic,adhd200_dx,60,0.005994842503189409,train,0.7479452054794521,0.022377202027422757,0.7396899224806202,0.023385345006422226,0.7372381999145142,0.02311944741925948 +flat_mae,patch,logistic,adhd200_dx,60,0.005994842503189409,test,0.6307692307692307,0.058383194469382234,0.61,0.06315728954702812,0.6105212355212355,0.06017631288936422 +flat_mae,patch,logistic,adhd200_dx,61,0.046415888336127774,train,0.8383561643835616,0.01850509122379503,0.8335536129725385,0.01925840932252261,0.8302497404897112,0.019342872520695126 +flat_mae,patch,logistic,adhd200_dx,61,0.046415888336127774,test,0.6307692307692307,0.05732064902575448,0.6153846153846154,0.06070649167713494,0.6148648648648649,0.05925127989546392 +flat_mae,patch,logistic,adhd200_dx,62,0.005994842503189409,train,0.7671232876712328,0.0222834561691024,0.7582310539645432,0.023586034574940587,0.754945960798681,0.02328753615396685 +flat_mae,patch,logistic,adhd200_dx,62,0.005994842503189409,test,0.5846153846153846,0.06108110041905243,0.5810455956075435,0.06141636019138602,0.583011583011583,0.06155607461492958 +flat_mae,patch,logistic,adhd200_dx,63,0.005994842503189409,train,0.7561643835616438,0.022952520772138704,0.747922308701084,0.024126336857604555,0.7452372229346034,0.023953504176077934 +flat_mae,patch,logistic,adhd200_dx,63,0.005994842503189409,test,0.6,0.056501046751575044,0.5775,0.06018250042000316,0.5791505791505791,0.05774833276460005 +flat_mae,patch,logistic,adhd200_dx,64,0.046415888336127774,train,0.8246575342465754,0.01977221685103503,0.8196194712132444,0.020568587601568305,0.8166788789155524,0.020604464913161084 +flat_mae,patch,logistic,adhd200_dx,64,0.046415888336127774,test,0.6461538461538462,0.059002027846005674,0.6233308138070043,0.06394371584928607,0.6240347490347491,0.06073228845923562 +flat_mae,patch,logistic,adhd200_dx,65,0.005994842503189409,train,0.7424657534246575,0.02295566328844742,0.7298084798084798,0.024786858338212103,0.7266440740062282,0.024137515092866216 +flat_mae,patch,logistic,adhd200_dx,65,0.005994842503189409,test,0.7384615384615385,0.0522936723292644,0.7257383966244726,0.05668058842990602,0.7224903474903475,0.054996775716552405 +flat_mae,patch,logistic,adhd200_dx,66,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adhd200_dx,66,1291.5496650148827,test,0.5076923076923077,0.05643425037496834,0.4715447154471545,0.05981134791200525,0.4806949806949807,0.05637187134242317 +flat_mae,patch,logistic,adhd200_dx,67,0.005994842503189409,train,0.7397260273972602,0.021504168055531826,0.7291883068704555,0.02291013874816857,0.7263692984063015,0.022495223161177216 +flat_mae,patch,logistic,adhd200_dx,67,0.005994842503189409,test,0.6307692307692307,0.053708448091987396,0.5962732919254659,0.06287446368471691,0.6018339768339769,0.05637455125514001 +flat_mae,patch,logistic,adhd200_dx,68,0.005994842503189409,train,0.7643835616438356,0.02267632687050031,0.7528035028035027,0.0247206216771129,0.7489314282225071,0.0241572589788755 +flat_mae,patch,logistic,adhd200_dx,68,0.005994842503189409,test,0.676923076923077,0.05523291189329979,0.6612062546537603,0.058941970775107086,0.6597490347490347,0.05705042759308765 +flat_mae,patch,logistic,adhd200_dx,69,0.005994842503189409,train,0.7589041095890411,0.022311852404958765,0.7510077519379845,0.02351883259467153,0.7483818770226537,0.023354869561881098 +flat_mae,patch,logistic,adhd200_dx,69,0.005994842503189409,test,0.5384615384615384,0.062059112877354765,0.5192307692307693,0.06491752908889238,0.5207528957528957,0.06298623886438025 +flat_mae,patch,logistic,adhd200_dx,70,0.005994842503189409,train,0.7534246575342466,0.022187390737760194,0.7425548589341693,0.023997467136096514,0.7392226903584295,0.023520580441723504 +flat_mae,patch,logistic,adhd200_dx,70,0.005994842503189409,test,0.49230769230769234,0.06271868251242746,0.48000000000000004,0.06443351625939978,0.48021235521235517,0.06363040302445853 +flat_mae,patch,logistic,adhd200_dx,71,0.046415888336127774,train,0.8383561643835616,0.018914243065213263,0.8335536129725385,0.01963898862945296,0.8302497404897112,0.01966933743324471 +flat_mae,patch,logistic,adhd200_dx,71,0.046415888336127774,test,0.6461538461538462,0.057800669515583505,0.6375757575757576,0.059627678482444164,0.6370656370656371,0.059171391075938294 +flat_mae,patch,logistic,adhd200_dx,72,0.005994842503189409,train,0.7506849315068493,0.02132767173263404,0.7393859504586148,0.022752809163675544,0.7360780362703792,0.022201254063570573 +flat_mae,patch,logistic,adhd200_dx,72,0.005994842503189409,test,0.6923076923076923,0.0533469962775255,0.6697154471544715,0.06010857336653079,0.6689189189189189,0.056163480756742795 +flat_mae,patch,logistic,adhd200_dx,73,0.000774263682681127,train,0.6547945205479452,0.02396099852214573,0.6369134087033411,0.02566345516990697,0.6367771875190816,0.02463606073442004 +flat_mae,patch,logistic,adhd200_dx,73,0.000774263682681127,test,0.5846153846153846,0.06058988921062831,0.5644080416976918,0.06387605978526852,0.5656370656370656,0.06172614473226555 +flat_mae,patch,logistic,adhd200_dx,74,0.005994842503189409,train,0.7452054794520548,0.02045832510840809,0.7348896056731828,0.021536422363800985,0.7319411369603712,0.021154951474571557 +flat_mae,patch,logistic,adhd200_dx,74,0.005994842503189409,test,0.6,0.06135742602008864,0.588206627680312,0.06332619318976772,0.5878378378378378,0.06202216707741433 +flat_mae,patch,logistic,adhd200_dx,75,0.005994842503189409,train,0.7397260273972602,0.02274657431125298,0.729787648548607,0.0238638473549043,0.7270867680283324,0.023431962451684833 +flat_mae,patch,logistic,adhd200_dx,75,0.005994842503189409,test,0.6,0.06136229399444219,0.588206627680312,0.06340325109637322,0.5878378378378378,0.06252046816793909 +flat_mae,patch,logistic,adhd200_dx,76,0.005994842503189409,train,0.7589041095890411,0.021722087776998567,0.7470547470547471,0.02346654244801141,0.7433595896684374,0.022841467681825014 +flat_mae,patch,logistic,adhd200_dx,76,0.005994842503189409,test,0.5384615384615384,0.04912426942106972,0.4583333333333333,0.058098442873152106,0.49469111969111973,0.04930274686895808 +flat_mae,patch,logistic,adhd200_dx,77,0.005994842503189409,train,0.7397260273972602,0.02163381491629745,0.7279303878414111,0.023170758562364304,0.7249343591622397,0.02257543048493343 +flat_mae,patch,logistic,adhd200_dx,77,0.005994842503189409,test,0.7076923076923077,0.04890956755908365,0.677124183006536,0.05873718213386517,0.678088803088803,0.05229187212019357 +flat_mae,patch,logistic,adhd200_dx,78,0.046415888336127774,train,0.8273972602739726,0.019279141949731148,0.8222691121571173,0.020101269271915283,0.8191060633815718,0.02018272031340908 +flat_mae,patch,logistic,adhd200_dx,78,0.046415888336127774,test,0.5538461538461539,0.05695716235202792,0.5250692869740489,0.061598041509229456,0.5299227799227799,0.05811808181411128 +flat_mae,patch,logistic,adhd200_dx,79,0.005994842503189409,train,0.7452054794520548,0.022107814089097226,0.7354763296317943,0.023461492571614583,0.7326586065824021,0.023074060090292534 +flat_mae,patch,logistic,adhd200_dx,79,0.005994842503189409,test,0.6153846153846154,0.061354339940918594,0.606060606060606,0.06332786489515485,0.6056949806949807,0.06289394688319375 +flat_mae,patch,logistic,adhd200_dx,80,0.005994842503189409,train,0.7479452054794521,0.0214322174238752,0.7380328278100231,0.022754979883023385,0.7350857910484215,0.022386319575315675 +flat_mae,patch,logistic,adhd200_dx,80,0.005994842503189409,test,0.6307692307692307,0.05966521193118231,0.61,0.06452932497771892,0.6105212355212355,0.061761496012970256 +flat_mae,patch,logistic,adhd200_dx,81,0.046415888336127774,train,0.8273972602739726,0.02004791857573663,0.8235348287531943,0.02065982779474093,0.8219759418696952,0.020804928577254467 +flat_mae,patch,logistic,adhd200_dx,81,0.046415888336127774,test,0.5846153846153846,0.05658196337952277,0.5644080416976918,0.060262705198037426,0.5656370656370656,0.057743522763898256 +flat_mae,patch,logistic,adhd200_dx,82,0.005994842503189409,train,0.7342465753424657,0.02237292146629797,0.7222026065328092,0.02397383474174715,0.71936252060817,0.023381861854329274 +flat_mae,patch,logistic,adhd200_dx,82,0.005994842503189409,test,0.676923076923077,0.055897412373554216,0.6690909090909091,0.058040415172690075,0.6684362934362934,0.05760580278578103 +flat_mae,patch,logistic,adhd200_dx,83,0.005994842503189409,train,0.7452054794520548,0.02115742670606868,0.7354763296317943,0.022134061045372553,0.7326586065824021,0.021717482477924984 +flat_mae,patch,logistic,adhd200_dx,83,0.005994842503189409,test,0.6923076923076923,0.05486867376697514,0.6862934362934363,0.05662765474172629,0.6862934362934363,0.056596999274857354 +flat_mae,patch,logistic,adhd200_dx,84,0.005994842503189409,train,0.7315068493150685,0.021898124723168485,0.7203196347031964,0.023249908251464658,0.7176528057641814,0.022712306372639962 +flat_mae,patch,logistic,adhd200_dx,84,0.005994842503189409,test,0.5846153846153846,0.06052622102818466,0.5810455956075435,0.06167932391557653,0.583011583011583,0.062267886685279925 +flat_mae,patch,logistic,adhd200_dx,85,0.000774263682681127,train,0.6602739726027397,0.022990137972307565,0.6332966035779103,0.02605106384931481,0.6358917994748733,0.023998946140233648 +flat_mae,patch,logistic,adhd200_dx,85,0.000774263682681127,test,0.6153846153846154,0.054722538437263234,0.5751633986928104,0.06297949882211273,0.583976833976834,0.05656047716346812 +flat_mae,patch,logistic,adhd200_dx,86,0.005994842503189409,train,0.7452054794520548,0.021855159779953986,0.734283634314163,0.02346451957477766,0.7312236673383403,0.023003824810007335 +flat_mae,patch,logistic,adhd200_dx,86,0.005994842503189409,test,0.5538461538461539,0.06034899684434152,0.5250692869740489,0.06450856987660823,0.5299227799227799,0.061323762752682705 +flat_mae,patch,logistic,adhd200_dx,87,0.005994842503189409,train,0.7397260273972602,0.021572776711975213,0.7285693038693062,0.022877079549593546,0.7256518287842706,0.022378104189863465 +flat_mae,patch,logistic,adhd200_dx,87,0.005994842503189409,test,0.6,0.06075968766353571,0.5775,0.06499308379261727,0.5791505791505791,0.062204520029738274 +flat_mae,patch,logistic,adhd200_dx,88,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adhd200_dx,88,1291.5496650148827,test,0.5076923076923077,0.058273990666211285,0.4980694980694981,0.058863877560438115,0.4980694980694981,0.058475358884207816 +flat_mae,patch,logistic,adhd200_dx,89,0.046415888336127774,train,0.8246575342465754,0.019658040373418454,0.8199531384880996,0.020456413161013428,0.8173963485375833,0.02065150980960782 +flat_mae,patch,logistic,adhd200_dx,89,0.046415888336127774,test,0.5230769230769231,0.06057344116977282,0.5115151515151515,0.06122341375958254,0.5115830115830116,0.060989915198880765 +flat_mae,patch,logistic,adhd200_dx,90,0.005994842503189409,train,0.7424657534246575,0.0220603168445779,0.7317351598173516,0.0235049537276283,0.7287964828723209,0.023021354625120966 +flat_mae,patch,logistic,adhd200_dx,90,0.005994842503189409,test,0.6461538461538462,0.057658377714865164,0.6336682185738789,0.06059572567033411,0.6327220077220077,0.05909260117472834 +flat_mae,patch,logistic,adhd200_dx,91,0.005994842503189409,train,0.7534246575342466,0.02110674974015972,0.7431506849315068,0.02241296476122322,0.7399401599804604,0.02200894943938215 +flat_mae,patch,logistic,adhd200_dx,91,0.005994842503189409,test,0.6153846153846154,0.051256551608943,0.5751633986928104,0.06041092957864183,0.583976833976834,0.05337328896785679 +flat_mae,patch,logistic,adhd200_dx,92,0.005994842503189409,train,0.7315068493150685,0.02117437526259762,0.7190013826043238,0.022710909560839734,0.7162178665201197,0.02211145417352246 +flat_mae,patch,logistic,adhd200_dx,92,0.005994842503189409,test,0.676923076923077,0.058322782703232885,0.656084656084656,0.0634509616543422,0.6554054054054055,0.060265073891928436 +flat_mae,patch,logistic,adhd200_dx,93,0.005994842503189409,train,0.7561643835616438,0.020946627974308633,0.7457122952038764,0.022262218958086243,0.7423673444464798,0.021821213785653566 +flat_mae,patch,logistic,adhd200_dx,93,0.005994842503189409,test,0.6307692307692307,0.05135656535180023,0.587737843551797,0.06082744815889114,0.5974903474903475,0.05352275895378762 +flat_mae,patch,logistic,adhd200_dx,94,0.005994842503189409,train,0.7534246575342466,0.02113982189628659,0.7419400452488687,0.022703347153721087,0.7385052207363986,0.022146742985411957 +flat_mae,patch,logistic,adhd200_dx,94,0.005994842503189409,test,0.6461538461538462,0.050533485295343274,0.6003742314889067,0.06292191560196679,0.6110038610038611,0.05379621221465482 +flat_mae,patch,logistic,adhd200_dx,95,0.005994842503189409,train,0.7643835616438356,0.021911368917102252,0.754566210045662,0.023389923226478173,0.7510838370885998,0.023031289005063744 +flat_mae,patch,logistic,adhd200_dx,95,0.005994842503189409,test,0.5384615384615384,0.059243954576362924,0.5125,0.06331235478283287,0.5164092664092664,0.06017758669267521 +flat_mae,patch,logistic,adhd200_dx,96,0.005994842503189409,train,0.7506849315068493,0.022317463144216673,0.7417205153925708,0.02341091171248029,0.7389479147585027,0.02306756133384911 +flat_mae,patch,logistic,adhd200_dx,96,0.005994842503189409,test,0.6153846153846154,0.06089917168916204,0.6139225469232596,0.061058232863683455,0.6187258687258688,0.06138991448572794 +flat_mae,patch,logistic,adhd200_dx,97,0.046415888336127774,train,0.8438356164383561,0.020297908121841637,0.839195863380249,0.021193863405571965,0.835821579043781,0.02128989647256299 +flat_mae,patch,logistic,adhd200_dx,97,0.046415888336127774,test,0.5692307692307692,0.061014818260298684,0.545,0.06451619755514218,0.5477799227799228,0.06189684440066301 +flat_mae,patch,logistic,adhd200_dx,98,0.005994842503189409,train,0.7150684931506849,0.02252360809792519,0.7010647010647011,0.02414405705031291,0.6987848812358796,0.023402858442913302 +flat_mae,patch,logistic,adhd200_dx,98,0.005994842503189409,test,0.6615384615384615,0.05906583229227113,0.6425000000000001,0.06369425834463806,0.6418918918918919,0.06064839218802852 +flat_mae,patch,logistic,adhd200_dx,99,0.000774263682681127,train,0.7123287671232876,0.023496648807020182,0.7026049709394813,0.02476669059270281,0.7006625145020455,0.0244899088422068 +flat_mae,patch,logistic,adhd200_dx,99,0.000774263682681127,test,0.5076923076923077,0.060057337494949334,0.4871794871794872,0.06267505726272306,0.48938223938223935,0.06075881843060992 +flat_mae,patch,logistic,adhd200_dx,100,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adhd200_dx,100,2.782559402207126,test,0.5692307692307692,0.05956957247200152,0.5608108108108107,0.06083623700020178,0.5608108108108107,0.06067518057945242 diff --git a/input_space_v3/flat_lr1e-3_2/eval_v2/adhd200_dx__patch__logistic/log.txt b/input_space_v3/flat_lr1e-3_2/eval_v2/adhd200_dx__patch__logistic/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..dd608b3936b644496840d3e033ad8186e8869f4e --- /dev/null +++ b/input_space_v3/flat_lr1e-3_2/eval_v2/adhd200_dx__patch__logistic/log.txt @@ -0,0 +1,241 @@ +fMRI foundation model logistic probe eval +version: 0.1.dev86+gf97f52698 +sha: bcce2b486277d3a5b520775efd9cdf1a2affce36, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-04-08 22:03:44 +config: +output_root: experiments/input_space_v3/output +name_prefix: eval_logistic +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_2; eval v2 (adhd200_dx patch logistic) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: input_space_v3/flat_lr1e-3_2/eval_v2/adhd200_dx__patch__logistic +model: flat_mae +representation: patch +dataset: adhd200_dx +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/eval_v2/adhd200_dx__patch__logistic +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=True, reg_tokens=0, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: adhd200_dx (flat) +train (n=301): +HFDataset( + dataset=Dataset({ + features: ['sub', 'site', 'gender', 'dx', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 301 +}), + labels=['ADHD' 'Control'], + counts=[131 170] +) + +validation (n=64): +HFDataset( + dataset=Dataset({ + features: ['sub', 'site', 'gender', 'dx', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 64 +}), + labels=['ADHD' 'Control'], + counts=[28 36] +) + +test (n=65): +HFDataset( + dataset=Dataset({ + features: ['sub', 'site', 'gender', 'dx', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 65 +}), + labels=['ADHD' 'Control'], + counts=[28 37] +) + +extracting features for all splits +extract (train) [ 0/151] eta: 0:14:29 time: 5.7579 data: 4.5980 max mem: 2698 +extract (train) [ 20/151] eta: 0:01:06 time: 0.2433 data: 0.0877 max mem: 2851 +extract (train) [ 40/151] eta: 0:00:40 time: 0.2160 data: 0.0758 max mem: 2851 +extract (train) [ 60/151] eta: 0:00:27 time: 0.1892 data: 0.0621 max mem: 2851 +extract (train) [ 80/151] eta: 0:00:19 time: 0.1746 data: 0.0561 max mem: 2851 +extract (train) [100/151] eta: 0:00:12 time: 0.1742 data: 0.0546 max mem: 2851 +extract (train) [120/151] eta: 0:00:07 time: 0.2142 data: 0.0729 max mem: 2851 +extract (train) [140/151] eta: 0:00:02 time: 0.1912 data: 0.0678 max mem: 2851 +extract (train) [150/151] eta: 0:00:00 time: 0.1685 data: 0.0554 max mem: 2851 +extract (train) Total time: 0:00:35 (0.2371 s / it) +extract (validation) [ 0/32] eta: 0:02:04 time: 3.8762 data: 3.7249 max mem: 2851 +extract (validation) [20/32] eta: 0:00:04 time: 0.2282 data: 0.0851 max mem: 2851 +extract (validation) [31/32] eta: 0:00:00 time: 0.1814 data: 0.0607 max mem: 2851 +extract (validation) Total time: 0:00:10 (0.3407 s / it) +extract (test) [ 0/33] eta: 0:02:09 time: 3.9176 data: 3.6960 max mem: 2851 +extract (test) [20/33] eta: 0:00:04 time: 0.2051 data: 0.0735 max mem: 2851 +extract (test) [32/33] eta: 0:00:00 time: 0.1564 data: 0.0499 max mem: 2851 +extract (test) Total time: 0:00:10 (0.3143 s / it) +feature extraction time: 0:00:57 +train features: (301, 768) +validation features: (64, 768) +test features: (65, 768) +evaluating fixed splits +eval results (fixed splits): + +| model | repr | clf | dataset | trial | C | split | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:-----------|:--------|----------:|:--------|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | adhd200_dx | | 0.0059948 | train | 0.75342 | 0.021775 | 0.74131 | 0.023344 | 0.73779 | 0.022683 | +| flat_mae | patch | logistic | adhd200_dx | | 0.0059948 | test | 0.63077 | 0.059098 | 0.61 | 0.064056 | 0.61052 | 0.0613 | + + +evaluating random splits (n=100) +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 1, "C": 0.005994842503189409, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.05894250734060804, "f1": 0.6153846153846154, "f1_std": 0.061603974574624375, "bacc": 0.6148648648648649, "bacc_std": 0.06021561682277206} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 2, "C": 0.005994842503189409, "split": "test", "acc": 0.6615384615384615, "acc_std": 0.05408022968334686, "f1": 0.6366869918699187, "f1_std": 0.05969321755407053, "bacc": 0.6375482625482626, "bacc_std": 0.05588518590094086} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 3, "C": 0.005994842503189409, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.05894918080143068, "f1": 0.5699583435432491, "f1_std": 0.061629831029543114, "bacc": 0.5699806949806949, "bacc_std": 0.060299441986599596} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 4, "C": 0.005994842503189409, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.058965889246873536, "f1": 0.606060606060606, "f1_std": 0.06106753965820011, "bacc": 0.6056949806949807, "bacc_std": 0.0604302455925058} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 5, "C": 0.005994842503189409, "split": "test", "acc": 0.5230769230769231, "acc_std": 0.062289448421184335, "f1": 0.5189782764382908, "f1_std": 0.0629660314164797, "bacc": 0.5202702702702703, "bacc_std": 0.06365376187269381} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 6, "C": 0.005994842503189409, "split": "test", "acc": 0.6461538461538462, "acc_std": 0.058195540608757666, "f1": 0.6289401836684041, "f1_std": 0.06253118357978447, "bacc": 0.6283783783783784, "bacc_std": 0.05997326096916544} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 7, "C": 0.005994842503189409, "split": "test", "acc": 0.6615384615384615, "acc_std": 0.05473751026111618, "f1": 0.6474358974358974, "f1_std": 0.05793048083082731, "bacc": 0.6462355212355213, "bacc_std": 0.056518194715923294} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 8, "C": 0.005994842503189409, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.06082428664730764, "f1": 0.5905769715293525, "f1_std": 0.06678012138586842, "bacc": 0.5926640926640927, "bacc_std": 0.06258889817433187} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 9, "C": 0.005994842503189409, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.061250487741084235, "f1": 0.5512820512820513, "f1_std": 0.06427367783625362, "bacc": 0.5521235521235521, "bacc_std": 0.062391303932445435} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 10, "C": 0.005994842503189409, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.05807225860025517, "f1": 0.5192307692307693, "f1_std": 0.06049564307801839, "bacc": 0.5207528957528957, "bacc_std": 0.05888729549029609} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 11, "C": 0.005994842503189409, "split": "test", "acc": 0.5230769230769231, "acc_std": 0.06047728117617009, "f1": 0.4923154446963971, "f1_std": 0.06387574247309044, "bacc": 0.4985521235521235, "bacc_std": 0.06092600840259674} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 12, "C": 0.005994842503189409, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.0570011938004333, "f1": 0.5644080416976918, "f1_std": 0.06198901346314867, "bacc": 0.5656370656370656, "bacc_std": 0.05903868831409257} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 13, "C": 0.005994842503189409, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.05837645630635329, "f1": 0.6198830409356726, "f1_std": 0.06020869626809582, "bacc": 0.6192084942084942, "bacc_std": 0.059438170571788095} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 14, "C": 0.000774263682681127, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.06060381771714956, "f1": 0.5644080416976918, "f1_std": 0.06405068894389736, "bacc": 0.5656370656370656, "bacc_std": 0.06180517511227803} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 15, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.05889687306474542, "f1": 0.599146110056926, "f1_std": 0.05890847049780926, "bacc": 0.6052123552123552, "bacc_std": 0.05910914783705134} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 16, "C": 0.005994842503189409, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.062264182339181684, "f1": 0.578226387887527, "f1_std": 0.06308873927466953, "bacc": 0.5786679536679536, "bacc_std": 0.06319487123244827} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 17, "C": 0.005994842503189409, "split": "test", "acc": 0.5538461538461539, "acc_std": 0.05728298693081547, "f1": 0.5167905665214048, "f1_std": 0.06341598226193546, "bacc": 0.5255791505791506, "bacc_std": 0.05860371717089946} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 18, "C": 0.005994842503189409, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.06039061018748335, "f1": 0.6235521235521235, "f1_std": 0.061506940769785357, "bacc": 0.6235521235521235, "bacc_std": 0.06117754172597732} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 19, "C": 0.005994842503189409, "split": "test", "acc": 0.7230769230769231, "acc_std": 0.05704970530808766, "f1": 0.7075, "f1_std": 0.061867771549056545, "bacc": 0.7046332046332047, "bacc_std": 0.059577119481288715} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 20, "C": 0.046415888336127774, "split": "test", "acc": 0.6, "acc_std": 0.05584343286441872, "f1": 0.5833333333333333, "f1_std": 0.05939518106483849, "bacc": 0.5834942084942085, "bacc_std": 0.05754575150529048} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 21, "C": 0.005994842503189409, "split": "test", "acc": 0.6615384615384615, "acc_std": 0.05912126540990678, "f1": 0.6575670498084292, "f1_std": 0.05970301337656005, "bacc": 0.6592664092664093, "bacc_std": 0.059881181016699085} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 22, "C": 0.005994842503189409, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.061056970195608753, "f1": 0.578226387887527, "f1_std": 0.06235933400563895, "bacc": 0.5786679536679536, "bacc_std": 0.062420509064024694} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 23, "C": 0.005994842503189409, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.05144463560512776, "f1": 0.5751633986928104, "f1_std": 0.06014826755001408, "bacc": 0.583976833976834, "bacc_std": 0.053668820095225486} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 24, "C": 0.005994842503189409, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.056974147568210794, "f1": 0.5501153550371699, "f1_std": 0.06349020861166332, "bacc": 0.556949806949807, "bacc_std": 0.05827987583466787} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 25, "C": 0.000774263682681127, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.05349738477266709, "f1": 0.5751633986928104, "f1_std": 0.06185897132333864, "bacc": 0.583976833976834, "bacc_std": 0.05539811962744256} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 26, "C": 0.3593813663804626, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.06119265145191844, "f1": 0.5810455956075435, "f1_std": 0.06153964511728402, "bacc": 0.583011583011583, "bacc_std": 0.06170853629571692} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 27, "C": 0.005994842503189409, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.05757741174449635, "f1": 0.606060606060606, "f1_std": 0.05885276147833077, "bacc": 0.6056949806949807, "bacc_std": 0.05803047228270683} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 28, "C": 0.046415888336127774, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.05664734883626518, "f1": 0.5512820512820513, "f1_std": 0.05885866272963064, "bacc": 0.5521235521235521, "bacc_std": 0.057365803430973646} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 29, "C": 0.3593813663804626, "split": "test", "acc": 0.5076923076923077, "acc_std": 0.06070396495243737, "f1": 0.5047619047619047, "f1_std": 0.061250041522727554, "bacc": 0.5067567567567568, "bacc_std": 0.06145650089676941} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 30, "C": 0.005994842503189409, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.059290032290378145, "f1": 0.5699583435432491, "f1_std": 0.06178904549839272, "bacc": 0.5699806949806949, "bacc_std": 0.06044961320880358} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 31, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.058537109051392984, "f1": 0.5775, "f1_std": 0.06365588266787665, "bacc": 0.5791505791505791, "bacc_std": 0.06054490047232745} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 32, "C": 2.782559402207126, "split": "test", "acc": 0.5538461538461539, "acc_std": 0.060355483418644114, "f1": 0.5469838981014179, "f1_std": 0.061088827618924584, "bacc": 0.5472972972972974, "bacc_std": 0.06120753335672655} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 33, "C": 0.046415888336127774, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.06012669857606357, "f1": 0.5810455956075435, "f1_std": 0.06078300300090024, "bacc": 0.583011583011583, "bacc_std": 0.06123524531523332} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 34, "C": 0.046415888336127774, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.06133162162091336, "f1": 0.5830363506771205, "f1_std": 0.06197959950036834, "bacc": 0.5873552123552124, "bacc_std": 0.06267626955224453} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 35, "C": 0.005994842503189409, "split": "test", "acc": 0.5230769230769231, "acc_std": 0.057014678894714954, "f1": 0.4923154446963971, "f1_std": 0.0608245198098326, "bacc": 0.4985521235521235, "bacc_std": 0.05760879708376629} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 36, "C": 0.000774263682681127, "split": "test", "acc": 0.5230769230769231, "acc_std": 0.05560244343530534, "f1": 0.4923154446963971, "f1_std": 0.05952932449781949, "bacc": 0.4985521235521235, "bacc_std": 0.0562998671589309} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 37, "C": 0.000774263682681127, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.048326463770813156, "f1": 0.5656241646618552, "f1_std": 0.060577168715194606, "bacc": 0.5796332046332047, "bacc_std": 0.051047202560797644} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 38, "C": 0.005994842503189409, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.05815155876657347, "f1": 0.5248538011695907, "f1_std": 0.05989667755854438, "bacc": 0.525096525096525, "bacc_std": 0.05872059650388699} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 39, "C": 0.005994842503189409, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.05786921798791258, "f1": 0.61, "f1_std": 0.06224133442202154, "bacc": 0.6105212355212355, "bacc_std": 0.05941162162010358} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 40, "C": 0.000774263682681127, "split": "test", "acc": 0.6615384615384615, "acc_std": 0.048211604584042285, "f1": 0.6130952380952381, "f1_std": 0.06007641908921364, "bacc": 0.6245173745173745, "bacc_std": 0.05100462526170923} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 41, "C": 0.005994842503189409, "split": "test", "acc": 0.6461538461538462, "acc_std": 0.05597371318795402, "f1": 0.6289401836684041, "f1_std": 0.059686489002563105, "bacc": 0.6283783783783784, "bacc_std": 0.057572793377780034} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 42, "C": 0.046415888336127774, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.06315605542842355, "f1": 0.5608108108108107, "f1_std": 0.06353841110614689, "bacc": 0.5608108108108107, "bacc_std": 0.06313109393233973} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 43, "C": 0.005994842503189409, "split": "test", "acc": 0.6461538461538462, "acc_std": 0.06240652370692852, "f1": 0.6407113674597452, "f1_std": 0.0629750619025757, "bacc": 0.6414092664092663, "bacc_std": 0.06284490731781295} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 44, "C": 0.3593813663804626, "split": "test", "acc": 0.676923076923077, "acc_std": 0.0547599300659561, "f1": 0.6612062546537603, "f1_std": 0.05916536798016416, "bacc": 0.6597490347490347, "bacc_std": 0.05691862080474488} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 45, "C": 0.046415888336127774, "split": "test", "acc": 0.47692307692307695, "acc_std": 0.061365572523396694, "f1": 0.4666988416988417, "f1_std": 0.062556501737144, "bacc": 0.4666988416988417, "bacc_std": 0.06201304402500115} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 46, "C": 0.3593813663804626, "split": "test", "acc": 0.6, "acc_std": 0.05639676855067655, "f1": 0.599905303030303, "f1_std": 0.056491723085260584, "bacc": 0.6095559845559846, "bacc_std": 0.056457784057814674} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 47, "C": 0.005994842503189409, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.05665833654981159, "f1": 0.5376016260162602, "f1_std": 0.06119665957552759, "bacc": 0.5434362934362934, "bacc_std": 0.057363646967686005} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 48, "C": 0.046415888336127774, "split": "test", "acc": 0.6923076923076923, "acc_std": 0.054970167272265315, "f1": 0.6904761904761905, "f1_std": 0.055486948035640145, "bacc": 0.6949806949806949, "bacc_std": 0.055714538364641186} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 49, "C": 0.005994842503189409, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.060494029242269, "f1": 0.5565302144249512, "f1_std": 0.06263942839932318, "bacc": 0.5564671814671815, "bacc_std": 0.061605363608883495} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 50, "C": 0.046415888336127774, "split": "test", "acc": 0.6615384615384615, "acc_std": 0.05866332785908893, "f1": 0.6515594541910331, "f1_std": 0.060761411796487905, "bacc": 0.6505791505791505, "bacc_std": 0.060007433524804046} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 51, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.059402141694301074, "f1": 0.5953065134099617, "f1_std": 0.06019669395954965, "bacc": 0.5965250965250966, "bacc_std": 0.06057435794005852} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 52, "C": 21.54434690031882, "split": "test", "acc": 0.5538461538461539, "acc_std": 0.06067068153262444, "f1": 0.5381034060279344, "f1_std": 0.06227076379630303, "bacc": 0.5386100386100386, "bacc_std": 0.06103541025983018} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 53, "C": 0.046415888336127774, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.059846936913998915, "f1": 0.5578231292517006, "f1_std": 0.06485177547968979, "bacc": 0.5612934362934363, "bacc_std": 0.061374970631221513} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 54, "C": 0.000774263682681127, "split": "test", "acc": 0.49230769230769234, "acc_std": 0.061449165982948854, "f1": 0.48000000000000004, "f1_std": 0.06322073269872715, "bacc": 0.48021235521235517, "bacc_std": 0.062390273345522204} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 55, "C": 0.005994842503189409, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.06010687916600664, "f1": 0.578226387887527, "f1_std": 0.06073980886754974, "bacc": 0.5786679536679536, "bacc_std": 0.06078583819527776} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 56, "C": 0.005994842503189409, "split": "test", "acc": 0.6461538461538462, "acc_std": 0.06112552997071832, "f1": 0.6407113674597452, "f1_std": 0.062384316205707085, "bacc": 0.6414092664092663, "bacc_std": 0.06245842620068136} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 57, "C": 0.046415888336127774, "split": "test", "acc": 0.5076923076923077, "acc_std": 0.06083860499705893, "f1": 0.48, "f1_std": 0.06338333171181566, "bacc": 0.48503861003861004, "bacc_std": 0.06106514003504446} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 58, "C": 0.005994842503189409, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.05962783988994427, "f1": 0.6235521235521235, "f1_std": 0.060761126416081467, "bacc": 0.6235521235521235, "bacc_std": 0.06030415097305269} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 59, "C": 0.046415888336127774, "split": "test", "acc": 0.6, "acc_std": 0.06083984991169938, "f1": 0.5833333333333333, "f1_std": 0.06365456070958665, "bacc": 0.5834942084942085, "bacc_std": 0.06187489303401872} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 60, "C": 0.005994842503189409, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.058383194469382234, "f1": 0.61, "f1_std": 0.06315728954702812, "bacc": 0.6105212355212355, "bacc_std": 0.06017631288936422} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 61, "C": 0.046415888336127774, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.05732064902575448, "f1": 0.6153846153846154, "f1_std": 0.06070649167713494, "bacc": 0.6148648648648649, "bacc_std": 0.05925127989546392} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 62, "C": 0.005994842503189409, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.06108110041905243, "f1": 0.5810455956075435, "f1_std": 0.06141636019138602, "bacc": 0.583011583011583, "bacc_std": 0.06155607461492958} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 63, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.056501046751575044, "f1": 0.5775, "f1_std": 0.06018250042000316, "bacc": 0.5791505791505791, "bacc_std": 0.05774833276460005} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 64, "C": 0.046415888336127774, "split": "test", "acc": 0.6461538461538462, "acc_std": 0.059002027846005674, "f1": 0.6233308138070043, "f1_std": 0.06394371584928607, "bacc": 0.6240347490347491, "bacc_std": 0.06073228845923562} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 65, "C": 0.005994842503189409, "split": "test", "acc": 0.7384615384615385, "acc_std": 0.0522936723292644, "f1": 0.7257383966244726, "f1_std": 0.05668058842990602, "bacc": 0.7224903474903475, "bacc_std": 0.054996775716552405} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 66, "C": 1291.5496650148827, "split": "test", "acc": 0.5076923076923077, "acc_std": 0.05643425037496834, "f1": 0.4715447154471545, "f1_std": 0.05981134791200525, "bacc": 0.4806949806949807, "bacc_std": 0.05637187134242317} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 67, "C": 0.005994842503189409, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.053708448091987396, "f1": 0.5962732919254659, "f1_std": 0.06287446368471691, "bacc": 0.6018339768339769, "bacc_std": 0.05637455125514001} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 68, "C": 0.005994842503189409, "split": "test", "acc": 0.676923076923077, "acc_std": 0.05523291189329979, "f1": 0.6612062546537603, "f1_std": 0.058941970775107086, "bacc": 0.6597490347490347, "bacc_std": 0.05705042759308765} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 69, "C": 0.005994842503189409, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.062059112877354765, "f1": 0.5192307692307693, "f1_std": 0.06491752908889238, "bacc": 0.5207528957528957, "bacc_std": 0.06298623886438025} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 70, "C": 0.005994842503189409, "split": "test", "acc": 0.49230769230769234, "acc_std": 0.06271868251242746, "f1": 0.48000000000000004, "f1_std": 0.06443351625939978, "bacc": 0.48021235521235517, "bacc_std": 0.06363040302445853} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 71, "C": 0.046415888336127774, "split": "test", "acc": 0.6461538461538462, "acc_std": 0.057800669515583505, "f1": 0.6375757575757576, "f1_std": 0.059627678482444164, "bacc": 0.6370656370656371, "bacc_std": 0.059171391075938294} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 72, "C": 0.005994842503189409, "split": "test", "acc": 0.6923076923076923, "acc_std": 0.0533469962775255, "f1": 0.6697154471544715, "f1_std": 0.06010857336653079, "bacc": 0.6689189189189189, "bacc_std": 0.056163480756742795} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 73, "C": 0.000774263682681127, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.06058988921062831, "f1": 0.5644080416976918, "f1_std": 0.06387605978526852, "bacc": 0.5656370656370656, "bacc_std": 0.06172614473226555} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 74, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.06135742602008864, "f1": 0.588206627680312, "f1_std": 0.06332619318976772, "bacc": 0.5878378378378378, "bacc_std": 0.06202216707741433} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 75, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.06136229399444219, "f1": 0.588206627680312, "f1_std": 0.06340325109637322, "bacc": 0.5878378378378378, "bacc_std": 0.06252046816793909} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 76, "C": 0.005994842503189409, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.04912426942106972, "f1": 0.4583333333333333, "f1_std": 0.058098442873152106, "bacc": 0.49469111969111973, "bacc_std": 0.04930274686895808} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 77, "C": 0.005994842503189409, "split": "test", "acc": 0.7076923076923077, "acc_std": 0.04890956755908365, "f1": 0.677124183006536, "f1_std": 0.05873718213386517, "bacc": 0.678088803088803, "bacc_std": 0.05229187212019357} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 78, "C": 0.046415888336127774, "split": "test", "acc": 0.5538461538461539, "acc_std": 0.05695716235202792, "f1": 0.5250692869740489, "f1_std": 0.061598041509229456, "bacc": 0.5299227799227799, "bacc_std": 0.05811808181411128} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 79, "C": 0.005994842503189409, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.061354339940918594, "f1": 0.606060606060606, "f1_std": 0.06332786489515485, "bacc": 0.6056949806949807, "bacc_std": 0.06289394688319375} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 80, "C": 0.005994842503189409, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.05966521193118231, "f1": 0.61, "f1_std": 0.06452932497771892, "bacc": 0.6105212355212355, "bacc_std": 0.061761496012970256} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 81, "C": 0.046415888336127774, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.05658196337952277, "f1": 0.5644080416976918, "f1_std": 0.060262705198037426, "bacc": 0.5656370656370656, "bacc_std": 0.057743522763898256} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 82, "C": 0.005994842503189409, "split": "test", "acc": 0.676923076923077, "acc_std": 0.055897412373554216, "f1": 0.6690909090909091, "f1_std": 0.058040415172690075, "bacc": 0.6684362934362934, "bacc_std": 0.05760580278578103} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 83, "C": 0.005994842503189409, "split": "test", "acc": 0.6923076923076923, "acc_std": 0.05486867376697514, "f1": 0.6862934362934363, "f1_std": 0.05662765474172629, "bacc": 0.6862934362934363, "bacc_std": 0.056596999274857354} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 84, "C": 0.005994842503189409, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.06052622102818466, "f1": 0.5810455956075435, "f1_std": 0.06167932391557653, "bacc": 0.583011583011583, "bacc_std": 0.062267886685279925} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 85, "C": 0.000774263682681127, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.054722538437263234, "f1": 0.5751633986928104, "f1_std": 0.06297949882211273, "bacc": 0.583976833976834, "bacc_std": 0.05656047716346812} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 86, "C": 0.005994842503189409, "split": "test", "acc": 0.5538461538461539, "acc_std": 0.06034899684434152, "f1": 0.5250692869740489, "f1_std": 0.06450856987660823, "bacc": 0.5299227799227799, "bacc_std": 0.061323762752682705} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 87, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.06075968766353571, "f1": 0.5775, "f1_std": 0.06499308379261727, "bacc": 0.5791505791505791, "bacc_std": 0.062204520029738274} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 88, "C": 1291.5496650148827, "split": "test", "acc": 0.5076923076923077, "acc_std": 0.058273990666211285, "f1": 0.4980694980694981, "f1_std": 0.058863877560438115, "bacc": 0.4980694980694981, "bacc_std": 0.058475358884207816} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 89, "C": 0.046415888336127774, "split": "test", "acc": 0.5230769230769231, "acc_std": 0.06057344116977282, "f1": 0.5115151515151515, "f1_std": 0.06122341375958254, "bacc": 0.5115830115830116, "bacc_std": 0.060989915198880765} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 90, "C": 0.005994842503189409, "split": "test", "acc": 0.6461538461538462, "acc_std": 0.057658377714865164, "f1": 0.6336682185738789, "f1_std": 0.06059572567033411, "bacc": 0.6327220077220077, "bacc_std": 0.05909260117472834} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 91, "C": 0.005994842503189409, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.051256551608943, "f1": 0.5751633986928104, "f1_std": 0.06041092957864183, "bacc": 0.583976833976834, "bacc_std": 0.05337328896785679} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 92, "C": 0.005994842503189409, "split": "test", "acc": 0.676923076923077, "acc_std": 0.058322782703232885, "f1": 0.656084656084656, "f1_std": 0.0634509616543422, "bacc": 0.6554054054054055, "bacc_std": 0.060265073891928436} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 93, "C": 0.005994842503189409, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.05135656535180023, "f1": 0.587737843551797, "f1_std": 0.06082744815889114, "bacc": 0.5974903474903475, "bacc_std": 0.05352275895378762} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 94, "C": 0.005994842503189409, "split": "test", "acc": 0.6461538461538462, "acc_std": 0.050533485295343274, "f1": 0.6003742314889067, "f1_std": 0.06292191560196679, "bacc": 0.6110038610038611, "bacc_std": 0.05379621221465482} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 95, "C": 0.005994842503189409, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.059243954576362924, "f1": 0.5125, "f1_std": 0.06331235478283287, "bacc": 0.5164092664092664, "bacc_std": 0.06017758669267521} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 96, "C": 0.005994842503189409, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.06089917168916204, "f1": 0.6139225469232596, "f1_std": 0.061058232863683455, "bacc": 0.6187258687258688, "bacc_std": 0.06138991448572794} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 97, "C": 0.046415888336127774, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.061014818260298684, "f1": 0.545, "f1_std": 0.06451619755514218, "bacc": 0.5477799227799228, "bacc_std": 0.06189684440066301} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 98, "C": 0.005994842503189409, "split": "test", "acc": 0.6615384615384615, "acc_std": 0.05906583229227113, "f1": 0.6425000000000001, "f1_std": 0.06369425834463806, "bacc": 0.6418918918918919, "bacc_std": 0.06064839218802852} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 99, "C": 0.000774263682681127, "split": "test", "acc": 0.5076923076923077, "acc_std": 0.060057337494949334, "f1": 0.4871794871794872, "f1_std": 0.06267505726272306, "bacc": 0.48938223938223935, "bacc_std": 0.06075881843060992} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 100, "C": 2.782559402207126, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.05956957247200152, "f1": 0.5608108108108107, "f1_std": 0.06083623700020178, "bacc": 0.5608108108108107, "bacc_std": 0.06067518057945242} +eval results (random splits): + +| model | repr | clf | dataset | split | n_trials | C | C_std | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:-----------|:--------|-----------:|-------:|--------:|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | adhd200_dx | train | 100 | 26.129 | 181.7 | 0.77789 | 0.076791 | 0.76851 | 0.081262 | 0.76598 | 0.08123 | +| flat_mae | patch | logistic | adhd200_dx | test | 100 | 26.129 | 181.7 | 0.59969 | 0.054797 | 0.58131 | 0.057184 | 0.58379 | 0.055504 | + + +done! total time: 0:04:56 diff --git a/input_space_v3/flat_lr1e-3_2/eval_v2/adni_ad_vs_cn__patch__logistic/config.yaml b/input_space_v3/flat_lr1e-3_2/eval_v2/adni_ad_vs_cn__patch__logistic/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..86674834225129cfe1e13b3d724a9ec1730a17eb --- /dev/null +++ b/input_space_v3/flat_lr1e-3_2/eval_v2/adni_ad_vs_cn__patch__logistic/config.yaml @@ -0,0 +1,30 @@ +output_root: experiments/input_space_v3/output +name_prefix: eval_logistic +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_2; eval v2 (adni_ad_vs_cn patch logistic) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: input_space_v3/flat_lr1e-3_2/eval_v2/adni_ad_vs_cn__patch__logistic +model: flat_mae +representation: patch +dataset: adni_ad_vs_cn +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/eval_v2/adni_ad_vs_cn__patch__logistic +remote_dir: null diff --git a/input_space_v3/flat_lr1e-3_2/eval_v2/adni_ad_vs_cn__patch__logistic/eval_table.csv b/input_space_v3/flat_lr1e-3_2/eval_v2/adni_ad_vs_cn__patch__logistic/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..08f2430b7471033bd2a5d010ad13f71f4dedfed9 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_2/eval_v2/adni_ad_vs_cn__patch__logistic/eval_table.csv @@ -0,0 +1,203 @@ +model,repr,clf,dataset,trial,C,split,acc,acc_std,f1,f1_std,bacc,bacc_std +flat_mae,patch,logistic,adni_ad_vs_cn,,0.046415888336127774,train,0.8888888888888888,0.014197085783087279,0.8276113535625164,0.024681982974217354,0.7961604304230863,0.026274866633991006 +flat_mae,patch,logistic,adni_ad_vs_cn,,0.046415888336127774,test,0.7317073170731707,0.05400938513195596,0.5512437810945273,0.08514565637586795,0.5486111111111112,0.07381133801000465 +flat_mae,patch,logistic,adni_ad_vs_cn,1,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,1,2.782559402207126,test,0.8048780487804879,0.05178684634051865,0.6893939393939394,0.09320644532173386,0.667741935483871,0.08305399093981082 +flat_mae,patch,logistic,adni_ad_vs_cn,2,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,2,21.54434690031882,test,0.7073170731707317,0.07283531250955178,0.646551724137931,0.08157829392740856,0.6709677419354838,0.09087396052419394 +flat_mae,patch,logistic,adni_ad_vs_cn,3,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,3,166.81005372000556,test,0.7560975609756098,0.06674154826881275,0.6693548387096775,0.0880974734690822,0.6693548387096775,0.08826519000664683 +flat_mae,patch,logistic,adni_ad_vs_cn,4,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,4,166.81005372000556,test,0.7804878048780488,0.06119358113721882,0.6917293233082706,0.08761366377076861,0.685483870967742,0.08615443022894946 +flat_mae,patch,logistic,adni_ad_vs_cn,5,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,5,166.81005372000556,test,0.6585365853658537,0.05058917595077964,0.4564393939393939,0.0650144571686218,0.4693548387096774,0.05524387856248356 +flat_mae,patch,logistic,adni_ad_vs_cn,6,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,6,166.81005372000556,test,0.7317073170731707,0.057254246833643746,0.5918552036199095,0.08958757228271201,0.5854838709677419,0.07883446077722216 +flat_mae,patch,logistic,adni_ad_vs_cn,7,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,7,2.782559402207126,test,0.7560975609756098,0.06113002885911701,0.6693548387096775,0.08293258442932223,0.6693548387096775,0.08595482103468714 +flat_mae,patch,logistic,adni_ad_vs_cn,8,0.3593813663804626,train,0.994579945799458,0.0036882622563761728,0.9923570836785418,0.0052682130988369715,0.9883720930232558,0.007912609143039607 +flat_mae,patch,logistic,adni_ad_vs_cn,8,0.3593813663804626,test,0.7073170731707317,0.061457432926115094,0.5729166666666666,0.08802793630094904,0.5693548387096774,0.0831612713030835 +flat_mae,patch,logistic,adni_ad_vs_cn,9,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,9,166.81005372000556,test,0.6341463414634146,0.06973861285217899,0.5199063231850116,0.07974438421127795,0.5209677419354839,0.08139234739433457 +flat_mae,patch,logistic,adni_ad_vs_cn,10,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,10,1291.5496650148827,test,0.6341463414634146,0.06791890745066566,0.5199063231850116,0.08086664425463178,0.5209677419354839,0.08314038777323743 +flat_mae,patch,logistic,adni_ad_vs_cn,11,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,11,21.54434690031882,test,0.7804878048780488,0.0476557904194202,0.6328358208955224,0.08925218579972471,0.6177419354838709,0.07301188954251327 +flat_mae,patch,logistic,adni_ad_vs_cn,12,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,12,166.81005372000556,test,0.6829268292682927,0.06723025507981038,0.5839188134270101,0.0840445814475537,0.5870967741935484,0.08638403346853771 +flat_mae,patch,logistic,adni_ad_vs_cn,13,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,13,2.782559402207126,test,0.8048780487804879,0.054395712292095465,0.7152777777777778,0.08793733405871604,0.7016129032258065,0.08585259946295944 +flat_mae,patch,logistic,adni_ad_vs_cn,14,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,14,2.782559402207126,test,0.7317073170731707,0.06875585097594628,0.6479313036690086,0.08915072476076948,0.6532258064516129,0.09108943564519568 +flat_mae,patch,logistic,adni_ad_vs_cn,15,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,15,2.782559402207126,test,0.7560975609756098,0.056580655817430374,0.6440972222222222,0.08651186652710242,0.635483870967742,0.08133782399906715 +flat_mae,patch,logistic,adni_ad_vs_cn,16,0.046415888336127774,train,0.8970189701897019,0.01406376547002278,0.8410204081632653,0.023746348644424545,0.8114471197304627,0.025680178085350513 +flat_mae,patch,logistic,adni_ad_vs_cn,16,0.046415888336127774,test,0.7804878048780488,0.03891068801601732,0.5886287625418061,0.09127597999335721,0.5838709677419355,0.0646823342996173 +flat_mae,patch,logistic,adni_ad_vs_cn,17,0.3593813663804626,train,0.986449864498645,0.006253368595954139,0.9806516564069758,0.009167531178640612,0.9709302325581395,0.013415657045971393 +flat_mae,patch,logistic,adni_ad_vs_cn,17,0.3593813663804626,test,0.7073170731707317,0.06261028342628557,0.5729166666666666,0.08991439854789625,0.5693548387096774,0.08210795512936304 +flat_mae,patch,logistic,adni_ad_vs_cn,18,0.005994842503189409,train,0.8157181571815718,0.013808272879289839,0.6661166702150308,0.031358311345441404,0.6410756841153751,0.025401603034894252 +flat_mae,patch,logistic,adni_ad_vs_cn,18,0.005994842503189409,test,0.8292682926829268,0.03574528169693307,0.6800445930880714,0.09742890175980444,0.65,0.07327782747871281 +flat_mae,patch,logistic,adni_ad_vs_cn,19,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,19,2.782559402207126,test,0.7560975609756098,0.06737184057040553,0.6693548387096775,0.08602365505908995,0.6693548387096775,0.08680596006861464 +flat_mae,patch,logistic,adni_ad_vs_cn,20,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,20,166.81005372000556,test,0.7073170731707317,0.0696024232553868,0.6272727272727273,0.08256111445458664,0.6370967741935484,0.08773578583762309 +flat_mae,patch,logistic,adni_ad_vs_cn,21,0.046415888336127774,train,0.8943089430894309,0.014348921731283779,0.8343520149176422,0.02506057528486259,0.8015859972060153,0.027045138334223087 +flat_mae,patch,logistic,adni_ad_vs_cn,21,0.046415888336127774,test,0.8048780487804879,0.050387646616887556,0.6893939393939394,0.095460422597811,0.667741935483871,0.08324381719345002 +flat_mae,patch,logistic,adni_ad_vs_cn,22,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,22,166.81005372000556,test,0.7560975609756098,0.0481623271457844,0.569327731092437,0.09395594959454302,0.567741935483871,0.07084989768574945 +flat_mae,patch,logistic,adni_ad_vs_cn,23,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,23,166.81005372000556,test,0.5853658536585366,0.062420424058786735,0.4177109440267335,0.06322721240913064,0.42096774193548386,0.06364695246241049 +flat_mae,patch,logistic,adni_ad_vs_cn,24,0.046415888336127774,train,0.8888888888888888,0.014936084182392166,0.832578985226581,0.024190793273874633,0.8101939354096475,0.02645033127776132 +flat_mae,patch,logistic,adni_ad_vs_cn,24,0.046415888336127774,test,0.7560975609756098,0.04552251993832065,0.569327731092437,0.08952695603708932,0.567741935483871,0.06694085481755126 +flat_mae,patch,logistic,adni_ad_vs_cn,25,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,25,1291.5496650148827,test,0.7560975609756098,0.06168899756988981,0.6693548387096775,0.08254351036279158,0.6693548387096775,0.08378794023127546 +flat_mae,patch,logistic,adni_ad_vs_cn,26,0.046415888336127774,train,0.8943089430894309,0.014173772322778,0.8360205558277596,0.02423642553499523,0.8056331662420906,0.026237050483546232 +flat_mae,patch,logistic,adni_ad_vs_cn,26,0.046415888336127774,test,0.6585365853658537,0.05963384208611096,0.4564393939393939,0.0703399889234458,0.4693548387096774,0.062170984646745704 +flat_mae,patch,logistic,adni_ad_vs_cn,27,0.046415888336127774,train,0.8753387533875339,0.014714442962836976,0.805611543747137,0.025283409905323184,0.7770769989317117,0.026218837058962427 +flat_mae,patch,logistic,adni_ad_vs_cn,27,0.046415888336127774,test,0.8048780487804879,0.04093874648437682,0.6554621848739496,0.09155479817665176,0.6338709677419355,0.07211687790721591 +flat_mae,patch,logistic,adni_ad_vs_cn,28,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,28,166.81005372000556,test,0.7560975609756098,0.06403419669381732,0.6693548387096775,0.08586836265517012,0.6693548387096775,0.08701149349367587 +flat_mae,patch,logistic,adni_ad_vs_cn,29,0.3593813663804626,train,0.986449864498645,0.006190306996085256,0.9808134274809954,0.008901177957658055,0.9749774015942148,0.012053598615777669 +flat_mae,patch,logistic,adni_ad_vs_cn,29,0.3593813663804626,test,0.7317073170731707,0.06868311737778446,0.6676492262343405,0.08083257703074967,0.6870967741935483,0.08725215530644011 +flat_mae,patch,logistic,adni_ad_vs_cn,30,0.3593813663804626,train,0.981029810298103,0.006941386199487051,0.9729123189697663,0.010131622827450126,0.9633494946174705,0.013563253639059258 +flat_mae,patch,logistic,adni_ad_vs_cn,30,0.3593813663804626,test,0.7317073170731707,0.06098341413469807,0.6232247284878863,0.0862808996052961,0.6193548387096774,0.0841836337630325 +flat_mae,patch,logistic,adni_ad_vs_cn,31,0.3593813663804626,train,0.983739837398374,0.006304552901211235,0.9768796992481203,0.009116460254055091,0.9691634481058427,0.01221953068939161 +flat_mae,patch,logistic,adni_ad_vs_cn,31,0.3593813663804626,test,0.7317073170731707,0.06392833212143637,0.6479313036690086,0.08126431748773526,0.6532258064516129,0.08456642993410686 +flat_mae,patch,logistic,adni_ad_vs_cn,32,0.3593813663804626,train,0.989159891598916,0.0051732735084179925,0.9848385241186621,0.00722720478777355,0.9848385241186621,0.008151009028526857 +flat_mae,patch,logistic,adni_ad_vs_cn,32,0.3593813663804626,test,0.6341463414634146,0.06827916242467993,0.5199063231850116,0.08228884424874298,0.5209677419354839,0.08469896770370253 +flat_mae,patch,logistic,adni_ad_vs_cn,33,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,33,1291.5496650148827,test,0.6341463414634146,0.0706967785918981,0.5684210526315789,0.07680196118999402,0.5887096774193548,0.08683493353243085 +flat_mae,patch,logistic,adni_ad_vs_cn,34,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,34,166.81005372000556,test,0.7073170731707317,0.07037377898471933,0.6272727272727273,0.08915587208109203,0.6370967741935484,0.09594664853575936 +flat_mae,patch,logistic,adni_ad_vs_cn,35,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,35,21.54434690031882,test,0.7804878048780488,0.04918222378287134,0.6328358208955224,0.09625074018481278,0.6177419354838709,0.07736649028448044 +flat_mae,patch,logistic,adni_ad_vs_cn,36,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,36,1291.5496650148827,test,0.6829268292682927,0.060248365589587065,0.5176470588235295,0.0816020533844962,0.5193548387096775,0.07391979475209241 +flat_mae,patch,logistic,adni_ad_vs_cn,37,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,37,2.782559402207126,test,0.7073170731707317,0.05760469608723577,0.5729166666666666,0.08258333945652464,0.5693548387096774,0.07587763274433709 +flat_mae,patch,logistic,adni_ad_vs_cn,38,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,38,2.782559402207126,test,0.7073170731707317,0.07025176107801683,0.646551724137931,0.0805283832313704,0.6709677419354838,0.08966407280585237 +flat_mae,patch,logistic,adni_ad_vs_cn,39,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,39,2.782559402207126,test,0.6829268292682927,0.06271074641275967,0.5547201336675021,0.08315431414363184,0.5532258064516129,0.08030485618665417 +flat_mae,patch,logistic,adni_ad_vs_cn,40,0.3593813663804626,train,0.991869918699187,0.004662440762144138,0.9884880564885973,0.006709102130027771,0.9825581395348837,0.010002561867623234 +flat_mae,patch,logistic,adni_ad_vs_cn,40,0.3593813663804626,test,0.6829268292682927,0.06772411403373083,0.5839188134270101,0.08436023011862094,0.5870967741935484,0.08805519854997397 +flat_mae,patch,logistic,adni_ad_vs_cn,41,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,41,21.54434690031882,test,0.7560975609756098,0.0638148720449289,0.6693548387096775,0.08605590504785669,0.6693548387096775,0.08768059590960518 +flat_mae,patch,logistic,adni_ad_vs_cn,42,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,42,2.782559402207126,test,0.7804878048780488,0.06147115708106678,0.7119437939110069,0.07679082151132947,0.7193548387096774,0.08152265691211495 +flat_mae,patch,logistic,adni_ad_vs_cn,43,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,43,2.782559402207126,test,0.8780487804878049,0.04489339610323919,0.8144796380090498,0.07585507855434435,0.7838709677419355,0.07826216374924629 +flat_mae,patch,logistic,adni_ad_vs_cn,44,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,44,21.54434690031882,test,0.8536585365853658,0.04632068853971814,0.7670454545454546,0.08766276270469826,0.7338709677419355,0.0838105272916926 +flat_mae,patch,logistic,adni_ad_vs_cn,45,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,45,166.81005372000556,test,0.8292682926829268,0.052763691480107525,0.7402714932126697,0.08904190572576509,0.717741935483871,0.08497621164340845 +flat_mae,patch,logistic,adni_ad_vs_cn,46,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,46,166.81005372000556,test,0.7317073170731707,0.06920799505416272,0.6479313036690086,0.08872900223229896,0.6532258064516129,0.09259589280980303 +flat_mae,patch,logistic,adni_ad_vs_cn,47,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,47,21.54434690031882,test,0.7317073170731707,0.06350498254351755,0.6232247284878863,0.0887257001946197,0.6193548387096774,0.08760106670958777 +flat_mae,patch,logistic,adni_ad_vs_cn,48,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,48,166.81005372000556,test,0.7073170731707317,0.07291754570162196,0.646551724137931,0.08186494791234171,0.6709677419354838,0.08921925640129022 +flat_mae,patch,logistic,adni_ad_vs_cn,49,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,49,21.54434690031882,test,0.6829268292682927,0.060216464572340256,0.5176470588235295,0.08601429169745131,0.5193548387096775,0.07531788166595794 +flat_mae,patch,logistic,adni_ad_vs_cn,50,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,50,166.81005372000556,test,0.7804878048780488,0.05912114625548764,0.6917293233082706,0.08510130150400332,0.685483870967742,0.08356466400171211 +flat_mae,patch,logistic,adni_ad_vs_cn,51,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,51,21.54434690031882,test,0.5365853658536586,0.07755177119797389,0.4533333333333333,0.07640264985917493,0.4564516129032258,0.08600097638774923 +flat_mae,patch,logistic,adni_ad_vs_cn,52,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,52,2.782559402207126,test,0.7073170731707317,0.0700114038471563,0.6272727272727273,0.08524069536490321,0.6370967741935484,0.09108199208404434 +flat_mae,patch,logistic,adni_ad_vs_cn,53,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,53,166.81005372000556,test,0.7317073170731707,0.057547311317360676,0.5918552036199095,0.09149914247272649,0.5854838709677419,0.08158279050483423 +flat_mae,patch,logistic,adni_ad_vs_cn,54,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,54,21.54434690031882,test,0.7560975609756098,0.06597840037378447,0.6893939393939394,0.08158447430596333,0.7032258064516128,0.08819411921376491 +flat_mae,patch,logistic,adni_ad_vs_cn,55,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,55,21.54434690031882,test,0.7073170731707317,0.06899058036040281,0.6272727272727273,0.08408822334251508,0.6370967741935484,0.08984160162137504 +flat_mae,patch,logistic,adni_ad_vs_cn,56,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,56,166.81005372000556,test,0.7073170731707317,0.06497463926617204,0.5729166666666666,0.09123197601496126,0.5693548387096774,0.08546755017662896 +flat_mae,patch,logistic,adni_ad_vs_cn,57,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,57,21.54434690031882,test,0.7317073170731707,0.06779989453523284,0.6479313036690086,0.08855985301528392,0.6532258064516129,0.09209999519817946 +flat_mae,patch,logistic,adni_ad_vs_cn,58,0.046415888336127774,train,0.8861788617886179,0.01497410607165017,0.8242857142857143,0.025211356096134868,0.7962856438491248,0.02661653933911789 +flat_mae,patch,logistic,adni_ad_vs_cn,58,0.046415888336127774,test,0.7804878048780488,0.04945735278196642,0.6328358208955224,0.09320927105681079,0.6177419354838709,0.07612478630860449 +flat_mae,patch,logistic,adni_ad_vs_cn,59,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,59,166.81005372000556,test,0.6829268292682927,0.07424862970111006,0.6072218128224024,0.0851769154889193,0.6209677419354839,0.09235734985825865 +flat_mae,patch,logistic,adni_ad_vs_cn,60,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,60,1291.5496650148827,test,0.7804878048780488,0.06424482840972032,0.7119437939110069,0.08365683816324747,0.7193548387096774,0.08679009064119453 +flat_mae,patch,logistic,adni_ad_vs_cn,61,0.046415888336127774,train,0.8997289972899729,0.014589436872123605,0.8444297580930026,0.024860346735714134,0.8132139041827595,0.026678383779716635 +flat_mae,patch,logistic,adni_ad_vs_cn,61,0.046415888336127774,test,0.6829268292682927,0.0593330169522364,0.5176470588235295,0.07946104365539795,0.5193548387096775,0.07036523203466613 +flat_mae,patch,logistic,adni_ad_vs_cn,62,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,62,2.782559402207126,test,0.7073170731707317,0.06841626449081285,0.603225806451613,0.0866565554454166,0.603225806451613,0.0869682609226402 +flat_mae,patch,logistic,adni_ad_vs_cn,63,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,63,21.54434690031882,test,0.8048780487804879,0.05414139726932466,0.7152777777777778,0.08112412797071655,0.7016129032258065,0.07925619852858773 +flat_mae,patch,logistic,adni_ad_vs_cn,64,0.005994842503189409,train,0.8346883468834688,0.014659757775218179,0.7099243527455958,0.030746270531005756,0.6777261894979045,0.02658622708629662 +flat_mae,patch,logistic,adni_ad_vs_cn,64,0.005994842503189409,test,0.7073170731707317,0.046074687834129616,0.4831932773109243,0.06999266595795238,0.5016129032258064,0.054207830683289084 +flat_mae,patch,logistic,adni_ad_vs_cn,65,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,65,2.782559402207126,test,0.7560975609756098,0.06118938137147195,0.6440972222222222,0.09067858163296634,0.635483870967742,0.08532106614912956 +flat_mae,patch,logistic,adni_ad_vs_cn,66,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,66,2.782559402207126,test,0.7560975609756098,0.06480610351614018,0.6693548387096775,0.08707426619979745,0.6693548387096775,0.08798179850313353 +flat_mae,patch,logistic,adni_ad_vs_cn,67,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,67,1291.5496650148827,test,0.8292682926829268,0.057649869349808334,0.7602339181286549,0.0829397049434909,0.7516129032258064,0.08488625400279146 +flat_mae,patch,logistic,adni_ad_vs_cn,68,0.046415888336127774,train,0.8997289972899729,0.013822191362181897,0.8444297580930026,0.023792323102310806,0.8132139041827595,0.025885998878178215 +flat_mae,patch,logistic,adni_ad_vs_cn,68,0.046415888336127774,test,0.6585365853658537,0.07002980584099391,0.5651515151515152,0.08309625585418531,0.5709677419354839,0.08870555978713399 +flat_mae,patch,logistic,adni_ad_vs_cn,69,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,69,166.81005372000556,test,0.6829268292682927,0.06636188710011492,0.5839188134270101,0.08379338000765313,0.5870967741935484,0.08613172032775211 +flat_mae,patch,logistic,adni_ad_vs_cn,70,0.046415888336127774,train,0.8943089430894309,0.01438268242025756,0.8392156862745098,0.023744933144327626,0.8137275043142411,0.0258329845943531 +flat_mae,patch,logistic,adni_ad_vs_cn,70,0.046415888336127774,test,0.8048780487804879,0.050227702811145074,0.6893939393939394,0.09200662217888364,0.667741935483871,0.08203815639748895 +flat_mae,patch,logistic,adni_ad_vs_cn,71,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,71,2.782559402207126,test,0.6585365853658537,0.06927548914867095,0.5876436781609196,0.07665837070343957,0.6048387096774194,0.08588687105831312 +flat_mae,patch,logistic,adni_ad_vs_cn,72,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,72,1291.5496650148827,test,0.7073170731707317,0.03505586601155852,0.4142857142857143,0.012264915083619718,0.46774193548387094,0.023182104943127422 +flat_mae,patch,logistic,adni_ad_vs_cn,73,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,73,166.81005372000556,test,0.6829268292682927,0.06467188957813268,0.5547201336675021,0.08213626489908459,0.5532258064516129,0.07941243543138972 +flat_mae,patch,logistic,adni_ad_vs_cn,74,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,74,1291.5496650148827,test,0.7317073170731707,0.05787586461503221,0.5918552036199095,0.08859796188105128,0.5854838709677419,0.08148773750180681 +flat_mae,patch,logistic,adni_ad_vs_cn,75,0.046415888336127774,train,0.8834688346883469,0.01507993112795002,0.8154678141536315,0.026959497486507916,0.7823773522886022,0.028416340283248936 +flat_mae,patch,logistic,adni_ad_vs_cn,75,0.046415888336127774,test,0.7317073170731707,0.05220366923405966,0.5512437810945273,0.08831514837653892,0.5516129032258065,0.07114782313418008 +flat_mae,patch,logistic,adni_ad_vs_cn,76,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,76,166.81005372000556,test,0.6341463414634146,0.06596983429028698,0.5199063231850116,0.0790083548971691,0.5209677419354839,0.08114888643099569 +flat_mae,patch,logistic,adni_ad_vs_cn,77,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,77,21.54434690031882,test,0.8048780487804879,0.06023748361183244,0.7354838709677419,0.08169961065007789,0.7354838709677419,0.08448840785216856 +flat_mae,patch,logistic,adni_ad_vs_cn,78,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,78,1291.5496650148827,test,0.7317073170731707,0.06288050857078183,0.6232247284878863,0.0868859148048858,0.6193548387096774,0.08527031120469099 +flat_mae,patch,logistic,adni_ad_vs_cn,79,0.3593813663804626,train,0.978319783197832,0.00700610722466196,0.9689106074648244,0.010330479421149704,0.9575355411290984,0.014107609840780341 +flat_mae,patch,logistic,adni_ad_vs_cn,79,0.3593813663804626,test,0.7560975609756098,0.06665155291698972,0.6893939393939394,0.08133246442851284,0.7032258064516128,0.08696713619727786 +flat_mae,patch,logistic,adni_ad_vs_cn,80,0.005994842503189409,train,0.8184281842818428,0.014322285805083662,0.6731707317073171,0.031187420019201724,0.6468896376037472,0.025559983802374123 +flat_mae,patch,logistic,adni_ad_vs_cn,80,0.005994842503189409,test,0.7560975609756098,0.04427957257351609,0.569327731092437,0.08886123500812136,0.567741935483871,0.06676228123446316 +flat_mae,patch,logistic,adni_ad_vs_cn,81,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,81,166.81005372000556,test,0.7560975609756098,0.06264151616849772,0.6693548387096775,0.08451680972309644,0.6693548387096775,0.08650129885402831 +flat_mae,patch,logistic,adni_ad_vs_cn,82,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,82,166.81005372000556,test,0.6585365853658537,0.06671150385933673,0.5370967741935484,0.08433599911085739,0.5370967741935484,0.08452060139607265 +flat_mae,patch,logistic,adni_ad_vs_cn,83,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,83,21.54434690031882,test,0.7560975609756098,0.05349978734244736,0.6117424242424243,0.09002834156922292,0.6016129032258064,0.07893740193037245 +flat_mae,patch,logistic,adni_ad_vs_cn,84,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,84,2.782559402207126,test,0.6585365853658537,0.06788538824329059,0.5651515151515152,0.0813467920441892,0.5709677419354839,0.08747674458318627 +flat_mae,patch,logistic,adni_ad_vs_cn,85,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,85,2.782559402207126,test,0.8048780487804879,0.0652452290724482,0.7515151515151515,0.08083638597730626,0.7693548387096774,0.08664099045998734 +flat_mae,patch,logistic,adni_ad_vs_cn,86,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,86,166.81005372000556,test,0.5853658536585366,0.06773772775969386,0.4558938329430133,0.07035269928442761,0.45483870967741935,0.07296447976222338 +flat_mae,patch,logistic,adni_ad_vs_cn,87,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,87,166.81005372000556,test,0.8048780487804879,0.054913809486666416,0.7354838709677419,0.07636284672915712,0.7354838709677419,0.0793623230144883 +flat_mae,patch,logistic,adni_ad_vs_cn,88,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,88,166.81005372000556,test,0.6341463414634146,0.07305656133486543,0.5684210526315789,0.07886340183129255,0.5887096774193548,0.08935463345731638 +flat_mae,patch,logistic,adni_ad_vs_cn,89,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,89,2.782559402207126,test,0.7560975609756098,0.06100791339431416,0.6440972222222222,0.09331410020307497,0.635483870967742,0.088421680072049 +flat_mae,patch,logistic,adni_ad_vs_cn,90,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,90,1291.5496650148827,test,0.6585365853658537,0.06698076117541746,0.5370967741935484,0.08077850342795254,0.5370967741935484,0.08062599068916786 +flat_mae,patch,logistic,adni_ad_vs_cn,91,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,91,1291.5496650148827,test,0.6829268292682927,0.06969460021570287,0.5839188134270101,0.0871310210333352,0.5870967741935484,0.09053048790531623 +flat_mae,patch,logistic,adni_ad_vs_cn,92,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,92,166.81005372000556,test,0.6341463414634146,0.07096841804147767,0.5199063231850116,0.08388450992927216,0.5209677419354839,0.08603743008511101 +flat_mae,patch,logistic,adni_ad_vs_cn,93,0.046415888336127774,train,0.8943089430894309,0.01462404147767629,0.8392156862745098,0.023743867578512684,0.8137275043142411,0.025615661375470566 +flat_mae,patch,logistic,adni_ad_vs_cn,93,0.046415888336127774,test,0.5853658536585366,0.0682793715249907,0.4558938329430133,0.0719701688806884,0.45483870967741935,0.07478484574407882 +flat_mae,patch,logistic,adni_ad_vs_cn,94,0.3593813663804626,train,0.978319783197832,0.007576444821879369,0.9689106074648244,0.01119144952301028,0.9575355411290984,0.015141736434660673 +flat_mae,patch,logistic,adni_ad_vs_cn,94,0.3593813663804626,test,0.6829268292682927,0.06601865508892277,0.5839188134270101,0.08012444978739268,0.5870967741935484,0.08272518374095027 +flat_mae,patch,logistic,adni_ad_vs_cn,95,0.046415888336127774,train,0.8861788617886179,0.015129898543985935,0.8225148877691251,0.02589628934773095,0.7922384748130495,0.02742295517160358 +flat_mae,patch,logistic,adni_ad_vs_cn,95,0.046415888336127774,test,0.7560975609756098,0.0526575141960646,0.6117424242424243,0.09143868183845345,0.6016129032258064,0.07868545370238159 +flat_mae,patch,logistic,adni_ad_vs_cn,96,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,96,2.782559402207126,test,0.8048780487804879,0.0585543672178732,0.7354838709677419,0.08061577023886532,0.7354838709677419,0.08466852666054751 +flat_mae,patch,logistic,adni_ad_vs_cn,97,0.046415888336127774,train,0.8888888888888888,0.013940349901134979,0.8258572464518803,0.024408317664767858,0.7940052592653464,0.02627339380215953 +flat_mae,patch,logistic,adni_ad_vs_cn,97,0.046415888336127774,test,0.7804878048780488,0.040679855999211666,0.5886287625418061,0.09401471810798798,0.5838709677419355,0.06759588518592444 +flat_mae,patch,logistic,adni_ad_vs_cn,98,0.3593813663804626,train,0.986449864498645,0.005881535547469612,0.9808134274809954,0.008462326278270888,0.9749774015942148,0.011361486755864 +flat_mae,patch,logistic,adni_ad_vs_cn,98,0.3593813663804626,test,0.7317073170731707,0.05656793255419784,0.5918552036199095,0.08988635910431447,0.5854838709677419,0.08023169206785283 +flat_mae,patch,logistic,adni_ad_vs_cn,99,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,99,1291.5496650148827,test,0.7560975609756098,0.0631970752115042,0.6693548387096775,0.08645995805759851,0.6693548387096775,0.08769599722473297 +flat_mae,patch,logistic,adni_ad_vs_cn,100,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,100,1291.5496650148827,test,0.6585365853658537,0.07071044255621749,0.5651515151515152,0.08183153626513043,0.5709677419354839,0.08691264138230956 diff --git a/input_space_v3/flat_lr1e-3_2/eval_v2/adni_ad_vs_cn__patch__logistic/log.txt b/input_space_v3/flat_lr1e-3_2/eval_v2/adni_ad_vs_cn__patch__logistic/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..24a0bded03e193204c0ab4f492a17d54c0b83f14 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_2/eval_v2/adni_ad_vs_cn__patch__logistic/log.txt @@ -0,0 +1,240 @@ +fMRI foundation model logistic probe eval +version: 0.1.dev86+gf97f52698 +sha: bcce2b486277d3a5b520775efd9cdf1a2affce36, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-04-08 22:08:44 +config: +output_root: experiments/input_space_v3/output +name_prefix: eval_logistic +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_2; eval v2 (adni_ad_vs_cn patch logistic) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: input_space_v3/flat_lr1e-3_2/eval_v2/adni_ad_vs_cn__patch__logistic +model: flat_mae +representation: patch +dataset: adni_ad_vs_cn +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/eval_v2/adni_ad_vs_cn__patch__logistic +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=True, reg_tokens=0, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: adni_ad_vs_cn (flat) +train (n=328): +ADNIDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'bold', 'mean', 'std'], + num_rows: 525 +}), + labels=[0 1], + counts=[251 77] +) + +validation (n=41): +ADNIDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'bold', 'mean', 'std'], + num_rows: 66 +}), + labels=[0 1], + counts=[31 10] +) + +test (n=41): +ADNIDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'bold', 'mean', 'std'], + num_rows: 66 +}), + labels=[0 1], + counts=[32 9] +) + +extracting features for all splits +extract (train) [ 0/164] eta: 0:13:45 time: 5.0345 data: 4.1564 max mem: 2698 +extract (train) [ 20/164] eta: 0:01:05 time: 0.2230 data: 0.0837 max mem: 2851 +extract (train) [ 40/164] eta: 0:00:40 time: 0.1898 data: 0.0653 max mem: 2851 +extract (train) [ 60/164] eta: 0:00:28 time: 0.1825 data: 0.0607 max mem: 2851 +extract (train) [ 80/164] eta: 0:00:21 time: 0.1869 data: 0.0644 max mem: 2851 +extract (train) [100/164] eta: 0:00:15 time: 0.2002 data: 0.0704 max mem: 2851 +extract (train) [120/164] eta: 0:00:10 time: 0.1789 data: 0.0594 max mem: 2851 +extract (train) [140/164] eta: 0:00:05 time: 0.1664 data: 0.0522 max mem: 2851 +extract (train) [160/164] eta: 0:00:00 time: 0.1658 data: 0.0521 max mem: 2851 +extract (train) [163/164] eta: 0:00:00 time: 0.1656 data: 0.0521 max mem: 2851 +extract (train) Total time: 0:00:35 (0.2179 s / it) +extract (validation) [ 0/21] eta: 0:01:25 time: 4.0835 data: 3.9645 max mem: 2851 +extract (validation) [20/21] eta: 0:00:00 time: 0.1594 data: 0.0485 max mem: 2851 +extract (validation) Total time: 0:00:07 (0.3605 s / it) +extract (test) [ 0/21] eta: 0:01:22 time: 3.9225 data: 3.7679 max mem: 2851 +extract (test) [20/21] eta: 0:00:00 time: 0.1749 data: 0.0582 max mem: 2851 +extract (test) Total time: 0:00:07 (0.3652 s / it) +feature extraction time: 0:00:51 +train features: (328, 768) +validation features: (41, 768) +test features: (41, 768) +evaluating fixed splits +eval results (fixed splits): + +| model | repr | clf | dataset | trial | C | split | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:--------------|:--------|---------:|:--------|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | adni_ad_vs_cn | | 0.046416 | train | 0.88889 | 0.014197 | 0.82761 | 0.024682 | 0.79616 | 0.026275 | +| flat_mae | patch | logistic | adni_ad_vs_cn | | 0.046416 | test | 0.73171 | 0.054009 | 0.55124 | 0.085146 | 0.54861 | 0.073811 | + + +evaluating random splits (n=100) +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 1, "C": 2.782559402207126, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.05178684634051865, "f1": 0.6893939393939394, "f1_std": 0.09320644532173386, "bacc": 0.667741935483871, "bacc_std": 0.08305399093981082} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 2, "C": 21.54434690031882, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.07283531250955178, "f1": 0.646551724137931, "f1_std": 0.08157829392740856, "bacc": 0.6709677419354838, "bacc_std": 0.09087396052419394} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 3, "C": 166.81005372000556, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.06674154826881275, "f1": 0.6693548387096775, "f1_std": 0.0880974734690822, "bacc": 0.6693548387096775, "bacc_std": 0.08826519000664683} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 4, "C": 166.81005372000556, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.06119358113721882, "f1": 0.6917293233082706, "f1_std": 0.08761366377076861, "bacc": 0.685483870967742, "bacc_std": 0.08615443022894946} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 5, "C": 166.81005372000556, "split": "test", "acc": 0.6585365853658537, "acc_std": 0.05058917595077964, "f1": 0.4564393939393939, "f1_std": 0.0650144571686218, "bacc": 0.4693548387096774, "bacc_std": 0.05524387856248356} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 6, "C": 166.81005372000556, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.057254246833643746, "f1": 0.5918552036199095, "f1_std": 0.08958757228271201, "bacc": 0.5854838709677419, "bacc_std": 0.07883446077722216} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 7, "C": 2.782559402207126, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.06113002885911701, "f1": 0.6693548387096775, "f1_std": 0.08293258442932223, "bacc": 0.6693548387096775, "bacc_std": 0.08595482103468714} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 8, "C": 0.3593813663804626, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.061457432926115094, "f1": 0.5729166666666666, "f1_std": 0.08802793630094904, "bacc": 0.5693548387096774, "bacc_std": 0.0831612713030835} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 9, "C": 166.81005372000556, "split": "test", "acc": 0.6341463414634146, "acc_std": 0.06973861285217899, "f1": 0.5199063231850116, "f1_std": 0.07974438421127795, "bacc": 0.5209677419354839, "bacc_std": 0.08139234739433457} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 10, "C": 1291.5496650148827, "split": "test", "acc": 0.6341463414634146, "acc_std": 0.06791890745066566, "f1": 0.5199063231850116, "f1_std": 0.08086664425463178, "bacc": 0.5209677419354839, "bacc_std": 0.08314038777323743} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 11, "C": 21.54434690031882, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.0476557904194202, "f1": 0.6328358208955224, "f1_std": 0.08925218579972471, "bacc": 0.6177419354838709, "bacc_std": 0.07301188954251327} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 12, "C": 166.81005372000556, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.06723025507981038, "f1": 0.5839188134270101, "f1_std": 0.0840445814475537, "bacc": 0.5870967741935484, "bacc_std": 0.08638403346853771} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 13, "C": 2.782559402207126, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.054395712292095465, "f1": 0.7152777777777778, "f1_std": 0.08793733405871604, "bacc": 0.7016129032258065, "bacc_std": 0.08585259946295944} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 14, "C": 2.782559402207126, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.06875585097594628, "f1": 0.6479313036690086, "f1_std": 0.08915072476076948, "bacc": 0.6532258064516129, "bacc_std": 0.09108943564519568} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 15, "C": 2.782559402207126, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.056580655817430374, "f1": 0.6440972222222222, "f1_std": 0.08651186652710242, "bacc": 0.635483870967742, "bacc_std": 0.08133782399906715} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 16, "C": 0.046415888336127774, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.03891068801601732, "f1": 0.5886287625418061, "f1_std": 0.09127597999335721, "bacc": 0.5838709677419355, "bacc_std": 0.0646823342996173} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 17, "C": 0.3593813663804626, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.06261028342628557, "f1": 0.5729166666666666, "f1_std": 0.08991439854789625, "bacc": 0.5693548387096774, "bacc_std": 0.08210795512936304} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 18, "C": 0.005994842503189409, "split": "test", "acc": 0.8292682926829268, "acc_std": 0.03574528169693307, "f1": 0.6800445930880714, "f1_std": 0.09742890175980444, "bacc": 0.65, "bacc_std": 0.07327782747871281} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 19, "C": 2.782559402207126, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.06737184057040553, "f1": 0.6693548387096775, "f1_std": 0.08602365505908995, "bacc": 0.6693548387096775, "bacc_std": 0.08680596006861464} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 20, "C": 166.81005372000556, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.0696024232553868, "f1": 0.6272727272727273, "f1_std": 0.08256111445458664, "bacc": 0.6370967741935484, "bacc_std": 0.08773578583762309} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 21, "C": 0.046415888336127774, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.050387646616887556, "f1": 0.6893939393939394, "f1_std": 0.095460422597811, "bacc": 0.667741935483871, "bacc_std": 0.08324381719345002} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 22, "C": 166.81005372000556, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.0481623271457844, "f1": 0.569327731092437, "f1_std": 0.09395594959454302, "bacc": 0.567741935483871, "bacc_std": 0.07084989768574945} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 23, "C": 166.81005372000556, "split": "test", "acc": 0.5853658536585366, "acc_std": 0.062420424058786735, "f1": 0.4177109440267335, "f1_std": 0.06322721240913064, "bacc": 0.42096774193548386, "bacc_std": 0.06364695246241049} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 24, "C": 0.046415888336127774, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.04552251993832065, "f1": 0.569327731092437, "f1_std": 0.08952695603708932, "bacc": 0.567741935483871, "bacc_std": 0.06694085481755126} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 25, "C": 1291.5496650148827, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.06168899756988981, "f1": 0.6693548387096775, "f1_std": 0.08254351036279158, "bacc": 0.6693548387096775, "bacc_std": 0.08378794023127546} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 26, "C": 0.046415888336127774, "split": "test", "acc": 0.6585365853658537, "acc_std": 0.05963384208611096, "f1": 0.4564393939393939, "f1_std": 0.0703399889234458, "bacc": 0.4693548387096774, "bacc_std": 0.062170984646745704} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 27, "C": 0.046415888336127774, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.04093874648437682, "f1": 0.6554621848739496, "f1_std": 0.09155479817665176, "bacc": 0.6338709677419355, "bacc_std": 0.07211687790721591} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 28, "C": 166.81005372000556, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.06403419669381732, "f1": 0.6693548387096775, "f1_std": 0.08586836265517012, "bacc": 0.6693548387096775, "bacc_std": 0.08701149349367587} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 29, "C": 0.3593813663804626, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.06868311737778446, "f1": 0.6676492262343405, "f1_std": 0.08083257703074967, "bacc": 0.6870967741935483, "bacc_std": 0.08725215530644011} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 30, "C": 0.3593813663804626, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.06098341413469807, "f1": 0.6232247284878863, "f1_std": 0.0862808996052961, "bacc": 0.6193548387096774, "bacc_std": 0.0841836337630325} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 31, "C": 0.3593813663804626, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.06392833212143637, "f1": 0.6479313036690086, "f1_std": 0.08126431748773526, "bacc": 0.6532258064516129, "bacc_std": 0.08456642993410686} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 32, "C": 0.3593813663804626, "split": "test", "acc": 0.6341463414634146, "acc_std": 0.06827916242467993, "f1": 0.5199063231850116, "f1_std": 0.08228884424874298, "bacc": 0.5209677419354839, "bacc_std": 0.08469896770370253} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 33, "C": 1291.5496650148827, "split": "test", "acc": 0.6341463414634146, "acc_std": 0.0706967785918981, "f1": 0.5684210526315789, "f1_std": 0.07680196118999402, "bacc": 0.5887096774193548, "bacc_std": 0.08683493353243085} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 34, "C": 166.81005372000556, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.07037377898471933, "f1": 0.6272727272727273, "f1_std": 0.08915587208109203, "bacc": 0.6370967741935484, "bacc_std": 0.09594664853575936} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 35, "C": 21.54434690031882, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.04918222378287134, "f1": 0.6328358208955224, "f1_std": 0.09625074018481278, "bacc": 0.6177419354838709, "bacc_std": 0.07736649028448044} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 36, "C": 1291.5496650148827, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.060248365589587065, "f1": 0.5176470588235295, "f1_std": 0.0816020533844962, "bacc": 0.5193548387096775, "bacc_std": 0.07391979475209241} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 37, "C": 2.782559402207126, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.05760469608723577, "f1": 0.5729166666666666, "f1_std": 0.08258333945652464, "bacc": 0.5693548387096774, "bacc_std": 0.07587763274433709} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 38, "C": 2.782559402207126, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.07025176107801683, "f1": 0.646551724137931, "f1_std": 0.0805283832313704, "bacc": 0.6709677419354838, "bacc_std": 0.08966407280585237} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 39, "C": 2.782559402207126, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.06271074641275967, "f1": 0.5547201336675021, "f1_std": 0.08315431414363184, "bacc": 0.5532258064516129, "bacc_std": 0.08030485618665417} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 40, "C": 0.3593813663804626, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.06772411403373083, "f1": 0.5839188134270101, "f1_std": 0.08436023011862094, "bacc": 0.5870967741935484, "bacc_std": 0.08805519854997397} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 41, "C": 21.54434690031882, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.0638148720449289, "f1": 0.6693548387096775, "f1_std": 0.08605590504785669, "bacc": 0.6693548387096775, "bacc_std": 0.08768059590960518} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 42, "C": 2.782559402207126, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.06147115708106678, "f1": 0.7119437939110069, "f1_std": 0.07679082151132947, "bacc": 0.7193548387096774, "bacc_std": 0.08152265691211495} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 43, "C": 2.782559402207126, "split": "test", "acc": 0.8780487804878049, "acc_std": 0.04489339610323919, "f1": 0.8144796380090498, "f1_std": 0.07585507855434435, "bacc": 0.7838709677419355, "bacc_std": 0.07826216374924629} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 44, "C": 21.54434690031882, "split": "test", "acc": 0.8536585365853658, "acc_std": 0.04632068853971814, "f1": 0.7670454545454546, "f1_std": 0.08766276270469826, "bacc": 0.7338709677419355, "bacc_std": 0.0838105272916926} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 45, "C": 166.81005372000556, "split": "test", "acc": 0.8292682926829268, "acc_std": 0.052763691480107525, "f1": 0.7402714932126697, "f1_std": 0.08904190572576509, "bacc": 0.717741935483871, "bacc_std": 0.08497621164340845} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 46, "C": 166.81005372000556, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.06920799505416272, "f1": 0.6479313036690086, "f1_std": 0.08872900223229896, "bacc": 0.6532258064516129, "bacc_std": 0.09259589280980303} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 47, "C": 21.54434690031882, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.06350498254351755, "f1": 0.6232247284878863, "f1_std": 0.0887257001946197, "bacc": 0.6193548387096774, "bacc_std": 0.08760106670958777} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 48, "C": 166.81005372000556, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.07291754570162196, "f1": 0.646551724137931, "f1_std": 0.08186494791234171, "bacc": 0.6709677419354838, "bacc_std": 0.08921925640129022} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 49, "C": 21.54434690031882, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.060216464572340256, "f1": 0.5176470588235295, "f1_std": 0.08601429169745131, "bacc": 0.5193548387096775, "bacc_std": 0.07531788166595794} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 50, "C": 166.81005372000556, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.05912114625548764, "f1": 0.6917293233082706, "f1_std": 0.08510130150400332, "bacc": 0.685483870967742, "bacc_std": 0.08356466400171211} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 51, "C": 21.54434690031882, "split": "test", "acc": 0.5365853658536586, "acc_std": 0.07755177119797389, "f1": 0.4533333333333333, "f1_std": 0.07640264985917493, "bacc": 0.4564516129032258, "bacc_std": 0.08600097638774923} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 52, "C": 2.782559402207126, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.0700114038471563, "f1": 0.6272727272727273, "f1_std": 0.08524069536490321, "bacc": 0.6370967741935484, "bacc_std": 0.09108199208404434} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 53, "C": 166.81005372000556, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.057547311317360676, "f1": 0.5918552036199095, "f1_std": 0.09149914247272649, "bacc": 0.5854838709677419, "bacc_std": 0.08158279050483423} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 54, "C": 21.54434690031882, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.06597840037378447, "f1": 0.6893939393939394, "f1_std": 0.08158447430596333, "bacc": 0.7032258064516128, "bacc_std": 0.08819411921376491} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 55, "C": 21.54434690031882, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.06899058036040281, "f1": 0.6272727272727273, "f1_std": 0.08408822334251508, "bacc": 0.6370967741935484, "bacc_std": 0.08984160162137504} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 56, "C": 166.81005372000556, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.06497463926617204, "f1": 0.5729166666666666, "f1_std": 0.09123197601496126, "bacc": 0.5693548387096774, "bacc_std": 0.08546755017662896} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 57, "C": 21.54434690031882, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.06779989453523284, "f1": 0.6479313036690086, "f1_std": 0.08855985301528392, "bacc": 0.6532258064516129, "bacc_std": 0.09209999519817946} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 58, "C": 0.046415888336127774, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.04945735278196642, "f1": 0.6328358208955224, "f1_std": 0.09320927105681079, "bacc": 0.6177419354838709, "bacc_std": 0.07612478630860449} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 59, "C": 166.81005372000556, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.07424862970111006, "f1": 0.6072218128224024, "f1_std": 0.0851769154889193, "bacc": 0.6209677419354839, "bacc_std": 0.09235734985825865} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 60, "C": 1291.5496650148827, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.06424482840972032, "f1": 0.7119437939110069, "f1_std": 0.08365683816324747, "bacc": 0.7193548387096774, "bacc_std": 0.08679009064119453} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 61, "C": 0.046415888336127774, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.0593330169522364, "f1": 0.5176470588235295, "f1_std": 0.07946104365539795, "bacc": 0.5193548387096775, "bacc_std": 0.07036523203466613} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 62, "C": 2.782559402207126, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.06841626449081285, "f1": 0.603225806451613, "f1_std": 0.0866565554454166, "bacc": 0.603225806451613, "bacc_std": 0.0869682609226402} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 63, "C": 21.54434690031882, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.05414139726932466, "f1": 0.7152777777777778, "f1_std": 0.08112412797071655, "bacc": 0.7016129032258065, "bacc_std": 0.07925619852858773} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 64, "C": 0.005994842503189409, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.046074687834129616, "f1": 0.4831932773109243, "f1_std": 0.06999266595795238, "bacc": 0.5016129032258064, "bacc_std": 0.054207830683289084} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 65, "C": 2.782559402207126, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.06118938137147195, "f1": 0.6440972222222222, "f1_std": 0.09067858163296634, "bacc": 0.635483870967742, "bacc_std": 0.08532106614912956} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 66, "C": 2.782559402207126, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.06480610351614018, "f1": 0.6693548387096775, "f1_std": 0.08707426619979745, "bacc": 0.6693548387096775, "bacc_std": 0.08798179850313353} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 67, "C": 1291.5496650148827, "split": "test", "acc": 0.8292682926829268, "acc_std": 0.057649869349808334, "f1": 0.7602339181286549, "f1_std": 0.0829397049434909, "bacc": 0.7516129032258064, "bacc_std": 0.08488625400279146} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 68, "C": 0.046415888336127774, "split": "test", "acc": 0.6585365853658537, "acc_std": 0.07002980584099391, "f1": 0.5651515151515152, "f1_std": 0.08309625585418531, "bacc": 0.5709677419354839, "bacc_std": 0.08870555978713399} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 69, "C": 166.81005372000556, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.06636188710011492, "f1": 0.5839188134270101, "f1_std": 0.08379338000765313, "bacc": 0.5870967741935484, "bacc_std": 0.08613172032775211} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 70, "C": 0.046415888336127774, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.050227702811145074, "f1": 0.6893939393939394, "f1_std": 0.09200662217888364, "bacc": 0.667741935483871, "bacc_std": 0.08203815639748895} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 71, "C": 2.782559402207126, "split": "test", "acc": 0.6585365853658537, "acc_std": 0.06927548914867095, "f1": 0.5876436781609196, "f1_std": 0.07665837070343957, "bacc": 0.6048387096774194, "bacc_std": 0.08588687105831312} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 72, "C": 1291.5496650148827, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.03505586601155852, "f1": 0.4142857142857143, "f1_std": 0.012264915083619718, "bacc": 0.46774193548387094, "bacc_std": 0.023182104943127422} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 73, "C": 166.81005372000556, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.06467188957813268, "f1": 0.5547201336675021, "f1_std": 0.08213626489908459, "bacc": 0.5532258064516129, "bacc_std": 0.07941243543138972} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 74, "C": 1291.5496650148827, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.05787586461503221, "f1": 0.5918552036199095, "f1_std": 0.08859796188105128, "bacc": 0.5854838709677419, "bacc_std": 0.08148773750180681} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 75, "C": 0.046415888336127774, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.05220366923405966, "f1": 0.5512437810945273, "f1_std": 0.08831514837653892, "bacc": 0.5516129032258065, "bacc_std": 0.07114782313418008} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 76, "C": 166.81005372000556, "split": "test", "acc": 0.6341463414634146, "acc_std": 0.06596983429028698, "f1": 0.5199063231850116, "f1_std": 0.0790083548971691, "bacc": 0.5209677419354839, "bacc_std": 0.08114888643099569} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 77, "C": 21.54434690031882, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.06023748361183244, "f1": 0.7354838709677419, "f1_std": 0.08169961065007789, "bacc": 0.7354838709677419, "bacc_std": 0.08448840785216856} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 78, "C": 1291.5496650148827, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.06288050857078183, "f1": 0.6232247284878863, "f1_std": 0.0868859148048858, "bacc": 0.6193548387096774, "bacc_std": 0.08527031120469099} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 79, "C": 0.3593813663804626, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.06665155291698972, "f1": 0.6893939393939394, "f1_std": 0.08133246442851284, "bacc": 0.7032258064516128, "bacc_std": 0.08696713619727786} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 80, "C": 0.005994842503189409, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.04427957257351609, "f1": 0.569327731092437, "f1_std": 0.08886123500812136, "bacc": 0.567741935483871, "bacc_std": 0.06676228123446316} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 81, "C": 166.81005372000556, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.06264151616849772, "f1": 0.6693548387096775, "f1_std": 0.08451680972309644, "bacc": 0.6693548387096775, "bacc_std": 0.08650129885402831} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 82, "C": 166.81005372000556, "split": "test", "acc": 0.6585365853658537, "acc_std": 0.06671150385933673, "f1": 0.5370967741935484, "f1_std": 0.08433599911085739, "bacc": 0.5370967741935484, "bacc_std": 0.08452060139607265} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 83, "C": 21.54434690031882, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.05349978734244736, "f1": 0.6117424242424243, "f1_std": 0.09002834156922292, "bacc": 0.6016129032258064, "bacc_std": 0.07893740193037245} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 84, "C": 2.782559402207126, "split": "test", "acc": 0.6585365853658537, "acc_std": 0.06788538824329059, "f1": 0.5651515151515152, "f1_std": 0.0813467920441892, "bacc": 0.5709677419354839, "bacc_std": 0.08747674458318627} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 85, "C": 2.782559402207126, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.0652452290724482, "f1": 0.7515151515151515, "f1_std": 0.08083638597730626, "bacc": 0.7693548387096774, "bacc_std": 0.08664099045998734} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 86, "C": 166.81005372000556, "split": "test", "acc": 0.5853658536585366, "acc_std": 0.06773772775969386, "f1": 0.4558938329430133, "f1_std": 0.07035269928442761, "bacc": 0.45483870967741935, "bacc_std": 0.07296447976222338} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 87, "C": 166.81005372000556, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.054913809486666416, "f1": 0.7354838709677419, "f1_std": 0.07636284672915712, "bacc": 0.7354838709677419, "bacc_std": 0.0793623230144883} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 88, "C": 166.81005372000556, "split": "test", "acc": 0.6341463414634146, "acc_std": 0.07305656133486543, "f1": 0.5684210526315789, "f1_std": 0.07886340183129255, "bacc": 0.5887096774193548, "bacc_std": 0.08935463345731638} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 89, "C": 2.782559402207126, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.06100791339431416, "f1": 0.6440972222222222, "f1_std": 0.09331410020307497, "bacc": 0.635483870967742, "bacc_std": 0.088421680072049} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 90, "C": 1291.5496650148827, "split": "test", "acc": 0.6585365853658537, "acc_std": 0.06698076117541746, "f1": 0.5370967741935484, "f1_std": 0.08077850342795254, "bacc": 0.5370967741935484, "bacc_std": 0.08062599068916786} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 91, "C": 1291.5496650148827, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.06969460021570287, "f1": 0.5839188134270101, "f1_std": 0.0871310210333352, "bacc": 0.5870967741935484, "bacc_std": 0.09053048790531623} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 92, "C": 166.81005372000556, "split": "test", "acc": 0.6341463414634146, "acc_std": 0.07096841804147767, "f1": 0.5199063231850116, "f1_std": 0.08388450992927216, "bacc": 0.5209677419354839, "bacc_std": 0.08603743008511101} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 93, "C": 0.046415888336127774, "split": "test", "acc": 0.5853658536585366, "acc_std": 0.0682793715249907, "f1": 0.4558938329430133, "f1_std": 0.0719701688806884, "bacc": 0.45483870967741935, "bacc_std": 0.07478484574407882} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 94, "C": 0.3593813663804626, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.06601865508892277, "f1": 0.5839188134270101, "f1_std": 0.08012444978739268, "bacc": 0.5870967741935484, "bacc_std": 0.08272518374095027} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 95, "C": 0.046415888336127774, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.0526575141960646, "f1": 0.6117424242424243, "f1_std": 0.09143868183845345, "bacc": 0.6016129032258064, "bacc_std": 0.07868545370238159} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 96, "C": 2.782559402207126, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.0585543672178732, "f1": 0.7354838709677419, "f1_std": 0.08061577023886532, "bacc": 0.7354838709677419, "bacc_std": 0.08466852666054751} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 97, "C": 0.046415888336127774, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.040679855999211666, "f1": 0.5886287625418061, "f1_std": 0.09401471810798798, "bacc": 0.5838709677419355, "bacc_std": 0.06759588518592444} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 98, "C": 0.3593813663804626, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.05656793255419784, "f1": 0.5918552036199095, "f1_std": 0.08988635910431447, "bacc": 0.5854838709677419, "bacc_std": 0.08023169206785283} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 99, "C": 1291.5496650148827, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.0631970752115042, "f1": 0.6693548387096775, "f1_std": 0.08645995805759851, "bacc": 0.6693548387096775, "bacc_std": 0.08769599722473297} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 100, "C": 1291.5496650148827, "split": "test", "acc": 0.6585365853658537, "acc_std": 0.07071044255621749, "f1": 0.5651515151515152, "f1_std": 0.08183153626513043, "bacc": 0.5709677419354839, "bacc_std": 0.08691264138230956} +eval results (random splits): + +| model | repr | clf | dataset | split | n_trials | C | C_std | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:--------------|:--------|-----------:|-------:|--------:|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | adni_ad_vs_cn | train | 100 | 216.56 | 423.47 | 0.97908 | 0.045829 | 0.9665 | 0.075693 | 0.96115 | 0.085702 | +| flat_mae | patch | logistic | adni_ad_vs_cn | test | 100 | 216.56 | 423.47 | 0.72585 | 0.063082 | 0.61291 | 0.08052 | 0.61311 | 0.076548 | + + +done! total time: 0:04:46 diff --git a/input_space_v3/flat_lr1e-3_2/eval_v2/hcpya_task21__patch__attn/config.yaml b/input_space_v3/flat_lr1e-3_2/eval_v2/hcpya_task21__patch__attn/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..8bc02f933e4d3873af6fb8b34c36e6f41972cd21 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_2/eval_v2/hcpya_task21__patch__attn/config.yaml @@ -0,0 +1,96 @@ +output_root: experiments/input_space_v3/output +name_prefix: eval_probe +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_2; eval v2 (hcpya_task21 patch attn) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +dataset_kwargs: {} +classifier_kwargs: + embed_dim: null + dropout: 0.0 + xavier_init: true + norm: true +lr_scale_grid: +- 0.02 +- 0.023 +- 0.028 +- 0.033 +- 0.038 +- 0.045 +- 0.053 +- 0.062 +- 0.074 +- 0.087 +- 0.1 +- 0.12 +- 0.14 +- 0.17 +- 0.2 +- 0.23 +- 0.27 +- 0.32 +- 0.38 +- 0.44 +- 0.52 +- 0.61 +- 0.72 +- 0.85 +- 1 +- 1.2 +- 1.4 +- 1.6 +- 1.9 +- 2.3 +- 2.7 +- 3.1 +- 3.7 +- 4.3 +- 5.1 +- 6 +- 7.1 +- 8.3 +- 9.8 +- 12 +- 14 +- 16 +- 19 +- 22 +- 26 +- 31 +- 36 +- 43 +- 50 +wd_scale_grid: +- 1.0 +num_workers: 8 +prefetch_factor: null +balanced_sampling: false +epochs: 20 +steps_per_epoch: 200 +batch_size: 64 +accum_iter: 2 +lr: 0.0003 +warmup_epochs: 5 +no_decay: false +weight_decay: 0.05 +clip_grad: 1.0 +metrics: +- acc +- f1 +cv_metric: acc +early_stopping: true +amp: true +device: cuda +seed: 4466 +debug: false +wandb: false +wandb_entity: null +wandb_project: fMRI-fm-eval +name: input_space_v3/flat_lr1e-3_2/eval_v2/hcpya_task21__patch__attn +model: flat_mae +representation: patch +classifier: attn +dataset: hcpya_task21 +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/eval_v2/hcpya_task21__patch__attn +remote_dir: null diff --git a/input_space_v3/flat_lr1e-3_2/eval_v2/hcpya_task21__patch__attn/eval_log.json b/input_space_v3/flat_lr1e-3_2/eval_v2/hcpya_task21__patch__attn/eval_log.json new file mode 100644 index 0000000000000000000000000000000000000000..cbb0a7b0cd3b1b91a132f6a67b393e506ffcb441 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_2/eval_v2/hcpya_task21__patch__attn/eval_log.json @@ -0,0 +1 @@ +{"eval/epoch": 10, "eval/id_best": 22, "eval/lr_best": 0.00021599999999999996, "eval/wd_best": 0.05, "eval/train/loss": 0.018581779673695564, "eval/train/acc": 0.9950523711774304, "eval/train/acc_std": 0.0005218320790474648, "eval/train/f1": 0.994484863868484, "eval/train/f1_std": 0.0006459126299039842, "eval/validation/loss": 0.021804677322506905, "eval/validation/acc": 0.9935515873015873, "eval/validation/acc_std": 0.001291634187989243, "eval/validation/f1": 0.9926627106112288, "eval/validation/f1_std": 0.001639358756269641, "eval/test/loss": 0.03435142710804939, "eval/test/acc": 0.9896825396825397, "eval/test/acc_std": 0.0014302355276845247, "eval/test/f1": 0.9868047264475971, "eval/test/f1_std": 0.001963156090980563} diff --git a/input_space_v3/flat_lr1e-3_2/eval_v2/hcpya_task21__patch__attn/eval_log_best.json b/input_space_v3/flat_lr1e-3_2/eval_v2/hcpya_task21__patch__attn/eval_log_best.json new file mode 100644 index 0000000000000000000000000000000000000000..d06ec7585785708fbe9b5f05a8f9807a501ebfca --- /dev/null +++ b/input_space_v3/flat_lr1e-3_2/eval_v2/hcpya_task21__patch__attn/eval_log_best.json @@ -0,0 +1 @@ +{"eval/best/epoch": 10, "eval/best/id_best": 22, "eval/best/lr_best": 0.00021599999999999996, "eval/best/wd_best": 0.05, "eval/best/train/loss": 0.018581779673695564, "eval/best/train/acc": 0.9950523711774304, "eval/best/train/acc_std": 0.0005218320790474648, "eval/best/train/f1": 0.994484863868484, "eval/best/train/f1_std": 0.0006459126299039842, "eval/best/validation/loss": 0.021804677322506905, "eval/best/validation/acc": 0.9935515873015873, "eval/best/validation/acc_std": 0.001291634187989243, "eval/best/validation/f1": 0.9926627106112288, "eval/best/validation/f1_std": 0.001639358756269641, "eval/best/test/loss": 0.03435142710804939, "eval/best/test/acc": 0.9896825396825397, "eval/best/test/acc_std": 0.0014302355276845247, "eval/best/test/f1": 0.9868047264475971, "eval/best/test/f1_std": 0.001963156090980563} diff --git a/input_space_v3/flat_lr1e-3_2/eval_v2/hcpya_task21__patch__attn/eval_log_last.json b/input_space_v3/flat_lr1e-3_2/eval_v2/hcpya_task21__patch__attn/eval_log_last.json new file mode 100644 index 0000000000000000000000000000000000000000..07581a9a5c014d2a5e0dcba792e1b5507a74a04a --- /dev/null +++ b/input_space_v3/flat_lr1e-3_2/eval_v2/hcpya_task21__patch__attn/eval_log_last.json @@ -0,0 +1 @@ +{"eval/last/epoch": 19, "eval/last/id_best": 40, "eval/last/lr_best": 0.0042, "eval/last/wd_best": 0.05, "eval/last/train/loss": 1.4315256748886895e-06, "eval/last/train/acc": 1.0, "eval/last/train/acc_std": 0.0, "eval/last/train/f1": 1.0, "eval/last/train/f1_std": 0.0, "eval/last/validation/loss": 0.16015657782554626, "eval/last/validation/acc": 0.9933035714285714, "eval/last/validation/acc_std": 0.0012900758710337242, "eval/last/validation/f1": 0.9926364146826077, "eval/last/validation/f1_std": 0.001568669072575863, "eval/last/test/loss": 0.27214646339416504, "eval/last/test/acc": 0.9886904761904762, "eval/last/test/acc_std": 0.0014199636504880937, "eval/last/test/f1": 0.986859702587797, "eval/last/test/f1_std": 0.0017417540048870108} diff --git a/input_space_v3/flat_lr1e-3_2/eval_v2/hcpya_task21__patch__attn/eval_table.csv b/input_space_v3/flat_lr1e-3_2/eval_v2/hcpya_task21__patch__attn/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..55a6cb46d6e362926a4e33a1ea9438efec03f65e --- /dev/null +++ b/input_space_v3/flat_lr1e-3_2/eval_v2/hcpya_task21__patch__attn/eval_table.csv @@ -0,0 +1,4 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,patch,attn,hcpya_task21,best,10,0.00021599999999999996,0.05,22,"[0.72, 1.0]",train,0.018581779673695564,0.9950523711774304,0.0005218320790474648,0.994484863868484,0.0006459126299039842 +flat_mae,patch,attn,hcpya_task21,best,10,0.00021599999999999996,0.05,22,"[0.72, 1.0]",validation,0.021804677322506905,0.9935515873015873,0.001291634187989243,0.9926627106112288,0.001639358756269641 +flat_mae,patch,attn,hcpya_task21,best,10,0.00021599999999999996,0.05,22,"[0.72, 1.0]",test,0.03435142710804939,0.9896825396825397,0.0014302355276845247,0.9868047264475971,0.001963156090980563 diff --git a/input_space_v3/flat_lr1e-3_2/eval_v2/hcpya_task21__patch__attn/eval_table_best.csv b/input_space_v3/flat_lr1e-3_2/eval_v2/hcpya_task21__patch__attn/eval_table_best.csv new file mode 100644 index 0000000000000000000000000000000000000000..55a6cb46d6e362926a4e33a1ea9438efec03f65e --- /dev/null +++ b/input_space_v3/flat_lr1e-3_2/eval_v2/hcpya_task21__patch__attn/eval_table_best.csv @@ -0,0 +1,4 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,patch,attn,hcpya_task21,best,10,0.00021599999999999996,0.05,22,"[0.72, 1.0]",train,0.018581779673695564,0.9950523711774304,0.0005218320790474648,0.994484863868484,0.0006459126299039842 +flat_mae,patch,attn,hcpya_task21,best,10,0.00021599999999999996,0.05,22,"[0.72, 1.0]",validation,0.021804677322506905,0.9935515873015873,0.001291634187989243,0.9926627106112288,0.001639358756269641 +flat_mae,patch,attn,hcpya_task21,best,10,0.00021599999999999996,0.05,22,"[0.72, 1.0]",test,0.03435142710804939,0.9896825396825397,0.0014302355276845247,0.9868047264475971,0.001963156090980563 diff --git a/input_space_v3/flat_lr1e-3_2/eval_v2/hcpya_task21__patch__attn/eval_table_last.csv b/input_space_v3/flat_lr1e-3_2/eval_v2/hcpya_task21__patch__attn/eval_table_last.csv new file mode 100644 index 0000000000000000000000000000000000000000..27629b849ab07cea8fde97b4acb60144616a87aa --- /dev/null +++ b/input_space_v3/flat_lr1e-3_2/eval_v2/hcpya_task21__patch__attn/eval_table_last.csv @@ -0,0 +1,4 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,patch,attn,hcpya_task21,last,19,0.0042,0.05,40,"[14, 1.0]",train,1.4315256748886895e-06,1.0,0.0,1.0,0.0 +flat_mae,patch,attn,hcpya_task21,last,19,0.0042,0.05,40,"[14, 1.0]",validation,0.16015657782554626,0.9933035714285714,0.0012900758710337242,0.9926364146826077,0.001568669072575863 +flat_mae,patch,attn,hcpya_task21,last,19,0.0042,0.05,40,"[14, 1.0]",test,0.27214646339416504,0.9886904761904762,0.0014199636504880937,0.986859702587797,0.0017417540048870108 diff --git a/input_space_v3/flat_lr1e-3_2/eval_v2/hcpya_task21__patch__attn/log.txt b/input_space_v3/flat_lr1e-3_2/eval_v2/hcpya_task21__patch__attn/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..80e5f882bc115012695a56c5ea506e43b0ce4a8a --- /dev/null +++ b/input_space_v3/flat_lr1e-3_2/eval_v2/hcpya_task21__patch__attn/log.txt @@ -0,0 +1,886 @@ +fMRI foundation model probe eval +version: 0.1.dev86+gf97f52698 +sha: bcce2b486277d3a5b520775efd9cdf1a2affce36, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-04-08 20:31:09 +config: +output_root: experiments/input_space_v3/output +name_prefix: eval_probe +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_2; eval v2 (hcpya_task21 patch attn) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +dataset_kwargs: {} +classifier_kwargs: + embed_dim: null + dropout: 0.0 + xavier_init: true + norm: true +lr_scale_grid: +- 0.02 +- 0.023 +- 0.028 +- 0.033 +- 0.038 +- 0.045 +- 0.053 +- 0.062 +- 0.074 +- 0.087 +- 0.1 +- 0.12 +- 0.14 +- 0.17 +- 0.2 +- 0.23 +- 0.27 +- 0.32 +- 0.38 +- 0.44 +- 0.52 +- 0.61 +- 0.72 +- 0.85 +- 1 +- 1.2 +- 1.4 +- 1.6 +- 1.9 +- 2.3 +- 2.7 +- 3.1 +- 3.7 +- 4.3 +- 5.1 +- 6 +- 7.1 +- 8.3 +- 9.8 +- 12 +- 14 +- 16 +- 19 +- 22 +- 26 +- 31 +- 36 +- 43 +- 50 +wd_scale_grid: +- 1.0 +num_workers: 8 +prefetch_factor: null +balanced_sampling: false +epochs: 20 +steps_per_epoch: 200 +batch_size: 64 +accum_iter: 2 +lr: 0.0003 +warmup_epochs: 5 +no_decay: false +weight_decay: 0.05 +clip_grad: 1.0 +metrics: +- acc +- f1 +cv_metric: acc +early_stopping: true +amp: true +device: cuda +seed: 4466 +debug: false +wandb: false +wandb_entity: null +wandb_project: fMRI-fm-eval +name: input_space_v3/flat_lr1e-3_2/eval_v2/hcpya_task21__patch__attn +model: flat_mae +representation: patch +classifier: attn +dataset: hcpya_task21 +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/eval_v2/hcpya_task21__patch__attn +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=True, reg_tokens=0, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: hcpya_task21 (flat) +train (n=18999): +HFDataset( + dataset=Dataset({ + features: ['sub', 'task', 'cond', 'cond_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 18999 +}), + labels=[ 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20], + counts=[ 832 1248 3201 1660 832 832 832 832 832 1248 1247 1243 832 416 + 416 416 416 416 416 416 416] +) + +validation (n=4032): +HFDataset( + dataset=Dataset({ + features: ['sub', 'task', 'cond', 'cond_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 4032 +}), + labels=[ 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20], + counts=[176 264 688 352 176 176 176 176 176 264 264 264 176 88 88 88 88 88 + 88 88 88] +) + +test (n=5040): +HFDataset( + dataset=Dataset({ + features: ['sub', 'task', 'cond', 'cond_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 5040 +}), + labels=[ 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20], + counts=[220 330 860 440 220 220 220 220 220 330 330 330 220 110 110 110 110 110 + 110 110 110] +) + +running backbone on example batch to get embedding dim +embedding feature dim (patch): 768 +initializing sweep of classifier heads +classifiers: +ModuleList( + (0-48): 49 x AttnPoolClassifier( + (kv): Linear(in_features=768, out_features=1536, bias=True) + (linear): Linear(in_features=768, out_features=21, bias=True) + ) +) +classifier params (train): 58.7M (58.7M) +setting up optimizer +total batch size: 128 = 64 bs per gpu x 2 accum +lr: 3.00e-04 +full schedule: epochs = 20 (steps = 4000) (decay = True) +warmup: epochs = 5 (steps = 1000) +start training for 20 epochs +train: [0] [ 0/400] eta: 0:30:59 lr: nan time: 4.6487 data: 4.1848 max mem: 21740 +train: [0] [ 20/400] eta: 0:04:12 lr: 0.000003 loss: 3.0147 (3.0183) grad: 0.2650 (0.2723) time: 0.4664 data: 0.0253 max mem: 22446 +train: [0] [ 40/400] eta: 0:03:39 lr: 0.000006 loss: 2.9874 (2.9793) grad: 0.2644 (0.2710) time: 0.5493 data: 0.0874 max mem: 22446 +train: [0] [ 60/400] eta: 0:03:08 lr: 0.000009 loss: 2.8509 (2.9180) grad: 0.2636 (0.2669) time: 0.4445 data: 0.0026 max mem: 22446 +train: [0] [ 80/400] eta: 0:02:50 lr: 0.000012 loss: 2.7151 (2.8524) grad: 0.2444 (0.2602) time: 0.4627 data: 0.0036 max mem: 22446 +train: [0] [100/400] eta: 0:02:35 lr: 0.000015 loss: 2.5730 (2.7813) grad: 0.2314 (0.2560) time: 0.4649 data: 0.0035 max mem: 22446 +train: [0] [120/400] eta: 0:02:22 lr: 0.000018 loss: 2.4346 (2.7102) grad: 0.2339 (0.2515) time: 0.4695 data: 0.0035 max mem: 22446 +train: [0] [140/400] eta: 0:02:10 lr: 0.000021 loss: 2.2912 (2.6424) grad: 0.2321 (0.2496) time: 0.4578 data: 0.0035 max mem: 22446 +train: [0] [160/400] eta: 0:01:59 lr: 0.000024 loss: 2.1738 (2.5819) grad: 0.2219 (0.2450) time: 0.4622 data: 0.0037 max mem: 22446 +train: [0] [180/400] eta: 0:01:48 lr: 0.000027 loss: 2.0819 (2.5214) grad: 0.2069 (0.2405) time: 0.4620 data: 0.0035 max mem: 22446 +train: [0] [200/400] eta: 0:01:38 lr: 0.000030 loss: 2.0026 (2.4647) grad: 0.2039 (0.2374) time: 0.4567 data: 0.0035 max mem: 22446 +train: [0] [220/400] eta: 0:01:27 lr: 0.000033 loss: 1.8934 (2.4105) grad: 0.1982 (0.2335) time: 0.4538 data: 0.0037 max mem: 22446 +train: [0] [240/400] eta: 0:01:17 lr: 0.000036 loss: 1.8219 (2.3568) grad: 0.1998 (0.2314) time: 0.4618 data: 0.0037 max mem: 22446 +train: [0] [260/400] eta: 0:01:07 lr: 0.000039 loss: 1.7537 (2.3082) grad: 0.2010 (0.2290) time: 0.4574 data: 0.0036 max mem: 22446 +train: [0] [280/400] eta: 0:00:57 lr: 0.000042 loss: 1.7142 (2.2651) grad: 0.1857 (0.2257) time: 0.4603 data: 0.0036 max mem: 22446 +train: [0] [300/400] eta: 0:00:49 lr: 0.000045 loss: 1.6636 (2.2236) grad: 0.1737 (0.2224) time: 0.6216 data: 0.1748 max mem: 22446 +train: [0] [320/400] eta: 0:00:39 lr: 0.000048 loss: 1.6140 (2.1829) grad: 0.1716 (0.2196) time: 0.5083 data: 0.0379 max mem: 22446 +train: [0] [340/400] eta: 0:00:29 lr: 0.000051 loss: 1.5421 (2.1441) grad: 0.1805 (0.2176) time: 0.4741 data: 0.0034 max mem: 22446 +train: [0] [360/400] eta: 0:00:19 lr: 0.000054 loss: 1.5152 (2.1090) grad: 0.1793 (0.2153) time: 0.4551 data: 0.0034 max mem: 22446 +train: [0] [380/400] eta: 0:00:09 lr: 0.000057 loss: 1.4798 (2.0748) grad: 0.1750 (0.2130) time: 0.4658 data: 0.0035 max mem: 22446 +train: [0] [399/400] eta: 0:00:00 lr: 0.000060 loss: 1.4328 (2.0406) grad: 0.1742 (0.2112) time: 0.4687 data: 0.0035 max mem: 22446 +train: [0] Total time: 0:03:14 (0.4869 s / it) +train: [0] Summary: lr: 0.000060 loss: 1.4328 (2.0406) grad: 0.1742 (0.2112) +eval (validation): [0] [ 0/63] eta: 0:03:37 time: 3.4533 data: 3.2031 max mem: 22446 +eval (validation): [0] [20/63] eta: 0:00:24 time: 0.4365 data: 0.0395 max mem: 22446 +eval (validation): [0] [40/63] eta: 0:00:10 time: 0.3667 data: 0.0031 max mem: 22446 +eval (validation): [0] [60/63] eta: 0:00:01 time: 0.3620 data: 0.0035 max mem: 22446 +eval (validation): [0] [62/63] eta: 0:00:00 time: 0.3587 data: 0.0035 max mem: 22446 +eval (validation): [0] Total time: 0:00:27 (0.4409 s / it) +cv: [0] best hparam: (26, 1.0) (044) ('044_lr2.6e+01_wd1.0e+00') loss: 0.040 acc: 0.988 f1: 0.985 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/eval_v2/hcpya_task21__patch__attn/checkpoint-best.pth +train: [1] [ 0/400] eta: 0:23:17 lr: nan time: 3.4943 data: 3.0980 max mem: 22446 +train: [1] [ 20/400] eta: 0:03:57 lr: 0.000063 loss: 1.3604 (1.3824) grad: 0.1716 (0.1719) time: 0.4827 data: 0.0022 max mem: 22446 +train: [1] [ 40/400] eta: 0:03:17 lr: 0.000066 loss: 1.3596 (1.3591) grad: 0.1703 (0.1702) time: 0.4676 data: 0.0038 max mem: 22446 +train: [1] [ 60/400] eta: 0:02:55 lr: 0.000069 loss: 1.3093 (1.3372) grad: 0.1632 (0.1665) time: 0.4480 data: 0.0036 max mem: 22446 +train: [1] [ 80/400] eta: 0:02:40 lr: 0.000072 loss: 1.2774 (1.3200) grad: 0.1542 (0.1642) time: 0.4562 data: 0.0034 max mem: 22446 +train: [1] [100/400] eta: 0:02:28 lr: 0.000075 loss: 1.2527 (1.3078) grad: 0.1571 (0.1638) time: 0.4637 data: 0.0036 max mem: 22446 +train: [1] [120/400] eta: 0:02:16 lr: 0.000078 loss: 1.2315 (1.2911) grad: 0.1549 (0.1629) time: 0.4624 data: 0.0037 max mem: 22446 +train: [1] [140/400] eta: 0:02:05 lr: 0.000081 loss: 1.1902 (1.2763) grad: 0.1523 (0.1612) time: 0.4500 data: 0.0036 max mem: 22446 +train: [1] [160/400] eta: 0:01:54 lr: 0.000084 loss: 1.1558 (1.2601) grad: 0.1464 (0.1598) time: 0.4502 data: 0.0035 max mem: 22446 +train: [1] [180/400] eta: 0:01:44 lr: 0.000087 loss: 1.1453 (1.2462) grad: 0.1510 (0.1591) time: 0.4533 data: 0.0034 max mem: 22446 +train: [1] [200/400] eta: 0:01:34 lr: 0.000090 loss: 1.1143 (1.2320) grad: 0.1440 (0.1580) time: 0.4511 data: 0.0034 max mem: 22446 +train: [1] [220/400] eta: 0:01:24 lr: 0.000093 loss: 1.0736 (1.2167) grad: 0.1484 (0.1580) time: 0.4512 data: 0.0035 max mem: 22446 +train: [1] [240/400] eta: 0:01:15 lr: 0.000096 loss: 1.0620 (1.2031) grad: 0.1515 (0.1570) time: 0.4496 data: 0.0036 max mem: 22446 +train: [1] [260/400] eta: 0:01:05 lr: 0.000099 loss: 1.0447 (1.1908) grad: 0.1441 (0.1558) time: 0.4586 data: 0.0036 max mem: 22446 +train: [1] [280/400] eta: 0:00:56 lr: 0.000102 loss: 1.0167 (1.1778) grad: 0.1408 (0.1552) time: 0.4502 data: 0.0036 max mem: 22446 +train: [1] [300/400] eta: 0:00:47 lr: 0.000105 loss: 0.9978 (1.1655) grad: 0.1346 (0.1537) time: 0.6330 data: 0.1747 max mem: 22446 +train: [1] [320/400] eta: 0:00:38 lr: 0.000108 loss: 0.9791 (1.1540) grad: 0.1341 (0.1527) time: 0.4706 data: 0.0030 max mem: 22446 +train: [1] [340/400] eta: 0:00:28 lr: 0.000111 loss: 0.9560 (1.1416) grad: 0.1335 (0.1514) time: 0.4545 data: 0.0035 max mem: 22446 +train: [1] [360/400] eta: 0:00:19 lr: 0.000114 loss: 0.9497 (1.1310) grad: 0.1322 (0.1502) time: 0.4481 data: 0.0035 max mem: 22446 +train: [1] [380/400] eta: 0:00:09 lr: 0.000117 loss: 0.9284 (1.1204) grad: 0.1320 (0.1493) time: 0.4506 data: 0.0034 max mem: 22446 +train: [1] [399/400] eta: 0:00:00 lr: 0.000120 loss: 0.9189 (1.1104) grad: 0.1298 (0.1483) time: 0.4699 data: 0.0034 max mem: 22446 +train: [1] Total time: 0:03:09 (0.4740 s / it) +train: [1] Summary: lr: 0.000120 loss: 0.9189 (1.1104) grad: 0.1298 (0.1483) +eval (validation): [1] [ 0/63] eta: 0:03:27 time: 3.2921 data: 3.0605 max mem: 22446 +eval (validation): [1] [20/63] eta: 0:00:22 time: 0.3805 data: 0.0035 max mem: 22446 +eval (validation): [1] [40/63] eta: 0:00:09 time: 0.3430 data: 0.0033 max mem: 22446 +eval (validation): [1] [60/63] eta: 0:00:01 time: 0.3312 data: 0.0030 max mem: 22446 +eval (validation): [1] [62/63] eta: 0:00:00 time: 0.3273 data: 0.0031 max mem: 22446 +eval (validation): [1] Total time: 0:00:25 (0.4013 s / it) +cv: [1] best hparam: (9.8, 1.0) (038) ('038_lr9.8e+00_wd1.0e+00') loss: 0.029 acc: 0.991 f1: 0.989 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/eval_v2/hcpya_task21__patch__attn/checkpoint-best.pth +train: [2] [ 0/400] eta: 0:22:30 lr: nan time: 3.3772 data: 2.9721 max mem: 22446 +train: [2] [ 20/400] eta: 0:03:54 lr: 0.000123 loss: 0.8453 (0.8645) grad: 0.1375 (0.1365) time: 0.4789 data: 0.0032 max mem: 22446 +train: [2] [ 40/400] eta: 0:03:18 lr: 0.000126 loss: 0.8665 (0.8738) grad: 0.1394 (0.1414) time: 0.4848 data: 0.0036 max mem: 22446 +train: [2] [ 60/400] eta: 0:02:56 lr: 0.000129 loss: 0.8665 (0.8669) grad: 0.1459 (0.1476) time: 0.4519 data: 0.0037 max mem: 22446 +train: [2] [ 80/400] eta: 0:02:41 lr: 0.000132 loss: 0.8660 (0.8648) grad: 0.1449 (0.1476) time: 0.4590 data: 0.0033 max mem: 22446 +train: [2] [100/400] eta: 0:02:29 lr: 0.000135 loss: 0.8294 (0.8582) grad: 0.1421 (0.1462) time: 0.4682 data: 0.0035 max mem: 22446 +train: [2] [120/400] eta: 0:02:17 lr: 0.000138 loss: 0.8183 (0.8561) grad: 0.1492 (0.1503) time: 0.4539 data: 0.0036 max mem: 22446 +train: [2] [140/400] eta: 0:02:05 lr: 0.000141 loss: 0.8221 (0.8530) grad: 0.1631 (0.1573) time: 0.4492 data: 0.0034 max mem: 22446 +train: [2] [160/400] eta: 0:01:55 lr: 0.000144 loss: 0.8221 (0.8533) grad: 0.1729 (0.1626) time: 0.4494 data: 0.0035 max mem: 22446 +train: [2] [180/400] eta: 0:01:45 lr: 0.000147 loss: 0.8040 (0.8492) grad: 0.1640 (0.1636) time: 0.4558 data: 0.0036 max mem: 22446 +train: [2] [200/400] eta: 0:01:34 lr: 0.000150 loss: 0.7908 (0.8419) grad: 0.1605 (0.1657) time: 0.4517 data: 0.0036 max mem: 22446 +train: [2] [220/400] eta: 0:01:25 lr: 0.000153 loss: 0.8073 (0.8424) grad: 0.2000 (0.1703) time: 0.4545 data: 0.0035 max mem: 22446 +train: [2] [240/400] eta: 0:01:15 lr: 0.000156 loss: 0.8159 (0.8378) grad: 0.2007 (0.1724) time: 0.4502 data: 0.0034 max mem: 22446 +train: [2] [260/400] eta: 0:01:05 lr: 0.000159 loss: 0.7739 (0.8350) grad: 0.1971 (0.1761) time: 0.4496 data: 0.0034 max mem: 22446 +train: [2] [280/400] eta: 0:00:56 lr: 0.000162 loss: 0.7682 (0.8320) grad: 0.1971 (0.1765) time: 0.4445 data: 0.0034 max mem: 22446 +train: [2] [300/400] eta: 0:00:47 lr: 0.000165 loss: 0.7697 (0.8298) grad: 0.2060 (0.1792) time: 0.6023 data: 0.1689 max mem: 22446 +train: [2] [320/400] eta: 0:00:38 lr: 0.000168 loss: 0.7726 (0.8289) grad: 0.2198 (0.1830) time: 0.4633 data: 0.0033 max mem: 22446 +train: [2] [340/400] eta: 0:00:28 lr: 0.000171 loss: 0.8075 (0.8287) grad: 0.2198 (0.1857) time: 0.4515 data: 0.0035 max mem: 22446 +train: [2] [360/400] eta: 0:00:18 lr: 0.000174 loss: 0.8077 (0.8279) grad: 0.2058 (0.1866) time: 0.4508 data: 0.0035 max mem: 22446 +train: [2] [380/400] eta: 0:00:09 lr: 0.000177 loss: 0.7627 (0.8210) grad: 0.1883 (0.1871) time: 0.4617 data: 0.0033 max mem: 22446 +train: [2] [399/400] eta: 0:00:00 lr: 0.000180 loss: 0.6566 (0.8129) grad: 0.2017 (0.1891) time: 0.4667 data: 0.0035 max mem: 22446 +train: [2] Total time: 0:03:08 (0.4725 s / it) +train: [2] Summary: lr: 0.000180 loss: 0.6566 (0.8129) grad: 0.2017 (0.1891) +eval (validation): [2] [ 0/63] eta: 0:03:31 time: 3.3639 data: 3.0888 max mem: 22446 +eval (validation): [2] [20/63] eta: 0:00:22 time: 0.3818 data: 0.0032 max mem: 22446 +eval (validation): [2] [40/63] eta: 0:00:10 time: 0.3576 data: 0.0031 max mem: 22446 +eval (validation): [2] [60/63] eta: 0:00:01 time: 0.3413 data: 0.0034 max mem: 22446 +eval (validation): [2] [62/63] eta: 0:00:00 time: 0.3355 data: 0.0034 max mem: 22446 +eval (validation): [2] Total time: 0:00:25 (0.4109 s / it) +cv: [2] best hparam: (3.7, 1.0) (032) ('032_lr3.7e+00_wd1.0e+00') loss: 0.026 acc: 0.991 f1: 0.990 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/eval_v2/hcpya_task21__patch__attn/checkpoint-best.pth +train: [3] [ 0/400] eta: 0:22:43 lr: nan time: 3.4086 data: 3.0093 max mem: 22446 +train: [3] [ 20/400] eta: 0:04:04 lr: 0.000183 loss: 0.5919 (0.6147) grad: 0.1914 (0.1919) time: 0.5060 data: 0.0040 max mem: 22446 +train: [3] [ 40/400] eta: 0:03:21 lr: 0.000186 loss: 0.6321 (0.6529) grad: 0.2025 (0.2173) time: 0.4715 data: 0.0036 max mem: 22446 +train: [3] [ 60/400] eta: 0:02:57 lr: 0.000189 loss: 0.6830 (0.6716) grad: 0.2220 (0.2247) time: 0.4451 data: 0.0034 max mem: 22446 +train: [3] [ 80/400] eta: 0:02:42 lr: 0.000192 loss: 0.6647 (0.6871) grad: 0.2151 (0.2191) time: 0.4677 data: 0.0034 max mem: 22446 +train: [3] [100/400] eta: 0:02:29 lr: 0.000195 loss: 0.6581 (0.6864) grad: 0.2151 (0.2207) time: 0.4610 data: 0.0037 max mem: 22446 +train: [3] [120/400] eta: 0:02:17 lr: 0.000198 loss: 0.6581 (0.6873) grad: 0.2135 (0.2172) time: 0.4471 data: 0.0035 max mem: 22446 +train: [3] [140/400] eta: 0:02:06 lr: 0.000201 loss: 0.7264 (0.7013) grad: 0.2027 (0.2226) time: 0.4549 data: 0.0035 max mem: 22446 +train: [3] [160/400] eta: 0:01:55 lr: 0.000204 loss: 0.7546 (0.7025) grad: 0.2350 (0.2289) time: 0.4484 data: 0.0034 max mem: 22446 +train: [3] [180/400] eta: 0:01:44 lr: 0.000207 loss: 0.7073 (0.7028) grad: 0.2350 (0.2295) time: 0.4453 data: 0.0035 max mem: 22446 +train: [3] [200/400] eta: 0:01:34 lr: 0.000210 loss: 0.7073 (0.7080) grad: 0.2280 (0.2296) time: 0.4439 data: 0.0035 max mem: 22446 +train: [3] [220/400] eta: 0:01:24 lr: 0.000213 loss: 0.6245 (0.6991) grad: 0.2339 (0.2338) time: 0.4472 data: 0.0035 max mem: 22446 +train: [3] [240/400] eta: 0:01:15 lr: 0.000216 loss: 0.6519 (0.7073) grad: 0.2427 (0.2367) time: 0.4431 data: 0.0034 max mem: 22446 +train: [3] [260/400] eta: 0:01:05 lr: 0.000219 loss: 0.6608 (0.7058) grad: 0.2775 (0.2399) time: 0.4482 data: 0.0034 max mem: 22446 +train: [3] [280/400] eta: 0:00:55 lr: 0.000222 loss: 0.6608 (0.7078) grad: 0.2795 (0.2432) time: 0.4467 data: 0.0035 max mem: 22446 +train: [3] [300/400] eta: 0:00:47 lr: 0.000225 loss: 0.7640 (0.7090) grad: 0.2751 (0.2472) time: 0.6023 data: 0.1687 max mem: 22446 +train: [3] [320/400] eta: 0:00:37 lr: 0.000228 loss: 0.6987 (0.7102) grad: 0.2990 (0.2573) time: 0.4643 data: 0.0033 max mem: 22446 +train: [3] [340/400] eta: 0:00:28 lr: 0.000231 loss: 0.6353 (0.7048) grad: 0.3280 (0.2614) time: 0.4475 data: 0.0036 max mem: 22446 +train: [3] [360/400] eta: 0:00:18 lr: 0.000234 loss: 0.5788 (0.6994) grad: 0.3366 (0.2685) time: 0.4442 data: 0.0036 max mem: 22446 +train: [3] [380/400] eta: 0:00:09 lr: 0.000237 loss: 0.5913 (0.7011) grad: 0.3544 (0.2715) time: 0.4593 data: 0.0035 max mem: 22446 +train: [3] [399/400] eta: 0:00:00 lr: 0.000240 loss: 0.7066 (0.7044) grad: 0.3544 (0.2800) time: 0.4577 data: 0.0036 max mem: 22446 +train: [3] Total time: 0:03:08 (0.4702 s / it) +train: [3] Summary: lr: 0.000240 loss: 0.7066 (0.7044) grad: 0.3544 (0.2800) +eval (validation): [3] [ 0/63] eta: 0:03:25 time: 3.2652 data: 3.0343 max mem: 22446 +eval (validation): [3] [20/63] eta: 0:00:21 time: 0.3632 data: 0.0030 max mem: 22446 +eval (validation): [3] [40/63] eta: 0:00:09 time: 0.3620 data: 0.0034 max mem: 22446 +eval (validation): [3] [60/63] eta: 0:00:01 time: 0.3344 data: 0.0034 max mem: 22446 +eval (validation): [3] [62/63] eta: 0:00:00 time: 0.3326 data: 0.0035 max mem: 22446 +eval (validation): [3] Total time: 0:00:25 (0.4034 s / it) +cv: [3] best hparam: (3.1, 1.0) (031) ('031_lr3.1e+00_wd1.0e+00') loss: 0.026 acc: 0.992 f1: 0.992 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/eval_v2/hcpya_task21__patch__attn/checkpoint-best.pth +train: [4] [ 0/400] eta: 0:22:16 lr: nan time: 3.3418 data: 2.9834 max mem: 22446 +train: [4] [ 20/400] eta: 0:03:56 lr: 0.000243 loss: 0.6188 (0.7279) grad: 0.2822 (0.3511) time: 0.4863 data: 0.0026 max mem: 22446 +train: [4] [ 40/400] eta: 0:03:16 lr: 0.000246 loss: 0.6969 (0.7280) grad: 0.3423 (0.3714) time: 0.4655 data: 0.0032 max mem: 22446 +train: [4] [ 60/400] eta: 0:02:54 lr: 0.000249 loss: 0.6261 (0.6858) grad: 0.3512 (0.3653) time: 0.4432 data: 0.0035 max mem: 22446 +train: [4] [ 80/400] eta: 0:02:40 lr: 0.000252 loss: 0.5846 (0.6866) grad: 0.3453 (0.3575) time: 0.4733 data: 0.0035 max mem: 22446 +train: [4] [100/400] eta: 0:02:28 lr: 0.000255 loss: 0.5955 (0.6852) grad: 0.3453 (0.3598) time: 0.4665 data: 0.0036 max mem: 22446 +train: [4] [120/400] eta: 0:02:16 lr: 0.000258 loss: 0.6348 (0.7004) grad: 0.3510 (0.3616) time: 0.4500 data: 0.0036 max mem: 22446 +train: [4] [140/400] eta: 0:02:05 lr: 0.000261 loss: 0.6497 (0.7021) grad: 0.3770 (0.3772) time: 0.4615 data: 0.0035 max mem: 22446 +train: [4] [160/400] eta: 0:01:55 lr: 0.000264 loss: 0.6936 (0.7361) grad: 0.3756 (0.3904) time: 0.4491 data: 0.0035 max mem: 22446 +train: [4] [180/400] eta: 0:01:44 lr: 0.000267 loss: 0.8331 (0.7369) grad: 0.3662 (0.3926) time: 0.4440 data: 0.0035 max mem: 22446 +train: [4] [200/400] eta: 0:01:34 lr: 0.000270 loss: 0.7342 (0.7393) grad: 0.3780 (0.3978) time: 0.4491 data: 0.0036 max mem: 22446 +train: [4] [220/400] eta: 0:01:24 lr: 0.000273 loss: 0.7379 (0.7499) grad: 0.4100 (0.4033) time: 0.4602 data: 0.0035 max mem: 22446 +train: [4] [240/400] eta: 0:01:15 lr: 0.000276 loss: 0.6383 (0.7484) grad: 0.4100 (0.4025) time: 0.4554 data: 0.0035 max mem: 22446 +train: [4] [260/400] eta: 0:01:05 lr: 0.000279 loss: 0.6017 (0.7686) grad: 0.4025 (0.4052) time: 0.4403 data: 0.0033 max mem: 22446 +train: [4] [280/400] eta: 0:00:55 lr: 0.000282 loss: 0.8584 (0.7762) grad: 0.4270 (0.4135) time: 0.4431 data: 0.0034 max mem: 22446 +train: [4] [300/400] eta: 0:00:47 lr: 0.000285 loss: 0.6960 (0.7809) grad: 0.4537 (0.4194) time: 0.6043 data: 0.1720 max mem: 22446 +train: [4] [320/400] eta: 0:00:37 lr: 0.000288 loss: 0.4100 (0.7639) grad: 0.3978 (0.4164) time: 0.4499 data: 0.0032 max mem: 22446 +train: [4] [340/400] eta: 0:00:28 lr: 0.000291 loss: 0.4320 (0.7517) grad: 0.3811 (0.4164) time: 0.4542 data: 0.0035 max mem: 22446 +train: [4] [360/400] eta: 0:00:18 lr: 0.000294 loss: 0.5047 (0.7510) grad: 0.3819 (0.4160) time: 0.4493 data: 0.0033 max mem: 22446 +train: [4] [380/400] eta: 0:00:09 lr: 0.000297 loss: 0.6336 (0.7585) grad: 0.4341 (0.4225) time: 0.4746 data: 0.0036 max mem: 22446 +train: [4] [399/400] eta: 0:00:00 lr: 0.000300 loss: 0.7170 (0.7557) grad: 0.4400 (0.4286) time: 0.4585 data: 0.0035 max mem: 22446 +train: [4] Total time: 0:03:08 (0.4714 s / it) +train: [4] Summary: lr: 0.000300 loss: 0.7170 (0.7557) grad: 0.4400 (0.4286) +eval (validation): [4] [ 0/63] eta: 0:03:27 time: 3.2890 data: 3.0525 max mem: 22446 +eval (validation): [4] [20/63] eta: 0:00:20 time: 0.3406 data: 0.0035 max mem: 22446 +eval (validation): [4] [40/63] eta: 0:00:09 time: 0.3571 data: 0.0030 max mem: 22446 +eval (validation): [4] [60/63] eta: 0:00:01 time: 0.3304 data: 0.0034 max mem: 22446 +eval (validation): [4] [62/63] eta: 0:00:00 time: 0.3277 data: 0.0034 max mem: 22446 +eval (validation): [4] Total time: 0:00:24 (0.3931 s / it) +cv: [4] best hparam: (1.2, 1.0) (025) ('025_lr1.2e+00_wd1.0e+00') loss: 0.031 acc: 0.990 f1: 0.988 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [5] [ 0/400] eta: 0:22:25 lr: nan time: 3.3644 data: 2.9556 max mem: 22446 +train: [5] [ 20/400] eta: 0:03:55 lr: 0.000300 loss: 0.4399 (0.5726) grad: 0.3227 (0.3586) time: 0.4825 data: 0.0026 max mem: 22446 +train: [5] [ 40/400] eta: 0:03:18 lr: 0.000300 loss: 0.5258 (0.6487) grad: 0.3419 (0.3822) time: 0.4772 data: 0.0037 max mem: 22446 +train: [5] [ 60/400] eta: 0:02:55 lr: 0.000300 loss: 0.6925 (0.7166) grad: 0.3869 (0.3874) time: 0.4458 data: 0.0035 max mem: 22446 +train: [5] [ 80/400] eta: 0:02:41 lr: 0.000300 loss: 0.5960 (0.7082) grad: 0.3686 (0.3929) time: 0.4696 data: 0.0034 max mem: 22446 +train: [5] [100/400] eta: 0:02:28 lr: 0.000300 loss: 0.5576 (0.7224) grad: 0.3682 (0.3852) time: 0.4576 data: 0.0035 max mem: 22446 +train: [5] [120/400] eta: 0:02:16 lr: 0.000300 loss: 0.7302 (0.7428) grad: 0.3827 (0.3886) time: 0.4408 data: 0.0036 max mem: 22446 +train: [5] [140/400] eta: 0:02:05 lr: 0.000300 loss: 0.6576 (0.7432) grad: 0.4164 (0.4019) time: 0.4484 data: 0.0037 max mem: 22446 +train: [5] [160/400] eta: 0:01:54 lr: 0.000299 loss: 0.6576 (0.7666) grad: 0.4316 (0.4054) time: 0.4493 data: 0.0036 max mem: 22446 +train: [5] [180/400] eta: 0:01:44 lr: 0.000299 loss: 0.6807 (0.7582) grad: 0.4529 (0.4131) time: 0.4501 data: 0.0035 max mem: 22446 +train: [5] [200/400] eta: 0:01:34 lr: 0.000299 loss: 0.5179 (0.7578) grad: 0.3812 (0.4162) time: 0.4554 data: 0.0034 max mem: 22446 +train: [5] [220/400] eta: 0:01:24 lr: 0.000299 loss: 0.7275 (0.7665) grad: 0.3663 (0.4222) time: 0.4515 data: 0.0036 max mem: 22446 +train: [5] [240/400] eta: 0:01:14 lr: 0.000299 loss: 0.6404 (0.7566) grad: 0.3957 (0.4230) time: 0.4478 data: 0.0036 max mem: 22446 +train: [5] [260/400] eta: 0:01:05 lr: 0.000299 loss: 0.6404 (0.7784) grad: 0.4676 (0.4290) time: 0.4612 data: 0.0035 max mem: 22446 +train: [5] [280/400] eta: 0:00:55 lr: 0.000298 loss: 0.8143 (0.7850) grad: 0.4973 (0.4330) time: 0.4467 data: 0.0036 max mem: 22446 +train: [5] [300/400] eta: 0:00:47 lr: 0.000298 loss: 0.6852 (0.7815) grad: 0.4460 (0.4368) time: 0.6034 data: 0.1695 max mem: 22446 +train: [5] [320/400] eta: 0:00:37 lr: 0.000298 loss: 0.6063 (0.7763) grad: 0.4270 (0.4356) time: 0.4602 data: 0.0029 max mem: 22446 +train: [5] [340/400] eta: 0:00:28 lr: 0.000298 loss: 0.5540 (0.7782) grad: 0.3743 (0.4324) time: 0.4533 data: 0.0034 max mem: 22446 +train: [5] [360/400] eta: 0:00:18 lr: 0.000297 loss: 0.5916 (0.7728) grad: 0.3871 (0.4319) time: 0.4441 data: 0.0034 max mem: 22446 +train: [5] [380/400] eta: 0:00:09 lr: 0.000297 loss: 0.7946 (0.7828) grad: 0.4102 (0.4329) time: 0.4639 data: 0.0035 max mem: 22446 +train: [5] [399/400] eta: 0:00:00 lr: 0.000297 loss: 0.6130 (0.7703) grad: 0.3827 (0.4297) time: 0.4643 data: 0.0035 max mem: 22446 +train: [5] Total time: 0:03:08 (0.4711 s / it) +train: [5] Summary: lr: 0.000297 loss: 0.6130 (0.7703) grad: 0.3827 (0.4297) +eval (validation): [5] [ 0/63] eta: 0:03:25 time: 3.2663 data: 3.0282 max mem: 22446 +eval (validation): [5] [20/63] eta: 0:00:21 time: 0.3722 data: 0.0045 max mem: 22446 +eval (validation): [5] [40/63] eta: 0:00:10 time: 0.4043 data: 0.0031 max mem: 22446 +eval (validation): [5] [60/63] eta: 0:00:01 time: 0.3390 data: 0.0034 max mem: 22446 +eval (validation): [5] [62/63] eta: 0:00:00 time: 0.3360 data: 0.0035 max mem: 22446 +eval (validation): [5] Total time: 0:00:26 (0.4203 s / it) +cv: [5] best hparam: (2.7, 1.0) (030) ('030_lr2.7e+00_wd1.0e+00') loss: 0.027 acc: 0.992 f1: 0.989 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [6] [ 0/400] eta: 0:22:30 lr: nan time: 3.3764 data: 3.0229 max mem: 22446 +train: [6] [ 20/400] eta: 0:03:54 lr: 0.000296 loss: 0.5333 (0.5446) grad: 0.3785 (0.4232) time: 0.4795 data: 0.0035 max mem: 22446 +train: [6] [ 40/400] eta: 0:03:14 lr: 0.000296 loss: 0.5333 (0.5932) grad: 0.3785 (0.3926) time: 0.4570 data: 0.0035 max mem: 22446 +train: [6] [ 60/400] eta: 0:02:52 lr: 0.000296 loss: 0.4936 (0.5796) grad: 0.3692 (0.3884) time: 0.4437 data: 0.0034 max mem: 22446 +train: [6] [ 80/400] eta: 0:02:38 lr: 0.000295 loss: 0.5558 (0.5972) grad: 0.3692 (0.3855) time: 0.4598 data: 0.0034 max mem: 22446 +train: [6] [100/400] eta: 0:02:26 lr: 0.000295 loss: 0.6147 (0.5884) grad: 0.3887 (0.3905) time: 0.4561 data: 0.0036 max mem: 22446 +train: [6] [120/400] eta: 0:02:15 lr: 0.000295 loss: 0.5252 (0.5728) grad: 0.3907 (0.3899) time: 0.4527 data: 0.0035 max mem: 22446 +train: [6] [140/400] eta: 0:02:04 lr: 0.000294 loss: 0.4438 (0.5762) grad: 0.3771 (0.3861) time: 0.4498 data: 0.0034 max mem: 22446 +train: [6] [160/400] eta: 0:01:53 lr: 0.000294 loss: 0.4511 (0.5665) grad: 0.3722 (0.3871) time: 0.4496 data: 0.0035 max mem: 22446 +train: [6] [180/400] eta: 0:01:43 lr: 0.000293 loss: 0.4388 (0.5655) grad: 0.3722 (0.3893) time: 0.4496 data: 0.0036 max mem: 22446 +train: [6] [200/400] eta: 0:01:33 lr: 0.000293 loss: 0.4388 (0.5970) grad: 0.3731 (0.3904) time: 0.4510 data: 0.0035 max mem: 22446 +train: [6] [220/400] eta: 0:01:24 lr: 0.000292 loss: 0.4488 (0.5868) grad: 0.3689 (0.3855) time: 0.4513 data: 0.0034 max mem: 22446 +train: [6] [240/400] eta: 0:01:14 lr: 0.000292 loss: 0.3218 (0.5779) grad: 0.2805 (0.3799) time: 0.4524 data: 0.0034 max mem: 22446 +train: [6] [260/400] eta: 0:01:05 lr: 0.000291 loss: 0.3718 (0.5679) grad: 0.3226 (0.3777) time: 0.4482 data: 0.0035 max mem: 22446 +train: [6] [280/400] eta: 0:00:55 lr: 0.000291 loss: 0.4652 (0.5746) grad: 0.3526 (0.3776) time: 0.4535 data: 0.0037 max mem: 22446 +train: [6] [300/400] eta: 0:00:47 lr: 0.000290 loss: 0.4782 (0.5698) grad: 0.3610 (0.3757) time: 0.6029 data: 0.1697 max mem: 22446 +train: [6] [320/400] eta: 0:00:37 lr: 0.000290 loss: 0.4054 (0.5645) grad: 0.3246 (0.3734) time: 0.4569 data: 0.0028 max mem: 22446 +train: [6] [340/400] eta: 0:00:28 lr: 0.000289 loss: 0.3380 (0.5583) grad: 0.3162 (0.3791) time: 0.4482 data: 0.0035 max mem: 22446 +train: [6] [360/400] eta: 0:00:18 lr: 0.000288 loss: 0.3262 (0.5523) grad: 0.3148 (0.3789) time: 0.4440 data: 0.0034 max mem: 22446 +train: [6] [380/400] eta: 0:00:09 lr: 0.000288 loss: 0.3925 (0.5472) grad: 0.3043 (0.3759) time: 0.4630 data: 0.0035 max mem: 22446 +train: [6] [399/400] eta: 0:00:00 lr: 0.000287 loss: 0.3326 (0.5333) grad: 0.2879 (0.3720) time: 0.4560 data: 0.0035 max mem: 22446 +train: [6] Total time: 0:03:07 (0.4688 s / it) +train: [6] Summary: lr: 0.000287 loss: 0.3326 (0.5333) grad: 0.2879 (0.3720) +eval (validation): [6] [ 0/63] eta: 0:03:29 time: 3.3321 data: 3.0624 max mem: 22446 +eval (validation): [6] [20/63] eta: 0:00:21 time: 0.3635 data: 0.0034 max mem: 22446 +eval (validation): [6] [40/63] eta: 0:00:10 time: 0.3829 data: 0.0035 max mem: 22446 +eval (validation): [6] [60/63] eta: 0:00:01 time: 0.3285 data: 0.0033 max mem: 22446 +eval (validation): [6] [62/63] eta: 0:00:00 time: 0.3265 data: 0.0033 max mem: 22446 +eval (validation): [6] Total time: 0:00:25 (0.4091 s / it) +cv: [6] best hparam: (1, 1.0) (024) ('024_lr1.0e+00_wd1.0e+00') loss: 0.024 acc: 0.993 f1: 0.991 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/eval_v2/hcpya_task21__patch__attn/checkpoint-best.pth +train: [7] [ 0/400] eta: 0:22:44 lr: nan time: 3.4103 data: 3.0125 max mem: 22446 +train: [7] [ 20/400] eta: 0:04:03 lr: 0.000286 loss: 0.3702 (0.3997) grad: 0.2916 (0.3276) time: 0.5023 data: 0.0033 max mem: 22446 +train: [7] [ 40/400] eta: 0:03:18 lr: 0.000286 loss: 0.3075 (0.3463) grad: 0.2750 (0.3473) time: 0.4599 data: 0.0038 max mem: 22446 +train: [7] [ 60/400] eta: 0:02:57 lr: 0.000285 loss: 0.2979 (0.3698) grad: 0.2530 (0.3263) time: 0.4612 data: 0.0033 max mem: 22446 +train: [7] [ 80/400] eta: 0:02:42 lr: 0.000284 loss: 0.2815 (0.3622) grad: 0.2800 (0.3143) time: 0.4690 data: 0.0035 max mem: 22446 +train: [7] [100/400] eta: 0:02:29 lr: 0.000284 loss: 0.2777 (0.3674) grad: 0.2951 (0.3188) time: 0.4489 data: 0.0035 max mem: 22446 +train: [7] [120/400] eta: 0:02:17 lr: 0.000283 loss: 0.3765 (0.3732) grad: 0.3262 (0.3206) time: 0.4542 data: 0.0035 max mem: 22446 +train: [7] [140/400] eta: 0:02:06 lr: 0.000282 loss: 0.3559 (0.3789) grad: 0.2907 (0.3200) time: 0.4526 data: 0.0033 max mem: 22446 +train: [7] [160/400] eta: 0:01:55 lr: 0.000282 loss: 0.3559 (0.3854) grad: 0.2906 (0.3179) time: 0.4501 data: 0.0035 max mem: 22446 +train: [7] [180/400] eta: 0:01:45 lr: 0.000281 loss: 0.3215 (0.3875) grad: 0.2906 (0.3173) time: 0.4532 data: 0.0035 max mem: 22446 +train: [7] [200/400] eta: 0:01:35 lr: 0.000280 loss: 0.2796 (0.3846) grad: 0.2943 (0.3168) time: 0.4538 data: 0.0035 max mem: 22446 +train: [7] [220/400] eta: 0:01:25 lr: 0.000279 loss: 0.2796 (0.3913) grad: 0.3021 (0.3174) time: 0.4503 data: 0.0034 max mem: 22446 +train: [7] [240/400] eta: 0:01:15 lr: 0.000278 loss: 0.3547 (0.3997) grad: 0.3405 (0.3223) time: 0.4456 data: 0.0036 max mem: 22446 +train: [7] [260/400] eta: 0:01:05 lr: 0.000278 loss: 0.3547 (0.3954) grad: 0.3502 (0.3241) time: 0.4457 data: 0.0035 max mem: 22446 +train: [7] [280/400] eta: 0:00:56 lr: 0.000277 loss: 0.3500 (0.4081) grad: 0.3179 (0.3234) time: 0.4438 data: 0.0036 max mem: 22446 +train: [7] [300/400] eta: 0:00:47 lr: 0.000276 loss: 0.3500 (0.4061) grad: 0.2845 (0.3193) time: 0.6077 data: 0.1712 max mem: 22446 +train: [7] [320/400] eta: 0:00:38 lr: 0.000275 loss: 0.3183 (0.4046) grad: 0.2533 (0.3161) time: 0.4731 data: 0.0033 max mem: 22446 +train: [7] [340/400] eta: 0:00:28 lr: 0.000274 loss: 0.2021 (0.3938) grad: 0.2263 (0.3101) time: 0.4412 data: 0.0037 max mem: 22446 +train: [7] [360/400] eta: 0:00:18 lr: 0.000273 loss: 0.1945 (0.3867) grad: 0.2168 (0.3059) time: 0.4484 data: 0.0037 max mem: 22446 +train: [7] [380/400] eta: 0:00:09 lr: 0.000272 loss: 0.1994 (0.3815) grad: 0.2370 (0.3038) time: 0.4751 data: 0.0038 max mem: 22446 +train: [7] [399/400] eta: 0:00:00 lr: 0.000271 loss: 0.1952 (0.3722) grad: 0.2200 (0.2984) time: 0.4627 data: 0.0036 max mem: 22446 +train: [7] Total time: 0:03:08 (0.4724 s / it) +train: [7] Summary: lr: 0.000271 loss: 0.1952 (0.3722) grad: 0.2200 (0.2984) +eval (validation): [7] [ 0/63] eta: 0:03:29 time: 3.3256 data: 3.0413 max mem: 22446 +eval (validation): [7] [20/63] eta: 0:00:22 time: 0.3816 data: 0.0037 max mem: 22446 +eval (validation): [7] [40/63] eta: 0:00:10 time: 0.3501 data: 0.0034 max mem: 22446 +eval (validation): [7] [60/63] eta: 0:00:01 time: 0.3293 data: 0.0032 max mem: 22446 +eval (validation): [7] [62/63] eta: 0:00:00 time: 0.3301 data: 0.0031 max mem: 22446 +eval (validation): [7] Total time: 0:00:25 (0.4041 s / it) +cv: [7] best hparam: (1.9, 1.0) (028) ('028_lr1.9e+00_wd1.0e+00') loss: 0.022 acc: 0.993 f1: 0.991 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [8] [ 0/400] eta: 0:23:13 lr: nan time: 3.4850 data: 3.0860 max mem: 22446 +train: [8] [ 20/400] eta: 0:04:05 lr: 0.000270 loss: 0.1860 (0.2333) grad: 0.2323 (0.2595) time: 0.5050 data: 0.0021 max mem: 22446 +train: [8] [ 40/400] eta: 0:03:19 lr: 0.000270 loss: 0.1599 (0.2251) grad: 0.2214 (0.2269) time: 0.4543 data: 0.0035 max mem: 22446 +train: [8] [ 60/400] eta: 0:02:55 lr: 0.000269 loss: 0.1797 (0.2296) grad: 0.2037 (0.2283) time: 0.4444 data: 0.0033 max mem: 22446 +train: [8] [ 80/400] eta: 0:02:41 lr: 0.000268 loss: 0.1842 (0.2273) grad: 0.2037 (0.2202) time: 0.4705 data: 0.0037 max mem: 22446 +train: [8] [100/400] eta: 0:02:28 lr: 0.000267 loss: 0.1946 (0.2344) grad: 0.2064 (0.2168) time: 0.4574 data: 0.0037 max mem: 22446 +train: [8] [120/400] eta: 0:02:16 lr: 0.000266 loss: 0.2490 (0.2504) grad: 0.2173 (0.2181) time: 0.4444 data: 0.0037 max mem: 22446 +train: [8] [140/400] eta: 0:02:05 lr: 0.000265 loss: 0.2388 (0.2468) grad: 0.2306 (0.2209) time: 0.4496 data: 0.0035 max mem: 22446 +train: [8] [160/400] eta: 0:01:54 lr: 0.000264 loss: 0.1799 (0.2397) grad: 0.1830 (0.2174) time: 0.4548 data: 0.0035 max mem: 22446 +train: [8] [180/400] eta: 0:01:44 lr: 0.000263 loss: 0.1727 (0.2423) grad: 0.1615 (0.2174) time: 0.4543 data: 0.0035 max mem: 22446 +train: [8] [200/400] eta: 0:01:34 lr: 0.000262 loss: 0.2328 (0.2419) grad: 0.2414 (0.2210) time: 0.4451 data: 0.0036 max mem: 22446 +train: [8] [220/400] eta: 0:01:24 lr: 0.000260 loss: 0.1856 (0.2408) grad: 0.2100 (0.2170) time: 0.4480 data: 0.0035 max mem: 22446 +train: [8] [240/400] eta: 0:01:15 lr: 0.000259 loss: 0.2128 (0.2440) grad: 0.1929 (0.2167) time: 0.4516 data: 0.0035 max mem: 22446 +train: [8] [260/400] eta: 0:01:05 lr: 0.000258 loss: 0.2249 (0.2447) grad: 0.2010 (0.2170) time: 0.4497 data: 0.0035 max mem: 22446 +train: [8] [280/400] eta: 0:00:55 lr: 0.000257 loss: 0.1624 (0.2471) grad: 0.2216 (0.2186) time: 0.4516 data: 0.0035 max mem: 22446 +train: [8] [300/400] eta: 0:00:47 lr: 0.000256 loss: 0.2418 (0.2578) grad: 0.2470 (0.2218) time: 0.6155 data: 0.1761 max mem: 22446 +train: [8] [320/400] eta: 0:00:38 lr: 0.000255 loss: 0.2421 (0.2546) grad: 0.2195 (0.2197) time: 0.4574 data: 0.0032 max mem: 22446 +train: [8] [340/400] eta: 0:00:28 lr: 0.000254 loss: 0.1872 (0.2515) grad: 0.1648 (0.2168) time: 0.4549 data: 0.0036 max mem: 22446 +train: [8] [360/400] eta: 0:00:18 lr: 0.000253 loss: 0.1472 (0.2468) grad: 0.1741 (0.2153) time: 0.4428 data: 0.0034 max mem: 22446 +train: [8] [380/400] eta: 0:00:09 lr: 0.000252 loss: 0.1510 (0.2447) grad: 0.1666 (0.2128) time: 0.4898 data: 0.0038 max mem: 22446 +train: [8] [399/400] eta: 0:00:00 lr: 0.000250 loss: 0.1579 (0.2411) grad: 0.1431 (0.2097) time: 0.4488 data: 0.0036 max mem: 22446 +train: [8] Total time: 0:03:08 (0.4724 s / it) +train: [8] Summary: lr: 0.000250 loss: 0.1579 (0.2411) grad: 0.1431 (0.2097) +eval (validation): [8] [ 0/63] eta: 0:03:31 time: 3.3629 data: 3.0831 max mem: 22446 +eval (validation): [8] [20/63] eta: 0:00:21 time: 0.3679 data: 0.0028 max mem: 22446 +eval (validation): [8] [40/63] eta: 0:00:10 time: 0.3608 data: 0.0036 max mem: 22446 +eval (validation): [8] [60/63] eta: 0:00:01 time: 0.3312 data: 0.0034 max mem: 22446 +eval (validation): [8] [62/63] eta: 0:00:00 time: 0.3272 data: 0.0034 max mem: 22446 +eval (validation): [8] Total time: 0:00:25 (0.4048 s / it) +cv: [8] best hparam: (3.1, 1.0) (031) ('031_lr3.1e+00_wd1.0e+00') loss: 0.023 acc: 0.993 f1: 0.992 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/eval_v2/hcpya_task21__patch__attn/checkpoint-best.pth +train: [9] [ 0/400] eta: 0:23:07 lr: nan time: 3.4688 data: 3.1225 max mem: 22446 +train: [9] [ 20/400] eta: 0:03:58 lr: 0.000249 loss: 0.1940 (0.2241) grad: 0.1993 (0.1998) time: 0.4844 data: 0.0038 max mem: 22446 +train: [9] [ 40/400] eta: 0:03:11 lr: 0.000248 loss: 0.1989 (0.2142) grad: 0.1993 (0.2031) time: 0.4311 data: 0.0035 max mem: 22446 +train: [9] [ 60/400] eta: 0:02:51 lr: 0.000247 loss: 0.1823 (0.2057) grad: 0.1683 (0.1849) time: 0.4454 data: 0.0034 max mem: 22446 +train: [9] [ 80/400] eta: 0:02:37 lr: 0.000246 loss: 0.1471 (0.1966) grad: 0.1448 (0.1762) time: 0.4572 data: 0.0036 max mem: 22446 +train: [9] [100/400] eta: 0:02:24 lr: 0.000244 loss: 0.1260 (0.1858) grad: 0.1495 (0.1743) time: 0.4441 data: 0.0036 max mem: 22446 +train: [9] [120/400] eta: 0:02:13 lr: 0.000243 loss: 0.1383 (0.1829) grad: 0.1495 (0.1715) time: 0.4431 data: 0.0035 max mem: 22446 +train: [9] [140/400] eta: 0:02:02 lr: 0.000242 loss: 0.1254 (0.1815) grad: 0.1527 (0.1803) time: 0.4453 data: 0.0037 max mem: 22446 +train: [9] [160/400] eta: 0:01:52 lr: 0.000241 loss: 0.1218 (0.1759) grad: 0.1847 (0.1790) time: 0.4537 data: 0.0037 max mem: 22446 +train: [9] [180/400] eta: 0:01:42 lr: 0.000240 loss: 0.1125 (0.1734) grad: 0.1546 (0.1771) time: 0.4434 data: 0.0036 max mem: 22446 +train: [9] [200/400] eta: 0:01:32 lr: 0.000238 loss: 0.1291 (0.1749) grad: 0.1742 (0.1793) time: 0.4401 data: 0.0036 max mem: 22446 +train: [9] [220/400] eta: 0:01:23 lr: 0.000237 loss: 0.1652 (0.1774) grad: 0.1978 (0.1822) time: 0.4485 data: 0.0035 max mem: 22446 +train: [9] [240/400] eta: 0:01:13 lr: 0.000236 loss: 0.1478 (0.1753) grad: 0.1926 (0.1795) time: 0.4418 data: 0.0035 max mem: 22446 +train: [9] [260/400] eta: 0:01:04 lr: 0.000234 loss: 0.1431 (0.1775) grad: 0.1438 (0.1791) time: 0.4469 data: 0.0036 max mem: 22446 +train: [9] [280/400] eta: 0:00:54 lr: 0.000233 loss: 0.1532 (0.1782) grad: 0.1528 (0.1777) time: 0.4406 data: 0.0036 max mem: 22446 +train: [9] [300/400] eta: 0:00:46 lr: 0.000232 loss: 0.1335 (0.1774) grad: 0.1528 (0.1773) time: 0.5953 data: 0.1695 max mem: 22446 +train: [9] [320/400] eta: 0:00:37 lr: 0.000230 loss: 0.1286 (0.1747) grad: 0.1661 (0.1770) time: 0.4741 data: 0.0039 max mem: 22446 +train: [9] [340/400] eta: 0:00:27 lr: 0.000229 loss: 0.1452 (0.1775) grad: 0.1681 (0.1777) time: 0.4471 data: 0.0035 max mem: 22446 +train: [9] [360/400] eta: 0:00:18 lr: 0.000228 loss: 0.1486 (0.1755) grad: 0.1662 (0.1765) time: 0.4654 data: 0.0036 max mem: 22446 +train: [9] [380/400] eta: 0:00:09 lr: 0.000226 loss: 0.1220 (0.1729) grad: 0.1525 (0.1747) time: 0.4518 data: 0.0036 max mem: 22446 +train: [9] [399/400] eta: 0:00:00 lr: 0.000225 loss: 0.1157 (0.1703) grad: 0.1246 (0.1723) time: 0.4459 data: 0.0036 max mem: 22446 +train: [9] Total time: 0:03:06 (0.4651 s / it) +train: [9] Summary: lr: 0.000225 loss: 0.1157 (0.1703) grad: 0.1246 (0.1723) +eval (validation): [9] [ 0/63] eta: 0:03:23 time: 3.2350 data: 3.0007 max mem: 22446 +eval (validation): [9] [20/63] eta: 0:00:21 time: 0.3589 data: 0.0031 max mem: 22446 +eval (validation): [9] [40/63] eta: 0:00:10 time: 0.3731 data: 0.0038 max mem: 22446 +eval (validation): [9] [60/63] eta: 0:00:01 time: 0.3271 data: 0.0034 max mem: 22446 +eval (validation): [9] [62/63] eta: 0:00:00 time: 0.3278 data: 0.0033 max mem: 22446 +eval (validation): [9] Total time: 0:00:25 (0.4021 s / it) +cv: [9] best hparam: (14, 1.0) (040) ('040_lr1.4e+01_wd1.0e+00') loss: 0.207 acc: 0.993 f1: 0.993 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [10] [ 0/400] eta: 0:29:14 lr: nan time: 4.3856 data: 4.0279 max mem: 22446 +train: [10] [ 20/400] eta: 0:04:01 lr: 0.000224 loss: 0.1766 (0.1663) grad: 0.1550 (0.1519) time: 0.4472 data: 0.0022 max mem: 22446 +train: [10] [ 40/400] eta: 0:03:12 lr: 0.000222 loss: 0.1201 (0.1425) grad: 0.1311 (0.1417) time: 0.4303 data: 0.0034 max mem: 22446 +train: [10] [ 60/400] eta: 0:02:53 lr: 0.000221 loss: 0.1189 (0.1475) grad: 0.1316 (0.1436) time: 0.4557 data: 0.0034 max mem: 22446 +train: [10] [ 80/400] eta: 0:02:40 lr: 0.000220 loss: 0.1249 (0.1423) grad: 0.1515 (0.1512) time: 0.4812 data: 0.0038 max mem: 22446 +train: [10] [100/400] eta: 0:02:26 lr: 0.000218 loss: 0.1093 (0.1376) grad: 0.1164 (0.1447) time: 0.4395 data: 0.0035 max mem: 22446 +train: [10] [120/400] eta: 0:02:14 lr: 0.000217 loss: 0.1053 (0.1346) grad: 0.1057 (0.1413) time: 0.4387 data: 0.0036 max mem: 22446 +train: [10] [140/400] eta: 0:02:03 lr: 0.000215 loss: 0.1053 (0.1346) grad: 0.1351 (0.1425) time: 0.4419 data: 0.0036 max mem: 22446 +train: [10] [160/400] eta: 0:01:53 lr: 0.000214 loss: 0.1009 (0.1308) grad: 0.1351 (0.1403) time: 0.4430 data: 0.0037 max mem: 22446 +train: [10] [180/400] eta: 0:01:43 lr: 0.000213 loss: 0.0964 (0.1300) grad: 0.1235 (0.1388) time: 0.4406 data: 0.0036 max mem: 22446 +train: [10] [200/400] eta: 0:01:33 lr: 0.000211 loss: 0.1320 (0.1309) grad: 0.1412 (0.1393) time: 0.4482 data: 0.0034 max mem: 22446 +train: [10] [220/400] eta: 0:01:23 lr: 0.000210 loss: 0.1263 (0.1298) grad: 0.1171 (0.1359) time: 0.4446 data: 0.0035 max mem: 22446 +train: [10] [240/400] eta: 0:01:14 lr: 0.000208 loss: 0.1079 (0.1284) grad: 0.1072 (0.1348) time: 0.4509 data: 0.0037 max mem: 22446 +train: [10] [260/400] eta: 0:01:04 lr: 0.000207 loss: 0.0978 (0.1280) grad: 0.1443 (0.1354) time: 0.4416 data: 0.0035 max mem: 22446 +train: [10] [280/400] eta: 0:00:55 lr: 0.000205 loss: 0.0978 (0.1259) grad: 0.0986 (0.1345) time: 0.4463 data: 0.0035 max mem: 22446 +train: [10] [300/400] eta: 0:00:47 lr: 0.000204 loss: 0.1043 (0.1256) grad: 0.1083 (0.1343) time: 0.6098 data: 0.1783 max mem: 22446 +train: [10] [320/400] eta: 0:00:37 lr: 0.000202 loss: 0.0918 (0.1238) grad: 0.1180 (0.1330) time: 0.4494 data: 0.0029 max mem: 22446 +train: [10] [340/400] eta: 0:00:28 lr: 0.000201 loss: 0.0886 (0.1219) grad: 0.0990 (0.1309) time: 0.4321 data: 0.0033 max mem: 22446 +train: [10] [360/400] eta: 0:00:18 lr: 0.000199 loss: 0.0908 (0.1207) grad: 0.0879 (0.1292) time: 0.4541 data: 0.0034 max mem: 22446 +train: [10] [380/400] eta: 0:00:09 lr: 0.000198 loss: 0.0917 (0.1222) grad: 0.1181 (0.1294) time: 0.4572 data: 0.0035 max mem: 22446 +train: [10] [399/400] eta: 0:00:00 lr: 0.000196 loss: 0.0937 (0.1215) grad: 0.1141 (0.1275) time: 0.4466 data: 0.0035 max mem: 22446 +train: [10] Total time: 0:03:06 (0.4651 s / it) +train: [10] Summary: lr: 0.000196 loss: 0.0937 (0.1215) grad: 0.1141 (0.1275) +eval (validation): [10] [ 0/63] eta: 0:03:29 time: 3.3301 data: 3.0924 max mem: 22446 +eval (validation): [10] [20/63] eta: 0:00:21 time: 0.3703 data: 0.0037 max mem: 22446 +eval (validation): [10] [40/63] eta: 0:00:10 time: 0.3596 data: 0.0036 max mem: 22446 +eval (validation): [10] [60/63] eta: 0:00:01 time: 0.3163 data: 0.0021 max mem: 22446 +eval (validation): [10] [62/63] eta: 0:00:00 time: 0.3094 data: 0.0024 max mem: 22446 +eval (validation): [10] Total time: 0:00:25 (0.3986 s / it) +cv: [10] best hparam: (0.72, 1.0) (022) ('022_lr7.2e-01_wd1.0e+00') loss: 0.022 acc: 0.994 f1: 0.993 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/eval_v2/hcpya_task21__patch__attn/checkpoint-best.pth +train: [11] [ 0/400] eta: 0:23:51 lr: nan time: 3.5788 data: 3.1679 max mem: 22446 +train: [11] [ 20/400] eta: 0:04:03 lr: 0.000195 loss: 0.1019 (0.1284) grad: 0.0990 (0.0984) time: 0.4943 data: 0.0033 max mem: 22446 +train: [11] [ 40/400] eta: 0:03:14 lr: 0.000193 loss: 0.0909 (0.1208) grad: 0.0715 (0.0862) time: 0.4345 data: 0.0034 max mem: 22446 +train: [11] [ 60/400] eta: 0:02:55 lr: 0.000192 loss: 0.0920 (0.1179) grad: 0.0906 (0.0915) time: 0.4644 data: 0.0036 max mem: 22446 +train: [11] [ 80/400] eta: 0:02:39 lr: 0.000190 loss: 0.0930 (0.1123) grad: 0.0906 (0.0920) time: 0.4462 data: 0.0034 max mem: 22446 +train: [11] [100/400] eta: 0:02:26 lr: 0.000189 loss: 0.0845 (0.1080) grad: 0.0790 (0.0917) time: 0.4426 data: 0.0037 max mem: 22446 +train: [11] [120/400] eta: 0:02:14 lr: 0.000187 loss: 0.0805 (0.1048) grad: 0.0925 (0.0926) time: 0.4388 data: 0.0036 max mem: 22446 +train: [11] [140/400] eta: 0:02:03 lr: 0.000186 loss: 0.0893 (0.1058) grad: 0.0960 (0.0946) time: 0.4360 data: 0.0034 max mem: 22446 +train: [11] [160/400] eta: 0:01:52 lr: 0.000184 loss: 0.1041 (0.1070) grad: 0.0991 (0.0958) time: 0.4382 data: 0.0035 max mem: 22446 +train: [11] [180/400] eta: 0:01:42 lr: 0.000183 loss: 0.0995 (0.1062) grad: 0.1203 (0.1008) time: 0.4457 data: 0.0036 max mem: 22446 +train: [11] [200/400] eta: 0:01:32 lr: 0.000181 loss: 0.0829 (0.1065) grad: 0.1295 (0.1048) time: 0.4498 data: 0.0034 max mem: 22446 +train: [11] [220/400] eta: 0:01:23 lr: 0.000180 loss: 0.0803 (0.1050) grad: 0.1260 (0.1037) time: 0.4407 data: 0.0035 max mem: 22446 +train: [11] [240/400] eta: 0:01:13 lr: 0.000178 loss: 0.0851 (0.1042) grad: 0.0971 (0.1047) time: 0.4416 data: 0.0036 max mem: 22446 +train: [11] [260/400] eta: 0:01:04 lr: 0.000177 loss: 0.1073 (0.1060) grad: 0.1047 (0.1048) time: 0.4365 data: 0.0035 max mem: 22446 +train: [11] [280/400] eta: 0:00:55 lr: 0.000175 loss: 0.1073 (0.1054) grad: 0.0970 (0.1035) time: 0.4516 data: 0.0036 max mem: 22446 +train: [11] [300/400] eta: 0:00:46 lr: 0.000174 loss: 0.0943 (0.1050) grad: 0.0837 (0.1021) time: 0.6094 data: 0.1800 max mem: 22446 +train: [11] [320/400] eta: 0:00:37 lr: 0.000172 loss: 0.0872 (0.1044) grad: 0.0763 (0.1007) time: 0.4448 data: 0.0031 max mem: 22446 +train: [11] [340/400] eta: 0:00:27 lr: 0.000170 loss: 0.0806 (0.1034) grad: 0.0763 (0.0990) time: 0.4294 data: 0.0028 max mem: 22446 +train: [11] [360/400] eta: 0:00:18 lr: 0.000169 loss: 0.0818 (0.1025) grad: 0.0767 (0.0978) time: 0.4608 data: 0.0037 max mem: 22446 +train: [11] [380/400] eta: 0:00:09 lr: 0.000167 loss: 0.0792 (0.1011) grad: 0.0605 (0.0956) time: 0.4388 data: 0.0035 max mem: 22446 +train: [11] [399/400] eta: 0:00:00 lr: 0.000166 loss: 0.0792 (0.1006) grad: 0.0657 (0.0954) time: 0.4459 data: 0.0036 max mem: 22446 +train: [11] Total time: 0:03:05 (0.4626 s / it) +train: [11] Summary: lr: 0.000166 loss: 0.0792 (0.1006) grad: 0.0657 (0.0954) +eval (validation): [11] [ 0/63] eta: 0:03:30 time: 3.3370 data: 3.0566 max mem: 22446 +eval (validation): [11] [20/63] eta: 0:00:21 time: 0.3536 data: 0.0032 max mem: 22446 +eval (validation): [11] [40/63] eta: 0:00:09 time: 0.3417 data: 0.0038 max mem: 22446 +eval (validation): [11] [60/63] eta: 0:00:01 time: 0.3201 data: 0.0033 max mem: 22446 +eval (validation): [11] [62/63] eta: 0:00:00 time: 0.3228 data: 0.0033 max mem: 22446 +eval (validation): [11] Total time: 0:00:24 (0.3899 s / it) +cv: [11] best hparam: (6, 1.0) (035) ('035_lr6.0e+00_wd1.0e+00') loss: 0.035 acc: 0.993 f1: 0.991 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [12] [ 0/400] eta: 0:22:39 lr: nan time: 3.3975 data: 3.0482 max mem: 22446 +train: [12] [ 20/400] eta: 0:03:47 lr: 0.000164 loss: 0.0761 (0.0815) grad: 0.0431 (0.0628) time: 0.4601 data: 0.0026 max mem: 22446 +train: [12] [ 40/400] eta: 0:03:07 lr: 0.000163 loss: 0.0802 (0.0859) grad: 0.0632 (0.0631) time: 0.4360 data: 0.0034 max mem: 22446 +train: [12] [ 60/400] eta: 0:02:49 lr: 0.000161 loss: 0.0722 (0.0814) grad: 0.0632 (0.0620) time: 0.4577 data: 0.0034 max mem: 22446 +train: [12] [ 80/400] eta: 0:02:36 lr: 0.000160 loss: 0.0712 (0.0795) grad: 0.0426 (0.0586) time: 0.4557 data: 0.0036 max mem: 22446 +train: [12] [100/400] eta: 0:02:24 lr: 0.000158 loss: 0.0775 (0.0805) grad: 0.0423 (0.0586) time: 0.4515 data: 0.0036 max mem: 22446 +train: [12] [120/400] eta: 0:02:13 lr: 0.000156 loss: 0.0867 (0.0844) grad: 0.0719 (0.0621) time: 0.4532 data: 0.0035 max mem: 22446 +train: [12] [140/400] eta: 0:02:02 lr: 0.000155 loss: 0.0819 (0.0839) grad: 0.0487 (0.0600) time: 0.4409 data: 0.0034 max mem: 22446 +train: [12] [160/400] eta: 0:01:52 lr: 0.000153 loss: 0.0743 (0.0838) grad: 0.0454 (0.0613) time: 0.4400 data: 0.0035 max mem: 22446 +train: [12] [180/400] eta: 0:01:42 lr: 0.000152 loss: 0.0737 (0.0833) grad: 0.0463 (0.0603) time: 0.4425 data: 0.0034 max mem: 22446 +train: [12] [200/400] eta: 0:01:32 lr: 0.000150 loss: 0.0684 (0.0828) grad: 0.0415 (0.0611) time: 0.4512 data: 0.0035 max mem: 22446 +train: [12] [220/400] eta: 0:01:23 lr: 0.000149 loss: 0.0709 (0.0831) grad: 0.0464 (0.0608) time: 0.4419 data: 0.0035 max mem: 22446 +train: [12] [240/400] eta: 0:01:13 lr: 0.000147 loss: 0.0818 (0.0838) grad: 0.0661 (0.0616) time: 0.4478 data: 0.0034 max mem: 22446 +train: [12] [260/400] eta: 0:01:04 lr: 0.000145 loss: 0.0763 (0.0832) grad: 0.0661 (0.0614) time: 0.4447 data: 0.0035 max mem: 22446 +train: [12] [280/400] eta: 0:00:54 lr: 0.000144 loss: 0.0752 (0.0831) grad: 0.0658 (0.0624) time: 0.4452 data: 0.0036 max mem: 22446 +train: [12] [300/400] eta: 0:00:46 lr: 0.000142 loss: 0.0798 (0.0830) grad: 0.0658 (0.0623) time: 0.5878 data: 0.1702 max mem: 22446 +train: [12] [320/400] eta: 0:00:37 lr: 0.000141 loss: 0.0767 (0.0827) grad: 0.0463 (0.0617) time: 0.4458 data: 0.0035 max mem: 22446 +train: [12] [340/400] eta: 0:00:27 lr: 0.000139 loss: 0.0777 (0.0828) grad: 0.0435 (0.0621) time: 0.4437 data: 0.0032 max mem: 22446 +train: [12] [360/400] eta: 0:00:18 lr: 0.000138 loss: 0.0754 (0.0825) grad: 0.0660 (0.0622) time: 0.4491 data: 0.0035 max mem: 22446 +train: [12] [380/400] eta: 0:00:09 lr: 0.000136 loss: 0.0741 (0.0827) grad: 0.0709 (0.0627) time: 0.4516 data: 0.0034 max mem: 22446 +train: [12] [399/400] eta: 0:00:00 lr: 0.000134 loss: 0.0693 (0.0823) grad: 0.0594 (0.0622) time: 0.4400 data: 0.0035 max mem: 22446 +train: [12] Total time: 0:03:04 (0.4618 s / it) +train: [12] Summary: lr: 0.000134 loss: 0.0693 (0.0823) grad: 0.0594 (0.0622) +eval (validation): [12] [ 0/63] eta: 0:03:29 time: 3.3185 data: 3.0436 max mem: 22446 +eval (validation): [12] [20/63] eta: 0:00:22 time: 0.3733 data: 0.0034 max mem: 22446 +eval (validation): [12] [40/63] eta: 0:00:10 time: 0.3535 data: 0.0029 max mem: 22446 +eval (validation): [12] [60/63] eta: 0:00:01 time: 0.3292 data: 0.0033 max mem: 22446 +eval (validation): [12] [62/63] eta: 0:00:00 time: 0.3265 data: 0.0033 max mem: 22446 +eval (validation): [12] Total time: 0:00:25 (0.4016 s / it) +cv: [12] best hparam: (0.72, 1.0) (022) ('022_lr7.2e-01_wd1.0e+00') loss: 0.022 acc: 0.993 f1: 0.991 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [13] [ 0/400] eta: 0:24:51 lr: nan time: 3.7277 data: 3.3295 max mem: 22446 +train: [13] [ 20/400] eta: 0:03:55 lr: 0.000133 loss: 0.0792 (0.0761) grad: 0.0404 (0.0439) time: 0.4652 data: 0.0031 max mem: 22446 +train: [13] [ 40/400] eta: 0:03:13 lr: 0.000131 loss: 0.0692 (0.0701) grad: 0.0336 (0.0412) time: 0.4493 data: 0.0036 max mem: 22446 +train: [13] [ 60/400] eta: 0:02:52 lr: 0.000130 loss: 0.0634 (0.0698) grad: 0.0383 (0.0445) time: 0.4435 data: 0.0035 max mem: 22446 +train: [13] [ 80/400] eta: 0:02:38 lr: 0.000128 loss: 0.0712 (0.0709) grad: 0.0398 (0.0438) time: 0.4580 data: 0.0035 max mem: 22446 +train: [13] [100/400] eta: 0:02:24 lr: 0.000127 loss: 0.0694 (0.0711) grad: 0.0375 (0.0446) time: 0.4375 data: 0.0035 max mem: 22446 +train: [13] [120/400] eta: 0:02:13 lr: 0.000125 loss: 0.0673 (0.0713) grad: 0.0414 (0.0449) time: 0.4396 data: 0.0035 max mem: 22446 +train: [13] [140/400] eta: 0:02:02 lr: 0.000124 loss: 0.0673 (0.0716) grad: 0.0414 (0.0463) time: 0.4530 data: 0.0034 max mem: 22446 +train: [13] [160/400] eta: 0:01:52 lr: 0.000122 loss: 0.0644 (0.0712) grad: 0.0361 (0.0457) time: 0.4460 data: 0.0035 max mem: 22446 +train: [13] [180/400] eta: 0:01:42 lr: 0.000120 loss: 0.0683 (0.0723) grad: 0.0404 (0.0468) time: 0.4330 data: 0.0036 max mem: 22446 +train: [13] [200/400] eta: 0:01:32 lr: 0.000119 loss: 0.0711 (0.0727) grad: 0.0427 (0.0464) time: 0.4427 data: 0.0036 max mem: 22446 +train: [13] [220/400] eta: 0:01:23 lr: 0.000117 loss: 0.0663 (0.0725) grad: 0.0426 (0.0465) time: 0.4451 data: 0.0034 max mem: 22446 +train: [13] [240/400] eta: 0:01:13 lr: 0.000116 loss: 0.0694 (0.0721) grad: 0.0378 (0.0461) time: 0.4453 data: 0.0034 max mem: 22446 +train: [13] [260/400] eta: 0:01:04 lr: 0.000114 loss: 0.0636 (0.0719) grad: 0.0347 (0.0459) time: 0.4474 data: 0.0034 max mem: 22446 +train: [13] [280/400] eta: 0:00:55 lr: 0.000113 loss: 0.0622 (0.0715) grad: 0.0363 (0.0463) time: 0.4478 data: 0.0035 max mem: 22446 +train: [13] [300/400] eta: 0:00:46 lr: 0.000111 loss: 0.0681 (0.0716) grad: 0.0545 (0.0474) time: 0.6100 data: 0.1693 max mem: 22446 +train: [13] [320/400] eta: 0:00:37 lr: 0.000110 loss: 0.0672 (0.0716) grad: 0.0442 (0.0468) time: 0.4497 data: 0.0029 max mem: 22446 +train: [13] [340/400] eta: 0:00:27 lr: 0.000108 loss: 0.0675 (0.0714) grad: 0.0352 (0.0467) time: 0.4343 data: 0.0036 max mem: 22446 +train: [13] [360/400] eta: 0:00:18 lr: 0.000107 loss: 0.0582 (0.0709) grad: 0.0370 (0.0464) time: 0.4516 data: 0.0035 max mem: 22446 +train: [13] [380/400] eta: 0:00:09 lr: 0.000105 loss: 0.0651 (0.0708) grad: 0.0367 (0.0463) time: 0.4559 data: 0.0036 max mem: 22446 +train: [13] [399/400] eta: 0:00:00 lr: 0.000104 loss: 0.0695 (0.0709) grad: 0.0367 (0.0459) time: 0.4455 data: 0.0035 max mem: 22446 +train: [13] Total time: 0:03:05 (0.4635 s / it) +train: [13] Summary: lr: 0.000104 loss: 0.0695 (0.0709) grad: 0.0367 (0.0459) +eval (validation): [13] [ 0/63] eta: 0:03:29 time: 3.3305 data: 3.0541 max mem: 22446 +eval (validation): [13] [20/63] eta: 0:00:21 time: 0.3688 data: 0.0036 max mem: 22446 +eval (validation): [13] [40/63] eta: 0:00:09 time: 0.3376 data: 0.0035 max mem: 22446 +eval (validation): [13] [60/63] eta: 0:00:01 time: 0.3353 data: 0.0035 max mem: 22446 +eval (validation): [13] [62/63] eta: 0:00:00 time: 0.3288 data: 0.0034 max mem: 22446 +eval (validation): [13] Total time: 0:00:24 (0.3968 s / it) +cv: [13] best hparam: (3.1, 1.0) (031) ('031_lr3.1e+00_wd1.0e+00') loss: 0.023 acc: 0.993 f1: 0.992 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [14] [ 0/400] eta: 0:22:51 lr: nan time: 3.4292 data: 3.0833 max mem: 22446 +train: [14] [ 20/400] eta: 0:03:52 lr: 0.000102 loss: 0.0665 (0.0718) grad: 0.0375 (0.0400) time: 0.4701 data: 0.0024 max mem: 22446 +train: [14] [ 40/400] eta: 0:03:10 lr: 0.000101 loss: 0.0665 (0.0706) grad: 0.0385 (0.0426) time: 0.4454 data: 0.0034 max mem: 22446 +train: [14] [ 60/400] eta: 0:02:50 lr: 0.000099 loss: 0.0628 (0.0682) grad: 0.0389 (0.0419) time: 0.4454 data: 0.0036 max mem: 22446 +train: [14] [ 80/400] eta: 0:02:36 lr: 0.000098 loss: 0.0582 (0.0681) grad: 0.0411 (0.0441) time: 0.4536 data: 0.0037 max mem: 22446 +train: [14] [100/400] eta: 0:02:24 lr: 0.000096 loss: 0.0590 (0.0675) grad: 0.0392 (0.0429) time: 0.4423 data: 0.0038 max mem: 22446 +train: [14] [120/400] eta: 0:02:13 lr: 0.000095 loss: 0.0645 (0.0691) grad: 0.0363 (0.0427) time: 0.4472 data: 0.0037 max mem: 22446 +train: [14] [140/400] eta: 0:02:02 lr: 0.000093 loss: 0.0729 (0.0701) grad: 0.0409 (0.0430) time: 0.4439 data: 0.0036 max mem: 22446 +train: [14] [160/400] eta: 0:01:52 lr: 0.000092 loss: 0.0602 (0.0694) grad: 0.0394 (0.0429) time: 0.4379 data: 0.0036 max mem: 22446 +train: [14] [180/400] eta: 0:01:42 lr: 0.000090 loss: 0.0576 (0.0683) grad: 0.0337 (0.0426) time: 0.4422 data: 0.0036 max mem: 22446 +train: [14] [200/400] eta: 0:01:32 lr: 0.000089 loss: 0.0622 (0.0686) grad: 0.0337 (0.0426) time: 0.4467 data: 0.0035 max mem: 22446 +train: [14] [220/400] eta: 0:01:22 lr: 0.000088 loss: 0.0604 (0.0680) grad: 0.0356 (0.0420) time: 0.4407 data: 0.0035 max mem: 22446 +train: [14] [240/400] eta: 0:01:13 lr: 0.000086 loss: 0.0606 (0.0676) grad: 0.0379 (0.0424) time: 0.4403 data: 0.0035 max mem: 22446 +train: [14] [260/400] eta: 0:01:04 lr: 0.000085 loss: 0.0597 (0.0669) grad: 0.0382 (0.0423) time: 0.4423 data: 0.0036 max mem: 22446 +train: [14] [280/400] eta: 0:00:54 lr: 0.000083 loss: 0.0649 (0.0675) grad: 0.0382 (0.0423) time: 0.4412 data: 0.0037 max mem: 22446 +train: [14] [300/400] eta: 0:00:46 lr: 0.000082 loss: 0.0680 (0.0676) grad: 0.0382 (0.0422) time: 0.6019 data: 0.1715 max mem: 22446 +train: [14] [320/400] eta: 0:00:37 lr: 0.000081 loss: 0.0601 (0.0673) grad: 0.0358 (0.0419) time: 0.4511 data: 0.0036 max mem: 22446 +train: [14] [340/400] eta: 0:00:27 lr: 0.000079 loss: 0.0697 (0.0677) grad: 0.0349 (0.0415) time: 0.4286 data: 0.0034 max mem: 22446 +train: [14] [360/400] eta: 0:00:18 lr: 0.000078 loss: 0.0699 (0.0678) grad: 0.0386 (0.0414) time: 0.4594 data: 0.0037 max mem: 22446 +train: [14] [380/400] eta: 0:00:09 lr: 0.000076 loss: 0.0699 (0.0679) grad: 0.0392 (0.0413) time: 0.4446 data: 0.0037 max mem: 22446 +train: [14] [399/400] eta: 0:00:00 lr: 0.000075 loss: 0.0643 (0.0679) grad: 0.0365 (0.0411) time: 0.4435 data: 0.0036 max mem: 22446 +train: [14] Total time: 0:03:04 (0.4612 s / it) +train: [14] Summary: lr: 0.000075 loss: 0.0643 (0.0679) grad: 0.0365 (0.0411) +eval (validation): [14] [ 0/63] eta: 0:03:28 time: 3.3168 data: 3.0417 max mem: 22446 +eval (validation): [14] [20/63] eta: 0:00:22 time: 0.3715 data: 0.0035 max mem: 22446 +eval (validation): [14] [40/63] eta: 0:00:09 time: 0.3510 data: 0.0033 max mem: 22446 +eval (validation): [14] [60/63] eta: 0:00:01 time: 0.3271 data: 0.0033 max mem: 22446 +eval (validation): [14] [62/63] eta: 0:00:00 time: 0.3194 data: 0.0032 max mem: 22446 +eval (validation): [14] Total time: 0:00:25 (0.4001 s / it) +cv: [14] best hparam: (1.9, 1.0) (028) ('028_lr1.9e+00_wd1.0e+00') loss: 0.022 acc: 0.993 f1: 0.991 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [15] [ 0/400] eta: 0:22:56 lr: nan time: 3.4423 data: 3.0488 max mem: 22446 +train: [15] [ 20/400] eta: 0:03:53 lr: 0.000074 loss: 0.0601 (0.0689) grad: 0.0349 (0.0375) time: 0.4718 data: 0.0061 max mem: 22446 +train: [15] [ 40/400] eta: 0:03:09 lr: 0.000072 loss: 0.0626 (0.0683) grad: 0.0371 (0.0391) time: 0.4349 data: 0.0033 max mem: 22446 +train: [15] [ 60/400] eta: 0:02:50 lr: 0.000071 loss: 0.0594 (0.0647) grad: 0.0371 (0.0383) time: 0.4475 data: 0.0034 max mem: 22446 +train: [15] [ 80/400] eta: 0:02:36 lr: 0.000070 loss: 0.0540 (0.0636) grad: 0.0320 (0.0373) time: 0.4583 data: 0.0035 max mem: 22446 +train: [15] [100/400] eta: 0:02:23 lr: 0.000068 loss: 0.0533 (0.0628) grad: 0.0319 (0.0371) time: 0.4376 data: 0.0035 max mem: 22446 +train: [15] [120/400] eta: 0:02:12 lr: 0.000067 loss: 0.0533 (0.0619) grad: 0.0319 (0.0368) time: 0.4353 data: 0.0035 max mem: 22446 +train: [15] [140/400] eta: 0:02:01 lr: 0.000066 loss: 0.0598 (0.0621) grad: 0.0355 (0.0365) time: 0.4396 data: 0.0035 max mem: 22446 +train: [15] [160/400] eta: 0:01:51 lr: 0.000064 loss: 0.0598 (0.0618) grad: 0.0355 (0.0369) time: 0.4419 data: 0.0035 max mem: 22446 +train: [15] [180/400] eta: 0:01:41 lr: 0.000063 loss: 0.0572 (0.0625) grad: 0.0364 (0.0368) time: 0.4371 data: 0.0036 max mem: 22446 +train: [15] [200/400] eta: 0:01:31 lr: 0.000062 loss: 0.0712 (0.0633) grad: 0.0361 (0.0367) time: 0.4401 data: 0.0036 max mem: 22446 +train: [15] [220/400] eta: 0:01:22 lr: 0.000061 loss: 0.0618 (0.0627) grad: 0.0361 (0.0367) time: 0.4501 data: 0.0035 max mem: 22446 +train: [15] [240/400] eta: 0:01:13 lr: 0.000059 loss: 0.0582 (0.0626) grad: 0.0372 (0.0368) time: 0.4459 data: 0.0037 max mem: 22446 +train: [15] [260/400] eta: 0:01:03 lr: 0.000058 loss: 0.0572 (0.0628) grad: 0.0347 (0.0367) time: 0.4396 data: 0.0035 max mem: 22446 +train: [15] [280/400] eta: 0:00:54 lr: 0.000057 loss: 0.0530 (0.0627) grad: 0.0340 (0.0367) time: 0.4403 data: 0.0036 max mem: 22446 +train: [15] [300/400] eta: 0:00:46 lr: 0.000056 loss: 0.0593 (0.0628) grad: 0.0346 (0.0366) time: 0.6144 data: 0.1691 max mem: 22446 +train: [15] [320/400] eta: 0:00:37 lr: 0.000054 loss: 0.0601 (0.0626) grad: 0.0351 (0.0367) time: 0.4524 data: 0.0028 max mem: 22446 +train: [15] [340/400] eta: 0:00:27 lr: 0.000053 loss: 0.0544 (0.0627) grad: 0.0389 (0.0369) time: 0.4409 data: 0.0036 max mem: 22446 +train: [15] [360/400] eta: 0:00:18 lr: 0.000052 loss: 0.0526 (0.0628) grad: 0.0378 (0.0370) time: 0.4563 data: 0.0036 max mem: 22446 +train: [15] [380/400] eta: 0:00:09 lr: 0.000051 loss: 0.0526 (0.0624) grad: 0.0366 (0.0368) time: 0.4505 data: 0.0036 max mem: 22446 +train: [15] [399/400] eta: 0:00:00 lr: 0.000050 loss: 0.0585 (0.0627) grad: 0.0328 (0.0367) time: 0.4436 data: 0.0036 max mem: 22446 +train: [15] Total time: 0:03:04 (0.4617 s / it) +train: [15] Summary: lr: 0.000050 loss: 0.0585 (0.0627) grad: 0.0328 (0.0367) +eval (validation): [15] [ 0/63] eta: 0:03:25 time: 3.2543 data: 3.0155 max mem: 22446 +eval (validation): [15] [20/63] eta: 0:00:20 time: 0.3430 data: 0.0040 max mem: 22446 +eval (validation): [15] [40/63] eta: 0:00:09 time: 0.3506 data: 0.0032 max mem: 22446 +eval (validation): [15] [60/63] eta: 0:00:01 time: 0.3156 data: 0.0033 max mem: 22446 +eval (validation): [15] [62/63] eta: 0:00:00 time: 0.3172 data: 0.0032 max mem: 22446 +eval (validation): [15] Total time: 0:00:24 (0.3869 s / it) +cv: [15] best hparam: (1, 1.0) (024) ('024_lr1.0e+00_wd1.0e+00') loss: 0.023 acc: 0.993 f1: 0.992 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [16] [ 0/400] eta: 0:23:26 lr: nan time: 3.5168 data: 3.1183 max mem: 22446 +train: [16] [ 20/400] eta: 0:03:51 lr: 0.000048 loss: 0.0666 (0.0669) grad: 0.0349 (0.0354) time: 0.4647 data: 0.0032 max mem: 22446 +train: [16] [ 40/400] eta: 0:03:10 lr: 0.000047 loss: 0.0630 (0.0638) grad: 0.0349 (0.0357) time: 0.4460 data: 0.0030 max mem: 22446 +train: [16] [ 60/400] eta: 0:02:50 lr: 0.000046 loss: 0.0616 (0.0624) grad: 0.0317 (0.0347) time: 0.4423 data: 0.0035 max mem: 22446 +train: [16] [ 80/400] eta: 0:02:36 lr: 0.000045 loss: 0.0634 (0.0631) grad: 0.0320 (0.0344) time: 0.4548 data: 0.0036 max mem: 22446 +train: [16] [100/400] eta: 0:02:24 lr: 0.000044 loss: 0.0577 (0.0633) grad: 0.0324 (0.0346) time: 0.4462 data: 0.0035 max mem: 22446 +train: [16] [120/400] eta: 0:02:13 lr: 0.000043 loss: 0.0560 (0.0625) grad: 0.0354 (0.0351) time: 0.4475 data: 0.0035 max mem: 22446 +train: [16] [140/400] eta: 0:02:02 lr: 0.000042 loss: 0.0538 (0.0625) grad: 0.0362 (0.0355) time: 0.4435 data: 0.0035 max mem: 22446 +train: [16] [160/400] eta: 0:01:52 lr: 0.000041 loss: 0.0565 (0.0622) grad: 0.0345 (0.0356) time: 0.4517 data: 0.0037 max mem: 22446 +train: [16] [180/400] eta: 0:01:42 lr: 0.000040 loss: 0.0581 (0.0623) grad: 0.0331 (0.0352) time: 0.4498 data: 0.0035 max mem: 22446 +train: [16] [200/400] eta: 0:01:32 lr: 0.000039 loss: 0.0664 (0.0631) grad: 0.0331 (0.0358) time: 0.4484 data: 0.0035 max mem: 22446 +train: [16] [220/400] eta: 0:01:23 lr: 0.000038 loss: 0.0586 (0.0629) grad: 0.0389 (0.0357) time: 0.4454 data: 0.0034 max mem: 22446 +train: [16] [240/400] eta: 0:01:13 lr: 0.000036 loss: 0.0526 (0.0624) grad: 0.0309 (0.0353) time: 0.4371 data: 0.0035 max mem: 22446 +train: [16] [260/400] eta: 0:01:04 lr: 0.000035 loss: 0.0619 (0.0630) grad: 0.0338 (0.0354) time: 0.4429 data: 0.0035 max mem: 22446 +train: [16] [280/400] eta: 0:00:54 lr: 0.000034 loss: 0.0599 (0.0626) grad: 0.0360 (0.0358) time: 0.4406 data: 0.0035 max mem: 22446 +train: [16] [300/400] eta: 0:00:46 lr: 0.000033 loss: 0.0545 (0.0626) grad: 0.0386 (0.0361) time: 0.5953 data: 0.1681 max mem: 22446 +train: [16] [320/400] eta: 0:00:37 lr: 0.000032 loss: 0.0604 (0.0626) grad: 0.0361 (0.0361) time: 0.4518 data: 0.0036 max mem: 22446 +train: [16] [340/400] eta: 0:00:27 lr: 0.000031 loss: 0.0624 (0.0631) grad: 0.0351 (0.0363) time: 0.4394 data: 0.0036 max mem: 22446 +train: [16] [360/400] eta: 0:00:18 lr: 0.000031 loss: 0.0616 (0.0630) grad: 0.0335 (0.0362) time: 0.4616 data: 0.0035 max mem: 22446 +train: [16] [380/400] eta: 0:00:09 lr: 0.000030 loss: 0.0569 (0.0625) grad: 0.0346 (0.0361) time: 0.4571 data: 0.0036 max mem: 22446 +train: [16] [399/400] eta: 0:00:00 lr: 0.000029 loss: 0.0553 (0.0624) grad: 0.0373 (0.0363) time: 0.4429 data: 0.0035 max mem: 22446 +train: [16] Total time: 0:03:05 (0.4634 s / it) +train: [16] Summary: lr: 0.000029 loss: 0.0553 (0.0624) grad: 0.0373 (0.0363) +eval (validation): [16] [ 0/63] eta: 0:03:25 time: 3.2678 data: 3.0284 max mem: 22446 +eval (validation): [16] [20/63] eta: 0:00:21 time: 0.3639 data: 0.0041 max mem: 22446 +eval (validation): [16] [40/63] eta: 0:00:09 time: 0.3512 data: 0.0034 max mem: 22446 +eval (validation): [16] [60/63] eta: 0:00:01 time: 0.3446 data: 0.0034 max mem: 22446 +eval (validation): [16] [62/63] eta: 0:00:00 time: 0.3394 data: 0.0033 max mem: 22446 +eval (validation): [16] Total time: 0:00:25 (0.4013 s / it) +cv: [16] best hparam: (14, 1.0) (040) ('040_lr1.4e+01_wd1.0e+00') loss: 0.162 acc: 0.993 f1: 0.993 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [17] [ 0/400] eta: 0:22:32 lr: nan time: 3.3813 data: 3.0317 max mem: 22446 +train: [17] [ 20/400] eta: 0:03:53 lr: 0.000028 loss: 0.0526 (0.0580) grad: 0.0329 (0.0354) time: 0.4761 data: 0.0028 max mem: 22446 +train: [17] [ 40/400] eta: 0:03:11 lr: 0.000027 loss: 0.0582 (0.0616) grad: 0.0333 (0.0356) time: 0.4475 data: 0.0036 max mem: 22446 +train: [17] [ 60/400] eta: 0:02:51 lr: 0.000026 loss: 0.0613 (0.0651) grad: 0.0378 (0.0361) time: 0.4476 data: 0.0035 max mem: 22446 +train: [17] [ 80/400] eta: 0:02:38 lr: 0.000025 loss: 0.0718 (0.0659) grad: 0.0378 (0.0361) time: 0.4646 data: 0.0035 max mem: 22446 +train: [17] [100/400] eta: 0:02:25 lr: 0.000024 loss: 0.0594 (0.0651) grad: 0.0344 (0.0359) time: 0.4432 data: 0.0035 max mem: 22446 +train: [17] [120/400] eta: 0:02:13 lr: 0.000023 loss: 0.0583 (0.0649) grad: 0.0344 (0.0356) time: 0.4426 data: 0.0035 max mem: 22446 +train: [17] [140/400] eta: 0:02:03 lr: 0.000023 loss: 0.0585 (0.0644) grad: 0.0323 (0.0356) time: 0.4478 data: 0.0036 max mem: 22446 +train: [17] [160/400] eta: 0:01:52 lr: 0.000022 loss: 0.0624 (0.0640) grad: 0.0336 (0.0356) time: 0.4407 data: 0.0036 max mem: 22446 +train: [17] [180/400] eta: 0:01:42 lr: 0.000021 loss: 0.0576 (0.0632) grad: 0.0339 (0.0355) time: 0.4424 data: 0.0035 max mem: 22446 +train: [17] [200/400] eta: 0:01:32 lr: 0.000020 loss: 0.0510 (0.0628) grad: 0.0329 (0.0355) time: 0.4431 data: 0.0035 max mem: 22446 +train: [17] [220/400] eta: 0:01:23 lr: 0.000019 loss: 0.0521 (0.0627) grad: 0.0329 (0.0354) time: 0.4432 data: 0.0036 max mem: 22446 +train: [17] [240/400] eta: 0:01:13 lr: 0.000019 loss: 0.0536 (0.0624) grad: 0.0320 (0.0355) time: 0.4416 data: 0.0034 max mem: 22446 +train: [17] [260/400] eta: 0:01:04 lr: 0.000018 loss: 0.0541 (0.0626) grad: 0.0345 (0.0355) time: 0.4499 data: 0.0035 max mem: 22446 +train: [17] [280/400] eta: 0:00:55 lr: 0.000017 loss: 0.0568 (0.0625) grad: 0.0345 (0.0353) time: 0.4549 data: 0.0035 max mem: 22446 +train: [17] [300/400] eta: 0:00:46 lr: 0.000016 loss: 0.0568 (0.0624) grad: 0.0348 (0.0354) time: 0.5973 data: 0.1692 max mem: 22446 +train: [17] [320/400] eta: 0:00:37 lr: 0.000016 loss: 0.0617 (0.0625) grad: 0.0365 (0.0357) time: 0.4537 data: 0.0035 max mem: 22446 +train: [17] [340/400] eta: 0:00:27 lr: 0.000015 loss: 0.0581 (0.0625) grad: 0.0340 (0.0355) time: 0.4348 data: 0.0032 max mem: 22446 +train: [17] [360/400] eta: 0:00:18 lr: 0.000014 loss: 0.0554 (0.0621) grad: 0.0308 (0.0352) time: 0.4500 data: 0.0035 max mem: 22446 +train: [17] [380/400] eta: 0:00:09 lr: 0.000014 loss: 0.0546 (0.0623) grad: 0.0331 (0.0352) time: 0.4514 data: 0.0036 max mem: 22446 +train: [17] [399/400] eta: 0:00:00 lr: 0.000013 loss: 0.0546 (0.0621) grad: 0.0348 (0.0352) time: 0.4449 data: 0.0036 max mem: 22446 +train: [17] Total time: 0:03:05 (0.4635 s / it) +train: [17] Summary: lr: 0.000013 loss: 0.0546 (0.0621) grad: 0.0348 (0.0352) +eval (validation): [17] [ 0/63] eta: 0:03:27 time: 3.2963 data: 3.0589 max mem: 22446 +eval (validation): [17] [20/63] eta: 0:00:21 time: 0.3682 data: 0.0032 max mem: 22446 +eval (validation): [17] [40/63] eta: 0:00:09 time: 0.3417 data: 0.0030 max mem: 22446 +eval (validation): [17] [60/63] eta: 0:00:01 time: 0.3279 data: 0.0035 max mem: 22446 +eval (validation): [17] [62/63] eta: 0:00:00 time: 0.3274 data: 0.0034 max mem: 22446 +eval (validation): [17] Total time: 0:00:25 (0.3969 s / it) +cv: [17] best hparam: (14, 1.0) (040) ('040_lr1.4e+01_wd1.0e+00') loss: 0.160 acc: 0.993 f1: 0.993 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [18] [ 0/400] eta: 0:22:19 lr: nan time: 3.3482 data: 2.9671 max mem: 22446 +train: [18] [ 20/400] eta: 0:04:05 lr: 0.000012 loss: 0.0525 (0.0588) grad: 0.0299 (0.0334) time: 0.5123 data: 0.0058 max mem: 22446 +train: [18] [ 40/400] eta: 0:03:16 lr: 0.000012 loss: 0.0547 (0.0619) grad: 0.0331 (0.0347) time: 0.4410 data: 0.0035 max mem: 22446 +train: [18] [ 60/400] eta: 0:02:56 lr: 0.000011 loss: 0.0551 (0.0618) grad: 0.0354 (0.0347) time: 0.4596 data: 0.0037 max mem: 22446 +train: [18] [ 80/400] eta: 0:02:40 lr: 0.000011 loss: 0.0565 (0.0625) grad: 0.0348 (0.0348) time: 0.4515 data: 0.0036 max mem: 22446 +train: [18] [100/400] eta: 0:02:27 lr: 0.000010 loss: 0.0565 (0.0625) grad: 0.0348 (0.0350) time: 0.4464 data: 0.0036 max mem: 22446 +train: [18] [120/400] eta: 0:02:15 lr: 0.000009 loss: 0.0530 (0.0606) grad: 0.0336 (0.0346) time: 0.4462 data: 0.0035 max mem: 22446 +train: [18] [140/400] eta: 0:02:04 lr: 0.000009 loss: 0.0577 (0.0612) grad: 0.0338 (0.0349) time: 0.4514 data: 0.0034 max mem: 22446 +train: [18] [160/400] eta: 0:01:53 lr: 0.000008 loss: 0.0634 (0.0609) grad: 0.0338 (0.0349) time: 0.4469 data: 0.0034 max mem: 22446 +train: [18] [180/400] eta: 0:01:43 lr: 0.000008 loss: 0.0529 (0.0602) grad: 0.0350 (0.0353) time: 0.4437 data: 0.0035 max mem: 22446 +train: [18] [200/400] eta: 0:01:33 lr: 0.000007 loss: 0.0529 (0.0600) grad: 0.0348 (0.0352) time: 0.4476 data: 0.0035 max mem: 22446 +train: [18] [220/400] eta: 0:01:24 lr: 0.000007 loss: 0.0525 (0.0599) grad: 0.0333 (0.0351) time: 0.4498 data: 0.0035 max mem: 22446 +train: [18] [240/400] eta: 0:01:14 lr: 0.000006 loss: 0.0524 (0.0597) grad: 0.0343 (0.0352) time: 0.4468 data: 0.0035 max mem: 22446 +train: [18] [260/400] eta: 0:01:04 lr: 0.000006 loss: 0.0545 (0.0602) grad: 0.0351 (0.0351) time: 0.4482 data: 0.0036 max mem: 22446 +train: [18] [280/400] eta: 0:00:55 lr: 0.000006 loss: 0.0577 (0.0603) grad: 0.0360 (0.0353) time: 0.4470 data: 0.0036 max mem: 22446 +train: [18] [300/400] eta: 0:00:47 lr: 0.000005 loss: 0.0538 (0.0600) grad: 0.0360 (0.0353) time: 0.5979 data: 0.1688 max mem: 22446 +train: [18] [320/400] eta: 0:00:37 lr: 0.000005 loss: 0.0522 (0.0599) grad: 0.0334 (0.0352) time: 0.4638 data: 0.0029 max mem: 22446 +train: [18] [340/400] eta: 0:00:28 lr: 0.000004 loss: 0.0561 (0.0601) grad: 0.0341 (0.0352) time: 0.4347 data: 0.0036 max mem: 22446 +train: [18] [360/400] eta: 0:00:18 lr: 0.000004 loss: 0.0585 (0.0600) grad: 0.0344 (0.0354) time: 0.4592 data: 0.0035 max mem: 22446 +train: [18] [380/400] eta: 0:00:09 lr: 0.000004 loss: 0.0503 (0.0595) grad: 0.0343 (0.0352) time: 0.4565 data: 0.0035 max mem: 22446 +train: [18] [399/400] eta: 0:00:00 lr: 0.000003 loss: 0.0494 (0.0593) grad: 0.0343 (0.0352) time: 0.4509 data: 0.0035 max mem: 22446 +train: [18] Total time: 0:03:07 (0.4675 s / it) +train: [18] Summary: lr: 0.000003 loss: 0.0494 (0.0593) grad: 0.0343 (0.0352) +eval (validation): [18] [ 0/63] eta: 0:03:28 time: 3.3174 data: 3.0403 max mem: 22446 +eval (validation): [18] [20/63] eta: 0:00:21 time: 0.3492 data: 0.0044 max mem: 22446 +eval (validation): [18] [40/63] eta: 0:00:09 time: 0.3481 data: 0.0030 max mem: 22446 +eval (validation): [18] [60/63] eta: 0:00:01 time: 0.3231 data: 0.0033 max mem: 22446 +eval (validation): [18] [62/63] eta: 0:00:00 time: 0.3250 data: 0.0033 max mem: 22446 +eval (validation): [18] Total time: 0:00:24 (0.3912 s / it) +cv: [18] best hparam: (14, 1.0) (040) ('040_lr1.4e+01_wd1.0e+00') loss: 0.160 acc: 0.993 f1: 0.993 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [19] [ 0/400] eta: 0:22:42 lr: nan time: 3.4059 data: 3.0065 max mem: 22446 +train: [19] [ 20/400] eta: 0:03:51 lr: 0.000003 loss: 0.0616 (0.0601) grad: 0.0327 (0.0332) time: 0.4707 data: 0.0032 max mem: 22446 +train: [19] [ 40/400] eta: 0:03:11 lr: 0.000003 loss: 0.0601 (0.0594) grad: 0.0328 (0.0344) time: 0.4512 data: 0.0032 max mem: 22446 +train: [19] [ 60/400] eta: 0:02:53 lr: 0.000002 loss: 0.0594 (0.0594) grad: 0.0350 (0.0342) time: 0.4628 data: 0.0035 max mem: 22446 +train: [19] [ 80/400] eta: 0:02:39 lr: 0.000002 loss: 0.0578 (0.0603) grad: 0.0352 (0.0349) time: 0.4580 data: 0.0036 max mem: 22446 +train: [19] [100/400] eta: 0:02:25 lr: 0.000002 loss: 0.0596 (0.0619) grad: 0.0348 (0.0347) time: 0.4433 data: 0.0035 max mem: 22446 +train: [19] [120/400] eta: 0:02:14 lr: 0.000002 loss: 0.0587 (0.0610) grad: 0.0334 (0.0344) time: 0.4500 data: 0.0034 max mem: 22446 +train: [19] [140/400] eta: 0:02:03 lr: 0.000001 loss: 0.0533 (0.0600) grad: 0.0334 (0.0346) time: 0.4487 data: 0.0034 max mem: 22446 +train: [19] [160/400] eta: 0:01:53 lr: 0.000001 loss: 0.0562 (0.0606) grad: 0.0334 (0.0344) time: 0.4543 data: 0.0036 max mem: 22446 +train: [19] [180/400] eta: 0:01:43 lr: 0.000001 loss: 0.0566 (0.0606) grad: 0.0345 (0.0345) time: 0.4509 data: 0.0035 max mem: 22446 +train: [19] [200/400] eta: 0:01:33 lr: 0.000001 loss: 0.0592 (0.0607) grad: 0.0349 (0.0345) time: 0.4433 data: 0.0034 max mem: 22446 +train: [19] [220/400] eta: 0:01:23 lr: 0.000001 loss: 0.0606 (0.0612) grad: 0.0338 (0.0347) time: 0.4433 data: 0.0035 max mem: 22446 +train: [19] [240/400] eta: 0:01:14 lr: 0.000001 loss: 0.0619 (0.0607) grad: 0.0333 (0.0346) time: 0.4442 data: 0.0035 max mem: 22446 +train: [19] [260/400] eta: 0:01:04 lr: 0.000000 loss: 0.0527 (0.0605) grad: 0.0333 (0.0345) time: 0.4471 data: 0.0034 max mem: 22446 +train: [19] [280/400] eta: 0:00:55 lr: 0.000000 loss: 0.0588 (0.0607) grad: 0.0338 (0.0346) time: 0.4503 data: 0.0035 max mem: 22446 +train: [19] [300/400] eta: 0:00:47 lr: 0.000000 loss: 0.0591 (0.0605) grad: 0.0363 (0.0347) time: 0.5995 data: 0.1723 max mem: 22446 +train: [19] [320/400] eta: 0:00:37 lr: 0.000000 loss: 0.0558 (0.0602) grad: 0.0359 (0.0348) time: 0.4580 data: 0.0033 max mem: 22446 +train: [19] [340/400] eta: 0:00:28 lr: 0.000000 loss: 0.0535 (0.0600) grad: 0.0359 (0.0349) time: 0.4376 data: 0.0034 max mem: 22446 +train: [19] [360/400] eta: 0:00:18 lr: 0.000000 loss: 0.0545 (0.0601) grad: 0.0344 (0.0350) time: 0.4606 data: 0.0036 max mem: 22446 +train: [19] [380/400] eta: 0:00:09 lr: 0.000000 loss: 0.0545 (0.0600) grad: 0.0351 (0.0350) time: 0.4586 data: 0.0036 max mem: 22446 +train: [19] [399/400] eta: 0:00:00 lr: 0.000000 loss: 0.0534 (0.0599) grad: 0.0351 (0.0350) time: 0.4460 data: 0.0035 max mem: 22446 +train: [19] Total time: 0:03:06 (0.4666 s / it) +train: [19] Summary: lr: 0.000000 loss: 0.0534 (0.0599) grad: 0.0351 (0.0350) +eval (validation): [19] [ 0/63] eta: 0:03:27 time: 3.2940 data: 3.0097 max mem: 22446 +eval (validation): [19] [20/63] eta: 0:00:21 time: 0.3720 data: 0.0042 max mem: 22446 +eval (validation): [19] [40/63] eta: 0:00:09 time: 0.3400 data: 0.0038 max mem: 22446 +eval (validation): [19] [60/63] eta: 0:00:01 time: 0.3180 data: 0.0024 max mem: 22446 +eval (validation): [19] [62/63] eta: 0:00:00 time: 0.3180 data: 0.0025 max mem: 22446 +eval (validation): [19] Total time: 0:00:24 (0.3944 s / it) +cv: [19] best hparam: (14, 1.0) (040) ('040_lr1.4e+01_wd1.0e+00') loss: 0.160 acc: 0.993 f1: 0.993 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +evaluating last checkpoint: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +eval model info: +{"score": 0.9933035714285714, "hparam": [14, 1.0], "hparam_id": 40, "epoch": 19, "is_best": false, "best_score": 0.9935515873015873} +eval (train): [20] [ 0/297] eta: 0:14:48 time: 2.9913 data: 2.7018 max mem: 22446 +eval (train): [20] [ 20/297] eta: 0:02:28 time: 0.4149 data: 0.0045 max mem: 22446 +eval (train): [20] [ 40/297] eta: 0:01:58 time: 0.3829 data: 0.0035 max mem: 22446 +eval (train): [20] [ 60/297] eta: 0:01:40 time: 0.3410 data: 0.0033 max mem: 22446 +eval (train): [20] [ 80/297] eta: 0:01:28 time: 0.3557 data: 0.0035 max mem: 22446 +eval (train): [20] [100/297] eta: 0:01:19 time: 0.3972 data: 0.0038 max mem: 22446 +eval (train): [20] [120/297] eta: 0:01:10 time: 0.3594 data: 0.0034 max mem: 22446 +eval (train): [20] [140/297] eta: 0:01:01 time: 0.3521 data: 0.0034 max mem: 22446 +eval (train): [20] [160/297] eta: 0:00:53 time: 0.3864 data: 0.0038 max mem: 22446 +eval (train): [20] [180/297] eta: 0:00:45 time: 0.3791 data: 0.0038 max mem: 22446 +eval (train): [20] [200/297] eta: 0:00:37 time: 0.3562 data: 0.0034 max mem: 22446 +eval (train): [20] [220/297] eta: 0:00:29 time: 0.3500 data: 0.0035 max mem: 22446 +eval (train): [20] [240/297] eta: 0:00:21 time: 0.3647 data: 0.0034 max mem: 22446 +eval (train): [20] [260/297] eta: 0:00:14 time: 0.3711 data: 0.0039 max mem: 22446 +eval (train): [20] [280/297] eta: 0:00:06 time: 0.3672 data: 0.0034 max mem: 22446 +eval (train): [20] [296/297] eta: 0:00:00 time: 0.3286 data: 0.0033 max mem: 22446 +eval (train): [20] Total time: 0:01:52 (0.3777 s / it) +eval (validation): [20] [ 0/63] eta: 0:03:15 time: 3.1082 data: 2.8594 max mem: 22446 +eval (validation): [20] [20/63] eta: 0:00:21 time: 0.3607 data: 0.0030 max mem: 22446 +eval (validation): [20] [40/63] eta: 0:00:09 time: 0.3568 data: 0.0033 max mem: 22446 +eval (validation): [20] [60/63] eta: 0:00:01 time: 0.3281 data: 0.0033 max mem: 22446 +eval (validation): [20] [62/63] eta: 0:00:00 time: 0.3260 data: 0.0033 max mem: 22446 +eval (validation): [20] Total time: 0:00:24 (0.3961 s / it) +eval (test): [20] [ 0/79] eta: 0:04:18 time: 3.2764 data: 2.9771 max mem: 22446 +eval (test): [20] [20/79] eta: 0:00:29 time: 0.3677 data: 0.0042 max mem: 22446 +eval (test): [20] [40/79] eta: 0:00:16 time: 0.3566 data: 0.0035 max mem: 22446 +eval (test): [20] [60/79] eta: 0:00:07 time: 0.3323 data: 0.0036 max mem: 22446 +eval (test): [20] [78/79] eta: 0:00:00 time: 0.3266 data: 0.0026 max mem: 22446 +eval (test): [20] Total time: 0:00:30 (0.3863 s / it) +evaluating best checkpoint: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/eval_v2/hcpya_task21__patch__attn/checkpoint-best.pth +eval model info: +{"score": 0.9935515873015873, "hparam": [0.72, 1.0], "hparam_id": 22, "epoch": 10, "is_best": true, "best_score": 0.9935515873015873} +eval (train): [20] [ 0/297] eta: 0:15:18 time: 3.0932 data: 2.7941 max mem: 22446 +eval (train): [20] [ 20/297] eta: 0:02:32 time: 0.4222 data: 0.0039 max mem: 22446 +eval (train): [20] [ 40/297] eta: 0:01:58 time: 0.3660 data: 0.0031 max mem: 22446 +eval (train): [20] [ 60/297] eta: 0:01:40 time: 0.3487 data: 0.0034 max mem: 22446 +eval (train): [20] [ 80/297] eta: 0:01:28 time: 0.3670 data: 0.0037 max mem: 22446 +eval (train): [20] [100/297] eta: 0:01:19 time: 0.3720 data: 0.0037 max mem: 22446 +eval (train): [20] [120/297] eta: 0:01:10 time: 0.3786 data: 0.0037 max mem: 22446 +eval (train): [20] [140/297] eta: 0:01:02 time: 0.3753 data: 0.0035 max mem: 22446 +eval (train): [20] [160/297] eta: 0:00:53 time: 0.3641 data: 0.0036 max mem: 22446 +eval (train): [20] [180/297] eta: 0:00:45 time: 0.3593 data: 0.0036 max mem: 22446 +eval (train): [20] [200/297] eta: 0:00:37 time: 0.3613 data: 0.0037 max mem: 22446 +eval (train): [20] [220/297] eta: 0:00:29 time: 0.4172 data: 0.0038 max mem: 22446 +eval (train): [20] [240/297] eta: 0:00:21 time: 0.3596 data: 0.0036 max mem: 22446 +eval (train): [20] [260/297] eta: 0:00:14 time: 0.4024 data: 0.0038 max mem: 22446 +eval (train): [20] [280/297] eta: 0:00:06 time: 0.3601 data: 0.0034 max mem: 22446 +eval (train): [20] [296/297] eta: 0:00:00 time: 0.3278 data: 0.0032 max mem: 22446 +eval (train): [20] Total time: 0:01:53 (0.3832 s / it) +eval (validation): [20] [ 0/63] eta: 0:03:12 time: 3.0583 data: 2.7783 max mem: 22446 +eval (validation): [20] [20/63] eta: 0:00:21 time: 0.3677 data: 0.0191 max mem: 22446 +eval (validation): [20] [40/63] eta: 0:00:09 time: 0.3703 data: 0.0037 max mem: 22446 +eval (validation): [20] [60/63] eta: 0:00:01 time: 0.3239 data: 0.0026 max mem: 22446 +eval (validation): [20] [62/63] eta: 0:00:00 time: 0.3237 data: 0.0029 max mem: 22446 +eval (validation): [20] Total time: 0:00:25 (0.3985 s / it) +eval (test): [20] [ 0/79] eta: 0:04:07 time: 3.1364 data: 2.8338 max mem: 22446 +eval (test): [20] [20/79] eta: 0:00:30 time: 0.3887 data: 0.0189 max mem: 22446 +eval (test): [20] [40/79] eta: 0:00:17 time: 0.3781 data: 0.0081 max mem: 22446 +eval (test): [20] [60/79] eta: 0:00:07 time: 0.3441 data: 0.0025 max mem: 22446 +eval (test): [20] [78/79] eta: 0:00:00 time: 0.3507 data: 0.0028 max mem: 22446 +eval (test): [20] Total time: 0:00:31 (0.4028 s / it) +eval results: + +| model | repr | clf | dataset | ckpt | epoch | lr | wd | hparam_id | hparam | split | loss | acc | acc_std | f1 | f1_std | +|:---------|:-------|:------|:-------------|:-------|--------:|---------:|-----:|------------:|:------------|:-----------|---------:|--------:|-----------:|--------:|-----------:| +| flat_mae | patch | attn | hcpya_task21 | best | 10 | 0.000216 | 0.05 | 22 | [0.72, 1.0] | train | 0.018582 | 0.99505 | 0.00052183 | 0.99448 | 0.00064591 | +| flat_mae | patch | attn | hcpya_task21 | best | 10 | 0.000216 | 0.05 | 22 | [0.72, 1.0] | validation | 0.021805 | 0.99355 | 0.0012916 | 0.99266 | 0.0016394 | +| flat_mae | patch | attn | hcpya_task21 | best | 10 | 0.000216 | 0.05 | 22 | [0.72, 1.0] | test | 0.034351 | 0.98968 | 0.0014302 | 0.9868 | 0.0019632 | + + +done! total time: 1:18:49 diff --git a/input_space_v3/flat_lr1e-3_2/eval_v2/hcpya_task21__patch__attn/train_log.json b/input_space_v3/flat_lr1e-3_2/eval_v2/hcpya_task21__patch__attn/train_log.json new file mode 100644 index 0000000000000000000000000000000000000000..712f525bc816d563d735958cd90dcdb1f2ebdb02 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_2/eval_v2/hcpya_task21__patch__attn/train_log.json @@ -0,0 +1,20 @@ +{"epoch": 0, "train/lr": 2.987987987987988e-05, "train/loss": 2.0406136643886565, "train/grad": 0.2111964312195778, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.005723876953125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.002677001953125, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.9976416015625, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.992640380859375, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.9876513671875, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.980799560546875, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.972906494140625, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.9641162109375, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.952686767578125, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.9403466796875, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.9282379150390625, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.909844970703125, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.891888427734375, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.8657122802734376, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.84035400390625, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.815758056640625, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.7842758178710936, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.7465591430664062, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.70331298828125, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.6620748901367186, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.60982177734375, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.5541372680664063, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.4896793365478516, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.418232879638672, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.3414229202270507, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.2472922134399416, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.1617749404907225, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.0839451217651366, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.9795996475219726, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.8597735357284546, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.7569151854515075, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.6673666894435883, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.5529012113809586, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.4574541817605495, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.3527795161306857, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.258123809248209, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.1667865594103932, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.0882148187141865, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.0111959318537265, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.9251455176901072, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.8646142169646919, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.8155352744273842, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.7570260020624846, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.7111453315243125, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.6631969218887389, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.6170463839825243, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.5813170136138797, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.5419868817925453, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.5104320583119989, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.03966970565728843, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.03960940640419722, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.03951195797882974, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.03941546114161611, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.03931954656727612, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.03918596484698355, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.03903226830996573, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.03886406027711928, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.03863786608912051, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.0383957561571151, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.038155856411904096, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.037791218142956495, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.03743458013981581, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.036914401538670066, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.03641459153965115, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.03594189650379121, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.035356957633048296, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.03469961921684444, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.034015589645132426, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.03342776513658464, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.03275641106069088, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.03211286191828549, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.03143353808671236, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.030731032248586417, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.030012300750240684, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.02915779617615044, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.02838982444256544, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.02769455062225461, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.026764410776086153, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.02570089873392135, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0247922121360898, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.02398082863073796, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.02290275293169543, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.021977541774977, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.020915839546360074, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.019919438904616983, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.018967299830401317, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.018110740140546113, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.017349892467609606, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0165477360523073, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.01590825915860478, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.015247484383871778, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.01448078482528217, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.014077343791141174, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.013804870615713298, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.013513197924476117, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.013400186105573085, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.013333502084715293, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.01326828844670672, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.9648468494415283, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.955935001373291, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.9410951137542725, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.9261271953582764, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.911471128463745, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.891195058822632, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.8683621883392334, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.842867136001587, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.80985426902771, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.774750232696533, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.7405383586883545, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.689605951309204, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.6405282020568848, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.5702879428863525, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.50376558303833, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.440845489501953, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.361192464828491, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.26753568649292, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.1617934703826904, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.0619654655456543, "validation/loss_020_lr5.2e-01_wd1.0e+00": 1.936492919921875, "validation/loss_021_lr6.1e-01_wd1.0e+00": 1.804429531097412, "validation/loss_022_lr7.2e-01_wd1.0e+00": 1.6551806926727295, "validation/loss_023_lr8.5e-01_wd1.0e+00": 1.495450496673584, "validation/loss_024_lr1.0e+00_wd1.0e+00": 1.3322736024856567, "validation/loss_025_lr1.2e+00_wd1.0e+00": 1.1473785638809204, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.9950440526008606, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.8688843250274658, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.7154439091682434, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.5550614595413208, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.4273272454738617, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.32506996393203735, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.2153499573469162, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.14740142226219177, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.09405212849378586, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.06699539721012115, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.05629314109683037, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.051329806447029114, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.04926391690969467, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.053503330796957016, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.06178652495145798, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.055632561445236206, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.04393468797206879, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.04032574221491814, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.04025061056017876, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.04486618936061859, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.04969014599919319, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.055274598300457, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.0620761439204216, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.1619543650793651, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.18725198412698413, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.2269345238095238, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.24379960317460317, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.2509920634920635, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.25322420634920634, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.251984126984127, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.2509920634920635, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.24975198412698413, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.2472718253968254, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.2472718253968254, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.24677579365079366, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.2472718253968254, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.25049603174603174, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.25744047619047616, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.2693452380952381, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.2941468253968254, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.3531746031746032, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.42683531746031744, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.4806547619047619, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.5632440476190477, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.6091269841269841, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.6398809523809523, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.7023809523809523, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.7678571428571429, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.8315972222222222, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.8702876984126984, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.8928571428571429, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9047619047619048, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9104662698412699, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9141865079365079, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9231150793650794, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9590773809523809, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9751984126984127, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9791666666666666, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9811507936507936, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9831349206349206, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9836309523809523, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9833829365079365, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9828869047619048, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9806547619047619, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9833829365079365, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9861111111111112, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9871031746031746, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9878472222222222, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9858630952380952, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9853670634920635, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9833829365079365, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9779265873015873, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.050519445777942595, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.055847587310926435, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.0629311281155576, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.06309115839606669, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.06257513486922764, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.06252559362721384, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.06105354870065819, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.06088035665278702, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.06200011952042325, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.0630966389639736, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.0652842848990338, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.06579942857906694, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.06681327716282538, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.0708197946932259, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.07639471588028511, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.08565676400823524, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.10674211918745335, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.15931426092305565, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.20826234647397354, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.24243497834429079, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.3134059658764581, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.354262780479698, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.41583358025175443, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.5513413271360895, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.6706708860136009, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.7752657893685766, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.8396588197008773, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.8742063357571721, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.8912074603049275, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.8938596416837535, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.89537647324112, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9084443983323661, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9538600241513728, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9714941921983253, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9757705377554813, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9781142590410445, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9807982371572621, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9812099080100936, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9808479597782968, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9808310623199985, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9795943946569207, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9819614025660548, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.983703453706981, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9852306215622568, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9848545492577377, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9819980844232605, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9806999808292602, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9789793863497076, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9733181516444491, "id_best": 44, "lr_best": 0.0078, "wd_best": 0.05, "train/loss_best": 0.6631969218887389, "validation/loss_best": 0.04025061056017876, "validation/acc_best": 0.9878472222222222, "validation/f1_best": 0.9848545492577377} +{"epoch": 1, "train/lr": 8.993993993993998e-05, "train/loss": 1.1103835704922675, "train/grad": 0.14825237531214952, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.88906494140625, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.86960205078125, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.8376995849609377, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.8066656494140627, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.776207275390625, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.734827880859375, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.6893060302734373, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.64001953125, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.577082214355469, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.512291259765625, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.450395202636719, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.3601913452148438, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.2749092102050783, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.155137176513672, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.0434939575195314, "train/loss_015_lr2.3e-01_wd1.0e+00": 1.9390898895263673, "train/loss_016_lr2.7e-01_wd1.0e+00": 1.8099799346923828, "train/loss_017_lr3.2e-01_wd1.0e+00": 1.6637367630004882, "train/loss_018_lr3.8e-01_wd1.0e+00": 1.5081164932250977, "train/loss_019_lr4.4e-01_wd1.0e+00": 1.3713653659820557, "train/loss_020_lr5.2e-01_wd1.0e+00": 1.2132853174209595, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.0624017381668092, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.9078975546360016, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.7591113835573197, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.6236106190085411, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.48763989776372907, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.3882035373523831, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.3148601660318673, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.23740114836022258, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.1710492916405201, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.12987116048112513, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.1040242709685117, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.08172703307121992, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.07018989162519575, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.06244991569779813, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.058660469008609654, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.05642969574779272, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.05485103533603251, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.05293446100316942, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.05123435100540519, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.05068565364927054, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.0508212467096746, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.05252448684535921, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.05456946984864772, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.058895157901570204, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.061937325522303584, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.07815883509814739, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.08740085380151869, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.11678827912546694, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.037045329976826906, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.03667443129234016, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.03606354808434844, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.03547071411274374, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.03489854237064719, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.034127977546304464, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.033300818083807825, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.032444759299978615, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.031429402865469455, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.030482061905786395, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.02967227860353887, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.02863978094421327, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.027799001531675457, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.026776309506967664, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.025936411479488015, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.02520630813203752, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.024331433102488517, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.023328513978049158, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.02221525602042675, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.021189301554113627, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.019950263407081364, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.01870684450957924, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.01735005580354482, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.015908327633515, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.014462984027341008, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.012855572698172182, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.011509567149914801, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.010490465947659686, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.009388158052461222, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.008361972216516734, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.007642622829880565, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.007143548473250121, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.00666186698130332, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0064749691868200895, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.006343338287551887, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.006391390743665397, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0064854958630166945, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0065112971502821896, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.006431966524687595, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.006393985573376995, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.00635874091021833, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.006478486524283653, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.006770777351339348, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.007021010580938309, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.007634294130257331, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.008105147054302507, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.00984603984921705, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.010613911749678663, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.013327724142945953, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.7945878505706787, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.7625794410705566, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.7110304832458496, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.6614084243774414, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.6134097576141357, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.5492634773254395, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.4795238971710205, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.4052486419677734, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.31182599067688, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.216606616973877, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.126354455947876, "validation/loss_011_lr1.2e-01_wd1.0e+00": 1.995429277420044, "validation/loss_012_lr1.4e-01_wd1.0e+00": 1.872596263885498, "validation/loss_013_lr1.7e-01_wd1.0e+00": 1.7025187015533447, "validation/loss_014_lr2.0e-01_wd1.0e+00": 1.5477956533432007, "validation/loss_015_lr2.3e-01_wd1.0e+00": 1.408290147781372, "validation/loss_016_lr2.7e-01_wd1.0e+00": 1.2441277503967285, "validation/loss_017_lr3.2e-01_wd1.0e+00": 1.0710703134536743, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.9018827676773071, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.7642380595207214, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.613355815410614, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.4746725857257843, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.3407321572303772, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.2306794375181198, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.1522550880908966, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.09445618838071823, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.07155244797468185, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.06147809699177742, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.05342545360326767, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.047202423214912415, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.043043069541454315, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.03998694196343422, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.036691222339868546, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.034115105867385864, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.032125361263751984, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.03116547502577305, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.030430790036916733, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.028951186686754227, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.02861706167459488, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.029916252940893173, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.0309246014803648, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.03611675277352333, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.041750092059373856, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.05232222005724907, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.05190817639231682, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.08122574537992477, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.07427665591239929, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.11360333114862442, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.22554010152816772, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.25049603174603174, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.24751984126984128, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.24751984126984128, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.24677579365079366, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.24677579365079366, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.2507440476190476, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.2614087301587302, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.2847222222222222, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.3385416666666667, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.4273313492063492, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.4789186507936508, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.5652281746031746, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.607390873015873, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.6475694444444444, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.7013888888888888, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.7495039682539683, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.8107638888888888, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.8576388888888888, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.8871527777777778, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9030257936507936, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9181547619047619, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9337797619047619, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9506448412698413, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9672619047619048, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9779265873015873, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9811507936507936, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9828869047619048, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9848710317460317, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9853670634920635, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9871031746031746, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9873511904761905, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9880952380952381, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9875992063492064, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9873511904761905, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9885912698412699, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9885912698412699, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9893353174603174, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9900793650793651, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9905753968253969, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9890873015873016, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9890873015873016, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9875992063492064, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9873511904761905, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9838789682539683, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9848710317460317, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9799107142857143, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9809027777777778, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9756944444444444, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.970734126984127, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.06327737480442142, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.0631465068010689, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.06612362280928476, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.06671930817158496, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.06653926531224748, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.07087742137805496, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.08143497228250646, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.10309543614338564, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.15135466033683997, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.21333054361788745, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.24456074426768146, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.3173095711564344, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.3450585584554233, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.4310408083544753, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.5478551750335766, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.6454093458381291, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.7499929361653206, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.8194794230643309, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.8608333334112737, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.8851613554274904, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9058534485951365, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9257677946188609, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9451390655852989, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9625546936690577, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9735414057661083, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9776508708197775, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9788257029835266, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9818084613949759, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.982093884094831, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9835898115464765, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9844953013024788, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9853584530520872, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9850108909087208, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9850476126541827, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.986273364569251, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9864512347648774, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9873194484854667, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9886259359964205, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9891557560643174, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9879911503912874, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.987895141705116, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.98671373473571, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9857128010918542, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9828292420147836, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9834384996982418, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9801713970708389, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.975277215398362, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9669652386579776, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9654530729002011, "id_best": 38, "lr_best": 0.00294, "wd_best": 0.05, "train/loss_best": 0.05293446100316942, "validation/loss_best": 0.02861706167459488, "validation/acc_best": 0.9905753968253969, "validation/f1_best": 0.9891557560643174} +{"epoch": 2, "train/lr": 0.00014999999999999988, "train/loss": 0.8128501570224762, "train/grad": 0.18906295761466027, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.675682373046875, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.63030029296875, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.5580233764648437, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.48953369140625, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.4244427490234375, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.3379107666015626, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.2447470092773436, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.145796813964844, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.0219641876220704, "train/loss_009_lr8.7e-02_wd1.0e+00": 1.8967765045166016, "train/loss_010_lr1.0e-01_wd1.0e+00": 1.7800487899780273, "train/loss_011_lr1.2e-01_wd1.0e+00": 1.6157980728149415, "train/loss_012_lr1.4e-01_wd1.0e+00": 1.4690274429321288, "train/loss_013_lr1.7e-01_wd1.0e+00": 1.278101453781128, "train/loss_014_lr2.0e-01_wd1.0e+00": 1.1173857259750366, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.9809792709350585, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.8284151351451874, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.6729449623823166, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.5259239912033081, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.41299187824130057, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.3022663779556751, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.21772424187511205, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.1540137254819274, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.11233783926814794, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.0874594432581216, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.07247093494050205, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.06574861500412225, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0618411114718765, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.058166378047317266, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.05515632562339306, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.053011980289593336, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.051615074118599294, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.050334371021017434, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.04936658729799092, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.04839049953967333, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.048506218045949935, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.04973989020101726, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.0510431653726846, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.0466136388015002, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.04912648560479283, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.055916098542511464, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.06448145117610693, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.08544410654343665, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.11521806353703141, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.19889441007748246, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.2948995623923838, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.5295019382052124, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.8719179345667363, "train/loss_048_lr5.0e+01_wd1.0e+00": 1.821657518800348, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.0335107397288084, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.03267351003363728, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.031411760412156584, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.030318646440282464, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.029391974667087196, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.0283323572576046, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.027385253766551612, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.026550939474254846, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.025661704493686557, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.02484791067428887, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.024107418796047567, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.023027133410796524, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.021987170511856675, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.020514356959611176, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.019178638034500182, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.017994755893014372, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.016631868286058307, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.015187802421860398, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.013687948344741017, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.012382499030791224, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.010891269932035357, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.009523805698845535, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.008249202879378572, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.007256194204092026, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.006561421657679602, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.006123315757140518, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0060056547005660835, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.005988221998559311, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.006006392406998202, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0060344316874397915, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.006036779151763767, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.00606535986327799, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.006076484437071486, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.006055056485347449, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.006043651832733303, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.006160894169443054, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.006376544778759125, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.006529754000948742, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.00621984268160304, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.00682817686261842, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.007623660784884123, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.008616345981135965, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.011322110384353436, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.014750159754185007, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.02138267713420646, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.028112989473120253, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.04564051975936309, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.05899616553309229, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.10089235071920796, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.547004461288452, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.4880013465881348, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.394948959350586, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.307644844055176, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.225137233734131, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.1157333850860596, "validation/loss_006_lr5.3e-02_wd1.0e+00": 1.9979853630065918, "validation/loss_007_lr6.2e-02_wd1.0e+00": 1.8735707998275757, "validation/loss_008_lr7.4e-02_wd1.0e+00": 1.7194353342056274, "validation/loss_009_lr8.7e-02_wd1.0e+00": 1.5670311450958252, "validation/loss_010_lr1.0e-01_wd1.0e+00": 1.4288448095321655, "validation/loss_011_lr1.2e-01_wd1.0e+00": 1.2428501844406128, "validation/loss_012_lr1.4e-01_wd1.0e+00": 1.0859278440475464, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.8944414854049683, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.7413979768753052, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.6144590973854065, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.4731026291847229, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.3349500894546509, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.22294165194034576, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.1531556397676468, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.09948039799928665, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.07412711530923843, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.0609816238284111, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.05307244881987572, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.04791097342967987, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.04363606870174408, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.040681205689907074, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.038898810744285583, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.03725840896368027, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.03572358191013336, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.03152364492416382, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.02784738503396511, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.026082869619131088, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.026233946904540062, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.027321558445692062, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.02993345633149147, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.03324823081493378, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.03522004187107086, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.041159890592098236, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.041646912693977356, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.11172234266996384, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.10967998951673508, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.16851848363876343, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.386667937040329, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.25433191657066345, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.4161003828048706, "validation/loss_046_lr3.6e+01_wd1.0e+00": 1.3716224431991577, "validation/loss_047_lr4.3e+01_wd1.0e+00": 1.491377592086792, "validation/loss_048_lr5.0e+01_wd1.0e+00": 1.5979769229888916, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.25124007936507936, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.2604166666666667, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.28869047619047616, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.3353174603174603, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.4037698412698413, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.47197420634920634, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.5473710317460317, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.6086309523809523, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.636656746031746, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.7043650793650794, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.7666170634920635, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.8380456349206349, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.8702876984126984, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.8903769841269841, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9079861111111112, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9191468253968254, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.933531746031746, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.951140873015873, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9702380952380952, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9781746031746031, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9811507936507936, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9828869047619048, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.984375, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9846230158730159, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9866071428571429, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9868551587301587, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9871031746031746, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9871031746031746, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9868551587301587, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9880952380952381, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9900793650793651, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9908234126984127, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9910714285714286, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9908234126984127, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9900793650793651, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.988343253968254, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9885912698412699, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9873511904761905, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9866071428571429, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9873511904761905, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9744543650793651, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9779265873015873, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9680059523809523, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9541170634920635, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.970734126984127, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9734623015873016, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9645337301587301, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9623015873015873, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9704861111111112, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.07237337410407822, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.08091060270264756, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.10524356865680085, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.1471023741884803, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.19591623033549294, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.24116236719512218, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.3071289967513146, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.34853729305803716, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.40441165692357683, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.5634371227446551, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.6894380989486836, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.8000448894785127, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.8413250656456623, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.8661307736156614, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.891303335710275, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9054662957215253, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9251942339664562, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9458722889349832, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9664020705424419, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9753407605210552, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.978258031863591, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9797778088573471, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9811312991845111, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.982259852981412, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9845035777347139, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9846308485716261, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9850004374358067, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9853710198604511, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9851911686558624, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9867798874522412, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9893568082551883, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9897027470796151, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9903052421658267, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9897106077179453, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9892494102521043, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.987360401089005, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9870888093814078, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9849201186852302, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9847404127556291, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.986200806724988, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.974954965369574, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9782000382699187, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9596086606785386, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9244131121077308, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9664638775085093, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9684206876047343, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9460952609677613, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9397967266609619, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9635082420277004, "id_best": 32, "lr_best": 0.0011099999999999999, "wd_best": 0.05, "train/loss_best": 0.050334371021017434, "validation/loss_best": 0.026082869619131088, "validation/acc_best": 0.9910714285714286, "validation/f1_best": 0.9903052421658267} +{"epoch": 3, "train/lr": 0.0002100600600600602, "train/loss": 0.7043892589211463, "train/grad": 0.28000063985586165, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.416482238769531, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.3447369384765624, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.2317941284179685, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.1256037902832032, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.025082702636719, "train/loss_005_lr4.5e-02_wd1.0e+00": 1.8926403045654296, "train/loss_006_lr5.3e-02_wd1.0e+00": 1.7521699523925782, "train/loss_007_lr6.2e-02_wd1.0e+00": 1.60716552734375, "train/loss_008_lr7.4e-02_wd1.0e+00": 1.4343133544921876, "train/loss_009_lr8.7e-02_wd1.0e+00": 1.271235466003418, "train/loss_010_lr1.0e-01_wd1.0e+00": 1.1307007312774657, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.95007248878479, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.802681941986084, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.6250005161762238, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.4854698371887207, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.37698054492473604, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.2709673801064491, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.18472705282270907, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.12709152292460202, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.09724028687924147, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.07838678430765868, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.06901618594303727, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.06301228449679912, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.0586937072314322, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.05529411566443741, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.05188672099262476, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.04922136695124209, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.04709058649837971, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.04458487283438444, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.04200015355832875, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.039925572657957674, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.038414633581414816, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.03708825247362256, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.03647588308900595, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.03610173630528152, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.0358913994487375, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.04064553792588413, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.04274440804496407, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.040730128409340975, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.05725680267438293, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.05563014532439411, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.08416039762087166, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.19244732323102653, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.28811337339691817, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.38612548685632647, "train/loss_045_lr3.1e+01_wd1.0e+00": 1.232528493143618, "train/loss_046_lr3.6e+01_wd1.0e+00": 1.4904599375184626, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.273438977850601, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.395552568798885, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.028815520517528056, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.027968259677290917, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.026894949320703746, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.026090379264205696, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.02543478710576892, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.024636535737663508, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.023788851127028464, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.02286029898561537, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.02164372072555125, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.02037400397006422, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.019193686256185175, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.017603873489424587, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.016270201783627272, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.014623232576996088, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.0131970797595568, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.01189103706041351, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.010304481484927236, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.008633952336385847, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.007305014628218487, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.006552886932622641, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.00609974395018071, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.005952333565219305, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.005915021005203016, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0059108861626009455, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.00590242839884013, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.00582873234670842, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.005691664354526438, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.005573773904179688, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0054814925824757665, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.005371656366041862, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.005269542686000932, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.005183281387435273, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.00515444613789441, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.005215687788149808, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.005321236058225622, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.005413072330848081, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.005854658578464296, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0062243015939748144, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0067386024156803614, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.008139880673425068, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.008287819961369678, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.012217101655696751, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.02167811964520297, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0314513926198209, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.03473648283179386, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.07823905335061844, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.09567178957106423, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.11535956090325658, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.16230979246982877, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.264803886413574, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.178769588470459, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.0437228679656982, "validation/loss_003_lr3.3e-02_wd1.0e+00": 1.9174489974975586, "validation/loss_004_lr3.8e-02_wd1.0e+00": 1.7990083694458008, "validation/loss_005_lr4.5e-02_wd1.0e+00": 1.64529287815094, "validation/loss_006_lr5.3e-02_wd1.0e+00": 1.4863262176513672, "validation/loss_007_lr6.2e-02_wd1.0e+00": 1.3277949094772339, "validation/loss_008_lr7.4e-02_wd1.0e+00": 1.1469097137451172, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.9846540689468384, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.8498757481575012, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.6805132627487183, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.5422793030738831, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.3776608407497406, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.2615755796432495, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.18583020567893982, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.12211018800735474, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.08443883806467056, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.06718023121356964, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.05864524841308594, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.05188088119029999, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.046909037977457047, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.0426580049097538, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.038749463856220245, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.03545333072543144, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.03219589591026306, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.029716255143284798, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.028061529621481895, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.026767099276185036, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.0260026752948761, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.02575366012752056, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.026381604373455048, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.029670454561710358, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.03238309547305107, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.03189784288406372, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.04210992902517319, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.04965658858418465, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.04952207952737808, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.07030293345451355, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.062119871377944946, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.13689647614955902, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.1641860455274582, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.17338645458221436, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.570409893989563, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.3130156099796295, "validation/loss_045_lr3.1e+01_wd1.0e+00": 1.1583783626556396, "validation/loss_046_lr3.6e+01_wd1.0e+00": 1.6943986415863037, "validation/loss_047_lr4.3e+01_wd1.0e+00": 5.9130539894104, "validation/loss_048_lr5.0e+01_wd1.0e+00": 4.906140327453613, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.3881448412698413, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.4503968253968254, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.5250496031746031, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.5954861111111112, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.6160714285714286, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.6671626984126984, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.7351190476190477, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.7983630952380952, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.8536706349206349, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.8787202380952381, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.8955853174603174, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9092261904761905, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9223710317460317, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9404761904761905, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9575892857142857, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9699900793650794, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9781746031746031, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9821428571428571, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9821428571428571, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9831349206349206, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.984375, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9858630952380952, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9871031746031746, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9878472222222222, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9885912698412699, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9903273809523809, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9915674603174603, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9905753968253969, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9908234126984127, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9905753968253969, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9908234126984127, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9923115079365079, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9895833333333334, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9888392857142857, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9893353174603174, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9851190476190477, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9848710317460317, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9851190476190477, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9826388888888888, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9851190476190477, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9759424603174603, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9809027777777778, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9821428571428571, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9751984126984127, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9816468253968254, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9781746031746031, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9734623015873016, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.953125, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9712301587301587, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.18759009501723684, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.2243203348185163, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.2851636098834514, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.33788571687706376, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.35913657703490837, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.49422580878932315, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.6406695530765613, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.7513996619827013, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.8274492234820663, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.8535591555992035, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.8764461041165319, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.8953704771232971, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9117956231541794, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9338832236935963, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9528172235645185, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9661149113166368, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9749365437214565, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9795197323466451, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9795232060172607, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9801546616613682, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9811475227243381, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9831943968288199, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9848260336356645, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9856486739638751, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9860932748992874, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9885971039300558, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9899133526528152, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9887523932718862, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9894212503123551, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9888768205442162, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.989318908844111, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9915728026400034, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9894815194964084, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9887643457037304, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9892243387389761, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9845909672280491, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9822130239830478, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9835549100506408, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.979394885574604, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9847994543989125, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.967701827085576, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9713985334730101, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9806835209848289, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9696015005386693, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9784316830817879, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9735745679907808, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9683792000683951, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9245320224299569, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9601603788722789, "id_best": 31, "lr_best": 0.0009299999999999999, "wd_best": 0.05, "train/loss_best": 0.038414633581414816, "validation/loss_best": 0.026381604373455048, "validation/acc_best": 0.9923115079365079, "validation/f1_best": 0.9915728026400034} +{"epoch": 4, "train/lr": 0.0002701201201201201, "train/loss": 0.7556881403923035, "train/grad": 0.428565718382597, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.1210235595703124, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.02129638671875, "train/loss_002_lr2.8e-02_wd1.0e+00": 1.8655154418945312, "train/loss_003_lr3.3e-02_wd1.0e+00": 1.7222496032714845, "train/loss_004_lr3.8e-02_wd1.0e+00": 1.59059627532959, "train/loss_005_lr4.5e-02_wd1.0e+00": 1.4246723175048828, "train/loss_006_lr5.3e-02_wd1.0e+00": 1.2594500732421876, "train/loss_007_lr6.2e-02_wd1.0e+00": 1.1011783218383788, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.9270251846313476, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.7736733484268189, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.6463961434364319, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.48777987241744997, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.36650932908058165, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.2413711181282997, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.16559288203716277, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.12215661779046058, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.09247410882264376, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.07653706228360534, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.0676210917904973, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.062446641232818366, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.05787050906568766, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.054284084727987646, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.0510234265960753, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.04819157192483545, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.04573421811684966, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.04307992529124022, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.04115360939875245, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.03962020698003471, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.03767042985185981, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.035565764931961896, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.034298939323052766, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.03353897863999009, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.03259847199544311, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.03254093702882528, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.03340036753565073, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.034026420135051014, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.03542941184714436, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.05307912103831768, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.08079538334161043, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.1156486075092107, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.16110316639766098, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.4438848585728556, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.4311740835756063, "train/loss_043_lr2.2e+01_wd1.0e+00": 1.1390635392814874, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.8916443444229663, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.010277119735256, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.364053392894566, "train/loss_047_lr4.3e+01_wd1.0e+00": 5.944225485334173, "train/loss_048_lr5.0e+01_wd1.0e+00": 5.56817783292383, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.026097037065774202, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.02545825225301087, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.024540825644508005, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.02369028756394982, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.022855797661468388, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.02170408018864691, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.020428622364997862, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.01910410029347986, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.017565554357133806, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.01618039740715176, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.015007212245836853, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.013402882241643965, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.011903959151823074, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.009889407970476896, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.008234467906877398, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.007095949479844421, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.006266397034050897, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.005898537472239696, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.005750998865114525, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.005672350546810776, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.005602293384727091, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.005550256465794518, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.00550065778370481, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.005468109955836553, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.005449514928041026, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.005435678242356516, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.005474342511733994, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.00548644636379322, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.005475676062924322, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.005446399523789296, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.005491498339833925, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.005517679877666524, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.005395413701698999, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.005406156211902271, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.005641073506376415, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.005954046081969863, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.006296991770504974, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.008089222305025033, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.012355586526182379, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.016294945136178286, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.018823673190845512, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.040909740802200556, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.03673097540889996, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.07533076706743308, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.07377864717007963, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.11175185654394582, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.1211662633298439, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.23368749553300144, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.21732995437042033, "validation/loss_000_lr2.0e-02_wd1.0e+00": 1.9597126245498657, "validation/loss_001_lr2.3e-02_wd1.0e+00": 1.845916986465454, "validation/loss_002_lr2.8e-02_wd1.0e+00": 1.6706578731536865, "validation/loss_003_lr3.3e-02_wd1.0e+00": 1.5124757289886475, "validation/loss_004_lr3.8e-02_wd1.0e+00": 1.370763897895813, "validation/loss_005_lr4.5e-02_wd1.0e+00": 1.1981356143951416, "validation/loss_006_lr5.3e-02_wd1.0e+00": 1.0329713821411133, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.8799648880958557, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.7149900794029236, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.5692652463912964, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.44843602180480957, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.30572113394737244, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.2116653025150299, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.127875417470932, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.08776941150426865, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.07081267982721329, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.05956534296274185, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.05183131620287895, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.04619157686829567, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.042380090802907944, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.03895463049411774, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.03626909852027893, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.0342923179268837, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.03294094279408455, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.03190257400274277, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.03070267289876938, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.02996681071817875, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.029953764751553535, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.03126925230026245, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.03617500513792038, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.04194006323814392, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.04727717116475105, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.051231663674116135, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.05537441745400429, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.060132913291454315, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.06949188560247421, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.06698467582464218, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.04582551121711731, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.11037848889827728, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.2222965657711029, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.519152045249939, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.6835551261901855, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.7636227607727051, "validation/loss_043_lr2.2e+01_wd1.0e+00": 1.810352087020874, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.7689547538757324, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.6090831756591797, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.2795872688293457, "validation/loss_047_lr4.3e+01_wd1.0e+00": 4.029718399047852, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.9686832427978516, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.582093253968254, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.6108630952380952, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.6572420634920635, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.7301587301587301, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.7859623015873016, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.8452380952380952, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.8784722222222222, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.8933531746031746, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.904265873015873, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9174107142857143, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9317956349206349, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9568452380952381, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9734623015873016, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9799107142857143, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9821428571428571, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9828869047619048, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9841269841269841, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9841269841269841, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9856150793650794, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9868551587301587, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9885912698412699, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9890873015873016, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9898313492063492, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9890873015873016, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9898313492063492, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9900793650793651, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9900793650793651, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9895833333333334, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9880952380952381, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9861111111111112, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9853670634920635, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.984375, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9836309523809523, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9836309523809523, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9833829365079365, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9816468253968254, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9831349206349206, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9871031746031746, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9848710317460317, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9784226190476191, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9623015873015873, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9719742063492064, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9697420634920635, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9677579365079365, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9513888888888888, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9756944444444444, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9779265873015873, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9789186507936508, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9769345238095238, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.3286495197576711, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.3473241430513154, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.45861345522913877, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.6215224203656098, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.7238280962231777, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.8077153271753863, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.8519307774833832, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.8709118074894706, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.885561008102308, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9025687074024153, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9217637832218593, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9525722883577804, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9711671887684223, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.977363882366302, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9795334421904246, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9805045433742, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.981006472206718, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.981046265521349, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9827653108751268, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9850330411701212, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9866052122515977, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9869135340012798, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9872608939271034, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9864092743088587, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9876833944451748, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9879406712198195, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9884854039436884, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9884876605655857, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9871922958324003, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9855594084407668, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.984885359108882, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9833025346988087, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9836540113604213, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9824834267069978, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9819671566939971, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9806856019438919, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9802571654561157, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9845462929241738, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9821836883387973, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9779981906976667, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9132770470515749, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9681247342116569, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9670967486443237, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9478985479934552, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.948175527680596, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9746937749329647, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9741622162578184, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9760595828639186, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9717505943484556, "id_best": 25, "lr_best": 0.00035999999999999997, "wd_best": 0.05, "train/loss_best": 0.04307992529124022, "validation/loss_best": 0.03070267289876938, "validation/acc_best": 0.9900793650793651, "validation/f1_best": 0.9879406712198195} +{"epoch": 5, "train/lr": 0.00029891323817685334, "train/loss": 0.7703413024544716, "train/grad": 0.4296988145262003, "train/loss_000_lr2.0e-02_wd1.0e+00": 1.8208509826660155, "train/loss_001_lr2.3e-02_wd1.0e+00": 1.6960590362548829, "train/loss_002_lr2.8e-02_wd1.0e+00": 1.50772029876709, "train/loss_003_lr3.3e-02_wd1.0e+00": 1.3429813766479493, "train/loss_004_lr3.8e-02_wd1.0e+00": 1.1997714042663574, "train/loss_005_lr4.5e-02_wd1.0e+00": 1.0304717826843262, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.8723766660690307, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.7268347883224487, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.5693387544155121, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.43326435089111326, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.32857252717018126, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.21887491703033446, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.15248567804694177, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.10297099001705647, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.08362622400745749, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.0746019752882421, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.06786719368770719, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.06279988179914653, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.058712085336446763, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.05579065917059779, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.05273001887835562, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.05006086747162044, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.047365609323605895, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.04471175078302622, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.04206196113489568, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.03924373948015272, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.036853646067902444, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.03488012665882707, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.03257706907577813, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.03070584530942142, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.029188781008124352, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.027751115886494516, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.02636571087874472, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.02523775488138199, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.026918845800682902, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.02918820735067129, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.03816020676866174, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.043657189216464755, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.12583613525144755, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.27517113705165686, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.6692399530857801, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.4998245769366622, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.5924736556690187, "train/loss_043_lr2.2e+01_wd1.0e+00": 1.8514258422888816, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.328314259238541, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.209460345581174, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.9830956611130386, "train/loss_047_lr4.3e+01_wd1.0e+00": 5.542804574975744, "train/loss_048_lr5.0e+01_wd1.0e+00": 5.605448359055445, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.024164877962321044, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.02342008494772017, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.02219076218083501, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.020972467986866833, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.019803169816732406, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.018315238542854786, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.016870343280024826, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.015536062470637262, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.014065183768980204, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.012625740761868655, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.011243613343685866, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.009386329520493746, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.007895720481174066, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.0065048141137231145, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.005978664413560182, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.005792969111935236, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.005684826450888068, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.005623067751294002, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.005586707262555137, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.005568037211196497, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.00553953474300215, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.005506859304732643, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.005460356943658553, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.00541591478016926, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.005371292274503503, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.005312201723718317, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.005235166840138845, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.005155534964578692, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.005054625260527246, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.005009010343492264, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.00497105566355458, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.004919279593232204, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.004822209964477225, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.004889243823272409, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.005191834760771599, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.005635068645024149, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.007257786211903294, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.007767230384342838, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.016557492410283883, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.02742912913374973, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.04667032436753218, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.03989287439242903, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.04583303742964228, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.10110957946284552, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.11851719621437472, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.14399031626139602, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.1602489693924173, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.1925272054985856, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.19037432291405998, "validation/loss_000_lr2.0e-02_wd1.0e+00": 1.6716537475585938, "validation/loss_001_lr2.3e-02_wd1.0e+00": 1.537912368774414, "validation/loss_002_lr2.8e-02_wd1.0e+00": 1.3406260013580322, "validation/loss_003_lr3.3e-02_wd1.0e+00": 1.1731982231140137, "validation/loss_004_lr3.8e-02_wd1.0e+00": 1.031568169593811, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.8678334355354309, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.7160289883613586, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.5756902098655701, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.4237695038318634, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.3000873923301697, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.21565648913383484, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.13455091416835785, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.0925733745098114, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.06829839944839478, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.05773646757006645, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.05154161527752876, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.046127066016197205, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.04158727824687958, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.037841103971004486, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.03520550951361656, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.03271747753024101, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.030815694481134415, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.028823353350162506, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.02709406428039074, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.025753546506166458, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.025285225361585617, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.02553442493081093, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.025994068011641502, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.027036674320697784, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.02785888873040676, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.027281949296593666, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.02843151055276394, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.025595471262931824, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.02652011252939701, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.032811377197504044, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.047992043197155, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.05874710902571678, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.08663392812013626, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.2405984103679657, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.23763003945350647, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.5020599961280823, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.6478392481803894, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.5411401391029358, "validation/loss_043_lr2.2e+01_wd1.0e+00": 1.960646152496338, "validation/loss_044_lr2.6e+01_wd1.0e+00": 4.15940523147583, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.243781566619873, "validation/loss_046_lr3.6e+01_wd1.0e+00": 5.634124279022217, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.89300274848938, "validation/loss_048_lr5.0e+01_wd1.0e+00": 6.218095779418945, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.6572420634920635, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.7113095238095238, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.7899305555555556, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.8509424603174603, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.8747519841269841, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.892609126984127, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9064980158730159, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.917906746031746, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9342757936507936, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9546130952380952, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9709821428571429, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9791666666666666, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9818948412698413, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9836309523809523, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9841269841269841, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9856150793650794, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9861111111111112, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9875992063492064, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9885912698412699, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9900793650793651, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9910714285714286, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9910714285714286, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9913194444444444, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9908234126984127, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9908234126984127, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9903273809523809, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9905753968253969, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9905753968253969, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9910714285714286, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9908234126984127, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9908234126984127, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9915674603174603, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9900793650793651, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9858630952380952, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9851190476190477, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9841269841269841, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9764384920634921, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9833829365079365, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9816468253968254, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9704861111111112, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9838789682539683, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9744543650793651, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9618055555555556, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9816468253968254, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9734623015873016, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.980406746031746, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9734623015873016, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.45490614095529724, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.5778929370019468, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.727705838322648, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.8194128460198824, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.8493101019635227, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.8718763498882663, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.8907465559736162, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.905627626280515, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9266440154812559, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9495759653697339, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9669128677538209, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9763257120548791, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9794073272316401, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9804982630211315, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9808280418505245, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9824286603822378, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9830813034012693, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9850217504087085, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9864580167810075, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9883108186701958, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9890335147770434, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9885398643759828, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9887199807355859, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9887367177822141, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9892928457973672, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9882553090498821, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9880760890416996, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9877804240597438, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9881910376381837, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9872619296343498, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9890485049020915, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9876073262958106, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9888212798234225, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9897548496382158, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9870333914574777, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9795125248143528, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9813131587263025, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.976961231230888, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9732455478195254, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9785391562874023, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9772907818802898, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9635758600799876, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9810949863606993, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9718806000035028, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9555372795128783, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9747999650416842, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9698146340704529, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9786859059814571, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.969353758672416, "id_best": 30, "lr_best": 0.00081, "wd_best": 0.05, "train/loss_best": 0.029188781008124352, "validation/loss_best": 0.027281949296593666, "validation/acc_best": 0.9920634920634921, "validation/f1_best": 0.9890485049020915} +{"epoch": 6, "train/lr": 0.0002924170901991409, "train/loss": 0.5333170165121556, "train/grad": 0.372034550216049, "train/loss_000_lr2.0e-02_wd1.0e+00": 1.555902099609375, "train/loss_001_lr2.3e-02_wd1.0e+00": 1.4170666885375978, "train/loss_002_lr2.8e-02_wd1.0e+00": 1.2170801734924317, "train/loss_003_lr3.3e-02_wd1.0e+00": 1.051593017578125, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.9139218235015869, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.7555686759948731, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.6086148738861084, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.4739264488220215, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.33635343074798585, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.23512323319911957, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.16916906476020813, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.11174647435545922, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.08728179313242436, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.0723857732117176, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.06508847233839334, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.0604756089951843, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.05621269078925252, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.052353780800476674, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.04879792236723006, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.04588302583433688, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.042772340839728716, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.03978297129273414, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.03679222707636654, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.033891203505918385, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.031298907306045294, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.0286250982619822, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.026444359794259072, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.02456963274627924, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.022214924218133092, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.019487481890246273, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.017929604416713117, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.017052969709038735, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.014879375100135803, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.014466140493750572, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.013617484141141176, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.020092449160292746, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.030341660995036365, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.07039975710213184, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.08325261497870087, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.15578867203556002, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.31322712258435786, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.22840926333330572, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.49397360177710653, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.9401794265862554, "train/loss_044_lr2.6e+01_wd1.0e+00": 1.7230095362197608, "train/loss_045_lr3.1e+01_wd1.0e+00": 1.756986344559118, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.721903835255653, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.87051423878409, "train/loss_048_lr5.0e+01_wd1.0e+00": 4.006085945721716, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.022518116496503354, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.02152531404979527, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.01993408939335495, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.01849090582691133, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.017242807890288533, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.015799931096844376, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.014451726693660022, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.013116826973855496, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.011403544198255986, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.009708265953231604, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.008298020411748439, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.006738772586686537, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.0060684973001480106, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.0057719377113971855, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.00566965413687285, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.005619025506312028, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.0055689024057937785, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.005512379514984786, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.0054266152845229955, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.005335991112806368, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.005225659740972333, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.00512003862997517, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.005032056161435321, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.004921358099090866, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.004809428956941701, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.004653708100377117, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.004517936443444341, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.004384265393018723, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.004199161555588944, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.00398241130184033, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.003849779302836396, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0036772126007417684, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.003369422423565993, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.003483063403382403, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0034832061399538363, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.005025658339832262, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.006243242831149018, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.010941493013577315, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.012373549586260864, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.02025453440967032, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.029661485403843453, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.02369598097394137, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.03765749179739595, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.06358565997517024, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.09669496468982244, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.10285220432909158, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.1819785733431688, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.13265633434755797, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.16832811170764067, "validation/loss_000_lr2.0e-02_wd1.0e+00": 1.4326486587524414, "validation/loss_001_lr2.3e-02_wd1.0e+00": 1.2910963296890259, "validation/loss_002_lr2.8e-02_wd1.0e+00": 1.0918744802474976, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.9308368563652039, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.7980368733406067, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.6450740098953247, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.5024580955505371, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.3735741376876831, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.25103703141212463, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.167605921626091, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.1154002994298935, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.0789104774594307, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.0642872229218483, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.05355110019445419, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.04745273292064667, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.043431755155324936, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.03951432555913925, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.03618567809462547, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.033338502049446106, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.03127118572592735, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.029306216165423393, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.027711080387234688, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.026331840083003044, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.025201644748449326, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.024276981130242348, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.023579001426696777, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.023244550451636314, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.02319316938519478, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.02348540537059307, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.02451440878212452, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.0257722195237875, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.027471642941236496, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.029592188075184822, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.030883697792887688, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.04071877896785736, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.056598491966724396, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.04504813626408577, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.06090619042515755, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.09042244404554367, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.19285441935062408, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.2858441174030304, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.23428215086460114, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.4205304980278015, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.9320949912071228, "validation/loss_044_lr2.6e+01_wd1.0e+00": 1.6666454076766968, "validation/loss_045_lr3.1e+01_wd1.0e+00": 1.9212918281555176, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.332674980163574, "validation/loss_047_lr4.3e+01_wd1.0e+00": 2.8653671741485596, "validation/loss_048_lr5.0e+01_wd1.0e+00": 5.096304893493652, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.7591765873015873, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.8139880952380952, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.8683035714285714, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.8921130952380952, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9057539682539683, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.9164186507936508, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9312996031746031, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.9494047619047619, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.96875, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9764384920634921, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9799107142857143, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9821428571428571, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9828869047619048, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9846230158730159, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9853670634920635, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9856150793650794, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9871031746031746, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9885912698412699, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9890873015873016, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9903273809523809, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9908234126984127, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9908234126984127, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9908234126984127, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9915674603174603, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9925595238095238, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9925595238095238, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9923115079365079, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9923115079365079, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9913194444444444, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9908234126984127, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9908234126984127, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9905753968253969, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9915674603174603, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9875992063492064, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9875992063492064, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9890873015873016, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9903273809523809, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.986359126984127, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9866071428571429, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9885912698412699, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9900793650793651, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9846230158730159, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9878472222222222, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9841269841269841, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.982390873015873, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9794146825396826, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9806547619047619, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9774305555555556, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.6809824353082133, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.7719617799132685, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.8491856575281514, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.8768901892111898, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.893245217594394, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.9065352547769153, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.9239316881480993, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9444791943242159, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9642193744914355, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9730316058399934, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9768764791561337, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9793997550279953, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9799230652086647, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9814900945399001, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9827080840722038, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9831719256586957, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.984520056688052, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9870894012424626, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9874965897762488, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.988444706326655, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9887258808141889, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9889075533707987, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9887337292167628, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9896760845077373, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9908926032676859, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9912050424633292, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9908428422089861, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9909371214019378, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9906685528687087, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9899946978581676, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9894162667651714, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9896014976645103, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9898614812385015, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9906441104337349, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9874650898944495, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9825542660133889, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9871259102788347, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9877697523579356, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9845269316627213, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9836233544248135, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9860573309546019, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9895291504974347, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9813290269943894, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9853884586773899, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9810483677568222, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9789592932647372, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9777245720105403, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9743346480849201, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9752338229353062, "id_best": 24, "lr_best": 0.0003, "wd_best": 0.05, "train/loss_best": 0.031298907306045294, "validation/loss_best": 0.024276981130242348, "validation/acc_best": 0.9925595238095238, "validation/f1_best": 0.9908926032676859} +{"epoch": 7, "train/lr": 0.00027969249556793234, "train/loss": 0.3722426416352391, "train/grad": 0.298421357832849, "train/loss_000_lr2.0e-02_wd1.0e+00": 1.3361684799194335, "train/loss_001_lr2.3e-02_wd1.0e+00": 1.1948637390136718, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.9998846626281739, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.8441440200805664, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.7159234857559205, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.5682545256614685, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.43213241815567016, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.31519806146621704, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.21144382536411285, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.14328052550554277, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.106239268258214, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.0825365199521184, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.07229670887812972, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.0642322251945734, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.05932490305043757, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.055790293905884025, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.052134556425735355, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.04862425838597119, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.04534953421913088, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.04260851892642677, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.03957009680569172, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.03664754321798682, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.03356675167568028, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.03043589393608272, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.027315971832722427, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.023716204240918158, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.020640145242214202, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.017726958515122532, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.014012375781312585, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.00993398517370224, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.007351610064506531, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.006035305000841618, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.005303257303312421, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.008409535456448793, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.009481400763615967, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.01148815411143005, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.043887561531737444, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.07121496747247874, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.07355145936831832, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.1022646217327565, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.11617284562438726, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.13115449237637222, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.2664964769408107, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.37658121017739177, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.7283712770603598, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.9172403742838651, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.6833962044026705, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.4169339957553895, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.6205585008021446, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.021128969741985203, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.019967407658696174, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.018229472297243775, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.016788571942597627, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.01559898109640926, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.014203372146002948, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.012759235152043403, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.011185088090132921, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.009352331927511842, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.0077270304353442044, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.006655056758318096, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.006054270811146126, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.005868653415236622, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.005743114061187953, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.005652688096743077, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.005579436930129304, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.005481224982067942, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.005376291834400035, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.005274120410322211, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.005192870189785026, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.005096173259662464, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.0049861343621159905, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.004860110929294024, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.004716471712163184, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.004558236916636815, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.004334388064453378, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.004125625005763141, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.00388547158545407, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0035039370827144012, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0029784579492843476, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0025638320028883756, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0021744942969235126, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0021848956160738452, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0020410455794626615, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0032563164855855574, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.004031986412011293, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.008091215394710503, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.011324610506418798, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.013351417792632034, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.014714890519036454, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.016965484858169524, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.019310112074436506, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.030930328940249396, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.04137520761309592, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.06831034877330602, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.07233232275063875, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.12024929980354561, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.13349704455422973, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.1326144467407371, "validation/loss_000_lr2.0e-02_wd1.0e+00": 1.2410318851470947, "validation/loss_001_lr2.3e-02_wd1.0e+00": 1.1002956628799438, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.9088536500930786, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.7568842172622681, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.6314574480056763, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.486130028963089, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.35501450300216675, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.24907632172107697, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.1597055345773697, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.10410202294588089, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.07878676801919937, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.062183354049921036, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.053774602711200714, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.046504322439432144, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.041903480887413025, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.03868836537003517, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.03575051948428154, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.033146753907203674, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.03109019622206688, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.029703250154852867, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.028227923437952995, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.02731146849691868, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.02657671645283699, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.025844315066933632, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.02499445527791977, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.023776251822710037, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.02282758429646492, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.022188521921634674, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.022153371945023537, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.022946501150727272, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.02380031906068325, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.023701172322034836, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.02427797019481659, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.025182822719216347, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.03174465522170067, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.03888275474309921, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.07554413378238678, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.10873270779848099, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.13355383276939392, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.15050406754016876, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.26214689016342163, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.22674965858459473, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.4768962562084198, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.7857877016067505, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.7753536701202393, "validation/loss_045_lr3.1e+01_wd1.0e+00": 1.7491687536239624, "validation/loss_046_lr3.6e+01_wd1.0e+00": 1.8425363302230835, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.071817636489868, "validation/loss_048_lr5.0e+01_wd1.0e+00": 4.006660461425781, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.8315972222222222, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.8673115079365079, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.8965773809523809, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.9084821428571429, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9186507936507936, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.9342757936507936, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9516369047619048, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.9685019841269841, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9766865079365079, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9799107142857143, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9821428571428571, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9833829365079365, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9848710317460317, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9861111111111112, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.986359126984127, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9880952380952381, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9888392857142857, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9900793650793651, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9900793650793651, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9905753968253969, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9905753968253969, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9905753968253969, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9913194444444444, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9920634920634921, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9923115079365079, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9925595238095238, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9923115079365079, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9923115079365079, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9915674603174603, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9910714285714286, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9910714285714286, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9888392857142857, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9888392857142857, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.988343253968254, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9898313492063492, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9888392857142857, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9893353174603174, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9873511904761905, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9861111111111112, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9898313492063492, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9848710317460317, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9846230158730159, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9791666666666666, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9818948412698413, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.7934947935570831, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.8453977987310114, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.880652061117806, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.896577866317054, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.9089702331977788, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.9279869810018431, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.9469316030394892, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9643558224503082, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9733031466637951, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9770570816497036, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9795652161586759, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9803739678581891, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9816651252613456, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9833449466434758, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9838935767933928, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9858695073137391, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9873657241374861, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9883598200655157, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9880013326160777, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9887729996724304, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9886857961752286, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9886857961752286, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9900846064587241, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9906714915312278, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9906750944922086, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9905838020209172, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9909014234007467, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9907244412731411, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9906769865602579, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9902751634023408, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.989910839904885, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9897535603593746, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9898766957186138, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9901960942767987, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9888318902244733, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9880022037335064, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9848653120856361, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9836723629332179, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9861713903871276, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9865606678076243, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9874311782481345, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9873930353331077, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9853895022578776, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9829784295991072, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9873366148170435, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.981673208907837, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.98077982701451, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9739368312199346, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9761546877196988, "id_best": 28, "lr_best": 0.00057, "wd_best": 0.05, "train/loss_best": 0.014012375781312585, "validation/loss_best": 0.022153371945023537, "validation/acc_best": 0.9925595238095238, "validation/f1_best": 0.9906769865602579} +{"epoch": 8, "train/lr": 0.0002612959497061927, "train/loss": 0.24107168063521386, "train/grad": 0.2096681268326938, "train/loss_000_lr2.0e-02_wd1.0e+00": 1.1557791709899903, "train/loss_001_lr2.3e-02_wd1.0e+00": 1.0176247978210449, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.8318465328216553, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.6847640180587768, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.563648943901062, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.4254865550994873, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.3062436842918396, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.21498277097940444, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.13948129028081893, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.0984676481038332, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.08107566118240356, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.06886785646900534, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.062366127725690605, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.056424880651757124, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.05236255530267954, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.04934384343214333, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.0460762320458889, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.042876085918396714, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.03966917414218187, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.03693155825138092, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.033743853764608506, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.030662486599758267, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.027517314702272415, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.02428476955741644, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.021130875051021576, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.017453396348282694, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.014305204236879945, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.01163911552168429, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.008261910071596504, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.005218563452363014, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0035082174371927977, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.0026878155767917633, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.0022377985157072543, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.002345013078302145, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.007062553549185395, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.010091524235904217, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.03644462225958705, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.049370342399924994, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.05214963614940643, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.0538272270001471, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.08245708632282912, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.08949809554964304, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.1882795017864555, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.19144401917234063, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.35125074985437094, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.45904996458441016, "train/loss_046_lr3.6e+01_wd1.0e+00": 1.0763294339925051, "train/loss_047_lr4.3e+01_wd1.0e+00": 1.3184462149441243, "train/loss_048_lr5.0e+01_wd1.0e+00": 1.6674958500824868, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.019494880167767407, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.01822824210394174, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.01644468483980745, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.015024360488168895, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.01383603353984654, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.012338980995118619, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.010708657153882086, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.009083826357964427, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.007344141870271414, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.006155011446680874, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.005708899646997452, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.005483336505712941, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.005383338521933183, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.005298583778785542, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.0052281455200864, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.005162517738644965, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.005076943763415329, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.004975242277723737, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.004846966800978407, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.004734007735969499, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.004600467164127622, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.004456813221913762, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0042927580149262215, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.004051235224033008, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0038009999284986406, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.00345870233795722, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0031450782571482705, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0028299738460918888, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.00233477064561157, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0017444152779353317, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0012868748494474858, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0010017485452954134, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0008032980697180392, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0007221991249116399, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0015868061443006808, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0031542606378326355, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.008802433754704709, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.008650962227580595, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.00788876263423274, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.009638481452171482, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.010223055063022022, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.014895992393509926, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.022867308471931275, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.022507366727184883, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.04057063844914527, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.04728041238287832, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.06922055307318349, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.08888913398365736, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.09425968822701099, "validation/loss_000_lr2.0e-02_wd1.0e+00": 1.0910743474960327, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.95494145154953, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.7725275754928589, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.627564549446106, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.5073837041854858, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.3713531494140625, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.25873422622680664, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.17565040290355682, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.10921351611614227, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.07811157405376434, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.06458886712789536, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.054026853293180466, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.0480157844722271, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.04243026673793793, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.03877277299761772, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.03613472729921341, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.033410731703042984, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.03107886202633381, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.029118206351995468, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.027535052970051765, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.025889253243803978, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.024463726207613945, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.023331042379140854, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.022412234917283058, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.021806925535202026, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.021605735644698143, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.021660879254341125, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.02208242006599903, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.022519836202263832, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.021984856575727463, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.022745804861187935, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.02306658774614334, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.02334190532565117, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.023381086066365242, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.03193751350045204, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.04980774223804474, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.10723073035478592, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.12156108021736145, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.16894686222076416, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.239939346909523, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.2599601149559021, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.24548158049583435, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.5509885549545288, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.8157534003257751, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.8043603897094727, "validation/loss_045_lr3.1e+01_wd1.0e+00": 1.8035491704940796, "validation/loss_046_lr3.6e+01_wd1.0e+00": 2.3035616874694824, "validation/loss_047_lr4.3e+01_wd1.0e+00": 2.1831233501434326, "validation/loss_048_lr5.0e+01_wd1.0e+00": 2.9689323902130127, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.8685515873015873, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.8859126984126984, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.9012896825396826, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.9141865079365079, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9248511904761905, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.9451884920634921, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9637896825396826, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.9754464285714286, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9799107142857143, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.982390873015873, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9828869047619048, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.984375, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9851190476190477, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9861111111111112, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9868551587301587, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9880952380952381, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9880952380952381, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9888392857142857, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9895833333333334, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9895833333333334, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9900793650793651, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9900793650793651, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9913194444444444, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9913194444444444, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9915674603174603, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9918154761904762, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9928075396825397, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9930555555555556, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9933035714285714, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9930555555555556, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9933035714285714, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9900793650793651, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9893353174603174, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9898313492063492, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9873511904761905, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.988343253968254, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9898313492063492, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9895833333333334, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9861111111111112, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9873511904761905, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9893353174603174, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9851190476190477, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9841269841269841, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9846230158730159, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9816468253968254, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.8441164742476837, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.8634072432964294, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.8837951221929411, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.900101107109364, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.9147107508385756, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.9396455227526647, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.9594673629777378, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9716672980473969, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9772163892302321, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9799183425662625, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9800891544152059, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9815470957737005, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9822060586081344, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9836405526760034, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9849887320572434, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9863685812311741, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9860135883662624, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.986598060329363, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9876865794605356, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9879395631762122, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9886572602083659, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9883407574723276, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9896560634995064, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9900177354964397, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9900770311045493, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9902675146348818, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9903245782913834, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9901018671965199, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9904243508139368, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9908244197336531, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9913403807045109, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9917493605454064, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9913836824030695, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9914657422560015, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9900172879222184, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9877621233256642, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9862264750076186, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9871523304621994, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9848510844230205, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9855060202146999, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9879225652865001, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9881034690061835, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9820989091685661, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9842587962497229, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9865195920892262, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9803399835209528, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9816344724804429, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9828010027669837, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9801783936207779, "id_best": 31, "lr_best": 0.0009299999999999999, "wd_best": 0.05, "train/loss_best": 0.0026878155767917633, "validation/loss_best": 0.02306658774614334, "validation/acc_best": 0.9933035714285714, "validation/f1_best": 0.9917493605454064} +{"epoch": 9, "train/lr": 0.00023803200426111704, "train/loss": 0.17034632731229066, "train/grad": 0.17228579111397266, "train/loss_000_lr2.0e-02_wd1.0e+00": 1.0351480102539063, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.9017597579956055, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.7234956598281861, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.5819391560554504, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.46541465759277345, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.3367005491256714, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.23453512370586396, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.16056271240115166, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.10623472854495049, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.08322081435471773, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.0728575518913567, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.06438844123855234, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.059247510470449925, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.05403316874988377, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.05022410929203033, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.047274909624829886, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.043970479564741254, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.040575753711163995, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.03720270992256701, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.034240593537688255, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.030836696522310376, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.027526855608448385, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.024129169089719654, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.020799071667715906, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.017603927291929722, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.01400018430314958, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.010993145434185862, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.008492672350257635, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.00569603537209332, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0034380146861076356, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0023178557120263578, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.001678908048197627, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.0008635297697037459, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.000316224405542016, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.0004349718801677227, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.0021923478692770005, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.03379288081079721, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.027738573662936687, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.04064917080104351, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.029505462935194373, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.02157016850076616, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.057830641753971575, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.10906384424306452, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.0828798705805093, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.17816052665002644, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.24787105059251188, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.5848186939861626, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.6347133392188699, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.994030015701428, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.018479474899359048, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.017233807197771966, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.015543450633995235, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.014180058441124856, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.012964191217906772, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.011314165443181992, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.009579433423932643, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.007988230597693474, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.006502990723820403, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.005909882491687312, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.005714119832264259, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.005603866435703822, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.005544148737681098, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.005483856675564312, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.005432661556405947, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.00538067399756983, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.005308580208220519, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.005216283849440515, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.005098503729386721, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.004978607794037089, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.00481560098240152, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.004629527605138719, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.004392404428072041, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.004105001968346187, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.003783493829832878, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0033388234725498477, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0028762480121076804, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.002410562112854677, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0018086929886521829, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0012715483476858935, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0007982644623916713, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0005781249790970833, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.00039744644064057863, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.00014953081060752992, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.00026692599856573904, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0012062611256829926, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0066274962355007214, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.005660438301831838, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.008484055466907654, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.008253084083324966, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.005869047778803137, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.011926986614228892, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.015588250852086916, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.014849450135051255, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.027586128470019317, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.03193514332157677, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.053235026584482634, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.05916875208381132, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.08028373125725445, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.9751894474029541, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.8442888855934143, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.669035792350769, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.5292336940765381, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.41454723477363586, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.2910672128200531, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.1969774067401886, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.12952379882335663, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.08471683412790298, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.06599706411361694, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.056849829852581024, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.048812925815582275, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.043936602771282196, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.03925389051437378, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.036076124757528305, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.03379072993993759, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.03139084577560425, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.029017087072134018, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.026917068287730217, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.02537389099597931, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.024083701893687248, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.02320190519094467, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.02286619134247303, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.022795280441641808, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.022835414856672287, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.023123849183321, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.02339516393840313, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.02355051599442959, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.023214293643832207, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.024010181427001953, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.023771828040480614, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.023102037608623505, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.023727351799607277, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.023553404957056046, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.031718600541353226, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.04044251888990402, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.11086399853229523, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.11863899976015091, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.15397556126117706, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.17321190237998962, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.2073533684015274, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.29695773124694824, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.44890519976615906, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.6172160506248474, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.6288403272628784, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.7761730551719666, "validation/loss_046_lr3.6e+01_wd1.0e+00": 1.371734857559204, "validation/loss_047_lr4.3e+01_wd1.0e+00": 1.2754430770874023, "validation/loss_048_lr5.0e+01_wd1.0e+00": 1.5088673830032349, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.8859126984126984, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.8998015873015873, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.9131944444444444, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.9263392857142857, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9409722222222222, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.9603174603174603, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9739583333333334, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.9796626984126984, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9828869047619048, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9833829365079365, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.984375, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9858630952380952, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9861111111111112, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9875992063492064, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9875992063492064, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9880952380952381, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9888392857142857, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9895833333333334, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9898313492063492, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9903273809523809, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9910714285714286, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9915674603174603, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9920634920634921, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9915674603174603, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9915674603174603, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9915674603174603, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9915674603174603, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9918154761904762, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9918154761904762, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9918154761904762, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9925595238095238, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9923115079365079, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9923115079365079, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9913194444444444, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9885912698412699, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9880952380952381, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9888392857142857, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9900793650793651, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9930555555555556, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9898313492063492, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9871031746031746, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9861111111111112, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.988343253968254, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9900793650793651, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9868551587301587, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9866071428571429, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9878472222222222, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.8669183693946275, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.8841294851646869, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.9011036783913828, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.9173479968998816, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.9350849694868304, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.9560056310880685, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.9707853581740832, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9773129582709152, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9809264910815937, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9809325414193718, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9818235095737681, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9829724935760558, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9835095434939602, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9853968923629508, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9857620041069375, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.986189526794048, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.987276257573152, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9880503894766465, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9882109977157602, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9888637642210631, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9894502635430997, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9899028545490716, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9909046547152046, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9902624533333372, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9906245773682023, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9907204911942517, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9906735454849587, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9908541939132197, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9906347269913217, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9904600577774132, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9905172458849206, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9909449166963998, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.990379409073103, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.990465866569469, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9892822661072683, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9890860996430357, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9866502749642085, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.983976744685734, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9870189576338627, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9866865272188287, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9928041553806013, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9870385172132988, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9831301285654133, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9851501887286768, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9856719825174287, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9871941858137006, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9864263506545382, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9847602315596733, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.986745069382716, "id_best": 40, "lr_best": 0.0042, "wd_best": 0.05, "train/loss_best": 0.02157016850076616, "validation/loss_best": 0.2073533684015274, "validation/acc_best": 0.9930555555555556, "validation/f1_best": 0.9928041553806013} +{"epoch": 10, "train/lr": 0.00021091808096876188, "train/loss": 0.12150993455201388, "train/grad": 0.12745975626632572, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.9343999481201172, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.8062787199020386, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.6347919201850891, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.49808922290802005, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.38734695196151736, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.27152222573757173, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.185100674033165, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.1249547965824604, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.08918329257518053, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.07433521449565887, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.06674954114481807, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.060003904197365045, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.055666309809312225, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.051078901859000325, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.04773400385864079, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.04492762411944568, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.041898647621273995, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.03861366499215364, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.035176022257655856, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.032200715811923145, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.028738361531868577, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.025347756007686257, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.02186942093074322, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.018315471531823276, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.01476322054862976, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.010846658693626523, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.007678841287270188, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.005325989294797182, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0032149867806583643, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0014601049106568098, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0007650046329945326, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.0005260544177144766, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.00031557638198137283, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.00022701941430568694, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.00012356759048998356, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.00011958535760641098, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.012328317342326044, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.014473171913996339, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.01343825925141573, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.014264493333175778, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.01873635908588767, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.023673520293086767, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.03860800046473742, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.034576197564601896, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.0704126859549433, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.10241066826507449, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.21091049555689095, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.30396360851824283, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.4765012517478317, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.01745771711692214, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.016281415834091605, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.014720014939084649, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.013414478907361627, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.012181764882989228, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.010497094339225441, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.008815007302910089, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.007205861015245318, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.0060888450621860105, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.005710741620277986, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.0055609730159631, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.005428981631994247, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.0053466526855481785, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.005247234257403761, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.005166743025183678, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.005089328433386981, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.0049985623091924935, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.004880321637610905, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.004742967615893576, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.004622329721460119, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.004465325940254843, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.0042704578458506144, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.004040945386368549, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.003730846127655241, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0033483814529972735, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0028907548893766944, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0024448724927970036, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.001998049744997843, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0013786323034037195, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0007344028655188595, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.00034680253612350497, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0002304527331898498, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.00013290007321984377, "train/grad_033_lr4.3e+00_wd1.0e+00": 9.631571092313606e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 9.102102825124803e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.00019666127780411103, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.003097463799097162, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0035328781128252914, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.003033159292635735, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.005328311836917641, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.005399197758074171, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.00626019516914959, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.006981050636193071, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.010114562983167596, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.012452559891896095, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.024167298788881308, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0354276483241402, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.039559452394400146, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.05266587903567693, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.8860951662063599, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.7596986889839172, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.5900002717971802, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.4546584188938141, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.346375972032547, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.23656073212623596, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.15606102347373962, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.10220759361982346, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.07256445288658142, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.05937238037586212, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.05224289745092392, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.045535679906606674, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.04138133302330971, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.037065353244543076, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.034034352749586105, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.03187146782875061, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.02967195212841034, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.027671638876199722, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.025831107050180435, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.02450236864387989, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.02323845773935318, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.022425934672355652, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.021804677322506905, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.0215102881193161, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.02169337123632431, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.022000964730978012, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.02248694747686386, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.023048879578709602, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.021959589794278145, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.02119048312306404, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.021728573366999626, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.02173757553100586, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.02277299389243126, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.023129401728510857, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.031013216823339462, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.0360717847943306, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.07031328231096268, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.13205407559871674, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.10908270627260208, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.1677984893321991, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.2878013551235199, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.27101388573646545, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.3977787494659424, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.524425208568573, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.47647616267204285, "validation/loss_045_lr3.1e+01_wd1.0e+00": 1.2130624055862427, "validation/loss_046_lr3.6e+01_wd1.0e+00": 1.4280322790145874, "validation/loss_047_lr4.3e+01_wd1.0e+00": 1.7885075807571411, "validation/loss_048_lr5.0e+01_wd1.0e+00": 1.6217193603515625, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.894593253968254, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.9037698412698413, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.919890873015873, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.933531746031746, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9501488095238095, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.9692460317460317, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9769345238095238, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.9801587301587301, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9821428571428571, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9836309523809523, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9851190476190477, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.986359126984127, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9873511904761905, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9885912698412699, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9895833333333334, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9893353174603174, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9900793650793651, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9910714285714286, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9913194444444444, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9913194444444444, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9923115079365079, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9930555555555556, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9935515873015873, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9928075396825397, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9928075396825397, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9925595238095238, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9928075396825397, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9930555555555556, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9930555555555556, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9925595238095238, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9925595238095238, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9928075396825397, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9925595238095238, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9923115079365079, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9925595238095238, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9908234126984127, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9888392857142857, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9910714285714286, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9908234126984127, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9895833333333334, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9893353174603174, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9885912698412699, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9878472222222222, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9915674603174603, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9858630952380952, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9873511904761905, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9831349206349206, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9841269841269841, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.8776585362633559, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.8897590508211816, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.9088202561739968, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.9269174491204473, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.9453233729428137, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.9649913976554044, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.9734397564366052, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9774442766435004, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9796582158692133, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9807321239788755, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.982053642099922, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9836850121479427, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9854846866359698, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9867192812160771, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9876759091388458, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9871412645324149, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9877279744429637, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9884626612027906, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9890099710358146, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9893649904963798, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.990803920796465, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9919388729709381, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9926627106112288, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9919475588285551, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9919475588285551, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9913990241541536, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9910154578082002, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9917645581922397, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9919424429879329, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9915340379872348, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9907717069954289, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9905692096410573, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.990784474853945, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9906462595393775, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9903562321929191, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.990618632101084, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9887983977984509, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9870567796185358, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9903913373442279, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9887561685031132, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9877791552815277, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9872212819128741, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9848264692960077, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9856661809390329, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9903626178774603, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9826258858510053, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9849900001987948, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9818797899964833, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.982489677168923, "id_best": 22, "lr_best": 0.00021599999999999996, "wd_best": 0.05, "train/loss_best": 0.02186942093074322, "validation/loss_best": 0.021804677322506905, "validation/acc_best": 0.9935515873015873, "validation/f1_best": 0.9926627106112288} +{"epoch": 11, "train/lr": 0.00018113997589164516, "train/loss": 0.10055014967918396, "train/grad": 0.09537951365113258, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.8521497821807862, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.728820743560791, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.5634554481506348, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.4323459267616272, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.3291756075620651, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.22699134796857834, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.15234840646386147, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.10550845794379711, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.08128508795052766, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.07043625142425299, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.06439501540735364, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.05855686826631427, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.054542213194072243, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.05009999168105424, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.04664221664890647, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.04374257548712194, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.040409991331398484, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.036844263663515446, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.03313284024596214, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.02991191397421062, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.026231863424181937, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.022708454485982656, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.01900607648305595, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.015176274664700031, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.011198781160637737, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.007008762015029788, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.00430275515653193, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0027365535218268635, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0015315059013664722, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0008254218846559525, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0005530724208801985, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.0003940120153129101, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.0002477181144058704, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.0001866754423826933, "train/loss_034_lr5.1e+00_wd1.0e+00": 8.894981816411018e-05, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.818645142018795e-05, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.002520483508706093, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.0017896946426481008, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.0060429472289979455, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.003054358446970582, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.0070806485321372745, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.004874824900180101, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.007457606643438339, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.021120945075526833, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.05002750417217612, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.1081403682474047, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.11698217686265706, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.27003164892084897, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.21480418918654323, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.016638168515637517, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.015436566625721753, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.013794322046451271, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.012345235073007643, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.010936228411737829, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.009166472086217254, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.007588934393133968, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.006347078531980514, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.005727246936876327, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.005526764884125441, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.005433646697783842, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.005345516660017893, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.005276462633046322, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.005183813312905841, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.005097235626017209, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.0050195205979980525, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.004925311145198066, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.004810143444919959, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.004682312794902828, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.004553535646409728, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.0043631103163352235, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.004131747209612513, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0038370282351388595, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0034574094973504545, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0029616660376632353, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0022744216873979897, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0016285004811652471, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0011417745860853757, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0007141008065718779, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.00036179331859329976, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.00023517978989730183, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0001690757291362388, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0001113982936612956, "train/grad_033_lr4.3e+00_wd1.0e+00": 8.267499788644272e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 5.02661929971282e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 2.9399421168001537e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0015455788234125932, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0008626547949788638, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.001906870902431309, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0025270606826600346, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0033757576708981054, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0019185207872860063, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.003653305791155073, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.00653236560624546, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.011019024701239334, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.015910104163148097, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.023674327383365158, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.03010504350696638, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.02798146852812576, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.8181864023208618, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.6952183246612549, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.5297083258628845, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.39883506298065186, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.2973591983318329, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.19916312396526337, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.1283336728811264, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.08682665228843689, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.06545635312795639, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.0549667552113533, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.04905064031481743, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.04318580403923988, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.03942367807030678, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.03557316213846207, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.0328378863632679, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.030843939632177353, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.028806664049625397, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.02691045217216015, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.02530200034379959, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.02409200556576252, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.02311931736767292, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.02254960499703884, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.022334901615977287, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.02252940461039543, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.022931447252631187, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.023376327008008957, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.02334999293088913, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.02302737347781658, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.02265877276659012, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.02243335172533989, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.02315099537372589, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.02292073704302311, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.023615635931491852, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.023777304217219353, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.03056611679494381, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.0350445918738842, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.06630970537662506, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.09443046152591705, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.10094576328992844, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.13747689127922058, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.22025913000106812, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.1570746749639511, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.3001048266887665, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.4250480532646179, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.3947938084602356, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.7719683051109314, "validation/loss_046_lr3.6e+01_wd1.0e+00": 1.0220428705215454, "validation/loss_047_lr4.3e+01_wd1.0e+00": 1.0888028144836426, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.9774711728096008, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.8995535714285714, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.9077380952380952, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.9243551587301587, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.9407242063492064, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.957093253968254, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.9732142857142857, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9794146825396826, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.982390873015873, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9826388888888888, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9841269841269841, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9851190476190477, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9866071428571429, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9880952380952381, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.988343253968254, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9885912698412699, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9893353174603174, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9900793650793651, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9898313492063492, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9908234126984127, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9913194444444444, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9915674603174603, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9918154761904762, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9915674603174603, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9918154761904762, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9913194444444444, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9908234126984127, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9908234126984127, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9910714285714286, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9925595238095238, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9923115079365079, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9925595238095238, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9925595238095238, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9923115079365079, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9928075396825397, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9905753968253969, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9928075396825397, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9905753968253969, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9910714285714286, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9900793650793651, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9903273809523809, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9888392857142857, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9898313492063492, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9918154761904762, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9905753968253969, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9903273809523809, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9880952380952381, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9893353174603174, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.8837824521699362, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.8935262130125261, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.913994827447776, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.9346939181708559, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.9522082464026699, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.970020541642536, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.976774574214402, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9797455620139229, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9800110873585952, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9812413409981722, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9820076244362617, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.983863919358443, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9861176787182199, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9859853898316873, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9861697461416155, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9869497795701166, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9881983202834173, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9880639369663364, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.989250976881501, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9895322866254914, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9897107326342451, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9902525013148384, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9897143805709065, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9900704035791085, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9897199742042783, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9896809987430902, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9896348066504627, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9897582062654384, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9905892818040799, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9913095957136552, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9904468082849288, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.990671041597659, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9906052738947903, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9906445440035819, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9899837924097971, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9907982999965221, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9894334967229129, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9908466432705714, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9892077209149529, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9893786535750996, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.987744761699048, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9882959303527903, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9850299393462025, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9871998308415633, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9898645557521042, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9882704970289856, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9889321733946561, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9855128769709344, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9874843096255881, "id_best": 35, "lr_best": 0.0018, "wd_best": 0.05, "train/loss_best": 3.818645142018795e-05, "validation/loss_best": 0.0350445918738842, "validation/acc_best": 0.9928075396825397, "validation/f1_best": 0.9907982999965221} +{"epoch": 12, "train/lr": 0.0001499999999999999, "train/loss": 0.08228916630148887, "train/grad": 0.06216059726662934, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.8014676237106323, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.6802157306671143, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.5172431814670563, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.38940420627593997, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.29198908746242525, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.1985250724852085, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.13143084749579428, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.09490103174000979, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.0766597249917686, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.06767507882788777, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.062365367403253914, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.05689054686576128, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.05298589190468192, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.048483087504282596, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.044947758037596944, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.041986323185265066, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.038555975630879404, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.03486574699170888, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.03108228063210845, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.027796753300353885, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.02404851165600121, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.020435068663209675, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.01659645965322852, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.012646305477246642, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.008865419663488866, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.005316197918727994, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.003246713038533926, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0020519039034843445, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.001152672814205289, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.000643845796585083, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.00045276629738509654, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.00034122309647500516, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.00022672702558338643, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.00016841686330735684, "train/loss_034_lr5.1e+00_wd1.0e+00": 8.573225699365139e-05, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.603140823543072e-05, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.00032239808700978756, "train/loss_037_lr8.3e+00_wd1.0e+00": 6.380647420883178e-05, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.0017117594368755817, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.0030249001551419497, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.0010766152571886779, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.00041379800997674463, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.002688803533092141, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.006545570846647024, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.010883381832391023, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.005054234582930803, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.07758906647562981, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.07076860073953867, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.06624096991494298, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.01616460308432579, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.01503854647744447, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.013465506248176098, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.01200920301489532, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.010593134339433163, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.00885959319304675, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.007218112135306, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.006175355821615085, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.005775782512500882, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.005634302907274105, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.005553656978299841, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.005454700239934027, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.0053675959806423635, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.005246146245335695, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.005143401921959594, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.005039132292731665, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.004906784596387297, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.00475717287074076, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.004584570890147006, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.0044187849560694305, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.004186006817762973, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.003904335190891288, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0035495385657122822, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0031044561518137927, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0025731961951896663, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0018569334262792836, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0012666341380645463, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0008524088025842502, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0004887800374126527, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0002644739034076338, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.00018701038545259507, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.00014095753143919865, "train/grad_032_lr3.7e+00_wd1.0e+00": 9.383044165588217e-05, "train/grad_033_lr4.3e+00_wd1.0e+00": 7.348672031412206e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 4.41429499358037e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 2.6830749722854818e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0003716623286622657, "train/grad_037_lr8.3e+00_wd1.0e+00": 7.133787636506924e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0007685852559242423, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0009176321041984152, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.001113553368775334, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.00038023203019202736, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.001484582520820268, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0019562875576604895, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.003079965018381732, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0032412556742636455, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.011935711885359381, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.012176814724096336, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.014642205077932912, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.7663963437080383, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.6460294723510742, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.4839213490486145, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.3574509918689728, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.26262351870536804, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.17309603095054626, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.11033685505390167, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.07783938944339752, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.06075156107544899, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.05189412832260132, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.046650420874357224, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.0413905531167984, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.037881091237068176, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.03426385670900345, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.03188449144363403, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.030035333707928658, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.028099635615944862, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.026423081755638123, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.024896837770938873, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.023951318114995956, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.02306806854903698, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.022670358419418335, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.022480396553874016, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.022289972752332687, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.02217317931354046, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.022082198411226273, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.022164206951856613, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.02212263084948063, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.022072158753871918, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.02211817540228367, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.022684495896100998, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.022593704983592033, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.023303160443902016, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.02345430478453636, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.029959633946418762, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.03408161178231239, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.06208955869078636, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.08961725980043411, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.10310739278793335, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.13146470487117767, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.19084642827510834, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.16552147269248962, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.2610563337802887, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.3732571601867676, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.35421738028526306, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.8026894927024841, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.9495722651481628, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.7201547622680664, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.7312085032463074, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.9040178571428571, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.9161706349206349, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.9305555555555556, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.9501488095238095, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9645337301587301, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.9756944444444444, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9799107142857143, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.9826388888888888, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9833829365079365, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9851190476190477, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9858630952380952, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9866071428571429, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9885912698412699, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9888392857142857, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9885912698412699, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9895833333333334, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9910714285714286, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9913194444444444, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9913194444444444, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9913194444444444, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9920634920634921, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9925595238095238, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9930555555555556, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9928075396825397, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9923115079365079, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9918154761904762, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9925595238095238, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9928075396825397, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9928075396825397, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9930555555555556, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9928075396825397, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9925595238095238, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9923115079365079, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9923115079365079, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9928075396825397, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9925595238095238, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9910714285714286, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9915674603174603, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9918154761904762, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9905753968253969, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9895833333333334, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9903273809523809, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9920634920634921, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9890873015873016, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9890873015873016, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9900793650793651, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9908234126984127, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.890609289349842, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.9050481484543628, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.9228068571115261, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.9451162063615606, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.9604274393818951, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.9722325753932, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.9772163892302321, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9800177892388023, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9803718665427458, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9816936459663472, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.982794849310977, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9842298740384715, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9867203265857877, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9865916431136735, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9866026557478099, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9874159130953877, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9890740671731638, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9892984869148778, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9896663651462253, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9894778797108051, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9898897197513727, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9905388171751306, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9912600838000595, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9908949826022799, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9902553776071857, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9903554354214124, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9909209248830732, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9911247203277765, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9913107186444945, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9915278880324332, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9902219929093348, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9908405696005201, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9906265108193537, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9906445440035819, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9903556481901858, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9907982999965221, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9909345538963132, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9904772867291923, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9892038435878059, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9896525538397926, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9914612816062429, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9880506572033645, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9866999534817964, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9875635062256571, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.990974790368209, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9863858366655798, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9882613654786206, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9875951295788992, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9894035349412716, "id_best": 22, "lr_best": 0.00021599999999999996, "wd_best": 0.05, "train/loss_best": 0.01659645965322852, "validation/loss_best": 0.022480396553874016, "validation/acc_best": 0.9930555555555556, "validation/f1_best": 0.9912600838000595} +{"epoch": 13, "train/lr": 0.00011886002410835478, "train/loss": 0.07088137017562986, "train/grad": 0.045945518203079704, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.7470854234695434, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.6278804087638855, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.46849143505096436, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.34552679002285, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.2549828585982323, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.17023826360702515, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.11225963205099106, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.08425099540501833, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.06984442530199886, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.06233609016984701, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.05763964096084237, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.05261248118244111, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.04894452238455415, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.0446457548905164, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.04124332662671804, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.038355867490172384, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.03505513937212527, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.03154929934069514, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.027874074783176182, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.024694714397192, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.02104336562566459, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.017588548650965093, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.013990440210327505, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.010364545676857233, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.006983121875673532, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.003953614672645926, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.0024151508696377277, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.001548992320895195, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0009085495956242084, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0005371508840471506, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.00038892352022230626, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.00029472069814801216, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.00020245933905243873, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.00016147373244166375, "train/loss_034_lr5.1e+00_wd1.0e+00": 8.079545572400094e-05, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.099280409514904e-05, "train/loss_036_lr7.1e+00_wd1.0e+00": 6.933219730854035e-05, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.4876447170972823e-06, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.0907789692282676e-05, "train/loss_039_lr1.2e+01_wd1.0e+00": 4.97286207973957e-06, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.2826146557927131e-05, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.0002231921162456274, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.00011313349008560181, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.003428258001804352, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.0014920447673648597, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.006332800434902311, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.006495740478858352, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.020189231811091304, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.00880727818235755, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.015593646815977991, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.014478150568902493, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.012909198543056846, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.011448612401727587, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.010060663816984743, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.00839831423945725, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.0067751727486029265, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.00588491179747507, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.005538436665083282, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.0054054837801959365, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.005334227425628342, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.005255972172599286, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.005197073132148944, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.005111888876417652, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.005019249266479164, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.004920605507795699, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.004791021282726433, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.004619182632886805, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.004420063893339829, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.004216359374186141, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.003952675676409854, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.0036551256455277324, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0032585315184041974, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0027613804375505426, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0021634594133684002, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0014326045225971028, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.000939177407144598, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.000618153255895777, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.00036116882155283746, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.00021409980060184354, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0001585545695775181, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.00012165437455564642, "train/grad_032_lr3.7e+00_wd1.0e+00": 8.442233592319326e-05, "train/grad_033_lr4.3e+00_wd1.0e+00": 6.64445054422913e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 4.2619997947781486e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 2.463230568917396e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 9.852140283551874e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 4.540890446480197e-06, "train/grad_038_lr9.8e+00_wd1.0e+00": 4.576144678391659e-05, "train/grad_039_lr1.2e+01_wd1.0e+00": 1.966939287006513e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 3.0814763241174004e-05, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.000546020151273097, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.00030420078237374784, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0017942863017466344, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0018255789202229079, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0028810230086845244, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.001895233557329378, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.005434392389088074, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0039341898530483085, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.728164553642273, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.6096262335777283, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.4504093825817108, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.32791832089424133, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.23853951692581177, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.15479889512062073, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.09889484941959381, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.07235149294137955, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.057632818818092346, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.049807868897914886, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.04495648294687271, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.040034327656030655, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.036695413291454315, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.0333692841231823, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.0309440977871418, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.029145294800400734, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.02738361991941929, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.02564939484000206, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.024230603128671646, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.023262543603777885, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.022532574832439423, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.022098446264863014, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.021979808807373047, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.022170094773173332, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.022483468055725098, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.022786777466535568, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.022884104400873184, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.022756963968276978, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.022668207064270973, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.02247847430408001, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.022922255098819733, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.022839322686195374, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.02342446893453598, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.023621127009391785, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.029731348156929016, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.03373967856168747, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.06713929027318954, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.08717785030603409, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.09744217991828918, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.126114159822464, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.17789287865161896, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.15427806973457336, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.23373787105083466, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.35118037462234497, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.4399503171443939, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.6995788812637329, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.9253298044204712, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.5811578631401062, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.8597267866134644, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.9064980158730159, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.9193948412698413, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.9340277777777778, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.9526289682539683, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9680059523809523, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.9769345238095238, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9801587301587301, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.9828869047619048, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9838789682539683, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9848710317460317, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9856150793650794, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9875992063492064, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9885912698412699, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9885912698412699, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9890873015873016, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9890873015873016, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9895833333333334, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9903273809523809, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9910714285714286, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9915674603174603, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9920634920634921, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9923115079365079, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9920634920634921, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9915674603174603, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9918154761904762, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9918154761904762, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9925595238095238, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9925595238095238, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9923115079365079, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9925595238095238, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9930555555555556, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9933035714285714, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9923115079365079, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9923115079365079, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9923115079365079, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9925595238095238, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9918154761904762, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9925595238095238, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9915674603174603, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9915674603174603, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9925595238095238, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9905753968253969, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9903273809523809, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9900793650793651, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9903273809523809, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9895833333333334, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9893353174603174, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9895833333333334, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9885912698412699, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.8937544782679144, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.9085009991959885, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.9274735384851824, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.9479949745143066, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.9635246098359616, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.9728824758956043, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.9772390607611806, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9801919016508123, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9807316491647354, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.981468815759526, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9826181092729526, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9855848119357776, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9864992115663072, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9865550421792337, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9869593412474489, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9869593412474489, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9876862323359035, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9889517342692691, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9897144848180527, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9904814886007285, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9908109374377994, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9906290476204899, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9904015842215506, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9901337404255653, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9905851118769766, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9906395554025338, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9913621136801266, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9911933479983953, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9901694479504393, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.990394581111674, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9915378605820804, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9917518688088727, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9901049259012529, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9906445440035819, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9903556481901858, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9902543392523517, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9899656861182228, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9904772867291923, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9895880121108307, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.989700754621993, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.991908921256681, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.988135210513939, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9874167996835033, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9889015421417758, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9894732779337618, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.986975752192266, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9879468426263249, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9880798630956352, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9873278754441281, "id_best": 31, "lr_best": 0.0009299999999999999, "wd_best": 0.05, "train/loss_best": 0.00029472069814801216, "validation/loss_best": 0.022839322686195374, "validation/acc_best": 0.9933035714285714, "validation/f1_best": 0.9917518688088727} +{"epoch": 14, "train/lr": 8.9081919031238e-05, "train/loss": 0.06792678004130721, "train/grad": 0.04111442985013127, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.7207797145843506, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.6037150526046753, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.4470449697971344, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.3276345360279083, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.24113304704427718, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.16065013125538827, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.1081401027739048, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.08400711562484503, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.07093226810917258, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.06369391685351729, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.059061181005090474, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.05405133841559291, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.05030053618364036, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.04591496952809394, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.04238910157233477, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.03938659780658781, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.035828945226967335, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.031982406610623, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.028034797850996256, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.02464286644011736, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.020783255491405726, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.017119982456788422, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.013216047249734401, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.009329006839543581, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.005879771113395691, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.003234270755201578, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.0019435586780309677, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0012757296580821276, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0007807253114879132, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.00047803780995309353, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.00035247323103249073, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.0002714795246720314, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.00018653129227459432, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.00014891164377331734, "train/loss_034_lr5.1e+00_wd1.0e+00": 7.472199387848378e-05, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.525005653500557e-05, "train/loss_036_lr7.1e+00_wd1.0e+00": 7.389578968286514e-06, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.5070924311876295e-06, "train/loss_038_lr9.8e+00_wd1.0e+00": 5.154618993401527e-06, "train/loss_039_lr1.2e+01_wd1.0e+00": 6.376868113875389e-06, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.0928308367729186e-06, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.251334324479103e-06, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.0002479714155197144, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.0017471557296812534, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.0030890782829374073, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.0024369159806519746, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.0008595738466829062, "train/loss_047_lr4.3e+01_wd1.0e+00": 1.9755028188228606e-06, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.005571489306166768, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.015522874584421515, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.014400564483366907, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.01278311054687947, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.011260744943283498, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.009854091142769902, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008149000788107515, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.006614765831036493, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.0059659430687315764, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.005733328600181267, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.005642524439608678, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.005577850800473243, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.005496063373866491, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.005417705946310889, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.005295303878956475, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.005180857963277958, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.005062380889139604, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.004908014062821166, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.004724688763526501, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.004501967633405002, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.004284441407071427, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.003984360072936397, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.0036439263944339473, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0032009450657642445, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.002638653048343258, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.001959621575224446, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0012216066296241478, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0007783769731395296, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0005241571389342425, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0003245413023432775, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.00020218568020936801, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.00015016812597423268, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0001152236711459409, "train/grad_032_lr3.7e+00_wd1.0e+00": 8.063589884159228e-05, "train/grad_033_lr4.3e+00_wd1.0e+00": 6.501922125153215e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 3.973074982638991e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 2.4467200938360634e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 1.0114575233410618e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 4.080927652981037e-06, "train/grad_038_lr9.8e+00_wd1.0e+00": 9.375415764273044e-06, "train/grad_039_lr1.2e+01_wd1.0e+00": 1.1092559154900861e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 3.627372693543545e-06, "train/grad_041_lr1.6e+01_wd1.0e+00": 5.5641316903005275e-06, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0002671550406663286, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.00086802787656261, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.001684324166086704, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0012835490151747928, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0005105436200902987, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0003622086137274271, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.003001139287244426, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.7005908489227295, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.5836547613143921, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.4265967011451721, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.3073589503765106, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.2218964546918869, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.14252571761608124, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.09190398454666138, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.06881051510572433, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.055720776319503784, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.04837823286652565, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.04381253570318222, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.03913820907473564, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.03598414361476898, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.03268183022737503, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.030334601178765297, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.02864602953195572, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.026915328577160835, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.025255676358938217, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.02388671413064003, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.02305976301431656, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.022496329620480537, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.02230960503220558, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.022325826808810234, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.02252558059990406, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.022604558616876602, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.022465121001005173, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.022463493049144745, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.022372152656316757, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.022240562364459038, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.022313609719276428, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.02277100831270218, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.02268688566982746, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.02312130108475685, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.023296019062399864, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.029489828273653984, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.03323487564921379, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.06549602001905441, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.08532077819108963, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.09457865357398987, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.12137243896722794, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.1702345609664917, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.14959974586963654, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.22433342039585114, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.3052605986595154, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.3734218180179596, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.6350415945053101, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.7993277311325073, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.5165597200393677, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.6935675740242004, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.910218253968254, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.9191468253968254, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.9375, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.9556051587301587, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9702380952380952, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.9791666666666666, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9801587301587301, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.9826388888888888, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9838789682539683, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9853670634920635, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.986359126984127, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9880952380952381, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9890873015873016, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9888392857142857, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9890873015873016, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9890873015873016, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9900793650793651, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9910714285714286, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9918154761904762, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9920634920634921, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9923115079365079, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9925595238095238, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9928075396825397, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9928075396825397, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9928075396825397, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9928075396825397, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9928075396825397, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9928075396825397, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9930555555555556, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9930555555555556, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9928075396825397, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9930555555555556, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9928075396825397, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9925595238095238, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9923115079365079, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9928075396825397, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9918154761904762, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9925595238095238, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9915674603174603, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9915674603174603, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9928075396825397, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9905753968253969, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9903273809523809, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9923115079365079, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9913194444444444, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9885912698412699, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9900793650793651, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9900793650793651, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9900793650793651, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.8982999019077477, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.9086828479413366, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.9314873584498862, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.9510632532161994, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.9663464975556902, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.976162291720521, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.9773251563743709, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9800110873585952, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9807765478934524, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9820696482728637, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9838808939681492, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9863125265797699, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9872688232557201, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9867348194440668, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9869147863023089, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9872821292770908, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9880936690642262, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9893934677024542, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9903875199396316, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.990613120384955, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9907151058230868, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9908039372089105, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.991628218280311, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.991944924431127, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9918083259241846, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9915169972271874, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9914705569727424, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9913108107692836, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.991484411260567, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9914825732093477, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9913130452064864, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9912076866637055, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9908760833098602, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9910140975662864, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9903549955397905, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9904340001957552, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9899656861182228, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9904772867291923, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9895880121108307, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.989700754621993, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9922769178094983, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.988135210513939, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9874167996835033, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9904691835173396, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.989389075909213, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9862225282814489, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9892038220747915, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9878700502956944, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9883100375130149, "id_best": 28, "lr_best": 0.00057, "wd_best": 0.05, "train/loss_best": 0.0007807253114879132, "validation/loss_best": 0.022240562364459038, "validation/acc_best": 0.9930555555555556, "validation/f1_best": 0.991484411260567} +{"epoch": 15, "train/lr": 6.196799573888289e-05, "train/loss": 0.06271582884714007, "train/grad": 0.036726453406736255, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.6910790205001831, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.5746601700782776, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.41953744053840636, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.30292916893959043, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.22021033853292465, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.14386004373431205, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.09643848873674869, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.07557143207639455, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.06392489982768894, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.057377920234575865, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.05306376609951258, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.048425828963518144, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.04497401081956923, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.04090151603333652, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.03761897066608071, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.03484104841016233, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.03158756012097001, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.028116719350218772, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.024563635392114522, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.021394165018573403, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.01777193325571716, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.014217244703322649, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.010589790642261504, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.0071791634242981675, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.004442010987550021, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.0024627483077347277, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.0015305938292294742, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0010357013065367938, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0006570489052683115, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0004214585106819868, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0003117114957422018, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.00024297615513205529, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.0001676823478192091, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.0001350011769682169, "train/loss_034_lr5.1e+00_wd1.0e+00": 7.339567877352237e-05, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.099133260548115e-05, "train/loss_036_lr7.1e+00_wd1.0e+00": 4.810737445950508e-06, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.4811440855264663e-06, "train/loss_038_lr9.8e+00_wd1.0e+00": 7.322076708078385e-06, "train/loss_039_lr1.2e+01_wd1.0e+00": 4.44936566054821e-06, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.4054495841264724e-06, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.2056140005588534e-06, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.7251353710889815e-06, "train/loss_043_lr2.2e+01_wd1.0e+00": 8.292496204376221e-08, "train/loss_044_lr2.6e+01_wd1.0e+00": 1.5887431800365448e-07, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.0007031384762376546, "train/loss_046_lr3.6e+01_wd1.0e+00": 1.0795146226882934e-06, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.7529895305633544e-08, "train/loss_048_lr5.0e+01_wd1.0e+00": 1.9690021872520446e-07, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.015196284535340965, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.014092320967465639, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.01246319112367928, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.01089474888285622, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.009451705091632902, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.007760921933222562, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.006413530507124961, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.005879425681196153, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.005663463722448796, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.005557022539433092, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.005490250554285012, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.005398261979862582, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.005320225509203738, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.00520010187959997, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.0050845969415968285, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.004965326558012748, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.004808045778336236, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.004613752146397019, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.00438849288111669, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.004146050918934634, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.0038190410313836765, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.003445934265764663, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0029696772480383516, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0023811520708113677, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0017229359898192343, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0010637152188792242, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0006786921905950294, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0004612181925585901, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.00028849465828898244, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0001839753451758952, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.00013759164277416859, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.00010613626139047483, "train/grad_032_lr3.7e+00_wd1.0e+00": 7.483445855996251e-05, "train/grad_033_lr4.3e+00_wd1.0e+00": 5.94253090116581e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 3.779474011253114e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 2.366740619631713e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 6.679323850771867e-06, "train/grad_037_lr8.3e+00_wd1.0e+00": 4.91371936426097e-06, "train/grad_038_lr9.8e+00_wd1.0e+00": 8.996847354742059e-06, "train/grad_039_lr1.2e+01_wd1.0e+00": 8.818296325916422e-06, "train/grad_040_lr1.4e+01_wd1.0e+00": 3.2946892712156153e-06, "train/grad_041_lr1.6e+01_wd1.0e+00": 4.7028985718362726e-06, "train/grad_042_lr1.9e+01_wd1.0e+00": 3.867338145991384e-06, "train/grad_043_lr2.2e+01_wd1.0e+00": 4.3286775333094253e-07, "train/grad_044_lr2.6e+01_wd1.0e+00": 1.8926669524212575e-06, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0001970306691712036, "train/grad_046_lr3.6e+01_wd1.0e+00": 3.4532487672848913e-06, "train/grad_047_lr4.3e+01_wd1.0e+00": 4.265913919686119e-06, "train/grad_048_lr5.0e+01_wd1.0e+00": 1.3968755790838225e-06, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.6819450855255127, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.5660368204116821, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.4106718599796295, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.29361480474472046, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.21091555058956146, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.1343216747045517, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.0874517560005188, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.06650770455598831, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.05431971698999405, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.047415461391210556, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.04303637519478798, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.038557253777980804, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.03553539142012596, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.0323045514523983, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.030107084661722183, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.02833419479429722, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.02659522369503975, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.02493024617433548, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.023561956360936165, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.02271405979990959, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.022052401676774025, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.02183997817337513, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.021975688636302948, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.02238561399281025, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.02282194048166275, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.022945867851376534, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.02282489836215973, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.02271358296275139, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.022476281970739365, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.022553062066435814, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.023233862593770027, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.022987017408013344, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.02337561547756195, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.023638641461730003, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.029509054496884346, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.03298918530344963, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.06415238231420517, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.08381056040525436, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.09253107011318207, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.11853533983230591, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.1649169921875, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.145391047000885, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.2163538634777069, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.29205000400543213, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.3511541485786438, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.5833367705345154, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.7549931406974792, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.48002949357032776, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.6435837149620056, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.9109623015873016, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.921875, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.939484126984127, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.9585813492063492, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9709821428571429, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.9786706349206349, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9813988095238095, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.9828869047619048, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9848710317460317, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9853670634920635, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9861111111111112, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9878472222222222, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9888392857142857, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.988343253968254, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9890873015873016, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9890873015873016, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9905753968253969, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9913194444444444, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9913194444444444, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9920634920634921, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9925595238095238, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9923115079365079, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9928075396825397, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9930555555555556, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9933035714285714, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9933035714285714, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9933035714285714, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9933035714285714, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9930555555555556, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9930555555555556, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9930555555555556, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9930555555555556, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9930555555555556, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9923115079365079, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9923115079365079, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9925595238095238, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9918154761904762, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9925595238095238, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9918154761904762, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9915674603174603, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9933035714285714, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9905753968253969, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9905753968253969, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9925595238095238, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9915674603174603, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9893353174603174, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9900793650793651, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9900793650793651, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9903273809523809, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.8990806768676566, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.9116734948860273, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.9331636881310214, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.9540340224319944, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.9672524734389072, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.9750730872483789, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.9789167617951281, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9801919016508123, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.981465758553079, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9824370032278499, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9835094069620511, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9857692473622629, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9868985903436105, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9863752296354733, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9869147863023089, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9869622455564033, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9890340735460674, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9896200113284938, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9896200113284938, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9903494522915937, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9914446122380564, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9912219313864172, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9915810272714788, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9919890978218856, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9922141656441907, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9921420569402192, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9920509310874402, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9920265261224406, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9914822554237072, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9914825732093477, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9914825732093477, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9913851452354921, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.991420211217666, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9906445440035819, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9903549955397905, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9902533544624258, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9899656861182228, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.990525194421825, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9897680874932165, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.989700754621993, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9926364146826077, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.988135210513939, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9875962194106334, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9906485447829441, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9899365447772129, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9868065612479594, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9893774041003512, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9878708233134645, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9884900330006445, "id_best": 24, "lr_best": 0.0003, "wd_best": 0.05, "train/loss_best": 0.004442010987550021, "validation/loss_best": 0.02282194048166275, "validation/acc_best": 0.9933035714285714, "validation/f1_best": 0.9922141656441907} +{"epoch": 16, "train/lr": 3.870405029380728e-05, "train/loss": 0.0623933682590723, "train/grad": 0.036347998082637785, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.6808427286148071, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.5655967283248902, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.4119392251968384, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.2971208930015564, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.21622903972864152, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.14171892687678336, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.09709852665662766, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.07782297253608704, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.06674230506643652, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.06029606913216412, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.05597680640406907, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.05109167636372149, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.04739478068426251, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.043041193718090655, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.0395225705113262, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.03648640610277653, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.032885566037148234, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.029091984191909434, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.025136773148551582, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.02168588993139565, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.017711756834760308, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.01393563613295555, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.01015141725540161, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.006749911811202765, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.004177504852414131, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.0023415983375161885, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.0014550961554050446, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0009932608529925346, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0006345540471374988, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.00040843390859663487, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.00030778453685343266, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.0002416330110281706, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.00017102790996432305, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.00013770491816103458, "train/loss_034_lr5.1e+00_wd1.0e+00": 7.68861547112465e-05, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.492560237646103e-05, "train/loss_036_lr7.1e+00_wd1.0e+00": 5.143415182828903e-06, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.0518881976604462e-06, "train/loss_038_lr9.8e+00_wd1.0e+00": 5.7050026953220366e-06, "train/loss_039_lr1.2e+01_wd1.0e+00": 4.433291032910347e-06, "train/loss_040_lr1.4e+01_wd1.0e+00": 8.223950862884521e-07, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.599043607711792e-06, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.8814299255609513e-06, "train/loss_043_lr2.2e+01_wd1.0e+00": 5.817878991365433e-07, "train/loss_044_lr2.6e+01_wd1.0e+00": 1.5515834093093872e-08, "train/loss_045_lr3.1e+01_wd1.0e+00": 1.8081627786159516e-07, "train/loss_046_lr3.6e+01_wd1.0e+00": 7.348600775003433e-07, "train/loss_047_lr4.3e+01_wd1.0e+00": 7.18953087925911e-07, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.629123628139496e-08, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.015197862316854297, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.014098970675840974, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.01246360555756837, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.010890818634070456, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.00948015324305743, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.007795145019190386, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.006439030895708128, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.005910680080996826, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.005680053235264495, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.0055591381253907455, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.005471708300174214, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.005358164909412153, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.005253333720029332, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.005107675656472565, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.004967379468725994, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.004834473169466946, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.004655214957310818, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.004436253455132828, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.004175547568229377, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.003913935422388022, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.0035719363918178715, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.003192142011685064, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0027279349638411076, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0021557233474595707, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0015220692088041686, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0009159460715454771, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0005882320394812268, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.00040329533787371476, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0002569421888347279, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.00016509803503140575, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.00012573896622143367, "train/grad_031_lr3.1e+00_wd1.0e+00": 9.835961261160264e-05, "train/grad_032_lr3.7e+00_wd1.0e+00": 6.90707285548342e-05, "train/grad_033_lr4.3e+00_wd1.0e+00": 5.690595485589256e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 3.6601143354459966e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 2.255828025646167e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 7.06220280940177e-06, "train/grad_037_lr8.3e+00_wd1.0e+00": 4.900793045135923e-06, "train/grad_038_lr9.8e+00_wd1.0e+00": 9.86233511555622e-06, "train/grad_039_lr1.2e+01_wd1.0e+00": 9.49104508431079e-06, "train/grad_040_lr1.4e+01_wd1.0e+00": 2.536346612040782e-06, "train/grad_041_lr1.6e+01_wd1.0e+00": 4.858204362671615e-06, "train/grad_042_lr1.9e+01_wd1.0e+00": 3.411267316555165e-06, "train/grad_043_lr2.2e+01_wd1.0e+00": 1.7354264491970631e-06, "train/grad_044_lr2.6e+01_wd1.0e+00": 7.505822867374918e-07, "train/grad_045_lr3.1e+01_wd1.0e+00": 4.832052305401597e-07, "train/grad_046_lr3.6e+01_wd1.0e+00": 3.7051998513290216e-06, "train/grad_047_lr4.3e+01_wd1.0e+00": 2.1733810287936623e-06, "train/grad_048_lr5.0e+01_wd1.0e+00": 1.9605757714089564e-07, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.6704124212265015, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.555029034614563, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.40078994631767273, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.2853594720363617, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.20423975586891174, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.1293845921754837, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.08488524705171585, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.06517928838729858, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.05347617343068123, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.046762626618146896, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.042575687170028687, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.03815070912241936, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.03519335016608238, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.031995657831430435, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.02983265183866024, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.028145546093583107, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.02634597383439541, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.024778146296739578, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.02351285144686699, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.022726600989699364, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.022126244381070137, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.022085342556238174, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.022298026829957962, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.02259809523820877, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.02290201559662819, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.02306702733039856, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.023012690246105194, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.02288566343486309, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.02268170565366745, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.02271287515759468, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.023114563897252083, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.02298179268836975, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.023323150351643562, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.023578256368637085, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.029531193897128105, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.03281749412417412, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.06352346390485764, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.08344458043575287, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.09157242625951767, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.11641544103622437, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.1621951162815094, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.14319558441638947, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.2106896936893463, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.28543782234191895, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.33933573961257935, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.5580658912658691, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.7263465523719788, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.4596782326698303, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.6116493940353394, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.9112103174603174, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.9233630952380952, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.9419642857142857, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.9610615079365079, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9717261904761905, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.9789186507936508, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9816468253968254, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.9828869047619048, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9848710317460317, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9856150793650794, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9866071428571429, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9878472222222222, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9888392857142857, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9888392857142857, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9888392857142857, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9900793650793651, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9905753968253969, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9913194444444444, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9913194444444444, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9918154761904762, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9918154761904762, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9918154761904762, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9913194444444444, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9913194444444444, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9913194444444444, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9925595238095238, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9923115079365079, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9928075396825397, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9930555555555556, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9930555555555556, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9928075396825397, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9930555555555556, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9925595238095238, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9928075396825397, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9918154761904762, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9925595238095238, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9918154761904762, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9915674603174603, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9933035714285714, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9905753968253969, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9905753968253969, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9925595238095238, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9913194444444444, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9893353174603174, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9900793650793651, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9900793650793651, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9903273809523809, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.8993581022800576, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.9134143976272314, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.9356169154045569, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.9567465361011849, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.9679801453901812, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.9755234925967374, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.9791873136469378, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9801919016508123, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.981465758553079, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9826159385286869, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9842298740384715, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9857682558810364, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9869016571600859, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9867348194440668, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9867348194440668, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9882692231568312, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9889867256857519, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9896200113284938, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9896200113284938, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9903870151111694, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9902478263140043, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9906468172439443, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9897391049420632, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9900033542002591, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9899558828371142, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.990944555693664, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.990817062694614, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9912846099338053, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9914822554237072, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9914825732093477, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9913130452064864, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9913851452354921, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9903315812527046, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9904655554825078, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9901756139836867, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9904340001957552, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9899656861182228, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.990525194421825, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9897680874932165, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.989678772869995, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9926364146826077, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.988135210513939, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9875962194106334, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9906485447829441, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.989389075909213, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9868065612479594, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9893774041003512, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9880365086732402, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9888069683060967, "id_best": 40, "lr_best": 0.0042, "wd_best": 0.05, "train/loss_best": 8.223950862884521e-07, "validation/loss_best": 0.1621951162815094, "validation/acc_best": 0.9933035714285714, "validation/f1_best": 0.9926364146826077} +{"epoch": 17, "train/lr": 2.030750443206766e-05, "train/loss": 0.06209003731608391, "train/grad": 0.035188003545627, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.6743747329711914, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.5597846722602844, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.40709154844284057, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.2934022343158722, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.2134752756357193, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.13999015010893345, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.09668910503387451, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.07786476224660874, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.06692732041701674, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.06046387562528253, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.0561746103875339, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.051489870864897966, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.04795131983235478, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.043790960926562546, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.04040448827669024, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.03747214660979807, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.03409101255238056, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.030282748397439718, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.02633079937659204, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.02280935851857066, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.018703256295993925, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.014677510187029839, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.01054093811661005, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.00682197586633265, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.004104569796472788, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.0022845686320215465, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.0014320396166294814, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0009780313353985547, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0006318565458059311, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.00040517693385481833, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0003052132669836283, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.00023858092725276948, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.00016444917768239974, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.00013327942229807377, "train/loss_034_lr5.1e+00_wd1.0e+00": 7.017899304628372e-05, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.15592996776104e-05, "train/loss_036_lr7.1e+00_wd1.0e+00": 4.7336332499980925e-06, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.196382895112038e-06, "train/loss_038_lr9.8e+00_wd1.0e+00": 5.754763260483742e-06, "train/loss_039_lr1.2e+01_wd1.0e+00": 4.93733212351799e-06, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.263432204723358e-06, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.6475282609462738e-06, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.663366660475731e-06, "train/loss_043_lr2.2e+01_wd1.0e+00": 8.958484977483749e-07, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.6690773665904996e-07, "train/loss_045_lr3.1e+01_wd1.0e+00": 5.459319800138474e-07, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.5021843612194063e-07, "train/loss_047_lr4.3e+01_wd1.0e+00": 5.258619785308838e-07, "train/loss_048_lr5.0e+01_wd1.0e+00": 5.245208740234375e-08, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.014637514492496848, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.013571179951541126, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.012013135289307683, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.010519752609543503, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.009137076414190233, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.007463962940964848, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.006203905702568591, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.005719010271131992, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.005504436856135726, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.005390442577190697, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.0053100104565965015, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.005210545183508657, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.005117423858027905, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.004986932574538514, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.00485753952700179, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.004736538108554669, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.004576739784097299, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.0043732658590306525, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.004134905055980198, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.003887914663791889, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.003557833138474962, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.0031820175297616517, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0026978912825143197, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.00209073617013928, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0014395948189121555, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0008633795955756795, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0005572355173353572, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.00038239820451053675, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0002463404598347552, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.00015877915453529567, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.00012049179079440364, "train/grad_031_lr3.1e+00_wd1.0e+00": 9.407178529500016e-05, "train/grad_032_lr3.7e+00_wd1.0e+00": 6.622453876730106e-05, "train/grad_033_lr4.3e+00_wd1.0e+00": 5.488082867259436e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 3.6001547084083544e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 2.1957347330516795e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 5.686993138602748e-06, "train/grad_037_lr8.3e+00_wd1.0e+00": 4.636367867478233e-06, "train/grad_038_lr9.8e+00_wd1.0e+00": 9.406544440240603e-06, "train/grad_039_lr1.2e+01_wd1.0e+00": 8.386626722756898e-06, "train/grad_040_lr1.4e+01_wd1.0e+00": 2.599652751682411e-06, "train/grad_041_lr1.6e+01_wd1.0e+00": 4.918934850900932e-06, "train/grad_042_lr1.9e+01_wd1.0e+00": 4.60405068363816e-06, "train/grad_043_lr2.2e+01_wd1.0e+00": 2.148358064834212e-06, "train/grad_044_lr2.6e+01_wd1.0e+00": 8.42375137071588e-07, "train/grad_045_lr3.1e+01_wd1.0e+00": 1.4658536483085961e-06, "train/grad_046_lr3.6e+01_wd1.0e+00": 1.090256308085216e-06, "train/grad_047_lr4.3e+01_wd1.0e+00": 2.27314656084702e-06, "train/grad_048_lr5.0e+01_wd1.0e+00": 2.8251072028675006e-07, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.6644235253334045, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.5492657423019409, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.3955569863319397, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.2810308039188385, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.20071452856063843, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.1268841177225113, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.08361242711544037, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.0644613727927208, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.053123556077480316, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.0465959757566452, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.04233355075120926, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.03795614838600159, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.03491499274969101, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.03179964795708656, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.029606979340314865, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.027871903032064438, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.026152919977903366, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.024519838392734528, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.023240549489855766, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.022487660869956017, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.02189861610531807, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.02177431806921959, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.021916324272751808, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.0222134031355381, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.022573089227080345, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.022743001580238342, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.02277279831469059, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.022671066224575043, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.02256140671670437, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.022641969844698906, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.023135343566536903, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.022965000942349434, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.023357439786195755, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.023469170555472374, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.029505426064133644, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.032709233462810516, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.06318679451942444, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.08284971117973328, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.09093724936246872, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.1156921237707138, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.16037219762802124, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.1420636624097824, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.20845246315002441, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.28109028935432434, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.3322905898094177, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.5476912260055542, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.7151694893836975, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.4490918219089508, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.596208393573761, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.9126984126984127, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.9226190476190477, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.9427083333333334, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.9613095238095238, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9719742063492064, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.9794146825396826, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9821428571428571, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.9826388888888888, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9846230158730159, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9858630952380952, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9868551587301587, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9880952380952381, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9893353174603174, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9888392857142857, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9890873015873016, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9900793650793651, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9905753968253969, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9910714285714286, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9915674603174603, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9915674603174603, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9920634920634921, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9928075396825397, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9918154761904762, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9918154761904762, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9923115079365079, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9928075396825397, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9925595238095238, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9928075396825397, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9930555555555556, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9930555555555556, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9928075396825397, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9930555555555556, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9928075396825397, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9923115079365079, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9925595238095238, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9918154761904762, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9925595238095238, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9918154761904762, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9915674603174603, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9933035714285714, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9905753968253969, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9905753968253969, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9925595238095238, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9913194444444444, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9895833333333334, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9898313492063492, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9903273809523809, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9903273809523809, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.9010150443011863, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.9124196978897755, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.9365798320317912, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.95699945542655, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.9685211474382385, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.9762432739686189, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.9795445712349107, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9800110873585952, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9812848213398647, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.982794849310977, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9844987060284812, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9859475844050068, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9874522652525707, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9867345548078283, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9869145652795508, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9880933967295236, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9889868126893996, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9893934677024542, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9901614146658462, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9902073506587634, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9904890414913197, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.99144119873733, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9900846911562217, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9904985819774416, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9909720763509737, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9911894181866762, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9911828150286397, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9912846099338053, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9914822554237072, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9914825732093477, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9913130452064864, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9913851452354921, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9908975366031679, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9904655554825078, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9903549955397905, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9902543392523517, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9899656861182228, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.990525194421825, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9897680874932165, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.989678772869995, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9926364146826077, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.988135210513939, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9875962194106334, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9906485447829441, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9897581975421997, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9873420092808323, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9890227727210702, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9882162181253766, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9884900330006445, "id_best": 40, "lr_best": 0.0042, "wd_best": 0.05, "train/loss_best": 1.263432204723358e-06, "validation/loss_best": 0.16037219762802124, "validation/acc_best": 0.9933035714285714, "validation/f1_best": 0.9926364146826077} +{"epoch": 18, "train/lr": 7.5829098008590064e-06, "train/loss": 0.05928028638474643, "train/grad": 0.03516384661197662, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.6601814699172973, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.5467715048789978, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.3957023453712463, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.28337258607149124, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.20448267936706543, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.13191206105053424, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.08984043512493373, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.07165108008310199, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.06118790598586202, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.054999675713479516, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.05097276838496327, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.046574260499328377, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.043227242017164824, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.03933411073870957, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.03620983881875873, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.033470657588914036, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.030309530328959226, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.02683128394186497, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.023223196053877473, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.02003915762528777, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.01641959202475846, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.012919775824993849, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.009346784939989448, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.006085987603291869, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.0036544695403426886, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.002035969430580735, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.0012873740028589964, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0008822987508028745, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0005691562313586473, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0003647981025278568, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0002741249278187752, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.0002144824340939522, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.0001488331612199545, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.00011931801214814187, "train/loss_034_lr5.1e+00_wd1.0e+00": 6.611885502934456e-05, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.9135681688785554e-05, "train/loss_036_lr7.1e+00_wd1.0e+00": 4.296433180570603e-06, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.0498206615447996e-06, "train/loss_038_lr9.8e+00_wd1.0e+00": 7.004458457231521e-06, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.438807860016823e-06, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.6001705080270768e-06, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.3820996284484865e-06, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.363005816936493e-08, "train/loss_043_lr2.2e+01_wd1.0e+00": 9.195879101753234e-08, "train/loss_044_lr2.6e+01_wd1.0e+00": 9.95676964521408e-08, "train/loss_045_lr3.1e+01_wd1.0e+00": 4.4330954551696775e-09, "train/loss_046_lr3.6e+01_wd1.0e+00": 6.892159581184387e-07, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.862380981445313e-07, "train/loss_048_lr5.0e+01_wd1.0e+00": 9.611248970031739e-09, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.014823077619075775, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.013743854877538979, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.012165246130898595, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.010650547053664923, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.00926172305829823, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.007526809659320861, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.006172958496026695, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.005670491764321923, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.0054591930127935485, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.005347742103622295, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.00526762853260152, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.005156001280993223, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.005050948044518009, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.0048954686999786645, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.004745184566418175, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.0045973740160116, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.004415052776021184, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.0042012942659494, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.00395331791442004, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.0037124437565216797, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.0033968653141346295, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.003030189344935934, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0025480789635912516, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0019524042947159615, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.00133450933280983, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0008046855032625899, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0005223588784065214, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0003613813817810296, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.000233102244010297, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.00015181605251200382, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.00011565728992991353, "train/grad_031_lr3.1e+00_wd1.0e+00": 9.12574032554403e-05, "train/grad_032_lr3.7e+00_wd1.0e+00": 6.521941124901787e-05, "train/grad_033_lr4.3e+00_wd1.0e+00": 5.3528281262060774e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 3.5117686921353196e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 2.1150690379698744e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 6.202903220788921e-06, "train/grad_037_lr8.3e+00_wd1.0e+00": 5.117753190423071e-06, "train/grad_038_lr9.8e+00_wd1.0e+00": 9.772211946949536e-06, "train/grad_039_lr1.2e+01_wd1.0e+00": 7.1794044603764315e-06, "train/grad_040_lr1.4e+01_wd1.0e+00": 3.193540878758621e-06, "train/grad_041_lr1.6e+01_wd1.0e+00": 4.5283044725731495e-06, "train/grad_042_lr1.9e+01_wd1.0e+00": 3.908763079930937e-06, "train/grad_043_lr2.2e+01_wd1.0e+00": 2.532117382592177e-06, "train/grad_044_lr2.6e+01_wd1.0e+00": 8.539738206547256e-07, "train/grad_045_lr3.1e+01_wd1.0e+00": 9.487622089161145e-07, "train/grad_046_lr3.6e+01_wd1.0e+00": 2.076880536338433e-06, "train/grad_047_lr4.3e+01_wd1.0e+00": 1.2506712606474102e-06, "train/grad_048_lr5.0e+01_wd1.0e+00": 1.471865000711789e-07, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.6620407104492188, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.5471304059028625, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.393582820892334, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.2794623374938965, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.19952929019927979, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.12596605718135834, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.0831306129693985, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.06414735317230225, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.05296371132135391, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.04649634286761284, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.04220559075474739, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.03784759342670441, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.03485832363367081, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.031735993921756744, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.029497649520635605, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.02778344415128231, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.026073312386870384, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.02448076382279396, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.023252468556165695, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.022444115951657295, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.021960424259305, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.021801136434078217, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.02196888066828251, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.022358212620019913, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.022691398859024048, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.022745078429579735, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.022751320153474808, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.02278575301170349, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.02264217846095562, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.022652938961982727, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.02312774956226349, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.0229690819978714, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.023316560313105583, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.02353208139538765, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.029509667307138443, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.03275777027010918, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.06310991942882538, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.08268658816814423, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.09083662927150726, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.11549645662307739, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.16039448976516724, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.1418437957763672, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.2069081813097, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.27900105714797974, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.3303474187850952, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.5445188283920288, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.7107441425323486, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.444230854511261, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.593748927116394, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.9141865079365079, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.9233630952380952, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.9427083333333334, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.9613095238095238, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9724702380952381, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.9794146825396826, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9821428571428571, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.9828869047619048, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9846230158730159, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9856150793650794, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9866071428571429, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.988343253968254, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9893353174603174, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9885912698412699, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9890873015873016, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9898313492063492, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9903273809523809, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9910714285714286, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9913194444444444, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9915674603174603, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9923115079365079, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9923115079365079, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9918154761904762, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9915674603174603, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9915674603174603, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9923115079365079, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9928075396825397, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9928075396825397, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9930555555555556, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9928075396825397, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9928075396825397, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9930555555555556, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9928075396825397, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9923115079365079, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9925595238095238, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9918154761904762, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9925595238095238, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9918154761904762, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9915674603174603, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9933035714285714, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9905753968253969, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9905753968253969, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9923115079365079, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9910714285714286, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9895833333333334, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9898313492063492, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9903273809523809, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9905753968253969, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.9021332716708572, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.9133546939392387, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.9362476085579498, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.956714777847432, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.9688964230869853, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.9762432739686189, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.9795669921612297, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9801919016508123, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9812848213398647, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9822539159641882, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9842281454415847, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9864918551037404, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9874522652525707, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9865548339876162, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9869145652795508, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9879136784754294, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9888070829854192, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9893934677024542, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9899348710398066, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9902073506587634, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9907138656764461, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9908493669091133, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.990408358868553, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9900816031957236, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9900097121649788, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9905488966024847, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9912846099338053, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9912846099338053, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9914822554237072, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9912120170272173, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9913130452064864, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9913851452354921, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9908975366031679, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9904655554825078, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9903549955397905, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9902543392523517, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9899656861182228, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.990525194421825, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9895667789011097, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.989678772869995, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9926364146826077, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.988135210513939, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9875962194106334, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9904445579933442, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9892107286741998, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9873420092808323, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9890227727210702, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9882162181253766, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9890310205170891, "id_best": 40, "lr_best": 0.0042, "wd_best": 0.05, "train/loss_best": 1.6001705080270768e-06, "validation/loss_best": 0.16039448976516724, "validation/acc_best": 0.9933035714285714, "validation/f1_best": 0.9926364146826077} +{"epoch": 19, "train/lr": 1.0867618231465446e-06, "train/loss": 0.059864071095362306, "train/grad": 0.03501352301798761, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.6630507493019104, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.5493206787109375, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.39786282658576966, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.28531227469444276, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.20637555837631225, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.13393874831497668, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.09195965442806482, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.07386479131877423, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.06333515094593167, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.05703982514329255, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.052851027557626364, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.04819444281980395, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.04462927090935409, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.040349146202206615, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.036857786579057576, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.03387467761524022, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.03044742119498551, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.02683439077809453, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.023094647359102966, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.019897320400923492, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.016233860785141586, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.01278235119767487, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.00925765722990036, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.006089230421930551, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.0037074351869523527, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.002081724004819989, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.0013145225122570992, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0009022641740739346, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0005836636759340763, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0003779295552521944, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0002857411187142134, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.00022274632938206195, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.0001596353016793728, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.00012446626089513302, "train/loss_034_lr5.1e+00_wd1.0e+00": 7.244301959872246e-05, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.905324101448059e-05, "train/loss_036_lr7.1e+00_wd1.0e+00": 4.513282328844071e-06, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.136759623885155e-06, "train/loss_038_lr9.8e+00_wd1.0e+00": 5.12741506099701e-06, "train/loss_039_lr1.2e+01_wd1.0e+00": 4.06644307076931e-06, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.968787983059883e-06, "train/loss_041_lr1.6e+01_wd1.0e+00": 7.566902786493301e-07, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.8010195344686508e-06, "train/loss_043_lr2.2e+01_wd1.0e+00": 7.629767060279846e-07, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.986658364534378e-07, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.2663345336914065e-07, "train/loss_046_lr3.6e+01_wd1.0e+00": 1.944880932569504e-07, "train/loss_047_lr4.3e+01_wd1.0e+00": 1.4734454452991485e-06, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.548339009284973e-09, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.014538288586772979, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.013456230079755186, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.011877129808999598, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.010370491512585431, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.009008081057108938, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.007388529507443309, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.006190063880058006, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.005778021311853081, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.005612571837264113, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.005530905404011719, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.005464969368767924, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.005363536910736002, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.0052590319287264715, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.0051023339942912575, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.004944895553344395, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.0047935069448431025, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.004601893561921315, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.004365563185274368, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.004092635279230308, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.0038198913176893255, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.003451176795133506, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.0030465281362558015, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0025359800861406256, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.001941592666116776, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.001325578305804811, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.000799440398986917, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0005192852977415896, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.00036124428577295476, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0002344309854970561, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.00015202058549220964, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.00011501712227982353, "train/grad_031_lr3.1e+00_wd1.0e+00": 9.05009234645604e-05, "train/grad_032_lr3.7e+00_wd1.0e+00": 6.46559472431818e-05, "train/grad_033_lr4.3e+00_wd1.0e+00": 5.3654400345521936e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 3.436642585768368e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 2.246337670882781e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 5.780419220887496e-06, "train/grad_037_lr8.3e+00_wd1.0e+00": 4.8374104569017075e-06, "train/grad_038_lr9.8e+00_wd1.0e+00": 8.193411738391992e-06, "train/grad_039_lr1.2e+01_wd1.0e+00": 8.148603164664318e-06, "train/grad_040_lr1.4e+01_wd1.0e+00": 3.2050558895391284e-06, "train/grad_041_lr1.6e+01_wd1.0e+00": 4.873570745100279e-06, "train/grad_042_lr1.9e+01_wd1.0e+00": 4.505479635344733e-06, "train/grad_043_lr2.2e+01_wd1.0e+00": 2.009220214408464e-06, "train/grad_044_lr2.6e+01_wd1.0e+00": 1.7089436125138825e-06, "train/grad_045_lr3.1e+01_wd1.0e+00": 1.104062322413365e-06, "train/grad_046_lr3.6e+01_wd1.0e+00": 1.3976866757807901e-06, "train/grad_047_lr4.3e+01_wd1.0e+00": 5.230899317035339e-06, "train/grad_048_lr5.0e+01_wd1.0e+00": 1.1127654397130392e-07, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.6617134809494019, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.5468399524688721, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.39339080452919006, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.27920007705688477, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.19935086369514465, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.12582899630069733, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.08306989073753357, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.0641159936785698, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.05293578654527664, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.046466074883937836, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.04218580946326256, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.037862468510866165, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.034877270460128784, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.03170578181743622, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.02948833629488945, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.027764417231082916, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.02608957141637802, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.024494381621479988, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.02321447804570198, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.022445574402809143, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.021938616409897804, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.021764889359474182, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.021935567259788513, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.022387396544218063, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.022674309089779854, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.02275463566184044, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.022769207134842873, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.022764071822166443, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.022579394280910492, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.022638168185949326, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.023153848946094513, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.02298467420041561, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.02328517474234104, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.02349887602031231, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.029466329142451286, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.03269372135400772, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.0630771741271019, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.0826830193400383, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.0908752977848053, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.11534979194402695, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.16015657782554626, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.14187589287757874, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.20704439282417297, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.27892225980758667, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.3292165696620941, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.5426494479179382, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.7089329957962036, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.44136860966682434, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.5926874876022339, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.9139384920634921, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.9233630952380952, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.9429563492063492, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.9613095238095238, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9724702380952381, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.9794146825396826, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9821428571428571, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.9826388888888888, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9848710317460317, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9856150793650794, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.986359126984127, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.988343253968254, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9893353174603174, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9885912698412699, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9890873015873016, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9898313492063492, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9903273809523809, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9910714285714286, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9913194444444444, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9915674603174603, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9920634920634921, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9923115079365079, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9918154761904762, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9915674603174603, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9915674603174603, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9925595238095238, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9925595238095238, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9928075396825397, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9930555555555556, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9928075396825397, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9928075396825397, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9930555555555556, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9928075396825397, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9923115079365079, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9925595238095238, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9918154761904762, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9925595238095238, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9918154761904762, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9915674603174603, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9933035714285714, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9905753968253969, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9905753968253969, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9923115079365079, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9913194444444444, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9895833333333334, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9900793650793651, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9903273809523809, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9905753968253969, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.9019727063876469, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.9133546939392387, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.9365274657949979, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.9567532648394687, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.9688964230869853, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.9762432739686189, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.9795669921612297, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9800110873585952, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.981512708753133, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9822539159641882, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9836867249359793, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9864918551037404, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9874522652525707, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9865548339876162, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9869145652795508, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9879136784754294, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9888070829854192, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9893934677024542, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9899348710398066, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9902073506587634, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9904873106674863, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9908493669091133, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.990408358868553, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9900816031957236, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9900097121649788, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9908194571893812, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9910572685794008, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9912846099338053, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9914822554237072, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9912120170272173, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9913130452064864, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9913851452354921, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9908975366031679, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9904655554825078, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9903549955397905, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9902543392523517, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9899656861182228, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.990525194421825, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9895667789011097, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.989678772869995, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9926364146826077, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.988135210513939, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9875962194106334, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9904445579933442, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9897581975421997, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9873420092808323, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9893774041003512, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9882162181253766, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9890310205170891, "id_best": 40, "lr_best": 0.0042, "wd_best": 0.05, "train/loss_best": 1.968787983059883e-06, "validation/loss_best": 0.16015657782554626, "validation/acc_best": 0.9933035714285714, "validation/f1_best": 0.9926364146826077} diff --git a/input_space_v3/flat_lr1e-3_2/eval_v2/nsd_cococlip__patch__attn/config.yaml b/input_space_v3/flat_lr1e-3_2/eval_v2/nsd_cococlip__patch__attn/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..31ce5df8f9a58f640e7a820a600399d5ef306b34 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_2/eval_v2/nsd_cococlip__patch__attn/config.yaml @@ -0,0 +1,96 @@ +output_root: experiments/input_space_v3/output +name_prefix: eval_probe +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_2; eval v2 (nsd_cococlip patch attn) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +dataset_kwargs: {} +classifier_kwargs: + embed_dim: null + dropout: 0.0 + xavier_init: true + norm: true +lr_scale_grid: +- 0.02 +- 0.023 +- 0.028 +- 0.033 +- 0.038 +- 0.045 +- 0.053 +- 0.062 +- 0.074 +- 0.087 +- 0.1 +- 0.12 +- 0.14 +- 0.17 +- 0.2 +- 0.23 +- 0.27 +- 0.32 +- 0.38 +- 0.44 +- 0.52 +- 0.61 +- 0.72 +- 0.85 +- 1 +- 1.2 +- 1.4 +- 1.6 +- 1.9 +- 2.3 +- 2.7 +- 3.1 +- 3.7 +- 4.3 +- 5.1 +- 6 +- 7.1 +- 8.3 +- 9.8 +- 12 +- 14 +- 16 +- 19 +- 22 +- 26 +- 31 +- 36 +- 43 +- 50 +wd_scale_grid: +- 1.0 +num_workers: 8 +prefetch_factor: null +balanced_sampling: false +epochs: 20 +steps_per_epoch: 200 +batch_size: 64 +accum_iter: 2 +lr: 0.0003 +warmup_epochs: 5 +no_decay: false +weight_decay: 0.05 +clip_grad: 1.0 +metrics: +- acc +- f1 +cv_metric: acc +early_stopping: true +amp: true +device: cuda +seed: 4466 +debug: false +wandb: false +wandb_entity: null +wandb_project: fMRI-fm-eval +name: input_space_v3/flat_lr1e-3_2/eval_v2/nsd_cococlip__patch__attn +model: flat_mae +representation: patch +classifier: attn +dataset: nsd_cococlip +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/eval_v2/nsd_cococlip__patch__attn +remote_dir: null diff --git a/input_space_v3/flat_lr1e-3_2/eval_v2/nsd_cococlip__patch__attn/eval_log.json b/input_space_v3/flat_lr1e-3_2/eval_v2/nsd_cococlip__patch__attn/eval_log.json new file mode 100644 index 0000000000000000000000000000000000000000..95bfe2e687bed3c6a0369f70a13459a4ab45c6c4 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_2/eval_v2/nsd_cococlip__patch__attn/eval_log.json @@ -0,0 +1 @@ +{"eval/epoch": 6, "eval/id_best": 21, "eval/lr_best": 0.00018299999999999998, "eval/wd_best": 0.05, "eval/train/loss": 2.1801669597625732, "eval/train/acc": 0.3458926211622976, "eval/train/acc_std": 0.0022717281877348396, "eval/train/f1": 0.2880159919860045, "eval/train/f1_std": 0.0022832071927879672, "eval/validation/loss": 2.3954458236694336, "eval/validation/acc": 0.28460686600221485, "eval/validation/acc_std": 0.005584828990540534, "eval/validation/f1": 0.21909736154722384, "eval/validation/f1_std": 0.0049502997991474175, "eval/test/loss": 2.2506749629974365, "eval/test/acc": 0.31131725417439704, "eval/test/acc_std": 0.0054005653276389814, "eval/test/f1": 0.2434273363467491, "eval/test/f1_std": 0.0051275802848570725, "eval/testid/loss": 2.3332247734069824, "eval/testid/acc": 0.28725660304607675, "eval/testid/acc_std": 0.005829950027686669, "eval/testid/f1": 0.2311441035349374, "eval/testid/f1_std": 0.005427085262412507} diff --git a/input_space_v3/flat_lr1e-3_2/eval_v2/nsd_cococlip__patch__attn/eval_log_best.json b/input_space_v3/flat_lr1e-3_2/eval_v2/nsd_cococlip__patch__attn/eval_log_best.json new file mode 100644 index 0000000000000000000000000000000000000000..af7fa44546c30af8094b8f4a49efa9da174dd267 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_2/eval_v2/nsd_cococlip__patch__attn/eval_log_best.json @@ -0,0 +1 @@ +{"eval/best/epoch": 6, "eval/best/id_best": 21, "eval/best/lr_best": 0.00018299999999999998, "eval/best/wd_best": 0.05, "eval/best/train/loss": 2.1801669597625732, "eval/best/train/acc": 0.3458926211622976, "eval/best/train/acc_std": 0.0022717281877348396, "eval/best/train/f1": 0.2880159919860045, "eval/best/train/f1_std": 0.0022832071927879672, "eval/best/validation/loss": 2.3954458236694336, "eval/best/validation/acc": 0.28460686600221485, "eval/best/validation/acc_std": 0.005584828990540534, "eval/best/validation/f1": 0.21909736154722384, "eval/best/validation/f1_std": 0.0049502997991474175, "eval/best/test/loss": 2.2506749629974365, "eval/best/test/acc": 0.31131725417439704, "eval/best/test/acc_std": 0.0054005653276389814, "eval/best/test/f1": 0.2434273363467491, "eval/best/test/f1_std": 0.0051275802848570725, "eval/best/testid/loss": 2.3332247734069824, "eval/best/testid/acc": 0.28725660304607675, "eval/best/testid/acc_std": 0.005829950027686669, "eval/best/testid/f1": 0.2311441035349374, "eval/best/testid/f1_std": 0.005427085262412507} diff --git a/input_space_v3/flat_lr1e-3_2/eval_v2/nsd_cococlip__patch__attn/eval_log_last.json b/input_space_v3/flat_lr1e-3_2/eval_v2/nsd_cococlip__patch__attn/eval_log_last.json new file mode 100644 index 0000000000000000000000000000000000000000..c213710d78a70d29da820075dd8a0772392c036d --- /dev/null +++ b/input_space_v3/flat_lr1e-3_2/eval_v2/nsd_cococlip__patch__attn/eval_log_last.json @@ -0,0 +1 @@ +{"eval/last/epoch": 19, "eval/last/id_best": 17, "eval/last/lr_best": 9.599999999999999e-05, "eval/last/wd_best": 0.05, "eval/last/train/loss": 2.0857467651367188, "eval/last/train/acc": 0.37278342911583023, "eval/last/train/acc_std": 0.0023572644117479495, "eval/last/train/f1": 0.3145470700921315, "eval/last/train/f1_std": 0.002455183329409054, "eval/last/validation/loss": 2.415623664855957, "eval/last/validation/acc": 0.27740863787375414, "eval/last/validation/acc_std": 0.005207116991620361, "eval/last/validation/f1": 0.21422279215362372, "eval/last/validation/f1_std": 0.004791825358844352, "eval/last/test/loss": 2.253831386566162, "eval/last/test/acc": 0.31391465677179964, "eval/last/test/acc_std": 0.005551675623331149, "eval/last/test/f1": 0.24906886323627356, "eval/last/test/f1_std": 0.005686832820022348, "eval/last/testid/loss": 2.2812986373901367, "eval/last/testid/acc": 0.3082706766917293, "eval/last/testid/acc_std": 0.005838718794456671, "eval/last/testid/f1": 0.2463791046735795, "eval/last/testid/f1_std": 0.005875197368562231} diff --git a/input_space_v3/flat_lr1e-3_2/eval_v2/nsd_cococlip__patch__attn/eval_table.csv b/input_space_v3/flat_lr1e-3_2/eval_v2/nsd_cococlip__patch__attn/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..9de751b850656f1553d04557adc8a08c74428960 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_2/eval_v2/nsd_cococlip__patch__attn/eval_table.csv @@ -0,0 +1,5 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,patch,attn,nsd_cococlip,best,6,0.00018299999999999998,0.05,21,"[0.61, 1.0]",train,2.1801669597625732,0.3458926211622976,0.0022717281877348396,0.2880159919860045,0.0022832071927879672 +flat_mae,patch,attn,nsd_cococlip,best,6,0.00018299999999999998,0.05,21,"[0.61, 1.0]",validation,2.3954458236694336,0.28460686600221485,0.005584828990540534,0.21909736154722384,0.0049502997991474175 +flat_mae,patch,attn,nsd_cococlip,best,6,0.00018299999999999998,0.05,21,"[0.61, 1.0]",test,2.2506749629974365,0.31131725417439704,0.0054005653276389814,0.2434273363467491,0.0051275802848570725 +flat_mae,patch,attn,nsd_cococlip,best,6,0.00018299999999999998,0.05,21,"[0.61, 1.0]",testid,2.3332247734069824,0.28725660304607675,0.005829950027686669,0.2311441035349374,0.005427085262412507 diff --git a/input_space_v3/flat_lr1e-3_2/eval_v2/nsd_cococlip__patch__attn/eval_table_best.csv b/input_space_v3/flat_lr1e-3_2/eval_v2/nsd_cococlip__patch__attn/eval_table_best.csv new file mode 100644 index 0000000000000000000000000000000000000000..9de751b850656f1553d04557adc8a08c74428960 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_2/eval_v2/nsd_cococlip__patch__attn/eval_table_best.csv @@ -0,0 +1,5 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,patch,attn,nsd_cococlip,best,6,0.00018299999999999998,0.05,21,"[0.61, 1.0]",train,2.1801669597625732,0.3458926211622976,0.0022717281877348396,0.2880159919860045,0.0022832071927879672 +flat_mae,patch,attn,nsd_cococlip,best,6,0.00018299999999999998,0.05,21,"[0.61, 1.0]",validation,2.3954458236694336,0.28460686600221485,0.005584828990540534,0.21909736154722384,0.0049502997991474175 +flat_mae,patch,attn,nsd_cococlip,best,6,0.00018299999999999998,0.05,21,"[0.61, 1.0]",test,2.2506749629974365,0.31131725417439704,0.0054005653276389814,0.2434273363467491,0.0051275802848570725 +flat_mae,patch,attn,nsd_cococlip,best,6,0.00018299999999999998,0.05,21,"[0.61, 1.0]",testid,2.3332247734069824,0.28725660304607675,0.005829950027686669,0.2311441035349374,0.005427085262412507 diff --git a/input_space_v3/flat_lr1e-3_2/eval_v2/nsd_cococlip__patch__attn/eval_table_last.csv b/input_space_v3/flat_lr1e-3_2/eval_v2/nsd_cococlip__patch__attn/eval_table_last.csv new file mode 100644 index 0000000000000000000000000000000000000000..5605edf15c145197993f3ff01d1497f5b4d9026c --- /dev/null +++ b/input_space_v3/flat_lr1e-3_2/eval_v2/nsd_cococlip__patch__attn/eval_table_last.csv @@ -0,0 +1,5 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,patch,attn,nsd_cococlip,last,19,9.599999999999999e-05,0.05,17,"[0.32, 1.0]",train,2.0857467651367188,0.37278342911583023,0.0023572644117479495,0.3145470700921315,0.002455183329409054 +flat_mae,patch,attn,nsd_cococlip,last,19,9.599999999999999e-05,0.05,17,"[0.32, 1.0]",validation,2.415623664855957,0.27740863787375414,0.005207116991620361,0.21422279215362372,0.004791825358844352 +flat_mae,patch,attn,nsd_cococlip,last,19,9.599999999999999e-05,0.05,17,"[0.32, 1.0]",test,2.253831386566162,0.31391465677179964,0.005551675623331149,0.24906886323627356,0.005686832820022348 +flat_mae,patch,attn,nsd_cococlip,last,19,9.599999999999999e-05,0.05,17,"[0.32, 1.0]",testid,2.2812986373901367,0.3082706766917293,0.005838718794456671,0.2463791046735795,0.005875197368562231 diff --git a/input_space_v3/flat_lr1e-3_2/eval_v2/nsd_cococlip__patch__attn/log.txt b/input_space_v3/flat_lr1e-3_2/eval_v2/nsd_cococlip__patch__attn/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..a342e9b091bd1832136295f2b1dc737a01abc08c --- /dev/null +++ b/input_space_v3/flat_lr1e-3_2/eval_v2/nsd_cococlip__patch__attn/log.txt @@ -0,0 +1,963 @@ +fMRI foundation model probe eval +version: 0.1.dev86+gf97f52698 +sha: bcce2b486277d3a5b520775efd9cdf1a2affce36, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-04-08 20:31:09 +config: +output_root: experiments/input_space_v3/output +name_prefix: eval_probe +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_2; eval v2 (nsd_cococlip patch attn) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +dataset_kwargs: {} +classifier_kwargs: + embed_dim: null + dropout: 0.0 + xavier_init: true + norm: true +lr_scale_grid: +- 0.02 +- 0.023 +- 0.028 +- 0.033 +- 0.038 +- 0.045 +- 0.053 +- 0.062 +- 0.074 +- 0.087 +- 0.1 +- 0.12 +- 0.14 +- 0.17 +- 0.2 +- 0.23 +- 0.27 +- 0.32 +- 0.38 +- 0.44 +- 0.52 +- 0.61 +- 0.72 +- 0.85 +- 1 +- 1.2 +- 1.4 +- 1.6 +- 1.9 +- 2.3 +- 2.7 +- 3.1 +- 3.7 +- 4.3 +- 5.1 +- 6 +- 7.1 +- 8.3 +- 9.8 +- 12 +- 14 +- 16 +- 19 +- 22 +- 26 +- 31 +- 36 +- 43 +- 50 +wd_scale_grid: +- 1.0 +num_workers: 8 +prefetch_factor: null +balanced_sampling: false +epochs: 20 +steps_per_epoch: 200 +batch_size: 64 +accum_iter: 2 +lr: 0.0003 +warmup_epochs: 5 +no_decay: false +weight_decay: 0.05 +clip_grad: 1.0 +metrics: +- acc +- f1 +cv_metric: acc +early_stopping: true +amp: true +device: cuda +seed: 4466 +debug: false +wandb: false +wandb_entity: null +wandb_project: fMRI-fm-eval +name: input_space_v3/flat_lr1e-3_2/eval_v2/nsd_cococlip__patch__attn +model: flat_mae +representation: patch +classifier: attn +dataset: nsd_cococlip +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/eval_v2/nsd_cococlip__patch__attn +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=True, reg_tokens=0, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: nsd_cococlip (flat) +train (n=32539): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'run', 'trial_id', 'nsd_id', 'category_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 32539 +}), + labels=[ 3 4 5 6 10 11 17 18 19 20 22 23 25 30 31 33 36 37 38 53 55 59 61 74], + counts=[1286 1180 1639 1868 834 824 1026 1042 913 1853 1503 2092 1001 1410 + 794 1241 1904 1872 2267 1428 889 904 1447 1322] +) + +validation (n=5418): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'run', 'trial_id', 'nsd_id', 'category_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 5418 +}), + labels=[ 3 4 5 6 10 11 17 18 19 20 22 23 25 30 31 33 36 37 38 53 55 59 61 74], + counts=[197 161 276 345 126 142 143 185 112 295 285 387 169 250 159 193 316 334 + 343 215 172 141 226 246] +) + +test (n=5390): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'run', 'trial_id', 'nsd_id', 'category_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 5390 +}), + labels=[ 3 4 5 6 10 11 17 18 19 20 22 23 25 30 31 33 36 37 38 53 55 59 61 74], + counts=[202 172 274 298 144 180 134 182 186 293 218 343 165 185 140 177 346 333 + 345 271 165 140 251 246] +) + +testid (n=5187): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'run', 'trial_id', 'nsd_id', 'category_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 5187 +}), + labels=[ 3 4 5 6 10 11 17 18 19 20 22 23 25 30 31 33 36 37 38 53 55 59 61 74], + counts=[197 159 267 273 123 153 175 184 139 310 215 386 153 230 118 192 330 306 + 349 223 143 127 249 186] +) + +running backbone on example batch to get embedding dim +embedding feature dim (patch): 768 +initializing sweep of classifier heads +classifiers: +ModuleList( + (0-48): 49 x AttnPoolClassifier( + (kv): Linear(in_features=768, out_features=1536, bias=True) + (linear): Linear(in_features=768, out_features=24, bias=True) + ) +) +classifier params (train): 58.8M (58.8M) +setting up optimizer +total batch size: 128 = 64 bs per gpu x 2 accum +lr: 3.00e-04 +full schedule: epochs = 20 (steps = 4000) (decay = True) +warmup: epochs = 5 (steps = 1000) +start training for 20 epochs +train: [0] [ 0/400] eta: 0:25:00 lr: nan time: 3.7506 data: 3.1382 max mem: 21740 +train: [0] [ 20/400] eta: 0:03:55 lr: 0.000003 loss: 3.1773 (3.1833) grad: 0.1586 (0.1629) time: 0.4629 data: 0.0041 max mem: 22448 +train: [0] [ 40/400] eta: 0:03:14 lr: 0.000006 loss: 3.1735 (3.1742) grad: 0.1577 (0.1631) time: 0.4596 data: 0.0040 max mem: 22448 +train: [0] [ 60/400] eta: 0:02:53 lr: 0.000009 loss: 3.1701 (3.1755) grad: 0.1563 (0.1631) time: 0.4503 data: 0.0042 max mem: 22448 +train: [0] [ 80/400] eta: 0:02:39 lr: 0.000012 loss: 3.1700 (3.1739) grad: 0.1606 (0.1622) time: 0.4573 data: 0.0041 max mem: 22448 +train: [0] [100/400] eta: 0:02:26 lr: 0.000015 loss: 3.1668 (3.1730) grad: 0.1575 (0.1608) time: 0.4533 data: 0.0041 max mem: 22448 +train: [0] [120/400] eta: 0:02:14 lr: 0.000018 loss: 3.1556 (3.1704) grad: 0.1437 (0.1584) time: 0.4392 data: 0.0040 max mem: 22448 +train: [0] [140/400] eta: 0:02:03 lr: 0.000021 loss: 3.1523 (3.1681) grad: 0.1447 (0.1580) time: 0.4446 data: 0.0041 max mem: 22448 +train: [0] [160/400] eta: 0:01:53 lr: 0.000024 loss: 3.1489 (3.1654) grad: 0.1613 (0.1594) time: 0.4494 data: 0.0039 max mem: 22448 +train: [0] [180/400] eta: 0:01:43 lr: 0.000027 loss: 3.1412 (3.1624) grad: 0.1593 (0.1590) time: 0.4420 data: 0.0041 max mem: 22448 +train: [0] [200/400] eta: 0:01:33 lr: 0.000030 loss: 3.1342 (3.1610) grad: 0.1458 (0.1576) time: 0.4503 data: 0.0040 max mem: 22448 +train: [0] [220/400] eta: 0:01:23 lr: 0.000033 loss: 3.1459 (3.1596) grad: 0.1485 (0.1571) time: 0.4538 data: 0.0039 max mem: 22448 +train: [0] [240/400] eta: 0:01:14 lr: 0.000036 loss: 3.1355 (3.1568) grad: 0.1532 (0.1566) time: 0.4636 data: 0.0040 max mem: 22448 +train: [0] [260/400] eta: 0:01:05 lr: 0.000039 loss: 3.1236 (3.1539) grad: 0.1493 (0.1560) time: 0.4609 data: 0.0042 max mem: 22448 +train: [0] [280/400] eta: 0:00:55 lr: 0.000042 loss: 3.1017 (3.1499) grad: 0.1493 (0.1558) time: 0.4651 data: 0.0042 max mem: 22448 +train: [0] [300/400] eta: 0:00:46 lr: 0.000045 loss: 3.0904 (3.1446) grad: 0.1527 (0.1557) time: 0.4657 data: 0.0042 max mem: 22448 +train: [0] [320/400] eta: 0:00:37 lr: 0.000048 loss: 3.0688 (3.1405) grad: 0.1600 (0.1564) time: 0.4511 data: 0.0045 max mem: 22448 +train: [0] [340/400] eta: 0:00:27 lr: 0.000051 loss: 3.0705 (3.1365) grad: 0.1631 (0.1566) time: 0.4618 data: 0.0043 max mem: 22448 +train: [0] [360/400] eta: 0:00:18 lr: 0.000054 loss: 3.0571 (3.1317) grad: 0.1618 (0.1573) time: 0.4563 data: 0.0041 max mem: 22448 +train: [0] [380/400] eta: 0:00:09 lr: 0.000057 loss: 3.0480 (3.1274) grad: 0.1709 (0.1581) time: 0.4671 data: 0.0041 max mem: 22448 +train: [0] [399/400] eta: 0:00:00 lr: 0.000060 loss: 3.0439 (3.1240) grad: 0.1792 (0.1590) time: 0.4488 data: 0.0040 max mem: 22448 +train: [0] Total time: 0:03:05 (0.4636 s / it) +train: [0] Summary: lr: 0.000060 loss: 3.0439 (3.1240) grad: 0.1792 (0.1590) +eval (validation): [0] [ 0/85] eta: 0:04:38 time: 3.2708 data: 2.9964 max mem: 22448 +eval (validation): [0] [20/85] eta: 0:00:31 time: 0.3461 data: 0.0046 max mem: 22448 +eval (validation): [0] [40/85] eta: 0:00:18 time: 0.3280 data: 0.0036 max mem: 22448 +eval (validation): [0] [60/85] eta: 0:00:09 time: 0.3255 data: 0.0040 max mem: 22448 +eval (validation): [0] [80/85] eta: 0:00:01 time: 0.3141 data: 0.0037 max mem: 22448 +eval (validation): [0] [84/85] eta: 0:00:00 time: 0.3100 data: 0.0037 max mem: 22448 +eval (validation): [0] Total time: 0:00:31 (0.3652 s / it) +cv: [0] best hparam: (31, 1.0) (045) ('045_lr3.1e+01_wd1.0e+00') loss: 2.569 acc: 0.246 f1: 0.168 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/eval_v2/nsd_cococlip__patch__attn/checkpoint-best.pth +train: [1] [ 0/400] eta: 0:21:33 lr: nan time: 3.2346 data: 2.8964 max mem: 22448 +train: [1] [ 20/400] eta: 0:03:35 lr: 0.000063 loss: 3.0023 (3.0080) grad: 0.1717 (0.1690) time: 0.4340 data: 0.0045 max mem: 22448 +train: [1] [ 40/400] eta: 0:03:03 lr: 0.000066 loss: 3.0023 (3.0063) grad: 0.1613 (0.1649) time: 0.4477 data: 0.0036 max mem: 22448 +train: [1] [ 60/400] eta: 0:02:45 lr: 0.000069 loss: 2.9956 (2.9949) grad: 0.1625 (0.1668) time: 0.4406 data: 0.0040 max mem: 22448 +train: [1] [ 80/400] eta: 0:02:32 lr: 0.000072 loss: 2.9779 (2.9959) grad: 0.1695 (0.1700) time: 0.4479 data: 0.0039 max mem: 22448 +train: [1] [100/400] eta: 0:02:21 lr: 0.000075 loss: 2.9756 (2.9885) grad: 0.1734 (0.1726) time: 0.4489 data: 0.0040 max mem: 22448 +train: [1] [120/400] eta: 0:02:10 lr: 0.000078 loss: 2.9710 (2.9856) grad: 0.1785 (0.1738) time: 0.4462 data: 0.0040 max mem: 22448 +train: [1] [140/400] eta: 0:02:00 lr: 0.000081 loss: 2.9710 (2.9840) grad: 0.1785 (0.1749) time: 0.4445 data: 0.0041 max mem: 22448 +train: [1] [160/400] eta: 0:01:50 lr: 0.000084 loss: 2.9697 (2.9841) grad: 0.1781 (0.1750) time: 0.4422 data: 0.0040 max mem: 22448 +train: [1] [180/400] eta: 0:01:40 lr: 0.000087 loss: 2.9716 (2.9836) grad: 0.1736 (0.1756) time: 0.4373 data: 0.0039 max mem: 22448 +train: [1] [200/400] eta: 0:01:31 lr: 0.000090 loss: 2.9529 (2.9797) grad: 0.1765 (0.1763) time: 0.4331 data: 0.0040 max mem: 22448 +train: [1] [220/400] eta: 0:01:21 lr: 0.000093 loss: 2.9095 (2.9727) grad: 0.1931 (0.1785) time: 0.4422 data: 0.0040 max mem: 22448 +train: [1] [240/400] eta: 0:01:12 lr: 0.000096 loss: 2.9102 (2.9693) grad: 0.1932 (0.1787) time: 0.4388 data: 0.0039 max mem: 22448 +train: [1] [260/400] eta: 0:01:03 lr: 0.000099 loss: 2.9346 (2.9677) grad: 0.1794 (0.1792) time: 0.4470 data: 0.0041 max mem: 22448 +train: [1] [280/400] eta: 0:00:54 lr: 0.000102 loss: 2.9346 (2.9639) grad: 0.1824 (0.1795) time: 0.4502 data: 0.0040 max mem: 22448 +train: [1] [300/400] eta: 0:00:45 lr: 0.000105 loss: 2.9046 (2.9624) grad: 0.1851 (0.1801) time: 0.4554 data: 0.0040 max mem: 22448 +train: [1] [320/400] eta: 0:00:36 lr: 0.000108 loss: 2.8892 (2.9579) grad: 0.1883 (0.1806) time: 0.4490 data: 0.0040 max mem: 22448 +train: [1] [340/400] eta: 0:00:27 lr: 0.000111 loss: 2.8725 (2.9531) grad: 0.1883 (0.1810) time: 0.4780 data: 0.0041 max mem: 22448 +train: [1] [360/400] eta: 0:00:18 lr: 0.000114 loss: 2.8780 (2.9511) grad: 0.1844 (0.1813) time: 0.4553 data: 0.0041 max mem: 22448 +train: [1] [380/400] eta: 0:00:09 lr: 0.000117 loss: 2.8959 (2.9477) grad: 0.1850 (0.1822) time: 0.4565 data: 0.0042 max mem: 22448 +train: [1] [399/400] eta: 0:00:00 lr: 0.000120 loss: 2.8959 (2.9458) grad: 0.1980 (0.1834) time: 0.4448 data: 0.0041 max mem: 22448 +train: [1] Total time: 0:03:01 (0.4543 s / it) +train: [1] Summary: lr: 0.000120 loss: 2.8959 (2.9458) grad: 0.1980 (0.1834) +eval (validation): [1] [ 0/85] eta: 0:04:34 time: 3.2248 data: 2.9480 max mem: 22448 +eval (validation): [1] [20/85] eta: 0:00:30 time: 0.3363 data: 0.0051 max mem: 22448 +eval (validation): [1] [40/85] eta: 0:00:18 time: 0.3393 data: 0.0042 max mem: 22448 +eval (validation): [1] [60/85] eta: 0:00:09 time: 0.3273 data: 0.0033 max mem: 22448 +eval (validation): [1] [80/85] eta: 0:00:01 time: 0.3225 data: 0.0042 max mem: 22448 +eval (validation): [1] [84/85] eta: 0:00:00 time: 0.3172 data: 0.0040 max mem: 22448 +eval (validation): [1] Total time: 0:00:31 (0.3673 s / it) +cv: [1] best hparam: (14, 1.0) (040) ('040_lr1.4e+01_wd1.0e+00') loss: 2.442 acc: 0.265 f1: 0.191 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/eval_v2/nsd_cococlip__patch__attn/checkpoint-best.pth +train: [2] [ 0/400] eta: 0:21:31 lr: nan time: 3.2290 data: 2.8936 max mem: 22448 +train: [2] [ 20/400] eta: 0:03:37 lr: 0.000123 loss: 2.8970 (2.8692) grad: 0.2187 (0.2183) time: 0.4393 data: 0.0042 max mem: 22448 +train: [2] [ 40/400] eta: 0:03:02 lr: 0.000126 loss: 2.8962 (2.8726) grad: 0.2091 (0.2135) time: 0.4392 data: 0.0035 max mem: 22448 +train: [2] [ 60/400] eta: 0:02:44 lr: 0.000129 loss: 2.8748 (2.8723) grad: 0.2065 (0.2103) time: 0.4401 data: 0.0040 max mem: 22448 +train: [2] [ 80/400] eta: 0:02:31 lr: 0.000132 loss: 2.8608 (2.8704) grad: 0.2046 (0.2089) time: 0.4408 data: 0.0040 max mem: 22448 +train: [2] [100/400] eta: 0:02:20 lr: 0.000135 loss: 2.8297 (2.8615) grad: 0.2091 (0.2095) time: 0.4372 data: 0.0038 max mem: 22448 +train: [2] [120/400] eta: 0:02:09 lr: 0.000138 loss: 2.8271 (2.8562) grad: 0.2131 (0.2123) time: 0.4478 data: 0.0041 max mem: 22448 +train: [2] [140/400] eta: 0:02:00 lr: 0.000141 loss: 2.8823 (2.8679) grad: 0.2383 (0.2391) time: 0.4560 data: 0.0038 max mem: 22448 +train: [2] [160/400] eta: 0:01:50 lr: 0.000144 loss: 3.0180 (2.9373) grad: 0.6262 (0.3405) time: 0.4477 data: 0.0041 max mem: 22448 +WARNING: classifier 48 (50, 1.0) diverged (loss=66.58 > 63.56) at step 484. Freezing. +train: [2] [180/400] eta: 0:01:40 lr: 0.000147 loss: 3.2679 (2.9715) grad: 1.0425 (0.3874) time: 0.4411 data: 0.0041 max mem: 22448 +train: [2] [200/400] eta: 0:01:31 lr: 0.000150 loss: 2.8201 (2.9561) grad: 0.2083 (0.3700) time: 0.4484 data: 0.0041 max mem: 22448 +train: [2] [220/400] eta: 0:01:22 lr: 0.000153 loss: 2.8201 (2.9453) grad: 0.2123 (0.3570) time: 0.4361 data: 0.0039 max mem: 22448 +train: [2] [240/400] eta: 0:01:12 lr: 0.000156 loss: 2.8607 (2.9393) grad: 0.2224 (0.3461) time: 0.4419 data: 0.0038 max mem: 22448 +train: [2] [260/400] eta: 0:01:03 lr: 0.000159 loss: 2.8537 (2.9299) grad: 0.2163 (0.3359) time: 0.4604 data: 0.0041 max mem: 22448 +train: [2] [280/400] eta: 0:00:54 lr: 0.000162 loss: 2.7999 (2.9207) grad: 0.2234 (0.3294) time: 0.4502 data: 0.0040 max mem: 22448 +train: [2] [300/400] eta: 0:00:45 lr: 0.000165 loss: 2.7925 (2.9125) grad: 0.2345 (0.3230) time: 0.4551 data: 0.0040 max mem: 22448 +train: [2] [320/400] eta: 0:00:36 lr: 0.000168 loss: 2.7801 (2.9054) grad: 0.2321 (0.3171) time: 0.4512 data: 0.0040 max mem: 22448 +train: [2] [340/400] eta: 0:00:27 lr: 0.000171 loss: 2.7801 (2.9008) grad: 0.2242 (0.3118) time: 0.4694 data: 0.0040 max mem: 22448 +train: [2] [360/400] eta: 0:00:18 lr: 0.000174 loss: 2.8175 (2.8977) grad: 0.2355 (0.3084) time: 0.4458 data: 0.0041 max mem: 22448 +train: [2] [380/400] eta: 0:00:09 lr: 0.000177 loss: 2.8557 (2.8988) grad: 0.2690 (0.3150) time: 0.4585 data: 0.0040 max mem: 22448 +WARNING: classifier 47 (43, 1.0) diverged (loss=65.86 > 63.56) at step 598. Freezing. +train: [2] [399/400] eta: 0:00:00 lr: 0.000180 loss: 2.9442 (2.9183) grad: 0.4832 (0.3536) time: 0.4373 data: 0.0039 max mem: 22448 +train: [2] Total time: 0:03:01 (0.4544 s / it) +train: [2] Summary: lr: 0.000180 loss: 2.9442 (2.9183) grad: 0.4832 (0.3536) +eval (validation): [2] [ 0/85] eta: 0:04:28 time: 3.1555 data: 2.9167 max mem: 22448 +eval (validation): [2] [20/85] eta: 0:00:31 time: 0.3465 data: 0.0060 max mem: 22448 +eval (validation): [2] [40/85] eta: 0:00:18 time: 0.3515 data: 0.0042 max mem: 22448 +eval (validation): [2] [60/85] eta: 0:00:09 time: 0.3412 data: 0.0039 max mem: 22448 +eval (validation): [2] [80/85] eta: 0:00:01 time: 0.3164 data: 0.0041 max mem: 22448 +eval (validation): [2] [84/85] eta: 0:00:00 time: 0.3076 data: 0.0040 max mem: 22448 +eval (validation): [2] Total time: 0:00:31 (0.3730 s / it) +cv: [2] best hparam: (3.1, 1.0) (031) ('031_lr3.1e+00_wd1.0e+00') loss: 2.419 acc: 0.273 f1: 0.192 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/eval_v2/nsd_cococlip__patch__attn/checkpoint-best.pth +train: [3] [ 0/400] eta: 0:22:23 lr: nan time: 3.3585 data: 2.9755 max mem: 22448 +train: [3] [ 20/400] eta: 0:03:41 lr: 0.000183 loss: 2.8011 (2.8132) grad: 0.2788 (0.3312) time: 0.4443 data: 0.0038 max mem: 22448 +WARNING: classifier 46 (36, 1.0) diverged (loss=66.60 > 63.56) at step 619. Freezing. +train: [3] [ 40/400] eta: 0:03:03 lr: 0.000186 loss: 2.9254 (3.0500) grad: 0.4245 (0.7056) time: 0.4355 data: 0.0042 max mem: 22448 +train: [3] [ 60/400] eta: 0:02:44 lr: 0.000189 loss: 2.8971 (2.9579) grad: 0.2354 (0.5429) time: 0.4299 data: 0.0040 max mem: 22448 +train: [3] [ 80/400] eta: 0:02:31 lr: 0.000192 loss: 2.7702 (2.9155) grad: 0.2149 (0.4618) time: 0.4351 data: 0.0041 max mem: 22448 +train: [3] [100/400] eta: 0:02:20 lr: 0.000195 loss: 2.7667 (2.8844) grad: 0.2121 (0.4126) time: 0.4453 data: 0.0042 max mem: 22448 +train: [3] [120/400] eta: 0:02:09 lr: 0.000198 loss: 2.7448 (2.8640) grad: 0.2177 (0.3814) time: 0.4436 data: 0.0040 max mem: 22448 +train: [3] [140/400] eta: 0:01:59 lr: 0.000201 loss: 2.7783 (2.8532) grad: 0.2343 (0.3616) time: 0.4304 data: 0.0042 max mem: 22448 +train: [3] [160/400] eta: 0:01:49 lr: 0.000204 loss: 2.7837 (2.8484) grad: 0.2374 (0.3455) time: 0.4547 data: 0.0042 max mem: 22448 +train: [3] [180/400] eta: 0:01:40 lr: 0.000207 loss: 2.7967 (2.8389) grad: 0.2355 (0.3352) time: 0.4439 data: 0.0041 max mem: 22448 +train: [3] [200/400] eta: 0:01:30 lr: 0.000210 loss: 2.8031 (2.8384) grad: 0.2639 (0.3349) time: 0.4393 data: 0.0040 max mem: 22448 +train: [3] [220/400] eta: 0:01:21 lr: 0.000213 loss: 2.8917 (2.8553) grad: 0.3873 (0.3775) time: 0.4466 data: 0.0041 max mem: 22448 +train: [3] [240/400] eta: 0:01:12 lr: 0.000216 loss: 3.3259 (2.9161) grad: 1.1041 (0.4626) time: 0.4497 data: 0.0041 max mem: 22448 +WARNING: classifier 44 (26, 1.0) diverged (loss=64.52 > 63.56) at step 721. Freezing. +train: [3] [260/400] eta: 0:01:03 lr: 0.000219 loss: 3.4085 (2.9140) grad: 0.9828 (0.4587) time: 0.4496 data: 0.0041 max mem: 22448 +train: [3] [280/400] eta: 0:00:54 lr: 0.000222 loss: 2.7672 (2.9036) grad: 0.2146 (0.4413) time: 0.4375 data: 0.0042 max mem: 22448 +train: [3] [300/400] eta: 0:00:45 lr: 0.000225 loss: 2.7763 (2.8953) grad: 0.2136 (0.4261) time: 0.4565 data: 0.0041 max mem: 22448 +train: [3] [320/400] eta: 0:00:36 lr: 0.000228 loss: 2.7592 (2.8865) grad: 0.2276 (0.4151) time: 0.4510 data: 0.0043 max mem: 22448 +train: [3] [340/400] eta: 0:00:27 lr: 0.000231 loss: 2.7956 (2.8946) grad: 0.2688 (0.4370) time: 0.4672 data: 0.0042 max mem: 22448 +WARNING: classifier 45 (31, 1.0) diverged (loss=68.03 > 63.56) at step 771. Freezing. +train: [3] [360/400] eta: 0:00:18 lr: 0.000234 loss: 2.8486 (2.8983) grad: 0.2676 (0.4323) time: 0.4408 data: 0.0041 max mem: 22448 +train: [3] [380/400] eta: 0:00:09 lr: 0.000237 loss: 2.7618 (2.8916) grad: 0.2198 (0.4210) time: 0.4561 data: 0.0043 max mem: 22448 +train: [3] [399/400] eta: 0:00:00 lr: 0.000240 loss: 2.7476 (2.8837) grad: 0.2153 (0.4103) time: 0.4302 data: 0.0039 max mem: 22448 +train: [3] Total time: 0:03:00 (0.4520 s / it) +train: [3] Summary: lr: 0.000240 loss: 2.7476 (2.8837) grad: 0.2153 (0.4103) +eval (validation): [3] [ 0/85] eta: 0:04:40 time: 3.3042 data: 3.0677 max mem: 22448 +eval (validation): [3] [20/85] eta: 0:00:31 time: 0.3404 data: 0.0055 max mem: 22448 +eval (validation): [3] [40/85] eta: 0:00:18 time: 0.3383 data: 0.0037 max mem: 22448 +eval (validation): [3] [60/85] eta: 0:00:09 time: 0.3265 data: 0.0039 max mem: 22448 +eval (validation): [3] [80/85] eta: 0:00:01 time: 0.3215 data: 0.0038 max mem: 22448 +eval (validation): [3] [84/85] eta: 0:00:00 time: 0.3148 data: 0.0039 max mem: 22448 +eval (validation): [3] Total time: 0:00:31 (0.3687 s / it) +cv: [3] best hparam: (3.7, 1.0) (032) ('032_lr3.7e+00_wd1.0e+00') loss: 2.411 acc: 0.271 f1: 0.200 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [4] [ 0/400] eta: 0:22:30 lr: nan time: 3.3758 data: 2.9949 max mem: 22448 +train: [4] [ 20/400] eta: 0:03:40 lr: 0.000243 loss: 2.6690 (2.6930) grad: 0.2128 (0.2125) time: 0.4418 data: 0.0043 max mem: 22448 +train: [4] [ 40/400] eta: 0:03:02 lr: 0.000246 loss: 2.7096 (2.7056) grad: 0.2127 (0.2117) time: 0.4280 data: 0.0041 max mem: 22448 +train: [4] [ 60/400] eta: 0:02:44 lr: 0.000249 loss: 2.7205 (2.7120) grad: 0.2129 (0.2123) time: 0.4335 data: 0.0041 max mem: 22448 +train: [4] [ 80/400] eta: 0:02:30 lr: 0.000252 loss: 2.7118 (2.7140) grad: 0.2100 (0.2112) time: 0.4381 data: 0.0042 max mem: 22448 +train: [4] [100/400] eta: 0:02:19 lr: 0.000255 loss: 2.7534 (2.7264) grad: 0.2078 (0.2122) time: 0.4390 data: 0.0041 max mem: 22448 +train: [4] [120/400] eta: 0:02:08 lr: 0.000258 loss: 2.7514 (2.7237) grad: 0.2157 (0.2138) time: 0.4367 data: 0.0042 max mem: 22448 +train: [4] [140/400] eta: 0:01:58 lr: 0.000261 loss: 2.7137 (2.7215) grad: 0.2221 (0.2168) time: 0.4396 data: 0.0040 max mem: 22448 +train: [4] [160/400] eta: 0:01:49 lr: 0.000264 loss: 2.7239 (2.7235) grad: 0.2401 (0.2198) time: 0.4348 data: 0.0041 max mem: 22448 +train: [4] [180/400] eta: 0:01:39 lr: 0.000267 loss: 2.7318 (2.7274) grad: 0.2488 (0.2239) time: 0.4305 data: 0.0040 max mem: 22448 +train: [4] [200/400] eta: 0:01:30 lr: 0.000270 loss: 2.7313 (2.7256) grad: 0.2513 (0.2264) time: 0.4397 data: 0.0039 max mem: 22448 +train: [4] [220/400] eta: 0:01:20 lr: 0.000273 loss: 2.7319 (2.7286) grad: 0.2509 (0.2290) time: 0.4401 data: 0.0040 max mem: 22448 +train: [4] [240/400] eta: 0:01:11 lr: 0.000276 loss: 2.7377 (2.7292) grad: 0.2555 (0.2318) time: 0.4332 data: 0.0042 max mem: 22448 +train: [4] [260/400] eta: 0:01:02 lr: 0.000279 loss: 2.7855 (2.7358) grad: 0.2739 (0.2408) time: 0.4485 data: 0.0041 max mem: 22448 +train: [4] [280/400] eta: 0:00:53 lr: 0.000282 loss: 2.8917 (2.7595) grad: 0.5090 (0.2818) time: 0.4375 data: 0.0041 max mem: 22448 +WARNING: classifier 43 (22, 1.0) diverged (loss=67.97 > 63.56) at step 947. Freezing. +train: [4] [300/400] eta: 0:00:44 lr: 0.000285 loss: 3.1583 (2.7989) grad: 0.9696 (0.3395) time: 0.4407 data: 0.0040 max mem: 22448 +train: [4] [320/400] eta: 0:00:35 lr: 0.000288 loss: 2.7447 (2.7944) grad: 0.2201 (0.3313) time: 0.4432 data: 0.0041 max mem: 22448 +train: [4] [340/400] eta: 0:00:26 lr: 0.000291 loss: 2.7419 (2.7911) grad: 0.2068 (0.3242) time: 0.4524 data: 0.0041 max mem: 22448 +train: [4] [360/400] eta: 0:00:17 lr: 0.000294 loss: 2.7361 (2.7891) grad: 0.2125 (0.3183) time: 0.4338 data: 0.0041 max mem: 22448 +train: [4] [380/400] eta: 0:00:08 lr: 0.000297 loss: 2.7218 (2.7849) grad: 0.2175 (0.3130) time: 0.4551 data: 0.0046 max mem: 22448 +train: [4] [399/400] eta: 0:00:00 lr: 0.000300 loss: 2.7164 (2.7809) grad: 0.2156 (0.3081) time: 0.4359 data: 0.0041 max mem: 22448 +train: [4] Total time: 0:02:58 (0.4466 s / it) +train: [4] Summary: lr: 0.000300 loss: 2.7164 (2.7809) grad: 0.2156 (0.3081) +eval (validation): [4] [ 0/85] eta: 0:04:46 time: 3.3665 data: 3.0737 max mem: 22448 +eval (validation): [4] [20/85] eta: 0:00:31 time: 0.3452 data: 0.0037 max mem: 22448 +eval (validation): [4] [40/85] eta: 0:00:18 time: 0.3354 data: 0.0040 max mem: 22448 +eval (validation): [4] [60/85] eta: 0:00:09 time: 0.3313 data: 0.0040 max mem: 22448 +eval (validation): [4] [80/85] eta: 0:00:01 time: 0.3218 data: 0.0040 max mem: 22448 +eval (validation): [4] [84/85] eta: 0:00:00 time: 0.3123 data: 0.0040 max mem: 22448 +eval (validation): [4] Total time: 0:00:31 (0.3704 s / it) +cv: [4] best hparam: (1.6, 1.0) (027) ('027_lr1.6e+00_wd1.0e+00') loss: 2.416 acc: 0.277 f1: 0.213 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/eval_v2/nsd_cococlip__patch__attn/checkpoint-best.pth +train: [5] [ 0/400] eta: 0:22:31 lr: nan time: 3.3791 data: 3.0094 max mem: 22448 +train: [5] [ 20/400] eta: 0:03:43 lr: 0.000300 loss: 2.5933 (2.6086) grad: 0.2146 (0.2184) time: 0.4483 data: 0.0024 max mem: 22448 +train: [5] [ 40/400] eta: 0:03:04 lr: 0.000300 loss: 2.6510 (2.6629) grad: 0.2222 (0.2249) time: 0.4324 data: 0.0041 max mem: 22448 +train: [5] [ 60/400] eta: 0:02:46 lr: 0.000300 loss: 2.6782 (2.6698) grad: 0.2323 (0.2285) time: 0.4433 data: 0.0041 max mem: 22448 +train: [5] [ 80/400] eta: 0:02:32 lr: 0.000300 loss: 2.6816 (2.6674) grad: 0.2312 (0.2279) time: 0.4354 data: 0.0042 max mem: 22448 +train: [5] [100/400] eta: 0:02:20 lr: 0.000300 loss: 2.6892 (2.6746) grad: 0.2312 (0.2308) time: 0.4381 data: 0.0042 max mem: 22448 +train: [5] [120/400] eta: 0:02:09 lr: 0.000300 loss: 2.6591 (2.6660) grad: 0.2303 (0.2300) time: 0.4387 data: 0.0040 max mem: 22448 +train: [5] [140/400] eta: 0:01:59 lr: 0.000300 loss: 2.6108 (2.6590) grad: 0.2206 (0.2287) time: 0.4415 data: 0.0042 max mem: 22448 +train: [5] [160/400] eta: 0:01:50 lr: 0.000299 loss: 2.6383 (2.6579) grad: 0.2202 (0.2289) time: 0.4470 data: 0.0043 max mem: 22448 +train: [5] [180/400] eta: 0:01:40 lr: 0.000299 loss: 2.6523 (2.6618) grad: 0.2249 (0.2288) time: 0.4365 data: 0.0041 max mem: 22448 +train: [5] [200/400] eta: 0:01:30 lr: 0.000299 loss: 2.6437 (2.6600) grad: 0.2286 (0.2291) time: 0.4369 data: 0.0040 max mem: 22448 +train: [5] [220/400] eta: 0:01:21 lr: 0.000299 loss: 2.6255 (2.6581) grad: 0.2266 (0.2283) time: 0.4296 data: 0.0040 max mem: 22448 +train: [5] [240/400] eta: 0:01:12 lr: 0.000299 loss: 2.6389 (2.6570) grad: 0.2277 (0.2285) time: 0.4350 data: 0.0040 max mem: 22448 +train: [5] [260/400] eta: 0:01:03 lr: 0.000299 loss: 2.6149 (2.6537) grad: 0.2277 (0.2282) time: 0.4456 data: 0.0040 max mem: 22448 +train: [5] [280/400] eta: 0:00:54 lr: 0.000298 loss: 2.6604 (2.6555) grad: 0.2303 (0.2290) time: 0.4499 data: 0.0042 max mem: 22448 +train: [5] [300/400] eta: 0:00:44 lr: 0.000298 loss: 2.6604 (2.6518) grad: 0.2351 (0.2292) time: 0.4434 data: 0.0042 max mem: 22448 +train: [5] [320/400] eta: 0:00:35 lr: 0.000298 loss: 2.6548 (2.6535) grad: 0.2383 (0.2298) time: 0.4465 data: 0.0038 max mem: 22448 +train: [5] [340/400] eta: 0:00:27 lr: 0.000298 loss: 2.6554 (2.6523) grad: 0.2378 (0.2300) time: 0.4576 data: 0.0040 max mem: 22448 +train: [5] [360/400] eta: 0:00:17 lr: 0.000297 loss: 2.6414 (2.6517) grad: 0.2346 (0.2303) time: 0.4419 data: 0.0043 max mem: 22448 +train: [5] [380/400] eta: 0:00:08 lr: 0.000297 loss: 2.6212 (2.6512) grad: 0.2353 (0.2306) time: 0.4459 data: 0.0042 max mem: 22448 +train: [5] [399/400] eta: 0:00:00 lr: 0.000297 loss: 2.5864 (2.6477) grad: 0.2266 (0.2300) time: 0.4321 data: 0.0040 max mem: 22448 +train: [5] Total time: 0:02:59 (0.4489 s / it) +train: [5] Summary: lr: 0.000297 loss: 2.5864 (2.6477) grad: 0.2266 (0.2300) +eval (validation): [5] [ 0/85] eta: 0:04:46 time: 3.3669 data: 3.0636 max mem: 22448 +eval (validation): [5] [20/85] eta: 0:00:31 time: 0.3385 data: 0.0045 max mem: 22448 +eval (validation): [5] [40/85] eta: 0:00:18 time: 0.3414 data: 0.0037 max mem: 22448 +eval (validation): [5] [60/85] eta: 0:00:09 time: 0.3377 data: 0.0042 max mem: 22448 +eval (validation): [5] [80/85] eta: 0:00:01 time: 0.3179 data: 0.0041 max mem: 22448 +eval (validation): [5] [84/85] eta: 0:00:00 time: 0.3096 data: 0.0040 max mem: 22448 +eval (validation): [5] Total time: 0:00:31 (0.3707 s / it) +cv: [5] best hparam: (1, 1.0) (024) ('024_lr1.0e+00_wd1.0e+00') loss: 2.388 acc: 0.284 f1: 0.213 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/eval_v2/nsd_cococlip__patch__attn/checkpoint-best.pth +train: [6] [ 0/400] eta: 0:22:13 lr: nan time: 3.3349 data: 3.0056 max mem: 22448 +train: [6] [ 20/400] eta: 0:03:36 lr: 0.000296 loss: 2.5768 (2.5577) grad: 0.2238 (0.2245) time: 0.4327 data: 0.0041 max mem: 22448 +train: [6] [ 40/400] eta: 0:03:01 lr: 0.000296 loss: 2.5815 (2.5832) grad: 0.2292 (0.2318) time: 0.4336 data: 0.0042 max mem: 22448 +train: [6] [ 60/400] eta: 0:02:43 lr: 0.000296 loss: 2.5666 (2.5767) grad: 0.2336 (0.2328) time: 0.4368 data: 0.0041 max mem: 22448 +train: [6] [ 80/400] eta: 0:02:31 lr: 0.000295 loss: 2.5519 (2.5650) grad: 0.2336 (0.2333) time: 0.4444 data: 0.0041 max mem: 22448 +train: [6] [100/400] eta: 0:02:19 lr: 0.000295 loss: 2.5325 (2.5650) grad: 0.2358 (0.2338) time: 0.4327 data: 0.0040 max mem: 22448 +train: [6] [120/400] eta: 0:02:08 lr: 0.000295 loss: 2.5583 (2.5691) grad: 0.2351 (0.2349) time: 0.4316 data: 0.0042 max mem: 22448 +train: [6] [140/400] eta: 0:01:58 lr: 0.000294 loss: 2.6059 (2.5742) grad: 0.2342 (0.2348) time: 0.4361 data: 0.0040 max mem: 22448 +train: [6] [160/400] eta: 0:01:48 lr: 0.000294 loss: 2.6052 (2.5785) grad: 0.2342 (0.2351) time: 0.4395 data: 0.0043 max mem: 22448 +train: [6] [180/400] eta: 0:01:39 lr: 0.000293 loss: 2.5700 (2.5788) grad: 0.2441 (0.2365) time: 0.4398 data: 0.0041 max mem: 22448 +train: [6] [200/400] eta: 0:01:30 lr: 0.000293 loss: 2.5698 (2.5824) grad: 0.2461 (0.2377) time: 0.4363 data: 0.0040 max mem: 22448 +train: [6] [220/400] eta: 0:01:20 lr: 0.000292 loss: 2.5871 (2.5813) grad: 0.2461 (0.2387) time: 0.4405 data: 0.0040 max mem: 22448 +train: [6] [240/400] eta: 0:01:11 lr: 0.000292 loss: 2.5871 (2.5835) grad: 0.2419 (0.2393) time: 0.4366 data: 0.0040 max mem: 22448 +train: [6] [260/400] eta: 0:01:02 lr: 0.000291 loss: 2.5771 (2.5804) grad: 0.2386 (0.2389) time: 0.4415 data: 0.0040 max mem: 22448 +train: [6] [280/400] eta: 0:00:53 lr: 0.000291 loss: 2.5822 (2.5819) grad: 0.2337 (0.2388) time: 0.4498 data: 0.0044 max mem: 22448 +train: [6] [300/400] eta: 0:00:44 lr: 0.000290 loss: 2.6168 (2.5832) grad: 0.2385 (0.2391) time: 0.4378 data: 0.0041 max mem: 22448 +train: [6] [320/400] eta: 0:00:35 lr: 0.000290 loss: 2.6168 (2.5837) grad: 0.2411 (0.2396) time: 0.4458 data: 0.0042 max mem: 22448 +train: [6] [340/400] eta: 0:00:26 lr: 0.000289 loss: 2.6057 (2.5851) grad: 0.2383 (0.2396) time: 0.4481 data: 0.0042 max mem: 22448 +train: [6] [360/400] eta: 0:00:17 lr: 0.000288 loss: 2.5629 (2.5824) grad: 0.2399 (0.2398) time: 0.4593 data: 0.0042 max mem: 22448 +train: [6] [380/400] eta: 0:00:08 lr: 0.000288 loss: 2.5418 (2.5836) grad: 0.2415 (0.2398) time: 0.4458 data: 0.0043 max mem: 22448 +train: [6] [399/400] eta: 0:00:00 lr: 0.000287 loss: 2.5854 (2.5837) grad: 0.2319 (0.2393) time: 0.4349 data: 0.0040 max mem: 22448 +train: [6] Total time: 0:02:59 (0.4477 s / it) +train: [6] Summary: lr: 0.000287 loss: 2.5854 (2.5837) grad: 0.2319 (0.2393) +eval (validation): [6] [ 0/85] eta: 0:04:34 time: 3.2353 data: 3.0064 max mem: 22448 +eval (validation): [6] [20/85] eta: 0:00:30 time: 0.3358 data: 0.0074 max mem: 22448 +eval (validation): [6] [40/85] eta: 0:00:18 time: 0.3331 data: 0.0043 max mem: 22448 +eval (validation): [6] [60/85] eta: 0:00:09 time: 0.3299 data: 0.0034 max mem: 22448 +eval (validation): [6] [80/85] eta: 0:00:01 time: 0.3242 data: 0.0039 max mem: 22448 +eval (validation): [6] [84/85] eta: 0:00:00 time: 0.3192 data: 0.0039 max mem: 22448 +eval (validation): [6] Total time: 0:00:31 (0.3667 s / it) +cv: [6] best hparam: (0.61, 1.0) (021) ('021_lr6.1e-01_wd1.0e+00') loss: 2.395 acc: 0.285 f1: 0.219 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/eval_v2/nsd_cococlip__patch__attn/checkpoint-best.pth +train: [7] [ 0/400] eta: 0:22:02 lr: nan time: 3.3073 data: 2.9870 max mem: 22448 +train: [7] [ 20/400] eta: 0:03:34 lr: 0.000286 loss: 2.4648 (2.4815) grad: 0.2313 (0.2359) time: 0.4283 data: 0.0044 max mem: 22448 +train: [7] [ 40/400] eta: 0:03:01 lr: 0.000286 loss: 2.4732 (2.4910) grad: 0.2340 (0.2390) time: 0.4417 data: 0.0038 max mem: 22448 +train: [7] [ 60/400] eta: 0:02:42 lr: 0.000285 loss: 2.4916 (2.4829) grad: 0.2398 (0.2421) time: 0.4262 data: 0.0042 max mem: 22448 +train: [7] [ 80/400] eta: 0:02:29 lr: 0.000284 loss: 2.5023 (2.4956) grad: 0.2401 (0.2401) time: 0.4327 data: 0.0042 max mem: 22448 +train: [7] [100/400] eta: 0:02:18 lr: 0.000284 loss: 2.4729 (2.4875) grad: 0.2354 (0.2397) time: 0.4302 data: 0.0042 max mem: 22448 +train: [7] [120/400] eta: 0:02:07 lr: 0.000283 loss: 2.4729 (2.4928) grad: 0.2429 (0.2412) time: 0.4335 data: 0.0042 max mem: 22448 +train: [7] [140/400] eta: 0:01:57 lr: 0.000282 loss: 2.5198 (2.4973) grad: 0.2425 (0.2411) time: 0.4406 data: 0.0043 max mem: 22448 +train: [7] [160/400] eta: 0:01:48 lr: 0.000282 loss: 2.5229 (2.4988) grad: 0.2389 (0.2415) time: 0.4324 data: 0.0039 max mem: 22448 +train: [7] [180/400] eta: 0:01:38 lr: 0.000281 loss: 2.5386 (2.5056) grad: 0.2475 (0.2430) time: 0.4350 data: 0.0040 max mem: 22448 +train: [7] [200/400] eta: 0:01:29 lr: 0.000280 loss: 2.5480 (2.5068) grad: 0.2498 (0.2436) time: 0.4318 data: 0.0041 max mem: 22448 +train: [7] [220/400] eta: 0:01:20 lr: 0.000279 loss: 2.5118 (2.5052) grad: 0.2468 (0.2442) time: 0.4309 data: 0.0040 max mem: 22448 +train: [7] [240/400] eta: 0:01:11 lr: 0.000278 loss: 2.5118 (2.5082) grad: 0.2506 (0.2449) time: 0.4654 data: 0.0043 max mem: 22448 +train: [7] [260/400] eta: 0:01:02 lr: 0.000278 loss: 2.5018 (2.5072) grad: 0.2448 (0.2445) time: 0.4374 data: 0.0043 max mem: 22448 +train: [7] [280/400] eta: 0:00:53 lr: 0.000277 loss: 2.4759 (2.5052) grad: 0.2427 (0.2446) time: 0.4574 data: 0.0044 max mem: 22448 +train: [7] [300/400] eta: 0:00:44 lr: 0.000276 loss: 2.4525 (2.5039) grad: 0.2432 (0.2448) time: 0.4509 data: 0.0043 max mem: 22448 +train: [7] [320/400] eta: 0:00:35 lr: 0.000275 loss: 2.4948 (2.5043) grad: 0.2449 (0.2448) time: 0.4651 data: 0.0042 max mem: 22448 +train: [7] [340/400] eta: 0:00:26 lr: 0.000274 loss: 2.4825 (2.5025) grad: 0.2431 (0.2448) time: 0.4455 data: 0.0041 max mem: 22448 +train: [7] [360/400] eta: 0:00:17 lr: 0.000273 loss: 2.4954 (2.5036) grad: 0.2435 (0.2451) time: 0.4418 data: 0.0042 max mem: 22448 +train: [7] [380/400] eta: 0:00:08 lr: 0.000272 loss: 2.5264 (2.5035) grad: 0.2472 (0.2457) time: 0.4373 data: 0.0043 max mem: 22448 +train: [7] [399/400] eta: 0:00:00 lr: 0.000271 loss: 2.5264 (2.5051) grad: 0.2472 (0.2458) time: 0.4357 data: 0.0041 max mem: 22448 +train: [7] Total time: 0:02:59 (0.4475 s / it) +train: [7] Summary: lr: 0.000271 loss: 2.5264 (2.5051) grad: 0.2472 (0.2458) +eval (validation): [7] [ 0/85] eta: 0:04:31 time: 3.1898 data: 2.9603 max mem: 22448 +eval (validation): [7] [20/85] eta: 0:00:31 time: 0.3468 data: 0.0048 max mem: 22448 +eval (validation): [7] [40/85] eta: 0:00:18 time: 0.3315 data: 0.0036 max mem: 22448 +eval (validation): [7] [60/85] eta: 0:00:09 time: 0.3408 data: 0.0041 max mem: 22448 +eval (validation): [7] [80/85] eta: 0:00:01 time: 0.3374 data: 0.0041 max mem: 22448 +eval (validation): [7] [84/85] eta: 0:00:00 time: 0.3308 data: 0.0040 max mem: 22448 +eval (validation): [7] Total time: 0:00:31 (0.3739 s / it) +cv: [7] best hparam: (0.44, 1.0) (019) ('019_lr4.4e-01_wd1.0e+00') loss: 2.406 acc: 0.275 f1: 0.210 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [8] [ 0/400] eta: 0:22:03 lr: nan time: 3.3088 data: 2.9786 max mem: 22448 +train: [8] [ 20/400] eta: 0:03:38 lr: 0.000270 loss: 2.3533 (2.3772) grad: 0.2271 (0.2310) time: 0.4379 data: 0.0040 max mem: 22448 +train: [8] [ 40/400] eta: 0:03:02 lr: 0.000270 loss: 2.3855 (2.4001) grad: 0.2350 (0.2385) time: 0.4355 data: 0.0037 max mem: 22448 +train: [8] [ 60/400] eta: 0:02:44 lr: 0.000269 loss: 2.4361 (2.4161) grad: 0.2424 (0.2395) time: 0.4384 data: 0.0043 max mem: 22448 +train: [8] [ 80/400] eta: 0:02:31 lr: 0.000268 loss: 2.4784 (2.4330) grad: 0.2451 (0.2432) time: 0.4374 data: 0.0041 max mem: 22448 +train: [8] [100/400] eta: 0:02:19 lr: 0.000267 loss: 2.4715 (2.4293) grad: 0.2555 (0.2466) time: 0.4322 data: 0.0041 max mem: 22448 +train: [8] [120/400] eta: 0:02:08 lr: 0.000266 loss: 2.4558 (2.4310) grad: 0.2636 (0.2505) time: 0.4379 data: 0.0041 max mem: 22448 +train: [8] [140/400] eta: 0:01:58 lr: 0.000265 loss: 2.4360 (2.4368) grad: 0.2657 (0.2526) time: 0.4373 data: 0.0041 max mem: 22448 +train: [8] [160/400] eta: 0:01:49 lr: 0.000264 loss: 2.4448 (2.4381) grad: 0.2664 (0.2550) time: 0.4416 data: 0.0040 max mem: 22448 +train: [8] [180/400] eta: 0:01:39 lr: 0.000263 loss: 2.4269 (2.4351) grad: 0.2596 (0.2552) time: 0.4394 data: 0.0041 max mem: 22448 +train: [8] [200/400] eta: 0:01:30 lr: 0.000262 loss: 2.4269 (2.4398) grad: 0.2558 (0.2556) time: 0.4286 data: 0.0041 max mem: 22448 +train: [8] [220/400] eta: 0:01:20 lr: 0.000260 loss: 2.4592 (2.4405) grad: 0.2557 (0.2550) time: 0.4275 data: 0.0042 max mem: 22448 +train: [8] [240/400] eta: 0:01:11 lr: 0.000259 loss: 2.4332 (2.4394) grad: 0.2464 (0.2545) time: 0.4495 data: 0.0042 max mem: 22448 +train: [8] [260/400] eta: 0:01:02 lr: 0.000258 loss: 2.4542 (2.4412) grad: 0.2458 (0.2546) time: 0.4373 data: 0.0042 max mem: 22448 +train: [8] [280/400] eta: 0:00:53 lr: 0.000257 loss: 2.4642 (2.4404) grad: 0.2457 (0.2547) time: 0.4545 data: 0.0043 max mem: 22448 +train: [8] [300/400] eta: 0:00:44 lr: 0.000256 loss: 2.4131 (2.4398) grad: 0.2515 (0.2548) time: 0.4321 data: 0.0042 max mem: 22448 +train: [8] [320/400] eta: 0:00:35 lr: 0.000255 loss: 2.4131 (2.4390) grad: 0.2448 (0.2539) time: 0.4444 data: 0.0041 max mem: 22448 +train: [8] [340/400] eta: 0:00:26 lr: 0.000254 loss: 2.4276 (2.4380) grad: 0.2440 (0.2543) time: 0.4470 data: 0.0041 max mem: 22448 +train: [8] [360/400] eta: 0:00:17 lr: 0.000253 loss: 2.4276 (2.4377) grad: 0.2489 (0.2540) time: 0.4554 data: 0.0042 max mem: 22448 +train: [8] [380/400] eta: 0:00:08 lr: 0.000252 loss: 2.4574 (2.4389) grad: 0.2486 (0.2538) time: 0.4441 data: 0.0041 max mem: 22448 +train: [8] [399/400] eta: 0:00:00 lr: 0.000250 loss: 2.4574 (2.4398) grad: 0.2497 (0.2543) time: 0.4511 data: 0.0042 max mem: 22448 +train: [8] Total time: 0:02:59 (0.4479 s / it) +train: [8] Summary: lr: 0.000250 loss: 2.4574 (2.4398) grad: 0.2497 (0.2543) +eval (validation): [8] [ 0/85] eta: 0:04:38 time: 3.2709 data: 2.9835 max mem: 22448 +eval (validation): [8] [20/85] eta: 0:00:31 time: 0.3510 data: 0.0046 max mem: 22448 +eval (validation): [8] [40/85] eta: 0:00:18 time: 0.3316 data: 0.0039 max mem: 22448 +eval (validation): [8] [60/85] eta: 0:00:09 time: 0.3447 data: 0.0045 max mem: 22448 +eval (validation): [8] [80/85] eta: 0:00:01 time: 0.3240 data: 0.0041 max mem: 22448 +eval (validation): [8] [84/85] eta: 0:00:00 time: 0.3157 data: 0.0039 max mem: 22448 +eval (validation): [8] Total time: 0:00:31 (0.3734 s / it) +cv: [8] best hparam: (0.44, 1.0) (019) ('019_lr4.4e-01_wd1.0e+00') loss: 2.433 acc: 0.269 f1: 0.209 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [9] [ 0/400] eta: 0:22:12 lr: nan time: 3.3311 data: 3.0045 max mem: 22448 +train: [9] [ 20/400] eta: 0:03:36 lr: 0.000249 loss: 2.3534 (2.3829) grad: 0.2496 (0.2580) time: 0.4327 data: 0.0039 max mem: 22448 +train: [9] [ 40/400] eta: 0:03:00 lr: 0.000248 loss: 2.3810 (2.3907) grad: 0.2496 (0.2517) time: 0.4285 data: 0.0039 max mem: 22448 +train: [9] [ 60/400] eta: 0:02:43 lr: 0.000247 loss: 2.3920 (2.3965) grad: 0.2435 (0.2500) time: 0.4359 data: 0.0041 max mem: 22448 +train: [9] [ 80/400] eta: 0:02:30 lr: 0.000246 loss: 2.3920 (2.4041) grad: 0.2496 (0.2521) time: 0.4366 data: 0.0043 max mem: 22448 +train: [9] [100/400] eta: 0:02:18 lr: 0.000244 loss: 2.3836 (2.4025) grad: 0.2581 (0.2536) time: 0.4326 data: 0.0041 max mem: 22448 +train: [9] [120/400] eta: 0:02:08 lr: 0.000243 loss: 2.3720 (2.3979) grad: 0.2532 (0.2537) time: 0.4457 data: 0.0043 max mem: 22448 +train: [9] [140/400] eta: 0:01:58 lr: 0.000242 loss: 2.3706 (2.3997) grad: 0.2572 (0.2545) time: 0.4383 data: 0.0041 max mem: 22448 +train: [9] [160/400] eta: 0:01:49 lr: 0.000241 loss: 2.3845 (2.3969) grad: 0.2578 (0.2552) time: 0.4437 data: 0.0043 max mem: 22448 +train: [9] [180/400] eta: 0:01:39 lr: 0.000240 loss: 2.3857 (2.4005) grad: 0.2569 (0.2561) time: 0.4329 data: 0.0041 max mem: 22448 +train: [9] [200/400] eta: 0:01:30 lr: 0.000238 loss: 2.3829 (2.3963) grad: 0.2612 (0.2570) time: 0.4497 data: 0.0039 max mem: 22448 +train: [9] [220/400] eta: 0:01:21 lr: 0.000237 loss: 2.3485 (2.3923) grad: 0.2627 (0.2577) time: 0.4322 data: 0.0041 max mem: 22448 +train: [9] [240/400] eta: 0:01:11 lr: 0.000236 loss: 2.3962 (2.3971) grad: 0.2597 (0.2574) time: 0.4465 data: 0.0041 max mem: 22448 +train: [9] [260/400] eta: 0:01:02 lr: 0.000234 loss: 2.4102 (2.3950) grad: 0.2519 (0.2566) time: 0.4416 data: 0.0044 max mem: 22448 +train: [9] [280/400] eta: 0:00:53 lr: 0.000233 loss: 2.3463 (2.3936) grad: 0.2530 (0.2569) time: 0.4490 data: 0.0042 max mem: 22448 +train: [9] [300/400] eta: 0:00:44 lr: 0.000232 loss: 2.3814 (2.3939) grad: 0.2583 (0.2574) time: 0.4373 data: 0.0041 max mem: 22448 +train: [9] [320/400] eta: 0:00:35 lr: 0.000230 loss: 2.3814 (2.3940) grad: 0.2568 (0.2574) time: 0.4533 data: 0.0042 max mem: 22448 +train: [9] [340/400] eta: 0:00:26 lr: 0.000229 loss: 2.3169 (2.3911) grad: 0.2575 (0.2576) time: 0.4614 data: 0.0043 max mem: 22448 +train: [9] [360/400] eta: 0:00:17 lr: 0.000228 loss: 2.3875 (2.3921) grad: 0.2684 (0.2584) time: 0.4517 data: 0.0042 max mem: 22448 +train: [9] [380/400] eta: 0:00:08 lr: 0.000226 loss: 2.3709 (2.3913) grad: 0.2675 (0.2586) time: 0.4311 data: 0.0042 max mem: 22448 +train: [9] [399/400] eta: 0:00:00 lr: 0.000225 loss: 2.3940 (2.3922) grad: 0.2666 (0.2592) time: 0.4537 data: 0.0042 max mem: 22448 +train: [9] Total time: 0:02:59 (0.4493 s / it) +train: [9] Summary: lr: 0.000225 loss: 2.3940 (2.3922) grad: 0.2666 (0.2592) +eval (validation): [9] [ 0/85] eta: 0:04:31 time: 3.1947 data: 2.9719 max mem: 22448 +eval (validation): [9] [20/85] eta: 0:00:31 time: 0.3517 data: 0.0048 max mem: 22448 +eval (validation): [9] [40/85] eta: 0:00:18 time: 0.3299 data: 0.0040 max mem: 22448 +eval (validation): [9] [60/85] eta: 0:00:09 time: 0.3405 data: 0.0044 max mem: 22448 +eval (validation): [9] [80/85] eta: 0:00:01 time: 0.3161 data: 0.0039 max mem: 22448 +eval (validation): [9] [84/85] eta: 0:00:00 time: 0.3099 data: 0.0039 max mem: 22448 +eval (validation): [9] Total time: 0:00:31 (0.3696 s / it) +cv: [9] best hparam: (0.38, 1.0) (018) ('018_lr3.8e-01_wd1.0e+00') loss: 2.400 acc: 0.276 f1: 0.208 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [10] [ 0/400] eta: 0:21:47 lr: nan time: 3.2677 data: 2.9425 max mem: 22448 +train: [10] [ 20/400] eta: 0:03:37 lr: 0.000224 loss: 2.2903 (2.3102) grad: 0.2581 (0.2620) time: 0.4384 data: 0.0051 max mem: 22448 +train: [10] [ 40/400] eta: 0:03:02 lr: 0.000222 loss: 2.2985 (2.3115) grad: 0.2562 (0.2582) time: 0.4376 data: 0.0040 max mem: 22448 +train: [10] [ 60/400] eta: 0:02:45 lr: 0.000221 loss: 2.3037 (2.3293) grad: 0.2537 (0.2547) time: 0.4441 data: 0.0042 max mem: 22448 +train: [10] [ 80/400] eta: 0:02:31 lr: 0.000220 loss: 2.2961 (2.3184) grad: 0.2450 (0.2529) time: 0.4321 data: 0.0042 max mem: 22448 +train: [10] [100/400] eta: 0:02:19 lr: 0.000218 loss: 2.3024 (2.3111) grad: 0.2513 (0.2537) time: 0.4305 data: 0.0043 max mem: 22448 +train: [10] [120/400] eta: 0:02:08 lr: 0.000217 loss: 2.3118 (2.3153) grad: 0.2528 (0.2544) time: 0.4360 data: 0.0043 max mem: 22448 +train: [10] [140/400] eta: 0:01:59 lr: 0.000215 loss: 2.3147 (2.3190) grad: 0.2524 (0.2550) time: 0.4453 data: 0.0042 max mem: 22448 +train: [10] [160/400] eta: 0:01:49 lr: 0.000214 loss: 2.3147 (2.3204) grad: 0.2524 (0.2552) time: 0.4389 data: 0.0041 max mem: 22448 +train: [10] [180/400] eta: 0:01:39 lr: 0.000213 loss: 2.3596 (2.3236) grad: 0.2548 (0.2559) time: 0.4357 data: 0.0040 max mem: 22448 +train: [10] [200/400] eta: 0:01:30 lr: 0.000211 loss: 2.3795 (2.3252) grad: 0.2552 (0.2562) time: 0.4481 data: 0.0041 max mem: 22448 +train: [10] [220/400] eta: 0:01:21 lr: 0.000210 loss: 2.3306 (2.3264) grad: 0.2552 (0.2564) time: 0.4481 data: 0.0042 max mem: 22448 +train: [10] [240/400] eta: 0:01:12 lr: 0.000208 loss: 2.3191 (2.3263) grad: 0.2565 (0.2565) time: 0.4521 data: 0.0040 max mem: 22448 +train: [10] [260/400] eta: 0:01:03 lr: 0.000207 loss: 2.3223 (2.3252) grad: 0.2536 (0.2565) time: 0.4522 data: 0.0041 max mem: 22448 +train: [10] [280/400] eta: 0:00:54 lr: 0.000205 loss: 2.3408 (2.3264) grad: 0.2572 (0.2569) time: 0.4554 data: 0.0042 max mem: 22448 +train: [10] [300/400] eta: 0:00:45 lr: 0.000204 loss: 2.2800 (2.3234) grad: 0.2601 (0.2568) time: 0.4343 data: 0.0039 max mem: 22448 +train: [10] [320/400] eta: 0:00:36 lr: 0.000202 loss: 2.2800 (2.3219) grad: 0.2601 (0.2573) time: 0.4448 data: 0.0039 max mem: 22448 +train: [10] [340/400] eta: 0:00:27 lr: 0.000201 loss: 2.3098 (2.3223) grad: 0.2616 (0.2576) time: 0.4491 data: 0.0041 max mem: 22448 +train: [10] [360/400] eta: 0:00:18 lr: 0.000199 loss: 2.3098 (2.3216) grad: 0.2553 (0.2576) time: 0.4477 data: 0.0041 max mem: 22448 +train: [10] [380/400] eta: 0:00:08 lr: 0.000198 loss: 2.3045 (2.3204) grad: 0.2577 (0.2577) time: 0.4265 data: 0.0039 max mem: 22448 +train: [10] [399/400] eta: 0:00:00 lr: 0.000196 loss: 2.3221 (2.3217) grad: 0.2634 (0.2581) time: 0.4328 data: 0.0041 max mem: 22448 +train: [10] Total time: 0:02:59 (0.4489 s / it) +train: [10] Summary: lr: 0.000196 loss: 2.3221 (2.3217) grad: 0.2634 (0.2581) +eval (validation): [10] [ 0/85] eta: 0:04:41 time: 3.3089 data: 3.0652 max mem: 22448 +eval (validation): [10] [20/85] eta: 0:00:30 time: 0.3312 data: 0.0045 max mem: 22448 +eval (validation): [10] [40/85] eta: 0:00:18 time: 0.3398 data: 0.0034 max mem: 22448 +eval (validation): [10] [60/85] eta: 0:00:09 time: 0.3422 data: 0.0044 max mem: 22448 +eval (validation): [10] [80/85] eta: 0:00:01 time: 0.3225 data: 0.0039 max mem: 22448 +eval (validation): [10] [84/85] eta: 0:00:00 time: 0.3166 data: 0.0039 max mem: 22448 +eval (validation): [10] Total time: 0:00:31 (0.3705 s / it) +cv: [10] best hparam: (0.32, 1.0) (017) ('017_lr3.2e-01_wd1.0e+00') loss: 2.417 acc: 0.274 f1: 0.204 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [11] [ 0/400] eta: 0:22:01 lr: nan time: 3.3048 data: 2.9716 max mem: 22448 +train: [11] [ 20/400] eta: 0:03:36 lr: 0.000195 loss: 2.2320 (2.2379) grad: 0.2407 (0.2495) time: 0.4334 data: 0.0034 max mem: 22448 +train: [11] [ 40/400] eta: 0:03:01 lr: 0.000193 loss: 2.2819 (2.2644) grad: 0.2497 (0.2521) time: 0.4333 data: 0.0040 max mem: 22448 +train: [11] [ 60/400] eta: 0:02:43 lr: 0.000192 loss: 2.2510 (2.2553) grad: 0.2550 (0.2556) time: 0.4345 data: 0.0041 max mem: 22448 +train: [11] [ 80/400] eta: 0:02:29 lr: 0.000190 loss: 2.2533 (2.2667) grad: 0.2599 (0.2572) time: 0.4312 data: 0.0040 max mem: 22448 +train: [11] [100/400] eta: 0:02:18 lr: 0.000189 loss: 2.2575 (2.2644) grad: 0.2554 (0.2573) time: 0.4355 data: 0.0039 max mem: 22448 +train: [11] [120/400] eta: 0:02:07 lr: 0.000187 loss: 2.2210 (2.2489) grad: 0.2566 (0.2576) time: 0.4315 data: 0.0041 max mem: 22448 +train: [11] [140/400] eta: 0:01:58 lr: 0.000186 loss: 2.2210 (2.2475) grad: 0.2562 (0.2575) time: 0.4405 data: 0.0040 max mem: 22448 +train: [11] [160/400] eta: 0:01:48 lr: 0.000184 loss: 2.2638 (2.2531) grad: 0.2616 (0.2585) time: 0.4390 data: 0.0041 max mem: 22448 +train: [11] [180/400] eta: 0:01:39 lr: 0.000183 loss: 2.2638 (2.2545) grad: 0.2658 (0.2604) time: 0.4477 data: 0.0041 max mem: 22448 +train: [11] [200/400] eta: 0:01:29 lr: 0.000181 loss: 2.2719 (2.2572) grad: 0.2667 (0.2606) time: 0.4296 data: 0.0041 max mem: 22448 +train: [11] [220/400] eta: 0:01:20 lr: 0.000180 loss: 2.3183 (2.2642) grad: 0.2535 (0.2608) time: 0.4331 data: 0.0040 max mem: 22448 +train: [11] [240/400] eta: 0:01:11 lr: 0.000178 loss: 2.3183 (2.2670) grad: 0.2561 (0.2611) time: 0.4469 data: 0.0039 max mem: 22448 +train: [11] [260/400] eta: 0:01:02 lr: 0.000177 loss: 2.2855 (2.2658) grad: 0.2631 (0.2618) time: 0.4479 data: 0.0042 max mem: 22448 +train: [11] [280/400] eta: 0:00:53 lr: 0.000175 loss: 2.2759 (2.2669) grad: 0.2677 (0.2620) time: 0.4604 data: 0.0042 max mem: 22448 +train: [11] [300/400] eta: 0:00:44 lr: 0.000174 loss: 2.2996 (2.2716) grad: 0.2603 (0.2623) time: 0.4459 data: 0.0041 max mem: 22448 +train: [11] [320/400] eta: 0:00:35 lr: 0.000172 loss: 2.2996 (2.2740) grad: 0.2671 (0.2629) time: 0.4507 data: 0.0040 max mem: 22448 +train: [11] [340/400] eta: 0:00:26 lr: 0.000170 loss: 2.2801 (2.2750) grad: 0.2671 (0.2637) time: 0.4609 data: 0.0041 max mem: 22448 +train: [11] [360/400] eta: 0:00:17 lr: 0.000169 loss: 2.2850 (2.2751) grad: 0.2592 (0.2638) time: 0.4415 data: 0.0042 max mem: 22448 +train: [11] [380/400] eta: 0:00:08 lr: 0.000167 loss: 2.2541 (2.2718) grad: 0.2569 (0.2634) time: 0.4376 data: 0.0041 max mem: 22448 +train: [11] [399/400] eta: 0:00:00 lr: 0.000166 loss: 2.2541 (2.2748) grad: 0.2572 (0.2632) time: 0.4308 data: 0.0041 max mem: 22448 +train: [11] Total time: 0:02:59 (0.4481 s / it) +train: [11] Summary: lr: 0.000166 loss: 2.2541 (2.2748) grad: 0.2572 (0.2632) +eval (validation): [11] [ 0/85] eta: 0:04:39 time: 3.2892 data: 3.0431 max mem: 22448 +eval (validation): [11] [20/85] eta: 0:00:31 time: 0.3381 data: 0.0049 max mem: 22448 +eval (validation): [11] [40/85] eta: 0:00:18 time: 0.3330 data: 0.0034 max mem: 22448 +eval (validation): [11] [60/85] eta: 0:00:09 time: 0.3326 data: 0.0041 max mem: 22448 +eval (validation): [11] [80/85] eta: 0:00:01 time: 0.3212 data: 0.0040 max mem: 22448 +eval (validation): [11] [84/85] eta: 0:00:00 time: 0.3176 data: 0.0039 max mem: 22448 +eval (validation): [11] Total time: 0:00:31 (0.3678 s / it) +cv: [11] best hparam: (0.38, 1.0) (018) ('018_lr3.8e-01_wd1.0e+00') loss: 2.418 acc: 0.277 f1: 0.212 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [12] [ 0/400] eta: 0:22:11 lr: nan time: 3.3291 data: 2.9479 max mem: 22448 +train: [12] [ 20/400] eta: 0:03:39 lr: 0.000164 loss: 2.1567 (2.1761) grad: 0.2497 (0.2536) time: 0.4393 data: 0.0045 max mem: 22448 +train: [12] [ 40/400] eta: 0:03:03 lr: 0.000163 loss: 2.1710 (2.1805) grad: 0.2522 (0.2536) time: 0.4386 data: 0.0042 max mem: 22448 +train: [12] [ 60/400] eta: 0:02:44 lr: 0.000161 loss: 2.1710 (2.1884) grad: 0.2517 (0.2521) time: 0.4328 data: 0.0042 max mem: 22448 +train: [12] [ 80/400] eta: 0:02:30 lr: 0.000160 loss: 2.1860 (2.1916) grad: 0.2521 (0.2527) time: 0.4334 data: 0.0042 max mem: 22448 +train: [12] [100/400] eta: 0:02:19 lr: 0.000158 loss: 2.1993 (2.1958) grad: 0.2564 (0.2538) time: 0.4395 data: 0.0040 max mem: 22448 +train: [12] [120/400] eta: 0:02:08 lr: 0.000156 loss: 2.1900 (2.1980) grad: 0.2525 (0.2528) time: 0.4261 data: 0.0042 max mem: 22448 +train: [12] [140/400] eta: 0:01:58 lr: 0.000155 loss: 2.1792 (2.1958) grad: 0.2525 (0.2547) time: 0.4319 data: 0.0041 max mem: 22448 +train: [12] [160/400] eta: 0:01:48 lr: 0.000153 loss: 2.2091 (2.1987) grad: 0.2713 (0.2567) time: 0.4362 data: 0.0041 max mem: 22448 +train: [12] [180/400] eta: 0:01:39 lr: 0.000152 loss: 2.2162 (2.2019) grad: 0.2694 (0.2575) time: 0.4393 data: 0.0041 max mem: 22448 +train: [12] [200/400] eta: 0:01:29 lr: 0.000150 loss: 2.2186 (2.2088) grad: 0.2600 (0.2581) time: 0.4344 data: 0.0041 max mem: 22448 +train: [12] [220/400] eta: 0:01:20 lr: 0.000149 loss: 2.2376 (2.2113) grad: 0.2574 (0.2584) time: 0.4265 data: 0.0041 max mem: 22448 +train: [12] [240/400] eta: 0:01:11 lr: 0.000147 loss: 2.1864 (2.2087) grad: 0.2586 (0.2596) time: 0.4453 data: 0.0041 max mem: 22448 +train: [12] [260/400] eta: 0:01:02 lr: 0.000145 loss: 2.1735 (2.2084) grad: 0.2606 (0.2597) time: 0.4444 data: 0.0042 max mem: 22448 +train: [12] [280/400] eta: 0:00:53 lr: 0.000144 loss: 2.1797 (2.2051) grad: 0.2610 (0.2599) time: 0.4408 data: 0.0043 max mem: 22448 +train: [12] [300/400] eta: 0:00:44 lr: 0.000142 loss: 2.1853 (2.2067) grad: 0.2648 (0.2607) time: 0.4463 data: 0.0041 max mem: 22448 +train: [12] [320/400] eta: 0:00:35 lr: 0.000141 loss: 2.1869 (2.2082) grad: 0.2648 (0.2610) time: 0.4408 data: 0.0040 max mem: 22448 +train: [12] [340/400] eta: 0:00:26 lr: 0.000139 loss: 2.1855 (2.2070) grad: 0.2663 (0.2610) time: 0.4548 data: 0.0042 max mem: 22448 +train: [12] [360/400] eta: 0:00:17 lr: 0.000138 loss: 2.1882 (2.2068) grad: 0.2616 (0.2611) time: 0.4492 data: 0.0042 max mem: 22448 +train: [12] [380/400] eta: 0:00:08 lr: 0.000136 loss: 2.2053 (2.2073) grad: 0.2616 (0.2613) time: 0.4313 data: 0.0043 max mem: 22448 +train: [12] [399/400] eta: 0:00:00 lr: 0.000134 loss: 2.2059 (2.2070) grad: 0.2653 (0.2616) time: 0.4874 data: 0.0642 max mem: 22448 +train: [12] Total time: 0:02:59 (0.4489 s / it) +train: [12] Summary: lr: 0.000134 loss: 2.2059 (2.2070) grad: 0.2653 (0.2616) +eval (validation): [12] [ 0/85] eta: 0:04:40 time: 3.2992 data: 3.0564 max mem: 22448 +eval (validation): [12] [20/85] eta: 0:00:31 time: 0.3379 data: 0.0054 max mem: 22448 +eval (validation): [12] [40/85] eta: 0:00:18 time: 0.3325 data: 0.0035 max mem: 22448 +eval (validation): [12] [60/85] eta: 0:00:09 time: 0.3416 data: 0.0038 max mem: 22448 +eval (validation): [12] [80/85] eta: 0:00:01 time: 0.3261 data: 0.0041 max mem: 22448 +eval (validation): [12] [84/85] eta: 0:00:00 time: 0.3206 data: 0.0039 max mem: 22448 +eval (validation): [12] Total time: 0:00:31 (0.3713 s / it) +cv: [12] best hparam: (0.38, 1.0) (018) ('018_lr3.8e-01_wd1.0e+00') loss: 2.437 acc: 0.265 f1: 0.204 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [13] [ 0/400] eta: 0:22:09 lr: nan time: 3.3241 data: 2.9446 max mem: 22448 +train: [13] [ 20/400] eta: 0:03:40 lr: 0.000133 loss: 2.1658 (2.1556) grad: 0.2508 (0.2566) time: 0.4420 data: 0.0046 max mem: 22448 +train: [13] [ 40/400] eta: 0:03:01 lr: 0.000131 loss: 2.1658 (2.1514) grad: 0.2508 (0.2566) time: 0.4261 data: 0.0039 max mem: 22448 +train: [13] [ 60/400] eta: 0:02:44 lr: 0.000130 loss: 2.1670 (2.1573) grad: 0.2575 (0.2569) time: 0.4389 data: 0.0042 max mem: 22448 +train: [13] [ 80/400] eta: 0:02:30 lr: 0.000128 loss: 2.1670 (2.1570) grad: 0.2575 (0.2582) time: 0.4276 data: 0.0042 max mem: 22448 +train: [13] [100/400] eta: 0:02:18 lr: 0.000127 loss: 2.1380 (2.1550) grad: 0.2517 (0.2568) time: 0.4350 data: 0.0043 max mem: 22448 +train: [13] [120/400] eta: 0:02:08 lr: 0.000125 loss: 2.1365 (2.1510) grad: 0.2526 (0.2576) time: 0.4314 data: 0.0043 max mem: 22448 +train: [13] [140/400] eta: 0:01:57 lr: 0.000124 loss: 2.1719 (2.1611) grad: 0.2718 (0.2597) time: 0.4274 data: 0.0041 max mem: 22448 +train: [13] [160/400] eta: 0:01:48 lr: 0.000122 loss: 2.1719 (2.1600) grad: 0.2676 (0.2609) time: 0.4323 data: 0.0039 max mem: 22448 +train: [13] [180/400] eta: 0:01:38 lr: 0.000120 loss: 2.1511 (2.1634) grad: 0.2629 (0.2610) time: 0.4328 data: 0.0041 max mem: 22448 +train: [13] [200/400] eta: 0:01:29 lr: 0.000119 loss: 2.1169 (2.1580) grad: 0.2588 (0.2611) time: 0.4402 data: 0.0041 max mem: 22448 +train: [13] [220/400] eta: 0:01:20 lr: 0.000117 loss: 2.1169 (2.1593) grad: 0.2611 (0.2616) time: 0.4388 data: 0.0041 max mem: 22448 +train: [13] [240/400] eta: 0:01:11 lr: 0.000116 loss: 2.1756 (2.1602) grad: 0.2652 (0.2618) time: 0.4392 data: 0.0040 max mem: 22448 +train: [13] [260/400] eta: 0:01:02 lr: 0.000114 loss: 2.1756 (2.1627) grad: 0.2538 (0.2612) time: 0.4461 data: 0.0041 max mem: 22448 +train: [13] [280/400] eta: 0:00:53 lr: 0.000113 loss: 2.1431 (2.1600) grad: 0.2486 (0.2606) time: 0.4479 data: 0.0043 max mem: 22448 +train: [13] [300/400] eta: 0:00:44 lr: 0.000111 loss: 2.1255 (2.1588) grad: 0.2446 (0.2596) time: 0.4471 data: 0.0042 max mem: 22448 +train: [13] [320/400] eta: 0:00:35 lr: 0.000110 loss: 2.1405 (2.1601) grad: 0.2568 (0.2600) time: 0.4409 data: 0.0040 max mem: 22448 +train: [13] [340/400] eta: 0:00:26 lr: 0.000108 loss: 2.1471 (2.1596) grad: 0.2631 (0.2596) time: 0.4571 data: 0.0041 max mem: 22448 +train: [13] [360/400] eta: 0:00:17 lr: 0.000107 loss: 2.1331 (2.1599) grad: 0.2635 (0.2603) time: 0.4495 data: 0.0043 max mem: 22448 +train: [13] [380/400] eta: 0:00:08 lr: 0.000105 loss: 2.1436 (2.1593) grad: 0.2696 (0.2607) time: 0.4381 data: 0.0042 max mem: 22448 +train: [13] [399/400] eta: 0:00:00 lr: 0.000104 loss: 2.1541 (2.1601) grad: 0.2640 (0.2608) time: 0.4336 data: 0.0041 max mem: 22448 +train: [13] Total time: 0:02:58 (0.4462 s / it) +train: [13] Summary: lr: 0.000104 loss: 2.1541 (2.1601) grad: 0.2640 (0.2608) +eval (validation): [13] [ 0/85] eta: 0:04:41 time: 3.3114 data: 3.0289 max mem: 22448 +eval (validation): [13] [20/85] eta: 0:00:30 time: 0.3327 data: 0.0039 max mem: 22448 +eval (validation): [13] [40/85] eta: 0:00:18 time: 0.3343 data: 0.0034 max mem: 22448 +eval (validation): [13] [60/85] eta: 0:00:09 time: 0.3381 data: 0.0043 max mem: 22448 +eval (validation): [13] [80/85] eta: 0:00:01 time: 0.3317 data: 0.0040 max mem: 22448 +eval (validation): [13] [84/85] eta: 0:00:00 time: 0.3249 data: 0.0039 max mem: 22448 +eval (validation): [13] Total time: 0:00:31 (0.3708 s / it) +cv: [13] best hparam: (0.32, 1.0) (017) ('017_lr3.2e-01_wd1.0e+00') loss: 2.420 acc: 0.275 f1: 0.211 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [14] [ 0/400] eta: 0:22:11 lr: nan time: 3.3296 data: 3.0080 max mem: 22448 +train: [14] [ 20/400] eta: 0:03:37 lr: 0.000102 loss: 2.0557 (2.0613) grad: 0.2426 (0.2470) time: 0.4354 data: 0.0037 max mem: 22448 +train: [14] [ 40/400] eta: 0:03:02 lr: 0.000101 loss: 2.0755 (2.0816) grad: 0.2456 (0.2516) time: 0.4378 data: 0.0039 max mem: 22448 +train: [14] [ 60/400] eta: 0:02:44 lr: 0.000099 loss: 2.1045 (2.0871) grad: 0.2546 (0.2537) time: 0.4366 data: 0.0041 max mem: 22448 +train: [14] [ 80/400] eta: 0:02:31 lr: 0.000098 loss: 2.0865 (2.0957) grad: 0.2531 (0.2525) time: 0.4409 data: 0.0041 max mem: 22448 +train: [14] [100/400] eta: 0:02:20 lr: 0.000096 loss: 2.0865 (2.0986) grad: 0.2520 (0.2530) time: 0.4427 data: 0.0040 max mem: 22448 +train: [14] [120/400] eta: 0:02:09 lr: 0.000095 loss: 2.0836 (2.0930) grad: 0.2559 (0.2537) time: 0.4308 data: 0.0040 max mem: 22448 +train: [14] [140/400] eta: 0:01:59 lr: 0.000093 loss: 2.0705 (2.0939) grad: 0.2603 (0.2544) time: 0.4413 data: 0.0043 max mem: 22448 +train: [14] [160/400] eta: 0:01:49 lr: 0.000092 loss: 2.0628 (2.0916) grad: 0.2552 (0.2544) time: 0.4323 data: 0.0042 max mem: 22448 +train: [14] [180/400] eta: 0:01:39 lr: 0.000090 loss: 2.0628 (2.0887) grad: 0.2542 (0.2552) time: 0.4259 data: 0.0041 max mem: 22448 +train: [14] [200/400] eta: 0:01:29 lr: 0.000089 loss: 2.0473 (2.0906) grad: 0.2628 (0.2559) time: 0.4316 data: 0.0042 max mem: 22448 +train: [14] [220/400] eta: 0:01:20 lr: 0.000088 loss: 2.0883 (2.0907) grad: 0.2600 (0.2565) time: 0.4376 data: 0.0040 max mem: 22448 +train: [14] [240/400] eta: 0:01:11 lr: 0.000086 loss: 2.0918 (2.0957) grad: 0.2586 (0.2571) time: 0.4363 data: 0.0040 max mem: 22448 +train: [14] [260/400] eta: 0:01:02 lr: 0.000085 loss: 2.1288 (2.0982) grad: 0.2619 (0.2572) time: 0.4540 data: 0.0041 max mem: 22448 +train: [14] [280/400] eta: 0:00:53 lr: 0.000083 loss: 2.1249 (2.0993) grad: 0.2538 (0.2567) time: 0.4557 data: 0.0043 max mem: 22448 +train: [14] [300/400] eta: 0:00:44 lr: 0.000082 loss: 2.1293 (2.1045) grad: 0.2570 (0.2572) time: 0.4378 data: 0.0039 max mem: 22448 +train: [14] [320/400] eta: 0:00:35 lr: 0.000081 loss: 2.1492 (2.1066) grad: 0.2616 (0.2578) time: 0.4343 data: 0.0040 max mem: 22448 +train: [14] [340/400] eta: 0:00:26 lr: 0.000079 loss: 2.1395 (2.1068) grad: 0.2626 (0.2581) time: 0.4639 data: 0.0043 max mem: 22448 +train: [14] [360/400] eta: 0:00:17 lr: 0.000078 loss: 2.1008 (2.1069) grad: 0.2571 (0.2578) time: 0.4476 data: 0.0042 max mem: 22448 +train: [14] [380/400] eta: 0:00:09 lr: 0.000076 loss: 2.0813 (2.1054) grad: 0.2535 (0.2578) time: 0.4927 data: 0.0495 max mem: 22448 +train: [14] [399/400] eta: 0:00:00 lr: 0.000075 loss: 2.0756 (2.1057) grad: 0.2600 (0.2581) time: 0.4370 data: 0.0038 max mem: 22448 +train: [14] Total time: 0:03:00 (0.4501 s / it) +train: [14] Summary: lr: 0.000075 loss: 2.0756 (2.1057) grad: 0.2600 (0.2581) +eval (validation): [14] [ 0/85] eta: 0:04:40 time: 3.3055 data: 3.0282 max mem: 22448 +eval (validation): [14] [20/85] eta: 0:00:32 time: 0.3554 data: 0.0043 max mem: 22448 +eval (validation): [14] [40/85] eta: 0:00:18 time: 0.3323 data: 0.0039 max mem: 22448 +eval (validation): [14] [60/85] eta: 0:00:09 time: 0.3500 data: 0.0041 max mem: 22448 +eval (validation): [14] [80/85] eta: 0:00:01 time: 0.3221 data: 0.0040 max mem: 22448 +eval (validation): [14] [84/85] eta: 0:00:00 time: 0.3142 data: 0.0039 max mem: 22448 +eval (validation): [14] Total time: 0:00:31 (0.3756 s / it) +cv: [14] best hparam: (0.32, 1.0) (017) ('017_lr3.2e-01_wd1.0e+00') loss: 2.415 acc: 0.276 f1: 0.210 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [15] [ 0/400] eta: 0:21:51 lr: nan time: 3.2786 data: 2.9092 max mem: 22448 +train: [15] [ 20/400] eta: 0:03:36 lr: 0.000074 loss: 2.0488 (2.0598) grad: 0.2461 (0.2480) time: 0.4345 data: 0.0052 max mem: 22448 +train: [15] [ 40/400] eta: 0:03:02 lr: 0.000072 loss: 2.0675 (2.0595) grad: 0.2436 (0.2477) time: 0.4382 data: 0.0036 max mem: 22448 +train: [15] [ 60/400] eta: 0:02:44 lr: 0.000071 loss: 2.0534 (2.0532) grad: 0.2449 (0.2488) time: 0.4405 data: 0.0041 max mem: 22448 +train: [15] [ 80/400] eta: 0:02:30 lr: 0.000070 loss: 2.0104 (2.0441) grad: 0.2454 (0.2475) time: 0.4283 data: 0.0042 max mem: 22448 +train: [15] [100/400] eta: 0:02:19 lr: 0.000068 loss: 2.0151 (2.0370) grad: 0.2435 (0.2485) time: 0.4347 data: 0.0042 max mem: 22448 +train: [15] [120/400] eta: 0:02:08 lr: 0.000067 loss: 2.0439 (2.0462) grad: 0.2574 (0.2509) time: 0.4342 data: 0.0040 max mem: 22448 +train: [15] [140/400] eta: 0:01:58 lr: 0.000066 loss: 2.0758 (2.0515) grad: 0.2619 (0.2534) time: 0.4390 data: 0.0042 max mem: 22448 +train: [15] [160/400] eta: 0:01:48 lr: 0.000064 loss: 2.0448 (2.0511) grad: 0.2529 (0.2535) time: 0.4355 data: 0.0042 max mem: 22448 +train: [15] [180/400] eta: 0:01:39 lr: 0.000063 loss: 2.0834 (2.0597) grad: 0.2549 (0.2544) time: 0.4454 data: 0.0040 max mem: 22448 +train: [15] [200/400] eta: 0:01:30 lr: 0.000062 loss: 2.0834 (2.0581) grad: 0.2546 (0.2538) time: 0.4405 data: 0.0041 max mem: 22448 +train: [15] [220/400] eta: 0:01:20 lr: 0.000061 loss: 2.0492 (2.0568) grad: 0.2459 (0.2538) time: 0.4372 data: 0.0041 max mem: 22448 +train: [15] [240/400] eta: 0:01:11 lr: 0.000059 loss: 2.0492 (2.0558) grad: 0.2542 (0.2542) time: 0.4423 data: 0.0041 max mem: 22448 +train: [15] [260/400] eta: 0:01:03 lr: 0.000058 loss: 2.1010 (2.0614) grad: 0.2557 (0.2542) time: 0.4592 data: 0.0041 max mem: 22448 +train: [15] [280/400] eta: 0:00:54 lr: 0.000057 loss: 2.1010 (2.0602) grad: 0.2460 (0.2537) time: 0.4577 data: 0.0042 max mem: 22448 +train: [15] [300/400] eta: 0:00:45 lr: 0.000056 loss: 2.0365 (2.0589) grad: 0.2460 (0.2535) time: 0.4467 data: 0.0040 max mem: 22448 +train: [15] [320/400] eta: 0:00:35 lr: 0.000054 loss: 2.0556 (2.0593) grad: 0.2553 (0.2536) time: 0.4443 data: 0.0038 max mem: 22448 +train: [15] [340/400] eta: 0:00:27 lr: 0.000053 loss: 2.0576 (2.0605) grad: 0.2564 (0.2536) time: 0.4633 data: 0.0043 max mem: 22448 +train: [15] [360/400] eta: 0:00:17 lr: 0.000052 loss: 2.0741 (2.0609) grad: 0.2558 (0.2539) time: 0.4358 data: 0.0042 max mem: 22448 +train: [15] [380/400] eta: 0:00:08 lr: 0.000051 loss: 2.0418 (2.0587) grad: 0.2489 (0.2534) time: 0.4340 data: 0.0043 max mem: 22448 +train: [15] [399/400] eta: 0:00:00 lr: 0.000050 loss: 2.0418 (2.0590) grad: 0.2435 (0.2531) time: 0.4440 data: 0.0041 max mem: 22448 +train: [15] Total time: 0:02:59 (0.4492 s / it) +train: [15] Summary: lr: 0.000050 loss: 2.0418 (2.0590) grad: 0.2435 (0.2531) +eval (validation): [15] [ 0/85] eta: 0:04:37 time: 3.2652 data: 3.0324 max mem: 22448 +eval (validation): [15] [20/85] eta: 0:00:31 time: 0.3528 data: 0.0045 max mem: 22448 +eval (validation): [15] [40/85] eta: 0:00:18 time: 0.3377 data: 0.0038 max mem: 22448 +eval (validation): [15] [60/85] eta: 0:00:09 time: 0.3365 data: 0.0040 max mem: 22448 +eval (validation): [15] [80/85] eta: 0:00:01 time: 0.3293 data: 0.0040 max mem: 22448 +eval (validation): [15] [84/85] eta: 0:00:00 time: 0.3180 data: 0.0040 max mem: 22448 +eval (validation): [15] Total time: 0:00:31 (0.3750 s / it) +cv: [15] best hparam: (0.32, 1.0) (017) ('017_lr3.2e-01_wd1.0e+00') loss: 2.422 acc: 0.276 f1: 0.210 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [16] [ 0/400] eta: 0:21:50 lr: nan time: 3.2772 data: 2.9446 max mem: 22448 +train: [16] [ 20/400] eta: 0:03:37 lr: 0.000048 loss: 1.9843 (2.0124) grad: 0.2323 (0.2345) time: 0.4375 data: 0.0035 max mem: 22448 +train: [16] [ 40/400] eta: 0:03:03 lr: 0.000047 loss: 2.0127 (2.0066) grad: 0.2375 (0.2366) time: 0.4427 data: 0.0041 max mem: 22448 +train: [16] [ 60/400] eta: 0:02:46 lr: 0.000046 loss: 1.9931 (2.0035) grad: 0.2436 (0.2403) time: 0.4460 data: 0.0040 max mem: 22448 +train: [16] [ 80/400] eta: 0:02:32 lr: 0.000045 loss: 2.0303 (2.0137) grad: 0.2468 (0.2434) time: 0.4405 data: 0.0043 max mem: 22448 +train: [16] [100/400] eta: 0:02:21 lr: 0.000044 loss: 2.0303 (2.0114) grad: 0.2481 (0.2439) time: 0.4454 data: 0.0042 max mem: 22448 +train: [16] [120/400] eta: 0:02:10 lr: 0.000043 loss: 2.0096 (2.0136) grad: 0.2435 (0.2453) time: 0.4395 data: 0.0042 max mem: 22448 +train: [16] [140/400] eta: 0:01:59 lr: 0.000042 loss: 2.0122 (2.0137) grad: 0.2434 (0.2451) time: 0.4355 data: 0.0041 max mem: 22448 +train: [16] [160/400] eta: 0:01:49 lr: 0.000041 loss: 2.0198 (2.0214) grad: 0.2491 (0.2467) time: 0.4332 data: 0.0042 max mem: 22448 +train: [16] [180/400] eta: 0:01:40 lr: 0.000040 loss: 2.0366 (2.0232) grad: 0.2521 (0.2466) time: 0.4353 data: 0.0043 max mem: 22448 +train: [16] [200/400] eta: 0:01:30 lr: 0.000039 loss: 2.0114 (2.0197) grad: 0.2431 (0.2457) time: 0.4346 data: 0.0040 max mem: 22448 +train: [16] [220/400] eta: 0:01:21 lr: 0.000038 loss: 1.9953 (2.0195) grad: 0.2343 (0.2452) time: 0.4343 data: 0.0042 max mem: 22448 +train: [16] [240/400] eta: 0:01:12 lr: 0.000036 loss: 2.0086 (2.0187) grad: 0.2371 (0.2454) time: 0.4447 data: 0.0041 max mem: 22448 +train: [16] [260/400] eta: 0:01:03 lr: 0.000035 loss: 2.0225 (2.0226) grad: 0.2551 (0.2462) time: 0.4773 data: 0.0042 max mem: 22448 +train: [16] [280/400] eta: 0:00:54 lr: 0.000034 loss: 2.0253 (2.0221) grad: 0.2506 (0.2464) time: 0.4477 data: 0.0043 max mem: 22448 +train: [16] [300/400] eta: 0:00:45 lr: 0.000033 loss: 2.0253 (2.0236) grad: 0.2489 (0.2466) time: 0.4393 data: 0.0041 max mem: 22448 +train: [16] [320/400] eta: 0:00:36 lr: 0.000032 loss: 2.0491 (2.0250) grad: 0.2434 (0.2467) time: 0.4422 data: 0.0040 max mem: 22448 +train: [16] [340/400] eta: 0:00:27 lr: 0.000031 loss: 2.0102 (2.0239) grad: 0.2473 (0.2467) time: 0.4666 data: 0.0043 max mem: 22448 +train: [16] [360/400] eta: 0:00:18 lr: 0.000031 loss: 2.0124 (2.0250) grad: 0.2480 (0.2470) time: 0.4801 data: 0.0044 max mem: 22448 +train: [16] [380/400] eta: 0:00:09 lr: 0.000030 loss: 2.0355 (2.0251) grad: 0.2477 (0.2474) time: 0.4397 data: 0.0042 max mem: 22448 +train: [16] [399/400] eta: 0:00:00 lr: 0.000029 loss: 2.0355 (2.0260) grad: 0.2513 (0.2480) time: 0.4473 data: 0.0043 max mem: 22448 +train: [16] Total time: 0:03:01 (0.4529 s / it) +train: [16] Summary: lr: 0.000029 loss: 2.0355 (2.0260) grad: 0.2513 (0.2480) +eval (validation): [16] [ 0/85] eta: 0:04:33 time: 3.2132 data: 2.9809 max mem: 22448 +eval (validation): [16] [20/85] eta: 0:00:30 time: 0.3310 data: 0.0044 max mem: 22448 +eval (validation): [16] [40/85] eta: 0:00:18 time: 0.3463 data: 0.0039 max mem: 22448 +eval (validation): [16] [60/85] eta: 0:00:09 time: 0.3266 data: 0.0041 max mem: 22448 +eval (validation): [16] [80/85] eta: 0:00:01 time: 0.3269 data: 0.0041 max mem: 22448 +eval (validation): [16] [84/85] eta: 0:00:00 time: 0.3189 data: 0.0040 max mem: 22448 +eval (validation): [16] Total time: 0:00:31 (0.3680 s / it) +cv: [16] best hparam: (0.32, 1.0) (017) ('017_lr3.2e-01_wd1.0e+00') loss: 2.417 acc: 0.275 f1: 0.213 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [17] [ 0/400] eta: 0:22:00 lr: nan time: 3.3001 data: 2.9739 max mem: 22448 +train: [17] [ 20/400] eta: 0:03:36 lr: 0.000028 loss: 1.9327 (1.9666) grad: 0.2232 (0.2362) time: 0.4331 data: 0.0042 max mem: 22448 +train: [17] [ 40/400] eta: 0:03:02 lr: 0.000027 loss: 1.9792 (1.9909) grad: 0.2380 (0.2385) time: 0.4390 data: 0.0040 max mem: 22448 +train: [17] [ 60/400] eta: 0:02:44 lr: 0.000026 loss: 2.0028 (1.9969) grad: 0.2380 (0.2372) time: 0.4372 data: 0.0042 max mem: 22448 +train: [17] [ 80/400] eta: 0:02:30 lr: 0.000025 loss: 1.9663 (1.9817) grad: 0.2309 (0.2370) time: 0.4331 data: 0.0042 max mem: 22448 +train: [17] [100/400] eta: 0:02:19 lr: 0.000024 loss: 1.9580 (1.9908) grad: 0.2318 (0.2361) time: 0.4392 data: 0.0042 max mem: 22448 +train: [17] [120/400] eta: 0:02:09 lr: 0.000023 loss: 2.0005 (1.9900) grad: 0.2345 (0.2369) time: 0.4440 data: 0.0042 max mem: 22448 +train: [17] [140/400] eta: 0:01:59 lr: 0.000023 loss: 1.9810 (1.9903) grad: 0.2388 (0.2372) time: 0.4379 data: 0.0042 max mem: 22448 +train: [17] [160/400] eta: 0:01:49 lr: 0.000022 loss: 1.9843 (1.9912) grad: 0.2412 (0.2379) time: 0.4406 data: 0.0041 max mem: 22448 +train: [17] [180/400] eta: 0:01:39 lr: 0.000021 loss: 1.9852 (1.9905) grad: 0.2407 (0.2377) time: 0.4342 data: 0.0041 max mem: 22448 +train: [17] [200/400] eta: 0:01:30 lr: 0.000020 loss: 1.9852 (1.9922) grad: 0.2407 (0.2379) time: 0.4359 data: 0.0041 max mem: 22448 +train: [17] [220/400] eta: 0:01:21 lr: 0.000019 loss: 2.0251 (1.9938) grad: 0.2429 (0.2389) time: 0.4423 data: 0.0040 max mem: 22448 +train: [17] [240/400] eta: 0:01:12 lr: 0.000019 loss: 2.0030 (1.9923) grad: 0.2396 (0.2392) time: 0.4474 data: 0.0043 max mem: 22448 +train: [17] [260/400] eta: 0:01:03 lr: 0.000018 loss: 1.9728 (1.9910) grad: 0.2396 (0.2398) time: 0.4602 data: 0.0041 max mem: 22448 +train: [17] [280/400] eta: 0:00:54 lr: 0.000017 loss: 1.9762 (1.9926) grad: 0.2432 (0.2399) time: 0.4457 data: 0.0042 max mem: 22448 +train: [17] [300/400] eta: 0:00:45 lr: 0.000016 loss: 2.0211 (1.9943) grad: 0.2388 (0.2400) time: 0.4385 data: 0.0041 max mem: 22448 +train: [17] [320/400] eta: 0:00:35 lr: 0.000016 loss: 2.0151 (1.9943) grad: 0.2300 (0.2394) time: 0.4447 data: 0.0040 max mem: 22448 +train: [17] [340/400] eta: 0:00:27 lr: 0.000015 loss: 1.9929 (1.9942) grad: 0.2350 (0.2397) time: 0.4577 data: 0.0041 max mem: 22448 +train: [17] [360/400] eta: 0:00:18 lr: 0.000014 loss: 1.9929 (1.9947) grad: 0.2400 (0.2399) time: 0.4481 data: 0.0043 max mem: 22448 +train: [17] [380/400] eta: 0:00:09 lr: 0.000014 loss: 1.9905 (1.9938) grad: 0.2414 (0.2403) time: 0.4494 data: 0.0042 max mem: 22448 +train: [17] [399/400] eta: 0:00:00 lr: 0.000013 loss: 1.9677 (1.9929) grad: 0.2343 (0.2399) time: 0.4440 data: 0.0043 max mem: 22448 +train: [17] Total time: 0:02:59 (0.4500 s / it) +train: [17] Summary: lr: 0.000013 loss: 1.9677 (1.9929) grad: 0.2343 (0.2399) +eval (validation): [17] [ 0/85] eta: 0:04:39 time: 3.2865 data: 3.0075 max mem: 22448 +eval (validation): [17] [20/85] eta: 0:00:32 time: 0.3686 data: 0.0044 max mem: 22448 +eval (validation): [17] [40/85] eta: 0:00:19 time: 0.3475 data: 0.0037 max mem: 22448 +eval (validation): [17] [60/85] eta: 0:00:09 time: 0.3306 data: 0.0040 max mem: 22448 +eval (validation): [17] [80/85] eta: 0:00:01 time: 0.3246 data: 0.0040 max mem: 22448 +eval (validation): [17] [84/85] eta: 0:00:00 time: 0.3162 data: 0.0038 max mem: 22448 +eval (validation): [17] Total time: 0:00:32 (0.3779 s / it) +cv: [17] best hparam: (0.32, 1.0) (017) ('017_lr3.2e-01_wd1.0e+00') loss: 2.412 acc: 0.278 f1: 0.215 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [18] [ 0/400] eta: 0:22:18 lr: nan time: 3.3454 data: 2.9722 max mem: 22448 +train: [18] [ 20/400] eta: 0:03:41 lr: 0.000012 loss: 1.9792 (2.0050) grad: 0.2356 (0.2344) time: 0.4434 data: 0.0034 max mem: 22448 +train: [18] [ 40/400] eta: 0:03:02 lr: 0.000012 loss: 1.9792 (1.9751) grad: 0.2327 (0.2343) time: 0.4261 data: 0.0039 max mem: 22448 +train: [18] [ 60/400] eta: 0:02:43 lr: 0.000011 loss: 1.9387 (1.9756) grad: 0.2441 (0.2383) time: 0.4337 data: 0.0040 max mem: 22448 +train: [18] [ 80/400] eta: 0:02:30 lr: 0.000011 loss: 1.9440 (1.9754) grad: 0.2397 (0.2363) time: 0.4301 data: 0.0041 max mem: 22448 +train: [18] [100/400] eta: 0:02:18 lr: 0.000010 loss: 1.9683 (1.9768) grad: 0.2312 (0.2359) time: 0.4353 data: 0.0042 max mem: 22448 +train: [18] [120/400] eta: 0:02:08 lr: 0.000009 loss: 1.9470 (1.9728) grad: 0.2320 (0.2356) time: 0.4358 data: 0.0040 max mem: 22448 +train: [18] [140/400] eta: 0:01:58 lr: 0.000009 loss: 1.9689 (1.9762) grad: 0.2383 (0.2362) time: 0.4363 data: 0.0041 max mem: 22448 +train: [18] [160/400] eta: 0:01:48 lr: 0.000008 loss: 1.9867 (1.9776) grad: 0.2366 (0.2355) time: 0.4345 data: 0.0040 max mem: 22448 +train: [18] [180/400] eta: 0:01:39 lr: 0.000008 loss: 1.9611 (1.9750) grad: 0.2366 (0.2361) time: 0.4349 data: 0.0041 max mem: 22448 +train: [18] [200/400] eta: 0:01:29 lr: 0.000007 loss: 1.9611 (1.9760) grad: 0.2343 (0.2360) time: 0.4367 data: 0.0040 max mem: 22448 +train: [18] [220/400] eta: 0:01:20 lr: 0.000007 loss: 1.9943 (1.9781) grad: 0.2339 (0.2359) time: 0.4402 data: 0.0040 max mem: 22448 +train: [18] [240/400] eta: 0:01:11 lr: 0.000006 loss: 2.0056 (1.9821) grad: 0.2372 (0.2359) time: 0.4516 data: 0.0041 max mem: 22448 +train: [18] [260/400] eta: 0:01:02 lr: 0.000006 loss: 1.9855 (1.9819) grad: 0.2372 (0.2359) time: 0.4638 data: 0.0043 max mem: 22448 +train: [18] [280/400] eta: 0:00:53 lr: 0.000006 loss: 1.9798 (1.9824) grad: 0.2382 (0.2359) time: 0.4462 data: 0.0041 max mem: 22448 +train: [18] [300/400] eta: 0:00:44 lr: 0.000005 loss: 1.9969 (1.9820) grad: 0.2322 (0.2358) time: 0.4394 data: 0.0041 max mem: 22448 +train: [18] [320/400] eta: 0:00:36 lr: 0.000005 loss: 2.0053 (1.9838) grad: 0.2322 (0.2358) time: 0.4932 data: 0.0361 max mem: 22448 +train: [18] [340/400] eta: 0:00:27 lr: 0.000004 loss: 1.9824 (1.9812) grad: 0.2311 (0.2356) time: 0.4452 data: 0.0038 max mem: 22448 +train: [18] [360/400] eta: 0:00:18 lr: 0.000004 loss: 1.9476 (1.9811) grad: 0.2311 (0.2355) time: 0.4367 data: 0.0038 max mem: 22448 +train: [18] [380/400] eta: 0:00:08 lr: 0.000004 loss: 1.9794 (1.9811) grad: 0.2354 (0.2355) time: 0.4368 data: 0.0041 max mem: 22448 +train: [18] [399/400] eta: 0:00:00 lr: 0.000003 loss: 1.9642 (1.9795) grad: 0.2354 (0.2357) time: 0.4437 data: 0.0042 max mem: 22448 +train: [18] Total time: 0:02:59 (0.4497 s / it) +train: [18] Summary: lr: 0.000003 loss: 1.9642 (1.9795) grad: 0.2354 (0.2357) +eval (validation): [18] [ 0/85] eta: 0:04:33 time: 3.2143 data: 2.9835 max mem: 22448 +eval (validation): [18] [20/85] eta: 0:00:30 time: 0.3335 data: 0.0036 max mem: 22448 +eval (validation): [18] [40/85] eta: 0:00:18 time: 0.3501 data: 0.0038 max mem: 22448 +eval (validation): [18] [60/85] eta: 0:00:09 time: 0.3389 data: 0.0041 max mem: 22448 +eval (validation): [18] [80/85] eta: 0:00:01 time: 0.3250 data: 0.0041 max mem: 22448 +eval (validation): [18] [84/85] eta: 0:00:00 time: 0.3198 data: 0.0039 max mem: 22448 +eval (validation): [18] Total time: 0:00:31 (0.3725 s / it) +cv: [18] best hparam: (0.32, 1.0) (017) ('017_lr3.2e-01_wd1.0e+00') loss: 2.416 acc: 0.277 f1: 0.213 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [19] [ 0/400] eta: 0:22:24 lr: nan time: 3.3616 data: 2.9911 max mem: 22448 +train: [19] [ 20/400] eta: 0:03:39 lr: 0.000003 loss: 1.9757 (1.9850) grad: 0.2253 (0.2294) time: 0.4398 data: 0.0029 max mem: 22448 +train: [19] [ 40/400] eta: 0:03:02 lr: 0.000003 loss: 1.9495 (1.9593) grad: 0.2260 (0.2313) time: 0.4314 data: 0.0042 max mem: 22448 +train: [19] [ 60/400] eta: 0:02:44 lr: 0.000002 loss: 1.9764 (1.9786) grad: 0.2299 (0.2324) time: 0.4350 data: 0.0041 max mem: 22448 +train: [19] [ 80/400] eta: 0:02:30 lr: 0.000002 loss: 1.9948 (1.9805) grad: 0.2327 (0.2322) time: 0.4321 data: 0.0040 max mem: 22448 +train: [19] [100/400] eta: 0:02:19 lr: 0.000002 loss: 1.9852 (1.9812) grad: 0.2344 (0.2331) time: 0.4382 data: 0.0041 max mem: 22448 +train: [19] [120/400] eta: 0:02:08 lr: 0.000002 loss: 1.9717 (1.9814) grad: 0.2347 (0.2339) time: 0.4328 data: 0.0041 max mem: 22448 +train: [19] [140/400] eta: 0:01:58 lr: 0.000001 loss: 1.9775 (1.9807) grad: 0.2296 (0.2332) time: 0.4348 data: 0.0042 max mem: 22448 +train: [19] [160/400] eta: 0:01:48 lr: 0.000001 loss: 1.9499 (1.9753) grad: 0.2263 (0.2326) time: 0.4349 data: 0.0042 max mem: 22448 +train: [19] [180/400] eta: 0:01:39 lr: 0.000001 loss: 1.9486 (1.9721) grad: 0.2299 (0.2336) time: 0.4371 data: 0.0041 max mem: 22448 +train: [19] [200/400] eta: 0:01:29 lr: 0.000001 loss: 1.9556 (1.9724) grad: 0.2350 (0.2334) time: 0.4358 data: 0.0042 max mem: 22448 +train: [19] [220/400] eta: 0:01:20 lr: 0.000001 loss: 1.9556 (1.9711) grad: 0.2283 (0.2330) time: 0.4420 data: 0.0041 max mem: 22448 +train: [19] [240/400] eta: 0:01:11 lr: 0.000001 loss: 1.9356 (1.9683) grad: 0.2282 (0.2331) time: 0.4590 data: 0.0041 max mem: 22448 +train: [19] [260/400] eta: 0:01:03 lr: 0.000000 loss: 1.9334 (1.9668) grad: 0.2335 (0.2329) time: 0.4557 data: 0.0042 max mem: 22448 +train: [19] [280/400] eta: 0:00:53 lr: 0.000000 loss: 1.9481 (1.9680) grad: 0.2311 (0.2327) time: 0.4357 data: 0.0042 max mem: 22448 +train: [19] [300/400] eta: 0:00:44 lr: 0.000000 loss: 1.9696 (1.9687) grad: 0.2311 (0.2326) time: 0.4338 data: 0.0041 max mem: 22448 +train: [19] [320/400] eta: 0:00:35 lr: 0.000000 loss: 1.9640 (1.9711) grad: 0.2336 (0.2329) time: 0.4552 data: 0.0042 max mem: 22448 +train: [19] [340/400] eta: 0:00:26 lr: 0.000000 loss: 2.0075 (1.9741) grad: 0.2292 (0.2327) time: 0.4541 data: 0.0043 max mem: 22448 +train: [19] [360/400] eta: 0:00:17 lr: 0.000000 loss: 2.0001 (1.9747) grad: 0.2259 (0.2324) time: 0.4553 data: 0.0041 max mem: 22448 +train: [19] [380/400] eta: 0:00:08 lr: 0.000000 loss: 1.9568 (1.9743) grad: 0.2249 (0.2322) time: 0.4481 data: 0.0041 max mem: 22448 +train: [19] [399/400] eta: 0:00:00 lr: 0.000000 loss: 1.9795 (1.9763) grad: 0.2249 (0.2322) time: 0.4612 data: 0.0042 max mem: 22448 +train: [19] Total time: 0:03:00 (0.4501 s / it) +train: [19] Summary: lr: 0.000000 loss: 1.9795 (1.9763) grad: 0.2249 (0.2322) +eval (validation): [19] [ 0/85] eta: 0:04:50 time: 3.4229 data: 3.1698 max mem: 22448 +eval (validation): [19] [20/85] eta: 0:00:32 time: 0.3608 data: 0.0040 max mem: 22448 +eval (validation): [19] [40/85] eta: 0:00:19 time: 0.3661 data: 0.0044 max mem: 22448 +eval (validation): [19] [60/85] eta: 0:00:10 time: 0.3774 data: 0.0047 max mem: 22448 +eval (validation): [19] [80/85] eta: 0:00:02 time: 0.3583 data: 0.0042 max mem: 22448 +eval (validation): [19] [84/85] eta: 0:00:00 time: 0.3475 data: 0.0040 max mem: 22448 +eval (validation): [19] Total time: 0:00:34 (0.4030 s / it) +cv: [19] best hparam: (0.32, 1.0) (017) ('017_lr3.2e-01_wd1.0e+00') loss: 2.416 acc: 0.277 f1: 0.214 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +evaluating last checkpoint: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +eval model info: +{"score": 0.27740863787375414, "hparam": [0.32, 1.0], "hparam_id": 17, "epoch": 19, "is_best": false, "best_score": 0.28460686600221485} +eval (train): [20] [ 0/509] eta: 0:25:44 time: 3.0341 data: 2.8000 max mem: 22448 +eval (train): [20] [ 20/509] eta: 0:04:08 time: 0.3814 data: 0.0056 max mem: 22448 +eval (train): [20] [ 40/509] eta: 0:03:29 time: 0.3810 data: 0.0036 max mem: 22448 +eval (train): [20] [ 60/509] eta: 0:03:06 time: 0.3533 data: 0.0043 max mem: 22448 +eval (train): [20] [ 80/509] eta: 0:02:53 time: 0.3681 data: 0.0050 max mem: 22448 +eval (train): [20] [100/509] eta: 0:02:41 time: 0.3598 data: 0.0044 max mem: 22448 +eval (train): [20] [120/509] eta: 0:02:30 time: 0.3523 data: 0.0045 max mem: 22448 +eval (train): [20] [140/509] eta: 0:02:21 time: 0.3506 data: 0.0045 max mem: 22448 +eval (train): [20] [160/509] eta: 0:02:12 time: 0.3609 data: 0.0042 max mem: 22448 +eval (train): [20] [180/509] eta: 0:02:04 time: 0.3756 data: 0.0043 max mem: 22448 +eval (train): [20] [200/509] eta: 0:01:57 time: 0.3782 data: 0.0042 max mem: 22448 +eval (train): [20] [220/509] eta: 0:01:49 time: 0.3783 data: 0.0043 max mem: 22448 +eval (train): [20] [240/509] eta: 0:01:41 time: 0.3501 data: 0.0045 max mem: 22448 +eval (train): [20] [260/509] eta: 0:01:33 time: 0.3540 data: 0.0045 max mem: 22448 +eval (train): [20] [280/509] eta: 0:01:25 time: 0.3367 data: 0.0040 max mem: 22448 +eval (train): [20] [300/509] eta: 0:01:17 time: 0.3640 data: 0.0041 max mem: 22448 +eval (train): [20] [320/509] eta: 0:01:10 time: 0.3620 data: 0.0043 max mem: 22448 +eval (train): [20] [340/509] eta: 0:01:04 time: 0.5596 data: 0.1997 max mem: 22448 +eval (train): [20] [360/509] eta: 0:00:56 time: 0.3418 data: 0.0039 max mem: 22448 +eval (train): [20] [380/509] eta: 0:00:48 time: 0.3418 data: 0.0040 max mem: 22448 +eval (train): [20] [400/509] eta: 0:00:41 time: 0.3778 data: 0.0043 max mem: 22448 +eval (train): [20] [420/509] eta: 0:00:33 time: 0.3658 data: 0.0044 max mem: 22448 +eval (train): [20] [440/509] eta: 0:00:26 time: 0.3799 data: 0.0047 max mem: 22448 +eval (train): [20] [460/509] eta: 0:00:18 time: 0.3417 data: 0.0042 max mem: 22448 +eval (train): [20] [480/509] eta: 0:00:10 time: 0.3393 data: 0.0041 max mem: 22448 +eval (train): [20] [500/509] eta: 0:00:03 time: 0.3603 data: 0.0038 max mem: 22448 +eval (train): [20] [508/509] eta: 0:00:00 time: 0.3643 data: 0.0042 max mem: 22448 +eval (train): [20] Total time: 0:03:10 (0.3749 s / it) +eval (validation): [20] [ 0/85] eta: 0:04:56 time: 3.4909 data: 3.1836 max mem: 22448 +eval (validation): [20] [20/85] eta: 0:00:33 time: 0.3685 data: 0.0037 max mem: 22448 +eval (validation): [20] [40/85] eta: 0:00:18 time: 0.3224 data: 0.0036 max mem: 22448 +eval (validation): [20] [60/85] eta: 0:00:10 time: 0.3871 data: 0.0047 max mem: 22448 +eval (validation): [20] [80/85] eta: 0:00:01 time: 0.3442 data: 0.0040 max mem: 22448 +eval (validation): [20] [84/85] eta: 0:00:00 time: 0.3320 data: 0.0039 max mem: 22448 +eval (validation): [20] Total time: 0:00:33 (0.3931 s / it) +eval (test): [20] [ 0/85] eta: 0:04:26 time: 3.1321 data: 2.8802 max mem: 22448 +eval (test): [20] [20/85] eta: 0:00:33 time: 0.3784 data: 0.0052 max mem: 22448 +eval (test): [20] [40/85] eta: 0:00:18 time: 0.3306 data: 0.0032 max mem: 22448 +eval (test): [20] [60/85] eta: 0:00:10 time: 0.3849 data: 0.0047 max mem: 22448 +eval (test): [20] [80/85] eta: 0:00:01 time: 0.3305 data: 0.0031 max mem: 22448 +eval (test): [20] [84/85] eta: 0:00:00 time: 0.3190 data: 0.0035 max mem: 22448 +eval (test): [20] Total time: 0:00:33 (0.3886 s / it) +eval (testid): [20] [ 0/82] eta: 0:04:22 time: 3.2049 data: 2.9510 max mem: 22448 +eval (testid): [20] [20/82] eta: 0:00:33 time: 0.3997 data: 0.0057 max mem: 22448 +eval (testid): [20] [40/82] eta: 0:00:19 time: 0.3738 data: 0.0035 max mem: 22448 +eval (testid): [20] [60/82] eta: 0:00:09 time: 0.3613 data: 0.0045 max mem: 22448 +eval (testid): [20] [80/82] eta: 0:00:00 time: 0.3361 data: 0.0042 max mem: 22448 +eval (testid): [20] [81/82] eta: 0:00:00 time: 0.3244 data: 0.0040 max mem: 22448 +eval (testid): [20] Total time: 0:00:32 (0.4024 s / it) +evaluating best checkpoint: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/eval_v2/nsd_cococlip__patch__attn/checkpoint-best.pth +eval model info: +{"score": 0.28460686600221485, "hparam": [0.61, 1.0], "hparam_id": 21, "epoch": 6, "is_best": true, "best_score": 0.28460686600221485} +eval (train): [20] [ 0/509] eta: 0:27:18 time: 3.2198 data: 2.9049 max mem: 22448 +eval (train): [20] [ 20/509] eta: 0:04:19 time: 0.3971 data: 0.0052 max mem: 22448 +eval (train): [20] [ 40/509] eta: 0:03:28 time: 0.3553 data: 0.0037 max mem: 22448 +eval (train): [20] [ 60/509] eta: 0:03:05 time: 0.3460 data: 0.0036 max mem: 22448 +eval (train): [20] [ 80/509] eta: 0:02:55 time: 0.3991 data: 0.0047 max mem: 22448 +eval (train): [20] [100/509] eta: 0:02:44 time: 0.3687 data: 0.0044 max mem: 22448 +eval (train): [20] [120/509] eta: 0:02:33 time: 0.3635 data: 0.0045 max mem: 22448 +eval (train): [20] [140/509] eta: 0:02:23 time: 0.3596 data: 0.0037 max mem: 22448 +eval (train): [20] [160/509] eta: 0:02:15 time: 0.3698 data: 0.0319 max mem: 22448 +eval (train): [20] [180/509] eta: 0:02:08 time: 0.4118 data: 0.0353 max mem: 22448 +eval (train): [20] [200/509] eta: 0:02:00 time: 0.3985 data: 0.0053 max mem: 22448 +eval (train): [20] [220/509] eta: 0:01:52 time: 0.3699 data: 0.0033 max mem: 22448 +eval (train): [20] [240/509] eta: 0:01:44 time: 0.3629 data: 0.0040 max mem: 22448 +eval (train): [20] [260/509] eta: 0:01:35 time: 0.3367 data: 0.0038 max mem: 22448 +eval (train): [20] [280/509] eta: 0:01:26 time: 0.3373 data: 0.0039 max mem: 22448 +eval (train): [20] [300/509] eta: 0:01:19 time: 0.3682 data: 0.0043 max mem: 22448 +eval (train): [20] [320/509] eta: 0:01:11 time: 0.3955 data: 0.0043 max mem: 22448 +eval (train): [20] [340/509] eta: 0:01:04 time: 0.3777 data: 0.0043 max mem: 22448 +eval (train): [20] [360/509] eta: 0:00:56 time: 0.3267 data: 0.0036 max mem: 22448 +eval (train): [20] [380/509] eta: 0:00:48 time: 0.3531 data: 0.0042 max mem: 22448 +eval (train): [20] [400/509] eta: 0:00:40 time: 0.3649 data: 0.0041 max mem: 22448 +eval (train): [20] [420/509] eta: 0:00:33 time: 0.3699 data: 0.0041 max mem: 22448 +eval (train): [20] [440/509] eta: 0:00:25 time: 0.3574 data: 0.0040 max mem: 22448 +eval (train): [20] [460/509] eta: 0:00:18 time: 0.3402 data: 0.0042 max mem: 22448 +eval (train): [20] [480/509] eta: 0:00:10 time: 0.3348 data: 0.0038 max mem: 22448 +eval (train): [20] [500/509] eta: 0:00:03 time: 0.3812 data: 0.0041 max mem: 22448 +eval (train): [20] [508/509] eta: 0:00:00 time: 0.3433 data: 0.0038 max mem: 22448 +eval (train): [20] Total time: 0:03:09 (0.3721 s / it) +eval (validation): [20] [ 0/85] eta: 0:04:12 time: 2.9682 data: 2.6863 max mem: 22448 +eval (validation): [20] [20/85] eta: 0:00:32 time: 0.3700 data: 0.0168 max mem: 22448 +eval (validation): [20] [40/85] eta: 0:00:18 time: 0.3224 data: 0.0035 max mem: 22448 +eval (validation): [20] [60/85] eta: 0:00:09 time: 0.3253 data: 0.0039 max mem: 22448 +eval (validation): [20] [80/85] eta: 0:00:01 time: 0.3228 data: 0.0036 max mem: 22448 +eval (validation): [20] [84/85] eta: 0:00:00 time: 0.3177 data: 0.0035 max mem: 22448 +eval (validation): [20] Total time: 0:00:31 (0.3674 s / it) +eval (test): [20] [ 0/85] eta: 0:03:56 time: 2.7880 data: 2.5622 max mem: 22448 +eval (test): [20] [20/85] eta: 0:00:28 time: 0.3141 data: 0.0042 max mem: 22448 +eval (test): [20] [40/85] eta: 0:00:17 time: 0.3248 data: 0.0032 max mem: 22448 +eval (test): [20] [60/85] eta: 0:00:09 time: 0.3339 data: 0.0035 max mem: 22448 +eval (test): [20] [80/85] eta: 0:00:01 time: 0.3666 data: 0.0483 max mem: 22448 +eval (test): [20] [84/85] eta: 0:00:00 time: 0.3570 data: 0.0478 max mem: 22448 +eval (test): [20] Total time: 0:00:30 (0.3638 s / it) +eval (testid): [20] [ 0/82] eta: 0:04:14 time: 3.1066 data: 2.8285 max mem: 22448 +eval (testid): [20] [20/82] eta: 0:00:29 time: 0.3488 data: 0.0035 max mem: 22448 +eval (testid): [20] [40/82] eta: 0:00:17 time: 0.3359 data: 0.0044 max mem: 22448 +eval (testid): [20] [60/82] eta: 0:00:08 time: 0.3365 data: 0.0032 max mem: 22448 +eval (testid): [20] [80/82] eta: 0:00:00 time: 0.3453 data: 0.0043 max mem: 22448 +eval (testid): [20] [81/82] eta: 0:00:00 time: 0.3312 data: 0.0040 max mem: 22448 +eval (testid): [20] Total time: 0:00:30 (0.3757 s / it) +eval results: + +| model | repr | clf | dataset | ckpt | epoch | lr | wd | hparam_id | hparam | split | loss | acc | acc_std | f1 | f1_std | +|:---------|:-------|:------|:-------------|:-------|--------:|---------:|-----:|------------:|:------------|:-----------|-------:|--------:|----------:|--------:|----------:| +| flat_mae | patch | attn | nsd_cococlip | best | 6 | 0.000183 | 0.05 | 21 | [0.61, 1.0] | train | 2.1802 | 0.34589 | 0.0022717 | 0.28802 | 0.0022832 | +| flat_mae | patch | attn | nsd_cococlip | best | 6 | 0.000183 | 0.05 | 21 | [0.61, 1.0] | validation | 2.3954 | 0.28461 | 0.0055848 | 0.2191 | 0.0049503 | +| flat_mae | patch | attn | nsd_cococlip | best | 6 | 0.000183 | 0.05 | 21 | [0.61, 1.0] | test | 2.2507 | 0.31132 | 0.0054006 | 0.24343 | 0.0051276 | +| flat_mae | patch | attn | nsd_cococlip | best | 6 | 0.000183 | 0.05 | 21 | [0.61, 1.0] | testid | 2.3332 | 0.28726 | 0.00583 | 0.23114 | 0.0054271 | + + +done! total time: 1:22:41 diff --git a/input_space_v3/flat_lr1e-3_2/eval_v2/nsd_cococlip__patch__attn/train_log.json b/input_space_v3/flat_lr1e-3_2/eval_v2/nsd_cococlip__patch__attn/train_log.json new file mode 100644 index 0000000000000000000000000000000000000000..2883ce5e553ac1343b3bd1d1829d6d0c9f019323 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_2/eval_v2/nsd_cococlip__patch__attn/train_log.json @@ -0,0 +1,20 @@ +{"epoch": 0, "train/lr": 2.987987987987988e-05, "train/loss": 3.1240372717380525, "train/grad": 0.15898942306637764, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.183328857421875, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.18255126953125, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.181265869140625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.180111083984375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.179019775390625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.17740966796875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.175760498046875, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.174073486328125, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.171998291015625, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.169923095703125, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.16809814453125, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.165660400390625, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.163502197265625, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.16087158203125, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.158712158203125, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.15683349609375, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.1549853515625, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.153076171875, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.15129150390625, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.149842529296875, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.148231201171875, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.1468505859375, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.145638427734375, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.14451416015625, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.1435107421875, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.142669677734375, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.142049560546875, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.141702880859375, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.1412158203125, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.140960693359375, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.140762939453125, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.140733642578125, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.14050537109375, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.14037841796875, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.140032958984375, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.139332275390625, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.137850341796875, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.1338720703125, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.1230479431152345, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.099773254394531, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.079640197753906, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.0600508880615234, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.0332386779785154, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.0095755767822268, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.9879310607910154, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.9689563751220702, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.9526173210144044, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.933000202178955, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.920870246887207, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.023906878447160124, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.02384481087792665, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.023744974019937217, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.02365044265985489, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.023559980685822667, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.02343850790988654, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.023308410556055606, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.023171636280603706, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.023003208632580936, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.02283985584974289, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.02269257658161223, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.02249621058348566, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.02232785593252629, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.022120845397002997, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.021958066280931235, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.021826985008083284, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.021689549651928246, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.021560238655656577, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.02144364745821804, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.021357826949097217, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.021271378519013524, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.02120106298942119, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.02113988583907485, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.021088586715050043, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.02104995840229094, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.02101717293262482, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0209993683360517, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.020988611849024893, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.020980329015292228, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.020975046847015618, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.020968841053545476, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.020958696706220508, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0209251574287191, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.020875351764261724, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.020786961913108824, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.020673420717939733, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.020545818381942808, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.020490681831724943, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.020673869531601666, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.02135858078021556, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.022123968354426326, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.022765769520774484, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.02349426945205778, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.02407469814643264, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.02497949690092355, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.025919277099892498, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.026847832687199116, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.027881863238289954, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.029005174851045014, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.172945737838745, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1706104278564453, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1669251918792725, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.163494110107422, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.160309076309204, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.156205415725708, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.151977062225342, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.147808074951172, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.14313006401062, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1389212608337402, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.135530471801758, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1315340995788574, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.128683567047119, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.125864028930664, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.124208450317383, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.123220205307007, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.122518301010132, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.122109889984131, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1219451427459717, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.1219842433929443, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.122180223464966, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.1225688457489014, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.123338222503662, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.124455213546753, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.1258468627929688, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.12766432762146, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.129117250442505, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.130131483078003, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.1308796405792236, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.130014419555664, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.1274144649505615, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.124159097671509, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.1190061569213867, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.1140763759613037, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.107154369354248, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.096586227416992, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.0688366889953613, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.9968814849853516, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.869486093521118, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.7302112579345703, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.6792662143707275, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.6330013275146484, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.60880970954895, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.6115596294403076, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.59192156791687, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.5690603256225586, "validation/loss_046_lr3.6e+01_wd1.0e+00": 2.5735130310058594, "validation/loss_047_lr4.3e+01_wd1.0e+00": 2.6051554679870605, "validation/loss_048_lr5.0e+01_wd1.0e+00": 2.6280462741851807, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.05795496493170912, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.05906238464377999, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.0592469545957918, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06016980435585087, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.059431524547803614, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06016980435585087, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.059431524547803614, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.060538944259874494, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.05906238464377999, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06164636397194537, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06256921373200443, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06423034330011074, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.062200073827980804, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06552233296419344, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06718346253229975, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.07032115171650055, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.07179771133259505, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.07216685123661867, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.07179771133259505, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.07438169066076043, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.07678110003691399, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.07401255075673681, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.06976744186046512, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.06109265411590993, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.055740125507567365, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.05278700627537837, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.052233296419342934, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.05149501661129568, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.053156146179401995, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.055740125507567365, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.06256921373200443, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.07438169066076043, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.07770394979697305, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.08176448874123293, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.08785529715762273, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.09542266519010704, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.11148025101513473, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.15042451088962716, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.1937984496124031, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.21059431524547803, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.21945367294204504, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.21926910299003322, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.21373200442967885, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.2351421188630491, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.2456626061277224, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.23661867847914358, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.22259136212624583, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.2115171650055371, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.009860472940031423, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.008451612004620856, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.008689386740065683, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.009810542568324407, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.010057787056013501, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.009841552554711403, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.010005622780224516, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.009737845383879075, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.009489075061336158, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.010013620480859723, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.010321129857956595, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.01092167098885774, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.0105389930964266, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.01148643125857874, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.012763115148450578, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.012365549432270253, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.012934515252913106, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.012707661579847027, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.012777961680583422, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.012762934854115412, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.01568848626783238, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.018418409040745674, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.018861048240085238, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.016484654044227172, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.013721411587956018, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.009578584372734544, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.006586556344538382, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.005851575961102649, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.0049342099660855164, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.0067456954844215865, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.008853704838623556, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.010570656251577638, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.014637484763074434, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.018252584164902885, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.022562871840055575, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.028075755673575693, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.032497147498187724, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.0517630128792629, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.08475985213354133, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.11428539875876265, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.12865413055149658, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.14006323493890202, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.14441295126443457, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.14686539121119643, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.17173990879448534, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.1679029459803483, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.15338482158529657, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.1422391419591298, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.1478410561265947, "id_best": 45, "lr_best": 0.0093, "wd_best": 0.05, "train/loss_best": 2.9689563751220702, "validation/loss_best": 2.5690603256225586, "validation/acc_best": 0.2456626061277224, "validation/f1_best": 0.1679029459803483} +{"epoch": 1, "train/lr": 8.993993993993998e-05, "train/loss": 2.9457748901844023, "train/grad": 0.18339259743690492, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.157545166015625, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.154552001953125, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.15017333984375, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.14657470703125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.14355224609375, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.140223388671875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.137294921875, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.134876708984375, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.132523193359375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.13075439453125, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.129635009765625, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.128466796875, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.127867431640625, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.127164306640625, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.12690673828125, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.126630859375, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.126329345703125, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.126025390625, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.125693359375, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.125299072265625, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.12473876953125, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.124249267578125, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.123489990234375, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.12265625, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.12169677734375, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.120352783203125, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.11833251953125, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.1152886962890625, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.104456787109375, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.067055511474609, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.0158935546875, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.966853561401367, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.9021123123168944, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.841647605895996, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.7731666946411133, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.7102231216430663, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.6532267570495605, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.6045246601104735, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.563815393447876, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.5353875064849856, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.5180295848846437, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.5060489845275877, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.502692255973816, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.507578773498535, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.5103482246398925, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.541293725967407, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.5738407659530638, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.6129177904129026, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.6629650568962098, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.021576287373900414, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.02133480930700898, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.02098947260528803, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.020706231854856014, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.020474940803833306, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.02021997920703143, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.020006949193775655, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.019838870973326265, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.019691799990832804, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.019596689413301647, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.019542447463609277, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.019503456787206233, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.019493448808789254, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.01950237259734422, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.019522599861957132, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.019544982155784964, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.019574250685982408, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.01960837163031101, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.019642283082939683, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.019672353751957417, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.01970530635211617, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.019732540170662106, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.01975420061033219, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.01975987180136144, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.01973659923300147, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.019658333528786896, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.01954455964267254, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.019422017708420752, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.01938373894430697, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.019975197040475904, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.020964348912239073, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.02191267191898078, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.02316713717300445, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.024167038039304315, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.02535544979851693, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.026635180679149925, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.027943129162304105, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.029197981068864464, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.030654791137203576, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.03213109276257455, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.033288334980607036, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.034639365803450346, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.036013864753767846, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0373317954223603, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.038043688097968695, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.03958909273147583, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.04215391971170902, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.044973012087866665, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.04959168527275324, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.141033411026001, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1375715732574463, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1331214904785156, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1299734115600586, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.127755641937256, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1257591247558594, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1244077682495117, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1235835552215576, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1230757236480713, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.12284779548645, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1227102279663086, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1224851608276367, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1222448348999023, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.121730089187622, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.121145248413086, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.120539426803589, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1197566986083984, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1189463138580322, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1182336807250977, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.1178064346313477, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.11752986907959, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.117461919784546, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.1175036430358887, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.1179134845733643, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.1185317039489746, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.1182501316070557, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.112905502319336, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.0940451622009277, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.001203775405884, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.792435884475708, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.699890375137329, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.653796434402466, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.5992138385772705, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.575239896774292, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.548464059829712, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.529799461364746, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.510842800140381, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.4724369049072266, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.4722464084625244, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.4471189975738525, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.4422826766967773, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.43873929977417, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.4716899394989014, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.5526185035705566, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.596839427947998, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.727097511291504, "validation/loss_046_lr3.6e+01_wd1.0e+00": 2.887535572052002, "validation/loss_047_lr4.3e+01_wd1.0e+00": 2.957646131515503, "validation/loss_048_lr5.0e+01_wd1.0e+00": 2.9078621864318848, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06201550387596899, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06459948320413436, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06478405315614617, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06441491325212255, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06256921373200443, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06275378368401624, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06275378368401624, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06459948320413436, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06459948320413436, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06404577334809892, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06459948320413436, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.0664451827242525, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06718346253229975, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.07013658176448874, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.07142857142857142, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.07235142118863049, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.07124400147655961, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.07216685123661867, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.073827980804725, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.07419712070874862, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.07511997046880768, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.07493540051679587, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.07733480989294943, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.08065706902916205, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.08859357696567, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.12366186784791436, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.16519010705057216, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.18549280177187155, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.19785898855666298, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.21834625322997417, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.22702104097452935, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.22554448135843486, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.2307124400147656, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.2397563676633444, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.25507567368032485, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.25544481358434845, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.25692137320044295, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.26541159099298633, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.26301218161683276, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.25655223329641935, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.24086378737541528, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.2334809892949428, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.21853082318198597, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.20025839793281655, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.19361387966039129, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.18512366186784793, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.00965493111180593, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.009577826522507805, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.008629142323161367, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.007688360693448173, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.005837328336147242, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.0061140652988454815, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.006354937046710393, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.007033017879984064, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.007709971461598172, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.007919334638246725, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.007759434815272533, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.008048101703801049, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.008967120610301998, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.010722293900270045, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.013033272167289283, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.013737987666131575, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.01564446463295324, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.01567081234075936, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.015915993300251157, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.014680685642301461, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.015038744677714114, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.016217464615638468, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.017069081175948197, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.016264378929339195, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.015607078555293688, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.015506248908461383, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.017222168633379418, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.023008098905418082, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.05223055111674566, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.08000559963897089, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.10364717170945183, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.11788309317604002, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.14438882641158415, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.15719004241197568, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.15871358040987732, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.1612635476919038, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.17095832559244975, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.18829014299509983, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.19200268312966476, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.196229473001466, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.19148666271204617, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.18831819122552848, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.18834559460902653, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.16362214288525267, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.1790974308534529, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.15448489479548191, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.12305899588216347, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.12798212074301926, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.13690009286547164, "id_best": 40, "lr_best": 0.0042, "wd_best": 0.05, "train/loss_best": 2.5180295848846437, "validation/loss_best": 2.4422826766967773, "validation/acc_best": 0.26541159099298633, "validation/f1_best": 0.19148666271204617} +{"epoch": 2, "train/lr": 0.00014999999999999988, "train/loss": 2.9182759857177736, "train/grad": 0.3536203806102276, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.13715576171875, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.135238037109375, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.133304443359375, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.1320751953125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.13155517578125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.13092529296875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.1306591796875, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.130474853515625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.130224609375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.129859619140625, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.12957763671875, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.129144287109375, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.128497314453125, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.127806396484375, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.12697265625, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.126295166015625, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.12537841796875, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.12414306640625, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.12276123046875, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.1213525390625, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.119268798828125, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.115919189453125, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.108138427734375, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.08352294921875, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.0250856018066408, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.929928436279297, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.839122428894043, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.7579780197143555, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.6577513122558596, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.5721279525756837, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.5178957271575926, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.4786662578582765, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.435000343322754, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.4009870052337647, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.367742862701416, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.3460826539993285, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.3351650071144103, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.325972971916199, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.3280691576004027, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.3413835191726684, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.353515133857727, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.35994695186615, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.3956013989448546, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.432283524274826, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.4803760147094724, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.5549337005615236, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.7528497803211214, "train/loss_047_lr4.3e+01_wd1.0e+00": 4.213093495368957, "train/loss_048_lr5.0e+01_wd1.0e+00": 5.783716205358505, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.01998488905373961, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.01983949840068817, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.019696819139644505, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.01962764445692301, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.019599138665944336, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.019593579792417586, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.019606563001871108, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.019625032278709112, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.019650045493617655, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.019674079869873823, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.0196939958864823, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.01971941037569195, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.01974142366554588, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.019767420040443538, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.01978687571827322, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.019802537551149725, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.019816647446714342, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.0198214264633134, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.01980959691107273, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.019779031989164652, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.019710652749054133, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.01960296164266765, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.019492998416535557, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.019733518133871256, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.020991965271532534, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.023109330497682094, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.024834735663607718, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.026299012238159777, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.02825031051412225, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.029855948369950057, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.030682493653148412, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.03132740711793303, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.03214677358977497, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.033066134909167884, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.033922489816322926, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.03477562682703137, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.035289833545684816, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.03611160962842405, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.03766431253403425, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.03922129034996033, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.040426342617720365, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.04168502446264029, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.044305280381813646, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.04656930610537529, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.049150234647095205, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.052807365525513884, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.06685365285724401, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.12978852851316333, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.11966450726613402, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1258835792541504, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1247057914733887, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1236298084259033, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.123166799545288, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.122957468032837, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1227426528930664, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.122619390487671, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1224911212921143, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.122295618057251, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1221413612365723, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.121985673904419, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1218175888061523, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1216835975646973, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.121490955352783, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.121227741241455, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.120832681655884, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.119997501373291, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1183979511260986, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1156890392303467, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.1120667457580566, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.1053974628448486, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.0924198627471924, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.0504047870635986, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.9060213565826416, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.7255403995513916, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.631197214126587, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.581031322479248, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.5400543212890625, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.493124008178711, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.4503941535949707, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.426631450653076, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.4193689823150635, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.4188170433044434, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.4162817001342773, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.423762321472168, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.4632956981658936, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.4935288429260254, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.484339714050293, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.48720383644104, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.4933183193206787, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.510042905807495, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.522312879562378, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.6073927879333496, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.6004557609558105, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.674717664718628, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.8653531074523926, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.5985004901885986, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06275378368401624, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06404577334809892, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06552233296419344, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06718346253229975, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.0664451827242525, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06736803248431156, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06755260243632337, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06884459210040605, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.0695828719084533, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06995201181247693, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06995201181247693, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06866002214839424, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.0681063122923588, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06773717238833518, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.0681063122923588, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.0664451827242525, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06607604282022887, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06699889258028793, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06736803248431156, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.06976744186046512, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.07511997046880768, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.08213362864525656, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.10225175341454411, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.1491325212255445, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.18955334071613142, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.2174234034699151, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.23237356958287192, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.24732373569582872, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.2567368032484312, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.2676264304171281, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.2722406792174234, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.2731635289774825, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.268733850129199, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.2705795496493171, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.2724252491694352, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.26393503137689184, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.2552602436323367, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.2532299741602067, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.2552602436323367, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.25507567368032485, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.2482465854558878, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.24289405684754523, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.23864894795127353, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.23569582871908454, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.22388335179032853, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.2201919527500923, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.1878922111480251, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.006861558695964984, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.007232475256385898, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.008949588024304017, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.00953312041023171, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.009441645631784177, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.010231922790263552, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.010314456743898573, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.011442503823687068, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.01226132312574512, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.013015169803875659, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.013089921895409813, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.012692933362016719, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.012578889853511315, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.012272202657851727, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.01211912944327012, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.01105688343582526, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.010598911151005232, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.01067820061776361, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.01081476869190706, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.0134641119234833, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.016449336340743737, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.019149323757058988, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.03054221699524623, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.06426322993188607, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.0976828699532853, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.1351749302151509, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.15133508879194565, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.16778498461129784, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.17900829489609607, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.18715862531789718, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.18909814790954838, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.19198554686222247, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.19515157016163528, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.20105790120701802, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.20674030414511532, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.19748084304476907, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.18862242603269533, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.19411724294242463, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.2036731500694069, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.20260676864971638, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.19621550014674694, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.18450145215125427, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.17643341200254561, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.17204882724693607, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.16154767989584196, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.1467953417590476, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.12534645516966791, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 31, "lr_best": 0.0009299999999999999, "wd_best": 0.05, "train/loss_best": 2.4786662578582765, "validation/loss_best": 2.4193689823150635, "validation/acc_best": 0.2731635289774825, "validation/f1_best": 0.19198554686222247} +{"epoch": 3, "train/lr": 0.0002100600600600602, "train/loss": 2.8837325274944305, "train/grad": 0.41031350575387476, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.129344482421875, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.128798828125, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.128341064453125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.127977294921875, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.127711181640625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.127281494140625, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.126751708984375, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.12623779296875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.125538330078125, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.124815673828125, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.124044189453125, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.123057861328125, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.121837158203125, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.12017822265625, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.118565673828125, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.116810302734375, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.11444091796875, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.110545654296875, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.10272705078125, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.083697509765625, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.0192294311523438, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.9137054443359376, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.7900012969970702, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.6763721466064454, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.590613479614258, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.5218356704711913, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.4731983184814452, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.4336427879333495, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.3860370540618896, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.335639533996582, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.3023317432403565, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.2793508434295653, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.255123662948608, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.239196727275848, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.234539804458618, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.229268968105316, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.2408861196041108, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.2572770977020262, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.2671651232242582, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.3056606566905975, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.344170768260956, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.3847861874103544, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.458244054317474, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.5144475305080416, "train/loss_044_lr2.6e+01_wd1.0e+00": 5.94891816496849, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.750882028341293, "train/loss_046_lr3.6e+01_wd1.0e+00": 4.397918939590454, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.019503843737766147, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.019505469063296914, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.019523826222866775, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.019544932334683837, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.019562294981442394, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.01958274288568646, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.019599393126554787, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.01961647699121386, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.01963470350485295, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.019650693857111035, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.01966399629134685, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.0196788630541414, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.019687977908179163, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.01968888650648296, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.019679942387156188, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.019656068761833012, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.01960758838802576, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.019521225984208287, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.019411133881658316, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.019513445533812047, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.020680251843295992, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.023080538348294793, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.025897717382758857, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.028251276249065996, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.02974283787421882, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.03041809213347733, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.031119761718437076, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.03183248438872397, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0327172711212188, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.03410284840501845, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.034996142331510785, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.03578835868276656, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.036910643307492136, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.037867760267108676, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.038688160190358756, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0394694974925369, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.04049727192148566, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.04141893347725272, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.042833148799836636, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.04484578425064683, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.046428076550364496, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.04984356869012117, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.05364634055644274, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.056023936960846184, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.16213073758408428, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.10085739651694894, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.06415545698255301, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.122817277908325, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.122530698776245, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.122182846069336, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.12185001373291, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1214873790740967, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1209640502929688, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1203207969665527, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1195805072784424, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.118603467941284, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.117563247680664, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.116530656814575, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.115028142929077, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1135711669921875, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1115574836730957, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1096785068511963, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1076478958129883, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1043105125427246, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.0968308448791504, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.0709519386291504, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.9850871562957764, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.789844036102295, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.6794371604919434, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.613255739212036, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.562814950942993, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.5243594646453857, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.4855599403381348, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.460571050643921, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.4467759132385254, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.4449374675750732, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.4352352619171143, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.418816566467285, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.4216673374176025, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.410710573196411, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.444732189178467, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.502624273300171, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.5544254779815674, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.639808416366577, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.5873780250549316, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.6267173290252686, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.6396701335906982, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.5648391246795654, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.6071221828460693, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.717139959335327, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.740939140319824, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.0664451827242525, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06718346253229975, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06829088224437062, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.067921742340347, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.0681063122923588, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06976744186046512, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.07050572166851236, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.0710594315245478, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.07124400147655961, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.07087486157253599, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.07069029162052418, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.07308970099667775, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.07401255075673681, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.07659653008490218, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.0769656699889258, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.07622739018087855, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.0769656699889258, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.08157991878922112, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.09634551495016612, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.12919896640826872, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.17220376522702105, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.19730527870062753, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.2131782945736434, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.2201919527500923, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.23717238833517904, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.24880029531192321, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.2532299741602067, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.26153562200073827, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.2619047619047619, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.2672572905131045, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.2646733111849391, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.266703580657069, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.2713178294573643, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.2676264304171281, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.2572905131044666, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.24492432631967515, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.23237356958287192, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.24031007751937986, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.23292727943890734, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.2294204503506829, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.24529346622369877, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.2425249169435216, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.2334809892949428, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.2277593207825766, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.009576190912152796, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.009850788627386996, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.010450543962062823, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.010146553998171689, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.010131517695939096, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.010720856042392627, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.010782672999439023, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.0114470678158136, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.011547073402783195, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.011826966615373921, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.012046211992413255, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.014208198608273942, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.017767074445889163, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.02125481669823126, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.022828848915957184, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.022560651917940683, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.02426745982397807, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.029600307612718344, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.04474923698267456, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.0683671266877409, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.0992230467470484, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.12348354037987126, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.13778520841849715, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.14469014217189954, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.16406774890428197, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.18207126939054194, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.18926837391125817, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.2000870799635346, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.19900254390683647, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.20329707758292015, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.19766315991590908, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.19932908883292896, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.19978667028957586, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.18846131215913622, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.18546724953002333, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.1836300137229795, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.17612256149144645, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.18272839416924133, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.18230793376451723, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.17449226847203006, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.19104153643899804, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.18336878887205288, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.1763153308305244, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.1729936368530032, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 32, "lr_best": 0.0011099999999999999, "wd_best": 0.05, "train/loss_best": 2.255123662948608, "validation/loss_best": 2.410710573196411, "validation/acc_best": 0.2713178294573643, "validation/f1_best": 0.19978667028957586} +{"epoch": 4, "train/lr": 0.0002701201201201201, "train/loss": 2.780932890176773, "train/grad": 0.3081179868429899, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.13103759765625, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.130828857421875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.13028564453125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.12966552734375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.129161376953125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.12844970703125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.127564697265625, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.126619873046875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.12533447265625, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.124073486328125, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.122894287109375, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.12092529296875, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.119005126953125, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.1157763671875, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.11167724609375, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.1055230712890625, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.0872320556640624, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.020162353515625, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.889006805419922, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.7642348480224608, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.650436019897461, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.575904998779297, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.5100877189636233, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.451265125274658, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.3998896980285647, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.3512239170074465, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.312204809188843, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.280190305709839, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.242019214630127, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.2056002378463746, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.184219298362732, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.1669794130325317, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.153689181804657, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.1480672335624695, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.1521552872657774, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.1645417380332947, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.1907344925403596, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.2278224658966064, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.2657071459293365, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.3230055141448975, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.402968374490738, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.4793955743312837, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.5649907141923904, "train/loss_043_lr2.2e+01_wd1.0e+00": 5.263781955242157, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.019340993743389844, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.019353960934095086, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.019369188714772462, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.019379585850983858, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.019387824232690035, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.019398761126212777, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.01940849549137056, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.01941842583939433, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.01942885076161474, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.019435501522384584, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.019438314284197986, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.01943324327468872, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.01941539069171995, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.019365191776305437, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.019284980725497006, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.01919052004814148, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.019215236781165004, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.020270518944598734, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.023197530368342996, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.02617382727563381, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.028669940400868656, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.029829836757853626, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.03051219037733972, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.03124453974887729, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.03211070072837174, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.03308408480137587, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.03399366880767048, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.034668152835220095, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.03570681777782738, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.036955817323178056, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.03759284058585763, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.03817563503049314, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.03935262890532613, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0403477049805224, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.041607784684747455, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.04276458583772182, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.04333994438871741, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0444060892239213, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.04668252119794488, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.049190296828746795, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.054508886002004146, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.05962873715907335, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.06345238098874688, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.15114476408809424, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1230885982513428, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.122987747192383, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.122790813446045, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1225123405456543, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.122232437133789, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1217451095581055, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1211345195770264, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1203620433807373, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1191914081573486, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.117767810821533, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1162455081939697, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1137959957122803, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1111416816711426, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1063649654388428, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.0990395545959473, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.0835163593292236, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.01826548576355, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.8291172981262207, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.686328887939453, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.619774580001831, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.5716657638549805, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.545116424560547, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.520224094390869, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.4735982418060303, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.433683156967163, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.415363073348999, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.4172756671905518, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.4157209396362305, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.4092490673065186, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.4319002628326416, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.4126358032226562, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.42942214012146, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.5116562843322754, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.5336124897003174, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.5304622650146484, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.5804922580718994, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.6150474548339844, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.641545295715332, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.7325730323791504, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.842782735824585, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.8757007122039795, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.925008773803711, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.9107232093811035, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06423034330011074, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06423034330011074, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06423034330011074, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06423034330011074, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06478405315614617, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06552233296419344, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06662975267626431, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.0681063122923588, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06847545219638243, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.0725359911406423, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.07345884090070137, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.07788851974898486, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.08176448874123293, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.09154669619785899, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.11812476928755998, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.16168327796234774, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.19564414913252123, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.21354743447766703, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.2320044296788483, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.2368032484311554, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.24640088593576967, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.2541528239202658, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.26836471022517533, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.2748246585455888, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.27353266888150607, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.2766703580657069, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.27500922849760057, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.2713178294573643, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.2691029900332226, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.268733850129199, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.25452196382428943, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.24953857511997046, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.25396825396825395, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.2454780361757106, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.2397563676633444, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.24492432631967515, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.22296050203026946, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.22535991140642303, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.2203765227021041, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.20025839793281655, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.21114802510151348, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.007576060070126577, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.00725374423116712, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.007679435097576427, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.00820174495136341, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.008643263908629807, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.009068555623124289, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.010158803751095825, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.011360102122721727, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.011996353237117759, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.013880256767745241, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.014872637094079752, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.01800597701389421, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.019002843436702856, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.02095416791145747, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.025249060591053515, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.034382891075045684, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.05263824242051481, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.08962347335041017, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.12236566734634802, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.1395120270223544, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.15819457203548, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.1660950695958616, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.17573953999075617, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.18523750910390302, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.19890639111869315, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.20403627861237697, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.20677974566223864, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.21333257097525093, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.2199329256208594, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.2199361878347836, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.22054167784930853, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.21852698113320582, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.19758455741191483, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.19146386478173827, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.2000671527856339, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.1889399444037355, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.18391485399464502, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.1770886941505807, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.16849050641652089, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.16300467381350384, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.16396002689579775, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.15543948219215456, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.1626256219403972, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 27, "lr_best": 0.00047999999999999996, "wd_best": 0.05, "train/loss_best": 2.280190305709839, "validation/loss_best": 2.4157209396362305, "validation/acc_best": 0.2766703580657069, "validation/f1_best": 0.21333257097525093} +{"epoch": 5, "train/lr": 0.00029891323817685334, "train/loss": 2.6476878261566164, "train/grad": 0.23001759745180606, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.122724609375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.122203369140625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.121455078125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.12066650390625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.119893798828125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.118912353515625, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.117578125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.11634765625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.114622802734375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.1127490234375, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.1108349609375, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.107481689453125, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.103402099609375, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.092288818359375, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.05998779296875, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.9768817138671877, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.8203179931640623, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.6727684783935546, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.5793582153320314, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.515077495574951, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.4526858711242676, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.397329921722412, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.337738609313965, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.283970413208008, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.235842270851135, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.191376075744629, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.156997220516205, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.1261202836036683, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.089252603054047, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.060521638393402, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.051681001186371, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.04483541727066, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.0340670228004454, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.037996480464935, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.056257268190384, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.091080051660538, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.1088781613111496, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.144155932664871, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.172722418308258, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.244135992527008, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.312153497934341, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.3962184309959413, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.4538872146606447, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.171875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.019604894816875457, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.019614970767870544, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.019629776924848557, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.019644510447978974, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.019656414445489646, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.01967141788918525, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.019685510084964334, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.019696111236698927, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.019706364371813834, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.019707385492511095, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.019698697733692826, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.01966881311032921, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.019616097840480507, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.019541357206180693, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.019854844156652687, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.02137994486372918, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.024882814772427084, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.02825131680816412, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.029776394432410598, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.0306215625628829, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.03144451905041933, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.03224912509322166, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.03341675788164139, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.03450152074918151, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.03534567633643746, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.03602367130108178, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.036837058020755646, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0374915200471878, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.03803773381747305, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.038920938801020384, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.03979043750092387, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.04096914265304804, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.04223501391708851, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.043441499061882494, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.045075469482690096, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.04685420569032431, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.04739457694813609, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.04790813598781824, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.04814415648579597, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0504515360109508, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.05344690570607782, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.05770844586193562, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.059682541079819205, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.12066912651062, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1201038360595703, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1191565990448, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1182620525360107, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.117391586303711, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1161818504333496, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.114858388900757, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1133642196655273, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.111377239227295, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1091182231903076, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.106692314147949, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.102029323577881, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.0951058864593506, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.0698554515838623, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.9792559146881104, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.8099489212036133, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.674276828765869, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.598184108734131, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.543341875076294, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.505946159362793, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.4786107540130615, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.452650785446167, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.4285333156585693, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.4075734615325928, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.3884353637695312, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.3789560794830322, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.3919529914855957, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.4502761363983154, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.495610475540161, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.4919252395629883, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.484408378601074, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.515617847442627, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.560678720474243, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.563258171081543, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.627718687057495, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.696664333343506, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.693589448928833, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.7340400218963623, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.7043826580047607, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.7965428829193115, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.812166929244995, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.845214366912842, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.9014384746551514, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06478405315614617, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06441491325212255, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06423034330011074, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06441491325212255, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06423034330011074, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06404577334809892, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06496862310815799, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06552233296419344, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06626061277224068, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06939830195644149, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.07069029162052418, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.07475083056478406, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.08065706902916205, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.09671465485418974, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.12993724621631597, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.16315983757844224, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.19619785898855666, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.21650055370985605, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.2355112587670727, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.2456626061277224, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.2513842746400886, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.26301218161683276, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.2713178294573643, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.28054632705795496, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.2838685861941676, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.28202288667404946, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.2822074566260613, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.2703949796973053, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.2633813215208564, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.26393503137689184, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.26504245108896274, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.2622739018087855, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.2561830933923957, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.25692137320044295, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.24363233665559247, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.2369878183831672, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.2279438907345884, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.21483942414174972, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.22535991140642303, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.2081949058693245, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.21262458471760798, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.2041343669250646, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.2041343669250646, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.007873207404023528, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.007698058310886521, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.007540389890353408, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.007704579772132062, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.007503432322684189, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.0073676619761084165, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.00819942476282383, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.009000436750686252, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.009753126141966502, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.01188921501273125, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.012844803091260746, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.015067151492165039, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.019873297948576285, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.0339802413704526, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.058357079685938375, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.08356981846727672, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.11263433654590045, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.1344470461000033, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.15677585485582943, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.1686899000477934, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.1768265205766121, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.18992115910081508, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.19950743097651266, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.20704705032612222, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.21298679604051327, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.21497365440444108, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.21947208415300257, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.20643826136422505, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.2003905373573829, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.20776241383461272, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.21345450979295824, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.2104905755088312, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.19900723719824334, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.19524135061861517, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.18801237610611085, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.17882452626488946, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.1892909182151092, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.17732717556512714, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.1844725955639945, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.1775910190445944, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.18114472019595892, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.1640349201764904, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.17350712186640624, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 24, "lr_best": 0.0003, "wd_best": 0.05, "train/loss_best": 2.235842270851135, "validation/loss_best": 2.3884353637695312, "validation/acc_best": 0.2838685861941676, "validation/f1_best": 0.21298679604051327} +{"epoch": 6, "train/lr": 0.0002924170901991409, "train/loss": 2.5837111377716067, "train/grad": 0.23926855325698854, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.127520751953125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.1268017578125, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.12571533203125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.124622802734375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.123389892578125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.12188720703125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.120216064453125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.118319091796875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.115731201171875, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.112774658203125, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.1094677734375, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.1022747802734374, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.0874310302734376, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.0113296508789062, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.846457824707031, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.7112356567382814, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.612589111328125, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.5328193283081055, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.462695293426514, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.4076022148132323, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.347826442718506, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.2884632682800294, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.226110134124756, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.1707402801513673, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.122730836868286, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.0795950365066527, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.0450060844421385, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.012564150094986, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.9794904470443726, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.9594289481639862, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.9530064737796784, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.945218541622162, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.9387814444303513, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.9512686622142792, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.969627122282982, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.998505095243454, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.049818867444992, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.1009828078746797, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.1479596972465513, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.207312232851982, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.271531066298485, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.313597080111504, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.39015118598938, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.171875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.019583964869379997, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.01958844891283661, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.01959300593007356, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.01959624561481178, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.019597650938667357, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.01959837870206684, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.019595559779554607, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.01958710968028754, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.019566528419964015, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.019531494937837124, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.019480086374096574, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.019378615971654654, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.01933976511005312, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.020461077773943542, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.02402243128977716, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.02722844888456166, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.0293793117441237, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.030537155205383897, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.031500865221023557, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.032241982808336615, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.03327498284168542, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.03442022675648332, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.03550063584931195, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.03646003509871662, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.037277111914008856, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.03796480689197779, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.03891234891489148, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.039592682160437105, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.040251883827149865, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.041044172439724205, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.04135587800294161, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0423071676120162, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.04426921544596553, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.04535609437152743, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.046462647002190355, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.04750570027157664, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.048948712497949604, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.05001850720494985, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.051508319880813364, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0535293510183692, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.055265267565846446, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.056404585298150775, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.059525145459920166, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.119744062423706, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1191210746765137, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.118119478225708, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1171770095825195, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1162631511688232, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1150028705596924, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1135761737823486, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1118814945220947, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1094706058502197, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.106323719024658, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.10209059715271, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.090153694152832, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.057011842727661, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.8854434490203857, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.7029569149017334, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.6192073822021484, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.5544631481170654, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.499023914337158, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.462148427963257, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.437135696411133, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.4084856510162354, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.3954458236694336, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.4009766578674316, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.407615900039673, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.417748212814331, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.4433834552764893, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.474975347518921, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.5215413570404053, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.5593018531799316, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.5657429695129395, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.5499391555786133, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.576327085494995, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.678986072540283, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.704150676727295, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.719593048095703, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.724928617477417, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.6522114276885986, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.677246332168579, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.7001099586486816, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.7474687099456787, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.707693576812744, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.7429912090301514, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.783926010131836, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06718346253229975, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06755260243632337, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06699889258028793, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06736803248431156, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06755260243632337, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06939830195644149, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.07013658176448874, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.07124400147655961, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.0725359911406423, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.07567368032484312, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.08028792912513842, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.08951642672572906, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.10538944259874493, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.14987080103359174, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.19306016980435586, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.21705426356589147, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.2382798080472499, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.25249169435215946, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.26153562200073827, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.268733850129199, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.27740863787375414, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.28460686600221485, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.28165374677002586, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.2766703580657069, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.2707641196013289, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.2631967515688446, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.26153562200073827, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.26005906238464377, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.25599852344038393, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.26135105204872644, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.26504245108896274, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.25489110372831303, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.24326319675156885, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.24197120708748615, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.2364341085271318, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.22739018087855298, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.2456626061277224, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.24732373569582872, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.23015873015873015, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.2279438907345884, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.2484311554078996, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.23735695828719083, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.23735695828719083, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.009139333265602246, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.009703232139805574, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.009612685484382525, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.010594483022600307, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.01104360826805825, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.012281084302691014, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.01331312682702355, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.014797292678224286, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.017858513557974198, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.02179698335956048, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.02642286787500246, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.03367010432787203, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.043270705773030604, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.07291264251099631, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.11200198460169575, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.1388387385932566, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.16174463651828794, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.17805571239636767, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.19062452547872144, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.2005296464585649, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.21083213444666948, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.21909736154722384, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.22004458968577112, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.21761999897600712, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.21534951674884648, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.20856589703358455, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.20892959557080173, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.20592637688581203, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.20091468111601207, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.21016378800343913, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.21436803776125246, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.20432175234926975, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.19141379377842113, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.1867030668369302, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.1789340102250915, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.1836370134241079, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.1991664458968692, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.1897121248325253, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.1919777575221909, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.17942794288713557, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.18755404621734398, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.19626268302258776, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.19605065757114568, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 21, "lr_best": 0.00018299999999999998, "wd_best": 0.05, "train/loss_best": 2.2884632682800294, "validation/loss_best": 2.3954458236694336, "validation/acc_best": 0.28460686600221485, "validation/f1_best": 0.21909736154722384} +{"epoch": 7, "train/lr": 0.00027969249556793234, "train/loss": 2.5050749838352204, "train/grad": 0.24583825707435608, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.125133056640625, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.124251708984375, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.122696533203125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.121292724609375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.11989501953125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.1178564453125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.115615234375, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.11299072265625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.109130859375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.10412353515625, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.0969012451171873, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.0722998046875, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.996153564453125, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.7783665466308594, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.6432679748535155, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.567889633178711, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.491712417602539, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.4189652252197265, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.3503731155395506, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.2915809249877928, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.2293821716308595, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.1707416725158692, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.107285566329956, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.0515552234649657, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.003570966720581, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.959478771686554, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.9232072114944458, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.8944718790054322, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.8647772479057312, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.8469107937812805, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.84365917801857, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.8341857439279556, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.8318422985076905, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.8378023546934128, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.8534413450956344, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.8770909643173217, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.9170246958732604, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.9668735986948014, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.0396333003044127, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.1160213738679885, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.167592340707779, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.207020807266235, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.2933608174324034, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.171875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.019112243833951652, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.01911518005654216, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.01911985048558563, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.019120178357698022, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.019118048446252943, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.019112478662282228, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.019100345806218683, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.019078821181319653, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.01903967371676117, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.01897641027811915, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.018905201642774046, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.01895532143767923, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.020106240957975387, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.024780041314661504, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.028102889889851213, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.02936333649791777, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.03051530701108277, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.03162566471844912, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.03253357119858265, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.03361641152761877, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.03478695859201252, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.0358163545653224, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.036944594578817484, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.03803057937882841, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.03891570573672652, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.039705963004380465, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.040797944832593205, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.041642877385020254, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.04277949934825301, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.04421045722439885, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.044744143653661014, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.04506533972918987, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.04663967274129391, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.04718784295022488, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.047793725840747356, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.04859252389520407, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.04897713117301464, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.049619283452630045, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.05196469776332378, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.053568492103368046, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.05511268967762589, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.056041538733989, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.05965726617723703, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1190989017486572, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.118450403213501, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.11737060546875, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1163079738616943, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1152539253234863, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1137845516204834, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.112048387527466, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.109957218170166, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1065726280212402, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.101184606552124, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.0913491249084473, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.046269655227661, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.9078357219696045, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.6947944164276123, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.6026558876037598, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.5456295013427734, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.4936234951019287, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.453991651535034, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.4247844219207764, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.40586256980896, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.39434814453125, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.391540288925171, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.4086334705352783, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.4277052879333496, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.449315071105957, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.4666335582733154, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.482712984085083, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.5227677822113037, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.5891189575195312, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.651318311691284, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.6607799530029297, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.664788007736206, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.6497819423675537, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.6659739017486572, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.6604208946228027, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.662041664123535, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.6228368282318115, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.6932806968688965, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.698211193084717, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.7341907024383545, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.7272651195526123, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.8124959468841553, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.8933911323547363, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06755260243632337, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06773717238833518, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06718346253229975, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06773717238833518, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06995201181247693, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.07161314138058324, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.0753045404208195, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.07604282022886674, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.07862679955703211, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.08139534883720931, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.08564045773348099, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.1079734219269103, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.15337763012181616, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.20007382798080472, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.2220376522702104, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.23754152823920266, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.25212255444813586, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.26116648209671467, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.2691029900332226, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.27500922849760057, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.27464008859357697, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.2748246585455888, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.2731635289774825, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.2713178294573643, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.2707641196013289, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.271686969361388, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.27113325950535255, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.26504245108896274, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.25987449243263194, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.2589516426725729, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.2513842746400886, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.24861572535991142, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.24769287559985234, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.24953857511997046, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.25230712440014763, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.25341454411221853, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.2558139534883721, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.257844222960502, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.2633813215208564, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.24640088593576967, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.24049464747139165, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.24473975636766335, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.22997416020671835, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.010838501159995753, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.011616024612877737, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.011364250568295, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.011863596151620567, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.013716255299882804, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.015508332771829787, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.017381938784084266, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.01815713475442152, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.018988977076539185, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.019080040832123335, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.020788418462192225, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.037839432345448766, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.06869371263631159, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.11727500631610432, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.14199300446818766, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.1573609601703619, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.17577852405695318, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.1915706341249095, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.20168917576958156, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.21027169520600622, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.2140172362282545, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.21775199374619714, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.21492173617486557, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.21734093279187197, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.2189054410235425, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.22454779989848114, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.22703159179350121, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.21907644628960563, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.21068357129007972, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.212962690871748, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.20644380094057846, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.20979396865534042, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.21076891074832027, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.21263229129650438, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.2035915143455447, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.20535682327208227, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.214987727482689, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.2047688399151307, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.19960262340581889, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.19264392382695142, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.1919719385047093, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.18367159119779322, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.17019357759274623, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 19, "lr_best": 0.00013199999999999998, "wd_best": 0.05, "train/loss_best": 2.2915809249877928, "validation/loss_best": 2.40586256980896, "validation/acc_best": 0.27500922849760057, "validation/f1_best": 0.21027169520600622} +{"epoch": 8, "train/lr": 0.0002612959497061927, "train/loss": 2.4398452389240264, "train/grad": 0.2542640718817711, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.121151123046875, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.120135498046875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.1184619140625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.116837158203125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.115201416015625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.112974853515625, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.110357666015625, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.107066650390625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.10168701171875, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.0930133056640625, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.0752691650390624, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.9904440307617186, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.8147346496582033, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.640855560302734, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.553550796508789, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.4873651885986328, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.420193786621094, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.3530146217346193, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.283960123062134, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.225619258880615, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.1623004245758057, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.1007808351516726, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.031075882911682, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.9687331652641296, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.9145918941497804, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.8627017986774446, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.8221112287044525, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.7962674790620803, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.7584246295690535, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.7361511087417603, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.7344123297929763, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.7267039132118225, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.7134728610515595, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.7283247959613801, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.7378457260131837, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.7669218677282332, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.8078709018230439, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.8660067486763001, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.923822969198227, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.004238284230232, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.0631916427612307, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.131761094927788, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.201564012169838, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.171875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.01975416960194707, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.019758147592656313, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.019763428163714708, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.019765536072663962, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.01976504516787827, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.01975565983913839, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.019740132126025857, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.019711091401986777, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.01965354508254677, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.019575956212356686, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.019588397620245813, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.020780934933573008, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.02438487099483609, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.02894363165833056, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.030656230486929417, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.0315127423312515, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.03258323316462338, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.033546487698331476, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.03473089714534581, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.035663729980587956, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.03656014312058687, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.037467970689758656, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.03860943347215653, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.039644093494862316, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.040563226379454136, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.04161076802760363, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.04286174835637212, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.04378159806132317, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.04477421229705215, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.04555606469511986, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.04601181633770466, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.047184294797480104, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.048600647393614055, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.04925261816009879, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.049465127605944875, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.05001814277842641, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.050254879109561446, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.05082088887691498, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.05183249205350876, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.05374264199286699, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.05422931883484125, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.05700273001566529, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.058711555935442444, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1184659004211426, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1176114082336426, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1161949634552, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1147701740264893, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1133415699005127, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.111281156539917, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1087405681610107, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.105442523956299, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.0993192195892334, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.087188482284546, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.057777166366577, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.9177749156951904, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.736131429672241, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.6130292415618896, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.54958176612854, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.5080204010009766, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.474323034286499, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.451091766357422, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.4365622997283936, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.4326226711273193, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.436943531036377, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.4588892459869385, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.4911389350891113, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.517133951187134, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.546053886413574, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.5889081954956055, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.6056013107299805, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.6465179920196533, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.6837263107299805, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.743504762649536, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.734936475753784, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.7766191959381104, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.8086602687835693, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.8648345470428467, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.8894174098968506, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.880896806716919, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.884003162384033, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.92118501663208, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.9808943271636963, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.9381325244903564, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.882300615310669, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.9760193824768066, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.9631011486053467, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.0664451827242525, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06662975267626431, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06902916205241787, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.0710594315245478, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.07364341085271318, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.07585825027685493, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.07715023994093761, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.08194905869324474, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.08748615725359911, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.09376153562200074, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.11092654115909929, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.14230343300110743, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.18014027316352899, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.21520856404577335, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.23089700996677742, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.24363233665559247, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.25249169435215946, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.257844222960502, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.2661498708010336, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.26891842008121075, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.26799557032115173, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.26707272056109266, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.26005906238464377, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.2502768549280177, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.2515688445921004, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.2484311554078996, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.25101513473606496, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.2427094868955334, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.24307862679955702, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.23920265780730898, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.24935400516795866, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.24510889627168697, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.24326319675156885, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.23772609819121446, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.2307124400147656, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.23274270948689554, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.2334809892949428, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.2353266888150609, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.2277593207825766, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.22720561092654115, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.22757475083056478, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.23145071982281284, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.2081949058693245, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.009171957641143149, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.009471552325188254, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.012152642114494615, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.014356590400024962, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.016595089842532183, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.018097475717470477, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.019146031585113105, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.022669566856677714, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.02679240905248965, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.03371885083307238, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.04860447551642936, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.06704891671610584, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.1027967073190324, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.13875230621304258, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.1583916060552035, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.17248128273231925, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.1861674132600016, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.1942837451732572, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.20561652710987474, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.2087959415129539, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.20969880521576567, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.21220496595631314, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.20794986190884926, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.19932296102817548, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.19781322339859672, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.19477702325339416, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.20025205375936705, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.19772091176807038, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.19565330544365703, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.19250894336153446, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.2000035646082768, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.19045518463350244, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.18968914861825095, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.1841334469668218, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.17107053474708836, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.17365599691246672, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.17882876714401863, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.17719202049564461, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.17316947130257968, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.17481468320626226, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.17846481514126622, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.16895653200589192, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.16030711539645032, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 19, "lr_best": 0.00013199999999999998, "wd_best": 0.05, "train/loss_best": 2.225619258880615, "validation/loss_best": 2.4326226711273193, "validation/acc_best": 0.26891842008121075, "validation/f1_best": 0.2087959415129539} +{"epoch": 9, "train/lr": 0.00023803200426111704, "train/loss": 2.392224349975586, "train/grad": 0.25918855890631676, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.118756103515625, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.11756103515625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.11564697265625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.11369140625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.111614990234375, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.108870849609375, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.10541015625, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.1009619140625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.092783203125, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.0755108642578124, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.0300872802734373, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.8536245727539065, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.692885284423828, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.575144500732422, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.4971923446655273, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.43666862487793, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.371838150024414, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.29960075378418, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.228964915275574, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.1691708946228028, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.104782066345215, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.041478214263916, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.9713784098625182, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.906117160320282, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.8499043571949005, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.795402356982231, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.750137533545494, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.7167482852935791, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.672078157067299, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.650987394452095, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.648623869419098, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.637821695804596, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.6177839970588683, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.6324257254600525, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.646280080676079, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.6896434926986694, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.7405257946252823, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.807130094766617, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.8653067725896835, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.9563169991970062, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.0254619574546813, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.0953093814849852, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.1501163762807844, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.171875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.01965069561265409, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.019651785767637195, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.01965185795444995, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.019648715532384814, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.01964284457266331, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.019627069197595118, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.01960018602665514, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.01955510802101344, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.019481869302690028, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.01946232412941754, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.019969009915366768, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.023274583080783486, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.02748020480386913, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.030204877434298397, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.03137456415221095, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.03214019584469497, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.03303877403959632, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.03428580517880619, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.035544078452512624, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.03643901949748397, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.03739851286634803, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.03833608060143888, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.039538232181221246, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.040738863833248616, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.04175550019368529, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.04290077578276396, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.043935083262622354, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.04458880415186286, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.04567400135099888, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.046901202946901324, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.047501845080405475, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.048317540623247626, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.049232260920107365, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.05017402023077011, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.05101034961640835, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.05171686055138707, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.05178106226027012, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.05202137317508459, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0530910368822515, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.05447778463363648, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.05500715170055628, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.056928351428359746, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.05716843796893954, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1175003051757812, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1165356636047363, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.114956855773926, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1134092807769775, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1117961406707764, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1094279289245605, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.106294870376587, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1018407344818115, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.091937780380249, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.0665674209594727, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.994234561920166, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.7827446460723877, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.6553049087524414, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.5654780864715576, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.512305736541748, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.4784629344940186, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.4511232376098633, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.421224594116211, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.400148868560791, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.3900675773620605, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.394817352294922, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.4153525829315186, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.440178155899048, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.459643602371216, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.4958879947662354, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.5389554500579834, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.575220823287964, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.633692979812622, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.6411373615264893, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.7112433910369873, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.7229254245758057, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.7260141372680664, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.783792495727539, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.8552331924438477, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.8713533878326416, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.8968029022216797, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.918257236480713, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.8884425163269043, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.9235591888427734, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.8963708877563477, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.815737724304199, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.8115828037261963, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.7712528705596924, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.0681063122923588, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.0695828719084533, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.0710594315245478, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.07142857142857142, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.07456626061277224, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.07751937984496124, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.08028792912513842, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.08342561830933924, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.08785529715762273, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.10243632336655592, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.1343669250645995, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.16925064599483206, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.20228866740494647, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.22739018087855298, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.24529346622369877, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.2576596530084902, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.26098191214470284, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.26947212993724623, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.27556293835363604, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.27500922849760057, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.2705795496493171, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.26891842008121075, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.2617201919527501, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.26098191214470284, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.2593207825765965, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.2556293835363603, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.2499077150239941, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.24510889627168697, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.24510889627168697, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.23791066814322628, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.24049464747139165, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.24012550756736803, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.2369878183831672, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.2336655592469546, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.22831303063861202, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.2321889996308601, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.23145071982281284, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.2349575489110373, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.23458840900701367, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.23329641934293097, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.2277593207825766, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.23274270948689554, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.2249907715023994, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.010788327925650947, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.011924492679859197, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.013776909236899199, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.015274198030994335, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.018413657642548563, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.020945298588724782, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.02303765605732509, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.024914466041535636, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.02785109668811459, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.03999090579916443, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.06063590380411016, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.0872917509094196, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.11920594973613152, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.14633086065283826, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.16589005719043418, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.18031173480849705, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.18616225878368542, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.1972972946957546, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.20776640519686765, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.2100085897676527, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.21087608005481553, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.2128905487850534, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.2112568302859228, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.2126489540083452, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.2144570753765953, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.21349223803809758, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.21500323308451078, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.21868622874859964, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.215241079341307, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.20736170321547998, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.20879615083771993, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.20250876899534254, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.20283949324411457, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.19033653252706295, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.19169753663551203, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.19198884658022608, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.18411972786464992, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.19137591836669854, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.19140015597384064, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.18824635410430104, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.1852048231026587, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.17689129481173768, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.18015010667865816, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 18, "lr_best": 0.00011399999999999999, "wd_best": 0.05, "train/loss_best": 2.228964915275574, "validation/loss_best": 2.400148868560791, "validation/acc_best": 0.27556293835363604, "validation/f1_best": 0.20776640519686765} +{"epoch": 10, "train/lr": 0.00021091808096876188, "train/loss": 2.3217090713977813, "train/grad": 0.25813712380826476, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.11825439453125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.116895751953125, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.11461669921875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.11234375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.1101806640625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.106845703125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.102685546875, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.096832275390625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.0839483642578127, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.0485467529296875, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.953451843261719, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.739951324462891, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.6220193481445313, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.519926223754883, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.445358200073242, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.388148422241211, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.321814374923706, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.2465067100524903, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.1728118896484374, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.10943115234375, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.0403480625152586, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.9727528810501098, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.898560552597046, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.8292034471035004, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.7668365120887757, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.701198867559433, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.645246869325638, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.6076137280464173, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.5601721519231797, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.5256009489297866, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.5147888684272766, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.4920302402973176, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.4760223507881165, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.486396826505661, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.5075113266706466, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.554273959994316, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.6088649654388427, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.6643799310922622, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.7286940091848373, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.80208950817585, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.8765323239564895, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.9330902034044266, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.009719133377075, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.171875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.019357911720871927, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.019357543769292534, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.01935485878493637, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.019349409714341164, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.01933988449163735, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.019319986579939722, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.019286279361695052, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.01923280996736139, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.01917381620965898, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.01941453240811825, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.02088605594821274, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.02553096950054169, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.0286794897634536, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.030604793429374694, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.031765344850718975, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.03249954817816615, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.0335285269562155, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.03498633009381592, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.03614872531965375, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.03697072304785252, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.037841510493308306, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.03873815055936575, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.03983446966856718, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.041034039426594976, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0419695402123034, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.04304441712796688, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.04416826831176877, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.04479512698948383, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.046195365861058234, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.04694975409656763, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.04718501621857286, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.04810828780755401, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.05036305632442236, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.05111999485641718, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.05180935537442565, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.05259250991046429, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.05276060096919537, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.05208580853417516, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.05278422029688954, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.05224918957799673, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.052145896460860965, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0527815068885684, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.05335091397166252, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.117236614227295, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.116279363632202, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.114623785018921, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.112945318222046, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.111180305480957, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1084282398223877, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1045427322387695, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.0983502864837646, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.082282066345215, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.0320682525634766, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.907078266143799, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.7063193321228027, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.6139118671417236, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.5383479595184326, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.4937126636505127, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.4671237468719482, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.443674325942993, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.4173316955566406, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.4013609886169434, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.398305654525757, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.404911994934082, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.431896686553955, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.4659552574157715, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.4902968406677246, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.545327663421631, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.595541477203369, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.626295566558838, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.6902830600738525, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.74936580657959, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.8617401123046875, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.879206895828247, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.8839457035064697, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.913065195083618, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.981327533721924, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.0811054706573486, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.0726981163024902, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.0306901931762695, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.9428329467773438, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.9918413162231445, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.9748220443725586, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.933276891708374, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.8916285037994385, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.8445990085601807, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06699889258028793, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06681432262827612, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06884459210040605, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.07032115171650055, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.07198228128460686, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.07511997046880768, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.07862679955703211, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.08250276854928018, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.09246954595791805, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.11904761904761904, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.14710225175341454, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.19158361018826134, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.2146548541897379, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.23735695828719083, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.25212255444813586, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.2593207825765965, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.26375046142488, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.2737172388335179, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.27297895902547065, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.27002583979328165, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.26947212993724623, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.26375046142488, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.25599852344038393, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.2591362126245847, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.25507567368032485, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.25212255444813586, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.2517534145441122, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.23864894795127353, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.23791066814322628, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.23034330011074197, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.23126614987080105, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.2334809892949428, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.23458840900701367, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.23329641934293097, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.21557770394979697, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.2100406053894426, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.22111480251015134, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.22517534145441123, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.2187153931339978, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.2115171650055371, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.21207087486157253, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.21650055370985605, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.22739018087855298, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.010785143405118955, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.01068545344949027, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.013308982266106328, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.015527335067270937, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.01666990615671024, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.019046578621704325, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.0205104602228615, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.02322429906213745, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.03201817257203426, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.05049016423599539, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.06902357257494933, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.11228531783560607, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.13500640786801169, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.16007694887638782, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.1770467437808694, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.18517948760954503, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.19162911008112568, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.20448939132012475, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.20813173688329015, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.20841766998218483, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.20885274753161168, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.20554970993057284, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.2026343308631752, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.20806259214697784, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.20872943466055402, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.20745086195435103, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.21157377829810134, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.20376253946084621, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.20393504591139544, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.19933519513238515, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.19776650680905472, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.2023625424255955, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.19876970417378267, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.18853158723086935, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.17498352108845394, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.17103867458143948, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.18240971966759192, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.19063661351142733, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.18628078013306326, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.18271001229407938, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.18337906576498986, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.18296950710282647, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.1833041818672497, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 17, "lr_best": 9.599999999999999e-05, "wd_best": 0.05, "train/loss_best": 2.2465067100524903, "validation/loss_best": 2.4173316955566406, "validation/acc_best": 0.2737172388335179, "validation/f1_best": 0.20448939132012475} +{"epoch": 11, "train/lr": 0.00018113997589164516, "train/loss": 2.274809433221817, "train/grad": 0.2631763362139463, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.123516845703125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.1220556640625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.11974609375, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.117373046875, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.114947509765625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.111326904296875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.106495361328125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.09896728515625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.0793463134765626, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.0169061279296874, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.8765911865234375, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.6873199462890627, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.593870849609375, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.498176612854004, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.4261852645874025, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.3678331184387207, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.294991569519043, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.215170497894287, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.137160120010376, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.0719239711761475, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.0012700843811033, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.9268963027000428, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.8462849712371827, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.770461790561676, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.7033243423700333, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.6322925937175752, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.5706107741594315, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.5279610335826874, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.47969064950943, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.4428469425439834, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.4359935069084167, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.414478957056999, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.3750879663228988, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.374416851401329, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.3871868979930877, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.4304347509145736, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.4906081938743592, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.5553013002872467, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.6234605860710145, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.7167864733934401, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.786961590051651, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.8420001792907714, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.9201535683870317, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.171875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.01945514339953661, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.019452215805649757, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.019446011129766703, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.019438754986040294, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.01942782155238092, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.019404244204051794, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.019365102872252463, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.019307288620620967, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.019310470139607787, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.020075957039371133, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.02255747633986175, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.027367656724527477, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.029714337419718503, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.03132951327599585, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.03243791458196938, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.033165185730904344, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.03446864371187985, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.036031920686364176, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.03722579788416624, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.03807430534623563, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.0390240029618144, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.039955965727567676, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.04120048932731152, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.04249389160424471, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.04346268741413951, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0447348759137094, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.04591698726639151, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.046651571970432994, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.04788909176364541, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.049086273033171895, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.049989702254533766, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.050627863593399526, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.05162863906472921, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.051275423262268305, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.05141449812799692, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.05170124337077141, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.052340592909604314, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.05232673581689596, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0529920208081603, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.05300956033170223, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.051895856130868195, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.052351984698325395, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.05281151590868831, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1167609691619873, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1156489849090576, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.113708734512329, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.111725330352783, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.109609603881836, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.106294870376587, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1014344692230225, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.0929958820343018, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.0677764415740967, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.9838032722473145, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.824955701828003, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.6613171100616455, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.5866289138793945, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.5218441486358643, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.486070394515991, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.4656310081481934, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.4425151348114014, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.4244935512542725, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.4176058769226074, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.4177865982055664, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.427152395248413, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.4535152912139893, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.4825143814086914, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.507215976715088, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.551759719848633, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.5943686962127686, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.638032913208008, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.6845927238464355, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.72556734085083, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.8411216735839844, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.8375346660614014, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.875556707382202, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.905299186706543, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.9544787406921387, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.021416425704956, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.0011370182037354, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.98736834526062, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.959484338760376, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.9586544036865234, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.9036624431610107, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.8400557041168213, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.802490711212158, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.8076345920562744, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.067921742340347, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.07013658176448874, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.0710594315245478, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.07401255075673681, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.0754891103728313, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.07678110003691399, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.08139534883720931, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.08674787744555186, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.10723514211886305, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.13473606496862311, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.16666666666666666, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.19859726836471023, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.22517534145441123, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.24049464747139165, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.2543373938722776, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.25839793281653745, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.26799557032115173, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.2727943890734588, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.27703949796973054, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.2739018087855297, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.26836471022517533, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.266703580657069, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.2606127722406792, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.26135105204872644, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.2591362126245847, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.25507567368032485, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.2517534145441122, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.2497231450719823, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.25378368401624213, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.24381690660760427, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.2441860465116279, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.2425249169435216, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.23440383905500184, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.23292727943890734, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.22831303063861202, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.22148394241417496, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.22960502030269472, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.23440383905500184, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.23237356958287192, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.22812846068660023, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.23717238833517904, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.23994093761535623, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.23883351790328536, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.011006660042369347, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.012824987653100877, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.014589613221762292, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.01717796115681804, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.018248714450628385, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.01980349165823821, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.024136848832900796, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.030416671113391927, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.0466931282671442, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.05958670642143608, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.0837728765684429, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.11797764535605255, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.14335450886509782, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.162548053422255, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.17635732481224853, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.18326437492633277, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.19535319552872502, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.2046841244354272, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.21215121223436897, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.21388180950466704, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.2120454195350839, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.21330421673332978, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.21050540663778908, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.21158412056970644, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.21268311960291533, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.21193417587328536, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.21061686402064858, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.21319348582253284, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.21362871553571525, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.20282978054866718, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.20755737633902457, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.20828309283804156, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.20362568850473203, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.20380183353737977, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.20058090739981052, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.19513328398553428, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.19356231606349814, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.19529071784218874, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.19792979472389885, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.1993832057600102, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.2055637462708303, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.20011201222705163, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.19115666908998774, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 18, "lr_best": 0.00011399999999999999, "wd_best": 0.05, "train/loss_best": 2.137160120010376, "validation/loss_best": 2.4176058769226074, "validation/acc_best": 0.27703949796973054, "validation/f1_best": 0.21215121223436897} +{"epoch": 12, "train/lr": 0.0001499999999999999, "train/loss": 2.2069585478305815, "train/grad": 0.26156765639781954, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.11481201171875, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.113248291015625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.11052001953125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.1077392578125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.10480712890625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.100458984375, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.094237060546875, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.083795166015625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.053126220703125, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.9548629760742187, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.79002685546875, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.6303741455078127, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.546081771850586, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.4527278900146485, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.382981014251709, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.3225390625, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.245506277084351, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.1660107803344726, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.0889019203186034, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.0246276378631594, "train/loss_020_lr5.2e-01_wd1.0e+00": 1.9523037147521973, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.8761821508407592, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.7946086621284485, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.7154861783981323, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.6427010256052017, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.5612959831953048, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.4922932094335557, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.442151619195938, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.3685327756404877, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.3224391120672225, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.2974984490871428, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.2672231635451316, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.2196809893846512, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.2235541263222693, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.2386198407411575, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.2781920385360719, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.3333613181114197, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.3996261847019196, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.479498996734619, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.5567601215839386, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.6498900157213212, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.7130071705579757, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.7974294155836106, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.171875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.019425844200886788, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.019424595609307288, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.019420744753442704, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.019412840120494365, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.01939976474735886, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.019371470673941075, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.019325988255441188, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.01927246087230742, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.019398800362832844, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.020808059931732716, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.02413693819195032, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.02858956130221486, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.030499136121943594, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.03207259128801525, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.03308677095919847, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.033807351859286426, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.03529222068376839, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.03671946557238698, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.037835608441382645, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.03856123629026115, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.03947194829583168, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.04045834107324481, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0416789616830647, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.04288174867630005, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0436669216118753, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.04451288202777505, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.04553444625809789, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.04627450043335557, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.04677710920572281, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.04764364147558808, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.04836299614980817, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.049058263916522266, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.050055058412253856, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.050594087541103366, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.05077348476275802, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.051189379431307316, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.05183372749015689, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.05201836418360472, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.05254218742251396, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.051838680673390626, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.05104697341099382, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.05171630943194032, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.05185653291642666, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.116433620452881, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.115260362625122, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.113253116607666, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.111126661300659, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1088356971740723, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.105109453201294, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.0993378162384033, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.088365077972412, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.0516555309295654, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.935774803161621, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.7709710597991943, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.636195182800293, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.571075916290283, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.512799024581909, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.483252763748169, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.4676644802093506, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.448756694793701, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.437725782394409, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.437108039855957, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.4411635398864746, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.461458683013916, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.5060901641845703, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.550600528717041, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.5885722637176514, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.631948471069336, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.675837516784668, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.716546058654785, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.8157782554626465, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.8961338996887207, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.075538396835327, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.1132073402404785, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.1469929218292236, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.1994171142578125, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.248703718185425, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.3019657135009766, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.2441539764404297, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.150272846221924, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.1558566093444824, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.0134387016296387, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.0005853176116943, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.879880905151367, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.8481605052948, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.8675801753997803, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06681432262827612, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06736803248431156, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06884459210040605, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06995201181247693, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.07142857142857142, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.07401255075673681, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.07899593946105574, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.08785529715762273, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.11129568106312292, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.14230343300110743, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.1744186046511628, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.2039497969730528, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.2262827611664821, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.24473975636766335, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.2511997046880768, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.25359911406423036, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.2606127722406792, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.2622739018087855, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.26504245108896274, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.262827611664821, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.2571059431524548, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.2558139534883721, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.25101513473606496, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.24806201550387597, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.24750830564784054, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.24861572535991142, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.24584717607973422, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.24012550756736803, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.2412329272794389, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.22443706164636398, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.2334809892949428, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.2321889996308601, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.22739018087855298, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.22572905131044665, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.21908453303802142, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.22406792174234036, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.23034330011074197, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.22886674049464747, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.23735695828719083, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.22997416020671835, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.24880029531192321, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.25230712440014763, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.24381690660760427, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.009436224234601364, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.009930508919597613, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.011459595696926029, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.01312262740405662, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.014677152746450891, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.01739725831162583, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.022818372662504735, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.03251767393373809, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.04900346367473968, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.0635574588888477, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.09121221886739643, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.12240385662578517, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.14628022452112135, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.16475310144198574, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.17442518510051308, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.18031228500445592, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.1901563652900581, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.19671616314308657, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.20380114574954475, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.20543433070906403, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.2024174603428898, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.204713584101439, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.2012021465444207, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.20079961103282362, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.19826587319245928, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.1982849106163643, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.19771040845769602, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.19195047603265403, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.18955695222463678, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.17895534586430517, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.1810109716267985, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.18172594380723275, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.18152939266442747, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.17823296567560712, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.17803300081743048, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.1827699539264418, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.1883784154651785, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.18633495885632712, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.19663157238949636, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.19782877722819414, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.20183305724845105, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.20021023416916303, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.19624221972585842, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 18, "lr_best": 0.00011399999999999999, "wd_best": 0.05, "train/loss_best": 2.0889019203186034, "validation/loss_best": 2.437108039855957, "validation/acc_best": 0.26504245108896274, "validation/f1_best": 0.20380114574954475} +{"epoch": 13, "train/lr": 0.00011886002410835478, "train/loss": 2.1601288110017776, "train/grad": 0.2608003244549036, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.11850830078125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.116639404296875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.11384033203125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.110887451171875, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.10784912109375, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.103048095703125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.095958251953125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.083438720703125, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.0421392822265627, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.9176541137695313, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.752496795654297, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.6142543029785155, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.5346395111083986, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.442125816345215, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.372941780090332, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.3104751014709475, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.232376880645752, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.150501699447632, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.0697352695465088, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.0011866188049314, "train/loss_020_lr5.2e-01_wd1.0e+00": 1.9234312510490417, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.8454207277297974, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.7575612568855286, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.6722986990213393, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.596910102367401, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.5122591918706894, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.4391267508268357, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.3853788077831268, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.3078100574016571, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.2467940533161164, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.2188594257831573, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.1784948241710662, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.1223738342523575, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.1082462733983993, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.113895719051361, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.1433362063765526, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.187686507999897, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.253885395526886, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.3281407436728478, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.4271810525655746, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.5158457601070403, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.5772462052106857, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.6621841669082642, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.171875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.019794342368841172, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.019790922431275247, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.01978462637402117, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.01977070152759552, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.01975380700081587, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.019718872108496724, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.019664634484797716, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.019615493048913777, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.019893481601029633, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.021807692288421096, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.025478534437716006, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.029388750810176133, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.031018807673826813, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.032544421097263694, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.03349289841018617, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.03426298616454005, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.035799947744235394, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.03711039240472019, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.03814532567746937, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.03878386694937944, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.03959375215694308, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.040519485753029584, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.04170952666550875, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.04297540655359626, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.04390311144292355, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.04491335513070226, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.04590865321457386, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.046664031762629746, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.04756347756832838, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.04823956208303571, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.04854528741911054, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.04890959581360221, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.049982714001089334, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.05026377217844129, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.05034872096031904, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.050736247655004264, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.050568046644330025, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.050394341722130774, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.050701389480382206, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.05123898250982165, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.050288107581436634, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.050163115561008456, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.04935257833451032, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1160340309143066, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.11470890045166, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1124770641326904, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.110091209411621, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1074795722961426, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1031391620635986, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.096212387084961, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.0825178623199463, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.033722162246704, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.8937714099884033, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.7342586517333984, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.6150870323181152, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.5537149906158447, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.4980530738830566, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.469715118408203, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.4511613845825195, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.429858684539795, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.419875383377075, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.4222605228424072, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.426496744155884, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.443985939025879, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.485635757446289, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.5292537212371826, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.5653178691864014, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.623181104660034, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.675262212753296, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.7183594703674316, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.7923712730407715, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.8551645278930664, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.0701329708099365, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.141807794570923, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.203432083129883, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.2578694820404053, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.32263445854187, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.3942863941192627, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.3823719024658203, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.3624954223632812, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.4163014888763428, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.3391032218933105, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.307663679122925, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.139012575149536, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.0849945545196533, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.991999387741089, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06995201181247693, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.07087486157253599, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.07216685123661867, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.07345884090070137, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.07715023994093761, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.08084163898117387, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.0843484680693983, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.09431524547803617, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.12089331856773718, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.15227021040974528, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.18309339239571798, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.21373200442967885, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.23274270948689554, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.25101513473606496, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.2574750830564784, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.26005906238464377, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.27150239940937615, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.2751937984496124, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.27205610926541157, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.2691029900332226, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.2691029900332226, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.25950535252860835, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.2552602436323367, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.25489110372831303, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.25212255444813586, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.25249169435215946, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.24953857511997046, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.24160206718346253, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.24067921742340348, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.21982281284606867, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.22093023255813954, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.21926910299003322, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.21816168327796234, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.2172388335179033, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.2115171650055371, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.2174234034699151, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.22148394241417496, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.21244001476559615, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.21816168327796234, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.2264673311184939, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.2369878183831672, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.23791066814322628, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.24012550756736803, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.012428463223633876, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.013729584800565707, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.015521193671675515, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.016965433354301885, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.01974089056344049, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.02289258325662667, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.027018151531186873, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.03733835699654806, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.052440842603233014, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.0726504049693981, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.10136720090811972, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.13291101698830957, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.15233988735514242, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.17196103353530648, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.18141939406769195, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.1869764596003647, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.20023442191454943, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.21068268677017032, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.2104859567989227, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.2111525636548195, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.2157752003689868, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.20941606414205674, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.20718524019586212, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.20803111440515798, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.2059636600436977, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.2053224121087579, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.20721742475357205, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.20248590394175756, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.20006406532326926, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.18375990211026735, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.18444743147015544, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.18520671595676277, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.187354760524721, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.18301345966057533, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.17942282027676704, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.18438403126810254, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.1809862137511947, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.17219675708353788, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.1810741329810309, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.18938994780039067, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.19743744434779395, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.1900385551748692, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.19722529717464374, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 17, "lr_best": 9.599999999999999e-05, "wd_best": 0.05, "train/loss_best": 2.150501699447632, "validation/loss_best": 2.419875383377075, "validation/acc_best": 0.2751937984496124, "validation/f1_best": 0.21068268677017032} +{"epoch": 14, "train/lr": 8.9081919031238e-05, "train/loss": 2.105675832629204, "train/grad": 0.2581426716595888, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.1152978515625, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.11355224609375, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.110555419921875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.1074169921875, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.10422607421875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.098983154296875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.0911688232421874, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.076177978515625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.0241546630859375, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.879488830566406, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.716678466796875, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.5862709045410157, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.506902961730957, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.415109939575195, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.3468971633911133, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.2834153175354004, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.2053422260284425, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.122858848571777, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.0413135719299316, "train/loss_019_lr4.4e-01_wd1.0e+00": 1.9726132297515868, "train/loss_020_lr5.2e-01_wd1.0e+00": 1.895098192691803, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.8153782725334167, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.7219921112060548, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.6302287626266478, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.5505155420303345, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.4589474707841874, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.37990116417408, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.3200590842962265, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.2360620325803757, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.1659903582930564, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.1223623809218406, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.0699505975842476, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.9962735664844513, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.9798116013407707, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.9743209853768349, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.9980288550257683, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.0402120068669318, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.0955979600548744, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.168622708618641, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.265715269446373, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.3730119436979293, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.4322013980150223, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.5381604433059692, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.171875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.019382661608979106, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.019380754381418227, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.019371952139772476, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.01936045929789543, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.019344681235961617, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.01930898561142385, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.01926243756432086, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.01924170171841979, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.0197218336770311, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.0220960480440408, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.025920725697651505, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.02943602927029133, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.030943281101062894, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.03252822550944984, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.0335366137791425, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.03444665084592998, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.036101137259975075, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.03741639317944646, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.038400352979078886, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.03899455934762955, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.039778315275907514, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.0406428530998528, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.041743915248662236, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.04294658811762929, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.04388593273237348, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.044902441296726464, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.04582488523796201, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.046415167190134526, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.04712223205715418, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.04750064557418227, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.047513396218419074, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.04796336518600583, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.04830917131155729, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.048368491269648074, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.049040488973259924, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.049509462453424934, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.049495544247329236, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.04961459182202816, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.050370045751333234, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.05049143260344863, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.04966754330322146, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.04970005663111806, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.049368167091161014, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.115288496017456, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1138925552368164, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.111506462097168, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.10900616645813, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1062510013580322, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.101545572280884, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.09385347366333, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.0778651237487793, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.0185396671295166, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.863232135772705, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.711538314819336, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.6013596057891846, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.5420656204223633, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.4890482425689697, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.46289324760437, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.4435739517211914, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.4234445095062256, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.41483211517334, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.418976068496704, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.4215972423553467, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.4347805976867676, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.4713432788848877, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.5102927684783936, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.5412628650665283, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.604621648788452, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.672990083694458, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.7305779457092285, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.826247215270996, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.8881547451019287, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.085949420928955, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.134279727935791, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.210853099822998, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.278899908065796, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.3361988067626953, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.4642250537872314, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.4529709815979004, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.39147686958313, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.4011120796203613, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.3572795391082764, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.4247474670410156, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.267242431640625, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.149491310119629, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.0919361114501953, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.07032115171650055, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.0710594315245478, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.07198228128460686, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.073827980804725, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.07604282022886674, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.07918050941306755, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.08545588778146918, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.09689922480620156, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.12403100775193798, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.15928386858619417, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.18992248062015504, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.2157622739018088, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.2353266888150609, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.2500922849760059, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.25950535252860835, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.2633813215208564, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.27113325950535255, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.2757475083056478, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.27464008859357697, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.27297895902547065, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.2724252491694352, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.2633813215208564, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.2591362126245847, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.2576596530084902, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.25507567368032485, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.2499077150239941, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.24640088593576967, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.23421926910299004, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.2353266888150609, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.2159468438538206, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.22369878183831673, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.2201919527500923, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.21557770394979697, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.21280915466961978, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.20764119601328904, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.20450350682908822, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.2117017349575489, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.2131782945736434, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.2207456626061277, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.20579549649317092, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.2188999630860096, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.22296050203026946, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.22185308231819859, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.012074592152391948, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.01270061567015174, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.01463445685205648, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.016194041099985096, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.017987269365282676, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.02108986688975266, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.026393163908951914, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.0378281661323986, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.053909795606450726, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.07647891462714553, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.10608185613925734, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.13491608938053176, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.1528861671711273, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.17036468078726572, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.1842413370448057, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.19123227905698725, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.20277214506224786, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.2102944842680933, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.21416576262393727, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.21767810043093805, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.22010805092306593, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.2155944986876008, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.2121197385226958, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.21447989515618437, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.21473887234406094, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.20923939043560677, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.20825360217221978, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.19958227010774313, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.20060840545256584, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.18446675640725818, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.19007329432231254, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.19088306315800355, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.18440116409544513, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.17838611590177603, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.17825049343297752, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.1779369718554006, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.18304672055075058, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.1817634193297156, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.19182393719044413, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.17645321880966272, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.1840697769829026, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.1883013939806063, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.18725817861929084, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 17, "lr_best": 9.599999999999999e-05, "wd_best": 0.05, "train/loss_best": 2.122858848571777, "validation/loss_best": 2.41483211517334, "validation/acc_best": 0.2757475083056478, "validation/f1_best": 0.2102944842680933} +{"epoch": 15, "train/lr": 6.196799573888289e-05, "train/loss": 2.0590307766199114, "train/grad": 0.25307945519685743, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.1111181640625, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.109306640625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.1061279296875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.103006591796875, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.09964111328125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.0943310546875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.0859088134765624, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.0692645263671876, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.0094500732421876, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.853826904296875, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.698609619140625, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.5759416961669923, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.4979796600341797, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.406111602783203, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.3362808799743653, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.270195140838623, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.1900658988952637, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.1058373832702637, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.0239030742645263, "train/loss_019_lr4.4e-01_wd1.0e+00": 1.9543615102767944, "train/loss_020_lr5.2e-01_wd1.0e+00": 1.8744993209838867, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.790259997844696, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.6976993799209594, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.607013876438141, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.5222024184465408, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.4243485969305039, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.3365415906906128, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.2669686889648437, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.1829011154174804, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.103698307275772, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.0535889837145804, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.9948876589536667, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.9101733246445656, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.8845408573746681, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.856022978425026, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.8630442053079606, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.8937539932131767, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.9470108479261399, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.0055795255303384, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.0943700635433198, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.2083004704117775, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.2730523037910462, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.3695335966348647, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.171875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.01978810122702271, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.01978490725159645, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.019773515141569078, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.019756867280229927, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.019736741124652325, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.019691059631295502, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.019632172784768046, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.01960882924962789, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.020192309487611054, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.022790388343855737, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.02668293848633766, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.029956341590732335, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.03140611863695085, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.03296809154562652, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.033916918477043506, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.03486368115991354, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.03651668377220631, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.037830716660246254, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.038840987347066404, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.03941033771261573, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.040190540459007024, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.041002935487777, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.042022205982357265, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.043076322302222254, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.043738272432237865, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.04455369494855404, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.04532168192788959, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.045846603121608494, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.04617187025025487, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.04632787084206939, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0460142601467669, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0460809226334095, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.04617265082895756, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.045709869526326656, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.04605853538960218, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.04622465906664729, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.04682192450389266, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.04723052253946662, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.04763420321047306, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.04845250990241766, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.047628059182316065, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.04816714394837618, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.04793224776163697, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.11521053314209, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1138036251068115, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.111433506011963, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1088955402374268, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.106081485748291, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.101203203201294, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.0930140018463135, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.07524037361145, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.008197784423828, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.843994140625, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.6986327171325684, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.593818187713623, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.536266565322876, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.486171245574951, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.462466239929199, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.4441585540771484, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.42769718170166, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.422269582748413, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.4287068843841553, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.4328665733337402, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.4478578567504883, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.4890480041503906, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.5290253162384033, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.559283971786499, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.6178653240203857, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.6750941276550293, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.7292051315307617, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.8118207454681396, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.895134449005127, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.1142146587371826, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.1650261878967285, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.2186288833618164, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.3156466484069824, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.408740282058716, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.5250160694122314, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.5212948322296143, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.508636951446533, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.5099077224731445, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.4295785427093506, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.4071834087371826, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.224839448928833, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.1368250846862793, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.0837535858154297, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.07069029162052418, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.07142857142857142, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.07216685123661867, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.0725359911406423, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.07585825027685493, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.07936507936507936, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.08656330749354005, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.10022148394241417, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.12809154669619785, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.16371354743447766, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.1925064599483204, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.2233296419342931, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.23846437799926173, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.25064599483204136, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.2602436323366556, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.26411960132890366, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.27464008859357697, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.2763012181616833, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.2748246585455888, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.2702104097452935, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.26707272056109266, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.26356589147286824, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.2587670727205611, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.26116648209671467, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.2589516426725729, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.25064599483204136, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.24732373569582872, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.24049464747139165, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.23809523809523808, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.21816168327796234, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.22443706164636398, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.22591362126245848, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.21262458471760798, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.21705426356589147, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.21557770394979697, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.20450350682908822, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.20764119601328904, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.2056109265411591, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.20985603543743078, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.2072720561092654, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.2294204503506829, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.22554448135843486, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.22702104097452935, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.012588429792989644, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.013453102907943779, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.01502401701208191, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.016444702754094317, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.018953235954880944, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.023171842245608202, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.029968977061162378, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.04022055802715054, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.056189779188727064, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.08157736648842152, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.11082654275547071, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.14144337799855208, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.15815364942382562, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.171932295451291, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.1838524303736685, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.1904164191676334, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.20522945691158223, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.21014147198975128, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.21222213027474937, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.2108806953431002, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.2121066108721806, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.21252089136692365, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.21029183442604973, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.21652690368249228, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.21595225602387055, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.20885517199879344, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.20817047329842395, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.2057385153466047, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.20542596699918073, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.18816382464708137, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.19301738696475038, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.1954237088963501, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.18438726208367742, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.18412535032777935, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.1876082842561413, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.1801667046503835, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.18481821419099012, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.18385938731870635, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.1872463219561794, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.1866292870101871, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.20539023919610813, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.1986438708977143, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.19449368622399074, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 17, "lr_best": 9.599999999999999e-05, "wd_best": 0.05, "train/loss_best": 2.1058373832702637, "validation/loss_best": 2.422269582748413, "validation/acc_best": 0.2763012181616833, "validation/f1_best": 0.21014147198975128} +{"epoch": 16, "train/lr": 3.870405029380728e-05, "train/loss": 2.0259645587205886, "train/grad": 0.24800540551543235, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.11861328125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.116593017578125, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.1134765625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.110081787109375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.106485595703125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.1007354736328123, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.0916290283203125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.07337646484375, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.0067535400390626, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.8430462646484376, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.6954446411132813, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.5805952453613283, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.5043396377563476, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.4120441818237306, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.3407879161834715, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.2740687561035156, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.1942636299133302, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.1102679920196534, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.02588436126709, "train/loss_019_lr4.4e-01_wd1.0e+00": 1.9535537004470824, "train/loss_020_lr5.2e-01_wd1.0e+00": 1.8691266083717346, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.7812343788146974, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.6850881803035735, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.5907418084144593, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.5053640174865723, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.401798101067543, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.306438752412796, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.2361947482824325, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.1375665274262428, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.0531163656711577, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.9970270797610283, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.9383762922883033, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.8459901660680771, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.8066601926088333, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.7710053315758705, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.7646860811114311, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.781164291203022, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.815458959043026, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.8671530765295029, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.9239742627739906, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.0601494878530502, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.118817616403103, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.2118419420719146, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.171875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.0197293754061684, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.01972552800551057, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.019712736415676772, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.01969522372353822, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.019673228692263366, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.01962862308137119, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.019572512665763497, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.019572055879980326, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.020284193539991974, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.023102893121540548, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.0270480992924422, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.03022244176827371, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.031616594735533, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.033113436847925184, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.0340224489197135, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.03499444212764501, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.03661088706925511, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.03786738853901625, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.038818478882312775, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.039336192421615124, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.04005440952256322, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.04083001349121332, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.04180174317210913, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0428827784024179, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.043587140813469885, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0442676636017859, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.04484537998214364, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.04514602463692427, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.04518387088552117, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.045404923111200333, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.04508013941347599, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.04499617284163833, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.044797630719840525, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.04434888897463679, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.04386334881186485, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.043777863420546057, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.04396251901984215, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.04442315280437469, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.04536155682057142, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.045963442847132684, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.046028125621378424, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.04662798497825861, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.04670833824202418, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1151232719421387, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1137192249298096, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.111319065093994, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.10874605178833, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.10587215423584, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1008753776550293, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.0922811031341553, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.073347806930542, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.001452684402466, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.832761526107788, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.6914103031158447, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.590000629425049, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.5332627296447754, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.4830596446990967, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.45904803276062, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.4390487670898438, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.4221205711364746, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.4174349308013916, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.4249000549316406, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.4313149452209473, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.4503419399261475, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.49284029006958, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.537769317626953, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.5724194049835205, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.6401054859161377, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.706193447113037, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.76586651802063, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.8542282581329346, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.9345591068267822, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.1432299613952637, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.1928305625915527, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.2495803833007812, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.3549821376800537, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.453788995742798, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.5869204998016357, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.609862804412842, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.6208443641662598, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.5912914276123047, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.5833752155303955, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.5401227474212646, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.346527099609375, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.2672486305236816, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.1962757110595703, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06995201181247693, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06976744186046512, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.07142857142857142, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.07235142118863049, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.07511997046880768, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.07770394979697305, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.08508674787744555, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.09782207456626062, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.13049095607235142, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.1640826873385013, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.1934293097083795, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.2222222222222222, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.23883351790328536, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.2517534145441122, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.25858250276854927, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.2648578811369509, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.27464008859357697, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.2753783684016242, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.2724252491694352, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.26836471022517533, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.26744186046511625, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.2631967515688446, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.2561830933923957, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.2582133628645257, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.2563676633444075, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.24640088593576967, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.24437061646363972, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.2382798080472499, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.23329641934293097, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.21650055370985605, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.22240679217423404, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.22812846068660023, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.21631598375784422, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.21908453303802142, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.21686969361387967, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.20524178663713546, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.20930232558139536, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.21207087486157253, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.21207087486157253, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.20505721668512367, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.21908453303802142, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.22314507198228128, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.22111480251015134, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.012428715399803761, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.012927020318327575, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.015315605774918395, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.016334372644273266, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.01829589319337149, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.020662599785333725, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.026855014834794026, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.03846613503700227, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.05758984111848476, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.08208915613591612, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.11159801328772118, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.14231583614529172, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.15884376445214712, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.1746907178843707, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.1845728399708816, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.19321043285027484, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.2062750562576876, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.21300756501817555, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.21193909024622917, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.21161704731730224, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.2144235639897739, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.2122616662630088, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.20937670702032288, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.21639395568047373, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.21473338685224844, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.20496545630332075, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.20625908707786997, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.2030941836962342, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.19713745050818277, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.18487835495287452, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.19140494307964154, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.1972462033258889, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.18723135096734622, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.18564649966264443, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.18647240897929085, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.17955096666651768, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.17911673671058734, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.18163643006667787, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.18270633886368434, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.18494517055030393, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.19346605676477271, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.19998566991183334, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.19389331683004743, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 17, "lr_best": 9.599999999999999e-05, "wd_best": 0.05, "train/loss_best": 2.1102679920196534, "validation/loss_best": 2.4174349308013916, "validation/acc_best": 0.2753783684016242, "validation/f1_best": 0.21300756501817555} +{"epoch": 17, "train/lr": 2.030750443206766e-05, "train/loss": 1.9928627216815948, "train/grad": 0.2399066510796547, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.114881591796875, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.11297119140625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.109796142578125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.106575927734375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.1030810546875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.097264404296875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.0881549072265626, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.069373779296875, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.999755859375, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.831104736328125, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.681600799560547, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.564350280761719, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.487334747314453, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.3982440185546876, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.32928524017334, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.262474384307861, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.1818817329406737, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.097417631149292, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.0123652458190917, "train/loss_019_lr4.4e-01_wd1.0e+00": 1.9392914056777955, "train/loss_020_lr5.2e-01_wd1.0e+00": 1.8545020771026612, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.7688385581970214, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.6709224414825439, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.573507204055786, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.484917066693306, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.3792355901002884, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.2834423059225082, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.214360153377056, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.109063860476017, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.020534619987011, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.9568477341532707, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.8890340963006019, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.7898552185297012, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.7472354137897491, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.7093331274390221, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.6922986498475074, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.696935364305973, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.7184488627314568, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.7519955489039422, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.7974414005875587, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.9212336379289627, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.9588658335804939, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.0429706847667695, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.171875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.01952746386639774, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.019520565662533046, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.019505251408554615, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.019486545189283788, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.019462880818173288, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.019418318415991963, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.019363659056834875, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.019373071510344744, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.020143978470005094, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.02303288779221475, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.026884636357426644, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.02992923470214009, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.03128622751682997, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.03278896484524012, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.03373338061384857, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.03473784797824919, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.03635140999220312, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.0375826851464808, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.03852944098412991, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.03902303103357554, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.03972130058333278, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.040486233159899715, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.04151524780318141, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.042575452104210855, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.043197663817554716, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.043818036168813704, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.04436471842229366, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.04468004761263728, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.04460448578000069, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.04445776669308543, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.04391759434714913, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.04332648243755102, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.04258208781480789, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.042037527710199356, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.04130555409938097, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.040996366050094366, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.040766448341310026, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.040794009640812874, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.04161756444722414, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.04218788301572204, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.04277566481381655, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.043097573388367894, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.043390667643398044, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1150965690612793, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.113678455352783, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.111262798309326, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1086745262145996, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.105740547180176, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1006345748901367, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.091794967651367, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.072206974029541, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.9976916313171387, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.8267459869384766, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.6873652935028076, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.5872302055358887, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.5309340953826904, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.481409788131714, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.4568705558776855, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.436033248901367, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.4179000854492188, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.4115610122680664, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.4178342819213867, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.4224720001220703, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.4410040378570557, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.48409104347229, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.524914264678955, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.5583386421203613, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.620870351791382, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.6814048290252686, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.741075277328491, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.8284127712249756, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.9142580032348633, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.127323627471924, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.1962742805480957, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.2554948329925537, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.3727376461029053, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.487609624862671, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.6257753372192383, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.648585319519043, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.663194417953491, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.6909360885620117, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.6650357246398926, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.618920087814331, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.4292120933532715, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.3775665760040283, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.302194356918335, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.07013658176448874, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.07013658176448874, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.07272056109265411, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.07327427094868956, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.07678110003691399, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.07918050941306755, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.08619416758951642, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.10243632336655592, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.132890365448505, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.16851236618678478, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.19472129937246216, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.22425249169435216, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.2397563676633444, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.25230712440014763, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.2589516426725729, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.26596530084902176, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.2757475083056478, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.2779623477297896, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.27260981912144705, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.268733850129199, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.26707272056109266, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.2622739018087855, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.2563676633444075, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.25802879291251385, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.2567368032484312, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.2528608342561831, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.24769287559985234, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.24289405684754523, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.23661867847914358, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.21668512366186785, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.2248062015503876, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.22517534145441123, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.21391657438169065, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.21797711332595054, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.21280915466961978, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.2059800664451827, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.2069029162052418, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.2074566260612772, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.21077888519748986, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.2115171650055371, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.22425249169435216, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.22886674049464747, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.22554448135843486, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.012800990882231666, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.013645553605123322, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.016207910301794835, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.01709276489741657, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.019743009291644128, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.022369094942101403, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.028672013017530775, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.04155572958119282, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.05904024440162523, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.08559722459793236, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.11340012135650519, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.1440535755300473, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.15922048103934874, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.1755721936045095, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.1839461785821848, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.1942450159331617, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.20639925177520424, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.21473742175872346, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.21194265414117328, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.2126594366201616, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.21426023464547192, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.21282896445217336, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.21055503079066154, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.214737964561149, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.21602369090943996, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.21164528136439528, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.20996860332815095, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.20721617256985694, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.20112083606462314, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.18588719518298627, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.1920702303930734, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.1943062694336765, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.18471844645621605, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.1847831715493685, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.18090501943349943, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.1808366336336985, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.17829456704996993, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.17554752983410993, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.17966738403332552, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.18806678960729903, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.1950154253248628, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.19484859978465485, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.19259549521295194, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 17, "lr_best": 9.599999999999999e-05, "wd_best": 0.05, "train/loss_best": 2.097417631149292, "validation/loss_best": 2.4115610122680664, "validation/acc_best": 0.2779623477297896, "validation/f1_best": 0.21473742175872346} +{"epoch": 18, "train/lr": 7.5829098008590064e-06, "train/loss": 1.979489272236824, "train/grad": 0.23572527080774308, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.117127685546875, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.11516357421875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.112052001953125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.10873779296875, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.105198974609375, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.09945068359375, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.0902716064453126, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.071146240234375, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.000185546875, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.8324734497070314, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.686631927490234, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.5716576385498047, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.494081039428711, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.4015288162231445, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.3297317695617674, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.261419563293457, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.1799747276306154, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.094432888031006, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.009542856216431, "train/loss_019_lr4.4e-01_wd1.0e+00": 1.9377320098876953, "train/loss_020_lr5.2e-01_wd1.0e+00": 1.8550033712387084, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.766994867324829, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.6670261025428772, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.5682789820432663, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.4783022969961166, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.3718286013603211, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.274319407939911, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.1978729671239854, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.0923295038938523, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.0007937926054, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.9400089350342751, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.8704792320728302, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.7697000244259834, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.7226304054260254, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.675933014601469, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.6596319301426411, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.6637064117193222, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.6761520554125309, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.7057923315465451, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.7328845149278641, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.8417438405752182, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.8688694906234741, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.9449040499329567, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.171875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.019629784217104315, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.01962389488238841, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.019608543305657804, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.019588752062991262, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.019564395560882984, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.019520601453259588, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.01946737171150744, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.01948286761995405, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.020279164207167924, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.02321965859271586, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.027116904659196736, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.030173692759126423, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.03155464372597635, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.0330422854796052, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.033952227029949426, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.034951534029096364, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.03651532768271863, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.037723232982680203, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.03862840034067631, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.03911545492708683, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.03980724275112152, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.04054905094206333, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.04147405132651329, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.04232985273003578, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.042938406206667425, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.043540283087641, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.04412053236737847, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.04427600719034672, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.043984577115625145, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.04365301292389631, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.04299510110169649, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.042401733659207824, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.04139119420200586, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.04073977516964078, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.039864131677895785, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.039140650723129514, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.03904179933480918, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.03900881973095238, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.03947622464969754, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.039810973592102526, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.04037003468722105, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.040617864169180395, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.041070366110652685, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1150591373443604, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.113649606704712, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1112542152404785, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.108621835708618, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1056857109069824, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.100538730621338, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.0916361808776855, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.0718438625335693, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.99639892578125, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.8246912956237793, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.68607759475708, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.5866317749023438, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.530733108520508, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.4817898273468018, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.458021640777588, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.437864065170288, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.421323776245117, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.416290521621704, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.423558235168457, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.4290688037872314, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.4481945037841797, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.4924888610839844, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.5336241722106934, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.5665669441223145, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.629058837890625, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.693382978439331, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.7571170330047607, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.848057985305786, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.9325549602508545, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.147480010986328, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.215578079223633, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.2735953330993652, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.377134084701538, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.493337392807007, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.62528920173645, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.669389009475708, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.656925916671753, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.678008794784546, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.6618740558624268, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.6312668323516846, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.468623161315918, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.403730869293213, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.3258979320526123, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06995201181247693, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.07032115171650055, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.07161314138058324, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.07290513104466592, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.07641196013289037, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.07936507936507936, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.08711701734957548, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.1020671834625323, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.132890365448505, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.16832779623477298, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.19490586932447398, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.22406792174234036, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.24031007751937986, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.25193798449612403, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.257844222960502, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.26356589147286824, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.27648578811369506, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.2768549280177187, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.2737172388335179, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.2692875599852344, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.2691029900332226, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.2622739018087855, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.2556293835363603, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.2574750830564784, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.2556293835363603, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.24916943521594684, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.24437061646363972, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.24049464747139165, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.2364341085271318, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.21539313399778517, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.22296050203026946, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.2222222222222222, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.21428571428571427, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.2159468438538206, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.21410114433370248, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.20358065706902917, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.20671834625322996, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.2072720561092654, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.20801033591731266, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.20837947582133629, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.21963824289405684, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.22535991140642303, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.2203765227021041, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.012742105202631764, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.01366890065455281, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.015469191543063976, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.01702033880439265, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.01930292210328308, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.0232357383094637, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.02966869776008495, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.04185111035854864, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.058728864327747606, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.08579740499725559, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.11352899616261934, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.14377126384143435, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.15988901018801027, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.17505665011609342, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.183653703228025, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.19236829956735743, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.20661466924969007, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.21344993579382965, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.2131840233151637, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.21282501388482103, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.21515945341145912, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.21309012451187917, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.2086531441505449, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.21369724614444263, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.21528494957786057, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.2075081702077939, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.2062051124707982, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.20434285853785236, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.19977319568611426, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.1841233891314613, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.19064183341714305, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.19204156574702988, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.18561984505632176, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.1849203818014901, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.18571025303219457, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.17824753124210155, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.1790221561678567, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.1785713834375476, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.17963275528704103, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.18674458903684707, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.19279930259654865, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.1963648532197999, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.1913306159035806, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 17, "lr_best": 9.599999999999999e-05, "wd_best": 0.05, "train/loss_best": 2.094432888031006, "validation/loss_best": 2.416290521621704, "validation/acc_best": 0.2768549280177187, "validation/f1_best": 0.21344993579382965} +{"epoch": 19, "train/lr": 1.0867618231465446e-06, "train/loss": 1.9763227838277817, "train/grad": 0.23215076863765716, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.117674560546875, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.1158837890625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.112779541015625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.10956787109375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.105899658203125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.1001629638671875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.0909027099609374, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.0715362548828127, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.9999517822265624, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.8311947631835936, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.6852590942382815, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.5706099700927734, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.4941152572631835, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.4034957122802734, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.3333820724487304, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.266510257720947, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.186553301811218, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.1017729473114013, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.016514902114868, "train/loss_019_lr4.4e-01_wd1.0e+00": 1.9431707501411437, "train/loss_020_lr5.2e-01_wd1.0e+00": 1.8583592510223388, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.7705296897888183, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.6709461188316346, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.5716871845722198, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.4815536206960678, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.3764333200454713, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.27926902115345, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.2058613550662995, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.1048068851232529, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.009303368330002, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.9407733741402626, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.8683479422330856, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.76455351293087, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.7142659986019134, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.6691442388296127, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.6434012922644615, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.6415248174965381, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.6613149175047874, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.6873696196079254, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.6989094761013984, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.808342900276184, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.827645066678524, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.8972873106598854, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.171875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.019273680062033238, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.01926610612310469, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.019249746603891255, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.019229674045927823, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.01920446043368429, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.01915924922097474, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.019104097723029553, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.019117229585535824, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.019915823205374182, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.022821868034079672, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.026641897782683374, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.029618379482999443, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.030975968819111587, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.032473029056563976, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.033406174024567005, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.03443582881242037, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.03604234931059182, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.037292004926130176, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.03823652071878314, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.0387511139549315, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.039464220674708485, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.04020767074078321, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.04113277116790414, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.04208208648487925, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.04269513277336955, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.04331895735114813, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.04385103465989232, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0439702126942575, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.04376678179949522, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.04327743209898472, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.04255273025482893, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.041914561875164506, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.04096734140068293, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.039963407181203364, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.03901601938530803, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.03838308159261942, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.03816307490691542, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.03818461443297565, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.03844542847946286, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.03846849298104644, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0391470167785883, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.039320308547466994, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.03968249661847949, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.115056276321411, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1136362552642822, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1112232208251953, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.108597755432129, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1056597232818604, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.10054349899292, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.091573476791382, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.0717532634735107, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.9961912631988525, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.824349880218506, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.685816526412964, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.586399555206299, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.530531644821167, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.48142147064209, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.4576306343078613, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.4374663829803467, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.420771837234497, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.415623664855957, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.4226136207580566, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.4278509616851807, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.446833848953247, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.4910573959350586, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.5320119857788086, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.5647661685943604, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.6275839805603027, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.692242383956909, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.7547342777252197, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.8453614711761475, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.930485725402832, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.1442487239837646, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.2094929218292236, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.2738542556762695, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.382387161254883, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.4967894554138184, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.6254444122314453, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.673466920852661, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.669386148452759, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.700864791870117, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.6807310581207275, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.651893138885498, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.4768385887145996, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.412957191467285, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.344024419784546, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06995201181247693, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.07032115171650055, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.07179771133259505, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.07290513104466592, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.07622739018087855, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.07936507936507936, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.08748615725359911, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.1020671834625323, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.13325950535252862, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.16814322628276115, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.19509043927648578, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.22517534145441123, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.24012550756736803, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.2517534145441122, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.2574750830564784, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.26393503137689184, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.27722406792174237, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.27740863787375414, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.2724252491694352, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.268733850129199, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.26744186046511625, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.26264304171280917, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.25489110372831303, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.2587670727205611, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.2558139534883721, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.25046142488002954, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.24510889627168697, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.24086378737541528, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.23883351790328536, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.21779254337393872, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.2248062015503876, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.22277593207825766, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.21539313399778517, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.21668512366186785, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.2131782945736434, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.20284237726098192, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.2054263565891473, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.2054263565891473, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.21114802510151348, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.20616463639719454, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.2220376522702104, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.22535991140642303, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.21963824289405684, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.012604483757328339, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.013664876557741715, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.015535810234113026, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.017016358534710303, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.01908810165370325, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.02282124549567334, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.029664132785832745, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.041843522903004415, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.058896120300224813, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.08568465922520208, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.1136040081685905, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.14454765480270024, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.15974549112562472, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.17499619139135414, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.1838530039649565, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.19255675570076422, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.2072847922697599, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.21422279215362372, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.21145957230555948, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.2121342998571646, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.21408281315050592, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.21303872110495972, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.2078860878494608, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.21491408148502358, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.2157940651966843, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.20868072509021088, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.20704410670040627, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.2051986222262062, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.2025795846978531, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.18635047749977582, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.19250656924504161, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.1929558122985071, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.18570882468887187, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.1851540158184477, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.18369213716235164, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.17678627017757256, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.17688226744490976, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.17528191586644812, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.18086008117226282, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.1835072221496491, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.19490648252760848, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.19560735972171914, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.1917748351964399, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 17, "lr_best": 9.599999999999999e-05, "wd_best": 0.05, "train/loss_best": 2.1017729473114013, "validation/loss_best": 2.415623664855957, "validation/acc_best": 0.27740863787375414, "validation/f1_best": 0.21422279215362372} diff --git a/input_space_v3/flat_lr1e-3_2/eval_v2/ppmi_dx__patch__logistic/config.yaml b/input_space_v3/flat_lr1e-3_2/eval_v2/ppmi_dx__patch__logistic/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..ecc7858e41dd0f2488d5b0a8ab95115a8010383d --- /dev/null +++ b/input_space_v3/flat_lr1e-3_2/eval_v2/ppmi_dx__patch__logistic/config.yaml @@ -0,0 +1,30 @@ +output_root: experiments/input_space_v3/output +name_prefix: eval_logistic +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_2; eval v2 (ppmi_dx patch logistic) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: input_space_v3/flat_lr1e-3_2/eval_v2/ppmi_dx__patch__logistic +model: flat_mae +representation: patch +dataset: ppmi_dx +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/eval_v2/ppmi_dx__patch__logistic +remote_dir: null diff --git a/input_space_v3/flat_lr1e-3_2/eval_v2/ppmi_dx__patch__logistic/eval_table.csv b/input_space_v3/flat_lr1e-3_2/eval_v2/ppmi_dx__patch__logistic/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..f97c76627cc050f4505f7cccdb8dd4992170414c --- /dev/null +++ b/input_space_v3/flat_lr1e-3_2/eval_v2/ppmi_dx__patch__logistic/eval_table.csv @@ -0,0 +1,203 @@ +model,repr,clf,dataset,trial,C,split,acc,acc_std,f1,f1_std,bacc,bacc_std +flat_mae,patch,logistic,ppmi_dx,,0.005994842503189409,train,0.7419928825622776,0.016454455060060928,0.705006099702074,0.020279700723245926,0.6975288853269218,0.018853414152125453 +flat_mae,patch,logistic,ppmi_dx,,0.005994842503189409,test,0.61,0.040036278548336635,0.5311936530833032,0.04826536676993107,0.53989703989704,0.04222657871651418 +flat_mae,patch,logistic,ppmi_dx,1,0.3593813663804626,train,0.9234875444839857,0.011419149185622542,0.9180310631268677,0.012376540137792727,0.912639156497538,0.013001615780329817 +flat_mae,patch,logistic,ppmi_dx,1,0.3593813663804626,test,0.58,0.05062304218436501,0.5384615384615385,0.05574943275392334,0.5390492359932089,0.0536327845110648 +flat_mae,patch,logistic,ppmi_dx,2,0.046415888336127774,train,0.7935943060498221,0.015746504994724745,0.7675864527629234,0.01899497661609481,0.756703596660244,0.018425195917072788 +flat_mae,patch,logistic,ppmi_dx,2,0.046415888336127774,test,0.68,0.04078560530383237,0.6323529411764706,0.04850766526743818,0.6298811544991512,0.04447386922062997 +flat_mae,patch,logistic,ppmi_dx,3,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,3,21.54434690031882,test,0.63,0.04749219304264649,0.6093337556752191,0.049654404405288975,0.6099320882852293,0.049892947644090746 +flat_mae,patch,logistic,ppmi_dx,4,0.3593813663804626,train,0.9199288256227758,0.011212869758508468,0.9143858223734322,0.012130949201599602,0.9097489830871334,0.012772959300878963 +flat_mae,patch,logistic,ppmi_dx,4,0.3593813663804626,test,0.61,0.04913491630195375,0.5953937130407718,0.05055084006885754,0.5988964346349746,0.051703797410431865 +flat_mae,patch,logistic,ppmi_dx,5,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,5,1291.5496650148827,test,0.62,0.04752782763813217,0.5967741935483871,0.050587240899973976,0.5967741935483871,0.05042166538941763 +flat_mae,patch,logistic,ppmi_dx,6,0.046415888336127774,train,0.8131672597864769,0.015130947361789592,0.7920740795551844,0.017830692693861096,0.7812968315135945,0.01768665183171283 +flat_mae,patch,logistic,ppmi_dx,6,0.046415888336127774,test,0.61,0.04558021939394325,0.568536342515765,0.05169585693936591,0.5683361629881154,0.04896557507806751 +flat_mae,patch,logistic,ppmi_dx,7,0.005994842503189409,train,0.7544483985765125,0.01605086321200304,0.7163360252808989,0.020081424938318247,0.7075171269535432,0.01853906974691657 +flat_mae,patch,logistic,ppmi_dx,7,0.005994842503189409,test,0.6,0.04808765330102936,0.5604395604395604,0.05221674921355568,0.5602716468590832,0.05024351606157129 +flat_mae,patch,logistic,ppmi_dx,8,0.046415888336127774,train,0.8096085409252669,0.01543389578965586,0.788113585832426,0.01804567697728303,0.7775369299935774,0.01783969809380515 +flat_mae,patch,logistic,ppmi_dx,8,0.046415888336127774,test,0.58,0.039933639954304184,0.5,0.048559469875930426,0.5135823429541596,0.041933181983866676 +flat_mae,patch,logistic,ppmi_dx,9,0.005994842503189409,train,0.7366548042704626,0.016791058367138106,0.694856555873505,0.021067232365993803,0.687847891243845,0.01924959973842367 +flat_mae,patch,logistic,ppmi_dx,9,0.005994842503189409,test,0.71,0.036938061670856524,0.6579785352046232,0.047708768034046424,0.6540747028862479,0.04235342685605443 +flat_mae,patch,logistic,ppmi_dx,10,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,10,166.81005372000556,test,0.6,0.04787431461650391,0.5833333333333333,0.0494137405004039,0.5857385398981324,0.05043196678553929 +flat_mae,patch,logistic,ppmi_dx,11,0.046415888336127774,train,0.8042704626334519,0.0155082582071014,0.7790122397620682,0.01868102627072336,0.767113573110683,0.018228716348721093 +flat_mae,patch,logistic,ppmi_dx,11,0.046415888336127774,test,0.64,0.044900939856533074,0.592944369063772,0.05248885384898926,0.5925297113752122,0.048622714663767226 +flat_mae,patch,logistic,ppmi_dx,12,0.005994842503189409,train,0.7473309608540926,0.015521382400896436,0.7089866826144668,0.019423367421747124,0.7008670520231214,0.017988705465498075 +flat_mae,patch,logistic,ppmi_dx,12,0.005994842503189409,test,0.58,0.03534770713921908,0.4672754946727549,0.045056884263041164,0.49830220713073003,0.036544257163874175 +flat_mae,patch,logistic,ppmi_dx,13,0.005994842503189409,train,0.7473309608540926,0.016560895020496024,0.7054115909929863,0.021134631164960952,0.6973881395846714,0.019216364974282824 +flat_mae,patch,logistic,ppmi_dx,13,0.005994842503189409,test,0.62,0.038803278212027406,0.5558672276764843,0.0467954586352611,0.5611205432937181,0.04129868821489986 +flat_mae,patch,logistic,ppmi_dx,14,0.005994842503189409,train,0.7455516014234875,0.016444021586094357,0.7064995489721313,0.020456112229315017,0.6985522372083066,0.018884744904651047 +flat_mae,patch,logistic,ppmi_dx,14,0.005994842503189409,test,0.61,0.04385001254275762,0.5481404240528328,0.05145581358092186,0.5530560271646858,0.04648665522218561 +flat_mae,patch,logistic,ppmi_dx,15,0.000774263682681127,train,0.6832740213523132,0.014748754293835934,0.6051376784135405,0.021123745841142773,0.6131850781417255,0.01694352935053809 +flat_mae,patch,logistic,ppmi_dx,15,0.000774263682681127,test,0.66,0.03575134123358171,0.5687468290208015,0.05190908101691091,0.5831918505942275,0.04055843739922853 +flat_mae,patch,logistic,ppmi_dx,16,0.046415888336127774,train,0.8256227758007118,0.014439389842636053,0.803650623885918,0.017400809216314272,0.7905427103403981,0.017254142663159572 +flat_mae,patch,logistic,ppmi_dx,16,0.046415888336127774,test,0.65,0.04639090859209377,0.6178622120318812,0.05091093889906162,0.615874363327674,0.04968206203710462 +flat_mae,patch,logistic,ppmi_dx,17,0.046415888336127774,train,0.8131672597864769,0.015252452741237224,0.7915452358495565,0.017860583496503133,0.780427103403982,0.017574193952301653 +flat_mae,patch,logistic,ppmi_dx,17,0.046415888336127774,test,0.65,0.04284631139316429,0.6072270227808326,0.04895443950805885,0.6056876061120543,0.04629867554081219 +flat_mae,patch,logistic,ppmi_dx,18,0.005994842503189409,train,0.7402135231316725,0.015854310601565228,0.7033979178716021,0.019101707113986576,0.6959564333119246,0.017802018685580664 +flat_mae,patch,logistic,ppmi_dx,18,0.005994842503189409,test,0.59,0.04515701938790912,0.5249681381068243,0.051488883798740274,0.5318336162988115,0.046699475747965305 +flat_mae,patch,logistic,ppmi_dx,19,2.782559402207126,train,0.998220640569395,0.0016936324053745853,0.9981184064710746,0.001793897517729083,0.9976851851851851,0.0022032903051400848 +flat_mae,patch,logistic,ppmi_dx,19,2.782559402207126,test,0.6,0.04586039249723012,0.5796553173602353,0.04762452440117721,0.5806451612903225,0.04810112326142243 +flat_mae,patch,logistic,ppmi_dx,20,0.005994842503189409,train,0.7348754448398577,0.016727921065374882,0.6904039190313338,0.021360887124910438,0.6837936202098052,0.019284488140902063 +flat_mae,patch,logistic,ppmi_dx,20,0.005994842503189409,test,0.64,0.040935383227716345,0.5714285714285714,0.05174307013246583,0.5772495755517827,0.044733386979458764 +flat_mae,patch,logistic,ppmi_dx,21,0.046415888336127774,train,0.8113879003558719,0.015526277254836565,0.7892897566496888,0.018199287966225452,0.7781122885891671,0.01786918751083217 +flat_mae,patch,logistic,ppmi_dx,21,0.046415888336127774,test,0.73,0.03751809696666397,0.6815662224318906,0.04822331452368974,0.6752971137521222,0.043026367324499146 +flat_mae,patch,logistic,ppmi_dx,22,0.005994842503189409,train,0.7348754448398577,0.01707050334856582,0.6932617813513068,0.021376566557669657,0.6864028045386428,0.01958657948488148 +flat_mae,patch,logistic,ppmi_dx,22,0.005994842503189409,test,0.66,0.04291888162569011,0.5952380952380952,0.054185921950591326,0.5984719864176571,0.047009202616914984 +flat_mae,patch,logistic,ppmi_dx,23,0.005994842503189409,train,0.7473309608540926,0.015842742901021892,0.7072272360407954,0.020153471634064963,0.6991275958038964,0.01847406681409053 +flat_mae,patch,logistic,ppmi_dx,23,0.005994842503189409,test,0.65,0.041254774269167925,0.5872154735228211,0.05243907453348672,0.5904074702886248,0.04586431599207431 +flat_mae,patch,logistic,ppmi_dx,24,0.046415888336127774,train,0.8131672597864769,0.014956161587045448,0.7925944150572026,0.017398872417677385,0.782166559623207,0.017246362763337235 +flat_mae,patch,logistic,ppmi_dx,24,0.046415888336127774,test,0.62,0.04764567136687235,0.5766488413547237,0.052929325669576525,0.5764006791171477,0.0502203206147114 +flat_mae,patch,logistic,ppmi_dx,25,0.005994842503189409,train,0.7348754448398577,0.015637836351644643,0.6904039190313338,0.02016594333252289,0.6837936202098052,0.018190414779588753 +flat_mae,patch,logistic,ppmi_dx,25,0.005994842503189409,test,0.68,0.03509116697974006,0.6031746031746031,0.05096606985912569,0.6095076400679117,0.04094598494604388 +flat_mae,patch,logistic,ppmi_dx,26,0.005994842503189409,train,0.7384341637010676,0.015257931896518355,0.6955142026293385,0.01942655012387205,0.6884232498394348,0.017633580658692315 +flat_mae,patch,logistic,ppmi_dx,26,0.005994842503189409,test,0.68,0.04371531081897965,0.64349376114082,0.048776443826310314,0.6400679117147707,0.04641883271680657 +flat_mae,patch,logistic,ppmi_dx,27,0.005994842503189409,train,0.7330960854092526,0.01729187720028431,0.6868359659420182,0.022232696969329595,0.6806090772853779,0.019965463519649486 +flat_mae,patch,logistic,ppmi_dx,27,0.005994842503189409,test,0.65,0.041165888791571105,0.5792763553311696,0.05297581897692633,0.5853140916808149,0.04537014016082375 +flat_mae,patch,logistic,ppmi_dx,28,0.005994842503189409,train,0.7384341637010676,0.015014581970937753,0.6964539632499642,0.019145873727540327,0.6892929779490473,0.017406463056166877 +flat_mae,patch,logistic,ppmi_dx,28,0.005994842503189409,test,0.68,0.038626265675055865,0.6190476190476191,0.05067643850152025,0.6196943972835314,0.043827925671537475 +flat_mae,patch,logistic,ppmi_dx,29,0.005994842503189409,train,0.7348754448398577,0.016091078583948544,0.6894209977783465,0.020755520979605882,0.6829238921001927,0.018603151554823054 +flat_mae,patch,logistic,ppmi_dx,29,0.005994842503189409,test,0.65,0.041641690647715064,0.5872154735228211,0.05280141029970335,0.5904074702886248,0.04616828378276605 +flat_mae,patch,logistic,ppmi_dx,30,2.782559402207126,train,0.99644128113879,0.002486268822022564,0.9962400984799828,0.002627303432558263,0.9962400984799828,0.002723732803738478 +flat_mae,patch,logistic,ppmi_dx,30,2.782559402207126,test,0.62,0.050120698319157525,0.5967741935483871,0.052457368811170836,0.5967741935483871,0.05229178981356136 +flat_mae,patch,logistic,ppmi_dx,31,0.005994842503189409,train,0.7491103202846975,0.01612539514043145,0.7123107140134256,0.020089578103188413,0.7040515949475488,0.018703156594970727 +flat_mae,patch,logistic,ppmi_dx,31,0.005994842503189409,test,0.62,0.04672172513938243,0.5824175824175825,0.050421569470349314,0.5814940577249575,0.048475571415569706 +flat_mae,patch,logistic,ppmi_dx,32,0.3593813663804626,train,0.9217081850533808,0.010993273680296557,0.9163690476190476,0.011859833406988906,0.9120637979019481,0.012547037989648189 +flat_mae,patch,logistic,ppmi_dx,32,0.3593813663804626,test,0.58,0.048550555094663946,0.565936337329475,0.04942247459965796,0.5696095076400679,0.05071181379071378 +flat_mae,patch,logistic,ppmi_dx,33,0.3593813663804626,train,0.9270462633451957,0.01098013048235338,0.9215305660274551,0.012052475921583492,0.9146596017983302,0.013025099035114318 +flat_mae,patch,logistic,ppmi_dx,33,0.3593813663804626,test,0.63,0.04943773457592894,0.6214833759590792,0.04973279805521636,0.6303056027164686,0.05108773384272932 +flat_mae,patch,logistic,ppmi_dx,34,0.005994842503189409,train,0.7366548042704626,0.016117588195257354,0.6910114863961246,0.020262472419618698,0.6843689788053949,0.01824870980606755 +flat_mae,patch,logistic,ppmi_dx,34,0.005994842503189409,test,0.7,0.04059388623918631,0.6493688639551192,0.050704570555705424,0.6460101867572157,0.045738304032563716 +flat_mae,patch,logistic,ppmi_dx,35,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,35,166.81005372000556,test,0.56,0.04939739264374183,0.5512035903712771,0.049388990122135386,0.5585738539898133,0.05073022639480729 +flat_mae,patch,logistic,ppmi_dx,36,0.3593813663804626,train,0.9074733096085409,0.011591321497507778,0.900776836158192,0.012620335094876292,0.8952847356026546,0.013285984174572224 +flat_mae,patch,logistic,ppmi_dx,36,0.3593813663804626,test,0.66,0.04478135326226754,0.609375,0.05328735223874716,0.6086587436332768,0.048691477040772105 +flat_mae,patch,logistic,ppmi_dx,37,0.005994842503189409,train,0.7330960854092526,0.016824004414224075,0.6916695926966292,0.020734413049113158,0.6849577178334404,0.018990888967492105 +flat_mae,patch,logistic,ppmi_dx,37,0.005994842503189409,test,0.65,0.04336484751500921,0.6011396011396011,0.05125487198635133,0.6005942275042444,0.0472370087721189 +flat_mae,patch,logistic,ppmi_dx,38,0.005994842503189409,train,0.7295373665480427,0.01671504867380067,0.683671051072402,0.021452684045025913,0.6777189038749732,0.019329654914530883 +flat_mae,patch,logistic,ppmi_dx,38,0.005994842503189409,test,0.63,0.043612195542072865,0.5906626839252129,0.04836086011611163,0.5895585738539898,0.046335604002988987 +flat_mae,patch,logistic,ppmi_dx,39,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,39,166.81005372000556,test,0.66,0.04646617694624769,0.6565656565656566,0.046046207180055504,0.6748726655348047,0.046517120660873316 +flat_mae,patch,logistic,ppmi_dx,40,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,40,21.54434690031882,test,0.57,0.051562509636362726,0.5538956323270048,0.052435337721578934,0.5564516129032258,0.05345295388958267 +flat_mae,patch,logistic,ppmi_dx,41,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,41,21.54434690031882,test,0.65,0.04822402305905222,0.6368917937545389,0.048996239875070936,0.6413412563667232,0.04961306825080136 +flat_mae,patch,logistic,ppmi_dx,42,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,42,21.54434690031882,test,0.64,0.046410929747205024,0.5989304812834224,0.05282586862041195,0.597623089983022,0.05028422002034392 +flat_mae,patch,logistic,ppmi_dx,43,0.005994842503189409,train,0.7384341637010676,0.016379500244730272,0.6973790728767926,0.02046071503101649,0.6901627060586598,0.018779036956946785 +flat_mae,patch,logistic,ppmi_dx,43,0.005994842503189409,test,0.69,0.03796678021639443,0.627359057579036,0.050574928600271754,0.6277589134125636,0.04335587484394197 +flat_mae,patch,logistic,ppmi_dx,44,0.005994842503189409,train,0.7277580071174378,0.01653404642860608,0.6840643290969015,0.020732156870651115,0.678013273388996,0.018841166100824397 +flat_mae,patch,logistic,ppmi_dx,44,0.005994842503189409,test,0.64,0.04122074720331984,0.5863970588235294,0.05019508886310412,0.5874363327674024,0.045533985056539376 +flat_mae,patch,logistic,ppmi_dx,45,0.005994842503189409,train,0.7330960854092526,0.015811340642933724,0.6837484993997599,0.0207504646282328,0.6779998929565404,0.018283673522757896 +flat_mae,patch,logistic,ppmi_dx,45,0.005994842503189409,test,0.75,0.03436125143239112,0.6865203761755485,0.051340018271145677,0.6812393887945671,0.04256957438169377 +flat_mae,patch,logistic,ppmi_dx,46,2.782559402207126,train,0.998220640569395,0.0017253695223348477,0.9981184064710746,0.0018274376383873934,0.9976851851851851,0.002244577943407832 +flat_mae,patch,logistic,ppmi_dx,46,2.782559402207126,test,0.62,0.046748155043808956,0.5766488413547237,0.054053880828127294,0.5764006791171477,0.05046591746984092 +flat_mae,patch,logistic,ppmi_dx,47,0.3593813663804626,train,0.9145907473309609,0.011260465807257983,0.9084093872229465,0.01225468890867792,0.902804538642689,0.012948390259899342 +flat_mae,patch,logistic,ppmi_dx,47,0.3593813663804626,test,0.65,0.050154226142968245,0.630450849963045,0.05188552909965393,0.6311544991511036,0.05189241205912363 +flat_mae,patch,logistic,ppmi_dx,48,0.046415888336127774,train,0.798932384341637,0.01574405338149039,0.7732924465324161,0.019023637542495146,0.7619085848854634,0.0185240521267247 +flat_mae,patch,logistic,ppmi_dx,48,0.046415888336127774,test,0.71,0.0433671719160934,0.6833715471121302,0.04840429742014023,0.6795415959252971,0.0472476025431973 +flat_mae,patch,logistic,ppmi_dx,49,0.005994842503189409,train,0.7455516014234875,0.015760624905122964,0.7028708753119512,0.02010855574255545,0.6950733247698566,0.018214356105653477 +flat_mae,patch,logistic,ppmi_dx,49,0.005994842503189409,test,0.68,0.03802072592678892,0.6114618746964546,0.051044365297386526,0.6146010186757216,0.04279390220497022 +flat_mae,patch,logistic,ppmi_dx,50,0.3593813663804626,train,0.9306049822064056,0.010594785396137231,0.9259434456334069,0.011402568861630213,0.9218984157567973,0.011980760113594393 +flat_mae,patch,logistic,ppmi_dx,50,0.3593813663804626,test,0.58,0.04475746194770208,0.5442708333333334,0.04849454694265064,0.5441426146010186,0.04716986441176352 +flat_mae,patch,logistic,ppmi_dx,51,0.005994842503189409,train,0.7348754448398577,0.01622632353028035,0.6950934877200649,0.01994565787175753,0.6881422607578677,0.018374094106255213 +flat_mae,patch,logistic,ppmi_dx,51,0.005994842503189409,test,0.6,0.04136009671168577,0.5324918186068257,0.05021692530386152,0.5398981324278438,0.04449026640691734 +flat_mae,patch,logistic,ppmi_dx,52,0.046415888336127774,train,0.8238434163701067,0.01558559401323643,0.8044461627682196,0.018099905424115017,0.7934462641832585,0.018010144646063146 +flat_mae,patch,logistic,ppmi_dx,52,0.046415888336127774,test,0.65,0.04609803032668532,0.6072270227808326,0.05233334738624817,0.6056876061120543,0.04936509660965328 +flat_mae,patch,logistic,ppmi_dx,53,0.3593813663804626,train,0.9145907473309609,0.012086697595317506,0.9085893977797959,0.01311105948146458,0.9036742667523014,0.01381967881735126 +flat_mae,patch,logistic,ppmi_dx,53,0.3593813663804626,test,0.64,0.046266186356776796,0.609375,0.05020029988000893,0.6078098471986417,0.04903475042929727 +flat_mae,patch,logistic,ppmi_dx,54,0.005994842503189409,train,0.7473309608540926,0.016108117061454166,0.706326542628356,0.01999144278152981,0.6982578676942839,0.018229487815327818 +flat_mae,patch,logistic,ppmi_dx,54,0.005994842503189409,test,0.58,0.0458673042591343,0.5442708333333334,0.04770655847157282,0.5441426146010186,0.046585778387492435 +flat_mae,patch,logistic,ppmi_dx,55,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,55,2.782559402207126,test,0.64,0.0445790264586386,0.6179966044142615,0.047702942848571475,0.6179966044142615,0.04776733415738953 +flat_mae,patch,logistic,ppmi_dx,56,0.005994842503189409,train,0.7455516014234875,0.015638215362183627,0.7028708753119512,0.020321881019768173,0.6950733247698566,0.018433101518074955 +flat_mae,patch,logistic,ppmi_dx,56,0.005994842503189409,test,0.6,0.043633638399748424,0.5324918186068257,0.05149826387142147,0.5398981324278438,0.045948443589461596 +flat_mae,patch,logistic,ppmi_dx,57,0.3593813663804626,train,0.9234875444839857,0.011325412968790182,0.917534286777026,0.012436516089208325,0.9100299721687005,0.01332001111302439 +flat_mae,patch,logistic,ppmi_dx,57,0.3593813663804626,test,0.62,0.049150609355327425,0.5924495924495925,0.052934944118743964,0.5916808149405772,0.052308622042181036 +flat_mae,patch,logistic,ppmi_dx,58,0.005994842503189409,train,0.7384341637010676,0.016832730808872348,0.6964539632499642,0.021424697212404763,0.6892929779490473,0.01951112710840313 +flat_mae,patch,logistic,ppmi_dx,58,0.005994842503189409,test,0.67,0.040387146470133285,0.6108031607500884,0.05154599275899867,0.6116298811544991,0.04529364329364356 +flat_mae,patch,logistic,ppmi_dx,59,0.046415888336127774,train,0.8185053380782918,0.01581509196226508,0.7992632227700582,0.018312860367798958,0.7891110040676514,0.01834459572570766 +flat_mae,patch,logistic,ppmi_dx,59,0.046415888336127774,test,0.63,0.045454588327252514,0.5906626839252129,0.05107029160643212,0.5895585738539898,0.04839746395804519 +flat_mae,patch,logistic,ppmi_dx,60,0.3593813663804626,train,0.9074733096085409,0.012075336689223342,0.9005783493229911,0.013159010633020529,0.8944150074930421,0.01376898457102308 +flat_mae,patch,logistic,ppmi_dx,60,0.3593813663804626,test,0.6,0.04340127187076434,0.5604395604395604,0.049238254514139435,0.5602716468590832,0.047152232377480625 +flat_mae,patch,logistic,ppmi_dx,61,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,61,21.54434690031882,test,0.56,0.04891586245789804,0.5416666666666666,0.050050896177890984,0.5432937181663837,0.05086556313812863 +flat_mae,patch,logistic,ppmi_dx,62,0.3593813663804626,train,0.9199288256227758,0.011133374463746975,0.9138750114935483,0.012185838853739247,0.9071397987582959,0.01294848693018725 +flat_mae,patch,logistic,ppmi_dx,62,0.3593813663804626,test,0.61,0.04615994367414242,0.584,0.048944657797565023,0.583616298811545,0.048724562485002634 +flat_mae,patch,logistic,ppmi_dx,63,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,63,2.782559402207126,test,0.56,0.05041666391184565,0.5280995280995281,0.05268242551501493,0.5280135823429541,0.051902707458053685 +flat_mae,patch,logistic,ppmi_dx,64,0.046415888336127774,train,0.8238434163701067,0.014791232196531794,0.8044461627682196,0.017176223448316007,0.7934462641832585,0.017163374663406915 +flat_mae,patch,logistic,ppmi_dx,64,0.046415888336127774,test,0.58,0.040862985696104,0.5,0.04785566883102513,0.5135823429541596,0.042157402501553705 +flat_mae,patch,logistic,ppmi_dx,65,0.005994842503189409,train,0.7402135231316725,0.01594594335590585,0.7033979178716021,0.019599827873798853,0.6959564333119246,0.018326413664122146 +flat_mae,patch,logistic,ppmi_dx,65,0.005994842503189409,test,0.56,0.045255412935912974,0.4944852941176471,0.04999001952778139,0.5025466893039049,0.04603407566671651 +flat_mae,patch,logistic,ppmi_dx,66,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,66,2.782559402207126,test,0.54,0.04702276469966435,0.5066495066495067,0.04886941528118106,0.5067911714770797,0.04826173164135048 +flat_mae,patch,logistic,ppmi_dx,67,0.046415888336127774,train,0.8113879003558719,0.015884511758567917,0.7903575450450451,0.018472742795886853,0.7798517448083921,0.018284879387434283 +flat_mae,patch,logistic,ppmi_dx,67,0.046415888336127774,test,0.6,0.04720052542080437,0.570999570999571,0.05056538004539158,0.5704584040747029,0.049884141294308085 +flat_mae,patch,logistic,ppmi_dx,68,2.782559402207126,train,0.994661921708185,0.002997132235362791,0.9943552194132241,0.0031725188403645987,0.993925283665168,0.0034584445051718533 +flat_mae,patch,logistic,ppmi_dx,68,2.782559402207126,test,0.61,0.04628556578459423,0.5793334052421529,0.049281085105863764,0.5785229202037352,0.04832147991858776 +flat_mae,patch,logistic,ppmi_dx,69,0.005994842503189409,train,0.7135231316725978,0.01609682144846962,0.666515555260704,0.020085874279540422,0.6621039391993149,0.01808218375379423 +flat_mae,patch,logistic,ppmi_dx,69,0.005994842503189409,test,0.7,0.04105377449151295,0.6493688639551192,0.05126743480214922,0.6460101867572157,0.04621248707431317 +flat_mae,patch,logistic,ppmi_dx,70,0.005994842503189409,train,0.7437722419928826,0.015266671227353519,0.6983899821109123,0.02012700521418517,0.6910190537358167,0.018026687614172563 +flat_mae,patch,logistic,ppmi_dx,70,0.005994842503189409,test,0.63,0.04326041608676459,0.5783475783475784,0.05062125387438295,0.5793718166383701,0.04636220230837917 +flat_mae,patch,logistic,ppmi_dx,71,0.005994842503189409,train,0.7348754448398577,0.016163520858478525,0.6923240851989433,0.020460345711746958,0.6855330764290302,0.018610404438550478 +flat_mae,patch,logistic,ppmi_dx,71,0.005994842503189409,test,0.66,0.04007331281538874,0.587178241864983,0.052404304063435,0.5933786078098472,0.04432237464763542 +flat_mae,patch,logistic,ppmi_dx,72,0.005994842503189409,train,0.7277580071174378,0.01651332791596524,0.681083306443537,0.02118158586490754,0.6754040890601585,0.018949636757057253 +flat_mae,patch,logistic,ppmi_dx,72,0.005994842503189409,test,0.63,0.04444985939235354,0.5783475783475784,0.05087994644508297,0.5793718166383701,0.04691483017809674 +flat_mae,patch,logistic,ppmi_dx,73,0.005994842503189409,train,0.7402135231316725,0.01695399362164112,0.701672484002327,0.021102107239541236,0.6942169770926996,0.01957597521978184 +flat_mae,patch,logistic,ppmi_dx,73,0.005994842503189409,test,0.67,0.04478043769326065,0.6547756041426928,0.04649715892655601,0.6574702886247878,0.04733047791634636 +flat_mae,patch,logistic,ppmi_dx,74,0.005994842503189409,train,0.7473309608540926,0.016871586993800123,0.711524002313476,0.02034822864668906,0.7034762363519589,0.019092290431495393 +flat_mae,patch,logistic,ppmi_dx,74,0.005994842503189409,test,0.62,0.04361868865520834,0.5634191176470589,0.05112333479648441,0.566213921901528,0.0465698234991788 +flat_mae,patch,logistic,ppmi_dx,75,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,75,2.782559402207126,test,0.56,0.045249548064041474,0.5098039215686274,0.049646380126728326,0.5127334465195246,0.04691978490627809 +flat_mae,patch,logistic,ppmi_dx,76,0.3593813663804626,train,0.9234875444839857,0.011087836684352637,0.918190896934613,0.012026719322863092,0.9135088846071505,0.012777925738476296 +flat_mae,patch,logistic,ppmi_dx,76,0.3593813663804626,test,0.57,0.047572328091023665,0.5361881134721174,0.05025785959049574,0.5360780984719864,0.0492750838907695 +flat_mae,patch,logistic,ppmi_dx,77,0.046415888336127774,train,0.8274021352313167,0.015280982566948877,0.8083967453385585,0.017833465411981195,0.7972061657032755,0.017824011072446123 +flat_mae,patch,logistic,ppmi_dx,77,0.046415888336127774,test,0.63,0.045488266618986486,0.5713127099988413,0.05373953228466832,0.5742784380305602,0.04855712274504877 +flat_mae,patch,logistic,ppmi_dx,78,0.046415888336127774,train,0.802491103202847,0.015275611582386548,0.7801925983869092,0.01790294453539451,0.7700171269535432,0.01769453651304859 +flat_mae,patch,logistic,ppmi_dx,78,0.046415888336127774,test,0.65,0.03838084939133057,0.5706048337627285,0.04985998978811539,0.580220713073005,0.04182106456380939 +flat_mae,patch,logistic,ppmi_dx,79,0.046415888336127774,train,0.7900355871886121,0.01584635571752935,0.7642081010353852,0.018770646262248093,0.7538134232498395,0.018212678270687337 +flat_mae,patch,logistic,ppmi_dx,79,0.046415888336127774,test,0.7,0.0398708464921426,0.6553308823529411,0.04858595544551323,0.6511035653650254,0.044311052635673955 +flat_mae,patch,logistic,ppmi_dx,80,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,80,166.81005372000556,test,0.67,0.045986937275709065,0.648,0.04953055167144808,0.6472835314091681,0.049579061350993964 +flat_mae,patch,logistic,ppmi_dx,81,0.046415888336127774,train,0.7953736654804271,0.015231358299740384,0.7728415022055076,0.01764353027771643,0.7633670520231214,0.01741456461293117 +flat_mae,patch,logistic,ppmi_dx,81,0.046415888336127774,test,0.7,0.043615428462873085,0.6782496782496783,0.0473675878397804,0.6765704584040747,0.04729909980141856 +flat_mae,patch,logistic,ppmi_dx,82,0.005994842503189409,train,0.7366548042704626,0.016212015136443114,0.694856555873505,0.02042821483832045,0.687847891243845,0.018627208049950182 +flat_mae,patch,logistic,ppmi_dx,82,0.005994842503189409,test,0.66,0.041782292900222694,0.5952380952380952,0.05405962879788714,0.5984719864176571,0.04673968067841298 +flat_mae,patch,logistic,ppmi_dx,83,0.005994842503189409,train,0.7704626334519573,0.016062757647107035,0.7383074340787266,0.019482708369062327,0.7283504602868764,0.01840934237982571 +flat_mae,patch,logistic,ppmi_dx,83,0.005994842503189409,test,0.48,0.04727433130145788,0.4357638888888889,0.04815037242380993,0.4380305602716469,0.04744600655705251 +flat_mae,patch,logistic,ppmi_dx,84,0.005994842503189409,train,0.7330960854092526,0.01641530932277423,0.6934991273996509,0.02040908390319361,0.6866971740526654,0.018848513613848473 +flat_mae,patch,logistic,ppmi_dx,84,0.005994842503189409,test,0.62,0.04557760853752641,0.5766488413547237,0.0513754798121224,0.5764006791171477,0.04877529726674091 +flat_mae,patch,logistic,ppmi_dx,85,0.046415888336127774,train,0.8167259786476868,0.015413131020152227,0.794988578208284,0.018157349243191224,0.7833172768143866,0.017850936393205796 +flat_mae,patch,logistic,ppmi_dx,85,0.046415888336127774,test,0.63,0.040423057776472086,0.5847828526540231,0.045461158697809374,0.5844651952461799,0.042787740548711636 +flat_mae,patch,logistic,ppmi_dx,86,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,86,166.81005372000556,test,0.56,0.04719915253476485,0.5280995280995281,0.049504089472301394,0.5280135823429541,0.04893365065268706 +flat_mae,patch,logistic,ppmi_dx,87,0.046415888336127774,train,0.8220640569395018,0.015360835558552022,0.803199238009861,0.017769946316777956,0.7928709055876686,0.01773682036378231 +flat_mae,patch,logistic,ppmi_dx,87,0.046415888336127774,test,0.64,0.04646655141066529,0.6043956043956044,0.05226324006632611,0.6027164685908319,0.05012590972933918 +flat_mae,patch,logistic,ppmi_dx,88,0.046415888336127774,train,0.8167259786476868,0.015469362020872415,0.7975412272878304,0.01781339709023365,0.7876659173624492,0.01776244961605983 +flat_mae,patch,logistic,ppmi_dx,88,0.046415888336127774,test,0.62,0.044901741614329395,0.5703301673450927,0.05209776256550068,0.5713073005093379,0.0481638918249751 +flat_mae,patch,logistic,ppmi_dx,89,0.005994842503189409,train,0.7330960854092526,0.016721834877024933,0.6888150609080841,0.021158455238843868,0.6823485335046029,0.019124134738747977 +flat_mae,patch,logistic,ppmi_dx,89,0.005994842503189409,test,0.69,0.041658857401517854,0.6408295678368672,0.05146769387011758,0.6379456706281834,0.046653876750586784 +flat_mae,patch,logistic,ppmi_dx,90,0.046415888336127774,train,0.8042704626334519,0.014719738817562581,0.782987208110423,0.017127370147564533,0.7732016698779705,0.016993628545249436 +flat_mae,patch,logistic,ppmi_dx,90,0.046415888336127774,test,0.68,0.0424562645554222,0.64349376114082,0.048260184299712315,0.6400679117147707,0.04597450561398131 +flat_mae,patch,logistic,ppmi_dx,91,0.046415888336127774,train,0.8256227758007118,0.01554732548690359,0.8056900128420429,0.018254019773822454,0.7940216227788482,0.01811412145228043 +flat_mae,patch,logistic,ppmi_dx,91,0.046415888336127774,test,0.63,0.04549681307520341,0.6009060511271707,0.0492182832924272,0.5997453310696095,0.04818904276915539 +flat_mae,patch,logistic,ppmi_dx,92,0.3593813663804626,train,0.9199288256227758,0.011743381315611399,0.9143858223734322,0.012709740883985712,0.9097489830871334,0.013436667569694158 +flat_mae,patch,logistic,ppmi_dx,92,0.3593813663804626,test,0.67,0.044214364181790505,0.6396986570586308,0.04894480311055005,0.6370967741935484,0.04776421540898359 +flat_mae,patch,logistic,ppmi_dx,93,0.005994842503189409,train,0.7437722419928826,0.015764269395120586,0.704002808988764,0.01945782816093361,0.6962374223934917,0.017900921187293462 +flat_mae,patch,logistic,ppmi_dx,93,0.005994842503189409,test,0.61,0.045560557503173726,0.568536342515765,0.05063678705401888,0.5683361629881154,0.04828835433969353 +flat_mae,patch,logistic,ppmi_dx,94,0.005994842503189409,train,0.7330960854092526,0.016320363848935766,0.6907329958177416,0.02028919018054198,0.6840879897238279,0.01844685202532332 +flat_mae,patch,logistic,ppmi_dx,94,0.005994842503189409,test,0.7,0.03776353267373167,0.6428571428571428,0.04899754390361405,0.6409168081494058,0.04276920873746684 +flat_mae,patch,logistic,ppmi_dx,95,0.046415888336127774,train,0.8220640569395018,0.01570194355874108,0.805056055056055,0.01770426135927115,0.7963498180261186,0.017762794553097615 +flat_mae,patch,logistic,ppmi_dx,95,0.046415888336127774,test,0.61,0.044433586395878515,0.5623386825272135,0.05010317619605685,0.5632427843803056,0.04716518658801797 +flat_mae,patch,logistic,ppmi_dx,96,0.046415888336127774,train,0.8078291814946619,0.015393392181075277,0.7847567981616239,0.018455471761296263,0.7734826589595376,0.018202742554526873 +flat_mae,patch,logistic,ppmi_dx,96,0.046415888336127774,test,0.61,0.04479732134849136,0.568536342515765,0.04927671429379426,0.5683361629881154,0.04708643555665793 +flat_mae,patch,logistic,ppmi_dx,97,0.046415888336127774,train,0.8042704626334519,0.015339874472694815,0.7801939924906133,0.018171795681523262,0.7688530293299078,0.017800591117054686 +flat_mae,patch,logistic,ppmi_dx,97,0.046415888336127774,test,0.68,0.042111281148879805,0.6381727725011307,0.049063652765318946,0.634974533106961,0.0456879704641437 +flat_mae,patch,logistic,ppmi_dx,98,0.3593813663804626,train,0.9199288256227758,0.011860948903405595,0.9140482947304025,0.0129729053218233,0.9080095268679084,0.013854306175586419 +flat_mae,patch,logistic,ppmi_dx,98,0.3593813663804626,test,0.62,0.04602992070382047,0.5824175824175825,0.05189372819498984,0.5814940577249575,0.04966789052137315 +flat_mae,patch,logistic,ppmi_dx,99,0.046415888336127774,train,0.8113879003558719,0.015527468102542024,0.7881869382182274,0.0184693636404483,0.7763728323699421,0.018139173243659948 +flat_mae,patch,logistic,ppmi_dx,99,0.046415888336127774,test,0.62,0.043527366104555425,0.5703301673450927,0.05030342788626905,0.5713073005093379,0.04661317431996313 +flat_mae,patch,logistic,ppmi_dx,100,0.046415888336127774,train,0.8096085409252669,0.014585265440123667,0.7870269695950134,0.0174381204315047,0.7757974737743524,0.017293951249701726 +flat_mae,patch,logistic,ppmi_dx,100,0.046415888336127774,test,0.6,0.04865373161433766,0.5755517826825127,0.05270138338998095,0.5755517826825127,0.05255262216535191 diff --git a/input_space_v3/flat_lr1e-3_2/eval_v2/ppmi_dx__patch__logistic/log.txt b/input_space_v3/flat_lr1e-3_2/eval_v2/ppmi_dx__patch__logistic/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..f7a44852f2cb0e63e680edebf9069b6b80924064 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_2/eval_v2/ppmi_dx__patch__logistic/log.txt @@ -0,0 +1,247 @@ +fMRI foundation model logistic probe eval +version: 0.1.dev86+gf97f52698 +sha: bcce2b486277d3a5b520775efd9cdf1a2affce36, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-04-08 22:09:29 +config: +output_root: experiments/input_space_v3/output +name_prefix: eval_logistic +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_2; eval v2 (ppmi_dx patch logistic) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: input_space_v3/flat_lr1e-3_2/eval_v2/ppmi_dx__patch__logistic +model: flat_mae +representation: patch +dataset: ppmi_dx +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/eval_v2/ppmi_dx__patch__logistic +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=True, reg_tokens=0, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: ppmi_dx (flat) +train (n=463): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'dir', 'sex', 'age', 'age_bin', 'dx', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 463 +}), + labels=['PD' 'Prodromal'], + counts=[178 285] +) + +validation (n=99): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'dir', 'sex', 'age', 'age_bin', 'dx', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 99 +}), + labels=['PD' 'Prodromal'], + counts=[39 60] +) + +test (n=100): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'dir', 'sex', 'age', 'age_bin', 'dx', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 100 +}), + labels=['PD' 'Prodromal'], + counts=[37 63] +) + +extracting features for all splits +extract (train) [ 0/232] eta: 0:20:09 time: 5.2115 data: 4.2470 max mem: 2698 +extract (train) [ 20/232] eta: 0:01:42 time: 0.2480 data: 0.0958 max mem: 2851 +extract (train) [ 40/232] eta: 0:01:08 time: 0.2263 data: 0.0858 max mem: 2851 +extract (train) [ 60/232] eta: 0:00:52 time: 0.1935 data: 0.0657 max mem: 2851 +extract (train) [ 80/232] eta: 0:00:42 time: 0.2064 data: 0.0729 max mem: 2851 +extract (train) [100/232] eta: 0:00:34 time: 0.1958 data: 0.0668 max mem: 2851 +extract (train) [120/232] eta: 0:00:28 time: 0.2233 data: 0.0827 max mem: 2851 +extract (train) [140/232] eta: 0:00:23 time: 0.2374 data: 0.0913 max mem: 2851 +extract (train) [160/232] eta: 0:00:17 time: 0.2173 data: 0.0804 max mem: 2851 +extract (train) [180/232] eta: 0:00:12 time: 0.2367 data: 0.0904 max mem: 2851 +extract (train) [200/232] eta: 0:00:07 time: 0.2049 data: 0.0720 max mem: 2851 +extract (train) [220/232] eta: 0:00:02 time: 0.1826 data: 0.0576 max mem: 2851 +extract (train) [231/232] eta: 0:00:00 time: 0.1786 data: 0.0601 max mem: 2851 +extract (train) Total time: 0:00:55 (0.2378 s / it) +extract (validation) [ 0/50] eta: 0:03:48 time: 4.5604 data: 4.2686 max mem: 2851 +extract (validation) [20/50] eta: 0:00:13 time: 0.2352 data: 0.0873 max mem: 2851 +extract (validation) [40/50] eta: 0:00:03 time: 0.1610 data: 0.0475 max mem: 2851 +extract (validation) [49/50] eta: 0:00:00 time: 0.1590 data: 0.0490 max mem: 2851 +extract (validation) Total time: 0:00:14 (0.2889 s / it) +extract (test) [ 0/50] eta: 0:03:35 time: 4.3034 data: 4.1272 max mem: 2851 +extract (test) [20/50] eta: 0:00:13 time: 0.2611 data: 0.0950 max mem: 2851 +extract (test) [40/50] eta: 0:00:03 time: 0.1635 data: 0.0521 max mem: 2851 +extract (test) [49/50] eta: 0:00:00 time: 0.1645 data: 0.0550 max mem: 2851 +extract (test) Total time: 0:00:14 (0.2951 s / it) +feature extraction time: 0:01:24 +train features: (463, 768) +validation features: (99, 768) +test features: (100, 768) +evaluating fixed splits +eval results (fixed splits): + +| model | repr | clf | dataset | trial | C | split | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|----------:|:--------|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | ppmi_dx | | 0.0059948 | train | 0.74199 | 0.016454 | 0.70501 | 0.02028 | 0.69753 | 0.018853 | +| flat_mae | patch | logistic | ppmi_dx | | 0.0059948 | test | 0.61 | 0.040036 | 0.53119 | 0.048265 | 0.5399 | 0.042227 | + + +evaluating random splits (n=100) +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 1, "C": 0.3593813663804626, "split": "test", "acc": 0.58, "acc_std": 0.05062304218436501, "f1": 0.5384615384615385, "f1_std": 0.05574943275392334, "bacc": 0.5390492359932089, "bacc_std": 0.0536327845110648} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 2, "C": 0.046415888336127774, "split": "test", "acc": 0.68, "acc_std": 0.04078560530383237, "f1": 0.6323529411764706, "f1_std": 0.04850766526743818, "bacc": 0.6298811544991512, "bacc_std": 0.04447386922062997} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 3, "C": 21.54434690031882, "split": "test", "acc": 0.63, "acc_std": 0.04749219304264649, "f1": 0.6093337556752191, "f1_std": 0.049654404405288975, "bacc": 0.6099320882852293, "bacc_std": 0.049892947644090746} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 4, "C": 0.3593813663804626, "split": "test", "acc": 0.61, "acc_std": 0.04913491630195375, "f1": 0.5953937130407718, "f1_std": 0.05055084006885754, "bacc": 0.5988964346349746, "bacc_std": 0.051703797410431865} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 5, "C": 1291.5496650148827, "split": "test", "acc": 0.62, "acc_std": 0.04752782763813217, "f1": 0.5967741935483871, "f1_std": 0.050587240899973976, "bacc": 0.5967741935483871, "bacc_std": 0.05042166538941763} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 6, "C": 0.046415888336127774, "split": "test", "acc": 0.61, "acc_std": 0.04558021939394325, "f1": 0.568536342515765, "f1_std": 0.05169585693936591, "bacc": 0.5683361629881154, "bacc_std": 0.04896557507806751} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 7, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.04808765330102936, "f1": 0.5604395604395604, "f1_std": 0.05221674921355568, "bacc": 0.5602716468590832, "bacc_std": 0.05024351606157129} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 8, "C": 0.046415888336127774, "split": "test", "acc": 0.58, "acc_std": 0.039933639954304184, "f1": 0.5, "f1_std": 0.048559469875930426, "bacc": 0.5135823429541596, "bacc_std": 0.041933181983866676} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 9, "C": 0.005994842503189409, "split": "test", "acc": 0.71, "acc_std": 0.036938061670856524, "f1": 0.6579785352046232, "f1_std": 0.047708768034046424, "bacc": 0.6540747028862479, "bacc_std": 0.04235342685605443} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 10, "C": 166.81005372000556, "split": "test", "acc": 0.6, "acc_std": 0.04787431461650391, "f1": 0.5833333333333333, "f1_std": 0.0494137405004039, "bacc": 0.5857385398981324, "bacc_std": 0.05043196678553929} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 11, "C": 0.046415888336127774, "split": "test", "acc": 0.64, "acc_std": 0.044900939856533074, "f1": 0.592944369063772, "f1_std": 0.05248885384898926, "bacc": 0.5925297113752122, "bacc_std": 0.048622714663767226} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 12, "C": 0.005994842503189409, "split": "test", "acc": 0.58, "acc_std": 0.03534770713921908, "f1": 0.4672754946727549, "f1_std": 0.045056884263041164, "bacc": 0.49830220713073003, "bacc_std": 0.036544257163874175} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 13, "C": 0.005994842503189409, "split": "test", "acc": 0.62, "acc_std": 0.038803278212027406, "f1": 0.5558672276764843, "f1_std": 0.0467954586352611, "bacc": 0.5611205432937181, "bacc_std": 0.04129868821489986} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 14, "C": 0.005994842503189409, "split": "test", "acc": 0.61, "acc_std": 0.04385001254275762, "f1": 0.5481404240528328, "f1_std": 0.05145581358092186, "bacc": 0.5530560271646858, "bacc_std": 0.04648665522218561} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 15, "C": 0.000774263682681127, "split": "test", "acc": 0.66, "acc_std": 0.03575134123358171, "f1": 0.5687468290208015, "f1_std": 0.05190908101691091, "bacc": 0.5831918505942275, "bacc_std": 0.04055843739922853} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 16, "C": 0.046415888336127774, "split": "test", "acc": 0.65, "acc_std": 0.04639090859209377, "f1": 0.6178622120318812, "f1_std": 0.05091093889906162, "bacc": 0.615874363327674, "bacc_std": 0.04968206203710462} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 17, "C": 0.046415888336127774, "split": "test", "acc": 0.65, "acc_std": 0.04284631139316429, "f1": 0.6072270227808326, "f1_std": 0.04895443950805885, "bacc": 0.6056876061120543, "bacc_std": 0.04629867554081219} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 18, "C": 0.005994842503189409, "split": "test", "acc": 0.59, "acc_std": 0.04515701938790912, "f1": 0.5249681381068243, "f1_std": 0.051488883798740274, "bacc": 0.5318336162988115, "bacc_std": 0.046699475747965305} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 19, "C": 2.782559402207126, "split": "test", "acc": 0.6, "acc_std": 0.04586039249723012, "f1": 0.5796553173602353, "f1_std": 0.04762452440117721, "bacc": 0.5806451612903225, "bacc_std": 0.04810112326142243} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 20, "C": 0.005994842503189409, "split": "test", "acc": 0.64, "acc_std": 0.040935383227716345, "f1": 0.5714285714285714, "f1_std": 0.05174307013246583, "bacc": 0.5772495755517827, "bacc_std": 0.044733386979458764} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 21, "C": 0.046415888336127774, "split": "test", "acc": 0.73, "acc_std": 0.03751809696666397, "f1": 0.6815662224318906, "f1_std": 0.04822331452368974, "bacc": 0.6752971137521222, "bacc_std": 0.043026367324499146} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 22, "C": 0.005994842503189409, "split": "test", "acc": 0.66, "acc_std": 0.04291888162569011, "f1": 0.5952380952380952, "f1_std": 0.054185921950591326, "bacc": 0.5984719864176571, "bacc_std": 0.047009202616914984} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 23, "C": 0.005994842503189409, "split": "test", "acc": 0.65, "acc_std": 0.041254774269167925, "f1": 0.5872154735228211, "f1_std": 0.05243907453348672, "bacc": 0.5904074702886248, "bacc_std": 0.04586431599207431} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 24, "C": 0.046415888336127774, "split": "test", "acc": 0.62, "acc_std": 0.04764567136687235, "f1": 0.5766488413547237, "f1_std": 0.052929325669576525, "bacc": 0.5764006791171477, "bacc_std": 0.0502203206147114} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 25, "C": 0.005994842503189409, "split": "test", "acc": 0.68, "acc_std": 0.03509116697974006, "f1": 0.6031746031746031, "f1_std": 0.05096606985912569, "bacc": 0.6095076400679117, "bacc_std": 0.04094598494604388} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 26, "C": 0.005994842503189409, "split": "test", "acc": 0.68, "acc_std": 0.04371531081897965, "f1": 0.64349376114082, "f1_std": 0.048776443826310314, "bacc": 0.6400679117147707, "bacc_std": 0.04641883271680657} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 27, "C": 0.005994842503189409, "split": "test", "acc": 0.65, "acc_std": 0.041165888791571105, "f1": 0.5792763553311696, "f1_std": 0.05297581897692633, "bacc": 0.5853140916808149, "bacc_std": 0.04537014016082375} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 28, "C": 0.005994842503189409, "split": "test", "acc": 0.68, "acc_std": 0.038626265675055865, "f1": 0.6190476190476191, "f1_std": 0.05067643850152025, "bacc": 0.6196943972835314, "bacc_std": 0.043827925671537475} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 29, "C": 0.005994842503189409, "split": "test", "acc": 0.65, "acc_std": 0.041641690647715064, "f1": 0.5872154735228211, "f1_std": 0.05280141029970335, "bacc": 0.5904074702886248, "bacc_std": 0.04616828378276605} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 30, "C": 2.782559402207126, "split": "test", "acc": 0.62, "acc_std": 0.050120698319157525, "f1": 0.5967741935483871, "f1_std": 0.052457368811170836, "bacc": 0.5967741935483871, "bacc_std": 0.05229178981356136} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 31, "C": 0.005994842503189409, "split": "test", "acc": 0.62, "acc_std": 0.04672172513938243, "f1": 0.5824175824175825, "f1_std": 0.050421569470349314, "bacc": 0.5814940577249575, "bacc_std": 0.048475571415569706} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 32, "C": 0.3593813663804626, "split": "test", "acc": 0.58, "acc_std": 0.048550555094663946, "f1": 0.565936337329475, "f1_std": 0.04942247459965796, "bacc": 0.5696095076400679, "bacc_std": 0.05071181379071378} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 33, "C": 0.3593813663804626, "split": "test", "acc": 0.63, "acc_std": 0.04943773457592894, "f1": 0.6214833759590792, "f1_std": 0.04973279805521636, "bacc": 0.6303056027164686, "bacc_std": 0.05108773384272932} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 34, "C": 0.005994842503189409, "split": "test", "acc": 0.7, "acc_std": 0.04059388623918631, "f1": 0.6493688639551192, "f1_std": 0.050704570555705424, "bacc": 0.6460101867572157, "bacc_std": 0.045738304032563716} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 35, "C": 166.81005372000556, "split": "test", "acc": 0.56, "acc_std": 0.04939739264374183, "f1": 0.5512035903712771, "f1_std": 0.049388990122135386, "bacc": 0.5585738539898133, "bacc_std": 0.05073022639480729} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 36, "C": 0.3593813663804626, "split": "test", "acc": 0.66, "acc_std": 0.04478135326226754, "f1": 0.609375, "f1_std": 0.05328735223874716, "bacc": 0.6086587436332768, "bacc_std": 0.048691477040772105} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 37, "C": 0.005994842503189409, "split": "test", "acc": 0.65, "acc_std": 0.04336484751500921, "f1": 0.6011396011396011, "f1_std": 0.05125487198635133, "bacc": 0.6005942275042444, "bacc_std": 0.0472370087721189} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 38, "C": 0.005994842503189409, "split": "test", "acc": 0.63, "acc_std": 0.043612195542072865, "f1": 0.5906626839252129, "f1_std": 0.04836086011611163, "bacc": 0.5895585738539898, "bacc_std": 0.046335604002988987} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 39, "C": 166.81005372000556, "split": "test", "acc": 0.66, "acc_std": 0.04646617694624769, "f1": 0.6565656565656566, "f1_std": 0.046046207180055504, "bacc": 0.6748726655348047, "bacc_std": 0.046517120660873316} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 40, "C": 21.54434690031882, "split": "test", "acc": 0.57, "acc_std": 0.051562509636362726, "f1": 0.5538956323270048, "f1_std": 0.052435337721578934, "bacc": 0.5564516129032258, "bacc_std": 0.05345295388958267} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 41, "C": 21.54434690031882, "split": "test", "acc": 0.65, "acc_std": 0.04822402305905222, "f1": 0.6368917937545389, "f1_std": 0.048996239875070936, "bacc": 0.6413412563667232, "bacc_std": 0.04961306825080136} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 42, "C": 21.54434690031882, "split": "test", "acc": 0.64, "acc_std": 0.046410929747205024, "f1": 0.5989304812834224, "f1_std": 0.05282586862041195, "bacc": 0.597623089983022, "bacc_std": 0.05028422002034392} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 43, "C": 0.005994842503189409, "split": "test", "acc": 0.69, "acc_std": 0.03796678021639443, "f1": 0.627359057579036, "f1_std": 0.050574928600271754, "bacc": 0.6277589134125636, "bacc_std": 0.04335587484394197} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 44, "C": 0.005994842503189409, "split": "test", "acc": 0.64, "acc_std": 0.04122074720331984, "f1": 0.5863970588235294, "f1_std": 0.05019508886310412, "bacc": 0.5874363327674024, "bacc_std": 0.045533985056539376} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 45, "C": 0.005994842503189409, "split": "test", "acc": 0.75, "acc_std": 0.03436125143239112, "f1": 0.6865203761755485, "f1_std": 0.051340018271145677, "bacc": 0.6812393887945671, "bacc_std": 0.04256957438169377} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 46, "C": 2.782559402207126, "split": "test", "acc": 0.62, "acc_std": 0.046748155043808956, "f1": 0.5766488413547237, "f1_std": 0.054053880828127294, "bacc": 0.5764006791171477, "bacc_std": 0.05046591746984092} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 47, "C": 0.3593813663804626, "split": "test", "acc": 0.65, "acc_std": 0.050154226142968245, "f1": 0.630450849963045, "f1_std": 0.05188552909965393, "bacc": 0.6311544991511036, "bacc_std": 0.05189241205912363} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 48, "C": 0.046415888336127774, "split": "test", "acc": 0.71, "acc_std": 0.0433671719160934, "f1": 0.6833715471121302, "f1_std": 0.04840429742014023, "bacc": 0.6795415959252971, "bacc_std": 0.0472476025431973} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 49, "C": 0.005994842503189409, "split": "test", "acc": 0.68, "acc_std": 0.03802072592678892, "f1": 0.6114618746964546, "f1_std": 0.051044365297386526, "bacc": 0.6146010186757216, "bacc_std": 0.04279390220497022} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 50, "C": 0.3593813663804626, "split": "test", "acc": 0.58, "acc_std": 0.04475746194770208, "f1": 0.5442708333333334, "f1_std": 0.04849454694265064, "bacc": 0.5441426146010186, "bacc_std": 0.04716986441176352} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 51, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.04136009671168577, "f1": 0.5324918186068257, "f1_std": 0.05021692530386152, "bacc": 0.5398981324278438, "bacc_std": 0.04449026640691734} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 52, "C": 0.046415888336127774, "split": "test", "acc": 0.65, "acc_std": 0.04609803032668532, "f1": 0.6072270227808326, "f1_std": 0.05233334738624817, "bacc": 0.6056876061120543, "bacc_std": 0.04936509660965328} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 53, "C": 0.3593813663804626, "split": "test", "acc": 0.64, "acc_std": 0.046266186356776796, "f1": 0.609375, "f1_std": 0.05020029988000893, "bacc": 0.6078098471986417, "bacc_std": 0.04903475042929727} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 54, "C": 0.005994842503189409, "split": "test", "acc": 0.58, "acc_std": 0.0458673042591343, "f1": 0.5442708333333334, "f1_std": 0.04770655847157282, "bacc": 0.5441426146010186, "bacc_std": 0.046585778387492435} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 55, "C": 2.782559402207126, "split": "test", "acc": 0.64, "acc_std": 0.0445790264586386, "f1": 0.6179966044142615, "f1_std": 0.047702942848571475, "bacc": 0.6179966044142615, "bacc_std": 0.04776733415738953} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 56, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.043633638399748424, "f1": 0.5324918186068257, "f1_std": 0.05149826387142147, "bacc": 0.5398981324278438, "bacc_std": 0.045948443589461596} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 57, "C": 0.3593813663804626, "split": "test", "acc": 0.62, "acc_std": 0.049150609355327425, "f1": 0.5924495924495925, "f1_std": 0.052934944118743964, "bacc": 0.5916808149405772, "bacc_std": 0.052308622042181036} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 58, "C": 0.005994842503189409, "split": "test", "acc": 0.67, "acc_std": 0.040387146470133285, "f1": 0.6108031607500884, "f1_std": 0.05154599275899867, "bacc": 0.6116298811544991, "bacc_std": 0.04529364329364356} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 59, "C": 0.046415888336127774, "split": "test", "acc": 0.63, "acc_std": 0.045454588327252514, "f1": 0.5906626839252129, "f1_std": 0.05107029160643212, "bacc": 0.5895585738539898, "bacc_std": 0.04839746395804519} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 60, "C": 0.3593813663804626, "split": "test", "acc": 0.6, "acc_std": 0.04340127187076434, "f1": 0.5604395604395604, "f1_std": 0.049238254514139435, "bacc": 0.5602716468590832, "bacc_std": 0.047152232377480625} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 61, "C": 21.54434690031882, "split": "test", "acc": 0.56, "acc_std": 0.04891586245789804, "f1": 0.5416666666666666, "f1_std": 0.050050896177890984, "bacc": 0.5432937181663837, "bacc_std": 0.05086556313812863} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 62, "C": 0.3593813663804626, "split": "test", "acc": 0.61, "acc_std": 0.04615994367414242, "f1": 0.584, "f1_std": 0.048944657797565023, "bacc": 0.583616298811545, "bacc_std": 0.048724562485002634} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 63, "C": 2.782559402207126, "split": "test", "acc": 0.56, "acc_std": 0.05041666391184565, "f1": 0.5280995280995281, "f1_std": 0.05268242551501493, "bacc": 0.5280135823429541, "bacc_std": 0.051902707458053685} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 64, "C": 0.046415888336127774, "split": "test", "acc": 0.58, "acc_std": 0.040862985696104, "f1": 0.5, "f1_std": 0.04785566883102513, "bacc": 0.5135823429541596, "bacc_std": 0.042157402501553705} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 65, "C": 0.005994842503189409, "split": "test", "acc": 0.56, "acc_std": 0.045255412935912974, "f1": 0.4944852941176471, "f1_std": 0.04999001952778139, "bacc": 0.5025466893039049, "bacc_std": 0.04603407566671651} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 66, "C": 2.782559402207126, "split": "test", "acc": 0.54, "acc_std": 0.04702276469966435, "f1": 0.5066495066495067, "f1_std": 0.04886941528118106, "bacc": 0.5067911714770797, "bacc_std": 0.04826173164135048} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 67, "C": 0.046415888336127774, "split": "test", "acc": 0.6, "acc_std": 0.04720052542080437, "f1": 0.570999570999571, "f1_std": 0.05056538004539158, "bacc": 0.5704584040747029, "bacc_std": 0.049884141294308085} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 68, "C": 2.782559402207126, "split": "test", "acc": 0.61, "acc_std": 0.04628556578459423, "f1": 0.5793334052421529, "f1_std": 0.049281085105863764, "bacc": 0.5785229202037352, "bacc_std": 0.04832147991858776} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 69, "C": 0.005994842503189409, "split": "test", "acc": 0.7, "acc_std": 0.04105377449151295, "f1": 0.6493688639551192, "f1_std": 0.05126743480214922, "bacc": 0.6460101867572157, "bacc_std": 0.04621248707431317} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 70, "C": 0.005994842503189409, "split": "test", "acc": 0.63, "acc_std": 0.04326041608676459, "f1": 0.5783475783475784, "f1_std": 0.05062125387438295, "bacc": 0.5793718166383701, "bacc_std": 0.04636220230837917} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 71, "C": 0.005994842503189409, "split": "test", "acc": 0.66, "acc_std": 0.04007331281538874, "f1": 0.587178241864983, "f1_std": 0.052404304063435, "bacc": 0.5933786078098472, "bacc_std": 0.04432237464763542} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 72, "C": 0.005994842503189409, "split": "test", "acc": 0.63, "acc_std": 0.04444985939235354, "f1": 0.5783475783475784, "f1_std": 0.05087994644508297, "bacc": 0.5793718166383701, "bacc_std": 0.04691483017809674} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 73, "C": 0.005994842503189409, "split": "test", "acc": 0.67, "acc_std": 0.04478043769326065, "f1": 0.6547756041426928, "f1_std": 0.04649715892655601, "bacc": 0.6574702886247878, "bacc_std": 0.04733047791634636} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 74, "C": 0.005994842503189409, "split": "test", "acc": 0.62, "acc_std": 0.04361868865520834, "f1": 0.5634191176470589, "f1_std": 0.05112333479648441, "bacc": 0.566213921901528, "bacc_std": 0.0465698234991788} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 75, "C": 2.782559402207126, "split": "test", "acc": 0.56, "acc_std": 0.045249548064041474, "f1": 0.5098039215686274, "f1_std": 0.049646380126728326, "bacc": 0.5127334465195246, "bacc_std": 0.04691978490627809} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 76, "C": 0.3593813663804626, "split": "test", "acc": 0.57, "acc_std": 0.047572328091023665, "f1": 0.5361881134721174, "f1_std": 0.05025785959049574, "bacc": 0.5360780984719864, "bacc_std": 0.0492750838907695} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 77, "C": 0.046415888336127774, "split": "test", "acc": 0.63, "acc_std": 0.045488266618986486, "f1": 0.5713127099988413, "f1_std": 0.05373953228466832, "bacc": 0.5742784380305602, "bacc_std": 0.04855712274504877} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 78, "C": 0.046415888336127774, "split": "test", "acc": 0.65, "acc_std": 0.03838084939133057, "f1": 0.5706048337627285, "f1_std": 0.04985998978811539, "bacc": 0.580220713073005, "bacc_std": 0.04182106456380939} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 79, "C": 0.046415888336127774, "split": "test", "acc": 0.7, "acc_std": 0.0398708464921426, "f1": 0.6553308823529411, "f1_std": 0.04858595544551323, "bacc": 0.6511035653650254, "bacc_std": 0.044311052635673955} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 80, "C": 166.81005372000556, "split": "test", "acc": 0.67, "acc_std": 0.045986937275709065, "f1": 0.648, "f1_std": 0.04953055167144808, "bacc": 0.6472835314091681, "bacc_std": 0.049579061350993964} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 81, "C": 0.046415888336127774, "split": "test", "acc": 0.7, "acc_std": 0.043615428462873085, "f1": 0.6782496782496783, "f1_std": 0.0473675878397804, "bacc": 0.6765704584040747, "bacc_std": 0.04729909980141856} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 82, "C": 0.005994842503189409, "split": "test", "acc": 0.66, "acc_std": 0.041782292900222694, "f1": 0.5952380952380952, "f1_std": 0.05405962879788714, "bacc": 0.5984719864176571, "bacc_std": 0.04673968067841298} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 83, "C": 0.005994842503189409, "split": "test", "acc": 0.48, "acc_std": 0.04727433130145788, "f1": 0.4357638888888889, "f1_std": 0.04815037242380993, "bacc": 0.4380305602716469, "bacc_std": 0.04744600655705251} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 84, "C": 0.005994842503189409, "split": "test", "acc": 0.62, "acc_std": 0.04557760853752641, "f1": 0.5766488413547237, "f1_std": 0.0513754798121224, "bacc": 0.5764006791171477, "bacc_std": 0.04877529726674091} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 85, "C": 0.046415888336127774, "split": "test", "acc": 0.63, "acc_std": 0.040423057776472086, "f1": 0.5847828526540231, "f1_std": 0.045461158697809374, "bacc": 0.5844651952461799, "bacc_std": 0.042787740548711636} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 86, "C": 166.81005372000556, "split": "test", "acc": 0.56, "acc_std": 0.04719915253476485, "f1": 0.5280995280995281, "f1_std": 0.049504089472301394, "bacc": 0.5280135823429541, "bacc_std": 0.04893365065268706} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 87, "C": 0.046415888336127774, "split": "test", "acc": 0.64, "acc_std": 0.04646655141066529, "f1": 0.6043956043956044, "f1_std": 0.05226324006632611, "bacc": 0.6027164685908319, "bacc_std": 0.05012590972933918} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 88, "C": 0.046415888336127774, "split": "test", "acc": 0.62, "acc_std": 0.044901741614329395, "f1": 0.5703301673450927, "f1_std": 0.05209776256550068, "bacc": 0.5713073005093379, "bacc_std": 0.0481638918249751} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 89, "C": 0.005994842503189409, "split": "test", "acc": 0.69, "acc_std": 0.041658857401517854, "f1": 0.6408295678368672, "f1_std": 0.05146769387011758, "bacc": 0.6379456706281834, "bacc_std": 0.046653876750586784} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 90, "C": 0.046415888336127774, "split": "test", "acc": 0.68, "acc_std": 0.0424562645554222, "f1": 0.64349376114082, "f1_std": 0.048260184299712315, "bacc": 0.6400679117147707, "bacc_std": 0.04597450561398131} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 91, "C": 0.046415888336127774, "split": "test", "acc": 0.63, "acc_std": 0.04549681307520341, "f1": 0.6009060511271707, "f1_std": 0.0492182832924272, "bacc": 0.5997453310696095, "bacc_std": 0.04818904276915539} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 92, "C": 0.3593813663804626, "split": "test", "acc": 0.67, "acc_std": 0.044214364181790505, "f1": 0.6396986570586308, "f1_std": 0.04894480311055005, "bacc": 0.6370967741935484, "bacc_std": 0.04776421540898359} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 93, "C": 0.005994842503189409, "split": "test", "acc": 0.61, "acc_std": 0.045560557503173726, "f1": 0.568536342515765, "f1_std": 0.05063678705401888, "bacc": 0.5683361629881154, "bacc_std": 0.04828835433969353} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 94, "C": 0.005994842503189409, "split": "test", "acc": 0.7, "acc_std": 0.03776353267373167, "f1": 0.6428571428571428, "f1_std": 0.04899754390361405, "bacc": 0.6409168081494058, "bacc_std": 0.04276920873746684} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 95, "C": 0.046415888336127774, "split": "test", "acc": 0.61, "acc_std": 0.044433586395878515, "f1": 0.5623386825272135, "f1_std": 0.05010317619605685, "bacc": 0.5632427843803056, "bacc_std": 0.04716518658801797} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 96, "C": 0.046415888336127774, "split": "test", "acc": 0.61, "acc_std": 0.04479732134849136, "f1": 0.568536342515765, "f1_std": 0.04927671429379426, "bacc": 0.5683361629881154, "bacc_std": 0.04708643555665793} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 97, "C": 0.046415888336127774, "split": "test", "acc": 0.68, "acc_std": 0.042111281148879805, "f1": 0.6381727725011307, "f1_std": 0.049063652765318946, "bacc": 0.634974533106961, "bacc_std": 0.0456879704641437} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 98, "C": 0.3593813663804626, "split": "test", "acc": 0.62, "acc_std": 0.04602992070382047, "f1": 0.5824175824175825, "f1_std": 0.05189372819498984, "bacc": 0.5814940577249575, "bacc_std": 0.04966789052137315} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 99, "C": 0.046415888336127774, "split": "test", "acc": 0.62, "acc_std": 0.043527366104555425, "f1": 0.5703301673450927, "f1_std": 0.05030342788626905, "bacc": 0.5713073005093379, "bacc_std": 0.04661317431996313} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 100, "C": 0.046415888336127774, "split": "test", "acc": 0.6, "acc_std": 0.04865373161433766, "f1": 0.5755517826825127, "f1_std": 0.05270138338998095, "bacc": 0.5755517826825127, "bacc_std": 0.05255262216535191} +eval results (random splits): + +| model | repr | clf | dataset | split | n_trials | C | C_std | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|-----------:|-------:|--------:|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | ppmi_dx | train | 100 | 22.621 | 133.27 | 0.83286 | 0.10128 | 0.80913 | 0.11845 | 0.80271 | 0.12074 | +| flat_mae | patch | logistic | ppmi_dx | test | 100 | 22.621 | 133.27 | 0.6312 | 0.04502 | 0.58724 | 0.046547 | 0.5889 | 0.044194 | + + +done! total time: 0:05:45 diff --git a/input_space_v3/flat_lr1e-3_2/pretrain/config.yaml b/input_space_v3/flat_lr1e-3_2/pretrain/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..d1da74aea943b9a65c53fc23ff36af22a5413907 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_2/pretrain/config.yaml @@ -0,0 +1,102 @@ +name: input_space_v3/flat_lr1e-3_2/pretrain +notes: input_space ablation v3 flat_lr1e-3_2; use tube masking and on-disk data (input_space=flat + base_lr=1e-3 seed=5402) +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain +input_space: flat +patch_size: 16 +num_frames: 16 +t_patch_size: 4 +mask_ratio: 0.9 +pred_mask_ratio: null +masking: tube +masking_kwargs: {} +mask_patch_size: null +model: mae_vit_base +model_kwargs: + decoding: attn + pos_embed: sep + target_norm: null + pca_norm_nc: 2 + t_pred_stride: 2 + no_decode_pos: true + mask_drop_scale: false + pred_edge_pad: 0 + gauss_sigma: null + class_token: true + reg_tokens: 0 + no_embed_class: true + head_init_scale: 0.0 + decoder_depth: 4 + drop_path_rate: 0.0 +datasets: + hcp-train: + type: wds + url: /data/fmri-datasets/pretrain/hcpya-all.${input_space}.wds/hcpya-all-${input_space}-{00000..01799}.tar + clipping: random + clipping_kwargs: + oversample: 4.0 + shuffle: true + buffer_size: 2000 + samples_per_epoch: 200000 + hcp-train-subset: + type: arrow + root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/validation + split_range: + - 0 + - 2000 + shuffle: false + hcp-val: + type: arrow + root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/test + split_range: + - 0 + - 2000 + shuffle: false +train_dataset: hcp-train +eval_datasets: +- hcp-train-subset +- hcp-val +val_dataset: null +clip_vmax: 3.0 +normalize: frame +tr_scale: null +crop_scale: null +crop_aspect: null +gray_jitter: null +num_workers: 16 +epochs: 100 +batch_size: 32 +accum_iter: 1 +base_lr: 0.001 +min_lr: 0.0 +warmup_epochs: 5 +weight_decay: 0.05 +betas: +- 0.9 +- 0.95 +clip_grad: 1.0 +amp: true +amp_dtype: float16 +ckpt: null +resume: true +auto_resume: true +start_epoch: 0 +max_checkpoints: 0 +checkpoint_period: null +plot_period: 5 +device: cuda +presend_cuda: false +seed: 5402 +debug: false +wandb: true +wandb_entity: null +wandb_project: fMRI-foundation-model +rank: 0 +world_size: 1 +gpu: 0 +distributed: true +dist_backend: nccl +in_chans: 1 +img_size: +- 224 +- 560 diff --git a/input_space_v3/flat_lr1e-3_2/pretrain/log.json b/input_space_v3/flat_lr1e-3_2/pretrain/log.json new file mode 100644 index 0000000000000000000000000000000000000000..e7bafab96c2ad78e342b435655e01f679ad43e1a --- /dev/null +++ b/input_space_v3/flat_lr1e-3_2/pretrain/log.json @@ -0,0 +1,100 @@ +{"epoch": 0, "train/lr": 1.2502400076802458e-05, "train/grad": 0.05454847666695714, "train/loss": 0.9929588839149475, "eval/hcp-train-subset/loss": 0.9923721869145671, "eval/hcp-val/loss": 0.9906213408516299} +{"epoch": 1, "train/lr": 3.750320010240327e-05, "train/grad": 0.07675362249553204, "train/loss": 0.9884395974254608, "eval/hcp-train-subset/loss": 0.988623752709358, "eval/hcp-val/loss": 0.9871691340400327} +{"epoch": 2, "train/lr": 6.250400012800409e-05, "train/grad": 0.13436773436253702, "train/loss": 0.984165839395523, "eval/hcp-train-subset/loss": 0.982871743940538, "eval/hcp-val/loss": 0.9809346150967383} +{"epoch": 3, "train/lr": 8.75048001536049e-05, "train/grad": 0.20680276547885745, "train/loss": 0.975158474740982, "eval/hcp-train-subset/loss": 0.9716144098389533, "eval/hcp-val/loss": 0.9682842031601937} +{"epoch": 4, "train/lr": 0.00011250559953918529, "train/grad": 0.2205818969798691, "train/loss": 0.943683482131958, "eval/hcp-train-subset/loss": 0.9249886908838826, "eval/hcp-val/loss": 0.9194095192417022} +{"epoch": 5, "train/lr": 0.00012498860637884563, "train/grad": 0.15727583374518056, "train/loss": 0.9028194780540466, "eval/hcp-train-subset/loss": 0.8858536568380171, "eval/hcp-val/loss": 0.8804098108122426} +{"epoch": 6, "train/lr": 0.0001249202705377922, "train/grad": 0.10791387108062313, "train/loss": 0.8734634943389893, "eval/hcp-train-subset/loss": 0.8711521654359756, "eval/hcp-val/loss": 0.865037682556337} +{"epoch": 7, "train/lr": 0.0001247836790473516, "train/grad": 0.08395457674991268, "train/loss": 0.8655173498439789, "eval/hcp-train-subset/loss": 0.8638488054275513, "eval/hcp-val/loss": 0.8578415003515059} +{"epoch": 8, "train/lr": 0.000124578981268311, "train/grad": 0.07451289842760675, "train/loss": 0.8586141684532166, "eval/hcp-train-subset/loss": 0.8595733008077068, "eval/hcp-val/loss": 0.8543623320518001} +{"epoch": 9, "train/lr": 0.00012430640103468907, "train/grad": 0.0710198438307591, "train/loss": 0.8531024506664276, "eval/hcp-train-subset/loss": 0.8563221991062164, "eval/hcp-val/loss": 0.8510348854526397} +{"epoch": 10, "train/lr": 0.00012396623640896796, "train/grad": 0.06891560291742642, "train/loss": 0.8491140551376343, "eval/hcp-train-subset/loss": 0.8544466447445654, "eval/hcp-val/loss": 0.8490336095133135} +{"epoch": 11, "train/lr": 0.0001235588593561712, "train/grad": 0.06573528261788467, "train/loss": 0.8481580335330963, "eval/hcp-train-subset/loss": 0.8529206427835649, "eval/hcp-val/loss": 0.8471173249906109} +{"epoch": 12, "train/lr": 0.00012308471533712604, "train/grad": 0.06511989402493344, "train/loss": 0.8469846354293823, "eval/hcp-train-subset/loss": 0.8514541849013297, "eval/hcp-val/loss": 0.8453809676631805} +{"epoch": 13, "train/lr": 0.00012254432282135565, "train/grad": 0.06542463161615404, "train/loss": 0.8440091907310486, "eval/hcp-train-subset/loss": 0.8505928487546982, "eval/hcp-val/loss": 0.8446970485871838} +{"epoch": 14, "train/lr": 0.00012193827272014171, "train/grad": 0.06557162251853432, "train/loss": 0.8414228653430939, "eval/hcp-train-subset/loss": 0.8482870276897184, "eval/hcp-val/loss": 0.8437854282317623} +{"epoch": 15, "train/lr": 0.00012126722774037197, "train/grad": 0.06280276225417557, "train/loss": 0.8427921316528321, "eval/hcp-train-subset/loss": 0.8483998737027568, "eval/hcp-val/loss": 0.8435921736301915} +{"epoch": 16, "train/lr": 0.00012053192165988122, "train/grad": 0.0640653094449965, "train/loss": 0.8393674468612671, "eval/hcp-train-subset/loss": 0.8478718784547621, "eval/hcp-val/loss": 0.8431085194310834} +{"epoch": 17, "train/lr": 0.00011973315852507104, "train/grad": 0.06449760176803143, "train/loss": 0.8389797674369812, "eval/hcp-train-subset/loss": 0.8469935251820472, "eval/hcp-val/loss": 0.8416705573758771} +{"epoch": 18, "train/lr": 0.00011887181177170142, "train/grad": 0.06561184599363501, "train/loss": 0.836694293384552, "eval/hcp-train-subset/loss": 0.8461682123522605, "eval/hcp-val/loss": 0.8413996927199825} +{"epoch": 19, "train/lr": 0.00011794882326980209, "train/grad": 0.06656866827516035, "train/loss": 0.8378256143951416, "eval/hcp-train-subset/loss": 0.8469854006844182, "eval/hcp-val/loss": 0.8415242173979359} +{"epoch": 20, "train/lr": 0.00011696520229374954, "train/grad": 0.06585909890740747, "train/loss": 0.8371871770954132, "eval/hcp-train-subset/loss": 0.8459832725986358, "eval/hcp-val/loss": 0.8408271804932625} +{"epoch": 21, "train/lr": 0.00011592202441863837, "train/grad": 0.06533177437420862, "train/loss": 0.8367929257297516, "eval/hcp-train-subset/loss": 0.8460024585646968, "eval/hcp-val/loss": 0.8410498076869596} +{"epoch": 22, "train/lr": 0.00011482043034415979, "train/grad": 0.06643678367910756, "train/loss": 0.8346013723754883, "eval/hcp-train-subset/loss": 0.8446446311089301, "eval/hcp-val/loss": 0.840955957289665} +{"epoch": 23, "train/lr": 0.00011366162464726024, "train/grad": 0.06659269590382197, "train/loss": 0.8351524771404266, "eval/hcp-train-subset/loss": 0.8443802095228626, "eval/hcp-val/loss": 0.8404323804763055} +{"epoch": 24, "train/lr": 0.0001124468744649569, "train/grad": 0.06829636148147275, "train/loss": 0.8342827572822571, "eval/hcp-train-subset/loss": 0.8441076605550705, "eval/hcp-val/loss": 0.8396203931300871} +{"epoch": 25, "train/lr": 0.0001111775081087387, "train/grad": 0.06815206812916469, "train/loss": 0.8332914790248871, "eval/hcp-train-subset/loss": 0.844654510098119, "eval/hcp-val/loss": 0.8402627898800757} +{"epoch": 26, "train/lr": 0.0001098549136120796, "train/grad": 0.06869214148281078, "train/loss": 0.8331698024749756, "eval/hcp-train-subset/loss": 0.8427886924436016, "eval/hcp-val/loss": 0.8395714442576131} +{"epoch": 27, "train/lr": 0.00010848053721264312, "train/grad": 0.06943331373164996, "train/loss": 0.8302846519756317, "eval/hcp-train-subset/loss": 0.8436315203866651, "eval/hcp-val/loss": 0.8398627638816833} +{"epoch": 28, "train/lr": 0.00010705588177084458, "train/grad": 0.06996354475798636, "train/loss": 0.8311486543655395, "eval/hcp-train-subset/loss": 0.84361925625032, "eval/hcp-val/loss": 0.838790682054335} +{"epoch": 29, "train/lr": 0.00010558250512649171, "train/grad": 0.0703615777418721, "train/loss": 0.8320011916446686, "eval/hcp-train-subset/loss": 0.8433211830354506, "eval/hcp-val/loss": 0.8391217252900524} +{"epoch": 30, "train/lr": 0.00010406201839531515, "train/grad": 0.07134841077289665, "train/loss": 0.8274994590282441, "eval/hcp-train-subset/loss": 0.841982453100143, "eval/hcp-val/loss": 0.838364778987823} +{"epoch": 31, "train/lr": 0.00010249608420723018, "train/grad": 0.0715736072455627, "train/loss": 0.8293852714252472, "eval/hcp-train-subset/loss": 0.84223289547428, "eval/hcp-val/loss": 0.8385185041735249} +{"epoch": 32, "train/lr": 0.00010088641488828097, "train/grad": 0.07338286142743204, "train/loss": 0.8291380492305755, "eval/hcp-train-subset/loss": 0.841593909648157, "eval/hcp-val/loss": 0.8383132796133718} +{"epoch": 33, "train/lr": 9.923477058823526e-05, "train/grad": 0.07419838390472756, "train/loss": 0.8286535998249054, "eval/hcp-train-subset/loss": 0.8416552543640137, "eval/hcp-val/loss": 0.8385220612249067} +{"epoch": 34, "train/lr": 9.754295735588547e-05, "train/grad": 0.0743370464389775, "train/loss": 0.8285935473060608, "eval/hcp-train-subset/loss": 0.8415432216659668, "eval/hcp-val/loss": 0.8377819282393302} +{"epoch": 35, "train/lr": 9.581282516416285e-05, "train/grad": 0.07637198778911566, "train/loss": 0.8262437226295472, "eval/hcp-train-subset/loss": 0.8405865152035991, "eval/hcp-val/loss": 0.8375011884397076} +{"epoch": 36, "train/lr": 9.404626588721676e-05, "train/grad": 0.07676920510003303, "train/loss": 0.8265554042243958, "eval/hcp-train-subset/loss": 0.8400881434640577, "eval/hcp-val/loss": 0.8375549566361212} +{"epoch": 37, "train/lr": 9.224521123168153e-05, "train/grad": 0.07692633751808414, "train/loss": 0.8261774384307862, "eval/hcp-train-subset/loss": 0.8404769637892323, "eval/hcp-val/loss": 0.8376543541108409} +{"epoch": 38, "train/lr": 9.041163062437843e-05, "train/grad": 0.08016919506243914, "train/loss": 0.8244994926452637, "eval/hcp-train-subset/loss": 0.8410743965256599, "eval/hcp-val/loss": 0.8375941082354514} +{"epoch": 39, "train/lr": 8.85475290587822e-05, "train/grad": 0.07957971267360416, "train/loss": 0.8254723467254639, "eval/hcp-train-subset/loss": 0.8393523789221241, "eval/hcp-val/loss": 0.8375709845173743} +{"epoch": 40, "train/lr": 8.665494490258622e-05, "train/grad": 0.08032399477014772, "train/loss": 0.82648730219841, "eval/hcp-train-subset/loss": 0.8405729118854769, "eval/hcp-val/loss": 0.8375965837509401} +{"epoch": 41, "train/lr": 8.473594766877838e-05, "train/grad": 0.08095308592740957, "train/loss": 0.8252784929466248, "eval/hcp-train-subset/loss": 0.8403502991122584, "eval/hcp-val/loss": 0.8374370028895717} +{"epoch": 42, "train/lr": 8.279263575265999e-05, "train/grad": 0.08108283759353542, "train/loss": 0.8254710999202728, "eval/hcp-train-subset/loss": 0.8389220901073948, "eval/hcp-val/loss": 0.8368590560651594} +{"epoch": 43, "train/lr": 8.082713413727944e-05, "train/grad": 0.08328707275811684, "train/loss": 0.8234768060016632, "eval/hcp-train-subset/loss": 0.8383768844989038, "eval/hcp-val/loss": 0.8371412407967352} +{"epoch": 44, "train/lr": 7.884159206979602e-05, "train/grad": 0.08266624313872516, "train/loss": 0.8260491606998444, "eval/hcp-train-subset/loss": 0.8386047520945149, "eval/hcp-val/loss": 0.8359582885619132} +{"epoch": 45, "train/lr": 7.683818071130916e-05, "train/grad": 0.08312187505773866, "train/loss": 0.8252147768688202, "eval/hcp-train-subset/loss": 0.8366418375122932, "eval/hcp-val/loss": 0.8358022320655084} +{"epoch": 46, "train/lr": 7.481909076272522e-05, "train/grad": 0.08467493361880508, "train/loss": 0.8226776430511474, "eval/hcp-train-subset/loss": 0.836982250213623, "eval/hcp-val/loss": 0.8366720022693757} +{"epoch": 47, "train/lr": 7.278653006925963e-05, "train/grad": 0.08704538320565254, "train/loss": 0.8191923590278626, "eval/hcp-train-subset/loss": 0.8362540410410974, "eval/hcp-val/loss": 0.8368456998179036} +{"epoch": 48, "train/lr": 7.074272120618864e-05, "train/grad": 0.08974658064401105, "train/loss": 0.8209733989334106, "eval/hcp-train-subset/loss": 0.8385795700934625, "eval/hcp-val/loss": 0.8361238279650288} +{"epoch": 49, "train/lr": 6.868989904849677e-05, "train/grad": 0.08960857699315548, "train/loss": 0.8221028245639801, "eval/hcp-train-subset/loss": 0.8377643419850257, "eval/hcp-val/loss": 0.8355583817728104} +{"epoch": 50, "train/lr": 6.6630308327075e-05, "train/grad": 0.09112848722757311, "train/loss": 0.8201087599563599, "eval/hcp-train-subset/loss": 0.8389821937007289, "eval/hcp-val/loss": 0.836230315508381} +{"epoch": 51, "train/lr": 6.456620117413798e-05, "train/grad": 0.08910827335655203, "train/loss": 0.8225639422512054, "eval/hcp-train-subset/loss": 0.8372277675136444, "eval/hcp-val/loss": 0.8358394397843268} +{"epoch": 52, "train/lr": 6.249983466055255e-05, "train/grad": 0.09132896617772923, "train/loss": 0.821227049703598, "eval/hcp-train-subset/loss": 0.8366572847289424, "eval/hcp-val/loss": 0.8350231291786316} +{"epoch": 53, "train/lr": 6.0433468327763305e-05, "train/grad": 0.09620157853257813, "train/loss": 0.8171052526283265, "eval/hcp-train-subset/loss": 0.8376313101860785, "eval/hcp-val/loss": 0.8352235161489056} +{"epoch": 54, "train/lr": 5.83693617170174e-05, "train/grad": 0.0944482777634439, "train/loss": 0.8196508842372894, "eval/hcp-train-subset/loss": 0.8352778179030265, "eval/hcp-val/loss": 0.8350441205886102} +{"epoch": 55, "train/lr": 5.6309771898588165e-05, "train/grad": 0.09575524518180462, "train/loss": 0.819943421831131, "eval/hcp-train-subset/loss": 0.833152275892996, "eval/hcp-val/loss": 0.8341701040344853} +{"epoch": 56, "train/lr": 5.4256951003704155e-05, "train/grad": 0.09796828048887644, "train/loss": 0.8190742979431153, "eval/hcp-train-subset/loss": 0.835026680461822, "eval/hcp-val/loss": 0.8345063194151847} +{"epoch": 57, "train/lr": 5.221314376187425e-05, "train/grad": 0.09799354083814614, "train/loss": 0.8189411697769166, "eval/hcp-train-subset/loss": 0.8338991826580416, "eval/hcp-val/loss": 0.8346979031639714} +{"epoch": 58, "train/lr": 5.018058504631059e-05, "train/grad": 0.09851793681852948, "train/loss": 0.8186805113887787, "eval/hcp-train-subset/loss": 0.832815820170987, "eval/hcp-val/loss": 0.8346041440963745} +{"epoch": 59, "train/lr": 4.816149743012713e-05, "train/grad": 0.09644485628722686, "train/loss": 0.8199044501209259, "eval/hcp-train-subset/loss": 0.8348744261649347, "eval/hcp-val/loss": 0.8333737436802157} +{"epoch": 60, "train/lr": 4.615808875598772e-05, "train/grad": 0.10218705402930794, "train/loss": 0.8161181366443634, "eval/hcp-train-subset/loss": 0.8329490471270776, "eval/hcp-val/loss": 0.8333299256140186} +{"epoch": 61, "train/lr": 4.417254972186445e-05, "train/grad": 0.10563795824586468, "train/loss": 0.8145519579315186, "eval/hcp-train-subset/loss": 0.8332418414854235, "eval/hcp-val/loss": 0.8345872846341902} +{"epoch": 62, "train/lr": 4.220705148553925e-05, "train/grad": 0.10091036710394981, "train/loss": 0.8190675114154816, "eval/hcp-train-subset/loss": 0.833212488120602, "eval/hcp-val/loss": 0.8331462808193699} +{"epoch": 63, "train/lr": 4.026374329047657e-05, "train/grad": 0.1048214796096282, "train/loss": 0.819147063293457, "eval/hcp-train-subset/loss": 0.8318721334780416, "eval/hcp-val/loss": 0.8335561511978027} +{"epoch": 64, "train/lr": 3.834475011565652e-05, "train/grad": 0.11037434163733012, "train/loss": 0.8141395277500153, "eval/hcp-train-subset/loss": 0.8323525776786189, "eval/hcp-val/loss": 0.8340111259491213} +{"epoch": 65, "train/lr": 3.6452170351940815e-05, "train/grad": 0.11007038200102394, "train/loss": 0.8156373052692414, "eval/hcp-train-subset/loss": 0.8321069238647338, "eval/hcp-val/loss": 0.8329415782805412} +{"epoch": 66, "train/lr": 3.458807350751516e-05, "train/grad": 0.11160427606805437, "train/loss": 0.814088339729309, "eval/hcp-train-subset/loss": 0.8305221199989319, "eval/hcp-val/loss": 0.8317997820915715} +{"epoch": 67, "train/lr": 3.2754497944910164e-05, "train/grad": 0.10988769530224307, "train/loss": 0.8168726810359955, "eval/hcp-train-subset/loss": 0.8315556606938762, "eval/hcp-val/loss": 0.8323218130296276} +{"epoch": 68, "train/lr": 3.0953448652083367e-05, "train/grad": 0.11305067358103713, "train/loss": 0.8127388539123536, "eval/hcp-train-subset/loss": 0.8308751083189442, "eval/hcp-val/loss": 0.8325146119440755} +{"epoch": 69, "train/lr": 2.9186895049993948e-05, "train/grad": 0.11228417137473173, "train/loss": 0.8165840325736999, "eval/hcp-train-subset/loss": 0.8294901069133512, "eval/hcp-val/loss": 0.8321623436866268} +{"epoch": 70, "train/lr": 2.7456768839068717e-05, "train/grad": 0.11609685264716209, "train/loss": 0.8138171372699737, "eval/hcp-train-subset/loss": 0.8285988021281457, "eval/hcp-val/loss": 0.8315755253837954} +{"epoch": 71, "train/lr": 2.5764961886919063e-05, "train/grad": 0.11767564653128991, "train/loss": 0.8153125314044952, "eval/hcp-train-subset/loss": 0.8274947577907193, "eval/hcp-val/loss": 0.8317726177553977} +{"epoch": 72, "train/lr": 2.411332415960724e-05, "train/grad": 0.11987956720897872, "train/loss": 0.8122294786930084, "eval/hcp-train-subset/loss": 0.8284010791009472, "eval/hcp-val/loss": 0.8318879825453604} +{"epoch": 73, "train/lr": 2.2503661698739544e-05, "train/grad": 0.12399469493059831, "train/loss": 0.8111889666080475, "eval/hcp-train-subset/loss": 0.8275864239661924, "eval/hcp-val/loss": 0.8320645959146561} +{"epoch": 74, "train/lr": 2.0937734646583902e-05, "train/grad": 0.12329658981199758, "train/loss": 0.8105496173095703, "eval/hcp-train-subset/loss": 0.8257122328204494, "eval/hcp-val/loss": 0.8314358120964419} +{"epoch": 75, "train/lr": 1.9417255321381202e-05, "train/grad": 0.12313769477769454, "train/loss": 0.8140740214538574, "eval/hcp-train-subset/loss": 0.826117504027582, "eval/hcp-val/loss": 0.8309027177672232} +{"epoch": 76, "train/lr": 1.7943886344950134e-05, "train/grad": 0.12306028096952291, "train/loss": 0.8150812616634369, "eval/hcp-train-subset/loss": 0.8247029819796162, "eval/hcp-val/loss": 0.8308771291086751} +{"epoch": 77, "train/lr": 1.651923882463461e-05, "train/grad": 0.12355961764509514, "train/loss": 0.8147859694194793, "eval/hcp-train-subset/loss": 0.8230017683198375, "eval/hcp-val/loss": 0.8302385970469444} +{"epoch": 78, "train/lr": 1.5144870591581508e-05, "train/grad": 0.126086488369705, "train/loss": 0.8142378909015655, "eval/hcp-train-subset/loss": 0.8224669070013108, "eval/hcp-val/loss": 0.8305225381928105} +{"epoch": 79, "train/lr": 1.3822284497275662e-05, "train/grad": 0.12824792957241038, "train/loss": 0.8141949711418152, "eval/hcp-train-subset/loss": 0.8229460024064587, "eval/hcp-val/loss": 0.8304367123111602} +{"epoch": 80, "train/lr": 1.2552926770192975e-05, "train/grad": 0.13145899692880267, "train/loss": 0.8119310477161408, "eval/hcp-train-subset/loss": 0.8219587716364092, "eval/hcp-val/loss": 0.8300683017699949} +{"epoch": 81, "train/lr": 1.1338185434371453e-05, "train/grad": 0.13169763870543244, "train/loss": 0.8120321962738037, "eval/hcp-train-subset/loss": 0.8215324936374542, "eval/hcp-val/loss": 0.8300118407895488} +{"epoch": 82, "train/lr": 1.0179388791627326e-05, "train/grad": 0.13373520445333245, "train/loss": 0.8124906825828552, "eval/hcp-train-subset/loss": 0.8211350796684143, "eval/hcp-val/loss": 0.8303428263433518} +{"epoch": 83, "train/lr": 9.07780396907607e-06, "train/grad": 0.13627996479659904, "train/loss": 0.8111069245910645, "eval/hcp-train-subset/loss": 0.8208480458105764, "eval/hcp-val/loss": 0.829437485625667} +{"epoch": 84, "train/lr": 8.034635533547902e-06, "train/grad": 0.13630997695494965, "train/loss": 0.8134738928699493, "eval/hcp-train-subset/loss": 0.8200996710408118, "eval/hcp-val/loss": 0.8295725343688842} +{"epoch": 85, "train/lr": 7.051024174411275e-06, "train/grad": 0.1367269862267859, "train/loss": 0.8126089343166352, "eval/hcp-train-subset/loss": 0.8195290440513242, "eval/hcp-val/loss": 0.8292808763442501} +{"epoch": 86, "train/lr": 6.1280454562463606e-06, "train/grad": 0.13652268818501073, "train/loss": 0.8137829009342193, "eval/hcp-train-subset/loss": 0.8183126680312618, "eval/hcp-val/loss": 0.8288266293464168} +{"epoch": 87, "train/lr": 5.266708642730326e-06, "train/grad": 0.14036835894279573, "train/loss": 0.8129039366340637, "eval/hcp-train-subset/loss": 0.8166653879227177, "eval/hcp-val/loss": 0.8291096283543494} +{"epoch": 88, "train/lr": 4.467955593022733e-06, "train/grad": 0.1397274377563416, "train/loss": 0.8125757193660736, "eval/hcp-train-subset/loss": 0.8169864300758608, "eval/hcp-val/loss": 0.8290941724854131} +{"epoch": 89, "train/lr": 3.732659731856291e-06, "train/grad": 0.13701571746169328, "train/loss": 0.8148056590557098, "eval/hcp-train-subset/loss": 0.8173656425168437, "eval/hcp-val/loss": 0.8286115190675182} +{"epoch": 90, "train/lr": 3.0616250944596583e-06, "train/grad": 0.14281231422942436, "train/loss": 0.812879245595932, "eval/hcp-train-subset/loss": 0.816582364420737, "eval/hcp-val/loss": 0.8282791693364421} +{"epoch": 91, "train/lr": 2.4555854473568305e-06, "train/grad": 0.14353687288633116, "train/loss": 0.814250746011734, "eval/hcp-train-subset/loss": 0.8160880073424308, "eval/hcp-val/loss": 0.8284580774845616} +{"epoch": 92, "train/lr": 1.915203486004091e-06, "train/grad": 0.14095680781121517, "train/loss": 0.8158836714935302, "eval/hcp-train-subset/loss": 0.8153550471028974, "eval/hcp-val/loss": 0.8278651881602502} +{"epoch": 93, "train/lr": 1.4410701101423926e-06, "train/grad": 0.14471933410194018, "train/loss": 0.8156014032268524, "eval/hcp-train-subset/loss": 0.8147184743035224, "eval/hcp-val/loss": 0.8275613842471954} +{"epoch": 94, "train/lr": 1.0337037776570775e-06, "train/grad": 0.14590523430723676, "train/loss": 0.8156309150218963, "eval/hcp-train-subset/loss": 0.8143198009460203, "eval/hcp-val/loss": 0.8277568547956405} +{"epoch": 95, "train/lr": 6.935499376518293e-07, "train/grad": 0.14665701947319257, "train/loss": 0.8166734611415863, "eval/hcp-train-subset/loss": 0.8142935922068935, "eval/hcp-val/loss": 0.8276385818758318} +{"epoch": 96, "train/lr": 4.209805433566085e-07, "train/grad": 0.14341582061697228, "train/loss": 0.8166821269130706, "eval/hcp-train-subset/loss": 0.8141113788850846, "eval/hcp-val/loss": 0.8273976762448588} +{"epoch": 97, "train/lr": 2.1629364540224422e-07, "train/grad": 0.14635717181224142, "train/loss": 0.817956442785263, "eval/hcp-train-subset/loss": 0.8138470207491229, "eval/hcp-val/loss": 0.8272118741466153} +{"epoch": 98, "train/lr": 7.971306590647406e-08, "train/grad": 0.14750817609013614, "train/loss": 0.81550695063591, "eval/hcp-train-subset/loss": 0.8140413665002392, "eval/hcp-val/loss": 0.8272682793678776} +{"epoch": 99, "train/lr": 1.1388153727718725e-08, "train/grad": 0.14914267852232135, "train/loss": 0.8159549069023132, "eval/hcp-train-subset/loss": 0.8139425429605669, "eval/hcp-val/loss": 0.8272643493067834} diff --git a/input_space_v3/flat_lr1e-3_2/pretrain/log.txt b/input_space_v3/flat_lr1e-3_2/pretrain/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..1252b2f57fd26e2bbf6a171e50ee8827058c93ee --- /dev/null +++ b/input_space_v3/flat_lr1e-3_2/pretrain/log.txt @@ -0,0 +1,8829 @@ +pretraining fmri mae +start: 2026-03-31 13:08:49 +cwd: /data/connor/fmri-fm +sha: ae0eae57a44753a80f371738f3276b064d5077cb, status: clean, branch: dev/clane9 +config: +name: input_space_v3/flat_lr1e-3_2/pretrain +notes: input_space ablation v3 flat_lr1e-3_2; use tube masking and on-disk data (input_space=flat + base_lr=1e-3 seed=5402) +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain +input_space: flat +patch_size: 16 +num_frames: 16 +t_patch_size: 4 +mask_ratio: 0.9 +pred_mask_ratio: null +masking: tube +masking_kwargs: {} +mask_patch_size: null +model: mae_vit_base +model_kwargs: + decoding: attn + pos_embed: sep + target_norm: null + pca_norm_nc: 2 + t_pred_stride: 2 + no_decode_pos: true + mask_drop_scale: false + pred_edge_pad: 0 + gauss_sigma: null + class_token: true + reg_tokens: 0 + no_embed_class: true + head_init_scale: 0.0 + decoder_depth: 4 + drop_path_rate: 0.0 +datasets: + hcp-train: + type: wds + url: /data/fmri-datasets/pretrain/hcpya-all.${input_space}.wds/hcpya-all-${input_space}-{00000..01799}.tar + clipping: random + clipping_kwargs: + oversample: 4.0 + shuffle: true + buffer_size: 2000 + samples_per_epoch: 200000 + hcp-train-subset: + type: arrow + root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/validation + split_range: + - 0 + - 2000 + shuffle: false + hcp-val: + type: arrow + root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/test + split_range: + - 0 + - 2000 + shuffle: false +train_dataset: hcp-train +eval_datasets: +- hcp-train-subset +- hcp-val +val_dataset: null +clip_vmax: 3.0 +normalize: frame +tr_scale: null +crop_scale: null +crop_aspect: null +gray_jitter: null +num_workers: 16 +epochs: 100 +batch_size: 32 +accum_iter: 1 +base_lr: 0.001 +min_lr: 0.0 +warmup_epochs: 5 +weight_decay: 0.05 +betas: +- 0.9 +- 0.95 +clip_grad: 1.0 +amp: true +amp_dtype: float16 +ckpt: null +resume: true +auto_resume: true +start_epoch: 0 +max_checkpoints: 0 +checkpoint_period: null +plot_period: 5 +device: cuda +presend_cuda: false +seed: 5402 +debug: false +wandb: true +wandb_entity: null +wandb_project: fMRI-foundation-model +rank: 0 +world_size: 1 +gpu: 0 +distributed: true +dist_backend: nccl +in_chans: 1 +img_size: +- 224 +- 560 + +train transform: +Compose( + ToTensor() + TemporalCenterCrop(num_frames=16) + Normalize(mode='frame') + Clip(vmax=3.0) + FlatUnmask((224, 560)) +) +val transform: +Compose( + ToTensor() + TemporalCenterCrop(num_frames=16) + Normalize(mode='frame') + Clip(vmax=3.0) + FlatUnmask((224, 560)) +) +mask generator: +TubeMasking( + mask_ratio=0.9 + (patchify): Patchify2D((224, 560), (16, 16), in_chans=1) +) +loading dataset: hcp-train + +type: wds +url: /data/fmri-datasets/pretrain/hcpya-all.${input_space}.wds/hcpya-all-${input_space}-{00000..01799}.tar +clipping: random +clipping_kwargs: + oversample: 4.0 +shuffle: true +buffer_size: 2000 +samples_per_epoch: 200000 + +loading dataset: hcp-train-subset + +type: arrow +root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/validation +split_range: +- 0 +- 2000 +shuffle: false + +split indices: [899, 472, 767, 116, 1265, 1852, 300, 1335, 361, 1560] +loading dataset: hcp-val + +type: arrow +root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/test +split_range: +- 0 +- 2000 +shuffle: false + +split indices: [1075, 1189, 738, 1350, 965, 1964, 1367, 1183, 1619, 1407] +model: +MaskedAutoencoderViT( + decoding=attn, t_pred_stride=2, pred_edge_pad=0, no_decode_pos=True + (encoder): MaskedEncoder( + class_token=True, reg_tokens=0, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) + (pred_patchify): StridedPatchify3D((16, 224, 560), (2, 16, 16), in_chans=1, t_stride=2) + (decoder): MaskedDecoder( + cross_decode=False, class_token=True, no_embed_class=True + (pos_embed): SeparablePosEmbed(512, (4, 14, 35)) + (proj): Linear(in_features=768, out_features=512, bias=True) + (blocks): ModuleList( + (0-3): 4 x Block( + (norm1): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=16 + (q): Linear(in_features=512, out_features=512, bias=True) + (k): Linear(in_features=512, out_features=512, bias=True) + (v): Linear(in_features=512, out_features=512, bias=True) + (proj): Linear(in_features=512, out_features=512, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=512, out_features=2048, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=2048, out_features=512, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (head): Linear(in_features=512, out_features=512, bias=True) + ) +) +num params: 99.7M +total batch size: 32 = 32 bs per gpu x 1 accum x 1 gpus +lr: 1.25e-04 = 1.00e-03 x 32 / 256 +full schedule: epochs = 100 (steps = 625000) +warmup: epochs = 5 (steps = 31250) +start training for 100 epochs +Train: [0] [ 0/6250] eta: 16:59:24 lr: 0.000000 grad: 0.0099 (0.0099) loss: 0.9951 (0.9951) time: 9.7863 data: 5.2905 max mem: 8589 +Train: [0] [ 100/6250] eta: 0:54:54 lr: 0.000000 grad: 0.0138 (0.0154) loss: 0.9960 (0.9960) time: 0.2416 data: 0.0339 max mem: 9394 +Train: [0] [ 200/6250] eta: 0:46:22 lr: 0.000001 grad: 0.0126 (0.0147) loss: 0.9960 (0.9959) time: 0.3878 data: 0.2203 max mem: 9394 +Train: [0] [ 300/6250] eta: 0:39:24 lr: 0.000001 grad: 0.0128 (0.0141) loss: 0.9958 (0.9958) time: 0.3037 data: 0.1257 max mem: 9394 +Train: [0] [ 400/6250] eta: 0:36:16 lr: 0.000002 grad: 0.0130 (0.0138) loss: 0.9962 (0.9958) time: 0.2539 data: 0.1118 max mem: 9394 +Train: [0] [ 500/6250] eta: 0:34:54 lr: 0.000002 grad: 0.0128 (0.0136) loss: 0.9959 (0.9958) time: 0.1050 data: 0.0003 max mem: 9394 +Train: [0] [ 600/6250] eta: 0:31:44 lr: 0.000002 grad: 0.0126 (0.0134) loss: 0.9962 (0.9958) time: 0.1004 data: 0.0021 max mem: 9394 +Train: [0] [ 700/6250] eta: 0:30:02 lr: 0.000003 grad: 0.0127 (0.0133) loss: 0.9953 (0.9958) time: 0.3096 data: 0.1996 max mem: 9394 +Train: [0] [ 800/6250] eta: 0:28:36 lr: 0.000003 grad: 0.0126 (0.0133) loss: 0.9960 (0.9958) time: 0.3349 data: 0.2422 max mem: 9394 +Train: [0] [ 900/6250] eta: 0:27:35 lr: 0.000004 grad: 0.0130 (0.0133) loss: 0.9954 (0.9958) time: 0.1039 data: 0.0002 max mem: 9394 +Train: [0] [1000/6250] eta: 0:26:17 lr: 0.000004 grad: 0.0130 (0.0133) loss: 0.9958 (0.9958) time: 0.1260 data: 0.0414 max mem: 9394 +Train: [0] [1100/6250] eta: 0:24:40 lr: 0.000004 grad: 0.0143 (0.0133) loss: 0.9957 (0.9958) time: 0.1711 data: 0.0773 max mem: 9394 +Train: [0] [1200/6250] eta: 0:23:14 lr: 0.000005 grad: 0.0142 (0.0135) loss: 0.9957 (0.9958) time: 0.1607 data: 0.0606 max mem: 9394 +Train: [0] [1300/6250] eta: 0:21:54 lr: 0.000005 grad: 0.0157 (0.0136) loss: 0.9955 (0.9957) time: 0.1335 data: 0.0538 max mem: 9394 +Train: [0] [1400/6250] eta: 0:20:52 lr: 0.000006 grad: 0.0173 (0.0140) loss: 0.9956 (0.9957) time: 0.2213 data: 0.1402 max mem: 9394 +Train: [0] [1500/6250] eta: 0:19:46 lr: 0.000006 grad: 0.0190 (0.0144) loss: 0.9954 (0.9957) time: 0.1289 data: 0.0505 max mem: 9394 +Train: [0] [1600/6250] eta: 0:18:54 lr: 0.000006 grad: 0.0202 (0.0148) loss: 0.9954 (0.9957) time: 0.1141 data: 0.0283 max mem: 9394 +Train: [0] [1700/6250] eta: 0:18:07 lr: 0.000007 grad: 0.0278 (0.0156) loss: 0.9952 (0.9957) time: 0.1932 data: 0.1115 max mem: 9394 +Train: [0] [1800/6250] eta: 0:17:18 lr: 0.000007 grad: 0.0321 (0.0165) loss: 0.9951 (0.9956) time: 0.1335 data: 0.0437 max mem: 9394 +Train: [0] [1900/6250] eta: 0:16:34 lr: 0.000008 grad: 0.0421 (0.0177) loss: 0.9947 (0.9956) time: 0.1330 data: 0.0553 max mem: 9394 +Train: [0] [2000/6250] eta: 0:15:56 lr: 0.000008 grad: 0.0379 (0.0191) loss: 0.9944 (0.9955) time: 0.1996 data: 0.0848 max mem: 9394 +Train: [0] [2100/6250] eta: 0:15:22 lr: 0.000008 grad: 0.0522 (0.0203) loss: 0.9944 (0.9955) time: 0.1325 data: 0.0524 max mem: 9394 +Train: [0] [2200/6250] eta: 0:14:44 lr: 0.000009 grad: 0.0425 (0.0216) loss: 0.9948 (0.9955) time: 0.1292 data: 0.0522 max mem: 9394 +Train: [0] [2300/6250] eta: 0:14:09 lr: 0.000009 grad: 0.0494 (0.0227) loss: 0.9944 (0.9954) time: 0.1436 data: 0.0425 max mem: 9394 +Train: [0] [2400/6250] eta: 0:13:38 lr: 0.000010 grad: 0.0541 (0.0236) loss: 0.9937 (0.9954) time: 0.1493 data: 0.0635 max mem: 9394 +Train: [0] [2500/6250] eta: 0:13:10 lr: 0.000010 grad: 0.0445 (0.0246) loss: 0.9938 (0.9953) time: 0.1303 data: 0.0068 max mem: 9394 +Train: [0] [2600/6250] eta: 0:12:39 lr: 0.000010 grad: 0.0372 (0.0255) loss: 0.9941 (0.9953) time: 0.1277 data: 0.0425 max mem: 9394 +Train: [0] [2700/6250] eta: 0:12:18 lr: 0.000011 grad: 0.0442 (0.0265) loss: 0.9940 (0.9952) time: 0.1313 data: 0.0180 max mem: 9394 +Train: [0] [2800/6250] eta: 0:11:48 lr: 0.000011 grad: 0.0593 (0.0275) loss: 0.9938 (0.9952) time: 0.1258 data: 0.0457 max mem: 9394 +Train: [0] [2900/6250] eta: 0:11:20 lr: 0.000012 grad: 0.0565 (0.0287) loss: 0.9941 (0.9951) time: 0.1435 data: 0.0590 max mem: 9394 +Train: [0] [3000/6250] eta: 0:11:00 lr: 0.000012 grad: 0.0559 (0.0298) loss: 0.9938 (0.9951) time: 0.1127 data: 0.0230 max mem: 9394 +Train: [0] [3100/6250] eta: 0:10:34 lr: 0.000012 grad: 0.0616 (0.0311) loss: 0.9931 (0.9950) time: 0.1698 data: 0.0955 max mem: 9394 +Train: [0] [3200/6250] eta: 0:10:07 lr: 0.000013 grad: 0.0777 (0.0323) loss: 0.9930 (0.9949) time: 0.1302 data: 0.0482 max mem: 9394 +Train: [0] [3300/6250] eta: 0:09:42 lr: 0.000013 grad: 0.0637 (0.0334) loss: 0.9931 (0.9949) time: 0.1549 data: 0.0620 max mem: 9394 +Train: [0] [3400/6250] eta: 0:09:18 lr: 0.000014 grad: 0.0688 (0.0345) loss: 0.9920 (0.9948) time: 0.1349 data: 0.0537 max mem: 9394 +Train: [0] [3500/6250] eta: 0:08:55 lr: 0.000014 grad: 0.0621 (0.0354) loss: 0.9924 (0.9948) time: 0.1541 data: 0.0615 max mem: 9394 +Train: [0] [3600/6250] eta: 0:08:31 lr: 0.000014 grad: 0.0573 (0.0364) loss: 0.9928 (0.9947) time: 0.1372 data: 0.0636 max mem: 9394 +Train: [0] [3700/6250] eta: 0:08:08 lr: 0.000015 grad: 0.0653 (0.0374) loss: 0.9921 (0.9946) time: 0.1604 data: 0.0729 max mem: 9394 +Train: [0] [3800/6250] eta: 0:07:45 lr: 0.000015 grad: 0.0663 (0.0382) loss: 0.9907 (0.9945) time: 0.1310 data: 0.0548 max mem: 9394 +Train: [0] [3900/6250] eta: 0:07:23 lr: 0.000016 grad: 0.0652 (0.0392) loss: 0.9922 (0.9945) time: 0.1182 data: 0.0337 max mem: 9394 +Train: [0] [4000/6250] eta: 0:07:02 lr: 0.000016 grad: 0.0587 (0.0401) loss: 0.9914 (0.9944) time: 0.1414 data: 0.0621 max mem: 9394 +Train: [0] [4100/6250] eta: 0:06:40 lr: 0.000016 grad: 0.0654 (0.0411) loss: 0.9918 (0.9943) time: 0.1443 data: 0.0636 max mem: 9394 +Train: [0] [4200/6250] eta: 0:06:19 lr: 0.000017 grad: 0.0758 (0.0422) loss: 0.9916 (0.9942) time: 0.1332 data: 0.0546 max mem: 9394 +Train: [0] [4300/6250] eta: 0:05:58 lr: 0.000017 grad: 0.0696 (0.0429) loss: 0.9916 (0.9942) time: 0.1420 data: 0.0641 max mem: 9394 +Train: [0] [4400/6250] eta: 0:05:38 lr: 0.000018 grad: 0.0636 (0.0438) loss: 0.9921 (0.9941) time: 0.1473 data: 0.0657 max mem: 9394 +Train: [0] [4500/6250] eta: 0:05:18 lr: 0.000018 grad: 0.0739 (0.0445) loss: 0.9905 (0.9940) time: 0.1419 data: 0.0624 max mem: 9394 +Train: [0] [4600/6250] eta: 0:04:59 lr: 0.000018 grad: 0.0853 (0.0452) loss: 0.9903 (0.9940) time: 0.1554 data: 0.0528 max mem: 9394 +Train: [0] [4700/6250] eta: 0:04:39 lr: 0.000019 grad: 0.0756 (0.0461) loss: 0.9912 (0.9939) time: 0.1144 data: 0.0339 max mem: 9394 +Train: [0] [4800/6250] eta: 0:04:20 lr: 0.000019 grad: 0.0708 (0.0466) loss: 0.9912 (0.9938) time: 0.1489 data: 0.0689 max mem: 9394 +Train: [0] [4900/6250] eta: 0:04:01 lr: 0.000020 grad: 0.0698 (0.0473) loss: 0.9911 (0.9938) time: 0.1260 data: 0.0442 max mem: 9394 +Train: [0] [5000/6250] eta: 0:03:42 lr: 0.000020 grad: 0.0875 (0.0479) loss: 0.9913 (0.9937) time: 0.1370 data: 0.0522 max mem: 9394 +Train: [0] [5100/6250] eta: 0:03:23 lr: 0.000020 grad: 0.0662 (0.0486) loss: 0.9912 (0.9936) time: 0.1375 data: 0.0595 max mem: 9394 +Train: [0] [5200/6250] eta: 0:03:05 lr: 0.000021 grad: 0.0799 (0.0490) loss: 0.9916 (0.9936) time: 0.1338 data: 0.0586 max mem: 9394 +Train: [0] [5300/6250] eta: 0:02:46 lr: 0.000021 grad: 0.0579 (0.0496) loss: 0.9907 (0.9935) time: 0.1853 data: 0.0533 max mem: 9394 +Train: [0] [5400/6250] eta: 0:02:29 lr: 0.000022 grad: 0.0852 (0.0502) loss: 0.9884 (0.9935) time: 0.1594 data: 0.0783 max mem: 9394 +Train: [0] [5500/6250] eta: 0:02:11 lr: 0.000022 grad: 0.0806 (0.0508) loss: 0.9898 (0.9934) time: 0.1456 data: 0.0571 max mem: 9394 +Train: [0] [5600/6250] eta: 0:01:53 lr: 0.000022 grad: 0.0791 (0.0513) loss: 0.9908 (0.9933) time: 0.1271 data: 0.0420 max mem: 9394 +Train: [0] [5700/6250] eta: 0:01:35 lr: 0.000023 grad: 0.0784 (0.0519) loss: 0.9907 (0.9933) time: 0.1378 data: 0.0547 max mem: 9394 +Train: [0] [5800/6250] eta: 0:01:17 lr: 0.000023 grad: 0.0751 (0.0524) loss: 0.9905 (0.9932) time: 0.1567 data: 0.0746 max mem: 9394 +Train: [0] [5900/6250] eta: 0:01:00 lr: 0.000024 grad: 0.0772 (0.0529) loss: 0.9902 (0.9932) time: 0.1091 data: 0.0312 max mem: 9394 +Train: [0] [6000/6250] eta: 0:00:42 lr: 0.000024 grad: 0.0707 (0.0533) loss: 0.9906 (0.9931) time: 0.1534 data: 0.0766 max mem: 9394 +Train: [0] [6100/6250] eta: 0:00:25 lr: 0.000024 grad: 0.0856 (0.0538) loss: 0.9887 (0.9930) time: 0.1392 data: 0.0522 max mem: 9394 +Train: [0] [6200/6250] eta: 0:00:08 lr: 0.000025 grad: 0.0733 (0.0542) loss: 0.9893 (0.9930) time: 0.1465 data: 0.0671 max mem: 9394 +Train: [0] [6249/6250] eta: 0:00:00 lr: 0.000025 grad: 0.0803 (0.0545) loss: 0.9906 (0.9930) time: 0.1296 data: 0.0509 max mem: 9394 +Train: [0] Total time: 0:17:51 (0.1715 s / it) +Averaged stats: lr: 0.000025 grad: 0.0803 (0.0545) loss: 0.9906 (0.9930) +Eval (hcp-train-subset): [0] [ 0/62] eta: 0:03:08 loss: 0.9921 (0.9921) time: 3.0366 data: 2.9799 max mem: 9394 +Eval (hcp-train-subset): [0] [61/62] eta: 0:00:00 loss: 0.9927 (0.9924) time: 0.1140 data: 0.0846 max mem: 9394 +Eval (hcp-train-subset): [0] Total time: 0:00:12 (0.2002 s / it) +Averaged stats (hcp-train-subset): loss: 0.9927 (0.9924) +Eval (hcp-val): [0] [ 0/62] eta: 0:04:46 loss: 0.9850 (0.9850) time: 4.6256 data: 4.5966 max mem: 9394 +Eval (hcp-val): [0] [61/62] eta: 0:00:00 loss: 0.9903 (0.9906) time: 0.1272 data: 0.1017 max mem: 9394 +Eval (hcp-val): [0] Total time: 0:00:13 (0.2164 s / it) +Averaged stats (hcp-val): loss: 0.9903 (0.9906) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +Train: [1] [ 0/6250] eta: 9:42:48 lr: 0.000025 grad: 0.0872 (0.0872) loss: 0.9954 (0.9954) time: 5.5950 data: 5.5022 max mem: 9394 +Train: [1] [ 100/6250] eta: 0:19:59 lr: 0.000025 grad: 0.0659 (0.0745) loss: 0.9915 (0.9918) time: 0.1480 data: 0.0721 max mem: 9394 +Train: [1] [ 200/6250] eta: 0:16:51 lr: 0.000026 grad: 0.0751 (0.0786) loss: 0.9892 (0.9901) time: 0.1419 data: 0.0531 max mem: 9394 +Train: [1] [ 300/6250] eta: 0:15:45 lr: 0.000026 grad: 0.0610 (0.0787) loss: 0.9914 (0.9899) time: 0.1236 data: 0.0315 max mem: 9394 +Train: [1] [ 400/6250] eta: 0:14:49 lr: 0.000027 grad: 0.0644 (0.0781) loss: 0.9905 (0.9899) time: 0.1207 data: 0.0344 max mem: 9394 +Train: [1] [ 500/6250] eta: 0:14:11 lr: 0.000027 grad: 0.0622 (0.0766) loss: 0.9903 (0.9900) time: 0.1355 data: 0.0433 max mem: 9394 +Train: [1] [ 600/6250] eta: 0:13:44 lr: 0.000027 grad: 0.0537 (0.0753) loss: 0.9917 (0.9901) time: 0.1164 data: 0.0254 max mem: 9394 +Train: [1] [ 700/6250] eta: 0:13:53 lr: 0.000028 grad: 0.0595 (0.0740) loss: 0.9913 (0.9902) time: 0.2135 data: 0.0827 max mem: 9394 +Train: [1] [ 800/6250] eta: 0:14:00 lr: 0.000028 grad: 0.0636 (0.0728) loss: 0.9907 (0.9903) time: 0.2679 data: 0.0911 max mem: 9394 +Train: [1] [ 900/6250] eta: 0:14:31 lr: 0.000029 grad: 0.0648 (0.0729) loss: 0.9916 (0.9903) time: 0.2275 data: 0.0208 max mem: 9394 +Train: [1] [1000/6250] eta: 0:14:47 lr: 0.000029 grad: 0.0685 (0.0725) loss: 0.9902 (0.9903) time: 0.1023 data: 0.0002 max mem: 9394 +Train: [1] [1100/6250] eta: 0:14:37 lr: 0.000029 grad: 0.0659 (0.0725) loss: 0.9910 (0.9902) time: 0.1062 data: 0.0205 max mem: 9394 +Train: [1] [1200/6250] eta: 0:14:07 lr: 0.000030 grad: 0.0595 (0.0726) loss: 0.9898 (0.9902) time: 0.1491 data: 0.0698 max mem: 9394 +Train: [1] [1300/6250] eta: 0:13:55 lr: 0.000030 grad: 0.0640 (0.0724) loss: 0.9904 (0.9901) time: 0.1506 data: 0.0244 max mem: 9394 +Train: [1] [1400/6250] eta: 0:13:33 lr: 0.000031 grad: 0.0691 (0.0727) loss: 0.9905 (0.9901) time: 0.1420 data: 0.0620 max mem: 9394 +Train: [1] [1500/6250] eta: 0:13:07 lr: 0.000031 grad: 0.0547 (0.0726) loss: 0.9905 (0.9900) time: 0.1292 data: 0.0479 max mem: 9394 +Train: [1] [1600/6250] eta: 0:12:41 lr: 0.000031 grad: 0.0794 (0.0729) loss: 0.9895 (0.9900) time: 0.1020 data: 0.0241 max mem: 9394 +Train: [1] [1700/6250] eta: 0:12:19 lr: 0.000032 grad: 0.0740 (0.0732) loss: 0.9890 (0.9900) time: 0.1330 data: 0.0483 max mem: 9394 +Train: [1] [1800/6250] eta: 0:11:57 lr: 0.000032 grad: 0.0668 (0.0735) loss: 0.9909 (0.9899) time: 0.1521 data: 0.0721 max mem: 9394 +Train: [1] [1900/6250] eta: 0:11:35 lr: 0.000033 grad: 0.0822 (0.0736) loss: 0.9888 (0.9898) time: 0.1342 data: 0.0551 max mem: 9394 +Train: [1] [2000/6250] eta: 0:11:32 lr: 0.000033 grad: 0.0822 (0.0738) loss: 0.9879 (0.9898) time: 0.1219 data: 0.0358 max mem: 9394 +Train: [1] [2100/6250] eta: 0:11:10 lr: 0.000033 grad: 0.0777 (0.0740) loss: 0.9883 (0.9897) time: 0.1570 data: 0.0803 max mem: 9394 +Train: [1] [2200/6250] eta: 0:10:50 lr: 0.000034 grad: 0.0747 (0.0742) loss: 0.9883 (0.9897) time: 0.1377 data: 0.0599 max mem: 9394 +Train: [1] [2300/6250] eta: 0:10:29 lr: 0.000034 grad: 0.0766 (0.0743) loss: 0.9894 (0.9897) time: 0.1520 data: 0.0731 max mem: 9394 +Train: [1] [2400/6250] eta: 0:10:15 lr: 0.000035 grad: 0.0665 (0.0744) loss: 0.9887 (0.9896) time: 0.1043 data: 0.0003 max mem: 9394 +Train: [1] [2500/6250] eta: 0:09:56 lr: 0.000035 grad: 0.0681 (0.0745) loss: 0.9884 (0.9896) time: 0.1419 data: 0.0621 max mem: 9394 +Train: [1] [2600/6250] eta: 0:09:36 lr: 0.000035 grad: 0.0692 (0.0746) loss: 0.9892 (0.9895) time: 0.1556 data: 0.0722 max mem: 9394 +Train: [1] [2700/6250] eta: 0:09:18 lr: 0.000036 grad: 0.0736 (0.0747) loss: 0.9887 (0.9895) time: 0.1372 data: 0.0644 max mem: 9394 +Train: [1] [2800/6250] eta: 0:09:04 lr: 0.000036 grad: 0.0739 (0.0749) loss: 0.9874 (0.9894) time: 0.1284 data: 0.0516 max mem: 9394 +Train: [1] [2900/6250] eta: 0:08:45 lr: 0.000037 grad: 0.0721 (0.0750) loss: 0.9883 (0.9894) time: 0.1458 data: 0.0680 max mem: 9394 +Train: [1] [3000/6250] eta: 0:08:29 lr: 0.000037 grad: 0.0715 (0.0751) loss: 0.9894 (0.9894) time: 0.0995 data: 0.0020 max mem: 9394 +Train: [1] [3100/6250] eta: 0:08:12 lr: 0.000037 grad: 0.0771 (0.0753) loss: 0.9864 (0.9893) time: 0.1230 data: 0.0467 max mem: 9394 +Train: [1] [3200/6250] eta: 0:07:54 lr: 0.000038 grad: 0.0692 (0.0752) loss: 0.9899 (0.9893) time: 0.1387 data: 0.0534 max mem: 9394 +Train: [1] [3300/6250] eta: 0:07:38 lr: 0.000038 grad: 0.0665 (0.0752) loss: 0.9875 (0.9893) time: 0.1422 data: 0.0671 max mem: 9394 +Train: [1] [3400/6250] eta: 0:07:21 lr: 0.000039 grad: 0.0700 (0.0752) loss: 0.9895 (0.9893) time: 0.1540 data: 0.0790 max mem: 9394 +Train: [1] [3500/6250] eta: 0:07:03 lr: 0.000039 grad: 0.0692 (0.0752) loss: 0.9891 (0.9892) time: 0.1421 data: 0.0630 max mem: 9394 +Train: [1] [3600/6250] eta: 0:06:47 lr: 0.000039 grad: 0.0670 (0.0752) loss: 0.9887 (0.9892) time: 0.1277 data: 0.0463 max mem: 9394 +Train: [1] [3700/6250] eta: 0:06:30 lr: 0.000040 grad: 0.0744 (0.0752) loss: 0.9883 (0.9892) time: 0.1236 data: 0.0416 max mem: 9394 +Train: [1] [3800/6250] eta: 0:06:14 lr: 0.000040 grad: 0.0715 (0.0752) loss: 0.9889 (0.9892) time: 0.1367 data: 0.0597 max mem: 9394 +Train: [1] [3900/6250] eta: 0:05:58 lr: 0.000041 grad: 0.0750 (0.0752) loss: 0.9865 (0.9891) time: 0.1306 data: 0.0521 max mem: 9394 +Train: [1] [4000/6250] eta: 0:05:42 lr: 0.000041 grad: 0.0844 (0.0752) loss: 0.9875 (0.9891) time: 0.1279 data: 0.0463 max mem: 9394 +Train: [1] [4100/6250] eta: 0:05:25 lr: 0.000041 grad: 0.0763 (0.0753) loss: 0.9882 (0.9891) time: 0.1454 data: 0.0725 max mem: 9394 +Train: [1] [4200/6250] eta: 0:05:10 lr: 0.000042 grad: 0.0771 (0.0753) loss: 0.9888 (0.9891) time: 0.1641 data: 0.0908 max mem: 9394 +Train: [1] [4300/6250] eta: 0:04:54 lr: 0.000042 grad: 0.0722 (0.0753) loss: 0.9873 (0.9891) time: 0.1288 data: 0.0496 max mem: 9394 +Train: [1] [4400/6250] eta: 0:04:38 lr: 0.000043 grad: 0.0882 (0.0755) loss: 0.9868 (0.9890) time: 0.1374 data: 0.0630 max mem: 9394 +Train: [1] [4500/6250] eta: 0:04:23 lr: 0.000043 grad: 0.0722 (0.0756) loss: 0.9876 (0.9890) time: 0.1523 data: 0.0675 max mem: 9394 +Train: [1] [4600/6250] eta: 0:04:08 lr: 0.000043 grad: 0.0807 (0.0757) loss: 0.9876 (0.9890) time: 0.1283 data: 0.0429 max mem: 9394 +Train: [1] [4700/6250] eta: 0:03:52 lr: 0.000044 grad: 0.0743 (0.0759) loss: 0.9869 (0.9889) time: 0.1545 data: 0.0783 max mem: 9394 +Train: [1] [4800/6250] eta: 0:03:37 lr: 0.000044 grad: 0.0804 (0.0759) loss: 0.9883 (0.9889) time: 0.1022 data: 0.0161 max mem: 9394 +Train: [1] [4900/6250] eta: 0:03:22 lr: 0.000045 grad: 0.0838 (0.0760) loss: 0.9856 (0.9888) time: 0.1400 data: 0.0604 max mem: 9394 +Train: [1] [5000/6250] eta: 0:03:07 lr: 0.000045 grad: 0.0766 (0.0761) loss: 0.9861 (0.9888) time: 0.1244 data: 0.0453 max mem: 9394 +Train: [1] [5100/6250] eta: 0:02:51 lr: 0.000045 grad: 0.0781 (0.0762) loss: 0.9884 (0.9888) time: 0.1718 data: 0.0818 max mem: 9394 +Train: [1] [5200/6250] eta: 0:02:37 lr: 0.000046 grad: 0.0824 (0.0763) loss: 0.9882 (0.9887) time: 0.1272 data: 0.0369 max mem: 9394 +Train: [1] [5300/6250] eta: 0:02:21 lr: 0.000046 grad: 0.0797 (0.0763) loss: 0.9868 (0.9887) time: 0.1440 data: 0.0595 max mem: 9394 +Train: [1] [5400/6250] eta: 0:02:06 lr: 0.000047 grad: 0.0748 (0.0765) loss: 0.9871 (0.9887) time: 0.1391 data: 0.0589 max mem: 9394 +Train: [1] [5500/6250] eta: 0:01:51 lr: 0.000047 grad: 0.0791 (0.0765) loss: 0.9880 (0.9886) time: 0.0991 data: 0.0154 max mem: 9394 +Train: [1] [5600/6250] eta: 0:01:36 lr: 0.000047 grad: 0.0734 (0.0766) loss: 0.9874 (0.9886) time: 0.1451 data: 0.0613 max mem: 9394 +Train: [1] [5700/6250] eta: 0:01:21 lr: 0.000048 grad: 0.0754 (0.0766) loss: 0.9870 (0.9886) time: 0.1378 data: 0.0552 max mem: 9394 +Train: [1] [5800/6250] eta: 0:01:06 lr: 0.000048 grad: 0.0740 (0.0766) loss: 0.9858 (0.9885) time: 0.1603 data: 0.0823 max mem: 9394 +Train: [1] [5900/6250] eta: 0:00:52 lr: 0.000049 grad: 0.0655 (0.0766) loss: 0.9870 (0.9885) time: 0.1121 data: 0.0272 max mem: 9394 +Train: [1] [6000/6250] eta: 0:00:37 lr: 0.000049 grad: 0.0764 (0.0767) loss: 0.9888 (0.9885) time: 0.1565 data: 0.0770 max mem: 9394 +Train: [1] [6100/6250] eta: 0:00:22 lr: 0.000049 grad: 0.0798 (0.0767) loss: 0.9867 (0.9885) time: 0.1165 data: 0.0338 max mem: 9394 +Train: [1] [6200/6250] eta: 0:00:07 lr: 0.000050 grad: 0.0646 (0.0768) loss: 0.9883 (0.9884) time: 0.1432 data: 0.0658 max mem: 9394 +Train: [1] [6249/6250] eta: 0:00:00 lr: 0.000050 grad: 0.0665 (0.0768) loss: 0.9877 (0.9884) time: 0.1034 data: 0.0154 max mem: 9394 +Train: [1] Total time: 0:15:39 (0.1503 s / it) +Averaged stats: lr: 0.000050 grad: 0.0665 (0.0768) loss: 0.9877 (0.9884) +Eval (hcp-train-subset): [1] [ 0/62] eta: 0:03:42 loss: 0.9876 (0.9876) time: 3.5828 data: 3.4707 max mem: 9394 +Eval (hcp-train-subset): [1] [61/62] eta: 0:00:00 loss: 0.9885 (0.9886) time: 0.1152 data: 0.0905 max mem: 9394 +Eval (hcp-train-subset): [1] Total time: 0:00:13 (0.2156 s / it) +Averaged stats (hcp-train-subset): loss: 0.9885 (0.9886) +Eval (hcp-val): [1] [ 0/62] eta: 0:03:13 loss: 0.9866 (0.9866) time: 3.1146 data: 3.0353 max mem: 9394 +Eval (hcp-val): [1] [61/62] eta: 0:00:00 loss: 0.9872 (0.9872) time: 0.1423 data: 0.1175 max mem: 9394 +Eval (hcp-val): [1] Total time: 0:00:13 (0.2177 s / it) +Averaged stats (hcp-val): loss: 0.9872 (0.9872) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +Train: [2] [ 0/6250] eta: 9:25:39 lr: 0.000050 grad: 0.0477 (0.0477) loss: 0.9940 (0.9940) time: 5.4304 data: 5.3056 max mem: 9394 +Train: [2] [ 100/6250] eta: 0:20:19 lr: 0.000050 grad: 0.0773 (0.0797) loss: 0.9873 (0.9876) time: 0.1468 data: 0.0574 max mem: 9394 +Train: [2] [ 200/6250] eta: 0:17:12 lr: 0.000051 grad: 0.0829 (0.0824) loss: 0.9866 (0.9871) time: 0.1370 data: 0.0479 max mem: 9394 +Train: [2] [ 300/6250] eta: 0:16:01 lr: 0.000051 grad: 0.0903 (0.0842) loss: 0.9860 (0.9868) time: 0.1009 data: 0.0195 max mem: 9394 +Train: [2] [ 400/6250] eta: 0:15:05 lr: 0.000052 grad: 0.0679 (0.0847) loss: 0.9888 (0.9866) time: 0.1113 data: 0.0217 max mem: 9394 +Train: [2] [ 500/6250] eta: 0:14:24 lr: 0.000052 grad: 0.0795 (0.0849) loss: 0.9851 (0.9865) time: 0.1395 data: 0.0534 max mem: 9394 +Train: [2] [ 600/6250] eta: 0:14:03 lr: 0.000052 grad: 0.0847 (0.0852) loss: 0.9867 (0.9863) time: 0.1617 data: 0.0679 max mem: 9394 +Train: [2] [ 700/6250] eta: 0:13:39 lr: 0.000053 grad: 0.0808 (0.0876) loss: 0.9859 (0.9861) time: 0.1617 data: 0.0814 max mem: 9394 +Train: [2] [ 800/6250] eta: 0:13:26 lr: 0.000053 grad: 0.0853 (0.0883) loss: 0.9839 (0.9860) time: 0.1484 data: 0.0628 max mem: 9394 +Train: [2] [ 900/6250] eta: 0:13:11 lr: 0.000054 grad: 0.0783 (0.0890) loss: 0.9878 (0.9860) time: 0.1638 data: 0.0769 max mem: 9394 +Train: [2] [1000/6250] eta: 0:12:55 lr: 0.000054 grad: 0.0801 (0.0887) loss: 0.9854 (0.9859) time: 0.1415 data: 0.0566 max mem: 9394 +Train: [2] [1100/6250] eta: 0:12:37 lr: 0.000054 grad: 0.0762 (0.0887) loss: 0.9851 (0.9860) time: 0.1443 data: 0.0611 max mem: 9394 +Train: [2] [1200/6250] eta: 0:12:16 lr: 0.000055 grad: 0.0806 (0.0889) loss: 0.9864 (0.9859) time: 0.1254 data: 0.0420 max mem: 9394 +Train: [2] [1300/6250] eta: 0:11:57 lr: 0.000055 grad: 0.0873 (0.0887) loss: 0.9852 (0.9859) time: 0.1326 data: 0.0467 max mem: 9394 +Train: [2] [1400/6250] eta: 0:11:42 lr: 0.000056 grad: 0.0799 (0.0886) loss: 0.9861 (0.9859) time: 0.1460 data: 0.0574 max mem: 9394 +Train: [2] [1500/6250] eta: 0:11:25 lr: 0.000056 grad: 0.0747 (0.0883) loss: 0.9859 (0.9860) time: 0.1275 data: 0.0447 max mem: 9394 +Train: [2] [1600/6250] eta: 0:11:09 lr: 0.000056 grad: 0.0825 (0.0882) loss: 0.9841 (0.9859) time: 0.1358 data: 0.0583 max mem: 9394 +Train: [2] [1700/6250] eta: 0:10:53 lr: 0.000057 grad: 0.0829 (0.0886) loss: 0.9863 (0.9859) time: 0.1467 data: 0.0691 max mem: 9394 +Train: [2] [1800/6250] eta: 0:10:38 lr: 0.000057 grad: 0.0822 (0.0890) loss: 0.9861 (0.9859) time: 0.1485 data: 0.0736 max mem: 9394 +Train: [2] [1900/6250] eta: 0:10:28 lr: 0.000058 grad: 0.0851 (0.0890) loss: 0.9866 (0.9859) time: 0.1701 data: 0.0891 max mem: 9394 +Train: [2] [2000/6250] eta: 0:10:14 lr: 0.000058 grad: 0.0884 (0.0891) loss: 0.9844 (0.9858) time: 0.2035 data: 0.1231 max mem: 9394 +Train: [2] [2100/6250] eta: 0:09:55 lr: 0.000058 grad: 0.0800 (0.0890) loss: 0.9867 (0.9858) time: 0.1409 data: 0.0618 max mem: 9394 +Train: [2] [2200/6250] eta: 0:09:40 lr: 0.000059 grad: 0.0770 (0.0891) loss: 0.9851 (0.9858) time: 0.1403 data: 0.0624 max mem: 9394 +Train: [2] [2300/6250] eta: 0:09:25 lr: 0.000059 grad: 0.0822 (0.0887) loss: 0.9861 (0.9858) time: 0.1097 data: 0.0269 max mem: 9394 +Train: [2] [2400/6250] eta: 0:09:09 lr: 0.000060 grad: 0.0808 (0.0888) loss: 0.9852 (0.9857) time: 0.1333 data: 0.0536 max mem: 9394 +Train: [2] [2500/6250] eta: 0:08:54 lr: 0.000060 grad: 0.0935 (0.0888) loss: 0.9859 (0.9857) time: 0.1229 data: 0.0459 max mem: 9394 +Train: [2] [2600/6250] eta: 0:08:38 lr: 0.000060 grad: 0.0758 (0.0886) loss: 0.9866 (0.9858) time: 0.1366 data: 0.0559 max mem: 9394 +Train: [2] [2700/6250] eta: 0:08:24 lr: 0.000061 grad: 0.0763 (0.0884) loss: 0.9862 (0.9858) time: 0.1432 data: 0.0663 max mem: 9394 +Train: [2] [2800/6250] eta: 0:08:08 lr: 0.000061 grad: 0.0904 (0.0884) loss: 0.9844 (0.9857) time: 0.1285 data: 0.0490 max mem: 9394 +Train: [2] [2900/6250] eta: 0:07:53 lr: 0.000062 grad: 0.0922 (0.0884) loss: 0.9863 (0.9858) time: 0.1356 data: 0.0549 max mem: 9394 +Train: [2] [3000/6250] eta: 0:07:39 lr: 0.000062 grad: 0.0910 (0.0886) loss: 0.9862 (0.9858) time: 0.1428 data: 0.0645 max mem: 9394 +Train: [2] [3100/6250] eta: 0:07:29 lr: 0.000062 grad: 0.0868 (0.0889) loss: 0.9844 (0.9857) time: 0.0922 data: 0.0002 max mem: 9394 +Train: [2] [3200/6250] eta: 0:07:15 lr: 0.000063 grad: 0.0953 (0.0892) loss: 0.9843 (0.9857) time: 0.1812 data: 0.0589 max mem: 9394 +Train: [2] [3300/6250] eta: 0:07:02 lr: 0.000063 grad: 0.0851 (0.0894) loss: 0.9863 (0.9857) time: 0.1879 data: 0.1091 max mem: 9394 +Train: [2] [3400/6250] eta: 0:06:46 lr: 0.000064 grad: 0.0951 (0.0895) loss: 0.9852 (0.9857) time: 0.1368 data: 0.0600 max mem: 9394 +Train: [2] [3500/6250] eta: 0:06:33 lr: 0.000064 grad: 0.0981 (0.0901) loss: 0.9841 (0.9856) time: 0.1816 data: 0.1000 max mem: 9394 +Train: [2] [3600/6250] eta: 0:06:19 lr: 0.000064 grad: 0.0902 (0.0908) loss: 0.9848 (0.9856) time: 0.1343 data: 0.0569 max mem: 9394 +Train: [2] [3700/6250] eta: 0:06:04 lr: 0.000065 grad: 0.1147 (0.0914) loss: 0.9823 (0.9856) time: 0.1342 data: 0.0547 max mem: 9394 +Train: [2] [3800/6250] eta: 0:05:49 lr: 0.000065 grad: 0.1278 (0.0920) loss: 0.9847 (0.9855) time: 0.1338 data: 0.0530 max mem: 9394 +Train: [2] [3900/6250] eta: 0:05:35 lr: 0.000066 grad: 0.1463 (0.0933) loss: 0.9859 (0.9855) time: 0.1276 data: 0.0469 max mem: 9394 +Train: [2] [4000/6250] eta: 0:05:20 lr: 0.000066 grad: 0.1230 (0.0946) loss: 0.9835 (0.9854) time: 0.1230 data: 0.0428 max mem: 9394 +Train: [2] [4100/6250] eta: 0:05:06 lr: 0.000066 grad: 0.1105 (0.0960) loss: 0.9834 (0.9854) time: 0.1285 data: 0.0480 max mem: 9394 +Train: [2] [4200/6250] eta: 0:04:51 lr: 0.000067 grad: 0.1376 (0.0977) loss: 0.9829 (0.9853) time: 0.1384 data: 0.0572 max mem: 9394 +Train: [2] [4300/6250] eta: 0:04:37 lr: 0.000067 grad: 0.1866 (0.0999) loss: 0.9847 (0.9853) time: 0.1323 data: 0.0422 max mem: 9394 +Train: [2] [4400/6250] eta: 0:04:22 lr: 0.000068 grad: 0.1720 (0.1022) loss: 0.9834 (0.9852) time: 0.1435 data: 0.0589 max mem: 9394 +Train: [2] [4500/6250] eta: 0:04:08 lr: 0.000068 grad: 0.2448 (0.1047) loss: 0.9835 (0.9851) time: 0.1316 data: 0.0397 max mem: 9394 +Train: [2] [4600/6250] eta: 0:03:54 lr: 0.000068 grad: 0.1499 (0.1063) loss: 0.9830 (0.9851) time: 0.1317 data: 0.0529 max mem: 9394 +Train: [2] [4700/6250] eta: 0:03:39 lr: 0.000069 grad: 0.1495 (0.1092) loss: 0.9823 (0.9850) time: 0.1311 data: 0.0551 max mem: 9394 +Train: [2] [4800/6250] eta: 0:03:25 lr: 0.000069 grad: 0.2422 (0.1112) loss: 0.9821 (0.9849) time: 0.1573 data: 0.0808 max mem: 9394 +Train: [2] [4900/6250] eta: 0:03:11 lr: 0.000070 grad: 0.1186 (0.1135) loss: 0.9819 (0.9849) time: 0.1363 data: 0.0596 max mem: 9394 +Train: [2] [5000/6250] eta: 0:02:57 lr: 0.000070 grad: 0.1703 (0.1158) loss: 0.9821 (0.9848) time: 0.1595 data: 0.0758 max mem: 9394 +Train: [2] [5100/6250] eta: 0:02:43 lr: 0.000070 grad: 0.1099 (0.1176) loss: 0.9818 (0.9848) time: 0.1684 data: 0.0836 max mem: 9394 +Train: [2] [5200/6250] eta: 0:02:28 lr: 0.000071 grad: 0.1946 (0.1194) loss: 0.9818 (0.9847) time: 0.1362 data: 0.0566 max mem: 9394 +Train: [2] [5300/6250] eta: 0:02:14 lr: 0.000071 grad: 0.1181 (0.1208) loss: 0.9816 (0.9847) time: 0.1335 data: 0.0472 max mem: 9394 +Train: [2] [5400/6250] eta: 0:02:00 lr: 0.000072 grad: 0.1959 (0.1223) loss: 0.9822 (0.9846) time: 0.1462 data: 0.0622 max mem: 9394 +Train: [2] [5500/6250] eta: 0:01:46 lr: 0.000072 grad: 0.1342 (0.1235) loss: 0.9807 (0.9846) time: 0.1453 data: 0.0634 max mem: 9394 +Train: [2] [5600/6250] eta: 0:01:31 lr: 0.000072 grad: 0.1981 (0.1251) loss: 0.9816 (0.9845) time: 0.1242 data: 0.0439 max mem: 9394 +Train: [2] [5700/6250] eta: 0:01:17 lr: 0.000073 grad: 0.2505 (0.1266) loss: 0.9842 (0.9845) time: 0.1414 data: 0.0573 max mem: 9394 +Train: [2] [5800/6250] eta: 0:01:03 lr: 0.000073 grad: 0.1849 (0.1283) loss: 0.9820 (0.9844) time: 0.1435 data: 0.0589 max mem: 9394 +Train: [2] [5900/6250] eta: 0:00:49 lr: 0.000074 grad: 0.1274 (0.1296) loss: 0.9810 (0.9844) time: 0.1829 data: 0.0985 max mem: 9394 +Train: [2] [6000/6250] eta: 0:00:35 lr: 0.000074 grad: 0.1310 (0.1307) loss: 0.9799 (0.9843) time: 0.1287 data: 0.0468 max mem: 9394 +Train: [2] [6100/6250] eta: 0:00:21 lr: 0.000074 grad: 0.1197 (0.1324) loss: 0.9816 (0.9843) time: 0.1380 data: 0.0580 max mem: 9394 +Train: [2] [6200/6250] eta: 0:00:07 lr: 0.000075 grad: 0.1577 (0.1338) loss: 0.9798 (0.9842) time: 0.1298 data: 0.0479 max mem: 9394 +Train: [2] [6249/6250] eta: 0:00:00 lr: 0.000075 grad: 0.1288 (0.1344) loss: 0.9812 (0.9842) time: 0.1625 data: 0.0805 max mem: 9394 +Train: [2] Total time: 0:14:49 (0.1424 s / it) +Averaged stats: lr: 0.000075 grad: 0.1288 (0.1344) loss: 0.9812 (0.9842) +Eval (hcp-train-subset): [2] [ 0/62] eta: 0:02:57 loss: 0.9856 (0.9856) time: 2.8551 data: 2.7939 max mem: 9394 +Eval (hcp-train-subset): [2] [61/62] eta: 0:00:00 loss: 0.9838 (0.9829) time: 0.1118 data: 0.0865 max mem: 9394 +Eval (hcp-train-subset): [2] Total time: 0:00:13 (0.2137 s / it) +Averaged stats (hcp-train-subset): loss: 0.9838 (0.9829) +Eval (hcp-val): [2] [ 0/62] eta: 0:04:32 loss: 0.9725 (0.9725) time: 4.3995 data: 4.3721 max mem: 9394 +Eval (hcp-val): [2] [61/62] eta: 0:00:00 loss: 0.9818 (0.9809) time: 0.1188 data: 0.0940 max mem: 9394 +Eval (hcp-val): [2] Total time: 0:00:12 (0.2089 s / it) +Averaged stats (hcp-val): loss: 0.9818 (0.9809) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +Train: [3] [ 0/6250] eta: 8:09:18 lr: 0.000075 grad: 0.2881 (0.2881) loss: 0.9533 (0.9533) time: 4.6974 data: 4.5221 max mem: 9394 +Train: [3] [ 100/6250] eta: 0:19:22 lr: 0.000075 grad: 0.2107 (0.2637) loss: 0.9810 (0.9782) time: 0.1461 data: 0.0558 max mem: 9394 +Train: [3] [ 200/6250] eta: 0:16:40 lr: 0.000076 grad: 0.1935 (0.2515) loss: 0.9825 (0.9782) time: 0.1306 data: 0.0470 max mem: 9394 +Train: [3] [ 300/6250] eta: 0:15:31 lr: 0.000076 grad: 0.1342 (0.2417) loss: 0.9821 (0.9785) time: 0.1282 data: 0.0462 max mem: 9394 +Train: [3] [ 400/6250] eta: 0:14:45 lr: 0.000077 grad: 0.1783 (0.2347) loss: 0.9791 (0.9782) time: 0.1508 data: 0.0628 max mem: 9394 +Train: [3] [ 500/6250] eta: 0:14:01 lr: 0.000077 grad: 0.2897 (0.2379) loss: 0.9788 (0.9781) time: 0.1331 data: 0.0356 max mem: 9394 +Train: [3] [ 600/6250] eta: 0:13:52 lr: 0.000077 grad: 0.1654 (0.2415) loss: 0.9742 (0.9778) time: 0.1692 data: 0.0799 max mem: 9394 +Train: [3] [ 700/6250] eta: 0:13:26 lr: 0.000078 grad: 0.1949 (0.2452) loss: 0.9790 (0.9779) time: 0.1411 data: 0.0510 max mem: 9394 +Train: [3] [ 800/6250] eta: 0:13:16 lr: 0.000078 grad: 0.1693 (0.2406) loss: 0.9755 (0.9777) time: 0.1931 data: 0.1174 max mem: 9394 +Train: [3] [ 900/6250] eta: 0:12:54 lr: 0.000079 grad: 0.2245 (0.2400) loss: 0.9798 (0.9778) time: 0.1260 data: 0.0426 max mem: 9394 +Train: [3] [1000/6250] eta: 0:12:41 lr: 0.000079 grad: 0.3004 (0.2393) loss: 0.9780 (0.9777) time: 0.0911 data: 0.0088 max mem: 9394 +Train: [3] [1100/6250] eta: 0:12:26 lr: 0.000079 grad: 0.1425 (0.2378) loss: 0.9775 (0.9779) time: 0.1161 data: 0.0361 max mem: 9394 +Train: [3] [1200/6250] eta: 0:12:06 lr: 0.000080 grad: 0.2292 (0.2378) loss: 0.9781 (0.9778) time: 0.1291 data: 0.0488 max mem: 9394 +Train: [3] [1300/6250] eta: 0:11:52 lr: 0.000080 grad: 0.2257 (0.2370) loss: 0.9788 (0.9778) time: 0.1473 data: 0.0688 max mem: 9394 +Train: [3] [1400/6250] eta: 0:11:36 lr: 0.000081 grad: 0.1451 (0.2345) loss: 0.9784 (0.9778) time: 0.1353 data: 0.0548 max mem: 9394 +Train: [3] [1500/6250] eta: 0:11:22 lr: 0.000081 grad: 0.1602 (0.2326) loss: 0.9794 (0.9778) time: 0.1435 data: 0.0637 max mem: 9394 +Train: [3] [1600/6250] eta: 0:11:06 lr: 0.000081 grad: 0.1513 (0.2320) loss: 0.9761 (0.9778) time: 0.1233 data: 0.0450 max mem: 9394 +Train: [3] [1700/6250] eta: 0:10:53 lr: 0.000082 grad: 0.1409 (0.2295) loss: 0.9765 (0.9777) time: 0.1082 data: 0.0283 max mem: 9394 +Train: [3] [1800/6250] eta: 0:10:37 lr: 0.000082 grad: 0.1792 (0.2297) loss: 0.9777 (0.9777) time: 0.1472 data: 0.0696 max mem: 9394 +Train: [3] [1900/6250] eta: 0:10:22 lr: 0.000083 grad: 0.1381 (0.2291) loss: 0.9792 (0.9777) time: 0.1314 data: 0.0541 max mem: 9394 +Train: [3] [2000/6250] eta: 0:10:06 lr: 0.000083 grad: 0.1809 (0.2283) loss: 0.9765 (0.9777) time: 0.1311 data: 0.0486 max mem: 9394 +Train: [3] [2100/6250] eta: 0:09:53 lr: 0.000083 grad: 0.2270 (0.2278) loss: 0.9762 (0.9776) time: 0.1590 data: 0.0787 max mem: 9394 +Train: [3] [2200/6250] eta: 0:09:38 lr: 0.000084 grad: 0.1401 (0.2279) loss: 0.9769 (0.9775) time: 0.1449 data: 0.0655 max mem: 9394 +Train: [3] [2300/6250] eta: 0:09:24 lr: 0.000084 grad: 0.1629 (0.2256) loss: 0.9751 (0.9774) time: 0.1548 data: 0.0664 max mem: 9394 +Train: [3] [2400/6250] eta: 0:09:11 lr: 0.000085 grad: 0.1870 (0.2237) loss: 0.9780 (0.9774) time: 0.1586 data: 0.0786 max mem: 9394 +Train: [3] [2500/6250] eta: 0:08:55 lr: 0.000085 grad: 0.1402 (0.2228) loss: 0.9764 (0.9773) time: 0.1359 data: 0.0510 max mem: 9394 +Train: [3] [2600/6250] eta: 0:08:40 lr: 0.000085 grad: 0.1108 (0.2220) loss: 0.9759 (0.9773) time: 0.1430 data: 0.0626 max mem: 9394 +Train: [3] [2700/6250] eta: 0:08:24 lr: 0.000086 grad: 0.1822 (0.2220) loss: 0.9734 (0.9772) time: 0.1215 data: 0.0364 max mem: 9394 +Train: [3] [2800/6250] eta: 0:08:09 lr: 0.000086 grad: 0.1669 (0.2207) loss: 0.9762 (0.9772) time: 0.1361 data: 0.0536 max mem: 9394 +Train: [3] [2900/6250] eta: 0:07:55 lr: 0.000087 grad: 0.2098 (0.2197) loss: 0.9723 (0.9772) time: 0.1499 data: 0.0720 max mem: 9394 +Train: [3] [3000/6250] eta: 0:07:40 lr: 0.000087 grad: 0.1325 (0.2185) loss: 0.9744 (0.9771) time: 0.1441 data: 0.0652 max mem: 9394 +Train: [3] [3100/6250] eta: 0:07:26 lr: 0.000087 grad: 0.1789 (0.2178) loss: 0.9731 (0.9771) time: 0.1481 data: 0.0663 max mem: 9394 +Train: [3] [3200/6250] eta: 0:07:12 lr: 0.000088 grad: 0.1666 (0.2168) loss: 0.9780 (0.9770) time: 0.1459 data: 0.0676 max mem: 9394 +Train: [3] [3300/6250] eta: 0:06:58 lr: 0.000088 grad: 0.1288 (0.2159) loss: 0.9754 (0.9770) time: 0.1436 data: 0.0597 max mem: 9394 +Train: [3] [3400/6250] eta: 0:06:43 lr: 0.000089 grad: 0.1602 (0.2157) loss: 0.9754 (0.9770) time: 0.1282 data: 0.0509 max mem: 9394 +Train: [3] [3500/6250] eta: 0:06:29 lr: 0.000089 grad: 0.2037 (0.2146) loss: 0.9752 (0.9769) time: 0.1152 data: 0.0359 max mem: 9394 +Train: [3] [3600/6250] eta: 0:06:14 lr: 0.000089 grad: 0.1431 (0.2144) loss: 0.9752 (0.9769) time: 0.1279 data: 0.0416 max mem: 9394 +Train: [3] [3700/6250] eta: 0:06:00 lr: 0.000090 grad: 0.1275 (0.2138) loss: 0.9741 (0.9768) time: 0.1535 data: 0.0683 max mem: 9394 +Train: [3] [3800/6250] eta: 0:05:46 lr: 0.000090 grad: 0.1437 (0.2131) loss: 0.9764 (0.9768) time: 0.1440 data: 0.0581 max mem: 9394 +Train: [3] [3900/6250] eta: 0:05:31 lr: 0.000091 grad: 0.1796 (0.2130) loss: 0.9756 (0.9767) time: 0.1168 data: 0.0370 max mem: 9394 +Train: [3] [4000/6250] eta: 0:05:17 lr: 0.000091 grad: 0.1148 (0.2122) loss: 0.9756 (0.9767) time: 0.0916 data: 0.0087 max mem: 9394 +Train: [3] [4100/6250] eta: 0:05:03 lr: 0.000091 grad: 0.2421 (0.2125) loss: 0.9765 (0.9766) time: 0.1356 data: 0.0456 max mem: 9394 +Train: [3] [4200/6250] eta: 0:04:48 lr: 0.000092 grad: 0.1827 (0.2121) loss: 0.9730 (0.9765) time: 0.1187 data: 0.0396 max mem: 9394 +Train: [3] [4300/6250] eta: 0:04:34 lr: 0.000092 grad: 0.1696 (0.2119) loss: 0.9744 (0.9765) time: 0.1355 data: 0.0615 max mem: 9394 +Train: [3] [4400/6250] eta: 0:04:20 lr: 0.000093 grad: 0.1783 (0.2116) loss: 0.9738 (0.9764) time: 0.1349 data: 0.0545 max mem: 9394 +Train: [3] [4500/6250] eta: 0:04:06 lr: 0.000093 grad: 0.1361 (0.2109) loss: 0.9750 (0.9764) time: 0.1841 data: 0.0842 max mem: 9394 +Train: [3] [4600/6250] eta: 0:03:52 lr: 0.000093 grad: 0.1851 (0.2104) loss: 0.9733 (0.9763) time: 0.1363 data: 0.0561 max mem: 9394 +Train: [3] [4700/6250] eta: 0:03:38 lr: 0.000094 grad: 0.1881 (0.2103) loss: 0.9712 (0.9762) time: 0.1378 data: 0.0551 max mem: 9394 +Train: [3] [4800/6250] eta: 0:03:23 lr: 0.000094 grad: 0.1695 (0.2106) loss: 0.9719 (0.9762) time: 0.1440 data: 0.0536 max mem: 9394 +Train: [3] [4900/6250] eta: 0:03:09 lr: 0.000095 grad: 0.1367 (0.2102) loss: 0.9722 (0.9761) time: 0.1419 data: 0.0622 max mem: 9394 +Train: [3] [5000/6250] eta: 0:02:55 lr: 0.000095 grad: 0.1899 (0.2100) loss: 0.9728 (0.9761) time: 0.1584 data: 0.0767 max mem: 9394 +Train: [3] [5100/6250] eta: 0:02:41 lr: 0.000095 grad: 0.2028 (0.2097) loss: 0.9756 (0.9760) time: 0.1561 data: 0.0665 max mem: 9394 +Train: [3] [5200/6250] eta: 0:02:27 lr: 0.000096 grad: 0.1721 (0.2095) loss: 0.9744 (0.9760) time: 0.1361 data: 0.0517 max mem: 9394 +Train: [3] [5300/6250] eta: 0:02:13 lr: 0.000096 grad: 0.1493 (0.2092) loss: 0.9741 (0.9759) time: 0.1341 data: 0.0547 max mem: 9394 +Train: [3] [5400/6250] eta: 0:01:59 lr: 0.000097 grad: 0.1426 (0.2084) loss: 0.9731 (0.9758) time: 0.1442 data: 0.0607 max mem: 9394 +Train: [3] [5500/6250] eta: 0:01:45 lr: 0.000097 grad: 0.2185 (0.2088) loss: 0.9698 (0.9758) time: 0.1537 data: 0.0697 max mem: 9394 +Train: [3] [5600/6250] eta: 0:01:31 lr: 0.000097 grad: 0.1885 (0.2084) loss: 0.9696 (0.9757) time: 0.1607 data: 0.0786 max mem: 9394 +Train: [3] [5700/6250] eta: 0:01:17 lr: 0.000098 grad: 0.1812 (0.2082) loss: 0.9705 (0.9756) time: 0.1314 data: 0.0484 max mem: 9394 +Train: [3] [5800/6250] eta: 0:01:03 lr: 0.000098 grad: 0.1606 (0.2081) loss: 0.9712 (0.9755) time: 0.1746 data: 0.1009 max mem: 9394 +Train: [3] [5900/6250] eta: 0:00:49 lr: 0.000099 grad: 0.1733 (0.2078) loss: 0.9708 (0.9755) time: 0.1471 data: 0.0634 max mem: 9394 +Train: [3] [6000/6250] eta: 0:00:35 lr: 0.000099 grad: 0.1350 (0.2069) loss: 0.9709 (0.9754) time: 0.1518 data: 0.0705 max mem: 9394 +Train: [3] [6100/6250] eta: 0:00:21 lr: 0.000099 grad: 0.2135 (0.2070) loss: 0.9703 (0.9753) time: 0.1322 data: 0.0512 max mem: 9394 +Train: [3] [6200/6250] eta: 0:00:07 lr: 0.000100 grad: 0.1863 (0.2068) loss: 0.9702 (0.9752) time: 0.1607 data: 0.0668 max mem: 9394 +Train: [3] [6249/6250] eta: 0:00:00 lr: 0.000100 grad: 0.1422 (0.2068) loss: 0.9688 (0.9752) time: 0.1589 data: 0.0750 max mem: 9394 +Train: [3] Total time: 0:14:43 (0.1414 s / it) +Averaged stats: lr: 0.000100 grad: 0.1422 (0.2068) loss: 0.9688 (0.9752) +Eval (hcp-train-subset): [3] [ 0/62] eta: 0:04:25 loss: 0.9701 (0.9701) time: 4.2816 data: 4.2501 max mem: 9394 +Eval (hcp-train-subset): [3] [61/62] eta: 0:00:00 loss: 0.9723 (0.9716) time: 0.1537 data: 0.1285 max mem: 9394 +Eval (hcp-train-subset): [3] Total time: 0:00:13 (0.2119 s / it) +Averaged stats (hcp-train-subset): loss: 0.9723 (0.9716) +Eval (hcp-val): [3] [ 0/62] eta: 0:04:01 loss: 0.9659 (0.9659) time: 3.9015 data: 3.8713 max mem: 9394 +Eval (hcp-val): [3] [61/62] eta: 0:00:00 loss: 0.9683 (0.9683) time: 0.1216 data: 0.0950 max mem: 9394 +Eval (hcp-val): [3] Total time: 0:00:12 (0.2020 s / it) +Averaged stats (hcp-val): loss: 0.9683 (0.9683) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +Train: [4] [ 0/6250] eta: 9:29:19 lr: 0.000100 grad: 0.0948 (0.0948) loss: 0.9806 (0.9806) time: 5.4655 data: 5.3377 max mem: 9394 +Train: [4] [ 100/6250] eta: 0:19:54 lr: 0.000100 grad: 0.2046 (0.1997) loss: 0.9725 (0.9711) time: 0.1650 data: 0.0836 max mem: 9394 +Train: [4] [ 200/6250] eta: 0:16:35 lr: 0.000101 grad: 0.1472 (0.1902) loss: 0.9697 (0.9704) time: 0.1399 data: 0.0581 max mem: 9394 +Train: [4] [ 300/6250] eta: 0:15:12 lr: 0.000101 grad: 0.1689 (0.1935) loss: 0.9696 (0.9699) time: 0.1315 data: 0.0496 max mem: 9394 +Train: [4] [ 400/6250] eta: 0:14:24 lr: 0.000102 grad: 0.2201 (0.1989) loss: 0.9673 (0.9697) time: 0.1368 data: 0.0545 max mem: 9394 +Train: [4] [ 500/6250] eta: 0:14:01 lr: 0.000102 grad: 0.1343 (0.1928) loss: 0.9659 (0.9692) time: 0.1499 data: 0.0563 max mem: 9394 +Train: [4] [ 600/6250] eta: 0:13:46 lr: 0.000102 grad: 0.2769 (0.1951) loss: 0.9676 (0.9687) time: 0.1249 data: 0.0359 max mem: 9394 +Train: [4] [ 700/6250] eta: 0:13:29 lr: 0.000103 grad: 0.1907 (0.1965) loss: 0.9635 (0.9684) time: 0.1619 data: 0.0788 max mem: 9394 +Train: [4] [ 800/6250] eta: 0:13:32 lr: 0.000103 grad: 0.1870 (0.1962) loss: 0.9642 (0.9680) time: 0.2105 data: 0.1305 max mem: 9394 +Train: [4] [ 900/6250] eta: 0:13:22 lr: 0.000104 grad: 0.2370 (0.1968) loss: 0.9663 (0.9676) time: 0.2091 data: 0.1319 max mem: 9394 +Train: [4] [1000/6250] eta: 0:13:04 lr: 0.000104 grad: 0.2241 (0.2008) loss: 0.9645 (0.9673) time: 0.1878 data: 0.0794 max mem: 9394 +Train: [4] [1100/6250] eta: 0:12:45 lr: 0.000104 grad: 0.1430 (0.1993) loss: 0.9656 (0.9670) time: 0.1301 data: 0.0492 max mem: 9394 +Train: [4] [1200/6250] eta: 0:12:29 lr: 0.000105 grad: 0.2516 (0.1998) loss: 0.9618 (0.9666) time: 0.1611 data: 0.0792 max mem: 9394 +Train: [4] [1300/6250] eta: 0:12:07 lr: 0.000105 grad: 0.1570 (0.1995) loss: 0.9617 (0.9662) time: 0.1409 data: 0.0613 max mem: 9394 +Train: [4] [1400/6250] eta: 0:11:51 lr: 0.000106 grad: 0.1754 (0.2007) loss: 0.9589 (0.9658) time: 0.1325 data: 0.0509 max mem: 9394 +Train: [4] [1500/6250] eta: 0:11:34 lr: 0.000106 grad: 0.1894 (0.2015) loss: 0.9596 (0.9654) time: 0.1235 data: 0.0311 max mem: 9394 +Train: [4] [1600/6250] eta: 0:11:19 lr: 0.000106 grad: 0.1683 (0.2047) loss: 0.9577 (0.9650) time: 0.1369 data: 0.0583 max mem: 9394 +Train: [4] [1700/6250] eta: 0:11:03 lr: 0.000107 grad: 0.1712 (0.2047) loss: 0.9566 (0.9646) time: 0.1465 data: 0.0726 max mem: 9394 +Train: [4] [1800/6250] eta: 0:10:48 lr: 0.000107 grad: 0.1916 (0.2055) loss: 0.9546 (0.9641) time: 0.1548 data: 0.0747 max mem: 9394 +Train: [4] [1900/6250] eta: 0:10:32 lr: 0.000108 grad: 0.2314 (0.2082) loss: 0.9566 (0.9636) time: 0.1346 data: 0.0579 max mem: 9394 +Train: [4] [2000/6250] eta: 0:10:16 lr: 0.000108 grad: 0.2265 (0.2082) loss: 0.9525 (0.9631) time: 0.1371 data: 0.0548 max mem: 9394 +Train: [4] [2100/6250] eta: 0:10:00 lr: 0.000108 grad: 0.2369 (0.2104) loss: 0.9542 (0.9626) time: 0.1290 data: 0.0456 max mem: 9394 +Train: [4] [2200/6250] eta: 0:09:44 lr: 0.000109 grad: 0.2537 (0.2136) loss: 0.9482 (0.9621) time: 0.1346 data: 0.0518 max mem: 9394 +Train: [4] [2300/6250] eta: 0:09:30 lr: 0.000109 grad: 0.2325 (0.2151) loss: 0.9502 (0.9616) time: 0.1560 data: 0.0781 max mem: 9394 +Train: [4] [2400/6250] eta: 0:09:13 lr: 0.000110 grad: 0.2404 (0.2186) loss: 0.9472 (0.9611) time: 0.1274 data: 0.0487 max mem: 9394 +Train: [4] [2500/6250] eta: 0:08:58 lr: 0.000110 grad: 0.2295 (0.2193) loss: 0.9454 (0.9605) time: 0.1422 data: 0.0568 max mem: 9394 +Train: [4] [2600/6250] eta: 0:08:43 lr: 0.000110 grad: 0.2245 (0.2219) loss: 0.9460 (0.9599) time: 0.1381 data: 0.0549 max mem: 9394 +Train: [4] [2700/6250] eta: 0:08:27 lr: 0.000111 grad: 0.2213 (0.2234) loss: 0.9420 (0.9593) time: 0.1466 data: 0.0638 max mem: 9394 +Train: [4] [2800/6250] eta: 0:08:12 lr: 0.000111 grad: 0.2265 (0.2243) loss: 0.9434 (0.9587) time: 0.1199 data: 0.0391 max mem: 9394 +Train: [4] [2900/6250] eta: 0:07:57 lr: 0.000112 grad: 0.2301 (0.2254) loss: 0.9386 (0.9581) time: 0.1388 data: 0.0557 max mem: 9394 +Train: [4] [3000/6250] eta: 0:07:42 lr: 0.000112 grad: 0.2695 (0.2267) loss: 0.9439 (0.9576) time: 0.1015 data: 0.0193 max mem: 9394 +Train: [4] [3100/6250] eta: 0:07:27 lr: 0.000112 grad: 0.2164 (0.2272) loss: 0.9394 (0.9571) time: 0.1405 data: 0.0588 max mem: 9394 +Train: [4] [3200/6250] eta: 0:07:13 lr: 0.000113 grad: 0.2129 (0.2274) loss: 0.9403 (0.9565) time: 0.1479 data: 0.0660 max mem: 9394 +Train: [4] [3300/6250] eta: 0:06:58 lr: 0.000113 grad: 0.1811 (0.2274) loss: 0.9410 (0.9560) time: 0.1547 data: 0.0704 max mem: 9394 +Train: [4] [3400/6250] eta: 0:06:43 lr: 0.000114 grad: 0.2101 (0.2275) loss: 0.9363 (0.9555) time: 0.1354 data: 0.0556 max mem: 9394 +Train: [4] [3500/6250] eta: 0:06:28 lr: 0.000114 grad: 0.2161 (0.2279) loss: 0.9381 (0.9550) time: 0.1196 data: 0.0411 max mem: 9394 +Train: [4] [3600/6250] eta: 0:06:13 lr: 0.000114 grad: 0.2016 (0.2277) loss: 0.9374 (0.9545) time: 0.1370 data: 0.0571 max mem: 9394 +Train: [4] [3700/6250] eta: 0:05:59 lr: 0.000115 grad: 0.2240 (0.2285) loss: 0.9387 (0.9540) time: 0.1326 data: 0.0505 max mem: 9394 +Train: [4] [3800/6250] eta: 0:05:45 lr: 0.000115 grad: 0.2051 (0.2284) loss: 0.9368 (0.9536) time: 0.1670 data: 0.0871 max mem: 9394 +Train: [4] [3900/6250] eta: 0:05:31 lr: 0.000116 grad: 0.2150 (0.2287) loss: 0.9325 (0.9531) time: 0.1636 data: 0.0811 max mem: 9394 +Train: [4] [4000/6250] eta: 0:05:17 lr: 0.000116 grad: 0.1955 (0.2285) loss: 0.9328 (0.9526) time: 0.1283 data: 0.0445 max mem: 9394 +Train: [4] [4100/6250] eta: 0:05:03 lr: 0.000116 grad: 0.1709 (0.2283) loss: 0.9313 (0.9522) time: 0.1365 data: 0.0467 max mem: 9394 +Train: [4] [4200/6250] eta: 0:04:48 lr: 0.000117 grad: 0.2607 (0.2286) loss: 0.9327 (0.9517) time: 0.1370 data: 0.0556 max mem: 9394 +Train: [4] [4300/6250] eta: 0:04:34 lr: 0.000117 grad: 0.2547 (0.2283) loss: 0.9316 (0.9513) time: 0.1387 data: 0.0595 max mem: 9394 +Train: [4] [4400/6250] eta: 0:04:20 lr: 0.000118 grad: 0.2020 (0.2284) loss: 0.9287 (0.9508) time: 0.1493 data: 0.0725 max mem: 9394 +Train: [4] [4500/6250] eta: 0:04:06 lr: 0.000118 grad: 0.2103 (0.2282) loss: 0.9331 (0.9504) time: 0.1488 data: 0.0616 max mem: 9394 +Train: [4] [4600/6250] eta: 0:03:52 lr: 0.000118 grad: 0.1960 (0.2280) loss: 0.9312 (0.9499) time: 0.1139 data: 0.0365 max mem: 9394 +Train: [4] [4700/6250] eta: 0:03:38 lr: 0.000119 grad: 0.2284 (0.2277) loss: 0.9308 (0.9495) time: 0.1349 data: 0.0565 max mem: 9394 +Train: [4] [4800/6250] eta: 0:03:23 lr: 0.000119 grad: 0.2096 (0.2272) loss: 0.9305 (0.9491) time: 0.1201 data: 0.0363 max mem: 9394 +Train: [4] [4900/6250] eta: 0:03:10 lr: 0.000120 grad: 0.1773 (0.2268) loss: 0.9293 (0.9487) time: 0.1613 data: 0.0377 max mem: 9394 +Train: [4] [5000/6250] eta: 0:02:56 lr: 0.000120 grad: 0.2667 (0.2269) loss: 0.9257 (0.9483) time: 0.1784 data: 0.1030 max mem: 9394 +Train: [4] [5100/6250] eta: 0:02:41 lr: 0.000120 grad: 0.1883 (0.2266) loss: 0.9246 (0.9478) time: 0.1239 data: 0.0407 max mem: 9394 +Train: [4] [5200/6250] eta: 0:02:27 lr: 0.000121 grad: 0.1925 (0.2262) loss: 0.9304 (0.9474) time: 0.1487 data: 0.0722 max mem: 9394 +Train: [4] [5300/6250] eta: 0:02:13 lr: 0.000121 grad: 0.1653 (0.2259) loss: 0.9256 (0.9471) time: 0.1281 data: 0.0440 max mem: 9394 +Train: [4] [5400/6250] eta: 0:01:59 lr: 0.000122 grad: 0.1916 (0.2251) loss: 0.9250 (0.9467) time: 0.1266 data: 0.0470 max mem: 9394 +Train: [4] [5500/6250] eta: 0:01:45 lr: 0.000122 grad: 0.1611 (0.2244) loss: 0.9248 (0.9463) time: 0.1396 data: 0.0584 max mem: 9394 +Train: [4] [5600/6250] eta: 0:01:31 lr: 0.000122 grad: 0.1698 (0.2237) loss: 0.9264 (0.9459) time: 0.1278 data: 0.0493 max mem: 9394 +Train: [4] [5700/6250] eta: 0:01:17 lr: 0.000123 grad: 0.1806 (0.2230) loss: 0.9282 (0.9456) time: 0.1152 data: 0.0354 max mem: 9394 +Train: [4] [5800/6250] eta: 0:01:03 lr: 0.000123 grad: 0.1724 (0.2228) loss: 0.9213 (0.9452) time: 0.1316 data: 0.0477 max mem: 9394 +Train: [4] [5900/6250] eta: 0:00:49 lr: 0.000124 grad: 0.1617 (0.2224) loss: 0.9220 (0.9449) time: 0.1554 data: 0.0740 max mem: 9394 +Train: [4] [6000/6250] eta: 0:00:35 lr: 0.000124 grad: 0.1783 (0.2220) loss: 0.9242 (0.9445) time: 0.1328 data: 0.0574 max mem: 9394 +Train: [4] [6100/6250] eta: 0:00:21 lr: 0.000124 grad: 0.1654 (0.2213) loss: 0.9252 (0.9442) time: 0.1205 data: 0.0419 max mem: 9394 +Train: [4] [6200/6250] eta: 0:00:07 lr: 0.000125 grad: 0.1810 (0.2208) loss: 0.9258 (0.9438) time: 0.1606 data: 0.0719 max mem: 9394 +Train: [4] [6249/6250] eta: 0:00:00 lr: 0.000125 grad: 0.1634 (0.2206) loss: 0.9217 (0.9437) time: 0.1630 data: 0.0760 max mem: 9394 +Train: [4] Total time: 0:14:43 (0.1413 s / it) +Averaged stats: lr: 0.000125 grad: 0.1634 (0.2206) loss: 0.9217 (0.9437) +Eval (hcp-train-subset): [4] [ 0/62] eta: 0:03:47 loss: 0.9300 (0.9300) time: 3.6653 data: 3.5794 max mem: 9394 +Eval (hcp-train-subset): [4] [61/62] eta: 0:00:00 loss: 0.9271 (0.9250) time: 0.1282 data: 0.1015 max mem: 9394 +Eval (hcp-train-subset): [4] Total time: 0:00:13 (0.2106 s / it) +Averaged stats (hcp-train-subset): loss: 0.9271 (0.9250) +Making plots (hcp-train-subset): example=52 +Eval (hcp-val): [4] [ 0/62] eta: 0:05:09 loss: 0.9164 (0.9164) time: 4.9875 data: 4.9596 max mem: 9394 +Eval (hcp-val): [4] [61/62] eta: 0:00:00 loss: 0.9199 (0.9194) time: 0.1265 data: 0.1014 max mem: 9394 +Eval (hcp-val): [4] Total time: 0:00:12 (0.2047 s / it) +Averaged stats (hcp-val): loss: 0.9199 (0.9194) +Making plots (hcp-val): example=29 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +Train: [5] [ 0/6250] eta: 8:27:11 lr: 0.000125 grad: 0.2208 (0.2208) loss: 0.9342 (0.9342) time: 4.8691 data: 4.7339 max mem: 9394 +Train: [5] [ 100/6250] eta: 0:19:40 lr: 0.000125 grad: 0.1892 (0.1884) loss: 0.9187 (0.9265) time: 0.1571 data: 0.0732 max mem: 9394 +Train: [5] [ 200/6250] eta: 0:16:31 lr: 0.000125 grad: 0.2789 (0.2006) loss: 0.9123 (0.9223) time: 0.1280 data: 0.0458 max mem: 9394 +Train: [5] [ 300/6250] eta: 0:15:14 lr: 0.000125 grad: 0.1686 (0.1942) loss: 0.9146 (0.9198) time: 0.1363 data: 0.0542 max mem: 9394 +Train: [5] [ 400/6250] eta: 0:14:49 lr: 0.000125 grad: 0.1551 (0.1913) loss: 0.9142 (0.9190) time: 0.1870 data: 0.0949 max mem: 9394 +Train: [5] [ 500/6250] eta: 0:14:24 lr: 0.000125 grad: 0.1634 (0.1881) loss: 0.9181 (0.9186) time: 0.1637 data: 0.0768 max mem: 9394 +Train: [5] [ 600/6250] eta: 0:14:05 lr: 0.000125 grad: 0.1740 (0.1856) loss: 0.9208 (0.9185) time: 0.1554 data: 0.0724 max mem: 9394 +Train: [5] [ 700/6250] eta: 0:13:57 lr: 0.000125 grad: 0.1572 (0.1856) loss: 0.9153 (0.9184) time: 0.1295 data: 0.0490 max mem: 9394 +Train: [5] [ 800/6250] eta: 0:13:41 lr: 0.000125 grad: 0.1690 (0.1841) loss: 0.9138 (0.9181) time: 0.1543 data: 0.0704 max mem: 9394 +Train: [5] [ 900/6250] eta: 0:13:26 lr: 0.000125 grad: 0.1632 (0.1838) loss: 0.9140 (0.9178) time: 0.1418 data: 0.0572 max mem: 9394 +Train: [5] [1000/6250] eta: 0:13:06 lr: 0.000125 grad: 0.1596 (0.1825) loss: 0.9165 (0.9177) time: 0.1559 data: 0.0735 max mem: 9394 +Train: [5] [1100/6250] eta: 0:12:48 lr: 0.000125 grad: 0.1593 (0.1814) loss: 0.9168 (0.9176) time: 0.1446 data: 0.0651 max mem: 9394 +Train: [5] [1200/6250] eta: 0:12:28 lr: 0.000125 grad: 0.1619 (0.1798) loss: 0.9161 (0.9174) time: 0.1105 data: 0.0306 max mem: 9394 +Train: [5] [1300/6250] eta: 0:12:11 lr: 0.000125 grad: 0.1480 (0.1788) loss: 0.9174 (0.9173) time: 0.1329 data: 0.0502 max mem: 9394 +Train: [5] [1400/6250] eta: 0:12:05 lr: 0.000125 grad: 0.1286 (0.1775) loss: 0.9171 (0.9172) time: 0.2720 data: 0.1647 max mem: 9394 +Train: [5] [1500/6250] eta: 0:11:44 lr: 0.000125 grad: 0.1483 (0.1774) loss: 0.9142 (0.9170) time: 0.1367 data: 0.0582 max mem: 9394 +Train: [5] [1600/6250] eta: 0:11:26 lr: 0.000125 grad: 0.1674 (0.1773) loss: 0.9178 (0.9168) time: 0.1461 data: 0.0671 max mem: 9394 +Train: [5] [1700/6250] eta: 0:11:11 lr: 0.000125 grad: 0.1523 (0.1763) loss: 0.9151 (0.9166) time: 0.1664 data: 0.0891 max mem: 9394 +Train: [5] [1800/6250] eta: 0:10:52 lr: 0.000125 grad: 0.1600 (0.1761) loss: 0.9117 (0.9164) time: 0.1220 data: 0.0422 max mem: 9394 +Train: [5] [1900/6250] eta: 0:10:36 lr: 0.000125 grad: 0.1607 (0.1749) loss: 0.9133 (0.9162) time: 0.1234 data: 0.0424 max mem: 9394 +Train: [5] [2000/6250] eta: 0:10:20 lr: 0.000125 grad: 0.1477 (0.1743) loss: 0.9109 (0.9159) time: 0.1350 data: 0.0576 max mem: 9394 +Train: [5] [2100/6250] eta: 0:10:04 lr: 0.000125 grad: 0.1659 (0.1736) loss: 0.9107 (0.9157) time: 0.1263 data: 0.0436 max mem: 9394 +Train: [5] [2200/6250] eta: 0:09:48 lr: 0.000125 grad: 0.1547 (0.1730) loss: 0.9083 (0.9155) time: 0.1419 data: 0.0594 max mem: 9394 +Train: [5] [2300/6250] eta: 0:09:31 lr: 0.000125 grad: 0.1409 (0.1729) loss: 0.9104 (0.9153) time: 0.1214 data: 0.0391 max mem: 9394 +Train: [5] [2400/6250] eta: 0:09:15 lr: 0.000125 grad: 0.1510 (0.1724) loss: 0.9060 (0.9150) time: 0.1417 data: 0.0623 max mem: 9394 +Train: [5] [2500/6250] eta: 0:09:00 lr: 0.000125 grad: 0.1455 (0.1718) loss: 0.9097 (0.9148) time: 0.1363 data: 0.0532 max mem: 9394 +Train: [5] [2600/6250] eta: 0:08:44 lr: 0.000125 grad: 0.1453 (0.1711) loss: 0.9088 (0.9145) time: 0.1712 data: 0.0962 max mem: 9394 +Train: [5] [2700/6250] eta: 0:08:29 lr: 0.000125 grad: 0.1664 (0.1706) loss: 0.9084 (0.9143) time: 0.1233 data: 0.0470 max mem: 9394 +Train: [5] [2800/6250] eta: 0:08:14 lr: 0.000125 grad: 0.1589 (0.1702) loss: 0.9062 (0.9140) time: 0.1346 data: 0.0565 max mem: 9394 +Train: [5] [2900/6250] eta: 0:07:59 lr: 0.000125 grad: 0.1633 (0.1702) loss: 0.9080 (0.9138) time: 0.1400 data: 0.0586 max mem: 9394 +Train: [5] [3000/6250] eta: 0:07:44 lr: 0.000125 grad: 0.1509 (0.1695) loss: 0.9032 (0.9135) time: 0.1269 data: 0.0454 max mem: 9394 +Train: [5] [3100/6250] eta: 0:07:29 lr: 0.000125 grad: 0.1438 (0.1691) loss: 0.9051 (0.9131) time: 0.1176 data: 0.0409 max mem: 9394 +Train: [5] [3200/6250] eta: 0:07:14 lr: 0.000125 grad: 0.1544 (0.1687) loss: 0.9032 (0.9129) time: 0.1431 data: 0.0650 max mem: 9394 +Train: [5] [3300/6250] eta: 0:06:58 lr: 0.000125 grad: 0.1470 (0.1684) loss: 0.9048 (0.9126) time: 0.1228 data: 0.0406 max mem: 9394 +Train: [5] [3400/6250] eta: 0:06:43 lr: 0.000125 grad: 0.1514 (0.1681) loss: 0.9009 (0.9123) time: 0.1317 data: 0.0415 max mem: 9394 +Train: [5] [3500/6250] eta: 0:06:29 lr: 0.000125 grad: 0.1476 (0.1680) loss: 0.9023 (0.9120) time: 0.1217 data: 0.0388 max mem: 9394 +Train: [5] [3600/6250] eta: 0:06:14 lr: 0.000125 grad: 0.1629 (0.1676) loss: 0.9020 (0.9117) time: 0.1139 data: 0.0299 max mem: 9394 +Train: [5] [3700/6250] eta: 0:06:00 lr: 0.000125 grad: 0.1629 (0.1672) loss: 0.9007 (0.9114) time: 0.1419 data: 0.0675 max mem: 9394 +Train: [5] [3800/6250] eta: 0:05:45 lr: 0.000125 grad: 0.1317 (0.1669) loss: 0.8975 (0.9110) time: 0.1353 data: 0.0560 max mem: 9394 +Train: [5] [3900/6250] eta: 0:05:31 lr: 0.000125 grad: 0.1433 (0.1666) loss: 0.8960 (0.9106) time: 0.1348 data: 0.0544 max mem: 9394 +Train: [5] [4000/6250] eta: 0:05:16 lr: 0.000125 grad: 0.1407 (0.1664) loss: 0.8933 (0.9102) time: 0.1522 data: 0.0714 max mem: 9394 +Train: [5] [4100/6250] eta: 0:05:02 lr: 0.000125 grad: 0.1414 (0.1663) loss: 0.8924 (0.9098) time: 0.1650 data: 0.0866 max mem: 9394 +Train: [5] [4200/6250] eta: 0:04:48 lr: 0.000125 grad: 0.1247 (0.1656) loss: 0.8949 (0.9094) time: 0.1465 data: 0.0664 max mem: 9394 +Train: [5] [4300/6250] eta: 0:04:34 lr: 0.000125 grad: 0.1572 (0.1653) loss: 0.8958 (0.9091) time: 0.1246 data: 0.0463 max mem: 9394 +Train: [5] [4400/6250] eta: 0:04:20 lr: 0.000125 grad: 0.1390 (0.1649) loss: 0.8926 (0.9087) time: 0.1415 data: 0.0565 max mem: 9394 +Train: [5] [4500/6250] eta: 0:04:06 lr: 0.000125 grad: 0.1402 (0.1645) loss: 0.8912 (0.9083) time: 0.1353 data: 0.0576 max mem: 9394 +Train: [5] [4600/6250] eta: 0:03:52 lr: 0.000125 grad: 0.1227 (0.1641) loss: 0.8930 (0.9080) time: 0.1072 data: 0.0270 max mem: 9394 +Train: [5] [4700/6250] eta: 0:03:38 lr: 0.000125 grad: 0.1358 (0.1637) loss: 0.8930 (0.9077) time: 0.2118 data: 0.1044 max mem: 9394 +Train: [5] [4800/6250] eta: 0:03:24 lr: 0.000125 grad: 0.1140 (0.1632) loss: 0.8929 (0.9073) time: 0.1287 data: 0.0488 max mem: 9394 +Train: [5] [4900/6250] eta: 0:03:10 lr: 0.000125 grad: 0.1229 (0.1631) loss: 0.8904 (0.9070) time: 0.1368 data: 0.0561 max mem: 9394 +Train: [5] [5000/6250] eta: 0:02:55 lr: 0.000125 grad: 0.1473 (0.1626) loss: 0.8904 (0.9067) time: 0.1443 data: 0.0707 max mem: 9394 +Train: [5] [5100/6250] eta: 0:02:41 lr: 0.000125 grad: 0.1224 (0.1623) loss: 0.8915 (0.9063) time: 0.1329 data: 0.0530 max mem: 9394 +Train: [5] [5200/6250] eta: 0:02:27 lr: 0.000125 grad: 0.1161 (0.1618) loss: 0.8869 (0.9060) time: 0.1341 data: 0.0540 max mem: 9394 +Train: [5] [5300/6250] eta: 0:02:13 lr: 0.000125 grad: 0.1678 (0.1618) loss: 0.8909 (0.9057) time: 0.1311 data: 0.0476 max mem: 9394 +Train: [5] [5400/6250] eta: 0:01:59 lr: 0.000125 grad: 0.1259 (0.1613) loss: 0.8889 (0.9053) time: 0.1483 data: 0.0680 max mem: 9394 +Train: [5] [5500/6250] eta: 0:01:45 lr: 0.000125 grad: 0.1344 (0.1608) loss: 0.8873 (0.9050) time: 0.2147 data: 0.0796 max mem: 9394 +Train: [5] [5600/6250] eta: 0:01:31 lr: 0.000125 grad: 0.1278 (0.1604) loss: 0.8886 (0.9047) time: 0.1347 data: 0.0486 max mem: 9394 +Train: [5] [5700/6250] eta: 0:01:17 lr: 0.000125 grad: 0.1146 (0.1597) loss: 0.8874 (0.9045) time: 0.1397 data: 0.0591 max mem: 9394 +Train: [5] [5800/6250] eta: 0:01:03 lr: 0.000125 grad: 0.1121 (0.1593) loss: 0.8870 (0.9042) time: 0.1472 data: 0.0682 max mem: 9394 +Train: [5] [5900/6250] eta: 0:00:49 lr: 0.000125 grad: 0.1217 (0.1589) loss: 0.8869 (0.9039) time: 0.1132 data: 0.0232 max mem: 9394 +Train: [5] [6000/6250] eta: 0:00:35 lr: 0.000125 grad: 0.1206 (0.1584) loss: 0.8844 (0.9036) time: 0.1499 data: 0.0699 max mem: 9394 +Train: [5] [6100/6250] eta: 0:00:21 lr: 0.000125 grad: 0.1169 (0.1579) loss: 0.8812 (0.9033) time: 0.1508 data: 0.0685 max mem: 9394 +Train: [5] [6200/6250] eta: 0:00:07 lr: 0.000125 grad: 0.1117 (0.1575) loss: 0.8839 (0.9030) time: 0.1601 data: 0.0753 max mem: 9394 +Train: [5] [6249/6250] eta: 0:00:00 lr: 0.000125 grad: 0.1203 (0.1573) loss: 0.8846 (0.9028) time: 0.1480 data: 0.0683 max mem: 9394 +Train: [5] Total time: 0:14:45 (0.1417 s / it) +Averaged stats: lr: 0.000125 grad: 0.1203 (0.1573) loss: 0.8846 (0.9028) +Eval (hcp-train-subset): [5] [ 0/62] eta: 0:04:26 loss: 0.8937 (0.8937) time: 4.2925 data: 4.2507 max mem: 9394 +Eval (hcp-train-subset): [5] [61/62] eta: 0:00:00 loss: 0.8860 (0.8859) time: 0.1134 data: 0.0886 max mem: 9394 +Eval (hcp-train-subset): [5] Total time: 0:00:12 (0.2042 s / it) +Averaged stats (hcp-train-subset): loss: 0.8860 (0.8859) +Eval (hcp-val): [5] [ 0/62] eta: 0:03:06 loss: 0.8746 (0.8746) time: 3.0142 data: 2.9559 max mem: 9394 +Eval (hcp-val): [5] [61/62] eta: 0:00:00 loss: 0.8795 (0.8804) time: 0.1230 data: 0.0980 max mem: 9394 +Eval (hcp-val): [5] Total time: 0:00:12 (0.1945 s / it) +Averaged stats (hcp-val): loss: 0.8795 (0.8804) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +Train: [6] [ 0/6250] eta: 7:34:05 lr: 0.000125 grad: 0.1230 (0.1230) loss: 0.9045 (0.9045) time: 4.3592 data: 4.1497 max mem: 9394 +Train: [6] [ 100/6250] eta: 0:19:27 lr: 0.000125 grad: 0.1192 (0.1519) loss: 0.8838 (0.8898) time: 0.1425 data: 0.0488 max mem: 9394 +Train: [6] [ 200/6250] eta: 0:16:59 lr: 0.000125 grad: 0.1434 (0.1448) loss: 0.8780 (0.8869) time: 0.1543 data: 0.0661 max mem: 9394 +Train: [6] [ 300/6250] eta: 0:16:27 lr: 0.000125 grad: 0.1231 (0.1421) loss: 0.8808 (0.8844) time: 0.1643 data: 0.0719 max mem: 9394 +Train: [6] [ 400/6250] eta: 0:15:48 lr: 0.000125 grad: 0.1170 (0.1390) loss: 0.8786 (0.8837) time: 0.1352 data: 0.0387 max mem: 9394 +Train: [6] [ 500/6250] eta: 0:15:14 lr: 0.000125 grad: 0.1027 (0.1341) loss: 0.8803 (0.8837) time: 0.1293 data: 0.0397 max mem: 9394 +Train: [6] [ 600/6250] eta: 0:14:51 lr: 0.000125 grad: 0.1274 (0.1336) loss: 0.8828 (0.8832) time: 0.1461 data: 0.0597 max mem: 9394 +Train: [6] [ 700/6250] eta: 0:14:38 lr: 0.000125 grad: 0.1127 (0.1320) loss: 0.8783 (0.8830) time: 0.1213 data: 0.0327 max mem: 9394 +Train: [6] [ 800/6250] eta: 0:14:40 lr: 0.000125 grad: 0.1034 (0.1306) loss: 0.8815 (0.8830) time: 0.1421 data: 0.0630 max mem: 9394 +Train: [6] [ 900/6250] eta: 0:14:12 lr: 0.000125 grad: 0.1150 (0.1299) loss: 0.8802 (0.8828) time: 0.1238 data: 0.0378 max mem: 9394 +Train: [6] [1000/6250] eta: 0:13:59 lr: 0.000125 grad: 0.0989 (0.1292) loss: 0.8755 (0.8823) time: 0.0977 data: 0.0004 max mem: 9394 +Train: [6] [1100/6250] eta: 0:13:47 lr: 0.000125 grad: 0.1021 (0.1287) loss: 0.8771 (0.8820) time: 0.1263 data: 0.0419 max mem: 9394 +Train: [6] [1200/6250] eta: 0:13:22 lr: 0.000125 grad: 0.1109 (0.1282) loss: 0.8798 (0.8816) time: 0.1237 data: 0.0399 max mem: 9394 +Train: [6] [1300/6250] eta: 0:12:59 lr: 0.000125 grad: 0.1449 (0.1278) loss: 0.8783 (0.8814) time: 0.1125 data: 0.0247 max mem: 9394 +Train: [6] [1400/6250] eta: 0:12:37 lr: 0.000125 grad: 0.1076 (0.1272) loss: 0.8829 (0.8812) time: 0.1345 data: 0.0510 max mem: 9394 +Train: [6] [1500/6250] eta: 0:12:21 lr: 0.000125 grad: 0.1144 (0.1267) loss: 0.8771 (0.8809) time: 0.1173 data: 0.0287 max mem: 9394 +Train: [6] [1600/6250] eta: 0:12:03 lr: 0.000125 grad: 0.1349 (0.1263) loss: 0.8741 (0.8806) time: 0.1615 data: 0.0793 max mem: 9394 +Train: [6] [1700/6250] eta: 0:11:43 lr: 0.000125 grad: 0.1087 (0.1260) loss: 0.8768 (0.8803) time: 0.1626 data: 0.0852 max mem: 9394 +Train: [6] [1800/6250] eta: 0:11:22 lr: 0.000125 grad: 0.1176 (0.1256) loss: 0.8744 (0.8800) time: 0.1405 data: 0.0610 max mem: 9394 +Train: [6] [1900/6250] eta: 0:11:03 lr: 0.000125 grad: 0.0960 (0.1249) loss: 0.8714 (0.8797) time: 0.1354 data: 0.0540 max mem: 9394 +Train: [6] [2000/6250] eta: 0:10:45 lr: 0.000125 grad: 0.1087 (0.1246) loss: 0.8743 (0.8794) time: 0.1380 data: 0.0618 max mem: 9394 +Train: [6] [2100/6250] eta: 0:10:29 lr: 0.000125 grad: 0.1013 (0.1237) loss: 0.8712 (0.8791) time: 0.1572 data: 0.0799 max mem: 9394 +Train: [6] [2200/6250] eta: 0:10:12 lr: 0.000125 grad: 0.1131 (0.1232) loss: 0.8718 (0.8788) time: 0.1273 data: 0.0458 max mem: 9394 +Train: [6] [2300/6250] eta: 0:09:57 lr: 0.000125 grad: 0.1149 (0.1227) loss: 0.8686 (0.8785) time: 0.1431 data: 0.0665 max mem: 9394 +Train: [6] [2400/6250] eta: 0:09:39 lr: 0.000125 grad: 0.1261 (0.1224) loss: 0.8709 (0.8782) time: 0.1328 data: 0.0508 max mem: 9394 +Train: [6] [2500/6250] eta: 0:09:22 lr: 0.000125 grad: 0.0972 (0.1219) loss: 0.8676 (0.8779) time: 0.1455 data: 0.0616 max mem: 9394 +Train: [6] [2600/6250] eta: 0:09:05 lr: 0.000125 grad: 0.1037 (0.1212) loss: 0.8673 (0.8777) time: 0.1350 data: 0.0512 max mem: 9394 +Train: [6] [2700/6250] eta: 0:08:49 lr: 0.000125 grad: 0.1034 (0.1208) loss: 0.8661 (0.8773) time: 0.1349 data: 0.0466 max mem: 9394 +Train: [6] [2800/6250] eta: 0:08:32 lr: 0.000125 grad: 0.1016 (0.1205) loss: 0.8716 (0.8771) time: 0.1305 data: 0.0515 max mem: 9394 +Train: [6] [2900/6250] eta: 0:08:16 lr: 0.000125 grad: 0.1025 (0.1200) loss: 0.8704 (0.8769) time: 0.1396 data: 0.0602 max mem: 9394 +Train: [6] [3000/6250] eta: 0:07:59 lr: 0.000125 grad: 0.1035 (0.1198) loss: 0.8715 (0.8767) time: 0.1562 data: 0.0749 max mem: 9394 +Train: [6] [3100/6250] eta: 0:07:48 lr: 0.000125 grad: 0.0968 (0.1192) loss: 0.8743 (0.8765) time: 0.1210 data: 0.0286 max mem: 9394 +Train: [6] [3200/6250] eta: 0:07:31 lr: 0.000125 grad: 0.0938 (0.1187) loss: 0.8737 (0.8764) time: 0.1371 data: 0.0547 max mem: 9394 +Train: [6] [3300/6250] eta: 0:07:15 lr: 0.000125 grad: 0.1055 (0.1183) loss: 0.8739 (0.8763) time: 0.1416 data: 0.0592 max mem: 9394 +Train: [6] [3400/6250] eta: 0:06:59 lr: 0.000125 grad: 0.0922 (0.1178) loss: 0.8715 (0.8761) time: 0.1347 data: 0.0532 max mem: 9394 +Train: [6] [3500/6250] eta: 0:06:43 lr: 0.000125 grad: 0.0961 (0.1172) loss: 0.8686 (0.8760) time: 0.1498 data: 0.0671 max mem: 9394 +Train: [6] [3600/6250] eta: 0:06:28 lr: 0.000125 grad: 0.0994 (0.1167) loss: 0.8665 (0.8758) time: 0.1445 data: 0.0569 max mem: 9394 +Train: [6] [3700/6250] eta: 0:06:13 lr: 0.000125 grad: 0.1014 (0.1163) loss: 0.8673 (0.8756) time: 0.1345 data: 0.0531 max mem: 9394 +Train: [6] [3800/6250] eta: 0:05:58 lr: 0.000125 grad: 0.0906 (0.1160) loss: 0.8702 (0.8755) time: 0.1444 data: 0.0659 max mem: 9394 +Train: [6] [3900/6250] eta: 0:05:43 lr: 0.000125 grad: 0.0852 (0.1158) loss: 0.8669 (0.8753) time: 0.1356 data: 0.0528 max mem: 9394 +Train: [6] [4000/6250] eta: 0:05:28 lr: 0.000125 grad: 0.1051 (0.1154) loss: 0.8702 (0.8752) time: 0.1557 data: 0.0682 max mem: 9394 +Train: [6] [4100/6250] eta: 0:05:13 lr: 0.000125 grad: 0.0864 (0.1150) loss: 0.8743 (0.8751) time: 0.1356 data: 0.0569 max mem: 9394 +Train: [6] [4200/6250] eta: 0:04:58 lr: 0.000125 grad: 0.0998 (0.1149) loss: 0.8686 (0.8750) time: 0.1059 data: 0.0270 max mem: 9394 +Train: [6] [4300/6250] eta: 0:04:43 lr: 0.000125 grad: 0.0925 (0.1144) loss: 0.8706 (0.8749) time: 0.1383 data: 0.0572 max mem: 9394 +Train: [6] [4400/6250] eta: 0:04:28 lr: 0.000125 grad: 0.0939 (0.1140) loss: 0.8690 (0.8748) time: 0.0948 data: 0.0002 max mem: 9394 +Train: [6] [4500/6250] eta: 0:04:14 lr: 0.000125 grad: 0.0832 (0.1136) loss: 0.8669 (0.8747) time: 0.1346 data: 0.0535 max mem: 9394 +Train: [6] [4600/6250] eta: 0:03:59 lr: 0.000125 grad: 0.0862 (0.1131) loss: 0.8677 (0.8746) time: 0.1278 data: 0.0476 max mem: 9394 +Train: [6] [4700/6250] eta: 0:03:44 lr: 0.000125 grad: 0.0914 (0.1127) loss: 0.8708 (0.8745) time: 0.1596 data: 0.0761 max mem: 9394 +Train: [6] [4800/6250] eta: 0:03:30 lr: 0.000125 grad: 0.0918 (0.1123) loss: 0.8763 (0.8745) time: 0.1505 data: 0.0667 max mem: 9394 +Train: [6] [4900/6250] eta: 0:03:15 lr: 0.000125 grad: 0.0865 (0.1120) loss: 0.8705 (0.8744) time: 0.1400 data: 0.0577 max mem: 9394 +Train: [6] [5000/6250] eta: 0:03:00 lr: 0.000125 grad: 0.0914 (0.1116) loss: 0.8711 (0.8743) time: 0.1313 data: 0.0481 max mem: 9394 +Train: [6] [5100/6250] eta: 0:02:45 lr: 0.000125 grad: 0.0851 (0.1112) loss: 0.8706 (0.8743) time: 0.1364 data: 0.0561 max mem: 9394 +Train: [6] [5200/6250] eta: 0:02:31 lr: 0.000125 grad: 0.1060 (0.1110) loss: 0.8699 (0.8742) time: 0.1229 data: 0.0342 max mem: 9394 +Train: [6] [5300/6250] eta: 0:02:16 lr: 0.000125 grad: 0.1041 (0.1109) loss: 0.8702 (0.8741) time: 0.1383 data: 0.0602 max mem: 9394 +Train: [6] [5400/6250] eta: 0:02:02 lr: 0.000125 grad: 0.0851 (0.1105) loss: 0.8706 (0.8741) time: 0.1358 data: 0.0531 max mem: 9394 +Train: [6] [5500/6250] eta: 0:01:48 lr: 0.000125 grad: 0.0934 (0.1103) loss: 0.8667 (0.8740) time: 0.1172 data: 0.0347 max mem: 9394 +Train: [6] [5600/6250] eta: 0:01:33 lr: 0.000125 grad: 0.0796 (0.1100) loss: 0.8712 (0.8740) time: 0.1479 data: 0.0684 max mem: 9394 +Train: [6] [5700/6250] eta: 0:01:19 lr: 0.000125 grad: 0.0847 (0.1097) loss: 0.8714 (0.8739) time: 0.1553 data: 0.0713 max mem: 9394 +Train: [6] [5800/6250] eta: 0:01:04 lr: 0.000125 grad: 0.0880 (0.1094) loss: 0.8727 (0.8739) time: 0.1415 data: 0.0581 max mem: 9394 +Train: [6] [5900/6250] eta: 0:00:50 lr: 0.000125 grad: 0.0855 (0.1090) loss: 0.8694 (0.8738) time: 0.1255 data: 0.0360 max mem: 9394 +Train: [6] [6000/6250] eta: 0:00:35 lr: 0.000125 grad: 0.0886 (0.1087) loss: 0.8708 (0.8737) time: 0.1346 data: 0.0566 max mem: 9394 +Train: [6] [6100/6250] eta: 0:00:21 lr: 0.000125 grad: 0.0904 (0.1084) loss: 0.8712 (0.8736) time: 0.1039 data: 0.0003 max mem: 9394 +Train: [6] [6200/6250] eta: 0:00:07 lr: 0.000125 grad: 0.0839 (0.1081) loss: 0.8673 (0.8735) time: 0.1803 data: 0.0961 max mem: 9394 +Train: [6] [6249/6250] eta: 0:00:00 lr: 0.000125 grad: 0.0830 (0.1079) loss: 0.8658 (0.8735) time: 0.1507 data: 0.0698 max mem: 9394 +Train: [6] Total time: 0:15:05 (0.1449 s / it) +Averaged stats: lr: 0.000125 grad: 0.0830 (0.1079) loss: 0.8658 (0.8735) +Eval (hcp-train-subset): [6] [ 0/62] eta: 0:03:59 loss: 0.8812 (0.8812) time: 3.8612 data: 3.7967 max mem: 9394 +Eval (hcp-train-subset): [6] [61/62] eta: 0:00:00 loss: 0.8723 (0.8712) time: 0.1257 data: 0.0995 max mem: 9394 +Eval (hcp-train-subset): [6] Total time: 0:00:12 (0.2004 s / it) +Averaged stats (hcp-train-subset): loss: 0.8723 (0.8712) +Eval (hcp-val): [6] [ 0/62] eta: 0:05:14 loss: 0.8615 (0.8615) time: 5.0730 data: 5.0452 max mem: 9394 +Eval (hcp-val): [6] [61/62] eta: 0:00:00 loss: 0.8651 (0.8650) time: 0.1117 data: 0.0865 max mem: 9394 +Eval (hcp-val): [6] Total time: 0:00:11 (0.1926 s / it) +Averaged stats (hcp-val): loss: 0.8651 (0.8650) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +Train: [7] [ 0/6250] eta: 6:28:24 lr: 0.000125 grad: 0.0635 (0.0635) loss: 0.8947 (0.8947) time: 3.7287 data: 3.4934 max mem: 9394 +Train: [7] [ 100/6250] eta: 0:20:28 lr: 0.000125 grad: 0.0893 (0.1281) loss: 0.8661 (0.8699) time: 0.1765 data: 0.0811 max mem: 9394 +Train: [7] [ 200/6250] eta: 0:18:50 lr: 0.000125 grad: 0.0876 (0.1110) loss: 0.8761 (0.8711) time: 0.1298 data: 0.0395 max mem: 9394 +Train: [7] [ 300/6250] eta: 0:17:51 lr: 0.000125 grad: 0.0976 (0.1043) loss: 0.8715 (0.8707) time: 0.1626 data: 0.0746 max mem: 9394 +Train: [7] [ 400/6250] eta: 0:16:57 lr: 0.000125 grad: 0.0815 (0.1016) loss: 0.8664 (0.8695) time: 0.1424 data: 0.0543 max mem: 9394 +Train: [7] [ 500/6250] eta: 0:16:19 lr: 0.000125 grad: 0.0865 (0.0989) loss: 0.8645 (0.8691) time: 0.1653 data: 0.0835 max mem: 9394 +Train: [7] [ 600/6250] eta: 0:15:58 lr: 0.000125 grad: 0.0909 (0.0973) loss: 0.8706 (0.8692) time: 0.2352 data: 0.1014 max mem: 9394 +Train: [7] [ 700/6250] eta: 0:15:38 lr: 0.000125 grad: 0.0985 (0.0964) loss: 0.8697 (0.8690) time: 0.1330 data: 0.0426 max mem: 9394 +Train: [7] [ 800/6250] eta: 0:15:49 lr: 0.000125 grad: 0.0793 (0.0950) loss: 0.8688 (0.8689) time: 0.1686 data: 0.0469 max mem: 9394 +Train: [7] [ 900/6250] eta: 0:15:14 lr: 0.000125 grad: 0.0768 (0.0938) loss: 0.8693 (0.8690) time: 0.1558 data: 0.0659 max mem: 9394 +Train: [7] [1000/6250] eta: 0:14:57 lr: 0.000125 grad: 0.0834 (0.0938) loss: 0.8659 (0.8689) time: 0.1456 data: 0.0377 max mem: 9394 +Train: [7] [1100/6250] eta: 0:14:29 lr: 0.000125 grad: 0.0905 (0.0930) loss: 0.8682 (0.8691) time: 0.0986 data: 0.0111 max mem: 9394 +Train: [7] [1200/6250] eta: 0:13:59 lr: 0.000125 grad: 0.0826 (0.0926) loss: 0.8611 (0.8688) time: 0.1379 data: 0.0543 max mem: 9394 +Train: [7] [1300/6250] eta: 0:13:36 lr: 0.000125 grad: 0.0823 (0.0920) loss: 0.8670 (0.8687) time: 0.1463 data: 0.0553 max mem: 9394 +Train: [7] [1400/6250] eta: 0:13:12 lr: 0.000125 grad: 0.0915 (0.0915) loss: 0.8649 (0.8686) time: 0.1435 data: 0.0649 max mem: 9394 +Train: [7] [1500/6250] eta: 0:12:49 lr: 0.000125 grad: 0.0903 (0.0912) loss: 0.8672 (0.8685) time: 0.1173 data: 0.0303 max mem: 9394 +Train: [7] [1600/6250] eta: 0:12:32 lr: 0.000125 grad: 0.0744 (0.0909) loss: 0.8671 (0.8685) time: 0.2424 data: 0.0909 max mem: 9394 +Train: [7] [1700/6250] eta: 0:12:11 lr: 0.000125 grad: 0.0809 (0.0911) loss: 0.8672 (0.8684) time: 0.1309 data: 0.0517 max mem: 9394 +Train: [7] [1800/6250] eta: 0:11:49 lr: 0.000125 grad: 0.0862 (0.0907) loss: 0.8637 (0.8683) time: 0.1323 data: 0.0486 max mem: 9394 +Train: [7] [1900/6250] eta: 0:11:29 lr: 0.000125 grad: 0.0748 (0.0905) loss: 0.8648 (0.8683) time: 0.1286 data: 0.0433 max mem: 9394 +Train: [7] [2000/6250] eta: 0:11:09 lr: 0.000125 grad: 0.0810 (0.0902) loss: 0.8709 (0.8682) time: 0.1353 data: 0.0575 max mem: 9394 +Train: [7] [2100/6250] eta: 0:10:50 lr: 0.000125 grad: 0.0837 (0.0899) loss: 0.8666 (0.8681) time: 0.1465 data: 0.0632 max mem: 9394 +Train: [7] [2200/6250] eta: 0:10:30 lr: 0.000125 grad: 0.0745 (0.0895) loss: 0.8653 (0.8681) time: 0.1405 data: 0.0539 max mem: 9394 +Train: [7] [2300/6250] eta: 0:10:11 lr: 0.000125 grad: 0.0831 (0.0893) loss: 0.8621 (0.8679) time: 0.1349 data: 0.0485 max mem: 9394 +Train: [7] [2400/6250] eta: 0:09:54 lr: 0.000125 grad: 0.0806 (0.0896) loss: 0.8649 (0.8678) time: 0.1428 data: 0.0644 max mem: 9394 +Train: [7] [2500/6250] eta: 0:09:36 lr: 0.000125 grad: 0.0789 (0.0894) loss: 0.8685 (0.8678) time: 0.1472 data: 0.0692 max mem: 9394 +Train: [7] [2600/6250] eta: 0:09:17 lr: 0.000125 grad: 0.0829 (0.0893) loss: 0.8639 (0.8677) time: 0.1417 data: 0.0612 max mem: 9394 +Train: [7] [2700/6250] eta: 0:09:02 lr: 0.000125 grad: 0.0758 (0.0890) loss: 0.8679 (0.8676) time: 0.1114 data: 0.0136 max mem: 9394 +Train: [7] [2800/6250] eta: 0:08:44 lr: 0.000125 grad: 0.0724 (0.0887) loss: 0.8651 (0.8676) time: 0.1205 data: 0.0436 max mem: 9394 +Train: [7] [2900/6250] eta: 0:08:27 lr: 0.000125 grad: 0.0780 (0.0887) loss: 0.8654 (0.8675) time: 0.1439 data: 0.0620 max mem: 9394 +Train: [7] [3000/6250] eta: 0:08:10 lr: 0.000125 grad: 0.0706 (0.0884) loss: 0.8650 (0.8675) time: 0.1297 data: 0.0506 max mem: 9394 +Train: [7] [3100/6250] eta: 0:07:54 lr: 0.000125 grad: 0.0775 (0.0883) loss: 0.8656 (0.8675) time: 0.1443 data: 0.0650 max mem: 9394 +Train: [7] [3200/6250] eta: 0:07:38 lr: 0.000125 grad: 0.0792 (0.0883) loss: 0.8615 (0.8674) time: 0.1517 data: 0.0728 max mem: 9394 +Train: [7] [3300/6250] eta: 0:07:23 lr: 0.000125 grad: 0.0739 (0.0880) loss: 0.8636 (0.8673) time: 0.1954 data: 0.1150 max mem: 9394 +Train: [7] [3400/6250] eta: 0:07:08 lr: 0.000125 grad: 0.0763 (0.0878) loss: 0.8644 (0.8672) time: 0.1293 data: 0.0492 max mem: 9394 +Train: [7] [3500/6250] eta: 0:06:52 lr: 0.000125 grad: 0.0797 (0.0877) loss: 0.8630 (0.8671) time: 0.1387 data: 0.0587 max mem: 9394 +Train: [7] [3600/6250] eta: 0:06:37 lr: 0.000125 grad: 0.0794 (0.0875) loss: 0.8654 (0.8671) time: 0.1710 data: 0.0799 max mem: 9394 +Train: [7] [3700/6250] eta: 0:06:21 lr: 0.000125 grad: 0.0801 (0.0873) loss: 0.8615 (0.8670) time: 0.1370 data: 0.0568 max mem: 9394 +Train: [7] [3800/6250] eta: 0:06:06 lr: 0.000125 grad: 0.0771 (0.0871) loss: 0.8651 (0.8670) time: 0.1620 data: 0.0815 max mem: 9394 +Train: [7] [3900/6250] eta: 0:05:50 lr: 0.000125 grad: 0.0770 (0.0869) loss: 0.8622 (0.8669) time: 0.1391 data: 0.0632 max mem: 9394 +Train: [7] [4000/6250] eta: 0:05:36 lr: 0.000125 grad: 0.0775 (0.0867) loss: 0.8584 (0.8668) time: 0.1257 data: 0.0393 max mem: 9394 +Train: [7] [4100/6250] eta: 0:05:20 lr: 0.000125 grad: 0.0733 (0.0867) loss: 0.8644 (0.8667) time: 0.1343 data: 0.0541 max mem: 9394 +Train: [7] [4200/6250] eta: 0:05:05 lr: 0.000125 grad: 0.0748 (0.0864) loss: 0.8624 (0.8666) time: 0.1426 data: 0.0623 max mem: 9394 +Train: [7] [4300/6250] eta: 0:04:51 lr: 0.000125 grad: 0.0754 (0.0862) loss: 0.8635 (0.8665) time: 0.1476 data: 0.0661 max mem: 9394 +Train: [7] [4400/6250] eta: 0:04:35 lr: 0.000125 grad: 0.0771 (0.0861) loss: 0.8607 (0.8664) time: 0.1353 data: 0.0535 max mem: 9394 +Train: [7] [4500/6250] eta: 0:04:20 lr: 0.000125 grad: 0.0728 (0.0858) loss: 0.8663 (0.8664) time: 0.1352 data: 0.0522 max mem: 9394 +Train: [7] [4600/6250] eta: 0:04:05 lr: 0.000125 grad: 0.0861 (0.0858) loss: 0.8645 (0.8663) time: 0.2233 data: 0.1368 max mem: 9394 +Train: [7] [4700/6250] eta: 0:03:50 lr: 0.000125 grad: 0.0843 (0.0857) loss: 0.8602 (0.8662) time: 0.1407 data: 0.0593 max mem: 9394 +Train: [7] [4800/6250] eta: 0:03:34 lr: 0.000125 grad: 0.0823 (0.0856) loss: 0.8650 (0.8662) time: 0.1540 data: 0.0778 max mem: 9394 +Train: [7] [4900/6250] eta: 0:03:19 lr: 0.000125 grad: 0.0696 (0.0854) loss: 0.8608 (0.8661) time: 0.1365 data: 0.0582 max mem: 9394 +Train: [7] [5000/6250] eta: 0:03:04 lr: 0.000125 grad: 0.0727 (0.0852) loss: 0.8675 (0.8661) time: 0.1504 data: 0.0737 max mem: 9394 +Train: [7] [5100/6250] eta: 0:02:49 lr: 0.000125 grad: 0.0773 (0.0851) loss: 0.8646 (0.8660) time: 0.1279 data: 0.0465 max mem: 9394 +Train: [7] [5200/6250] eta: 0:02:34 lr: 0.000125 grad: 0.0731 (0.0850) loss: 0.8645 (0.8660) time: 0.1349 data: 0.0522 max mem: 9394 +Train: [7] [5300/6250] eta: 0:02:19 lr: 0.000125 grad: 0.0775 (0.0850) loss: 0.8647 (0.8660) time: 0.1467 data: 0.0632 max mem: 9394 +Train: [7] [5400/6250] eta: 0:02:04 lr: 0.000125 grad: 0.0729 (0.0848) loss: 0.8632 (0.8659) time: 0.1649 data: 0.0887 max mem: 9394 +Train: [7] [5500/6250] eta: 0:01:50 lr: 0.000125 grad: 0.0740 (0.0847) loss: 0.8646 (0.8659) time: 0.1442 data: 0.0551 max mem: 9394 +Train: [7] [5600/6250] eta: 0:01:35 lr: 0.000125 grad: 0.0817 (0.0846) loss: 0.8649 (0.8659) time: 0.1486 data: 0.0737 max mem: 9394 +Train: [7] [5700/6250] eta: 0:01:20 lr: 0.000125 grad: 0.0720 (0.0845) loss: 0.8588 (0.8659) time: 0.1687 data: 0.0899 max mem: 9394 +Train: [7] [5800/6250] eta: 0:01:05 lr: 0.000125 grad: 0.0855 (0.0845) loss: 0.8644 (0.8658) time: 0.1340 data: 0.0481 max mem: 9394 +Train: [7] [5900/6250] eta: 0:00:51 lr: 0.000125 grad: 0.0720 (0.0844) loss: 0.8603 (0.8657) time: 0.1207 data: 0.0429 max mem: 9394 +Train: [7] [6000/6250] eta: 0:00:36 lr: 0.000125 grad: 0.0728 (0.0843) loss: 0.8596 (0.8657) time: 0.1524 data: 0.0793 max mem: 9394 +Train: [7] [6100/6250] eta: 0:00:21 lr: 0.000125 grad: 0.0714 (0.0841) loss: 0.8658 (0.8656) time: 0.1712 data: 0.0893 max mem: 9394 +Train: [7] [6200/6250] eta: 0:00:07 lr: 0.000125 grad: 0.0765 (0.0840) loss: 0.8598 (0.8656) time: 0.1460 data: 0.0677 max mem: 9394 +Train: [7] [6249/6250] eta: 0:00:00 lr: 0.000125 grad: 0.0679 (0.0840) loss: 0.8578 (0.8655) time: 0.1469 data: 0.0509 max mem: 9394 +Train: [7] Total time: 0:15:20 (0.1473 s / it) +Averaged stats: lr: 0.000125 grad: 0.0679 (0.0840) loss: 0.8578 (0.8655) +Eval (hcp-train-subset): [7] [ 0/62] eta: 0:03:26 loss: 0.8752 (0.8752) time: 3.3260 data: 3.2715 max mem: 9394 +Eval (hcp-train-subset): [7] [61/62] eta: 0:00:00 loss: 0.8641 (0.8638) time: 0.1229 data: 0.0975 max mem: 9394 +Eval (hcp-train-subset): [7] Total time: 0:00:12 (0.2044 s / it) +Averaged stats (hcp-train-subset): loss: 0.8641 (0.8638) +Eval (hcp-val): [7] [ 0/62] eta: 0:04:41 loss: 0.8541 (0.8541) time: 4.5399 data: 4.4868 max mem: 9394 +Eval (hcp-val): [7] [61/62] eta: 0:00:00 loss: 0.8587 (0.8578) time: 0.1405 data: 0.1134 max mem: 9394 +Eval (hcp-val): [7] Total time: 0:00:13 (0.2225 s / it) +Averaged stats (hcp-val): loss: 0.8587 (0.8578) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +Train: [8] [ 0/6250] eta: 7:14:56 lr: 0.000125 grad: 0.0708 (0.0708) loss: 0.8789 (0.8789) time: 4.1754 data: 3.9680 max mem: 9394 +Train: [8] [ 100/6250] eta: 0:21:57 lr: 0.000125 grad: 0.0825 (0.0835) loss: 0.8643 (0.8691) time: 0.1759 data: 0.0793 max mem: 9394 +Train: [8] [ 200/6250] eta: 0:18:50 lr: 0.000125 grad: 0.0731 (0.0797) loss: 0.8627 (0.8669) time: 0.1582 data: 0.0726 max mem: 9394 +Train: [8] [ 300/6250] eta: 0:17:18 lr: 0.000125 grad: 0.0739 (0.0801) loss: 0.8623 (0.8666) time: 0.1372 data: 0.0604 max mem: 9394 +Train: [8] [ 400/6250] eta: 0:16:17 lr: 0.000125 grad: 0.0698 (0.0792) loss: 0.8640 (0.8656) time: 0.1365 data: 0.0535 max mem: 9394 +Train: [8] [ 500/6250] eta: 0:16:04 lr: 0.000125 grad: 0.0745 (0.0790) loss: 0.8628 (0.8647) time: 0.2069 data: 0.0882 max mem: 9394 +Train: [8] [ 600/6250] eta: 0:16:00 lr: 0.000125 grad: 0.0715 (0.0778) loss: 0.8579 (0.8642) time: 0.1323 data: 0.0217 max mem: 9394 +Train: [8] [ 700/6250] eta: 0:15:48 lr: 0.000125 grad: 0.0695 (0.0779) loss: 0.8570 (0.8636) time: 0.1630 data: 0.0777 max mem: 9394 +Train: [8] [ 800/6250] eta: 0:15:38 lr: 0.000125 grad: 0.0700 (0.0775) loss: 0.8586 (0.8631) time: 0.1816 data: 0.0913 max mem: 9394 +Train: [8] [ 900/6250] eta: 0:15:11 lr: 0.000125 grad: 0.0692 (0.0771) loss: 0.8552 (0.8626) time: 0.1428 data: 0.0600 max mem: 9394 +Train: [8] [1000/6250] eta: 0:14:38 lr: 0.000125 grad: 0.0724 (0.0779) loss: 0.8543 (0.8622) time: 0.1347 data: 0.0567 max mem: 9394 +Train: [8] [1100/6250] eta: 0:14:59 lr: 0.000125 grad: 0.0720 (0.0778) loss: 0.8620 (0.8619) time: 0.4149 data: 0.2534 max mem: 9394 +Train: [8] [1200/6250] eta: 0:14:20 lr: 0.000125 grad: 0.0750 (0.0785) loss: 0.8604 (0.8617) time: 0.1531 data: 0.0698 max mem: 9394 +Train: [8] [1300/6250] eta: 0:13:56 lr: 0.000125 grad: 0.0694 (0.0783) loss: 0.8574 (0.8614) time: 0.1499 data: 0.0590 max mem: 9394 +Train: [8] [1400/6250] eta: 0:13:32 lr: 0.000125 grad: 0.0700 (0.0782) loss: 0.8586 (0.8612) time: 0.1439 data: 0.0639 max mem: 9394 +Train: [8] [1500/6250] eta: 0:13:10 lr: 0.000125 grad: 0.0837 (0.0780) loss: 0.8553 (0.8610) time: 0.1730 data: 0.0855 max mem: 9394 +Train: [8] [1600/6250] eta: 0:12:49 lr: 0.000125 grad: 0.0735 (0.0781) loss: 0.8579 (0.8610) time: 0.1400 data: 0.0558 max mem: 9394 +Train: [8] [1700/6250] eta: 0:12:26 lr: 0.000125 grad: 0.0716 (0.0783) loss: 0.8554 (0.8608) time: 0.1438 data: 0.0618 max mem: 9394 +Train: [8] [1800/6250] eta: 0:12:03 lr: 0.000125 grad: 0.0742 (0.0780) loss: 0.8563 (0.8606) time: 0.1338 data: 0.0520 max mem: 9394 +Train: [8] [1900/6250] eta: 0:11:43 lr: 0.000125 grad: 0.0713 (0.0778) loss: 0.8570 (0.8605) time: 0.1507 data: 0.0679 max mem: 9394 +Train: [8] [2000/6250] eta: 0:11:20 lr: 0.000125 grad: 0.0716 (0.0775) loss: 0.8529 (0.8605) time: 0.1159 data: 0.0357 max mem: 9394 +Train: [8] [2100/6250] eta: 0:11:01 lr: 0.000125 grad: 0.0690 (0.0772) loss: 0.8628 (0.8604) time: 0.1755 data: 0.0909 max mem: 9394 +Train: [8] [2200/6250] eta: 0:10:40 lr: 0.000125 grad: 0.0712 (0.0770) loss: 0.8585 (0.8604) time: 0.1298 data: 0.0464 max mem: 9394 +Train: [8] [2300/6250] eta: 0:10:21 lr: 0.000125 grad: 0.0645 (0.0770) loss: 0.8636 (0.8604) time: 0.1644 data: 0.0784 max mem: 9394 +Train: [8] [2400/6250] eta: 0:10:02 lr: 0.000125 grad: 0.0680 (0.0769) loss: 0.8581 (0.8603) time: 0.1483 data: 0.0675 max mem: 9394 +Train: [8] [2500/6250] eta: 0:09:44 lr: 0.000125 grad: 0.0668 (0.0767) loss: 0.8628 (0.8603) time: 0.1137 data: 0.0265 max mem: 9394 +Train: [8] [2600/6250] eta: 0:09:25 lr: 0.000125 grad: 0.0661 (0.0768) loss: 0.8559 (0.8602) time: 0.1428 data: 0.0637 max mem: 9394 +Train: [8] [2700/6250] eta: 0:09:07 lr: 0.000125 grad: 0.0780 (0.0768) loss: 0.8599 (0.8602) time: 0.1443 data: 0.0652 max mem: 9394 +Train: [8] [2800/6250] eta: 0:08:50 lr: 0.000125 grad: 0.0730 (0.0767) loss: 0.8514 (0.8601) time: 0.1282 data: 0.0435 max mem: 9394 +Train: [8] [2900/6250] eta: 0:08:35 lr: 0.000125 grad: 0.0719 (0.0769) loss: 0.8580 (0.8600) time: 0.1839 data: 0.1093 max mem: 9394 +Train: [8] [3000/6250] eta: 0:08:17 lr: 0.000125 grad: 0.0718 (0.0768) loss: 0.8569 (0.8599) time: 0.1352 data: 0.0554 max mem: 9394 +Train: [8] [3100/6250] eta: 0:08:01 lr: 0.000125 grad: 0.0656 (0.0767) loss: 0.8605 (0.8599) time: 0.1501 data: 0.0700 max mem: 9394 +Train: [8] [3200/6250] eta: 0:07:44 lr: 0.000125 grad: 0.0747 (0.0767) loss: 0.8602 (0.8599) time: 0.1454 data: 0.0691 max mem: 9394 +Train: [8] [3300/6250] eta: 0:07:28 lr: 0.000125 grad: 0.0702 (0.0766) loss: 0.8599 (0.8598) time: 0.1628 data: 0.0709 max mem: 9394 +Train: [8] [3400/6250] eta: 0:07:12 lr: 0.000125 grad: 0.0691 (0.0765) loss: 0.8581 (0.8598) time: 0.1391 data: 0.0568 max mem: 9394 +Train: [8] [3500/6250] eta: 0:06:56 lr: 0.000125 grad: 0.0713 (0.0764) loss: 0.8582 (0.8598) time: 0.1395 data: 0.0510 max mem: 9394 +Train: [8] [3600/6250] eta: 0:06:40 lr: 0.000125 grad: 0.0758 (0.0763) loss: 0.8606 (0.8597) time: 0.1285 data: 0.0451 max mem: 9394 +Train: [8] [3700/6250] eta: 0:06:24 lr: 0.000125 grad: 0.0684 (0.0762) loss: 0.8577 (0.8597) time: 0.1339 data: 0.0493 max mem: 9394 +Train: [8] [3800/6250] eta: 0:06:08 lr: 0.000125 grad: 0.0670 (0.0760) loss: 0.8579 (0.8597) time: 0.1358 data: 0.0553 max mem: 9394 +Train: [8] [3900/6250] eta: 0:05:52 lr: 0.000125 grad: 0.0772 (0.0760) loss: 0.8517 (0.8596) time: 0.1360 data: 0.0554 max mem: 9394 +Train: [8] [4000/6250] eta: 0:05:37 lr: 0.000125 grad: 0.0675 (0.0760) loss: 0.8573 (0.8596) time: 0.1671 data: 0.0848 max mem: 9394 +Train: [8] [4100/6250] eta: 0:05:21 lr: 0.000125 grad: 0.0688 (0.0759) loss: 0.8564 (0.8595) time: 0.1243 data: 0.0449 max mem: 9394 +Train: [8] [4200/6250] eta: 0:05:06 lr: 0.000125 grad: 0.0675 (0.0758) loss: 0.8535 (0.8594) time: 0.1321 data: 0.0545 max mem: 9394 +Train: [8] [4300/6250] eta: 0:04:51 lr: 0.000125 grad: 0.0664 (0.0757) loss: 0.8559 (0.8594) time: 0.1244 data: 0.0444 max mem: 9394 +Train: [8] [4400/6250] eta: 0:04:35 lr: 0.000125 grad: 0.0696 (0.0756) loss: 0.8601 (0.8594) time: 0.1614 data: 0.0777 max mem: 9394 +Train: [8] [4500/6250] eta: 0:04:20 lr: 0.000125 grad: 0.0677 (0.0755) loss: 0.8544 (0.8593) time: 0.1368 data: 0.0553 max mem: 9394 +Train: [8] [4600/6250] eta: 0:04:05 lr: 0.000125 grad: 0.0756 (0.0754) loss: 0.8596 (0.8593) time: 0.1467 data: 0.0643 max mem: 9394 +Train: [8] [4700/6250] eta: 0:03:50 lr: 0.000125 grad: 0.0644 (0.0753) loss: 0.8566 (0.8593) time: 0.1792 data: 0.0518 max mem: 9394 +Train: [8] [4800/6250] eta: 0:03:35 lr: 0.000125 grad: 0.0707 (0.0752) loss: 0.8588 (0.8593) time: 0.1305 data: 0.0451 max mem: 9394 +Train: [8] [4900/6250] eta: 0:03:20 lr: 0.000125 grad: 0.0688 (0.0751) loss: 0.8547 (0.8593) time: 0.1439 data: 0.0676 max mem: 9394 +Train: [8] [5000/6250] eta: 0:03:05 lr: 0.000125 grad: 0.0662 (0.0750) loss: 0.8555 (0.8592) time: 0.1201 data: 0.0371 max mem: 9394 +Train: [8] [5100/6250] eta: 0:02:50 lr: 0.000125 grad: 0.0666 (0.0749) loss: 0.8585 (0.8592) time: 0.1354 data: 0.0531 max mem: 9394 +Train: [8] [5200/6250] eta: 0:02:35 lr: 0.000124 grad: 0.0664 (0.0749) loss: 0.8598 (0.8592) time: 0.1237 data: 0.0410 max mem: 9394 +Train: [8] [5300/6250] eta: 0:02:20 lr: 0.000124 grad: 0.0670 (0.0748) loss: 0.8574 (0.8591) time: 0.1460 data: 0.0593 max mem: 9394 +Train: [8] [5400/6250] eta: 0:02:05 lr: 0.000124 grad: 0.0704 (0.0747) loss: 0.8544 (0.8591) time: 0.1298 data: 0.0516 max mem: 9394 +Train: [8] [5500/6250] eta: 0:01:50 lr: 0.000124 grad: 0.0754 (0.0747) loss: 0.8556 (0.8590) time: 0.1167 data: 0.0350 max mem: 9394 +Train: [8] [5600/6250] eta: 0:01:35 lr: 0.000124 grad: 0.0692 (0.0747) loss: 0.8578 (0.8590) time: 0.1585 data: 0.0770 max mem: 9394 +Train: [8] [5700/6250] eta: 0:01:20 lr: 0.000124 grad: 0.0648 (0.0748) loss: 0.8500 (0.8589) time: 0.1184 data: 0.0387 max mem: 9394 +Train: [8] [5800/6250] eta: 0:01:06 lr: 0.000124 grad: 0.0674 (0.0748) loss: 0.8553 (0.8588) time: 0.1511 data: 0.0717 max mem: 9394 +Train: [8] [5900/6250] eta: 0:00:51 lr: 0.000124 grad: 0.0634 (0.0747) loss: 0.8583 (0.8588) time: 0.1442 data: 0.0582 max mem: 9394 +Train: [8] [6000/6250] eta: 0:00:36 lr: 0.000124 grad: 0.0714 (0.0746) loss: 0.8553 (0.8587) time: 0.1602 data: 0.0854 max mem: 9394 +Train: [8] [6100/6250] eta: 0:00:22 lr: 0.000124 grad: 0.0674 (0.0746) loss: 0.8550 (0.8587) time: 0.1522 data: 0.0683 max mem: 9394 +Train: [8] [6200/6250] eta: 0:00:07 lr: 0.000124 grad: 0.0614 (0.0745) loss: 0.8592 (0.8586) time: 0.1582 data: 0.0704 max mem: 9394 +Train: [8] [6249/6250] eta: 0:00:00 lr: 0.000124 grad: 0.0656 (0.0745) loss: 0.8580 (0.8586) time: 0.1924 data: 0.1046 max mem: 9394 +Train: [8] Total time: 0:15:30 (0.1488 s / it) +Averaged stats: lr: 0.000124 grad: 0.0656 (0.0745) loss: 0.8580 (0.8586) +Eval (hcp-train-subset): [8] [ 0/62] eta: 0:05:30 loss: 0.8684 (0.8684) time: 5.3351 data: 5.3064 max mem: 9394 +Eval (hcp-train-subset): [8] [61/62] eta: 0:00:00 loss: 0.8614 (0.8596) time: 0.1213 data: 0.0963 max mem: 9394 +Eval (hcp-train-subset): [8] Total time: 0:00:13 (0.2187 s / it) +Averaged stats (hcp-train-subset): loss: 0.8614 (0.8596) +Eval (hcp-val): [8] [ 0/62] eta: 0:06:00 loss: 0.8519 (0.8519) time: 5.8073 data: 5.7787 max mem: 9394 +Eval (hcp-val): [8] [61/62] eta: 0:00:00 loss: 0.8545 (0.8544) time: 0.1285 data: 0.1012 max mem: 9394 +Eval (hcp-val): [8] Total time: 0:00:13 (0.2179 s / it) +Averaged stats (hcp-val): loss: 0.8545 (0.8544) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +Train: [9] [ 0/6250] eta: 7:54:34 lr: 0.000124 grad: 0.1165 (0.1165) loss: 0.8729 (0.8729) time: 4.5559 data: 4.2981 max mem: 9394 +Train: [9] [ 100/6250] eta: 0:21:33 lr: 0.000124 grad: 0.0715 (0.0841) loss: 0.8591 (0.8608) time: 0.1667 data: 0.0769 max mem: 9394 +Train: [9] [ 200/6250] eta: 0:17:53 lr: 0.000124 grad: 0.0725 (0.0794) loss: 0.8514 (0.8557) time: 0.1358 data: 0.0441 max mem: 9394 +Train: [9] [ 300/6250] eta: 0:16:43 lr: 0.000124 grad: 0.0730 (0.0793) loss: 0.8544 (0.8542) time: 0.1651 data: 0.0774 max mem: 9394 +Train: [9] [ 400/6250] eta: 0:15:56 lr: 0.000124 grad: 0.0693 (0.0778) loss: 0.8536 (0.8535) time: 0.1622 data: 0.0743 max mem: 9394 +Train: [9] [ 500/6250] eta: 0:15:43 lr: 0.000124 grad: 0.0690 (0.0775) loss: 0.8511 (0.8534) time: 0.1952 data: 0.0893 max mem: 9394 +Train: [9] [ 600/6250] eta: 0:15:39 lr: 0.000124 grad: 0.0740 (0.0771) loss: 0.8557 (0.8538) time: 0.1706 data: 0.0666 max mem: 9394 +Train: [9] [ 700/6250] eta: 0:15:34 lr: 0.000124 grad: 0.0681 (0.0765) loss: 0.8548 (0.8542) time: 0.2311 data: 0.1060 max mem: 9394 +Train: [9] [ 800/6250] eta: 0:15:08 lr: 0.000124 grad: 0.0674 (0.0758) loss: 0.8580 (0.8544) time: 0.1594 data: 0.0768 max mem: 9394 +Train: [9] [ 900/6250] eta: 0:15:04 lr: 0.000124 grad: 0.0754 (0.0750) loss: 0.8529 (0.8544) time: 0.2825 data: 0.1828 max mem: 9394 +Train: [9] [1000/6250] eta: 0:14:46 lr: 0.000124 grad: 0.0717 (0.0747) loss: 0.8473 (0.8542) time: 0.1229 data: 0.0199 max mem: 9394 +Train: [9] [1100/6250] eta: 0:14:16 lr: 0.000124 grad: 0.0660 (0.0742) loss: 0.8522 (0.8541) time: 0.1511 data: 0.0744 max mem: 9394 +Train: [9] [1200/6250] eta: 0:13:46 lr: 0.000124 grad: 0.0665 (0.0742) loss: 0.8569 (0.8541) time: 0.1393 data: 0.0442 max mem: 9394 +Train: [9] [1300/6250] eta: 0:13:26 lr: 0.000124 grad: 0.0706 (0.0742) loss: 0.8512 (0.8541) time: 0.1433 data: 0.0646 max mem: 9394 +Train: [9] [1400/6250] eta: 0:13:15 lr: 0.000124 grad: 0.0672 (0.0739) loss: 0.8540 (0.8541) time: 0.1582 data: 0.0725 max mem: 9394 +Train: [9] [1500/6250] eta: 0:12:50 lr: 0.000124 grad: 0.0627 (0.0742) loss: 0.8580 (0.8541) time: 0.1431 data: 0.0579 max mem: 9394 +Train: [9] [1600/6250] eta: 0:12:27 lr: 0.000124 grad: 0.0728 (0.0742) loss: 0.8567 (0.8540) time: 0.1286 data: 0.0423 max mem: 9394 +Train: [9] [1700/6250] eta: 0:12:08 lr: 0.000124 grad: 0.0823 (0.0745) loss: 0.8509 (0.8541) time: 0.1231 data: 0.0432 max mem: 9394 +Train: [9] [1800/6250] eta: 0:11:48 lr: 0.000124 grad: 0.0681 (0.0745) loss: 0.8544 (0.8541) time: 0.1477 data: 0.0636 max mem: 9394 +Train: [9] [1900/6250] eta: 0:11:29 lr: 0.000124 grad: 0.0662 (0.0743) loss: 0.8545 (0.8541) time: 0.1305 data: 0.0494 max mem: 9394 +Train: [9] [2000/6250] eta: 0:11:13 lr: 0.000124 grad: 0.0680 (0.0741) loss: 0.8499 (0.8540) time: 0.1664 data: 0.0851 max mem: 9394 +Train: [9] [2100/6250] eta: 0:10:54 lr: 0.000124 grad: 0.0748 (0.0740) loss: 0.8558 (0.8539) time: 0.1406 data: 0.0641 max mem: 9394 +Train: [9] [2200/6250] eta: 0:10:36 lr: 0.000124 grad: 0.0667 (0.0738) loss: 0.8481 (0.8539) time: 0.1540 data: 0.0739 max mem: 9394 +Train: [9] [2300/6250] eta: 0:10:18 lr: 0.000124 grad: 0.0686 (0.0737) loss: 0.8545 (0.8539) time: 0.1458 data: 0.0579 max mem: 9394 +Train: [9] [2400/6250] eta: 0:10:01 lr: 0.000124 grad: 0.0649 (0.0734) loss: 0.8503 (0.8539) time: 0.1396 data: 0.0618 max mem: 9394 +Train: [9] [2500/6250] eta: 0:09:43 lr: 0.000124 grad: 0.0674 (0.0733) loss: 0.8510 (0.8539) time: 0.1421 data: 0.0608 max mem: 9394 +Train: [9] [2600/6250] eta: 0:09:25 lr: 0.000124 grad: 0.0659 (0.0732) loss: 0.8559 (0.8539) time: 0.1514 data: 0.0715 max mem: 9394 +Train: [9] [2700/6250] eta: 0:09:09 lr: 0.000124 grad: 0.0698 (0.0730) loss: 0.8518 (0.8540) time: 0.2083 data: 0.1256 max mem: 9394 +Train: [9] [2800/6250] eta: 0:08:50 lr: 0.000124 grad: 0.0655 (0.0729) loss: 0.8564 (0.8540) time: 0.1463 data: 0.0642 max mem: 9394 +Train: [9] [2900/6250] eta: 0:08:32 lr: 0.000124 grad: 0.0667 (0.0728) loss: 0.8553 (0.8541) time: 0.1310 data: 0.0495 max mem: 9394 +Train: [9] [3000/6250] eta: 0:08:15 lr: 0.000124 grad: 0.0689 (0.0726) loss: 0.8548 (0.8542) time: 0.1364 data: 0.0604 max mem: 9394 +Train: [9] [3100/6250] eta: 0:07:59 lr: 0.000124 grad: 0.0635 (0.0724) loss: 0.8519 (0.8542) time: 0.1284 data: 0.0460 max mem: 9394 +Train: [9] [3200/6250] eta: 0:07:42 lr: 0.000124 grad: 0.0627 (0.0723) loss: 0.8545 (0.8542) time: 0.1262 data: 0.0442 max mem: 9394 +Train: [9] [3300/6250] eta: 0:07:26 lr: 0.000124 grad: 0.0639 (0.0721) loss: 0.8523 (0.8542) time: 0.1286 data: 0.0499 max mem: 9394 +Train: [9] [3400/6250] eta: 0:07:10 lr: 0.000124 grad: 0.0688 (0.0721) loss: 0.8546 (0.8542) time: 0.1365 data: 0.0598 max mem: 9394 +Train: [9] [3500/6250] eta: 0:06:54 lr: 0.000124 grad: 0.0664 (0.0720) loss: 0.8579 (0.8542) time: 0.1356 data: 0.0629 max mem: 9394 +Train: [9] [3600/6250] eta: 0:06:39 lr: 0.000124 grad: 0.0650 (0.0718) loss: 0.8530 (0.8542) time: 0.1298 data: 0.0450 max mem: 9394 +Train: [9] [3700/6250] eta: 0:06:26 lr: 0.000124 grad: 0.0691 (0.0718) loss: 0.8498 (0.8542) time: 0.2121 data: 0.1216 max mem: 9394 +Train: [9] [3800/6250] eta: 0:06:09 lr: 0.000124 grad: 0.0677 (0.0717) loss: 0.8520 (0.8542) time: 0.1522 data: 0.0705 max mem: 9394 +Train: [9] [3900/6250] eta: 0:05:54 lr: 0.000124 grad: 0.0711 (0.0717) loss: 0.8505 (0.8541) time: 0.1495 data: 0.0708 max mem: 9394 +Train: [9] [4000/6250] eta: 0:05:38 lr: 0.000124 grad: 0.0691 (0.0716) loss: 0.8515 (0.8540) time: 0.1294 data: 0.0480 max mem: 9394 +Train: [9] [4100/6250] eta: 0:05:22 lr: 0.000124 grad: 0.0680 (0.0716) loss: 0.8562 (0.8539) time: 0.1360 data: 0.0566 max mem: 9394 +Train: [9] [4200/6250] eta: 0:05:07 lr: 0.000124 grad: 0.0676 (0.0715) loss: 0.8482 (0.8539) time: 0.1354 data: 0.0544 max mem: 9394 +Train: [9] [4300/6250] eta: 0:04:51 lr: 0.000124 grad: 0.0683 (0.0715) loss: 0.8505 (0.8538) time: 0.1406 data: 0.0633 max mem: 9394 +Train: [9] [4400/6250] eta: 0:04:36 lr: 0.000124 grad: 0.0684 (0.0714) loss: 0.8512 (0.8538) time: 0.1356 data: 0.0591 max mem: 9394 +Train: [9] [4500/6250] eta: 0:04:20 lr: 0.000124 grad: 0.0628 (0.0713) loss: 0.8531 (0.8537) time: 0.1229 data: 0.0425 max mem: 9394 +Train: [9] [4600/6250] eta: 0:04:05 lr: 0.000124 grad: 0.0680 (0.0713) loss: 0.8530 (0.8538) time: 0.1394 data: 0.0560 max mem: 9394 +Train: [9] [4700/6250] eta: 0:03:50 lr: 0.000124 grad: 0.0715 (0.0712) loss: 0.8546 (0.8537) time: 0.1504 data: 0.0716 max mem: 9394 +Train: [9] [4800/6250] eta: 0:03:35 lr: 0.000124 grad: 0.0658 (0.0713) loss: 0.8517 (0.8537) time: 0.1333 data: 0.0520 max mem: 9394 +Train: [9] [4900/6250] eta: 0:03:20 lr: 0.000124 grad: 0.0618 (0.0713) loss: 0.8558 (0.8537) time: 0.1338 data: 0.0566 max mem: 9394 +Train: [9] [5000/6250] eta: 0:03:05 lr: 0.000124 grad: 0.0658 (0.0712) loss: 0.8518 (0.8537) time: 0.1286 data: 0.0438 max mem: 9394 +Train: [9] [5100/6250] eta: 0:02:50 lr: 0.000124 grad: 0.0863 (0.0714) loss: 0.8518 (0.8536) time: 0.1298 data: 0.0509 max mem: 9394 +Train: [9] [5200/6250] eta: 0:02:35 lr: 0.000124 grad: 0.0665 (0.0714) loss: 0.8511 (0.8536) time: 0.1934 data: 0.1034 max mem: 9394 +Train: [9] [5300/6250] eta: 0:02:20 lr: 0.000124 grad: 0.0705 (0.0713) loss: 0.8500 (0.8536) time: 0.1293 data: 0.0531 max mem: 9394 +Train: [9] [5400/6250] eta: 0:02:05 lr: 0.000124 grad: 0.0668 (0.0713) loss: 0.8481 (0.8535) time: 0.1438 data: 0.0609 max mem: 9394 +Train: [9] [5500/6250] eta: 0:01:50 lr: 0.000124 grad: 0.0648 (0.0712) loss: 0.8568 (0.8535) time: 0.1731 data: 0.0958 max mem: 9394 +Train: [9] [5600/6250] eta: 0:01:35 lr: 0.000124 grad: 0.0657 (0.0712) loss: 0.8504 (0.8534) time: 0.1292 data: 0.0469 max mem: 9394 +Train: [9] [5700/6250] eta: 0:01:21 lr: 0.000124 grad: 0.0649 (0.0711) loss: 0.8507 (0.8533) time: 0.1261 data: 0.0440 max mem: 9394 +Train: [9] [5800/6250] eta: 0:01:06 lr: 0.000124 grad: 0.0648 (0.0711) loss: 0.8537 (0.8533) time: 0.1223 data: 0.0390 max mem: 9394 +Train: [9] [5900/6250] eta: 0:00:51 lr: 0.000124 grad: 0.0676 (0.0710) loss: 0.8524 (0.8532) time: 0.1422 data: 0.0576 max mem: 9394 +Train: [9] [6000/6250] eta: 0:00:36 lr: 0.000124 grad: 0.0722 (0.0710) loss: 0.8495 (0.8532) time: 0.1557 data: 0.0738 max mem: 9394 +Train: [9] [6100/6250] eta: 0:00:22 lr: 0.000124 grad: 0.0700 (0.0710) loss: 0.8516 (0.8531) time: 0.1877 data: 0.0996 max mem: 9394 +Train: [9] [6200/6250] eta: 0:00:07 lr: 0.000124 grad: 0.0678 (0.0710) loss: 0.8466 (0.8531) time: 0.2017 data: 0.1214 max mem: 9394 +Train: [9] [6249/6250] eta: 0:00:00 lr: 0.000124 grad: 0.0662 (0.0710) loss: 0.8484 (0.8531) time: 0.1752 data: 0.0874 max mem: 9394 +Train: [9] Total time: 0:15:32 (0.1492 s / it) +Averaged stats: lr: 0.000124 grad: 0.0662 (0.0710) loss: 0.8484 (0.8531) +Eval (hcp-train-subset): [9] [ 0/62] eta: 0:04:39 loss: 0.8646 (0.8646) time: 4.5094 data: 4.4304 max mem: 9394 +Eval (hcp-train-subset): [9] [61/62] eta: 0:00:00 loss: 0.8561 (0.8563) time: 0.1367 data: 0.1109 max mem: 9394 +Eval (hcp-train-subset): [9] Total time: 0:00:13 (0.2251 s / it) +Averaged stats (hcp-train-subset): loss: 0.8561 (0.8563) +Making plots (hcp-train-subset): example=29 +Eval (hcp-val): [9] [ 0/62] eta: 0:04:39 loss: 0.8465 (0.8465) time: 4.5147 data: 4.4855 max mem: 9394 +Eval (hcp-val): [9] [61/62] eta: 0:00:00 loss: 0.8505 (0.8510) time: 0.1261 data: 0.1011 max mem: 9394 +Eval (hcp-val): [9] Total time: 0:00:12 (0.2095 s / it) +Averaged stats (hcp-val): loss: 0.8505 (0.8510) +Making plots (hcp-val): example=14 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +Train: [10] [ 0/6250] eta: 10:38:04 lr: 0.000124 grad: 0.0686 (0.0686) loss: 0.8448 (0.8448) time: 6.1256 data: 6.0393 max mem: 9394 +Train: [10] [ 100/6250] eta: 0:20:33 lr: 0.000124 grad: 0.0740 (0.0836) loss: 0.8486 (0.8525) time: 0.1621 data: 0.0763 max mem: 9394 +Train: [10] [ 200/6250] eta: 0:17:21 lr: 0.000124 grad: 0.0693 (0.0810) loss: 0.8566 (0.8509) time: 0.1459 data: 0.0640 max mem: 9394 +Train: [10] [ 300/6250] eta: 0:16:20 lr: 0.000124 grad: 0.0652 (0.0762) loss: 0.8445 (0.8505) time: 0.1403 data: 0.0579 max mem: 9394 +Train: [10] [ 400/6250] eta: 0:15:52 lr: 0.000124 grad: 0.0624 (0.0738) loss: 0.8530 (0.8506) time: 0.1822 data: 0.1010 max mem: 9394 +Train: [10] [ 500/6250] eta: 0:16:15 lr: 0.000124 grad: 0.0647 (0.0725) loss: 0.8504 (0.8505) time: 0.2514 data: 0.1631 max mem: 9394 +Train: [10] [ 600/6250] eta: 0:15:53 lr: 0.000124 grad: 0.0654 (0.0715) loss: 0.8532 (0.8505) time: 0.1235 data: 0.0004 max mem: 9394 +Train: [10] [ 700/6250] eta: 0:16:21 lr: 0.000124 grad: 0.0651 (0.0708) loss: 0.8499 (0.8506) time: 0.2079 data: 0.1273 max mem: 9394 +Train: [10] [ 800/6250] eta: 0:15:47 lr: 0.000124 grad: 0.0703 (0.0704) loss: 0.8575 (0.8509) time: 0.1287 data: 0.0399 max mem: 9394 +Train: [10] [ 900/6250] eta: 0:15:54 lr: 0.000124 grad: 0.0640 (0.0701) loss: 0.8524 (0.8509) time: 0.3448 data: 0.2221 max mem: 9394 +Train: [10] [1000/6250] eta: 0:15:15 lr: 0.000124 grad: 0.0665 (0.0700) loss: 0.8491 (0.8509) time: 0.1574 data: 0.0725 max mem: 9394 +Train: [10] [1100/6250] eta: 0:14:49 lr: 0.000124 grad: 0.0638 (0.0698) loss: 0.8479 (0.8507) time: 0.1708 data: 0.0734 max mem: 9394 +Train: [10] [1200/6250] eta: 0:14:40 lr: 0.000124 grad: 0.0639 (0.0697) loss: 0.8521 (0.8507) time: 0.2897 data: 0.1923 max mem: 9394 +Train: [10] [1300/6250] eta: 0:14:07 lr: 0.000124 grad: 0.0711 (0.0698) loss: 0.8522 (0.8506) time: 0.1622 data: 0.0703 max mem: 9394 +Train: [10] [1400/6250] eta: 0:13:53 lr: 0.000124 grad: 0.0796 (0.0703) loss: 0.8473 (0.8505) time: 0.1768 data: 0.0908 max mem: 9394 +Train: [10] [1500/6250] eta: 0:13:34 lr: 0.000124 grad: 0.0635 (0.0701) loss: 0.8499 (0.8505) time: 0.2570 data: 0.1650 max mem: 9394 +Train: [10] [1600/6250] eta: 0:13:11 lr: 0.000124 grad: 0.0625 (0.0699) loss: 0.8521 (0.8505) time: 0.1336 data: 0.0460 max mem: 9394 +Train: [10] [1700/6250] eta: 0:12:47 lr: 0.000124 grad: 0.0721 (0.0700) loss: 0.8504 (0.8505) time: 0.1515 data: 0.0644 max mem: 9394 +Train: [10] [1800/6250] eta: 0:12:40 lr: 0.000124 grad: 0.0639 (0.0703) loss: 0.8491 (0.8504) time: 0.1091 data: 0.0229 max mem: 9394 +Train: [10] [1900/6250] eta: 0:12:16 lr: 0.000124 grad: 0.0641 (0.0701) loss: 0.8523 (0.8505) time: 0.1387 data: 0.0599 max mem: 9394 +Train: [10] [2000/6250] eta: 0:12:03 lr: 0.000124 grad: 0.0728 (0.0703) loss: 0.8477 (0.8504) time: 0.3528 data: 0.2466 max mem: 9394 +Train: [10] [2100/6250] eta: 0:11:37 lr: 0.000124 grad: 0.0665 (0.0702) loss: 0.8491 (0.8504) time: 0.1593 data: 0.0748 max mem: 9394 +Train: [10] [2200/6250] eta: 0:11:15 lr: 0.000124 grad: 0.0676 (0.0703) loss: 0.8433 (0.8503) time: 0.1457 data: 0.0676 max mem: 9394 +Train: [10] [2300/6250] eta: 0:10:55 lr: 0.000124 grad: 0.0667 (0.0701) loss: 0.8506 (0.8502) time: 0.1655 data: 0.0849 max mem: 9394 +Train: [10] [2400/6250] eta: 0:10:34 lr: 0.000124 grad: 0.0643 (0.0701) loss: 0.8501 (0.8502) time: 0.1557 data: 0.0697 max mem: 9394 +Train: [10] [2500/6250] eta: 0:10:17 lr: 0.000124 grad: 0.0641 (0.0701) loss: 0.8500 (0.8501) time: 0.1281 data: 0.0491 max mem: 9394 +Train: [10] [2600/6250] eta: 0:09:56 lr: 0.000124 grad: 0.0681 (0.0700) loss: 0.8453 (0.8499) time: 0.1236 data: 0.0391 max mem: 9394 +Train: [10] [2700/6250] eta: 0:09:37 lr: 0.000124 grad: 0.0628 (0.0700) loss: 0.8531 (0.8499) time: 0.1481 data: 0.0676 max mem: 9394 +Train: [10] [2800/6250] eta: 0:09:17 lr: 0.000124 grad: 0.0693 (0.0701) loss: 0.8488 (0.8499) time: 0.1217 data: 0.0441 max mem: 9394 +Train: [10] [2900/6250] eta: 0:08:59 lr: 0.000124 grad: 0.0673 (0.0701) loss: 0.8490 (0.8498) time: 0.1546 data: 0.0734 max mem: 9394 +Train: [10] [3000/6250] eta: 0:08:41 lr: 0.000124 grad: 0.0658 (0.0701) loss: 0.8479 (0.8497) time: 0.1511 data: 0.0739 max mem: 9394 +Train: [10] [3100/6250] eta: 0:08:22 lr: 0.000124 grad: 0.0652 (0.0703) loss: 0.8444 (0.8496) time: 0.1444 data: 0.0654 max mem: 9394 +Train: [10] [3200/6250] eta: 0:08:04 lr: 0.000124 grad: 0.0708 (0.0703) loss: 0.8446 (0.8495) time: 0.1711 data: 0.0941 max mem: 9394 +Train: [10] [3300/6250] eta: 0:07:46 lr: 0.000124 grad: 0.0643 (0.0702) loss: 0.8473 (0.8494) time: 0.1551 data: 0.0760 max mem: 9394 +Train: [10] [3400/6250] eta: 0:07:29 lr: 0.000124 grad: 0.0649 (0.0701) loss: 0.8549 (0.8493) time: 0.1112 data: 0.0341 max mem: 9394 +Train: [10] [3500/6250] eta: 0:07:12 lr: 0.000124 grad: 0.0634 (0.0699) loss: 0.8511 (0.8493) time: 0.1324 data: 0.0476 max mem: 9394 +Train: [10] [3600/6250] eta: 0:06:55 lr: 0.000124 grad: 0.0619 (0.0698) loss: 0.8497 (0.8493) time: 0.1671 data: 0.0888 max mem: 9394 +Train: [10] [3700/6250] eta: 0:06:38 lr: 0.000124 grad: 0.0652 (0.0697) loss: 0.8447 (0.8492) time: 0.1482 data: 0.0692 max mem: 9394 +Train: [10] [3800/6250] eta: 0:06:22 lr: 0.000124 grad: 0.0687 (0.0697) loss: 0.8480 (0.8492) time: 0.1063 data: 0.0253 max mem: 9394 +Train: [10] [3900/6250] eta: 0:06:05 lr: 0.000124 grad: 0.0662 (0.0696) loss: 0.8439 (0.8492) time: 0.1362 data: 0.0575 max mem: 9394 +Train: [10] [4000/6250] eta: 0:05:49 lr: 0.000124 grad: 0.0633 (0.0696) loss: 0.8505 (0.8492) time: 0.1414 data: 0.0623 max mem: 9394 +Train: [10] [4100/6250] eta: 0:05:32 lr: 0.000124 grad: 0.0628 (0.0695) loss: 0.8484 (0.8492) time: 0.1220 data: 0.0361 max mem: 9394 +Train: [10] [4200/6250] eta: 0:05:18 lr: 0.000124 grad: 0.0668 (0.0694) loss: 0.8423 (0.8492) time: 0.1329 data: 0.0488 max mem: 9394 +Train: [10] [4300/6250] eta: 0:05:01 lr: 0.000124 grad: 0.0684 (0.0694) loss: 0.8456 (0.8491) time: 0.1537 data: 0.0765 max mem: 9394 +Train: [10] [4400/6250] eta: 0:04:45 lr: 0.000124 grad: 0.0658 (0.0693) loss: 0.8455 (0.8491) time: 0.1430 data: 0.0638 max mem: 9394 +Train: [10] [4500/6250] eta: 0:04:29 lr: 0.000124 grad: 0.0630 (0.0692) loss: 0.8481 (0.8491) time: 0.1308 data: 0.0525 max mem: 9394 +Train: [10] [4600/6250] eta: 0:04:13 lr: 0.000124 grad: 0.0638 (0.0691) loss: 0.8488 (0.8491) time: 0.1163 data: 0.0373 max mem: 9394 +Train: [10] [4700/6250] eta: 0:03:57 lr: 0.000124 grad: 0.0599 (0.0691) loss: 0.8487 (0.8490) time: 0.1226 data: 0.0375 max mem: 9394 +Train: [10] [4800/6250] eta: 0:03:42 lr: 0.000124 grad: 0.0648 (0.0690) loss: 0.8485 (0.8490) time: 0.1417 data: 0.0631 max mem: 9394 +Train: [10] [4900/6250] eta: 0:03:26 lr: 0.000124 grad: 0.0660 (0.0690) loss: 0.8497 (0.8490) time: 0.0883 data: 0.0002 max mem: 9394 +Train: [10] [5000/6250] eta: 0:03:11 lr: 0.000124 grad: 0.0628 (0.0690) loss: 0.8517 (0.8490) time: 0.1512 data: 0.0688 max mem: 9394 +Train: [10] [5100/6250] eta: 0:02:55 lr: 0.000124 grad: 0.0644 (0.0690) loss: 0.8466 (0.8490) time: 0.1341 data: 0.0490 max mem: 9394 +Train: [10] [5200/6250] eta: 0:02:40 lr: 0.000124 grad: 0.0609 (0.0690) loss: 0.8454 (0.8489) time: 0.1466 data: 0.0659 max mem: 9394 +Train: [10] [5300/6250] eta: 0:02:24 lr: 0.000124 grad: 0.0646 (0.0689) loss: 0.8473 (0.8489) time: 0.1603 data: 0.0778 max mem: 9394 +Train: [10] [5400/6250] eta: 0:02:09 lr: 0.000124 grad: 0.0653 (0.0689) loss: 0.8509 (0.8490) time: 0.1366 data: 0.0569 max mem: 9394 +Train: [10] [5500/6250] eta: 0:01:54 lr: 0.000124 grad: 0.0663 (0.0689) loss: 0.8481 (0.8490) time: 0.1219 data: 0.0407 max mem: 9394 +Train: [10] [5600/6250] eta: 0:01:38 lr: 0.000124 grad: 0.0655 (0.0689) loss: 0.8531 (0.8490) time: 0.1167 data: 0.0368 max mem: 9394 +Train: [10] [5700/6250] eta: 0:01:23 lr: 0.000124 grad: 0.0701 (0.0689) loss: 0.8504 (0.8490) time: 0.1247 data: 0.0452 max mem: 9394 +Train: [10] [5800/6250] eta: 0:01:08 lr: 0.000124 grad: 0.0748 (0.0690) loss: 0.8498 (0.8490) time: 0.1447 data: 0.0673 max mem: 9394 +Train: [10] [5900/6250] eta: 0:00:53 lr: 0.000124 grad: 0.0640 (0.0690) loss: 0.8510 (0.8491) time: 0.1735 data: 0.0901 max mem: 9394 +Train: [10] [6000/6250] eta: 0:00:38 lr: 0.000124 grad: 0.0650 (0.0690) loss: 0.8530 (0.8491) time: 0.1473 data: 0.0594 max mem: 9394 +Train: [10] [6100/6250] eta: 0:00:22 lr: 0.000124 grad: 0.0660 (0.0689) loss: 0.8522 (0.8491) time: 0.1735 data: 0.0846 max mem: 9394 +Train: [10] [6200/6250] eta: 0:00:07 lr: 0.000124 grad: 0.0637 (0.0689) loss: 0.8490 (0.8491) time: 0.1230 data: 0.0385 max mem: 9394 +Train: [10] [6249/6250] eta: 0:00:00 lr: 0.000124 grad: 0.0666 (0.0689) loss: 0.8473 (0.8491) time: 0.1400 data: 0.0520 max mem: 9394 +Train: [10] Total time: 0:15:58 (0.1534 s / it) +Averaged stats: lr: 0.000124 grad: 0.0666 (0.0689) loss: 0.8473 (0.8491) +Eval (hcp-train-subset): [10] [ 0/62] eta: 0:04:38 loss: 0.8632 (0.8632) time: 4.4903 data: 4.4615 max mem: 9394 +Eval (hcp-train-subset): [10] [61/62] eta: 0:00:00 loss: 0.8557 (0.8544) time: 0.1241 data: 0.0990 max mem: 9394 +Eval (hcp-train-subset): [10] Total time: 0:00:13 (0.2166 s / it) +Averaged stats (hcp-train-subset): loss: 0.8557 (0.8544) +Eval (hcp-val): [10] [ 0/62] eta: 0:04:50 loss: 0.8456 (0.8456) time: 4.6924 data: 4.6634 max mem: 9394 +Eval (hcp-val): [10] [61/62] eta: 0:00:00 loss: 0.8493 (0.8490) time: 0.1142 data: 0.0892 max mem: 9394 +Eval (hcp-val): [10] Total time: 0:00:14 (0.2281 s / it) +Averaged stats (hcp-val): loss: 0.8493 (0.8490) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +Train: [11] [ 0/6250] eta: 11:10:09 lr: 0.000124 grad: 0.0866 (0.0866) loss: 0.8138 (0.8138) time: 6.4334 data: 6.3466 max mem: 9394 +Train: [11] [ 100/6250] eta: 0:21:39 lr: 0.000124 grad: 0.0695 (0.0792) loss: 0.8473 (0.8534) time: 0.1842 data: 0.0810 max mem: 9394 +Train: [11] [ 200/6250] eta: 0:18:40 lr: 0.000124 grad: 0.0637 (0.0751) loss: 0.8492 (0.8496) time: 0.1791 data: 0.0973 max mem: 9394 +Train: [11] [ 300/6250] eta: 0:17:39 lr: 0.000124 grad: 0.0640 (0.0725) loss: 0.8503 (0.8496) time: 0.2280 data: 0.0787 max mem: 9394 +Train: [11] [ 400/6250] eta: 0:18:26 lr: 0.000124 grad: 0.0623 (0.0710) loss: 0.8475 (0.8500) time: 0.2998 data: 0.1881 max mem: 9394 +Train: [11] [ 500/6250] eta: 0:18:20 lr: 0.000124 grad: 0.0619 (0.0698) loss: 0.8508 (0.8505) time: 0.1095 data: 0.0239 max mem: 9394 +Train: [11] [ 600/6250] eta: 0:17:51 lr: 0.000124 grad: 0.0603 (0.0695) loss: 0.8474 (0.8503) time: 0.1640 data: 0.0603 max mem: 9394 +Train: [11] [ 700/6250] eta: 0:17:08 lr: 0.000124 grad: 0.0690 (0.0692) loss: 0.8468 (0.8502) time: 0.1615 data: 0.0776 max mem: 9394 +Train: [11] [ 800/6250] eta: 0:17:08 lr: 0.000124 grad: 0.0617 (0.0686) loss: 0.8533 (0.8503) time: 0.1224 data: 0.0115 max mem: 9394 +Train: [11] [ 900/6250] eta: 0:16:21 lr: 0.000124 grad: 0.0617 (0.0684) loss: 0.8516 (0.8502) time: 0.1119 data: 0.0315 max mem: 9394 +Train: [11] [1000/6250] eta: 0:15:54 lr: 0.000124 grad: 0.0676 (0.0681) loss: 0.8460 (0.8501) time: 0.2048 data: 0.1200 max mem: 9394 +Train: [11] [1100/6250] eta: 0:15:16 lr: 0.000124 grad: 0.0643 (0.0678) loss: 0.8507 (0.8502) time: 0.1436 data: 0.0646 max mem: 9394 +Train: [11] [1200/6250] eta: 0:14:42 lr: 0.000124 grad: 0.0618 (0.0677) loss: 0.8532 (0.8503) time: 0.1430 data: 0.0613 max mem: 9394 +Train: [11] [1300/6250] eta: 0:14:14 lr: 0.000124 grad: 0.0638 (0.0676) loss: 0.8542 (0.8504) time: 0.1409 data: 0.0603 max mem: 9394 +Train: [11] [1400/6250] eta: 0:13:46 lr: 0.000124 grad: 0.0658 (0.0675) loss: 0.8510 (0.8504) time: 0.1319 data: 0.0535 max mem: 9394 +Train: [11] [1500/6250] eta: 0:13:23 lr: 0.000124 grad: 0.0673 (0.0673) loss: 0.8498 (0.8503) time: 0.1643 data: 0.0759 max mem: 9394 +Train: [11] [1600/6250] eta: 0:13:00 lr: 0.000124 grad: 0.0628 (0.0673) loss: 0.8490 (0.8503) time: 0.1678 data: 0.0865 max mem: 9394 +Train: [11] [1700/6250] eta: 0:12:39 lr: 0.000124 grad: 0.0658 (0.0672) loss: 0.8515 (0.8502) time: 0.1272 data: 0.0480 max mem: 9394 +Train: [11] [1800/6250] eta: 0:12:17 lr: 0.000124 grad: 0.0616 (0.0671) loss: 0.8486 (0.8501) time: 0.1660 data: 0.0875 max mem: 9394 +Train: [11] [1900/6250] eta: 0:11:55 lr: 0.000124 grad: 0.0601 (0.0669) loss: 0.8513 (0.8500) time: 0.1417 data: 0.0589 max mem: 9394 +Train: [11] [2000/6250] eta: 0:11:36 lr: 0.000124 grad: 0.0633 (0.0668) loss: 0.8448 (0.8500) time: 0.1485 data: 0.0711 max mem: 9394 +Train: [11] [2100/6250] eta: 0:11:13 lr: 0.000124 grad: 0.0634 (0.0667) loss: 0.8515 (0.8500) time: 0.1506 data: 0.0645 max mem: 9394 +Train: [11] [2200/6250] eta: 0:10:54 lr: 0.000124 grad: 0.0698 (0.0669) loss: 0.8501 (0.8500) time: 0.1469 data: 0.0662 max mem: 9394 +Train: [11] [2300/6250] eta: 0:10:33 lr: 0.000124 grad: 0.0559 (0.0668) loss: 0.8544 (0.8500) time: 0.1469 data: 0.0604 max mem: 9394 +Train: [11] [2400/6250] eta: 0:10:14 lr: 0.000124 grad: 0.0602 (0.0667) loss: 0.8503 (0.8500) time: 0.1385 data: 0.0542 max mem: 9394 +Train: [11] [2500/6250] eta: 0:09:55 lr: 0.000124 grad: 0.0602 (0.0666) loss: 0.8492 (0.8500) time: 0.1359 data: 0.0476 max mem: 9394 +Train: [11] [2600/6250] eta: 0:09:36 lr: 0.000124 grad: 0.0637 (0.0665) loss: 0.8496 (0.8500) time: 0.1476 data: 0.0707 max mem: 9394 +Train: [11] [2700/6250] eta: 0:09:18 lr: 0.000124 grad: 0.0582 (0.0664) loss: 0.8542 (0.8501) time: 0.1359 data: 0.0578 max mem: 9394 +Train: [11] [2800/6250] eta: 0:09:00 lr: 0.000124 grad: 0.0642 (0.0662) loss: 0.8501 (0.8500) time: 0.1511 data: 0.0698 max mem: 9394 +Train: [11] [2900/6250] eta: 0:08:42 lr: 0.000124 grad: 0.0629 (0.0663) loss: 0.8475 (0.8500) time: 0.1372 data: 0.0585 max mem: 9394 +Train: [11] [3000/6250] eta: 0:08:24 lr: 0.000124 grad: 0.0652 (0.0662) loss: 0.8512 (0.8500) time: 0.1285 data: 0.0528 max mem: 9394 +Train: [11] [3100/6250] eta: 0:08:07 lr: 0.000124 grad: 0.0629 (0.0661) loss: 0.8476 (0.8500) time: 0.1301 data: 0.0517 max mem: 9394 +Train: [11] [3200/6250] eta: 0:07:53 lr: 0.000124 grad: 0.0593 (0.0660) loss: 0.8474 (0.8500) time: 0.1386 data: 0.0530 max mem: 9394 +Train: [11] [3300/6250] eta: 0:07:37 lr: 0.000124 grad: 0.0618 (0.0660) loss: 0.8441 (0.8499) time: 0.1383 data: 0.0517 max mem: 9394 +Train: [11] [3400/6250] eta: 0:07:20 lr: 0.000124 grad: 0.0636 (0.0659) loss: 0.8476 (0.8498) time: 0.1439 data: 0.0607 max mem: 9394 +Train: [11] [3500/6250] eta: 0:07:03 lr: 0.000124 grad: 0.0621 (0.0659) loss: 0.8460 (0.8497) time: 0.1278 data: 0.0432 max mem: 9394 +Train: [11] [3600/6250] eta: 0:06:48 lr: 0.000124 grad: 0.0616 (0.0658) loss: 0.8473 (0.8497) time: 0.1454 data: 0.0653 max mem: 9394 +Train: [11] [3700/6250] eta: 0:06:32 lr: 0.000124 grad: 0.0623 (0.0659) loss: 0.8471 (0.8496) time: 0.1400 data: 0.0684 max mem: 9394 +Train: [11] [3800/6250] eta: 0:06:15 lr: 0.000124 grad: 0.0639 (0.0658) loss: 0.8442 (0.8495) time: 0.1303 data: 0.0499 max mem: 9394 +Train: [11] [3900/6250] eta: 0:05:59 lr: 0.000124 grad: 0.0668 (0.0658) loss: 0.8443 (0.8494) time: 0.1458 data: 0.0687 max mem: 9394 +Train: [11] [4000/6250] eta: 0:05:43 lr: 0.000123 grad: 0.0616 (0.0658) loss: 0.8487 (0.8494) time: 0.1653 data: 0.0920 max mem: 9394 +Train: [11] [4100/6250] eta: 0:05:28 lr: 0.000123 grad: 0.0666 (0.0658) loss: 0.8422 (0.8493) time: 0.1679 data: 0.0910 max mem: 9394 +Train: [11] [4200/6250] eta: 0:05:12 lr: 0.000123 grad: 0.0632 (0.0658) loss: 0.8437 (0.8492) time: 0.1566 data: 0.0783 max mem: 9394 +Train: [11] [4300/6250] eta: 0:04:56 lr: 0.000123 grad: 0.0625 (0.0658) loss: 0.8485 (0.8492) time: 0.1272 data: 0.0465 max mem: 9394 +Train: [11] [4400/6250] eta: 0:04:41 lr: 0.000123 grad: 0.0644 (0.0658) loss: 0.8481 (0.8491) time: 0.1543 data: 0.0710 max mem: 9394 +Train: [11] [4500/6250] eta: 0:04:25 lr: 0.000123 grad: 0.0651 (0.0658) loss: 0.8461 (0.8491) time: 0.1433 data: 0.0719 max mem: 9394 +Train: [11] [4600/6250] eta: 0:04:09 lr: 0.000123 grad: 0.0655 (0.0658) loss: 0.8463 (0.8490) time: 0.1281 data: 0.0455 max mem: 9394 +Train: [11] [4700/6250] eta: 0:03:54 lr: 0.000123 grad: 0.0626 (0.0658) loss: 0.8434 (0.8490) time: 0.1459 data: 0.0661 max mem: 9394 +Train: [11] [4800/6250] eta: 0:03:39 lr: 0.000123 grad: 0.0612 (0.0658) loss: 0.8433 (0.8489) time: 0.1604 data: 0.0732 max mem: 9394 +Train: [11] [4900/6250] eta: 0:03:24 lr: 0.000123 grad: 0.0657 (0.0658) loss: 0.8458 (0.8488) time: 0.1197 data: 0.0367 max mem: 9394 +Train: [11] [5000/6250] eta: 0:03:09 lr: 0.000123 grad: 0.0711 (0.0658) loss: 0.8453 (0.8487) time: 0.1319 data: 0.0484 max mem: 9394 +Train: [11] [5100/6250] eta: 0:02:53 lr: 0.000123 grad: 0.0638 (0.0658) loss: 0.8456 (0.8487) time: 0.1544 data: 0.0747 max mem: 9394 +Train: [11] [5200/6250] eta: 0:02:38 lr: 0.000123 grad: 0.0666 (0.0657) loss: 0.8478 (0.8487) time: 0.1682 data: 0.0893 max mem: 9394 +Train: [11] [5300/6250] eta: 0:02:23 lr: 0.000123 grad: 0.0638 (0.0657) loss: 0.8417 (0.8486) time: 0.1525 data: 0.0716 max mem: 9394 +Train: [11] [5400/6250] eta: 0:02:07 lr: 0.000123 grad: 0.0639 (0.0657) loss: 0.8457 (0.8485) time: 0.1437 data: 0.0650 max mem: 9394 +Train: [11] [5500/6250] eta: 0:01:52 lr: 0.000123 grad: 0.0632 (0.0657) loss: 0.8443 (0.8485) time: 0.1290 data: 0.0508 max mem: 9394 +Train: [11] [5600/6250] eta: 0:01:37 lr: 0.000123 grad: 0.0642 (0.0657) loss: 0.8439 (0.8485) time: 0.1475 data: 0.0670 max mem: 9394 +Train: [11] [5700/6250] eta: 0:01:22 lr: 0.000123 grad: 0.0669 (0.0657) loss: 0.8414 (0.8484) time: 0.1722 data: 0.0956 max mem: 9394 +Train: [11] [5800/6250] eta: 0:01:07 lr: 0.000123 grad: 0.0655 (0.0657) loss: 0.8428 (0.8483) time: 0.2139 data: 0.1290 max mem: 9394 +Train: [11] [5900/6250] eta: 0:00:52 lr: 0.000123 grad: 0.0605 (0.0657) loss: 0.8423 (0.8483) time: 0.1687 data: 0.0787 max mem: 9394 +Train: [11] [6000/6250] eta: 0:00:37 lr: 0.000123 grad: 0.0629 (0.0657) loss: 0.8413 (0.8482) time: 0.1720 data: 0.0902 max mem: 9394 +Train: [11] [6100/6250] eta: 0:00:22 lr: 0.000123 grad: 0.0668 (0.0657) loss: 0.8471 (0.8482) time: 0.2074 data: 0.1199 max mem: 9394 +Train: [11] [6200/6250] eta: 0:00:07 lr: 0.000123 grad: 0.0646 (0.0657) loss: 0.8438 (0.8482) time: 0.1483 data: 0.0639 max mem: 9394 +Train: [11] [6249/6250] eta: 0:00:00 lr: 0.000123 grad: 0.0633 (0.0657) loss: 0.8494 (0.8482) time: 0.1456 data: 0.0573 max mem: 9394 +Train: [11] Total time: 0:15:48 (0.1517 s / it) +Averaged stats: lr: 0.000123 grad: 0.0633 (0.0657) loss: 0.8494 (0.8482) +Eval (hcp-train-subset): [11] [ 0/62] eta: 0:05:36 loss: 0.8639 (0.8639) time: 5.4234 data: 5.3958 max mem: 9394 +Eval (hcp-train-subset): [11] [61/62] eta: 0:00:00 loss: 0.8519 (0.8529) time: 0.1271 data: 0.1022 max mem: 9394 +Eval (hcp-train-subset): [11] Total time: 0:00:13 (0.2101 s / it) +Averaged stats (hcp-train-subset): loss: 0.8519 (0.8529) +Eval (hcp-val): [11] [ 0/62] eta: 0:05:16 loss: 0.8442 (0.8442) time: 5.1090 data: 5.0812 max mem: 9394 +Eval (hcp-val): [11] [61/62] eta: 0:00:00 loss: 0.8455 (0.8471) time: 0.1135 data: 0.0887 max mem: 9394 +Eval (hcp-val): [11] Total time: 0:00:12 (0.2033 s / it) +Averaged stats (hcp-val): loss: 0.8455 (0.8471) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +Train: [12] [ 0/6250] eta: 9:54:45 lr: 0.000123 grad: 0.0854 (0.0854) loss: 0.8632 (0.8632) time: 5.7097 data: 5.6057 max mem: 9394 +Train: [12] [ 100/6250] eta: 0:20:43 lr: 0.000123 grad: 0.0681 (0.0764) loss: 0.8447 (0.8473) time: 0.1511 data: 0.0527 max mem: 9394 +Train: [12] [ 200/6250] eta: 0:18:00 lr: 0.000123 grad: 0.0577 (0.0703) loss: 0.8496 (0.8490) time: 0.1519 data: 0.0651 max mem: 9394 +Train: [12] [ 300/6250] eta: 0:16:41 lr: 0.000123 grad: 0.0625 (0.0677) loss: 0.8451 (0.8489) time: 0.1423 data: 0.0548 max mem: 9394 +Train: [12] [ 400/6250] eta: 0:15:46 lr: 0.000123 grad: 0.0609 (0.0668) loss: 0.8502 (0.8486) time: 0.1325 data: 0.0434 max mem: 9394 +Train: [12] [ 500/6250] eta: 0:15:12 lr: 0.000123 grad: 0.0612 (0.0667) loss: 0.8464 (0.8484) time: 0.1625 data: 0.0791 max mem: 9394 +Train: [12] [ 600/6250] eta: 0:14:54 lr: 0.000123 grad: 0.0633 (0.0667) loss: 0.8494 (0.8482) time: 0.1545 data: 0.0466 max mem: 9394 +Train: [12] [ 700/6250] eta: 0:14:31 lr: 0.000123 grad: 0.0614 (0.0665) loss: 0.8540 (0.8481) time: 0.1347 data: 0.0541 max mem: 9394 +Train: [12] [ 800/6250] eta: 0:14:37 lr: 0.000123 grad: 0.0607 (0.0662) loss: 0.8466 (0.8480) time: 0.2244 data: 0.1421 max mem: 9394 +Train: [12] [ 900/6250] eta: 0:14:14 lr: 0.000123 grad: 0.0631 (0.0661) loss: 0.8474 (0.8480) time: 0.1384 data: 0.0189 max mem: 9394 +Train: [12] [1000/6250] eta: 0:13:52 lr: 0.000123 grad: 0.0632 (0.0660) loss: 0.8476 (0.8480) time: 0.1431 data: 0.0628 max mem: 9394 +Train: [12] [1100/6250] eta: 0:13:26 lr: 0.000123 grad: 0.0637 (0.0662) loss: 0.8471 (0.8480) time: 0.1405 data: 0.0557 max mem: 9394 +Train: [12] [1200/6250] eta: 0:13:07 lr: 0.000123 grad: 0.0637 (0.0662) loss: 0.8501 (0.8479) time: 0.0881 data: 0.0002 max mem: 9394 +Train: [12] [1300/6250] eta: 0:12:46 lr: 0.000123 grad: 0.0588 (0.0661) loss: 0.8476 (0.8478) time: 0.1538 data: 0.0731 max mem: 9394 +Train: [12] [1400/6250] eta: 0:12:22 lr: 0.000123 grad: 0.0650 (0.0660) loss: 0.8469 (0.8479) time: 0.1271 data: 0.0455 max mem: 9394 +Train: [12] [1500/6250] eta: 0:12:05 lr: 0.000123 grad: 0.0676 (0.0659) loss: 0.8460 (0.8479) time: 0.1397 data: 0.0595 max mem: 9394 +Train: [12] [1600/6250] eta: 0:11:46 lr: 0.000123 grad: 0.0629 (0.0658) loss: 0.8498 (0.8478) time: 0.1464 data: 0.0672 max mem: 9394 +Train: [12] [1700/6250] eta: 0:11:26 lr: 0.000123 grad: 0.0614 (0.0661) loss: 0.8487 (0.8478) time: 0.1366 data: 0.0550 max mem: 9394 +Train: [12] [1800/6250] eta: 0:11:09 lr: 0.000123 grad: 0.0622 (0.0660) loss: 0.8469 (0.8478) time: 0.1621 data: 0.0812 max mem: 9394 +Train: [12] [1900/6250] eta: 0:10:51 lr: 0.000123 grad: 0.0657 (0.0661) loss: 0.8485 (0.8477) time: 0.1417 data: 0.0614 max mem: 9394 +Train: [12] [2000/6250] eta: 0:10:34 lr: 0.000123 grad: 0.0632 (0.0663) loss: 0.8466 (0.8475) time: 0.1491 data: 0.0709 max mem: 9394 +Train: [12] [2100/6250] eta: 0:10:17 lr: 0.000123 grad: 0.0643 (0.0663) loss: 0.8472 (0.8474) time: 0.1456 data: 0.0629 max mem: 9394 +Train: [12] [2200/6250] eta: 0:10:01 lr: 0.000123 grad: 0.0700 (0.0666) loss: 0.8480 (0.8473) time: 0.1298 data: 0.0481 max mem: 9394 +Train: [12] [2300/6250] eta: 0:09:44 lr: 0.000123 grad: 0.0626 (0.0666) loss: 0.8463 (0.8472) time: 0.1251 data: 0.0453 max mem: 9394 +Train: [12] [2400/6250] eta: 0:09:29 lr: 0.000123 grad: 0.0647 (0.0668) loss: 0.8430 (0.8471) time: 0.1310 data: 0.0542 max mem: 9394 +Train: [12] [2500/6250] eta: 0:09:13 lr: 0.000123 grad: 0.0681 (0.0667) loss: 0.8445 (0.8470) time: 0.1510 data: 0.0732 max mem: 9394 +Train: [12] [2600/6250] eta: 0:08:57 lr: 0.000123 grad: 0.0605 (0.0665) loss: 0.8462 (0.8470) time: 0.1393 data: 0.0571 max mem: 9394 +Train: [12] [2700/6250] eta: 0:08:42 lr: 0.000123 grad: 0.0611 (0.0665) loss: 0.8447 (0.8471) time: 0.1361 data: 0.0537 max mem: 9394 +Train: [12] [2800/6250] eta: 0:08:26 lr: 0.000123 grad: 0.0631 (0.0664) loss: 0.8451 (0.8470) time: 0.1388 data: 0.0620 max mem: 9394 +Train: [12] [2900/6250] eta: 0:08:11 lr: 0.000123 grad: 0.0601 (0.0663) loss: 0.8462 (0.8470) time: 0.1756 data: 0.0980 max mem: 9394 +Train: [12] [3000/6250] eta: 0:07:57 lr: 0.000123 grad: 0.0624 (0.0664) loss: 0.8497 (0.8470) time: 0.2129 data: 0.0924 max mem: 9394 +Train: [12] [3100/6250] eta: 0:07:42 lr: 0.000123 grad: 0.0651 (0.0663) loss: 0.8497 (0.8470) time: 0.1217 data: 0.0293 max mem: 9394 +Train: [12] [3200/6250] eta: 0:07:28 lr: 0.000123 grad: 0.0607 (0.0662) loss: 0.8463 (0.8471) time: 0.1624 data: 0.0817 max mem: 9394 +Train: [12] [3300/6250] eta: 0:07:12 lr: 0.000123 grad: 0.0597 (0.0661) loss: 0.8461 (0.8471) time: 0.1189 data: 0.0339 max mem: 9394 +Train: [12] [3400/6250] eta: 0:06:57 lr: 0.000123 grad: 0.0637 (0.0662) loss: 0.8446 (0.8471) time: 0.1332 data: 0.0525 max mem: 9394 +Train: [12] [3500/6250] eta: 0:06:42 lr: 0.000123 grad: 0.0597 (0.0661) loss: 0.8449 (0.8471) time: 0.1213 data: 0.0398 max mem: 9394 +Train: [12] [3600/6250] eta: 0:06:27 lr: 0.000123 grad: 0.0634 (0.0660) loss: 0.8463 (0.8472) time: 0.1581 data: 0.0795 max mem: 9394 +Train: [12] [3700/6250] eta: 0:06:12 lr: 0.000123 grad: 0.0601 (0.0659) loss: 0.8507 (0.8472) time: 0.1430 data: 0.0651 max mem: 9394 +Train: [12] [3800/6250] eta: 0:05:57 lr: 0.000123 grad: 0.0622 (0.0659) loss: 0.8449 (0.8472) time: 0.1286 data: 0.0483 max mem: 9394 +Train: [12] [3900/6250] eta: 0:05:42 lr: 0.000123 grad: 0.0617 (0.0658) loss: 0.8505 (0.8473) time: 0.1205 data: 0.0431 max mem: 9394 +Train: [12] [4000/6250] eta: 0:05:27 lr: 0.000123 grad: 0.0587 (0.0657) loss: 0.8475 (0.8473) time: 0.1278 data: 0.0450 max mem: 9394 +Train: [12] [4100/6250] eta: 0:05:13 lr: 0.000123 grad: 0.0595 (0.0657) loss: 0.8501 (0.8473) time: 0.1526 data: 0.0764 max mem: 9394 +Train: [12] [4200/6250] eta: 0:04:58 lr: 0.000123 grad: 0.0618 (0.0656) loss: 0.8427 (0.8473) time: 0.1184 data: 0.0393 max mem: 9394 +Train: [12] [4300/6250] eta: 0:04:43 lr: 0.000123 grad: 0.0596 (0.0656) loss: 0.8468 (0.8473) time: 0.1432 data: 0.0630 max mem: 9394 +Train: [12] [4400/6250] eta: 0:04:28 lr: 0.000123 grad: 0.0622 (0.0656) loss: 0.8474 (0.8473) time: 0.1371 data: 0.0560 max mem: 9394 +Train: [12] [4500/6250] eta: 0:04:13 lr: 0.000123 grad: 0.0599 (0.0655) loss: 0.8528 (0.8473) time: 0.1507 data: 0.0744 max mem: 9394 +Train: [12] [4600/6250] eta: 0:03:59 lr: 0.000123 grad: 0.0562 (0.0655) loss: 0.8490 (0.8473) time: 0.1784 data: 0.0995 max mem: 9394 +Train: [12] [4700/6250] eta: 0:03:45 lr: 0.000123 grad: 0.0594 (0.0655) loss: 0.8500 (0.8472) time: 0.1269 data: 0.0372 max mem: 9394 +Train: [12] [4800/6250] eta: 0:03:30 lr: 0.000123 grad: 0.0592 (0.0654) loss: 0.8502 (0.8472) time: 0.1535 data: 0.0774 max mem: 9394 +Train: [12] [4900/6250] eta: 0:03:15 lr: 0.000123 grad: 0.0602 (0.0654) loss: 0.8425 (0.8472) time: 0.1752 data: 0.0948 max mem: 9394 +Train: [12] [5000/6250] eta: 0:03:01 lr: 0.000123 grad: 0.0595 (0.0654) loss: 0.8507 (0.8472) time: 0.1494 data: 0.0721 max mem: 9394 +Train: [12] [5100/6250] eta: 0:02:46 lr: 0.000123 grad: 0.0621 (0.0653) loss: 0.8460 (0.8472) time: 0.1433 data: 0.0608 max mem: 9394 +Train: [12] [5200/6250] eta: 0:02:32 lr: 0.000123 grad: 0.0586 (0.0653) loss: 0.8478 (0.8472) time: 0.1297 data: 0.0488 max mem: 9394 +Train: [12] [5300/6250] eta: 0:02:17 lr: 0.000123 grad: 0.0613 (0.0652) loss: 0.8474 (0.8472) time: 0.1519 data: 0.0691 max mem: 9394 +Train: [12] [5400/6250] eta: 0:02:02 lr: 0.000123 grad: 0.0647 (0.0652) loss: 0.8474 (0.8472) time: 0.1586 data: 0.0744 max mem: 9394 +Train: [12] [5500/6250] eta: 0:01:48 lr: 0.000123 grad: 0.0620 (0.0652) loss: 0.8474 (0.8472) time: 0.1463 data: 0.0606 max mem: 9394 +Train: [12] [5600/6250] eta: 0:01:33 lr: 0.000123 grad: 0.0635 (0.0651) loss: 0.8458 (0.8472) time: 0.1715 data: 0.0833 max mem: 9394 +Train: [12] [5700/6250] eta: 0:01:19 lr: 0.000123 grad: 0.0596 (0.0651) loss: 0.8453 (0.8471) time: 0.1323 data: 0.0311 max mem: 9394 +Train: [12] [5800/6250] eta: 0:01:05 lr: 0.000123 grad: 0.0630 (0.0651) loss: 0.8443 (0.8471) time: 0.2700 data: 0.1906 max mem: 9394 +Train: [12] [5900/6250] eta: 0:00:50 lr: 0.000123 grad: 0.0634 (0.0651) loss: 0.8465 (0.8471) time: 0.1287 data: 0.0495 max mem: 9394 +Train: [12] [6000/6250] eta: 0:00:36 lr: 0.000123 grad: 0.0587 (0.0651) loss: 0.8445 (0.8471) time: 0.1632 data: 0.0797 max mem: 9394 +Train: [12] [6100/6250] eta: 0:00:21 lr: 0.000123 grad: 0.0606 (0.0651) loss: 0.8446 (0.8470) time: 0.1585 data: 0.0713 max mem: 9394 +Train: [12] [6200/6250] eta: 0:00:07 lr: 0.000123 grad: 0.0631 (0.0651) loss: 0.8445 (0.8470) time: 0.1409 data: 0.0547 max mem: 9394 +Train: [12] [6249/6250] eta: 0:00:00 lr: 0.000123 grad: 0.0611 (0.0651) loss: 0.8468 (0.8470) time: 0.1546 data: 0.0747 max mem: 9394 +Train: [12] Total time: 0:15:20 (0.1473 s / it) +Averaged stats: lr: 0.000123 grad: 0.0611 (0.0651) loss: 0.8468 (0.8470) +Eval (hcp-train-subset): [12] [ 0/62] eta: 0:05:49 loss: 0.8619 (0.8619) time: 5.6425 data: 5.6082 max mem: 9394 +Eval (hcp-train-subset): [12] [61/62] eta: 0:00:00 loss: 0.8503 (0.8515) time: 0.1211 data: 0.0960 max mem: 9394 +Eval (hcp-train-subset): [12] Total time: 0:00:13 (0.2111 s / it) +Averaged stats (hcp-train-subset): loss: 0.8503 (0.8515) +Eval (hcp-val): [12] [ 0/62] eta: 0:05:30 loss: 0.8417 (0.8417) time: 5.3226 data: 5.2945 max mem: 9394 +Eval (hcp-val): [12] [61/62] eta: 0:00:00 loss: 0.8450 (0.8454) time: 0.1327 data: 0.1062 max mem: 9394 +Eval (hcp-val): [12] Total time: 0:00:13 (0.2137 s / it) +Averaged stats (hcp-val): loss: 0.8450 (0.8454) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +Train: [13] [ 0/6250] eta: 9:09:03 lr: 0.000123 grad: 0.0912 (0.0912) loss: 0.8610 (0.8610) time: 5.2709 data: 5.1053 max mem: 9394 +Train: [13] [ 100/6250] eta: 0:21:13 lr: 0.000123 grad: 0.0657 (0.0700) loss: 0.8475 (0.8448) time: 0.1364 data: 0.0460 max mem: 9394 +Train: [13] [ 200/6250] eta: 0:17:37 lr: 0.000123 grad: 0.0662 (0.0690) loss: 0.8393 (0.8423) time: 0.1232 data: 0.0393 max mem: 9394 +Train: [13] [ 300/6250] eta: 0:16:09 lr: 0.000123 grad: 0.0642 (0.0680) loss: 0.8410 (0.8409) time: 0.1237 data: 0.0303 max mem: 9394 +Train: [13] [ 400/6250] eta: 0:15:27 lr: 0.000123 grad: 0.0635 (0.0672) loss: 0.8423 (0.8402) time: 0.1536 data: 0.0740 max mem: 9394 +Train: [13] [ 500/6250] eta: 0:15:10 lr: 0.000123 grad: 0.0605 (0.0667) loss: 0.8474 (0.8407) time: 0.2111 data: 0.1213 max mem: 9394 +Train: [13] [ 600/6250] eta: 0:14:36 lr: 0.000123 grad: 0.0625 (0.0660) loss: 0.8447 (0.8410) time: 0.1326 data: 0.0531 max mem: 9394 +Train: [13] [ 700/6250] eta: 0:14:35 lr: 0.000123 grad: 0.0593 (0.0656) loss: 0.8464 (0.8416) time: 0.1107 data: 0.0191 max mem: 9394 +Train: [13] [ 800/6250] eta: 0:14:32 lr: 0.000123 grad: 0.0643 (0.0654) loss: 0.8451 (0.8422) time: 0.2701 data: 0.1226 max mem: 9394 +Train: [13] [ 900/6250] eta: 0:14:56 lr: 0.000123 grad: 0.0596 (0.0649) loss: 0.8419 (0.8426) time: 0.1693 data: 0.0791 max mem: 9394 +Train: [13] [1000/6250] eta: 0:14:32 lr: 0.000123 grad: 0.0618 (0.0646) loss: 0.8453 (0.8429) time: 0.1970 data: 0.0811 max mem: 9394 +Train: [13] [1100/6250] eta: 0:14:10 lr: 0.000123 grad: 0.0635 (0.0644) loss: 0.8443 (0.8432) time: 0.1171 data: 0.0285 max mem: 9394 +Train: [13] [1200/6250] eta: 0:13:51 lr: 0.000123 grad: 0.0609 (0.0641) loss: 0.8455 (0.8434) time: 0.1273 data: 0.0402 max mem: 9394 +Train: [13] [1300/6250] eta: 0:13:24 lr: 0.000123 grad: 0.0619 (0.0640) loss: 0.8496 (0.8437) time: 0.1362 data: 0.0569 max mem: 9394 +Train: [13] [1400/6250] eta: 0:12:59 lr: 0.000123 grad: 0.0613 (0.0639) loss: 0.8480 (0.8438) time: 0.1481 data: 0.0634 max mem: 9394 +Train: [13] [1500/6250] eta: 0:12:43 lr: 0.000123 grad: 0.0619 (0.0639) loss: 0.8472 (0.8439) time: 0.1201 data: 0.0289 max mem: 9394 +Train: [13] [1600/6250] eta: 0:12:34 lr: 0.000123 grad: 0.0615 (0.0639) loss: 0.8449 (0.8440) time: 0.1192 data: 0.0315 max mem: 9394 +Train: [13] [1700/6250] eta: 0:12:10 lr: 0.000123 grad: 0.0653 (0.0639) loss: 0.8449 (0.8441) time: 0.1276 data: 0.0409 max mem: 9394 +Train: [13] [1800/6250] eta: 0:11:49 lr: 0.000123 grad: 0.0609 (0.0638) loss: 0.8455 (0.8442) time: 0.1529 data: 0.0685 max mem: 9394 +Train: [13] [1900/6250] eta: 0:11:27 lr: 0.000123 grad: 0.0627 (0.0639) loss: 0.8441 (0.8443) time: 0.1286 data: 0.0435 max mem: 9394 +Train: [13] [2000/6250] eta: 0:11:08 lr: 0.000123 grad: 0.0653 (0.0641) loss: 0.8405 (0.8443) time: 0.1473 data: 0.0650 max mem: 9394 +Train: [13] [2100/6250] eta: 0:10:50 lr: 0.000123 grad: 0.0629 (0.0641) loss: 0.8431 (0.8443) time: 0.1468 data: 0.0690 max mem: 9394 +Train: [13] [2200/6250] eta: 0:10:31 lr: 0.000123 grad: 0.0659 (0.0641) loss: 0.8438 (0.8444) time: 0.1286 data: 0.0393 max mem: 9394 +Train: [13] [2300/6250] eta: 0:10:13 lr: 0.000123 grad: 0.0639 (0.0642) loss: 0.8441 (0.8443) time: 0.1565 data: 0.0801 max mem: 9394 +Train: [13] [2400/6250] eta: 0:09:56 lr: 0.000123 grad: 0.0634 (0.0642) loss: 0.8428 (0.8443) time: 0.1592 data: 0.0864 max mem: 9394 +Train: [13] [2500/6250] eta: 0:09:38 lr: 0.000123 grad: 0.0627 (0.0643) loss: 0.8433 (0.8442) time: 0.1318 data: 0.0548 max mem: 9394 +Train: [13] [2600/6250] eta: 0:09:20 lr: 0.000123 grad: 0.0630 (0.0643) loss: 0.8427 (0.8443) time: 0.1348 data: 0.0568 max mem: 9394 +Train: [13] [2700/6250] eta: 0:09:03 lr: 0.000123 grad: 0.0587 (0.0642) loss: 0.8448 (0.8443) time: 0.1306 data: 0.0493 max mem: 9394 +Train: [13] [2800/6250] eta: 0:08:46 lr: 0.000123 grad: 0.0611 (0.0642) loss: 0.8446 (0.8444) time: 0.1421 data: 0.0587 max mem: 9394 +Train: [13] [2900/6250] eta: 0:08:29 lr: 0.000123 grad: 0.0636 (0.0642) loss: 0.8453 (0.8443) time: 0.1171 data: 0.0340 max mem: 9394 +Train: [13] [3000/6250] eta: 0:08:13 lr: 0.000123 grad: 0.0598 (0.0642) loss: 0.8486 (0.8444) time: 0.1124 data: 0.0279 max mem: 9394 +Train: [13] [3100/6250] eta: 0:07:57 lr: 0.000123 grad: 0.0643 (0.0643) loss: 0.8427 (0.8443) time: 0.1385 data: 0.0590 max mem: 9394 +Train: [13] [3200/6250] eta: 0:07:41 lr: 0.000123 grad: 0.0594 (0.0642) loss: 0.8476 (0.8443) time: 0.1070 data: 0.0227 max mem: 9394 +Train: [13] [3300/6250] eta: 0:07:25 lr: 0.000123 grad: 0.0581 (0.0641) loss: 0.8471 (0.8443) time: 0.1463 data: 0.0644 max mem: 9394 +Train: [13] [3400/6250] eta: 0:07:09 lr: 0.000123 grad: 0.0628 (0.0642) loss: 0.8465 (0.8444) time: 0.1523 data: 0.0754 max mem: 9394 +Train: [13] [3500/6250] eta: 0:06:54 lr: 0.000123 grad: 0.0587 (0.0642) loss: 0.8458 (0.8444) time: 0.1447 data: 0.0603 max mem: 9394 +Train: [13] [3600/6250] eta: 0:06:38 lr: 0.000123 grad: 0.0645 (0.0642) loss: 0.8389 (0.8444) time: 0.1284 data: 0.0475 max mem: 9394 +Train: [13] [3700/6250] eta: 0:06:22 lr: 0.000122 grad: 0.0589 (0.0641) loss: 0.8475 (0.8445) time: 0.1296 data: 0.0510 max mem: 9394 +Train: [13] [3800/6250] eta: 0:06:06 lr: 0.000122 grad: 0.0615 (0.0641) loss: 0.8428 (0.8445) time: 0.1313 data: 0.0507 max mem: 9394 +Train: [13] [3900/6250] eta: 0:05:50 lr: 0.000122 grad: 0.0615 (0.0642) loss: 0.8452 (0.8445) time: 0.1417 data: 0.0597 max mem: 9394 +Train: [13] [4000/6250] eta: 0:05:35 lr: 0.000122 grad: 0.0612 (0.0642) loss: 0.8446 (0.8445) time: 0.1330 data: 0.0468 max mem: 9394 +Train: [13] [4100/6250] eta: 0:05:20 lr: 0.000122 grad: 0.0692 (0.0642) loss: 0.8440 (0.8444) time: 0.1348 data: 0.0547 max mem: 9394 +Train: [13] [4200/6250] eta: 0:05:05 lr: 0.000122 grad: 0.0641 (0.0643) loss: 0.8450 (0.8444) time: 0.1528 data: 0.0676 max mem: 9394 +Train: [13] [4300/6250] eta: 0:04:51 lr: 0.000122 grad: 0.0685 (0.0643) loss: 0.8411 (0.8444) time: 0.1206 data: 0.0439 max mem: 9394 +Train: [13] [4400/6250] eta: 0:04:35 lr: 0.000122 grad: 0.0650 (0.0644) loss: 0.8467 (0.8444) time: 0.1271 data: 0.0459 max mem: 9394 +Train: [13] [4500/6250] eta: 0:04:20 lr: 0.000122 grad: 0.0595 (0.0644) loss: 0.8445 (0.8444) time: 0.1421 data: 0.0652 max mem: 9394 +Train: [13] [4600/6250] eta: 0:04:05 lr: 0.000122 grad: 0.0647 (0.0644) loss: 0.8472 (0.8444) time: 0.1498 data: 0.0693 max mem: 9394 +Train: [13] [4700/6250] eta: 0:03:50 lr: 0.000122 grad: 0.0633 (0.0644) loss: 0.8439 (0.8444) time: 0.1617 data: 0.0841 max mem: 9394 +Train: [13] [4800/6250] eta: 0:03:36 lr: 0.000122 grad: 0.0624 (0.0644) loss: 0.8396 (0.8443) time: 0.1690 data: 0.0923 max mem: 9394 +Train: [13] [4900/6250] eta: 0:03:20 lr: 0.000122 grad: 0.0602 (0.0644) loss: 0.8415 (0.8443) time: 0.1307 data: 0.0515 max mem: 9394 +Train: [13] [5000/6250] eta: 0:03:05 lr: 0.000122 grad: 0.0640 (0.0644) loss: 0.8465 (0.8442) time: 0.1407 data: 0.0584 max mem: 9394 +pretraining fmri mae +start: 2026-03-31 20:03:56 +cwd: /data/connor/fmri-fm +sha: 7f4cedc35609f6857314e0d1ea6657523f17ddeb, status: has uncommitted changes, branch: dev/clane9 +config: +name: input_space_v3/flat_lr1e-3_2/pretrain +notes: input_space ablation v3 flat_lr1e-3_2; use tube masking and on-disk data (input_space=flat + base_lr=1e-3 seed=5402) +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain +input_space: flat +patch_size: 16 +num_frames: 16 +t_patch_size: 4 +mask_ratio: 0.9 +pred_mask_ratio: null +masking: tube +masking_kwargs: {} +mask_patch_size: null +model: mae_vit_base +model_kwargs: + decoding: attn + pos_embed: sep + target_norm: null + pca_norm_nc: 2 + t_pred_stride: 2 + no_decode_pos: true + mask_drop_scale: false + pred_edge_pad: 0 + gauss_sigma: null + class_token: true + reg_tokens: 0 + no_embed_class: true + head_init_scale: 0.0 + decoder_depth: 4 + drop_path_rate: 0.0 +datasets: + hcp-train: + type: wds + url: /data/fmri-datasets/pretrain/hcpya-all.${input_space}.wds/hcpya-all-${input_space}-{00000..01799}.tar + clipping: random + clipping_kwargs: + oversample: 4.0 + shuffle: true + buffer_size: 2000 + samples_per_epoch: 200000 + hcp-train-subset: + type: arrow + root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/validation + split_range: + - 0 + - 2000 + shuffle: false + hcp-val: + type: arrow + root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/test + split_range: + - 0 + - 2000 + shuffle: false +train_dataset: hcp-train +eval_datasets: +- hcp-train-subset +- hcp-val +val_dataset: null +clip_vmax: 3.0 +normalize: frame +tr_scale: null +crop_scale: null +crop_aspect: null +gray_jitter: null +num_workers: 16 +epochs: 100 +batch_size: 32 +accum_iter: 1 +base_lr: 0.001 +min_lr: 0.0 +warmup_epochs: 5 +weight_decay: 0.05 +betas: +- 0.9 +- 0.95 +clip_grad: 1.0 +amp: true +amp_dtype: float16 +ckpt: null +resume: true +auto_resume: true +start_epoch: 0 +max_checkpoints: 0 +checkpoint_period: null +plot_period: 5 +device: cuda +presend_cuda: false +seed: 5402 +debug: false +wandb: true +wandb_entity: null +wandb_project: fMRI-foundation-model +rank: 0 +world_size: 1 +gpu: 0 +distributed: true +dist_backend: nccl +in_chans: 1 +img_size: +- 224 +- 560 + +train transform: +Compose( + ToTensor() + TemporalCenterCrop(num_frames=16) + Normalize(mode='frame') + Clip(vmax=3.0) + FlatUnmask((224, 560)) +) +val transform: +Compose( + ToTensor() + TemporalCenterCrop(num_frames=16) + Normalize(mode='frame') + Clip(vmax=3.0) + FlatUnmask((224, 560)) +) +mask generator: +TubeMasking( + mask_ratio=0.9 + (patchify): Patchify2D((224, 560), (16, 16), in_chans=1) +) +loading dataset: hcp-train + +type: wds +url: /data/fmri-datasets/pretrain/hcpya-all.${input_space}.wds/hcpya-all-${input_space}-{00000..01799}.tar +clipping: random +clipping_kwargs: + oversample: 4.0 +shuffle: true +buffer_size: 2000 +samples_per_epoch: 200000 + +loading dataset: hcp-train-subset + +type: arrow +root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/validation +split_range: +- 0 +- 2000 +shuffle: false + +split indices: [899, 472, 767, 116, 1265, 1852, 300, 1335, 361, 1560] +loading dataset: hcp-val + +type: arrow +root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/test +split_range: +- 0 +- 2000 +shuffle: false + +split indices: [1075, 1189, 738, 1350, 965, 1964, 1367, 1183, 1619, 1407] +model: +MaskedAutoencoderViT( + decoding=attn, t_pred_stride=2, pred_edge_pad=0, no_decode_pos=True + (encoder): MaskedEncoder( + class_token=True, reg_tokens=0, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) + (pred_patchify): StridedPatchify3D((16, 224, 560), (2, 16, 16), in_chans=1, t_stride=2) + (decoder): MaskedDecoder( + cross_decode=False, class_token=True, no_embed_class=True + (pos_embed): SeparablePosEmbed(512, (4, 14, 35)) + (proj): Linear(in_features=768, out_features=512, bias=True) + (blocks): ModuleList( + (0-3): 4 x Block( + (norm1): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=16 + (q): Linear(in_features=512, out_features=512, bias=True) + (k): Linear(in_features=512, out_features=512, bias=True) + (v): Linear(in_features=512, out_features=512, bias=True) + (proj): Linear(in_features=512, out_features=512, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=512, out_features=2048, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=2048, out_features=512, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (head): Linear(in_features=512, out_features=512, bias=True) + ) +) +num params: 99.7M +total batch size: 32 = 32 bs per gpu x 1 accum x 1 gpus +lr: 1.25e-04 = 1.00e-03 x 32 / 256 +full schedule: epochs = 100 (steps = 625000) +warmup: epochs = 5 (steps = 31250) +loaded model state from checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +loaded optimizer state, resuming training from 13 +start training for 100 epochs +Train: [13] [ 0/6250] eta: 15:59:33 lr: 0.000123 grad: 0.0649 (0.0649) loss: 0.8418 (0.8418) time: 9.2118 data: 8.1836 max mem: 9353 +Train: [13] [ 100/6250] eta: 0:22:40 lr: 0.000123 grad: 0.0761 (0.0772) loss: 0.8558 (0.8489) time: 0.1708 data: 0.0879 max mem: 9390 +Train: [13] [ 200/6250] eta: 0:18:30 lr: 0.000123 grad: 0.0647 (0.0753) loss: 0.8480 (0.8478) time: 0.1651 data: 0.0850 max mem: 9390 +Train: [13] [ 300/6250] eta: 0:17:39 lr: 0.000123 grad: 0.0638 (0.0743) loss: 0.8398 (0.8469) time: 0.2064 data: 0.0772 max mem: 9390 +Train: [13] [ 400/6250] eta: 0:17:33 lr: 0.000123 grad: 0.0656 (0.0732) loss: 0.8449 (0.8465) time: 0.2083 data: 0.1151 max mem: 9390 +Train: [13] [ 500/6250] eta: 0:17:14 lr: 0.000123 grad: 0.0640 (0.0726) loss: 0.8418 (0.8463) time: 0.1067 data: 0.0248 max mem: 9390 +Train: [13] [ 600/6250] eta: 0:17:01 lr: 0.000123 grad: 0.0614 (0.0711) loss: 0.8486 (0.8457) time: 0.1003 data: 0.0114 max mem: 9390 +Train: [13] [ 700/6250] eta: 0:16:33 lr: 0.000123 grad: 0.0635 (0.0700) loss: 0.8473 (0.8460) time: 0.1397 data: 0.0381 max mem: 9390 +Train: [13] [ 800/6250] eta: 0:15:55 lr: 0.000123 grad: 0.0636 (0.0695) loss: 0.8459 (0.8459) time: 0.1429 data: 0.0618 max mem: 9390 +Train: [13] [ 900/6250] eta: 0:15:18 lr: 0.000123 grad: 0.0635 (0.0691) loss: 0.8429 (0.8457) time: 0.1601 data: 0.0817 max mem: 9390 +Train: [13] [1000/6250] eta: 0:14:40 lr: 0.000123 grad: 0.0629 (0.0685) loss: 0.8370 (0.8455) time: 0.1219 data: 0.0448 max mem: 9390 +Train: [13] [1100/6250] eta: 0:14:05 lr: 0.000123 grad: 0.0630 (0.0682) loss: 0.8427 (0.8453) time: 0.1162 data: 0.0295 max mem: 9390 +Train: [13] [1200/6250] eta: 0:13:37 lr: 0.000123 grad: 0.0656 (0.0680) loss: 0.8475 (0.8452) time: 0.1368 data: 0.0624 max mem: 9390 +Train: [13] [1300/6250] eta: 0:13:08 lr: 0.000123 grad: 0.0617 (0.0677) loss: 0.8420 (0.8450) time: 0.1346 data: 0.0573 max mem: 9390 +Train: [13] [1400/6250] eta: 0:12:44 lr: 0.000123 grad: 0.0625 (0.0675) loss: 0.8446 (0.8449) time: 0.1257 data: 0.0423 max mem: 9390 +Train: [13] [1500/6250] eta: 0:12:18 lr: 0.000123 grad: 0.0592 (0.0672) loss: 0.8469 (0.8449) time: 0.1240 data: 0.0460 max mem: 9390 +Train: [13] [1600/6250] eta: 0:11:55 lr: 0.000123 grad: 0.0627 (0.0669) loss: 0.8443 (0.8448) time: 0.1310 data: 0.0477 max mem: 9390 +Train: [13] [1700/6250] eta: 0:11:34 lr: 0.000123 grad: 0.0637 (0.0667) loss: 0.8405 (0.8448) time: 0.1202 data: 0.0400 max mem: 9390 +Train: [13] [1800/6250] eta: 0:11:13 lr: 0.000123 grad: 0.0617 (0.0667) loss: 0.8447 (0.8448) time: 0.1317 data: 0.0554 max mem: 9390 +Train: [13] [1900/6250] eta: 0:10:55 lr: 0.000123 grad: 0.0601 (0.0666) loss: 0.8425 (0.8447) time: 0.1358 data: 0.0568 max mem: 9390 +Train: [13] [2000/6250] eta: 0:10:35 lr: 0.000123 grad: 0.0624 (0.0664) loss: 0.8440 (0.8446) time: 0.1244 data: 0.0477 max mem: 9390 +Train: [13] [2100/6250] eta: 0:10:16 lr: 0.000123 grad: 0.0627 (0.0666) loss: 0.8403 (0.8445) time: 0.1330 data: 0.0570 max mem: 9390 +Train: [13] [2200/6250] eta: 0:09:59 lr: 0.000123 grad: 0.0616 (0.0665) loss: 0.8417 (0.8443) time: 0.1380 data: 0.0615 max mem: 9390 +Train: [13] [2300/6250] eta: 0:09:41 lr: 0.000123 grad: 0.0623 (0.0664) loss: 0.8394 (0.8442) time: 0.1471 data: 0.0653 max mem: 9390 +Train: [13] [2400/6250] eta: 0:09:24 lr: 0.000123 grad: 0.0594 (0.0664) loss: 0.8396 (0.8440) time: 0.1382 data: 0.0604 max mem: 9390 +Train: [13] [2500/6250] eta: 0:09:08 lr: 0.000123 grad: 0.0641 (0.0664) loss: 0.8417 (0.8439) time: 0.1175 data: 0.0342 max mem: 9390 +Train: [13] [2600/6250] eta: 0:08:51 lr: 0.000123 grad: 0.0618 (0.0663) loss: 0.8453 (0.8437) time: 0.1468 data: 0.0641 max mem: 9390 +Train: [13] [2700/6250] eta: 0:08:34 lr: 0.000123 grad: 0.0605 (0.0662) loss: 0.8415 (0.8437) time: 0.1338 data: 0.0544 max mem: 9390 +Train: [13] [2800/6250] eta: 0:08:17 lr: 0.000123 grad: 0.0642 (0.0661) loss: 0.8442 (0.8437) time: 0.1279 data: 0.0495 max mem: 9390 +Train: [13] [2900/6250] eta: 0:08:01 lr: 0.000123 grad: 0.0648 (0.0661) loss: 0.8393 (0.8436) time: 0.1292 data: 0.0477 max mem: 9390 +Train: [13] [3000/6250] eta: 0:07:46 lr: 0.000123 grad: 0.0654 (0.0660) loss: 0.8447 (0.8435) time: 0.1218 data: 0.0381 max mem: 9390 +Train: [13] [3100/6250] eta: 0:07:31 lr: 0.000123 grad: 0.0648 (0.0660) loss: 0.8399 (0.8434) time: 0.1323 data: 0.0548 max mem: 9390 +Train: [13] [3200/6250] eta: 0:07:15 lr: 0.000123 grad: 0.0617 (0.0660) loss: 0.8445 (0.8434) time: 0.1329 data: 0.0602 max mem: 9390 +Train: [13] [3300/6250] eta: 0:07:01 lr: 0.000123 grad: 0.0622 (0.0659) loss: 0.8475 (0.8434) time: 0.0967 data: 0.0158 max mem: 9390 +Train: [13] [3400/6250] eta: 0:06:46 lr: 0.000123 grad: 0.0596 (0.0660) loss: 0.8453 (0.8434) time: 0.1308 data: 0.0510 max mem: 9390 +Train: [13] [3500/6250] eta: 0:06:31 lr: 0.000123 grad: 0.0630 (0.0660) loss: 0.8440 (0.8434) time: 0.1313 data: 0.0565 max mem: 9390 +Train: [13] [3600/6250] eta: 0:06:16 lr: 0.000123 grad: 0.0627 (0.0660) loss: 0.8436 (0.8434) time: 0.1191 data: 0.0444 max mem: 9390 +Train: [13] [3700/6250] eta: 0:06:01 lr: 0.000122 grad: 0.0645 (0.0659) loss: 0.8414 (0.8434) time: 0.1275 data: 0.0476 max mem: 9390 +Train: [13] [3800/6250] eta: 0:05:47 lr: 0.000122 grad: 0.0603 (0.0659) loss: 0.8441 (0.8434) time: 0.1283 data: 0.0534 max mem: 9390 +Train: [13] [3900/6250] eta: 0:05:32 lr: 0.000122 grad: 0.0637 (0.0658) loss: 0.8451 (0.8435) time: 0.1242 data: 0.0466 max mem: 9390 +Train: [13] [4000/6250] eta: 0:05:17 lr: 0.000122 grad: 0.0629 (0.0658) loss: 0.8377 (0.8434) time: 0.1306 data: 0.0520 max mem: 9390 +Train: [13] [4100/6250] eta: 0:05:03 lr: 0.000122 grad: 0.0618 (0.0658) loss: 0.8425 (0.8434) time: 0.1260 data: 0.0503 max mem: 9390 +Train: [13] [4200/6250] eta: 0:04:48 lr: 0.000122 grad: 0.0664 (0.0657) loss: 0.8411 (0.8434) time: 0.1357 data: 0.0601 max mem: 9390 +Train: [13] [4300/6250] eta: 0:04:34 lr: 0.000122 grad: 0.0639 (0.0657) loss: 0.8454 (0.8434) time: 0.1358 data: 0.0619 max mem: 9390 +Train: [13] [4400/6250] eta: 0:04:20 lr: 0.000122 grad: 0.0610 (0.0657) loss: 0.8475 (0.8434) time: 0.1333 data: 0.0557 max mem: 9390 +Train: [13] [4500/6250] eta: 0:04:05 lr: 0.000122 grad: 0.0614 (0.0657) loss: 0.8416 (0.8435) time: 0.1272 data: 0.0441 max mem: 9390 +Train: [13] [4600/6250] eta: 0:03:51 lr: 0.000122 grad: 0.0594 (0.0656) loss: 0.8468 (0.8435) time: 0.1395 data: 0.0623 max mem: 9390 +Train: [13] [4700/6250] eta: 0:03:37 lr: 0.000122 grad: 0.0596 (0.0656) loss: 0.8457 (0.8436) time: 0.1303 data: 0.0483 max mem: 9390 +Train: [13] [4800/6250] eta: 0:03:23 lr: 0.000122 grad: 0.0655 (0.0655) loss: 0.8446 (0.8436) time: 0.1859 data: 0.1155 max mem: 9390 +Train: [13] [4900/6250] eta: 0:03:08 lr: 0.000122 grad: 0.0618 (0.0655) loss: 0.8490 (0.8437) time: 0.1338 data: 0.0592 max mem: 9390 +Train: [13] [5000/6250] eta: 0:02:54 lr: 0.000122 grad: 0.0646 (0.0655) loss: 0.8458 (0.8437) time: 0.1056 data: 0.0271 max mem: 9390 +Train: [13] [5100/6250] eta: 0:02:40 lr: 0.000122 grad: 0.0624 (0.0655) loss: 0.8444 (0.8437) time: 0.1484 data: 0.0714 max mem: 9390 +Train: [13] [5200/6250] eta: 0:02:26 lr: 0.000122 grad: 0.0595 (0.0656) loss: 0.8475 (0.8437) time: 0.1330 data: 0.0534 max mem: 9390 +Train: [13] [5300/6250] eta: 0:02:12 lr: 0.000122 grad: 0.0619 (0.0656) loss: 0.8438 (0.8438) time: 0.1500 data: 0.0745 max mem: 9390 +Train: [13] [5400/6250] eta: 0:01:58 lr: 0.000122 grad: 0.0623 (0.0656) loss: 0.8455 (0.8438) time: 0.1593 data: 0.0783 max mem: 9390 +Train: [13] [5500/6250] eta: 0:01:44 lr: 0.000122 grad: 0.0623 (0.0655) loss: 0.8477 (0.8439) time: 0.1419 data: 0.0646 max mem: 9390 +Train: [13] [5600/6250] eta: 0:01:30 lr: 0.000122 grad: 0.0643 (0.0655) loss: 0.8442 (0.8439) time: 0.1304 data: 0.0493 max mem: 9390 +Train: [13] [5700/6250] eta: 0:01:16 lr: 0.000122 grad: 0.0608 (0.0655) loss: 0.8454 (0.8439) time: 0.1146 data: 0.0357 max mem: 9390 +Train: [13] [5800/6250] eta: 0:01:02 lr: 0.000122 grad: 0.0615 (0.0655) loss: 0.8458 (0.8439) time: 0.1206 data: 0.0422 max mem: 9390 +Train: [13] [5900/6250] eta: 0:00:48 lr: 0.000122 grad: 0.0607 (0.0655) loss: 0.8423 (0.8439) time: 0.1352 data: 0.0534 max mem: 9390 +Train: [13] [6000/6250] eta: 0:00:34 lr: 0.000122 grad: 0.0620 (0.0655) loss: 0.8439 (0.8439) time: 0.1269 data: 0.0479 max mem: 9390 +Train: [13] [6100/6250] eta: 0:00:20 lr: 0.000122 grad: 0.0636 (0.0655) loss: 0.8460 (0.8440) time: 0.1362 data: 0.0617 max mem: 9390 +Train: [13] [6200/6250] eta: 0:00:06 lr: 0.000122 grad: 0.0653 (0.0654) loss: 0.8434 (0.8440) time: 0.1571 data: 0.0778 max mem: 9390 +Train: [13] [6249/6250] eta: 0:00:00 lr: 0.000122 grad: 0.0627 (0.0654) loss: 0.8447 (0.8440) time: 0.1403 data: 0.0547 max mem: 9390 +Train: [13] Total time: 0:14:33 (0.1397 s / it) +Averaged stats: lr: 0.000122 grad: 0.0627 (0.0654) loss: 0.8447 (0.8440) +Eval (hcp-train-subset): [13] [ 0/62] eta: 0:03:53 loss: 0.8612 (0.8612) time: 3.7586 data: 3.6502 max mem: 9390 +Eval (hcp-train-subset): [13] [61/62] eta: 0:00:00 loss: 0.8499 (0.8506) time: 0.2051 data: 0.1745 max mem: 9390 +Eval (hcp-train-subset): [13] Total time: 0:00:14 (0.2417 s / it) +Averaged stats (hcp-train-subset): loss: 0.8499 (0.8506) +Eval (hcp-val): [13] [ 0/62] eta: 0:02:56 loss: 0.8437 (0.8437) time: 2.8517 data: 2.8027 max mem: 9390 +Eval (hcp-val): [13] [61/62] eta: 0:00:00 loss: 0.8427 (0.8447) time: 0.1163 data: 0.0917 max mem: 9390 +Eval (hcp-val): [13] Total time: 0:00:11 (0.1927 s / it) +Averaged stats (hcp-val): loss: 0.8427 (0.8447) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +Train: [14] [ 0/6250] eta: 5:57:57 lr: 0.000122 grad: 0.0517 (0.0517) loss: 0.8755 (0.8755) time: 3.4364 data: 3.1882 max mem: 9390 +Train: [14] [ 100/6250] eta: 0:19:06 lr: 0.000122 grad: 0.0570 (0.0712) loss: 0.8584 (0.8545) time: 0.1432 data: 0.0622 max mem: 9390 +Train: [14] [ 200/6250] eta: 0:16:33 lr: 0.000122 grad: 0.0645 (0.0683) loss: 0.8419 (0.8504) time: 0.1257 data: 0.0386 max mem: 9390 +Train: [14] [ 300/6250] eta: 0:15:23 lr: 0.000122 grad: 0.0697 (0.0697) loss: 0.8462 (0.8477) time: 0.1412 data: 0.0654 max mem: 9390 +Train: [14] [ 400/6250] eta: 0:14:30 lr: 0.000122 grad: 0.0648 (0.0693) loss: 0.8403 (0.8460) time: 0.1203 data: 0.0264 max mem: 9390 +Train: [14] [ 500/6250] eta: 0:13:48 lr: 0.000122 grad: 0.0623 (0.0683) loss: 0.8464 (0.8454) time: 0.1247 data: 0.0447 max mem: 9390 +Train: [14] [ 600/6250] eta: 0:13:20 lr: 0.000122 grad: 0.0654 (0.0680) loss: 0.8373 (0.8444) time: 0.1348 data: 0.0518 max mem: 9390 +Train: [14] [ 700/6250] eta: 0:12:58 lr: 0.000122 grad: 0.0688 (0.0679) loss: 0.8417 (0.8440) time: 0.1496 data: 0.0642 max mem: 9390 +Train: [14] [ 800/6250] eta: 0:12:44 lr: 0.000122 grad: 0.0633 (0.0679) loss: 0.8395 (0.8432) time: 0.1403 data: 0.0473 max mem: 9390 +Train: [14] [ 900/6250] eta: 0:12:36 lr: 0.000122 grad: 0.0643 (0.0676) loss: 0.8383 (0.8428) time: 0.1328 data: 0.0452 max mem: 9390 +Train: [14] [1000/6250] eta: 0:12:18 lr: 0.000122 grad: 0.0670 (0.0675) loss: 0.8339 (0.8421) time: 0.1355 data: 0.0522 max mem: 9390 +Train: [14] [1100/6250] eta: 0:11:59 lr: 0.000122 grad: 0.0663 (0.0675) loss: 0.8371 (0.8416) time: 0.1286 data: 0.0493 max mem: 9390 +Train: [14] [1200/6250] eta: 0:11:45 lr: 0.000122 grad: 0.0629 (0.0673) loss: 0.8373 (0.8415) time: 0.1317 data: 0.0498 max mem: 9390 +Train: [14] [1300/6250] eta: 0:11:26 lr: 0.000122 grad: 0.0629 (0.0671) loss: 0.8423 (0.8412) time: 0.1102 data: 0.0283 max mem: 9390 +Train: [14] [1400/6250] eta: 0:11:13 lr: 0.000122 grad: 0.0620 (0.0672) loss: 0.8425 (0.8412) time: 0.1357 data: 0.0594 max mem: 9390 +Train: [14] [1500/6250] eta: 0:10:58 lr: 0.000122 grad: 0.0633 (0.0671) loss: 0.8381 (0.8410) time: 0.1494 data: 0.0726 max mem: 9390 +Train: [14] [1600/6250] eta: 0:10:44 lr: 0.000122 grad: 0.0615 (0.0670) loss: 0.8422 (0.8408) time: 0.1540 data: 0.0795 max mem: 9390 +Train: [14] [1700/6250] eta: 0:10:27 lr: 0.000122 grad: 0.0670 (0.0671) loss: 0.8382 (0.8408) time: 0.1338 data: 0.0549 max mem: 9390 +Train: [14] [1800/6250] eta: 0:10:12 lr: 0.000122 grad: 0.0630 (0.0670) loss: 0.8386 (0.8406) time: 0.1254 data: 0.0472 max mem: 9390 +Train: [14] [1900/6250] eta: 0:09:57 lr: 0.000122 grad: 0.0626 (0.0671) loss: 0.8351 (0.8405) time: 0.1467 data: 0.0682 max mem: 9390 +Train: [14] [2000/6250] eta: 0:09:42 lr: 0.000122 grad: 0.0609 (0.0671) loss: 0.8396 (0.8405) time: 0.1255 data: 0.0516 max mem: 9390 +Train: [14] [2100/6250] eta: 0:09:27 lr: 0.000122 grad: 0.0623 (0.0670) loss: 0.8362 (0.8405) time: 0.1194 data: 0.0379 max mem: 9390 +Train: [14] [2200/6250] eta: 0:09:13 lr: 0.000122 grad: 0.0617 (0.0669) loss: 0.8399 (0.8405) time: 0.1432 data: 0.0615 max mem: 9390 +Train: [14] [2300/6250] eta: 0:08:58 lr: 0.000122 grad: 0.0624 (0.0668) loss: 0.8389 (0.8405) time: 0.1228 data: 0.0448 max mem: 9390 +Train: [14] [2400/6250] eta: 0:08:45 lr: 0.000122 grad: 0.0580 (0.0667) loss: 0.8453 (0.8405) time: 0.1583 data: 0.0817 max mem: 9390 +Train: [14] [2500/6250] eta: 0:08:30 lr: 0.000122 grad: 0.0617 (0.0666) loss: 0.8430 (0.8405) time: 0.1464 data: 0.0673 max mem: 9390 +Train: [14] [2600/6250] eta: 0:08:16 lr: 0.000122 grad: 0.0604 (0.0665) loss: 0.8404 (0.8406) time: 0.1417 data: 0.0598 max mem: 9390 +Train: [14] [2700/6250] eta: 0:08:02 lr: 0.000122 grad: 0.0595 (0.0664) loss: 0.8429 (0.8407) time: 0.1362 data: 0.0592 max mem: 9390 +Train: [14] [2800/6250] eta: 0:07:48 lr: 0.000122 grad: 0.0619 (0.0663) loss: 0.8429 (0.8407) time: 0.1412 data: 0.0618 max mem: 9390 +Train: [14] [2900/6250] eta: 0:07:34 lr: 0.000122 grad: 0.0673 (0.0663) loss: 0.8402 (0.8408) time: 0.1373 data: 0.0535 max mem: 9390 +Train: [14] [3000/6250] eta: 0:07:20 lr: 0.000122 grad: 0.0655 (0.0662) loss: 0.8412 (0.8408) time: 0.1098 data: 0.0337 max mem: 9390 +Train: [14] [3100/6250] eta: 0:07:06 lr: 0.000122 grad: 0.0620 (0.0661) loss: 0.8453 (0.8408) time: 0.1489 data: 0.0735 max mem: 9390 +Train: [14] [3200/6250] eta: 0:06:52 lr: 0.000122 grad: 0.0638 (0.0661) loss: 0.8428 (0.8408) time: 0.1345 data: 0.0558 max mem: 9390 +Train: [14] [3300/6250] eta: 0:06:39 lr: 0.000122 grad: 0.0618 (0.0660) loss: 0.8404 (0.8409) time: 0.1405 data: 0.0598 max mem: 9390 +Train: [14] [3400/6250] eta: 0:06:25 lr: 0.000122 grad: 0.0603 (0.0659) loss: 0.8383 (0.8409) time: 0.1726 data: 0.0936 max mem: 9390 +Train: [14] [3500/6250] eta: 0:06:11 lr: 0.000122 grad: 0.0650 (0.0660) loss: 0.8393 (0.8409) time: 0.1325 data: 0.0497 max mem: 9390 +Train: [14] [3600/6250] eta: 0:05:58 lr: 0.000122 grad: 0.0615 (0.0661) loss: 0.8446 (0.8409) time: 0.1286 data: 0.0527 max mem: 9390 +Train: [14] [3700/6250] eta: 0:05:44 lr: 0.000122 grad: 0.0630 (0.0661) loss: 0.8393 (0.8409) time: 0.1500 data: 0.0700 max mem: 9390 +Train: [14] [3800/6250] eta: 0:05:30 lr: 0.000122 grad: 0.0673 (0.0662) loss: 0.8396 (0.8409) time: 0.1494 data: 0.0697 max mem: 9390 +Train: [14] [3900/6250] eta: 0:05:17 lr: 0.000122 grad: 0.0622 (0.0661) loss: 0.8403 (0.8409) time: 0.1291 data: 0.0460 max mem: 9390 +Train: [14] [4000/6250] eta: 0:05:03 lr: 0.000122 grad: 0.0651 (0.0662) loss: 0.8370 (0.8409) time: 0.1303 data: 0.0520 max mem: 9390 +Train: [14] [4100/6250] eta: 0:04:50 lr: 0.000122 grad: 0.0609 (0.0662) loss: 0.8386 (0.8408) time: 0.1311 data: 0.0539 max mem: 9390 +Train: [14] [4200/6250] eta: 0:04:37 lr: 0.000122 grad: 0.0642 (0.0661) loss: 0.8436 (0.8408) time: 0.1393 data: 0.0616 max mem: 9390 +Train: [14] [4300/6250] eta: 0:04:23 lr: 0.000122 grad: 0.0688 (0.0661) loss: 0.8417 (0.8408) time: 0.1270 data: 0.0493 max mem: 9390 +Train: [14] [4400/6250] eta: 0:04:10 lr: 0.000122 grad: 0.0636 (0.0662) loss: 0.8433 (0.8408) time: 0.1423 data: 0.0657 max mem: 9390 +Train: [14] [4500/6250] eta: 0:03:56 lr: 0.000122 grad: 0.0654 (0.0662) loss: 0.8402 (0.8408) time: 0.1322 data: 0.0521 max mem: 9390 +Train: [14] [4600/6250] eta: 0:03:43 lr: 0.000122 grad: 0.0608 (0.0661) loss: 0.8409 (0.8409) time: 0.1337 data: 0.0553 max mem: 9390 +Train: [14] [4700/6250] eta: 0:03:29 lr: 0.000122 grad: 0.0664 (0.0661) loss: 0.8390 (0.8409) time: 0.1301 data: 0.0496 max mem: 9390 +Train: [14] [4800/6250] eta: 0:03:16 lr: 0.000122 grad: 0.0641 (0.0660) loss: 0.8430 (0.8409) time: 0.1271 data: 0.0443 max mem: 9390 +Train: [14] [4900/6250] eta: 0:03:02 lr: 0.000122 grad: 0.0607 (0.0660) loss: 0.8431 (0.8410) time: 0.1296 data: 0.0500 max mem: 9390 +Train: [14] [5000/6250] eta: 0:02:48 lr: 0.000122 grad: 0.0605 (0.0659) loss: 0.8421 (0.8410) time: 0.1324 data: 0.0538 max mem: 9390 +Train: [14] [5100/6250] eta: 0:02:35 lr: 0.000122 grad: 0.0588 (0.0659) loss: 0.8431 (0.8410) time: 0.1351 data: 0.0594 max mem: 9390 +Train: [14] [5200/6250] eta: 0:02:21 lr: 0.000122 grad: 0.0609 (0.0658) loss: 0.8432 (0.8411) time: 0.1405 data: 0.0624 max mem: 9390 +Train: [14] [5300/6250] eta: 0:02:08 lr: 0.000122 grad: 0.0603 (0.0658) loss: 0.8435 (0.8412) time: 0.1442 data: 0.0621 max mem: 9390 +Train: [14] [5400/6250] eta: 0:01:54 lr: 0.000122 grad: 0.0628 (0.0658) loss: 0.8439 (0.8412) time: 0.1433 data: 0.0675 max mem: 9390 +Train: [14] [5500/6250] eta: 0:01:41 lr: 0.000122 grad: 0.0619 (0.0657) loss: 0.8424 (0.8412) time: 0.1324 data: 0.0535 max mem: 9390 +Train: [14] [5600/6250] eta: 0:01:27 lr: 0.000122 grad: 0.0605 (0.0657) loss: 0.8409 (0.8413) time: 0.1515 data: 0.0733 max mem: 9390 +Train: [14] [5700/6250] eta: 0:01:14 lr: 0.000122 grad: 0.0620 (0.0657) loss: 0.8387 (0.8413) time: 0.1316 data: 0.0518 max mem: 9390 +Train: [14] [5800/6250] eta: 0:01:00 lr: 0.000122 grad: 0.0653 (0.0657) loss: 0.8413 (0.8413) time: 0.1355 data: 0.0592 max mem: 9390 +Train: [14] [5900/6250] eta: 0:00:47 lr: 0.000122 grad: 0.0607 (0.0657) loss: 0.8463 (0.8414) time: 0.1441 data: 0.0709 max mem: 9390 +Train: [14] [6000/6250] eta: 0:00:33 lr: 0.000122 grad: 0.0652 (0.0656) loss: 0.8465 (0.8414) time: 0.1409 data: 0.0614 max mem: 9390 +Train: [14] [6100/6250] eta: 0:00:20 lr: 0.000122 grad: 0.0601 (0.0656) loss: 0.8484 (0.8414) time: 0.1279 data: 0.0491 max mem: 9390 +Train: [14] [6200/6250] eta: 0:00:06 lr: 0.000122 grad: 0.0632 (0.0656) loss: 0.8455 (0.8414) time: 0.1305 data: 0.0550 max mem: 9390 +Train: [14] [6249/6250] eta: 0:00:00 lr: 0.000122 grad: 0.0617 (0.0656) loss: 0.8466 (0.8414) time: 0.1354 data: 0.0597 max mem: 9390 +Train: [14] Total time: 0:14:07 (0.1357 s / it) +Averaged stats: lr: 0.000122 grad: 0.0617 (0.0656) loss: 0.8466 (0.8414) +Eval (hcp-train-subset): [14] [ 0/62] eta: 0:03:07 loss: 0.8618 (0.8618) time: 3.0245 data: 2.9360 max mem: 9390 +Eval (hcp-train-subset): [14] [61/62] eta: 0:00:00 loss: 0.8479 (0.8483) time: 0.1259 data: 0.1009 max mem: 9390 +Eval (hcp-train-subset): [14] Total time: 0:00:12 (0.2061 s / it) +Averaged stats (hcp-train-subset): loss: 0.8479 (0.8483) +Making plots (hcp-train-subset): example=19 +Eval (hcp-val): [14] [ 0/62] eta: 0:04:16 loss: 0.8420 (0.8420) time: 4.1380 data: 4.1078 max mem: 9390 +Eval (hcp-val): [14] [61/62] eta: 0:00:00 loss: 0.8437 (0.8438) time: 0.1279 data: 0.1034 max mem: 9390 +Eval (hcp-val): [14] Total time: 0:00:13 (0.2128 s / it) +Averaged stats (hcp-val): loss: 0.8437 (0.8438) +Making plots (hcp-val): example=11 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +Train: [15] [ 0/6250] eta: 9:14:44 lr: 0.000122 grad: 0.0569 (0.0569) loss: 0.8306 (0.8306) time: 5.3256 data: 5.2310 max mem: 9390 +Train: [15] [ 100/6250] eta: 0:19:00 lr: 0.000122 grad: 0.0657 (0.0662) loss: 0.8487 (0.8496) time: 0.1316 data: 0.0527 max mem: 9390 +Train: [15] [ 200/6250] eta: 0:16:31 lr: 0.000122 grad: 0.0687 (0.0671) loss: 0.8432 (0.8469) time: 0.1327 data: 0.0525 max mem: 9390 +Train: [15] [ 300/6250] eta: 0:15:26 lr: 0.000122 grad: 0.0663 (0.0672) loss: 0.8438 (0.8443) time: 0.1420 data: 0.0651 max mem: 9390 +Train: [15] [ 400/6250] eta: 0:14:43 lr: 0.000122 grad: 0.0618 (0.0663) loss: 0.8380 (0.8432) time: 0.1274 data: 0.0390 max mem: 9390 +Train: [15] [ 500/6250] eta: 0:14:07 lr: 0.000122 grad: 0.0620 (0.0661) loss: 0.8424 (0.8427) time: 0.1392 data: 0.0573 max mem: 9390 +Train: [15] [ 600/6250] eta: 0:13:40 lr: 0.000122 grad: 0.0665 (0.0656) loss: 0.8419 (0.8428) time: 0.1376 data: 0.0470 max mem: 9390 +Train: [15] [ 700/6250] eta: 0:13:29 lr: 0.000122 grad: 0.0611 (0.0653) loss: 0.8435 (0.8430) time: 0.1603 data: 0.0744 max mem: 9390 +Train: [15] [ 800/6250] eta: 0:13:15 lr: 0.000122 grad: 0.0615 (0.0649) loss: 0.8413 (0.8432) time: 0.1542 data: 0.0640 max mem: 9390 +Train: [15] [ 900/6250] eta: 0:12:56 lr: 0.000122 grad: 0.0632 (0.0647) loss: 0.8336 (0.8430) time: 0.1533 data: 0.0751 max mem: 9390 +Train: [15] [1000/6250] eta: 0:12:33 lr: 0.000122 grad: 0.0596 (0.0645) loss: 0.8428 (0.8429) time: 0.1105 data: 0.0251 max mem: 9390 +Train: [15] [1100/6250] eta: 0:12:19 lr: 0.000121 grad: 0.0629 (0.0645) loss: 0.8448 (0.8429) time: 0.1306 data: 0.0503 max mem: 9390 +Train: [15] [1200/6250] eta: 0:12:04 lr: 0.000121 grad: 0.0622 (0.0644) loss: 0.8411 (0.8429) time: 0.1484 data: 0.0680 max mem: 9390 +Train: [15] [1300/6250] eta: 0:11:49 lr: 0.000121 grad: 0.0637 (0.0642) loss: 0.8447 (0.8429) time: 0.1640 data: 0.0853 max mem: 9390 +Train: [15] [1400/6250] eta: 0:11:29 lr: 0.000121 grad: 0.0598 (0.0640) loss: 0.8387 (0.8429) time: 0.1264 data: 0.0417 max mem: 9390 +Train: [15] [1500/6250] eta: 0:11:13 lr: 0.000121 grad: 0.0617 (0.0639) loss: 0.8385 (0.8428) time: 0.1342 data: 0.0564 max mem: 9390 +Train: [15] [1600/6250] eta: 0:10:57 lr: 0.000121 grad: 0.0603 (0.0638) loss: 0.8387 (0.8426) time: 0.1376 data: 0.0519 max mem: 9390 +Train: [15] [1700/6250] eta: 0:10:41 lr: 0.000121 grad: 0.0642 (0.0638) loss: 0.8346 (0.8424) time: 0.1290 data: 0.0453 max mem: 9390 +Train: [15] [1800/6250] eta: 0:10:26 lr: 0.000121 grad: 0.0627 (0.0638) loss: 0.8405 (0.8423) time: 0.1464 data: 0.0640 max mem: 9390 +Train: [15] [1900/6250] eta: 0:10:10 lr: 0.000121 grad: 0.0612 (0.0638) loss: 0.8413 (0.8422) time: 0.1401 data: 0.0615 max mem: 9390 +Train: [15] [2000/6250] eta: 0:09:56 lr: 0.000121 grad: 0.0593 (0.0637) loss: 0.8447 (0.8421) time: 0.1517 data: 0.0755 max mem: 9390 +Train: [15] [2100/6250] eta: 0:09:41 lr: 0.000121 grad: 0.0593 (0.0636) loss: 0.8433 (0.8421) time: 0.1401 data: 0.0596 max mem: 9390 +Train: [15] [2200/6250] eta: 0:09:25 lr: 0.000121 grad: 0.0645 (0.0635) loss: 0.8470 (0.8421) time: 0.1288 data: 0.0419 max mem: 9390 +Train: [15] [2300/6250] eta: 0:09:11 lr: 0.000121 grad: 0.0621 (0.0636) loss: 0.8458 (0.8421) time: 0.1224 data: 0.0398 max mem: 9390 +Train: [15] [2400/6250] eta: 0:08:56 lr: 0.000121 grad: 0.0612 (0.0635) loss: 0.8432 (0.8422) time: 0.1445 data: 0.0672 max mem: 9390 +Train: [15] [2500/6250] eta: 0:08:40 lr: 0.000121 grad: 0.0620 (0.0635) loss: 0.8433 (0.8422) time: 0.1258 data: 0.0466 max mem: 9390 +Train: [15] [2600/6250] eta: 0:08:26 lr: 0.000121 grad: 0.0594 (0.0634) loss: 0.8465 (0.8422) time: 0.1241 data: 0.0428 max mem: 9390 +Train: [15] [2700/6250] eta: 0:08:11 lr: 0.000121 grad: 0.0609 (0.0633) loss: 0.8430 (0.8423) time: 0.1292 data: 0.0538 max mem: 9390 +Train: [15] [2800/6250] eta: 0:07:56 lr: 0.000121 grad: 0.0596 (0.0633) loss: 0.8454 (0.8423) time: 0.1408 data: 0.0556 max mem: 9390 +Train: [15] [2900/6250] eta: 0:07:41 lr: 0.000121 grad: 0.0603 (0.0633) loss: 0.8440 (0.8423) time: 0.1173 data: 0.0435 max mem: 9390 +Train: [15] [3000/6250] eta: 0:07:27 lr: 0.000121 grad: 0.0629 (0.0633) loss: 0.8430 (0.8424) time: 0.1462 data: 0.0691 max mem: 9390 +Train: [15] [3100/6250] eta: 0:07:13 lr: 0.000121 grad: 0.0596 (0.0633) loss: 0.8359 (0.8424) time: 0.1289 data: 0.0470 max mem: 9390 +Train: [15] [3200/6250] eta: 0:06:58 lr: 0.000121 grad: 0.0626 (0.0633) loss: 0.8434 (0.8424) time: 0.1286 data: 0.0443 max mem: 9390 +Train: [15] [3300/6250] eta: 0:06:44 lr: 0.000121 grad: 0.0595 (0.0632) loss: 0.8434 (0.8424) time: 0.1385 data: 0.0645 max mem: 9390 +Train: [15] [3400/6250] eta: 0:06:30 lr: 0.000121 grad: 0.0604 (0.0633) loss: 0.8456 (0.8424) time: 0.1284 data: 0.0470 max mem: 9390 +Train: [15] [3500/6250] eta: 0:06:16 lr: 0.000121 grad: 0.0617 (0.0633) loss: 0.8451 (0.8425) time: 0.1333 data: 0.0540 max mem: 9390 +Train: [15] [3600/6250] eta: 0:06:02 lr: 0.000121 grad: 0.0613 (0.0632) loss: 0.8453 (0.8426) time: 0.1425 data: 0.0645 max mem: 9390 +Train: [15] [3700/6250] eta: 0:05:48 lr: 0.000121 grad: 0.0601 (0.0631) loss: 0.8396 (0.8426) time: 0.1246 data: 0.0367 max mem: 9390 +Train: [15] [3800/6250] eta: 0:05:34 lr: 0.000121 grad: 0.0616 (0.0631) loss: 0.8388 (0.8426) time: 0.1299 data: 0.0467 max mem: 9390 +Train: [15] [3900/6250] eta: 0:05:20 lr: 0.000121 grad: 0.0633 (0.0631) loss: 0.8410 (0.8426) time: 0.1347 data: 0.0562 max mem: 9390 +Train: [15] [4000/6250] eta: 0:05:06 lr: 0.000121 grad: 0.0617 (0.0630) loss: 0.8470 (0.8426) time: 0.1351 data: 0.0579 max mem: 9390 +Train: [15] [4100/6250] eta: 0:04:52 lr: 0.000121 grad: 0.0571 (0.0630) loss: 0.8425 (0.8426) time: 0.1194 data: 0.0422 max mem: 9390 +Train: [15] [4200/6250] eta: 0:04:39 lr: 0.000121 grad: 0.0625 (0.0630) loss: 0.8428 (0.8426) time: 0.1165 data: 0.0423 max mem: 9390 +Train: [15] [4300/6250] eta: 0:04:25 lr: 0.000121 grad: 0.0615 (0.0630) loss: 0.8413 (0.8426) time: 0.1326 data: 0.0479 max mem: 9390 +Train: [15] [4400/6250] eta: 0:04:11 lr: 0.000121 grad: 0.0627 (0.0631) loss: 0.8397 (0.8426) time: 0.1356 data: 0.0555 max mem: 9390 +Train: [15] [4500/6250] eta: 0:03:58 lr: 0.000121 grad: 0.0628 (0.0631) loss: 0.8398 (0.8425) time: 0.1470 data: 0.0690 max mem: 9390 +Train: [15] [4600/6250] eta: 0:03:44 lr: 0.000121 grad: 0.0619 (0.0631) loss: 0.8422 (0.8425) time: 0.1319 data: 0.0518 max mem: 9390 +Train: [15] [4700/6250] eta: 0:03:30 lr: 0.000121 grad: 0.0610 (0.0631) loss: 0.8443 (0.8426) time: 0.1444 data: 0.0681 max mem: 9390 +Train: [15] [4800/6250] eta: 0:03:17 lr: 0.000121 grad: 0.0576 (0.0630) loss: 0.8424 (0.8426) time: 0.1413 data: 0.0613 max mem: 9390 +Train: [15] [4900/6250] eta: 0:03:03 lr: 0.000121 grad: 0.0592 (0.0630) loss: 0.8441 (0.8426) time: 0.1395 data: 0.0578 max mem: 9390 +Train: [15] [5000/6250] eta: 0:02:49 lr: 0.000121 grad: 0.0604 (0.0630) loss: 0.8425 (0.8426) time: 0.1242 data: 0.0442 max mem: 9390 +Train: [15] [5100/6250] eta: 0:02:36 lr: 0.000121 grad: 0.0572 (0.0629) loss: 0.8445 (0.8426) time: 0.1300 data: 0.0463 max mem: 9390 +Train: [15] [5200/6250] eta: 0:02:22 lr: 0.000121 grad: 0.0598 (0.0629) loss: 0.8439 (0.8426) time: 0.1385 data: 0.0609 max mem: 9390 +Train: [15] [5300/6250] eta: 0:02:08 lr: 0.000121 grad: 0.0597 (0.0628) loss: 0.8472 (0.8427) time: 0.1376 data: 0.0611 max mem: 9390 +Train: [15] [5400/6250] eta: 0:01:55 lr: 0.000121 grad: 0.0613 (0.0628) loss: 0.8453 (0.8427) time: 0.1097 data: 0.0319 max mem: 9390 +Train: [15] [5500/6250] eta: 0:01:41 lr: 0.000121 grad: 0.0588 (0.0628) loss: 0.8432 (0.8427) time: 0.1366 data: 0.0578 max mem: 9390 +Train: [15] [5600/6250] eta: 0:01:28 lr: 0.000121 grad: 0.0621 (0.0629) loss: 0.8438 (0.8427) time: 0.1246 data: 0.0431 max mem: 9390 +Train: [15] [5700/6250] eta: 0:01:14 lr: 0.000121 grad: 0.0608 (0.0628) loss: 0.8473 (0.8428) time: 0.1324 data: 0.0515 max mem: 9390 +Train: [15] [5800/6250] eta: 0:01:00 lr: 0.000121 grad: 0.0565 (0.0628) loss: 0.8415 (0.8428) time: 0.1406 data: 0.0620 max mem: 9390 +Train: [15] [5900/6250] eta: 0:00:47 lr: 0.000121 grad: 0.0603 (0.0628) loss: 0.8387 (0.8428) time: 0.1289 data: 0.0482 max mem: 9390 +Train: [15] [6000/6250] eta: 0:00:33 lr: 0.000121 grad: 0.0584 (0.0629) loss: 0.8409 (0.8428) time: 0.1323 data: 0.0564 max mem: 9390 +Train: [15] [6100/6250] eta: 0:00:20 lr: 0.000121 grad: 0.0577 (0.0629) loss: 0.8421 (0.8428) time: 0.1487 data: 0.0721 max mem: 9390 +Train: [15] [6200/6250] eta: 0:00:06 lr: 0.000121 grad: 0.0590 (0.0628) loss: 0.8427 (0.8428) time: 0.1136 data: 0.0339 max mem: 9390 +Train: [15] [6249/6250] eta: 0:00:00 lr: 0.000121 grad: 0.0600 (0.0628) loss: 0.8467 (0.8428) time: 0.1400 data: 0.0630 max mem: 9390 +Train: [15] Total time: 0:14:10 (0.1361 s / it) +Averaged stats: lr: 0.000121 grad: 0.0600 (0.0628) loss: 0.8467 (0.8428) +Eval (hcp-train-subset): [15] [ 0/62] eta: 0:03:07 loss: 0.8602 (0.8602) time: 3.0164 data: 2.9276 max mem: 9390 +Eval (hcp-train-subset): [15] [61/62] eta: 0:00:00 loss: 0.8473 (0.8484) time: 0.0920 data: 0.0670 max mem: 9390 +Eval (hcp-train-subset): [15] Total time: 0:00:12 (0.2073 s / it) +Averaged stats (hcp-train-subset): loss: 0.8473 (0.8484) +Eval (hcp-val): [15] [ 0/62] eta: 0:03:25 loss: 0.8390 (0.8390) time: 3.3216 data: 3.2533 max mem: 9390 +Eval (hcp-val): [15] [61/62] eta: 0:00:00 loss: 0.8424 (0.8436) time: 0.1093 data: 0.0844 max mem: 9390 +Eval (hcp-val): [15] Total time: 0:00:12 (0.1951 s / it) +Averaged stats (hcp-val): loss: 0.8424 (0.8436) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +Train: [16] [ 0/6250] eta: 8:14:27 lr: 0.000121 grad: 0.0763 (0.0763) loss: 0.8598 (0.8598) time: 4.7468 data: 4.6034 max mem: 9390 +Train: [16] [ 100/6250] eta: 0:19:34 lr: 0.000121 grad: 0.0609 (0.0694) loss: 0.8398 (0.8459) time: 0.1445 data: 0.0655 max mem: 9390 +Train: [16] [ 200/6250] eta: 0:16:36 lr: 0.000121 grad: 0.0679 (0.0678) loss: 0.8399 (0.8425) time: 0.1067 data: 0.0252 max mem: 9390 +Train: [16] [ 300/6250] eta: 0:15:30 lr: 0.000121 grad: 0.0618 (0.0672) loss: 0.8404 (0.8415) time: 0.1386 data: 0.0581 max mem: 9390 +Train: [16] [ 400/6250] eta: 0:14:52 lr: 0.000121 grad: 0.0612 (0.0664) loss: 0.8407 (0.8410) time: 0.1592 data: 0.0767 max mem: 9390 +Train: [16] [ 500/6250] eta: 0:14:09 lr: 0.000121 grad: 0.0613 (0.0654) loss: 0.8437 (0.8410) time: 0.1232 data: 0.0438 max mem: 9390 +Train: [16] [ 600/6250] eta: 0:13:32 lr: 0.000121 grad: 0.0590 (0.0645) loss: 0.8393 (0.8411) time: 0.1199 data: 0.0296 max mem: 9390 +Train: [16] [ 700/6250] eta: 0:13:13 lr: 0.000121 grad: 0.0591 (0.0641) loss: 0.8423 (0.8412) time: 0.1511 data: 0.0586 max mem: 9390 +Train: [16] [ 800/6250] eta: 0:12:55 lr: 0.000121 grad: 0.0598 (0.0639) loss: 0.8444 (0.8413) time: 0.1388 data: 0.0547 max mem: 9390 +Train: [16] [ 900/6250] eta: 0:12:41 lr: 0.000121 grad: 0.0589 (0.0638) loss: 0.8444 (0.8413) time: 0.1635 data: 0.0813 max mem: 9390 +Train: [16] [1000/6250] eta: 0:12:22 lr: 0.000121 grad: 0.0588 (0.0636) loss: 0.8439 (0.8413) time: 0.1349 data: 0.0544 max mem: 9390 +Train: [16] [1100/6250] eta: 0:12:08 lr: 0.000121 grad: 0.0608 (0.0634) loss: 0.8334 (0.8410) time: 0.1334 data: 0.0596 max mem: 9390 +Train: [16] [1200/6250] eta: 0:11:54 lr: 0.000121 grad: 0.0639 (0.0633) loss: 0.8353 (0.8409) time: 0.1266 data: 0.0426 max mem: 9390 +Train: [16] [1300/6250] eta: 0:11:37 lr: 0.000121 grad: 0.0606 (0.0633) loss: 0.8424 (0.8407) time: 0.1251 data: 0.0489 max mem: 9390 +Train: [16] [1400/6250] eta: 0:11:20 lr: 0.000121 grad: 0.0616 (0.0632) loss: 0.8392 (0.8406) time: 0.1223 data: 0.0450 max mem: 9390 +Train: [16] [1500/6250] eta: 0:11:05 lr: 0.000121 grad: 0.0637 (0.0631) loss: 0.8444 (0.8405) time: 0.1553 data: 0.0785 max mem: 9390 +Train: [16] [1600/6250] eta: 0:10:48 lr: 0.000121 grad: 0.0627 (0.0631) loss: 0.8405 (0.8405) time: 0.1346 data: 0.0531 max mem: 9390 +Train: [16] [1700/6250] eta: 0:10:32 lr: 0.000121 grad: 0.0637 (0.0632) loss: 0.8404 (0.8405) time: 0.1434 data: 0.0622 max mem: 9390 +Train: [16] [1800/6250] eta: 0:10:19 lr: 0.000121 grad: 0.0586 (0.0631) loss: 0.8437 (0.8406) time: 0.1363 data: 0.0586 max mem: 9390 +Train: [16] [1900/6250] eta: 0:10:02 lr: 0.000121 grad: 0.0585 (0.0631) loss: 0.8471 (0.8406) time: 0.1323 data: 0.0477 max mem: 9390 +Train: [16] [2000/6250] eta: 0:09:48 lr: 0.000121 grad: 0.0638 (0.0630) loss: 0.8356 (0.8406) time: 0.1462 data: 0.0671 max mem: 9390 +Train: [16] [2100/6250] eta: 0:09:32 lr: 0.000121 grad: 0.0611 (0.0630) loss: 0.8400 (0.8406) time: 0.1491 data: 0.0683 max mem: 9390 +Train: [16] [2200/6250] eta: 0:09:18 lr: 0.000121 grad: 0.0589 (0.0630) loss: 0.8452 (0.8406) time: 0.1470 data: 0.0667 max mem: 9390 +Train: [16] [2300/6250] eta: 0:09:03 lr: 0.000121 grad: 0.0631 (0.0630) loss: 0.8364 (0.8406) time: 0.1390 data: 0.0602 max mem: 9390 +Train: [16] [2400/6250] eta: 0:08:49 lr: 0.000121 grad: 0.0629 (0.0631) loss: 0.8357 (0.8405) time: 0.1479 data: 0.0664 max mem: 9390 +Train: [16] [2500/6250] eta: 0:08:35 lr: 0.000121 grad: 0.0597 (0.0631) loss: 0.8439 (0.8404) time: 0.1455 data: 0.0656 max mem: 9390 +Train: [16] [2600/6250] eta: 0:08:21 lr: 0.000121 grad: 0.0680 (0.0632) loss: 0.8318 (0.8402) time: 0.1353 data: 0.0610 max mem: 9390 +Train: [16] [2700/6250] eta: 0:08:06 lr: 0.000121 grad: 0.0671 (0.0634) loss: 0.8368 (0.8402) time: 0.1359 data: 0.0604 max mem: 9390 +Train: [16] [2800/6250] eta: 0:07:53 lr: 0.000121 grad: 0.0628 (0.0635) loss: 0.8378 (0.8401) time: 0.1143 data: 0.0338 max mem: 9390 +Train: [16] [2900/6250] eta: 0:07:39 lr: 0.000121 grad: 0.0610 (0.0635) loss: 0.8392 (0.8401) time: 0.1317 data: 0.0524 max mem: 9390 +Train: [16] [3000/6250] eta: 0:07:24 lr: 0.000121 grad: 0.0592 (0.0635) loss: 0.8437 (0.8401) time: 0.1456 data: 0.0668 max mem: 9390 +Train: [16] [3100/6250] eta: 0:07:10 lr: 0.000121 grad: 0.0624 (0.0636) loss: 0.8423 (0.8401) time: 0.1292 data: 0.0482 max mem: 9390 +Train: [16] [3200/6250] eta: 0:06:56 lr: 0.000121 grad: 0.0599 (0.0637) loss: 0.8439 (0.8401) time: 0.1336 data: 0.0523 max mem: 9390 +Train: [16] [3300/6250] eta: 0:06:42 lr: 0.000121 grad: 0.0596 (0.0636) loss: 0.8379 (0.8401) time: 0.1352 data: 0.0568 max mem: 9390 +Train: [16] [3400/6250] eta: 0:06:28 lr: 0.000121 grad: 0.0623 (0.0636) loss: 0.8369 (0.8401) time: 0.1315 data: 0.0506 max mem: 9390 +Train: [16] [3500/6250] eta: 0:06:15 lr: 0.000120 grad: 0.0641 (0.0636) loss: 0.8358 (0.8401) time: 0.1430 data: 0.0671 max mem: 9390 +Train: [16] [3600/6250] eta: 0:06:01 lr: 0.000120 grad: 0.0615 (0.0636) loss: 0.8367 (0.8401) time: 0.1261 data: 0.0438 max mem: 9390 +Train: [16] [3700/6250] eta: 0:05:47 lr: 0.000120 grad: 0.0639 (0.0637) loss: 0.8355 (0.8400) time: 0.1335 data: 0.0561 max mem: 9390 +Train: [16] [3800/6250] eta: 0:05:33 lr: 0.000120 grad: 0.0650 (0.0638) loss: 0.8398 (0.8400) time: 0.1421 data: 0.0655 max mem: 9390 +Train: [16] [3900/6250] eta: 0:05:19 lr: 0.000120 grad: 0.0674 (0.0639) loss: 0.8401 (0.8399) time: 0.1191 data: 0.0343 max mem: 9390 +Train: [16] [4000/6250] eta: 0:05:05 lr: 0.000120 grad: 0.0670 (0.0639) loss: 0.8335 (0.8398) time: 0.1249 data: 0.0431 max mem: 9390 +Train: [16] [4100/6250] eta: 0:04:51 lr: 0.000120 grad: 0.0660 (0.0640) loss: 0.8351 (0.8397) time: 0.1091 data: 0.0309 max mem: 9390 +Train: [16] [4200/6250] eta: 0:04:37 lr: 0.000120 grad: 0.0603 (0.0640) loss: 0.8425 (0.8397) time: 0.1403 data: 0.0633 max mem: 9390 +Train: [16] [4300/6250] eta: 0:04:24 lr: 0.000120 grad: 0.0637 (0.0641) loss: 0.8296 (0.8396) time: 0.1392 data: 0.0561 max mem: 9390 +Train: [16] [4400/6250] eta: 0:04:10 lr: 0.000120 grad: 0.0652 (0.0641) loss: 0.8350 (0.8395) time: 0.1268 data: 0.0501 max mem: 9390 +Train: [16] [4500/6250] eta: 0:03:56 lr: 0.000120 grad: 0.0633 (0.0641) loss: 0.8408 (0.8395) time: 0.1355 data: 0.0603 max mem: 9390 +Train: [16] [4600/6250] eta: 0:03:43 lr: 0.000120 grad: 0.0610 (0.0641) loss: 0.8387 (0.8395) time: 0.1400 data: 0.0610 max mem: 9390 +Train: [16] [4700/6250] eta: 0:03:29 lr: 0.000120 grad: 0.0621 (0.0642) loss: 0.8386 (0.8395) time: 0.1230 data: 0.0427 max mem: 9390 +Train: [16] [4800/6250] eta: 0:03:16 lr: 0.000120 grad: 0.0596 (0.0642) loss: 0.8397 (0.8395) time: 0.1197 data: 0.0390 max mem: 9390 +Train: [16] [4900/6250] eta: 0:03:02 lr: 0.000120 grad: 0.0621 (0.0642) loss: 0.8356 (0.8394) time: 0.1253 data: 0.0472 max mem: 9390 +Train: [16] [5000/6250] eta: 0:02:49 lr: 0.000120 grad: 0.0604 (0.0642) loss: 0.8373 (0.8394) time: 0.1348 data: 0.0554 max mem: 9390 +Train: [16] [5100/6250] eta: 0:02:35 lr: 0.000120 grad: 0.0635 (0.0642) loss: 0.8375 (0.8394) time: 0.1465 data: 0.0704 max mem: 9390 +Train: [16] [5200/6250] eta: 0:02:21 lr: 0.000120 grad: 0.0629 (0.0642) loss: 0.8358 (0.8394) time: 0.1287 data: 0.0526 max mem: 9390 +Train: [16] [5300/6250] eta: 0:02:08 lr: 0.000120 grad: 0.0637 (0.0642) loss: 0.8303 (0.8394) time: 0.1291 data: 0.0496 max mem: 9390 +Train: [16] [5400/6250] eta: 0:01:54 lr: 0.000120 grad: 0.0637 (0.0642) loss: 0.8397 (0.8394) time: 0.1492 data: 0.0700 max mem: 9390 +Train: [16] [5500/6250] eta: 0:01:41 lr: 0.000120 grad: 0.0631 (0.0642) loss: 0.8372 (0.8394) time: 0.1289 data: 0.0507 max mem: 9390 +Train: [16] [5600/6250] eta: 0:01:27 lr: 0.000120 grad: 0.0644 (0.0642) loss: 0.8367 (0.8393) time: 0.1194 data: 0.0385 max mem: 9390 +Train: [16] [5700/6250] eta: 0:01:14 lr: 0.000120 grad: 0.0623 (0.0642) loss: 0.8399 (0.8393) time: 0.1196 data: 0.0376 max mem: 9390 +Train: [16] [5800/6250] eta: 0:01:00 lr: 0.000120 grad: 0.0602 (0.0642) loss: 0.8397 (0.8393) time: 0.1283 data: 0.0454 max mem: 9390 +Train: [16] [5900/6250] eta: 0:00:47 lr: 0.000120 grad: 0.0629 (0.0641) loss: 0.8395 (0.8394) time: 0.1208 data: 0.0404 max mem: 9390 +Train: [16] [6000/6250] eta: 0:00:33 lr: 0.000120 grad: 0.0616 (0.0641) loss: 0.8397 (0.8394) time: 0.1455 data: 0.0672 max mem: 9390 +Train: [16] [6100/6250] eta: 0:00:20 lr: 0.000120 grad: 0.0607 (0.0641) loss: 0.8375 (0.8394) time: 0.1400 data: 0.0601 max mem: 9390 +Train: [16] [6200/6250] eta: 0:00:06 lr: 0.000120 grad: 0.0621 (0.0641) loss: 0.8365 (0.8394) time: 0.1338 data: 0.0607 max mem: 9390 +Train: [16] [6249/6250] eta: 0:00:00 lr: 0.000120 grad: 0.0596 (0.0641) loss: 0.8411 (0.8394) time: 0.1384 data: 0.0628 max mem: 9390 +Train: [16] Total time: 0:14:08 (0.1357 s / it) +Averaged stats: lr: 0.000120 grad: 0.0596 (0.0641) loss: 0.8411 (0.8394) +Eval (hcp-train-subset): [16] [ 0/62] eta: 0:05:11 loss: 0.8566 (0.8566) time: 5.0288 data: 4.9975 max mem: 9390 +Eval (hcp-train-subset): [16] [61/62] eta: 0:00:00 loss: 0.8462 (0.8479) time: 0.1268 data: 0.1019 max mem: 9390 +Eval (hcp-train-subset): [16] Total time: 0:00:13 (0.2118 s / it) +Averaged stats (hcp-train-subset): loss: 0.8462 (0.8479) +Eval (hcp-val): [16] [ 0/62] eta: 0:04:59 loss: 0.8399 (0.8399) time: 4.8335 data: 4.8034 max mem: 9390 +Eval (hcp-val): [16] [61/62] eta: 0:00:00 loss: 0.8430 (0.8431) time: 0.1204 data: 0.0942 max mem: 9390 +Eval (hcp-val): [16] Total time: 0:00:12 (0.1964 s / it) +Averaged stats (hcp-val): loss: 0.8430 (0.8431) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +Train: [17] [ 0/6250] eta: 9:10:49 lr: 0.000120 grad: 0.1150 (0.1150) loss: 0.8216 (0.8216) time: 5.2880 data: 5.1915 max mem: 9390 +Train: [17] [ 100/6250] eta: 0:19:21 lr: 0.000120 grad: 0.0698 (0.0720) loss: 0.8438 (0.8398) time: 0.1363 data: 0.0593 max mem: 9390 +Train: [17] [ 200/6250] eta: 0:17:01 lr: 0.000120 grad: 0.0619 (0.0677) loss: 0.8358 (0.8404) time: 0.1479 data: 0.0661 max mem: 9390 +Train: [17] [ 300/6250] eta: 0:15:45 lr: 0.000120 grad: 0.0654 (0.0662) loss: 0.8389 (0.8402) time: 0.1705 data: 0.0902 max mem: 9390 +Train: [17] [ 400/6250] eta: 0:15:01 lr: 0.000120 grad: 0.0609 (0.0655) loss: 0.8400 (0.8404) time: 0.1645 data: 0.0730 max mem: 9390 +Train: [17] [ 500/6250] eta: 0:14:26 lr: 0.000120 grad: 0.0615 (0.0650) loss: 0.8401 (0.8401) time: 0.1576 data: 0.0784 max mem: 9390 +Train: [17] [ 600/6250] eta: 0:13:54 lr: 0.000120 grad: 0.0601 (0.0649) loss: 0.8440 (0.8397) time: 0.1478 data: 0.0614 max mem: 9390 +Train: [17] [ 700/6250] eta: 0:13:43 lr: 0.000120 grad: 0.0631 (0.0653) loss: 0.8324 (0.8395) time: 0.1507 data: 0.0685 max mem: 9390 +Train: [17] [ 800/6250] eta: 0:13:27 lr: 0.000120 grad: 0.0616 (0.0653) loss: 0.8360 (0.8392) time: 0.1482 data: 0.0584 max mem: 9390 +Train: [17] [ 900/6250] eta: 0:13:05 lr: 0.000120 grad: 0.0647 (0.0650) loss: 0.8357 (0.8392) time: 0.1248 data: 0.0368 max mem: 9390 +Train: [17] [1000/6250] eta: 0:12:47 lr: 0.000120 grad: 0.0599 (0.0647) loss: 0.8385 (0.8394) time: 0.1416 data: 0.0592 max mem: 9390 +Train: [17] [1100/6250] eta: 0:12:30 lr: 0.000120 grad: 0.0594 (0.0646) loss: 0.8374 (0.8395) time: 0.1421 data: 0.0604 max mem: 9390 +Train: [17] [1200/6250] eta: 0:12:12 lr: 0.000120 grad: 0.0590 (0.0644) loss: 0.8411 (0.8396) time: 0.1154 data: 0.0355 max mem: 9390 +Train: [17] [1300/6250] eta: 0:11:56 lr: 0.000120 grad: 0.0597 (0.0642) loss: 0.8346 (0.8396) time: 0.1347 data: 0.0571 max mem: 9390 +Train: [17] [1400/6250] eta: 0:11:38 lr: 0.000120 grad: 0.0592 (0.0641) loss: 0.8404 (0.8397) time: 0.1155 data: 0.0353 max mem: 9390 +Train: [17] [1500/6250] eta: 0:11:22 lr: 0.000120 grad: 0.0638 (0.0640) loss: 0.8386 (0.8398) time: 0.1210 data: 0.0382 max mem: 9390 +Train: [17] [1600/6250] eta: 0:11:04 lr: 0.000120 grad: 0.0648 (0.0639) loss: 0.8382 (0.8399) time: 0.1284 data: 0.0473 max mem: 9390 +Train: [17] [1700/6250] eta: 0:10:48 lr: 0.000120 grad: 0.0618 (0.0638) loss: 0.8397 (0.8400) time: 0.1122 data: 0.0311 max mem: 9390 +Train: [17] [1800/6250] eta: 0:10:32 lr: 0.000120 grad: 0.0572 (0.0637) loss: 0.8371 (0.8401) time: 0.1321 data: 0.0500 max mem: 9390 +Train: [17] [1900/6250] eta: 0:10:16 lr: 0.000120 grad: 0.0613 (0.0636) loss: 0.8347 (0.8401) time: 0.1509 data: 0.0750 max mem: 9390 +Train: [17] [2000/6250] eta: 0:10:01 lr: 0.000120 grad: 0.0615 (0.0635) loss: 0.8421 (0.8402) time: 0.1221 data: 0.0449 max mem: 9390 +Train: [17] [2100/6250] eta: 0:09:45 lr: 0.000120 grad: 0.0585 (0.0635) loss: 0.8408 (0.8402) time: 0.1274 data: 0.0475 max mem: 9390 +Train: [17] [2200/6250] eta: 0:09:30 lr: 0.000120 grad: 0.0580 (0.0635) loss: 0.8449 (0.8402) time: 0.1425 data: 0.0566 max mem: 9390 +Train: [17] [2300/6250] eta: 0:09:14 lr: 0.000120 grad: 0.0595 (0.0634) loss: 0.8382 (0.8402) time: 0.1351 data: 0.0589 max mem: 9390 +Train: [17] [2400/6250] eta: 0:09:00 lr: 0.000120 grad: 0.0654 (0.0634) loss: 0.8385 (0.8402) time: 0.1340 data: 0.0559 max mem: 9390 +Train: [17] [2500/6250] eta: 0:08:44 lr: 0.000120 grad: 0.0649 (0.0635) loss: 0.8340 (0.8401) time: 0.1297 data: 0.0458 max mem: 9390 +Train: [17] [2600/6250] eta: 0:08:30 lr: 0.000120 grad: 0.0662 (0.0635) loss: 0.8345 (0.8401) time: 0.1541 data: 0.0748 max mem: 9390 +Train: [17] [2700/6250] eta: 0:08:14 lr: 0.000120 grad: 0.0637 (0.0635) loss: 0.8433 (0.8401) time: 0.1288 data: 0.0542 max mem: 9390 +Train: [17] [2800/6250] eta: 0:08:00 lr: 0.000120 grad: 0.0612 (0.0635) loss: 0.8367 (0.8400) time: 0.1256 data: 0.0440 max mem: 9390 +Train: [17] [2900/6250] eta: 0:07:45 lr: 0.000120 grad: 0.0616 (0.0635) loss: 0.8357 (0.8400) time: 0.1165 data: 0.0383 max mem: 9390 +Train: [17] [3000/6250] eta: 0:07:30 lr: 0.000120 grad: 0.0674 (0.0637) loss: 0.8403 (0.8400) time: 0.1424 data: 0.0682 max mem: 9390 +Train: [17] [3100/6250] eta: 0:07:16 lr: 0.000120 grad: 0.0642 (0.0638) loss: 0.8404 (0.8399) time: 0.1303 data: 0.0498 max mem: 9390 +Train: [17] [3200/6250] eta: 0:07:02 lr: 0.000120 grad: 0.0691 (0.0638) loss: 0.8357 (0.8398) time: 0.1155 data: 0.0285 max mem: 9390 +Train: [17] [3300/6250] eta: 0:06:48 lr: 0.000120 grad: 0.0610 (0.0640) loss: 0.8388 (0.8397) time: 0.1455 data: 0.0673 max mem: 9390 +Train: [17] [3400/6250] eta: 0:06:33 lr: 0.000120 grad: 0.0661 (0.0640) loss: 0.8408 (0.8397) time: 0.1144 data: 0.0287 max mem: 9390 +Train: [17] [3500/6250] eta: 0:06:19 lr: 0.000120 grad: 0.0693 (0.0640) loss: 0.8393 (0.8397) time: 0.1274 data: 0.0504 max mem: 9390 +Train: [17] [3600/6250] eta: 0:06:05 lr: 0.000120 grad: 0.0639 (0.0641) loss: 0.8349 (0.8396) time: 0.1641 data: 0.0914 max mem: 9390 +Train: [17] [3700/6250] eta: 0:05:51 lr: 0.000120 grad: 0.0698 (0.0643) loss: 0.8311 (0.8396) time: 0.1296 data: 0.0469 max mem: 9390 +Train: [17] [3800/6250] eta: 0:05:36 lr: 0.000120 grad: 0.0588 (0.0643) loss: 0.8418 (0.8396) time: 0.1475 data: 0.0665 max mem: 9390 +Train: [17] [3900/6250] eta: 0:05:22 lr: 0.000120 grad: 0.0607 (0.0644) loss: 0.8405 (0.8396) time: 0.1318 data: 0.0532 max mem: 9390 +Train: [17] [4000/6250] eta: 0:05:08 lr: 0.000120 grad: 0.0610 (0.0644) loss: 0.8350 (0.8395) time: 0.1338 data: 0.0563 max mem: 9390 +Train: [17] [4100/6250] eta: 0:04:54 lr: 0.000120 grad: 0.0611 (0.0645) loss: 0.8415 (0.8395) time: 0.1155 data: 0.0278 max mem: 9390 +Train: [17] [4200/6250] eta: 0:04:40 lr: 0.000120 grad: 0.0645 (0.0645) loss: 0.8412 (0.8395) time: 0.1300 data: 0.0531 max mem: 9390 +Train: [17] [4300/6250] eta: 0:04:26 lr: 0.000120 grad: 0.0612 (0.0644) loss: 0.8371 (0.8395) time: 0.1439 data: 0.0651 max mem: 9390 +Train: [17] [4400/6250] eta: 0:04:12 lr: 0.000120 grad: 0.0621 (0.0644) loss: 0.8381 (0.8395) time: 0.1350 data: 0.0498 max mem: 9390 +Train: [17] [4500/6250] eta: 0:03:58 lr: 0.000120 grad: 0.0649 (0.0645) loss: 0.8366 (0.8394) time: 0.1204 data: 0.0316 max mem: 9390 +Train: [17] [4600/6250] eta: 0:03:45 lr: 0.000120 grad: 0.0608 (0.0645) loss: 0.8389 (0.8394) time: 0.1301 data: 0.0500 max mem: 9390 +Train: [17] [4700/6250] eta: 0:03:31 lr: 0.000120 grad: 0.0600 (0.0645) loss: 0.8344 (0.8394) time: 0.1071 data: 0.0226 max mem: 9390 +Train: [17] [4800/6250] eta: 0:03:17 lr: 0.000120 grad: 0.0658 (0.0645) loss: 0.8351 (0.8394) time: 0.1442 data: 0.0656 max mem: 9390 +Train: [17] [4900/6250] eta: 0:03:04 lr: 0.000119 grad: 0.0641 (0.0645) loss: 0.8415 (0.8394) time: 0.1745 data: 0.0977 max mem: 9390 +Train: [17] [5000/6250] eta: 0:02:50 lr: 0.000119 grad: 0.0645 (0.0644) loss: 0.8346 (0.8393) time: 0.1325 data: 0.0572 max mem: 9390 +Train: [17] [5100/6250] eta: 0:02:36 lr: 0.000119 grad: 0.0634 (0.0644) loss: 0.8365 (0.8393) time: 0.1285 data: 0.0478 max mem: 9390 +Train: [17] [5200/6250] eta: 0:02:23 lr: 0.000119 grad: 0.0650 (0.0644) loss: 0.8335 (0.8393) time: 0.1371 data: 0.0585 max mem: 9390 +Train: [17] [5300/6250] eta: 0:02:09 lr: 0.000119 grad: 0.0632 (0.0644) loss: 0.8401 (0.8392) time: 0.1543 data: 0.0791 max mem: 9390 +Train: [17] [5400/6250] eta: 0:01:55 lr: 0.000119 grad: 0.0599 (0.0644) loss: 0.8348 (0.8392) time: 0.1204 data: 0.0403 max mem: 9390 +Train: [17] [5500/6250] eta: 0:01:42 lr: 0.000119 grad: 0.0644 (0.0644) loss: 0.8361 (0.8391) time: 0.1204 data: 0.0428 max mem: 9390 +Train: [17] [5600/6250] eta: 0:01:28 lr: 0.000119 grad: 0.0605 (0.0644) loss: 0.8347 (0.8391) time: 0.1462 data: 0.0645 max mem: 9390 +Train: [17] [5700/6250] eta: 0:01:14 lr: 0.000119 grad: 0.0610 (0.0645) loss: 0.8368 (0.8391) time: 0.1378 data: 0.0641 max mem: 9390 +Train: [17] [5800/6250] eta: 0:01:01 lr: 0.000119 grad: 0.0611 (0.0645) loss: 0.8346 (0.8391) time: 0.1387 data: 0.0597 max mem: 9390 +Train: [17] [5900/6250] eta: 0:00:47 lr: 0.000119 grad: 0.0640 (0.0645) loss: 0.8340 (0.8391) time: 0.1208 data: 0.0403 max mem: 9390 +Train: [17] [6000/6250] eta: 0:00:33 lr: 0.000119 grad: 0.0599 (0.0645) loss: 0.8385 (0.8390) time: 0.1362 data: 0.0552 max mem: 9390 +Train: [17] [6100/6250] eta: 0:00:20 lr: 0.000119 grad: 0.0626 (0.0645) loss: 0.8373 (0.8390) time: 0.1296 data: 0.0522 max mem: 9390 +Train: [17] [6200/6250] eta: 0:00:06 lr: 0.000119 grad: 0.0620 (0.0645) loss: 0.8315 (0.8390) time: 0.1096 data: 0.0208 max mem: 9390 +Train: [17] [6249/6250] eta: 0:00:00 lr: 0.000119 grad: 0.0636 (0.0645) loss: 0.8390 (0.8390) time: 0.1096 data: 0.0219 max mem: 9390 +Train: [17] Total time: 0:14:13 (0.1365 s / it) +Averaged stats: lr: 0.000119 grad: 0.0636 (0.0645) loss: 0.8390 (0.8390) +Eval (hcp-train-subset): [17] [ 0/62] eta: 0:03:10 loss: 0.8573 (0.8573) time: 3.0803 data: 3.0006 max mem: 9390 +Eval (hcp-train-subset): [17] [61/62] eta: 0:00:00 loss: 0.8466 (0.8470) time: 0.1279 data: 0.1015 max mem: 9390 +Eval (hcp-train-subset): [17] Total time: 0:00:13 (0.2148 s / it) +Averaged stats (hcp-train-subset): loss: 0.8466 (0.8470) +Eval (hcp-val): [17] [ 0/62] eta: 0:03:04 loss: 0.8397 (0.8397) time: 2.9718 data: 2.9090 max mem: 9390 +Eval (hcp-val): [17] [61/62] eta: 0:00:00 loss: 0.8416 (0.8417) time: 0.1263 data: 0.1014 max mem: 9390 +Eval (hcp-val): [17] Total time: 0:00:11 (0.1921 s / it) +Averaged stats (hcp-val): loss: 0.8416 (0.8417) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +Train: [18] [ 0/6250] eta: 9:29:47 lr: 0.000119 grad: 0.0680 (0.0680) loss: 0.8469 (0.8469) time: 5.4700 data: 5.3629 max mem: 9390 +Train: [18] [ 100/6250] eta: 0:19:29 lr: 0.000119 grad: 0.0683 (0.0783) loss: 0.8359 (0.8407) time: 0.1548 data: 0.0673 max mem: 9390 +Train: [18] [ 200/6250] eta: 0:17:14 lr: 0.000119 grad: 0.0640 (0.0753) loss: 0.8394 (0.8387) time: 0.1480 data: 0.0739 max mem: 9390 +Train: [18] [ 300/6250] eta: 0:15:53 lr: 0.000119 grad: 0.0649 (0.0724) loss: 0.8393 (0.8389) time: 0.1325 data: 0.0542 max mem: 9390 +Train: [18] [ 400/6250] eta: 0:15:05 lr: 0.000119 grad: 0.0627 (0.0702) loss: 0.8376 (0.8391) time: 0.1522 data: 0.0749 max mem: 9390 +Train: [18] [ 500/6250] eta: 0:14:30 lr: 0.000119 grad: 0.0619 (0.0686) loss: 0.8375 (0.8389) time: 0.1538 data: 0.0599 max mem: 9390 +Train: [18] [ 600/6250] eta: 0:14:09 lr: 0.000119 grad: 0.0601 (0.0677) loss: 0.8408 (0.8391) time: 0.1401 data: 0.0530 max mem: 9390 +Train: [18] [ 700/6250] eta: 0:13:57 lr: 0.000119 grad: 0.0608 (0.0668) loss: 0.8449 (0.8397) time: 0.1504 data: 0.0590 max mem: 9390 +Train: [18] [ 800/6250] eta: 0:13:38 lr: 0.000119 grad: 0.0614 (0.0663) loss: 0.8376 (0.8396) time: 0.1382 data: 0.0466 max mem: 9390 +Train: [18] [ 900/6250] eta: 0:13:21 lr: 0.000119 grad: 0.0628 (0.0661) loss: 0.8296 (0.8393) time: 0.1589 data: 0.0768 max mem: 9390 +Train: [18] [1000/6250] eta: 0:13:01 lr: 0.000119 grad: 0.0608 (0.0658) loss: 0.8361 (0.8391) time: 0.1332 data: 0.0512 max mem: 9390 +Train: [18] [1100/6250] eta: 0:12:43 lr: 0.000119 grad: 0.0594 (0.0655) loss: 0.8363 (0.8389) time: 0.1571 data: 0.0811 max mem: 9390 +Train: [18] [1200/6250] eta: 0:12:24 lr: 0.000119 grad: 0.0614 (0.0654) loss: 0.8350 (0.8387) time: 0.1424 data: 0.0606 max mem: 9390 +Train: [18] [1300/6250] eta: 0:12:07 lr: 0.000119 grad: 0.0615 (0.0653) loss: 0.8325 (0.8384) time: 0.1243 data: 0.0444 max mem: 9390 +Train: [18] [1400/6250] eta: 0:11:48 lr: 0.000119 grad: 0.0639 (0.0655) loss: 0.8357 (0.8381) time: 0.1290 data: 0.0474 max mem: 9390 +Train: [18] [1500/6250] eta: 0:11:30 lr: 0.000119 grad: 0.0643 (0.0656) loss: 0.8325 (0.8379) time: 0.1262 data: 0.0454 max mem: 9390 +Train: [18] [1600/6250] eta: 0:11:13 lr: 0.000119 grad: 0.0610 (0.0658) loss: 0.8344 (0.8377) time: 0.1445 data: 0.0680 max mem: 9390 +Train: [18] [1700/6250] eta: 0:10:56 lr: 0.000119 grad: 0.0659 (0.0660) loss: 0.8340 (0.8374) time: 0.1380 data: 0.0618 max mem: 9390 +Train: [18] [1800/6250] eta: 0:10:39 lr: 0.000119 grad: 0.0659 (0.0661) loss: 0.8337 (0.8372) time: 0.1427 data: 0.0653 max mem: 9390 +Train: [18] [1900/6250] eta: 0:10:23 lr: 0.000119 grad: 0.0659 (0.0662) loss: 0.8307 (0.8368) time: 0.1586 data: 0.0784 max mem: 9390 +Train: [18] [2000/6250] eta: 0:10:06 lr: 0.000119 grad: 0.0642 (0.0662) loss: 0.8296 (0.8367) time: 0.1450 data: 0.0641 max mem: 9390 +Train: [18] [2100/6250] eta: 0:09:51 lr: 0.000119 grad: 0.0638 (0.0662) loss: 0.8300 (0.8365) time: 0.1444 data: 0.0659 max mem: 9390 +Train: [18] [2200/6250] eta: 0:09:35 lr: 0.000119 grad: 0.0675 (0.0662) loss: 0.8325 (0.8363) time: 0.1391 data: 0.0556 max mem: 9390 +Train: [18] [2300/6250] eta: 0:09:19 lr: 0.000119 grad: 0.0669 (0.0664) loss: 0.8283 (0.8361) time: 0.1334 data: 0.0564 max mem: 9390 +Train: [18] [2400/6250] eta: 0:09:05 lr: 0.000119 grad: 0.0652 (0.0664) loss: 0.8263 (0.8358) time: 0.1393 data: 0.0608 max mem: 9390 +Train: [18] [2500/6250] eta: 0:08:49 lr: 0.000119 grad: 0.0647 (0.0665) loss: 0.8334 (0.8356) time: 0.1370 data: 0.0567 max mem: 9390 +Train: [18] [2600/6250] eta: 0:08:34 lr: 0.000119 grad: 0.0654 (0.0666) loss: 0.8374 (0.8355) time: 0.1446 data: 0.0689 max mem: 9390 +Train: [18] [2700/6250] eta: 0:08:19 lr: 0.000119 grad: 0.0661 (0.0668) loss: 0.8343 (0.8354) time: 0.1150 data: 0.0294 max mem: 9390 +Train: [18] [2800/6250] eta: 0:08:04 lr: 0.000119 grad: 0.0644 (0.0669) loss: 0.8292 (0.8353) time: 0.1500 data: 0.0708 max mem: 9390 +Train: [18] [2900/6250] eta: 0:07:49 lr: 0.000119 grad: 0.0655 (0.0668) loss: 0.8327 (0.8352) time: 0.1152 data: 0.0328 max mem: 9390 +Train: [18] [3000/6250] eta: 0:07:34 lr: 0.000119 grad: 0.0663 (0.0668) loss: 0.8353 (0.8352) time: 0.1320 data: 0.0570 max mem: 9390 +Train: [18] [3100/6250] eta: 0:07:20 lr: 0.000119 grad: 0.0640 (0.0667) loss: 0.8367 (0.8352) time: 0.1208 data: 0.0442 max mem: 9390 +Train: [18] [3200/6250] eta: 0:07:05 lr: 0.000119 grad: 0.0668 (0.0667) loss: 0.8337 (0.8351) time: 0.1334 data: 0.0565 max mem: 9390 +Train: [18] [3300/6250] eta: 0:06:50 lr: 0.000119 grad: 0.0635 (0.0666) loss: 0.8346 (0.8351) time: 0.1328 data: 0.0510 max mem: 9390 +Train: [18] [3400/6250] eta: 0:06:35 lr: 0.000119 grad: 0.0620 (0.0666) loss: 0.8393 (0.8351) time: 0.1281 data: 0.0548 max mem: 9390 +Train: [18] [3500/6250] eta: 0:06:21 lr: 0.000119 grad: 0.0618 (0.0666) loss: 0.8337 (0.8351) time: 0.1227 data: 0.0457 max mem: 9390 +Train: [18] [3600/6250] eta: 0:06:06 lr: 0.000119 grad: 0.0604 (0.0665) loss: 0.8373 (0.8351) time: 0.1249 data: 0.0464 max mem: 9390 +Train: [18] [3700/6250] eta: 0:05:52 lr: 0.000119 grad: 0.0609 (0.0665) loss: 0.8337 (0.8352) time: 0.1367 data: 0.0618 max mem: 9390 +Train: [18] [3800/6250] eta: 0:05:38 lr: 0.000119 grad: 0.0650 (0.0664) loss: 0.8367 (0.8351) time: 0.1164 data: 0.0397 max mem: 9390 +Train: [18] [3900/6250] eta: 0:05:23 lr: 0.000119 grad: 0.0637 (0.0664) loss: 0.8351 (0.8352) time: 0.1318 data: 0.0482 max mem: 9390 +Train: [18] [4000/6250] eta: 0:05:09 lr: 0.000119 grad: 0.0610 (0.0663) loss: 0.8369 (0.8352) time: 0.1378 data: 0.0534 max mem: 9390 +Train: [18] [4100/6250] eta: 0:04:55 lr: 0.000119 grad: 0.0587 (0.0662) loss: 0.8406 (0.8353) time: 0.1200 data: 0.0460 max mem: 9390 +Train: [18] [4200/6250] eta: 0:04:41 lr: 0.000119 grad: 0.0657 (0.0662) loss: 0.8364 (0.8354) time: 0.1226 data: 0.0414 max mem: 9390 +Train: [18] [4300/6250] eta: 0:04:27 lr: 0.000119 grad: 0.0653 (0.0661) loss: 0.8387 (0.8355) time: 0.1178 data: 0.0368 max mem: 9390 +Train: [18] [4400/6250] eta: 0:04:13 lr: 0.000119 grad: 0.0637 (0.0661) loss: 0.8416 (0.8356) time: 0.1109 data: 0.0324 max mem: 9390 +Train: [18] [4500/6250] eta: 0:03:59 lr: 0.000119 grad: 0.0594 (0.0660) loss: 0.8327 (0.8357) time: 0.1304 data: 0.0528 max mem: 9390 +Train: [18] [4600/6250] eta: 0:03:46 lr: 0.000119 grad: 0.0682 (0.0659) loss: 0.8407 (0.8357) time: 0.1018 data: 0.0005 max mem: 9390 +Train: [18] [4700/6250] eta: 0:03:32 lr: 0.000119 grad: 0.0601 (0.0659) loss: 0.8431 (0.8358) time: 0.1206 data: 0.0354 max mem: 9390 +Train: [18] [4800/6250] eta: 0:03:19 lr: 0.000119 grad: 0.0589 (0.0658) loss: 0.8419 (0.8359) time: 0.1418 data: 0.0623 max mem: 9390 +Train: [18] [4900/6250] eta: 0:03:05 lr: 0.000119 grad: 0.0617 (0.0658) loss: 0.8383 (0.8360) time: 0.1332 data: 0.0571 max mem: 9390 +Train: [18] [5000/6250] eta: 0:02:51 lr: 0.000119 grad: 0.0648 (0.0658) loss: 0.8404 (0.8361) time: 0.1156 data: 0.0373 max mem: 9390 +Train: [18] [5100/6250] eta: 0:02:37 lr: 0.000119 grad: 0.0630 (0.0658) loss: 0.8301 (0.8361) time: 0.1296 data: 0.0475 max mem: 9390 +Train: [18] [5200/6250] eta: 0:02:23 lr: 0.000119 grad: 0.0615 (0.0658) loss: 0.8391 (0.8362) time: 0.1415 data: 0.0649 max mem: 9390 +Train: [18] [5300/6250] eta: 0:02:09 lr: 0.000119 grad: 0.0600 (0.0658) loss: 0.8374 (0.8363) time: 0.1105 data: 0.0353 max mem: 9390 +Train: [18] [5400/6250] eta: 0:01:56 lr: 0.000119 grad: 0.0578 (0.0658) loss: 0.8379 (0.8363) time: 0.1298 data: 0.0511 max mem: 9390 +Train: [18] [5500/6250] eta: 0:01:42 lr: 0.000119 grad: 0.0630 (0.0657) loss: 0.8383 (0.8363) time: 0.1301 data: 0.0501 max mem: 9390 +Train: [18] [5600/6250] eta: 0:01:28 lr: 0.000119 grad: 0.0623 (0.0657) loss: 0.8403 (0.8364) time: 0.1285 data: 0.0506 max mem: 9390 +Train: [18] [5700/6250] eta: 0:01:14 lr: 0.000119 grad: 0.0636 (0.0657) loss: 0.8425 (0.8364) time: 0.1400 data: 0.0616 max mem: 9390 +Train: [18] [5800/6250] eta: 0:01:01 lr: 0.000118 grad: 0.0660 (0.0657) loss: 0.8392 (0.8364) time: 0.1264 data: 0.0483 max mem: 9390 +Train: [18] [5900/6250] eta: 0:00:47 lr: 0.000118 grad: 0.0666 (0.0657) loss: 0.8385 (0.8365) time: 0.1322 data: 0.0504 max mem: 9390 +Train: [18] [6000/6250] eta: 0:00:34 lr: 0.000118 grad: 0.0617 (0.0656) loss: 0.8380 (0.8366) time: 0.1258 data: 0.0403 max mem: 9390 +Train: [18] [6100/6250] eta: 0:00:20 lr: 0.000118 grad: 0.0653 (0.0656) loss: 0.8396 (0.8366) time: 0.1322 data: 0.0533 max mem: 9390 +Train: [18] [6200/6250] eta: 0:00:06 lr: 0.000118 grad: 0.0620 (0.0656) loss: 0.8419 (0.8367) time: 0.1102 data: 0.0317 max mem: 9390 +Train: [18] [6249/6250] eta: 0:00:00 lr: 0.000118 grad: 0.0667 (0.0656) loss: 0.8338 (0.8367) time: 0.1280 data: 0.0467 max mem: 9390 +Train: [18] Total time: 0:14:14 (0.1367 s / it) +Averaged stats: lr: 0.000118 grad: 0.0667 (0.0656) loss: 0.8338 (0.8367) +Eval (hcp-train-subset): [18] [ 0/62] eta: 0:03:52 loss: 0.8563 (0.8563) time: 3.7476 data: 3.6686 max mem: 9390 +Eval (hcp-train-subset): [18] [61/62] eta: 0:00:00 loss: 0.8456 (0.8462) time: 0.1262 data: 0.1012 max mem: 9390 +Eval (hcp-train-subset): [18] Total time: 0:00:13 (0.2146 s / it) +Averaged stats (hcp-train-subset): loss: 0.8456 (0.8462) +Eval (hcp-val): [18] [ 0/62] eta: 0:04:47 loss: 0.8364 (0.8364) time: 4.6305 data: 4.6002 max mem: 9390 +Eval (hcp-val): [18] [61/62] eta: 0:00:00 loss: 0.8407 (0.8414) time: 0.1244 data: 0.0997 max mem: 9390 +Eval (hcp-val): [18] Total time: 0:00:12 (0.1967 s / it) +Averaged stats (hcp-val): loss: 0.8407 (0.8414) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +Train: [19] [ 0/6250] eta: 10:11:09 lr: 0.000118 grad: 0.2006 (0.2006) loss: 0.8247 (0.8247) time: 5.8671 data: 5.7722 max mem: 9390 +Train: [19] [ 100/6250] eta: 0:19:26 lr: 0.000118 grad: 0.0626 (0.0719) loss: 0.8366 (0.8454) time: 0.1285 data: 0.0492 max mem: 9390 +Train: [19] [ 200/6250] eta: 0:17:18 lr: 0.000118 grad: 0.0685 (0.0694) loss: 0.8355 (0.8401) time: 0.1771 data: 0.0981 max mem: 9390 +Train: [19] [ 300/6250] eta: 0:16:04 lr: 0.000118 grad: 0.0665 (0.0681) loss: 0.8361 (0.8398) time: 0.1472 data: 0.0689 max mem: 9390 +Train: [19] [ 400/6250] eta: 0:15:14 lr: 0.000118 grad: 0.0610 (0.0672) loss: 0.8441 (0.8406) time: 0.1295 data: 0.0478 max mem: 9390 +Train: [19] [ 500/6250] eta: 0:14:38 lr: 0.000118 grad: 0.0603 (0.0664) loss: 0.8419 (0.8408) time: 0.1230 data: 0.0435 max mem: 9390 +Train: [19] [ 600/6250] eta: 0:14:07 lr: 0.000118 grad: 0.0601 (0.0658) loss: 0.8441 (0.8414) time: 0.1249 data: 0.0444 max mem: 9390 +Train: [19] [ 700/6250] eta: 0:13:44 lr: 0.000118 grad: 0.0554 (0.0652) loss: 0.8446 (0.8420) time: 0.1252 data: 0.0385 max mem: 9390 +Train: [19] [ 800/6250] eta: 0:13:21 lr: 0.000118 grad: 0.0580 (0.0648) loss: 0.8434 (0.8422) time: 0.1446 data: 0.0546 max mem: 9390 +Train: [19] [ 900/6250] eta: 0:12:59 lr: 0.000118 grad: 0.0597 (0.0644) loss: 0.8422 (0.8424) time: 0.1363 data: 0.0508 max mem: 9390 +Train: [19] [1000/6250] eta: 0:12:38 lr: 0.000118 grad: 0.0650 (0.0645) loss: 0.8400 (0.8422) time: 0.1284 data: 0.0529 max mem: 9390 +Train: [19] [1100/6250] eta: 0:12:17 lr: 0.000118 grad: 0.0648 (0.0645) loss: 0.8410 (0.8422) time: 0.1174 data: 0.0349 max mem: 9390 +Train: [19] [1200/6250] eta: 0:11:56 lr: 0.000118 grad: 0.0644 (0.0643) loss: 0.8390 (0.8419) time: 0.1272 data: 0.0450 max mem: 9390 +Train: [19] [1300/6250] eta: 0:11:40 lr: 0.000118 grad: 0.0591 (0.0644) loss: 0.8422 (0.8419) time: 0.1483 data: 0.0686 max mem: 9390 +Train: [19] [1400/6250] eta: 0:11:24 lr: 0.000118 grad: 0.0634 (0.0643) loss: 0.8381 (0.8417) time: 0.1315 data: 0.0554 max mem: 9390 +Train: [19] [1500/6250] eta: 0:11:08 lr: 0.000118 grad: 0.0604 (0.0643) loss: 0.8373 (0.8414) time: 0.1329 data: 0.0513 max mem: 9390 +Train: [19] [1600/6250] eta: 0:10:53 lr: 0.000118 grad: 0.0612 (0.0642) loss: 0.8415 (0.8413) time: 0.1220 data: 0.0409 max mem: 9390 +Train: [19] [1700/6250] eta: 0:10:37 lr: 0.000118 grad: 0.0637 (0.0642) loss: 0.8403 (0.8412) time: 0.1346 data: 0.0547 max mem: 9390 +Train: [19] [1800/6250] eta: 0:10:23 lr: 0.000118 grad: 0.0661 (0.0644) loss: 0.8293 (0.8409) time: 0.1387 data: 0.0574 max mem: 9390 +Train: [19] [1900/6250] eta: 0:10:07 lr: 0.000118 grad: 0.0651 (0.0645) loss: 0.8373 (0.8406) time: 0.1193 data: 0.0370 max mem: 9390 +Train: [19] [2000/6250] eta: 0:09:53 lr: 0.000118 grad: 0.0729 (0.0647) loss: 0.8304 (0.8404) time: 0.1451 data: 0.0650 max mem: 9390 +Train: [19] [2100/6250] eta: 0:09:39 lr: 0.000118 grad: 0.0611 (0.0649) loss: 0.8416 (0.8402) time: 0.1727 data: 0.0975 max mem: 9390 +Train: [19] [2200/6250] eta: 0:09:23 lr: 0.000118 grad: 0.0649 (0.0651) loss: 0.8346 (0.8399) time: 0.1442 data: 0.0603 max mem: 9390 +Train: [19] [2300/6250] eta: 0:09:08 lr: 0.000118 grad: 0.0694 (0.0651) loss: 0.8425 (0.8398) time: 0.1339 data: 0.0564 max mem: 9390 +Train: [19] [2400/6250] eta: 0:08:53 lr: 0.000118 grad: 0.0692 (0.0653) loss: 0.8382 (0.8397) time: 0.1277 data: 0.0499 max mem: 9390 +Train: [19] [2500/6250] eta: 0:08:38 lr: 0.000118 grad: 0.0648 (0.0654) loss: 0.8334 (0.8396) time: 0.1449 data: 0.0643 max mem: 9390 +Train: [19] [2600/6250] eta: 0:08:24 lr: 0.000118 grad: 0.0627 (0.0654) loss: 0.8365 (0.8395) time: 0.1442 data: 0.0591 max mem: 9390 +Train: [19] [2700/6250] eta: 0:08:09 lr: 0.000118 grad: 0.0642 (0.0654) loss: 0.8395 (0.8394) time: 0.1317 data: 0.0529 max mem: 9390 +Train: [19] [2800/6250] eta: 0:07:55 lr: 0.000118 grad: 0.0667 (0.0655) loss: 0.8329 (0.8392) time: 0.1347 data: 0.0507 max mem: 9390 +Train: [19] [2900/6250] eta: 0:07:42 lr: 0.000118 grad: 0.0666 (0.0656) loss: 0.8387 (0.8392) time: 0.1404 data: 0.0586 max mem: 9390 +Train: [19] [3000/6250] eta: 0:07:27 lr: 0.000118 grad: 0.0619 (0.0656) loss: 0.8429 (0.8391) time: 0.1268 data: 0.0486 max mem: 9390 +Train: [19] [3100/6250] eta: 0:07:13 lr: 0.000118 grad: 0.0631 (0.0656) loss: 0.8408 (0.8391) time: 0.1279 data: 0.0483 max mem: 9390 +Train: [19] [3200/6250] eta: 0:06:59 lr: 0.000118 grad: 0.0630 (0.0657) loss: 0.8393 (0.8391) time: 0.1387 data: 0.0553 max mem: 9390 +Train: [19] [3300/6250] eta: 0:06:45 lr: 0.000118 grad: 0.0647 (0.0657) loss: 0.8378 (0.8390) time: 0.1529 data: 0.0607 max mem: 9390 +Train: [19] [3400/6250] eta: 0:06:32 lr: 0.000118 grad: 0.0676 (0.0657) loss: 0.8350 (0.8389) time: 0.1193 data: 0.0383 max mem: 9390 +Train: [19] [3500/6250] eta: 0:06:18 lr: 0.000118 grad: 0.0622 (0.0658) loss: 0.8403 (0.8388) time: 0.1278 data: 0.0526 max mem: 9390 +Train: [19] [3600/6250] eta: 0:06:04 lr: 0.000118 grad: 0.0708 (0.0659) loss: 0.8355 (0.8387) time: 0.1452 data: 0.0641 max mem: 9390 +Train: [19] [3700/6250] eta: 0:05:51 lr: 0.000118 grad: 0.0700 (0.0660) loss: 0.8253 (0.8386) time: 0.1314 data: 0.0533 max mem: 9390 +Train: [19] [3800/6250] eta: 0:05:37 lr: 0.000118 grad: 0.0658 (0.0661) loss: 0.8383 (0.8385) time: 0.1153 data: 0.0318 max mem: 9390 +Train: [19] [3900/6250] eta: 0:05:23 lr: 0.000118 grad: 0.0608 (0.0661) loss: 0.8385 (0.8385) time: 0.1398 data: 0.0608 max mem: 9390 +Train: [19] [4000/6250] eta: 0:05:08 lr: 0.000118 grad: 0.0697 (0.0662) loss: 0.8306 (0.8384) time: 0.1178 data: 0.0340 max mem: 9390 +Train: [19] [4100/6250] eta: 0:04:55 lr: 0.000118 grad: 0.0674 (0.0663) loss: 0.8370 (0.8384) time: 0.1186 data: 0.0367 max mem: 9390 +Train: [19] [4200/6250] eta: 0:04:41 lr: 0.000118 grad: 0.0704 (0.0663) loss: 0.8344 (0.8383) time: 0.1468 data: 0.0692 max mem: 9390 +Train: [19] [4300/6250] eta: 0:04:27 lr: 0.000118 grad: 0.0635 (0.0664) loss: 0.8347 (0.8382) time: 0.1281 data: 0.0455 max mem: 9390 +Train: [19] [4400/6250] eta: 0:04:14 lr: 0.000118 grad: 0.0664 (0.0664) loss: 0.8355 (0.8381) time: 0.1425 data: 0.0411 max mem: 9390 +Train: [19] [4500/6250] eta: 0:04:00 lr: 0.000118 grad: 0.0682 (0.0665) loss: 0.8387 (0.8380) time: 0.1321 data: 0.0540 max mem: 9390 +Train: [19] [4600/6250] eta: 0:03:46 lr: 0.000118 grad: 0.0633 (0.0665) loss: 0.8405 (0.8380) time: 0.1200 data: 0.0416 max mem: 9390 +Train: [19] [4700/6250] eta: 0:03:32 lr: 0.000118 grad: 0.0633 (0.0665) loss: 0.8359 (0.8380) time: 0.1227 data: 0.0411 max mem: 9390 +Train: [19] [4800/6250] eta: 0:03:18 lr: 0.000118 grad: 0.0635 (0.0665) loss: 0.8405 (0.8380) time: 0.1425 data: 0.0658 max mem: 9390 +Train: [19] [4900/6250] eta: 0:03:04 lr: 0.000118 grad: 0.0665 (0.0665) loss: 0.8366 (0.8380) time: 0.1354 data: 0.0585 max mem: 9390 +Train: [19] [5000/6250] eta: 0:02:51 lr: 0.000118 grad: 0.0690 (0.0665) loss: 0.8378 (0.8380) time: 0.1655 data: 0.0735 max mem: 9390 +Train: [19] [5100/6250] eta: 0:02:37 lr: 0.000118 grad: 0.0608 (0.0665) loss: 0.8433 (0.8380) time: 0.1213 data: 0.0425 max mem: 9390 +Train: [19] [5200/6250] eta: 0:02:24 lr: 0.000118 grad: 0.0661 (0.0665) loss: 0.8387 (0.8380) time: 0.1383 data: 0.0586 max mem: 9390 +Train: [19] [5300/6250] eta: 0:02:10 lr: 0.000118 grad: 0.0658 (0.0665) loss: 0.8359 (0.8380) time: 0.1437 data: 0.0612 max mem: 9390 +Train: [19] [5400/6250] eta: 0:01:56 lr: 0.000118 grad: 0.0633 (0.0665) loss: 0.8372 (0.8379) time: 0.1332 data: 0.0555 max mem: 9390 +Train: [19] [5500/6250] eta: 0:01:42 lr: 0.000118 grad: 0.0642 (0.0665) loss: 0.8411 (0.8380) time: 0.1467 data: 0.0739 max mem: 9390 +Train: [19] [5600/6250] eta: 0:01:29 lr: 0.000118 grad: 0.0613 (0.0665) loss: 0.8429 (0.8380) time: 0.1474 data: 0.0729 max mem: 9390 +Train: [19] [5700/6250] eta: 0:01:15 lr: 0.000118 grad: 0.0635 (0.0665) loss: 0.8401 (0.8380) time: 0.1639 data: 0.0718 max mem: 9390 +Train: [19] [5800/6250] eta: 0:01:01 lr: 0.000118 grad: 0.0715 (0.0666) loss: 0.8329 (0.8379) time: 0.1606 data: 0.0740 max mem: 9390 +Train: [19] [5900/6250] eta: 0:00:47 lr: 0.000118 grad: 0.0618 (0.0666) loss: 0.8389 (0.8379) time: 0.1344 data: 0.0582 max mem: 9390 +Train: [19] [6000/6250] eta: 0:00:34 lr: 0.000118 grad: 0.0657 (0.0666) loss: 0.8356 (0.8379) time: 0.1200 data: 0.0432 max mem: 9390 +Train: [19] [6100/6250] eta: 0:00:20 lr: 0.000117 grad: 0.0626 (0.0666) loss: 0.8376 (0.8379) time: 0.1204 data: 0.0423 max mem: 9390 +Train: [19] [6200/6250] eta: 0:00:06 lr: 0.000117 grad: 0.0665 (0.0666) loss: 0.8344 (0.8378) time: 0.1416 data: 0.0614 max mem: 9390 +Train: [19] [6249/6250] eta: 0:00:00 lr: 0.000117 grad: 0.0682 (0.0666) loss: 0.8367 (0.8378) time: 0.1350 data: 0.0590 max mem: 9390 +Train: [19] Total time: 0:14:23 (0.1381 s / it) +Averaged stats: lr: 0.000117 grad: 0.0682 (0.0666) loss: 0.8367 (0.8378) +Eval (hcp-train-subset): [19] [ 0/62] eta: 0:04:07 loss: 0.8609 (0.8609) time: 3.9862 data: 3.8897 max mem: 9390 +Eval (hcp-train-subset): [19] [61/62] eta: 0:00:00 loss: 0.8471 (0.8470) time: 0.1270 data: 0.1001 max mem: 9390 +Eval (hcp-train-subset): [19] Total time: 0:00:13 (0.2106 s / it) +Averaged stats (hcp-train-subset): loss: 0.8471 (0.8470) +Making plots (hcp-train-subset): example=48 +Eval (hcp-val): [19] [ 0/62] eta: 0:03:46 loss: 0.8381 (0.8381) time: 3.6559 data: 3.5532 max mem: 9390 +Eval (hcp-val): [19] [61/62] eta: 0:00:00 loss: 0.8413 (0.8415) time: 0.1286 data: 0.1040 max mem: 9390 +Eval (hcp-val): [19] Total time: 0:00:12 (0.1967 s / it) +Averaged stats (hcp-val): loss: 0.8413 (0.8415) +Making plots (hcp-val): example=9 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +Train: [20] [ 0/6250] eta: 7:19:45 lr: 0.000117 grad: 0.0540 (0.0540) loss: 0.8640 (0.8640) time: 4.2217 data: 4.0535 max mem: 9390 +Train: [20] [ 100/6250] eta: 0:19:13 lr: 0.000117 grad: 0.0708 (0.0719) loss: 0.8470 (0.8492) time: 0.1406 data: 0.0550 max mem: 9390 +Train: [20] [ 200/6250] eta: 0:17:01 lr: 0.000117 grad: 0.0686 (0.0711) loss: 0.8313 (0.8427) time: 0.1213 data: 0.0416 max mem: 9390 +Train: [20] [ 300/6250] eta: 0:15:45 lr: 0.000117 grad: 0.0661 (0.0706) loss: 0.8394 (0.8400) time: 0.1371 data: 0.0581 max mem: 9390 +Train: [20] [ 400/6250] eta: 0:14:59 lr: 0.000117 grad: 0.0670 (0.0697) loss: 0.8403 (0.8392) time: 0.1333 data: 0.0481 max mem: 9390 +Train: [20] [ 500/6250] eta: 0:14:56 lr: 0.000117 grad: 0.0644 (0.0685) loss: 0.8374 (0.8387) time: 0.1787 data: 0.0943 max mem: 9390 +Train: [20] [ 600/6250] eta: 0:14:40 lr: 0.000117 grad: 0.0604 (0.0676) loss: 0.8369 (0.8384) time: 0.1497 data: 0.0684 max mem: 9390 +Train: [20] [ 700/6250] eta: 0:14:20 lr: 0.000117 grad: 0.0628 (0.0674) loss: 0.8388 (0.8384) time: 0.1535 data: 0.0656 max mem: 9390 +Train: [20] [ 800/6250] eta: 0:13:56 lr: 0.000117 grad: 0.0685 (0.0673) loss: 0.8346 (0.8384) time: 0.1444 data: 0.0484 max mem: 9390 +Train: [20] [ 900/6250] eta: 0:13:35 lr: 0.000117 grad: 0.0617 (0.0670) loss: 0.8430 (0.8385) time: 0.1260 data: 0.0425 max mem: 9390 +Train: [20] [1000/6250] eta: 0:13:11 lr: 0.000117 grad: 0.0588 (0.0664) loss: 0.8370 (0.8385) time: 0.1281 data: 0.0465 max mem: 9390 +Train: [20] [1100/6250] eta: 0:12:50 lr: 0.000117 grad: 0.0581 (0.0662) loss: 0.8426 (0.8386) time: 0.1311 data: 0.0510 max mem: 9390 +Train: [20] [1200/6250] eta: 0:12:35 lr: 0.000117 grad: 0.0606 (0.0660) loss: 0.8372 (0.8387) time: 0.1543 data: 0.0687 max mem: 9390 +Train: [20] [1300/6250] eta: 0:12:21 lr: 0.000117 grad: 0.0610 (0.0658) loss: 0.8379 (0.8388) time: 0.1540 data: 0.0800 max mem: 9390 +Train: [20] [1400/6250] eta: 0:12:03 lr: 0.000117 grad: 0.0623 (0.0657) loss: 0.8410 (0.8387) time: 0.1243 data: 0.0472 max mem: 9390 +Train: [20] [1500/6250] eta: 0:11:46 lr: 0.000117 grad: 0.0639 (0.0657) loss: 0.8366 (0.8385) time: 0.1512 data: 0.0736 max mem: 9390 +Train: [20] [1600/6250] eta: 0:11:29 lr: 0.000117 grad: 0.0601 (0.0657) loss: 0.8395 (0.8385) time: 0.1364 data: 0.0551 max mem: 9390 +Train: [20] [1700/6250] eta: 0:11:12 lr: 0.000117 grad: 0.0598 (0.0657) loss: 0.8384 (0.8384) time: 0.1309 data: 0.0537 max mem: 9390 +Train: [20] [1800/6250] eta: 0:10:54 lr: 0.000117 grad: 0.0624 (0.0658) loss: 0.8399 (0.8383) time: 0.1185 data: 0.0346 max mem: 9390 +Train: [20] [1900/6250] eta: 0:10:39 lr: 0.000117 grad: 0.0644 (0.0659) loss: 0.8357 (0.8382) time: 0.1584 data: 0.0717 max mem: 9390 +Train: [20] [2000/6250] eta: 0:10:23 lr: 0.000117 grad: 0.0624 (0.0661) loss: 0.8363 (0.8380) time: 0.1308 data: 0.0558 max mem: 9390 +Train: [20] [2100/6250] eta: 0:10:10 lr: 0.000117 grad: 0.0649 (0.0662) loss: 0.8321 (0.8378) time: 0.1884 data: 0.1028 max mem: 9390 +Train: [20] [2200/6250] eta: 0:09:54 lr: 0.000117 grad: 0.0596 (0.0663) loss: 0.8410 (0.8377) time: 0.1381 data: 0.0533 max mem: 9390 +Train: [20] [2300/6250] eta: 0:09:38 lr: 0.000117 grad: 0.0620 (0.0663) loss: 0.8359 (0.8376) time: 0.1374 data: 0.0554 max mem: 9390 +Train: [20] [2400/6250] eta: 0:09:24 lr: 0.000117 grad: 0.0665 (0.0664) loss: 0.8327 (0.8375) time: 0.1516 data: 0.0552 max mem: 9390 +Train: [20] [2500/6250] eta: 0:09:09 lr: 0.000117 grad: 0.0662 (0.0664) loss: 0.8379 (0.8375) time: 0.1546 data: 0.0777 max mem: 9390 +Train: [20] [2600/6250] eta: 0:08:54 lr: 0.000117 grad: 0.0678 (0.0665) loss: 0.8347 (0.8375) time: 0.1165 data: 0.0374 max mem: 9390 +Train: [20] [2700/6250] eta: 0:08:39 lr: 0.000117 grad: 0.0636 (0.0664) loss: 0.8402 (0.8376) time: 0.1413 data: 0.0605 max mem: 9390 +Train: [20] [2800/6250] eta: 0:08:22 lr: 0.000117 grad: 0.0675 (0.0665) loss: 0.8421 (0.8376) time: 0.1353 data: 0.0576 max mem: 9390 +Train: [20] [2900/6250] eta: 0:08:07 lr: 0.000117 grad: 0.0642 (0.0665) loss: 0.8373 (0.8376) time: 0.1425 data: 0.0690 max mem: 9390 +Train: [20] [3000/6250] eta: 0:07:52 lr: 0.000117 grad: 0.0632 (0.0665) loss: 0.8383 (0.8376) time: 0.1387 data: 0.0580 max mem: 9390 +Train: [20] [3100/6250] eta: 0:07:36 lr: 0.000117 grad: 0.0613 (0.0665) loss: 0.8357 (0.8376) time: 0.1359 data: 0.0629 max mem: 9390 +Train: [20] [3200/6250] eta: 0:07:21 lr: 0.000117 grad: 0.0630 (0.0664) loss: 0.8361 (0.8376) time: 0.1208 data: 0.0387 max mem: 9390 +Train: [20] [3300/6250] eta: 0:07:06 lr: 0.000117 grad: 0.0632 (0.0664) loss: 0.8351 (0.8375) time: 0.1382 data: 0.0613 max mem: 9390 +Train: [20] [3400/6250] eta: 0:06:51 lr: 0.000117 grad: 0.0603 (0.0664) loss: 0.8379 (0.8375) time: 0.1213 data: 0.0423 max mem: 9390 +Train: [20] [3500/6250] eta: 0:06:36 lr: 0.000117 grad: 0.0638 (0.0664) loss: 0.8347 (0.8375) time: 0.1435 data: 0.0584 max mem: 9390 +Train: [20] [3600/6250] eta: 0:06:21 lr: 0.000117 grad: 0.0619 (0.0664) loss: 0.8384 (0.8374) time: 0.1172 data: 0.0397 max mem: 9390 +Train: [20] [3700/6250] eta: 0:06:06 lr: 0.000117 grad: 0.0622 (0.0664) loss: 0.8290 (0.8373) time: 0.1478 data: 0.0629 max mem: 9390 +Train: [20] [3800/6250] eta: 0:05:52 lr: 0.000117 grad: 0.0677 (0.0663) loss: 0.8319 (0.8373) time: 0.1277 data: 0.0469 max mem: 9390 +Train: [20] [3900/6250] eta: 0:05:37 lr: 0.000117 grad: 0.0609 (0.0663) loss: 0.8388 (0.8373) time: 0.1282 data: 0.0479 max mem: 9390 +Train: [20] [4000/6250] eta: 0:05:22 lr: 0.000117 grad: 0.0623 (0.0662) loss: 0.8337 (0.8373) time: 0.1422 data: 0.0557 max mem: 9390 +Train: [20] [4100/6250] eta: 0:05:07 lr: 0.000117 grad: 0.0633 (0.0663) loss: 0.8346 (0.8373) time: 0.1255 data: 0.0445 max mem: 9390 +Train: [20] [4200/6250] eta: 0:04:53 lr: 0.000117 grad: 0.0578 (0.0662) loss: 0.8404 (0.8374) time: 0.1488 data: 0.0784 max mem: 9390 +Train: [20] [4300/6250] eta: 0:04:38 lr: 0.000117 grad: 0.0675 (0.0663) loss: 0.8353 (0.8374) time: 0.1245 data: 0.0458 max mem: 9390 +Train: [20] [4400/6250] eta: 0:04:24 lr: 0.000117 grad: 0.0637 (0.0662) loss: 0.8330 (0.8374) time: 0.1613 data: 0.0729 max mem: 9390 +Train: [20] [4500/6250] eta: 0:04:09 lr: 0.000117 grad: 0.0593 (0.0662) loss: 0.8396 (0.8374) time: 0.1332 data: 0.0549 max mem: 9390 +Train: [20] [4600/6250] eta: 0:03:54 lr: 0.000117 grad: 0.0562 (0.0661) loss: 0.8421 (0.8374) time: 0.1527 data: 0.0722 max mem: 9390 +Train: [20] [4700/6250] eta: 0:03:40 lr: 0.000117 grad: 0.0609 (0.0660) loss: 0.8312 (0.8374) time: 0.1635 data: 0.0877 max mem: 9390 +Train: [20] [4800/6250] eta: 0:03:26 lr: 0.000117 grad: 0.0629 (0.0660) loss: 0.8406 (0.8374) time: 0.1267 data: 0.0510 max mem: 9390 +Train: [20] [4900/6250] eta: 0:03:11 lr: 0.000117 grad: 0.0662 (0.0660) loss: 0.8356 (0.8374) time: 0.1512 data: 0.0738 max mem: 9390 +Train: [20] [5000/6250] eta: 0:02:57 lr: 0.000117 grad: 0.0635 (0.0659) loss: 0.8349 (0.8374) time: 0.1268 data: 0.0464 max mem: 9390 +Train: [20] [5100/6250] eta: 0:02:43 lr: 0.000117 grad: 0.0651 (0.0659) loss: 0.8341 (0.8373) time: 0.1462 data: 0.0618 max mem: 9390 +Train: [20] [5200/6250] eta: 0:02:29 lr: 0.000117 grad: 0.0642 (0.0658) loss: 0.8390 (0.8373) time: 0.1245 data: 0.0449 max mem: 9390 +Train: [20] [5300/6250] eta: 0:02:14 lr: 0.000117 grad: 0.0633 (0.0658) loss: 0.8356 (0.8373) time: 0.1332 data: 0.0534 max mem: 9390 +Train: [20] [5400/6250] eta: 0:02:00 lr: 0.000117 grad: 0.0623 (0.0658) loss: 0.8375 (0.8373) time: 0.1241 data: 0.0473 max mem: 9390 +Train: [20] [5500/6250] eta: 0:01:46 lr: 0.000117 grad: 0.0645 (0.0658) loss: 0.8331 (0.8373) time: 0.1363 data: 0.0611 max mem: 9390 +Train: [20] [5600/6250] eta: 0:01:32 lr: 0.000117 grad: 0.0619 (0.0658) loss: 0.8390 (0.8373) time: 0.1304 data: 0.0549 max mem: 9390 +Train: [20] [5700/6250] eta: 0:01:17 lr: 0.000117 grad: 0.0627 (0.0658) loss: 0.8358 (0.8373) time: 0.1207 data: 0.0444 max mem: 9390 +Train: [20] [5800/6250] eta: 0:01:03 lr: 0.000117 grad: 0.0612 (0.0658) loss: 0.8407 (0.8373) time: 0.1492 data: 0.0683 max mem: 9390 +Train: [20] [5900/6250] eta: 0:00:49 lr: 0.000117 grad: 0.0642 (0.0658) loss: 0.8366 (0.8373) time: 0.1246 data: 0.0329 max mem: 9390 +Train: [20] [6000/6250] eta: 0:00:35 lr: 0.000116 grad: 0.0669 (0.0658) loss: 0.8350 (0.8373) time: 0.0870 data: 0.0016 max mem: 9390 +Train: [20] [6100/6250] eta: 0:00:21 lr: 0.000116 grad: 0.0663 (0.0658) loss: 0.8360 (0.8373) time: 0.1239 data: 0.0416 max mem: 9390 +Train: [20] [6200/6250] eta: 0:00:07 lr: 0.000116 grad: 0.0687 (0.0658) loss: 0.8296 (0.8372) time: 0.1405 data: 0.0659 max mem: 9390 +Train: [20] [6249/6250] eta: 0:00:00 lr: 0.000116 grad: 0.0655 (0.0659) loss: 0.8269 (0.8372) time: 0.1689 data: 0.0852 max mem: 9390 +Train: [20] Total time: 0:14:50 (0.1425 s / it) +Averaged stats: lr: 0.000116 grad: 0.0655 (0.0659) loss: 0.8269 (0.8372) +Eval (hcp-train-subset): [20] [ 0/62] eta: 0:03:17 loss: 0.8582 (0.8582) time: 3.1854 data: 3.1024 max mem: 9390 +Eval (hcp-train-subset): [20] [61/62] eta: 0:00:00 loss: 0.8456 (0.8460) time: 0.1031 data: 0.0784 max mem: 9390 +Eval (hcp-train-subset): [20] Total time: 0:00:13 (0.2111 s / it) +Averaged stats (hcp-train-subset): loss: 0.8456 (0.8460) +Eval (hcp-val): [20] [ 0/62] eta: 0:03:21 loss: 0.8373 (0.8373) time: 3.2547 data: 3.1942 max mem: 9390 +Eval (hcp-val): [20] [61/62] eta: 0:00:00 loss: 0.8408 (0.8408) time: 0.1167 data: 0.0872 max mem: 9390 +Eval (hcp-val): [20] Total time: 0:00:12 (0.1965 s / it) +Averaged stats (hcp-val): loss: 0.8408 (0.8408) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +Train: [21] [ 0/6250] eta: 9:44:19 lr: 0.000116 grad: 0.0809 (0.0809) loss: 0.8156 (0.8156) time: 5.6095 data: 5.5129 max mem: 9390 +Train: [21] [ 100/6250] eta: 0:18:53 lr: 0.000116 grad: 0.0686 (0.0751) loss: 0.8311 (0.8342) time: 0.1341 data: 0.0528 max mem: 9390 +Train: [21] [ 200/6250] eta: 0:18:13 lr: 0.000116 grad: 0.0648 (0.0716) loss: 0.8320 (0.8314) time: 0.1545 data: 0.0776 max mem: 9390 +Train: [21] [ 300/6250] eta: 0:17:09 lr: 0.000116 grad: 0.0611 (0.0706) loss: 0.8322 (0.8314) time: 0.1546 data: 0.0763 max mem: 9390 +Train: [21] [ 400/6250] eta: 0:16:07 lr: 0.000116 grad: 0.0608 (0.0700) loss: 0.8379 (0.8326) time: 0.1337 data: 0.0531 max mem: 9390 +Train: [21] [ 500/6250] eta: 0:15:31 lr: 0.000116 grad: 0.0641 (0.0693) loss: 0.8404 (0.8335) time: 0.1423 data: 0.0583 max mem: 9390 +Train: [21] [ 600/6250] eta: 0:14:54 lr: 0.000116 grad: 0.0594 (0.0684) loss: 0.8410 (0.8343) time: 0.1341 data: 0.0490 max mem: 9390 +Train: [21] [ 700/6250] eta: 0:14:22 lr: 0.000116 grad: 0.0593 (0.0679) loss: 0.8404 (0.8346) time: 0.1213 data: 0.0362 max mem: 9390 +Train: [21] [ 800/6250] eta: 0:13:53 lr: 0.000116 grad: 0.0642 (0.0672) loss: 0.8376 (0.8351) time: 0.1347 data: 0.0497 max mem: 9390 +Train: [21] [ 900/6250] eta: 0:13:30 lr: 0.000116 grad: 0.0626 (0.0668) loss: 0.8400 (0.8357) time: 0.1420 data: 0.0596 max mem: 9390 +Train: [21] [1000/6250] eta: 0:13:13 lr: 0.000116 grad: 0.0596 (0.0664) loss: 0.8366 (0.8362) time: 0.1502 data: 0.0690 max mem: 9390 +Train: [21] [1100/6250] eta: 0:12:55 lr: 0.000116 grad: 0.0630 (0.0661) loss: 0.8363 (0.8366) time: 0.1231 data: 0.0433 max mem: 9390 +Train: [21] [1200/6250] eta: 0:12:35 lr: 0.000116 grad: 0.0622 (0.0659) loss: 0.8396 (0.8370) time: 0.1407 data: 0.0647 max mem: 9390 +Train: [21] [1300/6250] eta: 0:12:16 lr: 0.000116 grad: 0.0632 (0.0660) loss: 0.8376 (0.8371) time: 0.1035 data: 0.0211 max mem: 9390 +Train: [21] [1400/6250] eta: 0:11:58 lr: 0.000116 grad: 0.0639 (0.0659) loss: 0.8391 (0.8373) time: 0.1373 data: 0.0602 max mem: 9390 +Train: [21] [1500/6250] eta: 0:11:40 lr: 0.000116 grad: 0.0651 (0.0658) loss: 0.8368 (0.8374) time: 0.1400 data: 0.0600 max mem: 9390 +Train: [21] [1600/6250] eta: 0:11:24 lr: 0.000116 grad: 0.0619 (0.0657) loss: 0.8396 (0.8375) time: 0.1611 data: 0.0766 max mem: 9390 +Train: [21] [1700/6250] eta: 0:11:09 lr: 0.000116 grad: 0.0631 (0.0655) loss: 0.8436 (0.8374) time: 0.1608 data: 0.0819 max mem: 9390 +Train: [21] [1800/6250] eta: 0:10:53 lr: 0.000116 grad: 0.0599 (0.0656) loss: 0.8388 (0.8375) time: 0.1414 data: 0.0619 max mem: 9390 +Train: [21] [1900/6250] eta: 0:10:36 lr: 0.000116 grad: 0.0624 (0.0656) loss: 0.8341 (0.8375) time: 0.1391 data: 0.0623 max mem: 9390 +Train: [21] [2000/6250] eta: 0:10:19 lr: 0.000116 grad: 0.0615 (0.0654) loss: 0.8378 (0.8374) time: 0.1457 data: 0.0727 max mem: 9390 +Train: [21] [2100/6250] eta: 0:10:03 lr: 0.000116 grad: 0.0609 (0.0654) loss: 0.8414 (0.8375) time: 0.1407 data: 0.0655 max mem: 9390 +Train: [21] [2200/6250] eta: 0:09:53 lr: 0.000116 grad: 0.0624 (0.0653) loss: 0.8399 (0.8377) time: 0.2723 data: 0.1867 max mem: 9390 +Train: [21] [2300/6250] eta: 0:09:35 lr: 0.000116 grad: 0.0629 (0.0652) loss: 0.8412 (0.8378) time: 0.1519 data: 0.0737 max mem: 9390 +Train: [21] [2400/6250] eta: 0:09:19 lr: 0.000116 grad: 0.0615 (0.0652) loss: 0.8437 (0.8379) time: 0.1144 data: 0.0349 max mem: 9390 +Train: [21] [2500/6250] eta: 0:09:02 lr: 0.000116 grad: 0.0623 (0.0651) loss: 0.8365 (0.8380) time: 0.1298 data: 0.0531 max mem: 9390 +Train: [21] [2600/6250] eta: 0:08:47 lr: 0.000116 grad: 0.0635 (0.0650) loss: 0.8360 (0.8381) time: 0.1402 data: 0.0526 max mem: 9390 +Train: [21] [2700/6250] eta: 0:08:32 lr: 0.000116 grad: 0.0626 (0.0650) loss: 0.8378 (0.8381) time: 0.1258 data: 0.0448 max mem: 9390 +Train: [21] [2800/6250] eta: 0:08:16 lr: 0.000116 grad: 0.0647 (0.0649) loss: 0.8394 (0.8381) time: 0.1132 data: 0.0351 max mem: 9390 +Train: [21] [2900/6250] eta: 0:08:01 lr: 0.000116 grad: 0.0642 (0.0650) loss: 0.8380 (0.8381) time: 0.1441 data: 0.0679 max mem: 9390 +Train: [21] [3000/6250] eta: 0:07:45 lr: 0.000116 grad: 0.0584 (0.0649) loss: 0.8374 (0.8381) time: 0.1313 data: 0.0499 max mem: 9390 +Train: [21] [3100/6250] eta: 0:07:31 lr: 0.000116 grad: 0.0622 (0.0649) loss: 0.8412 (0.8382) time: 0.1461 data: 0.0671 max mem: 9390 +Train: [21] [3200/6250] eta: 0:07:16 lr: 0.000116 grad: 0.0614 (0.0649) loss: 0.8379 (0.8382) time: 0.1479 data: 0.0538 max mem: 9390 +Train: [21] [3300/6250] eta: 0:07:03 lr: 0.000116 grad: 0.0659 (0.0649) loss: 0.8360 (0.8381) time: 0.1574 data: 0.0768 max mem: 9390 +Train: [21] [3400/6250] eta: 0:06:47 lr: 0.000116 grad: 0.0687 (0.0650) loss: 0.8395 (0.8380) time: 0.1434 data: 0.0655 max mem: 9390 +Train: [21] [3500/6250] eta: 0:06:32 lr: 0.000116 grad: 0.0626 (0.0650) loss: 0.8385 (0.8380) time: 0.1263 data: 0.0485 max mem: 9390 +Train: [21] [3600/6250] eta: 0:06:17 lr: 0.000116 grad: 0.0637 (0.0650) loss: 0.8334 (0.8379) time: 0.1377 data: 0.0543 max mem: 9390 +Train: [21] [3700/6250] eta: 0:06:03 lr: 0.000116 grad: 0.0625 (0.0650) loss: 0.8370 (0.8378) time: 0.1326 data: 0.0537 max mem: 9390 +Train: [21] [3800/6250] eta: 0:05:48 lr: 0.000116 grad: 0.0623 (0.0650) loss: 0.8360 (0.8377) time: 0.1544 data: 0.0786 max mem: 9390 +Train: [21] [3900/6250] eta: 0:05:33 lr: 0.000116 grad: 0.0614 (0.0651) loss: 0.8390 (0.8377) time: 0.1355 data: 0.0596 max mem: 9390 +Train: [21] [4000/6250] eta: 0:05:19 lr: 0.000116 grad: 0.0628 (0.0651) loss: 0.8357 (0.8376) time: 0.1399 data: 0.0660 max mem: 9390 +Train: [21] [4100/6250] eta: 0:05:04 lr: 0.000116 grad: 0.0610 (0.0650) loss: 0.8359 (0.8375) time: 0.1272 data: 0.0414 max mem: 9390 +Train: [21] [4200/6250] eta: 0:04:50 lr: 0.000116 grad: 0.0642 (0.0650) loss: 0.8363 (0.8375) time: 0.1427 data: 0.0640 max mem: 9390 +Train: [21] [4300/6250] eta: 0:04:35 lr: 0.000116 grad: 0.0609 (0.0650) loss: 0.8338 (0.8375) time: 0.1466 data: 0.0700 max mem: 9390 +Train: [21] [4400/6250] eta: 0:04:21 lr: 0.000116 grad: 0.0616 (0.0650) loss: 0.8342 (0.8374) time: 0.1288 data: 0.0562 max mem: 9390 +Train: [21] [4500/6250] eta: 0:04:07 lr: 0.000116 grad: 0.0606 (0.0650) loss: 0.8342 (0.8374) time: 0.1523 data: 0.0686 max mem: 9390 +Train: [21] [4600/6250] eta: 0:03:52 lr: 0.000116 grad: 0.0673 (0.0650) loss: 0.8367 (0.8373) time: 0.1311 data: 0.0444 max mem: 9390 +Train: [21] [4700/6250] eta: 0:03:38 lr: 0.000116 grad: 0.0612 (0.0650) loss: 0.8376 (0.8373) time: 0.1663 data: 0.0899 max mem: 9390 +Train: [21] [4800/6250] eta: 0:03:24 lr: 0.000116 grad: 0.0647 (0.0650) loss: 0.8356 (0.8372) time: 0.1289 data: 0.0454 max mem: 9390 +Train: [21] [4900/6250] eta: 0:03:10 lr: 0.000116 grad: 0.0620 (0.0650) loss: 0.8315 (0.8372) time: 0.1417 data: 0.0666 max mem: 9390 +Train: [21] [5000/6250] eta: 0:02:56 lr: 0.000116 grad: 0.0629 (0.0650) loss: 0.8351 (0.8371) time: 0.1166 data: 0.0359 max mem: 9390 +Train: [21] [5100/6250] eta: 0:02:41 lr: 0.000116 grad: 0.0628 (0.0651) loss: 0.8341 (0.8371) time: 0.1531 data: 0.0589 max mem: 9390 +Train: [21] [5200/6250] eta: 0:02:27 lr: 0.000116 grad: 0.0639 (0.0651) loss: 0.8344 (0.8371) time: 0.1485 data: 0.0670 max mem: 9390 +Train: [21] [5300/6250] eta: 0:02:13 lr: 0.000116 grad: 0.0663 (0.0651) loss: 0.8389 (0.8371) time: 0.1326 data: 0.0542 max mem: 9390 +Train: [21] [5400/6250] eta: 0:01:59 lr: 0.000116 grad: 0.0659 (0.0652) loss: 0.8336 (0.8370) time: 0.1387 data: 0.0608 max mem: 9390 +Train: [21] [5500/6250] eta: 0:01:45 lr: 0.000116 grad: 0.0634 (0.0652) loss: 0.8358 (0.8370) time: 0.1422 data: 0.0559 max mem: 9390 +Train: [21] [5600/6250] eta: 0:01:31 lr: 0.000115 grad: 0.0659 (0.0652) loss: 0.8326 (0.8370) time: 0.1502 data: 0.0588 max mem: 9390 +Train: [21] [5700/6250] eta: 0:01:17 lr: 0.000115 grad: 0.0649 (0.0652) loss: 0.8372 (0.8370) time: 0.1510 data: 0.0687 max mem: 9390 +Train: [21] [5800/6250] eta: 0:01:03 lr: 0.000115 grad: 0.0641 (0.0652) loss: 0.8364 (0.8369) time: 0.1285 data: 0.0504 max mem: 9390 +Train: [21] [5900/6250] eta: 0:00:49 lr: 0.000115 grad: 0.0625 (0.0652) loss: 0.8352 (0.8369) time: 0.1227 data: 0.0446 max mem: 9390 +Train: [21] [6000/6250] eta: 0:00:35 lr: 0.000115 grad: 0.0677 (0.0653) loss: 0.8327 (0.8369) time: 0.1671 data: 0.0715 max mem: 9390 +Train: [21] [6100/6250] eta: 0:00:21 lr: 0.000115 grad: 0.0662 (0.0653) loss: 0.8330 (0.8369) time: 0.1658 data: 0.0759 max mem: 9390 +Train: [21] [6200/6250] eta: 0:00:07 lr: 0.000115 grad: 0.0696 (0.0653) loss: 0.8292 (0.8368) time: 0.1493 data: 0.0729 max mem: 9390 +Train: [21] [6249/6250] eta: 0:00:00 lr: 0.000115 grad: 0.0626 (0.0653) loss: 0.8345 (0.8368) time: 0.1484 data: 0.0685 max mem: 9390 +Train: [21] Total time: 0:14:49 (0.1423 s / it) +Averaged stats: lr: 0.000115 grad: 0.0626 (0.0653) loss: 0.8345 (0.8368) +Eval (hcp-train-subset): [21] [ 0/62] eta: 0:04:41 loss: 0.8565 (0.8565) time: 4.5454 data: 4.5120 max mem: 9390 +Eval (hcp-train-subset): [21] [61/62] eta: 0:00:00 loss: 0.8466 (0.8460) time: 0.1167 data: 0.0917 max mem: 9390 +Eval (hcp-train-subset): [21] Total time: 0:00:13 (0.2188 s / it) +Averaged stats (hcp-train-subset): loss: 0.8466 (0.8460) +Eval (hcp-val): [21] [ 0/62] eta: 0:05:19 loss: 0.8383 (0.8383) time: 5.1463 data: 5.1166 max mem: 9390 +Eval (hcp-val): [21] [61/62] eta: 0:00:00 loss: 0.8411 (0.8410) time: 0.1082 data: 0.0818 max mem: 9390 +Eval (hcp-val): [21] Total time: 0:00:12 (0.2040 s / it) +Averaged stats (hcp-val): loss: 0.8411 (0.8410) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +Train: [22] [ 0/6250] eta: 8:48:47 lr: 0.000115 grad: 0.0682 (0.0682) loss: 0.8431 (0.8431) time: 5.0764 data: 4.7418 max mem: 9390 +Train: [22] [ 100/6250] eta: 0:22:26 lr: 0.000115 grad: 0.0710 (0.0756) loss: 0.8337 (0.8353) time: 0.1399 data: 0.0621 max mem: 9390 +Train: [22] [ 200/6250] eta: 0:19:06 lr: 0.000115 grad: 0.0654 (0.0729) loss: 0.8233 (0.8308) time: 0.1637 data: 0.0872 max mem: 9390 +Train: [22] [ 300/6250] eta: 0:17:36 lr: 0.000115 grad: 0.0627 (0.0700) loss: 0.8286 (0.8313) time: 0.1641 data: 0.0743 max mem: 9390 +Train: [22] [ 400/6250] eta: 0:16:49 lr: 0.000115 grad: 0.0629 (0.0696) loss: 0.8315 (0.8311) time: 0.1420 data: 0.0589 max mem: 9390 +Train: [22] [ 500/6250] eta: 0:16:02 lr: 0.000115 grad: 0.0614 (0.0689) loss: 0.8350 (0.8314) time: 0.1302 data: 0.0417 max mem: 9390 +Train: [22] [ 600/6250] eta: 0:15:27 lr: 0.000115 grad: 0.0624 (0.0681) loss: 0.8336 (0.8317) time: 0.1121 data: 0.0167 max mem: 9390 +Train: [22] [ 700/6250] eta: 0:14:58 lr: 0.000115 grad: 0.0619 (0.0680) loss: 0.8326 (0.8320) time: 0.1705 data: 0.0842 max mem: 9390 +Train: [22] [ 800/6250] eta: 0:14:27 lr: 0.000115 grad: 0.0628 (0.0676) loss: 0.8372 (0.8324) time: 0.1261 data: 0.0377 max mem: 9390 +Train: [22] [ 900/6250] eta: 0:14:06 lr: 0.000115 grad: 0.0614 (0.0673) loss: 0.8356 (0.8329) time: 0.1518 data: 0.0663 max mem: 9390 +Train: [22] [1000/6250] eta: 0:13:46 lr: 0.000115 grad: 0.0609 (0.0670) loss: 0.8330 (0.8330) time: 0.1708 data: 0.0805 max mem: 9390 +Train: [22] [1100/6250] eta: 0:13:27 lr: 0.000115 grad: 0.0632 (0.0670) loss: 0.8386 (0.8332) time: 0.1631 data: 0.0872 max mem: 9390 +Train: [22] [1200/6250] eta: 0:13:10 lr: 0.000115 grad: 0.0611 (0.0669) loss: 0.8342 (0.8332) time: 0.1474 data: 0.0715 max mem: 9390 +Train: [22] [1300/6250] eta: 0:12:51 lr: 0.000115 grad: 0.0666 (0.0670) loss: 0.8315 (0.8332) time: 0.1650 data: 0.0862 max mem: 9390 +Train: [22] [1400/6250] eta: 0:12:28 lr: 0.000115 grad: 0.0675 (0.0671) loss: 0.8286 (0.8332) time: 0.1107 data: 0.0325 max mem: 9390 +Train: [22] [1500/6250] eta: 0:12:09 lr: 0.000115 grad: 0.0666 (0.0670) loss: 0.8370 (0.8333) time: 0.1562 data: 0.0820 max mem: 9390 +Train: [22] [1600/6250] eta: 0:11:52 lr: 0.000115 grad: 0.0631 (0.0671) loss: 0.8353 (0.8334) time: 0.1657 data: 0.0913 max mem: 9390 +Train: [22] [1700/6250] eta: 0:11:36 lr: 0.000115 grad: 0.0667 (0.0673) loss: 0.8336 (0.8334) time: 0.1466 data: 0.0719 max mem: 9390 +Train: [22] [1800/6250] eta: 0:11:18 lr: 0.000115 grad: 0.0647 (0.0674) loss: 0.8326 (0.8334) time: 0.1533 data: 0.0720 max mem: 9390 +Train: [22] [1900/6250] eta: 0:11:02 lr: 0.000115 grad: 0.0642 (0.0674) loss: 0.8298 (0.8333) time: 0.1495 data: 0.0618 max mem: 9390 +Train: [22] [2000/6250] eta: 0:10:45 lr: 0.000115 grad: 0.0659 (0.0673) loss: 0.8382 (0.8334) time: 0.1401 data: 0.0489 max mem: 9390 +Train: [22] [2100/6250] eta: 0:10:27 lr: 0.000115 grad: 0.0644 (0.0672) loss: 0.8352 (0.8335) time: 0.1287 data: 0.0478 max mem: 9390 +Train: [22] [2200/6250] eta: 0:10:09 lr: 0.000115 grad: 0.0723 (0.0673) loss: 0.8335 (0.8335) time: 0.1269 data: 0.0495 max mem: 9390 +Train: [22] [2300/6250] eta: 0:09:52 lr: 0.000115 grad: 0.0707 (0.0673) loss: 0.8302 (0.8334) time: 0.1356 data: 0.0622 max mem: 9390 +Train: [22] [2400/6250] eta: 0:09:34 lr: 0.000115 grad: 0.0637 (0.0673) loss: 0.8349 (0.8334) time: 0.1260 data: 0.0433 max mem: 9390 +Train: [22] [2500/6250] eta: 0:09:16 lr: 0.000115 grad: 0.0614 (0.0673) loss: 0.8300 (0.8334) time: 0.1180 data: 0.0407 max mem: 9390 +Train: [22] [2600/6250] eta: 0:09:00 lr: 0.000115 grad: 0.0647 (0.0673) loss: 0.8307 (0.8333) time: 0.1017 data: 0.0126 max mem: 9390 +Train: [22] [2700/6250] eta: 0:08:44 lr: 0.000115 grad: 0.0684 (0.0673) loss: 0.8324 (0.8333) time: 0.1506 data: 0.0717 max mem: 9390 +Train: [22] [2800/6250] eta: 0:08:28 lr: 0.000115 grad: 0.0690 (0.0674) loss: 0.8329 (0.8333) time: 0.1385 data: 0.0650 max mem: 9390 +Train: [22] [2900/6250] eta: 0:08:14 lr: 0.000115 grad: 0.0613 (0.0673) loss: 0.8345 (0.8333) time: 0.1529 data: 0.0740 max mem: 9390 +Train: [22] [3000/6250] eta: 0:07:58 lr: 0.000115 grad: 0.0651 (0.0673) loss: 0.8374 (0.8334) time: 0.1471 data: 0.0683 max mem: 9390 +Train: [22] [3100/6250] eta: 0:07:42 lr: 0.000115 grad: 0.0659 (0.0672) loss: 0.8379 (0.8335) time: 0.1268 data: 0.0523 max mem: 9390 +Train: [22] [3200/6250] eta: 0:07:25 lr: 0.000115 grad: 0.0633 (0.0671) loss: 0.8331 (0.8335) time: 0.1311 data: 0.0570 max mem: 9390 +Train: [22] [3300/6250] eta: 0:07:10 lr: 0.000115 grad: 0.0652 (0.0670) loss: 0.8375 (0.8336) time: 0.1277 data: 0.0494 max mem: 9390 +Train: [22] [3400/6250] eta: 0:06:55 lr: 0.000115 grad: 0.0648 (0.0670) loss: 0.8377 (0.8336) time: 0.1401 data: 0.0578 max mem: 9390 +Train: [22] [3500/6250] eta: 0:06:39 lr: 0.000115 grad: 0.0699 (0.0670) loss: 0.8339 (0.8337) time: 0.1574 data: 0.0780 max mem: 9390 +Train: [22] [3600/6250] eta: 0:06:24 lr: 0.000115 grad: 0.0614 (0.0669) loss: 0.8302 (0.8337) time: 0.1295 data: 0.0507 max mem: 9390 +Train: [22] [3700/6250] eta: 0:06:09 lr: 0.000115 grad: 0.0657 (0.0669) loss: 0.8326 (0.8337) time: 0.1365 data: 0.0514 max mem: 9390 +Train: [22] [3800/6250] eta: 0:05:55 lr: 0.000115 grad: 0.0682 (0.0669) loss: 0.8342 (0.8337) time: 0.1414 data: 0.0621 max mem: 9390 +Train: [22] [3900/6250] eta: 0:05:40 lr: 0.000115 grad: 0.0682 (0.0668) loss: 0.8336 (0.8338) time: 0.1349 data: 0.0570 max mem: 9390 +Train: [22] [4000/6250] eta: 0:05:25 lr: 0.000115 grad: 0.0634 (0.0668) loss: 0.8383 (0.8339) time: 0.1396 data: 0.0653 max mem: 9390 +Train: [22] [4100/6250] eta: 0:05:10 lr: 0.000115 grad: 0.0657 (0.0668) loss: 0.8367 (0.8339) time: 0.1560 data: 0.0812 max mem: 9390 +Train: [22] [4200/6250] eta: 0:04:55 lr: 0.000115 grad: 0.0654 (0.0668) loss: 0.8354 (0.8339) time: 0.1237 data: 0.0477 max mem: 9390 +Train: [22] [4300/6250] eta: 0:04:41 lr: 0.000115 grad: 0.0627 (0.0667) loss: 0.8389 (0.8340) time: 0.1407 data: 0.0636 max mem: 9390 +Train: [22] [4400/6250] eta: 0:04:26 lr: 0.000115 grad: 0.0657 (0.0667) loss: 0.8338 (0.8340) time: 0.1383 data: 0.0598 max mem: 9390 +Train: [22] [4500/6250] eta: 0:04:11 lr: 0.000115 grad: 0.0664 (0.0667) loss: 0.8290 (0.8340) time: 0.1455 data: 0.0698 max mem: 9390 +Train: [22] [4600/6250] eta: 0:03:57 lr: 0.000115 grad: 0.0649 (0.0668) loss: 0.8308 (0.8340) time: 0.1637 data: 0.0893 max mem: 9390 +Train: [22] [4700/6250] eta: 0:03:42 lr: 0.000115 grad: 0.0650 (0.0668) loss: 0.8299 (0.8340) time: 0.1327 data: 0.0532 max mem: 9390 +Train: [22] [4800/6250] eta: 0:03:27 lr: 0.000115 grad: 0.0625 (0.0667) loss: 0.8360 (0.8341) time: 0.1192 data: 0.0433 max mem: 9390 +Train: [22] [4900/6250] eta: 0:03:13 lr: 0.000114 grad: 0.0638 (0.0668) loss: 0.8366 (0.8341) time: 0.1686 data: 0.0796 max mem: 9390 +Train: [22] [5000/6250] eta: 0:02:58 lr: 0.000114 grad: 0.0622 (0.0668) loss: 0.8424 (0.8342) time: 0.1585 data: 0.0734 max mem: 9390 +Train: [22] [5100/6250] eta: 0:02:44 lr: 0.000114 grad: 0.0639 (0.0668) loss: 0.8401 (0.8343) time: 0.1447 data: 0.0612 max mem: 9390 +Train: [22] [5200/6250] eta: 0:02:29 lr: 0.000114 grad: 0.0646 (0.0668) loss: 0.8312 (0.8343) time: 0.1355 data: 0.0533 max mem: 9390 +Train: [22] [5300/6250] eta: 0:02:15 lr: 0.000114 grad: 0.0703 (0.0667) loss: 0.8353 (0.8343) time: 0.1579 data: 0.0712 max mem: 9390 +Train: [22] [5400/6250] eta: 0:02:01 lr: 0.000114 grad: 0.0649 (0.0667) loss: 0.8362 (0.8344) time: 0.1441 data: 0.0608 max mem: 9390 +Train: [22] [5500/6250] eta: 0:01:47 lr: 0.000114 grad: 0.0613 (0.0667) loss: 0.8329 (0.8344) time: 0.1426 data: 0.0632 max mem: 9390 +Train: [22] [5600/6250] eta: 0:01:32 lr: 0.000114 grad: 0.0666 (0.0667) loss: 0.8317 (0.8344) time: 0.1255 data: 0.0484 max mem: 9390 +Train: [22] [5700/6250] eta: 0:01:18 lr: 0.000114 grad: 0.0660 (0.0667) loss: 0.8383 (0.8344) time: 0.1426 data: 0.0656 max mem: 9390 +Train: [22] [5800/6250] eta: 0:01:04 lr: 0.000114 grad: 0.0628 (0.0666) loss: 0.8346 (0.8344) time: 0.1302 data: 0.0566 max mem: 9390 +Train: [22] [5900/6250] eta: 0:00:49 lr: 0.000114 grad: 0.0648 (0.0666) loss: 0.8352 (0.8344) time: 0.1288 data: 0.0504 max mem: 9390 +Train: [22] [6000/6250] eta: 0:00:35 lr: 0.000114 grad: 0.0638 (0.0665) loss: 0.8355 (0.8345) time: 0.1150 data: 0.0308 max mem: 9390 +Train: [22] [6100/6250] eta: 0:00:21 lr: 0.000114 grad: 0.0631 (0.0665) loss: 0.8319 (0.8345) time: 0.1225 data: 0.0422 max mem: 9390 +Train: [22] [6200/6250] eta: 0:00:07 lr: 0.000114 grad: 0.0616 (0.0664) loss: 0.8365 (0.8346) time: 0.1294 data: 0.0507 max mem: 9390 +Train: [22] [6249/6250] eta: 0:00:00 lr: 0.000114 grad: 0.0647 (0.0664) loss: 0.8362 (0.8346) time: 0.1314 data: 0.0558 max mem: 9390 +Train: [22] Total time: 0:14:51 (0.1427 s / it) +Averaged stats: lr: 0.000114 grad: 0.0647 (0.0664) loss: 0.8362 (0.8346) +Eval (hcp-train-subset): [22] [ 0/62] eta: 0:04:07 loss: 0.8550 (0.8550) time: 3.9853 data: 3.9140 max mem: 9390 +Eval (hcp-train-subset): [22] [61/62] eta: 0:00:00 loss: 0.8450 (0.8446) time: 0.1510 data: 0.1259 max mem: 9390 +Eval (hcp-train-subset): [22] Total time: 0:00:13 (0.2239 s / it) +Averaged stats (hcp-train-subset): loss: 0.8450 (0.8446) +Eval (hcp-val): [22] [ 0/62] eta: 0:04:56 loss: 0.8378 (0.8378) time: 4.7874 data: 4.7554 max mem: 9390 +Eval (hcp-val): [22] [61/62] eta: 0:00:00 loss: 0.8399 (0.8410) time: 0.1378 data: 0.1128 max mem: 9390 +Eval (hcp-val): [22] Total time: 0:00:13 (0.2105 s / it) +Averaged stats (hcp-val): loss: 0.8399 (0.8410) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +Train: [23] [ 0/6250] eta: 8:51:44 lr: 0.000114 grad: 0.0585 (0.0585) loss: 0.8725 (0.8725) time: 5.1047 data: 4.8742 max mem: 9390 +Train: [23] [ 100/6250] eta: 0:23:11 lr: 0.000114 grad: 0.0611 (0.0674) loss: 0.8394 (0.8415) time: 0.1712 data: 0.0792 max mem: 9390 +Train: [23] [ 200/6250] eta: 0:19:08 lr: 0.000114 grad: 0.0606 (0.0658) loss: 0.8303 (0.8395) time: 0.1487 data: 0.0736 max mem: 9390 +Train: [23] [ 300/6250] eta: 0:17:34 lr: 0.000114 grad: 0.0577 (0.0639) loss: 0.8380 (0.8385) time: 0.1126 data: 0.0300 max mem: 9390 +Train: [23] [ 400/6250] eta: 0:16:33 lr: 0.000114 grad: 0.0593 (0.0629) loss: 0.8384 (0.8385) time: 0.1396 data: 0.0574 max mem: 9390 +Train: [23] [ 500/6250] eta: 0:15:50 lr: 0.000114 grad: 0.0601 (0.0627) loss: 0.8366 (0.8382) time: 0.1283 data: 0.0418 max mem: 9390 +Train: [23] [ 600/6250] eta: 0:15:17 lr: 0.000114 grad: 0.0608 (0.0624) loss: 0.8317 (0.8376) time: 0.1618 data: 0.0786 max mem: 9390 +Train: [23] [ 700/6250] eta: 0:14:43 lr: 0.000114 grad: 0.0624 (0.0627) loss: 0.8310 (0.8377) time: 0.1147 data: 0.0274 max mem: 9390 +Train: [23] [ 800/6250] eta: 0:14:11 lr: 0.000114 grad: 0.0612 (0.0629) loss: 0.8353 (0.8372) time: 0.1174 data: 0.0341 max mem: 9390 +Train: [23] [ 900/6250] eta: 0:13:54 lr: 0.000114 grad: 0.0629 (0.0630) loss: 0.8341 (0.8370) time: 0.1865 data: 0.1009 max mem: 9390 +Train: [23] [1000/6250] eta: 0:13:30 lr: 0.000114 grad: 0.0613 (0.0632) loss: 0.8344 (0.8368) time: 0.1201 data: 0.0403 max mem: 9390 +Train: [23] [1100/6250] eta: 0:13:09 lr: 0.000114 grad: 0.0628 (0.0635) loss: 0.8350 (0.8365) time: 0.1428 data: 0.0693 max mem: 9390 +Train: [23] [1200/6250] eta: 0:12:47 lr: 0.000114 grad: 0.0616 (0.0637) loss: 0.8339 (0.8362) time: 0.1484 data: 0.0693 max mem: 9390 +Train: [23] [1300/6250] eta: 0:12:34 lr: 0.000114 grad: 0.0662 (0.0643) loss: 0.8362 (0.8360) time: 0.1761 data: 0.0741 max mem: 9390 +Train: [23] [1400/6250] eta: 0:12:16 lr: 0.000114 grad: 0.0644 (0.0644) loss: 0.8323 (0.8358) time: 0.1292 data: 0.0401 max mem: 9390 +Train: [23] [1500/6250] eta: 0:11:56 lr: 0.000114 grad: 0.0617 (0.0645) loss: 0.8319 (0.8355) time: 0.1217 data: 0.0443 max mem: 9390 +Train: [23] [1600/6250] eta: 0:11:40 lr: 0.000114 grad: 0.0647 (0.0647) loss: 0.8311 (0.8354) time: 0.1714 data: 0.0847 max mem: 9390 +Train: [23] [1700/6250] eta: 0:11:21 lr: 0.000114 grad: 0.0627 (0.0648) loss: 0.8344 (0.8352) time: 0.1239 data: 0.0387 max mem: 9390 +Train: [23] [1800/6250] eta: 0:11:02 lr: 0.000114 grad: 0.0656 (0.0649) loss: 0.8305 (0.8351) time: 0.1295 data: 0.0476 max mem: 9390 +Train: [23] [1900/6250] eta: 0:10:49 lr: 0.000114 grad: 0.0643 (0.0649) loss: 0.8309 (0.8351) time: 0.1678 data: 0.0796 max mem: 9390 +Train: [23] [2000/6250] eta: 0:10:33 lr: 0.000114 grad: 0.0658 (0.0651) loss: 0.8353 (0.8351) time: 0.1482 data: 0.0686 max mem: 9390 +Train: [23] [2100/6250] eta: 0:10:17 lr: 0.000114 grad: 0.0654 (0.0652) loss: 0.8328 (0.8350) time: 0.1533 data: 0.0751 max mem: 9390 +Train: [23] [2200/6250] eta: 0:10:00 lr: 0.000114 grad: 0.0662 (0.0654) loss: 0.8301 (0.8350) time: 0.1415 data: 0.0621 max mem: 9390 +Train: [23] [2300/6250] eta: 0:09:43 lr: 0.000114 grad: 0.0676 (0.0655) loss: 0.8346 (0.8350) time: 0.1367 data: 0.0553 max mem: 9390 +Train: [23] [2400/6250] eta: 0:09:28 lr: 0.000114 grad: 0.0669 (0.0656) loss: 0.8371 (0.8350) time: 0.1509 data: 0.0741 max mem: 9390 +Train: [23] [2500/6250] eta: 0:09:12 lr: 0.000114 grad: 0.0664 (0.0656) loss: 0.8329 (0.8350) time: 0.1359 data: 0.0585 max mem: 9390 +Train: [23] [2600/6250] eta: 0:08:55 lr: 0.000114 grad: 0.0653 (0.0657) loss: 0.8366 (0.8350) time: 0.1454 data: 0.0698 max mem: 9390 +Train: [23] [2700/6250] eta: 0:08:39 lr: 0.000114 grad: 0.0652 (0.0658) loss: 0.8356 (0.8350) time: 0.1346 data: 0.0557 max mem: 9390 +Train: [23] [2800/6250] eta: 0:08:23 lr: 0.000114 grad: 0.0669 (0.0658) loss: 0.8350 (0.8351) time: 0.1498 data: 0.0718 max mem: 9390 +Train: [23] [2900/6250] eta: 0:08:07 lr: 0.000114 grad: 0.0703 (0.0658) loss: 0.8346 (0.8350) time: 0.1436 data: 0.0652 max mem: 9390 +Train: [23] [3000/6250] eta: 0:07:52 lr: 0.000114 grad: 0.0684 (0.0659) loss: 0.8363 (0.8351) time: 0.1492 data: 0.0685 max mem: 9390 +Train: [23] [3100/6250] eta: 0:07:37 lr: 0.000114 grad: 0.0662 (0.0660) loss: 0.8355 (0.8351) time: 0.1414 data: 0.0623 max mem: 9390 +Train: [23] [3200/6250] eta: 0:07:22 lr: 0.000114 grad: 0.0608 (0.0659) loss: 0.8369 (0.8352) time: 0.1623 data: 0.0751 max mem: 9390 +Train: [23] [3300/6250] eta: 0:07:07 lr: 0.000114 grad: 0.0651 (0.0660) loss: 0.8405 (0.8353) time: 0.1468 data: 0.0661 max mem: 9390 +Train: [23] [3400/6250] eta: 0:06:53 lr: 0.000114 grad: 0.0649 (0.0659) loss: 0.8357 (0.8354) time: 0.1763 data: 0.0974 max mem: 9390 +Train: [23] [3500/6250] eta: 0:06:39 lr: 0.000114 grad: 0.0635 (0.0660) loss: 0.8341 (0.8354) time: 0.1365 data: 0.0511 max mem: 9390 +Train: [23] [3600/6250] eta: 0:06:24 lr: 0.000114 grad: 0.0653 (0.0660) loss: 0.8367 (0.8354) time: 0.1310 data: 0.0515 max mem: 9390 +Train: [23] [3700/6250] eta: 0:06:08 lr: 0.000114 grad: 0.0644 (0.0661) loss: 0.8319 (0.8354) time: 0.1252 data: 0.0430 max mem: 9390 +Train: [23] [3800/6250] eta: 0:05:54 lr: 0.000114 grad: 0.0622 (0.0662) loss: 0.8353 (0.8354) time: 0.1332 data: 0.0491 max mem: 9390 +Train: [23] [3900/6250] eta: 0:05:38 lr: 0.000114 grad: 0.0650 (0.0662) loss: 0.8383 (0.8353) time: 0.1213 data: 0.0445 max mem: 9390 +Train: [23] [4000/6250] eta: 0:05:23 lr: 0.000113 grad: 0.0626 (0.0662) loss: 0.8365 (0.8353) time: 0.1404 data: 0.0613 max mem: 9390 +Train: [23] [4100/6250] eta: 0:05:08 lr: 0.000113 grad: 0.0647 (0.0662) loss: 0.8308 (0.8353) time: 0.1270 data: 0.0447 max mem: 9390 +Train: [23] [4200/6250] eta: 0:04:54 lr: 0.000113 grad: 0.0615 (0.0662) loss: 0.8391 (0.8353) time: 0.1549 data: 0.0682 max mem: 9390 +Train: [23] [4300/6250] eta: 0:04:39 lr: 0.000113 grad: 0.0651 (0.0662) loss: 0.8323 (0.8352) time: 0.1432 data: 0.0624 max mem: 9390 +Train: [23] [4400/6250] eta: 0:04:25 lr: 0.000113 grad: 0.0680 (0.0663) loss: 0.8303 (0.8352) time: 0.1337 data: 0.0538 max mem: 9390 +Train: [23] [4500/6250] eta: 0:04:10 lr: 0.000113 grad: 0.0635 (0.0663) loss: 0.8337 (0.8351) time: 0.1471 data: 0.0656 max mem: 9390 +Train: [23] [4600/6250] eta: 0:03:56 lr: 0.000113 grad: 0.0642 (0.0664) loss: 0.8334 (0.8351) time: 0.1629 data: 0.0867 max mem: 9390 +Train: [23] [4700/6250] eta: 0:03:41 lr: 0.000113 grad: 0.0650 (0.0664) loss: 0.8321 (0.8351) time: 0.1386 data: 0.0568 max mem: 9390 +Train: [23] [4800/6250] eta: 0:03:27 lr: 0.000113 grad: 0.0651 (0.0664) loss: 0.8379 (0.8351) time: 0.1491 data: 0.0706 max mem: 9390 +Train: [23] [4900/6250] eta: 0:03:12 lr: 0.000113 grad: 0.0669 (0.0664) loss: 0.8375 (0.8352) time: 0.1311 data: 0.0539 max mem: 9390 +Train: [23] [5000/6250] eta: 0:02:58 lr: 0.000113 grad: 0.0645 (0.0664) loss: 0.8359 (0.8352) time: 0.1381 data: 0.0556 max mem: 9390 +Train: [23] [5100/6250] eta: 0:02:43 lr: 0.000113 grad: 0.0611 (0.0664) loss: 0.8276 (0.8352) time: 0.1409 data: 0.0642 max mem: 9390 +Train: [23] [5200/6250] eta: 0:02:29 lr: 0.000113 grad: 0.0667 (0.0664) loss: 0.8363 (0.8352) time: 0.1168 data: 0.0403 max mem: 9390 +Train: [23] [5300/6250] eta: 0:02:15 lr: 0.000113 grad: 0.0684 (0.0665) loss: 0.8333 (0.8352) time: 0.1587 data: 0.0655 max mem: 9390 +Train: [23] [5400/6250] eta: 0:02:01 lr: 0.000113 grad: 0.0646 (0.0665) loss: 0.8354 (0.8352) time: 0.1341 data: 0.0503 max mem: 9390 +Train: [23] [5500/6250] eta: 0:01:46 lr: 0.000113 grad: 0.0637 (0.0665) loss: 0.8408 (0.8352) time: 0.1243 data: 0.0428 max mem: 9390 +Train: [23] [5600/6250] eta: 0:01:32 lr: 0.000113 grad: 0.0703 (0.0666) loss: 0.8351 (0.8351) time: 0.1205 data: 0.0411 max mem: 9390 +Train: [23] [5700/6250] eta: 0:01:18 lr: 0.000113 grad: 0.0667 (0.0666) loss: 0.8300 (0.8351) time: 0.1607 data: 0.0754 max mem: 9390 +Train: [23] [5800/6250] eta: 0:01:03 lr: 0.000113 grad: 0.0628 (0.0666) loss: 0.8352 (0.8351) time: 0.0989 data: 0.0153 max mem: 9390 +Train: [23] [5900/6250] eta: 0:00:49 lr: 0.000113 grad: 0.0652 (0.0666) loss: 0.8336 (0.8351) time: 0.1361 data: 0.0521 max mem: 9390 +Train: [23] [6000/6250] eta: 0:00:35 lr: 0.000113 grad: 0.0655 (0.0666) loss: 0.8316 (0.8351) time: 0.1468 data: 0.0721 max mem: 9390 +Train: [23] [6100/6250] eta: 0:00:21 lr: 0.000113 grad: 0.0633 (0.0666) loss: 0.8324 (0.8351) time: 0.1336 data: 0.0489 max mem: 9390 +Train: [23] [6200/6250] eta: 0:00:07 lr: 0.000113 grad: 0.0601 (0.0666) loss: 0.8358 (0.8351) time: 0.1398 data: 0.0580 max mem: 9390 +Train: [23] [6249/6250] eta: 0:00:00 lr: 0.000113 grad: 0.0671 (0.0666) loss: 0.8357 (0.8352) time: 0.1283 data: 0.0448 max mem: 9390 +Train: [23] Total time: 0:14:49 (0.1424 s / it) +Averaged stats: lr: 0.000113 grad: 0.0671 (0.0666) loss: 0.8357 (0.8352) +Eval (hcp-train-subset): [23] [ 0/62] eta: 0:05:45 loss: 0.8570 (0.8570) time: 5.5790 data: 5.5481 max mem: 9390 +Eval (hcp-train-subset): [23] [61/62] eta: 0:00:00 loss: 0.8433 (0.8444) time: 0.1341 data: 0.1093 max mem: 9390 +Eval (hcp-train-subset): [23] Total time: 0:00:13 (0.2128 s / it) +Averaged stats (hcp-train-subset): loss: 0.8433 (0.8444) +Eval (hcp-val): [23] [ 0/62] eta: 0:04:38 loss: 0.8364 (0.8364) time: 4.4881 data: 4.4569 max mem: 9390 +Eval (hcp-val): [23] [61/62] eta: 0:00:00 loss: 0.8406 (0.8404) time: 0.1292 data: 0.1039 max mem: 9390 +Eval (hcp-val): [23] Total time: 0:00:12 (0.2027 s / it) +Averaged stats (hcp-val): loss: 0.8406 (0.8404) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +Train: [24] [ 0/6250] eta: 16:27:59 lr: 0.000113 grad: 0.2194 (0.2194) loss: 0.8359 (0.8359) time: 9.4847 data: 9.2605 max mem: 9390 +Train: [24] [ 100/6250] eta: 0:24:11 lr: 0.000113 grad: 0.0683 (0.0742) loss: 0.8214 (0.8334) time: 0.1544 data: 0.0665 max mem: 9390 +Train: [24] [ 200/6250] eta: 0:19:40 lr: 0.000113 grad: 0.0703 (0.0729) loss: 0.8293 (0.8310) time: 0.1674 data: 0.0888 max mem: 9390 +Train: [24] [ 300/6250] eta: 0:17:53 lr: 0.000113 grad: 0.0641 (0.0705) loss: 0.8362 (0.8318) time: 0.1391 data: 0.0531 max mem: 9390 +Train: [24] [ 400/6250] eta: 0:16:48 lr: 0.000113 grad: 0.0670 (0.0695) loss: 0.8372 (0.8328) time: 0.1497 data: 0.0704 max mem: 9390 +Train: [24] [ 500/6250] eta: 0:16:04 lr: 0.000113 grad: 0.0626 (0.0689) loss: 0.8322 (0.8336) time: 0.1615 data: 0.0769 max mem: 9390 +Train: [24] [ 600/6250] eta: 0:15:18 lr: 0.000113 grad: 0.0619 (0.0686) loss: 0.8350 (0.8342) time: 0.1454 data: 0.0603 max mem: 9390 +Train: [24] [ 700/6250] eta: 0:14:42 lr: 0.000113 grad: 0.0609 (0.0685) loss: 0.8347 (0.8347) time: 0.1568 data: 0.0742 max mem: 9390 +Train: [24] [ 800/6250] eta: 0:14:07 lr: 0.000113 grad: 0.0605 (0.0689) loss: 0.8386 (0.8350) time: 0.1351 data: 0.0490 max mem: 9390 +Train: [24] [ 900/6250] eta: 0:13:46 lr: 0.000113 grad: 0.0640 (0.0685) loss: 0.8392 (0.8352) time: 0.1425 data: 0.0614 max mem: 9390 +Train: [24] [1000/6250] eta: 0:13:30 lr: 0.000113 grad: 0.0629 (0.0681) loss: 0.8335 (0.8355) time: 0.1601 data: 0.0826 max mem: 9390 +Train: [24] [1100/6250] eta: 0:13:07 lr: 0.000113 grad: 0.0657 (0.0681) loss: 0.8324 (0.8356) time: 0.1180 data: 0.0377 max mem: 9390 +Train: [24] [1200/6250] eta: 0:12:47 lr: 0.000113 grad: 0.0642 (0.0679) loss: 0.8391 (0.8355) time: 0.1204 data: 0.0398 max mem: 9390 +Train: [24] [1300/6250] eta: 0:12:30 lr: 0.000113 grad: 0.0628 (0.0678) loss: 0.8409 (0.8357) time: 0.1652 data: 0.0883 max mem: 9390 +Train: [24] [1400/6250] eta: 0:12:10 lr: 0.000113 grad: 0.0637 (0.0680) loss: 0.8387 (0.8358) time: 0.1395 data: 0.0628 max mem: 9390 +Train: [24] [1500/6250] eta: 0:11:53 lr: 0.000113 grad: 0.0600 (0.0680) loss: 0.8358 (0.8359) time: 0.1472 data: 0.0651 max mem: 9390 +Train: [24] [1600/6250] eta: 0:11:33 lr: 0.000113 grad: 0.0674 (0.0678) loss: 0.8373 (0.8359) time: 0.1478 data: 0.0701 max mem: 9390 +Train: [24] [1700/6250] eta: 0:11:15 lr: 0.000113 grad: 0.0615 (0.0678) loss: 0.8395 (0.8360) time: 0.1455 data: 0.0707 max mem: 9390 +Train: [24] [1800/6250] eta: 0:10:59 lr: 0.000113 grad: 0.0622 (0.0677) loss: 0.8372 (0.8360) time: 0.1421 data: 0.0623 max mem: 9390 +Train: [24] [1900/6250] eta: 0:10:42 lr: 0.000113 grad: 0.0597 (0.0676) loss: 0.8371 (0.8360) time: 0.1432 data: 0.0627 max mem: 9390 +Train: [24] [2000/6250] eta: 0:10:27 lr: 0.000113 grad: 0.0706 (0.0676) loss: 0.8319 (0.8360) time: 0.1455 data: 0.0642 max mem: 9390 +Train: [24] [2100/6250] eta: 0:10:11 lr: 0.000113 grad: 0.0636 (0.0675) loss: 0.8358 (0.8360) time: 0.1210 data: 0.0426 max mem: 9390 +Train: [24] [2200/6250] eta: 0:09:56 lr: 0.000113 grad: 0.0685 (0.0676) loss: 0.8383 (0.8360) time: 0.1111 data: 0.0258 max mem: 9390 +Train: [24] [2300/6250] eta: 0:09:39 lr: 0.000113 grad: 0.0670 (0.0676) loss: 0.8359 (0.8360) time: 0.1397 data: 0.0605 max mem: 9390 +Train: [24] [2400/6250] eta: 0:09:23 lr: 0.000113 grad: 0.0683 (0.0676) loss: 0.8383 (0.8360) time: 0.1551 data: 0.0811 max mem: 9390 +Train: [24] [2500/6250] eta: 0:09:07 lr: 0.000113 grad: 0.0685 (0.0677) loss: 0.8386 (0.8361) time: 0.1257 data: 0.0449 max mem: 9390 +Train: [24] [2600/6250] eta: 0:08:53 lr: 0.000113 grad: 0.0644 (0.0676) loss: 0.8379 (0.8362) time: 0.1578 data: 0.0692 max mem: 9390 +Train: [24] [2700/6250] eta: 0:08:39 lr: 0.000113 grad: 0.0670 (0.0677) loss: 0.8353 (0.8362) time: 0.1386 data: 0.0550 max mem: 9390 +Train: [24] [2800/6250] eta: 0:08:23 lr: 0.000113 grad: 0.0654 (0.0676) loss: 0.8339 (0.8361) time: 0.1481 data: 0.0719 max mem: 9390 +Train: [24] [2900/6250] eta: 0:08:07 lr: 0.000112 grad: 0.0651 (0.0676) loss: 0.8329 (0.8361) time: 0.1195 data: 0.0398 max mem: 9390 +Train: [24] [3000/6250] eta: 0:07:52 lr: 0.000112 grad: 0.0594 (0.0675) loss: 0.8341 (0.8361) time: 0.1410 data: 0.0575 max mem: 9390 +Train: [24] [3100/6250] eta: 0:07:40 lr: 0.000112 grad: 0.0705 (0.0676) loss: 0.8343 (0.8360) time: 0.1632 data: 0.0627 max mem: 9390 +Train: [24] [3200/6250] eta: 0:07:25 lr: 0.000112 grad: 0.0666 (0.0677) loss: 0.8388 (0.8360) time: 0.1533 data: 0.0754 max mem: 9390 +Train: [24] [3300/6250] eta: 0:07:10 lr: 0.000112 grad: 0.0680 (0.0677) loss: 0.8302 (0.8359) time: 0.1650 data: 0.0754 max mem: 9390 +Train: [24] [3400/6250] eta: 0:06:55 lr: 0.000112 grad: 0.0680 (0.0676) loss: 0.8314 (0.8359) time: 0.1365 data: 0.0572 max mem: 9390 +Train: [24] [3500/6250] eta: 0:06:41 lr: 0.000112 grad: 0.0712 (0.0677) loss: 0.8301 (0.8359) time: 0.1624 data: 0.0872 max mem: 9390 +Train: [24] [3600/6250] eta: 0:06:26 lr: 0.000112 grad: 0.0719 (0.0677) loss: 0.8338 (0.8358) time: 0.1394 data: 0.0575 max mem: 9390 +Train: [24] [3700/6250] eta: 0:06:11 lr: 0.000112 grad: 0.0647 (0.0677) loss: 0.8385 (0.8357) time: 0.1471 data: 0.0700 max mem: 9390 +Train: [24] [3800/6250] eta: 0:05:56 lr: 0.000112 grad: 0.0665 (0.0677) loss: 0.8357 (0.8357) time: 0.1453 data: 0.0658 max mem: 9390 +Train: [24] [3900/6250] eta: 0:05:41 lr: 0.000112 grad: 0.0709 (0.0678) loss: 0.8320 (0.8356) time: 0.1291 data: 0.0489 max mem: 9390 +Train: [24] [4000/6250] eta: 0:05:25 lr: 0.000112 grad: 0.0686 (0.0678) loss: 0.8330 (0.8356) time: 0.1325 data: 0.0546 max mem: 9390 +Train: [24] [4100/6250] eta: 0:05:10 lr: 0.000112 grad: 0.0701 (0.0679) loss: 0.8346 (0.8355) time: 0.1316 data: 0.0520 max mem: 9390 +Train: [24] [4200/6250] eta: 0:04:56 lr: 0.000112 grad: 0.0676 (0.0679) loss: 0.8331 (0.8355) time: 0.1385 data: 0.0591 max mem: 9390 +Train: [24] [4300/6250] eta: 0:04:41 lr: 0.000112 grad: 0.0619 (0.0680) loss: 0.8223 (0.8354) time: 0.1384 data: 0.0628 max mem: 9390 +Train: [24] [4400/6250] eta: 0:04:26 lr: 0.000112 grad: 0.0665 (0.0680) loss: 0.8317 (0.8354) time: 0.1355 data: 0.0564 max mem: 9390 +Train: [24] [4500/6250] eta: 0:04:12 lr: 0.000112 grad: 0.0703 (0.0681) loss: 0.8296 (0.8353) time: 0.1460 data: 0.0707 max mem: 9390 +Train: [24] [4600/6250] eta: 0:03:57 lr: 0.000112 grad: 0.0708 (0.0683) loss: 0.8326 (0.8351) time: 0.1275 data: 0.0453 max mem: 9390 +Train: [24] [4700/6250] eta: 0:03:42 lr: 0.000112 grad: 0.0679 (0.0684) loss: 0.8294 (0.8350) time: 0.1547 data: 0.0681 max mem: 9390 +Train: [24] [4800/6250] eta: 0:03:28 lr: 0.000112 grad: 0.0657 (0.0685) loss: 0.8302 (0.8349) time: 0.1112 data: 0.0281 max mem: 9390 +Train: [24] [4900/6250] eta: 0:03:13 lr: 0.000112 grad: 0.0667 (0.0685) loss: 0.8281 (0.8349) time: 0.1482 data: 0.0593 max mem: 9390 +Train: [24] [5000/6250] eta: 0:02:59 lr: 0.000112 grad: 0.0712 (0.0685) loss: 0.8349 (0.8348) time: 0.1297 data: 0.0417 max mem: 9390 +Train: [24] [5100/6250] eta: 0:02:44 lr: 0.000112 grad: 0.0659 (0.0685) loss: 0.8272 (0.8348) time: 0.1288 data: 0.0482 max mem: 9390 +Train: [24] [5200/6250] eta: 0:02:30 lr: 0.000112 grad: 0.0650 (0.0685) loss: 0.8332 (0.8347) time: 0.1318 data: 0.0552 max mem: 9390 +Train: [24] [5300/6250] eta: 0:02:16 lr: 0.000112 grad: 0.0702 (0.0685) loss: 0.8317 (0.8347) time: 0.1334 data: 0.0537 max mem: 9390 +Train: [24] [5400/6250] eta: 0:02:01 lr: 0.000112 grad: 0.0652 (0.0685) loss: 0.8343 (0.8347) time: 0.1449 data: 0.0618 max mem: 9390 +Train: [24] [5500/6250] eta: 0:01:47 lr: 0.000112 grad: 0.0668 (0.0685) loss: 0.8308 (0.8346) time: 0.1365 data: 0.0557 max mem: 9390 +Train: [24] [5600/6250] eta: 0:01:33 lr: 0.000112 grad: 0.0669 (0.0684) loss: 0.8314 (0.8346) time: 0.1421 data: 0.0628 max mem: 9390 +Train: [24] [5700/6250] eta: 0:01:18 lr: 0.000112 grad: 0.0655 (0.0684) loss: 0.8370 (0.8346) time: 0.1318 data: 0.0506 max mem: 9390 +Train: [24] [5800/6250] eta: 0:01:04 lr: 0.000112 grad: 0.0685 (0.0684) loss: 0.8353 (0.8345) time: 0.1381 data: 0.0532 max mem: 9390 +Train: [24] [5900/6250] eta: 0:00:50 lr: 0.000112 grad: 0.0635 (0.0683) loss: 0.8343 (0.8345) time: 0.1310 data: 0.0443 max mem: 9390 +Train: [24] [6000/6250] eta: 0:00:35 lr: 0.000112 grad: 0.0707 (0.0683) loss: 0.8272 (0.8344) time: 0.1365 data: 0.0583 max mem: 9390 +Train: [24] [6100/6250] eta: 0:00:21 lr: 0.000112 grad: 0.0636 (0.0683) loss: 0.8339 (0.8344) time: 0.1316 data: 0.0497 max mem: 9390 +Train: [24] [6200/6250] eta: 0:00:07 lr: 0.000112 grad: 0.0645 (0.0683) loss: 0.8299 (0.8343) time: 0.1411 data: 0.0650 max mem: 9390 +Train: [24] [6249/6250] eta: 0:00:00 lr: 0.000112 grad: 0.0641 (0.0683) loss: 0.8306 (0.8343) time: 0.1249 data: 0.0455 max mem: 9390 +Train: [24] Total time: 0:14:56 (0.1434 s / it) +Averaged stats: lr: 0.000112 grad: 0.0641 (0.0683) loss: 0.8306 (0.8343) +Eval (hcp-train-subset): [24] [ 0/62] eta: 0:05:26 loss: 0.8558 (0.8558) time: 5.2668 data: 5.2280 max mem: 9390 +Eval (hcp-train-subset): [24] [61/62] eta: 0:00:00 loss: 0.8437 (0.8441) time: 0.1312 data: 0.1061 max mem: 9390 +Eval (hcp-train-subset): [24] Total time: 0:00:14 (0.2288 s / it) +Averaged stats (hcp-train-subset): loss: 0.8437 (0.8441) +Making plots (hcp-train-subset): example=35 +Eval (hcp-val): [24] [ 0/62] eta: 0:04:53 loss: 0.8365 (0.8365) time: 4.7343 data: 4.7030 max mem: 9390 +Eval (hcp-val): [24] [61/62] eta: 0:00:00 loss: 0.8381 (0.8396) time: 0.1288 data: 0.1040 max mem: 9390 +Eval (hcp-val): [24] Total time: 0:00:13 (0.2151 s / it) +Averaged stats (hcp-val): loss: 0.8381 (0.8396) +Making plots (hcp-val): example=21 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +Train: [25] [ 0/6250] eta: 10:03:16 lr: 0.000112 grad: 0.0527 (0.0527) loss: 0.8525 (0.8525) time: 5.7915 data: 5.6703 max mem: 9390 +Train: [25] [ 100/6250] eta: 0:21:02 lr: 0.000112 grad: 0.0696 (0.0806) loss: 0.8335 (0.8331) time: 0.1722 data: 0.0932 max mem: 9390 +Train: [25] [ 200/6250] eta: 0:17:29 lr: 0.000112 grad: 0.0665 (0.0741) loss: 0.8359 (0.8335) time: 0.1436 data: 0.0586 max mem: 9390 +Train: [25] [ 300/6250] eta: 0:16:27 lr: 0.000112 grad: 0.0675 (0.0724) loss: 0.8358 (0.8339) time: 0.1468 data: 0.0680 max mem: 9390 +Train: [25] [ 400/6250] eta: 0:15:48 lr: 0.000112 grad: 0.0645 (0.0715) loss: 0.8340 (0.8335) time: 0.1516 data: 0.0669 max mem: 9390 +Train: [25] [ 500/6250] eta: 0:15:08 lr: 0.000112 grad: 0.0642 (0.0708) loss: 0.8348 (0.8333) time: 0.1463 data: 0.0604 max mem: 9390 +Train: [25] [ 600/6250] eta: 0:14:36 lr: 0.000112 grad: 0.0631 (0.0702) loss: 0.8310 (0.8334) time: 0.1458 data: 0.0563 max mem: 9390 +Train: [25] [ 700/6250] eta: 0:14:07 lr: 0.000112 grad: 0.0675 (0.0697) loss: 0.8355 (0.8333) time: 0.1148 data: 0.0308 max mem: 9390 +Train: [25] [ 800/6250] eta: 0:13:39 lr: 0.000112 grad: 0.0711 (0.0694) loss: 0.8321 (0.8333) time: 0.1353 data: 0.0500 max mem: 9390 +Train: [25] [ 900/6250] eta: 0:13:19 lr: 0.000112 grad: 0.0621 (0.0692) loss: 0.8336 (0.8334) time: 0.1580 data: 0.0783 max mem: 9390 +Train: [25] [1000/6250] eta: 0:12:56 lr: 0.000112 grad: 0.0649 (0.0688) loss: 0.8371 (0.8338) time: 0.1348 data: 0.0493 max mem: 9390 +Train: [25] [1100/6250] eta: 0:12:39 lr: 0.000112 grad: 0.0629 (0.0685) loss: 0.8336 (0.8339) time: 0.1343 data: 0.0556 max mem: 9390 +Train: [25] [1200/6250] eta: 0:12:27 lr: 0.000112 grad: 0.0639 (0.0683) loss: 0.8385 (0.8341) time: 0.1612 data: 0.0845 max mem: 9390 +Train: [25] [1300/6250] eta: 0:12:10 lr: 0.000112 grad: 0.0616 (0.0680) loss: 0.8374 (0.8343) time: 0.1461 data: 0.0686 max mem: 9390 +Train: [25] [1400/6250] eta: 0:11:51 lr: 0.000112 grad: 0.0686 (0.0680) loss: 0.8311 (0.8343) time: 0.1333 data: 0.0549 max mem: 9390 +Train: [25] [1500/6250] eta: 0:11:35 lr: 0.000112 grad: 0.0657 (0.0680) loss: 0.8345 (0.8343) time: 0.1347 data: 0.0535 max mem: 9390 +Train: [25] [1600/6250] eta: 0:11:18 lr: 0.000111 grad: 0.0671 (0.0680) loss: 0.8296 (0.8342) time: 0.1373 data: 0.0567 max mem: 9390 +Train: [25] [1700/6250] eta: 0:11:01 lr: 0.000111 grad: 0.0674 (0.0679) loss: 0.8300 (0.8341) time: 0.1392 data: 0.0556 max mem: 9390 +Train: [25] [1800/6250] eta: 0:10:48 lr: 0.000111 grad: 0.0653 (0.0679) loss: 0.8287 (0.8339) time: 0.1970 data: 0.1101 max mem: 9390 +Train: [25] [1900/6250] eta: 0:10:30 lr: 0.000111 grad: 0.0645 (0.0678) loss: 0.8361 (0.8339) time: 0.1117 data: 0.0277 max mem: 9390 +Train: [25] [2000/6250] eta: 0:10:16 lr: 0.000111 grad: 0.0662 (0.0678) loss: 0.8339 (0.8338) time: 0.1473 data: 0.0564 max mem: 9390 +Train: [25] [2100/6250] eta: 0:10:04 lr: 0.000111 grad: 0.0662 (0.0679) loss: 0.8320 (0.8337) time: 0.1548 data: 0.0808 max mem: 9390 +Train: [25] [2200/6250] eta: 0:09:48 lr: 0.000111 grad: 0.0667 (0.0679) loss: 0.8310 (0.8337) time: 0.1253 data: 0.0447 max mem: 9390 +Train: [25] [2300/6250] eta: 0:09:32 lr: 0.000111 grad: 0.0682 (0.0679) loss: 0.8346 (0.8337) time: 0.1353 data: 0.0570 max mem: 9390 +Train: [25] [2400/6250] eta: 0:09:17 lr: 0.000111 grad: 0.0669 (0.0679) loss: 0.8341 (0.8337) time: 0.1374 data: 0.0585 max mem: 9390 +Train: [25] [2500/6250] eta: 0:09:02 lr: 0.000111 grad: 0.0651 (0.0680) loss: 0.8326 (0.8338) time: 0.1362 data: 0.0564 max mem: 9390 +Train: [25] [2600/6250] eta: 0:08:47 lr: 0.000111 grad: 0.0635 (0.0680) loss: 0.8355 (0.8338) time: 0.1566 data: 0.0778 max mem: 9390 +Train: [25] [2700/6250] eta: 0:08:33 lr: 0.000111 grad: 0.0671 (0.0681) loss: 0.8335 (0.8337) time: 0.1438 data: 0.0668 max mem: 9390 +Train: [25] [2800/6250] eta: 0:08:16 lr: 0.000111 grad: 0.0635 (0.0681) loss: 0.8348 (0.8337) time: 0.1370 data: 0.0645 max mem: 9390 +Train: [25] [2900/6250] eta: 0:08:02 lr: 0.000111 grad: 0.0729 (0.0682) loss: 0.8338 (0.8336) time: 0.1420 data: 0.0606 max mem: 9390 +Train: [25] [3000/6250] eta: 0:07:47 lr: 0.000111 grad: 0.0673 (0.0682) loss: 0.8305 (0.8336) time: 0.1485 data: 0.0685 max mem: 9390 +Train: [25] [3100/6250] eta: 0:07:32 lr: 0.000111 grad: 0.0660 (0.0682) loss: 0.8361 (0.8336) time: 0.1230 data: 0.0424 max mem: 9390 +Train: [25] [3200/6250] eta: 0:07:17 lr: 0.000111 grad: 0.0651 (0.0681) loss: 0.8306 (0.8336) time: 0.1306 data: 0.0537 max mem: 9390 +Train: [25] [3300/6250] eta: 0:07:01 lr: 0.000111 grad: 0.0658 (0.0681) loss: 0.8364 (0.8335) time: 0.1169 data: 0.0385 max mem: 9390 +Train: [25] [3400/6250] eta: 0:06:47 lr: 0.000111 grad: 0.0671 (0.0681) loss: 0.8291 (0.8335) time: 0.1267 data: 0.0247 max mem: 9390 +Train: [25] [3500/6250] eta: 0:06:32 lr: 0.000111 grad: 0.0644 (0.0681) loss: 0.8315 (0.8335) time: 0.1298 data: 0.0388 max mem: 9390 +Train: [25] [3600/6250] eta: 0:06:18 lr: 0.000111 grad: 0.0674 (0.0681) loss: 0.8325 (0.8334) time: 0.1512 data: 0.0611 max mem: 9390 +Train: [25] [3700/6250] eta: 0:06:05 lr: 0.000111 grad: 0.0635 (0.0681) loss: 0.8344 (0.8334) time: 0.1217 data: 0.0461 max mem: 9390 +Train: [25] [3800/6250] eta: 0:05:50 lr: 0.000111 grad: 0.0644 (0.0682) loss: 0.8353 (0.8334) time: 0.1437 data: 0.0683 max mem: 9390 +Train: [25] [3900/6250] eta: 0:05:36 lr: 0.000111 grad: 0.0615 (0.0682) loss: 0.8366 (0.8334) time: 0.1555 data: 0.0787 max mem: 9390 +Train: [25] [4000/6250] eta: 0:05:21 lr: 0.000111 grad: 0.0653 (0.0682) loss: 0.8357 (0.8335) time: 0.1412 data: 0.0646 max mem: 9390 +Train: [25] [4100/6250] eta: 0:05:07 lr: 0.000111 grad: 0.0650 (0.0682) loss: 0.8363 (0.8335) time: 0.1171 data: 0.0360 max mem: 9390 +Train: [25] [4200/6250] eta: 0:04:52 lr: 0.000111 grad: 0.0625 (0.0681) loss: 0.8283 (0.8335) time: 0.1274 data: 0.0472 max mem: 9390 +Train: [25] [4300/6250] eta: 0:04:38 lr: 0.000111 grad: 0.0652 (0.0681) loss: 0.8360 (0.8335) time: 0.1323 data: 0.0541 max mem: 9390 +Train: [25] [4400/6250] eta: 0:04:23 lr: 0.000111 grad: 0.0685 (0.0680) loss: 0.8323 (0.8335) time: 0.1166 data: 0.0356 max mem: 9390 +Train: [25] [4500/6250] eta: 0:04:08 lr: 0.000111 grad: 0.0606 (0.0680) loss: 0.8380 (0.8334) time: 0.1103 data: 0.0278 max mem: 9390 +Train: [25] [4600/6250] eta: 0:03:54 lr: 0.000111 grad: 0.0672 (0.0680) loss: 0.8400 (0.8334) time: 0.1410 data: 0.0625 max mem: 9390 +Train: [25] [4700/6250] eta: 0:03:39 lr: 0.000111 grad: 0.0617 (0.0679) loss: 0.8401 (0.8334) time: 0.1423 data: 0.0621 max mem: 9390 +Train: [25] [4800/6250] eta: 0:03:25 lr: 0.000111 grad: 0.0660 (0.0680) loss: 0.8356 (0.8334) time: 0.1240 data: 0.0426 max mem: 9390 +Train: [25] [4900/6250] eta: 0:03:11 lr: 0.000111 grad: 0.0637 (0.0680) loss: 0.8344 (0.8334) time: 0.1662 data: 0.0920 max mem: 9390 +Train: [25] [5000/6250] eta: 0:02:56 lr: 0.000111 grad: 0.0664 (0.0680) loss: 0.8331 (0.8333) time: 0.1223 data: 0.0401 max mem: 9390 +Train: [25] [5100/6250] eta: 0:02:42 lr: 0.000111 grad: 0.0652 (0.0680) loss: 0.8341 (0.8333) time: 0.1202 data: 0.0406 max mem: 9390 +Train: [25] [5200/6250] eta: 0:02:28 lr: 0.000111 grad: 0.0666 (0.0680) loss: 0.8387 (0.8333) time: 0.1393 data: 0.0584 max mem: 9390 +Train: [25] [5300/6250] eta: 0:02:14 lr: 0.000111 grad: 0.0649 (0.0680) loss: 0.8327 (0.8333) time: 0.1288 data: 0.0494 max mem: 9390 +Train: [25] [5400/6250] eta: 0:02:00 lr: 0.000111 grad: 0.0642 (0.0680) loss: 0.8394 (0.8333) time: 0.1877 data: 0.1126 max mem: 9390 +Train: [25] [5500/6250] eta: 0:01:46 lr: 0.000111 grad: 0.0653 (0.0680) loss: 0.8362 (0.8333) time: 0.1396 data: 0.0643 max mem: 9390 +Train: [25] [5600/6250] eta: 0:01:32 lr: 0.000111 grad: 0.0668 (0.0680) loss: 0.8349 (0.8333) time: 0.1708 data: 0.0876 max mem: 9390 +Train: [25] [5700/6250] eta: 0:01:17 lr: 0.000111 grad: 0.0688 (0.0680) loss: 0.8327 (0.8333) time: 0.1311 data: 0.0533 max mem: 9390 +Train: [25] [5800/6250] eta: 0:01:03 lr: 0.000111 grad: 0.0691 (0.0681) loss: 0.8288 (0.8333) time: 0.1588 data: 0.0776 max mem: 9390 +Train: [25] [5900/6250] eta: 0:00:49 lr: 0.000111 grad: 0.0642 (0.0681) loss: 0.8376 (0.8333) time: 0.1567 data: 0.0675 max mem: 9390 +Train: [25] [6000/6250] eta: 0:00:35 lr: 0.000111 grad: 0.0639 (0.0681) loss: 0.8305 (0.8333) time: 0.1416 data: 0.0662 max mem: 9390 +Train: [25] [6100/6250] eta: 0:00:21 lr: 0.000111 grad: 0.0658 (0.0681) loss: 0.8327 (0.8333) time: 0.1394 data: 0.0553 max mem: 9390 +Train: [25] [6200/6250] eta: 0:00:07 lr: 0.000111 grad: 0.0677 (0.0681) loss: 0.8319 (0.8333) time: 0.1455 data: 0.0593 max mem: 9390 +Train: [25] [6249/6250] eta: 0:00:00 lr: 0.000111 grad: 0.0681 (0.0682) loss: 0.8341 (0.8333) time: 0.1426 data: 0.0713 max mem: 9390 +Train: [25] Total time: 0:14:51 (0.1426 s / it) +Averaged stats: lr: 0.000111 grad: 0.0681 (0.0682) loss: 0.8341 (0.8333) +Eval (hcp-train-subset): [25] [ 0/62] eta: 0:04:55 loss: 0.8579 (0.8579) time: 4.7658 data: 4.7356 max mem: 9390 +Eval (hcp-train-subset): [25] [61/62] eta: 0:00:00 loss: 0.8452 (0.8447) time: 0.1320 data: 0.1072 max mem: 9390 +Eval (hcp-train-subset): [25] Total time: 0:00:12 (0.2049 s / it) +Averaged stats (hcp-train-subset): loss: 0.8452 (0.8447) +Eval (hcp-val): [25] [ 0/62] eta: 0:05:41 loss: 0.8359 (0.8359) time: 5.5157 data: 5.4863 max mem: 9390 +Eval (hcp-val): [25] [61/62] eta: 0:00:00 loss: 0.8401 (0.8403) time: 0.1597 data: 0.1336 max mem: 9390 +Eval (hcp-val): [25] Total time: 0:00:14 (0.2377 s / it) +Averaged stats (hcp-val): loss: 0.8401 (0.8403) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +Train: [26] [ 0/6250] eta: 8:19:49 lr: 0.000111 grad: 0.0563 (0.0563) loss: 0.8587 (0.8587) time: 4.7983 data: 4.5320 max mem: 9390 +Train: [26] [ 100/6250] eta: 0:20:53 lr: 0.000111 grad: 0.0595 (0.0695) loss: 0.8471 (0.8426) time: 0.1430 data: 0.0568 max mem: 9390 +Train: [26] [ 200/6250] eta: 0:18:12 lr: 0.000110 grad: 0.0699 (0.0684) loss: 0.8261 (0.8400) time: 0.1698 data: 0.0825 max mem: 9390 +Train: [26] [ 300/6250] eta: 0:16:44 lr: 0.000110 grad: 0.0664 (0.0684) loss: 0.8404 (0.8379) time: 0.1451 data: 0.0650 max mem: 9390 +Train: [26] [ 400/6250] eta: 0:15:48 lr: 0.000110 grad: 0.0654 (0.0678) loss: 0.8349 (0.8371) time: 0.1353 data: 0.0510 max mem: 9390 +Train: [26] [ 500/6250] eta: 0:15:10 lr: 0.000110 grad: 0.0596 (0.0671) loss: 0.8444 (0.8378) time: 0.1368 data: 0.0555 max mem: 9390 +Train: [26] [ 600/6250] eta: 0:14:33 lr: 0.000110 grad: 0.0663 (0.0673) loss: 0.8405 (0.8380) time: 0.1332 data: 0.0448 max mem: 9390 +Train: [26] [ 700/6250] eta: 0:14:05 lr: 0.000110 grad: 0.0678 (0.0676) loss: 0.8363 (0.8379) time: 0.1586 data: 0.0706 max mem: 9390 +Train: [26] [ 800/6250] eta: 0:13:41 lr: 0.000110 grad: 0.0694 (0.0678) loss: 0.8347 (0.8377) time: 0.1383 data: 0.0613 max mem: 9390 +Train: [26] [ 900/6250] eta: 0:13:19 lr: 0.000110 grad: 0.0648 (0.0678) loss: 0.8382 (0.8376) time: 0.1546 data: 0.0731 max mem: 9390 +Train: [26] [1000/6250] eta: 0:13:03 lr: 0.000110 grad: 0.0637 (0.0674) loss: 0.8377 (0.8374) time: 0.1164 data: 0.0301 max mem: 9390 +Train: [26] [1100/6250] eta: 0:12:43 lr: 0.000110 grad: 0.0656 (0.0673) loss: 0.8299 (0.8371) time: 0.1372 data: 0.0591 max mem: 9390 +Train: [26] [1200/6250] eta: 0:12:26 lr: 0.000110 grad: 0.0657 (0.0672) loss: 0.8308 (0.8369) time: 0.1120 data: 0.0294 max mem: 9390 +Train: [26] [1300/6250] eta: 0:12:10 lr: 0.000110 grad: 0.0664 (0.0670) loss: 0.8363 (0.8367) time: 0.1325 data: 0.0535 max mem: 9390 +Train: [26] [1400/6250] eta: 0:11:52 lr: 0.000110 grad: 0.0645 (0.0671) loss: 0.8357 (0.8363) time: 0.1359 data: 0.0576 max mem: 9390 +Train: [26] [1500/6250] eta: 0:11:37 lr: 0.000110 grad: 0.0632 (0.0671) loss: 0.8345 (0.8361) time: 0.1513 data: 0.0574 max mem: 9390 +Train: [26] [1600/6250] eta: 0:11:18 lr: 0.000110 grad: 0.0616 (0.0671) loss: 0.8332 (0.8359) time: 0.1242 data: 0.0471 max mem: 9390 +Train: [26] [1700/6250] eta: 0:11:01 lr: 0.000110 grad: 0.0604 (0.0672) loss: 0.8335 (0.8358) time: 0.1239 data: 0.0430 max mem: 9390 +Train: [26] [1800/6250] eta: 0:10:45 lr: 0.000110 grad: 0.0655 (0.0673) loss: 0.8305 (0.8356) time: 0.1316 data: 0.0572 max mem: 9390 +Train: [26] [1900/6250] eta: 0:10:32 lr: 0.000110 grad: 0.0651 (0.0675) loss: 0.8313 (0.8353) time: 0.1188 data: 0.0379 max mem: 9390 +Train: [26] [2000/6250] eta: 0:10:16 lr: 0.000110 grad: 0.0666 (0.0674) loss: 0.8344 (0.8354) time: 0.1421 data: 0.0665 max mem: 9390 +Train: [26] [2100/6250] eta: 0:10:01 lr: 0.000110 grad: 0.0653 (0.0675) loss: 0.8314 (0.8352) time: 0.1540 data: 0.0690 max mem: 9390 +Train: [26] [2200/6250] eta: 0:09:46 lr: 0.000110 grad: 0.0653 (0.0675) loss: 0.8302 (0.8350) time: 0.1396 data: 0.0605 max mem: 9390 +Train: [26] [2300/6250] eta: 0:09:31 lr: 0.000110 grad: 0.0648 (0.0676) loss: 0.8294 (0.8347) time: 0.1356 data: 0.0457 max mem: 9390 +Train: [26] [2400/6250] eta: 0:09:16 lr: 0.000110 grad: 0.0668 (0.0677) loss: 0.8283 (0.8344) time: 0.1530 data: 0.0742 max mem: 9390 +Train: [26] [2500/6250] eta: 0:09:01 lr: 0.000110 grad: 0.0679 (0.0678) loss: 0.8249 (0.8342) time: 0.1313 data: 0.0525 max mem: 9390 +Train: [26] [2600/6250] eta: 0:08:47 lr: 0.000110 grad: 0.0668 (0.0679) loss: 0.8327 (0.8339) time: 0.1554 data: 0.0683 max mem: 9390 +Train: [26] [2700/6250] eta: 0:08:31 lr: 0.000110 grad: 0.0684 (0.0679) loss: 0.8314 (0.8338) time: 0.1510 data: 0.0720 max mem: 9390 +Train: [26] [2800/6250] eta: 0:08:16 lr: 0.000110 grad: 0.0661 (0.0681) loss: 0.8321 (0.8338) time: 0.1231 data: 0.0380 max mem: 9390 +Train: [26] [2900/6250] eta: 0:08:01 lr: 0.000110 grad: 0.0680 (0.0681) loss: 0.8297 (0.8336) time: 0.1319 data: 0.0523 max mem: 9390 +Train: [26] [3000/6250] eta: 0:07:47 lr: 0.000110 grad: 0.0638 (0.0682) loss: 0.8350 (0.8336) time: 0.1463 data: 0.0553 max mem: 9390 +Train: [26] [3100/6250] eta: 0:07:31 lr: 0.000110 grad: 0.0636 (0.0681) loss: 0.8333 (0.8335) time: 0.1440 data: 0.0614 max mem: 9390 +Train: [26] [3200/6250] eta: 0:07:17 lr: 0.000110 grad: 0.0674 (0.0681) loss: 0.8327 (0.8334) time: 0.1390 data: 0.0505 max mem: 9390 +Train: [26] [3300/6250] eta: 0:07:02 lr: 0.000110 grad: 0.0637 (0.0681) loss: 0.8403 (0.8335) time: 0.1342 data: 0.0557 max mem: 9390 +Train: [26] [3400/6250] eta: 0:06:46 lr: 0.000110 grad: 0.0685 (0.0680) loss: 0.8273 (0.8335) time: 0.1163 data: 0.0397 max mem: 9390 +Train: [26] [3500/6250] eta: 0:06:32 lr: 0.000110 grad: 0.0626 (0.0681) loss: 0.8358 (0.8335) time: 0.1249 data: 0.0430 max mem: 9390 +Train: [26] [3600/6250] eta: 0:06:17 lr: 0.000110 grad: 0.0676 (0.0680) loss: 0.8326 (0.8335) time: 0.1546 data: 0.0789 max mem: 9390 +Train: [26] [3700/6250] eta: 0:06:02 lr: 0.000110 grad: 0.0684 (0.0681) loss: 0.8363 (0.8335) time: 0.1503 data: 0.0738 max mem: 9390 +Train: [26] [3800/6250] eta: 0:05:48 lr: 0.000110 grad: 0.0684 (0.0681) loss: 0.8282 (0.8335) time: 0.1427 data: 0.0640 max mem: 9390 +Train: [26] [3900/6250] eta: 0:05:34 lr: 0.000110 grad: 0.0656 (0.0681) loss: 0.8338 (0.8334) time: 0.1371 data: 0.0624 max mem: 9390 +Train: [26] [4000/6250] eta: 0:05:19 lr: 0.000110 grad: 0.0682 (0.0682) loss: 0.8338 (0.8334) time: 0.1352 data: 0.0610 max mem: 9390 +Train: [26] [4100/6250] eta: 0:05:05 lr: 0.000110 grad: 0.0669 (0.0681) loss: 0.8411 (0.8335) time: 0.1257 data: 0.0480 max mem: 9390 +Train: [26] [4200/6250] eta: 0:04:50 lr: 0.000110 grad: 0.0619 (0.0682) loss: 0.8380 (0.8335) time: 0.1592 data: 0.0882 max mem: 9390 +Train: [26] [4300/6250] eta: 0:04:36 lr: 0.000110 grad: 0.0645 (0.0682) loss: 0.8371 (0.8336) time: 0.1612 data: 0.0761 max mem: 9390 +Train: [26] [4400/6250] eta: 0:04:21 lr: 0.000110 grad: 0.0643 (0.0682) loss: 0.8334 (0.8336) time: 0.1443 data: 0.0618 max mem: 9390 +Train: [26] [4500/6250] eta: 0:04:07 lr: 0.000110 grad: 0.0669 (0.0682) loss: 0.8335 (0.8336) time: 0.1047 data: 0.0204 max mem: 9390 +Train: [26] [4600/6250] eta: 0:03:53 lr: 0.000110 grad: 0.0692 (0.0682) loss: 0.8311 (0.8336) time: 0.1346 data: 0.0582 max mem: 9390 +Train: [26] [4700/6250] eta: 0:03:39 lr: 0.000110 grad: 0.0624 (0.0682) loss: 0.8356 (0.8336) time: 0.1398 data: 0.0609 max mem: 9390 +Train: [26] [4800/6250] eta: 0:03:24 lr: 0.000109 grad: 0.0685 (0.0682) loss: 0.8305 (0.8336) time: 0.1474 data: 0.0686 max mem: 9390 +Train: [26] [4900/6250] eta: 0:03:10 lr: 0.000109 grad: 0.0682 (0.0683) loss: 0.8286 (0.8336) time: 0.1702 data: 0.0988 max mem: 9390 +Train: [26] [5000/6250] eta: 0:02:56 lr: 0.000109 grad: 0.0660 (0.0683) loss: 0.8371 (0.8336) time: 0.1467 data: 0.0572 max mem: 9390 +Train: [26] [5100/6250] eta: 0:02:42 lr: 0.000109 grad: 0.0707 (0.0683) loss: 0.8333 (0.8336) time: 0.1656 data: 0.0357 max mem: 9390 +Train: [26] [5200/6250] eta: 0:02:28 lr: 0.000109 grad: 0.0654 (0.0684) loss: 0.8302 (0.8336) time: 0.1288 data: 0.0497 max mem: 9390 +Train: [26] [5300/6250] eta: 0:02:14 lr: 0.000109 grad: 0.0645 (0.0684) loss: 0.8303 (0.8335) time: 0.1419 data: 0.0638 max mem: 9390 +Train: [26] [5400/6250] eta: 0:02:00 lr: 0.000109 grad: 0.0665 (0.0684) loss: 0.8333 (0.8335) time: 0.1570 data: 0.0813 max mem: 9390 +Train: [26] [5500/6250] eta: 0:01:46 lr: 0.000109 grad: 0.0682 (0.0685) loss: 0.8331 (0.8335) time: 0.1410 data: 0.0585 max mem: 9390 +Train: [26] [5600/6250] eta: 0:01:31 lr: 0.000109 grad: 0.0740 (0.0686) loss: 0.8272 (0.8334) time: 0.1444 data: 0.0703 max mem: 9390 +Train: [26] [5700/6250] eta: 0:01:17 lr: 0.000109 grad: 0.0697 (0.0686) loss: 0.8211 (0.8334) time: 0.1176 data: 0.0339 max mem: 9390 +Train: [26] [5800/6250] eta: 0:01:03 lr: 0.000109 grad: 0.0699 (0.0686) loss: 0.8315 (0.8333) time: 0.1040 data: 0.0297 max mem: 9390 +Train: [26] [5900/6250] eta: 0:00:49 lr: 0.000109 grad: 0.0669 (0.0686) loss: 0.8247 (0.8333) time: 0.1472 data: 0.0604 max mem: 9390 +Train: [26] [6000/6250] eta: 0:00:35 lr: 0.000109 grad: 0.0658 (0.0687) loss: 0.8288 (0.8333) time: 0.1524 data: 0.0701 max mem: 9390 +Train: [26] [6100/6250] eta: 0:00:21 lr: 0.000109 grad: 0.0705 (0.0687) loss: 0.8275 (0.8332) time: 0.1358 data: 0.0566 max mem: 9390 +Train: [26] [6200/6250] eta: 0:00:07 lr: 0.000109 grad: 0.0670 (0.0687) loss: 0.8351 (0.8332) time: 0.1558 data: 0.0785 max mem: 9390 +Train: [26] [6249/6250] eta: 0:00:00 lr: 0.000109 grad: 0.0651 (0.0687) loss: 0.8333 (0.8332) time: 0.1325 data: 0.0464 max mem: 9390 +Train: [26] Total time: 0:14:47 (0.1419 s / it) +Averaged stats: lr: 0.000109 grad: 0.0651 (0.0687) loss: 0.8333 (0.8332) +Eval (hcp-train-subset): [26] [ 0/62] eta: 0:05:59 loss: 0.8518 (0.8518) time: 5.8040 data: 5.7719 max mem: 9390 +Eval (hcp-train-subset): [26] [61/62] eta: 0:00:00 loss: 0.8420 (0.8428) time: 0.1304 data: 0.1036 max mem: 9390 +Eval (hcp-train-subset): [26] Total time: 0:00:14 (0.2353 s / it) +Averaged stats (hcp-train-subset): loss: 0.8420 (0.8428) +Eval (hcp-val): [26] [ 0/62] eta: 0:06:13 loss: 0.8380 (0.8380) time: 6.0196 data: 5.9889 max mem: 9390 +Eval (hcp-val): [26] [61/62] eta: 0:00:00 loss: 0.8390 (0.8396) time: 0.1220 data: 0.0973 max mem: 9390 +Eval (hcp-val): [26] Total time: 0:00:14 (0.2343 s / it) +Averaged stats (hcp-val): loss: 0.8390 (0.8396) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +Train: [27] [ 0/6250] eta: 10:25:27 lr: 0.000109 grad: 0.1015 (0.1015) loss: 0.8405 (0.8405) time: 6.0044 data: 5.8993 max mem: 9390 +Train: [27] [ 100/6250] eta: 0:20:21 lr: 0.000109 grad: 0.0675 (0.0752) loss: 0.8378 (0.8389) time: 0.1300 data: 0.0480 max mem: 9390 +Train: [27] [ 200/6250] eta: 0:17:40 lr: 0.000109 grad: 0.0765 (0.0751) loss: 0.8311 (0.8346) time: 0.1621 data: 0.0823 max mem: 9390 +Train: [27] [ 300/6250] eta: 0:16:27 lr: 0.000109 grad: 0.0660 (0.0741) loss: 0.8329 (0.8338) time: 0.1368 data: 0.0502 max mem: 9390 +Train: [27] [ 400/6250] eta: 0:15:46 lr: 0.000109 grad: 0.0710 (0.0729) loss: 0.8249 (0.8322) time: 0.1415 data: 0.0526 max mem: 9390 +Train: [27] [ 500/6250] eta: 0:15:07 lr: 0.000109 grad: 0.0620 (0.0719) loss: 0.8388 (0.8321) time: 0.1443 data: 0.0689 max mem: 9390 +Train: [27] [ 600/6250] eta: 0:14:34 lr: 0.000109 grad: 0.0625 (0.0714) loss: 0.8373 (0.8318) time: 0.1443 data: 0.0594 max mem: 9390 +Train: [27] [ 700/6250] eta: 0:14:08 lr: 0.000109 grad: 0.0680 (0.0708) loss: 0.8300 (0.8316) time: 0.1682 data: 0.0838 max mem: 9390 +Train: [27] [ 800/6250] eta: 0:13:45 lr: 0.000109 grad: 0.0647 (0.0704) loss: 0.8315 (0.8316) time: 0.1709 data: 0.0927 max mem: 9390 +Train: [27] [ 900/6250] eta: 0:13:27 lr: 0.000109 grad: 0.0683 (0.0700) loss: 0.8321 (0.8314) time: 0.1482 data: 0.0653 max mem: 9390 +Train: [27] [1000/6250] eta: 0:13:07 lr: 0.000109 grad: 0.0634 (0.0695) loss: 0.8292 (0.8315) time: 0.1427 data: 0.0624 max mem: 9390 +Train: [27] [1100/6250] eta: 0:12:55 lr: 0.000109 grad: 0.0648 (0.0695) loss: 0.8353 (0.8314) time: 0.1477 data: 0.0697 max mem: 9390 +Train: [27] [1200/6250] eta: 0:12:37 lr: 0.000109 grad: 0.0686 (0.0692) loss: 0.8248 (0.8315) time: 0.1578 data: 0.0758 max mem: 9390 +Train: [27] [1300/6250] eta: 0:12:18 lr: 0.000109 grad: 0.0648 (0.0692) loss: 0.8318 (0.8314) time: 0.1408 data: 0.0641 max mem: 9390 +Train: [27] [1400/6250] eta: 0:11:58 lr: 0.000109 grad: 0.0661 (0.0692) loss: 0.8276 (0.8313) time: 0.1366 data: 0.0577 max mem: 9390 +Train: [27] [1500/6250] eta: 0:11:40 lr: 0.000109 grad: 0.0709 (0.0695) loss: 0.8330 (0.8311) time: 0.1285 data: 0.0534 max mem: 9390 +Train: [27] [1600/6250] eta: 0:11:23 lr: 0.000109 grad: 0.0676 (0.0696) loss: 0.8280 (0.8308) time: 0.1218 data: 0.0456 max mem: 9390 +Train: [27] [1700/6250] eta: 0:11:07 lr: 0.000109 grad: 0.0689 (0.0697) loss: 0.8279 (0.8306) time: 0.1283 data: 0.0455 max mem: 9390 +Train: [27] [1800/6250] eta: 0:10:51 lr: 0.000109 grad: 0.0696 (0.0698) loss: 0.8281 (0.8303) time: 0.1276 data: 0.0440 max mem: 9390 +Train: [27] [1900/6250] eta: 0:10:34 lr: 0.000109 grad: 0.0665 (0.0699) loss: 0.8235 (0.8301) time: 0.1465 data: 0.0664 max mem: 9390 +Train: [27] [2000/6250] eta: 0:10:18 lr: 0.000109 grad: 0.0763 (0.0700) loss: 0.8184 (0.8299) time: 0.1382 data: 0.0592 max mem: 9390 +Train: [27] [2100/6250] eta: 0:10:01 lr: 0.000109 grad: 0.0700 (0.0700) loss: 0.8270 (0.8297) time: 0.1214 data: 0.0403 max mem: 9390 +Train: [27] [2200/6250] eta: 0:09:45 lr: 0.000109 grad: 0.0730 (0.0703) loss: 0.8172 (0.8295) time: 0.1386 data: 0.0612 max mem: 9390 +Train: [27] [2300/6250] eta: 0:09:28 lr: 0.000109 grad: 0.0711 (0.0703) loss: 0.8250 (0.8294) time: 0.1377 data: 0.0572 max mem: 9390 +Train: [27] [2400/6250] eta: 0:09:13 lr: 0.000109 grad: 0.0680 (0.0704) loss: 0.8255 (0.8293) time: 0.1257 data: 0.0414 max mem: 9390 +Train: [27] [2500/6250] eta: 0:08:57 lr: 0.000109 grad: 0.0666 (0.0704) loss: 0.8314 (0.8292) time: 0.1274 data: 0.0438 max mem: 9390 +Train: [27] [2600/6250] eta: 0:08:42 lr: 0.000109 grad: 0.0682 (0.0705) loss: 0.8212 (0.8291) time: 0.1413 data: 0.0469 max mem: 9390 +Train: [27] [2700/6250] eta: 0:08:26 lr: 0.000109 grad: 0.0703 (0.0704) loss: 0.8306 (0.8290) time: 0.1277 data: 0.0455 max mem: 9390 +Train: [27] [2800/6250] eta: 0:08:10 lr: 0.000109 grad: 0.0718 (0.0705) loss: 0.8277 (0.8290) time: 0.1378 data: 0.0553 max mem: 9390 +Train: [27] [2900/6250] eta: 0:07:55 lr: 0.000109 grad: 0.0638 (0.0704) loss: 0.8372 (0.8291) time: 0.1316 data: 0.0452 max mem: 9390 +Train: [27] [3000/6250] eta: 0:07:40 lr: 0.000109 grad: 0.0657 (0.0704) loss: 0.8353 (0.8292) time: 0.1605 data: 0.0846 max mem: 9390 +Train: [27] [3100/6250] eta: 0:07:25 lr: 0.000108 grad: 0.0628 (0.0704) loss: 0.8331 (0.8293) time: 0.1247 data: 0.0421 max mem: 9390 +Train: [27] [3200/6250] eta: 0:07:10 lr: 0.000108 grad: 0.0667 (0.0703) loss: 0.8332 (0.8294) time: 0.1342 data: 0.0529 max mem: 9390 +Train: [27] [3300/6250] eta: 0:06:56 lr: 0.000108 grad: 0.0638 (0.0703) loss: 0.8369 (0.8295) time: 0.1214 data: 0.0407 max mem: 9390 +Train: [27] [3400/6250] eta: 0:06:41 lr: 0.000108 grad: 0.0677 (0.0703) loss: 0.8274 (0.8295) time: 0.1417 data: 0.0597 max mem: 9390 +Train: [27] [3500/6250] eta: 0:06:27 lr: 0.000108 grad: 0.0649 (0.0703) loss: 0.8251 (0.8295) time: 0.1383 data: 0.0602 max mem: 9390 +Train: [27] [3600/6250] eta: 0:06:12 lr: 0.000108 grad: 0.0675 (0.0703) loss: 0.8269 (0.8295) time: 0.1394 data: 0.0606 max mem: 9390 +Train: [27] [3700/6250] eta: 0:05:58 lr: 0.000108 grad: 0.0673 (0.0703) loss: 0.8308 (0.8294) time: 0.1295 data: 0.0480 max mem: 9390 +Train: [27] [3800/6250] eta: 0:05:44 lr: 0.000108 grad: 0.0640 (0.0704) loss: 0.8339 (0.8294) time: 0.1461 data: 0.0600 max mem: 9390 +Train: [27] [3900/6250] eta: 0:05:30 lr: 0.000108 grad: 0.0752 (0.0704) loss: 0.8262 (0.8294) time: 0.1294 data: 0.0525 max mem: 9390 +Train: [27] [4000/6250] eta: 0:05:16 lr: 0.000108 grad: 0.0694 (0.0703) loss: 0.8288 (0.8294) time: 0.1454 data: 0.0682 max mem: 9390 +Train: [27] [4100/6250] eta: 0:05:02 lr: 0.000108 grad: 0.0688 (0.0704) loss: 0.8262 (0.8294) time: 0.0968 data: 0.0151 max mem: 9390 +Train: [27] [4200/6250] eta: 0:04:47 lr: 0.000108 grad: 0.0690 (0.0703) loss: 0.8282 (0.8294) time: 0.1331 data: 0.0555 max mem: 9390 +Train: [27] [4300/6250] eta: 0:04:33 lr: 0.000108 grad: 0.0658 (0.0703) loss: 0.8313 (0.8294) time: 0.1244 data: 0.0491 max mem: 9390 +Train: [27] [4400/6250] eta: 0:04:19 lr: 0.000108 grad: 0.0655 (0.0702) loss: 0.8300 (0.8295) time: 0.1506 data: 0.0677 max mem: 9390 +Train: [27] [4500/6250] eta: 0:04:05 lr: 0.000108 grad: 0.0628 (0.0702) loss: 0.8293 (0.8296) time: 0.1419 data: 0.0643 max mem: 9390 +Train: [27] [4600/6250] eta: 0:03:51 lr: 0.000108 grad: 0.0635 (0.0701) loss: 0.8307 (0.8297) time: 0.1300 data: 0.0522 max mem: 9390 +Train: [27] [4700/6250] eta: 0:03:37 lr: 0.000108 grad: 0.0651 (0.0700) loss: 0.8333 (0.8298) time: 0.1658 data: 0.0828 max mem: 9390 +Train: [27] [4800/6250] eta: 0:03:23 lr: 0.000108 grad: 0.0665 (0.0699) loss: 0.8323 (0.8299) time: 0.1654 data: 0.0844 max mem: 9390 +Train: [27] [4900/6250] eta: 0:03:10 lr: 0.000108 grad: 0.0606 (0.0699) loss: 0.8268 (0.8300) time: 0.1695 data: 0.0854 max mem: 9390 +Train: [27] [5000/6250] eta: 0:02:56 lr: 0.000108 grad: 0.0645 (0.0698) loss: 0.8316 (0.8301) time: 0.1418 data: 0.0615 max mem: 9390 +Train: [27] [5100/6250] eta: 0:02:42 lr: 0.000108 grad: 0.0672 (0.0698) loss: 0.8353 (0.8301) time: 0.1547 data: 0.0749 max mem: 9390 +Train: [27] [5200/6250] eta: 0:02:28 lr: 0.000108 grad: 0.0646 (0.0697) loss: 0.8258 (0.8301) time: 0.1704 data: 0.0750 max mem: 9390 +Train: [27] [5300/6250] eta: 0:02:13 lr: 0.000108 grad: 0.0640 (0.0696) loss: 0.8322 (0.8302) time: 0.1393 data: 0.0609 max mem: 9390 +Train: [27] [5400/6250] eta: 0:02:00 lr: 0.000108 grad: 0.0642 (0.0696) loss: 0.8335 (0.8302) time: 0.1346 data: 0.0468 max mem: 9390 +Train: [27] [5500/6250] eta: 0:01:46 lr: 0.000108 grad: 0.0685 (0.0695) loss: 0.8235 (0.8302) time: 0.1401 data: 0.0624 max mem: 9390 +Train: [27] [5600/6250] eta: 0:01:32 lr: 0.000108 grad: 0.0664 (0.0695) loss: 0.8365 (0.8303) time: 0.1382 data: 0.0609 max mem: 9390 +Train: [27] [5700/6250] eta: 0:01:17 lr: 0.000108 grad: 0.0668 (0.0694) loss: 0.8278 (0.8303) time: 0.1541 data: 0.0722 max mem: 9390 +Train: [27] [5800/6250] eta: 0:01:03 lr: 0.000108 grad: 0.0632 (0.0694) loss: 0.8299 (0.8303) time: 0.1485 data: 0.0656 max mem: 9390 +Train: [27] [5900/6250] eta: 0:00:49 lr: 0.000108 grad: 0.0671 (0.0694) loss: 0.8295 (0.8303) time: 0.1303 data: 0.0500 max mem: 9390 +Train: [27] [6000/6250] eta: 0:00:35 lr: 0.000108 grad: 0.0627 (0.0694) loss: 0.8284 (0.8303) time: 0.1451 data: 0.0668 max mem: 9390 +Train: [27] [6100/6250] eta: 0:00:21 lr: 0.000108 grad: 0.0664 (0.0694) loss: 0.8314 (0.8303) time: 0.1379 data: 0.0551 max mem: 9390 +Train: [27] [6200/6250] eta: 0:00:07 lr: 0.000108 grad: 0.0686 (0.0694) loss: 0.8313 (0.8303) time: 0.2050 data: 0.1203 max mem: 9390 +Train: [27] [6249/6250] eta: 0:00:00 lr: 0.000108 grad: 0.0648 (0.0694) loss: 0.8301 (0.8303) time: 0.1144 data: 0.0306 max mem: 9390 +Train: [27] Total time: 0:14:50 (0.1424 s / it) +Averaged stats: lr: 0.000108 grad: 0.0648 (0.0694) loss: 0.8301 (0.8303) +Eval (hcp-train-subset): [27] [ 0/62] eta: 0:04:01 loss: 0.8558 (0.8558) time: 3.8966 data: 3.8304 max mem: 9390 +Eval (hcp-train-subset): [27] [61/62] eta: 0:00:00 loss: 0.8443 (0.8436) time: 0.1464 data: 0.1216 max mem: 9390 +Eval (hcp-train-subset): [27] Total time: 0:00:14 (0.2309 s / it) +Averaged stats (hcp-train-subset): loss: 0.8443 (0.8436) +Eval (hcp-val): [27] [ 0/62] eta: 0:04:25 loss: 0.8376 (0.8376) time: 4.2742 data: 4.2294 max mem: 9390 +Eval (hcp-val): [27] [61/62] eta: 0:00:00 loss: 0.8380 (0.8399) time: 0.1283 data: 0.1017 max mem: 9390 +Eval (hcp-val): [27] Total time: 0:00:14 (0.2361 s / it) +Averaged stats (hcp-val): loss: 0.8380 (0.8399) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +Train: [28] [ 0/6250] eta: 6:26:03 lr: 0.000108 grad: 0.0597 (0.0597) loss: 0.8272 (0.8272) time: 3.7062 data: 3.4627 max mem: 9390 +Train: [28] [ 100/6250] eta: 0:20:28 lr: 0.000108 grad: 0.0718 (0.0704) loss: 0.8337 (0.8377) time: 0.1377 data: 0.0529 max mem: 9390 +Train: [28] [ 200/6250] eta: 0:17:53 lr: 0.000108 grad: 0.0729 (0.0735) loss: 0.8248 (0.8326) time: 0.1355 data: 0.0557 max mem: 9390 +Train: [28] [ 300/6250] eta: 0:16:44 lr: 0.000108 grad: 0.0720 (0.0732) loss: 0.8283 (0.8312) time: 0.1438 data: 0.0580 max mem: 9390 +Train: [28] [ 400/6250] eta: 0:15:57 lr: 0.000108 grad: 0.0712 (0.0725) loss: 0.8238 (0.8308) time: 0.1620 data: 0.0751 max mem: 9390 +Train: [28] [ 500/6250] eta: 0:15:08 lr: 0.000108 grad: 0.0639 (0.0722) loss: 0.8347 (0.8311) time: 0.1095 data: 0.0242 max mem: 9390 +Train: [28] [ 600/6250] eta: 0:14:32 lr: 0.000108 grad: 0.0678 (0.0715) loss: 0.8303 (0.8317) time: 0.1253 data: 0.0357 max mem: 9390 +Train: [28] [ 700/6250] eta: 0:14:06 lr: 0.000108 grad: 0.0663 (0.0709) loss: 0.8349 (0.8324) time: 0.1395 data: 0.0474 max mem: 9390 +Train: [28] [ 800/6250] eta: 0:13:37 lr: 0.000108 grad: 0.0645 (0.0702) loss: 0.8327 (0.8330) time: 0.1463 data: 0.0604 max mem: 9390 +Train: [28] [ 900/6250] eta: 0:13:17 lr: 0.000108 grad: 0.0644 (0.0697) loss: 0.8394 (0.8332) time: 0.1564 data: 0.0785 max mem: 9390 +Train: [28] [1000/6250] eta: 0:13:01 lr: 0.000108 grad: 0.0636 (0.0692) loss: 0.8338 (0.8335) time: 0.1096 data: 0.0266 max mem: 9390 +Train: [28] [1100/6250] eta: 0:12:48 lr: 0.000108 grad: 0.0635 (0.0688) loss: 0.8367 (0.8336) time: 0.1053 data: 0.0302 max mem: 9390 +Train: [28] [1200/6250] eta: 0:12:34 lr: 0.000108 grad: 0.0653 (0.0686) loss: 0.8376 (0.8337) time: 0.1687 data: 0.0875 max mem: 9390 +Train: [28] [1300/6250] eta: 0:12:29 lr: 0.000107 grad: 0.0673 (0.0687) loss: 0.8329 (0.8336) time: 0.0908 data: 0.0002 max mem: 9390 +Train: [28] [1400/6250] eta: 0:12:08 lr: 0.000107 grad: 0.0677 (0.0687) loss: 0.8285 (0.8334) time: 0.1493 data: 0.0738 max mem: 9390 +Train: [28] [1500/6250] eta: 0:11:48 lr: 0.000107 grad: 0.0637 (0.0689) loss: 0.8272 (0.8333) time: 0.1395 data: 0.0603 max mem: 9390 +Train: [28] [1600/6250] eta: 0:11:32 lr: 0.000107 grad: 0.0698 (0.0690) loss: 0.8341 (0.8332) time: 0.1410 data: 0.0677 max mem: 9390 +Train: [28] [1700/6250] eta: 0:11:14 lr: 0.000107 grad: 0.0643 (0.0691) loss: 0.8341 (0.8331) time: 0.1243 data: 0.0499 max mem: 9390 +Train: [28] [1800/6250] eta: 0:10:58 lr: 0.000107 grad: 0.0748 (0.0692) loss: 0.8319 (0.8329) time: 0.1427 data: 0.0623 max mem: 9390 +Train: [28] [1900/6250] eta: 0:10:42 lr: 0.000107 grad: 0.0656 (0.0693) loss: 0.8352 (0.8328) time: 0.1449 data: 0.0660 max mem: 9390 +Train: [28] [2000/6250] eta: 0:10:28 lr: 0.000107 grad: 0.0698 (0.0694) loss: 0.8272 (0.8327) time: 0.1442 data: 0.0632 max mem: 9390 +Train: [28] [2100/6250] eta: 0:10:13 lr: 0.000107 grad: 0.0697 (0.0700) loss: 0.8374 (0.8325) time: 0.1373 data: 0.0545 max mem: 9390 +Train: [28] [2200/6250] eta: 0:09:57 lr: 0.000107 grad: 0.0676 (0.0700) loss: 0.8297 (0.8325) time: 0.1531 data: 0.0617 max mem: 9390 +Train: [28] [2300/6250] eta: 0:09:45 lr: 0.000107 grad: 0.0632 (0.0700) loss: 0.8343 (0.8324) time: 0.0918 data: 0.0002 max mem: 9390 +Train: [28] [2400/6250] eta: 0:09:30 lr: 0.000107 grad: 0.0667 (0.0700) loss: 0.8311 (0.8323) time: 0.1580 data: 0.0794 max mem: 9390 +Train: [28] [2500/6250] eta: 0:09:13 lr: 0.000107 grad: 0.0613 (0.0700) loss: 0.8281 (0.8322) time: 0.1340 data: 0.0529 max mem: 9390 +Train: [28] [2600/6250] eta: 0:08:59 lr: 0.000107 grad: 0.0682 (0.0701) loss: 0.8339 (0.8321) time: 0.1366 data: 0.0625 max mem: 9390 +Train: [28] [2700/6250] eta: 0:08:43 lr: 0.000107 grad: 0.0665 (0.0700) loss: 0.8308 (0.8321) time: 0.1555 data: 0.0749 max mem: 9390 +Train: [28] [2800/6250] eta: 0:08:28 lr: 0.000107 grad: 0.0686 (0.0703) loss: 0.8337 (0.8320) time: 0.1467 data: 0.0638 max mem: 9390 +Train: [28] [2900/6250] eta: 0:08:13 lr: 0.000107 grad: 0.0660 (0.0702) loss: 0.8388 (0.8321) time: 0.1692 data: 0.0825 max mem: 9390 +Train: [28] [3000/6250] eta: 0:07:58 lr: 0.000107 grad: 0.0665 (0.0702) loss: 0.8310 (0.8320) time: 0.1419 data: 0.0597 max mem: 9390 +Train: [28] [3100/6250] eta: 0:07:43 lr: 0.000107 grad: 0.0673 (0.0702) loss: 0.8314 (0.8320) time: 0.1475 data: 0.0704 max mem: 9390 +Train: [28] [3200/6250] eta: 0:07:26 lr: 0.000107 grad: 0.0674 (0.0703) loss: 0.8339 (0.8321) time: 0.1244 data: 0.0391 max mem: 9390 +Train: [28] [3300/6250] eta: 0:07:11 lr: 0.000107 grad: 0.0678 (0.0702) loss: 0.8348 (0.8321) time: 0.1249 data: 0.0460 max mem: 9390 +Train: [28] [3400/6250] eta: 0:06:56 lr: 0.000107 grad: 0.0670 (0.0702) loss: 0.8361 (0.8322) time: 0.1358 data: 0.0503 max mem: 9390 +Train: [28] [3500/6250] eta: 0:06:41 lr: 0.000107 grad: 0.0673 (0.0702) loss: 0.8339 (0.8322) time: 0.1489 data: 0.0704 max mem: 9390 +Train: [28] [3600/6250] eta: 0:06:26 lr: 0.000107 grad: 0.0681 (0.0702) loss: 0.8313 (0.8322) time: 0.1343 data: 0.0559 max mem: 9390 +Train: [28] [3700/6250] eta: 0:06:12 lr: 0.000107 grad: 0.0673 (0.0701) loss: 0.8293 (0.8321) time: 0.1777 data: 0.0713 max mem: 9390 +Train: [28] [3800/6250] eta: 0:05:57 lr: 0.000107 grad: 0.0618 (0.0701) loss: 0.8329 (0.8321) time: 0.1436 data: 0.0594 max mem: 9390 +Train: [28] [3900/6250] eta: 0:05:43 lr: 0.000107 grad: 0.0651 (0.0700) loss: 0.8311 (0.8321) time: 0.1340 data: 0.0495 max mem: 9390 +Train: [28] [4000/6250] eta: 0:05:28 lr: 0.000107 grad: 0.0670 (0.0700) loss: 0.8335 (0.8321) time: 0.1464 data: 0.0638 max mem: 9390 +Train: [28] [4100/6250] eta: 0:05:12 lr: 0.000107 grad: 0.0649 (0.0700) loss: 0.8329 (0.8321) time: 0.1348 data: 0.0563 max mem: 9390 +Train: [28] [4200/6250] eta: 0:04:58 lr: 0.000107 grad: 0.0682 (0.0699) loss: 0.8304 (0.8321) time: 0.1570 data: 0.0777 max mem: 9390 +Train: [28] [4300/6250] eta: 0:04:43 lr: 0.000107 grad: 0.0677 (0.0699) loss: 0.8303 (0.8321) time: 0.1448 data: 0.0686 max mem: 9390 +Train: [28] [4400/6250] eta: 0:04:29 lr: 0.000107 grad: 0.0726 (0.0699) loss: 0.8286 (0.8320) time: 0.1837 data: 0.0988 max mem: 9390 +Train: [28] [4500/6250] eta: 0:04:14 lr: 0.000107 grad: 0.0604 (0.0699) loss: 0.8320 (0.8320) time: 0.1368 data: 0.0567 max mem: 9390 +Train: [28] [4600/6250] eta: 0:03:59 lr: 0.000107 grad: 0.0644 (0.0699) loss: 0.8327 (0.8320) time: 0.1461 data: 0.0722 max mem: 9390 +Train: [28] [4700/6250] eta: 0:03:45 lr: 0.000107 grad: 0.0698 (0.0699) loss: 0.8310 (0.8319) time: 0.1452 data: 0.0678 max mem: 9390 +Train: [28] [4800/6250] eta: 0:03:31 lr: 0.000107 grad: 0.0706 (0.0699) loss: 0.8331 (0.8319) time: 0.1416 data: 0.0667 max mem: 9390 +Train: [28] [4900/6250] eta: 0:03:17 lr: 0.000107 grad: 0.0692 (0.0698) loss: 0.8355 (0.8319) time: 0.1810 data: 0.0881 max mem: 9390 +Train: [28] [5000/6250] eta: 0:03:02 lr: 0.000107 grad: 0.0678 (0.0698) loss: 0.8298 (0.8319) time: 0.1443 data: 0.0644 max mem: 9390 +Train: [28] [5100/6250] eta: 0:02:48 lr: 0.000107 grad: 0.0691 (0.0699) loss: 0.8304 (0.8318) time: 0.1863 data: 0.0889 max mem: 9390 +Train: [28] [5200/6250] eta: 0:02:34 lr: 0.000107 grad: 0.0679 (0.0699) loss: 0.8327 (0.8317) time: 0.1338 data: 0.0500 max mem: 9390 +Train: [28] [5300/6250] eta: 0:02:19 lr: 0.000107 grad: 0.0713 (0.0700) loss: 0.8256 (0.8317) time: 0.1310 data: 0.0549 max mem: 9390 +Train: [28] [5400/6250] eta: 0:02:04 lr: 0.000107 grad: 0.0721 (0.0700) loss: 0.8225 (0.8316) time: 0.1375 data: 0.0526 max mem: 9390 +Train: [28] [5500/6250] eta: 0:01:50 lr: 0.000107 grad: 0.0749 (0.0700) loss: 0.8212 (0.8315) time: 0.1322 data: 0.0557 max mem: 9390 +Train: [28] [5600/6250] eta: 0:01:35 lr: 0.000106 grad: 0.0693 (0.0700) loss: 0.8332 (0.8314) time: 0.1573 data: 0.0751 max mem: 9390 +Train: [28] [5700/6250] eta: 0:01:20 lr: 0.000106 grad: 0.0677 (0.0700) loss: 0.8288 (0.8314) time: 0.1797 data: 0.1020 max mem: 9390 +Train: [28] [5800/6250] eta: 0:01:06 lr: 0.000106 grad: 0.0658 (0.0700) loss: 0.8264 (0.8313) time: 0.1335 data: 0.0514 max mem: 9390 +Train: [28] [5900/6250] eta: 0:00:51 lr: 0.000106 grad: 0.0693 (0.0700) loss: 0.8296 (0.8312) time: 0.1399 data: 0.0605 max mem: 9390 +Train: [28] [6000/6250] eta: 0:00:36 lr: 0.000106 grad: 0.0703 (0.0700) loss: 0.8368 (0.8312) time: 0.1233 data: 0.0389 max mem: 9390 +Train: [28] [6100/6250] eta: 0:00:21 lr: 0.000106 grad: 0.0718 (0.0700) loss: 0.8341 (0.8312) time: 0.1381 data: 0.0586 max mem: 9390 +Train: [28] [6200/6250] eta: 0:00:07 lr: 0.000106 grad: 0.0676 (0.0700) loss: 0.8318 (0.8312) time: 0.1385 data: 0.0624 max mem: 9390 +Train: [28] [6249/6250] eta: 0:00:00 lr: 0.000106 grad: 0.0656 (0.0700) loss: 0.8283 (0.8311) time: 0.1460 data: 0.0642 max mem: 9390 +Train: [28] Total time: 0:15:18 (0.1470 s / it) +Averaged stats: lr: 0.000106 grad: 0.0656 (0.0700) loss: 0.8283 (0.8311) +Eval (hcp-train-subset): [28] [ 0/62] eta: 0:05:17 loss: 0.8533 (0.8533) time: 5.1177 data: 5.0853 max mem: 9390 +Eval (hcp-train-subset): [28] [61/62] eta: 0:00:00 loss: 0.8437 (0.8436) time: 0.1563 data: 0.1311 max mem: 9390 +Eval (hcp-train-subset): [28] Total time: 0:00:14 (0.2308 s / it) +Averaged stats (hcp-train-subset): loss: 0.8437 (0.8436) +Eval (hcp-val): [28] [ 0/62] eta: 0:03:06 loss: 0.8375 (0.8375) time: 3.0114 data: 2.9382 max mem: 9390 +Eval (hcp-val): [28] [61/62] eta: 0:00:00 loss: 0.8383 (0.8388) time: 0.1360 data: 0.1096 max mem: 9390 +Eval (hcp-val): [28] Total time: 0:00:13 (0.2098 s / it) +Averaged stats (hcp-val): loss: 0.8383 (0.8388) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +Train: [29] [ 0/6250] eta: 10:37:31 lr: 0.000106 grad: 0.0750 (0.0750) loss: 0.8665 (0.8665) time: 6.1202 data: 6.0249 max mem: 9390 +Train: [29] [ 100/6250] eta: 0:19:50 lr: 0.000106 grad: 0.0662 (0.0781) loss: 0.8295 (0.8404) time: 0.1467 data: 0.0610 max mem: 9390 +Train: [29] [ 200/6250] eta: 0:17:11 lr: 0.000106 grad: 0.0647 (0.0747) loss: 0.8319 (0.8374) time: 0.1519 data: 0.0729 max mem: 9390 +Train: [29] [ 300/6250] eta: 0:15:52 lr: 0.000106 grad: 0.0626 (0.0730) loss: 0.8381 (0.8363) time: 0.1179 data: 0.0308 max mem: 9390 +Train: [29] [ 400/6250] eta: 0:14:58 lr: 0.000106 grad: 0.0609 (0.0720) loss: 0.8397 (0.8362) time: 0.1460 data: 0.0696 max mem: 9390 +Train: [29] [ 500/6250] eta: 0:14:19 lr: 0.000106 grad: 0.0659 (0.0709) loss: 0.8334 (0.8360) time: 0.1330 data: 0.0465 max mem: 9390 +Train: [29] [ 600/6250] eta: 0:13:44 lr: 0.000106 grad: 0.0628 (0.0703) loss: 0.8381 (0.8364) time: 0.1352 data: 0.0524 max mem: 9390 +Train: [29] [ 700/6250] eta: 0:13:15 lr: 0.000106 grad: 0.0638 (0.0698) loss: 0.8318 (0.8366) time: 0.1210 data: 0.0233 max mem: 9390 +Train: [29] [ 800/6250] eta: 0:12:55 lr: 0.000106 grad: 0.0673 (0.0692) loss: 0.8392 (0.8368) time: 0.1240 data: 0.0409 max mem: 9390 +Train: [29] [ 900/6250] eta: 0:12:41 lr: 0.000106 grad: 0.0635 (0.0688) loss: 0.8338 (0.8368) time: 0.1472 data: 0.0644 max mem: 9390 +Train: [29] [1000/6250] eta: 0:12:30 lr: 0.000106 grad: 0.0657 (0.0689) loss: 0.8338 (0.8365) time: 0.1339 data: 0.0507 max mem: 9390 +Train: [29] [1100/6250] eta: 0:12:16 lr: 0.000106 grad: 0.0619 (0.0687) loss: 0.8292 (0.8365) time: 0.1613 data: 0.0834 max mem: 9390 +Train: [29] [1200/6250] eta: 0:11:59 lr: 0.000106 grad: 0.0666 (0.0687) loss: 0.8397 (0.8362) time: 0.1288 data: 0.0478 max mem: 9390 +Train: [29] [1300/6250] eta: 0:11:47 lr: 0.000106 grad: 0.0694 (0.0689) loss: 0.8347 (0.8358) time: 0.1473 data: 0.0693 max mem: 9390 +Train: [29] [1400/6250] eta: 0:11:32 lr: 0.000106 grad: 0.0683 (0.0689) loss: 0.8367 (0.8355) time: 0.1423 data: 0.0650 max mem: 9390 +Train: [29] [1500/6250] eta: 0:11:17 lr: 0.000106 grad: 0.0682 (0.0689) loss: 0.8326 (0.8352) time: 0.1525 data: 0.0739 max mem: 9390 +Train: [29] [1600/6250] eta: 0:11:02 lr: 0.000106 grad: 0.0703 (0.0693) loss: 0.8315 (0.8348) time: 0.1405 data: 0.0637 max mem: 9390 +Train: [29] [1700/6250] eta: 0:10:47 lr: 0.000106 grad: 0.0691 (0.0694) loss: 0.8288 (0.8344) time: 0.1433 data: 0.0646 max mem: 9390 +Train: [29] [1800/6250] eta: 0:10:33 lr: 0.000106 grad: 0.0625 (0.0695) loss: 0.8323 (0.8342) time: 0.1317 data: 0.0493 max mem: 9390 +Train: [29] [1900/6250] eta: 0:10:19 lr: 0.000106 grad: 0.0679 (0.0695) loss: 0.8267 (0.8340) time: 0.1573 data: 0.0785 max mem: 9390 +Train: [29] [2000/6250] eta: 0:10:06 lr: 0.000106 grad: 0.0644 (0.0696) loss: 0.8301 (0.8338) time: 0.1353 data: 0.0569 max mem: 9390 +Train: [29] [2100/6250] eta: 0:09:54 lr: 0.000106 grad: 0.0705 (0.0695) loss: 0.8314 (0.8336) time: 0.1075 data: 0.0332 max mem: 9390 +Train: [29] [2200/6250] eta: 0:09:42 lr: 0.000106 grad: 0.0680 (0.0695) loss: 0.8299 (0.8334) time: 0.1557 data: 0.0548 max mem: 9390 +Train: [29] [2300/6250] eta: 0:09:28 lr: 0.000106 grad: 0.0672 (0.0696) loss: 0.8337 (0.8333) time: 0.1522 data: 0.0772 max mem: 9390 +Train: [29] [2400/6250] eta: 0:09:19 lr: 0.000106 grad: 0.0686 (0.0696) loss: 0.8268 (0.8331) time: 0.2352 data: 0.1508 max mem: 9390 +Train: [29] [2500/6250] eta: 0:09:03 lr: 0.000106 grad: 0.0715 (0.0696) loss: 0.8287 (0.8330) time: 0.1388 data: 0.0599 max mem: 9390 +Train: [29] [2600/6250] eta: 0:08:47 lr: 0.000106 grad: 0.0634 (0.0695) loss: 0.8336 (0.8329) time: 0.1276 data: 0.0465 max mem: 9390 +Train: [29] [2700/6250] eta: 0:08:32 lr: 0.000106 grad: 0.0666 (0.0695) loss: 0.8346 (0.8328) time: 0.1351 data: 0.0587 max mem: 9390 +Train: [29] [2800/6250] eta: 0:08:17 lr: 0.000106 grad: 0.0680 (0.0695) loss: 0.8273 (0.8327) time: 0.1594 data: 0.0623 max mem: 9390 +Train: [29] [2900/6250] eta: 0:08:05 lr: 0.000106 grad: 0.0665 (0.0694) loss: 0.8319 (0.8328) time: 0.1885 data: 0.0936 max mem: 9390 +Train: [29] [3000/6250] eta: 0:07:53 lr: 0.000106 grad: 0.0626 (0.0694) loss: 0.8377 (0.8328) time: 0.2200 data: 0.1085 max mem: 9390 +Train: [29] [3100/6250] eta: 0:07:39 lr: 0.000106 grad: 0.0712 (0.0695) loss: 0.8322 (0.8328) time: 0.1050 data: 0.0219 max mem: 9390 +Train: [29] [3200/6250] eta: 0:07:27 lr: 0.000106 grad: 0.0705 (0.0696) loss: 0.8318 (0.8327) time: 0.1289 data: 0.0375 max mem: 9390 +Train: [29] [3300/6250] eta: 0:07:11 lr: 0.000106 grad: 0.0715 (0.0696) loss: 0.8304 (0.8326) time: 0.1369 data: 0.0553 max mem: 9390 +Train: [29] [3400/6250] eta: 0:06:57 lr: 0.000106 grad: 0.0678 (0.0696) loss: 0.8315 (0.8326) time: 0.1321 data: 0.0448 max mem: 9390 +Train: [29] [3500/6250] eta: 0:06:42 lr: 0.000105 grad: 0.0684 (0.0696) loss: 0.8321 (0.8326) time: 0.1420 data: 0.0588 max mem: 9390 +Train: [29] [3600/6250] eta: 0:06:27 lr: 0.000105 grad: 0.0669 (0.0696) loss: 0.8340 (0.8326) time: 0.1109 data: 0.0261 max mem: 9390 +Train: [29] [3700/6250] eta: 0:06:11 lr: 0.000105 grad: 0.0664 (0.0696) loss: 0.8295 (0.8326) time: 0.1388 data: 0.0570 max mem: 9390 +Train: [29] [3800/6250] eta: 0:05:56 lr: 0.000105 grad: 0.0717 (0.0696) loss: 0.8341 (0.8326) time: 0.1263 data: 0.0443 max mem: 9390 +Train: [29] [3900/6250] eta: 0:05:40 lr: 0.000105 grad: 0.0672 (0.0696) loss: 0.8318 (0.8326) time: 0.1382 data: 0.0563 max mem: 9390 +Train: [29] [4000/6250] eta: 0:05:26 lr: 0.000105 grad: 0.0680 (0.0695) loss: 0.8348 (0.8326) time: 0.1309 data: 0.0502 max mem: 9390 +Train: [29] [4100/6250] eta: 0:05:11 lr: 0.000105 grad: 0.0646 (0.0697) loss: 0.8323 (0.8326) time: 0.1416 data: 0.0539 max mem: 9390 +Train: [29] [4200/6250] eta: 0:04:56 lr: 0.000105 grad: 0.0668 (0.0697) loss: 0.8280 (0.8325) time: 0.1303 data: 0.0471 max mem: 9390 +Train: [29] [4300/6250] eta: 0:04:42 lr: 0.000105 grad: 0.0670 (0.0697) loss: 0.8342 (0.8326) time: 0.1517 data: 0.0750 max mem: 9390 +Train: [29] [4400/6250] eta: 0:04:28 lr: 0.000105 grad: 0.0681 (0.0697) loss: 0.8396 (0.8326) time: 0.1323 data: 0.0500 max mem: 9390 +Train: [29] [4500/6250] eta: 0:04:13 lr: 0.000105 grad: 0.0648 (0.0697) loss: 0.8322 (0.8326) time: 0.1457 data: 0.0696 max mem: 9390 +Train: [29] [4600/6250] eta: 0:03:59 lr: 0.000105 grad: 0.0689 (0.0698) loss: 0.8295 (0.8326) time: 0.1377 data: 0.0549 max mem: 9390 +Train: [29] [4700/6250] eta: 0:03:45 lr: 0.000105 grad: 0.0699 (0.0698) loss: 0.8292 (0.8326) time: 0.1443 data: 0.0672 max mem: 9390 +Train: [29] [4800/6250] eta: 0:03:30 lr: 0.000105 grad: 0.0736 (0.0698) loss: 0.8263 (0.8325) time: 0.1373 data: 0.0616 max mem: 9390 +Train: [29] [4900/6250] eta: 0:03:16 lr: 0.000105 grad: 0.0697 (0.0698) loss: 0.8341 (0.8325) time: 0.1607 data: 0.0893 max mem: 9390 +Train: [29] [5000/6250] eta: 0:03:01 lr: 0.000105 grad: 0.0750 (0.0698) loss: 0.8286 (0.8325) time: 0.1449 data: 0.0693 max mem: 9390 +Train: [29] [5100/6250] eta: 0:02:47 lr: 0.000105 grad: 0.0755 (0.0699) loss: 0.8278 (0.8325) time: 0.1332 data: 0.0538 max mem: 9390 +Train: [29] [5200/6250] eta: 0:02:32 lr: 0.000105 grad: 0.0718 (0.0699) loss: 0.8292 (0.8324) time: 0.1535 data: 0.0664 max mem: 9390 +Train: [29] [5300/6250] eta: 0:02:18 lr: 0.000105 grad: 0.0676 (0.0700) loss: 0.8304 (0.8324) time: 0.1335 data: 0.0471 max mem: 9390 +Train: [29] [5400/6250] eta: 0:02:03 lr: 0.000105 grad: 0.0720 (0.0700) loss: 0.8299 (0.8323) time: 0.2639 data: 0.1908 max mem: 9390 +Train: [29] [5500/6250] eta: 0:01:48 lr: 0.000105 grad: 0.0711 (0.0701) loss: 0.8272 (0.8323) time: 0.1177 data: 0.0372 max mem: 9390 +Train: [29] [5600/6250] eta: 0:01:34 lr: 0.000105 grad: 0.0720 (0.0701) loss: 0.8326 (0.8322) time: 0.1304 data: 0.0494 max mem: 9390 +Train: [29] [5700/6250] eta: 0:01:19 lr: 0.000105 grad: 0.0738 (0.0701) loss: 0.8286 (0.8322) time: 0.1669 data: 0.0891 max mem: 9390 +Train: [29] [5800/6250] eta: 0:01:05 lr: 0.000105 grad: 0.0736 (0.0702) loss: 0.8272 (0.8322) time: 0.1407 data: 0.0558 max mem: 9390 +Train: [29] [5900/6250] eta: 0:00:50 lr: 0.000105 grad: 0.0668 (0.0702) loss: 0.8283 (0.8321) time: 0.1484 data: 0.0654 max mem: 9390 +Train: [29] [6000/6250] eta: 0:00:36 lr: 0.000105 grad: 0.0649 (0.0702) loss: 0.8304 (0.8321) time: 0.1487 data: 0.0618 max mem: 9390 +Train: [29] [6100/6250] eta: 0:00:21 lr: 0.000105 grad: 0.0732 (0.0703) loss: 0.8284 (0.8320) time: 0.1426 data: 0.0573 max mem: 9390 +Train: [29] [6200/6250] eta: 0:00:07 lr: 0.000105 grad: 0.0708 (0.0703) loss: 0.8305 (0.8320) time: 0.1274 data: 0.0477 max mem: 9390 +Train: [29] [6249/6250] eta: 0:00:00 lr: 0.000105 grad: 0.0680 (0.0704) loss: 0.8293 (0.8320) time: 0.1284 data: 0.0524 max mem: 9390 +Train: [29] Total time: 0:15:06 (0.1451 s / it) +Averaged stats: lr: 0.000105 grad: 0.0680 (0.0704) loss: 0.8293 (0.8320) +Eval (hcp-train-subset): [29] [ 0/62] eta: 0:04:20 loss: 0.8547 (0.8547) time: 4.1942 data: 4.1382 max mem: 9390 +Eval (hcp-train-subset): [29] [61/62] eta: 0:00:00 loss: 0.8435 (0.8433) time: 0.1191 data: 0.0939 max mem: 9390 +Eval (hcp-train-subset): [29] Total time: 0:00:14 (0.2325 s / it) +Averaged stats (hcp-train-subset): loss: 0.8435 (0.8433) +Making plots (hcp-train-subset): example=41 +Eval (hcp-val): [29] [ 0/62] eta: 0:04:49 loss: 0.8339 (0.8339) time: 4.6679 data: 4.6047 max mem: 9390 +Eval (hcp-val): [29] [61/62] eta: 0:00:00 loss: 0.8384 (0.8391) time: 0.1242 data: 0.0993 max mem: 9390 +Eval (hcp-val): [29] Total time: 0:00:13 (0.2150 s / it) +Averaged stats (hcp-val): loss: 0.8384 (0.8391) +Making plots (hcp-val): example=1 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +Train: [30] [ 0/6250] eta: 9:45:41 lr: 0.000105 grad: 0.0811 (0.0811) loss: 0.8585 (0.8585) time: 5.6226 data: 5.5166 max mem: 9390 +Train: [30] [ 100/6250] eta: 0:20:15 lr: 0.000105 grad: 0.0827 (0.0818) loss: 0.8155 (0.8283) time: 0.1460 data: 0.0605 max mem: 9390 +Train: [30] [ 200/6250] eta: 0:17:25 lr: 0.000105 grad: 0.0696 (0.0782) loss: 0.8319 (0.8269) time: 0.1345 data: 0.0549 max mem: 9390 +Train: [30] [ 300/6250] eta: 0:16:23 lr: 0.000105 grad: 0.0649 (0.0757) loss: 0.8311 (0.8273) time: 0.1630 data: 0.0814 max mem: 9390 +Train: [30] [ 400/6250] eta: 0:15:29 lr: 0.000105 grad: 0.0665 (0.0747) loss: 0.8283 (0.8276) time: 0.1362 data: 0.0503 max mem: 9390 +Train: [30] [ 500/6250] eta: 0:14:56 lr: 0.000105 grad: 0.0627 (0.0731) loss: 0.8307 (0.8276) time: 0.1503 data: 0.0647 max mem: 9390 +Train: [30] [ 600/6250] eta: 0:14:20 lr: 0.000105 grad: 0.0613 (0.0722) loss: 0.8337 (0.8278) time: 0.1129 data: 0.0283 max mem: 9390 +Train: [30] [ 700/6250] eta: 0:13:52 lr: 0.000105 grad: 0.0634 (0.0714) loss: 0.8306 (0.8282) time: 0.1441 data: 0.0590 max mem: 9390 +Train: [30] [ 800/6250] eta: 0:13:24 lr: 0.000105 grad: 0.0651 (0.0711) loss: 0.8308 (0.8283) time: 0.1345 data: 0.0466 max mem: 9390 +Train: [30] [ 900/6250] eta: 0:13:00 lr: 0.000105 grad: 0.0645 (0.0706) loss: 0.8250 (0.8283) time: 0.1303 data: 0.0499 max mem: 9390 +Train: [30] [1000/6250] eta: 0:12:45 lr: 0.000105 grad: 0.0664 (0.0702) loss: 0.8310 (0.8282) time: 0.1378 data: 0.0551 max mem: 9390 +Train: [30] [1100/6250] eta: 0:12:31 lr: 0.000105 grad: 0.0692 (0.0701) loss: 0.8298 (0.8282) time: 0.1588 data: 0.0706 max mem: 9390 +Train: [30] [1200/6250] eta: 0:12:16 lr: 0.000105 grad: 0.0660 (0.0699) loss: 0.8298 (0.8280) time: 0.1254 data: 0.0448 max mem: 9390 +Train: [30] [1300/6250] eta: 0:12:00 lr: 0.000105 grad: 0.0682 (0.0698) loss: 0.8240 (0.8280) time: 0.1619 data: 0.0879 max mem: 9390 +Train: [30] [1400/6250] eta: 0:11:47 lr: 0.000104 grad: 0.0661 (0.0698) loss: 0.8284 (0.8279) time: 0.1433 data: 0.0680 max mem: 9390 +Train: [30] [1500/6250] eta: 0:11:31 lr: 0.000104 grad: 0.0627 (0.0697) loss: 0.8317 (0.8280) time: 0.1549 data: 0.0732 max mem: 9390 +Train: [30] [1600/6250] eta: 0:11:17 lr: 0.000104 grad: 0.0631 (0.0698) loss: 0.8247 (0.8280) time: 0.1652 data: 0.0894 max mem: 9390 +Train: [30] [1700/6250] eta: 0:11:04 lr: 0.000104 grad: 0.0695 (0.0699) loss: 0.8265 (0.8280) time: 0.1201 data: 0.0388 max mem: 9390 +Train: [30] [1800/6250] eta: 0:10:48 lr: 0.000104 grad: 0.0673 (0.0698) loss: 0.8242 (0.8280) time: 0.1502 data: 0.0665 max mem: 9390 +Train: [30] [1900/6250] eta: 0:10:33 lr: 0.000104 grad: 0.0652 (0.0698) loss: 0.8331 (0.8280) time: 0.1474 data: 0.0610 max mem: 9390 +Train: [30] [2000/6250] eta: 0:10:19 lr: 0.000104 grad: 0.0687 (0.0698) loss: 0.8299 (0.8280) time: 0.1425 data: 0.0617 max mem: 9390 +Train: [30] [2100/6250] eta: 0:10:01 lr: 0.000104 grad: 0.0682 (0.0700) loss: 0.8300 (0.8280) time: 0.1346 data: 0.0495 max mem: 9390 +Train: [30] [2200/6250] eta: 0:09:47 lr: 0.000104 grad: 0.0692 (0.0701) loss: 0.8260 (0.8280) time: 0.1520 data: 0.0765 max mem: 9390 +Train: [30] [2300/6250] eta: 0:09:32 lr: 0.000104 grad: 0.0663 (0.0701) loss: 0.8255 (0.8280) time: 0.1674 data: 0.0922 max mem: 9390 +Train: [30] [2400/6250] eta: 0:09:18 lr: 0.000104 grad: 0.0727 (0.0701) loss: 0.8300 (0.8279) time: 0.1345 data: 0.0587 max mem: 9390 +Train: [30] [2500/6250] eta: 0:09:03 lr: 0.000104 grad: 0.0690 (0.0703) loss: 0.8246 (0.8278) time: 0.1271 data: 0.0476 max mem: 9390 +Train: [30] [2600/6250] eta: 0:08:47 lr: 0.000104 grad: 0.0684 (0.0704) loss: 0.8264 (0.8277) time: 0.1571 data: 0.0795 max mem: 9390 +Train: [30] [2700/6250] eta: 0:08:33 lr: 0.000104 grad: 0.0693 (0.0704) loss: 0.8269 (0.8277) time: 0.1315 data: 0.0500 max mem: 9390 +Train: [30] [2800/6250] eta: 0:08:20 lr: 0.000104 grad: 0.0725 (0.0705) loss: 0.8280 (0.8276) time: 0.1935 data: 0.0648 max mem: 9390 +Train: [30] [2900/6250] eta: 0:08:05 lr: 0.000104 grad: 0.0665 (0.0705) loss: 0.8253 (0.8276) time: 0.1427 data: 0.0657 max mem: 9390 +Train: [30] [3000/6250] eta: 0:07:49 lr: 0.000104 grad: 0.0723 (0.0706) loss: 0.8237 (0.8275) time: 0.1282 data: 0.0459 max mem: 9390 +Train: [30] [3100/6250] eta: 0:07:35 lr: 0.000104 grad: 0.0684 (0.0707) loss: 0.8307 (0.8275) time: 0.1462 data: 0.0663 max mem: 9390 +Train: [30] [3200/6250] eta: 0:07:20 lr: 0.000104 grad: 0.0689 (0.0707) loss: 0.8227 (0.8275) time: 0.1478 data: 0.0750 max mem: 9390 +Train: [30] [3300/6250] eta: 0:07:05 lr: 0.000104 grad: 0.0668 (0.0707) loss: 0.8276 (0.8274) time: 0.1559 data: 0.0788 max mem: 9390 +Train: [30] [3400/6250] eta: 0:06:51 lr: 0.000104 grad: 0.0678 (0.0707) loss: 0.8249 (0.8274) time: 0.1173 data: 0.0389 max mem: 9390 +Train: [30] [3500/6250] eta: 0:06:36 lr: 0.000104 grad: 0.0723 (0.0707) loss: 0.8218 (0.8274) time: 0.1419 data: 0.0675 max mem: 9390 +Train: [30] [3600/6250] eta: 0:06:22 lr: 0.000104 grad: 0.0730 (0.0707) loss: 0.8305 (0.8274) time: 0.1541 data: 0.0731 max mem: 9390 +Train: [30] [3700/6250] eta: 0:06:07 lr: 0.000104 grad: 0.0722 (0.0707) loss: 0.8297 (0.8275) time: 0.1456 data: 0.0664 max mem: 9390 +Train: [30] [3800/6250] eta: 0:05:52 lr: 0.000104 grad: 0.0735 (0.0708) loss: 0.8213 (0.8274) time: 0.1457 data: 0.0636 max mem: 9390 +Train: [30] [3900/6250] eta: 0:05:38 lr: 0.000104 grad: 0.0679 (0.0708) loss: 0.8328 (0.8274) time: 0.1523 data: 0.0701 max mem: 9390 +Train: [30] [4000/6250] eta: 0:05:23 lr: 0.000104 grad: 0.0696 (0.0709) loss: 0.8250 (0.8274) time: 0.1438 data: 0.0599 max mem: 9390 +Train: [30] [4100/6250] eta: 0:05:08 lr: 0.000104 grad: 0.0701 (0.0709) loss: 0.8278 (0.8273) time: 0.1209 data: 0.0362 max mem: 9390 +Train: [30] [4200/6250] eta: 0:04:53 lr: 0.000104 grad: 0.0687 (0.0709) loss: 0.8235 (0.8273) time: 0.1386 data: 0.0552 max mem: 9390 +Train: [30] [4300/6250] eta: 0:04:39 lr: 0.000104 grad: 0.0693 (0.0709) loss: 0.8296 (0.8274) time: 0.1407 data: 0.0527 max mem: 9390 +Train: [30] [4400/6250] eta: 0:04:26 lr: 0.000104 grad: 0.0701 (0.0709) loss: 0.8309 (0.8275) time: 0.1377 data: 0.0572 max mem: 9390 +Train: [30] [4500/6250] eta: 0:04:13 lr: 0.000104 grad: 0.0658 (0.0709) loss: 0.8285 (0.8275) time: 0.1364 data: 0.0637 max mem: 9390 +Train: [30] [4600/6250] eta: 0:03:58 lr: 0.000104 grad: 0.0730 (0.0709) loss: 0.8301 (0.8276) time: 0.1456 data: 0.0636 max mem: 9390 +Train: [30] [4700/6250] eta: 0:03:44 lr: 0.000104 grad: 0.0687 (0.0710) loss: 0.8315 (0.8276) time: 0.1432 data: 0.0629 max mem: 9390 +Train: [30] [4800/6250] eta: 0:03:30 lr: 0.000104 grad: 0.0700 (0.0710) loss: 0.8294 (0.8276) time: 0.1455 data: 0.0701 max mem: 9390 +Train: [30] [4900/6250] eta: 0:03:16 lr: 0.000104 grad: 0.0700 (0.0711) loss: 0.8248 (0.8276) time: 0.1552 data: 0.0813 max mem: 9390 +Train: [30] [5000/6250] eta: 0:03:01 lr: 0.000104 grad: 0.0703 (0.0711) loss: 0.8256 (0.8276) time: 0.1511 data: 0.0636 max mem: 9390 +Train: [30] [5100/6250] eta: 0:02:47 lr: 0.000104 grad: 0.0669 (0.0711) loss: 0.8289 (0.8276) time: 0.1414 data: 0.0618 max mem: 9390 +Train: [30] [5200/6250] eta: 0:02:32 lr: 0.000104 grad: 0.0689 (0.0711) loss: 0.8286 (0.8276) time: 0.1308 data: 0.0523 max mem: 9390 +Train: [30] [5300/6250] eta: 0:02:17 lr: 0.000104 grad: 0.0676 (0.0711) loss: 0.8249 (0.8276) time: 0.1371 data: 0.0558 max mem: 9390 +Train: [30] [5400/6250] eta: 0:02:03 lr: 0.000103 grad: 0.0666 (0.0711) loss: 0.8236 (0.8276) time: 0.1467 data: 0.0639 max mem: 9390 +Train: [30] [5500/6250] eta: 0:01:48 lr: 0.000103 grad: 0.0695 (0.0711) loss: 0.8237 (0.8276) time: 0.1411 data: 0.0605 max mem: 9390 +Train: [30] [5600/6250] eta: 0:01:34 lr: 0.000103 grad: 0.0742 (0.0711) loss: 0.8254 (0.8276) time: 0.1437 data: 0.0615 max mem: 9390 +Train: [30] [5700/6250] eta: 0:01:19 lr: 0.000103 grad: 0.0671 (0.0712) loss: 0.8260 (0.8275) time: 0.1188 data: 0.0413 max mem: 9390 +Train: [30] [5800/6250] eta: 0:01:05 lr: 0.000103 grad: 0.0777 (0.0712) loss: 0.8244 (0.8275) time: 0.1359 data: 0.0564 max mem: 9390 +Train: [30] [5900/6250] eta: 0:00:50 lr: 0.000103 grad: 0.0722 (0.0713) loss: 0.8253 (0.8274) time: 0.1393 data: 0.0614 max mem: 9390 +Train: [30] [6000/6250] eta: 0:00:36 lr: 0.000103 grad: 0.0798 (0.0713) loss: 0.8280 (0.8275) time: 0.1236 data: 0.0446 max mem: 9390 +Train: [30] [6100/6250] eta: 0:00:21 lr: 0.000103 grad: 0.0670 (0.0713) loss: 0.8258 (0.8275) time: 0.1203 data: 0.0445 max mem: 9390 +Train: [30] [6200/6250] eta: 0:00:07 lr: 0.000103 grad: 0.0646 (0.0714) loss: 0.8314 (0.8275) time: 0.1413 data: 0.0597 max mem: 9390 +Train: [30] [6249/6250] eta: 0:00:00 lr: 0.000103 grad: 0.0686 (0.0713) loss: 0.8281 (0.8275) time: 0.1294 data: 0.0508 max mem: 9390 +Train: [30] Total time: 0:15:05 (0.1449 s / it) +Averaged stats: lr: 0.000103 grad: 0.0686 (0.0713) loss: 0.8281 (0.8275) +Eval (hcp-train-subset): [30] [ 0/62] eta: 0:05:56 loss: 0.8503 (0.8503) time: 5.7548 data: 5.7048 max mem: 9390 +Eval (hcp-train-subset): [30] [61/62] eta: 0:00:00 loss: 0.8425 (0.8420) time: 0.1620 data: 0.1367 max mem: 9390 +Eval (hcp-train-subset): [30] Total time: 0:00:15 (0.2429 s / it) +Averaged stats (hcp-train-subset): loss: 0.8425 (0.8420) +Eval (hcp-val): [30] [ 0/62] eta: 0:03:35 loss: 0.8341 (0.8341) time: 3.4695 data: 3.4007 max mem: 9390 +Eval (hcp-val): [30] [61/62] eta: 0:00:00 loss: 0.8375 (0.8384) time: 0.0910 data: 0.0640 max mem: 9390 +Eval (hcp-val): [30] Total time: 0:00:13 (0.2117 s / it) +Averaged stats (hcp-val): loss: 0.8375 (0.8384) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +Train: [31] [ 0/6250] eta: 8:27:51 lr: 0.000103 grad: 0.1566 (0.1566) loss: 0.8042 (0.8042) time: 4.8754 data: 4.7777 max mem: 9390 +Train: [31] [ 100/6250] eta: 0:20:21 lr: 0.000103 grad: 0.0737 (0.0869) loss: 0.8460 (0.8341) time: 0.1641 data: 0.0780 max mem: 9390 +Train: [31] [ 200/6250] eta: 0:17:27 lr: 0.000103 grad: 0.0736 (0.0829) loss: 0.8324 (0.8300) time: 0.1556 data: 0.0731 max mem: 9390 +Train: [31] [ 300/6250] eta: 0:16:35 lr: 0.000103 grad: 0.0690 (0.0800) loss: 0.8273 (0.8282) time: 0.1818 data: 0.1000 max mem: 9390 +Train: [31] [ 400/6250] eta: 0:15:33 lr: 0.000103 grad: 0.0698 (0.0786) loss: 0.8264 (0.8272) time: 0.1516 data: 0.0652 max mem: 9390 +Train: [31] [ 500/6250] eta: 0:14:58 lr: 0.000103 grad: 0.0660 (0.0774) loss: 0.8306 (0.8270) time: 0.1735 data: 0.0888 max mem: 9390 +Train: [31] [ 600/6250] eta: 0:14:19 lr: 0.000103 grad: 0.0685 (0.0758) loss: 0.8271 (0.8275) time: 0.1312 data: 0.0369 max mem: 9390 +Train: [31] [ 700/6250] eta: 0:13:49 lr: 0.000103 grad: 0.0669 (0.0746) loss: 0.8266 (0.8278) time: 0.1318 data: 0.0506 max mem: 9390 +Train: [31] [ 800/6250] eta: 0:13:35 lr: 0.000103 grad: 0.0618 (0.0737) loss: 0.8331 (0.8280) time: 0.1471 data: 0.0673 max mem: 9390 +Train: [31] [ 900/6250] eta: 0:13:19 lr: 0.000103 grad: 0.0643 (0.0731) loss: 0.8412 (0.8286) time: 0.1418 data: 0.0559 max mem: 9390 +Train: [31] [1000/6250] eta: 0:13:02 lr: 0.000103 grad: 0.0618 (0.0724) loss: 0.8307 (0.8290) time: 0.1410 data: 0.0631 max mem: 9390 +Train: [31] [1100/6250] eta: 0:12:45 lr: 0.000103 grad: 0.0647 (0.0720) loss: 0.8302 (0.8294) time: 0.1376 data: 0.0597 max mem: 9390 +Train: [31] [1200/6250] eta: 0:12:29 lr: 0.000103 grad: 0.0636 (0.0717) loss: 0.8336 (0.8297) time: 0.1628 data: 0.0818 max mem: 9390 +Train: [31] [1300/6250] eta: 0:12:12 lr: 0.000103 grad: 0.0662 (0.0714) loss: 0.8387 (0.8300) time: 0.1585 data: 0.0817 max mem: 9390 +Train: [31] [1400/6250] eta: 0:11:51 lr: 0.000103 grad: 0.0680 (0.0713) loss: 0.8321 (0.8300) time: 0.1322 data: 0.0448 max mem: 9390 +Train: [31] [1500/6250] eta: 0:11:30 lr: 0.000103 grad: 0.0678 (0.0712) loss: 0.8309 (0.8300) time: 0.1191 data: 0.0401 max mem: 9390 +Train: [31] [1600/6250] eta: 0:11:16 lr: 0.000103 grad: 0.0637 (0.0711) loss: 0.8322 (0.8300) time: 0.1742 data: 0.0854 max mem: 9390 +Train: [31] [1700/6250] eta: 0:11:00 lr: 0.000103 grad: 0.0699 (0.0710) loss: 0.8274 (0.8300) time: 0.1589 data: 0.0766 max mem: 9390 +Train: [31] [1800/6250] eta: 0:10:44 lr: 0.000103 grad: 0.0700 (0.0711) loss: 0.8299 (0.8300) time: 0.1288 data: 0.0450 max mem: 9390 +Train: [31] [1900/6250] eta: 0:10:28 lr: 0.000103 grad: 0.0631 (0.0711) loss: 0.8322 (0.8300) time: 0.1279 data: 0.0486 max mem: 9390 +Train: [31] [2000/6250] eta: 0:10:12 lr: 0.000103 grad: 0.0664 (0.0710) loss: 0.8315 (0.8301) time: 0.1444 data: 0.0658 max mem: 9390 +Train: [31] [2100/6250] eta: 0:09:59 lr: 0.000103 grad: 0.0667 (0.0710) loss: 0.8314 (0.8302) time: 0.1630 data: 0.0794 max mem: 9390 +Train: [31] [2200/6250] eta: 0:09:43 lr: 0.000103 grad: 0.0693 (0.0709) loss: 0.8328 (0.8303) time: 0.1346 data: 0.0499 max mem: 9390 +Train: [31] [2300/6250] eta: 0:09:27 lr: 0.000103 grad: 0.0640 (0.0708) loss: 0.8346 (0.8304) time: 0.1311 data: 0.0543 max mem: 9390 +Train: [31] [2400/6250] eta: 0:09:13 lr: 0.000103 grad: 0.0641 (0.0707) loss: 0.8341 (0.8305) time: 0.1418 data: 0.0579 max mem: 9390 +Train: [31] [2500/6250] eta: 0:08:59 lr: 0.000103 grad: 0.0655 (0.0707) loss: 0.8345 (0.8306) time: 0.1320 data: 0.0517 max mem: 9390 +Train: [31] [2600/6250] eta: 0:08:43 lr: 0.000103 grad: 0.0693 (0.0707) loss: 0.8380 (0.8306) time: 0.1420 data: 0.0615 max mem: 9390 +Train: [31] [2700/6250] eta: 0:08:31 lr: 0.000103 grad: 0.0722 (0.0707) loss: 0.8307 (0.8306) time: 0.1850 data: 0.1029 max mem: 9390 +Train: [31] [2800/6250] eta: 0:08:16 lr: 0.000103 grad: 0.0679 (0.0708) loss: 0.8279 (0.8305) time: 0.1414 data: 0.0610 max mem: 9390 +Train: [31] [2900/6250] eta: 0:08:00 lr: 0.000103 grad: 0.0681 (0.0708) loss: 0.8315 (0.8305) time: 0.1531 data: 0.0777 max mem: 9390 +Train: [31] [3000/6250] eta: 0:07:45 lr: 0.000103 grad: 0.0671 (0.0708) loss: 0.8274 (0.8305) time: 0.1441 data: 0.0643 max mem: 9390 +Train: [31] [3100/6250] eta: 0:07:31 lr: 0.000103 grad: 0.0691 (0.0708) loss: 0.8344 (0.8305) time: 0.1344 data: 0.0608 max mem: 9390 +Train: [31] [3200/6250] eta: 0:07:17 lr: 0.000102 grad: 0.0674 (0.0708) loss: 0.8367 (0.8305) time: 0.1645 data: 0.0910 max mem: 9390 +Train: [31] [3300/6250] eta: 0:07:02 lr: 0.000102 grad: 0.0708 (0.0708) loss: 0.8315 (0.8304) time: 0.1195 data: 0.0389 max mem: 9390 +Train: [31] [3400/6250] eta: 0:06:48 lr: 0.000102 grad: 0.0671 (0.0707) loss: 0.8299 (0.8304) time: 0.1449 data: 0.0645 max mem: 9390 +Train: [31] [3500/6250] eta: 0:06:35 lr: 0.000102 grad: 0.0689 (0.0708) loss: 0.8279 (0.8304) time: 0.1254 data: 0.0448 max mem: 9390 +Train: [31] [3600/6250] eta: 0:06:20 lr: 0.000102 grad: 0.0668 (0.0708) loss: 0.8348 (0.8304) time: 0.1255 data: 0.0476 max mem: 9390 +Train: [31] [3700/6250] eta: 0:06:06 lr: 0.000102 grad: 0.0691 (0.0708) loss: 0.8302 (0.8303) time: 0.1440 data: 0.0675 max mem: 9390 +Train: [31] [3800/6250] eta: 0:05:52 lr: 0.000102 grad: 0.0705 (0.0708) loss: 0.8291 (0.8303) time: 0.1632 data: 0.0869 max mem: 9390 +Train: [31] [3900/6250] eta: 0:05:39 lr: 0.000102 grad: 0.0724 (0.0709) loss: 0.8311 (0.8303) time: 0.1597 data: 0.0673 max mem: 9390 +Train: [31] [4000/6250] eta: 0:05:24 lr: 0.000102 grad: 0.0710 (0.0710) loss: 0.8254 (0.8302) time: 0.1311 data: 0.0535 max mem: 9390 +Train: [31] [4100/6250] eta: 0:05:10 lr: 0.000102 grad: 0.0723 (0.0710) loss: 0.8304 (0.8302) time: 0.1374 data: 0.0626 max mem: 9390 +Train: [31] [4200/6250] eta: 0:04:55 lr: 0.000102 grad: 0.0676 (0.0710) loss: 0.8318 (0.8301) time: 0.1288 data: 0.0521 max mem: 9390 +Train: [31] [4300/6250] eta: 0:04:41 lr: 0.000102 grad: 0.0700 (0.0711) loss: 0.8295 (0.8301) time: 0.1394 data: 0.0533 max mem: 9390 +Train: [31] [4400/6250] eta: 0:04:27 lr: 0.000102 grad: 0.0715 (0.0711) loss: 0.8299 (0.8300) time: 0.1920 data: 0.1108 max mem: 9390 +Train: [31] [4500/6250] eta: 0:04:13 lr: 0.000102 grad: 0.0678 (0.0711) loss: 0.8336 (0.8300) time: 0.1728 data: 0.0909 max mem: 9390 +Train: [31] [4600/6250] eta: 0:03:59 lr: 0.000102 grad: 0.0711 (0.0711) loss: 0.8261 (0.8299) time: 0.1537 data: 0.0754 max mem: 9390 +Train: [31] [4700/6250] eta: 0:03:45 lr: 0.000102 grad: 0.0668 (0.0711) loss: 0.8230 (0.8299) time: 0.1406 data: 0.0593 max mem: 9390 +Train: [31] [4800/6250] eta: 0:03:30 lr: 0.000102 grad: 0.0695 (0.0712) loss: 0.8297 (0.8298) time: 0.1399 data: 0.0538 max mem: 9390 +Train: [31] [4900/6250] eta: 0:03:16 lr: 0.000102 grad: 0.0746 (0.0712) loss: 0.8283 (0.8298) time: 0.1752 data: 0.0987 max mem: 9390 +Train: [31] [5000/6250] eta: 0:03:01 lr: 0.000102 grad: 0.0680 (0.0713) loss: 0.8301 (0.8297) time: 0.1452 data: 0.0686 max mem: 9390 +Train: [31] [5100/6250] eta: 0:02:46 lr: 0.000102 grad: 0.0670 (0.0712) loss: 0.8332 (0.8297) time: 0.1448 data: 0.0663 max mem: 9390 +Train: [31] [5200/6250] eta: 0:02:32 lr: 0.000102 grad: 0.0656 (0.0712) loss: 0.8345 (0.8297) time: 0.1400 data: 0.0578 max mem: 9390 +Train: [31] [5300/6250] eta: 0:02:17 lr: 0.000102 grad: 0.0647 (0.0713) loss: 0.8334 (0.8297) time: 0.1655 data: 0.0875 max mem: 9390 +Train: [31] [5400/6250] eta: 0:02:02 lr: 0.000102 grad: 0.0692 (0.0713) loss: 0.8272 (0.8296) time: 0.1221 data: 0.0428 max mem: 9390 +Train: [31] [5500/6250] eta: 0:01:48 lr: 0.000102 grad: 0.0652 (0.0713) loss: 0.8321 (0.8296) time: 0.1510 data: 0.0639 max mem: 9390 +Train: [31] [5600/6250] eta: 0:01:34 lr: 0.000102 grad: 0.0689 (0.0714) loss: 0.8251 (0.8296) time: 0.1327 data: 0.0576 max mem: 9390 +Train: [31] [5700/6250] eta: 0:01:19 lr: 0.000102 grad: 0.0733 (0.0714) loss: 0.8256 (0.8295) time: 0.1402 data: 0.0615 max mem: 9390 +Train: [31] [5800/6250] eta: 0:01:05 lr: 0.000102 grad: 0.0666 (0.0714) loss: 0.8313 (0.8295) time: 0.1277 data: 0.0431 max mem: 9390 +Train: [31] [5900/6250] eta: 0:00:50 lr: 0.000102 grad: 0.0668 (0.0714) loss: 0.8311 (0.8295) time: 0.1621 data: 0.0859 max mem: 9390 +Train: [31] [6000/6250] eta: 0:00:36 lr: 0.000102 grad: 0.0693 (0.0714) loss: 0.8342 (0.8294) time: 0.1513 data: 0.0734 max mem: 9390 +Train: [31] [6100/6250] eta: 0:00:21 lr: 0.000102 grad: 0.0716 (0.0715) loss: 0.8262 (0.8294) time: 0.1309 data: 0.0514 max mem: 9390 +Train: [31] [6200/6250] eta: 0:00:07 lr: 0.000102 grad: 0.0702 (0.0716) loss: 0.8300 (0.8294) time: 0.1649 data: 0.0826 max mem: 9390 +Train: [31] [6249/6250] eta: 0:00:00 lr: 0.000102 grad: 0.0703 (0.0716) loss: 0.8319 (0.8294) time: 0.2014 data: 0.1137 max mem: 9390 +Train: [31] Total time: 0:15:09 (0.1456 s / it) +Averaged stats: lr: 0.000102 grad: 0.0703 (0.0716) loss: 0.8319 (0.8294) +Eval (hcp-train-subset): [31] [ 0/62] eta: 0:03:32 loss: 0.8539 (0.8539) time: 3.4352 data: 3.3480 max mem: 9390 +Eval (hcp-train-subset): [31] [61/62] eta: 0:00:00 loss: 0.8429 (0.8422) time: 0.1150 data: 0.0867 max mem: 9390 +Eval (hcp-train-subset): [31] Total time: 0:00:13 (0.2105 s / it) +Averaged stats (hcp-train-subset): loss: 0.8429 (0.8422) +Eval (hcp-val): [31] [ 0/62] eta: 0:04:09 loss: 0.8359 (0.8359) time: 4.0241 data: 3.9951 max mem: 9390 +Eval (hcp-val): [31] [61/62] eta: 0:00:00 loss: 0.8366 (0.8385) time: 0.1402 data: 0.1137 max mem: 9390 +Eval (hcp-val): [31] Total time: 0:00:12 (0.2038 s / it) +Averaged stats (hcp-val): loss: 0.8366 (0.8385) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +Train: [32] [ 0/6250] eta: 7:11:28 lr: 0.000102 grad: 0.0557 (0.0557) loss: 0.8537 (0.8537) time: 4.1421 data: 3.9550 max mem: 9390 +Train: [32] [ 100/6250] eta: 0:19:34 lr: 0.000102 grad: 0.0696 (0.0769) loss: 0.8411 (0.8449) time: 0.1488 data: 0.0627 max mem: 9390 +Train: [32] [ 200/6250] eta: 0:16:49 lr: 0.000102 grad: 0.0710 (0.0743) loss: 0.8255 (0.8378) time: 0.1435 data: 0.0522 max mem: 9390 +Train: [32] [ 300/6250] eta: 0:15:46 lr: 0.000102 grad: 0.0655 (0.0724) loss: 0.8308 (0.8357) time: 0.1252 data: 0.0464 max mem: 9390 +Train: [32] [ 400/6250] eta: 0:15:07 lr: 0.000102 grad: 0.0666 (0.0715) loss: 0.8278 (0.8344) time: 0.1520 data: 0.0647 max mem: 9390 +Train: [32] [ 500/6250] eta: 0:14:28 lr: 0.000102 grad: 0.0672 (0.0710) loss: 0.8376 (0.8342) time: 0.1420 data: 0.0535 max mem: 9390 +Train: [32] [ 600/6250] eta: 0:13:54 lr: 0.000102 grad: 0.0683 (0.0704) loss: 0.8316 (0.8340) time: 0.1172 data: 0.0262 max mem: 9390 +Train: [32] [ 700/6250] eta: 0:13:24 lr: 0.000102 grad: 0.0680 (0.0702) loss: 0.8271 (0.8337) time: 0.1175 data: 0.0371 max mem: 9390 +Train: [32] [ 800/6250] eta: 0:13:06 lr: 0.000101 grad: 0.0681 (0.0702) loss: 0.8304 (0.8336) time: 0.1292 data: 0.0525 max mem: 9390 +Train: [32] [ 900/6250] eta: 0:12:52 lr: 0.000101 grad: 0.0673 (0.0700) loss: 0.8350 (0.8336) time: 0.1464 data: 0.0686 max mem: 9390 +Train: [32] [1000/6250] eta: 0:12:37 lr: 0.000101 grad: 0.0636 (0.0698) loss: 0.8382 (0.8338) time: 0.1462 data: 0.0653 max mem: 9390 +Train: [32] [1100/6250] eta: 0:12:27 lr: 0.000101 grad: 0.0636 (0.0697) loss: 0.8366 (0.8338) time: 0.1285 data: 0.0503 max mem: 9390 +Train: [32] [1200/6250] eta: 0:12:13 lr: 0.000101 grad: 0.0681 (0.0696) loss: 0.8312 (0.8336) time: 0.1526 data: 0.0746 max mem: 9390 +Train: [32] [1300/6250] eta: 0:11:56 lr: 0.000101 grad: 0.0666 (0.0697) loss: 0.8304 (0.8333) time: 0.1496 data: 0.0716 max mem: 9390 +Train: [32] [1400/6250] eta: 0:11:41 lr: 0.000101 grad: 0.0688 (0.0699) loss: 0.8325 (0.8332) time: 0.1326 data: 0.0506 max mem: 9390 +Train: [32] [1500/6250] eta: 0:11:30 lr: 0.000101 grad: 0.0688 (0.0700) loss: 0.8322 (0.8331) time: 0.1718 data: 0.0851 max mem: 9390 +Train: [32] [1600/6250] eta: 0:11:14 lr: 0.000101 grad: 0.0674 (0.0702) loss: 0.8304 (0.8328) time: 0.1372 data: 0.0568 max mem: 9390 +Train: [32] [1700/6250] eta: 0:10:57 lr: 0.000101 grad: 0.0673 (0.0703) loss: 0.8286 (0.8326) time: 0.1215 data: 0.0443 max mem: 9390 +Train: [32] [1800/6250] eta: 0:10:41 lr: 0.000101 grad: 0.0696 (0.0704) loss: 0.8327 (0.8325) time: 0.1385 data: 0.0609 max mem: 9390 +Train: [32] [1900/6250] eta: 0:10:25 lr: 0.000101 grad: 0.0694 (0.0705) loss: 0.8310 (0.8323) time: 0.1238 data: 0.0453 max mem: 9390 +Train: [32] [2000/6250] eta: 0:10:10 lr: 0.000101 grad: 0.0682 (0.0708) loss: 0.8292 (0.8321) time: 0.1581 data: 0.0825 max mem: 9390 +Train: [32] [2100/6250] eta: 0:09:54 lr: 0.000101 grad: 0.0752 (0.0710) loss: 0.8320 (0.8319) time: 0.1457 data: 0.0650 max mem: 9390 +Train: [32] [2200/6250] eta: 0:09:38 lr: 0.000101 grad: 0.0736 (0.0712) loss: 0.8283 (0.8317) time: 0.1306 data: 0.0494 max mem: 9390 +Train: [32] [2300/6250] eta: 0:09:22 lr: 0.000101 grad: 0.0696 (0.0712) loss: 0.8286 (0.8316) time: 0.1272 data: 0.0512 max mem: 9390 +Train: [32] [2400/6250] eta: 0:09:09 lr: 0.000101 grad: 0.0697 (0.0714) loss: 0.8278 (0.8314) time: 0.1784 data: 0.0940 max mem: 9390 +Train: [32] [2500/6250] eta: 0:08:53 lr: 0.000101 grad: 0.0724 (0.0715) loss: 0.8285 (0.8312) time: 0.1343 data: 0.0524 max mem: 9390 +Train: [32] [2600/6250] eta: 0:08:40 lr: 0.000101 grad: 0.0707 (0.0717) loss: 0.8291 (0.8310) time: 0.1595 data: 0.0823 max mem: 9390 +Train: [32] [2700/6250] eta: 0:08:24 lr: 0.000101 grad: 0.0665 (0.0717) loss: 0.8348 (0.8309) time: 0.1001 data: 0.0111 max mem: 9390 +Train: [32] [2800/6250] eta: 0:08:09 lr: 0.000101 grad: 0.0736 (0.0719) loss: 0.8281 (0.8308) time: 0.1771 data: 0.1003 max mem: 9390 +Train: [32] [2900/6250] eta: 0:07:53 lr: 0.000101 grad: 0.0703 (0.0719) loss: 0.8263 (0.8307) time: 0.1355 data: 0.0470 max mem: 9390 +Train: [32] [3000/6250] eta: 0:07:39 lr: 0.000101 grad: 0.0742 (0.0722) loss: 0.8259 (0.8305) time: 0.1251 data: 0.0502 max mem: 9390 +Train: [32] [3100/6250] eta: 0:07:25 lr: 0.000101 grad: 0.0750 (0.0723) loss: 0.8297 (0.8303) time: 0.1653 data: 0.0848 max mem: 9390 +Train: [32] [3200/6250] eta: 0:07:11 lr: 0.000101 grad: 0.0751 (0.0724) loss: 0.8266 (0.8302) time: 0.1257 data: 0.0437 max mem: 9390 +Train: [32] [3300/6250] eta: 0:06:59 lr: 0.000101 grad: 0.0740 (0.0725) loss: 0.8262 (0.8300) time: 0.2280 data: 0.1483 max mem: 9390 +Train: [32] [3400/6250] eta: 0:06:44 lr: 0.000101 grad: 0.0703 (0.0725) loss: 0.8281 (0.8299) time: 0.1458 data: 0.0654 max mem: 9390 +Train: [32] [3500/6250] eta: 0:06:31 lr: 0.000101 grad: 0.0731 (0.0726) loss: 0.8239 (0.8298) time: 0.1536 data: 0.0732 max mem: 9390 +Train: [32] [3600/6250] eta: 0:06:17 lr: 0.000101 grad: 0.0715 (0.0727) loss: 0.8235 (0.8296) time: 0.1491 data: 0.0683 max mem: 9390 +Train: [32] [3700/6250] eta: 0:06:02 lr: 0.000101 grad: 0.0695 (0.0727) loss: 0.8255 (0.8294) time: 0.1407 data: 0.0623 max mem: 9390 +Train: [32] [3800/6250] eta: 0:05:48 lr: 0.000101 grad: 0.0736 (0.0728) loss: 0.8278 (0.8294) time: 0.1360 data: 0.0575 max mem: 9390 +Train: [32] [3900/6250] eta: 0:05:34 lr: 0.000101 grad: 0.0691 (0.0728) loss: 0.8334 (0.8293) time: 0.1258 data: 0.0502 max mem: 9390 +Train: [32] [4000/6250] eta: 0:05:19 lr: 0.000101 grad: 0.0747 (0.0728) loss: 0.8296 (0.8293) time: 0.1293 data: 0.0493 max mem: 9390 +Train: [32] [4100/6250] eta: 0:05:04 lr: 0.000101 grad: 0.0758 (0.0729) loss: 0.8293 (0.8293) time: 0.1351 data: 0.0528 max mem: 9390 +Train: [32] [4200/6250] eta: 0:04:50 lr: 0.000101 grad: 0.0755 (0.0729) loss: 0.8304 (0.8293) time: 0.0846 data: 0.0002 max mem: 9390 +Train: [32] [4300/6250] eta: 0:04:36 lr: 0.000101 grad: 0.0694 (0.0729) loss: 0.8310 (0.8292) time: 0.1378 data: 0.0647 max mem: 9390 +Train: [32] [4400/6250] eta: 0:04:22 lr: 0.000101 grad: 0.0680 (0.0730) loss: 0.8279 (0.8292) time: 0.1414 data: 0.0553 max mem: 9390 +Train: [32] [4500/6250] eta: 0:04:08 lr: 0.000101 grad: 0.0719 (0.0730) loss: 0.8283 (0.8292) time: 0.1360 data: 0.0515 max mem: 9390 +Train: [32] [4600/6250] eta: 0:03:54 lr: 0.000101 grad: 0.0722 (0.0730) loss: 0.8289 (0.8291) time: 0.1617 data: 0.0842 max mem: 9390 +Train: [32] [4700/6250] eta: 0:03:40 lr: 0.000100 grad: 0.0758 (0.0730) loss: 0.8269 (0.8291) time: 0.1631 data: 0.0861 max mem: 9390 +Train: [32] [4800/6250] eta: 0:03:26 lr: 0.000100 grad: 0.0688 (0.0730) loss: 0.8277 (0.8290) time: 0.1746 data: 0.0862 max mem: 9390 +Train: [32] [4900/6250] eta: 0:03:12 lr: 0.000100 grad: 0.0709 (0.0731) loss: 0.8267 (0.8290) time: 0.1457 data: 0.0637 max mem: 9390 +Train: [32] [5000/6250] eta: 0:02:58 lr: 0.000100 grad: 0.0686 (0.0731) loss: 0.8314 (0.8290) time: 0.1123 data: 0.0380 max mem: 9390 +Train: [32] [5100/6250] eta: 0:02:44 lr: 0.000100 grad: 0.0704 (0.0731) loss: 0.8254 (0.8290) time: 0.1323 data: 0.0530 max mem: 9390 +Train: [32] [5200/6250] eta: 0:02:29 lr: 0.000100 grad: 0.0744 (0.0731) loss: 0.8285 (0.8290) time: 0.1389 data: 0.0494 max mem: 9390 +Train: [32] [5300/6250] eta: 0:02:15 lr: 0.000100 grad: 0.0710 (0.0732) loss: 0.8298 (0.8290) time: 0.1535 data: 0.0754 max mem: 9390 +Train: [32] [5400/6250] eta: 0:02:01 lr: 0.000100 grad: 0.0738 (0.0732) loss: 0.8312 (0.8290) time: 0.1281 data: 0.0464 max mem: 9390 +Train: [32] [5500/6250] eta: 0:01:46 lr: 0.000100 grad: 0.0704 (0.0732) loss: 0.8267 (0.8291) time: 0.1415 data: 0.0527 max mem: 9390 +Train: [32] [5600/6250] eta: 0:01:32 lr: 0.000100 grad: 0.0704 (0.0732) loss: 0.8302 (0.8291) time: 0.1505 data: 0.0728 max mem: 9390 +Train: [32] [5700/6250] eta: 0:01:18 lr: 0.000100 grad: 0.0695 (0.0733) loss: 0.8335 (0.8291) time: 0.1095 data: 0.0274 max mem: 9390 +Train: [32] [5800/6250] eta: 0:01:04 lr: 0.000100 grad: 0.0710 (0.0733) loss: 0.8334 (0.8291) time: 0.1473 data: 0.0684 max mem: 9390 +Train: [32] [5900/6250] eta: 0:00:49 lr: 0.000100 grad: 0.0703 (0.0733) loss: 0.8353 (0.8292) time: 0.1378 data: 0.0582 max mem: 9390 +Train: [32] [6000/6250] eta: 0:00:35 lr: 0.000100 grad: 0.0787 (0.0734) loss: 0.8269 (0.8292) time: 0.1616 data: 0.0793 max mem: 9390 +Train: [32] [6100/6250] eta: 0:00:21 lr: 0.000100 grad: 0.0677 (0.0734) loss: 0.8290 (0.8292) time: 0.1391 data: 0.0613 max mem: 9390 +Train: [32] [6200/6250] eta: 0:00:07 lr: 0.000100 grad: 0.0695 (0.0734) loss: 0.8214 (0.8292) time: 0.1440 data: 0.0676 max mem: 9390 +Train: [32] [6249/6250] eta: 0:00:00 lr: 0.000100 grad: 0.0727 (0.0734) loss: 0.8195 (0.8291) time: 0.1516 data: 0.0625 max mem: 9390 +Train: [32] Total time: 0:15:00 (0.1441 s / it) +Averaged stats: lr: 0.000100 grad: 0.0727 (0.0734) loss: 0.8195 (0.8291) +Eval (hcp-train-subset): [32] [ 0/62] eta: 0:03:01 loss: 0.8518 (0.8518) time: 2.9229 data: 2.8737 max mem: 9390 +Eval (hcp-train-subset): [32] [61/62] eta: 0:00:00 loss: 0.8410 (0.8416) time: 0.1227 data: 0.0974 max mem: 9390 +Eval (hcp-train-subset): [32] Total time: 0:00:12 (0.2082 s / it) +Averaged stats (hcp-train-subset): loss: 0.8410 (0.8416) +Eval (hcp-val): [32] [ 0/62] eta: 0:05:29 loss: 0.8334 (0.8334) time: 5.3193 data: 5.2897 max mem: 9390 +Eval (hcp-val): [32] [61/62] eta: 0:00:00 loss: 0.8362 (0.8383) time: 0.1489 data: 0.1243 max mem: 9390 +Eval (hcp-val): [32] Total time: 0:00:13 (0.2135 s / it) +Averaged stats (hcp-val): loss: 0.8362 (0.8383) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +Train: [33] [ 0/6250] eta: 9:39:33 lr: 0.000100 grad: 0.0756 (0.0756) loss: 0.8723 (0.8723) time: 5.5637 data: 5.4444 max mem: 9390 +Train: [33] [ 100/6250] eta: 0:20:54 lr: 0.000100 grad: 0.0769 (0.0815) loss: 0.8318 (0.8405) time: 0.1657 data: 0.0792 max mem: 9390 +Train: [33] [ 200/6250] eta: 0:17:38 lr: 0.000100 grad: 0.0711 (0.0805) loss: 0.8273 (0.8346) time: 0.1601 data: 0.0706 max mem: 9390 +Train: [33] [ 300/6250] eta: 0:16:18 lr: 0.000100 grad: 0.0694 (0.0782) loss: 0.8335 (0.8324) time: 0.1300 data: 0.0480 max mem: 9390 +Train: [33] [ 400/6250] eta: 0:15:16 lr: 0.000100 grad: 0.0684 (0.0773) loss: 0.8242 (0.8314) time: 0.1159 data: 0.0319 max mem: 9390 +Train: [33] [ 500/6250] eta: 0:14:33 lr: 0.000100 grad: 0.0708 (0.0759) loss: 0.8249 (0.8309) time: 0.1324 data: 0.0432 max mem: 9390 +Train: [33] [ 600/6250] eta: 0:13:59 lr: 0.000100 grad: 0.0706 (0.0745) loss: 0.8324 (0.8311) time: 0.1082 data: 0.0254 max mem: 9390 +Train: [33] [ 700/6250] eta: 0:13:34 lr: 0.000100 grad: 0.0653 (0.0738) loss: 0.8331 (0.8314) time: 0.1280 data: 0.0479 max mem: 9390 +Train: [33] [ 800/6250] eta: 0:13:14 lr: 0.000100 grad: 0.0663 (0.0733) loss: 0.8272 (0.8312) time: 0.1539 data: 0.0693 max mem: 9390 +Train: [33] [ 900/6250] eta: 0:13:08 lr: 0.000100 grad: 0.0670 (0.0727) loss: 0.8319 (0.8311) time: 0.1320 data: 0.0548 max mem: 9390 +Train: [33] [1000/6250] eta: 0:12:52 lr: 0.000100 grad: 0.0657 (0.0725) loss: 0.8264 (0.8310) time: 0.1333 data: 0.0477 max mem: 9390 +Train: [33] [1100/6250] eta: 0:12:31 lr: 0.000100 grad: 0.0667 (0.0721) loss: 0.8270 (0.8309) time: 0.1417 data: 0.0635 max mem: 9390 +Train: [33] [1200/6250] eta: 0:12:13 lr: 0.000100 grad: 0.0686 (0.0719) loss: 0.8258 (0.8309) time: 0.1334 data: 0.0486 max mem: 9390 +Train: [33] [1300/6250] eta: 0:11:56 lr: 0.000100 grad: 0.0663 (0.0718) loss: 0.8257 (0.8307) time: 0.1471 data: 0.0704 max mem: 9390 +Train: [33] [1400/6250] eta: 0:11:38 lr: 0.000100 grad: 0.0698 (0.0718) loss: 0.8295 (0.8306) time: 0.1392 data: 0.0568 max mem: 9390 +Train: [33] [1500/6250] eta: 0:11:21 lr: 0.000100 grad: 0.0670 (0.0718) loss: 0.8299 (0.8306) time: 0.1348 data: 0.0532 max mem: 9390 +Train: [33] [1600/6250] eta: 0:11:04 lr: 0.000100 grad: 0.0676 (0.0718) loss: 0.8291 (0.8305) time: 0.1351 data: 0.0564 max mem: 9390 +Train: [33] [1700/6250] eta: 0:10:47 lr: 0.000100 grad: 0.0715 (0.0717) loss: 0.8282 (0.8304) time: 0.1292 data: 0.0514 max mem: 9390 +Train: [33] [1800/6250] eta: 0:10:30 lr: 0.000100 grad: 0.0699 (0.0717) loss: 0.8273 (0.8303) time: 0.1256 data: 0.0463 max mem: 9390 +Train: [33] [1900/6250] eta: 0:10:14 lr: 0.000100 grad: 0.0677 (0.0716) loss: 0.8237 (0.8301) time: 0.1217 data: 0.0403 max mem: 9390 +Train: [33] [2000/6250] eta: 0:10:01 lr: 0.000100 grad: 0.0690 (0.0716) loss: 0.8316 (0.8300) time: 0.1466 data: 0.0682 max mem: 9390 +Train: [33] [2100/6250] eta: 0:09:44 lr: 0.000100 grad: 0.0767 (0.0718) loss: 0.8208 (0.8299) time: 0.1404 data: 0.0577 max mem: 9390 +Train: [33] [2200/6250] eta: 0:09:29 lr: 0.000099 grad: 0.0721 (0.0719) loss: 0.8283 (0.8297) time: 0.1363 data: 0.0541 max mem: 9390 +Train: [33] [2300/6250] eta: 0:09:15 lr: 0.000099 grad: 0.0692 (0.0721) loss: 0.8316 (0.8294) time: 0.1566 data: 0.0798 max mem: 9390 +Train: [33] [2400/6250] eta: 0:09:00 lr: 0.000099 grad: 0.0718 (0.0723) loss: 0.8308 (0.8292) time: 0.1423 data: 0.0657 max mem: 9390 +Train: [33] [2500/6250] eta: 0:08:44 lr: 0.000099 grad: 0.0768 (0.0724) loss: 0.8233 (0.8290) time: 0.1272 data: 0.0469 max mem: 9390 +Train: [33] [2600/6250] eta: 0:08:30 lr: 0.000099 grad: 0.0669 (0.0725) loss: 0.8313 (0.8289) time: 0.1344 data: 0.0531 max mem: 9390 +Train: [33] [2700/6250] eta: 0:08:17 lr: 0.000099 grad: 0.0732 (0.0725) loss: 0.8257 (0.8289) time: 0.1289 data: 0.0497 max mem: 9390 +Train: [33] [2800/6250] eta: 0:08:03 lr: 0.000099 grad: 0.0740 (0.0726) loss: 0.8240 (0.8288) time: 0.1247 data: 0.0531 max mem: 9390 +Train: [33] [2900/6250] eta: 0:07:49 lr: 0.000099 grad: 0.0748 (0.0730) loss: 0.8303 (0.8287) time: 0.1412 data: 0.0631 max mem: 9390 +Train: [33] [3000/6250] eta: 0:07:34 lr: 0.000099 grad: 0.0707 (0.0731) loss: 0.8228 (0.8286) time: 0.1301 data: 0.0483 max mem: 9390 +Train: [33] [3100/6250] eta: 0:07:21 lr: 0.000099 grad: 0.0724 (0.0732) loss: 0.8259 (0.8285) time: 0.1159 data: 0.0351 max mem: 9390 +Train: [33] [3200/6250] eta: 0:07:07 lr: 0.000099 grad: 0.0735 (0.0733) loss: 0.8272 (0.8284) time: 0.1357 data: 0.0594 max mem: 9390 +Train: [33] [3300/6250] eta: 0:06:54 lr: 0.000099 grad: 0.0755 (0.0734) loss: 0.8273 (0.8284) time: 0.1449 data: 0.0625 max mem: 9390 +Train: [33] [3400/6250] eta: 0:06:39 lr: 0.000099 grad: 0.0700 (0.0734) loss: 0.8268 (0.8284) time: 0.1520 data: 0.0774 max mem: 9390 +Train: [33] [3500/6250] eta: 0:06:26 lr: 0.000099 grad: 0.0726 (0.0734) loss: 0.8310 (0.8283) time: 0.1318 data: 0.0440 max mem: 9390 +Train: [33] [3600/6250] eta: 0:06:12 lr: 0.000099 grad: 0.0688 (0.0734) loss: 0.8313 (0.8283) time: 0.1341 data: 0.0496 max mem: 9390 +Train: [33] [3700/6250] eta: 0:05:58 lr: 0.000099 grad: 0.0740 (0.0734) loss: 0.8247 (0.8283) time: 0.1559 data: 0.0748 max mem: 9390 +Train: [33] [3800/6250] eta: 0:05:44 lr: 0.000099 grad: 0.0731 (0.0734) loss: 0.8286 (0.8283) time: 0.1354 data: 0.0594 max mem: 9390 +Train: [33] [3900/6250] eta: 0:05:31 lr: 0.000099 grad: 0.0744 (0.0735) loss: 0.8212 (0.8282) time: 0.1352 data: 0.0513 max mem: 9390 +Train: [33] [4000/6250] eta: 0:05:17 lr: 0.000099 grad: 0.0720 (0.0736) loss: 0.8285 (0.8282) time: 0.1366 data: 0.0579 max mem: 9390 +Train: [33] [4100/6250] eta: 0:05:03 lr: 0.000099 grad: 0.0751 (0.0737) loss: 0.8258 (0.8282) time: 0.1423 data: 0.0644 max mem: 9390 +Train: [33] [4200/6250] eta: 0:04:49 lr: 0.000099 grad: 0.0713 (0.0738) loss: 0.8269 (0.8282) time: 0.1417 data: 0.0621 max mem: 9390 +Train: [33] [4300/6250] eta: 0:04:34 lr: 0.000099 grad: 0.0793 (0.0738) loss: 0.8249 (0.8281) time: 0.1359 data: 0.0560 max mem: 9390 +Train: [33] [4400/6250] eta: 0:04:20 lr: 0.000099 grad: 0.0747 (0.0739) loss: 0.8234 (0.8281) time: 0.1348 data: 0.0534 max mem: 9390 +Train: [33] [4500/6250] eta: 0:04:07 lr: 0.000099 grad: 0.0754 (0.0739) loss: 0.8296 (0.8281) time: 0.1833 data: 0.0998 max mem: 9390 +Train: [33] [4600/6250] eta: 0:03:53 lr: 0.000099 grad: 0.0718 (0.0739) loss: 0.8290 (0.8282) time: 0.1414 data: 0.0640 max mem: 9390 +Train: [33] [4700/6250] eta: 0:03:39 lr: 0.000099 grad: 0.0708 (0.0740) loss: 0.8341 (0.8282) time: 0.1626 data: 0.0742 max mem: 9390 +Train: [33] [4800/6250] eta: 0:03:25 lr: 0.000099 grad: 0.0721 (0.0741) loss: 0.8303 (0.8282) time: 0.1248 data: 0.0457 max mem: 9390 +Train: [33] [4900/6250] eta: 0:03:11 lr: 0.000099 grad: 0.0727 (0.0741) loss: 0.8297 (0.8282) time: 0.1522 data: 0.0757 max mem: 9390 +Train: [33] [5000/6250] eta: 0:02:57 lr: 0.000099 grad: 0.0703 (0.0741) loss: 0.8274 (0.8282) time: 0.1323 data: 0.0477 max mem: 9390 +Train: [33] [5100/6250] eta: 0:02:42 lr: 0.000099 grad: 0.0723 (0.0741) loss: 0.8312 (0.8283) time: 0.1431 data: 0.0635 max mem: 9390 +Train: [33] [5200/6250] eta: 0:02:28 lr: 0.000099 grad: 0.0729 (0.0741) loss: 0.8232 (0.8284) time: 0.1210 data: 0.0457 max mem: 9390 +Train: [33] [5300/6250] eta: 0:02:14 lr: 0.000099 grad: 0.0697 (0.0741) loss: 0.8255 (0.8284) time: 0.1568 data: 0.0668 max mem: 9390 +Train: [33] [5400/6250] eta: 0:02:00 lr: 0.000099 grad: 0.0742 (0.0741) loss: 0.8299 (0.8284) time: 0.1195 data: 0.0430 max mem: 9390 +Train: [33] [5500/6250] eta: 0:01:46 lr: 0.000099 grad: 0.0754 (0.0741) loss: 0.8296 (0.8284) time: 0.1505 data: 0.0758 max mem: 9390 +Train: [33] [5600/6250] eta: 0:01:31 lr: 0.000099 grad: 0.0742 (0.0741) loss: 0.8308 (0.8285) time: 0.1420 data: 0.0648 max mem: 9390 +Train: [33] [5700/6250] eta: 0:01:17 lr: 0.000099 grad: 0.0708 (0.0741) loss: 0.8336 (0.8285) time: 0.1590 data: 0.0834 max mem: 9390 +Train: [33] [5800/6250] eta: 0:01:03 lr: 0.000099 grad: 0.0767 (0.0741) loss: 0.8298 (0.8286) time: 0.1608 data: 0.0812 max mem: 9390 +Train: [33] [5900/6250] eta: 0:00:49 lr: 0.000098 grad: 0.0727 (0.0741) loss: 0.8289 (0.8286) time: 0.1766 data: 0.0867 max mem: 9390 +Train: [33] [6000/6250] eta: 0:00:35 lr: 0.000098 grad: 0.0733 (0.0741) loss: 0.8277 (0.8286) time: 0.1305 data: 0.0496 max mem: 9390 +Train: [33] [6100/6250] eta: 0:00:21 lr: 0.000098 grad: 0.0777 (0.0742) loss: 0.8310 (0.8286) time: 0.1383 data: 0.0583 max mem: 9390 +Train: [33] [6200/6250] eta: 0:00:07 lr: 0.000098 grad: 0.0696 (0.0742) loss: 0.8310 (0.8286) time: 0.1824 data: 0.0975 max mem: 9390 +Train: [33] [6249/6250] eta: 0:00:00 lr: 0.000098 grad: 0.0701 (0.0742) loss: 0.8336 (0.8287) time: 0.1531 data: 0.0629 max mem: 9390 +Train: [33] Total time: 0:14:51 (0.1426 s / it) +Averaged stats: lr: 0.000098 grad: 0.0701 (0.0742) loss: 0.8336 (0.8287) +Eval (hcp-train-subset): [33] [ 0/62] eta: 0:04:00 loss: 0.8545 (0.8545) time: 3.8846 data: 3.8066 max mem: 9390 +Eval (hcp-train-subset): [33] [61/62] eta: 0:00:00 loss: 0.8400 (0.8417) time: 0.1335 data: 0.1065 max mem: 9390 +Eval (hcp-train-subset): [33] Total time: 0:00:12 (0.2029 s / it) +Averaged stats (hcp-train-subset): loss: 0.8400 (0.8417) +Eval (hcp-val): [33] [ 0/62] eta: 0:03:35 loss: 0.8374 (0.8374) time: 3.4779 data: 3.4061 max mem: 9390 +Eval (hcp-val): [33] [61/62] eta: 0:00:00 loss: 0.8369 (0.8385) time: 0.1289 data: 0.1042 max mem: 9390 +Eval (hcp-val): [33] Total time: 0:00:12 (0.1984 s / it) +Averaged stats (hcp-val): loss: 0.8369 (0.8385) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +Train: [34] [ 0/6250] eta: 9:39:19 lr: 0.000098 grad: 0.0504 (0.0504) loss: 0.8835 (0.8835) time: 5.5614 data: 5.4633 max mem: 9390 +Train: [34] [ 100/6250] eta: 0:19:27 lr: 0.000098 grad: 0.0713 (0.0777) loss: 0.8326 (0.8408) time: 0.1266 data: 0.0233 max mem: 9390 +Train: [34] [ 200/6250] eta: 0:17:30 lr: 0.000098 grad: 0.0693 (0.0774) loss: 0.8302 (0.8328) time: 0.1599 data: 0.0729 max mem: 9390 +Train: [34] [ 300/6250] eta: 0:16:07 lr: 0.000098 grad: 0.0678 (0.0773) loss: 0.8264 (0.8307) time: 0.1420 data: 0.0525 max mem: 9390 +Train: [34] [ 400/6250] eta: 0:15:27 lr: 0.000098 grad: 0.0675 (0.0760) loss: 0.8302 (0.8303) time: 0.1604 data: 0.0761 max mem: 9390 +Train: [34] [ 500/6250] eta: 0:14:45 lr: 0.000098 grad: 0.0689 (0.0753) loss: 0.8364 (0.8305) time: 0.1442 data: 0.0450 max mem: 9390 +Train: [34] [ 600/6250] eta: 0:14:15 lr: 0.000098 grad: 0.0721 (0.0750) loss: 0.8291 (0.8304) time: 0.1386 data: 0.0467 max mem: 9390 +Train: [34] [ 700/6250] eta: 0:13:50 lr: 0.000098 grad: 0.0713 (0.0746) loss: 0.8226 (0.8304) time: 0.1579 data: 0.0797 max mem: 9390 +Train: [34] [ 800/6250] eta: 0:13:26 lr: 0.000098 grad: 0.0696 (0.0746) loss: 0.8293 (0.8306) time: 0.1440 data: 0.0629 max mem: 9390 +Train: [34] [ 900/6250] eta: 0:13:14 lr: 0.000098 grad: 0.0711 (0.0743) loss: 0.8333 (0.8306) time: 0.1497 data: 0.0636 max mem: 9390 +Train: [34] [1000/6250] eta: 0:13:00 lr: 0.000098 grad: 0.0681 (0.0738) loss: 0.8296 (0.8308) time: 0.1618 data: 0.0783 max mem: 9390 +Train: [34] [1100/6250] eta: 0:12:44 lr: 0.000098 grad: 0.0665 (0.0734) loss: 0.8313 (0.8309) time: 0.1089 data: 0.0343 max mem: 9390 +Train: [34] [1200/6250] eta: 0:12:29 lr: 0.000098 grad: 0.0688 (0.0733) loss: 0.8272 (0.8309) time: 0.1808 data: 0.1017 max mem: 9390 +Train: [34] [1300/6250] eta: 0:12:12 lr: 0.000098 grad: 0.0714 (0.0735) loss: 0.8288 (0.8308) time: 0.1614 data: 0.0877 max mem: 9390 +Train: [34] [1400/6250] eta: 0:11:54 lr: 0.000098 grad: 0.0702 (0.0734) loss: 0.8257 (0.8307) time: 0.1282 data: 0.0399 max mem: 9390 +Train: [34] [1500/6250] eta: 0:11:36 lr: 0.000098 grad: 0.0687 (0.0734) loss: 0.8185 (0.8305) time: 0.1295 data: 0.0476 max mem: 9390 +Train: [34] [1600/6250] eta: 0:11:18 lr: 0.000098 grad: 0.0686 (0.0734) loss: 0.8304 (0.8305) time: 0.1276 data: 0.0401 max mem: 9390 +Train: [34] [1700/6250] eta: 0:11:03 lr: 0.000098 grad: 0.0680 (0.0733) loss: 0.8272 (0.8305) time: 0.1476 data: 0.0665 max mem: 9390 +Train: [34] [1800/6250] eta: 0:10:44 lr: 0.000098 grad: 0.0659 (0.0734) loss: 0.8316 (0.8304) time: 0.1261 data: 0.0426 max mem: 9390 +Train: [34] [1900/6250] eta: 0:10:28 lr: 0.000098 grad: 0.0697 (0.0733) loss: 0.8244 (0.8303) time: 0.1543 data: 0.0738 max mem: 9390 +Train: [34] [2000/6250] eta: 0:10:12 lr: 0.000098 grad: 0.0680 (0.0732) loss: 0.8305 (0.8303) time: 0.0972 data: 0.0164 max mem: 9390 +Train: [34] [2100/6250] eta: 0:09:55 lr: 0.000098 grad: 0.0721 (0.0732) loss: 0.8268 (0.8302) time: 0.1246 data: 0.0363 max mem: 9390 +Train: [34] [2200/6250] eta: 0:09:41 lr: 0.000098 grad: 0.0728 (0.0731) loss: 0.8325 (0.8302) time: 0.1532 data: 0.0769 max mem: 9390 +Train: [34] [2300/6250] eta: 0:09:26 lr: 0.000098 grad: 0.0730 (0.0732) loss: 0.8234 (0.8301) time: 0.1652 data: 0.0838 max mem: 9390 +Train: [34] [2400/6250] eta: 0:09:11 lr: 0.000098 grad: 0.0716 (0.0732) loss: 0.8279 (0.8300) time: 0.1670 data: 0.0811 max mem: 9390 +Train: [34] [2500/6250] eta: 0:08:55 lr: 0.000098 grad: 0.0740 (0.0732) loss: 0.8293 (0.8300) time: 0.1230 data: 0.0424 max mem: 9390 +Train: [34] [2600/6250] eta: 0:08:39 lr: 0.000098 grad: 0.0693 (0.0732) loss: 0.8255 (0.8299) time: 0.1258 data: 0.0444 max mem: 9390 +Train: [34] [2700/6250] eta: 0:08:25 lr: 0.000098 grad: 0.0718 (0.0732) loss: 0.8293 (0.8299) time: 0.1347 data: 0.0570 max mem: 9390 +Train: [34] [2800/6250] eta: 0:08:11 lr: 0.000098 grad: 0.0683 (0.0732) loss: 0.8303 (0.8299) time: 0.1333 data: 0.0557 max mem: 9390 +Train: [34] [2900/6250] eta: 0:07:56 lr: 0.000098 grad: 0.0737 (0.0732) loss: 0.8274 (0.8298) time: 0.1466 data: 0.0665 max mem: 9390 +Train: [34] [3000/6250] eta: 0:07:42 lr: 0.000098 grad: 0.0729 (0.0733) loss: 0.8242 (0.8298) time: 0.1505 data: 0.0697 max mem: 9390 +Train: [34] [3100/6250] eta: 0:07:26 lr: 0.000098 grad: 0.0695 (0.0733) loss: 0.8285 (0.8298) time: 0.1245 data: 0.0418 max mem: 9390 +Train: [34] [3200/6250] eta: 0:07:13 lr: 0.000098 grad: 0.0733 (0.0734) loss: 0.8266 (0.8298) time: 0.1420 data: 0.0660 max mem: 9390 +Train: [34] [3300/6250] eta: 0:06:58 lr: 0.000097 grad: 0.0686 (0.0734) loss: 0.8334 (0.8298) time: 0.1465 data: 0.0694 max mem: 9390 +Train: [34] [3400/6250] eta: 0:06:44 lr: 0.000097 grad: 0.0700 (0.0734) loss: 0.8275 (0.8299) time: 0.1293 data: 0.0479 max mem: 9390 +Train: [34] [3500/6250] eta: 0:06:29 lr: 0.000097 grad: 0.0730 (0.0733) loss: 0.8310 (0.8299) time: 0.1453 data: 0.0614 max mem: 9390 +Train: [34] [3600/6250] eta: 0:06:15 lr: 0.000097 grad: 0.0720 (0.0734) loss: 0.8250 (0.8299) time: 0.1314 data: 0.0480 max mem: 9390 +Train: [34] [3700/6250] eta: 0:06:01 lr: 0.000097 grad: 0.0706 (0.0734) loss: 0.8291 (0.8298) time: 0.1495 data: 0.0748 max mem: 9390 +Train: [34] [3800/6250] eta: 0:05:46 lr: 0.000097 grad: 0.0764 (0.0735) loss: 0.8314 (0.8298) time: 0.1337 data: 0.0555 max mem: 9390 +Train: [34] [3900/6250] eta: 0:05:32 lr: 0.000097 grad: 0.0710 (0.0735) loss: 0.8273 (0.8297) time: 0.1319 data: 0.0530 max mem: 9390 +Train: [34] [4000/6250] eta: 0:05:17 lr: 0.000097 grad: 0.0766 (0.0736) loss: 0.8265 (0.8296) time: 0.1273 data: 0.0427 max mem: 9390 +Train: [34] [4100/6250] eta: 0:05:03 lr: 0.000097 grad: 0.0700 (0.0736) loss: 0.8357 (0.8296) time: 0.1517 data: 0.0767 max mem: 9390 +Train: [34] [4200/6250] eta: 0:04:49 lr: 0.000097 grad: 0.0737 (0.0738) loss: 0.8296 (0.8295) time: 0.1240 data: 0.0457 max mem: 9390 +Train: [34] [4300/6250] eta: 0:04:35 lr: 0.000097 grad: 0.0721 (0.0739) loss: 0.8291 (0.8294) time: 0.1457 data: 0.0674 max mem: 9390 +Train: [34] [4400/6250] eta: 0:04:21 lr: 0.000097 grad: 0.0722 (0.0739) loss: 0.8234 (0.8294) time: 0.1636 data: 0.0888 max mem: 9390 +Train: [34] [4500/6250] eta: 0:04:07 lr: 0.000097 grad: 0.0737 (0.0740) loss: 0.8295 (0.8294) time: 0.1350 data: 0.0530 max mem: 9390 +Train: [34] [4600/6250] eta: 0:03:54 lr: 0.000097 grad: 0.0704 (0.0740) loss: 0.8314 (0.8293) time: 0.1941 data: 0.1168 max mem: 9390 +Train: [34] [4700/6250] eta: 0:03:40 lr: 0.000097 grad: 0.0711 (0.0740) loss: 0.8279 (0.8293) time: 0.1451 data: 0.0656 max mem: 9390 +Train: [34] [4800/6250] eta: 0:03:25 lr: 0.000097 grad: 0.0700 (0.0740) loss: 0.8286 (0.8292) time: 0.1423 data: 0.0611 max mem: 9390 +Train: [34] [4900/6250] eta: 0:03:12 lr: 0.000097 grad: 0.0697 (0.0740) loss: 0.8368 (0.8292) time: 0.1392 data: 0.0585 max mem: 9390 +Train: [34] [5000/6250] eta: 0:02:57 lr: 0.000097 grad: 0.0724 (0.0739) loss: 0.8262 (0.8292) time: 0.1414 data: 0.0594 max mem: 9390 +Train: [34] [5100/6250] eta: 0:02:43 lr: 0.000097 grad: 0.0752 (0.0740) loss: 0.8276 (0.8292) time: 0.1472 data: 0.0599 max mem: 9390 +Train: [34] [5200/6250] eta: 0:02:29 lr: 0.000097 grad: 0.0710 (0.0740) loss: 0.8341 (0.8292) time: 0.1431 data: 0.0664 max mem: 9390 +Train: [34] [5300/6250] eta: 0:02:15 lr: 0.000097 grad: 0.0740 (0.0740) loss: 0.8308 (0.8291) time: 0.1282 data: 0.0490 max mem: 9390 +Train: [34] [5400/6250] eta: 0:02:01 lr: 0.000097 grad: 0.0690 (0.0740) loss: 0.8278 (0.8291) time: 0.1755 data: 0.0955 max mem: 9390 +Train: [34] [5500/6250] eta: 0:01:46 lr: 0.000097 grad: 0.0727 (0.0741) loss: 0.8258 (0.8290) time: 0.1545 data: 0.0763 max mem: 9390 +Train: [34] [5600/6250] eta: 0:01:32 lr: 0.000097 grad: 0.0727 (0.0741) loss: 0.8241 (0.8290) time: 0.1169 data: 0.0357 max mem: 9390 +Train: [34] [5700/6250] eta: 0:01:18 lr: 0.000097 grad: 0.0714 (0.0741) loss: 0.8202 (0.8289) time: 0.1892 data: 0.0977 max mem: 9390 +Train: [34] [5800/6250] eta: 0:01:04 lr: 0.000097 grad: 0.0752 (0.0741) loss: 0.8207 (0.8288) time: 0.1243 data: 0.0408 max mem: 9390 +Train: [34] [5900/6250] eta: 0:00:49 lr: 0.000097 grad: 0.0715 (0.0742) loss: 0.8261 (0.8288) time: 0.1341 data: 0.0564 max mem: 9390 +Train: [34] [6000/6250] eta: 0:00:35 lr: 0.000097 grad: 0.0764 (0.0742) loss: 0.8271 (0.8287) time: 0.1205 data: 0.0338 max mem: 9390 +Train: [34] [6100/6250] eta: 0:00:21 lr: 0.000097 grad: 0.0786 (0.0743) loss: 0.8268 (0.8287) time: 0.1231 data: 0.0431 max mem: 9390 +Train: [34] [6200/6250] eta: 0:00:07 lr: 0.000097 grad: 0.0822 (0.0743) loss: 0.8237 (0.8286) time: 0.1711 data: 0.0882 max mem: 9390 +Train: [34] [6249/6250] eta: 0:00:00 lr: 0.000097 grad: 0.0701 (0.0743) loss: 0.8266 (0.8286) time: 0.1680 data: 0.0865 max mem: 9390 +Train: [34] Total time: 0:14:54 (0.1431 s / it) +Averaged stats: lr: 0.000097 grad: 0.0701 (0.0743) loss: 0.8266 (0.8286) +Eval (hcp-train-subset): [34] [ 0/62] eta: 0:03:51 loss: 0.8511 (0.8511) time: 3.7295 data: 3.6303 max mem: 9390 +Eval (hcp-train-subset): [34] [61/62] eta: 0:00:00 loss: 0.8415 (0.8415) time: 0.1390 data: 0.1122 max mem: 9390 +Eval (hcp-train-subset): [34] Total time: 0:00:13 (0.2106 s / it) +Averaged stats (hcp-train-subset): loss: 0.8415 (0.8415) +Making plots (hcp-train-subset): example=56 +Eval (hcp-val): [34] [ 0/62] eta: 0:04:05 loss: 0.8353 (0.8353) time: 3.9530 data: 3.9061 max mem: 9390 +Eval (hcp-val): [34] [61/62] eta: 0:00:00 loss: 0.8381 (0.8378) time: 0.1202 data: 0.0957 max mem: 9390 +Eval (hcp-val): [34] Total time: 0:00:11 (0.1928 s / it) +Averaged stats (hcp-val): loss: 0.8381 (0.8378) +Making plots (hcp-val): example=35 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +Train: [35] [ 0/6250] eta: 8:04:45 lr: 0.000097 grad: 0.0725 (0.0725) loss: 0.8763 (0.8763) time: 4.6536 data: 4.4095 max mem: 9390 +Train: [35] [ 100/6250] eta: 0:19:50 lr: 0.000097 grad: 0.0769 (0.0795) loss: 0.8263 (0.8356) time: 0.1710 data: 0.0850 max mem: 9390 +Train: [35] [ 200/6250] eta: 0:17:45 lr: 0.000097 grad: 0.0784 (0.0803) loss: 0.8222 (0.8314) time: 0.1760 data: 0.0892 max mem: 9390 +Train: [35] [ 300/6250] eta: 0:16:21 lr: 0.000097 grad: 0.0777 (0.0791) loss: 0.8264 (0.8290) time: 0.1288 data: 0.0465 max mem: 9390 +Train: [35] [ 400/6250] eta: 0:15:35 lr: 0.000097 grad: 0.0719 (0.0783) loss: 0.8267 (0.8284) time: 0.1584 data: 0.0667 max mem: 9390 +Train: [35] [ 500/6250] eta: 0:14:54 lr: 0.000097 grad: 0.0723 (0.0773) loss: 0.8333 (0.8281) time: 0.1484 data: 0.0632 max mem: 9390 +Train: [35] [ 600/6250] eta: 0:14:21 lr: 0.000097 grad: 0.0763 (0.0769) loss: 0.8318 (0.8276) time: 0.1366 data: 0.0529 max mem: 9390 +Train: [35] [ 700/6250] eta: 0:13:50 lr: 0.000096 grad: 0.0721 (0.0767) loss: 0.8282 (0.8273) time: 0.1349 data: 0.0549 max mem: 9390 +Train: [35] [ 800/6250] eta: 0:13:25 lr: 0.000096 grad: 0.0778 (0.0764) loss: 0.8180 (0.8270) time: 0.1421 data: 0.0657 max mem: 9390 +Train: [35] [ 900/6250] eta: 0:13:12 lr: 0.000096 grad: 0.0711 (0.0762) loss: 0.8261 (0.8266) time: 0.1530 data: 0.0715 max mem: 9390 +Train: [35] [1000/6250] eta: 0:12:52 lr: 0.000096 grad: 0.0700 (0.0762) loss: 0.8228 (0.8264) time: 0.1280 data: 0.0443 max mem: 9390 +Train: [35] [1100/6250] eta: 0:12:38 lr: 0.000096 grad: 0.0699 (0.0760) loss: 0.8290 (0.8263) time: 0.1618 data: 0.0816 max mem: 9390 +Train: [35] [1200/6250] eta: 0:12:21 lr: 0.000096 grad: 0.0710 (0.0758) loss: 0.8270 (0.8260) time: 0.1454 data: 0.0656 max mem: 9390 +Train: [35] [1300/6250] eta: 0:12:06 lr: 0.000096 grad: 0.0785 (0.0758) loss: 0.8311 (0.8257) time: 0.1405 data: 0.0623 max mem: 9390 +Train: [35] [1400/6250] eta: 0:11:50 lr: 0.000096 grad: 0.0709 (0.0758) loss: 0.8256 (0.8254) time: 0.1280 data: 0.0500 max mem: 9390 +Train: [35] [1500/6250] eta: 0:11:31 lr: 0.000096 grad: 0.0722 (0.0759) loss: 0.8242 (0.8253) time: 0.1382 data: 0.0572 max mem: 9390 +Train: [35] [1600/6250] eta: 0:11:16 lr: 0.000096 grad: 0.0734 (0.0760) loss: 0.8246 (0.8251) time: 0.1400 data: 0.0612 max mem: 9390 +Train: [35] [1700/6250] eta: 0:11:02 lr: 0.000096 grad: 0.0686 (0.0760) loss: 0.8285 (0.8250) time: 0.1478 data: 0.0708 max mem: 9390 +Train: [35] [1800/6250] eta: 0:10:44 lr: 0.000096 grad: 0.0738 (0.0761) loss: 0.8243 (0.8249) time: 0.1263 data: 0.0403 max mem: 9390 +Train: [35] [1900/6250] eta: 0:10:30 lr: 0.000096 grad: 0.0730 (0.0761) loss: 0.8258 (0.8248) time: 0.1482 data: 0.0737 max mem: 9390 +Train: [35] [2000/6250] eta: 0:10:13 lr: 0.000096 grad: 0.0735 (0.0762) loss: 0.8247 (0.8247) time: 0.1345 data: 0.0548 max mem: 9390 +Train: [35] [2100/6250] eta: 0:09:58 lr: 0.000096 grad: 0.0796 (0.0762) loss: 0.8244 (0.8246) time: 0.1342 data: 0.0550 max mem: 9390 +Train: [35] [2200/6250] eta: 0:09:41 lr: 0.000096 grad: 0.0755 (0.0763) loss: 0.8223 (0.8245) time: 0.1385 data: 0.0601 max mem: 9390 +Train: [35] [2300/6250] eta: 0:09:26 lr: 0.000096 grad: 0.0747 (0.0763) loss: 0.8257 (0.8245) time: 0.1673 data: 0.0882 max mem: 9390 +Train: [35] [2400/6250] eta: 0:09:09 lr: 0.000096 grad: 0.0728 (0.0764) loss: 0.8215 (0.8244) time: 0.1344 data: 0.0521 max mem: 9390 +Train: [35] [2500/6250] eta: 0:08:54 lr: 0.000096 grad: 0.0742 (0.0764) loss: 0.8256 (0.8244) time: 0.1298 data: 0.0533 max mem: 9390 +Train: [35] [2600/6250] eta: 0:08:40 lr: 0.000096 grad: 0.0726 (0.0764) loss: 0.8261 (0.8243) time: 0.2023 data: 0.1196 max mem: 9390 +Train: [35] [2700/6250] eta: 0:08:27 lr: 0.000096 grad: 0.0699 (0.0764) loss: 0.8254 (0.8244) time: 0.1337 data: 0.0605 max mem: 9390 +Train: [35] [2800/6250] eta: 0:08:12 lr: 0.000096 grad: 0.0760 (0.0764) loss: 0.8237 (0.8244) time: 0.1360 data: 0.0580 max mem: 9390 +Train: [35] [2900/6250] eta: 0:07:57 lr: 0.000096 grad: 0.0750 (0.0764) loss: 0.8274 (0.8246) time: 0.1375 data: 0.0546 max mem: 9390 +Train: [35] [3000/6250] eta: 0:07:43 lr: 0.000096 grad: 0.0709 (0.0764) loss: 0.8297 (0.8247) time: 0.1578 data: 0.0811 max mem: 9390 +Train: [35] [3100/6250] eta: 0:07:28 lr: 0.000096 grad: 0.0729 (0.0764) loss: 0.8289 (0.8248) time: 0.1362 data: 0.0619 max mem: 9390 +Train: [35] [3200/6250] eta: 0:07:14 lr: 0.000096 grad: 0.0714 (0.0764) loss: 0.8260 (0.8249) time: 0.1216 data: 0.0432 max mem: 9390 +Train: [35] [3300/6250] eta: 0:07:00 lr: 0.000096 grad: 0.0753 (0.0766) loss: 0.8214 (0.8248) time: 0.1231 data: 0.0387 max mem: 9390 +Train: [35] [3400/6250] eta: 0:06:47 lr: 0.000096 grad: 0.0802 (0.0767) loss: 0.8264 (0.8249) time: 0.1677 data: 0.0780 max mem: 9390 +Train: [35] [3500/6250] eta: 0:06:32 lr: 0.000096 grad: 0.0727 (0.0767) loss: 0.8261 (0.8250) time: 0.1295 data: 0.0530 max mem: 9390 +Train: [35] [3600/6250] eta: 0:06:17 lr: 0.000096 grad: 0.0772 (0.0767) loss: 0.8276 (0.8251) time: 0.1045 data: 0.0271 max mem: 9390 +Train: [35] [3700/6250] eta: 0:06:03 lr: 0.000096 grad: 0.0787 (0.0767) loss: 0.8282 (0.8252) time: 0.1592 data: 0.0826 max mem: 9390 +Train: [35] [3800/6250] eta: 0:05:50 lr: 0.000096 grad: 0.0801 (0.0768) loss: 0.8298 (0.8252) time: 0.1552 data: 0.0725 max mem: 9390 +Train: [35] [3900/6250] eta: 0:05:36 lr: 0.000096 grad: 0.0760 (0.0768) loss: 0.8255 (0.8252) time: 0.1535 data: 0.0725 max mem: 9390 +Train: [35] [4000/6250] eta: 0:05:22 lr: 0.000096 grad: 0.0814 (0.0769) loss: 0.8299 (0.8253) time: 0.1702 data: 0.0930 max mem: 9390 +Train: [35] [4100/6250] eta: 0:05:07 lr: 0.000096 grad: 0.0747 (0.0769) loss: 0.8262 (0.8253) time: 0.1409 data: 0.0463 max mem: 9390 +Train: [35] [4200/6250] eta: 0:04:52 lr: 0.000096 grad: 0.0766 (0.0770) loss: 0.8260 (0.8253) time: 0.1289 data: 0.0517 max mem: 9390 +Train: [35] [4300/6250] eta: 0:04:38 lr: 0.000095 grad: 0.0746 (0.0770) loss: 0.8239 (0.8254) time: 0.1453 data: 0.0673 max mem: 9390 +Train: [35] [4400/6250] eta: 0:04:24 lr: 0.000095 grad: 0.0712 (0.0769) loss: 0.8228 (0.8254) time: 0.1201 data: 0.0421 max mem: 9390 +Train: [35] [4500/6250] eta: 0:04:10 lr: 0.000095 grad: 0.0772 (0.0770) loss: 0.8223 (0.8255) time: 0.1474 data: 0.0732 max mem: 9390 +Train: [35] [4600/6250] eta: 0:03:56 lr: 0.000095 grad: 0.0726 (0.0769) loss: 0.8267 (0.8255) time: 0.1249 data: 0.0423 max mem: 9390 +Train: [35] [4700/6250] eta: 0:03:41 lr: 0.000095 grad: 0.0715 (0.0769) loss: 0.8327 (0.8255) time: 0.1501 data: 0.0769 max mem: 9390 +Train: [35] [4800/6250] eta: 0:03:27 lr: 0.000095 grad: 0.0714 (0.0769) loss: 0.8263 (0.8255) time: 0.1461 data: 0.0671 max mem: 9390 +Train: [35] [4900/6250] eta: 0:03:13 lr: 0.000095 grad: 0.0713 (0.0768) loss: 0.8278 (0.8256) time: 0.1485 data: 0.0716 max mem: 9390 +Train: [35] [5000/6250] eta: 0:02:59 lr: 0.000095 grad: 0.0722 (0.0768) loss: 0.8287 (0.8256) time: 0.1456 data: 0.0623 max mem: 9390 +Train: [35] [5100/6250] eta: 0:02:44 lr: 0.000095 grad: 0.0680 (0.0767) loss: 0.8311 (0.8258) time: 0.1409 data: 0.0684 max mem: 9390 +Train: [35] [5200/6250] eta: 0:02:30 lr: 0.000095 grad: 0.0779 (0.0767) loss: 0.8306 (0.8258) time: 0.1287 data: 0.0461 max mem: 9390 +Train: [35] [5300/6250] eta: 0:02:15 lr: 0.000095 grad: 0.0732 (0.0766) loss: 0.8276 (0.8259) time: 0.1530 data: 0.0672 max mem: 9390 +Train: [35] [5400/6250] eta: 0:02:01 lr: 0.000095 grad: 0.0743 (0.0766) loss: 0.8256 (0.8259) time: 0.1456 data: 0.0699 max mem: 9390 +Train: [35] [5500/6250] eta: 0:01:46 lr: 0.000095 grad: 0.0668 (0.0765) loss: 0.8330 (0.8260) time: 0.1365 data: 0.0583 max mem: 9390 +Train: [35] [5600/6250] eta: 0:01:32 lr: 0.000095 grad: 0.0732 (0.0765) loss: 0.8264 (0.8261) time: 0.1242 data: 0.0389 max mem: 9390 +Train: [35] [5700/6250] eta: 0:01:18 lr: 0.000095 grad: 0.0730 (0.0765) loss: 0.8220 (0.8261) time: 0.2758 data: 0.1784 max mem: 9390 +Train: [35] [5800/6250] eta: 0:01:04 lr: 0.000095 grad: 0.0707 (0.0765) loss: 0.8263 (0.8261) time: 0.1634 data: 0.0849 max mem: 9390 +Train: [35] [5900/6250] eta: 0:00:49 lr: 0.000095 grad: 0.0752 (0.0764) loss: 0.8266 (0.8262) time: 0.1247 data: 0.0423 max mem: 9390 +Train: [35] [6000/6250] eta: 0:00:35 lr: 0.000095 grad: 0.0722 (0.0764) loss: 0.8293 (0.8262) time: 0.1234 data: 0.0464 max mem: 9390 +Train: [35] [6100/6250] eta: 0:00:21 lr: 0.000095 grad: 0.0755 (0.0764) loss: 0.8203 (0.8262) time: 0.1062 data: 0.0211 max mem: 9390 +Train: [35] [6200/6250] eta: 0:00:07 lr: 0.000095 grad: 0.0675 (0.0764) loss: 0.8320 (0.8262) time: 0.1905 data: 0.1049 max mem: 9390 +Train: [35] [6249/6250] eta: 0:00:00 lr: 0.000095 grad: 0.0702 (0.0764) loss: 0.8312 (0.8262) time: 0.1528 data: 0.0720 max mem: 9390 +Train: [35] Total time: 0:14:56 (0.1434 s / it) +Averaged stats: lr: 0.000095 grad: 0.0702 (0.0764) loss: 0.8312 (0.8262) +Eval (hcp-train-subset): [35] [ 0/62] eta: 0:05:11 loss: 0.8500 (0.8500) time: 5.0238 data: 4.9934 max mem: 9390 +Eval (hcp-train-subset): [35] [61/62] eta: 0:00:00 loss: 0.8408 (0.8406) time: 0.1299 data: 0.1053 max mem: 9390 +Eval (hcp-train-subset): [35] Total time: 0:00:12 (0.2085 s / it) +Averaged stats (hcp-train-subset): loss: 0.8408 (0.8406) +Eval (hcp-val): [35] [ 0/62] eta: 0:03:22 loss: 0.8331 (0.8331) time: 3.2621 data: 3.1880 max mem: 9390 +Eval (hcp-val): [35] [61/62] eta: 0:00:00 loss: 0.8361 (0.8375) time: 0.1161 data: 0.0912 max mem: 9390 +Eval (hcp-val): [35] Total time: 0:00:12 (0.2020 s / it) +Averaged stats (hcp-val): loss: 0.8361 (0.8375) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +Train: [36] [ 0/6250] eta: 8:46:58 lr: 0.000095 grad: 0.1206 (0.1206) loss: 0.8257 (0.8257) time: 5.0589 data: 4.9229 max mem: 9390 +Train: [36] [ 100/6250] eta: 0:18:15 lr: 0.000095 grad: 0.0755 (0.0859) loss: 0.8209 (0.8292) time: 0.1339 data: 0.0432 max mem: 9390 +Train: [36] [ 200/6250] eta: 0:16:10 lr: 0.000095 grad: 0.0643 (0.0812) loss: 0.8289 (0.8260) time: 0.1518 data: 0.0652 max mem: 9390 +Train: [36] [ 300/6250] eta: 0:15:22 lr: 0.000095 grad: 0.0680 (0.0791) loss: 0.8276 (0.8250) time: 0.1206 data: 0.0349 max mem: 9390 +Train: [36] [ 400/6250] eta: 0:14:42 lr: 0.000095 grad: 0.0680 (0.0779) loss: 0.8332 (0.8259) time: 0.1371 data: 0.0528 max mem: 9390 +Train: [36] [ 500/6250] eta: 0:14:09 lr: 0.000095 grad: 0.0737 (0.0768) loss: 0.8387 (0.8267) time: 0.1384 data: 0.0475 max mem: 9390 +Train: [36] [ 600/6250] eta: 0:13:41 lr: 0.000095 grad: 0.0718 (0.0766) loss: 0.8364 (0.8271) time: 0.0966 data: 0.0120 max mem: 9390 +Train: [36] [ 700/6250] eta: 0:13:21 lr: 0.000095 grad: 0.0705 (0.0763) loss: 0.8295 (0.8277) time: 0.1511 data: 0.0712 max mem: 9390 +Train: [36] [ 800/6250] eta: 0:13:12 lr: 0.000095 grad: 0.0703 (0.0760) loss: 0.8314 (0.8282) time: 0.1159 data: 0.0399 max mem: 9390 +Train: [36] [ 900/6250] eta: 0:12:59 lr: 0.000095 grad: 0.0747 (0.0759) loss: 0.8352 (0.8285) time: 0.1657 data: 0.0895 max mem: 9390 +Train: [36] [1000/6250] eta: 0:12:41 lr: 0.000095 grad: 0.0687 (0.0756) loss: 0.8318 (0.8288) time: 0.1402 data: 0.0624 max mem: 9390 +Train: [36] [1100/6250] eta: 0:12:20 lr: 0.000095 grad: 0.0737 (0.0757) loss: 0.8289 (0.8288) time: 0.1295 data: 0.0503 max mem: 9390 +Train: [36] [1200/6250] eta: 0:12:08 lr: 0.000095 grad: 0.0725 (0.0756) loss: 0.8230 (0.8287) time: 0.1885 data: 0.0941 max mem: 9390 +Train: [36] [1300/6250] eta: 0:11:50 lr: 0.000095 grad: 0.0706 (0.0755) loss: 0.8338 (0.8289) time: 0.1443 data: 0.0685 max mem: 9390 +Train: [36] [1400/6250] eta: 0:11:37 lr: 0.000095 grad: 0.0705 (0.0756) loss: 0.8311 (0.8289) time: 0.1549 data: 0.0643 max mem: 9390 +Train: [36] [1500/6250] eta: 0:11:32 lr: 0.000095 grad: 0.0724 (0.0756) loss: 0.8274 (0.8289) time: 0.2544 data: 0.1655 max mem: 9390 +Train: [36] [1600/6250] eta: 0:11:14 lr: 0.000094 grad: 0.0756 (0.0755) loss: 0.8281 (0.8290) time: 0.1419 data: 0.0622 max mem: 9390 +Train: [36] [1700/6250] eta: 0:10:57 lr: 0.000094 grad: 0.0734 (0.0756) loss: 0.8316 (0.8291) time: 0.1366 data: 0.0590 max mem: 9390 +Train: [36] [1800/6250] eta: 0:10:44 lr: 0.000094 grad: 0.0808 (0.0757) loss: 0.8177 (0.8289) time: 0.1533 data: 0.0745 max mem: 9390 +Train: [36] [1900/6250] eta: 0:10:26 lr: 0.000094 grad: 0.0820 (0.0759) loss: 0.8285 (0.8289) time: 0.1389 data: 0.0577 max mem: 9390 +Train: [36] [2000/6250] eta: 0:10:13 lr: 0.000094 grad: 0.0869 (0.0761) loss: 0.8213 (0.8288) time: 0.1534 data: 0.0811 max mem: 9390 +Train: [36] [2100/6250] eta: 0:09:59 lr: 0.000094 grad: 0.0708 (0.0762) loss: 0.8349 (0.8288) time: 0.1520 data: 0.0728 max mem: 9390 +Train: [36] [2200/6250] eta: 0:09:44 lr: 0.000094 grad: 0.0688 (0.0762) loss: 0.8239 (0.8288) time: 0.1410 data: 0.0563 max mem: 9390 +Train: [36] [2300/6250] eta: 0:09:30 lr: 0.000094 grad: 0.0765 (0.0762) loss: 0.8286 (0.8289) time: 0.1515 data: 0.0728 max mem: 9390 +Train: [36] [2400/6250] eta: 0:09:16 lr: 0.000094 grad: 0.0703 (0.0761) loss: 0.8282 (0.8289) time: 0.1250 data: 0.0466 max mem: 9390 +Train: [36] [2500/6250] eta: 0:09:02 lr: 0.000094 grad: 0.0784 (0.0762) loss: 0.8275 (0.8288) time: 0.1599 data: 0.0755 max mem: 9390 +Train: [36] [2600/6250] eta: 0:08:47 lr: 0.000094 grad: 0.0779 (0.0762) loss: 0.8341 (0.8289) time: 0.1312 data: 0.0526 max mem: 9390 +Train: [36] [2700/6250] eta: 0:08:35 lr: 0.000094 grad: 0.0699 (0.0762) loss: 0.8296 (0.8289) time: 0.1579 data: 0.0630 max mem: 9390 +Train: [36] [2800/6250] eta: 0:08:22 lr: 0.000094 grad: 0.0743 (0.0761) loss: 0.8322 (0.8289) time: 0.1639 data: 0.0823 max mem: 9390 +Train: [36] [2900/6250] eta: 0:08:06 lr: 0.000094 grad: 0.0738 (0.0763) loss: 0.8244 (0.8289) time: 0.1313 data: 0.0525 max mem: 9390 +Train: [36] [3000/6250] eta: 0:07:52 lr: 0.000094 grad: 0.0762 (0.0763) loss: 0.8303 (0.8288) time: 0.1420 data: 0.0617 max mem: 9390 +Train: [36] [3100/6250] eta: 0:07:36 lr: 0.000094 grad: 0.0783 (0.0763) loss: 0.8291 (0.8287) time: 0.1319 data: 0.0564 max mem: 9390 +Train: [36] [3200/6250] eta: 0:07:21 lr: 0.000094 grad: 0.0746 (0.0763) loss: 0.8204 (0.8286) time: 0.1619 data: 0.0857 max mem: 9390 +Train: [36] [3300/6250] eta: 0:07:07 lr: 0.000094 grad: 0.0740 (0.0765) loss: 0.8276 (0.8284) time: 0.1708 data: 0.0939 max mem: 9390 +Train: [36] [3400/6250] eta: 0:06:55 lr: 0.000094 grad: 0.0790 (0.0766) loss: 0.8284 (0.8283) time: 0.1416 data: 0.0630 max mem: 9390 +Train: [36] [3500/6250] eta: 0:06:39 lr: 0.000094 grad: 0.0781 (0.0767) loss: 0.8256 (0.8282) time: 0.1345 data: 0.0505 max mem: 9390 +Train: [36] [3600/6250] eta: 0:06:24 lr: 0.000094 grad: 0.0709 (0.0766) loss: 0.8241 (0.8282) time: 0.1530 data: 0.0681 max mem: 9390 +Train: [36] [3700/6250] eta: 0:06:09 lr: 0.000094 grad: 0.0729 (0.0767) loss: 0.8208 (0.8280) time: 0.1271 data: 0.0448 max mem: 9390 +Train: [36] [3800/6250] eta: 0:05:54 lr: 0.000094 grad: 0.0749 (0.0767) loss: 0.8286 (0.8279) time: 0.1404 data: 0.0591 max mem: 9390 +Train: [36] [3900/6250] eta: 0:05:40 lr: 0.000094 grad: 0.0685 (0.0767) loss: 0.8297 (0.8279) time: 0.1335 data: 0.0516 max mem: 9390 +Train: [36] [4000/6250] eta: 0:05:25 lr: 0.000094 grad: 0.0752 (0.0767) loss: 0.8204 (0.8277) time: 0.1380 data: 0.0642 max mem: 9390 +Train: [36] [4100/6250] eta: 0:05:11 lr: 0.000094 grad: 0.0744 (0.0767) loss: 0.8219 (0.8276) time: 0.1320 data: 0.0489 max mem: 9390 +Train: [36] [4200/6250] eta: 0:04:57 lr: 0.000094 grad: 0.0723 (0.0767) loss: 0.8259 (0.8276) time: 0.1344 data: 0.0571 max mem: 9390 +Train: [36] [4300/6250] eta: 0:04:43 lr: 0.000094 grad: 0.0747 (0.0767) loss: 0.8326 (0.8275) time: 0.1610 data: 0.0797 max mem: 9390 +Train: [36] [4400/6250] eta: 0:04:29 lr: 0.000094 grad: 0.0717 (0.0767) loss: 0.8218 (0.8274) time: 0.1873 data: 0.1032 max mem: 9390 +Train: [36] [4500/6250] eta: 0:04:15 lr: 0.000094 grad: 0.0762 (0.0767) loss: 0.8192 (0.8273) time: 0.1770 data: 0.0912 max mem: 9390 +Train: [36] [4600/6250] eta: 0:04:02 lr: 0.000094 grad: 0.0824 (0.0767) loss: 0.8140 (0.8272) time: 0.1432 data: 0.0580 max mem: 9390 +Train: [36] [4700/6250] eta: 0:03:47 lr: 0.000094 grad: 0.0773 (0.0768) loss: 0.8230 (0.8271) time: 0.1395 data: 0.0660 max mem: 9390 +Train: [36] [4800/6250] eta: 0:03:33 lr: 0.000094 grad: 0.0810 (0.0768) loss: 0.8301 (0.8270) time: 0.1409 data: 0.0671 max mem: 9390 +Train: [36] [4900/6250] eta: 0:03:19 lr: 0.000094 grad: 0.0773 (0.0768) loss: 0.8272 (0.8270) time: 0.1908 data: 0.1116 max mem: 9390 +Train: [36] [5000/6250] eta: 0:03:03 lr: 0.000094 grad: 0.0724 (0.0768) loss: 0.8261 (0.8269) time: 0.1187 data: 0.0362 max mem: 9390 +Train: [36] [5100/6250] eta: 0:02:48 lr: 0.000093 grad: 0.0709 (0.0768) loss: 0.8217 (0.8269) time: 0.1338 data: 0.0536 max mem: 9390 +Train: [36] [5200/6250] eta: 0:02:34 lr: 0.000093 grad: 0.0762 (0.0768) loss: 0.8270 (0.8269) time: 0.1565 data: 0.0674 max mem: 9390 +Train: [36] [5300/6250] eta: 0:02:19 lr: 0.000093 grad: 0.0753 (0.0768) loss: 0.8279 (0.8269) time: 0.1167 data: 0.0300 max mem: 9390 +Train: [36] [5400/6250] eta: 0:02:04 lr: 0.000093 grad: 0.0667 (0.0768) loss: 0.8287 (0.8268) time: 0.1618 data: 0.0833 max mem: 9390 +Train: [36] [5500/6250] eta: 0:01:49 lr: 0.000093 grad: 0.0771 (0.0768) loss: 0.8309 (0.8268) time: 0.1345 data: 0.0576 max mem: 9390 +Train: [36] [5600/6250] eta: 0:01:35 lr: 0.000093 grad: 0.0726 (0.0768) loss: 0.8222 (0.8268) time: 0.1517 data: 0.0746 max mem: 9390 +Train: [36] [5700/6250] eta: 0:01:20 lr: 0.000093 grad: 0.0754 (0.0768) loss: 0.8230 (0.8267) time: 0.0896 data: 0.0040 max mem: 9390 +Train: [36] [5800/6250] eta: 0:01:05 lr: 0.000093 grad: 0.0712 (0.0768) loss: 0.8284 (0.8267) time: 0.1506 data: 0.0576 max mem: 9390 +Train: [36] [5900/6250] eta: 0:00:51 lr: 0.000093 grad: 0.0757 (0.0767) loss: 0.8238 (0.8267) time: 0.1143 data: 0.0358 max mem: 9390 +Train: [36] [6000/6250] eta: 0:00:36 lr: 0.000093 grad: 0.0729 (0.0767) loss: 0.8257 (0.8266) time: 0.1302 data: 0.0487 max mem: 9390 +Train: [36] [6100/6250] eta: 0:00:21 lr: 0.000093 grad: 0.0709 (0.0767) loss: 0.8233 (0.8266) time: 0.1767 data: 0.0933 max mem: 9390 +Train: [36] [6200/6250] eta: 0:00:07 lr: 0.000093 grad: 0.0717 (0.0768) loss: 0.8291 (0.8266) time: 0.1812 data: 0.1013 max mem: 9390 +Train: [36] [6249/6250] eta: 0:00:00 lr: 0.000093 grad: 0.0729 (0.0768) loss: 0.8250 (0.8266) time: 0.1371 data: 0.0603 max mem: 9390 +Train: [36] Total time: 0:15:21 (0.1474 s / it) +Averaged stats: lr: 0.000093 grad: 0.0729 (0.0768) loss: 0.8250 (0.8266) +Eval (hcp-train-subset): [36] [ 0/62] eta: 0:03:18 loss: 0.8480 (0.8480) time: 3.2004 data: 3.1106 max mem: 9390 +Eval (hcp-train-subset): [36] [61/62] eta: 0:00:00 loss: 0.8391 (0.8401) time: 0.1317 data: 0.1065 max mem: 9390 +Eval (hcp-train-subset): [36] Total time: 0:00:12 (0.2061 s / it) +Averaged stats (hcp-train-subset): loss: 0.8391 (0.8401) +Eval (hcp-val): [36] [ 0/62] eta: 0:04:09 loss: 0.8363 (0.8363) time: 4.0228 data: 3.9439 max mem: 9390 +Eval (hcp-val): [36] [61/62] eta: 0:00:00 loss: 0.8375 (0.8376) time: 0.0987 data: 0.0737 max mem: 9390 +Eval (hcp-val): [36] Total time: 0:00:12 (0.1939 s / it) +Averaged stats (hcp-val): loss: 0.8375 (0.8376) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +Train: [37] [ 0/6250] eta: 9:35:23 lr: 0.000093 grad: 0.0738 (0.0738) loss: 0.8452 (0.8452) time: 5.5238 data: 5.4289 max mem: 9390 +Train: [37] [ 100/6250] eta: 0:18:31 lr: 0.000093 grad: 0.0692 (0.0918) loss: 0.8388 (0.8338) time: 0.1386 data: 0.0481 max mem: 9390 +Train: [37] [ 200/6250] eta: 0:16:13 lr: 0.000093 grad: 0.0703 (0.0839) loss: 0.8343 (0.8325) time: 0.1484 data: 0.0588 max mem: 9390 +Train: [37] [ 300/6250] eta: 0:15:23 lr: 0.000093 grad: 0.0684 (0.0824) loss: 0.8270 (0.8308) time: 0.1571 data: 0.0716 max mem: 9390 +Train: [37] [ 400/6250] eta: 0:14:36 lr: 0.000093 grad: 0.0753 (0.0809) loss: 0.8283 (0.8302) time: 0.1364 data: 0.0477 max mem: 9390 +Train: [37] [ 500/6250] eta: 0:14:07 lr: 0.000093 grad: 0.0737 (0.0794) loss: 0.8302 (0.8306) time: 0.1188 data: 0.0236 max mem: 9390 +Train: [37] [ 600/6250] eta: 0:13:40 lr: 0.000093 grad: 0.0690 (0.0784) loss: 0.8324 (0.8309) time: 0.1528 data: 0.0723 max mem: 9390 +Train: [37] [ 700/6250] eta: 0:13:16 lr: 0.000093 grad: 0.0751 (0.0775) loss: 0.8253 (0.8308) time: 0.1422 data: 0.0545 max mem: 9390 +Train: [37] [ 800/6250] eta: 0:13:09 lr: 0.000093 grad: 0.0713 (0.0768) loss: 0.8259 (0.8305) time: 0.1839 data: 0.1034 max mem: 9390 +Train: [37] [ 900/6250] eta: 0:12:54 lr: 0.000093 grad: 0.0672 (0.0762) loss: 0.8277 (0.8301) time: 0.1545 data: 0.0688 max mem: 9390 +Train: [37] [1000/6250] eta: 0:12:42 lr: 0.000093 grad: 0.0687 (0.0758) loss: 0.8263 (0.8298) time: 0.1430 data: 0.0660 max mem: 9390 +Train: [37] [1100/6250] eta: 0:12:24 lr: 0.000093 grad: 0.0672 (0.0754) loss: 0.8316 (0.8299) time: 0.1413 data: 0.0596 max mem: 9390 +Train: [37] [1200/6250] eta: 0:12:13 lr: 0.000093 grad: 0.0712 (0.0750) loss: 0.8300 (0.8298) time: 0.1523 data: 0.0721 max mem: 9390 +Train: [37] [1300/6250] eta: 0:12:01 lr: 0.000093 grad: 0.0772 (0.0750) loss: 0.8186 (0.8295) time: 0.1430 data: 0.0644 max mem: 9390 +Train: [37] [1400/6250] eta: 0:11:46 lr: 0.000093 grad: 0.0683 (0.0749) loss: 0.8274 (0.8293) time: 0.1425 data: 0.0475 max mem: 9390 +Train: [37] [1500/6250] eta: 0:11:34 lr: 0.000093 grad: 0.0623 (0.0748) loss: 0.8286 (0.8291) time: 0.1347 data: 0.0543 max mem: 9390 +Train: [37] [1600/6250] eta: 0:11:19 lr: 0.000093 grad: 0.0753 (0.0748) loss: 0.8258 (0.8289) time: 0.1335 data: 0.0415 max mem: 9390 +Train: [37] [1700/6250] eta: 0:11:03 lr: 0.000093 grad: 0.0723 (0.0747) loss: 0.8227 (0.8288) time: 0.1631 data: 0.0787 max mem: 9390 +Train: [37] [1800/6250] eta: 0:10:48 lr: 0.000093 grad: 0.0681 (0.0746) loss: 0.8233 (0.8286) time: 0.1402 data: 0.0569 max mem: 9390 +Train: [37] [1900/6250] eta: 0:10:33 lr: 0.000093 grad: 0.0690 (0.0745) loss: 0.8290 (0.8285) time: 0.1510 data: 0.0709 max mem: 9390 +Train: [37] [2000/6250] eta: 0:10:17 lr: 0.000093 grad: 0.0758 (0.0745) loss: 0.8192 (0.8283) time: 0.1316 data: 0.0537 max mem: 9390 +Train: [37] [2100/6250] eta: 0:10:02 lr: 0.000093 grad: 0.0760 (0.0747) loss: 0.8259 (0.8282) time: 0.1689 data: 0.0801 max mem: 9390 +Train: [37] [2200/6250] eta: 0:09:47 lr: 0.000093 grad: 0.0745 (0.0747) loss: 0.8274 (0.8281) time: 0.1310 data: 0.0540 max mem: 9390 +Train: [37] [2300/6250] eta: 0:09:32 lr: 0.000092 grad: 0.0718 (0.0748) loss: 0.8258 (0.8279) time: 0.1501 data: 0.0754 max mem: 9390 +Train: [37] [2400/6250] eta: 0:09:17 lr: 0.000092 grad: 0.0752 (0.0750) loss: 0.8228 (0.8277) time: 0.1937 data: 0.0922 max mem: 9390 +Train: [37] [2500/6250] eta: 0:09:07 lr: 0.000092 grad: 0.0750 (0.0751) loss: 0.8236 (0.8277) time: 0.1465 data: 0.0657 max mem: 9390 +Train: [37] [2600/6250] eta: 0:08:52 lr: 0.000092 grad: 0.0750 (0.0753) loss: 0.8277 (0.8275) time: 0.1356 data: 0.0544 max mem: 9390 +Train: [37] [2700/6250] eta: 0:08:40 lr: 0.000092 grad: 0.0710 (0.0754) loss: 0.8250 (0.8275) time: 0.1650 data: 0.0853 max mem: 9390 +Train: [37] [2800/6250] eta: 0:08:25 lr: 0.000092 grad: 0.0735 (0.0753) loss: 0.8247 (0.8274) time: 0.1360 data: 0.0559 max mem: 9390 +Train: [37] [2900/6250] eta: 0:08:09 lr: 0.000092 grad: 0.0729 (0.0754) loss: 0.8284 (0.8274) time: 0.1457 data: 0.0704 max mem: 9390 +Train: [37] [3000/6250] eta: 0:07:54 lr: 0.000092 grad: 0.0762 (0.0754) loss: 0.8300 (0.8275) time: 0.1737 data: 0.1003 max mem: 9390 +Train: [37] [3100/6250] eta: 0:07:39 lr: 0.000092 grad: 0.0758 (0.0754) loss: 0.8248 (0.8275) time: 0.1347 data: 0.0554 max mem: 9390 +Train: [37] [3200/6250] eta: 0:07:23 lr: 0.000092 grad: 0.0801 (0.0755) loss: 0.8268 (0.8274) time: 0.1329 data: 0.0549 max mem: 9390 +Train: [37] [3300/6250] eta: 0:07:08 lr: 0.000092 grad: 0.0698 (0.0755) loss: 0.8212 (0.8274) time: 0.1272 data: 0.0509 max mem: 9390 +Train: [37] [3400/6250] eta: 0:06:53 lr: 0.000092 grad: 0.0759 (0.0755) loss: 0.8270 (0.8274) time: 0.1284 data: 0.0476 max mem: 9390 +Train: [37] [3500/6250] eta: 0:06:39 lr: 0.000092 grad: 0.0693 (0.0755) loss: 0.8291 (0.8274) time: 0.1430 data: 0.0630 max mem: 9390 +Train: [37] [3600/6250] eta: 0:06:25 lr: 0.000092 grad: 0.0756 (0.0756) loss: 0.8244 (0.8273) time: 0.1528 data: 0.0708 max mem: 9390 +Train: [37] [3700/6250] eta: 0:06:10 lr: 0.000092 grad: 0.0754 (0.0756) loss: 0.8238 (0.8273) time: 0.1351 data: 0.0527 max mem: 9390 +Train: [37] [3800/6250] eta: 0:05:55 lr: 0.000092 grad: 0.0704 (0.0757) loss: 0.8263 (0.8272) time: 0.1362 data: 0.0603 max mem: 9390 +Train: [37] [3900/6250] eta: 0:05:41 lr: 0.000092 grad: 0.0731 (0.0760) loss: 0.8249 (0.8272) time: 0.1620 data: 0.0817 max mem: 9390 +Train: [37] [4000/6250] eta: 0:05:26 lr: 0.000092 grad: 0.0771 (0.0760) loss: 0.8260 (0.8271) time: 0.1710 data: 0.0911 max mem: 9390 +Train: [37] [4100/6250] eta: 0:05:13 lr: 0.000092 grad: 0.0783 (0.0761) loss: 0.8241 (0.8270) time: 0.1210 data: 0.0439 max mem: 9390 +Train: [37] [4200/6250] eta: 0:04:59 lr: 0.000092 grad: 0.0769 (0.0762) loss: 0.8254 (0.8270) time: 0.1350 data: 0.0538 max mem: 9390 +Train: [37] [4300/6250] eta: 0:04:45 lr: 0.000092 grad: 0.0734 (0.0762) loss: 0.8283 (0.8270) time: 0.1630 data: 0.0838 max mem: 9390 +Train: [37] [4400/6250] eta: 0:04:30 lr: 0.000092 grad: 0.0779 (0.0762) loss: 0.8267 (0.8269) time: 0.1544 data: 0.0639 max mem: 9390 +Train: [37] [4500/6250] eta: 0:04:15 lr: 0.000092 grad: 0.0766 (0.0763) loss: 0.8257 (0.8268) time: 0.1266 data: 0.0466 max mem: 9390 +Train: [37] [4600/6250] eta: 0:04:01 lr: 0.000092 grad: 0.0784 (0.0763) loss: 0.8220 (0.8268) time: 0.1686 data: 0.0926 max mem: 9390 +Train: [37] [4700/6250] eta: 0:03:46 lr: 0.000092 grad: 0.0744 (0.0764) loss: 0.8240 (0.8267) time: 0.1383 data: 0.0588 max mem: 9390 +Train: [37] [4800/6250] eta: 0:03:32 lr: 0.000092 grad: 0.0759 (0.0764) loss: 0.8220 (0.8267) time: 0.1938 data: 0.1138 max mem: 9390 +Train: [37] [4900/6250] eta: 0:03:17 lr: 0.000092 grad: 0.0687 (0.0764) loss: 0.8279 (0.8266) time: 0.1181 data: 0.0403 max mem: 9390 +Train: [37] [5000/6250] eta: 0:03:02 lr: 0.000092 grad: 0.0780 (0.0765) loss: 0.8180 (0.8266) time: 0.1218 data: 0.0382 max mem: 9390 +Train: [37] [5100/6250] eta: 0:02:47 lr: 0.000092 grad: 0.0743 (0.0765) loss: 0.8222 (0.8265) time: 0.1736 data: 0.0950 max mem: 9390 +Train: [37] [5200/6250] eta: 0:02:32 lr: 0.000092 grad: 0.0826 (0.0765) loss: 0.8241 (0.8265) time: 0.1273 data: 0.0469 max mem: 9390 +Train: [37] [5300/6250] eta: 0:02:17 lr: 0.000092 grad: 0.0739 (0.0766) loss: 0.8266 (0.8264) time: 0.1181 data: 0.0399 max mem: 9390 +Train: [37] [5400/6250] eta: 0:02:03 lr: 0.000092 grad: 0.0749 (0.0766) loss: 0.8236 (0.8264) time: 0.1277 data: 0.0488 max mem: 9390 +Train: [37] [5500/6250] eta: 0:01:48 lr: 0.000092 grad: 0.0745 (0.0767) loss: 0.8247 (0.8263) time: 0.1823 data: 0.1100 max mem: 9390 +Train: [37] [5600/6250] eta: 0:01:34 lr: 0.000092 grad: 0.0807 (0.0767) loss: 0.8229 (0.8263) time: 0.1395 data: 0.0461 max mem: 9390 +Train: [37] [5700/6250] eta: 0:01:19 lr: 0.000091 grad: 0.0790 (0.0767) loss: 0.8214 (0.8263) time: 0.1464 data: 0.0700 max mem: 9390 +Train: [37] [5800/6250] eta: 0:01:05 lr: 0.000091 grad: 0.0736 (0.0768) loss: 0.8265 (0.8262) time: 0.1569 data: 0.0824 max mem: 9390 +Train: [37] [5900/6250] eta: 0:00:50 lr: 0.000091 grad: 0.0779 (0.0768) loss: 0.8287 (0.8262) time: 0.1419 data: 0.0673 max mem: 9390 +Train: [37] [6000/6250] eta: 0:00:36 lr: 0.000091 grad: 0.0787 (0.0768) loss: 0.8265 (0.8262) time: 0.1522 data: 0.0755 max mem: 9390 +Train: [37] [6100/6250] eta: 0:00:21 lr: 0.000091 grad: 0.0791 (0.0768) loss: 0.8294 (0.8262) time: 0.1856 data: 0.0984 max mem: 9390 +Train: [37] [6200/6250] eta: 0:00:07 lr: 0.000091 grad: 0.0746 (0.0769) loss: 0.8272 (0.8262) time: 0.1480 data: 0.0551 max mem: 9390 +Train: [37] [6249/6250] eta: 0:00:00 lr: 0.000091 grad: 0.0770 (0.0769) loss: 0.8308 (0.8262) time: 0.1428 data: 0.0667 max mem: 9390 +Train: [37] Total time: 0:15:12 (0.1460 s / it) +Averaged stats: lr: 0.000091 grad: 0.0770 (0.0769) loss: 0.8308 (0.8262) +Eval (hcp-train-subset): [37] [ 0/62] eta: 0:03:17 loss: 0.8529 (0.8529) time: 3.1817 data: 3.1128 max mem: 9390 +Eval (hcp-train-subset): [37] [61/62] eta: 0:00:00 loss: 0.8409 (0.8405) time: 0.1259 data: 0.1011 max mem: 9390 +Eval (hcp-train-subset): [37] Total time: 0:00:12 (0.2066 s / it) +Averaged stats (hcp-train-subset): loss: 0.8409 (0.8405) +Eval (hcp-val): [37] [ 0/62] eta: 0:03:57 loss: 0.8361 (0.8361) time: 3.8354 data: 3.7382 max mem: 9390 +Eval (hcp-val): [37] [61/62] eta: 0:00:00 loss: 0.8365 (0.8377) time: 0.1089 data: 0.0842 max mem: 9390 +Eval (hcp-val): [37] Total time: 0:00:11 (0.1866 s / it) +Averaged stats (hcp-val): loss: 0.8365 (0.8377) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +Train: [38] [ 0/6250] eta: 6:51:30 lr: 0.000091 grad: 0.0668 (0.0668) loss: 0.8760 (0.8760) time: 3.9505 data: 3.6388 max mem: 9390 +Train: [38] [ 100/6250] eta: 0:18:47 lr: 0.000091 grad: 0.0768 (0.0837) loss: 0.8273 (0.8326) time: 0.1301 data: 0.0354 max mem: 9390 +Train: [38] [ 200/6250] eta: 0:15:53 lr: 0.000091 grad: 0.0755 (0.0838) loss: 0.8301 (0.8303) time: 0.1267 data: 0.0396 max mem: 9390 +Train: [38] [ 300/6250] eta: 0:14:41 lr: 0.000091 grad: 0.0754 (0.0825) loss: 0.8265 (0.8291) time: 0.1249 data: 0.0383 max mem: 9390 +Train: [38] [ 400/6250] eta: 0:13:47 lr: 0.000091 grad: 0.0711 (0.0801) loss: 0.8298 (0.8291) time: 0.1139 data: 0.0274 max mem: 9390 +Train: [38] [ 500/6250] eta: 0:13:22 lr: 0.000091 grad: 0.0722 (0.0794) loss: 0.8219 (0.8282) time: 0.1170 data: 0.0362 max mem: 9390 +Train: [38] [ 600/6250] eta: 0:12:53 lr: 0.000091 grad: 0.0756 (0.0789) loss: 0.8181 (0.8276) time: 0.1269 data: 0.0411 max mem: 9390 +Train: [38] [ 700/6250] eta: 0:12:30 lr: 0.000091 grad: 0.0735 (0.0786) loss: 0.8285 (0.8272) time: 0.1268 data: 0.0388 max mem: 9390 +Train: [38] [ 800/6250] eta: 0:12:17 lr: 0.000091 grad: 0.0729 (0.0781) loss: 0.8347 (0.8270) time: 0.1212 data: 0.0367 max mem: 9390 +Train: [38] [ 900/6250] eta: 0:12:16 lr: 0.000091 grad: 0.0739 (0.0785) loss: 0.8282 (0.8270) time: 0.1466 data: 0.0653 max mem: 9390 +Train: [38] [1000/6250] eta: 0:12:15 lr: 0.000091 grad: 0.0763 (0.0783) loss: 0.8230 (0.8267) time: 0.1537 data: 0.0662 max mem: 9390 +Train: [38] [1100/6250] eta: 0:12:00 lr: 0.000091 grad: 0.0782 (0.0783) loss: 0.8223 (0.8267) time: 0.1381 data: 0.0571 max mem: 9390 +Train: [38] [1200/6250] eta: 0:11:48 lr: 0.000091 grad: 0.0769 (0.0783) loss: 0.8216 (0.8265) time: 0.1826 data: 0.1040 max mem: 9390 +Train: [38] [1300/6250] eta: 0:11:29 lr: 0.000091 grad: 0.0755 (0.0783) loss: 0.8289 (0.8263) time: 0.1385 data: 0.0571 max mem: 9390 +Train: [38] [1400/6250] eta: 0:11:17 lr: 0.000091 grad: 0.0774 (0.0783) loss: 0.8188 (0.8260) time: 0.1611 data: 0.0827 max mem: 9390 +Train: [38] [1500/6250] eta: 0:11:01 lr: 0.000091 grad: 0.0773 (0.0783) loss: 0.8222 (0.8258) time: 0.1390 data: 0.0543 max mem: 9390 +Train: [38] [1600/6250] eta: 0:10:52 lr: 0.000091 grad: 0.0813 (0.0788) loss: 0.8171 (0.8257) time: 0.1730 data: 0.0908 max mem: 9390 +Train: [38] [1700/6250] eta: 0:10:39 lr: 0.000091 grad: 0.0797 (0.0790) loss: 0.8230 (0.8254) time: 0.1470 data: 0.0672 max mem: 9390 +Train: [38] [1800/6250] eta: 0:10:23 lr: 0.000091 grad: 0.0774 (0.0791) loss: 0.8233 (0.8252) time: 0.1455 data: 0.0690 max mem: 9390 +Train: [38] [1900/6250] eta: 0:10:08 lr: 0.000091 grad: 0.0840 (0.0793) loss: 0.8252 (0.8250) time: 0.1210 data: 0.0445 max mem: 9390 +Train: [38] [2000/6250] eta: 0:09:55 lr: 0.000091 grad: 0.0817 (0.0793) loss: 0.8201 (0.8249) time: 0.1253 data: 0.0422 max mem: 9390 +Train: [38] [2100/6250] eta: 0:09:41 lr: 0.000091 grad: 0.0784 (0.0795) loss: 0.8282 (0.8248) time: 0.1248 data: 0.0427 max mem: 9390 +Train: [38] [2200/6250] eta: 0:09:29 lr: 0.000091 grad: 0.0829 (0.0796) loss: 0.8235 (0.8247) time: 0.1356 data: 0.0583 max mem: 9390 +Train: [38] [2300/6250] eta: 0:09:14 lr: 0.000091 grad: 0.0785 (0.0797) loss: 0.8299 (0.8247) time: 0.1464 data: 0.0697 max mem: 9390 +Train: [38] [2400/6250] eta: 0:09:00 lr: 0.000091 grad: 0.0748 (0.0797) loss: 0.8289 (0.8247) time: 0.1387 data: 0.0568 max mem: 9390 +Train: [38] [2500/6250] eta: 0:08:47 lr: 0.000091 grad: 0.0756 (0.0796) loss: 0.8248 (0.8248) time: 0.1660 data: 0.0695 max mem: 9390 +Train: [38] [2600/6250] eta: 0:08:33 lr: 0.000091 grad: 0.0766 (0.0796) loss: 0.8250 (0.8248) time: 0.1452 data: 0.0689 max mem: 9390 +Train: [38] [2700/6250] eta: 0:08:19 lr: 0.000091 grad: 0.0727 (0.0797) loss: 0.8238 (0.8247) time: 0.1195 data: 0.0421 max mem: 9390 +Train: [38] [2800/6250] eta: 0:08:05 lr: 0.000091 grad: 0.0806 (0.0797) loss: 0.8226 (0.8246) time: 0.1384 data: 0.0591 max mem: 9390 +Train: [38] [2900/6250] eta: 0:07:53 lr: 0.000090 grad: 0.0750 (0.0796) loss: 0.8258 (0.8246) time: 0.2348 data: 0.0838 max mem: 9390 +Train: [38] [3000/6250] eta: 0:07:41 lr: 0.000090 grad: 0.0771 (0.0795) loss: 0.8258 (0.8247) time: 0.1475 data: 0.0710 max mem: 9390 +Train: [38] [3100/6250] eta: 0:07:29 lr: 0.000090 grad: 0.0806 (0.0795) loss: 0.8276 (0.8247) time: 0.2461 data: 0.1226 max mem: 9390 +Train: [38] [3200/6250] eta: 0:07:14 lr: 0.000090 grad: 0.0772 (0.0796) loss: 0.8276 (0.8247) time: 0.1229 data: 0.0394 max mem: 9390 +Train: [38] [3300/6250] eta: 0:07:02 lr: 0.000090 grad: 0.0773 (0.0796) loss: 0.8301 (0.8247) time: 0.0879 data: 0.0002 max mem: 9390 +Train: [38] [3400/6250] eta: 0:06:46 lr: 0.000090 grad: 0.0766 (0.0797) loss: 0.8262 (0.8248) time: 0.1431 data: 0.0611 max mem: 9390 +Train: [38] [3500/6250] eta: 0:06:32 lr: 0.000090 grad: 0.0748 (0.0796) loss: 0.8286 (0.8249) time: 0.1441 data: 0.0667 max mem: 9390 +Train: [38] [3600/6250] eta: 0:06:18 lr: 0.000090 grad: 0.0761 (0.0796) loss: 0.8169 (0.8249) time: 0.1672 data: 0.0850 max mem: 9390 +Train: [38] [3700/6250] eta: 0:06:03 lr: 0.000090 grad: 0.0800 (0.0796) loss: 0.8226 (0.8250) time: 0.1360 data: 0.0558 max mem: 9390 +Train: [38] [3800/6250] eta: 0:05:49 lr: 0.000090 grad: 0.0768 (0.0797) loss: 0.8298 (0.8251) time: 0.1786 data: 0.1037 max mem: 9390 +Train: [38] [3900/6250] eta: 0:05:34 lr: 0.000090 grad: 0.0792 (0.0797) loss: 0.8233 (0.8251) time: 0.1471 data: 0.0739 max mem: 9390 +Train: [38] [4000/6250] eta: 0:05:20 lr: 0.000090 grad: 0.0717 (0.0797) loss: 0.8266 (0.8251) time: 0.1488 data: 0.0604 max mem: 9390 +Train: [38] [4100/6250] eta: 0:05:07 lr: 0.000090 grad: 0.0744 (0.0796) loss: 0.8221 (0.8252) time: 0.1802 data: 0.0938 max mem: 9390 +Train: [38] [4200/6250] eta: 0:04:53 lr: 0.000090 grad: 0.0803 (0.0796) loss: 0.8256 (0.8252) time: 0.1451 data: 0.0640 max mem: 9390 +Train: [38] [4300/6250] eta: 0:04:38 lr: 0.000090 grad: 0.0782 (0.0797) loss: 0.8218 (0.8252) time: 0.1549 data: 0.0795 max mem: 9390 +Train: [38] [4400/6250] eta: 0:04:24 lr: 0.000090 grad: 0.0825 (0.0798) loss: 0.8277 (0.8252) time: 0.1566 data: 0.0819 max mem: 9390 +Train: [38] [4500/6250] eta: 0:04:10 lr: 0.000090 grad: 0.0710 (0.0798) loss: 0.8275 (0.8252) time: 0.1316 data: 0.0537 max mem: 9390 +Train: [38] [4600/6250] eta: 0:03:55 lr: 0.000090 grad: 0.0800 (0.0799) loss: 0.8294 (0.8252) time: 0.1343 data: 0.0579 max mem: 9390 +Train: [38] [4700/6250] eta: 0:03:41 lr: 0.000090 grad: 0.0752 (0.0799) loss: 0.8218 (0.8252) time: 0.1330 data: 0.0487 max mem: 9390 +Train: [38] [4800/6250] eta: 0:03:27 lr: 0.000090 grad: 0.0752 (0.0799) loss: 0.8264 (0.8252) time: 0.1454 data: 0.0532 max mem: 9390 +Train: [38] [4900/6250] eta: 0:03:13 lr: 0.000090 grad: 0.0755 (0.0799) loss: 0.8246 (0.8252) time: 0.1644 data: 0.0664 max mem: 9390 +Train: [38] [5000/6250] eta: 0:02:58 lr: 0.000090 grad: 0.0815 (0.0799) loss: 0.8215 (0.8251) time: 0.1375 data: 0.0547 max mem: 9390 +Train: [38] [5100/6250] eta: 0:02:44 lr: 0.000090 grad: 0.0776 (0.0799) loss: 0.8221 (0.8251) time: 0.1375 data: 0.0563 max mem: 9390 +Train: [38] [5200/6250] eta: 0:02:29 lr: 0.000090 grad: 0.0760 (0.0800) loss: 0.8295 (0.8251) time: 0.1435 data: 0.0697 max mem: 9390 +Train: [38] [5300/6250] eta: 0:02:15 lr: 0.000090 grad: 0.0749 (0.0800) loss: 0.8277 (0.8251) time: 0.1390 data: 0.0635 max mem: 9390 +Train: [38] [5400/6250] eta: 0:02:01 lr: 0.000090 grad: 0.0786 (0.0800) loss: 0.8226 (0.8250) time: 0.1846 data: 0.0947 max mem: 9390 +Train: [38] [5500/6250] eta: 0:01:47 lr: 0.000090 grad: 0.0824 (0.0800) loss: 0.8214 (0.8249) time: 0.1278 data: 0.0481 max mem: 9390 +Train: [38] [5600/6250] eta: 0:01:33 lr: 0.000090 grad: 0.0788 (0.0800) loss: 0.8235 (0.8249) time: 0.1640 data: 0.0841 max mem: 9390 +Train: [38] [5700/6250] eta: 0:01:19 lr: 0.000090 grad: 0.0803 (0.0801) loss: 0.8215 (0.8248) time: 0.1447 data: 0.0618 max mem: 9390 +Train: [38] [5800/6250] eta: 0:01:04 lr: 0.000090 grad: 0.0750 (0.0801) loss: 0.8234 (0.8247) time: 0.1672 data: 0.0899 max mem: 9390 +Train: [38] [5900/6250] eta: 0:00:50 lr: 0.000090 grad: 0.0747 (0.0801) loss: 0.8185 (0.8246) time: 0.1406 data: 0.0565 max mem: 9390 +Train: [38] [6000/6250] eta: 0:00:36 lr: 0.000090 grad: 0.0814 (0.0802) loss: 0.8206 (0.8246) time: 0.1140 data: 0.0383 max mem: 9390 +Train: [38] [6100/6250] eta: 0:00:21 lr: 0.000090 grad: 0.0748 (0.0801) loss: 0.8289 (0.8246) time: 0.1563 data: 0.0735 max mem: 9390 +Train: [38] [6200/6250] eta: 0:00:07 lr: 0.000089 grad: 0.0769 (0.0802) loss: 0.8220 (0.8245) time: 0.1519 data: 0.0709 max mem: 9390 +Train: [38] [6249/6250] eta: 0:00:00 lr: 0.000089 grad: 0.0885 (0.0802) loss: 0.8174 (0.8245) time: 0.1444 data: 0.0716 max mem: 9390 +Train: [38] Total time: 0:15:10 (0.1457 s / it) +Averaged stats: lr: 0.000089 grad: 0.0885 (0.0802) loss: 0.8174 (0.8245) +Eval (hcp-train-subset): [38] [ 0/62] eta: 0:04:15 loss: 0.8518 (0.8518) time: 4.1278 data: 4.0433 max mem: 9390 +Eval (hcp-train-subset): [38] [61/62] eta: 0:00:00 loss: 0.8404 (0.8411) time: 0.1183 data: 0.0934 max mem: 9390 +Eval (hcp-train-subset): [38] Total time: 0:00:12 (0.2055 s / it) +Averaged stats (hcp-train-subset): loss: 0.8404 (0.8411) +Eval (hcp-val): [38] [ 0/62] eta: 0:04:06 loss: 0.8365 (0.8365) time: 3.9808 data: 3.9219 max mem: 9390 +Eval (hcp-val): [38] [61/62] eta: 0:00:00 loss: 0.8370 (0.8376) time: 0.1137 data: 0.0887 max mem: 9390 +Eval (hcp-val): [38] Total time: 0:00:11 (0.1837 s / it) +Averaged stats (hcp-val): loss: 0.8370 (0.8376) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +Train: [39] [ 0/6250] eta: 6:14:39 lr: 0.000089 grad: 0.0569 (0.0569) loss: 0.8476 (0.8476) time: 3.5967 data: 3.3598 max mem: 9390 +Train: [39] [ 100/6250] eta: 0:19:42 lr: 0.000089 grad: 0.0791 (0.0943) loss: 0.8298 (0.8286) time: 0.1520 data: 0.0701 max mem: 9390 +Train: [39] [ 200/6250] eta: 0:16:42 lr: 0.000089 grad: 0.0734 (0.0861) loss: 0.8235 (0.8274) time: 0.1404 data: 0.0567 max mem: 9390 +Train: [39] [ 300/6250] eta: 0:15:22 lr: 0.000089 grad: 0.0733 (0.0823) loss: 0.8284 (0.8282) time: 0.1260 data: 0.0407 max mem: 9390 +Train: [39] [ 400/6250] eta: 0:14:33 lr: 0.000089 grad: 0.0689 (0.0801) loss: 0.8346 (0.8293) time: 0.1372 data: 0.0488 max mem: 9390 +Train: [39] [ 500/6250] eta: 0:13:58 lr: 0.000089 grad: 0.0692 (0.0788) loss: 0.8361 (0.8303) time: 0.1174 data: 0.0318 max mem: 9390 +Train: [39] [ 600/6250] eta: 0:13:30 lr: 0.000089 grad: 0.0688 (0.0783) loss: 0.8367 (0.8305) time: 0.1486 data: 0.0657 max mem: 9390 +Train: [39] [ 700/6250] eta: 0:13:03 lr: 0.000089 grad: 0.0713 (0.0782) loss: 0.8358 (0.8306) time: 0.1368 data: 0.0510 max mem: 9390 +Train: [39] [ 800/6250] eta: 0:12:46 lr: 0.000089 grad: 0.0734 (0.0776) loss: 0.8313 (0.8307) time: 0.1347 data: 0.0532 max mem: 9390 +Train: [39] [ 900/6250] eta: 0:12:39 lr: 0.000089 grad: 0.0669 (0.0772) loss: 0.8301 (0.8306) time: 0.1367 data: 0.0629 max mem: 9390 +Train: [39] [1000/6250] eta: 0:12:26 lr: 0.000089 grad: 0.0703 (0.0771) loss: 0.8243 (0.8303) time: 0.1397 data: 0.0640 max mem: 9390 +Train: [39] [1100/6250] eta: 0:12:12 lr: 0.000089 grad: 0.0709 (0.0770) loss: 0.8347 (0.8301) time: 0.1451 data: 0.0640 max mem: 9390 +Train: [39] [1200/6250] eta: 0:11:56 lr: 0.000089 grad: 0.0754 (0.0771) loss: 0.8208 (0.8297) time: 0.1428 data: 0.0643 max mem: 9390 +Train: [39] [1300/6250] eta: 0:11:41 lr: 0.000089 grad: 0.0684 (0.0769) loss: 0.8339 (0.8295) time: 0.1455 data: 0.0600 max mem: 9390 +Train: [39] [1400/6250] eta: 0:11:28 lr: 0.000089 grad: 0.0758 (0.0769) loss: 0.8259 (0.8292) time: 0.1266 data: 0.0441 max mem: 9390 +Train: [39] [1500/6250] eta: 0:11:13 lr: 0.000089 grad: 0.0738 (0.0768) loss: 0.8289 (0.8291) time: 0.1324 data: 0.0527 max mem: 9390 +Train: [39] [1600/6250] eta: 0:11:01 lr: 0.000089 grad: 0.0735 (0.0769) loss: 0.8270 (0.8289) time: 0.1464 data: 0.0532 max mem: 9390 +Train: [39] [1700/6250] eta: 0:10:48 lr: 0.000089 grad: 0.0765 (0.0769) loss: 0.8302 (0.8287) time: 0.1759 data: 0.0970 max mem: 9390 +Train: [39] [1800/6250] eta: 0:10:33 lr: 0.000089 grad: 0.0772 (0.0769) loss: 0.8229 (0.8284) time: 0.1276 data: 0.0464 max mem: 9390 +Train: [39] [1900/6250] eta: 0:10:17 lr: 0.000089 grad: 0.0773 (0.0769) loss: 0.8263 (0.8282) time: 0.1435 data: 0.0704 max mem: 9390 +Train: [39] [2000/6250] eta: 0:10:02 lr: 0.000089 grad: 0.0776 (0.0769) loss: 0.8231 (0.8281) time: 0.1518 data: 0.0761 max mem: 9390 +Train: [39] [2100/6250] eta: 0:09:48 lr: 0.000089 grad: 0.0769 (0.0769) loss: 0.8153 (0.8278) time: 0.1224 data: 0.0402 max mem: 9390 +Train: [39] [2200/6250] eta: 0:09:33 lr: 0.000089 grad: 0.0802 (0.0771) loss: 0.8233 (0.8275) time: 0.1355 data: 0.0536 max mem: 9390 +Train: [39] [2300/6250] eta: 0:09:20 lr: 0.000089 grad: 0.0723 (0.0772) loss: 0.8176 (0.8273) time: 0.1120 data: 0.0222 max mem: 9390 +Train: [39] [2400/6250] eta: 0:09:08 lr: 0.000089 grad: 0.0804 (0.0772) loss: 0.8216 (0.8271) time: 0.1981 data: 0.1134 max mem: 9390 +Train: [39] [2500/6250] eta: 0:08:52 lr: 0.000089 grad: 0.0772 (0.0772) loss: 0.8251 (0.8270) time: 0.1319 data: 0.0532 max mem: 9390 +Train: [39] [2600/6250] eta: 0:08:38 lr: 0.000089 grad: 0.0797 (0.0773) loss: 0.8255 (0.8270) time: 0.1350 data: 0.0550 max mem: 9390 +Train: [39] [2700/6250] eta: 0:08:22 lr: 0.000089 grad: 0.0773 (0.0774) loss: 0.8291 (0.8268) time: 0.1397 data: 0.0625 max mem: 9390 +Train: [39] [2800/6250] eta: 0:08:08 lr: 0.000089 grad: 0.0811 (0.0775) loss: 0.8207 (0.8267) time: 0.1444 data: 0.0716 max mem: 9390 +Train: [39] [2900/6250] eta: 0:07:55 lr: 0.000089 grad: 0.0771 (0.0776) loss: 0.8198 (0.8266) time: 0.1417 data: 0.0586 max mem: 9390 +Train: [39] [3000/6250] eta: 0:07:42 lr: 0.000089 grad: 0.0767 (0.0776) loss: 0.8225 (0.8265) time: 0.1181 data: 0.0388 max mem: 9390 +Train: [39] [3100/6250] eta: 0:07:28 lr: 0.000089 grad: 0.0793 (0.0777) loss: 0.8173 (0.8264) time: 0.1283 data: 0.0492 max mem: 9390 +Train: [39] [3200/6250] eta: 0:07:14 lr: 0.000089 grad: 0.0771 (0.0778) loss: 0.8204 (0.8262) time: 0.1347 data: 0.0529 max mem: 9390 +Train: [39] [3300/6250] eta: 0:07:00 lr: 0.000088 grad: 0.0802 (0.0779) loss: 0.8185 (0.8261) time: 0.1466 data: 0.0717 max mem: 9390 +Train: [39] [3400/6250] eta: 0:06:46 lr: 0.000088 grad: 0.0779 (0.0780) loss: 0.8274 (0.8259) time: 0.1406 data: 0.0570 max mem: 9390 +Train: [39] [3500/6250] eta: 0:06:32 lr: 0.000088 grad: 0.0766 (0.0781) loss: 0.8229 (0.8259) time: 0.1595 data: 0.0790 max mem: 9390 +Train: [39] [3600/6250] eta: 0:06:18 lr: 0.000088 grad: 0.0754 (0.0782) loss: 0.8259 (0.8259) time: 0.1426 data: 0.0584 max mem: 9390 +Train: [39] [3700/6250] eta: 0:06:03 lr: 0.000088 grad: 0.0748 (0.0783) loss: 0.8260 (0.8259) time: 0.1282 data: 0.0506 max mem: 9390 +Train: [39] [3800/6250] eta: 0:05:50 lr: 0.000088 grad: 0.0796 (0.0784) loss: 0.8196 (0.8258) time: 0.1093 data: 0.0304 max mem: 9390 +Train: [39] [3900/6250] eta: 0:05:35 lr: 0.000088 grad: 0.0763 (0.0784) loss: 0.8215 (0.8257) time: 0.1309 data: 0.0477 max mem: 9390 +Train: [39] [4000/6250] eta: 0:05:21 lr: 0.000088 grad: 0.0829 (0.0784) loss: 0.8135 (0.8257) time: 0.1657 data: 0.0875 max mem: 9390 +Train: [39] [4100/6250] eta: 0:05:07 lr: 0.000088 grad: 0.0791 (0.0785) loss: 0.8222 (0.8256) time: 0.1313 data: 0.0506 max mem: 9390 +Train: [39] [4200/6250] eta: 0:04:53 lr: 0.000088 grad: 0.0734 (0.0785) loss: 0.8237 (0.8256) time: 0.1767 data: 0.0871 max mem: 9390 +Train: [39] [4300/6250] eta: 0:04:39 lr: 0.000088 grad: 0.0756 (0.0785) loss: 0.8231 (0.8255) time: 0.1504 data: 0.0737 max mem: 9390 +Train: [39] [4400/6250] eta: 0:04:24 lr: 0.000088 grad: 0.0801 (0.0785) loss: 0.8206 (0.8255) time: 0.1380 data: 0.0591 max mem: 9390 +Train: [39] [4500/6250] eta: 0:04:10 lr: 0.000088 grad: 0.0784 (0.0786) loss: 0.8251 (0.8255) time: 0.1424 data: 0.0592 max mem: 9390 +Train: [39] [4600/6250] eta: 0:03:55 lr: 0.000088 grad: 0.0817 (0.0786) loss: 0.8219 (0.8255) time: 0.1464 data: 0.0663 max mem: 9390 +Train: [39] [4700/6250] eta: 0:03:41 lr: 0.000088 grad: 0.0758 (0.0787) loss: 0.8210 (0.8255) time: 0.1284 data: 0.0514 max mem: 9390 +Train: [39] [4800/6250] eta: 0:03:26 lr: 0.000088 grad: 0.0742 (0.0787) loss: 0.8233 (0.8255) time: 0.1207 data: 0.0410 max mem: 9390 +Train: [39] [4900/6250] eta: 0:03:12 lr: 0.000088 grad: 0.0773 (0.0787) loss: 0.8298 (0.8255) time: 0.1407 data: 0.0628 max mem: 9390 +Train: [39] [5000/6250] eta: 0:02:58 lr: 0.000088 grad: 0.0776 (0.0787) loss: 0.8237 (0.8255) time: 0.2037 data: 0.1214 max mem: 9390 +Train: [39] [5100/6250] eta: 0:02:44 lr: 0.000088 grad: 0.0789 (0.0787) loss: 0.8249 (0.8255) time: 0.1533 data: 0.0686 max mem: 9390 +Train: [39] [5200/6250] eta: 0:02:29 lr: 0.000088 grad: 0.0776 (0.0787) loss: 0.8263 (0.8255) time: 0.1437 data: 0.0627 max mem: 9390 +Train: [39] [5300/6250] eta: 0:02:15 lr: 0.000088 grad: 0.0766 (0.0788) loss: 0.8305 (0.8256) time: 0.1634 data: 0.0492 max mem: 9390 +Train: [39] [5400/6250] eta: 0:02:01 lr: 0.000088 grad: 0.0759 (0.0789) loss: 0.8282 (0.8256) time: 0.1262 data: 0.0427 max mem: 9390 +Train: [39] [5500/6250] eta: 0:01:47 lr: 0.000088 grad: 0.0707 (0.0790) loss: 0.8245 (0.8256) time: 0.1820 data: 0.1029 max mem: 9390 +Train: [39] [5600/6250] eta: 0:01:32 lr: 0.000088 grad: 0.0773 (0.0791) loss: 0.8228 (0.8256) time: 0.1516 data: 0.0761 max mem: 9390 +Train: [39] [5700/6250] eta: 0:01:18 lr: 0.000088 grad: 0.0826 (0.0792) loss: 0.8197 (0.8256) time: 0.1604 data: 0.0825 max mem: 9390 +Train: [39] [5800/6250] eta: 0:01:04 lr: 0.000088 grad: 0.0790 (0.0792) loss: 0.8196 (0.8256) time: 0.1611 data: 0.0831 max mem: 9390 +Train: [39] [5900/6250] eta: 0:00:49 lr: 0.000088 grad: 0.0809 (0.0793) loss: 0.8265 (0.8255) time: 0.1342 data: 0.0534 max mem: 9390 +Train: [39] [6000/6250] eta: 0:00:35 lr: 0.000088 grad: 0.0799 (0.0794) loss: 0.8253 (0.8255) time: 0.1962 data: 0.1223 max mem: 9390 +Train: [39] [6100/6250] eta: 0:00:21 lr: 0.000088 grad: 0.0842 (0.0795) loss: 0.8207 (0.8255) time: 0.1365 data: 0.0632 max mem: 9390 +Train: [39] [6200/6250] eta: 0:00:07 lr: 0.000088 grad: 0.0811 (0.0796) loss: 0.8220 (0.8255) time: 0.1525 data: 0.0709 max mem: 9390 +Train: [39] [6249/6250] eta: 0:00:00 lr: 0.000088 grad: 0.0767 (0.0796) loss: 0.8210 (0.8255) time: 0.1713 data: 0.0945 max mem: 9390 +Train: [39] Total time: 0:14:57 (0.1436 s / it) +Averaged stats: lr: 0.000088 grad: 0.0767 (0.0796) loss: 0.8210 (0.8255) +Eval (hcp-train-subset): [39] [ 0/62] eta: 0:04:30 loss: 0.8538 (0.8538) time: 4.3668 data: 4.3361 max mem: 9390 +Eval (hcp-train-subset): [39] [61/62] eta: 0:00:00 loss: 0.8383 (0.8394) time: 0.1061 data: 0.0794 max mem: 9390 +Eval (hcp-train-subset): [39] Total time: 0:00:12 (0.2047 s / it) +Averaged stats (hcp-train-subset): loss: 0.8383 (0.8394) +Making plots (hcp-train-subset): example=58 +Eval (hcp-val): [39] [ 0/62] eta: 0:05:02 loss: 0.8349 (0.8349) time: 4.8800 data: 4.8486 max mem: 9390 +Eval (hcp-val): [39] [61/62] eta: 0:00:00 loss: 0.8369 (0.8376) time: 0.1051 data: 0.0800 max mem: 9390 +Eval (hcp-val): [39] Total time: 0:00:12 (0.2049 s / it) +Averaged stats (hcp-val): loss: 0.8369 (0.8376) +Making plots (hcp-val): example=28 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +Train: [40] [ 0/6250] eta: 7:44:37 lr: 0.000088 grad: 0.0739 (0.0739) loss: 0.8745 (0.8745) time: 4.4604 data: 4.2969 max mem: 9390 +Train: [40] [ 100/6250] eta: 0:19:22 lr: 0.000088 grad: 0.0961 (0.1152) loss: 0.8196 (0.8289) time: 0.1447 data: 0.0526 max mem: 9390 +Train: [40] [ 200/6250] eta: 0:16:53 lr: 0.000088 grad: 0.0800 (0.1027) loss: 0.8301 (0.8261) time: 0.1571 data: 0.0709 max mem: 9390 +Train: [40] [ 300/6250] eta: 0:15:27 lr: 0.000088 grad: 0.0742 (0.0947) loss: 0.8317 (0.8256) time: 0.1292 data: 0.0308 max mem: 9390 +Train: [40] [ 400/6250] eta: 0:14:37 lr: 0.000087 grad: 0.0733 (0.0905) loss: 0.8319 (0.8253) time: 0.1294 data: 0.0453 max mem: 9390 +Train: [40] [ 500/6250] eta: 0:14:01 lr: 0.000087 grad: 0.0713 (0.0872) loss: 0.8349 (0.8261) time: 0.1266 data: 0.0478 max mem: 9390 +Train: [40] [ 600/6250] eta: 0:13:33 lr: 0.000087 grad: 0.0701 (0.0844) loss: 0.8395 (0.8270) time: 0.1146 data: 0.0295 max mem: 9390 +Train: [40] [ 700/6250] eta: 0:13:09 lr: 0.000087 grad: 0.0683 (0.0824) loss: 0.8344 (0.8279) time: 0.1341 data: 0.0534 max mem: 9390 +Train: [40] [ 800/6250] eta: 0:12:53 lr: 0.000087 grad: 0.0734 (0.0815) loss: 0.8291 (0.8280) time: 0.1371 data: 0.0514 max mem: 9390 +Train: [40] [ 900/6250] eta: 0:12:52 lr: 0.000087 grad: 0.0771 (0.0808) loss: 0.8230 (0.8281) time: 0.1782 data: 0.0851 max mem: 9390 +Train: [40] [1000/6250] eta: 0:12:37 lr: 0.000087 grad: 0.0743 (0.0803) loss: 0.8290 (0.8284) time: 0.1703 data: 0.0885 max mem: 9390 +Train: [40] [1100/6250] eta: 0:12:20 lr: 0.000087 grad: 0.0724 (0.0799) loss: 0.8318 (0.8284) time: 0.1481 data: 0.0623 max mem: 9390 +Train: [40] [1200/6250] eta: 0:12:06 lr: 0.000087 grad: 0.0753 (0.0796) loss: 0.8305 (0.8286) time: 0.1372 data: 0.0575 max mem: 9390 +Train: [40] [1300/6250] eta: 0:11:50 lr: 0.000087 grad: 0.0808 (0.0794) loss: 0.8260 (0.8285) time: 0.1433 data: 0.0671 max mem: 9390 +Train: [40] [1400/6250] eta: 0:11:33 lr: 0.000087 grad: 0.0757 (0.0791) loss: 0.8264 (0.8285) time: 0.1306 data: 0.0517 max mem: 9390 +Train: [40] [1500/6250] eta: 0:11:22 lr: 0.000087 grad: 0.0726 (0.0790) loss: 0.8284 (0.8285) time: 0.1893 data: 0.1060 max mem: 9390 +Train: [40] [1600/6250] eta: 0:11:07 lr: 0.000087 grad: 0.0761 (0.0791) loss: 0.8288 (0.8285) time: 0.1245 data: 0.0477 max mem: 9390 +Train: [40] [1700/6250] eta: 0:10:53 lr: 0.000087 grad: 0.0737 (0.0793) loss: 0.8281 (0.8284) time: 0.1651 data: 0.0891 max mem: 9390 +Train: [40] [1800/6250] eta: 0:10:38 lr: 0.000087 grad: 0.0747 (0.0793) loss: 0.8286 (0.8284) time: 0.1312 data: 0.0538 max mem: 9390 +Train: [40] [1900/6250] eta: 0:10:24 lr: 0.000087 grad: 0.0763 (0.0791) loss: 0.8269 (0.8284) time: 0.1437 data: 0.0674 max mem: 9390 +Train: [40] [2000/6250] eta: 0:10:09 lr: 0.000087 grad: 0.0704 (0.0790) loss: 0.8290 (0.8284) time: 0.1332 data: 0.0558 max mem: 9390 +Train: [40] [2100/6250] eta: 0:09:53 lr: 0.000087 grad: 0.0788 (0.0789) loss: 0.8276 (0.8284) time: 0.1267 data: 0.0472 max mem: 9390 +Train: [40] [2200/6250] eta: 0:09:42 lr: 0.000087 grad: 0.0738 (0.0789) loss: 0.8295 (0.8285) time: 0.1142 data: 0.0329 max mem: 9390 +Train: [40] [2300/6250] eta: 0:09:26 lr: 0.000087 grad: 0.0731 (0.0789) loss: 0.8266 (0.8283) time: 0.1654 data: 0.0704 max mem: 9390 +Train: [40] [2400/6250] eta: 0:09:13 lr: 0.000087 grad: 0.0776 (0.0789) loss: 0.8245 (0.8283) time: 0.1173 data: 0.0366 max mem: 9390 +Train: [40] [2500/6250] eta: 0:08:57 lr: 0.000087 grad: 0.0732 (0.0789) loss: 0.8223 (0.8282) time: 0.1392 data: 0.0591 max mem: 9390 +Train: [40] [2600/6250] eta: 0:08:42 lr: 0.000087 grad: 0.0757 (0.0789) loss: 0.8223 (0.8282) time: 0.1269 data: 0.0508 max mem: 9390 +Train: [40] [2700/6250] eta: 0:08:26 lr: 0.000087 grad: 0.0733 (0.0788) loss: 0.8264 (0.8282) time: 0.1193 data: 0.0426 max mem: 9390 +Train: [40] [2800/6250] eta: 0:08:15 lr: 0.000087 grad: 0.0792 (0.0788) loss: 0.8259 (0.8281) time: 0.1657 data: 0.0636 max mem: 9390 +Train: [40] [2900/6250] eta: 0:08:00 lr: 0.000087 grad: 0.0788 (0.0789) loss: 0.8255 (0.8280) time: 0.1431 data: 0.0682 max mem: 9390 +Train: [40] [3000/6250] eta: 0:07:44 lr: 0.000087 grad: 0.0793 (0.0790) loss: 0.8242 (0.8279) time: 0.1354 data: 0.0559 max mem: 9390 +Train: [40] [3100/6250] eta: 0:07:29 lr: 0.000087 grad: 0.0723 (0.0790) loss: 0.8238 (0.8278) time: 0.1410 data: 0.0647 max mem: 9390 +Train: [40] [3200/6250] eta: 0:07:14 lr: 0.000087 grad: 0.0747 (0.0791) loss: 0.8294 (0.8277) time: 0.1385 data: 0.0603 max mem: 9390 +Train: [40] [3300/6250] eta: 0:06:59 lr: 0.000087 grad: 0.0820 (0.0791) loss: 0.8201 (0.8277) time: 0.1352 data: 0.0541 max mem: 9390 +Train: [40] [3400/6250] eta: 0:06:45 lr: 0.000087 grad: 0.0742 (0.0791) loss: 0.8293 (0.8276) time: 0.1466 data: 0.0721 max mem: 9390 +Train: [40] [3500/6250] eta: 0:06:31 lr: 0.000087 grad: 0.0733 (0.0791) loss: 0.8253 (0.8275) time: 0.1880 data: 0.1040 max mem: 9390 +Train: [40] [3600/6250] eta: 0:06:17 lr: 0.000087 grad: 0.0794 (0.0791) loss: 0.8281 (0.8275) time: 0.1520 data: 0.0741 max mem: 9390 +Train: [40] [3700/6250] eta: 0:06:03 lr: 0.000086 grad: 0.0770 (0.0793) loss: 0.8261 (0.8273) time: 0.1539 data: 0.0755 max mem: 9390 +Train: [40] [3800/6250] eta: 0:05:49 lr: 0.000086 grad: 0.0800 (0.0794) loss: 0.8236 (0.8272) time: 0.1673 data: 0.0866 max mem: 9390 +Train: [40] [3900/6250] eta: 0:05:35 lr: 0.000086 grad: 0.0805 (0.0794) loss: 0.8195 (0.8271) time: 0.1508 data: 0.0730 max mem: 9390 +Train: [40] [4000/6250] eta: 0:05:21 lr: 0.000086 grad: 0.0797 (0.0796) loss: 0.8260 (0.8270) time: 0.1736 data: 0.1011 max mem: 9390 +Train: [40] [4100/6250] eta: 0:05:07 lr: 0.000086 grad: 0.0816 (0.0796) loss: 0.8182 (0.8269) time: 0.1526 data: 0.0782 max mem: 9390 +Train: [40] [4200/6250] eta: 0:04:53 lr: 0.000086 grad: 0.0750 (0.0797) loss: 0.8236 (0.8268) time: 0.1091 data: 0.0257 max mem: 9390 +Train: [40] [4300/6250] eta: 0:04:38 lr: 0.000086 grad: 0.0725 (0.0798) loss: 0.8262 (0.8267) time: 0.1325 data: 0.0554 max mem: 9390 +Train: [40] [4400/6250] eta: 0:04:23 lr: 0.000086 grad: 0.0782 (0.0798) loss: 0.8268 (0.8266) time: 0.1189 data: 0.0377 max mem: 9390 +Train: [40] [4500/6250] eta: 0:04:09 lr: 0.000086 grad: 0.0821 (0.0799) loss: 0.8242 (0.8266) time: 0.1400 data: 0.0636 max mem: 9390 +Train: [40] [4600/6250] eta: 0:03:54 lr: 0.000086 grad: 0.0799 (0.0799) loss: 0.8212 (0.8265) time: 0.1299 data: 0.0526 max mem: 9390 +Train: [40] [4700/6250] eta: 0:03:40 lr: 0.000086 grad: 0.0844 (0.0799) loss: 0.8239 (0.8265) time: 0.1525 data: 0.0717 max mem: 9390 +Train: [40] [4800/6250] eta: 0:03:26 lr: 0.000086 grad: 0.0839 (0.0800) loss: 0.8134 (0.8263) time: 0.1330 data: 0.0528 max mem: 9390 +Train: [40] [4900/6250] eta: 0:03:11 lr: 0.000086 grad: 0.0802 (0.0800) loss: 0.8262 (0.8263) time: 0.1383 data: 0.0584 max mem: 9390 +Train: [40] [5000/6250] eta: 0:02:57 lr: 0.000086 grad: 0.0778 (0.0801) loss: 0.8231 (0.8263) time: 0.1613 data: 0.0794 max mem: 9390 +Train: [40] [5100/6250] eta: 0:02:43 lr: 0.000086 grad: 0.0783 (0.0802) loss: 0.8340 (0.8263) time: 0.1610 data: 0.0789 max mem: 9390 +Train: [40] [5200/6250] eta: 0:02:28 lr: 0.000086 grad: 0.0855 (0.0802) loss: 0.8225 (0.8263) time: 0.1347 data: 0.0570 max mem: 9390 +Train: [40] [5300/6250] eta: 0:02:15 lr: 0.000086 grad: 0.0750 (0.0802) loss: 0.8339 (0.8263) time: 0.1981 data: 0.1204 max mem: 9390 +Train: [40] [5400/6250] eta: 0:02:00 lr: 0.000086 grad: 0.0864 (0.0803) loss: 0.8255 (0.8263) time: 0.1629 data: 0.0858 max mem: 9390 +Train: [40] [5500/6250] eta: 0:01:46 lr: 0.000086 grad: 0.0766 (0.0803) loss: 0.8233 (0.8263) time: 0.1297 data: 0.0494 max mem: 9390 +Train: [40] [5600/6250] eta: 0:01:32 lr: 0.000086 grad: 0.0791 (0.0803) loss: 0.8249 (0.8264) time: 0.1375 data: 0.0643 max mem: 9390 +Train: [40] [5700/6250] eta: 0:01:18 lr: 0.000086 grad: 0.0796 (0.0803) loss: 0.8225 (0.8263) time: 0.1747 data: 0.0917 max mem: 9390 +Train: [40] [5800/6250] eta: 0:01:03 lr: 0.000086 grad: 0.0753 (0.0803) loss: 0.8292 (0.8264) time: 0.1287 data: 0.0559 max mem: 9390 +Train: [40] [5900/6250] eta: 0:00:49 lr: 0.000086 grad: 0.0754 (0.0803) loss: 0.8196 (0.8264) time: 0.1485 data: 0.0701 max mem: 9390 +Train: [40] [6000/6250] eta: 0:00:35 lr: 0.000086 grad: 0.0862 (0.0803) loss: 0.8249 (0.8265) time: 0.1934 data: 0.1138 max mem: 9390 +Train: [40] [6100/6250] eta: 0:00:21 lr: 0.000086 grad: 0.0755 (0.0803) loss: 0.8254 (0.8265) time: 0.1197 data: 0.0383 max mem: 9390 +Train: [40] [6200/6250] eta: 0:00:07 lr: 0.000086 grad: 0.0777 (0.0803) loss: 0.8296 (0.8265) time: 0.1391 data: 0.0634 max mem: 9390 +Train: [40] [6249/6250] eta: 0:00:00 lr: 0.000086 grad: 0.0832 (0.0803) loss: 0.8178 (0.8265) time: 0.1242 data: 0.0446 max mem: 9390 +Train: [40] Total time: 0:14:57 (0.1435 s / it) +Averaged stats: lr: 0.000086 grad: 0.0832 (0.0803) loss: 0.8178 (0.8265) +Eval (hcp-train-subset): [40] [ 0/62] eta: 0:03:22 loss: 0.8495 (0.8495) time: 3.2605 data: 3.1970 max mem: 9390 +Eval (hcp-train-subset): [40] [61/62] eta: 0:00:00 loss: 0.8394 (0.8406) time: 0.0981 data: 0.0735 max mem: 9390 +Eval (hcp-train-subset): [40] Total time: 0:00:13 (0.2107 s / it) +Averaged stats (hcp-train-subset): loss: 0.8394 (0.8406) +Eval (hcp-val): [40] [ 0/62] eta: 0:04:31 loss: 0.8338 (0.8338) time: 4.3747 data: 4.3447 max mem: 9390 +Eval (hcp-val): [40] [61/62] eta: 0:00:00 loss: 0.8362 (0.8376) time: 0.1218 data: 0.0972 max mem: 9390 +Eval (hcp-val): [40] Total time: 0:00:12 (0.1967 s / it) +Averaged stats (hcp-val): loss: 0.8362 (0.8376) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +Train: [41] [ 0/6250] eta: 6:24:49 lr: 0.000086 grad: 0.0677 (0.0677) loss: 0.8652 (0.8652) time: 3.6943 data: 3.4765 max mem: 9390 +Train: [41] [ 100/6250] eta: 0:19:33 lr: 0.000086 grad: 0.0789 (0.0906) loss: 0.8310 (0.8377) time: 0.1444 data: 0.0555 max mem: 9390 +Train: [41] [ 200/6250] eta: 0:16:50 lr: 0.000086 grad: 0.0757 (0.0847) loss: 0.8372 (0.8339) time: 0.1539 data: 0.0691 max mem: 9390 +Train: [41] [ 300/6250] eta: 0:15:33 lr: 0.000086 grad: 0.0711 (0.0828) loss: 0.8297 (0.8327) time: 0.1342 data: 0.0438 max mem: 9390 +Train: [41] [ 400/6250] eta: 0:14:39 lr: 0.000086 grad: 0.0792 (0.0815) loss: 0.8271 (0.8320) time: 0.1178 data: 0.0245 max mem: 9390 +Train: [41] [ 500/6250] eta: 0:14:01 lr: 0.000086 grad: 0.0729 (0.0807) loss: 0.8278 (0.8318) time: 0.1334 data: 0.0524 max mem: 9390 +Train: [41] [ 600/6250] eta: 0:13:27 lr: 0.000086 grad: 0.0712 (0.0795) loss: 0.8354 (0.8320) time: 0.1235 data: 0.0379 max mem: 9390 +Train: [41] [ 700/6250] eta: 0:13:05 lr: 0.000085 grad: 0.0796 (0.0788) loss: 0.8310 (0.8322) time: 0.1400 data: 0.0568 max mem: 9390 +Train: [41] [ 800/6250] eta: 0:12:49 lr: 0.000085 grad: 0.0680 (0.0781) loss: 0.8302 (0.8324) time: 0.1284 data: 0.0421 max mem: 9390 +Train: [41] [ 900/6250] eta: 0:12:42 lr: 0.000085 grad: 0.0790 (0.0778) loss: 0.8319 (0.8322) time: 0.1712 data: 0.0912 max mem: 9390 +Train: [41] [1000/6250] eta: 0:12:43 lr: 0.000085 grad: 0.0715 (0.0778) loss: 0.8315 (0.8319) time: 0.2585 data: 0.1769 max mem: 9390 +Train: [41] [1100/6250] eta: 0:12:19 lr: 0.000085 grad: 0.0755 (0.0776) loss: 0.8276 (0.8316) time: 0.1357 data: 0.0591 max mem: 9390 +Train: [41] [1200/6250] eta: 0:12:02 lr: 0.000085 grad: 0.0708 (0.0775) loss: 0.8331 (0.8314) time: 0.1336 data: 0.0496 max mem: 9390 +Train: [41] [1300/6250] eta: 0:11:48 lr: 0.000085 grad: 0.0791 (0.0774) loss: 0.8301 (0.8312) time: 0.1318 data: 0.0511 max mem: 9390 +Train: [41] [1400/6250] eta: 0:11:35 lr: 0.000085 grad: 0.0800 (0.0776) loss: 0.8220 (0.8308) time: 0.1383 data: 0.0589 max mem: 9390 +Train: [41] [1500/6250] eta: 0:11:22 lr: 0.000085 grad: 0.0763 (0.0777) loss: 0.8222 (0.8305) time: 0.1091 data: 0.0268 max mem: 9390 +Train: [41] [1600/6250] eta: 0:11:06 lr: 0.000085 grad: 0.0709 (0.0776) loss: 0.8309 (0.8304) time: 0.1536 data: 0.0762 max mem: 9390 +Train: [41] [1700/6250] eta: 0:10:51 lr: 0.000085 grad: 0.0803 (0.0778) loss: 0.8129 (0.8300) time: 0.1702 data: 0.0847 max mem: 9390 +Train: [41] [1800/6250] eta: 0:10:37 lr: 0.000085 grad: 0.0804 (0.0778) loss: 0.8260 (0.8297) time: 0.1609 data: 0.0828 max mem: 9390 +Train: [41] [1900/6250] eta: 0:10:25 lr: 0.000085 grad: 0.0791 (0.0780) loss: 0.8270 (0.8294) time: 0.2091 data: 0.0898 max mem: 9390 +Train: [41] [2000/6250] eta: 0:10:15 lr: 0.000085 grad: 0.0812 (0.0781) loss: 0.8197 (0.8291) time: 0.1044 data: 0.0069 max mem: 9390 +Train: [41] [2100/6250] eta: 0:10:05 lr: 0.000085 grad: 0.0817 (0.0783) loss: 0.8232 (0.8288) time: 0.1921 data: 0.1121 max mem: 9390 +Train: [41] [2200/6250] eta: 0:09:48 lr: 0.000085 grad: 0.0744 (0.0784) loss: 0.8268 (0.8285) time: 0.1435 data: 0.0638 max mem: 9390 +Train: [41] [2300/6250] eta: 0:09:32 lr: 0.000085 grad: 0.0845 (0.0786) loss: 0.8180 (0.8282) time: 0.1423 data: 0.0645 max mem: 9390 +Train: [41] [2400/6250] eta: 0:09:15 lr: 0.000085 grad: 0.0808 (0.0787) loss: 0.8247 (0.8280) time: 0.1308 data: 0.0528 max mem: 9390 +Train: [41] [2500/6250] eta: 0:09:00 lr: 0.000085 grad: 0.0751 (0.0788) loss: 0.8242 (0.8279) time: 0.1323 data: 0.0513 max mem: 9390 +Train: [41] [2600/6250] eta: 0:08:45 lr: 0.000085 grad: 0.0818 (0.0788) loss: 0.8227 (0.8277) time: 0.1351 data: 0.0557 max mem: 9390 +Train: [41] [2700/6250] eta: 0:08:31 lr: 0.000085 grad: 0.0770 (0.0790) loss: 0.8214 (0.8275) time: 0.1118 data: 0.0310 max mem: 9390 +Train: [41] [2800/6250] eta: 0:08:16 lr: 0.000085 grad: 0.0797 (0.0791) loss: 0.8219 (0.8274) time: 0.1425 data: 0.0605 max mem: 9390 +Train: [41] [2900/6250] eta: 0:08:03 lr: 0.000085 grad: 0.0839 (0.0793) loss: 0.8221 (0.8273) time: 0.1558 data: 0.0817 max mem: 9390 +Train: [41] [3000/6250] eta: 0:07:49 lr: 0.000085 grad: 0.0851 (0.0794) loss: 0.8263 (0.8271) time: 0.1797 data: 0.0998 max mem: 9390 +Train: [41] [3100/6250] eta: 0:07:34 lr: 0.000085 grad: 0.0813 (0.0796) loss: 0.8216 (0.8270) time: 0.1500 data: 0.0742 max mem: 9390 +Train: [41] [3200/6250] eta: 0:07:19 lr: 0.000085 grad: 0.0823 (0.0798) loss: 0.8239 (0.8268) time: 0.1314 data: 0.0468 max mem: 9390 +Train: [41] [3300/6250] eta: 0:07:06 lr: 0.000085 grad: 0.0752 (0.0799) loss: 0.8223 (0.8267) time: 0.1691 data: 0.0744 max mem: 9390 +Train: [41] [3400/6250] eta: 0:06:51 lr: 0.000085 grad: 0.0792 (0.0800) loss: 0.8294 (0.8266) time: 0.1446 data: 0.0690 max mem: 9390 +Train: [41] [3500/6250] eta: 0:06:36 lr: 0.000085 grad: 0.0797 (0.0801) loss: 0.8218 (0.8265) time: 0.1286 data: 0.0484 max mem: 9390 +Train: [41] [3600/6250] eta: 0:06:23 lr: 0.000085 grad: 0.0777 (0.0802) loss: 0.8230 (0.8264) time: 0.1560 data: 0.0714 max mem: 9390 +Train: [41] [3700/6250] eta: 0:06:09 lr: 0.000085 grad: 0.0861 (0.0803) loss: 0.8195 (0.8263) time: 0.1073 data: 0.0286 max mem: 9390 +Train: [41] [3800/6250] eta: 0:05:55 lr: 0.000085 grad: 0.0824 (0.0804) loss: 0.8213 (0.8263) time: 0.1501 data: 0.0705 max mem: 9390 +Train: [41] [3900/6250] eta: 0:05:42 lr: 0.000084 grad: 0.0854 (0.0805) loss: 0.8146 (0.8261) time: 0.1490 data: 0.0658 max mem: 9390 +Train: [41] [4000/6250] eta: 0:05:28 lr: 0.000084 grad: 0.0781 (0.0805) loss: 0.8312 (0.8261) time: 0.1587 data: 0.0844 max mem: 9390 +Train: [41] [4100/6250] eta: 0:05:13 lr: 0.000084 grad: 0.0813 (0.0805) loss: 0.8215 (0.8260) time: 0.1348 data: 0.0518 max mem: 9390 +Train: [41] [4200/6250] eta: 0:04:58 lr: 0.000084 grad: 0.0824 (0.0805) loss: 0.8206 (0.8260) time: 0.1343 data: 0.0570 max mem: 9390 +Train: [41] [4300/6250] eta: 0:04:43 lr: 0.000084 grad: 0.0786 (0.0806) loss: 0.8266 (0.8259) time: 0.1285 data: 0.0457 max mem: 9390 +Train: [41] [4400/6250] eta: 0:04:29 lr: 0.000084 grad: 0.0770 (0.0806) loss: 0.8257 (0.8259) time: 0.1473 data: 0.0522 max mem: 9390 +Train: [41] [4500/6250] eta: 0:04:14 lr: 0.000084 grad: 0.0804 (0.0806) loss: 0.8250 (0.8258) time: 0.1550 data: 0.0758 max mem: 9390 +Train: [41] [4600/6250] eta: 0:03:59 lr: 0.000084 grad: 0.0790 (0.0806) loss: 0.8193 (0.8258) time: 0.1108 data: 0.0360 max mem: 9390 +Train: [41] [4700/6250] eta: 0:03:44 lr: 0.000084 grad: 0.0814 (0.0806) loss: 0.8248 (0.8257) time: 0.1130 data: 0.0350 max mem: 9390 +Train: [41] [4800/6250] eta: 0:03:29 lr: 0.000084 grad: 0.0743 (0.0807) loss: 0.8292 (0.8256) time: 0.1147 data: 0.0309 max mem: 9390 +Train: [41] [4900/6250] eta: 0:03:15 lr: 0.000084 grad: 0.0845 (0.0807) loss: 0.8166 (0.8256) time: 0.1496 data: 0.0751 max mem: 9390 +Train: [41] [5000/6250] eta: 0:03:00 lr: 0.000084 grad: 0.0865 (0.0808) loss: 0.8217 (0.8255) time: 0.1612 data: 0.0614 max mem: 9390 +Train: [41] [5100/6250] eta: 0:02:47 lr: 0.000084 grad: 0.0761 (0.0808) loss: 0.8250 (0.8255) time: 0.1705 data: 0.0906 max mem: 9390 +Train: [41] [5200/6250] eta: 0:02:32 lr: 0.000084 grad: 0.0751 (0.0808) loss: 0.8258 (0.8255) time: 0.1376 data: 0.0578 max mem: 9390 +Train: [41] [5300/6250] eta: 0:02:17 lr: 0.000084 grad: 0.0795 (0.0808) loss: 0.8187 (0.8255) time: 0.1512 data: 0.0731 max mem: 9390 +Train: [41] [5400/6250] eta: 0:02:03 lr: 0.000084 grad: 0.0750 (0.0808) loss: 0.8306 (0.8255) time: 0.1412 data: 0.0628 max mem: 9390 +Train: [41] [5500/6250] eta: 0:01:48 lr: 0.000084 grad: 0.0768 (0.0808) loss: 0.8257 (0.8255) time: 0.1432 data: 0.0666 max mem: 9390 +Train: [41] [5600/6250] eta: 0:01:34 lr: 0.000084 grad: 0.0874 (0.0808) loss: 0.8199 (0.8255) time: 0.1512 data: 0.0714 max mem: 9390 +Train: [41] [5700/6250] eta: 0:01:19 lr: 0.000084 grad: 0.0822 (0.0808) loss: 0.8217 (0.8254) time: 0.1376 data: 0.0615 max mem: 9390 +Train: [41] [5800/6250] eta: 0:01:05 lr: 0.000084 grad: 0.0763 (0.0808) loss: 0.8286 (0.8254) time: 0.1347 data: 0.0501 max mem: 9390 +Train: [41] [5900/6250] eta: 0:00:50 lr: 0.000084 grad: 0.0807 (0.0808) loss: 0.8212 (0.8254) time: 0.1311 data: 0.0527 max mem: 9390 +Train: [41] [6000/6250] eta: 0:00:36 lr: 0.000084 grad: 0.0788 (0.0809) loss: 0.8261 (0.8254) time: 0.1462 data: 0.0635 max mem: 9390 +Train: [41] [6100/6250] eta: 0:00:21 lr: 0.000084 grad: 0.0845 (0.0809) loss: 0.8248 (0.8254) time: 0.1365 data: 0.0568 max mem: 9390 +Train: [41] [6200/6250] eta: 0:00:07 lr: 0.000084 grad: 0.0793 (0.0809) loss: 0.8201 (0.8253) time: 0.1510 data: 0.0711 max mem: 9390 +Train: [41] [6249/6250] eta: 0:00:00 lr: 0.000084 grad: 0.0835 (0.0810) loss: 0.8238 (0.8253) time: 0.1380 data: 0.0609 max mem: 9390 +Train: [41] Total time: 0:15:12 (0.1460 s / it) +Averaged stats: lr: 0.000084 grad: 0.0835 (0.0810) loss: 0.8238 (0.8253) +Eval (hcp-train-subset): [41] [ 0/62] eta: 0:05:21 loss: 0.8519 (0.8519) time: 5.1911 data: 5.1280 max mem: 9390 +Eval (hcp-train-subset): [41] [61/62] eta: 0:00:00 loss: 0.8395 (0.8404) time: 0.1131 data: 0.0884 max mem: 9390 +Eval (hcp-train-subset): [41] Total time: 0:00:12 (0.2078 s / it) +Averaged stats (hcp-train-subset): loss: 0.8395 (0.8404) +Eval (hcp-val): [41] [ 0/62] eta: 0:04:03 loss: 0.8353 (0.8353) time: 3.9231 data: 3.8341 max mem: 9390 +Eval (hcp-val): [41] [61/62] eta: 0:00:00 loss: 0.8357 (0.8374) time: 0.1092 data: 0.0829 max mem: 9390 +Eval (hcp-val): [41] Total time: 0:00:12 (0.1940 s / it) +Averaged stats (hcp-val): loss: 0.8357 (0.8374) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +Train: [42] [ 0/6250] eta: 9:17:57 lr: 0.000084 grad: 0.0578 (0.0578) loss: 0.8626 (0.8626) time: 5.3565 data: 5.2199 max mem: 9390 +Train: [42] [ 100/6250] eta: 0:20:09 lr: 0.000084 grad: 0.0707 (0.0797) loss: 0.8416 (0.8443) time: 0.1743 data: 0.0775 max mem: 9390 +Train: [42] [ 200/6250] eta: 0:17:04 lr: 0.000084 grad: 0.0718 (0.0778) loss: 0.8340 (0.8382) time: 0.1362 data: 0.0484 max mem: 9390 +Train: [42] [ 300/6250] eta: 0:15:43 lr: 0.000084 grad: 0.0743 (0.0779) loss: 0.8331 (0.8354) time: 0.1343 data: 0.0439 max mem: 9390 +Train: [42] [ 400/6250] eta: 0:14:53 lr: 0.000084 grad: 0.0761 (0.0773) loss: 0.8315 (0.8344) time: 0.1389 data: 0.0482 max mem: 9390 +Train: [42] [ 500/6250] eta: 0:14:16 lr: 0.000084 grad: 0.0778 (0.0773) loss: 0.8261 (0.8334) time: 0.1448 data: 0.0612 max mem: 9390 +Train: [42] [ 600/6250] eta: 0:13:46 lr: 0.000084 grad: 0.0743 (0.0782) loss: 0.8270 (0.8324) time: 0.1358 data: 0.0492 max mem: 9390 +Train: [42] [ 700/6250] eta: 0:13:28 lr: 0.000084 grad: 0.0741 (0.0783) loss: 0.8300 (0.8315) time: 0.1376 data: 0.0570 max mem: 9390 +Train: [42] [ 800/6250] eta: 0:13:27 lr: 0.000084 grad: 0.0743 (0.0780) loss: 0.8299 (0.8309) time: 0.1432 data: 0.0544 max mem: 9390 +Train: [42] [ 900/6250] eta: 0:13:17 lr: 0.000083 grad: 0.0722 (0.0779) loss: 0.8243 (0.8303) time: 0.1637 data: 0.0885 max mem: 9390 +Train: [42] [1000/6250] eta: 0:13:00 lr: 0.000083 grad: 0.0761 (0.0778) loss: 0.8193 (0.8297) time: 0.1504 data: 0.0724 max mem: 9390 +Train: [42] [1100/6250] eta: 0:12:43 lr: 0.000083 grad: 0.0741 (0.0779) loss: 0.8198 (0.8293) time: 0.1652 data: 0.0839 max mem: 9390 +Train: [42] [1200/6250] eta: 0:12:33 lr: 0.000083 grad: 0.0719 (0.0780) loss: 0.8222 (0.8289) time: 0.1590 data: 0.0797 max mem: 9390 +Train: [42] [1300/6250] eta: 0:12:15 lr: 0.000083 grad: 0.0754 (0.0781) loss: 0.8263 (0.8285) time: 0.1407 data: 0.0645 max mem: 9390 +Train: [42] [1400/6250] eta: 0:11:56 lr: 0.000083 grad: 0.0755 (0.0783) loss: 0.8219 (0.8282) time: 0.1431 data: 0.0653 max mem: 9390 +Train: [42] [1500/6250] eta: 0:11:39 lr: 0.000083 grad: 0.0759 (0.0784) loss: 0.8296 (0.8280) time: 0.1267 data: 0.0401 max mem: 9390 +Train: [42] [1600/6250] eta: 0:11:22 lr: 0.000083 grad: 0.0748 (0.0786) loss: 0.8332 (0.8277) time: 0.1593 data: 0.0738 max mem: 9390 +Train: [42] [1700/6250] eta: 0:11:06 lr: 0.000083 grad: 0.0831 (0.0787) loss: 0.8200 (0.8274) time: 0.1439 data: 0.0677 max mem: 9390 +Train: [42] [1800/6250] eta: 0:10:59 lr: 0.000083 grad: 0.0813 (0.0788) loss: 0.8267 (0.8272) time: 0.2295 data: 0.1368 max mem: 9390 +Train: [42] [1900/6250] eta: 0:10:45 lr: 0.000083 grad: 0.0818 (0.0789) loss: 0.8294 (0.8271) time: 0.1419 data: 0.0635 max mem: 9390 +Train: [42] [2000/6250] eta: 0:10:29 lr: 0.000083 grad: 0.0778 (0.0790) loss: 0.8256 (0.8270) time: 0.1266 data: 0.0528 max mem: 9390 +Train: [42] [2100/6250] eta: 0:10:13 lr: 0.000083 grad: 0.0885 (0.0792) loss: 0.8196 (0.8269) time: 0.1344 data: 0.0482 max mem: 9390 +Train: [42] [2200/6250] eta: 0:09:57 lr: 0.000083 grad: 0.0784 (0.0792) loss: 0.8307 (0.8268) time: 0.1221 data: 0.0443 max mem: 9390 +Train: [42] [2300/6250] eta: 0:09:40 lr: 0.000083 grad: 0.0817 (0.0794) loss: 0.8241 (0.8267) time: 0.1427 data: 0.0635 max mem: 9390 +Train: [42] [2400/6250] eta: 0:09:27 lr: 0.000083 grad: 0.0788 (0.0795) loss: 0.8240 (0.8266) time: 0.1401 data: 0.0525 max mem: 9390 +Train: [42] [2500/6250] eta: 0:09:12 lr: 0.000083 grad: 0.0777 (0.0795) loss: 0.8273 (0.8265) time: 0.1023 data: 0.0223 max mem: 9390 +Train: [42] [2600/6250] eta: 0:08:56 lr: 0.000083 grad: 0.0842 (0.0796) loss: 0.8277 (0.8264) time: 0.1362 data: 0.0576 max mem: 9390 +Train: [42] [2700/6250] eta: 0:08:42 lr: 0.000083 grad: 0.0735 (0.0796) loss: 0.8293 (0.8264) time: 0.1119 data: 0.0387 max mem: 9390 +Train: [42] [2800/6250] eta: 0:08:26 lr: 0.000083 grad: 0.0743 (0.0798) loss: 0.8310 (0.8264) time: 0.1259 data: 0.0461 max mem: 9390 +Train: [42] [2900/6250] eta: 0:08:10 lr: 0.000083 grad: 0.0816 (0.0799) loss: 0.8233 (0.8264) time: 0.1496 data: 0.0706 max mem: 9390 +Train: [42] [3000/6250] eta: 0:07:58 lr: 0.000083 grad: 0.0783 (0.0799) loss: 0.8309 (0.8265) time: 0.1923 data: 0.1020 max mem: 9390 +Train: [42] [3100/6250] eta: 0:07:45 lr: 0.000083 grad: 0.0815 (0.0799) loss: 0.8259 (0.8265) time: 0.1312 data: 0.0545 max mem: 9390 +Train: [42] [3200/6250] eta: 0:07:29 lr: 0.000083 grad: 0.0745 (0.0799) loss: 0.8293 (0.8265) time: 0.1394 data: 0.0619 max mem: 9390 +Train: [42] [3300/6250] eta: 0:07:14 lr: 0.000083 grad: 0.0806 (0.0799) loss: 0.8256 (0.8265) time: 0.1469 data: 0.0706 max mem: 9390 +Train: [42] [3400/6250] eta: 0:06:59 lr: 0.000083 grad: 0.0768 (0.0799) loss: 0.8234 (0.8265) time: 0.1090 data: 0.0223 max mem: 9390 +Train: [42] [3500/6250] eta: 0:06:44 lr: 0.000083 grad: 0.0777 (0.0799) loss: 0.8284 (0.8265) time: 0.1450 data: 0.0644 max mem: 9390 +Train: [42] [3600/6250] eta: 0:06:30 lr: 0.000083 grad: 0.0760 (0.0800) loss: 0.8215 (0.8265) time: 0.1681 data: 0.0857 max mem: 9390 +Train: [42] [3700/6250] eta: 0:06:15 lr: 0.000083 grad: 0.0804 (0.0800) loss: 0.8277 (0.8264) time: 0.1331 data: 0.0558 max mem: 9390 +Train: [42] [3800/6250] eta: 0:06:01 lr: 0.000083 grad: 0.0775 (0.0801) loss: 0.8151 (0.8263) time: 0.1786 data: 0.0935 max mem: 9390 +Train: [42] [3900/6250] eta: 0:05:46 lr: 0.000083 grad: 0.0705 (0.0801) loss: 0.8224 (0.8263) time: 0.1517 data: 0.0695 max mem: 9390 +Train: [42] [4000/6250] eta: 0:05:31 lr: 0.000083 grad: 0.0748 (0.0801) loss: 0.8292 (0.8263) time: 0.1481 data: 0.0716 max mem: 9390 +Train: [42] [4100/6250] eta: 0:05:17 lr: 0.000082 grad: 0.0773 (0.0801) loss: 0.8271 (0.8263) time: 0.1459 data: 0.0638 max mem: 9390 +Train: [42] [4200/6250] eta: 0:05:02 lr: 0.000082 grad: 0.0891 (0.0802) loss: 0.8228 (0.8262) time: 0.1434 data: 0.0544 max mem: 9390 +Train: [42] [4300/6250] eta: 0:04:47 lr: 0.000082 grad: 0.0714 (0.0802) loss: 0.8314 (0.8262) time: 0.1404 data: 0.0607 max mem: 9390 +Train: [42] [4400/6250] eta: 0:04:32 lr: 0.000082 grad: 0.0764 (0.0803) loss: 0.8210 (0.8261) time: 0.1340 data: 0.0552 max mem: 9390 +Train: [42] [4500/6250] eta: 0:04:17 lr: 0.000082 grad: 0.0769 (0.0803) loss: 0.8214 (0.8261) time: 0.1466 data: 0.0683 max mem: 9390 +Train: [42] [4600/6250] eta: 0:04:02 lr: 0.000082 grad: 0.0785 (0.0803) loss: 0.8209 (0.8260) time: 0.1650 data: 0.0788 max mem: 9390 +Train: [42] [4700/6250] eta: 0:03:47 lr: 0.000082 grad: 0.0746 (0.0803) loss: 0.8276 (0.8259) time: 0.1410 data: 0.0602 max mem: 9390 +Train: [42] [4800/6250] eta: 0:03:33 lr: 0.000082 grad: 0.0798 (0.0804) loss: 0.8223 (0.8259) time: 0.1269 data: 0.0478 max mem: 9390 +Train: [42] [4900/6250] eta: 0:03:18 lr: 0.000082 grad: 0.0829 (0.0804) loss: 0.8239 (0.8259) time: 0.1478 data: 0.0620 max mem: 9390 +Train: [42] [5000/6250] eta: 0:03:03 lr: 0.000082 grad: 0.0805 (0.0805) loss: 0.8216 (0.8258) time: 0.1401 data: 0.0590 max mem: 9390 +Train: [42] [5100/6250] eta: 0:02:48 lr: 0.000082 grad: 0.0791 (0.0805) loss: 0.8266 (0.8257) time: 0.1602 data: 0.0675 max mem: 9390 +Train: [42] [5200/6250] eta: 0:02:33 lr: 0.000082 grad: 0.0834 (0.0806) loss: 0.8181 (0.8257) time: 0.1348 data: 0.0497 max mem: 9390 +Train: [42] [5300/6250] eta: 0:02:19 lr: 0.000082 grad: 0.0763 (0.0806) loss: 0.8245 (0.8256) time: 0.1410 data: 0.0447 max mem: 9390 +Train: [42] [5400/6250] eta: 0:02:04 lr: 0.000082 grad: 0.0815 (0.0807) loss: 0.8272 (0.8256) time: 0.1513 data: 0.0603 max mem: 9390 +Train: [42] [5500/6250] eta: 0:01:49 lr: 0.000082 grad: 0.0722 (0.0807) loss: 0.8326 (0.8256) time: 0.1370 data: 0.0558 max mem: 9390 +Train: [42] [5600/6250] eta: 0:01:34 lr: 0.000082 grad: 0.0778 (0.0808) loss: 0.8240 (0.8256) time: 0.1486 data: 0.0678 max mem: 9390 +Train: [42] [5700/6250] eta: 0:01:20 lr: 0.000082 grad: 0.0786 (0.0808) loss: 0.8213 (0.8256) time: 0.1325 data: 0.0483 max mem: 9390 +Train: [42] [5800/6250] eta: 0:01:05 lr: 0.000082 grad: 0.0762 (0.0808) loss: 0.8265 (0.8255) time: 0.1574 data: 0.0789 max mem: 9390 +Train: [42] [5900/6250] eta: 0:00:51 lr: 0.000082 grad: 0.0810 (0.0808) loss: 0.8294 (0.8256) time: 0.1573 data: 0.0757 max mem: 9390 +Train: [42] [6000/6250] eta: 0:00:36 lr: 0.000082 grad: 0.0805 (0.0809) loss: 0.8209 (0.8255) time: 0.1620 data: 0.0824 max mem: 9390 +Train: [42] [6100/6250] eta: 0:00:21 lr: 0.000082 grad: 0.0820 (0.0810) loss: 0.8235 (0.8255) time: 0.1891 data: 0.0980 max mem: 9390 +Train: [42] [6200/6250] eta: 0:00:07 lr: 0.000082 grad: 0.0827 (0.0810) loss: 0.8240 (0.8255) time: 0.1536 data: 0.0741 max mem: 9390 +Train: [42] [6249/6250] eta: 0:00:00 lr: 0.000082 grad: 0.0833 (0.0811) loss: 0.8275 (0.8255) time: 0.1358 data: 0.0512 max mem: 9390 +Train: [42] Total time: 0:15:19 (0.1472 s / it) +Averaged stats: lr: 0.000082 grad: 0.0833 (0.0811) loss: 0.8275 (0.8255) +Eval (hcp-train-subset): [42] [ 0/62] eta: 0:03:19 loss: 0.8530 (0.8530) time: 3.2244 data: 3.1299 max mem: 9390 +Eval (hcp-train-subset): [42] [61/62] eta: 0:00:00 loss: 0.8379 (0.8389) time: 0.1157 data: 0.0906 max mem: 9390 +Eval (hcp-train-subset): [42] Total time: 0:00:12 (0.2077 s / it) +Averaged stats (hcp-train-subset): loss: 0.8379 (0.8389) +Eval (hcp-val): [42] [ 0/62] eta: 0:03:58 loss: 0.8368 (0.8368) time: 3.8421 data: 3.7705 max mem: 9390 +Eval (hcp-val): [42] [61/62] eta: 0:00:00 loss: 0.8346 (0.8369) time: 0.1159 data: 0.0908 max mem: 9390 +Eval (hcp-val): [42] Total time: 0:00:11 (0.1913 s / it) +Averaged stats (hcp-val): loss: 0.8346 (0.8369) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +Train: [43] [ 0/6250] eta: 7:21:23 lr: 0.000082 grad: 0.0501 (0.0501) loss: 0.8739 (0.8739) time: 4.2373 data: 4.0748 max mem: 9390 +Train: [43] [ 100/6250] eta: 0:18:57 lr: 0.000082 grad: 0.0747 (0.0961) loss: 0.8316 (0.8306) time: 0.1517 data: 0.0635 max mem: 9390 +Train: [43] [ 200/6250] eta: 0:16:03 lr: 0.000082 grad: 0.0889 (0.0924) loss: 0.8237 (0.8294) time: 0.1363 data: 0.0535 max mem: 9390 +Train: [43] [ 300/6250] eta: 0:14:52 lr: 0.000082 grad: 0.0827 (0.0899) loss: 0.8323 (0.8292) time: 0.1255 data: 0.0383 max mem: 9390 +Train: [43] [ 400/6250] eta: 0:14:16 lr: 0.000082 grad: 0.0811 (0.0873) loss: 0.8243 (0.8287) time: 0.1378 data: 0.0523 max mem: 9390 +Train: [43] [ 500/6250] eta: 0:13:42 lr: 0.000082 grad: 0.0817 (0.0857) loss: 0.8234 (0.8281) time: 0.1305 data: 0.0419 max mem: 9390 +Train: [43] [ 600/6250] eta: 0:13:18 lr: 0.000082 grad: 0.0774 (0.0845) loss: 0.8347 (0.8283) time: 0.1484 data: 0.0668 max mem: 9390 +Train: [43] [ 700/6250] eta: 0:13:04 lr: 0.000082 grad: 0.0744 (0.0835) loss: 0.8338 (0.8285) time: 0.1421 data: 0.0619 max mem: 9390 +Train: [43] [ 800/6250] eta: 0:13:03 lr: 0.000082 grad: 0.0719 (0.0824) loss: 0.8300 (0.8287) time: 0.1621 data: 0.0836 max mem: 9390 +Train: [43] [ 900/6250] eta: 0:12:48 lr: 0.000082 grad: 0.0729 (0.0818) loss: 0.8334 (0.8288) time: 0.1397 data: 0.0508 max mem: 9390 +Train: [43] [1000/6250] eta: 0:12:32 lr: 0.000081 grad: 0.0755 (0.0814) loss: 0.8227 (0.8288) time: 0.1400 data: 0.0632 max mem: 9390 +Train: [43] [1100/6250] eta: 0:12:21 lr: 0.000081 grad: 0.0762 (0.0811) loss: 0.8308 (0.8289) time: 0.1319 data: 0.0469 max mem: 9390 +Train: [43] [1200/6250] eta: 0:12:08 lr: 0.000081 grad: 0.0782 (0.0808) loss: 0.8222 (0.8288) time: 0.1401 data: 0.0639 max mem: 9390 +Train: [43] [1300/6250] eta: 0:11:52 lr: 0.000081 grad: 0.0773 (0.0805) loss: 0.8274 (0.8288) time: 0.1361 data: 0.0557 max mem: 9390 +Train: [43] [1400/6250] eta: 0:11:35 lr: 0.000081 grad: 0.0744 (0.0803) loss: 0.8236 (0.8288) time: 0.1254 data: 0.0429 max mem: 9390 +Train: [43] [1500/6250] eta: 0:11:18 lr: 0.000081 grad: 0.0797 (0.0803) loss: 0.8287 (0.8287) time: 0.1293 data: 0.0513 max mem: 9390 +Train: [43] [1600/6250] eta: 0:11:03 lr: 0.000081 grad: 0.0776 (0.0803) loss: 0.8280 (0.8286) time: 0.1561 data: 0.0660 max mem: 9390 +Train: [43] [1700/6250] eta: 0:10:49 lr: 0.000081 grad: 0.0798 (0.0804) loss: 0.8242 (0.8284) time: 0.1399 data: 0.0548 max mem: 9390 +Train: [43] [1800/6250] eta: 0:10:38 lr: 0.000081 grad: 0.0788 (0.0803) loss: 0.8241 (0.8284) time: 0.1485 data: 0.0685 max mem: 9390 +Train: [43] [1900/6250] eta: 0:10:24 lr: 0.000081 grad: 0.0823 (0.0803) loss: 0.8260 (0.8283) time: 0.1538 data: 0.0613 max mem: 9390 +Train: [43] [2000/6250] eta: 0:10:09 lr: 0.000081 grad: 0.0770 (0.0803) loss: 0.8259 (0.8282) time: 0.1417 data: 0.0629 max mem: 9390 +Train: [43] [2100/6250] eta: 0:09:55 lr: 0.000081 grad: 0.0823 (0.0804) loss: 0.8205 (0.8280) time: 0.1511 data: 0.0705 max mem: 9390 +Train: [43] [2200/6250] eta: 0:09:40 lr: 0.000081 grad: 0.0802 (0.0804) loss: 0.8223 (0.8277) time: 0.1285 data: 0.0482 max mem: 9390 +Train: [43] [2300/6250] eta: 0:09:31 lr: 0.000081 grad: 0.0779 (0.0804) loss: 0.8202 (0.8275) time: 0.2367 data: 0.1390 max mem: 9390 +Train: [43] [2400/6250] eta: 0:09:14 lr: 0.000081 grad: 0.0767 (0.0805) loss: 0.8228 (0.8274) time: 0.1251 data: 0.0461 max mem: 9390 +Train: [43] [2500/6250] eta: 0:08:59 lr: 0.000081 grad: 0.0804 (0.0805) loss: 0.8201 (0.8271) time: 0.1217 data: 0.0365 max mem: 9390 +Train: [43] [2600/6250] eta: 0:08:44 lr: 0.000081 grad: 0.0788 (0.0805) loss: 0.8258 (0.8270) time: 0.1534 data: 0.0699 max mem: 9390 +Train: [43] [2700/6250] eta: 0:08:28 lr: 0.000081 grad: 0.0822 (0.0806) loss: 0.8247 (0.8269) time: 0.1434 data: 0.0654 max mem: 9390 +Train: [43] [2800/6250] eta: 0:08:14 lr: 0.000081 grad: 0.0810 (0.0807) loss: 0.8248 (0.8267) time: 0.1361 data: 0.0569 max mem: 9390 +Train: [43] [2900/6250] eta: 0:07:59 lr: 0.000081 grad: 0.0788 (0.0808) loss: 0.8148 (0.8266) time: 0.1484 data: 0.0713 max mem: 9390 +Train: [43] [3000/6250] eta: 0:07:46 lr: 0.000081 grad: 0.0870 (0.0809) loss: 0.8213 (0.8264) time: 0.1393 data: 0.0519 max mem: 9390 +Train: [43] [3100/6250] eta: 0:07:33 lr: 0.000081 grad: 0.0849 (0.0811) loss: 0.8189 (0.8261) time: 0.1212 data: 0.0237 max mem: 9390 +Train: [43] [3200/6250] eta: 0:07:18 lr: 0.000081 grad: 0.0849 (0.0811) loss: 0.8164 (0.8259) time: 0.1258 data: 0.0369 max mem: 9390 +Train: [43] [3300/6250] eta: 0:07:06 lr: 0.000081 grad: 0.0855 (0.0813) loss: 0.8149 (0.8257) time: 0.1631 data: 0.0813 max mem: 9390 +Train: [43] [3400/6250] eta: 0:06:50 lr: 0.000081 grad: 0.0841 (0.0815) loss: 0.8134 (0.8254) time: 0.1292 data: 0.0512 max mem: 9390 +Train: [43] [3500/6250] eta: 0:06:35 lr: 0.000081 grad: 0.0819 (0.0818) loss: 0.8198 (0.8252) time: 0.1336 data: 0.0516 max mem: 9390 +Train: [43] [3600/6250] eta: 0:06:20 lr: 0.000081 grad: 0.0856 (0.0820) loss: 0.8196 (0.8250) time: 0.1277 data: 0.0507 max mem: 9390 +Train: [43] [3700/6250] eta: 0:06:05 lr: 0.000081 grad: 0.0894 (0.0821) loss: 0.8198 (0.8248) time: 0.1357 data: 0.0578 max mem: 9390 +Train: [43] [3800/6250] eta: 0:05:51 lr: 0.000081 grad: 0.0838 (0.0823) loss: 0.8249 (0.8246) time: 0.1224 data: 0.0373 max mem: 9390 +Train: [43] [3900/6250] eta: 0:05:36 lr: 0.000081 grad: 0.0837 (0.0824) loss: 0.8143 (0.8244) time: 0.1334 data: 0.0349 max mem: 9390 +Train: [43] [4000/6250] eta: 0:05:22 lr: 0.000081 grad: 0.0897 (0.0826) loss: 0.8150 (0.8243) time: 0.1619 data: 0.0722 max mem: 9390 +Train: [43] [4100/6250] eta: 0:05:08 lr: 0.000081 grad: 0.0823 (0.0827) loss: 0.8190 (0.8242) time: 0.1447 data: 0.0683 max mem: 9390 +Train: [43] [4200/6250] eta: 0:04:53 lr: 0.000080 grad: 0.0834 (0.0828) loss: 0.8214 (0.8241) time: 0.1603 data: 0.0728 max mem: 9390 +Train: [43] [4300/6250] eta: 0:04:39 lr: 0.000080 grad: 0.0864 (0.0828) loss: 0.8233 (0.8240) time: 0.1380 data: 0.0586 max mem: 9390 +Train: [43] [4400/6250] eta: 0:04:24 lr: 0.000080 grad: 0.0854 (0.0829) loss: 0.8164 (0.8240) time: 0.1206 data: 0.0403 max mem: 9390 +Train: [43] [4500/6250] eta: 0:04:10 lr: 0.000080 grad: 0.0852 (0.0830) loss: 0.8202 (0.8238) time: 0.1606 data: 0.0781 max mem: 9390 +Train: [43] [4600/6250] eta: 0:03:56 lr: 0.000080 grad: 0.0882 (0.0831) loss: 0.8224 (0.8238) time: 0.1486 data: 0.0602 max mem: 9390 +Train: [43] [4700/6250] eta: 0:03:41 lr: 0.000080 grad: 0.0810 (0.0831) loss: 0.8221 (0.8238) time: 0.1444 data: 0.0643 max mem: 9390 +Train: [43] [4800/6250] eta: 0:03:27 lr: 0.000080 grad: 0.0810 (0.0831) loss: 0.8158 (0.8237) time: 0.1386 data: 0.0581 max mem: 9390 +Train: [43] [4900/6250] eta: 0:03:13 lr: 0.000080 grad: 0.0793 (0.0832) loss: 0.8236 (0.8237) time: 0.1360 data: 0.0543 max mem: 9390 +Train: [43] [5000/6250] eta: 0:02:58 lr: 0.000080 grad: 0.0840 (0.0831) loss: 0.8260 (0.8237) time: 0.1221 data: 0.0401 max mem: 9390 +Train: [43] [5100/6250] eta: 0:02:44 lr: 0.000080 grad: 0.0824 (0.0832) loss: 0.8204 (0.8237) time: 0.1486 data: 0.0742 max mem: 9390 +Train: [43] [5200/6250] eta: 0:02:30 lr: 0.000080 grad: 0.0813 (0.0832) loss: 0.8160 (0.8237) time: 0.1817 data: 0.1029 max mem: 9390 +Train: [43] [5300/6250] eta: 0:02:16 lr: 0.000080 grad: 0.0818 (0.0832) loss: 0.8220 (0.8237) time: 0.1403 data: 0.0600 max mem: 9390 +Train: [43] [5400/6250] eta: 0:02:01 lr: 0.000080 grad: 0.0821 (0.0832) loss: 0.8219 (0.8236) time: 0.1473 data: 0.0700 max mem: 9390 +Train: [43] [5500/6250] eta: 0:01:47 lr: 0.000080 grad: 0.0788 (0.0832) loss: 0.8170 (0.8235) time: 0.1612 data: 0.0662 max mem: 9390 +Train: [43] [5600/6250] eta: 0:01:33 lr: 0.000080 grad: 0.0865 (0.0833) loss: 0.8175 (0.8235) time: 0.1508 data: 0.0626 max mem: 9390 +Train: [43] [5700/6250] eta: 0:01:18 lr: 0.000080 grad: 0.0754 (0.0833) loss: 0.8279 (0.8235) time: 0.1180 data: 0.0332 max mem: 9390 +Train: [43] [5800/6250] eta: 0:01:04 lr: 0.000080 grad: 0.0840 (0.0833) loss: 0.8221 (0.8235) time: 0.1741 data: 0.0969 max mem: 9390 +Train: [43] [5900/6250] eta: 0:00:50 lr: 0.000080 grad: 0.0860 (0.0833) loss: 0.8185 (0.8234) time: 0.1531 data: 0.0730 max mem: 9390 +Train: [43] [6000/6250] eta: 0:00:35 lr: 0.000080 grad: 0.0818 (0.0833) loss: 0.8285 (0.8235) time: 0.1257 data: 0.0487 max mem: 9390 +Train: [43] [6100/6250] eta: 0:00:21 lr: 0.000080 grad: 0.0794 (0.0833) loss: 0.8236 (0.8234) time: 0.1395 data: 0.0572 max mem: 9390 +Train: [43] [6200/6250] eta: 0:00:07 lr: 0.000080 grad: 0.0770 (0.0833) loss: 0.8228 (0.8235) time: 0.1468 data: 0.0654 max mem: 9390 +Train: [43] [6249/6250] eta: 0:00:00 lr: 0.000080 grad: 0.0801 (0.0833) loss: 0.8258 (0.8235) time: 0.1307 data: 0.0479 max mem: 9390 +Train: [43] Total time: 0:15:01 (0.1442 s / it) +Averaged stats: lr: 0.000080 grad: 0.0801 (0.0833) loss: 0.8258 (0.8235) +Eval (hcp-train-subset): [43] [ 0/62] eta: 0:03:13 loss: 0.8493 (0.8493) time: 3.1235 data: 3.0581 max mem: 9390 +Eval (hcp-train-subset): [43] [61/62] eta: 0:00:00 loss: 0.8358 (0.8384) time: 0.0961 data: 0.0713 max mem: 9390 +Eval (hcp-train-subset): [43] Total time: 0:00:11 (0.1878 s / it) +Averaged stats (hcp-train-subset): loss: 0.8358 (0.8384) +Eval (hcp-val): [43] [ 0/62] eta: 0:04:52 loss: 0.8388 (0.8388) time: 4.7152 data: 4.6864 max mem: 9390 +Eval (hcp-val): [43] [61/62] eta: 0:00:00 loss: 0.8367 (0.8371) time: 0.0860 data: 0.0597 max mem: 9390 +Eval (hcp-val): [43] Total time: 0:00:11 (0.1814 s / it) +Averaged stats (hcp-val): loss: 0.8367 (0.8371) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +Train: [44] [ 0/6250] eta: 7:54:47 lr: 0.000080 grad: 0.1013 (0.1013) loss: 0.8503 (0.8503) time: 4.5581 data: 4.3923 max mem: 9390 +Train: [44] [ 100/6250] eta: 0:17:36 lr: 0.000080 grad: 0.0742 (0.0864) loss: 0.8303 (0.8372) time: 0.1052 data: 0.0048 max mem: 9390 +Train: [44] [ 200/6250] eta: 0:15:43 lr: 0.000080 grad: 0.0717 (0.0820) loss: 0.8445 (0.8349) time: 0.1491 data: 0.0649 max mem: 9390 +Train: [44] [ 300/6250] eta: 0:14:30 lr: 0.000080 grad: 0.0723 (0.0814) loss: 0.8302 (0.8331) time: 0.1333 data: 0.0532 max mem: 9390 +Train: [44] [ 400/6250] eta: 0:13:39 lr: 0.000080 grad: 0.0793 (0.0805) loss: 0.8234 (0.8325) time: 0.1179 data: 0.0323 max mem: 9390 +Train: [44] [ 500/6250] eta: 0:13:04 lr: 0.000080 grad: 0.0724 (0.0799) loss: 0.8257 (0.8317) time: 0.1239 data: 0.0406 max mem: 9390 +Train: [44] [ 600/6250] eta: 0:12:31 lr: 0.000080 grad: 0.0815 (0.0799) loss: 0.8272 (0.8310) time: 0.1179 data: 0.0371 max mem: 9390 +Train: [44] [ 700/6250] eta: 0:12:08 lr: 0.000080 grad: 0.0744 (0.0793) loss: 0.8238 (0.8307) time: 0.1201 data: 0.0284 max mem: 9390 +Train: [44] [ 800/6250] eta: 0:11:53 lr: 0.000080 grad: 0.0771 (0.0791) loss: 0.8281 (0.8304) time: 0.1355 data: 0.0543 max mem: 9390 +Train: [44] [ 900/6250] eta: 0:11:47 lr: 0.000080 grad: 0.0737 (0.0791) loss: 0.8264 (0.8301) time: 0.1556 data: 0.0753 max mem: 9390 +Train: [44] [1000/6250] eta: 0:11:35 lr: 0.000080 grad: 0.0769 (0.0793) loss: 0.8251 (0.8298) time: 0.1483 data: 0.0519 max mem: 9390 +Train: [44] [1100/6250] eta: 0:11:32 lr: 0.000079 grad: 0.0749 (0.0793) loss: 0.8297 (0.8295) time: 0.1545 data: 0.0792 max mem: 9390 +Train: [44] [1200/6250] eta: 0:11:20 lr: 0.000079 grad: 0.0772 (0.0794) loss: 0.8249 (0.8292) time: 0.1528 data: 0.0730 max mem: 9390 +Train: [44] [1300/6250] eta: 0:11:17 lr: 0.000079 grad: 0.0751 (0.0793) loss: 0.8230 (0.8289) time: 0.1918 data: 0.0983 max mem: 9390 +Train: [44] [1400/6250] eta: 0:11:09 lr: 0.000079 grad: 0.0826 (0.0794) loss: 0.8203 (0.8285) time: 0.1557 data: 0.0808 max mem: 9390 +Train: [44] [1500/6250] eta: 0:10:55 lr: 0.000079 grad: 0.0766 (0.0795) loss: 0.8232 (0.8281) time: 0.1223 data: 0.0451 max mem: 9390 +Train: [44] [1600/6250] eta: 0:10:40 lr: 0.000079 grad: 0.0783 (0.0798) loss: 0.8228 (0.8277) time: 0.1255 data: 0.0439 max mem: 9390 +Train: [44] [1700/6250] eta: 0:10:29 lr: 0.000079 grad: 0.0825 (0.0799) loss: 0.8249 (0.8274) time: 0.1273 data: 0.0441 max mem: 9390 +Train: [44] [1800/6250] eta: 0:10:16 lr: 0.000079 grad: 0.0845 (0.0802) loss: 0.8203 (0.8272) time: 0.1129 data: 0.0361 max mem: 9390 +Train: [44] [1900/6250] eta: 0:10:03 lr: 0.000079 grad: 0.0789 (0.0804) loss: 0.8297 (0.8271) time: 0.1149 data: 0.0346 max mem: 9390 +Train: [44] [2000/6250] eta: 0:09:47 lr: 0.000079 grad: 0.0789 (0.0805) loss: 0.8228 (0.8269) time: 0.1304 data: 0.0464 max mem: 9390 +Train: [44] [2100/6250] eta: 0:09:33 lr: 0.000079 grad: 0.0860 (0.0810) loss: 0.8235 (0.8268) time: 0.1874 data: 0.1018 max mem: 9390 +Train: [44] [2200/6250] eta: 0:09:18 lr: 0.000079 grad: 0.0810 (0.0811) loss: 0.8227 (0.8267) time: 0.1339 data: 0.0546 max mem: 9390 +Train: [44] [2300/6250] eta: 0:09:04 lr: 0.000079 grad: 0.0758 (0.0811) loss: 0.8291 (0.8266) time: 0.1406 data: 0.0650 max mem: 9390 +Train: [44] [2400/6250] eta: 0:08:50 lr: 0.000079 grad: 0.0867 (0.0813) loss: 0.8197 (0.8266) time: 0.1423 data: 0.0628 max mem: 9390 +Train: [44] [2500/6250] eta: 0:08:39 lr: 0.000079 grad: 0.0815 (0.0813) loss: 0.8245 (0.8266) time: 0.1027 data: 0.0240 max mem: 9390 +Train: [44] [2600/6250] eta: 0:08:25 lr: 0.000079 grad: 0.0864 (0.0814) loss: 0.8197 (0.8265) time: 0.1247 data: 0.0435 max mem: 9390 +Train: [44] [2700/6250] eta: 0:08:10 lr: 0.000079 grad: 0.0818 (0.0815) loss: 0.8208 (0.8264) time: 0.1250 data: 0.0447 max mem: 9390 +Train: [44] [2800/6250] eta: 0:07:56 lr: 0.000079 grad: 0.0834 (0.0815) loss: 0.8260 (0.8263) time: 0.1299 data: 0.0504 max mem: 9390 +Train: [44] [2900/6250] eta: 0:07:42 lr: 0.000079 grad: 0.0777 (0.0816) loss: 0.8275 (0.8262) time: 0.1272 data: 0.0494 max mem: 9390 +Train: [44] [3000/6250] eta: 0:07:28 lr: 0.000079 grad: 0.0809 (0.0815) loss: 0.8249 (0.8262) time: 0.1388 data: 0.0571 max mem: 9390 +Train: [44] [3100/6250] eta: 0:07:15 lr: 0.000079 grad: 0.0810 (0.0815) loss: 0.8243 (0.8262) time: 0.1251 data: 0.0468 max mem: 9390 +Train: [44] [3200/6250] eta: 0:07:02 lr: 0.000079 grad: 0.0773 (0.0815) loss: 0.8298 (0.8262) time: 0.1731 data: 0.0868 max mem: 9390 +Train: [44] [3300/6250] eta: 0:06:50 lr: 0.000079 grad: 0.0806 (0.0815) loss: 0.8273 (0.8263) time: 0.1229 data: 0.0332 max mem: 9390 +Train: [44] [3400/6250] eta: 0:06:38 lr: 0.000079 grad: 0.0788 (0.0815) loss: 0.8283 (0.8263) time: 0.1560 data: 0.0820 max mem: 9390 +Train: [44] [3500/6250] eta: 0:06:23 lr: 0.000079 grad: 0.0762 (0.0815) loss: 0.8197 (0.8264) time: 0.1422 data: 0.0594 max mem: 9390 +Train: [44] [3600/6250] eta: 0:06:11 lr: 0.000079 grad: 0.0810 (0.0815) loss: 0.8262 (0.8264) time: 0.1440 data: 0.0620 max mem: 9390 +Train: [44] [3700/6250] eta: 0:05:57 lr: 0.000079 grad: 0.0804 (0.0815) loss: 0.8268 (0.8264) time: 0.1477 data: 0.0609 max mem: 9390 +Train: [44] [3800/6250] eta: 0:05:43 lr: 0.000079 grad: 0.0830 (0.0815) loss: 0.8244 (0.8265) time: 0.1207 data: 0.0398 max mem: 9390 +Train: [44] [3900/6250] eta: 0:05:29 lr: 0.000079 grad: 0.0744 (0.0814) loss: 0.8287 (0.8265) time: 0.1284 data: 0.0496 max mem: 9390 +Train: [44] [4000/6250] eta: 0:05:16 lr: 0.000079 grad: 0.0811 (0.0814) loss: 0.8220 (0.8265) time: 0.1348 data: 0.0470 max mem: 9390 +Train: [44] [4100/6250] eta: 0:05:02 lr: 0.000079 grad: 0.0790 (0.0814) loss: 0.8279 (0.8265) time: 0.1312 data: 0.0540 max mem: 9390 +Train: [44] [4200/6250] eta: 0:04:48 lr: 0.000078 grad: 0.0776 (0.0815) loss: 0.8231 (0.8265) time: 0.1493 data: 0.0695 max mem: 9390 +Train: [44] [4300/6250] eta: 0:04:33 lr: 0.000078 grad: 0.0780 (0.0815) loss: 0.8258 (0.8266) time: 0.1405 data: 0.0594 max mem: 9390 +Train: [44] [4400/6250] eta: 0:04:19 lr: 0.000078 grad: 0.0790 (0.0815) loss: 0.8320 (0.8265) time: 0.1555 data: 0.0760 max mem: 9390 +Train: [44] [4500/6250] eta: 0:04:05 lr: 0.000078 grad: 0.0842 (0.0816) loss: 0.8282 (0.8265) time: 0.1341 data: 0.0546 max mem: 9390 +Train: [44] [4600/6250] eta: 0:03:51 lr: 0.000078 grad: 0.0874 (0.0817) loss: 0.8230 (0.8265) time: 0.1239 data: 0.0426 max mem: 9390 +Train: [44] [4700/6250] eta: 0:03:36 lr: 0.000078 grad: 0.0854 (0.0817) loss: 0.8263 (0.8265) time: 0.1507 data: 0.0699 max mem: 9390 +Train: [44] [4800/6250] eta: 0:03:22 lr: 0.000078 grad: 0.0829 (0.0818) loss: 0.8222 (0.8265) time: 0.1329 data: 0.0514 max mem: 9390 +Train: [44] [4900/6250] eta: 0:03:08 lr: 0.000078 grad: 0.0806 (0.0819) loss: 0.8277 (0.8265) time: 0.1474 data: 0.0587 max mem: 9390 +Train: [44] [5000/6250] eta: 0:02:54 lr: 0.000078 grad: 0.0822 (0.0819) loss: 0.8234 (0.8265) time: 0.1357 data: 0.0572 max mem: 9390 +Train: [44] [5100/6250] eta: 0:02:40 lr: 0.000078 grad: 0.0853 (0.0820) loss: 0.8201 (0.8264) time: 0.1247 data: 0.0461 max mem: 9390 +Train: [44] [5200/6250] eta: 0:02:26 lr: 0.000078 grad: 0.0846 (0.0820) loss: 0.8206 (0.8264) time: 0.1278 data: 0.0479 max mem: 9390 +Train: [44] [5300/6250] eta: 0:02:12 lr: 0.000078 grad: 0.0831 (0.0821) loss: 0.8257 (0.8263) time: 0.1574 data: 0.0779 max mem: 9390 +Train: [44] [5400/6250] eta: 0:01:58 lr: 0.000078 grad: 0.0816 (0.0822) loss: 0.8266 (0.8263) time: 0.1456 data: 0.0560 max mem: 9390 +Train: [44] [5500/6250] eta: 0:01:45 lr: 0.000078 grad: 0.0812 (0.0823) loss: 0.8223 (0.8263) time: 0.1583 data: 0.0809 max mem: 9390 +Train: [44] [5600/6250] eta: 0:01:30 lr: 0.000078 grad: 0.0884 (0.0824) loss: 0.8185 (0.8262) time: 0.1345 data: 0.0554 max mem: 9390 +Train: [44] [5700/6250] eta: 0:01:16 lr: 0.000078 grad: 0.0786 (0.0824) loss: 0.8220 (0.8262) time: 0.1290 data: 0.0497 max mem: 9390 +Train: [44] [5800/6250] eta: 0:01:03 lr: 0.000078 grad: 0.0805 (0.0825) loss: 0.8293 (0.8261) time: 0.1704 data: 0.0861 max mem: 9390 +Train: [44] [5900/6250] eta: 0:00:49 lr: 0.000078 grad: 0.0797 (0.0825) loss: 0.8298 (0.8261) time: 0.1344 data: 0.0597 max mem: 9390 +Train: [44] [6000/6250] eta: 0:00:35 lr: 0.000078 grad: 0.0842 (0.0826) loss: 0.8246 (0.8261) time: 0.1595 data: 0.0821 max mem: 9390 +Train: [44] [6100/6250] eta: 0:00:21 lr: 0.000078 grad: 0.0793 (0.0826) loss: 0.8187 (0.8261) time: 0.1312 data: 0.0544 max mem: 9390 +Train: [44] [6200/6250] eta: 0:00:07 lr: 0.000078 grad: 0.0763 (0.0826) loss: 0.8270 (0.8261) time: 0.1342 data: 0.0540 max mem: 9390 +Train: [44] [6249/6250] eta: 0:00:00 lr: 0.000078 grad: 0.0754 (0.0827) loss: 0.8310 (0.8260) time: 0.1372 data: 0.0583 max mem: 9390 +Train: [44] Total time: 0:14:42 (0.1411 s / it) +Averaged stats: lr: 0.000078 grad: 0.0754 (0.0827) loss: 0.8310 (0.8260) +Eval (hcp-train-subset): [44] [ 0/62] eta: 0:04:31 loss: 0.8518 (0.8518) time: 4.3775 data: 4.3479 max mem: 9390 +Eval (hcp-train-subset): [44] [61/62] eta: 0:00:00 loss: 0.8368 (0.8386) time: 0.1059 data: 0.0796 max mem: 9390 +Eval (hcp-train-subset): [44] Total time: 0:00:11 (0.1803 s / it) +Averaged stats (hcp-train-subset): loss: 0.8368 (0.8386) +Making plots (hcp-train-subset): example=53 +Eval (hcp-val): [44] [ 0/62] eta: 0:03:33 loss: 0.8351 (0.8351) time: 3.4458 data: 3.3636 max mem: 9390 +Eval (hcp-val): [44] [61/62] eta: 0:00:00 loss: 0.8341 (0.8360) time: 0.1048 data: 0.0800 max mem: 9390 +Eval (hcp-val): [44] Total time: 0:00:11 (0.1829 s / it) +Averaged stats (hcp-val): loss: 0.8341 (0.8360) +Making plots (hcp-val): example=35 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +Train: [45] [ 0/6250] eta: 6:44:24 lr: 0.000078 grad: 0.0465 (0.0465) loss: 0.8855 (0.8855) time: 3.8824 data: 3.6838 max mem: 9390 +Train: [45] [ 100/6250] eta: 0:18:36 lr: 0.000078 grad: 0.0827 (0.0911) loss: 0.8388 (0.8449) time: 0.1406 data: 0.0521 max mem: 9390 +Train: [45] [ 200/6250] eta: 0:15:44 lr: 0.000078 grad: 0.0781 (0.0895) loss: 0.8279 (0.8369) time: 0.1181 data: 0.0272 max mem: 9390 +Train: [45] [ 300/6250] eta: 0:14:45 lr: 0.000078 grad: 0.0800 (0.0866) loss: 0.8294 (0.8346) time: 0.1465 data: 0.0695 max mem: 9390 +Train: [45] [ 400/6250] eta: 0:13:55 lr: 0.000078 grad: 0.0784 (0.0858) loss: 0.8310 (0.8329) time: 0.1187 data: 0.0306 max mem: 9390 +Train: [45] [ 500/6250] eta: 0:13:21 lr: 0.000078 grad: 0.0914 (0.0860) loss: 0.8212 (0.8309) time: 0.1337 data: 0.0411 max mem: 9390 +Train: [45] [ 600/6250] eta: 0:12:52 lr: 0.000078 grad: 0.0832 (0.0860) loss: 0.8221 (0.8298) time: 0.1226 data: 0.0370 max mem: 9390 +Train: [45] [ 700/6250] eta: 0:12:28 lr: 0.000078 grad: 0.0802 (0.0864) loss: 0.8276 (0.8292) time: 0.1270 data: 0.0487 max mem: 9390 +Train: [45] [ 800/6250] eta: 0:12:10 lr: 0.000078 grad: 0.0860 (0.0863) loss: 0.8278 (0.8287) time: 0.1402 data: 0.0485 max mem: 9390 +Train: [45] [ 900/6250] eta: 0:12:13 lr: 0.000078 grad: 0.0806 (0.0858) loss: 0.8171 (0.8280) time: 0.1504 data: 0.0734 max mem: 9390 +Train: [45] [1000/6250] eta: 0:11:57 lr: 0.000078 grad: 0.0800 (0.0855) loss: 0.8286 (0.8277) time: 0.1557 data: 0.0775 max mem: 9390 +Train: [45] [1100/6250] eta: 0:11:42 lr: 0.000077 grad: 0.0817 (0.0851) loss: 0.8220 (0.8271) time: 0.1274 data: 0.0489 max mem: 9390 +Train: [45] [1200/6250] eta: 0:11:27 lr: 0.000077 grad: 0.0778 (0.0848) loss: 0.8213 (0.8269) time: 0.1376 data: 0.0602 max mem: 9390 +Train: [45] [1300/6250] eta: 0:11:14 lr: 0.000077 grad: 0.0835 (0.0846) loss: 0.8165 (0.8266) time: 0.1383 data: 0.0615 max mem: 9390 +Train: [45] [1400/6250] eta: 0:11:06 lr: 0.000077 grad: 0.0796 (0.0845) loss: 0.8241 (0.8264) time: 0.1780 data: 0.0262 max mem: 9390 +Train: [45] [1500/6250] eta: 0:11:00 lr: 0.000077 grad: 0.0783 (0.0843) loss: 0.8273 (0.8263) time: 0.1330 data: 0.0521 max mem: 9390 +Train: [45] [1600/6250] eta: 0:10:45 lr: 0.000077 grad: 0.0814 (0.0840) loss: 0.8229 (0.8261) time: 0.1429 data: 0.0587 max mem: 9390 +Train: [45] [1700/6250] eta: 0:10:31 lr: 0.000077 grad: 0.0799 (0.0840) loss: 0.8269 (0.8260) time: 0.1118 data: 0.0360 max mem: 9390 +Train: [45] [1800/6250] eta: 0:10:17 lr: 0.000077 grad: 0.0782 (0.0840) loss: 0.8248 (0.8259) time: 0.1325 data: 0.0550 max mem: 9390 +Train: [45] [1900/6250] eta: 0:10:04 lr: 0.000077 grad: 0.0794 (0.0839) loss: 0.8233 (0.8258) time: 0.1145 data: 0.0319 max mem: 9390 +Train: [45] [2000/6250] eta: 0:09:51 lr: 0.000077 grad: 0.0814 (0.0839) loss: 0.8243 (0.8256) time: 0.1671 data: 0.0918 max mem: 9390 +Train: [45] [2100/6250] eta: 0:09:37 lr: 0.000077 grad: 0.0774 (0.0838) loss: 0.8270 (0.8257) time: 0.1490 data: 0.0677 max mem: 9390 +Train: [45] [2200/6250] eta: 0:09:25 lr: 0.000077 grad: 0.0805 (0.0837) loss: 0.8261 (0.8257) time: 0.1501 data: 0.0587 max mem: 9390 +Train: [45] [2300/6250] eta: 0:09:11 lr: 0.000077 grad: 0.0753 (0.0836) loss: 0.8287 (0.8256) time: 0.1482 data: 0.0701 max mem: 9390 +Train: [45] [2400/6250] eta: 0:09:06 lr: 0.000077 grad: 0.0813 (0.0835) loss: 0.8196 (0.8256) time: 0.2791 data: 0.1974 max mem: 9390 +Train: [45] [2500/6250] eta: 0:08:50 lr: 0.000077 grad: 0.0816 (0.0833) loss: 0.8283 (0.8256) time: 0.1462 data: 0.0705 max mem: 9390 +Train: [45] [2600/6250] eta: 0:08:35 lr: 0.000077 grad: 0.0807 (0.0832) loss: 0.8278 (0.8256) time: 0.1408 data: 0.0686 max mem: 9390 +Train: [45] [2700/6250] eta: 0:08:20 lr: 0.000077 grad: 0.0796 (0.0831) loss: 0.8235 (0.8258) time: 0.1558 data: 0.0767 max mem: 9390 +Train: [45] [2800/6250] eta: 0:08:08 lr: 0.000077 grad: 0.0790 (0.0830) loss: 0.8233 (0.8258) time: 0.1649 data: 0.0891 max mem: 9390 +Train: [45] [2900/6250] eta: 0:07:55 lr: 0.000077 grad: 0.0788 (0.0830) loss: 0.8244 (0.8258) time: 0.2054 data: 0.1133 max mem: 9390 +Train: [45] [3000/6250] eta: 0:07:41 lr: 0.000077 grad: 0.0806 (0.0829) loss: 0.8237 (0.8259) time: 0.1383 data: 0.0587 max mem: 9390 +Train: [45] [3100/6250] eta: 0:07:27 lr: 0.000077 grad: 0.0785 (0.0829) loss: 0.8219 (0.8258) time: 0.1540 data: 0.0768 max mem: 9390 +Train: [45] [3200/6250] eta: 0:07:13 lr: 0.000077 grad: 0.0838 (0.0828) loss: 0.8234 (0.8259) time: 0.1479 data: 0.0573 max mem: 9390 +Train: [45] [3300/6250] eta: 0:07:00 lr: 0.000077 grad: 0.0808 (0.0828) loss: 0.8256 (0.8259) time: 0.1498 data: 0.0760 max mem: 9390 +Train: [45] [3400/6250] eta: 0:06:47 lr: 0.000077 grad: 0.0787 (0.0828) loss: 0.8211 (0.8259) time: 0.1564 data: 0.0568 max mem: 9390 +Train: [45] [3500/6250] eta: 0:06:33 lr: 0.000077 grad: 0.0859 (0.0828) loss: 0.8245 (0.8259) time: 0.1500 data: 0.0783 max mem: 9390 +Train: [45] [3600/6250] eta: 0:06:19 lr: 0.000077 grad: 0.0848 (0.0828) loss: 0.8228 (0.8259) time: 0.1546 data: 0.0798 max mem: 9390 +Train: [45] [3700/6250] eta: 0:06:05 lr: 0.000077 grad: 0.0783 (0.0829) loss: 0.8281 (0.8259) time: 0.1464 data: 0.0675 max mem: 9390 +Train: [45] [3800/6250] eta: 0:05:51 lr: 0.000077 grad: 0.0774 (0.0829) loss: 0.8288 (0.8258) time: 0.1205 data: 0.0312 max mem: 9390 +Train: [45] [3900/6250] eta: 0:05:37 lr: 0.000077 grad: 0.0826 (0.0829) loss: 0.8273 (0.8258) time: 0.1211 data: 0.0308 max mem: 9390 +Train: [45] [4000/6250] eta: 0:05:22 lr: 0.000077 grad: 0.0858 (0.0830) loss: 0.8296 (0.8258) time: 0.1365 data: 0.0570 max mem: 9390 +Train: [45] [4100/6250] eta: 0:05:08 lr: 0.000077 grad: 0.0802 (0.0829) loss: 0.8242 (0.8258) time: 0.1509 data: 0.0650 max mem: 9390 +Train: [45] [4200/6250] eta: 0:04:53 lr: 0.000076 grad: 0.0843 (0.0829) loss: 0.8268 (0.8258) time: 0.1339 data: 0.0566 max mem: 9390 +Train: [45] [4300/6250] eta: 0:04:39 lr: 0.000076 grad: 0.0799 (0.0829) loss: 0.8181 (0.8258) time: 0.1423 data: 0.0654 max mem: 9390 +Train: [45] [4400/6250] eta: 0:04:24 lr: 0.000076 grad: 0.0787 (0.0829) loss: 0.8253 (0.8257) time: 0.1404 data: 0.0546 max mem: 9390 +Train: [45] [4500/6250] eta: 0:04:09 lr: 0.000076 grad: 0.0787 (0.0828) loss: 0.8240 (0.8257) time: 0.1394 data: 0.0590 max mem: 9390 +Train: [45] [4600/6250] eta: 0:03:55 lr: 0.000076 grad: 0.0771 (0.0829) loss: 0.8243 (0.8256) time: 0.1303 data: 0.0494 max mem: 9390 +Train: [45] [4700/6250] eta: 0:03:40 lr: 0.000076 grad: 0.0803 (0.0828) loss: 0.8286 (0.8256) time: 0.1350 data: 0.0561 max mem: 9390 +Train: [45] [4800/6250] eta: 0:03:26 lr: 0.000076 grad: 0.0836 (0.0829) loss: 0.8273 (0.8256) time: 0.1425 data: 0.0628 max mem: 9390 +Train: [45] [4900/6250] eta: 0:03:12 lr: 0.000076 grad: 0.0824 (0.0829) loss: 0.8297 (0.8256) time: 0.1442 data: 0.0695 max mem: 9390 +Train: [45] [5000/6250] eta: 0:02:57 lr: 0.000076 grad: 0.0777 (0.0829) loss: 0.8237 (0.8256) time: 0.1242 data: 0.0502 max mem: 9390 +Train: [45] [5100/6250] eta: 0:02:43 lr: 0.000076 grad: 0.0779 (0.0829) loss: 0.8241 (0.8256) time: 0.1416 data: 0.0647 max mem: 9390 +Train: [45] [5200/6250] eta: 0:02:29 lr: 0.000076 grad: 0.0860 (0.0829) loss: 0.8191 (0.8255) time: 0.1131 data: 0.0349 max mem: 9390 +Train: [45] [5300/6250] eta: 0:02:15 lr: 0.000076 grad: 0.0784 (0.0830) loss: 0.8273 (0.8255) time: 0.1121 data: 0.0347 max mem: 9390 +Train: [45] [5400/6250] eta: 0:02:00 lr: 0.000076 grad: 0.0814 (0.0830) loss: 0.8239 (0.8255) time: 0.1312 data: 0.0500 max mem: 9390 +Train: [45] [5500/6250] eta: 0:01:46 lr: 0.000076 grad: 0.0866 (0.0830) loss: 0.8192 (0.8255) time: 0.1605 data: 0.0704 max mem: 9390 +Train: [45] [5600/6250] eta: 0:01:32 lr: 0.000076 grad: 0.0885 (0.0830) loss: 0.8264 (0.8255) time: 0.1404 data: 0.0591 max mem: 9390 +Train: [45] [5700/6250] eta: 0:01:18 lr: 0.000076 grad: 0.0819 (0.0831) loss: 0.8230 (0.8254) time: 0.1651 data: 0.0742 max mem: 9390 +Train: [45] [5800/6250] eta: 0:01:04 lr: 0.000076 grad: 0.0819 (0.0830) loss: 0.8242 (0.8254) time: 0.1624 data: 0.0799 max mem: 9390 +Train: [45] [5900/6250] eta: 0:00:49 lr: 0.000076 grad: 0.0785 (0.0830) loss: 0.8219 (0.8253) time: 0.1524 data: 0.0686 max mem: 9390 +Train: [45] [6000/6250] eta: 0:00:35 lr: 0.000076 grad: 0.0790 (0.0830) loss: 0.8192 (0.8253) time: 0.1454 data: 0.0654 max mem: 9390 +Train: [45] [6100/6250] eta: 0:00:21 lr: 0.000076 grad: 0.0817 (0.0831) loss: 0.8245 (0.8253) time: 0.1352 data: 0.0511 max mem: 9390 +Train: [45] [6200/6250] eta: 0:00:07 lr: 0.000076 grad: 0.0820 (0.0831) loss: 0.8232 (0.8252) time: 0.1316 data: 0.0517 max mem: 9390 +Train: [45] [6249/6250] eta: 0:00:00 lr: 0.000076 grad: 0.0753 (0.0831) loss: 0.8255 (0.8252) time: 0.1356 data: 0.0483 max mem: 9390 +Train: [45] Total time: 0:14:57 (0.1436 s / it) +Averaged stats: lr: 0.000076 grad: 0.0753 (0.0831) loss: 0.8255 (0.8252) +Eval (hcp-train-subset): [45] [ 0/62] eta: 0:04:55 loss: 0.8502 (0.8502) time: 4.7654 data: 4.7359 max mem: 9390 +Eval (hcp-train-subset): [45] [61/62] eta: 0:00:00 loss: 0.8364 (0.8366) time: 0.1093 data: 0.0846 max mem: 9390 +Eval (hcp-train-subset): [45] Total time: 0:00:11 (0.1856 s / it) +Averaged stats (hcp-train-subset): loss: 0.8364 (0.8366) +Eval (hcp-val): [45] [ 0/62] eta: 0:03:29 loss: 0.8322 (0.8322) time: 3.3737 data: 3.3263 max mem: 9390 +Eval (hcp-val): [45] [61/62] eta: 0:00:00 loss: 0.8343 (0.8358) time: 0.0982 data: 0.0736 max mem: 9390 +Eval (hcp-val): [45] Total time: 0:00:11 (0.1859 s / it) +Averaged stats (hcp-val): loss: 0.8343 (0.8358) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +Train: [46] [ 0/6250] eta: 10:07:16 lr: 0.000076 grad: 0.2902 (0.2902) loss: 0.8026 (0.8026) time: 5.8298 data: 5.7065 max mem: 9390 +Train: [46] [ 100/6250] eta: 0:19:20 lr: 0.000076 grad: 0.0873 (0.0937) loss: 0.8304 (0.8308) time: 0.1483 data: 0.0541 max mem: 9390 +Train: [46] [ 200/6250] eta: 0:16:16 lr: 0.000076 grad: 0.0893 (0.0929) loss: 0.8183 (0.8243) time: 0.1319 data: 0.0445 max mem: 9390 +Train: [46] [ 300/6250] eta: 0:15:01 lr: 0.000076 grad: 0.0835 (0.0906) loss: 0.8232 (0.8224) time: 0.1201 data: 0.0316 max mem: 9390 +Train: [46] [ 400/6250] eta: 0:14:07 lr: 0.000076 grad: 0.0781 (0.0897) loss: 0.8305 (0.8229) time: 0.1287 data: 0.0486 max mem: 9390 +Train: [46] [ 500/6250] eta: 0:13:34 lr: 0.000076 grad: 0.0807 (0.0888) loss: 0.8252 (0.8234) time: 0.1237 data: 0.0347 max mem: 9390 +Train: [46] [ 600/6250] eta: 0:13:03 lr: 0.000076 grad: 0.0829 (0.0879) loss: 0.8235 (0.8239) time: 0.1351 data: 0.0547 max mem: 9390 +Train: [46] [ 700/6250] eta: 0:12:50 lr: 0.000076 grad: 0.0784 (0.0870) loss: 0.8305 (0.8244) time: 0.1393 data: 0.0581 max mem: 9390 +Train: [46] [ 800/6250] eta: 0:12:36 lr: 0.000076 grad: 0.0786 (0.0861) loss: 0.8311 (0.8248) time: 0.1421 data: 0.0497 max mem: 9390 +Train: [46] [ 900/6250] eta: 0:12:29 lr: 0.000076 grad: 0.0822 (0.0856) loss: 0.8261 (0.8251) time: 0.1470 data: 0.0649 max mem: 9390 +Train: [46] [1000/6250] eta: 0:12:13 lr: 0.000076 grad: 0.0741 (0.0851) loss: 0.8289 (0.8255) time: 0.1322 data: 0.0502 max mem: 9390 +Train: [46] [1100/6250] eta: 0:11:58 lr: 0.000075 grad: 0.0778 (0.0847) loss: 0.8261 (0.8254) time: 0.1613 data: 0.0812 max mem: 9390 +Train: [46] [1200/6250] eta: 0:11:46 lr: 0.000075 grad: 0.0798 (0.0845) loss: 0.8206 (0.8253) time: 0.1607 data: 0.0810 max mem: 9390 +Train: [46] [1300/6250] eta: 0:11:27 lr: 0.000075 grad: 0.0802 (0.0842) loss: 0.8173 (0.8250) time: 0.1318 data: 0.0552 max mem: 9390 +Train: [46] [1400/6250] eta: 0:11:12 lr: 0.000075 grad: 0.0729 (0.0839) loss: 0.8231 (0.8247) time: 0.1521 data: 0.0718 max mem: 9390 +Train: [46] [1500/6250] eta: 0:10:57 lr: 0.000075 grad: 0.0777 (0.0838) loss: 0.8186 (0.8243) time: 0.1401 data: 0.0571 max mem: 9390 +Train: [46] [1600/6250] eta: 0:10:45 lr: 0.000075 grad: 0.0827 (0.0837) loss: 0.8163 (0.8241) time: 0.1297 data: 0.0498 max mem: 9390 +Train: [46] [1700/6250] eta: 0:10:31 lr: 0.000075 grad: 0.0775 (0.0837) loss: 0.8176 (0.8238) time: 0.1392 data: 0.0611 max mem: 9390 +Train: [46] [1800/6250] eta: 0:10:17 lr: 0.000075 grad: 0.0803 (0.0835) loss: 0.8215 (0.8238) time: 0.1432 data: 0.0526 max mem: 9390 +Train: [46] [1900/6250] eta: 0:10:03 lr: 0.000075 grad: 0.0791 (0.0835) loss: 0.8220 (0.8238) time: 0.1460 data: 0.0674 max mem: 9390 +Train: [46] [2000/6250] eta: 0:09:51 lr: 0.000075 grad: 0.0801 (0.0836) loss: 0.8206 (0.8236) time: 0.1397 data: 0.0664 max mem: 9390 +Train: [46] [2100/6250] eta: 0:09:39 lr: 0.000075 grad: 0.0811 (0.0835) loss: 0.8228 (0.8236) time: 0.1412 data: 0.0636 max mem: 9390 +Train: [46] [2200/6250] eta: 0:09:24 lr: 0.000075 grad: 0.0827 (0.0836) loss: 0.8220 (0.8235) time: 0.1445 data: 0.0675 max mem: 9390 +Train: [46] [2300/6250] eta: 0:09:11 lr: 0.000075 grad: 0.0846 (0.0837) loss: 0.8237 (0.8234) time: 0.1310 data: 0.0525 max mem: 9390 +Train: [46] [2400/6250] eta: 0:08:57 lr: 0.000075 grad: 0.0874 (0.0837) loss: 0.8202 (0.8233) time: 0.1638 data: 0.0910 max mem: 9390 +Train: [46] [2500/6250] eta: 0:08:42 lr: 0.000075 grad: 0.0808 (0.0837) loss: 0.8262 (0.8234) time: 0.1208 data: 0.0416 max mem: 9390 +Train: [46] [2600/6250] eta: 0:08:27 lr: 0.000075 grad: 0.0826 (0.0837) loss: 0.8255 (0.8234) time: 0.1311 data: 0.0564 max mem: 9390 +Train: [46] [2700/6250] eta: 0:08:14 lr: 0.000075 grad: 0.0780 (0.0837) loss: 0.8254 (0.8234) time: 0.1336 data: 0.0511 max mem: 9390 +Train: [46] [2800/6250] eta: 0:08:00 lr: 0.000075 grad: 0.0858 (0.0839) loss: 0.8188 (0.8234) time: 0.1417 data: 0.0667 max mem: 9390 +Train: [46] [2900/6250] eta: 0:07:47 lr: 0.000075 grad: 0.0853 (0.0840) loss: 0.8241 (0.8234) time: 0.1299 data: 0.0555 max mem: 9390 +Train: [46] [3000/6250] eta: 0:07:33 lr: 0.000075 grad: 0.0771 (0.0840) loss: 0.8278 (0.8234) time: 0.1370 data: 0.0597 max mem: 9390 +Train: [46] [3100/6250] eta: 0:07:20 lr: 0.000075 grad: 0.0823 (0.0840) loss: 0.8229 (0.8234) time: 0.1290 data: 0.0439 max mem: 9390 +Train: [46] [3200/6250] eta: 0:07:06 lr: 0.000075 grad: 0.0852 (0.0840) loss: 0.8249 (0.8234) time: 0.1335 data: 0.0612 max mem: 9390 +Train: [46] [3300/6250] eta: 0:06:52 lr: 0.000075 grad: 0.0781 (0.0840) loss: 0.8196 (0.8234) time: 0.1062 data: 0.0290 max mem: 9390 +Train: [46] [3400/6250] eta: 0:06:39 lr: 0.000075 grad: 0.0835 (0.0840) loss: 0.8243 (0.8233) time: 0.1623 data: 0.0754 max mem: 9390 +Train: [46] [3500/6250] eta: 0:06:25 lr: 0.000075 grad: 0.0852 (0.0840) loss: 0.8264 (0.8234) time: 0.1660 data: 0.0663 max mem: 9390 +Train: [46] [3600/6250] eta: 0:06:11 lr: 0.000075 grad: 0.0837 (0.0840) loss: 0.8249 (0.8234) time: 0.1381 data: 0.0639 max mem: 9390 +Train: [46] [3700/6250] eta: 0:05:56 lr: 0.000075 grad: 0.0777 (0.0840) loss: 0.8269 (0.8235) time: 0.1473 data: 0.0720 max mem: 9390 +Train: [46] [3800/6250] eta: 0:05:42 lr: 0.000075 grad: 0.0800 (0.0840) loss: 0.8246 (0.8235) time: 0.1313 data: 0.0534 max mem: 9390 +Train: [46] [3900/6250] eta: 0:05:28 lr: 0.000075 grad: 0.0817 (0.0840) loss: 0.8211 (0.8235) time: 0.1382 data: 0.0601 max mem: 9390 +Train: [46] [4000/6250] eta: 0:05:14 lr: 0.000075 grad: 0.0863 (0.0840) loss: 0.8202 (0.8235) time: 0.1540 data: 0.0718 max mem: 9390 +Train: [46] [4100/6250] eta: 0:04:59 lr: 0.000075 grad: 0.0843 (0.0840) loss: 0.8278 (0.8235) time: 0.1325 data: 0.0547 max mem: 9390 +Train: [46] [4200/6250] eta: 0:04:45 lr: 0.000074 grad: 0.0839 (0.0840) loss: 0.8208 (0.8235) time: 0.1310 data: 0.0421 max mem: 9390 +Train: [46] [4300/6250] eta: 0:04:31 lr: 0.000074 grad: 0.0827 (0.0840) loss: 0.8191 (0.8235) time: 0.1320 data: 0.0519 max mem: 9390 +Train: [46] [4400/6250] eta: 0:04:17 lr: 0.000074 grad: 0.0871 (0.0841) loss: 0.8226 (0.8235) time: 0.1381 data: 0.0618 max mem: 9390 +Train: [46] [4500/6250] eta: 0:04:03 lr: 0.000074 grad: 0.0874 (0.0842) loss: 0.8221 (0.8234) time: 0.1922 data: 0.1097 max mem: 9390 +Train: [46] [4600/6250] eta: 0:03:49 lr: 0.000074 grad: 0.0833 (0.0842) loss: 0.8183 (0.8234) time: 0.1526 data: 0.0754 max mem: 9390 +Train: [46] [4700/6250] eta: 0:03:35 lr: 0.000074 grad: 0.0870 (0.0842) loss: 0.8197 (0.8234) time: 0.1306 data: 0.0503 max mem: 9390 +Train: [46] [4800/6250] eta: 0:03:21 lr: 0.000074 grad: 0.0812 (0.0843) loss: 0.8272 (0.8233) time: 0.1526 data: 0.0636 max mem: 9390 +Train: [46] [4900/6250] eta: 0:03:07 lr: 0.000074 grad: 0.0850 (0.0843) loss: 0.8179 (0.8233) time: 0.1322 data: 0.0557 max mem: 9390 +Train: [46] [5000/6250] eta: 0:02:54 lr: 0.000074 grad: 0.0854 (0.0843) loss: 0.8227 (0.8233) time: 0.2232 data: 0.1445 max mem: 9390 +Train: [46] [5100/6250] eta: 0:02:40 lr: 0.000074 grad: 0.0803 (0.0844) loss: 0.8187 (0.8232) time: 0.1318 data: 0.0507 max mem: 9390 +Train: [46] [5200/6250] eta: 0:02:26 lr: 0.000074 grad: 0.0821 (0.0844) loss: 0.8174 (0.8232) time: 0.1438 data: 0.0620 max mem: 9390 +Train: [46] [5300/6250] eta: 0:02:12 lr: 0.000074 grad: 0.0837 (0.0844) loss: 0.8214 (0.8232) time: 0.1436 data: 0.0657 max mem: 9390 +Train: [46] [5400/6250] eta: 0:01:58 lr: 0.000074 grad: 0.0831 (0.0844) loss: 0.8223 (0.8231) time: 0.1422 data: 0.0653 max mem: 9390 +Train: [46] [5500/6250] eta: 0:01:44 lr: 0.000074 grad: 0.0823 (0.0845) loss: 0.8174 (0.8231) time: 0.1259 data: 0.0482 max mem: 9390 +Train: [46] [5600/6250] eta: 0:01:30 lr: 0.000074 grad: 0.0817 (0.0845) loss: 0.8225 (0.8230) time: 0.1442 data: 0.0669 max mem: 9390 +Train: [46] [5700/6250] eta: 0:01:16 lr: 0.000074 grad: 0.0843 (0.0845) loss: 0.8201 (0.8230) time: 0.1419 data: 0.0653 max mem: 9390 +Train: [46] [5800/6250] eta: 0:01:03 lr: 0.000074 grad: 0.0862 (0.0846) loss: 0.8186 (0.8229) time: 0.1703 data: 0.0868 max mem: 9390 +Train: [46] [5900/6250] eta: 0:00:49 lr: 0.000074 grad: 0.0849 (0.0846) loss: 0.8178 (0.8228) time: 0.1408 data: 0.0604 max mem: 9390 +Train: [46] [6000/6250] eta: 0:00:35 lr: 0.000074 grad: 0.0817 (0.0846) loss: 0.8239 (0.8228) time: 0.1379 data: 0.0551 max mem: 9390 +Train: [46] [6100/6250] eta: 0:00:21 lr: 0.000074 grad: 0.0811 (0.0846) loss: 0.8180 (0.8227) time: 0.1315 data: 0.0539 max mem: 9390 +Train: [46] [6200/6250] eta: 0:00:07 lr: 0.000074 grad: 0.0741 (0.0847) loss: 0.8274 (0.8227) time: 0.1251 data: 0.0425 max mem: 9390 +Train: [46] [6249/6250] eta: 0:00:00 lr: 0.000074 grad: 0.0820 (0.0847) loss: 0.8216 (0.8227) time: 0.1287 data: 0.0413 max mem: 9390 +Train: [46] Total time: 0:14:45 (0.1417 s / it) +Averaged stats: lr: 0.000074 grad: 0.0820 (0.0847) loss: 0.8216 (0.8227) +Eval (hcp-train-subset): [46] [ 0/62] eta: 0:03:24 loss: 0.8495 (0.8495) time: 3.2913 data: 3.2019 max mem: 9390 +Eval (hcp-train-subset): [46] [61/62] eta: 0:00:00 loss: 0.8355 (0.8370) time: 0.1161 data: 0.0889 max mem: 9390 +Eval (hcp-train-subset): [46] Total time: 0:00:11 (0.1874 s / it) +Averaged stats (hcp-train-subset): loss: 0.8355 (0.8370) +Eval (hcp-val): [46] [ 0/62] eta: 0:04:10 loss: 0.8364 (0.8364) time: 4.0423 data: 3.9857 max mem: 9390 +Eval (hcp-val): [46] [61/62] eta: 0:00:00 loss: 0.8368 (0.8367) time: 0.1121 data: 0.0875 max mem: 9390 +Eval (hcp-val): [46] Total time: 0:00:11 (0.1911 s / it) +Averaged stats (hcp-val): loss: 0.8368 (0.8367) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +Train: [47] [ 0/6250] eta: 7:40:22 lr: 0.000074 grad: 0.1187 (0.1187) loss: 0.8052 (0.8052) time: 4.4196 data: 4.1177 max mem: 9390 +Train: [47] [ 100/6250] eta: 0:18:35 lr: 0.000074 grad: 0.0852 (0.0864) loss: 0.8146 (0.8309) time: 0.1319 data: 0.0338 max mem: 9390 +Train: [47] [ 200/6250] eta: 0:16:01 lr: 0.000074 grad: 0.0848 (0.0872) loss: 0.8216 (0.8284) time: 0.1272 data: 0.0401 max mem: 9390 +Train: [47] [ 300/6250] eta: 0:14:49 lr: 0.000074 grad: 0.0843 (0.0876) loss: 0.8189 (0.8269) time: 0.1182 data: 0.0229 max mem: 9390 +Train: [47] [ 400/6250] eta: 0:14:09 lr: 0.000074 grad: 0.0752 (0.0876) loss: 0.8325 (0.8255) time: 0.1271 data: 0.0486 max mem: 9390 +Train: [47] [ 500/6250] eta: 0:13:36 lr: 0.000074 grad: 0.0832 (0.0869) loss: 0.8267 (0.8249) time: 0.1236 data: 0.0357 max mem: 9390 +Train: [47] [ 600/6250] eta: 0:13:11 lr: 0.000074 grad: 0.0778 (0.0860) loss: 0.8286 (0.8245) time: 0.1332 data: 0.0487 max mem: 9390 +Train: [47] [ 700/6250] eta: 0:13:07 lr: 0.000074 grad: 0.0782 (0.0855) loss: 0.8252 (0.8245) time: 0.1578 data: 0.0780 max mem: 9390 +Train: [47] [ 800/6250] eta: 0:12:55 lr: 0.000074 grad: 0.0801 (0.0853) loss: 0.8166 (0.8243) time: 0.1465 data: 0.0683 max mem: 9390 +Train: [47] [ 900/6250] eta: 0:12:39 lr: 0.000074 grad: 0.0822 (0.0848) loss: 0.8239 (0.8244) time: 0.1563 data: 0.0776 max mem: 9390 +Train: [47] [1000/6250] eta: 0:12:26 lr: 0.000073 grad: 0.0786 (0.0847) loss: 0.8254 (0.8243) time: 0.1322 data: 0.0532 max mem: 9390 +Train: [47] [1100/6250] eta: 0:12:12 lr: 0.000073 grad: 0.0797 (0.0847) loss: 0.8193 (0.8240) time: 0.1324 data: 0.0533 max mem: 9390 +Train: [47] [1200/6250] eta: 0:11:56 lr: 0.000073 grad: 0.0885 (0.0850) loss: 0.8200 (0.8234) time: 0.1600 data: 0.0842 max mem: 9390 +Train: [47] [1300/6250] eta: 0:11:40 lr: 0.000073 grad: 0.0824 (0.0850) loss: 0.8254 (0.8230) time: 0.1549 data: 0.0742 max mem: 9390 +Train: [47] [1400/6250] eta: 0:11:24 lr: 0.000073 grad: 0.0819 (0.0852) loss: 0.8166 (0.8224) time: 0.1433 data: 0.0624 max mem: 9390 +Train: [47] [1500/6250] eta: 0:11:23 lr: 0.000073 grad: 0.0868 (0.0853) loss: 0.8141 (0.8219) time: 0.2503 data: 0.1538 max mem: 9390 +Train: [47] [1600/6250] eta: 0:11:00 lr: 0.000073 grad: 0.0807 (0.0853) loss: 0.8122 (0.8215) time: 0.1264 data: 0.0440 max mem: 9390 +Train: [47] [1700/6250] eta: 0:10:47 lr: 0.000073 grad: 0.0799 (0.0855) loss: 0.8203 (0.8212) time: 0.1198 data: 0.0410 max mem: 9390 +Train: [47] [1800/6250] eta: 0:10:31 lr: 0.000073 grad: 0.0857 (0.0855) loss: 0.8215 (0.8209) time: 0.1358 data: 0.0566 max mem: 9390 +Train: [47] [1900/6250] eta: 0:10:16 lr: 0.000073 grad: 0.0810 (0.0856) loss: 0.8167 (0.8207) time: 0.1410 data: 0.0640 max mem: 9390 +Train: [47] [2000/6250] eta: 0:10:00 lr: 0.000073 grad: 0.0804 (0.0856) loss: 0.8185 (0.8205) time: 0.1630 data: 0.0828 max mem: 9390 +Train: [47] [2100/6250] eta: 0:09:45 lr: 0.000073 grad: 0.0868 (0.0857) loss: 0.8175 (0.8204) time: 0.1404 data: 0.0659 max mem: 9390 +Train: [47] [2200/6250] eta: 0:09:31 lr: 0.000073 grad: 0.0886 (0.0857) loss: 0.8159 (0.8203) time: 0.1586 data: 0.0807 max mem: 9390 +Train: [47] [2300/6250] eta: 0:09:19 lr: 0.000073 grad: 0.0817 (0.0857) loss: 0.8148 (0.8201) time: 0.1525 data: 0.0745 max mem: 9390 +Train: [47] [2400/6250] eta: 0:09:04 lr: 0.000073 grad: 0.0819 (0.0858) loss: 0.8229 (0.8201) time: 0.1338 data: 0.0539 max mem: 9390 +Train: [47] [2500/6250] eta: 0:08:50 lr: 0.000073 grad: 0.0866 (0.0859) loss: 0.8190 (0.8200) time: 0.1370 data: 0.0575 max mem: 9390 +Train: [47] [2600/6250] eta: 0:08:36 lr: 0.000073 grad: 0.0819 (0.0858) loss: 0.8234 (0.8200) time: 0.1588 data: 0.0772 max mem: 9390 +Train: [47] [2700/6250] eta: 0:08:22 lr: 0.000073 grad: 0.0875 (0.0860) loss: 0.8167 (0.8199) time: 0.1410 data: 0.0645 max mem: 9390 +Train: [47] [2800/6250] eta: 0:08:09 lr: 0.000073 grad: 0.0935 (0.0862) loss: 0.8100 (0.8199) time: 0.1423 data: 0.0517 max mem: 9390 +Train: [47] [2900/6250] eta: 0:07:55 lr: 0.000073 grad: 0.0824 (0.0862) loss: 0.8143 (0.8199) time: 0.1474 data: 0.0639 max mem: 9390 +Train: [47] [3000/6250] eta: 0:07:41 lr: 0.000073 grad: 0.0839 (0.0862) loss: 0.8203 (0.8198) time: 0.1488 data: 0.0630 max mem: 9390 +Train: [47] [3100/6250] eta: 0:07:27 lr: 0.000073 grad: 0.0897 (0.0864) loss: 0.8135 (0.8197) time: 0.1533 data: 0.0813 max mem: 9390 +Train: [47] [3200/6250] eta: 0:07:12 lr: 0.000073 grad: 0.0887 (0.0865) loss: 0.8182 (0.8196) time: 0.1629 data: 0.0866 max mem: 9390 +Train: [47] [3300/6250] eta: 0:06:58 lr: 0.000073 grad: 0.0828 (0.0866) loss: 0.8180 (0.8195) time: 0.1359 data: 0.0598 max mem: 9390 +Train: [47] [3400/6250] eta: 0:06:45 lr: 0.000073 grad: 0.0889 (0.0866) loss: 0.8147 (0.8195) time: 0.1389 data: 0.0499 max mem: 9390 +Train: [47] [3500/6250] eta: 0:06:30 lr: 0.000073 grad: 0.0869 (0.0867) loss: 0.8210 (0.8194) time: 0.1345 data: 0.0510 max mem: 9390 +Train: [47] [3600/6250] eta: 0:06:16 lr: 0.000073 grad: 0.0862 (0.0868) loss: 0.8184 (0.8194) time: 0.1496 data: 0.0612 max mem: 9390 +Train: [47] [3700/6250] eta: 0:06:01 lr: 0.000073 grad: 0.0847 (0.0869) loss: 0.8174 (0.8194) time: 0.1431 data: 0.0658 max mem: 9390 +Train: [47] [3800/6250] eta: 0:05:47 lr: 0.000073 grad: 0.0858 (0.0869) loss: 0.8164 (0.8193) time: 0.1445 data: 0.0625 max mem: 9390 +Train: [47] [3900/6250] eta: 0:05:32 lr: 0.000073 grad: 0.0833 (0.0869) loss: 0.8204 (0.8192) time: 0.1443 data: 0.0648 max mem: 9390 +Train: [47] [4000/6250] eta: 0:05:18 lr: 0.000073 grad: 0.0920 (0.0870) loss: 0.8179 (0.8191) time: 0.1746 data: 0.0885 max mem: 9390 +Train: [47] [4100/6250] eta: 0:05:03 lr: 0.000072 grad: 0.0847 (0.0870) loss: 0.8139 (0.8191) time: 0.1177 data: 0.0358 max mem: 9390 +Train: [47] [4200/6250] eta: 0:04:48 lr: 0.000072 grad: 0.0870 (0.0870) loss: 0.8131 (0.8191) time: 0.1219 data: 0.0425 max mem: 9390 +Train: [47] [4300/6250] eta: 0:04:35 lr: 0.000072 grad: 0.0808 (0.0869) loss: 0.8211 (0.8192) time: 0.1162 data: 0.0255 max mem: 9390 +Train: [47] [4400/6250] eta: 0:04:20 lr: 0.000072 grad: 0.0848 (0.0869) loss: 0.8125 (0.8192) time: 0.1282 data: 0.0375 max mem: 9390 +Train: [47] [4500/6250] eta: 0:04:06 lr: 0.000072 grad: 0.0812 (0.0869) loss: 0.8233 (0.8192) time: 0.1343 data: 0.0438 max mem: 9390 +Train: [47] [4600/6250] eta: 0:03:52 lr: 0.000072 grad: 0.0864 (0.0869) loss: 0.8148 (0.8191) time: 0.1225 data: 0.0252 max mem: 9390 +Train: [47] [4700/6250] eta: 0:03:39 lr: 0.000072 grad: 0.0870 (0.0869) loss: 0.8218 (0.8192) time: 0.2082 data: 0.1230 max mem: 9390 +Train: [47] [4800/6250] eta: 0:03:24 lr: 0.000072 grad: 0.0845 (0.0870) loss: 0.8169 (0.8191) time: 0.1080 data: 0.0354 max mem: 9390 +Train: [47] [4900/6250] eta: 0:03:10 lr: 0.000072 grad: 0.0849 (0.0870) loss: 0.8131 (0.8191) time: 0.1600 data: 0.0772 max mem: 9390 +Train: [47] [5000/6250] eta: 0:02:56 lr: 0.000072 grad: 0.0854 (0.0870) loss: 0.8236 (0.8191) time: 0.1341 data: 0.0578 max mem: 9390 +Train: [47] [5100/6250] eta: 0:02:42 lr: 0.000072 grad: 0.0824 (0.0870) loss: 0.8182 (0.8190) time: 0.1518 data: 0.0608 max mem: 9390 +Train: [47] [5200/6250] eta: 0:02:28 lr: 0.000072 grad: 0.0860 (0.0871) loss: 0.8264 (0.8190) time: 0.1429 data: 0.0641 max mem: 9390 +Train: [47] [5300/6250] eta: 0:02:13 lr: 0.000072 grad: 0.0806 (0.0870) loss: 0.8217 (0.8190) time: 0.1269 data: 0.0375 max mem: 9390 +Train: [47] [5400/6250] eta: 0:01:59 lr: 0.000072 grad: 0.0844 (0.0871) loss: 0.8208 (0.8190) time: 0.1727 data: 0.0786 max mem: 9390 +Train: [47] [5500/6250] eta: 0:01:45 lr: 0.000072 grad: 0.0811 (0.0870) loss: 0.8232 (0.8191) time: 0.1146 data: 0.0319 max mem: 9390 +Train: [47] [5600/6250] eta: 0:01:31 lr: 0.000072 grad: 0.0842 (0.0870) loss: 0.8172 (0.8191) time: 0.1484 data: 0.0637 max mem: 9390 +Train: [47] [5700/6250] eta: 0:01:17 lr: 0.000072 grad: 0.0813 (0.0870) loss: 0.8189 (0.8191) time: 0.1419 data: 0.0656 max mem: 9390 +Train: [47] [5800/6250] eta: 0:01:03 lr: 0.000072 grad: 0.0846 (0.0870) loss: 0.8180 (0.8191) time: 0.1858 data: 0.1092 max mem: 9390 +Train: [47] [5900/6250] eta: 0:00:49 lr: 0.000072 grad: 0.0842 (0.0870) loss: 0.8177 (0.8191) time: 0.1506 data: 0.0732 max mem: 9390 +Train: [47] [6000/6250] eta: 0:00:35 lr: 0.000072 grad: 0.0803 (0.0870) loss: 0.8177 (0.8192) time: 0.1438 data: 0.0637 max mem: 9390 +Train: [47] [6100/6250] eta: 0:00:21 lr: 0.000072 grad: 0.0865 (0.0870) loss: 0.8212 (0.8192) time: 0.1306 data: 0.0484 max mem: 9390 +Train: [47] [6200/6250] eta: 0:00:07 lr: 0.000072 grad: 0.0885 (0.0870) loss: 0.8222 (0.8192) time: 0.1380 data: 0.0590 max mem: 9390 +Train: [47] [6249/6250] eta: 0:00:00 lr: 0.000072 grad: 0.0842 (0.0870) loss: 0.8216 (0.8192) time: 0.1282 data: 0.0459 max mem: 9390 +Train: [47] Total time: 0:14:50 (0.1426 s / it) +Averaged stats: lr: 0.000072 grad: 0.0842 (0.0870) loss: 0.8216 (0.8192) +Eval (hcp-train-subset): [47] [ 0/62] eta: 0:05:33 loss: 0.8505 (0.8505) time: 5.3842 data: 5.3528 max mem: 9390 +Eval (hcp-train-subset): [47] [61/62] eta: 0:00:00 loss: 0.8357 (0.8363) time: 0.1299 data: 0.1044 max mem: 9390 +Eval (hcp-train-subset): [47] Total time: 0:00:12 (0.2071 s / it) +Averaged stats (hcp-train-subset): loss: 0.8357 (0.8363) +Eval (hcp-val): [47] [ 0/62] eta: 0:03:58 loss: 0.8374 (0.8374) time: 3.8402 data: 3.7660 max mem: 9390 +Eval (hcp-val): [47] [61/62] eta: 0:00:00 loss: 0.8346 (0.8368) time: 0.1075 data: 0.0828 max mem: 9390 +Eval (hcp-val): [47] Total time: 0:00:12 (0.1951 s / it) +Averaged stats (hcp-val): loss: 0.8346 (0.8368) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +Train: [48] [ 0/6250] eta: 6:29:48 lr: 0.000072 grad: 0.0601 (0.0601) loss: 0.8596 (0.8596) time: 3.7422 data: 3.4838 max mem: 9390 +Train: [48] [ 100/6250] eta: 0:19:07 lr: 0.000072 grad: 0.0987 (0.1088) loss: 0.8220 (0.8345) time: 0.1438 data: 0.0573 max mem: 9390 +Train: [48] [ 200/6250] eta: 0:15:55 lr: 0.000072 grad: 0.0882 (0.1007) loss: 0.8223 (0.8276) time: 0.1282 data: 0.0390 max mem: 9390 +Train: [48] [ 300/6250] eta: 0:14:45 lr: 0.000072 grad: 0.0843 (0.0967) loss: 0.8189 (0.8238) time: 0.1248 data: 0.0374 max mem: 9390 +Train: [48] [ 400/6250] eta: 0:13:53 lr: 0.000072 grad: 0.0811 (0.0954) loss: 0.8215 (0.8221) time: 0.1182 data: 0.0267 max mem: 9390 +Train: [48] [ 500/6250] eta: 0:13:12 lr: 0.000072 grad: 0.0831 (0.0939) loss: 0.8192 (0.8217) time: 0.1067 data: 0.0163 max mem: 9390 +Train: [48] [ 600/6250] eta: 0:12:49 lr: 0.000072 grad: 0.0796 (0.0924) loss: 0.8238 (0.8220) time: 0.1407 data: 0.0553 max mem: 9390 +Train: [48] [ 700/6250] eta: 0:12:36 lr: 0.000072 grad: 0.0838 (0.0916) loss: 0.8211 (0.8222) time: 0.1562 data: 0.0798 max mem: 9390 +Train: [48] [ 800/6250] eta: 0:12:29 lr: 0.000072 grad: 0.0809 (0.0905) loss: 0.8262 (0.8226) time: 0.1573 data: 0.0714 max mem: 9390 +Train: [48] [ 900/6250] eta: 0:12:16 lr: 0.000071 grad: 0.0849 (0.0900) loss: 0.8171 (0.8227) time: 0.1533 data: 0.0733 max mem: 9390 +Train: [48] [1000/6250] eta: 0:12:08 lr: 0.000071 grad: 0.0817 (0.0894) loss: 0.8259 (0.8227) time: 0.1384 data: 0.0507 max mem: 9390 +Train: [48] [1100/6250] eta: 0:11:56 lr: 0.000071 grad: 0.0812 (0.0890) loss: 0.8277 (0.8226) time: 0.1444 data: 0.0652 max mem: 9390 +Train: [48] [1200/6250] eta: 0:11:48 lr: 0.000071 grad: 0.0861 (0.0891) loss: 0.8175 (0.8225) time: 0.1408 data: 0.0446 max mem: 9390 +Train: [48] [1300/6250] eta: 0:11:35 lr: 0.000071 grad: 0.0835 (0.0894) loss: 0.8162 (0.8223) time: 0.1693 data: 0.0499 max mem: 9390 +Train: [48] [1400/6250] eta: 0:11:20 lr: 0.000071 grad: 0.0887 (0.0894) loss: 0.8143 (0.8221) time: 0.1336 data: 0.0534 max mem: 9390 +Train: [48] [1500/6250] eta: 0:11:04 lr: 0.000071 grad: 0.0931 (0.0894) loss: 0.8118 (0.8219) time: 0.1571 data: 0.0753 max mem: 9390 +Train: [48] [1600/6250] eta: 0:10:50 lr: 0.000071 grad: 0.0866 (0.0893) loss: 0.8190 (0.8218) time: 0.1236 data: 0.0485 max mem: 9390 +Train: [48] [1700/6250] eta: 0:10:38 lr: 0.000071 grad: 0.0859 (0.0892) loss: 0.8203 (0.8218) time: 0.1933 data: 0.1181 max mem: 9390 +Train: [48] [1800/6250] eta: 0:10:26 lr: 0.000071 grad: 0.0839 (0.0892) loss: 0.8207 (0.8217) time: 0.1515 data: 0.0722 max mem: 9390 +Train: [48] [1900/6250] eta: 0:10:12 lr: 0.000071 grad: 0.0853 (0.0891) loss: 0.8223 (0.8216) time: 0.1658 data: 0.0803 max mem: 9390 +Train: [48] [2000/6250] eta: 0:09:57 lr: 0.000071 grad: 0.0892 (0.0892) loss: 0.8204 (0.8215) time: 0.1364 data: 0.0600 max mem: 9390 +Train: [48] [2100/6250] eta: 0:09:44 lr: 0.000071 grad: 0.0885 (0.0892) loss: 0.8178 (0.8215) time: 0.1533 data: 0.0720 max mem: 9390 +Train: [48] [2200/6250] eta: 0:09:29 lr: 0.000071 grad: 0.0832 (0.0892) loss: 0.8219 (0.8214) time: 0.1423 data: 0.0653 max mem: 9390 +Train: [48] [2300/6250] eta: 0:09:13 lr: 0.000071 grad: 0.0913 (0.0891) loss: 0.8138 (0.8213) time: 0.1424 data: 0.0448 max mem: 9390 +Train: [48] [2400/6250] eta: 0:09:04 lr: 0.000071 grad: 0.0879 (0.0891) loss: 0.8138 (0.8212) time: 0.0898 data: 0.0002 max mem: 9390 +Train: [48] [2500/6250] eta: 0:08:49 lr: 0.000071 grad: 0.0845 (0.0890) loss: 0.8226 (0.8212) time: 0.1357 data: 0.0535 max mem: 9390 +Train: [48] [2600/6250] eta: 0:08:34 lr: 0.000071 grad: 0.0930 (0.0891) loss: 0.8244 (0.8212) time: 0.1368 data: 0.0602 max mem: 9390 +Train: [48] [2700/6250] eta: 0:08:20 lr: 0.000071 grad: 0.0920 (0.0891) loss: 0.8190 (0.8211) time: 0.1423 data: 0.0642 max mem: 9390 +Train: [48] [2800/6250] eta: 0:08:06 lr: 0.000071 grad: 0.0911 (0.0894) loss: 0.8158 (0.8210) time: 0.1264 data: 0.0512 max mem: 9390 +Train: [48] [2900/6250] eta: 0:07:51 lr: 0.000071 grad: 0.0844 (0.0893) loss: 0.8147 (0.8209) time: 0.1275 data: 0.0495 max mem: 9390 +Train: [48] [3000/6250] eta: 0:07:37 lr: 0.000071 grad: 0.0872 (0.0894) loss: 0.8212 (0.8209) time: 0.1372 data: 0.0567 max mem: 9390 +Train: [48] [3100/6250] eta: 0:07:23 lr: 0.000071 grad: 0.0812 (0.0894) loss: 0.8236 (0.8209) time: 0.1517 data: 0.0716 max mem: 9390 +Train: [48] [3200/6250] eta: 0:07:10 lr: 0.000071 grad: 0.0925 (0.0894) loss: 0.8224 (0.8208) time: 0.1708 data: 0.0719 max mem: 9390 +Train: [48] [3300/6250] eta: 0:06:56 lr: 0.000071 grad: 0.0882 (0.0894) loss: 0.8199 (0.8208) time: 0.1376 data: 0.0598 max mem: 9390 +Train: [48] [3400/6250] eta: 0:06:40 lr: 0.000071 grad: 0.0863 (0.0895) loss: 0.8156 (0.8208) time: 0.1306 data: 0.0479 max mem: 9390 +Train: [48] [3500/6250] eta: 0:06:27 lr: 0.000071 grad: 0.0877 (0.0894) loss: 0.8121 (0.8208) time: 0.1310 data: 0.0570 max mem: 9390 +Train: [48] [3600/6250] eta: 0:06:12 lr: 0.000071 grad: 0.0877 (0.0895) loss: 0.8166 (0.8207) time: 0.1443 data: 0.0648 max mem: 9390 +Train: [48] [3700/6250] eta: 0:05:58 lr: 0.000071 grad: 0.0909 (0.0895) loss: 0.8186 (0.8207) time: 0.1374 data: 0.0555 max mem: 9390 +Train: [48] [3800/6250] eta: 0:05:44 lr: 0.000071 grad: 0.0887 (0.0895) loss: 0.8204 (0.8206) time: 0.1467 data: 0.0633 max mem: 9390 +Train: [48] [3900/6250] eta: 0:05:29 lr: 0.000070 grad: 0.0881 (0.0896) loss: 0.8183 (0.8206) time: 0.1498 data: 0.0701 max mem: 9390 +Train: [48] [4000/6250] eta: 0:05:15 lr: 0.000070 grad: 0.0862 (0.0896) loss: 0.8245 (0.8205) time: 0.1205 data: 0.0352 max mem: 9390 +Train: [48] [4100/6250] eta: 0:05:01 lr: 0.000070 grad: 0.0880 (0.0896) loss: 0.8160 (0.8204) time: 0.1484 data: 0.0674 max mem: 9390 +Train: [48] [4200/6250] eta: 0:04:46 lr: 0.000070 grad: 0.0829 (0.0896) loss: 0.8253 (0.8204) time: 0.1365 data: 0.0572 max mem: 9390 +Train: [48] [4300/6250] eta: 0:04:32 lr: 0.000070 grad: 0.0866 (0.0895) loss: 0.8196 (0.8205) time: 0.1262 data: 0.0416 max mem: 9390 +Train: [48] [4400/6250] eta: 0:04:18 lr: 0.000070 grad: 0.0863 (0.0895) loss: 0.8229 (0.8205) time: 0.1386 data: 0.0659 max mem: 9390 +Train: [48] [4500/6250] eta: 0:04:05 lr: 0.000070 grad: 0.0903 (0.0896) loss: 0.8230 (0.8206) time: 0.1443 data: 0.0644 max mem: 9390 +Train: [48] [4600/6250] eta: 0:03:51 lr: 0.000070 grad: 0.0892 (0.0896) loss: 0.8228 (0.8206) time: 0.1265 data: 0.0492 max mem: 9390 +Train: [48] [4700/6250] eta: 0:03:37 lr: 0.000070 grad: 0.0833 (0.0895) loss: 0.8237 (0.8207) time: 0.1443 data: 0.0658 max mem: 9390 +Train: [48] [4800/6250] eta: 0:03:23 lr: 0.000070 grad: 0.0817 (0.0895) loss: 0.8260 (0.8208) time: 0.1285 data: 0.0487 max mem: 9390 +Train: [48] [4900/6250] eta: 0:03:09 lr: 0.000070 grad: 0.0850 (0.0895) loss: 0.8251 (0.8208) time: 0.1962 data: 0.1107 max mem: 9390 +Train: [48] [5000/6250] eta: 0:02:55 lr: 0.000070 grad: 0.0806 (0.0894) loss: 0.8255 (0.8209) time: 0.1407 data: 0.0547 max mem: 9390 +Train: [48] [5100/6250] eta: 0:02:41 lr: 0.000070 grad: 0.0856 (0.0894) loss: 0.8270 (0.8211) time: 0.1227 data: 0.0378 max mem: 9390 +Train: [48] [5200/6250] eta: 0:02:27 lr: 0.000070 grad: 0.0898 (0.0894) loss: 0.8231 (0.8211) time: 0.1397 data: 0.0497 max mem: 9390 +Train: [48] [5300/6250] eta: 0:02:13 lr: 0.000070 grad: 0.0849 (0.0894) loss: 0.8278 (0.8212) time: 0.1082 data: 0.0285 max mem: 9390 +Train: [48] [5400/6250] eta: 0:01:59 lr: 0.000070 grad: 0.0866 (0.0896) loss: 0.8233 (0.8212) time: 0.1542 data: 0.0782 max mem: 9390 +Train: [48] [5500/6250] eta: 0:01:45 lr: 0.000070 grad: 0.0843 (0.0895) loss: 0.8221 (0.8213) time: 0.1583 data: 0.0764 max mem: 9390 +Train: [48] [5600/6250] eta: 0:01:31 lr: 0.000070 grad: 0.0850 (0.0895) loss: 0.8184 (0.8213) time: 0.1885 data: 0.1098 max mem: 9390 +Train: [48] [5700/6250] eta: 0:01:17 lr: 0.000070 grad: 0.0914 (0.0896) loss: 0.8200 (0.8213) time: 0.1581 data: 0.0802 max mem: 9390 +Train: [48] [5800/6250] eta: 0:01:03 lr: 0.000070 grad: 0.0857 (0.0896) loss: 0.8234 (0.8213) time: 0.1524 data: 0.0706 max mem: 9390 +Train: [48] [5900/6250] eta: 0:00:49 lr: 0.000070 grad: 0.0890 (0.0896) loss: 0.8126 (0.8212) time: 0.1468 data: 0.0635 max mem: 9390 +Train: [48] [6000/6250] eta: 0:00:35 lr: 0.000070 grad: 0.0903 (0.0896) loss: 0.8173 (0.8212) time: 0.1207 data: 0.0391 max mem: 9390 +Train: [48] [6100/6250] eta: 0:00:21 lr: 0.000070 grad: 0.0918 (0.0896) loss: 0.8158 (0.8211) time: 0.1217 data: 0.0383 max mem: 9390 +Train: [48] [6200/6250] eta: 0:00:07 lr: 0.000070 grad: 0.0864 (0.0897) loss: 0.8179 (0.8210) time: 0.1247 data: 0.0405 max mem: 9390 +Train: [48] [6249/6250] eta: 0:00:00 lr: 0.000070 grad: 0.0875 (0.0897) loss: 0.8170 (0.8210) time: 0.1160 data: 0.0310 max mem: 9390 +Train: [48] Total time: 0:14:45 (0.1416 s / it) +Averaged stats: lr: 0.000070 grad: 0.0875 (0.0897) loss: 0.8170 (0.8210) +Eval (hcp-train-subset): [48] [ 0/62] eta: 0:04:32 loss: 0.8508 (0.8508) time: 4.3956 data: 4.3620 max mem: 9390 +Eval (hcp-train-subset): [48] [61/62] eta: 0:00:00 loss: 0.8374 (0.8386) time: 0.1198 data: 0.0947 max mem: 9390 +Eval (hcp-train-subset): [48] Total time: 0:00:13 (0.2113 s / it) +Averaged stats (hcp-train-subset): loss: 0.8374 (0.8386) +Eval (hcp-val): [48] [ 0/62] eta: 0:04:26 loss: 0.8308 (0.8308) time: 4.2993 data: 4.2494 max mem: 9390 +Eval (hcp-val): [48] [61/62] eta: 0:00:00 loss: 0.8344 (0.8361) time: 0.1238 data: 0.0975 max mem: 9390 +Eval (hcp-val): [48] Total time: 0:00:12 (0.2005 s / it) +Averaged stats (hcp-val): loss: 0.8344 (0.8361) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +Train: [49] [ 0/6250] eta: 9:35:22 lr: 0.000070 grad: 0.0682 (0.0682) loss: 0.8165 (0.8165) time: 5.5237 data: 5.3935 max mem: 9390 +Train: [49] [ 100/6250] eta: 0:19:30 lr: 0.000070 grad: 0.0898 (0.1145) loss: 0.8252 (0.8235) time: 0.1281 data: 0.0264 max mem: 9390 +Train: [49] [ 200/6250] eta: 0:16:20 lr: 0.000070 grad: 0.0779 (0.1025) loss: 0.8305 (0.8253) time: 0.1221 data: 0.0331 max mem: 9390 +Train: [49] [ 300/6250] eta: 0:15:08 lr: 0.000070 grad: 0.0812 (0.0967) loss: 0.8301 (0.8265) time: 0.1196 data: 0.0295 max mem: 9390 +Train: [49] [ 400/6250] eta: 0:14:17 lr: 0.000070 grad: 0.0797 (0.0931) loss: 0.8339 (0.8270) time: 0.1191 data: 0.0254 max mem: 9390 +Train: [49] [ 500/6250] eta: 0:13:42 lr: 0.000070 grad: 0.0787 (0.0907) loss: 0.8204 (0.8270) time: 0.1283 data: 0.0476 max mem: 9390 +Train: [49] [ 600/6250] eta: 0:13:09 lr: 0.000070 grad: 0.0816 (0.0899) loss: 0.8270 (0.8266) time: 0.1259 data: 0.0375 max mem: 9390 +Train: [49] [ 700/6250] eta: 0:12:43 lr: 0.000069 grad: 0.0788 (0.0891) loss: 0.8240 (0.8263) time: 0.1209 data: 0.0344 max mem: 9390 +Train: [49] [ 800/6250] eta: 0:12:28 lr: 0.000069 grad: 0.0820 (0.0884) loss: 0.8286 (0.8264) time: 0.1317 data: 0.0500 max mem: 9390 +Train: [49] [ 900/6250] eta: 0:12:18 lr: 0.000069 grad: 0.0815 (0.0878) loss: 0.8269 (0.8264) time: 0.0960 data: 0.0002 max mem: 9390 +Train: [49] [1000/6250] eta: 0:12:03 lr: 0.000069 grad: 0.0752 (0.0869) loss: 0.8273 (0.8264) time: 0.1156 data: 0.0322 max mem: 9390 +Train: [49] [1100/6250] eta: 0:11:49 lr: 0.000069 grad: 0.0857 (0.0865) loss: 0.8262 (0.8262) time: 0.1334 data: 0.0478 max mem: 9390 +Train: [49] [1200/6250] eta: 0:11:43 lr: 0.000069 grad: 0.0871 (0.0864) loss: 0.8151 (0.8258) time: 0.1144 data: 0.0325 max mem: 9390 +Train: [49] [1300/6250] eta: 0:11:29 lr: 0.000069 grad: 0.0865 (0.0865) loss: 0.8152 (0.8253) time: 0.1405 data: 0.0649 max mem: 9390 +Train: [49] [1400/6250] eta: 0:11:12 lr: 0.000069 grad: 0.0806 (0.0864) loss: 0.8245 (0.8250) time: 0.1473 data: 0.0560 max mem: 9390 +Train: [49] [1500/6250] eta: 0:10:56 lr: 0.000069 grad: 0.0839 (0.0864) loss: 0.8263 (0.8246) time: 0.1352 data: 0.0624 max mem: 9390 +Train: [49] [1600/6250] eta: 0:10:48 lr: 0.000069 grad: 0.0839 (0.0865) loss: 0.8191 (0.8243) time: 0.1045 data: 0.0115 max mem: 9390 +Train: [49] [1700/6250] eta: 0:10:32 lr: 0.000069 grad: 0.0874 (0.0865) loss: 0.8177 (0.8240) time: 0.1341 data: 0.0592 max mem: 9390 +Train: [49] [1800/6250] eta: 0:10:19 lr: 0.000069 grad: 0.0822 (0.0867) loss: 0.8152 (0.8237) time: 0.1712 data: 0.0904 max mem: 9390 +Train: [49] [1900/6250] eta: 0:10:04 lr: 0.000069 grad: 0.0819 (0.0868) loss: 0.8249 (0.8235) time: 0.1489 data: 0.0720 max mem: 9390 +Train: [49] [2000/6250] eta: 0:09:51 lr: 0.000069 grad: 0.0859 (0.0870) loss: 0.8163 (0.8232) time: 0.1269 data: 0.0497 max mem: 9390 +Train: [49] [2100/6250] eta: 0:09:41 lr: 0.000069 grad: 0.0801 (0.0870) loss: 0.8211 (0.8230) time: 0.2745 data: 0.2005 max mem: 9390 +Train: [49] [2200/6250] eta: 0:09:22 lr: 0.000069 grad: 0.0905 (0.0871) loss: 0.8208 (0.8229) time: 0.1423 data: 0.0644 max mem: 9390 +Train: [49] [2300/6250] eta: 0:09:10 lr: 0.000069 grad: 0.0805 (0.0872) loss: 0.8261 (0.8228) time: 0.1464 data: 0.0680 max mem: 9390 +Train: [49] [2400/6250] eta: 0:08:58 lr: 0.000069 grad: 0.0887 (0.0873) loss: 0.8231 (0.8228) time: 0.1738 data: 0.0910 max mem: 9390 +Train: [49] [2500/6250] eta: 0:08:46 lr: 0.000069 grad: 0.0874 (0.0874) loss: 0.8277 (0.8228) time: 0.1444 data: 0.0672 max mem: 9390 +Train: [49] [2600/6250] eta: 0:08:33 lr: 0.000069 grad: 0.0946 (0.0875) loss: 0.8197 (0.8228) time: 0.1427 data: 0.0572 max mem: 9390 +Train: [49] [2700/6250] eta: 0:08:18 lr: 0.000069 grad: 0.0865 (0.0875) loss: 0.8230 (0.8228) time: 0.1138 data: 0.0294 max mem: 9390 +Train: [49] [2800/6250] eta: 0:08:04 lr: 0.000069 grad: 0.0839 (0.0875) loss: 0.8194 (0.8228) time: 0.1185 data: 0.0379 max mem: 9390 +Train: [49] [2900/6250] eta: 0:07:51 lr: 0.000069 grad: 0.0859 (0.0875) loss: 0.8208 (0.8228) time: 0.1401 data: 0.0519 max mem: 9390 +Train: [49] [3000/6250] eta: 0:07:36 lr: 0.000069 grad: 0.0848 (0.0875) loss: 0.8170 (0.8229) time: 0.1285 data: 0.0442 max mem: 9390 +Train: [49] [3100/6250] eta: 0:07:23 lr: 0.000069 grad: 0.0911 (0.0876) loss: 0.8249 (0.8229) time: 0.1319 data: 0.0519 max mem: 9390 +Train: [49] [3200/6250] eta: 0:07:09 lr: 0.000069 grad: 0.0896 (0.0877) loss: 0.8232 (0.8230) time: 0.1545 data: 0.0560 max mem: 9390 +Train: [49] [3300/6250] eta: 0:06:55 lr: 0.000069 grad: 0.0839 (0.0877) loss: 0.8284 (0.8231) time: 0.1525 data: 0.0747 max mem: 9390 +Train: [49] [3400/6250] eta: 0:06:40 lr: 0.000069 grad: 0.0892 (0.0878) loss: 0.8226 (0.8231) time: 0.1463 data: 0.0656 max mem: 9390 +Train: [49] [3500/6250] eta: 0:06:27 lr: 0.000069 grad: 0.0914 (0.0880) loss: 0.8134 (0.8230) time: 0.1421 data: 0.0588 max mem: 9390 +Train: [49] [3600/6250] eta: 0:06:13 lr: 0.000069 grad: 0.0894 (0.0882) loss: 0.8185 (0.8229) time: 0.1758 data: 0.0538 max mem: 9390 +Train: [49] [3700/6250] eta: 0:06:00 lr: 0.000069 grad: 0.0892 (0.0883) loss: 0.8213 (0.8229) time: 0.1302 data: 0.0484 max mem: 9390 +Train: [49] [3800/6250] eta: 0:05:45 lr: 0.000068 grad: 0.0880 (0.0884) loss: 0.8237 (0.8229) time: 0.1282 data: 0.0527 max mem: 9390 +Train: [49] [3900/6250] eta: 0:05:30 lr: 0.000068 grad: 0.0910 (0.0886) loss: 0.8249 (0.8228) time: 0.1336 data: 0.0488 max mem: 9390 +Train: [49] [4000/6250] eta: 0:05:16 lr: 0.000068 grad: 0.0861 (0.0886) loss: 0.8266 (0.8227) time: 0.1341 data: 0.0553 max mem: 9390 +Train: [49] [4100/6250] eta: 0:05:02 lr: 0.000068 grad: 0.0861 (0.0887) loss: 0.8276 (0.8227) time: 0.1375 data: 0.0575 max mem: 9390 +Train: [49] [4200/6250] eta: 0:04:48 lr: 0.000068 grad: 0.0891 (0.0888) loss: 0.8190 (0.8227) time: 0.1153 data: 0.0345 max mem: 9390 +Train: [49] [4300/6250] eta: 0:04:33 lr: 0.000068 grad: 0.0932 (0.0888) loss: 0.8216 (0.8227) time: 0.1230 data: 0.0443 max mem: 9390 +Train: [49] [4400/6250] eta: 0:04:19 lr: 0.000068 grad: 0.0894 (0.0890) loss: 0.8234 (0.8227) time: 0.1423 data: 0.0421 max mem: 9390 +Train: [49] [4500/6250] eta: 0:04:06 lr: 0.000068 grad: 0.0867 (0.0890) loss: 0.8233 (0.8227) time: 0.1473 data: 0.0682 max mem: 9390 +Train: [49] [4600/6250] eta: 0:03:52 lr: 0.000068 grad: 0.0932 (0.0891) loss: 0.8245 (0.8226) time: 0.1388 data: 0.0610 max mem: 9390 +Train: [49] [4700/6250] eta: 0:03:38 lr: 0.000068 grad: 0.0896 (0.0892) loss: 0.8201 (0.8226) time: 0.1526 data: 0.0766 max mem: 9390 +Train: [49] [4800/6250] eta: 0:03:24 lr: 0.000068 grad: 0.0913 (0.0893) loss: 0.8186 (0.8226) time: 0.1533 data: 0.0630 max mem: 9390 +Train: [49] [4900/6250] eta: 0:03:10 lr: 0.000068 grad: 0.0842 (0.0894) loss: 0.8216 (0.8225) time: 0.1107 data: 0.0318 max mem: 9390 +Train: [49] [5000/6250] eta: 0:02:55 lr: 0.000068 grad: 0.0961 (0.0894) loss: 0.8205 (0.8225) time: 0.1487 data: 0.0572 max mem: 9390 +Train: [49] [5100/6250] eta: 0:02:41 lr: 0.000068 grad: 0.0906 (0.0895) loss: 0.8243 (0.8225) time: 0.1121 data: 0.0323 max mem: 9390 +Train: [49] [5200/6250] eta: 0:02:27 lr: 0.000068 grad: 0.0941 (0.0895) loss: 0.8182 (0.8225) time: 0.1187 data: 0.0378 max mem: 9390 +Train: [49] [5300/6250] eta: 0:02:13 lr: 0.000068 grad: 0.0860 (0.0895) loss: 0.8184 (0.8225) time: 0.1323 data: 0.0544 max mem: 9390 +Train: [49] [5400/6250] eta: 0:01:59 lr: 0.000068 grad: 0.0956 (0.0896) loss: 0.8187 (0.8224) time: 0.1731 data: 0.0936 max mem: 9390 +Train: [49] [5500/6250] eta: 0:01:46 lr: 0.000068 grad: 0.0900 (0.0896) loss: 0.8210 (0.8224) time: 0.1605 data: 0.0743 max mem: 9390 +Train: [49] [5600/6250] eta: 0:01:31 lr: 0.000068 grad: 0.0948 (0.0897) loss: 0.8156 (0.8223) time: 0.0975 data: 0.0137 max mem: 9390 +Train: [49] [5700/6250] eta: 0:01:17 lr: 0.000068 grad: 0.0834 (0.0897) loss: 0.8254 (0.8222) time: 0.1350 data: 0.0431 max mem: 9390 +Train: [49] [5800/6250] eta: 0:01:03 lr: 0.000068 grad: 0.0894 (0.0896) loss: 0.8250 (0.8222) time: 0.1470 data: 0.0665 max mem: 9390 +Train: [49] [5900/6250] eta: 0:00:49 lr: 0.000068 grad: 0.0842 (0.0896) loss: 0.8234 (0.8222) time: 0.1417 data: 0.0635 max mem: 9390 +Train: [49] [6000/6250] eta: 0:00:35 lr: 0.000068 grad: 0.0869 (0.0896) loss: 0.8251 (0.8222) time: 0.1327 data: 0.0458 max mem: 9390 +Train: [49] [6100/6250] eta: 0:00:21 lr: 0.000068 grad: 0.0864 (0.0895) loss: 0.8198 (0.8222) time: 0.1387 data: 0.0577 max mem: 9390 +Train: [49] [6200/6250] eta: 0:00:07 lr: 0.000068 grad: 0.0896 (0.0895) loss: 0.8153 (0.8221) time: 0.1285 data: 0.0465 max mem: 9390 +Train: [49] [6249/6250] eta: 0:00:00 lr: 0.000068 grad: 0.0915 (0.0896) loss: 0.8224 (0.8221) time: 0.1304 data: 0.0457 max mem: 9390 +Train: [49] Total time: 0:14:46 (0.1418 s / it) +Averaged stats: lr: 0.000068 grad: 0.0915 (0.0896) loss: 0.8224 (0.8221) +Eval (hcp-train-subset): [49] [ 0/62] eta: 0:04:00 loss: 0.8418 (0.8418) time: 3.8803 data: 3.8091 max mem: 9390 +Eval (hcp-train-subset): [49] [61/62] eta: 0:00:00 loss: 0.8364 (0.8378) time: 0.1029 data: 0.0781 max mem: 9390 +Eval (hcp-train-subset): [49] Total time: 0:00:12 (0.2090 s / it) +Averaged stats (hcp-train-subset): loss: 0.8364 (0.8378) +Making plots (hcp-train-subset): example=41 +Eval (hcp-val): [49] [ 0/62] eta: 0:05:05 loss: 0.8322 (0.8322) time: 4.9262 data: 4.8962 max mem: 9390 +Eval (hcp-val): [49] [61/62] eta: 0:00:00 loss: 0.8335 (0.8356) time: 0.1027 data: 0.0759 max mem: 9390 +Eval (hcp-val): [49] Total time: 0:00:11 (0.1901 s / it) +Averaged stats (hcp-val): loss: 0.8335 (0.8356) +Making plots (hcp-val): example=43 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +Train: [50] [ 0/6250] eta: 9:07:50 lr: 0.000068 grad: 0.2102 (0.2102) loss: 0.8649 (0.8649) time: 5.2594 data: 5.1632 max mem: 9390 +Train: [50] [ 100/6250] eta: 0:18:31 lr: 0.000068 grad: 0.0874 (0.1020) loss: 0.8344 (0.8329) time: 0.1381 data: 0.0449 max mem: 9390 +Train: [50] [ 200/6250] eta: 0:15:42 lr: 0.000068 grad: 0.0743 (0.0943) loss: 0.8341 (0.8312) time: 0.1370 data: 0.0514 max mem: 9390 +Train: [50] [ 300/6250] eta: 0:14:24 lr: 0.000068 grad: 0.0743 (0.0906) loss: 0.8335 (0.8312) time: 0.1261 data: 0.0444 max mem: 9390 +Train: [50] [ 400/6250] eta: 0:13:37 lr: 0.000068 grad: 0.0851 (0.0894) loss: 0.8262 (0.8298) time: 0.1276 data: 0.0419 max mem: 9390 +Train: [50] [ 500/6250] eta: 0:13:04 lr: 0.000067 grad: 0.0814 (0.0894) loss: 0.8216 (0.8280) time: 0.1115 data: 0.0209 max mem: 9390 +Train: [50] [ 600/6250] eta: 0:12:40 lr: 0.000067 grad: 0.0857 (0.0891) loss: 0.8152 (0.8266) time: 0.1262 data: 0.0355 max mem: 9390 +Train: [50] [ 700/6250] eta: 0:12:22 lr: 0.000067 grad: 0.0833 (0.0889) loss: 0.8204 (0.8259) time: 0.1276 data: 0.0429 max mem: 9390 +Train: [50] [ 800/6250] eta: 0:12:09 lr: 0.000067 grad: 0.0818 (0.0890) loss: 0.8228 (0.8255) time: 0.1419 data: 0.0621 max mem: 9390 +Train: [50] [ 900/6250] eta: 0:12:00 lr: 0.000067 grad: 0.0864 (0.0890) loss: 0.8157 (0.8251) time: 0.1600 data: 0.0784 max mem: 9390 +Train: [50] [1000/6250] eta: 0:11:45 lr: 0.000067 grad: 0.0877 (0.0891) loss: 0.8210 (0.8248) time: 0.1337 data: 0.0508 max mem: 9390 +Train: [50] [1100/6250] eta: 0:11:28 lr: 0.000067 grad: 0.0887 (0.0892) loss: 0.8188 (0.8241) time: 0.1332 data: 0.0533 max mem: 9390 +Train: [50] [1200/6250] eta: 0:11:19 lr: 0.000067 grad: 0.0870 (0.0895) loss: 0.8210 (0.8237) time: 0.1413 data: 0.0628 max mem: 9390 +Train: [50] [1300/6250] eta: 0:11:05 lr: 0.000067 grad: 0.0821 (0.0897) loss: 0.8190 (0.8233) time: 0.1312 data: 0.0505 max mem: 9390 +Train: [50] [1400/6250] eta: 0:10:50 lr: 0.000067 grad: 0.0882 (0.0899) loss: 0.8154 (0.8228) time: 0.1350 data: 0.0527 max mem: 9390 +Train: [50] [1500/6250] eta: 0:10:37 lr: 0.000067 grad: 0.0831 (0.0901) loss: 0.8168 (0.8223) time: 0.1326 data: 0.0608 max mem: 9390 +Train: [50] [1600/6250] eta: 0:10:23 lr: 0.000067 grad: 0.0842 (0.0900) loss: 0.8169 (0.8222) time: 0.1500 data: 0.0530 max mem: 9390 +Train: [50] [1700/6250] eta: 0:10:12 lr: 0.000067 grad: 0.0842 (0.0900) loss: 0.8164 (0.8219) time: 0.1560 data: 0.0781 max mem: 9390 +Train: [50] [1800/6250] eta: 0:09:58 lr: 0.000067 grad: 0.0861 (0.0899) loss: 0.8188 (0.8218) time: 0.1356 data: 0.0570 max mem: 9390 +Train: [50] [1900/6250] eta: 0:09:50 lr: 0.000067 grad: 0.0826 (0.0898) loss: 0.8257 (0.8218) time: 0.1945 data: 0.1153 max mem: 9390 +Train: [50] [2000/6250] eta: 0:09:41 lr: 0.000067 grad: 0.0905 (0.0897) loss: 0.8198 (0.8217) time: 0.1354 data: 0.0545 max mem: 9390 +Train: [50] [2100/6250] eta: 0:09:28 lr: 0.000067 grad: 0.0876 (0.0898) loss: 0.8178 (0.8216) time: 0.1858 data: 0.1055 max mem: 9390 +Train: [50] [2200/6250] eta: 0:09:17 lr: 0.000067 grad: 0.0813 (0.0897) loss: 0.8191 (0.8216) time: 0.1640 data: 0.0898 max mem: 9390 +Train: [50] [2300/6250] eta: 0:09:04 lr: 0.000067 grad: 0.0832 (0.0897) loss: 0.8253 (0.8215) time: 0.1245 data: 0.0489 max mem: 9390 +Train: [50] [2400/6250] eta: 0:08:50 lr: 0.000067 grad: 0.0831 (0.0897) loss: 0.8221 (0.8215) time: 0.1158 data: 0.0375 max mem: 9390 +Train: [50] [2500/6250] eta: 0:08:38 lr: 0.000067 grad: 0.0879 (0.0897) loss: 0.8212 (0.8215) time: 0.1319 data: 0.0545 max mem: 9390 +Train: [50] [2600/6250] eta: 0:08:24 lr: 0.000067 grad: 0.0900 (0.0896) loss: 0.8219 (0.8215) time: 0.1318 data: 0.0539 max mem: 9390 +Train: [50] [2700/6250] eta: 0:08:09 lr: 0.000067 grad: 0.0855 (0.0895) loss: 0.8187 (0.8214) time: 0.1199 data: 0.0382 max mem: 9390 +Train: [50] [2800/6250] eta: 0:07:55 lr: 0.000067 grad: 0.0841 (0.0895) loss: 0.8241 (0.8214) time: 0.1415 data: 0.0492 max mem: 9390 +Train: [50] [2900/6250] eta: 0:07:42 lr: 0.000067 grad: 0.0888 (0.0896) loss: 0.8176 (0.8214) time: 0.1405 data: 0.0598 max mem: 9390 +Train: [50] [3000/6250] eta: 0:07:29 lr: 0.000067 grad: 0.0894 (0.0896) loss: 0.8155 (0.8213) time: 0.1478 data: 0.0643 max mem: 9390 +Train: [50] [3100/6250] eta: 0:07:16 lr: 0.000067 grad: 0.0850 (0.0896) loss: 0.8201 (0.8213) time: 0.1492 data: 0.0628 max mem: 9390 +Train: [50] [3200/6250] eta: 0:07:03 lr: 0.000067 grad: 0.0799 (0.0895) loss: 0.8225 (0.8213) time: 0.1315 data: 0.0541 max mem: 9390 +Train: [50] [3300/6250] eta: 0:06:49 lr: 0.000067 grad: 0.0841 (0.0895) loss: 0.8238 (0.8213) time: 0.1284 data: 0.0511 max mem: 9390 +Train: [50] [3400/6250] eta: 0:06:34 lr: 0.000067 grad: 0.0897 (0.0895) loss: 0.8185 (0.8213) time: 0.1280 data: 0.0514 max mem: 9390 +Train: [50] [3500/6250] eta: 0:06:21 lr: 0.000067 grad: 0.0882 (0.0895) loss: 0.8148 (0.8212) time: 0.1315 data: 0.0500 max mem: 9390 +Train: [50] [3600/6250] eta: 0:06:08 lr: 0.000066 grad: 0.0847 (0.0894) loss: 0.8175 (0.8212) time: 0.1334 data: 0.0461 max mem: 9390 +Train: [50] [3700/6250] eta: 0:05:55 lr: 0.000066 grad: 0.0833 (0.0896) loss: 0.8186 (0.8212) time: 0.2025 data: 0.0950 max mem: 9390 +Train: [50] [3800/6250] eta: 0:05:41 lr: 0.000066 grad: 0.0948 (0.0897) loss: 0.8163 (0.8210) time: 0.1227 data: 0.0388 max mem: 9390 +Train: [50] [3900/6250] eta: 0:05:27 lr: 0.000066 grad: 0.0917 (0.0897) loss: 0.8184 (0.8209) time: 0.1347 data: 0.0523 max mem: 9390 +Train: [50] [4000/6250] eta: 0:05:13 lr: 0.000066 grad: 0.0880 (0.0898) loss: 0.8190 (0.8208) time: 0.1420 data: 0.0615 max mem: 9390 +Train: [50] [4100/6250] eta: 0:04:59 lr: 0.000066 grad: 0.0950 (0.0899) loss: 0.8106 (0.8207) time: 0.1414 data: 0.0624 max mem: 9390 +Train: [50] [4200/6250] eta: 0:04:45 lr: 0.000066 grad: 0.0946 (0.0900) loss: 0.8125 (0.8206) time: 0.1501 data: 0.0582 max mem: 9390 +Train: [50] [4300/6250] eta: 0:04:31 lr: 0.000066 grad: 0.0935 (0.0900) loss: 0.8146 (0.8205) time: 0.1510 data: 0.0760 max mem: 9390 +Train: [50] [4400/6250] eta: 0:04:18 lr: 0.000066 grad: 0.0944 (0.0901) loss: 0.8094 (0.8205) time: 0.1145 data: 0.0353 max mem: 9390 +Train: [50] [4500/6250] eta: 0:04:04 lr: 0.000066 grad: 0.0866 (0.0902) loss: 0.8236 (0.8204) time: 0.1261 data: 0.0472 max mem: 9390 +Train: [50] [4600/6250] eta: 0:03:50 lr: 0.000066 grad: 0.0870 (0.0902) loss: 0.8231 (0.8204) time: 0.1534 data: 0.0693 max mem: 9390 +Train: [50] [4700/6250] eta: 0:03:36 lr: 0.000066 grad: 0.0963 (0.0903) loss: 0.8165 (0.8203) time: 0.1662 data: 0.0840 max mem: 9390 +Train: [50] [4800/6250] eta: 0:03:22 lr: 0.000066 grad: 0.0870 (0.0903) loss: 0.8257 (0.8204) time: 0.1448 data: 0.0603 max mem: 9390 +Train: [50] [4900/6250] eta: 0:03:08 lr: 0.000066 grad: 0.0902 (0.0904) loss: 0.8130 (0.8204) time: 0.1355 data: 0.0570 max mem: 9390 +Train: [50] [5000/6250] eta: 0:02:54 lr: 0.000066 grad: 0.0888 (0.0904) loss: 0.8198 (0.8204) time: 0.1238 data: 0.0479 max mem: 9390 +Train: [50] [5100/6250] eta: 0:02:40 lr: 0.000066 grad: 0.0945 (0.0906) loss: 0.8163 (0.8203) time: 0.1266 data: 0.0419 max mem: 9390 +Train: [50] [5200/6250] eta: 0:02:26 lr: 0.000066 grad: 0.0858 (0.0908) loss: 0.8215 (0.8204) time: 0.1373 data: 0.0535 max mem: 9390 +Train: [50] [5300/6250] eta: 0:02:12 lr: 0.000066 grad: 0.0885 (0.0908) loss: 0.8152 (0.8204) time: 0.1905 data: 0.0963 max mem: 9390 +Train: [50] [5400/6250] eta: 0:01:59 lr: 0.000066 grad: 0.0836 (0.0908) loss: 0.8192 (0.8204) time: 0.1503 data: 0.0658 max mem: 9390 +Train: [50] [5500/6250] eta: 0:01:45 lr: 0.000066 grad: 0.0913 (0.0907) loss: 0.8173 (0.8203) time: 0.1271 data: 0.0498 max mem: 9390 +Train: [50] [5600/6250] eta: 0:01:31 lr: 0.000066 grad: 0.0839 (0.0907) loss: 0.8239 (0.8203) time: 0.1581 data: 0.0814 max mem: 9390 +Train: [50] [5700/6250] eta: 0:01:17 lr: 0.000066 grad: 0.0908 (0.0908) loss: 0.8193 (0.8203) time: 0.1803 data: 0.1010 max mem: 9390 +Train: [50] [5800/6250] eta: 0:01:03 lr: 0.000066 grad: 0.0860 (0.0908) loss: 0.8254 (0.8203) time: 0.1376 data: 0.0586 max mem: 9390 +Train: [50] [5900/6250] eta: 0:00:49 lr: 0.000066 grad: 0.0921 (0.0908) loss: 0.8136 (0.8202) time: 0.1136 data: 0.0327 max mem: 9390 +Train: [50] [6000/6250] eta: 0:00:34 lr: 0.000066 grad: 0.0912 (0.0909) loss: 0.8219 (0.8202) time: 0.1341 data: 0.0547 max mem: 9390 +Train: [50] [6100/6250] eta: 0:00:20 lr: 0.000066 grad: 0.0893 (0.0910) loss: 0.8146 (0.8201) time: 0.1228 data: 0.0436 max mem: 9390 +Train: [50] [6200/6250] eta: 0:00:06 lr: 0.000066 grad: 0.0877 (0.0911) loss: 0.8246 (0.8202) time: 0.1318 data: 0.0526 max mem: 9390 +Train: [50] [6249/6250] eta: 0:00:00 lr: 0.000066 grad: 0.0921 (0.0911) loss: 0.8118 (0.8201) time: 0.1147 data: 0.0364 max mem: 9390 +Train: [50] Total time: 0:14:35 (0.1400 s / it) +Averaged stats: lr: 0.000066 grad: 0.0921 (0.0911) loss: 0.8118 (0.8201) +Eval (hcp-train-subset): [50] [ 0/62] eta: 0:04:24 loss: 0.8484 (0.8484) time: 4.2687 data: 4.1950 max mem: 9390 +Eval (hcp-train-subset): [50] [61/62] eta: 0:00:00 loss: 0.8379 (0.8390) time: 0.1226 data: 0.0974 max mem: 9390 +Eval (hcp-train-subset): [50] Total time: 0:00:12 (0.2049 s / it) +Averaged stats (hcp-train-subset): loss: 0.8379 (0.8390) +Eval (hcp-val): [50] [ 0/62] eta: 0:04:41 loss: 0.8392 (0.8392) time: 4.5395 data: 4.5098 max mem: 9390 +Eval (hcp-val): [50] [61/62] eta: 0:00:00 loss: 0.8347 (0.8362) time: 0.1061 data: 0.0795 max mem: 9390 +Eval (hcp-val): [50] Total time: 0:00:11 (0.1896 s / it) +Averaged stats (hcp-val): loss: 0.8347 (0.8362) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +Train: [51] [ 0/6250] eta: 9:29:11 lr: 0.000066 grad: 0.1275 (0.1275) loss: 0.8396 (0.8396) time: 5.4643 data: 5.3759 max mem: 9390 +Train: [51] [ 100/6250] eta: 0:18:26 lr: 0.000066 grad: 0.0895 (0.0899) loss: 0.8267 (0.8339) time: 0.1374 data: 0.0415 max mem: 9390 +Train: [51] [ 200/6250] eta: 0:15:36 lr: 0.000066 grad: 0.0826 (0.0923) loss: 0.8300 (0.8306) time: 0.1329 data: 0.0452 max mem: 9390 +Train: [51] [ 300/6250] eta: 0:14:18 lr: 0.000065 grad: 0.0866 (0.0899) loss: 0.8379 (0.8303) time: 0.1121 data: 0.0293 max mem: 9390 +Train: [51] [ 400/6250] eta: 0:13:31 lr: 0.000065 grad: 0.0791 (0.0883) loss: 0.8284 (0.8298) time: 0.1047 data: 0.0070 max mem: 9390 +Train: [51] [ 500/6250] eta: 0:13:01 lr: 0.000065 grad: 0.0819 (0.0878) loss: 0.8253 (0.8287) time: 0.1324 data: 0.0512 max mem: 9390 +Train: [51] [ 600/6250] eta: 0:12:41 lr: 0.000065 grad: 0.0840 (0.0874) loss: 0.8229 (0.8281) time: 0.1359 data: 0.0491 max mem: 9390 +Train: [51] [ 700/6250] eta: 0:12:19 lr: 0.000065 grad: 0.0803 (0.0868) loss: 0.8303 (0.8281) time: 0.1280 data: 0.0413 max mem: 9390 +Train: [51] [ 800/6250] eta: 0:12:03 lr: 0.000065 grad: 0.0782 (0.0865) loss: 0.8297 (0.8278) time: 0.1341 data: 0.0537 max mem: 9390 +Train: [51] [ 900/6250] eta: 0:11:53 lr: 0.000065 grad: 0.0831 (0.0865) loss: 0.8286 (0.8275) time: 0.1234 data: 0.0411 max mem: 9390 +Train: [51] [1000/6250] eta: 0:11:41 lr: 0.000065 grad: 0.0826 (0.0864) loss: 0.8233 (0.8270) time: 0.1350 data: 0.0552 max mem: 9390 +Train: [51] [1100/6250] eta: 0:11:26 lr: 0.000065 grad: 0.0766 (0.0866) loss: 0.8265 (0.8265) time: 0.1316 data: 0.0554 max mem: 9390 +Train: [51] [1200/6250] eta: 0:11:20 lr: 0.000065 grad: 0.0886 (0.0874) loss: 0.8218 (0.8262) time: 0.1956 data: 0.0742 max mem: 9390 +Train: [51] [1300/6250] eta: 0:11:10 lr: 0.000065 grad: 0.0886 (0.0873) loss: 0.8196 (0.8259) time: 0.1463 data: 0.0674 max mem: 9390 +Train: [51] [1400/6250] eta: 0:10:55 lr: 0.000065 grad: 0.0791 (0.0874) loss: 0.8304 (0.8257) time: 0.1300 data: 0.0499 max mem: 9390 +Train: [51] [1500/6250] eta: 0:10:44 lr: 0.000065 grad: 0.0810 (0.0874) loss: 0.8273 (0.8256) time: 0.1599 data: 0.0662 max mem: 9390 +Train: [51] [1600/6250] eta: 0:10:35 lr: 0.000065 grad: 0.0908 (0.0874) loss: 0.8224 (0.8255) time: 0.1675 data: 0.0921 max mem: 9390 +Train: [51] [1700/6250] eta: 0:10:22 lr: 0.000065 grad: 0.0882 (0.0876) loss: 0.8310 (0.8254) time: 0.1567 data: 0.0636 max mem: 9390 +Train: [51] [1800/6250] eta: 0:10:09 lr: 0.000065 grad: 0.0879 (0.0879) loss: 0.8190 (0.8252) time: 0.1260 data: 0.0494 max mem: 9390 +Train: [51] [1900/6250] eta: 0:09:56 lr: 0.000065 grad: 0.0786 (0.0880) loss: 0.8296 (0.8250) time: 0.1204 data: 0.0393 max mem: 9390 +Train: [51] [2000/6250] eta: 0:09:44 lr: 0.000065 grad: 0.0911 (0.0880) loss: 0.8237 (0.8248) time: 0.1692 data: 0.0832 max mem: 9390 +Train: [51] [2100/6250] eta: 0:09:31 lr: 0.000065 grad: 0.0902 (0.0883) loss: 0.8211 (0.8247) time: 0.1331 data: 0.0564 max mem: 9390 +Train: [51] [2200/6250] eta: 0:09:18 lr: 0.000065 grad: 0.0853 (0.0884) loss: 0.8208 (0.8246) time: 0.1332 data: 0.0525 max mem: 9390 +Train: [51] [2300/6250] eta: 0:09:05 lr: 0.000065 grad: 0.0867 (0.0885) loss: 0.8247 (0.8245) time: 0.1582 data: 0.0698 max mem: 9390 +Train: [51] [2400/6250] eta: 0:08:51 lr: 0.000065 grad: 0.0889 (0.0886) loss: 0.8252 (0.8246) time: 0.1238 data: 0.0413 max mem: 9390 +Train: [51] [2500/6250] eta: 0:08:38 lr: 0.000065 grad: 0.0860 (0.0885) loss: 0.8164 (0.8245) time: 0.1107 data: 0.0343 max mem: 9390 +Train: [51] [2600/6250] eta: 0:08:24 lr: 0.000065 grad: 0.0854 (0.0885) loss: 0.8232 (0.8245) time: 0.1246 data: 0.0484 max mem: 9390 +Train: [51] [2700/6250] eta: 0:08:08 lr: 0.000065 grad: 0.0840 (0.0886) loss: 0.8245 (0.8244) time: 0.1263 data: 0.0498 max mem: 9390 +Train: [51] [2800/6250] eta: 0:07:54 lr: 0.000065 grad: 0.0857 (0.0888) loss: 0.8235 (0.8242) time: 0.1396 data: 0.0625 max mem: 9390 +Train: [51] [2900/6250] eta: 0:07:39 lr: 0.000065 grad: 0.0874 (0.0888) loss: 0.8230 (0.8241) time: 0.1155 data: 0.0351 max mem: 9390 +Train: [51] [3000/6250] eta: 0:07:24 lr: 0.000065 grad: 0.0825 (0.0888) loss: 0.8198 (0.8241) time: 0.1393 data: 0.0661 max mem: 9390 +Train: [51] [3100/6250] eta: 0:07:11 lr: 0.000065 grad: 0.0857 (0.0888) loss: 0.8228 (0.8240) time: 0.1257 data: 0.0476 max mem: 9390 +Train: [51] [3200/6250] eta: 0:06:56 lr: 0.000065 grad: 0.0873 (0.0888) loss: 0.8256 (0.8240) time: 0.1299 data: 0.0527 max mem: 9390 +Train: [51] [3300/6250] eta: 0:06:42 lr: 0.000065 grad: 0.0819 (0.0888) loss: 0.8229 (0.8239) time: 0.1187 data: 0.0369 max mem: 9390 +Train: [51] [3400/6250] eta: 0:06:29 lr: 0.000064 grad: 0.0812 (0.0887) loss: 0.8224 (0.8239) time: 0.1482 data: 0.0651 max mem: 9390 +Train: [51] [3500/6250] eta: 0:06:15 lr: 0.000064 grad: 0.0842 (0.0887) loss: 0.8276 (0.8239) time: 0.1389 data: 0.0601 max mem: 9390 +Train: [51] [3600/6250] eta: 0:06:01 lr: 0.000064 grad: 0.0849 (0.0886) loss: 0.8248 (0.8238) time: 0.1374 data: 0.0589 max mem: 9390 +Train: [51] [3700/6250] eta: 0:05:48 lr: 0.000064 grad: 0.0893 (0.0887) loss: 0.8219 (0.8238) time: 0.1567 data: 0.0667 max mem: 9390 +Train: [51] [3800/6250] eta: 0:05:36 lr: 0.000064 grad: 0.0874 (0.0886) loss: 0.8201 (0.8239) time: 0.0846 data: 0.0002 max mem: 9390 +Train: [51] [3900/6250] eta: 0:05:22 lr: 0.000064 grad: 0.0854 (0.0885) loss: 0.8210 (0.8239) time: 0.1674 data: 0.0877 max mem: 9390 +Train: [51] [4000/6250] eta: 0:05:09 lr: 0.000064 grad: 0.0885 (0.0885) loss: 0.8245 (0.8239) time: 0.0961 data: 0.0101 max mem: 9390 +Train: [51] [4100/6250] eta: 0:04:56 lr: 0.000064 grad: 0.0860 (0.0884) loss: 0.8265 (0.8239) time: 0.1901 data: 0.1204 max mem: 9390 +Train: [51] [4200/6250] eta: 0:04:42 lr: 0.000064 grad: 0.0865 (0.0884) loss: 0.8204 (0.8239) time: 0.1326 data: 0.0534 max mem: 9390 +Train: [51] [4300/6250] eta: 0:04:29 lr: 0.000064 grad: 0.0844 (0.0884) loss: 0.8255 (0.8238) time: 0.1413 data: 0.0647 max mem: 9390 +Train: [51] [4400/6250] eta: 0:04:16 lr: 0.000064 grad: 0.0864 (0.0884) loss: 0.8232 (0.8238) time: 0.1552 data: 0.0785 max mem: 9390 +Train: [51] [4500/6250] eta: 0:04:02 lr: 0.000064 grad: 0.0879 (0.0884) loss: 0.8191 (0.8237) time: 0.1344 data: 0.0524 max mem: 9390 +Train: [51] [4600/6250] eta: 0:03:48 lr: 0.000064 grad: 0.0886 (0.0884) loss: 0.8194 (0.8236) time: 0.1384 data: 0.0606 max mem: 9390 +Train: [51] [4700/6250] eta: 0:03:34 lr: 0.000064 grad: 0.0882 (0.0885) loss: 0.8198 (0.8235) time: 0.1383 data: 0.0608 max mem: 9390 +Train: [51] [4800/6250] eta: 0:03:20 lr: 0.000064 grad: 0.0900 (0.0886) loss: 0.8136 (0.8235) time: 0.1360 data: 0.0591 max mem: 9390 +Train: [51] [4900/6250] eta: 0:03:06 lr: 0.000064 grad: 0.0884 (0.0886) loss: 0.8209 (0.8234) time: 0.1437 data: 0.0702 max mem: 9390 +Train: [51] [5000/6250] eta: 0:02:52 lr: 0.000064 grad: 0.0842 (0.0887) loss: 0.8174 (0.8233) time: 0.1378 data: 0.0516 max mem: 9390 +Train: [51] [5100/6250] eta: 0:02:39 lr: 0.000064 grad: 0.0918 (0.0887) loss: 0.8172 (0.8232) time: 0.1375 data: 0.0500 max mem: 9390 +Train: [51] [5200/6250] eta: 0:02:25 lr: 0.000064 grad: 0.0860 (0.0887) loss: 0.8221 (0.8232) time: 0.1042 data: 0.0257 max mem: 9390 +Train: [51] [5300/6250] eta: 0:02:11 lr: 0.000064 grad: 0.0861 (0.0888) loss: 0.8194 (0.8231) time: 0.1231 data: 0.0467 max mem: 9390 +Train: [51] [5400/6250] eta: 0:01:58 lr: 0.000064 grad: 0.0895 (0.0888) loss: 0.8137 (0.8230) time: 0.1451 data: 0.0605 max mem: 9390 +Train: [51] [5500/6250] eta: 0:01:44 lr: 0.000064 grad: 0.0910 (0.0889) loss: 0.8206 (0.8229) time: 0.1482 data: 0.0663 max mem: 9390 +Train: [51] [5600/6250] eta: 0:01:30 lr: 0.000064 grad: 0.0884 (0.0889) loss: 0.8254 (0.8229) time: 0.1000 data: 0.0127 max mem: 9390 +Train: [51] [5700/6250] eta: 0:01:16 lr: 0.000064 grad: 0.0816 (0.0889) loss: 0.8289 (0.8229) time: 0.1474 data: 0.0651 max mem: 9390 +Train: [51] [5800/6250] eta: 0:01:02 lr: 0.000064 grad: 0.0868 (0.0889) loss: 0.8186 (0.8229) time: 0.1217 data: 0.0390 max mem: 9390 +Train: [51] [5900/6250] eta: 0:00:48 lr: 0.000064 grad: 0.0952 (0.0890) loss: 0.8124 (0.8228) time: 0.1237 data: 0.0445 max mem: 9390 +Train: [51] [6000/6250] eta: 0:00:34 lr: 0.000064 grad: 0.0932 (0.0890) loss: 0.8174 (0.8227) time: 0.1291 data: 0.0470 max mem: 9390 +Train: [51] [6100/6250] eta: 0:00:20 lr: 0.000064 grad: 0.0880 (0.0891) loss: 0.8217 (0.8227) time: 0.1417 data: 0.0598 max mem: 9390 +Train: [51] [6200/6250] eta: 0:00:06 lr: 0.000064 grad: 0.0881 (0.0891) loss: 0.8173 (0.8226) time: 0.1119 data: 0.0306 max mem: 9390 +Train: [51] [6249/6250] eta: 0:00:00 lr: 0.000064 grad: 0.0932 (0.0891) loss: 0.8162 (0.8226) time: 0.1311 data: 0.0531 max mem: 9390 +Train: [51] Total time: 0:14:26 (0.1387 s / it) +Averaged stats: lr: 0.000064 grad: 0.0932 (0.0891) loss: 0.8162 (0.8226) +Eval (hcp-train-subset): [51] [ 0/62] eta: 0:03:28 loss: 0.8462 (0.8462) time: 3.3636 data: 3.2474 max mem: 9390 +Eval (hcp-train-subset): [51] [61/62] eta: 0:00:00 loss: 0.8369 (0.8372) time: 0.1154 data: 0.0904 max mem: 9390 +Eval (hcp-train-subset): [51] Total time: 0:00:12 (0.1990 s / it) +Averaged stats (hcp-train-subset): loss: 0.8369 (0.8372) +Eval (hcp-val): [51] [ 0/62] eta: 0:04:26 loss: 0.8323 (0.8323) time: 4.3064 data: 4.2436 max mem: 9390 +Eval (hcp-val): [51] [61/62] eta: 0:00:00 loss: 0.8336 (0.8358) time: 0.0904 data: 0.0657 max mem: 9390 +Eval (hcp-val): [51] Total time: 0:00:11 (0.1927 s / it) +Averaged stats (hcp-val): loss: 0.8336 (0.8358) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +Train: [52] [ 0/6250] eta: 9:58:57 lr: 0.000064 grad: 0.0820 (0.0820) loss: 0.8700 (0.8700) time: 5.7501 data: 5.6441 max mem: 9390 +Train: [52] [ 100/6250] eta: 0:18:48 lr: 0.000063 grad: 0.0987 (0.0967) loss: 0.8314 (0.8362) time: 0.1312 data: 0.0457 max mem: 9390 +Train: [52] [ 200/6250] eta: 0:16:16 lr: 0.000063 grad: 0.0887 (0.0968) loss: 0.8284 (0.8317) time: 0.1380 data: 0.0420 max mem: 9390 +Train: [52] [ 300/6250] eta: 0:14:46 lr: 0.000063 grad: 0.0893 (0.0948) loss: 0.8236 (0.8295) time: 0.1256 data: 0.0372 max mem: 9390 +Train: [52] [ 400/6250] eta: 0:13:58 lr: 0.000063 grad: 0.0808 (0.0935) loss: 0.8278 (0.8282) time: 0.1013 data: 0.0040 max mem: 9390 +Train: [52] [ 500/6250] eta: 0:13:17 lr: 0.000063 grad: 0.0824 (0.0928) loss: 0.8280 (0.8270) time: 0.1347 data: 0.0538 max mem: 9390 +Train: [52] [ 600/6250] eta: 0:12:46 lr: 0.000063 grad: 0.0921 (0.0926) loss: 0.8206 (0.8258) time: 0.1223 data: 0.0381 max mem: 9390 +Train: [52] [ 700/6250] eta: 0:12:26 lr: 0.000063 grad: 0.0845 (0.0917) loss: 0.8245 (0.8254) time: 0.1385 data: 0.0466 max mem: 9390 +Train: [52] [ 800/6250] eta: 0:12:12 lr: 0.000063 grad: 0.0833 (0.0910) loss: 0.8253 (0.8251) time: 0.1378 data: 0.0589 max mem: 9390 +Train: [52] [ 900/6250] eta: 0:12:01 lr: 0.000063 grad: 0.0860 (0.0909) loss: 0.8204 (0.8246) time: 0.1286 data: 0.0539 max mem: 9390 +Train: [52] [1000/6250] eta: 0:11:45 lr: 0.000063 grad: 0.0888 (0.0908) loss: 0.8155 (0.8240) time: 0.1289 data: 0.0521 max mem: 9390 +Train: [52] [1100/6250] eta: 0:11:28 lr: 0.000063 grad: 0.0847 (0.0906) loss: 0.8161 (0.8236) time: 0.1282 data: 0.0469 max mem: 9390 +Train: [52] [1200/6250] eta: 0:11:21 lr: 0.000063 grad: 0.0849 (0.0902) loss: 0.8211 (0.8233) time: 0.1525 data: 0.0609 max mem: 9390 +Train: [52] [1300/6250] eta: 0:11:09 lr: 0.000063 grad: 0.0840 (0.0900) loss: 0.8171 (0.8230) time: 0.1513 data: 0.0686 max mem: 9390 +Train: [52] [1400/6250] eta: 0:10:55 lr: 0.000063 grad: 0.0837 (0.0898) loss: 0.8151 (0.8229) time: 0.1202 data: 0.0416 max mem: 9390 +Train: [52] [1500/6250] eta: 0:10:45 lr: 0.000063 grad: 0.0884 (0.0898) loss: 0.8129 (0.8225) time: 0.1257 data: 0.0487 max mem: 9390 +Train: [52] [1600/6250] eta: 0:10:36 lr: 0.000063 grad: 0.0846 (0.0898) loss: 0.8254 (0.8223) time: 0.1530 data: 0.0775 max mem: 9390 +Train: [52] [1700/6250] eta: 0:10:24 lr: 0.000063 grad: 0.0849 (0.0897) loss: 0.8166 (0.8221) time: 0.1514 data: 0.0750 max mem: 9390 +Train: [52] [1800/6250] eta: 0:10:12 lr: 0.000063 grad: 0.0903 (0.0897) loss: 0.8201 (0.8220) time: 0.1633 data: 0.0863 max mem: 9390 +Train: [52] [1900/6250] eta: 0:10:02 lr: 0.000063 grad: 0.0937 (0.0897) loss: 0.8217 (0.8220) time: 0.1615 data: 0.0815 max mem: 9390 +Train: [52] [2000/6250] eta: 0:09:48 lr: 0.000063 grad: 0.0893 (0.0897) loss: 0.8193 (0.8220) time: 0.1423 data: 0.0627 max mem: 9390 +Train: [52] [2100/6250] eta: 0:09:35 lr: 0.000063 grad: 0.0857 (0.0898) loss: 0.8153 (0.8218) time: 0.1390 data: 0.0603 max mem: 9390 +Train: [52] [2200/6250] eta: 0:09:22 lr: 0.000063 grad: 0.0842 (0.0898) loss: 0.8216 (0.8218) time: 0.1619 data: 0.0793 max mem: 9390 +Train: [52] [2300/6250] eta: 0:09:06 lr: 0.000063 grad: 0.0915 (0.0900) loss: 0.8167 (0.8217) time: 0.1351 data: 0.0545 max mem: 9390 +Train: [52] [2400/6250] eta: 0:08:51 lr: 0.000063 grad: 0.0882 (0.0901) loss: 0.8194 (0.8216) time: 0.1280 data: 0.0458 max mem: 9390 +Train: [52] [2500/6250] eta: 0:08:36 lr: 0.000063 grad: 0.0946 (0.0901) loss: 0.8174 (0.8216) time: 0.1266 data: 0.0484 max mem: 9390 +Train: [52] [2600/6250] eta: 0:08:21 lr: 0.000063 grad: 0.0852 (0.0901) loss: 0.8238 (0.8215) time: 0.1418 data: 0.0671 max mem: 9390 +Train: [52] [2700/6250] eta: 0:08:07 lr: 0.000063 grad: 0.0834 (0.0901) loss: 0.8214 (0.8215) time: 0.1221 data: 0.0445 max mem: 9390 +Train: [52] [2800/6250] eta: 0:07:53 lr: 0.000063 grad: 0.0865 (0.0901) loss: 0.8221 (0.8215) time: 0.1425 data: 0.0609 max mem: 9390 +Train: [52] [2900/6250] eta: 0:07:39 lr: 0.000063 grad: 0.0910 (0.0902) loss: 0.8248 (0.8215) time: 0.1204 data: 0.0444 max mem: 9390 +Train: [52] [3000/6250] eta: 0:07:25 lr: 0.000063 grad: 0.0873 (0.0903) loss: 0.8257 (0.8215) time: 0.1376 data: 0.0626 max mem: 9390 +Train: [52] [3100/6250] eta: 0:07:12 lr: 0.000063 grad: 0.0878 (0.0902) loss: 0.8107 (0.8215) time: 0.1773 data: 0.0893 max mem: 9390 +Train: [52] [3200/6250] eta: 0:06:59 lr: 0.000062 grad: 0.0881 (0.0902) loss: 0.8238 (0.8214) time: 0.1690 data: 0.0826 max mem: 9390 +Train: [52] [3300/6250] eta: 0:06:46 lr: 0.000062 grad: 0.0862 (0.0901) loss: 0.8250 (0.8215) time: 0.1365 data: 0.0644 max mem: 9390 +Train: [52] [3400/6250] eta: 0:06:32 lr: 0.000062 grad: 0.0935 (0.0900) loss: 0.8197 (0.8215) time: 0.1260 data: 0.0467 max mem: 9390 +Train: [52] [3500/6250] eta: 0:06:18 lr: 0.000062 grad: 0.0883 (0.0901) loss: 0.8215 (0.8215) time: 0.1512 data: 0.0698 max mem: 9390 +Train: [52] [3600/6250] eta: 0:06:05 lr: 0.000062 grad: 0.0845 (0.0901) loss: 0.8279 (0.8215) time: 0.1250 data: 0.0494 max mem: 9390 +Train: [52] [3700/6250] eta: 0:05:51 lr: 0.000062 grad: 0.0865 (0.0900) loss: 0.8224 (0.8214) time: 0.1382 data: 0.0617 max mem: 9390 +Train: [52] [3800/6250] eta: 0:05:37 lr: 0.000062 grad: 0.0901 (0.0900) loss: 0.8217 (0.8214) time: 0.1545 data: 0.0698 max mem: 9390 +Train: [52] [3900/6250] eta: 0:05:23 lr: 0.000062 grad: 0.0870 (0.0900) loss: 0.8224 (0.8215) time: 0.1016 data: 0.0204 max mem: 9390 +Train: [52] [4000/6250] eta: 0:05:10 lr: 0.000062 grad: 0.0838 (0.0899) loss: 0.8254 (0.8216) time: 0.1620 data: 0.0833 max mem: 9390 +Train: [52] [4100/6250] eta: 0:04:56 lr: 0.000062 grad: 0.0908 (0.0900) loss: 0.8223 (0.8215) time: 0.1413 data: 0.0632 max mem: 9390 +Train: [52] [4200/6250] eta: 0:04:42 lr: 0.000062 grad: 0.0891 (0.0900) loss: 0.8276 (0.8216) time: 0.1207 data: 0.0383 max mem: 9390 +Train: [52] [4300/6250] eta: 0:04:28 lr: 0.000062 grad: 0.0860 (0.0901) loss: 0.8281 (0.8216) time: 0.1361 data: 0.0578 max mem: 9390 +Train: [52] [4400/6250] eta: 0:04:14 lr: 0.000062 grad: 0.0923 (0.0901) loss: 0.8205 (0.8217) time: 0.1404 data: 0.0644 max mem: 9390 +Train: [52] [4500/6250] eta: 0:04:01 lr: 0.000062 grad: 0.0890 (0.0902) loss: 0.8236 (0.8217) time: 0.1450 data: 0.0651 max mem: 9390 +Train: [52] [4600/6250] eta: 0:03:47 lr: 0.000062 grad: 0.0951 (0.0902) loss: 0.8194 (0.8217) time: 0.1401 data: 0.0618 max mem: 9390 +Train: [52] [4700/6250] eta: 0:03:33 lr: 0.000062 grad: 0.0849 (0.0902) loss: 0.8180 (0.8217) time: 0.1511 data: 0.0730 max mem: 9390 +Train: [52] [4800/6250] eta: 0:03:19 lr: 0.000062 grad: 0.0921 (0.0903) loss: 0.8245 (0.8217) time: 0.1001 data: 0.0204 max mem: 9390 +Train: [52] [4900/6250] eta: 0:03:06 lr: 0.000062 grad: 0.0969 (0.0905) loss: 0.8204 (0.8216) time: 0.1245 data: 0.0444 max mem: 9390 +Train: [52] [5000/6250] eta: 0:02:52 lr: 0.000062 grad: 0.0881 (0.0906) loss: 0.8218 (0.8216) time: 0.1180 data: 0.0418 max mem: 9390 +Train: [52] [5100/6250] eta: 0:02:38 lr: 0.000062 grad: 0.0947 (0.0906) loss: 0.8211 (0.8216) time: 0.1456 data: 0.0691 max mem: 9390 +Train: [52] [5200/6250] eta: 0:02:25 lr: 0.000062 grad: 0.0896 (0.0907) loss: 0.8200 (0.8215) time: 0.1568 data: 0.0714 max mem: 9390 +Train: [52] [5300/6250] eta: 0:02:11 lr: 0.000062 grad: 0.0956 (0.0908) loss: 0.8173 (0.8215) time: 0.1501 data: 0.0742 max mem: 9390 +Train: [52] [5400/6250] eta: 0:01:57 lr: 0.000062 grad: 0.1001 (0.0909) loss: 0.8250 (0.8215) time: 0.1539 data: 0.0675 max mem: 9390 +Train: [52] [5500/6250] eta: 0:01:43 lr: 0.000062 grad: 0.0859 (0.0909) loss: 0.8186 (0.8215) time: 0.1614 data: 0.0850 max mem: 9390 +Train: [52] [5600/6250] eta: 0:01:30 lr: 0.000062 grad: 0.0965 (0.0910) loss: 0.8218 (0.8214) time: 0.1412 data: 0.0560 max mem: 9390 +Train: [52] [5700/6250] eta: 0:01:16 lr: 0.000062 grad: 0.0902 (0.0911) loss: 0.8192 (0.8214) time: 0.1245 data: 0.0462 max mem: 9390 +Train: [52] [5800/6250] eta: 0:01:02 lr: 0.000062 grad: 0.0863 (0.0911) loss: 0.8170 (0.8213) time: 0.1259 data: 0.0472 max mem: 9390 +Train: [52] [5900/6250] eta: 0:00:48 lr: 0.000062 grad: 0.0947 (0.0912) loss: 0.8205 (0.8213) time: 0.1361 data: 0.0522 max mem: 9390 +Train: [52] [6000/6250] eta: 0:00:34 lr: 0.000062 grad: 0.0934 (0.0912) loss: 0.8195 (0.8213) time: 0.1099 data: 0.0308 max mem: 9390 +Train: [52] [6100/6250] eta: 0:00:20 lr: 0.000062 grad: 0.0976 (0.0913) loss: 0.8179 (0.8212) time: 0.0897 data: 0.0002 max mem: 9390 +Train: [52] [6200/6250] eta: 0:00:06 lr: 0.000061 grad: 0.0929 (0.0913) loss: 0.8137 (0.8212) time: 0.1436 data: 0.0635 max mem: 9390 +Train: [52] [6249/6250] eta: 0:00:00 lr: 0.000061 grad: 0.0923 (0.0913) loss: 0.8163 (0.8212) time: 0.1150 data: 0.0412 max mem: 9390 +Train: [52] Total time: 0:14:21 (0.1378 s / it) +Averaged stats: lr: 0.000061 grad: 0.0923 (0.0913) loss: 0.8163 (0.8212) +Eval (hcp-train-subset): [52] [ 0/62] eta: 0:03:48 loss: 0.8503 (0.8503) time: 3.6817 data: 3.5990 max mem: 9390 +Eval (hcp-train-subset): [52] [61/62] eta: 0:00:00 loss: 0.8363 (0.8367) time: 0.1182 data: 0.0933 max mem: 9390 +Eval (hcp-train-subset): [52] Total time: 0:00:12 (0.2022 s / it) +Averaged stats (hcp-train-subset): loss: 0.8363 (0.8367) +Eval (hcp-val): [52] [ 0/62] eta: 0:03:20 loss: 0.8315 (0.8315) time: 3.2389 data: 3.1706 max mem: 9390 +Eval (hcp-val): [52] [61/62] eta: 0:00:00 loss: 0.8341 (0.8350) time: 0.1035 data: 0.0769 max mem: 9390 +Eval (hcp-val): [52] Total time: 0:00:11 (0.1886 s / it) +Averaged stats (hcp-val): loss: 0.8341 (0.8350) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +Train: [53] [ 0/6250] eta: 6:23:46 lr: 0.000061 grad: 0.0554 (0.0554) loss: 0.8706 (0.8706) time: 3.6843 data: 3.3914 max mem: 9390 +Train: [53] [ 100/6250] eta: 0:18:31 lr: 0.000061 grad: 0.0928 (0.1217) loss: 0.8146 (0.8256) time: 0.1271 data: 0.0212 max mem: 9390 +Train: [53] [ 200/6250] eta: 0:15:52 lr: 0.000061 grad: 0.0956 (0.1131) loss: 0.8105 (0.8199) time: 0.1132 data: 0.0237 max mem: 9390 +Train: [53] [ 300/6250] eta: 0:14:40 lr: 0.000061 grad: 0.0887 (0.1070) loss: 0.8171 (0.8193) time: 0.1355 data: 0.0565 max mem: 9390 +Train: [53] [ 400/6250] eta: 0:13:59 lr: 0.000061 grad: 0.0959 (0.1034) loss: 0.8128 (0.8193) time: 0.1148 data: 0.0354 max mem: 9390 +Train: [53] [ 500/6250] eta: 0:13:27 lr: 0.000061 grad: 0.0891 (0.1012) loss: 0.8244 (0.8196) time: 0.1397 data: 0.0609 max mem: 9390 +Train: [53] [ 600/6250] eta: 0:13:00 lr: 0.000061 grad: 0.0912 (0.1004) loss: 0.8218 (0.8194) time: 0.1459 data: 0.0534 max mem: 9390 +Train: [53] [ 700/6250] eta: 0:12:32 lr: 0.000061 grad: 0.0905 (0.0994) loss: 0.8226 (0.8194) time: 0.1362 data: 0.0513 max mem: 9390 +Train: [53] [ 800/6250] eta: 0:12:15 lr: 0.000061 grad: 0.0879 (0.0985) loss: 0.8284 (0.8193) time: 0.1431 data: 0.0674 max mem: 9390 +Train: [53] [ 900/6250] eta: 0:12:08 lr: 0.000061 grad: 0.0939 (0.0977) loss: 0.8206 (0.8193) time: 0.1450 data: 0.0630 max mem: 9390 +Train: [53] [1000/6250] eta: 0:11:51 lr: 0.000061 grad: 0.0917 (0.0973) loss: 0.8139 (0.8191) time: 0.1334 data: 0.0550 max mem: 9390 +Train: [53] [1100/6250] eta: 0:11:43 lr: 0.000061 grad: 0.0935 (0.0969) loss: 0.8236 (0.8192) time: 0.1708 data: 0.0921 max mem: 9390 +Train: [53] [1200/6250] eta: 0:11:25 lr: 0.000061 grad: 0.0918 (0.0964) loss: 0.8123 (0.8190) time: 0.1226 data: 0.0389 max mem: 9390 +Train: [53] [1300/6250] eta: 0:11:18 lr: 0.000061 grad: 0.0875 (0.0961) loss: 0.8185 (0.8189) time: 0.1723 data: 0.0936 max mem: 9390 +Train: [53] [1400/6250] eta: 0:11:06 lr: 0.000061 grad: 0.0940 (0.0961) loss: 0.8160 (0.8187) time: 0.1451 data: 0.0552 max mem: 9390 +Train: [53] [1500/6250] eta: 0:10:53 lr: 0.000061 grad: 0.0898 (0.0959) loss: 0.8166 (0.8186) time: 0.1398 data: 0.0610 max mem: 9390 +Train: [53] [1600/6250] eta: 0:10:40 lr: 0.000061 grad: 0.0899 (0.0958) loss: 0.8140 (0.8184) time: 0.1531 data: 0.0735 max mem: 9390 +Train: [53] [1700/6250] eta: 0:10:25 lr: 0.000061 grad: 0.0960 (0.0958) loss: 0.8129 (0.8183) time: 0.1232 data: 0.0445 max mem: 9390 +Train: [53] [1800/6250] eta: 0:10:14 lr: 0.000061 grad: 0.0891 (0.0957) loss: 0.8167 (0.8182) time: 0.1237 data: 0.0436 max mem: 9390 +Train: [53] [1900/6250] eta: 0:10:04 lr: 0.000061 grad: 0.0915 (0.0955) loss: 0.8221 (0.8183) time: 0.1480 data: 0.0635 max mem: 9390 +Train: [53] [2000/6250] eta: 0:09:51 lr: 0.000061 grad: 0.0897 (0.0957) loss: 0.8160 (0.8183) time: 0.1699 data: 0.0838 max mem: 9390 +Train: [53] [2100/6250] eta: 0:09:38 lr: 0.000061 grad: 0.0937 (0.0955) loss: 0.8209 (0.8184) time: 0.1462 data: 0.0721 max mem: 9390 +Train: [53] [2200/6250] eta: 0:09:23 lr: 0.000061 grad: 0.0930 (0.0954) loss: 0.8133 (0.8183) time: 0.1399 data: 0.0589 max mem: 9390 +Train: [53] [2300/6250] eta: 0:09:09 lr: 0.000061 grad: 0.0965 (0.0953) loss: 0.8151 (0.8183) time: 0.1348 data: 0.0514 max mem: 9390 +Train: [53] [2400/6250] eta: 0:08:55 lr: 0.000061 grad: 0.0962 (0.0954) loss: 0.8132 (0.8183) time: 0.1469 data: 0.0620 max mem: 9390 +Train: [53] [2500/6250] eta: 0:08:40 lr: 0.000061 grad: 0.0922 (0.0954) loss: 0.8204 (0.8183) time: 0.1156 data: 0.0356 max mem: 9390 +Train: [53] [2600/6250] eta: 0:08:27 lr: 0.000061 grad: 0.0970 (0.0954) loss: 0.8140 (0.8182) time: 0.1406 data: 0.0634 max mem: 9390 +Train: [53] [2700/6250] eta: 0:08:12 lr: 0.000061 grad: 0.0939 (0.0954) loss: 0.8173 (0.8182) time: 0.1317 data: 0.0563 max mem: 9390 +Train: [53] [2800/6250] eta: 0:07:57 lr: 0.000061 grad: 0.0937 (0.0955) loss: 0.8148 (0.8181) time: 0.1222 data: 0.0422 max mem: 9390 +Train: [53] [2900/6250] eta: 0:07:43 lr: 0.000061 grad: 0.0972 (0.0955) loss: 0.8123 (0.8180) time: 0.1268 data: 0.0478 max mem: 9390 +Train: [53] [3000/6250] eta: 0:07:30 lr: 0.000060 grad: 0.0834 (0.0954) loss: 0.8229 (0.8180) time: 0.1684 data: 0.0844 max mem: 9390 +Train: [53] [3100/6250] eta: 0:07:16 lr: 0.000060 grad: 0.0837 (0.0955) loss: 0.8258 (0.8180) time: 0.1188 data: 0.0261 max mem: 9390 +Train: [53] [3200/6250] eta: 0:07:03 lr: 0.000060 grad: 0.0955 (0.0955) loss: 0.8218 (0.8180) time: 0.1430 data: 0.0613 max mem: 9390 +Train: [53] [3300/6250] eta: 0:06:49 lr: 0.000060 grad: 0.0941 (0.0955) loss: 0.8136 (0.8180) time: 0.1521 data: 0.0678 max mem: 9390 +Train: [53] [3400/6250] eta: 0:06:36 lr: 0.000060 grad: 0.0949 (0.0956) loss: 0.8167 (0.8179) time: 0.1658 data: 0.0728 max mem: 9390 +Train: [53] [3500/6250] eta: 0:06:22 lr: 0.000060 grad: 0.0931 (0.0957) loss: 0.8098 (0.8177) time: 0.1417 data: 0.0519 max mem: 9390 +Train: [53] [3600/6250] eta: 0:06:08 lr: 0.000060 grad: 0.0844 (0.0958) loss: 0.8163 (0.8176) time: 0.1257 data: 0.0465 max mem: 9390 +Train: [53] [3700/6250] eta: 0:05:54 lr: 0.000060 grad: 0.0943 (0.0959) loss: 0.8130 (0.8175) time: 0.1419 data: 0.0576 max mem: 9390 +Train: [53] [3800/6250] eta: 0:05:41 lr: 0.000060 grad: 0.0910 (0.0959) loss: 0.8142 (0.8174) time: 0.1744 data: 0.0862 max mem: 9390 +Train: [53] [3900/6250] eta: 0:05:27 lr: 0.000060 grad: 0.0897 (0.0960) loss: 0.8110 (0.8172) time: 0.1365 data: 0.0559 max mem: 9390 +Train: [53] [4000/6250] eta: 0:05:15 lr: 0.000060 grad: 0.0931 (0.0960) loss: 0.8035 (0.8171) time: 0.1943 data: 0.1013 max mem: 9390 +Train: [53] [4100/6250] eta: 0:05:00 lr: 0.000060 grad: 0.0944 (0.0961) loss: 0.8094 (0.8170) time: 0.1440 data: 0.0706 max mem: 9390 +Train: [53] [4200/6250] eta: 0:04:46 lr: 0.000060 grad: 0.0963 (0.0962) loss: 0.8175 (0.8169) time: 0.1687 data: 0.0964 max mem: 9390 +Train: [53] [4300/6250] eta: 0:04:32 lr: 0.000060 grad: 0.0912 (0.0963) loss: 0.8091 (0.8168) time: 0.1346 data: 0.0558 max mem: 9390 +Train: [53] [4400/6250] eta: 0:04:19 lr: 0.000060 grad: 0.0934 (0.0964) loss: 0.8193 (0.8168) time: 0.1636 data: 0.0879 max mem: 9390 +Train: [53] [4500/6250] eta: 0:04:05 lr: 0.000060 grad: 0.0936 (0.0966) loss: 0.8107 (0.8167) time: 0.1087 data: 0.0286 max mem: 9390 +Train: [53] [4600/6250] eta: 0:03:51 lr: 0.000060 grad: 0.0921 (0.0966) loss: 0.8176 (0.8167) time: 0.1114 data: 0.0309 max mem: 9390 +Train: [53] [4700/6250] eta: 0:03:36 lr: 0.000060 grad: 0.0930 (0.0967) loss: 0.8188 (0.8166) time: 0.1022 data: 0.0227 max mem: 9390 +Train: [53] [4800/6250] eta: 0:03:22 lr: 0.000060 grad: 0.0941 (0.0967) loss: 0.8120 (0.8166) time: 0.0996 data: 0.0162 max mem: 9390 +Train: [53] [4900/6250] eta: 0:03:08 lr: 0.000060 grad: 0.0879 (0.0966) loss: 0.8201 (0.8166) time: 0.1372 data: 0.0528 max mem: 9390 +Train: [53] [5000/6250] eta: 0:02:54 lr: 0.000060 grad: 0.0952 (0.0966) loss: 0.8255 (0.8166) time: 0.1443 data: 0.0670 max mem: 9390 +Train: [53] [5100/6250] eta: 0:02:40 lr: 0.000060 grad: 0.0919 (0.0966) loss: 0.8174 (0.8166) time: 0.1682 data: 0.0920 max mem: 9390 +Train: [53] [5200/6250] eta: 0:02:26 lr: 0.000060 grad: 0.0967 (0.0966) loss: 0.8145 (0.8166) time: 0.1402 data: 0.0598 max mem: 9390 +Train: [53] [5300/6250] eta: 0:02:13 lr: 0.000060 grad: 0.0957 (0.0966) loss: 0.8125 (0.8167) time: 0.1473 data: 0.0688 max mem: 9390 +Train: [53] [5400/6250] eta: 0:01:59 lr: 0.000060 grad: 0.0932 (0.0965) loss: 0.8172 (0.8167) time: 0.1567 data: 0.0767 max mem: 9390 +Train: [53] [5500/6250] eta: 0:01:45 lr: 0.000060 grad: 0.0906 (0.0964) loss: 0.8209 (0.8168) time: 0.1390 data: 0.0583 max mem: 9390 +Train: [53] [5600/6250] eta: 0:01:31 lr: 0.000060 grad: 0.0920 (0.0964) loss: 0.8257 (0.8168) time: 0.1415 data: 0.0602 max mem: 9390 +Train: [53] [5700/6250] eta: 0:01:17 lr: 0.000060 grad: 0.0936 (0.0963) loss: 0.8162 (0.8169) time: 0.1346 data: 0.0565 max mem: 9390 +Train: [53] [5800/6250] eta: 0:01:02 lr: 0.000060 grad: 0.0932 (0.0963) loss: 0.8173 (0.8169) time: 0.1155 data: 0.0337 max mem: 9390 +Train: [53] [5900/6250] eta: 0:00:48 lr: 0.000060 grad: 0.0917 (0.0963) loss: 0.8161 (0.8170) time: 0.1219 data: 0.0442 max mem: 9390 +Train: [53] [6000/6250] eta: 0:00:34 lr: 0.000059 grad: 0.0923 (0.0963) loss: 0.8234 (0.8170) time: 0.1234 data: 0.0452 max mem: 9390 +Train: [53] [6100/6250] eta: 0:00:20 lr: 0.000059 grad: 0.0875 (0.0963) loss: 0.8211 (0.8171) time: 0.0936 data: 0.0065 max mem: 9390 +Train: [53] [6200/6250] eta: 0:00:06 lr: 0.000059 grad: 0.0894 (0.0962) loss: 0.8182 (0.8171) time: 0.1211 data: 0.0365 max mem: 9390 +Train: [53] [6249/6250] eta: 0:00:00 lr: 0.000059 grad: 0.0981 (0.0962) loss: 0.8167 (0.8171) time: 0.1168 data: 0.0291 max mem: 9390 +Train: [53] Total time: 0:14:28 (0.1390 s / it) +Averaged stats: lr: 0.000059 grad: 0.0981 (0.0962) loss: 0.8167 (0.8171) +Eval (hcp-train-subset): [53] [ 0/62] eta: 0:04:36 loss: 0.8507 (0.8507) time: 4.4541 data: 4.4229 max mem: 9390 +Eval (hcp-train-subset): [53] [61/62] eta: 0:00:00 loss: 0.8387 (0.8376) time: 0.1249 data: 0.0997 max mem: 9390 +Eval (hcp-train-subset): [53] Total time: 0:00:12 (0.2095 s / it) +Averaged stats (hcp-train-subset): loss: 0.8387 (0.8376) +Eval (hcp-val): [53] [ 0/62] eta: 0:03:12 loss: 0.8323 (0.8323) time: 3.1069 data: 3.0337 max mem: 9390 +Eval (hcp-val): [53] [61/62] eta: 0:00:00 loss: 0.8338 (0.8352) time: 0.1079 data: 0.0832 max mem: 9390 +Eval (hcp-val): [53] Total time: 0:00:11 (0.1888 s / it) +Averaged stats (hcp-val): loss: 0.8338 (0.8352) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +Train: [54] [ 0/6250] eta: 9:52:33 lr: 0.000059 grad: nan (nan) loss: 0.8539 (0.8539) time: 5.6885 data: 5.6020 max mem: 9390 +Train: [54] [ 100/6250] eta: 0:18:51 lr: 0.000059 grad: 0.0867 (0.1086) loss: 0.8219 (0.8302) time: 0.1602 data: 0.0707 max mem: 9390 +Train: [54] [ 200/6250] eta: 0:16:08 lr: 0.000059 grad: 0.0965 (0.1084) loss: 0.8045 (0.8196) time: 0.1376 data: 0.0476 max mem: 9390 +Train: [54] [ 300/6250] eta: 0:15:00 lr: 0.000059 grad: 0.0988 (0.1049) loss: 0.8111 (0.8180) time: 0.1267 data: 0.0415 max mem: 9390 +Train: [54] [ 400/6250] eta: 0:14:15 lr: 0.000059 grad: 0.0939 (0.1027) loss: 0.8185 (0.8178) time: 0.1369 data: 0.0490 max mem: 9390 +Train: [54] [ 500/6250] eta: 0:13:29 lr: 0.000059 grad: 0.0855 (0.1003) loss: 0.8289 (0.8180) time: 0.1190 data: 0.0336 max mem: 9390 +Train: [54] [ 600/6250] eta: 0:12:53 lr: 0.000059 grad: 0.0908 (0.0988) loss: 0.8191 (0.8181) time: 0.1035 data: 0.0212 max mem: 9390 +Train: [54] [ 700/6250] eta: 0:12:28 lr: 0.000059 grad: 0.0896 (0.0980) loss: 0.8224 (0.8184) time: 0.1389 data: 0.0565 max mem: 9390 +Train: [54] [ 800/6250] eta: 0:12:09 lr: 0.000059 grad: 0.0887 (0.0970) loss: 0.8175 (0.8188) time: 0.1469 data: 0.0669 max mem: 9390 +Train: [54] [ 900/6250] eta: 0:11:58 lr: 0.000059 grad: 0.0818 (0.0958) loss: 0.8260 (0.8194) time: 0.1369 data: 0.0612 max mem: 9390 +Train: [54] [1000/6250] eta: 0:11:52 lr: 0.000059 grad: 0.0865 (0.0953) loss: 0.8244 (0.8197) time: 0.1457 data: 0.0601 max mem: 9390 +Train: [54] [1100/6250] eta: 0:11:42 lr: 0.000059 grad: 0.0853 (0.0948) loss: 0.8245 (0.8200) time: 0.1634 data: 0.0869 max mem: 9390 +Train: [54] [1200/6250] eta: 0:11:27 lr: 0.000059 grad: 0.0894 (0.0944) loss: 0.8244 (0.8204) time: 0.1247 data: 0.0446 max mem: 9390 +Train: [54] [1300/6250] eta: 0:11:14 lr: 0.000059 grad: 0.0895 (0.0940) loss: 0.8183 (0.8205) time: 0.1381 data: 0.0631 max mem: 9390 +Train: [54] [1400/6250] eta: 0:11:06 lr: 0.000059 grad: 0.0904 (0.0939) loss: 0.8220 (0.8207) time: 0.1406 data: 0.0637 max mem: 9390 +Train: [54] [1500/6250] eta: 0:10:50 lr: 0.000059 grad: 0.0860 (0.0936) loss: 0.8178 (0.8207) time: 0.1207 data: 0.0390 max mem: 9390 +Train: [54] [1600/6250] eta: 0:10:38 lr: 0.000059 grad: 0.0844 (0.0933) loss: 0.8229 (0.8208) time: 0.1245 data: 0.0397 max mem: 9390 +Train: [54] [1700/6250] eta: 0:10:27 lr: 0.000059 grad: 0.0887 (0.0931) loss: 0.8196 (0.8208) time: 0.1480 data: 0.0715 max mem: 9390 +Train: [54] [1800/6250] eta: 0:10:14 lr: 0.000059 grad: 0.0883 (0.0929) loss: 0.8266 (0.8209) time: 0.1554 data: 0.0611 max mem: 9390 +Train: [54] [1900/6250] eta: 0:09:59 lr: 0.000059 grad: 0.0862 (0.0927) loss: 0.8296 (0.8210) time: 0.1433 data: 0.0564 max mem: 9390 +Train: [54] [2000/6250] eta: 0:09:46 lr: 0.000059 grad: 0.0850 (0.0926) loss: 0.8223 (0.8211) time: 0.1424 data: 0.0653 max mem: 9390 +Train: [54] [2100/6250] eta: 0:09:31 lr: 0.000059 grad: 0.0835 (0.0925) loss: 0.8234 (0.8210) time: 0.1406 data: 0.0590 max mem: 9390 +Train: [54] [2200/6250] eta: 0:09:16 lr: 0.000059 grad: 0.0898 (0.0925) loss: 0.8215 (0.8211) time: 0.1426 data: 0.0577 max mem: 9390 +Train: [54] [2300/6250] eta: 0:09:05 lr: 0.000059 grad: 0.0854 (0.0923) loss: 0.8256 (0.8212) time: 0.1502 data: 0.0681 max mem: 9390 +Train: [54] [2400/6250] eta: 0:08:50 lr: 0.000059 grad: 0.0846 (0.0923) loss: 0.8273 (0.8213) time: 0.1242 data: 0.0460 max mem: 9390 +Train: [54] [2500/6250] eta: 0:08:36 lr: 0.000059 grad: 0.0917 (0.0923) loss: 0.8203 (0.8213) time: 0.1525 data: 0.0756 max mem: 9390 +Train: [54] [2600/6250] eta: 0:08:20 lr: 0.000059 grad: 0.0865 (0.0924) loss: 0.8240 (0.8213) time: 0.1248 data: 0.0436 max mem: 9390 +Train: [54] [2700/6250] eta: 0:08:07 lr: 0.000059 grad: 0.0925 (0.0924) loss: 0.8177 (0.8213) time: 0.1276 data: 0.0487 max mem: 9390 +Train: [54] [2800/6250] eta: 0:07:53 lr: 0.000058 grad: 0.0924 (0.0923) loss: 0.8148 (0.8212) time: 0.1540 data: 0.0714 max mem: 9390 +Train: [54] [2900/6250] eta: 0:07:39 lr: 0.000058 grad: 0.0845 (0.0923) loss: 0.8257 (0.8212) time: 0.1337 data: 0.0553 max mem: 9390 +Train: [54] [3000/6250] eta: 0:07:26 lr: 0.000058 grad: 0.0909 (0.0924) loss: 0.8186 (0.8212) time: 0.1104 data: 0.0224 max mem: 9390 +Train: [54] [3100/6250] eta: 0:07:12 lr: 0.000058 grad: 0.0905 (0.0925) loss: 0.8191 (0.8211) time: 0.1365 data: 0.0556 max mem: 9390 +Train: [54] [3200/6250] eta: 0:06:58 lr: 0.000058 grad: 0.0947 (0.0926) loss: 0.8197 (0.8211) time: 0.1333 data: 0.0514 max mem: 9390 +Train: [54] [3300/6250] eta: 0:06:46 lr: 0.000058 grad: 0.0929 (0.0928) loss: 0.8218 (0.8210) time: 0.1744 data: 0.0850 max mem: 9390 +Train: [54] [3400/6250] eta: 0:06:32 lr: 0.000058 grad: 0.0934 (0.0928) loss: 0.8171 (0.8209) time: 0.1404 data: 0.0656 max mem: 9390 +Train: [54] [3500/6250] eta: 0:06:18 lr: 0.000058 grad: 0.0957 (0.0929) loss: 0.8130 (0.8208) time: 0.1391 data: 0.0476 max mem: 9390 +Train: [54] [3600/6250] eta: 0:06:04 lr: 0.000058 grad: 0.0926 (0.0929) loss: 0.8142 (0.8207) time: 0.1385 data: 0.0581 max mem: 9390 +Train: [54] [3700/6250] eta: 0:05:51 lr: 0.000058 grad: 0.0930 (0.0932) loss: 0.8188 (0.8206) time: 0.1627 data: 0.0901 max mem: 9390 +Train: [54] [3800/6250] eta: 0:05:38 lr: 0.000058 grad: 0.0910 (0.0934) loss: 0.8180 (0.8205) time: 0.1806 data: 0.0905 max mem: 9390 +Train: [54] [3900/6250] eta: 0:05:24 lr: 0.000058 grad: 0.0932 (0.0936) loss: 0.8159 (0.8205) time: 0.1384 data: 0.0533 max mem: 9390 +Train: [54] [4000/6250] eta: 0:05:11 lr: 0.000058 grad: 0.0996 (0.0938) loss: 0.8132 (0.8203) time: 0.1584 data: 0.0797 max mem: 9390 +Train: [54] [4100/6250] eta: 0:04:57 lr: 0.000058 grad: 0.0890 (0.0938) loss: 0.8149 (0.8202) time: 0.1741 data: 0.0945 max mem: 9390 +Train: [54] [4200/6250] eta: 0:04:43 lr: 0.000058 grad: 0.0919 (0.0938) loss: 0.8216 (0.8202) time: 0.1383 data: 0.0492 max mem: 9390 +Train: [54] [4300/6250] eta: 0:04:30 lr: 0.000058 grad: 0.0949 (0.0938) loss: 0.8132 (0.8201) time: 0.1909 data: 0.0731 max mem: 9390 +Train: [54] [4400/6250] eta: 0:04:16 lr: 0.000058 grad: 0.0984 (0.0939) loss: 0.8150 (0.8200) time: 0.1357 data: 0.0518 max mem: 9390 +Train: [54] [4500/6250] eta: 0:04:02 lr: 0.000058 grad: 0.0945 (0.0939) loss: 0.8127 (0.8199) time: 0.1344 data: 0.0594 max mem: 9390 +Train: [54] [4600/6250] eta: 0:03:48 lr: 0.000058 grad: 0.0960 (0.0940) loss: 0.8161 (0.8199) time: 0.1598 data: 0.0761 max mem: 9390 +Train: [54] [4700/6250] eta: 0:03:34 lr: 0.000058 grad: 0.0900 (0.0940) loss: 0.8220 (0.8198) time: 0.1201 data: 0.0385 max mem: 9390 +Train: [54] [4800/6250] eta: 0:03:20 lr: 0.000058 grad: 0.0910 (0.0940) loss: 0.8142 (0.8197) time: 0.1349 data: 0.0496 max mem: 9390 +Train: [54] [4900/6250] eta: 0:03:06 lr: 0.000058 grad: 0.0970 (0.0941) loss: 0.8190 (0.8197) time: 0.1585 data: 0.0752 max mem: 9390 +Train: [54] [5000/6250] eta: 0:02:52 lr: 0.000058 grad: 0.0909 (0.0943) loss: 0.8215 (0.8196) time: 0.1432 data: 0.0630 max mem: 9390 +Train: [54] [5100/6250] eta: 0:02:39 lr: 0.000058 grad: 0.0901 (0.0943) loss: 0.8262 (0.8196) time: 0.1542 data: 0.0770 max mem: 9390 +Train: [54] [5200/6250] eta: 0:02:25 lr: 0.000058 grad: 0.0852 (0.0943) loss: 0.8201 (0.8196) time: 0.1574 data: 0.0790 max mem: 9390 +Train: [54] [5300/6250] eta: 0:02:11 lr: 0.000058 grad: 0.0932 (0.0943) loss: 0.8224 (0.8196) time: 0.1713 data: 0.0863 max mem: 9390 +Train: [54] [5400/6250] eta: 0:01:57 lr: 0.000058 grad: 0.0942 (0.0943) loss: 0.8219 (0.8196) time: 0.2045 data: 0.1277 max mem: 9390 +Train: [54] [5500/6250] eta: 0:01:43 lr: 0.000058 grad: 0.0873 (0.0943) loss: 0.8212 (0.8196) time: 0.1382 data: 0.0575 max mem: 9390 +Train: [54] [5600/6250] eta: 0:01:30 lr: 0.000058 grad: 0.0942 (0.0943) loss: 0.8175 (0.8196) time: 0.1364 data: 0.0535 max mem: 9390 +Train: [54] [5700/6250] eta: 0:01:16 lr: 0.000058 grad: 0.0902 (0.0943) loss: 0.8206 (0.8196) time: 0.1365 data: 0.0564 max mem: 9390 +Train: [54] [5800/6250] eta: 0:01:02 lr: 0.000057 grad: 0.0880 (0.0943) loss: 0.8212 (0.8196) time: 0.1213 data: 0.0401 max mem: 9390 +Train: [54] [5900/6250] eta: 0:00:48 lr: 0.000057 grad: 0.0892 (0.0943) loss: 0.8260 (0.8196) time: 0.1153 data: 0.0309 max mem: 9390 +Train: [54] [6000/6250] eta: 0:00:34 lr: 0.000057 grad: 0.0893 (0.0943) loss: 0.8193 (0.8196) time: 0.1256 data: 0.0409 max mem: 9390 +Train: [54] [6100/6250] eta: 0:00:20 lr: 0.000057 grad: 0.0909 (0.0942) loss: 0.8205 (0.8197) time: 0.1176 data: 0.0288 max mem: 9390 +Train: [54] [6200/6250] eta: 0:00:06 lr: 0.000057 grad: 0.0863 (0.0944) loss: 0.8265 (0.8197) time: 0.1331 data: 0.0502 max mem: 9390 +Train: [54] [6249/6250] eta: 0:00:00 lr: 0.000057 grad: 0.0953 (0.0944) loss: 0.8200 (0.8197) time: 0.1238 data: 0.0438 max mem: 9390 +Train: [54] Total time: 0:14:23 (0.1382 s / it) +Averaged stats: lr: 0.000057 grad: 0.0953 (0.0944) loss: 0.8200 (0.8197) +Eval (hcp-train-subset): [54] [ 0/62] eta: 0:03:38 loss: 0.8466 (0.8466) time: 3.5184 data: 3.4381 max mem: 9390 +Eval (hcp-train-subset): [54] [61/62] eta: 0:00:00 loss: 0.8322 (0.8353) time: 0.1209 data: 0.0960 max mem: 9390 +Eval (hcp-train-subset): [54] Total time: 0:00:12 (0.2034 s / it) +Averaged stats (hcp-train-subset): loss: 0.8322 (0.8353) +Making plots (hcp-train-subset): example=28 +Eval (hcp-val): [54] [ 0/62] eta: 0:03:23 loss: 0.8294 (0.8294) time: 3.2771 data: 3.2058 max mem: 9390 +Eval (hcp-val): [54] [61/62] eta: 0:00:00 loss: 0.8347 (0.8350) time: 0.0965 data: 0.0718 max mem: 9390 +Eval (hcp-val): [54] Total time: 0:00:11 (0.1898 s / it) +Averaged stats (hcp-val): loss: 0.8347 (0.8350) +Making plots (hcp-val): example=36 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +Train: [55] [ 0/6250] eta: 8:12:31 lr: 0.000057 grad: 0.0634 (0.0634) loss: 0.8381 (0.8381) time: 4.7282 data: 4.4694 max mem: 9390 +Train: [55] [ 100/6250] eta: 0:19:03 lr: 0.000057 grad: 0.1000 (0.1046) loss: 0.8133 (0.8291) time: 0.1387 data: 0.0380 max mem: 9390 +Train: [55] [ 200/6250] eta: 0:16:14 lr: 0.000057 grad: 0.1056 (0.1048) loss: 0.8155 (0.8235) time: 0.1382 data: 0.0478 max mem: 9390 +Train: [55] [ 300/6250] eta: 0:14:47 lr: 0.000057 grad: 0.0978 (0.1031) loss: 0.8210 (0.8237) time: 0.1308 data: 0.0446 max mem: 9390 +Train: [55] [ 400/6250] eta: 0:13:52 lr: 0.000057 grad: 0.0900 (0.1007) loss: 0.8269 (0.8238) time: 0.1128 data: 0.0317 max mem: 9390 +Train: [55] [ 500/6250] eta: 0:13:19 lr: 0.000057 grad: 0.0877 (0.0994) loss: 0.8271 (0.8239) time: 0.1319 data: 0.0484 max mem: 9390 +Train: [55] [ 600/6250] eta: 0:12:46 lr: 0.000057 grad: 0.0853 (0.0983) loss: 0.8282 (0.8243) time: 0.1308 data: 0.0414 max mem: 9390 +Train: [55] [ 700/6250] eta: 0:12:20 lr: 0.000057 grad: 0.0842 (0.0972) loss: 0.8257 (0.8246) time: 0.1039 data: 0.0155 max mem: 9390 +Train: [55] [ 800/6250] eta: 0:11:58 lr: 0.000057 grad: 0.0806 (0.0970) loss: 0.8255 (0.8243) time: 0.1121 data: 0.0288 max mem: 9390 +Train: [55] [ 900/6250] eta: 0:11:43 lr: 0.000057 grad: 0.0933 (0.0968) loss: 0.8242 (0.8242) time: 0.1291 data: 0.0474 max mem: 9390 +Train: [55] [1000/6250] eta: 0:11:33 lr: 0.000057 grad: 0.0921 (0.0964) loss: 0.8217 (0.8242) time: 0.1361 data: 0.0560 max mem: 9390 +Train: [55] [1100/6250] eta: 0:11:20 lr: 0.000057 grad: 0.0842 (0.0960) loss: 0.8303 (0.8242) time: 0.1349 data: 0.0517 max mem: 9390 +Train: [55] [1200/6250] eta: 0:11:08 lr: 0.000057 grad: 0.0960 (0.0959) loss: 0.8214 (0.8240) time: 0.1450 data: 0.0594 max mem: 9390 +Train: [55] [1300/6250] eta: 0:11:03 lr: 0.000057 grad: 0.0935 (0.0960) loss: 0.8233 (0.8236) time: 0.1633 data: 0.0891 max mem: 9390 +Train: [55] [1400/6250] eta: 0:10:55 lr: 0.000057 grad: 0.0882 (0.0959) loss: 0.8231 (0.8233) time: 0.1539 data: 0.0703 max mem: 9390 +Train: [55] [1500/6250] eta: 0:10:42 lr: 0.000057 grad: 0.0907 (0.0962) loss: 0.8170 (0.8229) time: 0.1453 data: 0.0743 max mem: 9390 +Train: [55] [1600/6250] eta: 0:10:31 lr: 0.000057 grad: 0.0912 (0.0961) loss: 0.8185 (0.8226) time: 0.1503 data: 0.0592 max mem: 9390 +Train: [55] [1700/6250] eta: 0:10:17 lr: 0.000057 grad: 0.0886 (0.0961) loss: 0.8252 (0.8224) time: 0.1204 data: 0.0397 max mem: 9390 +Train: [55] [1800/6250] eta: 0:10:02 lr: 0.000057 grad: 0.0890 (0.0958) loss: 0.8193 (0.8223) time: 0.0946 data: 0.0130 max mem: 9390 +Train: [55] [1900/6250] eta: 0:09:48 lr: 0.000057 grad: 0.0959 (0.0959) loss: 0.8194 (0.8221) time: 0.1290 data: 0.0498 max mem: 9390 +Train: [55] [2000/6250] eta: 0:09:33 lr: 0.000057 grad: 0.0935 (0.0958) loss: 0.8210 (0.8219) time: 0.1352 data: 0.0573 max mem: 9390 +Train: [55] [2100/6250] eta: 0:09:20 lr: 0.000057 grad: 0.0970 (0.0958) loss: 0.8214 (0.8219) time: 0.1421 data: 0.0614 max mem: 9390 +Train: [55] [2200/6250] eta: 0:09:06 lr: 0.000057 grad: 0.0926 (0.0958) loss: 0.8228 (0.8220) time: 0.1381 data: 0.0620 max mem: 9390 +Train: [55] [2300/6250] eta: 0:08:52 lr: 0.000057 grad: 0.0846 (0.0958) loss: 0.8239 (0.8220) time: 0.1367 data: 0.0597 max mem: 9390 +Train: [55] [2400/6250] eta: 0:08:39 lr: 0.000057 grad: 0.0857 (0.0957) loss: 0.8250 (0.8221) time: 0.1400 data: 0.0635 max mem: 9390 +Train: [55] [2500/6250] eta: 0:08:27 lr: 0.000057 grad: 0.0917 (0.0957) loss: 0.8276 (0.8220) time: 0.1663 data: 0.0728 max mem: 9390 +Train: [55] [2600/6250] eta: 0:08:14 lr: 0.000056 grad: 0.0943 (0.0957) loss: 0.8181 (0.8219) time: 0.1356 data: 0.0549 max mem: 9390 +Train: [55] [2700/6250] eta: 0:08:02 lr: 0.000056 grad: 0.0918 (0.0955) loss: 0.8141 (0.8219) time: 0.1933 data: 0.0972 max mem: 9390 +Train: [55] [2800/6250] eta: 0:07:49 lr: 0.000056 grad: 0.0892 (0.0955) loss: 0.8239 (0.8218) time: 0.1575 data: 0.0802 max mem: 9390 +Train: [55] [2900/6250] eta: 0:07:35 lr: 0.000056 grad: 0.0921 (0.0954) loss: 0.8214 (0.8218) time: 0.1274 data: 0.0493 max mem: 9390 +Train: [55] [3000/6250] eta: 0:07:21 lr: 0.000056 grad: 0.0938 (0.0954) loss: 0.8158 (0.8216) time: 0.1557 data: 0.0766 max mem: 9390 +Train: [55] [3100/6250] eta: 0:07:07 lr: 0.000056 grad: 0.0984 (0.0954) loss: 0.8175 (0.8216) time: 0.1402 data: 0.0600 max mem: 9390 +Train: [55] [3200/6250] eta: 0:06:53 lr: 0.000056 grad: 0.0897 (0.0953) loss: 0.8203 (0.8215) time: 0.1312 data: 0.0502 max mem: 9390 +Train: [55] [3300/6250] eta: 0:06:40 lr: 0.000056 grad: 0.0900 (0.0952) loss: 0.8240 (0.8215) time: 0.1390 data: 0.0624 max mem: 9390 +Train: [55] [3400/6250] eta: 0:06:27 lr: 0.000056 grad: 0.0887 (0.0951) loss: 0.8222 (0.8215) time: 0.1732 data: 0.0801 max mem: 9390 +Train: [55] [3500/6250] eta: 0:06:13 lr: 0.000056 grad: 0.0889 (0.0951) loss: 0.8213 (0.8214) time: 0.1219 data: 0.0427 max mem: 9390 +Train: [55] [3600/6250] eta: 0:05:59 lr: 0.000056 grad: 0.0925 (0.0950) loss: 0.8172 (0.8214) time: 0.1332 data: 0.0519 max mem: 9390 +Train: [55] [3700/6250] eta: 0:05:46 lr: 0.000056 grad: 0.0882 (0.0949) loss: 0.8269 (0.8214) time: 0.1566 data: 0.0778 max mem: 9390 +Train: [55] [3800/6250] eta: 0:05:33 lr: 0.000056 grad: 0.0917 (0.0949) loss: 0.8220 (0.8214) time: 0.1267 data: 0.0445 max mem: 9390 +Train: [55] [3900/6250] eta: 0:05:20 lr: 0.000056 grad: 0.0879 (0.0948) loss: 0.8212 (0.8214) time: 0.1463 data: 0.0719 max mem: 9390 +Train: [55] [4000/6250] eta: 0:05:06 lr: 0.000056 grad: 0.0951 (0.0948) loss: 0.8193 (0.8214) time: 0.1297 data: 0.0517 max mem: 9390 +Train: [55] [4100/6250] eta: 0:04:52 lr: 0.000056 grad: 0.0921 (0.0947) loss: 0.8225 (0.8214) time: 0.1400 data: 0.0563 max mem: 9390 +Train: [55] [4200/6250] eta: 0:04:39 lr: 0.000056 grad: 0.0980 (0.0948) loss: 0.8164 (0.8213) time: 0.1172 data: 0.0362 max mem: 9390 +Train: [55] [4300/6250] eta: 0:04:25 lr: 0.000056 grad: 0.0896 (0.0948) loss: 0.8187 (0.8213) time: 0.1343 data: 0.0558 max mem: 9390 +Train: [55] [4400/6250] eta: 0:04:12 lr: 0.000056 grad: 0.0915 (0.0948) loss: 0.8187 (0.8213) time: 0.1219 data: 0.0395 max mem: 9390 +Train: [55] [4500/6250] eta: 0:03:58 lr: 0.000056 grad: 0.0890 (0.0947) loss: 0.8203 (0.8213) time: 0.1279 data: 0.0491 max mem: 9390 +Train: [55] [4600/6250] eta: 0:03:45 lr: 0.000056 grad: 0.0931 (0.0947) loss: 0.8183 (0.8212) time: 0.1367 data: 0.0503 max mem: 9390 +Train: [55] [4700/6250] eta: 0:03:31 lr: 0.000056 grad: 0.0993 (0.0948) loss: 0.8065 (0.8212) time: 0.1527 data: 0.0709 max mem: 9390 +Train: [55] [4800/6250] eta: 0:03:17 lr: 0.000056 grad: 0.1013 (0.0949) loss: 0.8147 (0.8210) time: 0.1281 data: 0.0479 max mem: 9390 +Train: [55] [4900/6250] eta: 0:03:04 lr: 0.000056 grad: 0.1007 (0.0949) loss: 0.8119 (0.8210) time: 0.1343 data: 0.0583 max mem: 9390 +Train: [55] [5000/6250] eta: 0:02:50 lr: 0.000056 grad: 0.0899 (0.0950) loss: 0.8167 (0.8209) time: 0.1345 data: 0.0526 max mem: 9390 +Train: [55] [5100/6250] eta: 0:02:37 lr: 0.000056 grad: 0.0967 (0.0950) loss: 0.8170 (0.8208) time: 0.1660 data: 0.0861 max mem: 9390 +Train: [55] [5200/6250] eta: 0:02:23 lr: 0.000056 grad: 0.0957 (0.0951) loss: 0.8094 (0.8207) time: 0.1511 data: 0.0682 max mem: 9390 +Train: [55] [5300/6250] eta: 0:02:10 lr: 0.000056 grad: 0.0956 (0.0952) loss: 0.8146 (0.8206) time: 0.1279 data: 0.0489 max mem: 9390 +Train: [55] [5400/6250] eta: 0:01:56 lr: 0.000056 grad: 0.0998 (0.0953) loss: 0.8168 (0.8205) time: 0.1177 data: 0.0384 max mem: 9390 +Train: [55] [5500/6250] eta: 0:01:42 lr: 0.000056 grad: 0.1000 (0.0954) loss: 0.8116 (0.8204) time: 0.1544 data: 0.0750 max mem: 9390 +Train: [55] [5600/6250] eta: 0:01:29 lr: 0.000055 grad: 0.0962 (0.0955) loss: 0.8138 (0.8203) time: 0.1549 data: 0.0767 max mem: 9390 +Train: [55] [5700/6250] eta: 0:01:15 lr: 0.000055 grad: 0.1006 (0.0956) loss: 0.8151 (0.8202) time: 0.1343 data: 0.0538 max mem: 9390 +Train: [55] [5800/6250] eta: 0:01:01 lr: 0.000055 grad: 0.0950 (0.0956) loss: 0.8211 (0.8202) time: 0.1200 data: 0.0385 max mem: 9390 +Train: [55] [5900/6250] eta: 0:00:47 lr: 0.000055 grad: 0.0933 (0.0957) loss: 0.8217 (0.8201) time: 0.1231 data: 0.0363 max mem: 9390 +Train: [55] [6000/6250] eta: 0:00:34 lr: 0.000055 grad: 0.0932 (0.0957) loss: 0.8182 (0.8201) time: 0.1472 data: 0.0651 max mem: 9390 +Train: [55] [6100/6250] eta: 0:00:20 lr: 0.000055 grad: 0.0977 (0.0957) loss: 0.8186 (0.8201) time: 0.0951 data: 0.0144 max mem: 9390 +Train: [55] [6200/6250] eta: 0:00:06 lr: 0.000055 grad: 0.0930 (0.0958) loss: 0.8157 (0.8200) time: 0.1273 data: 0.0462 max mem: 9390 +Train: [55] [6249/6250] eta: 0:00:00 lr: 0.000055 grad: 0.0950 (0.0958) loss: 0.8197 (0.8199) time: 0.1224 data: 0.0446 max mem: 9390 +Train: [55] Total time: 0:14:14 (0.1367 s / it) +Averaged stats: lr: 0.000055 grad: 0.0950 (0.0958) loss: 0.8197 (0.8199) +Eval (hcp-train-subset): [55] [ 0/62] eta: 0:05:29 loss: 0.8461 (0.8461) time: 5.3124 data: 5.2796 max mem: 9390 +Eval (hcp-train-subset): [55] [61/62] eta: 0:00:00 loss: 0.8326 (0.8332) time: 0.1037 data: 0.0787 max mem: 9390 +Eval (hcp-train-subset): [55] Total time: 0:00:12 (0.2062 s / it) +Averaged stats (hcp-train-subset): loss: 0.8326 (0.8332) +Eval (hcp-val): [55] [ 0/62] eta: 0:03:07 loss: 0.8309 (0.8309) time: 3.0226 data: 2.9567 max mem: 9390 +Eval (hcp-val): [55] [61/62] eta: 0:00:00 loss: 0.8327 (0.8342) time: 0.1100 data: 0.0853 max mem: 9390 +Eval (hcp-val): [55] Total time: 0:00:11 (0.1863 s / it) +Averaged stats (hcp-val): loss: 0.8327 (0.8342) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +Train: [56] [ 0/6250] eta: 8:12:12 lr: 0.000055 grad: 0.1891 (0.1891) loss: 0.8534 (0.8534) time: 4.7252 data: 4.4636 max mem: 9390 +Train: [56] [ 100/6250] eta: 0:18:37 lr: 0.000055 grad: 0.0999 (0.1101) loss: 0.8239 (0.8358) time: 0.1364 data: 0.0443 max mem: 9390 +Train: [56] [ 200/6250] eta: 0:16:09 lr: 0.000055 grad: 0.0895 (0.1039) loss: 0.8329 (0.8300) time: 0.1418 data: 0.0487 max mem: 9390 +Train: [56] [ 300/6250] eta: 0:14:44 lr: 0.000055 grad: 0.0897 (0.1034) loss: 0.8244 (0.8274) time: 0.1130 data: 0.0209 max mem: 9390 +Train: [56] [ 400/6250] eta: 0:13:45 lr: 0.000055 grad: 0.0947 (0.1014) loss: 0.8223 (0.8260) time: 0.1217 data: 0.0378 max mem: 9390 +Train: [56] [ 500/6250] eta: 0:13:15 lr: 0.000055 grad: 0.0870 (0.1011) loss: 0.8252 (0.8254) time: 0.1396 data: 0.0514 max mem: 9390 +Train: [56] [ 600/6250] eta: 0:12:47 lr: 0.000055 grad: 0.0946 (0.0997) loss: 0.8197 (0.8253) time: 0.1228 data: 0.0251 max mem: 9390 +Train: [56] [ 700/6250] eta: 0:12:22 lr: 0.000055 grad: 0.0862 (0.0989) loss: 0.8184 (0.8251) time: 0.1078 data: 0.0203 max mem: 9390 +Train: [56] [ 800/6250] eta: 0:12:01 lr: 0.000055 grad: 0.0888 (0.0980) loss: 0.8210 (0.8253) time: 0.1284 data: 0.0453 max mem: 9390 +Train: [56] [ 900/6250] eta: 0:11:48 lr: 0.000055 grad: 0.0890 (0.0976) loss: 0.8205 (0.8252) time: 0.1315 data: 0.0463 max mem: 9390 +Train: [56] [1000/6250] eta: 0:11:48 lr: 0.000055 grad: 0.0916 (0.0972) loss: 0.8207 (0.8250) time: 0.1630 data: 0.0870 max mem: 9390 +Train: [56] [1100/6250] eta: 0:11:40 lr: 0.000055 grad: 0.0963 (0.0970) loss: 0.8149 (0.8244) time: 0.1410 data: 0.0624 max mem: 9390 +Train: [56] [1200/6250] eta: 0:11:34 lr: 0.000055 grad: 0.0963 (0.0968) loss: 0.8126 (0.8238) time: 0.1725 data: 0.0976 max mem: 9390 +Train: [56] [1300/6250] eta: 0:11:20 lr: 0.000055 grad: 0.0934 (0.0967) loss: 0.8198 (0.8234) time: 0.1349 data: 0.0594 max mem: 9390 +Train: [56] [1400/6250] eta: 0:11:09 lr: 0.000055 grad: 0.0926 (0.0970) loss: 0.8220 (0.8231) time: 0.1548 data: 0.0788 max mem: 9390 +Train: [56] [1500/6250] eta: 0:10:59 lr: 0.000055 grad: 0.0940 (0.0968) loss: 0.8161 (0.8228) time: 0.1099 data: 0.0343 max mem: 9390 +Train: [56] [1600/6250] eta: 0:10:45 lr: 0.000055 grad: 0.0911 (0.0966) loss: 0.8173 (0.8226) time: 0.1349 data: 0.0504 max mem: 9390 +Train: [56] [1700/6250] eta: 0:10:31 lr: 0.000055 grad: 0.0900 (0.0965) loss: 0.8185 (0.8224) time: 0.1065 data: 0.0244 max mem: 9390 +Train: [56] [1800/6250] eta: 0:10:16 lr: 0.000055 grad: 0.0875 (0.0963) loss: 0.8167 (0.8223) time: 0.1362 data: 0.0538 max mem: 9390 +Train: [56] [1900/6250] eta: 0:10:03 lr: 0.000055 grad: 0.0946 (0.0963) loss: 0.8204 (0.8221) time: 0.1703 data: 0.0818 max mem: 9390 +Train: [56] [2000/6250] eta: 0:09:47 lr: 0.000055 grad: 0.0940 (0.0962) loss: 0.8201 (0.8220) time: 0.1268 data: 0.0493 max mem: 9390 +Train: [56] [2100/6250] eta: 0:09:31 lr: 0.000055 grad: 0.0946 (0.0963) loss: 0.8198 (0.8219) time: 0.1159 data: 0.0351 max mem: 9390 +Train: [56] [2200/6250] eta: 0:09:16 lr: 0.000055 grad: 0.0978 (0.0963) loss: 0.8176 (0.8218) time: 0.1452 data: 0.0698 max mem: 9390 +Train: [56] [2300/6250] eta: 0:09:01 lr: 0.000055 grad: 0.0969 (0.0963) loss: 0.8168 (0.8216) time: 0.1186 data: 0.0379 max mem: 9390 +Train: [56] [2400/6250] eta: 0:08:46 lr: 0.000054 grad: 0.0976 (0.0963) loss: 0.8162 (0.8215) time: 0.1400 data: 0.0630 max mem: 9390 +Train: [56] [2500/6250] eta: 0:08:32 lr: 0.000054 grad: 0.1020 (0.0963) loss: 0.8196 (0.8213) time: 0.1280 data: 0.0503 max mem: 9390 +Train: [56] [2600/6250] eta: 0:08:17 lr: 0.000054 grad: 0.0945 (0.0965) loss: 0.8151 (0.8211) time: 0.1234 data: 0.0441 max mem: 9390 +Train: [56] [2700/6250] eta: 0:08:05 lr: 0.000054 grad: 0.0968 (0.0966) loss: 0.8145 (0.8210) time: 0.1626 data: 0.0739 max mem: 9390 +Train: [56] [2800/6250] eta: 0:07:50 lr: 0.000054 grad: 0.1054 (0.0967) loss: 0.8112 (0.8209) time: 0.1395 data: 0.0637 max mem: 9390 +Train: [56] [2900/6250] eta: 0:07:36 lr: 0.000054 grad: 0.0947 (0.0968) loss: 0.8164 (0.8207) time: 0.1332 data: 0.0533 max mem: 9390 +Train: [56] [3000/6250] eta: 0:07:23 lr: 0.000054 grad: 0.0914 (0.0969) loss: 0.8154 (0.8206) time: 0.1453 data: 0.0674 max mem: 9390 +Train: [56] [3100/6250] eta: 0:07:09 lr: 0.000054 grad: 0.0928 (0.0969) loss: 0.8182 (0.8206) time: 0.1359 data: 0.0613 max mem: 9390 +Train: [56] [3200/6250] eta: 0:06:56 lr: 0.000054 grad: 0.0952 (0.0969) loss: 0.8131 (0.8205) time: 0.1513 data: 0.0763 max mem: 9390 +Train: [56] [3300/6250] eta: 0:06:43 lr: 0.000054 grad: 0.1002 (0.0970) loss: 0.8115 (0.8203) time: 0.1227 data: 0.0477 max mem: 9390 +Train: [56] [3400/6250] eta: 0:06:29 lr: 0.000054 grad: 0.0989 (0.0972) loss: 0.8142 (0.8202) time: 0.1386 data: 0.0613 max mem: 9390 +Train: [56] [3500/6250] eta: 0:06:15 lr: 0.000054 grad: 0.1007 (0.0972) loss: 0.8210 (0.8202) time: 0.1260 data: 0.0434 max mem: 9390 +Train: [56] [3600/6250] eta: 0:06:01 lr: 0.000054 grad: 0.0972 (0.0974) loss: 0.8195 (0.8201) time: 0.1022 data: 0.0205 max mem: 9390 +Train: [56] [3700/6250] eta: 0:05:48 lr: 0.000054 grad: 0.0942 (0.0974) loss: 0.8178 (0.8200) time: 0.1011 data: 0.0174 max mem: 9390 +Train: [56] [3800/6250] eta: 0:05:36 lr: 0.000054 grad: 0.0969 (0.0975) loss: 0.8180 (0.8199) time: 0.1941 data: 0.1154 max mem: 9390 +Train: [56] [3900/6250] eta: 0:05:22 lr: 0.000054 grad: 0.0955 (0.0976) loss: 0.8191 (0.8198) time: 0.1503 data: 0.0747 max mem: 9390 +Train: [56] [4000/6250] eta: 0:05:09 lr: 0.000054 grad: 0.0947 (0.0976) loss: 0.8173 (0.8198) time: 0.1427 data: 0.0653 max mem: 9390 +Train: [56] [4100/6250] eta: 0:04:55 lr: 0.000054 grad: 0.0991 (0.0976) loss: 0.8152 (0.8198) time: 0.1337 data: 0.0563 max mem: 9390 +Train: [56] [4200/6250] eta: 0:04:42 lr: 0.000054 grad: 0.0892 (0.0976) loss: 0.8150 (0.8197) time: 0.1555 data: 0.0678 max mem: 9390 +Train: [56] [4300/6250] eta: 0:04:28 lr: 0.000054 grad: 0.0992 (0.0976) loss: 0.8209 (0.8197) time: 0.1286 data: 0.0480 max mem: 9390 +Train: [56] [4400/6250] eta: 0:04:14 lr: 0.000054 grad: 0.0974 (0.0977) loss: 0.8130 (0.8196) time: 0.1478 data: 0.0594 max mem: 9390 +Train: [56] [4500/6250] eta: 0:04:01 lr: 0.000054 grad: 0.0975 (0.0977) loss: 0.8208 (0.8196) time: 0.1457 data: 0.0719 max mem: 9390 +Train: [56] [4600/6250] eta: 0:03:47 lr: 0.000054 grad: 0.0949 (0.0977) loss: 0.8138 (0.8196) time: 0.1334 data: 0.0510 max mem: 9390 +Train: [56] [4700/6250] eta: 0:03:33 lr: 0.000054 grad: 0.0979 (0.0977) loss: 0.8132 (0.8195) time: 0.1467 data: 0.0610 max mem: 9390 +Train: [56] [4800/6250] eta: 0:03:20 lr: 0.000054 grad: 0.0918 (0.0978) loss: 0.8231 (0.8194) time: 0.1359 data: 0.0623 max mem: 9390 +Train: [56] [4900/6250] eta: 0:03:06 lr: 0.000054 grad: 0.0962 (0.0978) loss: 0.8187 (0.8194) time: 0.1334 data: 0.0555 max mem: 9390 +Train: [56] [5000/6250] eta: 0:02:52 lr: 0.000054 grad: 0.0927 (0.0979) loss: 0.8238 (0.8193) time: 0.1323 data: 0.0525 max mem: 9390 +Train: [56] [5100/6250] eta: 0:02:38 lr: 0.000054 grad: 0.0985 (0.0979) loss: 0.8166 (0.8192) time: 0.1529 data: 0.0671 max mem: 9390 +Train: [56] [5200/6250] eta: 0:02:25 lr: 0.000054 grad: 0.0951 (0.0980) loss: 0.8161 (0.8192) time: 0.1456 data: 0.0599 max mem: 9390 +Train: [56] [5300/6250] eta: 0:02:11 lr: 0.000054 grad: 0.0978 (0.0980) loss: 0.8172 (0.8192) time: 0.1538 data: 0.0728 max mem: 9390 +Train: [56] [5400/6250] eta: 0:01:57 lr: 0.000054 grad: 0.0943 (0.0981) loss: 0.8218 (0.8191) time: 0.1401 data: 0.0549 max mem: 9390 +Train: [56] [5500/6250] eta: 0:01:43 lr: 0.000053 grad: 0.0902 (0.0981) loss: 0.8158 (0.8191) time: 0.1361 data: 0.0557 max mem: 9390 +Train: [56] [5600/6250] eta: 0:01:29 lr: 0.000053 grad: 0.0948 (0.0981) loss: 0.8144 (0.8191) time: 0.1336 data: 0.0503 max mem: 9390 +Train: [56] [5700/6250] eta: 0:01:15 lr: 0.000053 grad: 0.1036 (0.0981) loss: 0.8143 (0.8191) time: 0.1445 data: 0.0661 max mem: 9390 +Train: [56] [5800/6250] eta: 0:01:01 lr: 0.000053 grad: 0.0934 (0.0980) loss: 0.8204 (0.8191) time: 0.1141 data: 0.0300 max mem: 9390 +Train: [56] [5900/6250] eta: 0:00:48 lr: 0.000053 grad: 0.0924 (0.0980) loss: 0.8143 (0.8191) time: 0.1275 data: 0.0436 max mem: 9390 +Train: [56] [6000/6250] eta: 0:00:34 lr: 0.000053 grad: 0.0915 (0.0980) loss: 0.8249 (0.8191) time: 0.1161 data: 0.0323 max mem: 9390 +Train: [56] [6100/6250] eta: 0:00:20 lr: 0.000053 grad: 0.0903 (0.0980) loss: 0.8205 (0.8191) time: 0.0933 data: 0.0077 max mem: 9390 +Train: [56] [6200/6250] eta: 0:00:06 lr: 0.000053 grad: 0.0973 (0.0980) loss: 0.8229 (0.8191) time: 0.1149 data: 0.0373 max mem: 9390 +Train: [56] [6249/6250] eta: 0:00:00 lr: 0.000053 grad: 0.0913 (0.0980) loss: 0.8202 (0.8191) time: 0.1358 data: 0.0579 max mem: 9390 +Train: [56] Total time: 0:14:18 (0.1373 s / it) +Averaged stats: lr: 0.000053 grad: 0.0913 (0.0980) loss: 0.8202 (0.8191) +Eval (hcp-train-subset): [56] [ 0/62] eta: 0:04:49 loss: 0.8445 (0.8445) time: 4.6662 data: 4.6349 max mem: 9390 +Eval (hcp-train-subset): [56] [61/62] eta: 0:00:00 loss: 0.8325 (0.8350) time: 0.1188 data: 0.0936 max mem: 9390 +Eval (hcp-train-subset): [56] Total time: 0:00:12 (0.2064 s / it) +Averaged stats (hcp-train-subset): loss: 0.8325 (0.8350) +Eval (hcp-val): [56] [ 0/62] eta: 0:04:09 loss: 0.8336 (0.8336) time: 4.0174 data: 3.9454 max mem: 9390 +Eval (hcp-val): [56] [61/62] eta: 0:00:00 loss: 0.8327 (0.8345) time: 0.1018 data: 0.0767 max mem: 9390 +Eval (hcp-val): [56] Total time: 0:00:11 (0.1909 s / it) +Averaged stats (hcp-val): loss: 0.8327 (0.8345) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +Train: [57] [ 0/6250] eta: 6:19:00 lr: 0.000053 grad: 0.0855 (0.0855) loss: 0.8339 (0.8339) time: 3.6384 data: 3.3861 max mem: 9390 +Train: [57] [ 100/6250] eta: 0:19:31 lr: 0.000053 grad: 0.0923 (0.1148) loss: 0.8150 (0.8214) time: 0.1796 data: 0.0907 max mem: 9390 +Train: [57] [ 200/6250] eta: 0:16:13 lr: 0.000053 grad: 0.0923 (0.1061) loss: 0.8247 (0.8208) time: 0.1504 data: 0.0672 max mem: 9390 +Train: [57] [ 300/6250] eta: 0:14:49 lr: 0.000053 grad: 0.0959 (0.1029) loss: 0.8227 (0.8207) time: 0.1466 data: 0.0644 max mem: 9390 +Train: [57] [ 400/6250] eta: 0:13:55 lr: 0.000053 grad: 0.0939 (0.1012) loss: 0.8271 (0.8204) time: 0.1471 data: 0.0663 max mem: 9390 +Train: [57] [ 500/6250] eta: 0:13:15 lr: 0.000053 grad: 0.0986 (0.1008) loss: 0.8172 (0.8204) time: 0.1225 data: 0.0360 max mem: 9390 +Train: [57] [ 600/6250] eta: 0:12:40 lr: 0.000053 grad: 0.0940 (0.1001) loss: 0.8197 (0.8204) time: 0.1122 data: 0.0272 max mem: 9390 +Train: [57] [ 700/6250] eta: 0:12:16 lr: 0.000053 grad: 0.0948 (0.0994) loss: 0.8167 (0.8205) time: 0.1350 data: 0.0578 max mem: 9390 +Train: [57] [ 800/6250] eta: 0:12:00 lr: 0.000053 grad: 0.0918 (0.0988) loss: 0.8237 (0.8206) time: 0.1280 data: 0.0483 max mem: 9390 +Train: [57] [ 900/6250] eta: 0:11:53 lr: 0.000053 grad: 0.0939 (0.0984) loss: 0.8231 (0.8208) time: 0.1591 data: 0.0732 max mem: 9390 +Train: [57] [1000/6250] eta: 0:11:53 lr: 0.000053 grad: 0.0912 (0.0978) loss: 0.8195 (0.8210) time: 0.1738 data: 0.1003 max mem: 9390 +Train: [57] [1100/6250] eta: 0:11:48 lr: 0.000053 grad: 0.0928 (0.0975) loss: 0.8235 (0.8210) time: 0.1611 data: 0.0833 max mem: 9390 +Train: [57] [1200/6250] eta: 0:11:42 lr: 0.000053 grad: 0.0937 (0.0972) loss: 0.8206 (0.8210) time: 0.1453 data: 0.0690 max mem: 9390 +Train: [57] [1300/6250] eta: 0:11:33 lr: 0.000053 grad: 0.0943 (0.0970) loss: 0.8224 (0.8210) time: 0.1365 data: 0.0565 max mem: 9390 +Train: [57] [1400/6250] eta: 0:11:23 lr: 0.000053 grad: 0.0984 (0.0971) loss: 0.8202 (0.8209) time: 0.1531 data: 0.0656 max mem: 9390 +Train: [57] [1500/6250] eta: 0:11:10 lr: 0.000053 grad: 0.0919 (0.0971) loss: 0.8221 (0.8207) time: 0.1385 data: 0.0621 max mem: 9390 +Train: [57] [1600/6250] eta: 0:10:56 lr: 0.000053 grad: 0.0966 (0.0970) loss: 0.8203 (0.8207) time: 0.1172 data: 0.0370 max mem: 9390 +Train: [57] [1700/6250] eta: 0:10:39 lr: 0.000053 grad: 0.0957 (0.0970) loss: 0.8169 (0.8207) time: 0.1212 data: 0.0374 max mem: 9390 +Train: [57] [1800/6250] eta: 0:10:24 lr: 0.000053 grad: 0.0975 (0.0972) loss: 0.8182 (0.8207) time: 0.1649 data: 0.0617 max mem: 9390 +Train: [57] [1900/6250] eta: 0:10:10 lr: 0.000053 grad: 0.0961 (0.0973) loss: 0.8149 (0.8204) time: 0.1407 data: 0.0660 max mem: 9390 +Train: [57] [2000/6250] eta: 0:09:57 lr: 0.000053 grad: 0.0959 (0.0973) loss: 0.8203 (0.8203) time: 0.1462 data: 0.0688 max mem: 9390 +Train: [57] [2100/6250] eta: 0:09:40 lr: 0.000053 grad: 0.0940 (0.0974) loss: 0.8201 (0.8203) time: 0.1322 data: 0.0562 max mem: 9390 +Train: [57] [2200/6250] eta: 0:09:24 lr: 0.000053 grad: 0.1005 (0.0975) loss: 0.8176 (0.8202) time: 0.1288 data: 0.0503 max mem: 9390 +Train: [57] [2300/6250] eta: 0:09:09 lr: 0.000052 grad: 0.0976 (0.0976) loss: 0.8137 (0.8201) time: 0.1415 data: 0.0636 max mem: 9390 +Train: [57] [2400/6250] eta: 0:08:54 lr: 0.000052 grad: 0.1024 (0.0976) loss: 0.8126 (0.8200) time: 0.1261 data: 0.0380 max mem: 9390 +Train: [57] [2500/6250] eta: 0:08:40 lr: 0.000052 grad: 0.0982 (0.0979) loss: 0.8191 (0.8198) time: 0.1446 data: 0.0699 max mem: 9390 +Train: [57] [2600/6250] eta: 0:08:26 lr: 0.000052 grad: 0.0945 (0.0980) loss: 0.8245 (0.8197) time: 0.1443 data: 0.0671 max mem: 9390 +Train: [57] [2700/6250] eta: 0:08:11 lr: 0.000052 grad: 0.1048 (0.0981) loss: 0.8119 (0.8195) time: 0.1145 data: 0.0326 max mem: 9390 +Train: [57] [2800/6250] eta: 0:07:57 lr: 0.000052 grad: 0.1018 (0.0983) loss: 0.8131 (0.8193) time: 0.1240 data: 0.0446 max mem: 9390 +Train: [57] [2900/6250] eta: 0:07:44 lr: 0.000052 grad: 0.0973 (0.0984) loss: 0.8159 (0.8193) time: 0.1289 data: 0.0495 max mem: 9390 +Train: [57] [3000/6250] eta: 0:07:29 lr: 0.000052 grad: 0.0994 (0.0986) loss: 0.8104 (0.8191) time: 0.1434 data: 0.0613 max mem: 9390 +Train: [57] [3100/6250] eta: 0:07:15 lr: 0.000052 grad: 0.0985 (0.0986) loss: 0.8138 (0.8189) time: 0.1307 data: 0.0540 max mem: 9390 +Train: [57] [3200/6250] eta: 0:07:01 lr: 0.000052 grad: 0.0990 (0.0986) loss: 0.8137 (0.8188) time: 0.1392 data: 0.0441 max mem: 9390 +Train: [57] [3300/6250] eta: 0:06:47 lr: 0.000052 grad: 0.1007 (0.0988) loss: 0.8153 (0.8187) time: 0.1326 data: 0.0538 max mem: 9390 +Train: [57] [3400/6250] eta: 0:06:34 lr: 0.000052 grad: 0.0968 (0.0988) loss: 0.8152 (0.8187) time: 0.1094 data: 0.0082 max mem: 9390 +Train: [57] [3500/6250] eta: 0:06:21 lr: 0.000052 grad: 0.0885 (0.0988) loss: 0.8216 (0.8186) time: 0.1455 data: 0.0470 max mem: 9390 +Train: [57] [3600/6250] eta: 0:06:07 lr: 0.000052 grad: 0.0944 (0.0987) loss: 0.8256 (0.8187) time: 0.1382 data: 0.0590 max mem: 9390 +Train: [57] [3700/6250] eta: 0:05:54 lr: 0.000052 grad: 0.0956 (0.0987) loss: 0.8195 (0.8187) time: 0.1329 data: 0.0548 max mem: 9390 +Train: [57] [3800/6250] eta: 0:05:41 lr: 0.000052 grad: 0.0932 (0.0987) loss: 0.8259 (0.8187) time: 0.1695 data: 0.0895 max mem: 9390 +Train: [57] [3900/6250] eta: 0:05:26 lr: 0.000052 grad: 0.0963 (0.0987) loss: 0.8179 (0.8188) time: 0.1312 data: 0.0497 max mem: 9390 +Train: [57] [4000/6250] eta: 0:05:13 lr: 0.000052 grad: 0.0975 (0.0986) loss: 0.8187 (0.8187) time: 0.1257 data: 0.0492 max mem: 9390 +Train: [57] [4100/6250] eta: 0:04:59 lr: 0.000052 grad: 0.0907 (0.0986) loss: 0.8192 (0.8187) time: 0.1435 data: 0.0663 max mem: 9390 +Train: [57] [4200/6250] eta: 0:04:45 lr: 0.000052 grad: 0.0888 (0.0985) loss: 0.8196 (0.8188) time: 0.1353 data: 0.0574 max mem: 9390 +Train: [57] [4300/6250] eta: 0:04:31 lr: 0.000052 grad: 0.0924 (0.0984) loss: 0.8172 (0.8188) time: 0.1054 data: 0.0243 max mem: 9390 +Train: [57] [4400/6250] eta: 0:04:17 lr: 0.000052 grad: 0.0917 (0.0983) loss: 0.8233 (0.8188) time: 0.1740 data: 0.0927 max mem: 9390 +Train: [57] [4500/6250] eta: 0:04:03 lr: 0.000052 grad: 0.0946 (0.0983) loss: 0.8286 (0.8189) time: 0.1472 data: 0.0693 max mem: 9390 +Train: [57] [4600/6250] eta: 0:03:49 lr: 0.000052 grad: 0.0916 (0.0983) loss: 0.8200 (0.8189) time: 0.1124 data: 0.0310 max mem: 9390 +Train: [57] [4700/6250] eta: 0:03:35 lr: 0.000052 grad: 0.0962 (0.0982) loss: 0.8206 (0.8189) time: 0.1424 data: 0.0624 max mem: 9390 +Train: [57] [4800/6250] eta: 0:03:21 lr: 0.000052 grad: 0.1009 (0.0982) loss: 0.8147 (0.8189) time: 0.1315 data: 0.0476 max mem: 9390 +Train: [57] [4900/6250] eta: 0:03:07 lr: 0.000052 grad: 0.0954 (0.0982) loss: 0.8194 (0.8189) time: 0.1494 data: 0.0742 max mem: 9390 +Train: [57] [5000/6250] eta: 0:02:53 lr: 0.000052 grad: 0.0941 (0.0981) loss: 0.8182 (0.8189) time: 0.1466 data: 0.0705 max mem: 9390 +Train: [57] [5100/6250] eta: 0:02:40 lr: 0.000052 grad: 0.0943 (0.0981) loss: 0.8177 (0.8190) time: 0.1544 data: 0.0657 max mem: 9390 +Train: [57] [5200/6250] eta: 0:02:26 lr: 0.000052 grad: 0.1002 (0.0980) loss: 0.8214 (0.8190) time: 0.1424 data: 0.0665 max mem: 9390 +Train: [57] [5300/6250] eta: 0:02:12 lr: 0.000052 grad: 0.0922 (0.0980) loss: 0.8186 (0.8190) time: 0.1377 data: 0.0613 max mem: 9390 +Train: [57] [5400/6250] eta: 0:01:58 lr: 0.000051 grad: 0.0940 (0.0980) loss: 0.8239 (0.8190) time: 0.1199 data: 0.0370 max mem: 9390 +Train: [57] [5500/6250] eta: 0:01:44 lr: 0.000051 grad: 0.0868 (0.0979) loss: 0.8210 (0.8191) time: 0.1403 data: 0.0603 max mem: 9390 +Train: [57] [5600/6250] eta: 0:01:30 lr: 0.000051 grad: 0.0921 (0.0979) loss: 0.8186 (0.8191) time: 0.1298 data: 0.0485 max mem: 9390 +Train: [57] [5700/6250] eta: 0:01:16 lr: 0.000051 grad: 0.0972 (0.0979) loss: 0.8197 (0.8191) time: 0.1231 data: 0.0356 max mem: 9390 +Train: [57] [5800/6250] eta: 0:01:02 lr: 0.000051 grad: 0.0927 (0.0979) loss: 0.8172 (0.8190) time: 0.1212 data: 0.0433 max mem: 9390 +Train: [57] [5900/6250] eta: 0:00:48 lr: 0.000051 grad: 0.0948 (0.0979) loss: 0.8195 (0.8190) time: 0.1141 data: 0.0355 max mem: 9390 +Train: [57] [6000/6250] eta: 0:00:34 lr: 0.000051 grad: 0.0987 (0.0980) loss: 0.8136 (0.8190) time: 0.1224 data: 0.0414 max mem: 9390 +Train: [57] [6100/6250] eta: 0:00:20 lr: 0.000051 grad: 0.0993 (0.0980) loss: 0.8177 (0.8190) time: 0.1092 data: 0.0249 max mem: 9390 +Train: [57] [6200/6250] eta: 0:00:06 lr: 0.000051 grad: 0.0970 (0.0980) loss: 0.8165 (0.8190) time: 0.1156 data: 0.0349 max mem: 9390 +Train: [57] [6249/6250] eta: 0:00:00 lr: 0.000051 grad: 0.0970 (0.0980) loss: 0.8146 (0.8189) time: 0.1085 data: 0.0282 max mem: 9390 +Train: [57] Total time: 0:14:26 (0.1387 s / it) +Averaged stats: lr: 0.000051 grad: 0.0970 (0.0980) loss: 0.8146 (0.8189) +Eval (hcp-train-subset): [57] [ 0/62] eta: 0:05:02 loss: 0.8414 (0.8414) time: 4.8831 data: 4.8502 max mem: 9390 +Eval (hcp-train-subset): [57] [61/62] eta: 0:00:00 loss: 0.8330 (0.8339) time: 0.1054 data: 0.0785 max mem: 9390 +Eval (hcp-train-subset): [57] Total time: 0:00:13 (0.2117 s / it) +Averaged stats (hcp-train-subset): loss: 0.8330 (0.8339) +Eval (hcp-val): [57] [ 0/62] eta: 0:05:28 loss: 0.8292 (0.8292) time: 5.3000 data: 5.2699 max mem: 9390 +Eval (hcp-val): [57] [61/62] eta: 0:00:00 loss: 0.8331 (0.8347) time: 0.1187 data: 0.0923 max mem: 9390 +Eval (hcp-val): [57] Total time: 0:00:12 (0.1960 s / it) +Averaged stats (hcp-val): loss: 0.8331 (0.8347) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +Train: [58] [ 0/6250] eta: 9:48:16 lr: 0.000051 grad: 0.0771 (0.0771) loss: 0.8603 (0.8603) time: 5.6475 data: 5.5500 max mem: 9390 +Train: [58] [ 100/6250] eta: 0:19:01 lr: 0.000051 grad: 0.1025 (0.1056) loss: 0.8184 (0.8327) time: 0.1310 data: 0.0350 max mem: 9390 +Train: [58] [ 200/6250] eta: 0:16:21 lr: 0.000051 grad: 0.0962 (0.1050) loss: 0.8244 (0.8288) time: 0.1204 data: 0.0313 max mem: 9390 +Train: [58] [ 300/6250] eta: 0:14:54 lr: 0.000051 grad: 0.0944 (0.1028) loss: 0.8267 (0.8267) time: 0.1226 data: 0.0365 max mem: 9390 +Train: [58] [ 400/6250] eta: 0:14:02 lr: 0.000051 grad: 0.0922 (0.1013) loss: 0.8244 (0.8258) time: 0.1350 data: 0.0481 max mem: 9390 +Train: [58] [ 500/6250] eta: 0:13:21 lr: 0.000051 grad: 0.0852 (0.1000) loss: 0.8321 (0.8251) time: 0.1188 data: 0.0317 max mem: 9390 +Train: [58] [ 600/6250] eta: 0:12:50 lr: 0.000051 grad: 0.0877 (0.0991) loss: 0.8223 (0.8240) time: 0.1253 data: 0.0362 max mem: 9390 +Train: [58] [ 700/6250] eta: 0:12:23 lr: 0.000051 grad: 0.0886 (0.0982) loss: 0.8212 (0.8237) time: 0.1197 data: 0.0361 max mem: 9390 +Train: [58] [ 800/6250] eta: 0:12:09 lr: 0.000051 grad: 0.0930 (0.0976) loss: 0.8161 (0.8236) time: 0.1496 data: 0.0694 max mem: 9390 +Train: [58] [ 900/6250] eta: 0:12:10 lr: 0.000051 grad: 0.0799 (0.0966) loss: 0.8284 (0.8238) time: 0.1429 data: 0.0688 max mem: 9390 +Train: [58] [1000/6250] eta: 0:12:10 lr: 0.000051 grad: 0.0848 (0.0961) loss: 0.8199 (0.8237) time: 0.1878 data: 0.1093 max mem: 9390 +Train: [58] [1100/6250] eta: 0:12:07 lr: 0.000051 grad: 0.0920 (0.0961) loss: 0.8145 (0.8233) time: 0.1390 data: 0.0618 max mem: 9390 +Train: [58] [1200/6250] eta: 0:12:00 lr: 0.000051 grad: 0.0894 (0.0958) loss: 0.8188 (0.8233) time: 0.1091 data: 0.0251 max mem: 9390 +Train: [58] [1300/6250] eta: 0:11:54 lr: 0.000051 grad: 0.0892 (0.0956) loss: 0.8177 (0.8231) time: 0.1205 data: 0.0392 max mem: 9390 +Train: [58] [1400/6250] eta: 0:11:42 lr: 0.000051 grad: 0.1027 (0.0955) loss: 0.8229 (0.8230) time: 0.1376 data: 0.0554 max mem: 9390 +Train: [58] [1500/6250] eta: 0:11:26 lr: 0.000051 grad: 0.0969 (0.0954) loss: 0.8211 (0.8229) time: 0.1387 data: 0.0583 max mem: 9390 +Train: [58] [1600/6250] eta: 0:11:07 lr: 0.000051 grad: 0.0908 (0.0955) loss: 0.8211 (0.8226) time: 0.1382 data: 0.0588 max mem: 9390 +Train: [58] [1700/6250] eta: 0:10:53 lr: 0.000051 grad: 0.0980 (0.0957) loss: 0.8196 (0.8223) time: 0.1463 data: 0.0708 max mem: 9390 +Train: [58] [1800/6250] eta: 0:10:36 lr: 0.000051 grad: 0.0965 (0.0958) loss: 0.8190 (0.8220) time: 0.1304 data: 0.0535 max mem: 9390 +Train: [58] [1900/6250] eta: 0:10:22 lr: 0.000051 grad: 0.1018 (0.0959) loss: 0.8176 (0.8218) time: 0.1616 data: 0.0807 max mem: 9390 +Train: [58] [2000/6250] eta: 0:10:09 lr: 0.000051 grad: 0.0994 (0.0960) loss: 0.8138 (0.8215) time: 0.1438 data: 0.0644 max mem: 9390 +Train: [58] [2100/6250] eta: 0:09:52 lr: 0.000051 grad: 0.0946 (0.0963) loss: 0.8130 (0.8212) time: 0.1161 data: 0.0293 max mem: 9390 +Train: [58] [2200/6250] eta: 0:09:37 lr: 0.000050 grad: 0.0897 (0.0963) loss: 0.8233 (0.8210) time: 0.1521 data: 0.0784 max mem: 9390 +Train: [58] [2300/6250] eta: 0:09:23 lr: 0.000050 grad: 0.0965 (0.0965) loss: 0.8183 (0.8207) time: 0.1569 data: 0.0703 max mem: 9390 +Train: [58] [2400/6250] eta: 0:09:06 lr: 0.000050 grad: 0.0944 (0.0967) loss: 0.8185 (0.8205) time: 0.1080 data: 0.0197 max mem: 9390 +Train: [58] [2500/6250] eta: 0:09:00 lr: 0.000050 grad: 0.1002 (0.0969) loss: 0.8172 (0.8203) time: 0.3466 data: 0.2127 max mem: 9390 +Train: [58] [2600/6250] eta: 0:08:42 lr: 0.000050 grad: 0.0949 (0.0970) loss: 0.8093 (0.8200) time: 0.1278 data: 0.0502 max mem: 9390 +Train: [58] [2700/6250] eta: 0:08:26 lr: 0.000050 grad: 0.0921 (0.0972) loss: 0.8146 (0.8198) time: 0.1325 data: 0.0473 max mem: 9390 +Train: [58] [2800/6250] eta: 0:08:10 lr: 0.000050 grad: 0.0969 (0.0974) loss: 0.8187 (0.8196) time: 0.1282 data: 0.0465 max mem: 9390 +Train: [58] [2900/6250] eta: 0:07:56 lr: 0.000050 grad: 0.0990 (0.0976) loss: 0.8148 (0.8194) time: 0.1300 data: 0.0530 max mem: 9390 +Train: [58] [3000/6250] eta: 0:07:41 lr: 0.000050 grad: 0.0975 (0.0977) loss: 0.8172 (0.8192) time: 0.1461 data: 0.0686 max mem: 9390 +Train: [58] [3100/6250] eta: 0:07:27 lr: 0.000050 grad: 0.1019 (0.0979) loss: 0.8123 (0.8190) time: 0.1403 data: 0.0538 max mem: 9390 +Train: [58] [3200/6250] eta: 0:07:12 lr: 0.000050 grad: 0.1000 (0.0980) loss: 0.8122 (0.8189) time: 0.1309 data: 0.0531 max mem: 9390 +Train: [58] [3300/6250] eta: 0:06:57 lr: 0.000050 grad: 0.0979 (0.0981) loss: 0.8167 (0.8188) time: 0.1499 data: 0.0652 max mem: 9390 +Train: [58] [3400/6250] eta: 0:06:44 lr: 0.000050 grad: 0.0962 (0.0982) loss: 0.8116 (0.8187) time: 0.1366 data: 0.0448 max mem: 9390 +Train: [58] [3500/6250] eta: 0:06:30 lr: 0.000050 grad: 0.0965 (0.0982) loss: 0.8190 (0.8187) time: 0.1444 data: 0.0669 max mem: 9390 +Train: [58] [3600/6250] eta: 0:06:15 lr: 0.000050 grad: 0.0994 (0.0983) loss: 0.8196 (0.8187) time: 0.1152 data: 0.0358 max mem: 9390 +Train: [58] [3700/6250] eta: 0:06:00 lr: 0.000050 grad: 0.0978 (0.0983) loss: 0.8247 (0.8187) time: 0.1309 data: 0.0532 max mem: 9390 +Train: [58] [3800/6250] eta: 0:05:46 lr: 0.000050 grad: 0.0981 (0.0984) loss: 0.8154 (0.8187) time: 0.1638 data: 0.0818 max mem: 9390 +Train: [58] [3900/6250] eta: 0:05:33 lr: 0.000050 grad: 0.0990 (0.0984) loss: 0.8246 (0.8187) time: 0.1383 data: 0.0594 max mem: 9390 +Train: [58] [4000/6250] eta: 0:05:19 lr: 0.000050 grad: 0.0986 (0.0984) loss: 0.8144 (0.8187) time: 0.1382 data: 0.0632 max mem: 9390 +Train: [58] [4100/6250] eta: 0:05:05 lr: 0.000050 grad: 0.0939 (0.0984) loss: 0.8196 (0.8186) time: 0.1443 data: 0.0589 max mem: 9390 +Train: [58] [4200/6250] eta: 0:04:51 lr: 0.000050 grad: 0.0938 (0.0984) loss: 0.8191 (0.8187) time: 0.1413 data: 0.0622 max mem: 9390 +Train: [58] [4300/6250] eta: 0:04:36 lr: 0.000050 grad: 0.0934 (0.0983) loss: 0.8197 (0.8188) time: 0.1328 data: 0.0432 max mem: 9390 +Train: [58] [4400/6250] eta: 0:04:22 lr: 0.000050 grad: 0.0962 (0.0984) loss: 0.8156 (0.8188) time: 0.1355 data: 0.0548 max mem: 9390 +Train: [58] [4500/6250] eta: 0:04:07 lr: 0.000050 grad: 0.0987 (0.0983) loss: 0.8177 (0.8188) time: 0.1407 data: 0.0595 max mem: 9390 +Train: [58] [4600/6250] eta: 0:03:53 lr: 0.000050 grad: 0.0931 (0.0982) loss: 0.8217 (0.8189) time: 0.1393 data: 0.0620 max mem: 9390 +Train: [58] [4700/6250] eta: 0:03:39 lr: 0.000050 grad: 0.0974 (0.0982) loss: 0.8248 (0.8190) time: 0.1359 data: 0.0518 max mem: 9390 +Train: [58] [4800/6250] eta: 0:03:24 lr: 0.000050 grad: 0.0956 (0.0982) loss: 0.8198 (0.8190) time: 0.1165 data: 0.0370 max mem: 9390 +Train: [58] [4900/6250] eta: 0:03:10 lr: 0.000050 grad: 0.1001 (0.0982) loss: 0.8239 (0.8190) time: 0.2057 data: 0.1344 max mem: 9390 +Train: [58] [5000/6250] eta: 0:02:56 lr: 0.000050 grad: 0.1027 (0.0982) loss: 0.8190 (0.8191) time: 0.1618 data: 0.0822 max mem: 9390 +Train: [58] [5100/6250] eta: 0:02:42 lr: 0.000050 grad: 0.0932 (0.0982) loss: 0.8194 (0.8191) time: 0.1589 data: 0.0807 max mem: 9390 +Train: [58] [5200/6250] eta: 0:02:28 lr: 0.000050 grad: 0.0968 (0.0982) loss: 0.8179 (0.8191) time: 0.1496 data: 0.0691 max mem: 9390 +Train: [58] [5300/6250] eta: 0:02:14 lr: 0.000049 grad: 0.0962 (0.0982) loss: 0.8167 (0.8190) time: 0.1365 data: 0.0548 max mem: 9390 +Train: [58] [5400/6250] eta: 0:02:00 lr: 0.000049 grad: 0.1046 (0.0983) loss: 0.8181 (0.8190) time: 0.1475 data: 0.0689 max mem: 9390 +Train: [58] [5500/6250] eta: 0:01:46 lr: 0.000049 grad: 0.0992 (0.0983) loss: 0.8145 (0.8189) time: 0.1302 data: 0.0558 max mem: 9390 +Train: [58] [5600/6250] eta: 0:01:31 lr: 0.000049 grad: 0.0951 (0.0983) loss: 0.8189 (0.8189) time: 0.1218 data: 0.0353 max mem: 9390 +Train: [58] [5700/6250] eta: 0:01:17 lr: 0.000049 grad: 0.1025 (0.0984) loss: 0.8190 (0.8189) time: 0.1187 data: 0.0418 max mem: 9390 +Train: [58] [5800/6250] eta: 0:01:03 lr: 0.000049 grad: 0.0992 (0.0985) loss: 0.8142 (0.8188) time: 0.1281 data: 0.0429 max mem: 9390 +Train: [58] [5900/6250] eta: 0:00:49 lr: 0.000049 grad: 0.0912 (0.0985) loss: 0.8149 (0.8187) time: 0.1279 data: 0.0456 max mem: 9390 +Train: [58] [6000/6250] eta: 0:00:34 lr: 0.000049 grad: 0.0957 (0.0985) loss: 0.8157 (0.8187) time: 0.1238 data: 0.0440 max mem: 9390 +Train: [58] [6100/6250] eta: 0:00:20 lr: 0.000049 grad: 0.0972 (0.0985) loss: 0.8161 (0.8187) time: 0.1258 data: 0.0440 max mem: 9390 +Train: [58] [6200/6250] eta: 0:00:06 lr: 0.000049 grad: 0.0945 (0.0985) loss: 0.8229 (0.8187) time: 0.1718 data: 0.0884 max mem: 9390 +Train: [58] [6249/6250] eta: 0:00:00 lr: 0.000049 grad: 0.0941 (0.0985) loss: 0.8160 (0.8187) time: 0.1336 data: 0.0537 max mem: 9390 +Train: [58] Total time: 0:14:38 (0.1405 s / it) +Averaged stats: lr: 0.000049 grad: 0.0941 (0.0985) loss: 0.8160 (0.8187) +Eval (hcp-train-subset): [58] [ 0/62] eta: 0:03:24 loss: 0.8397 (0.8397) time: 3.2968 data: 3.2171 max mem: 9390 +Eval (hcp-train-subset): [58] [61/62] eta: 0:00:00 loss: 0.8303 (0.8328) time: 0.1053 data: 0.0804 max mem: 9390 +Eval (hcp-train-subset): [58] Total time: 0:00:13 (0.2161 s / it) +Averaged stats (hcp-train-subset): loss: 0.8303 (0.8328) +Eval (hcp-val): [58] [ 0/62] eta: 0:03:36 loss: 0.8326 (0.8326) time: 3.4905 data: 3.4292 max mem: 9390 +Eval (hcp-val): [58] [61/62] eta: 0:00:00 loss: 0.8345 (0.8346) time: 0.1175 data: 0.0925 max mem: 9390 +Eval (hcp-val): [58] Total time: 0:00:12 (0.1994 s / it) +Averaged stats (hcp-val): loss: 0.8345 (0.8346) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +Train: [59] [ 0/6250] eta: 10:12:43 lr: 0.000049 grad: 0.1485 (0.1485) loss: 0.8098 (0.8098) time: 5.8822 data: 5.7862 max mem: 9390 +Train: [59] [ 100/6250] eta: 0:18:54 lr: 0.000049 grad: 0.0932 (0.1016) loss: 0.8336 (0.8316) time: 0.1359 data: 0.0360 max mem: 9390 +Train: [59] [ 200/6250] eta: 0:16:02 lr: 0.000049 grad: 0.0870 (0.0980) loss: 0.8216 (0.8282) time: 0.1317 data: 0.0424 max mem: 9390 +Train: [59] [ 300/6250] eta: 0:14:44 lr: 0.000049 grad: 0.0878 (0.0969) loss: 0.8220 (0.8263) time: 0.1198 data: 0.0317 max mem: 9390 +Train: [59] [ 400/6250] eta: 0:14:00 lr: 0.000049 grad: 0.0860 (0.0965) loss: 0.8308 (0.8251) time: 0.1359 data: 0.0462 max mem: 9390 +Train: [59] [ 500/6250] eta: 0:13:16 lr: 0.000049 grad: 0.0975 (0.0965) loss: 0.8147 (0.8241) time: 0.1272 data: 0.0393 max mem: 9390 +Train: [59] [ 600/6250] eta: 0:12:47 lr: 0.000049 grad: 0.0886 (0.0961) loss: 0.8192 (0.8230) time: 0.1139 data: 0.0259 max mem: 9390 +Train: [59] [ 700/6250] eta: 0:12:18 lr: 0.000049 grad: 0.0893 (0.0955) loss: 0.8245 (0.8225) time: 0.1167 data: 0.0231 max mem: 9390 +Train: [59] [ 800/6250] eta: 0:12:01 lr: 0.000049 grad: 0.0906 (0.0953) loss: 0.8193 (0.8221) time: 0.1322 data: 0.0477 max mem: 9390 +Train: [59] [ 900/6250] eta: 0:12:05 lr: 0.000049 grad: 0.0856 (0.0946) loss: 0.8251 (0.8223) time: 0.1375 data: 0.0558 max mem: 9390 +Train: [59] [1000/6250] eta: 0:12:06 lr: 0.000049 grad: 0.0911 (0.0944) loss: 0.8180 (0.8221) time: 0.1702 data: 0.0946 max mem: 9390 +Train: [59] [1100/6250] eta: 0:12:04 lr: 0.000049 grad: 0.0846 (0.0942) loss: 0.8245 (0.8220) time: 0.1665 data: 0.0886 max mem: 9390 +Train: [59] [1200/6250] eta: 0:11:58 lr: 0.000049 grad: 0.0838 (0.0942) loss: 0.8204 (0.8218) time: 0.1590 data: 0.0785 max mem: 9390 +Train: [59] [1300/6250] eta: 0:11:43 lr: 0.000049 grad: 0.0887 (0.0943) loss: 0.8197 (0.8215) time: 0.1281 data: 0.0484 max mem: 9390 +Train: [59] [1400/6250] eta: 0:11:26 lr: 0.000049 grad: 0.0961 (0.0943) loss: 0.8172 (0.8214) time: 0.1241 data: 0.0396 max mem: 9390 +Train: [59] [1500/6250] eta: 0:11:13 lr: 0.000049 grad: 0.0901 (0.0945) loss: 0.8254 (0.8212) time: 0.1439 data: 0.0510 max mem: 9390 +Train: [59] [1600/6250] eta: 0:10:56 lr: 0.000049 grad: 0.0952 (0.0944) loss: 0.8203 (0.8212) time: 0.1512 data: 0.0679 max mem: 9390 +Train: [59] [1700/6250] eta: 0:10:43 lr: 0.000049 grad: 0.0924 (0.0944) loss: 0.8196 (0.8209) time: 0.1247 data: 0.0491 max mem: 9390 +Train: [59] [1800/6250] eta: 0:10:28 lr: 0.000049 grad: 0.0986 (0.0945) loss: 0.8125 (0.8209) time: 0.1090 data: 0.0258 max mem: 9390 +Train: [59] [1900/6250] eta: 0:10:10 lr: 0.000049 grad: 0.0983 (0.0946) loss: 0.8213 (0.8208) time: 0.1270 data: 0.0433 max mem: 9390 +Train: [59] [2000/6250] eta: 0:09:58 lr: 0.000049 grad: 0.0976 (0.0948) loss: 0.8190 (0.8208) time: 0.1567 data: 0.0659 max mem: 9390 +Train: [59] [2100/6250] eta: 0:09:45 lr: 0.000048 grad: 0.0956 (0.0950) loss: 0.8183 (0.8207) time: 0.1641 data: 0.0841 max mem: 9390 +Train: [59] [2200/6250] eta: 0:09:28 lr: 0.000048 grad: 0.0934 (0.0949) loss: 0.8202 (0.8207) time: 0.1361 data: 0.0587 max mem: 9390 +Train: [59] [2300/6250] eta: 0:09:13 lr: 0.000048 grad: 0.0905 (0.0950) loss: 0.8152 (0.8206) time: 0.1315 data: 0.0462 max mem: 9390 +Train: [59] [2400/6250] eta: 0:08:57 lr: 0.000048 grad: 0.0999 (0.0952) loss: 0.8174 (0.8206) time: 0.1416 data: 0.0616 max mem: 9390 +Train: [59] [2500/6250] eta: 0:08:43 lr: 0.000048 grad: 0.0959 (0.0953) loss: 0.8155 (0.8204) time: 0.1490 data: 0.0670 max mem: 9390 +Train: [59] [2600/6250] eta: 0:08:27 lr: 0.000048 grad: 0.0937 (0.0956) loss: 0.8178 (0.8203) time: 0.1294 data: 0.0472 max mem: 9390 +Train: [59] [2700/6250] eta: 0:08:13 lr: 0.000048 grad: 0.0950 (0.0956) loss: 0.8180 (0.8203) time: 0.1447 data: 0.0702 max mem: 9390 +Train: [59] [2800/6250] eta: 0:07:59 lr: 0.000048 grad: 0.0889 (0.0957) loss: 0.8237 (0.8203) time: 0.1279 data: 0.0446 max mem: 9390 +Train: [59] [2900/6250] eta: 0:07:45 lr: 0.000048 grad: 0.0905 (0.0957) loss: 0.8122 (0.8203) time: 0.1735 data: 0.0750 max mem: 9390 +Train: [59] [3000/6250] eta: 0:07:31 lr: 0.000048 grad: 0.0871 (0.0956) loss: 0.8227 (0.8203) time: 0.1578 data: 0.0809 max mem: 9390 +Train: [59] [3100/6250] eta: 0:07:16 lr: 0.000048 grad: 0.0939 (0.0957) loss: 0.8209 (0.8203) time: 0.1359 data: 0.0606 max mem: 9390 +Train: [59] [3200/6250] eta: 0:07:02 lr: 0.000048 grad: 0.0898 (0.0957) loss: 0.8231 (0.8203) time: 0.1384 data: 0.0628 max mem: 9390 +Train: [59] [3300/6250] eta: 0:06:48 lr: 0.000048 grad: 0.0959 (0.0957) loss: 0.8258 (0.8202) time: 0.1288 data: 0.0458 max mem: 9390 +Train: [59] [3400/6250] eta: 0:06:35 lr: 0.000048 grad: 0.0958 (0.0957) loss: 0.8202 (0.8203) time: 0.1469 data: 0.0723 max mem: 9390 +Train: [59] [3500/6250] eta: 0:06:21 lr: 0.000048 grad: 0.0993 (0.0957) loss: 0.8226 (0.8203) time: 0.1320 data: 0.0592 max mem: 9390 +Train: [59] [3600/6250] eta: 0:06:07 lr: 0.000048 grad: 0.0942 (0.0957) loss: 0.8167 (0.8203) time: 0.1616 data: 0.0847 max mem: 9390 +Train: [59] [3700/6250] eta: 0:05:53 lr: 0.000048 grad: 0.0942 (0.0959) loss: 0.8175 (0.8203) time: 0.1385 data: 0.0502 max mem: 9390 +Train: [59] [3800/6250] eta: 0:05:39 lr: 0.000048 grad: 0.0928 (0.0959) loss: 0.8179 (0.8203) time: 0.1460 data: 0.0763 max mem: 9390 +Train: [59] [3900/6250] eta: 0:05:26 lr: 0.000048 grad: 0.0894 (0.0958) loss: 0.8215 (0.8204) time: 0.1175 data: 0.0380 max mem: 9390 +Train: [59] [4000/6250] eta: 0:05:12 lr: 0.000048 grad: 0.0873 (0.0958) loss: 0.8215 (0.8203) time: 0.1164 data: 0.0292 max mem: 9390 +Train: [59] [4100/6250] eta: 0:04:58 lr: 0.000048 grad: 0.0942 (0.0957) loss: 0.8252 (0.8205) time: 0.1562 data: 0.0631 max mem: 9390 +Train: [59] [4200/6250] eta: 0:04:44 lr: 0.000048 grad: 0.0899 (0.0957) loss: 0.8252 (0.8205) time: 0.1385 data: 0.0611 max mem: 9390 +Train: [59] [4300/6250] eta: 0:04:30 lr: 0.000048 grad: 0.0946 (0.0958) loss: 0.8218 (0.8205) time: 0.1476 data: 0.0700 max mem: 9390 +Train: [59] [4400/6250] eta: 0:04:16 lr: 0.000048 grad: 0.0889 (0.0957) loss: 0.8217 (0.8205) time: 0.1187 data: 0.0373 max mem: 9390 +Train: [59] [4500/6250] eta: 0:04:02 lr: 0.000048 grad: 0.0887 (0.0957) loss: 0.8208 (0.8205) time: 0.1091 data: 0.0184 max mem: 9390 +Train: [59] [4600/6250] eta: 0:03:48 lr: 0.000048 grad: 0.0968 (0.0958) loss: 0.8195 (0.8206) time: 0.1353 data: 0.0557 max mem: 9390 +Train: [59] [4700/6250] eta: 0:03:34 lr: 0.000048 grad: 0.0999 (0.0958) loss: 0.8180 (0.8206) time: 0.1411 data: 0.0592 max mem: 9390 +Train: [59] [4800/6250] eta: 0:03:20 lr: 0.000048 grad: 0.0984 (0.0958) loss: 0.8191 (0.8206) time: 0.1415 data: 0.0553 max mem: 9390 +Train: [59] [4900/6250] eta: 0:03:07 lr: 0.000048 grad: 0.0935 (0.0959) loss: 0.8178 (0.8206) time: 0.1561 data: 0.0717 max mem: 9390 +Train: [59] [5000/6250] eta: 0:02:53 lr: 0.000048 grad: 0.0982 (0.0960) loss: 0.8130 (0.8205) time: 0.1327 data: 0.0541 max mem: 9390 +Train: [59] [5100/6250] eta: 0:02:40 lr: 0.000048 grad: 0.0933 (0.0960) loss: 0.8234 (0.8205) time: 0.1433 data: 0.0617 max mem: 9390 +Train: [59] [5200/6250] eta: 0:02:26 lr: 0.000047 grad: 0.0848 (0.0961) loss: 0.8226 (0.8204) time: 0.1395 data: 0.0565 max mem: 9390 +Train: [59] [5300/6250] eta: 0:02:12 lr: 0.000047 grad: 0.0959 (0.0961) loss: 0.8179 (0.8204) time: 0.1522 data: 0.0727 max mem: 9390 +Train: [59] [5400/6250] eta: 0:01:58 lr: 0.000047 grad: 0.0915 (0.0961) loss: 0.8205 (0.8203) time: 0.1208 data: 0.0377 max mem: 9390 +Train: [59] [5500/6250] eta: 0:01:44 lr: 0.000047 grad: 0.0951 (0.0962) loss: 0.8166 (0.8202) time: 0.1236 data: 0.0435 max mem: 9390 +Train: [59] [5600/6250] eta: 0:01:30 lr: 0.000047 grad: 0.0960 (0.0962) loss: 0.8192 (0.8202) time: 0.1174 data: 0.0368 max mem: 9390 +Train: [59] [5700/6250] eta: 0:01:15 lr: 0.000047 grad: 0.0932 (0.0963) loss: 0.8170 (0.8201) time: 0.1236 data: 0.0359 max mem: 9390 +Train: [59] [5800/6250] eta: 0:01:02 lr: 0.000047 grad: 0.1002 (0.0964) loss: 0.8058 (0.8200) time: 0.1298 data: 0.0478 max mem: 9390 +Train: [59] [5900/6250] eta: 0:00:48 lr: 0.000047 grad: 0.0967 (0.0964) loss: 0.8194 (0.8200) time: 0.1294 data: 0.0480 max mem: 9390 +Train: [59] [6000/6250] eta: 0:00:34 lr: 0.000047 grad: 0.0979 (0.0964) loss: 0.8157 (0.8199) time: 0.1301 data: 0.0511 max mem: 9390 +Train: [59] [6100/6250] eta: 0:00:20 lr: 0.000047 grad: 0.0950 (0.0964) loss: 0.8190 (0.8199) time: 0.1554 data: 0.0784 max mem: 9390 +Train: [59] [6200/6250] eta: 0:00:06 lr: 0.000047 grad: 0.0953 (0.0964) loss: 0.8190 (0.8199) time: 0.1362 data: 0.0556 max mem: 9390 +Train: [59] [6249/6250] eta: 0:00:00 lr: 0.000047 grad: 0.0963 (0.0964) loss: 0.8190 (0.8199) time: 0.1153 data: 0.0397 max mem: 9390 +Train: [59] Total time: 0:14:22 (0.1380 s / it) +Averaged stats: lr: 0.000047 grad: 0.0963 (0.0964) loss: 0.8190 (0.8199) +Eval (hcp-train-subset): [59] [ 0/62] eta: 0:05:10 loss: 0.8460 (0.8460) time: 5.0106 data: 4.9799 max mem: 9390 +Eval (hcp-train-subset): [59] [61/62] eta: 0:00:00 loss: 0.8338 (0.8349) time: 0.1214 data: 0.0948 max mem: 9390 +Eval (hcp-train-subset): [59] Total time: 0:00:13 (0.2135 s / it) +Averaged stats (hcp-train-subset): loss: 0.8338 (0.8349) +Making plots (hcp-train-subset): example=43 +Eval (hcp-val): [59] [ 0/62] eta: 0:03:30 loss: 0.8308 (0.8308) time: 3.3934 data: 3.3285 max mem: 9390 +Eval (hcp-val): [59] [61/62] eta: 0:00:00 loss: 0.8331 (0.8334) time: 0.1117 data: 0.0853 max mem: 9390 +Eval (hcp-val): [59] Total time: 0:00:12 (0.1983 s / it) +Averaged stats (hcp-val): loss: 0.8331 (0.8334) +Making plots (hcp-val): example=43 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +Train: [60] [ 0/6250] eta: 9:31:05 lr: 0.000047 grad: 0.1440 (0.1440) loss: 0.8405 (0.8405) time: 5.4826 data: 5.3601 max mem: 9390 +Train: [60] [ 100/6250] eta: 0:18:28 lr: 0.000047 grad: 0.1175 (0.1118) loss: 0.8236 (0.8355) time: 0.1252 data: 0.0276 max mem: 9390 +Train: [60] [ 200/6250] eta: 0:15:57 lr: 0.000047 grad: 0.0993 (0.1112) loss: 0.8138 (0.8264) time: 0.1360 data: 0.0482 max mem: 9390 +Train: [60] [ 300/6250] eta: 0:14:51 lr: 0.000047 grad: 0.0927 (0.1099) loss: 0.8182 (0.8241) time: 0.1284 data: 0.0366 max mem: 9390 +Train: [60] [ 400/6250] eta: 0:14:04 lr: 0.000047 grad: 0.0921 (0.1072) loss: 0.8143 (0.8218) time: 0.1313 data: 0.0456 max mem: 9390 +Train: [60] [ 500/6250] eta: 0:13:19 lr: 0.000047 grad: 0.0893 (0.1048) loss: 0.8161 (0.8208) time: 0.1106 data: 0.0265 max mem: 9390 +Train: [60] [ 600/6250] eta: 0:12:46 lr: 0.000047 grad: 0.0926 (0.1035) loss: 0.8180 (0.8204) time: 0.1217 data: 0.0349 max mem: 9390 +Train: [60] [ 700/6250] eta: 0:12:18 lr: 0.000047 grad: 0.0981 (0.1030) loss: 0.8141 (0.8201) time: 0.1145 data: 0.0243 max mem: 9390 +Train: [60] [ 800/6250] eta: 0:12:00 lr: 0.000047 grad: 0.0947 (0.1024) loss: 0.8192 (0.8199) time: 0.1504 data: 0.0657 max mem: 9390 +Train: [60] [ 900/6250] eta: 0:11:56 lr: 0.000047 grad: 0.1021 (0.1020) loss: 0.8188 (0.8195) time: 0.1493 data: 0.0735 max mem: 9390 +Train: [60] [1000/6250] eta: 0:11:51 lr: 0.000047 grad: 0.0995 (0.1018) loss: 0.8192 (0.8192) time: 0.1417 data: 0.0627 max mem: 9390 +Train: [60] [1100/6250] eta: 0:11:43 lr: 0.000047 grad: 0.0917 (0.1015) loss: 0.8175 (0.8190) time: 0.1740 data: 0.0830 max mem: 9390 +Train: [60] [1200/6250] eta: 0:11:35 lr: 0.000047 grad: 0.1020 (0.1014) loss: 0.8075 (0.8187) time: 0.1565 data: 0.0768 max mem: 9390 +Train: [60] [1300/6250] eta: 0:11:24 lr: 0.000047 grad: 0.0915 (0.1013) loss: 0.8175 (0.8182) time: 0.1687 data: 0.0940 max mem: 9390 +Train: [60] [1400/6250] eta: 0:11:08 lr: 0.000047 grad: 0.0971 (0.1014) loss: 0.8107 (0.8179) time: 0.1286 data: 0.0511 max mem: 9390 +Train: [60] [1500/6250] eta: 0:10:54 lr: 0.000047 grad: 0.0935 (0.1013) loss: 0.8141 (0.8176) time: 0.1416 data: 0.0651 max mem: 9390 +Train: [60] [1600/6250] eta: 0:10:40 lr: 0.000047 grad: 0.0987 (0.1013) loss: 0.8165 (0.8174) time: 0.1535 data: 0.0732 max mem: 9390 +Train: [60] [1700/6250] eta: 0:10:25 lr: 0.000047 grad: 0.0982 (0.1011) loss: 0.8157 (0.8173) time: 0.1444 data: 0.0639 max mem: 9390 +Train: [60] [1800/6250] eta: 0:10:08 lr: 0.000047 grad: 0.1017 (0.1011) loss: 0.8100 (0.8169) time: 0.1121 data: 0.0322 max mem: 9390 +Train: [60] [1900/6250] eta: 0:09:54 lr: 0.000047 grad: 0.0966 (0.1012) loss: 0.8113 (0.8165) time: 0.1169 data: 0.0368 max mem: 9390 +Train: [60] [2000/6250] eta: 0:09:40 lr: 0.000047 grad: 0.0989 (0.1014) loss: 0.8046 (0.8162) time: 0.1405 data: 0.0505 max mem: 9390 +Train: [60] [2100/6250] eta: 0:09:28 lr: 0.000046 grad: 0.0964 (0.1015) loss: 0.8068 (0.8157) time: 0.1417 data: 0.0586 max mem: 9390 +Train: [60] [2200/6250] eta: 0:09:15 lr: 0.000046 grad: 0.0998 (0.1017) loss: 0.8144 (0.8155) time: 0.1691 data: 0.0807 max mem: 9390 +Train: [60] [2300/6250] eta: 0:09:00 lr: 0.000046 grad: 0.0967 (0.1020) loss: 0.8149 (0.8151) time: 0.1254 data: 0.0442 max mem: 9390 +Train: [60] [2400/6250] eta: 0:08:47 lr: 0.000046 grad: 0.1006 (0.1022) loss: 0.8092 (0.8148) time: 0.1377 data: 0.0654 max mem: 9390 +Train: [60] [2500/6250] eta: 0:08:34 lr: 0.000046 grad: 0.0970 (0.1023) loss: 0.8113 (0.8147) time: 0.1333 data: 0.0547 max mem: 9390 +Train: [60] [2600/6250] eta: 0:08:20 lr: 0.000046 grad: 0.0932 (0.1024) loss: 0.8145 (0.8145) time: 0.1291 data: 0.0472 max mem: 9390 +Train: [60] [2700/6250] eta: 0:08:06 lr: 0.000046 grad: 0.0998 (0.1024) loss: 0.8145 (0.8145) time: 0.1263 data: 0.0451 max mem: 9390 +Train: [60] [2800/6250] eta: 0:07:52 lr: 0.000046 grad: 0.0955 (0.1024) loss: 0.8152 (0.8145) time: 0.1339 data: 0.0534 max mem: 9390 +Train: [60] [2900/6250] eta: 0:07:39 lr: 0.000046 grad: 0.0989 (0.1024) loss: 0.8092 (0.8145) time: 0.1156 data: 0.0399 max mem: 9390 +Train: [60] [3000/6250] eta: 0:07:25 lr: 0.000046 grad: 0.0967 (0.1024) loss: 0.8178 (0.8146) time: 0.1358 data: 0.0590 max mem: 9390 +Train: [60] [3100/6250] eta: 0:07:12 lr: 0.000046 grad: 0.0984 (0.1025) loss: 0.8160 (0.8147) time: 0.1591 data: 0.0811 max mem: 9390 +Train: [60] [3200/6250] eta: 0:06:58 lr: 0.000046 grad: 0.0934 (0.1025) loss: 0.8163 (0.8148) time: 0.1104 data: 0.0240 max mem: 9390 +Train: [60] [3300/6250] eta: 0:06:46 lr: 0.000046 grad: 0.0958 (0.1025) loss: 0.8224 (0.8148) time: 0.1740 data: 0.0897 max mem: 9390 +Train: [60] [3400/6250] eta: 0:06:31 lr: 0.000046 grad: 0.0982 (0.1024) loss: 0.8192 (0.8149) time: 0.1303 data: 0.0494 max mem: 9390 +Train: [60] [3500/6250] eta: 0:06:17 lr: 0.000046 grad: 0.1036 (0.1024) loss: 0.8150 (0.8150) time: 0.1369 data: 0.0615 max mem: 9390 +Train: [60] [3600/6250] eta: 0:06:07 lr: 0.000046 grad: 0.0990 (0.1025) loss: 0.8138 (0.8152) time: 0.3496 data: 0.2666 max mem: 9390 +Train: [60] [3700/6250] eta: 0:05:51 lr: 0.000046 grad: 0.0938 (0.1025) loss: 0.8221 (0.8152) time: 0.1257 data: 0.0435 max mem: 9390 +Train: [60] [3800/6250] eta: 0:05:38 lr: 0.000046 grad: 0.1048 (0.1025) loss: 0.8214 (0.8153) time: 0.1581 data: 0.0762 max mem: 9390 +Train: [60] [3900/6250] eta: 0:05:25 lr: 0.000046 grad: 0.1001 (0.1025) loss: 0.8193 (0.8154) time: 0.0873 data: 0.0042 max mem: 9390 +Train: [60] [4000/6250] eta: 0:05:11 lr: 0.000046 grad: 0.1018 (0.1025) loss: 0.8203 (0.8154) time: 0.1211 data: 0.0444 max mem: 9390 +Train: [60] [4100/6250] eta: 0:04:58 lr: 0.000046 grad: 0.0932 (0.1025) loss: 0.8205 (0.8155) time: 0.1494 data: 0.0714 max mem: 9390 +Train: [60] [4200/6250] eta: 0:04:44 lr: 0.000046 grad: 0.0976 (0.1025) loss: 0.8202 (0.8155) time: 0.1510 data: 0.0698 max mem: 9390 +Train: [60] [4300/6250] eta: 0:04:30 lr: 0.000046 grad: 0.1038 (0.1025) loss: 0.8160 (0.8155) time: 0.1323 data: 0.0587 max mem: 9390 +Train: [60] [4400/6250] eta: 0:04:16 lr: 0.000046 grad: 0.0971 (0.1026) loss: 0.8220 (0.8155) time: 0.1199 data: 0.0275 max mem: 9390 +Train: [60] [4500/6250] eta: 0:04:02 lr: 0.000046 grad: 0.0958 (0.1025) loss: 0.8193 (0.8156) time: 0.1370 data: 0.0606 max mem: 9390 +Train: [60] [4600/6250] eta: 0:03:48 lr: 0.000046 grad: 0.1059 (0.1026) loss: 0.8111 (0.8156) time: 0.1164 data: 0.0355 max mem: 9390 +Train: [60] [4700/6250] eta: 0:03:34 lr: 0.000046 grad: 0.0966 (0.1025) loss: 0.8190 (0.8156) time: 0.1516 data: 0.0683 max mem: 9390 +Train: [60] [4800/6250] eta: 0:03:21 lr: 0.000046 grad: 0.0964 (0.1025) loss: 0.8209 (0.8157) time: 0.1568 data: 0.0805 max mem: 9390 +Train: [60] [4900/6250] eta: 0:03:07 lr: 0.000046 grad: 0.0997 (0.1024) loss: 0.8192 (0.8157) time: 0.1391 data: 0.0618 max mem: 9390 +Train: [60] [5000/6250] eta: 0:02:53 lr: 0.000046 grad: 0.0939 (0.1024) loss: 0.8196 (0.8158) time: 0.1530 data: 0.0691 max mem: 9390 +Train: [60] [5100/6250] eta: 0:02:40 lr: 0.000046 grad: 0.0963 (0.1024) loss: 0.8189 (0.8158) time: 0.1501 data: 0.0708 max mem: 9390 +Train: [60] [5200/6250] eta: 0:02:26 lr: 0.000045 grad: 0.1034 (0.1024) loss: 0.8134 (0.8158) time: 0.1308 data: 0.0437 max mem: 9390 +Train: [60] [5300/6250] eta: 0:02:12 lr: 0.000045 grad: 0.1013 (0.1024) loss: 0.8173 (0.8159) time: 0.1589 data: 0.0838 max mem: 9390 +Train: [60] [5400/6250] eta: 0:01:58 lr: 0.000045 grad: 0.0996 (0.1024) loss: 0.8166 (0.8159) time: 0.1238 data: 0.0424 max mem: 9390 +Train: [60] [5500/6250] eta: 0:01:44 lr: 0.000045 grad: 0.1027 (0.1024) loss: 0.8085 (0.8159) time: 0.1210 data: 0.0404 max mem: 9390 +Train: [60] [5600/6250] eta: 0:01:30 lr: 0.000045 grad: 0.1019 (0.1023) loss: 0.8159 (0.8159) time: 0.1403 data: 0.0609 max mem: 9390 +Train: [60] [5700/6250] eta: 0:01:16 lr: 0.000045 grad: 0.0976 (0.1023) loss: 0.8187 (0.8159) time: 0.1133 data: 0.0316 max mem: 9390 +Train: [60] [5800/6250] eta: 0:01:02 lr: 0.000045 grad: 0.0965 (0.1023) loss: 0.8187 (0.8160) time: 0.1229 data: 0.0405 max mem: 9390 +Train: [60] [5900/6250] eta: 0:00:48 lr: 0.000045 grad: 0.0953 (0.1022) loss: 0.8213 (0.8160) time: 0.1276 data: 0.0471 max mem: 9390 +Train: [60] [6000/6250] eta: 0:00:34 lr: 0.000045 grad: 0.0953 (0.1022) loss: 0.8192 (0.8160) time: 0.1378 data: 0.0596 max mem: 9390 +Train: [60] [6100/6250] eta: 0:00:20 lr: 0.000045 grad: 0.1020 (0.1022) loss: 0.8089 (0.8161) time: 0.1234 data: 0.0429 max mem: 9390 +Train: [60] [6200/6250] eta: 0:00:06 lr: 0.000045 grad: 0.0982 (0.1022) loss: 0.8222 (0.8161) time: 0.1506 data: 0.0723 max mem: 9390 +Train: [60] [6249/6250] eta: 0:00:00 lr: 0.000045 grad: 0.0931 (0.1022) loss: 0.8179 (0.8161) time: 0.1246 data: 0.0442 max mem: 9390 +Train: [60] Total time: 0:14:24 (0.1384 s / it) +Averaged stats: lr: 0.000045 grad: 0.0931 (0.1022) loss: 0.8179 (0.8161) +Eval (hcp-train-subset): [60] [ 0/62] eta: 0:05:43 loss: 0.8439 (0.8439) time: 5.5340 data: 5.5024 max mem: 9390 +Eval (hcp-train-subset): [60] [61/62] eta: 0:00:00 loss: 0.8317 (0.8329) time: 0.1227 data: 0.0962 max mem: 9390 +Eval (hcp-train-subset): [60] Total time: 0:00:13 (0.2167 s / it) +Averaged stats (hcp-train-subset): loss: 0.8317 (0.8329) +Eval (hcp-val): [60] [ 0/62] eta: 0:03:59 loss: 0.8302 (0.8302) time: 3.8603 data: 3.7772 max mem: 9390 +Eval (hcp-val): [60] [61/62] eta: 0:00:00 loss: 0.8317 (0.8333) time: 0.1037 data: 0.0787 max mem: 9390 +Eval (hcp-val): [60] Total time: 0:00:12 (0.1971 s / it) +Averaged stats (hcp-val): loss: 0.8317 (0.8333) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +Train: [61] [ 0/6250] eta: 9:42:57 lr: 0.000045 grad: 0.3138 (0.3138) loss: 0.7576 (0.7576) time: 5.5964 data: 5.4999 max mem: 9390 +Train: [61] [ 100/6250] eta: 0:19:07 lr: 0.000045 grad: 0.1062 (0.1400) loss: 0.8086 (0.8139) time: 0.1281 data: 0.0278 max mem: 9390 +Train: [61] [ 200/6250] eta: 0:16:15 lr: 0.000045 grad: 0.1181 (0.1292) loss: 0.8118 (0.8135) time: 0.1379 data: 0.0506 max mem: 9390 +Train: [61] [ 300/6250] eta: 0:14:55 lr: 0.000045 grad: 0.0959 (0.1209) loss: 0.8184 (0.8150) time: 0.1199 data: 0.0333 max mem: 9390 +Train: [61] [ 400/6250] eta: 0:13:59 lr: 0.000045 grad: 0.0959 (0.1175) loss: 0.8170 (0.8152) time: 0.1167 data: 0.0299 max mem: 9390 +Train: [61] [ 500/6250] eta: 0:13:20 lr: 0.000045 grad: 0.0937 (0.1153) loss: 0.8223 (0.8150) time: 0.1173 data: 0.0377 max mem: 9390 +Train: [61] [ 600/6250] eta: 0:12:43 lr: 0.000045 grad: 0.1020 (0.1132) loss: 0.8100 (0.8149) time: 0.1102 data: 0.0251 max mem: 9390 +Train: [61] [ 700/6250] eta: 0:12:16 lr: 0.000045 grad: 0.0964 (0.1115) loss: 0.8201 (0.8154) time: 0.1185 data: 0.0312 max mem: 9390 +Train: [61] [ 800/6250] eta: 0:11:54 lr: 0.000045 grad: 0.1022 (0.1102) loss: 0.8184 (0.8159) time: 0.1339 data: 0.0518 max mem: 9390 +Train: [61] [ 900/6250] eta: 0:11:38 lr: 0.000045 grad: 0.0946 (0.1090) loss: 0.8172 (0.8162) time: 0.1394 data: 0.0609 max mem: 9390 +Train: [61] [1000/6250] eta: 0:11:26 lr: 0.000045 grad: 0.0981 (0.1081) loss: 0.8159 (0.8162) time: 0.1125 data: 0.0307 max mem: 9390 +Train: [61] [1100/6250] eta: 0:11:21 lr: 0.000045 grad: 0.0988 (0.1075) loss: 0.8202 (0.8164) time: 0.1493 data: 0.0652 max mem: 9390 +Train: [61] [1200/6250] eta: 0:11:11 lr: 0.000045 grad: 0.1009 (0.1070) loss: 0.8187 (0.8165) time: 0.1410 data: 0.0572 max mem: 9390 +Train: [61] [1300/6250] eta: 0:10:57 lr: 0.000045 grad: 0.1014 (0.1064) loss: 0.8193 (0.8166) time: 0.1166 data: 0.0330 max mem: 9390 +Train: [61] [1400/6250] eta: 0:10:44 lr: 0.000045 grad: 0.0981 (0.1061) loss: 0.8165 (0.8166) time: 0.1402 data: 0.0601 max mem: 9390 +Train: [61] [1500/6250] eta: 0:10:30 lr: 0.000045 grad: 0.0985 (0.1060) loss: 0.8185 (0.8165) time: 0.1301 data: 0.0485 max mem: 9390 +Train: [61] [1600/6250] eta: 0:10:16 lr: 0.000045 grad: 0.0960 (0.1059) loss: 0.8166 (0.8162) time: 0.0836 data: 0.0002 max mem: 9390 +Train: [61] [1700/6250] eta: 0:10:00 lr: 0.000045 grad: 0.1057 (0.1058) loss: 0.8104 (0.8160) time: 0.1319 data: 0.0512 max mem: 9390 +Train: [61] [1800/6250] eta: 0:09:48 lr: 0.000045 grad: 0.1029 (0.1057) loss: 0.8143 (0.8160) time: 0.1379 data: 0.0624 max mem: 9390 +Train: [61] [1900/6250] eta: 0:09:35 lr: 0.000045 grad: 0.1039 (0.1057) loss: 0.8096 (0.8158) time: 0.1450 data: 0.0688 max mem: 9390 +Train: [61] [2000/6250] eta: 0:09:21 lr: 0.000045 grad: 0.1013 (0.1059) loss: 0.8181 (0.8156) time: 0.1150 data: 0.0326 max mem: 9390 +Train: [61] [2100/6250] eta: 0:09:07 lr: 0.000044 grad: 0.1001 (0.1059) loss: 0.8146 (0.8153) time: 0.1113 data: 0.0349 max mem: 9390 +Train: [61] [2200/6250] eta: 0:08:54 lr: 0.000044 grad: 0.1029 (0.1059) loss: 0.8094 (0.8151) time: 0.1334 data: 0.0549 max mem: 9390 +Train: [61] [2300/6250] eta: 0:08:43 lr: 0.000044 grad: 0.1001 (0.1059) loss: 0.8181 (0.8150) time: 0.1489 data: 0.0551 max mem: 9390 +Train: [61] [2400/6250] eta: 0:08:28 lr: 0.000044 grad: 0.1030 (0.1058) loss: 0.8107 (0.8148) time: 0.1210 data: 0.0373 max mem: 9390 +Train: [61] [2500/6250] eta: 0:08:15 lr: 0.000044 grad: 0.1075 (0.1059) loss: 0.8085 (0.8146) time: 0.1279 data: 0.0509 max mem: 9390 +Train: [61] [2600/6250] eta: 0:08:03 lr: 0.000044 grad: 0.0985 (0.1058) loss: 0.8163 (0.8145) time: 0.1325 data: 0.0523 max mem: 9390 +Train: [61] [2700/6250] eta: 0:07:51 lr: 0.000044 grad: 0.1075 (0.1058) loss: 0.8139 (0.8144) time: 0.1278 data: 0.0496 max mem: 9390 +Train: [61] [2800/6250] eta: 0:07:38 lr: 0.000044 grad: 0.0922 (0.1058) loss: 0.8165 (0.8144) time: 0.1625 data: 0.0838 max mem: 9390 +Train: [61] [2900/6250] eta: 0:07:25 lr: 0.000044 grad: 0.1042 (0.1057) loss: 0.8086 (0.8144) time: 0.1364 data: 0.0540 max mem: 9390 +Train: [61] [3000/6250] eta: 0:07:12 lr: 0.000044 grad: 0.1002 (0.1057) loss: 0.8147 (0.8143) time: 0.1425 data: 0.0641 max mem: 9390 +Train: [61] [3100/6250] eta: 0:06:59 lr: 0.000044 grad: 0.0995 (0.1056) loss: 0.8141 (0.8143) time: 0.1422 data: 0.0662 max mem: 9390 +Train: [61] [3200/6250] eta: 0:06:45 lr: 0.000044 grad: 0.0999 (0.1057) loss: 0.8122 (0.8143) time: 0.1486 data: 0.0633 max mem: 9390 +Train: [61] [3300/6250] eta: 0:06:32 lr: 0.000044 grad: 0.1093 (0.1058) loss: 0.8099 (0.8143) time: 0.1272 data: 0.0501 max mem: 9390 +Train: [61] [3400/6250] eta: 0:06:20 lr: 0.000044 grad: 0.1004 (0.1058) loss: 0.8097 (0.8142) time: 0.1574 data: 0.0613 max mem: 9390 +Train: [61] [3500/6250] eta: 0:06:07 lr: 0.000044 grad: 0.1079 (0.1060) loss: 0.8149 (0.8142) time: 0.1415 data: 0.0647 max mem: 9390 +Train: [61] [3600/6250] eta: 0:05:54 lr: 0.000044 grad: 0.1081 (0.1061) loss: 0.8096 (0.8143) time: 0.1434 data: 0.0649 max mem: 9390 +Train: [61] [3700/6250] eta: 0:05:43 lr: 0.000044 grad: 0.1010 (0.1061) loss: 0.8190 (0.8143) time: 0.1711 data: 0.0919 max mem: 9390 +Train: [61] [3800/6250] eta: 0:05:30 lr: 0.000044 grad: 0.1014 (0.1060) loss: 0.8208 (0.8143) time: 0.1198 data: 0.0431 max mem: 9390 +Train: [61] [3900/6250] eta: 0:05:17 lr: 0.000044 grad: 0.0974 (0.1059) loss: 0.8164 (0.8144) time: 0.1517 data: 0.0606 max mem: 9390 +Train: [61] [4000/6250] eta: 0:05:04 lr: 0.000044 grad: 0.1043 (0.1059) loss: 0.8113 (0.8144) time: 0.1487 data: 0.0714 max mem: 9390 +Train: [61] [4100/6250] eta: 0:04:51 lr: 0.000044 grad: 0.1064 (0.1058) loss: 0.8101 (0.8144) time: 0.1361 data: 0.0585 max mem: 9390 +Train: [61] [4200/6250] eta: 0:04:38 lr: 0.000044 grad: 0.1031 (0.1058) loss: 0.8134 (0.8143) time: 0.1594 data: 0.0841 max mem: 9390 +Train: [61] [4300/6250] eta: 0:04:24 lr: 0.000044 grad: 0.1002 (0.1057) loss: 0.8137 (0.8143) time: 0.1509 data: 0.0661 max mem: 9390 +Train: [61] [4400/6250] eta: 0:04:11 lr: 0.000044 grad: 0.1044 (0.1058) loss: 0.8119 (0.8143) time: 0.1437 data: 0.0644 max mem: 9390 +Train: [61] [4500/6250] eta: 0:03:57 lr: 0.000044 grad: 0.1032 (0.1058) loss: 0.8129 (0.8143) time: 0.1359 data: 0.0553 max mem: 9390 +Train: [61] [4600/6250] eta: 0:03:43 lr: 0.000044 grad: 0.1033 (0.1058) loss: 0.8149 (0.8143) time: 0.1253 data: 0.0411 max mem: 9390 +Train: [61] [4700/6250] eta: 0:03:30 lr: 0.000044 grad: 0.1015 (0.1057) loss: 0.8204 (0.8143) time: 0.1304 data: 0.0548 max mem: 9390 +Train: [61] [4800/6250] eta: 0:03:17 lr: 0.000044 grad: 0.1031 (0.1058) loss: 0.8142 (0.8143) time: 0.1302 data: 0.0494 max mem: 9390 +Train: [61] [4900/6250] eta: 0:03:03 lr: 0.000044 grad: 0.0985 (0.1057) loss: 0.8162 (0.8143) time: 0.1337 data: 0.0558 max mem: 9390 +Train: [61] [5000/6250] eta: 0:02:50 lr: 0.000044 grad: 0.1030 (0.1057) loss: 0.8114 (0.8143) time: 0.1587 data: 0.0736 max mem: 9390 +Train: [61] [5100/6250] eta: 0:02:37 lr: 0.000044 grad: 0.1017 (0.1057) loss: 0.8194 (0.8144) time: 0.1437 data: 0.0672 max mem: 9390 +Train: [61] [5200/6250] eta: 0:02:23 lr: 0.000044 grad: 0.1008 (0.1058) loss: 0.8151 (0.8143) time: 0.1346 data: 0.0528 max mem: 9390 +Train: [61] [5300/6250] eta: 0:02:10 lr: 0.000043 grad: 0.1031 (0.1058) loss: 0.8116 (0.8143) time: 0.1315 data: 0.0483 max mem: 9390 +Train: [61] [5400/6250] eta: 0:01:56 lr: 0.000043 grad: 0.0954 (0.1059) loss: 0.8220 (0.8143) time: 0.1288 data: 0.0474 max mem: 9390 +Train: [61] [5500/6250] eta: 0:01:42 lr: 0.000043 grad: 0.1042 (0.1059) loss: 0.8182 (0.8143) time: 0.1365 data: 0.0552 max mem: 9390 +Train: [61] [5600/6250] eta: 0:01:28 lr: 0.000043 grad: 0.1017 (0.1059) loss: 0.8176 (0.8143) time: 0.1076 data: 0.0226 max mem: 9390 +Train: [61] [5700/6250] eta: 0:01:14 lr: 0.000043 grad: 0.0950 (0.1059) loss: 0.8122 (0.8143) time: 0.1163 data: 0.0352 max mem: 9390 +Train: [61] [5800/6250] eta: 0:01:01 lr: 0.000043 grad: 0.0984 (0.1059) loss: 0.8117 (0.8143) time: 0.1066 data: 0.0225 max mem: 9390 +Train: [61] [5900/6250] eta: 0:00:47 lr: 0.000043 grad: 0.1047 (0.1059) loss: 0.8159 (0.8143) time: 0.1347 data: 0.0579 max mem: 9390 +Train: [61] [6000/6250] eta: 0:00:33 lr: 0.000043 grad: 0.1002 (0.1058) loss: 0.8160 (0.8143) time: 0.1623 data: 0.0770 max mem: 9390 +Train: [61] [6100/6250] eta: 0:00:20 lr: 0.000043 grad: 0.0974 (0.1058) loss: 0.8233 (0.8144) time: 0.1484 data: 0.0517 max mem: 9390 +Train: [61] [6200/6250] eta: 0:00:06 lr: 0.000043 grad: 0.0934 (0.1057) loss: 0.8240 (0.8145) time: 0.1203 data: 0.0324 max mem: 9390 +Train: [61] [6249/6250] eta: 0:00:00 lr: 0.000043 grad: 0.0980 (0.1056) loss: 0.8209 (0.8146) time: 0.1424 data: 0.0640 max mem: 9390 +Train: [61] Total time: 0:14:12 (0.1364 s / it) +Averaged stats: lr: 0.000043 grad: 0.0980 (0.1056) loss: 0.8209 (0.8146) +Eval (hcp-train-subset): [61] [ 0/62] eta: 0:04:15 loss: 0.8449 (0.8449) time: 4.1214 data: 4.0904 max mem: 9390 +Eval (hcp-train-subset): [61] [61/62] eta: 0:00:00 loss: 0.8310 (0.8332) time: 0.1139 data: 0.0891 max mem: 9390 +Eval (hcp-train-subset): [61] Total time: 0:00:12 (0.1949 s / it) +Averaged stats (hcp-train-subset): loss: 0.8310 (0.8332) +Eval (hcp-val): [61] [ 0/62] eta: 0:04:25 loss: 0.8341 (0.8341) time: 4.2798 data: 4.2005 max mem: 9390 +Eval (hcp-val): [61] [61/62] eta: 0:00:00 loss: 0.8341 (0.8346) time: 0.1241 data: 0.0991 max mem: 9390 +Eval (hcp-val): [61] Total time: 0:00:13 (0.2125 s / it) +Averaged stats (hcp-val): loss: 0.8341 (0.8346) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +Train: [62] [ 0/6250] eta: 9:15:25 lr: 0.000043 grad: 0.0856 (0.0856) loss: 0.8384 (0.8384) time: 5.3321 data: 5.2385 max mem: 9390 +Train: [62] [ 100/6250] eta: 0:19:14 lr: 0.000043 grad: 0.0980 (0.1095) loss: 0.8265 (0.8355) time: 0.1465 data: 0.0550 max mem: 9390 +Train: [62] [ 200/6250] eta: 0:16:24 lr: 0.000043 grad: 0.1030 (0.1112) loss: 0.8192 (0.8289) time: 0.1395 data: 0.0437 max mem: 9390 +Train: [62] [ 300/6250] eta: 0:14:56 lr: 0.000043 grad: 0.0947 (0.1120) loss: 0.8275 (0.8255) time: 0.1207 data: 0.0308 max mem: 9390 +Train: [62] [ 400/6250] eta: 0:14:06 lr: 0.000043 grad: 0.1078 (0.1113) loss: 0.8098 (0.8233) time: 0.1107 data: 0.0203 max mem: 9390 +Train: [62] [ 500/6250] eta: 0:13:26 lr: 0.000043 grad: 0.1001 (0.1099) loss: 0.8143 (0.8225) time: 0.1224 data: 0.0395 max mem: 9390 +Train: [62] [ 600/6250] eta: 0:12:58 lr: 0.000043 grad: 0.0964 (0.1088) loss: 0.8191 (0.8218) time: 0.1524 data: 0.0717 max mem: 9390 +Train: [62] [ 700/6250] eta: 0:12:51 lr: 0.000043 grad: 0.0922 (0.1082) loss: 0.8215 (0.8210) time: 0.1688 data: 0.0876 max mem: 9390 +Train: [62] [ 800/6250] eta: 0:12:52 lr: 0.000043 grad: 0.1014 (0.1078) loss: 0.8231 (0.8208) time: 0.1813 data: 0.0997 max mem: 9390 +Train: [62] [ 900/6250] eta: 0:12:49 lr: 0.000043 grad: 0.0980 (0.1067) loss: 0.8252 (0.8209) time: 0.1712 data: 0.0849 max mem: 9390 +Train: [62] [1000/6250] eta: 0:12:38 lr: 0.000043 grad: 0.0942 (0.1058) loss: 0.8199 (0.8211) time: 0.1475 data: 0.0674 max mem: 9390 +Train: [62] [1100/6250] eta: 0:12:28 lr: 0.000043 grad: 0.0964 (0.1048) loss: 0.8242 (0.8212) time: 0.1609 data: 0.0814 max mem: 9390 +Train: [62] [1200/6250] eta: 0:12:08 lr: 0.000043 grad: 0.0900 (0.1040) loss: 0.8220 (0.8212) time: 0.1308 data: 0.0519 max mem: 9390 +Train: [62] [1300/6250] eta: 0:11:47 lr: 0.000043 grad: 0.0932 (0.1033) loss: 0.8260 (0.8212) time: 0.1415 data: 0.0580 max mem: 9390 +Train: [62] [1400/6250] eta: 0:11:33 lr: 0.000043 grad: 0.0970 (0.1029) loss: 0.8128 (0.8209) time: 0.1020 data: 0.0015 max mem: 9390 +Train: [62] [1500/6250] eta: 0:11:16 lr: 0.000043 grad: 0.0980 (0.1025) loss: 0.8106 (0.8208) time: 0.1461 data: 0.0627 max mem: 9390 +Train: [62] [1600/6250] eta: 0:10:58 lr: 0.000043 grad: 0.0951 (0.1023) loss: 0.8205 (0.8207) time: 0.1027 data: 0.0236 max mem: 9390 +Train: [62] [1700/6250] eta: 0:10:42 lr: 0.000043 grad: 0.0948 (0.1019) loss: 0.8212 (0.8206) time: 0.1537 data: 0.0599 max mem: 9390 +Train: [62] [1800/6250] eta: 0:10:32 lr: 0.000043 grad: 0.0947 (0.1016) loss: 0.8169 (0.8206) time: 0.1215 data: 0.0327 max mem: 9390 +Train: [62] [1900/6250] eta: 0:10:19 lr: 0.000043 grad: 0.0983 (0.1015) loss: 0.8211 (0.8205) time: 0.1239 data: 0.0320 max mem: 9390 +Train: [62] [2000/6250] eta: 0:10:12 lr: 0.000043 grad: 0.0974 (0.1013) loss: 0.8191 (0.8205) time: 0.0988 data: 0.0003 max mem: 9390 +Train: [62] [2100/6250] eta: 0:09:53 lr: 0.000043 grad: 0.1023 (0.1014) loss: 0.8115 (0.8203) time: 0.1154 data: 0.0330 max mem: 9390 +Train: [62] [2200/6250] eta: 0:09:37 lr: 0.000042 grad: 0.0971 (0.1013) loss: 0.8166 (0.8201) time: 0.1443 data: 0.0622 max mem: 9390 +Train: [62] [2300/6250] eta: 0:09:25 lr: 0.000042 grad: 0.0980 (0.1013) loss: 0.8204 (0.8199) time: 0.1902 data: 0.0652 max mem: 9390 +Train: [62] [2400/6250] eta: 0:09:11 lr: 0.000042 grad: 0.0989 (0.1013) loss: 0.8190 (0.8198) time: 0.1329 data: 0.0581 max mem: 9390 +Train: [62] [2500/6250] eta: 0:08:56 lr: 0.000042 grad: 0.0995 (0.1012) loss: 0.8099 (0.8198) time: 0.1389 data: 0.0622 max mem: 9390 +Train: [62] [2600/6250] eta: 0:08:40 lr: 0.000042 grad: 0.0943 (0.1012) loss: 0.8164 (0.8197) time: 0.1375 data: 0.0607 max mem: 9390 +Train: [62] [2700/6250] eta: 0:08:25 lr: 0.000042 grad: 0.0958 (0.1012) loss: 0.8175 (0.8196) time: 0.1363 data: 0.0557 max mem: 9390 +Train: [62] [2800/6250] eta: 0:08:09 lr: 0.000042 grad: 0.0965 (0.1012) loss: 0.8252 (0.8196) time: 0.1322 data: 0.0547 max mem: 9390 +Train: [62] [2900/6250] eta: 0:07:56 lr: 0.000042 grad: 0.1001 (0.1012) loss: 0.8136 (0.8195) time: 0.0963 data: 0.0002 max mem: 9390 +Train: [62] [3000/6250] eta: 0:07:41 lr: 0.000042 grad: 0.0978 (0.1012) loss: 0.8152 (0.8194) time: 0.1552 data: 0.0681 max mem: 9390 +Train: [62] [3100/6250] eta: 0:07:28 lr: 0.000042 grad: 0.0961 (0.1011) loss: 0.8212 (0.8194) time: 0.1307 data: 0.0506 max mem: 9390 +Train: [62] [3200/6250] eta: 0:07:14 lr: 0.000042 grad: 0.0977 (0.1010) loss: 0.8190 (0.8195) time: 0.1283 data: 0.0450 max mem: 9390 +Train: [62] [3300/6250] eta: 0:07:01 lr: 0.000042 grad: 0.0974 (0.1010) loss: 0.8217 (0.8195) time: 0.1775 data: 0.0844 max mem: 9390 +Train: [62] [3400/6250] eta: 0:06:46 lr: 0.000042 grad: 0.0976 (0.1009) loss: 0.8183 (0.8195) time: 0.1499 data: 0.0708 max mem: 9390 +Train: [62] [3500/6250] eta: 0:06:31 lr: 0.000042 grad: 0.1045 (0.1008) loss: 0.8166 (0.8196) time: 0.1441 data: 0.0644 max mem: 9390 +Train: [62] [3600/6250] eta: 0:06:19 lr: 0.000042 grad: 0.0986 (0.1007) loss: 0.8233 (0.8196) time: 0.2718 data: 0.1853 max mem: 9390 +Train: [62] [3700/6250] eta: 0:06:04 lr: 0.000042 grad: 0.0981 (0.1006) loss: 0.8213 (0.8196) time: 0.1295 data: 0.0491 max mem: 9390 +Train: [62] [3800/6250] eta: 0:05:50 lr: 0.000042 grad: 0.0994 (0.1005) loss: 0.8214 (0.8197) time: 0.1390 data: 0.0596 max mem: 9390 +Train: [62] [3900/6250] eta: 0:05:37 lr: 0.000042 grad: 0.0989 (0.1006) loss: 0.8169 (0.8197) time: 0.1714 data: 0.0945 max mem: 9390 +Train: [62] [4000/6250] eta: 0:05:22 lr: 0.000042 grad: 0.1014 (0.1006) loss: 0.8236 (0.8197) time: 0.1451 data: 0.0684 max mem: 9390 +Train: [62] [4100/6250] eta: 0:05:08 lr: 0.000042 grad: 0.0960 (0.1006) loss: 0.8208 (0.8196) time: 0.1346 data: 0.0508 max mem: 9390 +Train: [62] [4200/6250] eta: 0:04:54 lr: 0.000042 grad: 0.0918 (0.1005) loss: 0.8201 (0.8197) time: 0.1274 data: 0.0479 max mem: 9390 +Train: [62] [4300/6250] eta: 0:04:39 lr: 0.000042 grad: 0.0945 (0.1004) loss: 0.8253 (0.8197) time: 0.1531 data: 0.0750 max mem: 9390 +Train: [62] [4400/6250] eta: 0:04:25 lr: 0.000042 grad: 0.0973 (0.1004) loss: 0.8204 (0.8197) time: 0.1211 data: 0.0337 max mem: 9390 +Train: [62] [4500/6250] eta: 0:04:10 lr: 0.000042 grad: 0.1052 (0.1004) loss: 0.8192 (0.8196) time: 0.1365 data: 0.0569 max mem: 9390 +Train: [62] [4600/6250] eta: 0:03:56 lr: 0.000042 grad: 0.1011 (0.1005) loss: 0.8159 (0.8196) time: 0.1366 data: 0.0606 max mem: 9390 +Train: [62] [4700/6250] eta: 0:03:42 lr: 0.000042 grad: 0.1066 (0.1006) loss: 0.8160 (0.8195) time: 0.1568 data: 0.0620 max mem: 9390 +Train: [62] [4800/6250] eta: 0:03:28 lr: 0.000042 grad: 0.0986 (0.1007) loss: 0.8186 (0.8194) time: 0.1409 data: 0.0594 max mem: 9390 +Train: [62] [4900/6250] eta: 0:03:14 lr: 0.000042 grad: 0.0978 (0.1008) loss: 0.8225 (0.8194) time: 0.1274 data: 0.0475 max mem: 9390 +Train: [62] [5000/6250] eta: 0:02:59 lr: 0.000042 grad: 0.0984 (0.1008) loss: 0.8157 (0.8194) time: 0.1463 data: 0.0535 max mem: 9390 +Train: [62] [5100/6250] eta: 0:02:45 lr: 0.000042 grad: 0.1023 (0.1008) loss: 0.8158 (0.8193) time: 0.1057 data: 0.0227 max mem: 9390 +Train: [62] [5200/6250] eta: 0:02:30 lr: 0.000042 grad: 0.1008 (0.1009) loss: 0.8154 (0.8193) time: 0.1363 data: 0.0505 max mem: 9390 +Train: [62] [5300/6250] eta: 0:02:16 lr: 0.000042 grad: 0.1014 (0.1009) loss: 0.8090 (0.8192) time: 0.1253 data: 0.0433 max mem: 9390 +Train: [62] [5400/6250] eta: 0:02:01 lr: 0.000041 grad: 0.0976 (0.1009) loss: 0.8215 (0.8192) time: 0.1303 data: 0.0475 max mem: 9390 +Train: [62] [5500/6250] eta: 0:01:46 lr: 0.000041 grad: 0.0962 (0.1009) loss: 0.8230 (0.8192) time: 0.1066 data: 0.0179 max mem: 9390 +Train: [62] [5600/6250] eta: 0:01:32 lr: 0.000041 grad: 0.0968 (0.1009) loss: 0.8237 (0.8191) time: 0.1177 data: 0.0337 max mem: 9390 +Train: [62] [5700/6250] eta: 0:01:17 lr: 0.000041 grad: 0.0954 (0.1008) loss: 0.8173 (0.8191) time: 0.1277 data: 0.0487 max mem: 9390 +Train: [62] [5800/6250] eta: 0:01:03 lr: 0.000041 grad: 0.0952 (0.1009) loss: 0.8164 (0.8191) time: 0.1635 data: 0.0785 max mem: 9390 +Train: [62] [5900/6250] eta: 0:00:49 lr: 0.000041 grad: 0.1010 (0.1009) loss: 0.8166 (0.8191) time: 0.1545 data: 0.0725 max mem: 9390 +Train: [62] [6000/6250] eta: 0:00:35 lr: 0.000041 grad: 0.0983 (0.1009) loss: 0.8234 (0.8191) time: 0.1447 data: 0.0617 max mem: 9390 +Train: [62] [6100/6250] eta: 0:00:21 lr: 0.000041 grad: 0.0978 (0.1009) loss: 0.8192 (0.8191) time: 0.1319 data: 0.0493 max mem: 9390 +Train: [62] [6200/6250] eta: 0:00:07 lr: 0.000041 grad: 0.0975 (0.1009) loss: 0.8198 (0.8191) time: 0.1069 data: 0.0266 max mem: 9390 +Train: [62] [6249/6250] eta: 0:00:00 lr: 0.000041 grad: 0.1026 (0.1009) loss: 0.8143 (0.8191) time: 0.1167 data: 0.0409 max mem: 9390 +Train: [62] Total time: 0:14:47 (0.1420 s / it) +Averaged stats: lr: 0.000041 grad: 0.1026 (0.1009) loss: 0.8143 (0.8191) +Eval (hcp-train-subset): [62] [ 0/62] eta: 0:04:48 loss: 0.8467 (0.8467) time: 4.6532 data: 4.6226 max mem: 9390 +Eval (hcp-train-subset): [62] [61/62] eta: 0:00:00 loss: 0.8313 (0.8332) time: 0.1262 data: 0.1012 max mem: 9390 +Eval (hcp-train-subset): [62] Total time: 0:00:13 (0.2135 s / it) +Averaged stats (hcp-train-subset): loss: 0.8313 (0.8332) +Eval (hcp-val): [62] [ 0/62] eta: 0:03:43 loss: 0.8286 (0.8286) time: 3.6013 data: 3.5191 max mem: 9390 +Eval (hcp-val): [62] [61/62] eta: 0:00:00 loss: 0.8319 (0.8331) time: 0.1242 data: 0.0976 max mem: 9390 +Eval (hcp-val): [62] Total time: 0:00:12 (0.2007 s / it) +Averaged stats (hcp-val): loss: 0.8319 (0.8331) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +Train: [63] [ 0/6250] eta: 7:54:55 lr: 0.000041 grad: 0.1575 (0.1575) loss: 0.8507 (0.8507) time: 4.5592 data: 4.2739 max mem: 9390 +Train: [63] [ 100/6250] eta: 0:18:59 lr: 0.000041 grad: 0.1088 (0.1412) loss: 0.8157 (0.8275) time: 0.1255 data: 0.0313 max mem: 9390 +Train: [63] [ 200/6250] eta: 0:16:28 lr: 0.000041 grad: 0.0989 (0.1274) loss: 0.8146 (0.8213) time: 0.1343 data: 0.0426 max mem: 9390 +Train: [63] [ 300/6250] eta: 0:15:08 lr: 0.000041 grad: 0.1007 (0.1204) loss: 0.8166 (0.8202) time: 0.1475 data: 0.0673 max mem: 9390 +Train: [63] [ 400/6250] eta: 0:14:12 lr: 0.000041 grad: 0.1046 (0.1172) loss: 0.8170 (0.8191) time: 0.1320 data: 0.0510 max mem: 9390 +Train: [63] [ 500/6250] eta: 0:13:29 lr: 0.000041 grad: 0.0921 (0.1145) loss: 0.8225 (0.8190) time: 0.1375 data: 0.0559 max mem: 9390 +Train: [63] [ 600/6250] eta: 0:12:56 lr: 0.000041 grad: 0.0998 (0.1122) loss: 0.8288 (0.8193) time: 0.1373 data: 0.0554 max mem: 9390 +Train: [63] [ 700/6250] eta: 0:12:27 lr: 0.000041 grad: 0.0977 (0.1107) loss: 0.8220 (0.8193) time: 0.1276 data: 0.0452 max mem: 9390 +Train: [63] [ 800/6250] eta: 0:12:10 lr: 0.000041 grad: 0.0956 (0.1090) loss: 0.8257 (0.8199) time: 0.1329 data: 0.0473 max mem: 9390 +Train: [63] [ 900/6250] eta: 0:12:05 lr: 0.000041 grad: 0.0943 (0.1076) loss: 0.8232 (0.8202) time: 0.1722 data: 0.0926 max mem: 9390 +Train: [63] [1000/6250] eta: 0:11:57 lr: 0.000041 grad: 0.0978 (0.1071) loss: 0.8161 (0.8200) time: 0.1417 data: 0.0637 max mem: 9390 +Train: [63] [1100/6250] eta: 0:11:44 lr: 0.000041 grad: 0.1008 (0.1066) loss: 0.8169 (0.8199) time: 0.1454 data: 0.0690 max mem: 9390 +Train: [63] [1200/6250] eta: 0:11:30 lr: 0.000041 grad: 0.0941 (0.1059) loss: 0.8216 (0.8199) time: 0.1184 data: 0.0314 max mem: 9390 +Train: [63] [1300/6250] eta: 0:11:18 lr: 0.000041 grad: 0.1047 (0.1057) loss: 0.8161 (0.8198) time: 0.1417 data: 0.0605 max mem: 9390 +Train: [63] [1400/6250] eta: 0:11:04 lr: 0.000041 grad: 0.0997 (0.1054) loss: 0.8149 (0.8197) time: 0.1484 data: 0.0680 max mem: 9390 +Train: [63] [1500/6250] eta: 0:10:49 lr: 0.000041 grad: 0.0991 (0.1052) loss: 0.8184 (0.8195) time: 0.1299 data: 0.0506 max mem: 9390 +Train: [63] [1600/6250] eta: 0:10:34 lr: 0.000041 grad: 0.0978 (0.1051) loss: 0.8171 (0.8193) time: 0.1419 data: 0.0618 max mem: 9390 +Train: [63] [1700/6250] eta: 0:10:19 lr: 0.000041 grad: 0.1012 (0.1052) loss: 0.8154 (0.8190) time: 0.1408 data: 0.0545 max mem: 9390 +Train: [63] [1800/6250] eta: 0:10:04 lr: 0.000041 grad: 0.0959 (0.1051) loss: 0.8188 (0.8189) time: 0.1288 data: 0.0472 max mem: 9390 +Train: [63] [1900/6250] eta: 0:09:53 lr: 0.000041 grad: 0.0982 (0.1052) loss: 0.8237 (0.8188) time: 0.1623 data: 0.0636 max mem: 9390 +Train: [63] [2000/6250] eta: 0:09:38 lr: 0.000041 grad: 0.1004 (0.1052) loss: 0.8115 (0.8187) time: 0.1303 data: 0.0536 max mem: 9390 +Train: [63] [2100/6250] eta: 0:09:23 lr: 0.000041 grad: 0.1004 (0.1052) loss: 0.8151 (0.8186) time: 0.1231 data: 0.0415 max mem: 9390 +Train: [63] [2200/6250] eta: 0:09:08 lr: 0.000041 grad: 0.1018 (0.1052) loss: 0.8133 (0.8184) time: 0.1307 data: 0.0511 max mem: 9390 +Train: [63] [2300/6250] eta: 0:08:54 lr: 0.000041 grad: 0.1067 (0.1053) loss: 0.8161 (0.8184) time: 0.1494 data: 0.0653 max mem: 9390 +Train: [63] [2400/6250] eta: 0:08:40 lr: 0.000040 grad: 0.0980 (0.1052) loss: 0.8191 (0.8183) time: 0.1324 data: 0.0498 max mem: 9390 +Train: [63] [2500/6250] eta: 0:08:27 lr: 0.000040 grad: 0.1059 (0.1053) loss: 0.8120 (0.8183) time: 0.1408 data: 0.0678 max mem: 9390 +Train: [63] [2600/6250] eta: 0:08:15 lr: 0.000040 grad: 0.1084 (0.1054) loss: 0.8192 (0.8182) time: 0.1589 data: 0.0753 max mem: 9390 +Train: [63] [2700/6250] eta: 0:08:02 lr: 0.000040 grad: 0.0996 (0.1053) loss: 0.8225 (0.8182) time: 0.1407 data: 0.0625 max mem: 9390 +Train: [63] [2800/6250] eta: 0:07:49 lr: 0.000040 grad: 0.1027 (0.1054) loss: 0.8228 (0.8181) time: 0.1486 data: 0.0701 max mem: 9390 +Train: [63] [2900/6250] eta: 0:07:35 lr: 0.000040 grad: 0.1051 (0.1054) loss: 0.8162 (0.8181) time: 0.1392 data: 0.0447 max mem: 9390 +Train: [63] [3000/6250] eta: 0:07:21 lr: 0.000040 grad: 0.1075 (0.1054) loss: 0.8146 (0.8180) time: 0.1356 data: 0.0549 max mem: 9390 +Train: [63] [3100/6250] eta: 0:07:07 lr: 0.000040 grad: 0.1003 (0.1053) loss: 0.8222 (0.8181) time: 0.1277 data: 0.0448 max mem: 9390 +Train: [63] [3200/6250] eta: 0:06:54 lr: 0.000040 grad: 0.1008 (0.1052) loss: 0.8204 (0.8181) time: 0.1371 data: 0.0573 max mem: 9390 +Train: [63] [3300/6250] eta: 0:06:43 lr: 0.000040 grad: 0.1036 (0.1052) loss: 0.8177 (0.8181) time: 0.2236 data: 0.1304 max mem: 9390 +Train: [63] [3400/6250] eta: 0:06:29 lr: 0.000040 grad: 0.0988 (0.1051) loss: 0.8206 (0.8181) time: 0.1396 data: 0.0571 max mem: 9390 +Train: [63] [3500/6250] eta: 0:06:15 lr: 0.000040 grad: 0.0941 (0.1050) loss: 0.8240 (0.8182) time: 0.1244 data: 0.0425 max mem: 9390 +Train: [63] [3600/6250] eta: 0:06:02 lr: 0.000040 grad: 0.1007 (0.1049) loss: 0.8213 (0.8183) time: 0.1497 data: 0.0714 max mem: 9390 +Train: [63] [3700/6250] eta: 0:05:48 lr: 0.000040 grad: 0.1041 (0.1048) loss: 0.8125 (0.8183) time: 0.1303 data: 0.0489 max mem: 9390 +Train: [63] [3800/6250] eta: 0:05:35 lr: 0.000040 grad: 0.1015 (0.1048) loss: 0.8210 (0.8184) time: 0.1413 data: 0.0593 max mem: 9390 +Train: [63] [3900/6250] eta: 0:05:22 lr: 0.000040 grad: 0.1019 (0.1048) loss: 0.8223 (0.8184) time: 0.1726 data: 0.0864 max mem: 9390 +Train: [63] [4000/6250] eta: 0:05:09 lr: 0.000040 grad: 0.1023 (0.1048) loss: 0.8176 (0.8185) time: 0.1453 data: 0.0653 max mem: 9390 +Train: [63] [4100/6250] eta: 0:04:55 lr: 0.000040 grad: 0.0994 (0.1047) loss: 0.8182 (0.8186) time: 0.1384 data: 0.0570 max mem: 9390 +Train: [63] [4200/6250] eta: 0:04:43 lr: 0.000040 grad: 0.1016 (0.1047) loss: 0.8097 (0.8186) time: 0.1553 data: 0.0723 max mem: 9390 +Train: [63] [4300/6250] eta: 0:04:29 lr: 0.000040 grad: 0.0986 (0.1047) loss: 0.8182 (0.8186) time: 0.1420 data: 0.0447 max mem: 9390 +Train: [63] [4400/6250] eta: 0:04:16 lr: 0.000040 grad: 0.1023 (0.1046) loss: 0.8206 (0.8187) time: 0.1260 data: 0.0493 max mem: 9390 +Train: [63] [4500/6250] eta: 0:04:02 lr: 0.000040 grad: 0.0976 (0.1046) loss: 0.8199 (0.8188) time: 0.1287 data: 0.0411 max mem: 9390 +Train: [63] [4600/6250] eta: 0:03:48 lr: 0.000040 grad: 0.1034 (0.1046) loss: 0.8227 (0.8188) time: 0.1409 data: 0.0633 max mem: 9390 +Train: [63] [4700/6250] eta: 0:03:34 lr: 0.000040 grad: 0.1035 (0.1045) loss: 0.8205 (0.8189) time: 0.1293 data: 0.0509 max mem: 9390 +Train: [63] [4800/6250] eta: 0:03:21 lr: 0.000040 grad: 0.1034 (0.1045) loss: 0.8231 (0.8189) time: 0.1407 data: 0.0605 max mem: 9390 +Train: [63] [4900/6250] eta: 0:03:07 lr: 0.000040 grad: 0.1065 (0.1045) loss: 0.8193 (0.8189) time: 0.1531 data: 0.0672 max mem: 9390 +Train: [63] [5000/6250] eta: 0:02:53 lr: 0.000040 grad: 0.1001 (0.1045) loss: 0.8214 (0.8190) time: 0.1334 data: 0.0512 max mem: 9390 +Train: [63] [5100/6250] eta: 0:02:39 lr: 0.000040 grad: 0.1003 (0.1045) loss: 0.8189 (0.8190) time: 0.1297 data: 0.0460 max mem: 9390 +Train: [63] [5200/6250] eta: 0:02:25 lr: 0.000040 grad: 0.1024 (0.1045) loss: 0.8222 (0.8191) time: 0.1381 data: 0.0585 max mem: 9390 +Train: [63] [5300/6250] eta: 0:02:11 lr: 0.000040 grad: 0.1035 (0.1045) loss: 0.8169 (0.8191) time: 0.1289 data: 0.0467 max mem: 9390 +Train: [63] [5400/6250] eta: 0:01:57 lr: 0.000040 grad: 0.1017 (0.1045) loss: 0.8253 (0.8192) time: 0.1079 data: 0.0208 max mem: 9390 +Train: [63] [5500/6250] eta: 0:01:43 lr: 0.000040 grad: 0.1068 (0.1046) loss: 0.8198 (0.8192) time: 0.1263 data: 0.0462 max mem: 9390 +Train: [63] [5600/6250] eta: 0:01:29 lr: 0.000039 grad: 0.1055 (0.1046) loss: 0.8192 (0.8192) time: 0.1124 data: 0.0319 max mem: 9390 +Train: [63] [5700/6250] eta: 0:01:15 lr: 0.000039 grad: 0.1126 (0.1047) loss: 0.8183 (0.8192) time: 0.1090 data: 0.0309 max mem: 9390 +Train: [63] [5800/6250] eta: 0:01:01 lr: 0.000039 grad: 0.0966 (0.1047) loss: 0.8209 (0.8192) time: 0.1317 data: 0.0518 max mem: 9390 +Train: [63] [5900/6250] eta: 0:00:47 lr: 0.000039 grad: 0.1035 (0.1048) loss: 0.8189 (0.8192) time: 0.1328 data: 0.0487 max mem: 9390 +Train: [63] [6000/6250] eta: 0:00:34 lr: 0.000039 grad: 0.1010 (0.1048) loss: 0.8198 (0.8192) time: 0.1260 data: 0.0397 max mem: 9390 +Train: [63] [6100/6250] eta: 0:00:20 lr: 0.000039 grad: 0.1054 (0.1048) loss: 0.8147 (0.8192) time: 0.1346 data: 0.0530 max mem: 9390 +Train: [63] [6200/6250] eta: 0:00:06 lr: 0.000039 grad: 0.1053 (0.1048) loss: 0.8222 (0.8192) time: 0.1491 data: 0.0704 max mem: 9390 +Train: [63] [6249/6250] eta: 0:00:00 lr: 0.000039 grad: 0.1001 (0.1048) loss: 0.8196 (0.8191) time: 0.1652 data: 0.0837 max mem: 9390 +Train: [63] Total time: 0:14:20 (0.1376 s / it) +Averaged stats: lr: 0.000039 grad: 0.1001 (0.1048) loss: 0.8196 (0.8191) +Eval (hcp-train-subset): [63] [ 0/62] eta: 0:03:56 loss: 0.8446 (0.8446) time: 3.8154 data: 3.7216 max mem: 9390 +Eval (hcp-train-subset): [63] [61/62] eta: 0:00:00 loss: 0.8300 (0.8319) time: 0.1275 data: 0.1027 max mem: 9390 +Eval (hcp-train-subset): [63] Total time: 0:00:13 (0.2178 s / it) +Averaged stats (hcp-train-subset): loss: 0.8300 (0.8319) +Eval (hcp-val): [63] [ 0/62] eta: 0:05:30 loss: 0.8311 (0.8311) time: 5.3365 data: 5.3059 max mem: 9390 +Eval (hcp-val): [63] [61/62] eta: 0:00:00 loss: 0.8326 (0.8336) time: 0.1073 data: 0.0826 max mem: 9390 +Eval (hcp-val): [63] Total time: 0:00:12 (0.1990 s / it) +Averaged stats (hcp-val): loss: 0.8326 (0.8336) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +Train: [64] [ 0/6250] eta: 7:32:28 lr: 0.000039 grad: 0.2668 (0.2668) loss: 0.8117 (0.8117) time: 4.3438 data: 4.1076 max mem: 9390 +Train: [64] [ 100/6250] eta: 0:19:25 lr: 0.000039 grad: 0.1224 (0.1410) loss: 0.8225 (0.8224) time: 0.1438 data: 0.0429 max mem: 9390 +Train: [64] [ 200/6250] eta: 0:16:30 lr: 0.000039 grad: 0.1006 (0.1353) loss: 0.8177 (0.8175) time: 0.1425 data: 0.0565 max mem: 9390 +Train: [64] [ 300/6250] eta: 0:15:16 lr: 0.000039 grad: 0.1222 (0.1327) loss: 0.8058 (0.8146) time: 0.1279 data: 0.0444 max mem: 9390 +Train: [64] [ 400/6250] eta: 0:14:11 lr: 0.000039 grad: 0.1087 (0.1283) loss: 0.8126 (0.8134) time: 0.1184 data: 0.0378 max mem: 9390 +Train: [64] [ 500/6250] eta: 0:13:30 lr: 0.000039 grad: 0.0939 (0.1245) loss: 0.8239 (0.8138) time: 0.1183 data: 0.0343 max mem: 9390 +Train: [64] [ 600/6250] eta: 0:13:03 lr: 0.000039 grad: 0.1012 (0.1216) loss: 0.8151 (0.8144) time: 0.1388 data: 0.0432 max mem: 9390 +Train: [64] [ 700/6250] eta: 0:12:33 lr: 0.000039 grad: 0.0936 (0.1192) loss: 0.8219 (0.8147) time: 0.1225 data: 0.0426 max mem: 9390 +Train: [64] [ 800/6250] eta: 0:12:16 lr: 0.000039 grad: 0.1033 (0.1174) loss: 0.8148 (0.8148) time: 0.1430 data: 0.0524 max mem: 9390 +Train: [64] [ 900/6250] eta: 0:12:11 lr: 0.000039 grad: 0.0976 (0.1157) loss: 0.8222 (0.8150) time: 0.1477 data: 0.0591 max mem: 9390 +Train: [64] [1000/6250] eta: 0:11:59 lr: 0.000039 grad: 0.1027 (0.1145) loss: 0.8141 (0.8151) time: 0.1360 data: 0.0518 max mem: 9390 +Train: [64] [1100/6250] eta: 0:11:44 lr: 0.000039 grad: 0.1071 (0.1138) loss: 0.8085 (0.8150) time: 0.1452 data: 0.0561 max mem: 9390 +Train: [64] [1200/6250] eta: 0:11:31 lr: 0.000039 grad: 0.1062 (0.1131) loss: 0.8096 (0.8149) time: 0.1449 data: 0.0658 max mem: 9390 +Train: [64] [1300/6250] eta: 0:11:15 lr: 0.000039 grad: 0.1081 (0.1127) loss: 0.8200 (0.8149) time: 0.1211 data: 0.0386 max mem: 9390 +Train: [64] [1400/6250] eta: 0:11:08 lr: 0.000039 grad: 0.1073 (0.1122) loss: 0.8106 (0.8147) time: 0.2222 data: 0.1279 max mem: 9390 +Train: [64] [1500/6250] eta: 0:10:49 lr: 0.000039 grad: 0.1039 (0.1119) loss: 0.8135 (0.8147) time: 0.1295 data: 0.0493 max mem: 9390 +Train: [64] [1600/6250] eta: 0:10:33 lr: 0.000039 grad: 0.1040 (0.1117) loss: 0.8079 (0.8146) time: 0.1300 data: 0.0487 max mem: 9390 +Train: [64] [1700/6250] eta: 0:10:22 lr: 0.000039 grad: 0.1024 (0.1115) loss: 0.8106 (0.8145) time: 0.1860 data: 0.1031 max mem: 9390 +Train: [64] [1800/6250] eta: 0:10:09 lr: 0.000039 grad: 0.1097 (0.1113) loss: 0.8044 (0.8144) time: 0.1758 data: 0.0507 max mem: 9390 +Train: [64] [1900/6250] eta: 0:09:57 lr: 0.000039 grad: 0.1077 (0.1113) loss: 0.8112 (0.8143) time: 0.1289 data: 0.0481 max mem: 9390 +Train: [64] [2000/6250] eta: 0:09:42 lr: 0.000039 grad: 0.1088 (0.1112) loss: 0.8142 (0.8142) time: 0.1355 data: 0.0545 max mem: 9390 +Train: [64] [2100/6250] eta: 0:09:32 lr: 0.000039 grad: 0.1118 (0.1113) loss: 0.8079 (0.8141) time: 0.1545 data: 0.0750 max mem: 9390 +Train: [64] [2200/6250] eta: 0:09:18 lr: 0.000039 grad: 0.1081 (0.1111) loss: 0.8105 (0.8140) time: 0.1433 data: 0.0664 max mem: 9390 +Train: [64] [2300/6250] eta: 0:09:03 lr: 0.000039 grad: 0.1024 (0.1110) loss: 0.8167 (0.8139) time: 0.1523 data: 0.0717 max mem: 9390 +Train: [64] [2400/6250] eta: 0:08:53 lr: 0.000039 grad: 0.1008 (0.1109) loss: 0.8138 (0.8138) time: 0.2088 data: 0.0922 max mem: 9390 +Train: [64] [2500/6250] eta: 0:08:42 lr: 0.000039 grad: 0.1030 (0.1108) loss: 0.8155 (0.8138) time: 0.1460 data: 0.0703 max mem: 9390 +Train: [64] [2600/6250] eta: 0:08:27 lr: 0.000039 grad: 0.0976 (0.1106) loss: 0.8214 (0.8138) time: 0.1434 data: 0.0661 max mem: 9390 +Train: [64] [2700/6250] eta: 0:08:14 lr: 0.000038 grad: 0.1103 (0.1106) loss: 0.8123 (0.8137) time: 0.2013 data: 0.1114 max mem: 9390 +Train: [64] [2800/6250] eta: 0:07:58 lr: 0.000038 grad: 0.1090 (0.1105) loss: 0.8136 (0.8137) time: 0.1419 data: 0.0632 max mem: 9390 +Train: [64] [2900/6250] eta: 0:07:44 lr: 0.000038 grad: 0.1068 (0.1104) loss: 0.8114 (0.8136) time: 0.1299 data: 0.0481 max mem: 9390 +Train: [64] [3000/6250] eta: 0:07:32 lr: 0.000038 grad: 0.1025 (0.1103) loss: 0.8123 (0.8136) time: 0.1026 data: 0.0251 max mem: 9390 +Train: [64] [3100/6250] eta: 0:07:17 lr: 0.000038 grad: 0.1065 (0.1102) loss: 0.8160 (0.8135) time: 0.1428 data: 0.0654 max mem: 9390 +Train: [64] [3200/6250] eta: 0:07:02 lr: 0.000038 grad: 0.1068 (0.1101) loss: 0.8144 (0.8135) time: 0.1279 data: 0.0508 max mem: 9390 +Train: [64] [3300/6250] eta: 0:06:51 lr: 0.000038 grad: 0.0994 (0.1100) loss: 0.8163 (0.8136) time: 0.0947 data: 0.0032 max mem: 9390 +Train: [64] [3400/6250] eta: 0:06:37 lr: 0.000038 grad: 0.1069 (0.1100) loss: 0.8079 (0.8137) time: 0.1202 data: 0.0416 max mem: 9390 +Train: [64] [3500/6250] eta: 0:06:24 lr: 0.000038 grad: 0.1104 (0.1101) loss: 0.8116 (0.8136) time: 0.1370 data: 0.0587 max mem: 9390 +Train: [64] [3600/6250] eta: 0:06:10 lr: 0.000038 grad: 0.1073 (0.1101) loss: 0.8104 (0.8135) time: 0.1504 data: 0.0763 max mem: 9390 +Train: [64] [3700/6250] eta: 0:05:57 lr: 0.000038 grad: 0.1093 (0.1102) loss: 0.8107 (0.8134) time: 0.1179 data: 0.0395 max mem: 9390 +Train: [64] [3800/6250] eta: 0:05:43 lr: 0.000038 grad: 0.1117 (0.1102) loss: 0.8158 (0.8134) time: 0.1443 data: 0.0659 max mem: 9390 +Train: [64] [3900/6250] eta: 0:05:30 lr: 0.000038 grad: 0.1081 (0.1102) loss: 0.8139 (0.8134) time: 0.1459 data: 0.0727 max mem: 9390 +Train: [64] [4000/6250] eta: 0:05:16 lr: 0.000038 grad: 0.1014 (0.1102) loss: 0.8194 (0.8134) time: 0.1403 data: 0.0588 max mem: 9390 +Train: [64] [4100/6250] eta: 0:05:02 lr: 0.000038 grad: 0.1027 (0.1102) loss: 0.8175 (0.8135) time: 0.1547 data: 0.0793 max mem: 9390 +Train: [64] [4200/6250] eta: 0:04:48 lr: 0.000038 grad: 0.1110 (0.1102) loss: 0.8142 (0.8135) time: 0.1423 data: 0.0549 max mem: 9390 +Train: [64] [4300/6250] eta: 0:04:34 lr: 0.000038 grad: 0.1102 (0.1102) loss: 0.8196 (0.8136) time: 0.1479 data: 0.0746 max mem: 9390 +Train: [64] [4400/6250] eta: 0:04:20 lr: 0.000038 grad: 0.1044 (0.1103) loss: 0.8149 (0.8137) time: 0.1330 data: 0.0517 max mem: 9390 +Train: [64] [4500/6250] eta: 0:04:06 lr: 0.000038 grad: 0.1028 (0.1103) loss: 0.8182 (0.8137) time: 0.1779 data: 0.0884 max mem: 9390 +Train: [64] [4600/6250] eta: 0:03:52 lr: 0.000038 grad: 0.1111 (0.1103) loss: 0.8191 (0.8137) time: 0.1314 data: 0.0550 max mem: 9390 +Train: [64] [4700/6250] eta: 0:03:37 lr: 0.000038 grad: 0.1037 (0.1105) loss: 0.8181 (0.8138) time: 0.1425 data: 0.0627 max mem: 9390 +Train: [64] [4800/6250] eta: 0:03:24 lr: 0.000038 grad: 0.1045 (0.1105) loss: 0.8116 (0.8139) time: 0.1533 data: 0.0686 max mem: 9390 +Train: [64] [4900/6250] eta: 0:03:10 lr: 0.000038 grad: 0.1062 (0.1104) loss: 0.8105 (0.8139) time: 0.1529 data: 0.0732 max mem: 9390 +Train: [64] [5000/6250] eta: 0:02:56 lr: 0.000038 grad: 0.1070 (0.1105) loss: 0.8153 (0.8140) time: 0.1389 data: 0.0524 max mem: 9390 +Train: [64] [5100/6250] eta: 0:02:42 lr: 0.000038 grad: 0.1084 (0.1105) loss: 0.8200 (0.8141) time: 0.1257 data: 0.0499 max mem: 9390 +Train: [64] [5200/6250] eta: 0:02:27 lr: 0.000038 grad: 0.1039 (0.1105) loss: 0.8174 (0.8142) time: 0.1334 data: 0.0540 max mem: 9390 +Train: [64] [5300/6250] eta: 0:02:13 lr: 0.000038 grad: 0.1090 (0.1105) loss: 0.8207 (0.8142) time: 0.1365 data: 0.0434 max mem: 9390 +Train: [64] [5400/6250] eta: 0:01:59 lr: 0.000038 grad: 0.1094 (0.1104) loss: 0.8153 (0.8143) time: 0.1173 data: 0.0352 max mem: 9390 +Train: [64] [5500/6250] eta: 0:01:44 lr: 0.000038 grad: 0.1039 (0.1104) loss: 0.8180 (0.8143) time: 0.1245 data: 0.0450 max mem: 9390 +Train: [64] [5600/6250] eta: 0:01:30 lr: 0.000038 grad: 0.1063 (0.1104) loss: 0.8165 (0.8143) time: 0.1442 data: 0.0641 max mem: 9390 +Train: [64] [5700/6250] eta: 0:01:16 lr: 0.000038 grad: 0.0986 (0.1104) loss: 0.8066 (0.8143) time: 0.1504 data: 0.0673 max mem: 9390 +Train: [64] [5800/6250] eta: 0:01:02 lr: 0.000038 grad: 0.1095 (0.1103) loss: 0.8112 (0.8143) time: 0.1612 data: 0.0755 max mem: 9390 +Train: [64] [5900/6250] eta: 0:00:48 lr: 0.000037 grad: 0.1065 (0.1103) loss: 0.8186 (0.8143) time: 0.1382 data: 0.0560 max mem: 9390 +Train: [64] [6000/6250] eta: 0:00:35 lr: 0.000037 grad: 0.1032 (0.1103) loss: 0.8148 (0.8143) time: 0.0903 data: 0.0004 max mem: 9390 +Train: [64] [6100/6250] eta: 0:00:21 lr: 0.000037 grad: 0.1048 (0.1103) loss: 0.8116 (0.8143) time: 0.1443 data: 0.0660 max mem: 9390 +Train: [64] [6200/6250] eta: 0:00:07 lr: 0.000037 grad: 0.1081 (0.1103) loss: 0.8176 (0.8142) time: 0.1307 data: 0.0487 max mem: 9390 +Train: [64] [6249/6250] eta: 0:00:00 lr: 0.000037 grad: 0.1131 (0.1104) loss: 0.8057 (0.8141) time: 0.1429 data: 0.0666 max mem: 9390 +Train: [64] Total time: 0:14:41 (0.1411 s / it) +Averaged stats: lr: 0.000037 grad: 0.1131 (0.1104) loss: 0.8057 (0.8141) +Eval (hcp-train-subset): [64] [ 0/62] eta: 0:03:06 loss: 0.8468 (0.8468) time: 3.0073 data: 2.9424 max mem: 9390 +Eval (hcp-train-subset): [64] [61/62] eta: 0:00:00 loss: 0.8304 (0.8324) time: 0.1216 data: 0.0971 max mem: 9390 +Eval (hcp-train-subset): [64] Total time: 0:00:11 (0.1866 s / it) +Averaged stats (hcp-train-subset): loss: 0.8304 (0.8324) +Making plots (hcp-train-subset): example=35 +Eval (hcp-val): [64] [ 0/62] eta: 0:05:00 loss: 0.8308 (0.8308) time: 4.8465 data: 4.8135 max mem: 9390 +Eval (hcp-val): [64] [61/62] eta: 0:00:00 loss: 0.8329 (0.8340) time: 0.1091 data: 0.0844 max mem: 9390 +Eval (hcp-val): [64] Total time: 0:00:13 (0.2156 s / it) +Averaged stats (hcp-val): loss: 0.8329 (0.8340) +Making plots (hcp-val): example=6 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +Train: [65] [ 0/6250] eta: 9:12:15 lr: 0.000037 grad: 0.1194 (0.1194) loss: 0.8600 (0.8600) time: 5.3017 data: 5.1974 max mem: 9390 +Train: [65] [ 100/6250] eta: 0:18:32 lr: 0.000037 grad: 0.1068 (0.1091) loss: 0.8225 (0.8270) time: 0.1414 data: 0.0517 max mem: 9390 +Train: [65] [ 200/6250] eta: 0:16:08 lr: 0.000037 grad: 0.1085 (0.1147) loss: 0.8173 (0.8237) time: 0.1359 data: 0.0409 max mem: 9390 +Train: [65] [ 300/6250] eta: 0:15:07 lr: 0.000037 grad: 0.1033 (0.1119) loss: 0.8236 (0.8231) time: 0.1627 data: 0.0818 max mem: 9390 +Train: [65] [ 400/6250] eta: 0:14:11 lr: 0.000037 grad: 0.1032 (0.1112) loss: 0.8252 (0.8224) time: 0.1270 data: 0.0427 max mem: 9390 +Train: [65] [ 500/6250] eta: 0:13:28 lr: 0.000037 grad: 0.1013 (0.1098) loss: 0.8216 (0.8219) time: 0.1267 data: 0.0399 max mem: 9390 +Train: [65] [ 600/6250] eta: 0:12:57 lr: 0.000037 grad: 0.1033 (0.1086) loss: 0.8206 (0.8216) time: 0.1171 data: 0.0371 max mem: 9390 +Train: [65] [ 700/6250] eta: 0:12:31 lr: 0.000037 grad: 0.1076 (0.1082) loss: 0.8201 (0.8212) time: 0.1296 data: 0.0416 max mem: 9390 +Train: [65] [ 800/6250] eta: 0:12:06 lr: 0.000037 grad: 0.0969 (0.1074) loss: 0.8171 (0.8213) time: 0.1232 data: 0.0413 max mem: 9390 +Train: [65] [ 900/6250] eta: 0:11:49 lr: 0.000037 grad: 0.1018 (0.1070) loss: 0.8218 (0.8212) time: 0.1281 data: 0.0420 max mem: 9390 +Train: [65] [1000/6250] eta: 0:11:35 lr: 0.000037 grad: 0.1022 (0.1068) loss: 0.8146 (0.8210) time: 0.1222 data: 0.0389 max mem: 9390 +Train: [65] [1100/6250] eta: 0:11:19 lr: 0.000037 grad: 0.0965 (0.1063) loss: 0.8205 (0.8209) time: 0.1389 data: 0.0602 max mem: 9390 +Train: [65] [1200/6250] eta: 0:11:08 lr: 0.000037 grad: 0.1010 (0.1060) loss: 0.8202 (0.8209) time: 0.1249 data: 0.0447 max mem: 9390 +Train: [65] [1300/6250] eta: 0:10:56 lr: 0.000037 grad: 0.1026 (0.1060) loss: 0.8171 (0.8208) time: 0.1573 data: 0.0806 max mem: 9390 +Train: [65] [1400/6250] eta: 0:10:41 lr: 0.000037 grad: 0.1031 (0.1059) loss: 0.8219 (0.8207) time: 0.1269 data: 0.0492 max mem: 9390 +Train: [65] [1500/6250] eta: 0:10:29 lr: 0.000037 grad: 0.1038 (0.1057) loss: 0.8176 (0.8206) time: 0.1431 data: 0.0618 max mem: 9390 +Train: [65] [1600/6250] eta: 0:10:15 lr: 0.000037 grad: 0.0978 (0.1056) loss: 0.8220 (0.8205) time: 0.1233 data: 0.0347 max mem: 9390 +Train: [65] [1700/6250] eta: 0:10:04 lr: 0.000037 grad: 0.1051 (0.1057) loss: 0.8148 (0.8201) time: 0.1426 data: 0.0639 max mem: 9390 +Train: [65] [1800/6250] eta: 0:09:53 lr: 0.000037 grad: 0.1014 (0.1058) loss: 0.8142 (0.8198) time: 0.1688 data: 0.0682 max mem: 9390 +Train: [65] [1900/6250] eta: 0:09:42 lr: 0.000037 grad: 0.1063 (0.1061) loss: 0.8148 (0.8195) time: 0.1127 data: 0.0342 max mem: 9390 +Train: [65] [2000/6250] eta: 0:09:31 lr: 0.000037 grad: 0.1073 (0.1063) loss: 0.8150 (0.8191) time: 0.1022 data: 0.0228 max mem: 9390 +Train: [65] [2100/6250] eta: 0:09:19 lr: 0.000037 grad: 0.1066 (0.1065) loss: 0.8119 (0.8188) time: 0.1621 data: 0.0867 max mem: 9390 +Train: [65] [2200/6250] eta: 0:09:07 lr: 0.000037 grad: 0.1130 (0.1069) loss: 0.8081 (0.8184) time: 0.1311 data: 0.0525 max mem: 9390 +Train: [65] [2300/6250] eta: 0:08:57 lr: 0.000037 grad: 0.1164 (0.1073) loss: 0.8128 (0.8181) time: 0.1156 data: 0.0350 max mem: 9390 +Train: [65] [2400/6250] eta: 0:08:44 lr: 0.000037 grad: 0.1122 (0.1075) loss: 0.8187 (0.8177) time: 0.1574 data: 0.0698 max mem: 9390 +Train: [65] [2500/6250] eta: 0:08:33 lr: 0.000037 grad: 0.1052 (0.1077) loss: 0.8065 (0.8174) time: 0.1409 data: 0.0628 max mem: 9390 +Train: [65] [2600/6250] eta: 0:08:18 lr: 0.000037 grad: 0.1110 (0.1079) loss: 0.8114 (0.8171) time: 0.1297 data: 0.0508 max mem: 9390 +Train: [65] [2700/6250] eta: 0:08:06 lr: 0.000037 grad: 0.1078 (0.1081) loss: 0.8160 (0.8170) time: 0.1857 data: 0.1005 max mem: 9390 +Train: [65] [2800/6250] eta: 0:07:53 lr: 0.000037 grad: 0.1103 (0.1083) loss: 0.8114 (0.8168) time: 0.1257 data: 0.0481 max mem: 9390 +Train: [65] [2900/6250] eta: 0:07:40 lr: 0.000037 grad: 0.1051 (0.1082) loss: 0.8215 (0.8167) time: 0.1478 data: 0.0747 max mem: 9390 +Train: [65] [3000/6250] eta: 0:07:27 lr: 0.000036 grad: 0.1052 (0.1083) loss: 0.8143 (0.8167) time: 0.1501 data: 0.0654 max mem: 9390 +Train: [65] [3100/6250] eta: 0:07:13 lr: 0.000036 grad: 0.1102 (0.1084) loss: 0.8083 (0.8166) time: 0.1107 data: 0.0293 max mem: 9390 +Train: [65] [3200/6250] eta: 0:06:59 lr: 0.000036 grad: 0.1075 (0.1085) loss: 0.8120 (0.8164) time: 0.1500 data: 0.0658 max mem: 9390 +Train: [65] [3300/6250] eta: 0:06:49 lr: 0.000036 grad: 0.1121 (0.1086) loss: 0.8218 (0.8164) time: 0.1538 data: 0.0803 max mem: 9390 +Train: [65] [3400/6250] eta: 0:06:35 lr: 0.000036 grad: 0.1114 (0.1086) loss: 0.8075 (0.8163) time: 0.1247 data: 0.0387 max mem: 9390 +Train: [65] [3500/6250] eta: 0:06:21 lr: 0.000036 grad: 0.1160 (0.1088) loss: 0.8085 (0.8162) time: 0.1357 data: 0.0545 max mem: 9390 +Train: [65] [3600/6250] eta: 0:06:09 lr: 0.000036 grad: 0.1104 (0.1089) loss: 0.8128 (0.8161) time: 0.1719 data: 0.0939 max mem: 9390 +Train: [65] [3700/6250] eta: 0:05:55 lr: 0.000036 grad: 0.1124 (0.1091) loss: 0.8078 (0.8160) time: 0.1425 data: 0.0642 max mem: 9390 +Train: [65] [3800/6250] eta: 0:05:43 lr: 0.000036 grad: 0.1102 (0.1093) loss: 0.8065 (0.8159) time: 0.2034 data: 0.1187 max mem: 9390 +Train: [65] [3900/6250] eta: 0:05:29 lr: 0.000036 grad: 0.1116 (0.1094) loss: 0.8069 (0.8158) time: 0.1365 data: 0.0604 max mem: 9390 +Train: [65] [4000/6250] eta: 0:05:15 lr: 0.000036 grad: 0.1053 (0.1095) loss: 0.8166 (0.8156) time: 0.1363 data: 0.0518 max mem: 9390 +Train: [65] [4100/6250] eta: 0:05:01 lr: 0.000036 grad: 0.1094 (0.1096) loss: 0.8164 (0.8156) time: 0.1464 data: 0.0538 max mem: 9390 +Train: [65] [4200/6250] eta: 0:04:47 lr: 0.000036 grad: 0.1131 (0.1096) loss: 0.8152 (0.8156) time: 0.1266 data: 0.0411 max mem: 9390 +Train: [65] [4300/6250] eta: 0:04:33 lr: 0.000036 grad: 0.1125 (0.1097) loss: 0.8076 (0.8155) time: 0.1193 data: 0.0315 max mem: 9390 +Train: [65] [4400/6250] eta: 0:04:18 lr: 0.000036 grad: 0.1100 (0.1098) loss: 0.8076 (0.8154) time: 0.1338 data: 0.0493 max mem: 9390 +Train: [65] [4500/6250] eta: 0:04:04 lr: 0.000036 grad: 0.1116 (0.1099) loss: 0.8147 (0.8153) time: 0.1348 data: 0.0551 max mem: 9390 +Train: [65] [4600/6250] eta: 0:03:50 lr: 0.000036 grad: 0.1082 (0.1099) loss: 0.8121 (0.8153) time: 0.1635 data: 0.0830 max mem: 9390 +Train: [65] [4700/6250] eta: 0:03:37 lr: 0.000036 grad: 0.1056 (0.1099) loss: 0.8144 (0.8152) time: 0.1645 data: 0.0915 max mem: 9390 +Train: [65] [4800/6250] eta: 0:03:23 lr: 0.000036 grad: 0.1033 (0.1100) loss: 0.8110 (0.8152) time: 0.1535 data: 0.0730 max mem: 9390 +Train: [65] [4900/6250] eta: 0:03:09 lr: 0.000036 grad: 0.1067 (0.1100) loss: 0.8214 (0.8151) time: 0.1449 data: 0.0613 max mem: 9390 +Train: [65] [5000/6250] eta: 0:02:55 lr: 0.000036 grad: 0.1050 (0.1100) loss: 0.8210 (0.8152) time: 0.1416 data: 0.0605 max mem: 9390 +Train: [65] [5100/6250] eta: 0:02:41 lr: 0.000036 grad: 0.1097 (0.1101) loss: 0.8160 (0.8152) time: 0.1479 data: 0.0666 max mem: 9390 +Train: [65] [5200/6250] eta: 0:02:27 lr: 0.000036 grad: 0.1028 (0.1101) loss: 0.8134 (0.8152) time: 0.1099 data: 0.0227 max mem: 9390 +Train: [65] [5300/6250] eta: 0:02:12 lr: 0.000036 grad: 0.1114 (0.1102) loss: 0.8184 (0.8152) time: 0.1145 data: 0.0331 max mem: 9390 +Train: [65] [5400/6250] eta: 0:01:58 lr: 0.000036 grad: 0.1064 (0.1102) loss: 0.8172 (0.8153) time: 0.1225 data: 0.0309 max mem: 9390 +Train: [65] [5500/6250] eta: 0:01:44 lr: 0.000036 grad: 0.1039 (0.1102) loss: 0.8146 (0.8153) time: 0.1337 data: 0.0519 max mem: 9390 +Train: [65] [5600/6250] eta: 0:01:30 lr: 0.000036 grad: 0.1044 (0.1102) loss: 0.8197 (0.8154) time: 0.1328 data: 0.0490 max mem: 9390 +Train: [65] [5700/6250] eta: 0:01:16 lr: 0.000036 grad: 0.1009 (0.1102) loss: 0.8231 (0.8155) time: 0.1264 data: 0.0467 max mem: 9390 +Train: [65] [5800/6250] eta: 0:01:02 lr: 0.000036 grad: 0.1030 (0.1102) loss: 0.8168 (0.8155) time: 0.1115 data: 0.0298 max mem: 9390 +Train: [65] [5900/6250] eta: 0:00:48 lr: 0.000036 grad: 0.1165 (0.1102) loss: 0.8103 (0.8155) time: 0.1244 data: 0.0431 max mem: 9390 +Train: [65] [6000/6250] eta: 0:00:34 lr: 0.000036 grad: 0.1034 (0.1101) loss: 0.8135 (0.8156) time: 0.1403 data: 0.0595 max mem: 9390 +Train: [65] [6100/6250] eta: 0:00:20 lr: 0.000036 grad: 0.1067 (0.1101) loss: 0.8168 (0.8156) time: 0.1338 data: 0.0565 max mem: 9390 +Train: [65] [6200/6250] eta: 0:00:06 lr: 0.000036 grad: 0.1128 (0.1101) loss: 0.8159 (0.8156) time: 0.1498 data: 0.0737 max mem: 9390 +Train: [65] [6249/6250] eta: 0:00:00 lr: 0.000036 grad: 0.1004 (0.1101) loss: 0.8193 (0.8156) time: 0.1264 data: 0.0472 max mem: 9390 +Train: [65] Total time: 0:14:29 (0.1391 s / it) +Averaged stats: lr: 0.000036 grad: 0.1004 (0.1101) loss: 0.8193 (0.8156) +Eval (hcp-train-subset): [65] [ 0/62] eta: 0:04:21 loss: 0.8466 (0.8466) time: 4.2164 data: 4.1121 max mem: 9390 +Eval (hcp-train-subset): [65] [61/62] eta: 0:00:00 loss: 0.8316 (0.8321) time: 0.1383 data: 0.1132 max mem: 9390 +Eval (hcp-train-subset): [65] Total time: 0:00:13 (0.2218 s / it) +Averaged stats (hcp-train-subset): loss: 0.8316 (0.8321) +Eval (hcp-val): [65] [ 0/62] eta: 0:03:45 loss: 0.8328 (0.8328) time: 3.6314 data: 3.5528 max mem: 9390 +Eval (hcp-val): [65] [61/62] eta: 0:00:00 loss: 0.8306 (0.8329) time: 0.1235 data: 0.0989 max mem: 9390 +Eval (hcp-val): [65] Total time: 0:00:12 (0.1999 s / it) +Averaged stats (hcp-val): loss: 0.8306 (0.8329) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +Train: [66] [ 0/6250] eta: 9:13:43 lr: 0.000036 grad: 0.1479 (0.1479) loss: 0.7817 (0.7817) time: 5.3157 data: 5.1894 max mem: 9390 +Train: [66] [ 100/6250] eta: 0:18:35 lr: 0.000035 grad: 0.1129 (0.1208) loss: 0.8284 (0.8262) time: 0.1500 data: 0.0566 max mem: 9390 +Train: [66] [ 200/6250] eta: 0:16:29 lr: 0.000035 grad: 0.1148 (0.1203) loss: 0.8128 (0.8218) time: 0.1477 data: 0.0583 max mem: 9390 +Train: [66] [ 300/6250] eta: 0:15:01 lr: 0.000035 grad: 0.1215 (0.1210) loss: 0.8107 (0.8183) time: 0.1297 data: 0.0354 max mem: 9390 +Train: [66] [ 400/6250] eta: 0:14:10 lr: 0.000035 grad: 0.1019 (0.1189) loss: 0.8185 (0.8167) time: 0.1183 data: 0.0345 max mem: 9390 +Train: [66] [ 500/6250] eta: 0:13:28 lr: 0.000035 grad: 0.1036 (0.1171) loss: 0.8148 (0.8164) time: 0.1109 data: 0.0212 max mem: 9390 +Train: [66] [ 600/6250] eta: 0:12:51 lr: 0.000035 grad: 0.1053 (0.1157) loss: 0.8170 (0.8163) time: 0.1025 data: 0.0106 max mem: 9390 +Train: [66] [ 700/6250] eta: 0:12:25 lr: 0.000035 grad: 0.1054 (0.1147) loss: 0.8143 (0.8163) time: 0.1162 data: 0.0304 max mem: 9390 +Train: [66] [ 800/6250] eta: 0:12:10 lr: 0.000035 grad: 0.1010 (0.1139) loss: 0.8196 (0.8163) time: 0.1391 data: 0.0526 max mem: 9390 +Train: [66] [ 900/6250] eta: 0:12:02 lr: 0.000035 grad: 0.1053 (0.1134) loss: 0.8110 (0.8161) time: 0.1273 data: 0.0378 max mem: 9390 +Train: [66] [1000/6250] eta: 0:11:50 lr: 0.000035 grad: 0.1061 (0.1129) loss: 0.8108 (0.8162) time: 0.1008 data: 0.0200 max mem: 9390 +Train: [66] [1100/6250] eta: 0:11:33 lr: 0.000035 grad: 0.1034 (0.1124) loss: 0.8155 (0.8161) time: 0.1281 data: 0.0466 max mem: 9390 +Train: [66] [1200/6250] eta: 0:11:27 lr: 0.000035 grad: 0.1100 (0.1121) loss: 0.8088 (0.8159) time: 0.2094 data: 0.1266 max mem: 9390 +Train: [66] [1300/6250] eta: 0:11:12 lr: 0.000035 grad: 0.1050 (0.1121) loss: 0.8204 (0.8157) time: 0.1371 data: 0.0617 max mem: 9390 +Train: [66] [1400/6250] eta: 0:10:59 lr: 0.000035 grad: 0.1104 (0.1121) loss: 0.8134 (0.8156) time: 0.1071 data: 0.0212 max mem: 9390 +Train: [66] [1500/6250] eta: 0:10:46 lr: 0.000035 grad: 0.1095 (0.1120) loss: 0.8186 (0.8156) time: 0.1482 data: 0.0635 max mem: 9390 +Train: [66] [1600/6250] eta: 0:10:35 lr: 0.000035 grad: 0.1144 (0.1121) loss: 0.8131 (0.8155) time: 0.1123 data: 0.0404 max mem: 9390 +Train: [66] [1700/6250] eta: 0:10:21 lr: 0.000035 grad: 0.1099 (0.1121) loss: 0.8173 (0.8154) time: 0.1287 data: 0.0490 max mem: 9390 +Train: [66] [1800/6250] eta: 0:10:06 lr: 0.000035 grad: 0.1089 (0.1121) loss: 0.8065 (0.8152) time: 0.1343 data: 0.0519 max mem: 9390 +Train: [66] [1900/6250] eta: 0:09:58 lr: 0.000035 grad: 0.1118 (0.1121) loss: 0.8122 (0.8150) time: 0.1638 data: 0.0700 max mem: 9390 +Train: [66] [2000/6250] eta: 0:09:43 lr: 0.000035 grad: 0.1133 (0.1121) loss: 0.8165 (0.8149) time: 0.1263 data: 0.0417 max mem: 9390 +Train: [66] [2100/6250] eta: 0:09:29 lr: 0.000035 grad: 0.1094 (0.1121) loss: 0.8099 (0.8147) time: 0.1335 data: 0.0530 max mem: 9390 +Train: [66] [2200/6250] eta: 0:09:15 lr: 0.000035 grad: 0.1110 (0.1120) loss: 0.8164 (0.8145) time: 0.1489 data: 0.0609 max mem: 9390 +Train: [66] [2300/6250] eta: 0:09:00 lr: 0.000035 grad: 0.1097 (0.1120) loss: 0.8119 (0.8144) time: 0.1167 data: 0.0359 max mem: 9390 +Train: [66] [2400/6250] eta: 0:08:46 lr: 0.000035 grad: 0.1128 (0.1120) loss: 0.8119 (0.8143) time: 0.1343 data: 0.0548 max mem: 9390 +Train: [66] [2500/6250] eta: 0:08:31 lr: 0.000035 grad: 0.1159 (0.1121) loss: 0.8083 (0.8142) time: 0.1399 data: 0.0594 max mem: 9390 +Train: [66] [2600/6250] eta: 0:08:16 lr: 0.000035 grad: 0.1106 (0.1121) loss: 0.8081 (0.8141) time: 0.1045 data: 0.0295 max mem: 9390 +Train: [66] [2700/6250] eta: 0:08:04 lr: 0.000035 grad: 0.1092 (0.1122) loss: 0.8161 (0.8140) time: 0.1240 data: 0.0251 max mem: 9390 +Train: [66] [2800/6250] eta: 0:07:50 lr: 0.000035 grad: 0.1187 (0.1123) loss: 0.8074 (0.8138) time: 0.1421 data: 0.0612 max mem: 9390 +Train: [66] [2900/6250] eta: 0:07:36 lr: 0.000035 grad: 0.1101 (0.1124) loss: 0.8157 (0.8138) time: 0.1346 data: 0.0511 max mem: 9390 +Train: [66] [3000/6250] eta: 0:07:23 lr: 0.000035 grad: 0.1106 (0.1124) loss: 0.8068 (0.8137) time: 0.1454 data: 0.0609 max mem: 9390 +Train: [66] [3100/6250] eta: 0:07:09 lr: 0.000035 grad: 0.1017 (0.1123) loss: 0.8234 (0.8137) time: 0.1404 data: 0.0646 max mem: 9390 +Train: [66] [3200/6250] eta: 0:06:54 lr: 0.000035 grad: 0.1133 (0.1123) loss: 0.8098 (0.8136) time: 0.1413 data: 0.0510 max mem: 9390 +Train: [66] [3300/6250] eta: 0:06:41 lr: 0.000035 grad: 0.1132 (0.1123) loss: 0.8081 (0.8136) time: 0.1331 data: 0.0594 max mem: 9390 +Train: [66] [3400/6250] eta: 0:06:27 lr: 0.000035 grad: 0.1082 (0.1123) loss: 0.8193 (0.8136) time: 0.1327 data: 0.0547 max mem: 9390 +Train: [66] [3500/6250] eta: 0:06:14 lr: 0.000034 grad: 0.1130 (0.1123) loss: 0.8162 (0.8136) time: 0.1489 data: 0.0748 max mem: 9390 +Train: [66] [3600/6250] eta: 0:06:00 lr: 0.000034 grad: 0.1147 (0.1122) loss: 0.8126 (0.8136) time: 0.1292 data: 0.0445 max mem: 9390 +Train: [66] [3700/6250] eta: 0:05:48 lr: 0.000034 grad: 0.1093 (0.1122) loss: 0.8141 (0.8136) time: 0.1243 data: 0.0470 max mem: 9390 +Train: [66] [3800/6250] eta: 0:05:35 lr: 0.000034 grad: 0.1060 (0.1121) loss: 0.8208 (0.8136) time: 0.1627 data: 0.0875 max mem: 9390 +Train: [66] [3900/6250] eta: 0:05:21 lr: 0.000034 grad: 0.1066 (0.1120) loss: 0.8150 (0.8137) time: 0.1485 data: 0.0688 max mem: 9390 +Train: [66] [4000/6250] eta: 0:05:08 lr: 0.000034 grad: 0.1098 (0.1120) loss: 0.8154 (0.8137) time: 0.1829 data: 0.0970 max mem: 9390 +Train: [66] [4100/6250] eta: 0:04:55 lr: 0.000034 grad: 0.1047 (0.1119) loss: 0.8181 (0.8137) time: 0.1509 data: 0.0569 max mem: 9390 +Train: [66] [4200/6250] eta: 0:04:42 lr: 0.000034 grad: 0.1015 (0.1117) loss: 0.8176 (0.8138) time: 0.1352 data: 0.0567 max mem: 9390 +Train: [66] [4300/6250] eta: 0:04:28 lr: 0.000034 grad: 0.1120 (0.1117) loss: 0.8192 (0.8138) time: 0.1372 data: 0.0580 max mem: 9390 +Train: [66] [4400/6250] eta: 0:04:14 lr: 0.000034 grad: 0.1052 (0.1117) loss: 0.8188 (0.8139) time: 0.1161 data: 0.0354 max mem: 9390 +Train: [66] [4500/6250] eta: 0:04:00 lr: 0.000034 grad: 0.1054 (0.1117) loss: 0.8107 (0.8139) time: 0.1322 data: 0.0383 max mem: 9390 +Train: [66] [4600/6250] eta: 0:03:47 lr: 0.000034 grad: 0.1078 (0.1117) loss: 0.8206 (0.8139) time: 0.1624 data: 0.0779 max mem: 9390 +Train: [66] [4700/6250] eta: 0:03:34 lr: 0.000034 grad: 0.1153 (0.1117) loss: 0.8182 (0.8139) time: 0.1343 data: 0.0554 max mem: 9390 +Train: [66] [4800/6250] eta: 0:03:20 lr: 0.000034 grad: 0.1138 (0.1117) loss: 0.8141 (0.8139) time: 0.1242 data: 0.0358 max mem: 9390 +Train: [66] [4900/6250] eta: 0:03:06 lr: 0.000034 grad: 0.1096 (0.1117) loss: 0.8158 (0.8139) time: 0.1237 data: 0.0337 max mem: 9390 +Train: [66] [5000/6250] eta: 0:02:52 lr: 0.000034 grad: 0.1061 (0.1117) loss: 0.8149 (0.8139) time: 0.1385 data: 0.0658 max mem: 9390 +Train: [66] [5100/6250] eta: 0:02:39 lr: 0.000034 grad: 0.1094 (0.1117) loss: 0.8121 (0.8139) time: 0.1288 data: 0.0515 max mem: 9390 +Train: [66] [5200/6250] eta: 0:02:24 lr: 0.000034 grad: 0.1144 (0.1117) loss: 0.8110 (0.8139) time: 0.1080 data: 0.0312 max mem: 9390 +Train: [66] [5300/6250] eta: 0:02:10 lr: 0.000034 grad: 0.1034 (0.1118) loss: 0.8201 (0.8138) time: 0.1216 data: 0.0371 max mem: 9390 +Train: [66] [5400/6250] eta: 0:01:56 lr: 0.000034 grad: 0.1167 (0.1118) loss: 0.8093 (0.8138) time: 0.1077 data: 0.0271 max mem: 9390 +Train: [66] [5500/6250] eta: 0:01:42 lr: 0.000034 grad: 0.1041 (0.1118) loss: 0.8186 (0.8138) time: 0.1202 data: 0.0354 max mem: 9390 +Train: [66] [5600/6250] eta: 0:01:28 lr: 0.000034 grad: 0.1081 (0.1118) loss: 0.8174 (0.8138) time: 0.1201 data: 0.0353 max mem: 9390 +Train: [66] [5700/6250] eta: 0:01:14 lr: 0.000034 grad: 0.1050 (0.1117) loss: 0.8217 (0.8139) time: 0.1149 data: 0.0300 max mem: 9390 +Train: [66] [5800/6250] eta: 0:01:01 lr: 0.000034 grad: 0.1079 (0.1117) loss: 0.8131 (0.8139) time: 0.1387 data: 0.0598 max mem: 9390 +Train: [66] [5900/6250] eta: 0:00:47 lr: 0.000034 grad: 0.1096 (0.1117) loss: 0.8137 (0.8140) time: 0.1265 data: 0.0438 max mem: 9390 +Train: [66] [6000/6250] eta: 0:00:34 lr: 0.000034 grad: 0.1071 (0.1116) loss: 0.8108 (0.8140) time: 0.1462 data: 0.0638 max mem: 9390 +Train: [66] [6100/6250] eta: 0:00:20 lr: 0.000034 grad: 0.1087 (0.1116) loss: 0.8127 (0.8140) time: 0.1300 data: 0.0497 max mem: 9390 +Train: [66] [6200/6250] eta: 0:00:06 lr: 0.000034 grad: 0.1058 (0.1116) loss: 0.8125 (0.8141) time: 0.1807 data: 0.0873 max mem: 9390 +Train: [66] [6249/6250] eta: 0:00:00 lr: 0.000034 grad: 0.1093 (0.1116) loss: 0.8185 (0.8141) time: 0.1446 data: 0.0677 max mem: 9390 +Train: [66] Total time: 0:14:17 (0.1373 s / it) +Averaged stats: lr: 0.000034 grad: 0.1093 (0.1116) loss: 0.8185 (0.8141) +Eval (hcp-train-subset): [66] [ 0/62] eta: 0:04:16 loss: 0.8421 (0.8421) time: 4.1380 data: 4.0433 max mem: 9390 +Eval (hcp-train-subset): [66] [61/62] eta: 0:00:00 loss: 0.8305 (0.8305) time: 0.1237 data: 0.0969 max mem: 9390 +Eval (hcp-train-subset): [66] Total time: 0:00:13 (0.2158 s / it) +Averaged stats (hcp-train-subset): loss: 0.8305 (0.8305) +Eval (hcp-val): [66] [ 0/62] eta: 0:03:35 loss: 0.8294 (0.8294) time: 3.4712 data: 3.4096 max mem: 9390 +Eval (hcp-val): [66] [61/62] eta: 0:00:00 loss: 0.8306 (0.8318) time: 0.1210 data: 0.0963 max mem: 9390 +Eval (hcp-val): [66] Total time: 0:00:12 (0.1991 s / it) +Averaged stats (hcp-val): loss: 0.8306 (0.8318) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +Train: [67] [ 0/6250] eta: 8:51:52 lr: 0.000034 grad: 0.1770 (0.1770) loss: 0.8571 (0.8571) time: 5.1060 data: 4.9646 max mem: 9390 +Train: [67] [ 100/6250] eta: 0:18:42 lr: 0.000034 grad: 0.1036 (0.1217) loss: 0.8217 (0.8311) time: 0.1378 data: 0.0360 max mem: 9390 +Train: [67] [ 200/6250] eta: 0:16:18 lr: 0.000034 grad: 0.1039 (0.1183) loss: 0.8178 (0.8270) time: 0.1273 data: 0.0340 max mem: 9390 +Train: [67] [ 300/6250] eta: 0:15:11 lr: 0.000034 grad: 0.1085 (0.1149) loss: 0.8202 (0.8261) time: 0.1575 data: 0.0770 max mem: 9390 +Train: [67] [ 400/6250] eta: 0:14:06 lr: 0.000034 grad: 0.0963 (0.1119) loss: 0.8267 (0.8257) time: 0.1220 data: 0.0386 max mem: 9390 +Train: [67] [ 500/6250] eta: 0:13:24 lr: 0.000034 grad: 0.1022 (0.1100) loss: 0.8258 (0.8254) time: 0.1212 data: 0.0349 max mem: 9390 +Train: [67] [ 600/6250] eta: 0:12:55 lr: 0.000033 grad: 0.1000 (0.1082) loss: 0.8237 (0.8255) time: 0.1157 data: 0.0280 max mem: 9390 +Train: [67] [ 700/6250] eta: 0:12:27 lr: 0.000033 grad: 0.0965 (0.1069) loss: 0.8301 (0.8256) time: 0.1162 data: 0.0334 max mem: 9390 +Train: [67] [ 800/6250] eta: 0:12:04 lr: 0.000033 grad: 0.0971 (0.1067) loss: 0.8197 (0.8253) time: 0.1252 data: 0.0320 max mem: 9390 +Train: [67] [ 900/6250] eta: 0:11:53 lr: 0.000033 grad: 0.1028 (0.1065) loss: 0.8221 (0.8248) time: 0.1443 data: 0.0613 max mem: 9390 +Train: [67] [1000/6250] eta: 0:11:35 lr: 0.000033 grad: 0.0972 (0.1066) loss: 0.8269 (0.8242) time: 0.1258 data: 0.0477 max mem: 9390 +Train: [67] [1100/6250] eta: 0:11:19 lr: 0.000033 grad: 0.1048 (0.1066) loss: 0.8228 (0.8239) time: 0.1136 data: 0.0319 max mem: 9390 +Train: [67] [1200/6250] eta: 0:11:05 lr: 0.000033 grad: 0.1019 (0.1067) loss: 0.8266 (0.8236) time: 0.1363 data: 0.0551 max mem: 9390 +Train: [67] [1300/6250] eta: 0:10:52 lr: 0.000033 grad: 0.1040 (0.1068) loss: 0.8221 (0.8232) time: 0.1220 data: 0.0407 max mem: 9390 +Train: [67] [1400/6250] eta: 0:10:37 lr: 0.000033 grad: 0.1034 (0.1069) loss: 0.8207 (0.8228) time: 0.1072 data: 0.0225 max mem: 9390 +Train: [67] [1500/6250] eta: 0:10:28 lr: 0.000033 grad: 0.1067 (0.1070) loss: 0.8224 (0.8226) time: 0.1626 data: 0.0834 max mem: 9390 +Train: [67] [1600/6250] eta: 0:10:20 lr: 0.000033 grad: 0.1010 (0.1070) loss: 0.8213 (0.8223) time: 0.1668 data: 0.0797 max mem: 9390 +Train: [67] [1700/6250] eta: 0:10:08 lr: 0.000033 grad: 0.1081 (0.1071) loss: 0.8175 (0.8220) time: 0.1357 data: 0.0462 max mem: 9390 +Train: [67] [1800/6250] eta: 0:09:57 lr: 0.000033 grad: 0.1027 (0.1074) loss: 0.8194 (0.8216) time: 0.1562 data: 0.0791 max mem: 9390 +Train: [67] [1900/6250] eta: 0:09:43 lr: 0.000033 grad: 0.1093 (0.1076) loss: 0.8088 (0.8212) time: 0.1318 data: 0.0532 max mem: 9390 +Train: [67] [2000/6250] eta: 0:09:36 lr: 0.000033 grad: 0.1099 (0.1078) loss: 0.8123 (0.8209) time: 0.0895 data: 0.0002 max mem: 9390 +Train: [67] [2100/6250] eta: 0:09:21 lr: 0.000033 grad: 0.1070 (0.1079) loss: 0.8211 (0.8207) time: 0.1610 data: 0.0716 max mem: 9390 +Train: [67] [2200/6250] eta: 0:09:06 lr: 0.000033 grad: 0.1060 (0.1080) loss: 0.8133 (0.8205) time: 0.1261 data: 0.0485 max mem: 9390 +Train: [67] [2300/6250] eta: 0:08:54 lr: 0.000033 grad: 0.1064 (0.1081) loss: 0.8146 (0.8203) time: 0.1256 data: 0.0423 max mem: 9390 +Train: [67] [2400/6250] eta: 0:08:45 lr: 0.000033 grad: 0.1073 (0.1082) loss: 0.8174 (0.8201) time: 0.2496 data: 0.1047 max mem: 9390 +Train: [67] [2500/6250] eta: 0:08:31 lr: 0.000033 grad: 0.1088 (0.1082) loss: 0.8161 (0.8199) time: 0.1460 data: 0.0672 max mem: 9390 +Train: [67] [2600/6250] eta: 0:08:17 lr: 0.000033 grad: 0.1062 (0.1083) loss: 0.8197 (0.8198) time: 0.1398 data: 0.0577 max mem: 9390 +Train: [67] [2700/6250] eta: 0:08:03 lr: 0.000033 grad: 0.1105 (0.1083) loss: 0.8133 (0.8196) time: 0.1276 data: 0.0464 max mem: 9390 +Train: [67] [2800/6250] eta: 0:07:51 lr: 0.000033 grad: 0.1122 (0.1084) loss: 0.8172 (0.8196) time: 0.1849 data: 0.0958 max mem: 9390 +Train: [67] [2900/6250] eta: 0:07:36 lr: 0.000033 grad: 0.1066 (0.1085) loss: 0.8182 (0.8195) time: 0.1359 data: 0.0531 max mem: 9390 +Train: [67] [3000/6250] eta: 0:07:24 lr: 0.000033 grad: 0.1092 (0.1086) loss: 0.8191 (0.8194) time: 0.1544 data: 0.0698 max mem: 9390 +Train: [67] [3100/6250] eta: 0:07:10 lr: 0.000033 grad: 0.1124 (0.1086) loss: 0.8111 (0.8193) time: 0.1441 data: 0.0673 max mem: 9390 +Train: [67] [3200/6250] eta: 0:06:55 lr: 0.000033 grad: 0.1031 (0.1087) loss: 0.8111 (0.8192) time: 0.1174 data: 0.0339 max mem: 9390 +Train: [67] [3300/6250] eta: 0:06:42 lr: 0.000033 grad: 0.1109 (0.1088) loss: 0.8114 (0.8189) time: 0.1619 data: 0.0711 max mem: 9390 +Train: [67] [3400/6250] eta: 0:06:29 lr: 0.000033 grad: 0.1060 (0.1088) loss: 0.8142 (0.8188) time: 0.1416 data: 0.0629 max mem: 9390 +Train: [67] [3500/6250] eta: 0:06:16 lr: 0.000033 grad: 0.1088 (0.1088) loss: 0.8093 (0.8187) time: 0.1821 data: 0.1024 max mem: 9390 +Train: [67] [3600/6250] eta: 0:06:02 lr: 0.000033 grad: 0.1127 (0.1089) loss: 0.8189 (0.8186) time: 0.1338 data: 0.0576 max mem: 9390 +Train: [67] [3700/6250] eta: 0:05:49 lr: 0.000033 grad: 0.1091 (0.1089) loss: 0.8071 (0.8184) time: 0.1445 data: 0.0660 max mem: 9390 +Train: [67] [3800/6250] eta: 0:05:36 lr: 0.000033 grad: 0.1080 (0.1090) loss: 0.8139 (0.8183) time: 0.1537 data: 0.0737 max mem: 9390 +Train: [67] [3900/6250] eta: 0:05:22 lr: 0.000033 grad: 0.1100 (0.1091) loss: 0.8087 (0.8181) time: 0.1201 data: 0.0389 max mem: 9390 +Train: [67] [4000/6250] eta: 0:05:09 lr: 0.000032 grad: 0.1065 (0.1091) loss: 0.8177 (0.8181) time: 0.1284 data: 0.0474 max mem: 9390 +Train: [67] [4100/6250] eta: 0:04:56 lr: 0.000032 grad: 0.1098 (0.1091) loss: 0.8111 (0.8180) time: 0.2004 data: 0.1199 max mem: 9390 +Train: [67] [4200/6250] eta: 0:04:42 lr: 0.000032 grad: 0.1126 (0.1093) loss: 0.8095 (0.8179) time: 0.1482 data: 0.0700 max mem: 9390 +Train: [67] [4300/6250] eta: 0:04:29 lr: 0.000032 grad: 0.1072 (0.1093) loss: 0.8147 (0.8178) time: 0.1262 data: 0.0388 max mem: 9390 +Train: [67] [4400/6250] eta: 0:04:15 lr: 0.000032 grad: 0.1054 (0.1094) loss: 0.8141 (0.8177) time: 0.1283 data: 0.0411 max mem: 9390 +Train: [67] [4500/6250] eta: 0:04:01 lr: 0.000032 grad: 0.1111 (0.1094) loss: 0.8027 (0.8176) time: 0.1524 data: 0.0679 max mem: 9390 +Train: [67] [4600/6250] eta: 0:03:48 lr: 0.000032 grad: 0.1048 (0.1094) loss: 0.8094 (0.8175) time: 0.1636 data: 0.0811 max mem: 9390 +Train: [67] [4700/6250] eta: 0:03:35 lr: 0.000032 grad: 0.1114 (0.1095) loss: 0.8112 (0.8175) time: 0.1398 data: 0.0605 max mem: 9390 +Train: [67] [4800/6250] eta: 0:03:21 lr: 0.000032 grad: 0.1072 (0.1096) loss: 0.8122 (0.8174) time: 0.1727 data: 0.0965 max mem: 9390 +Train: [67] [4900/6250] eta: 0:03:07 lr: 0.000032 grad: 0.1102 (0.1096) loss: 0.8085 (0.8174) time: 0.1431 data: 0.0594 max mem: 9390 +Train: [67] [5000/6250] eta: 0:02:53 lr: 0.000032 grad: 0.1080 (0.1097) loss: 0.8157 (0.8173) time: 0.1197 data: 0.0401 max mem: 9390 +Train: [67] [5100/6250] eta: 0:02:39 lr: 0.000032 grad: 0.1029 (0.1096) loss: 0.8146 (0.8173) time: 0.1193 data: 0.0385 max mem: 9390 +Train: [67] [5200/6250] eta: 0:02:25 lr: 0.000032 grad: 0.1051 (0.1096) loss: 0.8143 (0.8172) time: 0.1398 data: 0.0644 max mem: 9390 +Train: [67] [5300/6250] eta: 0:02:11 lr: 0.000032 grad: 0.1046 (0.1096) loss: 0.8136 (0.8172) time: 0.1363 data: 0.0465 max mem: 9390 +Train: [67] [5400/6250] eta: 0:01:57 lr: 0.000032 grad: 0.1089 (0.1097) loss: 0.8180 (0.8171) time: 0.1432 data: 0.0586 max mem: 9390 +Train: [67] [5500/6250] eta: 0:01:43 lr: 0.000032 grad: 0.1040 (0.1097) loss: 0.8113 (0.8170) time: 0.1248 data: 0.0511 max mem: 9390 +Train: [67] [5600/6250] eta: 0:01:29 lr: 0.000032 grad: 0.1055 (0.1097) loss: 0.8166 (0.8170) time: 0.1154 data: 0.0279 max mem: 9390 +Train: [67] [5700/6250] eta: 0:01:15 lr: 0.000032 grad: 0.1004 (0.1098) loss: 0.8190 (0.8169) time: 0.1463 data: 0.0670 max mem: 9390 +Train: [67] [5800/6250] eta: 0:01:02 lr: 0.000032 grad: 0.1123 (0.1098) loss: 0.8156 (0.8169) time: 0.1284 data: 0.0488 max mem: 9390 +Train: [67] [5900/6250] eta: 0:00:48 lr: 0.000032 grad: 0.1039 (0.1098) loss: 0.8160 (0.8169) time: 0.1595 data: 0.0716 max mem: 9390 +Train: [67] [6000/6250] eta: 0:00:34 lr: 0.000032 grad: 0.1047 (0.1098) loss: 0.8183 (0.8168) time: 0.1634 data: 0.0864 max mem: 9390 +Train: [67] [6100/6250] eta: 0:00:20 lr: 0.000032 grad: 0.1048 (0.1098) loss: 0.8192 (0.8169) time: 0.1170 data: 0.0318 max mem: 9390 +Train: [67] [6200/6250] eta: 0:00:06 lr: 0.000032 grad: 0.1070 (0.1099) loss: 0.8168 (0.8169) time: 0.1426 data: 0.0590 max mem: 9390 +Train: [67] [6249/6250] eta: 0:00:00 lr: 0.000032 grad: 0.1154 (0.1099) loss: 0.8199 (0.8169) time: 0.1380 data: 0.0494 max mem: 9390 +Train: [67] Total time: 0:14:26 (0.1387 s / it) +Averaged stats: lr: 0.000032 grad: 0.1154 (0.1099) loss: 0.8199 (0.8169) +Eval (hcp-train-subset): [67] [ 0/62] eta: 0:04:16 loss: 0.8476 (0.8476) time: 4.1326 data: 4.0386 max mem: 9390 +Eval (hcp-train-subset): [67] [61/62] eta: 0:00:00 loss: 0.8313 (0.8316) time: 0.1350 data: 0.1100 max mem: 9390 +Eval (hcp-train-subset): [67] Total time: 0:00:13 (0.2111 s / it) +Averaged stats (hcp-train-subset): loss: 0.8313 (0.8316) +Eval (hcp-val): [67] [ 0/62] eta: 0:05:42 loss: 0.8331 (0.8331) time: 5.5290 data: 5.4996 max mem: 9390 +Eval (hcp-val): [67] [61/62] eta: 0:00:00 loss: 0.8310 (0.8323) time: 0.1206 data: 0.0956 max mem: 9390 +Eval (hcp-val): [67] Total time: 0:00:12 (0.2031 s / it) +Averaged stats (hcp-val): loss: 0.8310 (0.8323) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +Train: [68] [ 0/6250] eta: 7:33:55 lr: 0.000032 grad: 0.1673 (0.1673) loss: 0.8494 (0.8494) time: 4.3577 data: 4.1768 max mem: 9390 +Train: [68] [ 100/6250] eta: 0:18:36 lr: 0.000032 grad: 0.1032 (0.1141) loss: 0.8319 (0.8374) time: 0.1421 data: 0.0460 max mem: 9390 +Train: [68] [ 200/6250] eta: 0:16:06 lr: 0.000032 grad: 0.0935 (0.1088) loss: 0.8262 (0.8334) time: 0.1352 data: 0.0429 max mem: 9390 +Train: [68] [ 300/6250] eta: 0:14:55 lr: 0.000032 grad: 0.0891 (0.1055) loss: 0.8287 (0.8310) time: 0.1248 data: 0.0343 max mem: 9390 +Train: [68] [ 400/6250] eta: 0:13:59 lr: 0.000032 grad: 0.1085 (0.1050) loss: 0.8233 (0.8280) time: 0.1329 data: 0.0423 max mem: 9390 +Train: [68] [ 500/6250] eta: 0:13:14 lr: 0.000032 grad: 0.0985 (0.1052) loss: 0.8220 (0.8259) time: 0.1044 data: 0.0209 max mem: 9390 +Train: [68] [ 600/6250] eta: 0:12:42 lr: 0.000032 grad: 0.1059 (0.1051) loss: 0.8196 (0.8250) time: 0.1150 data: 0.0299 max mem: 9390 +Train: [68] [ 700/6250] eta: 0:12:19 lr: 0.000032 grad: 0.1002 (0.1054) loss: 0.8168 (0.8238) time: 0.1214 data: 0.0363 max mem: 9390 +Train: [68] [ 800/6250] eta: 0:11:53 lr: 0.000032 grad: 0.1020 (0.1056) loss: 0.8125 (0.8229) time: 0.1297 data: 0.0472 max mem: 9390 +Train: [68] [ 900/6250] eta: 0:11:38 lr: 0.000032 grad: 0.1094 (0.1057) loss: 0.8169 (0.8223) time: 0.1124 data: 0.0210 max mem: 9390 +Train: [68] [1000/6250] eta: 0:11:22 lr: 0.000032 grad: 0.1067 (0.1060) loss: 0.8135 (0.8218) time: 0.1187 data: 0.0364 max mem: 9390 +Train: [68] [1100/6250] eta: 0:11:15 lr: 0.000032 grad: 0.1055 (0.1062) loss: 0.8138 (0.8214) time: 0.1290 data: 0.0545 max mem: 9390 +Train: [68] [1200/6250] eta: 0:11:03 lr: 0.000032 grad: 0.1072 (0.1067) loss: 0.8139 (0.8208) time: 0.1096 data: 0.0309 max mem: 9390 +Train: [68] [1300/6250] eta: 0:10:48 lr: 0.000031 grad: 0.1066 (0.1070) loss: 0.8160 (0.8201) time: 0.1217 data: 0.0445 max mem: 9390 +Train: [68] [1400/6250] eta: 0:10:39 lr: 0.000031 grad: 0.1159 (0.1076) loss: 0.8092 (0.8195) time: 0.1865 data: 0.1046 max mem: 9390 +Train: [68] [1500/6250] eta: 0:10:27 lr: 0.000031 grad: 0.1122 (0.1080) loss: 0.8155 (0.8189) time: 0.1408 data: 0.0585 max mem: 9390 +Train: [68] [1600/6250] eta: 0:10:15 lr: 0.000031 grad: 0.1065 (0.1086) loss: 0.8107 (0.8182) time: 0.1409 data: 0.0643 max mem: 9390 +Train: [68] [1700/6250] eta: 0:10:00 lr: 0.000031 grad: 0.1214 (0.1090) loss: 0.8076 (0.8176) time: 0.1311 data: 0.0487 max mem: 9390 +Train: [68] [1800/6250] eta: 0:09:47 lr: 0.000031 grad: 0.1122 (0.1095) loss: 0.8055 (0.8171) time: 0.1528 data: 0.0715 max mem: 9390 +Train: [68] [1900/6250] eta: 0:09:34 lr: 0.000031 grad: 0.1134 (0.1097) loss: 0.8058 (0.8166) time: 0.1290 data: 0.0516 max mem: 9390 +Train: [68] [2000/6250] eta: 0:09:22 lr: 0.000031 grad: 0.1104 (0.1100) loss: 0.8058 (0.8162) time: 0.1225 data: 0.0428 max mem: 9390 +Train: [68] [2100/6250] eta: 0:09:08 lr: 0.000031 grad: 0.1191 (0.1103) loss: 0.8113 (0.8158) time: 0.1264 data: 0.0460 max mem: 9390 +Train: [68] [2200/6250] eta: 0:08:55 lr: 0.000031 grad: 0.1192 (0.1106) loss: 0.7963 (0.8154) time: 0.1328 data: 0.0544 max mem: 9390 +Train: [68] [2300/6250] eta: 0:08:41 lr: 0.000031 grad: 0.1177 (0.1110) loss: 0.8108 (0.8152) time: 0.1379 data: 0.0577 max mem: 9390 +Train: [68] [2400/6250] eta: 0:08:30 lr: 0.000031 grad: 0.1100 (0.1112) loss: 0.8060 (0.8149) time: 0.1382 data: 0.0521 max mem: 9390 +Train: [68] [2500/6250] eta: 0:08:19 lr: 0.000031 grad: 0.1106 (0.1113) loss: 0.8042 (0.8147) time: 0.1162 data: 0.0296 max mem: 9390 +Train: [68] [2600/6250] eta: 0:08:07 lr: 0.000031 grad: 0.1141 (0.1114) loss: 0.8081 (0.8146) time: 0.1227 data: 0.0430 max mem: 9390 +Train: [68] [2700/6250] eta: 0:07:55 lr: 0.000031 grad: 0.1146 (0.1116) loss: 0.8109 (0.8144) time: 0.1806 data: 0.0918 max mem: 9390 +Train: [68] [2800/6250] eta: 0:07:41 lr: 0.000031 grad: 0.1072 (0.1116) loss: 0.8122 (0.8143) time: 0.1108 data: 0.0321 max mem: 9390 +Train: [68] [2900/6250] eta: 0:07:30 lr: 0.000031 grad: 0.1119 (0.1117) loss: 0.8118 (0.8142) time: 0.1672 data: 0.0841 max mem: 9390 +Train: [68] [3000/6250] eta: 0:07:16 lr: 0.000031 grad: 0.1112 (0.1118) loss: 0.8151 (0.8142) time: 0.1326 data: 0.0495 max mem: 9390 +Train: [68] [3100/6250] eta: 0:07:03 lr: 0.000031 grad: 0.1087 (0.1118) loss: 0.8166 (0.8142) time: 0.1285 data: 0.0456 max mem: 9390 +Train: [68] [3200/6250] eta: 0:06:50 lr: 0.000031 grad: 0.1094 (0.1119) loss: 0.8177 (0.8142) time: 0.1482 data: 0.0672 max mem: 9390 +Train: [68] [3300/6250] eta: 0:06:38 lr: 0.000031 grad: 0.1144 (0.1119) loss: 0.8121 (0.8142) time: 0.1565 data: 0.0765 max mem: 9390 +Train: [68] [3400/6250] eta: 0:06:25 lr: 0.000031 grad: 0.1025 (0.1120) loss: 0.8142 (0.8142) time: 0.1491 data: 0.0754 max mem: 9390 +Train: [68] [3500/6250] eta: 0:06:12 lr: 0.000031 grad: 0.1133 (0.1119) loss: 0.8138 (0.8142) time: 0.1415 data: 0.0612 max mem: 9390 +Train: [68] [3600/6250] eta: 0:05:58 lr: 0.000031 grad: 0.1129 (0.1120) loss: 0.8095 (0.8141) time: 0.1256 data: 0.0466 max mem: 9390 +Train: [68] [3700/6250] eta: 0:05:45 lr: 0.000031 grad: 0.1141 (0.1120) loss: 0.8090 (0.8140) time: 0.1657 data: 0.0804 max mem: 9390 +Train: [68] [3800/6250] eta: 0:05:32 lr: 0.000031 grad: 0.1127 (0.1120) loss: 0.8122 (0.8140) time: 0.1357 data: 0.0511 max mem: 9390 +Train: [68] [3900/6250] eta: 0:05:20 lr: 0.000031 grad: 0.1150 (0.1121) loss: 0.8106 (0.8139) time: 0.1445 data: 0.0621 max mem: 9390 +Train: [68] [4000/6250] eta: 0:05:06 lr: 0.000031 grad: 0.1148 (0.1122) loss: 0.8002 (0.8137) time: 0.1407 data: 0.0619 max mem: 9390 +Train: [68] [4100/6250] eta: 0:04:53 lr: 0.000031 grad: 0.1093 (0.1123) loss: 0.8085 (0.8136) time: 0.1226 data: 0.0387 max mem: 9390 +Train: [68] [4200/6250] eta: 0:04:40 lr: 0.000031 grad: 0.1053 (0.1124) loss: 0.8128 (0.8135) time: 0.1501 data: 0.0614 max mem: 9390 +Train: [68] [4300/6250] eta: 0:04:26 lr: 0.000031 grad: 0.1145 (0.1124) loss: 0.8194 (0.8135) time: 0.1411 data: 0.0629 max mem: 9390 +Train: [68] [4400/6250] eta: 0:04:13 lr: 0.000031 grad: 0.1073 (0.1125) loss: 0.8121 (0.8134) time: 0.1421 data: 0.0606 max mem: 9390 +Train: [68] [4500/6250] eta: 0:04:00 lr: 0.000031 grad: 0.1111 (0.1125) loss: 0.8116 (0.8133) time: 0.1547 data: 0.0677 max mem: 9390 +Train: [68] [4600/6250] eta: 0:03:46 lr: 0.000031 grad: 0.1125 (0.1126) loss: 0.8073 (0.8133) time: 0.1398 data: 0.0507 max mem: 9390 +Train: [68] [4700/6250] eta: 0:03:33 lr: 0.000031 grad: 0.1191 (0.1126) loss: 0.8053 (0.8131) time: 0.1593 data: 0.0712 max mem: 9390 +Train: [68] [4800/6250] eta: 0:03:19 lr: 0.000030 grad: 0.1173 (0.1126) loss: 0.8071 (0.8130) time: 0.1551 data: 0.0736 max mem: 9390 +Train: [68] [4900/6250] eta: 0:03:06 lr: 0.000030 grad: 0.1113 (0.1127) loss: 0.8050 (0.8130) time: 0.1454 data: 0.0694 max mem: 9390 +Train: [68] [5000/6250] eta: 0:02:51 lr: 0.000030 grad: 0.1166 (0.1128) loss: 0.8108 (0.8129) time: 0.1134 data: 0.0315 max mem: 9390 +Train: [68] [5100/6250] eta: 0:02:37 lr: 0.000030 grad: 0.1134 (0.1129) loss: 0.8111 (0.8128) time: 0.1173 data: 0.0340 max mem: 9390 +Train: [68] [5200/6250] eta: 0:02:23 lr: 0.000030 grad: 0.1133 (0.1129) loss: 0.8124 (0.8128) time: 0.1118 data: 0.0285 max mem: 9390 +Train: [68] [5300/6250] eta: 0:02:09 lr: 0.000030 grad: 0.1190 (0.1130) loss: 0.8048 (0.8127) time: 0.1246 data: 0.0392 max mem: 9390 +Train: [68] [5400/6250] eta: 0:01:55 lr: 0.000030 grad: 0.1081 (0.1130) loss: 0.8145 (0.8127) time: 0.1209 data: 0.0445 max mem: 9390 +Train: [68] [5500/6250] eta: 0:01:41 lr: 0.000030 grad: 0.1096 (0.1130) loss: 0.8130 (0.8127) time: 0.1052 data: 0.0248 max mem: 9390 +Train: [68] [5600/6250] eta: 0:01:28 lr: 0.000030 grad: 0.1084 (0.1131) loss: 0.8074 (0.8126) time: 0.1326 data: 0.0500 max mem: 9390 +Train: [68] [5700/6250] eta: 0:01:14 lr: 0.000030 grad: 0.1150 (0.1131) loss: 0.8080 (0.8126) time: 0.1312 data: 0.0555 max mem: 9390 +Train: [68] [5800/6250] eta: 0:01:01 lr: 0.000030 grad: 0.1074 (0.1130) loss: 0.8119 (0.8127) time: 0.1271 data: 0.0513 max mem: 9390 +Train: [68] [5900/6250] eta: 0:00:47 lr: 0.000030 grad: 0.1173 (0.1130) loss: 0.8108 (0.8127) time: 0.1265 data: 0.0489 max mem: 9390 +Train: [68] [6000/6250] eta: 0:00:33 lr: 0.000030 grad: 0.1090 (0.1130) loss: 0.8142 (0.8127) time: 0.1388 data: 0.0638 max mem: 9390 +Train: [68] [6100/6250] eta: 0:00:20 lr: 0.000030 grad: 0.1106 (0.1130) loss: 0.8157 (0.8127) time: 0.1821 data: 0.0850 max mem: 9390 +Train: [68] [6200/6250] eta: 0:00:06 lr: 0.000030 grad: 0.1115 (0.1130) loss: 0.8190 (0.8127) time: 0.1464 data: 0.0670 max mem: 9390 +Train: [68] [6249/6250] eta: 0:00:00 lr: 0.000030 grad: 0.1168 (0.1131) loss: 0.8070 (0.8127) time: 0.1317 data: 0.0478 max mem: 9390 +Train: [68] Total time: 0:14:13 (0.1366 s / it) +Averaged stats: lr: 0.000030 grad: 0.1168 (0.1131) loss: 0.8070 (0.8127) +Eval (hcp-train-subset): [68] [ 0/62] eta: 0:05:25 loss: 0.8457 (0.8457) time: 5.2486 data: 5.2190 max mem: 9390 +Eval (hcp-train-subset): [68] [61/62] eta: 0:00:00 loss: 0.8307 (0.8309) time: 0.1317 data: 0.1068 max mem: 9390 +Eval (hcp-train-subset): [68] Total time: 0:00:12 (0.2090 s / it) +Averaged stats (hcp-train-subset): loss: 0.8307 (0.8309) +Eval (hcp-val): [68] [ 0/62] eta: 0:03:24 loss: 0.8295 (0.8295) time: 3.2983 data: 3.2074 max mem: 9390 +Eval (hcp-val): [68] [61/62] eta: 0:00:00 loss: 0.8309 (0.8325) time: 0.1013 data: 0.0763 max mem: 9390 +Eval (hcp-val): [68] Total time: 0:00:12 (0.1986 s / it) +Averaged stats (hcp-val): loss: 0.8309 (0.8325) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +Train: [69] [ 0/6250] eta: 8:55:53 lr: 0.000030 grad: 0.2333 (0.2333) loss: 0.8153 (0.8153) time: 5.1445 data: 5.0474 max mem: 9390 +Train: [69] [ 100/6250] eta: 0:18:30 lr: 0.000030 grad: 0.1140 (0.1366) loss: 0.8268 (0.8187) time: 0.1397 data: 0.0488 max mem: 9390 +Train: [69] [ 200/6250] eta: 0:16:11 lr: 0.000030 grad: 0.1049 (0.1270) loss: 0.8216 (0.8163) time: 0.1349 data: 0.0479 max mem: 9390 +Train: [69] [ 300/6250] eta: 0:14:51 lr: 0.000030 grad: 0.1076 (0.1212) loss: 0.8144 (0.8166) time: 0.1250 data: 0.0359 max mem: 9390 +Train: [69] [ 400/6250] eta: 0:14:06 lr: 0.000030 grad: 0.1054 (0.1173) loss: 0.8184 (0.8175) time: 0.1242 data: 0.0431 max mem: 9390 +Train: [69] [ 500/6250] eta: 0:13:19 lr: 0.000030 grad: 0.1031 (0.1150) loss: 0.8263 (0.8187) time: 0.1146 data: 0.0229 max mem: 9390 +Train: [69] [ 600/6250] eta: 0:12:47 lr: 0.000030 grad: 0.1032 (0.1146) loss: 0.8242 (0.8193) time: 0.1363 data: 0.0507 max mem: 9390 +Train: [69] [ 700/6250] eta: 0:12:16 lr: 0.000030 grad: 0.1065 (0.1140) loss: 0.8182 (0.8196) time: 0.1237 data: 0.0396 max mem: 9390 +Train: [69] [ 800/6250] eta: 0:11:50 lr: 0.000030 grad: 0.1017 (0.1134) loss: 0.8282 (0.8198) time: 0.1000 data: 0.0192 max mem: 9390 +Train: [69] [ 900/6250] eta: 0:11:33 lr: 0.000030 grad: 0.1091 (0.1128) loss: 0.8219 (0.8198) time: 0.1327 data: 0.0477 max mem: 9390 +Train: [69] [1000/6250] eta: 0:11:22 lr: 0.000030 grad: 0.1049 (0.1123) loss: 0.8180 (0.8200) time: 0.1087 data: 0.0215 max mem: 9390 +Train: [69] [1100/6250] eta: 0:11:10 lr: 0.000030 grad: 0.1076 (0.1119) loss: 0.8165 (0.8200) time: 0.1320 data: 0.0430 max mem: 9390 +Train: [69] [1200/6250] eta: 0:10:59 lr: 0.000030 grad: 0.1115 (0.1116) loss: 0.8188 (0.8200) time: 0.1523 data: 0.0663 max mem: 9390 +Train: [69] [1300/6250] eta: 0:10:45 lr: 0.000030 grad: 0.1070 (0.1115) loss: 0.8189 (0.8199) time: 0.1243 data: 0.0382 max mem: 9390 +Train: [69] [1400/6250] eta: 0:10:35 lr: 0.000030 grad: 0.1077 (0.1114) loss: 0.8210 (0.8198) time: 0.1582 data: 0.0701 max mem: 9390 +Train: [69] [1500/6250] eta: 0:10:22 lr: 0.000030 grad: 0.1064 (0.1111) loss: 0.8167 (0.8196) time: 0.1433 data: 0.0591 max mem: 9390 +Train: [69] [1600/6250] eta: 0:10:10 lr: 0.000030 grad: 0.1121 (0.1111) loss: 0.8111 (0.8193) time: 0.1355 data: 0.0574 max mem: 9390 +Train: [69] [1700/6250] eta: 0:09:58 lr: 0.000030 grad: 0.1104 (0.1111) loss: 0.8180 (0.8191) time: 0.1374 data: 0.0581 max mem: 9390 +Train: [69] [1800/6250] eta: 0:09:45 lr: 0.000030 grad: 0.1018 (0.1109) loss: 0.8197 (0.8189) time: 0.1429 data: 0.0646 max mem: 9390 +Train: [69] [1900/6250] eta: 0:09:33 lr: 0.000030 grad: 0.1077 (0.1108) loss: 0.8169 (0.8187) time: 0.1244 data: 0.0466 max mem: 9390 +Train: [69] [2000/6250] eta: 0:09:19 lr: 0.000030 grad: 0.1097 (0.1109) loss: 0.8124 (0.8184) time: 0.1356 data: 0.0607 max mem: 9390 +Train: [69] [2100/6250] eta: 0:09:05 lr: 0.000029 grad: 0.1055 (0.1108) loss: 0.8172 (0.8183) time: 0.1395 data: 0.0647 max mem: 9390 +Train: [69] [2200/6250] eta: 0:08:53 lr: 0.000029 grad: 0.1101 (0.1107) loss: 0.8163 (0.8182) time: 0.1237 data: 0.0407 max mem: 9390 +Train: [69] [2300/6250] eta: 0:08:41 lr: 0.000029 grad: 0.1067 (0.1107) loss: 0.8170 (0.8182) time: 0.1311 data: 0.0557 max mem: 9390 +Train: [69] [2400/6250] eta: 0:08:27 lr: 0.000029 grad: 0.1040 (0.1107) loss: 0.8166 (0.8180) time: 0.1154 data: 0.0375 max mem: 9390 +Train: [69] [2500/6250] eta: 0:08:13 lr: 0.000029 grad: 0.1069 (0.1106) loss: 0.8168 (0.8180) time: 0.1234 data: 0.0435 max mem: 9390 +Train: [69] [2600/6250] eta: 0:08:03 lr: 0.000029 grad: 0.1083 (0.1105) loss: 0.8182 (0.8179) time: 0.1851 data: 0.0621 max mem: 9390 +Train: [69] [2700/6250] eta: 0:07:50 lr: 0.000029 grad: 0.1025 (0.1104) loss: 0.8178 (0.8180) time: 0.1159 data: 0.0393 max mem: 9390 +Train: [69] [2800/6250] eta: 0:07:37 lr: 0.000029 grad: 0.1015 (0.1103) loss: 0.8165 (0.8180) time: 0.1356 data: 0.0548 max mem: 9390 +Train: [69] [2900/6250] eta: 0:07:24 lr: 0.000029 grad: 0.1052 (0.1103) loss: 0.8182 (0.8179) time: 0.1272 data: 0.0498 max mem: 9390 +Train: [69] [3000/6250] eta: 0:07:11 lr: 0.000029 grad: 0.1082 (0.1102) loss: 0.8112 (0.8178) time: 0.1292 data: 0.0536 max mem: 9390 +Train: [69] [3100/6250] eta: 0:06:59 lr: 0.000029 grad: 0.1033 (0.1102) loss: 0.8171 (0.8178) time: 0.1519 data: 0.0701 max mem: 9390 +Train: [69] [3200/6250] eta: 0:06:48 lr: 0.000029 grad: 0.1055 (0.1101) loss: 0.8208 (0.8179) time: 0.1484 data: 0.0660 max mem: 9390 +Train: [69] [3300/6250] eta: 0:06:35 lr: 0.000029 grad: 0.1077 (0.1101) loss: 0.8194 (0.8179) time: 0.1409 data: 0.0662 max mem: 9390 +Train: [69] [3400/6250] eta: 0:06:22 lr: 0.000029 grad: 0.1085 (0.1102) loss: 0.8161 (0.8179) time: 0.1381 data: 0.0623 max mem: 9390 +Train: [69] [3500/6250] eta: 0:06:09 lr: 0.000029 grad: 0.1125 (0.1102) loss: 0.8185 (0.8179) time: 0.1656 data: 0.0692 max mem: 9390 +Train: [69] [3600/6250] eta: 0:05:57 lr: 0.000029 grad: 0.1053 (0.1102) loss: 0.8181 (0.8178) time: 0.1372 data: 0.0572 max mem: 9390 +Train: [69] [3700/6250] eta: 0:05:45 lr: 0.000029 grad: 0.1055 (0.1102) loss: 0.8208 (0.8177) time: 0.1373 data: 0.0452 max mem: 9390 +Train: [69] [3800/6250] eta: 0:05:32 lr: 0.000029 grad: 0.1122 (0.1103) loss: 0.8113 (0.8177) time: 0.1651 data: 0.0875 max mem: 9390 +Train: [69] [3900/6250] eta: 0:05:19 lr: 0.000029 grad: 0.1184 (0.1105) loss: 0.8096 (0.8176) time: 0.1362 data: 0.0544 max mem: 9390 +Train: [69] [4000/6250] eta: 0:05:05 lr: 0.000029 grad: 0.1084 (0.1105) loss: 0.8166 (0.8175) time: 0.1546 data: 0.0773 max mem: 9390 +Train: [69] [4100/6250] eta: 0:04:51 lr: 0.000029 grad: 0.1137 (0.1107) loss: 0.8132 (0.8174) time: 0.1300 data: 0.0542 max mem: 9390 +Train: [69] [4200/6250] eta: 0:04:38 lr: 0.000029 grad: 0.1096 (0.1108) loss: 0.8120 (0.8174) time: 0.1388 data: 0.0549 max mem: 9390 +Train: [69] [4300/6250] eta: 0:04:24 lr: 0.000029 grad: 0.1053 (0.1108) loss: 0.8096 (0.8173) time: 0.1366 data: 0.0559 max mem: 9390 +Train: [69] [4400/6250] eta: 0:04:11 lr: 0.000029 grad: 0.1077 (0.1110) loss: 0.8189 (0.8173) time: 0.1762 data: 0.1012 max mem: 9390 +Train: [69] [4500/6250] eta: 0:03:58 lr: 0.000029 grad: 0.1189 (0.1111) loss: 0.8153 (0.8172) time: 0.1896 data: 0.1015 max mem: 9390 +Train: [69] [4600/6250] eta: 0:03:44 lr: 0.000029 grad: 0.1155 (0.1112) loss: 0.8226 (0.8172) time: 0.1387 data: 0.0580 max mem: 9390 +Train: [69] [4700/6250] eta: 0:03:31 lr: 0.000029 grad: 0.1153 (0.1112) loss: 0.8122 (0.8172) time: 0.1322 data: 0.0593 max mem: 9390 +Train: [69] [4800/6250] eta: 0:03:18 lr: 0.000029 grad: 0.1126 (0.1113) loss: 0.8152 (0.8172) time: 0.1524 data: 0.0765 max mem: 9390 +Train: [69] [4900/6250] eta: 0:03:04 lr: 0.000029 grad: 0.1108 (0.1114) loss: 0.8186 (0.8172) time: 0.1465 data: 0.0678 max mem: 9390 +Train: [69] [5000/6250] eta: 0:02:51 lr: 0.000029 grad: 0.1108 (0.1114) loss: 0.8177 (0.8172) time: 0.1474 data: 0.0702 max mem: 9390 +Train: [69] [5100/6250] eta: 0:02:37 lr: 0.000029 grad: 0.1118 (0.1114) loss: 0.8188 (0.8172) time: 0.1375 data: 0.0577 max mem: 9390 +Train: [69] [5200/6250] eta: 0:02:23 lr: 0.000029 grad: 0.1110 (0.1115) loss: 0.8173 (0.8172) time: 0.1180 data: 0.0273 max mem: 9390 +Train: [69] [5300/6250] eta: 0:02:09 lr: 0.000029 grad: 0.1082 (0.1116) loss: 0.8139 (0.8172) time: 0.0965 data: 0.0002 max mem: 9390 +Train: [69] [5400/6250] eta: 0:01:56 lr: 0.000029 grad: 0.1183 (0.1117) loss: 0.8103 (0.8172) time: 0.1236 data: 0.0355 max mem: 9390 +Train: [69] [5500/6250] eta: 0:01:42 lr: 0.000029 grad: 0.1198 (0.1117) loss: 0.8136 (0.8171) time: 0.1487 data: 0.0671 max mem: 9390 +Train: [69] [5600/6250] eta: 0:01:28 lr: 0.000028 grad: 0.1190 (0.1118) loss: 0.8064 (0.8170) time: 0.1356 data: 0.0542 max mem: 9390 +Train: [69] [5700/6250] eta: 0:01:15 lr: 0.000028 grad: 0.1105 (0.1119) loss: 0.8160 (0.8170) time: 0.1517 data: 0.0760 max mem: 9390 +Train: [69] [5800/6250] eta: 0:01:01 lr: 0.000028 grad: 0.1117 (0.1120) loss: 0.8175 (0.8170) time: 0.1156 data: 0.0387 max mem: 9390 +Train: [69] [5900/6250] eta: 0:00:47 lr: 0.000028 grad: 0.1146 (0.1121) loss: 0.8103 (0.8169) time: 0.1446 data: 0.0671 max mem: 9390 +Train: [69] [6000/6250] eta: 0:00:34 lr: 0.000028 grad: 0.1149 (0.1122) loss: 0.8133 (0.8168) time: 0.1489 data: 0.0694 max mem: 9390 +Train: [69] [6100/6250] eta: 0:00:20 lr: 0.000028 grad: 0.1113 (0.1122) loss: 0.8075 (0.8167) time: 0.1096 data: 0.0298 max mem: 9390 +Train: [69] [6200/6250] eta: 0:00:06 lr: 0.000028 grad: 0.1080 (0.1123) loss: 0.8160 (0.8166) time: 0.1495 data: 0.0716 max mem: 9390 +Train: [69] [6249/6250] eta: 0:00:00 lr: 0.000028 grad: 0.1064 (0.1123) loss: 0.8163 (0.8166) time: 0.1379 data: 0.0605 max mem: 9390 +Train: [69] Total time: 0:14:17 (0.1372 s / it) +Averaged stats: lr: 0.000028 grad: 0.1064 (0.1123) loss: 0.8163 (0.8166) +Eval (hcp-train-subset): [69] [ 0/62] eta: 0:05:15 loss: 0.8446 (0.8446) time: 5.0913 data: 5.0603 max mem: 9390 +Eval (hcp-train-subset): [69] [61/62] eta: 0:00:00 loss: 0.8268 (0.8295) time: 0.1414 data: 0.1146 max mem: 9390 +Eval (hcp-train-subset): [69] Total time: 0:00:14 (0.2267 s / it) +Averaged stats (hcp-train-subset): loss: 0.8268 (0.8295) +Making plots (hcp-train-subset): example=45 +Eval (hcp-val): [69] [ 0/62] eta: 0:03:32 loss: 0.8297 (0.8297) time: 3.4287 data: 3.3370 max mem: 9390 +Eval (hcp-val): [69] [61/62] eta: 0:00:00 loss: 0.8305 (0.8322) time: 0.1199 data: 0.0953 max mem: 9390 +Eval (hcp-val): [69] Total time: 0:00:12 (0.1973 s / it) +Averaged stats (hcp-val): loss: 0.8305 (0.8322) +Making plots (hcp-val): example=8 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +Train: [70] [ 0/6250] eta: 8:34:44 lr: 0.000028 grad: 0.0843 (0.0843) loss: 0.8351 (0.8351) time: 4.9415 data: 4.7754 max mem: 9390 +Train: [70] [ 100/6250] eta: 0:19:07 lr: 0.000028 grad: 0.1062 (0.1222) loss: 0.8211 (0.8314) time: 0.1345 data: 0.0428 max mem: 9390 +Train: [70] [ 200/6250] eta: 0:16:13 lr: 0.000028 grad: 0.1036 (0.1169) loss: 0.8159 (0.8269) time: 0.1437 data: 0.0521 max mem: 9390 +Train: [70] [ 300/6250] eta: 0:14:51 lr: 0.000028 grad: 0.1071 (0.1157) loss: 0.8228 (0.8250) time: 0.1047 data: 0.0124 max mem: 9390 +Train: [70] [ 400/6250] eta: 0:13:59 lr: 0.000028 grad: 0.1041 (0.1149) loss: 0.8124 (0.8224) time: 0.1224 data: 0.0390 max mem: 9390 +Train: [70] [ 500/6250] eta: 0:13:20 lr: 0.000028 grad: 0.1068 (0.1140) loss: 0.8245 (0.8213) time: 0.1412 data: 0.0545 max mem: 9390 +Train: [70] [ 600/6250] eta: 0:12:44 lr: 0.000028 grad: 0.1081 (0.1133) loss: 0.8199 (0.8211) time: 0.1083 data: 0.0193 max mem: 9390 +Train: [70] [ 700/6250] eta: 0:12:20 lr: 0.000028 grad: 0.1071 (0.1134) loss: 0.8150 (0.8211) time: 0.1180 data: 0.0302 max mem: 9390 +Train: [70] [ 800/6250] eta: 0:11:58 lr: 0.000028 grad: 0.1000 (0.1130) loss: 0.8265 (0.8209) time: 0.1178 data: 0.0306 max mem: 9390 +Train: [70] [ 900/6250] eta: 0:11:45 lr: 0.000028 grad: 0.0990 (0.1129) loss: 0.8282 (0.8207) time: 0.1501 data: 0.0686 max mem: 9390 +Train: [70] [1000/6250] eta: 0:11:28 lr: 0.000028 grad: 0.1053 (0.1126) loss: 0.8146 (0.8202) time: 0.1298 data: 0.0453 max mem: 9390 +Train: [70] [1100/6250] eta: 0:11:19 lr: 0.000028 grad: 0.1092 (0.1124) loss: 0.8167 (0.8198) time: 0.1546 data: 0.0768 max mem: 9390 +Train: [70] [1200/6250] eta: 0:11:03 lr: 0.000028 grad: 0.1132 (0.1123) loss: 0.8153 (0.8194) time: 0.1208 data: 0.0404 max mem: 9390 +Train: [70] [1300/6250] eta: 0:10:52 lr: 0.000028 grad: 0.1101 (0.1123) loss: 0.8143 (0.8190) time: 0.1414 data: 0.0644 max mem: 9390 +Train: [70] [1400/6250] eta: 0:10:38 lr: 0.000028 grad: 0.1123 (0.1123) loss: 0.8119 (0.8186) time: 0.1325 data: 0.0570 max mem: 9390 +Train: [70] [1500/6250] eta: 0:10:23 lr: 0.000028 grad: 0.1193 (0.1126) loss: 0.8110 (0.8182) time: 0.1357 data: 0.0606 max mem: 9390 +Train: [70] [1600/6250] eta: 0:10:11 lr: 0.000028 grad: 0.1132 (0.1129) loss: 0.8127 (0.8179) time: 0.1291 data: 0.0454 max mem: 9390 +Train: [70] [1700/6250] eta: 0:10:00 lr: 0.000028 grad: 0.1147 (0.1130) loss: 0.8039 (0.8176) time: 0.0990 data: 0.0205 max mem: 9390 +Train: [70] [1800/6250] eta: 0:09:46 lr: 0.000028 grad: 0.1204 (0.1131) loss: 0.8089 (0.8173) time: 0.1254 data: 0.0444 max mem: 9390 +Train: [70] [1900/6250] eta: 0:09:32 lr: 0.000028 grad: 0.1118 (0.1133) loss: 0.8153 (0.8170) time: 0.1358 data: 0.0579 max mem: 9390 +Train: [70] [2000/6250] eta: 0:09:19 lr: 0.000028 grad: 0.1072 (0.1133) loss: 0.8094 (0.8168) time: 0.1291 data: 0.0511 max mem: 9390 +Train: [70] [2100/6250] eta: 0:09:04 lr: 0.000028 grad: 0.1090 (0.1133) loss: 0.8173 (0.8166) time: 0.1345 data: 0.0627 max mem: 9390 +Train: [70] [2200/6250] eta: 0:08:53 lr: 0.000028 grad: 0.1105 (0.1134) loss: 0.8063 (0.8164) time: 0.1445 data: 0.0685 max mem: 9390 +Train: [70] [2300/6250] eta: 0:08:42 lr: 0.000028 grad: 0.1049 (0.1135) loss: 0.8164 (0.8162) time: 0.1613 data: 0.0824 max mem: 9390 +Train: [70] [2400/6250] eta: 0:08:30 lr: 0.000028 grad: 0.1116 (0.1135) loss: 0.8107 (0.8161) time: 0.1582 data: 0.0852 max mem: 9390 +Train: [70] [2500/6250] eta: 0:08:16 lr: 0.000028 grad: 0.1006 (0.1135) loss: 0.8174 (0.8160) time: 0.1344 data: 0.0591 max mem: 9390 +Train: [70] [2600/6250] eta: 0:08:04 lr: 0.000028 grad: 0.1071 (0.1134) loss: 0.8177 (0.8159) time: 0.1559 data: 0.0771 max mem: 9390 +Train: [70] [2700/6250] eta: 0:07:51 lr: 0.000028 grad: 0.1087 (0.1133) loss: 0.8180 (0.8158) time: 0.1386 data: 0.0638 max mem: 9390 +Train: [70] [2800/6250] eta: 0:07:38 lr: 0.000028 grad: 0.1132 (0.1133) loss: 0.8144 (0.8158) time: 0.1407 data: 0.0635 max mem: 9390 +Train: [70] [2900/6250] eta: 0:07:25 lr: 0.000028 grad: 0.1077 (0.1132) loss: 0.8109 (0.8157) time: 0.1578 data: 0.0693 max mem: 9390 +Train: [70] [3000/6250] eta: 0:07:12 lr: 0.000027 grad: 0.1095 (0.1133) loss: 0.8137 (0.8156) time: 0.1205 data: 0.0411 max mem: 9390 +Train: [70] [3100/6250] eta: 0:06:59 lr: 0.000027 grad: 0.1181 (0.1136) loss: 0.8088 (0.8154) time: 0.1479 data: 0.0664 max mem: 9390 +Train: [70] [3200/6250] eta: 0:06:45 lr: 0.000027 grad: 0.1148 (0.1138) loss: 0.8139 (0.8153) time: 0.1236 data: 0.0497 max mem: 9390 +Train: [70] [3300/6250] eta: 0:06:31 lr: 0.000027 grad: 0.1058 (0.1139) loss: 0.8182 (0.8153) time: 0.1238 data: 0.0444 max mem: 9390 +Train: [70] [3400/6250] eta: 0:06:18 lr: 0.000027 grad: 0.1176 (0.1140) loss: 0.8091 (0.8152) time: 0.1683 data: 0.0897 max mem: 9390 +Train: [70] [3500/6250] eta: 0:06:04 lr: 0.000027 grad: 0.1089 (0.1141) loss: 0.8147 (0.8151) time: 0.1200 data: 0.0365 max mem: 9390 +Train: [70] [3600/6250] eta: 0:05:51 lr: 0.000027 grad: 0.1131 (0.1141) loss: 0.8125 (0.8150) time: 0.1315 data: 0.0502 max mem: 9390 +Train: [70] [3700/6250] eta: 0:05:37 lr: 0.000027 grad: 0.1170 (0.1143) loss: 0.8030 (0.8149) time: 0.1218 data: 0.0425 max mem: 9390 +Train: [70] [3800/6250] eta: 0:05:25 lr: 0.000027 grad: 0.1131 (0.1143) loss: 0.8155 (0.8148) time: 0.1503 data: 0.0580 max mem: 9390 +Train: [70] [3900/6250] eta: 0:05:12 lr: 0.000027 grad: 0.1081 (0.1144) loss: 0.8117 (0.8147) time: 0.1404 data: 0.0650 max mem: 9390 +Train: [70] [4000/6250] eta: 0:04:59 lr: 0.000027 grad: 0.1155 (0.1145) loss: 0.8142 (0.8146) time: 0.1457 data: 0.0654 max mem: 9390 +Train: [70] [4100/6250] eta: 0:04:46 lr: 0.000027 grad: 0.1128 (0.1146) loss: 0.8128 (0.8146) time: 0.1350 data: 0.0584 max mem: 9390 +Train: [70] [4200/6250] eta: 0:04:32 lr: 0.000027 grad: 0.1157 (0.1146) loss: 0.8085 (0.8146) time: 0.1164 data: 0.0287 max mem: 9390 +Train: [70] [4300/6250] eta: 0:04:19 lr: 0.000027 grad: 0.1184 (0.1146) loss: 0.8145 (0.8146) time: 0.1235 data: 0.0438 max mem: 9390 +Train: [70] [4400/6250] eta: 0:04:06 lr: 0.000027 grad: 0.1158 (0.1146) loss: 0.8132 (0.8146) time: 0.1336 data: 0.0579 max mem: 9390 +Train: [70] [4500/6250] eta: 0:03:54 lr: 0.000027 grad: 0.1206 (0.1147) loss: 0.8112 (0.8145) time: 0.1559 data: 0.0699 max mem: 9390 +Train: [70] [4600/6250] eta: 0:03:41 lr: 0.000027 grad: 0.1138 (0.1148) loss: 0.8118 (0.8145) time: 0.1286 data: 0.0529 max mem: 9390 +Train: [70] [4700/6250] eta: 0:03:28 lr: 0.000027 grad: 0.1156 (0.1149) loss: 0.8092 (0.8144) time: 0.1435 data: 0.0697 max mem: 9390 +Train: [70] [4800/6250] eta: 0:03:15 lr: 0.000027 grad: 0.1113 (0.1149) loss: 0.8162 (0.8144) time: 0.1230 data: 0.0433 max mem: 9390 +Train: [70] [4900/6250] eta: 0:03:01 lr: 0.000027 grad: 0.1115 (0.1150) loss: 0.8129 (0.8143) time: 0.1465 data: 0.0648 max mem: 9390 +Train: [70] [5000/6250] eta: 0:02:48 lr: 0.000027 grad: 0.1152 (0.1151) loss: 0.8129 (0.8143) time: 0.1438 data: 0.0691 max mem: 9390 +Train: [70] [5100/6250] eta: 0:02:34 lr: 0.000027 grad: 0.1151 (0.1151) loss: 0.8133 (0.8142) time: 0.1129 data: 0.0401 max mem: 9390 +Train: [70] [5200/6250] eta: 0:02:21 lr: 0.000027 grad: 0.1118 (0.1152) loss: 0.8065 (0.8142) time: 0.1305 data: 0.0435 max mem: 9390 +Train: [70] [5300/6250] eta: 0:02:07 lr: 0.000027 grad: 0.1168 (0.1152) loss: 0.8094 (0.8141) time: 0.1276 data: 0.0393 max mem: 9390 +Train: [70] [5400/6250] eta: 0:01:54 lr: 0.000027 grad: 0.1178 (0.1154) loss: 0.8101 (0.8141) time: 0.1432 data: 0.0629 max mem: 9390 +Train: [70] [5500/6250] eta: 0:01:40 lr: 0.000027 grad: 0.1114 (0.1155) loss: 0.8195 (0.8141) time: 0.1231 data: 0.0437 max mem: 9390 +Train: [70] [5600/6250] eta: 0:01:26 lr: 0.000027 grad: 0.1130 (0.1155) loss: 0.8126 (0.8141) time: 0.1432 data: 0.0634 max mem: 9390 +Train: [70] [5700/6250] eta: 0:01:13 lr: 0.000027 grad: 0.1226 (0.1156) loss: 0.8058 (0.8141) time: 0.1261 data: 0.0477 max mem: 9390 +Train: [70] [5800/6250] eta: 0:01:00 lr: 0.000027 grad: 0.1135 (0.1157) loss: 0.8098 (0.8140) time: 0.1346 data: 0.0551 max mem: 9390 +Train: [70] [5900/6250] eta: 0:00:46 lr: 0.000027 grad: 0.1217 (0.1158) loss: 0.8047 (0.8140) time: 0.1063 data: 0.0251 max mem: 9390 +Train: [70] [6000/6250] eta: 0:00:33 lr: 0.000027 grad: 0.1132 (0.1159) loss: 0.8172 (0.8139) time: 0.1235 data: 0.0431 max mem: 9390 +Train: [70] [6100/6250] eta: 0:00:20 lr: 0.000027 grad: 0.1131 (0.1160) loss: 0.8188 (0.8138) time: 0.1291 data: 0.0493 max mem: 9390 +Train: [70] [6200/6250] eta: 0:00:06 lr: 0.000027 grad: 0.1113 (0.1161) loss: 0.8156 (0.8138) time: 0.1607 data: 0.0667 max mem: 9390 +Train: [70] [6249/6250] eta: 0:00:00 lr: 0.000027 grad: 0.1153 (0.1161) loss: 0.8146 (0.8138) time: 0.1473 data: 0.0672 max mem: 9390 +Train: [70] Total time: 0:14:02 (0.1348 s / it) +Averaged stats: lr: 0.000027 grad: 0.1153 (0.1161) loss: 0.8146 (0.8138) +Eval (hcp-train-subset): [70] [ 0/62] eta: 0:04:25 loss: 0.8410 (0.8410) time: 4.2758 data: 4.2034 max mem: 9390 +Eval (hcp-train-subset): [70] [61/62] eta: 0:00:00 loss: 0.8283 (0.8286) time: 0.1302 data: 0.1052 max mem: 9390 +Eval (hcp-train-subset): [70] Total time: 0:00:12 (0.2083 s / it) +Averaged stats (hcp-train-subset): loss: 0.8283 (0.8286) +Eval (hcp-val): [70] [ 0/62] eta: 0:04:25 loss: 0.8281 (0.8281) time: 4.2813 data: 4.2266 max mem: 9390 +Eval (hcp-val): [70] [61/62] eta: 0:00:00 loss: 0.8305 (0.8316) time: 0.1240 data: 0.0992 max mem: 9390 +Eval (hcp-val): [70] Total time: 0:00:12 (0.1960 s / it) +Averaged stats (hcp-val): loss: 0.8305 (0.8316) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +Train: [71] [ 0/6250] eta: 9:00:13 lr: 0.000027 grad: 0.2474 (0.2474) loss: 0.8656 (0.8656) time: 5.1862 data: 5.0769 max mem: 9390 +Train: [71] [ 100/6250] eta: 0:19:04 lr: 0.000027 grad: 0.1122 (0.1217) loss: 0.8261 (0.8355) time: 0.1413 data: 0.0527 max mem: 9390 +Train: [71] [ 200/6250] eta: 0:16:22 lr: 0.000027 grad: 0.1056 (0.1192) loss: 0.8218 (0.8287) time: 0.1458 data: 0.0547 max mem: 9390 +Train: [71] [ 300/6250] eta: 0:15:07 lr: 0.000027 grad: 0.1065 (0.1173) loss: 0.8259 (0.8265) time: 0.1474 data: 0.0607 max mem: 9390 +Train: [71] [ 400/6250] eta: 0:14:14 lr: 0.000026 grad: 0.1073 (0.1170) loss: 0.8238 (0.8249) time: 0.1378 data: 0.0543 max mem: 9390 +Train: [71] [ 500/6250] eta: 0:13:33 lr: 0.000026 grad: 0.1208 (0.1175) loss: 0.8204 (0.8235) time: 0.1218 data: 0.0361 max mem: 9390 +Train: [71] [ 600/6250] eta: 0:13:02 lr: 0.000026 grad: 0.1135 (0.1180) loss: 0.8212 (0.8227) time: 0.1280 data: 0.0442 max mem: 9390 +Train: [71] [ 700/6250] eta: 0:12:32 lr: 0.000026 grad: 0.1127 (0.1186) loss: 0.8197 (0.8218) time: 0.1109 data: 0.0273 max mem: 9390 +Train: [71] [ 800/6250] eta: 0:12:07 lr: 0.000026 grad: 0.1137 (0.1184) loss: 0.8178 (0.8211) time: 0.1237 data: 0.0412 max mem: 9390 +Train: [71] [ 900/6250] eta: 0:11:46 lr: 0.000026 grad: 0.1065 (0.1175) loss: 0.8210 (0.8209) time: 0.1112 data: 0.0252 max mem: 9390 +Train: [71] [1000/6250] eta: 0:11:23 lr: 0.000026 grad: 0.1107 (0.1172) loss: 0.8189 (0.8208) time: 0.0987 data: 0.0071 max mem: 9390 +Train: [71] [1100/6250] eta: 0:11:05 lr: 0.000026 grad: 0.1134 (0.1170) loss: 0.8140 (0.8204) time: 0.1109 data: 0.0297 max mem: 9390 +Train: [71] [1200/6250] eta: 0:10:50 lr: 0.000026 grad: 0.1046 (0.1164) loss: 0.8256 (0.8203) time: 0.1133 data: 0.0326 max mem: 9390 +Train: [71] [1300/6250] eta: 0:10:36 lr: 0.000026 grad: 0.1075 (0.1159) loss: 0.8250 (0.8202) time: 0.1159 data: 0.0340 max mem: 9390 +Train: [71] [1400/6250] eta: 0:10:26 lr: 0.000026 grad: 0.1074 (0.1155) loss: 0.8172 (0.8201) time: 0.1411 data: 0.0596 max mem: 9390 +Train: [71] [1500/6250] eta: 0:10:14 lr: 0.000026 grad: 0.1075 (0.1152) loss: 0.8220 (0.8201) time: 0.1105 data: 0.0184 max mem: 9390 +Train: [71] [1600/6250] eta: 0:10:01 lr: 0.000026 grad: 0.1063 (0.1148) loss: 0.8189 (0.8200) time: 0.1247 data: 0.0480 max mem: 9390 +Train: [71] [1700/6250] eta: 0:09:47 lr: 0.000026 grad: 0.1077 (0.1148) loss: 0.8209 (0.8199) time: 0.1300 data: 0.0467 max mem: 9390 +Train: [71] [1800/6250] eta: 0:09:35 lr: 0.000026 grad: 0.1046 (0.1146) loss: 0.8200 (0.8198) time: 0.1382 data: 0.0603 max mem: 9390 +Train: [71] [1900/6250] eta: 0:09:24 lr: 0.000026 grad: 0.1124 (0.1147) loss: 0.8168 (0.8197) time: 0.1295 data: 0.0509 max mem: 9390 +Train: [71] [2000/6250] eta: 0:09:13 lr: 0.000026 grad: 0.1070 (0.1145) loss: 0.8203 (0.8197) time: 0.1291 data: 0.0533 max mem: 9390 +Train: [71] [2100/6250] eta: 0:09:07 lr: 0.000026 grad: 0.1125 (0.1144) loss: 0.8201 (0.8196) time: 0.2336 data: 0.1509 max mem: 9390 +Train: [71] [2200/6250] eta: 0:08:55 lr: 0.000026 grad: 0.1107 (0.1145) loss: 0.8125 (0.8194) time: 0.1689 data: 0.0872 max mem: 9390 +Train: [71] [2300/6250] eta: 0:08:44 lr: 0.000026 grad: 0.1137 (0.1145) loss: 0.8141 (0.8192) time: 0.1194 data: 0.0381 max mem: 9390 +Train: [71] [2400/6250] eta: 0:08:32 lr: 0.000026 grad: 0.1163 (0.1145) loss: 0.8143 (0.8191) time: 0.1524 data: 0.0748 max mem: 9390 +Train: [71] [2500/6250] eta: 0:08:19 lr: 0.000026 grad: 0.1167 (0.1147) loss: 0.8129 (0.8188) time: 0.1272 data: 0.0417 max mem: 9390 +Train: [71] [2600/6250] eta: 0:08:06 lr: 0.000026 grad: 0.1227 (0.1149) loss: 0.8152 (0.8187) time: 0.1330 data: 0.0546 max mem: 9390 +Train: [71] [2700/6250] eta: 0:07:52 lr: 0.000026 grad: 0.1096 (0.1150) loss: 0.8223 (0.8185) time: 0.1310 data: 0.0492 max mem: 9390 +Train: [71] [2800/6250] eta: 0:07:40 lr: 0.000026 grad: 0.1150 (0.1151) loss: 0.8129 (0.8183) time: 0.1440 data: 0.0589 max mem: 9390 +Train: [71] [2900/6250] eta: 0:07:28 lr: 0.000026 grad: 0.1113 (0.1153) loss: 0.8188 (0.8181) time: 0.1129 data: 0.0292 max mem: 9390 +Train: [71] [3000/6250] eta: 0:07:16 lr: 0.000026 grad: 0.1159 (0.1155) loss: 0.8101 (0.8178) time: 0.1722 data: 0.0898 max mem: 9390 +Train: [71] [3100/6250] eta: 0:07:04 lr: 0.000026 grad: 0.1167 (0.1158) loss: 0.8143 (0.8176) time: 0.1269 data: 0.0449 max mem: 9390 +Train: [71] [3200/6250] eta: 0:06:52 lr: 0.000026 grad: 0.1168 (0.1160) loss: 0.8088 (0.8173) time: 0.1580 data: 0.0819 max mem: 9390 +Train: [71] [3300/6250] eta: 0:06:40 lr: 0.000026 grad: 0.1130 (0.1162) loss: 0.8098 (0.8170) time: 0.1445 data: 0.0657 max mem: 9390 +Train: [71] [3400/6250] eta: 0:06:27 lr: 0.000026 grad: 0.1157 (0.1163) loss: 0.8035 (0.8167) time: 0.1304 data: 0.0524 max mem: 9390 +Train: [71] [3500/6250] eta: 0:06:14 lr: 0.000026 grad: 0.1290 (0.1165) loss: 0.8055 (0.8165) time: 0.1262 data: 0.0430 max mem: 9390 +Train: [71] [3600/6250] eta: 0:06:01 lr: 0.000026 grad: 0.1247 (0.1167) loss: 0.8130 (0.8163) time: 0.1817 data: 0.0977 max mem: 9390 +Train: [71] [3700/6250] eta: 0:05:47 lr: 0.000026 grad: 0.1182 (0.1169) loss: 0.8050 (0.8161) time: 0.1298 data: 0.0575 max mem: 9390 +Train: [71] [3800/6250] eta: 0:05:34 lr: 0.000026 grad: 0.1139 (0.1169) loss: 0.8121 (0.8160) time: 0.1140 data: 0.0423 max mem: 9390 +Train: [71] [3900/6250] eta: 0:05:20 lr: 0.000026 grad: 0.1107 (0.1170) loss: 0.8161 (0.8159) time: 0.1548 data: 0.0767 max mem: 9390 +Train: [71] [4000/6250] eta: 0:05:07 lr: 0.000026 grad: 0.1140 (0.1170) loss: 0.8157 (0.8158) time: 0.1896 data: 0.1115 max mem: 9390 +Train: [71] [4100/6250] eta: 0:04:54 lr: 0.000026 grad: 0.1102 (0.1170) loss: 0.8126 (0.8158) time: 0.1418 data: 0.0658 max mem: 9390 +Train: [71] [4200/6250] eta: 0:04:41 lr: 0.000025 grad: 0.1118 (0.1170) loss: 0.8209 (0.8158) time: 0.1303 data: 0.0528 max mem: 9390 +Train: [71] [4300/6250] eta: 0:04:27 lr: 0.000025 grad: 0.1039 (0.1170) loss: 0.8192 (0.8158) time: 0.1495 data: 0.0677 max mem: 9390 +Train: [71] [4400/6250] eta: 0:04:15 lr: 0.000025 grad: 0.1161 (0.1170) loss: 0.8054 (0.8158) time: 0.1920 data: 0.1129 max mem: 9390 +Train: [71] [4500/6250] eta: 0:04:01 lr: 0.000025 grad: 0.1163 (0.1170) loss: 0.8154 (0.8157) time: 0.1302 data: 0.0522 max mem: 9390 +Train: [71] [4600/6250] eta: 0:03:48 lr: 0.000025 grad: 0.1175 (0.1169) loss: 0.8141 (0.8157) time: 0.1191 data: 0.0428 max mem: 9390 +Train: [71] [4700/6250] eta: 0:03:34 lr: 0.000025 grad: 0.1173 (0.1170) loss: 0.8161 (0.8157) time: 0.1851 data: 0.1027 max mem: 9390 +Train: [71] [4800/6250] eta: 0:03:20 lr: 0.000025 grad: 0.1131 (0.1170) loss: 0.8165 (0.8157) time: 0.1210 data: 0.0343 max mem: 9390 +Train: [71] [4900/6250] eta: 0:03:06 lr: 0.000025 grad: 0.1212 (0.1170) loss: 0.8083 (0.8157) time: 0.1496 data: 0.0725 max mem: 9390 +Train: [71] [5000/6250] eta: 0:02:52 lr: 0.000025 grad: 0.1198 (0.1171) loss: 0.8143 (0.8156) time: 0.1378 data: 0.0579 max mem: 9390 +Train: [71] [5100/6250] eta: 0:02:38 lr: 0.000025 grad: 0.1032 (0.1171) loss: 0.8206 (0.8156) time: 0.1156 data: 0.0346 max mem: 9390 +Train: [71] [5200/6250] eta: 0:02:24 lr: 0.000025 grad: 0.1247 (0.1171) loss: 0.8091 (0.8156) time: 0.1193 data: 0.0401 max mem: 9390 +Train: [71] [5300/6250] eta: 0:02:10 lr: 0.000025 grad: 0.1230 (0.1171) loss: 0.8133 (0.8156) time: 0.1076 data: 0.0246 max mem: 9390 +Train: [71] [5400/6250] eta: 0:01:56 lr: 0.000025 grad: 0.1222 (0.1172) loss: 0.8114 (0.8156) time: 0.1068 data: 0.0256 max mem: 9390 +Train: [71] [5500/6250] eta: 0:01:42 lr: 0.000025 grad: 0.1140 (0.1173) loss: 0.8113 (0.8156) time: 0.1310 data: 0.0518 max mem: 9390 +Train: [71] [5600/6250] eta: 0:01:28 lr: 0.000025 grad: 0.1120 (0.1174) loss: 0.8136 (0.8155) time: 0.1253 data: 0.0439 max mem: 9390 +Train: [71] [5700/6250] eta: 0:01:14 lr: 0.000025 grad: 0.1105 (0.1174) loss: 0.8135 (0.8155) time: 0.1197 data: 0.0385 max mem: 9390 +Train: [71] [5800/6250] eta: 0:01:01 lr: 0.000025 grad: 0.1193 (0.1174) loss: 0.8143 (0.8155) time: 0.1369 data: 0.0577 max mem: 9390 +Train: [71] [5900/6250] eta: 0:00:47 lr: 0.000025 grad: 0.1164 (0.1175) loss: 0.8096 (0.8154) time: 0.1478 data: 0.0713 max mem: 9390 +Train: [71] [6000/6250] eta: 0:00:33 lr: 0.000025 grad: 0.1163 (0.1175) loss: 0.8149 (0.8154) time: 0.1191 data: 0.0357 max mem: 9390 +Train: [71] [6100/6250] eta: 0:00:20 lr: 0.000025 grad: 0.1137 (0.1176) loss: 0.8173 (0.8154) time: 0.1298 data: 0.0524 max mem: 9390 +Train: [71] [6200/6250] eta: 0:00:06 lr: 0.000025 grad: 0.1181 (0.1176) loss: 0.8113 (0.8153) time: 0.1335 data: 0.0538 max mem: 9390 +Train: [71] [6249/6250] eta: 0:00:00 lr: 0.000025 grad: 0.1205 (0.1177) loss: 0.8147 (0.8153) time: 0.1313 data: 0.0514 max mem: 9390 +Train: [71] Total time: 0:14:15 (0.1368 s / it) +Averaged stats: lr: 0.000025 grad: 0.1205 (0.1177) loss: 0.8147 (0.8153) +Eval (hcp-train-subset): [71] [ 0/62] eta: 0:05:23 loss: 0.8384 (0.8384) time: 5.2155 data: 5.1854 max mem: 9390 +Eval (hcp-train-subset): [71] [61/62] eta: 0:00:00 loss: 0.8227 (0.8275) time: 0.1122 data: 0.0875 max mem: 9390 +Eval (hcp-train-subset): [71] Total time: 0:00:12 (0.1942 s / it) +Averaged stats (hcp-train-subset): loss: 0.8227 (0.8275) +Eval (hcp-val): [71] [ 0/62] eta: 0:04:31 loss: 0.8301 (0.8301) time: 4.3767 data: 4.3281 max mem: 9390 +Eval (hcp-val): [71] [61/62] eta: 0:00:00 loss: 0.8299 (0.8318) time: 0.1174 data: 0.0917 max mem: 9390 +Eval (hcp-val): [71] Total time: 0:00:13 (0.2156 s / it) +Averaged stats (hcp-val): loss: 0.8299 (0.8318) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +Train: [72] [ 0/6250] eta: 9:39:07 lr: 0.000025 grad: 0.2021 (0.2021) loss: 0.8054 (0.8054) time: 5.5597 data: 5.4548 max mem: 9390 +Train: [72] [ 100/6250] eta: 0:19:14 lr: 0.000025 grad: 0.1088 (0.1274) loss: 0.8251 (0.8243) time: 0.1397 data: 0.0429 max mem: 9390 +Train: [72] [ 200/6250] eta: 0:16:45 lr: 0.000025 grad: 0.1170 (0.1282) loss: 0.8163 (0.8211) time: 0.1550 data: 0.0700 max mem: 9390 +Train: [72] [ 300/6250] eta: 0:15:28 lr: 0.000025 grad: 0.1178 (0.1278) loss: 0.8241 (0.8197) time: 0.1286 data: 0.0444 max mem: 9390 +Train: [72] [ 400/6250] eta: 0:14:28 lr: 0.000025 grad: 0.1136 (0.1262) loss: 0.8123 (0.8184) time: 0.1162 data: 0.0193 max mem: 9390 +Train: [72] [ 500/6250] eta: 0:13:43 lr: 0.000025 grad: 0.1154 (0.1249) loss: 0.8190 (0.8174) time: 0.1278 data: 0.0489 max mem: 9390 +Train: [72] [ 600/6250] eta: 0:13:12 lr: 0.000025 grad: 0.1083 (0.1236) loss: 0.8158 (0.8167) time: 0.1161 data: 0.0318 max mem: 9390 +Train: [72] [ 700/6250] eta: 0:12:41 lr: 0.000025 grad: 0.1200 (0.1219) loss: 0.8082 (0.8168) time: 0.1290 data: 0.0411 max mem: 9390 +Train: [72] [ 800/6250] eta: 0:12:15 lr: 0.000025 grad: 0.1114 (0.1210) loss: 0.8162 (0.8166) time: 0.1241 data: 0.0416 max mem: 9390 +Train: [72] [ 900/6250] eta: 0:11:53 lr: 0.000025 grad: 0.1129 (0.1203) loss: 0.8247 (0.8166) time: 0.1140 data: 0.0320 max mem: 9390 +Train: [72] [1000/6250] eta: 0:11:39 lr: 0.000025 grad: 0.1143 (0.1200) loss: 0.8126 (0.8164) time: 0.1249 data: 0.0477 max mem: 9390 +Train: [72] [1100/6250] eta: 0:11:21 lr: 0.000025 grad: 0.1186 (0.1199) loss: 0.8126 (0.8160) time: 0.1299 data: 0.0514 max mem: 9390 +Train: [72] [1200/6250] eta: 0:11:04 lr: 0.000025 grad: 0.1130 (0.1198) loss: 0.8178 (0.8156) time: 0.1240 data: 0.0362 max mem: 9390 +Train: [72] [1300/6250] eta: 0:10:52 lr: 0.000025 grad: 0.1153 (0.1195) loss: 0.8124 (0.8152) time: 0.1596 data: 0.0893 max mem: 9390 +Train: [72] [1400/6250] eta: 0:10:41 lr: 0.000025 grad: 0.1160 (0.1193) loss: 0.8094 (0.8150) time: 0.1335 data: 0.0507 max mem: 9390 +Train: [72] [1500/6250] eta: 0:10:30 lr: 0.000025 grad: 0.1180 (0.1193) loss: 0.8001 (0.8145) time: 0.1673 data: 0.0778 max mem: 9390 +Train: [72] [1600/6250] eta: 0:10:15 lr: 0.000025 grad: 0.1262 (0.1194) loss: 0.8081 (0.8143) time: 0.1037 data: 0.0229 max mem: 9390 +Train: [72] [1700/6250] eta: 0:10:01 lr: 0.000024 grad: 0.1169 (0.1194) loss: 0.8090 (0.8140) time: 0.1389 data: 0.0594 max mem: 9390 +Train: [72] [1800/6250] eta: 0:09:48 lr: 0.000024 grad: 0.1181 (0.1194) loss: 0.8106 (0.8137) time: 0.1234 data: 0.0415 max mem: 9390 +Train: [72] [1900/6250] eta: 0:09:34 lr: 0.000024 grad: 0.1200 (0.1193) loss: 0.8012 (0.8135) time: 0.1366 data: 0.0569 max mem: 9390 +Train: [72] [2000/6250] eta: 0:09:22 lr: 0.000024 grad: 0.1174 (0.1194) loss: 0.8073 (0.8133) time: 0.1431 data: 0.0688 max mem: 9390 +Train: [72] [2100/6250] eta: 0:09:11 lr: 0.000024 grad: 0.1223 (0.1195) loss: 0.8029 (0.8131) time: 0.1625 data: 0.0753 max mem: 9390 +Train: [72] [2200/6250] eta: 0:08:56 lr: 0.000024 grad: 0.1161 (0.1194) loss: 0.8132 (0.8129) time: 0.1205 data: 0.0418 max mem: 9390 +Train: [72] [2300/6250] eta: 0:08:45 lr: 0.000024 grad: 0.1175 (0.1196) loss: 0.8059 (0.8126) time: 0.1500 data: 0.0670 max mem: 9390 +Train: [72] [2400/6250] eta: 0:08:35 lr: 0.000024 grad: 0.1156 (0.1195) loss: 0.8074 (0.8123) time: 0.1632 data: 0.0653 max mem: 9390 +Train: [72] [2500/6250] eta: 0:08:21 lr: 0.000024 grad: 0.1122 (0.1196) loss: 0.8173 (0.8121) time: 0.1393 data: 0.0635 max mem: 9390 +Train: [72] [2600/6250] eta: 0:08:09 lr: 0.000024 grad: 0.1142 (0.1197) loss: 0.8126 (0.8118) time: 0.1670 data: 0.0664 max mem: 9390 +Train: [72] [2700/6250] eta: 0:07:57 lr: 0.000024 grad: 0.1175 (0.1198) loss: 0.8112 (0.8118) time: 0.1515 data: 0.0709 max mem: 9390 +Train: [72] [2800/6250] eta: 0:07:46 lr: 0.000024 grad: 0.1145 (0.1197) loss: 0.8097 (0.8118) time: 0.1947 data: 0.1083 max mem: 9390 +Train: [72] [2900/6250] eta: 0:07:32 lr: 0.000024 grad: 0.1053 (0.1197) loss: 0.8125 (0.8117) time: 0.1372 data: 0.0642 max mem: 9390 +Train: [72] [3000/6250] eta: 0:07:18 lr: 0.000024 grad: 0.1176 (0.1197) loss: 0.8101 (0.8117) time: 0.1388 data: 0.0601 max mem: 9390 +Train: [72] [3100/6250] eta: 0:07:04 lr: 0.000024 grad: 0.1150 (0.1197) loss: 0.8107 (0.8117) time: 0.1346 data: 0.0599 max mem: 9390 +Train: [72] [3200/6250] eta: 0:06:51 lr: 0.000024 grad: 0.1175 (0.1196) loss: 0.8095 (0.8116) time: 0.1715 data: 0.0873 max mem: 9390 +Train: [72] [3300/6250] eta: 0:06:37 lr: 0.000024 grad: 0.1123 (0.1196) loss: 0.8130 (0.8116) time: 0.1452 data: 0.0691 max mem: 9390 +Train: [72] [3400/6250] eta: 0:06:23 lr: 0.000024 grad: 0.1161 (0.1196) loss: 0.8104 (0.8116) time: 0.1174 data: 0.0319 max mem: 9390 +Train: [72] [3500/6250] eta: 0:06:09 lr: 0.000024 grad: 0.1159 (0.1196) loss: 0.8083 (0.8116) time: 0.1359 data: 0.0538 max mem: 9390 +Train: [72] [3600/6250] eta: 0:05:56 lr: 0.000024 grad: 0.1119 (0.1196) loss: 0.8145 (0.8117) time: 0.1378 data: 0.0570 max mem: 9390 +Train: [72] [3700/6250] eta: 0:05:42 lr: 0.000024 grad: 0.1217 (0.1196) loss: 0.8113 (0.8117) time: 0.1346 data: 0.0535 max mem: 9390 +Train: [72] [3800/6250] eta: 0:05:29 lr: 0.000024 grad: 0.1100 (0.1196) loss: 0.8173 (0.8118) time: 0.1065 data: 0.0285 max mem: 9390 +Train: [72] [3900/6250] eta: 0:05:16 lr: 0.000024 grad: 0.1126 (0.1196) loss: 0.8171 (0.8119) time: 0.1491 data: 0.0748 max mem: 9390 +Train: [72] [4000/6250] eta: 0:05:03 lr: 0.000024 grad: 0.1218 (0.1198) loss: 0.8093 (0.8119) time: 0.1488 data: 0.0627 max mem: 9390 +Train: [72] [4100/6250] eta: 0:04:50 lr: 0.000024 grad: 0.1281 (0.1199) loss: 0.8079 (0.8119) time: 0.1482 data: 0.0647 max mem: 9390 +Train: [72] [4200/6250] eta: 0:04:37 lr: 0.000024 grad: 0.1225 (0.1199) loss: 0.8142 (0.8119) time: 0.1134 data: 0.0351 max mem: 9390 +Train: [72] [4300/6250] eta: 0:04:24 lr: 0.000024 grad: 0.1196 (0.1200) loss: 0.8096 (0.8119) time: 0.1416 data: 0.0571 max mem: 9390 +Train: [72] [4400/6250] eta: 0:04:12 lr: 0.000024 grad: 0.1288 (0.1202) loss: 0.8062 (0.8118) time: 0.1588 data: 0.0696 max mem: 9390 +Train: [72] [4500/6250] eta: 0:03:59 lr: 0.000024 grad: 0.1144 (0.1203) loss: 0.8064 (0.8118) time: 0.1296 data: 0.0537 max mem: 9390 +Train: [72] [4600/6250] eta: 0:03:45 lr: 0.000024 grad: 0.1141 (0.1203) loss: 0.8077 (0.8117) time: 0.1253 data: 0.0440 max mem: 9390 +Train: [72] [4700/6250] eta: 0:03:31 lr: 0.000024 grad: 0.1150 (0.1203) loss: 0.8105 (0.8118) time: 0.1368 data: 0.0569 max mem: 9390 +Train: [72] [4800/6250] eta: 0:03:18 lr: 0.000024 grad: 0.1129 (0.1202) loss: 0.8147 (0.8118) time: 0.1364 data: 0.0572 max mem: 9390 +Train: [72] [4900/6250] eta: 0:03:04 lr: 0.000024 grad: 0.1123 (0.1202) loss: 0.8162 (0.8118) time: 0.1307 data: 0.0466 max mem: 9390 +Train: [72] [5000/6250] eta: 0:02:50 lr: 0.000024 grad: 0.1131 (0.1202) loss: 0.8129 (0.8118) time: 0.1255 data: 0.0498 max mem: 9390 +Train: [72] [5100/6250] eta: 0:02:36 lr: 0.000024 grad: 0.1190 (0.1201) loss: 0.8125 (0.8118) time: 0.1225 data: 0.0349 max mem: 9390 +Train: [72] [5200/6250] eta: 0:02:22 lr: 0.000024 grad: 0.1218 (0.1201) loss: 0.8155 (0.8119) time: 0.1341 data: 0.0482 max mem: 9390 +Train: [72] [5300/6250] eta: 0:02:08 lr: 0.000024 grad: 0.1133 (0.1200) loss: 0.8174 (0.8119) time: 0.1264 data: 0.0512 max mem: 9390 +Train: [72] [5400/6250] eta: 0:01:54 lr: 0.000024 grad: 0.1156 (0.1200) loss: 0.8117 (0.8120) time: 0.1161 data: 0.0370 max mem: 9390 +Train: [72] [5500/6250] eta: 0:01:41 lr: 0.000023 grad: 0.1247 (0.1200) loss: 0.8098 (0.8120) time: 0.1373 data: 0.0565 max mem: 9390 +Train: [72] [5600/6250] eta: 0:01:27 lr: 0.000023 grad: 0.1257 (0.1201) loss: 0.8087 (0.8120) time: 0.1372 data: 0.0629 max mem: 9390 +Train: [72] [5700/6250] eta: 0:01:14 lr: 0.000023 grad: 0.1117 (0.1201) loss: 0.8156 (0.8121) time: 0.1402 data: 0.0591 max mem: 9390 +Train: [72] [5800/6250] eta: 0:01:00 lr: 0.000023 grad: 0.1100 (0.1201) loss: 0.8135 (0.8121) time: 0.1336 data: 0.0546 max mem: 9390 +Train: [72] [5900/6250] eta: 0:00:47 lr: 0.000023 grad: 0.1121 (0.1201) loss: 0.8146 (0.8121) time: 0.1242 data: 0.0432 max mem: 9390 +Train: [72] [6000/6250] eta: 0:00:33 lr: 0.000023 grad: 0.1163 (0.1201) loss: 0.8121 (0.8121) time: 0.1453 data: 0.0646 max mem: 9390 +Train: [72] [6100/6250] eta: 0:00:20 lr: 0.000023 grad: 0.1087 (0.1200) loss: 0.8198 (0.8122) time: 0.1429 data: 0.0607 max mem: 9390 +Train: [72] [6200/6250] eta: 0:00:06 lr: 0.000023 grad: 0.1135 (0.1199) loss: 0.8128 (0.8122) time: 0.1701 data: 0.0934 max mem: 9390 +Train: [72] [6249/6250] eta: 0:00:00 lr: 0.000023 grad: 0.1166 (0.1199) loss: 0.8149 (0.8122) time: 0.1288 data: 0.0486 max mem: 9390 +Train: [72] Total time: 0:14:09 (0.1360 s / it) +Averaged stats: lr: 0.000023 grad: 0.1166 (0.1199) loss: 0.8149 (0.8122) +Eval (hcp-train-subset): [72] [ 0/62] eta: 0:04:08 loss: 0.8417 (0.8417) time: 4.0013 data: 3.8899 max mem: 9390 +Eval (hcp-train-subset): [72] [61/62] eta: 0:00:00 loss: 0.8250 (0.8284) time: 0.1237 data: 0.0969 max mem: 9390 +Eval (hcp-train-subset): [72] Total time: 0:00:12 (0.2095 s / it) +Averaged stats (hcp-train-subset): loss: 0.8250 (0.8284) +Eval (hcp-val): [72] [ 0/62] eta: 0:04:07 loss: 0.8324 (0.8324) time: 3.9870 data: 3.9079 max mem: 9390 +Eval (hcp-val): [72] [61/62] eta: 0:00:00 loss: 0.8308 (0.8319) time: 0.1045 data: 0.0799 max mem: 9390 +Eval (hcp-val): [72] Total time: 0:00:12 (0.2022 s / it) +Averaged stats (hcp-val): loss: 0.8308 (0.8319) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +Train: [73] [ 0/6250] eta: 7:14:43 lr: 0.000023 grad: 0.0786 (0.0786) loss: 0.8567 (0.8567) time: 4.1733 data: 3.8381 max mem: 9390 +Train: [73] [ 100/6250] eta: 0:18:41 lr: 0.000023 grad: 0.1206 (0.1639) loss: 0.8223 (0.8247) time: 0.1312 data: 0.0349 max mem: 9390 +Train: [73] [ 200/6250] eta: 0:16:31 lr: 0.000023 grad: 0.1027 (0.1423) loss: 0.8183 (0.8225) time: 0.1483 data: 0.0619 max mem: 9390 +Train: [73] [ 300/6250] eta: 0:15:09 lr: 0.000023 grad: 0.1085 (0.1336) loss: 0.8195 (0.8213) time: 0.1319 data: 0.0494 max mem: 9390 +Train: [73] [ 400/6250] eta: 0:14:11 lr: 0.000023 grad: 0.1199 (0.1308) loss: 0.8213 (0.8208) time: 0.1135 data: 0.0285 max mem: 9390 +Train: [73] [ 500/6250] eta: 0:13:36 lr: 0.000023 grad: 0.1168 (0.1289) loss: 0.8138 (0.8197) time: 0.1340 data: 0.0493 max mem: 9390 +Train: [73] [ 600/6250] eta: 0:13:01 lr: 0.000023 grad: 0.1148 (0.1274) loss: 0.8172 (0.8189) time: 0.1192 data: 0.0304 max mem: 9390 +Train: [73] [ 700/6250] eta: 0:12:33 lr: 0.000023 grad: 0.1021 (0.1258) loss: 0.8168 (0.8182) time: 0.1143 data: 0.0284 max mem: 9390 +Train: [73] [ 800/6250] eta: 0:12:14 lr: 0.000023 grad: 0.1149 (0.1243) loss: 0.8185 (0.8182) time: 0.1201 data: 0.0254 max mem: 9390 +Train: [73] [ 900/6250] eta: 0:11:58 lr: 0.000023 grad: 0.1207 (0.1238) loss: 0.8084 (0.8180) time: 0.1264 data: 0.0469 max mem: 9390 +Train: [73] [1000/6250] eta: 0:11:41 lr: 0.000023 grad: 0.1118 (0.1235) loss: 0.8171 (0.8176) time: 0.1301 data: 0.0542 max mem: 9390 +Train: [73] [1100/6250] eta: 0:11:26 lr: 0.000023 grad: 0.1132 (0.1231) loss: 0.8195 (0.8173) time: 0.1326 data: 0.0519 max mem: 9390 +Train: [73] [1200/6250] eta: 0:11:12 lr: 0.000023 grad: 0.1136 (0.1228) loss: 0.8179 (0.8169) time: 0.1265 data: 0.0459 max mem: 9390 +Train: [73] [1300/6250] eta: 0:10:59 lr: 0.000023 grad: 0.1155 (0.1227) loss: 0.8124 (0.8166) time: 0.1522 data: 0.0577 max mem: 9390 +Train: [73] [1400/6250] eta: 0:10:48 lr: 0.000023 grad: 0.1181 (0.1227) loss: 0.8093 (0.8162) time: 0.1192 data: 0.0346 max mem: 9390 +Train: [73] [1500/6250] eta: 0:10:35 lr: 0.000023 grad: 0.1210 (0.1229) loss: 0.8060 (0.8158) time: 0.1297 data: 0.0518 max mem: 9390 +Train: [73] [1600/6250] eta: 0:10:19 lr: 0.000023 grad: 0.1186 (0.1231) loss: 0.8104 (0.8153) time: 0.1386 data: 0.0634 max mem: 9390 +Train: [73] [1700/6250] eta: 0:10:07 lr: 0.000023 grad: 0.1167 (0.1232) loss: 0.8102 (0.8149) time: 0.1130 data: 0.0308 max mem: 9390 +Train: [73] [1800/6250] eta: 0:09:53 lr: 0.000023 grad: 0.1199 (0.1231) loss: 0.8106 (0.8146) time: 0.1308 data: 0.0473 max mem: 9390 +Train: [73] [1900/6250] eta: 0:09:44 lr: 0.000023 grad: 0.1167 (0.1231) loss: 0.8116 (0.8144) time: 0.1954 data: 0.1061 max mem: 9390 +Train: [73] [2000/6250] eta: 0:09:27 lr: 0.000023 grad: 0.1228 (0.1232) loss: 0.8061 (0.8141) time: 0.1119 data: 0.0333 max mem: 9390 +Train: [73] [2100/6250] eta: 0:09:15 lr: 0.000023 grad: 0.1200 (0.1233) loss: 0.8090 (0.8139) time: 0.1411 data: 0.0663 max mem: 9390 +Train: [73] [2200/6250] eta: 0:09:01 lr: 0.000023 grad: 0.1159 (0.1234) loss: 0.8117 (0.8136) time: 0.1290 data: 0.0429 max mem: 9390 +Train: [73] [2300/6250] eta: 0:08:48 lr: 0.000023 grad: 0.1186 (0.1234) loss: 0.8123 (0.8135) time: 0.1264 data: 0.0481 max mem: 9390 +Train: [73] [2400/6250] eta: 0:08:36 lr: 0.000023 grad: 0.1188 (0.1234) loss: 0.8176 (0.8134) time: 0.1444 data: 0.0663 max mem: 9390 +Train: [73] [2500/6250] eta: 0:08:24 lr: 0.000023 grad: 0.1260 (0.1234) loss: 0.8121 (0.8132) time: 0.1578 data: 0.0774 max mem: 9390 +Train: [73] [2600/6250] eta: 0:08:13 lr: 0.000023 grad: 0.1169 (0.1235) loss: 0.8064 (0.8131) time: 0.1938 data: 0.1093 max mem: 9390 +Train: [73] [2700/6250] eta: 0:07:59 lr: 0.000023 grad: 0.1188 (0.1235) loss: 0.8110 (0.8130) time: 0.1356 data: 0.0544 max mem: 9390 +Train: [73] [2800/6250] eta: 0:07:46 lr: 0.000023 grad: 0.1226 (0.1235) loss: 0.8130 (0.8129) time: 0.1199 data: 0.0403 max mem: 9390 +Train: [73] [2900/6250] eta: 0:07:32 lr: 0.000023 grad: 0.1278 (0.1236) loss: 0.8050 (0.8128) time: 0.0883 data: 0.0120 max mem: 9390 +Train: [73] [3000/6250] eta: 0:07:18 lr: 0.000023 grad: 0.1188 (0.1236) loss: 0.8144 (0.8127) time: 0.1247 data: 0.0479 max mem: 9390 +Train: [73] [3100/6250] eta: 0:07:04 lr: 0.000023 grad: 0.1145 (0.1235) loss: 0.8121 (0.8126) time: 0.1167 data: 0.0301 max mem: 9390 +Train: [73] [3200/6250] eta: 0:06:50 lr: 0.000022 grad: 0.1214 (0.1235) loss: 0.8116 (0.8126) time: 0.1252 data: 0.0440 max mem: 9390 +Train: [73] [3300/6250] eta: 0:06:37 lr: 0.000022 grad: 0.1104 (0.1233) loss: 0.8123 (0.8125) time: 0.1383 data: 0.0647 max mem: 9390 +Train: [73] [3400/6250] eta: 0:06:23 lr: 0.000022 grad: 0.1165 (0.1232) loss: 0.8097 (0.8125) time: 0.1347 data: 0.0577 max mem: 9390 +Train: [73] [3500/6250] eta: 0:06:10 lr: 0.000022 grad: 0.1192 (0.1231) loss: 0.8115 (0.8125) time: 0.1393 data: 0.0568 max mem: 9390 +Train: [73] [3600/6250] eta: 0:05:57 lr: 0.000022 grad: 0.1179 (0.1232) loss: 0.8115 (0.8124) time: 0.1343 data: 0.0553 max mem: 9390 +Train: [73] [3700/6250] eta: 0:05:43 lr: 0.000022 grad: 0.1260 (0.1232) loss: 0.8029 (0.8124) time: 0.1302 data: 0.0521 max mem: 9390 +Train: [73] [3800/6250] eta: 0:05:30 lr: 0.000022 grad: 0.1221 (0.1233) loss: 0.8103 (0.8123) time: 0.1491 data: 0.0723 max mem: 9390 +Train: [73] [3900/6250] eta: 0:05:17 lr: 0.000022 grad: 0.1198 (0.1234) loss: 0.8026 (0.8121) time: 0.1396 data: 0.0388 max mem: 9390 +Train: [73] [4000/6250] eta: 0:05:04 lr: 0.000022 grad: 0.1220 (0.1235) loss: 0.7972 (0.8120) time: 0.1341 data: 0.0566 max mem: 9390 +Train: [73] [4100/6250] eta: 0:04:51 lr: 0.000022 grad: 0.1240 (0.1235) loss: 0.8098 (0.8120) time: 0.1374 data: 0.0589 max mem: 9390 +Train: [73] [4200/6250] eta: 0:04:38 lr: 0.000022 grad: 0.1256 (0.1235) loss: 0.8090 (0.8119) time: 0.1559 data: 0.0831 max mem: 9390 +Train: [73] [4300/6250] eta: 0:04:25 lr: 0.000022 grad: 0.1200 (0.1235) loss: 0.8107 (0.8119) time: 0.1318 data: 0.0589 max mem: 9390 +Train: [73] [4400/6250] eta: 0:04:12 lr: 0.000022 grad: 0.1187 (0.1235) loss: 0.8133 (0.8119) time: 0.1491 data: 0.0596 max mem: 9390 +Train: [73] [4500/6250] eta: 0:03:59 lr: 0.000022 grad: 0.1176 (0.1235) loss: 0.8072 (0.8118) time: 0.1422 data: 0.0621 max mem: 9390 +Train: [73] [4600/6250] eta: 0:03:45 lr: 0.000022 grad: 0.1201 (0.1235) loss: 0.8070 (0.8118) time: 0.1544 data: 0.0743 max mem: 9390 +Train: [73] [4700/6250] eta: 0:03:32 lr: 0.000022 grad: 0.1190 (0.1235) loss: 0.8058 (0.8118) time: 0.1366 data: 0.0562 max mem: 9390 +Train: [73] [4800/6250] eta: 0:03:18 lr: 0.000022 grad: 0.1215 (0.1235) loss: 0.8070 (0.8117) time: 0.1187 data: 0.0399 max mem: 9390 +Train: [73] [4900/6250] eta: 0:03:04 lr: 0.000022 grad: 0.1283 (0.1235) loss: 0.8084 (0.8117) time: 0.1315 data: 0.0507 max mem: 9390 +Train: [73] [5000/6250] eta: 0:02:50 lr: 0.000022 grad: 0.1320 (0.1236) loss: 0.8025 (0.8116) time: 0.1277 data: 0.0360 max mem: 9390 +Train: [73] [5100/6250] eta: 0:02:36 lr: 0.000022 grad: 0.1250 (0.1236) loss: 0.8138 (0.8116) time: 0.1152 data: 0.0351 max mem: 9390 +Train: [73] [5200/6250] eta: 0:02:22 lr: 0.000022 grad: 0.1200 (0.1237) loss: 0.8102 (0.8114) time: 0.1258 data: 0.0474 max mem: 9390 +Train: [73] [5300/6250] eta: 0:02:08 lr: 0.000022 grad: 0.1243 (0.1238) loss: 0.8084 (0.8113) time: 0.1352 data: 0.0562 max mem: 9390 +Train: [73] [5400/6250] eta: 0:01:54 lr: 0.000022 grad: 0.1245 (0.1239) loss: 0.8096 (0.8113) time: 0.1347 data: 0.0552 max mem: 9390 +Train: [73] [5500/6250] eta: 0:01:41 lr: 0.000022 grad: 0.1148 (0.1240) loss: 0.8067 (0.8111) time: 0.1199 data: 0.0366 max mem: 9390 +Train: [73] [5600/6250] eta: 0:01:27 lr: 0.000022 grad: 0.1222 (0.1240) loss: 0.8063 (0.8111) time: 0.1253 data: 0.0450 max mem: 9390 +Train: [73] [5700/6250] eta: 0:01:14 lr: 0.000022 grad: 0.1161 (0.1240) loss: 0.8148 (0.8111) time: 0.1343 data: 0.0525 max mem: 9390 +Train: [73] [5800/6250] eta: 0:01:00 lr: 0.000022 grad: 0.1233 (0.1240) loss: 0.8117 (0.8111) time: 0.1283 data: 0.0505 max mem: 9390 +Train: [73] [5900/6250] eta: 0:00:47 lr: 0.000022 grad: 0.1118 (0.1240) loss: 0.8080 (0.8111) time: 0.1382 data: 0.0585 max mem: 9390 +Train: [73] [6000/6250] eta: 0:00:33 lr: 0.000022 grad: 0.1170 (0.1240) loss: 0.8155 (0.8112) time: 0.1370 data: 0.0595 max mem: 9390 +Train: [73] [6100/6250] eta: 0:00:20 lr: 0.000022 grad: 0.1230 (0.1240) loss: 0.8095 (0.8112) time: 0.1302 data: 0.0547 max mem: 9390 +Train: [73] [6200/6250] eta: 0:00:06 lr: 0.000022 grad: 0.1240 (0.1240) loss: 0.8098 (0.8112) time: 0.1630 data: 0.0746 max mem: 9390 +Train: [73] [6249/6250] eta: 0:00:00 lr: 0.000022 grad: 0.1200 (0.1240) loss: 0.8157 (0.8112) time: 0.1441 data: 0.0668 max mem: 9390 +Train: [73] Total time: 0:14:07 (0.1355 s / it) +Averaged stats: lr: 0.000022 grad: 0.1200 (0.1240) loss: 0.8157 (0.8112) +Eval (hcp-train-subset): [73] [ 0/62] eta: 0:04:51 loss: 0.8390 (0.8390) time: 4.6958 data: 4.6652 max mem: 9390 +Eval (hcp-train-subset): [73] [61/62] eta: 0:00:00 loss: 0.8253 (0.8276) time: 0.1224 data: 0.0959 max mem: 9390 +Eval (hcp-train-subset): [73] Total time: 0:00:13 (0.2201 s / it) +Averaged stats (hcp-train-subset): loss: 0.8253 (0.8276) +Eval (hcp-val): [73] [ 0/62] eta: 0:04:51 loss: 0.8321 (0.8321) time: 4.7076 data: 4.6723 max mem: 9390 +Eval (hcp-val): [73] [61/62] eta: 0:00:00 loss: 0.8291 (0.8321) time: 0.1036 data: 0.0772 max mem: 9390 +Eval (hcp-val): [73] Total time: 0:00:11 (0.1934 s / it) +Averaged stats (hcp-val): loss: 0.8291 (0.8321) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +Train: [74] [ 0/6250] eta: 7:50:32 lr: 0.000022 grad: 0.2622 (0.2622) loss: 0.8505 (0.8505) time: 4.5172 data: 4.3334 max mem: 9390 +Train: [74] [ 100/6250] eta: 0:18:43 lr: 0.000022 grad: 0.1148 (0.1296) loss: 0.8264 (0.8277) time: 0.1323 data: 0.0320 max mem: 9390 +Train: [74] [ 200/6250] eta: 0:16:22 lr: 0.000022 grad: 0.1213 (0.1294) loss: 0.8158 (0.8218) time: 0.1447 data: 0.0573 max mem: 9390 +Train: [74] [ 300/6250] eta: 0:14:57 lr: 0.000022 grad: 0.1177 (0.1295) loss: 0.8185 (0.8190) time: 0.1469 data: 0.0589 max mem: 9390 +Train: [74] [ 400/6250] eta: 0:14:07 lr: 0.000022 grad: 0.1181 (0.1306) loss: 0.8161 (0.8178) time: 0.1154 data: 0.0308 max mem: 9390 +Train: [74] [ 500/6250] eta: 0:13:27 lr: 0.000022 grad: 0.1175 (0.1302) loss: 0.8181 (0.8176) time: 0.1181 data: 0.0222 max mem: 9390 +Train: [74] [ 600/6250] eta: 0:12:58 lr: 0.000022 grad: 0.1224 (0.1288) loss: 0.8157 (0.8170) time: 0.1341 data: 0.0503 max mem: 9390 +Train: [74] [ 700/6250] eta: 0:12:30 lr: 0.000022 grad: 0.1155 (0.1281) loss: 0.8143 (0.8167) time: 0.1148 data: 0.0203 max mem: 9390 +Train: [74] [ 800/6250] eta: 0:12:06 lr: 0.000022 grad: 0.1100 (0.1271) loss: 0.8206 (0.8165) time: 0.1250 data: 0.0437 max mem: 9390 +Train: [74] [ 900/6250] eta: 0:11:56 lr: 0.000021 grad: 0.1150 (0.1267) loss: 0.8148 (0.8161) time: 0.1761 data: 0.0976 max mem: 9390 +Train: [74] [1000/6250] eta: 0:11:38 lr: 0.000021 grad: 0.1170 (0.1261) loss: 0.8130 (0.8159) time: 0.1287 data: 0.0506 max mem: 9390 +Train: [74] [1100/6250] eta: 0:11:27 lr: 0.000021 grad: 0.1195 (0.1256) loss: 0.8100 (0.8155) time: 0.1361 data: 0.0622 max mem: 9390 +Train: [74] [1200/6250] eta: 0:11:14 lr: 0.000021 grad: 0.1152 (0.1252) loss: 0.8087 (0.8152) time: 0.1401 data: 0.0536 max mem: 9390 +Train: [74] [1300/6250] eta: 0:11:00 lr: 0.000021 grad: 0.1155 (0.1249) loss: 0.8130 (0.8151) time: 0.1397 data: 0.0646 max mem: 9390 +Train: [74] [1400/6250] eta: 0:10:50 lr: 0.000021 grad: 0.1185 (0.1245) loss: 0.8143 (0.8149) time: 0.1513 data: 0.0704 max mem: 9390 +Train: [74] [1500/6250] eta: 0:10:38 lr: 0.000021 grad: 0.1213 (0.1243) loss: 0.8107 (0.8146) time: 0.1425 data: 0.0581 max mem: 9390 +Train: [74] [1600/6250] eta: 0:10:25 lr: 0.000021 grad: 0.1146 (0.1240) loss: 0.8167 (0.8144) time: 0.1399 data: 0.0549 max mem: 9390 +Train: [74] [1700/6250] eta: 0:10:10 lr: 0.000021 grad: 0.1169 (0.1239) loss: 0.8041 (0.8142) time: 0.1151 data: 0.0358 max mem: 9390 +Train: [74] [1800/6250] eta: 0:09:57 lr: 0.000021 grad: 0.1196 (0.1240) loss: 0.8052 (0.8140) time: 0.1420 data: 0.0672 max mem: 9390 +Train: [74] [1900/6250] eta: 0:09:46 lr: 0.000021 grad: 0.1239 (0.1240) loss: 0.8063 (0.8137) time: 0.1543 data: 0.0708 max mem: 9390 +Train: [74] [2000/6250] eta: 0:09:36 lr: 0.000021 grad: 0.1268 (0.1240) loss: 0.8041 (0.8133) time: 0.1523 data: 0.0755 max mem: 9390 +Train: [74] [2100/6250] eta: 0:09:21 lr: 0.000021 grad: 0.1179 (0.1242) loss: 0.8096 (0.8131) time: 0.1093 data: 0.0282 max mem: 9390 +Train: [74] [2200/6250] eta: 0:09:06 lr: 0.000021 grad: 0.1158 (0.1241) loss: 0.8130 (0.8129) time: 0.1398 data: 0.0607 max mem: 9390 +Train: [74] [2300/6250] eta: 0:08:52 lr: 0.000021 grad: 0.1280 (0.1240) loss: 0.8057 (0.8128) time: 0.1325 data: 0.0515 max mem: 9390 +Train: [74] [2400/6250] eta: 0:08:41 lr: 0.000021 grad: 0.1188 (0.1241) loss: 0.8086 (0.8126) time: 0.1236 data: 0.0398 max mem: 9390 +Train: [74] [2500/6250] eta: 0:08:27 lr: 0.000021 grad: 0.1172 (0.1241) loss: 0.8127 (0.8125) time: 0.1281 data: 0.0464 max mem: 9390 +Train: [74] [2600/6250] eta: 0:08:15 lr: 0.000021 grad: 0.1291 (0.1242) loss: 0.8032 (0.8122) time: 0.1378 data: 0.0580 max mem: 9390 +Train: [74] [2700/6250] eta: 0:08:02 lr: 0.000021 grad: 0.1213 (0.1241) loss: 0.8075 (0.8122) time: 0.1381 data: 0.0621 max mem: 9390 +Train: [74] [2800/6250] eta: 0:07:51 lr: 0.000021 grad: 0.1252 (0.1241) loss: 0.8056 (0.8121) time: 0.1562 data: 0.0639 max mem: 9390 +Train: [74] [2900/6250] eta: 0:07:38 lr: 0.000021 grad: 0.1214 (0.1239) loss: 0.8071 (0.8120) time: 0.1488 data: 0.0702 max mem: 9390 +Train: [74] [3000/6250] eta: 0:07:25 lr: 0.000021 grad: 0.1315 (0.1240) loss: 0.8038 (0.8118) time: 0.1770 data: 0.1008 max mem: 9390 +Train: [74] [3100/6250] eta: 0:07:12 lr: 0.000021 grad: 0.1265 (0.1241) loss: 0.8066 (0.8117) time: 0.1512 data: 0.0630 max mem: 9390 +Train: [74] [3200/6250] eta: 0:06:59 lr: 0.000021 grad: 0.1221 (0.1240) loss: 0.7977 (0.8117) time: 0.1405 data: 0.0580 max mem: 9390 +Train: [74] [3300/6250] eta: 0:06:46 lr: 0.000021 grad: 0.1153 (0.1240) loss: 0.8125 (0.8116) time: 0.1363 data: 0.0589 max mem: 9390 +Train: [74] [3400/6250] eta: 0:06:32 lr: 0.000021 grad: 0.1130 (0.1238) loss: 0.8156 (0.8117) time: 0.1288 data: 0.0509 max mem: 9390 +Train: [74] [3500/6250] eta: 0:06:18 lr: 0.000021 grad: 0.1146 (0.1238) loss: 0.8133 (0.8116) time: 0.1399 data: 0.0635 max mem: 9390 +Train: [74] [3600/6250] eta: 0:06:05 lr: 0.000021 grad: 0.1140 (0.1236) loss: 0.8108 (0.8117) time: 0.1306 data: 0.0492 max mem: 9390 +Train: [74] [3700/6250] eta: 0:05:52 lr: 0.000021 grad: 0.1170 (0.1235) loss: 0.8131 (0.8117) time: 0.1701 data: 0.0914 max mem: 9390 +Train: [74] [3800/6250] eta: 0:05:39 lr: 0.000021 grad: 0.1163 (0.1235) loss: 0.8084 (0.8116) time: 0.1490 data: 0.0744 max mem: 9390 +Train: [74] [3900/6250] eta: 0:05:25 lr: 0.000021 grad: 0.1212 (0.1234) loss: 0.8014 (0.8116) time: 0.1305 data: 0.0507 max mem: 9390 +Train: [74] [4000/6250] eta: 0:05:12 lr: 0.000021 grad: 0.1179 (0.1234) loss: 0.8100 (0.8115) time: 0.1812 data: 0.1053 max mem: 9390 +Train: [74] [4100/6250] eta: 0:04:59 lr: 0.000021 grad: 0.1199 (0.1233) loss: 0.8093 (0.8115) time: 0.1568 data: 0.0803 max mem: 9390 +Train: [74] [4200/6250] eta: 0:04:45 lr: 0.000021 grad: 0.1120 (0.1231) loss: 0.8043 (0.8114) time: 0.1291 data: 0.0466 max mem: 9390 +Train: [74] [4300/6250] eta: 0:04:32 lr: 0.000021 grad: 0.1158 (0.1230) loss: 0.8131 (0.8114) time: 0.1683 data: 0.0899 max mem: 9390 +Train: [74] [4400/6250] eta: 0:04:18 lr: 0.000021 grad: 0.1270 (0.1230) loss: 0.8011 (0.8114) time: 0.1514 data: 0.0684 max mem: 9390 +Train: [74] [4500/6250] eta: 0:04:04 lr: 0.000021 grad: 0.1168 (0.1229) loss: 0.8104 (0.8114) time: 0.1303 data: 0.0517 max mem: 9390 +Train: [74] [4600/6250] eta: 0:03:51 lr: 0.000021 grad: 0.1179 (0.1229) loss: 0.8073 (0.8113) time: 0.1367 data: 0.0542 max mem: 9390 +Train: [74] [4700/6250] eta: 0:03:37 lr: 0.000021 grad: 0.1125 (0.1228) loss: 0.8114 (0.8113) time: 0.1541 data: 0.0677 max mem: 9390 +Train: [74] [4800/6250] eta: 0:03:22 lr: 0.000021 grad: 0.1252 (0.1228) loss: 0.8054 (0.8113) time: 0.1217 data: 0.0463 max mem: 9390 +Train: [74] [4900/6250] eta: 0:03:08 lr: 0.000020 grad: 0.1123 (0.1228) loss: 0.8162 (0.8112) time: 0.1268 data: 0.0511 max mem: 9390 +Train: [74] [5000/6250] eta: 0:02:54 lr: 0.000020 grad: 0.1173 (0.1228) loss: 0.8104 (0.8111) time: 0.1358 data: 0.0556 max mem: 9390 +Train: [74] [5100/6250] eta: 0:02:39 lr: 0.000020 grad: 0.1181 (0.1228) loss: 0.8153 (0.8111) time: 0.1144 data: 0.0293 max mem: 9390 +Train: [74] [5200/6250] eta: 0:02:25 lr: 0.000020 grad: 0.1271 (0.1229) loss: 0.8099 (0.8111) time: 0.1183 data: 0.0275 max mem: 9390 +Train: [74] [5300/6250] eta: 0:02:11 lr: 0.000020 grad: 0.1250 (0.1228) loss: 0.8070 (0.8110) time: 0.1185 data: 0.0304 max mem: 9390 +Train: [74] [5400/6250] eta: 0:01:57 lr: 0.000020 grad: 0.1177 (0.1229) loss: 0.8062 (0.8110) time: 0.1358 data: 0.0563 max mem: 9390 +Train: [74] [5500/6250] eta: 0:01:43 lr: 0.000020 grad: 0.1179 (0.1230) loss: 0.8096 (0.8110) time: 0.1303 data: 0.0548 max mem: 9390 +Train: [74] [5600/6250] eta: 0:01:29 lr: 0.000020 grad: 0.1230 (0.1230) loss: 0.8121 (0.8109) time: 0.1382 data: 0.0598 max mem: 9390 +Train: [74] [5700/6250] eta: 0:01:15 lr: 0.000020 grad: 0.1190 (0.1230) loss: 0.8030 (0.8108) time: 0.1174 data: 0.0411 max mem: 9390 +Train: [74] [5800/6250] eta: 0:01:01 lr: 0.000020 grad: 0.1235 (0.1231) loss: 0.8050 (0.8108) time: 0.1289 data: 0.0480 max mem: 9390 +Train: [74] [5900/6250] eta: 0:00:48 lr: 0.000020 grad: 0.1271 (0.1232) loss: 0.8044 (0.8107) time: 0.1295 data: 0.0491 max mem: 9390 +Train: [74] [6000/6250] eta: 0:00:34 lr: 0.000020 grad: 0.1232 (0.1232) loss: 0.7963 (0.8106) time: 0.1391 data: 0.0547 max mem: 9390 +Train: [74] [6100/6250] eta: 0:00:20 lr: 0.000020 grad: 0.1227 (0.1233) loss: 0.8178 (0.8106) time: 0.1570 data: 0.0815 max mem: 9390 +Train: [74] [6200/6250] eta: 0:00:06 lr: 0.000020 grad: 0.1195 (0.1232) loss: 0.8149 (0.8106) time: 0.1376 data: 0.0615 max mem: 9390 +Train: [74] [6249/6250] eta: 0:00:00 lr: 0.000020 grad: 0.1266 (0.1233) loss: 0.8074 (0.8105) time: 0.1572 data: 0.0780 max mem: 9390 +Train: [74] Total time: 0:14:24 (0.1383 s / it) +Averaged stats: lr: 0.000020 grad: 0.1266 (0.1233) loss: 0.8074 (0.8105) +Eval (hcp-train-subset): [74] [ 0/62] eta: 0:05:41 loss: 0.8349 (0.8349) time: 5.5139 data: 5.4828 max mem: 9390 +Eval (hcp-train-subset): [74] [61/62] eta: 0:00:00 loss: 0.8255 (0.8257) time: 0.1161 data: 0.0911 max mem: 9390 +Eval (hcp-train-subset): [74] Total time: 0:00:13 (0.2155 s / it) +Averaged stats (hcp-train-subset): loss: 0.8255 (0.8257) +Making plots (hcp-train-subset): example=7 +Eval (hcp-val): [74] [ 0/62] eta: 0:04:12 loss: 0.8259 (0.8259) time: 4.0785 data: 4.0140 max mem: 9390 +Eval (hcp-val): [74] [61/62] eta: 0:00:00 loss: 0.8306 (0.8314) time: 0.1027 data: 0.0778 max mem: 9390 +Eval (hcp-val): [74] Total time: 0:00:12 (0.1979 s / it) +Averaged stats (hcp-val): loss: 0.8306 (0.8314) +Making plots (hcp-val): example=20 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +Train: [75] [ 0/6250] eta: 7:42:39 lr: 0.000020 grad: 0.0932 (0.0932) loss: 0.8414 (0.8414) time: 4.4414 data: 4.1901 max mem: 9390 +Train: [75] [ 100/6250] eta: 0:19:12 lr: 0.000020 grad: 0.1307 (0.1312) loss: 0.8272 (0.8326) time: 0.1419 data: 0.0502 max mem: 9390 +Train: [75] [ 200/6250] eta: 0:16:07 lr: 0.000020 grad: 0.1261 (0.1336) loss: 0.8062 (0.8243) time: 0.1192 data: 0.0276 max mem: 9390 +Train: [75] [ 300/6250] eta: 0:14:45 lr: 0.000020 grad: 0.1140 (0.1311) loss: 0.8095 (0.8215) time: 0.1326 data: 0.0422 max mem: 9390 +Train: [75] [ 400/6250] eta: 0:13:52 lr: 0.000020 grad: 0.1167 (0.1292) loss: 0.8198 (0.8204) time: 0.1178 data: 0.0319 max mem: 9390 +Train: [75] [ 500/6250] eta: 0:13:09 lr: 0.000020 grad: 0.1114 (0.1268) loss: 0.8187 (0.8198) time: 0.1149 data: 0.0237 max mem: 9390 +Train: [75] [ 600/6250] eta: 0:12:42 lr: 0.000020 grad: 0.1193 (0.1258) loss: 0.8178 (0.8194) time: 0.1025 data: 0.0077 max mem: 9390 +Train: [75] [ 700/6250] eta: 0:12:18 lr: 0.000020 grad: 0.1168 (0.1252) loss: 0.8181 (0.8192) time: 0.1155 data: 0.0280 max mem: 9390 +Train: [75] [ 800/6250] eta: 0:12:01 lr: 0.000020 grad: 0.1172 (0.1246) loss: 0.8151 (0.8190) time: 0.1280 data: 0.0435 max mem: 9390 +Train: [75] [ 900/6250] eta: 0:11:47 lr: 0.000020 grad: 0.1125 (0.1239) loss: 0.8191 (0.8189) time: 0.1587 data: 0.0804 max mem: 9390 +Train: [75] [1000/6250] eta: 0:11:30 lr: 0.000020 grad: 0.1162 (0.1233) loss: 0.8142 (0.8188) time: 0.1199 data: 0.0427 max mem: 9390 +Train: [75] [1100/6250] eta: 0:11:15 lr: 0.000020 grad: 0.1080 (0.1224) loss: 0.8193 (0.8188) time: 0.1282 data: 0.0475 max mem: 9390 +Train: [75] [1200/6250] eta: 0:11:07 lr: 0.000020 grad: 0.1104 (0.1219) loss: 0.8125 (0.8186) time: 0.1444 data: 0.0668 max mem: 9390 +Train: [75] [1300/6250] eta: 0:10:54 lr: 0.000020 grad: 0.1176 (0.1215) loss: 0.8156 (0.8184) time: 0.1410 data: 0.0621 max mem: 9390 +Train: [75] [1400/6250] eta: 0:10:42 lr: 0.000020 grad: 0.1120 (0.1211) loss: 0.8148 (0.8183) time: 0.1332 data: 0.0539 max mem: 9390 +Train: [75] [1500/6250] eta: 0:10:34 lr: 0.000020 grad: 0.1176 (0.1208) loss: 0.8172 (0.8182) time: 0.1657 data: 0.0820 max mem: 9390 +Train: [75] [1600/6250] eta: 0:10:21 lr: 0.000020 grad: 0.1204 (0.1207) loss: 0.8138 (0.8180) time: 0.1428 data: 0.0558 max mem: 9390 +Train: [75] [1700/6250] eta: 0:10:20 lr: 0.000020 grad: 0.1266 (0.1209) loss: 0.8126 (0.8177) time: 0.0927 data: 0.0002 max mem: 9390 +Train: [75] [1800/6250] eta: 0:10:04 lr: 0.000020 grad: 0.1191 (0.1210) loss: 0.8146 (0.8174) time: 0.1273 data: 0.0464 max mem: 9390 +Train: [75] [1900/6250] eta: 0:09:53 lr: 0.000020 grad: 0.1234 (0.1210) loss: 0.8128 (0.8172) time: 0.1446 data: 0.0654 max mem: 9390 +Train: [75] [2000/6250] eta: 0:09:41 lr: 0.000020 grad: 0.1292 (0.1213) loss: 0.8062 (0.8168) time: 0.1684 data: 0.0912 max mem: 9390 +Train: [75] [2100/6250] eta: 0:09:29 lr: 0.000020 grad: 0.1217 (0.1215) loss: 0.8083 (0.8165) time: 0.1464 data: 0.0661 max mem: 9390 +Train: [75] [2200/6250] eta: 0:09:23 lr: 0.000020 grad: 0.1180 (0.1216) loss: 0.8115 (0.8163) time: 0.1233 data: 0.0404 max mem: 9390 +Train: [75] [2300/6250] eta: 0:09:06 lr: 0.000020 grad: 0.1186 (0.1218) loss: 0.8097 (0.8160) time: 0.1356 data: 0.0608 max mem: 9390 +Train: [75] [2400/6250] eta: 0:08:52 lr: 0.000020 grad: 0.1191 (0.1220) loss: 0.8117 (0.8158) time: 0.1238 data: 0.0428 max mem: 9390 +Train: [75] [2500/6250] eta: 0:08:38 lr: 0.000020 grad: 0.1226 (0.1222) loss: 0.8136 (0.8155) time: 0.1383 data: 0.0674 max mem: 9390 +Train: [75] [2600/6250] eta: 0:08:24 lr: 0.000020 grad: 0.1174 (0.1224) loss: 0.8129 (0.8153) time: 0.1559 data: 0.0793 max mem: 9390 +Train: [75] [2700/6250] eta: 0:08:10 lr: 0.000020 grad: 0.1217 (0.1224) loss: 0.8144 (0.8152) time: 0.1443 data: 0.0662 max mem: 9390 +Train: [75] [2800/6250] eta: 0:07:56 lr: 0.000019 grad: 0.1196 (0.1224) loss: 0.8107 (0.8150) time: 0.1370 data: 0.0600 max mem: 9390 +Train: [75] [2900/6250] eta: 0:07:43 lr: 0.000019 grad: 0.1124 (0.1224) loss: 0.8090 (0.8149) time: 0.1420 data: 0.0645 max mem: 9390 +Train: [75] [3000/6250] eta: 0:07:28 lr: 0.000019 grad: 0.1200 (0.1224) loss: 0.8146 (0.8148) time: 0.1513 data: 0.0765 max mem: 9390 +Train: [75] [3100/6250] eta: 0:07:15 lr: 0.000019 grad: 0.1192 (0.1225) loss: 0.8110 (0.8146) time: 0.1365 data: 0.0570 max mem: 9390 +Train: [75] [3200/6250] eta: 0:07:01 lr: 0.000019 grad: 0.1211 (0.1225) loss: 0.8125 (0.8145) time: 0.1616 data: 0.0759 max mem: 9390 +Train: [75] [3300/6250] eta: 0:06:47 lr: 0.000019 grad: 0.1130 (0.1226) loss: 0.8108 (0.8143) time: 0.1568 data: 0.0719 max mem: 9390 +Train: [75] [3400/6250] eta: 0:06:35 lr: 0.000019 grad: 0.1142 (0.1226) loss: 0.8091 (0.8142) time: 0.1243 data: 0.0492 max mem: 9390 +Train: [75] [3500/6250] eta: 0:06:21 lr: 0.000019 grad: 0.1174 (0.1226) loss: 0.8082 (0.8140) time: 0.1344 data: 0.0564 max mem: 9390 +Train: [75] [3600/6250] eta: 0:06:07 lr: 0.000019 grad: 0.1228 (0.1227) loss: 0.8100 (0.8140) time: 0.1390 data: 0.0679 max mem: 9390 +Train: [75] [3700/6250] eta: 0:05:53 lr: 0.000019 grad: 0.1214 (0.1228) loss: 0.8135 (0.8139) time: 0.1453 data: 0.0510 max mem: 9390 +Train: [75] [3800/6250] eta: 0:05:39 lr: 0.000019 grad: 0.1148 (0.1227) loss: 0.8107 (0.8139) time: 0.1380 data: 0.0582 max mem: 9390 +Train: [75] [3900/6250] eta: 0:05:25 lr: 0.000019 grad: 0.1206 (0.1227) loss: 0.8109 (0.8139) time: 0.1501 data: 0.0733 max mem: 9390 +Train: [75] [4000/6250] eta: 0:05:12 lr: 0.000019 grad: 0.1240 (0.1227) loss: 0.8104 (0.8139) time: 0.1332 data: 0.0526 max mem: 9390 +Train: [75] [4100/6250] eta: 0:04:58 lr: 0.000019 grad: 0.1192 (0.1226) loss: 0.8160 (0.8140) time: 0.1692 data: 0.0872 max mem: 9390 +Train: [75] [4200/6250] eta: 0:04:44 lr: 0.000019 grad: 0.1152 (0.1226) loss: 0.8141 (0.8140) time: 0.1325 data: 0.0560 max mem: 9390 +Train: [75] [4300/6250] eta: 0:04:30 lr: 0.000019 grad: 0.1183 (0.1227) loss: 0.8201 (0.8140) time: 0.1173 data: 0.0416 max mem: 9390 +Train: [75] [4400/6250] eta: 0:04:16 lr: 0.000019 grad: 0.1242 (0.1226) loss: 0.8148 (0.8141) time: 0.1176 data: 0.0422 max mem: 9390 +Train: [75] [4500/6250] eta: 0:04:02 lr: 0.000019 grad: 0.1139 (0.1226) loss: 0.8160 (0.8141) time: 0.1551 data: 0.0698 max mem: 9390 +Train: [75] [4600/6250] eta: 0:03:49 lr: 0.000019 grad: 0.1156 (0.1225) loss: 0.8215 (0.8142) time: 0.1407 data: 0.0634 max mem: 9390 +Train: [75] [4700/6250] eta: 0:03:35 lr: 0.000019 grad: 0.1204 (0.1225) loss: 0.8176 (0.8142) time: 0.1386 data: 0.0632 max mem: 9390 +Train: [75] [4800/6250] eta: 0:03:21 lr: 0.000019 grad: 0.1169 (0.1225) loss: 0.8202 (0.8143) time: 0.1281 data: 0.0452 max mem: 9390 +Train: [75] [4900/6250] eta: 0:03:07 lr: 0.000019 grad: 0.1227 (0.1225) loss: 0.8128 (0.8143) time: 0.1511 data: 0.0764 max mem: 9390 +Train: [75] [5000/6250] eta: 0:02:53 lr: 0.000019 grad: 0.1164 (0.1225) loss: 0.8154 (0.8144) time: 0.1290 data: 0.0414 max mem: 9390 +Train: [75] [5100/6250] eta: 0:02:39 lr: 0.000019 grad: 0.1194 (0.1225) loss: 0.8116 (0.8144) time: 0.1343 data: 0.0545 max mem: 9390 +Train: [75] [5200/6250] eta: 0:02:24 lr: 0.000019 grad: 0.1270 (0.1226) loss: 0.8189 (0.8144) time: 0.1150 data: 0.0300 max mem: 9390 +Train: [75] [5300/6250] eta: 0:02:10 lr: 0.000019 grad: 0.1234 (0.1227) loss: 0.8166 (0.8144) time: 0.1114 data: 0.0289 max mem: 9390 +Train: [75] [5400/6250] eta: 0:01:56 lr: 0.000019 grad: 0.1214 (0.1227) loss: 0.8159 (0.8144) time: 0.1161 data: 0.0320 max mem: 9390 +Train: [75] [5500/6250] eta: 0:01:42 lr: 0.000019 grad: 0.1275 (0.1228) loss: 0.8125 (0.8143) time: 0.1314 data: 0.0542 max mem: 9390 +Train: [75] [5600/6250] eta: 0:01:29 lr: 0.000019 grad: 0.1302 (0.1229) loss: 0.8139 (0.8143) time: 0.1438 data: 0.0646 max mem: 9390 +Train: [75] [5700/6250] eta: 0:01:15 lr: 0.000019 grad: 0.1199 (0.1229) loss: 0.8103 (0.8142) time: 0.1656 data: 0.0824 max mem: 9390 +Train: [75] [5800/6250] eta: 0:01:01 lr: 0.000019 grad: 0.1244 (0.1230) loss: 0.8052 (0.8142) time: 0.1341 data: 0.0597 max mem: 9390 +Train: [75] [5900/6250] eta: 0:00:48 lr: 0.000019 grad: 0.1220 (0.1231) loss: 0.8170 (0.8141) time: 0.1722 data: 0.0824 max mem: 9390 +Train: [75] [6000/6250] eta: 0:00:34 lr: 0.000019 grad: 0.1220 (0.1231) loss: 0.8131 (0.8141) time: 0.1394 data: 0.0597 max mem: 9390 +Train: [75] [6100/6250] eta: 0:00:20 lr: 0.000019 grad: 0.1254 (0.1231) loss: 0.8123 (0.8141) time: 0.1335 data: 0.0556 max mem: 9390 +Train: [75] [6200/6250] eta: 0:00:06 lr: 0.000019 grad: 0.1164 (0.1231) loss: 0.8146 (0.8141) time: 0.1135 data: 0.0272 max mem: 9390 +Train: [75] [6249/6250] eta: 0:00:00 lr: 0.000019 grad: 0.1169 (0.1231) loss: 0.8142 (0.8141) time: 0.1418 data: 0.0677 max mem: 9390 +Train: [75] Total time: 0:14:28 (0.1389 s / it) +Averaged stats: lr: 0.000019 grad: 0.1169 (0.1231) loss: 0.8142 (0.8141) +Eval (hcp-train-subset): [75] [ 0/62] eta: 0:03:46 loss: 0.8386 (0.8386) time: 3.6525 data: 3.5836 max mem: 9390 +Eval (hcp-train-subset): [75] [61/62] eta: 0:00:00 loss: 0.8242 (0.8261) time: 0.1195 data: 0.0947 max mem: 9390 +Eval (hcp-train-subset): [75] Total time: 0:00:12 (0.1976 s / it) +Averaged stats (hcp-train-subset): loss: 0.8242 (0.8261) +Eval (hcp-val): [75] [ 0/62] eta: 0:03:25 loss: 0.8251 (0.8251) time: 3.3176 data: 3.2463 max mem: 9390 +Eval (hcp-val): [75] [61/62] eta: 0:00:00 loss: 0.8294 (0.8309) time: 0.1245 data: 0.0994 max mem: 9390 +Eval (hcp-val): [75] Total time: 0:00:13 (0.2243 s / it) +Averaged stats (hcp-val): loss: 0.8294 (0.8309) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +Train: [76] [ 0/6250] eta: 8:29:38 lr: 0.000019 grad: 0.4300 (0.4300) loss: 0.8225 (0.8225) time: 4.8926 data: 4.6719 max mem: 9390 +Train: [76] [ 100/6250] eta: 0:26:35 lr: 0.000019 grad: 0.1239 (0.1539) loss: 0.8053 (0.8177) time: 0.2770 data: 0.1468 max mem: 9390 +Train: [76] [ 200/6250] eta: 0:24:39 lr: 0.000019 grad: 0.1291 (0.1415) loss: 0.8170 (0.8161) time: 0.2298 data: 0.1087 max mem: 9390 +Train: [76] [ 300/6250] eta: 0:23:59 lr: 0.000019 grad: 0.1161 (0.1365) loss: 0.8177 (0.8162) time: 0.2239 data: 0.0837 max mem: 9390 +Train: [76] [ 400/6250] eta: 0:22:58 lr: 0.000019 grad: 0.1266 (0.1339) loss: 0.8139 (0.8161) time: 0.2087 data: 0.0854 max mem: 9390 +Train: [76] [ 500/6250] eta: 0:24:03 lr: 0.000019 grad: 0.1318 (0.1332) loss: 0.8039 (0.8149) time: 0.4656 data: 0.2653 max mem: 9390 +Train: [76] [ 600/6250] eta: 0:23:22 lr: 0.000019 grad: 0.1248 (0.1325) loss: 0.8041 (0.8141) time: 0.2079 data: 0.0614 max mem: 9390 +Train: [76] [ 700/6250] eta: 0:22:51 lr: 0.000019 grad: 0.1237 (0.1316) loss: 0.8197 (0.8140) time: 0.1720 data: 0.0640 max mem: 9390 +Train: [76] [ 800/6250] eta: 0:22:40 lr: 0.000018 grad: 0.1236 (0.1309) loss: 0.8152 (0.8140) time: 0.2937 data: 0.1558 max mem: 9390 +Train: [76] [ 900/6250] eta: 0:22:04 lr: 0.000018 grad: 0.1194 (0.1300) loss: 0.8187 (0.8142) time: 0.1875 data: 0.0794 max mem: 9390 +Train: [76] [1000/6250] eta: 0:21:09 lr: 0.000018 grad: 0.1194 (0.1289) loss: 0.8165 (0.8146) time: 0.1537 data: 0.0284 max mem: 9390 +Train: [76] [1100/6250] eta: 0:20:41 lr: 0.000018 grad: 0.1121 (0.1284) loss: 0.8180 (0.8147) time: 0.2670 data: 0.1016 max mem: 9390 +Train: [76] [1200/6250] eta: 0:20:21 lr: 0.000018 grad: 0.1209 (0.1278) loss: 0.8157 (0.8148) time: 0.4863 data: 0.3648 max mem: 9390 +Train: [76] [1300/6250] eta: 0:19:29 lr: 0.000018 grad: 0.1207 (0.1275) loss: 0.8152 (0.8149) time: 0.1748 data: 0.0805 max mem: 9390 +Train: [76] [1400/6250] eta: 0:18:46 lr: 0.000018 grad: 0.1226 (0.1273) loss: 0.8181 (0.8149) time: 0.1632 data: 0.0736 max mem: 9390 +Train: [76] [1500/6250] eta: 0:18:16 lr: 0.000018 grad: 0.1262 (0.1269) loss: 0.8129 (0.8148) time: 0.1772 data: 0.0765 max mem: 9390 +Train: [76] [1600/6250] eta: 0:17:43 lr: 0.000018 grad: 0.1185 (0.1268) loss: 0.8160 (0.8149) time: 0.1802 data: 0.0616 max mem: 9390 +Train: [76] [1700/6250] eta: 0:17:18 lr: 0.000018 grad: 0.1226 (0.1264) loss: 0.8150 (0.8150) time: 0.1238 data: 0.0003 max mem: 9390 +Train: [76] [1800/6250] eta: 0:16:54 lr: 0.000018 grad: 0.1202 (0.1260) loss: 0.8201 (0.8151) time: 0.3167 data: 0.2235 max mem: 9390 +Train: [76] [1900/6250] eta: 0:16:18 lr: 0.000018 grad: 0.1166 (0.1259) loss: 0.8207 (0.8151) time: 0.1677 data: 0.0678 max mem: 9390 +Train: [76] [2000/6250] eta: 0:15:50 lr: 0.000018 grad: 0.1218 (0.1258) loss: 0.8188 (0.8151) time: 0.1289 data: 0.0154 max mem: 9390 +Train: [76] [2100/6250] eta: 0:15:16 lr: 0.000018 grad: 0.1213 (0.1255) loss: 0.8127 (0.8152) time: 0.1583 data: 0.0659 max mem: 9390 +Train: [76] [2200/6250] eta: 0:14:50 lr: 0.000018 grad: 0.1165 (0.1253) loss: 0.8124 (0.8151) time: 0.2277 data: 0.1410 max mem: 9390 +Train: [76] [2300/6250] eta: 0:14:23 lr: 0.000018 grad: 0.1159 (0.1251) loss: 0.8160 (0.8152) time: 0.1197 data: 0.0003 max mem: 9390 +Train: [76] [2400/6250] eta: 0:13:58 lr: 0.000018 grad: 0.1231 (0.1250) loss: 0.8087 (0.8152) time: 0.2413 data: 0.1239 max mem: 9390 +Train: [76] [2500/6250] eta: 0:13:32 lr: 0.000018 grad: 0.1149 (0.1248) loss: 0.8109 (0.8152) time: 0.1824 data: 0.0841 max mem: 9390 +Train: [76] [2600/6250] eta: 0:13:09 lr: 0.000018 grad: 0.1181 (0.1245) loss: 0.8227 (0.8153) time: 0.1055 data: 0.0004 max mem: 9390 +Train: [76] [2700/6250] eta: 0:12:43 lr: 0.000018 grad: 0.1151 (0.1243) loss: 0.8205 (0.8153) time: 0.1553 data: 0.0638 max mem: 9390 +Train: [76] [2800/6250] eta: 0:12:17 lr: 0.000018 grad: 0.1170 (0.1241) loss: 0.8199 (0.8154) time: 0.2102 data: 0.1228 max mem: 9390 +Train: [76] [2900/6250] eta: 0:11:53 lr: 0.000018 grad: 0.1151 (0.1239) loss: 0.8171 (0.8155) time: 0.2603 data: 0.1534 max mem: 9390 +Train: [76] [3000/6250] eta: 0:11:33 lr: 0.000018 grad: 0.1085 (0.1237) loss: 0.8128 (0.8155) time: 0.3823 data: 0.2729 max mem: 9390 +Train: [76] [3100/6250] eta: 0:11:10 lr: 0.000018 grad: 0.1166 (0.1235) loss: 0.8163 (0.8156) time: 0.2549 data: 0.1660 max mem: 9390 +Train: [76] [3200/6250] eta: 0:10:44 lr: 0.000018 grad: 0.1151 (0.1234) loss: 0.8172 (0.8157) time: 0.1848 data: 0.0962 max mem: 9390 +Train: [76] [3300/6250] eta: 0:10:23 lr: 0.000018 grad: 0.1237 (0.1234) loss: 0.8112 (0.8157) time: 0.1871 data: 0.0968 max mem: 9390 +Train: [76] [3400/6250] eta: 0:10:00 lr: 0.000018 grad: 0.1155 (0.1233) loss: 0.8145 (0.8157) time: 0.2294 data: 0.1414 max mem: 9390 +Train: [76] [3500/6250] eta: 0:09:35 lr: 0.000018 grad: 0.1228 (0.1233) loss: 0.8159 (0.8157) time: 0.1753 data: 0.0928 max mem: 9390 +Train: [76] [3600/6250] eta: 0:09:12 lr: 0.000018 grad: 0.1117 (0.1233) loss: 0.8188 (0.8157) time: 0.1865 data: 0.0978 max mem: 9390 +Train: [76] [3700/6250] eta: 0:08:49 lr: 0.000018 grad: 0.1129 (0.1232) loss: 0.8211 (0.8156) time: 0.2348 data: 0.1416 max mem: 9390 +Train: [76] [3800/6250] eta: 0:08:26 lr: 0.000018 grad: 0.1205 (0.1232) loss: 0.8135 (0.8156) time: 0.1708 data: 0.0813 max mem: 9390 +Train: [76] [3900/6250] eta: 0:08:03 lr: 0.000018 grad: 0.1188 (0.1232) loss: 0.8192 (0.8156) time: 0.1543 data: 0.0633 max mem: 9390 +Train: [76] [4000/6250] eta: 0:07:40 lr: 0.000018 grad: 0.1204 (0.1231) loss: 0.8092 (0.8156) time: 0.1823 data: 0.0989 max mem: 9390 +Train: [76] [4100/6250] eta: 0:07:17 lr: 0.000018 grad: 0.1219 (0.1231) loss: 0.8127 (0.8155) time: 0.1246 data: 0.0320 max mem: 9390 +Train: [76] [4200/6250] eta: 0:06:55 lr: 0.000018 grad: 0.1188 (0.1231) loss: 0.8124 (0.8155) time: 0.2015 data: 0.1188 max mem: 9390 +Train: [76] [4300/6250] eta: 0:06:34 lr: 0.000018 grad: 0.1160 (0.1230) loss: 0.8146 (0.8155) time: 0.1616 data: 0.0811 max mem: 9390 +Train: [76] [4400/6250] eta: 0:06:13 lr: 0.000018 grad: 0.1194 (0.1230) loss: 0.8197 (0.8155) time: 0.2267 data: 0.1357 max mem: 9390 +Train: [76] [4500/6250] eta: 0:05:52 lr: 0.000018 grad: 0.1165 (0.1230) loss: 0.8152 (0.8155) time: 0.2052 data: 0.1169 max mem: 9390 +Train: [76] [4600/6250] eta: 0:05:32 lr: 0.000018 grad: 0.1225 (0.1230) loss: 0.8147 (0.8155) time: 0.1828 data: 0.0940 max mem: 9390 +Train: [76] [4700/6250] eta: 0:05:11 lr: 0.000018 grad: 0.1200 (0.1230) loss: 0.8142 (0.8155) time: 0.1634 data: 0.0648 max mem: 9390 +Train: [76] [4800/6250] eta: 0:04:50 lr: 0.000018 grad: 0.1273 (0.1230) loss: 0.8076 (0.8155) time: 0.1859 data: 0.0963 max mem: 9390 +Train: [76] [4900/6250] eta: 0:04:29 lr: 0.000018 grad: 0.1127 (0.1230) loss: 0.8174 (0.8154) time: 0.1764 data: 0.0884 max mem: 9390 +Train: [76] [5000/6250] eta: 0:04:08 lr: 0.000018 grad: 0.1228 (0.1231) loss: 0.8132 (0.8154) time: 0.1789 data: 0.0759 max mem: 9390 +Train: [76] [5100/6250] eta: 0:03:48 lr: 0.000017 grad: 0.1144 (0.1231) loss: 0.8176 (0.8153) time: 0.1474 data: 0.0651 max mem: 9390 +Train: [76] [5200/6250] eta: 0:03:28 lr: 0.000017 grad: 0.1231 (0.1232) loss: 0.8175 (0.8153) time: 0.4068 data: 0.3086 max mem: 9390 +Train: [76] [5300/6250] eta: 0:03:08 lr: 0.000017 grad: 0.1250 (0.1232) loss: 0.8161 (0.8153) time: 0.1610 data: 0.0608 max mem: 9390 +Train: [76] [5400/6250] eta: 0:02:48 lr: 0.000017 grad: 0.1190 (0.1233) loss: 0.8141 (0.8152) time: 0.1569 data: 0.0477 max mem: 9390 +Train: [76] [5500/6250] eta: 0:02:28 lr: 0.000017 grad: 0.1163 (0.1233) loss: 0.8143 (0.8152) time: 0.1773 data: 0.0938 max mem: 9390 +Train: [76] [5600/6250] eta: 0:02:08 lr: 0.000017 grad: 0.1328 (0.1233) loss: 0.8091 (0.8151) time: 0.2306 data: 0.1327 max mem: 9390 +Train: [76] [5700/6250] eta: 0:01:48 lr: 0.000017 grad: 0.1280 (0.1233) loss: 0.8126 (0.8151) time: 0.1773 data: 0.0905 max mem: 9390 +Train: [76] [5800/6250] eta: 0:01:28 lr: 0.000017 grad: 0.1164 (0.1232) loss: 0.8131 (0.8151) time: 0.1945 data: 0.1173 max mem: 9390 +Train: [76] [5900/6250] eta: 0:01:09 lr: 0.000017 grad: 0.1210 (0.1232) loss: 0.8140 (0.8151) time: 0.1693 data: 0.0834 max mem: 9390 +Train: [76] [6000/6250] eta: 0:00:49 lr: 0.000017 grad: 0.1150 (0.1231) loss: 0.8142 (0.8151) time: 0.1844 data: 0.0955 max mem: 9390 +Train: [76] [6100/6250] eta: 0:00:29 lr: 0.000017 grad: 0.1212 (0.1231) loss: 0.8146 (0.8151) time: 0.1794 data: 0.0979 max mem: 9390 +Train: [76] [6200/6250] eta: 0:00:09 lr: 0.000017 grad: 0.1198 (0.1231) loss: 0.8178 (0.8151) time: 0.2103 data: 0.1115 max mem: 9390 +Train: [76] [6249/6250] eta: 0:00:00 lr: 0.000017 grad: 0.1173 (0.1231) loss: 0.8134 (0.8151) time: 0.2229 data: 0.1407 max mem: 9390 +Train: [76] Total time: 0:20:38 (0.1981 s / it) +Averaged stats: lr: 0.000017 grad: 0.1173 (0.1231) loss: 0.8134 (0.8151) +Eval (hcp-train-subset): [76] [ 0/62] eta: 0:03:49 loss: 0.8405 (0.8405) time: 3.7007 data: 3.6303 max mem: 9390 +Eval (hcp-train-subset): [76] [61/62] eta: 0:00:00 loss: 0.8229 (0.8247) time: 0.1225 data: 0.0973 max mem: 9390 +Eval (hcp-train-subset): [76] Total time: 0:00:13 (0.2249 s / it) +Averaged stats (hcp-train-subset): loss: 0.8229 (0.8247) +Eval (hcp-val): [76] [ 0/62] eta: 0:04:41 loss: 0.8281 (0.8281) time: 4.5364 data: 4.4642 max mem: 9390 +Eval (hcp-val): [76] [61/62] eta: 0:00:00 loss: 0.8295 (0.8309) time: 0.1531 data: 0.1277 max mem: 9390 +Eval (hcp-val): [76] Total time: 0:00:16 (0.2630 s / it) +Averaged stats (hcp-val): loss: 0.8295 (0.8309) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +Train: [77] [ 0/6250] eta: 9:45:48 lr: 0.000017 grad: 0.1228 (0.1228) loss: 0.8487 (0.8487) time: 5.6238 data: 5.3768 max mem: 9390 +Train: [77] [ 100/6250] eta: 0:24:39 lr: 0.000017 grad: 0.1218 (0.1592) loss: 0.8180 (0.8231) time: 0.1846 data: 0.0622 max mem: 9390 +Train: [77] [ 200/6250] eta: 0:20:56 lr: 0.000017 grad: 0.1263 (0.1466) loss: 0.8108 (0.8197) time: 0.1822 data: 0.0660 max mem: 9390 +Train: [77] [ 300/6250] eta: 0:19:26 lr: 0.000017 grad: 0.1320 (0.1405) loss: 0.8131 (0.8187) time: 0.1341 data: 0.0222 max mem: 9390 +Train: [77] [ 400/6250] eta: 0:18:54 lr: 0.000017 grad: 0.1124 (0.1352) loss: 0.8227 (0.8192) time: 0.2107 data: 0.0958 max mem: 9390 +Train: [77] [ 500/6250] eta: 0:18:39 lr: 0.000017 grad: 0.1150 (0.1324) loss: 0.8268 (0.8199) time: 0.1968 data: 0.0978 max mem: 9390 +Train: [77] [ 600/6250] eta: 0:18:49 lr: 0.000017 grad: 0.1143 (0.1300) loss: 0.8221 (0.8206) time: 0.1925 data: 0.0849 max mem: 9390 +Train: [77] [ 700/6250] eta: 0:19:05 lr: 0.000017 grad: 0.1101 (0.1282) loss: 0.8207 (0.8207) time: 0.2848 data: 0.1217 max mem: 9390 +Train: [77] [ 800/6250] eta: 0:19:40 lr: 0.000017 grad: 0.1133 (0.1266) loss: 0.8246 (0.8208) time: 0.1260 data: 0.0003 max mem: 9390 +Train: [77] [ 900/6250] eta: 0:19:35 lr: 0.000017 grad: 0.1200 (0.1258) loss: 0.8173 (0.8206) time: 0.2066 data: 0.0789 max mem: 9390 +Train: [77] [1000/6250] eta: 0:19:03 lr: 0.000017 grad: 0.1102 (0.1251) loss: 0.8228 (0.8205) time: 0.1906 data: 0.0561 max mem: 9390 +Train: [77] [1100/6250] eta: 0:18:27 lr: 0.000017 grad: 0.1181 (0.1246) loss: 0.8175 (0.8203) time: 0.1902 data: 0.0883 max mem: 9390 +Train: [77] [1200/6250] eta: 0:18:16 lr: 0.000017 grad: 0.1142 (0.1244) loss: 0.8169 (0.8199) time: 0.1337 data: 0.0003 max mem: 9390 +Train: [77] [1300/6250] eta: 0:17:41 lr: 0.000017 grad: 0.1097 (0.1239) loss: 0.8208 (0.8197) time: 0.1786 data: 0.0912 max mem: 9390 +Train: [77] [1400/6250] eta: 0:17:20 lr: 0.000017 grad: 0.1110 (0.1236) loss: 0.8212 (0.8194) time: 0.1759 data: 0.0715 max mem: 9390 +Train: [77] [1500/6250] eta: 0:16:49 lr: 0.000017 grad: 0.1237 (0.1237) loss: 0.8137 (0.8190) time: 0.1363 data: 0.0367 max mem: 9390 +Train: [77] [1600/6250] eta: 0:16:17 lr: 0.000017 grad: 0.1214 (0.1236) loss: 0.8116 (0.8186) time: 0.1782 data: 0.0854 max mem: 9390 +Train: [77] [1700/6250] eta: 0:15:52 lr: 0.000017 grad: 0.1164 (0.1234) loss: 0.8154 (0.8185) time: 0.1150 data: 0.0212 max mem: 9390 +Train: [77] [1800/6250] eta: 0:15:24 lr: 0.000017 grad: 0.1242 (0.1233) loss: 0.8156 (0.8184) time: 0.2018 data: 0.0950 max mem: 9390 +Train: [77] [1900/6250] eta: 0:14:58 lr: 0.000017 grad: 0.1143 (0.1232) loss: 0.8184 (0.8183) time: 0.1785 data: 0.0668 max mem: 9390 +Train: [77] [2000/6250] eta: 0:14:37 lr: 0.000017 grad: 0.1271 (0.1233) loss: 0.8131 (0.8181) time: 0.1264 data: 0.0157 max mem: 9390 +Train: [77] [2100/6250] eta: 0:14:32 lr: 0.000017 grad: 0.1264 (0.1234) loss: 0.8147 (0.8179) time: 0.1524 data: 0.0095 max mem: 9390 +Train: [77] [2200/6250] eta: 0:14:03 lr: 0.000017 grad: 0.1284 (0.1236) loss: 0.8137 (0.8176) time: 0.1593 data: 0.0696 max mem: 9390 +Train: [77] [2300/6250] eta: 0:13:38 lr: 0.000017 grad: 0.1214 (0.1237) loss: 0.8099 (0.8175) time: 0.2150 data: 0.0711 max mem: 9390 +Train: [77] [2400/6250] eta: 0:13:13 lr: 0.000017 grad: 0.1224 (0.1237) loss: 0.8181 (0.8174) time: 0.1493 data: 0.0484 max mem: 9390 +Train: [77] [2500/6250] eta: 0:12:54 lr: 0.000017 grad: 0.1144 (0.1236) loss: 0.8139 (0.8173) time: 0.1119 data: 0.0182 max mem: 9390 +Train: [77] [2600/6250] eta: 0:12:29 lr: 0.000017 grad: 0.1178 (0.1235) loss: 0.8147 (0.8171) time: 0.1901 data: 0.0443 max mem: 9390 +Train: [77] [2700/6250] eta: 0:12:08 lr: 0.000017 grad: 0.1158 (0.1234) loss: 0.8115 (0.8171) time: 0.1574 data: 0.0599 max mem: 9390 +Train: [77] [2800/6250] eta: 0:11:45 lr: 0.000017 grad: 0.1165 (0.1232) loss: 0.8143 (0.8170) time: 0.2255 data: 0.1150 max mem: 9390 +Train: [77] [2900/6250] eta: 0:11:22 lr: 0.000017 grad: 0.1169 (0.1232) loss: 0.8136 (0.8170) time: 0.1701 data: 0.0831 max mem: 9390 +Train: [77] [3000/6250] eta: 0:11:01 lr: 0.000017 grad: 0.1154 (0.1231) loss: 0.8150 (0.8169) time: 0.2124 data: 0.1058 max mem: 9390 +Train: [77] [3100/6250] eta: 0:10:37 lr: 0.000017 grad: 0.1166 (0.1231) loss: 0.8161 (0.8169) time: 0.1973 data: 0.1165 max mem: 9390 +Train: [77] [3200/6250] eta: 0:10:20 lr: 0.000017 grad: 0.1157 (0.1231) loss: 0.8119 (0.8168) time: 0.2175 data: 0.1168 max mem: 9390 +Train: [77] [3300/6250] eta: 0:09:56 lr: 0.000016 grad: 0.1173 (0.1230) loss: 0.8132 (0.8167) time: 0.1710 data: 0.0835 max mem: 9390 +Train: [77] [3400/6250] eta: 0:09:32 lr: 0.000016 grad: 0.1209 (0.1229) loss: 0.8208 (0.8167) time: 0.1399 data: 0.0496 max mem: 9390 +Train: [77] [3500/6250] eta: 0:09:11 lr: 0.000016 grad: 0.1149 (0.1228) loss: 0.8147 (0.8166) time: 0.2510 data: 0.1570 max mem: 9390 +Train: [77] [3600/6250] eta: 0:08:52 lr: 0.000016 grad: 0.1121 (0.1227) loss: 0.8217 (0.8166) time: 0.1190 data: 0.0003 max mem: 9390 +Train: [77] [3700/6250] eta: 0:08:31 lr: 0.000016 grad: 0.1180 (0.1226) loss: 0.8204 (0.8167) time: 0.3238 data: 0.2381 max mem: 9390 +Train: [77] [3800/6250] eta: 0:08:09 lr: 0.000016 grad: 0.1187 (0.1225) loss: 0.8129 (0.8166) time: 0.2257 data: 0.1415 max mem: 9390 +Train: [77] [3900/6250] eta: 0:07:48 lr: 0.000016 grad: 0.1165 (0.1225) loss: 0.8146 (0.8165) time: 0.1992 data: 0.1010 max mem: 9390 +Train: [77] [4000/6250] eta: 0:07:27 lr: 0.000016 grad: 0.1102 (0.1224) loss: 0.8120 (0.8164) time: 0.1609 data: 0.0752 max mem: 9390 +Train: [77] [4100/6250] eta: 0:07:06 lr: 0.000016 grad: 0.1159 (0.1224) loss: 0.8088 (0.8164) time: 0.1798 data: 0.0926 max mem: 9390 +Train: [77] [4200/6250] eta: 0:06:45 lr: 0.000016 grad: 0.1211 (0.1225) loss: 0.8098 (0.8163) time: 0.1328 data: 0.0428 max mem: 9390 +Train: [77] [4300/6250] eta: 0:06:25 lr: 0.000016 grad: 0.1167 (0.1225) loss: 0.8073 (0.8162) time: 0.1536 data: 0.0639 max mem: 9390 +Train: [77] [4400/6250] eta: 0:06:06 lr: 0.000016 grad: 0.1149 (0.1224) loss: 0.8174 (0.8162) time: 0.1842 data: 0.1072 max mem: 9390 +Train: [77] [4500/6250] eta: 0:05:46 lr: 0.000016 grad: 0.1178 (0.1224) loss: 0.8164 (0.8161) time: 0.2485 data: 0.1538 max mem: 9390 +Train: [77] [4600/6250] eta: 0:05:28 lr: 0.000016 grad: 0.1174 (0.1225) loss: 0.8077 (0.8161) time: 0.2594 data: 0.1350 max mem: 9390 +Train: [77] [4700/6250] eta: 0:05:10 lr: 0.000016 grad: 0.1263 (0.1225) loss: 0.8137 (0.8160) time: 0.1196 data: 0.0004 max mem: 9390 +Train: [77] [4800/6250] eta: 0:04:49 lr: 0.000016 grad: 0.1144 (0.1226) loss: 0.8165 (0.8159) time: 0.1892 data: 0.0930 max mem: 9390 +Train: [77] [4900/6250] eta: 0:04:29 lr: 0.000016 grad: 0.1157 (0.1226) loss: 0.8115 (0.8158) time: 0.1540 data: 0.0643 max mem: 9390 +Train: [77] [5000/6250] eta: 0:04:09 lr: 0.000016 grad: 0.1226 (0.1227) loss: 0.8103 (0.8157) time: 0.2159 data: 0.1347 max mem: 9390 +Train: [77] [5100/6250] eta: 0:03:49 lr: 0.000016 grad: 0.1147 (0.1226) loss: 0.8144 (0.8157) time: 0.3031 data: 0.2261 max mem: 9390 +Train: [77] [5200/6250] eta: 0:03:29 lr: 0.000016 grad: 0.1222 (0.1225) loss: 0.8116 (0.8157) time: 0.2058 data: 0.1276 max mem: 9390 +Train: [77] [5300/6250] eta: 0:03:09 lr: 0.000016 grad: 0.1227 (0.1225) loss: 0.8130 (0.8156) time: 0.3023 data: 0.2224 max mem: 9390 +Train: [77] [5400/6250] eta: 0:02:50 lr: 0.000016 grad: 0.1253 (0.1226) loss: 0.8123 (0.8156) time: 0.3626 data: 0.2576 max mem: 9390 +Train: [77] [5500/6250] eta: 0:02:30 lr: 0.000016 grad: 0.1251 (0.1226) loss: 0.8099 (0.8155) time: 0.1717 data: 0.0888 max mem: 9390 +Train: [77] [5600/6250] eta: 0:02:10 lr: 0.000016 grad: 0.1221 (0.1227) loss: 0.8126 (0.8155) time: 0.2011 data: 0.1151 max mem: 9390 +Train: [77] [5700/6250] eta: 0:01:50 lr: 0.000016 grad: 0.1254 (0.1229) loss: 0.8114 (0.8154) time: 0.2058 data: 0.1192 max mem: 9390 +Train: [77] [5800/6250] eta: 0:01:29 lr: 0.000016 grad: 0.1277 (0.1230) loss: 0.8079 (0.8152) time: 0.1840 data: 0.0984 max mem: 9390 +Train: [77] [5900/6250] eta: 0:01:09 lr: 0.000016 grad: 0.1243 (0.1232) loss: 0.8096 (0.8151) time: 0.1976 data: 0.1068 max mem: 9390 +Train: [77] [6000/6250] eta: 0:00:49 lr: 0.000016 grad: 0.1204 (0.1233) loss: 0.8116 (0.8150) time: 0.4503 data: 0.3731 max mem: 9390 +Train: [77] [6100/6250] eta: 0:00:29 lr: 0.000016 grad: 0.1193 (0.1234) loss: 0.8163 (0.8150) time: 0.1833 data: 0.0922 max mem: 9390 +Train: [77] [6200/6250] eta: 0:00:09 lr: 0.000016 grad: 0.1242 (0.1235) loss: 0.8072 (0.8148) time: 0.1589 data: 0.0788 max mem: 9390 +Train: [77] [6249/6250] eta: 0:00:00 lr: 0.000016 grad: 0.1234 (0.1236) loss: 0.8059 (0.8148) time: 0.1751 data: 0.0850 max mem: 9390 +Train: [77] Total time: 0:20:50 (0.2001 s / it) +Averaged stats: lr: 0.000016 grad: 0.1234 (0.1236) loss: 0.8059 (0.8148) +Eval (hcp-train-subset): [77] [ 0/62] eta: 0:05:37 loss: 0.8364 (0.8364) time: 5.4361 data: 5.4057 max mem: 9390 +Eval (hcp-train-subset): [77] [61/62] eta: 0:00:00 loss: 0.8190 (0.8230) time: 0.1253 data: 0.1003 max mem: 9390 +Eval (hcp-train-subset): [77] Total time: 0:00:14 (0.2323 s / it) +Averaged stats (hcp-train-subset): loss: 0.8190 (0.8230) +Eval (hcp-val): [77] [ 0/62] eta: 0:05:54 loss: 0.8250 (0.8250) time: 5.7148 data: 5.6837 max mem: 9390 +Eval (hcp-val): [77] [61/62] eta: 0:00:00 loss: 0.8293 (0.8302) time: 0.1364 data: 0.1112 max mem: 9390 +Eval (hcp-val): [77] Total time: 0:00:14 (0.2337 s / it) +Averaged stats (hcp-val): loss: 0.8293 (0.8302) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +Train: [78] [ 0/6250] eta: 12:21:44 lr: 0.000016 grad: 0.1208 (0.1208) loss: 0.8101 (0.8101) time: 7.1208 data: 6.9970 max mem: 9390 +Train: [78] [ 100/6250] eta: 0:25:54 lr: 0.000016 grad: 0.1227 (0.1573) loss: 0.8280 (0.8270) time: 0.1676 data: 0.0636 max mem: 9390 +Train: [78] [ 200/6250] eta: 0:21:36 lr: 0.000016 grad: 0.1206 (0.1426) loss: 0.8051 (0.8240) time: 0.1723 data: 0.0581 max mem: 9390 +Train: [78] [ 300/6250] eta: 0:21:04 lr: 0.000016 grad: 0.1316 (0.1392) loss: 0.8147 (0.8220) time: 0.2302 data: 0.1019 max mem: 9390 +Train: [78] [ 400/6250] eta: 0:20:23 lr: 0.000016 grad: 0.1199 (0.1374) loss: 0.8145 (0.8201) time: 0.1825 data: 0.0885 max mem: 9390 +Train: [78] [ 500/6250] eta: 0:19:45 lr: 0.000016 grad: 0.1200 (0.1351) loss: 0.8187 (0.8192) time: 0.2108 data: 0.1188 max mem: 9390 +Train: [78] [ 600/6250] eta: 0:20:27 lr: 0.000016 grad: 0.1148 (0.1332) loss: 0.8206 (0.8189) time: 0.2428 data: 0.1013 max mem: 9390 +Train: [78] [ 700/6250] eta: 0:20:28 lr: 0.000016 grad: 0.1299 (0.1321) loss: 0.8219 (0.8189) time: 0.3489 data: 0.2531 max mem: 9390 +Train: [78] [ 800/6250] eta: 0:20:00 lr: 0.000016 grad: 0.1161 (0.1307) loss: 0.8184 (0.8187) time: 0.1480 data: 0.0003 max mem: 9390 +Train: [78] [ 900/6250] eta: 0:20:00 lr: 0.000016 grad: 0.1196 (0.1298) loss: 0.8193 (0.8185) time: 0.3762 data: 0.2407 max mem: 9390 +Train: [78] [1000/6250] eta: 0:19:41 lr: 0.000016 grad: 0.1205 (0.1292) loss: 0.8158 (0.8183) time: 0.2753 data: 0.1733 max mem: 9390 +Train: [78] [1100/6250] eta: 0:18:51 lr: 0.000016 grad: 0.1221 (0.1288) loss: 0.8140 (0.8180) time: 0.1851 data: 0.0915 max mem: 9390 +Train: [78] [1200/6250] eta: 0:18:26 lr: 0.000016 grad: 0.1208 (0.1282) loss: 0.8194 (0.8177) time: 0.1677 data: 0.0118 max mem: 9390 +Train: [78] [1300/6250] eta: 0:17:56 lr: 0.000016 grad: 0.1156 (0.1279) loss: 0.8137 (0.8173) time: 0.1196 data: 0.0003 max mem: 9390 +Train: [78] [1400/6250] eta: 0:17:25 lr: 0.000016 grad: 0.1197 (0.1276) loss: 0.8184 (0.8171) time: 0.1487 data: 0.0304 max mem: 9390 +Train: [78] [1500/6250] eta: 0:17:00 lr: 0.000015 grad: 0.1172 (0.1273) loss: 0.8181 (0.8169) time: 0.1203 data: 0.0178 max mem: 9390 +Train: [78] [1600/6250] eta: 0:16:26 lr: 0.000015 grad: 0.1145 (0.1269) loss: 0.8156 (0.8167) time: 0.1494 data: 0.0617 max mem: 9390 +Train: [78] [1700/6250] eta: 0:16:08 lr: 0.000015 grad: 0.1184 (0.1266) loss: 0.8171 (0.8165) time: 0.1129 data: 0.0003 max mem: 9390 +Train: [78] [1800/6250] eta: 0:15:40 lr: 0.000015 grad: 0.1160 (0.1263) loss: 0.8178 (0.8165) time: 0.1526 data: 0.0395 max mem: 9390 +Train: [78] [1900/6250] eta: 0:15:24 lr: 0.000015 grad: 0.1209 (0.1261) loss: 0.8112 (0.8163) time: 0.3798 data: 0.2660 max mem: 9390 +Train: [78] [2000/6250] eta: 0:15:11 lr: 0.000015 grad: 0.1214 (0.1260) loss: 0.8148 (0.8162) time: 0.3388 data: 0.1865 max mem: 9390 +Train: [78] [2100/6250] eta: 0:14:37 lr: 0.000015 grad: 0.1165 (0.1258) loss: 0.8112 (0.8160) time: 0.1679 data: 0.0760 max mem: 9390 +Train: [78] [2200/6250] eta: 0:14:10 lr: 0.000015 grad: 0.1238 (0.1257) loss: 0.8082 (0.8159) time: 0.2084 data: 0.1101 max mem: 9390 +Train: [78] [2300/6250] eta: 0:13:53 lr: 0.000015 grad: 0.1240 (0.1254) loss: 0.8116 (0.8158) time: 0.2942 data: 0.1997 max mem: 9390 +Train: [78] [2400/6250] eta: 0:13:28 lr: 0.000015 grad: 0.1232 (0.1252) loss: 0.8126 (0.8157) time: 0.1498 data: 0.0447 max mem: 9390 +Train: [78] [2500/6250] eta: 0:13:02 lr: 0.000015 grad: 0.1139 (0.1251) loss: 0.8124 (0.8157) time: 0.1811 data: 0.0908 max mem: 9390 +Train: [78] [2600/6250] eta: 0:12:38 lr: 0.000015 grad: 0.1222 (0.1249) loss: 0.8117 (0.8156) time: 0.2406 data: 0.1530 max mem: 9390 +Train: [78] [2700/6250] eta: 0:12:16 lr: 0.000015 grad: 0.1237 (0.1247) loss: 0.8128 (0.8157) time: 0.1807 data: 0.0772 max mem: 9390 +Train: [78] [2800/6250] eta: 0:11:52 lr: 0.000015 grad: 0.1190 (0.1246) loss: 0.8134 (0.8157) time: 0.1746 data: 0.0824 max mem: 9390 +Train: [78] [2900/6250] eta: 0:11:32 lr: 0.000015 grad: 0.1199 (0.1244) loss: 0.8205 (0.8157) time: 0.1214 data: 0.0177 max mem: 9390 +Train: [78] [3000/6250] eta: 0:11:10 lr: 0.000015 grad: 0.1250 (0.1244) loss: 0.8155 (0.8158) time: 0.2955 data: 0.1933 max mem: 9390 +Train: [78] [3100/6250] eta: 0:10:47 lr: 0.000015 grad: 0.1180 (0.1243) loss: 0.8084 (0.8159) time: 0.1535 data: 0.0285 max mem: 9390 +Train: [78] [3200/6250] eta: 0:10:24 lr: 0.000015 grad: 0.1206 (0.1242) loss: 0.8158 (0.8159) time: 0.1698 data: 0.0768 max mem: 9390 +Train: [78] [3300/6250] eta: 0:10:02 lr: 0.000015 grad: 0.1150 (0.1241) loss: 0.8252 (0.8159) time: 0.2054 data: 0.1114 max mem: 9390 +Train: [78] [3400/6250] eta: 0:09:40 lr: 0.000015 grad: 0.1225 (0.1242) loss: 0.8121 (0.8159) time: 0.2192 data: 0.1227 max mem: 9390 +Train: [78] [3500/6250] eta: 0:09:22 lr: 0.000015 grad: 0.1129 (0.1242) loss: 0.8199 (0.8159) time: 0.1472 data: 0.0105 max mem: 9390 +Train: [78] [3600/6250] eta: 0:09:01 lr: 0.000015 grad: 0.1275 (0.1242) loss: 0.8148 (0.8160) time: 0.1112 data: 0.0183 max mem: 9390 +Train: [78] [3700/6250] eta: 0:08:39 lr: 0.000015 grad: 0.1189 (0.1241) loss: 0.8196 (0.8160) time: 0.1594 data: 0.0574 max mem: 9390 +Train: [78] [3800/6250] eta: 0:08:17 lr: 0.000015 grad: 0.1249 (0.1241) loss: 0.8156 (0.8161) time: 0.1757 data: 0.0809 max mem: 9390 +Train: [78] [3900/6250] eta: 0:07:54 lr: 0.000015 grad: 0.1240 (0.1240) loss: 0.8171 (0.8160) time: 0.1650 data: 0.0783 max mem: 9390 +Train: [78] [4000/6250] eta: 0:07:33 lr: 0.000015 grad: 0.1213 (0.1240) loss: 0.8131 (0.8160) time: 0.1088 data: 0.0173 max mem: 9390 +Train: [78] [4100/6250] eta: 0:07:11 lr: 0.000015 grad: 0.1178 (0.1241) loss: 0.8169 (0.8160) time: 0.1624 data: 0.0689 max mem: 9390 +Train: [78] [4200/6250] eta: 0:06:51 lr: 0.000015 grad: 0.1315 (0.1242) loss: 0.8107 (0.8159) time: 0.1509 data: 0.0440 max mem: 9390 +Train: [78] [4300/6250] eta: 0:06:31 lr: 0.000015 grad: 0.1148 (0.1244) loss: 0.8198 (0.8159) time: 0.1849 data: 0.0946 max mem: 9390 +Train: [78] [4400/6250] eta: 0:06:10 lr: 0.000015 grad: 0.1234 (0.1245) loss: 0.8138 (0.8158) time: 0.1966 data: 0.1104 max mem: 9390 +Train: [78] [4500/6250] eta: 0:05:50 lr: 0.000015 grad: 0.1288 (0.1246) loss: 0.8141 (0.8157) time: 0.1829 data: 0.0930 max mem: 9390 +Train: [78] [4600/6250] eta: 0:05:30 lr: 0.000015 grad: 0.1232 (0.1246) loss: 0.8095 (0.8156) time: 0.2153 data: 0.1216 max mem: 9390 +Train: [78] [4700/6250] eta: 0:05:09 lr: 0.000015 grad: 0.1262 (0.1246) loss: 0.8141 (0.8156) time: 0.1461 data: 0.0527 max mem: 9390 +Train: [78] [4800/6250] eta: 0:04:50 lr: 0.000015 grad: 0.1237 (0.1247) loss: 0.8162 (0.8155) time: 0.1123 data: 0.0003 max mem: 9390 +Train: [78] [4900/6250] eta: 0:04:31 lr: 0.000015 grad: 0.1315 (0.1248) loss: 0.8076 (0.8154) time: 0.1996 data: 0.0883 max mem: 9390 +Train: [78] [5000/6250] eta: 0:04:12 lr: 0.000015 grad: 0.1327 (0.1250) loss: 0.8014 (0.8153) time: 0.2085 data: 0.0361 max mem: 9390 +Train: [78] [5100/6250] eta: 0:03:53 lr: 0.000015 grad: 0.1255 (0.1251) loss: 0.8076 (0.8151) time: 0.4615 data: 0.3633 max mem: 9390 +Train: [78] [5200/6250] eta: 0:03:33 lr: 0.000015 grad: 0.1340 (0.1253) loss: 0.8054 (0.8150) time: 0.2267 data: 0.0778 max mem: 9390 +Train: [78] [5300/6250] eta: 0:03:13 lr: 0.000015 grad: 0.1261 (0.1253) loss: 0.8072 (0.8149) time: 0.1661 data: 0.0765 max mem: 9390 +Train: [78] [5400/6250] eta: 0:02:53 lr: 0.000015 grad: 0.1251 (0.1255) loss: 0.8100 (0.8148) time: 0.1141 data: 0.0003 max mem: 9390 +Train: [78] [5500/6250] eta: 0:02:33 lr: 0.000015 grad: 0.1241 (0.1256) loss: 0.8135 (0.8147) time: 0.1210 data: 0.0245 max mem: 9390 +Train: [78] [5600/6250] eta: 0:02:12 lr: 0.000015 grad: 0.1245 (0.1256) loss: 0.8046 (0.8146) time: 0.1992 data: 0.0554 max mem: 9390 +Train: [78] [5700/6250] eta: 0:01:52 lr: 0.000015 grad: 0.1296 (0.1257) loss: 0.8120 (0.8145) time: 0.2395 data: 0.1303 max mem: 9390 +Train: [78] [5800/6250] eta: 0:01:32 lr: 0.000015 grad: 0.1262 (0.1258) loss: 0.8156 (0.8145) time: 0.1566 data: 0.0712 max mem: 9390 +Train: [78] [5900/6250] eta: 0:01:11 lr: 0.000015 grad: 0.1289 (0.1259) loss: 0.8116 (0.8144) time: 0.1727 data: 0.0896 max mem: 9390 +Train: [78] [6000/6250] eta: 0:00:50 lr: 0.000015 grad: 0.1256 (0.1260) loss: 0.8093 (0.8143) time: 0.1843 data: 0.0882 max mem: 9390 +Train: [78] [6100/6250] eta: 0:00:30 lr: 0.000015 grad: 0.1162 (0.1260) loss: 0.8108 (0.8143) time: 0.1683 data: 0.0681 max mem: 9390 +Train: [78] [6200/6250] eta: 0:00:10 lr: 0.000014 grad: 0.1250 (0.1261) loss: 0.8057 (0.8143) time: 0.1911 data: 0.0916 max mem: 9390 +Train: [78] [6249/6250] eta: 0:00:00 lr: 0.000014 grad: 0.1255 (0.1261) loss: 0.8120 (0.8142) time: 0.1650 data: 0.0776 max mem: 9390 +Train: [78] Total time: 0:21:12 (0.2036 s / it) +Averaged stats: lr: 0.000014 grad: 0.1255 (0.1261) loss: 0.8120 (0.8142) +Eval (hcp-train-subset): [78] [ 0/62] eta: 0:05:21 loss: 0.8333 (0.8333) time: 5.1796 data: 5.1313 max mem: 9390 +Eval (hcp-train-subset): [78] [61/62] eta: 0:00:00 loss: 0.8187 (0.8225) time: 0.1340 data: 0.1037 max mem: 9390 +Eval (hcp-train-subset): [78] Total time: 0:00:14 (0.2358 s / it) +Averaged stats (hcp-train-subset): loss: 0.8187 (0.8225) +Eval (hcp-val): [78] [ 0/62] eta: 0:04:00 loss: 0.8257 (0.8257) time: 3.8833 data: 3.7774 max mem: 9390 +Eval (hcp-val): [78] [61/62] eta: 0:00:00 loss: 0.8309 (0.8305) time: 0.1223 data: 0.0968 max mem: 9390 +Eval (hcp-val): [78] Total time: 0:00:14 (0.2313 s / it) +Averaged stats (hcp-val): loss: 0.8309 (0.8305) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +Train: [79] [ 0/6250] eta: 12:23:23 lr: 0.000014 grad: 0.1511 (0.1511) loss: 0.8294 (0.8294) time: 7.1366 data: 7.0260 max mem: 9390 +Train: [79] [ 100/6250] eta: 0:24:36 lr: 0.000014 grad: 0.1479 (0.1812) loss: 0.8044 (0.8149) time: 0.1350 data: 0.0006 max mem: 9390 +Train: [79] [ 200/6250] eta: 0:21:00 lr: 0.000014 grad: 0.1428 (0.1751) loss: 0.8122 (0.8096) time: 0.1654 data: 0.0580 max mem: 9390 +Train: [79] [ 300/6250] eta: 0:19:40 lr: 0.000014 grad: 0.1296 (0.1624) loss: 0.8207 (0.8102) time: 0.1945 data: 0.0683 max mem: 9390 +Train: [79] [ 400/6250] eta: 0:18:56 lr: 0.000014 grad: 0.1168 (0.1543) loss: 0.8149 (0.8114) time: 0.1952 data: 0.0671 max mem: 9390 +Train: [79] [ 500/6250] eta: 0:18:27 lr: 0.000014 grad: 0.1268 (0.1498) loss: 0.8106 (0.8113) time: 0.1266 data: 0.0101 max mem: 9390 +Train: [79] [ 600/6250] eta: 0:18:17 lr: 0.000014 grad: 0.1210 (0.1467) loss: 0.8114 (0.8111) time: 0.2317 data: 0.1092 max mem: 9390 +pretraining fmri mae +start: 2026-04-01 13:10:37 +cwd: /data/connor/fmri-fm +sha: 7f4cedc35609f6857314e0d1ea6657523f17ddeb, status: has uncommitted changes, branch: dev/clane9 +config: +name: input_space_v3/flat_lr1e-3_2/pretrain +notes: input_space ablation v3 flat_lr1e-3_2; use tube masking and on-disk data (input_space=flat + base_lr=1e-3 seed=5402) +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain +input_space: flat +patch_size: 16 +num_frames: 16 +t_patch_size: 4 +mask_ratio: 0.9 +pred_mask_ratio: null +masking: tube +masking_kwargs: {} +mask_patch_size: null +model: mae_vit_base +model_kwargs: + decoding: attn + pos_embed: sep + target_norm: null + pca_norm_nc: 2 + t_pred_stride: 2 + no_decode_pos: true + mask_drop_scale: false + pred_edge_pad: 0 + gauss_sigma: null + class_token: true + reg_tokens: 0 + no_embed_class: true + head_init_scale: 0.0 + decoder_depth: 4 + drop_path_rate: 0.0 +datasets: + hcp-train: + type: wds + url: /data/fmri-datasets/pretrain/hcpya-all.${input_space}.wds/hcpya-all-${input_space}-{00000..01799}.tar + clipping: random + clipping_kwargs: + oversample: 4.0 + shuffle: true + buffer_size: 2000 + samples_per_epoch: 200000 + hcp-train-subset: + type: arrow + root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/validation + split_range: + - 0 + - 2000 + shuffle: false + hcp-val: + type: arrow + root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/test + split_range: + - 0 + - 2000 + shuffle: false +train_dataset: hcp-train +eval_datasets: +- hcp-train-subset +- hcp-val +val_dataset: null +clip_vmax: 3.0 +normalize: frame +tr_scale: null +crop_scale: null +crop_aspect: null +gray_jitter: null +num_workers: 16 +epochs: 100 +batch_size: 32 +accum_iter: 1 +base_lr: 0.001 +min_lr: 0.0 +warmup_epochs: 5 +weight_decay: 0.05 +betas: +- 0.9 +- 0.95 +clip_grad: 1.0 +amp: true +amp_dtype: float16 +ckpt: null +resume: true +auto_resume: true +start_epoch: 0 +max_checkpoints: 0 +checkpoint_period: null +plot_period: 5 +device: cuda +presend_cuda: false +seed: 5402 +debug: false +wandb: true +wandb_entity: null +wandb_project: fMRI-foundation-model +rank: 0 +world_size: 1 +gpu: 0 +distributed: true +dist_backend: nccl +in_chans: 1 +img_size: +- 224 +- 560 + +train transform: +Compose( + ToTensor() + TemporalCenterCrop(num_frames=16) + Normalize(mode='frame') + Clip(vmax=3.0) + FlatUnmask((224, 560)) +) +val transform: +Compose( + ToTensor() + TemporalCenterCrop(num_frames=16) + Normalize(mode='frame') + Clip(vmax=3.0) + FlatUnmask((224, 560)) +) +mask generator: +TubeMasking( + mask_ratio=0.9 + (patchify): Patchify2D((224, 560), (16, 16), in_chans=1) +) +loading dataset: hcp-train + +type: wds +url: /data/fmri-datasets/pretrain/hcpya-all.${input_space}.wds/hcpya-all-${input_space}-{00000..01799}.tar +clipping: random +clipping_kwargs: + oversample: 4.0 +shuffle: true +buffer_size: 2000 +samples_per_epoch: 200000 + +loading dataset: hcp-train-subset + +type: arrow +root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/validation +split_range: +- 0 +- 2000 +shuffle: false + +split indices: [899, 472, 767, 116, 1265, 1852, 300, 1335, 361, 1560] +loading dataset: hcp-val + +type: arrow +root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/test +split_range: +- 0 +- 2000 +shuffle: false + +split indices: [1075, 1189, 738, 1350, 965, 1964, 1367, 1183, 1619, 1407] +model: +MaskedAutoencoderViT( + decoding=attn, t_pred_stride=2, pred_edge_pad=0, no_decode_pos=True + (encoder): MaskedEncoder( + class_token=True, reg_tokens=0, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) + (pred_patchify): StridedPatchify3D((16, 224, 560), (2, 16, 16), in_chans=1, t_stride=2) + (decoder): MaskedDecoder( + cross_decode=False, class_token=True, no_embed_class=True + (pos_embed): SeparablePosEmbed(512, (4, 14, 35)) + (proj): Linear(in_features=768, out_features=512, bias=True) + (blocks): ModuleList( + (0-3): 4 x Block( + (norm1): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=16 + (q): Linear(in_features=512, out_features=512, bias=True) + (k): Linear(in_features=512, out_features=512, bias=True) + (v): Linear(in_features=512, out_features=512, bias=True) + (proj): Linear(in_features=512, out_features=512, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=512, out_features=2048, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=2048, out_features=512, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (head): Linear(in_features=512, out_features=512, bias=True) + ) +) +num params: 99.7M +total batch size: 32 = 32 bs per gpu x 1 accum x 1 gpus +lr: 1.25e-04 = 1.00e-03 x 32 / 256 +full schedule: epochs = 100 (steps = 625000) +warmup: epochs = 5 (steps = 31250) +loaded model state from checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +loaded optimizer state, resuming training from 79 +start training for 100 epochs +Train: [79] [ 0/6250] eta: 1 day, 13:13:17 lr: 0.000014 grad: 0.1346 (0.1346) loss: 0.8418 (0.8418) time: 21.4396 data: 17.3816 max mem: 9353 +Train: [79] [ 100/6250] eta: 1:38:13 lr: 0.000014 grad: 0.1244 (0.1352) loss: 0.8296 (0.8367) time: 0.1069 data: 0.0002 max mem: 9390 +Train: [79] [ 200/6250] eta: 1:24:09 lr: 0.000014 grad: 0.1157 (0.1277) loss: 0.8226 (0.8320) time: 1.6961 data: 1.5855 max mem: 9390 +Train: [79] [ 300/6250] eta: 1:08:38 lr: 0.000014 grad: 0.1286 (0.1293) loss: 0.8159 (0.8282) time: 0.3273 data: 0.2399 max mem: 9390 +Train: [79] [ 400/6250] eta: 1:08:34 lr: 0.000014 grad: 0.1214 (0.1290) loss: 0.8156 (0.8256) time: 0.4929 data: 0.2919 max mem: 9390 +Train: [79] [ 500/6250] eta: 1:11:51 lr: 0.000014 grad: 0.1416 (0.1310) loss: 0.8111 (0.8228) time: 1.5422 data: 1.4382 max mem: 9390 +Train: [79] [ 600/6250] eta: 1:07:41 lr: 0.000014 grad: 0.1347 (0.1322) loss: 0.8095 (0.8207) time: 1.2589 data: 1.1087 max mem: 9390 +Train: [79] [ 700/6250] eta: 1:03:16 lr: 0.000014 grad: 0.1176 (0.1319) loss: 0.8087 (0.8193) time: 0.3280 data: 0.2343 max mem: 9390 +Train: [79] [ 800/6250] eta: 1:05:41 lr: 0.000014 grad: 0.1276 (0.1313) loss: 0.8078 (0.8185) time: 0.1095 data: 0.0002 max mem: 9390 +Train: [79] [ 900/6250] eta: 1:03:04 lr: 0.000014 grad: 0.1143 (0.1306) loss: 0.8181 (0.8180) time: 0.6621 data: 0.5402 max mem: 9390 +Train: [79] [1000/6250] eta: 0:58:28 lr: 0.000014 grad: 0.1169 (0.1304) loss: 0.8204 (0.8175) time: 0.4062 data: 0.3228 max mem: 9390 +Train: [79] [1100/6250] eta: 0:53:59 lr: 0.000014 grad: 0.1244 (0.1299) loss: 0.8083 (0.8170) time: 0.1191 data: 0.0006 max mem: 9390 +Train: [79] [1200/6250] eta: 0:49:53 lr: 0.000014 grad: 0.1162 (0.1291) loss: 0.8187 (0.8168) time: 0.1052 data: 0.0023 max mem: 9390 +Train: [79] [1300/6250] eta: 0:46:39 lr: 0.000014 grad: 0.1172 (0.1286) loss: 0.8150 (0.8168) time: 0.3365 data: 0.2562 max mem: 9390 +Train: [79] [1400/6250] eta: 0:43:35 lr: 0.000014 grad: 0.1143 (0.1282) loss: 0.8153 (0.8168) time: 0.1270 data: 0.0320 max mem: 9390 +Train: [79] [1500/6250] eta: 0:40:57 lr: 0.000014 grad: 0.1149 (0.1280) loss: 0.8149 (0.8167) time: 0.2071 data: 0.0958 max mem: 9390 +Train: [79] [1600/6250] eta: 0:38:32 lr: 0.000014 grad: 0.1230 (0.1278) loss: 0.8166 (0.8166) time: 0.1678 data: 0.0677 max mem: 9390 +Train: [79] [1700/6250] eta: 0:36:18 lr: 0.000014 grad: 0.1224 (0.1279) loss: 0.8144 (0.8164) time: 0.1786 data: 0.0771 max mem: 9390 +Train: [79] [1800/6250] eta: 0:34:22 lr: 0.000014 grad: 0.1252 (0.1278) loss: 0.8097 (0.8164) time: 0.2428 data: 0.1470 max mem: 9390 +Train: [79] [1900/6250] eta: 0:32:32 lr: 0.000014 grad: 0.1264 (0.1278) loss: 0.8136 (0.8163) time: 0.2026 data: 0.1045 max mem: 9390 +Train: [79] [2000/6250] eta: 0:30:56 lr: 0.000014 grad: 0.1281 (0.1278) loss: 0.8137 (0.8163) time: 0.2179 data: 0.1256 max mem: 9390 +Train: [79] [2100/6250] eta: 0:29:50 lr: 0.000014 grad: 0.1280 (0.1278) loss: 0.8168 (0.8162) time: 0.2400 data: 0.1178 max mem: 9390 +Train: [79] [2200/6250] eta: 0:28:25 lr: 0.000014 grad: 0.1261 (0.1278) loss: 0.8207 (0.8162) time: 0.1462 data: 0.0003 max mem: 9390 +Train: [79] [2300/6250] eta: 0:27:46 lr: 0.000014 grad: 0.1227 (0.1278) loss: 0.8127 (0.8162) time: 0.3201 data: 0.2009 max mem: 9390 +Train: [79] [2400/6250] eta: 0:26:25 lr: 0.000014 grad: 0.1249 (0.1277) loss: 0.8145 (0.8162) time: 0.1427 data: 0.0410 max mem: 9390 +Train: [79] [2500/6250] eta: 0:25:51 lr: 0.000014 grad: 0.1244 (0.1276) loss: 0.8220 (0.8162) time: 0.2075 data: 0.1071 max mem: 9390 +Train: [79] [2600/6250] eta: 0:25:02 lr: 0.000014 grad: 0.1249 (0.1276) loss: 0.8189 (0.8163) time: 0.1053 data: 0.0002 max mem: 9390 +Train: [79] [2700/6250] eta: 0:24:08 lr: 0.000014 grad: 0.1240 (0.1275) loss: 0.8120 (0.8163) time: 0.1490 data: 0.0505 max mem: 9390 +Train: [79] [2800/6250] eta: 0:23:17 lr: 0.000014 grad: 0.1251 (0.1275) loss: 0.8122 (0.8162) time: 0.2893 data: 0.1997 max mem: 9390 +Train: [79] [2900/6250] eta: 0:22:15 lr: 0.000014 grad: 0.1179 (0.1274) loss: 0.8216 (0.8162) time: 0.1173 data: 0.0003 max mem: 9390 +Train: [79] [3000/6250] eta: 0:21:41 lr: 0.000014 grad: 0.1173 (0.1274) loss: 0.8170 (0.8161) time: 0.7960 data: 0.6609 max mem: 9390 +Train: [79] [3100/6250] eta: 0:20:49 lr: 0.000014 grad: 0.1264 (0.1274) loss: 0.8166 (0.8161) time: 0.1188 data: 0.0003 max mem: 9390 +Train: [79] [3200/6250] eta: 0:20:01 lr: 0.000014 grad: 0.1242 (0.1273) loss: 0.8157 (0.8161) time: 0.6950 data: 0.5937 max mem: 9390 +Train: [79] [3300/6250] eta: 0:19:24 lr: 0.000014 grad: 0.1227 (0.1273) loss: 0.8159 (0.8160) time: 0.1261 data: 0.0279 max mem: 9390 +Train: [79] [3400/6250] eta: 0:18:32 lr: 0.000014 grad: 0.1333 (0.1274) loss: 0.8113 (0.8158) time: 0.2037 data: 0.1075 max mem: 9390 +Train: [79] [3500/6250] eta: 0:18:20 lr: 0.000014 grad: 0.1276 (0.1275) loss: 0.8100 (0.8157) time: 0.3045 data: 0.2151 max mem: 9390 +Train: [79] [3600/6250] eta: 0:17:27 lr: 0.000014 grad: 0.1272 (0.1275) loss: 0.8102 (0.8156) time: 0.2079 data: 0.1224 max mem: 9390 +Train: [79] [3700/6250] eta: 0:16:58 lr: 0.000014 grad: 0.1292 (0.1275) loss: 0.8064 (0.8155) time: 0.2106 data: 0.1048 max mem: 9390 +Train: [79] [3800/6250] eta: 0:16:06 lr: 0.000014 grad: 0.1267 (0.1275) loss: 0.8116 (0.8153) time: 0.2123 data: 0.1267 max mem: 9390 +Train: [79] [3900/6250] eta: 0:15:21 lr: 0.000014 grad: 0.1285 (0.1275) loss: 0.8110 (0.8152) time: 0.0970 data: 0.0211 max mem: 9390 +Train: [79] [4000/6250] eta: 0:14:28 lr: 0.000014 grad: 0.1257 (0.1275) loss: 0.8118 (0.8152) time: 0.1323 data: 0.0552 max mem: 9390 +Train: [79] [4100/6250] eta: 0:13:37 lr: 0.000014 grad: 0.1272 (0.1275) loss: 0.8126 (0.8151) time: 0.1364 data: 0.0407 max mem: 9390 +Train: [79] [4200/6250] eta: 0:12:47 lr: 0.000014 grad: 0.1223 (0.1275) loss: 0.8184 (0.8150) time: 0.1717 data: 0.0889 max mem: 9390 +Train: [79] [4300/6250] eta: 0:11:59 lr: 0.000014 grad: 0.1278 (0.1275) loss: 0.8111 (0.8149) time: 0.1364 data: 0.0576 max mem: 9390 +Train: [79] [4400/6250] eta: 0:11:13 lr: 0.000014 grad: 0.1307 (0.1275) loss: 0.8149 (0.8149) time: 0.1420 data: 0.0625 max mem: 9390 +Train: [79] [4500/6250] eta: 0:10:28 lr: 0.000014 grad: 0.1324 (0.1276) loss: 0.8158 (0.8148) time: 0.1491 data: 0.0634 max mem: 9390 +Train: [79] [4600/6250] eta: 0:09:45 lr: 0.000014 grad: 0.1285 (0.1276) loss: 0.8143 (0.8148) time: 0.1647 data: 0.0783 max mem: 9390 +Train: [79] [4700/6250] eta: 0:09:03 lr: 0.000013 grad: 0.1327 (0.1277) loss: 0.8118 (0.8147) time: 0.1839 data: 0.0950 max mem: 9390 +Train: [79] [4800/6250] eta: 0:08:22 lr: 0.000013 grad: 0.1253 (0.1277) loss: 0.8133 (0.8147) time: 0.1610 data: 0.0806 max mem: 9390 +Train: [79] [4900/6250] eta: 0:07:42 lr: 0.000013 grad: 0.1325 (0.1277) loss: 0.8143 (0.8146) time: 0.1506 data: 0.0706 max mem: 9390 +Train: [79] [5000/6250] eta: 0:07:03 lr: 0.000013 grad: 0.1226 (0.1277) loss: 0.8148 (0.8146) time: 0.1603 data: 0.0868 max mem: 9390 +Train: [79] [5100/6250] eta: 0:06:25 lr: 0.000013 grad: 0.1166 (0.1276) loss: 0.8184 (0.8147) time: 0.1320 data: 0.0412 max mem: 9390 +Train: [79] [5200/6250] eta: 0:05:48 lr: 0.000013 grad: 0.1274 (0.1276) loss: 0.8167 (0.8146) time: 0.1315 data: 0.0499 max mem: 9390 +Train: [79] [5300/6250] eta: 0:05:11 lr: 0.000013 grad: 0.1306 (0.1277) loss: 0.8126 (0.8146) time: 0.1577 data: 0.0811 max mem: 9390 +Train: [79] [5400/6250] eta: 0:04:35 lr: 0.000013 grad: 0.1222 (0.1277) loss: 0.8170 (0.8146) time: 0.1356 data: 0.0591 max mem: 9390 +Train: [79] [5500/6250] eta: 0:04:00 lr: 0.000013 grad: 0.1287 (0.1278) loss: 0.8125 (0.8145) time: 0.1368 data: 0.0588 max mem: 9390 +Train: [79] [5600/6250] eta: 0:03:26 lr: 0.000013 grad: 0.1244 (0.1278) loss: 0.8163 (0.8145) time: 0.1472 data: 0.0659 max mem: 9390 +Train: [79] [5700/6250] eta: 0:02:53 lr: 0.000013 grad: 0.1347 (0.1279) loss: 0.8129 (0.8145) time: 0.1388 data: 0.0549 max mem: 9390 +Train: [79] [5800/6250] eta: 0:02:20 lr: 0.000013 grad: 0.1319 (0.1280) loss: 0.8039 (0.8145) time: 0.1568 data: 0.0641 max mem: 9390 +Train: [79] [5900/6250] eta: 0:01:48 lr: 0.000013 grad: 0.1247 (0.1280) loss: 0.8114 (0.8144) time: 0.1532 data: 0.0657 max mem: 9390 +Train: [79] [6000/6250] eta: 0:01:16 lr: 0.000013 grad: 0.1271 (0.1281) loss: 0.8102 (0.8143) time: 0.1447 data: 0.0650 max mem: 9390 +Train: [79] [6100/6250] eta: 0:00:45 lr: 0.000013 grad: 0.1235 (0.1281) loss: 0.8150 (0.8143) time: 0.1290 data: 0.0496 max mem: 9390 +Train: [79] [6200/6250] eta: 0:00:15 lr: 0.000013 grad: 0.1295 (0.1282) loss: 0.8138 (0.8142) time: 0.1752 data: 0.0940 max mem: 9390 +Train: [79] [6249/6250] eta: 0:00:00 lr: 0.000013 grad: 0.1394 (0.1282) loss: 0.8007 (0.8142) time: 0.1220 data: 0.0420 max mem: 9390 +Train: [79] Total time: 0:31:23 (0.3013 s / it) +Averaged stats: lr: 0.000013 grad: 0.1394 (0.1282) loss: 0.8007 (0.8142) +Eval (hcp-train-subset): [79] [ 0/62] eta: 0:04:49 loss: 0.8352 (0.8352) time: 4.6625 data: 4.6322 max mem: 9390 +Eval (hcp-train-subset): [79] [61/62] eta: 0:00:00 loss: 0.8203 (0.8229) time: 0.1421 data: 0.1111 max mem: 9390 +Eval (hcp-train-subset): [79] Total time: 0:00:12 (0.2025 s / it) +Averaged stats (hcp-train-subset): loss: 0.8203 (0.8229) +Making plots (hcp-train-subset): example=48 +Eval (hcp-val): [79] [ 0/62] eta: 0:04:13 loss: 0.8289 (0.8289) time: 4.0875 data: 4.0061 max mem: 9390 +Eval (hcp-val): [79] [61/62] eta: 0:00:00 loss: 0.8286 (0.8304) time: 0.1544 data: 0.1288 max mem: 9390 +Eval (hcp-val): [79] Total time: 0:00:13 (0.2258 s / it) +Averaged stats (hcp-val): loss: 0.8286 (0.8304) +Making plots (hcp-val): example=31 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +Train: [80] [ 0/6250] eta: 7:54:59 lr: 0.000013 grad: 0.0817 (0.0817) loss: 0.8520 (0.8520) time: 4.5599 data: 4.2908 max mem: 9390 +Train: [80] [ 100/6250] eta: 0:20:20 lr: 0.000013 grad: 0.1437 (0.1490) loss: 0.8169 (0.8266) time: 0.1522 data: 0.0679 max mem: 9390 +Train: [80] [ 200/6250] eta: 0:17:47 lr: 0.000013 grad: 0.1372 (0.1494) loss: 0.8139 (0.8175) time: 0.1396 data: 0.0477 max mem: 9390 +Train: [80] [ 300/6250] eta: 0:16:23 lr: 0.000013 grad: 0.1256 (0.1445) loss: 0.8141 (0.8161) time: 0.1541 data: 0.0759 max mem: 9390 +Train: [80] [ 400/6250] eta: 0:15:27 lr: 0.000013 grad: 0.1320 (0.1400) loss: 0.8080 (0.8151) time: 0.1530 data: 0.0682 max mem: 9390 +Train: [80] [ 500/6250] eta: 0:14:36 lr: 0.000013 grad: 0.1183 (0.1371) loss: 0.8181 (0.8148) time: 0.1169 data: 0.0304 max mem: 9390 +Train: [80] [ 600/6250] eta: 0:14:02 lr: 0.000013 grad: 0.1259 (0.1349) loss: 0.8052 (0.8145) time: 0.1287 data: 0.0469 max mem: 9390 +Train: [80] [ 700/6250] eta: 0:13:31 lr: 0.000013 grad: 0.1180 (0.1337) loss: 0.8098 (0.8142) time: 0.1058 data: 0.0177 max mem: 9390 +Train: [80] [ 800/6250] eta: 0:13:08 lr: 0.000013 grad: 0.1238 (0.1329) loss: 0.8082 (0.8140) time: 0.1294 data: 0.0432 max mem: 9390 +Train: [80] [ 900/6250] eta: 0:12:44 lr: 0.000013 grad: 0.1250 (0.1327) loss: 0.8130 (0.8139) time: 0.1314 data: 0.0424 max mem: 9390 +Train: [80] [1000/6250] eta: 0:12:20 lr: 0.000013 grad: 0.1212 (0.1323) loss: 0.8062 (0.8135) time: 0.1306 data: 0.0456 max mem: 9390 +Train: [80] [1100/6250] eta: 0:12:12 lr: 0.000013 grad: 0.1274 (0.1323) loss: 0.8087 (0.8132) time: 0.1757 data: 0.1031 max mem: 9390 +Train: [80] [1200/6250] eta: 0:11:56 lr: 0.000013 grad: 0.1294 (0.1322) loss: 0.8025 (0.8130) time: 0.1482 data: 0.0753 max mem: 9390 +Train: [80] [1300/6250] eta: 0:11:41 lr: 0.000013 grad: 0.1236 (0.1320) loss: 0.8161 (0.8128) time: 0.1261 data: 0.0491 max mem: 9390 +Train: [80] [1400/6250] eta: 0:11:30 lr: 0.000013 grad: 0.1290 (0.1319) loss: 0.8074 (0.8127) time: 0.1539 data: 0.0780 max mem: 9390 +Train: [80] [1500/6250] eta: 0:11:15 lr: 0.000013 grad: 0.1223 (0.1319) loss: 0.8094 (0.8125) time: 0.1448 data: 0.0622 max mem: 9390 +Train: [80] [1600/6250] eta: 0:10:59 lr: 0.000013 grad: 0.1262 (0.1319) loss: 0.8108 (0.8124) time: 0.1380 data: 0.0588 max mem: 9390 +Train: [80] [1700/6250] eta: 0:10:42 lr: 0.000013 grad: 0.1248 (0.1319) loss: 0.8134 (0.8124) time: 0.1198 data: 0.0393 max mem: 9390 +Train: [80] [1800/6250] eta: 0:10:27 lr: 0.000013 grad: 0.1287 (0.1318) loss: 0.8080 (0.8123) time: 0.1798 data: 0.0596 max mem: 9390 +Train: [80] [1900/6250] eta: 0:10:08 lr: 0.000013 grad: 0.1256 (0.1318) loss: 0.8097 (0.8122) time: 0.1250 data: 0.0372 max mem: 9390 +Train: [80] [2000/6250] eta: 0:09:50 lr: 0.000013 grad: 0.1274 (0.1318) loss: 0.8101 (0.8119) time: 0.1291 data: 0.0446 max mem: 9390 +Train: [80] [2100/6250] eta: 0:09:33 lr: 0.000013 grad: 0.1307 (0.1319) loss: 0.8069 (0.8118) time: 0.1038 data: 0.0173 max mem: 9390 +Train: [80] [2200/6250] eta: 0:09:15 lr: 0.000013 grad: 0.1226 (0.1317) loss: 0.8109 (0.8117) time: 0.1208 data: 0.0356 max mem: 9390 +Train: [80] [2300/6250] eta: 0:08:59 lr: 0.000013 grad: 0.1326 (0.1318) loss: 0.8077 (0.8117) time: 0.1109 data: 0.0275 max mem: 9390 +Train: [80] [2400/6250] eta: 0:08:42 lr: 0.000013 grad: 0.1222 (0.1317) loss: 0.8102 (0.8118) time: 0.1172 data: 0.0394 max mem: 9390 +Train: [80] [2500/6250] eta: 0:08:26 lr: 0.000013 grad: 0.1239 (0.1314) loss: 0.8094 (0.8118) time: 0.1162 data: 0.0350 max mem: 9390 +Train: [80] [2600/6250] eta: 0:08:26 lr: 0.000013 grad: 0.1229 (0.1313) loss: 0.8072 (0.8117) time: 0.4361 data: 0.3465 max mem: 9390 +Train: [80] [2700/6250] eta: 0:08:19 lr: 0.000013 grad: 0.1209 (0.1312) loss: 0.8133 (0.8117) time: 0.1533 data: 0.0697 max mem: 9390 +Train: [80] [2800/6250] eta: 0:08:15 lr: 0.000013 grad: 0.1205 (0.1310) loss: 0.8147 (0.8118) time: 0.1457 data: 0.0004 max mem: 9390 +Train: [80] [2900/6250] eta: 0:08:08 lr: 0.000013 grad: 0.1231 (0.1308) loss: 0.8176 (0.8119) time: 0.3436 data: 0.2490 max mem: 9390 +Train: [80] [3000/6250] eta: 0:08:00 lr: 0.000013 grad: 0.1240 (0.1309) loss: 0.8145 (0.8119) time: 0.3198 data: 0.2243 max mem: 9390 +Train: [80] [3100/6250] eta: 0:07:53 lr: 0.000013 grad: 0.1181 (0.1308) loss: 0.8210 (0.8118) time: 0.1323 data: 0.0246 max mem: 9390 +Train: [80] [3200/6250] eta: 0:07:50 lr: 0.000013 grad: 0.1210 (0.1307) loss: 0.8154 (0.8118) time: 0.1232 data: 0.0005 max mem: 9390 +Train: [80] [3300/6250] eta: 0:07:49 lr: 0.000013 grad: 0.1314 (0.1307) loss: 0.8143 (0.8118) time: 0.2696 data: 0.1761 max mem: 9390 +Train: [80] [3400/6250] eta: 0:07:45 lr: 0.000012 grad: 0.1235 (0.1305) loss: 0.8126 (0.8118) time: 0.1205 data: 0.0004 max mem: 9390 +Train: [80] [3500/6250] eta: 0:07:28 lr: 0.000012 grad: 0.1202 (0.1304) loss: 0.8066 (0.8119) time: 0.1334 data: 0.0464 max mem: 9390 +Train: [80] [3600/6250] eta: 0:07:14 lr: 0.000012 grad: 0.1226 (0.1303) loss: 0.8176 (0.8119) time: 0.0957 data: 0.0002 max mem: 9390 +Train: [80] [3700/6250] eta: 0:06:57 lr: 0.000012 grad: 0.1250 (0.1303) loss: 0.8175 (0.8120) time: 0.1732 data: 0.0913 max mem: 9390 +Train: [80] [3800/6250] eta: 0:06:43 lr: 0.000012 grad: 0.1190 (0.1301) loss: 0.8232 (0.8121) time: 0.2100 data: 0.1131 max mem: 9390 +Train: [80] [3900/6250] eta: 0:06:25 lr: 0.000012 grad: 0.1218 (0.1300) loss: 0.8109 (0.8121) time: 0.1740 data: 0.0908 max mem: 9390 +Train: [80] [4000/6250] eta: 0:06:08 lr: 0.000012 grad: 0.1230 (0.1300) loss: 0.8178 (0.8121) time: 0.1478 data: 0.0517 max mem: 9390 +Train: [80] [4100/6250] eta: 0:05:51 lr: 0.000012 grad: 0.1299 (0.1300) loss: 0.8106 (0.8122) time: 0.0961 data: 0.0002 max mem: 9390 +Train: [80] [4200/6250] eta: 0:05:35 lr: 0.000012 grad: 0.1302 (0.1301) loss: 0.8156 (0.8121) time: 0.1538 data: 0.0565 max mem: 9390 +Train: [80] [4300/6250] eta: 0:05:19 lr: 0.000012 grad: 0.1308 (0.1301) loss: 0.8139 (0.8121) time: 0.1558 data: 0.0702 max mem: 9390 +Train: [80] [4400/6250] eta: 0:05:03 lr: 0.000012 grad: 0.1319 (0.1302) loss: 0.8095 (0.8121) time: 0.2141 data: 0.1246 max mem: 9390 +Train: [80] [4500/6250] eta: 0:04:46 lr: 0.000012 grad: 0.1232 (0.1303) loss: 0.8140 (0.8122) time: 0.1292 data: 0.0441 max mem: 9390 +Train: [80] [4600/6250] eta: 0:04:31 lr: 0.000012 grad: 0.1206 (0.1303) loss: 0.8118 (0.8122) time: 0.0957 data: 0.0002 max mem: 9390 +Train: [80] [4700/6250] eta: 0:04:17 lr: 0.000012 grad: 0.1240 (0.1303) loss: 0.8046 (0.8121) time: 0.2140 data: 0.1024 max mem: 9390 +Train: [80] [4800/6250] eta: 0:04:00 lr: 0.000012 grad: 0.1312 (0.1304) loss: 0.8130 (0.8121) time: 0.2013 data: 0.1053 max mem: 9390 +Train: [80] [4900/6250] eta: 0:03:45 lr: 0.000012 grad: 0.1374 (0.1305) loss: 0.8055 (0.8120) time: 0.2485 data: 0.1643 max mem: 9390 +Train: [80] [5000/6250] eta: 0:03:28 lr: 0.000012 grad: 0.1332 (0.1307) loss: 0.8154 (0.8119) time: 0.1330 data: 0.0343 max mem: 9390 +Train: [80] [5100/6250] eta: 0:03:12 lr: 0.000012 grad: 0.1298 (0.1308) loss: 0.8085 (0.8119) time: 0.3242 data: 0.2318 max mem: 9390 +Train: [80] [5200/6250] eta: 0:02:56 lr: 0.000012 grad: 0.1315 (0.1309) loss: 0.8064 (0.8118) time: 0.3185 data: 0.2227 max mem: 9390 +Train: [80] [5300/6250] eta: 0:02:40 lr: 0.000012 grad: 0.1244 (0.1309) loss: 0.8157 (0.8118) time: 0.1320 data: 0.0239 max mem: 9390 +Train: [80] [5400/6250] eta: 0:02:24 lr: 0.000012 grad: 0.1234 (0.1309) loss: 0.8141 (0.8118) time: 0.3399 data: 0.2447 max mem: 9390 +Train: [80] [5500/6250] eta: 0:02:07 lr: 0.000012 grad: 0.1415 (0.1310) loss: 0.8109 (0.8118) time: 0.1355 data: 0.0526 max mem: 9390 +Train: [80] [5600/6250] eta: 0:01:50 lr: 0.000012 grad: 0.1309 (0.1311) loss: 0.8063 (0.8118) time: 0.2896 data: 0.2027 max mem: 9390 +Train: [80] [5700/6250] eta: 0:01:33 lr: 0.000012 grad: 0.1269 (0.1311) loss: 0.8114 (0.8118) time: 0.1691 data: 0.0684 max mem: 9390 +Train: [80] [5800/6250] eta: 0:01:17 lr: 0.000012 grad: 0.1297 (0.1312) loss: 0.8117 (0.8118) time: 0.2354 data: 0.1291 max mem: 9390 +Train: [80] [5900/6250] eta: 0:01:00 lr: 0.000012 grad: 0.1410 (0.1313) loss: 0.8078 (0.8118) time: 0.4049 data: 0.3170 max mem: 9390 +Train: [80] [6000/6250] eta: 0:00:43 lr: 0.000012 grad: 0.1265 (0.1313) loss: 0.8132 (0.8119) time: 0.1674 data: 0.0753 max mem: 9390 +Train: [80] [6100/6250] eta: 0:00:26 lr: 0.000012 grad: 0.1269 (0.1314) loss: 0.8109 (0.8119) time: 0.1109 data: 0.0003 max mem: 9390 +Train: [80] [6200/6250] eta: 0:00:08 lr: 0.000012 grad: 0.1368 (0.1314) loss: 0.8128 (0.8119) time: 0.4902 data: 0.4100 max mem: 9390 +Train: [80] [6249/6250] eta: 0:00:00 lr: 0.000012 grad: 0.1304 (0.1315) loss: 0.8081 (0.8119) time: 0.3217 data: 0.2303 max mem: 9390 +Train: [80] Total time: 0:18:30 (0.1777 s / it) +Averaged stats: lr: 0.000012 grad: 0.1304 (0.1315) loss: 0.8081 (0.8119) +Eval (hcp-train-subset): [80] [ 0/62] eta: 0:05:08 loss: 0.8334 (0.8334) time: 4.9697 data: 4.9190 max mem: 9390 +Eval (hcp-train-subset): [80] [61/62] eta: 0:00:00 loss: 0.8191 (0.8220) time: 0.1357 data: 0.1108 max mem: 9390 +Eval (hcp-train-subset): [80] Total time: 0:00:15 (0.2462 s / it) +Averaged stats (hcp-train-subset): loss: 0.8191 (0.8220) +Eval (hcp-val): [80] [ 0/62] eta: 0:04:17 loss: 0.8279 (0.8279) time: 4.1516 data: 4.0755 max mem: 9390 +Eval (hcp-val): [80] [61/62] eta: 0:00:00 loss: 0.8288 (0.8301) time: 0.1240 data: 0.0990 max mem: 9390 +Eval (hcp-val): [80] Total time: 0:00:13 (0.2241 s / it) +Averaged stats (hcp-val): loss: 0.8288 (0.8301) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +Train: [81] [ 0/6250] eta: 12:57:05 lr: 0.000012 grad: 0.1685 (0.1685) loss: 0.8144 (0.8144) time: 7.4602 data: 7.2891 max mem: 9390 +Train: [81] [ 100/6250] eta: 0:23:09 lr: 0.000012 grad: 0.1404 (0.1716) loss: 0.8266 (0.8226) time: 0.1668 data: 0.0808 max mem: 9390 +Train: [81] [ 200/6250] eta: 0:21:28 lr: 0.000012 grad: 0.1321 (0.1542) loss: 0.8158 (0.8204) time: 0.1694 data: 0.0511 max mem: 9390 +Train: [81] [ 300/6250] eta: 0:19:26 lr: 0.000012 grad: 0.1283 (0.1483) loss: 0.8159 (0.8177) time: 0.1575 data: 0.0506 max mem: 9390 +Train: [81] [ 400/6250] eta: 0:18:14 lr: 0.000012 grad: 0.1372 (0.1445) loss: 0.8086 (0.8166) time: 0.1752 data: 0.0881 max mem: 9390 +Train: [81] [ 500/6250] eta: 0:17:25 lr: 0.000012 grad: 0.1287 (0.1418) loss: 0.8090 (0.8156) time: 0.1447 data: 0.0342 max mem: 9390 +Train: [81] [ 600/6250] eta: 0:17:08 lr: 0.000012 grad: 0.1301 (0.1405) loss: 0.8089 (0.8144) time: 0.2151 data: 0.1300 max mem: 9390 +Train: [81] [ 700/6250] eta: 0:16:55 lr: 0.000012 grad: 0.1261 (0.1389) loss: 0.8146 (0.8139) time: 0.1725 data: 0.0823 max mem: 9390 +Train: [81] [ 800/6250] eta: 0:16:52 lr: 0.000012 grad: 0.1182 (0.1374) loss: 0.8125 (0.8138) time: 0.2317 data: 0.1373 max mem: 9390 +Train: [81] [ 900/6250] eta: 0:16:35 lr: 0.000012 grad: 0.1235 (0.1363) loss: 0.8083 (0.8134) time: 0.1914 data: 0.1052 max mem: 9390 +Train: [81] [1000/6250] eta: 0:16:20 lr: 0.000012 grad: 0.1205 (0.1354) loss: 0.8147 (0.8134) time: 0.2260 data: 0.1401 max mem: 9390 +Train: [81] [1100/6250] eta: 0:15:54 lr: 0.000012 grad: 0.1221 (0.1347) loss: 0.8082 (0.8130) time: 0.1939 data: 0.1100 max mem: 9390 +Train: [81] [1200/6250] eta: 0:15:29 lr: 0.000012 grad: 0.1267 (0.1340) loss: 0.8093 (0.8129) time: 0.1809 data: 0.1000 max mem: 9390 +Train: [81] [1300/6250] eta: 0:15:12 lr: 0.000012 grad: 0.1341 (0.1337) loss: 0.8051 (0.8126) time: 0.1995 data: 0.1107 max mem: 9390 +Train: [81] [1400/6250] eta: 0:14:52 lr: 0.000012 grad: 0.1180 (0.1332) loss: 0.8168 (0.8126) time: 0.2073 data: 0.1128 max mem: 9390 +Train: [81] [1500/6250] eta: 0:14:35 lr: 0.000012 grad: 0.1311 (0.1330) loss: 0.8026 (0.8124) time: 0.1659 data: 0.0836 max mem: 9390 +Train: [81] [1600/6250] eta: 0:14:17 lr: 0.000012 grad: 0.1293 (0.1327) loss: 0.8089 (0.8124) time: 0.1415 data: 0.0101 max mem: 9390 +Train: [81] [1700/6250] eta: 0:14:13 lr: 0.000012 grad: 0.1185 (0.1323) loss: 0.8161 (0.8124) time: 0.3252 data: 0.2159 max mem: 9390 +Train: [81] [1800/6250] eta: 0:14:06 lr: 0.000012 grad: 0.1288 (0.1321) loss: 0.8090 (0.8124) time: 0.2857 data: 0.1846 max mem: 9390 +Train: [81] [1900/6250] eta: 0:13:52 lr: 0.000012 grad: 0.1162 (0.1317) loss: 0.8156 (0.8125) time: 0.2383 data: 0.1491 max mem: 9390 +Train: [81] [2000/6250] eta: 0:13:26 lr: 0.000012 grad: 0.1235 (0.1313) loss: 0.8127 (0.8125) time: 0.1831 data: 0.0807 max mem: 9390 +Train: [81] [2100/6250] eta: 0:13:18 lr: 0.000012 grad: 0.1281 (0.1310) loss: 0.8151 (0.8126) time: 0.1607 data: 0.0548 max mem: 9390 +Train: [81] [2200/6250] eta: 0:13:04 lr: 0.000012 grad: 0.1189 (0.1306) loss: 0.8198 (0.8128) time: 0.1107 data: 0.0002 max mem: 9390 +Train: [81] [2300/6250] eta: 0:12:46 lr: 0.000011 grad: 0.1181 (0.1304) loss: 0.8210 (0.8128) time: 0.1815 data: 0.0931 max mem: 9390 +Train: [81] [2400/6250] eta: 0:12:36 lr: 0.000011 grad: 0.1258 (0.1302) loss: 0.8097 (0.8128) time: 0.1066 data: 0.0002 max mem: 9390 +Train: [81] [2500/6250] eta: 0:12:22 lr: 0.000011 grad: 0.1228 (0.1300) loss: 0.8188 (0.8129) time: 0.1448 data: 0.0413 max mem: 9390 +Train: [81] [2600/6250] eta: 0:12:14 lr: 0.000011 grad: 0.1200 (0.1299) loss: 0.8107 (0.8128) time: 0.3746 data: 0.2842 max mem: 9390 +Train: [81] [2700/6250] eta: 0:12:03 lr: 0.000011 grad: 0.1315 (0.1298) loss: 0.8071 (0.8128) time: 0.2368 data: 0.1327 max mem: 9390 +Train: [81] [2800/6250] eta: 0:11:36 lr: 0.000011 grad: 0.1258 (0.1297) loss: 0.8159 (0.8129) time: 0.1531 data: 0.0558 max mem: 9390 +Train: [81] [2900/6250] eta: 0:11:21 lr: 0.000011 grad: 0.1214 (0.1296) loss: 0.8164 (0.8129) time: 0.3541 data: 0.2320 max mem: 9390 +Train: [81] [3000/6250] eta: 0:10:56 lr: 0.000011 grad: 0.1268 (0.1296) loss: 0.8122 (0.8129) time: 0.1717 data: 0.0593 max mem: 9390 +Train: [81] [3100/6250] eta: 0:10:39 lr: 0.000011 grad: 0.1195 (0.1297) loss: 0.8098 (0.8129) time: 0.1931 data: 0.0899 max mem: 9390 +Train: [81] [3200/6250] eta: 0:10:19 lr: 0.000011 grad: 0.1266 (0.1298) loss: 0.8153 (0.8129) time: 0.3255 data: 0.2364 max mem: 9390 +Train: [81] [3300/6250] eta: 0:10:03 lr: 0.000011 grad: 0.1296 (0.1299) loss: 0.8121 (0.8128) time: 0.3770 data: 0.2846 max mem: 9390 +Train: [81] [3400/6250] eta: 0:09:48 lr: 0.000011 grad: 0.1246 (0.1300) loss: 0.8163 (0.8128) time: 0.2876 data: 0.1824 max mem: 9390 +Train: [81] [3500/6250] eta: 0:09:31 lr: 0.000011 grad: 0.1331 (0.1303) loss: 0.8114 (0.8127) time: 0.3525 data: 0.2527 max mem: 9390 +Train: [81] [3600/6250] eta: 0:09:14 lr: 0.000011 grad: 0.1240 (0.1304) loss: 0.8142 (0.8126) time: 0.6592 data: 0.5341 max mem: 9390 +Train: [81] [3700/6250] eta: 0:08:50 lr: 0.000011 grad: 0.1257 (0.1305) loss: 0.8090 (0.8125) time: 0.1675 data: 0.0847 max mem: 9390 +Train: [81] [3800/6250] eta: 0:08:30 lr: 0.000011 grad: 0.1373 (0.1307) loss: 0.8024 (0.8124) time: 0.1888 data: 0.0896 max mem: 9390 +Train: [81] [3900/6250] eta: 0:08:12 lr: 0.000011 grad: 0.1351 (0.1308) loss: 0.8063 (0.8123) time: 0.1028 data: 0.0002 max mem: 9390 +Train: [81] [4000/6250] eta: 0:07:50 lr: 0.000011 grad: 0.1349 (0.1310) loss: 0.8101 (0.8122) time: 0.1357 data: 0.0419 max mem: 9390 +Train: [81] [4100/6250] eta: 0:07:29 lr: 0.000011 grad: 0.1335 (0.1311) loss: 0.8135 (0.8122) time: 0.1916 data: 0.1128 max mem: 9390 +Train: [81] [4200/6250] eta: 0:07:06 lr: 0.000011 grad: 0.1316 (0.1312) loss: 0.8088 (0.8121) time: 0.1805 data: 0.0999 max mem: 9390 +Train: [81] [4300/6250] eta: 0:06:46 lr: 0.000011 grad: 0.1271 (0.1312) loss: 0.8128 (0.8121) time: 0.4727 data: 0.3803 max mem: 9390 +Train: [81] [4400/6250] eta: 0:06:25 lr: 0.000011 grad: 0.1330 (0.1312) loss: 0.8052 (0.8121) time: 0.3254 data: 0.2304 max mem: 9390 +Train: [81] [4500/6250] eta: 0:06:04 lr: 0.000011 grad: 0.1321 (0.1313) loss: 0.8097 (0.8121) time: 0.1817 data: 0.0813 max mem: 9390 +Train: [81] [4600/6250] eta: 0:05:43 lr: 0.000011 grad: 0.1278 (0.1313) loss: 0.8111 (0.8120) time: 0.2064 data: 0.1193 max mem: 9390 +Train: [81] [4700/6250] eta: 0:05:22 lr: 0.000011 grad: 0.1285 (0.1314) loss: 0.8120 (0.8120) time: 0.1545 data: 0.0743 max mem: 9390 +Train: [81] [4800/6250] eta: 0:05:00 lr: 0.000011 grad: 0.1272 (0.1315) loss: 0.8123 (0.8120) time: 0.1903 data: 0.1020 max mem: 9390 +Train: [81] [4900/6250] eta: 0:04:42 lr: 0.000011 grad: 0.1365 (0.1315) loss: 0.8103 (0.8120) time: 0.2213 data: 0.1318 max mem: 9390 +Train: [81] [5000/6250] eta: 0:04:19 lr: 0.000011 grad: 0.1246 (0.1315) loss: 0.8160 (0.8120) time: 0.1596 data: 0.0678 max mem: 9390 +Train: [81] [5100/6250] eta: 0:03:59 lr: 0.000011 grad: 0.1337 (0.1316) loss: 0.8088 (0.8119) time: 0.2005 data: 0.1161 max mem: 9390 +Train: [81] [5200/6250] eta: 0:03:39 lr: 0.000011 grad: 0.1368 (0.1317) loss: 0.8133 (0.8118) time: 0.1489 data: 0.0519 max mem: 9390 +Train: [81] [5300/6250] eta: 0:03:18 lr: 0.000011 grad: 0.1300 (0.1317) loss: 0.8147 (0.8119) time: 0.0990 data: 0.0080 max mem: 9390 +Train: [81] [5400/6250] eta: 0:02:56 lr: 0.000011 grad: 0.1225 (0.1317) loss: 0.8181 (0.8119) time: 0.1123 data: 0.0260 max mem: 9390 +Train: [81] [5500/6250] eta: 0:02:35 lr: 0.000011 grad: 0.1238 (0.1318) loss: 0.8101 (0.8118) time: 0.1588 data: 0.0776 max mem: 9390 +Train: [81] [5600/6250] eta: 0:02:15 lr: 0.000011 grad: 0.1261 (0.1317) loss: 0.8167 (0.8119) time: 0.3699 data: 0.2786 max mem: 9390 +Train: [81] [5700/6250] eta: 0:01:54 lr: 0.000011 grad: 0.1296 (0.1317) loss: 0.8108 (0.8119) time: 0.2001 data: 0.0975 max mem: 9390 +Train: [81] [5800/6250] eta: 0:01:33 lr: 0.000011 grad: 0.1268 (0.1317) loss: 0.8183 (0.8119) time: 0.1561 data: 0.0717 max mem: 9390 +Train: [81] [5900/6250] eta: 0:01:12 lr: 0.000011 grad: 0.1312 (0.1317) loss: 0.8136 (0.8119) time: 0.1554 data: 0.0756 max mem: 9390 +Train: [81] [6000/6250] eta: 0:00:51 lr: 0.000011 grad: 0.1346 (0.1317) loss: 0.8065 (0.8119) time: 0.1091 data: 0.0003 max mem: 9390 +Train: [81] [6100/6250] eta: 0:00:31 lr: 0.000011 grad: 0.1230 (0.1317) loss: 0.8194 (0.8120) time: 0.1529 data: 0.0552 max mem: 9390 +Train: [81] [6200/6250] eta: 0:00:10 lr: 0.000011 grad: 0.1322 (0.1317) loss: 0.8192 (0.8120) time: 0.1638 data: 0.0698 max mem: 9390 +Train: [81] [6249/6250] eta: 0:00:00 lr: 0.000011 grad: 0.1297 (0.1317) loss: 0.8142 (0.8120) time: 0.5110 data: 0.4167 max mem: 9390 +Train: [81] Total time: 0:21:51 (0.2098 s / it) +Averaged stats: lr: 0.000011 grad: 0.1297 (0.1317) loss: 0.8142 (0.8120) +Eval (hcp-train-subset): [81] [ 0/62] eta: 0:04:43 loss: 0.8360 (0.8360) time: 4.5722 data: 4.5282 max mem: 9390 +Eval (hcp-train-subset): [81] [61/62] eta: 0:00:00 loss: 0.8179 (0.8215) time: 0.1396 data: 0.1147 max mem: 9390 +Eval (hcp-train-subset): [81] Total time: 0:00:13 (0.2175 s / it) +Averaged stats (hcp-train-subset): loss: 0.8179 (0.8215) +Eval (hcp-val): [81] [ 0/62] eta: 0:03:10 loss: 0.8262 (0.8262) time: 3.0796 data: 3.0176 max mem: 9390 +Eval (hcp-val): [81] [61/62] eta: 0:00:00 loss: 0.8280 (0.8300) time: 0.1059 data: 0.0811 max mem: 9390 +Eval (hcp-val): [81] Total time: 0:00:13 (0.2214 s / it) +Averaged stats (hcp-val): loss: 0.8280 (0.8300) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +Train: [82] [ 0/6250] eta: 10:52:26 lr: 0.000011 grad: 0.1710 (0.1710) loss: 0.8516 (0.8516) time: 6.2634 data: 6.1477 max mem: 9390 +Train: [82] [ 100/6250] eta: 0:22:48 lr: 0.000011 grad: 0.1444 (0.1777) loss: 0.8181 (0.8199) time: 0.1703 data: 0.0849 max mem: 9390 +Train: [82] [ 200/6250] eta: 0:19:52 lr: 0.000011 grad: 0.1364 (0.1598) loss: 0.8147 (0.8187) time: 0.1615 data: 0.0669 max mem: 9390 +Train: [82] [ 300/6250] eta: 0:20:21 lr: 0.000011 grad: 0.1342 (0.1511) loss: 0.8093 (0.8184) time: 0.3489 data: 0.2205 max mem: 9390 +Train: [82] [ 400/6250] eta: 0:23:16 lr: 0.000011 grad: 0.1308 (0.1457) loss: 0.8188 (0.8193) time: 0.1687 data: 0.0793 max mem: 9390 +Train: [82] [ 500/6250] eta: 0:25:28 lr: 0.000011 grad: 0.1234 (0.1428) loss: 0.8240 (0.8201) time: 0.3927 data: 0.2849 max mem: 9390 +Train: [82] [ 600/6250] eta: 0:25:32 lr: 0.000011 grad: 0.1160 (0.1395) loss: 0.8300 (0.8206) time: 0.5882 data: 0.4682 max mem: 9390 +Train: [82] [ 700/6250] eta: 0:27:48 lr: 0.000011 grad: 0.1199 (0.1369) loss: 0.8210 (0.8211) time: 0.2077 data: 0.0727 max mem: 9390 +Train: [82] [ 800/6250] eta: 0:25:54 lr: 0.000011 grad: 0.1167 (0.1355) loss: 0.8187 (0.8210) time: 0.2210 data: 0.1269 max mem: 9390 +Train: [82] [ 900/6250] eta: 0:24:07 lr: 0.000011 grad: 0.1245 (0.1344) loss: 0.8180 (0.8209) time: 0.1060 data: 0.0154 max mem: 9390 +Train: [82] [1000/6250] eta: 0:22:41 lr: 0.000011 grad: 0.1203 (0.1336) loss: 0.8139 (0.8206) time: 0.1556 data: 0.0729 max mem: 9390 +Train: [82] [1100/6250] eta: 0:21:24 lr: 0.000011 grad: 0.1241 (0.1327) loss: 0.8181 (0.8202) time: 0.1684 data: 0.0818 max mem: 9390 +Train: [82] [1200/6250] eta: 0:20:18 lr: 0.000011 grad: 0.1214 (0.1322) loss: 0.8112 (0.8199) time: 0.1241 data: 0.0343 max mem: 9390 +Train: [82] [1300/6250] eta: 0:19:24 lr: 0.000011 grad: 0.1283 (0.1318) loss: 0.8113 (0.8196) time: 0.1597 data: 0.0799 max mem: 9390 +Train: [82] [1400/6250] eta: 0:18:39 lr: 0.000010 grad: 0.1267 (0.1317) loss: 0.8153 (0.8191) time: 0.1762 data: 0.0889 max mem: 9390 +Train: [82] [1500/6250] eta: 0:17:55 lr: 0.000010 grad: 0.1347 (0.1317) loss: 0.8125 (0.8186) time: 0.1722 data: 0.0873 max mem: 9390 +Train: [82] [1600/6250] eta: 0:17:12 lr: 0.000010 grad: 0.1301 (0.1318) loss: 0.8060 (0.8180) time: 0.1484 data: 0.0622 max mem: 9390 +Train: [82] [1700/6250] eta: 0:16:37 lr: 0.000010 grad: 0.1285 (0.1319) loss: 0.8142 (0.8176) time: 0.1591 data: 0.0771 max mem: 9390 +Train: [82] [1800/6250] eta: 0:16:13 lr: 0.000010 grad: 0.1344 (0.1321) loss: 0.8152 (0.8171) time: 0.1956 data: 0.0981 max mem: 9390 +Train: [82] [1900/6250] eta: 0:15:47 lr: 0.000010 grad: 0.1305 (0.1324) loss: 0.8113 (0.8166) time: 0.1673 data: 0.0756 max mem: 9390 +Train: [82] [2000/6250] eta: 0:15:29 lr: 0.000010 grad: 0.1245 (0.1323) loss: 0.8140 (0.8163) time: 0.1540 data: 0.0637 max mem: 9390 +Train: [82] [2100/6250] eta: 0:15:07 lr: 0.000010 grad: 0.1242 (0.1322) loss: 0.8137 (0.8161) time: 0.1809 data: 0.0901 max mem: 9390 +Train: [82] [2200/6250] eta: 0:14:39 lr: 0.000010 grad: 0.1277 (0.1324) loss: 0.8046 (0.8157) time: 0.1804 data: 0.0975 max mem: 9390 +Train: [82] [2300/6250] eta: 0:14:13 lr: 0.000010 grad: 0.1329 (0.1327) loss: 0.8130 (0.8155) time: 0.1650 data: 0.0781 max mem: 9390 +Train: [82] [2400/6250] eta: 0:13:42 lr: 0.000010 grad: 0.1295 (0.1327) loss: 0.8108 (0.8153) time: 0.1375 data: 0.0550 max mem: 9390 +Train: [82] [2500/6250] eta: 0:13:14 lr: 0.000010 grad: 0.1374 (0.1328) loss: 0.8082 (0.8152) time: 0.1614 data: 0.0807 max mem: 9390 +Train: [82] [2600/6250] eta: 0:12:46 lr: 0.000010 grad: 0.1294 (0.1329) loss: 0.8125 (0.8150) time: 0.2104 data: 0.1269 max mem: 9390 +Train: [82] [2700/6250] eta: 0:12:37 lr: 0.000010 grad: 0.1313 (0.1330) loss: 0.8125 (0.8148) time: 0.6439 data: 0.5624 max mem: 9390 +Train: [82] [2800/6250] eta: 0:12:23 lr: 0.000010 grad: 0.1306 (0.1330) loss: 0.8158 (0.8147) time: 0.2522 data: 0.1590 max mem: 9390 +Train: [82] [2900/6250] eta: 0:11:54 lr: 0.000010 grad: 0.1337 (0.1330) loss: 0.8168 (0.8145) time: 0.2135 data: 0.0920 max mem: 9390 +Train: [82] [3000/6250] eta: 0:11:31 lr: 0.000010 grad: 0.1378 (0.1332) loss: 0.8071 (0.8144) time: 0.1261 data: 0.0359 max mem: 9390 +Train: [82] [3100/6250] eta: 0:11:07 lr: 0.000010 grad: 0.1258 (0.1332) loss: 0.8085 (0.8143) time: 0.1580 data: 0.0562 max mem: 9390 +Train: [82] [3200/6250] eta: 0:10:43 lr: 0.000010 grad: 0.1307 (0.1332) loss: 0.8026 (0.8142) time: 0.1905 data: 0.0856 max mem: 9390 +Train: [82] [3300/6250] eta: 0:10:22 lr: 0.000010 grad: 0.1287 (0.1332) loss: 0.8108 (0.8142) time: 0.2607 data: 0.1535 max mem: 9390 +Train: [82] [3400/6250] eta: 0:09:57 lr: 0.000010 grad: 0.1334 (0.1333) loss: 0.8129 (0.8141) time: 0.1349 data: 0.0476 max mem: 9390 +Train: [82] [3500/6250] eta: 0:09:35 lr: 0.000010 grad: 0.1314 (0.1332) loss: 0.8127 (0.8141) time: 0.3038 data: 0.2090 max mem: 9390 +Train: [82] [3600/6250] eta: 0:09:13 lr: 0.000010 grad: 0.1315 (0.1331) loss: 0.8162 (0.8141) time: 0.2495 data: 0.1530 max mem: 9390 +Train: [82] [3700/6250] eta: 0:08:54 lr: 0.000010 grad: 0.1291 (0.1331) loss: 0.8104 (0.8140) time: 0.2998 data: 0.2084 max mem: 9390 +Train: [82] [3800/6250] eta: 0:08:30 lr: 0.000010 grad: 0.1278 (0.1331) loss: 0.8155 (0.8139) time: 0.1827 data: 0.0934 max mem: 9390 +Train: [82] [3900/6250] eta: 0:08:16 lr: 0.000010 grad: 0.1309 (0.1331) loss: 0.8104 (0.8138) time: 0.0980 data: 0.0003 max mem: 9390 +Train: [82] [4000/6250] eta: 0:07:54 lr: 0.000010 grad: 0.1361 (0.1331) loss: 0.8114 (0.8138) time: 0.2511 data: 0.1449 max mem: 9390 +Train: [82] [4100/6250] eta: 0:07:30 lr: 0.000010 grad: 0.1309 (0.1331) loss: 0.8163 (0.8137) time: 0.1829 data: 0.0901 max mem: 9390 +Train: [82] [4200/6250] eta: 0:07:19 lr: 0.000010 grad: 0.1345 (0.1331) loss: 0.8158 (0.8136) time: 0.0907 data: 0.0002 max mem: 9390 +Train: [82] [4300/6250] eta: 0:06:55 lr: 0.000010 grad: 0.1335 (0.1331) loss: 0.8115 (0.8136) time: 0.1576 data: 0.0629 max mem: 9390 +Train: [82] [4400/6250] eta: 0:06:35 lr: 0.000010 grad: 0.1335 (0.1332) loss: 0.8091 (0.8135) time: 0.4470 data: 0.3543 max mem: 9390 +Train: [82] [4500/6250] eta: 0:06:12 lr: 0.000010 grad: 0.1335 (0.1333) loss: 0.8060 (0.8134) time: 0.2403 data: 0.1449 max mem: 9390 +Train: [82] [4600/6250] eta: 0:05:50 lr: 0.000010 grad: 0.1278 (0.1333) loss: 0.8116 (0.8134) time: 0.1340 data: 0.0475 max mem: 9390 +Train: [82] [4700/6250] eta: 0:05:30 lr: 0.000010 grad: 0.1443 (0.1334) loss: 0.8118 (0.8133) time: 0.1179 data: 0.0073 max mem: 9390 +Train: [82] [4800/6250] eta: 0:05:09 lr: 0.000010 grad: 0.1193 (0.1333) loss: 0.8108 (0.8133) time: 0.3848 data: 0.2961 max mem: 9390 +Train: [82] [4900/6250] eta: 0:04:47 lr: 0.000010 grad: 0.1248 (0.1334) loss: 0.8070 (0.8132) time: 0.1043 data: 0.0003 max mem: 9390 +Train: [82] [5000/6250] eta: 0:04:26 lr: 0.000010 grad: 0.1286 (0.1334) loss: 0.8152 (0.8131) time: 0.1522 data: 0.0507 max mem: 9390 +Train: [82] [5100/6250] eta: 0:04:04 lr: 0.000010 grad: 0.1361 (0.1335) loss: 0.8069 (0.8130) time: 0.1343 data: 0.0448 max mem: 9390 +Train: [82] [5200/6250] eta: 0:03:43 lr: 0.000010 grad: 0.1302 (0.1335) loss: 0.8121 (0.8129) time: 0.1626 data: 0.0712 max mem: 9390 +Train: [82] [5300/6250] eta: 0:03:23 lr: 0.000010 grad: 0.1395 (0.1336) loss: 0.8122 (0.8128) time: 0.1867 data: 0.1035 max mem: 9390 +Train: [82] [5400/6250] eta: 0:03:05 lr: 0.000010 grad: 0.1407 (0.1337) loss: 0.8097 (0.8128) time: 0.5415 data: 0.4476 max mem: 9390 +Train: [82] [5500/6250] eta: 0:02:42 lr: 0.000010 grad: 0.1367 (0.1338) loss: 0.8088 (0.8126) time: 0.3083 data: 0.1890 max mem: 9390 +Train: [82] [5600/6250] eta: 0:02:22 lr: 0.000010 grad: 0.1361 (0.1338) loss: 0.8098 (0.8126) time: 0.5651 data: 0.4657 max mem: 9390 +Train: [82] [5700/6250] eta: 0:02:00 lr: 0.000010 grad: 0.1312 (0.1338) loss: 0.8095 (0.8125) time: 0.1047 data: 0.0002 max mem: 9390 +Train: [82] [5800/6250] eta: 0:01:37 lr: 0.000010 grad: 0.1360 (0.1338) loss: 0.8071 (0.8125) time: 0.1388 data: 0.0483 max mem: 9390 +Train: [82] [5900/6250] eta: 0:01:16 lr: 0.000010 grad: 0.1261 (0.1338) loss: 0.8226 (0.8125) time: 0.1358 data: 0.0511 max mem: 9390 +Train: [82] [6000/6250] eta: 0:00:54 lr: 0.000010 grad: 0.1246 (0.1337) loss: 0.8142 (0.8125) time: 0.0937 data: 0.0002 max mem: 9390 +Train: [82] [6100/6250] eta: 0:00:32 lr: 0.000010 grad: 0.1344 (0.1337) loss: 0.8151 (0.8126) time: 0.2381 data: 0.1561 max mem: 9390 +Train: [82] [6200/6250] eta: 0:00:10 lr: 0.000010 grad: 0.1364 (0.1337) loss: 0.8090 (0.8125) time: 0.1826 data: 0.0994 max mem: 9390 +Train: [82] [6249/6250] eta: 0:00:00 lr: 0.000010 grad: 0.1311 (0.1337) loss: 0.8090 (0.8125) time: 0.1597 data: 0.0745 max mem: 9390 +Train: [82] Total time: 0:22:46 (0.2187 s / it) +Averaged stats: lr: 0.000010 grad: 0.1311 (0.1337) loss: 0.8090 (0.8125) +Eval (hcp-train-subset): [82] [ 0/62] eta: 0:04:51 loss: 0.8330 (0.8330) time: 4.6997 data: 4.6692 max mem: 9390 +Eval (hcp-train-subset): [82] [61/62] eta: 0:00:00 loss: 0.8184 (0.8211) time: 0.0904 data: 0.0654 max mem: 9390 +Eval (hcp-train-subset): [82] Total time: 0:00:13 (0.2200 s / it) +Averaged stats (hcp-train-subset): loss: 0.8184 (0.8211) +Eval (hcp-val): [82] [ 0/62] eta: 0:03:24 loss: 0.8296 (0.8296) time: 3.2966 data: 3.2419 max mem: 9390 +Eval (hcp-val): [82] [61/62] eta: 0:00:00 loss: 0.8295 (0.8303) time: 0.1209 data: 0.0940 max mem: 9390 +Eval (hcp-val): [82] Total time: 0:00:13 (0.2189 s / it) +Averaged stats (hcp-val): loss: 0.8295 (0.8303) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +Train: [83] [ 0/6250] eta: 11:52:38 lr: 0.000010 grad: 0.4132 (0.4132) loss: 0.8197 (0.8197) time: 6.8414 data: 6.7175 max mem: 9390 +Train: [83] [ 100/6250] eta: 0:22:53 lr: 0.000010 grad: 0.1652 (0.1583) loss: 0.8170 (0.8282) time: 0.1825 data: 0.0961 max mem: 9390 +Train: [83] [ 200/6250] eta: 0:19:52 lr: 0.000010 grad: 0.1303 (0.1518) loss: 0.8154 (0.8226) time: 0.1763 data: 0.0917 max mem: 9390 +Train: [83] [ 300/6250] eta: 0:18:35 lr: 0.000010 grad: 0.1273 (0.1472) loss: 0.8298 (0.8218) time: 0.1802 data: 0.0973 max mem: 9390 +Train: [83] [ 400/6250] eta: 0:17:34 lr: 0.000010 grad: 0.1340 (0.1448) loss: 0.8120 (0.8196) time: 0.1556 data: 0.0700 max mem: 9390 +Train: [83] [ 500/6250] eta: 0:16:59 lr: 0.000010 grad: 0.1217 (0.1423) loss: 0.8157 (0.8186) time: 0.1486 data: 0.0597 max mem: 9390 +Train: [83] [ 600/6250] eta: 0:16:22 lr: 0.000010 grad: 0.1325 (0.1400) loss: 0.8144 (0.8178) time: 0.1546 data: 0.0654 max mem: 9390 +Train: [83] [ 700/6250] eta: 0:15:47 lr: 0.000009 grad: 0.1320 (0.1390) loss: 0.8116 (0.8170) time: 0.1494 data: 0.0593 max mem: 9390 +Train: [83] [ 800/6250] eta: 0:15:13 lr: 0.000009 grad: 0.1257 (0.1385) loss: 0.8202 (0.8161) time: 0.1380 data: 0.0575 max mem: 9390 +Train: [83] [ 900/6250] eta: 0:14:46 lr: 0.000009 grad: 0.1239 (0.1372) loss: 0.8113 (0.8157) time: 0.1604 data: 0.0740 max mem: 9390 +Train: [83] [1000/6250] eta: 0:14:19 lr: 0.000009 grad: 0.1246 (0.1364) loss: 0.8094 (0.8153) time: 0.1309 data: 0.0532 max mem: 9390 +Train: [83] [1100/6250] eta: 0:13:50 lr: 0.000009 grad: 0.1293 (0.1369) loss: 0.8124 (0.8148) time: 0.1306 data: 0.0482 max mem: 9390 +Train: [83] [1200/6250] eta: 0:13:22 lr: 0.000009 grad: 0.1274 (0.1366) loss: 0.8055 (0.8144) time: 0.1360 data: 0.0549 max mem: 9390 +Train: [83] [1300/6250] eta: 0:12:55 lr: 0.000009 grad: 0.1197 (0.1361) loss: 0.8164 (0.8141) time: 0.1265 data: 0.0294 max mem: 9390 +Train: [83] [1400/6250] eta: 0:12:31 lr: 0.000009 grad: 0.1264 (0.1358) loss: 0.8103 (0.8139) time: 0.1275 data: 0.0472 max mem: 9390 +Train: [83] [1500/6250] eta: 0:12:15 lr: 0.000009 grad: 0.1273 (0.1359) loss: 0.8111 (0.8137) time: 0.2242 data: 0.1488 max mem: 9390 +Train: [83] [1600/6250] eta: 0:11:58 lr: 0.000009 grad: 0.1296 (0.1356) loss: 0.8072 (0.8135) time: 0.1471 data: 0.0675 max mem: 9390 +Train: [83] [1700/6250] eta: 0:11:41 lr: 0.000009 grad: 0.1206 (0.1352) loss: 0.8137 (0.8136) time: 0.1566 data: 0.0647 max mem: 9390 +Train: [83] [1800/6250] eta: 0:11:29 lr: 0.000009 grad: 0.1344 (0.1352) loss: 0.8071 (0.8133) time: 0.1809 data: 0.1001 max mem: 9390 +Train: [83] [1900/6250] eta: 0:11:12 lr: 0.000009 grad: 0.1262 (0.1349) loss: 0.8084 (0.8131) time: 0.1461 data: 0.0574 max mem: 9390 +Train: [83] [2000/6250] eta: 0:10:55 lr: 0.000009 grad: 0.1277 (0.1348) loss: 0.8149 (0.8130) time: 0.1513 data: 0.0639 max mem: 9390 +Train: [83] [2100/6250] eta: 0:10:36 lr: 0.000009 grad: 0.1316 (0.1348) loss: 0.8121 (0.8128) time: 0.1369 data: 0.0588 max mem: 9390 +Train: [83] [2200/6250] eta: 0:10:17 lr: 0.000009 grad: 0.1224 (0.1346) loss: 0.8135 (0.8127) time: 0.1404 data: 0.0535 max mem: 9390 +Train: [83] [2300/6250] eta: 0:09:57 lr: 0.000009 grad: 0.1270 (0.1345) loss: 0.8100 (0.8125) time: 0.1439 data: 0.0611 max mem: 9390 +Train: [83] [2400/6250] eta: 0:09:41 lr: 0.000009 grad: 0.1228 (0.1344) loss: 0.8091 (0.8124) time: 0.1018 data: 0.0074 max mem: 9390 +Train: [83] [2500/6250] eta: 0:09:30 lr: 0.000009 grad: 0.1325 (0.1344) loss: 0.8151 (0.8123) time: 0.0954 data: 0.0003 max mem: 9390 +Train: [83] [2600/6250] eta: 0:09:18 lr: 0.000009 grad: 0.1370 (0.1345) loss: 0.8083 (0.8122) time: 0.1207 data: 0.0382 max mem: 9390 +Train: [83] [2700/6250] eta: 0:09:17 lr: 0.000009 grad: 0.1320 (0.1345) loss: 0.8093 (0.8120) time: 0.4139 data: 0.3176 max mem: 9390 +Train: [83] [2800/6250] eta: 0:09:03 lr: 0.000009 grad: 0.1367 (0.1344) loss: 0.8104 (0.8120) time: 0.2742 data: 0.1870 max mem: 9390 +Train: [83] [2900/6250] eta: 0:08:49 lr: 0.000009 grad: 0.1360 (0.1345) loss: 0.8088 (0.8119) time: 0.0993 data: 0.0008 max mem: 9390 +Train: [83] [3000/6250] eta: 0:08:31 lr: 0.000009 grad: 0.1386 (0.1346) loss: 0.8085 (0.8118) time: 0.1372 data: 0.0564 max mem: 9390 +Train: [83] [3100/6250] eta: 0:08:17 lr: 0.000009 grad: 0.1392 (0.1346) loss: 0.8051 (0.8118) time: 0.2497 data: 0.1586 max mem: 9390 +Train: [83] [3200/6250] eta: 0:08:05 lr: 0.000009 grad: 0.1275 (0.1348) loss: 0.8118 (0.8117) time: 0.3195 data: 0.2272 max mem: 9390 +Train: [83] [3300/6250] eta: 0:07:50 lr: 0.000009 grad: 0.1400 (0.1349) loss: 0.8045 (0.8116) time: 0.1945 data: 0.1056 max mem: 9390 +Train: [83] [3400/6250] eta: 0:07:37 lr: 0.000009 grad: 0.1301 (0.1350) loss: 0.8056 (0.8115) time: 0.1496 data: 0.0475 max mem: 9390 +Train: [83] [3500/6250] eta: 0:07:20 lr: 0.000009 grad: 0.1383 (0.1352) loss: 0.8033 (0.8114) time: 0.1769 data: 0.0962 max mem: 9390 +Train: [83] [3600/6250] eta: 0:07:05 lr: 0.000009 grad: 0.1402 (0.1354) loss: 0.8023 (0.8112) time: 0.1627 data: 0.0821 max mem: 9390 +Train: [83] [3700/6250] eta: 0:06:49 lr: 0.000009 grad: 0.1403 (0.1356) loss: 0.8032 (0.8111) time: 0.1318 data: 0.0426 max mem: 9390 +Train: [83] [3800/6250] eta: 0:06:35 lr: 0.000009 grad: 0.1302 (0.1358) loss: 0.8121 (0.8110) time: 0.3021 data: 0.1960 max mem: 9390 +Train: [83] [3900/6250] eta: 0:06:20 lr: 0.000009 grad: 0.1367 (0.1359) loss: 0.8050 (0.8109) time: 0.1849 data: 0.1027 max mem: 9390 +Train: [83] [4000/6250] eta: 0:06:04 lr: 0.000009 grad: 0.1337 (0.1360) loss: 0.8086 (0.8109) time: 0.1333 data: 0.0502 max mem: 9390 +Train: [83] [4100/6250] eta: 0:05:47 lr: 0.000009 grad: 0.1297 (0.1361) loss: 0.8095 (0.8109) time: 0.1497 data: 0.0640 max mem: 9390 +Train: [83] [4200/6250] eta: 0:05:31 lr: 0.000009 grad: 0.1362 (0.1361) loss: 0.8113 (0.8108) time: 0.0992 data: 0.0003 max mem: 9390 +Train: [83] [4300/6250] eta: 0:05:14 lr: 0.000009 grad: 0.1245 (0.1361) loss: 0.8155 (0.8108) time: 0.1572 data: 0.0748 max mem: 9390 +Train: [83] [4400/6250] eta: 0:04:59 lr: 0.000009 grad: 0.1384 (0.1362) loss: 0.8113 (0.8109) time: 0.0868 data: 0.0002 max mem: 9390 +Train: [83] [4500/6250] eta: 0:04:42 lr: 0.000009 grad: 0.1293 (0.1362) loss: 0.8098 (0.8109) time: 0.1220 data: 0.0421 max mem: 9390 +Train: [83] [4600/6250] eta: 0:04:27 lr: 0.000009 grad: 0.1311 (0.1362) loss: 0.8147 (0.8109) time: 0.0969 data: 0.0119 max mem: 9390 +Train: [83] [4700/6250] eta: 0:04:10 lr: 0.000009 grad: 0.1348 (0.1363) loss: 0.8091 (0.8108) time: 0.1433 data: 0.0620 max mem: 9390 +Train: [83] [4800/6250] eta: 0:03:54 lr: 0.000009 grad: 0.1254 (0.1363) loss: 0.8204 (0.8109) time: 0.1726 data: 0.0952 max mem: 9390 +Train: [83] [4900/6250] eta: 0:03:37 lr: 0.000009 grad: 0.1274 (0.1363) loss: 0.8178 (0.8109) time: 0.1454 data: 0.0606 max mem: 9390 +Train: [83] [5000/6250] eta: 0:03:22 lr: 0.000009 grad: 0.1364 (0.1363) loss: 0.8176 (0.8109) time: 0.1243 data: 0.0326 max mem: 9390 +Train: [83] [5100/6250] eta: 0:03:06 lr: 0.000009 grad: 0.1309 (0.1363) loss: 0.8145 (0.8109) time: 0.1819 data: 0.1039 max mem: 9390 +Train: [83] [5200/6250] eta: 0:02:49 lr: 0.000009 grad: 0.1399 (0.1364) loss: 0.8078 (0.8109) time: 0.1447 data: 0.0632 max mem: 9390 +Train: [83] [5300/6250] eta: 0:02:33 lr: 0.000009 grad: 0.1317 (0.1365) loss: 0.8184 (0.8109) time: 0.1613 data: 0.0835 max mem: 9390 +Train: [83] [5400/6250] eta: 0:02:16 lr: 0.000009 grad: 0.1344 (0.1365) loss: 0.8054 (0.8109) time: 0.1355 data: 0.0500 max mem: 9390 +Train: [83] [5500/6250] eta: 0:02:00 lr: 0.000009 grad: 0.1310 (0.1366) loss: 0.8110 (0.8109) time: 0.1474 data: 0.0700 max mem: 9390 +Train: [83] [5600/6250] eta: 0:01:44 lr: 0.000009 grad: 0.1284 (0.1367) loss: 0.8144 (0.8109) time: 0.1082 data: 0.0237 max mem: 9390 +Train: [83] [5700/6250] eta: 0:01:27 lr: 0.000009 grad: 0.1267 (0.1366) loss: 0.8158 (0.8110) time: 0.1482 data: 0.0679 max mem: 9390 +Train: [83] [5800/6250] eta: 0:01:11 lr: 0.000009 grad: 0.1340 (0.1365) loss: 0.8035 (0.8110) time: 0.1623 data: 0.0833 max mem: 9390 +Train: [83] [5900/6250] eta: 0:00:55 lr: 0.000009 grad: 0.1326 (0.1365) loss: 0.8131 (0.8110) time: 0.1310 data: 0.0523 max mem: 9390 +Train: [83] [6000/6250] eta: 0:00:39 lr: 0.000009 grad: 0.1314 (0.1364) loss: 0.8126 (0.8111) time: 0.1179 data: 0.0351 max mem: 9390 +Train: [83] [6100/6250] eta: 0:00:23 lr: 0.000009 grad: 0.1264 (0.1363) loss: 0.8158 (0.8111) time: 0.1833 data: 0.0997 max mem: 9390 +Train: [83] [6200/6250] eta: 0:00:07 lr: 0.000009 grad: 0.1302 (0.1363) loss: 0.8073 (0.8111) time: 0.1270 data: 0.0452 max mem: 9390 +Train: [83] [6249/6250] eta: 0:00:00 lr: 0.000009 grad: 0.1299 (0.1363) loss: 0.8067 (0.8111) time: 0.1295 data: 0.0463 max mem: 9390 +Train: [83] Total time: 0:16:35 (0.1593 s / it) +Averaged stats: lr: 0.000009 grad: 0.1299 (0.1363) loss: 0.8067 (0.8111) +Eval (hcp-train-subset): [83] [ 0/62] eta: 0:04:51 loss: 0.8333 (0.8333) time: 4.6966 data: 4.6664 max mem: 9390 +Eval (hcp-train-subset): [83] [61/62] eta: 0:00:00 loss: 0.8184 (0.8208) time: 0.1067 data: 0.0800 max mem: 9390 +Eval (hcp-train-subset): [83] Total time: 0:00:11 (0.1929 s / it) +Averaged stats (hcp-train-subset): loss: 0.8184 (0.8208) +Eval (hcp-val): [83] [ 0/62] eta: 0:04:08 loss: 0.8267 (0.8267) time: 4.0159 data: 3.9827 max mem: 9390 +Eval (hcp-val): [83] [61/62] eta: 0:00:00 loss: 0.8287 (0.8294) time: 0.0989 data: 0.0740 max mem: 9390 +Eval (hcp-val): [83] Total time: 0:00:12 (0.1965 s / it) +Averaged stats (hcp-val): loss: 0.8287 (0.8294) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +Train: [84] [ 0/6250] eta: 8:12:44 lr: 0.000009 grad: 0.1217 (0.1217) loss: 0.8358 (0.8358) time: 4.7303 data: 4.4795 max mem: 9390 +Train: [84] [ 100/6250] eta: 0:20:12 lr: 0.000009 grad: 0.1635 (0.1829) loss: 0.8110 (0.8154) time: 0.1817 data: 0.0966 max mem: 9390 +Train: [84] [ 200/6250] eta: 0:18:05 lr: 0.000009 grad: 0.1308 (0.1678) loss: 0.8231 (0.8171) time: 0.1744 data: 0.0923 max mem: 9390 +Train: [84] [ 300/6250] eta: 0:17:01 lr: 0.000008 grad: 0.1257 (0.1592) loss: 0.8164 (0.8174) time: 0.1585 data: 0.0758 max mem: 9390 +Train: [84] [ 400/6250] eta: 0:15:53 lr: 0.000008 grad: 0.1165 (0.1551) loss: 0.8142 (0.8164) time: 0.1385 data: 0.0545 max mem: 9390 +Train: [84] [ 500/6250] eta: 0:14:59 lr: 0.000008 grad: 0.1316 (0.1516) loss: 0.8141 (0.8159) time: 0.1333 data: 0.0489 max mem: 9390 +Train: [84] [ 600/6250] eta: 0:14:16 lr: 0.000008 grad: 0.1281 (0.1490) loss: 0.8161 (0.8156) time: 0.1349 data: 0.0559 max mem: 9390 +Train: [84] [ 700/6250] eta: 0:13:50 lr: 0.000008 grad: 0.1288 (0.1466) loss: 0.8158 (0.8157) time: 0.1286 data: 0.0252 max mem: 9390 +Train: [84] [ 800/6250] eta: 0:13:42 lr: 0.000008 grad: 0.1189 (0.1446) loss: 0.8163 (0.8159) time: 0.1922 data: 0.0968 max mem: 9390 +Train: [84] [ 900/6250] eta: 0:13:18 lr: 0.000008 grad: 0.1240 (0.1431) loss: 0.8216 (0.8159) time: 0.1217 data: 0.0353 max mem: 9390 +Train: [84] [1000/6250] eta: 0:13:05 lr: 0.000008 grad: 0.1264 (0.1417) loss: 0.8213 (0.8159) time: 0.1652 data: 0.0794 max mem: 9390 +Train: [84] [1100/6250] eta: 0:12:45 lr: 0.000008 grad: 0.1276 (0.1409) loss: 0.8174 (0.8157) time: 0.1626 data: 0.0813 max mem: 9390 +Train: [84] [1200/6250] eta: 0:12:39 lr: 0.000008 grad: 0.1294 (0.1402) loss: 0.8151 (0.8155) time: 0.1286 data: 0.0303 max mem: 9390 +Train: [84] [1300/6250] eta: 0:12:28 lr: 0.000008 grad: 0.1306 (0.1396) loss: 0.8163 (0.8155) time: 0.1505 data: 0.0678 max mem: 9390 +Train: [84] [1400/6250] eta: 0:12:08 lr: 0.000008 grad: 0.1246 (0.1389) loss: 0.8209 (0.8156) time: 0.1427 data: 0.0593 max mem: 9390 +Train: [84] [1500/6250] eta: 0:11:52 lr: 0.000008 grad: 0.1320 (0.1383) loss: 0.8133 (0.8156) time: 0.1557 data: 0.0740 max mem: 9390 +Train: [84] [1600/6250] eta: 0:11:39 lr: 0.000008 grad: 0.1234 (0.1378) loss: 0.8196 (0.8156) time: 0.2026 data: 0.1260 max mem: 9390 +Train: [84] [1700/6250] eta: 0:11:23 lr: 0.000008 grad: 0.1322 (0.1374) loss: 0.8204 (0.8156) time: 0.1264 data: 0.0453 max mem: 9390 +Train: [84] [1800/6250] eta: 0:11:06 lr: 0.000008 grad: 0.1253 (0.1372) loss: 0.8253 (0.8158) time: 0.1359 data: 0.0497 max mem: 9390 +Train: [84] [1900/6250] eta: 0:10:52 lr: 0.000008 grad: 0.1354 (0.1370) loss: 0.8179 (0.8157) time: 0.1364 data: 0.0500 max mem: 9390 +Train: [84] [2000/6250] eta: 0:10:36 lr: 0.000008 grad: 0.1310 (0.1368) loss: 0.8171 (0.8157) time: 0.1542 data: 0.0646 max mem: 9390 +Train: [84] [2100/6250] eta: 0:10:21 lr: 0.000008 grad: 0.1292 (0.1367) loss: 0.8123 (0.8157) time: 0.1467 data: 0.0690 max mem: 9390 +Train: [84] [2200/6250] eta: 0:10:03 lr: 0.000008 grad: 0.1465 (0.1368) loss: 0.8106 (0.8157) time: 0.1327 data: 0.0434 max mem: 9390 +Train: [84] [2300/6250] eta: 0:09:44 lr: 0.000008 grad: 0.1417 (0.1369) loss: 0.8096 (0.8155) time: 0.1182 data: 0.0351 max mem: 9390 +Train: [84] [2400/6250] eta: 0:09:27 lr: 0.000008 grad: 0.1402 (0.1370) loss: 0.8162 (0.8154) time: 0.1220 data: 0.0329 max mem: 9390 +Train: [84] [2500/6250] eta: 0:09:11 lr: 0.000008 grad: 0.1454 (0.1372) loss: 0.8067 (0.8151) time: 0.1485 data: 0.0643 max mem: 9390 +Train: [84] [2600/6250] eta: 0:08:56 lr: 0.000008 grad: 0.1358 (0.1375) loss: 0.8164 (0.8149) time: 0.1357 data: 0.0593 max mem: 9390 +Train: [84] [2700/6250] eta: 0:08:43 lr: 0.000008 grad: 0.1409 (0.1376) loss: 0.8099 (0.8148) time: 0.1544 data: 0.0719 max mem: 9390 +Train: [84] [2800/6250] eta: 0:08:27 lr: 0.000008 grad: 0.1357 (0.1376) loss: 0.8075 (0.8146) time: 0.1545 data: 0.0721 max mem: 9390 +Train: [84] [2900/6250] eta: 0:08:14 lr: 0.000008 grad: 0.1317 (0.1376) loss: 0.8121 (0.8145) time: 0.1407 data: 0.0497 max mem: 9390 +Train: [84] [3000/6250] eta: 0:08:02 lr: 0.000008 grad: 0.1393 (0.1377) loss: 0.8139 (0.8143) time: 0.1289 data: 0.0400 max mem: 9390 +Train: [84] [3100/6250] eta: 0:07:51 lr: 0.000008 grad: 0.1336 (0.1376) loss: 0.8136 (0.8143) time: 0.2773 data: 0.1820 max mem: 9390 +Train: [84] [3200/6250] eta: 0:07:39 lr: 0.000008 grad: 0.1247 (0.1374) loss: 0.8159 (0.8142) time: 0.0912 data: 0.0003 max mem: 9390 +Train: [84] [3300/6250] eta: 0:07:27 lr: 0.000008 grad: 0.1290 (0.1373) loss: 0.8147 (0.8141) time: 0.0912 data: 0.0002 max mem: 9390 +Train: [84] [3400/6250] eta: 0:07:12 lr: 0.000008 grad: 0.1294 (0.1372) loss: 0.8121 (0.8141) time: 0.1572 data: 0.0666 max mem: 9390 +Train: [84] [3500/6250] eta: 0:06:59 lr: 0.000008 grad: 0.1302 (0.1372) loss: 0.8192 (0.8141) time: 0.1458 data: 0.0606 max mem: 9390 +Train: [84] [3600/6250] eta: 0:06:46 lr: 0.000008 grad: 0.1269 (0.1370) loss: 0.8128 (0.8142) time: 0.1300 data: 0.0245 max mem: 9390 +Train: [84] [3700/6250] eta: 0:06:30 lr: 0.000008 grad: 0.1347 (0.1369) loss: 0.8143 (0.8142) time: 0.1533 data: 0.0702 max mem: 9390 +Train: [84] [3800/6250] eta: 0:06:17 lr: 0.000008 grad: 0.1260 (0.1369) loss: 0.8185 (0.8142) time: 0.2435 data: 0.1410 max mem: 9390 +Train: [84] [3900/6250] eta: 0:06:03 lr: 0.000008 grad: 0.1385 (0.1369) loss: 0.8037 (0.8141) time: 0.2144 data: 0.1313 max mem: 9390 +Train: [84] [4000/6250] eta: 0:05:48 lr: 0.000008 grad: 0.1345 (0.1369) loss: 0.8164 (0.8141) time: 0.1148 data: 0.0195 max mem: 9390 +Train: [84] [4100/6250] eta: 0:05:33 lr: 0.000008 grad: 0.1407 (0.1369) loss: 0.8127 (0.8140) time: 0.1283 data: 0.0346 max mem: 9390 +Train: [84] [4200/6250] eta: 0:05:17 lr: 0.000008 grad: 0.1334 (0.1369) loss: 0.8080 (0.8140) time: 0.1503 data: 0.0724 max mem: 9390 +Train: [84] [4300/6250] eta: 0:05:03 lr: 0.000008 grad: 0.1308 (0.1370) loss: 0.8141 (0.8139) time: 0.1892 data: 0.1028 max mem: 9390 +Train: [84] [4400/6250] eta: 0:04:49 lr: 0.000008 grad: 0.1328 (0.1370) loss: 0.8154 (0.8138) time: 0.1151 data: 0.0233 max mem: 9390 +Train: [84] [4500/6250] eta: 0:04:32 lr: 0.000008 grad: 0.1368 (0.1370) loss: 0.8112 (0.8138) time: 0.1343 data: 0.0471 max mem: 9390 +Train: [84] [4600/6250] eta: 0:04:18 lr: 0.000008 grad: 0.1423 (0.1371) loss: 0.8142 (0.8137) time: 0.1553 data: 0.0568 max mem: 9390 +Train: [84] [4700/6250] eta: 0:04:01 lr: 0.000008 grad: 0.1400 (0.1371) loss: 0.8124 (0.8137) time: 0.1434 data: 0.0640 max mem: 9390 +Train: [84] [4800/6250] eta: 0:03:47 lr: 0.000008 grad: 0.1334 (0.1371) loss: 0.8141 (0.8136) time: 0.1978 data: 0.1113 max mem: 9390 +Train: [84] [4900/6250] eta: 0:03:32 lr: 0.000008 grad: 0.1282 (0.1371) loss: 0.8145 (0.8136) time: 0.2931 data: 0.2003 max mem: 9390 +Train: [84] [5000/6250] eta: 0:03:16 lr: 0.000008 grad: 0.1248 (0.1370) loss: 0.8111 (0.8136) time: 0.1205 data: 0.0148 max mem: 9390 +Train: [84] [5100/6250] eta: 0:03:03 lr: 0.000008 grad: 0.1248 (0.1368) loss: 0.8164 (0.8136) time: 0.3741 data: 0.2876 max mem: 9390 +Train: [84] [5200/6250] eta: 0:02:46 lr: 0.000008 grad: 0.1291 (0.1367) loss: 0.8182 (0.8136) time: 0.1010 data: 0.0099 max mem: 9390 +Train: [84] [5300/6250] eta: 0:02:32 lr: 0.000008 grad: 0.1289 (0.1366) loss: 0.8164 (0.8137) time: 0.4804 data: 0.4021 max mem: 9390 +Train: [84] [5400/6250] eta: 0:02:15 lr: 0.000008 grad: 0.1300 (0.1365) loss: 0.8124 (0.8136) time: 0.1317 data: 0.0484 max mem: 9390 +Train: [84] [5500/6250] eta: 0:01:59 lr: 0.000008 grad: 0.1230 (0.1364) loss: 0.8161 (0.8137) time: 0.1975 data: 0.1137 max mem: 9390 +Train: [84] [5600/6250] eta: 0:01:43 lr: 0.000008 grad: 0.1313 (0.1363) loss: 0.8143 (0.8137) time: 0.1052 data: 0.0002 max mem: 9390 +Train: [84] [5700/6250] eta: 0:01:27 lr: 0.000008 grad: 0.1291 (0.1362) loss: 0.8152 (0.8137) time: 0.1692 data: 0.0723 max mem: 9390 +Train: [84] [5800/6250] eta: 0:01:12 lr: 0.000008 grad: 0.1331 (0.1362) loss: 0.8078 (0.8137) time: 0.2892 data: 0.2003 max mem: 9390 +Train: [84] [5900/6250] eta: 0:00:56 lr: 0.000008 grad: 0.1404 (0.1362) loss: 0.8052 (0.8137) time: 0.2047 data: 0.1262 max mem: 9390 +Train: [84] [6000/6250] eta: 0:00:40 lr: 0.000008 grad: 0.1337 (0.1362) loss: 0.8132 (0.8136) time: 0.1571 data: 0.0236 max mem: 9390 +Train: [84] [6100/6250] eta: 0:00:24 lr: 0.000008 grad: 0.1343 (0.1363) loss: 0.7979 (0.8135) time: 0.4613 data: 0.3829 max mem: 9390 +Train: [84] [6200/6250] eta: 0:00:08 lr: 0.000008 grad: 0.1313 (0.1363) loss: 0.8141 (0.8135) time: 0.1018 data: 0.0081 max mem: 9390 +Train: [84] [6249/6250] eta: 0:00:00 lr: 0.000008 grad: 0.1444 (0.1363) loss: 0.8033 (0.8135) time: 0.1298 data: 0.0273 max mem: 9390 +Train: [84] Total time: 0:17:29 (0.1679 s / it) +Averaged stats: lr: 0.000008 grad: 0.1444 (0.1363) loss: 0.8033 (0.8135) +Eval (hcp-train-subset): [84] [ 0/62] eta: 0:03:38 loss: 0.8328 (0.8328) time: 3.5230 data: 3.4407 max mem: 9390 +Eval (hcp-train-subset): [84] [61/62] eta: 0:00:00 loss: 0.8189 (0.8201) time: 0.1507 data: 0.1253 max mem: 9390 +Eval (hcp-train-subset): [84] Total time: 0:00:15 (0.2444 s / it) +Averaged stats (hcp-train-subset): loss: 0.8189 (0.8201) +Making plots (hcp-train-subset): example=11 +Eval (hcp-val): [84] [ 0/62] eta: 0:05:13 loss: 0.8253 (0.8253) time: 5.0640 data: 5.0259 max mem: 9390 +Eval (hcp-val): [84] [61/62] eta: 0:00:00 loss: 0.8285 (0.8296) time: 0.1307 data: 0.1053 max mem: 9390 +Eval (hcp-val): [84] Total time: 0:00:14 (0.2387 s / it) +Averaged stats (hcp-val): loss: 0.8285 (0.8296) +Making plots (hcp-val): example=3 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +Train: [85] [ 0/6250] eta: 21:09:45 lr: 0.000008 grad: 0.1456 (0.1456) loss: 0.8711 (0.8711) time: 12.1897 data: 12.0629 max mem: 9390 +Train: [85] [ 100/6250] eta: 0:30:10 lr: 0.000008 grad: 0.1599 (0.1769) loss: 0.8049 (0.8112) time: 0.2058 data: 0.1198 max mem: 9390 +Train: [85] [ 200/6250] eta: 0:27:23 lr: 0.000008 grad: 0.1401 (0.1624) loss: 0.8203 (0.8131) time: 0.4883 data: 0.3920 max mem: 9390 +Train: [85] [ 300/6250] eta: 0:23:51 lr: 0.000007 grad: 0.1401 (0.1569) loss: 0.8154 (0.8133) time: 0.2525 data: 0.1436 max mem: 9390 +Train: [85] [ 400/6250] eta: 0:23:34 lr: 0.000007 grad: 0.1304 (0.1520) loss: 0.8138 (0.8127) time: 0.2343 data: 0.1153 max mem: 9390 +Train: [85] [ 500/6250] eta: 0:24:51 lr: 0.000007 grad: 0.1321 (0.1498) loss: 0.8147 (0.8123) time: 0.1320 data: 0.0361 max mem: 9390 +Train: [85] [ 600/6250] eta: 0:24:47 lr: 0.000007 grad: 0.1222 (0.1473) loss: 0.8226 (0.8127) time: 0.2898 data: 0.2009 max mem: 9390 +Train: [85] [ 700/6250] eta: 0:24:03 lr: 0.000007 grad: 0.1247 (0.1446) loss: 0.8147 (0.8131) time: 0.2685 data: 0.1709 max mem: 9390 +Train: [85] [ 800/6250] eta: 0:23:29 lr: 0.000007 grad: 0.1221 (0.1427) loss: 0.8197 (0.8136) time: 0.2517 data: 0.1263 max mem: 9390 +Train: [85] [ 900/6250] eta: 0:22:34 lr: 0.000007 grad: 0.1295 (0.1416) loss: 0.8193 (0.8139) time: 0.1007 data: 0.0002 max mem: 9390 +Train: [85] [1000/6250] eta: 0:22:06 lr: 0.000007 grad: 0.1332 (0.1412) loss: 0.8153 (0.8139) time: 0.1676 data: 0.0762 max mem: 9390 +Train: [85] [1100/6250] eta: 0:22:06 lr: 0.000007 grad: 0.1385 (0.1408) loss: 0.8117 (0.8137) time: 0.2034 data: 0.1078 max mem: 9390 +Train: [85] [1200/6250] eta: 0:22:13 lr: 0.000007 grad: 0.1296 (0.1404) loss: 0.8160 (0.8137) time: 0.3185 data: 0.1899 max mem: 9390 +Train: [85] [1300/6250] eta: 0:22:53 lr: 0.000007 grad: 0.1311 (0.1399) loss: 0.8146 (0.8137) time: 0.1053 data: 0.0002 max mem: 9390 +Train: [85] [1400/6250] eta: 0:22:25 lr: 0.000007 grad: 0.1373 (0.1397) loss: 0.8114 (0.8136) time: 0.4538 data: 0.3741 max mem: 9390 +Train: [85] [1500/6250] eta: 0:22:24 lr: 0.000007 grad: 0.1397 (0.1394) loss: 0.8088 (0.8135) time: 0.1123 data: 0.0005 max mem: 9390 +Train: [85] [1600/6250] eta: 0:21:35 lr: 0.000007 grad: 0.1371 (0.1393) loss: 0.8124 (0.8134) time: 0.3483 data: 0.2623 max mem: 9390 +Train: [85] [1700/6250] eta: 0:21:14 lr: 0.000007 grad: 0.1296 (0.1389) loss: 0.8176 (0.8134) time: 0.1440 data: 0.0666 max mem: 9390 +Train: [85] [1800/6250] eta: 0:20:17 lr: 0.000007 grad: 0.1326 (0.1388) loss: 0.8068 (0.8134) time: 0.1646 data: 0.0839 max mem: 9390 +Train: [85] [1900/6250] eta: 0:19:25 lr: 0.000007 grad: 0.1289 (0.1386) loss: 0.8143 (0.8134) time: 0.1725 data: 0.0868 max mem: 9390 +Train: [85] [2000/6250] eta: 0:18:35 lr: 0.000007 grad: 0.1333 (0.1385) loss: 0.8087 (0.8132) time: 0.1724 data: 0.0869 max mem: 9390 +Train: [85] [2100/6250] eta: 0:17:50 lr: 0.000007 grad: 0.1391 (0.1385) loss: 0.8060 (0.8132) time: 0.1648 data: 0.0751 max mem: 9390 +Train: [85] [2200/6250] eta: 0:17:08 lr: 0.000007 grad: 0.1355 (0.1384) loss: 0.8112 (0.8131) time: 0.1582 data: 0.0675 max mem: 9390 +Train: [85] [2300/6250] eta: 0:16:26 lr: 0.000007 grad: 0.1292 (0.1384) loss: 0.8161 (0.8131) time: 0.1561 data: 0.0654 max mem: 9390 +Train: [85] [2400/6250] eta: 0:15:45 lr: 0.000007 grad: 0.1304 (0.1384) loss: 0.8084 (0.8131) time: 0.1752 data: 0.0927 max mem: 9390 +Train: [85] [2500/6250] eta: 0:15:05 lr: 0.000007 grad: 0.1306 (0.1381) loss: 0.8167 (0.8132) time: 0.1404 data: 0.0520 max mem: 9390 +Train: [85] [2600/6250] eta: 0:14:27 lr: 0.000007 grad: 0.1356 (0.1379) loss: 0.8150 (0.8132) time: 0.1649 data: 0.0771 max mem: 9390 +Train: [85] [2700/6250] eta: 0:13:52 lr: 0.000007 grad: 0.1295 (0.1379) loss: 0.8091 (0.8132) time: 0.1779 data: 0.0894 max mem: 9390 +Train: [85] [2800/6250] eta: 0:13:22 lr: 0.000007 grad: 0.1346 (0.1378) loss: 0.8103 (0.8132) time: 0.2294 data: 0.1447 max mem: 9390 +Train: [85] [2900/6250] eta: 0:12:49 lr: 0.000007 grad: 0.1320 (0.1378) loss: 0.8147 (0.8132) time: 0.1328 data: 0.0368 max mem: 9390 +Train: [85] [3000/6250] eta: 0:12:23 lr: 0.000007 grad: 0.1220 (0.1377) loss: 0.8126 (0.8132) time: 0.1342 data: 0.0430 max mem: 9390 +Train: [85] [3100/6250] eta: 0:12:02 lr: 0.000007 grad: 0.1291 (0.1376) loss: 0.8147 (0.8132) time: 0.2039 data: 0.1083 max mem: 9390 +Train: [85] [3200/6250] eta: 0:11:52 lr: 0.000007 grad: 0.1348 (0.1374) loss: 0.8131 (0.8132) time: 0.1196 data: 0.0188 max mem: 9390 +Train: [85] [3300/6250] eta: 0:11:33 lr: 0.000007 grad: 0.1309 (0.1375) loss: 0.8134 (0.8132) time: 0.2321 data: 0.1356 max mem: 9390 +Train: [85] [3400/6250] eta: 0:11:09 lr: 0.000007 grad: 0.1333 (0.1376) loss: 0.8146 (0.8131) time: 0.2689 data: 0.1517 max mem: 9390 +Train: [85] [3500/6250] eta: 0:10:51 lr: 0.000007 grad: 0.1384 (0.1376) loss: 0.8146 (0.8131) time: 0.5516 data: 0.4577 max mem: 9390 +Train: [85] [3600/6250] eta: 0:10:37 lr: 0.000007 grad: 0.1473 (0.1376) loss: 0.8109 (0.8131) time: 0.7506 data: 0.6565 max mem: 9390 +Train: [85] [3700/6250] eta: 0:10:11 lr: 0.000007 grad: 0.1318 (0.1377) loss: 0.8169 (0.8131) time: 0.2159 data: 0.1180 max mem: 9390 +Train: [85] [3800/6250] eta: 0:09:50 lr: 0.000007 grad: 0.1290 (0.1375) loss: 0.8143 (0.8131) time: 0.1649 data: 0.0665 max mem: 9390 +Train: [85] [3900/6250] eta: 0:09:25 lr: 0.000007 grad: 0.1322 (0.1375) loss: 0.8143 (0.8131) time: 0.1440 data: 0.0209 max mem: 9390 +Train: [85] [4000/6250] eta: 0:09:06 lr: 0.000007 grad: 0.1329 (0.1375) loss: 0.8156 (0.8131) time: 0.1354 data: 0.0351 max mem: 9390 +Train: [85] [4100/6250] eta: 0:08:50 lr: 0.000007 grad: 0.1354 (0.1375) loss: 0.8105 (0.8131) time: 0.1486 data: 0.0357 max mem: 9390 +Train: [85] [4200/6250] eta: 0:08:32 lr: 0.000007 grad: 0.1297 (0.1375) loss: 0.8125 (0.8130) time: 0.2525 data: 0.1469 max mem: 9390 +Train: [85] [4300/6250] eta: 0:08:07 lr: 0.000007 grad: 0.1342 (0.1375) loss: 0.8080 (0.8130) time: 0.3650 data: 0.2492 max mem: 9390 +Train: [85] [4400/6250] eta: 0:07:40 lr: 0.000007 grad: 0.1348 (0.1375) loss: 0.8099 (0.8130) time: 0.3506 data: 0.2600 max mem: 9390 +Train: [85] [4500/6250] eta: 0:07:18 lr: 0.000007 grad: 0.1348 (0.1375) loss: 0.8146 (0.8130) time: 0.1900 data: 0.0982 max mem: 9390 +Train: [85] [4600/6250] eta: 0:06:57 lr: 0.000007 grad: 0.1247 (0.1375) loss: 0.8120 (0.8130) time: 0.6144 data: 0.5219 max mem: 9390 +Train: [85] [4700/6250] eta: 0:06:31 lr: 0.000007 grad: 0.1306 (0.1375) loss: 0.8134 (0.8130) time: 0.3822 data: 0.2877 max mem: 9390 +Train: [85] [4800/6250] eta: 0:06:08 lr: 0.000007 grad: 0.1291 (0.1374) loss: 0.8124 (0.8131) time: 0.9642 data: 0.8756 max mem: 9390 +Train: [85] [4900/6250] eta: 0:05:43 lr: 0.000007 grad: 0.1278 (0.1373) loss: 0.8128 (0.8131) time: 0.1047 data: 0.0050 max mem: 9390 +pretraining fmri mae +start: 2026-04-01 15:51:34 +cwd: /data/connor/fmri-fm +sha: 7f4cedc35609f6857314e0d1ea6657523f17ddeb, status: has uncommitted changes, branch: dev/clane9 +config: +name: input_space_v3/flat_lr1e-3_2/pretrain +notes: input_space ablation v3 flat_lr1e-3_2; use tube masking and on-disk data (input_space=flat + base_lr=1e-3 seed=5402) +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain +input_space: flat +patch_size: 16 +num_frames: 16 +t_patch_size: 4 +mask_ratio: 0.9 +pred_mask_ratio: null +masking: tube +masking_kwargs: {} +mask_patch_size: null +model: mae_vit_base +model_kwargs: + decoding: attn + pos_embed: sep + target_norm: null + pca_norm_nc: 2 + t_pred_stride: 2 + no_decode_pos: true + mask_drop_scale: false + pred_edge_pad: 0 + gauss_sigma: null + class_token: true + reg_tokens: 0 + no_embed_class: true + head_init_scale: 0.0 + decoder_depth: 4 + drop_path_rate: 0.0 +datasets: + hcp-train: + type: wds + url: /data/fmri-datasets/pretrain/hcpya-all.${input_space}.wds/hcpya-all-${input_space}-{00000..01799}.tar + clipping: random + clipping_kwargs: + oversample: 4.0 + shuffle: true + buffer_size: 2000 + samples_per_epoch: 200000 + hcp-train-subset: + type: arrow + root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/validation + split_range: + - 0 + - 2000 + shuffle: false + hcp-val: + type: arrow + root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/test + split_range: + - 0 + - 2000 + shuffle: false +train_dataset: hcp-train +eval_datasets: +- hcp-train-subset +- hcp-val +val_dataset: null +clip_vmax: 3.0 +normalize: frame +tr_scale: null +crop_scale: null +crop_aspect: null +gray_jitter: null +num_workers: 16 +epochs: 100 +batch_size: 32 +accum_iter: 1 +base_lr: 0.001 +min_lr: 0.0 +warmup_epochs: 5 +weight_decay: 0.05 +betas: +- 0.9 +- 0.95 +clip_grad: 1.0 +amp: true +amp_dtype: float16 +ckpt: null +resume: true +auto_resume: true +start_epoch: 0 +max_checkpoints: 0 +checkpoint_period: null +plot_period: 5 +device: cuda +presend_cuda: false +seed: 5402 +debug: false +wandb: true +wandb_entity: null +wandb_project: fMRI-foundation-model +rank: 0 +world_size: 1 +gpu: 0 +distributed: true +dist_backend: nccl +in_chans: 1 +img_size: +- 224 +- 560 + +train transform: +Compose( + ToTensor() + TemporalCenterCrop(num_frames=16) + Normalize(mode='frame') + Clip(vmax=3.0) + FlatUnmask((224, 560)) +) +val transform: +Compose( + ToTensor() + TemporalCenterCrop(num_frames=16) + Normalize(mode='frame') + Clip(vmax=3.0) + FlatUnmask((224, 560)) +) +mask generator: +TubeMasking( + mask_ratio=0.9 + (patchify): Patchify2D((224, 560), (16, 16), in_chans=1) +) +loading dataset: hcp-train + +type: wds +url: /data/fmri-datasets/pretrain/hcpya-all.${input_space}.wds/hcpya-all-${input_space}-{00000..01799}.tar +clipping: random +clipping_kwargs: + oversample: 4.0 +shuffle: true +buffer_size: 2000 +samples_per_epoch: 200000 + +loading dataset: hcp-train-subset + +type: arrow +root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/validation +split_range: +- 0 +- 2000 +shuffle: false + +split indices: [899, 472, 767, 116, 1265, 1852, 300, 1335, 361, 1560] +loading dataset: hcp-val + +type: arrow +root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/test +split_range: +- 0 +- 2000 +shuffle: false + +split indices: [1075, 1189, 738, 1350, 965, 1964, 1367, 1183, 1619, 1407] +model: +MaskedAutoencoderViT( + decoding=attn, t_pred_stride=2, pred_edge_pad=0, no_decode_pos=True + (encoder): MaskedEncoder( + class_token=True, reg_tokens=0, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) + (pred_patchify): StridedPatchify3D((16, 224, 560), (2, 16, 16), in_chans=1, t_stride=2) + (decoder): MaskedDecoder( + cross_decode=False, class_token=True, no_embed_class=True + (pos_embed): SeparablePosEmbed(512, (4, 14, 35)) + (proj): Linear(in_features=768, out_features=512, bias=True) + (blocks): ModuleList( + (0-3): 4 x Block( + (norm1): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=16 + (q): Linear(in_features=512, out_features=512, bias=True) + (k): Linear(in_features=512, out_features=512, bias=True) + (v): Linear(in_features=512, out_features=512, bias=True) + (proj): Linear(in_features=512, out_features=512, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=512, out_features=2048, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=2048, out_features=512, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (head): Linear(in_features=512, out_features=512, bias=True) + ) +) +num params: 99.7M +total batch size: 32 = 32 bs per gpu x 1 accum x 1 gpus +lr: 1.25e-04 = 1.00e-03 x 32 / 256 +full schedule: epochs = 100 (steps = 625000) +warmup: epochs = 5 (steps = 31250) +loaded model state from checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +loaded optimizer state, resuming training from 85 +start training for 100 epochs +Train: [85] [ 0/6250] eta: 13:17:23 lr: 0.000008 grad: 0.0817 (0.0817) loss: 0.8092 (0.8092) time: 7.6550 data: 6.6650 max mem: 9353 +Train: [85] [ 100/6250] eta: 0:20:47 lr: 0.000008 grad: 0.1445 (0.1599) loss: 0.8205 (0.8187) time: 0.1316 data: 0.0491 max mem: 9390 +Train: [85] [ 200/6250] eta: 0:17:04 lr: 0.000008 grad: 0.1528 (0.1549) loss: 0.8054 (0.8157) time: 0.1290 data: 0.0385 max mem: 9390 +Train: [85] [ 300/6250] eta: 0:15:29 lr: 0.000007 grad: 0.1391 (0.1510) loss: 0.8188 (0.8153) time: 0.1364 data: 0.0493 max mem: 9390 +Train: [85] [ 400/6250] eta: 0:14:31 lr: 0.000007 grad: 0.1498 (0.1489) loss: 0.8091 (0.8144) time: 0.1357 data: 0.0401 max mem: 9390 +Train: [85] [ 500/6250] eta: 0:13:50 lr: 0.000007 grad: 0.1233 (0.1476) loss: 0.8177 (0.8137) time: 0.1393 data: 0.0542 max mem: 9390 +Train: [85] [ 600/6250] eta: 0:13:21 lr: 0.000007 grad: 0.1394 (0.1466) loss: 0.8083 (0.8132) time: 0.1024 data: 0.0002 max mem: 9390 +Train: [85] [ 700/6250] eta: 0:13:07 lr: 0.000007 grad: 0.1426 (0.1452) loss: 0.8134 (0.8129) time: 0.1248 data: 0.0350 max mem: 9390 +Train: [85] [ 800/6250] eta: 0:13:02 lr: 0.000007 grad: 0.1348 (0.1441) loss: 0.8143 (0.8130) time: 0.1674 data: 0.0864 max mem: 9390 +Train: [85] [ 900/6250] eta: 0:12:57 lr: 0.000007 grad: 0.1315 (0.1430) loss: 0.8213 (0.8132) time: 0.1534 data: 0.0693 max mem: 9390 +Train: [85] [1000/6250] eta: 0:12:48 lr: 0.000007 grad: 0.1304 (0.1425) loss: 0.8052 (0.8129) time: 0.1680 data: 0.0892 max mem: 9390 +Train: [85] [1100/6250] eta: 0:12:34 lr: 0.000007 grad: 0.1292 (0.1418) loss: 0.8127 (0.8127) time: 0.1230 data: 0.0379 max mem: 9390 +Train: [85] [1200/6250] eta: 0:12:21 lr: 0.000007 grad: 0.1325 (0.1411) loss: 0.8075 (0.8127) time: 0.1378 data: 0.0534 max mem: 9390 +Train: [85] [1300/6250] eta: 0:12:11 lr: 0.000007 grad: 0.1316 (0.1407) loss: 0.8144 (0.8127) time: 0.1209 data: 0.0302 max mem: 9390 +Train: [85] [1400/6250] eta: 0:11:58 lr: 0.000007 grad: 0.1297 (0.1403) loss: 0.8079 (0.8127) time: 0.1544 data: 0.0644 max mem: 9390 +Train: [85] [1500/6250] eta: 0:11:44 lr: 0.000007 grad: 0.1323 (0.1400) loss: 0.8149 (0.8126) time: 0.1448 data: 0.0611 max mem: 9390 +Train: [85] [1600/6250] eta: 0:11:31 lr: 0.000007 grad: 0.1281 (0.1394) loss: 0.8193 (0.8128) time: 0.1720 data: 0.0885 max mem: 9390 +Train: [85] [1700/6250] eta: 0:11:16 lr: 0.000007 grad: 0.1257 (0.1389) loss: 0.8147 (0.8128) time: 0.1630 data: 0.0716 max mem: 9390 +Train: [85] [1800/6250] eta: 0:11:02 lr: 0.000007 grad: 0.1319 (0.1386) loss: 0.8064 (0.8127) time: 0.1578 data: 0.0769 max mem: 9390 +Train: [85] [1900/6250] eta: 0:10:48 lr: 0.000007 grad: 0.1337 (0.1385) loss: 0.8143 (0.8127) time: 0.1592 data: 0.0790 max mem: 9390 +Train: [85] [2000/6250] eta: 0:10:33 lr: 0.000007 grad: 0.1260 (0.1383) loss: 0.8136 (0.8128) time: 0.1233 data: 0.0376 max mem: 9390 +Train: [85] [2100/6250] eta: 0:10:19 lr: 0.000007 grad: 0.1337 (0.1382) loss: 0.8119 (0.8127) time: 0.1412 data: 0.0562 max mem: 9390 +Train: [85] [2200/6250] eta: 0:10:31 lr: 0.000007 grad: 0.1354 (0.1381) loss: 0.8073 (0.8126) time: 0.2071 data: 0.1327 max mem: 9390 +Train: [85] [2300/6250] eta: 0:10:27 lr: 0.000007 grad: 0.1252 (0.1381) loss: 0.8218 (0.8125) time: 0.2532 data: 0.1741 max mem: 9390 +Train: [85] [2400/6250] eta: 0:10:15 lr: 0.000007 grad: 0.1363 (0.1382) loss: 0.8144 (0.8126) time: 0.2004 data: 0.1155 max mem: 9390 +Train: [85] [2500/6250] eta: 0:10:01 lr: 0.000007 grad: 0.1295 (0.1381) loss: 0.8033 (0.8125) time: 0.1792 data: 0.0900 max mem: 9390 +Train: [85] [2600/6250] eta: 0:09:47 lr: 0.000007 grad: 0.1408 (0.1381) loss: 0.8066 (0.8124) time: 0.1588 data: 0.0567 max mem: 9390 +Train: [85] [2700/6250] eta: 0:09:32 lr: 0.000007 grad: 0.1322 (0.1379) loss: 0.8102 (0.8123) time: 0.1669 data: 0.0765 max mem: 9390 +Train: [85] [2800/6250] eta: 0:09:17 lr: 0.000007 grad: 0.1402 (0.1379) loss: 0.8098 (0.8123) time: 0.1719 data: 0.0796 max mem: 9390 +Train: [85] [2900/6250] eta: 0:09:02 lr: 0.000007 grad: 0.1384 (0.1377) loss: 0.8063 (0.8123) time: 0.1789 data: 0.0926 max mem: 9390 +Train: [85] [3000/6250] eta: 0:08:47 lr: 0.000007 grad: 0.1268 (0.1377) loss: 0.8143 (0.8123) time: 0.1928 data: 0.1011 max mem: 9390 +Train: [85] [3100/6250] eta: 0:08:33 lr: 0.000007 grad: 0.1319 (0.1376) loss: 0.8137 (0.8123) time: 0.1944 data: 0.1035 max mem: 9390 +Train: [85] [3200/6250] eta: 0:08:17 lr: 0.000007 grad: 0.1379 (0.1376) loss: 0.8141 (0.8123) time: 0.1694 data: 0.0808 max mem: 9390 +Train: [85] [3300/6250] eta: 0:08:02 lr: 0.000007 grad: 0.1328 (0.1377) loss: 0.8095 (0.8122) time: 0.1756 data: 0.0856 max mem: 9390 +Train: [85] [3400/6250] eta: 0:07:46 lr: 0.000007 grad: 0.1276 (0.1377) loss: 0.8098 (0.8122) time: 0.1560 data: 0.0675 max mem: 9390 +Train: [85] [3500/6250] eta: 0:07:30 lr: 0.000007 grad: 0.1316 (0.1377) loss: 0.8063 (0.8121) time: 0.1900 data: 0.0979 max mem: 9390 +Train: [85] [3600/6250] eta: 0:07:14 lr: 0.000007 grad: 0.1379 (0.1377) loss: 0.8100 (0.8120) time: 0.1747 data: 0.0896 max mem: 9390 +Train: [85] [3700/6250] eta: 0:06:58 lr: 0.000007 grad: 0.1331 (0.1377) loss: 0.8077 (0.8119) time: 0.1679 data: 0.0789 max mem: 9390 +Train: [85] [3800/6250] eta: 0:06:42 lr: 0.000007 grad: 0.1352 (0.1376) loss: 0.8132 (0.8119) time: 0.1681 data: 0.0787 max mem: 9390 +Train: [85] [3900/6250] eta: 0:06:26 lr: 0.000007 grad: 0.1417 (0.1376) loss: 0.8066 (0.8118) time: 0.1576 data: 0.0669 max mem: 9390 +Train: [85] [4000/6250] eta: 0:06:10 lr: 0.000007 grad: 0.1405 (0.1376) loss: 0.8095 (0.8118) time: 0.1492 data: 0.0592 max mem: 9390 +Train: [85] [4100/6250] eta: 0:05:54 lr: 0.000007 grad: 0.1224 (0.1377) loss: 0.8089 (0.8117) time: 0.1684 data: 0.0795 max mem: 9390 +Train: [85] [4200/6250] eta: 0:05:38 lr: 0.000007 grad: 0.1323 (0.1378) loss: 0.8070 (0.8117) time: 0.1927 data: 0.1073 max mem: 9390 +Train: [85] [4300/6250] eta: 0:05:22 lr: 0.000007 grad: 0.1377 (0.1377) loss: 0.8107 (0.8117) time: 0.1882 data: 0.0962 max mem: 9390 +Train: [85] [4400/6250] eta: 0:05:05 lr: 0.000007 grad: 0.1307 (0.1376) loss: 0.8123 (0.8117) time: 0.1714 data: 0.0795 max mem: 9390 +Train: [85] [4500/6250] eta: 0:04:49 lr: 0.000007 grad: 0.1355 (0.1376) loss: 0.8126 (0.8117) time: 0.1926 data: 0.1059 max mem: 9390 +Train: [85] [4600/6250] eta: 0:04:33 lr: 0.000007 grad: 0.1303 (0.1376) loss: 0.8098 (0.8117) time: 0.1850 data: 0.0935 max mem: 9390 +Train: [85] [4700/6250] eta: 0:04:17 lr: 0.000007 grad: 0.1298 (0.1376) loss: 0.8141 (0.8117) time: 0.1759 data: 0.0890 max mem: 9390 +Train: [85] [4800/6250] eta: 0:04:00 lr: 0.000007 grad: 0.1364 (0.1375) loss: 0.8101 (0.8117) time: 0.1510 data: 0.0628 max mem: 9390 +Train: [85] [4900/6250] eta: 0:03:44 lr: 0.000007 grad: 0.1351 (0.1375) loss: 0.8116 (0.8118) time: 0.1742 data: 0.0929 max mem: 9390 +Train: [85] [5000/6250] eta: 0:03:27 lr: 0.000007 grad: 0.1276 (0.1375) loss: 0.8124 (0.8118) time: 0.1694 data: 0.0775 max mem: 9390 +Train: [85] [5100/6250] eta: 0:03:11 lr: 0.000007 grad: 0.1351 (0.1374) loss: 0.8156 (0.8119) time: 0.1878 data: 0.0956 max mem: 9390 +Train: [85] [5200/6250] eta: 0:02:55 lr: 0.000007 grad: 0.1300 (0.1373) loss: 0.8208 (0.8120) time: 0.1871 data: 0.0960 max mem: 9390 +Train: [85] [5300/6250] eta: 0:02:38 lr: 0.000007 grad: 0.1315 (0.1372) loss: 0.8155 (0.8121) time: 0.1857 data: 0.1024 max mem: 9390 +Train: [85] [5400/6250] eta: 0:02:21 lr: 0.000007 grad: 0.1321 (0.1372) loss: 0.8183 (0.8122) time: 0.1800 data: 0.0879 max mem: 9390 +Train: [85] [5500/6250] eta: 0:02:05 lr: 0.000007 grad: 0.1343 (0.1372) loss: 0.8148 (0.8123) time: 0.1507 data: 0.0666 max mem: 9390 +Train: [85] [5600/6250] eta: 0:01:48 lr: 0.000007 grad: 0.1327 (0.1371) loss: 0.8157 (0.8123) time: 0.1532 data: 0.0632 max mem: 9390 +Train: [85] [5700/6250] eta: 0:01:32 lr: 0.000007 grad: 0.1361 (0.1371) loss: 0.8155 (0.8124) time: 0.1648 data: 0.0816 max mem: 9390 +Train: [85] [5800/6250] eta: 0:01:15 lr: 0.000007 grad: 0.1346 (0.1370) loss: 0.8148 (0.8124) time: 0.1771 data: 0.0935 max mem: 9390 +Train: [85] [5900/6250] eta: 0:00:58 lr: 0.000007 grad: 0.1322 (0.1370) loss: 0.8132 (0.8124) time: 0.1533 data: 0.0670 max mem: 9390 +Train: [85] [6000/6250] eta: 0:00:41 lr: 0.000007 grad: 0.1341 (0.1370) loss: 0.8130 (0.8124) time: 0.1700 data: 0.0806 max mem: 9390 +Train: [85] [6100/6250] eta: 0:00:25 lr: 0.000007 grad: 0.1256 (0.1369) loss: 0.8143 (0.8125) time: 0.2135 data: 0.1204 max mem: 9390 +Train: [85] [6200/6250] eta: 0:00:08 lr: 0.000007 grad: 0.1290 (0.1368) loss: 0.8148 (0.8126) time: 0.1713 data: 0.0857 max mem: 9390 +Train: [85] [6249/6250] eta: 0:00:00 lr: 0.000007 grad: 0.1346 (0.1367) loss: 0.8202 (0.8126) time: 0.2256 data: 0.1466 max mem: 9390 +Train: [85] Total time: 0:17:38 (0.1693 s / it) +Averaged stats: lr: 0.000007 grad: 0.1346 (0.1367) loss: 0.8202 (0.8126) +Eval (hcp-train-subset): [85] [ 0/62] eta: 0:04:56 loss: 0.8328 (0.8328) time: 4.7879 data: 4.7443 max mem: 9390 +Eval (hcp-train-subset): [85] [61/62] eta: 0:00:00 loss: 0.8155 (0.8195) time: 0.1143 data: 0.0831 max mem: 9390 +Eval (hcp-train-subset): [85] Total time: 0:00:14 (0.2272 s / it) +Averaged stats (hcp-train-subset): loss: 0.8155 (0.8195) +Eval (hcp-val): [85] [ 0/62] eta: 0:04:59 loss: 0.8288 (0.8288) time: 4.8268 data: 4.7872 max mem: 9390 +Eval (hcp-val): [85] [61/62] eta: 0:00:00 loss: 0.8274 (0.8293) time: 0.1444 data: 0.1185 max mem: 9390 +Eval (hcp-val): [85] Total time: 0:00:14 (0.2328 s / it) +Averaged stats (hcp-val): loss: 0.8274 (0.8293) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +Train: [86] [ 0/6250] eta: 10:04:32 lr: 0.000007 grad: 0.1117 (0.1117) loss: 0.7970 (0.7970) time: 5.8035 data: 5.6589 max mem: 9390 +Train: [86] [ 100/6250] eta: 0:23:43 lr: 0.000007 grad: 0.1602 (0.1629) loss: 0.8120 (0.8185) time: 0.1705 data: 0.0723 max mem: 9390 +Train: [86] [ 200/6250] eta: 0:20:48 lr: 0.000007 grad: 0.1383 (0.1557) loss: 0.8224 (0.8163) time: 0.2046 data: 0.1010 max mem: 9390 +Train: [86] [ 300/6250] eta: 0:18:58 lr: 0.000007 grad: 0.1354 (0.1519) loss: 0.8116 (0.8155) time: 0.1527 data: 0.0663 max mem: 9390 +Train: [86] [ 400/6250] eta: 0:18:43 lr: 0.000007 grad: 0.1342 (0.1504) loss: 0.8184 (0.8150) time: 0.1965 data: 0.1051 max mem: 9390 +Train: [86] [ 500/6250] eta: 0:18:06 lr: 0.000007 grad: 0.1336 (0.1486) loss: 0.8092 (0.8149) time: 0.1963 data: 0.1005 max mem: 9390 +Train: [86] [ 600/6250] eta: 0:17:20 lr: 0.000006 grad: 0.1295 (0.1472) loss: 0.8177 (0.8148) time: 0.1931 data: 0.0933 max mem: 9390 +Train: [86] [ 700/6250] eta: 0:17:07 lr: 0.000006 grad: 0.1348 (0.1458) loss: 0.8188 (0.8149) time: 0.2221 data: 0.1120 max mem: 9390 +Train: [86] [ 800/6250] eta: 0:16:47 lr: 0.000006 grad: 0.1338 (0.1449) loss: 0.8132 (0.8150) time: 0.1622 data: 0.0676 max mem: 9390 +Train: [86] [ 900/6250] eta: 0:16:35 lr: 0.000006 grad: 0.1476 (0.1446) loss: 0.8086 (0.8148) time: 0.1778 data: 0.0774 max mem: 9390 +Train: [86] [1000/6250] eta: 0:16:10 lr: 0.000006 grad: 0.1322 (0.1442) loss: 0.8120 (0.8145) time: 0.1537 data: 0.0650 max mem: 9390 +Train: [86] [1100/6250] eta: 0:15:46 lr: 0.000006 grad: 0.1314 (0.1436) loss: 0.8132 (0.8145) time: 0.1359 data: 0.0475 max mem: 9390 +Train: [86] [1200/6250] eta: 0:15:21 lr: 0.000006 grad: 0.1342 (0.1429) loss: 0.8175 (0.8145) time: 0.1673 data: 0.0779 max mem: 9390 +Train: [86] [1300/6250] eta: 0:15:00 lr: 0.000006 grad: 0.1388 (0.1426) loss: 0.8067 (0.8143) time: 0.1159 data: 0.0038 max mem: 9390 +Train: [86] [1400/6250] eta: 0:14:39 lr: 0.000006 grad: 0.1242 (0.1420) loss: 0.8154 (0.8142) time: 0.1717 data: 0.0838 max mem: 9390 +Train: [86] [1500/6250] eta: 0:14:18 lr: 0.000006 grad: 0.1332 (0.1415) loss: 0.8094 (0.8141) time: 0.1760 data: 0.0864 max mem: 9390 +Train: [86] [1600/6250] eta: 0:13:57 lr: 0.000006 grad: 0.1387 (0.1407) loss: 0.8086 (0.8141) time: 0.1776 data: 0.0803 max mem: 9390 +Train: [86] [1700/6250] eta: 0:13:36 lr: 0.000006 grad: 0.1395 (0.1406) loss: 0.8064 (0.8141) time: 0.1580 data: 0.0677 max mem: 9390 +Train: [86] [1800/6250] eta: 0:13:17 lr: 0.000006 grad: 0.1326 (0.1403) loss: 0.8059 (0.8138) time: 0.1743 data: 0.0864 max mem: 9390 +Train: [86] [1900/6250] eta: 0:12:56 lr: 0.000006 grad: 0.1276 (0.1401) loss: 0.8088 (0.8135) time: 0.1787 data: 0.0903 max mem: 9390 +Train: [86] [2000/6250] eta: 0:12:35 lr: 0.000006 grad: 0.1341 (0.1398) loss: 0.8043 (0.8133) time: 0.1688 data: 0.0774 max mem: 9390 +Train: [86] [2100/6250] eta: 0:12:17 lr: 0.000006 grad: 0.1295 (0.1396) loss: 0.8130 (0.8132) time: 0.1627 data: 0.0732 max mem: 9390 +Train: [86] [2200/6250] eta: 0:11:59 lr: 0.000006 grad: 0.1288 (0.1392) loss: 0.8079 (0.8131) time: 0.2018 data: 0.1104 max mem: 9390 +Train: [86] [2300/6250] eta: 0:11:39 lr: 0.000006 grad: 0.1373 (0.1390) loss: 0.8078 (0.8130) time: 0.1765 data: 0.0832 max mem: 9390 +Train: [86] [2400/6250] eta: 0:11:20 lr: 0.000006 grad: 0.1280 (0.1387) loss: 0.8060 (0.8129) time: 0.1665 data: 0.0819 max mem: 9390 +Train: [86] [2500/6250] eta: 0:11:01 lr: 0.000006 grad: 0.1371 (0.1386) loss: 0.8057 (0.8128) time: 0.1743 data: 0.0865 max mem: 9390 +Train: [86] [2600/6250] eta: 0:10:42 lr: 0.000006 grad: 0.1288 (0.1383) loss: 0.8165 (0.8128) time: 0.1933 data: 0.1028 max mem: 9390 +Train: [86] [2700/6250] eta: 0:10:23 lr: 0.000006 grad: 0.1350 (0.1381) loss: 0.8105 (0.8127) time: 0.1834 data: 0.0944 max mem: 9390 +Train: [86] [2800/6250] eta: 0:10:04 lr: 0.000006 grad: 0.1289 (0.1379) loss: 0.8147 (0.8127) time: 0.1483 data: 0.0579 max mem: 9390 +Train: [86] [2900/6250] eta: 0:09:45 lr: 0.000006 grad: 0.1274 (0.1377) loss: 0.8180 (0.8128) time: 0.1538 data: 0.0659 max mem: 9390 +Train: [86] [3000/6250] eta: 0:09:28 lr: 0.000006 grad: 0.1237 (0.1374) loss: 0.8108 (0.8129) time: 0.1842 data: 0.1024 max mem: 9390 +Train: [86] [3100/6250] eta: 0:09:10 lr: 0.000006 grad: 0.1321 (0.1372) loss: 0.8115 (0.8130) time: 0.1557 data: 0.0619 max mem: 9390 +Train: [86] [3200/6250] eta: 0:08:53 lr: 0.000006 grad: 0.1275 (0.1370) loss: 0.8140 (0.8131) time: 0.2106 data: 0.1265 max mem: 9390 +Train: [86] [3300/6250] eta: 0:08:35 lr: 0.000006 grad: 0.1279 (0.1369) loss: 0.8070 (0.8131) time: 0.1938 data: 0.1002 max mem: 9390 +Train: [86] [3400/6250] eta: 0:08:18 lr: 0.000006 grad: 0.1305 (0.1367) loss: 0.8086 (0.8131) time: 0.2087 data: 0.1241 max mem: 9390 +Train: [86] [3500/6250] eta: 0:08:00 lr: 0.000006 grad: 0.1406 (0.1365) loss: 0.8042 (0.8131) time: 0.1922 data: 0.1003 max mem: 9390 +Train: [86] [3600/6250] eta: 0:07:42 lr: 0.000006 grad: 0.1360 (0.1364) loss: 0.8094 (0.8130) time: 0.1656 data: 0.0784 max mem: 9390 +Train: [86] [3700/6250] eta: 0:07:25 lr: 0.000006 grad: 0.1288 (0.1363) loss: 0.8140 (0.8130) time: 0.1955 data: 0.1123 max mem: 9390 +Train: [86] [3800/6250] eta: 0:07:07 lr: 0.000006 grad: 0.1307 (0.1363) loss: 0.8175 (0.8130) time: 0.1912 data: 0.1082 max mem: 9390 +Train: [86] [3900/6250] eta: 0:06:49 lr: 0.000006 grad: 0.1324 (0.1363) loss: 0.8086 (0.8130) time: 0.1909 data: 0.0958 max mem: 9390 +Train: [86] [4000/6250] eta: 0:06:32 lr: 0.000006 grad: 0.1413 (0.1363) loss: 0.8110 (0.8129) time: 0.1621 data: 0.0757 max mem: 9390 +Train: [86] [4100/6250] eta: 0:06:14 lr: 0.000006 grad: 0.1354 (0.1363) loss: 0.8101 (0.8129) time: 0.1713 data: 0.0880 max mem: 9390 +Train: [86] [4200/6250] eta: 0:05:57 lr: 0.000006 grad: 0.1381 (0.1362) loss: 0.8147 (0.8129) time: 0.1723 data: 0.0899 max mem: 9390 +Train: [86] [4300/6250] eta: 0:05:40 lr: 0.000006 grad: 0.1300 (0.1362) loss: 0.8212 (0.8129) time: 0.1813 data: 0.0940 max mem: 9390 +Train: [86] [4400/6250] eta: 0:05:22 lr: 0.000006 grad: 0.1324 (0.1363) loss: 0.8135 (0.8129) time: 0.1641 data: 0.0754 max mem: 9390 +Train: [86] [4500/6250] eta: 0:05:04 lr: 0.000006 grad: 0.1246 (0.1363) loss: 0.8172 (0.8130) time: 0.1679 data: 0.0829 max mem: 9390 +Train: [86] [4600/6250] eta: 0:04:47 lr: 0.000006 grad: 0.1333 (0.1363) loss: 0.8187 (0.8130) time: 0.2374 data: 0.1601 max mem: 9390 +pretraining fmri mae +start: 2026-04-02 10:08:25 +cwd: /data/connor/fmri-fm +sha: 7f4cedc35609f6857314e0d1ea6657523f17ddeb, status: has uncommitted changes, branch: dev/clane9 +config: +name: input_space_v3/flat_lr1e-3_2/pretrain +notes: input_space ablation v3 flat_lr1e-3_2; use tube masking and on-disk data (input_space=flat + base_lr=1e-3 seed=5402) +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain +input_space: flat +patch_size: 16 +num_frames: 16 +t_patch_size: 4 +mask_ratio: 0.9 +pred_mask_ratio: null +masking: tube +masking_kwargs: {} +mask_patch_size: null +model: mae_vit_base +model_kwargs: + decoding: attn + pos_embed: sep + target_norm: null + pca_norm_nc: 2 + t_pred_stride: 2 + no_decode_pos: true + mask_drop_scale: false + pred_edge_pad: 0 + gauss_sigma: null + class_token: true + reg_tokens: 0 + no_embed_class: true + head_init_scale: 0.0 + decoder_depth: 4 + drop_path_rate: 0.0 +datasets: + hcp-train: + type: wds + url: /data/fmri-datasets/pretrain/hcpya-all.${input_space}.wds/hcpya-all-${input_space}-{00000..01799}.tar + clipping: random + clipping_kwargs: + oversample: 4.0 + shuffle: true + buffer_size: 2000 + samples_per_epoch: 200000 + hcp-train-subset: + type: arrow + root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/validation + split_range: + - 0 + - 2000 + shuffle: false + hcp-val: + type: arrow + root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/test + split_range: + - 0 + - 2000 + shuffle: false +train_dataset: hcp-train +eval_datasets: +- hcp-train-subset +- hcp-val +val_dataset: null +clip_vmax: 3.0 +normalize: frame +tr_scale: null +crop_scale: null +crop_aspect: null +gray_jitter: null +num_workers: 16 +epochs: 100 +batch_size: 32 +accum_iter: 1 +base_lr: 0.001 +min_lr: 0.0 +warmup_epochs: 5 +weight_decay: 0.05 +betas: +- 0.9 +- 0.95 +clip_grad: 1.0 +amp: true +amp_dtype: float16 +ckpt: null +resume: true +auto_resume: true +start_epoch: 0 +max_checkpoints: 0 +checkpoint_period: null +plot_period: 5 +device: cuda +presend_cuda: false +seed: 5402 +debug: false +wandb: true +wandb_entity: null +wandb_project: fMRI-foundation-model +rank: 0 +world_size: 1 +gpu: 0 +distributed: true +dist_backend: nccl +in_chans: 1 +img_size: +- 224 +- 560 + +train transform: +Compose( + ToTensor() + TemporalCenterCrop(num_frames=16) + Normalize(mode='frame') + Clip(vmax=3.0) + FlatUnmask((224, 560)) +) +val transform: +Compose( + ToTensor() + TemporalCenterCrop(num_frames=16) + Normalize(mode='frame') + Clip(vmax=3.0) + FlatUnmask((224, 560)) +) +mask generator: +TubeMasking( + mask_ratio=0.9 + (patchify): Patchify2D((224, 560), (16, 16), in_chans=1) +) +loading dataset: hcp-train + +type: wds +url: /data/fmri-datasets/pretrain/hcpya-all.${input_space}.wds/hcpya-all-${input_space}-{00000..01799}.tar +clipping: random +clipping_kwargs: + oversample: 4.0 +shuffle: true +buffer_size: 2000 +samples_per_epoch: 200000 + +loading dataset: hcp-train-subset + +type: arrow +root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/validation +split_range: +- 0 +- 2000 +shuffle: false + +split indices: [899, 472, 767, 116, 1265, 1852, 300, 1335, 361, 1560] +loading dataset: hcp-val + +type: arrow +root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/test +split_range: +- 0 +- 2000 +shuffle: false + +split indices: [1075, 1189, 738, 1350, 965, 1964, 1367, 1183, 1619, 1407] +model: +MaskedAutoencoderViT( + decoding=attn, t_pred_stride=2, pred_edge_pad=0, no_decode_pos=True + (encoder): MaskedEncoder( + class_token=True, reg_tokens=0, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) + (pred_patchify): StridedPatchify3D((16, 224, 560), (2, 16, 16), in_chans=1, t_stride=2) + (decoder): MaskedDecoder( + cross_decode=False, class_token=True, no_embed_class=True + (pos_embed): SeparablePosEmbed(512, (4, 14, 35)) + (proj): Linear(in_features=768, out_features=512, bias=True) + (blocks): ModuleList( + (0-3): 4 x Block( + (norm1): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=16 + (q): Linear(in_features=512, out_features=512, bias=True) + (k): Linear(in_features=512, out_features=512, bias=True) + (v): Linear(in_features=512, out_features=512, bias=True) + (proj): Linear(in_features=512, out_features=512, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=512, out_features=2048, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=2048, out_features=512, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (head): Linear(in_features=512, out_features=512, bias=True) + ) +) +num params: 99.7M +total batch size: 32 = 32 bs per gpu x 1 accum x 1 gpus +lr: 1.25e-04 = 1.00e-03 x 32 / 256 +full schedule: epochs = 100 (steps = 625000) +warmup: epochs = 5 (steps = 31250) +loaded model state from checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +loaded optimizer state, resuming training from 86 +start training for 100 epochs +Train: [86] [ 0/6250] eta: 15:04:44 lr: 0.000007 grad: 0.2069 (0.2069) loss: 0.8379 (0.8379) time: 8.6855 data: 7.6354 max mem: 9353 +Train: [86] [ 100/6250] eta: 0:23:41 lr: 0.000007 grad: 0.1471 (0.1811) loss: 0.8111 (0.8161) time: 0.1622 data: 0.0605 max mem: 9390 +Train: [86] [ 200/6250] eta: 0:20:17 lr: 0.000007 grad: 0.1300 (0.1643) loss: 0.8191 (0.8151) time: 0.1849 data: 0.0869 max mem: 9390 +Train: [86] [ 300/6250] eta: 0:18:46 lr: 0.000007 grad: 0.1439 (0.1580) loss: 0.8052 (0.8128) time: 0.1799 data: 0.0753 max mem: 9390 +Train: [86] [ 400/6250] eta: 0:18:04 lr: 0.000007 grad: 0.1358 (0.1528) loss: 0.8138 (0.8122) time: 0.1595 data: 0.0713 max mem: 9390 +Train: [86] [ 500/6250] eta: 0:17:22 lr: 0.000007 grad: 0.1278 (0.1497) loss: 0.8166 (0.8129) time: 0.1556 data: 0.0576 max mem: 9390 +Train: [86] [ 600/6250] eta: 0:16:54 lr: 0.000006 grad: 0.1271 (0.1472) loss: 0.8240 (0.8137) time: 0.1807 data: 0.0794 max mem: 9390 +Train: [86] [ 700/6250] eta: 0:16:27 lr: 0.000006 grad: 0.1309 (0.1456) loss: 0.8149 (0.8142) time: 0.1876 data: 0.0939 max mem: 9390 +Train: [86] [ 800/6250] eta: 0:16:03 lr: 0.000006 grad: 0.1273 (0.1437) loss: 0.8212 (0.8150) time: 0.1650 data: 0.0735 max mem: 9390 +Train: [86] [ 900/6250] eta: 0:15:40 lr: 0.000006 grad: 0.1290 (0.1423) loss: 0.8144 (0.8152) time: 0.1709 data: 0.0804 max mem: 9390 +Train: [86] [1000/6250] eta: 0:15:23 lr: 0.000006 grad: 0.1257 (0.1410) loss: 0.8150 (0.8156) time: 0.1870 data: 0.0946 max mem: 9390 +Train: [86] [1100/6250] eta: 0:14:59 lr: 0.000006 grad: 0.1325 (0.1404) loss: 0.8208 (0.8159) time: 0.1496 data: 0.0536 max mem: 9390 +Train: [86] [1200/6250] eta: 0:14:40 lr: 0.000006 grad: 0.1244 (0.1394) loss: 0.8207 (0.8160) time: 0.1520 data: 0.0606 max mem: 9390 +Train: [86] [1300/6250] eta: 0:14:20 lr: 0.000006 grad: 0.1264 (0.1389) loss: 0.8170 (0.8160) time: 0.1596 data: 0.0668 max mem: 9390 +Train: [86] [1400/6250] eta: 0:13:59 lr: 0.000006 grad: 0.1267 (0.1386) loss: 0.8190 (0.8160) time: 0.1517 data: 0.0577 max mem: 9390 +Train: [86] [1500/6250] eta: 0:13:40 lr: 0.000006 grad: 0.1283 (0.1384) loss: 0.8159 (0.8158) time: 0.1844 data: 0.0993 max mem: 9390 +Train: [86] [1600/6250] eta: 0:13:18 lr: 0.000006 grad: 0.1307 (0.1381) loss: 0.8133 (0.8158) time: 0.1422 data: 0.0560 max mem: 9390 +Train: [86] [1700/6250] eta: 0:12:57 lr: 0.000006 grad: 0.1335 (0.1379) loss: 0.8142 (0.8156) time: 0.1372 data: 0.0444 max mem: 9390 +Train: [86] [1800/6250] eta: 0:12:37 lr: 0.000006 grad: 0.1362 (0.1379) loss: 0.8094 (0.8153) time: 0.1521 data: 0.0602 max mem: 9390 +Train: [86] [1900/6250] eta: 0:12:17 lr: 0.000006 grad: 0.1445 (0.1381) loss: 0.8073 (0.8150) time: 0.1694 data: 0.0771 max mem: 9390 +Train: [86] [2000/6250] eta: 0:11:58 lr: 0.000006 grad: 0.1349 (0.1381) loss: 0.8081 (0.8149) time: 0.1697 data: 0.0750 max mem: 9390 +Train: [86] [2100/6250] eta: 0:11:38 lr: 0.000006 grad: 0.1319 (0.1381) loss: 0.8123 (0.8147) time: 0.1454 data: 0.0572 max mem: 9390 +Train: [86] [2200/6250] eta: 0:11:19 lr: 0.000006 grad: 0.1377 (0.1381) loss: 0.8135 (0.8146) time: 0.1607 data: 0.0638 max mem: 9390 +Train: [86] [2300/6250] eta: 0:11:01 lr: 0.000006 grad: 0.1339 (0.1380) loss: 0.8126 (0.8145) time: 0.1638 data: 0.0776 max mem: 9390 +Train: [86] [2400/6250] eta: 0:10:42 lr: 0.000006 grad: 0.1399 (0.1380) loss: 0.8060 (0.8145) time: 0.1421 data: 0.0384 max mem: 9390 +Train: [86] [2500/6250] eta: 0:10:24 lr: 0.000006 grad: 0.1426 (0.1379) loss: 0.8075 (0.8144) time: 0.1408 data: 0.0574 max mem: 9390 +Train: [86] [2600/6250] eta: 0:10:06 lr: 0.000006 grad: 0.1315 (0.1379) loss: 0.8196 (0.8143) time: 0.1753 data: 0.0835 max mem: 9390 +Train: [86] [2700/6250] eta: 0:09:48 lr: 0.000006 grad: 0.1392 (0.1380) loss: 0.8044 (0.8141) time: 0.1564 data: 0.0683 max mem: 9390 +Train: [86] [2800/6250] eta: 0:09:31 lr: 0.000006 grad: 0.1302 (0.1380) loss: 0.8140 (0.8139) time: 0.1662 data: 0.0723 max mem: 9390 +Train: [86] [2900/6250] eta: 0:09:13 lr: 0.000006 grad: 0.1314 (0.1381) loss: 0.8136 (0.8139) time: 0.1644 data: 0.0801 max mem: 9390 +Train: [86] [3000/6250] eta: 0:08:56 lr: 0.000006 grad: 0.1332 (0.1380) loss: 0.8099 (0.8138) time: 0.1467 data: 0.0545 max mem: 9390 +Train: [86] [3100/6250] eta: 0:08:39 lr: 0.000006 grad: 0.1340 (0.1380) loss: 0.8075 (0.8137) time: 0.1460 data: 0.0545 max mem: 9390 +Train: [86] [3200/6250] eta: 0:08:22 lr: 0.000006 grad: 0.1291 (0.1379) loss: 0.8137 (0.8136) time: 0.1508 data: 0.0686 max mem: 9390 +Train: [86] [3300/6250] eta: 0:08:05 lr: 0.000006 grad: 0.1339 (0.1380) loss: 0.8138 (0.8136) time: 0.1651 data: 0.0768 max mem: 9390 +Train: [86] [3400/6250] eta: 0:07:48 lr: 0.000006 grad: 0.1349 (0.1379) loss: 0.8152 (0.8135) time: 0.1650 data: 0.0729 max mem: 9390 +Train: [86] [3500/6250] eta: 0:07:31 lr: 0.000006 grad: 0.1453 (0.1379) loss: 0.8090 (0.8135) time: 0.1567 data: 0.0677 max mem: 9390 +Train: [86] [3600/6250] eta: 0:07:14 lr: 0.000006 grad: 0.1393 (0.1379) loss: 0.8136 (0.8134) time: 0.1712 data: 0.0878 max mem: 9390 +Train: [86] [3700/6250] eta: 0:06:57 lr: 0.000006 grad: 0.1295 (0.1378) loss: 0.8141 (0.8134) time: 0.1613 data: 0.0737 max mem: 9390 +Train: [86] [3800/6250] eta: 0:06:41 lr: 0.000006 grad: 0.1323 (0.1377) loss: 0.8167 (0.8135) time: 0.1745 data: 0.0877 max mem: 9390 +Train: [86] [3900/6250] eta: 0:06:24 lr: 0.000006 grad: 0.1276 (0.1375) loss: 0.8162 (0.8135) time: 0.1612 data: 0.0659 max mem: 9390 +Train: [86] [4000/6250] eta: 0:06:07 lr: 0.000006 grad: 0.1303 (0.1373) loss: 0.8178 (0.8136) time: 0.1889 data: 0.0975 max mem: 9390 +Train: [86] [4100/6250] eta: 0:05:51 lr: 0.000006 grad: 0.1348 (0.1373) loss: 0.8117 (0.8136) time: 0.1699 data: 0.0834 max mem: 9390 +Train: [86] [4200/6250] eta: 0:05:34 lr: 0.000006 grad: 0.1356 (0.1372) loss: 0.8128 (0.8136) time: 0.1462 data: 0.0571 max mem: 9390 +Train: [86] [4300/6250] eta: 0:05:17 lr: 0.000006 grad: 0.1326 (0.1372) loss: 0.8171 (0.8136) time: 0.1506 data: 0.0615 max mem: 9390 +Train: [86] [4400/6250] eta: 0:05:01 lr: 0.000006 grad: 0.1335 (0.1372) loss: 0.8160 (0.8136) time: 0.1363 data: 0.0562 max mem: 9390 +Train: [86] [4500/6250] eta: 0:04:44 lr: 0.000006 grad: 0.1368 (0.1372) loss: 0.8106 (0.8137) time: 0.1599 data: 0.0685 max mem: 9390 +Train: [86] [4600/6250] eta: 0:04:28 lr: 0.000006 grad: 0.1269 (0.1371) loss: 0.8135 (0.8137) time: 0.1494 data: 0.0616 max mem: 9390 +Train: [86] [4700/6250] eta: 0:04:12 lr: 0.000006 grad: 0.1287 (0.1370) loss: 0.8103 (0.8138) time: 0.1653 data: 0.0815 max mem: 9390 +Train: [86] [4800/6250] eta: 0:03:55 lr: 0.000006 grad: 0.1303 (0.1369) loss: 0.8175 (0.8137) time: 0.1431 data: 0.0477 max mem: 9390 +Train: [86] [4900/6250] eta: 0:03:39 lr: 0.000006 grad: 0.1342 (0.1368) loss: 0.8147 (0.8138) time: 0.1653 data: 0.0811 max mem: 9390 +Train: [86] [5000/6250] eta: 0:03:22 lr: 0.000006 grad: 0.1248 (0.1367) loss: 0.8129 (0.8137) time: 0.1678 data: 0.0757 max mem: 9390 +Train: [86] [5100/6250] eta: 0:03:06 lr: 0.000006 grad: 0.1314 (0.1367) loss: 0.8103 (0.8137) time: 0.1788 data: 0.0934 max mem: 9390 +Train: [86] [5200/6250] eta: 0:02:50 lr: 0.000006 grad: 0.1356 (0.1367) loss: 0.8138 (0.8137) time: 0.1575 data: 0.0665 max mem: 9390 +Train: [86] [5300/6250] eta: 0:02:34 lr: 0.000006 grad: 0.1247 (0.1366) loss: 0.8144 (0.8137) time: 0.1549 data: 0.0617 max mem: 9390 +Train: [86] [5400/6250] eta: 0:02:17 lr: 0.000006 grad: 0.1356 (0.1366) loss: 0.8135 (0.8137) time: 0.1675 data: 0.0861 max mem: 9390 +Train: [86] [5500/6250] eta: 0:02:01 lr: 0.000006 grad: 0.1334 (0.1365) loss: 0.8172 (0.8138) time: 0.1580 data: 0.0721 max mem: 9390 +Train: [86] [5600/6250] eta: 0:01:45 lr: 0.000006 grad: 0.1386 (0.1365) loss: 0.8108 (0.8138) time: 0.1467 data: 0.0622 max mem: 9390 +Train: [86] [5700/6250] eta: 0:01:29 lr: 0.000006 grad: 0.1363 (0.1366) loss: 0.8156 (0.8138) time: 0.1611 data: 0.0747 max mem: 9390 +Train: [86] [5800/6250] eta: 0:01:12 lr: 0.000006 grad: 0.1359 (0.1366) loss: 0.8113 (0.8138) time: 0.1412 data: 0.0550 max mem: 9390 +Train: [86] [5900/6250] eta: 0:00:56 lr: 0.000006 grad: 0.1254 (0.1365) loss: 0.8106 (0.8138) time: 0.1554 data: 0.0673 max mem: 9390 +Train: [86] [6000/6250] eta: 0:00:40 lr: 0.000006 grad: 0.1318 (0.1365) loss: 0.8037 (0.8138) time: 0.1545 data: 0.0687 max mem: 9390 +Train: [86] [6100/6250] eta: 0:00:24 lr: 0.000006 grad: 0.1361 (0.1365) loss: 0.8137 (0.8138) time: 0.1619 data: 0.0690 max mem: 9390 +Train: [86] [6200/6250] eta: 0:00:08 lr: 0.000006 grad: 0.1312 (0.1365) loss: 0.8146 (0.8138) time: 0.1588 data: 0.0731 max mem: 9390 +Train: [86] [6249/6250] eta: 0:00:00 lr: 0.000006 grad: 0.1335 (0.1365) loss: 0.8157 (0.8138) time: 0.1524 data: 0.0686 max mem: 9390 +Train: [86] Total time: 0:16:55 (0.1625 s / it) +Averaged stats: lr: 0.000006 grad: 0.1335 (0.1365) loss: 0.8157 (0.8138) +Eval (hcp-train-subset): [86] [ 0/62] eta: 0:04:52 loss: 0.8294 (0.8294) time: 4.7225 data: 4.6928 max mem: 9390 +Eval (hcp-train-subset): [86] [61/62] eta: 0:00:00 loss: 0.8142 (0.8183) time: 0.1184 data: 0.0879 max mem: 9390 +Eval (hcp-train-subset): [86] Total time: 0:00:12 (0.2039 s / it) +Averaged stats (hcp-train-subset): loss: 0.8142 (0.8183) +Eval (hcp-val): [86] [ 0/62] eta: 0:04:36 loss: 0.8284 (0.8284) time: 4.4596 data: 4.4309 max mem: 9390 +Eval (hcp-val): [86] [61/62] eta: 0:00:00 loss: 0.8269 (0.8288) time: 0.1104 data: 0.0851 max mem: 9390 +Eval (hcp-val): [86] Total time: 0:00:12 (0.1995 s / it) +Averaged stats (hcp-val): loss: 0.8269 (0.8288) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +Train: [87] [ 0/6250] eta: 8:20:51 lr: 0.000006 grad: 0.9644 (0.9644) loss: 0.8228 (0.8228) time: 4.8082 data: 4.4774 max mem: 9390 +Train: [87] [ 100/6250] eta: 0:20:39 lr: 0.000006 grad: 0.1408 (0.1751) loss: 0.8191 (0.8234) time: 0.1424 data: 0.0557 max mem: 9390 +Train: [87] [ 200/6250] eta: 0:18:14 lr: 0.000006 grad: 0.1290 (0.1663) loss: 0.8058 (0.8180) time: 0.1968 data: 0.1101 max mem: 9390 +Train: [87] [ 300/6250] eta: 0:17:17 lr: 0.000006 grad: 0.1232 (0.1585) loss: 0.8190 (0.8174) time: 0.1580 data: 0.0666 max mem: 9390 +Train: [87] [ 400/6250] eta: 0:16:49 lr: 0.000006 grad: 0.1438 (0.1539) loss: 0.8164 (0.8175) time: 0.1444 data: 0.0450 max mem: 9390 +Train: [87] [ 500/6250] eta: 0:16:33 lr: 0.000006 grad: 0.1256 (0.1507) loss: 0.8184 (0.8174) time: 0.1804 data: 0.0930 max mem: 9390 +Train: [87] [ 600/6250] eta: 0:16:26 lr: 0.000006 grad: 0.1325 (0.1490) loss: 0.8143 (0.8174) time: 0.1983 data: 0.1016 max mem: 9390 +Train: [87] [ 700/6250] eta: 0:16:05 lr: 0.000006 grad: 0.1303 (0.1471) loss: 0.8206 (0.8175) time: 0.1604 data: 0.0721 max mem: 9390 +Train: [87] [ 800/6250] eta: 0:15:48 lr: 0.000006 grad: 0.1333 (0.1463) loss: 0.8170 (0.8175) time: 0.1681 data: 0.0769 max mem: 9390 +Train: [87] [ 900/6250] eta: 0:15:33 lr: 0.000006 grad: 0.1356 (0.1451) loss: 0.8183 (0.8175) time: 0.1881 data: 0.0845 max mem: 9390 +Train: [87] [1000/6250] eta: 0:15:06 lr: 0.000006 grad: 0.1308 (0.1442) loss: 0.8106 (0.8175) time: 0.1570 data: 0.0661 max mem: 9390 +Train: [87] [1100/6250] eta: 0:14:46 lr: 0.000006 grad: 0.1332 (0.1432) loss: 0.8200 (0.8175) time: 0.1764 data: 0.0916 max mem: 9390 +Train: [87] [1200/6250] eta: 0:14:23 lr: 0.000006 grad: 0.1339 (0.1423) loss: 0.8213 (0.8175) time: 0.1695 data: 0.0793 max mem: 9390 +Train: [87] [1300/6250] eta: 0:13:59 lr: 0.000006 grad: 0.1293 (0.1416) loss: 0.8148 (0.8175) time: 0.1548 data: 0.0657 max mem: 9390 +Train: [87] [1400/6250] eta: 0:13:42 lr: 0.000005 grad: 0.1329 (0.1413) loss: 0.8118 (0.8173) time: 0.1730 data: 0.0885 max mem: 9390 +Train: [87] [1500/6250] eta: 0:13:22 lr: 0.000005 grad: 0.1388 (0.1410) loss: 0.8121 (0.8172) time: 0.1597 data: 0.0684 max mem: 9390 +Train: [87] [1600/6250] eta: 0:13:03 lr: 0.000005 grad: 0.1359 (0.1407) loss: 0.8212 (0.8171) time: 0.1772 data: 0.0916 max mem: 9390 +Train: [87] [1700/6250] eta: 0:12:41 lr: 0.000005 grad: 0.1293 (0.1405) loss: 0.8158 (0.8170) time: 0.1572 data: 0.0636 max mem: 9390 +Train: [87] [1800/6250] eta: 0:12:24 lr: 0.000005 grad: 0.1327 (0.1404) loss: 0.8170 (0.8168) time: 0.1864 data: 0.0954 max mem: 9390 +Train: [87] [1900/6250] eta: 0:12:06 lr: 0.000005 grad: 0.1382 (0.1401) loss: 0.8133 (0.8167) time: 0.1619 data: 0.0735 max mem: 9390 +Train: [87] [2000/6250] eta: 0:11:49 lr: 0.000005 grad: 0.1352 (0.1399) loss: 0.8150 (0.8166) time: 0.1578 data: 0.0786 max mem: 9390 +Train: [87] [2100/6250] eta: 0:11:31 lr: 0.000005 grad: 0.1409 (0.1399) loss: 0.8147 (0.8164) time: 0.1654 data: 0.0814 max mem: 9390 +Train: [87] [2200/6250] eta: 0:11:14 lr: 0.000005 grad: 0.1327 (0.1398) loss: 0.8134 (0.8162) time: 0.1396 data: 0.0514 max mem: 9390 +Train: [87] [2300/6250] eta: 0:10:58 lr: 0.000005 grad: 0.1383 (0.1398) loss: 0.8144 (0.8161) time: 0.1787 data: 0.0851 max mem: 9390 +Train: [87] [2400/6250] eta: 0:10:41 lr: 0.000005 grad: 0.1433 (0.1401) loss: 0.8063 (0.8158) time: 0.1783 data: 0.0942 max mem: 9390 +Train: [87] [2500/6250] eta: 0:10:24 lr: 0.000005 grad: 0.1420 (0.1401) loss: 0.8137 (0.8157) time: 0.1627 data: 0.0682 max mem: 9390 +Train: [87] [2600/6250] eta: 0:10:08 lr: 0.000005 grad: 0.1333 (0.1401) loss: 0.8145 (0.8156) time: 0.1760 data: 0.0941 max mem: 9390 +Train: [87] [2700/6250] eta: 0:09:51 lr: 0.000005 grad: 0.1396 (0.1401) loss: 0.8110 (0.8154) time: 0.1713 data: 0.0864 max mem: 9390 +Train: [87] [2800/6250] eta: 0:09:33 lr: 0.000005 grad: 0.1401 (0.1402) loss: 0.8056 (0.8152) time: 0.1571 data: 0.0759 max mem: 9390 +Train: [87] [2900/6250] eta: 0:09:16 lr: 0.000005 grad: 0.1453 (0.1403) loss: 0.8098 (0.8150) time: 0.1638 data: 0.0757 max mem: 9390 +Train: [87] [3000/6250] eta: 0:08:59 lr: 0.000005 grad: 0.1275 (0.1403) loss: 0.8134 (0.8149) time: 0.1550 data: 0.0678 max mem: 9390 +Train: [87] [3100/6250] eta: 0:08:42 lr: 0.000005 grad: 0.1379 (0.1403) loss: 0.8107 (0.8148) time: 0.1793 data: 0.0951 max mem: 9390 +Train: [87] [3200/6250] eta: 0:08:25 lr: 0.000005 grad: 0.1338 (0.1404) loss: 0.8098 (0.8146) time: 0.1306 data: 0.0431 max mem: 9390 +Train: [87] [3300/6250] eta: 0:08:08 lr: 0.000005 grad: 0.1375 (0.1405) loss: 0.8092 (0.8145) time: 0.1627 data: 0.0770 max mem: 9390 +Train: [87] [3400/6250] eta: 0:07:51 lr: 0.000005 grad: 0.1358 (0.1405) loss: 0.8092 (0.8143) time: 0.1497 data: 0.0615 max mem: 9390 +Train: [87] [3500/6250] eta: 0:07:34 lr: 0.000005 grad: 0.1412 (0.1406) loss: 0.8100 (0.8142) time: 0.1619 data: 0.0700 max mem: 9390 +Train: [87] [3600/6250] eta: 0:07:18 lr: 0.000005 grad: 0.1432 (0.1405) loss: 0.8092 (0.8142) time: 0.1769 data: 0.0957 max mem: 9390 +Train: [87] [3700/6250] eta: 0:07:01 lr: 0.000005 grad: 0.1354 (0.1405) loss: 0.8144 (0.8141) time: 0.1672 data: 0.0786 max mem: 9390 +Train: [87] [3800/6250] eta: 0:06:44 lr: 0.000005 grad: 0.1349 (0.1405) loss: 0.8126 (0.8141) time: 0.1734 data: 0.0900 max mem: 9390 +Train: [87] [3900/6250] eta: 0:06:28 lr: 0.000005 grad: 0.1478 (0.1406) loss: 0.8104 (0.8140) time: 0.1553 data: 0.0616 max mem: 9390 +Train: [87] [4000/6250] eta: 0:06:11 lr: 0.000005 grad: 0.1390 (0.1406) loss: 0.8082 (0.8139) time: 0.1309 data: 0.0431 max mem: 9390 +Train: [87] [4100/6250] eta: 0:05:55 lr: 0.000005 grad: 0.1432 (0.1406) loss: 0.8072 (0.8138) time: 0.2030 data: 0.1142 max mem: 9390 +Train: [87] [4200/6250] eta: 0:05:38 lr: 0.000005 grad: 0.1345 (0.1406) loss: 0.8141 (0.8137) time: 0.1419 data: 0.0514 max mem: 9390 +Train: [87] [4300/6250] eta: 0:05:21 lr: 0.000005 grad: 0.1353 (0.1406) loss: 0.8064 (0.8136) time: 0.1398 data: 0.0460 max mem: 9390 +Train: [87] [4400/6250] eta: 0:05:04 lr: 0.000005 grad: 0.1376 (0.1406) loss: 0.8097 (0.8135) time: 0.1497 data: 0.0644 max mem: 9390 +Train: [87] [4500/6250] eta: 0:04:48 lr: 0.000005 grad: 0.1393 (0.1406) loss: 0.8053 (0.8134) time: 0.1862 data: 0.1000 max mem: 9390 +Train: [87] [4600/6250] eta: 0:04:32 lr: 0.000005 grad: 0.1446 (0.1406) loss: 0.8111 (0.8134) time: 0.1530 data: 0.0681 max mem: 9390 +Train: [87] [4700/6250] eta: 0:04:15 lr: 0.000005 grad: 0.1427 (0.1406) loss: 0.8027 (0.8133) time: 0.1851 data: 0.1066 max mem: 9390 +Train: [87] [4800/6250] eta: 0:03:59 lr: 0.000005 grad: 0.1359 (0.1406) loss: 0.8080 (0.8133) time: 0.1556 data: 0.0769 max mem: 9390 +Train: [87] [4900/6250] eta: 0:03:42 lr: 0.000005 grad: 0.1429 (0.1406) loss: 0.8002 (0.8132) time: 0.1475 data: 0.0679 max mem: 9390 +Train: [87] [5000/6250] eta: 0:03:25 lr: 0.000005 grad: 0.1321 (0.1406) loss: 0.8114 (0.8132) time: 0.1598 data: 0.0732 max mem: 9390 +Train: [87] [5100/6250] eta: 0:03:08 lr: 0.000005 grad: 0.1313 (0.1406) loss: 0.8131 (0.8131) time: 0.1292 data: 0.0513 max mem: 9390 +Train: [87] [5200/6250] eta: 0:02:52 lr: 0.000005 grad: 0.1421 (0.1407) loss: 0.8034 (0.8131) time: 0.1780 data: 0.0851 max mem: 9390 +Train: [87] [5300/6250] eta: 0:02:36 lr: 0.000005 grad: 0.1292 (0.1406) loss: 0.8133 (0.8131) time: 0.1673 data: 0.0602 max mem: 9390 +Train: [87] [5400/6250] eta: 0:02:19 lr: 0.000005 grad: 0.1392 (0.1406) loss: 0.8098 (0.8130) time: 0.1670 data: 0.0699 max mem: 9390 +Train: [87] [5500/6250] eta: 0:02:03 lr: 0.000005 grad: 0.1313 (0.1406) loss: 0.8137 (0.8130) time: 0.1374 data: 0.0406 max mem: 9390 +Train: [87] [5600/6250] eta: 0:01:46 lr: 0.000005 grad: 0.1331 (0.1405) loss: 0.8151 (0.8130) time: 0.1581 data: 0.0636 max mem: 9390 +Train: [87] [5700/6250] eta: 0:01:30 lr: 0.000005 grad: 0.1317 (0.1405) loss: 0.8185 (0.8130) time: 0.1733 data: 0.0768 max mem: 9390 +Train: [87] [5800/6250] eta: 0:01:13 lr: 0.000005 grad: 0.1383 (0.1405) loss: 0.8088 (0.8130) time: 0.1525 data: 0.0599 max mem: 9390 +Train: [87] [5900/6250] eta: 0:00:57 lr: 0.000005 grad: 0.1395 (0.1404) loss: 0.8128 (0.8130) time: 0.1538 data: 0.0635 max mem: 9390 +Train: [87] [6000/6250] eta: 0:00:40 lr: 0.000005 grad: 0.1384 (0.1404) loss: 0.8098 (0.8130) time: 0.1514 data: 0.0493 max mem: 9390 +Train: [87] [6100/6250] eta: 0:00:24 lr: 0.000005 grad: 0.1328 (0.1404) loss: 0.8125 (0.8129) time: 0.1759 data: 0.0831 max mem: 9390 +Train: [87] [6200/6250] eta: 0:00:08 lr: 0.000005 grad: 0.1358 (0.1403) loss: 0.8090 (0.8129) time: 0.1836 data: 0.0984 max mem: 9390 +Train: [87] [6249/6250] eta: 0:00:00 lr: 0.000005 grad: 0.1391 (0.1404) loss: 0.8003 (0.8129) time: 0.1543 data: 0.0603 max mem: 9390 +Train: [87] Total time: 0:17:05 (0.1641 s / it) +Averaged stats: lr: 0.000005 grad: 0.1391 (0.1404) loss: 0.8003 (0.8129) +Eval (hcp-train-subset): [87] [ 0/62] eta: 0:02:43 loss: 0.8309 (0.8309) time: 2.6338 data: 2.5452 max mem: 9390 +Eval (hcp-train-subset): [87] [61/62] eta: 0:00:00 loss: 0.8147 (0.8167) time: 0.1407 data: 0.1147 max mem: 9390 +Eval (hcp-train-subset): [87] Total time: 0:00:12 (0.2066 s / it) +Averaged stats (hcp-train-subset): loss: 0.8147 (0.8167) +Eval (hcp-val): [87] [ 0/62] eta: 0:02:51 loss: 0.8282 (0.8282) time: 2.7734 data: 2.6670 max mem: 9390 +Eval (hcp-val): [87] [61/62] eta: 0:00:00 loss: 0.8274 (0.8291) time: 0.1313 data: 0.1046 max mem: 9390 +Eval (hcp-val): [87] Total time: 0:00:13 (0.2098 s / it) +Averaged stats (hcp-val): loss: 0.8274 (0.8291) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +Train: [88] [ 0/6250] eta: 9:20:55 lr: 0.000005 grad: 0.1031 (0.1031) loss: 0.8314 (0.8314) time: 5.3848 data: 5.2092 max mem: 9390 +Train: [88] [ 100/6250] eta: 0:21:18 lr: 0.000005 grad: 0.1572 (0.1805) loss: 0.8244 (0.8158) time: 0.1307 data: 0.0472 max mem: 9390 +Train: [88] [ 200/6250] eta: 0:19:27 lr: 0.000005 grad: 0.1453 (0.1722) loss: 0.8196 (0.8134) time: 0.1400 data: 0.0477 max mem: 9390 +Train: [88] [ 300/6250] eta: 0:19:08 lr: 0.000005 grad: 0.1427 (0.1649) loss: 0.8185 (0.8140) time: 0.1520 data: 0.0085 max mem: 9390 +Train: [88] [ 400/6250] eta: 0:18:50 lr: 0.000005 grad: 0.1394 (0.1608) loss: 0.8113 (0.8147) time: 0.1769 data: 0.0816 max mem: 9390 +Train: [88] [ 500/6250] eta: 0:18:11 lr: 0.000005 grad: 0.1276 (0.1569) loss: 0.8234 (0.8157) time: 0.1514 data: 0.0616 max mem: 9390 +Train: [88] [ 600/6250] eta: 0:17:35 lr: 0.000005 grad: 0.1300 (0.1539) loss: 0.8228 (0.8164) time: 0.1436 data: 0.0398 max mem: 9390 +Train: [88] [ 700/6250] eta: 0:17:09 lr: 0.000005 grad: 0.1387 (0.1516) loss: 0.8153 (0.8164) time: 0.1884 data: 0.0899 max mem: 9390 +Train: [88] [ 800/6250] eta: 0:16:43 lr: 0.000005 grad: 0.1312 (0.1502) loss: 0.8155 (0.8158) time: 0.1362 data: 0.0368 max mem: 9390 +Train: [88] [ 900/6250] eta: 0:16:18 lr: 0.000005 grad: 0.1395 (0.1488) loss: 0.8168 (0.8154) time: 0.1768 data: 0.0966 max mem: 9390 +Train: [88] [1000/6250] eta: 0:15:49 lr: 0.000005 grad: 0.1285 (0.1479) loss: 0.8152 (0.8152) time: 0.1459 data: 0.0618 max mem: 9390 +Train: [88] [1100/6250] eta: 0:15:25 lr: 0.000005 grad: 0.1359 (0.1468) loss: 0.8115 (0.8150) time: 0.1936 data: 0.1082 max mem: 9390 +Train: [88] [1200/6250] eta: 0:14:57 lr: 0.000005 grad: 0.1290 (0.1462) loss: 0.8149 (0.8148) time: 0.1334 data: 0.0457 max mem: 9390 +Train: [88] [1300/6250] eta: 0:14:31 lr: 0.000005 grad: 0.1345 (0.1458) loss: 0.8131 (0.8146) time: 0.1600 data: 0.0677 max mem: 9390 +Train: [88] [1400/6250] eta: 0:14:07 lr: 0.000005 grad: 0.1318 (0.1453) loss: 0.8141 (0.8145) time: 0.1638 data: 0.0747 max mem: 9390 +Train: [88] [1500/6250] eta: 0:13:45 lr: 0.000005 grad: 0.1386 (0.1446) loss: 0.8110 (0.8144) time: 0.1673 data: 0.0816 max mem: 9390 +Train: [88] [1600/6250] eta: 0:13:23 lr: 0.000005 grad: 0.1330 (0.1444) loss: 0.8171 (0.8144) time: 0.1585 data: 0.0683 max mem: 9390 +Train: [88] [1700/6250] eta: 0:13:03 lr: 0.000005 grad: 0.1271 (0.1440) loss: 0.8201 (0.8143) time: 0.1625 data: 0.0794 max mem: 9390 +Train: [88] [1800/6250] eta: 0:12:41 lr: 0.000005 grad: 0.1362 (0.1437) loss: 0.8183 (0.8143) time: 0.1432 data: 0.0469 max mem: 9390 +Train: [88] [1900/6250] eta: 0:12:21 lr: 0.000005 grad: 0.1346 (0.1435) loss: 0.8154 (0.8141) time: 0.1619 data: 0.0691 max mem: 9390 +Train: [88] [2000/6250] eta: 0:12:01 lr: 0.000005 grad: 0.1415 (0.1433) loss: 0.8159 (0.8139) time: 0.1598 data: 0.0745 max mem: 9390 +Train: [88] [2100/6250] eta: 0:11:42 lr: 0.000005 grad: 0.1400 (0.1432) loss: 0.8132 (0.8138) time: 0.1586 data: 0.0722 max mem: 9390 +Train: [88] [2200/6250] eta: 0:11:24 lr: 0.000005 grad: 0.1347 (0.1431) loss: 0.8157 (0.8137) time: 0.1740 data: 0.0819 max mem: 9390 +Train: [88] [2300/6250] eta: 0:11:05 lr: 0.000005 grad: 0.1332 (0.1428) loss: 0.8161 (0.8137) time: 0.1452 data: 0.0602 max mem: 9390 +Train: [88] [2400/6250] eta: 0:10:47 lr: 0.000005 grad: 0.1259 (0.1425) loss: 0.8166 (0.8138) time: 0.1685 data: 0.0795 max mem: 9390 +Train: [88] [2500/6250] eta: 0:10:29 lr: 0.000005 grad: 0.1373 (0.1423) loss: 0.8163 (0.8139) time: 0.1785 data: 0.0913 max mem: 9390 +Train: [88] [2600/6250] eta: 0:10:12 lr: 0.000005 grad: 0.1453 (0.1421) loss: 0.8178 (0.8140) time: 0.1539 data: 0.0714 max mem: 9390 +Train: [88] [2700/6250] eta: 0:09:54 lr: 0.000005 grad: 0.1334 (0.1419) loss: 0.8144 (0.8140) time: 0.1487 data: 0.0548 max mem: 9390 +Train: [88] [2800/6250] eta: 0:09:37 lr: 0.000005 grad: 0.1284 (0.1415) loss: 0.8141 (0.8140) time: 0.1794 data: 0.0904 max mem: 9390 +Train: [88] [2900/6250] eta: 0:09:20 lr: 0.000004 grad: 0.1271 (0.1412) loss: 0.8103 (0.8141) time: 0.1586 data: 0.0748 max mem: 9390 +Train: [88] [3000/6250] eta: 0:09:03 lr: 0.000004 grad: 0.1493 (0.1411) loss: 0.8083 (0.8142) time: 0.1911 data: 0.1031 max mem: 9390 +Train: [88] [3100/6250] eta: 0:08:46 lr: 0.000004 grad: 0.1364 (0.1411) loss: 0.8156 (0.8141) time: 0.1615 data: 0.0744 max mem: 9390 +Train: [88] [3200/6250] eta: 0:08:29 lr: 0.000004 grad: 0.1318 (0.1409) loss: 0.8110 (0.8141) time: 0.1794 data: 0.0911 max mem: 9390 +Train: [88] [3300/6250] eta: 0:08:12 lr: 0.000004 grad: 0.1367 (0.1408) loss: 0.8066 (0.8140) time: 0.1616 data: 0.0711 max mem: 9390 +Train: [88] [3400/6250] eta: 0:07:55 lr: 0.000004 grad: 0.1329 (0.1407) loss: 0.8104 (0.8140) time: 0.1653 data: 0.0827 max mem: 9390 +Train: [88] [3500/6250] eta: 0:07:38 lr: 0.000004 grad: 0.1389 (0.1406) loss: 0.8132 (0.8139) time: 0.1463 data: 0.0633 max mem: 9390 +Train: [88] [3600/6250] eta: 0:07:21 lr: 0.000004 grad: 0.1353 (0.1405) loss: 0.8181 (0.8137) time: 0.1790 data: 0.0933 max mem: 9390 +Train: [88] [3700/6250] eta: 0:07:04 lr: 0.000004 grad: 0.1346 (0.1405) loss: 0.8148 (0.8136) time: 0.1672 data: 0.0832 max mem: 9390 +Train: [88] [3800/6250] eta: 0:06:47 lr: 0.000004 grad: 0.1349 (0.1406) loss: 0.8086 (0.8134) time: 0.1598 data: 0.0756 max mem: 9390 +Train: [88] [3900/6250] eta: 0:06:30 lr: 0.000004 grad: 0.1344 (0.1405) loss: 0.8167 (0.8134) time: 0.1639 data: 0.0789 max mem: 9390 +Train: [88] [4000/6250] eta: 0:06:13 lr: 0.000004 grad: 0.1319 (0.1404) loss: 0.8167 (0.8133) time: 0.1789 data: 0.0937 max mem: 9390 +Train: [88] [4100/6250] eta: 0:05:56 lr: 0.000004 grad: 0.1426 (0.1403) loss: 0.8098 (0.8133) time: 0.1356 data: 0.0481 max mem: 9390 +Train: [88] [4200/6250] eta: 0:05:39 lr: 0.000004 grad: 0.1372 (0.1404) loss: 0.8123 (0.8132) time: 0.1699 data: 0.0825 max mem: 9390 +Train: [88] [4300/6250] eta: 0:05:22 lr: 0.000004 grad: 0.1410 (0.1403) loss: 0.8129 (0.8132) time: 0.1556 data: 0.0692 max mem: 9390 +Train: [88] [4400/6250] eta: 0:05:05 lr: 0.000004 grad: 0.1366 (0.1403) loss: 0.8127 (0.8131) time: 0.1520 data: 0.0693 max mem: 9390 +Train: [88] [4500/6250] eta: 0:04:49 lr: 0.000004 grad: 0.1319 (0.1402) loss: 0.8167 (0.8131) time: 0.1361 data: 0.0559 max mem: 9390 +Train: [88] [4600/6250] eta: 0:04:32 lr: 0.000004 grad: 0.1354 (0.1402) loss: 0.8133 (0.8131) time: 0.1593 data: 0.0731 max mem: 9390 +Train: [88] [4700/6250] eta: 0:04:16 lr: 0.000004 grad: 0.1357 (0.1401) loss: 0.8096 (0.8131) time: 0.1728 data: 0.0870 max mem: 9390 +Train: [88] [4800/6250] eta: 0:03:59 lr: 0.000004 grad: 0.1315 (0.1401) loss: 0.8151 (0.8130) time: 0.1591 data: 0.0781 max mem: 9390 +Train: [88] [4900/6250] eta: 0:03:43 lr: 0.000004 grad: 0.1311 (0.1400) loss: 0.8120 (0.8130) time: 0.1704 data: 0.0787 max mem: 9390 +Train: [88] [5000/6250] eta: 0:03:26 lr: 0.000004 grad: 0.1294 (0.1400) loss: 0.8075 (0.8130) time: 0.1491 data: 0.0655 max mem: 9390 +Train: [88] [5100/6250] eta: 0:03:09 lr: 0.000004 grad: 0.1334 (0.1399) loss: 0.8149 (0.8129) time: 0.1559 data: 0.0698 max mem: 9390 +Train: [88] [5200/6250] eta: 0:02:53 lr: 0.000004 grad: 0.1379 (0.1398) loss: 0.8109 (0.8129) time: 0.1552 data: 0.0646 max mem: 9390 +Train: [88] [5300/6250] eta: 0:02:36 lr: 0.000004 grad: 0.1364 (0.1397) loss: 0.8100 (0.8129) time: 0.1654 data: 0.0749 max mem: 9390 +Train: [88] [5400/6250] eta: 0:02:20 lr: 0.000004 grad: 0.1363 (0.1397) loss: 0.8141 (0.8129) time: 0.1635 data: 0.0783 max mem: 9390 +Train: [88] [5500/6250] eta: 0:02:03 lr: 0.000004 grad: 0.1415 (0.1397) loss: 0.8079 (0.8129) time: 0.1601 data: 0.0745 max mem: 9390 +Train: [88] [5600/6250] eta: 0:01:47 lr: 0.000004 grad: 0.1453 (0.1397) loss: 0.8102 (0.8129) time: 0.1428 data: 0.0540 max mem: 9390 +Train: [88] [5700/6250] eta: 0:01:30 lr: 0.000004 grad: 0.1380 (0.1397) loss: 0.8148 (0.8128) time: 0.1445 data: 0.0570 max mem: 9390 +Train: [88] [5800/6250] eta: 0:01:14 lr: 0.000004 grad: 0.1360 (0.1398) loss: 0.8049 (0.8127) time: 0.1682 data: 0.0788 max mem: 9390 +Train: [88] [5900/6250] eta: 0:00:57 lr: 0.000004 grad: 0.1365 (0.1398) loss: 0.8061 (0.8126) time: 0.1763 data: 0.0871 max mem: 9390 +Train: [88] [6000/6250] eta: 0:00:41 lr: 0.000004 grad: 0.1277 (0.1398) loss: 0.8119 (0.8126) time: 0.1528 data: 0.0671 max mem: 9390 +Train: [88] [6100/6250] eta: 0:00:24 lr: 0.000004 grad: 0.1366 (0.1397) loss: 0.8100 (0.8126) time: 0.1645 data: 0.0768 max mem: 9390 +Train: [88] [6200/6250] eta: 0:00:08 lr: 0.000004 grad: 0.1428 (0.1397) loss: 0.8065 (0.8126) time: 0.2327 data: 0.0941 max mem: 9390 +Train: [88] [6249/6250] eta: 0:00:00 lr: 0.000004 grad: 0.1338 (0.1397) loss: 0.8089 (0.8126) time: 0.1699 data: 0.0877 max mem: 9390 +Train: [88] Total time: 0:17:17 (0.1660 s / it) +Averaged stats: lr: 0.000004 grad: 0.1338 (0.1397) loss: 0.8089 (0.8126) +Eval (hcp-train-subset): [88] [ 0/62] eta: 0:03:02 loss: 0.8291 (0.8291) time: 2.9485 data: 2.8899 max mem: 9390 +Eval (hcp-train-subset): [88] [61/62] eta: 0:00:00 loss: 0.8137 (0.8170) time: 0.1287 data: 0.1036 max mem: 9390 +Eval (hcp-train-subset): [88] Total time: 0:00:12 (0.2088 s / it) +Averaged stats (hcp-train-subset): loss: 0.8137 (0.8170) +Eval (hcp-val): [88] [ 0/62] eta: 0:04:19 loss: 0.8259 (0.8259) time: 4.1902 data: 4.1609 max mem: 9390 +Eval (hcp-val): [88] [61/62] eta: 0:00:00 loss: 0.8275 (0.8291) time: 0.1343 data: 0.1084 max mem: 9390 +Eval (hcp-val): [88] Total time: 0:00:13 (0.2118 s / it) +Averaged stats (hcp-val): loss: 0.8275 (0.8291) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +Train: [89] [ 0/6250] eta: 6:45:31 lr: 0.000004 grad: 0.0825 (0.0825) loss: 0.8741 (0.8741) time: 3.8930 data: 3.6707 max mem: 9390 +Train: [89] [ 100/6250] eta: 0:21:29 lr: 0.000004 grad: 0.1465 (0.1757) loss: 0.8263 (0.8305) time: 0.1700 data: 0.0870 max mem: 9390 +Train: [89] [ 200/6250] eta: 0:19:12 lr: 0.000004 grad: 0.1425 (0.1643) loss: 0.8263 (0.8252) time: 0.1623 data: 0.0684 max mem: 9390 +Train: [89] [ 300/6250] eta: 0:18:10 lr: 0.000004 grad: 0.1321 (0.1557) loss: 0.8208 (0.8239) time: 0.1686 data: 0.0730 max mem: 9390 +Train: [89] [ 400/6250] eta: 0:17:34 lr: 0.000004 grad: 0.1354 (0.1530) loss: 0.8181 (0.8220) time: 0.1755 data: 0.0670 max mem: 9390 +Train: [89] [ 500/6250] eta: 0:17:27 lr: 0.000004 grad: 0.1375 (0.1516) loss: 0.8133 (0.8207) time: 0.2133 data: 0.0848 max mem: 9390 +Train: [89] [ 600/6250] eta: 0:17:20 lr: 0.000004 grad: 0.1448 (0.1504) loss: 0.8131 (0.8197) time: 0.1769 data: 0.0762 max mem: 9390 +Train: [89] [ 700/6250] eta: 0:16:54 lr: 0.000004 grad: 0.1350 (0.1492) loss: 0.8113 (0.8188) time: 0.1904 data: 0.0970 max mem: 9390 +Train: [89] [ 800/6250] eta: 0:16:30 lr: 0.000004 grad: 0.1325 (0.1480) loss: 0.8118 (0.8177) time: 0.1983 data: 0.1039 max mem: 9390 +Train: [89] [ 900/6250] eta: 0:16:04 lr: 0.000004 grad: 0.1352 (0.1470) loss: 0.8114 (0.8171) time: 0.1687 data: 0.0717 max mem: 9390 +Train: [89] [1000/6250] eta: 0:15:37 lr: 0.000004 grad: 0.1317 (0.1467) loss: 0.8145 (0.8164) time: 0.1732 data: 0.0805 max mem: 9390 +Train: [89] [1100/6250] eta: 0:15:15 lr: 0.000004 grad: 0.1279 (0.1460) loss: 0.8169 (0.8163) time: 0.1626 data: 0.0776 max mem: 9390 +Train: [89] [1200/6250] eta: 0:14:54 lr: 0.000004 grad: 0.1315 (0.1452) loss: 0.8150 (0.8160) time: 0.1893 data: 0.1064 max mem: 9390 +Train: [89] [1300/6250] eta: 0:14:33 lr: 0.000004 grad: 0.1357 (0.1446) loss: 0.8075 (0.8157) time: 0.1845 data: 0.1040 max mem: 9390 +Train: [89] [1400/6250] eta: 0:14:08 lr: 0.000004 grad: 0.1309 (0.1440) loss: 0.8131 (0.8156) time: 0.1703 data: 0.0810 max mem: 9390 +Train: [89] [1500/6250] eta: 0:13:48 lr: 0.000004 grad: 0.1363 (0.1433) loss: 0.8195 (0.8154) time: 0.1541 data: 0.0681 max mem: 9390 +Train: [89] [1600/6250] eta: 0:13:26 lr: 0.000004 grad: 0.1336 (0.1430) loss: 0.8123 (0.8153) time: 0.1642 data: 0.0743 max mem: 9390 +Train: [89] [1700/6250] eta: 0:13:07 lr: 0.000004 grad: 0.1343 (0.1425) loss: 0.8180 (0.8153) time: 0.1417 data: 0.0479 max mem: 9390 +Train: [89] [1800/6250] eta: 0:12:47 lr: 0.000004 grad: 0.1411 (0.1420) loss: 0.8091 (0.8151) time: 0.1545 data: 0.0647 max mem: 9390 +Train: [89] [1900/6250] eta: 0:12:27 lr: 0.000004 grad: 0.1353 (0.1415) loss: 0.8132 (0.8151) time: 0.1886 data: 0.1036 max mem: 9390 +Train: [89] [2000/6250] eta: 0:12:08 lr: 0.000004 grad: 0.1263 (0.1412) loss: 0.8137 (0.8150) time: 0.1715 data: 0.0851 max mem: 9390 +Train: [89] [2100/6250] eta: 0:11:49 lr: 0.000004 grad: 0.1276 (0.1407) loss: 0.8108 (0.8150) time: 0.1613 data: 0.0753 max mem: 9390 +Train: [89] [2200/6250] eta: 0:11:30 lr: 0.000004 grad: 0.1257 (0.1404) loss: 0.8073 (0.8148) time: 0.1438 data: 0.0513 max mem: 9390 +Train: [89] [2300/6250] eta: 0:11:11 lr: 0.000004 grad: 0.1338 (0.1401) loss: 0.8231 (0.8148) time: 0.1536 data: 0.0685 max mem: 9390 +Train: [89] [2400/6250] eta: 0:10:53 lr: 0.000004 grad: 0.1409 (0.1401) loss: 0.8055 (0.8147) time: 0.1726 data: 0.0913 max mem: 9390 +Train: [89] [2500/6250] eta: 0:10:35 lr: 0.000004 grad: 0.1270 (0.1400) loss: 0.8101 (0.8146) time: 0.1383 data: 0.0429 max mem: 9390 +Train: [89] [2600/6250] eta: 0:10:17 lr: 0.000004 grad: 0.1380 (0.1400) loss: 0.8121 (0.8146) time: 0.1650 data: 0.0744 max mem: 9390 +Train: [89] [2700/6250] eta: 0:10:00 lr: 0.000004 grad: 0.1250 (0.1397) loss: 0.8106 (0.8146) time: 0.1702 data: 0.0853 max mem: 9390 +Train: [89] [2800/6250] eta: 0:09:42 lr: 0.000004 grad: 0.1349 (0.1397) loss: 0.8071 (0.8145) time: 0.1542 data: 0.0613 max mem: 9390 +Train: [89] [2900/6250] eta: 0:09:24 lr: 0.000004 grad: 0.1219 (0.1392) loss: 0.8214 (0.8146) time: 0.1549 data: 0.0659 max mem: 9390 +Train: [89] [3000/6250] eta: 0:09:07 lr: 0.000004 grad: 0.1204 (0.1389) loss: 0.8100 (0.8146) time: 0.1787 data: 0.0910 max mem: 9390 +Train: [89] [3100/6250] eta: 0:08:49 lr: 0.000004 grad: 0.1370 (0.1387) loss: 0.8181 (0.8148) time: 0.1800 data: 0.0912 max mem: 9390 +Train: [89] [3200/6250] eta: 0:08:32 lr: 0.000004 grad: 0.1275 (0.1384) loss: 0.8096 (0.8148) time: 0.1972 data: 0.1143 max mem: 9390 +Train: [89] [3300/6250] eta: 0:08:15 lr: 0.000004 grad: 0.1192 (0.1382) loss: 0.8159 (0.8148) time: 0.1760 data: 0.0959 max mem: 9390 +Train: [89] [3400/6250] eta: 0:07:58 lr: 0.000004 grad: 0.1266 (0.1380) loss: 0.8094 (0.8148) time: 0.1546 data: 0.0641 max mem: 9390 +Train: [89] [3500/6250] eta: 0:07:41 lr: 0.000004 grad: 0.1281 (0.1377) loss: 0.8160 (0.8149) time: 0.1640 data: 0.0836 max mem: 9390 +Train: [89] [3600/6250] eta: 0:07:24 lr: 0.000004 grad: 0.1270 (0.1376) loss: 0.8151 (0.8149) time: 0.1784 data: 0.1005 max mem: 9390 +Train: [89] [3700/6250] eta: 0:07:08 lr: 0.000004 grad: 0.1257 (0.1374) loss: 0.8154 (0.8149) time: 0.1754 data: 0.0956 max mem: 9390 +Train: [89] [3800/6250] eta: 0:06:50 lr: 0.000004 grad: 0.1295 (0.1373) loss: 0.8121 (0.8149) time: 0.1353 data: 0.0628 max mem: 9390 +Train: [89] [3900/6250] eta: 0:06:34 lr: 0.000004 grad: 0.1376 (0.1373) loss: 0.8089 (0.8148) time: 0.1477 data: 0.0659 max mem: 9390 +Train: [89] [4000/6250] eta: 0:06:16 lr: 0.000004 grad: 0.1232 (0.1372) loss: 0.8163 (0.8148) time: 0.1997 data: 0.1101 max mem: 9390 +Train: [89] [4100/6250] eta: 0:05:59 lr: 0.000004 grad: 0.1354 (0.1372) loss: 0.8157 (0.8148) time: 0.1753 data: 0.0845 max mem: 9390 +Train: [89] [4200/6250] eta: 0:05:43 lr: 0.000004 grad: 0.1424 (0.1372) loss: 0.8097 (0.8147) time: 0.1593 data: 0.0619 max mem: 9390 +Train: [89] [4300/6250] eta: 0:05:26 lr: 0.000004 grad: 0.1330 (0.1372) loss: 0.8140 (0.8147) time: 0.1578 data: 0.0685 max mem: 9390 +Train: [89] [4400/6250] eta: 0:05:09 lr: 0.000004 grad: 0.1336 (0.1371) loss: 0.8104 (0.8146) time: 0.1524 data: 0.0519 max mem: 9390 +Train: [89] [4500/6250] eta: 0:04:52 lr: 0.000004 grad: 0.1256 (0.1371) loss: 0.8159 (0.8146) time: 0.1506 data: 0.0551 max mem: 9390 +Train: [89] [4600/6250] eta: 0:04:35 lr: 0.000004 grad: 0.1322 (0.1371) loss: 0.8142 (0.8146) time: 0.1441 data: 0.0414 max mem: 9390 +Train: [89] [4700/6250] eta: 0:04:18 lr: 0.000004 grad: 0.1368 (0.1372) loss: 0.8104 (0.8145) time: 0.1811 data: 0.0957 max mem: 9390 +Train: [89] [4800/6250] eta: 0:04:02 lr: 0.000004 grad: 0.1290 (0.1373) loss: 0.8146 (0.8145) time: 0.2022 data: 0.1091 max mem: 9390 +Train: [89] [4900/6250] eta: 0:03:45 lr: 0.000004 grad: 0.1298 (0.1373) loss: 0.8142 (0.8144) time: 0.1579 data: 0.0680 max mem: 9390 +Train: [89] [5000/6250] eta: 0:03:28 lr: 0.000004 grad: 0.1304 (0.1373) loss: 0.8186 (0.8145) time: 0.1974 data: 0.1094 max mem: 9390 +Train: [89] [5100/6250] eta: 0:03:12 lr: 0.000004 grad: 0.1401 (0.1373) loss: 0.8144 (0.8145) time: 0.1738 data: 0.0870 max mem: 9390 +Train: [89] [5200/6250] eta: 0:02:55 lr: 0.000003 grad: 0.1341 (0.1373) loss: 0.8216 (0.8146) time: 0.1900 data: 0.0955 max mem: 9390 +Train: [89] [5300/6250] eta: 0:02:38 lr: 0.000003 grad: 0.1386 (0.1373) loss: 0.8119 (0.8146) time: 0.1441 data: 0.0550 max mem: 9390 +Train: [89] [5400/6250] eta: 0:02:22 lr: 0.000003 grad: 0.1368 (0.1373) loss: 0.8127 (0.8146) time: 0.1610 data: 0.0692 max mem: 9390 +Train: [89] [5500/6250] eta: 0:02:05 lr: 0.000003 grad: 0.1318 (0.1372) loss: 0.8119 (0.8146) time: 0.1738 data: 0.0727 max mem: 9390 +Train: [89] [5600/6250] eta: 0:01:48 lr: 0.000003 grad: 0.1291 (0.1372) loss: 0.8172 (0.8147) time: 0.1696 data: 0.0834 max mem: 9390 +Train: [89] [5700/6250] eta: 0:01:31 lr: 0.000003 grad: 0.1275 (0.1372) loss: 0.8180 (0.8147) time: 0.1508 data: 0.0582 max mem: 9390 +Train: [89] [5800/6250] eta: 0:01:15 lr: 0.000003 grad: 0.1389 (0.1372) loss: 0.8162 (0.8147) time: 0.1536 data: 0.0617 max mem: 9390 +Train: [89] [5900/6250] eta: 0:00:58 lr: 0.000003 grad: 0.1387 (0.1372) loss: 0.8129 (0.8147) time: 0.1840 data: 0.0959 max mem: 9390 +Train: [89] [6000/6250] eta: 0:00:41 lr: 0.000003 grad: 0.1323 (0.1371) loss: 0.8174 (0.8148) time: 0.1545 data: 0.0623 max mem: 9390 +Train: [89] [6100/6250] eta: 0:00:24 lr: 0.000003 grad: 0.1287 (0.1371) loss: 0.8154 (0.8148) time: 0.1301 data: 0.0455 max mem: 9390 +Train: [89] [6200/6250] eta: 0:00:08 lr: 0.000003 grad: 0.1328 (0.1370) loss: 0.8204 (0.8148) time: 0.1574 data: 0.0614 max mem: 9390 +Train: [89] [6249/6250] eta: 0:00:00 lr: 0.000003 grad: 0.1271 (0.1370) loss: 0.8193 (0.8148) time: 0.1570 data: 0.0649 max mem: 9390 +Train: [89] Total time: 0:17:26 (0.1674 s / it) +Averaged stats: lr: 0.000003 grad: 0.1271 (0.1370) loss: 0.8193 (0.8148) +Eval (hcp-train-subset): [89] [ 0/62] eta: 0:02:53 loss: 0.8264 (0.8264) time: 2.7922 data: 2.7517 max mem: 9390 +Eval (hcp-train-subset): [89] [61/62] eta: 0:00:00 loss: 0.8135 (0.8174) time: 0.1228 data: 0.0977 max mem: 9390 +Eval (hcp-train-subset): [89] Total time: 0:00:13 (0.2155 s / it) +Averaged stats (hcp-train-subset): loss: 0.8135 (0.8174) +Making plots (hcp-train-subset): example=16 +Eval (hcp-val): [89] [ 0/62] eta: 0:02:55 loss: 0.8276 (0.8276) time: 2.8277 data: 2.7804 max mem: 9390 +Eval (hcp-val): [89] [61/62] eta: 0:00:00 loss: 0.8276 (0.8286) time: 0.1739 data: 0.1477 max mem: 9390 +Eval (hcp-val): [89] Total time: 0:00:14 (0.2277 s / it) +Averaged stats (hcp-val): loss: 0.8276 (0.8286) +Making plots (hcp-val): example=45 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +Train: [90] [ 0/6250] eta: 7:59:42 lr: 0.000003 grad: 0.9005 (0.9005) loss: 0.8481 (0.8481) time: 4.6051 data: 4.3809 max mem: 9390 +Train: [90] [ 100/6250] eta: 0:22:12 lr: 0.000003 grad: 0.1604 (0.2057) loss: 0.8140 (0.8112) time: 0.1992 data: 0.1157 max mem: 9390 +Train: [90] [ 200/6250] eta: 0:19:09 lr: 0.000003 grad: 0.1417 (0.1796) loss: 0.8203 (0.8132) time: 0.1641 data: 0.0730 max mem: 9390 +Train: [90] [ 300/6250] eta: 0:18:09 lr: 0.000003 grad: 0.1381 (0.1674) loss: 0.8191 (0.8142) time: 0.1685 data: 0.0746 max mem: 9390 +Train: [90] [ 400/6250] eta: 0:17:54 lr: 0.000003 grad: 0.1374 (0.1607) loss: 0.8167 (0.8146) time: 0.2360 data: 0.1309 max mem: 9390 +Train: [90] [ 500/6250] eta: 0:18:20 lr: 0.000003 grad: 0.1282 (0.1561) loss: 0.8183 (0.8151) time: 0.2287 data: 0.1211 max mem: 9390 +Train: [90] [ 600/6250] eta: 0:17:52 lr: 0.000003 grad: 0.1343 (0.1536) loss: 0.8193 (0.8155) time: 0.1731 data: 0.0746 max mem: 9390 +Train: [90] [ 700/6250] eta: 0:17:20 lr: 0.000003 grad: 0.1421 (0.1521) loss: 0.8091 (0.8153) time: 0.1518 data: 0.0597 max mem: 9390 +Train: [90] [ 800/6250] eta: 0:16:50 lr: 0.000003 grad: 0.1296 (0.1506) loss: 0.8168 (0.8154) time: 0.1336 data: 0.0438 max mem: 9390 +Train: [90] [ 900/6250] eta: 0:16:23 lr: 0.000003 grad: 0.1426 (0.1501) loss: 0.8114 (0.8151) time: 0.1689 data: 0.0789 max mem: 9390 +Train: [90] [1000/6250] eta: 0:15:56 lr: 0.000003 grad: 0.1369 (0.1497) loss: 0.8097 (0.8149) time: 0.1620 data: 0.0796 max mem: 9390 +Train: [90] [1100/6250] eta: 0:15:28 lr: 0.000003 grad: 0.1395 (0.1491) loss: 0.8119 (0.8147) time: 0.1587 data: 0.0682 max mem: 9390 +Train: [90] [1200/6250] eta: 0:15:04 lr: 0.000003 grad: 0.1406 (0.1483) loss: 0.8079 (0.8144) time: 0.1747 data: 0.0821 max mem: 9390 +Train: [90] [1300/6250] eta: 0:14:40 lr: 0.000003 grad: 0.1378 (0.1481) loss: 0.8016 (0.8138) time: 0.1650 data: 0.0739 max mem: 9390 +Train: [90] [1400/6250] eta: 0:14:16 lr: 0.000003 grad: 0.1377 (0.1478) loss: 0.8150 (0.8135) time: 0.1674 data: 0.0884 max mem: 9390 +Train: [90] [1500/6250] eta: 0:13:53 lr: 0.000003 grad: 0.1418 (0.1475) loss: 0.8109 (0.8134) time: 0.1571 data: 0.0692 max mem: 9390 +Train: [90] [1600/6250] eta: 0:13:30 lr: 0.000003 grad: 0.1423 (0.1470) loss: 0.8144 (0.8134) time: 0.1638 data: 0.0825 max mem: 9390 +Train: [90] [1700/6250] eta: 0:13:09 lr: 0.000003 grad: 0.1425 (0.1469) loss: 0.8091 (0.8134) time: 0.1389 data: 0.0535 max mem: 9390 +Train: [90] [1800/6250] eta: 0:12:48 lr: 0.000003 grad: 0.1404 (0.1466) loss: 0.8129 (0.8133) time: 0.1643 data: 0.0702 max mem: 9390 +Train: [90] [1900/6250] eta: 0:12:28 lr: 0.000003 grad: 0.1334 (0.1464) loss: 0.8081 (0.8134) time: 0.1467 data: 0.0593 max mem: 9390 +Train: [90] [2000/6250] eta: 0:12:09 lr: 0.000003 grad: 0.1426 (0.1464) loss: 0.8209 (0.8134) time: 0.1560 data: 0.0699 max mem: 9390 +Train: [90] [2100/6250] eta: 0:11:50 lr: 0.000003 grad: 0.1435 (0.1461) loss: 0.8145 (0.8133) time: 0.1690 data: 0.0833 max mem: 9390 +Train: [90] [2200/6250] eta: 0:11:31 lr: 0.000003 grad: 0.1354 (0.1459) loss: 0.8158 (0.8133) time: 0.1664 data: 0.0779 max mem: 9390 +Train: [90] [2300/6250] eta: 0:11:13 lr: 0.000003 grad: 0.1398 (0.1456) loss: 0.8069 (0.8133) time: 0.1808 data: 0.0988 max mem: 9390 +Train: [90] [2400/6250] eta: 0:10:55 lr: 0.000003 grad: 0.1390 (0.1453) loss: 0.8131 (0.8132) time: 0.1733 data: 0.0906 max mem: 9390 +Train: [90] [2500/6250] eta: 0:10:37 lr: 0.000003 grad: 0.1453 (0.1451) loss: 0.8079 (0.8131) time: 0.1744 data: 0.0881 max mem: 9390 +Train: [90] [2600/6250] eta: 0:10:19 lr: 0.000003 grad: 0.1380 (0.1450) loss: 0.8077 (0.8130) time: 0.1806 data: 0.0835 max mem: 9390 +Train: [90] [2700/6250] eta: 0:10:01 lr: 0.000003 grad: 0.1376 (0.1449) loss: 0.8085 (0.8129) time: 0.1632 data: 0.0770 max mem: 9390 +Train: [90] [2800/6250] eta: 0:09:44 lr: 0.000003 grad: 0.1275 (0.1448) loss: 0.8167 (0.8129) time: 0.1831 data: 0.0967 max mem: 9390 +Train: [90] [2900/6250] eta: 0:09:26 lr: 0.000003 grad: 0.1360 (0.1447) loss: 0.8120 (0.8129) time: 0.1837 data: 0.0937 max mem: 9390 +Train: [90] [3000/6250] eta: 0:09:08 lr: 0.000003 grad: 0.1406 (0.1446) loss: 0.8111 (0.8128) time: 0.1531 data: 0.0678 max mem: 9390 +Train: [90] [3100/6250] eta: 0:08:51 lr: 0.000003 grad: 0.1539 (0.1446) loss: 0.8154 (0.8129) time: 0.1673 data: 0.0858 max mem: 9390 +Train: [90] [3200/6250] eta: 0:08:34 lr: 0.000003 grad: 0.1347 (0.1444) loss: 0.8090 (0.8129) time: 0.1570 data: 0.0764 max mem: 9390 +Train: [90] [3300/6250] eta: 0:08:16 lr: 0.000003 grad: 0.1314 (0.1443) loss: 0.8174 (0.8130) time: 0.1461 data: 0.0497 max mem: 9390 +Train: [90] [3400/6250] eta: 0:07:59 lr: 0.000003 grad: 0.1385 (0.1440) loss: 0.8050 (0.8130) time: 0.1721 data: 0.0920 max mem: 9390 +Train: [90] [3500/6250] eta: 0:07:42 lr: 0.000003 grad: 0.1413 (0.1440) loss: 0.8116 (0.8130) time: 0.1768 data: 0.0895 max mem: 9390 +Train: [90] [3600/6250] eta: 0:07:25 lr: 0.000003 grad: 0.1375 (0.1439) loss: 0.8138 (0.8130) time: 0.1471 data: 0.0628 max mem: 9390 +Train: [90] [3700/6250] eta: 0:07:08 lr: 0.000003 grad: 0.1305 (0.1438) loss: 0.8186 (0.8130) time: 0.1707 data: 0.0824 max mem: 9390 +Train: [90] [3800/6250] eta: 0:06:51 lr: 0.000003 grad: 0.1381 (0.1436) loss: 0.8112 (0.8130) time: 0.1602 data: 0.0712 max mem: 9390 +Train: [90] [3900/6250] eta: 0:06:34 lr: 0.000003 grad: 0.1388 (0.1435) loss: 0.8164 (0.8131) time: 0.1765 data: 0.0894 max mem: 9390 +Train: [90] [4000/6250] eta: 0:06:17 lr: 0.000003 grad: 0.1318 (0.1433) loss: 0.8183 (0.8131) time: 0.1844 data: 0.0982 max mem: 9390 +Train: [90] [4100/6250] eta: 0:06:00 lr: 0.000003 grad: 0.1267 (0.1432) loss: 0.8187 (0.8132) time: 0.2101 data: 0.1262 max mem: 9390 +Train: [90] [4200/6250] eta: 0:05:43 lr: 0.000003 grad: 0.1300 (0.1431) loss: 0.8213 (0.8133) time: 0.1767 data: 0.0848 max mem: 9390 +Train: [90] [4300/6250] eta: 0:05:26 lr: 0.000003 grad: 0.1342 (0.1430) loss: 0.8141 (0.8133) time: 0.1512 data: 0.0609 max mem: 9390 +Train: [90] [4400/6250] eta: 0:05:09 lr: 0.000003 grad: 0.1303 (0.1428) loss: 0.8172 (0.8133) time: 0.1874 data: 0.1028 max mem: 9390 +Train: [90] [4500/6250] eta: 0:04:52 lr: 0.000003 grad: 0.1367 (0.1428) loss: 0.8166 (0.8134) time: 0.1667 data: 0.0779 max mem: 9390 +Train: [90] [4600/6250] eta: 0:04:35 lr: 0.000003 grad: 0.1365 (0.1428) loss: 0.8117 (0.8133) time: 0.1447 data: 0.0564 max mem: 9390 +Train: [90] [4700/6250] eta: 0:04:18 lr: 0.000003 grad: 0.1356 (0.1428) loss: 0.8174 (0.8133) time: 0.1560 data: 0.0747 max mem: 9390 +Train: [90] [4800/6250] eta: 0:04:01 lr: 0.000003 grad: 0.1432 (0.1428) loss: 0.8168 (0.8134) time: 0.1645 data: 0.0773 max mem: 9390 +Train: [90] [4900/6250] eta: 0:03:45 lr: 0.000003 grad: 0.1415 (0.1428) loss: 0.8163 (0.8134) time: 0.1688 data: 0.0810 max mem: 9390 +Train: [90] [5000/6250] eta: 0:03:28 lr: 0.000003 grad: 0.1345 (0.1427) loss: 0.8153 (0.8134) time: 0.1514 data: 0.0606 max mem: 9390 +Train: [90] [5100/6250] eta: 0:03:11 lr: 0.000003 grad: 0.1334 (0.1426) loss: 0.8125 (0.8134) time: 0.1605 data: 0.0730 max mem: 9390 +Train: [90] [5200/6250] eta: 0:02:55 lr: 0.000003 grad: 0.1383 (0.1425) loss: 0.8056 (0.8133) time: 0.1576 data: 0.0699 max mem: 9390 +Train: [90] [5300/6250] eta: 0:02:38 lr: 0.000003 grad: 0.1304 (0.1426) loss: 0.8117 (0.8133) time: 0.1680 data: 0.0851 max mem: 9390 +Train: [90] [5400/6250] eta: 0:02:21 lr: 0.000003 grad: 0.1258 (0.1426) loss: 0.8143 (0.8132) time: 0.1622 data: 0.0769 max mem: 9390 +Train: [90] [5500/6250] eta: 0:02:05 lr: 0.000003 grad: 0.1372 (0.1426) loss: 0.8067 (0.8131) time: 0.1902 data: 0.1001 max mem: 9390 +Train: [90] [5600/6250] eta: 0:01:48 lr: 0.000003 grad: 0.1404 (0.1426) loss: 0.8079 (0.8131) time: 0.1798 data: 0.0953 max mem: 9390 +Train: [90] [5700/6250] eta: 0:01:31 lr: 0.000003 grad: 0.1444 (0.1426) loss: 0.8125 (0.8130) time: 0.1909 data: 0.1053 max mem: 9390 +Train: [90] [5800/6250] eta: 0:01:14 lr: 0.000003 grad: 0.1366 (0.1426) loss: 0.8071 (0.8130) time: 0.1479 data: 0.0615 max mem: 9390 +Train: [90] [5900/6250] eta: 0:00:58 lr: 0.000003 grad: 0.1465 (0.1426) loss: 0.8156 (0.8130) time: 0.1534 data: 0.0658 max mem: 9390 +Train: [90] [6000/6250] eta: 0:00:41 lr: 0.000003 grad: 0.1443 (0.1427) loss: 0.8114 (0.8129) time: 0.1415 data: 0.0535 max mem: 9390 +Train: [90] [6100/6250] eta: 0:00:24 lr: 0.000003 grad: 0.1485 (0.1427) loss: 0.8132 (0.8129) time: 0.1497 data: 0.0653 max mem: 9390 +Train: [90] [6200/6250] eta: 0:00:08 lr: 0.000003 grad: 0.1371 (0.1428) loss: 0.8109 (0.8129) time: 0.1533 data: 0.0706 max mem: 9390 +Train: [90] [6249/6250] eta: 0:00:00 lr: 0.000003 grad: 0.1369 (0.1428) loss: 0.8149 (0.8129) time: 0.1476 data: 0.0560 max mem: 9390 +Train: [90] Total time: 0:17:24 (0.1672 s / it) +Averaged stats: lr: 0.000003 grad: 0.1369 (0.1428) loss: 0.8149 (0.8129) +Eval (hcp-train-subset): [90] [ 0/62] eta: 0:04:24 loss: 0.8270 (0.8270) time: 4.2663 data: 4.2265 max mem: 9390 +Eval (hcp-train-subset): [90] [61/62] eta: 0:00:00 loss: 0.8149 (0.8166) time: 0.1308 data: 0.1039 max mem: 9390 +Eval (hcp-train-subset): [90] Total time: 0:00:13 (0.2141 s / it) +Averaged stats (hcp-train-subset): loss: 0.8149 (0.8166) +Eval (hcp-val): [90] [ 0/62] eta: 0:03:53 loss: 0.8256 (0.8256) time: 3.7698 data: 3.7072 max mem: 9390 +Eval (hcp-val): [90] [61/62] eta: 0:00:00 loss: 0.8282 (0.8283) time: 0.1283 data: 0.1033 max mem: 9390 +Eval (hcp-val): [90] Total time: 0:00:13 (0.2107 s / it) +Averaged stats (hcp-val): loss: 0.8282 (0.8283) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +Train: [91] [ 0/6250] eta: 10:23:15 lr: 0.000003 grad: 0.1415 (0.1415) loss: 0.8416 (0.8416) time: 5.9832 data: 5.8951 max mem: 9390 +Train: [91] [ 100/6250] eta: 0:21:37 lr: 0.000003 grad: 0.1774 (0.2040) loss: 0.8112 (0.8160) time: 0.1552 data: 0.0707 max mem: 9390 +Train: [91] [ 200/6250] eta: 0:18:52 lr: 0.000003 grad: 0.1383 (0.1844) loss: 0.8059 (0.8158) time: 0.1682 data: 0.0777 max mem: 9390 +Train: [91] [ 300/6250] eta: 0:18:04 lr: 0.000003 grad: 0.1654 (0.1813) loss: 0.8157 (0.8142) time: 0.1738 data: 0.0843 max mem: 9390 +Train: [91] [ 400/6250] eta: 0:17:58 lr: 0.000003 grad: 0.1498 (0.1779) loss: 0.8087 (0.8136) time: 0.2177 data: 0.1006 max mem: 9390 +Train: [91] [ 500/6250] eta: 0:18:19 lr: 0.000003 grad: 0.1540 (0.1730) loss: 0.8119 (0.8129) time: 0.2150 data: 0.1039 max mem: 9390 +Train: [91] [ 600/6250] eta: 0:17:52 lr: 0.000003 grad: 0.1460 (0.1697) loss: 0.8174 (0.8126) time: 0.1822 data: 0.0846 max mem: 9390 +Train: [91] [ 700/6250] eta: 0:17:25 lr: 0.000003 grad: 0.1554 (0.1674) loss: 0.8110 (0.8122) time: 0.2027 data: 0.1113 max mem: 9390 +Train: [91] [ 800/6250] eta: 0:16:57 lr: 0.000003 grad: 0.1543 (0.1656) loss: 0.8127 (0.8122) time: 0.1816 data: 0.0941 max mem: 9390 +Train: [91] [ 900/6250] eta: 0:16:30 lr: 0.000003 grad: 0.1523 (0.1634) loss: 0.8157 (0.8121) time: 0.1786 data: 0.0875 max mem: 9390 +Train: [91] [1000/6250] eta: 0:16:00 lr: 0.000003 grad: 0.1397 (0.1615) loss: 0.8154 (0.8121) time: 0.1751 data: 0.0971 max mem: 9390 +Train: [91] [1100/6250] eta: 0:15:36 lr: 0.000003 grad: 0.1375 (0.1601) loss: 0.8144 (0.8120) time: 0.1660 data: 0.0832 max mem: 9390 +Train: [91] [1200/6250] eta: 0:15:09 lr: 0.000003 grad: 0.1402 (0.1589) loss: 0.8131 (0.8121) time: 0.1718 data: 0.0822 max mem: 9390 +Train: [91] [1300/6250] eta: 0:14:43 lr: 0.000003 grad: 0.1350 (0.1576) loss: 0.8139 (0.8122) time: 0.1493 data: 0.0661 max mem: 9390 +Train: [91] [1400/6250] eta: 0:14:21 lr: 0.000003 grad: 0.1357 (0.1568) loss: 0.8103 (0.8121) time: 0.1758 data: 0.0936 max mem: 9390 +Train: [91] [1500/6250] eta: 0:14:01 lr: 0.000003 grad: 0.1391 (0.1557) loss: 0.8133 (0.8120) time: 0.1746 data: 0.0848 max mem: 9390 +Train: [91] [1600/6250] eta: 0:13:38 lr: 0.000003 grad: 0.1424 (0.1550) loss: 0.8041 (0.8120) time: 0.1381 data: 0.0522 max mem: 9390 +Train: [91] [1700/6250] eta: 0:13:18 lr: 0.000003 grad: 0.1341 (0.1541) loss: 0.8081 (0.8119) time: 0.1578 data: 0.0689 max mem: 9390 +Train: [91] [1800/6250] eta: 0:12:57 lr: 0.000003 grad: 0.1350 (0.1534) loss: 0.8133 (0.8120) time: 0.1611 data: 0.0708 max mem: 9390 +Train: [91] [1900/6250] eta: 0:12:37 lr: 0.000003 grad: 0.1354 (0.1526) loss: 0.8173 (0.8122) time: 0.1741 data: 0.0883 max mem: 9390 +Train: [91] [2000/6250] eta: 0:12:17 lr: 0.000003 grad: 0.1420 (0.1520) loss: 0.8098 (0.8124) time: 0.1651 data: 0.0781 max mem: 9390 +Train: [91] [2100/6250] eta: 0:11:57 lr: 0.000003 grad: 0.1412 (0.1515) loss: 0.8081 (0.8124) time: 0.1616 data: 0.0753 max mem: 9390 +Train: [91] [2200/6250] eta: 0:11:39 lr: 0.000003 grad: 0.1366 (0.1509) loss: 0.8117 (0.8125) time: 0.1986 data: 0.1125 max mem: 9390 +Train: [91] [2300/6250] eta: 0:11:21 lr: 0.000003 grad: 0.1323 (0.1506) loss: 0.8153 (0.8126) time: 0.1679 data: 0.0839 max mem: 9390 +Train: [91] [2400/6250] eta: 0:11:02 lr: 0.000003 grad: 0.1333 (0.1503) loss: 0.8115 (0.8127) time: 0.1393 data: 0.0590 max mem: 9390 +Train: [91] [2500/6250] eta: 0:10:47 lr: 0.000003 grad: 0.1354 (0.1499) loss: 0.8167 (0.8127) time: 0.1544 data: 0.0741 max mem: 9390 +Train: [91] [2600/6250] eta: 0:10:29 lr: 0.000003 grad: 0.1397 (0.1496) loss: 0.8166 (0.8128) time: 0.2047 data: 0.1192 max mem: 9390 +Train: [91] [2700/6250] eta: 0:10:11 lr: 0.000002 grad: 0.1375 (0.1492) loss: 0.8193 (0.8129) time: 0.1702 data: 0.0860 max mem: 9390 +Train: [91] [2800/6250] eta: 0:09:52 lr: 0.000002 grad: 0.1373 (0.1487) loss: 0.8170 (0.8130) time: 0.1720 data: 0.0789 max mem: 9390 +Train: [91] [2900/6250] eta: 0:09:35 lr: 0.000002 grad: 0.1335 (0.1482) loss: 0.8140 (0.8131) time: 0.1792 data: 0.0883 max mem: 9390 +Train: [91] [3000/6250] eta: 0:09:17 lr: 0.000002 grad: 0.1324 (0.1479) loss: 0.8160 (0.8132) time: 0.1782 data: 0.0945 max mem: 9390 +Train: [91] [3100/6250] eta: 0:08:58 lr: 0.000002 grad: 0.1244 (0.1475) loss: 0.8212 (0.8133) time: 0.1654 data: 0.0787 max mem: 9390 +Train: [91] [3200/6250] eta: 0:08:40 lr: 0.000002 grad: 0.1295 (0.1472) loss: 0.8171 (0.8134) time: 0.1635 data: 0.0737 max mem: 9390 +Train: [91] [3300/6250] eta: 0:08:22 lr: 0.000002 grad: 0.1310 (0.1469) loss: 0.8120 (0.8134) time: 0.1841 data: 0.0931 max mem: 9390 +Train: [91] [3400/6250] eta: 0:08:04 lr: 0.000002 grad: 0.1290 (0.1467) loss: 0.8191 (0.8135) time: 0.1646 data: 0.0670 max mem: 9390 +Train: [91] [3500/6250] eta: 0:07:46 lr: 0.000002 grad: 0.1332 (0.1465) loss: 0.8140 (0.8135) time: 0.1547 data: 0.0613 max mem: 9390 +Train: [91] [3600/6250] eta: 0:07:29 lr: 0.000002 grad: 0.1319 (0.1461) loss: 0.8192 (0.8136) time: 0.1726 data: 0.0828 max mem: 9390 +Train: [91] [3700/6250] eta: 0:07:12 lr: 0.000002 grad: 0.1385 (0.1459) loss: 0.8158 (0.8137) time: 0.1782 data: 0.0858 max mem: 9390 +Train: [91] [3800/6250] eta: 0:06:55 lr: 0.000002 grad: 0.1310 (0.1456) loss: 0.8116 (0.8138) time: 0.1662 data: 0.0796 max mem: 9390 +Train: [91] [3900/6250] eta: 0:06:38 lr: 0.000002 grad: 0.1326 (0.1454) loss: 0.8188 (0.8138) time: 0.1866 data: 0.1013 max mem: 9390 +Train: [91] [4000/6250] eta: 0:06:21 lr: 0.000002 grad: 0.1388 (0.1453) loss: 0.8080 (0.8138) time: 0.1753 data: 0.0782 max mem: 9390 +Train: [91] [4100/6250] eta: 0:06:04 lr: 0.000002 grad: 0.1353 (0.1451) loss: 0.8126 (0.8138) time: 0.1668 data: 0.0687 max mem: 9390 +Train: [91] [4200/6250] eta: 0:05:47 lr: 0.000002 grad: 0.1322 (0.1449) loss: 0.8122 (0.8139) time: 0.1763 data: 0.0910 max mem: 9390 +Train: [91] [4300/6250] eta: 0:05:30 lr: 0.000002 grad: 0.1264 (0.1446) loss: 0.8181 (0.8139) time: 0.1855 data: 0.0939 max mem: 9390 +Train: [91] [4400/6250] eta: 0:05:13 lr: 0.000002 grad: 0.1391 (0.1444) loss: 0.8112 (0.8139) time: 0.1593 data: 0.0693 max mem: 9390 +Train: [91] [4500/6250] eta: 0:04:56 lr: 0.000002 grad: 0.1372 (0.1443) loss: 0.8187 (0.8140) time: 0.1463 data: 0.0564 max mem: 9390 +Train: [91] [4600/6250] eta: 0:04:38 lr: 0.000002 grad: 0.1365 (0.1442) loss: 0.8189 (0.8140) time: 0.1860 data: 0.0967 max mem: 9390 +Train: [91] [4700/6250] eta: 0:04:21 lr: 0.000002 grad: 0.1304 (0.1441) loss: 0.8154 (0.8140) time: 0.1459 data: 0.0530 max mem: 9390 +Train: [91] [4800/6250] eta: 0:04:04 lr: 0.000002 grad: 0.1387 (0.1441) loss: 0.8125 (0.8140) time: 0.1730 data: 0.0870 max mem: 9390 +Train: [91] [4900/6250] eta: 0:03:47 lr: 0.000002 grad: 0.1392 (0.1441) loss: 0.8181 (0.8141) time: 0.1344 data: 0.0488 max mem: 9390 +Train: [91] [5000/6250] eta: 0:03:30 lr: 0.000002 grad: 0.1450 (0.1439) loss: 0.8160 (0.8141) time: 0.1617 data: 0.0784 max mem: 9390 +Train: [91] [5100/6250] eta: 0:03:13 lr: 0.000002 grad: 0.1337 (0.1438) loss: 0.8141 (0.8142) time: 0.1383 data: 0.0527 max mem: 9390 +Train: [91] [5200/6250] eta: 0:02:56 lr: 0.000002 grad: 0.1301 (0.1437) loss: 0.8144 (0.8142) time: 0.2026 data: 0.1104 max mem: 9390 +Train: [91] [5300/6250] eta: 0:02:39 lr: 0.000002 grad: 0.1326 (0.1436) loss: 0.8209 (0.8143) time: 0.1744 data: 0.0846 max mem: 9390 +Train: [91] [5400/6250] eta: 0:02:22 lr: 0.000002 grad: 0.1368 (0.1436) loss: 0.8218 (0.8144) time: 0.1518 data: 0.0688 max mem: 9390 +Train: [91] [5500/6250] eta: 0:02:06 lr: 0.000002 grad: 0.1428 (0.1436) loss: 0.8114 (0.8144) time: 0.1741 data: 0.0883 max mem: 9390 +Train: [91] [5600/6250] eta: 0:01:49 lr: 0.000002 grad: 0.1372 (0.1436) loss: 0.8130 (0.8144) time: 0.1509 data: 0.0625 max mem: 9390 +Train: [91] [5700/6250] eta: 0:01:32 lr: 0.000002 grad: 0.1353 (0.1437) loss: 0.8181 (0.8143) time: 0.1498 data: 0.0640 max mem: 9390 +Train: [91] [5800/6250] eta: 0:01:15 lr: 0.000002 grad: 0.1373 (0.1436) loss: 0.8174 (0.8144) time: 0.1641 data: 0.0802 max mem: 9390 +Train: [91] [5900/6250] eta: 0:00:58 lr: 0.000002 grad: 0.1470 (0.1437) loss: 0.8092 (0.8143) time: 0.1686 data: 0.0800 max mem: 9390 +Train: [91] [6000/6250] eta: 0:00:41 lr: 0.000002 grad: 0.1412 (0.1437) loss: 0.8084 (0.8143) time: 0.1620 data: 0.0783 max mem: 9390 +Train: [91] [6100/6250] eta: 0:00:25 lr: 0.000002 grad: 0.1289 (0.1436) loss: 0.8183 (0.8143) time: 0.1634 data: 0.0836 max mem: 9390 +Train: [91] [6200/6250] eta: 0:00:08 lr: 0.000002 grad: 0.1382 (0.1436) loss: 0.8141 (0.8142) time: 0.1337 data: 0.0466 max mem: 9390 +Train: [91] [6249/6250] eta: 0:00:00 lr: 0.000002 grad: 0.1348 (0.1435) loss: 0.8193 (0.8143) time: 0.1620 data: 0.0751 max mem: 9390 +Train: [91] Total time: 0:17:31 (0.1682 s / it) +Averaged stats: lr: 0.000002 grad: 0.1348 (0.1435) loss: 0.8193 (0.8143) +Eval (hcp-train-subset): [91] [ 0/62] eta: 0:03:15 loss: 0.8265 (0.8265) time: 3.1521 data: 3.0866 max mem: 9390 +Eval (hcp-train-subset): [91] [61/62] eta: 0:00:00 loss: 0.8136 (0.8161) time: 0.1383 data: 0.1130 max mem: 9390 +Eval (hcp-train-subset): [91] Total time: 0:00:13 (0.2217 s / it) +Averaged stats (hcp-train-subset): loss: 0.8136 (0.8161) +Eval (hcp-val): [91] [ 0/62] eta: 0:04:07 loss: 0.8239 (0.8239) time: 3.9912 data: 3.9234 max mem: 9390 +Eval (hcp-val): [91] [61/62] eta: 0:00:00 loss: 0.8278 (0.8285) time: 0.1302 data: 0.1054 max mem: 9390 +Eval (hcp-val): [91] Total time: 0:00:13 (0.2134 s / it) +Averaged stats (hcp-val): loss: 0.8278 (0.8285) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +Train: [92] [ 0/6250] eta: 10:43:40 lr: 0.000002 grad: 0.2208 (0.2208) loss: 0.7836 (0.7836) time: 6.1793 data: 6.0814 max mem: 9390 +Train: [92] [ 100/6250] eta: 0:22:27 lr: 0.000002 grad: 0.1448 (0.1777) loss: 0.8284 (0.8185) time: 0.1867 data: 0.0995 max mem: 9390 +Train: [92] [ 200/6250] eta: 0:18:53 lr: 0.000002 grad: 0.1282 (0.1627) loss: 0.8275 (0.8204) time: 0.1369 data: 0.0500 max mem: 9390 +Train: [92] [ 300/6250] eta: 0:18:07 lr: 0.000002 grad: 0.1396 (0.1592) loss: 0.8295 (0.8196) time: 0.1679 data: 0.0768 max mem: 9390 +Train: [92] [ 400/6250] eta: 0:18:07 lr: 0.000002 grad: 0.1476 (0.1547) loss: 0.8085 (0.8194) time: 0.2318 data: 0.1271 max mem: 9390 +Train: [92] [ 500/6250] eta: 0:18:35 lr: 0.000002 grad: 0.1459 (0.1532) loss: 0.8144 (0.8182) time: 0.1891 data: 0.0785 max mem: 9390 +Train: [92] [ 600/6250] eta: 0:18:05 lr: 0.000002 grad: 0.1398 (0.1522) loss: 0.8175 (0.8170) time: 0.1679 data: 0.0784 max mem: 9390 +Train: [92] [ 700/6250] eta: 0:17:36 lr: 0.000002 grad: 0.1397 (0.1514) loss: 0.8078 (0.8163) time: 0.1903 data: 0.0969 max mem: 9390 +Train: [92] [ 800/6250] eta: 0:17:06 lr: 0.000002 grad: 0.1381 (0.1504) loss: 0.8159 (0.8162) time: 0.1601 data: 0.0661 max mem: 9390 +Train: [92] [ 900/6250] eta: 0:16:35 lr: 0.000002 grad: 0.1377 (0.1499) loss: 0.8087 (0.8161) time: 0.1716 data: 0.0775 max mem: 9390 +Train: [92] [1000/6250] eta: 0:16:02 lr: 0.000002 grad: 0.1338 (0.1488) loss: 0.8193 (0.8160) time: 0.1401 data: 0.0537 max mem: 9390 +Train: [92] [1100/6250] eta: 0:15:36 lr: 0.000002 grad: 0.1372 (0.1477) loss: 0.8222 (0.8162) time: 0.1548 data: 0.0791 max mem: 9390 +Train: [92] [1200/6250] eta: 0:15:08 lr: 0.000002 grad: 0.1425 (0.1472) loss: 0.8179 (0.8161) time: 0.1568 data: 0.0704 max mem: 9390 +Train: [92] [1300/6250] eta: 0:14:44 lr: 0.000002 grad: 0.1375 (0.1468) loss: 0.8129 (0.8160) time: 0.1504 data: 0.0639 max mem: 9390 +Train: [92] [1400/6250] eta: 0:14:22 lr: 0.000002 grad: 0.1428 (0.1464) loss: 0.8137 (0.8159) time: 0.1512 data: 0.0618 max mem: 9390 +Train: [92] [1500/6250] eta: 0:14:04 lr: 0.000002 grad: 0.1375 (0.1462) loss: 0.8103 (0.8156) time: 0.2090 data: 0.1273 max mem: 9390 +Train: [92] [1600/6250] eta: 0:13:37 lr: 0.000002 grad: 0.1325 (0.1458) loss: 0.8170 (0.8155) time: 0.1503 data: 0.0636 max mem: 9390 +Train: [92] [1700/6250] eta: 0:13:16 lr: 0.000002 grad: 0.1336 (0.1456) loss: 0.8105 (0.8152) time: 0.1577 data: 0.0725 max mem: 9390 +Train: [92] [1800/6250] eta: 0:12:55 lr: 0.000002 grad: 0.1342 (0.1455) loss: 0.8115 (0.8150) time: 0.1487 data: 0.0583 max mem: 9390 +Train: [92] [1900/6250] eta: 0:12:36 lr: 0.000002 grad: 0.1334 (0.1454) loss: 0.8197 (0.8148) time: 0.1633 data: 0.0696 max mem: 9390 +Train: [92] [2000/6250] eta: 0:12:17 lr: 0.000002 grad: 0.1371 (0.1454) loss: 0.8103 (0.8147) time: 0.1806 data: 0.0868 max mem: 9390 +Train: [92] [2100/6250] eta: 0:11:56 lr: 0.000002 grad: 0.1422 (0.1452) loss: 0.8042 (0.8146) time: 0.1632 data: 0.0793 max mem: 9390 +Train: [92] [2200/6250] eta: 0:11:36 lr: 0.000002 grad: 0.1392 (0.1450) loss: 0.8172 (0.8147) time: 0.1626 data: 0.0688 max mem: 9390 +Train: [92] [2300/6250] eta: 0:11:18 lr: 0.000002 grad: 0.1357 (0.1447) loss: 0.8169 (0.8147) time: 0.1702 data: 0.0852 max mem: 9390 +Train: [92] [2400/6250] eta: 0:10:59 lr: 0.000002 grad: 0.1357 (0.1445) loss: 0.8159 (0.8148) time: 0.1791 data: 0.0967 max mem: 9390 +Train: [92] [2500/6250] eta: 0:10:42 lr: 0.000002 grad: 0.1427 (0.1443) loss: 0.8105 (0.8149) time: 0.1876 data: 0.1066 max mem: 9390 +Train: [92] [2600/6250] eta: 0:10:23 lr: 0.000002 grad: 0.1366 (0.1441) loss: 0.8148 (0.8148) time: 0.1651 data: 0.0786 max mem: 9390 +Train: [92] [2700/6250] eta: 0:10:05 lr: 0.000002 grad: 0.1280 (0.1439) loss: 0.8113 (0.8148) time: 0.1628 data: 0.0739 max mem: 9390 +Train: [92] [2800/6250] eta: 0:09:48 lr: 0.000002 grad: 0.1291 (0.1437) loss: 0.8120 (0.8148) time: 0.1677 data: 0.0809 max mem: 9390 +Train: [92] [2900/6250] eta: 0:09:30 lr: 0.000002 grad: 0.1344 (0.1436) loss: 0.8165 (0.8147) time: 0.1718 data: 0.0880 max mem: 9390 +Train: [92] [3000/6250] eta: 0:09:13 lr: 0.000002 grad: 0.1438 (0.1435) loss: 0.8152 (0.8146) time: 0.1634 data: 0.0800 max mem: 9390 +Train: [92] [3100/6250] eta: 0:08:55 lr: 0.000002 grad: 0.1399 (0.1433) loss: 0.8140 (0.8147) time: 0.1796 data: 0.0907 max mem: 9390 +Train: [92] [3200/6250] eta: 0:08:36 lr: 0.000002 grad: 0.1381 (0.1432) loss: 0.8180 (0.8148) time: 0.1501 data: 0.0624 max mem: 9390 +Train: [92] [3300/6250] eta: 0:08:19 lr: 0.000002 grad: 0.1305 (0.1430) loss: 0.8220 (0.8149) time: 0.1936 data: 0.1023 max mem: 9390 +Train: [92] [3400/6250] eta: 0:08:02 lr: 0.000002 grad: 0.1378 (0.1427) loss: 0.8199 (0.8151) time: 0.1740 data: 0.0814 max mem: 9390 +Train: [92] [3500/6250] eta: 0:07:45 lr: 0.000002 grad: 0.1354 (0.1426) loss: 0.8154 (0.8152) time: 0.1704 data: 0.0807 max mem: 9390 +Train: [92] [3600/6250] eta: 0:07:27 lr: 0.000002 grad: 0.1309 (0.1425) loss: 0.8199 (0.8152) time: 0.1484 data: 0.0542 max mem: 9390 +Train: [92] [3700/6250] eta: 0:07:10 lr: 0.000002 grad: 0.1301 (0.1425) loss: 0.8221 (0.8152) time: 0.1670 data: 0.0835 max mem: 9390 +Train: [92] [3800/6250] eta: 0:06:54 lr: 0.000002 grad: 0.1354 (0.1424) loss: 0.8134 (0.8152) time: 0.1535 data: 0.0618 max mem: 9390 +Train: [92] [3900/6250] eta: 0:06:37 lr: 0.000002 grad: 0.1433 (0.1424) loss: 0.8144 (0.8151) time: 0.1740 data: 0.0849 max mem: 9390 +Train: [92] [4000/6250] eta: 0:06:19 lr: 0.000002 grad: 0.1411 (0.1423) loss: 0.8100 (0.8151) time: 0.1507 data: 0.0672 max mem: 9390 +Train: [92] [4100/6250] eta: 0:06:02 lr: 0.000002 grad: 0.1368 (0.1421) loss: 0.8117 (0.8152) time: 0.1887 data: 0.0999 max mem: 9390 +Train: [92] [4200/6250] eta: 0:05:45 lr: 0.000002 grad: 0.1369 (0.1420) loss: 0.8160 (0.8152) time: 0.1629 data: 0.0813 max mem: 9390 +Train: [92] [4300/6250] eta: 0:05:28 lr: 0.000002 grad: 0.1282 (0.1419) loss: 0.8172 (0.8153) time: 0.1457 data: 0.0622 max mem: 9390 +Train: [92] [4400/6250] eta: 0:05:11 lr: 0.000002 grad: 0.1277 (0.1418) loss: 0.8222 (0.8153) time: 0.1695 data: 0.0878 max mem: 9390 +Train: [92] [4500/6250] eta: 0:04:54 lr: 0.000002 grad: 0.1329 (0.1417) loss: 0.8156 (0.8153) time: 0.1615 data: 0.0701 max mem: 9390 +Train: [92] [4600/6250] eta: 0:04:37 lr: 0.000002 grad: 0.1424 (0.1416) loss: 0.8145 (0.8153) time: 0.1855 data: 0.1075 max mem: 9390 +Train: [92] [4700/6250] eta: 0:04:20 lr: 0.000002 grad: 0.1339 (0.1415) loss: 0.8125 (0.8153) time: 0.1551 data: 0.0645 max mem: 9390 +Train: [92] [4800/6250] eta: 0:04:03 lr: 0.000002 grad: 0.1372 (0.1415) loss: 0.8180 (0.8154) time: 0.1625 data: 0.0758 max mem: 9390 +Train: [92] [4900/6250] eta: 0:03:46 lr: 0.000002 grad: 0.1424 (0.1415) loss: 0.8201 (0.8154) time: 0.1570 data: 0.0686 max mem: 9390 +Train: [92] [5000/6250] eta: 0:03:30 lr: 0.000002 grad: 0.1455 (0.1414) loss: 0.8172 (0.8154) time: 0.1709 data: 0.0832 max mem: 9390 +Train: [92] [5100/6250] eta: 0:03:13 lr: 0.000002 grad: 0.1372 (0.1415) loss: 0.8177 (0.8154) time: 0.1850 data: 0.1028 max mem: 9390 +Train: [92] [5200/6250] eta: 0:02:56 lr: 0.000002 grad: 0.1283 (0.1415) loss: 0.8190 (0.8154) time: 0.1622 data: 0.0731 max mem: 9390 +Train: [92] [5300/6250] eta: 0:02:39 lr: 0.000002 grad: 0.1368 (0.1415) loss: 0.8182 (0.8155) time: 0.1620 data: 0.0783 max mem: 9390 +Train: [92] [5400/6250] eta: 0:02:22 lr: 0.000002 grad: 0.1416 (0.1415) loss: 0.8167 (0.8155) time: 0.1723 data: 0.0887 max mem: 9390 +Train: [92] [5500/6250] eta: 0:02:05 lr: 0.000002 grad: 0.1390 (0.1415) loss: 0.8125 (0.8155) time: 0.1754 data: 0.0863 max mem: 9390 +Train: [92] [5600/6250] eta: 0:01:48 lr: 0.000002 grad: 0.1326 (0.1414) loss: 0.8183 (0.8155) time: 0.1506 data: 0.0584 max mem: 9390 +Train: [92] [5700/6250] eta: 0:01:32 lr: 0.000002 grad: 0.1349 (0.1413) loss: 0.8203 (0.8156) time: 0.1715 data: 0.0854 max mem: 9390 +Train: [92] [5800/6250] eta: 0:01:15 lr: 0.000002 grad: 0.1359 (0.1413) loss: 0.8208 (0.8156) time: 0.1477 data: 0.0600 max mem: 9390 +Train: [92] [5900/6250] eta: 0:00:58 lr: 0.000002 grad: 0.1327 (0.1412) loss: 0.8215 (0.8157) time: 0.1811 data: 0.0946 max mem: 9390 +Train: [92] [6000/6250] eta: 0:00:41 lr: 0.000002 grad: 0.1239 (0.1411) loss: 0.8190 (0.8158) time: 0.1525 data: 0.0615 max mem: 9390 +Train: [92] [6100/6250] eta: 0:00:25 lr: 0.000002 grad: 0.1376 (0.1410) loss: 0.8165 (0.8158) time: 0.1527 data: 0.0652 max mem: 9390 +Train: [92] [6200/6250] eta: 0:00:08 lr: 0.000002 grad: 0.1318 (0.1410) loss: 0.8191 (0.8159) time: 0.1611 data: 0.0737 max mem: 9390 +Train: [92] [6249/6250] eta: 0:00:00 lr: 0.000002 grad: 0.1337 (0.1410) loss: 0.8199 (0.8159) time: 0.2031 data: 0.1231 max mem: 9390 +Train: [92] Total time: 0:17:31 (0.1683 s / it) +Averaged stats: lr: 0.000002 grad: 0.1337 (0.1410) loss: 0.8199 (0.8159) +Eval (hcp-train-subset): [92] [ 0/62] eta: 0:05:18 loss: 0.8271 (0.8271) time: 5.1362 data: 5.1063 max mem: 9390 +Eval (hcp-train-subset): [92] [61/62] eta: 0:00:00 loss: 0.8132 (0.8154) time: 0.1314 data: 0.1047 max mem: 9390 +Eval (hcp-train-subset): [92] Total time: 0:00:13 (0.2167 s / it) +Averaged stats (hcp-train-subset): loss: 0.8132 (0.8154) +Eval (hcp-val): [92] [ 0/62] eta: 0:03:38 loss: 0.8240 (0.8240) time: 3.5234 data: 3.4652 max mem: 9390 +Eval (hcp-val): [92] [61/62] eta: 0:00:00 loss: 0.8271 (0.8279) time: 0.1166 data: 0.0918 max mem: 9390 +Eval (hcp-val): [92] Total time: 0:00:13 (0.2160 s / it) +Averaged stats (hcp-val): loss: 0.8271 (0.8279) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +Train: [93] [ 0/6250] eta: 7:44:26 lr: 0.000002 grad: 0.3449 (0.3449) loss: 0.8153 (0.8153) time: 4.4587 data: 4.2633 max mem: 9390 +Train: [93] [ 100/6250] eta: 0:22:42 lr: 0.000002 grad: 0.1508 (0.1634) loss: 0.8188 (0.8307) time: 0.1680 data: 0.0853 max mem: 9390 +Train: [93] [ 200/6250] eta: 0:19:55 lr: 0.000002 grad: 0.1438 (0.1653) loss: 0.8265 (0.8253) time: 0.1569 data: 0.0739 max mem: 9390 +Train: [93] [ 300/6250] eta: 0:18:54 lr: 0.000002 grad: 0.1454 (0.1663) loss: 0.8187 (0.8214) time: 0.1588 data: 0.0662 max mem: 9390 +Train: [93] [ 400/6250] eta: 0:18:26 lr: 0.000002 grad: 0.1379 (0.1667) loss: 0.8262 (0.8186) time: 0.2049 data: 0.1038 max mem: 9390 +Train: [93] [ 500/6250] eta: 0:18:19 lr: 0.000002 grad: 0.1398 (0.1654) loss: 0.8084 (0.8169) time: 0.1993 data: 0.0893 max mem: 9390 +Train: [93] [ 600/6250] eta: 0:17:54 lr: 0.000002 grad: 0.1428 (0.1634) loss: 0.8180 (0.8165) time: 0.1592 data: 0.0625 max mem: 9390 +Train: [93] [ 700/6250] eta: 0:17:25 lr: 0.000002 grad: 0.1341 (0.1615) loss: 0.8231 (0.8163) time: 0.1725 data: 0.0828 max mem: 9390 +Train: [93] [ 800/6250] eta: 0:16:58 lr: 0.000002 grad: 0.1406 (0.1597) loss: 0.8158 (0.8161) time: 0.1774 data: 0.0843 max mem: 9390 +Train: [93] [ 900/6250] eta: 0:16:32 lr: 0.000002 grad: 0.1369 (0.1586) loss: 0.8162 (0.8160) time: 0.1703 data: 0.0788 max mem: 9390 +Train: [93] [1000/6250] eta: 0:16:17 lr: 0.000002 grad: 0.1432 (0.1573) loss: 0.8099 (0.8160) time: 0.1037 data: 0.0077 max mem: 9390 +Train: [93] [1100/6250] eta: 0:15:58 lr: 0.000002 grad: 0.1475 (0.1563) loss: 0.8100 (0.8158) time: 0.1842 data: 0.1111 max mem: 9390 +Train: [93] [1200/6250] eta: 0:15:35 lr: 0.000002 grad: 0.1482 (0.1554) loss: 0.8078 (0.8157) time: 0.1387 data: 0.0505 max mem: 9390 +Train: [93] [1300/6250] eta: 0:15:12 lr: 0.000002 grad: 0.1349 (0.1542) loss: 0.8170 (0.8157) time: 0.1772 data: 0.0958 max mem: 9390 +Train: [93] [1400/6250] eta: 0:14:46 lr: 0.000002 grad: 0.1405 (0.1534) loss: 0.8154 (0.8156) time: 0.1442 data: 0.0632 max mem: 9390 +Train: [93] [1500/6250] eta: 0:14:26 lr: 0.000002 grad: 0.1320 (0.1525) loss: 0.8240 (0.8158) time: 0.1611 data: 0.0677 max mem: 9390 +Train: [93] [1600/6250] eta: 0:14:01 lr: 0.000002 grad: 0.1300 (0.1518) loss: 0.8190 (0.8158) time: 0.1858 data: 0.0788 max mem: 9390 +Train: [93] [1700/6250] eta: 0:13:42 lr: 0.000002 grad: 0.1347 (0.1510) loss: 0.8131 (0.8158) time: 0.1810 data: 0.0846 max mem: 9390 +Train: [93] [1800/6250] eta: 0:13:18 lr: 0.000002 grad: 0.1428 (0.1505) loss: 0.8161 (0.8157) time: 0.1519 data: 0.0574 max mem: 9390 +Train: [93] [1900/6250] eta: 0:12:55 lr: 0.000002 grad: 0.1374 (0.1500) loss: 0.8209 (0.8157) time: 0.1626 data: 0.0728 max mem: 9390 +Train: [93] [2000/6250] eta: 0:12:35 lr: 0.000002 grad: 0.1322 (0.1496) loss: 0.8162 (0.8157) time: 0.1691 data: 0.0782 max mem: 9390 +Train: [93] [2100/6250] eta: 0:12:13 lr: 0.000002 grad: 0.1321 (0.1493) loss: 0.8135 (0.8157) time: 0.1518 data: 0.0588 max mem: 9390 +Train: [93] [2200/6250] eta: 0:11:56 lr: 0.000002 grad: 0.1370 (0.1490) loss: 0.8111 (0.8157) time: 0.1892 data: 0.0944 max mem: 9390 +Train: [93] [2300/6250] eta: 0:11:37 lr: 0.000001 grad: 0.1382 (0.1487) loss: 0.8116 (0.8157) time: 0.1704 data: 0.0710 max mem: 9390 +Train: [93] [2400/6250] eta: 0:11:18 lr: 0.000001 grad: 0.1288 (0.1484) loss: 0.8134 (0.8156) time: 0.1788 data: 0.0835 max mem: 9390 +Train: [93] [2500/6250] eta: 0:10:59 lr: 0.000001 grad: 0.1329 (0.1482) loss: 0.8131 (0.8155) time: 0.1639 data: 0.0784 max mem: 9390 +Train: [93] [2600/6250] eta: 0:10:41 lr: 0.000001 grad: 0.1468 (0.1482) loss: 0.8132 (0.8154) time: 0.1637 data: 0.0675 max mem: 9390 +Train: [93] [2700/6250] eta: 0:10:22 lr: 0.000001 grad: 0.1372 (0.1480) loss: 0.8134 (0.8153) time: 0.1617 data: 0.0738 max mem: 9390 +Train: [93] [2800/6250] eta: 0:10:04 lr: 0.000001 grad: 0.1400 (0.1477) loss: 0.8198 (0.8153) time: 0.1640 data: 0.0705 max mem: 9390 +Train: [93] [2900/6250] eta: 0:09:46 lr: 0.000001 grad: 0.1361 (0.1475) loss: 0.8173 (0.8154) time: 0.1798 data: 0.0852 max mem: 9390 +Train: [93] [3000/6250] eta: 0:09:27 lr: 0.000001 grad: 0.1426 (0.1474) loss: 0.8151 (0.8154) time: 0.1537 data: 0.0660 max mem: 9390 +Train: [93] [3100/6250] eta: 0:09:10 lr: 0.000001 grad: 0.1421 (0.1471) loss: 0.8173 (0.8155) time: 0.1995 data: 0.1051 max mem: 9390 +Train: [93] [3200/6250] eta: 0:08:51 lr: 0.000001 grad: 0.1420 (0.1470) loss: 0.8139 (0.8155) time: 0.1836 data: 0.0883 max mem: 9390 +Train: [93] [3300/6250] eta: 0:08:33 lr: 0.000001 grad: 0.1382 (0.1469) loss: 0.8162 (0.8155) time: 0.1586 data: 0.0648 max mem: 9390 +Train: [93] [3400/6250] eta: 0:08:14 lr: 0.000001 grad: 0.1330 (0.1468) loss: 0.8146 (0.8154) time: 0.1679 data: 0.0782 max mem: 9390 +Train: [93] [3500/6250] eta: 0:07:56 lr: 0.000001 grad: 0.1351 (0.1467) loss: 0.8145 (0.8154) time: 0.1478 data: 0.0626 max mem: 9390 +Train: [93] [3600/6250] eta: 0:07:38 lr: 0.000001 grad: 0.1382 (0.1466) loss: 0.8122 (0.8154) time: 0.1664 data: 0.0776 max mem: 9390 +Train: [93] [3700/6250] eta: 0:07:20 lr: 0.000001 grad: 0.1380 (0.1466) loss: 0.8146 (0.8154) time: 0.1484 data: 0.0502 max mem: 9390 +Train: [93] [3800/6250] eta: 0:07:02 lr: 0.000001 grad: 0.1365 (0.1465) loss: 0.8177 (0.8154) time: 0.1608 data: 0.0697 max mem: 9390 +Train: [93] [3900/6250] eta: 0:06:44 lr: 0.000001 grad: 0.1397 (0.1464) loss: 0.8145 (0.8154) time: 0.1654 data: 0.0823 max mem: 9390 +Train: [93] [4000/6250] eta: 0:06:26 lr: 0.000001 grad: 0.1420 (0.1463) loss: 0.8109 (0.8154) time: 0.1759 data: 0.0871 max mem: 9390 +Train: [93] [4100/6250] eta: 0:06:09 lr: 0.000001 grad: 0.1433 (0.1462) loss: 0.8159 (0.8154) time: 0.1542 data: 0.0597 max mem: 9390 +Train: [93] [4200/6250] eta: 0:05:51 lr: 0.000001 grad: 0.1341 (0.1461) loss: 0.8183 (0.8155) time: 0.1417 data: 0.0455 max mem: 9390 +Train: [93] [4300/6250] eta: 0:05:33 lr: 0.000001 grad: 0.1255 (0.1459) loss: 0.8219 (0.8156) time: 0.1829 data: 0.0936 max mem: 9390 +Train: [93] [4400/6250] eta: 0:05:16 lr: 0.000001 grad: 0.1449 (0.1458) loss: 0.8130 (0.8157) time: 0.1763 data: 0.0801 max mem: 9390 +Train: [93] [4500/6250] eta: 0:04:59 lr: 0.000001 grad: 0.1277 (0.1457) loss: 0.8190 (0.8158) time: 0.1758 data: 0.0846 max mem: 9390 +Train: [93] [4600/6250] eta: 0:04:41 lr: 0.000001 grad: 0.1440 (0.1456) loss: 0.8138 (0.8158) time: 0.1741 data: 0.0890 max mem: 9390 +Train: [93] [4700/6250] eta: 0:04:24 lr: 0.000001 grad: 0.1386 (0.1455) loss: 0.8176 (0.8159) time: 0.1718 data: 0.0823 max mem: 9390 +Train: [93] [4800/6250] eta: 0:04:07 lr: 0.000001 grad: 0.1418 (0.1453) loss: 0.8128 (0.8159) time: 0.1619 data: 0.0749 max mem: 9390 +Train: [93] [4900/6250] eta: 0:03:50 lr: 0.000001 grad: 0.1431 (0.1454) loss: 0.8120 (0.8158) time: 0.1522 data: 0.0627 max mem: 9390 +Train: [93] [5000/6250] eta: 0:03:32 lr: 0.000001 grad: 0.1385 (0.1454) loss: 0.8153 (0.8158) time: 0.1574 data: 0.0688 max mem: 9390 +Train: [93] [5100/6250] eta: 0:03:15 lr: 0.000001 grad: 0.1345 (0.1454) loss: 0.8164 (0.8157) time: 0.1574 data: 0.0697 max mem: 9390 +Train: [93] [5200/6250] eta: 0:02:58 lr: 0.000001 grad: 0.1426 (0.1454) loss: 0.8152 (0.8157) time: 0.1717 data: 0.0749 max mem: 9390 +Train: [93] [5300/6250] eta: 0:02:41 lr: 0.000001 grad: 0.1425 (0.1454) loss: 0.8125 (0.8156) time: 0.1632 data: 0.0730 max mem: 9390 +Train: [93] [5400/6250] eta: 0:02:24 lr: 0.000001 grad: 0.1461 (0.1454) loss: 0.8123 (0.8156) time: 0.1807 data: 0.0974 max mem: 9390 +Train: [93] [5500/6250] eta: 0:02:07 lr: 0.000001 grad: 0.1354 (0.1453) loss: 0.8210 (0.8156) time: 0.1629 data: 0.0780 max mem: 9390 +Train: [93] [5600/6250] eta: 0:01:50 lr: 0.000001 grad: 0.1432 (0.1453) loss: 0.8169 (0.8157) time: 0.1498 data: 0.0626 max mem: 9390 +Train: [93] [5700/6250] eta: 0:01:33 lr: 0.000001 grad: 0.1414 (0.1452) loss: 0.8086 (0.8156) time: 0.1711 data: 0.0885 max mem: 9390 +Train: [93] [5800/6250] eta: 0:01:16 lr: 0.000001 grad: 0.1331 (0.1451) loss: 0.8169 (0.8156) time: 0.1775 data: 0.0942 max mem: 9390 +Train: [93] [5900/6250] eta: 0:00:59 lr: 0.000001 grad: 0.1369 (0.1450) loss: 0.8115 (0.8156) time: 0.1580 data: 0.0687 max mem: 9390 +Train: [93] [6000/6250] eta: 0:00:42 lr: 0.000001 grad: 0.1456 (0.1450) loss: 0.8131 (0.8156) time: 0.1718 data: 0.0878 max mem: 9390 +Train: [93] [6100/6250] eta: 0:00:25 lr: 0.000001 grad: 0.1354 (0.1448) loss: 0.8179 (0.8156) time: 0.1603 data: 0.0672 max mem: 9390 +Train: [93] [6200/6250] eta: 0:00:08 lr: 0.000001 grad: 0.1472 (0.1448) loss: 0.8121 (0.8156) time: 0.1769 data: 0.0904 max mem: 9390 +Train: [93] [6249/6250] eta: 0:00:00 lr: 0.000001 grad: 0.1337 (0.1447) loss: 0.8106 (0.8156) time: 0.1727 data: 0.0840 max mem: 9390 +Train: [93] Total time: 0:17:43 (0.1701 s / it) +Averaged stats: lr: 0.000001 grad: 0.1337 (0.1447) loss: 0.8106 (0.8156) +Eval (hcp-train-subset): [93] [ 0/62] eta: 0:02:53 loss: 0.8252 (0.8252) time: 2.8048 data: 2.7405 max mem: 9390 +Eval (hcp-train-subset): [93] [61/62] eta: 0:00:00 loss: 0.8112 (0.8147) time: 0.1343 data: 0.1090 max mem: 9390 +Eval (hcp-train-subset): [93] Total time: 0:00:13 (0.2166 s / it) +Averaged stats (hcp-train-subset): loss: 0.8112 (0.8147) +Eval (hcp-val): [93] [ 0/62] eta: 0:03:08 loss: 0.8242 (0.8242) time: 3.0323 data: 2.9648 max mem: 9390 +Eval (hcp-val): [93] [61/62] eta: 0:00:00 loss: 0.8274 (0.8276) time: 0.1383 data: 0.1115 max mem: 9390 +Eval (hcp-val): [93] Total time: 0:00:13 (0.2132 s / it) +Averaged stats (hcp-val): loss: 0.8274 (0.8276) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +Train: [94] [ 0/6250] eta: 9:42:21 lr: 0.000001 grad: 0.0944 (0.0944) loss: 0.8374 (0.8374) time: 5.5906 data: 5.4824 max mem: 9390 +Train: [94] [ 100/6250] eta: 0:23:01 lr: 0.000001 grad: 0.1896 (0.1761) loss: 0.8209 (0.8254) time: 0.1405 data: 0.0534 max mem: 9390 +Train: [94] [ 200/6250] eta: 0:20:26 lr: 0.000001 grad: 0.1695 (0.1766) loss: 0.8219 (0.8213) time: 0.1726 data: 0.0877 max mem: 9390 +Train: [94] [ 300/6250] eta: 0:18:51 lr: 0.000001 grad: 0.1405 (0.1706) loss: 0.8312 (0.8212) time: 0.1888 data: 0.1022 max mem: 9390 +Train: [94] [ 400/6250] eta: 0:18:01 lr: 0.000001 grad: 0.1411 (0.1657) loss: 0.8280 (0.8218) time: 0.1617 data: 0.0725 max mem: 9390 +Train: [94] [ 500/6250] eta: 0:18:08 lr: 0.000001 grad: 0.1423 (0.1623) loss: 0.8174 (0.8212) time: 0.2381 data: 0.1191 max mem: 9390 +Train: [94] [ 600/6250] eta: 0:17:52 lr: 0.000001 grad: 0.1472 (0.1602) loss: 0.8147 (0.8205) time: 0.1694 data: 0.0667 max mem: 9390 +Train: [94] [ 700/6250] eta: 0:17:25 lr: 0.000001 grad: 0.1261 (0.1580) loss: 0.8212 (0.8206) time: 0.1905 data: 0.0924 max mem: 9390 +Train: [94] [ 800/6250] eta: 0:16:58 lr: 0.000001 grad: 0.1427 (0.1567) loss: 0.8220 (0.8206) time: 0.1825 data: 0.0938 max mem: 9390 +Train: [94] [ 900/6250] eta: 0:16:31 lr: 0.000001 grad: 0.1386 (0.1552) loss: 0.8133 (0.8205) time: 0.1936 data: 0.0992 max mem: 9390 +Train: [94] [1000/6250] eta: 0:16:03 lr: 0.000001 grad: 0.1596 (0.1546) loss: 0.8179 (0.8203) time: 0.1696 data: 0.0868 max mem: 9390 +Train: [94] [1100/6250] eta: 0:15:39 lr: 0.000001 grad: 0.1378 (0.1538) loss: 0.8213 (0.8201) time: 0.1819 data: 0.0974 max mem: 9390 +Train: [94] [1200/6250] eta: 0:15:14 lr: 0.000001 grad: 0.1336 (0.1526) loss: 0.8169 (0.8201) time: 0.1606 data: 0.0672 max mem: 9390 +Train: [94] [1300/6250] eta: 0:14:50 lr: 0.000001 grad: 0.1358 (0.1519) loss: 0.8198 (0.8200) time: 0.1566 data: 0.0697 max mem: 9390 +Train: [94] [1400/6250] eta: 0:14:29 lr: 0.000001 grad: 0.1348 (0.1510) loss: 0.8221 (0.8199) time: 0.1702 data: 0.0832 max mem: 9390 +Train: [94] [1500/6250] eta: 0:14:09 lr: 0.000001 grad: 0.1377 (0.1501) loss: 0.8202 (0.8199) time: 0.1882 data: 0.1036 max mem: 9390 +Train: [94] [1600/6250] eta: 0:13:46 lr: 0.000001 grad: 0.1458 (0.1497) loss: 0.8156 (0.8198) time: 0.1785 data: 0.0850 max mem: 9390 +Train: [94] [1700/6250] eta: 0:13:27 lr: 0.000001 grad: 0.1401 (0.1494) loss: 0.8174 (0.8197) time: 0.1687 data: 0.0848 max mem: 9390 +Train: [94] [1800/6250] eta: 0:13:06 lr: 0.000001 grad: 0.1359 (0.1489) loss: 0.8168 (0.8196) time: 0.1653 data: 0.0801 max mem: 9390 +Train: [94] [1900/6250] eta: 0:12:47 lr: 0.000001 grad: 0.1319 (0.1485) loss: 0.8172 (0.8195) time: 0.1462 data: 0.0474 max mem: 9390 +Train: [94] [2000/6250] eta: 0:12:26 lr: 0.000001 grad: 0.1344 (0.1483) loss: 0.8199 (0.8193) time: 0.1417 data: 0.0589 max mem: 9390 +Train: [94] [2100/6250] eta: 0:12:07 lr: 0.000001 grad: 0.1417 (0.1484) loss: 0.8170 (0.8192) time: 0.1839 data: 0.0930 max mem: 9390 +Train: [94] [2200/6250] eta: 0:11:46 lr: 0.000001 grad: 0.1373 (0.1480) loss: 0.8135 (0.8190) time: 0.1514 data: 0.0669 max mem: 9390 +Train: [94] [2300/6250] eta: 0:11:27 lr: 0.000001 grad: 0.1368 (0.1476) loss: 0.8165 (0.8190) time: 0.1569 data: 0.0735 max mem: 9390 +Train: [94] [2400/6250] eta: 0:11:07 lr: 0.000001 grad: 0.1341 (0.1473) loss: 0.8184 (0.8189) time: 0.1347 data: 0.0465 max mem: 9390 +Train: [94] [2500/6250] eta: 0:10:50 lr: 0.000001 grad: 0.1354 (0.1471) loss: 0.8146 (0.8187) time: 0.1953 data: 0.1161 max mem: 9390 +Train: [94] [2600/6250] eta: 0:10:31 lr: 0.000001 grad: 0.1360 (0.1468) loss: 0.8151 (0.8186) time: 0.1426 data: 0.0560 max mem: 9390 +Train: [94] [2700/6250] eta: 0:10:13 lr: 0.000001 grad: 0.1424 (0.1465) loss: 0.8161 (0.8185) time: 0.1766 data: 0.0905 max mem: 9390 +Train: [94] [2800/6250] eta: 0:09:54 lr: 0.000001 grad: 0.1295 (0.1461) loss: 0.8210 (0.8185) time: 0.1700 data: 0.0846 max mem: 9390 +Train: [94] [2900/6250] eta: 0:09:37 lr: 0.000001 grad: 0.1330 (0.1459) loss: 0.8175 (0.8185) time: 0.1855 data: 0.0908 max mem: 9390 +Train: [94] [3000/6250] eta: 0:09:19 lr: 0.000001 grad: 0.1479 (0.1458) loss: 0.8133 (0.8184) time: 0.1765 data: 0.0914 max mem: 9390 +Train: [94] [3100/6250] eta: 0:09:02 lr: 0.000001 grad: 0.1436 (0.1458) loss: 0.8130 (0.8182) time: 0.1953 data: 0.1081 max mem: 9390 +Train: [94] [3200/6250] eta: 0:08:44 lr: 0.000001 grad: 0.1345 (0.1457) loss: 0.8143 (0.8181) time: 0.1798 data: 0.0845 max mem: 9390 +Train: [94] [3300/6250] eta: 0:08:26 lr: 0.000001 grad: 0.1370 (0.1456) loss: 0.8153 (0.8179) time: 0.1752 data: 0.0861 max mem: 9390 +Train: [94] [3400/6250] eta: 0:08:09 lr: 0.000001 grad: 0.1341 (0.1456) loss: 0.8175 (0.8177) time: 0.1912 data: 0.0937 max mem: 9390 +Train: [94] [3500/6250] eta: 0:07:51 lr: 0.000001 grad: 0.1359 (0.1455) loss: 0.8194 (0.8176) time: 0.1445 data: 0.0563 max mem: 9390 +Train: [94] [3600/6250] eta: 0:07:34 lr: 0.000001 grad: 0.1415 (0.1455) loss: 0.8189 (0.8174) time: 0.1718 data: 0.0824 max mem: 9390 +Train: [94] [3700/6250] eta: 0:07:16 lr: 0.000001 grad: 0.1451 (0.1455) loss: 0.8176 (0.8173) time: 0.1722 data: 0.0543 max mem: 9390 +Train: [94] [3800/6250] eta: 0:06:59 lr: 0.000001 grad: 0.1424 (0.1454) loss: 0.8137 (0.8172) time: 0.1686 data: 0.0831 max mem: 9390 +Train: [94] [3900/6250] eta: 0:06:42 lr: 0.000001 grad: 0.1393 (0.1454) loss: 0.8090 (0.8170) time: 0.1767 data: 0.0888 max mem: 9390 +Train: [94] [4000/6250] eta: 0:06:25 lr: 0.000001 grad: 0.1365 (0.1454) loss: 0.8139 (0.8168) time: 0.1322 data: 0.0300 max mem: 9390 +Train: [94] [4100/6250] eta: 0:06:08 lr: 0.000001 grad: 0.1406 (0.1454) loss: 0.8089 (0.8166) time: 0.1772 data: 0.0828 max mem: 9390 +Train: [94] [4200/6250] eta: 0:05:51 lr: 0.000001 grad: 0.1357 (0.1454) loss: 0.8155 (0.8165) time: 0.1736 data: 0.0809 max mem: 9390 +Train: [94] [4300/6250] eta: 0:05:33 lr: 0.000001 grad: 0.1354 (0.1453) loss: 0.8075 (0.8164) time: 0.1680 data: 0.0775 max mem: 9390 +Train: [94] [4400/6250] eta: 0:05:16 lr: 0.000001 grad: 0.1470 (0.1454) loss: 0.8104 (0.8163) time: 0.1528 data: 0.0636 max mem: 9390 +Train: [94] [4500/6250] eta: 0:04:59 lr: 0.000001 grad: 0.1352 (0.1452) loss: 0.8178 (0.8162) time: 0.1401 data: 0.0472 max mem: 9390 +Train: [94] [4600/6250] eta: 0:04:41 lr: 0.000001 grad: 0.1340 (0.1453) loss: 0.8162 (0.8162) time: 0.1558 data: 0.0628 max mem: 9390 +Train: [94] [4700/6250] eta: 0:04:24 lr: 0.000001 grad: 0.1351 (0.1452) loss: 0.8064 (0.8161) time: 0.1757 data: 0.0863 max mem: 9390 +Train: [94] [4800/6250] eta: 0:04:07 lr: 0.000001 grad: 0.1315 (0.1452) loss: 0.8135 (0.8161) time: 0.1696 data: 0.0763 max mem: 9390 +Train: [94] [4900/6250] eta: 0:03:51 lr: 0.000001 grad: 0.1510 (0.1451) loss: 0.8152 (0.8161) time: 0.1832 data: 0.0986 max mem: 9390 +Train: [94] [5000/6250] eta: 0:03:33 lr: 0.000001 grad: 0.1373 (0.1451) loss: 0.8195 (0.8160) time: 0.1593 data: 0.0655 max mem: 9390 +Train: [94] [5100/6250] eta: 0:03:16 lr: 0.000001 grad: 0.1463 (0.1452) loss: 0.8071 (0.8160) time: 0.1543 data: 0.0715 max mem: 9390 +Train: [94] [5200/6250] eta: 0:02:59 lr: 0.000001 grad: 0.1381 (0.1452) loss: 0.8165 (0.8160) time: 0.1743 data: 0.0886 max mem: 9390 +Train: [94] [5300/6250] eta: 0:02:42 lr: 0.000001 grad: 0.1433 (0.1453) loss: 0.8137 (0.8160) time: 0.1617 data: 0.0761 max mem: 9390 +Train: [94] [5400/6250] eta: 0:02:25 lr: 0.000001 grad: 0.1402 (0.1453) loss: 0.8144 (0.8159) time: 0.2043 data: 0.0994 max mem: 9390 +Train: [94] [5500/6250] eta: 0:02:08 lr: 0.000001 grad: 0.1436 (0.1453) loss: 0.8107 (0.8159) time: 0.1482 data: 0.0563 max mem: 9390 +Train: [94] [5600/6250] eta: 0:01:51 lr: 0.000001 grad: 0.1449 (0.1454) loss: 0.8090 (0.8159) time: 0.2343 data: 0.1478 max mem: 9390 +Train: [94] [5700/6250] eta: 0:01:34 lr: 0.000001 grad: 0.1468 (0.1454) loss: 0.8154 (0.8158) time: 0.1841 data: 0.0806 max mem: 9390 +Train: [94] [5800/6250] eta: 0:01:17 lr: 0.000001 grad: 0.1425 (0.1455) loss: 0.8098 (0.8158) time: 0.1524 data: 0.0668 max mem: 9390 +Train: [94] [5900/6250] eta: 0:00:59 lr: 0.000001 grad: 0.1480 (0.1456) loss: 0.8088 (0.8158) time: 0.1565 data: 0.0758 max mem: 9390 +Train: [94] [6000/6250] eta: 0:00:42 lr: 0.000001 grad: 0.1424 (0.1457) loss: 0.8132 (0.8157) time: 0.1564 data: 0.0637 max mem: 9390 +Train: [94] [6100/6250] eta: 0:00:25 lr: 0.000001 grad: 0.1573 (0.1458) loss: 0.8124 (0.8157) time: 0.1837 data: 0.0942 max mem: 9390 +Train: [94] [6200/6250] eta: 0:00:08 lr: 0.000001 grad: 0.1381 (0.1459) loss: 0.8165 (0.8157) time: 0.1498 data: 0.0603 max mem: 9390 +Train: [94] [6249/6250] eta: 0:00:00 lr: 0.000001 grad: 0.1474 (0.1459) loss: 0.8138 (0.8156) time: 0.1650 data: 0.0784 max mem: 9390 +Train: [94] Total time: 0:17:57 (0.1723 s / it) +Averaged stats: lr: 0.000001 grad: 0.1474 (0.1459) loss: 0.8138 (0.8156) +Eval (hcp-train-subset): [94] [ 0/62] eta: 0:05:58 loss: 0.8267 (0.8267) time: 5.7836 data: 5.7442 max mem: 9390 +Eval (hcp-train-subset): [94] [61/62] eta: 0:00:00 loss: 0.8102 (0.8143) time: 0.1139 data: 0.0884 max mem: 9390 +Eval (hcp-train-subset): [94] Total time: 0:00:14 (0.2345 s / it) +Averaged stats (hcp-train-subset): loss: 0.8102 (0.8143) +Making plots (hcp-train-subset): example=16 +Eval (hcp-val): [94] [ 0/62] eta: 0:05:50 loss: 0.8252 (0.8252) time: 5.6588 data: 5.6287 max mem: 9390 +Eval (hcp-val): [94] [61/62] eta: 0:00:00 loss: 0.8276 (0.8278) time: 0.1416 data: 0.1135 max mem: 9390 +Eval (hcp-val): [94] Total time: 0:00:14 (0.2324 s / it) +Averaged stats (hcp-val): loss: 0.8276 (0.8278) +Making plots (hcp-val): example=51 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +Train: [95] [ 0/6250] eta: 6:08:56 lr: 0.000001 grad: 0.0835 (0.0835) loss: 0.8724 (0.8724) time: 3.5419 data: 3.2933 max mem: 9390 +Train: [95] [ 100/6250] eta: 0:22:50 lr: 0.000001 grad: 0.1651 (0.1837) loss: 0.8184 (0.8173) time: 0.2011 data: 0.1121 max mem: 9390 +Train: [95] [ 200/6250] eta: 0:20:13 lr: 0.000001 grad: 0.1290 (0.1757) loss: 0.8162 (0.8152) time: 0.1558 data: 0.0699 max mem: 9390 +Train: [95] [ 300/6250] eta: 0:18:55 lr: 0.000001 grad: 0.1480 (0.1689) loss: 0.8136 (0.8149) time: 0.1953 data: 0.1060 max mem: 9390 +Train: [95] [ 400/6250] eta: 0:18:34 lr: 0.000001 grad: 0.1647 (0.1670) loss: 0.8119 (0.8139) time: 0.1859 data: 0.1001 max mem: 9390 +Train: [95] [ 500/6250] eta: 0:18:07 lr: 0.000001 grad: 0.1409 (0.1652) loss: 0.8167 (0.8136) time: 0.2097 data: 0.1115 max mem: 9390 +Train: [95] [ 600/6250] eta: 0:17:29 lr: 0.000001 grad: 0.1363 (0.1625) loss: 0.8198 (0.8138) time: 0.1601 data: 0.0548 max mem: 9390 +Train: [95] [ 700/6250] eta: 0:17:03 lr: 0.000001 grad: 0.1492 (0.1610) loss: 0.8137 (0.8140) time: 0.1513 data: 0.0445 max mem: 9390 +Train: [95] [ 800/6250] eta: 0:16:36 lr: 0.000001 grad: 0.1543 (0.1602) loss: 0.8122 (0.8138) time: 0.1720 data: 0.0738 max mem: 9390 +Train: [95] [ 900/6250] eta: 0:16:10 lr: 0.000001 grad: 0.1485 (0.1590) loss: 0.8173 (0.8141) time: 0.1757 data: 0.0684 max mem: 9390 +Train: [95] [1000/6250] eta: 0:15:43 lr: 0.000001 grad: 0.1387 (0.1577) loss: 0.8157 (0.8143) time: 0.1579 data: 0.0537 max mem: 9390 +Train: [95] [1100/6250] eta: 0:15:16 lr: 0.000001 grad: 0.1453 (0.1567) loss: 0.8212 (0.8145) time: 0.1760 data: 0.0773 max mem: 9390 +Train: [95] [1200/6250] eta: 0:14:47 lr: 0.000001 grad: 0.1401 (0.1557) loss: 0.8202 (0.8148) time: 0.1609 data: 0.0680 max mem: 9390 +Train: [95] [1300/6250] eta: 0:14:27 lr: 0.000001 grad: 0.1453 (0.1551) loss: 0.8147 (0.8148) time: 0.1835 data: 0.0872 max mem: 9390 +Train: [95] [1400/6250] eta: 0:14:06 lr: 0.000001 grad: 0.1392 (0.1543) loss: 0.8110 (0.8148) time: 0.1545 data: 0.0645 max mem: 9390 +Train: [95] [1500/6250] eta: 0:13:48 lr: 0.000001 grad: 0.1376 (0.1537) loss: 0.8211 (0.8149) time: 0.1641 data: 0.0643 max mem: 9390 +Train: [95] [1600/6250] eta: 0:13:26 lr: 0.000001 grad: 0.1396 (0.1532) loss: 0.8126 (0.8151) time: 0.1655 data: 0.0721 max mem: 9390 +Train: [95] [1700/6250] eta: 0:13:07 lr: 0.000001 grad: 0.1435 (0.1527) loss: 0.8177 (0.8153) time: 0.1795 data: 0.0887 max mem: 9390 +Train: [95] [1800/6250] eta: 0:12:47 lr: 0.000001 grad: 0.1398 (0.1522) loss: 0.8168 (0.8153) time: 0.1580 data: 0.0717 max mem: 9390 +Train: [95] [1900/6250] eta: 0:12:28 lr: 0.000001 grad: 0.1408 (0.1516) loss: 0.8181 (0.8155) time: 0.1616 data: 0.0746 max mem: 9390 +Train: [95] [2000/6250] eta: 0:12:10 lr: 0.000001 grad: 0.1433 (0.1512) loss: 0.8124 (0.8155) time: 0.1596 data: 0.0659 max mem: 9390 +Train: [95] [2100/6250] eta: 0:11:51 lr: 0.000001 grad: 0.1355 (0.1511) loss: 0.8235 (0.8156) time: 0.1518 data: 0.0602 max mem: 9390 +Train: [95] [2200/6250] eta: 0:11:32 lr: 0.000001 grad: 0.1403 (0.1507) loss: 0.8133 (0.8156) time: 0.1596 data: 0.0724 max mem: 9390 +Train: [95] [2300/6250] eta: 0:11:13 lr: 0.000001 grad: 0.1461 (0.1505) loss: 0.8099 (0.8156) time: 0.1502 data: 0.0602 max mem: 9390 +Train: [95] [2400/6250] eta: 0:10:55 lr: 0.000001 grad: 0.1399 (0.1503) loss: 0.8174 (0.8157) time: 0.1715 data: 0.0852 max mem: 9390 +Train: [95] [2500/6250] eta: 0:10:37 lr: 0.000001 grad: 0.1475 (0.1502) loss: 0.8177 (0.8158) time: 0.1757 data: 0.0909 max mem: 9390 +Train: [95] [2600/6250] eta: 0:10:19 lr: 0.000001 grad: 0.1442 (0.1501) loss: 0.8187 (0.8159) time: 0.1797 data: 0.0914 max mem: 9390 +Train: [95] [2700/6250] eta: 0:10:02 lr: 0.000001 grad: 0.1513 (0.1500) loss: 0.8146 (0.8159) time: 0.1683 data: 0.0844 max mem: 9390 +Train: [95] [2800/6250] eta: 0:09:44 lr: 0.000001 grad: 0.1519 (0.1501) loss: 0.8127 (0.8159) time: 0.1343 data: 0.0467 max mem: 9390 +Train: [95] [2900/6250] eta: 0:09:27 lr: 0.000001 grad: 0.1394 (0.1499) loss: 0.8169 (0.8160) time: 0.1568 data: 0.0728 max mem: 9390 +Train: [95] [3000/6250] eta: 0:09:09 lr: 0.000001 grad: 0.1332 (0.1497) loss: 0.8141 (0.8160) time: 0.1638 data: 0.0847 max mem: 9390 +Train: [95] [3100/6250] eta: 0:08:52 lr: 0.000001 grad: 0.1344 (0.1496) loss: 0.8178 (0.8161) time: 0.1681 data: 0.0778 max mem: 9390 +Train: [95] [3200/6250] eta: 0:08:35 lr: 0.000001 grad: 0.1432 (0.1494) loss: 0.8185 (0.8162) time: 0.1744 data: 0.0878 max mem: 9390 +Train: [95] [3300/6250] eta: 0:08:18 lr: 0.000001 grad: 0.1506 (0.1494) loss: 0.8204 (0.8162) time: 0.1559 data: 0.0727 max mem: 9390 +Train: [95] [3400/6250] eta: 0:08:00 lr: 0.000001 grad: 0.1409 (0.1493) loss: 0.8133 (0.8162) time: 0.1357 data: 0.0412 max mem: 9390 +Train: [95] [3500/6250] eta: 0:07:43 lr: 0.000001 grad: 0.1347 (0.1493) loss: 0.8185 (0.8162) time: 0.1623 data: 0.0730 max mem: 9390 +Train: [95] [3600/6250] eta: 0:07:26 lr: 0.000001 grad: 0.1465 (0.1493) loss: 0.8206 (0.8163) time: 0.1521 data: 0.0591 max mem: 9390 +Train: [95] [3700/6250] eta: 0:07:09 lr: 0.000001 grad: 0.1495 (0.1492) loss: 0.8193 (0.8163) time: 0.1845 data: 0.0967 max mem: 9390 +Train: [95] [3800/6250] eta: 0:06:53 lr: 0.000001 grad: 0.1399 (0.1490) loss: 0.8179 (0.8163) time: 0.2204 data: 0.1365 max mem: 9390 +Train: [95] [3900/6250] eta: 0:06:35 lr: 0.000001 grad: 0.1291 (0.1489) loss: 0.8157 (0.8164) time: 0.1639 data: 0.0727 max mem: 9390 +Train: [95] [4000/6250] eta: 0:06:18 lr: 0.000001 grad: 0.1385 (0.1487) loss: 0.8172 (0.8164) time: 0.1626 data: 0.0727 max mem: 9390 +Train: [95] [4100/6250] eta: 0:06:01 lr: 0.000001 grad: 0.1390 (0.1486) loss: 0.8122 (0.8164) time: 0.1590 data: 0.0688 max mem: 9390 +Train: [95] [4200/6250] eta: 0:05:45 lr: 0.000001 grad: 0.1402 (0.1484) loss: 0.8112 (0.8163) time: 0.1577 data: 0.0765 max mem: 9390 +Train: [95] [4300/6250] eta: 0:05:27 lr: 0.000001 grad: 0.1380 (0.1483) loss: 0.8155 (0.8163) time: 0.1479 data: 0.0584 max mem: 9390 +Train: [95] [4400/6250] eta: 0:05:10 lr: 0.000001 grad: 0.1385 (0.1482) loss: 0.8192 (0.8163) time: 0.1397 data: 0.0443 max mem: 9390 +Train: [95] [4500/6250] eta: 0:04:53 lr: 0.000001 grad: 0.1424 (0.1481) loss: 0.8173 (0.8163) time: 0.1564 data: 0.0723 max mem: 9390 +Train: [95] [4600/6250] eta: 0:04:36 lr: 0.000001 grad: 0.1387 (0.1479) loss: 0.8136 (0.8163) time: 0.1413 data: 0.0546 max mem: 9390 +Train: [95] [4700/6250] eta: 0:04:20 lr: 0.000001 grad: 0.1430 (0.1478) loss: 0.8129 (0.8163) time: 0.1572 data: 0.0687 max mem: 9390 +Train: [95] [4800/6250] eta: 0:04:03 lr: 0.000001 grad: 0.1295 (0.1477) loss: 0.8180 (0.8163) time: 0.1368 data: 0.0469 max mem: 9390 +Train: [95] [4900/6250] eta: 0:03:46 lr: 0.000001 grad: 0.1313 (0.1476) loss: 0.8176 (0.8163) time: 0.1469 data: 0.0502 max mem: 9390 +Train: [95] [5000/6250] eta: 0:03:29 lr: 0.000001 grad: 0.1384 (0.1477) loss: 0.8164 (0.8163) time: 0.1777 data: 0.0976 max mem: 9390 +Train: [95] [5100/6250] eta: 0:03:12 lr: 0.000001 grad: 0.1430 (0.1477) loss: 0.8188 (0.8164) time: 0.1820 data: 0.0970 max mem: 9390 +Train: [95] [5200/6250] eta: 0:02:56 lr: 0.000001 grad: 0.1385 (0.1475) loss: 0.8141 (0.8164) time: 0.1646 data: 0.0713 max mem: 9390 +Train: [95] [5300/6250] eta: 0:02:39 lr: 0.000001 grad: 0.1417 (0.1475) loss: 0.8197 (0.8165) time: 0.1788 data: 0.0900 max mem: 9390 +Train: [95] [5400/6250] eta: 0:02:22 lr: 0.000001 grad: 0.1437 (0.1474) loss: 0.8178 (0.8164) time: 0.1777 data: 0.0878 max mem: 9390 +Train: [95] [5500/6250] eta: 0:02:05 lr: 0.000001 grad: 0.1318 (0.1473) loss: 0.8192 (0.8165) time: 0.1696 data: 0.0772 max mem: 9390 +Train: [95] [5600/6250] eta: 0:01:48 lr: 0.000001 grad: 0.1344 (0.1472) loss: 0.8164 (0.8165) time: 0.1711 data: 0.0885 max mem: 9390 +Train: [95] [5700/6250] eta: 0:01:32 lr: 0.000001 grad: 0.1433 (0.1471) loss: 0.8158 (0.8165) time: 0.1582 data: 0.0686 max mem: 9390 +Train: [95] [5800/6250] eta: 0:01:15 lr: 0.000001 grad: 0.1379 (0.1469) loss: 0.8150 (0.8165) time: 0.1755 data: 0.0920 max mem: 9390 +Train: [95] [5900/6250] eta: 0:00:58 lr: 0.000001 grad: 0.1303 (0.1468) loss: 0.8223 (0.8166) time: 0.1758 data: 0.0786 max mem: 9390 +Train: [95] [6000/6250] eta: 0:00:41 lr: 0.000001 grad: 0.1426 (0.1467) loss: 0.8183 (0.8166) time: 0.1620 data: 0.0844 max mem: 9390 +Train: [95] [6100/6250] eta: 0:00:25 lr: 0.000001 grad: 0.1414 (0.1467) loss: 0.8202 (0.8166) time: 0.1768 data: 0.0929 max mem: 9390 +Train: [95] [6200/6250] eta: 0:00:08 lr: 0.000001 grad: 0.1375 (0.1466) loss: 0.8189 (0.8167) time: 0.1584 data: 0.0694 max mem: 9390 +Train: [95] [6249/6250] eta: 0:00:00 lr: 0.000001 grad: 0.1363 (0.1467) loss: 0.8112 (0.8167) time: 0.1618 data: 0.0738 max mem: 9390 +Train: [95] Total time: 0:17:34 (0.1687 s / it) +Averaged stats: lr: 0.000001 grad: 0.1363 (0.1467) loss: 0.8112 (0.8167) +Eval (hcp-train-subset): [95] [ 0/62] eta: 0:06:05 loss: 0.8223 (0.8223) time: 5.8871 data: 5.8563 max mem: 9390 +Eval (hcp-train-subset): [95] [61/62] eta: 0:00:00 loss: 0.8109 (0.8143) time: 0.1355 data: 0.1103 max mem: 9390 +Eval (hcp-train-subset): [95] Total time: 0:00:14 (0.2336 s / it) +Averaged stats (hcp-train-subset): loss: 0.8109 (0.8143) +Eval (hcp-val): [95] [ 0/62] eta: 0:03:41 loss: 0.8214 (0.8214) time: 3.5780 data: 3.5254 max mem: 9390 +Eval (hcp-val): [95] [61/62] eta: 0:00:00 loss: 0.8262 (0.8276) time: 0.1394 data: 0.1138 max mem: 9390 +Eval (hcp-val): [95] Total time: 0:00:13 (0.2194 s / it) +Averaged stats (hcp-val): loss: 0.8262 (0.8276) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +Train: [96] [ 0/6250] eta: 7:16:33 lr: 0.000001 grad: 0.0847 (0.0847) loss: 0.8507 (0.8507) time: 4.1910 data: 3.8448 max mem: 9390 +Train: [96] [ 100/6250] eta: 0:22:26 lr: 0.000001 grad: 0.1402 (0.1600) loss: 0.8262 (0.8238) time: 0.1714 data: 0.0766 max mem: 9390 +Train: [96] [ 200/6250] eta: 0:20:16 lr: 0.000001 grad: 0.1639 (0.1591) loss: 0.8223 (0.8244) time: 0.2093 data: 0.1236 max mem: 9390 +Train: [96] [ 300/6250] eta: 0:18:34 lr: 0.000001 grad: 0.1395 (0.1599) loss: 0.8119 (0.8215) time: 0.1549 data: 0.0668 max mem: 9390 +Train: [96] [ 400/6250] eta: 0:17:54 lr: 0.000001 grad: 0.1530 (0.1589) loss: 0.8139 (0.8203) time: 0.1952 data: 0.0980 max mem: 9390 +Train: [96] [ 500/6250] eta: 0:17:19 lr: 0.000001 grad: 0.1403 (0.1575) loss: 0.8199 (0.8196) time: 0.1792 data: 0.0837 max mem: 9390 +Train: [96] [ 600/6250] eta: 0:16:48 lr: 0.000001 grad: 0.1473 (0.1561) loss: 0.8106 (0.8187) time: 0.1247 data: 0.0275 max mem: 9390 +Train: [96] [ 700/6250] eta: 0:16:21 lr: 0.000001 grad: 0.1431 (0.1560) loss: 0.8086 (0.8178) time: 0.1738 data: 0.0795 max mem: 9390 +Train: [96] [ 800/6250] eta: 0:15:59 lr: 0.000001 grad: 0.1570 (0.1559) loss: 0.8087 (0.8168) time: 0.1721 data: 0.0862 max mem: 9390 +Train: [96] [ 900/6250] eta: 0:15:43 lr: 0.000001 grad: 0.1481 (0.1555) loss: 0.8133 (0.8161) time: 0.2008 data: 0.1094 max mem: 9390 +Train: [96] [1000/6250] eta: 0:15:21 lr: 0.000001 grad: 0.1401 (0.1550) loss: 0.8106 (0.8156) time: 0.1928 data: 0.1028 max mem: 9390 +Train: [96] [1100/6250] eta: 0:14:58 lr: 0.000000 grad: 0.1441 (0.1544) loss: 0.8110 (0.8151) time: 0.1790 data: 0.0848 max mem: 9390 +Train: [96] [1200/6250] eta: 0:14:37 lr: 0.000000 grad: 0.1421 (0.1537) loss: 0.8085 (0.8149) time: 0.1685 data: 0.0748 max mem: 9390 +Train: [96] [1300/6250] eta: 0:14:17 lr: 0.000000 grad: 0.1266 (0.1527) loss: 0.8193 (0.8149) time: 0.1926 data: 0.1031 max mem: 9390 +Train: [96] [1400/6250] eta: 0:13:54 lr: 0.000000 grad: 0.1372 (0.1522) loss: 0.8173 (0.8148) time: 0.1518 data: 0.0667 max mem: 9390 +Train: [96] [1500/6250] eta: 0:13:35 lr: 0.000000 grad: 0.1437 (0.1519) loss: 0.8122 (0.8147) time: 0.1513 data: 0.0700 max mem: 9390 +Train: [96] [1600/6250] eta: 0:13:17 lr: 0.000000 grad: 0.1428 (0.1516) loss: 0.8071 (0.8145) time: 0.1746 data: 0.0867 max mem: 9390 +Train: [96] [1700/6250] eta: 0:12:57 lr: 0.000000 grad: 0.1421 (0.1512) loss: 0.8186 (0.8145) time: 0.1607 data: 0.0736 max mem: 9390 +Train: [96] [1800/6250] eta: 0:12:42 lr: 0.000000 grad: 0.1401 (0.1513) loss: 0.8166 (0.8145) time: 0.1679 data: 0.0770 max mem: 9390 +Train: [96] [1900/6250] eta: 0:12:23 lr: 0.000000 grad: 0.1452 (0.1513) loss: 0.8137 (0.8146) time: 0.1621 data: 0.0706 max mem: 9390 +Train: [96] [2000/6250] eta: 0:12:06 lr: 0.000000 grad: 0.1352 (0.1508) loss: 0.8210 (0.8146) time: 0.1705 data: 0.0836 max mem: 9390 +Train: [96] [2100/6250] eta: 0:11:49 lr: 0.000000 grad: 0.1300 (0.1503) loss: 0.8262 (0.8148) time: 0.2022 data: 0.1166 max mem: 9390 +Train: [96] [2200/6250] eta: 0:11:30 lr: 0.000000 grad: 0.1392 (0.1500) loss: 0.8167 (0.8149) time: 0.1555 data: 0.0639 max mem: 9390 +Train: [96] [2300/6250] eta: 0:11:12 lr: 0.000000 grad: 0.1345 (0.1495) loss: 0.8208 (0.8151) time: 0.1569 data: 0.0776 max mem: 9390 +Train: [96] [2400/6250] eta: 0:10:55 lr: 0.000000 grad: 0.1329 (0.1491) loss: 0.8155 (0.8152) time: 0.1766 data: 0.0906 max mem: 9390 +Train: [96] [2500/6250] eta: 0:10:37 lr: 0.000000 grad: 0.1418 (0.1488) loss: 0.8122 (0.8153) time: 0.1684 data: 0.0818 max mem: 9390 +Train: [96] [2600/6250] eta: 0:10:19 lr: 0.000000 grad: 0.1348 (0.1486) loss: 0.8172 (0.8154) time: 0.1444 data: 0.0495 max mem: 9390 +Train: [96] [2700/6250] eta: 0:10:03 lr: 0.000000 grad: 0.1365 (0.1482) loss: 0.8247 (0.8154) time: 0.1843 data: 0.1010 max mem: 9390 +Train: [96] [2800/6250] eta: 0:09:45 lr: 0.000000 grad: 0.1283 (0.1478) loss: 0.8187 (0.8155) time: 0.1829 data: 0.0918 max mem: 9390 +Train: [96] [2900/6250] eta: 0:09:27 lr: 0.000000 grad: 0.1398 (0.1475) loss: 0.8056 (0.8155) time: 0.1537 data: 0.0692 max mem: 9390 +Train: [96] [3000/6250] eta: 0:09:10 lr: 0.000000 grad: 0.1325 (0.1472) loss: 0.8148 (0.8155) time: 0.1738 data: 0.0894 max mem: 9390 +Train: [96] [3100/6250] eta: 0:08:53 lr: 0.000000 grad: 0.1362 (0.1470) loss: 0.8229 (0.8156) time: 0.1416 data: 0.0597 max mem: 9390 +Train: [96] [3200/6250] eta: 0:08:36 lr: 0.000000 grad: 0.1406 (0.1468) loss: 0.8144 (0.8156) time: 0.1328 data: 0.0419 max mem: 9390 +Train: [96] [3300/6250] eta: 0:08:18 lr: 0.000000 grad: 0.1267 (0.1466) loss: 0.8225 (0.8157) time: 0.1655 data: 0.0744 max mem: 9390 +Train: [96] [3400/6250] eta: 0:08:02 lr: 0.000000 grad: 0.1452 (0.1464) loss: 0.8111 (0.8157) time: 0.1926 data: 0.1046 max mem: 9390 +Train: [96] [3500/6250] eta: 0:07:44 lr: 0.000000 grad: 0.1351 (0.1462) loss: 0.8136 (0.8157) time: 0.1753 data: 0.0846 max mem: 9390 +Train: [96] [3600/6250] eta: 0:07:27 lr: 0.000000 grad: 0.1357 (0.1461) loss: 0.8087 (0.8156) time: 0.1563 data: 0.0685 max mem: 9390 +Train: [96] [3700/6250] eta: 0:07:10 lr: 0.000000 grad: 0.1264 (0.1458) loss: 0.8196 (0.8156) time: 0.1798 data: 0.0916 max mem: 9390 +Train: [96] [3800/6250] eta: 0:06:53 lr: 0.000000 grad: 0.1409 (0.1458) loss: 0.8141 (0.8156) time: 0.1861 data: 0.0932 max mem: 9390 +Train: [96] [3900/6250] eta: 0:06:36 lr: 0.000000 grad: 0.1419 (0.1458) loss: 0.8145 (0.8156) time: 0.1841 data: 0.0965 max mem: 9390 +Train: [96] [4000/6250] eta: 0:06:19 lr: 0.000000 grad: 0.1415 (0.1457) loss: 0.8140 (0.8156) time: 0.1715 data: 0.0826 max mem: 9390 +Train: [96] [4100/6250] eta: 0:06:02 lr: 0.000000 grad: 0.1399 (0.1457) loss: 0.8144 (0.8156) time: 0.1579 data: 0.0693 max mem: 9390 +Train: [96] [4200/6250] eta: 0:05:46 lr: 0.000000 grad: 0.1514 (0.1456) loss: 0.8159 (0.8156) time: 0.1706 data: 0.0877 max mem: 9390 +Train: [96] [4300/6250] eta: 0:05:29 lr: 0.000000 grad: 0.1403 (0.1455) loss: 0.8164 (0.8156) time: 0.1816 data: 0.0921 max mem: 9390 +Train: [96] [4400/6250] eta: 0:05:12 lr: 0.000000 grad: 0.1318 (0.1455) loss: 0.8191 (0.8157) time: 0.1596 data: 0.0733 max mem: 9390 +Train: [96] [4500/6250] eta: 0:04:55 lr: 0.000000 grad: 0.1277 (0.1454) loss: 0.8212 (0.8157) time: 0.1632 data: 0.0705 max mem: 9390 +Train: [96] [4600/6250] eta: 0:04:38 lr: 0.000000 grad: 0.1350 (0.1455) loss: 0.8160 (0.8157) time: 0.1501 data: 0.0563 max mem: 9390 +Train: [96] [4700/6250] eta: 0:04:21 lr: 0.000000 grad: 0.1373 (0.1454) loss: 0.8196 (0.8157) time: 0.1691 data: 0.0784 max mem: 9390 +Train: [96] [4800/6250] eta: 0:04:04 lr: 0.000000 grad: 0.1301 (0.1452) loss: 0.8210 (0.8158) time: 0.1877 data: 0.1042 max mem: 9390 +Train: [96] [4900/6250] eta: 0:03:47 lr: 0.000000 grad: 0.1359 (0.1451) loss: 0.8142 (0.8158) time: 0.1899 data: 0.0981 max mem: 9390 +Train: [96] [5000/6250] eta: 0:03:30 lr: 0.000000 grad: 0.1356 (0.1450) loss: 0.8216 (0.8158) time: 0.1601 data: 0.0724 max mem: 9390 +Train: [96] [5100/6250] eta: 0:03:13 lr: 0.000000 grad: 0.1310 (0.1448) loss: 0.8200 (0.8159) time: 0.1717 data: 0.0873 max mem: 9390 +Train: [96] [5200/6250] eta: 0:02:56 lr: 0.000000 grad: 0.1383 (0.1447) loss: 0.8182 (0.8159) time: 0.2095 data: 0.1306 max mem: 9390 +Train: [96] [5300/6250] eta: 0:02:40 lr: 0.000000 grad: 0.1407 (0.1446) loss: 0.8163 (0.8160) time: 0.1560 data: 0.0718 max mem: 9390 +Train: [96] [5400/6250] eta: 0:02:23 lr: 0.000000 grad: 0.1366 (0.1445) loss: 0.8175 (0.8160) time: 0.2594 data: 0.1838 max mem: 9390 +Train: [96] [5500/6250] eta: 0:02:06 lr: 0.000000 grad: 0.1448 (0.1444) loss: 0.8233 (0.8161) time: 0.1635 data: 0.0834 max mem: 9390 +Train: [96] [5600/6250] eta: 0:01:49 lr: 0.000000 grad: 0.1257 (0.1442) loss: 0.8243 (0.8162) time: 0.1837 data: 0.0839 max mem: 9390 +Train: [96] [5700/6250] eta: 0:01:32 lr: 0.000000 grad: 0.1256 (0.1440) loss: 0.8249 (0.8163) time: 0.1393 data: 0.0512 max mem: 9390 +Train: [96] [5800/6250] eta: 0:01:15 lr: 0.000000 grad: 0.1243 (0.1439) loss: 0.8238 (0.8164) time: 0.1576 data: 0.0614 max mem: 9390 +Train: [96] [5900/6250] eta: 0:00:59 lr: 0.000000 grad: 0.1368 (0.1437) loss: 0.8231 (0.8165) time: 0.1792 data: 0.0864 max mem: 9390 +Train: [96] [6000/6250] eta: 0:00:42 lr: 0.000000 grad: 0.1331 (0.1436) loss: 0.8214 (0.8166) time: 0.1597 data: 0.0647 max mem: 9390 +Train: [96] [6100/6250] eta: 0:00:25 lr: 0.000000 grad: 0.1416 (0.1436) loss: 0.8163 (0.8166) time: 0.1949 data: 0.1025 max mem: 9390 +Train: [96] [6200/6250] eta: 0:00:08 lr: 0.000000 grad: 0.1381 (0.1435) loss: 0.8169 (0.8167) time: 0.1581 data: 0.0542 max mem: 9390 +Train: [96] [6249/6250] eta: 0:00:00 lr: 0.000000 grad: 0.1268 (0.1434) loss: 0.8251 (0.8167) time: 0.1636 data: 0.0788 max mem: 9390 +Train: [96] Total time: 0:17:41 (0.1699 s / it) +Averaged stats: lr: 0.000000 grad: 0.1268 (0.1434) loss: 0.8251 (0.8167) +Eval (hcp-train-subset): [96] [ 0/62] eta: 0:06:24 loss: 0.8243 (0.8243) time: 6.1998 data: 6.1688 max mem: 9390 +Eval (hcp-train-subset): [96] [61/62] eta: 0:00:00 loss: 0.8106 (0.8141) time: 0.1260 data: 0.1003 max mem: 9390 +Eval (hcp-train-subset): [96] Total time: 0:00:14 (0.2277 s / it) +Averaged stats (hcp-train-subset): loss: 0.8106 (0.8141) +Eval (hcp-val): [96] [ 0/62] eta: 0:05:57 loss: 0.8231 (0.8231) time: 5.7659 data: 5.7363 max mem: 9390 +Eval (hcp-val): [96] [61/62] eta: 0:00:00 loss: 0.8261 (0.8274) time: 0.1141 data: 0.0881 max mem: 9390 +Eval (hcp-val): [96] Total time: 0:00:13 (0.2244 s / it) +Averaged stats (hcp-val): loss: 0.8261 (0.8274) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +Train: [97] [ 0/6250] eta: 10:29:14 lr: 0.000000 grad: 0.2703 (0.2703) loss: 0.8377 (0.8377) time: 6.0408 data: 5.9172 max mem: 9390 +Train: [97] [ 100/6250] eta: 0:23:30 lr: 0.000000 grad: 0.1665 (0.1738) loss: 0.8208 (0.8279) time: 0.1829 data: 0.0902 max mem: 9390 +Train: [97] [ 200/6250] eta: 0:20:22 lr: 0.000000 grad: 0.1373 (0.1676) loss: 0.8255 (0.8248) time: 0.1671 data: 0.0774 max mem: 9390 +Train: [97] [ 300/6250] eta: 0:19:00 lr: 0.000000 grad: 0.1497 (0.1654) loss: 0.8152 (0.8232) time: 0.1723 data: 0.0859 max mem: 9390 +Train: [97] [ 400/6250] eta: 0:18:04 lr: 0.000000 grad: 0.1524 (0.1631) loss: 0.8137 (0.8214) time: 0.1727 data: 0.0672 max mem: 9390 +Train: [97] [ 500/6250] eta: 0:17:30 lr: 0.000000 grad: 0.1399 (0.1603) loss: 0.8101 (0.8199) time: 0.1598 data: 0.0623 max mem: 9390 +Train: [97] [ 600/6250] eta: 0:16:54 lr: 0.000000 grad: 0.1296 (0.1579) loss: 0.8108 (0.8190) time: 0.1486 data: 0.0471 max mem: 9390 +Train: [97] [ 700/6250] eta: 0:16:41 lr: 0.000000 grad: 0.1402 (0.1559) loss: 0.8095 (0.8182) time: 0.1672 data: 0.0758 max mem: 9390 +Train: [97] [ 800/6250] eta: 0:16:32 lr: 0.000000 grad: 0.1375 (0.1552) loss: 0.8235 (0.8180) time: 0.2101 data: 0.1134 max mem: 9390 +Train: [97] [ 900/6250] eta: 0:16:15 lr: 0.000000 grad: 0.1404 (0.1541) loss: 0.8188 (0.8181) time: 0.1646 data: 0.0713 max mem: 9390 +Train: [97] [1000/6250] eta: 0:15:52 lr: 0.000000 grad: 0.1432 (0.1530) loss: 0.8195 (0.8179) time: 0.1874 data: 0.1040 max mem: 9390 +Train: [97] [1100/6250] eta: 0:15:32 lr: 0.000000 grad: 0.1417 (0.1523) loss: 0.8141 (0.8179) time: 0.1759 data: 0.0889 max mem: 9390 +Train: [97] [1200/6250] eta: 0:15:09 lr: 0.000000 grad: 0.1454 (0.1517) loss: 0.8178 (0.8177) time: 0.1754 data: 0.0850 max mem: 9390 +Train: [97] [1300/6250] eta: 0:14:46 lr: 0.000000 grad: 0.1466 (0.1514) loss: 0.8148 (0.8177) time: 0.1464 data: 0.0558 max mem: 9390 +Train: [97] [1400/6250] eta: 0:14:27 lr: 0.000000 grad: 0.1396 (0.1512) loss: 0.8143 (0.8177) time: 0.1771 data: 0.0908 max mem: 9390 +Train: [97] [1500/6250] eta: 0:14:07 lr: 0.000000 grad: 0.1406 (0.1511) loss: 0.8102 (0.8175) time: 0.1679 data: 0.0823 max mem: 9390 +Train: [97] [1600/6250] eta: 0:13:48 lr: 0.000000 grad: 0.1361 (0.1508) loss: 0.8157 (0.8175) time: 0.1686 data: 0.0794 max mem: 9390 +Train: [97] [1700/6250] eta: 0:13:27 lr: 0.000000 grad: 0.1464 (0.1504) loss: 0.8236 (0.8175) time: 0.1449 data: 0.0542 max mem: 9390 +Train: [97] [1800/6250] eta: 0:13:09 lr: 0.000000 grad: 0.1376 (0.1502) loss: 0.8221 (0.8175) time: 0.1707 data: 0.0833 max mem: 9390 +Train: [97] [1900/6250] eta: 0:12:50 lr: 0.000000 grad: 0.1551 (0.1499) loss: 0.8167 (0.8175) time: 0.1646 data: 0.0761 max mem: 9390 +Train: [97] [2000/6250] eta: 0:12:32 lr: 0.000000 grad: 0.1371 (0.1496) loss: 0.8116 (0.8174) time: 0.1564 data: 0.0663 max mem: 9390 +Train: [97] [2100/6250] eta: 0:12:14 lr: 0.000000 grad: 0.1321 (0.1493) loss: 0.8153 (0.8173) time: 0.1637 data: 0.0712 max mem: 9390 +Train: [97] [2200/6250] eta: 0:11:57 lr: 0.000000 grad: 0.1356 (0.1489) loss: 0.8173 (0.8174) time: 0.1817 data: 0.0954 max mem: 9390 +Train: [97] [2300/6250] eta: 0:11:38 lr: 0.000000 grad: 0.1466 (0.1487) loss: 0.8094 (0.8174) time: 0.1935 data: 0.1086 max mem: 9390 +Train: [97] [2400/6250] eta: 0:11:21 lr: 0.000000 grad: 0.1344 (0.1484) loss: 0.8181 (0.8174) time: 0.1766 data: 0.0925 max mem: 9390 +Train: [97] [2500/6250] eta: 0:11:02 lr: 0.000000 grad: 0.1475 (0.1483) loss: 0.8150 (0.8173) time: 0.1843 data: 0.0910 max mem: 9390 +Train: [97] [2600/6250] eta: 0:10:45 lr: 0.000000 grad: 0.1400 (0.1481) loss: 0.8163 (0.8173) time: 0.1701 data: 0.0849 max mem: 9390 +Train: [97] [2700/6250] eta: 0:10:26 lr: 0.000000 grad: 0.1347 (0.1478) loss: 0.8170 (0.8173) time: 0.1617 data: 0.0760 max mem: 9390 +Train: [97] [2800/6250] eta: 0:10:08 lr: 0.000000 grad: 0.1434 (0.1477) loss: 0.8185 (0.8172) time: 0.1667 data: 0.0804 max mem: 9390 +Train: [97] [2900/6250] eta: 0:09:51 lr: 0.000000 grad: 0.1359 (0.1476) loss: 0.8086 (0.8172) time: 0.1797 data: 0.0933 max mem: 9390 +Train: [97] [3000/6250] eta: 0:09:33 lr: 0.000000 grad: 0.1481 (0.1477) loss: 0.8139 (0.8170) time: 0.1829 data: 0.0949 max mem: 9390 +Train: [97] [3100/6250] eta: 0:09:14 lr: 0.000000 grad: 0.1394 (0.1476) loss: 0.8164 (0.8169) time: 0.1819 data: 0.1026 max mem: 9390 +Train: [97] [3200/6250] eta: 0:08:57 lr: 0.000000 grad: 0.1446 (0.1477) loss: 0.8083 (0.8168) time: 0.1722 data: 0.0901 max mem: 9390 +Train: [97] [3300/6250] eta: 0:08:40 lr: 0.000000 grad: 0.1337 (0.1477) loss: 0.8164 (0.8167) time: 0.1875 data: 0.0803 max mem: 9390 +Train: [97] [3400/6250] eta: 0:08:22 lr: 0.000000 grad: 0.1363 (0.1476) loss: 0.8192 (0.8168) time: 0.1603 data: 0.0657 max mem: 9390 +Train: [97] [3500/6250] eta: 0:08:04 lr: 0.000000 grad: 0.1468 (0.1475) loss: 0.8119 (0.8168) time: 0.1924 data: 0.1041 max mem: 9390 +Train: [97] [3600/6250] eta: 0:07:47 lr: 0.000000 grad: 0.1419 (0.1475) loss: 0.8144 (0.8168) time: 0.1911 data: 0.1060 max mem: 9390 +Train: [97] [3700/6250] eta: 0:07:29 lr: 0.000000 grad: 0.1434 (0.1474) loss: 0.8144 (0.8168) time: 0.1950 data: 0.1093 max mem: 9390 +Train: [97] [3800/6250] eta: 0:07:12 lr: 0.000000 grad: 0.1530 (0.1474) loss: 0.8220 (0.8168) time: 0.1548 data: 0.0644 max mem: 9390 +Train: [97] [3900/6250] eta: 0:06:54 lr: 0.000000 grad: 0.1408 (0.1473) loss: 0.8155 (0.8168) time: 0.1637 data: 0.0741 max mem: 9390 +Train: [97] [4000/6250] eta: 0:06:37 lr: 0.000000 grad: 0.1379 (0.1473) loss: 0.8249 (0.8168) time: 0.1791 data: 0.0745 max mem: 9390 +Train: [97] [4100/6250] eta: 0:06:20 lr: 0.000000 grad: 0.1438 (0.1472) loss: 0.8125 (0.8169) time: 0.2004 data: 0.1150 max mem: 9390 +Train: [97] [4200/6250] eta: 0:06:01 lr: 0.000000 grad: 0.1453 (0.1472) loss: 0.8254 (0.8170) time: 0.1728 data: 0.0871 max mem: 9390 +Train: [97] [4300/6250] eta: 0:05:43 lr: 0.000000 grad: 0.1386 (0.1471) loss: 0.8253 (0.8171) time: 0.1700 data: 0.0753 max mem: 9390 +Train: [97] [4400/6250] eta: 0:05:26 lr: 0.000000 grad: 0.1403 (0.1471) loss: 0.8241 (0.8172) time: 0.1859 data: 0.0998 max mem: 9390 +Train: [97] [4500/6250] eta: 0:05:09 lr: 0.000000 grad: 0.1435 (0.1470) loss: 0.8163 (0.8173) time: 0.2205 data: 0.1285 max mem: 9390 +Train: [97] [4600/6250] eta: 0:04:52 lr: 0.000000 grad: 0.1393 (0.1469) loss: 0.8186 (0.8174) time: 0.2481 data: 0.0595 max mem: 9390 +Train: [97] [4700/6250] eta: 0:04:34 lr: 0.000000 grad: 0.1346 (0.1468) loss: 0.8211 (0.8175) time: 0.2006 data: 0.1035 max mem: 9390 +Train: [97] [4800/6250] eta: 0:04:16 lr: 0.000000 grad: 0.1475 (0.1467) loss: 0.8163 (0.8175) time: 0.1653 data: 0.0791 max mem: 9390 +Train: [97] [4900/6250] eta: 0:03:59 lr: 0.000000 grad: 0.1360 (0.1467) loss: 0.8196 (0.8175) time: 0.1902 data: 0.0943 max mem: 9390 +Train: [97] [5000/6250] eta: 0:03:41 lr: 0.000000 grad: 0.1416 (0.1466) loss: 0.8209 (0.8176) time: 0.1754 data: 0.0909 max mem: 9390 +Train: [97] [5100/6250] eta: 0:03:24 lr: 0.000000 grad: 0.1357 (0.1466) loss: 0.8191 (0.8176) time: 0.1777 data: 0.0229 max mem: 9390 +Train: [97] [5200/6250] eta: 0:03:06 lr: 0.000000 grad: 0.1413 (0.1465) loss: 0.8171 (0.8176) time: 0.1039 data: 0.0092 max mem: 9390 +Train: [97] [5300/6250] eta: 0:02:49 lr: 0.000000 grad: 0.1408 (0.1464) loss: 0.8201 (0.8176) time: 0.1249 data: 0.0316 max mem: 9390 +Train: [97] [5400/6250] eta: 0:02:31 lr: 0.000000 grad: 0.1330 (0.1463) loss: 0.8207 (0.8177) time: 0.1583 data: 0.0694 max mem: 9390 +Train: [97] [5500/6250] eta: 0:02:14 lr: 0.000000 grad: 0.1439 (0.1463) loss: 0.8184 (0.8177) time: 0.1874 data: 0.0959 max mem: 9390 +Train: [97] [5600/6250] eta: 0:01:56 lr: 0.000000 grad: 0.1366 (0.1463) loss: 0.8203 (0.8177) time: 0.2767 data: 0.1290 max mem: 9390 +Train: [97] [5700/6250] eta: 0:01:38 lr: 0.000000 grad: 0.1398 (0.1464) loss: 0.8268 (0.8178) time: 0.1855 data: 0.0924 max mem: 9390 +Train: [97] [5800/6250] eta: 0:01:20 lr: 0.000000 grad: 0.1390 (0.1464) loss: 0.8194 (0.8178) time: 0.2475 data: 0.1616 max mem: 9390 +Train: [97] [5900/6250] eta: 0:01:02 lr: 0.000000 grad: 0.1433 (0.1463) loss: 0.8170 (0.8179) time: 0.2033 data: 0.1123 max mem: 9390 +Train: [97] [6000/6250] eta: 0:00:44 lr: 0.000000 grad: 0.1429 (0.1463) loss: 0.8182 (0.8179) time: 0.2006 data: 0.0695 max mem: 9390 +Train: [97] [6100/6250] eta: 0:00:26 lr: 0.000000 grad: 0.1411 (0.1464) loss: 0.8245 (0.8179) time: 0.1729 data: 0.0917 max mem: 9390 +Train: [97] [6200/6250] eta: 0:00:08 lr: 0.000000 grad: 0.1504 (0.1464) loss: 0.8154 (0.8179) time: 0.1450 data: 0.0526 max mem: 9390 +Train: [97] [6249/6250] eta: 0:00:00 lr: 0.000000 grad: 0.1350 (0.1464) loss: 0.8225 (0.8180) time: 0.1843 data: 0.0961 max mem: 9390 +Train: [97] Total time: 0:18:47 (0.1805 s / it) +Averaged stats: lr: 0.000000 grad: 0.1350 (0.1464) loss: 0.8225 (0.8180) +Eval (hcp-train-subset): [97] [ 0/62] eta: 0:05:14 loss: 0.8243 (0.8243) time: 5.0693 data: 5.0393 max mem: 9390 +Eval (hcp-train-subset): [97] [61/62] eta: 0:00:00 loss: 0.8098 (0.8138) time: 0.1483 data: 0.1226 max mem: 9390 +Eval (hcp-train-subset): [97] Total time: 0:00:13 (0.2205 s / it) +Averaged stats (hcp-train-subset): loss: 0.8098 (0.8138) +Eval (hcp-val): [97] [ 0/62] eta: 0:03:22 loss: 0.8250 (0.8250) time: 3.2697 data: 3.1932 max mem: 9390 +Eval (hcp-val): [97] [61/62] eta: 0:00:00 loss: 0.8253 (0.8272) time: 0.1147 data: 0.0895 max mem: 9390 +Eval (hcp-val): [97] Total time: 0:00:13 (0.2174 s / it) +Averaged stats (hcp-val): loss: 0.8253 (0.8272) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +Train: [98] [ 0/6250] eta: 10:06:30 lr: 0.000000 grad: 0.1218 (0.1218) loss: 0.8320 (0.8320) time: 5.8225 data: 5.7220 max mem: 9390 +Train: [98] [ 100/6250] eta: 0:22:40 lr: 0.000000 grad: 0.1583 (0.1797) loss: 0.8219 (0.8159) time: 0.1862 data: 0.1051 max mem: 9390 +Train: [98] [ 200/6250] eta: 0:19:59 lr: 0.000000 grad: 0.1686 (0.1732) loss: 0.8119 (0.8147) time: 0.1632 data: 0.0811 max mem: 9390 +Train: [98] [ 300/6250] eta: 0:18:42 lr: 0.000000 grad: 0.1542 (0.1715) loss: 0.8168 (0.8136) time: 0.1717 data: 0.0861 max mem: 9390 +Train: [98] [ 400/6250] eta: 0:17:52 lr: 0.000000 grad: 0.1475 (0.1701) loss: 0.8229 (0.8147) time: 0.1755 data: 0.0838 max mem: 9390 +Train: [98] [ 500/6250] eta: 0:17:10 lr: 0.000000 grad: 0.1411 (0.1711) loss: 0.8235 (0.8149) time: 0.1503 data: 0.0581 max mem: 9390 +Train: [98] [ 600/6250] eta: 0:16:41 lr: 0.000000 grad: 0.1489 (0.1698) loss: 0.8244 (0.8157) time: 0.1601 data: 0.0648 max mem: 9390 +Train: [98] [ 700/6250] eta: 0:16:14 lr: 0.000000 grad: 0.1605 (0.1680) loss: 0.8224 (0.8162) time: 0.1897 data: 0.0924 max mem: 9390 +Train: [98] [ 800/6250] eta: 0:15:43 lr: 0.000000 grad: 0.1430 (0.1661) loss: 0.8149 (0.8162) time: 0.1449 data: 0.0426 max mem: 9390 +Train: [98] [ 900/6250] eta: 0:15:21 lr: 0.000000 grad: 0.1357 (0.1644) loss: 0.8165 (0.8163) time: 0.1816 data: 0.0875 max mem: 9390 +Train: [98] [1000/6250] eta: 0:14:59 lr: 0.000000 grad: 0.1284 (0.1628) loss: 0.8156 (0.8162) time: 0.1767 data: 0.0854 max mem: 9390 +Train: [98] [1100/6250] eta: 0:14:34 lr: 0.000000 grad: 0.1395 (0.1616) loss: 0.8150 (0.8161) time: 0.1644 data: 0.0756 max mem: 9390 +Train: [98] [1200/6250] eta: 0:14:16 lr: 0.000000 grad: 0.1384 (0.1606) loss: 0.8146 (0.8160) time: 0.1835 data: 0.0946 max mem: 9390 +Train: [98] [1300/6250] eta: 0:13:58 lr: 0.000000 grad: 0.1434 (0.1596) loss: 0.8140 (0.8158) time: 0.1466 data: 0.0572 max mem: 9390 +Train: [98] [1400/6250] eta: 0:13:40 lr: 0.000000 grad: 0.1511 (0.1589) loss: 0.8090 (0.8156) time: 0.1562 data: 0.0713 max mem: 9390 +Train: [98] [1500/6250] eta: 0:13:18 lr: 0.000000 grad: 0.1400 (0.1588) loss: 0.8166 (0.8152) time: 0.1754 data: 0.0877 max mem: 9390 +Train: [98] [1600/6250] eta: 0:13:02 lr: 0.000000 grad: 0.1401 (0.1581) loss: 0.8128 (0.8151) time: 0.1528 data: 0.0715 max mem: 9390 +Train: [98] [1700/6250] eta: 0:12:42 lr: 0.000000 grad: 0.1349 (0.1573) loss: 0.8199 (0.8152) time: 0.1525 data: 0.0636 max mem: 9390 +Train: [98] [1800/6250] eta: 0:12:24 lr: 0.000000 grad: 0.1390 (0.1566) loss: 0.8086 (0.8152) time: 0.1775 data: 0.0859 max mem: 9390 +Train: [98] [1900/6250] eta: 0:12:06 lr: 0.000000 grad: 0.1379 (0.1559) loss: 0.8198 (0.8152) time: 0.1685 data: 0.0739 max mem: 9390 +Train: [98] [2000/6250] eta: 0:11:47 lr: 0.000000 grad: 0.1389 (0.1554) loss: 0.8196 (0.8152) time: 0.1505 data: 0.0682 max mem: 9390 +Train: [98] [2100/6250] eta: 0:11:29 lr: 0.000000 grad: 0.1355 (0.1550) loss: 0.8228 (0.8152) time: 0.1677 data: 0.0768 max mem: 9390 +Train: [98] [2200/6250] eta: 0:11:12 lr: 0.000000 grad: 0.1379 (0.1544) loss: 0.8184 (0.8152) time: 0.1675 data: 0.0813 max mem: 9390 +Train: [98] [2300/6250] eta: 0:10:54 lr: 0.000000 grad: 0.1413 (0.1539) loss: 0.8161 (0.8153) time: 0.1643 data: 0.0757 max mem: 9390 +Train: [98] [2400/6250] eta: 0:10:37 lr: 0.000000 grad: 0.1409 (0.1535) loss: 0.8178 (0.8153) time: 0.1516 data: 0.0665 max mem: 9390 +Train: [98] [2500/6250] eta: 0:10:20 lr: 0.000000 grad: 0.1352 (0.1529) loss: 0.8226 (0.8155) time: 0.1589 data: 0.0716 max mem: 9390 +Train: [98] [2600/6250] eta: 0:10:03 lr: 0.000000 grad: 0.1430 (0.1525) loss: 0.8182 (0.8155) time: 0.1415 data: 0.0527 max mem: 9390 +Train: [98] [2700/6250] eta: 0:09:46 lr: 0.000000 grad: 0.1318 (0.1520) loss: 0.8173 (0.8156) time: 0.1551 data: 0.0633 max mem: 9390 +Train: [98] [2800/6250] eta: 0:09:29 lr: 0.000000 grad: 0.1464 (0.1517) loss: 0.8116 (0.8156) time: 0.1478 data: 0.0590 max mem: 9390 +Train: [98] [2900/6250] eta: 0:09:12 lr: 0.000000 grad: 0.1381 (0.1513) loss: 0.8151 (0.8157) time: 0.1745 data: 0.0827 max mem: 9390 +Train: [98] [3000/6250] eta: 0:08:54 lr: 0.000000 grad: 0.1407 (0.1511) loss: 0.8174 (0.8157) time: 0.1613 data: 0.0728 max mem: 9390 +Train: [98] [3100/6250] eta: 0:08:37 lr: 0.000000 grad: 0.1392 (0.1509) loss: 0.8178 (0.8157) time: 0.1422 data: 0.0509 max mem: 9390 +Train: [98] [3200/6250] eta: 0:08:20 lr: 0.000000 grad: 0.1475 (0.1508) loss: 0.8140 (0.8157) time: 0.1501 data: 0.0612 max mem: 9390 +Train: [98] [3300/6250] eta: 0:08:04 lr: 0.000000 grad: 0.1382 (0.1506) loss: 0.8116 (0.8157) time: 0.1264 data: 0.0344 max mem: 9390 +Train: [98] [3400/6250] eta: 0:07:48 lr: 0.000000 grad: 0.1389 (0.1505) loss: 0.8118 (0.8157) time: 0.1516 data: 0.0652 max mem: 9390 +Train: [98] [3500/6250] eta: 0:07:32 lr: 0.000000 grad: 0.1393 (0.1503) loss: 0.8151 (0.8157) time: 0.1852 data: 0.0979 max mem: 9390 +Train: [98] [3600/6250] eta: 0:07:16 lr: 0.000000 grad: 0.1460 (0.1501) loss: 0.8157 (0.8156) time: 0.1475 data: 0.0582 max mem: 9390 +Train: [98] [3700/6250] eta: 0:07:00 lr: 0.000000 grad: 0.1452 (0.1499) loss: 0.8126 (0.8156) time: 0.1685 data: 0.0851 max mem: 9390 +Train: [98] [3800/6250] eta: 0:06:44 lr: 0.000000 grad: 0.1372 (0.1497) loss: 0.8137 (0.8156) time: 0.1692 data: 0.0933 max mem: 9390 +Train: [98] [3900/6250] eta: 0:06:27 lr: 0.000000 grad: 0.1410 (0.1495) loss: 0.8162 (0.8156) time: 0.1687 data: 0.0788 max mem: 9390 +Train: [98] [4000/6250] eta: 0:06:11 lr: 0.000000 grad: 0.1351 (0.1493) loss: 0.8211 (0.8156) time: 0.1650 data: 0.0790 max mem: 9390 +Train: [98] [4100/6250] eta: 0:05:55 lr: 0.000000 grad: 0.1391 (0.1491) loss: 0.8185 (0.8156) time: 0.1608 data: 0.0595 max mem: 9390 +Train: [98] [4200/6250] eta: 0:05:38 lr: 0.000000 grad: 0.1332 (0.1490) loss: 0.8121 (0.8156) time: 0.2022 data: 0.1170 max mem: 9390 +Train: [98] [4300/6250] eta: 0:05:22 lr: 0.000000 grad: 0.1374 (0.1489) loss: 0.8140 (0.8156) time: 0.1652 data: 0.0894 max mem: 9390 +Train: [98] [4400/6250] eta: 0:05:06 lr: 0.000000 grad: 0.1254 (0.1487) loss: 0.8185 (0.8156) time: 0.1945 data: 0.1003 max mem: 9390 +Train: [98] [4500/6250] eta: 0:04:49 lr: 0.000000 grad: 0.1402 (0.1485) loss: 0.8142 (0.8156) time: 0.1303 data: 0.0436 max mem: 9390 +Train: [98] [4600/6250] eta: 0:04:33 lr: 0.000000 grad: 0.1332 (0.1484) loss: 0.8155 (0.8156) time: 0.1664 data: 0.0844 max mem: 9390 +Train: [98] [4700/6250] eta: 0:04:16 lr: 0.000000 grad: 0.1407 (0.1483) loss: 0.8197 (0.8156) time: 0.1739 data: 0.0827 max mem: 9390 +Train: [98] [4800/6250] eta: 0:03:59 lr: 0.000000 grad: 0.1420 (0.1482) loss: 0.8148 (0.8156) time: 0.1682 data: 0.0746 max mem: 9390 +Train: [98] [4900/6250] eta: 0:03:43 lr: 0.000000 grad: 0.1381 (0.1482) loss: 0.8115 (0.8155) time: 0.1318 data: 0.0437 max mem: 9390 +Train: [98] [5000/6250] eta: 0:03:26 lr: 0.000000 grad: 0.1452 (0.1481) loss: 0.8101 (0.8155) time: 0.1556 data: 0.0607 max mem: 9390 +Train: [98] [5100/6250] eta: 0:03:10 lr: 0.000000 grad: 0.1489 (0.1481) loss: 0.8120 (0.8154) time: 0.1910 data: 0.0910 max mem: 9390 +Train: [98] [5200/6250] eta: 0:02:55 lr: 0.000000 grad: 0.1407 (0.1480) loss: 0.8076 (0.8154) time: 0.2370 data: 0.1565 max mem: 9390 +Train: [98] [5300/6250] eta: 0:02:38 lr: 0.000000 grad: 0.1393 (0.1479) loss: 0.8158 (0.8155) time: 0.1690 data: 0.0800 max mem: 9390 +Train: [98] [5400/6250] eta: 0:02:21 lr: 0.000000 grad: 0.1455 (0.1479) loss: 0.8130 (0.8155) time: 0.1341 data: 0.0426 max mem: 9390 +Train: [98] [5500/6250] eta: 0:02:04 lr: 0.000000 grad: 0.1404 (0.1479) loss: 0.8185 (0.8155) time: 0.1630 data: 0.0726 max mem: 9390 +Train: [98] [5600/6250] eta: 0:01:48 lr: 0.000000 grad: 0.1418 (0.1479) loss: 0.8092 (0.8154) time: 0.1400 data: 0.0559 max mem: 9390 +Train: [98] [5700/6250] eta: 0:01:31 lr: 0.000000 grad: 0.1445 (0.1478) loss: 0.8121 (0.8154) time: 0.1505 data: 0.0675 max mem: 9390 +Train: [98] [5800/6250] eta: 0:01:14 lr: 0.000000 grad: 0.1379 (0.1478) loss: 0.8175 (0.8154) time: 0.1609 data: 0.0789 max mem: 9390 +Train: [98] [5900/6250] eta: 0:00:58 lr: 0.000000 grad: 0.1477 (0.1477) loss: 0.8120 (0.8154) time: 0.1672 data: 0.0821 max mem: 9390 +Train: [98] [6000/6250] eta: 0:00:41 lr: 0.000000 grad: 0.1385 (0.1476) loss: 0.8209 (0.8155) time: 0.1587 data: 0.0720 max mem: 9390 +Train: [98] [6100/6250] eta: 0:00:24 lr: 0.000000 grad: 0.1401 (0.1475) loss: 0.8167 (0.8155) time: 0.1782 data: 0.0916 max mem: 9390 +Train: [98] [6200/6250] eta: 0:00:08 lr: 0.000000 grad: 0.1486 (0.1475) loss: 0.8161 (0.8155) time: 0.1558 data: 0.0658 max mem: 9390 +Train: [98] [6249/6250] eta: 0:00:00 lr: 0.000000 grad: 0.1375 (0.1475) loss: 0.8124 (0.8155) time: 0.1581 data: 0.0785 max mem: 9390 +Train: [98] Total time: 0:17:23 (0.1669 s / it) +Averaged stats: lr: 0.000000 grad: 0.1375 (0.1475) loss: 0.8124 (0.8155) +Eval (hcp-train-subset): [98] [ 0/62] eta: 0:05:42 loss: 0.8241 (0.8241) time: 5.5285 data: 5.4812 max mem: 9390 +Eval (hcp-train-subset): [98] [61/62] eta: 0:00:00 loss: 0.8104 (0.8140) time: 0.1230 data: 0.0982 max mem: 9390 +Eval (hcp-train-subset): [98] Total time: 0:00:13 (0.2200 s / it) +Averaged stats (hcp-train-subset): loss: 0.8104 (0.8140) +Eval (hcp-val): [98] [ 0/62] eta: 0:04:37 loss: 0.8234 (0.8234) time: 4.4713 data: 4.4412 max mem: 9390 +Eval (hcp-val): [98] [61/62] eta: 0:00:00 loss: 0.8257 (0.8273) time: 0.1090 data: 0.0841 max mem: 9390 +Eval (hcp-val): [98] Total time: 0:00:12 (0.2093 s / it) +Averaged stats (hcp-val): loss: 0.8257 (0.8273) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +Train: [99] [ 0/6250] eta: 6:49:16 lr: 0.000000 grad: 0.1441 (0.1441) loss: 0.8567 (0.8567) time: 3.9290 data: 3.6339 max mem: 9390 +Train: [99] [ 100/6250] eta: 0:21:33 lr: 0.000000 grad: 0.1727 (0.1871) loss: 0.8090 (0.8209) time: 0.1568 data: 0.0681 max mem: 9390 +Train: [99] [ 200/6250] eta: 0:19:57 lr: 0.000000 grad: 0.1658 (0.1863) loss: 0.8169 (0.8172) time: 0.2024 data: 0.1174 max mem: 9390 +Train: [99] [ 300/6250] eta: 0:18:35 lr: 0.000000 grad: 0.1641 (0.1808) loss: 0.8167 (0.8173) time: 0.1645 data: 0.0826 max mem: 9390 +Train: [99] [ 400/6250] eta: 0:17:40 lr: 0.000000 grad: 0.1539 (0.1783) loss: 0.8144 (0.8164) time: 0.1638 data: 0.0765 max mem: 9390 +Train: [99] [ 500/6250] eta: 0:17:14 lr: 0.000000 grad: 0.1563 (0.1738) loss: 0.8073 (0.8162) time: 0.1665 data: 0.0778 max mem: 9390 +Train: [99] [ 600/6250] eta: 0:16:42 lr: 0.000000 grad: 0.1487 (0.1707) loss: 0.8113 (0.8161) time: 0.1623 data: 0.0771 max mem: 9390 +Train: [99] [ 700/6250] eta: 0:16:15 lr: 0.000000 grad: 0.1465 (0.1679) loss: 0.8199 (0.8165) time: 0.1680 data: 0.0629 max mem: 9390 +Train: [99] [ 800/6250] eta: 0:15:54 lr: 0.000000 grad: 0.1544 (0.1660) loss: 0.8158 (0.8161) time: 0.1827 data: 0.0884 max mem: 9390 +Train: [99] [ 900/6250] eta: 0:15:30 lr: 0.000000 grad: 0.1375 (0.1646) loss: 0.8126 (0.8155) time: 0.1422 data: 0.0542 max mem: 9390 +Train: [99] [1000/6250] eta: 0:15:08 lr: 0.000000 grad: 0.1403 (0.1629) loss: 0.8117 (0.8153) time: 0.1760 data: 0.0900 max mem: 9390 +Train: [99] [1100/6250] eta: 0:14:46 lr: 0.000000 grad: 0.1467 (0.1620) loss: 0.8144 (0.8151) time: 0.1437 data: 0.0529 max mem: 9390 +Train: [99] [1200/6250] eta: 0:14:24 lr: 0.000000 grad: 0.1544 (0.1612) loss: 0.8090 (0.8148) time: 0.1812 data: 0.0966 max mem: 9390 +Train: [99] [1300/6250] eta: 0:14:03 lr: 0.000000 grad: 0.1407 (0.1603) loss: 0.8137 (0.8148) time: 0.1225 data: 0.0417 max mem: 9390 +Train: [99] [1400/6250] eta: 0:13:41 lr: 0.000000 grad: 0.1436 (0.1595) loss: 0.8114 (0.8147) time: 0.1554 data: 0.0762 max mem: 9390 +Train: [99] [1500/6250] eta: 0:13:22 lr: 0.000000 grad: 0.1483 (0.1588) loss: 0.8129 (0.8147) time: 0.1636 data: 0.0735 max mem: 9390 +Train: [99] [1600/6250] eta: 0:13:02 lr: 0.000000 grad: 0.1481 (0.1582) loss: 0.8151 (0.8149) time: 0.1574 data: 0.0693 max mem: 9390 +Train: [99] [1700/6250] eta: 0:12:42 lr: 0.000000 grad: 0.1376 (0.1577) loss: 0.8169 (0.8149) time: 0.1661 data: 0.0770 max mem: 9390 +Train: [99] [1800/6250] eta: 0:12:21 lr: 0.000000 grad: 0.1375 (0.1572) loss: 0.8158 (0.8150) time: 0.1446 data: 0.0548 max mem: 9390 +Train: [99] [1900/6250] eta: 0:12:03 lr: 0.000000 grad: 0.1473 (0.1566) loss: 0.8152 (0.8150) time: 0.1742 data: 0.0902 max mem: 9390 +Train: [99] [2000/6250] eta: 0:11:47 lr: 0.000000 grad: 0.1387 (0.1561) loss: 0.8165 (0.8150) time: 0.1989 data: 0.1141 max mem: 9390 +Train: [99] [2100/6250] eta: 0:11:28 lr: 0.000000 grad: 0.1392 (0.1555) loss: 0.8126 (0.8150) time: 0.1586 data: 0.0678 max mem: 9390 +Train: [99] [2200/6250] eta: 0:11:10 lr: 0.000000 grad: 0.1486 (0.1551) loss: 0.8144 (0.8149) time: 0.1609 data: 0.0782 max mem: 9390 +Train: [99] [2300/6250] eta: 0:10:52 lr: 0.000000 grad: 0.1359 (0.1548) loss: 0.8143 (0.8149) time: 0.1635 data: 0.0842 max mem: 9390 +Train: [99] [2400/6250] eta: 0:10:34 lr: 0.000000 grad: 0.1415 (0.1545) loss: 0.8128 (0.8150) time: 0.1534 data: 0.0689 max mem: 9390 +Train: [99] [2500/6250] eta: 0:10:16 lr: 0.000000 grad: 0.1336 (0.1542) loss: 0.8170 (0.8149) time: 0.1213 data: 0.0329 max mem: 9390 +Train: [99] [2600/6250] eta: 0:09:59 lr: 0.000000 grad: 0.1487 (0.1540) loss: 0.8143 (0.8149) time: 0.1796 data: 0.0897 max mem: 9390 +Train: [99] [2700/6250] eta: 0:09:40 lr: 0.000000 grad: 0.1395 (0.1538) loss: 0.8197 (0.8150) time: 0.1752 data: 0.0924 max mem: 9390 +Train: [99] [2800/6250] eta: 0:09:23 lr: 0.000000 grad: 0.1533 (0.1536) loss: 0.8114 (0.8150) time: 0.1624 data: 0.0748 max mem: 9390 +Train: [99] [2900/6250] eta: 0:09:06 lr: 0.000000 grad: 0.1453 (0.1534) loss: 0.8156 (0.8151) time: 0.1604 data: 0.0764 max mem: 9390 +Train: [99] [3000/6250] eta: 0:08:50 lr: 0.000000 grad: 0.1522 (0.1532) loss: 0.8176 (0.8151) time: 0.1582 data: 0.0673 max mem: 9390 +Train: [99] [3100/6250] eta: 0:08:34 lr: 0.000000 grad: 0.1432 (0.1530) loss: 0.8168 (0.8152) time: 0.1654 data: 0.0839 max mem: 9390 +Train: [99] [3200/6250] eta: 0:08:17 lr: 0.000000 grad: 0.1487 (0.1530) loss: 0.8120 (0.8152) time: 0.1559 data: 0.0655 max mem: 9390 +Train: [99] [3300/6250] eta: 0:08:00 lr: 0.000000 grad: 0.1359 (0.1529) loss: 0.8177 (0.8152) time: 0.1625 data: 0.0773 max mem: 9390 +Train: [99] [3400/6250] eta: 0:07:44 lr: 0.000000 grad: 0.1470 (0.1530) loss: 0.8153 (0.8152) time: 0.1740 data: 0.0889 max mem: 9390 +Train: [99] [3500/6250] eta: 0:07:27 lr: 0.000000 grad: 0.1347 (0.1527) loss: 0.8144 (0.8152) time: 0.1458 data: 0.0576 max mem: 9390 +Train: [99] [3600/6250] eta: 0:07:11 lr: 0.000000 grad: 0.1385 (0.1527) loss: 0.8154 (0.8153) time: 0.1605 data: 0.0757 max mem: 9390 +Train: [99] [3700/6250] eta: 0:06:54 lr: 0.000000 grad: 0.1405 (0.1525) loss: 0.8103 (0.8153) time: 0.1588 data: 0.0785 max mem: 9390 +Train: [99] [3800/6250] eta: 0:06:38 lr: 0.000000 grad: 0.1401 (0.1523) loss: 0.8202 (0.8154) time: 0.1867 data: 0.1068 max mem: 9390 +Train: [99] [3900/6250] eta: 0:06:22 lr: 0.000000 grad: 0.1403 (0.1521) loss: 0.8174 (0.8154) time: 0.1564 data: 0.0648 max mem: 9390 +Train: [99] [4000/6250] eta: 0:06:05 lr: 0.000000 grad: 0.1469 (0.1519) loss: 0.8117 (0.8154) time: 0.1594 data: 0.0680 max mem: 9390 +Train: [99] [4100/6250] eta: 0:05:49 lr: 0.000000 grad: 0.1442 (0.1518) loss: 0.8126 (0.8154) time: 0.1428 data: 0.0567 max mem: 9390 +Train: [99] [4200/6250] eta: 0:05:33 lr: 0.000000 grad: 0.1470 (0.1518) loss: 0.8199 (0.8154) time: 0.1540 data: 0.0689 max mem: 9390 +Train: [99] [4300/6250] eta: 0:05:16 lr: 0.000000 grad: 0.1434 (0.1516) loss: 0.8132 (0.8154) time: 0.1619 data: 0.0748 max mem: 9390 +Train: [99] [4400/6250] eta: 0:05:00 lr: 0.000000 grad: 0.1453 (0.1515) loss: 0.8167 (0.8154) time: 0.1785 data: 0.0885 max mem: 9390 +Train: [99] [4500/6250] eta: 0:04:44 lr: 0.000000 grad: 0.1444 (0.1513) loss: 0.8197 (0.8154) time: 0.1626 data: 0.0833 max mem: 9390 +Train: [99] [4600/6250] eta: 0:04:27 lr: 0.000000 grad: 0.1403 (0.1511) loss: 0.8245 (0.8155) time: 0.1156 data: 0.0287 max mem: 9390 +Train: [99] [4700/6250] eta: 0:04:11 lr: 0.000000 grad: 0.1359 (0.1508) loss: 0.8137 (0.8156) time: 0.1445 data: 0.0570 max mem: 9390 +Train: [99] [4800/6250] eta: 0:03:55 lr: 0.000000 grad: 0.1433 (0.1506) loss: 0.8179 (0.8156) time: 0.1646 data: 0.0842 max mem: 9390 +Train: [99] [4900/6250] eta: 0:03:38 lr: 0.000000 grad: 0.1479 (0.1505) loss: 0.8180 (0.8156) time: 0.1608 data: 0.0694 max mem: 9390 +Train: [99] [5000/6250] eta: 0:03:22 lr: 0.000000 grad: 0.1337 (0.1504) loss: 0.8162 (0.8157) time: 0.1659 data: 0.0829 max mem: 9390 +Train: [99] [5100/6250] eta: 0:03:06 lr: 0.000000 grad: 0.1381 (0.1503) loss: 0.8161 (0.8157) time: 0.1668 data: 0.0769 max mem: 9390 +Train: [99] [5200/6250] eta: 0:02:50 lr: 0.000000 grad: 0.1358 (0.1502) loss: 0.8220 (0.8157) time: 0.1625 data: 0.0798 max mem: 9390 +Train: [99] [5300/6250] eta: 0:02:33 lr: 0.000000 grad: 0.1330 (0.1500) loss: 0.8189 (0.8158) time: 0.1442 data: 0.0588 max mem: 9390 +Train: [99] [5400/6250] eta: 0:02:17 lr: 0.000000 grad: 0.1238 (0.1498) loss: 0.8274 (0.8158) time: 0.1624 data: 0.0826 max mem: 9390 +Train: [99] [5500/6250] eta: 0:02:01 lr: 0.000000 grad: 0.1463 (0.1498) loss: 0.8105 (0.8158) time: 0.1665 data: 0.0778 max mem: 9390 +Train: [99] [5600/6250] eta: 0:01:45 lr: 0.000000 grad: 0.1468 (0.1497) loss: 0.8131 (0.8158) time: 0.1589 data: 0.0726 max mem: 9390 +Train: [99] [5700/6250] eta: 0:01:28 lr: 0.000000 grad: 0.1361 (0.1496) loss: 0.8181 (0.8158) time: 0.1622 data: 0.0771 max mem: 9390 +Train: [99] [5800/6250] eta: 0:01:12 lr: 0.000000 grad: 0.1397 (0.1495) loss: 0.8139 (0.8158) time: 0.1846 data: 0.0925 max mem: 9390 +Train: [99] [5900/6250] eta: 0:00:56 lr: 0.000000 grad: 0.1449 (0.1494) loss: 0.8157 (0.8158) time: 0.1475 data: 0.0663 max mem: 9390 +Train: [99] [6000/6250] eta: 0:00:40 lr: 0.000000 grad: 0.1346 (0.1492) loss: 0.8248 (0.8159) time: 0.1429 data: 0.0572 max mem: 9390 +Train: [99] [6100/6250] eta: 0:00:24 lr: 0.000000 grad: 0.1466 (0.1492) loss: 0.8212 (0.8159) time: 0.1566 data: 0.0688 max mem: 9390 +Train: [99] [6200/6250] eta: 0:00:08 lr: 0.000000 grad: 0.1413 (0.1492) loss: 0.8161 (0.8159) time: 0.1636 data: 0.0727 max mem: 9390 +Train: [99] [6249/6250] eta: 0:00:00 lr: 0.000000 grad: 0.1398 (0.1491) loss: 0.8169 (0.8160) time: 0.1582 data: 0.0771 max mem: 9390 +Train: [99] Total time: 0:16:55 (0.1626 s / it) +Averaged stats: lr: 0.000000 grad: 0.1398 (0.1491) loss: 0.8169 (0.8160) +Eval (hcp-train-subset): [99] [ 0/62] eta: 0:04:22 loss: 0.8207 (0.8207) time: 4.2313 data: 4.1954 max mem: 9390 +Eval (hcp-train-subset): [99] [61/62] eta: 0:00:00 loss: 0.8118 (0.8139) time: 0.1394 data: 0.1128 max mem: 9390 +Eval (hcp-train-subset): [99] Total time: 0:00:13 (0.2162 s / it) +Averaged stats (hcp-train-subset): loss: 0.8118 (0.8139) +Making plots (hcp-train-subset): example=49 +Eval (hcp-val): [99] [ 0/62] eta: 0:05:26 loss: 0.8254 (0.8254) time: 5.2688 data: 5.2381 max mem: 9390 +Eval (hcp-val): [99] [61/62] eta: 0:00:00 loss: 0.8269 (0.8273) time: 0.1424 data: 0.1175 max mem: 9390 +Eval (hcp-val): [99] Total time: 0:00:13 (0.2102 s / it) +Averaged stats (hcp-val): loss: 0.8269 (0.8273) +Making plots (hcp-val): example=30 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_2/pretrain/checkpoint-last.pth +done! training time: 4:13:05 diff --git a/input_space_v3/flat_lr1e-3_3/eval_v2/aabc_age__patch__logistic/config.yaml b/input_space_v3/flat_lr1e-3_3/eval_v2/aabc_age__patch__logistic/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..cccc2491145e97105617682019368ab46afd2e68 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_3/eval_v2/aabc_age__patch__logistic/config.yaml @@ -0,0 +1,30 @@ +output_root: experiments/input_space_v3/output +name_prefix: eval_logistic +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_3; eval v2 (aabc_age patch logistic) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: input_space_v3/flat_lr1e-3_3/eval_v2/aabc_age__patch__logistic +model: flat_mae +representation: patch +dataset: aabc_age +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/eval_v2/aabc_age__patch__logistic +remote_dir: null diff --git a/input_space_v3/flat_lr1e-3_3/eval_v2/aabc_age__patch__logistic/eval_table.csv b/input_space_v3/flat_lr1e-3_3/eval_v2/aabc_age__patch__logistic/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..5fbe01027bf7d0ff662d623c5737255cb698968b --- /dev/null +++ b/input_space_v3/flat_lr1e-3_3/eval_v2/aabc_age__patch__logistic/eval_table.csv @@ -0,0 +1,203 @@ +model,repr,clf,dataset,trial,C,split,acc,acc_std,f1,f1_std,bacc,bacc_std +flat_mae,patch,logistic,aabc_age,,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,,166.81005372000556,test,0.36538461538461536,0.06620525730389208,0.3650366956818569,0.06613498970437301,0.36217948717948717,0.06582870901094266 +flat_mae,patch,logistic,aabc_age,1,0.046415888336127774,train,0.8149606299212598,0.016474665241794417,0.8154234223333602,0.01655620859577547,0.8165991467023661,0.016397607980896192 +flat_mae,patch,logistic,aabc_age,1,0.046415888336127774,test,0.4423076923076923,0.05982469459044682,0.4212962962962963,0.05589375587860719,0.4356684981684982,0.05875185573125088 +flat_mae,patch,logistic,aabc_age,2,0.000774263682681127,train,0.5610236220472441,0.020208579731722593,0.5536055646152016,0.0207277636147479,0.5607637723465588,0.020222999606634696 +flat_mae,patch,logistic,aabc_age,2,0.000774263682681127,test,0.5384615384615384,0.06753429985425725,0.5329697106012896,0.06887958646280781,0.5338827838827839,0.06740223478994882 +flat_mae,patch,logistic,aabc_age,3,0.005994842503189409,train,0.6811023622047244,0.020235032824611546,0.6798030367693493,0.02059438414571321,0.6814162506305274,0.02031281062851396 +flat_mae,patch,logistic,aabc_age,3,0.005994842503189409,test,0.4807692307692308,0.06416740310548476,0.4720912599944858,0.06514598349634758,0.4759615384615385,0.06410598786644263 +flat_mae,patch,logistic,aabc_age,4,9.999999999999999e-05,train,0.4881889763779528,0.02046880646115146,0.45111830101585615,0.021084612362272756,0.48406468107305684,0.020307407362149036 +flat_mae,patch,logistic,aabc_age,4,9.999999999999999e-05,test,0.5192307692307693,0.061156639994236234,0.47015056022408963,0.06254179823744715,0.5084706959706959,0.060090611717238715 +flat_mae,patch,logistic,aabc_age,5,9.999999999999999e-05,train,0.4881889763779528,0.02004856270134427,0.4560342535694648,0.020733208245363767,0.48438222229467826,0.019906853762104597 +flat_mae,patch,logistic,aabc_age,5,9.999999999999999e-05,test,0.38461538461538464,0.058888559381559874,0.34205665024630544,0.050216259709214485,0.3791208791208791,0.057506060634693525 +flat_mae,patch,logistic,aabc_age,6,0.005994842503189409,train,0.6437007874015748,0.02028337706918576,0.6424460533787412,0.02039094812962437,0.6437801238614547,0.020256955867786374 +flat_mae,patch,logistic,aabc_age,6,0.005994842503189409,test,0.5384615384615384,0.06736740208665705,0.5361471861471861,0.06768965421874146,0.5366300366300366,0.06742560482850331 +flat_mae,patch,logistic,aabc_age,7,0.046415888336127774,train,0.812992125984252,0.016598686665902137,0.8128430708202069,0.016749910900520876,0.813177637042592,0.01663300569983496 +flat_mae,patch,logistic,aabc_age,7,0.046415888336127774,test,0.40384615384615385,0.06490661247665962,0.4006577480490524,0.06239032733339668,0.4001831501831502,0.06422443637663307 +flat_mae,patch,logistic,aabc_age,8,0.046415888336127774,train,0.797244094488189,0.01879043535048939,0.7970036271191221,0.018885463496708974,0.7973837672064429,0.018811667139510536 +flat_mae,patch,logistic,aabc_age,8,0.046415888336127774,test,0.5384615384615384,0.06304026843048008,0.5313755837949385,0.0659415650144414,0.5412087912087912,0.06331860352933869 +flat_mae,patch,logistic,aabc_age,9,0.046415888336127774,train,0.8149606299212598,0.01764669348097771,0.8154388276529612,0.01773733843760943,0.815411333956029,0.017650497837530962 +flat_mae,patch,logistic,aabc_age,9,0.046415888336127774,test,0.4423076923076923,0.06630858468077014,0.44606349120725,0.06464359846291891,0.43887362637362637,0.06618357951602477 +flat_mae,patch,logistic,aabc_age,10,0.005994842503189409,train,0.65748031496063,0.02000833108149267,0.6568130498137892,0.020248265000721462,0.6580929737681462,0.02002511176042052 +flat_mae,patch,logistic,aabc_age,10,0.005994842503189409,test,0.46153846153846156,0.06519496250550862,0.4561050800531866,0.06491409856598622,0.45810439560439564,0.06494615419032937 +flat_mae,patch,logistic,aabc_age,11,0.000774263682681127,train,0.5570866141732284,0.021154464706599256,0.5498774172097209,0.021548003685676727,0.5567315142820428,0.021114169586781452 +flat_mae,patch,logistic,aabc_age,11,0.000774263682681127,test,0.5192307692307693,0.06532445195842548,0.5064727279800809,0.069315251380239,0.5144230769230769,0.06521845068299512 +flat_mae,patch,logistic,aabc_age,12,0.005994842503189409,train,0.6771653543307087,0.020867940793041984,0.6748490702813296,0.021117115239647762,0.677116438014611,0.020838912833039205 +flat_mae,patch,logistic,aabc_age,12,0.005994842503189409,test,0.4423076923076923,0.06494963911602415,0.4419642857142857,0.0648281892021364,0.43887362637362637,0.06469942338065637 +flat_mae,patch,logistic,aabc_age,13,9.999999999999999e-05,train,0.5118110236220472,0.019754787850120945,0.4857119269752722,0.020659029183674873,0.5083905682705235,0.019633238554322446 +flat_mae,patch,logistic,aabc_age,13,9.999999999999999e-05,test,0.40384615384615385,0.05683381775172847,0.3684077079107505,0.04811405820416629,0.3956043956043956,0.05544308465257663 +flat_mae,patch,logistic,aabc_age,14,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,14,21.54434690031882,test,0.4423076923076923,0.06123874126688646,0.4244318181818182,0.06178028723408098,0.4429945054945055,0.0613966954290129 +flat_mae,patch,logistic,aabc_age,15,0.005994842503189409,train,0.6732283464566929,0.01947228492857889,0.6707867920312975,0.019783598257943426,0.672866612068916,0.019537920577541192 +flat_mae,patch,logistic,aabc_age,15,0.005994842503189409,test,0.46153846153846156,0.06974657209875355,0.4638720538720539,0.06916689783906864,0.46108058608058605,0.06981244169402016 +flat_mae,patch,logistic,aabc_age,16,0.005994842503189409,train,0.6456692913385826,0.02040228591375342,0.642593089181544,0.020636165498660895,0.6447760213583331,0.02035237416758065 +flat_mae,patch,logistic,aabc_age,16,0.005994842503189409,test,0.4423076923076923,0.06358384484634275,0.4378563964770861,0.06582689951633297,0.43887362637362637,0.06322654688994395 +flat_mae,patch,logistic,aabc_age,17,0.000774263682681127,train,0.5767716535433071,0.02107178416841289,0.572043591054823,0.021843912467832235,0.5767575888635932,0.021067098698278726 +flat_mae,patch,logistic,aabc_age,17,0.000774263682681127,test,0.4807692307692308,0.058203517147024916,0.4373015873015873,0.05820808952987053,0.475503663003663,0.05724211519129262 +flat_mae,patch,logistic,aabc_age,18,0.000774263682681127,train,0.5511811023622047,0.020785052658986166,0.544753834323313,0.02109381594011029,0.5509006950664475,0.02074082730015225 +flat_mae,patch,logistic,aabc_age,18,0.000774263682681127,test,0.5,0.058216846216812126,0.4654716725399838,0.05737680250207652,0.4933608058608059,0.057399777464636356 +flat_mae,patch,logistic,aabc_age,19,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,19,166.81005372000556,test,0.40384615384615385,0.06936460354425787,0.41407867494824013,0.069566940008961,0.4049908424908425,0.06977092292359788 +flat_mae,patch,logistic,aabc_age,20,0.005994842503189409,train,0.6515748031496063,0.021307169180604855,0.6511015974812668,0.021448261421161477,0.6525297091039511,0.021262010733864346 +flat_mae,patch,logistic,aabc_age,20,0.005994842503189409,test,0.4807692307692308,0.0556044116209854,0.4527058962542833,0.058005795206363106,0.47847985347985345,0.05559058148367466 +flat_mae,patch,logistic,aabc_age,21,0.005994842503189409,train,0.6653543307086615,0.019847616440161194,0.6627779036560196,0.020160340610628425,0.66491969048062,0.019863843552505964 +flat_mae,patch,logistic,aabc_age,21,0.005994842503189409,test,0.46153846153846156,0.06594935971893341,0.4481601731601731,0.06582506910206148,0.4668040293040293,0.06692899263432617 +flat_mae,patch,logistic,aabc_age,22,0.000774263682681127,train,0.5669291338582677,0.02016145499383749,0.5589710437101946,0.02050088250465937,0.5666445782323755,0.020154143051592216 +flat_mae,patch,logistic,aabc_age,22,0.000774263682681127,test,0.40384615384615385,0.06737929158807804,0.41061006658832744,0.06796626017695821,0.4036172161172161,0.06768330698564361 +flat_mae,patch,logistic,aabc_age,23,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,23,2.782559402207126,test,0.4423076923076923,0.060605170459215214,0.4493131868131868,0.05861586240288008,0.4416208791208791,0.06065515642054557 +flat_mae,patch,logistic,aabc_age,24,0.046415888336127774,train,0.8228346456692913,0.017335224631369096,0.8228103091066907,0.01746145684666958,0.8235258367552825,0.017289650526802865 +flat_mae,patch,logistic,aabc_age,24,0.046415888336127774,test,0.4230769230769231,0.06378240561684852,0.4246794871794872,0.06324005302965884,0.42399267399267393,0.06391519696217829 +flat_mae,patch,logistic,aabc_age,25,9.999999999999999e-05,train,0.5216535433070866,0.02025040825904677,0.49660266577298795,0.020729949750999524,0.518738767983214,0.020117375859339207 +flat_mae,patch,logistic,aabc_age,25,9.999999999999999e-05,test,0.34615384615384615,0.057022574165825256,0.302522349936143,0.04873206115468315,0.34065934065934067,0.055881604426856316 +flat_mae,patch,logistic,aabc_age,26,0.000774263682681127,train,0.5708661417322834,0.0216205514591208,0.5643525202700743,0.021987881832941043,0.5705092550859339,0.02149961897858423 +flat_mae,patch,logistic,aabc_age,26,0.000774263682681127,test,0.4423076923076923,0.06464724489248827,0.4319389978213508,0.0645925858345282,0.43727106227106227,0.06425549637015895 +flat_mae,patch,logistic,aabc_age,27,9.999999999999999e-05,train,0.49803149606299213,0.019694238401777617,0.46015496179399396,0.02026779090546003,0.49436289411552603,0.01951190492496779 +flat_mae,patch,logistic,aabc_age,27,9.999999999999999e-05,test,0.3269230769230769,0.056234715214592064,0.2718715393133998,0.0472103635357678,0.3173076923076923,0.054481865225499235 +flat_mae,patch,logistic,aabc_age,28,0.046415888336127774,train,0.812992125984252,0.017318275616970073,0.8127173776564021,0.01757672010090293,0.8133452182535497,0.017323312513871196 +flat_mae,patch,logistic,aabc_age,28,0.046415888336127774,test,0.5192307692307693,0.06397821143531239,0.5075051759834368,0.06722891134038755,0.5187728937728938,0.06412329109404576 +flat_mae,patch,logistic,aabc_age,29,0.005994842503189409,train,0.6594488188976378,0.02007585705717376,0.6570405182078543,0.020357990160669075,0.6597415749085616,0.02002560882238659 +flat_mae,patch,logistic,aabc_age,29,0.005994842503189409,test,0.4807692307692308,0.065631783954794,0.4876018808777429,0.06462681640753505,0.4832875457875458,0.06620319957237059 +flat_mae,patch,logistic,aabc_age,30,0.005994842503189409,train,0.6535433070866141,0.02114818264038918,0.6522121092166266,0.021487754229074847,0.6533080387196508,0.02123617632801749 +flat_mae,patch,logistic,aabc_age,30,0.005994842503189409,test,0.5192307692307693,0.07059614074974209,0.5314478114478114,0.06887965172253718,0.5206043956043955,0.07048463243010714 +flat_mae,patch,logistic,aabc_age,31,9.999999999999999e-05,train,0.49015748031496065,0.019180660736676736,0.44728276244479276,0.018987837955072424,0.48549571433229316,0.019025666916377273 +flat_mae,patch,logistic,aabc_age,31,9.999999999999999e-05,test,0.5384615384615384,0.05848707691174584,0.4875457875457875,0.059812608937825994,0.5277014652014652,0.05762843748334259 +flat_mae,patch,logistic,aabc_age,32,9.999999999999999e-05,train,0.48031496062992124,0.020277033432338408,0.44115260948572776,0.02068609768050414,0.47611775948476087,0.020075089801886836 +flat_mae,patch,logistic,aabc_age,32,9.999999999999999e-05,test,0.4423076923076923,0.05226242385065548,0.3750915750915751,0.04712294688930005,0.43543956043956045,0.05089968099467084 +flat_mae,patch,logistic,aabc_age,33,0.005994842503189409,train,0.6653543307086615,0.019458330343409214,0.6638774727095483,0.01977477636870202,0.6652372317022415,0.019420296219761796 +flat_mae,patch,logistic,aabc_age,33,0.005994842503189409,test,0.5192307692307693,0.06225870581456173,0.5229646215853112,0.061202225127880296,0.5233516483516483,0.06300932590323621 +flat_mae,patch,logistic,aabc_age,34,0.005994842503189409,train,0.639763779527559,0.021045176069562153,0.6374963308451307,0.021367605498060733,0.6407857185326119,0.02090943362058202 +flat_mae,patch,logistic,aabc_age,34,0.005994842503189409,test,0.4807692307692308,0.06789196952974055,0.48930481283422456,0.06945420199554292,0.48076923076923084,0.06811872850244728 +flat_mae,patch,logistic,aabc_age,35,0.005994842503189409,train,0.6614173228346457,0.02021063059231894,0.6590123958545011,0.020595837222621902,0.6610550136270616,0.02026463940301445 +flat_mae,patch,logistic,aabc_age,35,0.005994842503189409,test,0.38461538461538464,0.0644353719610845,0.37812500000000004,0.06353842871220462,0.38095238095238093,0.0638966468471451 +flat_mae,patch,logistic,aabc_age,36,0.3593813663804626,train,0.9763779527559056,0.006659223918034787,0.9766074969649527,0.0066030763035777205,0.976961898889313,0.006512337190687765 +flat_mae,patch,logistic,aabc_age,36,0.3593813663804626,test,0.5,0.0609595243540126,0.469094315321117,0.0632703770450332,0.49633699633699635,0.06059205142107227 +flat_mae,patch,logistic,aabc_age,37,0.005994842503189409,train,0.6594488188976378,0.02134995629131984,0.6588535708601497,0.0215422336601973,0.660276684011362,0.021392937738461782 +flat_mae,patch,logistic,aabc_age,37,0.005994842503189409,test,0.5192307692307693,0.06476323515096304,0.5164507274481699,0.06662854755185013,0.5148809523809524,0.06494332014075618 +flat_mae,patch,logistic,aabc_age,38,0.000774263682681127,train,0.5551181102362205,0.020662831761528534,0.5470969812303262,0.021045026427801237,0.5557532379854581,0.020653127418012486 +flat_mae,patch,logistic,aabc_age,38,0.000774263682681127,test,0.5384615384615384,0.0633364618245265,0.5287047511312217,0.06619469736386072,0.5322802197802198,0.06305212561593228 +flat_mae,patch,logistic,aabc_age,39,0.005994842503189409,train,0.6673228346456693,0.02031763090550302,0.6651881835921291,0.020463270181032295,0.6675885231564148,0.02025133775815251 +flat_mae,patch,logistic,aabc_age,39,0.005994842503189409,test,0.4807692307692308,0.06641023661023365,0.45883699633699637,0.06779852829603082,0.47298534798534797,0.06580751401114761 +flat_mae,patch,logistic,aabc_age,40,0.005994842503189409,train,0.6633858267716536,0.0202206518131716,0.6612228488810767,0.020443801849342594,0.6638738063135202,0.020245307795252118 +flat_mae,patch,logistic,aabc_age,40,0.005994842503189409,test,0.4423076923076923,0.062413537827477876,0.4233351578179164,0.0620791271764868,0.440018315018315,0.06230876339327421 +flat_mae,patch,logistic,aabc_age,41,0.005994842503189409,train,0.6653543307086615,0.020981648432836304,0.6650028414849127,0.021128083369807538,0.6657723408050419,0.021006891475436128 +flat_mae,patch,logistic,aabc_age,41,0.005994842503189409,test,0.4423076923076923,0.06423250803726566,0.42189976689976694,0.06740276687323588,0.4416208791208791,0.06433146840169637 +flat_mae,patch,logistic,aabc_age,42,0.005994842503189409,train,0.6673228346456693,0.01988834034282809,0.6655225621961333,0.020111995532429892,0.6678560777078151,0.019852801696609523 +flat_mae,patch,logistic,aabc_age,42,0.005994842503189409,test,0.5,0.06590439327734106,0.489673345145609,0.06855910186283821,0.5057234432234432,0.06633396874500345 +flat_mae,patch,logistic,aabc_age,43,0.005994842503189409,train,0.6732283464566929,0.019854032093385484,0.6710217248039164,0.020098334457905893,0.6744395739073897,0.019800524929284104 +flat_mae,patch,logistic,aabc_age,43,0.005994842503189409,test,0.46153846153846156,0.06690256095787286,0.45046574115539634,0.06780024339835107,0.45970695970695974,0.06697064348517025 +flat_mae,patch,logistic,aabc_age,44,0.005994842503189409,train,0.6535433070866141,0.019035261665718537,0.6507290591728269,0.01928336739005861,0.6535432278011235,0.019065426663601556 +flat_mae,patch,logistic,aabc_age,44,0.005994842503189409,test,0.5192307692307693,0.06800708064423497,0.5165673981191223,0.06974559867041524,0.5208333333333334,0.06829083664435515 +flat_mae,patch,logistic,aabc_age,45,0.000774263682681127,train,0.5669291338582677,0.01994575382546849,0.5554581654767128,0.021029869911963758,0.5650892375941956,0.019890493441892868 +flat_mae,patch,logistic,aabc_age,45,0.000774263682681127,test,0.4230769230769231,0.06141587549904023,0.4127227884033692,0.062239643005933216,0.4237637362637363,0.06146110579069848 +flat_mae,patch,logistic,aabc_age,46,0.000774263682681127,train,0.5551181102362205,0.021218967340310174,0.5488980993679362,0.021713938087768093,0.554765371920006,0.02120725559131429 +flat_mae,patch,logistic,aabc_age,46,0.000774263682681127,test,0.5384615384615384,0.06371138463841748,0.5233860342555995,0.06697060642511267,0.5322802197802198,0.0634183695522604 +flat_mae,patch,logistic,aabc_age,47,0.000774263682681127,train,0.5708661417322834,0.02059113796005273,0.5632177380810697,0.021021588327920913,0.5706768362968916,0.020601999591334075 +flat_mae,patch,logistic,aabc_age,47,0.000774263682681127,test,0.4230769230769231,0.06100027888189233,0.39786967418546365,0.0642118536791946,0.41804029304029305,0.060395222628446474 +flat_mae,patch,logistic,aabc_age,48,0.005994842503189409,train,0.6673228346456693,0.021603673424614875,0.6658392847727945,0.02180333397662939,0.6667682383019204,0.021589726384209716 +flat_mae,patch,logistic,aabc_age,48,0.005994842503189409,test,0.5,0.06789317880178133,0.5005411255411255,0.07086623404869163,0.4967948717948718,0.06777350787558592 +flat_mae,patch,logistic,aabc_age,49,0.005994842503189409,train,0.6673228346456693,0.020083033352968807,0.6644870617297574,0.02042144736834927,0.6671034007238358,0.02008154712466635 +flat_mae,patch,logistic,aabc_age,49,0.005994842503189409,test,0.40384615384615385,0.061178405808570285,0.3883972374374851,0.05842972621448846,0.39720695970695974,0.06046576656719725 +flat_mae,patch,logistic,aabc_age,50,0.046415888336127774,train,0.8149606299212598,0.017154650639522703,0.814917269154062,0.01727760481163078,0.8155789151669866,0.01702760792265155 +flat_mae,patch,logistic,aabc_age,50,0.046415888336127774,test,0.4230769230769231,0.06729132768095077,0.42440476190476195,0.06731428979498298,0.4198717948717948,0.06695531987190254 +flat_mae,patch,logistic,aabc_age,51,0.046415888336127774,train,0.8307086614173228,0.016062321952207696,0.8297989598532298,0.0163099865535915,0.8325605977494731,0.01588428783892186 +flat_mae,patch,logistic,aabc_age,51,0.046415888336127774,test,0.5,0.07129316921228401,0.4960109231098736,0.07230914442456858,0.49977106227106227,0.07124164075790278 +flat_mae,patch,logistic,aabc_age,52,0.000774263682681127,train,0.5728346456692913,0.020488096300637106,0.5631485792574109,0.021410034653029406,0.5719402883451703,0.020433462351534884 +flat_mae,patch,logistic,aabc_age,52,0.000774263682681127,test,0.38461538461538464,0.06472591279373546,0.38003663003663,0.06552754823548834,0.38118131868131866,0.06436768871950835 +flat_mae,patch,logistic,aabc_age,53,9.999999999999999e-05,train,0.4921259842519685,0.02057826789188582,0.47095110472886514,0.0210154773841775,0.48941709069428013,0.020424962883087743 +flat_mae,patch,logistic,aabc_age,53,9.999999999999999e-05,test,0.5384615384615384,0.05654950180015872,0.49775124069478904,0.05583275777708156,0.530448717948718,0.05560941715237431 +flat_mae,patch,logistic,aabc_age,54,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,54,2.782559402207126,test,0.4423076923076923,0.06882465285227879,0.4387926887926888,0.06897070880612334,0.4450549450549451,0.0689131433245207 +flat_mae,patch,logistic,aabc_age,55,0.000774263682681127,train,0.5610236220472441,0.021336917737295534,0.5508088919729335,0.021942704012848032,0.5606637990061163,0.021284404106425753 +flat_mae,patch,logistic,aabc_age,55,0.000774263682681127,test,0.4423076923076923,0.06469893865220583,0.43281657490582437,0.06602172636068064,0.44299450549450553,0.06483723506368402 +flat_mae,patch,logistic,aabc_age,56,9.999999999999999e-05,train,0.5059055118110236,0.01962458867719172,0.47668454799138205,0.020204175068090656,0.5013719363085911,0.01954202720542595 +flat_mae,patch,logistic,aabc_age,56,9.999999999999999e-05,test,0.4230769230769231,0.06456649936489267,0.4004621848739496,0.06677528976417386,0.41941391941391937,0.0641425038759074 +flat_mae,patch,logistic,aabc_age,57,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,57,2.782559402207126,test,0.4807692307692308,0.06275193011954143,0.46963684463684463,0.062000227558525085,0.47870879120879123,0.06250826173440455 +flat_mae,patch,logistic,aabc_age,58,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,58,2.782559402207126,test,0.38461538461538464,0.0604892650263826,0.3579831932773109,0.06104941533845162,0.37797619047619047,0.059647966757503286 +flat_mae,patch,logistic,aabc_age,59,0.3593813663804626,train,0.9763779527559056,0.006786372713733707,0.9767313399463371,0.00668176951611812,0.9764767764567338,0.006741384017994475 +flat_mae,patch,logistic,aabc_age,59,0.3593813663804626,test,0.40384615384615385,0.06764526337301625,0.4129440961337513,0.06711780623566589,0.4049908424908425,0.06776775946083288 +flat_mae,patch,logistic,aabc_age,60,0.005994842503189409,train,0.6496062992125984,0.021712767612364736,0.6470078549993868,0.02211826225269452,0.6497285376177864,0.02165509117872066 +flat_mae,patch,logistic,aabc_age,60,0.005994842503189409,test,0.4230769230769231,0.06101915500977139,0.4160830403817781,0.06304045292777831,0.4223901098901099,0.06095404752987991 +flat_mae,patch,logistic,aabc_age,61,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,61,166.81005372000556,test,0.40384615384615385,0.06705641006031798,0.4004446640316206,0.06757002306934394,0.39903846153846156,0.06688467149687251 +flat_mae,patch,logistic,aabc_age,62,0.005994842503189409,train,0.6673228346456693,0.020375090693997948,0.665054856109107,0.02076355549278977,0.6676884964968575,0.020460324005309324 +flat_mae,patch,logistic,aabc_age,62,0.005994842503189409,test,0.5,0.06455320955541503,0.4958998588030846,0.0633150492999732,0.4951923076923077,0.06430632583088487 +flat_mae,patch,logistic,aabc_age,63,0.005994842503189409,train,0.6830708661417323,0.01939821391472436,0.681953439865174,0.019530987020580922,0.6824445135973333,0.019457775026957898 +flat_mae,patch,logistic,aabc_age,63,0.005994842503189409,test,0.40384615384615385,0.06256551595713288,0.3957729468599034,0.06199428942826261,0.40453296703296704,0.0628698533844527 +flat_mae,patch,logistic,aabc_age,64,0.005994842503189409,train,0.6830708661417323,0.019770327051712198,0.6809600409463921,0.02011019927533987,0.6827796760192486,0.019811543748332855 +flat_mae,patch,logistic,aabc_age,64,0.005994842503189409,test,0.4423076923076923,0.06432738012945596,0.4473578595317726,0.06337807072626256,0.44047619047619047,0.06414402484898052 +flat_mae,patch,logistic,aabc_age,65,0.046415888336127774,train,0.8051181102362205,0.017406374707668468,0.8059968978236861,0.017336769904642692,0.8070536106438763,0.017314546980748618 +flat_mae,patch,logistic,aabc_age,65,0.046415888336127774,test,0.4807692307692308,0.06795181899067906,0.4802134646962233,0.06828061152266963,0.4775641025641026,0.06758840880179856 +flat_mae,patch,logistic,aabc_age,66,0.046415888336127774,train,0.8110236220472441,0.01744277154011247,0.8111700647402811,0.017547763036452026,0.8115966437726918,0.01741171533836764 +flat_mae,patch,logistic,aabc_age,66,0.046415888336127774,test,0.38461538461538464,0.05877269170236147,0.362983312983313,0.05481960649147857,0.38804945054945056,0.0595749877267414 +flat_mae,patch,logistic,aabc_age,67,0.046415888336127774,train,0.8070866141732284,0.01731674911002637,0.8079127491706607,0.017415241358621603,0.8069616687348601,0.01738172517837894 +flat_mae,patch,logistic,aabc_age,67,0.046415888336127774,test,0.5,0.049858661180125524,0.4358974358974359,0.04488571430531685,0.49313186813186816,0.048381339145155605 +flat_mae,patch,logistic,aabc_age,68,0.046415888336127774,train,0.8149606299212598,0.017634541671223535,0.81447967609896,0.017796346468347,0.8158964563886081,0.017616530266349344 +flat_mae,patch,logistic,aabc_age,68,0.046415888336127774,test,0.4230769230769231,0.061208381585624055,0.414686887325568,0.060471723530721576,0.4237637362637363,0.06158857687824521 +flat_mae,patch,logistic,aabc_age,69,0.000774263682681127,train,0.5570866141732284,0.01951846808643528,0.5458723151823471,0.02003727763933947,0.5571842712446944,0.019464829442876964 +flat_mae,patch,logistic,aabc_age,69,0.000774263682681127,test,0.40384615384615385,0.06313481161664952,0.3911877394636015,0.06324951018985656,0.4015567765567766,0.06277843518532499 +flat_mae,patch,logistic,aabc_age,70,0.3593813663804626,train,0.9744094488188977,0.006719349135095295,0.9744356508381754,0.006706503843955245,0.9746282286354335,0.006663689283198618 +flat_mae,patch,logistic,aabc_age,70,0.3593813663804626,test,0.46153846153846156,0.0612429805179491,0.45675620675620676,0.06215219059637828,0.4674908424908425,0.06152747746652749 +flat_mae,patch,logistic,aabc_age,71,0.005994842503189409,train,0.6535433070866141,0.021680118266629828,0.6520384814206653,0.02183058783596205,0.6534756199306084,0.021701330532978118 +flat_mae,patch,logistic,aabc_age,71,0.005994842503189409,test,0.4423076923076923,0.06314555365776407,0.44116300366300365,0.06191998606988123,0.44459706959706957,0.06369399838315967 +flat_mae,patch,logistic,aabc_age,72,0.3593813663804626,train,0.968503937007874,0.007523558181329886,0.9684953432392995,0.007529506087331414,0.9685798415386593,0.007511689356017056 +flat_mae,patch,logistic,aabc_age,72,0.3593813663804626,test,0.5384615384615384,0.0642926348768526,0.5268147981051207,0.06672373445324699,0.5352564102564102,0.06429537515428509 +flat_mae,patch,logistic,aabc_age,73,0.005994842503189409,train,0.65748031496063,0.02016569522259344,0.6569035287503602,0.020131732216291706,0.6578254192167461,0.020099855304959554 +flat_mae,patch,logistic,aabc_age,73,0.005994842503189409,test,0.5,0.06306594651210314,0.5026171529619805,0.06226223594232982,0.502518315018315,0.0632445397425038 +flat_mae,patch,logistic,aabc_age,74,0.046415888336127774,train,0.8070866141732284,0.01686603512762503,0.8065244075600075,0.0170651982175087,0.8072468444865541,0.01683429721339952 +flat_mae,patch,logistic,aabc_age,74,0.046415888336127774,test,0.4230769230769231,0.06916022046432875,0.4312025534851622,0.07001092635909684,0.42147435897435903,0.06925700799598918 +flat_mae,patch,logistic,aabc_age,75,0.005994842503189409,train,0.6673228346456693,0.019864331141100713,0.666103251639383,0.019978758316827976,0.6681236322592152,0.01989321384454205 +flat_mae,patch,logistic,aabc_age,75,0.005994842503189409,test,0.5384615384615384,0.0700952859500982,0.5445512820512821,0.07001398084543628,0.5398351648351648,0.07028346986551098 +flat_mae,patch,logistic,aabc_age,76,0.046415888336127774,train,0.8248031496062992,0.016557027519162982,0.8253520083348629,0.01652103606916473,0.8258595070091621,0.016558169014436828 +flat_mae,patch,logistic,aabc_age,76,0.046415888336127774,test,0.46153846153846156,0.06722306768068806,0.4603846153846154,0.06788499669420045,0.46565934065934067,0.06765160304876516 +flat_mae,patch,logistic,aabc_age,77,9.999999999999999e-05,train,0.5118110236220472,0.01986743022963886,0.4736458445412705,0.020253561356433126,0.5070028088433013,0.01964324559949952 +flat_mae,patch,logistic,aabc_age,77,9.999999999999999e-05,test,0.36538461538461536,0.05779696916768573,0.32604679802955666,0.048270664377570834,0.3598901098901099,0.05639427090232659 +flat_mae,patch,logistic,aabc_age,78,0.046415888336127774,train,0.8149606299212598,0.016855122965743676,0.8142988716522715,0.017138925725590372,0.8167167412431026,0.01667660313824316 +flat_mae,patch,logistic,aabc_age,78,0.046415888336127774,test,0.4807692307692308,0.06745819437374291,0.4771208995346926,0.06801848249642121,0.4789377289377289,0.06765857224143541 +flat_mae,patch,logistic,aabc_age,79,0.000774263682681127,train,0.5669291338582677,0.021155701114058567,0.5570075324428808,0.021607390345190613,0.5667121861028905,0.021043738403950046 +flat_mae,patch,logistic,aabc_age,79,0.000774263682681127,test,0.5384615384615384,0.06132041900527301,0.5229166666666667,0.06342142494094022,0.5336538461538461,0.06111353749106224 +flat_mae,patch,logistic,aabc_age,80,0.046415888336127774,train,0.8149606299212598,0.01627098005621,0.8158708488067653,0.016323082723540393,0.8172842158158304,0.016214793168698616 +flat_mae,patch,logistic,aabc_age,80,0.046415888336127774,test,0.4807692307692308,0.06213466002426794,0.46875,0.06441715745825462,0.48168498168498164,0.062196716276203906 +flat_mae,patch,logistic,aabc_age,81,0.3593813663804626,train,0.9744094488188977,0.006571883929233462,0.9741785301762157,0.006671025449285911,0.9743606740840332,0.006645075425940432 +flat_mae,patch,logistic,aabc_age,81,0.3593813663804626,test,0.4807692307692308,0.06756818821880307,0.4840802675585284,0.06769285272785192,0.48054029304029305,0.06768852432247319 +flat_mae,patch,logistic,aabc_age,82,0.005994842503189409,train,0.6594488188976378,0.020599394376294117,0.6581662899552231,0.020804408722526438,0.6600591161301831,0.02060767637288664 +flat_mae,patch,logistic,aabc_age,82,0.005994842503189409,test,0.4807692307692308,0.06353411933384004,0.4674912810974192,0.06414869461062706,0.48305860805860806,0.0639978898189623 +flat_mae,patch,logistic,aabc_age,83,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,83,166.81005372000556,test,0.34615384615384615,0.06118775064015973,0.34989010989010993,0.05974570763283775,0.3498168498168498,0.06182422215122304 +flat_mae,patch,logistic,aabc_age,84,0.005994842503189409,train,0.6456692913385826,0.021314064349125868,0.6448732851402537,0.021399129105377158,0.6454610904717974,0.021275341383897712 +flat_mae,patch,logistic,aabc_age,84,0.005994842503189409,test,0.5576923076923077,0.05863702154661326,0.5331854106902407,0.063184459466838,0.5528846153846154,0.058231281373536135 +flat_mae,patch,logistic,aabc_age,85,0.005994842503189409,train,0.6653543307086615,0.02057157215380395,0.6638049915846005,0.020887106016873953,0.6652372317022415,0.020551676663317326 +flat_mae,patch,logistic,aabc_age,85,0.005994842503189409,test,0.4230769230769231,0.06034937727332493,0.4072304935208161,0.061063942486436,0.4237637362637363,0.060252078896384904 +flat_mae,patch,logistic,aabc_age,86,0.046415888336127774,train,0.8169291338582677,0.016346063651154468,0.8166113958291836,0.01650624550012951,0.8176450308694659,0.016320425775842133 +flat_mae,patch,logistic,aabc_age,86,0.046415888336127774,test,0.5384615384615384,0.0634321493721007,0.5187100893997445,0.0664927516849539,0.5336538461538461,0.06314864582756859 +flat_mae,patch,logistic,aabc_age,87,0.046415888336127774,train,0.8228346456692913,0.016347485952910124,0.8234536056788857,0.01636431144833215,0.8236757967659463,0.01633672429447702 +flat_mae,patch,logistic,aabc_age,87,0.046415888336127774,test,0.4423076923076923,0.06289160158793747,0.4328439153439153,0.0625246485175888,0.44459706959706957,0.06350229247900603 +flat_mae,patch,logistic,aabc_age,88,0.005994842503189409,train,0.6535433070866141,0.01933334010346064,0.6508137329701595,0.019612997967645814,0.6542459181148816,0.019256811153351892 +flat_mae,patch,logistic,aabc_age,88,0.005994842503189409,test,0.4423076923076923,0.06406011414953981,0.4401768346595933,0.06479329919409826,0.4448260073260073,0.0643696956478833 +flat_mae,patch,logistic,aabc_age,89,9.999999999999999e-05,train,0.5098425196850394,0.02054967676335641,0.4802927362839389,0.02124696786633579,0.506056898016644,0.020457787124991255 +flat_mae,patch,logistic,aabc_age,89,9.999999999999999e-05,test,0.38461538461538464,0.06273646392111563,0.3546130952380952,0.061429227676595914,0.3807234432234432,0.06192777078794661 +flat_mae,patch,logistic,aabc_age,90,0.005994842503189409,train,0.655511811023622,0.021312262583430067,0.6531016339022875,0.021557589239892545,0.655174207741245,0.021342752355843025 +flat_mae,patch,logistic,aabc_age,90,0.005994842503189409,test,0.5,0.06122288072494102,0.4809523809523809,0.0637736598826827,0.4993131868131868,0.061041988981768776 +flat_mae,patch,logistic,aabc_age,91,0.000774263682681127,train,0.562992125984252,0.021961304665201582,0.5501632141878144,0.022327634166049545,0.5613421552813733,0.021811630139353035 +flat_mae,patch,logistic,aabc_age,91,0.000774263682681127,test,0.46153846153846156,0.06519184252159888,0.448656015037594,0.06952225271160185,0.4624542124542125,0.06563985865507282 +flat_mae,patch,logistic,aabc_age,92,0.000774263682681127,train,0.5748031496062992,0.02096209219802781,0.5673466189875802,0.02175209758875954,0.5734536737445554,0.020987671588355978 +flat_mae,patch,logistic,aabc_age,92,0.000774263682681127,test,0.4423076923076923,0.05556555646341318,0.39701692642869113,0.05599130541834791,0.4397893772893773,0.055052219476579886 +flat_mae,patch,logistic,aabc_age,93,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,93,2.782559402207126,test,0.4423076923076923,0.06931912097354076,0.46216210076779796,0.06554069068899719,0.44482600732600736,0.06961680637583775 +flat_mae,patch,logistic,aabc_age,94,0.000774263682681127,train,0.5748031496062992,0.022110433560709394,0.5675772588972148,0.022659111814928343,0.5743739319394925,0.02205187074157588 +flat_mae,patch,logistic,aabc_age,94,0.000774263682681127,test,0.38461538461538464,0.057488601906051144,0.36666979010494755,0.059493109437784984,0.38369963369963367,0.0575602766711752 +flat_mae,patch,logistic,aabc_age,95,0.046415888336127774,train,0.812992125984252,0.017364184721138556,0.813339988685303,0.017504616498068098,0.8138803273563501,0.017298219039770694 +flat_mae,patch,logistic,aabc_age,95,0.046415888336127774,test,0.5192307692307693,0.06633529454050195,0.5123968784838351,0.06486264541457161,0.5130494505494505,0.06600215711645958 +flat_mae,patch,logistic,aabc_age,96,0.005994842503189409,train,0.639763779527559,0.021215379284486913,0.6390342405772158,0.021378527661238655,0.6396802579264235,0.021167387394985318 +flat_mae,patch,logistic,aabc_age,96,0.005994842503189409,test,0.4807692307692308,0.06516406240855306,0.47046091163738224,0.06711561339362196,0.47619047619047616,0.065059207688111 +flat_mae,patch,logistic,aabc_age,97,0.005994842503189409,train,0.6751968503937008,0.01990956170490185,0.6727228332046034,0.02025972338315317,0.6747827677607314,0.019944073134612224 +flat_mae,patch,logistic,aabc_age,97,0.005994842503189409,test,0.4230769230769231,0.06397506679635148,0.4139784946236559,0.06279635629797659,0.41941391941391937,0.06343113513788781 +flat_mae,patch,logistic,aabc_age,98,0.005994842503189409,train,0.6653543307086615,0.020380080500217918,0.6639784165484074,0.020709092501632026,0.6666426123297576,0.02030575744436519 +flat_mae,patch,logistic,aabc_age,98,0.005994842503189409,test,0.46153846153846156,0.05925138252700055,0.43672014260249553,0.06730227692146434,0.459478021978022,0.05926300463910353 +flat_mae,patch,logistic,aabc_age,99,9.999999999999999e-05,train,0.5,0.02083549190049146,0.4735669246615235,0.020999956414424467,0.4960762261957962,0.02070194840846334 +flat_mae,patch,logistic,aabc_age,99,9.999999999999999e-05,test,0.4807692307692308,0.06257658030259294,0.4400849150849151,0.062361730313475396,0.4741300366300366,0.06167235404678007 +flat_mae,patch,logistic,aabc_age,100,0.005994842503189409,train,0.6791338582677166,0.020727817776718786,0.6770582873692019,0.020968092124338523,0.6789149991656902,0.02073195580730196 +flat_mae,patch,logistic,aabc_age,100,0.005994842503189409,test,0.40384615384615385,0.07045607973480808,0.4056940760389036,0.0709387888619285,0.4033882783882784,0.0704642288614083 diff --git a/input_space_v3/flat_lr1e-3_3/eval_v2/aabc_age__patch__logistic/log.txt b/input_space_v3/flat_lr1e-3_3/eval_v2/aabc_age__patch__logistic/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..d6065ca8c0f58caa74f73a797bcd39cfc2b3b78c --- /dev/null +++ b/input_space_v3/flat_lr1e-3_3/eval_v2/aabc_age__patch__logistic/log.txt @@ -0,0 +1,245 @@ +fMRI foundation model logistic probe eval +version: 0.1.dev86+gf97f52698 +sha: bcce2b486277d3a5b520775efd9cdf1a2affce36, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-04-08 22:16:26 +config: +output_root: experiments/input_space_v3/output +name_prefix: eval_logistic +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_3; eval v2 (aabc_age patch logistic) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: input_space_v3/flat_lr1e-3_3/eval_v2/aabc_age__patch__logistic +model: flat_mae +representation: patch +dataset: aabc_age +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/eval_v2/aabc_age__patch__logistic +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=True, reg_tokens=0, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: aabc_age (flat) +train (n=455): +HFDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'segment', 'bold', 'mean', 'std'], + num_rows: 471 +}), + labels=[0 1 2 3], + counts=[110 127 109 109] +) + +validation (n=53): +HFDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'segment', 'bold', 'mean', 'std'], + num_rows: 58 +}), + labels=[0 1 2 3], + counts=[14 13 12 14] +) + +test (n=52): +HFDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'segment', 'bold', 'mean', 'std'], + num_rows: 55 +}), + labels=[0 1 2 3], + counts=[13 13 12 14] +) + +extracting features for all splits +extract (train) [ 0/228] eta: 0:25:32 time: 6.7205 data: 5.6221 max mem: 3205 +extract (train) [ 20/228] eta: 0:02:05 time: 0.2997 data: 0.1192 max mem: 3393 +extract (train) [ 40/228] eta: 0:01:17 time: 0.2089 data: 0.0697 max mem: 3393 +extract (train) [ 60/228] eta: 0:01:01 time: 0.2709 data: 0.1047 max mem: 3393 +extract (train) [ 80/228] eta: 0:00:50 time: 0.2597 data: 0.1023 max mem: 3393 +extract (train) [100/228] eta: 0:00:41 time: 0.2498 data: 0.0952 max mem: 3393 +extract (train) [120/228] eta: 0:00:33 time: 0.2649 data: 0.1003 max mem: 3393 +extract (train) [140/228] eta: 0:00:26 time: 0.2566 data: 0.0914 max mem: 3393 +extract (train) [160/228] eta: 0:00:20 time: 0.2476 data: 0.0890 max mem: 3393 +extract (train) [180/228] eta: 0:00:13 time: 0.2261 data: 0.0768 max mem: 3393 +extract (train) [200/228] eta: 0:00:07 time: 0.2203 data: 0.0765 max mem: 3393 +extract (train) [220/228] eta: 0:00:02 time: 0.2169 data: 0.0710 max mem: 3393 +extract (train) [227/228] eta: 0:00:00 time: 0.2171 data: 0.0752 max mem: 3393 +extract (train) Total time: 0:01:03 (0.2773 s / it) +extract (validation) [ 0/27] eta: 0:02:17 time: 5.0933 data: 4.9326 max mem: 3393 +extract (validation) [20/27] eta: 0:00:03 time: 0.2047 data: 0.0607 max mem: 3393 +extract (validation) [26/27] eta: 0:00:00 time: 0.1979 data: 0.0596 max mem: 3393 +extract (validation) Total time: 0:00:10 (0.4041 s / it) +extract (test) [ 0/26] eta: 0:02:16 time: 5.2664 data: 5.0790 max mem: 3393 +extract (test) [20/26] eta: 0:00:02 time: 0.2000 data: 0.0628 max mem: 3393 +extract (test) [25/26] eta: 0:00:00 time: 0.1983 data: 0.0645 max mem: 3393 +extract (test) Total time: 0:00:10 (0.4117 s / it) +feature extraction time: 0:01:24 +train features: (455, 768) +validation features: (53, 768) +test features: (52, 768) +evaluating fixed splits +eval results (fixed splits): + +| model | repr | clf | dataset | trial | C | split | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|-------:|:--------|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | aabc_age | | 166.81 | train | 1 | 0 | 1 | 0 | 1 | 0 | +| flat_mae | patch | logistic | aabc_age | | 166.81 | test | 0.36538 | 0.066205 | 0.36504 | 0.066135 | 0.36218 | 0.065829 | + + +evaluating random splits (n=100) +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 1, "C": 0.046415888336127774, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.05982469459044682, "f1": 0.4212962962962963, "f1_std": 0.05589375587860719, "bacc": 0.4356684981684982, "bacc_std": 0.05875185573125088} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 2, "C": 0.000774263682681127, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.06753429985425725, "f1": 0.5329697106012896, "f1_std": 0.06887958646280781, "bacc": 0.5338827838827839, "bacc_std": 0.06740223478994882} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 3, "C": 0.005994842503189409, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.06416740310548476, "f1": 0.4720912599944858, "f1_std": 0.06514598349634758, "bacc": 0.4759615384615385, "bacc_std": 0.06410598786644263} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 4, "C": 9.999999999999999e-05, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.061156639994236234, "f1": 0.47015056022408963, "f1_std": 0.06254179823744715, "bacc": 0.5084706959706959, "bacc_std": 0.060090611717238715} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 5, "C": 9.999999999999999e-05, "split": "test", "acc": 0.38461538461538464, "acc_std": 0.058888559381559874, "f1": 0.34205665024630544, "f1_std": 0.050216259709214485, "bacc": 0.3791208791208791, "bacc_std": 0.057506060634693525} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 6, "C": 0.005994842503189409, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.06736740208665705, "f1": 0.5361471861471861, "f1_std": 0.06768965421874146, "bacc": 0.5366300366300366, "bacc_std": 0.06742560482850331} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 7, "C": 0.046415888336127774, "split": "test", "acc": 0.40384615384615385, "acc_std": 0.06490661247665962, "f1": 0.4006577480490524, "f1_std": 0.06239032733339668, "bacc": 0.4001831501831502, "bacc_std": 0.06422443637663307} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 8, "C": 0.046415888336127774, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.06304026843048008, "f1": 0.5313755837949385, "f1_std": 0.0659415650144414, "bacc": 0.5412087912087912, "bacc_std": 0.06331860352933869} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 9, "C": 0.046415888336127774, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.06630858468077014, "f1": 0.44606349120725, "f1_std": 0.06464359846291891, "bacc": 0.43887362637362637, "bacc_std": 0.06618357951602477} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 10, "C": 0.005994842503189409, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.06519496250550862, "f1": 0.4561050800531866, "f1_std": 0.06491409856598622, "bacc": 0.45810439560439564, "bacc_std": 0.06494615419032937} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 11, "C": 0.000774263682681127, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.06532445195842548, "f1": 0.5064727279800809, "f1_std": 0.069315251380239, "bacc": 0.5144230769230769, "bacc_std": 0.06521845068299512} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 12, "C": 0.005994842503189409, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.06494963911602415, "f1": 0.4419642857142857, "f1_std": 0.0648281892021364, "bacc": 0.43887362637362637, "bacc_std": 0.06469942338065637} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 13, "C": 9.999999999999999e-05, "split": "test", "acc": 0.40384615384615385, "acc_std": 0.05683381775172847, "f1": 0.3684077079107505, "f1_std": 0.04811405820416629, "bacc": 0.3956043956043956, "bacc_std": 0.05544308465257663} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 14, "C": 21.54434690031882, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.06123874126688646, "f1": 0.4244318181818182, "f1_std": 0.06178028723408098, "bacc": 0.4429945054945055, "bacc_std": 0.0613966954290129} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 15, "C": 0.005994842503189409, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.06974657209875355, "f1": 0.4638720538720539, "f1_std": 0.06916689783906864, "bacc": 0.46108058608058605, "bacc_std": 0.06981244169402016} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 16, "C": 0.005994842503189409, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.06358384484634275, "f1": 0.4378563964770861, "f1_std": 0.06582689951633297, "bacc": 0.43887362637362637, "bacc_std": 0.06322654688994395} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 17, "C": 0.000774263682681127, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.058203517147024916, "f1": 0.4373015873015873, "f1_std": 0.05820808952987053, "bacc": 0.475503663003663, "bacc_std": 0.05724211519129262} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 18, "C": 0.000774263682681127, "split": "test", "acc": 0.5, "acc_std": 0.058216846216812126, "f1": 0.4654716725399838, "f1_std": 0.05737680250207652, "bacc": 0.4933608058608059, "bacc_std": 0.057399777464636356} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 19, "C": 166.81005372000556, "split": "test", "acc": 0.40384615384615385, "acc_std": 0.06936460354425787, "f1": 0.41407867494824013, "f1_std": 0.069566940008961, "bacc": 0.4049908424908425, "bacc_std": 0.06977092292359788} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 20, "C": 0.005994842503189409, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.0556044116209854, "f1": 0.4527058962542833, "f1_std": 0.058005795206363106, "bacc": 0.47847985347985345, "bacc_std": 0.05559058148367466} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 21, "C": 0.005994842503189409, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.06594935971893341, "f1": 0.4481601731601731, "f1_std": 0.06582506910206148, "bacc": 0.4668040293040293, "bacc_std": 0.06692899263432617} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 22, "C": 0.000774263682681127, "split": "test", "acc": 0.40384615384615385, "acc_std": 0.06737929158807804, "f1": 0.41061006658832744, "f1_std": 0.06796626017695821, "bacc": 0.4036172161172161, "bacc_std": 0.06768330698564361} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 23, "C": 2.782559402207126, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.060605170459215214, "f1": 0.4493131868131868, "f1_std": 0.05861586240288008, "bacc": 0.4416208791208791, "bacc_std": 0.06065515642054557} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 24, "C": 0.046415888336127774, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.06378240561684852, "f1": 0.4246794871794872, "f1_std": 0.06324005302965884, "bacc": 0.42399267399267393, "bacc_std": 0.06391519696217829} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 25, "C": 9.999999999999999e-05, "split": "test", "acc": 0.34615384615384615, "acc_std": 0.057022574165825256, "f1": 0.302522349936143, "f1_std": 0.04873206115468315, "bacc": 0.34065934065934067, "bacc_std": 0.055881604426856316} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 26, "C": 0.000774263682681127, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.06464724489248827, "f1": 0.4319389978213508, "f1_std": 0.0645925858345282, "bacc": 0.43727106227106227, "bacc_std": 0.06425549637015895} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 27, "C": 9.999999999999999e-05, "split": "test", "acc": 0.3269230769230769, "acc_std": 0.056234715214592064, "f1": 0.2718715393133998, "f1_std": 0.0472103635357678, "bacc": 0.3173076923076923, "bacc_std": 0.054481865225499235} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 28, "C": 0.046415888336127774, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.06397821143531239, "f1": 0.5075051759834368, "f1_std": 0.06722891134038755, "bacc": 0.5187728937728938, "bacc_std": 0.06412329109404576} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 29, "C": 0.005994842503189409, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.065631783954794, "f1": 0.4876018808777429, "f1_std": 0.06462681640753505, "bacc": 0.4832875457875458, "bacc_std": 0.06620319957237059} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 30, "C": 0.005994842503189409, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.07059614074974209, "f1": 0.5314478114478114, "f1_std": 0.06887965172253718, "bacc": 0.5206043956043955, "bacc_std": 0.07048463243010714} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 31, "C": 9.999999999999999e-05, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.05848707691174584, "f1": 0.4875457875457875, "f1_std": 0.059812608937825994, "bacc": 0.5277014652014652, "bacc_std": 0.05762843748334259} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 32, "C": 9.999999999999999e-05, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.05226242385065548, "f1": 0.3750915750915751, "f1_std": 0.04712294688930005, "bacc": 0.43543956043956045, "bacc_std": 0.05089968099467084} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 33, "C": 0.005994842503189409, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.06225870581456173, "f1": 0.5229646215853112, "f1_std": 0.061202225127880296, "bacc": 0.5233516483516483, "bacc_std": 0.06300932590323621} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 34, "C": 0.005994842503189409, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.06789196952974055, "f1": 0.48930481283422456, "f1_std": 0.06945420199554292, "bacc": 0.48076923076923084, "bacc_std": 0.06811872850244728} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 35, "C": 0.005994842503189409, "split": "test", "acc": 0.38461538461538464, "acc_std": 0.0644353719610845, "f1": 0.37812500000000004, "f1_std": 0.06353842871220462, "bacc": 0.38095238095238093, "bacc_std": 0.0638966468471451} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 36, "C": 0.3593813663804626, "split": "test", "acc": 0.5, "acc_std": 0.0609595243540126, "f1": 0.469094315321117, "f1_std": 0.0632703770450332, "bacc": 0.49633699633699635, "bacc_std": 0.06059205142107227} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 37, "C": 0.005994842503189409, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.06476323515096304, "f1": 0.5164507274481699, "f1_std": 0.06662854755185013, "bacc": 0.5148809523809524, "bacc_std": 0.06494332014075618} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 38, "C": 0.000774263682681127, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.0633364618245265, "f1": 0.5287047511312217, "f1_std": 0.06619469736386072, "bacc": 0.5322802197802198, "bacc_std": 0.06305212561593228} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 39, "C": 0.005994842503189409, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.06641023661023365, "f1": 0.45883699633699637, "f1_std": 0.06779852829603082, "bacc": 0.47298534798534797, "bacc_std": 0.06580751401114761} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 40, "C": 0.005994842503189409, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.062413537827477876, "f1": 0.4233351578179164, "f1_std": 0.0620791271764868, "bacc": 0.440018315018315, "bacc_std": 0.06230876339327421} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 41, "C": 0.005994842503189409, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.06423250803726566, "f1": 0.42189976689976694, "f1_std": 0.06740276687323588, "bacc": 0.4416208791208791, "bacc_std": 0.06433146840169637} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 42, "C": 0.005994842503189409, "split": "test", "acc": 0.5, "acc_std": 0.06590439327734106, "f1": 0.489673345145609, "f1_std": 0.06855910186283821, "bacc": 0.5057234432234432, "bacc_std": 0.06633396874500345} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 43, "C": 0.005994842503189409, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.06690256095787286, "f1": 0.45046574115539634, "f1_std": 0.06780024339835107, "bacc": 0.45970695970695974, "bacc_std": 0.06697064348517025} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 44, "C": 0.005994842503189409, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.06800708064423497, "f1": 0.5165673981191223, "f1_std": 0.06974559867041524, "bacc": 0.5208333333333334, "bacc_std": 0.06829083664435515} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 45, "C": 0.000774263682681127, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.06141587549904023, "f1": 0.4127227884033692, "f1_std": 0.062239643005933216, "bacc": 0.4237637362637363, "bacc_std": 0.06146110579069848} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 46, "C": 0.000774263682681127, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.06371138463841748, "f1": 0.5233860342555995, "f1_std": 0.06697060642511267, "bacc": 0.5322802197802198, "bacc_std": 0.0634183695522604} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 47, "C": 0.000774263682681127, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.06100027888189233, "f1": 0.39786967418546365, "f1_std": 0.0642118536791946, "bacc": 0.41804029304029305, "bacc_std": 0.060395222628446474} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 48, "C": 0.005994842503189409, "split": "test", "acc": 0.5, "acc_std": 0.06789317880178133, "f1": 0.5005411255411255, "f1_std": 0.07086623404869163, "bacc": 0.4967948717948718, "bacc_std": 0.06777350787558592} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 49, "C": 0.005994842503189409, "split": "test", "acc": 0.40384615384615385, "acc_std": 0.061178405808570285, "f1": 0.3883972374374851, "f1_std": 0.05842972621448846, "bacc": 0.39720695970695974, "bacc_std": 0.06046576656719725} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 50, "C": 0.046415888336127774, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.06729132768095077, "f1": 0.42440476190476195, "f1_std": 0.06731428979498298, "bacc": 0.4198717948717948, "bacc_std": 0.06695531987190254} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 51, "C": 0.046415888336127774, "split": "test", "acc": 0.5, "acc_std": 0.07129316921228401, "f1": 0.4960109231098736, "f1_std": 0.07230914442456858, "bacc": 0.49977106227106227, "bacc_std": 0.07124164075790278} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 52, "C": 0.000774263682681127, "split": "test", "acc": 0.38461538461538464, "acc_std": 0.06472591279373546, "f1": 0.38003663003663, "f1_std": 0.06552754823548834, "bacc": 0.38118131868131866, "bacc_std": 0.06436768871950835} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 53, "C": 9.999999999999999e-05, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.05654950180015872, "f1": 0.49775124069478904, "f1_std": 0.05583275777708156, "bacc": 0.530448717948718, "bacc_std": 0.05560941715237431} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 54, "C": 2.782559402207126, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.06882465285227879, "f1": 0.4387926887926888, "f1_std": 0.06897070880612334, "bacc": 0.4450549450549451, "bacc_std": 0.0689131433245207} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 55, "C": 0.000774263682681127, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.06469893865220583, "f1": 0.43281657490582437, "f1_std": 0.06602172636068064, "bacc": 0.44299450549450553, "bacc_std": 0.06483723506368402} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 56, "C": 9.999999999999999e-05, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.06456649936489267, "f1": 0.4004621848739496, "f1_std": 0.06677528976417386, "bacc": 0.41941391941391937, "bacc_std": 0.0641425038759074} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 57, "C": 2.782559402207126, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.06275193011954143, "f1": 0.46963684463684463, "f1_std": 0.062000227558525085, "bacc": 0.47870879120879123, "bacc_std": 0.06250826173440455} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 58, "C": 2.782559402207126, "split": "test", "acc": 0.38461538461538464, "acc_std": 0.0604892650263826, "f1": 0.3579831932773109, "f1_std": 0.06104941533845162, "bacc": 0.37797619047619047, "bacc_std": 0.059647966757503286} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 59, "C": 0.3593813663804626, "split": "test", "acc": 0.40384615384615385, "acc_std": 0.06764526337301625, "f1": 0.4129440961337513, "f1_std": 0.06711780623566589, "bacc": 0.4049908424908425, "bacc_std": 0.06776775946083288} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 60, "C": 0.005994842503189409, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.06101915500977139, "f1": 0.4160830403817781, "f1_std": 0.06304045292777831, "bacc": 0.4223901098901099, "bacc_std": 0.06095404752987991} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 61, "C": 166.81005372000556, "split": "test", "acc": 0.40384615384615385, "acc_std": 0.06705641006031798, "f1": 0.4004446640316206, "f1_std": 0.06757002306934394, "bacc": 0.39903846153846156, "bacc_std": 0.06688467149687251} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 62, "C": 0.005994842503189409, "split": "test", "acc": 0.5, "acc_std": 0.06455320955541503, "f1": 0.4958998588030846, "f1_std": 0.0633150492999732, "bacc": 0.4951923076923077, "bacc_std": 0.06430632583088487} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 63, "C": 0.005994842503189409, "split": "test", "acc": 0.40384615384615385, "acc_std": 0.06256551595713288, "f1": 0.3957729468599034, "f1_std": 0.06199428942826261, "bacc": 0.40453296703296704, "bacc_std": 0.0628698533844527} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 64, "C": 0.005994842503189409, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.06432738012945596, "f1": 0.4473578595317726, "f1_std": 0.06337807072626256, "bacc": 0.44047619047619047, "bacc_std": 0.06414402484898052} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 65, "C": 0.046415888336127774, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.06795181899067906, "f1": 0.4802134646962233, "f1_std": 0.06828061152266963, "bacc": 0.4775641025641026, "bacc_std": 0.06758840880179856} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 66, "C": 0.046415888336127774, "split": "test", "acc": 0.38461538461538464, "acc_std": 0.05877269170236147, "f1": 0.362983312983313, "f1_std": 0.05481960649147857, "bacc": 0.38804945054945056, "bacc_std": 0.0595749877267414} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 67, "C": 0.046415888336127774, "split": "test", "acc": 0.5, "acc_std": 0.049858661180125524, "f1": 0.4358974358974359, "f1_std": 0.04488571430531685, "bacc": 0.49313186813186816, "bacc_std": 0.048381339145155605} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 68, "C": 0.046415888336127774, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.061208381585624055, "f1": 0.414686887325568, "f1_std": 0.060471723530721576, "bacc": 0.4237637362637363, "bacc_std": 0.06158857687824521} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 69, "C": 0.000774263682681127, "split": "test", "acc": 0.40384615384615385, "acc_std": 0.06313481161664952, "f1": 0.3911877394636015, "f1_std": 0.06324951018985656, "bacc": 0.4015567765567766, "bacc_std": 0.06277843518532499} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 70, "C": 0.3593813663804626, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.0612429805179491, "f1": 0.45675620675620676, "f1_std": 0.06215219059637828, "bacc": 0.4674908424908425, "bacc_std": 0.06152747746652749} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 71, "C": 0.005994842503189409, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.06314555365776407, "f1": 0.44116300366300365, "f1_std": 0.06191998606988123, "bacc": 0.44459706959706957, "bacc_std": 0.06369399838315967} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 72, "C": 0.3593813663804626, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.0642926348768526, "f1": 0.5268147981051207, "f1_std": 0.06672373445324699, "bacc": 0.5352564102564102, "bacc_std": 0.06429537515428509} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 73, "C": 0.005994842503189409, "split": "test", "acc": 0.5, "acc_std": 0.06306594651210314, "f1": 0.5026171529619805, "f1_std": 0.06226223594232982, "bacc": 0.502518315018315, "bacc_std": 0.0632445397425038} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 74, "C": 0.046415888336127774, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.06916022046432875, "f1": 0.4312025534851622, "f1_std": 0.07001092635909684, "bacc": 0.42147435897435903, "bacc_std": 0.06925700799598918} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 75, "C": 0.005994842503189409, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.0700952859500982, "f1": 0.5445512820512821, "f1_std": 0.07001398084543628, "bacc": 0.5398351648351648, "bacc_std": 0.07028346986551098} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 76, "C": 0.046415888336127774, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.06722306768068806, "f1": 0.4603846153846154, "f1_std": 0.06788499669420045, "bacc": 0.46565934065934067, "bacc_std": 0.06765160304876516} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 77, "C": 9.999999999999999e-05, "split": "test", "acc": 0.36538461538461536, "acc_std": 0.05779696916768573, "f1": 0.32604679802955666, "f1_std": 0.048270664377570834, "bacc": 0.3598901098901099, "bacc_std": 0.05639427090232659} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 78, "C": 0.046415888336127774, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.06745819437374291, "f1": 0.4771208995346926, "f1_std": 0.06801848249642121, "bacc": 0.4789377289377289, "bacc_std": 0.06765857224143541} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 79, "C": 0.000774263682681127, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.06132041900527301, "f1": 0.5229166666666667, "f1_std": 0.06342142494094022, "bacc": 0.5336538461538461, "bacc_std": 0.06111353749106224} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 80, "C": 0.046415888336127774, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.06213466002426794, "f1": 0.46875, "f1_std": 0.06441715745825462, "bacc": 0.48168498168498164, "bacc_std": 0.062196716276203906} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 81, "C": 0.3593813663804626, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.06756818821880307, "f1": 0.4840802675585284, "f1_std": 0.06769285272785192, "bacc": 0.48054029304029305, "bacc_std": 0.06768852432247319} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 82, "C": 0.005994842503189409, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.06353411933384004, "f1": 0.4674912810974192, "f1_std": 0.06414869461062706, "bacc": 0.48305860805860806, "bacc_std": 0.0639978898189623} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 83, "C": 166.81005372000556, "split": "test", "acc": 0.34615384615384615, "acc_std": 0.06118775064015973, "f1": 0.34989010989010993, "f1_std": 0.05974570763283775, "bacc": 0.3498168498168498, "bacc_std": 0.06182422215122304} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 84, "C": 0.005994842503189409, "split": "test", "acc": 0.5576923076923077, "acc_std": 0.05863702154661326, "f1": 0.5331854106902407, "f1_std": 0.063184459466838, "bacc": 0.5528846153846154, "bacc_std": 0.058231281373536135} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 85, "C": 0.005994842503189409, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.06034937727332493, "f1": 0.4072304935208161, "f1_std": 0.061063942486436, "bacc": 0.4237637362637363, "bacc_std": 0.060252078896384904} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 86, "C": 0.046415888336127774, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.0634321493721007, "f1": 0.5187100893997445, "f1_std": 0.0664927516849539, "bacc": 0.5336538461538461, "bacc_std": 0.06314864582756859} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 87, "C": 0.046415888336127774, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.06289160158793747, "f1": 0.4328439153439153, "f1_std": 0.0625246485175888, "bacc": 0.44459706959706957, "bacc_std": 0.06350229247900603} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 88, "C": 0.005994842503189409, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.06406011414953981, "f1": 0.4401768346595933, "f1_std": 0.06479329919409826, "bacc": 0.4448260073260073, "bacc_std": 0.0643696956478833} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 89, "C": 9.999999999999999e-05, "split": "test", "acc": 0.38461538461538464, "acc_std": 0.06273646392111563, "f1": 0.3546130952380952, "f1_std": 0.061429227676595914, "bacc": 0.3807234432234432, "bacc_std": 0.06192777078794661} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 90, "C": 0.005994842503189409, "split": "test", "acc": 0.5, "acc_std": 0.06122288072494102, "f1": 0.4809523809523809, "f1_std": 0.0637736598826827, "bacc": 0.4993131868131868, "bacc_std": 0.061041988981768776} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 91, "C": 0.000774263682681127, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.06519184252159888, "f1": 0.448656015037594, "f1_std": 0.06952225271160185, "bacc": 0.4624542124542125, "bacc_std": 0.06563985865507282} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 92, "C": 0.000774263682681127, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.05556555646341318, "f1": 0.39701692642869113, "f1_std": 0.05599130541834791, "bacc": 0.4397893772893773, "bacc_std": 0.055052219476579886} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 93, "C": 2.782559402207126, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.06931912097354076, "f1": 0.46216210076779796, "f1_std": 0.06554069068899719, "bacc": 0.44482600732600736, "bacc_std": 0.06961680637583775} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 94, "C": 0.000774263682681127, "split": "test", "acc": 0.38461538461538464, "acc_std": 0.057488601906051144, "f1": 0.36666979010494755, "f1_std": 0.059493109437784984, "bacc": 0.38369963369963367, "bacc_std": 0.0575602766711752} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 95, "C": 0.046415888336127774, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.06633529454050195, "f1": 0.5123968784838351, "f1_std": 0.06486264541457161, "bacc": 0.5130494505494505, "bacc_std": 0.06600215711645958} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 96, "C": 0.005994842503189409, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.06516406240855306, "f1": 0.47046091163738224, "f1_std": 0.06711561339362196, "bacc": 0.47619047619047616, "bacc_std": 0.065059207688111} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 97, "C": 0.005994842503189409, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.06397506679635148, "f1": 0.4139784946236559, "f1_std": 0.06279635629797659, "bacc": 0.41941391941391937, "bacc_std": 0.06343113513788781} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 98, "C": 0.005994842503189409, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.05925138252700055, "f1": 0.43672014260249553, "f1_std": 0.06730227692146434, "bacc": 0.459478021978022, "bacc_std": 0.05926300463910353} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 99, "C": 9.999999999999999e-05, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.06257658030259294, "f1": 0.4400849150849151, "f1_std": 0.062361730313475396, "bacc": 0.4741300366300366, "bacc_std": 0.06167235404678007} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 100, "C": 0.005994842503189409, "split": "test", "acc": 0.40384615384615385, "acc_std": 0.07045607973480808, "f1": 0.4056940760389036, "f1_std": 0.0709387888619285, "bacc": 0.4033882783882784, "bacc_std": 0.0704642288614083} +eval results (random splits): + +| model | repr | clf | dataset | split | n_trials | C | C_std | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|-----------:|-------:|--------:|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | aabc_age | train | 100 | 5.3881 | 28.618 | 0.70104 | 0.15205 | 0.69512 | 0.1589 | 0.70073 | 0.15288 | +| flat_mae | patch | logistic | aabc_age | test | 100 | 5.3881 | 28.618 | 0.45865 | 0.052104 | 0.44571 | 0.055648 | 0.45654 | 0.052023 | + + +done! total time: 0:06:07 diff --git a/input_space_v3/flat_lr1e-3_3/eval_v2/aabc_sex__patch__logistic/config.yaml b/input_space_v3/flat_lr1e-3_3/eval_v2/aabc_sex__patch__logistic/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..ddf505c4d772c7d503d00df4585c01a9d022ee27 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_3/eval_v2/aabc_sex__patch__logistic/config.yaml @@ -0,0 +1,30 @@ +output_root: experiments/input_space_v3/output +name_prefix: eval_logistic +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_3; eval v2 (aabc_sex patch logistic) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: input_space_v3/flat_lr1e-3_3/eval_v2/aabc_sex__patch__logistic +model: flat_mae +representation: patch +dataset: aabc_sex +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/eval_v2/aabc_sex__patch__logistic +remote_dir: null diff --git a/input_space_v3/flat_lr1e-3_3/eval_v2/aabc_sex__patch__logistic/eval_table.csv b/input_space_v3/flat_lr1e-3_3/eval_v2/aabc_sex__patch__logistic/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..7444f85f3a2c56b2a6438f476b40ff871732671a --- /dev/null +++ b/input_space_v3/flat_lr1e-3_3/eval_v2/aabc_sex__patch__logistic/eval_table.csv @@ -0,0 +1,203 @@ +model,repr,clf,dataset,trial,C,split,acc,acc_std,f1,f1_std,bacc,bacc_std +flat_mae,patch,logistic,aabc_sex,,0.3593813663804626,train,0.9905482041587902,0.004068193474778966,0.9903381466044704,0.004150403803994348,0.9912104800936768,0.0038053166460081155 +flat_mae,patch,logistic,aabc_sex,,0.3593813663804626,test,0.9090909090909091,0.03909684521524881,0.9071259709557582,0.03937251996783646,0.9166666666666667,0.036541157594514 +flat_mae,patch,logistic,aabc_sex,1,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,1,21.54434690031882,test,0.7818181818181819,0.05545113551363998,0.7758152173913043,0.056986834247449006,0.7758152173913043,0.05662444779491383 +flat_mae,patch,logistic,aabc_sex,2,0.046415888336127774,train,0.947069943289225,0.009589865654913559,0.9457991803278689,0.009809945562323714,0.9463422140156511,0.00987580295203857 +flat_mae,patch,logistic,aabc_sex,2,0.046415888336127774,test,0.9090909090909091,0.04105547949658139,0.9071259709557582,0.04176483863106337,0.9096467391304348,0.041056633389286654 +flat_mae,patch,logistic,aabc_sex,3,0.3593813663804626,train,0.994328922495274,0.003255396080234988,0.9941893034853195,0.0033325766755414824,0.9944898736774231,0.0031787133101733728 +flat_mae,patch,logistic,aabc_sex,3,0.3593813663804626,test,0.8181818181818182,0.05355730382859491,0.8131793478260869,0.05533455720534445,0.8131793478260869,0.05555934978276752 +flat_mae,patch,logistic,aabc_sex,4,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,4,21.54434690031882,test,0.8363636363636363,0.050399842581414896,0.8354935194416749,0.05024155884788907,0.8471467391304348,0.04733826769948187 +flat_mae,patch,logistic,aabc_sex,5,0.046415888336127774,train,0.9508506616257089,0.009498485814668917,0.9497295321637427,0.009685320520057945,0.9508265189483864,0.009541859245760637 +flat_mae,patch,logistic,aabc_sex,5,0.046415888336127774,test,0.8545454545454545,0.047699486283769715,0.8484848484848485,0.050504954892117385,0.8444293478260869,0.05086695000579118 +flat_mae,patch,logistic,aabc_sex,6,0.3593813663804626,train,0.9905482041587902,0.004251213935188609,0.9903269809575008,0.004342225376004746,0.991221899821214,0.003990604211712141 +flat_mae,patch,logistic,aabc_sex,6,0.3593813663804626,test,0.8909090909090909,0.04303603717662406,0.8879076086956521,0.044211112790652575,0.8879076086956521,0.04433977081690678 +flat_mae,patch,logistic,aabc_sex,7,0.3593813663804626,train,0.994328922495274,0.003340786143301328,0.9941893034853195,0.003420493980714837,0.9944898736774231,0.003295261479644231 +flat_mae,patch,logistic,aabc_sex,7,0.3593813663804626,test,0.8363636363636363,0.04913000463435657,0.8354935194416749,0.04897572674572996,0.8471467391304348,0.046665724949920225 +flat_mae,patch,logistic,aabc_sex,8,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,8,2.782559402207126,test,0.8363636363636363,0.049171529759027964,0.8328267477203647,0.05045668413031784,0.8349184782608696,0.05050240661202059 +flat_mae,patch,logistic,aabc_sex,9,0.3593813663804626,train,0.9905482041587902,0.004292197759929404,0.9903155058088658,0.004396582564837237,0.9906137342829509,0.004348662992963833 +flat_mae,patch,logistic,aabc_sex,9,0.3593813663804626,test,0.9454545454545454,0.03081774738229595,0.9435897435897436,0.03218413647209804,0.9408967391304348,0.03382174238242263 +flat_mae,patch,logistic,aabc_sex,10,0.3593813663804626,train,0.9905482041587902,0.004216312958489432,0.9903269809575008,0.004308163018489384,0.991221899821214,0.004013255190692628 +flat_mae,patch,logistic,aabc_sex,10,0.3593813663804626,test,0.8909090909090909,0.042553596734486755,0.8891129032258065,0.04293996886226611,0.8940217391304348,0.041665444964761045 +flat_mae,patch,logistic,aabc_sex,11,0.005994842503189409,train,0.8998109640831758,0.012919127805901267,0.8972194218890335,0.013254158667153237,0.8969782232773528,0.013340218221624602 +flat_mae,patch,logistic,aabc_sex,11,0.005994842503189409,test,0.9090909090909091,0.039095559977027516,0.9045470322804582,0.0424735734702768,0.8974184782608696,0.04409067525408761 +flat_mae,patch,logistic,aabc_sex,12,0.046415888336127774,train,0.9527410207939508,0.009662358560505983,0.9516349047875045,0.009879101127103449,0.9524605058764911,0.009856330997501318 +flat_mae,patch,logistic,aabc_sex,12,0.046415888336127774,test,0.8181818181818182,0.05215468410775932,0.8106060606060606,0.05551496676886814,0.8070652173913043,0.05561450464576429 +flat_mae,patch,logistic,aabc_sex,13,0.3593813663804626,train,0.9905482041587902,0.0038758983251187943,0.9903155058088658,0.0039689831934131715,0.9906137342829509,0.00389329140688869 +flat_mae,patch,logistic,aabc_sex,13,0.3593813663804626,test,0.8909090909090909,0.043273323143338184,0.8879076086956521,0.044452542565442274,0.8879076086956521,0.04445228755199523 +flat_mae,patch,logistic,aabc_sex,14,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,14,2.782559402207126,test,0.8909090909090909,0.0416247065857179,0.8891129032258065,0.04205977032024507,0.8940217391304348,0.04103055483180367 +flat_mae,patch,logistic,aabc_sex,15,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,15,21.54434690031882,test,0.8363636363636363,0.04401316106697445,0.8250265111346766,0.04930249741120148,0.8165760869565217,0.048722978854727886 +flat_mae,patch,logistic,aabc_sex,16,0.3593813663804626,train,0.9905482041587902,0.00409635903011585,0.9903155058088658,0.004195164921355557,0.9906137342829509,0.004143019314474823 +flat_mae,patch,logistic,aabc_sex,16,0.3593813663804626,test,0.8545454545454545,0.0465507241335231,0.84593837535014,0.051605497053739124,0.8383152173913043,0.05191454041156165 +flat_mae,patch,logistic,aabc_sex,17,0.3593813663804626,train,0.9905482041587902,0.004069753195254759,0.9903269809575008,0.004157908539757352,0.991221899821214,0.0038455816020821 +flat_mae,patch,logistic,aabc_sex,17,0.3593813663804626,test,0.9272727272727272,0.03463910750286505,0.9242424242424243,0.03688055219883087,0.9191576086956521,0.03837289279491788 +flat_mae,patch,logistic,aabc_sex,18,0.3593813663804626,train,0.9905482041587902,0.003958271266743651,0.9903269809575008,0.004043734453511222,0.991221899821214,0.00372948695661225 +flat_mae,patch,logistic,aabc_sex,18,0.3593813663804626,test,0.8727272727272727,0.04229569268654563,0.8720505151213027,0.04218939673262764,0.8845108695652174,0.039254261260592324 +flat_mae,patch,logistic,aabc_sex,19,0.3593813663804626,train,0.9905482041587902,0.004167872879509411,0.9903269809575008,0.00425790189707791,0.991221899821214,0.003953473070221664 +flat_mae,patch,logistic,aabc_sex,19,0.3593813663804626,test,0.8727272727272727,0.042912850374599056,0.8683760683760684,0.04466861718780109,0.8661684782608696,0.044990776087452895 +flat_mae,patch,logistic,aabc_sex,20,0.3593813663804626,train,0.994328922495274,0.0033460425260368404,0.9941961885745005,0.003416563388924203,0.9950980392156863,0.0028922491769174646 +flat_mae,patch,logistic,aabc_sex,20,0.3593813663804626,test,0.9090909090909091,0.037992100092275605,0.905982905982906,0.03987016719479078,0.9035326086956521,0.040974245042385816 +flat_mae,patch,logistic,aabc_sex,21,0.046415888336127774,train,0.9546313799621928,0.009097997620385524,0.9535421545667447,0.009311745499695575,0.9540944928045957,0.009365708241677411 +flat_mae,patch,logistic,aabc_sex,21,0.046415888336127774,test,0.8,0.05050922180754029,0.790003471017008,0.05460227449100145,0.7853260869565217,0.054204549915613444 +flat_mae,patch,logistic,aabc_sex,22,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,22,2.782559402207126,test,0.9454545454545454,0.03156824432221053,0.9447975911676145,0.03155911125349677,0.953125,0.027128959964399665 +flat_mae,patch,logistic,aabc_sex,23,0.3593813663804626,train,0.996219281663516,0.0026602371141491517,0.9961285128805621,0.0027195812139166704,0.9967320261437909,0.0022994533225243435 +flat_mae,patch,logistic,aabc_sex,23,0.3593813663804626,test,0.9090909090909091,0.04032625623770152,0.9071259709557582,0.0410846055667245,0.9096467391304348,0.040593685105256704 +flat_mae,patch,logistic,aabc_sex,24,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,24,2.782559402207126,test,0.8727272727272727,0.047411488651996,0.8683760683760684,0.049772739079337054,0.8661684782608696,0.050161728393043656 +flat_mae,patch,logistic,aabc_sex,25,0.046415888336127774,train,0.9489603024574669,0.009277592383485253,0.9477037313678753,0.0094980027436153,0.9479762009437558,0.0095425884366424 +flat_mae,patch,logistic,aabc_sex,25,0.046415888336127774,test,0.9636363636363636,0.023204901163688015,0.9630376344086022,0.02334271983025949,0.96875,0.01994171193754438 +flat_mae,patch,logistic,aabc_sex,26,0.3593813663804626,train,0.9924385633270322,0.003766041455205086,0.9922570257611241,0.0038529604400086154,0.9928558867493186,0.0036555703569448993 +flat_mae,patch,logistic,aabc_sex,26,0.3593813663804626,test,0.8363636363636363,0.04740434823309942,0.8307692307692308,0.04981713412942737,0.8288043478260869,0.050045534042620216 +flat_mae,patch,logistic,aabc_sex,27,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,27,166.81005372000556,test,0.9090909090909091,0.03659365432954303,0.905982905982906,0.038236487622334024,0.9035326086956521,0.03912946129808863 +flat_mae,patch,logistic,aabc_sex,28,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,28,166.81005372000556,test,0.8545454545454545,0.046461216386349286,0.8484848484848485,0.049219246905889115,0.8444293478260869,0.049440323191568485 +flat_mae,patch,logistic,aabc_sex,29,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,29,2.782559402207126,test,0.8545454545454545,0.04701213488500899,0.8521505376344086,0.047529813093721784,0.8566576086956521,0.04677217187126145 +flat_mae,patch,logistic,aabc_sex,30,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,30,166.81005372000556,test,0.8727272727272727,0.04514769152001878,0.8711943793911007,0.04552937215590051,0.8783967391304348,0.0443523026258279 +flat_mae,patch,logistic,aabc_sex,31,0.005994842503189409,train,0.9035916824196597,0.012755246639601332,0.9008478594030804,0.01316537984517147,0.8996380315952988,0.013383301063874462 +flat_mae,patch,logistic,aabc_sex,31,0.005994842503189409,test,0.8181818181818182,0.05022585682907633,0.8151881720430108,0.0508431623023483,0.8192934782608696,0.05054768892801622 +flat_mae,patch,logistic,aabc_sex,32,0.3593813663804626,train,0.9924385633270322,0.0033998287009348476,0.9922570257611241,0.0034781962539152493,0.9928558867493186,0.003303287629509073 +flat_mae,patch,logistic,aabc_sex,32,0.3593813663804626,test,0.9272727272727272,0.035177359360393276,0.9242424242424243,0.03742718378151296,0.9191576086956521,0.03917614479962339 +flat_mae,patch,logistic,aabc_sex,33,0.3593813663804626,train,0.9905482041587902,0.00415982114734193,0.9903269809575008,0.00424825689568988,0.991221899821214,0.00391080123730141 +flat_mae,patch,logistic,aabc_sex,33,0.3593813663804626,test,0.9454545454545454,0.0322849093525261,0.9442755825734549,0.03279495688397755,0.9470108695652174,0.03153861874704795 +flat_mae,patch,logistic,aabc_sex,34,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,34,2.782559402207126,test,0.8909090909090909,0.042866481154995334,0.8879076086956521,0.04414762885152944,0.8879076086956521,0.04441818374145626 +flat_mae,patch,logistic,aabc_sex,35,0.005994842503189409,train,0.9017013232514177,0.01294471581947573,0.8988378934980876,0.013387513584145567,0.8973958791289312,0.013695556959694542 +flat_mae,patch,logistic,aabc_sex,35,0.005994842503189409,test,0.8909090909090909,0.04178123268835755,0.8879076086956521,0.04291608865389405,0.8879076086956521,0.04276081810467495 +flat_mae,patch,logistic,aabc_sex,36,0.3593813663804626,train,0.9886578449905482,0.004422509717408323,0.9883991228070176,0.0045118346739388086,0.9895879128931093,0.004092345711460301 +flat_mae,patch,logistic,aabc_sex,36,0.3593813663804626,test,0.9090909090909091,0.03768190481402477,0.905982905982906,0.039540261574199945,0.9035326086956521,0.04074322842887127 +flat_mae,patch,logistic,aabc_sex,37,0.3593813663804626,train,0.994328922495274,0.003352974984013492,0.9941893034853195,0.0034319969677507095,0.9944898736774231,0.003288971312036248 +flat_mae,patch,logistic,aabc_sex,37,0.3593813663804626,test,0.8181818181818182,0.05284049286248578,0.8131793478260869,0.05465274089691268,0.8131793478260869,0.05472729385290482 +flat_mae,patch,logistic,aabc_sex,38,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,38,166.81005372000556,test,0.8545454545454545,0.0448730661546066,0.84593837535014,0.049104353697448956,0.8383152173913043,0.049305983265951675 +flat_mae,patch,logistic,aabc_sex,39,0.046415888336127774,train,0.9489603024574669,0.009171884763416174,0.9477656971705049,0.009369643036066607,0.9485843664820188,0.009351276388550595 +flat_mae,patch,logistic,aabc_sex,39,0.046415888336127774,test,0.8181818181818182,0.050182068510574544,0.8131793478260869,0.05189587115638289,0.8131793478260869,0.052058944817648174 +flat_mae,patch,logistic,aabc_sex,40,0.3593813663804626,train,0.9905482041587902,0.004400111360529746,0.9903269809575008,0.004493440618907912,0.991221899821214,0.0041244794921868775 +flat_mae,patch,logistic,aabc_sex,40,0.3593813663804626,test,0.8545454545454545,0.04525592970599231,0.8505434782608696,0.046653553627960385,0.8505434782608696,0.04689666764494444 +flat_mae,patch,logistic,aabc_sex,41,0.3593813663804626,train,0.9924385633270322,0.0038974255230616764,0.9922660818713451,0.003974674143860746,0.9934640522875817,0.0033688531073523273 +flat_mae,patch,logistic,aabc_sex,41,0.3593813663804626,test,0.8727272727272727,0.044564137084090225,0.8711943793911007,0.04475461650497854,0.8783967391304348,0.04339584188857657 +flat_mae,patch,logistic,aabc_sex,42,0.3593813663804626,train,0.994328922495274,0.003370338108015165,0.9941893034853195,0.003449760619215632,0.9944898736774231,0.003295930604128341 +flat_mae,patch,logistic,aabc_sex,42,0.3593813663804626,test,0.8363636363636363,0.05211906267590462,0.8343927735028438,0.05246252883595243,0.8410326086956521,0.05133280022057388 +flat_mae,patch,logistic,aabc_sex,43,0.3593813663804626,train,0.9886578449905482,0.004561137010252011,0.9883991228070176,0.004652446640014264,0.9895879128931093,0.004215446870060243 +flat_mae,patch,logistic,aabc_sex,43,0.3593813663804626,test,0.9454545454545454,0.02937972539801573,0.9447975911676145,0.029404415306318998,0.953125,0.02524820151391976 +flat_mae,patch,logistic,aabc_sex,44,0.3593813663804626,train,0.9905482041587902,0.0042048727141310105,0.9903155058088658,0.0043056001960513485,0.9906137342829509,0.004195243702602405 +flat_mae,patch,logistic,aabc_sex,44,0.3593813663804626,test,0.8545454545454545,0.04623538768497744,0.8484848484848485,0.04925375700396379,0.8444293478260869,0.04952354094996705 +flat_mae,patch,logistic,aabc_sex,45,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,45,21.54434690031882,test,0.9090909090909091,0.0376267181316066,0.9071259709557582,0.03830435547745905,0.9096467391304348,0.03785417232098941 +flat_mae,patch,logistic,aabc_sex,46,0.046415888336127774,train,0.945179584120983,0.01005248216171015,0.9438299336914217,0.010293750437957735,0.9441000615492834,0.010349201832206875 +flat_mae,patch,logistic,aabc_sex,46,0.046415888336127774,test,0.9090909090909091,0.0397935000298805,0.9071259709557582,0.040490327095684,0.9096467391304348,0.03985598622758495 +flat_mae,patch,logistic,aabc_sex,47,0.3593813663804626,train,0.9924385633270322,0.00392468975441611,0.9922570257611241,0.004012202097928713,0.9928558867493186,0.003729693475972929 +flat_mae,patch,logistic,aabc_sex,47,0.3593813663804626,test,0.9090909090909091,0.03886924042529864,0.9071259709557582,0.039670762577109046,0.9096467391304348,0.03942925594313299 +flat_mae,patch,logistic,aabc_sex,48,0.046415888336127774,train,0.941398865784499,0.009845736790745576,0.939956136014968,0.010093921602281182,0.9402239221548111,0.010230613285438001 +flat_mae,patch,logistic,aabc_sex,48,0.046415888336127774,test,0.9454545454545454,0.029847856630829388,0.9442755825734549,0.030281506363586504,0.9470108695652174,0.02892172505735102 +flat_mae,patch,logistic,aabc_sex,49,0.3593813663804626,train,0.9924385633270322,0.00373694699630003,0.9922570257611241,0.00382063117102105,0.9928558867493186,0.0035465089298365605 +flat_mae,patch,logistic,aabc_sex,49,0.3593813663804626,test,0.8545454545454545,0.04808884339952594,0.8521505376344086,0.048639699210198215,0.8566576086956521,0.04777374536705808 +flat_mae,patch,logistic,aabc_sex,50,0.3593813663804626,train,0.996219281663516,0.0027501471169461386,0.9961238606055277,0.002819854071477727,0.9961238606055277,0.00285730669963345 +flat_mae,patch,logistic,aabc_sex,50,0.3593813663804626,test,0.9272727272727272,0.03497741420019828,0.9266666666666667,0.03486633378766793,0.9375,0.030058715328295387 +flat_mae,patch,logistic,aabc_sex,51,0.3593813663804626,train,0.9905482041587902,0.004190460268448427,0.9903269809575008,0.004278373317661311,0.991221899821214,0.0038800833981860066 +flat_mae,patch,logistic,aabc_sex,51,0.3593813663804626,test,0.9090909090909091,0.037034020544439286,0.9045470322804582,0.04016031982005333,0.8974184782608696,0.041966533533175164 +flat_mae,patch,logistic,aabc_sex,52,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,52,21.54434690031882,test,0.9090909090909091,0.037893125044258825,0.9079959852793577,0.0380694397921639,0.9157608695652174,0.035896070576007785 +flat_mae,patch,logistic,aabc_sex,53,0.046415888336127774,train,0.941398865784499,0.010452531410867882,0.9398830580860384,0.010731929016602398,0.939615756616548,0.010860252009648946 +flat_mae,patch,logistic,aabc_sex,53,0.046415888336127774,test,0.8909090909090909,0.04406052936511186,0.8879076086956521,0.045337543271216744,0.8879076086956521,0.04536888722758947 +flat_mae,patch,logistic,aabc_sex,54,0.046415888336127774,train,0.947069943289225,0.009499310438679002,0.9457991803278689,0.009719600577327226,0.9463422140156511,0.009776238976441273 +flat_mae,patch,logistic,aabc_sex,54,0.046415888336127774,test,0.8545454545454545,0.04825840910749933,0.8533333333333333,0.048308465850341015,0.8627717391304348,0.04604639753169467 +flat_mae,patch,logistic,aabc_sex,55,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,55,21.54434690031882,test,0.8909090909090909,0.041658572877798825,0.8879076086956521,0.0429928992876171,0.8879076086956521,0.04335349410998816 +flat_mae,patch,logistic,aabc_sex,56,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,56,21.54434690031882,test,0.8181818181818182,0.05018977539020279,0.8151881720430108,0.051086827175515465,0.8192934782608696,0.051171298378582135 +flat_mae,patch,logistic,aabc_sex,57,0.3593813663804626,train,0.9905482041587902,0.004133105079139146,0.9903269809575008,0.004223130638293488,0.991221899821214,0.003919951723234826 +flat_mae,patch,logistic,aabc_sex,57,0.3593813663804626,test,0.9090909090909091,0.03755282780341659,0.9071259709557582,0.03836821415727181,0.9096467391304348,0.03821119114869681 +flat_mae,patch,logistic,aabc_sex,58,0.3593813663804626,train,0.9924385633270322,0.0038545234645390686,0.9922570257611241,0.0039422751149347495,0.9928558867493186,0.0037096321827295993 +flat_mae,patch,logistic,aabc_sex,58,0.3593813663804626,test,0.8181818181818182,0.05144522883852235,0.8151881720430108,0.051970568466821555,0.8192934782608696,0.05162918567925512 +flat_mae,patch,logistic,aabc_sex,59,0.046415888336127774,train,0.947069943289225,0.01004284260614961,0.9457991803278689,0.01026110580677899,0.9463422140156511,0.0101824156110469 +flat_mae,patch,logistic,aabc_sex,59,0.046415888336127774,test,0.9090909090909091,0.039573528175175454,0.9071259709557582,0.04030609160723739,0.9096467391304348,0.03973978301956799 +flat_mae,patch,logistic,aabc_sex,60,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,60,2.782559402207126,test,0.8909090909090909,0.03709297676946183,0.8821428571428571,0.043399241681467936,0.8695652173913043,0.04435029831131305 +flat_mae,patch,logistic,aabc_sex,61,0.3593813663804626,train,0.9886578449905482,0.0044509364676094355,0.9883991228070176,0.004540248844781382,0.9895879128931093,0.0041179188105885224 +flat_mae,patch,logistic,aabc_sex,61,0.3593813663804626,test,0.8545454545454545,0.046427407123717374,0.8521505376344086,0.04699889548586324,0.8566576086956521,0.046269629864550015 +flat_mae,patch,logistic,aabc_sex,62,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,62,2.782559402207126,test,0.9818181818181818,0.016719365720105676,0.9814251941911516,0.01694977278756107,0.984375,0.014368204915715811 +flat_mae,patch,logistic,aabc_sex,63,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,63,21.54434690031882,test,0.9454545454545454,0.028883327570940445,0.9447975911676145,0.028902389126117145,0.953125,0.024821609631276935 +flat_mae,patch,logistic,aabc_sex,64,0.3593813663804626,train,0.9924385633270322,0.003786798513555328,0.9922570257611241,0.0038740929487176357,0.9928558867493186,0.003672091667975497 +flat_mae,patch,logistic,aabc_sex,64,0.3593813663804626,test,0.8727272727272727,0.04304894005279828,0.8711943793911007,0.043258943929121024,0.8783967391304348,0.04201691143751516 +flat_mae,patch,logistic,aabc_sex,65,0.3593813663804626,train,0.9886578449905482,0.004513834122949072,0.9883991228070176,0.004604530054333343,0.9895879128931093,0.004187170881858884 +flat_mae,patch,logistic,aabc_sex,65,0.3593813663804626,test,0.9272727272727272,0.03529521307650236,0.9252717391304348,0.036366560155708404,0.9252717391304348,0.03656428930941531 +flat_mae,patch,logistic,aabc_sex,66,0.046415888336127774,train,0.9395085066162571,0.010161555332279984,0.9379053320421398,0.010432734638905188,0.9373736041501802,0.01053878538411042 +flat_mae,patch,logistic,aabc_sex,66,0.046415888336127774,test,0.9272727272727272,0.03636356363629092,0.9252717391304348,0.037506574677144945,0.9252717391304348,0.03768291636441889 +flat_mae,patch,logistic,aabc_sex,67,0.3593813663804626,train,0.994328922495274,0.0032435368506775713,0.9941961885745005,0.00331183100916364,0.9950980392156863,0.002803645415046465 +flat_mae,patch,logistic,aabc_sex,67,0.3593813663804626,test,0.9272727272727272,0.03712431650593797,0.9252717391304348,0.03816103274248126,0.9252717391304348,0.038312557724525326 +flat_mae,patch,logistic,aabc_sex,68,0.046415888336127774,train,0.945179584120983,0.009686831215097298,0.9438299336914217,0.009931135844461147,0.9441000615492834,0.010043124197531773 +flat_mae,patch,logistic,aabc_sex,68,0.046415888336127774,test,0.9636363636363636,0.026223804717933247,0.9621212121212122,0.02805388556670852,0.9565217391304348,0.03135454911926801 +flat_mae,patch,logistic,aabc_sex,69,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,69,166.81005372000556,test,0.9272727272727272,0.034600912422880825,0.9252717391304348,0.03570323598794902,0.9252717391304348,0.03605696384497541 +flat_mae,patch,logistic,aabc_sex,70,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,70,2.782559402207126,test,0.8909090909090909,0.039607645976941254,0.89,0.039586551801505145,0.9001358695652174,0.03682984864295979 +flat_mae,patch,logistic,aabc_sex,71,0.000774263682681127,train,0.8771266540642723,0.014347053982727023,0.8729422632794457,0.01494172683988913,0.8700723936809402,0.015162460501869849 +flat_mae,patch,logistic,aabc_sex,71,0.000774263682681127,test,0.7818181818181819,0.05077702350180126,0.7727272727272727,0.053415582656524185,0.7697010869565217,0.05276502237722602 +flat_mae,patch,logistic,aabc_sex,72,0.3593813663804626,train,0.9924385633270322,0.0035456688423235595,0.9922570257611241,0.0036263050371549287,0.9928558867493186,0.0033942749205489622 +flat_mae,patch,logistic,aabc_sex,72,0.3593813663804626,test,0.9090909090909091,0.03873154052455129,0.905982905982906,0.04032585981605473,0.9035326086956521,0.04090119583816405 +flat_mae,patch,logistic,aabc_sex,73,0.3593813663804626,train,0.9905482041587902,0.004128115088778238,0.9903269809575008,0.004216943583869793,0.991221899821214,0.0038951767598190013 +flat_mae,patch,logistic,aabc_sex,73,0.3593813663804626,test,0.9636363636363636,0.025441529139552093,0.9621212121212122,0.02715940139159333,0.9565217391304348,0.030419219623377496 +flat_mae,patch,logistic,aabc_sex,74,0.046415888336127774,train,0.9508506616257089,0.009018185416789318,0.9495480822842386,0.009272559060787389,0.9490020223335971,0.009508638464472953 +flat_mae,patch,logistic,aabc_sex,74,0.046415888336127774,test,0.8909090909090909,0.043400742652746356,0.8879076086956521,0.044767749053928864,0.8879076086956521,0.045200349914890275 +flat_mae,patch,logistic,aabc_sex,75,0.3593813663804626,train,0.9886578449905482,0.004372071790216722,0.9883991228070176,0.004461588749814692,0.9895879128931093,0.0040901608999732875 +flat_mae,patch,logistic,aabc_sex,75,0.3593813663804626,test,0.9272727272727272,0.03314822209559925,0.9260752688172043,0.03348184239691993,0.9313858695652174,0.03186708994457018 +flat_mae,patch,logistic,aabc_sex,76,0.046415888336127774,train,0.943289224952741,0.010091328623984581,0.9418579090829157,0.010368656522209078,0.9418579090829157,0.010588116458968065 +flat_mae,patch,logistic,aabc_sex,76,0.046415888336127774,test,0.8727272727272727,0.0458398217295655,0.8683760683760684,0.04757609473924986,0.8661684782608696,0.04758266119470326 +flat_mae,patch,logistic,aabc_sex,77,0.3593813663804626,train,0.9886578449905482,0.004621145282600385,0.9883855386416862,0.0047272942544248275,0.9889797473548463,0.004569484623403534 +flat_mae,patch,logistic,aabc_sex,77,0.3593813663804626,test,0.9272727272727272,0.033266268623023745,0.9229691876750701,0.036899297644641,0.9130434782608696,0.03977488639709361 +flat_mae,patch,logistic,aabc_sex,78,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,78,21.54434690031882,test,0.9454545454545454,0.02933759047495267,0.9442755825734549,0.029830908267620165,0.9470108695652174,0.02898396911609022 +flat_mae,patch,logistic,aabc_sex,79,0.3593813663804626,train,0.9924385633270322,0.003676404025044756,0.9922570257611241,0.0037597104807662297,0.9928558867493186,0.0035283241289392063 +flat_mae,patch,logistic,aabc_sex,79,0.3593813663804626,test,0.8909090909090909,0.03963476226956949,0.8863636363636364,0.0422971092055011,0.8817934782608696,0.04354965681829217 +flat_mae,patch,logistic,aabc_sex,80,0.3593813663804626,train,0.994328922495274,0.0032707037813054195,0.9941893034853195,0.0033483793319263105,0.9944898736774231,0.003213071352763994 +flat_mae,patch,logistic,aabc_sex,80,0.3593813663804626,test,0.8545454545454545,0.048837920505881906,0.8521505376344086,0.04940648405116192,0.8566576086956521,0.048948428022359554 +flat_mae,patch,logistic,aabc_sex,81,0.046415888336127774,train,0.9395085066162571,0.009974434249053855,0.938056206088993,0.010195665754860668,0.9385899352267065,0.010163624503654 +flat_mae,patch,logistic,aabc_sex,81,0.046415888336127774,test,0.9636363636363636,0.02580975534704621,0.9626358695652174,0.026566929023660795,0.9626358695652174,0.02698644775990158 +flat_mae,patch,logistic,aabc_sex,82,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,82,166.81005372000556,test,0.9272727272727272,0.032578469795478064,0.9229691876750701,0.036234512091027876,0.9130434782608696,0.03895251823372377 +flat_mae,patch,logistic,aabc_sex,83,0.3593813663804626,train,0.9867674858223062,0.004903687875543317,0.9864577733405013,0.005012281668687529,0.9873457604267417,0.004803736065753266 +flat_mae,patch,logistic,aabc_sex,83,0.3593813663804626,test,0.8909090909090909,0.038761299605501336,0.8821428571428571,0.04549473230497597,0.8695652173913043,0.046345032137012465 +flat_mae,patch,logistic,aabc_sex,84,0.3593813663804626,train,0.996219281663516,0.002612394298635058,0.9961285128805621,0.002670831443028855,0.9967320261437909,0.002258098993428012 +flat_mae,patch,logistic,aabc_sex,84,0.3593813663804626,test,0.9090909090909091,0.04002437273990863,0.905982905982906,0.041826539104401664,0.9035326086956521,0.042670551363574304 +flat_mae,patch,logistic,aabc_sex,85,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,85,166.81005372000556,test,0.8909090909090909,0.04328745356755969,0.8891129032258065,0.04382821910624668,0.8940217391304348,0.042938919465672284 +flat_mae,patch,logistic,aabc_sex,86,0.3593813663804626,train,0.9886578449905482,0.004475297475232874,0.9883855386416862,0.004577247265580902,0.9889797473548463,0.004406620225572415 +flat_mae,patch,logistic,aabc_sex,86,0.3593813663804626,test,0.9272727272727272,0.03452705730221465,0.9260752688172043,0.03493085734599923,0.9313858695652174,0.0336320659243706 +flat_mae,patch,logistic,aabc_sex,87,0.3593813663804626,train,0.9924385633270322,0.003845291655573591,0.9922570257611241,0.003931340478561233,0.9928558867493186,0.0036380504272074212 +flat_mae,patch,logistic,aabc_sex,87,0.3593813663804626,test,0.9090909090909091,0.03820603560989799,0.905982905982906,0.039893767866445044,0.9035326086956521,0.040687917756160895 +flat_mae,patch,logistic,aabc_sex,88,0.3593813663804626,train,0.9905482041587902,0.0042105797480481615,0.9903269809575008,0.00429975563704634,0.991221899821214,0.003941817145479083 +flat_mae,patch,logistic,aabc_sex,88,0.3593813663804626,test,0.8909090909090909,0.040798946672515664,0.884453781512605,0.04496543334906494,0.8756793478260869,0.04614881649108548 +flat_mae,patch,logistic,aabc_sex,89,0.046415888336127774,train,0.943289224952741,0.01019120381242504,0.9419956140350878,0.01040450779783329,0.943074240159442,0.010367066113815286 +flat_mae,patch,logistic,aabc_sex,89,0.046415888336127774,test,0.9090909090909091,0.03601769996465352,0.9027925061859314,0.040934546006901794,0.8913043478260869,0.04306464126208572 +flat_mae,patch,logistic,aabc_sex,90,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,90,21.54434690031882,test,0.8363636363636363,0.05134231254872765,0.8281846581048247,0.05542719920765732,0.8226902173913043,0.05554332967826102 +flat_mae,patch,logistic,aabc_sex,91,0.3593813663804626,train,0.9905482041587902,0.0041684781470150934,0.9903155058088658,0.004268242620429933,0.9906137342829509,0.004207971328397171 +flat_mae,patch,logistic,aabc_sex,91,0.3593813663804626,test,0.8909090909090909,0.041272583099467845,0.89,0.04123135920918216,0.9001358695652174,0.0385616329134072 +flat_mae,patch,logistic,aabc_sex,92,0.3593813663804626,train,0.9924385633270322,0.0036959320911788443,0.9922570257611241,0.003779687987199247,0.9928558867493186,0.003540495738063461 +flat_mae,patch,logistic,aabc_sex,92,0.3593813663804626,test,0.8909090909090909,0.040708372237758826,0.884453781512605,0.045242670067305604,0.8756793478260869,0.04639605689293083 +flat_mae,patch,logistic,aabc_sex,93,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,93,2.782559402207126,test,0.8727272727272727,0.04409844734059509,0.8663658451926415,0.04773306398132326,0.8600543478260869,0.04864735379175175 +flat_mae,patch,logistic,aabc_sex,94,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,94,2.782559402207126,test,0.9454545454545454,0.029793226808057637,0.9442755825734549,0.03024346459685576,0.9470108695652174,0.029029717826260494 +flat_mae,patch,logistic,aabc_sex,95,0.046415888336127774,train,0.947069943289225,0.009532251897856489,0.9457991803278689,0.009759486389477741,0.9463422140156511,0.009839170082295639 +flat_mae,patch,logistic,aabc_sex,95,0.046415888336127774,test,0.9090909090909091,0.03858618773988331,0.9071259709557582,0.039310523325167386,0.9096467391304348,0.03882445226517596 +flat_mae,patch,logistic,aabc_sex,96,0.3593813663804626,train,0.998109640831758,0.001851780248961594,0.9980631011617731,0.0018951964570287569,0.9983660130718954,0.0016006401171579625 +flat_mae,patch,logistic,aabc_sex,96,0.3593813663804626,test,0.9272727272727272,0.034779000028396546,0.9242424242424243,0.03690396877201548,0.9191576086956521,0.0386411165712355 +flat_mae,patch,logistic,aabc_sex,97,0.3593813663804626,train,0.9905482041587902,0.004294834460007566,0.9903269809575008,0.004385965312297221,0.991221899821214,0.004043974771231197 +flat_mae,patch,logistic,aabc_sex,97,0.3593813663804626,test,0.9090909090909091,0.03628739279740359,0.905982905982906,0.03793881084461186,0.9035326086956521,0.03883116937041574 +flat_mae,patch,logistic,aabc_sex,98,0.046415888336127774,train,0.947069943289225,0.009345809550050297,0.9457991803278689,0.009553070720653988,0.9463422140156511,0.009488429131636689 +flat_mae,patch,logistic,aabc_sex,98,0.046415888336127774,test,0.8727272727272727,0.04298204891493213,0.8639095086603039,0.04840505745883859,0.8539402173913043,0.04899899745062858 +flat_mae,patch,logistic,aabc_sex,99,0.3593813663804626,train,0.9924385633270322,0.0036414343460330293,0.9922570257611241,0.0037233362757411906,0.9928558867493186,0.003458227602039974 +flat_mae,patch,logistic,aabc_sex,99,0.3593813663804626,test,0.9454545454545454,0.03179045025275244,0.9435897435897436,0.03319493454265957,0.9408967391304348,0.03448147121148796 +flat_mae,patch,logistic,aabc_sex,100,0.3593813663804626,train,0.9886578449905482,0.0048785317651776385,0.9883991228070176,0.004975470695336992,0.9895879128931093,0.004492136293075245 +flat_mae,patch,logistic,aabc_sex,100,0.3593813663804626,test,0.8909090909090909,0.040509335726369736,0.89,0.040488936800197044,0.9001358695652174,0.03771616141021961 diff --git a/input_space_v3/flat_lr1e-3_3/eval_v2/aabc_sex__patch__logistic/log.txt b/input_space_v3/flat_lr1e-3_3/eval_v2/aabc_sex__patch__logistic/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..5307a1708753bb36709991f9d513b8b186a5ef83 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_3/eval_v2/aabc_sex__patch__logistic/log.txt @@ -0,0 +1,245 @@ +fMRI foundation model logistic probe eval +version: 0.1.dev86+gf97f52698 +sha: bcce2b486277d3a5b520775efd9cdf1a2affce36, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-04-08 22:17:12 +config: +output_root: experiments/input_space_v3/output +name_prefix: eval_logistic +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_3; eval v2 (aabc_sex patch logistic) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: input_space_v3/flat_lr1e-3_3/eval_v2/aabc_sex__patch__logistic +model: flat_mae +representation: patch +dataset: aabc_sex +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/eval_v2/aabc_sex__patch__logistic +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=True, reg_tokens=0, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: aabc_sex (flat) +train (n=471): +HFDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'segment', 'bold', 'mean', 'std'], + num_rows: 471 +}), + labels=[0 1], + counts=[269 202] +) + +validation (n=58): +HFDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'segment', 'bold', 'mean', 'std'], + num_rows: 58 +}), + labels=[0 1], + counts=[36 22] +) + +test (n=55): +HFDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'segment', 'bold', 'mean', 'std'], + num_rows: 55 +}), + labels=[0 1], + counts=[33 22] +) + +extracting features for all splits +extract (train) [ 0/236] eta: 0:23:22 time: 5.9426 data: 4.8042 max mem: 3205 +extract (train) [ 20/236] eta: 0:01:57 time: 0.2726 data: 0.1004 max mem: 3393 +extract (train) [ 40/236] eta: 0:01:19 time: 0.2592 data: 0.0924 max mem: 3393 +extract (train) [ 60/236] eta: 0:01:02 time: 0.2571 data: 0.0879 max mem: 3393 +extract (train) [ 80/236] eta: 0:00:52 time: 0.2812 data: 0.0990 max mem: 3393 +extract (train) [100/236] eta: 0:00:43 time: 0.2557 data: 0.0857 max mem: 3393 +extract (train) [120/236] eta: 0:00:36 time: 0.2610 data: 0.0915 max mem: 3393 +extract (train) [140/236] eta: 0:00:29 time: 0.2586 data: 0.0895 max mem: 3393 +extract (train) [160/236] eta: 0:00:22 time: 0.2612 data: 0.0898 max mem: 3393 +extract (train) [180/236] eta: 0:00:16 time: 0.2635 data: 0.0886 max mem: 3393 +extract (train) [200/236] eta: 0:00:10 time: 0.2713 data: 0.0933 max mem: 3393 +extract (train) [220/236] eta: 0:00:04 time: 0.2208 data: 0.0689 max mem: 3393 +extract (train) [235/236] eta: 0:00:00 time: 0.1973 data: 0.0591 max mem: 3393 +extract (train) Total time: 0:01:06 (0.2826 s / it) +extract (validation) [ 0/29] eta: 0:02:29 time: 5.1548 data: 4.9765 max mem: 3393 +extract (validation) [20/29] eta: 0:00:04 time: 0.2170 data: 0.0620 max mem: 3393 +extract (validation) [28/29] eta: 0:00:00 time: 0.1950 data: 0.0539 max mem: 3393 +extract (validation) Total time: 0:00:11 (0.3983 s / it) +extract (test) [ 0/28] eta: 0:02:40 time: 5.7193 data: 5.4921 max mem: 3393 +extract (test) [20/28] eta: 0:00:04 time: 0.2428 data: 0.0747 max mem: 3393 +extract (test) [27/28] eta: 0:00:00 time: 0.2007 data: 0.0584 max mem: 3393 +extract (test) Total time: 0:00:12 (0.4365 s / it) +feature extraction time: 0:01:30 +train features: (471, 768) +validation features: (58, 768) +test features: (55, 768) +evaluating fixed splits +eval results (fixed splits): + +| model | repr | clf | dataset | trial | C | split | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|--------:|:--------|--------:|----------:|--------:|----------:|--------:|-----------:| +| flat_mae | patch | logistic | aabc_sex | | 0.35938 | train | 0.99055 | 0.0040682 | 0.99034 | 0.0041504 | 0.99121 | 0.0038053 | +| flat_mae | patch | logistic | aabc_sex | | 0.35938 | test | 0.90909 | 0.039097 | 0.90713 | 0.039373 | 0.91667 | 0.036541 | + + +evaluating random splits (n=100) +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 1, "C": 21.54434690031882, "split": "test", "acc": 0.7818181818181819, "acc_std": 0.05545113551363998, "f1": 0.7758152173913043, "f1_std": 0.056986834247449006, "bacc": 0.7758152173913043, "bacc_std": 0.05662444779491383} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 2, "C": 0.046415888336127774, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.04105547949658139, "f1": 0.9071259709557582, "f1_std": 0.04176483863106337, "bacc": 0.9096467391304348, "bacc_std": 0.041056633389286654} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 3, "C": 0.3593813663804626, "split": "test", "acc": 0.8181818181818182, "acc_std": 0.05355730382859491, "f1": 0.8131793478260869, "f1_std": 0.05533455720534445, "bacc": 0.8131793478260869, "bacc_std": 0.05555934978276752} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 4, "C": 21.54434690031882, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.050399842581414896, "f1": 0.8354935194416749, "f1_std": 0.05024155884788907, "bacc": 0.8471467391304348, "bacc_std": 0.04733826769948187} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 5, "C": 0.046415888336127774, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.047699486283769715, "f1": 0.8484848484848485, "f1_std": 0.050504954892117385, "bacc": 0.8444293478260869, "bacc_std": 0.05086695000579118} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 6, "C": 0.3593813663804626, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.04303603717662406, "f1": 0.8879076086956521, "f1_std": 0.044211112790652575, "bacc": 0.8879076086956521, "bacc_std": 0.04433977081690678} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 7, "C": 0.3593813663804626, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.04913000463435657, "f1": 0.8354935194416749, "f1_std": 0.04897572674572996, "bacc": 0.8471467391304348, "bacc_std": 0.046665724949920225} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 8, "C": 2.782559402207126, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.049171529759027964, "f1": 0.8328267477203647, "f1_std": 0.05045668413031784, "bacc": 0.8349184782608696, "bacc_std": 0.05050240661202059} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 9, "C": 0.3593813663804626, "split": "test", "acc": 0.9454545454545454, "acc_std": 0.03081774738229595, "f1": 0.9435897435897436, "f1_std": 0.03218413647209804, "bacc": 0.9408967391304348, "bacc_std": 0.03382174238242263} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 10, "C": 0.3593813663804626, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.042553596734486755, "f1": 0.8891129032258065, "f1_std": 0.04293996886226611, "bacc": 0.8940217391304348, "bacc_std": 0.041665444964761045} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 11, "C": 0.005994842503189409, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.039095559977027516, "f1": 0.9045470322804582, "f1_std": 0.0424735734702768, "bacc": 0.8974184782608696, "bacc_std": 0.04409067525408761} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 12, "C": 0.046415888336127774, "split": "test", "acc": 0.8181818181818182, "acc_std": 0.05215468410775932, "f1": 0.8106060606060606, "f1_std": 0.05551496676886814, "bacc": 0.8070652173913043, "bacc_std": 0.05561450464576429} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 13, "C": 0.3593813663804626, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.043273323143338184, "f1": 0.8879076086956521, "f1_std": 0.044452542565442274, "bacc": 0.8879076086956521, "bacc_std": 0.04445228755199523} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 14, "C": 2.782559402207126, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.0416247065857179, "f1": 0.8891129032258065, "f1_std": 0.04205977032024507, "bacc": 0.8940217391304348, "bacc_std": 0.04103055483180367} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 15, "C": 21.54434690031882, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.04401316106697445, "f1": 0.8250265111346766, "f1_std": 0.04930249741120148, "bacc": 0.8165760869565217, "bacc_std": 0.048722978854727886} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 16, "C": 0.3593813663804626, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.0465507241335231, "f1": 0.84593837535014, "f1_std": 0.051605497053739124, "bacc": 0.8383152173913043, "bacc_std": 0.05191454041156165} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 17, "C": 0.3593813663804626, "split": "test", "acc": 0.9272727272727272, "acc_std": 0.03463910750286505, "f1": 0.9242424242424243, "f1_std": 0.03688055219883087, "bacc": 0.9191576086956521, "bacc_std": 0.03837289279491788} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 18, "C": 0.3593813663804626, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.04229569268654563, "f1": 0.8720505151213027, "f1_std": 0.04218939673262764, "bacc": 0.8845108695652174, "bacc_std": 0.039254261260592324} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 19, "C": 0.3593813663804626, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.042912850374599056, "f1": 0.8683760683760684, "f1_std": 0.04466861718780109, "bacc": 0.8661684782608696, "bacc_std": 0.044990776087452895} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 20, "C": 0.3593813663804626, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.037992100092275605, "f1": 0.905982905982906, "f1_std": 0.03987016719479078, "bacc": 0.9035326086956521, "bacc_std": 0.040974245042385816} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 21, "C": 0.046415888336127774, "split": "test", "acc": 0.8, "acc_std": 0.05050922180754029, "f1": 0.790003471017008, "f1_std": 0.05460227449100145, "bacc": 0.7853260869565217, "bacc_std": 0.054204549915613444} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 22, "C": 2.782559402207126, "split": "test", "acc": 0.9454545454545454, "acc_std": 0.03156824432221053, "f1": 0.9447975911676145, "f1_std": 0.03155911125349677, "bacc": 0.953125, "bacc_std": 0.027128959964399665} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 23, "C": 0.3593813663804626, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.04032625623770152, "f1": 0.9071259709557582, "f1_std": 0.0410846055667245, "bacc": 0.9096467391304348, "bacc_std": 0.040593685105256704} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 24, "C": 2.782559402207126, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.047411488651996, "f1": 0.8683760683760684, "f1_std": 0.049772739079337054, "bacc": 0.8661684782608696, "bacc_std": 0.050161728393043656} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 25, "C": 0.046415888336127774, "split": "test", "acc": 0.9636363636363636, "acc_std": 0.023204901163688015, "f1": 0.9630376344086022, "f1_std": 0.02334271983025949, "bacc": 0.96875, "bacc_std": 0.01994171193754438} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 26, "C": 0.3593813663804626, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.04740434823309942, "f1": 0.8307692307692308, "f1_std": 0.04981713412942737, "bacc": 0.8288043478260869, "bacc_std": 0.050045534042620216} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 27, "C": 166.81005372000556, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.03659365432954303, "f1": 0.905982905982906, "f1_std": 0.038236487622334024, "bacc": 0.9035326086956521, "bacc_std": 0.03912946129808863} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 28, "C": 166.81005372000556, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.046461216386349286, "f1": 0.8484848484848485, "f1_std": 0.049219246905889115, "bacc": 0.8444293478260869, "bacc_std": 0.049440323191568485} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 29, "C": 2.782559402207126, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.04701213488500899, "f1": 0.8521505376344086, "f1_std": 0.047529813093721784, "bacc": 0.8566576086956521, "bacc_std": 0.04677217187126145} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 30, "C": 166.81005372000556, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.04514769152001878, "f1": 0.8711943793911007, "f1_std": 0.04552937215590051, "bacc": 0.8783967391304348, "bacc_std": 0.0443523026258279} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 31, "C": 0.005994842503189409, "split": "test", "acc": 0.8181818181818182, "acc_std": 0.05022585682907633, "f1": 0.8151881720430108, "f1_std": 0.0508431623023483, "bacc": 0.8192934782608696, "bacc_std": 0.05054768892801622} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 32, "C": 0.3593813663804626, "split": "test", "acc": 0.9272727272727272, "acc_std": 0.035177359360393276, "f1": 0.9242424242424243, "f1_std": 0.03742718378151296, "bacc": 0.9191576086956521, "bacc_std": 0.03917614479962339} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 33, "C": 0.3593813663804626, "split": "test", "acc": 0.9454545454545454, "acc_std": 0.0322849093525261, "f1": 0.9442755825734549, "f1_std": 0.03279495688397755, "bacc": 0.9470108695652174, "bacc_std": 0.03153861874704795} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 34, "C": 2.782559402207126, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.042866481154995334, "f1": 0.8879076086956521, "f1_std": 0.04414762885152944, "bacc": 0.8879076086956521, "bacc_std": 0.04441818374145626} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 35, "C": 0.005994842503189409, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.04178123268835755, "f1": 0.8879076086956521, "f1_std": 0.04291608865389405, "bacc": 0.8879076086956521, "bacc_std": 0.04276081810467495} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 36, "C": 0.3593813663804626, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.03768190481402477, "f1": 0.905982905982906, "f1_std": 0.039540261574199945, "bacc": 0.9035326086956521, "bacc_std": 0.04074322842887127} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 37, "C": 0.3593813663804626, "split": "test", "acc": 0.8181818181818182, "acc_std": 0.05284049286248578, "f1": 0.8131793478260869, "f1_std": 0.05465274089691268, "bacc": 0.8131793478260869, "bacc_std": 0.05472729385290482} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 38, "C": 166.81005372000556, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.0448730661546066, "f1": 0.84593837535014, "f1_std": 0.049104353697448956, "bacc": 0.8383152173913043, "bacc_std": 0.049305983265951675} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 39, "C": 0.046415888336127774, "split": "test", "acc": 0.8181818181818182, "acc_std": 0.050182068510574544, "f1": 0.8131793478260869, "f1_std": 0.05189587115638289, "bacc": 0.8131793478260869, "bacc_std": 0.052058944817648174} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 40, "C": 0.3593813663804626, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.04525592970599231, "f1": 0.8505434782608696, "f1_std": 0.046653553627960385, "bacc": 0.8505434782608696, "bacc_std": 0.04689666764494444} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 41, "C": 0.3593813663804626, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.044564137084090225, "f1": 0.8711943793911007, "f1_std": 0.04475461650497854, "bacc": 0.8783967391304348, "bacc_std": 0.04339584188857657} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 42, "C": 0.3593813663804626, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.05211906267590462, "f1": 0.8343927735028438, "f1_std": 0.05246252883595243, "bacc": 0.8410326086956521, "bacc_std": 0.05133280022057388} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 43, "C": 0.3593813663804626, "split": "test", "acc": 0.9454545454545454, "acc_std": 0.02937972539801573, "f1": 0.9447975911676145, "f1_std": 0.029404415306318998, "bacc": 0.953125, "bacc_std": 0.02524820151391976} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 44, "C": 0.3593813663804626, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.04623538768497744, "f1": 0.8484848484848485, "f1_std": 0.04925375700396379, "bacc": 0.8444293478260869, "bacc_std": 0.04952354094996705} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 45, "C": 21.54434690031882, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.0376267181316066, "f1": 0.9071259709557582, "f1_std": 0.03830435547745905, "bacc": 0.9096467391304348, "bacc_std": 0.03785417232098941} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 46, "C": 0.046415888336127774, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.0397935000298805, "f1": 0.9071259709557582, "f1_std": 0.040490327095684, "bacc": 0.9096467391304348, "bacc_std": 0.03985598622758495} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 47, "C": 0.3593813663804626, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.03886924042529864, "f1": 0.9071259709557582, "f1_std": 0.039670762577109046, "bacc": 0.9096467391304348, "bacc_std": 0.03942925594313299} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 48, "C": 0.046415888336127774, "split": "test", "acc": 0.9454545454545454, "acc_std": 0.029847856630829388, "f1": 0.9442755825734549, "f1_std": 0.030281506363586504, "bacc": 0.9470108695652174, "bacc_std": 0.02892172505735102} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 49, "C": 0.3593813663804626, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.04808884339952594, "f1": 0.8521505376344086, "f1_std": 0.048639699210198215, "bacc": 0.8566576086956521, "bacc_std": 0.04777374536705808} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 50, "C": 0.3593813663804626, "split": "test", "acc": 0.9272727272727272, "acc_std": 0.03497741420019828, "f1": 0.9266666666666667, "f1_std": 0.03486633378766793, "bacc": 0.9375, "bacc_std": 0.030058715328295387} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 51, "C": 0.3593813663804626, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.037034020544439286, "f1": 0.9045470322804582, "f1_std": 0.04016031982005333, "bacc": 0.8974184782608696, "bacc_std": 0.041966533533175164} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 52, "C": 21.54434690031882, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.037893125044258825, "f1": 0.9079959852793577, "f1_std": 0.0380694397921639, "bacc": 0.9157608695652174, "bacc_std": 0.035896070576007785} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 53, "C": 0.046415888336127774, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.04406052936511186, "f1": 0.8879076086956521, "f1_std": 0.045337543271216744, "bacc": 0.8879076086956521, "bacc_std": 0.04536888722758947} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 54, "C": 0.046415888336127774, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.04825840910749933, "f1": 0.8533333333333333, "f1_std": 0.048308465850341015, "bacc": 0.8627717391304348, "bacc_std": 0.04604639753169467} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 55, "C": 21.54434690031882, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.041658572877798825, "f1": 0.8879076086956521, "f1_std": 0.0429928992876171, "bacc": 0.8879076086956521, "bacc_std": 0.04335349410998816} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 56, "C": 21.54434690031882, "split": "test", "acc": 0.8181818181818182, "acc_std": 0.05018977539020279, "f1": 0.8151881720430108, "f1_std": 0.051086827175515465, "bacc": 0.8192934782608696, "bacc_std": 0.051171298378582135} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 57, "C": 0.3593813663804626, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.03755282780341659, "f1": 0.9071259709557582, "f1_std": 0.03836821415727181, "bacc": 0.9096467391304348, "bacc_std": 0.03821119114869681} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 58, "C": 0.3593813663804626, "split": "test", "acc": 0.8181818181818182, "acc_std": 0.05144522883852235, "f1": 0.8151881720430108, "f1_std": 0.051970568466821555, "bacc": 0.8192934782608696, "bacc_std": 0.05162918567925512} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 59, "C": 0.046415888336127774, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.039573528175175454, "f1": 0.9071259709557582, "f1_std": 0.04030609160723739, "bacc": 0.9096467391304348, "bacc_std": 0.03973978301956799} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 60, "C": 2.782559402207126, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.03709297676946183, "f1": 0.8821428571428571, "f1_std": 0.043399241681467936, "bacc": 0.8695652173913043, "bacc_std": 0.04435029831131305} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 61, "C": 0.3593813663804626, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.046427407123717374, "f1": 0.8521505376344086, "f1_std": 0.04699889548586324, "bacc": 0.8566576086956521, "bacc_std": 0.046269629864550015} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 62, "C": 2.782559402207126, "split": "test", "acc": 0.9818181818181818, "acc_std": 0.016719365720105676, "f1": 0.9814251941911516, "f1_std": 0.01694977278756107, "bacc": 0.984375, "bacc_std": 0.014368204915715811} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 63, "C": 21.54434690031882, "split": "test", "acc": 0.9454545454545454, "acc_std": 0.028883327570940445, "f1": 0.9447975911676145, "f1_std": 0.028902389126117145, "bacc": 0.953125, "bacc_std": 0.024821609631276935} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 64, "C": 0.3593813663804626, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.04304894005279828, "f1": 0.8711943793911007, "f1_std": 0.043258943929121024, "bacc": 0.8783967391304348, "bacc_std": 0.04201691143751516} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 65, "C": 0.3593813663804626, "split": "test", "acc": 0.9272727272727272, "acc_std": 0.03529521307650236, "f1": 0.9252717391304348, "f1_std": 0.036366560155708404, "bacc": 0.9252717391304348, "bacc_std": 0.03656428930941531} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 66, "C": 0.046415888336127774, "split": "test", "acc": 0.9272727272727272, "acc_std": 0.03636356363629092, "f1": 0.9252717391304348, "f1_std": 0.037506574677144945, "bacc": 0.9252717391304348, "bacc_std": 0.03768291636441889} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 67, "C": 0.3593813663804626, "split": "test", "acc": 0.9272727272727272, "acc_std": 0.03712431650593797, "f1": 0.9252717391304348, "f1_std": 0.03816103274248126, "bacc": 0.9252717391304348, "bacc_std": 0.038312557724525326} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 68, "C": 0.046415888336127774, "split": "test", "acc": 0.9636363636363636, "acc_std": 0.026223804717933247, "f1": 0.9621212121212122, "f1_std": 0.02805388556670852, "bacc": 0.9565217391304348, "bacc_std": 0.03135454911926801} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 69, "C": 166.81005372000556, "split": "test", "acc": 0.9272727272727272, "acc_std": 0.034600912422880825, "f1": 0.9252717391304348, "f1_std": 0.03570323598794902, "bacc": 0.9252717391304348, "bacc_std": 0.03605696384497541} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 70, "C": 2.782559402207126, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.039607645976941254, "f1": 0.89, "f1_std": 0.039586551801505145, "bacc": 0.9001358695652174, "bacc_std": 0.03682984864295979} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 71, "C": 0.000774263682681127, "split": "test", "acc": 0.7818181818181819, "acc_std": 0.05077702350180126, "f1": 0.7727272727272727, "f1_std": 0.053415582656524185, "bacc": 0.7697010869565217, "bacc_std": 0.05276502237722602} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 72, "C": 0.3593813663804626, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.03873154052455129, "f1": 0.905982905982906, "f1_std": 0.04032585981605473, "bacc": 0.9035326086956521, "bacc_std": 0.04090119583816405} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 73, "C": 0.3593813663804626, "split": "test", "acc": 0.9636363636363636, "acc_std": 0.025441529139552093, "f1": 0.9621212121212122, "f1_std": 0.02715940139159333, "bacc": 0.9565217391304348, "bacc_std": 0.030419219623377496} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 74, "C": 0.046415888336127774, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.043400742652746356, "f1": 0.8879076086956521, "f1_std": 0.044767749053928864, "bacc": 0.8879076086956521, "bacc_std": 0.045200349914890275} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 75, "C": 0.3593813663804626, "split": "test", "acc": 0.9272727272727272, "acc_std": 0.03314822209559925, "f1": 0.9260752688172043, "f1_std": 0.03348184239691993, "bacc": 0.9313858695652174, "bacc_std": 0.03186708994457018} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 76, "C": 0.046415888336127774, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.0458398217295655, "f1": 0.8683760683760684, "f1_std": 0.04757609473924986, "bacc": 0.8661684782608696, "bacc_std": 0.04758266119470326} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 77, "C": 0.3593813663804626, "split": "test", "acc": 0.9272727272727272, "acc_std": 0.033266268623023745, "f1": 0.9229691876750701, "f1_std": 0.036899297644641, "bacc": 0.9130434782608696, "bacc_std": 0.03977488639709361} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 78, "C": 21.54434690031882, "split": "test", "acc": 0.9454545454545454, "acc_std": 0.02933759047495267, "f1": 0.9442755825734549, "f1_std": 0.029830908267620165, "bacc": 0.9470108695652174, "bacc_std": 0.02898396911609022} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 79, "C": 0.3593813663804626, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.03963476226956949, "f1": 0.8863636363636364, "f1_std": 0.0422971092055011, "bacc": 0.8817934782608696, "bacc_std": 0.04354965681829217} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 80, "C": 0.3593813663804626, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.048837920505881906, "f1": 0.8521505376344086, "f1_std": 0.04940648405116192, "bacc": 0.8566576086956521, "bacc_std": 0.048948428022359554} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 81, "C": 0.046415888336127774, "split": "test", "acc": 0.9636363636363636, "acc_std": 0.02580975534704621, "f1": 0.9626358695652174, "f1_std": 0.026566929023660795, "bacc": 0.9626358695652174, "bacc_std": 0.02698644775990158} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 82, "C": 166.81005372000556, "split": "test", "acc": 0.9272727272727272, "acc_std": 0.032578469795478064, "f1": 0.9229691876750701, "f1_std": 0.036234512091027876, "bacc": 0.9130434782608696, "bacc_std": 0.03895251823372377} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 83, "C": 0.3593813663804626, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.038761299605501336, "f1": 0.8821428571428571, "f1_std": 0.04549473230497597, "bacc": 0.8695652173913043, "bacc_std": 0.046345032137012465} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 84, "C": 0.3593813663804626, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.04002437273990863, "f1": 0.905982905982906, "f1_std": 0.041826539104401664, "bacc": 0.9035326086956521, "bacc_std": 0.042670551363574304} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 85, "C": 166.81005372000556, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.04328745356755969, "f1": 0.8891129032258065, "f1_std": 0.04382821910624668, "bacc": 0.8940217391304348, "bacc_std": 0.042938919465672284} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 86, "C": 0.3593813663804626, "split": "test", "acc": 0.9272727272727272, "acc_std": 0.03452705730221465, "f1": 0.9260752688172043, "f1_std": 0.03493085734599923, "bacc": 0.9313858695652174, "bacc_std": 0.0336320659243706} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 87, "C": 0.3593813663804626, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.03820603560989799, "f1": 0.905982905982906, "f1_std": 0.039893767866445044, "bacc": 0.9035326086956521, "bacc_std": 0.040687917756160895} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 88, "C": 0.3593813663804626, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.040798946672515664, "f1": 0.884453781512605, "f1_std": 0.04496543334906494, "bacc": 0.8756793478260869, "bacc_std": 0.04614881649108548} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 89, "C": 0.046415888336127774, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.03601769996465352, "f1": 0.9027925061859314, "f1_std": 0.040934546006901794, "bacc": 0.8913043478260869, "bacc_std": 0.04306464126208572} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 90, "C": 21.54434690031882, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.05134231254872765, "f1": 0.8281846581048247, "f1_std": 0.05542719920765732, "bacc": 0.8226902173913043, "bacc_std": 0.05554332967826102} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 91, "C": 0.3593813663804626, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.041272583099467845, "f1": 0.89, "f1_std": 0.04123135920918216, "bacc": 0.9001358695652174, "bacc_std": 0.0385616329134072} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 92, "C": 0.3593813663804626, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.040708372237758826, "f1": 0.884453781512605, "f1_std": 0.045242670067305604, "bacc": 0.8756793478260869, "bacc_std": 0.04639605689293083} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 93, "C": 2.782559402207126, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.04409844734059509, "f1": 0.8663658451926415, "f1_std": 0.04773306398132326, "bacc": 0.8600543478260869, "bacc_std": 0.04864735379175175} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 94, "C": 2.782559402207126, "split": "test", "acc": 0.9454545454545454, "acc_std": 0.029793226808057637, "f1": 0.9442755825734549, "f1_std": 0.03024346459685576, "bacc": 0.9470108695652174, "bacc_std": 0.029029717826260494} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 95, "C": 0.046415888336127774, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.03858618773988331, "f1": 0.9071259709557582, "f1_std": 0.039310523325167386, "bacc": 0.9096467391304348, "bacc_std": 0.03882445226517596} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 96, "C": 0.3593813663804626, "split": "test", "acc": 0.9272727272727272, "acc_std": 0.034779000028396546, "f1": 0.9242424242424243, "f1_std": 0.03690396877201548, "bacc": 0.9191576086956521, "bacc_std": 0.0386411165712355} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 97, "C": 0.3593813663804626, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.03628739279740359, "f1": 0.905982905982906, "f1_std": 0.03793881084461186, "bacc": 0.9035326086956521, "bacc_std": 0.03883116937041574} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 98, "C": 0.046415888336127774, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.04298204891493213, "f1": 0.8639095086603039, "f1_std": 0.04840505745883859, "bacc": 0.8539402173913043, "bacc_std": 0.04899899745062858} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 99, "C": 0.3593813663804626, "split": "test", "acc": 0.9454545454545454, "acc_std": 0.03179045025275244, "f1": 0.9435897435897436, "f1_std": 0.03319493454265957, "bacc": 0.9408967391304348, "bacc_std": 0.03448147121148796} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 100, "C": 0.3593813663804626, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.040509335726369736, "f1": 0.89, "f1_std": 0.040488936800197044, "bacc": 0.9001358695652174, "bacc_std": 0.03771616141021961} +eval results (random splits): + +| model | repr | clf | dataset | split | n_trials | C | C_std | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|-----------:|-------:|--------:|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | aabc_sex | train | 100 | 14.322 | 42.521 | 0.98155 | 0.026344 | 0.98108 | 0.027066 | 0.98144 | 0.027306 | +| flat_mae | patch | logistic | aabc_sex | test | 100 | 14.322 | 42.521 | 0.88982 | 0.043306 | 0.88647 | 0.044688 | 0.88673 | 0.04527 | + + +done! total time: 0:05:48 diff --git a/input_space_v3/flat_lr1e-3_3/eval_v2/abide_dx__patch__logistic/config.yaml b/input_space_v3/flat_lr1e-3_3/eval_v2/abide_dx__patch__logistic/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..8beaa7265215af1def40451ae4d7e9d097009245 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_3/eval_v2/abide_dx__patch__logistic/config.yaml @@ -0,0 +1,30 @@ +output_root: experiments/input_space_v3/output +name_prefix: eval_logistic +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_3; eval v2 (abide_dx patch logistic) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: input_space_v3/flat_lr1e-3_3/eval_v2/abide_dx__patch__logistic +model: flat_mae +representation: patch +dataset: abide_dx +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/eval_v2/abide_dx__patch__logistic +remote_dir: null diff --git a/input_space_v3/flat_lr1e-3_3/eval_v2/abide_dx__patch__logistic/eval_table.csv b/input_space_v3/flat_lr1e-3_3/eval_v2/abide_dx__patch__logistic/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..9992f656ed74e7c8ae1129db6bd566da7d6d6a1a --- /dev/null +++ b/input_space_v3/flat_lr1e-3_3/eval_v2/abide_dx__patch__logistic/eval_table.csv @@ -0,0 +1,203 @@ +model,repr,clf,dataset,trial,C,split,acc,acc_std,f1,f1_std,bacc,bacc_std +flat_mae,patch,logistic,abide_dx,,0.046415888336127774,train,0.8162393162393162,0.01433880547749953,0.8126625223678359,0.014740265983875593,0.8106819226475803,0.01473521513363533 +flat_mae,patch,logistic,abide_dx,,0.046415888336127774,test,0.6290322580645161,0.04337179248007214,0.6255252100840336,0.043939071426446624,0.6252945797329144,0.04367895388755486 +flat_mae,patch,logistic,abide_dx,1,0.3593813663804626,train,0.9002849002849003,0.010893591486192986,0.8989728702888957,0.011064105559101495,0.8980435585086748,0.011169663181971693 +flat_mae,patch,logistic,abide_dx,1,0.3593813663804626,test,0.6451612903225806,0.04300657876252702,0.6443285528031291,0.04322811658789657,0.6465336134453781,0.04344068331182653 +flat_mae,patch,logistic,abide_dx,2,0.3593813663804626,train,0.905982905982906,0.01113750207925099,0.9046823568136932,0.011323011521082626,0.9035068290882244,0.011428420866906703 +flat_mae,patch,logistic,abide_dx,2,0.3593813663804626,test,0.6532258064516129,0.04410852133688608,0.650475254015077,0.044326136532800174,0.6507352941176471,0.04407500460178709 +flat_mae,patch,logistic,abide_dx,3,2.782559402207126,train,0.9914529914529915,0.0034623004566201234,0.9913621262458472,0.0034990717454394253,0.9913621262458472,0.0035108151898283206 +flat_mae,patch,logistic,abide_dx,3,2.782559402207126,test,0.6451612903225806,0.041989097242032154,0.6375232527238905,0.04332711147017001,0.6370798319327731,0.042696028553470336 +flat_mae,patch,logistic,abide_dx,4,0.3593813663804626,train,0.9102564102564102,0.010861724253436036,0.9089211024364727,0.011058200177520542,0.9073827980804725,0.011184595699061021 +flat_mae,patch,logistic,abide_dx,4,0.3593813663804626,test,0.7258064516129032,0.039382364118193576,0.719904331650279,0.04083622773788191,0.7184873949579832,0.040450842236804306 +flat_mae,patch,logistic,abide_dx,5,0.046415888336127774,train,0.7977207977207977,0.015602466235250693,0.7940277043110289,0.015914458574437327,0.7923218899963086,0.0158456294626684 +flat_mae,patch,logistic,abide_dx,5,0.046415888336127774,test,0.6290322580645161,0.04192832134862333,0.6266038229903116,0.042422615643904045,0.6271008403361344,0.04258352000826197 +flat_mae,patch,logistic,abide_dx,6,2.782559402207126,train,0.9943019943019943,0.0028957125365879875,0.9942414174972314,0.0029261785125785553,0.9942414174972314,0.0029311064207352324 +flat_mae,patch,logistic,abide_dx,6,2.782559402207126,test,0.6935483870967742,0.04355305829188673,0.6883597883597883,0.04453848194301506,0.6875,0.04426446183472584 +flat_mae,patch,logistic,abide_dx,7,0.3593813663804626,train,0.905982905982906,0.011834858996559526,0.9046823568136932,0.012052317444609486,0.9035068290882244,0.012223126016098816 +flat_mae,patch,logistic,abide_dx,7,0.3593813663804626,test,0.6532258064516129,0.04286334248553486,0.6465831510572015,0.04431296719286068,0.6460084033613445,0.04373150515235767 +flat_mae,patch,logistic,abide_dx,8,0.3593813663804626,train,0.9202279202279202,0.010229656464462243,0.9192818482715572,0.010368960084060103,0.9187892211148025,0.010477435410441585 +flat_mae,patch,logistic,abide_dx,8,0.3593813663804626,test,0.6774193548387096,0.04054652650541754,0.6766623207301173,0.04073121603662115,0.6790966386554622,0.04103616405807564 +flat_mae,patch,logistic,abide_dx,9,0.3593813663804626,train,0.905982905982906,0.010860164181343217,0.9046823568136932,0.011031393008868979,0.9035068290882244,0.011102634347396442 +flat_mae,patch,logistic,abide_dx,9,0.3593813663804626,test,0.6854838709677419,0.040367536229865594,0.6761968530297957,0.04238242950374441,0.6754201680672269,0.04119526232311009 +flat_mae,patch,logistic,abide_dx,10,0.3593813663804626,train,0.9017094017094017,0.011233474445843595,0.9005745321534795,0.011376149119236968,0.9002214839424141,0.011437739440202044 +flat_mae,patch,logistic,abide_dx,10,0.3593813663804626,test,0.6774193548387096,0.043331656028265594,0.6766623207301173,0.04344998027389303,0.6790966386554622,0.0433712931122584 +flat_mae,patch,logistic,abide_dx,11,0.3593813663804626,train,0.9131054131054132,0.01134801716993655,0.9121021226284385,0.011507326504320067,0.9117386489479513,0.011639895439780076 +flat_mae,patch,logistic,abide_dx,11,0.3593813663804626,test,0.5725806451612904,0.043824913564174756,0.5643931861867832,0.04474779584860554,0.5646008403361344,0.044273694549756784 +flat_mae,patch,logistic,abide_dx,12,0.3593813663804626,train,0.9188034188034188,0.009869683999557339,0.9175368635815636,0.010068991535605542,0.9157253599114064,0.010215592747783732 +flat_mae,patch,logistic,abide_dx,12,0.3593813663804626,test,0.6451612903225806,0.04120392927526601,0.6405797101449275,0.041821707950114737,0.6402310924369747,0.04155381701889031 +flat_mae,patch,logistic,abide_dx,13,0.3593813663804626,train,0.9074074074074074,0.01109941088990335,0.9060946873424365,0.01128391875188066,0.904798818752307,0.011395041745979878 +flat_mae,patch,logistic,abide_dx,13,0.3593813663804626,test,0.6451612903225806,0.04289359581469793,0.6450689565443664,0.043035360616818945,0.6496848739495797,0.043181629615549506 +flat_mae,patch,logistic,abide_dx,14,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,14,1291.5496650148827,test,0.6370967741935484,0.043756599026623294,0.6283716283716283,0.04518740441526309,0.6281512605042017,0.044421377084685035 +flat_mae,patch,logistic,abide_dx,15,0.3593813663804626,train,0.9002849002849003,0.010353914497704127,0.8988364337063663,0.010542052648074096,0.8974529346622371,0.010663201560279957 +flat_mae,patch,logistic,abide_dx,15,0.3593813663804626,test,0.7258064516129032,0.040518556019358096,0.7211640211640211,0.04146511670467718,0.720063025210084,0.04115418969028522 +flat_mae,patch,logistic,abide_dx,16,10000.0,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,16,10000.0,test,0.6129032258064516,0.04133967249957996,0.6112852664576802,0.041352044076267726,0.6123949579831933,0.04134570404261445 +flat_mae,patch,logistic,abide_dx,17,0.3593813663804626,train,0.9074074074074074,0.010249828134852777,0.906338327390959,0.010372097024124487,0.9059800664451827,0.010436440275610992 +flat_mae,patch,logistic,abide_dx,17,0.3593813663804626,test,0.6370967741935484,0.04449079164392355,0.6317074780542539,0.04548551468239325,0.6313025210084033,0.04508618085412664 +flat_mae,patch,logistic,abide_dx,18,0.3593813663804626,train,0.9116809116809117,0.011101164003902486,0.9105188279701647,0.011274731080780712,0.9095607235142118,0.01137526071095477 +flat_mae,patch,logistic,abide_dx,18,0.3593813663804626,test,0.6935483870967742,0.03975618656822422,0.6835885038947085,0.04214719543477339,0.6827731092436975,0.04081320719617547 +flat_mae,patch,logistic,abide_dx,19,0.046415888336127774,train,0.8091168091168092,0.0146225134366621,0.8049999999999999,0.015085261918593516,0.8026578073089701,0.015062221857124048 +flat_mae,patch,logistic,abide_dx,19,0.046415888336127774,test,0.6209677419354839,0.04301480458064807,0.607462787095036,0.04576185385441218,0.608718487394958,0.04412176695199119 +flat_mae,patch,logistic,abide_dx,20,0.3593813663804626,train,0.905982905982906,0.011180344969429223,0.9046823568136932,0.011378228249340887,0.9035068290882244,0.01153384683608285 +flat_mae,patch,logistic,abide_dx,20,0.3593813663804626,test,0.6451612903225806,0.04276902367433925,0.6405797101449275,0.04326834163498406,0.6402310924369747,0.043028899462580705 +flat_mae,patch,logistic,abide_dx,21,0.3593813663804626,train,0.915954415954416,0.010203032994649999,0.9147628700492885,0.010392965378069883,0.9134366925064599,0.010573054230449087 +flat_mae,patch,logistic,abide_dx,21,0.3593813663804626,test,0.5887096774193549,0.04563032928976748,0.5865315462569467,0.04587990794375706,0.5871848739495797,0.045964049202303174 +flat_mae,patch,logistic,abide_dx,22,0.3593813663804626,train,0.905982905982906,0.011147451711565793,0.9048076923076923,0.01131023421097863,0.9040974529346621,0.011413252640175292 +flat_mae,patch,logistic,abide_dx,22,0.3593813663804626,test,0.6774193548387096,0.0402390715898634,0.6688034188034189,0.04171120854530946,0.6680672268907563,0.04093310590627398 +flat_mae,patch,logistic,abide_dx,23,0.3593813663804626,train,0.9102564102564102,0.01106546104827133,0.9089840815780538,0.01126509470878167,0.9076781100036914,0.011403609806935383 +flat_mae,patch,logistic,abide_dx,23,0.3593813663804626,test,0.6532258064516129,0.04387696828033433,0.6465831510572015,0.045305701919547525,0.6460084033613445,0.04469172178657362 +flat_mae,patch,logistic,abide_dx,24,2.782559402207126,train,0.9943019943019943,0.0030198677623262775,0.994237967036575,0.003056156881642874,0.9939461055740126,0.0032125707262324545 +flat_mae,patch,logistic,abide_dx,24,2.782559402207126,test,0.5806451612903226,0.043157432683579196,0.5752305665349143,0.043671535123313066,0.5751050420168067,0.04343892322583984 +flat_mae,patch,logistic,abide_dx,25,0.046415888336127774,train,0.8133903133903134,0.014580659947885504,0.809284625514574,0.01506916248676773,0.8068290882244371,0.015035752904474842 +flat_mae,patch,logistic,abide_dx,25,0.046415888336127774,test,0.6048387096774194,0.044536609944967956,0.6004471624909581,0.045487196600107714,0.6003151260504203,0.045244725097332426 +flat_mae,patch,logistic,abide_dx,26,0.046415888336127774,train,0.8048433048433048,0.015019551763317731,0.8017991282574423,0.015351103985996777,0.8005537098560354,0.015398105189828246 +flat_mae,patch,logistic,abide_dx,26,0.046415888336127774,test,0.5645161290322581,0.04241086324917312,0.5503626107977437,0.04440930920486153,0.5525210084033614,0.04291890285270592 +flat_mae,patch,logistic,abide_dx,27,2.782559402207126,train,0.9943019943019943,0.0029529897350683543,0.9942447694628451,0.0029802688585076464,0.9945367294204503,0.0028294376325043026 +flat_mae,patch,logistic,abide_dx,27,2.782559402207126,test,0.5645161290322581,0.044936549092346026,0.5634941329856584,0.04497188148047038,0.5651260504201681,0.045217984728731106 +flat_mae,patch,logistic,abide_dx,28,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,28,1291.5496650148827,test,0.5887096774193549,0.04487859678657231,0.5841388834089565,0.04559306026155082,0.5840336134453781,0.04545462505489881 +flat_mae,patch,logistic,abide_dx,29,2.782559402207126,train,0.9871794871794872,0.004153696666438915,0.9870393353505308,0.004199737926574838,0.9868955334071613,0.0042573490898558455 +flat_mae,patch,logistic,abide_dx,29,2.782559402207126,test,0.6209677419354839,0.04474886275652243,0.6179613241560145,0.04503195607248571,0.618172268907563,0.04503600513850987 +flat_mae,patch,logistic,abide_dx,30,0.3593813663804626,train,0.9116809116809117,0.011400159857458606,0.9107419712070874,0.011519637720708806,0.9107419712070874,0.011517796080002396 +flat_mae,patch,logistic,abide_dx,30,0.3593813663804626,test,0.6532258064516129,0.04180362644775142,0.6429862738533645,0.043746785528678375,0.6428571428571428,0.04257354237031403 +flat_mae,patch,logistic,abide_dx,31,0.3593813663804626,train,0.9074074074074074,0.010867626211366117,0.9060946873424365,0.011068824484695415,0.904798818752307,0.01123335184684071 +flat_mae,patch,logistic,abide_dx,31,0.3593813663804626,test,0.6048387096774194,0.043991446879401264,0.6017043592264831,0.04410614821335244,0.601890756302521,0.04402149158947519 +flat_mae,patch,logistic,abide_dx,32,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,32,1291.5496650148827,test,0.6532258064516129,0.04346708061020654,0.650475254015077,0.043902531059984345,0.6507352941176471,0.04389476728179776 +flat_mae,patch,logistic,abide_dx,33,0.046415888336127774,train,0.8034188034188035,0.014052708790899187,0.8001336898395722,0.014319384731563689,0.7986710963455149,0.01429530546732026 +flat_mae,patch,logistic,abide_dx,33,0.046415888336127774,test,0.6451612903225806,0.0428937504695548,0.6418067226890756,0.04333200672214733,0.6418067226890756,0.043335531468792675 +flat_mae,patch,logistic,abide_dx,34,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,34,166.81005372000556,test,0.6612903225806451,0.040075033682603574,0.6569169960474308,0.04069306681509759,0.6565126050420168,0.04042924983743274 +flat_mae,patch,logistic,abide_dx,35,0.3593813663804626,train,0.9031339031339032,0.010747307309768216,0.9017939433838051,0.010937067924497706,0.9006275378368402,0.011063303898950274 +flat_mae,patch,logistic,abide_dx,35,0.3593813663804626,test,0.6854838709677419,0.04163893596807669,0.6829891838741396,0.04203787680251706,0.6832983193277311,0.04188982065954423 +flat_mae,patch,logistic,abide_dx,36,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,36,1291.5496650148827,test,0.6290322580645161,0.04121236024345885,0.6274817136886102,0.04129792978396508,0.6286764705882353,0.041305366074420785 +flat_mae,patch,logistic,abide_dx,37,2.782559402207126,train,0.9943019943019943,0.002769364129836079,0.994237967036575,0.002802306672405558,0.9939461055740126,0.0029321168435167476 +flat_mae,patch,logistic,abide_dx,37,2.782559402207126,test,0.6129032258064516,0.04280056538765114,0.6063492063492064,0.0437353780025886,0.60609243697479,0.04328360171909211 +flat_mae,patch,logistic,abide_dx,38,0.046415888336127774,train,0.8076923076923077,0.014057875899516651,0.8046925716405453,0.014291791222524084,0.8034330011074197,0.014280524707080581 +flat_mae,patch,logistic,abide_dx,38,0.046415888336127774,test,0.6290322580645161,0.04461819470403573,0.6242424242424243,0.04515560103369899,0.6239495798319328,0.04497723605809898 +flat_mae,patch,logistic,abide_dx,39,2.782559402207126,train,0.9985754985754985,0.0013623954263416746,0.9985607764426576,0.0013757672925332521,0.9987080103359174,0.001235660968077354 +flat_mae,patch,logistic,abide_dx,39,2.782559402207126,test,0.5887096774193549,0.0430466919740222,0.5841388834089565,0.043421378448672054,0.5840336134453781,0.043258990421383876 +flat_mae,patch,logistic,abide_dx,40,0.046415888336127774,train,0.8091168091168092,0.014419785703062394,0.8063440302379011,0.014633184864058112,0.8053156146179402,0.014607177535246988 +flat_mae,patch,logistic,abide_dx,40,0.046415888336127774,test,0.5967741935483871,0.0425979772887715,0.5782312925170068,0.04613143131598013,0.5819327731092437,0.043649260878609646 +flat_mae,patch,logistic,abide_dx,41,0.3593813663804626,train,0.9017094017094017,0.011727522873014233,0.9005124518613608,0.011890245334255808,0.8999261720191953,0.011981750772194825 +flat_mae,patch,logistic,abide_dx,41,0.3593813663804626,test,0.6290322580645161,0.044594589574911865,0.6227513227513227,0.04554461125674764,0.6223739495798319,0.04500698356302589 +flat_mae,patch,logistic,abide_dx,42,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,42,1291.5496650148827,test,0.6048387096774194,0.042531554668972925,0.6048130081300813,0.04274214424425171,0.6097689075630253,0.04256732072445528 +flat_mae,patch,logistic,abide_dx,43,0.3593813663804626,train,0.9017094017094017,0.010673303144053863,0.9003158988712018,0.01084744939259621,0.8990402362495387,0.01091673806648116 +flat_mae,patch,logistic,abide_dx,43,0.3593813663804626,test,0.6693548387096774,0.04093451471945622,0.6614052614052615,0.04246751402362738,0.6607142857142857,0.04162654758285654 +flat_mae,patch,logistic,abide_dx,44,0.005994842503189409,train,0.7264957264957265,0.01686059503510432,0.7176872743115192,0.017623500682000914,0.7159099298634183,0.017266220500645506 +flat_mae,patch,logistic,abide_dx,44,0.005994842503189409,test,0.5725806451612904,0.042976444313936525,0.5513074349696183,0.04641511921762918,0.5567226890756303,0.043699756475474985 +flat_mae,patch,logistic,abide_dx,45,0.3593813663804626,train,0.9088319088319088,0.010356762541286946,0.9076923076923077,0.010513730783937776,0.9069767441860466,0.010632452141171799 +flat_mae,patch,logistic,abide_dx,45,0.3593813663804626,test,0.6290322580645161,0.04204081065662236,0.6210470369386127,0.04348157884077692,0.6207983193277311,0.042706933483603236 +flat_mae,patch,logistic,abide_dx,46,0.005994842503189409,train,0.7336182336182336,0.015810067389436255,0.7282128682430544,0.01618196069454761,0.7267995570321152,0.016050924707421168 +flat_mae,patch,logistic,abide_dx,46,0.005994842503189409,test,0.5806451612903226,0.04332822183626044,0.5752305665349143,0.04366003568055535,0.5751050420168067,0.04359944638391767 +flat_mae,patch,logistic,abide_dx,47,0.3593813663804626,train,0.9188034188034188,0.010147994179251767,0.9176522642849059,0.010334020731206527,0.9163159837578443,0.010502262461743734 +flat_mae,patch,logistic,abide_dx,47,0.3593813663804626,test,0.6612903225806451,0.03959997687593267,0.6502820306204673,0.04194595427102032,0.6502100840336134,0.04068178587046119 +flat_mae,patch,logistic,abide_dx,48,0.046415888336127774,train,0.8048433048433048,0.014284893182278734,0.8016552446672702,0.014566157809498248,0.8002583979328165,0.014558294161169192 +flat_mae,patch,logistic,abide_dx,48,0.046415888336127774,test,0.6048387096774194,0.04515577155220033,0.5989703649924097,0.04582911302777228,0.5987394957983193,0.04553405770541794 +flat_mae,patch,logistic,abide_dx,49,0.005994842503189409,train,0.7307692307692307,0.016218635054112352,0.7233448503791867,0.016893406644269186,0.7215577703949797,0.01665200583864375 +flat_mae,patch,logistic,abide_dx,49,0.005994842503189409,test,0.5887096774193549,0.042008060645656535,0.5682392298764252,0.045573714481685824,0.5730042016806722,0.042887268771948185 +flat_mae,patch,logistic,abide_dx,50,0.046415888336127774,train,0.811965811965812,0.014245947262891962,0.8088235294117647,0.014558041804124204,0.8073089700996677,0.014575183323392183 +flat_mae,patch,logistic,abide_dx,50,0.046415888336127774,test,0.5645161290322581,0.044241024063618954,0.555142173797502,0.045163866152988334,0.555672268907563,0.044519121354319 +flat_mae,patch,logistic,abide_dx,51,0.3593813663804626,train,0.9173789173789174,0.01056901687298221,0.9161787593567035,0.01077252294305882,0.9147286821705426,0.010958332878994316 +flat_mae,patch,logistic,abide_dx,51,0.3593813663804626,test,0.6129032258064516,0.041837677506108034,0.607905138339921,0.042301059326126225,0.6076680672268908,0.04210945269095508 +flat_mae,patch,logistic,abide_dx,52,0.3593813663804626,train,0.9031339031339032,0.011428703463784776,0.9016579866833674,0.011669880799022364,0.9000369139904023,0.011840915465111498 +flat_mae,patch,logistic,abide_dx,52,0.3593813663804626,test,0.6209677419354839,0.044229238590619335,0.6179613241560145,0.04454936537519137,0.618172268907563,0.04457135727588503 +flat_mae,patch,logistic,abide_dx,53,2.782559402207126,train,0.9971509971509972,0.001994894091998845,0.9971189835182874,0.0020192056658613323,0.9968253968253968,0.002222881988227277 +flat_mae,patch,logistic,abide_dx,53,2.782559402207126,test,0.6774193548387096,0.042146047050677475,0.6760710553814002,0.042257020096097025,0.6775210084033614,0.04218132197530253 +flat_mae,patch,logistic,abide_dx,54,0.3593813663804626,train,0.905982905982906,0.011117327503498406,0.9048076923076923,0.011283593319689386,0.9040974529346621,0.011405403354093697 +flat_mae,patch,logistic,abide_dx,54,0.3593813663804626,test,0.6774193548387096,0.039403311634200695,0.6688034188034189,0.04106324719141257,0.6680672268907563,0.040187153968825856 +flat_mae,patch,logistic,abide_dx,55,0.3593813663804626,train,0.9031339031339032,0.012226189927043577,0.9018593597092128,0.012430531950093734,0.900922849760059,0.012558914633364882 +flat_mae,patch,logistic,abide_dx,55,0.3593813663804626,test,0.6209677419354839,0.04349656115678779,0.6153389215233318,0.044385111955129015,0.6150210084033614,0.04405197406667049 +flat_mae,patch,logistic,abide_dx,56,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,56,21.54434690031882,test,0.6854838709677419,0.041210163496912366,0.6808131476470201,0.041978127067127585,0.6801470588235294,0.04171344795135153 +flat_mae,patch,logistic,abide_dx,57,0.3593813663804626,train,0.9102564102564102,0.010417489070708141,0.9090454772613693,0.010583904123096703,0.9079734219269102,0.010690549010675834 +flat_mae,patch,logistic,abide_dx,57,0.3593813663804626,test,0.6290322580645161,0.04219799966655387,0.6227513227513227,0.04329637383041011,0.6223739495798319,0.042779840625232275 +flat_mae,patch,logistic,abide_dx,58,2.782559402207126,train,0.9943019943019943,0.0029129908238177873,0.9942414174972314,0.0029436781978128363,0.9942414174972314,0.0029496228988884336 +flat_mae,patch,logistic,abide_dx,58,2.782559402207126,test,0.6612903225806451,0.04389468049851368,0.6590730557737627,0.04426509587340182,0.6596638655462186,0.044293220304434305 +flat_mae,patch,logistic,abide_dx,59,0.046415888336127774,train,0.7991452991452992,0.014449416700118978,0.7952357802625183,0.014828695391586088,0.7933185677371724,0.014796964888332808 +flat_mae,patch,logistic,abide_dx,59,0.046415888336127774,test,0.6451612903225806,0.04540066456994104,0.6418067226890756,0.04593766942423239,0.6418067226890756,0.045866530471639404 +flat_mae,patch,logistic,abide_dx,60,2.782559402207126,train,0.9943019943019943,0.003050124673760526,0.9942344177336826,0.003091508831115533,0.9936507936507937,0.0033987103507617158 +flat_mae,patch,logistic,abide_dx,60,2.782559402207126,test,0.6290322580645161,0.04461409276981049,0.6227513227513227,0.04585245592560989,0.6223739495798319,0.04526395791617043 +flat_mae,patch,logistic,abide_dx,61,0.046415888336127774,train,0.8133903133903134,0.014830840280535626,0.8106137209393323,0.015097958752966576,0.8094868955334071,0.015134386093784764 +flat_mae,patch,logistic,abide_dx,61,0.046415888336127774,test,0.5806451612903226,0.04508748577564732,0.5766806722689075,0.045405316200221826,0.5766806722689075,0.045192111735768634 +flat_mae,patch,logistic,abide_dx,62,0.3593813663804626,train,0.9116809116809117,0.0108595449480894,0.9102708943223519,0.01109661526999673,0.9083794758213363,0.011285737242322028 +flat_mae,patch,logistic,abide_dx,62,0.3593813663804626,test,0.5564516129032258,0.04419054322252409,0.5541026479241582,0.04419346970630387,0.5546218487394958,0.04414560252496117 +flat_mae,patch,logistic,abide_dx,63,10000.0,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,63,10000.0,test,0.5161290322580645,0.04383500364120854,0.514993481095176,0.04438481777139778,0.5257352941176471,0.0440434359208474 +flat_mae,patch,logistic,abide_dx,64,0.3593813663804626,train,0.9116809116809117,0.01094873092231158,0.9106334748720812,0.011099665303411603,0.9101513473606497,0.011221818572541216 +flat_mae,patch,logistic,abide_dx,64,0.3593813663804626,test,0.6774193548387096,0.04243377652552885,0.6732542819499341,0.04344233543682853,0.6727941176470589,0.04308222535513617 +flat_mae,patch,logistic,abide_dx,65,10000.0,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,65,10000.0,test,0.6370967741935484,0.04393231005541833,0.626380984265149,0.04569729684251623,0.6265756302521008,0.04450216505660088 +flat_mae,patch,logistic,abide_dx,66,2.782559402207126,train,0.99002849002849,0.0037000244710261674,0.989913358334411,0.003747013293468409,0.9894795127353266,0.0039382691927695125 +flat_mae,patch,logistic,abide_dx,66,2.782559402207126,test,0.6209677419354839,0.043316212031592374,0.620745753888202,0.043627604673452496,0.6292016806722689,0.04308722218498891 +flat_mae,patch,logistic,abide_dx,67,2.782559402207126,train,0.9943019943019943,0.002768390889484286,0.9942414174972314,0.0027983590217892434,0.9942414174972314,0.0028352102429186543 +flat_mae,patch,logistic,abide_dx,67,2.782559402207126,test,0.6935483870967742,0.04135444554692079,0.6883597883597883,0.04275831754755823,0.6875,0.0424320197805079 +flat_mae,patch,logistic,abide_dx,68,0.3593813663804626,train,0.905982905982906,0.01100344172996748,0.904550398839739,0.011222509341021437,0.9029162052417866,0.01139524644640399 +flat_mae,patch,logistic,abide_dx,68,0.3593813663804626,test,0.6612903225806451,0.041500648791989836,0.6580882352941176,0.04212009706380063,0.6580882352941176,0.04208460405977905 +flat_mae,patch,logistic,abide_dx,69,0.3593813663804626,train,0.9131054131054132,0.010466018940119084,0.9116859118591495,0.010696943971223227,0.909671465485419,0.010881557021426945 +flat_mae,patch,logistic,abide_dx,69,0.3593813663804626,test,0.6612903225806451,0.043074902094220005,0.6555555555555556,0.0438853258432345,0.654936974789916,0.04341771017303568 +flat_mae,patch,logistic,abide_dx,70,0.3593813663804626,train,0.9116809116809117,0.01078106157607275,0.9104591836734695,0.010966653493529448,0.909265411590993,0.011099614039050226 +flat_mae,patch,logistic,abide_dx,70,0.3593813663804626,test,0.6935483870967742,0.04149992164279303,0.6906512605042017,0.04186879967660821,0.6906512605042017,0.04177785428851516 +flat_mae,patch,logistic,abide_dx,71,0.046415888336127774,train,0.7934472934472935,0.014950247709500795,0.7902253547250302,0.015239994758314286,0.7890365448504983,0.015253860151505202 +flat_mae,patch,logistic,abide_dx,71,0.046415888336127774,test,0.7016129032258065,0.03795166431319607,0.6928021426180114,0.039781851830785045,0.6917016806722689,0.038784807119913084 +flat_mae,patch,logistic,abide_dx,72,0.046415888336127774,train,0.811965811965812,0.014261611698332842,0.808532795556731,0.014606512636028468,0.8067183462532299,0.014605273402562052 +flat_mae,patch,logistic,abide_dx,72,0.046415888336127774,test,0.5967741935483871,0.044008971155249696,0.5941345902068604,0.0442515679924657,0.5945378151260504,0.04429294226091721 +flat_mae,patch,logistic,abide_dx,73,0.046415888336127774,train,0.8048433048433048,0.015164311380346305,0.802210006108057,0.01539555447472703,0.8014396456256921,0.015403701627023326 +flat_mae,patch,logistic,abide_dx,73,0.046415888336127774,test,0.5645161290322581,0.041817983649425794,0.555142173797502,0.04300330261762354,0.555672268907563,0.042283129945071114 +flat_mae,patch,logistic,abide_dx,74,0.005994842503189409,train,0.7250712250712251,0.015833937661563435,0.7174897149374764,0.016470120190071918,0.7157991878922112,0.016218513095450214 +flat_mae,patch,logistic,abide_dx,74,0.005994842503189409,test,0.6290322580645161,0.04544638984161223,0.6210470369386127,0.04662615869755055,0.6207983193277311,0.04595125151938361 +flat_mae,patch,logistic,abide_dx,75,0.3593813663804626,train,0.905982905982906,0.010552276962944345,0.9047458491295302,0.010717263185489906,0.9038021410114434,0.010826911796387128 +flat_mae,patch,logistic,abide_dx,75,0.3593813663804626,test,0.6854838709677419,0.041612087388851825,0.6829891838741396,0.0419239619511887,0.6832983193277311,0.04185614465874945 +flat_mae,patch,logistic,abide_dx,76,0.3593813663804626,train,0.9045584045584045,0.011352650770798212,0.9033342033816792,0.011551273388459998,0.9025101513473606,0.011726064972759463 +flat_mae,patch,logistic,abide_dx,76,0.3593813663804626,test,0.6774193548387096,0.042410985927791474,0.6704756842944459,0.04388845180811113,0.6696428571428572,0.043137722317929915 +flat_mae,patch,logistic,abide_dx,77,0.046415888336127774,train,0.8062678062678063,0.014103374462314315,0.8027307590584501,0.014478096435168137,0.8009597637504614,0.014521648142621362 +flat_mae,patch,logistic,abide_dx,77,0.046415888336127774,test,0.5564516129032258,0.04474800526309542,0.5561918396564065,0.04489126392537217,0.5593487394957983,0.045260435600571476 +flat_mae,patch,logistic,abide_dx,78,2.782559402207126,train,0.9957264957264957,0.0024647596181625723,0.995679778450177,0.0024929082335983658,0.9955334071613142,0.0025936659769817618 +flat_mae,patch,logistic,abide_dx,78,2.782559402207126,test,0.5403225806451613,0.04652491975456352,0.5352140461629513,0.04718142894236241,0.5351890756302521,0.04697770544612004 +flat_mae,patch,logistic,abide_dx,79,0.3593813663804626,train,0.9102564102564102,0.011296179533280996,0.908790367985679,0.011578026221364317,0.9067921742340347,0.011830388525087613 +flat_mae,patch,logistic,abide_dx,79,0.3593813663804626,test,0.5725806451612904,0.04306920054261297,0.5662332519305657,0.044009299426661194,0.5661764705882353,0.04363176058696979 +flat_mae,patch,logistic,abide_dx,80,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,80,21.54434690031882,test,0.6693548387096774,0.043204749324628124,0.667603792088918,0.043242511716292995,0.66859243697479,0.04309419216287774 +flat_mae,patch,logistic,abide_dx,81,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,81,1291.5496650148827,test,0.6451612903225806,0.04406072280937877,0.6443285528031291,0.04415521009726014,0.6465336134453781,0.04420729292461391 +flat_mae,patch,logistic,abide_dx,82,0.046415888336127774,train,0.8062678062678063,0.014056721080581935,0.8031748649651589,0.014347882920183488,0.8018456995201181,0.014401731014450346 +flat_mae,patch,logistic,abide_dx,82,0.046415888336127774,test,0.6612903225806451,0.04058269649669386,0.6481081081081081,0.04375981376152152,0.6486344537815126,0.041849481374832104 +flat_mae,patch,logistic,abide_dx,83,0.046415888336127774,train,0.7934472934472935,0.015996231323758024,0.7894268662274124,0.016495039879079895,0.7875599852344037,0.016503913572192514 +flat_mae,patch,logistic,abide_dx,83,0.046415888336127774,test,0.6693548387096774,0.04307772843111159,0.665680278818965,0.043627046978333375,0.6654411764705883,0.04356356585448422 +flat_mae,patch,logistic,abide_dx,84,0.046415888336127774,train,0.801994301994302,0.015190610684415528,0.7983004636414561,0.015573269101029576,0.7964931709117755,0.015571686982268773 +flat_mae,patch,logistic,abide_dx,84,0.046415888336127774,test,0.6209677419354839,0.04418017221634108,0.6203504657677024,0.04418499944124069,0.6228991596638656,0.04411356443694859 +flat_mae,patch,logistic,abide_dx,85,2.782559402207126,train,0.9971509971509972,0.0018715932191784724,0.9971223847314226,0.0018889636060742277,0.9974160206718345,0.0016974915243711823 +flat_mae,patch,logistic,abide_dx,85,2.782559402207126,test,0.6774193548387096,0.042041215964220884,0.6753076721654884,0.04233615159370961,0.6759453781512605,0.042360843340025885 +flat_mae,patch,logistic,abide_dx,86,0.3593813663804626,train,0.9088319088319088,0.010788121254341513,0.9078074725851992,0.01092012705581729,0.9075673680324843,0.010982190645379345 +flat_mae,patch,logistic,abide_dx,86,0.3593813663804626,test,0.6290322580645161,0.044334279692798566,0.6169755573462261,0.046976802217568794,0.6176470588235294,0.04521400531829196 +flat_mae,patch,logistic,abide_dx,87,0.3593813663804626,train,0.905982905982906,0.010622808084046814,0.904867892605764,0.010769721227459096,0.9043927648578811,0.010858219530588461 +flat_mae,patch,logistic,abide_dx,87,0.3593813663804626,test,0.6693548387096774,0.04393811275352312,0.6693333333333333,0.04411108839172643,0.6748949579831933,0.04355453576608326 +flat_mae,patch,logistic,abide_dx,88,2.782559402207126,train,0.9943019943019943,0.0028116222941858633,0.9942344177336826,0.0028492232825984604,0.9936507936507937,0.003132950556378516 +flat_mae,patch,logistic,abide_dx,88,2.782559402207126,test,0.5887096774193549,0.043871264230497184,0.5884687967723043,0.04401376082358202,0.5919117647058824,0.04401328196868175 +flat_mae,patch,logistic,abide_dx,89,0.046415888336127774,train,0.801994301994302,0.01476233417643588,0.7979764100844094,0.015179059352274385,0.7959025470653378,0.015151057995190858 +flat_mae,patch,logistic,abide_dx,89,0.046415888336127774,test,0.5806451612903226,0.043300642368821154,0.580536039552433,0.04331349409214275,0.5845588235294117,0.04325695404188943 +flat_mae,patch,logistic,abide_dx,90,0.3593813663804626,train,0.9116809116809117,0.00999044640680836,0.910335223152482,0.010193832563477554,0.9086747877445551,0.010359097408394828 +flat_mae,patch,logistic,abide_dx,90,0.3593813663804626,test,0.6209677419354839,0.04231730334426929,0.6049081418208935,0.04542519461724438,0.6071428571428572,0.04329156801700556 +flat_mae,patch,logistic,abide_dx,91,0.3593813663804626,train,0.9074074074074074,0.010403741975625741,0.9062798459563544,0.010559557278019018,0.9056847545219637,0.010706606085682075 +flat_mae,patch,logistic,abide_dx,91,0.3593813663804626,test,0.6451612903225806,0.04179685211872227,0.6428384393820372,0.04197365285141334,0.6433823529411764,0.04194891114905117 +flat_mae,patch,logistic,abide_dx,92,2.782559402207126,train,0.9943019943019943,0.0029449981354397136,0.994237967036575,0.002980606461482422,0.9939461055740126,0.003147478127863617 +flat_mae,patch,logistic,abide_dx,92,2.782559402207126,test,0.5806451612903226,0.04304249467159903,0.5694444444444444,0.044334471906568695,0.5703781512605042,0.04334735036744757 +flat_mae,patch,logistic,abide_dx,93,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,93,1291.5496650148827,test,0.5645161290322581,0.043845177428845125,0.5528846153846154,0.04527784334780585,0.5540966386554622,0.044390637229057596 +flat_mae,patch,logistic,abide_dx,94,0.046415888336127774,train,0.8034188034188035,0.01484314188600937,0.8002803776852347,0.015152260042743254,0.7989664082687338,0.015170447388336403 +flat_mae,patch,logistic,abide_dx,94,0.046415888336127774,test,0.6774193548387096,0.04256579347543693,0.6770833333333333,0.04257915722423383,0.680672268907563,0.0426226035540377 +flat_mae,patch,logistic,abide_dx,95,0.046415888336127774,train,0.8205128205128205,0.01469692823952551,0.8179055806714592,0.014962955817357251,0.8168327796234773,0.01498894261648567 +flat_mae,patch,logistic,abide_dx,95,0.046415888336127774,test,0.6693548387096774,0.04018094803271188,0.6575739206573719,0.04277269709355297,0.657563025210084,0.04126483636912403 +flat_mae,patch,logistic,abide_dx,96,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,96,166.81005372000556,test,0.5725806451612904,0.044554973701952584,0.5691904293674206,0.04493482221626299,0.569327731092437,0.044755491364352945 +flat_mae,patch,logistic,abide_dx,97,0.3593813663804626,train,0.9074074074074074,0.010630461160788605,0.9061580320950635,0.010786347158056068,0.905094130675526,0.010838657639963667 +flat_mae,patch,logistic,abide_dx,97,0.3593813663804626,test,0.6451612903225806,0.04465887294101949,0.6428384393820372,0.04507165557315406,0.6433823529411764,0.04505045390601817 +flat_mae,patch,logistic,abide_dx,98,0.046415888336127774,train,0.811965811965812,0.014636106833779649,0.8083823419935978,0.015044805252458443,0.8064230343300111,0.015063534918649878 +flat_mae,patch,logistic,abide_dx,98,0.046415888336127774,test,0.6209677419354839,0.04378766700199529,0.6137071651090342,0.04493953151509092,0.6134453781512605,0.044352944895630506 +flat_mae,patch,logistic,abide_dx,99,0.3593813663804626,train,0.9031339031339032,0.011088024448318485,0.9015874324825794,0.011329881968756334,0.8997416020671835,0.011490736641136142 +flat_mae,patch,logistic,abide_dx,99,0.3593813663804626,test,0.6290322580645161,0.0421381301000016,0.6266038229903116,0.042465556267628525,0.6271008403361344,0.042543073581126994 +flat_mae,patch,logistic,abide_dx,100,0.046415888336127774,train,0.801994301994302,0.015428314796511248,0.7979764100844094,0.01587065592321041,0.7959025470653378,0.0158375404714679 +flat_mae,patch,logistic,abide_dx,100,0.046415888336127774,test,0.6612903225806451,0.04239476780392603,0.6539994685091681,0.043500014734034,0.6533613445378151,0.04295310863168431 diff --git a/input_space_v3/flat_lr1e-3_3/eval_v2/abide_dx__patch__logistic/log.txt b/input_space_v3/flat_lr1e-3_3/eval_v2/abide_dx__patch__logistic/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..dd6ebaf140347956dcb592c49ee0f1642cc28b11 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_3/eval_v2/abide_dx__patch__logistic/log.txt @@ -0,0 +1,252 @@ +fMRI foundation model logistic probe eval +version: 0.1.dev86+gf97f52698 +sha: bcce2b486277d3a5b520775efd9cdf1a2affce36, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-04-08 22:10:04 +config: +output_root: experiments/input_space_v3/output +name_prefix: eval_logistic +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_3; eval v2 (abide_dx patch logistic) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: input_space_v3/flat_lr1e-3_3/eval_v2/abide_dx__patch__logistic +model: flat_mae +representation: patch +dataset: abide_dx +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/eval_v2/abide_dx__patch__logistic +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=True, reg_tokens=0, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: abide_dx (flat) +train (n=578): +HFDataset( + dataset=Dataset({ + features: ['sub', 'site', 'dataset', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 578 +}), + labels=['Autism' 'Control'], + counts=[260 318] +) + +validation (n=124): +HFDataset( + dataset=Dataset({ + features: ['sub', 'site', 'dataset', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 124 +}), + labels=['Autism' 'Control'], + counts=[54 70] +) + +test (n=124): +HFDataset( + dataset=Dataset({ + features: ['sub', 'site', 'dataset', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 124 +}), + labels=['Autism' 'Control'], + counts=[57 67] +) + +extracting features for all splits +extract (train) [ 0/289] eta: 0:22:31 time: 4.6774 data: 3.8850 max mem: 2698 +extract (train) [ 20/289] eta: 0:02:01 time: 0.2391 data: 0.0871 max mem: 2851 +extract (train) [ 40/289] eta: 0:01:21 time: 0.2014 data: 0.0670 max mem: 2851 +extract (train) [ 60/289] eta: 0:01:05 time: 0.2008 data: 0.0677 max mem: 2851 +extract (train) [ 80/289] eta: 0:00:55 time: 0.1979 data: 0.0663 max mem: 2851 +extract (train) [100/289] eta: 0:00:47 time: 0.1905 data: 0.0633 max mem: 2851 +extract (train) [120/289] eta: 0:00:41 time: 0.2142 data: 0.0763 max mem: 2851 +extract (train) [140/289] eta: 0:00:35 time: 0.1822 data: 0.0589 max mem: 2851 +extract (train) [160/289] eta: 0:00:29 time: 0.1840 data: 0.0607 max mem: 2851 +extract (train) [180/289] eta: 0:00:24 time: 0.1752 data: 0.0548 max mem: 2851 +extract (train) [200/289] eta: 0:00:19 time: 0.1930 data: 0.0627 max mem: 2851 +extract (train) [220/289] eta: 0:00:14 time: 0.1746 data: 0.0547 max mem: 2851 +extract (train) [240/289] eta: 0:00:10 time: 0.1809 data: 0.0603 max mem: 2851 +extract (train) [260/289] eta: 0:00:06 time: 0.1954 data: 0.0657 max mem: 2851 +extract (train) [280/289] eta: 0:00:01 time: 0.1705 data: 0.0516 max mem: 2851 +extract (train) [288/289] eta: 0:00:00 time: 0.1713 data: 0.0520 max mem: 2851 +extract (train) Total time: 0:01:00 (0.2095 s / it) +extract (validation) [ 0/62] eta: 0:04:24 time: 4.2594 data: 4.0284 max mem: 2851 +extract (validation) [20/62] eta: 0:00:18 time: 0.2497 data: 0.0966 max mem: 2851 +extract (validation) [40/62] eta: 0:00:07 time: 0.1899 data: 0.0616 max mem: 2851 +extract (validation) [60/62] eta: 0:00:00 time: 0.1818 data: 0.0581 max mem: 2851 +extract (validation) [61/62] eta: 0:00:00 time: 0.1806 data: 0.0579 max mem: 2851 +extract (validation) Total time: 0:00:17 (0.2784 s / it) +extract (test) [ 0/62] eta: 0:04:21 time: 4.2101 data: 4.0294 max mem: 2851 +extract (test) [20/62] eta: 0:00:18 time: 0.2561 data: 0.0917 max mem: 2851 +extract (test) [40/62] eta: 0:00:06 time: 0.1775 data: 0.0551 max mem: 2851 +extract (test) [60/62] eta: 0:00:00 time: 0.1655 data: 0.0508 max mem: 2851 +extract (test) [61/62] eta: 0:00:00 time: 0.1652 data: 0.0508 max mem: 2851 +extract (test) Total time: 0:00:16 (0.2690 s / it) +feature extraction time: 0:01:34 +train features: (578, 768) +validation features: (124, 768) +test features: (124, 768) +evaluating fixed splits +eval results (fixed splits): + +| model | repr | clf | dataset | trial | C | split | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|---------:|:--------|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | abide_dx | | 0.046416 | train | 0.81624 | 0.014339 | 0.81266 | 0.01474 | 0.81068 | 0.014735 | +| flat_mae | patch | logistic | abide_dx | | 0.046416 | test | 0.62903 | 0.043372 | 0.62553 | 0.043939 | 0.62529 | 0.043679 | + + +evaluating random splits (n=100) +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 1, "C": 0.3593813663804626, "split": "test", "acc": 0.6451612903225806, "acc_std": 0.04300657876252702, "f1": 0.6443285528031291, "f1_std": 0.04322811658789657, "bacc": 0.6465336134453781, "bacc_std": 0.04344068331182653} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 2, "C": 0.3593813663804626, "split": "test", "acc": 0.6532258064516129, "acc_std": 0.04410852133688608, "f1": 0.650475254015077, "f1_std": 0.044326136532800174, "bacc": 0.6507352941176471, "bacc_std": 0.04407500460178709} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 3, "C": 2.782559402207126, "split": "test", "acc": 0.6451612903225806, "acc_std": 0.041989097242032154, "f1": 0.6375232527238905, "f1_std": 0.04332711147017001, "bacc": 0.6370798319327731, "bacc_std": 0.042696028553470336} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 4, "C": 0.3593813663804626, "split": "test", "acc": 0.7258064516129032, "acc_std": 0.039382364118193576, "f1": 0.719904331650279, "f1_std": 0.04083622773788191, "bacc": 0.7184873949579832, "bacc_std": 0.040450842236804306} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 5, "C": 0.046415888336127774, "split": "test", "acc": 0.6290322580645161, "acc_std": 0.04192832134862333, "f1": 0.6266038229903116, "f1_std": 0.042422615643904045, "bacc": 0.6271008403361344, "bacc_std": 0.04258352000826197} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 6, "C": 2.782559402207126, "split": "test", "acc": 0.6935483870967742, "acc_std": 0.04355305829188673, "f1": 0.6883597883597883, "f1_std": 0.04453848194301506, "bacc": 0.6875, "bacc_std": 0.04426446183472584} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 7, "C": 0.3593813663804626, "split": "test", "acc": 0.6532258064516129, "acc_std": 0.04286334248553486, "f1": 0.6465831510572015, "f1_std": 0.04431296719286068, "bacc": 0.6460084033613445, "bacc_std": 0.04373150515235767} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 8, "C": 0.3593813663804626, "split": "test", "acc": 0.6774193548387096, "acc_std": 0.04054652650541754, "f1": 0.6766623207301173, "f1_std": 0.04073121603662115, "bacc": 0.6790966386554622, "bacc_std": 0.04103616405807564} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 9, "C": 0.3593813663804626, "split": "test", "acc": 0.6854838709677419, "acc_std": 0.040367536229865594, "f1": 0.6761968530297957, "f1_std": 0.04238242950374441, "bacc": 0.6754201680672269, "bacc_std": 0.04119526232311009} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 10, "C": 0.3593813663804626, "split": "test", "acc": 0.6774193548387096, "acc_std": 0.043331656028265594, "f1": 0.6766623207301173, "f1_std": 0.04344998027389303, "bacc": 0.6790966386554622, "bacc_std": 0.0433712931122584} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 11, "C": 0.3593813663804626, "split": "test", "acc": 0.5725806451612904, "acc_std": 0.043824913564174756, "f1": 0.5643931861867832, "f1_std": 0.04474779584860554, "bacc": 0.5646008403361344, "bacc_std": 0.044273694549756784} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 12, "C": 0.3593813663804626, "split": "test", "acc": 0.6451612903225806, "acc_std": 0.04120392927526601, "f1": 0.6405797101449275, "f1_std": 0.041821707950114737, "bacc": 0.6402310924369747, "bacc_std": 0.04155381701889031} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 13, "C": 0.3593813663804626, "split": "test", "acc": 0.6451612903225806, "acc_std": 0.04289359581469793, "f1": 0.6450689565443664, "f1_std": 0.043035360616818945, "bacc": 0.6496848739495797, "bacc_std": 0.043181629615549506} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 14, "C": 1291.5496650148827, "split": "test", "acc": 0.6370967741935484, "acc_std": 0.043756599026623294, "f1": 0.6283716283716283, "f1_std": 0.04518740441526309, "bacc": 0.6281512605042017, "bacc_std": 0.044421377084685035} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 15, "C": 0.3593813663804626, "split": "test", "acc": 0.7258064516129032, "acc_std": 0.040518556019358096, "f1": 0.7211640211640211, "f1_std": 0.04146511670467718, "bacc": 0.720063025210084, "bacc_std": 0.04115418969028522} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 16, "C": 10000.0, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.04133967249957996, "f1": 0.6112852664576802, "f1_std": 0.041352044076267726, "bacc": 0.6123949579831933, "bacc_std": 0.04134570404261445} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 17, "C": 0.3593813663804626, "split": "test", "acc": 0.6370967741935484, "acc_std": 0.04449079164392355, "f1": 0.6317074780542539, "f1_std": 0.04548551468239325, "bacc": 0.6313025210084033, "bacc_std": 0.04508618085412664} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 18, "C": 0.3593813663804626, "split": "test", "acc": 0.6935483870967742, "acc_std": 0.03975618656822422, "f1": 0.6835885038947085, "f1_std": 0.04214719543477339, "bacc": 0.6827731092436975, "bacc_std": 0.04081320719617547} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 19, "C": 0.046415888336127774, "split": "test", "acc": 0.6209677419354839, "acc_std": 0.04301480458064807, "f1": 0.607462787095036, "f1_std": 0.04576185385441218, "bacc": 0.608718487394958, "bacc_std": 0.04412176695199119} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 20, "C": 0.3593813663804626, "split": "test", "acc": 0.6451612903225806, "acc_std": 0.04276902367433925, "f1": 0.6405797101449275, "f1_std": 0.04326834163498406, "bacc": 0.6402310924369747, "bacc_std": 0.043028899462580705} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 21, "C": 0.3593813663804626, "split": "test", "acc": 0.5887096774193549, "acc_std": 0.04563032928976748, "f1": 0.5865315462569467, "f1_std": 0.04587990794375706, "bacc": 0.5871848739495797, "bacc_std": 0.045964049202303174} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 22, "C": 0.3593813663804626, "split": "test", "acc": 0.6774193548387096, "acc_std": 0.0402390715898634, "f1": 0.6688034188034189, "f1_std": 0.04171120854530946, "bacc": 0.6680672268907563, "bacc_std": 0.04093310590627398} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 23, "C": 0.3593813663804626, "split": "test", "acc": 0.6532258064516129, "acc_std": 0.04387696828033433, "f1": 0.6465831510572015, "f1_std": 0.045305701919547525, "bacc": 0.6460084033613445, "bacc_std": 0.04469172178657362} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 24, "C": 2.782559402207126, "split": "test", "acc": 0.5806451612903226, "acc_std": 0.043157432683579196, "f1": 0.5752305665349143, "f1_std": 0.043671535123313066, "bacc": 0.5751050420168067, "bacc_std": 0.04343892322583984} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 25, "C": 0.046415888336127774, "split": "test", "acc": 0.6048387096774194, "acc_std": 0.044536609944967956, "f1": 0.6004471624909581, "f1_std": 0.045487196600107714, "bacc": 0.6003151260504203, "bacc_std": 0.045244725097332426} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 26, "C": 0.046415888336127774, "split": "test", "acc": 0.5645161290322581, "acc_std": 0.04241086324917312, "f1": 0.5503626107977437, "f1_std": 0.04440930920486153, "bacc": 0.5525210084033614, "bacc_std": 0.04291890285270592} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 27, "C": 2.782559402207126, "split": "test", "acc": 0.5645161290322581, "acc_std": 0.044936549092346026, "f1": 0.5634941329856584, "f1_std": 0.04497188148047038, "bacc": 0.5651260504201681, "bacc_std": 0.045217984728731106} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 28, "C": 1291.5496650148827, "split": "test", "acc": 0.5887096774193549, "acc_std": 0.04487859678657231, "f1": 0.5841388834089565, "f1_std": 0.04559306026155082, "bacc": 0.5840336134453781, "bacc_std": 0.04545462505489881} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 29, "C": 2.782559402207126, "split": "test", "acc": 0.6209677419354839, "acc_std": 0.04474886275652243, "f1": 0.6179613241560145, "f1_std": 0.04503195607248571, "bacc": 0.618172268907563, "bacc_std": 0.04503600513850987} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 30, "C": 0.3593813663804626, "split": "test", "acc": 0.6532258064516129, "acc_std": 0.04180362644775142, "f1": 0.6429862738533645, "f1_std": 0.043746785528678375, "bacc": 0.6428571428571428, "bacc_std": 0.04257354237031403} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 31, "C": 0.3593813663804626, "split": "test", "acc": 0.6048387096774194, "acc_std": 0.043991446879401264, "f1": 0.6017043592264831, "f1_std": 0.04410614821335244, "bacc": 0.601890756302521, "bacc_std": 0.04402149158947519} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 32, "C": 1291.5496650148827, "split": "test", "acc": 0.6532258064516129, "acc_std": 0.04346708061020654, "f1": 0.650475254015077, "f1_std": 0.043902531059984345, "bacc": 0.6507352941176471, "bacc_std": 0.04389476728179776} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 33, "C": 0.046415888336127774, "split": "test", "acc": 0.6451612903225806, "acc_std": 0.0428937504695548, "f1": 0.6418067226890756, "f1_std": 0.04333200672214733, "bacc": 0.6418067226890756, "bacc_std": 0.043335531468792675} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 34, "C": 166.81005372000556, "split": "test", "acc": 0.6612903225806451, "acc_std": 0.040075033682603574, "f1": 0.6569169960474308, "f1_std": 0.04069306681509759, "bacc": 0.6565126050420168, "bacc_std": 0.04042924983743274} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 35, "C": 0.3593813663804626, "split": "test", "acc": 0.6854838709677419, "acc_std": 0.04163893596807669, "f1": 0.6829891838741396, "f1_std": 0.04203787680251706, "bacc": 0.6832983193277311, "bacc_std": 0.04188982065954423} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 36, "C": 1291.5496650148827, "split": "test", "acc": 0.6290322580645161, "acc_std": 0.04121236024345885, "f1": 0.6274817136886102, "f1_std": 0.04129792978396508, "bacc": 0.6286764705882353, "bacc_std": 0.041305366074420785} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 37, "C": 2.782559402207126, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.04280056538765114, "f1": 0.6063492063492064, "f1_std": 0.0437353780025886, "bacc": 0.60609243697479, "bacc_std": 0.04328360171909211} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 38, "C": 0.046415888336127774, "split": "test", "acc": 0.6290322580645161, "acc_std": 0.04461819470403573, "f1": 0.6242424242424243, "f1_std": 0.04515560103369899, "bacc": 0.6239495798319328, "bacc_std": 0.04497723605809898} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 39, "C": 2.782559402207126, "split": "test", "acc": 0.5887096774193549, "acc_std": 0.0430466919740222, "f1": 0.5841388834089565, "f1_std": 0.043421378448672054, "bacc": 0.5840336134453781, "bacc_std": 0.043258990421383876} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 40, "C": 0.046415888336127774, "split": "test", "acc": 0.5967741935483871, "acc_std": 0.0425979772887715, "f1": 0.5782312925170068, "f1_std": 0.04613143131598013, "bacc": 0.5819327731092437, "bacc_std": 0.043649260878609646} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 41, "C": 0.3593813663804626, "split": "test", "acc": 0.6290322580645161, "acc_std": 0.044594589574911865, "f1": 0.6227513227513227, "f1_std": 0.04554461125674764, "bacc": 0.6223739495798319, "bacc_std": 0.04500698356302589} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 42, "C": 1291.5496650148827, "split": "test", "acc": 0.6048387096774194, "acc_std": 0.042531554668972925, "f1": 0.6048130081300813, "f1_std": 0.04274214424425171, "bacc": 0.6097689075630253, "bacc_std": 0.04256732072445528} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 43, "C": 0.3593813663804626, "split": "test", "acc": 0.6693548387096774, "acc_std": 0.04093451471945622, "f1": 0.6614052614052615, "f1_std": 0.04246751402362738, "bacc": 0.6607142857142857, "bacc_std": 0.04162654758285654} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 44, "C": 0.005994842503189409, "split": "test", "acc": 0.5725806451612904, "acc_std": 0.042976444313936525, "f1": 0.5513074349696183, "f1_std": 0.04641511921762918, "bacc": 0.5567226890756303, "bacc_std": 0.043699756475474985} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 45, "C": 0.3593813663804626, "split": "test", "acc": 0.6290322580645161, "acc_std": 0.04204081065662236, "f1": 0.6210470369386127, "f1_std": 0.04348157884077692, "bacc": 0.6207983193277311, "bacc_std": 0.042706933483603236} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 46, "C": 0.005994842503189409, "split": "test", "acc": 0.5806451612903226, "acc_std": 0.04332822183626044, "f1": 0.5752305665349143, "f1_std": 0.04366003568055535, "bacc": 0.5751050420168067, "bacc_std": 0.04359944638391767} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 47, "C": 0.3593813663804626, "split": "test", "acc": 0.6612903225806451, "acc_std": 0.03959997687593267, "f1": 0.6502820306204673, "f1_std": 0.04194595427102032, "bacc": 0.6502100840336134, "bacc_std": 0.04068178587046119} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 48, "C": 0.046415888336127774, "split": "test", "acc": 0.6048387096774194, "acc_std": 0.04515577155220033, "f1": 0.5989703649924097, "f1_std": 0.04582911302777228, "bacc": 0.5987394957983193, "bacc_std": 0.04553405770541794} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 49, "C": 0.005994842503189409, "split": "test", "acc": 0.5887096774193549, "acc_std": 0.042008060645656535, "f1": 0.5682392298764252, "f1_std": 0.045573714481685824, "bacc": 0.5730042016806722, "bacc_std": 0.042887268771948185} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 50, "C": 0.046415888336127774, "split": "test", "acc": 0.5645161290322581, "acc_std": 0.044241024063618954, "f1": 0.555142173797502, "f1_std": 0.045163866152988334, "bacc": 0.555672268907563, "bacc_std": 0.044519121354319} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 51, "C": 0.3593813663804626, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.041837677506108034, "f1": 0.607905138339921, "f1_std": 0.042301059326126225, "bacc": 0.6076680672268908, "bacc_std": 0.04210945269095508} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 52, "C": 0.3593813663804626, "split": "test", "acc": 0.6209677419354839, "acc_std": 0.044229238590619335, "f1": 0.6179613241560145, "f1_std": 0.04454936537519137, "bacc": 0.618172268907563, "bacc_std": 0.04457135727588503} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 53, "C": 2.782559402207126, "split": "test", "acc": 0.6774193548387096, "acc_std": 0.042146047050677475, "f1": 0.6760710553814002, "f1_std": 0.042257020096097025, "bacc": 0.6775210084033614, "bacc_std": 0.04218132197530253} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 54, "C": 0.3593813663804626, "split": "test", "acc": 0.6774193548387096, "acc_std": 0.039403311634200695, "f1": 0.6688034188034189, "f1_std": 0.04106324719141257, "bacc": 0.6680672268907563, "bacc_std": 0.040187153968825856} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 55, "C": 0.3593813663804626, "split": "test", "acc": 0.6209677419354839, "acc_std": 0.04349656115678779, "f1": 0.6153389215233318, "f1_std": 0.044385111955129015, "bacc": 0.6150210084033614, "bacc_std": 0.04405197406667049} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 56, "C": 21.54434690031882, "split": "test", "acc": 0.6854838709677419, "acc_std": 0.041210163496912366, "f1": 0.6808131476470201, "f1_std": 0.041978127067127585, "bacc": 0.6801470588235294, "bacc_std": 0.04171344795135153} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 57, "C": 0.3593813663804626, "split": "test", "acc": 0.6290322580645161, "acc_std": 0.04219799966655387, "f1": 0.6227513227513227, "f1_std": 0.04329637383041011, "bacc": 0.6223739495798319, "bacc_std": 0.042779840625232275} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 58, "C": 2.782559402207126, "split": "test", "acc": 0.6612903225806451, "acc_std": 0.04389468049851368, "f1": 0.6590730557737627, "f1_std": 0.04426509587340182, "bacc": 0.6596638655462186, "bacc_std": 0.044293220304434305} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 59, "C": 0.046415888336127774, "split": "test", "acc": 0.6451612903225806, "acc_std": 0.04540066456994104, "f1": 0.6418067226890756, "f1_std": 0.04593766942423239, "bacc": 0.6418067226890756, "bacc_std": 0.045866530471639404} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 60, "C": 2.782559402207126, "split": "test", "acc": 0.6290322580645161, "acc_std": 0.04461409276981049, "f1": 0.6227513227513227, "f1_std": 0.04585245592560989, "bacc": 0.6223739495798319, "bacc_std": 0.04526395791617043} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 61, "C": 0.046415888336127774, "split": "test", "acc": 0.5806451612903226, "acc_std": 0.04508748577564732, "f1": 0.5766806722689075, "f1_std": 0.045405316200221826, "bacc": 0.5766806722689075, "bacc_std": 0.045192111735768634} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 62, "C": 0.3593813663804626, "split": "test", "acc": 0.5564516129032258, "acc_std": 0.04419054322252409, "f1": 0.5541026479241582, "f1_std": 0.04419346970630387, "bacc": 0.5546218487394958, "bacc_std": 0.04414560252496117} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 63, "C": 10000.0, "split": "test", "acc": 0.5161290322580645, "acc_std": 0.04383500364120854, "f1": 0.514993481095176, "f1_std": 0.04438481777139778, "bacc": 0.5257352941176471, "bacc_std": 0.0440434359208474} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 64, "C": 0.3593813663804626, "split": "test", "acc": 0.6774193548387096, "acc_std": 0.04243377652552885, "f1": 0.6732542819499341, "f1_std": 0.04344233543682853, "bacc": 0.6727941176470589, "bacc_std": 0.04308222535513617} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 65, "C": 10000.0, "split": "test", "acc": 0.6370967741935484, "acc_std": 0.04393231005541833, "f1": 0.626380984265149, "f1_std": 0.04569729684251623, "bacc": 0.6265756302521008, "bacc_std": 0.04450216505660088} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 66, "C": 2.782559402207126, "split": "test", "acc": 0.6209677419354839, "acc_std": 0.043316212031592374, "f1": 0.620745753888202, "f1_std": 0.043627604673452496, "bacc": 0.6292016806722689, "bacc_std": 0.04308722218498891} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 67, "C": 2.782559402207126, "split": "test", "acc": 0.6935483870967742, "acc_std": 0.04135444554692079, "f1": 0.6883597883597883, "f1_std": 0.04275831754755823, "bacc": 0.6875, "bacc_std": 0.0424320197805079} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 68, "C": 0.3593813663804626, "split": "test", "acc": 0.6612903225806451, "acc_std": 0.041500648791989836, "f1": 0.6580882352941176, "f1_std": 0.04212009706380063, "bacc": 0.6580882352941176, "bacc_std": 0.04208460405977905} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 69, "C": 0.3593813663804626, "split": "test", "acc": 0.6612903225806451, "acc_std": 0.043074902094220005, "f1": 0.6555555555555556, "f1_std": 0.0438853258432345, "bacc": 0.654936974789916, "bacc_std": 0.04341771017303568} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 70, "C": 0.3593813663804626, "split": "test", "acc": 0.6935483870967742, "acc_std": 0.04149992164279303, "f1": 0.6906512605042017, "f1_std": 0.04186879967660821, "bacc": 0.6906512605042017, "bacc_std": 0.04177785428851516} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 71, "C": 0.046415888336127774, "split": "test", "acc": 0.7016129032258065, "acc_std": 0.03795166431319607, "f1": 0.6928021426180114, "f1_std": 0.039781851830785045, "bacc": 0.6917016806722689, "bacc_std": 0.038784807119913084} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 72, "C": 0.046415888336127774, "split": "test", "acc": 0.5967741935483871, "acc_std": 0.044008971155249696, "f1": 0.5941345902068604, "f1_std": 0.0442515679924657, "bacc": 0.5945378151260504, "bacc_std": 0.04429294226091721} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 73, "C": 0.046415888336127774, "split": "test", "acc": 0.5645161290322581, "acc_std": 0.041817983649425794, "f1": 0.555142173797502, "f1_std": 0.04300330261762354, "bacc": 0.555672268907563, "bacc_std": 0.042283129945071114} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 74, "C": 0.005994842503189409, "split": "test", "acc": 0.6290322580645161, "acc_std": 0.04544638984161223, "f1": 0.6210470369386127, "f1_std": 0.04662615869755055, "bacc": 0.6207983193277311, "bacc_std": 0.04595125151938361} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 75, "C": 0.3593813663804626, "split": "test", "acc": 0.6854838709677419, "acc_std": 0.041612087388851825, "f1": 0.6829891838741396, "f1_std": 0.0419239619511887, "bacc": 0.6832983193277311, "bacc_std": 0.04185614465874945} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 76, "C": 0.3593813663804626, "split": "test", "acc": 0.6774193548387096, "acc_std": 0.042410985927791474, "f1": 0.6704756842944459, "f1_std": 0.04388845180811113, "bacc": 0.6696428571428572, "bacc_std": 0.043137722317929915} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 77, "C": 0.046415888336127774, "split": "test", "acc": 0.5564516129032258, "acc_std": 0.04474800526309542, "f1": 0.5561918396564065, "f1_std": 0.04489126392537217, "bacc": 0.5593487394957983, "bacc_std": 0.045260435600571476} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 78, "C": 2.782559402207126, "split": "test", "acc": 0.5403225806451613, "acc_std": 0.04652491975456352, "f1": 0.5352140461629513, "f1_std": 0.04718142894236241, "bacc": 0.5351890756302521, "bacc_std": 0.04697770544612004} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 79, "C": 0.3593813663804626, "split": "test", "acc": 0.5725806451612904, "acc_std": 0.04306920054261297, "f1": 0.5662332519305657, "f1_std": 0.044009299426661194, "bacc": 0.5661764705882353, "bacc_std": 0.04363176058696979} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 80, "C": 21.54434690031882, "split": "test", "acc": 0.6693548387096774, "acc_std": 0.043204749324628124, "f1": 0.667603792088918, "f1_std": 0.043242511716292995, "bacc": 0.66859243697479, "bacc_std": 0.04309419216287774} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 81, "C": 1291.5496650148827, "split": "test", "acc": 0.6451612903225806, "acc_std": 0.04406072280937877, "f1": 0.6443285528031291, "f1_std": 0.04415521009726014, "bacc": 0.6465336134453781, "bacc_std": 0.04420729292461391} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 82, "C": 0.046415888336127774, "split": "test", "acc": 0.6612903225806451, "acc_std": 0.04058269649669386, "f1": 0.6481081081081081, "f1_std": 0.04375981376152152, "bacc": 0.6486344537815126, "bacc_std": 0.041849481374832104} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 83, "C": 0.046415888336127774, "split": "test", "acc": 0.6693548387096774, "acc_std": 0.04307772843111159, "f1": 0.665680278818965, "f1_std": 0.043627046978333375, "bacc": 0.6654411764705883, "bacc_std": 0.04356356585448422} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 84, "C": 0.046415888336127774, "split": "test", "acc": 0.6209677419354839, "acc_std": 0.04418017221634108, "f1": 0.6203504657677024, "f1_std": 0.04418499944124069, "bacc": 0.6228991596638656, "bacc_std": 0.04411356443694859} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 85, "C": 2.782559402207126, "split": "test", "acc": 0.6774193548387096, "acc_std": 0.042041215964220884, "f1": 0.6753076721654884, "f1_std": 0.04233615159370961, "bacc": 0.6759453781512605, "bacc_std": 0.042360843340025885} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 86, "C": 0.3593813663804626, "split": "test", "acc": 0.6290322580645161, "acc_std": 0.044334279692798566, "f1": 0.6169755573462261, "f1_std": 0.046976802217568794, "bacc": 0.6176470588235294, "bacc_std": 0.04521400531829196} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 87, "C": 0.3593813663804626, "split": "test", "acc": 0.6693548387096774, "acc_std": 0.04393811275352312, "f1": 0.6693333333333333, "f1_std": 0.04411108839172643, "bacc": 0.6748949579831933, "bacc_std": 0.04355453576608326} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 88, "C": 2.782559402207126, "split": "test", "acc": 0.5887096774193549, "acc_std": 0.043871264230497184, "f1": 0.5884687967723043, "f1_std": 0.04401376082358202, "bacc": 0.5919117647058824, "bacc_std": 0.04401328196868175} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 89, "C": 0.046415888336127774, "split": "test", "acc": 0.5806451612903226, "acc_std": 0.043300642368821154, "f1": 0.580536039552433, "f1_std": 0.04331349409214275, "bacc": 0.5845588235294117, "bacc_std": 0.04325695404188943} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 90, "C": 0.3593813663804626, "split": "test", "acc": 0.6209677419354839, "acc_std": 0.04231730334426929, "f1": 0.6049081418208935, "f1_std": 0.04542519461724438, "bacc": 0.6071428571428572, "bacc_std": 0.04329156801700556} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 91, "C": 0.3593813663804626, "split": "test", "acc": 0.6451612903225806, "acc_std": 0.04179685211872227, "f1": 0.6428384393820372, "f1_std": 0.04197365285141334, "bacc": 0.6433823529411764, "bacc_std": 0.04194891114905117} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 92, "C": 2.782559402207126, "split": "test", "acc": 0.5806451612903226, "acc_std": 0.04304249467159903, "f1": 0.5694444444444444, "f1_std": 0.044334471906568695, "bacc": 0.5703781512605042, "bacc_std": 0.04334735036744757} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 93, "C": 1291.5496650148827, "split": "test", "acc": 0.5645161290322581, "acc_std": 0.043845177428845125, "f1": 0.5528846153846154, "f1_std": 0.04527784334780585, "bacc": 0.5540966386554622, "bacc_std": 0.044390637229057596} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 94, "C": 0.046415888336127774, "split": "test", "acc": 0.6774193548387096, "acc_std": 0.04256579347543693, "f1": 0.6770833333333333, "f1_std": 0.04257915722423383, "bacc": 0.680672268907563, "bacc_std": 0.0426226035540377} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 95, "C": 0.046415888336127774, "split": "test", "acc": 0.6693548387096774, "acc_std": 0.04018094803271188, "f1": 0.6575739206573719, "f1_std": 0.04277269709355297, "bacc": 0.657563025210084, "bacc_std": 0.04126483636912403} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 96, "C": 166.81005372000556, "split": "test", "acc": 0.5725806451612904, "acc_std": 0.044554973701952584, "f1": 0.5691904293674206, "f1_std": 0.04493482221626299, "bacc": 0.569327731092437, "bacc_std": 0.044755491364352945} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 97, "C": 0.3593813663804626, "split": "test", "acc": 0.6451612903225806, "acc_std": 0.04465887294101949, "f1": 0.6428384393820372, "f1_std": 0.04507165557315406, "bacc": 0.6433823529411764, "bacc_std": 0.04505045390601817} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 98, "C": 0.046415888336127774, "split": "test", "acc": 0.6209677419354839, "acc_std": 0.04378766700199529, "f1": 0.6137071651090342, "f1_std": 0.04493953151509092, "bacc": 0.6134453781512605, "bacc_std": 0.044352944895630506} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 99, "C": 0.3593813663804626, "split": "test", "acc": 0.6290322580645161, "acc_std": 0.0421381301000016, "f1": 0.6266038229903116, "f1_std": 0.042465556267628525, "bacc": 0.6271008403361344, "bacc_std": 0.042543073581126994} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 100, "C": 0.046415888336127774, "split": "test", "acc": 0.6612903225806451, "acc_std": 0.04239476780392603, "f1": 0.6539994685091681, "f1_std": 0.043500014734034, "bacc": 0.6533613445378151, "bacc_std": 0.04295310863168431} +eval results (random splits): + +| model | repr | clf | dataset | split | n_trials | C | C_std | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|-----------:|-------:|--------:|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | abide_dx | train | 100 | 394.79 | 1729.6 | 0.90415 | 0.078264 | 0.90253 | 0.079884 | 0.90161 | 0.080446 | +| flat_mae | patch | logistic | abide_dx | test | 100 | 394.79 | 1729.6 | 0.6321 | 0.043221 | 0.62652 | 0.043919 | 0.6273 | 0.043243 | + + +done! total time: 0:06:20 diff --git a/input_space_v3/flat_lr1e-3_3/eval_v2/adhd200_dx__patch__logistic/config.yaml b/input_space_v3/flat_lr1e-3_3/eval_v2/adhd200_dx__patch__logistic/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..16d478692a95cbbd97adc9c441b7c71dc14fc713 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_3/eval_v2/adhd200_dx__patch__logistic/config.yaml @@ -0,0 +1,30 @@ +output_root: experiments/input_space_v3/output +name_prefix: eval_logistic +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_3; eval v2 (adhd200_dx patch logistic) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: input_space_v3/flat_lr1e-3_3/eval_v2/adhd200_dx__patch__logistic +model: flat_mae +representation: patch +dataset: adhd200_dx +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/eval_v2/adhd200_dx__patch__logistic +remote_dir: null diff --git a/input_space_v3/flat_lr1e-3_3/eval_v2/adhd200_dx__patch__logistic/eval_table.csv b/input_space_v3/flat_lr1e-3_3/eval_v2/adhd200_dx__patch__logistic/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..1086d873b3cb02a9cfa51f03368b7e28f7c6f003 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_3/eval_v2/adhd200_dx__patch__logistic/eval_table.csv @@ -0,0 +1,203 @@ +model,repr,clf,dataset,trial,C,split,acc,acc_std,f1,f1_std,bacc,bacc_std +flat_mae,patch,logistic,adhd200_dx,,0.000774263682681127,train,0.6767123287671233,0.023482332906175594,0.6616547259929613,0.02517324279139531,0.6604994809794223,0.024337452989876798 +flat_mae,patch,logistic,adhd200_dx,,0.000774263682681127,test,0.5692307692307692,0.057362784051010286,0.5376016260162602,0.06331069706008581,0.5434362934362934,0.05893765844324887 +flat_mae,patch,logistic,adhd200_dx,1,0.005994842503189409,train,0.7671232876712328,0.021690672402700915,0.755371575004928,0.02363899301875823,0.7513586126885266,0.023057460743260934 +flat_mae,patch,logistic,adhd200_dx,1,0.005994842503189409,test,0.6307692307692307,0.05645408460544776,0.6153846153846154,0.059353464656266786,0.6148648648648649,0.05774612185315023 +flat_mae,patch,logistic,adhd200_dx,2,0.005994842503189409,train,0.7342465753424657,0.022748607607011837,0.7234870080677283,0.02412066849896362,0.7207974598522318,0.02364820383228397 +flat_mae,patch,logistic,adhd200_dx,2,0.005994842503189409,test,0.7076923076923077,0.05441262470981024,0.6888384983623079,0.05959467127998364,0.6867760617760618,0.056748273561321984 +flat_mae,patch,logistic,adhd200_dx,3,0.005994842503189409,train,0.7589041095890411,0.02224561101898094,0.7488584474885844,0.0237912126831541,0.7455119985345301,0.023435273390065847 +flat_mae,patch,logistic,adhd200_dx,3,0.005994842503189409,test,0.5692307692307692,0.05813280856756073,0.545,0.06253248875995678,0.5477799227799228,0.05961259063419758 +flat_mae,patch,logistic,adhd200_dx,4,0.046415888336127774,train,0.8602739726027397,0.01836764229168311,0.8563934426229508,0.019090111288855585,0.853254564328021,0.019282902293222767 +flat_mae,patch,logistic,adhd200_dx,4,0.046415888336127774,test,0.6461538461538462,0.05776074709805478,0.6375757575757576,0.05992587741184569,0.6370656370656371,0.05943629596792959 +flat_mae,patch,logistic,adhd200_dx,5,0.046415888336127774,train,0.8438356164383561,0.01973593662828316,0.8394985535197685,0.02058989826849901,0.8365390486658119,0.020812005484766603 +flat_mae,patch,logistic,adhd200_dx,5,0.046415888336127774,test,0.49230769230769234,0.06298980851162639,0.4879446168536643,0.06358614599292695,0.4888996138996139,0.0641842784430938 +flat_mae,patch,logistic,adhd200_dx,6,0.005994842503189409,train,0.7506849315068493,0.021258067248842605,0.7411650107149814,0.022352638128534434,0.7382304451364718,0.02197053508093893 +flat_mae,patch,logistic,adhd200_dx,6,0.005994842503189409,test,0.6461538461538462,0.05862425937256904,0.6336682185738789,0.06123242516744314,0.6327220077220077,0.06009868205884733 +flat_mae,patch,logistic,adhd200_dx,7,0.046415888336127774,train,0.8383561643835616,0.019364340147713578,0.8335536129725385,0.020160268947416533,0.8302497404897112,0.020245341918664502 +flat_mae,patch,logistic,adhd200_dx,7,0.046415888336127774,test,0.6,0.05972759464544155,0.5833333333333333,0.06225230830118442,0.5834942084942085,0.0605888104623543 +flat_mae,patch,logistic,adhd200_dx,8,0.005994842503189409,train,0.7561643835616438,0.02210845577717249,0.7473969875817451,0.02354608325596142,0.7445197533125725,0.023297576458604023 +flat_mae,patch,logistic,adhd200_dx,8,0.005994842503189409,test,0.6461538461538462,0.06088492200710001,0.6289401836684041,0.06499062215598711,0.6283783783783784,0.06252493495681333 +flat_mae,patch,logistic,adhd200_dx,9,0.005994842503189409,train,0.7534246575342466,0.022376101773288994,0.7458531905675558,0.023223270771766325,0.7435275080906149,0.023050284747964354 +flat_mae,patch,logistic,adhd200_dx,9,0.005994842503189409,test,0.6307692307692307,0.05886419230818235,0.61,0.06405206692227464,0.6105212355212355,0.060930424518010395 +flat_mae,patch,logistic,adhd200_dx,10,0.005994842503189409,train,0.7589041095890411,0.02195043051713129,0.7482758620689656,0.0235553205590337,0.7447945289124992,0.023062803049366934 +flat_mae,patch,logistic,adhd200_dx,10,0.005994842503189409,test,0.5692307692307692,0.06033189467265966,0.5565302144249512,0.062316785296942824,0.5564671814671815,0.0613734899347189 +flat_mae,patch,logistic,adhd200_dx,11,0.005994842503189409,train,0.7452054794520548,0.021125001085386286,0.7348896056731828,0.022521553072452183,0.7319411369603712,0.0221774627048028 +flat_mae,patch,logistic,adhd200_dx,11,0.005994842503189409,test,0.5692307692307692,0.05814276654731135,0.5512820512820513,0.06134508591821687,0.5521235521235521,0.059471412828469065 +flat_mae,patch,logistic,adhd200_dx,12,0.005994842503189409,train,0.7616438356164383,0.022204562529132426,0.7540831261761494,0.02308190441544733,0.751526531110704,0.02285048458386873 +flat_mae,patch,logistic,adhd200_dx,12,0.005994842503189409,test,0.5538461538461539,0.057278152427973184,0.5250692869740489,0.06355234830624508,0.5299227799227799,0.05920962181356487 +flat_mae,patch,logistic,adhd200_dx,13,10000.0,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adhd200_dx,13,10000.0,test,0.5538461538461539,0.05965304815217873,0.5500119360229172,0.06057238372063565,0.5516409266409266,0.06088535756771399 +flat_mae,patch,logistic,adhd200_dx,14,0.005994842503189409,train,0.7397260273972602,0.02140434450282048,0.7291883068704555,0.022633510641200068,0.7263692984063015,0.022243614456772597 +flat_mae,patch,logistic,adhd200_dx,14,0.005994842503189409,test,0.7230769230769231,0.05043286239613469,0.7027439024390244,0.05759425254078379,0.7002895752895753,0.05368166594497259 +flat_mae,patch,logistic,adhd200_dx,15,0.005994842503189409,train,0.7452054794520548,0.02268520680132077,0.7336581691500129,0.024404424957888648,0.7305061977163094,0.023840657608692754 +flat_mae,patch,logistic,adhd200_dx,15,0.005994842503189409,test,0.5846153846153846,0.06231522081772743,0.5810455956075435,0.06254351135493867,0.583011583011583,0.06304016211698336 +flat_mae,patch,logistic,adhd200_dx,16,0.005994842503189409,train,0.7643835616438356,0.02074122504128368,0.7576136644427971,0.021636067317493176,0.7553886548207852,0.021551135217645533 +flat_mae,patch,logistic,adhd200_dx,16,0.005994842503189409,test,0.5846153846153846,0.059477257351124004,0.5699583435432491,0.0618550616026021,0.5699806949806949,0.06056825225995016 +flat_mae,patch,logistic,adhd200_dx,17,0.005994842503189409,train,0.7616438356164383,0.020824856317524128,0.751426625648733,0.022226006710905036,0.7479391830005495,0.021797124840015232 +flat_mae,patch,logistic,adhd200_dx,17,0.005994842503189409,test,0.6,0.0600708930293958,0.5775,0.06541945224228665,0.5791505791505791,0.062015053176813044 +flat_mae,patch,logistic,adhd200_dx,18,0.046415888336127774,train,0.8438356164383561,0.018368407285030957,0.839790237253679,0.019111356933382704,0.8372565182878428,0.01942552413315683 +flat_mae,patch,logistic,adhd200_dx,18,0.046415888336127774,test,0.5692307692307692,0.06159425163373223,0.5608108108108107,0.06241959558119888,0.5608108108108107,0.062021857018422104 +flat_mae,patch,logistic,adhd200_dx,19,0.005994842503189409,train,0.736986301369863,0.023488158102040673,0.72473604826546,0.025212252734447736,0.7217897050741894,0.02451480286197827 +flat_mae,patch,logistic,adhd200_dx,19,0.005994842503189409,test,0.6923076923076923,0.05996053139727655,0.6794871794871795,0.0633558152766689,0.6776061776061776,0.06187534565193812 +flat_mae,patch,logistic,adhd200_dx,20,0.046415888336127774,train,0.8301369863013699,0.018835487122843768,0.8261904761904761,0.019452506162916702,0.8244031263357148,0.0196389302042118 +flat_mae,patch,logistic,adhd200_dx,20,0.046415888336127774,test,0.6307692307692307,0.057471816607290324,0.6153846153846154,0.06137936255123,0.6148648648648649,0.0593912583023595 +flat_mae,patch,logistic,adhd200_dx,21,0.005994842503189409,train,0.7534246575342466,0.021100159681862893,0.7413059913059913,0.02270882588361398,0.7377877511143677,0.022061046254234367 +flat_mae,patch,logistic,adhd200_dx,21,0.005994842503189409,test,0.7076923076923077,0.05430345592541774,0.7031963470319634,0.055123198464955434,0.7041505791505791,0.055018842848428014 +flat_mae,patch,logistic,adhd200_dx,22,0.005994842503189409,train,0.7589041095890411,0.022389700202851723,0.7494227048617612,0.023703952276326667,0.746229468156561,0.023300477374395185 +flat_mae,patch,logistic,adhd200_dx,22,0.005994842503189409,test,0.6461538461538462,0.05952557204941966,0.6431129147767964,0.06021341014876336,0.6457528957528957,0.06065591171497275 +flat_mae,patch,logistic,adhd200_dx,23,0.005994842503189409,train,0.7506849315068493,0.021930584632326413,0.7427766032417196,0.02298303815121946,0.7403828540025645,0.02277068760880002 +flat_mae,patch,logistic,adhd200_dx,23,0.005994842503189409,test,0.6307692307692307,0.050283918165110235,0.587737843551797,0.05923324734441184,0.5974903474903475,0.05223326912497778 +flat_mae,patch,logistic,adhd200_dx,24,0.046415888336127774,train,0.8410958904109589,0.01846754188323008,0.8362165005879805,0.0194229283958886,0.8326769249557306,0.019629386940616556 +flat_mae,patch,logistic,adhd200_dx,24,0.046415888336127774,test,0.6615384615384615,0.05506123541086246,0.6366869918699187,0.06090477468244201,0.6375482625482626,0.05693024691907049 +flat_mae,patch,logistic,adhd200_dx,25,0.046415888336127774,train,0.8465753424657534,0.018263282490654807,0.8412254536415611,0.019228643105318882,0.8368138242657386,0.019337562521343454 +flat_mae,patch,logistic,adhd200_dx,25,0.046415888336127774,test,0.5692307692307692,0.06162304955685324,0.5565302144249512,0.0641975535937441,0.5564671814671815,0.06305994422724037 +flat_mae,patch,logistic,adhd200_dx,26,0.005994842503189409,train,0.7534246575342466,0.021525918428627132,0.7448266219239373,0.02257873076536466,0.7420925688465531,0.022316562403125968 +flat_mae,patch,logistic,adhd200_dx,26,0.005994842503189409,test,0.6923076923076923,0.055334165056366465,0.675,0.060410254650346926,0.6732625482625483,0.05786702963490405 +flat_mae,patch,logistic,adhd200_dx,27,0.005994842503189409,train,0.7534246575342466,0.02172354733724426,0.7425548589341693,0.0233241823648334,0.7392226903584295,0.022826580841563065 +flat_mae,patch,logistic,adhd200_dx,27,0.005994842503189409,test,0.6307692307692307,0.05697374875622349,0.6153846153846154,0.06067559855783656,0.6148648648648649,0.058847824572960485 +flat_mae,patch,logistic,adhd200_dx,28,0.046415888336127774,train,0.8356164383561644,0.018275430719588776,0.8315073552040377,0.018896314090140406,0.8292574952677536,0.019070406904104137 +flat_mae,patch,logistic,adhd200_dx,28,0.046415888336127774,test,0.6461538461538462,0.05378140282607761,0.6289401836684041,0.05776939595905378,0.6283783783783784,0.05556612936391727 +flat_mae,patch,logistic,adhd200_dx,29,0.005994842503189409,train,0.7534246575342466,0.021724547963932247,0.7425548589341693,0.0233868150584167,0.7392226903584295,0.022915052152479447 +flat_mae,patch,logistic,adhd200_dx,29,0.005994842503189409,test,0.6,0.056545734749344226,0.570630081300813,0.06271868683143063,0.5748069498069498,0.05829581961160906 +flat_mae,patch,logistic,adhd200_dx,30,0.005994842503189409,train,0.7452054794520548,0.021164339406789953,0.7376353560414589,0.022160719446999984,0.7355284850705257,0.02204861063556573 +flat_mae,patch,logistic,adhd200_dx,30,0.005994842503189409,test,0.5384615384615384,0.06075696857784488,0.5192307692307693,0.06330356413530823,0.5207528957528957,0.06171470175241471 +flat_mae,patch,logistic,adhd200_dx,31,0.005994842503189409,train,0.7506849315068493,0.022108692076660462,0.7387546110224081,0.023696739758631447,0.7353605666483483,0.02307047868542558 +flat_mae,patch,logistic,adhd200_dx,31,0.005994842503189409,test,0.6615384615384615,0.05708447804032279,0.6366869918699187,0.06340057290241352,0.6375482625482626,0.059399719109648606 +flat_mae,patch,logistic,adhd200_dx,32,0.005994842503189409,train,0.7424657534246575,0.022703284217935358,0.7329212853406402,0.023893337450589032,0.7302314221163827,0.023526960599533252 +flat_mae,patch,logistic,adhd200_dx,32,0.005994842503189409,test,0.5692307692307692,0.06340107329276497,0.5608108108108107,0.06425838114502436,0.5608108108108107,0.06413431581278412 +flat_mae,patch,logistic,adhd200_dx,33,0.000774263682681127,train,0.6712328767123288,0.022874441032355107,0.6567398119122256,0.02450519454993889,0.6556451120473835,0.023757638945093522 +flat_mae,patch,logistic,adhd200_dx,33,0.000774263682681127,test,0.5846153846153846,0.0599402937644457,0.578226387887527,0.060919254754752884,0.5786679536679536,0.06100008977242822 +flat_mae,patch,logistic,adhd200_dx,34,0.046415888336127774,train,0.8438356164383561,0.01927360632885027,0.8400710282960127,0.019942778180847255,0.8379739879098737,0.020136480551218753 +flat_mae,patch,logistic,adhd200_dx,34,0.046415888336127774,test,0.5846153846153846,0.05871990680869054,0.5830363506771205,0.058882520199999205,0.5873552123552124,0.05924455719888071 +flat_mae,patch,logistic,adhd200_dx,35,0.000774263682681127,train,0.684931506849315,0.02253242096114898,0.6625505470740982,0.024913242111646004,0.6627587470232643,0.023371286895622737 +flat_mae,patch,logistic,adhd200_dx,35,0.000774263682681127,test,0.6153846153846154,0.05423071467536809,0.5656241646618552,0.06548773161981235,0.5796332046332047,0.05654828201507634 +flat_mae,patch,logistic,adhd200_dx,36,0.000774263682681127,train,0.6876712328767123,0.02302729930793343,0.6739028213166145,0.024515454423428173,0.6723606277095927,0.023856221518836006 +flat_mae,patch,logistic,adhd200_dx,36,0.000774263682681127,test,0.5384615384615384,0.05791701061297272,0.5125,0.061848406804352905,0.5164092664092664,0.058851895923256965 +flat_mae,patch,logistic,adhd200_dx,37,0.000774263682681127,train,0.6794520547945205,0.021863205272618286,0.6534388314059647,0.024748150319195823,0.6550344996031019,0.022873445718991043 +flat_mae,patch,logistic,adhd200_dx,37,0.000774263682681127,test,0.7076923076923077,0.050502150636729436,0.677124183006536,0.06151728759991229,0.678088803088803,0.05459792539385357 +flat_mae,patch,logistic,adhd200_dx,38,0.005994842503189409,train,0.7452054794520548,0.022828938715144503,0.7348896056731828,0.024427885946643517,0.7319411369603712,0.023966101147870723 +flat_mae,patch,logistic,adhd200_dx,38,0.005994842503189409,test,0.6,0.0581160316616222,0.5833333333333333,0.060824010213259984,0.5834942084942085,0.05887725626620784 +flat_mae,patch,logistic,adhd200_dx,39,0.005994842503189409,train,0.7561643835616438,0.022024651229365526,0.7444962679230146,0.023793188344346357,0.740932405202418,0.023219533804335387 +flat_mae,patch,logistic,adhd200_dx,39,0.005994842503189409,test,0.6,0.057237212209702015,0.570630081300813,0.06266464230219504,0.5748069498069498,0.05867511161217262 +flat_mae,patch,logistic,adhd200_dx,40,0.000774263682681127,train,0.673972602739726,0.022772710192634802,0.6518543455086125,0.024811668474341023,0.6523325395371558,0.023450655692179738 +flat_mae,patch,logistic,adhd200_dx,40,0.000774263682681127,test,0.6615384615384615,0.05240977369440003,0.6299171842650104,0.05991457987764455,0.6332046332046332,0.05483342979962937 +flat_mae,patch,logistic,adhd200_dx,41,0.000774263682681127,train,0.6958904109589041,0.02209375678664155,0.6752590953903864,0.024933043688105706,0.6746198937534347,0.02339019475517168 +flat_mae,patch,logistic,adhd200_dx,41,0.000774263682681127,test,0.5846153846153846,0.06028943993807984,0.5699583435432491,0.062174873324498184,0.5699806949806949,0.06089282989977672 +flat_mae,patch,logistic,adhd200_dx,42,0.005994842503189409,train,0.7671232876712328,0.02223948601530187,0.7565692943844204,0.023705658680969497,0.7527935519325883,0.023207999930176474 +flat_mae,patch,logistic,adhd200_dx,42,0.005994842503189409,test,0.6,0.06241380517900729,0.5953065134099617,0.06253127527109048,0.5965250965250966,0.06223260339980902 +flat_mae,patch,logistic,adhd200_dx,43,0.005994842503189409,train,0.7534246575342466,0.021444968125636173,0.7425548589341693,0.022955000343712506,0.7392226903584295,0.022443697243665864 +flat_mae,patch,logistic,adhd200_dx,43,0.005994842503189409,test,0.6461538461538462,0.05945835198945372,0.6289401836684041,0.06294072002436416,0.6283783783783784,0.061009199432856466 +flat_mae,patch,logistic,adhd200_dx,44,0.046415888336127774,train,0.8438356164383561,0.018028875319346476,0.8403410355386044,0.018585046484334244,0.8386914575319045,0.018807601272247492 +flat_mae,patch,logistic,adhd200_dx,44,0.046415888336127774,test,0.6153846153846154,0.06097231110835057,0.6094688776736361,0.061530640417012464,0.61003861003861,0.06145296177269567 +flat_mae,patch,logistic,adhd200_dx,45,0.005994842503189409,train,0.7753424657534247,0.021953871700503003,0.7665075204393684,0.023426267224730447,0.7629449838187702,0.02317045759431687 +flat_mae,patch,logistic,adhd200_dx,45,0.005994842503189409,test,0.47692307692307695,0.059268918783185257,0.4551282051282051,0.06139568838766094,0.45801158301158307,0.05978963790260599 +flat_mae,patch,logistic,adhd200_dx,46,0.005994842503189409,train,0.7397260273972602,0.021001540302195462,0.7285693038693062,0.02245019349386226,0.7256518287842706,0.022000688364456334 +flat_mae,patch,logistic,adhd200_dx,46,0.005994842503189409,test,0.6153846153846154,0.058728612624753894,0.5966741126830479,0.06174118111825436,0.597007722007722,0.05945352408418053 +flat_mae,patch,logistic,adhd200_dx,47,0.005994842503189409,train,0.7671232876712328,0.020832020620430537,0.7597363876433645,0.021786233130870154,0.7570983696647737,0.021624334459594042 +flat_mae,patch,logistic,adhd200_dx,47,0.005994842503189409,test,0.6,0.05901864914368645,0.5833333333333333,0.06205284113216413,0.5834942084942085,0.060259457036312865 +flat_mae,patch,logistic,adhd200_dx,48,0.005994842503189409,train,0.7452054794520548,0.022214428490892047,0.7360440432033966,0.023427261394833306,0.733376076204433,0.023136564297026853 +flat_mae,patch,logistic,adhd200_dx,48,0.005994842503189409,test,0.6923076923076923,0.05599445450141686,0.6832358674463938,0.057986717164425015,0.6819498069498069,0.05708813401568564 +flat_mae,patch,logistic,adhd200_dx,49,0.005994842503189409,train,0.7424657534246575,0.022356386649445743,0.7304707139265962,0.02408385970699718,0.7273615436282591,0.023448705822367997 +flat_mae,patch,logistic,adhd200_dx,49,0.005994842503189409,test,0.5384615384615384,0.0625138394145104,0.5248538011695907,0.06396385949470873,0.525096525096525,0.06292588896304034 +flat_mae,patch,logistic,adhd200_dx,50,0.005994842503189409,train,0.7315068493150685,0.02308152496902778,0.7203196347031964,0.024524995511228265,0.7176528057641814,0.02406912073222323 +flat_mae,patch,logistic,adhd200_dx,50,0.005994842503189409,test,0.6461538461538462,0.05787465746189226,0.6289401836684041,0.06129856715386992,0.6283783783783784,0.05943536318987176 +flat_mae,patch,logistic,adhd200_dx,51,0.000774263682681127,train,0.6794520547945205,0.024021882811693332,0.6711483817312358,0.02478176754903782,0.6701013616657507,0.02462417560848794 +flat_mae,patch,logistic,adhd200_dx,51,0.000774263682681127,test,0.5846153846153846,0.06485891105465205,0.5745454545454545,0.06657780698997749,0.5743243243243243,0.0661906035415146 +flat_mae,patch,logistic,adhd200_dx,52,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adhd200_dx,52,21.54434690031882,test,0.4153846153846154,0.06040325239097878,0.4119047619047619,0.06044147405333898,0.4126447876447876,0.060892436751927195 +flat_mae,patch,logistic,adhd200_dx,53,0.046415888336127774,train,0.8383561643835616,0.018869975933829157,0.8341688420695975,0.019545769035390292,0.831684679733773,0.019715258390885435 +flat_mae,patch,logistic,adhd200_dx,53,0.046415888336127774,test,0.6615384615384615,0.05586543426450859,0.6425000000000001,0.06070992980394119,0.6418918918918919,0.05789365882010085 +flat_mae,patch,logistic,adhd200_dx,54,0.005994842503189409,train,0.7397260273972602,0.020868369238591117,0.7303675710142223,0.02217354812007473,0.7278042376503633,0.02191629225339838 +flat_mae,patch,logistic,adhd200_dx,54,0.005994842503189409,test,0.6,0.06241905337997422,0.588206627680312,0.06411885321501828,0.5878378378378378,0.06332080571141774 +flat_mae,patch,logistic,adhd200_dx,55,0.005994842503189409,train,0.7589041095890411,0.02288155407708463,0.7504971414367387,0.02399827494012611,0.7476644074006228,0.0237610719756117 +flat_mae,patch,logistic,adhd200_dx,55,0.005994842503189409,test,0.5538461538461539,0.060646739254872725,0.5521501544309813,0.060911143540115044,0.555984555984556,0.061333385455026895 +flat_mae,patch,logistic,adhd200_dx,56,0.000774263682681127,train,0.6931506849315069,0.02233962321183513,0.6755555555555555,0.024079730762994807,0.674345118153508,0.023031400287491 +flat_mae,patch,logistic,adhd200_dx,56,0.000774263682681127,test,0.5692307692307692,0.06336636032866157,0.5512820512820513,0.06668651814094909,0.5521235521235521,0.06476098280751365 +flat_mae,patch,logistic,adhd200_dx,57,0.046415888336127774,train,0.852054794520548,0.018580506818365372,0.8472093023255813,0.019535178863469504,0.8431031324418392,0.019747630128975138 +flat_mae,patch,logistic,adhd200_dx,57,0.046415888336127774,test,0.5230769230769231,0.06255138668591896,0.5062484685126194,0.06496445301426314,0.5072393822393823,0.06346152103049064 +flat_mae,patch,logistic,adhd200_dx,58,0.005994842503189409,train,0.7780821917808219,0.020875704861895158,0.7714888584877223,0.021831449222909863,0.7689595163949441,0.021810754144243768 +flat_mae,patch,logistic,adhd200_dx,58,0.005994842503189409,test,0.6153846153846154,0.057303667385761516,0.606060606060606,0.05906400837791979,0.6056949806949807,0.05834474757018397 +flat_mae,patch,logistic,adhd200_dx,59,0.005994842503189409,train,0.7589041095890411,0.02214300406473953,0.7499688628720886,0.023338660058269647,0.7469469377785919,0.023049279039505224 +flat_mae,patch,logistic,adhd200_dx,59,0.005994842503189409,test,0.5846153846153846,0.05718591294237816,0.5578231292517006,0.0618227199833988,0.5612934362934363,0.05857900732935741 +flat_mae,patch,logistic,adhd200_dx,60,0.005994842503189409,train,0.7671232876712328,0.02212038167436094,0.7592516431414847,0.023173984471264633,0.7563809000427428,0.022960601399723658 +flat_mae,patch,logistic,adhd200_dx,60,0.005994842503189409,test,0.6615384615384615,0.058208814070576625,0.6474358974358974,0.06173202197343795,0.6462355212355213,0.06006966241879162 +flat_mae,patch,logistic,adhd200_dx,61,0.046415888336127774,train,0.8493150684931506,0.01802764708158499,0.8454116324377604,0.018673357179854966,0.8428283568419125,0.01886873165263022 +flat_mae,patch,logistic,adhd200_dx,61,0.046415888336127774,test,0.5230769230769231,0.0640153531880203,0.5189782764382908,0.0645872607290842,0.5202702702702703,0.06520531230041848 +flat_mae,patch,logistic,adhd200_dx,62,0.3593813663804626,train,0.9561643835616438,0.010694587838942135,0.9552915237628614,0.010941099054093567,0.9539903523233804,0.011275115864022512 +flat_mae,patch,logistic,adhd200_dx,62,0.3593813663804626,test,0.5538461538461539,0.060051094615311065,0.5381034060279344,0.062295877496865,0.5386100386100386,0.06078602865745665 +flat_mae,patch,logistic,adhd200_dx,63,0.005994842503189409,train,0.7424657534246575,0.022601083210365247,0.7329212853406402,0.023929751219923048,0.7302314221163827,0.023616156430296086 +flat_mae,patch,logistic,adhd200_dx,63,0.005994842503189409,test,0.6615384615384615,0.05459484770974001,0.6366869918699187,0.060574138767634594,0.6375482625482626,0.05672895199049742 +flat_mae,patch,logistic,adhd200_dx,64,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adhd200_dx,64,2.782559402207126,test,0.5692307692307692,0.05736543296627581,0.5691287878787878,0.057959068131872,0.5825289575289576,0.057419864390081364 +flat_mae,patch,logistic,adhd200_dx,65,0.005994842503189409,train,0.7397260273972602,0.022461783143995523,0.729787648548607,0.02381142974384061,0.7270867680283324,0.02350191209341693 +flat_mae,patch,logistic,adhd200_dx,65,0.005994842503189409,test,0.7230769230769231,0.05392555903428136,0.7149122807017544,0.05632554678881103,0.7133204633204633,0.055938807662837896 +flat_mae,patch,logistic,adhd200_dx,66,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adhd200_dx,66,21.54434690031882,test,0.5384615384615384,0.05580028631344754,0.4953416149068323,0.0605196682120132,0.5077220077220077,0.05612825968271165 +flat_mae,patch,logistic,adhd200_dx,67,0.005994842503189409,train,0.7589041095890411,0.021944914745051385,0.7510077519379845,0.023067006226225106,0.7483818770226537,0.022894106234919262 +flat_mae,patch,logistic,adhd200_dx,67,0.005994842503189409,test,0.6153846153846154,0.0529841865434267,0.5751633986928104,0.06213030794653716,0.583976833976834,0.0552138256395578 +flat_mae,patch,logistic,adhd200_dx,68,0.005994842503189409,train,0.7479452054794521,0.02294811987216174,0.7348891555611696,0.024843516250353134,0.731498442938267,0.02405917556407392 +flat_mae,patch,logistic,adhd200_dx,68,0.005994842503189409,test,0.7076923076923077,0.05424372785709256,0.6934723256391164,0.05829355858789588,0.6911196911196911,0.056317089001566935 +flat_mae,patch,logistic,adhd200_dx,69,0.000774263682681127,train,0.7150684931506849,0.022539015858709356,0.7045086561215594,0.023922723283061855,0.702372229346034,0.023516450832264803 +flat_mae,patch,logistic,adhd200_dx,69,0.000774263682681127,test,0.6,0.06092875653401327,0.5921814671814671,0.06194754982368146,0.5921814671814671,0.06141183143958622 +flat_mae,patch,logistic,adhd200_dx,70,0.000774263682681127,train,0.6958904109589041,0.02330790353986243,0.6780154018548983,0.02569668678475955,0.6767723026195274,0.024455091947002704 +flat_mae,patch,logistic,adhd200_dx,70,0.000774263682681127,test,0.5692307692307692,0.06256652033999989,0.5565302144249512,0.0644834502215749,0.5564671814671815,0.06337357840313088 +flat_mae,patch,logistic,adhd200_dx,71,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adhd200_dx,71,2.782559402207126,test,0.5384615384615384,0.06002063550472064,0.5357142857142857,0.0602699739205873,0.5381274131274132,0.06050176168287387 +flat_mae,patch,logistic,adhd200_dx,72,0.005994842503189409,train,0.736986301369863,0.02234083277672165,0.726642950758285,0.023545629553910947,0.7239421139402821,0.02308587069134924 +flat_mae,patch,logistic,adhd200_dx,72,0.005994842503189409,test,0.6307692307692307,0.057546227365689824,0.6036585365853658,0.06361059738709833,0.6061776061776062,0.05945441940574374 +flat_mae,patch,logistic,adhd200_dx,73,0.005994842503189409,train,0.7561643835616438,0.022842347086422368,0.7468536917981687,0.02398624751752052,0.7438022836905416,0.02360206815535986 +flat_mae,patch,logistic,adhd200_dx,73,0.005994842503189409,test,0.6,0.061022576091962946,0.5775,0.06534288601149887,0.5791505791505791,0.06245544002678026 +flat_mae,patch,logistic,adhd200_dx,74,0.005994842503189409,train,0.736986301369863,0.021854459135942972,0.726027397260274,0.023472785375859048,0.7232246443182512,0.02301599043063582 +flat_mae,patch,logistic,adhd200_dx,74,0.005994842503189409,test,0.6615384615384615,0.05846065586378303,0.6515594541910331,0.060431678519899994,0.6505791505791505,0.05918849067676747 +flat_mae,patch,logistic,adhd200_dx,75,0.005994842503189409,train,0.7479452054794521,0.02219135057928951,0.7402054836912793,0.023053875505944683,0.7379556695365451,0.02281030032975023 +flat_mae,patch,logistic,adhd200_dx,75,0.005994842503189409,test,0.5384615384615384,0.05906249823894052,0.5294401544401545,0.06043687590739913,0.5294401544401545,0.06021302283025585 +flat_mae,patch,logistic,adhd200_dx,76,0.000774263682681127,train,0.7068493150684931,0.023051290888678078,0.6904548660923048,0.025007027626430228,0.6886334493496977,0.02396224822161338 +flat_mae,patch,logistic,adhd200_dx,76,0.000774263682681127,test,0.5230769230769231,0.05121252620440321,0.4477939161414086,0.058809223718791895,0.4811776061776062,0.05092806898773755 +flat_mae,patch,logistic,adhd200_dx,77,0.005994842503189409,train,0.7150684931506849,0.02179075228093416,0.701797385620915,0.02348504367004291,0.6995023508579105,0.02277790011979082 +flat_mae,patch,logistic,adhd200_dx,77,0.005994842503189409,test,0.7384615384615385,0.04940737553641612,0.7167392976159959,0.057955634169857724,0.7138030888030888,0.053176870399052306 +flat_mae,patch,logistic,adhd200_dx,78,0.046415888336127774,train,0.8657534246575342,0.017483676219090305,0.862517199763239,0.018007013532607596,0.8602613421261526,0.018162566522785677 +flat_mae,patch,logistic,adhd200_dx,78,0.046415888336127774,test,0.47692307692307695,0.0597214441182894,0.4551282051282051,0.06110497340495287,0.45801158301158307,0.05975286675045276 +flat_mae,patch,logistic,adhd200_dx,79,0.000774263682681127,train,0.6958904109589041,0.023918231884399115,0.6849557935008281,0.025282186663839086,0.6832295292178054,0.02482159925399416 +flat_mae,patch,logistic,adhd200_dx,79,0.000774263682681127,test,0.6153846153846154,0.05762875679265913,0.5966741126830479,0.062059323713861136,0.597007722007722,0.05948192694658748 +flat_mae,patch,logistic,adhd200_dx,80,0.005994842503189409,train,0.7643835616438356,0.02103782152033894,0.7539968652037617,0.02257985039925359,0.7503663674665689,0.022175858817057126 +flat_mae,patch,logistic,adhd200_dx,80,0.005994842503189409,test,0.5692307692307692,0.061120612159640805,0.545,0.06526005786456451,0.5477799227799228,0.062383106732493775 +flat_mae,patch,logistic,adhd200_dx,81,0.005994842503189409,train,0.7561643835616438,0.022182967977831508,0.7484298647089345,0.02320680190724213,0.7459546925566343,0.023031200124235703 +flat_mae,patch,logistic,adhd200_dx,81,0.005994842503189409,test,0.6153846153846154,0.053434700513195654,0.5834401435529352,0.06038888230649373,0.5883204633204633,0.05509576624136153 +flat_mae,patch,logistic,adhd200_dx,82,0.3593813663804626,train,0.9671232876712329,0.00888537375503968,0.9664686428221461,0.009094897581155278,0.9651340294315198,0.009494392618156522 +flat_mae,patch,logistic,adhd200_dx,82,0.3593813663804626,test,0.5846153846153846,0.06192141612679678,0.5846153846153846,0.062217931076735525,0.596042471042471,0.06228769144965096 +flat_mae,patch,logistic,adhd200_dx,83,0.046415888336127774,train,0.8356164383561644,0.019047485672713933,0.8298844146159583,0.020078536407556555,0.8256701471575991,0.020134802640525036 +flat_mae,patch,logistic,adhd200_dx,83,0.046415888336127774,test,0.5846153846153846,0.0614695845315812,0.5830363506771205,0.061554278287695025,0.5873552123552124,0.062101039662290206 +flat_mae,patch,logistic,adhd200_dx,84,0.005994842503189409,train,0.7424657534246575,0.020761101523302523,0.7311128526645768,0.022043020134402694,0.72807901325029,0.021519223748841364 +flat_mae,patch,logistic,adhd200_dx,84,0.005994842503189409,test,0.6,0.062011230133919244,0.5953065134099617,0.06300031558132627,0.5965250965250966,0.06322640582882358 +flat_mae,patch,logistic,adhd200_dx,85,0.005994842503189409,train,0.7424657534246575,0.020996671138816637,0.7311128526645768,0.022406976421014035,0.72807901325029,0.021903779374824815 +flat_mae,patch,logistic,adhd200_dx,85,0.005994842503189409,test,0.7076923076923077,0.05572900618329305,0.6934723256391164,0.05950619580708433,0.6911196911196911,0.057805435272435014 +flat_mae,patch,logistic,adhd200_dx,86,0.005994842503189409,train,0.7506849315068493,0.02229128646871013,0.7393859504586148,0.023949472131124375,0.7360780362703792,0.023402127134825368 +flat_mae,patch,logistic,adhd200_dx,86,0.005994842503189409,test,0.5846153846153846,0.06166282817628644,0.5578231292517006,0.06686657761845305,0.5612934362934363,0.06328608148016715 +flat_mae,patch,logistic,adhd200_dx,87,0.005994842503189409,train,0.7589041095890411,0.02201393373044921,0.7494227048617612,0.023446461536422054,0.746229468156561,0.02314053301463914 +flat_mae,patch,logistic,adhd200_dx,87,0.005994842503189409,test,0.6,0.06162504677915096,0.5833333333333333,0.06501609063700409,0.5834942084942085,0.06316429656893666 +flat_mae,patch,logistic,adhd200_dx,88,0.005994842503189409,train,0.7561643835616438,0.02175490902771782,0.7473969875817451,0.022851662134225497,0.7445197533125725,0.0226145772616757 +flat_mae,patch,logistic,adhd200_dx,88,0.005994842503189409,test,0.6461538461538462,0.05637718284520902,0.6289401836684041,0.060351463010407454,0.6283783783783784,0.0581914117265973 +flat_mae,patch,logistic,adhd200_dx,89,0.046415888336127774,train,0.852054794520548,0.019185028096375966,0.8483566196836339,0.01983795511395582,0.8459730109299628,0.019983886749336405 +flat_mae,patch,logistic,adhd200_dx,89,0.046415888336127774,test,0.6,0.05786415431879728,0.5833333333333333,0.06101022973539354,0.5834942084942085,0.05933837432583707 +flat_mae,patch,logistic,adhd200_dx,90,0.005994842503189409,train,0.736986301369863,0.023230974334106525,0.726027397260274,0.024721165560362208,0.7232246443182512,0.024202720720379375 +flat_mae,patch,logistic,adhd200_dx,90,0.005994842503189409,test,0.6615384615384615,0.054487390648157955,0.6366869918699187,0.06146621247601546,0.6375482625482626,0.05705558826446409 +flat_mae,patch,logistic,adhd200_dx,91,0.046415888336127774,train,0.8657534246575342,0.017878752625919134,0.8620250723240116,0.01857626165806044,0.8588264028820908,0.01880036075421533 +flat_mae,patch,logistic,adhd200_dx,91,0.046415888336127774,test,0.5846153846153846,0.05493212595138169,0.5411764705882354,0.06259756587702266,0.5526061776061776,0.05618305453120384 +flat_mae,patch,logistic,adhd200_dx,92,0.005994842503189409,train,0.7342465753424657,0.020619523912367075,0.720835797358565,0.022368994096786943,0.7179275813641082,0.021680308222823914 +flat_mae,patch,logistic,adhd200_dx,92,0.005994842503189409,test,0.676923076923077,0.056439559754886855,0.6500897205844656,0.0634045327460604,0.6510617760617761,0.05887863125023158 +flat_mae,patch,logistic,adhd200_dx,93,0.000774263682681127,train,0.6876712328767123,0.02305922698094038,0.6659870279989726,0.02570047967161113,0.6659034011113146,0.024151548083168117 +flat_mae,patch,logistic,adhd200_dx,93,0.000774263682681127,test,0.6307692307692307,0.04520471253644867,0.5666666666666667,0.060411419612476695,0.5888030888030888,0.04815903086601905 +flat_mae,patch,logistic,adhd200_dx,94,0.3593813663804626,train,0.9726027397260274,0.008836988743382332,0.9721408072296513,0.008985756716567104,0.9721408072296513,0.009031131182613172 +flat_mae,patch,logistic,adhd200_dx,94,0.3593813663804626,test,0.5538461538461539,0.05777668496412533,0.5250692869740489,0.06292972924917535,0.5299227799227799,0.05915445088837516 +flat_mae,patch,logistic,adhd200_dx,95,0.005994842503189409,train,0.7780821917808219,0.02195084838434825,0.7723334950447016,0.022736086792136925,0.7703944556390059,0.02274791722148813 +flat_mae,patch,logistic,adhd200_dx,95,0.005994842503189409,test,0.5692307692307692,0.059872298026766246,0.5512820512820513,0.06343288531743242,0.5521235521235521,0.0611540516745817 +flat_mae,patch,logistic,adhd200_dx,96,0.046415888336127774,train,0.8328767123287671,0.019174301780041716,0.8288479425623996,0.019862803468351797,0.8268303108017341,0.02011994573367833 +flat_mae,patch,logistic,adhd200_dx,96,0.046415888336127774,test,0.6615384615384615,0.05951614767707606,0.6595238095238095,0.05992424941432771,0.6636100386100386,0.06047264899289846 +flat_mae,patch,logistic,adhd200_dx,97,0.005994842503189409,train,0.736986301369863,0.022236966681257058,0.726027397260274,0.02368349307958991,0.7232246443182512,0.023176545104433174 +flat_mae,patch,logistic,adhd200_dx,97,0.005994842503189409,test,0.5846153846153846,0.049606976031662295,0.5190463140586462,0.06223018385924776,0.5439189189189189,0.051368245145450096 +flat_mae,patch,logistic,adhd200_dx,98,0.005994842503189409,train,0.7452054794520548,0.022191986469535897,0.732347723240686,0.023895366828578315,0.7290712584722476,0.02318208355224917 +flat_mae,patch,logistic,adhd200_dx,98,0.005994842503189409,test,0.7076923076923077,0.05395719539515784,0.6888384983623079,0.05921018453485367,0.6867760617760618,0.056253459343147405 +flat_mae,patch,logistic,adhd200_dx,99,0.000774263682681127,train,0.6931506849315069,0.024121693101095257,0.6854803963808703,0.024936659940545332,0.6843896928619405,0.0248129053251969 +flat_mae,patch,logistic,adhd200_dx,99,0.000774263682681127,test,0.5538461538461539,0.060451915460473515,0.5500119360229172,0.06096661554260506,0.5516409266409266,0.06105602932857275 +flat_mae,patch,logistic,adhd200_dx,100,0.005994842503189409,train,0.726027397260274,0.022353566193367636,0.7158737078091917,0.023534114861556626,0.7135159064541735,0.023174417387326125 +flat_mae,patch,logistic,adhd200_dx,100,0.005994842503189409,test,0.7076923076923077,0.05271884564736346,0.6934723256391164,0.05659124131338988,0.6911196911196911,0.05477322718376005 diff --git a/input_space_v3/flat_lr1e-3_3/eval_v2/adhd200_dx__patch__logistic/log.txt b/input_space_v3/flat_lr1e-3_3/eval_v2/adhd200_dx__patch__logistic/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..552de8f3774a7c1e0e647f8f3897724193633d36 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_3/eval_v2/adhd200_dx__patch__logistic/log.txt @@ -0,0 +1,241 @@ +fMRI foundation model logistic probe eval +version: 0.1.dev86+gf97f52698 +sha: bcce2b486277d3a5b520775efd9cdf1a2affce36, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-04-08 22:14:14 +config: +output_root: experiments/input_space_v3/output +name_prefix: eval_logistic +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_3; eval v2 (adhd200_dx patch logistic) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: input_space_v3/flat_lr1e-3_3/eval_v2/adhd200_dx__patch__logistic +model: flat_mae +representation: patch +dataset: adhd200_dx +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/eval_v2/adhd200_dx__patch__logistic +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=True, reg_tokens=0, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: adhd200_dx (flat) +train (n=301): +HFDataset( + dataset=Dataset({ + features: ['sub', 'site', 'gender', 'dx', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 301 +}), + labels=['ADHD' 'Control'], + counts=[131 170] +) + +validation (n=64): +HFDataset( + dataset=Dataset({ + features: ['sub', 'site', 'gender', 'dx', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 64 +}), + labels=['ADHD' 'Control'], + counts=[28 36] +) + +test (n=65): +HFDataset( + dataset=Dataset({ + features: ['sub', 'site', 'gender', 'dx', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 65 +}), + labels=['ADHD' 'Control'], + counts=[28 37] +) + +extracting features for all splits +extract (train) [ 0/151] eta: 0:13:15 time: 5.2660 data: 4.1330 max mem: 2698 +extract (train) [ 20/151] eta: 0:00:59 time: 0.2161 data: 0.0748 max mem: 2851 +extract (train) [ 40/151] eta: 0:00:35 time: 0.1753 data: 0.0557 max mem: 2851 +extract (train) [ 60/151] eta: 0:00:25 time: 0.1918 data: 0.0661 max mem: 2851 +extract (train) [ 80/151] eta: 0:00:18 time: 0.1925 data: 0.0654 max mem: 2851 +extract (train) [100/151] eta: 0:00:12 time: 0.1845 data: 0.0623 max mem: 2851 +extract (train) [120/151] eta: 0:00:07 time: 0.1832 data: 0.0599 max mem: 2851 +extract (train) [140/151] eta: 0:00:02 time: 0.1573 data: 0.0474 max mem: 2851 +extract (train) [150/151] eta: 0:00:00 time: 0.1543 data: 0.0469 max mem: 2851 +extract (train) Total time: 0:00:33 (0.2191 s / it) +extract (validation) [ 0/32] eta: 0:02:04 time: 3.8873 data: 3.6848 max mem: 2851 +extract (validation) [20/32] eta: 0:00:04 time: 0.2047 data: 0.0718 max mem: 2851 +extract (validation) [31/32] eta: 0:00:00 time: 0.1677 data: 0.0521 max mem: 2851 +extract (validation) Total time: 0:00:10 (0.3147 s / it) +extract (test) [ 0/33] eta: 0:02:14 time: 4.0827 data: 3.8734 max mem: 2851 +extract (test) [20/33] eta: 0:00:05 time: 0.2132 data: 0.0748 max mem: 2851 +extract (test) [32/33] eta: 0:00:00 time: 0.1650 data: 0.0523 max mem: 2851 +extract (test) Total time: 0:00:10 (0.3239 s / it) +feature extraction time: 0:00:53 +train features: (301, 768) +validation features: (64, 768) +test features: (65, 768) +evaluating fixed splits +eval results (fixed splits): + +| model | repr | clf | dataset | trial | C | split | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:-----------|:--------|-----------:|:--------|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | adhd200_dx | | 0.00077426 | train | 0.67671 | 0.023482 | 0.66165 | 0.025173 | 0.6605 | 0.024337 | +| flat_mae | patch | logistic | adhd200_dx | | 0.00077426 | test | 0.56923 | 0.057363 | 0.5376 | 0.063311 | 0.54344 | 0.058938 | + + +evaluating random splits (n=100) +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 1, "C": 0.005994842503189409, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.05645408460544776, "f1": 0.6153846153846154, "f1_std": 0.059353464656266786, "bacc": 0.6148648648648649, "bacc_std": 0.05774612185315023} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 2, "C": 0.005994842503189409, "split": "test", "acc": 0.7076923076923077, "acc_std": 0.05441262470981024, "f1": 0.6888384983623079, "f1_std": 0.05959467127998364, "bacc": 0.6867760617760618, "bacc_std": 0.056748273561321984} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 3, "C": 0.005994842503189409, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.05813280856756073, "f1": 0.545, "f1_std": 0.06253248875995678, "bacc": 0.5477799227799228, "bacc_std": 0.05961259063419758} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 4, "C": 0.046415888336127774, "split": "test", "acc": 0.6461538461538462, "acc_std": 0.05776074709805478, "f1": 0.6375757575757576, "f1_std": 0.05992587741184569, "bacc": 0.6370656370656371, "bacc_std": 0.05943629596792959} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 5, "C": 0.046415888336127774, "split": "test", "acc": 0.49230769230769234, "acc_std": 0.06298980851162639, "f1": 0.4879446168536643, "f1_std": 0.06358614599292695, "bacc": 0.4888996138996139, "bacc_std": 0.0641842784430938} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 6, "C": 0.005994842503189409, "split": "test", "acc": 0.6461538461538462, "acc_std": 0.05862425937256904, "f1": 0.6336682185738789, "f1_std": 0.06123242516744314, "bacc": 0.6327220077220077, "bacc_std": 0.06009868205884733} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 7, "C": 0.046415888336127774, "split": "test", "acc": 0.6, "acc_std": 0.05972759464544155, "f1": 0.5833333333333333, "f1_std": 0.06225230830118442, "bacc": 0.5834942084942085, "bacc_std": 0.0605888104623543} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 8, "C": 0.005994842503189409, "split": "test", "acc": 0.6461538461538462, "acc_std": 0.06088492200710001, "f1": 0.6289401836684041, "f1_std": 0.06499062215598711, "bacc": 0.6283783783783784, "bacc_std": 0.06252493495681333} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 9, "C": 0.005994842503189409, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.05886419230818235, "f1": 0.61, "f1_std": 0.06405206692227464, "bacc": 0.6105212355212355, "bacc_std": 0.060930424518010395} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 10, "C": 0.005994842503189409, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.06033189467265966, "f1": 0.5565302144249512, "f1_std": 0.062316785296942824, "bacc": 0.5564671814671815, "bacc_std": 0.0613734899347189} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 11, "C": 0.005994842503189409, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.05814276654731135, "f1": 0.5512820512820513, "f1_std": 0.06134508591821687, "bacc": 0.5521235521235521, "bacc_std": 0.059471412828469065} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 12, "C": 0.005994842503189409, "split": "test", "acc": 0.5538461538461539, "acc_std": 0.057278152427973184, "f1": 0.5250692869740489, "f1_std": 0.06355234830624508, "bacc": 0.5299227799227799, "bacc_std": 0.05920962181356487} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 13, "C": 10000.0, "split": "test", "acc": 0.5538461538461539, "acc_std": 0.05965304815217873, "f1": 0.5500119360229172, "f1_std": 0.06057238372063565, "bacc": 0.5516409266409266, "bacc_std": 0.06088535756771399} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 14, "C": 0.005994842503189409, "split": "test", "acc": 0.7230769230769231, "acc_std": 0.05043286239613469, "f1": 0.7027439024390244, "f1_std": 0.05759425254078379, "bacc": 0.7002895752895753, "bacc_std": 0.05368166594497259} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 15, "C": 0.005994842503189409, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.06231522081772743, "f1": 0.5810455956075435, "f1_std": 0.06254351135493867, "bacc": 0.583011583011583, "bacc_std": 0.06304016211698336} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 16, "C": 0.005994842503189409, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.059477257351124004, "f1": 0.5699583435432491, "f1_std": 0.0618550616026021, "bacc": 0.5699806949806949, "bacc_std": 0.06056825225995016} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 17, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.0600708930293958, "f1": 0.5775, "f1_std": 0.06541945224228665, "bacc": 0.5791505791505791, "bacc_std": 0.062015053176813044} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 18, "C": 0.046415888336127774, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.06159425163373223, "f1": 0.5608108108108107, "f1_std": 0.06241959558119888, "bacc": 0.5608108108108107, "bacc_std": 0.062021857018422104} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 19, "C": 0.005994842503189409, "split": "test", "acc": 0.6923076923076923, "acc_std": 0.05996053139727655, "f1": 0.6794871794871795, "f1_std": 0.0633558152766689, "bacc": 0.6776061776061776, "bacc_std": 0.06187534565193812} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 20, "C": 0.046415888336127774, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.057471816607290324, "f1": 0.6153846153846154, "f1_std": 0.06137936255123, "bacc": 0.6148648648648649, "bacc_std": 0.0593912583023595} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 21, "C": 0.005994842503189409, "split": "test", "acc": 0.7076923076923077, "acc_std": 0.05430345592541774, "f1": 0.7031963470319634, "f1_std": 0.055123198464955434, "bacc": 0.7041505791505791, "bacc_std": 0.055018842848428014} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 22, "C": 0.005994842503189409, "split": "test", "acc": 0.6461538461538462, "acc_std": 0.05952557204941966, "f1": 0.6431129147767964, "f1_std": 0.06021341014876336, "bacc": 0.6457528957528957, "bacc_std": 0.06065591171497275} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 23, "C": 0.005994842503189409, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.050283918165110235, "f1": 0.587737843551797, "f1_std": 0.05923324734441184, "bacc": 0.5974903474903475, "bacc_std": 0.05223326912497778} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 24, "C": 0.046415888336127774, "split": "test", "acc": 0.6615384615384615, "acc_std": 0.05506123541086246, "f1": 0.6366869918699187, "f1_std": 0.06090477468244201, "bacc": 0.6375482625482626, "bacc_std": 0.05693024691907049} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 25, "C": 0.046415888336127774, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.06162304955685324, "f1": 0.5565302144249512, "f1_std": 0.0641975535937441, "bacc": 0.5564671814671815, "bacc_std": 0.06305994422724037} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 26, "C": 0.005994842503189409, "split": "test", "acc": 0.6923076923076923, "acc_std": 0.055334165056366465, "f1": 0.675, "f1_std": 0.060410254650346926, "bacc": 0.6732625482625483, "bacc_std": 0.05786702963490405} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 27, "C": 0.005994842503189409, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.05697374875622349, "f1": 0.6153846153846154, "f1_std": 0.06067559855783656, "bacc": 0.6148648648648649, "bacc_std": 0.058847824572960485} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 28, "C": 0.046415888336127774, "split": "test", "acc": 0.6461538461538462, "acc_std": 0.05378140282607761, "f1": 0.6289401836684041, "f1_std": 0.05776939595905378, "bacc": 0.6283783783783784, "bacc_std": 0.05556612936391727} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 29, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.056545734749344226, "f1": 0.570630081300813, "f1_std": 0.06271868683143063, "bacc": 0.5748069498069498, "bacc_std": 0.05829581961160906} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 30, "C": 0.005994842503189409, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.06075696857784488, "f1": 0.5192307692307693, "f1_std": 0.06330356413530823, "bacc": 0.5207528957528957, "bacc_std": 0.06171470175241471} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 31, "C": 0.005994842503189409, "split": "test", "acc": 0.6615384615384615, "acc_std": 0.05708447804032279, "f1": 0.6366869918699187, "f1_std": 0.06340057290241352, "bacc": 0.6375482625482626, "bacc_std": 0.059399719109648606} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 32, "C": 0.005994842503189409, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.06340107329276497, "f1": 0.5608108108108107, "f1_std": 0.06425838114502436, "bacc": 0.5608108108108107, "bacc_std": 0.06413431581278412} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 33, "C": 0.000774263682681127, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.0599402937644457, "f1": 0.578226387887527, "f1_std": 0.060919254754752884, "bacc": 0.5786679536679536, "bacc_std": 0.06100008977242822} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 34, "C": 0.046415888336127774, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.05871990680869054, "f1": 0.5830363506771205, "f1_std": 0.058882520199999205, "bacc": 0.5873552123552124, "bacc_std": 0.05924455719888071} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 35, "C": 0.000774263682681127, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.05423071467536809, "f1": 0.5656241646618552, "f1_std": 0.06548773161981235, "bacc": 0.5796332046332047, "bacc_std": 0.05654828201507634} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 36, "C": 0.000774263682681127, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.05791701061297272, "f1": 0.5125, "f1_std": 0.061848406804352905, "bacc": 0.5164092664092664, "bacc_std": 0.058851895923256965} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 37, "C": 0.000774263682681127, "split": "test", "acc": 0.7076923076923077, "acc_std": 0.050502150636729436, "f1": 0.677124183006536, "f1_std": 0.06151728759991229, "bacc": 0.678088803088803, "bacc_std": 0.05459792539385357} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 38, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.0581160316616222, "f1": 0.5833333333333333, "f1_std": 0.060824010213259984, "bacc": 0.5834942084942085, "bacc_std": 0.05887725626620784} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 39, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.057237212209702015, "f1": 0.570630081300813, "f1_std": 0.06266464230219504, "bacc": 0.5748069498069498, "bacc_std": 0.05867511161217262} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 40, "C": 0.000774263682681127, "split": "test", "acc": 0.6615384615384615, "acc_std": 0.05240977369440003, "f1": 0.6299171842650104, "f1_std": 0.05991457987764455, "bacc": 0.6332046332046332, "bacc_std": 0.05483342979962937} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 41, "C": 0.000774263682681127, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.06028943993807984, "f1": 0.5699583435432491, "f1_std": 0.062174873324498184, "bacc": 0.5699806949806949, "bacc_std": 0.06089282989977672} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 42, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.06241380517900729, "f1": 0.5953065134099617, "f1_std": 0.06253127527109048, "bacc": 0.5965250965250966, "bacc_std": 0.06223260339980902} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 43, "C": 0.005994842503189409, "split": "test", "acc": 0.6461538461538462, "acc_std": 0.05945835198945372, "f1": 0.6289401836684041, "f1_std": 0.06294072002436416, "bacc": 0.6283783783783784, "bacc_std": 0.061009199432856466} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 44, "C": 0.046415888336127774, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.06097231110835057, "f1": 0.6094688776736361, "f1_std": 0.061530640417012464, "bacc": 0.61003861003861, "bacc_std": 0.06145296177269567} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 45, "C": 0.005994842503189409, "split": "test", "acc": 0.47692307692307695, "acc_std": 0.059268918783185257, "f1": 0.4551282051282051, "f1_std": 0.06139568838766094, "bacc": 0.45801158301158307, "bacc_std": 0.05978963790260599} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 46, "C": 0.005994842503189409, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.058728612624753894, "f1": 0.5966741126830479, "f1_std": 0.06174118111825436, "bacc": 0.597007722007722, "bacc_std": 0.05945352408418053} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 47, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.05901864914368645, "f1": 0.5833333333333333, "f1_std": 0.06205284113216413, "bacc": 0.5834942084942085, "bacc_std": 0.060259457036312865} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 48, "C": 0.005994842503189409, "split": "test", "acc": 0.6923076923076923, "acc_std": 0.05599445450141686, "f1": 0.6832358674463938, "f1_std": 0.057986717164425015, "bacc": 0.6819498069498069, "bacc_std": 0.05708813401568564} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 49, "C": 0.005994842503189409, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.0625138394145104, "f1": 0.5248538011695907, "f1_std": 0.06396385949470873, "bacc": 0.525096525096525, "bacc_std": 0.06292588896304034} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 50, "C": 0.005994842503189409, "split": "test", "acc": 0.6461538461538462, "acc_std": 0.05787465746189226, "f1": 0.6289401836684041, "f1_std": 0.06129856715386992, "bacc": 0.6283783783783784, "bacc_std": 0.05943536318987176} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 51, "C": 0.000774263682681127, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.06485891105465205, "f1": 0.5745454545454545, "f1_std": 0.06657780698997749, "bacc": 0.5743243243243243, "bacc_std": 0.0661906035415146} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 52, "C": 21.54434690031882, "split": "test", "acc": 0.4153846153846154, "acc_std": 0.06040325239097878, "f1": 0.4119047619047619, "f1_std": 0.06044147405333898, "bacc": 0.4126447876447876, "bacc_std": 0.060892436751927195} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 53, "C": 0.046415888336127774, "split": "test", "acc": 0.6615384615384615, "acc_std": 0.05586543426450859, "f1": 0.6425000000000001, "f1_std": 0.06070992980394119, "bacc": 0.6418918918918919, "bacc_std": 0.05789365882010085} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 54, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.06241905337997422, "f1": 0.588206627680312, "f1_std": 0.06411885321501828, "bacc": 0.5878378378378378, "bacc_std": 0.06332080571141774} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 55, "C": 0.005994842503189409, "split": "test", "acc": 0.5538461538461539, "acc_std": 0.060646739254872725, "f1": 0.5521501544309813, "f1_std": 0.060911143540115044, "bacc": 0.555984555984556, "bacc_std": 0.061333385455026895} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 56, "C": 0.000774263682681127, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.06336636032866157, "f1": 0.5512820512820513, "f1_std": 0.06668651814094909, "bacc": 0.5521235521235521, "bacc_std": 0.06476098280751365} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 57, "C": 0.046415888336127774, "split": "test", "acc": 0.5230769230769231, "acc_std": 0.06255138668591896, "f1": 0.5062484685126194, "f1_std": 0.06496445301426314, "bacc": 0.5072393822393823, "bacc_std": 0.06346152103049064} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 58, "C": 0.005994842503189409, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.057303667385761516, "f1": 0.606060606060606, "f1_std": 0.05906400837791979, "bacc": 0.6056949806949807, "bacc_std": 0.05834474757018397} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 59, "C": 0.005994842503189409, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.05718591294237816, "f1": 0.5578231292517006, "f1_std": 0.0618227199833988, "bacc": 0.5612934362934363, "bacc_std": 0.05857900732935741} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 60, "C": 0.005994842503189409, "split": "test", "acc": 0.6615384615384615, "acc_std": 0.058208814070576625, "f1": 0.6474358974358974, "f1_std": 0.06173202197343795, "bacc": 0.6462355212355213, "bacc_std": 0.06006966241879162} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 61, "C": 0.046415888336127774, "split": "test", "acc": 0.5230769230769231, "acc_std": 0.0640153531880203, "f1": 0.5189782764382908, "f1_std": 0.0645872607290842, "bacc": 0.5202702702702703, "bacc_std": 0.06520531230041848} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 62, "C": 0.3593813663804626, "split": "test", "acc": 0.5538461538461539, "acc_std": 0.060051094615311065, "f1": 0.5381034060279344, "f1_std": 0.062295877496865, "bacc": 0.5386100386100386, "bacc_std": 0.06078602865745665} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 63, "C": 0.005994842503189409, "split": "test", "acc": 0.6615384615384615, "acc_std": 0.05459484770974001, "f1": 0.6366869918699187, "f1_std": 0.060574138767634594, "bacc": 0.6375482625482626, "bacc_std": 0.05672895199049742} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 64, "C": 2.782559402207126, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.05736543296627581, "f1": 0.5691287878787878, "f1_std": 0.057959068131872, "bacc": 0.5825289575289576, "bacc_std": 0.057419864390081364} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 65, "C": 0.005994842503189409, "split": "test", "acc": 0.7230769230769231, "acc_std": 0.05392555903428136, "f1": 0.7149122807017544, "f1_std": 0.05632554678881103, "bacc": 0.7133204633204633, "bacc_std": 0.055938807662837896} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 66, "C": 21.54434690031882, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.05580028631344754, "f1": 0.4953416149068323, "f1_std": 0.0605196682120132, "bacc": 0.5077220077220077, "bacc_std": 0.05612825968271165} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 67, "C": 0.005994842503189409, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.0529841865434267, "f1": 0.5751633986928104, "f1_std": 0.06213030794653716, "bacc": 0.583976833976834, "bacc_std": 0.0552138256395578} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 68, "C": 0.005994842503189409, "split": "test", "acc": 0.7076923076923077, "acc_std": 0.05424372785709256, "f1": 0.6934723256391164, "f1_std": 0.05829355858789588, "bacc": 0.6911196911196911, "bacc_std": 0.056317089001566935} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 69, "C": 0.000774263682681127, "split": "test", "acc": 0.6, "acc_std": 0.06092875653401327, "f1": 0.5921814671814671, "f1_std": 0.06194754982368146, "bacc": 0.5921814671814671, "bacc_std": 0.06141183143958622} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 70, "C": 0.000774263682681127, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.06256652033999989, "f1": 0.5565302144249512, "f1_std": 0.0644834502215749, "bacc": 0.5564671814671815, "bacc_std": 0.06337357840313088} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 71, "C": 2.782559402207126, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.06002063550472064, "f1": 0.5357142857142857, "f1_std": 0.0602699739205873, "bacc": 0.5381274131274132, "bacc_std": 0.06050176168287387} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 72, "C": 0.005994842503189409, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.057546227365689824, "f1": 0.6036585365853658, "f1_std": 0.06361059738709833, "bacc": 0.6061776061776062, "bacc_std": 0.05945441940574374} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 73, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.061022576091962946, "f1": 0.5775, "f1_std": 0.06534288601149887, "bacc": 0.5791505791505791, "bacc_std": 0.06245544002678026} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 74, "C": 0.005994842503189409, "split": "test", "acc": 0.6615384615384615, "acc_std": 0.05846065586378303, "f1": 0.6515594541910331, "f1_std": 0.060431678519899994, "bacc": 0.6505791505791505, "bacc_std": 0.05918849067676747} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 75, "C": 0.005994842503189409, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.05906249823894052, "f1": 0.5294401544401545, "f1_std": 0.06043687590739913, "bacc": 0.5294401544401545, "bacc_std": 0.06021302283025585} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 76, "C": 0.000774263682681127, "split": "test", "acc": 0.5230769230769231, "acc_std": 0.05121252620440321, "f1": 0.4477939161414086, "f1_std": 0.058809223718791895, "bacc": 0.4811776061776062, "bacc_std": 0.05092806898773755} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 77, "C": 0.005994842503189409, "split": "test", "acc": 0.7384615384615385, "acc_std": 0.04940737553641612, "f1": 0.7167392976159959, "f1_std": 0.057955634169857724, "bacc": 0.7138030888030888, "bacc_std": 0.053176870399052306} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 78, "C": 0.046415888336127774, "split": "test", "acc": 0.47692307692307695, "acc_std": 0.0597214441182894, "f1": 0.4551282051282051, "f1_std": 0.06110497340495287, "bacc": 0.45801158301158307, "bacc_std": 0.05975286675045276} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 79, "C": 0.000774263682681127, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.05762875679265913, "f1": 0.5966741126830479, "f1_std": 0.062059323713861136, "bacc": 0.597007722007722, "bacc_std": 0.05948192694658748} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 80, "C": 0.005994842503189409, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.061120612159640805, "f1": 0.545, "f1_std": 0.06526005786456451, "bacc": 0.5477799227799228, "bacc_std": 0.062383106732493775} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 81, "C": 0.005994842503189409, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.053434700513195654, "f1": 0.5834401435529352, "f1_std": 0.06038888230649373, "bacc": 0.5883204633204633, "bacc_std": 0.05509576624136153} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 82, "C": 0.3593813663804626, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.06192141612679678, "f1": 0.5846153846153846, "f1_std": 0.062217931076735525, "bacc": 0.596042471042471, "bacc_std": 0.06228769144965096} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 83, "C": 0.046415888336127774, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.0614695845315812, "f1": 0.5830363506771205, "f1_std": 0.061554278287695025, "bacc": 0.5873552123552124, "bacc_std": 0.062101039662290206} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 84, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.062011230133919244, "f1": 0.5953065134099617, "f1_std": 0.06300031558132627, "bacc": 0.5965250965250966, "bacc_std": 0.06322640582882358} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 85, "C": 0.005994842503189409, "split": "test", "acc": 0.7076923076923077, "acc_std": 0.05572900618329305, "f1": 0.6934723256391164, "f1_std": 0.05950619580708433, "bacc": 0.6911196911196911, "bacc_std": 0.057805435272435014} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 86, "C": 0.005994842503189409, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.06166282817628644, "f1": 0.5578231292517006, "f1_std": 0.06686657761845305, "bacc": 0.5612934362934363, "bacc_std": 0.06328608148016715} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 87, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.06162504677915096, "f1": 0.5833333333333333, "f1_std": 0.06501609063700409, "bacc": 0.5834942084942085, "bacc_std": 0.06316429656893666} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 88, "C": 0.005994842503189409, "split": "test", "acc": 0.6461538461538462, "acc_std": 0.05637718284520902, "f1": 0.6289401836684041, "f1_std": 0.060351463010407454, "bacc": 0.6283783783783784, "bacc_std": 0.0581914117265973} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 89, "C": 0.046415888336127774, "split": "test", "acc": 0.6, "acc_std": 0.05786415431879728, "f1": 0.5833333333333333, "f1_std": 0.06101022973539354, "bacc": 0.5834942084942085, "bacc_std": 0.05933837432583707} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 90, "C": 0.005994842503189409, "split": "test", "acc": 0.6615384615384615, "acc_std": 0.054487390648157955, "f1": 0.6366869918699187, "f1_std": 0.06146621247601546, "bacc": 0.6375482625482626, "bacc_std": 0.05705558826446409} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 91, "C": 0.046415888336127774, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.05493212595138169, "f1": 0.5411764705882354, "f1_std": 0.06259756587702266, "bacc": 0.5526061776061776, "bacc_std": 0.05618305453120384} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 92, "C": 0.005994842503189409, "split": "test", "acc": 0.676923076923077, "acc_std": 0.056439559754886855, "f1": 0.6500897205844656, "f1_std": 0.0634045327460604, "bacc": 0.6510617760617761, "bacc_std": 0.05887863125023158} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 93, "C": 0.000774263682681127, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.04520471253644867, "f1": 0.5666666666666667, "f1_std": 0.060411419612476695, "bacc": 0.5888030888030888, "bacc_std": 0.04815903086601905} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 94, "C": 0.3593813663804626, "split": "test", "acc": 0.5538461538461539, "acc_std": 0.05777668496412533, "f1": 0.5250692869740489, "f1_std": 0.06292972924917535, "bacc": 0.5299227799227799, "bacc_std": 0.05915445088837516} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 95, "C": 0.005994842503189409, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.059872298026766246, "f1": 0.5512820512820513, "f1_std": 0.06343288531743242, "bacc": 0.5521235521235521, "bacc_std": 0.0611540516745817} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 96, "C": 0.046415888336127774, "split": "test", "acc": 0.6615384615384615, "acc_std": 0.05951614767707606, "f1": 0.6595238095238095, "f1_std": 0.05992424941432771, "bacc": 0.6636100386100386, "bacc_std": 0.06047264899289846} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 97, "C": 0.005994842503189409, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.049606976031662295, "f1": 0.5190463140586462, "f1_std": 0.06223018385924776, "bacc": 0.5439189189189189, "bacc_std": 0.051368245145450096} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 98, "C": 0.005994842503189409, "split": "test", "acc": 0.7076923076923077, "acc_std": 0.05395719539515784, "f1": 0.6888384983623079, "f1_std": 0.05921018453485367, "bacc": 0.6867760617760618, "bacc_std": 0.056253459343147405} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 99, "C": 0.000774263682681127, "split": "test", "acc": 0.5538461538461539, "acc_std": 0.060451915460473515, "f1": 0.5500119360229172, "f1_std": 0.06096661554260506, "bacc": 0.5516409266409266, "bacc_std": 0.06105602932857275} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 100, "C": 0.005994842503189409, "split": "test", "acc": 0.7076923076923077, "acc_std": 0.05271884564736346, "f1": 0.6934723256391164, "f1_std": 0.05659124131338988, "bacc": 0.6911196911196911, "bacc_std": 0.05477322718376005} +eval results (random splits): + +| model | repr | clf | dataset | split | n_trials | C | C_std | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:-----------|:--------|-----------:|-------:|--------:|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | adhd200_dx | train | 100 | 100.51 | 999.95 | 0.77808 | 0.077876 | 0.76902 | 0.082114 | 0.76661 | 0.082326 | +| flat_mae | patch | logistic | adhd200_dx | test | 100 | 100.51 | 999.95 | 0.608 | 0.060103 | 0.58974 | 0.061286 | 0.59204 | 0.059046 | + + +done! total time: 0:04:50 diff --git a/input_space_v3/flat_lr1e-3_3/eval_v2/adni_ad_vs_cn__patch__logistic/config.yaml b/input_space_v3/flat_lr1e-3_3/eval_v2/adni_ad_vs_cn__patch__logistic/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..087e937b7f3cc3f0278f85c0ed50c33149a395db --- /dev/null +++ b/input_space_v3/flat_lr1e-3_3/eval_v2/adni_ad_vs_cn__patch__logistic/config.yaml @@ -0,0 +1,30 @@ +output_root: experiments/input_space_v3/output +name_prefix: eval_logistic +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_3; eval v2 (adni_ad_vs_cn patch logistic) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: input_space_v3/flat_lr1e-3_3/eval_v2/adni_ad_vs_cn__patch__logistic +model: flat_mae +representation: patch +dataset: adni_ad_vs_cn +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/eval_v2/adni_ad_vs_cn__patch__logistic +remote_dir: null diff --git a/input_space_v3/flat_lr1e-3_3/eval_v2/adni_ad_vs_cn__patch__logistic/eval_table.csv b/input_space_v3/flat_lr1e-3_3/eval_v2/adni_ad_vs_cn__patch__logistic/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..3588355467984c8dc8a470107aa190bdf7c8be92 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_3/eval_v2/adni_ad_vs_cn__patch__logistic/eval_table.csv @@ -0,0 +1,203 @@ +model,repr,clf,dataset,trial,C,split,acc,acc_std,f1,f1_std,bacc,bacc_std +flat_mae,patch,logistic,adni_ad_vs_cn,,0.3593813663804626,train,0.975609756097561,0.0078023840489846,0.9654641694657917,0.0113212444619923,0.9562240156517485,0.014885013461002862 +flat_mae,patch,logistic,adni_ad_vs_cn,,0.3593813663804626,test,0.6585365853658537,0.0658253959225774,0.5017361111111112,0.07924218781004233,0.5017361111111112,0.0794193992184669 +flat_mae,patch,logistic,adni_ad_vs_cn,1,0.046415888336127774,train,0.8970189701897019,0.014965902299969597,0.8410204081632653,0.02512764502919792,0.8114471197304627,0.02731274062924598 +flat_mae,patch,logistic,adni_ad_vs_cn,1,0.046415888336127774,test,0.7560975609756098,0.05123344758163885,0.6117424242424243,0.08973724608677408,0.6016129032258064,0.07680382892380379 +flat_mae,patch,logistic,adni_ad_vs_cn,2,0.046415888336127774,train,0.8861788617886179,0.014263386252773338,0.8206914105886709,0.025067818544646327,0.7881913057769743,0.026234969515118046 +flat_mae,patch,logistic,adni_ad_vs_cn,2,0.046415888336127774,test,0.7317073170731707,0.062209543999806736,0.6232247284878863,0.08723731366087865,0.6193548387096774,0.08630467019701063 +flat_mae,patch,logistic,adni_ad_vs_cn,3,0.046415888336127774,train,0.8970189701897019,0.013797864457728008,0.8394182317911132,0.023992341478860812,0.8073999506943874,0.026312260894446795 +flat_mae,patch,logistic,adni_ad_vs_cn,3,0.046415888336127774,test,0.7073170731707317,0.05509699413435623,0.5340909090909092,0.08221981372333416,0.535483870967742,0.06923012973903532 +flat_mae,patch,logistic,adni_ad_vs_cn,4,0.046415888336127774,train,0.8780487804878049,0.01536787146862741,0.8088677095203564,0.026593828900063402,0.7788437833840085,0.02733671913672023 +flat_mae,patch,logistic,adni_ad_vs_cn,4,0.046415888336127774,test,0.8048780487804879,0.05735598056734071,0.7152777777777778,0.08861475747178658,0.7016129032258065,0.08536697857003549 +flat_mae,patch,logistic,adni_ad_vs_cn,5,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,5,21.54434690031882,test,0.6829268292682927,0.047468603230798,0.4696517412935323,0.06732311561941388,0.4854838709677419,0.05467435513347356 +flat_mae,patch,logistic,adni_ad_vs_cn,6,0.046415888336127774,train,0.8915989159891599,0.013955059767983374,0.8326530612244898,0.02396990690795321,0.8038663817897937,0.02632084301924582 +flat_mae,patch,logistic,adni_ad_vs_cn,6,0.046415888336127774,test,0.8048780487804879,0.030272645664861653,0.6095238095238095,0.09367341473139215,0.6,0.0620589236129664 +flat_mae,patch,logistic,adni_ad_vs_cn,7,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,7,166.81005372000556,test,0.7804878048780488,0.06293512896674383,0.7119437939110069,0.08306693029955815,0.7193548387096774,0.0881729793485557 +flat_mae,patch,logistic,adni_ad_vs_cn,8,0.046415888336127774,train,0.8915989159891599,0.015564916024520991,0.8326530612244898,0.025951392148006205,0.8038663817897937,0.027276231149914135 +flat_mae,patch,logistic,adni_ad_vs_cn,8,0.046415888336127774,test,0.6829268292682927,0.05273644526446079,0.4696517412935323,0.06831084402518633,0.4854838709677419,0.05711177641435183 +flat_mae,patch,logistic,adni_ad_vs_cn,9,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,9,166.81005372000556,test,0.6829268292682927,0.06997067457454172,0.6072218128224024,0.08155582444493122,0.6209677419354839,0.08833928604475463 +flat_mae,patch,logistic,adni_ad_vs_cn,10,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,10,21.54434690031882,test,0.6585365853658537,0.06584462449325641,0.5370967741935484,0.0820781074771174,0.5370967741935484,0.08236500171045824 +flat_mae,patch,logistic,adni_ad_vs_cn,11,0.046415888336127774,train,0.8780487804878049,0.01475650841427728,0.8107929490320301,0.024989474040517722,0.7828909524200838,0.0260939786767131 +flat_mae,patch,logistic,adni_ad_vs_cn,11,0.046415888336127774,test,0.7804878048780488,0.03926753521463045,0.5886287625418061,0.0886394037932827,0.5838709677419355,0.06323654912027536 +flat_mae,patch,logistic,adni_ad_vs_cn,12,0.3593813663804626,train,0.978319783197832,0.007525104562988551,0.9694283347141673,0.010659620864353521,0.9656298792012491,0.012810729173321265 +flat_mae,patch,logistic,adni_ad_vs_cn,12,0.3593813663804626,test,0.6829268292682927,0.07034098981607083,0.5839188134270101,0.08588432332605155,0.5870967741935484,0.0888826500722777 +flat_mae,patch,logistic,adni_ad_vs_cn,13,0.3593813663804626,train,0.989159891598916,0.005625094566584045,0.9847141673570836,0.008033395372214624,0.9807913550825869,0.010565413750411177 +flat_mae,patch,logistic,adni_ad_vs_cn,13,0.3593813663804626,test,0.7560975609756098,0.059392121971607516,0.6440972222222222,0.0873095566734307,0.635483870967742,0.08391024291327506 +flat_mae,patch,logistic,adni_ad_vs_cn,14,0.3593813663804626,train,0.981029810298103,0.007279526269363625,0.9731387984733936,0.01048325333326521,0.9673966636535458,0.013480373233144015 +flat_mae,patch,logistic,adni_ad_vs_cn,14,0.3593813663804626,test,0.6585365853658537,0.07060375306214564,0.5651515151515152,0.08354457791784438,0.5709677419354839,0.08773539651867587 +flat_mae,patch,logistic,adni_ad_vs_cn,15,0.046415888336127774,train,0.8834688346883469,0.015525006120056698,0.8192021512972733,0.02642322575421958,0.7904716903607527,0.027514580284422645 +flat_mae,patch,logistic,adni_ad_vs_cn,15,0.046415888336127774,test,0.7317073170731707,0.041952892763000495,0.4972129319955407,0.07825391058148987,0.5177419354838709,0.05558732253525905 +flat_mae,patch,logistic,adni_ad_vs_cn,16,0.3593813663804626,train,0.983739837398374,0.006365737711238188,0.9768796992481203,0.009208371213321322,0.9691634481058427,0.012491933520448532 +flat_mae,patch,logistic,adni_ad_vs_cn,16,0.3593813663804626,test,0.8292682926829268,0.04552178812971945,0.7144278606965174,0.09622888490770774,0.6838709677419355,0.08081816823176054 +flat_mae,patch,logistic,adni_ad_vs_cn,17,0.3593813663804626,train,0.983739837398374,0.0072777504049893514,0.9770712510356255,0.010360730266297295,0.9732106171419179,0.01245463673150129 +flat_mae,patch,logistic,adni_ad_vs_cn,17,0.3593813663804626,test,0.7560975609756098,0.061556259724282365,0.6440972222222222,0.09272749411667944,0.635483870967742,0.08692742460698655 +flat_mae,patch,logistic,adni_ad_vs_cn,18,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,18,2.782559402207126,test,0.8292682926829268,0.05397095303554074,0.7402714932126697,0.09081431235297628,0.717741935483871,0.0872452202102312 +flat_mae,patch,logistic,adni_ad_vs_cn,19,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,19,21.54434690031882,test,0.6829268292682927,0.06101267166343247,0.5176470588235295,0.07975397030621992,0.5193548387096775,0.07162051826702058 +flat_mae,patch,logistic,adni_ad_vs_cn,20,0.3593813663804626,train,0.981029810298103,0.006947613131265847,0.9731387984733936,0.009951573611554592,0.9673966636535458,0.012567471811025261 +flat_mae,patch,logistic,adni_ad_vs_cn,20,0.3593813663804626,test,0.7317073170731707,0.06431072325452827,0.6479313036690086,0.07931010719609831,0.6532258064516129,0.08272858944117274 +flat_mae,patch,logistic,adni_ad_vs_cn,21,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,21,2.782559402207126,test,0.7560975609756098,0.060901242454814944,0.6440972222222222,0.09294454878494983,0.635483870967742,0.08738055626341151 +flat_mae,patch,logistic,adni_ad_vs_cn,22,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,22,2.782559402207126,test,0.6585365853658537,0.05494014914525005,0.4564393939393939,0.06550264072734918,0.4693548387096774,0.05729794803581979 +flat_mae,patch,logistic,adni_ad_vs_cn,23,0.3593813663804626,train,0.983739837398374,0.0067919486173783315,0.9770712510356255,0.009700691908384683,0.9732106171419179,0.01228724181388101 +flat_mae,patch,logistic,adni_ad_vs_cn,23,0.3593813663804626,test,0.7560975609756098,0.06316754865320835,0.6693548387096775,0.08719513359093745,0.6693548387096775,0.08927381554251643 +flat_mae,patch,logistic,adni_ad_vs_cn,24,0.046415888336127774,train,0.8943089430894309,0.014319512397711082,0.8392156862745098,0.023443451667298196,0.8137275043142411,0.025746053288840595 +flat_mae,patch,logistic,adni_ad_vs_cn,24,0.046415888336127774,test,0.6829268292682927,0.05099565482883588,0.4696517412935323,0.06838816067238122,0.4854838709677419,0.05671317055923018 +flat_mae,patch,logistic,adni_ad_vs_cn,25,0.046415888336127774,train,0.8888888888888888,0.014085364224253018,0.8240507065185788,0.025298581477063372,0.7899580902292711,0.027004717143648653 +flat_mae,patch,logistic,adni_ad_vs_cn,25,0.046415888336127774,test,0.7317073170731707,0.06001171807047666,0.5918552036199095,0.09179157071087227,0.5854838709677419,0.08268877749124652 +flat_mae,patch,logistic,adni_ad_vs_cn,26,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,26,166.81005372000556,test,0.6341463414634146,0.07141588363561069,0.5467943994104643,0.081450409450251,0.5548387096774194,0.08790619462284623 +flat_mae,patch,logistic,adni_ad_vs_cn,27,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,27,166.81005372000556,test,0.8292682926829268,0.05089212442388279,0.7402714932126697,0.0862993228671721,0.717741935483871,0.08267666110434771 +flat_mae,patch,logistic,adni_ad_vs_cn,28,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,28,21.54434690031882,test,0.7073170731707317,0.06335674656198573,0.603225806451613,0.07963654322875974,0.603225806451613,0.07977037805727527 +flat_mae,patch,logistic,adni_ad_vs_cn,29,0.3593813663804626,train,0.981029810298103,0.006874396000964884,0.9731387984733936,0.009831415091209375,0.9673966636535458,0.012254738843569486 +flat_mae,patch,logistic,adni_ad_vs_cn,29,0.3593813663804626,test,0.7804878048780488,0.061967426341781796,0.6917293233082706,0.09029180737507286,0.685483870967742,0.08877823837371912 +flat_mae,patch,logistic,adni_ad_vs_cn,30,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,30,166.81005372000556,test,0.7317073170731707,0.06334142115197178,0.6479313036690086,0.08051980986116901,0.6532258064516129,0.08398770411964028 +flat_mae,patch,logistic,adni_ad_vs_cn,31,0.046415888336127774,train,0.8997289972899729,0.0136968651784251,0.8444297580930026,0.02367129672323475,0.8132139041827595,0.025923727681069705 +flat_mae,patch,logistic,adni_ad_vs_cn,31,0.046415888336127774,test,0.6585365853658537,0.053514218340034767,0.4564393939393939,0.06527760260660724,0.4693548387096774,0.057288016155258886 +flat_mae,patch,logistic,adni_ad_vs_cn,32,0.005994842503189409,train,0.8211382113821138,0.01367883702386045,0.662462578999889,0.033128308117077176,0.6365149149478182,0.025576533760626498 +flat_mae,patch,logistic,adni_ad_vs_cn,32,0.005994842503189409,test,0.6829268292682927,0.06162317602910723,0.5176470588235295,0.08422379764938481,0.5193548387096775,0.07509654943985879 +flat_mae,patch,logistic,adni_ad_vs_cn,33,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,33,21.54434690031882,test,0.6829268292682927,0.07038229929981918,0.6072218128224024,0.08366459578902238,0.6209677419354839,0.09160821040911148 +flat_mae,patch,logistic,adni_ad_vs_cn,34,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,34,166.81005372000556,test,0.5853658536585366,0.07290396900858034,0.5108771929824562,0.07776005555951794,0.5225806451612903,0.08795801967874477 +flat_mae,patch,logistic,adni_ad_vs_cn,35,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,35,2.782559402207126,test,0.8048780487804879,0.05330785629838335,0.6893939393939394,0.09645721810719854,0.667741935483871,0.08617579224825836 +flat_mae,patch,logistic,adni_ad_vs_cn,36,0.3593813663804626,train,0.983739837398374,0.006710797596857198,0.9770712510356255,0.009556790373665709,0.9732106171419179,0.011978694574501403 +flat_mae,patch,logistic,adni_ad_vs_cn,36,0.3593813663804626,test,0.6829268292682927,0.06131193101825605,0.5176470588235295,0.07997464584842308,0.5193548387096775,0.07110807210742356 +flat_mae,patch,logistic,adni_ad_vs_cn,37,0.005994842503189409,train,0.8346883468834688,0.013543338132462517,0.7024390243902439,0.030636675528469257,0.669631851425754,0.02572412588395463 +flat_mae,patch,logistic,adni_ad_vs_cn,37,0.005994842503189409,test,0.6829268292682927,0.05180559000016044,0.4696517412935323,0.07199816492952844,0.4854838709677419,0.05950491012365401 +flat_mae,patch,logistic,adni_ad_vs_cn,38,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,38,166.81005372000556,test,0.7073170731707317,0.06897117659193518,0.646551724137931,0.07848329770478404,0.6709677419354838,0.08727385075734063 +flat_mae,patch,logistic,adni_ad_vs_cn,39,0.046415888336127774,train,0.9051490514905149,0.0137562256940479,0.8542933537913061,0.02346624044375808,0.8248418111595037,0.026418170302194104 +flat_mae,patch,logistic,adni_ad_vs_cn,39,0.046415888336127774,test,0.6341463414634146,0.062185671209272715,0.48621553884711777,0.07124610278956674,0.48709677419354835,0.06904530506794129 +flat_mae,patch,logistic,adni_ad_vs_cn,40,0.3593813663804626,train,0.994579945799458,0.0035606868584797235,0.9924192620593311,0.004991617700663698,0.9924192620593311,0.005921578075134194 +flat_mae,patch,logistic,adni_ad_vs_cn,40,0.3593813663804626,test,0.6585365853658537,0.06253458769306551,0.5017361111111112,0.07996649715556137,0.5032258064516129,0.07543478270139761 +flat_mae,patch,logistic,adni_ad_vs_cn,41,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,41,1291.5496650148827,test,0.7073170731707317,0.06991676873871233,0.646551724137931,0.07894114414752278,0.6709677419354838,0.08725953752259777 +flat_mae,patch,logistic,adni_ad_vs_cn,42,0.3593813663804626,train,0.991869918699187,0.004647474454864286,0.9886746125121489,0.006438406244581162,0.9906524776070342,0.006203939555376704 +flat_mae,patch,logistic,adni_ad_vs_cn,42,0.3593813663804626,test,0.6585365853658537,0.06911028009631474,0.5370967741935484,0.08656659668915004,0.5370967741935484,0.08591092742237347 +flat_mae,patch,logistic,adni_ad_vs_cn,43,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,43,21.54434690031882,test,0.7317073170731707,0.058947561366665034,0.5918552036199095,0.0908701930112124,0.5854838709677419,0.08170146922082118 +flat_mae,patch,logistic,adni_ad_vs_cn,44,0.046415888336127774,train,0.8834688346883469,0.014507082619406182,0.8192021512972733,0.0250918767603907,0.7904716903607527,0.026620070154215827 +flat_mae,patch,logistic,adni_ad_vs_cn,44,0.046415888336127774,test,0.8292682926829268,0.0487042086529655,0.7402714932126697,0.08396601544447335,0.717741935483871,0.08134643602202835 +flat_mae,patch,logistic,adni_ad_vs_cn,45,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,45,2.782559402207126,test,0.8292682926829268,0.058536097558943075,0.7759562841530054,0.07603944891048171,0.7854838709677419,0.08019685068331132 +flat_mae,patch,logistic,adni_ad_vs_cn,46,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,46,166.81005372000556,test,0.8048780487804879,0.0624995704922779,0.7515151515151515,0.07635315965586958,0.7693548387096774,0.08036862127820939 +flat_mae,patch,logistic,adni_ad_vs_cn,47,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,47,1291.5496650148827,test,0.7560975609756098,0.05952290987110839,0.6440972222222222,0.08764842885293449,0.635483870967742,0.08424528499390618 +flat_mae,patch,logistic,adni_ad_vs_cn,48,0.3593813663804626,train,0.981029810298103,0.006795416595700119,0.9731387984733936,0.00971908540144298,0.9673966636535458,0.012123563590541366 +flat_mae,patch,logistic,adni_ad_vs_cn,48,0.3593813663804626,test,0.7560975609756098,0.061854274060182735,0.6693548387096775,0.08439574356579191,0.6693548387096775,0.08610621807304551 +flat_mae,patch,logistic,adni_ad_vs_cn,49,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,49,166.81005372000556,test,0.7804878048780488,0.06103394282917851,0.6917293233082706,0.08836653485890829,0.685483870967742,0.08823311162773874 +flat_mae,patch,logistic,adni_ad_vs_cn,50,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,50,166.81005372000556,test,0.7560975609756098,0.06305283281783113,0.6893939393939394,0.07713242558306944,0.7032258064516128,0.08182248977821904 +flat_mae,patch,logistic,adni_ad_vs_cn,51,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,51,21.54434690031882,test,0.6341463414634146,0.07665859478668938,0.5684210526315789,0.0837186252030975,0.5887096774193548,0.09448699204087492 +flat_mae,patch,logistic,adni_ad_vs_cn,52,0.046415888336127774,train,0.907859078590786,0.01395653326978228,0.8577551020408163,0.023828900946525296,0.8266085956118004,0.026719526459982886 +flat_mae,patch,logistic,adni_ad_vs_cn,52,0.046415888336127774,test,0.7317073170731707,0.04937578228508515,0.5512437810945273,0.08623775350429151,0.5516129032258065,0.0681553146854677 +flat_mae,patch,logistic,adni_ad_vs_cn,53,0.046415888336127774,train,0.8834688346883469,0.014181102356473227,0.8192021512972733,0.02413906959607781,0.7904716903607527,0.025483076174696338 +flat_mae,patch,logistic,adni_ad_vs_cn,53,0.046415888336127774,test,0.7560975609756098,0.058458871176873074,0.6440972222222222,0.08782769383154992,0.635483870967742,0.08281749169276355 +flat_mae,patch,logistic,adni_ad_vs_cn,54,0.046415888336127774,train,0.907859078590786,0.01447996263599433,0.8605008005692938,0.023635080337973846,0.8347029336839511,0.026306402238760046 +flat_mae,patch,logistic,adni_ad_vs_cn,54,0.046415888336127774,test,0.7317073170731707,0.0611557144985153,0.6232247284878863,0.08591094853981288,0.6193548387096774,0.08423100291601218 +flat_mae,patch,logistic,adni_ad_vs_cn,55,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,55,166.81005372000556,test,0.7804878048780488,0.06237946854832291,0.7119437939110069,0.08024699067685367,0.7193548387096774,0.08405370235946173 +flat_mae,patch,logistic,adni_ad_vs_cn,56,0.046415888336127774,train,0.907859078590786,0.01308873401164639,0.8548454276194002,0.0233606721249696,0.81851425753965,0.02590747859088358 +flat_mae,patch,logistic,adni_ad_vs_cn,56,0.046415888336127774,test,0.7804878048780488,0.05251126051302016,0.6328358208955224,0.09783738766302445,0.6177419354838709,0.08020137110523241 +flat_mae,patch,logistic,adni_ad_vs_cn,57,0.046415888336127774,train,0.8997289972899729,0.014372544860067686,0.8444297580930026,0.024831624806428455,0.8132139041827595,0.027306061028989526 +flat_mae,patch,logistic,adni_ad_vs_cn,57,0.046415888336127774,test,0.8048780487804879,0.0604628390649412,0.7354838709677419,0.0837156147339335,0.7354838709677419,0.08576343688997089 +flat_mae,patch,logistic,adni_ad_vs_cn,58,0.3593813663804626,train,0.981029810298103,0.007121546972642544,0.9731387984733936,0.01022995386577982,0.9673966636535458,0.013051237656855539 +flat_mae,patch,logistic,adni_ad_vs_cn,58,0.3593813663804626,test,0.7317073170731707,0.06589187689547962,0.6232247284878863,0.08925342018309064,0.6193548387096774,0.08585919043833529 +flat_mae,patch,logistic,adni_ad_vs_cn,59,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,59,166.81005372000556,test,0.6585365853658537,0.07394703637052226,0.5876436781609196,0.08063975024057786,0.6048387096774194,0.08906272246444275 +flat_mae,patch,logistic,adni_ad_vs_cn,60,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,60,166.81005372000556,test,0.7804878048780488,0.06281131390183584,0.7119437939110069,0.08294455490614333,0.7193548387096774,0.08609803815893771 +flat_mae,patch,logistic,adni_ad_vs_cn,61,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,61,166.81005372000556,test,0.5853658536585366,0.07065279028975949,0.4558938329430133,0.07558256718518437,0.45483870967741935,0.0776880832756125 +flat_mae,patch,logistic,adni_ad_vs_cn,62,0.3593813663804626,train,0.981029810298103,0.006830754344275052,0.9733593242365172,0.009627117793291999,0.9714438326896212,0.011346990607465598 +flat_mae,patch,logistic,adni_ad_vs_cn,62,0.3593813663804626,test,0.7317073170731707,0.06235686286386196,0.6232247284878863,0.0873467091558941,0.6193548387096774,0.08499091608435244 +flat_mae,patch,logistic,adni_ad_vs_cn,63,10000.0,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,63,10000.0,test,0.8536585365853658,0.04982357929870599,0.7864583333333333,0.07931872473862542,0.7677419354838709,0.08217912537404164 +flat_mae,patch,logistic,adni_ad_vs_cn,64,0.046415888336127774,train,0.8997289972899729,0.014011211225185656,0.8444297580930026,0.02432015204984807,0.8132139041827595,0.026916990417893482 +flat_mae,patch,logistic,adni_ad_vs_cn,64,0.046415888336127774,test,0.7073170731707317,0.06005502137131896,0.5729166666666666,0.08730034718724931,0.5693548387096774,0.08110422348828622 +flat_mae,patch,logistic,adni_ad_vs_cn,65,0.3593813663804626,train,0.986449864498645,0.006063197358124488,0.9809709458832265,0.00853910269311789,0.97902457063029,0.010106847853294066 +flat_mae,patch,logistic,adni_ad_vs_cn,65,0.3593813663804626,test,0.6829268292682927,0.07114095232814822,0.6072218128224024,0.08258508982760863,0.6209677419354839,0.09044888053256475 +flat_mae,patch,logistic,adni_ad_vs_cn,66,0.3593813663804626,train,0.981029810298103,0.006830719938632524,0.9731387984733936,0.009788244494078155,0.9673966636535458,0.012325558108103112 +flat_mae,patch,logistic,adni_ad_vs_cn,66,0.3593813663804626,test,0.7073170731707317,0.06317498808525161,0.603225806451613,0.08189253450681538,0.603225806451613,0.08284060644999601 +flat_mae,patch,logistic,adni_ad_vs_cn,67,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,67,166.81005372000556,test,0.7317073170731707,0.06760602530796868,0.6479313036690086,0.08528233007239008,0.6532258064516129,0.08848298895283237 +flat_mae,patch,logistic,adni_ad_vs_cn,68,0.046415888336127774,train,0.9051490514905149,0.013649770275808309,0.8528389603582457,0.023411110934446904,0.8207946421234283,0.02555695889165271 +flat_mae,patch,logistic,adni_ad_vs_cn,68,0.046415888336127774,test,0.6829268292682927,0.06711415156044784,0.5839188134270101,0.08380825050837176,0.5870967741935484,0.08691814274351051 +flat_mae,patch,logistic,adni_ad_vs_cn,69,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,69,2.782559402207126,test,0.7073170731707317,0.06843210506892351,0.603225806451613,0.09054793164366101,0.603225806451613,0.09053704814256078 +flat_mae,patch,logistic,adni_ad_vs_cn,70,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,70,166.81005372000556,test,0.7073170731707317,0.0563709984881698,0.5340909090909092,0.08521740122417228,0.535483870967742,0.07242671986401253 +flat_mae,patch,logistic,adni_ad_vs_cn,71,0.3593813663804626,train,0.981029810298103,0.006823811645484593,0.9733593242365172,0.009607511226956052,0.9714438326896212,0.01117424385539271 +flat_mae,patch,logistic,adni_ad_vs_cn,71,0.3593813663804626,test,0.7317073170731707,0.05007670499449114,0.5512437810945273,0.08382410477259199,0.5516129032258065,0.06752751402861278 +flat_mae,patch,logistic,adni_ad_vs_cn,72,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,72,1291.5496650148827,test,0.7317073170731707,0.05535093814345963,0.5918552036199095,0.08626927409695621,0.5854838709677419,0.07674546568783097 +flat_mae,patch,logistic,adni_ad_vs_cn,73,0.3593813663804626,train,0.981029810298103,0.0068798637679954285,0.9729123189697663,0.010051832103661371,0.9633494946174705,0.01362824624722049 +flat_mae,patch,logistic,adni_ad_vs_cn,73,0.3593813663804626,test,0.7804878048780488,0.06198585549925898,0.7119437939110069,0.08021073369702614,0.7193548387096774,0.08417772907866301 +flat_mae,patch,logistic,adni_ad_vs_cn,74,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,74,2.782559402207126,test,0.7073170731707317,0.05760384926658275,0.5729166666666666,0.08495896949926589,0.5693548387096774,0.07925242348667937 +flat_mae,patch,logistic,adni_ad_vs_cn,75,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,75,166.81005372000556,test,0.6585365853658537,0.06444927080146963,0.5370967741935484,0.08283788698898152,0.5370967741935484,0.08286810477355994 +flat_mae,patch,logistic,adni_ad_vs_cn,76,0.3593813663804626,train,0.983739837398374,0.006213649514974679,0.9768796992481203,0.009018947692561261,0.9691634481058427,0.012257156593665676 +flat_mae,patch,logistic,adni_ad_vs_cn,76,0.3593813663804626,test,0.6829268292682927,0.06306656823194387,0.5547201336675021,0.08425660364726134,0.5532258064516129,0.08049319255605909 +flat_mae,patch,logistic,adni_ad_vs_cn,77,0.046415888336127774,train,0.8915989159891599,0.015051047457500686,0.8326530612244898,0.025604769925261443,0.8038663817897937,0.027735657536753233 +flat_mae,patch,logistic,adni_ad_vs_cn,77,0.046415888336127774,test,0.8048780487804879,0.04159519946675767,0.6554621848739496,0.09670328830088414,0.6338709677419355,0.07579785064453282 +flat_mae,patch,logistic,adni_ad_vs_cn,78,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,78,2.782559402207126,test,0.7560975609756098,0.06355142844270979,0.6693548387096775,0.08718701899121467,0.6693548387096775,0.08969950273464658 +flat_mae,patch,logistic,adni_ad_vs_cn,79,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,79,1291.5496650148827,test,0.7317073170731707,0.06744905760499918,0.6676492262343405,0.08019456960110002,0.6870967741935483,0.08688150523634586 +flat_mae,patch,logistic,adni_ad_vs_cn,80,0.005994842503189409,train,0.8428184281842819,0.01517370770099002,0.7258965163934425,0.03155770029025171,0.6911208809269456,0.02800853235952588 +flat_mae,patch,logistic,adni_ad_vs_cn,80,0.005994842503189409,test,0.7317073170731707,0.048652784059985986,0.5512437810945273,0.0848140684363761,0.5516129032258065,0.06759438085063466 +flat_mae,patch,logistic,adni_ad_vs_cn,81,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,81,2.782559402207126,test,0.7317073170731707,0.05271579823639379,0.5512437810945273,0.09059973601741594,0.5516129032258065,0.07320479299172629 +flat_mae,patch,logistic,adni_ad_vs_cn,82,0.3593813663804626,train,0.986449864498645,0.005477087463711145,0.9809709458832265,0.007725314007404685,0.97902457063029,0.009357928868786973 +flat_mae,patch,logistic,adni_ad_vs_cn,82,0.3593813663804626,test,0.6585365853658537,0.0662038745404239,0.5370967741935484,0.08429389180034207,0.5370967741935484,0.08377412374076364 +flat_mae,patch,logistic,adni_ad_vs_cn,83,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,83,21.54434690031882,test,0.7560975609756098,0.05994373725361969,0.6440972222222222,0.08646285863303275,0.635483870967742,0.08239682009967994 +flat_mae,patch,logistic,adni_ad_vs_cn,84,0.046415888336127774,train,0.8888888888888888,0.014287652510817574,0.8240507065185788,0.025409882747540247,0.7899580902292711,0.02675385740689436 +flat_mae,patch,logistic,adni_ad_vs_cn,84,0.046415888336127774,test,0.7317073170731707,0.05850183928122379,0.5918552036199095,0.0884847013642466,0.5854838709677419,0.07905898455268422 +flat_mae,patch,logistic,adni_ad_vs_cn,85,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,85,2.782559402207126,test,0.8048780487804879,0.05958883509763119,0.7354838709677419,0.08231586016541544,0.7354838709677419,0.08427378601537516 +flat_mae,patch,logistic,adni_ad_vs_cn,86,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,86,21.54434690031882,test,0.6097560975609756,0.06457173240527131,0.47096774193548385,0.07051463215125399,0.47096774193548385,0.07094648149282866 +flat_mae,patch,logistic,adni_ad_vs_cn,87,0.046415888336127774,train,0.8888888888888888,0.013867485921452559,0.8276113535625164,0.023530356206924737,0.7980524283014216,0.02501609135677604 +flat_mae,patch,logistic,adni_ad_vs_cn,87,0.046415888336127774,test,0.8536585365853658,0.04039613483610294,0.7415966386554622,0.10037409535566423,0.7,0.08281207641401102 +flat_mae,patch,logistic,adni_ad_vs_cn,88,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,88,166.81005372000556,test,0.6829268292682927,0.06896565630050186,0.5839188134270101,0.08497339474133392,0.5870967741935484,0.0892204161831348 +flat_mae,patch,logistic,adni_ad_vs_cn,89,0.3593813663804626,train,0.978319783197832,0.007501736835685692,0.9694283347141673,0.010731148724159456,0.9656298792012491,0.013389604255008656 +flat_mae,patch,logistic,adni_ad_vs_cn,89,0.3593813663804626,test,0.8048780487804879,0.06099543092473591,0.7354838709677419,0.08308134494607201,0.7354838709677419,0.08749036819293228 +flat_mae,patch,logistic,adni_ad_vs_cn,90,0.046415888336127774,train,0.8915989159891599,0.01412639572384858,0.8326530612244898,0.02384110231574261,0.8038663817897937,0.025622686995727614 +flat_mae,patch,logistic,adni_ad_vs_cn,90,0.046415888336127774,test,0.7560975609756098,0.06409756097560976,0.6693548387096775,0.08758449848837768,0.6693548387096775,0.08889360311235901 +flat_mae,patch,logistic,adni_ad_vs_cn,91,0.046415888336127774,train,0.8834688346883469,0.014309657533284914,0.8154678141536315,0.025459452108947157,0.7823773522886022,0.026596645517411057 +flat_mae,patch,logistic,adni_ad_vs_cn,91,0.046415888336127774,test,0.7073170731707317,0.05444818088918657,0.5340909090909092,0.08578844622397573,0.535483870967742,0.07350144059126076 +flat_mae,patch,logistic,adni_ad_vs_cn,92,0.3593813663804626,train,0.981029810298103,0.007459764947121099,0.9733593242365172,0.01050964359431741,0.9714438326896212,0.012108245564842753 +flat_mae,patch,logistic,adni_ad_vs_cn,92,0.3593813663804626,test,0.5853658536585366,0.06529475565466479,0.4177109440267335,0.06516119376867963,0.42096774193548386,0.06555645873594698 +flat_mae,patch,logistic,adni_ad_vs_cn,93,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,93,166.81005372000556,test,0.5365853658536586,0.07530031091117388,0.4533333333333333,0.07714706157901509,0.4564516129032258,0.08801984947831497 +flat_mae,patch,logistic,adni_ad_vs_cn,94,0.046415888336127774,train,0.9159891598915989,0.012899842863472304,0.8734133790737564,0.020617820736814455,0.848097625112992,0.023143457000990172 +flat_mae,patch,logistic,adni_ad_vs_cn,94,0.046415888336127774,test,0.6829268292682927,0.05195694460610538,0.4696517412935323,0.06883330036013881,0.4854838709677419,0.057035878224032645 +flat_mae,patch,logistic,adni_ad_vs_cn,95,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,95,166.81005372000556,test,0.6097560975609756,0.07291158989153644,0.5030303030303029,0.07999044595236218,0.5048387096774194,0.08459821789106076 +flat_mae,patch,logistic,adni_ad_vs_cn,96,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,96,21.54434690031882,test,0.7560975609756098,0.06457173240527131,0.7054597701149425,0.07381484080463055,0.7370967741935484,0.08179171308160836 +flat_mae,patch,logistic,adni_ad_vs_cn,97,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,97,166.81005372000556,test,0.8048780487804879,0.05999595465244254,0.7354838709677419,0.0821993943013019,0.7354838709677419,0.08564399725835534 +flat_mae,patch,logistic,adni_ad_vs_cn,98,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,98,166.81005372000556,test,0.6341463414634146,0.07160397398069106,0.5467943994104643,0.08041768032778196,0.5548387096774194,0.08882080453011969 +flat_mae,patch,logistic,adni_ad_vs_cn,99,0.046415888336127774,train,0.9132791327913279,0.013611001509026277,0.8674330878390515,0.02277190820524584,0.8382365025885447,0.025750334190505823 +flat_mae,patch,logistic,adni_ad_vs_cn,99,0.046415888336127774,test,0.7560975609756098,0.05098053424690585,0.6117424242424243,0.0881463406365662,0.6016129032258064,0.0746472436071672 +flat_mae,patch,logistic,adni_ad_vs_cn,100,0.3593813663804626,train,0.991869918699187,0.004731195084912484,0.9885825675299359,0.00667317781585125,0.986605308570959,0.008249310020531123 +flat_mae,patch,logistic,adni_ad_vs_cn,100,0.3593813663804626,test,0.6341463414634146,0.06856392129098185,0.5199063231850116,0.08295166076685709,0.5209677419354839,0.08592418669083084 diff --git a/input_space_v3/flat_lr1e-3_3/eval_v2/adni_ad_vs_cn__patch__logistic/log.txt b/input_space_v3/flat_lr1e-3_3/eval_v2/adni_ad_vs_cn__patch__logistic/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..98a84da8e6647219edf36d0f0cc04abb13b5559c --- /dev/null +++ b/input_space_v3/flat_lr1e-3_3/eval_v2/adni_ad_vs_cn__patch__logistic/log.txt @@ -0,0 +1,240 @@ +fMRI foundation model logistic probe eval +version: 0.1.dev86+gf97f52698 +sha: bcce2b486277d3a5b520775efd9cdf1a2affce36, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-04-08 22:15:49 +config: +output_root: experiments/input_space_v3/output +name_prefix: eval_logistic +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_3; eval v2 (adni_ad_vs_cn patch logistic) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: input_space_v3/flat_lr1e-3_3/eval_v2/adni_ad_vs_cn__patch__logistic +model: flat_mae +representation: patch +dataset: adni_ad_vs_cn +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/eval_v2/adni_ad_vs_cn__patch__logistic +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=True, reg_tokens=0, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: adni_ad_vs_cn (flat) +train (n=328): +ADNIDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'bold', 'mean', 'std'], + num_rows: 525 +}), + labels=[0 1], + counts=[251 77] +) + +validation (n=41): +ADNIDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'bold', 'mean', 'std'], + num_rows: 66 +}), + labels=[0 1], + counts=[31 10] +) + +test (n=41): +ADNIDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'bold', 'mean', 'std'], + num_rows: 66 +}), + labels=[0 1], + counts=[32 9] +) + +extracting features for all splits +extract (train) [ 0/164] eta: 0:13:44 time: 5.0247 data: 3.9870 max mem: 2698 +extract (train) [ 20/164] eta: 0:01:03 time: 0.2120 data: 0.0754 max mem: 2851 +extract (train) [ 40/164] eta: 0:00:39 time: 0.1894 data: 0.0619 max mem: 2851 +extract (train) [ 60/164] eta: 0:00:29 time: 0.2025 data: 0.0703 max mem: 2851 +extract (train) [ 80/164] eta: 0:00:21 time: 0.1790 data: 0.0589 max mem: 2851 +extract (train) [100/164] eta: 0:00:15 time: 0.2026 data: 0.0709 max mem: 2851 +extract (train) [120/164] eta: 0:00:10 time: 0.1890 data: 0.0650 max mem: 2851 +extract (train) [140/164] eta: 0:00:05 time: 0.1860 data: 0.0615 max mem: 2851 +extract (train) [160/164] eta: 0:00:00 time: 0.1661 data: 0.0523 max mem: 2851 +extract (train) [163/164] eta: 0:00:00 time: 0.1672 data: 0.0528 max mem: 2851 +extract (train) Total time: 0:00:36 (0.2220 s / it) +extract (validation) [ 0/21] eta: 0:01:18 time: 3.7390 data: 3.6152 max mem: 2851 +extract (validation) [20/21] eta: 0:00:00 time: 0.1718 data: 0.0556 max mem: 2851 +extract (validation) Total time: 0:00:07 (0.3521 s / it) +extract (test) [ 0/21] eta: 0:01:17 time: 3.6827 data: 3.5559 max mem: 2851 +extract (test) [20/21] eta: 0:00:00 time: 0.1706 data: 0.0549 max mem: 2851 +extract (test) Total time: 0:00:07 (0.3490 s / it) +feature extraction time: 0:00:51 +train features: (328, 768) +validation features: (41, 768) +test features: (41, 768) +evaluating fixed splits +eval results (fixed splits): + +| model | repr | clf | dataset | trial | C | split | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:--------------|:--------|--------:|:--------|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | adni_ad_vs_cn | | 0.35938 | train | 0.97561 | 0.0078024 | 0.96546 | 0.011321 | 0.95622 | 0.014885 | +| flat_mae | patch | logistic | adni_ad_vs_cn | | 0.35938 | test | 0.65854 | 0.065825 | 0.50174 | 0.079242 | 0.50174 | 0.079419 | + + +evaluating random splits (n=100) +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 1, "C": 0.046415888336127774, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.05123344758163885, "f1": 0.6117424242424243, "f1_std": 0.08973724608677408, "bacc": 0.6016129032258064, "bacc_std": 0.07680382892380379} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 2, "C": 0.046415888336127774, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.062209543999806736, "f1": 0.6232247284878863, "f1_std": 0.08723731366087865, "bacc": 0.6193548387096774, "bacc_std": 0.08630467019701063} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 3, "C": 0.046415888336127774, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.05509699413435623, "f1": 0.5340909090909092, "f1_std": 0.08221981372333416, "bacc": 0.535483870967742, "bacc_std": 0.06923012973903532} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 4, "C": 0.046415888336127774, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.05735598056734071, "f1": 0.7152777777777778, "f1_std": 0.08861475747178658, "bacc": 0.7016129032258065, "bacc_std": 0.08536697857003549} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 5, "C": 21.54434690031882, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.047468603230798, "f1": 0.4696517412935323, "f1_std": 0.06732311561941388, "bacc": 0.4854838709677419, "bacc_std": 0.05467435513347356} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 6, "C": 0.046415888336127774, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.030272645664861653, "f1": 0.6095238095238095, "f1_std": 0.09367341473139215, "bacc": 0.6, "bacc_std": 0.0620589236129664} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 7, "C": 166.81005372000556, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.06293512896674383, "f1": 0.7119437939110069, "f1_std": 0.08306693029955815, "bacc": 0.7193548387096774, "bacc_std": 0.0881729793485557} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 8, "C": 0.046415888336127774, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.05273644526446079, "f1": 0.4696517412935323, "f1_std": 0.06831084402518633, "bacc": 0.4854838709677419, "bacc_std": 0.05711177641435183} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 9, "C": 166.81005372000556, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.06997067457454172, "f1": 0.6072218128224024, "f1_std": 0.08155582444493122, "bacc": 0.6209677419354839, "bacc_std": 0.08833928604475463} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 10, "C": 21.54434690031882, "split": "test", "acc": 0.6585365853658537, "acc_std": 0.06584462449325641, "f1": 0.5370967741935484, "f1_std": 0.0820781074771174, "bacc": 0.5370967741935484, "bacc_std": 0.08236500171045824} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 11, "C": 0.046415888336127774, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.03926753521463045, "f1": 0.5886287625418061, "f1_std": 0.0886394037932827, "bacc": 0.5838709677419355, "bacc_std": 0.06323654912027536} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 12, "C": 0.3593813663804626, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.07034098981607083, "f1": 0.5839188134270101, "f1_std": 0.08588432332605155, "bacc": 0.5870967741935484, "bacc_std": 0.0888826500722777} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 13, "C": 0.3593813663804626, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.059392121971607516, "f1": 0.6440972222222222, "f1_std": 0.0873095566734307, "bacc": 0.635483870967742, "bacc_std": 0.08391024291327506} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 14, "C": 0.3593813663804626, "split": "test", "acc": 0.6585365853658537, "acc_std": 0.07060375306214564, "f1": 0.5651515151515152, "f1_std": 0.08354457791784438, "bacc": 0.5709677419354839, "bacc_std": 0.08773539651867587} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 15, "C": 0.046415888336127774, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.041952892763000495, "f1": 0.4972129319955407, "f1_std": 0.07825391058148987, "bacc": 0.5177419354838709, "bacc_std": 0.05558732253525905} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 16, "C": 0.3593813663804626, "split": "test", "acc": 0.8292682926829268, "acc_std": 0.04552178812971945, "f1": 0.7144278606965174, "f1_std": 0.09622888490770774, "bacc": 0.6838709677419355, "bacc_std": 0.08081816823176054} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 17, "C": 0.3593813663804626, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.061556259724282365, "f1": 0.6440972222222222, "f1_std": 0.09272749411667944, "bacc": 0.635483870967742, "bacc_std": 0.08692742460698655} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 18, "C": 2.782559402207126, "split": "test", "acc": 0.8292682926829268, "acc_std": 0.05397095303554074, "f1": 0.7402714932126697, "f1_std": 0.09081431235297628, "bacc": 0.717741935483871, "bacc_std": 0.0872452202102312} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 19, "C": 21.54434690031882, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.06101267166343247, "f1": 0.5176470588235295, "f1_std": 0.07975397030621992, "bacc": 0.5193548387096775, "bacc_std": 0.07162051826702058} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 20, "C": 0.3593813663804626, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.06431072325452827, "f1": 0.6479313036690086, "f1_std": 0.07931010719609831, "bacc": 0.6532258064516129, "bacc_std": 0.08272858944117274} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 21, "C": 2.782559402207126, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.060901242454814944, "f1": 0.6440972222222222, "f1_std": 0.09294454878494983, "bacc": 0.635483870967742, "bacc_std": 0.08738055626341151} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 22, "C": 2.782559402207126, "split": "test", "acc": 0.6585365853658537, "acc_std": 0.05494014914525005, "f1": 0.4564393939393939, "f1_std": 0.06550264072734918, "bacc": 0.4693548387096774, "bacc_std": 0.05729794803581979} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 23, "C": 0.3593813663804626, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.06316754865320835, "f1": 0.6693548387096775, "f1_std": 0.08719513359093745, "bacc": 0.6693548387096775, "bacc_std": 0.08927381554251643} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 24, "C": 0.046415888336127774, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.05099565482883588, "f1": 0.4696517412935323, "f1_std": 0.06838816067238122, "bacc": 0.4854838709677419, "bacc_std": 0.05671317055923018} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 25, "C": 0.046415888336127774, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.06001171807047666, "f1": 0.5918552036199095, "f1_std": 0.09179157071087227, "bacc": 0.5854838709677419, "bacc_std": 0.08268877749124652} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 26, "C": 166.81005372000556, "split": "test", "acc": 0.6341463414634146, "acc_std": 0.07141588363561069, "f1": 0.5467943994104643, "f1_std": 0.081450409450251, "bacc": 0.5548387096774194, "bacc_std": 0.08790619462284623} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 27, "C": 166.81005372000556, "split": "test", "acc": 0.8292682926829268, "acc_std": 0.05089212442388279, "f1": 0.7402714932126697, "f1_std": 0.0862993228671721, "bacc": 0.717741935483871, "bacc_std": 0.08267666110434771} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 28, "C": 21.54434690031882, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.06335674656198573, "f1": 0.603225806451613, "f1_std": 0.07963654322875974, "bacc": 0.603225806451613, "bacc_std": 0.07977037805727527} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 29, "C": 0.3593813663804626, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.061967426341781796, "f1": 0.6917293233082706, "f1_std": 0.09029180737507286, "bacc": 0.685483870967742, "bacc_std": 0.08877823837371912} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 30, "C": 166.81005372000556, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.06334142115197178, "f1": 0.6479313036690086, "f1_std": 0.08051980986116901, "bacc": 0.6532258064516129, "bacc_std": 0.08398770411964028} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 31, "C": 0.046415888336127774, "split": "test", "acc": 0.6585365853658537, "acc_std": 0.053514218340034767, "f1": 0.4564393939393939, "f1_std": 0.06527760260660724, "bacc": 0.4693548387096774, "bacc_std": 0.057288016155258886} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 32, "C": 0.005994842503189409, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.06162317602910723, "f1": 0.5176470588235295, "f1_std": 0.08422379764938481, "bacc": 0.5193548387096775, "bacc_std": 0.07509654943985879} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 33, "C": 21.54434690031882, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.07038229929981918, "f1": 0.6072218128224024, "f1_std": 0.08366459578902238, "bacc": 0.6209677419354839, "bacc_std": 0.09160821040911148} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 34, "C": 166.81005372000556, "split": "test", "acc": 0.5853658536585366, "acc_std": 0.07290396900858034, "f1": 0.5108771929824562, "f1_std": 0.07776005555951794, "bacc": 0.5225806451612903, "bacc_std": 0.08795801967874477} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 35, "C": 2.782559402207126, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.05330785629838335, "f1": 0.6893939393939394, "f1_std": 0.09645721810719854, "bacc": 0.667741935483871, "bacc_std": 0.08617579224825836} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 36, "C": 0.3593813663804626, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.06131193101825605, "f1": 0.5176470588235295, "f1_std": 0.07997464584842308, "bacc": 0.5193548387096775, "bacc_std": 0.07110807210742356} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 37, "C": 0.005994842503189409, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.05180559000016044, "f1": 0.4696517412935323, "f1_std": 0.07199816492952844, "bacc": 0.4854838709677419, "bacc_std": 0.05950491012365401} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 38, "C": 166.81005372000556, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.06897117659193518, "f1": 0.646551724137931, "f1_std": 0.07848329770478404, "bacc": 0.6709677419354838, "bacc_std": 0.08727385075734063} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 39, "C": 0.046415888336127774, "split": "test", "acc": 0.6341463414634146, "acc_std": 0.062185671209272715, "f1": 0.48621553884711777, "f1_std": 0.07124610278956674, "bacc": 0.48709677419354835, "bacc_std": 0.06904530506794129} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 40, "C": 0.3593813663804626, "split": "test", "acc": 0.6585365853658537, "acc_std": 0.06253458769306551, "f1": 0.5017361111111112, "f1_std": 0.07996649715556137, "bacc": 0.5032258064516129, "bacc_std": 0.07543478270139761} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 41, "C": 1291.5496650148827, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.06991676873871233, "f1": 0.646551724137931, "f1_std": 0.07894114414752278, "bacc": 0.6709677419354838, "bacc_std": 0.08725953752259777} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 42, "C": 0.3593813663804626, "split": "test", "acc": 0.6585365853658537, "acc_std": 0.06911028009631474, "f1": 0.5370967741935484, "f1_std": 0.08656659668915004, "bacc": 0.5370967741935484, "bacc_std": 0.08591092742237347} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 43, "C": 21.54434690031882, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.058947561366665034, "f1": 0.5918552036199095, "f1_std": 0.0908701930112124, "bacc": 0.5854838709677419, "bacc_std": 0.08170146922082118} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 44, "C": 0.046415888336127774, "split": "test", "acc": 0.8292682926829268, "acc_std": 0.0487042086529655, "f1": 0.7402714932126697, "f1_std": 0.08396601544447335, "bacc": 0.717741935483871, "bacc_std": 0.08134643602202835} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 45, "C": 2.782559402207126, "split": "test", "acc": 0.8292682926829268, "acc_std": 0.058536097558943075, "f1": 0.7759562841530054, "f1_std": 0.07603944891048171, "bacc": 0.7854838709677419, "bacc_std": 0.08019685068331132} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 46, "C": 166.81005372000556, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.0624995704922779, "f1": 0.7515151515151515, "f1_std": 0.07635315965586958, "bacc": 0.7693548387096774, "bacc_std": 0.08036862127820939} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 47, "C": 1291.5496650148827, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.05952290987110839, "f1": 0.6440972222222222, "f1_std": 0.08764842885293449, "bacc": 0.635483870967742, "bacc_std": 0.08424528499390618} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 48, "C": 0.3593813663804626, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.061854274060182735, "f1": 0.6693548387096775, "f1_std": 0.08439574356579191, "bacc": 0.6693548387096775, "bacc_std": 0.08610621807304551} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 49, "C": 166.81005372000556, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.06103394282917851, "f1": 0.6917293233082706, "f1_std": 0.08836653485890829, "bacc": 0.685483870967742, "bacc_std": 0.08823311162773874} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 50, "C": 166.81005372000556, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.06305283281783113, "f1": 0.6893939393939394, "f1_std": 0.07713242558306944, "bacc": 0.7032258064516128, "bacc_std": 0.08182248977821904} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 51, "C": 21.54434690031882, "split": "test", "acc": 0.6341463414634146, "acc_std": 0.07665859478668938, "f1": 0.5684210526315789, "f1_std": 0.0837186252030975, "bacc": 0.5887096774193548, "bacc_std": 0.09448699204087492} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 52, "C": 0.046415888336127774, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.04937578228508515, "f1": 0.5512437810945273, "f1_std": 0.08623775350429151, "bacc": 0.5516129032258065, "bacc_std": 0.0681553146854677} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 53, "C": 0.046415888336127774, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.058458871176873074, "f1": 0.6440972222222222, "f1_std": 0.08782769383154992, "bacc": 0.635483870967742, "bacc_std": 0.08281749169276355} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 54, "C": 0.046415888336127774, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.0611557144985153, "f1": 0.6232247284878863, "f1_std": 0.08591094853981288, "bacc": 0.6193548387096774, "bacc_std": 0.08423100291601218} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 55, "C": 166.81005372000556, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.06237946854832291, "f1": 0.7119437939110069, "f1_std": 0.08024699067685367, "bacc": 0.7193548387096774, "bacc_std": 0.08405370235946173} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 56, "C": 0.046415888336127774, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.05251126051302016, "f1": 0.6328358208955224, "f1_std": 0.09783738766302445, "bacc": 0.6177419354838709, "bacc_std": 0.08020137110523241} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 57, "C": 0.046415888336127774, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.0604628390649412, "f1": 0.7354838709677419, "f1_std": 0.0837156147339335, "bacc": 0.7354838709677419, "bacc_std": 0.08576343688997089} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 58, "C": 0.3593813663804626, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.06589187689547962, "f1": 0.6232247284878863, "f1_std": 0.08925342018309064, "bacc": 0.6193548387096774, "bacc_std": 0.08585919043833529} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 59, "C": 166.81005372000556, "split": "test", "acc": 0.6585365853658537, "acc_std": 0.07394703637052226, "f1": 0.5876436781609196, "f1_std": 0.08063975024057786, "bacc": 0.6048387096774194, "bacc_std": 0.08906272246444275} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 60, "C": 166.81005372000556, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.06281131390183584, "f1": 0.7119437939110069, "f1_std": 0.08294455490614333, "bacc": 0.7193548387096774, "bacc_std": 0.08609803815893771} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 61, "C": 166.81005372000556, "split": "test", "acc": 0.5853658536585366, "acc_std": 0.07065279028975949, "f1": 0.4558938329430133, "f1_std": 0.07558256718518437, "bacc": 0.45483870967741935, "bacc_std": 0.0776880832756125} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 62, "C": 0.3593813663804626, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.06235686286386196, "f1": 0.6232247284878863, "f1_std": 0.0873467091558941, "bacc": 0.6193548387096774, "bacc_std": 0.08499091608435244} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 63, "C": 10000.0, "split": "test", "acc": 0.8536585365853658, "acc_std": 0.04982357929870599, "f1": 0.7864583333333333, "f1_std": 0.07931872473862542, "bacc": 0.7677419354838709, "bacc_std": 0.08217912537404164} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 64, "C": 0.046415888336127774, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.06005502137131896, "f1": 0.5729166666666666, "f1_std": 0.08730034718724931, "bacc": 0.5693548387096774, "bacc_std": 0.08110422348828622} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 65, "C": 0.3593813663804626, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.07114095232814822, "f1": 0.6072218128224024, "f1_std": 0.08258508982760863, "bacc": 0.6209677419354839, "bacc_std": 0.09044888053256475} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 66, "C": 0.3593813663804626, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.06317498808525161, "f1": 0.603225806451613, "f1_std": 0.08189253450681538, "bacc": 0.603225806451613, "bacc_std": 0.08284060644999601} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 67, "C": 166.81005372000556, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.06760602530796868, "f1": 0.6479313036690086, "f1_std": 0.08528233007239008, "bacc": 0.6532258064516129, "bacc_std": 0.08848298895283237} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 68, "C": 0.046415888336127774, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.06711415156044784, "f1": 0.5839188134270101, "f1_std": 0.08380825050837176, "bacc": 0.5870967741935484, "bacc_std": 0.08691814274351051} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 69, "C": 2.782559402207126, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.06843210506892351, "f1": 0.603225806451613, "f1_std": 0.09054793164366101, "bacc": 0.603225806451613, "bacc_std": 0.09053704814256078} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 70, "C": 166.81005372000556, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.0563709984881698, "f1": 0.5340909090909092, "f1_std": 0.08521740122417228, "bacc": 0.535483870967742, "bacc_std": 0.07242671986401253} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 71, "C": 0.3593813663804626, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.05007670499449114, "f1": 0.5512437810945273, "f1_std": 0.08382410477259199, "bacc": 0.5516129032258065, "bacc_std": 0.06752751402861278} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 72, "C": 1291.5496650148827, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.05535093814345963, "f1": 0.5918552036199095, "f1_std": 0.08626927409695621, "bacc": 0.5854838709677419, "bacc_std": 0.07674546568783097} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 73, "C": 0.3593813663804626, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.06198585549925898, "f1": 0.7119437939110069, "f1_std": 0.08021073369702614, "bacc": 0.7193548387096774, "bacc_std": 0.08417772907866301} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 74, "C": 2.782559402207126, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.05760384926658275, "f1": 0.5729166666666666, "f1_std": 0.08495896949926589, "bacc": 0.5693548387096774, "bacc_std": 0.07925242348667937} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 75, "C": 166.81005372000556, "split": "test", "acc": 0.6585365853658537, "acc_std": 0.06444927080146963, "f1": 0.5370967741935484, "f1_std": 0.08283788698898152, "bacc": 0.5370967741935484, "bacc_std": 0.08286810477355994} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 76, "C": 0.3593813663804626, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.06306656823194387, "f1": 0.5547201336675021, "f1_std": 0.08425660364726134, "bacc": 0.5532258064516129, "bacc_std": 0.08049319255605909} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 77, "C": 0.046415888336127774, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.04159519946675767, "f1": 0.6554621848739496, "f1_std": 0.09670328830088414, "bacc": 0.6338709677419355, "bacc_std": 0.07579785064453282} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 78, "C": 2.782559402207126, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.06355142844270979, "f1": 0.6693548387096775, "f1_std": 0.08718701899121467, "bacc": 0.6693548387096775, "bacc_std": 0.08969950273464658} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 79, "C": 1291.5496650148827, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.06744905760499918, "f1": 0.6676492262343405, "f1_std": 0.08019456960110002, "bacc": 0.6870967741935483, "bacc_std": 0.08688150523634586} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 80, "C": 0.005994842503189409, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.048652784059985986, "f1": 0.5512437810945273, "f1_std": 0.0848140684363761, "bacc": 0.5516129032258065, "bacc_std": 0.06759438085063466} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 81, "C": 2.782559402207126, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.05271579823639379, "f1": 0.5512437810945273, "f1_std": 0.09059973601741594, "bacc": 0.5516129032258065, "bacc_std": 0.07320479299172629} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 82, "C": 0.3593813663804626, "split": "test", "acc": 0.6585365853658537, "acc_std": 0.0662038745404239, "f1": 0.5370967741935484, "f1_std": 0.08429389180034207, "bacc": 0.5370967741935484, "bacc_std": 0.08377412374076364} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 83, "C": 21.54434690031882, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.05994373725361969, "f1": 0.6440972222222222, "f1_std": 0.08646285863303275, "bacc": 0.635483870967742, "bacc_std": 0.08239682009967994} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 84, "C": 0.046415888336127774, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.05850183928122379, "f1": 0.5918552036199095, "f1_std": 0.0884847013642466, "bacc": 0.5854838709677419, "bacc_std": 0.07905898455268422} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 85, "C": 2.782559402207126, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.05958883509763119, "f1": 0.7354838709677419, "f1_std": 0.08231586016541544, "bacc": 0.7354838709677419, "bacc_std": 0.08427378601537516} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 86, "C": 21.54434690031882, "split": "test", "acc": 0.6097560975609756, "acc_std": 0.06457173240527131, "f1": 0.47096774193548385, "f1_std": 0.07051463215125399, "bacc": 0.47096774193548385, "bacc_std": 0.07094648149282866} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 87, "C": 0.046415888336127774, "split": "test", "acc": 0.8536585365853658, "acc_std": 0.04039613483610294, "f1": 0.7415966386554622, "f1_std": 0.10037409535566423, "bacc": 0.7, "bacc_std": 0.08281207641401102} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 88, "C": 166.81005372000556, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.06896565630050186, "f1": 0.5839188134270101, "f1_std": 0.08497339474133392, "bacc": 0.5870967741935484, "bacc_std": 0.0892204161831348} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 89, "C": 0.3593813663804626, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.06099543092473591, "f1": 0.7354838709677419, "f1_std": 0.08308134494607201, "bacc": 0.7354838709677419, "bacc_std": 0.08749036819293228} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 90, "C": 0.046415888336127774, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.06409756097560976, "f1": 0.6693548387096775, "f1_std": 0.08758449848837768, "bacc": 0.6693548387096775, "bacc_std": 0.08889360311235901} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 91, "C": 0.046415888336127774, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.05444818088918657, "f1": 0.5340909090909092, "f1_std": 0.08578844622397573, "bacc": 0.535483870967742, "bacc_std": 0.07350144059126076} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 92, "C": 0.3593813663804626, "split": "test", "acc": 0.5853658536585366, "acc_std": 0.06529475565466479, "f1": 0.4177109440267335, "f1_std": 0.06516119376867963, "bacc": 0.42096774193548386, "bacc_std": 0.06555645873594698} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 93, "C": 166.81005372000556, "split": "test", "acc": 0.5365853658536586, "acc_std": 0.07530031091117388, "f1": 0.4533333333333333, "f1_std": 0.07714706157901509, "bacc": 0.4564516129032258, "bacc_std": 0.08801984947831497} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 94, "C": 0.046415888336127774, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.05195694460610538, "f1": 0.4696517412935323, "f1_std": 0.06883330036013881, "bacc": 0.4854838709677419, "bacc_std": 0.057035878224032645} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 95, "C": 166.81005372000556, "split": "test", "acc": 0.6097560975609756, "acc_std": 0.07291158989153644, "f1": 0.5030303030303029, "f1_std": 0.07999044595236218, "bacc": 0.5048387096774194, "bacc_std": 0.08459821789106076} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 96, "C": 21.54434690031882, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.06457173240527131, "f1": 0.7054597701149425, "f1_std": 0.07381484080463055, "bacc": 0.7370967741935484, "bacc_std": 0.08179171308160836} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 97, "C": 166.81005372000556, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.05999595465244254, "f1": 0.7354838709677419, "f1_std": 0.0821993943013019, "bacc": 0.7354838709677419, "bacc_std": 0.08564399725835534} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 98, "C": 166.81005372000556, "split": "test", "acc": 0.6341463414634146, "acc_std": 0.07160397398069106, "f1": 0.5467943994104643, "f1_std": 0.08041768032778196, "bacc": 0.5548387096774194, "bacc_std": 0.08882080453011969} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 99, "C": 0.046415888336127774, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.05098053424690585, "f1": 0.6117424242424243, "f1_std": 0.0881463406365662, "bacc": 0.6016129032258064, "bacc_std": 0.0746472436071672} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 100, "C": 0.3593813663804626, "split": "test", "acc": 0.6341463414634146, "acc_std": 0.06856392129098185, "f1": 0.5199063231850116, "f1_std": 0.08295166076685709, "bacc": 0.5209677419354839, "bacc_std": 0.08592418669083084} +eval results (random splits): + +| model | repr | clf | dataset | split | n_trials | C | C_std | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:--------------|:--------|-----------:|-------:|--------:|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | adni_ad_vs_cn | train | 100 | 190.89 | 1023.2 | 0.96285 | 0.050665 | 0.94157 | 0.082643 | 0.93158 | 0.095556 | +| flat_mae | patch | logistic | adni_ad_vs_cn | test | 100 | 190.89 | 1023.2 | 0.72293 | 0.064718 | 0.60465 | 0.087601 | 0.60542 | 0.084193 | + + +done! total time: 0:04:47 diff --git a/input_space_v3/flat_lr1e-3_3/eval_v2/hcpya_task21__patch__attn/config.yaml b/input_space_v3/flat_lr1e-3_3/eval_v2/hcpya_task21__patch__attn/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..92d2bcb303f7fab80fb2a88952a0563eaae3b370 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_3/eval_v2/hcpya_task21__patch__attn/config.yaml @@ -0,0 +1,96 @@ +output_root: experiments/input_space_v3/output +name_prefix: eval_probe +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_3; eval v2 (hcpya_task21 patch attn) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +dataset_kwargs: {} +classifier_kwargs: + embed_dim: null + dropout: 0.0 + xavier_init: true + norm: true +lr_scale_grid: +- 0.02 +- 0.023 +- 0.028 +- 0.033 +- 0.038 +- 0.045 +- 0.053 +- 0.062 +- 0.074 +- 0.087 +- 0.1 +- 0.12 +- 0.14 +- 0.17 +- 0.2 +- 0.23 +- 0.27 +- 0.32 +- 0.38 +- 0.44 +- 0.52 +- 0.61 +- 0.72 +- 0.85 +- 1 +- 1.2 +- 1.4 +- 1.6 +- 1.9 +- 2.3 +- 2.7 +- 3.1 +- 3.7 +- 4.3 +- 5.1 +- 6 +- 7.1 +- 8.3 +- 9.8 +- 12 +- 14 +- 16 +- 19 +- 22 +- 26 +- 31 +- 36 +- 43 +- 50 +wd_scale_grid: +- 1.0 +num_workers: 8 +prefetch_factor: null +balanced_sampling: false +epochs: 20 +steps_per_epoch: 200 +batch_size: 64 +accum_iter: 2 +lr: 0.0003 +warmup_epochs: 5 +no_decay: false +weight_decay: 0.05 +clip_grad: 1.0 +metrics: +- acc +- f1 +cv_metric: acc +early_stopping: true +amp: true +device: cuda +seed: 4466 +debug: false +wandb: false +wandb_entity: null +wandb_project: fMRI-fm-eval +name: input_space_v3/flat_lr1e-3_3/eval_v2/hcpya_task21__patch__attn +model: flat_mae +representation: patch +classifier: attn +dataset: hcpya_task21 +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/eval_v2/hcpya_task21__patch__attn +remote_dir: null diff --git a/input_space_v3/flat_lr1e-3_3/eval_v2/hcpya_task21__patch__attn/eval_log.json b/input_space_v3/flat_lr1e-3_3/eval_v2/hcpya_task21__patch__attn/eval_log.json new file mode 100644 index 0000000000000000000000000000000000000000..5e3d19c44a9c14643f7f47395a94b175d75ce966 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_3/eval_v2/hcpya_task21__patch__attn/eval_log.json @@ -0,0 +1 @@ +{"eval/epoch": 11, "eval/id_best": 33, "eval/lr_best": 0.00129, "eval/wd_best": 0.05, "eval/train/loss": 0.000191636907402426, "eval/train/acc": 1.0, "eval/train/acc_std": 0.0, "eval/train/f1": 1.0, "eval/train/f1_std": 0.0, "eval/validation/loss": 0.029056383296847343, "eval/validation/acc": 0.9923115079365079, "eval/validation/acc_std": 0.0014241447205239398, "eval/validation/f1": 0.9919416770538232, "eval/validation/f1_std": 0.0016152582959399091, "eval/test/loss": 0.05844989791512489, "eval/test/acc": 0.9873015873015873, "eval/test/acc_std": 0.0015051881282203093, "eval/test/f1": 0.9846697114880368, "eval/test/f1_std": 0.00198985236960189} diff --git a/input_space_v3/flat_lr1e-3_3/eval_v2/hcpya_task21__patch__attn/eval_log_best.json b/input_space_v3/flat_lr1e-3_3/eval_v2/hcpya_task21__patch__attn/eval_log_best.json new file mode 100644 index 0000000000000000000000000000000000000000..a7c096502c021878ccf3ea9f447933170908652b --- /dev/null +++ b/input_space_v3/flat_lr1e-3_3/eval_v2/hcpya_task21__patch__attn/eval_log_best.json @@ -0,0 +1 @@ +{"eval/best/epoch": 11, "eval/best/id_best": 33, "eval/best/lr_best": 0.00129, "eval/best/wd_best": 0.05, "eval/best/train/loss": 0.000191636907402426, "eval/best/train/acc": 1.0, "eval/best/train/acc_std": 0.0, "eval/best/train/f1": 1.0, "eval/best/train/f1_std": 0.0, "eval/best/validation/loss": 0.029056383296847343, "eval/best/validation/acc": 0.9923115079365079, "eval/best/validation/acc_std": 0.0014241447205239398, "eval/best/validation/f1": 0.9919416770538232, "eval/best/validation/f1_std": 0.0016152582959399091, "eval/best/test/loss": 0.05844989791512489, "eval/best/test/acc": 0.9873015873015873, "eval/best/test/acc_std": 0.0015051881282203093, "eval/best/test/f1": 0.9846697114880368, "eval/best/test/f1_std": 0.00198985236960189} diff --git a/input_space_v3/flat_lr1e-3_3/eval_v2/hcpya_task21__patch__attn/eval_log_last.json b/input_space_v3/flat_lr1e-3_3/eval_v2/hcpya_task21__patch__attn/eval_log_last.json new file mode 100644 index 0000000000000000000000000000000000000000..2d213e951acea1e7b3d1d0df78f8631383c029e3 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_3/eval_v2/hcpya_task21__patch__attn/eval_log_last.json @@ -0,0 +1 @@ +{"eval/last/epoch": 19, "eval/last/id_best": 33, "eval/last/lr_best": 0.00129, "eval/last/wd_best": 0.05, "eval/last/train/loss": 0.0001365818316116929, "eval/last/train/acc": 1.0, "eval/last/train/acc_std": 0.0, "eval/last/train/f1": 1.0, "eval/last/train/f1_std": 0.0, "eval/last/validation/loss": 0.028295176103711128, "eval/last/validation/acc": 0.9920634920634921, "eval/last/validation/acc_std": 0.0014199401504237591, "eval/last/validation/f1": 0.9916310630039791, "eval/last/validation/f1_std": 0.0016116754520959474, "eval/last/test/loss": 0.05833357572555542, "eval/last/test/acc": 0.9876984126984127, "eval/last/test/acc_std": 0.001483068706384123, "eval/last/test/f1": 0.9852531013885311, "eval/last/test/f1_std": 0.001936061300775141} diff --git a/input_space_v3/flat_lr1e-3_3/eval_v2/hcpya_task21__patch__attn/eval_table.csv b/input_space_v3/flat_lr1e-3_3/eval_v2/hcpya_task21__patch__attn/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..742acd3b70d59ca1391256c1379f0c09b8d54a83 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_3/eval_v2/hcpya_task21__patch__attn/eval_table.csv @@ -0,0 +1,4 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,patch,attn,hcpya_task21,best,11,0.00129,0.05,33,"[4.3, 1.0]",train,0.000191636907402426,1.0,0.0,1.0,0.0 +flat_mae,patch,attn,hcpya_task21,best,11,0.00129,0.05,33,"[4.3, 1.0]",validation,0.029056383296847343,0.9923115079365079,0.0014241447205239398,0.9919416770538232,0.0016152582959399091 +flat_mae,patch,attn,hcpya_task21,best,11,0.00129,0.05,33,"[4.3, 1.0]",test,0.05844989791512489,0.9873015873015873,0.0015051881282203093,0.9846697114880368,0.00198985236960189 diff --git a/input_space_v3/flat_lr1e-3_3/eval_v2/hcpya_task21__patch__attn/eval_table_best.csv b/input_space_v3/flat_lr1e-3_3/eval_v2/hcpya_task21__patch__attn/eval_table_best.csv new file mode 100644 index 0000000000000000000000000000000000000000..742acd3b70d59ca1391256c1379f0c09b8d54a83 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_3/eval_v2/hcpya_task21__patch__attn/eval_table_best.csv @@ -0,0 +1,4 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,patch,attn,hcpya_task21,best,11,0.00129,0.05,33,"[4.3, 1.0]",train,0.000191636907402426,1.0,0.0,1.0,0.0 +flat_mae,patch,attn,hcpya_task21,best,11,0.00129,0.05,33,"[4.3, 1.0]",validation,0.029056383296847343,0.9923115079365079,0.0014241447205239398,0.9919416770538232,0.0016152582959399091 +flat_mae,patch,attn,hcpya_task21,best,11,0.00129,0.05,33,"[4.3, 1.0]",test,0.05844989791512489,0.9873015873015873,0.0015051881282203093,0.9846697114880368,0.00198985236960189 diff --git a/input_space_v3/flat_lr1e-3_3/eval_v2/hcpya_task21__patch__attn/eval_table_last.csv b/input_space_v3/flat_lr1e-3_3/eval_v2/hcpya_task21__patch__attn/eval_table_last.csv new file mode 100644 index 0000000000000000000000000000000000000000..1452f827914bfc55bde0669310643fad6e7c3194 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_3/eval_v2/hcpya_task21__patch__attn/eval_table_last.csv @@ -0,0 +1,4 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,patch,attn,hcpya_task21,last,19,0.00129,0.05,33,"[4.3, 1.0]",train,0.0001365818316116929,1.0,0.0,1.0,0.0 +flat_mae,patch,attn,hcpya_task21,last,19,0.00129,0.05,33,"[4.3, 1.0]",validation,0.028295176103711128,0.9920634920634921,0.0014199401504237591,0.9916310630039791,0.0016116754520959474 +flat_mae,patch,attn,hcpya_task21,last,19,0.00129,0.05,33,"[4.3, 1.0]",test,0.05833357572555542,0.9876984126984127,0.001483068706384123,0.9852531013885311,0.001936061300775141 diff --git a/input_space_v3/flat_lr1e-3_3/eval_v2/hcpya_task21__patch__attn/log.txt b/input_space_v3/flat_lr1e-3_3/eval_v2/hcpya_task21__patch__attn/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..0d6881605810800af60086d4c3f5fc79609b906f --- /dev/null +++ b/input_space_v3/flat_lr1e-3_3/eval_v2/hcpya_task21__patch__attn/log.txt @@ -0,0 +1,887 @@ +fMRI foundation model probe eval +version: 0.1.dev86+gf97f52698 +sha: bcce2b486277d3a5b520775efd9cdf1a2affce36, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-04-08 20:31:09 +config: +output_root: experiments/input_space_v3/output +name_prefix: eval_probe +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_3; eval v2 (hcpya_task21 patch attn) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +dataset_kwargs: {} +classifier_kwargs: + embed_dim: null + dropout: 0.0 + xavier_init: true + norm: true +lr_scale_grid: +- 0.02 +- 0.023 +- 0.028 +- 0.033 +- 0.038 +- 0.045 +- 0.053 +- 0.062 +- 0.074 +- 0.087 +- 0.1 +- 0.12 +- 0.14 +- 0.17 +- 0.2 +- 0.23 +- 0.27 +- 0.32 +- 0.38 +- 0.44 +- 0.52 +- 0.61 +- 0.72 +- 0.85 +- 1 +- 1.2 +- 1.4 +- 1.6 +- 1.9 +- 2.3 +- 2.7 +- 3.1 +- 3.7 +- 4.3 +- 5.1 +- 6 +- 7.1 +- 8.3 +- 9.8 +- 12 +- 14 +- 16 +- 19 +- 22 +- 26 +- 31 +- 36 +- 43 +- 50 +wd_scale_grid: +- 1.0 +num_workers: 8 +prefetch_factor: null +balanced_sampling: false +epochs: 20 +steps_per_epoch: 200 +batch_size: 64 +accum_iter: 2 +lr: 0.0003 +warmup_epochs: 5 +no_decay: false +weight_decay: 0.05 +clip_grad: 1.0 +metrics: +- acc +- f1 +cv_metric: acc +early_stopping: true +amp: true +device: cuda +seed: 4466 +debug: false +wandb: false +wandb_entity: null +wandb_project: fMRI-fm-eval +name: input_space_v3/flat_lr1e-3_3/eval_v2/hcpya_task21__patch__attn +model: flat_mae +representation: patch +classifier: attn +dataset: hcpya_task21 +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/eval_v2/hcpya_task21__patch__attn +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=True, reg_tokens=0, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: hcpya_task21 (flat) +train (n=18999): +HFDataset( + dataset=Dataset({ + features: ['sub', 'task', 'cond', 'cond_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 18999 +}), + labels=[ 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20], + counts=[ 832 1248 3201 1660 832 832 832 832 832 1248 1247 1243 832 416 + 416 416 416 416 416 416 416] +) + +validation (n=4032): +HFDataset( + dataset=Dataset({ + features: ['sub', 'task', 'cond', 'cond_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 4032 +}), + labels=[ 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20], + counts=[176 264 688 352 176 176 176 176 176 264 264 264 176 88 88 88 88 88 + 88 88 88] +) + +test (n=5040): +HFDataset( + dataset=Dataset({ + features: ['sub', 'task', 'cond', 'cond_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 5040 +}), + labels=[ 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20], + counts=[220 330 860 440 220 220 220 220 220 330 330 330 220 110 110 110 110 110 + 110 110 110] +) + +running backbone on example batch to get embedding dim +embedding feature dim (patch): 768 +initializing sweep of classifier heads +classifiers: +ModuleList( + (0-48): 49 x AttnPoolClassifier( + (kv): Linear(in_features=768, out_features=1536, bias=True) + (linear): Linear(in_features=768, out_features=21, bias=True) + ) +) +classifier params (train): 58.7M (58.7M) +setting up optimizer +total batch size: 128 = 64 bs per gpu x 2 accum +lr: 3.00e-04 +full schedule: epochs = 20 (steps = 4000) (decay = True) +warmup: epochs = 5 (steps = 1000) +start training for 20 epochs +train: [0] [ 0/400] eta: 0:26:12 lr: nan time: 3.9305 data: 3.4188 max mem: 21740 +train: [0] [ 20/400] eta: 0:03:57 lr: 0.000003 loss: 3.0586 (3.0663) grad: 0.2783 (0.2850) time: 0.4590 data: 0.0023 max mem: 22446 +train: [0] [ 40/400] eta: 0:03:13 lr: 0.000006 loss: 3.0267 (3.0282) grad: 0.2787 (0.2830) time: 0.4467 data: 0.0031 max mem: 22446 +train: [0] [ 60/400] eta: 0:02:53 lr: 0.000009 loss: 2.9137 (2.9757) grad: 0.2800 (0.2787) time: 0.4539 data: 0.0034 max mem: 22446 +train: [0] [ 80/400] eta: 0:02:39 lr: 0.000012 loss: 2.8026 (2.9152) grad: 0.2584 (0.2712) time: 0.4682 data: 0.0037 max mem: 22446 +train: [0] [100/400] eta: 0:02:27 lr: 0.000015 loss: 2.6429 (2.8495) grad: 0.2386 (0.2665) time: 0.4633 data: 0.0036 max mem: 22446 +train: [0] [120/400] eta: 0:02:16 lr: 0.000018 loss: 2.5443 (2.7821) grad: 0.2434 (0.2613) time: 0.4626 data: 0.0037 max mem: 22446 +train: [0] [140/400] eta: 0:02:06 lr: 0.000021 loss: 2.3853 (2.7167) grad: 0.2391 (0.2595) time: 0.4691 data: 0.0035 max mem: 22446 +train: [0] [160/400] eta: 0:01:55 lr: 0.000024 loss: 2.2743 (2.6586) grad: 0.2280 (0.2547) time: 0.4611 data: 0.0034 max mem: 22446 +train: [0] [180/400] eta: 0:01:45 lr: 0.000027 loss: 2.1914 (2.5992) grad: 0.2133 (0.2500) time: 0.4645 data: 0.0035 max mem: 22446 +train: [0] [200/400] eta: 0:01:35 lr: 0.000030 loss: 2.1023 (2.5428) grad: 0.2141 (0.2468) time: 0.4600 data: 0.0034 max mem: 22446 +train: [0] [220/400] eta: 0:01:25 lr: 0.000033 loss: 1.9800 (2.4895) grad: 0.2072 (0.2428) time: 0.4576 data: 0.0035 max mem: 22446 +train: [0] [240/400] eta: 0:01:15 lr: 0.000036 loss: 1.8924 (2.4362) grad: 0.2089 (0.2407) time: 0.4542 data: 0.0035 max mem: 22446 +train: [0] [260/400] eta: 0:01:06 lr: 0.000039 loss: 1.8253 (2.3880) grad: 0.2095 (0.2382) time: 0.4526 data: 0.0033 max mem: 22446 +train: [0] [280/400] eta: 0:00:56 lr: 0.000042 loss: 1.7950 (2.3446) grad: 0.1932 (0.2347) time: 0.4606 data: 0.0034 max mem: 22446 +train: [0] [300/400] eta: 0:00:48 lr: 0.000045 loss: 1.7473 (2.3029) grad: 0.1789 (0.2313) time: 0.6374 data: 0.1714 max mem: 22446 +train: [0] [320/400] eta: 0:00:38 lr: 0.000048 loss: 1.6897 (2.2621) grad: 0.1778 (0.2283) time: 0.4516 data: 0.0029 max mem: 22446 +train: [0] [340/400] eta: 0:00:28 lr: 0.000051 loss: 1.6124 (2.2232) grad: 0.1878 (0.2263) time: 0.4541 data: 0.0034 max mem: 22446 +train: [0] [360/400] eta: 0:00:19 lr: 0.000054 loss: 1.5825 (2.1874) grad: 0.1859 (0.2239) time: 0.4621 data: 0.0036 max mem: 22446 +train: [0] [380/400] eta: 0:00:09 lr: 0.000057 loss: 1.5475 (2.1526) grad: 0.1791 (0.2213) time: 0.4708 data: 0.0036 max mem: 22446 +train: [0] [399/400] eta: 0:00:00 lr: 0.000060 loss: 1.5023 (2.1180) grad: 0.1761 (0.2194) time: 0.4707 data: 0.0037 max mem: 22446 +train: [0] Total time: 0:03:11 (0.4780 s / it) +train: [0] Summary: lr: 0.000060 loss: 1.5023 (2.1180) grad: 0.1761 (0.2194) +eval (validation): [0] [ 0/63] eta: 0:03:31 time: 3.3522 data: 3.0753 max mem: 22446 +eval (validation): [0] [20/63] eta: 0:00:21 time: 0.3660 data: 0.0035 max mem: 22446 +eval (validation): [0] [40/63] eta: 0:00:09 time: 0.3308 data: 0.0032 max mem: 22446 +eval (validation): [0] [60/63] eta: 0:00:01 time: 0.3297 data: 0.0031 max mem: 22446 +eval (validation): [0] [62/63] eta: 0:00:00 time: 0.3292 data: 0.0031 max mem: 22446 +eval (validation): [0] Total time: 0:00:24 (0.3943 s / it) +cv: [0] best hparam: (31, 1.0) (045) ('045_lr3.1e+01_wd1.0e+00') loss: 0.049 acc: 0.984 f1: 0.983 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/eval_v2/hcpya_task21__patch__attn/checkpoint-best.pth +train: [1] [ 0/400] eta: 0:22:55 lr: nan time: 3.4387 data: 3.0463 max mem: 22446 +train: [1] [ 20/400] eta: 0:03:52 lr: 0.000063 loss: 1.4416 (1.4547) grad: 0.1699 (0.1775) time: 0.4712 data: 0.0030 max mem: 22446 +train: [1] [ 40/400] eta: 0:03:12 lr: 0.000066 loss: 1.4276 (1.4296) grad: 0.1756 (0.1769) time: 0.4507 data: 0.0028 max mem: 22446 +train: [1] [ 60/400] eta: 0:02:52 lr: 0.000069 loss: 1.3877 (1.4072) grad: 0.1684 (0.1725) time: 0.4562 data: 0.0036 max mem: 22446 +train: [1] [ 80/400] eta: 0:02:39 lr: 0.000072 loss: 1.3416 (1.3892) grad: 0.1585 (0.1695) time: 0.4666 data: 0.0036 max mem: 22446 +train: [1] [100/400] eta: 0:02:27 lr: 0.000075 loss: 1.3233 (1.3756) grad: 0.1597 (0.1689) time: 0.4584 data: 0.0035 max mem: 22446 +train: [1] [120/400] eta: 0:02:15 lr: 0.000078 loss: 1.3038 (1.3579) grad: 0.1581 (0.1678) time: 0.4523 data: 0.0037 max mem: 22446 +train: [1] [140/400] eta: 0:02:04 lr: 0.000081 loss: 1.2507 (1.3425) grad: 0.1553 (0.1662) time: 0.4563 data: 0.0036 max mem: 22446 +train: [1] [160/400] eta: 0:01:54 lr: 0.000084 loss: 1.2338 (1.3263) grad: 0.1480 (0.1646) time: 0.4515 data: 0.0035 max mem: 22446 +train: [1] [180/400] eta: 0:01:44 lr: 0.000087 loss: 1.2136 (1.3119) grad: 0.1535 (0.1640) time: 0.4507 data: 0.0036 max mem: 22446 +train: [1] [200/400] eta: 0:01:34 lr: 0.000090 loss: 1.1773 (1.2976) grad: 0.1515 (0.1628) time: 0.4536 data: 0.0035 max mem: 22446 +train: [1] [220/400] eta: 0:01:24 lr: 0.000093 loss: 1.1432 (1.2823) grad: 0.1522 (0.1628) time: 0.4555 data: 0.0035 max mem: 22446 +train: [1] [240/400] eta: 0:01:14 lr: 0.000096 loss: 1.1208 (1.2683) grad: 0.1523 (0.1618) time: 0.4534 data: 0.0035 max mem: 22446 +train: [1] [260/400] eta: 0:01:05 lr: 0.000099 loss: 1.1056 (1.2559) grad: 0.1481 (0.1607) time: 0.4501 data: 0.0035 max mem: 22446 +train: [1] [280/400] eta: 0:00:55 lr: 0.000102 loss: 1.0838 (1.2428) grad: 0.1441 (0.1602) time: 0.4405 data: 0.0034 max mem: 22446 +train: [1] [300/400] eta: 0:00:47 lr: 0.000105 loss: 1.0542 (1.2303) grad: 0.1395 (0.1587) time: 0.6187 data: 0.1736 max mem: 22446 +train: [1] [320/400] eta: 0:00:37 lr: 0.000108 loss: 1.0502 (1.2181) grad: 0.1394 (0.1576) time: 0.4596 data: 0.0035 max mem: 22446 +train: [1] [340/400] eta: 0:00:28 lr: 0.000111 loss: 1.0131 (1.2054) grad: 0.1355 (0.1563) time: 0.4448 data: 0.0035 max mem: 22446 +train: [1] [360/400] eta: 0:00:18 lr: 0.000114 loss: 1.0197 (1.1957) grad: 0.1345 (0.1552) time: 0.4563 data: 0.0035 max mem: 22446 +train: [1] [380/400] eta: 0:00:09 lr: 0.000117 loss: 1.0057 (1.1852) grad: 0.1422 (0.1547) time: 0.4629 data: 0.0036 max mem: 22446 +train: [1] [399/400] eta: 0:00:00 lr: 0.000120 loss: 0.9795 (1.1753) grad: 0.1436 (0.1540) time: 0.4570 data: 0.0035 max mem: 22446 +train: [1] Total time: 0:03:08 (0.4710 s / it) +train: [1] Summary: lr: 0.000120 loss: 0.9795 (1.1753) grad: 0.1436 (0.1540) +eval (validation): [1] [ 0/63] eta: 0:03:26 time: 3.2823 data: 3.0436 max mem: 22446 +eval (validation): [1] [20/63] eta: 0:00:20 time: 0.3407 data: 0.0033 max mem: 22446 +eval (validation): [1] [40/63] eta: 0:00:09 time: 0.3337 data: 0.0034 max mem: 22446 +eval (validation): [1] [60/63] eta: 0:00:01 time: 0.3320 data: 0.0032 max mem: 22446 +eval (validation): [1] [62/63] eta: 0:00:00 time: 0.3330 data: 0.0033 max mem: 22446 +eval (validation): [1] Total time: 0:00:24 (0.3870 s / it) +cv: [1] best hparam: (9.8, 1.0) (038) ('038_lr9.8e+00_wd1.0e+00') loss: 0.036 acc: 0.987 f1: 0.985 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/eval_v2/hcpya_task21__patch__attn/checkpoint-best.pth +train: [2] [ 0/400] eta: 0:23:33 lr: nan time: 3.5344 data: 3.1394 max mem: 22446 +train: [2] [ 20/400] eta: 0:03:59 lr: 0.000123 loss: 0.9270 (0.9365) grad: 0.1548 (0.1660) time: 0.4853 data: 0.0030 max mem: 22446 +train: [2] [ 40/400] eta: 0:03:17 lr: 0.000126 loss: 0.9573 (0.9537) grad: 0.1538 (0.1661) time: 0.4633 data: 0.0036 max mem: 22446 +train: [2] [ 60/400] eta: 0:02:56 lr: 0.000129 loss: 0.9333 (0.9385) grad: 0.1537 (0.1673) time: 0.4588 data: 0.0035 max mem: 22446 +train: [2] [ 80/400] eta: 0:02:41 lr: 0.000132 loss: 0.9158 (0.9339) grad: 0.1545 (0.1659) time: 0.4655 data: 0.0035 max mem: 22446 +train: [2] [100/400] eta: 0:02:29 lr: 0.000135 loss: 0.9100 (0.9284) grad: 0.1545 (0.1669) time: 0.4661 data: 0.0035 max mem: 22446 +train: [2] [120/400] eta: 0:02:17 lr: 0.000138 loss: 0.8905 (0.9247) grad: 0.1706 (0.1708) time: 0.4574 data: 0.0035 max mem: 22446 +train: [2] [140/400] eta: 0:02:06 lr: 0.000141 loss: 0.8755 (0.9185) grad: 0.1743 (0.1776) time: 0.4530 data: 0.0035 max mem: 22446 +train: [2] [160/400] eta: 0:01:55 lr: 0.000144 loss: 0.8712 (0.9169) grad: 0.1775 (0.1836) time: 0.4461 data: 0.0035 max mem: 22446 +train: [2] [180/400] eta: 0:01:44 lr: 0.000147 loss: 0.8488 (0.9103) grad: 0.1784 (0.1841) time: 0.4468 data: 0.0035 max mem: 22446 +train: [2] [200/400] eta: 0:01:34 lr: 0.000150 loss: 0.8224 (0.9023) grad: 0.1657 (0.1830) time: 0.4520 data: 0.0034 max mem: 22446 +train: [2] [220/400] eta: 0:01:25 lr: 0.000153 loss: 0.8224 (0.8997) grad: 0.1775 (0.1829) time: 0.4507 data: 0.0036 max mem: 22446 +train: [2] [240/400] eta: 0:01:15 lr: 0.000156 loss: 0.8564 (0.8930) grad: 0.1775 (0.1818) time: 0.4462 data: 0.0035 max mem: 22446 +train: [2] [260/400] eta: 0:01:05 lr: 0.000159 loss: 0.7991 (0.8891) grad: 0.1776 (0.1848) time: 0.4436 data: 0.0035 max mem: 22446 +train: [2] [280/400] eta: 0:00:56 lr: 0.000162 loss: 0.8287 (0.8859) grad: 0.1955 (0.1881) time: 0.4462 data: 0.0035 max mem: 22446 +train: [2] [300/400] eta: 0:00:47 lr: 0.000165 loss: 0.8096 (0.8794) grad: 0.1955 (0.1906) time: 0.6179 data: 0.1782 max mem: 22446 +train: [2] [320/400] eta: 0:00:38 lr: 0.000168 loss: 0.7971 (0.8777) grad: 0.2097 (0.1929) time: 0.4677 data: 0.0033 max mem: 22446 +train: [2] [340/400] eta: 0:00:28 lr: 0.000171 loss: 0.8280 (0.8776) grad: 0.2003 (0.1944) time: 0.4615 data: 0.0034 max mem: 22446 +train: [2] [360/400] eta: 0:00:18 lr: 0.000174 loss: 0.8598 (0.8790) grad: 0.2058 (0.1970) time: 0.4605 data: 0.0034 max mem: 22446 +train: [2] [380/400] eta: 0:00:09 lr: 0.000177 loss: 0.8086 (0.8735) grad: 0.2050 (0.1972) time: 0.4707 data: 0.0035 max mem: 22446 +train: [2] [399/400] eta: 0:00:00 lr: 0.000180 loss: 0.7045 (0.8643) grad: 0.2013 (0.1978) time: 0.4582 data: 0.0035 max mem: 22446 +train: [2] Total time: 0:03:09 (0.4739 s / it) +train: [2] Summary: lr: 0.000180 loss: 0.7045 (0.8643) grad: 0.2013 (0.1978) +eval (validation): [2] [ 0/63] eta: 0:03:30 time: 3.3445 data: 3.0646 max mem: 22446 +eval (validation): [2] [20/63] eta: 0:00:22 time: 0.3761 data: 0.0042 max mem: 22446 +eval (validation): [2] [40/63] eta: 0:00:10 time: 0.3551 data: 0.0031 max mem: 22446 +eval (validation): [2] [60/63] eta: 0:00:01 time: 0.3405 data: 0.0033 max mem: 22446 +eval (validation): [2] [62/63] eta: 0:00:00 time: 0.3405 data: 0.0034 max mem: 22446 +eval (validation): [2] Total time: 0:00:25 (0.4101 s / it) +cv: [2] best hparam: (6, 1.0) (035) ('035_lr6.0e+00_wd1.0e+00') loss: 0.034 acc: 0.988 f1: 0.986 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/eval_v2/hcpya_task21__patch__attn/checkpoint-best.pth +train: [3] [ 0/400] eta: 0:24:04 lr: nan time: 3.6111 data: 3.2655 max mem: 22446 +train: [3] [ 20/400] eta: 0:03:58 lr: 0.000183 loss: 0.6427 (0.7067) grad: 0.1799 (0.1974) time: 0.4781 data: 0.0031 max mem: 22446 +train: [3] [ 40/400] eta: 0:03:14 lr: 0.000186 loss: 0.6975 (0.7333) grad: 0.2135 (0.2140) time: 0.4516 data: 0.0034 max mem: 22446 +train: [3] [ 60/400] eta: 0:02:54 lr: 0.000189 loss: 0.7585 (0.7520) grad: 0.2405 (0.2211) time: 0.4563 data: 0.0034 max mem: 22446 +train: [3] [ 80/400] eta: 0:02:40 lr: 0.000192 loss: 0.7639 (0.7526) grad: 0.2218 (0.2185) time: 0.4707 data: 0.0035 max mem: 22446 +train: [3] [100/400] eta: 0:02:27 lr: 0.000195 loss: 0.7045 (0.7443) grad: 0.2259 (0.2212) time: 0.4470 data: 0.0036 max mem: 22446 +train: [3] [120/400] eta: 0:02:15 lr: 0.000198 loss: 0.7166 (0.7492) grad: 0.2259 (0.2222) time: 0.4521 data: 0.0037 max mem: 22446 +train: [3] [140/400] eta: 0:02:04 lr: 0.000201 loss: 0.7339 (0.7567) grad: 0.2181 (0.2274) time: 0.4465 data: 0.0036 max mem: 22446 +train: [3] [160/400] eta: 0:01:54 lr: 0.000204 loss: 0.7129 (0.7522) grad: 0.2447 (0.2286) time: 0.4479 data: 0.0036 max mem: 22446 +train: [3] [180/400] eta: 0:01:44 lr: 0.000207 loss: 0.7078 (0.7521) grad: 0.2447 (0.2297) time: 0.4575 data: 0.0035 max mem: 22446 +train: [3] [200/400] eta: 0:01:34 lr: 0.000210 loss: 0.7138 (0.7520) grad: 0.2267 (0.2303) time: 0.4622 data: 0.0036 max mem: 22446 +train: [3] [220/400] eta: 0:01:24 lr: 0.000213 loss: 0.7048 (0.7459) grad: 0.2389 (0.2352) time: 0.4523 data: 0.0036 max mem: 22446 +train: [3] [240/400] eta: 0:01:14 lr: 0.000216 loss: 0.7519 (0.7654) grad: 0.2630 (0.2452) time: 0.4455 data: 0.0037 max mem: 22446 +train: [3] [260/400] eta: 0:01:05 lr: 0.000219 loss: 0.7666 (0.7606) grad: 0.2522 (0.2474) time: 0.4584 data: 0.0036 max mem: 22446 +train: [3] [280/400] eta: 0:00:55 lr: 0.000222 loss: 0.6589 (0.7592) grad: 0.2722 (0.2526) time: 0.4390 data: 0.0037 max mem: 22446 +train: [3] [300/400] eta: 0:00:47 lr: 0.000225 loss: 0.7410 (0.7593) grad: 0.2941 (0.2557) time: 0.6395 data: 0.1767 max mem: 22446 +train: [3] [320/400] eta: 0:00:38 lr: 0.000228 loss: 0.7323 (0.7583) grad: 0.2835 (0.2591) time: 0.4424 data: 0.0034 max mem: 22446 +train: [3] [340/400] eta: 0:00:28 lr: 0.000231 loss: 0.6078 (0.7498) grad: 0.2639 (0.2613) time: 0.4395 data: 0.0035 max mem: 22446 +train: [3] [360/400] eta: 0:00:18 lr: 0.000234 loss: 0.5719 (0.7422) grad: 0.2702 (0.2648) time: 0.4555 data: 0.0035 max mem: 22446 +train: [3] [380/400] eta: 0:00:09 lr: 0.000237 loss: 0.6257 (0.7433) grad: 0.2777 (0.2661) time: 0.4557 data: 0.0035 max mem: 22446 +train: [3] [399/400] eta: 0:00:00 lr: 0.000240 loss: 0.6961 (0.7407) grad: 0.2769 (0.2671) time: 0.4514 data: 0.0035 max mem: 22446 +train: [3] Total time: 0:03:08 (0.4707 s / it) +train: [3] Summary: lr: 0.000240 loss: 0.6961 (0.7407) grad: 0.2769 (0.2671) +eval (validation): [3] [ 0/63] eta: 0:03:27 time: 3.2886 data: 3.0602 max mem: 22446 +eval (validation): [3] [20/63] eta: 0:00:20 time: 0.3359 data: 0.0034 max mem: 22446 +eval (validation): [3] [40/63] eta: 0:00:09 time: 0.3492 data: 0.0031 max mem: 22446 +eval (validation): [3] [60/63] eta: 0:00:01 time: 0.3420 data: 0.0033 max mem: 22446 +eval (validation): [3] [62/63] eta: 0:00:00 time: 0.3423 data: 0.0033 max mem: 22446 +eval (validation): [3] Total time: 0:00:24 (0.3928 s / it) +cv: [3] best hparam: (1.2, 1.0) (025) ('025_lr1.2e+00_wd1.0e+00') loss: 0.041 acc: 0.985 f1: 0.983 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [4] [ 0/400] eta: 0:23:52 lr: nan time: 3.5805 data: 3.1903 max mem: 22446 +train: [4] [ 20/400] eta: 0:03:58 lr: 0.000243 loss: 0.6829 (0.7310) grad: 0.3054 (0.3752) time: 0.4814 data: 0.0030 max mem: 22446 +train: [4] [ 40/400] eta: 0:03:16 lr: 0.000246 loss: 0.7324 (0.7630) grad: 0.2919 (0.3531) time: 0.4584 data: 0.0036 max mem: 22446 +train: [4] [ 60/400] eta: 0:02:55 lr: 0.000249 loss: 0.6979 (0.7239) grad: 0.3489 (0.3665) time: 0.4551 data: 0.0035 max mem: 22446 +train: [4] [ 80/400] eta: 0:02:42 lr: 0.000252 loss: 0.5797 (0.6947) grad: 0.3547 (0.3634) time: 0.4771 data: 0.0035 max mem: 22446 +train: [4] [100/400] eta: 0:02:28 lr: 0.000255 loss: 0.5644 (0.7046) grad: 0.3342 (0.3925) time: 0.4507 data: 0.0036 max mem: 22446 +train: [4] [120/400] eta: 0:02:16 lr: 0.000258 loss: 0.6820 (0.7185) grad: 0.3370 (0.3854) time: 0.4433 data: 0.0038 max mem: 22446 +train: [4] [140/400] eta: 0:02:05 lr: 0.000261 loss: 0.6387 (0.7108) grad: 0.3388 (0.3808) time: 0.4482 data: 0.0036 max mem: 22446 +train: [4] [160/400] eta: 0:01:54 lr: 0.000264 loss: 0.7846 (0.7385) grad: 0.3880 (0.3922) time: 0.4490 data: 0.0036 max mem: 22446 +train: [4] [180/400] eta: 0:01:44 lr: 0.000267 loss: 0.9298 (0.7471) grad: 0.4048 (0.3917) time: 0.4509 data: 0.0036 max mem: 22446 +train: [4] [200/400] eta: 0:01:34 lr: 0.000270 loss: 0.8057 (0.7558) grad: 0.3832 (0.3999) time: 0.4511 data: 0.0035 max mem: 22446 +train: [4] [220/400] eta: 0:01:24 lr: 0.000273 loss: 0.9181 (0.7697) grad: 0.4351 (0.4273) time: 0.4456 data: 0.0035 max mem: 22446 +train: [4] [240/400] eta: 0:01:14 lr: 0.000276 loss: 0.8263 (0.7759) grad: 0.5004 (0.4331) time: 0.4470 data: 0.0036 max mem: 22446 +train: [4] [260/400] eta: 0:01:05 lr: 0.000279 loss: 0.8263 (0.8048) grad: 0.4785 (0.4393) time: 0.4500 data: 0.0034 max mem: 22446 +train: [4] [280/400] eta: 0:00:55 lr: 0.000282 loss: 0.9543 (0.8155) grad: 0.5267 (0.4486) time: 0.4444 data: 0.0036 max mem: 22446 +train: [4] [300/400] eta: 0:00:47 lr: 0.000285 loss: 0.8123 (0.8302) grad: 0.5191 (0.4521) time: 0.6131 data: 0.1808 max mem: 22446 +train: [4] [320/400] eta: 0:00:37 lr: 0.000288 loss: 0.6020 (0.8121) grad: 0.4141 (0.4480) time: 0.4491 data: 0.0034 max mem: 22446 +train: [4] [340/400] eta: 0:00:28 lr: 0.000291 loss: 0.5799 (0.7993) grad: 0.3975 (0.4473) time: 0.4494 data: 0.0036 max mem: 22446 +train: [4] [360/400] eta: 0:00:18 lr: 0.000294 loss: 0.5994 (0.7974) grad: 0.4261 (0.4451) time: 0.4586 data: 0.0036 max mem: 22446 +train: [4] [380/400] eta: 0:00:09 lr: 0.000297 loss: 0.7975 (0.8067) grad: 0.4391 (0.4453) time: 0.4651 data: 0.0037 max mem: 22446 +train: [4] [399/400] eta: 0:00:00 lr: 0.000300 loss: 0.7787 (0.8073) grad: 0.4548 (0.4462) time: 0.4580 data: 0.0035 max mem: 22446 +train: [4] Total time: 0:03:08 (0.4705 s / it) +train: [4] Summary: lr: 0.000300 loss: 0.7787 (0.8073) grad: 0.4548 (0.4462) +eval (validation): [4] [ 0/63] eta: 0:03:25 time: 3.2562 data: 3.0179 max mem: 22446 +eval (validation): [4] [20/63] eta: 0:00:22 time: 0.3864 data: 0.0381 max mem: 22446 +eval (validation): [4] [40/63] eta: 0:00:10 time: 0.3480 data: 0.0030 max mem: 22446 +eval (validation): [4] [60/63] eta: 0:00:01 time: 0.3300 data: 0.0032 max mem: 22446 +eval (validation): [4] [62/63] eta: 0:00:00 time: 0.3304 data: 0.0032 max mem: 22446 +eval (validation): [4] Total time: 0:00:25 (0.4054 s / it) +cv: [4] best hparam: (5.1, 1.0) (034) ('034_lr5.1e+00_wd1.0e+00') loss: 0.034 acc: 0.990 f1: 0.989 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/eval_v2/hcpya_task21__patch__attn/checkpoint-best.pth +train: [5] [ 0/400] eta: 0:23:29 lr: nan time: 3.5229 data: 3.1150 max mem: 22446 +train: [5] [ 20/400] eta: 0:03:53 lr: 0.000300 loss: 0.4645 (0.5865) grad: 0.3562 (0.4105) time: 0.4685 data: 0.0033 max mem: 22446 +train: [5] [ 40/400] eta: 0:03:09 lr: 0.000300 loss: 0.5626 (0.6834) grad: 0.3426 (0.3759) time: 0.4369 data: 0.0031 max mem: 22446 +train: [5] [ 60/400] eta: 0:02:51 lr: 0.000300 loss: 0.8390 (0.7351) grad: 0.3426 (0.3884) time: 0.4546 data: 0.0036 max mem: 22446 +train: [5] [ 80/400] eta: 0:02:38 lr: 0.000300 loss: 0.6186 (0.6996) grad: 0.3911 (0.3947) time: 0.4643 data: 0.0035 max mem: 22446 +train: [5] [100/400] eta: 0:02:25 lr: 0.000300 loss: 0.7141 (0.7486) grad: 0.4082 (0.4415) time: 0.4524 data: 0.0035 max mem: 22446 +train: [5] [120/400] eta: 0:02:14 lr: 0.000300 loss: 1.0658 (0.7942) grad: 0.4703 (0.4441) time: 0.4425 data: 0.0036 max mem: 22446 +train: [5] [140/400] eta: 0:02:03 lr: 0.000300 loss: 0.8916 (0.8015) grad: 0.4703 (0.4499) time: 0.4438 data: 0.0035 max mem: 22446 +train: [5] [160/400] eta: 0:01:53 lr: 0.000299 loss: 0.7549 (0.8019) grad: 0.4522 (0.4527) time: 0.4540 data: 0.0036 max mem: 22446 +train: [5] [180/400] eta: 0:01:43 lr: 0.000299 loss: 0.6149 (0.7840) grad: 0.4198 (0.4535) time: 0.4559 data: 0.0036 max mem: 22446 +train: [5] [200/400] eta: 0:01:33 lr: 0.000299 loss: 0.5767 (0.7928) grad: 0.3903 (0.4503) time: 0.4548 data: 0.0036 max mem: 22446 +train: [5] [220/400] eta: 0:01:24 lr: 0.000299 loss: 0.6211 (0.7994) grad: 0.3903 (0.4479) time: 0.4541 data: 0.0035 max mem: 22446 +train: [5] [240/400] eta: 0:01:14 lr: 0.000299 loss: 0.6777 (0.7880) grad: 0.4146 (0.4493) time: 0.4481 data: 0.0035 max mem: 22446 +train: [5] [260/400] eta: 0:01:05 lr: 0.000299 loss: 0.6777 (0.8116) grad: 0.4803 (0.4611) time: 0.4534 data: 0.0035 max mem: 22446 +train: [5] [280/400] eta: 0:00:55 lr: 0.000298 loss: 1.0139 (0.8253) grad: 0.5037 (0.4642) time: 0.4476 data: 0.0035 max mem: 22446 +train: [5] [300/400] eta: 0:00:47 lr: 0.000298 loss: 0.9120 (0.8157) grad: 0.4712 (0.4701) time: 0.6208 data: 0.1769 max mem: 22446 +train: [5] [320/400] eta: 0:00:37 lr: 0.000298 loss: 0.5865 (0.8028) grad: 0.4619 (0.4658) time: 0.4550 data: 0.0036 max mem: 22446 +train: [5] [340/400] eta: 0:00:28 lr: 0.000298 loss: 0.4935 (0.8015) grad: 0.4066 (0.4622) time: 0.4416 data: 0.0029 max mem: 22446 +train: [5] [360/400] eta: 0:00:18 lr: 0.000297 loss: 0.4935 (0.7956) grad: 0.4080 (0.4585) time: 0.4644 data: 0.0036 max mem: 22446 +train: [5] [380/400] eta: 0:00:09 lr: 0.000297 loss: 0.5998 (0.7951) grad: 0.4147 (0.4551) time: 0.4520 data: 0.0037 max mem: 22446 +train: [5] [399/400] eta: 0:00:00 lr: 0.000297 loss: 0.6160 (0.7827) grad: 0.3152 (0.4497) time: 0.4536 data: 0.0036 max mem: 22446 +train: [5] Total time: 0:03:07 (0.4689 s / it) +train: [5] Summary: lr: 0.000297 loss: 0.6160 (0.7827) grad: 0.3152 (0.4497) +eval (validation): [5] [ 0/63] eta: 0:04:15 time: 4.0631 data: 3.8155 max mem: 22446 +eval (validation): [5] [20/63] eta: 0:00:22 time: 0.3378 data: 0.0033 max mem: 22446 +eval (validation): [5] [40/63] eta: 0:00:09 time: 0.3483 data: 0.0034 max mem: 22446 +eval (validation): [5] [60/63] eta: 0:00:01 time: 0.3321 data: 0.0032 max mem: 22446 +eval (validation): [5] [62/63] eta: 0:00:00 time: 0.3368 data: 0.0032 max mem: 22446 +eval (validation): [5] Total time: 0:00:25 (0.4045 s / it) +cv: [5] best hparam: (1.6, 1.0) (027) ('027_lr1.6e+00_wd1.0e+00') loss: 0.031 acc: 0.989 f1: 0.986 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [6] [ 0/400] eta: 0:23:28 lr: nan time: 3.5201 data: 3.1047 max mem: 22446 +train: [6] [ 20/400] eta: 0:03:59 lr: 0.000296 loss: 0.5261 (0.5389) grad: 0.4284 (0.4241) time: 0.4869 data: 0.0041 max mem: 22446 +train: [6] [ 40/400] eta: 0:03:15 lr: 0.000296 loss: 0.4505 (0.5030) grad: 0.3885 (0.3722) time: 0.4523 data: 0.0035 max mem: 22446 +train: [6] [ 60/400] eta: 0:02:54 lr: 0.000296 loss: 0.4372 (0.5610) grad: 0.3667 (0.3856) time: 0.4529 data: 0.0034 max mem: 22446 +train: [6] [ 80/400] eta: 0:02:41 lr: 0.000295 loss: 0.5384 (0.5712) grad: 0.3667 (0.3833) time: 0.4716 data: 0.0034 max mem: 22446 +train: [6] [100/400] eta: 0:02:27 lr: 0.000295 loss: 0.5150 (0.5632) grad: 0.3630 (0.3816) time: 0.4484 data: 0.0035 max mem: 22446 +train: [6] [120/400] eta: 0:02:15 lr: 0.000295 loss: 0.4619 (0.5687) grad: 0.3630 (0.3771) time: 0.4482 data: 0.0038 max mem: 22446 +train: [6] [140/400] eta: 0:02:04 lr: 0.000294 loss: 0.4507 (0.5702) grad: 0.3555 (0.3736) time: 0.4500 data: 0.0035 max mem: 22446 +train: [6] [160/400] eta: 0:01:54 lr: 0.000294 loss: 0.4309 (0.5524) grad: 0.3319 (0.3679) time: 0.4614 data: 0.0035 max mem: 22446 +train: [6] [180/400] eta: 0:01:44 lr: 0.000293 loss: 0.4822 (0.5765) grad: 0.3319 (0.3681) time: 0.4528 data: 0.0034 max mem: 22446 +train: [6] [200/400] eta: 0:01:34 lr: 0.000293 loss: 0.6372 (0.5985) grad: 0.3365 (0.3690) time: 0.4538 data: 0.0033 max mem: 22446 +train: [6] [220/400] eta: 0:01:24 lr: 0.000292 loss: 0.4755 (0.5934) grad: 0.3225 (0.3640) time: 0.4460 data: 0.0034 max mem: 22446 +train: [6] [240/400] eta: 0:01:14 lr: 0.000292 loss: 0.4417 (0.5806) grad: 0.3225 (0.3613) time: 0.4461 data: 0.0035 max mem: 22446 +train: [6] [260/400] eta: 0:01:05 lr: 0.000291 loss: 0.4030 (0.5716) grad: 0.3477 (0.3644) time: 0.4526 data: 0.0034 max mem: 22446 +train: [6] [280/400] eta: 0:00:55 lr: 0.000291 loss: 0.5127 (0.5858) grad: 0.3559 (0.3672) time: 0.4457 data: 0.0035 max mem: 22446 +train: [6] [300/400] eta: 0:00:47 lr: 0.000290 loss: 0.5311 (0.5795) grad: 0.3559 (0.3665) time: 0.6426 data: 0.1760 max mem: 22446 +train: [6] [320/400] eta: 0:00:38 lr: 0.000290 loss: 0.4511 (0.5741) grad: 0.3777 (0.3678) time: 0.4400 data: 0.0033 max mem: 22446 +train: [6] [340/400] eta: 0:00:28 lr: 0.000289 loss: 0.4511 (0.5687) grad: 0.3385 (0.3653) time: 0.4454 data: 0.0037 max mem: 22446 +train: [6] [360/400] eta: 0:00:18 lr: 0.000288 loss: 0.4164 (0.5565) grad: 0.3283 (0.3728) time: 0.4645 data: 0.0035 max mem: 22446 +train: [6] [380/400] eta: 0:00:09 lr: 0.000288 loss: 0.3017 (0.5489) grad: 0.2937 (0.3692) time: 0.4637 data: 0.0038 max mem: 22446 +train: [6] [399/400] eta: 0:00:00 lr: 0.000287 loss: 0.2788 (0.5375) grad: 0.2615 (0.3663) time: 0.4540 data: 0.0036 max mem: 22446 +train: [6] Total time: 0:03:08 (0.4719 s / it) +train: [6] Summary: lr: 0.000287 loss: 0.2788 (0.5375) grad: 0.2615 (0.3663) +eval (validation): [6] [ 0/63] eta: 0:03:31 time: 3.3538 data: 3.0755 max mem: 22446 +eval (validation): [6] [20/63] eta: 0:00:20 time: 0.3446 data: 0.0039 max mem: 22446 +eval (validation): [6] [40/63] eta: 0:00:09 time: 0.3459 data: 0.0029 max mem: 22446 +eval (validation): [6] [60/63] eta: 0:00:01 time: 0.3389 data: 0.0032 max mem: 22446 +eval (validation): [6] [62/63] eta: 0:00:00 time: 0.3385 data: 0.0032 max mem: 22446 +eval (validation): [6] Total time: 0:00:24 (0.3946 s / it) +cv: [6] best hparam: (3.7, 1.0) (032) ('032_lr3.7e+00_wd1.0e+00') loss: 0.032 acc: 0.991 f1: 0.991 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/eval_v2/hcpya_task21__patch__attn/checkpoint-best.pth +train: [7] [ 0/400] eta: 0:23:18 lr: nan time: 3.4951 data: 3.1051 max mem: 22446 +train: [7] [ 20/400] eta: 0:03:57 lr: 0.000286 loss: 0.3262 (0.4627) grad: 0.2555 (0.3001) time: 0.4818 data: 0.0030 max mem: 22446 +train: [7] [ 40/400] eta: 0:03:13 lr: 0.000286 loss: 0.3266 (0.3948) grad: 0.2377 (0.2672) time: 0.4440 data: 0.0033 max mem: 22446 +train: [7] [ 60/400] eta: 0:02:55 lr: 0.000285 loss: 0.3831 (0.4300) grad: 0.2638 (0.2785) time: 0.4724 data: 0.0036 max mem: 22446 +train: [7] [ 80/400] eta: 0:02:40 lr: 0.000284 loss: 0.4436 (0.4334) grad: 0.2872 (0.2818) time: 0.4605 data: 0.0037 max mem: 22446 +train: [7] [100/400] eta: 0:02:27 lr: 0.000284 loss: 0.3387 (0.4174) grad: 0.2784 (0.2872) time: 0.4572 data: 0.0035 max mem: 22446 +train: [7] [120/400] eta: 0:02:15 lr: 0.000283 loss: 0.3145 (0.4089) grad: 0.3062 (0.2900) time: 0.4417 data: 0.0035 max mem: 22446 +train: [7] [140/400] eta: 0:02:04 lr: 0.000282 loss: 0.3346 (0.4145) grad: 0.2802 (0.2925) time: 0.4521 data: 0.0036 max mem: 22446 +train: [7] [160/400] eta: 0:01:54 lr: 0.000282 loss: 0.3346 (0.4036) grad: 0.2692 (0.2918) time: 0.4523 data: 0.0035 max mem: 22446 +train: [7] [180/400] eta: 0:01:44 lr: 0.000281 loss: 0.2418 (0.3963) grad: 0.2692 (0.2950) time: 0.4516 data: 0.0035 max mem: 22446 +train: [7] [200/400] eta: 0:01:34 lr: 0.000280 loss: 0.2699 (0.3943) grad: 0.2902 (0.2968) time: 0.4514 data: 0.0035 max mem: 22446 +train: [7] [220/400] eta: 0:01:24 lr: 0.000279 loss: 0.2676 (0.3931) grad: 0.2902 (0.2962) time: 0.4491 data: 0.0034 max mem: 22446 +train: [7] [240/400] eta: 0:01:14 lr: 0.000278 loss: 0.2918 (0.3945) grad: 0.2797 (0.2987) time: 0.4462 data: 0.0035 max mem: 22446 +train: [7] [260/400] eta: 0:01:05 lr: 0.000278 loss: 0.2918 (0.3887) grad: 0.2632 (0.2968) time: 0.4511 data: 0.0035 max mem: 22446 +train: [7] [280/400] eta: 0:00:55 lr: 0.000277 loss: 0.2836 (0.3941) grad: 0.2548 (0.2966) time: 0.4417 data: 0.0036 max mem: 22446 +train: [7] [300/400] eta: 0:00:47 lr: 0.000276 loss: 0.4220 (0.3997) grad: 0.2902 (0.2971) time: 0.6314 data: 0.1790 max mem: 22446 +train: [7] [320/400] eta: 0:00:37 lr: 0.000275 loss: 0.4028 (0.4053) grad: 0.2974 (0.2978) time: 0.4446 data: 0.0031 max mem: 22446 +train: [7] [340/400] eta: 0:00:28 lr: 0.000274 loss: 0.2989 (0.3970) grad: 0.2700 (0.2942) time: 0.4367 data: 0.0035 max mem: 22446 +train: [7] [360/400] eta: 0:00:18 lr: 0.000273 loss: 0.2523 (0.3909) grad: 0.2242 (0.2920) time: 0.4672 data: 0.0035 max mem: 22446 +train: [7] [380/400] eta: 0:00:09 lr: 0.000272 loss: 0.2672 (0.3832) grad: 0.2006 (0.2879) time: 0.4542 data: 0.0035 max mem: 22446 +train: [7] [399/400] eta: 0:00:00 lr: 0.000271 loss: 0.2620 (0.3783) grad: 0.2150 (0.2868) time: 0.4469 data: 0.0037 max mem: 22446 +train: [7] Total time: 0:03:07 (0.4696 s / it) +train: [7] Summary: lr: 0.000271 loss: 0.2620 (0.3783) grad: 0.2150 (0.2868) +eval (validation): [7] [ 0/63] eta: 0:03:31 time: 3.3528 data: 3.0789 max mem: 22446 +eval (validation): [7] [20/63] eta: 0:00:21 time: 0.3589 data: 0.0032 max mem: 22446 +eval (validation): [7] [40/63] eta: 0:00:09 time: 0.3448 data: 0.0038 max mem: 22446 +eval (validation): [7] [60/63] eta: 0:00:01 time: 0.3292 data: 0.0032 max mem: 22446 +eval (validation): [7] [62/63] eta: 0:00:00 time: 0.3284 data: 0.0032 max mem: 22446 +eval (validation): [7] Total time: 0:00:25 (0.3974 s / it) +cv: [7] best hparam: (3.7, 1.0) (032) ('032_lr3.7e+00_wd1.0e+00') loss: 0.030 acc: 0.992 f1: 0.990 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/eval_v2/hcpya_task21__patch__attn/checkpoint-best.pth +train: [8] [ 0/400] eta: 0:29:41 lr: nan time: 4.4547 data: 4.0414 max mem: 22446 +train: [8] [ 20/400] eta: 0:04:03 lr: 0.000270 loss: 0.1651 (0.1957) grad: 0.1920 (0.1944) time: 0.4505 data: 0.0025 max mem: 22446 +train: [8] [ 40/400] eta: 0:03:16 lr: 0.000270 loss: 0.2210 (0.2410) grad: 0.2178 (0.2120) time: 0.4429 data: 0.0033 max mem: 22446 +train: [8] [ 60/400] eta: 0:02:56 lr: 0.000269 loss: 0.2310 (0.2327) grad: 0.2073 (0.2072) time: 0.4714 data: 0.0035 max mem: 22446 +train: [8] [ 80/400] eta: 0:02:41 lr: 0.000268 loss: 0.2117 (0.2396) grad: 0.2073 (0.2273) time: 0.4554 data: 0.0034 max mem: 22446 +train: [8] [100/400] eta: 0:02:28 lr: 0.000267 loss: 0.2327 (0.2495) grad: 0.2499 (0.2329) time: 0.4495 data: 0.0035 max mem: 22446 +train: [8] [120/400] eta: 0:02:16 lr: 0.000266 loss: 0.2988 (0.2615) grad: 0.2499 (0.2437) time: 0.4534 data: 0.0034 max mem: 22446 +train: [8] [140/400] eta: 0:02:05 lr: 0.000265 loss: 0.2988 (0.2609) grad: 0.2272 (0.2450) time: 0.4465 data: 0.0035 max mem: 22446 +train: [8] [160/400] eta: 0:01:54 lr: 0.000264 loss: 0.2376 (0.2614) grad: 0.2259 (0.2423) time: 0.4498 data: 0.0036 max mem: 22446 +train: [8] [180/400] eta: 0:01:44 lr: 0.000263 loss: 0.2734 (0.2673) grad: 0.2172 (0.2430) time: 0.4511 data: 0.0035 max mem: 22446 +train: [8] [200/400] eta: 0:01:34 lr: 0.000262 loss: 0.2758 (0.2697) grad: 0.2204 (0.2428) time: 0.4514 data: 0.0037 max mem: 22446 +train: [8] [220/400] eta: 0:01:24 lr: 0.000260 loss: 0.2321 (0.2710) grad: 0.2169 (0.2420) time: 0.4550 data: 0.0035 max mem: 22446 +train: [8] [240/400] eta: 0:01:14 lr: 0.000259 loss: 0.2120 (0.2751) grad: 0.2226 (0.2400) time: 0.4462 data: 0.0036 max mem: 22446 +train: [8] [260/400] eta: 0:01:05 lr: 0.000258 loss: 0.1988 (0.2746) grad: 0.2226 (0.2388) time: 0.4488 data: 0.0036 max mem: 22446 +train: [8] [280/400] eta: 0:00:55 lr: 0.000257 loss: 0.2208 (0.2781) grad: 0.2252 (0.2388) time: 0.4480 data: 0.0035 max mem: 22446 +train: [8] [300/400] eta: 0:00:47 lr: 0.000256 loss: 0.2787 (0.2846) grad: 0.2726 (0.2444) time: 0.6284 data: 0.1753 max mem: 22446 +train: [8] [320/400] eta: 0:00:37 lr: 0.000255 loss: 0.2494 (0.2811) grad: 0.2740 (0.2411) time: 0.4496 data: 0.0033 max mem: 22446 +train: [8] [340/400] eta: 0:00:28 lr: 0.000254 loss: 0.1957 (0.2785) grad: 0.1976 (0.2409) time: 0.4395 data: 0.0036 max mem: 22446 +train: [8] [360/400] eta: 0:00:18 lr: 0.000253 loss: 0.1679 (0.2724) grad: 0.1621 (0.2379) time: 0.4832 data: 0.0037 max mem: 22446 +train: [8] [380/400] eta: 0:00:09 lr: 0.000252 loss: 0.1459 (0.2681) grad: 0.1560 (0.2341) time: 0.4558 data: 0.0036 max mem: 22446 +train: [8] [399/400] eta: 0:00:00 lr: 0.000250 loss: 0.1727 (0.2649) grad: 0.1628 (0.2310) time: 0.4525 data: 0.0036 max mem: 22446 +train: [8] Total time: 0:03:08 (0.4718 s / it) +train: [8] Summary: lr: 0.000250 loss: 0.1727 (0.2649) grad: 0.1628 (0.2310) +eval (validation): [8] [ 0/63] eta: 0:03:29 time: 3.3230 data: 3.0468 max mem: 22446 +eval (validation): [8] [20/63] eta: 0:00:20 time: 0.3433 data: 0.0044 max mem: 22446 +eval (validation): [8] [40/63] eta: 0:00:09 time: 0.3599 data: 0.0036 max mem: 22446 +eval (validation): [8] [60/63] eta: 0:00:01 time: 0.3352 data: 0.0032 max mem: 22446 +eval (validation): [8] [62/63] eta: 0:00:00 time: 0.3353 data: 0.0033 max mem: 22446 +eval (validation): [8] Total time: 0:00:25 (0.3990 s / it) +cv: [8] best hparam: (3.1, 1.0) (031) ('031_lr3.1e+00_wd1.0e+00') loss: 0.029 acc: 0.991 f1: 0.990 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [9] [ 0/400] eta: 0:23:29 lr: nan time: 3.5235 data: 3.1909 max mem: 22446 +train: [9] [ 20/400] eta: 0:03:39 lr: 0.000249 loss: 0.2173 (0.2476) grad: 0.1672 (0.1700) time: 0.4306 data: 0.0032 max mem: 22446 +train: [9] [ 40/400] eta: 0:03:02 lr: 0.000248 loss: 0.2050 (0.2289) grad: 0.1719 (0.1810) time: 0.4351 data: 0.0027 max mem: 22446 +train: [9] [ 60/400] eta: 0:02:48 lr: 0.000247 loss: 0.1778 (0.2161) grad: 0.1698 (0.1699) time: 0.4733 data: 0.0036 max mem: 22446 +train: [9] [ 80/400] eta: 0:02:35 lr: 0.000246 loss: 0.1778 (0.2112) grad: 0.1395 (0.1687) time: 0.4528 data: 0.0036 max mem: 22446 +train: [9] [100/400] eta: 0:02:22 lr: 0.000244 loss: 0.1547 (0.2025) grad: 0.1600 (0.1676) time: 0.4389 data: 0.0035 max mem: 22446 +train: [9] [120/400] eta: 0:02:11 lr: 0.000243 loss: 0.1774 (0.2054) grad: 0.1696 (0.1684) time: 0.4405 data: 0.0037 max mem: 22446 +train: [9] [140/400] eta: 0:02:01 lr: 0.000242 loss: 0.1764 (0.2017) grad: 0.1655 (0.1661) time: 0.4445 data: 0.0035 max mem: 22446 +train: [9] [160/400] eta: 0:01:51 lr: 0.000241 loss: 0.1474 (0.1949) grad: 0.1566 (0.1665) time: 0.4376 data: 0.0036 max mem: 22446 +train: [9] [180/400] eta: 0:01:41 lr: 0.000240 loss: 0.1470 (0.1904) grad: 0.1566 (0.1667) time: 0.4463 data: 0.0036 max mem: 22446 +train: [9] [200/400] eta: 0:01:31 lr: 0.000238 loss: 0.1626 (0.1926) grad: 0.1588 (0.1686) time: 0.4346 data: 0.0036 max mem: 22446 +train: [9] [220/400] eta: 0:01:22 lr: 0.000237 loss: 0.1701 (0.1930) grad: 0.1652 (0.1695) time: 0.4453 data: 0.0036 max mem: 22446 +train: [9] [240/400] eta: 0:01:13 lr: 0.000236 loss: 0.1611 (0.1901) grad: 0.1584 (0.1681) time: 0.4505 data: 0.0037 max mem: 22446 +train: [9] [260/400] eta: 0:01:03 lr: 0.000234 loss: 0.1415 (0.1896) grad: 0.1568 (0.1694) time: 0.4433 data: 0.0036 max mem: 22446 +train: [9] [280/400] eta: 0:00:54 lr: 0.000233 loss: 0.1643 (0.1912) grad: 0.1623 (0.1698) time: 0.4427 data: 0.0035 max mem: 22446 +train: [9] [300/400] eta: 0:00:46 lr: 0.000232 loss: 0.1738 (0.1914) grad: 0.1575 (0.1699) time: 0.6078 data: 0.1786 max mem: 22446 +train: [9] [320/400] eta: 0:00:37 lr: 0.000230 loss: 0.1288 (0.1876) grad: 0.1575 (0.1686) time: 0.4416 data: 0.0031 max mem: 22446 +train: [9] [340/400] eta: 0:00:27 lr: 0.000229 loss: 0.1306 (0.1889) grad: 0.1628 (0.1693) time: 0.4337 data: 0.0034 max mem: 22446 +train: [9] [360/400] eta: 0:00:18 lr: 0.000228 loss: 0.1425 (0.1873) grad: 0.1628 (0.1685) time: 0.4793 data: 0.0037 max mem: 22446 +train: [9] [380/400] eta: 0:00:09 lr: 0.000226 loss: 0.1259 (0.1847) grad: 0.1488 (0.1673) time: 0.4458 data: 0.0036 max mem: 22446 +train: [9] [399/400] eta: 0:00:00 lr: 0.000225 loss: 0.1293 (0.1829) grad: 0.1487 (0.1665) time: 0.4417 data: 0.0036 max mem: 22446 +train: [9] Total time: 0:03:04 (0.4613 s / it) +train: [9] Summary: lr: 0.000225 loss: 0.1293 (0.1829) grad: 0.1487 (0.1665) +eval (validation): [9] [ 0/63] eta: 0:03:28 time: 3.3156 data: 3.0785 max mem: 22446 +eval (validation): [9] [20/63] eta: 0:00:20 time: 0.3452 data: 0.0174 max mem: 22446 +eval (validation): [9] [40/63] eta: 0:00:09 time: 0.3360 data: 0.0030 max mem: 22446 +eval (validation): [9] [60/63] eta: 0:00:01 time: 0.3166 data: 0.0030 max mem: 22446 +eval (validation): [9] [62/63] eta: 0:00:00 time: 0.3155 data: 0.0028 max mem: 22446 +eval (validation): [9] Total time: 0:00:24 (0.3835 s / it) +cv: [9] best hparam: (2.7, 1.0) (030) ('030_lr2.7e+00_wd1.0e+00') loss: 0.028 acc: 0.991 f1: 0.990 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [10] [ 0/400] eta: 0:23:45 lr: nan time: 3.5625 data: 3.2130 max mem: 22446 +train: [10] [ 20/400] eta: 0:03:49 lr: 0.000224 loss: 0.1394 (0.1657) grad: 0.1339 (0.1211) time: 0.4564 data: 0.0032 max mem: 22446 +train: [10] [ 40/400] eta: 0:03:07 lr: 0.000222 loss: 0.1232 (0.1488) grad: 0.0870 (0.1181) time: 0.4330 data: 0.0033 max mem: 22446 +train: [10] [ 60/400] eta: 0:02:50 lr: 0.000221 loss: 0.1224 (0.1495) grad: 0.1068 (0.1244) time: 0.4584 data: 0.0035 max mem: 22446 +train: [10] [ 80/400] eta: 0:02:36 lr: 0.000220 loss: 0.1422 (0.1551) grad: 0.1495 (0.1414) time: 0.4523 data: 0.0035 max mem: 22446 +train: [10] [100/400] eta: 0:02:23 lr: 0.000218 loss: 0.1344 (0.1515) grad: 0.1366 (0.1370) time: 0.4337 data: 0.0034 max mem: 22446 +train: [10] [120/400] eta: 0:02:12 lr: 0.000217 loss: 0.1271 (0.1491) grad: 0.1239 (0.1397) time: 0.4443 data: 0.0034 max mem: 22446 +train: [10] [140/400] eta: 0:02:01 lr: 0.000215 loss: 0.1421 (0.1530) grad: 0.1400 (0.1407) time: 0.4412 data: 0.0035 max mem: 22446 +train: [10] [160/400] eta: 0:01:51 lr: 0.000214 loss: 0.1271 (0.1500) grad: 0.1452 (0.1404) time: 0.4431 data: 0.0034 max mem: 22446 +train: [10] [180/400] eta: 0:01:41 lr: 0.000213 loss: 0.1270 (0.1492) grad: 0.1402 (0.1397) time: 0.4427 data: 0.0036 max mem: 22446 +train: [10] [200/400] eta: 0:01:31 lr: 0.000211 loss: 0.1173 (0.1478) grad: 0.1402 (0.1402) time: 0.4381 data: 0.0036 max mem: 22446 +train: [10] [220/400] eta: 0:01:22 lr: 0.000210 loss: 0.1173 (0.1460) grad: 0.1114 (0.1372) time: 0.4436 data: 0.0035 max mem: 22446 +train: [10] [240/400] eta: 0:01:13 lr: 0.000208 loss: 0.1237 (0.1448) grad: 0.1138 (0.1372) time: 0.4500 data: 0.0035 max mem: 22446 +train: [10] [260/400] eta: 0:01:04 lr: 0.000207 loss: 0.1215 (0.1441) grad: 0.1539 (0.1409) time: 0.4511 data: 0.0036 max mem: 22446 +train: [10] [280/400] eta: 0:00:54 lr: 0.000205 loss: 0.1257 (0.1435) grad: 0.1420 (0.1388) time: 0.4547 data: 0.0036 max mem: 22446 +train: [10] [300/400] eta: 0:00:46 lr: 0.000204 loss: 0.1158 (0.1433) grad: 0.1060 (0.1375) time: 0.6020 data: 0.1771 max mem: 22446 +train: [10] [320/400] eta: 0:00:37 lr: 0.000202 loss: 0.1025 (0.1417) grad: 0.0979 (0.1354) time: 0.4528 data: 0.0032 max mem: 22446 +train: [10] [340/400] eta: 0:00:27 lr: 0.000201 loss: 0.1012 (0.1398) grad: 0.0939 (0.1336) time: 0.4369 data: 0.0034 max mem: 22446 +train: [10] [360/400] eta: 0:00:18 lr: 0.000199 loss: 0.1012 (0.1399) grad: 0.0772 (0.1311) time: 0.4627 data: 0.0036 max mem: 22446 +train: [10] [380/400] eta: 0:00:09 lr: 0.000198 loss: 0.0995 (0.1390) grad: 0.1000 (0.1292) time: 0.4499 data: 0.0035 max mem: 22446 +train: [10] [399/400] eta: 0:00:00 lr: 0.000196 loss: 0.1136 (0.1383) grad: 0.1000 (0.1275) time: 0.4466 data: 0.0035 max mem: 22446 +train: [10] Total time: 0:03:05 (0.4628 s / it) +train: [10] Summary: lr: 0.000196 loss: 0.1136 (0.1383) grad: 0.1000 (0.1275) +eval (validation): [10] [ 0/63] eta: 0:03:32 time: 3.3682 data: 3.0903 max mem: 22446 +eval (validation): [10] [20/63] eta: 0:00:20 time: 0.3382 data: 0.0037 max mem: 22446 +eval (validation): [10] [40/63] eta: 0:00:09 time: 0.3487 data: 0.0031 max mem: 22446 +eval (validation): [10] [60/63] eta: 0:00:01 time: 0.3179 data: 0.0032 max mem: 22446 +eval (validation): [10] [62/63] eta: 0:00:00 time: 0.3166 data: 0.0031 max mem: 22446 +eval (validation): [10] Total time: 0:00:24 (0.3868 s / it) +cv: [10] best hparam: (4.3, 1.0) (033) ('033_lr4.3e+00_wd1.0e+00') loss: 0.028 acc: 0.992 f1: 0.992 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/eval_v2/hcpya_task21__patch__attn/checkpoint-best.pth +train: [11] [ 0/400] eta: 0:23:13 lr: nan time: 3.4845 data: 3.1308 max mem: 22446 +train: [11] [ 20/400] eta: 0:03:50 lr: 0.000195 loss: 0.1024 (0.1404) grad: 0.0906 (0.1026) time: 0.4623 data: 0.0200 max mem: 22446 +train: [11] [ 40/400] eta: 0:03:06 lr: 0.000193 loss: 0.1024 (0.1323) grad: 0.0893 (0.1012) time: 0.4249 data: 0.0028 max mem: 22446 +train: [11] [ 60/400] eta: 0:02:52 lr: 0.000192 loss: 0.1166 (0.1339) grad: 0.0914 (0.1069) time: 0.4881 data: 0.0036 max mem: 22446 +train: [11] [ 80/400] eta: 0:02:38 lr: 0.000190 loss: 0.1110 (0.1270) grad: 0.0891 (0.1011) time: 0.4592 data: 0.0038 max mem: 22446 +train: [11] [100/400] eta: 0:02:25 lr: 0.000189 loss: 0.1003 (0.1227) grad: 0.0812 (0.1003) time: 0.4473 data: 0.0037 max mem: 22446 +train: [11] [120/400] eta: 0:02:14 lr: 0.000187 loss: 0.0983 (0.1192) grad: 0.0995 (0.0997) time: 0.4588 data: 0.0035 max mem: 22446 +train: [11] [140/400] eta: 0:02:03 lr: 0.000186 loss: 0.1039 (0.1194) grad: 0.0995 (0.1001) time: 0.4390 data: 0.0035 max mem: 22446 +train: [11] [160/400] eta: 0:01:53 lr: 0.000184 loss: 0.1179 (0.1198) grad: 0.0914 (0.1000) time: 0.4451 data: 0.0035 max mem: 22446 +train: [11] [180/400] eta: 0:01:43 lr: 0.000183 loss: 0.1074 (0.1190) grad: 0.0914 (0.1012) time: 0.4464 data: 0.0035 max mem: 22446 +train: [11] [200/400] eta: 0:01:33 lr: 0.000181 loss: 0.0918 (0.1170) grad: 0.0926 (0.1014) time: 0.4364 data: 0.0035 max mem: 22446 +train: [11] [220/400] eta: 0:01:23 lr: 0.000180 loss: 0.0906 (0.1154) grad: 0.0924 (0.1002) time: 0.4430 data: 0.0036 max mem: 22446 +train: [11] [240/400] eta: 0:01:13 lr: 0.000178 loss: 0.0991 (0.1153) grad: 0.0855 (0.0996) time: 0.4398 data: 0.0037 max mem: 22446 +train: [11] [260/400] eta: 0:01:04 lr: 0.000177 loss: 0.1122 (0.1158) grad: 0.0836 (0.0994) time: 0.4367 data: 0.0037 max mem: 22446 +train: [11] [280/400] eta: 0:00:55 lr: 0.000175 loss: 0.1020 (0.1153) grad: 0.0864 (0.0989) time: 0.4408 data: 0.0037 max mem: 22446 +train: [11] [300/400] eta: 0:00:46 lr: 0.000174 loss: 0.1012 (0.1146) grad: 0.0885 (0.0980) time: 0.6002 data: 0.1724 max mem: 22446 +train: [11] [320/400] eta: 0:00:37 lr: 0.000172 loss: 0.1012 (0.1141) grad: 0.0842 (0.0972) time: 0.4387 data: 0.0032 max mem: 22446 +train: [11] [340/400] eta: 0:00:27 lr: 0.000170 loss: 0.0968 (0.1130) grad: 0.0760 (0.0952) time: 0.4379 data: 0.0035 max mem: 22446 +train: [11] [360/400] eta: 0:00:18 lr: 0.000169 loss: 0.0925 (0.1120) grad: 0.0595 (0.0937) time: 0.4678 data: 0.0037 max mem: 22446 +train: [11] [380/400] eta: 0:00:09 lr: 0.000167 loss: 0.0919 (0.1109) grad: 0.0500 (0.0917) time: 0.4441 data: 0.0037 max mem: 22446 +train: [11] [399/400] eta: 0:00:00 lr: 0.000166 loss: 0.0982 (0.1106) grad: 0.0709 (0.0910) time: 0.4455 data: 0.0036 max mem: 22446 +train: [11] Total time: 0:03:05 (0.4629 s / it) +train: [11] Summary: lr: 0.000166 loss: 0.0982 (0.1106) grad: 0.0709 (0.0910) +eval (validation): [11] [ 0/63] eta: 0:03:25 time: 3.2566 data: 3.0140 max mem: 22446 +eval (validation): [11] [20/63] eta: 0:00:21 time: 0.3743 data: 0.0047 max mem: 22446 +eval (validation): [11] [40/63] eta: 0:00:09 time: 0.3285 data: 0.0031 max mem: 22446 +eval (validation): [11] [60/63] eta: 0:00:01 time: 0.3214 data: 0.0032 max mem: 22446 +eval (validation): [11] [62/63] eta: 0:00:00 time: 0.3231 data: 0.0032 max mem: 22446 +eval (validation): [11] Total time: 0:00:24 (0.3923 s / it) +cv: [11] best hparam: (4.3, 1.0) (033) ('033_lr4.3e+00_wd1.0e+00') loss: 0.029 acc: 0.992 f1: 0.992 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/eval_v2/hcpya_task21__patch__attn/checkpoint-best.pth +train: [12] [ 0/400] eta: 0:23:34 lr: nan time: 3.5363 data: 3.1923 max mem: 22446 +train: [12] [ 20/400] eta: 0:03:49 lr: 0.000164 loss: 0.0979 (0.0977) grad: 0.0657 (0.0746) time: 0.4583 data: 0.0043 max mem: 22446 +train: [12] [ 40/400] eta: 0:03:07 lr: 0.000163 loss: 0.0905 (0.0956) grad: 0.0665 (0.0698) time: 0.4305 data: 0.0030 max mem: 22446 +train: [12] [ 60/400] eta: 0:02:51 lr: 0.000161 loss: 0.0814 (0.0928) grad: 0.0503 (0.0646) time: 0.4709 data: 0.0036 max mem: 22446 +train: [12] [ 80/400] eta: 0:02:36 lr: 0.000160 loss: 0.0814 (0.0922) grad: 0.0438 (0.0684) time: 0.4477 data: 0.0035 max mem: 22446 +train: [12] [100/400] eta: 0:02:24 lr: 0.000158 loss: 0.0933 (0.0929) grad: 0.0528 (0.0686) time: 0.4415 data: 0.0036 max mem: 22446 +train: [12] [120/400] eta: 0:02:12 lr: 0.000156 loss: 0.0981 (0.0960) grad: 0.0701 (0.0701) time: 0.4460 data: 0.0034 max mem: 22446 +train: [12] [140/400] eta: 0:02:02 lr: 0.000155 loss: 0.0934 (0.0956) grad: 0.0686 (0.0687) time: 0.4452 data: 0.0037 max mem: 22446 +train: [12] [160/400] eta: 0:01:52 lr: 0.000153 loss: 0.0849 (0.0954) grad: 0.0518 (0.0677) time: 0.4486 data: 0.0035 max mem: 22446 +train: [12] [180/400] eta: 0:01:42 lr: 0.000152 loss: 0.0828 (0.0949) grad: 0.0518 (0.0672) time: 0.4415 data: 0.0035 max mem: 22446 +train: [12] [200/400] eta: 0:01:32 lr: 0.000150 loss: 0.0808 (0.0943) grad: 0.0576 (0.0672) time: 0.4484 data: 0.0034 max mem: 22446 +train: [12] [220/400] eta: 0:01:23 lr: 0.000149 loss: 0.0808 (0.0952) grad: 0.0576 (0.0669) time: 0.4420 data: 0.0035 max mem: 22446 +train: [12] [240/400] eta: 0:01:13 lr: 0.000147 loss: 0.0958 (0.0960) grad: 0.0613 (0.0673) time: 0.4473 data: 0.0035 max mem: 22446 +train: [12] [260/400] eta: 0:01:04 lr: 0.000145 loss: 0.0937 (0.0955) grad: 0.0566 (0.0663) time: 0.4559 data: 0.0035 max mem: 22446 +train: [12] [280/400] eta: 0:00:54 lr: 0.000144 loss: 0.0853 (0.0947) grad: 0.0468 (0.0658) time: 0.4369 data: 0.0035 max mem: 22446 +train: [12] [300/400] eta: 0:00:46 lr: 0.000142 loss: 0.0881 (0.0949) grad: 0.0571 (0.0660) time: 0.6099 data: 0.1795 max mem: 22446 +train: [12] [320/400] eta: 0:00:37 lr: 0.000141 loss: 0.0915 (0.0946) grad: 0.0488 (0.0653) time: 0.4458 data: 0.0034 max mem: 22446 +train: [12] [340/400] eta: 0:00:27 lr: 0.000139 loss: 0.0881 (0.0945) grad: 0.0492 (0.0653) time: 0.4282 data: 0.0034 max mem: 22446 +train: [12] [360/400] eta: 0:00:18 lr: 0.000138 loss: 0.0876 (0.0942) grad: 0.0622 (0.0652) time: 0.4744 data: 0.0036 max mem: 22446 +train: [12] [380/400] eta: 0:00:09 lr: 0.000136 loss: 0.0843 (0.0944) grad: 0.0659 (0.0651) time: 0.4414 data: 0.0036 max mem: 22446 +train: [12] [399/400] eta: 0:00:00 lr: 0.000134 loss: 0.0826 (0.0939) grad: 0.0659 (0.0647) time: 0.4408 data: 0.0036 max mem: 22446 +train: [12] Total time: 0:03:05 (0.4631 s / it) +train: [12] Summary: lr: 0.000134 loss: 0.0826 (0.0939) grad: 0.0659 (0.0647) +eval (validation): [12] [ 0/63] eta: 0:03:27 time: 3.2888 data: 3.0557 max mem: 22446 +eval (validation): [12] [20/63] eta: 0:00:22 time: 0.3765 data: 0.0287 max mem: 22446 +eval (validation): [12] [40/63] eta: 0:00:09 time: 0.3266 data: 0.0028 max mem: 22446 +eval (validation): [12] [60/63] eta: 0:00:01 time: 0.3173 data: 0.0032 max mem: 22446 +eval (validation): [12] [62/63] eta: 0:00:00 time: 0.3222 data: 0.0032 max mem: 22446 +eval (validation): [12] Total time: 0:00:24 (0.3914 s / it) +cv: [12] best hparam: (4.3, 1.0) (033) ('033_lr4.3e+00_wd1.0e+00') loss: 0.028 acc: 0.992 f1: 0.991 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [13] [ 0/400] eta: 0:24:02 lr: nan time: 3.6056 data: 3.1997 max mem: 22446 +train: [13] [ 20/400] eta: 0:03:50 lr: 0.000133 loss: 0.0853 (0.0872) grad: 0.0375 (0.0418) time: 0.4554 data: 0.0038 max mem: 22446 +train: [13] [ 40/400] eta: 0:03:09 lr: 0.000131 loss: 0.0749 (0.0818) grad: 0.0447 (0.0486) time: 0.4449 data: 0.0035 max mem: 22446 +train: [13] [ 60/400] eta: 0:02:51 lr: 0.000130 loss: 0.0749 (0.0817) grad: 0.0523 (0.0504) time: 0.4574 data: 0.0036 max mem: 22446 +train: [13] [ 80/400] eta: 0:02:36 lr: 0.000128 loss: 0.0781 (0.0825) grad: 0.0475 (0.0522) time: 0.4486 data: 0.0037 max mem: 22446 +train: [13] [100/400] eta: 0:02:24 lr: 0.000127 loss: 0.0795 (0.0837) grad: 0.0448 (0.0528) time: 0.4482 data: 0.0036 max mem: 22446 +train: [13] [120/400] eta: 0:02:13 lr: 0.000125 loss: 0.0790 (0.0839) grad: 0.0479 (0.0533) time: 0.4443 data: 0.0036 max mem: 22446 +train: [13] [140/400] eta: 0:02:02 lr: 0.000124 loss: 0.0786 (0.0845) grad: 0.0479 (0.0533) time: 0.4387 data: 0.0035 max mem: 22446 +train: [13] [160/400] eta: 0:01:51 lr: 0.000122 loss: 0.0775 (0.0843) grad: 0.0482 (0.0533) time: 0.4372 data: 0.0036 max mem: 22446 +train: [13] [180/400] eta: 0:01:42 lr: 0.000120 loss: 0.0907 (0.0850) grad: 0.0463 (0.0529) time: 0.4420 data: 0.0035 max mem: 22446 +train: [13] [200/400] eta: 0:01:32 lr: 0.000119 loss: 0.0907 (0.0853) grad: 0.0463 (0.0537) time: 0.4408 data: 0.0035 max mem: 22446 +train: [13] [220/400] eta: 0:01:22 lr: 0.000117 loss: 0.0782 (0.0852) grad: 0.0570 (0.0544) time: 0.4415 data: 0.0035 max mem: 22446 +train: [13] [240/400] eta: 0:01:13 lr: 0.000116 loss: 0.0813 (0.0853) grad: 0.0522 (0.0542) time: 0.4565 data: 0.0036 max mem: 22446 +train: [13] [260/400] eta: 0:01:04 lr: 0.000114 loss: 0.0759 (0.0851) grad: 0.0438 (0.0537) time: 0.4496 data: 0.0034 max mem: 22446 +train: [13] [280/400] eta: 0:00:54 lr: 0.000113 loss: 0.0747 (0.0845) grad: 0.0454 (0.0535) time: 0.4452 data: 0.0035 max mem: 22446 +train: [13] [300/400] eta: 0:00:46 lr: 0.000111 loss: 0.0759 (0.0843) grad: 0.0499 (0.0531) time: 0.6316 data: 0.1801 max mem: 22446 +train: [13] [320/400] eta: 0:00:37 lr: 0.000110 loss: 0.0794 (0.0842) grad: 0.0441 (0.0525) time: 0.4427 data: 0.0032 max mem: 22446 +train: [13] [340/400] eta: 0:00:27 lr: 0.000108 loss: 0.0794 (0.0838) grad: 0.0389 (0.0519) time: 0.4282 data: 0.0034 max mem: 22446 +train: [13] [360/400] eta: 0:00:18 lr: 0.000107 loss: 0.0692 (0.0834) grad: 0.0416 (0.0517) time: 0.4696 data: 0.0035 max mem: 22446 +train: [13] [380/400] eta: 0:00:09 lr: 0.000105 loss: 0.0763 (0.0835) grad: 0.0446 (0.0516) time: 0.4441 data: 0.0035 max mem: 22446 +train: [13] [399/400] eta: 0:00:00 lr: 0.000104 loss: 0.0828 (0.0836) grad: 0.0433 (0.0514) time: 0.4411 data: 0.0034 max mem: 22446 +train: [13] Total time: 0:03:05 (0.4636 s / it) +train: [13] Summary: lr: 0.000104 loss: 0.0828 (0.0836) grad: 0.0433 (0.0514) +eval (validation): [13] [ 0/63] eta: 0:03:32 time: 3.3742 data: 3.0924 max mem: 22446 +eval (validation): [13] [20/63] eta: 0:00:21 time: 0.3542 data: 0.0031 max mem: 22446 +eval (validation): [13] [40/63] eta: 0:00:09 time: 0.3318 data: 0.0033 max mem: 22446 +eval (validation): [13] [60/63] eta: 0:00:01 time: 0.3253 data: 0.0031 max mem: 22446 +eval (validation): [13] [62/63] eta: 0:00:00 time: 0.3179 data: 0.0031 max mem: 22446 +eval (validation): [13] Total time: 0:00:24 (0.3898 s / it) +cv: [13] best hparam: (4.3, 1.0) (033) ('033_lr4.3e+00_wd1.0e+00') loss: 0.028 acc: 0.992 f1: 0.992 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [14] [ 0/400] eta: 0:24:10 lr: nan time: 3.6252 data: 3.2192 max mem: 22446 +train: [14] [ 20/400] eta: 0:03:48 lr: 0.000102 loss: 0.0750 (0.0814) grad: 0.0417 (0.0412) time: 0.4500 data: 0.0029 max mem: 22446 +train: [14] [ 40/400] eta: 0:03:06 lr: 0.000101 loss: 0.0781 (0.0802) grad: 0.0435 (0.0470) time: 0.4284 data: 0.0028 max mem: 22446 +train: [14] [ 60/400] eta: 0:02:49 lr: 0.000099 loss: 0.0765 (0.0791) grad: 0.0442 (0.0468) time: 0.4627 data: 0.0036 max mem: 22446 +train: [14] [ 80/400] eta: 0:02:35 lr: 0.000098 loss: 0.0698 (0.0792) grad: 0.0455 (0.0490) time: 0.4449 data: 0.0035 max mem: 22446 +train: [14] [100/400] eta: 0:02:23 lr: 0.000096 loss: 0.0697 (0.0784) grad: 0.0455 (0.0488) time: 0.4418 data: 0.0036 max mem: 22446 +train: [14] [120/400] eta: 0:02:12 lr: 0.000095 loss: 0.0803 (0.0807) grad: 0.0416 (0.0485) time: 0.4444 data: 0.0037 max mem: 22446 +train: [14] [140/400] eta: 0:02:01 lr: 0.000093 loss: 0.0865 (0.0822) grad: 0.0471 (0.0493) time: 0.4391 data: 0.0036 max mem: 22446 +train: [14] [160/400] eta: 0:01:51 lr: 0.000092 loss: 0.0716 (0.0815) grad: 0.0437 (0.0489) time: 0.4478 data: 0.0035 max mem: 22446 +train: [14] [180/400] eta: 0:01:41 lr: 0.000090 loss: 0.0672 (0.0804) grad: 0.0404 (0.0482) time: 0.4459 data: 0.0035 max mem: 22446 +train: [14] [200/400] eta: 0:01:32 lr: 0.000089 loss: 0.0702 (0.0804) grad: 0.0418 (0.0477) time: 0.4561 data: 0.0035 max mem: 22446 +train: [14] [220/400] eta: 0:01:22 lr: 0.000088 loss: 0.0719 (0.0798) grad: 0.0436 (0.0475) time: 0.4426 data: 0.0036 max mem: 22446 +train: [14] [240/400] eta: 0:01:13 lr: 0.000086 loss: 0.0731 (0.0794) grad: 0.0438 (0.0471) time: 0.4413 data: 0.0035 max mem: 22446 +train: [14] [260/400] eta: 0:01:04 lr: 0.000085 loss: 0.0694 (0.0787) grad: 0.0403 (0.0469) time: 0.4415 data: 0.0035 max mem: 22446 +train: [14] [280/400] eta: 0:00:54 lr: 0.000083 loss: 0.0775 (0.0795) grad: 0.0435 (0.0466) time: 0.4397 data: 0.0035 max mem: 22446 +train: [14] [300/400] eta: 0:00:46 lr: 0.000082 loss: 0.0816 (0.0795) grad: 0.0435 (0.0468) time: 0.6041 data: 0.1786 max mem: 22446 +train: [14] [320/400] eta: 0:00:37 lr: 0.000081 loss: 0.0721 (0.0792) grad: 0.0444 (0.0468) time: 0.4485 data: 0.0037 max mem: 22446 +train: [14] [340/400] eta: 0:00:27 lr: 0.000079 loss: 0.0789 (0.0796) grad: 0.0423 (0.0464) time: 0.4425 data: 0.0034 max mem: 22446 +train: [14] [360/400] eta: 0:00:18 lr: 0.000078 loss: 0.0825 (0.0797) grad: 0.0423 (0.0463) time: 0.4618 data: 0.0036 max mem: 22446 +train: [14] [380/400] eta: 0:00:09 lr: 0.000076 loss: 0.0817 (0.0798) grad: 0.0475 (0.0464) time: 0.4468 data: 0.0035 max mem: 22446 +train: [14] [399/400] eta: 0:00:00 lr: 0.000075 loss: 0.0752 (0.0798) grad: 0.0428 (0.0464) time: 0.4490 data: 0.0035 max mem: 22446 +train: [14] Total time: 0:03:04 (0.4622 s / it) +train: [14] Summary: lr: 0.000075 loss: 0.0752 (0.0798) grad: 0.0428 (0.0464) +eval (validation): [14] [ 0/63] eta: 0:03:34 time: 3.4126 data: 3.1231 max mem: 22446 +eval (validation): [14] [20/63] eta: 0:00:21 time: 0.3647 data: 0.0027 max mem: 22446 +eval (validation): [14] [40/63] eta: 0:00:09 time: 0.3476 data: 0.0036 max mem: 22446 +eval (validation): [14] [60/63] eta: 0:00:01 time: 0.3206 data: 0.0033 max mem: 22446 +eval (validation): [14] [62/63] eta: 0:00:00 time: 0.3221 data: 0.0033 max mem: 22446 +eval (validation): [14] Total time: 0:00:25 (0.3974 s / it) +cv: [14] best hparam: (4.3, 1.0) (033) ('033_lr4.3e+00_wd1.0e+00') loss: 0.028 acc: 0.992 f1: 0.991 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [15] [ 0/400] eta: 0:24:13 lr: nan time: 3.6340 data: 3.2081 max mem: 22446 +train: [15] [ 20/400] eta: 0:03:55 lr: 0.000074 loss: 0.0769 (0.0822) grad: 0.0386 (0.0442) time: 0.4690 data: 0.0033 max mem: 22446 +train: [15] [ 40/400] eta: 0:03:10 lr: 0.000072 loss: 0.0769 (0.0799) grad: 0.0440 (0.0471) time: 0.4343 data: 0.0032 max mem: 22446 +train: [15] [ 60/400] eta: 0:02:53 lr: 0.000071 loss: 0.0700 (0.0753) grad: 0.0440 (0.0455) time: 0.4705 data: 0.0035 max mem: 22446 +train: [15] [ 80/400] eta: 0:02:38 lr: 0.000070 loss: 0.0688 (0.0751) grad: 0.0380 (0.0441) time: 0.4488 data: 0.0034 max mem: 22446 +train: [15] [100/400] eta: 0:02:25 lr: 0.000068 loss: 0.0676 (0.0740) grad: 0.0371 (0.0435) time: 0.4432 data: 0.0036 max mem: 22446 +train: [15] [120/400] eta: 0:02:13 lr: 0.000067 loss: 0.0681 (0.0735) grad: 0.0377 (0.0444) time: 0.4403 data: 0.0035 max mem: 22446 +train: [15] [140/400] eta: 0:02:02 lr: 0.000066 loss: 0.0692 (0.0738) grad: 0.0405 (0.0437) time: 0.4380 data: 0.0035 max mem: 22446 +train: [15] [160/400] eta: 0:01:52 lr: 0.000064 loss: 0.0765 (0.0736) grad: 0.0413 (0.0439) time: 0.4421 data: 0.0035 max mem: 22446 +train: [15] [180/400] eta: 0:01:42 lr: 0.000063 loss: 0.0658 (0.0741) grad: 0.0418 (0.0439) time: 0.4390 data: 0.0034 max mem: 22446 +train: [15] [200/400] eta: 0:01:32 lr: 0.000062 loss: 0.0779 (0.0747) grad: 0.0406 (0.0435) time: 0.4456 data: 0.0035 max mem: 22446 +train: [15] [220/400] eta: 0:01:22 lr: 0.000061 loss: 0.0718 (0.0741) grad: 0.0408 (0.0437) time: 0.4421 data: 0.0035 max mem: 22446 +train: [15] [240/400] eta: 0:01:13 lr: 0.000059 loss: 0.0683 (0.0740) grad: 0.0425 (0.0436) time: 0.4399 data: 0.0035 max mem: 22446 +train: [15] [260/400] eta: 0:01:04 lr: 0.000058 loss: 0.0709 (0.0741) grad: 0.0425 (0.0435) time: 0.4443 data: 0.0035 max mem: 22446 +train: [15] [280/400] eta: 0:00:54 lr: 0.000057 loss: 0.0651 (0.0740) grad: 0.0417 (0.0434) time: 0.4439 data: 0.0035 max mem: 22446 +train: [15] [300/400] eta: 0:00:46 lr: 0.000056 loss: 0.0737 (0.0742) grad: 0.0393 (0.0433) time: 0.6052 data: 0.1759 max mem: 22446 +train: [15] [320/400] eta: 0:00:37 lr: 0.000054 loss: 0.0704 (0.0738) grad: 0.0397 (0.0434) time: 0.4310 data: 0.0031 max mem: 22446 +train: [15] [340/400] eta: 0:00:27 lr: 0.000053 loss: 0.0704 (0.0740) grad: 0.0448 (0.0436) time: 0.4369 data: 0.0034 max mem: 22446 +train: [15] [360/400] eta: 0:00:18 lr: 0.000052 loss: 0.0707 (0.0741) grad: 0.0411 (0.0436) time: 0.4694 data: 0.0033 max mem: 22446 +train: [15] [380/400] eta: 0:00:09 lr: 0.000051 loss: 0.0617 (0.0736) grad: 0.0403 (0.0433) time: 0.4471 data: 0.0035 max mem: 22446 +train: [15] [399/400] eta: 0:00:00 lr: 0.000050 loss: 0.0718 (0.0740) grad: 0.0386 (0.0432) time: 0.4434 data: 0.0036 max mem: 22446 +train: [15] Total time: 0:03:04 (0.4620 s / it) +train: [15] Summary: lr: 0.000050 loss: 0.0718 (0.0740) grad: 0.0386 (0.0432) +eval (validation): [15] [ 0/63] eta: 0:03:28 time: 3.3125 data: 3.0786 max mem: 22446 +eval (validation): [15] [20/63] eta: 0:00:21 time: 0.3583 data: 0.0051 max mem: 22446 +eval (validation): [15] [40/63] eta: 0:00:09 time: 0.3388 data: 0.0030 max mem: 22446 +eval (validation): [15] [60/63] eta: 0:00:01 time: 0.3198 data: 0.0033 max mem: 22446 +eval (validation): [15] [62/63] eta: 0:00:00 time: 0.3259 data: 0.0033 max mem: 22446 +eval (validation): [15] Total time: 0:00:24 (0.3920 s / it) +cv: [15] best hparam: (4.3, 1.0) (033) ('033_lr4.3e+00_wd1.0e+00') loss: 0.028 acc: 0.992 f1: 0.991 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [16] [ 0/400] eta: 0:23:50 lr: nan time: 3.5765 data: 3.2314 max mem: 22446 +train: [16] [ 20/400] eta: 0:03:44 lr: 0.000048 loss: 0.0743 (0.0743) grad: 0.0385 (0.0398) time: 0.4418 data: 0.0033 max mem: 22446 +train: [16] [ 40/400] eta: 0:03:05 lr: 0.000047 loss: 0.0735 (0.0743) grad: 0.0388 (0.0407) time: 0.4350 data: 0.0034 max mem: 22446 +train: [16] [ 60/400] eta: 0:02:49 lr: 0.000046 loss: 0.0715 (0.0739) grad: 0.0388 (0.0406) time: 0.4690 data: 0.0036 max mem: 22446 +train: [16] [ 80/400] eta: 0:02:35 lr: 0.000045 loss: 0.0737 (0.0744) grad: 0.0370 (0.0403) time: 0.4447 data: 0.0036 max mem: 22446 +train: [16] [100/400] eta: 0:02:23 lr: 0.000044 loss: 0.0770 (0.0745) grad: 0.0378 (0.0403) time: 0.4425 data: 0.0036 max mem: 22446 +train: [16] [120/400] eta: 0:02:12 lr: 0.000043 loss: 0.0637 (0.0739) grad: 0.0390 (0.0405) time: 0.4502 data: 0.0036 max mem: 22446 +train: [16] [140/400] eta: 0:02:01 lr: 0.000042 loss: 0.0642 (0.0740) grad: 0.0410 (0.0408) time: 0.4430 data: 0.0033 max mem: 22446 +train: [16] [160/400] eta: 0:01:51 lr: 0.000041 loss: 0.0711 (0.0736) grad: 0.0391 (0.0409) time: 0.4459 data: 0.0034 max mem: 22446 +train: [16] [180/400] eta: 0:01:41 lr: 0.000040 loss: 0.0733 (0.0737) grad: 0.0384 (0.0406) time: 0.4366 data: 0.0034 max mem: 22446 +train: [16] [200/400] eta: 0:01:32 lr: 0.000039 loss: 0.0739 (0.0740) grad: 0.0420 (0.0410) time: 0.4381 data: 0.0035 max mem: 22446 +train: [16] [220/400] eta: 0:01:22 lr: 0.000038 loss: 0.0695 (0.0737) grad: 0.0424 (0.0406) time: 0.4475 data: 0.0035 max mem: 22446 +train: [16] [240/400] eta: 0:01:13 lr: 0.000036 loss: 0.0691 (0.0733) grad: 0.0354 (0.0402) time: 0.4466 data: 0.0034 max mem: 22446 +train: [16] [260/400] eta: 0:01:03 lr: 0.000035 loss: 0.0742 (0.0738) grad: 0.0372 (0.0403) time: 0.4439 data: 0.0035 max mem: 22446 +train: [16] [280/400] eta: 0:00:54 lr: 0.000034 loss: 0.0699 (0.0734) grad: 0.0406 (0.0408) time: 0.4401 data: 0.0035 max mem: 22446 +train: [16] [300/400] eta: 0:00:46 lr: 0.000033 loss: 0.0666 (0.0735) grad: 0.0427 (0.0412) time: 0.6102 data: 0.1812 max mem: 22446 +train: [16] [320/400] eta: 0:00:37 lr: 0.000032 loss: 0.0716 (0.0735) grad: 0.0419 (0.0413) time: 0.4365 data: 0.0034 max mem: 22446 +train: [16] [340/400] eta: 0:00:27 lr: 0.000031 loss: 0.0766 (0.0741) grad: 0.0419 (0.0415) time: 0.4433 data: 0.0029 max mem: 22446 +train: [16] [360/400] eta: 0:00:18 lr: 0.000031 loss: 0.0751 (0.0739) grad: 0.0410 (0.0415) time: 0.4764 data: 0.0035 max mem: 22446 +train: [16] [380/400] eta: 0:00:09 lr: 0.000030 loss: 0.0658 (0.0734) grad: 0.0392 (0.0413) time: 0.4533 data: 0.0035 max mem: 22446 +train: [16] [399/400] eta: 0:00:00 lr: 0.000029 loss: 0.0624 (0.0735) grad: 0.0417 (0.0415) time: 0.4470 data: 0.0034 max mem: 22446 +train: [16] Total time: 0:03:05 (0.4627 s / it) +train: [16] Summary: lr: 0.000029 loss: 0.0624 (0.0735) grad: 0.0417 (0.0415) +eval (validation): [16] [ 0/63] eta: 0:03:31 time: 3.3570 data: 3.0716 max mem: 22446 +eval (validation): [16] [20/63] eta: 0:00:21 time: 0.3489 data: 0.0045 max mem: 22446 +eval (validation): [16] [40/63] eta: 0:00:09 time: 0.3410 data: 0.0029 max mem: 22446 +eval (validation): [16] [60/63] eta: 0:00:01 time: 0.3278 data: 0.0030 max mem: 22446 +eval (validation): [16] [62/63] eta: 0:00:00 time: 0.3303 data: 0.0031 max mem: 22446 +eval (validation): [16] Total time: 0:00:24 (0.3914 s / it) +cv: [16] best hparam: (4.3, 1.0) (033) ('033_lr4.3e+00_wd1.0e+00') loss: 0.028 acc: 0.992 f1: 0.992 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [17] [ 0/400] eta: 0:24:47 lr: nan time: 3.7192 data: 3.2940 max mem: 22446 +train: [17] [ 20/400] eta: 0:04:06 lr: 0.000028 loss: 0.0597 (0.0694) grad: 0.0369 (0.0409) time: 0.4961 data: 0.0028 max mem: 22446 +train: [17] [ 40/400] eta: 0:03:16 lr: 0.000027 loss: 0.0694 (0.0733) grad: 0.0414 (0.0415) time: 0.4352 data: 0.0035 max mem: 22446 +train: [17] [ 60/400] eta: 0:02:56 lr: 0.000026 loss: 0.0747 (0.0757) grad: 0.0388 (0.0409) time: 0.4655 data: 0.0035 max mem: 22446 +train: [17] [ 80/400] eta: 0:02:40 lr: 0.000025 loss: 0.0770 (0.0765) grad: 0.0403 (0.0409) time: 0.4432 data: 0.0035 max mem: 22446 +train: [17] [100/400] eta: 0:02:26 lr: 0.000024 loss: 0.0750 (0.0751) grad: 0.0403 (0.0408) time: 0.4422 data: 0.0035 max mem: 22446 +train: [17] [120/400] eta: 0:02:15 lr: 0.000023 loss: 0.0672 (0.0743) grad: 0.0383 (0.0409) time: 0.4495 data: 0.0036 max mem: 22446 +train: [17] [140/400] eta: 0:02:03 lr: 0.000023 loss: 0.0719 (0.0739) grad: 0.0367 (0.0411) time: 0.4394 data: 0.0036 max mem: 22446 +train: [17] [160/400] eta: 0:01:53 lr: 0.000022 loss: 0.0719 (0.0735) grad: 0.0383 (0.0412) time: 0.4428 data: 0.0034 max mem: 22446 +train: [17] [180/400] eta: 0:01:43 lr: 0.000021 loss: 0.0688 (0.0730) grad: 0.0411 (0.0409) time: 0.4479 data: 0.0035 max mem: 22446 +train: [17] [200/400] eta: 0:01:33 lr: 0.000020 loss: 0.0643 (0.0728) grad: 0.0386 (0.0408) time: 0.4428 data: 0.0035 max mem: 22446 +train: [17] [220/400] eta: 0:01:23 lr: 0.000019 loss: 0.0643 (0.0727) grad: 0.0371 (0.0406) time: 0.4423 data: 0.0036 max mem: 22446 +train: [17] [240/400] eta: 0:01:14 lr: 0.000019 loss: 0.0671 (0.0728) grad: 0.0356 (0.0407) time: 0.4459 data: 0.0035 max mem: 22446 +train: [17] [260/400] eta: 0:01:04 lr: 0.000018 loss: 0.0679 (0.0731) grad: 0.0397 (0.0407) time: 0.4510 data: 0.0034 max mem: 22446 +train: [17] [280/400] eta: 0:00:55 lr: 0.000017 loss: 0.0679 (0.0729) grad: 0.0388 (0.0404) time: 0.4457 data: 0.0034 max mem: 22446 +train: [17] [300/400] eta: 0:00:47 lr: 0.000016 loss: 0.0658 (0.0730) grad: 0.0385 (0.0406) time: 0.6129 data: 0.1772 max mem: 22446 +train: [17] [320/400] eta: 0:00:37 lr: 0.000016 loss: 0.0718 (0.0730) grad: 0.0418 (0.0407) time: 0.4436 data: 0.0052 max mem: 22446 +train: [17] [340/400] eta: 0:00:28 lr: 0.000015 loss: 0.0718 (0.0730) grad: 0.0381 (0.0405) time: 0.4442 data: 0.0035 max mem: 22446 +train: [17] [360/400] eta: 0:00:18 lr: 0.000014 loss: 0.0669 (0.0726) grad: 0.0358 (0.0403) time: 0.4676 data: 0.0036 max mem: 22446 +train: [17] [380/400] eta: 0:00:09 lr: 0.000014 loss: 0.0659 (0.0727) grad: 0.0368 (0.0402) time: 0.4403 data: 0.0036 max mem: 22446 +train: [17] [399/400] eta: 0:00:00 lr: 0.000013 loss: 0.0659 (0.0725) grad: 0.0387 (0.0402) time: 0.4360 data: 0.0036 max mem: 22446 +train: [17] Total time: 0:03:06 (0.4652 s / it) +train: [17] Summary: lr: 0.000013 loss: 0.0659 (0.0725) grad: 0.0387 (0.0402) +eval (validation): [17] [ 0/63] eta: 0:03:29 time: 3.3254 data: 3.0892 max mem: 22446 +eval (validation): [17] [20/63] eta: 0:00:20 time: 0.3452 data: 0.0033 max mem: 22446 +eval (validation): [17] [40/63] eta: 0:00:09 time: 0.3472 data: 0.0034 max mem: 22446 +eval (validation): [17] [60/63] eta: 0:00:01 time: 0.3405 data: 0.0034 max mem: 22446 +eval (validation): [17] [62/63] eta: 0:00:00 time: 0.3404 data: 0.0033 max mem: 22446 +eval (validation): [17] Total time: 0:00:24 (0.3961 s / it) +cv: [17] best hparam: (4.3, 1.0) (033) ('033_lr4.3e+00_wd1.0e+00') loss: 0.028 acc: 0.992 f1: 0.991 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [18] [ 0/400] eta: 0:23:47 lr: nan time: 3.5676 data: 3.1709 max mem: 22446 +train: [18] [ 20/400] eta: 0:03:51 lr: 0.000012 loss: 0.0627 (0.0709) grad: 0.0365 (0.0395) time: 0.4617 data: 0.0035 max mem: 22446 +train: [18] [ 40/400] eta: 0:03:09 lr: 0.000012 loss: 0.0637 (0.0746) grad: 0.0403 (0.0400) time: 0.4365 data: 0.0033 max mem: 22446 +train: [18] [ 60/400] eta: 0:02:51 lr: 0.000011 loss: 0.0652 (0.0735) grad: 0.0410 (0.0399) time: 0.4658 data: 0.0034 max mem: 22446 +train: [18] [ 80/400] eta: 0:02:37 lr: 0.000011 loss: 0.0712 (0.0739) grad: 0.0410 (0.0401) time: 0.4551 data: 0.0035 max mem: 22446 +train: [18] [100/400] eta: 0:02:25 lr: 0.000010 loss: 0.0712 (0.0739) grad: 0.0408 (0.0402) time: 0.4464 data: 0.0035 max mem: 22446 +train: [18] [120/400] eta: 0:02:13 lr: 0.000009 loss: 0.0627 (0.0715) grad: 0.0373 (0.0396) time: 0.4476 data: 0.0036 max mem: 22446 +train: [18] [140/400] eta: 0:02:02 lr: 0.000009 loss: 0.0671 (0.0721) grad: 0.0378 (0.0400) time: 0.4414 data: 0.0035 max mem: 22446 +train: [18] [160/400] eta: 0:01:52 lr: 0.000008 loss: 0.0710 (0.0717) grad: 0.0400 (0.0401) time: 0.4431 data: 0.0036 max mem: 22446 +train: [18] [180/400] eta: 0:01:42 lr: 0.000008 loss: 0.0618 (0.0710) grad: 0.0402 (0.0403) time: 0.4494 data: 0.0035 max mem: 22446 +train: [18] [200/400] eta: 0:01:33 lr: 0.000007 loss: 0.0640 (0.0708) grad: 0.0406 (0.0403) time: 0.4539 data: 0.0036 max mem: 22446 +train: [18] [220/400] eta: 0:01:23 lr: 0.000007 loss: 0.0644 (0.0708) grad: 0.0406 (0.0402) time: 0.4500 data: 0.0035 max mem: 22446 +train: [18] [240/400] eta: 0:01:14 lr: 0.000006 loss: 0.0654 (0.0706) grad: 0.0408 (0.0402) time: 0.4473 data: 0.0036 max mem: 22446 +train: [18] [260/400] eta: 0:01:04 lr: 0.000006 loss: 0.0654 (0.0709) grad: 0.0367 (0.0399) time: 0.4526 data: 0.0036 max mem: 22446 +train: [18] [280/400] eta: 0:00:55 lr: 0.000006 loss: 0.0701 (0.0709) grad: 0.0414 (0.0402) time: 0.4445 data: 0.0036 max mem: 22446 +train: [18] [300/400] eta: 0:00:47 lr: 0.000005 loss: 0.0689 (0.0706) grad: 0.0426 (0.0402) time: 0.6107 data: 0.1754 max mem: 22446 +train: [18] [320/400] eta: 0:00:37 lr: 0.000005 loss: 0.0643 (0.0705) grad: 0.0385 (0.0402) time: 0.4353 data: 0.0034 max mem: 22446 +train: [18] [340/400] eta: 0:00:28 lr: 0.000004 loss: 0.0694 (0.0707) grad: 0.0388 (0.0401) time: 0.4419 data: 0.0029 max mem: 22446 +train: [18] [360/400] eta: 0:00:18 lr: 0.000004 loss: 0.0656 (0.0705) grad: 0.0394 (0.0403) time: 0.4599 data: 0.0037 max mem: 22446 +train: [18] [380/400] eta: 0:00:09 lr: 0.000004 loss: 0.0644 (0.0701) grad: 0.0364 (0.0401) time: 0.4508 data: 0.0035 max mem: 22446 +train: [18] [399/400] eta: 0:00:00 lr: 0.000003 loss: 0.0628 (0.0699) grad: 0.0371 (0.0401) time: 0.4443 data: 0.0036 max mem: 22446 +train: [18] Total time: 0:03:06 (0.4651 s / it) +train: [18] Summary: lr: 0.000003 loss: 0.0628 (0.0699) grad: 0.0371 (0.0401) +eval (validation): [18] [ 0/63] eta: 0:03:38 time: 3.4739 data: 3.1973 max mem: 22446 +eval (validation): [18] [20/63] eta: 0:00:22 time: 0.3712 data: 0.0039 max mem: 22446 +eval (validation): [18] [40/63] eta: 0:00:09 time: 0.3400 data: 0.0039 max mem: 22446 +eval (validation): [18] [60/63] eta: 0:00:01 time: 0.3317 data: 0.0032 max mem: 22446 +eval (validation): [18] [62/63] eta: 0:00:00 time: 0.3344 data: 0.0032 max mem: 22446 +eval (validation): [18] Total time: 0:00:25 (0.4015 s / it) +cv: [18] best hparam: (4.3, 1.0) (033) ('033_lr4.3e+00_wd1.0e+00') loss: 0.028 acc: 0.992 f1: 0.992 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [19] [ 0/400] eta: 0:23:51 lr: nan time: 3.5778 data: 3.2296 max mem: 22446 +train: [19] [ 20/400] eta: 0:03:44 lr: 0.000003 loss: 0.0691 (0.0694) grad: 0.0373 (0.0372) time: 0.4421 data: 0.0039 max mem: 22446 +train: [19] [ 40/400] eta: 0:03:07 lr: 0.000003 loss: 0.0656 (0.0689) grad: 0.0392 (0.0389) time: 0.4441 data: 0.0032 max mem: 22446 +train: [19] [ 60/400] eta: 0:02:50 lr: 0.000002 loss: 0.0649 (0.0691) grad: 0.0397 (0.0384) time: 0.4673 data: 0.0035 max mem: 22446 +train: [19] [ 80/400] eta: 0:02:36 lr: 0.000002 loss: 0.0677 (0.0701) grad: 0.0402 (0.0396) time: 0.4476 data: 0.0036 max mem: 22446 +train: [19] [100/400] eta: 0:02:23 lr: 0.000002 loss: 0.0687 (0.0713) grad: 0.0395 (0.0394) time: 0.4368 data: 0.0036 max mem: 22446 +train: [19] [120/400] eta: 0:02:12 lr: 0.000002 loss: 0.0687 (0.0711) grad: 0.0371 (0.0393) time: 0.4496 data: 0.0036 max mem: 22446 +train: [19] [140/400] eta: 0:02:02 lr: 0.000001 loss: 0.0645 (0.0702) grad: 0.0379 (0.0393) time: 0.4505 data: 0.0035 max mem: 22446 +train: [19] [160/400] eta: 0:01:52 lr: 0.000001 loss: 0.0681 (0.0706) grad: 0.0365 (0.0391) time: 0.4473 data: 0.0038 max mem: 22446 +train: [19] [180/400] eta: 0:01:42 lr: 0.000001 loss: 0.0673 (0.0708) grad: 0.0365 (0.0391) time: 0.4403 data: 0.0035 max mem: 22446 +train: [19] [200/400] eta: 0:01:32 lr: 0.000001 loss: 0.0673 (0.0709) grad: 0.0392 (0.0392) time: 0.4406 data: 0.0035 max mem: 22446 +train: [19] [220/400] eta: 0:01:22 lr: 0.000001 loss: 0.0710 (0.0714) grad: 0.0404 (0.0393) time: 0.4423 data: 0.0036 max mem: 22446 +train: [19] [240/400] eta: 0:01:13 lr: 0.000001 loss: 0.0710 (0.0711) grad: 0.0404 (0.0393) time: 0.4437 data: 0.0036 max mem: 22446 +train: [19] [260/400] eta: 0:01:04 lr: 0.000000 loss: 0.0627 (0.0711) grad: 0.0378 (0.0393) time: 0.4474 data: 0.0035 max mem: 22446 +train: [19] [280/400] eta: 0:00:54 lr: 0.000000 loss: 0.0653 (0.0713) grad: 0.0394 (0.0394) time: 0.4427 data: 0.0035 max mem: 22446 +train: [19] [300/400] eta: 0:00:46 lr: 0.000000 loss: 0.0709 (0.0713) grad: 0.0419 (0.0396) time: 0.6034 data: 0.1761 max mem: 22446 +train: [19] [320/400] eta: 0:00:37 lr: 0.000000 loss: 0.0684 (0.0712) grad: 0.0427 (0.0397) time: 0.4457 data: 0.0033 max mem: 22446 +train: [19] [340/400] eta: 0:00:27 lr: 0.000000 loss: 0.0633 (0.0710) grad: 0.0412 (0.0397) time: 0.4294 data: 0.0035 max mem: 22446 +train: [19] [360/400] eta: 0:00:18 lr: 0.000000 loss: 0.0663 (0.0710) grad: 0.0396 (0.0398) time: 0.4633 data: 0.0037 max mem: 22446 +train: [19] [380/400] eta: 0:00:09 lr: 0.000000 loss: 0.0642 (0.0706) grad: 0.0380 (0.0398) time: 0.4414 data: 0.0035 max mem: 22446 +train: [19] [399/400] eta: 0:00:00 lr: 0.000000 loss: 0.0642 (0.0705) grad: 0.0348 (0.0398) time: 0.4531 data: 0.0035 max mem: 22446 +train: [19] Total time: 0:03:04 (0.4621 s / it) +train: [19] Summary: lr: 0.000000 loss: 0.0642 (0.0705) grad: 0.0348 (0.0398) +eval (validation): [19] [ 0/63] eta: 0:03:30 time: 3.3352 data: 3.0986 max mem: 22446 +eval (validation): [19] [20/63] eta: 0:00:20 time: 0.3341 data: 0.0038 max mem: 22446 +eval (validation): [19] [40/63] eta: 0:00:09 time: 0.3369 data: 0.0030 max mem: 22446 +eval (validation): [19] [60/63] eta: 0:00:01 time: 0.3229 data: 0.0030 max mem: 22446 +eval (validation): [19] [62/63] eta: 0:00:00 time: 0.3261 data: 0.0026 max mem: 22446 +eval (validation): [19] Total time: 0:00:24 (0.3840 s / it) +cv: [19] best hparam: (4.3, 1.0) (033) ('033_lr4.3e+00_wd1.0e+00') loss: 0.028 acc: 0.992 f1: 0.992 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +evaluating last checkpoint: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +eval model info: +{"score": 0.9920634920634921, "hparam": [4.3, 1.0], "hparam_id": 33, "epoch": 19, "is_best": false, "best_score": 0.9923115079365079} +eval (train): [20] [ 0/297] eta: 0:15:57 time: 3.2249 data: 2.9869 max mem: 22446 +eval (train): [20] [ 20/297] eta: 0:02:13 time: 0.3441 data: 0.0034 max mem: 22446 +eval (train): [20] [ 40/297] eta: 0:01:49 time: 0.3647 data: 0.0037 max mem: 22446 +eval (train): [20] [ 60/297] eta: 0:01:34 time: 0.3499 data: 0.0032 max mem: 22446 +eval (train): [20] [ 80/297] eta: 0:01:26 time: 0.3930 data: 0.0039 max mem: 22446 +eval (train): [20] [100/297] eta: 0:01:18 time: 0.3889 data: 0.0039 max mem: 22446 +eval (train): [20] [120/297] eta: 0:01:09 time: 0.3610 data: 0.0036 max mem: 22446 +eval (train): [20] [140/297] eta: 0:01:01 time: 0.3857 data: 0.0037 max mem: 22446 +eval (train): [20] [160/297] eta: 0:00:52 time: 0.3526 data: 0.0037 max mem: 22446 +eval (train): [20] [180/297] eta: 0:00:44 time: 0.3637 data: 0.0035 max mem: 22446 +eval (train): [20] [200/297] eta: 0:00:36 time: 0.3679 data: 0.0036 max mem: 22446 +eval (train): [20] [220/297] eta: 0:00:29 time: 0.3729 data: 0.0039 max mem: 22446 +eval (train): [20] [240/297] eta: 0:00:21 time: 0.3488 data: 0.0035 max mem: 22446 +eval (train): [20] [260/297] eta: 0:00:13 time: 0.3631 data: 0.0034 max mem: 22446 +eval (train): [20] [280/297] eta: 0:00:06 time: 0.3706 data: 0.0039 max mem: 22446 +eval (train): [20] [296/297] eta: 0:00:00 time: 0.3308 data: 0.0033 max mem: 22446 +eval (train): [20] Total time: 0:01:51 (0.3753 s / it) +eval (validation): [20] [ 0/63] eta: 0:03:20 time: 3.1844 data: 2.8935 max mem: 22446 +eval (validation): [20] [20/63] eta: 0:00:20 time: 0.3522 data: 0.0040 max mem: 22446 +eval (validation): [20] [40/63] eta: 0:00:09 time: 0.3442 data: 0.0036 max mem: 22446 +eval (validation): [20] [60/63] eta: 0:00:01 time: 0.3229 data: 0.0025 max mem: 22446 +eval (validation): [20] [62/63] eta: 0:00:00 time: 0.3222 data: 0.0025 max mem: 22446 +eval (validation): [20] Total time: 0:00:24 (0.3887 s / it) +eval (test): [20] [ 0/79] eta: 0:04:18 time: 3.2667 data: 2.9606 max mem: 22446 +eval (test): [20] [20/79] eta: 0:00:30 time: 0.3868 data: 0.0048 max mem: 22446 +eval (test): [20] [40/79] eta: 0:00:17 time: 0.3774 data: 0.0079 max mem: 22446 +eval (test): [20] [60/79] eta: 0:00:07 time: 0.3483 data: 0.0034 max mem: 22446 +eval (test): [20] [78/79] eta: 0:00:00 time: 0.3319 data: 0.0027 max mem: 22446 +eval (test): [20] Total time: 0:00:31 (0.4029 s / it) +evaluating best checkpoint: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/eval_v2/hcpya_task21__patch__attn/checkpoint-best.pth +eval model info: +{"score": 0.9923115079365079, "hparam": [4.3, 1.0], "hparam_id": 33, "epoch": 11, "is_best": true, "best_score": 0.9923115079365079} +eval (train): [20] [ 0/297] eta: 0:16:21 time: 3.3057 data: 3.0430 max mem: 22446 +eval (train): [20] [ 20/297] eta: 0:02:18 time: 0.3608 data: 0.0035 max mem: 22446 +eval (train): [20] [ 40/297] eta: 0:01:52 time: 0.3715 data: 0.0037 max mem: 22446 +eval (train): [20] [ 60/297] eta: 0:01:36 time: 0.3440 data: 0.0034 max mem: 22446 +eval (train): [20] [ 80/297] eta: 0:01:27 time: 0.3857 data: 0.0039 max mem: 22446 +eval (train): [20] [100/297] eta: 0:01:17 time: 0.3688 data: 0.0036 max mem: 22446 +eval (train): [20] [120/297] eta: 0:01:10 time: 0.4124 data: 0.0040 max mem: 22446 +eval (train): [20] [140/297] eta: 0:01:01 time: 0.3677 data: 0.0036 max mem: 22446 +eval (train): [20] [160/297] eta: 0:00:53 time: 0.3583 data: 0.0038 max mem: 22446 +eval (train): [20] [180/297] eta: 0:00:45 time: 0.3707 data: 0.0035 max mem: 22446 +eval (train): [20] [200/297] eta: 0:00:37 time: 0.3626 data: 0.0036 max mem: 22446 +eval (train): [20] [220/297] eta: 0:00:29 time: 0.3725 data: 0.0036 max mem: 22446 +eval (train): [20] [240/297] eta: 0:00:21 time: 0.3969 data: 0.0035 max mem: 22446 +eval (train): [20] [260/297] eta: 0:00:14 time: 0.3792 data: 0.0038 max mem: 22446 +eval (train): [20] [280/297] eta: 0:00:06 time: 0.3555 data: 0.0036 max mem: 22446 +eval (train): [20] [296/297] eta: 0:00:00 time: 0.3252 data: 0.0032 max mem: 22446 +eval (train): [20] Total time: 0:01:52 (0.3804 s / it) +eval (validation): [20] [ 0/63] eta: 0:03:32 time: 3.3671 data: 3.1132 max mem: 22446 +eval (validation): [20] [20/63] eta: 0:00:22 time: 0.3887 data: 0.0040 max mem: 22446 +eval (validation): [20] [40/63] eta: 0:00:10 time: 0.3524 data: 0.0032 max mem: 22446 +eval (validation): [20] [60/63] eta: 0:00:01 time: 0.3223 data: 0.0031 max mem: 22446 +eval (validation): [20] [62/63] eta: 0:00:00 time: 0.3234 data: 0.0030 max mem: 22446 +eval (validation): [20] Total time: 0:00:25 (0.4056 s / it) +eval (test): [20] [ 0/79] eta: 0:04:20 time: 3.3005 data: 3.0475 max mem: 22446 +eval (test): [20] [20/79] eta: 0:00:29 time: 0.3638 data: 0.0042 max mem: 22446 +eval (test): [20] [40/79] eta: 0:00:17 time: 0.3789 data: 0.0031 max mem: 22446 +eval (test): [20] [60/79] eta: 0:00:07 time: 0.3440 data: 0.0034 max mem: 22446 +eval (test): [20] [78/79] eta: 0:00:00 time: 0.3496 data: 0.0033 max mem: 22446 +eval (test): [20] Total time: 0:00:31 (0.4005 s / it) +eval results: + +| model | repr | clf | dataset | ckpt | epoch | lr | wd | hparam_id | hparam | split | loss | acc | acc_std | f1 | f1_std | +|:---------|:-------|:------|:-------------|:-------|--------:|--------:|-----:|------------:|:-----------|:-----------|-----------:|--------:|----------:|--------:|----------:| +| flat_mae | patch | attn | hcpya_task21 | best | 11 | 0.00129 | 0.05 | 33 | [4.3, 1.0] | train | 0.00019164 | 1 | 0 | 1 | 0 | +| flat_mae | patch | attn | hcpya_task21 | best | 11 | 0.00129 | 0.05 | 33 | [4.3, 1.0] | validation | 0.029056 | 0.99231 | 0.0014241 | 0.99194 | 0.0016153 | +| flat_mae | patch | attn | hcpya_task21 | best | 11 | 0.00129 | 0.05 | 33 | [4.3, 1.0] | test | 0.05845 | 0.9873 | 0.0015052 | 0.98467 | 0.0019899 | + + +done! total time: 1:18:36 diff --git a/input_space_v3/flat_lr1e-3_3/eval_v2/hcpya_task21__patch__attn/train_log.json b/input_space_v3/flat_lr1e-3_3/eval_v2/hcpya_task21__patch__attn/train_log.json new file mode 100644 index 0000000000000000000000000000000000000000..b14b58129049aa0df49eca08013ff45df8cea067 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_3/eval_v2/hcpya_task21__patch__attn/train_log.json @@ -0,0 +1,20 @@ +{"epoch": 0, "train/lr": 2.987987987987988e-05, "train/loss": 2.1180163222551345, "train/grad": 0.21940263740718366, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.06191162109375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.05897705078125, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.05408447265625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.049180908203125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.04434814453125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.037655029296875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.03011962890625, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.021661376953125, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.01062255859375, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.998726806640625, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.987198486328125, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.969681396484375, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.952645263671875, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.928006591796875, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.9041925048828126, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.8813232421875, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.8521612548828124, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.8173602294921873, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.777752685546875, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.7401898193359373, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.6922528076171877, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.6412994384765627, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.582119903564453, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.5161196899414064, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.4445273590087893, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.3560065460205077, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.274733581542969, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.200022048950195, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.098801727294922, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.9804197120666505, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.8768364667892456, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.784821343421936, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.6649049073457718, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.5641394871473313, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.4536355775594711, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.3538191762194038, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.2571998035162688, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.1736151462048292, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.0916614408325405, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.0001445922721177, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.9353941643610597, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.8833249466866255, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.8210505467001349, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.7727173186652362, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.7221813224349171, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.6733350396994502, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.634915698999539, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.593562878081575, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.5614402749668806, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.041499413773417475, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.04142762327566743, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.04130922314710915, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.041190544506534935, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.041074443105608226, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.04091102633625269, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.0407247560005635, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.040519989011809227, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.04024780323728919, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.039955941308289764, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.03966394256800413, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.03922654525376856, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.03879720227792859, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.03817188614979386, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.03757534554228187, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.03700824691914022, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.03631234866566956, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.03554105850867927, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.034756471812725065, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.034095953181385995, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.033363148709759115, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.032682911604642866, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.03199014566838741, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.031299595842137935, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.030611160239204765, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.029809195967391133, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.029098837869241834, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.028457159455865622, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.02760604107286781, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.026636784966103732, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.025810088911093772, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.025075028585270047, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.024071738603524864, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.023212092639878393, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.022227954205591233, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.021266079337801783, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.020429560692282394, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.019697322237771004, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.01896458093309775, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.018151564279105515, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.01719159695727285, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.01659002845757641, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.01586005019256845, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.015540007473609875, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.015494663411227521, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.01536947020475054, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.01512380035885144, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.015072270215023309, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.015217770651215688, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.0234384536743164, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.014622688293457, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.000110387802124, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.9856839179992676, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.9715800285339355, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.9520184993743896, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.9300248622894287, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.9057347774505615, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.874083995819092, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.840970516204834, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.808753252029419, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.7610859870910645, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.7155630588531494, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.651113271713257, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.590484857559204, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.5334737300872803, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.4620254039764404, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.3779006004333496, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.282771587371826, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.1921586990356445, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.077075719833374, "validation/loss_021_lr6.1e-01_wd1.0e+00": 1.9543509483337402, "validation/loss_022_lr7.2e-01_wd1.0e+00": 1.8134698867797852, "validation/loss_023_lr8.5e-01_wd1.0e+00": 1.6595979928970337, "validation/loss_024_lr1.0e+00_wd1.0e+00": 1.4988476037979126, "validation/loss_025_lr1.2e+00_wd1.0e+00": 1.3123310804367065, "validation/loss_026_lr1.4e+00_wd1.0e+00": 1.1546692848205566, "validation/loss_027_lr1.6e+00_wd1.0e+00": 1.0211182832717896, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.8545559048652649, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.6711190938949585, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.5138891339302063, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.38211482763290405, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.24655041098594666, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.17321941256523132, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.1222897469997406, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.08946076780557632, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.07508453726768494, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.073506660759449, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.07466161996126175, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.07162417471408844, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.06237485632300377, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.055223498493433, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.049725938588380814, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.04689502343535423, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.04691634327173233, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.04937588796019554, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.05464638024568558, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.07290548086166382, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.0893247053027153, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.05133928571428571, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.057787698412698416, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06721230158730158, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.0818452380952381, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.10788690476190477, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.17733134920634921, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.2353670634920635, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.2442956349206349, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.22991071428571427, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.2204861111111111, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.21106150793650794, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.20238095238095238, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.19270833333333334, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.1892361111111111, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.19246031746031747, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.203125, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.23511904761904762, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.28422619047619047, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.34399801587301587, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.4020337301587302, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.46304563492063494, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.5282738095238095, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.5597718253968254, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.5994543650793651, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.658234126984127, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.7321428571428571, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.8055555555555556, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.8504464285714286, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.8849206349206349, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.8978174603174603, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9005456349206349, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9074900793650794, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9417162698412699, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9600694444444444, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9662698412698413, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9747023809523809, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9769345238095238, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9751984126984127, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9747023809523809, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9756944444444444, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9801587301587301, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9809027777777778, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9831349206349206, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9833829365079365, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9831349206349206, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9838789682539683, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9801587301587301, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9739583333333334, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9660218253968254, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.01974148945796037, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.02309975811026786, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.027571562509539654, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.03377564674295336, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.04567781885943852, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.07083648152073665, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.07934055024403698, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.07486349660479094, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.0665257060516855, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.05649591365929331, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.04899580227472708, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.0456788375548359, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.03973531032875305, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.037045335044640235, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.041109740637730284, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.05206793536029965, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.07935871987583223, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.11028309672304688, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.15226605014511932, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.18753685881335572, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.24013160345534626, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.2958654965035417, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.3168763021129828, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.3637273453855582, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.4765894605458039, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.6269461232534123, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.7534994834599807, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.8189355446864128, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.8631693865347602, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.8749549678853225, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.8764271662614249, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.8859365122271224, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9355603523523919, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9561033879414254, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9626174903638927, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9721429790153789, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9747531898575533, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9734340716928629, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9732161980651994, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9742793959290933, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9775661767383138, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9765479061240735, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9790224536985586, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9804850599343764, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9810941200769098, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9826849944592793, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9783760816353014, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9704768861675055, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9589740239908315, "id_best": 45, "lr_best": 0.0093, "wd_best": 0.05, "train/loss_best": 0.6733350396994502, "validation/loss_best": 0.04937588796019554, "validation/acc_best": 0.9838789682539683, "validation/f1_best": 0.9826849944592793} +{"epoch": 1, "train/lr": 8.993993993993998e-05, "train/loss": 1.175339287519455, "train/grad": 0.15398458812385798, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.951610107421875, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.93291748046875, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.90271484375, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.873260498046875, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.844713134765625, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.8061749267578127, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.7638720703125, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.7183465576171875, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.66072021484375, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.601778869628906, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.54564208984375, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.463704833984375, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.3862860107421877, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.27677734375, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.1737705993652345, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.076423797607422, "train/loss_016_lr2.7e-01_wd1.0e+00": 1.9545571899414063, "train/loss_017_lr3.2e-01_wd1.0e+00": 1.814385986328125, "train/loss_018_lr3.8e-01_wd1.0e+00": 1.6625141143798827, "train/loss_019_lr4.4e-01_wd1.0e+00": 1.5266046714782715, "train/loss_020_lr5.2e-01_wd1.0e+00": 1.3661327075958252, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.208408989906311, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.0413891315460204, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.876044625043869, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.7232172712683678, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.5689547359198331, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.4549332031607628, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.36989690409973264, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.27891742065548897, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.19974797876551748, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.15070545847527683, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.11988501102663576, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.09398267850279808, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.08097042311914265, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.07201381583698094, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.06709180814214051, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.06401230217888951, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.062259190510958434, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.06044494950212538, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.058503889413550496, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.05805373463779688, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.05784055437892675, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.06005845465697348, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.06309268607757985, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.06881455806083978, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.07145510393194854, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.08407507361844183, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.12461530363187194, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.14933296862989665, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.038344006845727564, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.03788985910825431, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.03714871314354241, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.036432455023750664, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.03573531623929739, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.034804831501096485, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.03380890191532671, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.03278436355292797, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.03158283886499703, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.030487480098381637, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.029580184947699307, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.02846862711943686, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.02761252986267209, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.026640256699174643, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.025899986233562232, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.025293913772329688, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.024595130523666738, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.02380605780519545, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.02291968123987317, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.022077906504273416, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.021037311688996852, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.019976826175116, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.018787210285663606, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.01746092475950718, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.01607354570645839, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.014542639260180295, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.013233172509353608, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.012191208791919053, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.011020266166888178, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.009850045890780167, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.00906671967706643, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.008514273880864493, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.008010082199471072, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.007868448352382984, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.007655061716504861, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.00740768629941158, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.007301062871702016, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.007301526597002521, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.007218686850683298, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.007147555257834028, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.00721575613526511, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0072796571692742874, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.007516907565732253, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.007860326468071435, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.008617212714161724, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.008888082961202599, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.010716736875474453, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.013871368911059107, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.016282006701803766, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.8599183559417725, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.829824924468994, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.7814860343933105, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.7353460788726807, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.691166400909424, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.6323719024658203, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.5691404342651367, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.502115249633789, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.4182002544403076, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.332388401031494, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.2505850791931152, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.130795478820801, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.0173065662384033, "validation/loss_013_lr1.7e-01_wd1.0e+00": 1.8569499254226685, "validation/loss_014_lr2.0e-01_wd1.0e+00": 1.708500623703003, "validation/loss_015_lr2.3e-01_wd1.0e+00": 1.571770191192627, "validation/loss_016_lr2.7e-01_wd1.0e+00": 1.4075515270233154, "validation/loss_017_lr3.2e-01_wd1.0e+00": 1.2299431562423706, "validation/loss_018_lr3.8e-01_wd1.0e+00": 1.051572561264038, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.9013451933860779, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.7289159893989563, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.559307336807251, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.38914182782173157, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.256562203168869, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.1727691888809204, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.11298114061355591, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.08460769802331924, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.07183994352817535, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.061906859278678894, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.05528351292014122, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.051305901259183884, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.04845612496137619, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.04476512596011162, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.04204940423369408, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.03940372169017792, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.03757013753056526, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.03590703383088112, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.03535660356283188, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.03579065576195717, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.035164181143045425, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.03776911646127701, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.0395166240632534, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.035593561828136444, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.040534429252147675, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.048922911286354065, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.060063686221838, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.10143958777189255, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.38742610812187195, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.2940942347049713, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.22941468253968253, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.21577380952380953, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.20163690476190477, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.19270833333333334, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.18898809523809523, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.18973214285714285, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.19692460317460317, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.22123015873015872, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.2648809523809524, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.32490079365079366, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.38244047619047616, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.4600694444444444, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.5265376984126984, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.5600198412698413, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.5944940476190477, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.6512896825396826, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.7180059523809523, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.7924107142857143, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.8454861111111112, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.8745039682539683, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.8950892857142857, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9104662698412699, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9305555555555556, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9558531746031746, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9732142857142857, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9779265873015873, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9799107142857143, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9821428571428571, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9833829365079365, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9846230158730159, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9848710317460317, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9856150793650794, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9853670634920635, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9853670634920635, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9861111111111112, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9866071428571429, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9856150793650794, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9858630952380952, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9868551587301587, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.986359126984127, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9861111111111112, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9858630952380952, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9866071428571429, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9858630952380952, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9841269841269841, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9833829365079365, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9806547619047619, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9610615079365079, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.964781746031746, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.06973797325721388, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.060758469808869696, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.04821018281413911, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.041501364038199096, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.03773385720272999, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.0385182418518454, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.04630072505702477, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.06857271158249108, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.09686503082880342, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.13717127099708834, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.17215131275317788, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.24549838026474508, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.29152252820679064, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.31175750249807, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.3549627582246883, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.48545233766176565, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.6045428394704248, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.7347700914402693, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.8060754760892236, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.8409530312561673, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.8664473416830616, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.8898841937990928, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9202923345556875, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9517342629091962, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9707251302600006, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9752720195703324, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9772490799592705, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9801944179120751, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9817230627913214, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9833063660225201, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.983535452651542, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9842614083410947, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9829073688053256, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9829073731356465, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9833593962736729, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9845181886157193, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9832585578974425, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9829105969046326, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9846778945085668, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.983905766677167, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9837663325201902, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9837995092343096, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9853808986768848, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9831180631108981, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.981096356746252, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9809229213307817, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9760523810054182, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9346576654809589, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9584861695880162, "id_best": 38, "lr_best": 0.00294, "wd_best": 0.05, "train/loss_best": 0.06044494950212538, "validation/loss_best": 0.03579065576195717, "validation/acc_best": 0.9868551587301587, "validation/f1_best": 0.9846778945085668} +{"epoch": 2, "train/lr": 0.00014999999999999988, "train/loss": 0.8643450698256493, "train/grad": 0.1978070242702961, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.7478778076171877, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.70602294921875, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.6397998046875, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.577445068359375, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.5185443115234376, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.440478515625, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.3562075805664064, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.2662786865234374, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.1528445434570314, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.0368307495117186, "train/loss_010_lr1.0e-01_wd1.0e+00": 1.92737548828125, "train/loss_011_lr1.2e-01_wd1.0e+00": 1.7706940460205078, "train/loss_012_lr1.4e-01_wd1.0e+00": 1.6277751159667968, "train/loss_013_lr1.7e-01_wd1.0e+00": 1.4376256561279297, "train/loss_014_lr2.0e-01_wd1.0e+00": 1.2732221221923827, "train/loss_015_lr2.3e-01_wd1.0e+00": 1.129765739440918, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.96340970993042, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.7859200644493103, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.6121224504709244, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.47727709025144577, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.3457388487458229, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.24599371097981929, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.1721553448215127, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.12544140396639705, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.097839912828058, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.0804068220127374, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.07239269294776023, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.06808610203675926, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.06403605612926185, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.06114734739996493, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.05977127591148019, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.05841473141685128, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.05625891221687198, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.053751070667058226, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.05113682296127081, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.04996598314493895, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.04971962538547814, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.05055832116864622, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.05171059565618634, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.05248016915284097, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.05788942502811551, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.062471116278320554, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.09023295567370951, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.11347725040279329, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.22445088578388095, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.35934223742224275, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.551142478119582, "train/loss_047_lr4.3e+01_wd1.0e+00": 1.0128321993350982, "train/loss_048_lr5.0e+01_wd1.0e+00": 1.5665475563332438, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.03403390056453645, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.0330376604385674, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.03155251770280301, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.030289492830634118, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.029247278105467556, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.028103455090895294, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.02714714447967708, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.02636961248703301, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.025623386623337865, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.02499525660648942, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.024439558507874607, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.023616750510409474, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.022793693179264666, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.02157021396793425, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.020409114486537875, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.01935600270051509, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.018121849414892494, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.01677642098162323, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.015304146215785295, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.014009612700901926, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.012545764727983624, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.011196640136186034, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.009865017856936902, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.008798151571536437, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.008044788767583667, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.007531327281612903, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.007342713621910662, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0072803206893149765, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0072092924208845945, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.007221349784522317, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.007259637784445658, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.007178731498424895, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.006993818866321817, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.006741244230943267, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.006536999643431045, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.00649860245452146, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.00657919523131568, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.006719699524401221, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.006904852852167096, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.007275017743668286, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.007997605806631327, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.008331127399433171, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.011426249880896648, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.014319657919113524, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.024973034494905733, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.03598865277483128, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.04742062279372647, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.07145593737452145, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.09877275926322909, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.6301310062408447, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.5764753818511963, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.4925005435943604, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.414067506790161, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.339695930480957, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.24053692817688, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.133009433746338, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.0179333686828613, "validation/loss_008_lr7.4e-02_wd1.0e+00": 1.8731633424758911, "validation/loss_009_lr8.7e-02_wd1.0e+00": 1.727165699005127, "validation/loss_010_lr1.0e-01_wd1.0e+00": 1.5922303199768066, "validation/loss_011_lr1.2e-01_wd1.0e+00": 1.4062846899032593, "validation/loss_012_lr1.4e-01_wd1.0e+00": 1.2452155351638794, "validation/loss_013_lr1.7e-01_wd1.0e+00": 1.042598009109497, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.874020516872406, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.7269312739372253, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.5530725717544556, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.377733051776886, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.24543754756450653, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.1720748096704483, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.11680745333433151, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.08622223138809204, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.07034427672624588, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.061243560165166855, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.055344704538583755, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.050923120230436325, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.04868505522608757, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.048137862235307693, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.04760291054844856, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.04597555100917816, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.04481774941086769, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.042543645948171616, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.038555193692445755, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.036902982741594315, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.03214656561613083, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.0342353880405426, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.03739128261804581, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.03975297138094902, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.04134812578558922, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.039509329944849014, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.0780911073088646, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.04545215517282486, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.07215448468923569, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.12426719814538956, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.5398085713386536, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.8398829102516174, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.3181459903717041, "validation/loss_047_lr4.3e+01_wd1.0e+00": 1.9776557683944702, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.0618255138397217, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.1902281746031746, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.19791666666666666, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.22842261904761904, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.2673611111111111, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.3003472222222222, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.3576388888888889, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.4347718253968254, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.5161210317460317, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.5647321428571429, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.5927579365079365, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.6453373015873016, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.7318948412698413, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.7943948412698413, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.8484623015873016, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.8715277777777778, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.8958333333333334, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9141865079365079, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9367559523809523, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9575892857142857, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9702380952380952, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9759424603174603, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9789186507936508, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9816468253968254, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9833829365079365, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.984375, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9853670634920635, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9858630952380952, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9853670634920635, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9851190476190477, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9853670634920635, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9861111111111112, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9868551587301587, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9871031746031746, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9875992063492064, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9873511904761905, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9878472222222222, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9875992063492064, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9868551587301587, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9871031746031746, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9875992063492064, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9781746031746031, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9868551587301587, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9831349206349206, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9761904761904762, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9702380952380952, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9605654761904762, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9826388888888888, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9670138888888888, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9585813492063492, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.039235655337144945, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.04770576922717745, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.07512102861384486, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.09964871923095216, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.1155094782475562, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.16154171337264, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.22717926388410886, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.29717648404449326, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.3321268762695208, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.3593360133349949, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.4575769882728716, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.5933889120734269, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.6998440147644812, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.7845894821581697, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.8235041766933329, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.8666751265960675, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.8991508122663654, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9299082528338755, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9537668381576994, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.967687522834174, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9735921856158422, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9761868321937264, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9784321172904427, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9807689923769277, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.981520972095393, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9830545642951615, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9836318708788315, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9832713806328622, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9838178727145678, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9840456079844803, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9849515514285893, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9863977411084415, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9863977417302999, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.986858236855675, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9863141833081528, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9864032655133519, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9861526532096686, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9846161229004442, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9852671820192885, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9861943582024579, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9740157210430264, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.985674886843676, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9763748322861465, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9716777277954248, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.968347537417546, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9404237997361626, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9761327759754469, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9502875423297281, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9300394553070417, "id_best": 35, "lr_best": 0.0018, "wd_best": 0.05, "train/loss_best": 0.04996598314493895, "validation/loss_best": 0.0342353880405426, "validation/acc_best": 0.9878472222222222, "validation/f1_best": 0.9864032655133519} +{"epoch": 3, "train/lr": 0.0002100600600600602, "train/loss": 0.740697863548994, "train/grad": 0.2671358325332403, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.5138714599609373, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.4492645263671875, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.3474334716796874, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.2511032104492186, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.159000244140625, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.0364558410644533, "train/loss_006_lr5.3e-02_wd1.0e+00": 1.904481201171875, "train/loss_007_lr6.2e-02_wd1.0e+00": 1.7660047149658202, "train/loss_008_lr7.4e-02_wd1.0e+00": 1.5973013305664063, "train/loss_009_lr8.7e-02_wd1.0e+00": 1.4345232009887696, "train/loss_010_lr1.0e-01_wd1.0e+00": 1.2908546066284179, "train/loss_011_lr1.2e-01_wd1.0e+00": 1.1010105323791504, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.9393272876739502, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.7334250450134278, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.5638083791732789, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.4309220767021179, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.30433237135410307, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.20677925311028958, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.14406697817146777, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.11087508797645569, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.08833664387464524, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.07648702028207481, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.06916999896988273, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.06406337922438979, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.060283543299883606, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.056658964063972236, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.053999668546020986, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.051877136044204235, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.04920801619067788, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.046524790385738014, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0446583347953856, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.04332498176023364, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.042229894259944556, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.04124516132287681, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.04061244086362421, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.03956611798144877, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.0384221828263253, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.03907408533617854, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.045454318653792146, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.05318299320526421, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.06397168654948474, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.11851900966838003, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.1930817063525319, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.44232008633203806, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.47294197253882886, "train/loss_045_lr3.1e+01_wd1.0e+00": 1.0492112310230732, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.9873150827083736, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.1525026413891464, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.485112241646275, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.028583546662703158, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.027670252555981278, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.026600408013910056, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.025889864889904857, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.0253699984587729, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.024782107109203935, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.02417296730913222, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.02347859360277653, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.022509865509346128, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.021435514325276017, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.020391448698937893, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.01893429032061249, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.01769788287114352, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.01614644983317703, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.014742006449960172, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.013415874931961298, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.011805634899064898, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.010110150747932494, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.00868579743313603, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.007786470216233283, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.007107360874069855, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.006775497538037598, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0066280895518139, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.00652732390735764, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.006433099781861529, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0063210986461490395, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.006232040242175572, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.006175499005476013, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.006016538538970054, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0058432740886928515, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.005725736763561144, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.005685536754899658, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.00568603241306846, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.005716060901177116, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.005891828716848977, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.005905148711754009, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.006003319841838674, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.00594396944026812, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.006890403065553983, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.008088019093484035, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.009304372680235247, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.015111642065458, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.021810950788767512, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.03943975570318799, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.04101996929199353, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.06681527544071726, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.07357457121636418, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.11129083172249392, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.15725499106742885, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.375460147857666, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.297757387161255, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.1747612953186035, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.058481216430664, "validation/loss_004_lr3.8e-02_wd1.0e+00": 1.947879433631897, "validation/loss_005_lr4.5e-02_wd1.0e+00": 1.8020480871200562, "validation/loss_006_lr5.3e-02_wd1.0e+00": 1.6481034755706787, "validation/loss_007_lr6.2e-02_wd1.0e+00": 1.4910763502120972, "validation/loss_008_lr7.4e-02_wd1.0e+00": 1.307533621788025, "validation/loss_009_lr8.7e-02_wd1.0e+00": 1.1383841037750244, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.9938146471977234, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.8040496706962585, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.6387478709220886, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.4303116500377655, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.2888100743293762, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.20533861219882965, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.14052437245845795, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.09792150557041168, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.07652101665735245, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.0663209930062294, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.058632515370845795, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.05318746715784073, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.04893093556165695, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.045528165996074677, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.04288143664598465, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.04116041585803032, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.04139392450451851, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.04307142645120621, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.044753219932317734, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.04726189747452736, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.04976436495780945, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.0535622276365757, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.056996140629053116, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.057112615555524826, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.05522095412015915, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.050274789333343506, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.057874660938978195, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.05236625298857689, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.06554994732141495, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.08658017218112946, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.08100252598524094, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.23166203498840332, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.6264531016349792, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.5947558879852295, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.5815580487251282, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.8284999132156372, "validation/loss_046_lr3.6e+01_wd1.0e+00": 1.495918869972229, "validation/loss_047_lr4.3e+01_wd1.0e+00": 4.154029369354248, "validation/loss_048_lr5.0e+01_wd1.0e+00": 5.301921367645264, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.2899305555555556, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.34077380952380953, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.4211309523809524, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.4975198412698413, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.5441468253968254, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.5731646825396826, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.6145833333333334, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.6830357142857143, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.7514880952380952, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.8204365079365079, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.8536706349206349, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.8792162698412699, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.8980654761904762, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9191468253968254, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9412202380952381, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9610615079365079, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9756944444444444, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9791666666666666, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9809027777777778, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9821428571428571, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9828869047619048, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9836309523809523, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.984375, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9841269841269841, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.984375, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9853670634920635, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9851190476190477, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9846230158730159, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9848710317460317, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.984375, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9838789682539683, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.982390873015873, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9806547619047619, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9813988095238095, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.982390873015873, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9828869047619048, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9811507936507936, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9826388888888888, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9821428571428571, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9779265873015873, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9818948412698413, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9734623015873016, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9526289682539683, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9749503968253969, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9771825396825397, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9744543650793651, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9722222222222222, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9605654761904762, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9662698412698413, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.11133360993670402, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.1488639741542769, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.20559757020494138, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.2754763679936677, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.30900870703681105, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.3289638925364771, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.4065842986395647, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.5315305518961343, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.6524452232467628, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.7605435195468131, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.8049692538130755, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.8430183450763066, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.8731681811730019, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9037043440765639, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9347214943046579, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9579391185397901, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9733643001142905, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.976989852263908, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9786266030371226, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9800487227140289, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9808105080299486, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9817572413459804, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9823922762943746, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9822002848863217, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9822113644844925, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9827681551079375, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9822761343194392, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9823696163773492, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9841046284160461, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9844580959284925, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9840014639526596, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9825579129616577, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9809061137560884, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9829766568760282, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9847911312055428, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9832220096874102, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.981200726239042, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9815409543295769, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9822238176774831, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9789205487333361, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9746958459178162, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9719154175584732, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9433946318233327, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9725373828313298, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9720359588629418, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9702520868523437, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9607734049221834, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9614157408405352, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9633816579708994, "id_best": 25, "lr_best": 0.00035999999999999997, "wd_best": 0.05, "train/loss_best": 0.056658964063972236, "validation/loss_best": 0.04116041585803032, "validation/acc_best": 0.9853670634920635, "validation/f1_best": 0.9827681551079375} +{"epoch": 4, "train/lr": 0.0002701201201201201, "train/loss": 0.8073011031746864, "train/grad": 0.44618384644389153, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.2460617065429687, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.1548236083984373, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.0107273864746094, "train/loss_003_lr3.3e-02_wd1.0e+00": 1.8757015991210937, "train/loss_004_lr3.8e-02_wd1.0e+00": 1.7494502258300781, "train/loss_005_lr4.5e-02_wd1.0e+00": 1.5871302795410156, "train/loss_006_lr5.3e-02_wd1.0e+00": 1.4219649887084962, "train/loss_007_lr6.2e-02_wd1.0e+00": 1.2596419143676758, "train/loss_008_lr7.4e-02_wd1.0e+00": 1.0755437469482423, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.9065613079071045, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.7590976428985595, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.5655685377120971, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.4151616269350052, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.2668024840950966, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.18354074403643608, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.1364926865696907, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.10284079134464263, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.08324114127084613, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.07241287074051797, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.06638706141151487, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.06126236040145159, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.05750218991190195, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.05425595866516233, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.051463155103847386, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.04902608048170805, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.04651111752726138, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.04453042848035693, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.042776638343930244, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.04074840526096523, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.038545103725045916, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.03703139597550034, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.03605217139236629, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.03476934339851141, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.034089296218007804, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.033540947465226054, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.03369100227952004, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.0391082177311182, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.058957777172327044, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.052604745868593455, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.16976665928959847, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.321691431812942, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.403636950654909, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.8372818503901363, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.8285275876428932, "train/loss_044_lr2.6e+01_wd1.0e+00": 1.231143544157967, "train/loss_045_lr3.1e+01_wd1.0e+00": 1.2278763917833566, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.970181412231177, "train/loss_047_lr4.3e+01_wd1.0e+00": 5.1098368578962985, "train/loss_048_lr5.0e+01_wd1.0e+00": 5.67219354422763, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.025912412870675326, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.02540780672803521, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.024741604328155517, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.024131798772141336, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.023511448651552202, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.022600921243429183, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.02153398976661265, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.020368653875775636, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.018973877797834576, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.01769624059088528, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.016608647550456226, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.015054824836552143, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.013488978524692356, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.011397739150561392, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.00975046492414549, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.008509606211446226, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.007471904455451294, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.00687294146628119, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.006618633293546736, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.00650866242183838, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.006428161598742008, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.0064037602132884786, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.006399548962363042, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.006408598851703573, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.006402237289585173, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0063985105277970435, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.006358662145503331, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.006283023445867002, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.00619701058283681, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.006065030390454922, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.005975575399061199, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.005912886223813985, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.005767378028249368, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.005716020544496132, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.005661614070268115, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.005767924869142007, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0067087422795884775, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.009085254536694265, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.00825885027545155, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.023718120534831542, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.03080742954422021, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.03777434572780294, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.05888976002411024, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.06320684297033373, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.08090335957544696, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.08109128434214341, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.1939912876212192, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.21490660870169281, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.22335493975840298, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.0975091457366943, "validation/loss_001_lr2.3e-02_wd1.0e+00": 1.9917019605636597, "validation/loss_002_lr2.8e-02_wd1.0e+00": 1.8261042833328247, "validation/loss_003_lr3.3e-02_wd1.0e+00": 1.6734693050384521, "validation/loss_004_lr3.8e-02_wd1.0e+00": 1.533888816833496, "validation/loss_005_lr4.5e-02_wd1.0e+00": 1.3600192070007324, "validation/loss_006_lr5.3e-02_wd1.0e+00": 1.1892668008804321, "validation/loss_007_lr6.2e-02_wd1.0e+00": 1.026941180229187, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.8442946672439575, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.6727391481399536, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.5211842060089111, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.34120699763298035, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.2330152988433838, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.14656956493854523, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.10223275423049927, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.08150152117013931, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.06840774416923523, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.05994143709540367, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.05409673973917961, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.050367049872875214, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.04740200564265251, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.04510355368256569, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.04300941526889801, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.04113348200917244, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.040113650262355804, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.04014086350798607, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.0390046164393425, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.03694009408354759, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.03633151948451996, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.036637552082538605, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.037045955657958984, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.03765510395169258, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.03688688203692436, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.03501276671886444, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.033792175352573395, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.038188472390174866, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.049255210906267166, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.06488803029060364, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.06956709921360016, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.16722729802131653, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.37482938170433044, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.30148255825042725, "validation/loss_042_lr1.9e+01_wd1.0e+00": 1.473519206047058, "validation/loss_043_lr2.2e+01_wd1.0e+00": 1.794593095779419, "validation/loss_044_lr2.6e+01_wd1.0e+00": 6.794002056121826, "validation/loss_045_lr3.1e+01_wd1.0e+00": 1.5395643711090088, "validation/loss_046_lr3.6e+01_wd1.0e+00": 6.2876482009887695, "validation/loss_047_lr4.3e+01_wd1.0e+00": 4.49256706237793, "validation/loss_048_lr5.0e+01_wd1.0e+00": 5.9011030197143555, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.4739583333333333, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.5324900793650794, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.5699404761904762, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.6101190476190477, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.671875, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.7353670634920635, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.8067956349206349, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.8563988095238095, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.8908730158730159, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9092261904761905, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9203869047619048, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9404761904761905, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9625496031746031, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9751984126984127, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9771825396825397, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9791666666666666, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9813988095238095, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9826388888888888, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9833829365079365, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9833829365079365, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9846230158730159, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9848710317460317, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9858630952380952, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9856150793650794, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9861111111111112, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9848710317460317, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9853670634920635, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9866071428571429, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9878472222222222, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9875992063492064, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9873511904761905, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9878472222222222, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9880952380952381, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9888392857142857, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9898313492063492, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9871031746031746, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9868551587301587, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.986359126984127, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9856150793650794, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9831349206349206, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9811507936507936, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9846230158730159, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9747023809523809, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9652777777777778, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.939484126984127, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9776785714285714, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9692460317460317, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9744543650793651, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9714781746031746, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.2595307084858233, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.30099116681766663, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.32381020116223086, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.38619378268605753, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.5014359264627539, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.6071341405591323, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.7316237627849966, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.8133967312449786, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.867121985079565, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.8927528078813565, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9103007394610116, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9357711263915938, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9598301875011369, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9728634905657197, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9749854224601682, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9762182182337499, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9790344559047979, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9805618202262267, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9810921906281754, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9809993749464833, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9828511298169093, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9829816185697076, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9841579119140709, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.983937026952318, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.984487356102884, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9828264278358299, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9826514714365011, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9842857906971829, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9860115621840857, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9854701170873622, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.985245831702092, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.985645527072199, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9857355947236593, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9875243527525474, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9885217334136033, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9850791492502543, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.985880514969061, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9846903146221498, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.983746272563647, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9809997700622101, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9790019481418577, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9813534600066237, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9740227022326506, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9578154613353811, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.8978265236742589, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9712160152099847, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.964720698005212, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9699061677654328, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9693665273626276, "id_best": 34, "lr_best": 0.0015299999999999997, "wd_best": 0.05, "train/loss_best": 0.033540947465226054, "validation/loss_best": 0.033792175352573395, "validation/acc_best": 0.9898313492063492, "validation/f1_best": 0.9885217334136033} +{"epoch": 5, "train/lr": 0.00029891323817685334, "train/loss": 0.7826783113181591, "train/grad": 0.4496826477348804, "train/loss_000_lr2.0e-02_wd1.0e+00": 1.9685079956054687, "train/loss_001_lr2.3e-02_wd1.0e+00": 1.8502925109863282, "train/loss_002_lr2.8e-02_wd1.0e+00": 1.6686825561523437, "train/loss_003_lr3.3e-02_wd1.0e+00": 1.505745391845703, "train/loss_004_lr3.8e-02_wd1.0e+00": 1.361138153076172, "train/loss_005_lr4.5e-02_wd1.0e+00": 1.1859826278686523, "train/loss_006_lr5.3e-02_wd1.0e+00": 1.017165050506592, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.8551950359344482, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.6684725713729859, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.49794732093811034, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.3673046839237213, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.239980648458004, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.16942117467522622, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.1151838793605566, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.09137395299971103, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.08016558459028601, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.07221185832284391, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.0663761012814939, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.06198898191563785, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.058873763140290976, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.05574352512136102, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.05297811915166676, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.05021962068043649, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.04754612873308361, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.04487085439264774, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.04179178452119231, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.03917589179240167, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.03701808787882328, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.03445646708831191, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.03173321361653507, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.029288826556876302, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.027137191658839585, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.02479798669926822, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.021960253221914174, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.024348760824650525, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.036579320104792715, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.0374160597473383, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.06570292771793902, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.1440193741954863, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.24354040952399372, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.43033371067605913, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.6048904105462134, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.9091294680628925, "train/loss_043_lr2.2e+01_wd1.0e+00": 1.1490980085823685, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.528335844250396, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.717198786884546, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.964548647683114, "train/loss_047_lr4.3e+01_wd1.0e+00": 5.34429461479187, "train/loss_048_lr5.0e+01_wd1.0e+00": 6.711074185986072, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.024403789080679417, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.023868368295952676, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.02293300151824951, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.0219407229218632, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.02093882010318339, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.019604686978273094, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.018269336610101165, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.017025166349485518, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.01565822836942971, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.01423543153796345, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.012753856314811856, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.010749701478052884, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.009268179051578045, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.007757501823361963, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.007014078666106798, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.006723905106191523, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.006574860190739855, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.006476763074751943, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.006407668967440259, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.00634888771106489, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.006267992122157011, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.006222078634891659, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.006184127729211468, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.006153406412922777, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.006074442499666475, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.005941504186193924, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.005803773011430167, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.005654729532252532, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.005511952607485, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.005345214086264605, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.005140118852432351, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0050123007628280905, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.004927958757834858, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.004779306817072211, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.005481208661949495, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.007234427639086789, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.007438345770642627, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.010319985894511774, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.019627060003040243, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.025175339000611245, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.03790018898362547, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.048166790541084546, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.06322414678063543, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.07318599109532575, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.11936740407545585, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.13029972113475477, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.15021202713381507, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.20708662997931243, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.23509955045198924, "validation/loss_000_lr2.0e-02_wd1.0e+00": 1.8269720077514648, "validation/loss_001_lr2.3e-02_wd1.0e+00": 1.6981782913208008, "validation/loss_002_lr2.8e-02_wd1.0e+00": 1.5038379430770874, "validation/loss_003_lr3.3e-02_wd1.0e+00": 1.3345770835876465, "validation/loss_004_lr3.8e-02_wd1.0e+00": 1.1881085634231567, "validation/loss_005_lr4.5e-02_wd1.0e+00": 1.0140012502670288, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.8461906313896179, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.6816318035125732, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.49093058705329895, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.33532997965812683, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.23774316906929016, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.15345416963100433, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.10784560441970825, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.0785285085439682, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.06640983372926712, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.05967424809932709, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.053837940096855164, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.04913962259888649, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.04532572254538536, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.042856451123952866, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.04026559740304947, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.038114700466394424, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.03653542697429657, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.03570430353283882, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.03421007841825485, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.031930264085531235, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.030947089195251465, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.031312935054302216, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.03395428881049156, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.03877543658018112, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.0430586040019989, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.044543977826833725, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.037464775145053864, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.034238897264003754, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.04230853170156479, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.0620400570333004, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.08311672508716583, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.08976544439792633, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.48539721965789795, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.30631503462791443, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.4081479012966156, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.556961178779602, "validation/loss_042_lr1.9e+01_wd1.0e+00": 1.0971275568008423, "validation/loss_043_lr2.2e+01_wd1.0e+00": 1.460326075553894, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.1158154010772705, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.125396728515625, "validation/loss_046_lr3.6e+01_wd1.0e+00": 4.461386680603027, "validation/loss_047_lr4.3e+01_wd1.0e+00": 6.589052200317383, "validation/loss_048_lr5.0e+01_wd1.0e+00": 12.065174102783203, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.5719246031746031, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.6011904761904762, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.6860119047619048, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.7609126984126984, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.8266369047619048, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.8725198412698413, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.8921130952380952, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.9084821428571429, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9181547619047619, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9370039682539683, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9558531746031746, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9722222222222222, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9776785714285714, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9801587301587301, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9816468253968254, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9833829365079365, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.984375, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9851190476190477, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9856150793650794, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9856150793650794, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9873511904761905, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9875992063492064, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.988343253968254, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.988343253968254, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9875992063492064, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9875992063492064, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.988343253968254, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9888392857142857, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9873511904761905, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9873511904761905, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9853670634920635, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.984375, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9861111111111112, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9888392857142857, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9851190476190477, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9818948412698413, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9821428571428571, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9833829365079365, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9623015873015873, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9796626984126984, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9809027777777778, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9764384920634921, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9776785714285714, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9774305555555556, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9771825396825397, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9809027777777778, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9675099206349206, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9642857142857143, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9541170634920635, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.32343708097521423, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.36335272216398296, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.5290762408964972, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.6789140726337507, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.7860124377283509, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.8494135878651866, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.8735349291930439, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.8944128188036984, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9057253749859394, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9303025907802196, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9520063217573064, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9699352910678025, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9752340374602175, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9774994258083531, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9788724766730513, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.981171952650188, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9821953585359108, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9830987336193835, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9838243689141288, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9838200761378036, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.986334706820205, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9863346142841716, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9871863784891308, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9872388341027316, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9865511186385317, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9866013697125908, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9865890779758638, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9860034181790014, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9831115466640897, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9834708870708646, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.98167773169148, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9811231283844956, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9829336951948401, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9865812836710626, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9813869863745998, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9752555443058516, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9819031678699401, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9799391826681514, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9506606543839131, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9746167482345534, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9743631709275759, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9754168935767241, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9741478286450734, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9758930904248567, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9748674719143159, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9763683691686422, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9562598377261196, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9534688186114528, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9539678104969886, "id_best": 27, "lr_best": 0.00047999999999999996, "wd_best": 0.05, "train/loss_best": 0.03701808787882328, "validation/loss_best": 0.031312935054302216, "validation/acc_best": 0.9888392857142857, "validation/f1_best": 0.9860034181790014} +{"epoch": 6, "train/lr": 0.0002924170901991409, "train/loss": 0.5375172910839319, "train/grad": 0.36629904959350823, "train/loss_000_lr2.0e-02_wd1.0e+00": 1.7154267883300782, "train/loss_001_lr2.3e-02_wd1.0e+00": 1.57954345703125, "train/loss_002_lr2.8e-02_wd1.0e+00": 1.3793373107910156, "train/loss_003_lr3.3e-02_wd1.0e+00": 1.2092019653320312, "train/loss_004_lr3.8e-02_wd1.0e+00": 1.0639003753662108, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.890604133605957, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.7202035903930664, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.5531828761100769, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.37859954953193664, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.2584572783112526, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.18736374035477638, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.1260777885466814, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.09671746976673604, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.07835178926587105, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.06979821774177253, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.06464334359392523, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.0600062747951597, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.05585997977294028, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.05218118015676737, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.049256616635248066, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.04598137159831822, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.04298339739441872, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.03995537340641022, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.0369720815308392, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.03428550998680294, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.031532131265848876, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.029321322031319142, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.027513078255578874, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.02509255036711693, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.022294222582131623, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.01974774689413607, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.01759857918135822, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.01682012399658561, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.015745602678507567, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.018726074127480386, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.02235389972105622, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.02127094369381666, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.06146666233427823, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.1590576993767172, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.16712463146075607, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.2949747016187757, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.25040606746450067, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.5377798765338957, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.6354188445210457, "train/loss_044_lr2.6e+01_wd1.0e+00": 1.2892886613495649, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.281070100739598, "train/loss_046_lr3.6e+01_wd1.0e+00": 1.7703838483151049, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.790597080178559, "train/loss_048_lr5.0e+01_wd1.0e+00": 5.043871672162786, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.0231654404476285, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.0223705383669585, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.021015553176403044, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.01972572194878012, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.01857748133596033, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.01724934273865074, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.016025829045102, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.014765005046501755, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.012937502183485777, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.011101037748157978, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.009717640781309456, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.008127859880914912, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.007218159965705126, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.0067430364992469545, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.006584395651589148, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.006508770665386692, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.006442694888683036, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.006368315836298279, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.006291631496278569, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.006229212009930052, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.006138779471511952, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.006052660224959254, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0059507800804567525, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0058578303584363315, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.00576411380112404, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.005610469940875191, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0054314127995166925, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.005261819184815977, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.004994160793576157, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.004655588237073971, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0043120240869757255, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.004052950228142436, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0038798403694090666, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0038711324256291845, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.004289961125668924, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.005140786502943228, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0053191990290997635, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.011259992579586821, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.01974413090734627, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.022140116765649122, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.028993872785113766, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.028137611017367545, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.04843759318213074, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.05008268494895287, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.08640365632261458, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.12537857444066147, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.11229902766085217, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.14690441503737073, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.19472382484073297, "validation/loss_000_lr2.0e-02_wd1.0e+00": 1.5950820446014404, "validation/loss_001_lr2.3e-02_wd1.0e+00": 1.4542895555496216, "validation/loss_002_lr2.8e-02_wd1.0e+00": 1.2513114213943481, "validation/loss_003_lr3.3e-02_wd1.0e+00": 1.08250892162323, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.9391768574714661, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.7664995789527893, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.5935524702072144, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.42906445264816284, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.2790457010269165, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.18769210577011108, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.13393475115299225, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.0912899300456047, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.07388134300708771, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.06176738440990448, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.0553894080221653, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.05125885084271431, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.0475175715982914, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.04437284544110298, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.0418369397521019, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.0399322509765625, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.03808563947677612, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.03666272014379501, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.03563893213868141, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.034824520349502563, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.03428862616419792, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.03359999135136604, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.032535482197999954, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.03186234459280968, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.030480319634079933, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.02915947139263153, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.028397705405950546, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.02913670800626278, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.03211796656250954, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.03030090406537056, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.03302391991019249, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.05306582897901535, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.06481017917394638, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.09356959909200668, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.13431550562381744, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.26213836669921875, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.42370450496673584, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.4523676335811615, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.6326358318328857, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.8175377249717712, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.422529935836792, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.5795955657958984, "validation/loss_046_lr3.6e+01_wd1.0e+00": 2.9592232704162598, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.695408821105957, "validation/loss_048_lr5.0e+01_wd1.0e+00": 5.587402820587158, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.6463293650793651, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.7018849206349206, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.7869543650793651, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.8509424603174603, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.8819444444444444, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.9037698412698413, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9159226190476191, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.9325396825396826, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.955109126984127, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9699900793650794, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9747023809523809, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9786706349206349, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.980406746031746, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9821428571428571, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9833829365079365, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9833829365079365, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9846230158730159, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9853670634920635, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.986359126984127, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.986359126984127, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9861111111111112, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9866071428571429, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9875992063492064, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.988343253968254, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9885912698412699, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9885912698412699, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9888392857142857, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9893353174603174, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9898313492063492, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9900793650793651, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9905753968253969, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9900793650793651, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9910714285714286, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9910714285714286, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9895833333333334, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.988343253968254, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9858630952380952, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9866071428571429, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9851190476190477, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9856150793650794, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9831349206349206, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9851190476190477, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.986359126984127, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9828869047619048, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9764384920634921, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.980406746031746, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9774305555555556, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.982390873015873, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9766865079365079, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.4593636667055803, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.5546012426702192, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.7278298844553883, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.8235061813111361, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.8638640897802764, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.8897332957025702, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.9034505830594577, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9255959383690892, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9512491812396662, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9676538695642358, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9722409832111973, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9762339780427141, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.977974576954987, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9799351476089326, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.981118366853185, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9811158653144618, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9828253349848239, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9840739640627638, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9853345352640162, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9853326805845237, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.984657992940629, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.985060853391162, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.986416019609649, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9870079037227244, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9872894650709126, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9873626605112926, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9881445230884263, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9888723610121724, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9893230568224548, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.989551008121956, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9905578158764693, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9903229754611453, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9908527254353201, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9908213559113437, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9894555012689704, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9873127933959603, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9838006122320564, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9849219993538948, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9836742784807548, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9815642453603493, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.979889310556526, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9835683478177574, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9858127754367978, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9792426115856727, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9711146163879799, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9759883542738044, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.973745170803071, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9800914893396969, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9733171984916529, "id_best": 32, "lr_best": 0.0011099999999999999, "wd_best": 0.05, "train/loss_best": 0.01682012399658561, "validation/loss_best": 0.03211796656250954, "validation/acc_best": 0.9910714285714286, "validation/f1_best": 0.9908527254353201} +{"epoch": 7, "train/lr": 0.00027969249556793234, "train/loss": 0.37832453805953264, "train/grad": 0.2868445734679699, "train/loss_000_lr2.0e-02_wd1.0e+00": 1.4994404602050782, "train/loss_001_lr2.3e-02_wd1.0e+00": 1.3569566345214843, "train/loss_002_lr2.8e-02_wd1.0e+00": 1.1553231811523437, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.9891671371459961, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.8472752857208252, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.6735187339782714, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.5023534178733826, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.3544615423679352, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.23344253420829772, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.16123779147863387, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.12016245096921921, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.09095570515841246, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.07842164002358913, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.06897596346214413, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.0633638765476644, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.059494772823527456, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.05568943354301155, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.05205531342886388, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.04860049687325954, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.04577624846249819, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.04255168658681214, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.03952960046008229, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.036457872632890936, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.03352209498174488, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.030568525129929185, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.027353099612519145, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.024757902501150966, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.022490825764834882, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.018991822469979526, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.014452568804845214, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.010885570226237177, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.008350799968466162, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.00624544832855463, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.005719266636297107, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.009515988891944289, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.01793748957104981, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.026837491374462844, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.06563774612732232, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.07102738907560706, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.07669817094691098, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.14131119002588094, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.15732447053305804, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.28406673507764935, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.3427847940661013, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.7902120986301452, "train/loss_045_lr3.1e+01_wd1.0e+00": 1.6785429479181766, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.873416592143476, "train/loss_047_lr4.3e+01_wd1.0e+00": 1.9962637966126204, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.2277762414887547, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.022126717083156108, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.021123664919286966, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.019552491568028928, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.01821487273555249, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.01710952989757061, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.015824663299135865, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.014417392080649733, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.01270231909584254, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.010704420176334679, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.009091475286986679, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.00786678954027593, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.006948195366421714, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.006644419626099989, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.0064552455348894, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.0063430831057485195, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.006248129401355982, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.006147932122694329, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.00603422932268586, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.005921553199295886, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.0058335003152024, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.0057523203623713924, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.0056594500888604675, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.005553560151311103, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0054248396729235536, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.005260559785238001, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0050393160461680965, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.004877209918922745, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.004698019805946387, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.004392178352572955, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.003899200080631999, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.003404811648579198, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.002976974494486058, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0026390801950765307, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0025681739198080322, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0036020420986960745, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0051059282083701875, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.006375840058262838, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.012542542675745966, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.011901369696764426, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.013713054063825156, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.02040891239459934, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.019028532956519302, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.031041238024306046, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.03824749365580569, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.06502839885875811, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.09735151773393438, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.07673968404641582, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.11430253895963557, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.15784905289956674, "validation/loss_000_lr2.0e-02_wd1.0e+00": 1.404004454612732, "validation/loss_001_lr2.3e-02_wd1.0e+00": 1.2602065801620483, "validation/loss_002_lr2.8e-02_wd1.0e+00": 1.0598160028457642, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.8951133489608765, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.7525570392608643, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.5760038495063782, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.4082220494747162, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.2784014046192169, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.18021295964717865, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.1215309128165245, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.09110216051340103, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.07135578989982605, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.062029723078012466, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.05428670719265938, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.04971270263195038, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.04665640741586685, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.04387202486395836, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.04142646864056587, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.039418891072273254, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.03837230056524277, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.037545345723629, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.03663923591375351, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.035183876752853394, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.03351537510752678, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.03195283189415932, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.0308830589056015, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.03013543225824833, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.029637768864631653, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.029273562133312225, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.029220260679721832, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.029165059328079224, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.029197828844189644, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.029876191169023514, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.03372972831130028, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.03925270587205887, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.11419771611690521, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.10882757604122162, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.14970651268959045, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.15377596020698547, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.22923099994659424, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.4114321768283844, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.2707265019416809, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.5722552537918091, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.5928325057029724, "validation/loss_044_lr2.6e+01_wd1.0e+00": 1.701058030128479, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.1595852375030518, "validation/loss_046_lr3.6e+01_wd1.0e+00": 1.4897329807281494, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.399033308029175, "validation/loss_048_lr5.0e+01_wd1.0e+00": 4.261078357696533, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.7244543650793651, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.7911706349206349, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.8616071428571429, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.8883928571428571, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9077380952380952, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.9169146825396826, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9347718253968254, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.9548611111111112, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9702380952380952, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9764384920634921, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9784226190476191, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.980406746031746, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9818948412698413, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.984375, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9846230158730159, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9848710317460317, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.984375, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9846230158730159, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9861111111111112, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9866071428571429, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9871031746031746, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9868551587301587, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9873511904761905, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9888392857142857, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9893353174603174, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9893353174603174, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9900793650793651, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9900793650793651, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9903273809523809, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9905753968253969, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9900793650793651, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9898313492063492, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9915674603174603, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9900793650793651, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9895833333333334, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9806547619047619, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9813988095238095, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9853670634920635, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9875992063492064, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9841269841269841, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9826388888888888, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9871031746031746, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9861111111111112, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9858630952380952, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9836309523809523, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9836309523809523, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.986359126984127, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9771825396825397, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9754464285714286, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.6127993582381299, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.7327177480530315, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.8392049530783898, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.8725483728754637, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.8965985442209795, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.907024372566673, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.9288175064010519, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9512719835790467, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9680599937936779, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9742372284969288, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9761316612473978, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.977974576954987, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9797983105015983, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9820548457606078, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9823683494132387, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9825476607923178, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.982267238695165, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9826245928430202, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.984597672343267, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9851292143755831, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9858175883297152, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9855503845416751, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9865025410788283, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.988042202497338, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9882724669388911, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9883086649983448, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.98915055063021, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9895259105244953, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9904441695337424, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.990403035479425, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9895928802861347, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9890464746954469, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.990404537046572, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9882427555731742, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9880291576290554, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9788263941145675, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9770388632643081, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9844078690750926, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9867830749647881, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9797482755159922, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9809309948252662, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9853375798444514, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9841680139698002, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.985038277984092, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9801976769350575, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9818981856709948, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9842510083797958, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9773077446808438, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9699711131755161, "id_best": 32, "lr_best": 0.0011099999999999999, "wd_best": 0.05, "train/loss_best": 0.00624544832855463, "validation/loss_best": 0.029876191169023514, "validation/acc_best": 0.9915674603174603, "validation/f1_best": 0.990404537046572} +{"epoch": 8, "train/lr": 0.0002612959497061927, "train/loss": 0.2648920285701752, "train/grad": 0.23100496109575033, "train/loss_000_lr2.0e-02_wd1.0e+00": 1.3182403564453125, "train/loss_001_lr2.3e-02_wd1.0e+00": 1.1758094787597657, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.9786721992492676, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.8156559371948242, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.6729421377182007, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.4989683318138123, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.34652513146400454, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.23859883069992066, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.15790143728256226, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.11155220963060856, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.08991522453725338, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.07516574134118854, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.06780408988706768, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.06121463628485799, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.05695539484731853, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.05374993427656591, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.050315346205607056, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.04682744608260691, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.04345013028010726, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.04060834120027721, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.03746081428602338, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.034459608616307376, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.03135960889048874, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.028109747106209396, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.024903855556622147, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.021149771260097622, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.01790923691354692, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.014827284915372729, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.011142941555008293, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.007617733338847756, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.005226437449455262, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.0037420892901718615, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.0038732444774359463, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.002994957882910967, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.004806989645585418, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.01413118802011013, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.025915266089141367, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.05410428195260465, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.06496585054323077, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.03004943828098476, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.07825549336150289, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.05879819111898541, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.12189566324464977, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.1481374866515398, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.4178568978048861, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.6708362425491213, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.7278815475013107, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.894396088635549, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.522029445460066, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.020622006598860026, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.019492133450694383, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.017855229880660774, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.01654258109629154, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.015445738374255598, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.014010495375841855, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.012232772530987859, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.010447866248432547, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.008744386911857874, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.00742132043116726, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.006759558487683535, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.006395463204244152, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.0062397141638211905, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.006103545328951441, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.006005515549622942, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.005924576499091927, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.005826597602863331, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.005711284045828506, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.005591550591343548, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.005489730500266887, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.0053726987016852945, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.005250828062708024, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.005107421178836375, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.00490656778900302, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.004663991040724795, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.004303935924763209, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0039302537747425955, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.003502094756840961, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0029223214088051463, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0022548430312963317, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0017578368846261584, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0014130425928033218, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0012468685903877486, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.001325713431248232, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.001627058449107608, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.00369804242286591, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.005923839571873515, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.009937632481833703, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.011347782422702677, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.007238077326997763, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.013440528086288282, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.010462800108903271, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.01963558509140607, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.018547881335550864, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.04040493587576649, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.07095458640591412, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.05962796921484759, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.06692180824646793, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.138061429840653, "validation/loss_000_lr2.0e-02_wd1.0e+00": 1.2513755559921265, "validation/loss_001_lr2.3e-02_wd1.0e+00": 1.1095879077911377, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.9138513803482056, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.7502145767211914, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.6052202582359314, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.431873083114624, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.29130393266677856, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.19753709435462952, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.12768657505512238, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.09067611396312714, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.0744292140007019, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.06263293325901031, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.056310269981622696, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.05058997869491577, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.04697467014193535, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.044472966343164444, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.04204947128891945, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.03988734632730484, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.03797255456447601, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.03642445430159569, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.03508709743618965, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.033891890197992325, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.03283877298235893, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.0318877287209034, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.030827436596155167, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.02964596450328827, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.028605014085769653, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.027971766889095306, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.02778475172817707, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.028960464522242546, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.028823014348745346, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.02880917489528656, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.03198445588350296, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.03179103508591652, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.034657854586839676, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.06246257200837135, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.1030655950307846, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.09931638836860657, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.20032340288162231, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.1488039195537567, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.21701528131961823, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.29778075218200684, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.6755280494689941, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.588374674320221, "validation/loss_044_lr2.6e+01_wd1.0e+00": 1.461366891860962, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.420612335205078, "validation/loss_046_lr3.6e+01_wd1.0e+00": 1.9186158180236816, "validation/loss_047_lr4.3e+01_wd1.0e+00": 2.4539473056793213, "validation/loss_048_lr5.0e+01_wd1.0e+00": 4.4668288230896, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.7896825396825397, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.8382936507936508, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.8784722222222222, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.9015376984126984, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9134424603174603, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.9270833333333334, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9496527777777778, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.9660218253968254, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9761904761904762, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9794146825396826, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9813988095238095, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9816468253968254, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9831349206349206, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9841269841269841, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9853670634920635, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9861111111111112, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.986359126984127, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9871031746031746, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.986359126984127, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.986359126984127, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9868551587301587, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9868551587301587, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9875992063492064, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.988343253968254, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9880952380952381, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9878472222222222, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9880952380952381, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9890873015873016, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9900793650793651, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9900793650793651, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9898313492063492, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9910714285714286, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9903273809523809, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9908234126984127, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9895833333333334, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9880952380952381, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9861111111111112, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9868551587301587, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.984375, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9893353174603174, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9890873015873016, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9885912698412699, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9841269841269841, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9871031746031746, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.986359126984127, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9826388888888888, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9791666666666666, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9811507936507936, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9737103174603174, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.7247245635527777, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.7969822032734862, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.8536596556183494, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.8856638974576344, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.9007043853958553, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.919406052000969, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.9465830375882088, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9633216011149929, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9735799780822285, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9775516700227419, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9795667485972851, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9800030796315042, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9811344918553182, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.982500617708663, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9842453860805345, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9851377999391224, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9853131837013223, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9862211982123416, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9854006345952949, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.985126906411302, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9858537085755136, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9854989305059346, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9869523904678201, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9874580593736069, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9869864912770835, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9871511041103435, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9873591568375895, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9882691194386375, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.989102541769383, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9889601442138074, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9886913980834322, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9900860820787307, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9893050078932795, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9897856284737261, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9887121172124522, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9867455651766518, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.980306626805974, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9836126612487099, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9826618314055088, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.988221876960886, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9878956527604087, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9873470578576802, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9825105158472929, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9863804947969893, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9842220055280374, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9797198498797935, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9714232998363692, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9787261634829856, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9695799011819676, "id_best": 31, "lr_best": 0.0009299999999999999, "wd_best": 0.05, "train/loss_best": 0.0037420892901718615, "validation/loss_best": 0.02880917489528656, "validation/acc_best": 0.9910714285714286, "validation/f1_best": 0.9900860820787307} +{"epoch": 9, "train/lr": 0.00023803200426111704, "train/loss": 0.18289793346077204, "train/grad": 0.16646250823512673, "train/loss_000_lr2.0e-02_wd1.0e+00": 1.1948745346069336, "train/loss_001_lr2.3e-02_wd1.0e+00": 1.0542568969726562, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.8597614860534668, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.6953355026245117, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.5503859615325928, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.38467404127120974, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.26044107496738433, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.17951760232448577, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.11991724081337451, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.09111391138285399, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.0784772577136755, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.0686974866129458, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.06300660656765103, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.05754524629563093, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.053702685311436654, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.05061631713062525, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.04726168347522616, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.043754619602113964, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.04027375805191696, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.037292884448543194, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.033940726807340976, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.03084591415710747, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.027731849672272803, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.02467373915947974, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.021683098804205655, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.01801153932698071, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.014712721118703484, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.011758462972939015, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.008183668442070484, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.005044409343972802, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.00294867561198771, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.0014636831544339657, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.0010719113145023584, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.0007633958756923675, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.0011149709112942218, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.007364161033183336, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.016244632303714753, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.014813768547028303, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.04149855029769242, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.019692172072827818, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.01944220582023263, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.033942951429635285, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.056894740546122195, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.08286712719127536, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.13786001687869429, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.4759041576180607, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.3822905941866338, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.2755235911998898, "train/loss_048_lr5.0e+01_wd1.0e+00": 1.2628046606481076, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.019769647428765892, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.01863676158245653, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.017091468679718672, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.015851667867973446, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.014713773764669895, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.012975575337186455, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.011030062658246607, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.00939088106388226, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.007768106774892658, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.006860553232254461, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.00654711990035139, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.006358511442667805, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.006266241748817265, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.006186143740196712, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.006117464376729913, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.006040629279741552, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.005951289868971798, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.005833945152990055, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.005701695947209373, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.005555935100710485, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.005363347245147452, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.0051559274955070575, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0049036918570345735, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.004629815653315745, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0043413436338596515, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.003949725382917677, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0035406862897070825, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0031353458369267175, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.002528504892870842, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0017929092065242002, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0011676085880571918, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0006315191685098399, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0005572582943977977, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0003325474052780919, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0005705046366415445, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.003244129619591831, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.004625541113289451, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.003946245477094634, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.006872491952994169, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.006545722587806395, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.007061358351534775, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0066980044627932625, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.012521457274278606, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.012156695290747739, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.024551658506711326, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.05330673129013177, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.03972333324662178, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.04144263927682021, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.08864323865287674, "validation/loss_000_lr2.0e-02_wd1.0e+00": 1.1317036151885986, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.9928015470504761, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.8000012040138245, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.6350517272949219, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.4903034567832947, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.3326568603515625, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.22168831527233124, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.14977163076400757, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.09876155108213425, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.07613386958837509, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.06566379219293594, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.05723349377512932, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.05226295068860054, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.047550737857818604, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.044356949627399445, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.04202187806367874, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.039503272622823715, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.037167198956012726, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.035129353404045105, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.03351558744907379, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.03212490677833557, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.03073929063975811, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.029541699215769768, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.028721701353788376, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.0283281859010458, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.028049902990460396, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.027558788657188416, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.027169037610292435, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.02682449296116829, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.02714409865438938, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.027856161817908287, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.028001392260193825, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.028570247814059258, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.029188502579927444, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.029860425740480423, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.053802210837602615, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.06183037534356117, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.10500699281692505, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.16633811593055725, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.2628832459449768, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.1927626132965088, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.30053916573524475, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.44273290038108826, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.5434378981590271, "validation/loss_044_lr2.6e+01_wd1.0e+00": 1.242179036140442, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.1782126426696777, "validation/loss_046_lr3.6e+01_wd1.0e+00": 1.5587817430496216, "validation/loss_047_lr4.3e+01_wd1.0e+00": 1.6397769451141357, "validation/loss_048_lr5.0e+01_wd1.0e+00": 2.472543478012085, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.8350694444444444, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.8665674603174603, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.8983134920634921, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.9136904761904762, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9228670634920635, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.9434523809523809, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9635416666666666, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.9744543650793651, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9789186507936508, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.980406746031746, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9813988095238095, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9836309523809523, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9848710317460317, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9856150793650794, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9861111111111112, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9861111111111112, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9868551587301587, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9866071428571429, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9875992063492064, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9873511904761905, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9875992063492064, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9880952380952381, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9890873015873016, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9890873015873016, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9895833333333334, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9898313492063492, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9905753968253969, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9895833333333334, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9893353174603174, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9903273809523809, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9908234126984127, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9905753968253969, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9908234126984127, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9908234126984127, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9905753968253969, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9895833333333334, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9885912698412699, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9858630952380952, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9866071428571429, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9833829365079365, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9885912698412699, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9878472222222222, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9871031746031746, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9861111111111112, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9833829365079365, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9821428571428571, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9831349206349206, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9831349206349206, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9801587301587301, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.7962719867014192, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.8408010934362666, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.883797856512061, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.9021252541457284, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.9142135027232766, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.9391755049669932, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.9606055741673293, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9716618402024583, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9764842733150684, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9777753594281903, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9792534801429699, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9811532332018179, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9824495557850745, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.983794920558574, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.984698999704152, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.984698999704152, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9856022017804756, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9851857789127488, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9859179726222578, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9860246143340845, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9864613063934672, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9868668625131738, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9883116565321733, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9876381344571266, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9884190500977297, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9883851597071643, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9888413217524733, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9885328281571982, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.987926724223346, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9893469174580994, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9898496533279184, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9900361828183626, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9896718296433323, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9900562545899826, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9905851166594631, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9887099079815846, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9876912826079063, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9841414460248142, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9846386838313392, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9805224580249862, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9879178832972303, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9869745434791236, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9865197868972999, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.985586677591811, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9823837730449447, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9826784665382398, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9810461271812517, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9818735500045014, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9765589665314551, "id_best": 30, "lr_best": 0.00081, "wd_best": 0.05, "train/loss_best": 0.00294867561198771, "validation/loss_best": 0.027856161817908287, "validation/acc_best": 0.9908234126984127, "validation/f1_best": 0.9898496533279184} +{"epoch": 10, "train/lr": 0.00021091808096876188, "train/loss": 0.13834831215441226, "train/grad": 0.12746406888589262, "train/loss_000_lr2.0e-02_wd1.0e+00": 1.0899235916137695, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.9532290077209473, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.7615950298309326, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.5964432454109192, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.45422945737838744, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.3076071602106094, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.20817314743995666, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.1438503935933113, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.10070674329996109, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.08214826449751854, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.0732394963502884, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.06562105004675686, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.060785272028297185, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.055923603391274807, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.052257925840094685, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.04932878557592631, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.04599295703694224, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.04252088121138513, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.038905717730522156, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.035849451962858436, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.03231094134040177, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.02873732748441398, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.025024287682026625, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.02131265215575695, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.01756608944386244, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.013274488262832165, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.009625340914353728, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.006792193921282888, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.003918432611972094, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0022159618232399226, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.001291940687224269, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.0007089219894260168, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.00044005272909998895, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.00026161930523812773, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.00022697401233017444, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.0011978464666754008, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.010928874369710684, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.0032893746625632047, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.011431381339207292, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.023737382693216205, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.013632321860641242, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.021146668335422874, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.022730019725859165, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.02068210597150028, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.09612158106639981, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.16511439550668, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.2396099511999637, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.22774433985352516, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.539662778833881, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.018776644775643943, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.017682208935730158, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.01625228242017329, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.015068613179028034, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.013851878577843308, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.011988391673658044, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.0102146084071137, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.008671353335957975, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.007263589332578704, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.00668742427311372, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.006474351814831607, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.0063015833229292184, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.006183081457857042, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.006055934021132998, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.005945983161800541, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.005836585091310553, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.005705591961741447, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.005544035845086909, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.005358546490897425, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.005188083704269957, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.004965952835627832, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.004698986928269732, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0043874875188339504, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.004048765987099614, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0036623679022886792, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0031615543070074637, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0026549990135390543, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.002153669132239884, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.001483135368252988, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0009684389831636508, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0005776983055238816, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0002909617963882738, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.00022327542472567075, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.00013453364716269788, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.00020328402727216144, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0010275691529635367, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.003569664307122409, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.001654317234888696, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.004082106661206797, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.004795296001282112, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0050874012587887145, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.005987672622010834, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.006145970132230536, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.004834226826667742, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.01381234180232717, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.022958951691840986, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.029478887863746875, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.039669573831715585, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.06075692868378673, "validation/loss_000_lr2.0e-02_wd1.0e+00": 1.0385632514953613, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.9023213386535645, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.710209846496582, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.5444336533546448, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.40502747893333435, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.2683001160621643, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.1783239245414734, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.1201387494802475, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.0839776024222374, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.06857699155807495, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.06070738658308983, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.0538058876991272, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.04950042814016342, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.045279692858457565, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.042486198246479034, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.040246862918138504, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.03799038007855415, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.03584250062704086, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.03390209376811981, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.03235930576920509, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.030875984579324722, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.029651325196027756, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.028778132051229477, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.028472956269979477, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.028496259823441505, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.028385315090417862, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.02808123640716076, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.027856148779392242, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.02788410894572735, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.02728762850165367, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.028069406747817993, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.02817477285861969, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.028553413227200508, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.028082488104701042, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.02988150715827942, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.05055345967411995, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.0905279591679573, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.08250503242015839, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.15188917517662048, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.19821114838123322, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.19307902455329895, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.2619764804840088, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.4062875509262085, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.48836055397987366, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.8294385671615601, "validation/loss_045_lr3.1e+01_wd1.0e+00": 1.328624963760376, "validation/loss_046_lr3.6e+01_wd1.0e+00": 1.2983412742614746, "validation/loss_047_lr4.3e+01_wd1.0e+00": 1.610079288482666, "validation/loss_048_lr5.0e+01_wd1.0e+00": 2.2827534675598145, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.8611111111111112, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.8829365079365079, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.9064980158730159, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.9196428571428571, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9322916666666666, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.9538690476190477, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9702380952380952, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.9771825396825397, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9794146825396826, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9816468253968254, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9828869047619048, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9846230158730159, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9853670634920635, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9861111111111112, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9858630952380952, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9868551587301587, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9873511904761905, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9878472222222222, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9885912698412699, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9880952380952381, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9888392857142857, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9903273809523809, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9903273809523809, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9895833333333334, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9893353174603174, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9895833333333334, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9898313492063492, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9905753968253969, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9908234126984127, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9910714285714286, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9910714285714286, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9913194444444444, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9910714285714286, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9905753968253969, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9895833333333334, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9873511904761905, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9880952380952381, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9885912698412699, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9868551587301587, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9885912698412699, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9890873015873016, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9866071428571429, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9873511904761905, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9873511904761905, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9868551587301587, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9851190476190477, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9841269841269841, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9799107142857143, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.8330801516408458, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.8638418373546085, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.893735322733623, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.9093751154238079, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.9259769317613579, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.9499950872140867, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.9672086470281559, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9742242881154584, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9768253498456577, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9797399424458054, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9805976786140985, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9822700348411564, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9839678926540747, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9852340253438653, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.984871856355015, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9859599151119425, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9864112072934168, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9866987500816015, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9874141580358494, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9863529830826837, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9868909050781121, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9887275988828896, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9890043294335629, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9884798905299974, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9882999352181792, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9884910990583232, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9892048782930665, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9903177951399261, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9904975107120277, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9906787208799921, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9907184005230527, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9907633944632572, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9905840112862634, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9915830842663961, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9909503727125059, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9898176331733146, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9856838488932438, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9871398718043345, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9882982070134619, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.98612101450115, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.987584101643652, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9891842691581756, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.98526950017527, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9858779666994776, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9840007524174122, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9857360795235076, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9848366613616565, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9814705042698493, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9734823627113491, "id_best": 33, "lr_best": 0.00129, "wd_best": 0.05, "train/loss_best": 0.00026161930523812773, "validation/loss_best": 0.028082488104701042, "validation/acc_best": 0.9920634920634921, "validation/f1_best": 0.9915830842663961} +{"epoch": 11, "train/lr": 0.00018113997589164516, "train/loss": 0.11058327451348304, "train/grad": 0.09103944563306868, "train/loss_000_lr2.0e-02_wd1.0e+00": 1.0021609497070312, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.8680373287200928, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.6775132131576538, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.5135793757438659, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.37998494148254397, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.2544993025064468, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.17234357073903084, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.11978122621774673, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.0889704642444849, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.07575503388419748, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.06882937412708998, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.062291379701346156, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.05797183954156935, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.053276227125898, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.04969225975684822, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.04673326510936022, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.04334899663925171, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.039745106799528, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.03616277877241373, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.03310396277345717, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.029475700072944165, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.02596578447148204, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.022146238600835203, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.018242226736620067, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.014277710961177945, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.00985414944589138, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.006327187698334455, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.00396461883559823, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0021197454165667296, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0011142097134143115, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0006887475773692131, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.0004969335068017245, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.000329720601439476, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.00023523208685219288, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.00013394431211054324, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.000269508920609951, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.0036546482890844347, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.005091183967888355, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.0045101494994014505, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.003101638238877058, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.004299865774810314, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.012791487192735075, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.00905384348705411, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.008865970065817236, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.05431740930303931, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.08665772996842862, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.0675114839989692, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.12537256130948662, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.25393029490485786, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.018092144336551427, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.016981749259866775, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.015474832095205783, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.014109059860929847, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.01260323938447982, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.010573955506552012, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.008907389363739639, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.007549154749140144, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.006608097582357004, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.00627804845222272, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.006139448165195063, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.006018735741381533, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.005928166841622442, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.0058115567272761836, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.005715031969011761, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.0056284672507899815, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.005514936390973162, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.0053850192259415055, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.005231350120593561, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.005090601913398132, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.0048805845923197925, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.004615733431710396, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.004286759612732567, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.003876968549375306, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.003390164977245149, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.002750127079707454, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.002090451293006481, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0015040863519971027, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0009428486554315896, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0005371878002733866, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.00029763671384898773, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.00019690774173795943, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.000137360071726107, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.00010364291631162814, "train/grad_034_lr5.1e+00_wd1.0e+00": 6.497931560033976e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.00019250664154476737, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.001058274374539694, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0008510951112110587, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0021063793571049934, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0016828565061820361, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0014036338241699292, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0032764433937797215, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.005021127285174214, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.004027966559970002, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.008113989481794263, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.015222819756322501, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.015436348037718395, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.023746308543751704, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.03465576898282926, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.9668840765953064, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.8322654962539673, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.6400182843208313, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.47503387928009033, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.34443891048431396, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.22598224878311157, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.14940887689590454, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.10164673626422882, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.07526364177465439, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.0634649246931076, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.057068806141614914, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.05116976052522659, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.0473974347114563, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.04367762431502342, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.04110001027584076, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.03910405933856964, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.0371309295296669, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.03512207418680191, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.03329921141266823, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.03209087252616882, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.030757322907447815, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.029896721243858337, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.02925620786845684, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.02908189408481121, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.02905847504734993, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.02922370471060276, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.029193928465247154, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.028846120461821556, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.028664754703640938, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.02861311472952366, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.029332973062992096, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.028882808983325958, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.029035013169050217, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.029056383296847343, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.030100516974925995, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.04614434763789177, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.07654571533203125, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.0758092999458313, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.13325273990631104, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.17645463347434998, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.1801261156797409, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.17082640528678894, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.41473188996315, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.44879820942878723, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.8133174777030945, "validation/loss_045_lr3.1e+01_wd1.0e+00": 1.1876561641693115, "validation/loss_046_lr3.6e+01_wd1.0e+00": 1.1653302907943726, "validation/loss_047_lr4.3e+01_wd1.0e+00": 1.1228455305099487, "validation/loss_048_lr5.0e+01_wd1.0e+00": 1.5314475297927856, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.8700396825396826, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.8911210317460317, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.9094742063492064, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.9248511904761905, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9409722222222222, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.9613095238095238, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9737103174603174, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.9784226190476191, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9809027777777778, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9816468253968254, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9833829365079365, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9848710317460317, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9856150793650794, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.986359126984127, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.986359126984127, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9871031746031746, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9868551587301587, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9873511904761905, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9878472222222222, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9880952380952381, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9885912698412699, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.988343253968254, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9893353174603174, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9885912698412699, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9898313492063492, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9895833333333334, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9898313492063492, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9903273809523809, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9903273809523809, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9910714285714286, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9910714285714286, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9910714285714286, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9915674603174603, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9923115079365079, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9908234126984127, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9895833333333334, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9895833333333334, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.988343253968254, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9885912698412699, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9875992063492064, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9888392857142857, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9900793650793651, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9848710317460317, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9875992063492064, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9868551587301587, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9851190476190477, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9848710317460317, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9838789682539683, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9841269841269841, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.8462387865970202, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.8746550998179989, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.8978019312138515, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.9166237804061469, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.93658749202747, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.9579189199942086, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.9708971473242984, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9757552051018822, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9784823073193588, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9792510018463102, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9805597237413224, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9827089277778217, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9845151476334034, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9856034973027351, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9856034973027351, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9861431121441304, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9857331466319208, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9861863223905039, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9867295205936271, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9874754203101015, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9878348208638834, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9877808493306707, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9890591963099489, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9882782040307776, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9893162078004304, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9889442813303242, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9892176222916921, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9899450101494313, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9899892326096198, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9907578682315313, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9908071042741289, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9908071042741289, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9914803177037435, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9919416770538232, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9911300118749214, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9897731881719641, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9883669855057567, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9869695274231968, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.988500365526708, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9873124546532539, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9875785465578473, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9897613969349569, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9819407033816001, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9860273147458374, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9843458715091331, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9839449916017855, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9841375822266639, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9812859364227092, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9833702162149297, "id_best": 33, "lr_best": 0.00129, "wd_best": 0.05, "train/loss_best": 0.00023523208685219288, "validation/loss_best": 0.029056383296847343, "validation/acc_best": 0.9923115079365079, "validation/f1_best": 0.9919416770538232} +{"epoch": 12, "train/lr": 0.0001499999999999999, "train/loss": 0.09392312996089458, "train/grad": 0.06473015668801964, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.94970458984375, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.8162010097503662, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.62414146900177, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.46074527502059937, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.33519510507583616, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.22386168092489242, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.1508976350724697, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.10666129522025586, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.08305177120491862, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.07218608854338526, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.06607497205026448, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.06005001803860068, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.05591688425280154, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.051362767526879904, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.04775048214010894, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.04476329658180475, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.04143529928289354, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.037896787617355585, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.03434789421036839, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.031287188436836005, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.027634678119793536, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.024019858073443173, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.020282315630465744, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.01643527946434915, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.012530429027974606, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.008235881375148892, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.005148015590384603, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0032312873285263778, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0017808174900710582, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0009325768705457449, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0005858433432877064, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.00043301444500684736, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.00027382771484553816, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.00019552800804376603, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.00010891594924032688, "train/loss_035_lr6.0e+00_wd1.0e+00": 4.4991681352257726e-05, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.7801386788487435e-05, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.4578431621193885e-05, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.0013737486861646175, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.002016186947003007, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.0017762751784175634, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.004869911773130298, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.016984906448051333, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.0015405083447694778, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.02293509531766176, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.022939158026129006, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.03015127444639802, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.0447877877485007, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.037391456160694364, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.01756902682594955, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.016548726256005467, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.01513956074602902, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.013742815917357803, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.012181709611322731, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.010269684037193656, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.008613344389013946, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.007254622259642929, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.006549136231187731, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.006298376851482317, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.006163470277097076, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.006027162739774212, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.005918889836757444, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.005781021956354379, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.005655535752885044, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.005535762383951806, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.005400808861886617, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.005235459683754016, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.005065419686725363, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.004898186411592178, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.004664544294646475, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.004391378966101911, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.004043143567978405, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0036061965335102285, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.003097636418970069, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.002427355153049575, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.001768270515385666, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.001233461416013597, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0007319117592305701, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.00037994274456650603, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.00022934753160370748, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.00017108335275224816, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.00011305334182907246, "train/grad_033_lr4.3e+00_wd1.0e+00": 8.396007047167586e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 5.482920301290051e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 3.623872651255411e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.00010530771151388229, "train/grad_037_lr8.3e+00_wd1.0e+00": 3.130711990219973e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0005410916020245436, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0010153242044086243, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0006824689041796594, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0013825743194242992, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.004069739110006187, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0011989364370205678, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.004789542864679631, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0051339927423582924, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.007476531784131431, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.010975950799299321, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.01452070544102835, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.911740243434906, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.7783023715019226, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.585693359375, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.42368632555007935, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.3026617765426636, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.19782190024852753, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.12983180582523346, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.09052149206399918, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.06990811228752136, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.0601317398250103, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.0546291284263134, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.04927299544215202, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.04588984325528145, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.04250717908143997, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.04017096012830734, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.038477782160043716, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.036715712398290634, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.03502144291996956, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.033603768795728683, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.032624103128910065, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.031465090811252594, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.030561435967683792, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.029853051528334618, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.02928871475160122, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.029064757749438286, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.02881437912583351, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.028695890679955482, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.028279123827815056, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.028543826192617416, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.028603894636034966, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.028996456414461136, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.028439844027161598, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.028539929538965225, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.028268134221434593, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.029541637748479843, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.04500637948513031, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.0737486183643341, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.0662982240319252, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.11527778953313828, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.1811332404613495, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.1695071905851364, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.15589599311351776, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.38499245047569275, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.3766035735607147, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.5814867615699768, "validation/loss_045_lr3.1e+01_wd1.0e+00": 1.0301569700241089, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.8382115364074707, "validation/loss_047_lr4.3e+01_wd1.0e+00": 1.0835254192352295, "validation/loss_048_lr5.0e+01_wd1.0e+00": 1.3133225440979004, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.8826884920634921, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.9020337301587301, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.9171626984126984, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.9327876984126984, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9484126984126984, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.9670138888888888, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9764384920634921, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.9794146825396826, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9809027777777778, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.982390873015873, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.984375, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9856150793650794, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9861111111111112, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.986359126984127, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9868551587301587, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9871031746031746, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9880952380952381, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9875992063492064, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9875992063492064, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9875992063492064, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9878472222222222, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9885912698412699, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.988343253968254, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9885912698412699, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9895833333333334, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9895833333333334, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9895833333333334, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9903273809523809, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9908234126984127, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9910714285714286, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9908234126984127, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9910714285714286, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9905753968253969, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9918154761904762, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9905753968253969, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9895833333333334, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9893353174603174, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9878472222222222, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9890873015873016, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9890873015873016, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9893353174603174, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9878472222222222, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9878472222222222, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9888392857142857, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9890873015873016, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9856150793650794, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9866071428571429, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9838789682539683, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9841269841269841, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.8648578341782673, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.8897045057055293, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.9079190899170936, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.9275395001679654, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.9451049702903082, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.9639581349672858, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.9735939472458343, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9768253498456577, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9788440670140414, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9798835474342876, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9817352520380372, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9845088043065291, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9852370675821016, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9850610118907319, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9856934484506765, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9859628821999354, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9864128109400185, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9860658194339555, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9859744330527678, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9862938020769205, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9860464923496233, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9870874581190714, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9873955926147042, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9883883047031038, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9895542645347771, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9895542645347771, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9896447060987628, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.990179092488631, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9905790760479773, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9907616043995708, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9905835020577646, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9905840287560146, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9902246209682048, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.991451057577697, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9909503683821852, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9894524978516271, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9886340201520794, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9866425098670458, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9891823757303005, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9874292457409292, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9888599760853685, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9865308124193698, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9866685312526378, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9874836745521998, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9878408180411937, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9847589819800397, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9865102399770833, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9827329471178833, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9830713143166866, "id_best": 33, "lr_best": 0.00129, "wd_best": 0.05, "train/loss_best": 0.00019552800804376603, "validation/loss_best": 0.028268134221434593, "validation/acc_best": 0.9918154761904762, "validation/f1_best": 0.991451057577697} +{"epoch": 13, "train/lr": 0.00011886002410835478, "train/loss": 0.08358278496190906, "train/grad": 0.05139445045031607, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.8941278076171875, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.7601952457427978, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.5670970463752747, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.40739365696907043, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.29202899992465975, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.19373615980148315, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.13012984178960324, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.09456654936075211, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.07622121747583151, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.06735705462284386, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.06209010411053896, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.056655406439676884, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.05282893187366426, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.048427123548462986, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.04493483799509704, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.04188515602611005, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.038530402313917876, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.034930325970053674, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.031344863772392276, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.02823275338858366, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.024644473856315015, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.02110630818642676, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.01735310352407396, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.013438706789165734, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.009608504353091121, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.00585057538934052, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.003515373710542917, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.002172408774495125, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.001227682651951909, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0007151625584810972, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0004687156807631254, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.00036132387816905975, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.00024693417362868785, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.0001691377628594637, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.00011288006789982319, "train/loss_035_lr6.0e+00_wd1.0e+00": 4.106886684894562e-05, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.335949033498764e-05, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.00011485479772090911, "train/loss_038_lr9.8e+00_wd1.0e+00": 5.034422501921654e-06, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.291472628712654e-05, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.0005591349303722382, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.00021468758583068848, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.00027191635221242907, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.000790677322074771, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.00032715199515223506, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.01235938268713653, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.007495218999683857, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.01984901544637978, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.02976734804920852, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.01704578722361475, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.016028344407677652, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.014588503967970609, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.013088748701848089, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.011506599623244256, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.00974282159935683, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.008178369437810034, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.006985604938818142, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.0064293464785441755, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.006215349273406901, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.0060884467524010685, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.00596719728957396, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.005869563838350586, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.005735872768564149, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.005608606398745906, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.005481820343702566, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.0053339921185397545, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.005164212143281475, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.004975500621658285, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.0047836036403896285, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.004533592800289626, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.004263328915985767, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.003920270523012732, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0034924293242511338, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0029336736800905784, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0021368392397562276, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0014196358851222613, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0009132479971776775, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.000514878848225635, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0002964325416724023, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0001948968057718048, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.00014719149149641452, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.00010120742049139152, "train/grad_033_lr4.3e+00_wd1.0e+00": 7.633590336808993e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 5.306051981051496e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 2.7967814225089426e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 3.406603853793211e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 7.092100172964938e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 9.749492033609307e-06, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.00012326120613863792, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0002729745034897002, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0002938937895064308, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0005100999057317755, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0005206852002106324, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.001005500580350026, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0035585768159944876, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.002403322263165938, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.004697436433614367, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.006850693549928499, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.8709200620651245, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.7379248142242432, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.5452916622161865, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.38690027594566345, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.274004727602005, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.17850333452224731, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.1166720762848854, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.08353827148675919, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.06638592481613159, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.0578993484377861, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.05280720442533493, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.048012565821409225, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.044947169721126556, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.041656043380498886, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.03947436437010765, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.0377572700381279, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.03608865290880203, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.03435368090867996, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.03266202658414841, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.031429871916770935, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.0301304180175066, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.029110033065080643, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.028382573276758194, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.028051363304257393, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.02808019146323204, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.028630901128053665, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.02888985350728035, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.029171807691454887, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.02920963428914547, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.02923894114792347, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.029208876192569733, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.028758710250258446, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.028522012755274773, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.02809671312570572, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.029506197199225426, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.043760064989328384, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.07084071636199951, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.06462981551885605, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.11181420087814331, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.17222104966640472, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.15957079827785492, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.13586266338825226, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.34203657507896423, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.3452575206756592, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.631934404373169, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.9829477667808533, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.8302226066589355, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.9072065949440002, "validation/loss_048_lr5.0e+01_wd1.0e+00": 1.0670686960220337, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.8869047619047619, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.9072420634920635, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.9211309523809523, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.9357638888888888, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9523809523809523, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.9694940476190477, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9779265873015873, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.9799107142857143, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9811507936507936, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9836309523809523, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.984375, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9853670634920635, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9858630952380952, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9866071428571429, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.986359126984127, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.986359126984127, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9866071428571429, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.986359126984127, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9871031746031746, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9873511904761905, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9875992063492064, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9880952380952381, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9893353174603174, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9905753968253969, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9900793650793651, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9903273809523809, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9905753968253969, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9908234126984127, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9908234126984127, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9908234126984127, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9910714285714286, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9908234126984127, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9915674603174603, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9905753968253969, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9898313492063492, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9893353174603174, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9885912698412699, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9888392857142857, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9875992063492064, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9900793650793651, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9895833333333334, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9880952380952381, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9878472222222222, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9888392857142857, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9856150793650794, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9861111111111112, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9861111111111112, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9875992063492064, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.8702472375229716, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.8960739705513168, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.9127725882716526, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.9310885748280503, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.9495291736541579, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.9667148124720027, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.9756745790357506, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9776004481825379, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9788046006454837, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9814728269243884, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9820569830435711, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9839408830994262, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9843040199835189, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9855109509897912, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9851482699803749, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.985154634518453, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9847051590322922, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9845156273646692, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9859692718034423, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9861491664616461, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9862536190548846, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9872354899569936, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9886510756159164, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9899084540898324, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9894576724767814, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9896392158844481, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9904058716356413, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9906267987085914, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9905790760479773, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9905792135599525, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9906728278312755, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9904462983586123, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9909545444810226, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9915837239854357, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9909503683821852, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9896315726413251, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9886340201520794, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.98718159727054, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9886382858584035, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9865237660201074, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9890016900999321, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.987832210849967, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9868759852668435, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9869852967599714, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9877334428137632, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9852014767694686, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9864779173409559, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9843478857597383, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9864412000991507, "id_best": 33, "lr_best": 0.00129, "wd_best": 0.05, "train/loss_best": 0.0001691377628594637, "validation/loss_best": 0.02809671312570572, "validation/acc_best": 0.9920634920634921, "validation/f1_best": 0.9915837239854357} +{"epoch": 14, "train/lr": 8.9081919031238e-05, "train/loss": 0.07980919854715467, "train/grad": 0.04639044216834009, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.8626208305358887, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.7300670051574707, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.5385055327415467, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.38343852281570434, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.2750487816333771, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.1837187811732292, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.12475540772080422, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.09378776017576457, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.07762606415897608, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.06929984477348626, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.0642317437659949, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.058801930295303464, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.054921263260766864, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.05034384957514703, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.046704598339274525, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.043526884755119684, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.03994805756956339, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.0360610287822783, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.03222677401266992, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.02884272095747292, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.024867659751325846, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.021001060381531714, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.016897372379899026, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.012677550725638866, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.008763577919453383, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.005113653913140297, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.003002922050654888, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0019036726281046867, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0011122767999768258, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0006665973272174597, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.00045794286765158174, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.00035267054103314875, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.0002378038037568331, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.00017387677915394305, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.00010630789212882518, "train/loss_035_lr6.0e+00_wd1.0e+00": 4.261712543666363e-05, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.2293105721473695e-05, "train/loss_037_lr8.3e+00_wd1.0e+00": 7.509626448154449e-06, "train/loss_038_lr9.8e+00_wd1.0e+00": 4.773167893290519e-06, "train/loss_039_lr1.2e+01_wd1.0e+00": 4.871273413300514e-06, "train/loss_040_lr1.4e+01_wd1.0e+00": 6.606746464967727e-06, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.7888471484184265e-06, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.1364277452230454e-06, "train/loss_043_lr2.2e+01_wd1.0e+00": 8.566388860344887e-06, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.0012842870131134986, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.00617331619374454, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.0034307370241731406, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.0033148688171058894, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.004535121014341712, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.017093233363702894, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.016059687682427465, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.01454321009106934, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.012925150608643889, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.011294921541120858, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.009493851349689067, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.007843263139948249, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.006816396389622241, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.006429885883117095, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.006292391855968162, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.00621877996774856, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.006118656350299716, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.006033615272608586, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.0058896336954785515, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.005755089704762213, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.005623027951805852, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.0054572409248794425, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.005247500260011293, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.005020310487598181, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.0047917297868116295, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.004474512687011156, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.004129571994344588, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.003703238606613013, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0031787957236520015, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0025662337729590945, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0017703272620565257, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0011294273353269092, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0007344980240668519, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0004338342439041298, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0002619100321408041, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.00017736473678269248, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0001375832438179714, "train/grad_032_lr3.7e+00_wd1.0e+00": 9.570436921762848e-05, "train/grad_033_lr4.3e+00_wd1.0e+00": 7.513144452730103e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 4.826405145308854e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 2.6353162324390667e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 2.1809643342056705e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 9.417806846748755e-06, "train/grad_038_lr9.8e+00_wd1.0e+00": 7.748988413105656e-06, "train/grad_039_lr1.2e+01_wd1.0e+00": 9.286092365774394e-06, "train/grad_040_lr1.4e+01_wd1.0e+00": 8.439726645901165e-06, "train/grad_041_lr1.6e+01_wd1.0e+00": 5.589540926840884e-06, "train/grad_042_lr1.9e+01_wd1.0e+00": 4.884129964277424e-05, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0001148795918839032, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.000602872372336699, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0017515505155078826, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0016565552915264747, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.001726259710624702, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0033875750413533863, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.8414685130119324, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.7087028622627258, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.516462504863739, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.3617664575576782, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.25485676527023315, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.16540038585662842, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.10827186703681946, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.079338438808918, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.06426312029361725, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.0564783476293087, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.051686227321624756, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.04704923555254936, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.04403567686676979, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.04077146574854851, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.03857151418924332, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.0367666557431221, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.03510785102844238, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.033363115042448044, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.03192850947380066, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.030661337077617645, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.029751410707831383, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.029294628649950027, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.029296644032001495, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.02928810752928257, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.029251432046294212, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.028946086764335632, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.028855782002210617, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.028939414769411087, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.029104579240083694, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.029047757387161255, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.029201854020357132, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.02894558198750019, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.02881590463221073, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.028393320739269257, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.029476113617420197, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.043542515486478806, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.06935586035251617, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.06336798518896103, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.1080893874168396, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.16733436286449432, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.15175476670265198, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.13118743896484375, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.33103832602500916, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.3165411353111267, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.5065642595291138, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.9343894720077515, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.6706051826477051, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.8011378645896912, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.9893374443054199, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.8923611111111112, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.910218253968254, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.9231150793650794, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.9377480158730159, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9563492063492064, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.9729662698412699, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9786706349206349, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.9806547619047619, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9813988095238095, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9833829365079365, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9851190476190477, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9856150793650794, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9861111111111112, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9866071428571429, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9875992063492064, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9875992063492064, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9878472222222222, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9878472222222222, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.988343253968254, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9893353174603174, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9898313492063492, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9908234126984127, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9910714285714286, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9905753968253969, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9908234126984127, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9903273809523809, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9903273809523809, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9908234126984127, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9905753968253969, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9908234126984127, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9913194444444444, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9910714285714286, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9910714285714286, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9915674603174603, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9905753968253969, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9898313492063492, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9893353174603174, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9885912698412699, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9888392857142857, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9878472222222222, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9900793650793651, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9895833333333334, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9875992063492064, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9895833333333334, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9903273809523809, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9861111111111112, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.986359126984127, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9878472222222222, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9856150793650794, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.877385871002837, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.8993834036256875, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.916025476257697, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.9332916993073626, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.9530338620223896, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.9703956261314216, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.9762082931999626, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9780594271158197, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9793429653681072, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9811556170383421, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9829967670901711, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9841754184798506, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9850591136841962, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.985781870148018, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9869592475605925, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9870491408737008, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9864202894037533, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.986391730736739, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9866136818671581, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9874899635795616, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9884640877809168, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9896425950193918, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9904649294983912, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9899108042309102, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9899972319346476, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9897703128220308, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9901317613135904, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9905379265059567, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9903150973940212, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9904031243772632, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9907633944632572, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9905840287560146, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.990627590171236, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9910044279162704, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9909503683821852, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9896315726413251, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9886340201520794, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.98718159727054, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9886382858584035, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.986703149559929, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9890016900999321, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.987832210849967, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9863497556068784, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9883393386608071, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9887253059888435, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.985119274849703, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9858183001981873, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9862999910540646, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9846973122888057, "id_best": 33, "lr_best": 0.00129, "wd_best": 0.05, "train/loss_best": 0.00017387677915394305, "validation/loss_best": 0.028393320739269257, "validation/acc_best": 0.9915674603174603, "validation/f1_best": 0.9910044279162704} +{"epoch": 15, "train/lr": 6.196799573888289e-05, "train/loss": 0.07402870135381817, "train/grad": 0.043177534732967614, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.8326663017272949, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.6996964359283447, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.5073398208618164, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.35496784150600436, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.251712207198143, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.16557743817567824, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.11095237731933594, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.08392925627529621, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.0697237135283649, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.06232967061921954, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.057582795480266215, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.05267600865103304, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.04909004302695394, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.04495482640340924, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.0415085475705564, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.03867429479956627, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.03536766894161701, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.03179914010688663, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.028130816277116538, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.024906250238418578, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.021117989718914033, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.0174570603761822, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.013684460083022714, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.010001819850876927, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.006668794928118587, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.003837448339909315, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.002297719744965434, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0014925440959632397, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0008833534922450781, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0005386825650930405, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.00037556529976427554, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.00029283895157277583, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.0002036150451749563, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.00014217767864465713, "train/loss_034_lr5.1e+00_wd1.0e+00": 9.610640816390514e-05, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.912597894668579e-05, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.278202213346958e-05, "train/loss_037_lr8.3e+00_wd1.0e+00": 7.863165810704231e-06, "train/loss_038_lr9.8e+00_wd1.0e+00": 4.775971174240112e-06, "train/loss_039_lr1.2e+01_wd1.0e+00": 7.654717192053795e-06, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.685496583580971e-06, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.1710263788700105e-06, "train/loss_042_lr1.9e+01_wd1.0e+00": 9.792856872081757e-08, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.0362157374620437e-06, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.7957634776830674e-06, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.0011586800869554281, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.8072001188993452e-06, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.0003500681184232235, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.003126285383477807, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.016748223179019986, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.01575805388856679, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.014253769181668758, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.012598641235381364, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.010972337231505662, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.009222402607556433, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.007724548252299428, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.006912111162673682, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.006579147474840283, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.006435429673874751, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.006342685827985406, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.006219727019779384, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.006118969332310371, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.0059621840587351475, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.005807148973690346, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.005673132552183233, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.0054998921588412485, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.005301960479991976, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.005064284999098163, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.0048345934455574025, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.004518687404779485, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.0041535442622262055, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.00370527467559441, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0031332462452701294, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.00242953194945585, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.001593729893102136, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.000998332219060103, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0006533750129892724, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0003839997862723976, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.00023055166289850603, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.00015879688426821304, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0001256497054623651, "train/grad_032_lr3.7e+00_wd1.0e+00": 8.769607484737207e-05, "train/grad_033_lr4.3e+00_wd1.0e+00": 6.638884525727917e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 4.678458398245766e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 2.4698034908112733e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 2.0188374429856993e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 9.466526170136269e-06, "train/grad_038_lr9.8e+00_wd1.0e+00": 6.6055831680964515e-06, "train/grad_039_lr1.2e+01_wd1.0e+00": 1.0572100000997457e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 4.660686736297175e-06, "train/grad_041_lr1.6e+01_wd1.0e+00": 2.7988745198494207e-06, "train/grad_042_lr1.9e+01_wd1.0e+00": 5.398979654767098e-07, "train/grad_043_lr2.2e+01_wd1.0e+00": 3.1347719551241882e-06, "train/grad_044_lr2.6e+01_wd1.0e+00": 2.148459623671092e-05, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0007216305854703265, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0002414007977899701, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.00039185873029634063, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.001422000706278996, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.8214002847671509, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.688775360584259, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.4969496428966522, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.3450321555137634, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.24245333671569824, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.15657441318035126, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.10280894488096237, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.07669093459844589, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.06282918155193329, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.05549774691462517, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.05100450664758682, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.04654393345117569, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.043661557137966156, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.0406913161277771, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.03850681334733963, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.03683449327945709, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.035087160766124725, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.033241745084524155, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.03153035417199135, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.030210083350539207, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.028859920799732208, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.028023667633533478, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.027633536607027054, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.027694012969732285, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.027930716052651405, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.028318751603364944, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.02856920287013054, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.028785111382603645, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.02912074699997902, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.029252249747514725, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.029316376894712448, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.02892104908823967, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.028813514858484268, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.02824103645980358, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.029579423367977142, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.04302605986595154, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.06849991530179977, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.062329746782779694, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.10664187371730804, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.1630709171295166, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.1478232443332672, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.12831692397594452, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.3187752962112427, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.3033938705921173, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.47642001509666443, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.8380295038223267, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.5830053687095642, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.6703932285308838, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.928609311580658, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.8940972222222222, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.9072420634920635, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.9241071428571429, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.9392361111111112, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9590773809523809, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.9734623015873016, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9784226190476191, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.9806547619047619, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9821428571428571, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.984375, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9851190476190477, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9858630952380952, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9866071428571429, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9868551587301587, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9875992063492064, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9878472222222222, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9878472222222222, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9873511904761905, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9878472222222222, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9888392857142857, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9895833333333334, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9900793650793651, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9900793650793651, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9893353174603174, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9898313492063492, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9900793650793651, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9900793650793651, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9903273809523809, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9910714285714286, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9905753968253969, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9908234126984127, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9910714285714286, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9910714285714286, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9918154761904762, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9905753968253969, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9898313492063492, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9893353174603174, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9885912698412699, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9888392857142857, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9878472222222222, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9900793650793651, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9893353174603174, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9878472222222222, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9893353174603174, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9900793650793651, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9858630952380952, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9878472222222222, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9871031746031746, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9873511904761905, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.8795267730466243, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.8963729206187662, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.9167378240721975, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.9350355830538758, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.9558856449623842, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.9703964659677128, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.9761228058807464, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9781522346015864, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9804589629217388, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9824149295798883, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9830892987354279, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9848796263213928, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.985598831986105, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9859645581802199, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9865944902861459, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9867804276806915, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.986422181881615, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.985658580822953, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9864330918386782, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9874423282542344, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.988284571994348, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.989288058620711, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.989298596344935, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9885100943182508, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.98886978222424, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9895925977806959, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9899543248836975, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9901313559154687, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.990805588625482, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9902237087917082, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9904046400259102, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9905840287560146, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.990627590171236, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9912757681093697, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9909503683821852, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9896315726413251, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9886340201520794, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.98718159727054, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9886382858584035, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.986703149559929, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9890016900999321, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9874741583996302, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9865292232725101, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9881592674367882, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9884471702600989, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9857964184674831, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9868413670425094, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9859142047728975, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9857913922535192, "id_best": 33, "lr_best": 0.00129, "wd_best": 0.05, "train/loss_best": 0.00014217767864465713, "validation/loss_best": 0.02824103645980358, "validation/acc_best": 0.9918154761904762, "validation/f1_best": 0.9912757681093697} +{"epoch": 16, "train/lr": 3.870405029380728e-05, "train/loss": 0.07346980167552829, "train/grad": 0.0415457980055362, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.8214118671417237, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.6891285991668701, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.49792208671569826, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.3480553364753723, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.24757854789495468, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.1638805928826332, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.11132671874016524, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.08590736791491509, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.07235801526345313, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.06505118233151734, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.06034028064459562, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.05519756750203669, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.05145916145294905, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.04696423452347517, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.043294410910457375, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.04015953917987645, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.036507615419104696, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.032680496014654635, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.028689065370708703, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.025235472228378058, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.0212108738347888, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.017263155933469533, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.013230536663904786, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.009371595177799463, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.006084325304254889, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.003453827574849129, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.0020615749061107637, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0013565034326165914, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0008356150332838297, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0005213010404258966, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0003638162836432457, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.0002895347215235233, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.00020450125448405742, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.00015095703303813935, "train/loss_034_lr5.1e+00_wd1.0e+00": 9.896300733089447e-05, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.8723088800907134e-05, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.6293879598379134e-05, "train/loss_037_lr8.3e+00_wd1.0e+00": 7.281973958015442e-06, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.1415017545223237e-06, "train/loss_039_lr1.2e+01_wd1.0e+00": 4.051290452480316e-06, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.919567584991455e-06, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.466488465666771e-06, "train/loss_042_lr1.9e+01_wd1.0e+00": 8.203089237213135e-08, "train/loss_043_lr2.2e+01_wd1.0e+00": 1.3862084597349167e-06, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.514570951461792e-10, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.4417731910943985e-05, "train/loss_046_lr3.6e+01_wd1.0e+00": 7.6335147023201e-05, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.440391272306442e-05, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.00016659654676914214, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.016741826911456884, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.015728930905461312, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.014199415072798729, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.012513903416693211, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.010933369789272547, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.009251334120053798, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.0077358042425476016, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.006904205080354586, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.006553100565797649, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.006389852142892778, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.006271662602666765, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.006111618472496048, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.0059810284903505815, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.00577863052545581, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.005590873678738717, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.005423979950719513, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.005213725247886032, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.004979901775659528, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.004708690978004597, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.0044576197769492865, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.004114882498834049, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.0037327638556598685, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0032828622216766233, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.002730970945849549, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.002072471242136089, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0013211233074980554, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.000830967922374839, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.000554465300137963, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.00034105059366083877, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.00021089250956720206, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0001468490621618912, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.00011630277546373691, "train/grad_032_lr3.7e+00_wd1.0e+00": 8.204342479757543e-05, "train/grad_033_lr4.3e+00_wd1.0e+00": 6.326068953569574e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 4.456494601086547e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 2.4023556883374653e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 1.790355116744413e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 9.228958199705935e-06, "train/grad_038_lr9.8e+00_wd1.0e+00": 6.9172906070377024e-06, "train/grad_039_lr1.2e+01_wd1.0e+00": 1.1837133786491619e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 3.961997593852099e-06, "train/grad_041_lr1.6e+01_wd1.0e+00": 2.420339038770815e-06, "train/grad_042_lr1.9e+01_wd1.0e+00": 4.5905128978451624e-07, "train/grad_043_lr2.2e+01_wd1.0e+00": 2.767213051548281e-06, "train/grad_044_lr2.6e+01_wd1.0e+00": 1.437111673787772e-06, "train/grad_045_lr3.1e+01_wd1.0e+00": 7.9071392260491e-05, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.00022057339548139636, "train/grad_047_lr4.3e+01_wd1.0e+00": 8.96537455494459e-05, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.00022405739603069473, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.8090861439704895, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.6766261458396912, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.48502251505851746, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.33511534333229065, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.23485629260540009, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.1513892263174057, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.09967093169689178, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.07502587884664536, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.06189119070768356, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.05486026406288147, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.050502579659223557, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.04611710458993912, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.043282922357320786, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.0402863435447216, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.03812377154827118, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.036485057324171066, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.034707631915807724, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.03301156684756279, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.03145964816212654, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.03028671257197857, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.0291654821485281, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.028404943645000458, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.028133580461144447, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.028230490162968636, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.028508802875876427, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.02875623106956482, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.02898506075143814, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.029183531180024147, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.02931990474462509, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.02931656502187252, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.029341919347643852, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.029059583321213722, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.02892640419304371, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.028303636237978935, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.029591431841254234, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.04288904741406441, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.06791254132986069, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.0619877427816391, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.10507851094007492, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.16122718155384064, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.14499738812446594, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.12664592266082764, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.31089913845062256, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.295382559299469, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.4613885283470154, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.8134203553199768, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.5526400804519653, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.645378828048706, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.8779320120811462, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.8963293650793651, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.9094742063492064, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.9248511904761905, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.9427083333333334, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9600694444444444, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.9742063492063492, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9784226190476191, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.980406746031746, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9816468253968254, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9848710317460317, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9851190476190477, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9861111111111112, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.986359126984127, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9868551587301587, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9868551587301587, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9878472222222222, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9880952380952381, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9875992063492064, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9878472222222222, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9885912698412699, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9903273809523809, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9905753968253969, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9893353174603174, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9900793650793651, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9900793650793651, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9898313492063492, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9900793650793651, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9900793650793651, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9910714285714286, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9910714285714286, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9910714285714286, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9913194444444444, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9908234126984127, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9905753968253969, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9898313492063492, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9893353174603174, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9885912698412699, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9888392857142857, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9875992063492064, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9903273809523809, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9893353174603174, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9878472222222222, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9895833333333334, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9905753968253969, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9858630952380952, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9880952380952381, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9880952380952381, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9866071428571429, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.8818610728574835, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.8988977908275282, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.9180910494951553, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.9387668621464013, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.9568208248787597, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.9713096166789954, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.9761259662007966, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9779729122528713, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9793830720472453, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9828194807794078, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9830892987354279, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9852370675821016, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9854179603890791, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9859645581802199, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9859635978858394, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9871410023216892, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9871413346555871, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9860243223172706, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9860744927457921, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9867068620380893, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9897228114841267, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.990005351151129, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9883436144527006, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9892506165593938, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9894139101320457, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9892284182340069, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9899543248836975, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9899555958861609, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.990805588625482, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.990805588625482, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9905840287560146, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.990807630972379, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9904482231845693, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9916310630039791, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9909503683821852, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9896315726413251, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9886340201520794, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.98718159727054, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9886382858584035, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9865237660201074, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.989181179843154, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9874741583996302, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9865292232725101, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9883393386608071, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9888063102141432, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9857964184674831, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9870244324306344, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9868268670059974, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9856108113595483, "id_best": 33, "lr_best": 0.00129, "wd_best": 0.05, "train/loss_best": 0.00015095703303813935, "validation/loss_best": 0.028303636237978935, "validation/acc_best": 0.9920634920634921, "validation/f1_best": 0.9916310630039791} +{"epoch": 17, "train/lr": 2.030750443206766e-05, "train/loss": 0.07250005273148417, "train/grad": 0.04016761022619903, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.8126824378967286, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.6804408740997314, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.4896216893196106, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.34116805911064146, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.24226051926612854, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.15984334103763104, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.10857629772275686, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.08433773849159479, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.07130706551484764, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.06421988237649202, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.0596125506889075, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.054779244605451825, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.05115772692486644, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.04688705198466778, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.04341417166404426, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.04040542397648096, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.03692839850671589, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.03314372702501714, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.0292443370539695, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.025720932288095355, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.02158391969278455, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.017524192547425627, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.01333450771868229, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.009282224150374531, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.005904835667461156, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.0032424639724195005, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.001918496210128069, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.001258575627580285, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0007813099958002567, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0004889964498579502, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0003456452488899231, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.00027208254672586915, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.00019066113978624344, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.00013788885436952114, "train/loss_034_lr5.1e+00_wd1.0e+00": 9.063786827027798e-05, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.8766274228692056e-05, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.729297451674938e-05, "train/loss_037_lr8.3e+00_wd1.0e+00": 6.319954991340637e-06, "train/loss_038_lr9.8e+00_wd1.0e+00": 4.433710128068924e-06, "train/loss_039_lr1.2e+01_wd1.0e+00": 5.8472994714975355e-06, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.6352517306804656e-06, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.0939966887235642e-06, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.6799196600914e-07, "train/loss_043_lr2.2e+01_wd1.0e+00": 1.9636284559965132e-06, "train/loss_044_lr2.6e+01_wd1.0e+00": 1.1870637536048889e-07, "train/loss_045_lr3.1e+01_wd1.0e+00": 7.495284080505371e-08, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.3605843782424924e-07, "train/loss_047_lr4.3e+01_wd1.0e+00": 5.384255200624466e-07, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.0003151386696845293, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.016149138328619302, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.015174192562699317, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.013725322200916707, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.012125432561151683, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.010571287013590336, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008851488779764622, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.0073764132894575596, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.006640515088802204, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.006328255684347823, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.006171503332443535, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.006066878959536552, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.0059367727470817045, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.005807932707248256, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.00562938074755948, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.005461859059869312, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.005311425909458194, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.005122662534704432, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.004899997933243867, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.004667399346944876, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.004427035298140254, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.0041121385057340375, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.003751067161501851, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0032901056294213048, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.002705896719417069, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0020120537262118886, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0012501528298525955, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0007749243000944262, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0005163253576756688, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.00032050124884335673, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.00020122133932090947, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.00014173992728956365, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.00011191430146482162, "train/grad_032_lr3.7e+00_wd1.0e+00": 8.136398596889194e-05, "train/grad_033_lr4.3e+00_wd1.0e+00": 6.251524229355709e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 4.392920166651493e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 2.509332025079303e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 1.7524974993117224e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 9.202095856675197e-06, "train/grad_038_lr9.8e+00_wd1.0e+00": 6.522699203838685e-06, "train/grad_039_lr1.2e+01_wd1.0e+00": 1.0164437960537632e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 4.683376835480687e-06, "train/grad_041_lr1.6e+01_wd1.0e+00": 2.144937463507276e-06, "train/grad_042_lr1.9e+01_wd1.0e+00": 4.7201742372964846e-07, "train/grad_043_lr2.2e+01_wd1.0e+00": 5.033236242654092e-06, "train/grad_044_lr2.6e+01_wd1.0e+00": 9.63768125113667e-07, "train/grad_045_lr3.1e+01_wd1.0e+00": 2.9081382450100114e-07, "train/grad_046_lr3.6e+01_wd1.0e+00": 2.199348864726294e-06, "train/grad_047_lr4.3e+01_wd1.0e+00": 4.3836631486196366e-06, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0002863178081669082, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.802613377571106, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.6701768040657043, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.4789677560329437, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.33001255989074707, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.23099267482757568, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.1488044261932373, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.09806013107299805, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.07427476346492767, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.06144113093614578, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.05448341369628906, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.05014194920659065, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.04589017108082771, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.04290606081485748, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.04000178724527359, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.03775354102253914, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.03617415204644203, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.03435622155666351, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.032721519470214844, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.031126365065574646, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.029936404898762703, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.028765810653567314, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.02812536060810089, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.027875220403075218, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.0278491098433733, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.02814669907093048, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.028348242864012718, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.028547734022140503, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.02875608392059803, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.029083365574479103, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.029098447412252426, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.029230035841464996, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.028884895145893097, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.02882232703268528, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.028250670060515404, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.02952755056321621, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.042742546647787094, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.06772945076227188, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.06153300404548645, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.10425413399934769, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.16016295552253723, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.14406822621822357, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.12548445165157318, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.3067242503166199, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.2915128469467163, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.4546196460723877, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.7992242574691772, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.5424454808235168, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.6325555443763733, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.8584199547767639, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.8970734126984127, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.9109623015873016, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.9253472222222222, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.9432043650793651, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9605654761904762, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.9742063492063492, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9789186507936508, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.9806547619047619, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9821428571428571, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9848710317460317, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9848710317460317, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9861111111111112, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9868551587301587, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9868551587301587, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9871031746031746, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9873511904761905, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9875992063492064, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9878472222222222, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9878472222222222, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9890873015873016, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9903273809523809, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9905753968253969, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9895833333333334, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9903273809523809, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9900793650793651, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9900793650793651, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9895833333333334, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9900793650793651, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9910714285714286, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9910714285714286, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9910714285714286, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9913194444444444, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9910714285714286, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9918154761904762, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9908234126984127, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9898313492063492, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9893353174603174, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9885912698412699, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9888392857142857, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9878472222222222, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9903273809523809, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9893353174603174, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9878472222222222, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9895833333333334, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9903273809523809, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9858630952380952, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.988343253968254, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9880952380952381, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9868551587301587, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.8833440668622166, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.9006219924591027, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.9183080195828214, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.9392467349660624, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.9574028943611153, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.9713921838748503, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.9764809353053914, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9781522346015864, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9801035745510537, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9828173434964446, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9829076944450149, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9850591136841962, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9861447203375165, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9859625039940857, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9861419437078472, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9867785802868043, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9862399719441012, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9862031263318338, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9860269981676749, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9874274349320451, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9897228114841267, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.990005351151129, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9885229495114756, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9895933096150664, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9894139101320457, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9897695612448836, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9894108439328719, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9899526728099565, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9908053618330244, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9905825131073676, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9905840287560146, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9907633944632572, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.990627590171236, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.991451057577697, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9911297519220069, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9896315726413251, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9886340201520794, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.98718159727054, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9886382858584035, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.986703149559929, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.989181179843154, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9874741583996302, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9865292232725101, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9883393386608071, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9886267614289129, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9857964184674831, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9875750314309331, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9868268670059974, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.985430796877561, "id_best": 33, "lr_best": 0.00129, "wd_best": 0.05, "train/loss_best": 0.00013788885436952114, "validation/loss_best": 0.028250670060515404, "validation/acc_best": 0.9918154761904762, "validation/f1_best": 0.991451057577697} +{"epoch": 18, "train/lr": 7.5829098008590064e-06, "train/loss": 0.06988491287454962, "train/grad": 0.040071774180978535, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.7991717433929444, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.6682220935821533, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.47934436559677124, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.33261088371276853, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.23484149932861328, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.1533700218051672, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.10315079163759946, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.07941628457978368, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.06653046233579517, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.05944082826375961, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.05484715878032148, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.049968929728493094, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.046482508666813374, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.04238978828303516, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.039027637224644425, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.036307362942025065, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.03308892349712551, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.02962934226728976, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.026032701060175897, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.022919889148324726, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.019209435414522885, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.015533073619008065, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.01177247698418796, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.008138474142178893, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.0051441413257271055, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.0028326373267918824, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.0016914656478911637, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0011174983251839876, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0006929890345782042, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.000431826077401638, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0003052608296275139, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.0002444526180624962, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.00017181091941893101, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.00012868218123912811, "train/loss_034_lr5.1e+00_wd1.0e+00": 8.377020247280598e-05, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.2251058146357534e-05, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.650744117796421e-05, "train/loss_037_lr8.3e+00_wd1.0e+00": 6.552478298544884e-06, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.356458619236946e-06, "train/loss_039_lr1.2e+01_wd1.0e+00": 4.38367947936058e-06, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.9058119505643844e-06, "train/loss_041_lr1.6e+01_wd1.0e+00": 8.445419371128083e-07, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.423712819814682e-07, "train/loss_043_lr2.2e+01_wd1.0e+00": 1.689111813902855e-06, "train/loss_044_lr2.6e+01_wd1.0e+00": 1.9436702132225036e-07, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.684071660041809e-08, "train/loss_046_lr3.6e+01_wd1.0e+00": 6.107054650783539e-07, "train/loss_047_lr4.3e+01_wd1.0e+00": 1.1221226304769515e-06, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.986060619354248e-09, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.01644409100525081, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.015446233837865293, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.013936539492569865, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.01226536302594468, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.010679364535026253, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008939582586754114, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.007355576055124402, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.006574750859290362, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.006259929998777807, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.006108843729016371, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.005996569126727991, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.005850896044285037, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.005714462299365551, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.005512549871054944, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.005328231758030597, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.005160084311501123, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.004948198071215302, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.00471127270750003, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.004442270993604325, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.004187183291651309, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.0038567656241502847, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.0034789808724599424, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.003011286751498119, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.002428023127868073, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0017785389629352722, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0010954149571443849, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0006931882155549829, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0004688008961693413, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.00029563219994088285, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.00018635182968864683, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.00013238824073141586, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.00010549640762747003, "train/grad_032_lr3.7e+00_wd1.0e+00": 7.623316231274658e-05, "train/grad_033_lr4.3e+00_wd1.0e+00": 5.855003435385697e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 4.0476701236684676e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 2.21309056127339e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 1.700638503993268e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 8.435228286141072e-06, "train/grad_038_lr9.8e+00_wd1.0e+00": 5.604433352559049e-06, "train/grad_039_lr1.2e+01_wd1.0e+00": 8.758883712512625e-06, "train/grad_040_lr1.4e+01_wd1.0e+00": 4.254034134053672e-06, "train/grad_041_lr1.6e+01_wd1.0e+00": 2.477062290743473e-06, "train/grad_042_lr1.9e+01_wd1.0e+00": 4.938255549727157e-07, "train/grad_043_lr2.2e+01_wd1.0e+00": 3.805101089661586e-06, "train/grad_044_lr2.6e+01_wd1.0e+00": 4.3436469586938606e-07, "train/grad_045_lr3.1e+01_wd1.0e+00": 1.0756265829306382e-07, "train/grad_046_lr3.6e+01_wd1.0e+00": 1.7341591942234251e-06, "train/grad_047_lr4.3e+01_wd1.0e+00": 3.173911257912444e-06, "train/grad_048_lr5.0e+01_wd1.0e+00": 4.5480203745773735e-08, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.8001871109008789, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.6677199006080627, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.47650787234306335, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.3280022442340851, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.22946271300315857, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.14775948226451874, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.09744202345609665, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.07396671921014786, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.06121143698692322, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.05437304079532623, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.0500139556825161, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.0457521490752697, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.04287342354655266, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.039972882717847824, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.03775906562805176, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.036188654601573944, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.034298866987228394, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.032709572464227676, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.03110741265118122, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.02991606667637825, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.02870618924498558, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.02809063345193863, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.02783178724348545, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.02791942097246647, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.02818435989320278, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.028448158875107765, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.028758538886904716, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.028996571898460388, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.029264431446790695, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.029246948659420013, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.029322009533643723, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.029013877734541893, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.028853880241513252, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.028266185894608498, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.029602961614727974, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.04272087290883064, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.06767668575048447, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.06152552366256714, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.10415954142808914, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.15948812663555145, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.1438315063714981, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.12476124614477158, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.30521324276924133, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.28941696882247925, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.45236897468566895, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.7941012978553772, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.537955641746521, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.6273870468139648, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.8504834771156311, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.8968253968253969, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.9122023809523809, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.9260912698412699, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.9427083333333334, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9605654761904762, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.9742063492063492, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9784226190476191, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.9806547619047619, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.982390873015873, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9848710317460317, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9848710317460317, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9858630952380952, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9866071428571429, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9868551587301587, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9873511904761905, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9880952380952381, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9878472222222222, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9878472222222222, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9880952380952381, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9888392857142857, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9903273809523809, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9903273809523809, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9895833333333334, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9903273809523809, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9900793650793651, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9900793650793651, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9898313492063492, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9903273809523809, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9910714285714286, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9908234126984127, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9910714285714286, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9910714285714286, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9913194444444444, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9908234126984127, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9898313492063492, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9893353174603174, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9885912698412699, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9888392857142857, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9878472222222222, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9903273809523809, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9895833333333334, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9880952380952381, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9893353174603174, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9905753968253969, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.986359126984127, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.988343253968254, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9880952380952381, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9868551587301587, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.8827532888466985, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.9018582301603699, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.9196558136865788, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.9387094377590838, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.9571371379548432, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.970947119408315, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.9761228058807464, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9781522346015864, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9806843991445646, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9828194807794078, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9829076944450149, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9848796263213928, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9859651779488329, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9859625039940857, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.986689451256802, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9873205049980799, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9864202894037533, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9862037506976163, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9863864363212104, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9875686059701814, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9897228114841267, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9897788804780797, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9888912472941195, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9895933096150664, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9894139101320457, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9897695612448836, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9895901453370085, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9901787851379291, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.990805588625482, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9904473110080726, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9905840287560146, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9905840287560146, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9908076135026278, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9916310630039791, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9911297519220069, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9896315726413251, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9886340201520794, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.98718159727054, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9886382858584035, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.986703149559929, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.989181179843154, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9876543312960893, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9867095099955252, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9881592674367882, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9888073429251042, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9861347080489683, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9875750314309331, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9868268670059974, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.985430796877561, "id_best": 33, "lr_best": 0.00129, "wd_best": 0.05, "train/loss_best": 0.00012868218123912811, "validation/loss_best": 0.028266185894608498, "validation/acc_best": 0.9920634920634921, "validation/f1_best": 0.9916310630039791} +{"epoch": 19, "train/lr": 1.0867618231465446e-06, "train/loss": 0.07054889725521207, "train/grad": 0.03975460382178426, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.8024456214904785, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.6706119108200074, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.48043606996536253, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.33303934931755064, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.23538390457630157, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.15442319460213183, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.10470987774431706, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.08134363010525704, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.06865276535972953, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.061663154726848, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.05711438482627273, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.05219499758444726, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.04854676615446806, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.044223020626232026, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.04062717075459659, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.037615054016932846, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.03407710548490286, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.030358829591423272, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.026632692441344263, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.02336886855773628, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.01956562776118517, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.015886378232389687, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.012041554907336832, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.008361811600625515, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.005325316535308957, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.002976249512284994, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.0017873498518019915, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.001191426133736968, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0007458201982080936, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.00047048711217939854, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.00033576544374227526, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.00026650881394743917, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.00018447467125952245, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.00013531527481973172, "train/loss_034_lr5.1e+00_wd1.0e+00": 8.714042603969575e-05, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.121309913694858e-05, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.5384526923298834e-05, "train/loss_037_lr8.3e+00_wd1.0e+00": 6.23888336122036e-06, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.0054617673158647e-06, "train/loss_039_lr1.2e+01_wd1.0e+00": 4.485528916120529e-06, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.659689635038376e-06, "train/loss_041_lr1.6e+01_wd1.0e+00": 8.046906441450119e-07, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.7317011952400207e-07, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.0263809710741043e-06, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.123415470123291e-09, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.4437904357910155e-08, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.297626972198486e-07, "train/loss_047_lr4.3e+01_wd1.0e+00": 7.57351517677307e-08, "train/loss_048_lr5.0e+01_wd1.0e+00": 1.679174602031708e-08, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.016118063279427587, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.015124825513921678, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.013639645767398179, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.012009734436869621, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.010439246757887304, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008749043371062725, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.0072904240852221846, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.0065957971685566006, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.0063244458951521665, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.006198399608256295, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.006118383078137413, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.005994191682548262, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.005880243049468845, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.005694490898167715, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.005521623123786412, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.005350866172811948, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.005137057655811077, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.004879242584429448, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.004591425229882588, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.004313998186480603, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.0039526971576560755, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.003557987174463051, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.003066863303538412, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.002472323068723199, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0018051874628508813, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0011095674116040754, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.000695945871193544, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0004690439548176073, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.00029441538047649376, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0001858171526419028, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.00013209990176164864, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0001054646043030516, "train/grad_032_lr3.7e+00_wd1.0e+00": 7.604078947338167e-05, "train/grad_033_lr4.3e+00_wd1.0e+00": 5.910216895586018e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 4.075394761116513e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 2.3032916184941853e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 1.6927161639372913e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 8.107998555452884e-06, "train/grad_038_lr9.8e+00_wd1.0e+00": 5.516074416327594e-06, "train/grad_039_lr1.2e+01_wd1.0e+00": 1.0487528581028095e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 4.669192946136869e-06, "train/grad_041_lr1.6e+01_wd1.0e+00": 2.3361263461975535e-06, "train/grad_042_lr1.9e+01_wd1.0e+00": 6.715046560690792e-07, "train/grad_043_lr2.2e+01_wd1.0e+00": 4.671139809829112e-06, "train/grad_044_lr2.6e+01_wd1.0e+00": 1.84872798591804e-06, "train/grad_045_lr3.1e+01_wd1.0e+00": 2.066159902437705e-07, "train/grad_046_lr3.6e+01_wd1.0e+00": 1.5756206695336146e-06, "train/grad_047_lr4.3e+01_wd1.0e+00": 3.2828100213341714e-06, "train/grad_048_lr5.0e+01_wd1.0e+00": 7.020259695405755e-08, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.7997999787330627, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.6674829125404358, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.47622907161712646, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.3276842534542084, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.2293643206357956, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.14755044877529144, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.09730836749076843, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.0739280954003334, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.0612054206430912, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.0543358251452446, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.04999842122197151, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.04572818800806999, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.04288497567176819, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.03995625674724579, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.037740062922239304, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.03615560010075569, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.03427714854478836, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.032670460641384125, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.031122371554374695, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.029896264895796776, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.028698835521936417, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.02804039791226387, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.02777286060154438, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.0278998464345932, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.028130432590842247, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.028458228334784508, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.028649404644966125, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.028999237343668938, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.029223140329122543, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.029203886166214943, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.029255904257297516, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.02896575629711151, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.028882425278425217, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.028295176103711128, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.02961849980056286, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.04272373393177986, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.0677473247051239, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.0614972859621048, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.10424266010522842, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.15945102274417877, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.14366210997104645, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.12483260035514832, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.3050835132598877, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.28967759013175964, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.45191502571105957, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.7931026816368103, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.5372844934463501, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.6268081665039062, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.8488762378692627, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.8975694444444444, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.9112103174603174, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.9253472222222222, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.9432043650793651, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9603174603174603, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.9742063492063492, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9784226190476191, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.9806547619047619, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9826388888888888, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9848710317460317, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9848710317460317, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9858630952380952, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9866071428571429, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9868551587301587, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9873511904761905, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9880952380952381, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9878472222222222, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9878472222222222, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9880952380952381, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9888392857142857, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9903273809523809, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9903273809523809, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9895833333333334, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9903273809523809, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9900793650793651, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9900793650793651, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9898313492063492, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9900793650793651, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9910714285714286, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9908234126984127, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9910714285714286, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9910714285714286, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9913194444444444, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9908234126984127, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9898313492063492, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9893353174603174, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9885912698412699, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9888392857142857, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9878472222222222, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9903273809523809, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9895833333333334, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9880952380952381, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9893353174603174, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9905753968253969, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9861111111111112, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.988343253968254, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9880952380952381, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9871031746031746, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.8833179823442595, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.9009410643087906, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.9185685990753466, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.9392628894020114, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.9568698418334952, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.970947119408315, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.9761228058807464, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9781522346015864, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9807862444602607, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9828194807794078, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9829076944450149, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9848796263213928, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9859651779488329, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9859625039940857, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.986689451256802, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9873205049980799, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9864202894037533, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9862037506976163, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9865574233639087, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9875686059701814, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9897228114841267, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9897788804780797, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9888912472941195, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9895933096150664, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9894139101320457, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9897695612448836, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9895901453370085, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9899991656425106, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.990805588625482, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9904473110080726, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9905840287560146, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9905840287560146, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9908076135026278, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9916310630039791, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9911297519220069, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9896315726413251, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9886340201520794, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.98718159727054, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9886382858584035, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.986703149559929, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.989181179843154, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9876543312960893, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9867095099955252, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9881592674367882, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9888073429251042, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9859547843164966, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9875750314309331, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9868268670059974, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9856107475582987, "id_best": 33, "lr_best": 0.00129, "wd_best": 0.05, "train/loss_best": 0.00013531527481973172, "validation/loss_best": 0.028295176103711128, "validation/acc_best": 0.9920634920634921, "validation/f1_best": 0.9916310630039791} diff --git a/input_space_v3/flat_lr1e-3_3/eval_v2/nsd_cococlip__patch__attn/config.yaml b/input_space_v3/flat_lr1e-3_3/eval_v2/nsd_cococlip__patch__attn/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..e132b6ec6233820d8522635d78b894219c9e69a6 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_3/eval_v2/nsd_cococlip__patch__attn/config.yaml @@ -0,0 +1,96 @@ +output_root: experiments/input_space_v3/output +name_prefix: eval_probe +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_3; eval v2 (nsd_cococlip patch attn) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +dataset_kwargs: {} +classifier_kwargs: + embed_dim: null + dropout: 0.0 + xavier_init: true + norm: true +lr_scale_grid: +- 0.02 +- 0.023 +- 0.028 +- 0.033 +- 0.038 +- 0.045 +- 0.053 +- 0.062 +- 0.074 +- 0.087 +- 0.1 +- 0.12 +- 0.14 +- 0.17 +- 0.2 +- 0.23 +- 0.27 +- 0.32 +- 0.38 +- 0.44 +- 0.52 +- 0.61 +- 0.72 +- 0.85 +- 1 +- 1.2 +- 1.4 +- 1.6 +- 1.9 +- 2.3 +- 2.7 +- 3.1 +- 3.7 +- 4.3 +- 5.1 +- 6 +- 7.1 +- 8.3 +- 9.8 +- 12 +- 14 +- 16 +- 19 +- 22 +- 26 +- 31 +- 36 +- 43 +- 50 +wd_scale_grid: +- 1.0 +num_workers: 8 +prefetch_factor: null +balanced_sampling: false +epochs: 20 +steps_per_epoch: 200 +batch_size: 64 +accum_iter: 2 +lr: 0.0003 +warmup_epochs: 5 +no_decay: false +weight_decay: 0.05 +clip_grad: 1.0 +metrics: +- acc +- f1 +cv_metric: acc +early_stopping: true +amp: true +device: cuda +seed: 4466 +debug: false +wandb: false +wandb_entity: null +wandb_project: fMRI-fm-eval +name: input_space_v3/flat_lr1e-3_3/eval_v2/nsd_cococlip__patch__attn +model: flat_mae +representation: patch +classifier: attn +dataset: nsd_cococlip +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/eval_v2/nsd_cococlip__patch__attn +remote_dir: null diff --git a/input_space_v3/flat_lr1e-3_3/eval_v2/nsd_cococlip__patch__attn/eval_log.json b/input_space_v3/flat_lr1e-3_3/eval_v2/nsd_cococlip__patch__attn/eval_log.json new file mode 100644 index 0000000000000000000000000000000000000000..9910fc026f4014e2b43409fd0d66160ed988068f --- /dev/null +++ b/input_space_v3/flat_lr1e-3_3/eval_v2/nsd_cococlip__patch__attn/eval_log.json @@ -0,0 +1 @@ +{"eval/epoch": 17, "eval/id_best": 19, "eval/lr_best": 0.00013199999999999998, "eval/wd_best": 0.05, "eval/train/loss": 1.9963765144348145, "eval/train/acc": 0.4035772457666185, "eval/train/acc_std": 0.002417427898649545, "eval/train/f1": 0.3508025821249845, "eval/train/f1_std": 0.0026154400097303404, "eval/validation/loss": 2.354748487472534, "eval/validation/acc": 0.2884828349944629, "eval/validation/acc_std": 0.005438188046729676, "eval/validation/f1": 0.233313540014799, "eval/validation/f1_std": 0.005111000740674951, "eval/test/loss": 2.2413253784179688, "eval/test/acc": 0.3053803339517625, "eval/test/acc_std": 0.0053639577275507696, "eval/test/f1": 0.23928091924666636, "eval/test/f1_std": 0.005518093774506598, "eval/testid/loss": 2.242295503616333, "eval/testid/acc": 0.31116252168883746, "eval/testid/acc_std": 0.00557001135477462, "eval/testid/f1": 0.25579144024712414, "eval/testid/f1_std": 0.005364933853345691} diff --git a/input_space_v3/flat_lr1e-3_3/eval_v2/nsd_cococlip__patch__attn/eval_log_best.json b/input_space_v3/flat_lr1e-3_3/eval_v2/nsd_cococlip__patch__attn/eval_log_best.json new file mode 100644 index 0000000000000000000000000000000000000000..c06f6b3bd99f89f8ed279425b54473901c564513 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_3/eval_v2/nsd_cococlip__patch__attn/eval_log_best.json @@ -0,0 +1 @@ +{"eval/best/epoch": 17, "eval/best/id_best": 19, "eval/best/lr_best": 0.00013199999999999998, "eval/best/wd_best": 0.05, "eval/best/train/loss": 1.9963765144348145, "eval/best/train/acc": 0.4035772457666185, "eval/best/train/acc_std": 0.002417427898649545, "eval/best/train/f1": 0.3508025821249845, "eval/best/train/f1_std": 0.0026154400097303404, "eval/best/validation/loss": 2.354748487472534, "eval/best/validation/acc": 0.2884828349944629, "eval/best/validation/acc_std": 0.005438188046729676, "eval/best/validation/f1": 0.233313540014799, "eval/best/validation/f1_std": 0.005111000740674951, "eval/best/test/loss": 2.2413253784179688, "eval/best/test/acc": 0.3053803339517625, "eval/best/test/acc_std": 0.0053639577275507696, "eval/best/test/f1": 0.23928091924666636, "eval/best/test/f1_std": 0.005518093774506598, "eval/best/testid/loss": 2.242295503616333, "eval/best/testid/acc": 0.31116252168883746, "eval/best/testid/acc_std": 0.00557001135477462, "eval/best/testid/f1": 0.25579144024712414, "eval/best/testid/f1_std": 0.005364933853345691} diff --git a/input_space_v3/flat_lr1e-3_3/eval_v2/nsd_cococlip__patch__attn/eval_log_last.json b/input_space_v3/flat_lr1e-3_3/eval_v2/nsd_cococlip__patch__attn/eval_log_last.json new file mode 100644 index 0000000000000000000000000000000000000000..56d25d15bb5b3bab3aa525f35c95007cb1b1b0ae --- /dev/null +++ b/input_space_v3/flat_lr1e-3_3/eval_v2/nsd_cococlip__patch__attn/eval_log_last.json @@ -0,0 +1 @@ +{"eval/last/epoch": 19, "eval/last/id_best": 18, "eval/last/lr_best": 0.00011399999999999999, "eval/last/wd_best": 0.05, "eval/last/train/loss": 2.0677294731140137, "eval/last/train/acc": 0.3816958111804296, "eval/last/train/acc_std": 0.002298841491400537, "eval/last/train/f1": 0.3248512556847351, "eval/last/train/f1_std": 0.002499011793692615, "eval/last/validation/loss": 2.3487589359283447, "eval/last/validation/acc": 0.28755998523440385, "eval/last/validation/acc_std": 0.005421359234990114, "eval/last/validation/f1": 0.23108099248291247, "eval/last/validation/f1_std": 0.005037634026923443, "eval/last/test/loss": 2.2427444458007812, "eval/last/test/acc": 0.3046382189239332, "eval/last/test/acc_std": 0.005169761778811452, "eval/last/test/f1": 0.23459085400118465, "eval/last/test/f1_std": 0.005289930412422146, "eval/last/testid/loss": 2.2671167850494385, "eval/last/testid/acc": 0.31058415268941586, "eval/last/testid/acc_std": 0.005754149235931524, "eval/last/testid/f1": 0.2520116743100901, "eval/last/testid/f1_std": 0.0055101488080264195} diff --git a/input_space_v3/flat_lr1e-3_3/eval_v2/nsd_cococlip__patch__attn/eval_table.csv b/input_space_v3/flat_lr1e-3_3/eval_v2/nsd_cococlip__patch__attn/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..662b84b5510f400a92517e8e77a2324827ff2fc5 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_3/eval_v2/nsd_cococlip__patch__attn/eval_table.csv @@ -0,0 +1,5 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,patch,attn,nsd_cococlip,best,17,0.00013199999999999998,0.05,19,"[0.44, 1.0]",train,1.9963765144348145,0.4035772457666185,0.002417427898649545,0.3508025821249845,0.0026154400097303404 +flat_mae,patch,attn,nsd_cococlip,best,17,0.00013199999999999998,0.05,19,"[0.44, 1.0]",validation,2.354748487472534,0.2884828349944629,0.005438188046729676,0.233313540014799,0.005111000740674951 +flat_mae,patch,attn,nsd_cococlip,best,17,0.00013199999999999998,0.05,19,"[0.44, 1.0]",test,2.2413253784179688,0.3053803339517625,0.0053639577275507696,0.23928091924666636,0.005518093774506598 +flat_mae,patch,attn,nsd_cococlip,best,17,0.00013199999999999998,0.05,19,"[0.44, 1.0]",testid,2.242295503616333,0.31116252168883746,0.00557001135477462,0.25579144024712414,0.005364933853345691 diff --git a/input_space_v3/flat_lr1e-3_3/eval_v2/nsd_cococlip__patch__attn/eval_table_best.csv b/input_space_v3/flat_lr1e-3_3/eval_v2/nsd_cococlip__patch__attn/eval_table_best.csv new file mode 100644 index 0000000000000000000000000000000000000000..662b84b5510f400a92517e8e77a2324827ff2fc5 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_3/eval_v2/nsd_cococlip__patch__attn/eval_table_best.csv @@ -0,0 +1,5 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,patch,attn,nsd_cococlip,best,17,0.00013199999999999998,0.05,19,"[0.44, 1.0]",train,1.9963765144348145,0.4035772457666185,0.002417427898649545,0.3508025821249845,0.0026154400097303404 +flat_mae,patch,attn,nsd_cococlip,best,17,0.00013199999999999998,0.05,19,"[0.44, 1.0]",validation,2.354748487472534,0.2884828349944629,0.005438188046729676,0.233313540014799,0.005111000740674951 +flat_mae,patch,attn,nsd_cococlip,best,17,0.00013199999999999998,0.05,19,"[0.44, 1.0]",test,2.2413253784179688,0.3053803339517625,0.0053639577275507696,0.23928091924666636,0.005518093774506598 +flat_mae,patch,attn,nsd_cococlip,best,17,0.00013199999999999998,0.05,19,"[0.44, 1.0]",testid,2.242295503616333,0.31116252168883746,0.00557001135477462,0.25579144024712414,0.005364933853345691 diff --git a/input_space_v3/flat_lr1e-3_3/eval_v2/nsd_cococlip__patch__attn/eval_table_last.csv b/input_space_v3/flat_lr1e-3_3/eval_v2/nsd_cococlip__patch__attn/eval_table_last.csv new file mode 100644 index 0000000000000000000000000000000000000000..ead4a342ffadd67ab027184c47b49302f267b3fc --- /dev/null +++ b/input_space_v3/flat_lr1e-3_3/eval_v2/nsd_cococlip__patch__attn/eval_table_last.csv @@ -0,0 +1,5 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,patch,attn,nsd_cococlip,last,19,0.00011399999999999999,0.05,18,"[0.38, 1.0]",train,2.0677294731140137,0.3816958111804296,0.002298841491400537,0.3248512556847351,0.002499011793692615 +flat_mae,patch,attn,nsd_cococlip,last,19,0.00011399999999999999,0.05,18,"[0.38, 1.0]",validation,2.3487589359283447,0.28755998523440385,0.005421359234990114,0.23108099248291247,0.005037634026923443 +flat_mae,patch,attn,nsd_cococlip,last,19,0.00011399999999999999,0.05,18,"[0.38, 1.0]",test,2.2427444458007812,0.3046382189239332,0.005169761778811452,0.23459085400118465,0.005289930412422146 +flat_mae,patch,attn,nsd_cococlip,last,19,0.00011399999999999999,0.05,18,"[0.38, 1.0]",testid,2.2671167850494385,0.31058415268941586,0.005754149235931524,0.2520116743100901,0.0055101488080264195 diff --git a/input_space_v3/flat_lr1e-3_3/eval_v2/nsd_cococlip__patch__attn/log.txt b/input_space_v3/flat_lr1e-3_3/eval_v2/nsd_cococlip__patch__attn/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..6490df26461e748d9c1916cbec8ce0b82136da40 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_3/eval_v2/nsd_cococlip__patch__attn/log.txt @@ -0,0 +1,967 @@ +fMRI foundation model probe eval +version: 0.1.dev86+gf97f52698 +sha: bcce2b486277d3a5b520775efd9cdf1a2affce36, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-04-08 20:31:09 +config: +output_root: experiments/input_space_v3/output +name_prefix: eval_probe +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_3; eval v2 (nsd_cococlip patch attn) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +dataset_kwargs: {} +classifier_kwargs: + embed_dim: null + dropout: 0.0 + xavier_init: true + norm: true +lr_scale_grid: +- 0.02 +- 0.023 +- 0.028 +- 0.033 +- 0.038 +- 0.045 +- 0.053 +- 0.062 +- 0.074 +- 0.087 +- 0.1 +- 0.12 +- 0.14 +- 0.17 +- 0.2 +- 0.23 +- 0.27 +- 0.32 +- 0.38 +- 0.44 +- 0.52 +- 0.61 +- 0.72 +- 0.85 +- 1 +- 1.2 +- 1.4 +- 1.6 +- 1.9 +- 2.3 +- 2.7 +- 3.1 +- 3.7 +- 4.3 +- 5.1 +- 6 +- 7.1 +- 8.3 +- 9.8 +- 12 +- 14 +- 16 +- 19 +- 22 +- 26 +- 31 +- 36 +- 43 +- 50 +wd_scale_grid: +- 1.0 +num_workers: 8 +prefetch_factor: null +balanced_sampling: false +epochs: 20 +steps_per_epoch: 200 +batch_size: 64 +accum_iter: 2 +lr: 0.0003 +warmup_epochs: 5 +no_decay: false +weight_decay: 0.05 +clip_grad: 1.0 +metrics: +- acc +- f1 +cv_metric: acc +early_stopping: true +amp: true +device: cuda +seed: 4466 +debug: false +wandb: false +wandb_entity: null +wandb_project: fMRI-fm-eval +name: input_space_v3/flat_lr1e-3_3/eval_v2/nsd_cococlip__patch__attn +model: flat_mae +representation: patch +classifier: attn +dataset: nsd_cococlip +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/eval_v2/nsd_cococlip__patch__attn +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=True, reg_tokens=0, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: nsd_cococlip (flat) +train (n=32539): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'run', 'trial_id', 'nsd_id', 'category_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 32539 +}), + labels=[ 3 4 5 6 10 11 17 18 19 20 22 23 25 30 31 33 36 37 38 53 55 59 61 74], + counts=[1286 1180 1639 1868 834 824 1026 1042 913 1853 1503 2092 1001 1410 + 794 1241 1904 1872 2267 1428 889 904 1447 1322] +) + +validation (n=5418): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'run', 'trial_id', 'nsd_id', 'category_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 5418 +}), + labels=[ 3 4 5 6 10 11 17 18 19 20 22 23 25 30 31 33 36 37 38 53 55 59 61 74], + counts=[197 161 276 345 126 142 143 185 112 295 285 387 169 250 159 193 316 334 + 343 215 172 141 226 246] +) + +test (n=5390): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'run', 'trial_id', 'nsd_id', 'category_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 5390 +}), + labels=[ 3 4 5 6 10 11 17 18 19 20 22 23 25 30 31 33 36 37 38 53 55 59 61 74], + counts=[202 172 274 298 144 180 134 182 186 293 218 343 165 185 140 177 346 333 + 345 271 165 140 251 246] +) + +testid (n=5187): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'run', 'trial_id', 'nsd_id', 'category_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 5187 +}), + labels=[ 3 4 5 6 10 11 17 18 19 20 22 23 25 30 31 33 36 37 38 53 55 59 61 74], + counts=[197 159 267 273 123 153 175 184 139 310 215 386 153 230 118 192 330 306 + 349 223 143 127 249 186] +) + +running backbone on example batch to get embedding dim +embedding feature dim (patch): 768 +initializing sweep of classifier heads +classifiers: +ModuleList( + (0-48): 49 x AttnPoolClassifier( + (kv): Linear(in_features=768, out_features=1536, bias=True) + (linear): Linear(in_features=768, out_features=24, bias=True) + ) +) +classifier params (train): 58.8M (58.8M) +setting up optimizer +total batch size: 128 = 64 bs per gpu x 2 accum +lr: 3.00e-04 +full schedule: epochs = 20 (steps = 4000) (decay = True) +warmup: epochs = 5 (steps = 1000) +start training for 20 epochs +train: [0] [ 0/400] eta: 0:23:08 lr: nan time: 3.4710 data: 2.9820 max mem: 21740 +train: [0] [ 20/400] eta: 0:03:53 lr: 0.000003 loss: 3.2046 (3.2029) grad: 0.1737 (0.1754) time: 0.4729 data: 0.0045 max mem: 22448 +train: [0] [ 40/400] eta: 0:03:11 lr: 0.000006 loss: 3.1912 (3.1925) grad: 0.1718 (0.1754) time: 0.4445 data: 0.0038 max mem: 22448 +train: [0] [ 60/400] eta: 0:02:52 lr: 0.000009 loss: 3.1820 (3.1895) grad: 0.1679 (0.1735) time: 0.4582 data: 0.0040 max mem: 22448 +train: [0] [ 80/400] eta: 0:02:37 lr: 0.000012 loss: 3.1689 (3.1834) grad: 0.1640 (0.1709) time: 0.4481 data: 0.0040 max mem: 22448 +train: [0] [100/400] eta: 0:02:25 lr: 0.000015 loss: 3.1649 (3.1804) grad: 0.1600 (0.1686) time: 0.4504 data: 0.0044 max mem: 22448 +train: [0] [120/400] eta: 0:02:13 lr: 0.000018 loss: 3.1649 (3.1780) grad: 0.1487 (0.1659) time: 0.4390 data: 0.0041 max mem: 22448 +train: [0] [140/400] eta: 0:02:03 lr: 0.000021 loss: 3.1613 (3.1757) grad: 0.1539 (0.1652) time: 0.4615 data: 0.0041 max mem: 22448 +train: [0] [160/400] eta: 0:01:53 lr: 0.000024 loss: 3.1543 (3.1721) grad: 0.1664 (0.1661) time: 0.4558 data: 0.0041 max mem: 22448 +train: [0] [180/400] eta: 0:01:43 lr: 0.000027 loss: 3.1421 (3.1697) grad: 0.1613 (0.1656) time: 0.4504 data: 0.0041 max mem: 22448 +train: [0] [200/400] eta: 0:01:33 lr: 0.000030 loss: 3.1565 (3.1689) grad: 0.1538 (0.1640) time: 0.4474 data: 0.0041 max mem: 22448 +train: [0] [220/400] eta: 0:01:23 lr: 0.000033 loss: 3.1587 (3.1680) grad: 0.1514 (0.1629) time: 0.4509 data: 0.0042 max mem: 22448 +train: [0] [240/400] eta: 0:01:14 lr: 0.000036 loss: 3.1517 (3.1662) grad: 0.1514 (0.1620) time: 0.4562 data: 0.0042 max mem: 22448 +train: [0] [260/400] eta: 0:01:05 lr: 0.000039 loss: 3.1416 (3.1642) grad: 0.1486 (0.1609) time: 0.4522 data: 0.0041 max mem: 22448 +train: [0] [280/400] eta: 0:00:55 lr: 0.000042 loss: 3.1275 (3.1613) grad: 0.1481 (0.1602) time: 0.4435 data: 0.0042 max mem: 22448 +train: [0] [300/400] eta: 0:00:46 lr: 0.000045 loss: 3.1145 (3.1572) grad: 0.1499 (0.1600) time: 0.4420 data: 0.0040 max mem: 22448 +train: [0] [320/400] eta: 0:00:36 lr: 0.000048 loss: 3.1074 (3.1542) grad: 0.1575 (0.1603) time: 0.4542 data: 0.0041 max mem: 22448 +train: [0] [340/400] eta: 0:00:27 lr: 0.000051 loss: 3.1119 (3.1511) grad: 0.1640 (0.1603) time: 0.4574 data: 0.0041 max mem: 22448 +train: [0] [360/400] eta: 0:00:18 lr: 0.000054 loss: 3.0856 (3.1471) grad: 0.1640 (0.1609) time: 0.4629 data: 0.0042 max mem: 22448 +train: [0] [380/400] eta: 0:00:09 lr: 0.000057 loss: 3.0828 (3.1438) grad: 0.1722 (0.1616) time: 0.4668 data: 0.0043 max mem: 22448 +train: [0] [399/400] eta: 0:00:00 lr: 0.000060 loss: 3.0772 (3.1410) grad: 0.1765 (0.1622) time: 0.4648 data: 0.0042 max mem: 22448 +train: [0] Total time: 0:03:04 (0.4618 s / it) +train: [0] Summary: lr: 0.000060 loss: 3.0772 (3.1410) grad: 0.1765 (0.1622) +eval (validation): [0] [ 0/85] eta: 0:04:45 time: 3.3575 data: 3.0631 max mem: 22448 +eval (validation): [0] [20/85] eta: 0:00:31 time: 0.3472 data: 0.0062 max mem: 22448 +eval (validation): [0] [40/85] eta: 0:00:18 time: 0.3461 data: 0.0036 max mem: 22448 +eval (validation): [0] [60/85] eta: 0:00:09 time: 0.3409 data: 0.0041 max mem: 22448 +eval (validation): [0] [80/85] eta: 0:00:01 time: 0.3269 data: 0.0039 max mem: 22448 +eval (validation): [0] [84/85] eta: 0:00:00 time: 0.3167 data: 0.0038 max mem: 22448 +eval (validation): [0] Total time: 0:00:32 (0.3773 s / it) +cv: [0] best hparam: (31, 1.0) (045) ('045_lr3.1e+01_wd1.0e+00') loss: 2.610 acc: 0.232 f1: 0.154 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/eval_v2/nsd_cococlip__patch__attn/checkpoint-best.pth +train: [1] [ 0/400] eta: 0:23:07 lr: nan time: 3.4685 data: 3.1268 max mem: 22448 +train: [1] [ 20/400] eta: 0:03:40 lr: 0.000063 loss: 3.0298 (3.0375) grad: 0.1699 (0.1693) time: 0.4355 data: 0.0030 max mem: 22448 +train: [1] [ 40/400] eta: 0:03:04 lr: 0.000066 loss: 3.0336 (3.0344) grad: 0.1633 (0.1660) time: 0.4438 data: 0.0037 max mem: 22448 +train: [1] [ 60/400] eta: 0:02:48 lr: 0.000069 loss: 3.0250 (3.0235) grad: 0.1628 (0.1666) time: 0.4619 data: 0.0044 max mem: 22448 +train: [1] [ 80/400] eta: 0:02:35 lr: 0.000072 loss: 3.0115 (3.0239) grad: 0.1685 (0.1696) time: 0.4557 data: 0.0042 max mem: 22448 +train: [1] [100/400] eta: 0:02:23 lr: 0.000075 loss: 3.0063 (3.0175) grad: 0.1700 (0.1708) time: 0.4509 data: 0.0039 max mem: 22448 +train: [1] [120/400] eta: 0:02:12 lr: 0.000078 loss: 3.0010 (3.0149) grad: 0.1725 (0.1714) time: 0.4430 data: 0.0040 max mem: 22448 +train: [1] [140/400] eta: 0:02:02 lr: 0.000081 loss: 3.0010 (3.0125) grad: 0.1756 (0.1722) time: 0.4484 data: 0.0042 max mem: 22448 +train: [1] [160/400] eta: 0:01:52 lr: 0.000084 loss: 2.9937 (3.0123) grad: 0.1756 (0.1722) time: 0.4539 data: 0.0042 max mem: 22448 +train: [1] [180/400] eta: 0:01:42 lr: 0.000087 loss: 2.9988 (3.0124) grad: 0.1698 (0.1728) time: 0.4423 data: 0.0039 max mem: 22448 +train: [1] [200/400] eta: 0:01:32 lr: 0.000090 loss: 2.9944 (3.0103) grad: 0.1788 (0.1738) time: 0.4397 data: 0.0040 max mem: 22448 +train: [1] [220/400] eta: 0:01:22 lr: 0.000093 loss: 2.9490 (3.0027) grad: 0.1897 (0.1760) time: 0.4407 data: 0.0040 max mem: 22448 +train: [1] [240/400] eta: 0:01:13 lr: 0.000096 loss: 2.9416 (2.9994) grad: 0.1913 (0.1763) time: 0.4425 data: 0.0040 max mem: 22448 +train: [1] [260/400] eta: 0:01:04 lr: 0.000099 loss: 2.9586 (2.9979) grad: 0.1824 (0.1773) time: 0.4474 data: 0.0042 max mem: 22448 +train: [1] [280/400] eta: 0:00:54 lr: 0.000102 loss: 2.9508 (2.9939) grad: 0.1826 (0.1775) time: 0.4398 data: 0.0042 max mem: 22448 +train: [1] [300/400] eta: 0:00:45 lr: 0.000105 loss: 2.9499 (2.9927) grad: 0.1826 (0.1782) time: 0.4508 data: 0.0041 max mem: 22448 +train: [1] [320/400] eta: 0:00:36 lr: 0.000108 loss: 2.9397 (2.9886) grad: 0.1873 (0.1790) time: 0.4354 data: 0.0040 max mem: 22448 +train: [1] [340/400] eta: 0:00:27 lr: 0.000111 loss: 2.9200 (2.9848) grad: 0.1873 (0.1796) time: 0.4384 data: 0.0042 max mem: 22448 +train: [1] [360/400] eta: 0:00:18 lr: 0.000114 loss: 2.9228 (2.9827) grad: 0.1881 (0.1801) time: 0.4421 data: 0.0040 max mem: 22448 +train: [1] [380/400] eta: 0:00:09 lr: 0.000117 loss: 2.9332 (2.9788) grad: 0.1881 (0.1809) time: 0.4528 data: 0.0043 max mem: 22448 +train: [1] [399/400] eta: 0:00:00 lr: 0.000120 loss: 2.9120 (2.9772) grad: 0.1959 (0.1822) time: 0.4498 data: 0.0040 max mem: 22448 +train: [1] Total time: 0:03:01 (0.4534 s / it) +train: [1] Summary: lr: 0.000120 loss: 2.9120 (2.9772) grad: 0.1959 (0.1822) +eval (validation): [1] [ 0/85] eta: 0:04:35 time: 3.2389 data: 2.9652 max mem: 22448 +eval (validation): [1] [20/85] eta: 0:00:31 time: 0.3389 data: 0.0048 max mem: 22448 +eval (validation): [1] [40/85] eta: 0:00:18 time: 0.3332 data: 0.0035 max mem: 22448 +eval (validation): [1] [60/85] eta: 0:00:09 time: 0.3579 data: 0.0043 max mem: 22448 +eval (validation): [1] [80/85] eta: 0:00:01 time: 0.3207 data: 0.0041 max mem: 22448 +eval (validation): [1] [84/85] eta: 0:00:00 time: 0.3142 data: 0.0040 max mem: 22448 +eval (validation): [1] Total time: 0:00:31 (0.3740 s / it) +cv: [1] best hparam: (12, 1.0) (039) ('039_lr1.2e+01_wd1.0e+00') loss: 2.438 acc: 0.257 f1: 0.190 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/eval_v2/nsd_cococlip__patch__attn/checkpoint-best.pth +train: [2] [ 0/400] eta: 0:22:46 lr: nan time: 3.4151 data: 3.0344 max mem: 22448 +train: [2] [ 20/400] eta: 0:03:44 lr: 0.000123 loss: 2.9229 (2.9123) grad: 0.2222 (0.2210) time: 0.4503 data: 0.0035 max mem: 22448 +train: [2] [ 40/400] eta: 0:03:07 lr: 0.000126 loss: 2.9093 (2.9120) grad: 0.2117 (0.2142) time: 0.4464 data: 0.0039 max mem: 22448 +train: [2] [ 60/400] eta: 0:02:50 lr: 0.000129 loss: 2.9067 (2.9113) grad: 0.2042 (0.2109) time: 0.4620 data: 0.0041 max mem: 22448 +train: [2] [ 80/400] eta: 0:02:36 lr: 0.000132 loss: 2.9000 (2.9087) grad: 0.2033 (0.2100) time: 0.4475 data: 0.0042 max mem: 22448 +train: [2] [100/400] eta: 0:02:23 lr: 0.000135 loss: 2.8716 (2.8997) grad: 0.2126 (0.2123) time: 0.4460 data: 0.0042 max mem: 22448 +train: [2] [120/400] eta: 0:02:13 lr: 0.000138 loss: 2.8689 (2.8969) grad: 0.2400 (0.2209) time: 0.4509 data: 0.0040 max mem: 22448 +train: [2] [140/400] eta: 0:02:02 lr: 0.000141 loss: 2.9461 (2.9385) grad: 0.3106 (0.2979) time: 0.4518 data: 0.0041 max mem: 22448 +WARNING: classifier 48 (50, 1.0) diverged (loss=79.70 > 63.56) at step 477. Freezing. +train: [2] [160/400] eta: 0:01:52 lr: 0.000144 loss: 3.2155 (3.0142) grad: 0.8229 (0.4418) time: 0.4362 data: 0.0040 max mem: 22448 +train: [2] [180/400] eta: 0:01:42 lr: 0.000147 loss: 2.8684 (2.9953) grad: 0.2236 (0.4164) time: 0.4361 data: 0.0040 max mem: 22448 +train: [2] [200/400] eta: 0:01:32 lr: 0.000150 loss: 2.8584 (2.9823) grad: 0.2211 (0.3984) time: 0.4390 data: 0.0041 max mem: 22448 +train: [2] [220/400] eta: 0:01:22 lr: 0.000153 loss: 2.8906 (2.9757) grad: 0.2406 (0.3878) time: 0.4386 data: 0.0040 max mem: 22448 +train: [2] [240/400] eta: 0:01:13 lr: 0.000156 loss: 2.9425 (2.9921) grad: 0.3226 (0.4287) time: 0.4420 data: 0.0041 max mem: 22448 +WARNING: classifier 47 (43, 1.0) diverged (loss=65.12 > 63.56) at step 528. Freezing. +train: [2] [260/400] eta: 0:01:03 lr: 0.000159 loss: 3.4055 (3.0371) grad: 1.0516 (0.4863) time: 0.4448 data: 0.0040 max mem: 22448 +train: [2] [280/400] eta: 0:00:54 lr: 0.000162 loss: 2.9092 (3.0248) grad: 0.2502 (0.4682) time: 0.4362 data: 0.0040 max mem: 22448 +train: [2] [300/400] eta: 0:00:45 lr: 0.000165 loss: 2.8472 (3.0129) grad: 0.2253 (0.4516) time: 0.4442 data: 0.0040 max mem: 22448 +train: [2] [320/400] eta: 0:00:36 lr: 0.000168 loss: 2.8499 (3.0026) grad: 0.2209 (0.4375) time: 0.4341 data: 0.0040 max mem: 22448 +train: [2] [340/400] eta: 0:00:27 lr: 0.000171 loss: 2.8499 (2.9956) grad: 0.2356 (0.4261) time: 0.4359 data: 0.0041 max mem: 22448 +train: [2] [360/400] eta: 0:00:18 lr: 0.000174 loss: 2.8428 (2.9885) grad: 0.2344 (0.4151) time: 0.4383 data: 0.0039 max mem: 22448 +train: [2] [380/400] eta: 0:00:09 lr: 0.000177 loss: 2.9027 (2.9840) grad: 0.2453 (0.4080) time: 0.4455 data: 0.0042 max mem: 22448 +train: [2] [399/400] eta: 0:00:00 lr: 0.000180 loss: 2.9333 (2.9841) grad: 0.3160 (0.4174) time: 0.4474 data: 0.0040 max mem: 22448 +train: [2] Total time: 0:03:00 (0.4514 s / it) +train: [2] Summary: lr: 0.000180 loss: 2.9333 (2.9841) grad: 0.3160 (0.4174) +eval (validation): [2] [ 0/85] eta: 0:04:43 time: 3.3396 data: 3.0655 max mem: 22448 +eval (validation): [2] [20/85] eta: 0:00:32 time: 0.3619 data: 0.0033 max mem: 22448 +eval (validation): [2] [40/85] eta: 0:00:18 time: 0.3280 data: 0.0035 max mem: 22448 +eval (validation): [2] [60/85] eta: 0:00:09 time: 0.3459 data: 0.0042 max mem: 22448 +eval (validation): [2] [80/85] eta: 0:00:01 time: 0.3320 data: 0.0041 max mem: 22448 +eval (validation): [2] [84/85] eta: 0:00:00 time: 0.3135 data: 0.0040 max mem: 22448 +eval (validation): [2] Total time: 0:00:32 (0.3785 s / it) +cv: [2] best hparam: (3.1, 1.0) (031) ('031_lr3.1e+00_wd1.0e+00') loss: 2.417 acc: 0.272 f1: 0.199 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/eval_v2/nsd_cococlip__patch__attn/checkpoint-best.pth +train: [3] [ 0/400] eta: 0:22:39 lr: nan time: 3.3983 data: 3.0598 max mem: 22448 +WARNING: classifier 46 (36, 1.0) diverged (loss=65.84 > 63.56) at step 604. Freezing. +train: [3] [ 20/400] eta: 0:03:39 lr: 0.000183 loss: 2.8630 (3.1076) grad: 0.2047 (0.7085) time: 0.4356 data: 0.0038 max mem: 22448 +train: [3] [ 40/400] eta: 0:03:03 lr: 0.000186 loss: 2.8396 (2.9862) grad: 0.2188 (0.4638) time: 0.4366 data: 0.0038 max mem: 22448 +train: [3] [ 60/400] eta: 0:02:47 lr: 0.000189 loss: 2.8349 (2.9319) grad: 0.2151 (0.3797) time: 0.4625 data: 0.0044 max mem: 22448 +train: [3] [ 80/400] eta: 0:02:33 lr: 0.000192 loss: 2.8080 (2.9053) grad: 0.2068 (0.3362) time: 0.4382 data: 0.0043 max mem: 22448 +train: [3] [100/400] eta: 0:02:21 lr: 0.000195 loss: 2.7989 (2.8848) grad: 0.1997 (0.3097) time: 0.4325 data: 0.0043 max mem: 22448 +train: [3] [120/400] eta: 0:02:10 lr: 0.000198 loss: 2.7975 (2.8695) grad: 0.2044 (0.2932) time: 0.4344 data: 0.0042 max mem: 22448 +train: [3] [140/400] eta: 0:02:00 lr: 0.000201 loss: 2.8170 (2.8626) grad: 0.2169 (0.2841) time: 0.4482 data: 0.0041 max mem: 22448 +train: [3] [160/400] eta: 0:01:50 lr: 0.000204 loss: 2.8277 (2.8617) grad: 0.2242 (0.2767) time: 0.4344 data: 0.0043 max mem: 22448 +train: [3] [180/400] eta: 0:01:40 lr: 0.000207 loss: 2.8177 (2.8537) grad: 0.2197 (0.2698) time: 0.4400 data: 0.0042 max mem: 22448 +train: [3] [200/400] eta: 0:01:30 lr: 0.000210 loss: 2.8039 (2.8506) grad: 0.2171 (0.2647) time: 0.4392 data: 0.0041 max mem: 22448 +train: [3] [220/400] eta: 0:01:21 lr: 0.000213 loss: 2.8048 (2.8463) grad: 0.2233 (0.2610) time: 0.4438 data: 0.0041 max mem: 22448 +train: [3] [240/400] eta: 0:01:12 lr: 0.000216 loss: 2.8048 (2.8433) grad: 0.2300 (0.2584) time: 0.4492 data: 0.0043 max mem: 22448 +train: [3] [260/400] eta: 0:01:03 lr: 0.000219 loss: 2.8078 (2.8385) grad: 0.2192 (0.2552) time: 0.4399 data: 0.0041 max mem: 22448 +train: [3] [280/400] eta: 0:00:54 lr: 0.000222 loss: 2.7814 (2.8343) grad: 0.2236 (0.2527) time: 0.4314 data: 0.0041 max mem: 22448 +train: [3] [300/400] eta: 0:00:44 lr: 0.000225 loss: 2.7844 (2.8321) grad: 0.2194 (0.2504) time: 0.4355 data: 0.0041 max mem: 22448 +train: [3] [320/400] eta: 0:00:35 lr: 0.000228 loss: 2.7721 (2.8284) grad: 0.2194 (0.2494) time: 0.4320 data: 0.0041 max mem: 22448 +train: [3] [340/400] eta: 0:00:26 lr: 0.000231 loss: 2.7977 (2.8278) grad: 0.2338 (0.2496) time: 0.4377 data: 0.0042 max mem: 22448 +train: [3] [360/400] eta: 0:00:17 lr: 0.000234 loss: 2.8399 (2.8322) grad: 0.2669 (0.2552) time: 0.4422 data: 0.0041 max mem: 22448 +train: [3] [380/400] eta: 0:00:08 lr: 0.000237 loss: 2.9503 (2.8645) grad: 0.4955 (0.3078) time: 0.4499 data: 0.0042 max mem: 22448 +WARNING: classifier 45 (31, 1.0) diverged (loss=79.70 > 63.56) at step 791. Freezing. +WARNING: classifier 44 (26, 1.0) diverged (loss=72.95 > 63.56) at step 799. Freezing. +train: [3] [399/400] eta: 0:00:00 lr: 0.000240 loss: 3.4154 (2.9041) grad: 1.1341 (0.3729) time: 0.4448 data: 0.0041 max mem: 22448 +train: [3] Total time: 0:02:59 (0.4481 s / it) +train: [3] Summary: lr: 0.000240 loss: 3.4154 (2.9041) grad: 1.1341 (0.3729) +eval (validation): [3] [ 0/85] eta: 0:04:41 time: 3.3102 data: 3.0245 max mem: 22448 +eval (validation): [3] [20/85] eta: 0:00:31 time: 0.3437 data: 0.0120 max mem: 22448 +eval (validation): [3] [40/85] eta: 0:00:18 time: 0.3277 data: 0.0036 max mem: 22448 +eval (validation): [3] [60/85] eta: 0:00:09 time: 0.3406 data: 0.0039 max mem: 22448 +eval (validation): [3] [80/85] eta: 0:00:01 time: 0.3268 data: 0.0042 max mem: 22448 +eval (validation): [3] [84/85] eta: 0:00:00 time: 0.3159 data: 0.0040 max mem: 22448 +eval (validation): [3] Total time: 0:00:31 (0.3720 s / it) +cv: [3] best hparam: (3.7, 1.0) (032) ('032_lr3.7e+00_wd1.0e+00') loss: 2.414 acc: 0.276 f1: 0.201 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/eval_v2/nsd_cococlip__patch__attn/checkpoint-best.pth +train: [4] [ 0/400] eta: 0:23:00 lr: nan time: 3.4501 data: 3.0607 max mem: 22448 +train: [4] [ 20/400] eta: 0:03:46 lr: 0.000243 loss: 2.6992 (2.7355) grad: 0.2014 (0.2065) time: 0.4529 data: 0.0038 max mem: 22448 +train: [4] [ 40/400] eta: 0:03:05 lr: 0.000246 loss: 2.7429 (2.7505) grad: 0.2019 (0.2071) time: 0.4304 data: 0.0041 max mem: 22448 +train: [4] [ 60/400] eta: 0:02:48 lr: 0.000249 loss: 2.7518 (2.7574) grad: 0.2039 (0.2067) time: 0.4574 data: 0.0042 max mem: 22448 +train: [4] [ 80/400] eta: 0:02:34 lr: 0.000252 loss: 2.7579 (2.7597) grad: 0.2043 (0.2070) time: 0.4411 data: 0.0041 max mem: 22448 +train: [4] [100/400] eta: 0:02:21 lr: 0.000255 loss: 2.8250 (2.7837) grad: 0.2165 (0.2458) time: 0.4346 data: 0.0041 max mem: 22448 +train: [4] [120/400] eta: 0:02:10 lr: 0.000258 loss: 2.9753 (2.8566) grad: 0.6336 (0.3880) time: 0.4338 data: 0.0040 max mem: 22448 +WARNING: classifier 43 (22, 1.0) diverged (loss=83.29 > 63.56) at step 869. Freezing. +train: [4] [140/400] eta: 0:02:00 lr: 0.000261 loss: 3.4771 (2.9795) grad: 1.2623 (0.5422) time: 0.4508 data: 0.0043 max mem: 22448 +train: [4] [160/400] eta: 0:01:50 lr: 0.000264 loss: 2.8383 (2.9559) grad: 0.2426 (0.5027) time: 0.4301 data: 0.0042 max mem: 22448 +train: [4] [180/400] eta: 0:01:40 lr: 0.000267 loss: 2.7759 (2.9386) grad: 0.2276 (0.4719) time: 0.4366 data: 0.0042 max mem: 22448 +train: [4] [200/400] eta: 0:01:30 lr: 0.000270 loss: 2.7666 (2.9193) grad: 0.2179 (0.4461) time: 0.4284 data: 0.0043 max mem: 22448 +train: [4] [220/400] eta: 0:01:21 lr: 0.000273 loss: 2.7610 (2.9085) grad: 0.2168 (0.4260) time: 0.4323 data: 0.0041 max mem: 22448 +train: [4] [240/400] eta: 0:01:12 lr: 0.000276 loss: 2.7710 (2.8976) grad: 0.2166 (0.4088) time: 0.4312 data: 0.0039 max mem: 22448 +train: [4] [260/400] eta: 0:01:02 lr: 0.000279 loss: 2.7921 (2.8900) grad: 0.2157 (0.3946) time: 0.4254 data: 0.0041 max mem: 22448 +train: [4] [280/400] eta: 0:00:53 lr: 0.000282 loss: 2.8057 (2.8828) grad: 0.2231 (0.3826) time: 0.4327 data: 0.0040 max mem: 22448 +train: [4] [300/400] eta: 0:00:44 lr: 0.000285 loss: 2.7820 (2.8769) grad: 0.2309 (0.3726) time: 0.4241 data: 0.0039 max mem: 22448 +train: [4] [320/400] eta: 0:00:35 lr: 0.000288 loss: 2.7856 (2.8700) grad: 0.2282 (0.3634) time: 0.4309 data: 0.0040 max mem: 22448 +train: [4] [340/400] eta: 0:00:26 lr: 0.000291 loss: 2.7883 (2.8649) grad: 0.2297 (0.3561) time: 0.4341 data: 0.0042 max mem: 22448 +train: [4] [360/400] eta: 0:00:17 lr: 0.000294 loss: 2.7976 (2.8625) grad: 0.2454 (0.3518) time: 0.4384 data: 0.0043 max mem: 22448 +train: [4] [380/400] eta: 0:00:08 lr: 0.000297 loss: 2.8691 (2.8664) grad: 0.3490 (0.3634) time: 0.4419 data: 0.0044 max mem: 22448 +train: [4] [399/400] eta: 0:00:00 lr: 0.000300 loss: 3.0734 (2.8962) grad: 0.7942 (0.4309) time: 0.4419 data: 0.0043 max mem: 22448 +train: [4] Total time: 0:02:57 (0.4443 s / it) +train: [4] Summary: lr: 0.000300 loss: 3.0734 (2.8962) grad: 0.7942 (0.4309) +eval (validation): [4] [ 0/85] eta: 0:04:31 time: 3.1992 data: 2.9175 max mem: 22448 +eval (validation): [4] [20/85] eta: 0:00:29 time: 0.3182 data: 0.0049 max mem: 22448 +eval (validation): [4] [40/85] eta: 0:00:17 time: 0.3297 data: 0.0035 max mem: 22448 +eval (validation): [4] [60/85] eta: 0:00:09 time: 0.3432 data: 0.0041 max mem: 22448 +eval (validation): [4] [80/85] eta: 0:00:01 time: 0.3360 data: 0.0040 max mem: 22448 +eval (validation): [4] [84/85] eta: 0:00:00 time: 0.3254 data: 0.0039 max mem: 22448 +eval (validation): [4] Total time: 0:00:31 (0.3682 s / it) +cv: [4] best hparam: (1.2, 1.0) (025) ('025_lr1.2e+00_wd1.0e+00') loss: 2.409 acc: 0.272 f1: 0.205 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [5] [ 0/400] eta: 0:23:31 lr: nan time: 3.5278 data: 3.1402 max mem: 22448 +WARNING: classifier 42 (19, 1.0) diverged (loss=69.09 > 63.56) at step 1003. Freezing. +train: [5] [ 20/400] eta: 0:03:46 lr: 0.000300 loss: 2.6981 (3.0506) grad: 0.2074 (0.7186) time: 0.4503 data: 0.0025 max mem: 22448 +train: [5] [ 40/400] eta: 0:03:04 lr: 0.000300 loss: 2.7082 (2.9041) grad: 0.2100 (0.4670) time: 0.4243 data: 0.0040 max mem: 22448 +train: [5] [ 60/400] eta: 0:02:47 lr: 0.000300 loss: 2.7283 (2.8494) grad: 0.2118 (0.3835) time: 0.4500 data: 0.0043 max mem: 22448 +train: [5] [ 80/400] eta: 0:02:33 lr: 0.000300 loss: 2.7401 (2.8168) grad: 0.2121 (0.3394) time: 0.4385 data: 0.0043 max mem: 22448 +train: [5] [100/400] eta: 0:02:21 lr: 0.000300 loss: 2.7354 (2.8033) grad: 0.2121 (0.3164) time: 0.4368 data: 0.0040 max mem: 22448 +train: [5] [120/400] eta: 0:02:09 lr: 0.000300 loss: 2.6964 (2.7831) grad: 0.2136 (0.2990) time: 0.4250 data: 0.0039 max mem: 22448 +train: [5] [140/400] eta: 0:01:59 lr: 0.000300 loss: 2.6655 (2.7698) grad: 0.2104 (0.2858) time: 0.4451 data: 0.0042 max mem: 22448 +train: [5] [160/400] eta: 0:01:49 lr: 0.000299 loss: 2.6841 (2.7636) grad: 0.2079 (0.2771) time: 0.4289 data: 0.0041 max mem: 22448 +train: [5] [180/400] eta: 0:01:39 lr: 0.000299 loss: 2.7260 (2.7619) grad: 0.2135 (0.2705) time: 0.4264 data: 0.0041 max mem: 22448 +train: [5] [200/400] eta: 0:01:30 lr: 0.000299 loss: 2.7183 (2.7562) grad: 0.2162 (0.2652) time: 0.4309 data: 0.0041 max mem: 22448 +train: [5] [220/400] eta: 0:01:20 lr: 0.000299 loss: 2.6940 (2.7513) grad: 0.2162 (0.2602) time: 0.4385 data: 0.0041 max mem: 22448 +train: [5] [240/400] eta: 0:01:11 lr: 0.000299 loss: 2.6908 (2.7477) grad: 0.2141 (0.2563) time: 0.4350 data: 0.0041 max mem: 22448 +train: [5] [260/400] eta: 0:01:02 lr: 0.000299 loss: 2.6908 (2.7426) grad: 0.2104 (0.2525) time: 0.4273 data: 0.0041 max mem: 22448 +train: [5] [280/400] eta: 0:00:53 lr: 0.000298 loss: 2.7034 (2.7416) grad: 0.2149 (0.2504) time: 0.4274 data: 0.0042 max mem: 22448 +train: [5] [300/400] eta: 0:00:44 lr: 0.000298 loss: 2.6948 (2.7372) grad: 0.2220 (0.2481) time: 0.4326 data: 0.0042 max mem: 22448 +train: [5] [320/400] eta: 0:00:35 lr: 0.000298 loss: 2.6938 (2.7362) grad: 0.2212 (0.2466) time: 0.4402 data: 0.0043 max mem: 22448 +train: [5] [340/400] eta: 0:00:26 lr: 0.000298 loss: 2.7132 (2.7336) grad: 0.2175 (0.2446) time: 0.4362 data: 0.0043 max mem: 22448 +train: [5] [360/400] eta: 0:00:17 lr: 0.000297 loss: 2.6754 (2.7316) grad: 0.2141 (0.2430) time: 0.4334 data: 0.0042 max mem: 22448 +train: [5] [380/400] eta: 0:00:08 lr: 0.000297 loss: 2.6646 (2.7293) grad: 0.2126 (0.2415) time: 0.4491 data: 0.0043 max mem: 22448 +train: [5] [399/400] eta: 0:00:00 lr: 0.000297 loss: 2.6387 (2.7253) grad: 0.2098 (0.2397) time: 0.4336 data: 0.0043 max mem: 22448 +train: [5] Total time: 0:02:57 (0.4434 s / it) +train: [5] Summary: lr: 0.000297 loss: 2.6387 (2.7253) grad: 0.2098 (0.2397) +eval (validation): [5] [ 0/85] eta: 0:04:36 time: 3.2499 data: 3.0156 max mem: 22448 +eval (validation): [5] [20/85] eta: 0:00:31 time: 0.3488 data: 0.0049 max mem: 22448 +eval (validation): [5] [40/85] eta: 0:00:18 time: 0.3228 data: 0.0031 max mem: 22448 +eval (validation): [5] [60/85] eta: 0:00:09 time: 0.3362 data: 0.0041 max mem: 22448 +eval (validation): [5] [80/85] eta: 0:00:01 time: 0.3517 data: 0.0041 max mem: 22448 +eval (validation): [5] [84/85] eta: 0:00:00 time: 0.3444 data: 0.0040 max mem: 22448 +eval (validation): [5] Total time: 0:00:32 (0.3767 s / it) +cv: [5] best hparam: (1.4, 1.0) (026) ('026_lr1.4e+00_wd1.0e+00') loss: 2.359 acc: 0.286 f1: 0.216 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/eval_v2/nsd_cococlip__patch__attn/checkpoint-best.pth +train: [6] [ 0/400] eta: 0:22:16 lr: nan time: 3.3405 data: 3.0111 max mem: 22448 +train: [6] [ 20/400] eta: 0:03:40 lr: 0.000296 loss: 2.6420 (2.6241) grad: 0.2114 (0.2079) time: 0.4423 data: 0.0042 max mem: 22448 +train: [6] [ 40/400] eta: 0:03:01 lr: 0.000296 loss: 2.6435 (2.6491) grad: 0.2116 (0.2118) time: 0.4258 data: 0.0039 max mem: 22448 +train: [6] [ 60/400] eta: 0:02:45 lr: 0.000296 loss: 2.6362 (2.6447) grad: 0.2129 (0.2145) time: 0.4502 data: 0.0043 max mem: 22448 +train: [6] [ 80/400] eta: 0:02:31 lr: 0.000295 loss: 2.6072 (2.6376) grad: 0.2230 (0.2157) time: 0.4384 data: 0.0044 max mem: 22448 +train: [6] [100/400] eta: 0:02:20 lr: 0.000295 loss: 2.6098 (2.6350) grad: 0.2200 (0.2165) time: 0.4394 data: 0.0044 max mem: 22448 +train: [6] [120/400] eta: 0:02:09 lr: 0.000295 loss: 2.6286 (2.6375) grad: 0.2237 (0.2179) time: 0.4260 data: 0.0041 max mem: 22448 +train: [6] [140/400] eta: 0:01:59 lr: 0.000294 loss: 2.6526 (2.6455) grad: 0.2237 (0.2183) time: 0.4440 data: 0.0044 max mem: 22448 +train: [6] [160/400] eta: 0:01:49 lr: 0.000294 loss: 2.6904 (2.6493) grad: 0.2187 (0.2186) time: 0.4315 data: 0.0044 max mem: 22448 +train: [6] [180/400] eta: 0:01:39 lr: 0.000293 loss: 2.6414 (2.6475) grad: 0.2232 (0.2200) time: 0.4316 data: 0.0040 max mem: 22448 +train: [6] [200/400] eta: 0:01:30 lr: 0.000293 loss: 2.6414 (2.6499) grad: 0.2263 (0.2206) time: 0.4265 data: 0.0042 max mem: 22448 +train: [6] [220/400] eta: 0:01:20 lr: 0.000292 loss: 2.6793 (2.6487) grad: 0.2263 (0.2216) time: 0.4393 data: 0.0042 max mem: 22448 +train: [6] [240/400] eta: 0:01:11 lr: 0.000292 loss: 2.6542 (2.6502) grad: 0.2263 (0.2219) time: 0.4487 data: 0.0041 max mem: 22448 +train: [6] [260/400] eta: 0:01:02 lr: 0.000291 loss: 2.6388 (2.6462) grad: 0.2196 (0.2214) time: 0.4273 data: 0.0042 max mem: 22448 +train: [6] [280/400] eta: 0:00:53 lr: 0.000291 loss: 2.6275 (2.6467) grad: 0.2118 (0.2215) time: 0.4294 data: 0.0041 max mem: 22448 +train: [6] [300/400] eta: 0:00:44 lr: 0.000290 loss: 2.6854 (2.6491) grad: 0.2198 (0.2218) time: 0.4351 data: 0.0042 max mem: 22448 +train: [6] [320/400] eta: 0:00:35 lr: 0.000290 loss: 2.6825 (2.6497) grad: 0.2267 (0.2223) time: 0.4331 data: 0.0042 max mem: 22448 +train: [6] [340/400] eta: 0:00:26 lr: 0.000289 loss: 2.6602 (2.6514) grad: 0.2269 (0.2224) time: 0.4354 data: 0.0042 max mem: 22448 +train: [6] [360/400] eta: 0:00:17 lr: 0.000288 loss: 2.6546 (2.6494) grad: 0.2236 (0.2225) time: 0.4276 data: 0.0042 max mem: 22448 +train: [6] [380/400] eta: 0:00:08 lr: 0.000288 loss: 2.6256 (2.6506) grad: 0.2257 (0.2226) time: 0.4422 data: 0.0040 max mem: 22448 +train: [6] [399/400] eta: 0:00:00 lr: 0.000287 loss: 2.6650 (2.6513) grad: 0.2122 (0.2222) time: 0.4388 data: 0.0041 max mem: 22448 +train: [6] Total time: 0:02:57 (0.4431 s / it) +train: [6] Summary: lr: 0.000287 loss: 2.6650 (2.6513) grad: 0.2122 (0.2222) +eval (validation): [6] [ 0/85] eta: 0:04:41 time: 3.3074 data: 3.0258 max mem: 22448 +eval (validation): [6] [20/85] eta: 0:00:33 time: 0.3767 data: 0.0037 max mem: 22448 +eval (validation): [6] [40/85] eta: 0:00:18 time: 0.3220 data: 0.0040 max mem: 22448 +eval (validation): [6] [60/85] eta: 0:00:10 time: 0.3636 data: 0.0040 max mem: 22448 +eval (validation): [6] [80/85] eta: 0:00:01 time: 0.3458 data: 0.0041 max mem: 22448 +eval (validation): [6] [84/85] eta: 0:00:00 time: 0.3340 data: 0.0039 max mem: 22448 +eval (validation): [6] Total time: 0:00:33 (0.3883 s / it) +cv: [6] best hparam: (0.61, 1.0) (021) ('021_lr6.1e-01_wd1.0e+00') loss: 2.365 acc: 0.283 f1: 0.223 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [7] [ 0/400] eta: 0:22:14 lr: nan time: 3.3360 data: 3.0089 max mem: 22448 +train: [7] [ 20/400] eta: 0:03:38 lr: 0.000286 loss: 2.5621 (2.5751) grad: 0.2124 (0.2189) time: 0.4369 data: 0.0060 max mem: 22448 +train: [7] [ 40/400] eta: 0:03:01 lr: 0.000286 loss: 2.5683 (2.5804) grad: 0.2138 (0.2223) time: 0.4303 data: 0.0040 max mem: 22448 +train: [7] [ 60/400] eta: 0:02:44 lr: 0.000285 loss: 2.5643 (2.5684) grad: 0.2269 (0.2250) time: 0.4383 data: 0.0041 max mem: 22448 +train: [7] [ 80/400] eta: 0:02:31 lr: 0.000284 loss: 2.5643 (2.5783) grad: 0.2265 (0.2234) time: 0.4448 data: 0.0042 max mem: 22448 +train: [7] [100/400] eta: 0:02:20 lr: 0.000284 loss: 2.5581 (2.5720) grad: 0.2225 (0.2231) time: 0.4454 data: 0.0042 max mem: 22448 +train: [7] [120/400] eta: 0:02:09 lr: 0.000283 loss: 2.5373 (2.5709) grad: 0.2231 (0.2241) time: 0.4340 data: 0.0042 max mem: 22448 +train: [7] [140/400] eta: 0:01:59 lr: 0.000282 loss: 2.5732 (2.5753) grad: 0.2235 (0.2246) time: 0.4344 data: 0.0042 max mem: 22448 +train: [7] [160/400] eta: 0:01:49 lr: 0.000282 loss: 2.6167 (2.5766) grad: 0.2234 (0.2249) time: 0.4394 data: 0.0043 max mem: 22448 +train: [7] [180/400] eta: 0:01:39 lr: 0.000281 loss: 2.6320 (2.5829) grad: 0.2307 (0.2262) time: 0.4298 data: 0.0040 max mem: 22448 +train: [7] [200/400] eta: 0:01:30 lr: 0.000280 loss: 2.6021 (2.5826) grad: 0.2312 (0.2265) time: 0.4260 data: 0.0042 max mem: 22448 +train: [7] [220/400] eta: 0:01:20 lr: 0.000279 loss: 2.5716 (2.5817) grad: 0.2303 (0.2271) time: 0.4277 data: 0.0042 max mem: 22448 +train: [7] [240/400] eta: 0:01:11 lr: 0.000278 loss: 2.6064 (2.5854) grad: 0.2278 (0.2277) time: 0.4252 data: 0.0042 max mem: 22448 +train: [7] [260/400] eta: 0:01:02 lr: 0.000278 loss: 2.6064 (2.5843) grad: 0.2246 (0.2272) time: 0.4363 data: 0.0041 max mem: 22448 +train: [7] [280/400] eta: 0:00:53 lr: 0.000277 loss: 2.5588 (2.5816) grad: 0.2217 (0.2271) time: 0.4283 data: 0.0041 max mem: 22448 +train: [7] [300/400] eta: 0:00:44 lr: 0.000276 loss: 2.5075 (2.5801) grad: 0.2254 (0.2274) time: 0.4289 data: 0.0040 max mem: 22448 +train: [7] [320/400] eta: 0:00:35 lr: 0.000275 loss: 2.5266 (2.5801) grad: 0.2248 (0.2274) time: 0.4272 data: 0.0041 max mem: 22448 +train: [7] [340/400] eta: 0:00:26 lr: 0.000274 loss: 2.5573 (2.5781) grad: 0.2247 (0.2271) time: 0.4290 data: 0.0041 max mem: 22448 +train: [7] [360/400] eta: 0:00:17 lr: 0.000273 loss: 2.5699 (2.5793) grad: 0.2247 (0.2273) time: 0.4284 data: 0.0042 max mem: 22448 +train: [7] [380/400] eta: 0:00:08 lr: 0.000272 loss: 2.5879 (2.5794) grad: 0.2328 (0.2277) time: 0.4386 data: 0.0044 max mem: 22448 +train: [7] [399/400] eta: 0:00:00 lr: 0.000271 loss: 2.5879 (2.5802) grad: 0.2341 (0.2280) time: 0.4428 data: 0.0043 max mem: 22448 +train: [7] Total time: 0:02:56 (0.4411 s / it) +train: [7] Summary: lr: 0.000271 loss: 2.5879 (2.5802) grad: 0.2341 (0.2280) +eval (validation): [7] [ 0/85] eta: 0:04:35 time: 3.2418 data: 2.9968 max mem: 22448 +eval (validation): [7] [20/85] eta: 0:00:30 time: 0.3360 data: 0.0037 max mem: 22448 +eval (validation): [7] [40/85] eta: 0:00:18 time: 0.3288 data: 0.0040 max mem: 22448 +eval (validation): [7] [60/85] eta: 0:00:09 time: 0.3480 data: 0.0040 max mem: 22448 +eval (validation): [7] [80/85] eta: 0:00:01 time: 0.3378 data: 0.0040 max mem: 22448 +eval (validation): [7] [84/85] eta: 0:00:00 time: 0.3320 data: 0.0040 max mem: 22448 +eval (validation): [7] Total time: 0:00:31 (0.3738 s / it) +cv: [7] best hparam: (0.61, 1.0) (021) ('021_lr6.1e-01_wd1.0e+00') loss: 2.356 acc: 0.279 f1: 0.219 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [8] [ 0/400] eta: 0:24:13 lr: nan time: 3.6334 data: 3.2602 max mem: 22448 +train: [8] [ 20/400] eta: 0:03:45 lr: 0.000270 loss: 2.4715 (2.4825) grad: 0.2138 (0.2162) time: 0.4416 data: 0.0027 max mem: 22448 +train: [8] [ 40/400] eta: 0:03:05 lr: 0.000270 loss: 2.4870 (2.4920) grad: 0.2189 (0.2197) time: 0.4340 data: 0.0043 max mem: 22448 +train: [8] [ 60/400] eta: 0:02:47 lr: 0.000269 loss: 2.5297 (2.5020) grad: 0.2214 (0.2208) time: 0.4409 data: 0.0044 max mem: 22448 +train: [8] [ 80/400] eta: 0:02:33 lr: 0.000268 loss: 2.5419 (2.5104) grad: 0.2249 (0.2243) time: 0.4403 data: 0.0044 max mem: 22448 +train: [8] [100/400] eta: 0:02:21 lr: 0.000267 loss: 2.5414 (2.5074) grad: 0.2353 (0.2275) time: 0.4434 data: 0.0045 max mem: 22448 +train: [8] [120/400] eta: 0:02:10 lr: 0.000266 loss: 2.4960 (2.5078) grad: 0.2446 (0.2305) time: 0.4380 data: 0.0042 max mem: 22448 +train: [8] [140/400] eta: 0:01:59 lr: 0.000265 loss: 2.4960 (2.5146) grad: 0.2412 (0.2321) time: 0.4257 data: 0.0040 max mem: 22448 +train: [8] [160/400] eta: 0:01:49 lr: 0.000264 loss: 2.5316 (2.5137) grad: 0.2449 (0.2347) time: 0.4416 data: 0.0043 max mem: 22448 +train: [8] [180/400] eta: 0:01:40 lr: 0.000263 loss: 2.4754 (2.5089) grad: 0.2428 (0.2351) time: 0.4359 data: 0.0042 max mem: 22448 +train: [8] [200/400] eta: 0:01:30 lr: 0.000262 loss: 2.4855 (2.5135) grad: 0.2411 (0.2363) time: 0.4366 data: 0.0042 max mem: 22448 +train: [8] [220/400] eta: 0:01:21 lr: 0.000260 loss: 2.5527 (2.5154) grad: 0.2396 (0.2359) time: 0.4428 data: 0.0042 max mem: 22448 +train: [8] [240/400] eta: 0:01:12 lr: 0.000259 loss: 2.5454 (2.5155) grad: 0.2289 (0.2357) time: 0.4338 data: 0.0042 max mem: 22448 +train: [8] [260/400] eta: 0:01:02 lr: 0.000258 loss: 2.5378 (2.5182) grad: 0.2304 (0.2357) time: 0.4345 data: 0.0040 max mem: 22448 +train: [8] [280/400] eta: 0:00:53 lr: 0.000257 loss: 2.5150 (2.5176) grad: 0.2304 (0.2357) time: 0.4265 data: 0.0039 max mem: 22448 +train: [8] [300/400] eta: 0:00:44 lr: 0.000256 loss: 2.4958 (2.5174) grad: 0.2263 (0.2355) time: 0.4412 data: 0.0041 max mem: 22448 +train: [8] [320/400] eta: 0:00:35 lr: 0.000255 loss: 2.4958 (2.5167) grad: 0.2232 (0.2346) time: 0.4238 data: 0.0041 max mem: 22448 +train: [8] [340/400] eta: 0:00:26 lr: 0.000254 loss: 2.4809 (2.5165) grad: 0.2264 (0.2353) time: 0.4339 data: 0.0041 max mem: 22448 +train: [8] [360/400] eta: 0:00:17 lr: 0.000253 loss: 2.4790 (2.5157) grad: 0.2418 (0.2354) time: 0.4309 data: 0.0042 max mem: 22448 +train: [8] [380/400] eta: 0:00:08 lr: 0.000252 loss: 2.5002 (2.5172) grad: 0.2341 (0.2353) time: 0.4374 data: 0.0040 max mem: 22448 +train: [8] [399/400] eta: 0:00:00 lr: 0.000250 loss: 2.5235 (2.5177) grad: 0.2386 (0.2357) time: 0.4405 data: 0.0041 max mem: 22448 +train: [8] Total time: 0:02:57 (0.4445 s / it) +train: [8] Summary: lr: 0.000250 loss: 2.5235 (2.5177) grad: 0.2386 (0.2357) +eval (validation): [8] [ 0/85] eta: 0:04:31 time: 3.1916 data: 2.9529 max mem: 22448 +eval (validation): [8] [20/85] eta: 0:00:30 time: 0.3406 data: 0.0043 max mem: 22448 +eval (validation): [8] [40/85] eta: 0:00:18 time: 0.3362 data: 0.0035 max mem: 22448 +eval (validation): [8] [60/85] eta: 0:00:09 time: 0.3317 data: 0.0041 max mem: 22448 +eval (validation): [8] [80/85] eta: 0:00:01 time: 0.3382 data: 0.0042 max mem: 22448 +eval (validation): [8] [84/85] eta: 0:00:00 time: 0.3294 data: 0.0040 max mem: 22448 +eval (validation): [8] Total time: 0:00:31 (0.3726 s / it) +cv: [8] best hparam: (0.52, 1.0) (020) ('020_lr5.2e-01_wd1.0e+00') loss: 2.378 acc: 0.275 f1: 0.221 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [9] [ 0/400] eta: 0:22:07 lr: nan time: 3.3188 data: 2.9951 max mem: 22448 +train: [9] [ 20/400] eta: 0:03:37 lr: 0.000249 loss: 2.4406 (2.4625) grad: 0.2333 (0.2407) time: 0.4353 data: 0.0040 max mem: 22448 +train: [9] [ 40/400] eta: 0:03:01 lr: 0.000248 loss: 2.4797 (2.4791) grad: 0.2333 (0.2357) time: 0.4331 data: 0.0037 max mem: 22448 +train: [9] [ 60/400] eta: 0:02:43 lr: 0.000247 loss: 2.4797 (2.4719) grad: 0.2296 (0.2320) time: 0.4361 data: 0.0041 max mem: 22448 +train: [9] [ 80/400] eta: 0:02:31 lr: 0.000246 loss: 2.4524 (2.4801) grad: 0.2306 (0.2336) time: 0.4488 data: 0.0042 max mem: 22448 +train: [9] [100/400] eta: 0:02:20 lr: 0.000244 loss: 2.4664 (2.4791) grad: 0.2386 (0.2350) time: 0.4395 data: 0.0044 max mem: 22448 +train: [9] [120/400] eta: 0:02:09 lr: 0.000243 loss: 2.4664 (2.4778) grad: 0.2386 (0.2352) time: 0.4394 data: 0.0045 max mem: 22448 +train: [9] [140/400] eta: 0:01:59 lr: 0.000242 loss: 2.4681 (2.4799) grad: 0.2387 (0.2363) time: 0.4332 data: 0.0042 max mem: 22448 +train: [9] [160/400] eta: 0:01:49 lr: 0.000241 loss: 2.4519 (2.4776) grad: 0.2362 (0.2374) time: 0.4467 data: 0.0042 max mem: 22448 +train: [9] [180/400] eta: 0:01:40 lr: 0.000240 loss: 2.4474 (2.4789) grad: 0.2338 (0.2383) time: 0.4402 data: 0.0043 max mem: 22448 +train: [9] [200/400] eta: 0:01:30 lr: 0.000238 loss: 2.4474 (2.4768) grad: 0.2414 (0.2391) time: 0.4292 data: 0.0043 max mem: 22448 +train: [9] [220/400] eta: 0:01:21 lr: 0.000237 loss: 2.4379 (2.4754) grad: 0.2428 (0.2400) time: 0.4408 data: 0.0048 max mem: 22448 +train: [9] [240/400] eta: 0:01:12 lr: 0.000236 loss: 2.4969 (2.4795) grad: 0.2439 (0.2398) time: 0.4419 data: 0.0043 max mem: 22448 +train: [9] [260/400] eta: 0:01:02 lr: 0.000234 loss: 2.4945 (2.4786) grad: 0.2396 (0.2394) time: 0.4407 data: 0.0045 max mem: 22448 +train: [9] [280/400] eta: 0:00:53 lr: 0.000233 loss: 2.4426 (2.4774) grad: 0.2385 (0.2397) time: 0.4372 data: 0.0043 max mem: 22448 +train: [9] [300/400] eta: 0:00:44 lr: 0.000232 loss: 2.4644 (2.4780) grad: 0.2425 (0.2403) time: 0.4324 data: 0.0042 max mem: 22448 +train: [9] [320/400] eta: 0:00:35 lr: 0.000230 loss: 2.4644 (2.4794) grad: 0.2416 (0.2403) time: 0.4305 data: 0.0043 max mem: 22448 +train: [9] [340/400] eta: 0:00:26 lr: 0.000229 loss: 2.4520 (2.4770) grad: 0.2402 (0.2405) time: 0.4329 data: 0.0041 max mem: 22448 +train: [9] [360/400] eta: 0:00:17 lr: 0.000228 loss: 2.4456 (2.4770) grad: 0.2455 (0.2409) time: 0.4263 data: 0.0042 max mem: 22448 +train: [9] [380/400] eta: 0:00:08 lr: 0.000226 loss: 2.4469 (2.4762) grad: 0.2425 (0.2407) time: 0.4303 data: 0.0042 max mem: 22448 +train: [9] [399/400] eta: 0:00:00 lr: 0.000225 loss: 2.4676 (2.4766) grad: 0.2399 (0.2410) time: 0.4396 data: 0.0042 max mem: 22448 +train: [9] Total time: 0:02:57 (0.4443 s / it) +train: [9] Summary: lr: 0.000225 loss: 2.4676 (2.4766) grad: 0.2399 (0.2410) +eval (validation): [9] [ 0/85] eta: 0:04:31 time: 3.1959 data: 2.9111 max mem: 22448 +eval (validation): [9] [20/85] eta: 0:00:32 time: 0.3689 data: 0.0101 max mem: 22448 +eval (validation): [9] [40/85] eta: 0:00:18 time: 0.3368 data: 0.0039 max mem: 22448 +eval (validation): [9] [60/85] eta: 0:00:09 time: 0.3362 data: 0.0040 max mem: 22448 +eval (validation): [9] [80/85] eta: 0:00:01 time: 0.3442 data: 0.0040 max mem: 22448 +eval (validation): [9] [84/85] eta: 0:00:00 time: 0.3386 data: 0.0040 max mem: 22448 +eval (validation): [9] Total time: 0:00:32 (0.3830 s / it) +cv: [9] best hparam: (0.52, 1.0) (020) ('020_lr5.2e-01_wd1.0e+00') loss: 2.350 acc: 0.281 f1: 0.220 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [10] [ 0/400] eta: 0:23:04 lr: nan time: 3.4621 data: 3.0897 max mem: 22448 +train: [10] [ 20/400] eta: 0:03:43 lr: 0.000224 loss: 2.3988 (2.4172) grad: 0.2385 (0.2442) time: 0.4435 data: 0.0033 max mem: 22448 +train: [10] [ 40/400] eta: 0:03:03 lr: 0.000222 loss: 2.3988 (2.4140) grad: 0.2385 (0.2403) time: 0.4310 data: 0.0042 max mem: 22448 +train: [10] [ 60/400] eta: 0:02:45 lr: 0.000221 loss: 2.4058 (2.4275) grad: 0.2312 (0.2374) time: 0.4394 data: 0.0041 max mem: 22448 +train: [10] [ 80/400] eta: 0:02:32 lr: 0.000220 loss: 2.4004 (2.4161) grad: 0.2258 (0.2354) time: 0.4461 data: 0.0044 max mem: 22448 +train: [10] [100/400] eta: 0:02:20 lr: 0.000218 loss: 2.3942 (2.4117) grad: 0.2315 (0.2358) time: 0.4389 data: 0.0043 max mem: 22448 +train: [10] [120/400] eta: 0:02:10 lr: 0.000217 loss: 2.4104 (2.4107) grad: 0.2381 (0.2367) time: 0.4469 data: 0.0042 max mem: 22448 +train: [10] [140/400] eta: 0:01:59 lr: 0.000215 loss: 2.3973 (2.4126) grad: 0.2372 (0.2369) time: 0.4286 data: 0.0040 max mem: 22448 +train: [10] [160/400] eta: 0:01:49 lr: 0.000214 loss: 2.4185 (2.4143) grad: 0.2333 (0.2367) time: 0.4413 data: 0.0041 max mem: 22448 +train: [10] [180/400] eta: 0:01:40 lr: 0.000213 loss: 2.4311 (2.4164) grad: 0.2351 (0.2369) time: 0.4347 data: 0.0042 max mem: 22448 +train: [10] [200/400] eta: 0:01:30 lr: 0.000211 loss: 2.4434 (2.4171) grad: 0.2352 (0.2375) time: 0.4378 data: 0.0042 max mem: 22448 +train: [10] [220/400] eta: 0:01:21 lr: 0.000210 loss: 2.4279 (2.4161) grad: 0.2361 (0.2378) time: 0.4358 data: 0.0042 max mem: 22448 +train: [10] [240/400] eta: 0:01:11 lr: 0.000208 loss: 2.4269 (2.4165) grad: 0.2378 (0.2379) time: 0.4252 data: 0.0041 max mem: 22448 +train: [10] [260/400] eta: 0:01:02 lr: 0.000207 loss: 2.4104 (2.4163) grad: 0.2390 (0.2381) time: 0.4336 data: 0.0041 max mem: 22448 +train: [10] [280/400] eta: 0:00:53 lr: 0.000205 loss: 2.4138 (2.4156) grad: 0.2378 (0.2381) time: 0.4335 data: 0.0042 max mem: 22448 +train: [10] [300/400] eta: 0:00:44 lr: 0.000204 loss: 2.3428 (2.4120) grad: 0.2378 (0.2380) time: 0.4393 data: 0.0044 max mem: 22448 +train: [10] [320/400] eta: 0:00:35 lr: 0.000202 loss: 2.3626 (2.4100) grad: 0.2385 (0.2385) time: 0.4394 data: 0.0042 max mem: 22448 +train: [10] [340/400] eta: 0:00:26 lr: 0.000201 loss: 2.4099 (2.4105) grad: 0.2476 (0.2390) time: 0.4375 data: 0.0041 max mem: 22448 +train: [10] [360/400] eta: 0:00:17 lr: 0.000199 loss: 2.4073 (2.4098) grad: 0.2441 (0.2391) time: 0.4302 data: 0.0042 max mem: 22448 +train: [10] [380/400] eta: 0:00:08 lr: 0.000198 loss: 2.3758 (2.4095) grad: 0.2436 (0.2391) time: 0.4430 data: 0.0042 max mem: 22448 +train: [10] [399/400] eta: 0:00:00 lr: 0.000196 loss: 2.4135 (2.4105) grad: 0.2440 (0.2395) time: 0.4458 data: 0.0042 max mem: 22448 +train: [10] Total time: 0:02:58 (0.4454 s / it) +train: [10] Summary: lr: 0.000196 loss: 2.4135 (2.4105) grad: 0.2440 (0.2395) +eval (validation): [10] [ 0/85] eta: 0:04:39 time: 3.2927 data: 3.0517 max mem: 22448 +eval (validation): [10] [20/85] eta: 0:00:31 time: 0.3404 data: 0.0061 max mem: 22448 +eval (validation): [10] [40/85] eta: 0:00:18 time: 0.3384 data: 0.0038 max mem: 22448 +eval (validation): [10] [60/85] eta: 0:00:09 time: 0.3244 data: 0.0034 max mem: 22448 +eval (validation): [10] [80/85] eta: 0:00:01 time: 0.3309 data: 0.0038 max mem: 22448 +eval (validation): [10] [84/85] eta: 0:00:00 time: 0.3310 data: 0.0038 max mem: 22448 +eval (validation): [10] Total time: 0:00:31 (0.3721 s / it) +cv: [10] best hparam: (0.52, 1.0) (020) ('020_lr5.2e-01_wd1.0e+00') loss: 2.342 acc: 0.287 f1: 0.227 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/eval_v2/nsd_cococlip__patch__attn/checkpoint-best.pth +train: [11] [ 0/400] eta: 0:22:42 lr: nan time: 3.4068 data: 3.0340 max mem: 22448 +train: [11] [ 20/400] eta: 0:03:38 lr: 0.000195 loss: 2.3266 (2.3445) grad: 0.2352 (0.2395) time: 0.4344 data: 0.0041 max mem: 22448 +train: [11] [ 40/400] eta: 0:03:00 lr: 0.000193 loss: 2.3490 (2.3593) grad: 0.2392 (0.2384) time: 0.4237 data: 0.0036 max mem: 22448 +train: [11] [ 60/400] eta: 0:02:42 lr: 0.000192 loss: 2.3411 (2.3464) grad: 0.2394 (0.2395) time: 0.4279 data: 0.0041 max mem: 22448 +train: [11] [ 80/400] eta: 0:02:29 lr: 0.000190 loss: 2.3405 (2.3619) grad: 0.2394 (0.2413) time: 0.4367 data: 0.0044 max mem: 22448 +train: [11] [100/400] eta: 0:02:18 lr: 0.000189 loss: 2.3727 (2.3576) grad: 0.2420 (0.2415) time: 0.4382 data: 0.0041 max mem: 22448 +train: [11] [120/400] eta: 0:02:07 lr: 0.000187 loss: 2.2883 (2.3494) grad: 0.2436 (0.2423) time: 0.4340 data: 0.0043 max mem: 22448 +train: [11] [140/400] eta: 0:01:57 lr: 0.000186 loss: 2.3464 (2.3503) grad: 0.2455 (0.2430) time: 0.4281 data: 0.0041 max mem: 22448 +train: [11] [160/400] eta: 0:01:48 lr: 0.000184 loss: 2.3508 (2.3536) grad: 0.2465 (0.2434) time: 0.4365 data: 0.0042 max mem: 22448 +train: [11] [180/400] eta: 0:01:38 lr: 0.000183 loss: 2.3380 (2.3551) grad: 0.2479 (0.2450) time: 0.4290 data: 0.0041 max mem: 22448 +train: [11] [200/400] eta: 0:01:29 lr: 0.000181 loss: 2.3850 (2.3594) grad: 0.2536 (0.2456) time: 0.4287 data: 0.0041 max mem: 22448 +train: [11] [220/400] eta: 0:01:20 lr: 0.000180 loss: 2.4048 (2.3648) grad: 0.2476 (0.2452) time: 0.4237 data: 0.0042 max mem: 22448 +train: [11] [240/400] eta: 0:01:10 lr: 0.000178 loss: 2.4036 (2.3646) grad: 0.2377 (0.2453) time: 0.4329 data: 0.0042 max mem: 22448 +train: [11] [260/400] eta: 0:01:01 lr: 0.000177 loss: 2.3411 (2.3632) grad: 0.2445 (0.2458) time: 0.4220 data: 0.0042 max mem: 22448 +train: [11] [280/400] eta: 0:00:52 lr: 0.000175 loss: 2.3500 (2.3643) grad: 0.2520 (0.2463) time: 0.4274 data: 0.0043 max mem: 22448 +train: [11] [300/400] eta: 0:00:44 lr: 0.000174 loss: 2.3972 (2.3687) grad: 0.2451 (0.2462) time: 0.4360 data: 0.0042 max mem: 22448 +train: [11] [320/400] eta: 0:00:35 lr: 0.000172 loss: 2.3987 (2.3703) grad: 0.2453 (0.2469) time: 0.4331 data: 0.0044 max mem: 22448 +train: [11] [340/400] eta: 0:00:26 lr: 0.000170 loss: 2.3743 (2.3709) grad: 0.2478 (0.2475) time: 0.4391 data: 0.0043 max mem: 22448 +train: [11] [360/400] eta: 0:00:17 lr: 0.000169 loss: 2.3869 (2.3716) grad: 0.2514 (0.2477) time: 0.4324 data: 0.0042 max mem: 22448 +train: [11] [380/400] eta: 0:00:08 lr: 0.000167 loss: 2.3496 (2.3685) grad: 0.2479 (0.2475) time: 0.4299 data: 0.0042 max mem: 22448 +train: [11] [399/400] eta: 0:00:00 lr: 0.000166 loss: 2.3685 (2.3711) grad: 0.2409 (0.2473) time: 0.4481 data: 0.0042 max mem: 22448 +train: [11] Total time: 0:02:55 (0.4398 s / it) +train: [11] Summary: lr: 0.000166 loss: 2.3685 (2.3711) grad: 0.2409 (0.2473) +eval (validation): [11] [ 0/85] eta: 0:04:30 time: 3.1836 data: 2.9476 max mem: 22448 +eval (validation): [11] [20/85] eta: 0:00:31 time: 0.3481 data: 0.0054 max mem: 22448 +eval (validation): [11] [40/85] eta: 0:00:18 time: 0.3448 data: 0.0035 max mem: 22448 +eval (validation): [11] [60/85] eta: 0:00:09 time: 0.3362 data: 0.0040 max mem: 22448 +eval (validation): [11] [80/85] eta: 0:00:01 time: 0.3348 data: 0.0040 max mem: 22448 +eval (validation): [11] [84/85] eta: 0:00:00 time: 0.3297 data: 0.0040 max mem: 22448 +eval (validation): [11] Total time: 0:00:32 (0.3768 s / it) +cv: [11] best hparam: (0.44, 1.0) (019) ('019_lr4.4e-01_wd1.0e+00') loss: 2.360 acc: 0.283 f1: 0.226 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [12] [ 0/400] eta: 0:22:33 lr: nan time: 3.3841 data: 3.0635 max mem: 22448 +train: [12] [ 20/400] eta: 0:03:38 lr: 0.000164 loss: 2.2544 (2.2785) grad: 0.2312 (0.2330) time: 0.4351 data: 0.0043 max mem: 22448 +train: [12] [ 40/400] eta: 0:03:03 lr: 0.000163 loss: 2.2661 (2.2803) grad: 0.2387 (0.2380) time: 0.4417 data: 0.0035 max mem: 22448 +train: [12] [ 60/400] eta: 0:02:43 lr: 0.000161 loss: 2.2709 (2.2873) grad: 0.2388 (0.2378) time: 0.4239 data: 0.0039 max mem: 22448 +train: [12] [ 80/400] eta: 0:02:31 lr: 0.000160 loss: 2.2946 (2.2960) grad: 0.2357 (0.2377) time: 0.4447 data: 0.0042 max mem: 22448 +train: [12] [100/400] eta: 0:02:19 lr: 0.000158 loss: 2.3016 (2.2964) grad: 0.2371 (0.2384) time: 0.4416 data: 0.0042 max mem: 22448 +train: [12] [120/400] eta: 0:02:09 lr: 0.000156 loss: 2.3026 (2.3029) grad: 0.2353 (0.2372) time: 0.4454 data: 0.0043 max mem: 22448 +train: [12] [140/400] eta: 0:01:59 lr: 0.000155 loss: 2.3001 (2.2988) grad: 0.2363 (0.2394) time: 0.4346 data: 0.0042 max mem: 22448 +train: [12] [160/400] eta: 0:01:49 lr: 0.000153 loss: 2.2898 (2.3000) grad: 0.2543 (0.2413) time: 0.4488 data: 0.0042 max mem: 22448 +train: [12] [180/400] eta: 0:01:40 lr: 0.000152 loss: 2.3175 (2.3007) grad: 0.2536 (0.2423) time: 0.4395 data: 0.0040 max mem: 22448 +train: [12] [200/400] eta: 0:01:30 lr: 0.000150 loss: 2.3227 (2.3088) grad: 0.2467 (0.2435) time: 0.4302 data: 0.0041 max mem: 22448 +train: [12] [220/400] eta: 0:01:21 lr: 0.000149 loss: 2.3541 (2.3132) grad: 0.2514 (0.2441) time: 0.4331 data: 0.0041 max mem: 22448 +train: [12] [240/400] eta: 0:01:11 lr: 0.000147 loss: 2.3031 (2.3098) grad: 0.2520 (0.2455) time: 0.4252 data: 0.0042 max mem: 22448 +train: [12] [260/400] eta: 0:01:02 lr: 0.000145 loss: 2.2735 (2.3111) grad: 0.2520 (0.2457) time: 0.4372 data: 0.0041 max mem: 22448 +train: [12] [280/400] eta: 0:00:53 lr: 0.000144 loss: 2.2834 (2.3077) grad: 0.2509 (0.2459) time: 0.4318 data: 0.0040 max mem: 22448 +train: [12] [300/400] eta: 0:00:44 lr: 0.000142 loss: 2.2834 (2.3088) grad: 0.2512 (0.2469) time: 0.4284 data: 0.0039 max mem: 22448 +train: [12] [320/400] eta: 0:00:35 lr: 0.000141 loss: 2.2879 (2.3092) grad: 0.2490 (0.2469) time: 0.4458 data: 0.0041 max mem: 22448 +train: [12] [340/400] eta: 0:00:26 lr: 0.000139 loss: 2.2471 (2.3085) grad: 0.2490 (0.2467) time: 0.4258 data: 0.0040 max mem: 22448 +train: [12] [360/400] eta: 0:00:17 lr: 0.000138 loss: 2.3067 (2.3083) grad: 0.2418 (0.2465) time: 0.4353 data: 0.0040 max mem: 22448 +train: [12] [380/400] eta: 0:00:08 lr: 0.000136 loss: 2.3067 (2.3081) grad: 0.2444 (0.2467) time: 0.4392 data: 0.0040 max mem: 22448 +train: [12] [399/400] eta: 0:00:00 lr: 0.000134 loss: 2.3043 (2.3078) grad: 0.2500 (0.2471) time: 0.4442 data: 0.0040 max mem: 22448 +train: [12] Total time: 0:02:57 (0.4442 s / it) +train: [12] Summary: lr: 0.000134 loss: 2.3043 (2.3078) grad: 0.2500 (0.2471) +eval (validation): [12] [ 0/85] eta: 0:04:43 time: 3.3297 data: 3.0481 max mem: 22448 +eval (validation): [12] [20/85] eta: 0:00:33 time: 0.3782 data: 0.0032 max mem: 22448 +eval (validation): [12] [40/85] eta: 0:00:19 time: 0.3350 data: 0.0039 max mem: 22448 +eval (validation): [12] [60/85] eta: 0:00:09 time: 0.3254 data: 0.0038 max mem: 22448 +eval (validation): [12] [80/85] eta: 0:00:01 time: 0.3320 data: 0.0040 max mem: 22448 +eval (validation): [12] [84/85] eta: 0:00:00 time: 0.3236 data: 0.0039 max mem: 22448 +eval (validation): [12] Total time: 0:00:32 (0.3790 s / it) +cv: [12] best hparam: (0.38, 1.0) (018) ('018_lr3.8e-01_wd1.0e+00') loss: 2.367 acc: 0.283 f1: 0.224 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [13] [ 0/400] eta: 0:22:46 lr: nan time: 3.4164 data: 3.0514 max mem: 22448 +train: [13] [ 20/400] eta: 0:03:35 lr: 0.000133 loss: 2.2799 (2.2797) grad: 0.2410 (0.2452) time: 0.4242 data: 0.0042 max mem: 22448 +train: [13] [ 40/400] eta: 0:03:00 lr: 0.000131 loss: 2.2696 (2.2656) grad: 0.2428 (0.2441) time: 0.4355 data: 0.0038 max mem: 22448 +train: [13] [ 60/400] eta: 0:02:43 lr: 0.000130 loss: 2.2671 (2.2704) grad: 0.2412 (0.2437) time: 0.4341 data: 0.0041 max mem: 22448 +train: [13] [ 80/400] eta: 0:02:30 lr: 0.000128 loss: 2.2458 (2.2684) grad: 0.2391 (0.2445) time: 0.4378 data: 0.0042 max mem: 22448 +train: [13] [100/400] eta: 0:02:19 lr: 0.000127 loss: 2.2488 (2.2634) grad: 0.2425 (0.2437) time: 0.4466 data: 0.0043 max mem: 22448 +train: [13] [120/400] eta: 0:02:09 lr: 0.000125 loss: 2.2553 (2.2587) grad: 0.2431 (0.2440) time: 0.4428 data: 0.0042 max mem: 22448 +train: [13] [140/400] eta: 0:01:58 lr: 0.000124 loss: 2.2927 (2.2681) grad: 0.2530 (0.2453) time: 0.4347 data: 0.0042 max mem: 22448 +train: [13] [160/400] eta: 0:01:49 lr: 0.000122 loss: 2.2887 (2.2690) grad: 0.2560 (0.2472) time: 0.4335 data: 0.0042 max mem: 22448 +train: [13] [180/400] eta: 0:01:39 lr: 0.000120 loss: 2.2781 (2.2729) grad: 0.2522 (0.2476) time: 0.4327 data: 0.0042 max mem: 22448 +train: [13] [200/400] eta: 0:01:30 lr: 0.000119 loss: 2.2502 (2.2680) grad: 0.2458 (0.2473) time: 0.4375 data: 0.0041 max mem: 22448 +train: [13] [220/400] eta: 0:01:20 lr: 0.000117 loss: 2.2580 (2.2685) grad: 0.2403 (0.2474) time: 0.4276 data: 0.0041 max mem: 22448 +train: [13] [240/400] eta: 0:01:11 lr: 0.000116 loss: 2.2740 (2.2686) grad: 0.2476 (0.2478) time: 0.4371 data: 0.0041 max mem: 22448 +train: [13] [260/400] eta: 0:01:02 lr: 0.000114 loss: 2.2726 (2.2691) grad: 0.2429 (0.2469) time: 0.4304 data: 0.0041 max mem: 22448 +train: [13] [280/400] eta: 0:00:53 lr: 0.000113 loss: 2.2362 (2.2663) grad: 0.2360 (0.2463) time: 0.4307 data: 0.0043 max mem: 22448 +train: [13] [300/400] eta: 0:00:44 lr: 0.000111 loss: 2.2285 (2.2659) grad: 0.2322 (0.2453) time: 0.4294 data: 0.0040 max mem: 22448 +train: [13] [320/400] eta: 0:00:35 lr: 0.000110 loss: 2.2808 (2.2671) grad: 0.2423 (0.2457) time: 0.4278 data: 0.0042 max mem: 22448 +train: [13] [340/400] eta: 0:00:26 lr: 0.000108 loss: 2.2659 (2.2671) grad: 0.2488 (0.2454) time: 0.4418 data: 0.0041 max mem: 22448 +train: [13] [360/400] eta: 0:00:17 lr: 0.000107 loss: 2.2640 (2.2677) grad: 0.2489 (0.2459) time: 0.4432 data: 0.0040 max mem: 22448 +train: [13] [380/400] eta: 0:00:08 lr: 0.000105 loss: 2.2671 (2.2677) grad: 0.2533 (0.2461) time: 0.4322 data: 0.0040 max mem: 22448 +train: [13] [399/400] eta: 0:00:00 lr: 0.000104 loss: 2.2544 (2.2678) grad: 0.2434 (0.2462) time: 0.4302 data: 0.0039 max mem: 22448 +train: [13] Total time: 0:02:56 (0.4422 s / it) +train: [13] Summary: lr: 0.000104 loss: 2.2544 (2.2678) grad: 0.2434 (0.2462) +eval (validation): [13] [ 0/85] eta: 0:05:26 time: 3.8365 data: 3.5910 max mem: 22448 +eval (validation): [13] [20/85] eta: 0:00:33 time: 0.3455 data: 0.0046 max mem: 22448 +eval (validation): [13] [40/85] eta: 0:00:19 time: 0.3325 data: 0.0037 max mem: 22448 +eval (validation): [13] [60/85] eta: 0:00:09 time: 0.3261 data: 0.0040 max mem: 22448 +eval (validation): [13] [80/85] eta: 0:00:01 time: 0.3256 data: 0.0039 max mem: 22448 +eval (validation): [13] [84/85] eta: 0:00:00 time: 0.3233 data: 0.0039 max mem: 22448 +eval (validation): [13] Total time: 0:00:31 (0.3759 s / it) +cv: [13] best hparam: (0.44, 1.0) (019) ('019_lr4.4e-01_wd1.0e+00') loss: 2.360 acc: 0.287 f1: 0.232 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/eval_v2/nsd_cococlip__patch__attn/checkpoint-best.pth +train: [14] [ 0/400] eta: 0:22:38 lr: nan time: 3.3971 data: 3.0769 max mem: 22448 +train: [14] [ 20/400] eta: 0:03:39 lr: 0.000102 loss: 2.1608 (2.1679) grad: 0.2315 (0.2309) time: 0.4373 data: 0.0041 max mem: 22448 +train: [14] [ 40/400] eta: 0:03:02 lr: 0.000101 loss: 2.1767 (2.1759) grad: 0.2275 (0.2313) time: 0.4344 data: 0.0035 max mem: 22448 +train: [14] [ 60/400] eta: 0:02:44 lr: 0.000099 loss: 2.2207 (2.1925) grad: 0.2430 (0.2358) time: 0.4340 data: 0.0042 max mem: 22448 +train: [14] [ 80/400] eta: 0:02:32 lr: 0.000098 loss: 2.2227 (2.2046) grad: 0.2390 (0.2362) time: 0.4484 data: 0.0042 max mem: 22448 +train: [14] [100/400] eta: 0:02:20 lr: 0.000096 loss: 2.2131 (2.2077) grad: 0.2368 (0.2374) time: 0.4396 data: 0.0042 max mem: 22448 +train: [14] [120/400] eta: 0:02:09 lr: 0.000095 loss: 2.1829 (2.2020) grad: 0.2441 (0.2380) time: 0.4442 data: 0.0043 max mem: 22448 +train: [14] [140/400] eta: 0:01:59 lr: 0.000093 loss: 2.1829 (2.1990) grad: 0.2447 (0.2391) time: 0.4390 data: 0.0042 max mem: 22448 +train: [14] [160/400] eta: 0:01:49 lr: 0.000092 loss: 2.1739 (2.1978) grad: 0.2447 (0.2394) time: 0.4410 data: 0.0040 max mem: 22448 +train: [14] [180/400] eta: 0:01:40 lr: 0.000090 loss: 2.1806 (2.1973) grad: 0.2419 (0.2401) time: 0.4368 data: 0.0041 max mem: 22448 +train: [14] [200/400] eta: 0:01:30 lr: 0.000089 loss: 2.1847 (2.1980) grad: 0.2465 (0.2415) time: 0.4386 data: 0.0041 max mem: 22448 +train: [14] [220/400] eta: 0:01:21 lr: 0.000088 loss: 2.1998 (2.2002) grad: 0.2518 (0.2427) time: 0.4299 data: 0.0041 max mem: 22448 +train: [14] [240/400] eta: 0:01:12 lr: 0.000086 loss: 2.2094 (2.2052) grad: 0.2453 (0.2431) time: 0.4295 data: 0.0040 max mem: 22448 +train: [14] [260/400] eta: 0:01:02 lr: 0.000085 loss: 2.2184 (2.2063) grad: 0.2437 (0.2431) time: 0.4294 data: 0.0041 max mem: 22448 +train: [14] [280/400] eta: 0:00:53 lr: 0.000083 loss: 2.2184 (2.2070) grad: 0.2397 (0.2426) time: 0.4362 data: 0.0039 max mem: 22448 +train: [14] [300/400] eta: 0:00:44 lr: 0.000082 loss: 2.2355 (2.2120) grad: 0.2426 (0.2430) time: 0.4374 data: 0.0043 max mem: 22448 +train: [14] [320/400] eta: 0:00:35 lr: 0.000081 loss: 2.2520 (2.2134) grad: 0.2484 (0.2436) time: 0.4325 data: 0.0040 max mem: 22448 +train: [14] [340/400] eta: 0:00:26 lr: 0.000079 loss: 2.2391 (2.2141) grad: 0.2495 (0.2443) time: 0.4330 data: 0.0040 max mem: 22448 +train: [14] [360/400] eta: 0:00:17 lr: 0.000078 loss: 2.2354 (2.2150) grad: 0.2484 (0.2441) time: 0.4372 data: 0.0040 max mem: 22448 +train: [14] [380/400] eta: 0:00:08 lr: 0.000076 loss: 2.2203 (2.2147) grad: 0.2422 (0.2441) time: 0.4299 data: 0.0040 max mem: 22448 +train: [14] [399/400] eta: 0:00:00 lr: 0.000075 loss: 2.1981 (2.2146) grad: 0.2497 (0.2447) time: 0.4374 data: 0.0041 max mem: 22448 +train: [14] Total time: 0:02:57 (0.4440 s / it) +train: [14] Summary: lr: 0.000075 loss: 2.1981 (2.2146) grad: 0.2497 (0.2447) +eval (validation): [14] [ 0/85] eta: 0:04:35 time: 3.2459 data: 2.9592 max mem: 22448 +eval (validation): [14] [20/85] eta: 0:00:31 time: 0.3483 data: 0.0053 max mem: 22448 +eval (validation): [14] [40/85] eta: 0:00:18 time: 0.3423 data: 0.0037 max mem: 22448 +eval (validation): [14] [60/85] eta: 0:00:09 time: 0.3393 data: 0.0040 max mem: 22448 +eval (validation): [14] [80/85] eta: 0:00:01 time: 0.3345 data: 0.0040 max mem: 22448 +eval (validation): [14] [84/85] eta: 0:00:00 time: 0.3290 data: 0.0039 max mem: 22448 +eval (validation): [14] Total time: 0:00:32 (0.3767 s / it) +cv: [14] best hparam: (0.38, 1.0) (018) ('018_lr3.8e-01_wd1.0e+00') loss: 2.349 acc: 0.288 f1: 0.229 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/eval_v2/nsd_cococlip__patch__attn/checkpoint-best.pth +train: [15] [ 0/400] eta: 0:23:02 lr: nan time: 3.4559 data: 3.0771 max mem: 22448 +train: [15] [ 20/400] eta: 0:03:46 lr: 0.000074 loss: 2.1811 (2.1787) grad: 0.2338 (0.2363) time: 0.4530 data: 0.0044 max mem: 22448 +train: [15] [ 40/400] eta: 0:03:04 lr: 0.000072 loss: 2.1811 (2.1775) grad: 0.2338 (0.2355) time: 0.4224 data: 0.0043 max mem: 22448 +train: [15] [ 60/400] eta: 0:02:44 lr: 0.000071 loss: 2.1474 (2.1694) grad: 0.2376 (0.2362) time: 0.4319 data: 0.0040 max mem: 22448 +train: [15] [ 80/400] eta: 0:02:32 lr: 0.000070 loss: 2.1344 (2.1613) grad: 0.2370 (0.2349) time: 0.4523 data: 0.0044 max mem: 22448 +train: [15] [100/400] eta: 0:02:21 lr: 0.000068 loss: 2.1239 (2.1547) grad: 0.2320 (0.2360) time: 0.4488 data: 0.0042 max mem: 22448 +train: [15] [120/400] eta: 0:02:10 lr: 0.000067 loss: 2.1586 (2.1599) grad: 0.2442 (0.2377) time: 0.4396 data: 0.0043 max mem: 22448 +train: [15] [140/400] eta: 0:01:59 lr: 0.000066 loss: 2.1924 (2.1689) grad: 0.2456 (0.2402) time: 0.4290 data: 0.0040 max mem: 22448 +train: [15] [160/400] eta: 0:01:49 lr: 0.000064 loss: 2.1655 (2.1675) grad: 0.2443 (0.2405) time: 0.4317 data: 0.0041 max mem: 22448 +train: [15] [180/400] eta: 0:01:40 lr: 0.000063 loss: 2.1655 (2.1739) grad: 0.2493 (0.2417) time: 0.4343 data: 0.0042 max mem: 22448 +train: [15] [200/400] eta: 0:01:30 lr: 0.000062 loss: 2.1876 (2.1734) grad: 0.2421 (0.2413) time: 0.4275 data: 0.0040 max mem: 22448 +train: [15] [220/400] eta: 0:01:20 lr: 0.000061 loss: 2.1773 (2.1734) grad: 0.2390 (0.2415) time: 0.4283 data: 0.0043 max mem: 22448 +train: [15] [240/400] eta: 0:01:11 lr: 0.000059 loss: 2.1869 (2.1744) grad: 0.2452 (0.2419) time: 0.4286 data: 0.0043 max mem: 22448 +train: [15] [260/400] eta: 0:01:02 lr: 0.000058 loss: 2.2172 (2.1788) grad: 0.2456 (0.2421) time: 0.4332 data: 0.0042 max mem: 22448 +train: [15] [280/400] eta: 0:00:53 lr: 0.000057 loss: 2.1983 (2.1775) grad: 0.2371 (0.2416) time: 0.4331 data: 0.0041 max mem: 22448 +train: [15] [300/400] eta: 0:00:44 lr: 0.000056 loss: 2.1443 (2.1771) grad: 0.2384 (0.2419) time: 0.4309 data: 0.0041 max mem: 22448 +train: [15] [320/400] eta: 0:00:35 lr: 0.000054 loss: 2.1842 (2.1777) grad: 0.2401 (0.2418) time: 0.4302 data: 0.0040 max mem: 22448 +train: [15] [340/400] eta: 0:00:26 lr: 0.000053 loss: 2.1758 (2.1782) grad: 0.2401 (0.2417) time: 0.4332 data: 0.0040 max mem: 22448 +train: [15] [360/400] eta: 0:00:17 lr: 0.000052 loss: 2.1758 (2.1774) grad: 0.2428 (0.2419) time: 0.4334 data: 0.0040 max mem: 22448 +train: [15] [380/400] eta: 0:00:08 lr: 0.000051 loss: 2.1562 (2.1750) grad: 0.2345 (0.2415) time: 0.4303 data: 0.0039 max mem: 22448 +train: [15] [399/400] eta: 0:00:00 lr: 0.000050 loss: 2.1555 (2.1752) grad: 0.2345 (0.2414) time: 0.4426 data: 0.0042 max mem: 22448 +train: [15] Total time: 0:02:57 (0.4426 s / it) +train: [15] Summary: lr: 0.000050 loss: 2.1555 (2.1752) grad: 0.2345 (0.2414) +eval (validation): [15] [ 0/85] eta: 0:04:38 time: 3.2748 data: 2.9904 max mem: 22448 +eval (validation): [15] [20/85] eta: 0:00:32 time: 0.3616 data: 0.0042 max mem: 22448 +eval (validation): [15] [40/85] eta: 0:00:19 time: 0.3436 data: 0.0036 max mem: 22448 +eval (validation): [15] [60/85] eta: 0:00:09 time: 0.3231 data: 0.0039 max mem: 22448 +eval (validation): [15] [80/85] eta: 0:00:01 time: 0.3354 data: 0.0039 max mem: 22448 +eval (validation): [15] [84/85] eta: 0:00:00 time: 0.3343 data: 0.0038 max mem: 22448 +eval (validation): [15] Total time: 0:00:32 (0.3777 s / it) +cv: [15] best hparam: (0.38, 1.0) (018) ('018_lr3.8e-01_wd1.0e+00') loss: 2.355 acc: 0.285 f1: 0.227 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [16] [ 0/400] eta: 0:23:13 lr: nan time: 3.4831 data: 3.1064 max mem: 22448 +train: [16] [ 20/400] eta: 0:03:47 lr: 0.000048 loss: 2.1066 (2.1202) grad: 0.2160 (0.2264) time: 0.4553 data: 0.0044 max mem: 22448 +train: [16] [ 40/400] eta: 0:03:07 lr: 0.000047 loss: 2.1219 (2.1286) grad: 0.2281 (0.2275) time: 0.4363 data: 0.0043 max mem: 22448 +train: [16] [ 60/400] eta: 0:02:46 lr: 0.000046 loss: 2.1233 (2.1227) grad: 0.2283 (0.2288) time: 0.4269 data: 0.0040 max mem: 22448 +train: [16] [ 80/400] eta: 0:02:33 lr: 0.000045 loss: 2.1575 (2.1349) grad: 0.2307 (0.2319) time: 0.4469 data: 0.0040 max mem: 22448 +train: [16] [100/400] eta: 0:02:22 lr: 0.000044 loss: 2.1575 (2.1277) grad: 0.2404 (0.2328) time: 0.4585 data: 0.0043 max mem: 22448 +train: [16] [120/400] eta: 0:02:11 lr: 0.000043 loss: 2.1202 (2.1322) grad: 0.2380 (0.2337) time: 0.4488 data: 0.0042 max mem: 22448 +train: [16] [140/400] eta: 0:02:01 lr: 0.000042 loss: 2.1511 (2.1366) grad: 0.2322 (0.2338) time: 0.4410 data: 0.0041 max mem: 22448 +train: [16] [160/400] eta: 0:01:50 lr: 0.000041 loss: 2.1511 (2.1419) grad: 0.2394 (0.2355) time: 0.4320 data: 0.0040 max mem: 22448 +train: [16] [180/400] eta: 0:01:41 lr: 0.000040 loss: 2.1218 (2.1425) grad: 0.2415 (0.2356) time: 0.4443 data: 0.0041 max mem: 22448 +train: [16] [200/400] eta: 0:01:31 lr: 0.000039 loss: 2.1245 (2.1404) grad: 0.2335 (0.2348) time: 0.4384 data: 0.0040 max mem: 22448 +train: [16] [220/400] eta: 0:01:21 lr: 0.000038 loss: 2.1422 (2.1417) grad: 0.2260 (0.2344) time: 0.4293 data: 0.0040 max mem: 22448 +train: [16] [240/400] eta: 0:01:12 lr: 0.000036 loss: 2.1422 (2.1412) grad: 0.2260 (0.2348) time: 0.4330 data: 0.0040 max mem: 22448 +train: [16] [260/400] eta: 0:01:03 lr: 0.000035 loss: 2.1431 (2.1439) grad: 0.2442 (0.2354) time: 0.4366 data: 0.0041 max mem: 22448 +train: [16] [280/400] eta: 0:00:54 lr: 0.000034 loss: 2.1451 (2.1441) grad: 0.2406 (0.2355) time: 0.4316 data: 0.0041 max mem: 22448 +train: [16] [300/400] eta: 0:00:44 lr: 0.000033 loss: 2.1519 (2.1456) grad: 0.2364 (0.2357) time: 0.4394 data: 0.0042 max mem: 22448 +train: [16] [320/400] eta: 0:00:35 lr: 0.000032 loss: 2.2012 (2.1484) grad: 0.2353 (0.2359) time: 0.4367 data: 0.0042 max mem: 22448 +train: [16] [340/400] eta: 0:00:26 lr: 0.000031 loss: 2.1283 (2.1474) grad: 0.2359 (0.2359) time: 0.4298 data: 0.0039 max mem: 22448 +train: [16] [360/400] eta: 0:00:17 lr: 0.000031 loss: 2.1243 (2.1484) grad: 0.2359 (0.2362) time: 0.4323 data: 0.0040 max mem: 22448 +train: [16] [380/400] eta: 0:00:08 lr: 0.000030 loss: 2.1736 (2.1476) grad: 0.2366 (0.2365) time: 0.4407 data: 0.0042 max mem: 22448 +train: [16] [399/400] eta: 0:00:00 lr: 0.000029 loss: 2.1328 (2.1470) grad: 0.2435 (0.2370) time: 0.4360 data: 0.0041 max mem: 22448 +train: [16] Total time: 0:02:58 (0.4466 s / it) +train: [16] Summary: lr: 0.000029 loss: 2.1328 (2.1470) grad: 0.2435 (0.2370) +eval (validation): [16] [ 0/85] eta: 0:04:40 time: 3.2969 data: 3.0105 max mem: 22448 +eval (validation): [16] [20/85] eta: 0:00:31 time: 0.3379 data: 0.0043 max mem: 22448 +eval (validation): [16] [40/85] eta: 0:00:18 time: 0.3408 data: 0.0036 max mem: 22448 +eval (validation): [16] [60/85] eta: 0:00:09 time: 0.3415 data: 0.0041 max mem: 22448 +eval (validation): [16] [80/85] eta: 0:00:01 time: 0.3362 data: 0.0041 max mem: 22448 +eval (validation): [16] [84/85] eta: 0:00:00 time: 0.3287 data: 0.0040 max mem: 22448 +eval (validation): [16] Total time: 0:00:31 (0.3760 s / it) +cv: [16] best hparam: (0.38, 1.0) (018) ('018_lr3.8e-01_wd1.0e+00') loss: 2.354 acc: 0.287 f1: 0.229 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [17] [ 0/400] eta: 0:26:05 lr: nan time: 3.9141 data: 3.5238 max mem: 22448 +train: [17] [ 20/400] eta: 0:03:51 lr: 0.000028 loss: 2.0823 (2.1018) grad: 0.2144 (0.2234) time: 0.4428 data: 0.0031 max mem: 22448 +train: [17] [ 40/400] eta: 0:03:09 lr: 0.000027 loss: 2.0884 (2.1147) grad: 0.2249 (0.2265) time: 0.4398 data: 0.0038 max mem: 22448 +train: [17] [ 60/400] eta: 0:02:48 lr: 0.000026 loss: 2.1220 (2.1238) grad: 0.2255 (0.2255) time: 0.4319 data: 0.0042 max mem: 22448 +train: [17] [ 80/400] eta: 0:02:34 lr: 0.000025 loss: 2.1176 (2.1143) grad: 0.2207 (0.2262) time: 0.4443 data: 0.0043 max mem: 22448 +train: [17] [100/400] eta: 0:02:22 lr: 0.000024 loss: 2.1176 (2.1213) grad: 0.2234 (0.2260) time: 0.4394 data: 0.0043 max mem: 22448 +train: [17] [120/400] eta: 0:02:11 lr: 0.000023 loss: 2.1281 (2.1204) grad: 0.2246 (0.2270) time: 0.4442 data: 0.0043 max mem: 22448 +train: [17] [140/400] eta: 0:02:01 lr: 0.000023 loss: 2.1162 (2.1181) grad: 0.2296 (0.2274) time: 0.4493 data: 0.0041 max mem: 22448 +train: [17] [160/400] eta: 0:01:50 lr: 0.000022 loss: 2.1067 (2.1163) grad: 0.2296 (0.2279) time: 0.4300 data: 0.0041 max mem: 22448 +train: [17] [180/400] eta: 0:01:41 lr: 0.000021 loss: 2.1125 (2.1155) grad: 0.2291 (0.2276) time: 0.4447 data: 0.0043 max mem: 22448 +train: [17] [200/400] eta: 0:01:31 lr: 0.000020 loss: 2.1093 (2.1150) grad: 0.2280 (0.2274) time: 0.4398 data: 0.0042 max mem: 22448 +train: [17] [220/400] eta: 0:01:22 lr: 0.000019 loss: 2.1159 (2.1164) grad: 0.2245 (0.2281) time: 0.4333 data: 0.0043 max mem: 22448 +train: [17] [240/400] eta: 0:01:12 lr: 0.000019 loss: 2.1340 (2.1163) grad: 0.2286 (0.2290) time: 0.4338 data: 0.0043 max mem: 22448 +train: [17] [260/400] eta: 0:01:03 lr: 0.000018 loss: 2.0847 (2.1156) grad: 0.2321 (0.2294) time: 0.4395 data: 0.0042 max mem: 22448 +train: [17] [280/400] eta: 0:00:54 lr: 0.000017 loss: 2.1076 (2.1170) grad: 0.2256 (0.2292) time: 0.4405 data: 0.0043 max mem: 22448 +train: [17] [300/400] eta: 0:00:45 lr: 0.000016 loss: 2.1511 (2.1197) grad: 0.2236 (0.2292) time: 0.4378 data: 0.0041 max mem: 22448 +train: [17] [320/400] eta: 0:00:35 lr: 0.000016 loss: 2.1396 (2.1199) grad: 0.2204 (0.2286) time: 0.4317 data: 0.0041 max mem: 22448 +train: [17] [340/400] eta: 0:00:26 lr: 0.000015 loss: 2.1199 (2.1201) grad: 0.2221 (0.2289) time: 0.4381 data: 0.0042 max mem: 22448 +train: [17] [360/400] eta: 0:00:17 lr: 0.000014 loss: 2.1418 (2.1211) grad: 0.2268 (0.2291) time: 0.4296 data: 0.0041 max mem: 22448 +train: [17] [380/400] eta: 0:00:08 lr: 0.000014 loss: 2.1185 (2.1202) grad: 0.2285 (0.2298) time: 0.4431 data: 0.0044 max mem: 22448 +train: [17] [399/400] eta: 0:00:00 lr: 0.000013 loss: 2.1003 (2.1189) grad: 0.2315 (0.2296) time: 0.4536 data: 0.0042 max mem: 22448 +train: [17] Total time: 0:02:59 (0.4484 s / it) +train: [17] Summary: lr: 0.000013 loss: 2.1003 (2.1189) grad: 0.2315 (0.2296) +eval (validation): [17] [ 0/85] eta: 0:04:40 time: 3.3038 data: 3.0767 max mem: 22448 +eval (validation): [17] [20/85] eta: 0:00:32 time: 0.3519 data: 0.0038 max mem: 22448 +eval (validation): [17] [40/85] eta: 0:00:18 time: 0.3373 data: 0.0038 max mem: 22448 +eval (validation): [17] [60/85] eta: 0:00:09 time: 0.3381 data: 0.0042 max mem: 22448 +eval (validation): [17] [80/85] eta: 0:00:01 time: 0.3413 data: 0.0041 max mem: 22448 +eval (validation): [17] [84/85] eta: 0:00:00 time: 0.3296 data: 0.0039 max mem: 22448 +eval (validation): [17] Total time: 0:00:32 (0.3785 s / it) +cv: [17] best hparam: (0.44, 1.0) (019) ('019_lr4.4e-01_wd1.0e+00') loss: 2.355 acc: 0.288 f1: 0.233 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/eval_v2/nsd_cococlip__patch__attn/checkpoint-best.pth +train: [18] [ 0/400] eta: 0:23:08 lr: nan time: 3.4707 data: 3.0868 max mem: 22448 +train: [18] [ 20/400] eta: 0:03:41 lr: 0.000012 loss: 2.1135 (2.1263) grad: 0.2215 (0.2264) time: 0.4376 data: 0.0039 max mem: 22448 +train: [18] [ 40/400] eta: 0:03:03 lr: 0.000012 loss: 2.1015 (2.0960) grad: 0.2215 (0.2257) time: 0.4348 data: 0.0040 max mem: 22448 +train: [18] [ 60/400] eta: 0:02:45 lr: 0.000011 loss: 2.0505 (2.0973) grad: 0.2324 (0.2293) time: 0.4410 data: 0.0041 max mem: 22448 +train: [18] [ 80/400] eta: 0:02:32 lr: 0.000011 loss: 2.0807 (2.0955) grad: 0.2312 (0.2277) time: 0.4404 data: 0.0041 max mem: 22448 +train: [18] [100/400] eta: 0:02:21 lr: 0.000010 loss: 2.0933 (2.0985) grad: 0.2215 (0.2270) time: 0.4506 data: 0.0044 max mem: 22448 +train: [18] [120/400] eta: 0:02:10 lr: 0.000009 loss: 2.0867 (2.0944) grad: 0.2254 (0.2266) time: 0.4363 data: 0.0043 max mem: 22448 +train: [18] [140/400] eta: 0:01:59 lr: 0.000009 loss: 2.0867 (2.0984) grad: 0.2263 (0.2268) time: 0.4355 data: 0.0042 max mem: 22448 +train: [18] [160/400] eta: 0:01:49 lr: 0.000008 loss: 2.0954 (2.0991) grad: 0.2263 (0.2263) time: 0.4235 data: 0.0042 max mem: 22448 +train: [18] [180/400] eta: 0:01:40 lr: 0.000008 loss: 2.0938 (2.0975) grad: 0.2263 (0.2270) time: 0.4448 data: 0.0042 max mem: 22448 +train: [18] [200/400] eta: 0:01:30 lr: 0.000007 loss: 2.0902 (2.0977) grad: 0.2231 (0.2267) time: 0.4293 data: 0.0045 max mem: 22448 +train: [18] [220/400] eta: 0:01:21 lr: 0.000007 loss: 2.1089 (2.1001) grad: 0.2237 (0.2268) time: 0.4269 data: 0.0042 max mem: 22448 +train: [18] [240/400] eta: 0:01:11 lr: 0.000006 loss: 2.1213 (2.1032) grad: 0.2252 (0.2266) time: 0.4338 data: 0.0043 max mem: 22448 +train: [18] [260/400] eta: 0:01:02 lr: 0.000006 loss: 2.1143 (2.1038) grad: 0.2252 (0.2265) time: 0.4297 data: 0.0039 max mem: 22448 +train: [18] [280/400] eta: 0:00:53 lr: 0.000006 loss: 2.0918 (2.1027) grad: 0.2262 (0.2264) time: 0.4301 data: 0.0041 max mem: 22448 +train: [18] [300/400] eta: 0:00:44 lr: 0.000005 loss: 2.0846 (2.1018) grad: 0.2249 (0.2263) time: 0.4314 data: 0.0042 max mem: 22448 +train: [18] [320/400] eta: 0:00:35 lr: 0.000005 loss: 2.1007 (2.1043) grad: 0.2249 (0.2265) time: 0.4357 data: 0.0041 max mem: 22448 +train: [18] [340/400] eta: 0:00:26 lr: 0.000004 loss: 2.0972 (2.1021) grad: 0.2243 (0.2262) time: 0.4295 data: 0.0042 max mem: 22448 +train: [18] [360/400] eta: 0:00:17 lr: 0.000004 loss: 2.0835 (2.1031) grad: 0.2243 (0.2263) time: 0.4476 data: 0.0040 max mem: 22448 +train: [18] [380/400] eta: 0:00:08 lr: 0.000004 loss: 2.0887 (2.1030) grad: 0.2287 (0.2263) time: 0.4401 data: 0.0042 max mem: 22448 +train: [18] [399/400] eta: 0:00:00 lr: 0.000003 loss: 2.0843 (2.1013) grad: 0.2255 (0.2264) time: 0.4436 data: 0.0041 max mem: 22448 +train: [18] Total time: 0:02:57 (0.4439 s / it) +train: [18] Summary: lr: 0.000003 loss: 2.0843 (2.1013) grad: 0.2255 (0.2264) +eval (validation): [18] [ 0/85] eta: 0:04:33 time: 3.2191 data: 2.9881 max mem: 22448 +eval (validation): [18] [20/85] eta: 0:00:31 time: 0.3546 data: 0.0048 max mem: 22448 +eval (validation): [18] [40/85] eta: 0:00:18 time: 0.3493 data: 0.0037 max mem: 22448 +eval (validation): [18] [60/85] eta: 0:00:09 time: 0.3313 data: 0.0041 max mem: 22448 +eval (validation): [18] [80/85] eta: 0:00:01 time: 0.3453 data: 0.0040 max mem: 22448 +eval (validation): [18] [84/85] eta: 0:00:00 time: 0.3427 data: 0.0040 max mem: 22448 +eval (validation): [18] Total time: 0:00:32 (0.3817 s / it) +cv: [18] best hparam: (0.44, 1.0) (019) ('019_lr4.4e-01_wd1.0e+00') loss: 2.356 acc: 0.287 f1: 0.231 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [19] [ 0/400] eta: 0:23:08 lr: nan time: 3.4714 data: 3.0919 max mem: 22448 +train: [19] [ 20/400] eta: 0:03:40 lr: 0.000003 loss: 2.0854 (2.0976) grad: 0.2138 (0.2201) time: 0.4348 data: 0.0048 max mem: 22448 +train: [19] [ 40/400] eta: 0:03:02 lr: 0.000003 loss: 2.0686 (2.0719) grad: 0.2183 (0.2222) time: 0.4324 data: 0.0044 max mem: 22448 +train: [19] [ 60/400] eta: 0:02:43 lr: 0.000002 loss: 2.0884 (2.0935) grad: 0.2219 (0.2230) time: 0.4263 data: 0.0041 max mem: 22448 +train: [19] [ 80/400] eta: 0:02:30 lr: 0.000002 loss: 2.1091 (2.0964) grad: 0.2234 (0.2225) time: 0.4437 data: 0.0042 max mem: 22448 +train: [19] [100/400] eta: 0:02:19 lr: 0.000002 loss: 2.0841 (2.0946) grad: 0.2238 (0.2229) time: 0.4422 data: 0.0041 max mem: 22448 +train: [19] [120/400] eta: 0:02:09 lr: 0.000002 loss: 2.0871 (2.0998) grad: 0.2246 (0.2240) time: 0.4365 data: 0.0043 max mem: 22448 +train: [19] [140/400] eta: 0:01:59 lr: 0.000001 loss: 2.1129 (2.0974) grad: 0.2225 (0.2233) time: 0.4487 data: 0.0042 max mem: 22448 +train: [19] [160/400] eta: 0:01:49 lr: 0.000001 loss: 2.0812 (2.0933) grad: 0.2152 (0.2232) time: 0.4336 data: 0.0040 max mem: 22448 +train: [19] [180/400] eta: 0:01:40 lr: 0.000001 loss: 2.0641 (2.0902) grad: 0.2257 (0.2240) time: 0.4435 data: 0.0042 max mem: 22448 +train: [19] [200/400] eta: 0:01:30 lr: 0.000001 loss: 2.0641 (2.0892) grad: 0.2262 (0.2235) time: 0.4335 data: 0.0042 max mem: 22448 +train: [19] [220/400] eta: 0:01:21 lr: 0.000001 loss: 2.0841 (2.0888) grad: 0.2166 (0.2231) time: 0.4301 data: 0.0042 max mem: 22448 +train: [19] [240/400] eta: 0:01:11 lr: 0.000001 loss: 2.0841 (2.0868) grad: 0.2166 (0.2232) time: 0.4214 data: 0.0040 max mem: 22448 +train: [19] [260/400] eta: 0:01:02 lr: 0.000000 loss: 2.0586 (2.0863) grad: 0.2208 (0.2231) time: 0.4378 data: 0.0042 max mem: 22448 +train: [19] [280/400] eta: 0:00:53 lr: 0.000000 loss: 2.0926 (2.0892) grad: 0.2208 (0.2230) time: 0.4399 data: 0.0042 max mem: 22448 +train: [19] [300/400] eta: 0:00:44 lr: 0.000000 loss: 2.1176 (2.0898) grad: 0.2211 (0.2228) time: 0.4257 data: 0.0042 max mem: 22448 +train: [19] [320/400] eta: 0:00:35 lr: 0.000000 loss: 2.1079 (2.0915) grad: 0.2211 (0.2231) time: 0.4364 data: 0.0043 max mem: 22448 +train: [19] [340/400] eta: 0:00:26 lr: 0.000000 loss: 2.1293 (2.0938) grad: 0.2216 (0.2230) time: 0.4288 data: 0.0041 max mem: 22448 +train: [19] [360/400] eta: 0:00:17 lr: 0.000000 loss: 2.1107 (2.0945) grad: 0.2197 (0.2228) time: 0.4357 data: 0.0040 max mem: 22448 +train: [19] [380/400] eta: 0:00:08 lr: 0.000000 loss: 2.0800 (2.0937) grad: 0.2197 (0.2228) time: 0.4242 data: 0.0040 max mem: 22448 +train: [19] [399/400] eta: 0:00:00 lr: 0.000000 loss: 2.0943 (2.0959) grad: 0.2206 (0.2228) time: 0.4380 data: 0.0041 max mem: 22448 +train: [19] Total time: 0:02:57 (0.4426 s / it) +train: [19] Summary: lr: 0.000000 loss: 2.0943 (2.0959) grad: 0.2206 (0.2228) +eval (validation): [19] [ 0/85] eta: 0:04:38 time: 3.2781 data: 3.0002 max mem: 22448 +eval (validation): [19] [20/85] eta: 0:00:32 time: 0.3625 data: 0.0051 max mem: 22448 +eval (validation): [19] [40/85] eta: 0:00:19 time: 0.3462 data: 0.0032 max mem: 22448 +eval (validation): [19] [60/85] eta: 0:00:09 time: 0.3263 data: 0.0038 max mem: 22448 +eval (validation): [19] [80/85] eta: 0:00:01 time: 0.3346 data: 0.0040 max mem: 22448 +eval (validation): [19] [84/85] eta: 0:00:00 time: 0.3277 data: 0.0039 max mem: 22448 +eval (validation): [19] Total time: 0:00:32 (0.3796 s / it) +cv: [19] best hparam: (0.38, 1.0) (018) ('018_lr3.8e-01_wd1.0e+00') loss: 2.349 acc: 0.288 f1: 0.231 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +evaluating last checkpoint: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +eval model info: +{"score": 0.28755998523440385, "hparam": [0.38, 1.0], "hparam_id": 18, "epoch": 19, "is_best": false, "best_score": 0.2884828349944629} +eval (train): [20] [ 0/509] eta: 0:26:03 time: 3.0718 data: 2.7847 max mem: 22448 +eval (train): [20] [ 20/509] eta: 0:03:57 time: 0.3572 data: 0.0050 max mem: 22448 +eval (train): [20] [ 40/509] eta: 0:03:21 time: 0.3691 data: 0.0048 max mem: 22448 +eval (train): [20] [ 60/509] eta: 0:03:01 time: 0.3506 data: 0.0041 max mem: 22448 +eval (train): [20] [ 80/509] eta: 0:02:46 time: 0.3400 data: 0.0041 max mem: 22448 +eval (train): [20] [100/509] eta: 0:02:36 time: 0.3579 data: 0.0045 max mem: 22448 +eval (train): [20] [120/509] eta: 0:02:27 time: 0.3618 data: 0.0043 max mem: 22448 +eval (train): [20] [140/509] eta: 0:02:20 time: 0.3865 data: 0.0048 max mem: 22448 +eval (train): [20] [160/509] eta: 0:02:11 time: 0.3595 data: 0.0045 max mem: 22448 +eval (train): [20] [180/509] eta: 0:02:03 time: 0.3586 data: 0.0049 max mem: 22448 +eval (train): [20] [200/509] eta: 0:01:55 time: 0.3573 data: 0.0044 max mem: 22448 +eval (train): [20] [220/509] eta: 0:01:47 time: 0.3510 data: 0.0040 max mem: 22448 +eval (train): [20] [240/509] eta: 0:01:39 time: 0.3654 data: 0.0046 max mem: 22448 +eval (train): [20] [260/509] eta: 0:01:31 time: 0.3517 data: 0.0042 max mem: 22448 +eval (train): [20] [280/509] eta: 0:01:24 time: 0.3676 data: 0.0042 max mem: 22448 +eval (train): [20] [300/509] eta: 0:01:16 time: 0.3529 data: 0.0044 max mem: 22448 +eval (train): [20] [320/509] eta: 0:01:09 time: 0.3528 data: 0.0043 max mem: 22448 +eval (train): [20] [340/509] eta: 0:01:01 time: 0.3532 data: 0.0041 max mem: 22448 +eval (train): [20] [360/509] eta: 0:00:54 time: 0.3715 data: 0.0041 max mem: 22448 +eval (train): [20] [380/509] eta: 0:00:47 time: 0.3496 data: 0.0042 max mem: 22448 +eval (train): [20] [400/509] eta: 0:00:39 time: 0.3527 data: 0.0041 max mem: 22448 +eval (train): [20] [420/509] eta: 0:00:32 time: 0.3574 data: 0.0045 max mem: 22448 +eval (train): [20] [440/509] eta: 0:00:25 time: 0.3458 data: 0.0043 max mem: 22448 +eval (train): [20] [460/509] eta: 0:00:17 time: 0.3575 data: 0.0040 max mem: 22448 +eval (train): [20] [480/509] eta: 0:00:10 time: 0.3629 data: 0.0042 max mem: 22448 +eval (train): [20] [500/509] eta: 0:00:03 time: 0.3420 data: 0.0044 max mem: 22448 +eval (train): [20] [508/509] eta: 0:00:00 time: 0.3276 data: 0.0040 max mem: 22448 +eval (train): [20] Total time: 0:03:04 (0.3632 s / it) +eval (validation): [20] [ 0/85] eta: 0:04:56 time: 3.4916 data: 3.2097 max mem: 22448 +eval (validation): [20] [20/85] eta: 0:00:33 time: 0.3586 data: 0.0040 max mem: 22448 +eval (validation): [20] [40/85] eta: 0:00:19 time: 0.3607 data: 0.0038 max mem: 22448 +eval (validation): [20] [60/85] eta: 0:00:10 time: 0.3339 data: 0.0038 max mem: 22448 +eval (validation): [20] [80/85] eta: 0:00:01 time: 0.3382 data: 0.0038 max mem: 22448 +eval (validation): [20] [84/85] eta: 0:00:00 time: 0.3347 data: 0.0037 max mem: 22448 +eval (validation): [20] Total time: 0:00:32 (0.3869 s / it) +eval (test): [20] [ 0/85] eta: 0:04:46 time: 3.3704 data: 3.0735 max mem: 22448 +eval (test): [20] [20/85] eta: 0:00:34 time: 0.3949 data: 0.0053 max mem: 22448 +eval (test): [20] [40/85] eta: 0:00:20 time: 0.3689 data: 0.0039 max mem: 22448 +eval (test): [20] [60/85] eta: 0:00:10 time: 0.3573 data: 0.0044 max mem: 22448 +eval (test): [20] [80/85] eta: 0:00:02 time: 0.3316 data: 0.0046 max mem: 22448 +eval (test): [20] [84/85] eta: 0:00:00 time: 0.3169 data: 0.0042 max mem: 22448 +eval (test): [20] Total time: 0:00:33 (0.3980 s / it) +eval (testid): [20] [ 0/82] eta: 0:04:30 time: 3.3030 data: 3.0485 max mem: 22448 +eval (testid): [20] [20/82] eta: 0:00:31 time: 0.3664 data: 0.0049 max mem: 22448 +eval (testid): [20] [40/82] eta: 0:00:18 time: 0.3902 data: 0.0044 max mem: 22448 +eval (testid): [20] [60/82] eta: 0:00:08 time: 0.3256 data: 0.0034 max mem: 22448 +eval (testid): [20] [80/82] eta: 0:00:00 time: 0.3297 data: 0.0039 max mem: 22448 +eval (testid): [20] [81/82] eta: 0:00:00 time: 0.3163 data: 0.0039 max mem: 22448 +eval (testid): [20] Total time: 0:00:31 (0.3897 s / it) +evaluating best checkpoint: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/eval_v2/nsd_cococlip__patch__attn/checkpoint-best.pth +eval model info: +{"score": 0.2884828349944629, "hparam": [0.44, 1.0], "hparam_id": 19, "epoch": 17, "is_best": true, "best_score": 0.2884828349944629} +eval (train): [20] [ 0/509] eta: 0:28:28 time: 3.3567 data: 3.0809 max mem: 22448 +eval (train): [20] [ 20/509] eta: 0:04:10 time: 0.3697 data: 0.0130 max mem: 22448 +eval (train): [20] [ 40/509] eta: 0:03:26 time: 0.3631 data: 0.0043 max mem: 22448 +eval (train): [20] [ 60/509] eta: 0:03:05 time: 0.3570 data: 0.0039 max mem: 22448 +eval (train): [20] [ 80/509] eta: 0:02:47 time: 0.3276 data: 0.0040 max mem: 22448 +eval (train): [20] [100/509] eta: 0:02:39 time: 0.3831 data: 0.0048 max mem: 22448 +eval (train): [20] [120/509] eta: 0:02:30 time: 0.3713 data: 0.0040 max mem: 22448 +eval (train): [20] [140/509] eta: 0:02:22 time: 0.3754 data: 0.0048 max mem: 22448 +eval (train): [20] [160/509] eta: 0:02:13 time: 0.3733 data: 0.0042 max mem: 22448 +eval (train): [20] [180/509] eta: 0:02:05 time: 0.3616 data: 0.0044 max mem: 22448 +eval (train): [20] [200/509] eta: 0:01:57 time: 0.3620 data: 0.0044 max mem: 22448 +eval (train): [20] [220/509] eta: 0:01:48 time: 0.3531 data: 0.0039 max mem: 22448 +eval (train): [20] [240/509] eta: 0:01:40 time: 0.3469 data: 0.0043 max mem: 22448 +eval (train): [20] [260/509] eta: 0:01:32 time: 0.3578 data: 0.0041 max mem: 22448 +eval (train): [20] [280/509] eta: 0:01:25 time: 0.3523 data: 0.0041 max mem: 22448 +eval (train): [20] [300/509] eta: 0:01:18 time: 0.4007 data: 0.0048 max mem: 22448 +eval (train): [20] [320/509] eta: 0:01:10 time: 0.3963 data: 0.0044 max mem: 22448 +eval (train): [20] [340/509] eta: 0:01:03 time: 0.3922 data: 0.0047 max mem: 22448 +eval (train): [20] [360/509] eta: 0:00:56 time: 0.4022 data: 0.0048 max mem: 22448 +eval (train): [20] [380/509] eta: 0:00:48 time: 0.3806 data: 0.0048 max mem: 22448 +eval (train): [20] [400/509] eta: 0:00:41 time: 0.3508 data: 0.0040 max mem: 22448 +eval (train): [20] [420/509] eta: 0:00:33 time: 0.3433 data: 0.0039 max mem: 22448 +eval (train): [20] [440/509] eta: 0:00:25 time: 0.3615 data: 0.0043 max mem: 22448 +eval (train): [20] [460/509] eta: 0:00:18 time: 0.3582 data: 0.0041 max mem: 22448 +eval (train): [20] [480/509] eta: 0:00:10 time: 0.3278 data: 0.0035 max mem: 22448 +eval (train): [20] [500/509] eta: 0:00:03 time: 0.3176 data: 0.0036 max mem: 22448 +eval (train): [20] [508/509] eta: 0:00:00 time: 0.3133 data: 0.0038 max mem: 22448 +eval (train): [20] Total time: 0:03:08 (0.3699 s / it) +eval (validation): [20] [ 0/85] eta: 0:04:19 time: 3.0527 data: 2.7515 max mem: 22448 +eval (validation): [20] [20/85] eta: 0:00:33 time: 0.3866 data: 0.0055 max mem: 22448 +eval (validation): [20] [40/85] eta: 0:00:19 time: 0.3620 data: 0.0035 max mem: 22448 +eval (validation): [20] [60/85] eta: 0:00:10 time: 0.3213 data: 0.0036 max mem: 22448 +eval (validation): [20] [80/85] eta: 0:00:01 time: 0.3274 data: 0.0036 max mem: 22448 +eval (validation): [20] [84/85] eta: 0:00:00 time: 0.3263 data: 0.0036 max mem: 22448 +eval (validation): [20] Total time: 0:00:32 (0.3827 s / it) +eval (test): [20] [ 0/85] eta: 0:04:46 time: 3.3683 data: 3.1054 max mem: 22448 +eval (test): [20] [20/85] eta: 0:00:34 time: 0.3868 data: 0.0042 max mem: 22448 +eval (test): [20] [40/85] eta: 0:00:19 time: 0.3553 data: 0.0032 max mem: 22448 +eval (test): [20] [60/85] eta: 0:00:10 time: 0.3605 data: 0.0042 max mem: 22448 +eval (test): [20] [80/85] eta: 0:00:01 time: 0.3268 data: 0.0038 max mem: 22448 +eval (test): [20] [84/85] eta: 0:00:00 time: 0.3199 data: 0.0037 max mem: 22448 +eval (test): [20] Total time: 0:00:33 (0.3930 s / it) +eval (testid): [20] [ 0/82] eta: 0:04:27 time: 3.2656 data: 2.9663 max mem: 22448 +eval (testid): [20] [20/82] eta: 0:00:31 time: 0.3712 data: 0.0047 max mem: 22448 +eval (testid): [20] [40/82] eta: 0:00:18 time: 0.3505 data: 0.0034 max mem: 22448 +eval (testid): [20] [60/82] eta: 0:00:08 time: 0.3369 data: 0.0037 max mem: 22448 +eval (testid): [20] [80/82] eta: 0:00:00 time: 0.3176 data: 0.0037 max mem: 22448 +eval (testid): [20] [81/82] eta: 0:00:00 time: 0.3021 data: 0.0034 max mem: 22448 +eval (testid): [20] Total time: 0:00:31 (0.3795 s / it) +eval results: + +| model | repr | clf | dataset | ckpt | epoch | lr | wd | hparam_id | hparam | split | loss | acc | acc_std | f1 | f1_std | +|:---------|:-------|:------|:-------------|:-------|--------:|---------:|-----:|------------:|:------------|:-----------|-------:|--------:|----------:|--------:|----------:| +| flat_mae | patch | attn | nsd_cococlip | best | 17 | 0.000132 | 0.05 | 19 | [0.44, 1.0] | train | 1.9964 | 0.40358 | 0.0024174 | 0.3508 | 0.0026154 | +| flat_mae | patch | attn | nsd_cococlip | best | 17 | 0.000132 | 0.05 | 19 | [0.44, 1.0] | validation | 2.3547 | 0.28848 | 0.0054382 | 0.23331 | 0.005111 | +| flat_mae | patch | attn | nsd_cococlip | best | 17 | 0.000132 | 0.05 | 19 | [0.44, 1.0] | test | 2.2413 | 0.30538 | 0.005364 | 0.23928 | 0.0055181 | +| flat_mae | patch | attn | nsd_cococlip | best | 17 | 0.000132 | 0.05 | 19 | [0.44, 1.0] | testid | 2.2423 | 0.31116 | 0.00557 | 0.25579 | 0.0053649 | + + +done! total time: 1:22:14 diff --git a/input_space_v3/flat_lr1e-3_3/eval_v2/nsd_cococlip__patch__attn/train_log.json b/input_space_v3/flat_lr1e-3_3/eval_v2/nsd_cococlip__patch__attn/train_log.json new file mode 100644 index 0000000000000000000000000000000000000000..7ecae31575271fc9dba801956820f56c998f3f5c --- /dev/null +++ b/input_space_v3/flat_lr1e-3_3/eval_v2/nsd_cococlip__patch__attn/train_log.json @@ -0,0 +1,20 @@ +{"epoch": 0, "train/lr": 2.987987987987988e-05, "train/loss": 3.1409518444538116, "train/grad": 0.16223378725349902, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.1938623046875, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.1929833984375, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.1915087890625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.1901171875, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.18863037109375, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.186796875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.184815673828125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.182760009765625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.180242919921875, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.17774658203125, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.175477294921875, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.172532958984375, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.169920654296875, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.1667626953125, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.16411865234375, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.1620654296875, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.15974609375, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.157506103515625, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.155408935546875, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.153704833984375, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.15194091796875, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.150455322265625, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.149007568359375, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.14773681640625, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.1466943359375, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.145625, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.1448681640625, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.14442626953125, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.144017333984375, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.1437060546875, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.1436083984375, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.14361083984375, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.143773193359375, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.1440423583984374, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.1441064453125, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.144344482421875, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.1446441650390624, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.14521484375, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.145675048828125, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.1435198974609375, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.1341824340820312, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.1208056640625, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.0981820678710936, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.075223693847656, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.049444808959961, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.0285943603515624, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.011092300415039, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.993372344970703, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.978020706176758, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.025285927522927524, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.025211564246565104, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.025090886913239956, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.02497475385200232, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.024861879902891813, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.024711255840957166, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.024548488962464036, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.024375857999548316, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.024163059988059104, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.023953693704679608, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.02376411244273186, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.02350817714817822, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.02329122496303171, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.023020193236880003, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.022804871732369066, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.02263155340682715, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.022448881207965315, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.022272778898477553, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.022116089831106366, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.02199661615304649, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.02187512578908354, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.021776211257092656, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.02168830409646034, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.02161389430053532, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.021552629717625678, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.021498431023210286, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.021460672221146525, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.02143685095012188, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.021409712117165327, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.021390047413296996, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.021374814785085617, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.02135754663962871, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.021323392898775637, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.021271660597994922, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.021184922149404883, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.021063922676257788, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0209072329942137, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.020744954966939986, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.02057325059082359, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.020536362254060806, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.020861092442646622, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.02146940120495856, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.022303374544717373, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.023228114997036756, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0242105308547616, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.025355960461311042, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.026457614554092287, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.027740615243092178, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.028973286147229372, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.183333158493042, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.180523157119751, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1760973930358887, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1719982624053955, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1681463718414307, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.163200855255127, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1581332683563232, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.153193473815918, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1475932598114014, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1426000595092773, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.138636827468872, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1340279579162598, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1308324337005615, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.127810001373291, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1260757446289062, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.125089406967163, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.124358654022217, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1239521503448486, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1237595081329346, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.123746871948242, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.1238973140716553, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.1243128776550293, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.1250345706939697, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.1261911392211914, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.127633810043335, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.1295087337493896, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.1311113834381104, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.1324570178985596, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.133645534515381, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.1335842609405518, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.131903648376465, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.129687786102295, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.1264076232910156, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.1239919662475586, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.1220133304595947, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.1218619346618652, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.1234707832336426, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.1231250762939453, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.1080212593078613, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.993952751159668, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.8399269580841064, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.7647528648376465, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.6929006576538086, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.6612141132354736, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.6200802326202393, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.610142230987549, "validation/loss_046_lr3.6e+01_wd1.0e+00": 2.5955145359039307, "validation/loss_047_lr4.3e+01_wd1.0e+00": 2.5720510482788086, "validation/loss_048_lr5.0e+01_wd1.0e+00": 2.668534278869629, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.03857511997046881, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.041343669250646, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.04392764857881137, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.045035068290882246, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.04540420819490587, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.04964931709117756, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.05334071613141381, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.05075673680324843, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.05389442598744924, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.058693244739756366, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.061461794019933555, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06423034330011074, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06533776301218161, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06626061277224068, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06699889258028793, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.07013658176448874, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.07013658176448874, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06976744186046512, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06995201181247693, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.06939830195644149, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.07069029162052418, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.07013658176448874, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.0695828719084533, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.07290513104466592, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.06533776301218161, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.055740125507567365, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.05297157622739018, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.0518641565153193, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.05149501661129568, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.05167958656330749, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.05518641565153193, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.06201550387596899, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.07032115171650055, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.07493540051679587, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.07751937984496124, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.08379475821336287, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.0799187892211148, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.07308970099667775, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.07825765965300849, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.11590992986341823, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.16020671834625322, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.1849390919158361, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.19416758951642674, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.21391657438169065, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.22296050203026946, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.23163528977482467, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.2188999630860096, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.22554448135843486, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.1984126984126984, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.012319860555000442, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.013094152156026393, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.012908867869012566, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.012484666724398167, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.011894216082756396, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.01335673446727101, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.015267419217900305, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.016682366703077264, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.018762958871772564, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.01831302341310022, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.017554952519189208, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.015414326550458308, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.013965868618766322, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.011579340945036003, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.010263535289930284, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.01078986834421617, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.01054381308953172, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.010236783776630938, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.010142829740056125, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.010026019189365803, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.010287336932073775, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.010240302499877363, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.01164260069540092, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.015655543956227102, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.014339923930242325, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.009506030815530057, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.006851032442485319, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.005376245827408394, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.005093700097466992, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.005289778381399458, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.007865119025841886, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.009642983164541548, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.012298082631298148, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.014967520855103812, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.019681620122624203, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.024800452111343945, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.021076369075256954, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.01686175296017399, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.02058013029186966, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.05338308192846344, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.08443149451915172, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.10121311428957791, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.1143308386413054, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.13067916471823068, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.14909974210307322, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.15390279410381724, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.14583047015620434, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.15199048654793754, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.132922779342885, "id_best": 45, "lr_best": 0.0093, "wd_best": 0.05, "train/loss_best": 3.0285943603515624, "validation/loss_best": 2.610142230987549, "validation/acc_best": 0.23163528977482467, "validation/f1_best": 0.15390279410381724} +{"epoch": 1, "train/lr": 8.993993993993998e-05, "train/loss": 2.9771524024009706, "train/grad": 0.1822414231300354, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.164271240234375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.16055908203125, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.1554931640625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.151256103515625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.147816162109375, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.143795166015625, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.140443115234375, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.13764892578125, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.134964599609375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.13313232421875, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.131839599609375, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.13063720703125, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.129912109375, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.12924072265625, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.12898193359375, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.128798828125, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.12861572265625, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.12832275390625, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.128121337890625, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.127840576171875, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.1275830078125, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.12725830078125, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.126890869140625, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.126541748046875, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.12609619140625, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.12555908203125, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.125211181640625, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.124852294921875, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.124212646484375, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.1213623046875, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.1075311279296876, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.0734385681152343, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.0150633239746094, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.9612371063232423, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.8923278045654297, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.8225450897216797, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.7585016250610352, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.7041750812530516, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.65055326461792, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.5983525848388673, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.576188802719116, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.5689102697372435, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.5517399644851686, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.539227695465088, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.5414733600616457, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.562625789642334, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.6025364542007448, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.651960027217865, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.6848248481750487, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.022489072852768004, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.02217629400547594, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.021727323471568524, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.021355184186249973, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.02104970396030694, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.020712432339787482, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.020427096053026617, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.020200838558375834, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.019998206119053067, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.01986553015653044, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.019786546621471644, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.019725090963765977, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.019703030455857515, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.019706497276201843, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.01972397188190371, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.01974595433566719, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.01977572781033814, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.0198109389282763, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.01984707829076797, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.019879434509202838, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.019913656045682727, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.019943250906653703, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.019965312462300062, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.01997339471708983, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.01995243761688471, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.019882763945497574, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.019772527660243212, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.019639864987693725, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.01941497081425041, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.019133463972248136, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.019165736003778876, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.019636012949049472, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.020720630907453595, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.021839626152068376, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0231625427166, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.02458957416471094, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.02616249657701701, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.027735215490683914, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.029500974086113275, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.03126811302267015, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.03292075419798493, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.034194594882428646, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.03523305654525757, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.03611546748317778, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0379346101731062, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.03979913150891662, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.04265776328742504, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0469305180106312, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.04973178571090102, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1451330184936523, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1410250663757324, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.135850667953491, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1322407722473145, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1297552585601807, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.127533435821533, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.126075267791748, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.125235080718994, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1246840953826904, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1244168281555176, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1242783069610596, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.124124765396118, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1239514350891113, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1236701011657715, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.123295545578003, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1228928565979004, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.122424364089966, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1219518184661865, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.121666669845581, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.121674060821533, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.1219661235809326, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.12264084815979, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.123868465423584, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.125854253768921, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.1288275718688965, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.1333961486816406, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.1376397609710693, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.1403005123138428, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.1390817165374756, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.1025025844573975, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.9357826709747314, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.763209342956543, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.6460633277893066, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.5823235511779785, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.5480902194976807, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.521043539047241, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.4716973304748535, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.439603567123413, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.4452149868011475, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.4382851123809814, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.448603391647339, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.454270839691162, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.501434087753296, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.5272929668426514, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.596585512161255, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.6259355545043945, "validation/loss_046_lr3.6e+01_wd1.0e+00": 2.908630847930908, "validation/loss_047_lr4.3e+01_wd1.0e+00": 2.868744134902954, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1063642501831055, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.054078995939461055, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.058693244739756366, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06275378368401624, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06533776301218161, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06552233296419344, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.0664451827242525, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.0664451827242525, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06607604282022887, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06496862310815799, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06459948320413436, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06441491325212255, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06441491325212255, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.0636766334440753, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.0636766334440753, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06275378368401624, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06404577334809892, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06441491325212255, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06607604282022887, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.067921742340347, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.06921373200442968, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.06829088224437062, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.0695828719084533, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.0695828719084533, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.06902916205241787, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.07087486157253599, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.0725359911406423, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.07345884090070137, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.073827980804725, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.07825765965300849, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.09339239571797711, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.13602805463270579, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.16758951642672573, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.19915097822074565, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.22000738279808046, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.22517534145441123, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.23145071982281284, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.2412329272794389, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.2541528239202658, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.25341454411221853, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.25655223329641935, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.2561830933923957, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.25064599483204136, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.24437061646363972, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.24603174603174602, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.22739018087855298, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.21668512366186785, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.19490586932447398, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.19232188999630861, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.16851236618678478, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.015691064501911007, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.016053443962724668, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.013700895890233841, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.012226905476888534, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.010064808056845275, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.00953520004879185, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.009398533978029262, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.009083781100067247, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.008385785106298897, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.008048907609562108, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.007812171907874481, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.007711416855230324, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.007992266557899669, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.008257586663646328, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.007656668684136056, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.008816393809193572, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.009411779274831548, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.011303796747697955, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.013338256094384318, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.014884276061887733, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.015205460505366662, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.01624236921197318, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.015956667302313682, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.014067558598483576, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.013582825942571835, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.014825868482303503, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.015065121755594104, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.015758370106264245, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.01875307301929437, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.029895528148770504, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.058825340481840904, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.08371717467136881, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.11880589442213597, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.14665184498913583, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.1557925848102242, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.16032444279718805, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.16804237235121755, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.18335777573422427, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.19052545268103382, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.1904586937826601, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.18311911991380755, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.1781698388740505, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.17564294669003896, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.16274185128474292, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.16612767224956002, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.15462122064948502, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.12899944357527882, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.12347571572990144, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.10801069790381868, "id_best": 39, "lr_best": 0.0036, "wd_best": 0.05, "train/loss_best": 2.5983525848388673, "validation/loss_best": 2.4382851123809814, "validation/acc_best": 0.25655223329641935, "validation/f1_best": 0.1904586937826601} +{"epoch": 2, "train/lr": 0.00014999999999999988, "train/loss": 2.984093551635742, "train/grad": 0.41739546284079554, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.140001220703125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.13783935546875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.135552978515625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.134293212890625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.133648681640625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.13323486328125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.132969970703125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.132855224609375, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.132547607421875, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.132388916015625, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.13218017578125, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.13189697265625, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.1314892578125, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.130985107421875, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.130423583984375, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.1299072265625, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.12929931640625, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.12851318359375, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.1277880859375, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.12708251953125, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.12611328125, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.125120849609375, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.123804931640625, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.121488037109375, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.1151025390625, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.077181091308594, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.003858947753906, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.922598342895508, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.814836654663086, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.6929122543334962, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.6043503952026366, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.545324459075928, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.484048671722412, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.447380962371826, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.4159986925125123, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.3907926988601687, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.3777566528320313, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.3719395351409913, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.3765077137947084, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.390673642158508, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.4031143975257874, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.420886950492859, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.4371779918670655, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.473056960105896, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.5201734590530394, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.6290669083595275, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.223925737142563, "train/loss_047_lr4.3e+01_wd1.0e+00": 5.480166010856628, "train/loss_048_lr5.0e+01_wd1.0e+00": 5.460331147909164, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.020351095013320445, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.020153501401655376, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.019957396243698897, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.01986395152285695, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.01982262026052922, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.01980796124320477, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.019816448641940952, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.019834197447635232, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.01985889971256256, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.019882479570806025, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.019901623618789017, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.019926435803063212, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.019947049506008625, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.01997308511752635, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.019995123036205768, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.02001123159658164, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.020026386566460132, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.020032198992557825, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.020023155654780567, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.019997060722671448, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.01993749149609357, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.019841797072440385, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.019686947953887285, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.019470649315044285, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.019283709554001688, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.019852172913961113, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.021395046026445926, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.022673126072622837, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.024480306887999178, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.026681984914466737, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.028492019027471543, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.029818452186882494, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.03064138718880713, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.03156190707348287, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.03263147768564522, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.033620785977691414, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.03466272607445717, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.035272224182263015, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.03635538256727159, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.037957038646563884, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.039609183026477694, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.041865269178524615, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.04387050027959049, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.04492839027196169, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.048552497569471595, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0588180978782475, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.09985790165141224, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.14405985008925198, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.13179504316300153, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.127933979034424, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1267125606536865, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.125627279281616, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1251542568206787, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1249258518218994, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1247894763946533, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.124724864959717, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.124708652496338, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.12475848197937, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.124850034713745, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.124969005584717, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.125239372253418, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1255335807800293, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.125967264175415, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1263322830200195, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1265487670898438, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.126549482345581, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1259632110595703, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1246395111083984, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.1228370666503906, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.1199841499328613, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.116438388824463, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.111398696899414, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.101073741912842, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.0489931106567383, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.7853071689605713, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.642671823501587, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.5743141174316406, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.504380226135254, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.453319787979126, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.428267478942871, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.4173901081085205, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.4080557823181152, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.407940626144409, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.4215259552001953, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.4434354305267334, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.4487874507904053, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.453341245651245, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.450024366378784, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.462862968444824, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.524934768676758, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.527585029602051, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.605897903442383, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.6246390342712402, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.5863516330718994, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.7737858295440674, "validation/loss_046_lr3.6e+01_wd1.0e+00": 29.032583236694336, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06626061277224068, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06570690291620525, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06607604282022887, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06626061277224068, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06607604282022887, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06607604282022887, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06699889258028793, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06699889258028793, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.0681063122923588, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06921373200442968, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.0664451827242525, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06533776301218161, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06459948320413436, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06478405315614617, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06570690291620525, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06662975267626431, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06533776301218161, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06441491325212255, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.06478405315614617, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.06607604282022887, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.06829088224437062, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.07179771133259505, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.08065706902916205, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.10095976375046142, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.16500553709856036, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.21502399409376152, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.23772609819121446, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.2528608342561831, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.2648578811369509, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.26891842008121075, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.27205610926541157, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.27150239940937615, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.26799557032115173, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.27002583979328165, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.2617201919527501, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.257844222960502, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.2593207825765965, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.2576596530084902, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.2543373938722776, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.24732373569582872, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.2427094868955334, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.2397563676633444, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.22720561092654115, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.23791066814322628, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.2207456626061277, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.06847545219638243, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.00967656155950121, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.009644311183278432, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.009635381310880141, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.00969443108331997, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.009694282977226293, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.009793361188825926, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.01020130801855155, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.010166477324375917, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.01050516424848468, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.011162183688485226, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.011018135452162486, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.011341179403841738, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.011139174565212942, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.010995921847165307, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.010974364023151597, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.010959456952241585, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.009890793591831782, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.009362445706290438, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.008575458972868953, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.009438615925603059, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.010986931499600441, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.012414217686158005, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.01368609089658661, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.017063923340645982, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.026334227139987093, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.07940091617714974, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.1282852379772912, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.15479974150004902, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.1730754583492006, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.1889317033492702, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.19229659586316747, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.1992580345745617, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.19915985496775082, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.20103177093263405, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.202439108056079, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.19238569856236531, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.19161504980393093, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.2010854728466933, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.20875431574930814, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.19533994088247808, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.16971396236488015, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.18109784554885353, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.1649418467551985, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.1576008416559707, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.17877697443574037, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.15791963654923677, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.01673695293964636, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 31, "lr_best": 0.0009299999999999999, "wd_best": 0.05, "train/loss_best": 2.545324459075928, "validation/loss_best": 2.4173901081085205, "validation/acc_best": 0.27205610926541157, "validation/f1_best": 0.1992580345745617} +{"epoch": 3, "train/lr": 0.0002100600600600602, "train/loss": 2.9041384053230286, "train/grad": 0.3728811832517385, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.131162109375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.130654296875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.130216064453125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.129964599609375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.1297021484375, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.129320068359375, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.12895751953125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.1284912109375, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.12802001953125, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.127244873046875, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.126766357421875, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.125938720703125, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.12501708984375, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.123975830078125, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.122877197265625, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.12191650390625, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.120498046875, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.118966064453125, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.116849365234375, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.1143902587890624, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.108314208984375, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.08199462890625, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.991849212646484, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.8660432434082033, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.7330059814453125, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.606419715881348, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.538618469238281, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.4892933654785154, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.4355738258361814, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.3883588218688967, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.358122272491455, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.3328725624084474, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.3134682083129885, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.3043806552886963, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.2946329140663146, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.283046681880951, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.2928809261322023, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.298805181980133, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.316522263288498, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.368095099925995, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.395896966457367, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.437747828960419, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.4814313888549804, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.5432257795333864, "train/loss_044_lr2.6e+01_wd1.0e+00": 4.906694771051407, "train/loss_045_lr3.1e+01_wd1.0e+00": 4.409922779798507, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.870887727737427, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.01971258357167244, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.01971018357668072, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.019728394933044912, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.019748399532400072, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.01976490145549178, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.01978205320890993, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.019798747459426523, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.019814168866723776, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.01983201106544584, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.019848217871040106, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.01986142711248249, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.01987540036905557, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.019884359114803372, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.019887709319591523, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.01987898990046233, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.019859910779632627, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.019818103848956527, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.019744597347453235, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.01962425956502557, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.01947466938290745, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.019280718280933796, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.01957225681748241, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.02116766391787678, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.023684831196442248, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.026342110149562357, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.028342529879882932, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.02913031751289964, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.030196032375097274, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.03161713127046824, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.03256385100074113, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.03331282335333526, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.034203996667638424, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.035025080600753426, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.035742440205067394, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.037260016622021795, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.03852034940384328, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.03963598037138581, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.03977419762872159, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.04094809249974787, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.043760065557435154, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.046319773411378266, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.04880863554775715, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.051566837150603534, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.05459867922589183, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.15499825013801455, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.14203559013083578, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.02916834771633148, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.124784469604492, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.124500274658203, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1241989135742188, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.123952865600586, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1236989498138428, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1233699321746826, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1229560375213623, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1224851608276367, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1218421459198, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1212055683135986, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.120574951171875, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.119685411453247, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1189301013946533, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1179826259613037, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.117297887802124, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1168320178985596, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.116434335708618, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1159582138061523, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.114513397216797, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.110154390335083, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.0835916996002197, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.9222724437713623, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.6995129585266113, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.597749710083008, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.5323729515075684, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.4795501232147217, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.4503769874572754, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.43778657913208, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.4399032592773438, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.4485583305358887, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.4465742111206055, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.451566219329834, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.4135167598724365, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.4123902320861816, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.4998342990875244, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.4936165809631348, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.5554566383361816, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.5631518363952637, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.556849718093872, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.544245958328247, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.57399845123291, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.586207866668701, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.7074925899505615, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.8603615760803223, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06607604282022887, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06589147286821706, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.0664451827242525, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.0664451827242525, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06681432262827612, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06662975267626431, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06755260243632337, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06681432262827612, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.0681063122923588, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06884459210040605, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06884459210040605, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.07087486157253599, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.07327427094868956, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.07308970099667775, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.07585825027685493, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.0753045404208195, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.0725359911406423, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.07272056109265411, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.07235142118863049, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.07456626061277224, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.08527131782945736, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.14728682170542637, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.18752307124400147, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.2131782945736434, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.22812846068660023, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.2382798080472499, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.25212255444813586, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.25655223329641935, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.2572905131044666, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.25655223329641935, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.2591362126245847, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.2622739018087855, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.27556293835363604, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.27500922849760057, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.26264304171280917, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.2646733111849391, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.2511997046880768, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.24769287559985234, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.23901808785529716, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.2353266888150609, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.2364341085271318, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.22997416020671835, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.21816168327796234, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.2131782945736434, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.009565882903916747, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.009502385717723919, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.009579141481751922, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.009560706284007256, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.009562516066811739, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.009419200836119928, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.009790373577098327, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.00963607218713524, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.010170438775896464, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.010265099289670681, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.010241893726535084, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.011416389408395074, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.012650023845031366, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.013975841572519293, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.01670967353757995, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.017781178531074363, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.017726343229591986, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.018966866606838093, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.01989611220924704, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.023292643657978812, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.0356772418298873, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.07515613789592439, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.10963808154219168, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.13583062239975838, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.15386367943784496, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.16957360630902577, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.18727258240627154, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.1945495166519915, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.19838500781306748, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.20194412455204466, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.1972764367189491, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.19565209633314892, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.2010920788216061, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.19902174389171493, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.1896848526076997, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.19388576512991743, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.19187451280315124, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.19322066638405103, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.19269996602020387, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.18225485949383133, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.17788444775933873, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.1750471419025499, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.15727150718167962, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.15832456335178494, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 32, "lr_best": 0.0011099999999999999, "wd_best": 0.05, "train/loss_best": 2.3134682083129885, "validation/loss_best": 2.4135167598724365, "validation/acc_best": 0.27556293835363604, "validation/f1_best": 0.2010920788216061} +{"epoch": 4, "train/lr": 0.0002701201201201201, "train/loss": 2.8961900103092195, "train/grad": 0.43090817116200925, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.132188720703125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.131947021484375, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.1315478515625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.1311572265625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.13073486328125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.1301953125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.129637451171875, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.1288916015625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.1281494140625, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.1271875, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.12635498046875, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.125076904296875, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.123836669921875, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.12205078125, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.120328369140625, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.118607177734375, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.11579345703125, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.1097259521484375, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.0789410400390627, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.9862249755859374, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.833291473388672, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.685208282470703, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.5802371597290037, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.5049211311340334, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.4475092697143555, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.398613052368164, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.360551471710205, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.3280028438568117, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.2915384769439697, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.262204294204712, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.2426874923706053, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.223956656455994, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.2103450393676756, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.2102928042411802, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.2119451475143435, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.214819049835205, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.234064931869507, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.264980926513672, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.306659461259842, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.3794298505783082, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.4199494302272795, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.500507024526596, "train/loss_042_lr1.9e+01_wd1.0e+00": 4.939827481508255, "train/loss_043_lr2.2e+01_wd1.0e+00": 6.673818502426148, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.019542482369579374, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.0195543714100495, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.01956930400338024, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.019580655703321098, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.019588551353663206, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.019597768168896437, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.019606605092994868, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.019616248784586787, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.019626909894868733, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.019635317604988812, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.019639375382103027, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.019638525526970624, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.019624920026399196, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.019582418613135814, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.01951898269355297, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.01943131599575281, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.019288255413994194, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.019095540065318346, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.01938920698594302, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.02095888158772141, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.02389338013250381, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.026585712181404233, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.028198702046647667, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.029067784631624818, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.029994491105899215, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.03114205832593143, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.032058029901236296, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.03287083060480654, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.033766505289822814, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.034504066118970514, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.03516055978834629, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.03590776870958507, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.036767063410952684, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.037750314939767125, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.039937546132132414, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.04154289532452822, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.04230605062097311, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.043055435726419095, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.045877324789762496, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.04932118298485875, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.05329522829502821, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.058258513156324625, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.1830353837274015, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.15468407666310668, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1247684955596924, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1247308254241943, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1246564388275146, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1245944499969482, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.124526262283325, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1244137287139893, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.124260187149048, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.123931407928467, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1234347820281982, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1227760314941406, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.122016191482544, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1208245754241943, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.119635581970215, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.118075132369995, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1167545318603516, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1154918670654297, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.112565040588379, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.095376968383789, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.942567825317383, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.718383312225342, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.607518196105957, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.544703483581543, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.501945734024048, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.45263671875, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.418300151824951, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.4094600677490234, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.416388750076294, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.410602569580078, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.417722225189209, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.4422595500946045, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.436814069747925, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.444870948791504, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.45538592338562, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.541564702987671, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.630526304244995, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.526888132095337, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.5673820972442627, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.6077041625976562, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.6418282985687256, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.6787474155426025, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.7113430500030518, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.9870123863220215, "validation/loss_042_lr1.9e+01_wd1.0e+00": 64.73753356933594, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06404577334809892, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06423034330011074, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06459948320413436, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.062384643779992616, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06275378368401624, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06423034330011074, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06478405315614617, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.0651531930601698, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06866002214839424, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06736803248431156, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06829088224437062, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.0681063122923588, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.07032115171650055, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.07641196013289037, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.1391657438169066, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.18696936138796605, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.21613141380583242, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.2307124400147656, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.23846437799926173, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.25858250276854927, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.2718715393133998, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.2724252491694352, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.2707641196013289, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.2724252491694352, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.2705795496493171, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.2646733111849391, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.26707272056109266, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.2648578811369509, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.2604282022886674, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.24178663713547435, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.2277593207825766, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.2440014765596161, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.24473975636766335, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.24344776670358065, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.23255813953488372, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.23458840900701367, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.2262827611664821, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.21760797342192692, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.07733480989294943, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.006941290087826205, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.007033755340785469, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.006834991792368764, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.006546660464773446, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.007241051689256285, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.006700116422531097, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.006483468525514521, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.007127041774310374, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.00819657984596432, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.009248699485813468, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.010201947865151093, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.011332574851857695, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.01370743857239712, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.014252332444837998, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.01489004533935146, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.014820641390679373, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.01669239190252947, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.02285918674300144, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.07165545515265231, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.10756286557511961, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.13702582428390572, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.15487225966455356, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.1682471728975946, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.19183394205484403, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.20307333471659494, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.20461207457991074, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.20632519094871263, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.21048171967867255, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.21377719726207875, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.2099161957275244, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.2115815838695191, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.2113558728459254, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.21090747752539143, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.192392881974782, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.18431840200447713, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.19098083521996997, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.18071520009306616, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.1778245280086311, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.17360974669194174, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.17291146922052847, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.17623570539557906, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.16170683099915048, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.01595841819885402, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 25, "lr_best": 0.00035999999999999997, "wd_best": 0.05, "train/loss_best": 2.398613052368164, "validation/loss_best": 2.4094600677490234, "validation/acc_best": 0.2724252491694352, "validation/f1_best": 0.20461207457991074} +{"epoch": 5, "train/lr": 0.00029891323817685334, "train/loss": 2.725325493812561, "train/grad": 0.2396774969995022, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.125142822265625, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.124683837890625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.12405517578125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.12345458984375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.122938232421875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.1221484375, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.12128662109375, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.12037109375, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.119249267578125, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.11806884765625, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.11683837890625, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.11519775390625, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.113409423828125, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.11076416015625, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.1071240234375, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.100167236328125, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.0604473876953127, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.905642547607422, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.7137496948242186, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.6037296295166015, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.519183120727539, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.453670082092285, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.3885751724243165, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.3348330879211425, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.2907732772827147, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.2501354789733887, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.2173749828338623, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.1873566579818724, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.152945775985718, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.1311875057220457, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.1226725912094118, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.109504294395447, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.1054960346221923, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.1111750531196596, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.115616683959961, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.1209054934978484, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.1539831411838533, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.1950262248516084, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.2456761479377745, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.3004183888435366, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.363317526578903, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.393559888601303, "train/loss_042_lr1.9e+01_wd1.0e+00": 4.077845783233642, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.171875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.01983327987138182, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.019843538561835884, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.019858065266162156, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.019871708224527537, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.019883298818022012, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.019897513445466756, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.019911016253754497, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.01992185933049768, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.01993032793048769, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.01993366677314043, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.019929238497279584, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.019908149405382575, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.019870126065798105, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.019785356111824512, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.01966801302973181, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.01956266866065562, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.020149078373797237, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.022716895970515908, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.02613215837627649, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.027964357137680054, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.029094189004972577, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.030094123017042874, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.03142715295776725, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.03247279956936836, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0332972271181643, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.03380900796502829, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.03477792126126587, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.035499625876545905, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.03601124999113381, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0364135969709605, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.03729944766499102, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.03861634203232825, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.039910430768504736, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.041267906669527295, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.042911383528262376, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.04487564776092768, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.04562165703624487, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.04666512219235301, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.048633555211126805, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.05166331067681312, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.055693861376494166, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.05563865229487419, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.02851828396320343, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1230483055114746, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.122683525085449, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1220991611480713, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.121567487716675, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1210572719573975, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1203620433807373, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1195905208587646, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1187758445739746, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1176769733428955, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.116513729095459, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1153225898742676, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1133880615234375, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.111396312713623, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.108023166656494, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.102184772491455, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.0830812454223633, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.93465256690979, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.6828391551971436, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.573857069015503, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.510674238204956, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.4572246074676514, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.4207677841186523, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.39699649810791, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.3716845512390137, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.356330394744873, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.353955030441284, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.3588805198669434, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.3696556091308594, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.4180243015289307, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.447946786880493, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.4606761932373047, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.4865546226501465, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.528722047805786, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.555312156677246, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.5907058715820312, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.596482038497925, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.6695034503936768, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.6953694820404053, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.7306969165802, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.697427988052368, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.691394329071045, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.7404134273529053, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06441491325212255, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06459948320413436, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06423034330011074, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06459948320413436, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06441491325212255, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06423034330011074, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06459948320413436, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06441491325212255, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06533776301218161, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06589147286821706, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06718346253229975, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06884459210040605, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06902916205241787, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.07032115171650055, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.07511997046880768, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.08693244739756367, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.14138058324104835, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.19139904023624954, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.21816168327796234, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.2355112587670727, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.2499077150239941, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.26393503137689184, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.271686969361388, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.27870062753783686, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.28460686600221485, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.2836840162421558, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.2857142857142857, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.27851605758582504, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.26854928017718716, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.26947212993724623, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.26707272056109266, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.26688815060908083, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.2587670727205611, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.257844222960502, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.2511997046880768, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.2467700258397933, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.23588039867109634, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.22702104097452935, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.21391657438169065, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.2146548541897379, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.22702104097452935, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.2249907715023994, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.007267320272202699, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.006695309055224821, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.006532760815788093, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.006810414767300512, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.006727484845818625, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.006557723019470431, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.007001158188478481, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.007302568633399523, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.008308149128299643, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.009060131526246703, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.010075334289101788, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.01141594364041857, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.011544228036937223, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.012568944428769204, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.019096315248954516, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.030957209886053744, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.0641496308206652, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.10443472378895173, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.1336232993662417, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.15618882087964855, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.17312226964423102, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.18631076745062305, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.19210149112533156, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.20185190119301655, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.20672120078437217, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.20803002995621314, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.21551453759681638, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.2106682617638591, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.20672940679651597, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.20597844574190807, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.20742967342494922, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.20634600884428747, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.1955244547190118, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.20909664139325254, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.19660877807930396, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.19460949980380018, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.1822072340870877, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.17341388618818465, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.1701786703890218, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.17160478946288002, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.18625883332901147, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.18594056635139236, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 26, "lr_best": 0.00041999999999999996, "wd_best": 0.05, "train/loss_best": 2.2173749828338623, "validation/loss_best": 2.3588805198669434, "validation/acc_best": 0.2857142857142857, "validation/f1_best": 0.21551453759681638} +{"epoch": 6, "train/lr": 0.0002924170901991409, "train/loss": 2.65129408121109, "train/grad": 0.2221850211918354, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.12987548828125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.129423828125, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.128389892578125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.1274853515625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.1266845703125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.125455322265625, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.124229736328125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.122874755859375, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.1210595703125, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.119246826171875, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.117529296875, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.11470458984375, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.11162109375, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.1045001220703123, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.079012451171875, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.974468078613281, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.7650630187988283, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.6198130798339845, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.525628852844238, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.4634986114501953, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.398488845825195, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.339439506530762, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.279672718048096, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.22708740234375, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.1840452480316164, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.149209837913513, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.120336036682129, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.092877516746521, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.0669701528549194, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.051008222103119, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.04066012263298, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.0297899758815765, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.033691598176956, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.05041960477829, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.049436899423599, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.0698032188415527, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.106826792359352, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.1556892359256743, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.1901538705825807, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.270404825210571, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.311763787269592, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.361948467493057, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.171875, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.171875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.01980083162430674, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.01980470774229616, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.01981083323713392, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.019813998816534877, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.019815010987222194, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.019816756802611052, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.019814818212762476, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.019806369026191532, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.01978825280442834, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.019759504362009465, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.019719980163499712, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.01963802447076887, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.019528096029534935, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.019323689783923327, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.0194922708068043, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.021313774567097425, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.024909229977056385, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.027329914439469576, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.02884362014941871, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.02980208456516266, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.030990549409762026, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.03208440203219652, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.03302151942625642, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.03378450846299529, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.03431727559305728, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.03503843629732728, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.036053100461140276, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0368938859924674, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.03798017193563283, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.03904121397063136, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.039231044836342335, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.040622026603668926, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.04149097150191665, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.04289621764793992, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.04458175642415881, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.046989077124744656, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.04782941484823823, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.048854691982269285, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.04969128359109163, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.05389763336628675, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.05580006903037429, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.05655329573899508, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.122544288635254, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1221814155578613, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1215994358062744, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1210994720458984, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1205804347991943, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1199536323547363, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1192615032196045, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1184492111206055, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.117424964904785, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.116196870803833, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.114882469177246, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1123807430267334, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1086807250976562, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.0947890281677246, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.0092287063598633, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.77411150932312, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.617173194885254, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.526395320892334, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.4645440578460693, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.4263267517089844, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.3899447917938232, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.365342140197754, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.3567006587982178, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.357675552368164, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.371504783630371, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.3829734325408936, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.4091358184814453, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.444739818572998, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.4964540004730225, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.5186567306518555, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.521815776824951, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.5032386779785156, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.564251184463501, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.5767874717712402, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.602299451828003, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.5615556240081787, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.604604959487915, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.593095064163208, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.6818454265594482, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.694582223892212, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.6725921630859375, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.6347386837005615, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06552233296419344, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06589147286821706, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06570690291620525, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06589147286821706, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06681432262827612, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06626061277224068, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06589147286821706, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06662975267626431, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06607604282022887, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06755260243632337, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.067921742340347, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.0710594315245478, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.07456626061277224, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.0902547065337763, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.12163159837578442, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.17700258397932817, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.21945367294204504, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.24012550756736803, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.2571059431524548, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.26707272056109266, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.28054632705795496, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.28294573643410853, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.2809154669619786, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.2779623477297896, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.27464008859357697, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.2709486895533407, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.27353266888150607, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.2631967515688446, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.2556293835363603, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.24953857511997046, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.2499077150239941, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.25249169435215946, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.2469545957918051, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.24953857511997046, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.25249169435215946, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.2582133628645257, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.24603174603174602, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.24732373569582872, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.23994093761535623, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.22997416020671835, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.23569582871908454, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.23569582871908454, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.008770590775696233, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.00877962462031957, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.008603639691822202, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.008653796408862522, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.009115474995546312, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.009466456520609021, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.009487804675287924, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.010657361395055591, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.01186713453872955, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.013798877723666997, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.014246290375393602, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.017607094481494633, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.023217172069655904, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.03344024343335747, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.0558749077984218, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.09374374483519592, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.13863128080539114, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.16477898310237266, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.18872614628493453, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.200402887268485, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.21813877603500254, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.222585508297288, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.22098902503894766, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.22446120245844145, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.2258365375765334, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.22269639937392505, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.22294209577732396, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.21430648966312923, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.2075785804565379, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.1992332195559213, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.20528617881280056, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.20591236709739527, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.19564973353139758, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.2013054348032971, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.20547913039276397, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.21198124607079463, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.204422743306953, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.1989656251362193, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.19820838850899145, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.18414187190373074, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.1886847091913754, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.1944499395587146, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 21, "lr_best": 0.00018299999999999998, "wd_best": 0.05, "train/loss_best": 2.339439506530762, "validation/loss_best": 2.365342140197754, "validation/acc_best": 0.28294573643410853, "validation/f1_best": 0.222585508297288} +{"epoch": 7, "train/lr": 0.00027969249556793234, "train/loss": 2.580240043401718, "train/grad": 0.22799643769860267, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.127784423828125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.12708740234375, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.12595458984375, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.12478515625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.12375732421875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.122322998046875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.120684814453125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.118892822265625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.116602783203125, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.11404052734375, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.111502685546875, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.10678955078125, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.0994879150390626, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.055159912109375, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.870716857910156, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.690432586669922, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.576577682495117, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.485793571472168, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.407262725830078, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.3501112174987795, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.2883503341674807, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.2354256248474123, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.181013946533203, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.129464979171753, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.085512094497681, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.049603908061981, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.0128918790817263, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.9759215259552, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.947548236846924, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.9345826148986816, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.9337676250934601, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.921786133646965, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.9221392858028412, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.9361249309778215, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.9462559360265732, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.9561734437942504, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.9960627281665801, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.0580824291706086, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.111527645587921, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.15925102353096, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.202074809670448, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.2693304765224456, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.171875, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.171875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.019313071863725783, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.019315738161094487, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.019319301485083998, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.019319665553048253, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.01931894671637565, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.01931272675283253, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.019302910696715116, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.01928341519087553, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.01924966396763921, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.019199530822224916, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.019134898483753205, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.019005600260570646, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.018864490264095365, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.01934929484501481, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.022467363537289203, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.025609490955248476, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.027518485356122255, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.028837180621922018, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.03018323396332562, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.031293432991951704, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.03251421183347702, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.03339395688846707, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.03438737215474248, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.03531129011884332, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.03614619445055723, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.03687624603509903, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.03780316859483719, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.038868617340922354, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.04024663140997291, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.04127898445352912, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.04190074410289526, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.04322084579616785, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.043533330205827954, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.04444617759436369, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.04723547788336873, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.04827149607241154, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.048546830303967, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0494352850690484, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.05101735135540366, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.052258077226579186, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.05471692191436887, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.05505833905190229, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.122161865234375, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1217808723449707, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1211698055267334, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1205999851226807, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.120084762573242, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1193764209747314, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.118593692779541, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.117755651473999, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.116718053817749, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1155076026916504, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1140804290771484, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.110313653945923, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.100029706954956, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.9869630336761475, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.723121166229248, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.6093909740448, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.521800994873047, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.4572486877441406, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.407742738723755, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.382596492767334, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.361966609954834, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.355884313583374, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.366156816482544, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.3888237476348877, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.4163124561309814, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.4275479316711426, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.4539995193481445, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.5000874996185303, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.546616792678833, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.5658211708068848, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.572298765182495, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.613704204559326, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.6291186809539795, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.6982624530792236, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.720611572265625, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.6949546337127686, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.689987897872925, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.818312406539917, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.8102688789367676, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.7906858921051025, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.919279098510742, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.986142158508301, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06533776301218161, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06570690291620525, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06589147286821706, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06607604282022887, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06662975267626431, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06736803248431156, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.067921742340347, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06866002214839424, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.0681063122923588, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06829088224437062, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06939830195644149, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.07124400147655961, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.07825765965300849, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.12698412698412698, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.19029162052417867, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.21908453303802142, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.24289405684754523, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.25599852344038393, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.26799557032115173, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.2709486895533407, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.27722406792174237, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.27870062753783686, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.2722406792174234, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.27500922849760057, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.2681801402731635, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.26744186046511625, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.2718715393133998, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.2593207825765965, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.2547065337763012, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.2454780361757106, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.2530454042081949, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.24455518641565152, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.24529346622369877, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.23329641934293097, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.23883351790328536, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.24750830564784054, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.24806201550387597, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.23052787006275377, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.23791066814322628, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.23034330011074197, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.2220376522702104, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.21520856404577335, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.009147323682226151, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.009261326555648696, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.009659911990345972, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.01000653990215553, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.011158167673318944, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.012025712230234057, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.012939971220891515, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.014235268149850891, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.013774357566901723, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.013793002095388368, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.014118233367940098, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.015027855069953945, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.01770661301319061, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.0496372703599345, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.10642413994200757, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.1385932581686393, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.1636924185688262, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.18377502305461754, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.20078577191479904, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.20655250454709684, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.21668589244846811, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.21906303287083384, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.21386867921193686, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.2226857151953551, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.21750460607764624, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.22172857605840587, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.22543022987585926, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.21705344253001083, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.20831363798210448, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.1978196629914266, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.2115325076840691, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.20578558368702662, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.2041466822088168, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.18789264129217842, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.18610766386149183, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.1918170640310791, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.19130972785738143, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.17202107982610404, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.18025809862096123, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.1751467250434319, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.16354837420529056, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.15058090405150287, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 21, "lr_best": 0.00018299999999999998, "wd_best": 0.05, "train/loss_best": 2.2354256248474123, "validation/loss_best": 2.355884313583374, "validation/acc_best": 0.27870062753783686, "validation/f1_best": 0.21906303287083384} +{"epoch": 8, "train/lr": 0.0002612959497061927, "train/loss": 2.517715964317322, "train/grad": 0.23570969723165036, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.12343017578125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.12262451171875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.1213671875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.12017333984375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.11893310546875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.11729736328125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.115557861328125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.113599853515625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.110950927734375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.1079931640625, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.10449462890625, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.0963507080078125, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.0693060302734376, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.8681851196289063, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.666221160888672, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.5721160888671877, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.487919235229492, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.4105538177490233, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.336134185791016, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.28078426361084, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.2191562271118164, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.163447551727295, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.1067331314086912, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.0528523778915404, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.004850518703461, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.965464563369751, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.920748908519745, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.8826716417074203, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.8453988045454026, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.8290510362386703, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.8259501385688781, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.815681654214859, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.8186502528190613, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.8334058445692063, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.8312597531080246, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.8423673856258391, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.8752863597869873, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.9372594767808915, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.9884323680400848, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.056662583351135, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.1119153827428816, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.1737207871675492, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.171875, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.171875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.019961953572928907, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.01996569152455777, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.01997172727249563, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.01997294825036079, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.019971756818704306, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.019966459926217796, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.019953056005761027, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.019930585585534573, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.019888396421447397, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.019822405665181578, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.01973701667971909, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.01958152889739722, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.019754036921076478, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.023025670824572443, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.026723334481939674, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.02840463489294052, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.029720811937004328, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.030926855113357306, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.032640968067571524, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.033797311233356594, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.034628205811604855, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.035251695830374956, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.03613736134953797, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.03697088850662112, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.038024699920788406, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.03923230016604066, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.040461052991449836, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.041516035180538896, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.04265192154794931, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.04348564753308892, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.04397903248667717, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.045206744000315664, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.045582445934414864, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.04605339538305998, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.047338732220232486, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.04905133064836264, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.04875601651147008, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.048679530378431084, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.05021263567730785, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.05126457242295146, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.05463340690359473, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.054784203357994554, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.121711015701294, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.121209144592285, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.120412826538086, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1196298599243164, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.11887526512146, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.117856502532959, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1166889667510986, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1153745651245117, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1135036945343018, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.111102342605591, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1076691150665283, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.0958967208862305, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.0363926887512207, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.744950532913208, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.6037797927856445, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.5302622318267822, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.473858118057251, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.4294447898864746, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.4001240730285645, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.3877031803131104, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.3775417804718018, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.3877508640289307, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.405604124069214, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.4229841232299805, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.4467339515686035, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.465796709060669, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.517423629760742, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.5506463050842285, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.579007625579834, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.616295576095581, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.6659514904022217, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.70308780670166, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.7561802864074707, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.7688472270965576, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.815924882888794, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.841287612915039, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.881538152694702, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.8067753314971924, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.757463216781616, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.679044008255005, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.8574914932250977, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.729156970977783, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06589147286821706, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06607604282022887, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06607604282022887, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06681432262827612, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06755260243632337, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06884459210040605, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.0681063122923588, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.0695828719084533, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.0695828719084533, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.0710594315245478, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.07456626061277224, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.08176448874123293, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.11221853082318199, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.17977113325950536, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.2207456626061277, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.2364341085271318, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.2517534145441122, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.2631967515688446, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.2733480989294943, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.2727943890734588, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.27500922849760057, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.26799557032115173, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.26356589147286824, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.2576596530084902, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.2571059431524548, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.26245847176079734, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.25507567368032485, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.24584717607973422, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.24806201550387597, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.2410483573274271, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.23938722775932078, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.23661867847914358, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.23126614987080105, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.22369878183831673, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.2412329272794389, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.23421926910299004, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.22997416020671835, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.23938722775932078, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.23089700996677742, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.24492432631967515, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.2222222222222222, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.23809523809523808, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.008950314350963806, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.009370864989100806, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.009858492887045394, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.011505289765737363, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.012446019588877496, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.014277887379647069, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.0145708778826949, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.016039706090094495, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.017371566867138, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.01906045384805936, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.021275033699830147, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.03014083000126383, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.05103926238385104, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.09663961891930449, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.1400495145244506, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.16213967982424435, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.18462248735898554, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.20276999098716475, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.21462526637792623, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.21725516261269062, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.22121930482741722, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.21635665024384365, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.2125786918928756, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.20833555763543288, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.20958715517506435, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.21617985022771066, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.2071574595036678, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.203539491957882, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.2032802369409545, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.19374746760578931, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.1898297094679241, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.18597670828956928, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.18252132231480153, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.1766793610746407, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.186518894350166, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.17884846682977198, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.173860230067684, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.17705654958054973, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.1840072470762555, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.19850167770888374, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.17338834913665244, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.19034200248355912, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 20, "lr_best": 0.000156, "wd_best": 0.05, "train/loss_best": 2.2191562271118164, "validation/loss_best": 2.3775417804718018, "validation/acc_best": 0.27500922849760057, "validation/f1_best": 0.22121930482741722} +{"epoch": 9, "train/lr": 0.00023803200426111704, "train/loss": 2.476610826253891, "train/grad": 0.24099197819828988, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.1221875, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.12123291015625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.119757080078125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.118148193359375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.1167529296875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.114825439453125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.112691650390625, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.11030029296875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.10706298828125, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.10298095703125, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.0976123046875, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.0765753173828125, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.969301452636719, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.698323516845703, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.5802871704101564, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.504151611328125, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.4313493728637696, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.357232437133789, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.2874191761016847, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.2325298023223876, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.1761754322052003, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.1225625324249267, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.0636429738998414, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.0064867401123045, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.9531178975105286, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.9080391395092011, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.861340582370758, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.8132835268974303, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.7684175789356231, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.7453620487451553, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.7455908066034318, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.7240396791696548, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.7320213282108308, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.7441565132141112, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.7502413845062257, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.7571054184436798, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.8245160728693008, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.894044297337532, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.948167245388031, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.017318141460419, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.071305832862854, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.1431511354446413, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.171875, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.171875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.019861896387301386, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.019863861319608985, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.01986393518280238, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.019861212498508394, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.019855344565585256, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.019842980075627566, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.019822672512382268, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.01978999809361994, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.01973114567808807, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.01964381540659815, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.019537609606049954, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.019542375397868454, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.02136757238768041, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.025859446749091148, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.028055596463382244, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.029200276862829923, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.030186954494565724, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.03163252123631537, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.03323505046777427, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.03422288797795772, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.03496636977419257, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.03576291896402836, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.03677453259937465, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.03781373301520943, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.03909720432944596, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.04012429554015398, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.04154335735365748, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.042810915187001225, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.04408547015860677, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0449937873147428, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.04569914879277349, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.046556947901844975, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0468650515563786, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.04694408843293786, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.04899399697780609, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.05025637531653047, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.050865982603281734, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.05009144026786089, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.050788453035056594, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.05227010753005743, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.05483951555565, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.05534376269206405, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1211774349212646, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.120635509490967, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1197686195373535, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1189334392547607, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1181163787841797, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1170241832733154, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1157326698303223, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1141774654388428, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.111753463745117, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1081645488739014, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1018989086151123, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.064227819442749, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.8819985389709473, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.637620449066162, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.5437700748443604, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.4892871379852295, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.4427385330200195, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.3983185291290283, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.3679051399230957, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.3565495014190674, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.3503761291503906, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.3633742332458496, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.381762981414795, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.407961368560791, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.447780132293701, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.4751312732696533, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.5239882469177246, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.5851120948791504, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.624293804168701, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.662714719772339, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.6922447681427, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.7162771224975586, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.7278149127960205, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.73012375831604, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.7858927249908447, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.8469111919403076, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.8688056468963623, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.8361103534698486, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.8378305435180664, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.7725026607513428, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.7301506996154785, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.7143495082855225, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06626061277224068, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06662975267626431, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06589147286821706, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06570690291620525, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06662975267626431, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06921373200442968, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06866002214839424, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06976744186046512, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.07198228128460686, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.07475083056478406, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.07788851974898486, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.1005906238464378, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.15466961978589885, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.2081949058693245, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.2277593207825766, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.24603174603174602, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.26098191214470284, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.27353266888150607, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.2781469176818014, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.2798080472499077, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.2809154669619786, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.2766703580657069, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.26707272056109266, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.26356589147286824, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.26448874123292726, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.257844222960502, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.2589516426725729, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.2440014765596161, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.23864894795127353, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.23274270948689554, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.23329641934293097, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.23052787006275377, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.23791066814322628, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.24067921742340348, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.24160206718346253, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.2368032484311554, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.2294204503506829, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.23329641934293097, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.22997416020671835, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.2334809892949428, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.2368032484311554, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.2355112587670727, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.009444628059343405, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.009892958379206758, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.009967412835210713, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.010785194438294282, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.01174925116063486, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.013797519070397947, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.014791528449817024, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.016305961849399832, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.01912306634991981, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.02144658512254431, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.02381026069156678, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.04221662620084374, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.07355035848398676, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.12235191263340987, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.14552908063884093, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.16697968480640726, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.18641505560875218, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.20370576930620435, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.213263793243791, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.21725079097122044, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.22042313330226213, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.22065407149196573, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.21592515768685114, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.21719403548682595, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.22300473466278428, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.21908615570053738, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.22053176183857195, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.20965823747160028, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.2107602102442574, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.20574297053112414, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.20870898260855683, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.20379972023823, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.20007325037312787, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.20328216209540906, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.19635520169793422, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.18915782119494592, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.18409041927140427, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.17392842416982737, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.17322853356694834, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.1780812222665007, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.1892037547725852, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.19042440359116117, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 20, "lr_best": 0.000156, "wd_best": 0.05, "train/loss_best": 2.1761754322052003, "validation/loss_best": 2.3503761291503906, "validation/acc_best": 0.2809154669619786, "validation/f1_best": 0.22042313330226213} +{"epoch": 10, "train/lr": 0.00021091808096876188, "train/loss": 2.4105112636089325, "train/grad": 0.23954296939074993, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.12132080078125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.120220947265625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.11847412109375, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.116878662109375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.1152197265625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.113070068359375, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.110621337890625, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.107864990234375, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.103916015625, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.098580322265625, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.0893389892578127, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.0271209716796874, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.819576416015625, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.6180213928222655, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.5171974182128904, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.4491961288452146, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.3768913650512697, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.301182518005371, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.229491882324219, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.1700108814239503, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.110951919555664, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.0531874084472657, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.9919588708877562, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.926825246810913, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.8629613709449768, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.8090243816375733, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.7537311244010925, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.7033652031421662, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.6565145415067672, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.6241370767354966, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.6220460605621339, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.608296583890915, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.615612298846245, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.626010940670967, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.6064092326164245, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.6234499698877334, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.6842783051729202, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.7442933422327043, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.8027570730447768, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.874269653558731, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.8914786994457244, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.996175180077553, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.171875, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.171875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.019555178615264596, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.019555031196214257, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.019553330582566558, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.019547611931338905, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.01953980963677168, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.01952349553350359, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.019497756874188782, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.019459312884137034, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.019388968111015856, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.019287309045903384, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.019197374312207104, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.02002423768863082, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.023231813302263617, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.02704027373343706, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.028721418408676983, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.029680075151845814, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.030847972510382533, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.03251765843480826, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.03395882865414023, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.03504508861340582, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.03563187055289745, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.036332272673025724, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.037166434051468966, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.03818256989121437, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.039228893034160134, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.04015211870893836, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.04161733133718371, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0431078478321433, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.04463695852085948, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.04566860599443316, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.04635383378714323, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.047524119690060616, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.04788362022489309, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.04804127138108015, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.04906427662819624, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.05041196955367923, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.050565713942050936, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.048858649488538505, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.04914919530972838, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.04915885830298066, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.05030554354190826, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.05114435378462076, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.121080160140991, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.12056827545166, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.119703769683838, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.118882417678833, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.118034601211548, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1168501377105713, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1153829097747803, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.113563060760498, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1105380058288574, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1052098274230957, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.0929739475250244, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.9872024059295654, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.7455787658691406, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.58323073387146, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.504547119140625, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.459617853164673, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.420745611190796, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.383413791656494, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.3561666011810303, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.346372365951538, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.341855525970459, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.356417655944824, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.380206823348999, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.4192585945129395, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.4774796962738037, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.5138914585113525, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.579667091369629, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.6297073364257812, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.718155860900879, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.8185489177703857, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.806474447250366, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.8054358959198, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.8441436290740967, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.8916285037994385, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.91853404045105, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.925154447555542, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.907392978668213, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.9175562858581543, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.905886173248291, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.913184404373169, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.9888412952423096, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.009516477584839, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06459948320413436, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06459948320413436, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.0651531930601698, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06496862310815799, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06681432262827612, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06736803248431156, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06718346253229975, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.0681063122923588, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06829088224437062, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.07124400147655961, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.0812107788851975, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.1288298265042451, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.18530823181985973, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.22757475083056478, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.24326319675156885, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.2591362126245847, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.2692875599852344, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.27703949796973054, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.28165374677002586, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.2870062753783684, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.2871908453303802, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.2796234772978959, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.27445551864156514, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.2692875599852344, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.2602436323366556, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.25544481358434845, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.25064599483204136, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.24197120708748615, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.23477297895902546, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.22443706164636398, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.22535991140642303, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.22056109265411591, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.22960502030269472, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.21926910299003322, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.23163528977482467, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.22517534145441123, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.22277593207825766, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.21483942414174972, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.21797711332595054, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.22425249169435216, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.2115171650055371, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.2039497969730528, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.008154966707517267, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.00869425344176399, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.010660157961051651, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.011832885284303214, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.013566190920477192, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.014074659608384879, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.014070952784232654, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.014664118430924779, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.015442680862582001, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.016749899535721577, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.024528290633362388, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.056098075244383684, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.10268565988834454, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.14554808084271553, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.16703301343871316, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.18757236784226528, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.20202191456061755, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.21363376571936574, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.2210217880787578, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.22558794863482348, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.22749691533930785, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.22638236349722976, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.2240439938902409, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.22175023813987824, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.21478345570549104, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.2141581377630024, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.20948748433123676, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.20843005776654452, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.19946845375277036, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.18806392226900315, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.19767907740378488, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.19288688125498757, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.19973676807457497, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.18665782488898985, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.18879086880499807, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.18298986536009745, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.18205962288811917, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.17452551027004148, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.17287290937889022, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.17303745560870576, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.16727201044126486, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.15766169402729402, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 20, "lr_best": 0.000156, "wd_best": 0.05, "train/loss_best": 2.110951919555664, "validation/loss_best": 2.341855525970459, "validation/acc_best": 0.2871908453303802, "validation/f1_best": 0.22749691533930785} +{"epoch": 11, "train/lr": 0.00018113997589164516, "train/loss": 2.371124737262726, "train/grad": 0.24726065777242184, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.12640869140625, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.12536376953125, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.123577880859375, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.12190185546875, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.12025390625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.118013916015625, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.115401611328125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.112310791015625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.10772705078125, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.100421142578125, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.0833441162109376, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.9477828979492187, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.7226898193359377, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.576713409423828, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.4881233978271484, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.4234011459350584, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.34875301361084, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.272361927032471, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.198493843078613, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.1355073261260986, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.075870990753174, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.0139394998550415, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.94879976272583, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.8811081075668334, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.8143734407424927, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.7581854844093323, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.686920289993286, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.632182341814041, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.5758409863710403, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.5386358124017716, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.5395879912376405, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.525125018954277, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.5276980340480804, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.53382055580616, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.519786736369133, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.511808443069458, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.5825906372070313, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.6770107692480087, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.7278439426422119, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.7946656435728072, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.8321241688728334, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.9155193746089936, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.171875, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.171875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.019651714731007814, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.01964938482735306, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.019642448322847485, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.019635168230161072, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.019626457234844564, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.01960957615170628, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.019580841809511185, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.019538840781897306, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.01945756055880338, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.019349359413608908, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.019369262009859084, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.02157372621819377, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.025137173272669316, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.0280874203145504, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.029607900166884065, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.030523524647578598, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.03197301254607737, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.033600751580670475, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.0349312387406826, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.03600489115342498, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.03652050168253482, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.03731753990985453, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.038346827318891885, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.03947990506887436, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.04089245691895485, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0420843892917037, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0437782546505332, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.045272333454340695, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0466238709166646, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.04797531669959426, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.04906654700636864, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.050197878926992415, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.050205562505871056, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0496520514972508, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.05115034256130457, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.05157817650586367, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.05088045978918672, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.05077188219875097, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.05007842311635614, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.049286042638123036, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.05157575100660324, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.051031422168016434, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1208200454711914, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1201930046081543, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1191558837890625, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1181414127349854, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.117141008377075, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.115717887878418, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1140260696411133, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1118545532226562, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.10797381401062, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.100053548812866, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.0755410194396973, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.886809825897217, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.675217390060425, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.5528860092163086, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.4889984130859375, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.4501426219940186, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.418670892715454, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.386212110519409, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.3639280796051025, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.360438108444214, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.360719680786133, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.3785183429718018, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.400038957595825, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.4350690841674805, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.488176107406616, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.5162625312805176, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.58612060546875, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.644263744354248, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.7095224857330322, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.782872438430786, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.8151416778564453, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.8330042362213135, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.851421594619751, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.8992762565612793, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.9121100902557373, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.9204578399658203, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.915449380874634, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.815793514251709, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.8444464206695557, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.7826924324035645, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.9151530265808105, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.8599791526794434, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06552233296419344, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06533776301218161, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06589147286821706, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.0664451827242525, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06755260243632337, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06939830195644149, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.07087486157253599, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.07327427094868956, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.07622739018087855, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.08379475821336287, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.09837578442229605, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.15596160944998155, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.1997046880767811, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.23034330011074197, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.24658545588778147, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.2617201919527501, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.2702104097452935, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.27740863787375414, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.28146917681801403, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.2833148763381321, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.2827611664820967, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.27353266888150607, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.26891842008121075, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.2619047619047619, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.2547065337763012, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.26264304171280917, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.2561830933923957, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.2467700258397933, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.24640088593576967, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.23661867847914358, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.2412329272794389, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.24473975636766335, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.24049464747139165, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.23421926910299004, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.2517534145441122, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.23588039867109634, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.2355112587670727, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.23901808785529716, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.22831303063861202, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.24381690660760427, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.22259136212624583, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.22314507198228128, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.009132457394275912, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.009536133389580552, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.010693214850505969, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.011901551418768162, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.012979492601837755, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.014570661828199187, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.015577858377606594, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.017347837932070134, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.020579264269208183, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.02800985531406494, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.04139978413517355, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.07350077386053833, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.11413726994503637, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.14764377781631174, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.16805584046611022, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.18521815934516062, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.19975462248763598, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.21353850840572638, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.2215693686724903, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.22575649892402408, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.22887141990692395, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.2230008603711547, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.22085508196592726, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.21905386725649653, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.21299815093449137, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.22272590264932957, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.21513570694477938, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.20645135418466476, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.20349173974467827, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.1961890301052299, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.2001896955577621, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.2057983941139088, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.20398007938950458, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.19364849957299204, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.20383082010992826, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.19384036162651264, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.19231896699108966, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.20342768434597, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.1976185894964655, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.19854126461379287, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.1898529830495517, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.18598390087112496, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 19, "lr_best": 0.00013199999999999998, "wd_best": 0.05, "train/loss_best": 2.1355073261260986, "validation/loss_best": 2.360438108444214, "validation/acc_best": 0.2833148763381321, "validation/f1_best": 0.22575649892402408} +{"epoch": 12, "train/lr": 0.0001499999999999999, "train/loss": 2.3077977859973906, "train/grad": 0.24709032110869886, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.11834228515625, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.117025146484375, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.114998779296875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.113011474609375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.11117919921875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.10847900390625, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.105531005859375, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.1018212890625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.09593017578125, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.0850909423828123, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.05200439453125, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.8444363403320314, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.654426727294922, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.5247842407226564, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.4413975524902343, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.3769968032836912, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.3023565292358397, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.2272507476806642, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.1499317932128905, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.084086103439331, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.023466958999634, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.9583923625946045, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.8887553787231446, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.8155251002311708, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.7427015936374664, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.6787836956977844, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.6030857002735137, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.5313332200050354, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.463054176568985, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.405132530927658, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.3965137004852295, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.3697027784585953, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.3666194504499436, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.3862554413080215, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.366792009472847, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.3758206582069397, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.4458446180820466, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.5417023462057113, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.6054795879125594, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.6777837538719178, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.6998433607816696, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.8073003667593002, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.171875, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.171875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.019627970061264932, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.019627187657169996, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.019623510716482998, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.01961835374124348, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.01960737564135343, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.019587957207113503, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.019556496874429286, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.01950723255984485, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.019417044566944243, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.019324142192490398, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.01962502844631672, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.022884124498814343, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.026498128129169345, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.02904032458551228, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.03041846798732877, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.03132488290779292, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.032922914130613205, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.03441878936253488, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.03565268954262137, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.03661553053185344, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.03710501040332019, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.03798043525777757, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.03912465423345566, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.040207996759563686, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.04128968141973019, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.04229987582191825, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.04388450305908918, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.045112655237317084, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.046553144827485085, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.04763295151293278, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.048437256030738354, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0486355865560472, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.04886330766603351, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.04934182234108448, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.050656887274235486, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.05176778262481094, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0510895642824471, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.05008402924984694, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0494661695882678, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.04955072019249201, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.05013420324772597, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.04975012816488743, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.120800733566284, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1201798915863037, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.119126319885254, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1181161403656006, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.117065906524658, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.115593433380127, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.113717794418335, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1111907958984375, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1064116954803467, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.09486722946167, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.0498757362365723, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.808781147003174, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.6379427909851074, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.530792713165283, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.476182699203491, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.4412899017333984, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.414262056350708, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.383915901184082, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.367147922515869, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.369445323944092, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.3772177696228027, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.406061887741089, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.4365179538726807, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.4830310344696045, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.539508104324341, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.5759589672088623, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.6764557361602783, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.724156141281128, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.8334238529205322, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.9499964714050293, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.9729959964752197, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.0134987831115723, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.08795166015625, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.0608627796173096, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.0709946155548096, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.0845439434051514, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.0219550132751465, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.9470407962799072, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.9557387828826904, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.890981435775757, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.9056718349456787, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.825519323348999, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06570690291620525, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06570690291620525, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.0664451827242525, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06681432262827612, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06755260243632337, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06736803248431156, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06718346253229975, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06939830195644149, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.07401255075673681, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.08342561830933924, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.10908084163898117, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.16943521594684385, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.2100406053894426, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.2355112587670727, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.24750830564784054, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.2622739018087855, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.2713178294573643, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.2727943890734588, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.2833148763381321, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.2809154669619786, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.27740863787375414, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.2698412698412698, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.2619047619047619, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.2596899224806202, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.25950535252860835, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.2596899224806202, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.25396825396825395, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.24750830564784054, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.24289405684754523, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.2351421188630491, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.23163528977482467, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.2368032484311554, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.23440383905500184, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.2279438907345884, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.24031007751937986, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.23901808785529716, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.2395717977113326, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.23809523809523808, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.23883351790328536, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.24713916574381692, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.2351421188630491, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.24178663713547435, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.008582392884561828, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.008728088660934299, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.009410793316301626, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.009942150264876081, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.010953649652137134, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.01159428600177141, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.012057309026183509, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.014139843262648619, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.018703809941541628, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.029262361883786784, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.04934845204185056, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.0833664730861285, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.12370290148621231, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.152568234157755, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.17016738454106783, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.18965335139906114, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.2037446579935683, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.21053742398961964, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.22426775139747393, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.22363850054166456, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.22069481551204537, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.2166448518785811, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.20805169252027636, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.20609953897517974, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.20722618295952358, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.20955772203066678, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.2003822289742697, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.1917162801951758, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.18885219315633486, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.17903829450865272, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.18241489657552767, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.18547707684802983, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.18585225839103092, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.18134966078735015, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.1919397342322656, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.18764698306902053, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.1925011973085096, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.19127780854789042, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.18458848898051952, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.18852376841603094, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.1845390467009547, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.19694623280011525, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 18, "lr_best": 0.00011399999999999999, "wd_best": 0.05, "train/loss_best": 2.1499317932128905, "validation/loss_best": 2.367147922515869, "validation/acc_best": 0.2833148763381321, "validation/f1_best": 0.22426775139747393} +{"epoch": 13, "train/lr": 0.00011886002410835478, "train/loss": 2.2678047895431517, "train/grad": 0.24620905362069606, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.121942138671875, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.12058837890625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.118468017578125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.116463623046875, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.11443603515625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.111697998046875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.10846923828125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.10453857421875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.0978204345703126, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.0834521484375, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.02989013671875, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.7860865783691406, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.62838134765625, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.5060869598388673, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.4267305755615234, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.362802028656006, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.288280839920044, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.2117713832855226, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.133824987411499, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.0659242343902586, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.003086566925049, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.9341687870025634, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.8582109105587006, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.7782476091384887, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.7028028202056884, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.6344735789299012, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.5448465806245804, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.474262000322342, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.3938614654541015, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.3306454423069953, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.3034086588025093, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.273460444509983, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.2578886264562608, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.275829690694809, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.2378944951295852, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.2497945228219032, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.32141221255064, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.4313351085782051, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.504090831875801, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.5661990058422088, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.606077120900154, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.699660183787346, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.171875, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.171875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.02000420759432018, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.020002802964299918, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.019995875940658152, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.01998832973651588, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.01997430738992989, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.019949782215990128, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.019912630915641785, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.019854599563404917, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.01975284416228533, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.019685755562968553, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.020374838737770917, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.024011162938550115, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.027182113621383907, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.029435993060469626, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.030688943285495044, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.031659266324713824, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.033340113535523415, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.03470478610135615, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.03591782580129802, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.036820035250857475, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.03732870546169579, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.03815658330917358, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.03916506739333272, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.040212499517947434, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.04130686035379767, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.04243941182270646, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.043752704821527, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.045091012548655274, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.046222100090235474, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.04751535039395094, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.04771951775997877, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.04872195506468415, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0490235684812069, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.04928430175408721, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.05003575410693884, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.05075125433504581, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.04984757356345654, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.049029584862291815, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.04894100163131952, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.04825326286256313, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.05036551708355546, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.047941659167408945, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1205191612243652, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.119764566421509, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.118579626083374, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.117330551147461, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1160945892333984, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.114284038543701, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.112028121948242, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.109010934829712, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1029698848724365, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.086782455444336, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.01712965965271, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.7542221546173096, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.6111948490142822, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.511510133743286, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.459972381591797, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.4254825115203857, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.4006361961364746, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.3708019256591797, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.3556137084960938, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.359790563583374, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.3671438694000244, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.3909637928009033, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.4204280376434326, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.458869457244873, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.5108234882354736, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.5359749794006348, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.626544237136841, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.707461357116699, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.7830891609191895, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.8893699645996094, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.9622714519500732, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.040396213531494, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.0626649856567383, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.0916621685028076, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.1490089893341064, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.205934762954712, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.153709650039673, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.0484347343444824, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.024291753768921, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.067282199859619, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.067955732345581, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.99666428565979, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06589147286821706, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06496862310815799, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06533776301218161, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06626061277224068, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06829088224437062, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06884459210040605, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06976744186046512, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.07161314138058324, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.07364341085271318, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.08767072720561092, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.12236987818383167, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.18235511258767073, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.21834625322997417, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.24344776670358065, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.2556293835363603, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.26854928017718716, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.2751937984496124, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.2779623477297896, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.2842377260981912, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.287375415282392, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.2847914359542267, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.2751937984496124, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.2652270210409745, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.260797342192691, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.26541159099298633, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.2648578811369509, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.2561830933923957, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.2440014765596161, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.2454780361757106, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.23920265780730898, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.23108157991878922, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.22296050203026946, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.22905131044665927, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.22148394241417496, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.2292358803986711, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.21945367294204504, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.22572905131044665, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.22905131044665927, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.23385012919896642, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.24160206718346253, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.2349575489110373, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.2382798080472499, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.00970398750887747, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.009762632692959747, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.011385573880329375, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.012873485331046966, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.014819601149625947, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.015487185047107175, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.016969912135499407, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.0184888004337755, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.021571904277938345, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.034585600712352345, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.053443209982700544, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.09817192094079001, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.13343495735929664, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.16345210869793447, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.17915867311628908, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.19627704544200522, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.20729365764413576, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.21575704468245208, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.22721280542473474, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.2315587309532825, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.22974193368363072, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.2236298858271303, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.2142574633384142, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.21373901219380556, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.21983013218754344, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.22014037795097677, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.21140257436924534, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.2002535082234109, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.20143218660549458, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.1995982402557571, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.19362516965720122, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.18663362528296082, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.1954849918384597, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.1900760556092135, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.19587119372383746, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.18282120303111604, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.18890397768971282, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.19105277080792804, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.19219820302330914, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.18095038407057193, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.18204236430457066, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.18343464817785413, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 19, "lr_best": 0.00013199999999999998, "wd_best": 0.05, "train/loss_best": 2.0659242343902586, "validation/loss_best": 2.359790563583374, "validation/acc_best": 0.287375415282392, "validation/f1_best": 0.2315587309532825} +{"epoch": 14, "train/lr": 8.9081919031238e-05, "train/loss": 2.214632184505463, "train/grad": 0.24471923887729644, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.11952880859375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.1181982421875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.1160009765625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.113914794921875, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.111903076171875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.109044189453125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.1057373046875, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.1015618896484374, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.0940863037109376, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.0755914306640624, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.0003753662109376, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.7386380004882813, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.596898193359375, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.4791949462890623, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.4009174346923827, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.335586585998535, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.2599241638183596, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.182300148010254, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.1011863422393797, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.033863105773926, "train/loss_020_lr5.2e-01_wd1.0e+00": 1.9687719678878783, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.895209286212921, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.820749317407608, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.7359353113174438, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.6511341685056686, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.575439458489418, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.485486203432083, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.4037931537628174, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.3182932066917419, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.232905041575432, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.1971105742454529, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.1520306184887885, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.1210665261745454, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.1285791882872582, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.0976684188842774, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.079569480419159, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.1715230506658554, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.2813937968015672, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.3561180692911148, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.4291937446594238, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.4563786047697067, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.5610531055927277, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.171875, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.171875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.01957938644103706, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.01957725405227393, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.01957074586767703, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.019560865121893586, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.019547204948030413, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.019523565690033138, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.019485901691950858, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.019428662499412896, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.01933610136155039, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.019339453717693685, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.020455036740750075, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.02439795929007232, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.027304986659437418, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.029449316142126918, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.030655945502221584, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.03169048089534044, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.03345760280266404, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.03484792942181229, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.036097843442112205, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.03699430599808693, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.03750926313921809, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.03833402967080474, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0394832506403327, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.040598441921174525, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.041595549285411836, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.04263430871069431, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.04400414876639843, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.04502930475398898, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.046041451748460534, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.047161112502217294, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.047556632962077856, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.04791937701404095, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.047636980153620244, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.04791497092694044, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.048894428759813306, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.04897551853209734, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.04962625550106168, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.04882041515782475, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.04920843530446291, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.04860689813271165, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.04971215086057782, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.04821214269846678, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1199870109558105, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1192054748535156, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1178998947143555, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.116617202758789, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1153039932250977, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1134305000305176, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1110548973083496, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.107801914215088, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.100876808166504, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.0800282955169678, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.9881374835968018, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.7202398777008057, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.5928955078125, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.498143196105957, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.4481351375579834, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.41357421875, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.389918088912964, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.361827850341797, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.349194049835205, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.3536853790283203, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.3614652156829834, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.3891355991363525, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.4160685539245605, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.462277889251709, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.526163101196289, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.568366050720215, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.6606976985931396, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.743535041809082, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.8409836292266846, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.960728645324707, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.02485990524292, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.0830283164978027, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.1554911136627197, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.2088675498962402, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.2816240787506104, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.3160126209259033, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.262660264968872, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.214582681655884, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.170548439025879, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.0230212211608887, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.067472457885742, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.0551717281341553, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06662975267626431, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06589147286821706, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06533776301218161, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.0664451827242525, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06847545219638243, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06884459210040605, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.07069029162052418, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.07198228128460686, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.07678110003691399, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.09246954595791805, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.13178294573643412, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.18696936138796605, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.22240679217423404, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.24640088593576967, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.2604282022886674, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.2709486895533407, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.27611664820967147, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.2812846068660022, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.28811369509043927, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.2858988556662975, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.2851605758582503, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.27703949796973054, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.2705795496493171, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.2606127722406792, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.25802879291251385, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.2617201919527501, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.25101513473606496, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.23809523809523808, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.2382798080472499, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.22129937246216316, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.22369878183831673, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.2207456626061277, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.21963824289405684, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.2100406053894426, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.22369878183831673, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.2172388335179033, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.2235142118863049, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.21502399409376152, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.2085640457733481, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.23809523809523808, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.2249907715023994, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.2235142118863049, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.009862920770433624, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.009850335982983011, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.010105375059783468, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.011035756819995003, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.013259181304872155, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.013918447133924363, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.015110486099158459, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.015940913146721764, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.021101682952485976, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.03525220359063734, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.05842962194919903, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.10355093953919181, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.1381744540640619, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.16654169834552907, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.18528407131012292, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.19955691966984715, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.20866794136741684, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.218211433189883, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.22931283686141357, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.22930085644661688, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.23062601346068667, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.22719845993881393, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.22466130913243101, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.21934390575748144, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.21588838591302592, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.22246548340922853, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.21272001547693256, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.20452470217105903, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.20374402665800337, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.18981538067247503, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.193522642257273, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.18834369066859155, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.1876958595414159, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.18182583778632067, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.18829145498446528, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.18192885189458016, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.18719014574655188, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.18026089853795865, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.1725368588991194, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.19428899569694766, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.18409643966525122, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.17885635983775036, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 18, "lr_best": 0.00011399999999999999, "wd_best": 0.05, "train/loss_best": 2.1011863422393797, "validation/loss_best": 2.349194049835205, "validation/acc_best": 0.28811369509043927, "validation/f1_best": 0.22931283686141357} +{"epoch": 15, "train/lr": 6.196799573888289e-05, "train/loss": 2.1751972526311874, "train/grad": 0.24136983282864094, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.114664306640625, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.113265380859375, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.11088134765625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.108729248046875, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.1066015625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.10361572265625, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.100068359375, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.095537109375, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.0871051025390623, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.0646044921875, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.972261962890625, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.7107670593261717, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.5821897888183596, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.467108154296875, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.3896629714965822, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.3240979385375975, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.2485516929626463, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.1722537231445314, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.0919055938720703, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.0213976669311524, "train/loss_020_lr5.2e-01_wd1.0e+00": 1.9514247751235962, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.875914340019226, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.795126178264618, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.7061444067955016, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.6183555960655212, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.5372503399848938, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.4319130384922027, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.3452081781625749, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.2516171103715896, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.165374755859375, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.1248552846908568, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.0745890253782273, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.0455225056409836, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.0368932867050171, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.9810136818885803, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.9703181287646294, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.0429750767350197, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.1674627482891082, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.2382928296923637, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.3012433904409408, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.311579010784626, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.4231995749473572, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.171875, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.171875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.020014881175011396, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.020011753630824386, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.020002886727452276, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.01999052124097943, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.019972964487969876, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.01994227561634034, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.019894988830201327, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.019826104692183436, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.019717301749624314, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.019762542182579636, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.021141307894140482, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.025126254269853234, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.027834838451817633, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.029897279292345046, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.031071843216195702, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.0321716025006026, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.033987062564119694, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.03530052325688302, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.03645864472724497, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.03730911137536168, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.03778104792349041, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.03851818790659309, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.03952027866616845, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.04064131153747439, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.04169934663921595, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.04264075124636293, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0437550738453865, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.04454376513138413, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.04528470436111093, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.04550124030560255, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.04544886503368616, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.04605144202709198, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.04591988591477275, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.046116951145231726, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0463616593927145, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.04752127578482032, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.04721964426338673, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.04793978057801723, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.04791895760223269, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.04776103286072612, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.04823725311085582, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.04705434175208211, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1199426651000977, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1191742420196533, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1179001331329346, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1166412830352783, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1153652667999268, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.113511562347412, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1111061573028564, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.107701539993286, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1000924110412598, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.075364112854004, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.9679760932922363, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.701709747314453, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.5834226608276367, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.492280960083008, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.444037914276123, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.4119248390197754, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.392472743988037, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.366720199584961, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.3552932739257812, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.3609182834625244, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.367705821990967, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.3956589698791504, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.4312613010406494, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.4807708263397217, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.5409979820251465, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.5773465633392334, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.6749343872070312, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.762206792831421, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.8572542667388916, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.981196641921997, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.0502636432647705, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.144043207168579, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.180629014968872, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.2706682682037354, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.3453469276428223, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.3526620864868164, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.303420305252075, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.219149112701416, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.1797683238983154, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.1132874488830566, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.106776237487793, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.065434694290161, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06662975267626431, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06589147286821706, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06552233296419344, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06626061277224068, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06736803248431156, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06847545219638243, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.07013658176448874, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.0725359911406423, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.07788851974898486, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.09671465485418974, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.13658176448874124, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.19269102990033224, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.22886674049464747, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.24732373569582872, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.26245847176079734, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.2681801402731635, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.2737172388335179, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.28165374677002586, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.28460686600221485, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.28313030638612036, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.2842377260981912, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.2794389073458841, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.2678110003691399, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.26264304171280917, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.2576596530084902, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.2571059431524548, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.2484311554078996, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.23938722775932078, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.2369878183831672, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.22517534145441123, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.22129937246216316, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.2172388335179033, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.2235142118863049, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.21650055370985605, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.2203765227021041, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.22000738279808046, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.21410114433370248, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.22129937246216316, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.21188630490956073, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.23052787006275377, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.22812846068660023, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.2248062015503876, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.009821856070944641, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.010098168402998271, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.010787782266697353, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.012484876410504794, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.01365023929978984, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.014933401974581045, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.016979118906828548, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.01949049345904329, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.023206707351105766, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.04003913439052221, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.06128507869312846, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.10942921132070871, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.14480485344439983, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.16835575634596167, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.18872128487383488, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.1998395131139802, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.2078221762852673, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.21854542596835516, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.22727080648365142, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.22749681692952486, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.2301426991017749, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.22839495139349952, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.21934677108832182, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.21701404231180774, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.2159668973454815, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.21773339007499862, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.2095967532795017, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.2047801693352944, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.20288358075070487, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.19272440652323874, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.19258722172298007, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.1876756586997411, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.19475935217036688, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.19065409511610096, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.19669970320758334, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.19433163054785152, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.19217920308474587, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.19808442300306173, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.19058995309965762, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.19525552317134778, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.20282912997410238, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.19557868713727045, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 18, "lr_best": 0.00011399999999999999, "wd_best": 0.05, "train/loss_best": 2.0919055938720703, "validation/loss_best": 2.3552932739257812, "validation/acc_best": 0.28460686600221485, "validation/f1_best": 0.22727080648365142} +{"epoch": 16, "train/lr": 3.870405029380728e-05, "train/loss": 2.1469875031709673, "train/grad": 0.2370486321300268, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.12270751953125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.1212451171875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.11894287109375, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.116708984375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.114453125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.1113720703125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.107593994140625, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.1029705810546875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.094105224609375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.068931884765625, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.965892333984375, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.7072077941894532, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.5865484619140626, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.474728660583496, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.398246421813965, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.331971969604492, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.254325103759766, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.176701097488403, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.094944200515747, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.0231294345855715, "train/loss_020_lr5.2e-01_wd1.0e+00": 1.952111201286316, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.8727150654792786, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.7881430554389954, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.6943102914094925, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.6030555546283722, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.5168885600566864, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.4090533620119094, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.3159116929769517, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.2154592081904412, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.115541414320469, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.0605372992157935, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.0076742109656334, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.962019354403019, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.9477991691231727, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.8868878975510597, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.8770151335000992, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.9259539279341698, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.0398038196563721, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.1040596342086793, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.1612035438418389, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.172190149128437, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.2782040438055993, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.171875, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.171875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.01996039105579257, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.019955284181050956, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.01994416075292975, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.01992994403000921, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.019910536012612282, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.01987696371972561, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.01982983989175409, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.01975995324552059, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.019655299624428153, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.019753609118051827, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.021357416571117938, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.02544346417300403, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.028062418596819044, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.030082056783139705, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.031244588950648904, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.03236048765480518, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.03413759751245379, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.0354271356202662, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.03653874428942799, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.03735973918810487, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.037857865123078226, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.03863695858046413, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.039665672201663255, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.040729925651103255, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.04169664919376373, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.04247044479474425, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.04352441094815731, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.044289103876799345, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.04484011840075255, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0448927628993988, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.044721813257783655, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.04474815348163247, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.044402792416512966, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.04441546892747283, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.04441341059282422, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.04479481706395745, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.045202042907476425, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.04546612720936537, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.04582856835797429, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.045821183156222106, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.04622956939041614, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.04605168910697102, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.119915008544922, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.119135856628418, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.117851972579956, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1166038513183594, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1153202056884766, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1134002208709717, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.110948085784912, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1074204444885254, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.0993080139160156, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.0717804431915283, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.954960346221924, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.6910300254821777, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.577065944671631, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.4880857467651367, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.440298557281494, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.4082577228546143, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.389066696166992, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.3635878562927246, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.3541512489318848, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.3632564544677734, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.3736038208007812, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.4050376415252686, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.440626382827759, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.4922125339508057, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.556736946105957, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.5999338626861572, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.712028980255127, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.7983851432800293, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.9074881076812744, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.040825605392456, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.105154037475586, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.180778980255127, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.2489936351776123, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.316411256790161, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.398265838623047, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.4294679164886475, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.3979990482330322, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.30875301361084, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.2660834789276123, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.1886672973632812, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.250457763671875, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.17647123336792, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06662975267626431, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06662975267626431, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06607604282022887, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06718346253229975, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.067921742340347, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06921373200442968, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06866002214839424, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.07013658176448874, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.07622739018087855, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.09800664451827243, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.13953488372093023, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.19490586932447398, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.22812846068660023, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.2467700258397933, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.2633813215208564, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.2742709486895533, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.2739018087855297, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.27906976744186046, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.287375415282392, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.2838685861941676, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.2870062753783684, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.2777777777777778, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.26947212993724623, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.26356589147286824, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.25692137320044295, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.2552602436323367, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.24529346622369877, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.23588039867109634, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.2355112587670727, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.22277593207825766, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.22259136212624583, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.2220376522702104, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.22000738279808046, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.22056109265411591, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.2248062015503876, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.2222222222222222, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.22240679217423404, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.21613141380583242, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.21207087486157253, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.22720561092654115, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.22093023255813954, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.2172388335179033, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.009769178620959293, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.01017066752160863, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.010529206858975187, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.012549113274349521, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.01344922968935641, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.015198347171077917, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.01521664536899025, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.016943415433243923, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.021625586440680574, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.03996200875401323, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.0629952417648471, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.11196931454057306, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.1451079721840459, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.168570251113395, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.19183776669879607, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.2055543171320422, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.20877196659844824, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.21687067706873756, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.22916718202319286, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.22754606728592855, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.23194921839082328, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.22683421739774615, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.2199413443517199, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.21816900320577035, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.21456535995485249, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.21469012339382107, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.20273381118530062, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.1978191171683975, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.19563937281521207, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.18488127442039948, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.18996682844939497, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.18724164880345553, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.1870271165358767, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.18864602602043576, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.1927200877858153, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.18728254046256143, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.19031620433860988, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.18733073489829802, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.1856238289154659, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.1958841729271811, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.19365589257992924, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.18983117728975615, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 18, "lr_best": 0.00011399999999999999, "wd_best": 0.05, "train/loss_best": 2.094944200515747, "validation/loss_best": 2.3541512489318848, "validation/acc_best": 0.287375415282392, "validation/f1_best": 0.22916718202319286} +{"epoch": 17, "train/lr": 2.030750443206766e-05, "train/loss": 2.118912535905838, "train/grad": 0.2295945758372545, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.1189501953125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.117412109375, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.115167236328125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.11294921875, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.110794677734375, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.10771484375, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.103963623046875, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.09924560546875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.09002685546875, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.062559814453125, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.9520880126953126, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.691153717041016, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.570581359863281, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.4586374664306643, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.3815367126464846, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.315489635467529, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.239599380493164, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.1626906299591067, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.0790438556671145, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.00685359954834, "train/loss_020_lr5.2e-01_wd1.0e+00": 1.9378387594223023, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.8608342599868775, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.7778895139694213, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.681590895652771, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.5915953850746154, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.4996105360984802, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.3870789116621018, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.2937908458709717, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.1863370585441588, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.0845411866903305, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.0247723478078843, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.9585093680024147, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.9113433966040612, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.8901347103714943, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.8197071886062622, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.7966585329174996, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.8455339297652245, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.946368744969368, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.9955893981456757, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.049735358953476, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.0452296277880668, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.1424428594112397, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.171875, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.171875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.01972955005709082, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.01972316574305296, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.01970956217497587, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.01969450219068676, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.019673501164652406, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.019640242359600962, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.019592451229691506, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.019525015596300363, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.01942801714409143, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.01956449680496007, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.02126832937821746, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.025342268226668237, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.02791192357428372, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.029941304875537752, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.03108465254306793, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.032195139210671186, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.033946315087378026, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.03515602154657245, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.03619448439218104, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.037012802818790075, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.037454439401626585, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.03819607449695468, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.03917678384110332, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.04018769796937704, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.04114021673798561, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.04180004706606269, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.042684114221483466, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.04340892840176821, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.043842663299292324, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.043858668971806763, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.043360367398709056, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.043299674969166514, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0425662006996572, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.04226142983883619, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.041831235643476246, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.04186010643839836, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.042108361814171075, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.04277207612991333, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.04295665813609958, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0427965666167438, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0432023486495018, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.04321151372045279, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.119882583618164, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1190836429595947, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.117805004119873, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1165452003479004, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.115238666534424, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1133015155792236, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1107583045959473, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1071436405181885, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.0987110137939453, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.0696330070495605, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.947976589202881, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.6852052211761475, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.572995901107788, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.4848318099975586, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.4370691776275635, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.404628038406372, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.384833812713623, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.358050584793091, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.3474624156951904, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.354748487472534, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.3643505573272705, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.3943257331848145, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.42679500579834, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.478393316268921, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.5434539318084717, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.5855164527893066, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.693187952041626, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.7811880111694336, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.8835127353668213, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.016814947128296, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.0896098613739014, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.1795387268066406, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.2381176948547363, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.319265604019165, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.416973114013672, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.4851746559143066, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.438242197036743, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.3636059761047363, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.332319974899292, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.2138171195983887, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.2827484607696533, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.232440710067749, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06662975267626431, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06589147286821706, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06626061277224068, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06736803248431156, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06847545219638243, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06884459210040605, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06939830195644149, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.07308970099667775, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.07751937984496124, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.09929863418235511, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.14285714285714285, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.19712070874861573, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.2294204503506829, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.24935400516795866, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.2643041712809155, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.27260981912144705, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.27740863787375414, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.28294573643410853, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.28755998523440385, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.2884828349944629, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.2842377260981912, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.27870062753783686, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.26651901070505724, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.2622739018087855, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.2543373938722776, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.2619047619047619, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.24806201550387597, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.23717238833517904, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.23791066814322628, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.2220376522702104, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.2249907715023994, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.2222222222222222, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.21963824289405684, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.21077888519748986, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.2216685123661868, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.2216685123661868, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.21483942414174972, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.21705426356589147, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.20653377630121816, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.23421926910299004, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.22665190107050573, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.22369878183831673, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.010058293484971564, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.010026798010648569, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.011275249866110637, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.013444568801562957, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.014357959892327465, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.015180754890151978, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.016478032124786563, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.019174297205053936, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.02317720219346917, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.04229636843136764, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.06546120089714418, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.11444559987399533, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.14700264908896768, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.17093249094010807, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.1924515443482752, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.20451573905516338, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.21269090928574785, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.220954212617825, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.2308406982991503, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.233313540014799, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.23105319330392818, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.22934652546626821, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.2195202253961146, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.21681629591027174, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.21363316711147906, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.222855425925608, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.2101343642009975, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.20407966260398014, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.20295245354956204, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.18582229836495645, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.19460450826246975, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.1893441417479286, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.1905789904962325, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.1855256012857485, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.19258978492712134, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.19177380037439629, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.18689980146265375, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.18515506088334052, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.17895416657748764, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.1966714113916379, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.19581332300762513, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.1933673085368466, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 19, "lr_best": 0.00013199999999999998, "wd_best": 0.05, "train/loss_best": 2.00685359954834, "validation/loss_best": 2.354748487472534, "validation/acc_best": 0.2884828349944629, "validation/f1_best": 0.233313540014799} +{"epoch": 18, "train/lr": 7.5829098008590064e-06, "train/loss": 2.101255870461464, "train/grad": 0.22640167348086834, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.12069580078125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.119144287109375, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.11694091796875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.114632568359375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.112371826171875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.10919677734375, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.105472412109375, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.1005889892578127, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.091103515625, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.0629638671875, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.951231689453125, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.6949386596679688, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.5751002502441405, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.4618865966796877, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.3836359405517578, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.3166792678833006, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.2386608123779297, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.159228343963623, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.0730045890808104, "train/loss_019_lr4.4e-01_wd1.0e+00": 1.9985458469390869, "train/loss_020_lr5.2e-01_wd1.0e+00": 1.9271206760406494, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.847446732521057, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.7633250665664673, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.6698800253868102, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.5733149927854537, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.483063259124756, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.369828800559044, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.277407597899437, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.1673446369171143, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.056114656329155, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.9951613748073578, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.9333808198571205, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.8825921964645386, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.8531983229517937, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.7761548155546188, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.7495117673277855, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.7850909298658371, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.8723952525854111, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.9222102144360542, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.9576120150089263, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.9527234840393066, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.0375140064954758, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.171875, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.171875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.019846954867243766, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.019839208968915046, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.019824685752391814, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.019808657420799135, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.019787303078919648, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.019753417847678065, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.01970465134829283, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.019635400036349893, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.01953737801872194, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.019687223294749857, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.021420817938633263, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.0254870624281466, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.028018712420016526, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.0299969123583287, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.03111784553155303, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.03221257341094315, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.03394845010712743, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.03519064700230956, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.03629177790135145, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.0371115755289793, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.037569618765264746, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.0383445087634027, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.03923336934298277, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.04022979255765677, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.04104830050840974, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.04171507904306054, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.04254437353461981, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.04307995332404971, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.04326581912115216, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.04297761330381036, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0426763079687953, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.042341503519564866, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.04176502401009202, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0414297660626471, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.040666362792253496, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.04034856310114265, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.04061646766960621, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.04107016222551465, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.04144239550456405, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0410063174366951, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.04130993867293, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.04121172472834587, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1198763847351074, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1190645694732666, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.117797374725342, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1165051460266113, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1152045726776123, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1132757663726807, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1107287406921387, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1070735454559326, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.098555326461792, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.0689401626586914, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.9456498622894287, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.6835176944732666, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.572316884994507, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.484837055206299, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.437415361404419, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.4053285121917725, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.3860933780670166, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.3595011234283447, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.3490920066833496, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.356381416320801, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.366046667098999, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.396303653717041, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.4285786151885986, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.4804277420043945, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.548219919204712, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.592634677886963, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.7037153244018555, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.78910756111145, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.893754720687866, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.020409107208252, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.095421552658081, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.181123971939087, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.2471320629119873, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.3338279724121094, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.432429075241089, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.4910383224487305, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.4561119079589844, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.3883347511291504, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.353560209274292, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.2584152221679688, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.332209348678589, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.2858598232269287, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06681432262827612, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06626061277224068, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.0664451827242525, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06755260243632337, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06773717238833518, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06921373200442968, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06866002214839424, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.07308970099667775, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.07641196013289037, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.09874492432631968, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.14525655223329642, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.1969361387966039, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.22868217054263565, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.25046142488002954, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.26541159099298633, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.27297895902547065, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.27611664820967147, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.28202288667404946, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.28645256552233295, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.2870062753783684, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.284422296050203, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.2763012181616833, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.2698412698412698, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.26264304171280917, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.25489110372831303, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.26098191214470284, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.24880029531192321, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.23717238833517904, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.23292727943890734, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.2220376522702104, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.2216685123661868, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.2207456626061277, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.22314507198228128, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.21077888519748986, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.21908453303802142, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.21853082318198597, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.21631598375784422, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.2146548541897379, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.2054263565891473, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.23052787006275377, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.21926910299003322, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.21963824289405684, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.009947977697793296, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.010062211241599619, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.011223726002462913, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.013118779400853035, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.013726429263656434, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.015573451689714904, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.01571322582479461, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.019427201527907435, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.022782775256904923, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.042014995964865944, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.06665869128601949, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.11409427582032045, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.14660737563083143, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.1721922358977723, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.19235185824699533, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.20479268311070245, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.21150763983217105, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.2203069570383229, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.23020531985287943, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.23060986410390724, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.2303674923506608, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.2253204392513891, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.22100970364684583, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.21598321763039663, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.2128468650134756, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.22108062784264523, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.20888541437659147, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.20138342855303923, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.19605445928839224, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.18650583362085338, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.19243600536872899, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.18879266247790213, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.1945270444016403, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.18683532764660846, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.1913349041672013, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.1906818351912357, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.18856335049715653, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.1862909046141125, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.18038454727158912, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.19459808083898697, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.19117125021751968, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.18897724537734895, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 19, "lr_best": 0.00013199999999999998, "wd_best": 0.05, "train/loss_best": 1.9985458469390869, "validation/loss_best": 2.356381416320801, "validation/acc_best": 0.2870062753783684, "validation/f1_best": 0.23060986410390724} +{"epoch": 19, "train/lr": 1.0867618231465446e-06, "train/loss": 2.095931504368782, "train/grad": 0.22278786867856978, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.12143310546875, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.119986572265625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.117652587890625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.115318603515625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.11298583984375, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.109815673828125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.10596923828125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.101075439453125, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.091461181640625, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.062999267578125, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.9500286865234373, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.691566619873047, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.5737384033203123, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.462919120788574, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.3853548049926756, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.3183171272277834, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.240949420928955, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.1625126457214354, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.0776461219787596, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.004200701713562, "train/loss_020_lr5.2e-01_wd1.0e+00": 1.9332346630096435, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.8531396293640137, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.7671439671516418, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.6718750405311584, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.5748591899871827, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.4810459870100021, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.366707026362419, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.2743620997667313, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.1637955334782601, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.0505962726473808, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.9880518013238907, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.9216490930318832, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.867065369784832, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.8363813677430153, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.7638767403364182, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.7342709788680076, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.7667885765433311, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.8478319826722145, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.8844057443737984, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.9171597421169281, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.9106950253248215, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.9966536650061607, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.171875, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.171875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.01947273643221706, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.019466488556936383, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.019451842717826365, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.019435340417549015, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.019414957286790012, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.01938101783860475, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.01933333755005151, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.01926534897647798, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.019165697759017348, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.01931863909587264, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.021049746801145373, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.02500843971967697, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.027478810781612992, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.02945780048146844, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.030625044461339714, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.031771652344614265, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.03353609055280685, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.03481126841157675, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.03589998419396579, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.036730164475739, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.03719999079592526, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.037970420448109506, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.038886572746559975, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.039887200901284815, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.04076038801111281, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.04141705272719264, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.042231674771755934, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.042792604193091395, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.042914024218916894, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.04265369914472103, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.04224335568025708, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0419711690954864, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.041132211722433566, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.040801200177520515, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.03994103476405144, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.03947071002796292, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.03954006660729647, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.03985136240720749, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.04002750936895609, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.03976611150428653, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.03988170517608523, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.03993832070380449, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1198723316192627, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1190640926361084, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1177895069122314, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1164968013763428, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.115199089050293, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.113255023956299, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.110706329345703, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1070210933685303, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.098494052886963, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.068794012069702, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.945268392562866, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.683198928833008, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.5721018314361572, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.4846596717834473, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.4371438026428223, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.4051637649536133, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.3857831954956055, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.359205484390259, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.3487589359283447, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.35610294342041, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.365894317626953, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.3964412212371826, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.429165840148926, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.4813003540039062, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.548741340637207, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.5926740169525146, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.703693389892578, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.7888989448547363, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.892813205718994, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.0218570232391357, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.09596848487854, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.1821236610412598, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.2473349571228027, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.3301384449005127, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.4283220767974854, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.4829039573669434, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.4501993656158447, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.3857929706573486, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.356797218322754, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.247694730758667, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.3309502601623535, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.2770190238952637, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06718346253229975, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06607604282022887, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06662975267626431, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06699889258028793, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06773717238833518, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06921373200442968, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06847545219638243, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.0725359911406423, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.07659653008490218, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.09874492432631968, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.1448874123292728, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.19767441860465115, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.22868217054263565, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.2500922849760059, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.26504245108896274, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.2733480989294943, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.2763012181616833, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.2823920265780731, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.28755998523440385, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.2870062753783684, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.28460686600221485, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.27722406792174237, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.26891842008121075, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.2633813215208564, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.2558139534883721, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.2604282022886674, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.2484311554078996, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.23883351790328536, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.23624953857511996, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.22185308231819859, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.22406792174234036, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.22000738279808046, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.2207456626061277, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.2117017349575489, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.22111480251015134, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.21982281284606867, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.21336286452565523, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.21502399409376152, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.20948689553340716, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.23163528977482467, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.2203765227021041, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.2216685123661868, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.0101923476558366, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.010036600068440874, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.011301870621075356, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.012872386847833343, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.01361296398175855, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.015570309426901236, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.01554028198198633, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.01886136324752026, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.02277691036004317, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.04196204629886476, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.0663585801931832, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.11462407750976776, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.14689765162480117, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.17199269890763833, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.1921528111539581, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.20498070230240648, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.21184930269759858, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.22075488366590887, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.23108099248291247, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.23130724692905916, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.23073749721676573, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.22623623059549824, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.22040167136200625, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.21648320754101005, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.2135732868512362, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.22009311474503224, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.2079709204545134, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.20389374729061926, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.19956852812708784, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.1857997291442556, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.19471968643032075, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.18743478259069846, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.192342212336765, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.18691658372959086, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.1939583449139919, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.1923180148290796, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.18632923698703696, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.18671828710615976, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.18333054021581807, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.19657759360883062, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.19265112265007311, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.19082443131172122, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 18, "lr_best": 0.00011399999999999999, "wd_best": 0.05, "train/loss_best": 2.0776461219787596, "validation/loss_best": 2.3487589359283447, "validation/acc_best": 0.28755998523440385, "validation/f1_best": 0.23108099248291247} diff --git a/input_space_v3/flat_lr1e-3_3/eval_v2/ppmi_dx__patch__logistic/config.yaml b/input_space_v3/flat_lr1e-3_3/eval_v2/ppmi_dx__patch__logistic/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..dc6933d4b6fae11a0d5d976586e1d75753b1a755 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_3/eval_v2/ppmi_dx__patch__logistic/config.yaml @@ -0,0 +1,30 @@ +output_root: experiments/input_space_v3/output +name_prefix: eval_logistic +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_3; eval v2 (ppmi_dx patch logistic) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: input_space_v3/flat_lr1e-3_3/eval_v2/ppmi_dx__patch__logistic +model: flat_mae +representation: patch +dataset: ppmi_dx +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/eval_v2/ppmi_dx__patch__logistic +remote_dir: null diff --git a/input_space_v3/flat_lr1e-3_3/eval_v2/ppmi_dx__patch__logistic/eval_table.csv b/input_space_v3/flat_lr1e-3_3/eval_v2/ppmi_dx__patch__logistic/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..810b7af1939aed9ff07fa4b2966f750c5e436ae1 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_3/eval_v2/ppmi_dx__patch__logistic/eval_table.csv @@ -0,0 +1,203 @@ +model,repr,clf,dataset,trial,C,split,acc,acc_std,f1,f1_std,bacc,bacc_std +flat_mae,patch,logistic,ppmi_dx,,0.3593813663804626,train,0.9217081850533808,0.011836709793576561,0.916041938287701,0.012900401624927858,0.9097308488612836,0.013637999665252937 +flat_mae,patch,logistic,ppmi_dx,,0.3593813663804626,test,0.69,0.04459852463927477,0.6521153630344518,0.05050840054808068,0.6480051480051481,0.04841896740995558 +flat_mae,patch,logistic,ppmi_dx,1,0.005994842503189409,train,0.7508896797153025,0.016649165255786608,0.7147663171937761,0.020441034747737213,0.7063664097623634,0.019021329947373513 +flat_mae,patch,logistic,ppmi_dx,1,0.005994842503189409,test,0.67,0.04304172394316937,0.6176572818908586,0.05261837286469396,0.616723259762309,0.04750418212707875 +flat_mae,patch,logistic,ppmi_dx,2,0.046415888336127774,train,0.8096085409252669,0.015281486453188843,0.7901836338070432,0.017523288215927912,0.7810158424320275,0.017468783498180002 +flat_mae,patch,logistic,ppmi_dx,2,0.046415888336127774,test,0.68,0.04614853843839477,0.6567996567996568,0.049125936970562153,0.6553480475382003,0.04840618253889528 +flat_mae,patch,logistic,ppmi_dx,3,0.005994842503189409,train,0.7419928825622776,0.01573107470627788,0.7014963644022785,0.019862561157028818,0.693922607578677,0.018210194148015276 +flat_mae,patch,logistic,ppmi_dx,3,0.005994842503189409,test,0.62,0.04372872739973118,0.5703301673450927,0.05167280500577023,0.5713073005093379,0.04755213796410491 +flat_mae,patch,logistic,ppmi_dx,4,0.046415888336127774,train,0.8113879003558719,0.015473563332966438,0.7918954796338993,0.017782900606783503,0.7824609291372298,0.017680854903953602 +flat_mae,patch,logistic,ppmi_dx,4,0.046415888336127774,test,0.69,0.04282793013910431,0.6570417081535569,0.04883218569715067,0.6532258064516129,0.04711503945227294 +flat_mae,patch,logistic,ppmi_dx,5,0.3593813663804626,train,0.9359430604982206,0.01059631533405983,0.9314420483348469,0.01150041049710233,0.9262336758724042,0.012367053834320118 +flat_mae,patch,logistic,ppmi_dx,5,0.3593813663804626,test,0.62,0.04718665489309451,0.5876736111111112,0.051184735759030695,0.5865874363327674,0.049753308745394784 +flat_mae,patch,logistic,ppmi_dx,6,0.046415888336127774,train,0.802491103202847,0.015481650460921849,0.7812838555636196,0.018059304280948228,0.7717565831727682,0.017925486411935535 +flat_mae,patch,logistic,ppmi_dx,6,0.046415888336127774,test,0.65,0.04462456274295581,0.6224786970121885,0.049020523365380445,0.6209677419354839,0.04810812179177235 +flat_mae,patch,logistic,ppmi_dx,7,0.3593813663804626,train,0.9252669039145908,0.01010130861367811,0.9203224369101146,0.010862500933462653,0.9166934275315779,0.011432091302818602 +flat_mae,patch,logistic,ppmi_dx,7,0.3593813663804626,test,0.6,0.04883580244042275,0.5755517826825127,0.05121325029895319,0.5755517826825127,0.051020101868826405 +flat_mae,patch,logistic,ppmi_dx,8,0.3593813663804626,train,0.9377224199288257,0.009811126511103439,0.9335389896710061,0.010597431597259102,0.9294182187968315,0.011438556759750394 +flat_mae,patch,logistic,ppmi_dx,8,0.3593813663804626,test,0.54,0.047691659648202635,0.5166036149642708,0.048755878717169465,0.5169779286926994,0.0489214682840002 +flat_mae,patch,logistic,ppmi_dx,9,0.005994842503189409,train,0.7402135231316725,0.016052553602058022,0.694200954084675,0.02097647080993646,0.6872591522157996,0.018759040355816582 +flat_mae,patch,logistic,ppmi_dx,9,0.005994842503189409,test,0.7,0.03672729774976645,0.6357455075279261,0.050024815323777665,0.6358234295415959,0.04236858140888164 +flat_mae,patch,logistic,ppmi_dx,10,0.3593813663804626,train,0.9199288256227758,0.010905893542022342,0.9140482947304025,0.011897393468812762,0.9080095268679084,0.012663439427273526 +flat_mae,patch,logistic,ppmi_dx,10,0.3593813663804626,test,0.64,0.045514551519266894,0.6216897856242118,0.04734701094260005,0.6230899830220713,0.04777408581845406 +flat_mae,patch,logistic,ppmi_dx,11,0.3593813663804626,train,0.9217081850533808,0.011096956793206313,0.9153521743893088,0.012327735843125099,0.9068454292442731,0.013428215589780529 +flat_mae,patch,logistic,ppmi_dx,11,0.3593813663804626,test,0.61,0.05201162946880245,0.5793334052421529,0.05627745777013522,0.5785229202037352,0.05528542386157481 +flat_mae,patch,logistic,ppmi_dx,12,0.046415888336127774,train,0.8042704626334519,0.01590150118375341,0.782987208110423,0.01836054685821872,0.7732016698779705,0.01812671471061987 +flat_mae,patch,logistic,ppmi_dx,12,0.046415888336127774,test,0.61,0.040596921065519244,0.5311936530833032,0.04927403398026479,0.5428692699490663,0.04254045778343916 +flat_mae,patch,logistic,ppmi_dx,13,0.046415888336127774,train,0.8185053380782918,0.01481993251731031,0.7997484804024313,0.017040396867928815,0.789980732177264,0.017088219249789365 +flat_mae,patch,logistic,ppmi_dx,13,0.046415888336127774,test,0.6,0.04699649348621661,0.570999570999571,0.04967337414655429,0.5704584040747029,0.048939672067760134 +flat_mae,patch,logistic,ppmi_dx,14,0.005994842503189409,train,0.7437722419928826,0.016238746903679494,0.705759162303665,0.01979509170320904,0.6979768786127167,0.01833817196731239 +flat_mae,patch,logistic,ppmi_dx,14,0.005994842503189409,test,0.63,0.04357496528971653,0.5636277862955537,0.05372977004006386,0.5691850594227504,0.046908008955386125 +flat_mae,patch,logistic,ppmi_dx,15,0.005994842503189409,train,0.7384341637010676,0.015367078379914096,0.6955142026293385,0.01975630706048527,0.6884232498394348,0.01790220808149744 +flat_mae,patch,logistic,ppmi_dx,15,0.005994842503189409,test,0.69,0.04282679535057461,0.6408295678368672,0.053170719343802866,0.6379456706281834,0.04808563326883216 +flat_mae,patch,logistic,ppmi_dx,16,0.046415888336127774,train,0.8256227758007118,0.014726224608318664,0.8071352532496638,0.017129013693909872,0.7966308071076857,0.01726129343897176 +flat_mae,patch,logistic,ppmi_dx,16,0.046415888336127774,test,0.6,0.0447986562298469,0.5659722222222222,0.04826623031932172,0.565365025466893,0.047010022666281605 +flat_mae,patch,logistic,ppmi_dx,17,0.005994842503189409,train,0.7491103202846975,0.016429745533362804,0.7114643071713365,0.020503765745134614,0.7031818668379362,0.01904228369367373 +flat_mae,patch,logistic,ppmi_dx,17,0.005994842503189409,test,0.7,0.04011411721576332,0.6493688639551192,0.050429278197408535,0.6460101867572157,0.04501853517769544 +flat_mae,patch,logistic,ppmi_dx,18,0.005994842503189409,train,0.7419928825622776,0.016925594263974546,0.7041493158294093,0.02062251905103236,0.6965317919075145,0.019098896615164604 +flat_mae,patch,logistic,ppmi_dx,18,0.005994842503189409,test,0.62,0.042627990804165294,0.5703301673450927,0.048983573314206,0.5713073005093379,0.04525683358841364 +flat_mae,patch,logistic,ppmi_dx,19,0.046415888336127774,train,0.8220640569395018,0.015501385166666017,0.8041429686628749,0.0176040721916802,0.7946103618068936,0.017571649758086755 +flat_mae,patch,logistic,ppmi_dx,19,0.046415888336127774,test,0.65,0.044524415773820096,0.6266666666666667,0.047462621844499474,0.6260611205432938,0.047335711082041446 +flat_mae,patch,logistic,ppmi_dx,20,0.046415888336127774,train,0.8078291814946619,0.015406487222362536,0.7864020270270271,0.01808259247633948,0.776091843288375,0.017935401116508185 +flat_mae,patch,logistic,ppmi_dx,20,0.046415888336127774,test,0.7,0.03931177431762651,0.6493688639551192,0.0494004257932938,0.6460101867572157,0.04397233720735772 +flat_mae,patch,logistic,ppmi_dx,21,0.046415888336127774,train,0.8149466192170819,0.016355197837251603,0.7958219800181653,0.018594632893649023,0.7862208306572469,0.018367208739164444 +flat_mae,patch,logistic,ppmi_dx,21,0.046415888336127774,test,0.67,0.04150243848257593,0.6108031607500884,0.05296131715022752,0.6116298811544991,0.046249221973426936 +flat_mae,patch,logistic,ppmi_dx,22,0.3593813663804626,train,0.9270462633451957,0.011065623855282375,0.9215305660274551,0.012124856864720524,0.9146596017983302,0.0130347829411895 +flat_mae,patch,logistic,ppmi_dx,22,0.3593813663804626,test,0.62,0.03996298287165261,0.5634191176470589,0.04712754090395979,0.566213921901528,0.0429102224672043 +flat_mae,patch,logistic,ppmi_dx,23,0.046415888336127774,train,0.8096085409252669,0.015382261255182161,0.7906802699776875,0.017745004568666244,0.7818855705416399,0.0178072592226517 +flat_mae,patch,logistic,ppmi_dx,23,0.046415888336127774,test,0.65,0.04574962732088644,0.612789025334661,0.05172860033673028,0.6107809847198642,0.04950343624366135 +flat_mae,patch,logistic,ppmi_dx,24,0.005994842503189409,train,0.7508896797153025,0.015957055293256528,0.7113507960965588,0.020068458470621588,0.7028874973239134,0.018440076205058702 +flat_mae,patch,logistic,ppmi_dx,24,0.005994842503189409,test,0.62,0.04510301098596413,0.5634191176470589,0.05300360564676334,0.566213921901528,0.048241511720928186 +flat_mae,patch,logistic,ppmi_dx,25,0.046415888336127774,train,0.8167259786476868,0.01573879375314681,0.7970471812887641,0.018394301815708867,0.7867961892528367,0.018466788766332023 +flat_mae,patch,logistic,ppmi_dx,25,0.046415888336127774,test,0.66,0.042225352574016474,0.6155585707824514,0.04913753013991262,0.6137521222410866,0.04586751078115734 +flat_mae,patch,logistic,ppmi_dx,26,0.005994842503189409,train,0.7437722419928826,0.016311646737159045,0.703103675985032,0.020664237299038705,0.6953676942838792,0.01891160773946696 +flat_mae,patch,logistic,ppmi_dx,26,0.005994842503189409,test,0.64,0.0469522097456552,0.6043956043956044,0.05213543823006843,0.6027164685908319,0.050082068486917854 +flat_mae,patch,logistic,ppmi_dx,27,0.005994842503189409,train,0.7366548042704626,0.016576526207536822,0.6858532753202804,0.022240346457699678,0.6800203382573324,0.01949956391672775 +flat_mae,patch,logistic,ppmi_dx,27,0.005994842503189409,test,0.69,0.04135552683741315,0.6408295678368672,0.050638764189146056,0.6379456706281834,0.0459280575211758 +flat_mae,patch,logistic,ppmi_dx,28,0.3593813663804626,train,0.9323843416370107,0.010422983309574488,0.9271981018872042,0.01145392588754936,0.9198645900235496,0.012481924138023875 +flat_mae,patch,logistic,ppmi_dx,28,0.3593813663804626,test,0.69,0.04698286921847152,0.6756982948007113,0.04832736498958284,0.6786926994906621,0.04864509316849883 +flat_mae,patch,logistic,ppmi_dx,29,0.046415888336127774,train,0.8113879003558719,0.016017676182244783,0.7913911922904526,0.018602199850879894,0.7815912010276171,0.0185222578715214 +flat_mae,patch,logistic,ppmi_dx,29,0.046415888336127774,test,0.67,0.04429401765475784,0.6396986570586308,0.04853173029425262,0.6370967741935484,0.04733558034824792 +flat_mae,patch,logistic,ppmi_dx,30,0.046415888336127774,train,0.8256227758007118,0.015622960626019445,0.8080601092896175,0.017631721076197624,0.7983702633269107,0.017525029019911372 +flat_mae,patch,logistic,ppmi_dx,30,0.046415888336127774,test,0.7,0.04239627813853475,0.6493688639551192,0.053662298182253675,0.6460101867572157,0.04814321988797351 +flat_mae,patch,logistic,ppmi_dx,31,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,31,166.81005372000556,test,0.66,0.04894311391809883,0.6486151302190988,0.0499258344034549,0.6544991511035654,0.0508356658954075 +flat_mae,patch,logistic,ppmi_dx,32,0.3593813663804626,train,0.9234875444839857,0.010608608971668959,0.918190896934613,0.011509273602728782,0.9135088846071505,0.012288550179730141 +flat_mae,patch,logistic,ppmi_dx,32,0.3593813663804626,test,0.61,0.04507219098291096,0.568536342515765,0.05029184264582976,0.5683361629881154,0.04786662638939085 +flat_mae,patch,logistic,ppmi_dx,33,0.046415888336127774,train,0.8202846975088968,0.015878339574990755,0.8019490375187978,0.01825544855868272,0.7922955469920787,0.01827705407906523 +flat_mae,patch,logistic,ppmi_dx,33,0.046415888336127774,test,0.59,0.04810725932746533,0.5626666666666666,0.050136174257836036,0.5623938879456706,0.04944208505590077 +flat_mae,patch,logistic,ppmi_dx,34,0.005994842503189409,train,0.7419928825622776,0.016785815583925855,0.7014963644022785,0.0208072824442017,0.693922607578677,0.019092927234378398 +flat_mae,patch,logistic,ppmi_dx,34,0.005994842503189409,test,0.65,0.04683135274578346,0.612789025334661,0.05230902992333402,0.6107809847198642,0.05024652559721942 +flat_mae,patch,logistic,ppmi_dx,35,0.005994842503189409,train,0.7508896797153025,0.016331369919398434,0.7113507960965588,0.020395255475288244,0.7028874973239134,0.01876847613253173 +flat_mae,patch,logistic,ppmi_dx,35,0.005994842503189409,test,0.67,0.043568699774035026,0.6349153667441089,0.04892081575306327,0.6320033955857385,0.04681768313216853 +flat_mae,patch,logistic,ppmi_dx,36,0.046415888336127774,train,0.802491103202847,0.015380944302979978,0.7790653609817428,0.018180062629861618,0.7682776707343182,0.017882530165796856 +flat_mae,patch,logistic,ppmi_dx,36,0.046415888336127774,test,0.69,0.0418209277754571,0.6408295678368672,0.05121051200267609,0.6379456706281834,0.04644763864286007 +flat_mae,patch,logistic,ppmi_dx,37,0.046415888336127774,train,0.8078291814946619,0.015176204880153837,0.7879689792496332,0.017309936973219562,0.7787010276172126,0.017134294934948818 +flat_mae,patch,logistic,ppmi_dx,37,0.046415888336127774,test,0.64,0.04781725211678312,0.625,0.049387992273371276,0.6281833616298811,0.05029900088871264 +flat_mae,patch,logistic,ppmi_dx,38,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,38,21.54434690031882,test,0.64,0.045855647416648694,0.625,0.046893456482992875,0.6281833616298811,0.047699440618164946 +flat_mae,patch,logistic,ppmi_dx,39,0.046415888336127774,train,0.8096085409252669,0.015122786164079388,0.7896787506776489,0.017438795354017128,0.7801461143224149,0.017398467005578486 +flat_mae,patch,logistic,ppmi_dx,39,0.046415888336127774,test,0.69,0.04413895784904758,0.6570417081535569,0.05024110006867244,0.6532258064516129,0.0482419208000771 +flat_mae,patch,logistic,ppmi_dx,40,0.005994842503189409,train,0.7419928825622776,0.016260064535911976,0.700583841300985,0.02071223809452151,0.6930528794690645,0.018913830951937417 +flat_mae,patch,logistic,ppmi_dx,40,0.005994842503189409,test,0.68,0.04190429094973448,0.6381727725011307,0.04904306658826965,0.634974533106961,0.04564584962220806 +flat_mae,patch,logistic,ppmi_dx,41,0.046415888336127774,train,0.7882562277580071,0.016397940131977796,0.766091320847105,0.018773547982939565,0.7575867052023122,0.01849175917800841 +flat_mae,patch,logistic,ppmi_dx,41,0.046415888336127774,test,0.7,0.0457889899429983,0.6816638370118846,0.04824415852950108,0.6816638370118846,0.048244587232060224 +flat_mae,patch,logistic,ppmi_dx,42,0.046415888336127774,train,0.8078291814946619,0.016658756412793997,0.7889715596968222,0.01891101086858656,0.7804404838364376,0.01882642966977878 +flat_mae,patch,logistic,ppmi_dx,42,0.046415888336127774,test,0.68,0.04156766050669678,0.6381727725011307,0.04791900121636441,0.634974533106961,0.0450474879697533 +flat_mae,patch,logistic,ppmi_dx,43,0.005994842503189409,train,0.7419928825622776,0.016928844699353438,0.7058494414063206,0.020415504273651235,0.6982712481267395,0.019125150816612674 +flat_mae,patch,logistic,ppmi_dx,43,0.005994842503189409,test,0.71,0.040965834545386715,0.6640018537828757,0.05139877669273814,0.6591680814940577,0.04682162920723183 +flat_mae,patch,logistic,ppmi_dx,44,0.005994842503189409,train,0.7437722419928826,0.01613952530430071,0.703103675985032,0.020402443483975484,0.6953676942838792,0.01865513520210217 +flat_mae,patch,logistic,ppmi_dx,44,0.005994842503189409,test,0.67,0.03918838603464041,0.6108031607500884,0.05011717965725812,0.6116298811544991,0.04419755230312127 +flat_mae,patch,logistic,ppmi_dx,45,0.3593813663804626,train,0.9234875444839857,0.010986933433525338,0.9171883941758419,0.012192405479624021,0.9082905159494754,0.01317457368273946 +flat_mae,patch,logistic,ppmi_dx,45,0.3593813663804626,test,0.66,0.04680281615458625,0.6486151302190988,0.04778701933043274,0.6544991511035654,0.04874793442096206 +flat_mae,patch,logistic,ppmi_dx,46,0.046415888336127774,train,0.8185053380782918,0.01525426315561205,0.7972410865874364,0.017819092936242297,0.7856320916292014,0.017514600680805178 +flat_mae,patch,logistic,ppmi_dx,46,0.046415888336127774,test,0.63,0.04533136221204918,0.5906626839252129,0.05023005851427968,0.5895585738539898,0.04762381766026289 +flat_mae,patch,logistic,ppmi_dx,47,0.005994842503189409,train,0.7455516014234875,0.0156942693296363,0.7056136559277643,0.019859073236592518,0.6976825090986941,0.01821997330390097 +flat_mae,patch,logistic,ppmi_dx,47,0.005994842503189409,test,0.69,0.043010747494085705,0.6521153630344518,0.05033248463630214,0.6481324278438031,0.047600048257335575 +flat_mae,patch,logistic,ppmi_dx,48,0.046415888336127774,train,0.791814946619217,0.016298573011935814,0.7683111172186341,0.019196749740361188,0.7587374223934917,0.01891035534093446 +flat_mae,patch,logistic,ppmi_dx,48,0.046415888336127774,test,0.7,0.04157412175861325,0.6782496782496783,0.045260929281968544,0.6765704584040747,0.045003909453856406 +flat_mae,patch,logistic,ppmi_dx,49,0.3593813663804626,train,0.9234875444839857,0.011063852617474678,0.917534286777026,0.012167542523623346,0.9100299721687005,0.01306512046019348 +flat_mae,patch,logistic,ppmi_dx,49,0.3593813663804626,test,0.63,0.04243682834520036,0.5713127099988413,0.052072817644025,0.5742784380305602,0.046483215005438186 +flat_mae,patch,logistic,ppmi_dx,50,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,50,2.782559402207126,test,0.65,0.04733056517727206,0.6266666666666667,0.050934146393898705,0.6260611205432938,0.0507071883648179 +flat_mae,patch,logistic,ppmi_dx,51,0.046415888336127774,train,0.8185053380782918,0.015216913318129681,0.8016113625981145,0.017245022023786524,0.793459644615714,0.017388898628076997 +flat_mae,patch,logistic,ppmi_dx,51,0.046415888336127774,test,0.6,0.04755955845043139,0.5755517826825127,0.049659850521193184,0.5755517826825127,0.04938874328744666 +flat_mae,patch,logistic,ppmi_dx,52,0.3593813663804626,train,0.9288256227758007,0.011004985796885915,0.9239718614718615,0.011867280520177144,0.9195836009419824,0.012460364636256547 +flat_mae,patch,logistic,ppmi_dx,52,0.3593813663804626,test,0.58,0.048746757840906714,0.5442708333333334,0.052686901971222694,0.5441426146010186,0.05146871653508333 +flat_mae,patch,logistic,ppmi_dx,53,0.046415888336127774,train,0.8167259786476868,0.015373284478605604,0.7985053066140357,0.01765982161113972,0.7894053735816742,0.017793297843814 +flat_mae,patch,logistic,ppmi_dx,53,0.046415888336127774,test,0.59,0.047617387580588665,0.5577607593571352,0.05061339318514271,0.5573005093378608,0.049805240489823016 +flat_mae,patch,logistic,ppmi_dx,54,0.3593813663804626,train,0.9306049822064056,0.010734882375874683,0.9259434456334069,0.011569602857853035,0.9218984157567973,0.012228860269116855 +flat_mae,patch,logistic,ppmi_dx,54,0.3593813663804626,test,0.58,0.04722136804456219,0.5320855614973261,0.05190647241191665,0.533955857385399,0.04922465547700165 +flat_mae,patch,logistic,ppmi_dx,55,0.005994842503189409,train,0.7473309608540926,0.015706356004044946,0.7044821661334282,0.02057271488169463,0.6965184114750589,0.01860042761853875 +flat_mae,patch,logistic,ppmi_dx,55,0.005994842503189409,test,0.71,0.03986623132426741,0.6695156695156695,0.04849511615076751,0.6642614601018676,0.04479167378303506 +flat_mae,patch,logistic,ppmi_dx,56,0.005994842503189409,train,0.7491103202846975,0.016156277530139988,0.7131438624689133,0.01955000377321195,0.7049213230571612,0.018241642278659827 +flat_mae,patch,logistic,ppmi_dx,56,0.005994842503189409,test,0.65,0.04706070972690488,0.6011396011396011,0.05496715744943529,0.6005942275042444,0.050541539035601796 +flat_mae,patch,logistic,ppmi_dx,57,0.046415888336127774,train,0.8131672597864769,0.015678881331782305,0.7936099889827396,0.01787502162873399,0.783906015842432,0.017682861631869457 +flat_mae,patch,logistic,ppmi_dx,57,0.046415888336127774,test,0.65,0.046605900913940075,0.6178622120318812,0.05112196602974902,0.615874363327674,0.04973875162194532 +flat_mae,patch,logistic,ppmi_dx,58,0.046415888336127774,train,0.8042704626334519,0.015088296500200835,0.7818969531900481,0.017807014521548495,0.7714622136587455,0.01760113808962773 +flat_mae,patch,logistic,ppmi_dx,58,0.046415888336127774,test,0.69,0.04390181773002115,0.6521153630344518,0.051720656918915586,0.6481324278438031,0.04901402909291965 +flat_mae,patch,logistic,ppmi_dx,59,0.3593813663804626,train,0.9163701067615658,0.01153585163302993,0.9098630576400051,0.01268974495228875,0.9025101691286662,0.01355609994910922 +flat_mae,patch,logistic,ppmi_dx,59,0.3593813663804626,test,0.61,0.0474021096576935,0.5793334052421529,0.05189098821916744,0.5785229202037352,0.05083541678020466 +flat_mae,patch,logistic,ppmi_dx,60,0.046415888336127774,train,0.8113879003558719,0.015256427815301806,0.7928794937765107,0.01720593990446764,0.7842003853564548,0.01710757908107093 +flat_mae,patch,logistic,ppmi_dx,60,0.046415888336127774,test,0.68,0.04107212680151832,0.6323529411764706,0.050915076992490683,0.6298811544991512,0.04623332994672404 +flat_mae,patch,logistic,ppmi_dx,61,0.005994842503189409,train,0.7402135231316725,0.017988091449596944,0.7042403794858485,0.021801223445976434,0.6968261614215372,0.02043039517197499 +flat_mae,patch,logistic,ppmi_dx,61,0.005994842503189409,test,0.7,0.04020895422663961,0.6553308823529411,0.04915556246143496,0.6511035653650254,0.04498928716033764 +flat_mae,patch,logistic,ppmi_dx,62,0.005994842503189409,train,0.7508896797153025,0.01584531352049588,0.7139325189063409,0.01977405880116914,0.705496681652751,0.01837662332603963 +flat_mae,patch,logistic,ppmi_dx,62,0.005994842503189409,test,0.63,0.0398369476742383,0.5636277862955537,0.0499220432480929,0.5691850594227504,0.04326987592103045 +flat_mae,patch,logistic,ppmi_dx,63,2.782559402207126,train,0.994661921708185,0.0032154753019434817,0.9943452231222015,0.0034189276579663355,0.9930555555555556,0.00418309518447277 +flat_mae,patch,logistic,ppmi_dx,63,2.782559402207126,test,0.67,0.047195440457739136,0.648,0.05022082452466916,0.6472835314091681,0.04972622899958616 +flat_mae,patch,logistic,ppmi_dx,64,0.046415888336127774,train,0.8220640569395018,0.01516224067813468,0.803199238009861,0.017572239178784636,0.7928709055876686,0.01759319741297496 +flat_mae,patch,logistic,ppmi_dx,64,0.046415888336127774,test,0.63,0.0434699896480319,0.5783475783475784,0.051884169243076025,0.5793718166383701,0.04738118992875794 +flat_mae,patch,logistic,ppmi_dx,65,0.046415888336127774,train,0.8309608540925267,0.014806954229090523,0.8137144412305524,0.017118023549591795,0.8035752515521302,0.017364462423042973 +flat_mae,patch,logistic,ppmi_dx,65,0.046415888336127774,test,0.62,0.047217556057043024,0.5876736111111112,0.05028877949028039,0.5865874363327674,0.0490854170774758 +flat_mae,patch,logistic,ppmi_dx,66,0.046415888336127774,train,0.8238434163701067,0.015538810834974458,0.8072268284485775,0.017640418158859607,0.7986646328409335,0.017786762795887083 +flat_mae,patch,logistic,ppmi_dx,66,0.046415888336127774,test,0.61,0.04920762136092335,0.5741893219783819,0.05305301820472493,0.5734295415959253,0.05125784468575636 +flat_mae,patch,logistic,ppmi_dx,67,0.046415888336127774,train,0.806049822064057,0.015876485856636802,0.7841530921096677,0.018559192716842067,0.7737770284735603,0.018347123841638873 +flat_mae,patch,logistic,ppmi_dx,67,0.046415888336127774,test,0.65,0.04502910614258293,0.6178622120318812,0.04946250005344651,0.615874363327674,0.04812125371472414 +flat_mae,patch,logistic,ppmi_dx,68,0.005994842503189409,train,0.7437722419928826,0.01658264434320425,0.7066167833993127,0.020542129747900657,0.6988466067223293,0.019145804410675458 +flat_mae,patch,logistic,ppmi_dx,68,0.005994842503189409,test,0.72,0.03969573780646986,0.6783088235294117,0.048842510220025566,0.6723259762308998,0.045164421516928635 +flat_mae,patch,logistic,ppmi_dx,69,0.046415888336127774,train,0.8078291814946619,0.015886441070641303,0.7879689792496332,0.01814107180287072,0.7787010276172126,0.01794852303678019 +flat_mae,patch,logistic,ppmi_dx,69,0.046415888336127774,test,0.69,0.04167788862214591,0.6408295678368672,0.05143210147657819,0.6379456706281834,0.04664760026662357 +flat_mae,patch,logistic,ppmi_dx,70,0.005994842503189409,train,0.7455516014234875,0.016034206210388285,0.7056136559277643,0.01997490391650635,0.6976825090986941,0.01832763783617833 +flat_mae,patch,logistic,ppmi_dx,70,0.005994842503189409,test,0.62,0.04648889759931935,0.5634191176470589,0.05381878472937171,0.566213921901528,0.049170329171532676 +flat_mae,patch,logistic,ppmi_dx,71,0.005994842503189409,train,0.7402135231316725,0.015790166722667018,0.6980540508714084,0.0199188850162789,0.6907380646542496,0.01809637562226836 +flat_mae,patch,logistic,ppmi_dx,71,0.005994842503189409,test,0.67,0.04354784035976984,0.6033177064551027,0.056466843593592615,0.6065365025466893,0.048514450074042696 +flat_mae,patch,logistic,ppmi_dx,72,0.005994842503189409,train,0.7544483985765125,0.01575074816653563,0.7137098560354375,0.02017780521902138,0.7049079426247057,0.018396582224888717 +flat_mae,patch,logistic,ppmi_dx,72,0.005994842503189409,test,0.67,0.0471180474977476,0.6440513428972063,0.0509022624226613,0.6421901528013583,0.050120404806171096 +flat_mae,patch,logistic,ppmi_dx,73,0.005994842503189409,train,0.7384341637010676,0.01687683727563047,0.7000686167374013,0.020882428062336512,0.6927718903874973,0.019383976532550456 +flat_mae,patch,logistic,ppmi_dx,73,0.005994842503189409,test,0.64,0.04552702933423177,0.609375,0.050259694046708187,0.6078098471986417,0.04920490793197611 +flat_mae,patch,logistic,ppmi_dx,74,0.005994842503189409,train,0.7402135231316725,0.017750579680347378,0.701672484002327,0.021627096145095243,0.6942169770926996,0.02006717558796241 +flat_mae,patch,logistic,ppmi_dx,74,0.005994842503189409,test,0.61,0.04435628027686723,0.5555555555555556,0.051762751282332854,0.5581494057724957,0.047611989625702095 +flat_mae,patch,logistic,ppmi_dx,75,0.005994842503189409,train,0.7526690391459074,0.016164371349619667,0.7163914131054339,0.019882836028604436,0.7078114964675658,0.018553022718369356 +flat_mae,patch,logistic,ppmi_dx,75,0.005994842503189409,test,0.66,0.04361926180026434,0.6155585707824514,0.050873713259636084,0.6137521222410866,0.04750590553532694 +flat_mae,patch,logistic,ppmi_dx,76,0.005994842503189409,train,0.7348754448398577,0.016615406453479892,0.6923240851989433,0.02102003546041708,0.6855330764290302,0.019107759154402014 +flat_mae,patch,logistic,ppmi_dx,76,0.005994842503189409,test,0.72,0.04320601809933427,0.6880570409982174,0.050228806965840006,0.6825127334465195,0.048073824272208014 +flat_mae,patch,logistic,ppmi_dx,77,0.046415888336127774,train,0.8274021352313167,0.014955602706153372,0.8106856974179993,0.017045255683556592,0.801554806251338,0.017262179469189117 +flat_mae,patch,logistic,ppmi_dx,77,0.046415888336127774,test,0.64,0.04506706114225777,0.6043956043956044,0.05083841690190432,0.6027164685908319,0.04880919648886307 +flat_mae,patch,logistic,ppmi_dx,78,0.046415888336127774,train,0.8274021352313167,0.014904873068732265,0.8115495635640826,0.016730296081179066,0.803294262470563,0.016895082331800634 +flat_mae,patch,logistic,ppmi_dx,78,0.046415888336127774,test,0.58,0.045636349547263304,0.5091164095371669,0.05206360287766519,0.5186757215619694,0.047037385446461875 +flat_mae,patch,logistic,ppmi_dx,79,0.005994842503189409,train,0.7402135231316725,0.016194307473121856,0.6980540508714084,0.020496423613501184,0.6907380646542496,0.018609605892829333 +flat_mae,patch,logistic,ppmi_dx,79,0.005994842503189409,test,0.69,0.04143592161398126,0.6408295678368672,0.05067071699814611,0.6379456706281834,0.046088849574886036 +flat_mae,patch,logistic,ppmi_dx,80,0.046415888336127774,train,0.8202846975088968,0.014546158759840376,0.7999950670007012,0.01697550850109671,0.7888166345536287,0.01680113795479573 +flat_mae,patch,logistic,ppmi_dx,80,0.046415888336127774,test,0.65,0.04614000866926663,0.6072270227808326,0.05294847330705651,0.6056876061120543,0.04977212159655057 +flat_mae,patch,logistic,ppmi_dx,81,0.046415888336127774,train,0.791814946619217,0.015896986360703375,0.7711176783868172,0.018081268398796344,0.7630860629415542,0.017898030894617018 +flat_mae,patch,logistic,ppmi_dx,81,0.046415888336127774,test,0.67,0.0426543081059815,0.648,0.04540251355128882,0.6472835314091681,0.045326291461740914 +flat_mae,patch,logistic,ppmi_dx,82,0.046415888336127774,train,0.802491103202847,0.015013024406748166,0.7790653609817428,0.017783664025102175,0.7682776707343182,0.017455344591925583 +flat_mae,patch,logistic,ppmi_dx,82,0.046415888336127774,test,0.65,0.04634360365789437,0.6178622120318812,0.05163327164311699,0.615874363327674,0.05016623531359643 +flat_mae,patch,logistic,ppmi_dx,83,0.005994842503189409,train,0.7437722419928826,0.016577434961625274,0.707460960092539,0.019906674372229552,0.6997163348319417,0.018620835399906426 +flat_mae,patch,logistic,ppmi_dx,83,0.005994842503189409,test,0.56,0.046858403728680297,0.5098039215686274,0.0499789639512692,0.5127334465195246,0.04765680598195394 +flat_mae,patch,logistic,ppmi_dx,84,0.046415888336127774,train,0.8238434163701067,0.01570840071961559,0.8058708387560494,0.018058826098698057,0.7960554485120959,0.018108610231751497 +flat_mae,patch,logistic,ppmi_dx,84,0.046415888336127774,test,0.65,0.045282804683455725,0.6178622120318812,0.04993877101521104,0.615874363327674,0.048652836032145035 +flat_mae,patch,logistic,ppmi_dx,85,0.005994842503189409,train,0.7419928825622776,0.01571725418537445,0.705006099702074,0.018967952990783514,0.697401520017127,0.017638717765476115 +flat_mae,patch,logistic,ppmi_dx,85,0.005994842503189409,test,0.67,0.03786324867203023,0.6108031607500884,0.04786935245598305,0.6116298811544991,0.042185698131596755 +flat_mae,patch,logistic,ppmi_dx,86,0.005994842503189409,train,0.7437722419928826,0.016327691840920634,0.705759162303665,0.020033880052302937,0.6979768786127167,0.01853812698631521 +flat_mae,patch,logistic,ppmi_dx,86,0.005994842503189409,test,0.64,0.04300280921056204,0.5863970588235294,0.05161492374426305,0.5874363327674024,0.04673954697466903 +flat_mae,patch,logistic,ppmi_dx,87,0.005994842503189409,train,0.7508896797153025,0.016845194507837065,0.7139325189063409,0.021084804271376538,0.705496681652751,0.019608503803758486 +flat_mae,patch,logistic,ppmi_dx,87,0.005994842503189409,test,0.63,0.04578654387481108,0.5847828526540231,0.05332682482019128,0.5844651952461799,0.04970606859421351 +flat_mae,patch,logistic,ppmi_dx,88,0.005994842503189409,train,0.7419928825622776,0.016376062664023784,0.7041493158294093,0.0202838749064358,0.6965317919075145,0.018813418888950783 +flat_mae,patch,logistic,ppmi_dx,88,0.005994842503189409,test,0.64,0.038178004138508866,0.5628946090335114,0.04977002401318596,0.5721561969439728,0.041551715912595696 +flat_mae,patch,logistic,ppmi_dx,89,0.046415888336127774,train,0.8096085409252669,0.014547030680513016,0.7875746689133576,0.01710987938946336,0.7766672018839649,0.016918601488025542 +flat_mae,patch,logistic,ppmi_dx,89,0.046415888336127774,test,0.65,0.04545208906090016,0.6178622120318812,0.05108581347447792,0.615874363327674,0.049556458656441954 +flat_mae,patch,logistic,ppmi_dx,90,0.046415888336127774,train,0.8202846975088968,0.014741259965845218,0.8024178249322097,0.016729053486857413,0.7931652751016913,0.016730346435966718 +flat_mae,patch,logistic,ppmi_dx,90,0.046415888336127774,test,0.66,0.043462167456306176,0.6263736263736264,0.04815635025427291,0.6239388794567062,0.046350402552602074 +flat_mae,patch,logistic,ppmi_dx,91,0.046415888336127774,train,0.8096085409252669,0.016044988659179166,0.7891655184261919,0.018566983931543036,0.7792763862128024,0.018433638568590316 +flat_mae,patch,logistic,ppmi_dx,91,0.046415888336127774,test,0.66,0.044835142466596443,0.6310763888888888,0.04824487264128342,0.6290322580645161,0.047126372795299465 +flat_mae,patch,logistic,ppmi_dx,92,0.3593813663804626,train,0.9306049822064056,0.010717582145214682,0.9250500111135808,0.011851433116842601,0.9166800470991223,0.013026056584150845 +flat_mae,patch,logistic,ppmi_dx,92,0.3593813663804626,test,0.62,0.045921232561855305,0.5824175824175825,0.05099423645410384,0.5814940577249575,0.04906597349122452 +flat_mae,patch,logistic,ppmi_dx,93,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,93,21.54434690031882,test,0.59,0.04571907260651729,0.5849782366636299,0.04582313202686858,0.5980475382003396,0.04803070730544548 +flat_mae,patch,logistic,ppmi_dx,94,0.3593813663804626,train,0.9199288256227758,0.011167600002982881,0.9143858223734322,0.012074019105362963,0.9097489830871334,0.012719145795074811 +flat_mae,patch,logistic,ppmi_dx,94,0.3593813663804626,test,0.66,0.04198885090116184,0.6212121212121212,0.04862045024776411,0.6188455008488964,0.04604989154922895 +flat_mae,patch,logistic,ppmi_dx,95,0.046415888336127774,train,0.8185053380782918,0.015038936643916829,0.8002258280361325,0.01720018374812566,0.7908504602868764,0.017295513827621373 +flat_mae,patch,logistic,ppmi_dx,95,0.046415888336127774,test,0.6,0.04201534957607755,0.5404411764705883,0.04946123139622325,0.5449915110356536,0.04486466386809645 +flat_mae,patch,logistic,ppmi_dx,96,0.005994842503189409,train,0.7455516014234875,0.01597708779805971,0.7073716023085186,0.019999731154787346,0.699421965317919,0.018489633162926473 +flat_mae,patch,logistic,ppmi_dx,96,0.005994842503189409,test,0.58,0.04225304249400272,0.5174632352941176,0.04734419022414805,0.5237691001697793,0.04353846128240357 +flat_mae,patch,logistic,ppmi_dx,97,0.005994842503189409,train,0.7419928825622776,0.015650030134757062,0.6987152232184121,0.01989322254811252,0.6913134232498395,0.018046018824887298 +flat_mae,patch,logistic,ppmi_dx,97,0.005994842503189409,test,0.72,0.04140668545054048,0.6783088235294117,0.0514083434984532,0.6723259762308998,0.0474553455437808 +flat_mae,patch,logistic,ppmi_dx,98,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,98,1291.5496650148827,test,0.51,0.04801984589729542,0.4873940788785438,0.04987226657516899,0.4876910016977929,0.050343224613628564 +flat_mae,patch,logistic,ppmi_dx,99,0.3593813663804626,train,0.9199288256227758,0.011737016821179055,0.914218554435094,0.012771762749616328,0.9088792549775209,0.013534718578854202 +flat_mae,patch,logistic,ppmi_dx,99,0.3593813663804626,test,0.61,0.04875791628033339,0.5882166613873931,0.050990641383141334,0.5887096774193548,0.050960795724783264 +flat_mae,patch,logistic,ppmi_dx,100,0.046415888336127774,train,0.797153024911032,0.01544785545449208,0.7772477574577568,0.017616787914200786,0.7691607792763862,0.01758889503104306 +flat_mae,patch,logistic,ppmi_dx,100,0.046415888336127774,test,0.65,0.046653184242878856,0.630450849963045,0.049670500142160845,0.6311544991511036,0.05009981432116296 diff --git a/input_space_v3/flat_lr1e-3_3/eval_v2/ppmi_dx__patch__logistic/log.txt b/input_space_v3/flat_lr1e-3_3/eval_v2/ppmi_dx__patch__logistic/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..2562052fec09769fe19ed494c4b333fd43211fa9 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_3/eval_v2/ppmi_dx__patch__logistic/log.txt @@ -0,0 +1,247 @@ +fMRI foundation model logistic probe eval +version: 0.1.dev86+gf97f52698 +sha: bcce2b486277d3a5b520775efd9cdf1a2affce36, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-04-08 22:16:02 +config: +output_root: experiments/input_space_v3/output +name_prefix: eval_logistic +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_3; eval v2 (ppmi_dx patch logistic) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: input_space_v3/flat_lr1e-3_3/eval_v2/ppmi_dx__patch__logistic +model: flat_mae +representation: patch +dataset: ppmi_dx +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/eval_v2/ppmi_dx__patch__logistic +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=True, reg_tokens=0, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: ppmi_dx (flat) +train (n=463): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'dir', 'sex', 'age', 'age_bin', 'dx', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 463 +}), + labels=['PD' 'Prodromal'], + counts=[178 285] +) + +validation (n=99): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'dir', 'sex', 'age', 'age_bin', 'dx', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 99 +}), + labels=['PD' 'Prodromal'], + counts=[39 60] +) + +test (n=100): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'dir', 'sex', 'age', 'age_bin', 'dx', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 100 +}), + labels=['PD' 'Prodromal'], + counts=[37 63] +) + +extracting features for all splits +extract (train) [ 0/232] eta: 0:18:50 time: 4.8709 data: 3.6974 max mem: 2698 +extract (train) [ 20/232] eta: 0:01:29 time: 0.2007 data: 0.0729 max mem: 2851 +extract (train) [ 40/232] eta: 0:00:58 time: 0.1794 data: 0.0594 max mem: 2851 +extract (train) [ 60/232] eta: 0:00:45 time: 0.1869 data: 0.0637 max mem: 2851 +extract (train) [ 80/232] eta: 0:00:37 time: 0.1799 data: 0.0620 max mem: 2851 +extract (train) [100/232] eta: 0:00:30 time: 0.1856 data: 0.0638 max mem: 2851 +extract (train) [120/232] eta: 0:00:25 time: 0.1865 data: 0.0584 max mem: 2851 +extract (train) [140/232] eta: 0:00:20 time: 0.1890 data: 0.0692 max mem: 2851 +extract (train) [160/232] eta: 0:00:15 time: 0.1889 data: 0.0650 max mem: 2851 +extract (train) [180/232] eta: 0:00:11 time: 0.2033 data: 0.0715 max mem: 2851 +extract (train) [200/232] eta: 0:00:06 time: 0.2197 data: 0.0790 max mem: 2851 +extract (train) [220/232] eta: 0:00:02 time: 0.1761 data: 0.0571 max mem: 2851 +extract (train) [231/232] eta: 0:00:00 time: 0.1672 data: 0.0535 max mem: 2851 +extract (train) Total time: 0:00:49 (0.2115 s / it) +extract (validation) [ 0/50] eta: 0:03:40 time: 4.4000 data: 4.1353 max mem: 2851 +extract (validation) [20/50] eta: 0:00:13 time: 0.2563 data: 0.0849 max mem: 2851 +extract (validation) [40/50] eta: 0:00:03 time: 0.1704 data: 0.0493 max mem: 2851 +extract (validation) [49/50] eta: 0:00:00 time: 0.1788 data: 0.0602 max mem: 2851 +extract (validation) Total time: 0:00:14 (0.2995 s / it) +extract (test) [ 0/50] eta: 0:03:46 time: 4.5373 data: 4.2361 max mem: 2851 +extract (test) [20/50] eta: 0:00:14 time: 0.2654 data: 0.0984 max mem: 2851 +extract (test) [40/50] eta: 0:00:03 time: 0.1688 data: 0.0546 max mem: 2851 +extract (test) [49/50] eta: 0:00:00 time: 0.1730 data: 0.0589 max mem: 2851 +extract (test) Total time: 0:00:15 (0.3058 s / it) +feature extraction time: 0:01:19 +train features: (463, 768) +validation features: (99, 768) +test features: (100, 768) +evaluating fixed splits +eval results (fixed splits): + +| model | repr | clf | dataset | trial | C | split | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|--------:|:--------|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | ppmi_dx | | 0.35938 | train | 0.92171 | 0.011837 | 0.91604 | 0.0129 | 0.90973 | 0.013638 | +| flat_mae | patch | logistic | ppmi_dx | | 0.35938 | test | 0.69 | 0.044599 | 0.65212 | 0.050508 | 0.64801 | 0.048419 | + + +evaluating random splits (n=100) +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 1, "C": 0.005994842503189409, "split": "test", "acc": 0.67, "acc_std": 0.04304172394316937, "f1": 0.6176572818908586, "f1_std": 0.05261837286469396, "bacc": 0.616723259762309, "bacc_std": 0.04750418212707875} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 2, "C": 0.046415888336127774, "split": "test", "acc": 0.68, "acc_std": 0.04614853843839477, "f1": 0.6567996567996568, "f1_std": 0.049125936970562153, "bacc": 0.6553480475382003, "bacc_std": 0.04840618253889528} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 3, "C": 0.005994842503189409, "split": "test", "acc": 0.62, "acc_std": 0.04372872739973118, "f1": 0.5703301673450927, "f1_std": 0.05167280500577023, "bacc": 0.5713073005093379, "bacc_std": 0.04755213796410491} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 4, "C": 0.046415888336127774, "split": "test", "acc": 0.69, "acc_std": 0.04282793013910431, "f1": 0.6570417081535569, "f1_std": 0.04883218569715067, "bacc": 0.6532258064516129, "bacc_std": 0.04711503945227294} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 5, "C": 0.3593813663804626, "split": "test", "acc": 0.62, "acc_std": 0.04718665489309451, "f1": 0.5876736111111112, "f1_std": 0.051184735759030695, "bacc": 0.5865874363327674, "bacc_std": 0.049753308745394784} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 6, "C": 0.046415888336127774, "split": "test", "acc": 0.65, "acc_std": 0.04462456274295581, "f1": 0.6224786970121885, "f1_std": 0.049020523365380445, "bacc": 0.6209677419354839, "bacc_std": 0.04810812179177235} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 7, "C": 0.3593813663804626, "split": "test", "acc": 0.6, "acc_std": 0.04883580244042275, "f1": 0.5755517826825127, "f1_std": 0.05121325029895319, "bacc": 0.5755517826825127, "bacc_std": 0.051020101868826405} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 8, "C": 0.3593813663804626, "split": "test", "acc": 0.54, "acc_std": 0.047691659648202635, "f1": 0.5166036149642708, "f1_std": 0.048755878717169465, "bacc": 0.5169779286926994, "bacc_std": 0.0489214682840002} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 9, "C": 0.005994842503189409, "split": "test", "acc": 0.7, "acc_std": 0.03672729774976645, "f1": 0.6357455075279261, "f1_std": 0.050024815323777665, "bacc": 0.6358234295415959, "bacc_std": 0.04236858140888164} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 10, "C": 0.3593813663804626, "split": "test", "acc": 0.64, "acc_std": 0.045514551519266894, "f1": 0.6216897856242118, "f1_std": 0.04734701094260005, "bacc": 0.6230899830220713, "bacc_std": 0.04777408581845406} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 11, "C": 0.3593813663804626, "split": "test", "acc": 0.61, "acc_std": 0.05201162946880245, "f1": 0.5793334052421529, "f1_std": 0.05627745777013522, "bacc": 0.5785229202037352, "bacc_std": 0.05528542386157481} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 12, "C": 0.046415888336127774, "split": "test", "acc": 0.61, "acc_std": 0.040596921065519244, "f1": 0.5311936530833032, "f1_std": 0.04927403398026479, "bacc": 0.5428692699490663, "bacc_std": 0.04254045778343916} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 13, "C": 0.046415888336127774, "split": "test", "acc": 0.6, "acc_std": 0.04699649348621661, "f1": 0.570999570999571, "f1_std": 0.04967337414655429, "bacc": 0.5704584040747029, "bacc_std": 0.048939672067760134} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 14, "C": 0.005994842503189409, "split": "test", "acc": 0.63, "acc_std": 0.04357496528971653, "f1": 0.5636277862955537, "f1_std": 0.05372977004006386, "bacc": 0.5691850594227504, "bacc_std": 0.046908008955386125} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 15, "C": 0.005994842503189409, "split": "test", "acc": 0.69, "acc_std": 0.04282679535057461, "f1": 0.6408295678368672, "f1_std": 0.053170719343802866, "bacc": 0.6379456706281834, "bacc_std": 0.04808563326883216} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 16, "C": 0.046415888336127774, "split": "test", "acc": 0.6, "acc_std": 0.0447986562298469, "f1": 0.5659722222222222, "f1_std": 0.04826623031932172, "bacc": 0.565365025466893, "bacc_std": 0.047010022666281605} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 17, "C": 0.005994842503189409, "split": "test", "acc": 0.7, "acc_std": 0.04011411721576332, "f1": 0.6493688639551192, "f1_std": 0.050429278197408535, "bacc": 0.6460101867572157, "bacc_std": 0.04501853517769544} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 18, "C": 0.005994842503189409, "split": "test", "acc": 0.62, "acc_std": 0.042627990804165294, "f1": 0.5703301673450927, "f1_std": 0.048983573314206, "bacc": 0.5713073005093379, "bacc_std": 0.04525683358841364} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 19, "C": 0.046415888336127774, "split": "test", "acc": 0.65, "acc_std": 0.044524415773820096, "f1": 0.6266666666666667, "f1_std": 0.047462621844499474, "bacc": 0.6260611205432938, "bacc_std": 0.047335711082041446} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 20, "C": 0.046415888336127774, "split": "test", "acc": 0.7, "acc_std": 0.03931177431762651, "f1": 0.6493688639551192, "f1_std": 0.0494004257932938, "bacc": 0.6460101867572157, "bacc_std": 0.04397233720735772} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 21, "C": 0.046415888336127774, "split": "test", "acc": 0.67, "acc_std": 0.04150243848257593, "f1": 0.6108031607500884, "f1_std": 0.05296131715022752, "bacc": 0.6116298811544991, "bacc_std": 0.046249221973426936} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 22, "C": 0.3593813663804626, "split": "test", "acc": 0.62, "acc_std": 0.03996298287165261, "f1": 0.5634191176470589, "f1_std": 0.04712754090395979, "bacc": 0.566213921901528, "bacc_std": 0.0429102224672043} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 23, "C": 0.046415888336127774, "split": "test", "acc": 0.65, "acc_std": 0.04574962732088644, "f1": 0.612789025334661, "f1_std": 0.05172860033673028, "bacc": 0.6107809847198642, "bacc_std": 0.04950343624366135} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 24, "C": 0.005994842503189409, "split": "test", "acc": 0.62, "acc_std": 0.04510301098596413, "f1": 0.5634191176470589, "f1_std": 0.05300360564676334, "bacc": 0.566213921901528, "bacc_std": 0.048241511720928186} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 25, "C": 0.046415888336127774, "split": "test", "acc": 0.66, "acc_std": 0.042225352574016474, "f1": 0.6155585707824514, "f1_std": 0.04913753013991262, "bacc": 0.6137521222410866, "bacc_std": 0.04586751078115734} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 26, "C": 0.005994842503189409, "split": "test", "acc": 0.64, "acc_std": 0.0469522097456552, "f1": 0.6043956043956044, "f1_std": 0.05213543823006843, "bacc": 0.6027164685908319, "bacc_std": 0.050082068486917854} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 27, "C": 0.005994842503189409, "split": "test", "acc": 0.69, "acc_std": 0.04135552683741315, "f1": 0.6408295678368672, "f1_std": 0.050638764189146056, "bacc": 0.6379456706281834, "bacc_std": 0.0459280575211758} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 28, "C": 0.3593813663804626, "split": "test", "acc": 0.69, "acc_std": 0.04698286921847152, "f1": 0.6756982948007113, "f1_std": 0.04832736498958284, "bacc": 0.6786926994906621, "bacc_std": 0.04864509316849883} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 29, "C": 0.046415888336127774, "split": "test", "acc": 0.67, "acc_std": 0.04429401765475784, "f1": 0.6396986570586308, "f1_std": 0.04853173029425262, "bacc": 0.6370967741935484, "bacc_std": 0.04733558034824792} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 30, "C": 0.046415888336127774, "split": "test", "acc": 0.7, "acc_std": 0.04239627813853475, "f1": 0.6493688639551192, "f1_std": 0.053662298182253675, "bacc": 0.6460101867572157, "bacc_std": 0.04814321988797351} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 31, "C": 166.81005372000556, "split": "test", "acc": 0.66, "acc_std": 0.04894311391809883, "f1": 0.6486151302190988, "f1_std": 0.0499258344034549, "bacc": 0.6544991511035654, "bacc_std": 0.0508356658954075} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 32, "C": 0.3593813663804626, "split": "test", "acc": 0.61, "acc_std": 0.04507219098291096, "f1": 0.568536342515765, "f1_std": 0.05029184264582976, "bacc": 0.5683361629881154, "bacc_std": 0.04786662638939085} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 33, "C": 0.046415888336127774, "split": "test", "acc": 0.59, "acc_std": 0.04810725932746533, "f1": 0.5626666666666666, "f1_std": 0.050136174257836036, "bacc": 0.5623938879456706, "bacc_std": 0.04944208505590077} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 34, "C": 0.005994842503189409, "split": "test", "acc": 0.65, "acc_std": 0.04683135274578346, "f1": 0.612789025334661, "f1_std": 0.05230902992333402, "bacc": 0.6107809847198642, "bacc_std": 0.05024652559721942} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 35, "C": 0.005994842503189409, "split": "test", "acc": 0.67, "acc_std": 0.043568699774035026, "f1": 0.6349153667441089, "f1_std": 0.04892081575306327, "bacc": 0.6320033955857385, "bacc_std": 0.04681768313216853} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 36, "C": 0.046415888336127774, "split": "test", "acc": 0.69, "acc_std": 0.0418209277754571, "f1": 0.6408295678368672, "f1_std": 0.05121051200267609, "bacc": 0.6379456706281834, "bacc_std": 0.04644763864286007} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 37, "C": 0.046415888336127774, "split": "test", "acc": 0.64, "acc_std": 0.04781725211678312, "f1": 0.625, "f1_std": 0.049387992273371276, "bacc": 0.6281833616298811, "bacc_std": 0.05029900088871264} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 38, "C": 21.54434690031882, "split": "test", "acc": 0.64, "acc_std": 0.045855647416648694, "f1": 0.625, "f1_std": 0.046893456482992875, "bacc": 0.6281833616298811, "bacc_std": 0.047699440618164946} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 39, "C": 0.046415888336127774, "split": "test", "acc": 0.69, "acc_std": 0.04413895784904758, "f1": 0.6570417081535569, "f1_std": 0.05024110006867244, "bacc": 0.6532258064516129, "bacc_std": 0.0482419208000771} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 40, "C": 0.005994842503189409, "split": "test", "acc": 0.68, "acc_std": 0.04190429094973448, "f1": 0.6381727725011307, "f1_std": 0.04904306658826965, "bacc": 0.634974533106961, "bacc_std": 0.04564584962220806} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 41, "C": 0.046415888336127774, "split": "test", "acc": 0.7, "acc_std": 0.0457889899429983, "f1": 0.6816638370118846, "f1_std": 0.04824415852950108, "bacc": 0.6816638370118846, "bacc_std": 0.048244587232060224} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 42, "C": 0.046415888336127774, "split": "test", "acc": 0.68, "acc_std": 0.04156766050669678, "f1": 0.6381727725011307, "f1_std": 0.04791900121636441, "bacc": 0.634974533106961, "bacc_std": 0.0450474879697533} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 43, "C": 0.005994842503189409, "split": "test", "acc": 0.71, "acc_std": 0.040965834545386715, "f1": 0.6640018537828757, "f1_std": 0.05139877669273814, "bacc": 0.6591680814940577, "bacc_std": 0.04682162920723183} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 44, "C": 0.005994842503189409, "split": "test", "acc": 0.67, "acc_std": 0.03918838603464041, "f1": 0.6108031607500884, "f1_std": 0.05011717965725812, "bacc": 0.6116298811544991, "bacc_std": 0.04419755230312127} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 45, "C": 0.3593813663804626, "split": "test", "acc": 0.66, "acc_std": 0.04680281615458625, "f1": 0.6486151302190988, "f1_std": 0.04778701933043274, "bacc": 0.6544991511035654, "bacc_std": 0.04874793442096206} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 46, "C": 0.046415888336127774, "split": "test", "acc": 0.63, "acc_std": 0.04533136221204918, "f1": 0.5906626839252129, "f1_std": 0.05023005851427968, "bacc": 0.5895585738539898, "bacc_std": 0.04762381766026289} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 47, "C": 0.005994842503189409, "split": "test", "acc": 0.69, "acc_std": 0.043010747494085705, "f1": 0.6521153630344518, "f1_std": 0.05033248463630214, "bacc": 0.6481324278438031, "bacc_std": 0.047600048257335575} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 48, "C": 0.046415888336127774, "split": "test", "acc": 0.7, "acc_std": 0.04157412175861325, "f1": 0.6782496782496783, "f1_std": 0.045260929281968544, "bacc": 0.6765704584040747, "bacc_std": 0.045003909453856406} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 49, "C": 0.3593813663804626, "split": "test", "acc": 0.63, "acc_std": 0.04243682834520036, "f1": 0.5713127099988413, "f1_std": 0.052072817644025, "bacc": 0.5742784380305602, "bacc_std": 0.046483215005438186} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 50, "C": 2.782559402207126, "split": "test", "acc": 0.65, "acc_std": 0.04733056517727206, "f1": 0.6266666666666667, "f1_std": 0.050934146393898705, "bacc": 0.6260611205432938, "bacc_std": 0.0507071883648179} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 51, "C": 0.046415888336127774, "split": "test", "acc": 0.6, "acc_std": 0.04755955845043139, "f1": 0.5755517826825127, "f1_std": 0.049659850521193184, "bacc": 0.5755517826825127, "bacc_std": 0.04938874328744666} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 52, "C": 0.3593813663804626, "split": "test", "acc": 0.58, "acc_std": 0.048746757840906714, "f1": 0.5442708333333334, "f1_std": 0.052686901971222694, "bacc": 0.5441426146010186, "bacc_std": 0.05146871653508333} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 53, "C": 0.046415888336127774, "split": "test", "acc": 0.59, "acc_std": 0.047617387580588665, "f1": 0.5577607593571352, "f1_std": 0.05061339318514271, "bacc": 0.5573005093378608, "bacc_std": 0.049805240489823016} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 54, "C": 0.3593813663804626, "split": "test", "acc": 0.58, "acc_std": 0.04722136804456219, "f1": 0.5320855614973261, "f1_std": 0.05190647241191665, "bacc": 0.533955857385399, "bacc_std": 0.04922465547700165} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 55, "C": 0.005994842503189409, "split": "test", "acc": 0.71, "acc_std": 0.03986623132426741, "f1": 0.6695156695156695, "f1_std": 0.04849511615076751, "bacc": 0.6642614601018676, "bacc_std": 0.04479167378303506} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 56, "C": 0.005994842503189409, "split": "test", "acc": 0.65, "acc_std": 0.04706070972690488, "f1": 0.6011396011396011, "f1_std": 0.05496715744943529, "bacc": 0.6005942275042444, "bacc_std": 0.050541539035601796} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 57, "C": 0.046415888336127774, "split": "test", "acc": 0.65, "acc_std": 0.046605900913940075, "f1": 0.6178622120318812, "f1_std": 0.05112196602974902, "bacc": 0.615874363327674, "bacc_std": 0.04973875162194532} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 58, "C": 0.046415888336127774, "split": "test", "acc": 0.69, "acc_std": 0.04390181773002115, "f1": 0.6521153630344518, "f1_std": 0.051720656918915586, "bacc": 0.6481324278438031, "bacc_std": 0.04901402909291965} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 59, "C": 0.3593813663804626, "split": "test", "acc": 0.61, "acc_std": 0.0474021096576935, "f1": 0.5793334052421529, "f1_std": 0.05189098821916744, "bacc": 0.5785229202037352, "bacc_std": 0.05083541678020466} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 60, "C": 0.046415888336127774, "split": "test", "acc": 0.68, "acc_std": 0.04107212680151832, "f1": 0.6323529411764706, "f1_std": 0.050915076992490683, "bacc": 0.6298811544991512, "bacc_std": 0.04623332994672404} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 61, "C": 0.005994842503189409, "split": "test", "acc": 0.7, "acc_std": 0.04020895422663961, "f1": 0.6553308823529411, "f1_std": 0.04915556246143496, "bacc": 0.6511035653650254, "bacc_std": 0.04498928716033764} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 62, "C": 0.005994842503189409, "split": "test", "acc": 0.63, "acc_std": 0.0398369476742383, "f1": 0.5636277862955537, "f1_std": 0.0499220432480929, "bacc": 0.5691850594227504, "bacc_std": 0.04326987592103045} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 63, "C": 2.782559402207126, "split": "test", "acc": 0.67, "acc_std": 0.047195440457739136, "f1": 0.648, "f1_std": 0.05022082452466916, "bacc": 0.6472835314091681, "bacc_std": 0.04972622899958616} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 64, "C": 0.046415888336127774, "split": "test", "acc": 0.63, "acc_std": 0.0434699896480319, "f1": 0.5783475783475784, "f1_std": 0.051884169243076025, "bacc": 0.5793718166383701, "bacc_std": 0.04738118992875794} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 65, "C": 0.046415888336127774, "split": "test", "acc": 0.62, "acc_std": 0.047217556057043024, "f1": 0.5876736111111112, "f1_std": 0.05028877949028039, "bacc": 0.5865874363327674, "bacc_std": 0.0490854170774758} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 66, "C": 0.046415888336127774, "split": "test", "acc": 0.61, "acc_std": 0.04920762136092335, "f1": 0.5741893219783819, "f1_std": 0.05305301820472493, "bacc": 0.5734295415959253, "bacc_std": 0.05125784468575636} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 67, "C": 0.046415888336127774, "split": "test", "acc": 0.65, "acc_std": 0.04502910614258293, "f1": 0.6178622120318812, "f1_std": 0.04946250005344651, "bacc": 0.615874363327674, "bacc_std": 0.04812125371472414} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 68, "C": 0.005994842503189409, "split": "test", "acc": 0.72, "acc_std": 0.03969573780646986, "f1": 0.6783088235294117, "f1_std": 0.048842510220025566, "bacc": 0.6723259762308998, "bacc_std": 0.045164421516928635} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 69, "C": 0.046415888336127774, "split": "test", "acc": 0.69, "acc_std": 0.04167788862214591, "f1": 0.6408295678368672, "f1_std": 0.05143210147657819, "bacc": 0.6379456706281834, "bacc_std": 0.04664760026662357} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 70, "C": 0.005994842503189409, "split": "test", "acc": 0.62, "acc_std": 0.04648889759931935, "f1": 0.5634191176470589, "f1_std": 0.05381878472937171, "bacc": 0.566213921901528, "bacc_std": 0.049170329171532676} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 71, "C": 0.005994842503189409, "split": "test", "acc": 0.67, "acc_std": 0.04354784035976984, "f1": 0.6033177064551027, "f1_std": 0.056466843593592615, "bacc": 0.6065365025466893, "bacc_std": 0.048514450074042696} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 72, "C": 0.005994842503189409, "split": "test", "acc": 0.67, "acc_std": 0.0471180474977476, "f1": 0.6440513428972063, "f1_std": 0.0509022624226613, "bacc": 0.6421901528013583, "bacc_std": 0.050120404806171096} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 73, "C": 0.005994842503189409, "split": "test", "acc": 0.64, "acc_std": 0.04552702933423177, "f1": 0.609375, "f1_std": 0.050259694046708187, "bacc": 0.6078098471986417, "bacc_std": 0.04920490793197611} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 74, "C": 0.005994842503189409, "split": "test", "acc": 0.61, "acc_std": 0.04435628027686723, "f1": 0.5555555555555556, "f1_std": 0.051762751282332854, "bacc": 0.5581494057724957, "bacc_std": 0.047611989625702095} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 75, "C": 0.005994842503189409, "split": "test", "acc": 0.66, "acc_std": 0.04361926180026434, "f1": 0.6155585707824514, "f1_std": 0.050873713259636084, "bacc": 0.6137521222410866, "bacc_std": 0.04750590553532694} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 76, "C": 0.005994842503189409, "split": "test", "acc": 0.72, "acc_std": 0.04320601809933427, "f1": 0.6880570409982174, "f1_std": 0.050228806965840006, "bacc": 0.6825127334465195, "bacc_std": 0.048073824272208014} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 77, "C": 0.046415888336127774, "split": "test", "acc": 0.64, "acc_std": 0.04506706114225777, "f1": 0.6043956043956044, "f1_std": 0.05083841690190432, "bacc": 0.6027164685908319, "bacc_std": 0.04880919648886307} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 78, "C": 0.046415888336127774, "split": "test", "acc": 0.58, "acc_std": 0.045636349547263304, "f1": 0.5091164095371669, "f1_std": 0.05206360287766519, "bacc": 0.5186757215619694, "bacc_std": 0.047037385446461875} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 79, "C": 0.005994842503189409, "split": "test", "acc": 0.69, "acc_std": 0.04143592161398126, "f1": 0.6408295678368672, "f1_std": 0.05067071699814611, "bacc": 0.6379456706281834, "bacc_std": 0.046088849574886036} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 80, "C": 0.046415888336127774, "split": "test", "acc": 0.65, "acc_std": 0.04614000866926663, "f1": 0.6072270227808326, "f1_std": 0.05294847330705651, "bacc": 0.6056876061120543, "bacc_std": 0.04977212159655057} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 81, "C": 0.046415888336127774, "split": "test", "acc": 0.67, "acc_std": 0.0426543081059815, "f1": 0.648, "f1_std": 0.04540251355128882, "bacc": 0.6472835314091681, "bacc_std": 0.045326291461740914} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 82, "C": 0.046415888336127774, "split": "test", "acc": 0.65, "acc_std": 0.04634360365789437, "f1": 0.6178622120318812, "f1_std": 0.05163327164311699, "bacc": 0.615874363327674, "bacc_std": 0.05016623531359643} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 83, "C": 0.005994842503189409, "split": "test", "acc": 0.56, "acc_std": 0.046858403728680297, "f1": 0.5098039215686274, "f1_std": 0.0499789639512692, "bacc": 0.5127334465195246, "bacc_std": 0.04765680598195394} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 84, "C": 0.046415888336127774, "split": "test", "acc": 0.65, "acc_std": 0.045282804683455725, "f1": 0.6178622120318812, "f1_std": 0.04993877101521104, "bacc": 0.615874363327674, "bacc_std": 0.048652836032145035} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 85, "C": 0.005994842503189409, "split": "test", "acc": 0.67, "acc_std": 0.03786324867203023, "f1": 0.6108031607500884, "f1_std": 0.04786935245598305, "bacc": 0.6116298811544991, "bacc_std": 0.042185698131596755} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 86, "C": 0.005994842503189409, "split": "test", "acc": 0.64, "acc_std": 0.04300280921056204, "f1": 0.5863970588235294, "f1_std": 0.05161492374426305, "bacc": 0.5874363327674024, "bacc_std": 0.04673954697466903} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 87, "C": 0.005994842503189409, "split": "test", "acc": 0.63, "acc_std": 0.04578654387481108, "f1": 0.5847828526540231, "f1_std": 0.05332682482019128, "bacc": 0.5844651952461799, "bacc_std": 0.04970606859421351} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 88, "C": 0.005994842503189409, "split": "test", "acc": 0.64, "acc_std": 0.038178004138508866, "f1": 0.5628946090335114, "f1_std": 0.04977002401318596, "bacc": 0.5721561969439728, "bacc_std": 0.041551715912595696} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 89, "C": 0.046415888336127774, "split": "test", "acc": 0.65, "acc_std": 0.04545208906090016, "f1": 0.6178622120318812, "f1_std": 0.05108581347447792, "bacc": 0.615874363327674, "bacc_std": 0.049556458656441954} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 90, "C": 0.046415888336127774, "split": "test", "acc": 0.66, "acc_std": 0.043462167456306176, "f1": 0.6263736263736264, "f1_std": 0.04815635025427291, "bacc": 0.6239388794567062, "bacc_std": 0.046350402552602074} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 91, "C": 0.046415888336127774, "split": "test", "acc": 0.66, "acc_std": 0.044835142466596443, "f1": 0.6310763888888888, "f1_std": 0.04824487264128342, "bacc": 0.6290322580645161, "bacc_std": 0.047126372795299465} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 92, "C": 0.3593813663804626, "split": "test", "acc": 0.62, "acc_std": 0.045921232561855305, "f1": 0.5824175824175825, "f1_std": 0.05099423645410384, "bacc": 0.5814940577249575, "bacc_std": 0.04906597349122452} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 93, "C": 21.54434690031882, "split": "test", "acc": 0.59, "acc_std": 0.04571907260651729, "f1": 0.5849782366636299, "f1_std": 0.04582313202686858, "bacc": 0.5980475382003396, "bacc_std": 0.04803070730544548} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 94, "C": 0.3593813663804626, "split": "test", "acc": 0.66, "acc_std": 0.04198885090116184, "f1": 0.6212121212121212, "f1_std": 0.04862045024776411, "bacc": 0.6188455008488964, "bacc_std": 0.04604989154922895} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 95, "C": 0.046415888336127774, "split": "test", "acc": 0.6, "acc_std": 0.04201534957607755, "f1": 0.5404411764705883, "f1_std": 0.04946123139622325, "bacc": 0.5449915110356536, "bacc_std": 0.04486466386809645} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 96, "C": 0.005994842503189409, "split": "test", "acc": 0.58, "acc_std": 0.04225304249400272, "f1": 0.5174632352941176, "f1_std": 0.04734419022414805, "bacc": 0.5237691001697793, "bacc_std": 0.04353846128240357} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 97, "C": 0.005994842503189409, "split": "test", "acc": 0.72, "acc_std": 0.04140668545054048, "f1": 0.6783088235294117, "f1_std": 0.0514083434984532, "bacc": 0.6723259762308998, "bacc_std": 0.0474553455437808} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 98, "C": 1291.5496650148827, "split": "test", "acc": 0.51, "acc_std": 0.04801984589729542, "f1": 0.4873940788785438, "f1_std": 0.04987226657516899, "bacc": 0.4876910016977929, "bacc_std": 0.050343224613628564} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 99, "C": 0.3593813663804626, "split": "test", "acc": 0.61, "acc_std": 0.04875791628033339, "f1": 0.5882166613873931, "f1_std": 0.050990641383141334, "bacc": 0.5887096774193548, "bacc_std": 0.050960795724783264} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 100, "C": 0.046415888336127774, "split": "test", "acc": 0.65, "acc_std": 0.046653184242878856, "f1": 0.630450849963045, "f1_std": 0.049670500142160845, "bacc": 0.6311544991511036, "bacc_std": 0.05009981432116296} +eval results (random splits): + +| model | repr | clf | dataset | split | n_trials | C | C_std | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|-----------:|-------:|--------:|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | ppmi_dx | train | 100 | 15.149 | 130.03 | 0.81733 | 0.07696 | 0.79396 | 0.090139 | 0.78617 | 0.091577 | +| flat_mae | patch | logistic | ppmi_dx | test | 100 | 15.149 | 130.03 | 0.647 | 0.041084 | 0.60753 | 0.043485 | 0.60734 | 0.041527 | + + +done! total time: 0:05:40 diff --git a/input_space_v3/flat_lr1e-3_3/pretrain/config.yaml b/input_space_v3/flat_lr1e-3_3/pretrain/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..dd5da743b57207c21c928b7810acec2d99a019aa --- /dev/null +++ b/input_space_v3/flat_lr1e-3_3/pretrain/config.yaml @@ -0,0 +1,102 @@ +name: input_space_v3/flat_lr1e-3_3/pretrain +notes: input_space ablation v3 flat_lr1e-3_3; use tube masking and on-disk data (input_space=flat + base_lr=1e-3 seed=5403) +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain +input_space: flat +patch_size: 16 +num_frames: 16 +t_patch_size: 4 +mask_ratio: 0.9 +pred_mask_ratio: null +masking: tube +masking_kwargs: {} +mask_patch_size: null +model: mae_vit_base +model_kwargs: + decoding: attn + pos_embed: sep + target_norm: null + pca_norm_nc: 2 + t_pred_stride: 2 + no_decode_pos: true + mask_drop_scale: false + pred_edge_pad: 0 + gauss_sigma: null + class_token: true + reg_tokens: 0 + no_embed_class: true + head_init_scale: 0.0 + decoder_depth: 4 + drop_path_rate: 0.0 +datasets: + hcp-train: + type: wds + url: /data/fmri-datasets/pretrain/hcpya-all.${input_space}.wds/hcpya-all-${input_space}-{00000..01799}.tar + clipping: random + clipping_kwargs: + oversample: 4.0 + shuffle: true + buffer_size: 2000 + samples_per_epoch: 200000 + hcp-train-subset: + type: arrow + root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/validation + split_range: + - 0 + - 2000 + shuffle: false + hcp-val: + type: arrow + root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/test + split_range: + - 0 + - 2000 + shuffle: false +train_dataset: hcp-train +eval_datasets: +- hcp-train-subset +- hcp-val +val_dataset: null +clip_vmax: 3.0 +normalize: frame +tr_scale: null +crop_scale: null +crop_aspect: null +gray_jitter: null +num_workers: 16 +epochs: 100 +batch_size: 32 +accum_iter: 1 +base_lr: 0.001 +min_lr: 0.0 +warmup_epochs: 5 +weight_decay: 0.05 +betas: +- 0.9 +- 0.95 +clip_grad: 1.0 +amp: true +amp_dtype: float16 +ckpt: null +resume: true +auto_resume: true +start_epoch: 0 +max_checkpoints: 0 +checkpoint_period: null +plot_period: 5 +device: cuda +presend_cuda: false +seed: 5403 +debug: false +wandb: true +wandb_entity: null +wandb_project: fMRI-foundation-model +rank: 0 +world_size: 1 +gpu: 0 +distributed: true +dist_backend: nccl +in_chans: 1 +img_size: +- 224 +- 560 diff --git a/input_space_v3/flat_lr1e-3_3/pretrain/log.json b/input_space_v3/flat_lr1e-3_3/pretrain/log.json new file mode 100644 index 0000000000000000000000000000000000000000..24c279ddcb66729812177ddbbabb34dfc6b5e5f0 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_3/pretrain/log.json @@ -0,0 +1,100 @@ +{"epoch": 0, "train/lr": 1.2502400076802458e-05, "train/grad": 0.057663170993030075, "train/loss": 0.992888036108017, "eval/hcp-train-subset/loss": 0.9916725024100272, "eval/hcp-val/loss": 0.9904409608533306} +{"epoch": 1, "train/lr": 3.750320010240327e-05, "train/grad": 0.08431479340910912, "train/loss": 0.9881605464935302, "eval/hcp-train-subset/loss": 0.9888326967916181, "eval/hcp-val/loss": 0.9866220403102136} +{"epoch": 2, "train/lr": 6.250400012800409e-05, "train/grad": 0.11648405863594413, "train/loss": 0.984689339094162, "eval/hcp-train-subset/loss": 0.9835697460559106, "eval/hcp-val/loss": 0.9820809133591191} +{"epoch": 3, "train/lr": 8.75048001536049e-05, "train/grad": 0.19053553183301902, "train/loss": 0.9776757322502136, "eval/hcp-train-subset/loss": 0.9756705809024072, "eval/hcp-val/loss": 0.9731109248053643} +{"epoch": 4, "train/lr": 0.00011250559953918529, "train/grad": 0.21549053385386244, "train/loss": 0.948475979976654, "eval/hcp-train-subset/loss": 0.9247977743225713, "eval/hcp-val/loss": 0.9188321434682415} +{"epoch": 5, "train/lr": 0.00012498860637884563, "train/grad": 0.15432420259457547, "train/loss": 0.9022090183734894, "eval/hcp-train-subset/loss": 0.8845572913846662, "eval/hcp-val/loss": 0.8781649931784599} +{"epoch": 6, "train/lr": 0.0001249202705377922, "train/grad": 0.10598930655817636, "train/loss": 0.8730926077651977, "eval/hcp-train-subset/loss": 0.8709637234287877, "eval/hcp-val/loss": 0.8651409629852541} +{"epoch": 7, "train/lr": 0.0001247836790473516, "train/grad": 0.08312860818656422, "train/loss": 0.8627548583602905, "eval/hcp-train-subset/loss": 0.8637748668270726, "eval/hcp-val/loss": 0.8576825924458042} +{"epoch": 8, "train/lr": 0.000124578981268311, "train/grad": 0.0766359082823737, "train/loss": 0.8553035590839386, "eval/hcp-train-subset/loss": 0.8590201312495817, "eval/hcp-val/loss": 0.853122696761162} +{"epoch": 9, "train/lr": 0.00012430640103468907, "train/grad": 0.07038652947203528, "train/loss": 0.8533152300739288, "eval/hcp-train-subset/loss": 0.856645550458662, "eval/hcp-val/loss": 0.8510504653376918} +{"epoch": 10, "train/lr": 0.00012396623640896796, "train/grad": 0.06817760395206068, "train/loss": 0.8505075331974029, "eval/hcp-train-subset/loss": 0.8545708579401816, "eval/hcp-val/loss": 0.849102993165293} +{"epoch": 11, "train/lr": 0.0001235588593561712, "train/grad": 0.06725541553521931, "train/loss": 0.8478863467216492, "eval/hcp-train-subset/loss": 0.8525827892364994, "eval/hcp-val/loss": 0.846795137851469} +{"epoch": 12, "train/lr": 0.00012308471533712604, "train/grad": 0.06525515457829902, "train/loss": 0.8463749000549317, "eval/hcp-train-subset/loss": 0.8507350125620442, "eval/hcp-val/loss": 0.8456463727258867} +{"epoch": 13, "train/lr": 0.00012254432282135565, "train/grad": 0.06376872178186184, "train/loss": 0.8449851282691956, "eval/hcp-train-subset/loss": 0.849829662230707, "eval/hcp-val/loss": 0.8446831693572383} +{"epoch": 14, "train/lr": 0.00012193827272014171, "train/grad": 0.06399575045341853, "train/loss": 0.8440329052066803, "eval/hcp-train-subset/loss": 0.8497045520813234, "eval/hcp-val/loss": 0.8448183930689289} +{"epoch": 15, "train/lr": 0.00012126722774037197, "train/grad": 0.0646649010166972, "train/loss": 0.8417725370788575, "eval/hcp-train-subset/loss": 0.8481353425210522, "eval/hcp-val/loss": 0.8435188205011429} +{"epoch": 16, "train/lr": 0.00012053192165988122, "train/grad": 0.06380222598150391, "train/loss": 0.8405665182781219, "eval/hcp-train-subset/loss": 0.8480430620331918, "eval/hcp-val/loss": 0.8428491555875347} +{"epoch": 17, "train/lr": 0.00011973315852507104, "train/grad": 0.06366361862837924, "train/loss": 0.8404089340877533, "eval/hcp-train-subset/loss": 0.8475889948106581, "eval/hcp-val/loss": 0.8422352786987058} +{"epoch": 18, "train/lr": 0.00011887181177170142, "train/grad": 0.06370887460316184, "train/loss": 0.8395393246269226, "eval/hcp-train-subset/loss": 0.8465900325006054, "eval/hcp-val/loss": 0.8410551038480574} +{"epoch": 19, "train/lr": 0.00011794882326980209, "train/grad": 0.06418309861641477, "train/loss": 0.8378311490821838, "eval/hcp-train-subset/loss": 0.8463502853147445, "eval/hcp-val/loss": 0.8411965062541347} +{"epoch": 20, "train/lr": 0.00011696520229374954, "train/grad": 0.06478807604221792, "train/loss": 0.8373862478256225, "eval/hcp-train-subset/loss": 0.8466271604261091, "eval/hcp-val/loss": 0.8419510491432682} +{"epoch": 21, "train/lr": 0.00011592202441863837, "train/grad": 0.06494474316611278, "train/loss": 0.8375790552711487, "eval/hcp-train-subset/loss": 0.8463042378425598, "eval/hcp-val/loss": 0.8410786428759175} +{"epoch": 22, "train/lr": 0.00011482043034415979, "train/grad": 0.066092871049617, "train/loss": 0.8353107934379578, "eval/hcp-train-subset/loss": 0.8454144818167533, "eval/hcp-val/loss": 0.8411297894293263} +{"epoch": 23, "train/lr": 0.00011366162464726024, "train/grad": 0.067531870524238, "train/loss": 0.8348687470722198, "eval/hcp-train-subset/loss": 0.8448400641641309, "eval/hcp-val/loss": 0.8402906762015435} +{"epoch": 24, "train/lr": 0.0001124468744649569, "train/grad": 0.06925363638726668, "train/loss": 0.8317636639118194, "eval/hcp-train-subset/loss": 0.8439373085575719, "eval/hcp-val/loss": 0.8406059049790905} +{"epoch": 25, "train/lr": 0.0001111775081087387, "train/grad": 0.06786594826597508, "train/loss": 0.8337348464298249, "eval/hcp-train-subset/loss": 0.8438422574150947, "eval/hcp-val/loss": 0.8390617822447131} +{"epoch": 26, "train/lr": 0.0001098549136120796, "train/grad": 0.06989262432513446, "train/loss": 0.8321718486118317, "eval/hcp-train-subset/loss": 0.8435271699582377, "eval/hcp-val/loss": 0.8386021977470767} +{"epoch": 27, "train/lr": 0.00010848053721264312, "train/grad": 0.07013656080844918, "train/loss": 0.8296392954826355, "eval/hcp-train-subset/loss": 0.842915213877155, "eval/hcp-val/loss": 0.8392730730195199} +{"epoch": 28, "train/lr": 0.00010705588177084458, "train/grad": 0.07166669707299328, "train/loss": 0.8309507929039002, "eval/hcp-train-subset/loss": 0.8417398852686728, "eval/hcp-val/loss": 0.8395226770831693} +{"epoch": 29, "train/lr": 0.00010558250512649171, "train/grad": 0.07268179566259574, "train/loss": 0.8299539168167114, "eval/hcp-train-subset/loss": 0.8434371852105663, "eval/hcp-val/loss": 0.8394403659528301} +{"epoch": 30, "train/lr": 0.00010406201839531515, "train/grad": 0.0720942852107591, "train/loss": 0.8299167493247985, "eval/hcp-train-subset/loss": 0.8418546203644045, "eval/hcp-val/loss": 0.8382890224456787} +{"epoch": 31, "train/lr": 0.00010249608420723018, "train/grad": 0.07449437525581268, "train/loss": 0.8283167677593232, "eval/hcp-train-subset/loss": 0.842156647674499, "eval/hcp-val/loss": 0.8390527838660825} +{"epoch": 32, "train/lr": 0.00010088641488828097, "train/grad": 0.07491945920490616, "train/loss": 0.8279192007160187, "eval/hcp-train-subset/loss": 0.8419383600834878, "eval/hcp-val/loss": 0.8379020796668145} +{"epoch": 33, "train/lr": 9.923477058823526e-05, "train/grad": 0.07624718094608661, "train/loss": 0.82740446393013, "eval/hcp-train-subset/loss": 0.8426968051541236, "eval/hcp-val/loss": 0.8384645744677512} +{"epoch": 34, "train/lr": 9.754295735588547e-05, "train/grad": 0.07538381139001638, "train/loss": 0.8289342578220368, "eval/hcp-train-subset/loss": 0.8414301526161932, "eval/hcp-val/loss": 0.8377807592192004} +{"epoch": 35, "train/lr": 9.581282516416285e-05, "train/grad": 0.0793078128735657, "train/loss": 0.8254630466175079, "eval/hcp-train-subset/loss": 0.8422637783711956, "eval/hcp-val/loss": 0.8383458843154292} +{"epoch": 36, "train/lr": 9.404626588721676e-05, "train/grad": 0.07809510756589272, "train/loss": 0.8288264723491668, "eval/hcp-train-subset/loss": 0.8413222230249836, "eval/hcp-val/loss": 0.8376821346821324} +{"epoch": 37, "train/lr": 9.224521123168153e-05, "train/grad": 0.0793020318235295, "train/loss": 0.825801165189743, "eval/hcp-train-subset/loss": 0.8403466190061262, "eval/hcp-val/loss": 0.8374731473384365} +{"epoch": 38, "train/lr": 9.041163062437843e-05, "train/grad": 0.08040724803763193, "train/loss": 0.8228252223014831, "eval/hcp-train-subset/loss": 0.8411925992658061, "eval/hcp-val/loss": 0.8375134544987832} +{"epoch": 39, "train/lr": 8.85475290587822e-05, "train/grad": 0.07886539270538508, "train/loss": 0.8259341397857666, "eval/hcp-train-subset/loss": 0.8401572233246218, "eval/hcp-val/loss": 0.8364279558581691} +{"epoch": 40, "train/lr": 8.665494490258622e-05, "train/grad": 0.07904680997128484, "train/loss": 0.8257352266120911, "eval/hcp-train-subset/loss": 0.8403579352363464, "eval/hcp-val/loss": 0.8366355367245213} +{"epoch": 41, "train/lr": 8.473594766877838e-05, "train/grad": 0.0824744944065981, "train/loss": 0.822239191608429, "eval/hcp-train-subset/loss": 0.8385236686275851, "eval/hcp-val/loss": 0.8367891734646212} +{"epoch": 42, "train/lr": 8.279263575265999e-05, "train/grad": 0.0840076866201552, "train/loss": 0.8231129967403412, "eval/hcp-train-subset/loss": 0.8394104223097524, "eval/hcp-val/loss": 0.8367908491242316} +{"epoch": 43, "train/lr": 8.082713413727944e-05, "train/grad": 0.08636778035164165, "train/loss": 0.819701063785553, "eval/hcp-train-subset/loss": 0.8396567683066091, "eval/hcp-val/loss": 0.8379060299165787} +{"epoch": 44, "train/lr": 7.884159206979602e-05, "train/grad": 0.08606677536736988, "train/loss": 0.8225176060009003, "eval/hcp-train-subset/loss": 0.8399111926555634, "eval/hcp-val/loss": 0.8364391682609436} +{"epoch": 45, "train/lr": 7.683818071130916e-05, "train/grad": 0.08892598023606518, "train/loss": 0.8209498456287384, "eval/hcp-train-subset/loss": 0.8390660372472578, "eval/hcp-val/loss": 0.8356843888759613} +{"epoch": 46, "train/lr": 7.481909076272522e-05, "train/grad": 0.08874883070747903, "train/loss": 0.8199465424919128, "eval/hcp-train-subset/loss": 0.8396347482358256, "eval/hcp-val/loss": 0.8366585373878479} +{"epoch": 47, "train/lr": 7.278653006925963e-05, "train/grad": 0.0895397670128205, "train/loss": 0.8219107923316955, "eval/hcp-train-subset/loss": 0.8381077637595515, "eval/hcp-val/loss": 0.8361071453940484} +{"epoch": 48, "train/lr": 7.074272120618864e-05, "train/grad": 0.08974514025130698, "train/loss": 0.8205806045341492, "eval/hcp-train-subset/loss": 0.8377024617887312, "eval/hcp-val/loss": 0.8358184445288873} +{"epoch": 49, "train/lr": 6.868989904849677e-05, "train/grad": 0.09183195537772869, "train/loss": 0.8169673592185974, "eval/hcp-train-subset/loss": 0.8356773468755907, "eval/hcp-val/loss": 0.8355112537260978} +{"epoch": 50, "train/lr": 6.6630308327075e-05, "train/grad": 0.09228342966797849, "train/loss": 0.8182519322776795, "eval/hcp-train-subset/loss": 0.8374616753670477, "eval/hcp-val/loss": 0.8353849899384284} +{"epoch": 51, "train/lr": 6.456620117413798e-05, "train/grad": 0.09224766685070515, "train/loss": 0.8180080138969421, "eval/hcp-train-subset/loss": 0.8369311536512067, "eval/hcp-val/loss": 0.8351399206346081} +{"epoch": 52, "train/lr": 6.249983466055255e-05, "train/grad": 0.09224350305832207, "train/loss": 0.8199486435317993, "eval/hcp-train-subset/loss": 0.8359786454708346, "eval/hcp-val/loss": 0.8354689526942468} +{"epoch": 53, "train/lr": 6.0433468327763305e-05, "train/grad": 0.09743147468090306, "train/loss": 0.8153952337551117, "eval/hcp-train-subset/loss": 0.835812089904662, "eval/hcp-val/loss": 0.8344348159528547} +{"epoch": 54, "train/lr": 5.83693617170174e-05, "train/grad": 0.09762661544028932, "train/loss": 0.8170896362686157, "eval/hcp-train-subset/loss": 0.8350840345505746, "eval/hcp-val/loss": 0.8343056401898784} +{"epoch": 55, "train/lr": 5.6309771898588165e-05, "train/grad": 0.09753345752912412, "train/loss": 0.8173340476894378, "eval/hcp-train-subset/loss": 0.8350353125602968, "eval/hcp-val/loss": 0.8350347732343981} +{"epoch": 56, "train/lr": 5.4256951003704155e-05, "train/grad": 0.09976677077723412, "train/loss": 0.8172751941680908, "eval/hcp-train-subset/loss": 0.8343104018319037, "eval/hcp-val/loss": 0.8344275807180712} +{"epoch": 57, "train/lr": 5.221314376187425e-05, "train/grad": 0.10025256925310366, "train/loss": 0.8163463750171661, "eval/hcp-train-subset/loss": 0.8337565362453461, "eval/hcp-val/loss": 0.8346248144103635} +{"epoch": 58, "train/lr": 5.018058504631059e-05, "train/grad": 0.10230133993248247, "train/loss": 0.8153494595623016, "eval/hcp-train-subset/loss": 0.8350501819964378, "eval/hcp-val/loss": 0.8341864184025796} +{"epoch": 59, "train/lr": 4.816149743012713e-05, "train/grad": 0.10459126102539354, "train/loss": 0.813468591041565, "eval/hcp-train-subset/loss": 0.8319983415065273, "eval/hcp-val/loss": 0.8346539976135376} +{"epoch": 60, "train/lr": 4.615808875598772e-05, "train/grad": 0.10541750106094341, "train/loss": 0.8150587037849426, "eval/hcp-train-subset/loss": 0.8299781622425202, "eval/hcp-val/loss": 0.8337417446797893} +{"epoch": 61, "train/lr": 4.417254972186445e-05, "train/grad": 0.10537536592197853, "train/loss": 0.8152473581027985, "eval/hcp-train-subset/loss": 0.8310992631220049, "eval/hcp-val/loss": 0.8343176476417049} +{"epoch": 62, "train/lr": 4.220705148553925e-05, "train/grad": 0.104014526359106, "train/loss": 0.817360478029251, "eval/hcp-train-subset/loss": 0.8318170318680425, "eval/hcp-val/loss": 0.8333442547628956} +{"epoch": 63, "train/lr": 4.026374329047657e-05, "train/grad": 0.10741904891536079, "train/loss": 0.8143833387374878, "eval/hcp-train-subset/loss": 0.8299496423813605, "eval/hcp-val/loss": 0.8325638328829119} +{"epoch": 64, "train/lr": 3.834475011565652e-05, "train/grad": 0.10749498859591833, "train/loss": 0.8163919665145875, "eval/hcp-train-subset/loss": 0.8309286765513881, "eval/hcp-val/loss": 0.8331777761059422} +{"epoch": 65, "train/lr": 3.6452170351940815e-05, "train/grad": 0.1100508305745652, "train/loss": 0.8141084110355378, "eval/hcp-train-subset/loss": 0.8309567484163469, "eval/hcp-val/loss": 0.8321070959491115} +{"epoch": 66, "train/lr": 3.458807350751516e-05, "train/grad": 0.11262036886287438, "train/loss": 0.8123011817550659, "eval/hcp-train-subset/loss": 0.8309211673275116, "eval/hcp-val/loss": 0.8327557473413406} +{"epoch": 67, "train/lr": 3.2754497944910164e-05, "train/grad": 0.11345507427131983, "train/loss": 0.8134257115459442, "eval/hcp-train-subset/loss": 0.8294018276276127, "eval/hcp-val/loss": 0.8322096582381956} +{"epoch": 68, "train/lr": 3.0953448652083367e-05, "train/grad": 0.1144005067949489, "train/loss": 0.8152269368553161, "eval/hcp-train-subset/loss": 0.8310907204304973, "eval/hcp-val/loss": 0.8325220875201687} +{"epoch": 69, "train/lr": 2.9186895049993948e-05, "train/grad": 0.11546733764495482, "train/loss": 0.812412312412262, "eval/hcp-train-subset/loss": 0.8296299336418029, "eval/hcp-val/loss": 0.832570327866462} +{"epoch": 70, "train/lr": 2.7456768839068717e-05, "train/grad": 0.11711657836465472, "train/loss": 0.8124752880573273, "eval/hcp-train-subset/loss": 0.8299808425288047, "eval/hcp-val/loss": 0.8322174385670693} +{"epoch": 71, "train/lr": 2.5764961886919063e-05, "train/grad": 0.12044826203848966, "train/loss": 0.8096160152339935, "eval/hcp-train-subset/loss": 0.8281398473247406, "eval/hcp-val/loss": 0.8319092527512582} +{"epoch": 72, "train/lr": 2.411332415960724e-05, "train/grad": 0.12166487795649786, "train/loss": 0.81054305809021, "eval/hcp-train-subset/loss": 0.8278980966537229, "eval/hcp-val/loss": 0.8311586726096368} +{"epoch": 73, "train/lr": 2.2503661698739544e-05, "train/grad": 0.12156132072329522, "train/loss": 0.8128448574447632, "eval/hcp-train-subset/loss": 0.8292405143860848, "eval/hcp-val/loss": 0.8315522824564288} +{"epoch": 74, "train/lr": 2.0937734646583902e-05, "train/grad": 0.1234355170539229, "train/loss": 0.8107013354206085, "eval/hcp-train-subset/loss": 0.8252598816348661, "eval/hcp-val/loss": 0.8312870148689516} +{"epoch": 75, "train/lr": 1.9417255321381202e-05, "train/grad": 0.1232696954649169, "train/loss": 0.8140029505062103, "eval/hcp-train-subset/loss": 0.8257568334379504, "eval/hcp-val/loss": 0.8315077202935373} +{"epoch": 76, "train/lr": 1.7943886344950134e-05, "train/grad": 0.1281503325747982, "train/loss": 0.8109674677371979, "eval/hcp-train-subset/loss": 0.8245214425748394, "eval/hcp-val/loss": 0.8312980205781998} +{"epoch": 77, "train/lr": 1.651923882463461e-05, "train/grad": 0.12782763470102593, "train/loss": 0.8113340941905975, "eval/hcp-train-subset/loss": 0.824443434515307, "eval/hcp-val/loss": 0.8304367690317093} +{"epoch": 78, "train/lr": 1.5144870591581508e-05, "train/grad": 0.13048017899637646, "train/loss": 0.8100881939601898, "eval/hcp-train-subset/loss": 0.82374950954991, "eval/hcp-val/loss": 0.8302141408766469} +{"epoch": 79, "train/lr": 1.3822284497275662e-05, "train/grad": 0.13186553447060365, "train/loss": 0.8123195531463623, "eval/hcp-train-subset/loss": 0.8234205092153242, "eval/hcp-val/loss": 0.8308628835985737} +{"epoch": 80, "train/lr": 1.2552926770192975e-05, "train/grad": 0.133252968701621, "train/loss": 0.8115529925251007, "eval/hcp-train-subset/loss": 0.8225048011349093, "eval/hcp-val/loss": 0.8300711733679618} +{"epoch": 81, "train/lr": 1.1338185434371453e-05, "train/grad": 0.134329247826871, "train/loss": 0.8113075026893616, "eval/hcp-train-subset/loss": 0.8220049200519439, "eval/hcp-val/loss": 0.8305859075438592} +{"epoch": 82, "train/lr": 1.0179388791627326e-05, "train/grad": 0.13651890857006543, "train/loss": 0.8103209806919098, "eval/hcp-train-subset/loss": 0.8216377035264046, "eval/hcp-val/loss": 0.8303592080070127} +{"epoch": 83, "train/lr": 9.07780396907607e-06, "train/grad": 0.13964630670190945, "train/loss": 0.8110128638267518, "eval/hcp-train-subset/loss": 0.8207122548933952, "eval/hcp-val/loss": 0.8297350916170305} +{"epoch": 84, "train/lr": 8.034635533547902e-06, "train/grad": 0.13676641611489687, "train/loss": 0.8121027170372009, "eval/hcp-train-subset/loss": 0.8208339714234875, "eval/hcp-val/loss": 0.829455417010092} +{"epoch": 85, "train/lr": 7.051024174411275e-06, "train/grad": 0.1407652093438128, "train/loss": 0.8103673832988739, "eval/hcp-train-subset/loss": 0.81967723850281, "eval/hcp-val/loss": 0.8295612421727949} +{"epoch": 86, "train/lr": 6.1280454562463606e-06, "train/grad": 0.14109719035820262, "train/loss": 0.8111404280471802, "eval/hcp-train-subset/loss": 0.8191962617058908, "eval/hcp-val/loss": 0.829715863350899} +{"epoch": 87, "train/lr": 5.266708642730326e-06, "train/grad": 0.14252701867610293, "train/loss": 0.8110980360603333, "eval/hcp-train-subset/loss": 0.8185332532851927, "eval/hcp-val/loss": 0.8297625876242115} +{"epoch": 88, "train/lr": 4.467955593022733e-06, "train/grad": 0.14274378764819237, "train/loss": 0.8101865449142456, "eval/hcp-train-subset/loss": 0.8184996362655393, "eval/hcp-val/loss": 0.8292296548043528} +{"epoch": 89, "train/lr": 3.732659731856291e-06, "train/grad": 0.14494894878218356, "train/loss": 0.8110534390354156, "eval/hcp-train-subset/loss": 0.8179104145496122, "eval/hcp-val/loss": 0.8291324771219685} +{"epoch": 90, "train/lr": 3.0616250944596583e-06, "train/grad": 0.14563188105034577, "train/loss": 0.8135384068584443, "eval/hcp-train-subset/loss": 0.81761664632828, "eval/hcp-val/loss": 0.8287415687114962} +{"epoch": 91, "train/lr": 2.4555854473568305e-06, "train/grad": 0.145325279766014, "train/loss": 0.8126901114463806, "eval/hcp-train-subset/loss": 0.8164434750233928, "eval/hcp-val/loss": 0.8283805818327011} +{"epoch": 92, "train/lr": 1.915203486004091e-06, "train/grad": 0.14750749984440353, "train/loss": 0.8124701114273071, "eval/hcp-train-subset/loss": 0.8163517030977434, "eval/hcp-val/loss": 0.8282923352333807} +{"epoch": 93, "train/lr": 1.4410701101423926e-06, "train/grad": 0.1511913374145056, "train/loss": 0.8091307321071625, "eval/hcp-train-subset/loss": 0.8156593951486772, "eval/hcp-val/loss": 0.828918864650111} +{"epoch": 94, "train/lr": 1.0337037776570775e-06, "train/grad": 0.15193439094189304, "train/loss": 0.8122176195716858, "eval/hcp-train-subset/loss": 0.815055831786125, "eval/hcp-val/loss": 0.8280118261614153} +{"epoch": 95, "train/lr": 6.935499376518293e-07, "train/grad": 0.15589539393374854, "train/loss": 0.810269676475525, "eval/hcp-train-subset/loss": 0.8147308576491571, "eval/hcp-val/loss": 0.8276319071169822} +{"epoch": 96, "train/lr": 4.209805433566085e-07, "train/grad": 0.14931738390688631, "train/loss": 0.8136823121356964, "eval/hcp-train-subset/loss": 0.814656368186397, "eval/hcp-val/loss": 0.8278536575455819} +{"epoch": 97, "train/lr": 2.1629364540224422e-07, "train/grad": 0.15398189609377447, "train/loss": 0.8126531840705872, "eval/hcp-train-subset/loss": 0.8142786179819415, "eval/hcp-val/loss": 0.8278481825705497} +{"epoch": 98, "train/lr": 7.971306590647406e-08, "train/grad": 0.15058308516585658, "train/loss": 0.8153153794384003, "eval/hcp-train-subset/loss": 0.8144680761521862, "eval/hcp-val/loss": 0.8276507989052804} +{"epoch": 99, "train/lr": 1.1388153727718725e-08, "train/grad": 0.15051311655466337, "train/loss": 0.8175804828643799, "eval/hcp-train-subset/loss": 0.8142545377054522, "eval/hcp-val/loss": 0.8278325440422181} diff --git a/input_space_v3/flat_lr1e-3_3/pretrain/log.txt b/input_space_v3/flat_lr1e-3_3/pretrain/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..56eca2ea60a84eab22dfded1636f514331854b11 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_3/pretrain/log.txt @@ -0,0 +1,8786 @@ +pretraining fmri mae +start: 2026-03-31 13:08:51 +cwd: /data/connor/fmri-fm +sha: ae0eae57a44753a80f371738f3276b064d5077cb, status: clean, branch: dev/clane9 +config: +name: input_space_v3/flat_lr1e-3_3/pretrain +notes: input_space ablation v3 flat_lr1e-3_3; use tube masking and on-disk data (input_space=flat + base_lr=1e-3 seed=5403) +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain +input_space: flat +patch_size: 16 +num_frames: 16 +t_patch_size: 4 +mask_ratio: 0.9 +pred_mask_ratio: null +masking: tube +masking_kwargs: {} +mask_patch_size: null +model: mae_vit_base +model_kwargs: + decoding: attn + pos_embed: sep + target_norm: null + pca_norm_nc: 2 + t_pred_stride: 2 + no_decode_pos: true + mask_drop_scale: false + pred_edge_pad: 0 + gauss_sigma: null + class_token: true + reg_tokens: 0 + no_embed_class: true + head_init_scale: 0.0 + decoder_depth: 4 + drop_path_rate: 0.0 +datasets: + hcp-train: + type: wds + url: /data/fmri-datasets/pretrain/hcpya-all.${input_space}.wds/hcpya-all-${input_space}-{00000..01799}.tar + clipping: random + clipping_kwargs: + oversample: 4.0 + shuffle: true + buffer_size: 2000 + samples_per_epoch: 200000 + hcp-train-subset: + type: arrow + root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/validation + split_range: + - 0 + - 2000 + shuffle: false + hcp-val: + type: arrow + root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/test + split_range: + - 0 + - 2000 + shuffle: false +train_dataset: hcp-train +eval_datasets: +- hcp-train-subset +- hcp-val +val_dataset: null +clip_vmax: 3.0 +normalize: frame +tr_scale: null +crop_scale: null +crop_aspect: null +gray_jitter: null +num_workers: 16 +epochs: 100 +batch_size: 32 +accum_iter: 1 +base_lr: 0.001 +min_lr: 0.0 +warmup_epochs: 5 +weight_decay: 0.05 +betas: +- 0.9 +- 0.95 +clip_grad: 1.0 +amp: true +amp_dtype: float16 +ckpt: null +resume: true +auto_resume: true +start_epoch: 0 +max_checkpoints: 0 +checkpoint_period: null +plot_period: 5 +device: cuda +presend_cuda: false +seed: 5403 +debug: false +wandb: true +wandb_entity: null +wandb_project: fMRI-foundation-model +rank: 0 +world_size: 1 +gpu: 0 +distributed: true +dist_backend: nccl +in_chans: 1 +img_size: +- 224 +- 560 + +train transform: +Compose( + ToTensor() + TemporalCenterCrop(num_frames=16) + Normalize(mode='frame') + Clip(vmax=3.0) + FlatUnmask((224, 560)) +) +val transform: +Compose( + ToTensor() + TemporalCenterCrop(num_frames=16) + Normalize(mode='frame') + Clip(vmax=3.0) + FlatUnmask((224, 560)) +) +mask generator: +TubeMasking( + mask_ratio=0.9 + (patchify): Patchify2D((224, 560), (16, 16), in_chans=1) +) +loading dataset: hcp-train + +type: wds +url: /data/fmri-datasets/pretrain/hcpya-all.${input_space}.wds/hcpya-all-${input_space}-{00000..01799}.tar +clipping: random +clipping_kwargs: + oversample: 4.0 +shuffle: true +buffer_size: 2000 +samples_per_epoch: 200000 + +loading dataset: hcp-train-subset + +type: arrow +root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/validation +split_range: +- 0 +- 2000 +shuffle: false + +split indices: [899, 472, 767, 116, 1265, 1852, 300, 1335, 361, 1560] +loading dataset: hcp-val + +type: arrow +root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/test +split_range: +- 0 +- 2000 +shuffle: false + +split indices: [1075, 1189, 738, 1350, 965, 1964, 1367, 1183, 1619, 1407] +model: +MaskedAutoencoderViT( + decoding=attn, t_pred_stride=2, pred_edge_pad=0, no_decode_pos=True + (encoder): MaskedEncoder( + class_token=True, reg_tokens=0, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) + (pred_patchify): StridedPatchify3D((16, 224, 560), (2, 16, 16), in_chans=1, t_stride=2) + (decoder): MaskedDecoder( + cross_decode=False, class_token=True, no_embed_class=True + (pos_embed): SeparablePosEmbed(512, (4, 14, 35)) + (proj): Linear(in_features=768, out_features=512, bias=True) + (blocks): ModuleList( + (0-3): 4 x Block( + (norm1): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=16 + (q): Linear(in_features=512, out_features=512, bias=True) + (k): Linear(in_features=512, out_features=512, bias=True) + (v): Linear(in_features=512, out_features=512, bias=True) + (proj): Linear(in_features=512, out_features=512, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=512, out_features=2048, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=2048, out_features=512, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (head): Linear(in_features=512, out_features=512, bias=True) + ) +) +num params: 99.7M +total batch size: 32 = 32 bs per gpu x 1 accum x 1 gpus +lr: 1.25e-04 = 1.00e-03 x 32 / 256 +full schedule: epochs = 100 (steps = 625000) +warmup: epochs = 5 (steps = 31250) +start training for 100 epochs +Train: [0] [ 0/6250] eta: 23:27:19 lr: 0.000000 grad: 0.0375 (0.0375) loss: 0.9965 (0.9965) time: 13.5104 data: 11.3143 max mem: 8589 +Train: [0] [ 100/6250] eta: 1:02:39 lr: 0.000000 grad: 0.0131 (0.0158) loss: 0.9952 (0.9960) time: 0.1646 data: 0.0685 max mem: 9394 +Train: [0] [ 200/6250] eta: 0:49:59 lr: 0.000001 grad: 0.0132 (0.0147) loss: 0.9958 (0.9960) time: 0.3601 data: 0.2636 max mem: 9394 +Train: [0] [ 300/6250] eta: 0:42:20 lr: 0.000001 grad: 0.0128 (0.0141) loss: 0.9959 (0.9960) time: 0.2106 data: 0.0884 max mem: 9394 +Train: [0] [ 400/6250] eta: 0:37:45 lr: 0.000002 grad: 0.0130 (0.0138) loss: 0.9958 (0.9959) time: 0.3578 data: 0.1049 max mem: 9394 +Train: [0] [ 500/6250] eta: 0:35:34 lr: 0.000002 grad: 0.0124 (0.0136) loss: 0.9955 (0.9959) time: 0.1229 data: 0.0010 max mem: 9394 +Train: [0] [ 600/6250] eta: 0:33:07 lr: 0.000002 grad: 0.0129 (0.0135) loss: 0.9956 (0.9959) time: 0.2537 data: 0.1092 max mem: 9394 +Train: [0] [ 700/6250] eta: 0:31:17 lr: 0.000003 grad: 0.0127 (0.0134) loss: 0.9957 (0.9959) time: 0.4400 data: 0.2664 max mem: 9394 +Train: [0] [ 800/6250] eta: 0:29:12 lr: 0.000003 grad: 0.0128 (0.0133) loss: 0.9955 (0.9959) time: 0.2228 data: 0.0900 max mem: 9394 +Train: [0] [ 900/6250] eta: 0:28:16 lr: 0.000004 grad: 0.0129 (0.0133) loss: 0.9959 (0.9958) time: 0.3678 data: 0.2590 max mem: 9394 +Train: [0] [1000/6250] eta: 0:26:10 lr: 0.000004 grad: 0.0132 (0.0133) loss: 0.9958 (0.9959) time: 0.1060 data: 0.0243 max mem: 9394 +Train: [0] [1100/6250] eta: 0:24:35 lr: 0.000004 grad: 0.0136 (0.0133) loss: 0.9957 (0.9958) time: 0.1057 data: 0.0233 max mem: 9394 +Train: [0] [1200/6250] eta: 0:23:05 lr: 0.000005 grad: 0.0140 (0.0134) loss: 0.9958 (0.9958) time: 0.1491 data: 0.0718 max mem: 9394 +Train: [0] [1300/6250] eta: 0:21:41 lr: 0.000005 grad: 0.0159 (0.0136) loss: 0.9964 (0.9958) time: 0.1081 data: 0.0312 max mem: 9394 +Train: [0] [1400/6250] eta: 0:20:36 lr: 0.000006 grad: 0.0179 (0.0138) loss: 0.9958 (0.9958) time: 0.2160 data: 0.0780 max mem: 9394 +Train: [0] [1500/6250] eta: 0:19:34 lr: 0.000006 grad: 0.0223 (0.0142) loss: 0.9954 (0.9958) time: 0.1226 data: 0.0447 max mem: 9394 +Train: [0] [1600/6250] eta: 0:18:40 lr: 0.000006 grad: 0.0241 (0.0149) loss: 0.9951 (0.9958) time: 0.1958 data: 0.1209 max mem: 9394 +Train: [0] [1700/6250] eta: 0:17:49 lr: 0.000007 grad: 0.0252 (0.0158) loss: 0.9954 (0.9958) time: 0.2194 data: 0.1296 max mem: 9394 +Train: [0] [1800/6250] eta: 0:17:00 lr: 0.000007 grad: 0.0344 (0.0168) loss: 0.9949 (0.9957) time: 0.1145 data: 0.0345 max mem: 9394 +Train: [0] [1900/6250] eta: 0:16:16 lr: 0.000008 grad: 0.0377 (0.0181) loss: 0.9943 (0.9957) time: 0.1350 data: 0.0464 max mem: 9394 +Train: [0] [2000/6250] eta: 0:15:33 lr: 0.000008 grad: 0.0464 (0.0195) loss: 0.9943 (0.9957) time: 0.1347 data: 0.0549 max mem: 9394 +Train: [0] [2100/6250] eta: 0:15:06 lr: 0.000008 grad: 0.0427 (0.0209) loss: 0.9938 (0.9956) time: 0.0884 data: 0.0002 max mem: 9394 +Train: [0] [2200/6250] eta: 0:14:28 lr: 0.000009 grad: 0.0572 (0.0221) loss: 0.9942 (0.9956) time: 0.1364 data: 0.0553 max mem: 9394 +Train: [0] [2300/6250] eta: 0:13:52 lr: 0.000009 grad: 0.0480 (0.0237) loss: 0.9946 (0.9955) time: 0.1551 data: 0.0773 max mem: 9394 +Train: [0] [2400/6250] eta: 0:13:19 lr: 0.000010 grad: 0.0530 (0.0251) loss: 0.9946 (0.9954) time: 0.1199 data: 0.0427 max mem: 9394 +Train: [0] [2500/6250] eta: 0:12:47 lr: 0.000010 grad: 0.0509 (0.0264) loss: 0.9943 (0.9954) time: 0.1211 data: 0.0398 max mem: 9394 +Train: [0] [2600/6250] eta: 0:12:25 lr: 0.000010 grad: 0.0633 (0.0276) loss: 0.9935 (0.9953) time: 0.0934 data: 0.0002 max mem: 9394 +Train: [0] [2700/6250] eta: 0:11:56 lr: 0.000011 grad: 0.0515 (0.0291) loss: 0.9939 (0.9953) time: 0.1343 data: 0.0188 max mem: 9394 +Train: [0] [2800/6250] eta: 0:11:35 lr: 0.000011 grad: 0.0752 (0.0304) loss: 0.9941 (0.9952) time: 0.1710 data: 0.0797 max mem: 9394 +Train: [0] [2900/6250] eta: 0:11:07 lr: 0.000012 grad: 0.0659 (0.0317) loss: 0.9931 (0.9951) time: 0.1483 data: 0.0684 max mem: 9394 +Train: [0] [3000/6250] eta: 0:10:43 lr: 0.000012 grad: 0.0694 (0.0333) loss: 0.9927 (0.9951) time: 0.2534 data: 0.1328 max mem: 9394 +Train: [0] [3100/6250] eta: 0:10:21 lr: 0.000012 grad: 0.0844 (0.0349) loss: 0.9923 (0.9950) time: 0.1196 data: 0.0415 max mem: 9394 +Train: [0] [3200/6250] eta: 0:09:55 lr: 0.000013 grad: 0.0668 (0.0364) loss: 0.9922 (0.9949) time: 0.1565 data: 0.0682 max mem: 9394 +Train: [0] [3300/6250] eta: 0:09:31 lr: 0.000013 grad: 0.0758 (0.0379) loss: 0.9925 (0.9948) time: 0.1462 data: 0.0663 max mem: 9394 +Train: [0] [3400/6250] eta: 0:09:09 lr: 0.000014 grad: 0.0616 (0.0391) loss: 0.9934 (0.9947) time: 0.0878 data: 0.0002 max mem: 9394 +Train: [0] [3500/6250] eta: 0:08:45 lr: 0.000014 grad: 0.0533 (0.0403) loss: 0.9928 (0.9947) time: 0.1331 data: 0.0467 max mem: 9394 +Train: [0] [3600/6250] eta: 0:08:22 lr: 0.000014 grad: 0.0818 (0.0414) loss: 0.9911 (0.9946) time: 0.1081 data: 0.0244 max mem: 9394 +Train: [0] [3700/6250] eta: 0:07:59 lr: 0.000015 grad: 0.0639 (0.0425) loss: 0.9934 (0.9945) time: 0.1272 data: 0.0483 max mem: 9394 +Train: [0] [3800/6250] eta: 0:07:37 lr: 0.000015 grad: 0.0695 (0.0434) loss: 0.9925 (0.9944) time: 0.1287 data: 0.0526 max mem: 9394 +Train: [0] [3900/6250] eta: 0:07:15 lr: 0.000016 grad: 0.0781 (0.0443) loss: 0.9914 (0.9944) time: 0.1422 data: 0.0615 max mem: 9394 +Train: [0] [4000/6250] eta: 0:06:54 lr: 0.000016 grad: 0.0856 (0.0452) loss: 0.9922 (0.9943) time: 0.1186 data: 0.0351 max mem: 9394 +Train: [0] [4100/6250] eta: 0:06:33 lr: 0.000016 grad: 0.0928 (0.0462) loss: 0.9902 (0.9942) time: 0.1315 data: 0.0507 max mem: 9394 +Train: [0] [4200/6250] eta: 0:06:13 lr: 0.000017 grad: 0.0803 (0.0470) loss: 0.9926 (0.9941) time: 0.1245 data: 0.0396 max mem: 9394 +Train: [0] [4300/6250] eta: 0:05:53 lr: 0.000017 grad: 0.0678 (0.0477) loss: 0.9915 (0.9941) time: 0.1528 data: 0.0717 max mem: 9394 +Train: [0] [4400/6250] eta: 0:05:32 lr: 0.000018 grad: 0.0642 (0.0483) loss: 0.9919 (0.9940) time: 0.1201 data: 0.0338 max mem: 9394 +Train: [0] [4500/6250] eta: 0:05:13 lr: 0.000018 grad: 0.0796 (0.0488) loss: 0.9904 (0.9940) time: 0.1444 data: 0.0639 max mem: 9394 +Train: [0] [4600/6250] eta: 0:04:53 lr: 0.000018 grad: 0.0696 (0.0495) loss: 0.9920 (0.9939) time: 0.1266 data: 0.0483 max mem: 9394 +Train: [0] [4700/6250] eta: 0:04:36 lr: 0.000019 grad: 0.0555 (0.0500) loss: 0.9923 (0.9939) time: 0.1120 data: 0.0037 max mem: 9394 +Train: [0] [4800/6250] eta: 0:04:17 lr: 0.000019 grad: 0.0634 (0.0504) loss: 0.9915 (0.9938) time: 0.1495 data: 0.0636 max mem: 9394 +Train: [0] [4900/6250] eta: 0:03:58 lr: 0.000020 grad: 0.0631 (0.0509) loss: 0.9931 (0.9938) time: 0.1677 data: 0.0840 max mem: 9394 +Train: [0] [5000/6250] eta: 0:03:39 lr: 0.000020 grad: 0.0664 (0.0514) loss: 0.9916 (0.9937) time: 0.1285 data: 0.0518 max mem: 9394 +Train: [0] [5100/6250] eta: 0:03:21 lr: 0.000020 grad: 0.0731 (0.0519) loss: 0.9902 (0.9937) time: 0.1603 data: 0.0835 max mem: 9394 +Train: [0] [5200/6250] eta: 0:03:02 lr: 0.000021 grad: 0.0656 (0.0525) loss: 0.9917 (0.9936) time: 0.1244 data: 0.0436 max mem: 9394 +Train: [0] [5300/6250] eta: 0:02:44 lr: 0.000021 grad: 0.0678 (0.0530) loss: 0.9898 (0.9935) time: 0.1264 data: 0.0474 max mem: 9394 +Train: [0] [5400/6250] eta: 0:02:27 lr: 0.000022 grad: 0.0723 (0.0535) loss: 0.9903 (0.9935) time: 0.2514 data: 0.1693 max mem: 9394 +Train: [0] [5500/6250] eta: 0:02:09 lr: 0.000022 grad: 0.0731 (0.0540) loss: 0.9893 (0.9934) time: 0.1838 data: 0.0859 max mem: 9394 +Train: [0] [5600/6250] eta: 0:01:51 lr: 0.000022 grad: 0.0812 (0.0545) loss: 0.9898 (0.9933) time: 0.1282 data: 0.0449 max mem: 9394 +Train: [0] [5700/6250] eta: 0:01:34 lr: 0.000023 grad: 0.0729 (0.0550) loss: 0.9913 (0.9933) time: 0.1366 data: 0.0586 max mem: 9394 +Train: [0] [5800/6250] eta: 0:01:16 lr: 0.000023 grad: 0.0606 (0.0555) loss: 0.9898 (0.9932) time: 0.1465 data: 0.0654 max mem: 9394 +Train: [0] [5900/6250] eta: 0:00:59 lr: 0.000024 grad: 0.0752 (0.0560) loss: 0.9882 (0.9931) time: 0.1457 data: 0.0672 max mem: 9394 +Train: [0] [6000/6250] eta: 0:00:42 lr: 0.000024 grad: 0.0752 (0.0565) loss: 0.9895 (0.9931) time: 0.1403 data: 0.0585 max mem: 9394 +Train: [0] [6100/6250] eta: 0:00:25 lr: 0.000024 grad: 0.0764 (0.0569) loss: 0.9891 (0.9930) time: 0.1370 data: 0.0568 max mem: 9394 +Train: [0] [6200/6250] eta: 0:00:08 lr: 0.000025 grad: 0.0768 (0.0574) loss: 0.9904 (0.9929) time: 0.1526 data: 0.0733 max mem: 9394 +Train: [0] [6249/6250] eta: 0:00:00 lr: 0.000025 grad: 0.0791 (0.0577) loss: 0.9886 (0.9929) time: 0.1238 data: 0.0414 max mem: 9394 +Train: [0] Total time: 0:17:40 (0.1697 s / it) +Averaged stats: lr: 0.000025 grad: 0.0791 (0.0577) loss: 0.9886 (0.9929) +Eval (hcp-train-subset): [0] [ 0/62] eta: 0:05:23 loss: 0.9937 (0.9937) time: 5.2208 data: 5.1904 max mem: 9394 +Eval (hcp-train-subset): [0] [61/62] eta: 0:00:00 loss: 0.9926 (0.9917) time: 0.1235 data: 0.0977 max mem: 9394 +Eval (hcp-train-subset): [0] Total time: 0:00:13 (0.2230 s / it) +Averaged stats (hcp-train-subset): loss: 0.9926 (0.9917) +Eval (hcp-val): [0] [ 0/62] eta: 0:03:55 loss: 0.9911 (0.9911) time: 3.7991 data: 3.7247 max mem: 9394 +Eval (hcp-val): [0] [61/62] eta: 0:00:00 loss: 0.9901 (0.9904) time: 0.1195 data: 0.0933 max mem: 9394 +Eval (hcp-val): [0] Total time: 0:00:13 (0.2103 s / it) +Averaged stats (hcp-val): loss: 0.9901 (0.9904) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +Train: [1] [ 0/6250] eta: 8:05:52 lr: 0.000025 grad: 0.1588 (0.1588) loss: 0.9863 (0.9863) time: 4.6644 data: 4.4777 max mem: 9394 +Train: [1] [ 100/6250] eta: 0:19:22 lr: 0.000025 grad: 0.0899 (0.1095) loss: 0.9890 (0.9883) time: 0.1674 data: 0.0824 max mem: 9394 +Train: [1] [ 200/6250] eta: 0:16:48 lr: 0.000026 grad: 0.0752 (0.1041) loss: 0.9907 (0.9884) time: 0.1375 data: 0.0545 max mem: 9394 +Train: [1] [ 300/6250] eta: 0:15:40 lr: 0.000026 grad: 0.0973 (0.0987) loss: 0.9893 (0.9887) time: 0.1497 data: 0.0539 max mem: 9394 +Train: [1] [ 400/6250] eta: 0:15:05 lr: 0.000027 grad: 0.0725 (0.0945) loss: 0.9898 (0.9890) time: 0.1467 data: 0.0609 max mem: 9394 +Train: [1] [ 500/6250] eta: 0:14:23 lr: 0.000027 grad: 0.0750 (0.0927) loss: 0.9891 (0.9891) time: 0.1253 data: 0.0433 max mem: 9394 +Train: [1] [ 600/6250] eta: 0:13:54 lr: 0.000027 grad: 0.0765 (0.0908) loss: 0.9899 (0.9892) time: 0.1130 data: 0.0338 max mem: 9394 +Train: [1] [ 700/6250] eta: 0:13:44 lr: 0.000028 grad: 0.0701 (0.0890) loss: 0.9901 (0.9892) time: 0.1784 data: 0.0853 max mem: 9394 +Train: [1] [ 800/6250] eta: 0:13:45 lr: 0.000028 grad: 0.0653 (0.0884) loss: 0.9897 (0.9892) time: 0.1076 data: 0.0002 max mem: 9394 +Train: [1] [ 900/6250] eta: 0:14:06 lr: 0.000029 grad: 0.0770 (0.0871) loss: 0.9899 (0.9892) time: 0.1323 data: 0.0003 max mem: 9394 +Train: [1] [1000/6250] eta: 0:14:43 lr: 0.000029 grad: 0.0687 (0.0867) loss: 0.9910 (0.9893) time: 0.0972 data: 0.0002 max mem: 9394 +Train: [1] [1100/6250] eta: 0:14:29 lr: 0.000029 grad: 0.0751 (0.0865) loss: 0.9884 (0.9893) time: 0.1761 data: 0.0837 max mem: 9394 +Train: [1] [1200/6250] eta: 0:14:12 lr: 0.000030 grad: 0.0869 (0.0864) loss: 0.9889 (0.9892) time: 0.1338 data: 0.0574 max mem: 9394 +Train: [1] [1300/6250] eta: 0:13:44 lr: 0.000030 grad: 0.0818 (0.0862) loss: 0.9879 (0.9892) time: 0.1467 data: 0.0688 max mem: 9394 +Train: [1] [1400/6250] eta: 0:13:45 lr: 0.000031 grad: 0.0769 (0.0861) loss: 0.9895 (0.9892) time: 0.1195 data: 0.0381 max mem: 9394 +Train: [1] [1500/6250] eta: 0:13:15 lr: 0.000031 grad: 0.0940 (0.0861) loss: 0.9888 (0.9892) time: 0.1618 data: 0.0867 max mem: 9394 +Train: [1] [1600/6250] eta: 0:12:47 lr: 0.000031 grad: 0.0788 (0.0859) loss: 0.9892 (0.9891) time: 0.1270 data: 0.0467 max mem: 9394 +Train: [1] [1700/6250] eta: 0:12:23 lr: 0.000032 grad: 0.0580 (0.0857) loss: 0.9898 (0.9891) time: 0.1527 data: 0.0754 max mem: 9394 +Train: [1] [1800/6250] eta: 0:11:58 lr: 0.000032 grad: 0.0786 (0.0860) loss: 0.9893 (0.9891) time: 0.1310 data: 0.0456 max mem: 9394 +Train: [1] [1900/6250] eta: 0:11:35 lr: 0.000033 grad: 0.0774 (0.0859) loss: 0.9881 (0.9890) time: 0.1384 data: 0.0600 max mem: 9394 +Train: [1] [2000/6250] eta: 0:11:15 lr: 0.000033 grad: 0.0932 (0.0862) loss: 0.9871 (0.9890) time: 0.1311 data: 0.0484 max mem: 9394 +Train: [1] [2100/6250] eta: 0:11:12 lr: 0.000033 grad: 0.0846 (0.0862) loss: 0.9883 (0.9889) time: 0.1305 data: 0.0511 max mem: 9394 +Train: [1] [2200/6250] eta: 0:10:52 lr: 0.000034 grad: 0.0747 (0.0859) loss: 0.9885 (0.9889) time: 0.1646 data: 0.0718 max mem: 9394 +Train: [1] [2300/6250] eta: 0:10:32 lr: 0.000034 grad: 0.0796 (0.0858) loss: 0.9879 (0.9889) time: 0.1552 data: 0.0784 max mem: 9394 +Train: [1] [2400/6250] eta: 0:10:13 lr: 0.000035 grad: 0.0770 (0.0857) loss: 0.9868 (0.9888) time: 0.1440 data: 0.0528 max mem: 9394 +Train: [1] [2500/6250] eta: 0:09:56 lr: 0.000035 grad: 0.0714 (0.0854) loss: 0.9885 (0.9889) time: 0.1108 data: 0.0355 max mem: 9394 +Train: [1] [2600/6250] eta: 0:09:37 lr: 0.000035 grad: 0.0750 (0.0852) loss: 0.9878 (0.9888) time: 0.1396 data: 0.0630 max mem: 9394 +Train: [1] [2700/6250] eta: 0:09:21 lr: 0.000036 grad: 0.0841 (0.0853) loss: 0.9891 (0.9888) time: 0.0883 data: 0.0084 max mem: 9394 +Train: [1] [2800/6250] eta: 0:09:03 lr: 0.000036 grad: 0.0714 (0.0850) loss: 0.9874 (0.9888) time: 0.1983 data: 0.0859 max mem: 9394 +Train: [1] [2900/6250] eta: 0:08:47 lr: 0.000037 grad: 0.0686 (0.0848) loss: 0.9891 (0.9888) time: 0.1521 data: 0.0711 max mem: 9394 +Train: [1] [3000/6250] eta: 0:08:30 lr: 0.000037 grad: 0.0689 (0.0846) loss: 0.9895 (0.9888) time: 0.1674 data: 0.0682 max mem: 9394 +Train: [1] [3100/6250] eta: 0:08:14 lr: 0.000037 grad: 0.0773 (0.0846) loss: 0.9883 (0.9888) time: 0.1354 data: 0.0490 max mem: 9394 +Train: [1] [3200/6250] eta: 0:07:56 lr: 0.000038 grad: 0.0672 (0.0844) loss: 0.9901 (0.9888) time: 0.1264 data: 0.0471 max mem: 9394 +Train: [1] [3300/6250] eta: 0:07:40 lr: 0.000038 grad: 0.0769 (0.0844) loss: 0.9870 (0.9887) time: 0.1747 data: 0.0917 max mem: 9394 +Train: [1] [3400/6250] eta: 0:07:22 lr: 0.000039 grad: 0.0795 (0.0842) loss: 0.9881 (0.9887) time: 0.1349 data: 0.0585 max mem: 9394 +Train: [1] [3500/6250] eta: 0:07:05 lr: 0.000039 grad: 0.0741 (0.0841) loss: 0.9878 (0.9887) time: 0.1461 data: 0.0651 max mem: 9394 +Train: [1] [3600/6250] eta: 0:06:48 lr: 0.000039 grad: 0.0914 (0.0843) loss: 0.9881 (0.9887) time: 0.1404 data: 0.0578 max mem: 9394 +Train: [1] [3700/6250] eta: 0:06:32 lr: 0.000040 grad: 0.0742 (0.0843) loss: 0.9868 (0.9886) time: 0.1318 data: 0.0513 max mem: 9394 +Train: [1] [3800/6250] eta: 0:06:15 lr: 0.000040 grad: 0.0872 (0.0842) loss: 0.9873 (0.9886) time: 0.1405 data: 0.0618 max mem: 9394 +Train: [1] [3900/6250] eta: 0:05:59 lr: 0.000041 grad: 0.0868 (0.0842) loss: 0.9870 (0.9886) time: 0.1421 data: 0.0680 max mem: 9394 +Train: [1] [4000/6250] eta: 0:05:43 lr: 0.000041 grad: 0.0790 (0.0841) loss: 0.9890 (0.9886) time: 0.1518 data: 0.0742 max mem: 9394 +Train: [1] [4100/6250] eta: 0:05:27 lr: 0.000041 grad: 0.0725 (0.0841) loss: 0.9888 (0.9886) time: 0.1571 data: 0.0813 max mem: 9394 +Train: [1] [4200/6250] eta: 0:05:11 lr: 0.000042 grad: 0.0694 (0.0840) loss: 0.9877 (0.9886) time: 0.1294 data: 0.0536 max mem: 9394 +Train: [1] [4300/6250] eta: 0:04:55 lr: 0.000042 grad: 0.0783 (0.0840) loss: 0.9876 (0.9885) time: 0.1222 data: 0.0337 max mem: 9394 +Train: [1] [4400/6250] eta: 0:04:39 lr: 0.000043 grad: 0.0689 (0.0839) loss: 0.9885 (0.9885) time: 0.1391 data: 0.0599 max mem: 9394 +Train: [1] [4500/6250] eta: 0:04:24 lr: 0.000043 grad: 0.0847 (0.0839) loss: 0.9894 (0.9885) time: 0.1526 data: 0.0742 max mem: 9394 +Train: [1] [4600/6250] eta: 0:04:09 lr: 0.000043 grad: 0.0782 (0.0838) loss: 0.9873 (0.9885) time: 0.1565 data: 0.0811 max mem: 9394 +Train: [1] [4700/6250] eta: 0:03:53 lr: 0.000044 grad: 0.0786 (0.0838) loss: 0.9883 (0.9885) time: 0.1238 data: 0.0408 max mem: 9394 +Train: [1] [4800/6250] eta: 0:03:37 lr: 0.000044 grad: 0.0898 (0.0838) loss: 0.9862 (0.9885) time: 0.1325 data: 0.0488 max mem: 9394 +Train: [1] [4900/6250] eta: 0:03:22 lr: 0.000045 grad: 0.0791 (0.0839) loss: 0.9879 (0.9884) time: 0.1252 data: 0.0488 max mem: 9394 +Train: [1] [5000/6250] eta: 0:03:07 lr: 0.000045 grad: 0.0856 (0.0839) loss: 0.9879 (0.9884) time: 0.1513 data: 0.0719 max mem: 9394 +Train: [1] [5100/6250] eta: 0:02:51 lr: 0.000045 grad: 0.0805 (0.0840) loss: 0.9867 (0.9884) time: 0.1271 data: 0.0448 max mem: 9394 +Train: [1] [5200/6250] eta: 0:02:37 lr: 0.000046 grad: 0.1054 (0.0842) loss: 0.9855 (0.9883) time: 0.2010 data: 0.1210 max mem: 9394 +Train: [1] [5300/6250] eta: 0:02:21 lr: 0.000046 grad: 0.0835 (0.0843) loss: 0.9866 (0.9883) time: 0.1315 data: 0.0538 max mem: 9394 +Train: [1] [5400/6250] eta: 0:02:06 lr: 0.000047 grad: 0.0717 (0.0843) loss: 0.9877 (0.9883) time: 0.1247 data: 0.0475 max mem: 9394 +Train: [1] [5500/6250] eta: 0:01:51 lr: 0.000047 grad: 0.0829 (0.0844) loss: 0.9868 (0.9883) time: 0.1220 data: 0.0360 max mem: 9394 +Train: [1] [5600/6250] eta: 0:01:36 lr: 0.000047 grad: 0.0759 (0.0845) loss: 0.9874 (0.9883) time: 0.1862 data: 0.1113 max mem: 9394 +Train: [1] [5700/6250] eta: 0:01:21 lr: 0.000048 grad: 0.0673 (0.0845) loss: 0.9873 (0.9882) time: 0.1562 data: 0.0790 max mem: 9394 +Train: [1] [5800/6250] eta: 0:01:06 lr: 0.000048 grad: 0.0738 (0.0844) loss: 0.9868 (0.9882) time: 0.1428 data: 0.0665 max mem: 9394 +Train: [1] [5900/6250] eta: 0:00:51 lr: 0.000049 grad: 0.0741 (0.0843) loss: 0.9886 (0.9882) time: 0.1889 data: 0.0992 max mem: 9394 +Train: [1] [6000/6250] eta: 0:00:37 lr: 0.000049 grad: 0.0678 (0.0843) loss: 0.9891 (0.9882) time: 0.1258 data: 0.0437 max mem: 9394 +Train: [1] [6100/6250] eta: 0:00:22 lr: 0.000049 grad: 0.0771 (0.0844) loss: 0.9883 (0.9882) time: 0.1166 data: 0.0337 max mem: 9394 +Train: [1] [6200/6250] eta: 0:00:07 lr: 0.000050 grad: 0.0823 (0.0844) loss: 0.9871 (0.9882) time: 0.1034 data: 0.0144 max mem: 9394 +Train: [1] [6249/6250] eta: 0:00:00 lr: 0.000050 grad: 0.0701 (0.0843) loss: 0.9871 (0.9882) time: 0.1418 data: 0.0680 max mem: 9394 +Train: [1] Total time: 0:15:32 (0.1493 s / it) +Averaged stats: lr: 0.000050 grad: 0.0701 (0.0843) loss: 0.9871 (0.9882) +Eval (hcp-train-subset): [1] [ 0/62] eta: 0:04:05 loss: 0.9896 (0.9896) time: 3.9566 data: 3.9255 max mem: 9394 +Eval (hcp-train-subset): [1] [61/62] eta: 0:00:00 loss: 0.9881 (0.9888) time: 0.1317 data: 0.1068 max mem: 9394 +Eval (hcp-train-subset): [1] Total time: 0:00:13 (0.2132 s / it) +Averaged stats (hcp-train-subset): loss: 0.9881 (0.9888) +Eval (hcp-val): [1] [ 0/62] eta: 0:04:35 loss: 0.9892 (0.9892) time: 4.4464 data: 4.4162 max mem: 9394 +Eval (hcp-val): [1] [61/62] eta: 0:00:00 loss: 0.9869 (0.9866) time: 0.1329 data: 0.1065 max mem: 9394 +Eval (hcp-val): [1] Total time: 0:00:12 (0.2096 s / it) +Averaged stats (hcp-val): loss: 0.9869 (0.9866) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +Train: [2] [ 0/6250] eta: 7:06:38 lr: 0.000050 grad: 0.0594 (0.0594) loss: 0.9905 (0.9905) time: 4.0958 data: 3.8287 max mem: 9394 +Train: [2] [ 100/6250] eta: 0:19:33 lr: 0.000050 grad: 0.0946 (0.0965) loss: 0.9857 (0.9849) time: 0.1509 data: 0.0676 max mem: 9394 +Train: [2] [ 200/6250] eta: 0:16:56 lr: 0.000051 grad: 0.0913 (0.0979) loss: 0.9870 (0.9842) time: 0.1300 data: 0.0501 max mem: 9394 +Train: [2] [ 300/6250] eta: 0:15:48 lr: 0.000051 grad: 0.0748 (0.0951) loss: 0.9890 (0.9845) time: 0.1224 data: 0.0347 max mem: 9394 +Train: [2] [ 400/6250] eta: 0:14:52 lr: 0.000052 grad: 0.0737 (0.0917) loss: 0.9880 (0.9849) time: 0.1290 data: 0.0425 max mem: 9394 +Train: [2] [ 500/6250] eta: 0:14:07 lr: 0.000052 grad: 0.0772 (0.0890) loss: 0.9869 (0.9852) time: 0.1232 data: 0.0352 max mem: 9394 +Train: [2] [ 600/6250] eta: 0:13:33 lr: 0.000052 grad: 0.0757 (0.0877) loss: 0.9865 (0.9854) time: 0.1306 data: 0.0476 max mem: 9394 +Train: [2] [ 700/6250] eta: 0:13:00 lr: 0.000053 grad: 0.0639 (0.0860) loss: 0.9881 (0.9856) time: 0.1177 data: 0.0336 max mem: 9394 +Train: [2] [ 800/6250] eta: 0:12:46 lr: 0.000053 grad: 0.0702 (0.0847) loss: 0.9869 (0.9858) time: 0.1395 data: 0.0566 max mem: 9394 +Train: [2] [ 900/6250] eta: 0:12:36 lr: 0.000054 grad: 0.0721 (0.0839) loss: 0.9865 (0.9859) time: 0.1669 data: 0.0865 max mem: 9394 +Train: [2] [1000/6250] eta: 0:12:27 lr: 0.000054 grad: 0.0710 (0.0842) loss: 0.9883 (0.9860) time: 0.1121 data: 0.0266 max mem: 9394 +Train: [2] [1100/6250] eta: 0:12:14 lr: 0.000054 grad: 0.0739 (0.0838) loss: 0.9857 (0.9860) time: 0.1275 data: 0.0460 max mem: 9394 +Train: [2] [1200/6250] eta: 0:11:59 lr: 0.000055 grad: 0.0781 (0.0838) loss: 0.9857 (0.9860) time: 0.1452 data: 0.0687 max mem: 9394 +Train: [2] [1300/6250] eta: 0:11:42 lr: 0.000055 grad: 0.0765 (0.0838) loss: 0.9851 (0.9859) time: 0.1306 data: 0.0480 max mem: 9394 +Train: [2] [1400/6250] eta: 0:11:26 lr: 0.000056 grad: 0.0774 (0.0838) loss: 0.9866 (0.9859) time: 0.1303 data: 0.0461 max mem: 9394 +Train: [2] [1500/6250] eta: 0:11:11 lr: 0.000056 grad: 0.0762 (0.0836) loss: 0.9864 (0.9860) time: 0.1421 data: 0.0605 max mem: 9394 +Train: [2] [1600/6250] eta: 0:10:59 lr: 0.000056 grad: 0.0809 (0.0834) loss: 0.9871 (0.9860) time: 0.1710 data: 0.0905 max mem: 9394 +Train: [2] [1700/6250] eta: 0:10:41 lr: 0.000057 grad: 0.0838 (0.0836) loss: 0.9829 (0.9860) time: 0.1316 data: 0.0501 max mem: 9394 +Train: [2] [1800/6250] eta: 0:10:27 lr: 0.000057 grad: 0.0808 (0.0837) loss: 0.9875 (0.9860) time: 0.1259 data: 0.0452 max mem: 9394 +Train: [2] [1900/6250] eta: 0:10:11 lr: 0.000058 grad: 0.0843 (0.0837) loss: 0.9855 (0.9859) time: 0.1212 data: 0.0389 max mem: 9394 +Train: [2] [2000/6250] eta: 0:10:02 lr: 0.000058 grad: 0.0723 (0.0839) loss: 0.9861 (0.9859) time: 0.2203 data: 0.1376 max mem: 9394 +Train: [2] [2100/6250] eta: 0:09:46 lr: 0.000058 grad: 0.0789 (0.0840) loss: 0.9847 (0.9859) time: 0.1570 data: 0.0821 max mem: 9394 +Train: [2] [2200/6250] eta: 0:09:30 lr: 0.000059 grad: 0.0838 (0.0844) loss: 0.9855 (0.9858) time: 0.1197 data: 0.0427 max mem: 9394 +Train: [2] [2300/6250] eta: 0:09:16 lr: 0.000059 grad: 0.0781 (0.0843) loss: 0.9880 (0.9858) time: 0.1288 data: 0.0521 max mem: 9394 +Train: [2] [2400/6250] eta: 0:09:01 lr: 0.000060 grad: 0.0843 (0.0844) loss: 0.9870 (0.9858) time: 0.1368 data: 0.0576 max mem: 9394 +Train: [2] [2500/6250] eta: 0:08:48 lr: 0.000060 grad: 0.0794 (0.0845) loss: 0.9864 (0.9858) time: 0.1442 data: 0.0605 max mem: 9394 +Train: [2] [2600/6250] eta: 0:08:33 lr: 0.000060 grad: 0.0843 (0.0848) loss: 0.9843 (0.9858) time: 0.1368 data: 0.0525 max mem: 9394 +Train: [2] [2700/6250] eta: 0:08:18 lr: 0.000061 grad: 0.0852 (0.0848) loss: 0.9865 (0.9858) time: 0.1239 data: 0.0428 max mem: 9394 +Train: [2] [2800/6250] eta: 0:08:03 lr: 0.000061 grad: 0.0869 (0.0849) loss: 0.9846 (0.9858) time: 0.1364 data: 0.0561 max mem: 9394 +Train: [2] [2900/6250] eta: 0:07:50 lr: 0.000062 grad: 0.0710 (0.0849) loss: 0.9872 (0.9858) time: 0.1110 data: 0.0266 max mem: 9394 +Train: [2] [3000/6250] eta: 0:07:35 lr: 0.000062 grad: 0.0833 (0.0851) loss: 0.9859 (0.9858) time: 0.1342 data: 0.0583 max mem: 9394 +Train: [2] [3100/6250] eta: 0:07:21 lr: 0.000062 grad: 0.0860 (0.0852) loss: 0.9857 (0.9857) time: 0.1312 data: 0.0521 max mem: 9394 +Train: [2] [3200/6250] eta: 0:07:08 lr: 0.000063 grad: 0.0862 (0.0853) loss: 0.9855 (0.9857) time: 0.1851 data: 0.0911 max mem: 9394 +Train: [2] [3300/6250] eta: 0:06:58 lr: 0.000063 grad: 0.0802 (0.0854) loss: 0.9869 (0.9857) time: 0.1071 data: 0.0243 max mem: 9394 +Train: [2] [3400/6250] eta: 0:06:45 lr: 0.000064 grad: 0.0791 (0.0854) loss: 0.9844 (0.9857) time: 0.2414 data: 0.1268 max mem: 9394 +Train: [2] [3500/6250] eta: 0:06:30 lr: 0.000064 grad: 0.0918 (0.0856) loss: 0.9864 (0.9857) time: 0.1138 data: 0.0340 max mem: 9394 +Train: [2] [3600/6250] eta: 0:06:15 lr: 0.000064 grad: 0.0878 (0.0856) loss: 0.9842 (0.9857) time: 0.1288 data: 0.0490 max mem: 9394 +Train: [2] [3700/6250] eta: 0:06:02 lr: 0.000065 grad: 0.0726 (0.0855) loss: 0.9849 (0.9857) time: 0.1027 data: 0.0161 max mem: 9394 +Train: [2] [3800/6250] eta: 0:05:48 lr: 0.000065 grad: 0.0860 (0.0856) loss: 0.9859 (0.9857) time: 0.1395 data: 0.0574 max mem: 9394 +Train: [2] [3900/6250] eta: 0:05:33 lr: 0.000066 grad: 0.1051 (0.0860) loss: 0.9843 (0.9857) time: 0.1385 data: 0.0572 max mem: 9394 +Train: [2] [4000/6250] eta: 0:05:18 lr: 0.000066 grad: 0.1023 (0.0862) loss: 0.9830 (0.9856) time: 0.1217 data: 0.0404 max mem: 9394 +Train: [2] [4100/6250] eta: 0:05:03 lr: 0.000066 grad: 0.0841 (0.0864) loss: 0.9838 (0.9856) time: 0.1503 data: 0.0760 max mem: 9394 +Train: [2] [4200/6250] eta: 0:04:48 lr: 0.000067 grad: 0.1098 (0.0868) loss: 0.9829 (0.9856) time: 0.1258 data: 0.0449 max mem: 9394 +Train: [2] [4300/6250] eta: 0:04:34 lr: 0.000067 grad: 0.0887 (0.0873) loss: 0.9848 (0.9856) time: 0.1395 data: 0.0654 max mem: 9394 +Train: [2] [4400/6250] eta: 0:04:20 lr: 0.000068 grad: 0.0993 (0.0878) loss: 0.9839 (0.9855) time: 0.1365 data: 0.0486 max mem: 9394 +Train: [2] [4500/6250] eta: 0:04:05 lr: 0.000068 grad: 0.0877 (0.0884) loss: 0.9873 (0.9855) time: 0.1293 data: 0.0473 max mem: 9394 +Train: [2] [4600/6250] eta: 0:03:51 lr: 0.000068 grad: 0.0991 (0.0886) loss: 0.9828 (0.9855) time: 0.1387 data: 0.0526 max mem: 9394 +Train: [2] [4700/6250] eta: 0:03:37 lr: 0.000069 grad: 0.1257 (0.0897) loss: 0.9819 (0.9855) time: 0.1703 data: 0.0937 max mem: 9394 +Train: [2] [4800/6250] eta: 0:03:23 lr: 0.000069 grad: 0.0992 (0.0908) loss: 0.9838 (0.9854) time: 0.1247 data: 0.0441 max mem: 9394 +Train: [2] [4900/6250] eta: 0:03:08 lr: 0.000070 grad: 0.1561 (0.0922) loss: 0.9836 (0.9854) time: 0.1422 data: 0.0626 max mem: 9394 +Train: [2] [5000/6250] eta: 0:02:54 lr: 0.000070 grad: 0.1228 (0.0933) loss: 0.9826 (0.9854) time: 0.1287 data: 0.0500 max mem: 9394 +Train: [2] [5100/6250] eta: 0:02:40 lr: 0.000070 grad: 0.1497 (0.0946) loss: 0.9831 (0.9853) time: 0.1689 data: 0.0948 max mem: 9394 +Train: [2] [5200/6250] eta: 0:02:26 lr: 0.000071 grad: 0.1281 (0.0961) loss: 0.9802 (0.9853) time: 0.1339 data: 0.0473 max mem: 9394 +Train: [2] [5300/6250] eta: 0:02:13 lr: 0.000071 grad: 0.2138 (0.0986) loss: 0.9830 (0.9852) time: 0.1155 data: 0.0259 max mem: 9394 +Train: [2] [5400/6250] eta: 0:01:59 lr: 0.000072 grad: 0.1381 (0.1004) loss: 0.9837 (0.9852) time: 0.1282 data: 0.0480 max mem: 9394 +Train: [2] [5500/6250] eta: 0:01:45 lr: 0.000072 grad: 0.1871 (0.1027) loss: 0.9824 (0.9851) time: 0.1371 data: 0.0608 max mem: 9394 +Train: [2] [5600/6250] eta: 0:01:31 lr: 0.000072 grad: 0.1581 (0.1048) loss: 0.9811 (0.9850) time: 0.1997 data: 0.1215 max mem: 9394 +Train: [2] [5700/6250] eta: 0:01:17 lr: 0.000073 grad: 0.1537 (0.1066) loss: 0.9817 (0.9850) time: 0.1589 data: 0.0797 max mem: 9394 +Train: [2] [5800/6250] eta: 0:01:03 lr: 0.000073 grad: 0.1695 (0.1086) loss: 0.9791 (0.9849) time: 0.1347 data: 0.0545 max mem: 9394 +Train: [2] [5900/6250] eta: 0:00:49 lr: 0.000074 grad: 0.1428 (0.1107) loss: 0.9813 (0.9849) time: 0.1381 data: 0.0605 max mem: 9394 +Train: [2] [6000/6250] eta: 0:00:34 lr: 0.000074 grad: 0.1492 (0.1125) loss: 0.9812 (0.9848) time: 0.1346 data: 0.0566 max mem: 9394 +Train: [2] [6100/6250] eta: 0:00:20 lr: 0.000074 grad: 0.1860 (0.1143) loss: 0.9815 (0.9848) time: 0.1330 data: 0.0499 max mem: 9394 +Train: [2] [6200/6250] eta: 0:00:06 lr: 0.000075 grad: 0.1680 (0.1159) loss: 0.9791 (0.9847) time: 0.1464 data: 0.0657 max mem: 9394 +Train: [2] [6249/6250] eta: 0:00:00 lr: 0.000075 grad: 0.2073 (0.1165) loss: 0.9791 (0.9847) time: 0.1394 data: 0.0602 max mem: 9394 +Train: [2] Total time: 0:14:41 (0.1410 s / it) +Averaged stats: lr: 0.000075 grad: 0.2073 (0.1165) loss: 0.9791 (0.9847) +Eval (hcp-train-subset): [2] [ 0/62] eta: 0:04:15 loss: 0.9832 (0.9832) time: 4.1262 data: 4.0964 max mem: 9394 +Eval (hcp-train-subset): [2] [61/62] eta: 0:00:00 loss: 0.9847 (0.9836) time: 0.1263 data: 0.0997 max mem: 9394 +Eval (hcp-train-subset): [2] Total time: 0:00:13 (0.2181 s / it) +Averaged stats (hcp-train-subset): loss: 0.9847 (0.9836) +Eval (hcp-val): [2] [ 0/62] eta: 0:04:45 loss: 0.9796 (0.9796) time: 4.6074 data: 4.5759 max mem: 9394 +Eval (hcp-val): [2] [61/62] eta: 0:00:00 loss: 0.9820 (0.9821) time: 0.1249 data: 0.1003 max mem: 9394 +Eval (hcp-val): [2] Total time: 0:00:13 (0.2184 s / it) +Averaged stats (hcp-val): loss: 0.9820 (0.9821) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +Train: [3] [ 0/6250] eta: 7:42:35 lr: 0.000075 grad: 0.2908 (0.2908) loss: 0.9865 (0.9865) time: 4.4409 data: 4.2282 max mem: 9394 +Train: [3] [ 100/6250] eta: 0:19:55 lr: 0.000075 grad: 0.1742 (0.2115) loss: 0.9839 (0.9824) time: 0.1546 data: 0.0731 max mem: 9394 +Train: [3] [ 200/6250] eta: 0:17:00 lr: 0.000076 grad: 0.2095 (0.2221) loss: 0.9822 (0.9808) time: 0.1375 data: 0.0520 max mem: 9394 +Train: [3] [ 300/6250] eta: 0:15:45 lr: 0.000076 grad: 0.1402 (0.2180) loss: 0.9804 (0.9809) time: 0.1476 data: 0.0693 max mem: 9394 +Train: [3] [ 400/6250] eta: 0:14:36 lr: 0.000077 grad: 0.1971 (0.2184) loss: 0.9813 (0.9808) time: 0.1202 data: 0.0352 max mem: 9394 +Train: [3] [ 500/6250] eta: 0:13:58 lr: 0.000077 grad: 0.1479 (0.2154) loss: 0.9816 (0.9808) time: 0.1157 data: 0.0270 max mem: 9394 +Train: [3] [ 600/6250] eta: 0:13:26 lr: 0.000077 grad: 0.1465 (0.2159) loss: 0.9804 (0.9808) time: 0.1416 data: 0.0567 max mem: 9394 +Train: [3] [ 700/6250] eta: 0:13:00 lr: 0.000078 grad: 0.1622 (0.2109) loss: 0.9815 (0.9808) time: 0.1307 data: 0.0488 max mem: 9394 +Train: [3] [ 800/6250] eta: 0:12:41 lr: 0.000078 grad: 0.1356 (0.2087) loss: 0.9812 (0.9809) time: 0.1439 data: 0.0592 max mem: 9394 +Train: [3] [ 900/6250] eta: 0:12:31 lr: 0.000079 grad: 0.1644 (0.2061) loss: 0.9819 (0.9810) time: 0.1526 data: 0.0710 max mem: 9394 +Train: [3] [1000/6250] eta: 0:12:13 lr: 0.000079 grad: 0.1762 (0.2045) loss: 0.9817 (0.9811) time: 0.1456 data: 0.0695 max mem: 9394 +Train: [3] [1100/6250] eta: 0:11:56 lr: 0.000079 grad: 0.2073 (0.2050) loss: 0.9818 (0.9811) time: 0.1368 data: 0.0528 max mem: 9394 +Train: [3] [1200/6250] eta: 0:11:46 lr: 0.000080 grad: 0.1197 (0.2040) loss: 0.9824 (0.9812) time: 0.1368 data: 0.0584 max mem: 9394 +Train: [3] [1300/6250] eta: 0:11:33 lr: 0.000080 grad: 0.1502 (0.2029) loss: 0.9794 (0.9811) time: 0.1418 data: 0.0527 max mem: 9394 +Train: [3] [1400/6250] eta: 0:11:15 lr: 0.000081 grad: 0.1148 (0.2021) loss: 0.9812 (0.9812) time: 0.1158 data: 0.0387 max mem: 9394 +Train: [3] [1500/6250] eta: 0:11:05 lr: 0.000081 grad: 0.1970 (0.2015) loss: 0.9833 (0.9812) time: 0.1391 data: 0.0538 max mem: 9394 +Train: [3] [1600/6250] eta: 0:10:50 lr: 0.000081 grad: 0.1285 (0.1984) loss: 0.9824 (0.9812) time: 0.1504 data: 0.0698 max mem: 9394 +Train: [3] [1700/6250] eta: 0:10:35 lr: 0.000082 grad: 0.1370 (0.1981) loss: 0.9809 (0.9811) time: 0.1415 data: 0.0611 max mem: 9394 +Train: [3] [1800/6250] eta: 0:10:21 lr: 0.000082 grad: 0.1898 (0.1968) loss: 0.9801 (0.9810) time: 0.1396 data: 0.0624 max mem: 9394 +Train: [3] [1900/6250] eta: 0:10:08 lr: 0.000083 grad: 0.2033 (0.1971) loss: 0.9807 (0.9810) time: 0.1439 data: 0.0667 max mem: 9394 +Train: [3] [2000/6250] eta: 0:09:53 lr: 0.000083 grad: 0.1865 (0.1969) loss: 0.9790 (0.9809) time: 0.1256 data: 0.0464 max mem: 9394 +Train: [3] [2100/6250] eta: 0:09:39 lr: 0.000083 grad: 0.1491 (0.1968) loss: 0.9765 (0.9808) time: 0.1408 data: 0.0627 max mem: 9394 +Train: [3] [2200/6250] eta: 0:09:25 lr: 0.000084 grad: 0.1945 (0.1972) loss: 0.9795 (0.9808) time: 0.1253 data: 0.0465 max mem: 9394 +Train: [3] [2300/6250] eta: 0:09:12 lr: 0.000084 grad: 0.1812 (0.1965) loss: 0.9799 (0.9807) time: 0.1304 data: 0.0529 max mem: 9394 +Train: [3] [2400/6250] eta: 0:08:58 lr: 0.000085 grad: 0.1731 (0.1964) loss: 0.9780 (0.9806) time: 0.1423 data: 0.0618 max mem: 9394 +Train: [3] [2500/6250] eta: 0:08:45 lr: 0.000085 grad: 0.2115 (0.1965) loss: 0.9790 (0.9805) time: 0.1722 data: 0.0944 max mem: 9394 +Train: [3] [2600/6250] eta: 0:08:32 lr: 0.000085 grad: 0.1538 (0.1963) loss: 0.9758 (0.9804) time: 0.1323 data: 0.0399 max mem: 9394 +Train: [3] [2700/6250] eta: 0:08:17 lr: 0.000086 grad: 0.2147 (0.1966) loss: 0.9771 (0.9803) time: 0.1597 data: 0.0804 max mem: 9394 +Train: [3] [2800/6250] eta: 0:08:03 lr: 0.000086 grad: 0.1438 (0.1964) loss: 0.9809 (0.9802) time: 0.1184 data: 0.0403 max mem: 9394 +Train: [3] [2900/6250] eta: 0:07:49 lr: 0.000087 grad: 0.1392 (0.1956) loss: 0.9784 (0.9801) time: 0.1328 data: 0.0515 max mem: 9394 +Train: [3] [3000/6250] eta: 0:07:34 lr: 0.000087 grad: 0.2242 (0.1956) loss: 0.9800 (0.9801) time: 0.1385 data: 0.0609 max mem: 9394 +Train: [3] [3100/6250] eta: 0:07:21 lr: 0.000087 grad: 0.1637 (0.1953) loss: 0.9782 (0.9800) time: 0.1629 data: 0.0841 max mem: 9394 +Train: [3] [3200/6250] eta: 0:07:07 lr: 0.000088 grad: 0.1358 (0.1956) loss: 0.9780 (0.9799) time: 0.1183 data: 0.0390 max mem: 9394 +Train: [3] [3300/6250] eta: 0:06:54 lr: 0.000088 grad: 0.1491 (0.1947) loss: 0.9771 (0.9798) time: 0.1433 data: 0.0579 max mem: 9394 +Train: [3] [3400/6250] eta: 0:06:39 lr: 0.000089 grad: 0.1546 (0.1950) loss: 0.9758 (0.9798) time: 0.1083 data: 0.0312 max mem: 9394 +Train: [3] [3500/6250] eta: 0:06:25 lr: 0.000089 grad: 0.2128 (0.1953) loss: 0.9770 (0.9796) time: 0.1319 data: 0.0495 max mem: 9394 +Train: [3] [3600/6250] eta: 0:06:11 lr: 0.000089 grad: 0.1854 (0.1949) loss: 0.9746 (0.9795) time: 0.1238 data: 0.0432 max mem: 9394 +Train: [3] [3700/6250] eta: 0:05:57 lr: 0.000090 grad: 0.1522 (0.1945) loss: 0.9774 (0.9794) time: 0.1119 data: 0.0314 max mem: 9394 +Train: [3] [3800/6250] eta: 0:05:42 lr: 0.000090 grad: 0.1741 (0.1946) loss: 0.9791 (0.9793) time: 0.1265 data: 0.0480 max mem: 9394 +Train: [3] [3900/6250] eta: 0:05:28 lr: 0.000091 grad: 0.2816 (0.1948) loss: 0.9778 (0.9793) time: 0.1510 data: 0.0711 max mem: 9394 +Train: [3] [4000/6250] eta: 0:05:13 lr: 0.000091 grad: 0.1300 (0.1948) loss: 0.9750 (0.9792) time: 0.1396 data: 0.0599 max mem: 9394 +Train: [3] [4100/6250] eta: 0:04:59 lr: 0.000091 grad: 0.1299 (0.1944) loss: 0.9738 (0.9791) time: 0.1577 data: 0.0794 max mem: 9394 +Train: [3] [4200/6250] eta: 0:04:45 lr: 0.000092 grad: 0.1340 (0.1942) loss: 0.9766 (0.9791) time: 0.1230 data: 0.0384 max mem: 9394 +Train: [3] [4300/6250] eta: 0:04:30 lr: 0.000092 grad: 0.1595 (0.1941) loss: 0.9758 (0.9790) time: 0.1263 data: 0.0497 max mem: 9394 +Train: [3] [4400/6250] eta: 0:04:17 lr: 0.000093 grad: 0.1877 (0.1938) loss: 0.9739 (0.9789) time: 0.1638 data: 0.0811 max mem: 9394 +Train: [3] [4500/6250] eta: 0:04:02 lr: 0.000093 grad: 0.1508 (0.1939) loss: 0.9753 (0.9789) time: 0.1402 data: 0.0617 max mem: 9394 +Train: [3] [4600/6250] eta: 0:03:48 lr: 0.000093 grad: 0.1614 (0.1934) loss: 0.9789 (0.9788) time: 0.1317 data: 0.0448 max mem: 9394 +Train: [3] [4700/6250] eta: 0:03:34 lr: 0.000094 grad: 0.1865 (0.1932) loss: 0.9779 (0.9788) time: 0.1227 data: 0.0430 max mem: 9394 +Train: [3] [4800/6250] eta: 0:03:21 lr: 0.000094 grad: 0.1413 (0.1933) loss: 0.9731 (0.9787) time: 0.1328 data: 0.0560 max mem: 9394 +Train: [3] [4900/6250] eta: 0:03:07 lr: 0.000095 grad: 0.1104 (0.1929) loss: 0.9753 (0.9786) time: 0.1325 data: 0.0533 max mem: 9394 +Train: [3] [5000/6250] eta: 0:02:53 lr: 0.000095 grad: 0.1385 (0.1924) loss: 0.9766 (0.9786) time: 0.1351 data: 0.0588 max mem: 9394 +Train: [3] [5100/6250] eta: 0:02:39 lr: 0.000095 grad: 0.2080 (0.1927) loss: 0.9774 (0.9785) time: 0.1256 data: 0.0484 max mem: 9394 +Train: [3] [5200/6250] eta: 0:02:25 lr: 0.000096 grad: 0.1785 (0.1927) loss: 0.9718 (0.9784) time: 0.1558 data: 0.0802 max mem: 9394 +Train: [3] [5300/6250] eta: 0:02:11 lr: 0.000096 grad: 0.1609 (0.1929) loss: 0.9741 (0.9783) time: 0.1267 data: 0.0427 max mem: 9394 +Train: [3] [5400/6250] eta: 0:01:57 lr: 0.000097 grad: 0.1783 (0.1931) loss: 0.9770 (0.9783) time: 0.1623 data: 0.0819 max mem: 9394 +Train: [3] [5500/6250] eta: 0:01:43 lr: 0.000097 grad: 0.1371 (0.1928) loss: 0.9719 (0.9782) time: 0.1388 data: 0.0627 max mem: 9394 +Train: [3] [5600/6250] eta: 0:01:30 lr: 0.000097 grad: 0.1597 (0.1925) loss: 0.9719 (0.9781) time: 0.1309 data: 0.0511 max mem: 9394 +Train: [3] [5700/6250] eta: 0:01:16 lr: 0.000098 grad: 0.1546 (0.1923) loss: 0.9736 (0.9781) time: 0.1307 data: 0.0530 max mem: 9394 +Train: [3] [5800/6250] eta: 0:01:02 lr: 0.000098 grad: 0.1358 (0.1922) loss: 0.9723 (0.9780) time: 0.1579 data: 0.0842 max mem: 9394 +Train: [3] [5900/6250] eta: 0:00:48 lr: 0.000099 grad: 0.1447 (0.1916) loss: 0.9753 (0.9779) time: 0.1396 data: 0.0625 max mem: 9394 +Train: [3] [6000/6250] eta: 0:00:34 lr: 0.000099 grad: 0.1696 (0.1915) loss: 0.9762 (0.9779) time: 0.1280 data: 0.0536 max mem: 9394 +Train: [3] [6100/6250] eta: 0:00:20 lr: 0.000099 grad: 0.1121 (0.1910) loss: 0.9751 (0.9778) time: 0.1370 data: 0.0601 max mem: 9394 +Train: [3] [6200/6250] eta: 0:00:06 lr: 0.000100 grad: 0.1197 (0.1907) loss: 0.9721 (0.9777) time: 0.1367 data: 0.0581 max mem: 9394 +Train: [3] [6249/6250] eta: 0:00:00 lr: 0.000100 grad: 0.1475 (0.1905) loss: 0.9738 (0.9777) time: 0.1975 data: 0.1239 max mem: 9394 +Train: [3] Total time: 0:14:33 (0.1397 s / it) +Averaged stats: lr: 0.000100 grad: 0.1475 (0.1905) loss: 0.9738 (0.9777) +Eval (hcp-train-subset): [3] [ 0/62] eta: 0:04:19 loss: 0.9795 (0.9795) time: 4.1860 data: 4.1574 max mem: 9394 +Eval (hcp-train-subset): [3] [61/62] eta: 0:00:00 loss: 0.9765 (0.9757) time: 0.1231 data: 0.0983 max mem: 9394 +Eval (hcp-train-subset): [3] Total time: 0:00:12 (0.1953 s / it) +Averaged stats (hcp-train-subset): loss: 0.9765 (0.9757) +Eval (hcp-val): [3] [ 0/62] eta: 0:04:12 loss: 0.9692 (0.9692) time: 4.0783 data: 4.0497 max mem: 9394 +Eval (hcp-val): [3] [61/62] eta: 0:00:00 loss: 0.9732 (0.9731) time: 0.1472 data: 0.1224 max mem: 9394 +Eval (hcp-val): [3] Total time: 0:00:12 (0.1983 s / it) +Averaged stats (hcp-val): loss: 0.9732 (0.9731) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +Train: [4] [ 0/6250] eta: 7:07:18 lr: 0.000100 grad: 0.2034 (0.2034) loss: 0.9718 (0.9718) time: 4.1022 data: 3.8795 max mem: 9394 +Train: [4] [ 100/6250] eta: 0:20:00 lr: 0.000100 grad: 0.1272 (0.1734) loss: 0.9755 (0.9726) time: 0.1461 data: 0.0579 max mem: 9394 +Train: [4] [ 200/6250] eta: 0:17:10 lr: 0.000101 grad: 0.1255 (0.1739) loss: 0.9724 (0.9735) time: 0.1578 data: 0.0756 max mem: 9394 +Train: [4] [ 300/6250] eta: 0:15:56 lr: 0.000101 grad: 0.1365 (0.1672) loss: 0.9749 (0.9734) time: 0.1599 data: 0.0801 max mem: 9394 +Train: [4] [ 400/6250] eta: 0:14:45 lr: 0.000102 grad: 0.1772 (0.1684) loss: 0.9733 (0.9731) time: 0.1127 data: 0.0201 max mem: 9394 +Train: [4] [ 500/6250] eta: 0:14:02 lr: 0.000102 grad: 0.1887 (0.1698) loss: 0.9682 (0.9725) time: 0.1357 data: 0.0524 max mem: 9394 +Train: [4] [ 600/6250] eta: 0:13:27 lr: 0.000102 grad: 0.1426 (0.1758) loss: 0.9715 (0.9721) time: 0.1260 data: 0.0433 max mem: 9394 +Train: [4] [ 700/6250] eta: 0:13:03 lr: 0.000103 grad: 0.1629 (0.1815) loss: 0.9683 (0.9717) time: 0.1255 data: 0.0346 max mem: 9394 +Train: [4] [ 800/6250] eta: 0:12:50 lr: 0.000103 grad: 0.1520 (0.1817) loss: 0.9696 (0.9714) time: 0.1362 data: 0.0369 max mem: 9394 +Train: [4] [ 900/6250] eta: 0:12:36 lr: 0.000104 grad: 0.1865 (0.1850) loss: 0.9688 (0.9711) time: 0.1444 data: 0.0659 max mem: 9394 +Train: [4] [1000/6250] eta: 0:12:25 lr: 0.000104 grad: 0.1953 (0.1878) loss: 0.9708 (0.9708) time: 0.1439 data: 0.0658 max mem: 9394 +Train: [4] [1100/6250] eta: 0:12:17 lr: 0.000104 grad: 0.1459 (0.1862) loss: 0.9669 (0.9705) time: 0.1816 data: 0.0990 max mem: 9394 +Train: [4] [1200/6250] eta: 0:11:59 lr: 0.000105 grad: 0.1469 (0.1869) loss: 0.9674 (0.9702) time: 0.1114 data: 0.0266 max mem: 9394 +Train: [4] [1300/6250] eta: 0:11:48 lr: 0.000105 grad: 0.1947 (0.1863) loss: 0.9669 (0.9698) time: 0.1755 data: 0.0708 max mem: 9394 +Train: [4] [1400/6250] eta: 0:11:34 lr: 0.000106 grad: 0.1605 (0.1868) loss: 0.9617 (0.9695) time: 0.1207 data: 0.0405 max mem: 9394 +Train: [4] [1500/6250] eta: 0:11:18 lr: 0.000106 grad: 0.1841 (0.1875) loss: 0.9652 (0.9692) time: 0.1247 data: 0.0420 max mem: 9394 +Train: [4] [1600/6250] eta: 0:11:03 lr: 0.000106 grad: 0.2086 (0.1879) loss: 0.9652 (0.9689) time: 0.1473 data: 0.0659 max mem: 9394 +Train: [4] [1700/6250] eta: 0:10:46 lr: 0.000107 grad: 0.1716 (0.1889) loss: 0.9658 (0.9685) time: 0.1372 data: 0.0568 max mem: 9394 +Train: [4] [1800/6250] eta: 0:10:31 lr: 0.000107 grad: 0.1408 (0.1888) loss: 0.9623 (0.9682) time: 0.1281 data: 0.0453 max mem: 9394 +Train: [4] [1900/6250] eta: 0:10:16 lr: 0.000108 grad: 0.1723 (0.1900) loss: 0.9610 (0.9678) time: 0.1249 data: 0.0451 max mem: 9394 +Train: [4] [2000/6250] eta: 0:10:02 lr: 0.000108 grad: 0.1737 (0.1904) loss: 0.9604 (0.9675) time: 0.1569 data: 0.0806 max mem: 9394 +Train: [4] [2100/6250] eta: 0:09:47 lr: 0.000108 grad: 0.1889 (0.1909) loss: 0.9582 (0.9671) time: 0.1373 data: 0.0548 max mem: 9394 +Train: [4] [2200/6250] eta: 0:09:33 lr: 0.000109 grad: 0.2330 (0.1925) loss: 0.9620 (0.9667) time: 0.1336 data: 0.0465 max mem: 9394 +Train: [4] [2300/6250] eta: 0:09:18 lr: 0.000109 grad: 0.1814 (0.1940) loss: 0.9578 (0.9664) time: 0.1356 data: 0.0609 max mem: 9394 +Train: [4] [2400/6250] eta: 0:09:04 lr: 0.000110 grad: 0.1700 (0.1954) loss: 0.9553 (0.9660) time: 0.1448 data: 0.0608 max mem: 9394 +Train: [4] [2500/6250] eta: 0:08:50 lr: 0.000110 grad: 0.2276 (0.1977) loss: 0.9545 (0.9656) time: 0.1471 data: 0.0702 max mem: 9394 +Train: [4] [2600/6250] eta: 0:08:35 lr: 0.000110 grad: 0.2072 (0.1989) loss: 0.9518 (0.9652) time: 0.1262 data: 0.0470 max mem: 9394 +Train: [4] [2700/6250] eta: 0:08:21 lr: 0.000111 grad: 0.1588 (0.1992) loss: 0.9512 (0.9647) time: 0.1366 data: 0.0597 max mem: 9394 +Train: [4] [2800/6250] eta: 0:08:08 lr: 0.000111 grad: 0.2824 (0.2012) loss: 0.9546 (0.9643) time: 0.1481 data: 0.0716 max mem: 9394 +Train: [4] [2900/6250] eta: 0:07:53 lr: 0.000112 grad: 0.3062 (0.2032) loss: 0.9501 (0.9639) time: 0.1472 data: 0.0653 max mem: 9394 +Train: [4] [3000/6250] eta: 0:07:38 lr: 0.000112 grad: 0.1950 (0.2050) loss: 0.9511 (0.9635) time: 0.1360 data: 0.0561 max mem: 9394 +Train: [4] [3100/6250] eta: 0:07:23 lr: 0.000112 grad: 0.1851 (0.2066) loss: 0.9480 (0.9630) time: 0.1306 data: 0.0450 max mem: 9394 +Train: [4] [3200/6250] eta: 0:07:09 lr: 0.000113 grad: 0.2162 (0.2084) loss: 0.9471 (0.9625) time: 0.1418 data: 0.0637 max mem: 9394 +Train: [4] [3300/6250] eta: 0:06:55 lr: 0.000113 grad: 0.2364 (0.2097) loss: 0.9471 (0.9620) time: 0.1313 data: 0.0534 max mem: 9394 +Train: [4] [3400/6250] eta: 0:06:40 lr: 0.000114 grad: 0.2136 (0.2107) loss: 0.9458 (0.9616) time: 0.1517 data: 0.0744 max mem: 9394 +Train: [4] [3500/6250] eta: 0:06:26 lr: 0.000114 grad: 0.2078 (0.2118) loss: 0.9436 (0.9611) time: 0.1150 data: 0.0377 max mem: 9394 +Train: [4] [3600/6250] eta: 0:06:11 lr: 0.000114 grad: 0.2586 (0.2130) loss: 0.9469 (0.9606) time: 0.1454 data: 0.0611 max mem: 9394 +Train: [4] [3700/6250] eta: 0:05:57 lr: 0.000115 grad: 0.2537 (0.2144) loss: 0.9434 (0.9601) time: 0.1490 data: 0.0686 max mem: 9394 +Train: [4] [3800/6250] eta: 0:05:42 lr: 0.000115 grad: 0.2184 (0.2149) loss: 0.9395 (0.9596) time: 0.1269 data: 0.0459 max mem: 9394 +Train: [4] [3900/6250] eta: 0:05:27 lr: 0.000116 grad: 0.2140 (0.2152) loss: 0.9421 (0.9592) time: 0.1391 data: 0.0658 max mem: 9394 +Train: [4] [4000/6250] eta: 0:05:13 lr: 0.000116 grad: 0.1869 (0.2156) loss: 0.9415 (0.9587) time: 0.1265 data: 0.0414 max mem: 9394 +Train: [4] [4100/6250] eta: 0:04:59 lr: 0.000116 grad: 0.1952 (0.2162) loss: 0.9367 (0.9582) time: 0.1476 data: 0.0713 max mem: 9394 +Train: [4] [4200/6250] eta: 0:04:45 lr: 0.000117 grad: 0.1924 (0.2165) loss: 0.9433 (0.9578) time: 0.1533 data: 0.0765 max mem: 9394 +Train: [4] [4300/6250] eta: 0:04:31 lr: 0.000117 grad: 0.2459 (0.2170) loss: 0.9354 (0.9573) time: 0.1139 data: 0.0265 max mem: 9394 +Train: [4] [4400/6250] eta: 0:04:17 lr: 0.000118 grad: 0.2174 (0.2173) loss: 0.9340 (0.9568) time: 0.1406 data: 0.0534 max mem: 9394 +Train: [4] [4500/6250] eta: 0:04:03 lr: 0.000118 grad: 0.2622 (0.2177) loss: 0.9375 (0.9564) time: 0.1540 data: 0.0695 max mem: 9394 +Train: [4] [4600/6250] eta: 0:03:48 lr: 0.000118 grad: 0.1753 (0.2176) loss: 0.9352 (0.9559) time: 0.1266 data: 0.0487 max mem: 9394 +Train: [4] [4700/6250] eta: 0:03:34 lr: 0.000119 grad: 0.1908 (0.2176) loss: 0.9346 (0.9554) time: 0.1390 data: 0.0494 max mem: 9394 +Train: [4] [4800/6250] eta: 0:03:21 lr: 0.000119 grad: 0.1736 (0.2177) loss: 0.9343 (0.9549) time: 0.1353 data: 0.0542 max mem: 9394 +Train: [4] [4900/6250] eta: 0:03:07 lr: 0.000120 grad: 0.1739 (0.2178) loss: 0.9294 (0.9545) time: 0.1300 data: 0.0504 max mem: 9394 +Train: [4] [5000/6250] eta: 0:02:53 lr: 0.000120 grad: 0.1919 (0.2176) loss: 0.9297 (0.9540) time: 0.1453 data: 0.0680 max mem: 9394 +Train: [4] [5100/6250] eta: 0:02:39 lr: 0.000120 grad: 0.2042 (0.2181) loss: 0.9284 (0.9535) time: 0.1223 data: 0.0418 max mem: 9394 +Train: [4] [5200/6250] eta: 0:02:25 lr: 0.000121 grad: 0.2067 (0.2180) loss: 0.9287 (0.9531) time: 0.1347 data: 0.0545 max mem: 9394 +Train: [4] [5300/6250] eta: 0:02:12 lr: 0.000121 grad: 0.2112 (0.2179) loss: 0.9275 (0.9526) time: 0.2033 data: 0.1238 max mem: 9394 +Train: [4] [5400/6250] eta: 0:01:58 lr: 0.000122 grad: 0.1732 (0.2179) loss: 0.9301 (0.9522) time: 0.1332 data: 0.0541 max mem: 9394 +Train: [4] [5500/6250] eta: 0:01:44 lr: 0.000122 grad: 0.1855 (0.2178) loss: 0.9266 (0.9517) time: 0.1414 data: 0.0648 max mem: 9394 +Train: [4] [5600/6250] eta: 0:01:30 lr: 0.000122 grad: 0.1724 (0.2173) loss: 0.9237 (0.9512) time: 0.1495 data: 0.0689 max mem: 9394 +Train: [4] [5700/6250] eta: 0:01:16 lr: 0.000123 grad: 0.1661 (0.2171) loss: 0.9232 (0.9508) time: 0.1207 data: 0.0428 max mem: 9394 +Train: [4] [5800/6250] eta: 0:01:02 lr: 0.000123 grad: 0.1690 (0.2165) loss: 0.9272 (0.9504) time: 0.1306 data: 0.0531 max mem: 9394 +Train: [4] [5900/6250] eta: 0:00:48 lr: 0.000124 grad: 0.1774 (0.2163) loss: 0.9239 (0.9500) time: 0.1485 data: 0.0674 max mem: 9394 +Train: [4] [6000/6250] eta: 0:00:34 lr: 0.000124 grad: 0.2143 (0.2162) loss: 0.9234 (0.9495) time: 0.1200 data: 0.0414 max mem: 9394 +Train: [4] [6100/6250] eta: 0:00:20 lr: 0.000124 grad: 0.1712 (0.2159) loss: 0.9223 (0.9491) time: 0.1373 data: 0.0563 max mem: 9394 +Train: [4] [6200/6250] eta: 0:00:06 lr: 0.000125 grad: 0.1736 (0.2154) loss: 0.9237 (0.9487) time: 0.1813 data: 0.1066 max mem: 9394 +Train: [4] [6249/6250] eta: 0:00:00 lr: 0.000125 grad: 0.1727 (0.2155) loss: 0.9237 (0.9485) time: 0.1624 data: 0.0743 max mem: 9394 +Train: [4] Total time: 0:14:37 (0.1404 s / it) +Averaged stats: lr: 0.000125 grad: 0.1727 (0.2155) loss: 0.9237 (0.9485) +Eval (hcp-train-subset): [4] [ 0/62] eta: 0:04:02 loss: 0.9305 (0.9305) time: 3.9036 data: 3.8710 max mem: 9394 +Eval (hcp-train-subset): [4] [61/62] eta: 0:00:00 loss: 0.9266 (0.9248) time: 0.1222 data: 0.0974 max mem: 9394 +Eval (hcp-train-subset): [4] Total time: 0:00:13 (0.2145 s / it) +Averaged stats (hcp-train-subset): loss: 0.9266 (0.9248) +Making plots (hcp-train-subset): example=39 +Eval (hcp-val): [4] [ 0/62] eta: 0:04:27 loss: 0.9155 (0.9155) time: 4.3172 data: 4.2857 max mem: 9394 +Eval (hcp-val): [4] [61/62] eta: 0:00:00 loss: 0.9176 (0.9188) time: 0.1341 data: 0.1073 max mem: 9394 +Eval (hcp-val): [4] Total time: 0:00:12 (0.1992 s / it) +Averaged stats (hcp-val): loss: 0.9176 (0.9188) +Making plots (hcp-val): example=55 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +Train: [5] [ 0/6250] eta: 8:04:14 lr: 0.000125 grad: 0.1311 (0.1311) loss: 0.9192 (0.9192) time: 4.6488 data: 4.4817 max mem: 9394 +Train: [5] [ 100/6250] eta: 0:19:22 lr: 0.000125 grad: 0.1616 (0.2042) loss: 0.9185 (0.9275) time: 0.1332 data: 0.0472 max mem: 9394 +Train: [5] [ 200/6250] eta: 0:16:23 lr: 0.000125 grad: 0.2055 (0.2056) loss: 0.9224 (0.9257) time: 0.1243 data: 0.0461 max mem: 9394 +Train: [5] [ 300/6250] eta: 0:15:11 lr: 0.000125 grad: 0.1476 (0.1986) loss: 0.9230 (0.9246) time: 0.1576 data: 0.0790 max mem: 9394 +Train: [5] [ 400/6250] eta: 0:14:11 lr: 0.000125 grad: 0.1673 (0.1947) loss: 0.9287 (0.9245) time: 0.1223 data: 0.0361 max mem: 9394 +Train: [5] [ 500/6250] eta: 0:13:32 lr: 0.000125 grad: 0.1798 (0.1928) loss: 0.9249 (0.9242) time: 0.1007 data: 0.0175 max mem: 9394 +Train: [5] [ 600/6250] eta: 0:13:03 lr: 0.000125 grad: 0.1609 (0.1889) loss: 0.9210 (0.9238) time: 0.1172 data: 0.0338 max mem: 9394 +Train: [5] [ 700/6250] eta: 0:12:37 lr: 0.000125 grad: 0.1593 (0.1849) loss: 0.9138 (0.9232) time: 0.1255 data: 0.0435 max mem: 9394 +Train: [5] [ 800/6250] eta: 0:12:29 lr: 0.000125 grad: 0.1381 (0.1832) loss: 0.9231 (0.9230) time: 0.1266 data: 0.0418 max mem: 9394 +Train: [5] [ 900/6250] eta: 0:12:20 lr: 0.000125 grad: 0.1554 (0.1809) loss: 0.9198 (0.9226) time: 0.1416 data: 0.0549 max mem: 9394 +Train: [5] [1000/6250] eta: 0:12:08 lr: 0.000125 grad: 0.1820 (0.1800) loss: 0.9214 (0.9224) time: 0.1404 data: 0.0614 max mem: 9394 +Train: [5] [1100/6250] eta: 0:12:01 lr: 0.000125 grad: 0.1505 (0.1793) loss: 0.9204 (0.9222) time: 0.1438 data: 0.0619 max mem: 9394 +Train: [5] [1200/6250] eta: 0:11:53 lr: 0.000125 grad: 0.1302 (0.1773) loss: 0.9193 (0.9220) time: 0.1675 data: 0.0871 max mem: 9394 +Train: [5] [1300/6250] eta: 0:11:37 lr: 0.000125 grad: 0.1415 (0.1759) loss: 0.9168 (0.9217) time: 0.1549 data: 0.0762 max mem: 9394 +Train: [5] [1400/6250] eta: 0:11:20 lr: 0.000125 grad: 0.1749 (0.1754) loss: 0.9190 (0.9213) time: 0.1708 data: 0.0761 max mem: 9394 +Train: [5] [1500/6250] eta: 0:11:08 lr: 0.000125 grad: 0.1399 (0.1746) loss: 0.9133 (0.9209) time: 0.1685 data: 0.0877 max mem: 9394 +Train: [5] [1600/6250] eta: 0:10:51 lr: 0.000125 grad: 0.1469 (0.1738) loss: 0.9158 (0.9206) time: 0.1373 data: 0.0585 max mem: 9394 +Train: [5] [1700/6250] eta: 0:10:35 lr: 0.000125 grad: 0.1485 (0.1730) loss: 0.9132 (0.9202) time: 0.1354 data: 0.0551 max mem: 9394 +Train: [5] [1800/6250] eta: 0:10:31 lr: 0.000125 grad: 0.1366 (0.1723) loss: 0.9126 (0.9200) time: 0.2256 data: 0.1491 max mem: 9394 +Train: [5] [1900/6250] eta: 0:10:13 lr: 0.000125 grad: 0.1563 (0.1723) loss: 0.9150 (0.9196) time: 0.1423 data: 0.0638 max mem: 9394 +Train: [5] [2000/6250] eta: 0:09:57 lr: 0.000125 grad: 0.1506 (0.1723) loss: 0.9129 (0.9193) time: 0.1410 data: 0.0662 max mem: 9394 +Train: [5] [2100/6250] eta: 0:09:43 lr: 0.000125 grad: 0.1352 (0.1715) loss: 0.9148 (0.9190) time: 0.1270 data: 0.0508 max mem: 9394 +Train: [5] [2200/6250] eta: 0:09:28 lr: 0.000125 grad: 0.1445 (0.1710) loss: 0.9107 (0.9186) time: 0.1019 data: 0.0225 max mem: 9394 +Train: [5] [2300/6250] eta: 0:09:15 lr: 0.000125 grad: 0.1515 (0.1706) loss: 0.9101 (0.9183) time: 0.1404 data: 0.0614 max mem: 9394 +Train: [5] [2400/6250] eta: 0:09:00 lr: 0.000125 grad: 0.1595 (0.1697) loss: 0.9153 (0.9180) time: 0.1480 data: 0.0670 max mem: 9394 +Train: [5] [2500/6250] eta: 0:08:45 lr: 0.000125 grad: 0.1722 (0.1696) loss: 0.9090 (0.9176) time: 0.1335 data: 0.0582 max mem: 9394 +Train: [5] [2600/6250] eta: 0:08:30 lr: 0.000125 grad: 0.1343 (0.1690) loss: 0.9055 (0.9172) time: 0.1403 data: 0.0535 max mem: 9394 +Train: [5] [2700/6250] eta: 0:08:15 lr: 0.000125 grad: 0.1508 (0.1689) loss: 0.9013 (0.9167) time: 0.1356 data: 0.0559 max mem: 9394 +Train: [5] [2800/6250] eta: 0:08:01 lr: 0.000125 grad: 0.1953 (0.1688) loss: 0.9048 (0.9163) time: 0.1339 data: 0.0570 max mem: 9394 +Train: [5] [2900/6250] eta: 0:07:47 lr: 0.000125 grad: 0.1410 (0.1684) loss: 0.9005 (0.9159) time: 0.1452 data: 0.0629 max mem: 9394 +Train: [5] [3000/6250] eta: 0:07:33 lr: 0.000125 grad: 0.1539 (0.1683) loss: 0.8986 (0.9154) time: 0.1514 data: 0.0685 max mem: 9394 +Train: [5] [3100/6250] eta: 0:07:20 lr: 0.000125 grad: 0.1395 (0.1677) loss: 0.8997 (0.9149) time: 0.1727 data: 0.0949 max mem: 9394 +Train: [5] [3200/6250] eta: 0:07:04 lr: 0.000125 grad: 0.1624 (0.1675) loss: 0.8993 (0.9145) time: 0.1390 data: 0.0579 max mem: 9394 +Train: [5] [3300/6250] eta: 0:06:51 lr: 0.000125 grad: 0.1432 (0.1671) loss: 0.8987 (0.9140) time: 0.1461 data: 0.0741 max mem: 9394 +Train: [5] [3400/6250] eta: 0:06:37 lr: 0.000125 grad: 0.1475 (0.1669) loss: 0.8964 (0.9135) time: 0.1192 data: 0.0419 max mem: 9394 +Train: [5] [3500/6250] eta: 0:06:23 lr: 0.000125 grad: 0.1269 (0.1668) loss: 0.8981 (0.9130) time: 0.1505 data: 0.0683 max mem: 9394 +Train: [5] [3600/6250] eta: 0:06:08 lr: 0.000125 grad: 0.1523 (0.1663) loss: 0.8957 (0.9126) time: 0.1334 data: 0.0526 max mem: 9394 +Train: [5] [3700/6250] eta: 0:05:54 lr: 0.000125 grad: 0.1329 (0.1663) loss: 0.8896 (0.9122) time: 0.1294 data: 0.0480 max mem: 9394 +Train: [5] [3800/6250] eta: 0:05:40 lr: 0.000125 grad: 0.1366 (0.1660) loss: 0.8943 (0.9117) time: 0.1400 data: 0.0596 max mem: 9394 +Train: [5] [3900/6250] eta: 0:05:25 lr: 0.000125 grad: 0.1336 (0.1654) loss: 0.8942 (0.9112) time: 0.1278 data: 0.0510 max mem: 9394 +Train: [5] [4000/6250] eta: 0:05:11 lr: 0.000125 grad: 0.1246 (0.1647) loss: 0.8950 (0.9108) time: 0.1381 data: 0.0612 max mem: 9394 +Train: [5] [4100/6250] eta: 0:04:57 lr: 0.000125 grad: 0.1267 (0.1640) loss: 0.8956 (0.9104) time: 0.1376 data: 0.0557 max mem: 9394 +Train: [5] [4200/6250] eta: 0:04:43 lr: 0.000125 grad: 0.1169 (0.1634) loss: 0.8945 (0.9100) time: 0.1387 data: 0.0581 max mem: 9394 +Train: [5] [4300/6250] eta: 0:04:29 lr: 0.000125 grad: 0.1400 (0.1631) loss: 0.8905 (0.9096) time: 0.1518 data: 0.0772 max mem: 9394 +Train: [5] [4400/6250] eta: 0:04:15 lr: 0.000125 grad: 0.1263 (0.1627) loss: 0.8874 (0.9092) time: 0.1396 data: 0.0576 max mem: 9394 +Train: [5] [4500/6250] eta: 0:04:01 lr: 0.000125 grad: 0.1504 (0.1623) loss: 0.8895 (0.9088) time: 0.1405 data: 0.0637 max mem: 9394 +Train: [5] [4600/6250] eta: 0:03:47 lr: 0.000125 grad: 0.1304 (0.1620) loss: 0.8915 (0.9084) time: 0.1428 data: 0.0679 max mem: 9394 +Train: [5] [4700/6250] eta: 0:03:33 lr: 0.000125 grad: 0.1240 (0.1613) loss: 0.8828 (0.9080) time: 0.1347 data: 0.0518 max mem: 9394 +Train: [5] [4800/6250] eta: 0:03:19 lr: 0.000125 grad: 0.1454 (0.1609) loss: 0.8872 (0.9075) time: 0.1579 data: 0.0759 max mem: 9394 +Train: [5] [4900/6250] eta: 0:03:05 lr: 0.000125 grad: 0.1313 (0.1606) loss: 0.8858 (0.9071) time: 0.1282 data: 0.0545 max mem: 9394 +Train: [5] [5000/6250] eta: 0:02:51 lr: 0.000125 grad: 0.1440 (0.1602) loss: 0.8900 (0.9067) time: 0.1159 data: 0.0352 max mem: 9394 +Train: [5] [5100/6250] eta: 0:02:37 lr: 0.000125 grad: 0.1219 (0.1596) loss: 0.8889 (0.9063) time: 0.1461 data: 0.0595 max mem: 9394 +Train: [5] [5200/6250] eta: 0:02:24 lr: 0.000125 grad: 0.1226 (0.1593) loss: 0.8853 (0.9059) time: 0.1437 data: 0.0636 max mem: 9394 +Train: [5] [5300/6250] eta: 0:02:10 lr: 0.000125 grad: 0.1241 (0.1589) loss: 0.8802 (0.9055) time: 0.1432 data: 0.0656 max mem: 9394 +Train: [5] [5400/6250] eta: 0:01:56 lr: 0.000125 grad: 0.1336 (0.1587) loss: 0.8856 (0.9052) time: 0.1222 data: 0.0409 max mem: 9394 +Train: [5] [5500/6250] eta: 0:01:42 lr: 0.000125 grad: 0.1234 (0.1580) loss: 0.8824 (0.9048) time: 0.1276 data: 0.0494 max mem: 9394 +Train: [5] [5600/6250] eta: 0:01:29 lr: 0.000125 grad: 0.1130 (0.1574) loss: 0.8825 (0.9045) time: 0.1572 data: 0.0832 max mem: 9394 +Train: [5] [5700/6250] eta: 0:01:15 lr: 0.000125 grad: 0.1221 (0.1572) loss: 0.8841 (0.9041) time: 0.1472 data: 0.0755 max mem: 9394 +Train: [5] [5800/6250] eta: 0:01:01 lr: 0.000125 grad: 0.1086 (0.1566) loss: 0.8860 (0.9038) time: 0.1245 data: 0.0476 max mem: 9394 +Train: [5] [5900/6250] eta: 0:00:47 lr: 0.000125 grad: 0.1096 (0.1561) loss: 0.8833 (0.9034) time: 0.1207 data: 0.0349 max mem: 9394 +Train: [5] [6000/6250] eta: 0:00:34 lr: 0.000125 grad: 0.1043 (0.1556) loss: 0.8847 (0.9030) time: 0.1060 data: 0.0197 max mem: 9394 +Train: [5] [6100/6250] eta: 0:00:20 lr: 0.000125 grad: 0.1231 (0.1551) loss: 0.8852 (0.9027) time: 0.1337 data: 0.0526 max mem: 9394 +Train: [5] [6200/6250] eta: 0:00:06 lr: 0.000125 grad: 0.1052 (0.1545) loss: 0.8845 (0.9024) time: 0.1729 data: 0.0951 max mem: 9394 +Train: [5] [6249/6250] eta: 0:00:00 lr: 0.000125 grad: 0.1084 (0.1543) loss: 0.8779 (0.9022) time: 0.1818 data: 0.1026 max mem: 9394 +Train: [5] Total time: 0:14:25 (0.1385 s / it) +Averaged stats: lr: 0.000125 grad: 0.1084 (0.1543) loss: 0.8779 (0.9022) +Eval (hcp-train-subset): [5] [ 0/62] eta: 0:02:50 loss: 0.8900 (0.8900) time: 2.7564 data: 2.6602 max mem: 9394 +Eval (hcp-train-subset): [5] [61/62] eta: 0:00:00 loss: 0.8836 (0.8846) time: 0.1185 data: 0.0938 max mem: 9394 +Eval (hcp-train-subset): [5] Total time: 0:00:13 (0.2218 s / it) +Averaged stats (hcp-train-subset): loss: 0.8836 (0.8846) +Eval (hcp-val): [5] [ 0/62] eta: 0:04:39 loss: 0.8727 (0.8727) time: 4.5002 data: 4.4708 max mem: 9394 +Eval (hcp-val): [5] [61/62] eta: 0:00:00 loss: 0.8780 (0.8782) time: 0.1404 data: 0.1159 max mem: 9394 +Eval (hcp-val): [5] Total time: 0:00:12 (0.2084 s / it) +Averaged stats (hcp-val): loss: 0.8780 (0.8782) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +Train: [6] [ 0/6250] eta: 10:11:18 lr: 0.000125 grad: 0.0608 (0.0608) loss: 0.9159 (0.9159) time: 5.8685 data: 5.7746 max mem: 9394 +Train: [6] [ 100/6250] eta: 0:19:42 lr: 0.000125 grad: 0.1084 (0.1332) loss: 0.8866 (0.8817) time: 0.1672 data: 0.0821 max mem: 9394 +Train: [6] [ 200/6250] eta: 0:16:08 lr: 0.000125 grad: 0.1150 (0.1280) loss: 0.8866 (0.8839) time: 0.1388 data: 0.0592 max mem: 9394 +Train: [6] [ 300/6250] eta: 0:14:47 lr: 0.000125 grad: 0.1270 (0.1256) loss: 0.8822 (0.8835) time: 0.1262 data: 0.0389 max mem: 9394 +Train: [6] [ 400/6250] eta: 0:13:59 lr: 0.000125 grad: 0.1234 (0.1267) loss: 0.8847 (0.8832) time: 0.1226 data: 0.0402 max mem: 9394 +Train: [6] [ 500/6250] eta: 0:13:25 lr: 0.000125 grad: 0.1084 (0.1265) loss: 0.8776 (0.8826) time: 0.1256 data: 0.0436 max mem: 9394 +Train: [6] [ 600/6250] eta: 0:12:54 lr: 0.000125 grad: 0.1148 (0.1240) loss: 0.8809 (0.8820) time: 0.1136 data: 0.0229 max mem: 9394 +Train: [6] [ 700/6250] eta: 0:12:43 lr: 0.000125 grad: 0.0988 (0.1235) loss: 0.8764 (0.8814) time: 0.1566 data: 0.0606 max mem: 9394 +Train: [6] [ 800/6250] eta: 0:12:42 lr: 0.000125 grad: 0.0986 (0.1226) loss: 0.8747 (0.8808) time: 0.1514 data: 0.0559 max mem: 9394 +Train: [6] [ 900/6250] eta: 0:12:31 lr: 0.000125 grad: 0.1202 (0.1227) loss: 0.8771 (0.8805) time: 0.1198 data: 0.0317 max mem: 9394 +Train: [6] [1000/6250] eta: 0:12:18 lr: 0.000125 grad: 0.1063 (0.1224) loss: 0.8778 (0.8801) time: 0.1357 data: 0.0598 max mem: 9394 +Train: [6] [1100/6250] eta: 0:12:09 lr: 0.000125 grad: 0.1066 (0.1212) loss: 0.8752 (0.8798) time: 0.1225 data: 0.0416 max mem: 9394 +Train: [6] [1200/6250] eta: 0:11:57 lr: 0.000125 grad: 0.1017 (0.1204) loss: 0.8716 (0.8794) time: 0.1664 data: 0.0741 max mem: 9394 +Train: [6] [1300/6250] eta: 0:11:50 lr: 0.000125 grad: 0.1118 (0.1198) loss: 0.8787 (0.8792) time: 0.1297 data: 0.0512 max mem: 9394 +Train: [6] [1400/6250] eta: 0:11:34 lr: 0.000125 grad: 0.0897 (0.1204) loss: 0.8790 (0.8790) time: 0.1464 data: 0.0537 max mem: 9394 +Train: [6] [1500/6250] eta: 0:11:28 lr: 0.000125 grad: 0.1071 (0.1216) loss: 0.8730 (0.8788) time: 0.2554 data: 0.1693 max mem: 9394 +Train: [6] [1600/6250] eta: 0:11:21 lr: 0.000125 grad: 0.0903 (0.1204) loss: 0.8733 (0.8786) time: 0.1512 data: 0.0718 max mem: 9394 +Train: [6] [1700/6250] eta: 0:11:05 lr: 0.000125 grad: 0.1018 (0.1194) loss: 0.8763 (0.8786) time: 0.1335 data: 0.0549 max mem: 9394 +Train: [6] [1800/6250] eta: 0:10:48 lr: 0.000125 grad: 0.0985 (0.1190) loss: 0.8779 (0.8785) time: 0.1100 data: 0.0258 max mem: 9394 +Train: [6] [1900/6250] eta: 0:10:30 lr: 0.000125 grad: 0.1085 (0.1181) loss: 0.8774 (0.8784) time: 0.1314 data: 0.0488 max mem: 9394 +Train: [6] [2000/6250] eta: 0:10:16 lr: 0.000125 grad: 0.0987 (0.1179) loss: 0.8719 (0.8782) time: 0.1248 data: 0.0380 max mem: 9394 +Train: [6] [2100/6250] eta: 0:10:01 lr: 0.000125 grad: 0.0995 (0.1174) loss: 0.8735 (0.8780) time: 0.1452 data: 0.0667 max mem: 9394 +Train: [6] [2200/6250] eta: 0:09:46 lr: 0.000125 grad: 0.0968 (0.1168) loss: 0.8723 (0.8779) time: 0.1412 data: 0.0633 max mem: 9394 +Train: [6] [2300/6250] eta: 0:09:30 lr: 0.000125 grad: 0.1106 (0.1171) loss: 0.8734 (0.8777) time: 0.1216 data: 0.0481 max mem: 9394 +Train: [6] [2400/6250] eta: 0:09:15 lr: 0.000125 grad: 0.0974 (0.1165) loss: 0.8723 (0.8775) time: 0.1511 data: 0.0723 max mem: 9394 +Train: [6] [2500/6250] eta: 0:09:00 lr: 0.000125 grad: 0.0948 (0.1159) loss: 0.8768 (0.8774) time: 0.1099 data: 0.0333 max mem: 9394 +Train: [6] [2600/6250] eta: 0:08:43 lr: 0.000125 grad: 0.0957 (0.1154) loss: 0.8776 (0.8773) time: 0.1364 data: 0.0571 max mem: 9394 +Train: [6] [2700/6250] eta: 0:08:28 lr: 0.000125 grad: 0.0936 (0.1149) loss: 0.8725 (0.8771) time: 0.1219 data: 0.0393 max mem: 9394 +Train: [6] [2800/6250] eta: 0:08:14 lr: 0.000125 grad: 0.1075 (0.1149) loss: 0.8756 (0.8770) time: 0.1155 data: 0.0392 max mem: 9394 +Train: [6] [2900/6250] eta: 0:07:59 lr: 0.000125 grad: 0.0931 (0.1144) loss: 0.8705 (0.8768) time: 0.1316 data: 0.0496 max mem: 9394 +Train: [6] [3000/6250] eta: 0:07:44 lr: 0.000125 grad: 0.0944 (0.1139) loss: 0.8687 (0.8767) time: 0.1339 data: 0.0521 max mem: 9394 +Train: [6] [3100/6250] eta: 0:07:29 lr: 0.000125 grad: 0.0924 (0.1134) loss: 0.8721 (0.8765) time: 0.1283 data: 0.0475 max mem: 9394 +Train: [6] [3200/6250] eta: 0:07:14 lr: 0.000125 grad: 0.1025 (0.1130) loss: 0.8653 (0.8763) time: 0.1666 data: 0.0878 max mem: 9394 +Train: [6] [3300/6250] eta: 0:06:59 lr: 0.000125 grad: 0.0939 (0.1128) loss: 0.8736 (0.8762) time: 0.1094 data: 0.0327 max mem: 9394 +Train: [6] [3400/6250] eta: 0:06:45 lr: 0.000125 grad: 0.0917 (0.1124) loss: 0.8728 (0.8760) time: 0.1468 data: 0.0422 max mem: 9394 +Train: [6] [3500/6250] eta: 0:06:29 lr: 0.000125 grad: 0.0967 (0.1120) loss: 0.8711 (0.8759) time: 0.1280 data: 0.0525 max mem: 9394 +Train: [6] [3600/6250] eta: 0:06:16 lr: 0.000125 grad: 0.1050 (0.1115) loss: 0.8717 (0.8758) time: 0.1470 data: 0.0281 max mem: 9394 +Train: [6] [3700/6250] eta: 0:06:02 lr: 0.000125 grad: 0.0868 (0.1111) loss: 0.8699 (0.8757) time: 0.1143 data: 0.0319 max mem: 9394 +Train: [6] [3800/6250] eta: 0:05:47 lr: 0.000125 grad: 0.1143 (0.1111) loss: 0.8703 (0.8755) time: 0.1355 data: 0.0540 max mem: 9394 +Train: [6] [3900/6250] eta: 0:05:33 lr: 0.000125 grad: 0.1075 (0.1108) loss: 0.8709 (0.8754) time: 0.1377 data: 0.0610 max mem: 9394 +Train: [6] [4000/6250] eta: 0:05:18 lr: 0.000125 grad: 0.0925 (0.1104) loss: 0.8704 (0.8753) time: 0.1431 data: 0.0682 max mem: 9394 +Train: [6] [4100/6250] eta: 0:05:03 lr: 0.000125 grad: 0.0927 (0.1101) loss: 0.8700 (0.8751) time: 0.1297 data: 0.0526 max mem: 9394 +Train: [6] [4200/6250] eta: 0:04:49 lr: 0.000125 grad: 0.0867 (0.1100) loss: 0.8698 (0.8750) time: 0.1338 data: 0.0499 max mem: 9394 +Train: [6] [4300/6250] eta: 0:04:35 lr: 0.000125 grad: 0.0971 (0.1098) loss: 0.8701 (0.8749) time: 0.1431 data: 0.0623 max mem: 9394 +Train: [6] [4400/6250] eta: 0:04:20 lr: 0.000125 grad: 0.0849 (0.1095) loss: 0.8699 (0.8748) time: 0.1346 data: 0.0535 max mem: 9394 +Train: [6] [4500/6250] eta: 0:04:06 lr: 0.000125 grad: 0.1005 (0.1093) loss: 0.8666 (0.8747) time: 0.1278 data: 0.0458 max mem: 9394 +Train: [6] [4600/6250] eta: 0:03:51 lr: 0.000125 grad: 0.0945 (0.1091) loss: 0.8646 (0.8745) time: 0.1151 data: 0.0308 max mem: 9394 +Train: [6] [4700/6250] eta: 0:03:37 lr: 0.000125 grad: 0.0992 (0.1090) loss: 0.8701 (0.8744) time: 0.1213 data: 0.0358 max mem: 9394 +Train: [6] [4800/6250] eta: 0:03:23 lr: 0.000125 grad: 0.0950 (0.1088) loss: 0.8686 (0.8743) time: 0.1142 data: 0.0362 max mem: 9394 +Train: [6] [4900/6250] eta: 0:03:09 lr: 0.000125 grad: 0.0880 (0.1086) loss: 0.8687 (0.8742) time: 0.1555 data: 0.0794 max mem: 9394 +Train: [6] [5000/6250] eta: 0:02:55 lr: 0.000125 grad: 0.0894 (0.1084) loss: 0.8698 (0.8741) time: 0.1518 data: 0.0781 max mem: 9394 +Train: [6] [5100/6250] eta: 0:02:41 lr: 0.000125 grad: 0.0906 (0.1083) loss: 0.8721 (0.8740) time: 0.1385 data: 0.0651 max mem: 9394 +Train: [6] [5200/6250] eta: 0:02:27 lr: 0.000125 grad: 0.0825 (0.1082) loss: 0.8713 (0.8739) time: 0.1244 data: 0.0469 max mem: 9394 +Train: [6] [5300/6250] eta: 0:02:13 lr: 0.000125 grad: 0.0816 (0.1080) loss: 0.8714 (0.8738) time: 0.1312 data: 0.0488 max mem: 9394 +Train: [6] [5400/6250] eta: 0:01:59 lr: 0.000125 grad: 0.1148 (0.1079) loss: 0.8698 (0.8737) time: 0.1431 data: 0.0650 max mem: 9394 +Train: [6] [5500/6250] eta: 0:01:45 lr: 0.000125 grad: 0.1091 (0.1078) loss: 0.8698 (0.8737) time: 0.1294 data: 0.0469 max mem: 9394 +Train: [6] [5600/6250] eta: 0:01:30 lr: 0.000125 grad: 0.0871 (0.1076) loss: 0.8670 (0.8736) time: 0.1274 data: 0.0449 max mem: 9394 +Train: [6] [5700/6250] eta: 0:01:17 lr: 0.000125 grad: 0.0884 (0.1073) loss: 0.8626 (0.8735) time: 0.1799 data: 0.0756 max mem: 9394 +Train: [6] [5800/6250] eta: 0:01:03 lr: 0.000125 grad: 0.0878 (0.1070) loss: 0.8647 (0.8734) time: 0.1083 data: 0.0323 max mem: 9394 +Train: [6] [5900/6250] eta: 0:00:49 lr: 0.000125 grad: 0.0844 (0.1067) loss: 0.8660 (0.8733) time: 0.1508 data: 0.0737 max mem: 9394 +Train: [6] [6000/6250] eta: 0:00:35 lr: 0.000125 grad: 0.0842 (0.1066) loss: 0.8750 (0.8732) time: 0.2029 data: 0.0740 max mem: 9394 +Train: [6] [6100/6250] eta: 0:00:21 lr: 0.000125 grad: 0.0815 (0.1063) loss: 0.8695 (0.8732) time: 0.1236 data: 0.0417 max mem: 9394 +Train: [6] [6200/6250] eta: 0:00:07 lr: 0.000125 grad: 0.0883 (0.1062) loss: 0.8658 (0.8731) time: 0.1436 data: 0.0671 max mem: 9394 +Train: [6] [6249/6250] eta: 0:00:00 lr: 0.000125 grad: 0.0830 (0.1060) loss: 0.8673 (0.8731) time: 0.1800 data: 0.1028 max mem: 9394 +Train: [6] Total time: 0:14:43 (0.1413 s / it) +Averaged stats: lr: 0.000125 grad: 0.0830 (0.1060) loss: 0.8673 (0.8731) +Eval (hcp-train-subset): [6] [ 0/62] eta: 0:04:44 loss: 0.8802 (0.8802) time: 4.5918 data: 4.5572 max mem: 9394 +Eval (hcp-train-subset): [6] [61/62] eta: 0:00:00 loss: 0.8718 (0.8710) time: 0.1371 data: 0.1107 max mem: 9394 +Eval (hcp-train-subset): [6] Total time: 0:00:12 (0.1975 s / it) +Averaged stats (hcp-train-subset): loss: 0.8718 (0.8710) +Eval (hcp-val): [6] [ 0/62] eta: 0:02:45 loss: 0.8603 (0.8603) time: 2.6769 data: 2.6265 max mem: 9394 +Eval (hcp-val): [6] [61/62] eta: 0:00:00 loss: 0.8650 (0.8651) time: 0.1498 data: 0.1229 max mem: 9394 +Eval (hcp-val): [6] Total time: 0:00:13 (0.2198 s / it) +Averaged stats (hcp-val): loss: 0.8650 (0.8651) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +Train: [7] [ 0/6250] eta: 7:13:34 lr: 0.000125 grad: 0.0611 (0.0611) loss: 0.9038 (0.9038) time: 4.1624 data: 3.9209 max mem: 9394 +Train: [7] [ 100/6250] eta: 0:19:33 lr: 0.000125 grad: 0.0783 (0.0837) loss: 0.8771 (0.8819) time: 0.1693 data: 0.0850 max mem: 9394 +Train: [7] [ 200/6250] eta: 0:16:44 lr: 0.000125 grad: 0.0765 (0.0893) loss: 0.8698 (0.8754) time: 0.1219 data: 0.0385 max mem: 9394 +Train: [7] [ 300/6250] eta: 0:15:39 lr: 0.000125 grad: 0.0858 (0.0888) loss: 0.8621 (0.8725) time: 0.1099 data: 0.0291 max mem: 9394 +Train: [7] [ 400/6250] eta: 0:14:41 lr: 0.000125 grad: 0.0809 (0.0876) loss: 0.8715 (0.8707) time: 0.1380 data: 0.0507 max mem: 9394 +Train: [7] [ 500/6250] eta: 0:13:49 lr: 0.000125 grad: 0.0812 (0.0877) loss: 0.8662 (0.8697) time: 0.1110 data: 0.0297 max mem: 9394 +Train: [7] [ 600/6250] eta: 0:13:20 lr: 0.000125 grad: 0.0775 (0.0886) loss: 0.8664 (0.8692) time: 0.1383 data: 0.0528 max mem: 9394 +Train: [7] [ 700/6250] eta: 0:12:54 lr: 0.000125 grad: 0.0791 (0.0875) loss: 0.8663 (0.8689) time: 0.1391 data: 0.0502 max mem: 9394 +Train: [7] [ 800/6250] eta: 0:12:48 lr: 0.000125 grad: 0.0748 (0.0875) loss: 0.8639 (0.8687) time: 0.1526 data: 0.0656 max mem: 9394 +Train: [7] [ 900/6250] eta: 0:12:47 lr: 0.000125 grad: 0.0791 (0.0873) loss: 0.8643 (0.8687) time: 0.1561 data: 0.0706 max mem: 9394 +Train: [7] [1000/6250] eta: 0:12:38 lr: 0.000125 grad: 0.0809 (0.0875) loss: 0.8693 (0.8684) time: 0.1672 data: 0.0820 max mem: 9394 +Train: [7] [1100/6250] eta: 0:12:27 lr: 0.000125 grad: 0.0812 (0.0872) loss: 0.8673 (0.8682) time: 0.1005 data: 0.0041 max mem: 9394 +Train: [7] [1200/6250] eta: 0:12:12 lr: 0.000125 grad: 0.0790 (0.0869) loss: 0.8645 (0.8681) time: 0.1008 data: 0.0193 max mem: 9394 +Train: [7] [1300/6250] eta: 0:12:00 lr: 0.000125 grad: 0.0848 (0.0867) loss: 0.8664 (0.8676) time: 0.1487 data: 0.0698 max mem: 9394 +Train: [7] [1400/6250] eta: 0:11:47 lr: 0.000125 grad: 0.0990 (0.0869) loss: 0.8616 (0.8674) time: 0.1727 data: 0.0944 max mem: 9394 +Train: [7] [1500/6250] eta: 0:11:36 lr: 0.000125 grad: 0.0774 (0.0870) loss: 0.8631 (0.8672) time: 0.1119 data: 0.0132 max mem: 9394 +Train: [7] [1600/6250] eta: 0:11:19 lr: 0.000125 grad: 0.0888 (0.0872) loss: 0.8643 (0.8671) time: 0.1411 data: 0.0556 max mem: 9394 +Train: [7] [1700/6250] eta: 0:11:16 lr: 0.000125 grad: 0.0860 (0.0871) loss: 0.8643 (0.8670) time: 0.3201 data: 0.2118 max mem: 9394 +Train: [7] [1800/6250] eta: 0:10:53 lr: 0.000125 grad: 0.0761 (0.0871) loss: 0.8646 (0.8669) time: 0.1265 data: 0.0463 max mem: 9394 +Train: [7] [1900/6250] eta: 0:10:36 lr: 0.000125 grad: 0.0806 (0.0871) loss: 0.8642 (0.8667) time: 0.1394 data: 0.0600 max mem: 9394 +Train: [7] [2000/6250] eta: 0:10:18 lr: 0.000125 grad: 0.0818 (0.0869) loss: 0.8650 (0.8665) time: 0.1306 data: 0.0515 max mem: 9394 +Train: [7] [2100/6250] eta: 0:10:02 lr: 0.000125 grad: 0.0794 (0.0867) loss: 0.8647 (0.8664) time: 0.1307 data: 0.0488 max mem: 9394 +Train: [7] [2200/6250] eta: 0:09:46 lr: 0.000125 grad: 0.0845 (0.0868) loss: 0.8632 (0.8663) time: 0.1300 data: 0.0462 max mem: 9394 +Train: [7] [2300/6250] eta: 0:09:30 lr: 0.000125 grad: 0.0756 (0.0866) loss: 0.8606 (0.8662) time: 0.1609 data: 0.0759 max mem: 9394 +Train: [7] [2400/6250] eta: 0:09:19 lr: 0.000125 grad: 0.0787 (0.0865) loss: 0.8657 (0.8662) time: 0.0957 data: 0.0088 max mem: 9394 +Train: [7] [2500/6250] eta: 0:09:05 lr: 0.000125 grad: 0.0816 (0.0865) loss: 0.8642 (0.8661) time: 0.1370 data: 0.0614 max mem: 9394 +Train: [7] [2600/6250] eta: 0:08:50 lr: 0.000125 grad: 0.0825 (0.0865) loss: 0.8661 (0.8660) time: 0.1522 data: 0.0741 max mem: 9394 +Train: [7] [2700/6250] eta: 0:08:35 lr: 0.000125 grad: 0.0751 (0.0863) loss: 0.8666 (0.8659) time: 0.1373 data: 0.0561 max mem: 9394 +Train: [7] [2800/6250] eta: 0:08:20 lr: 0.000125 grad: 0.0776 (0.0865) loss: 0.8652 (0.8658) time: 0.1021 data: 0.0220 max mem: 9394 +Train: [7] [2900/6250] eta: 0:08:05 lr: 0.000125 grad: 0.0772 (0.0865) loss: 0.8627 (0.8656) time: 0.1260 data: 0.0514 max mem: 9394 +Train: [7] [3000/6250] eta: 0:07:50 lr: 0.000125 grad: 0.0838 (0.0864) loss: 0.8623 (0.8655) time: 0.1525 data: 0.0775 max mem: 9394 +Train: [7] [3100/6250] eta: 0:07:36 lr: 0.000125 grad: 0.0776 (0.0865) loss: 0.8615 (0.8654) time: 0.1508 data: 0.0726 max mem: 9394 +Train: [7] [3200/6250] eta: 0:07:21 lr: 0.000125 grad: 0.0757 (0.0863) loss: 0.8574 (0.8653) time: 0.1273 data: 0.0501 max mem: 9394 +Train: [7] [3300/6250] eta: 0:07:05 lr: 0.000125 grad: 0.0774 (0.0861) loss: 0.8619 (0.8652) time: 0.1430 data: 0.0613 max mem: 9394 +Train: [7] [3400/6250] eta: 0:06:52 lr: 0.000125 grad: 0.0871 (0.0861) loss: 0.8587 (0.8650) time: 0.0980 data: 0.0002 max mem: 9394 +Train: [7] [3500/6250] eta: 0:06:36 lr: 0.000125 grad: 0.0793 (0.0864) loss: 0.8580 (0.8648) time: 0.1316 data: 0.0529 max mem: 9394 +Train: [7] [3600/6250] eta: 0:06:21 lr: 0.000125 grad: 0.0748 (0.0861) loss: 0.8599 (0.8647) time: 0.1490 data: 0.0675 max mem: 9394 +Train: [7] [3700/6250] eta: 0:06:06 lr: 0.000125 grad: 0.0797 (0.0861) loss: 0.8625 (0.8646) time: 0.1297 data: 0.0494 max mem: 9394 +Train: [7] [3800/6250] eta: 0:05:51 lr: 0.000125 grad: 0.0774 (0.0860) loss: 0.8582 (0.8645) time: 0.1496 data: 0.0532 max mem: 9394 +Train: [7] [3900/6250] eta: 0:05:36 lr: 0.000125 grad: 0.0759 (0.0859) loss: 0.8618 (0.8645) time: 0.1310 data: 0.0493 max mem: 9394 +Train: [7] [4000/6250] eta: 0:05:21 lr: 0.000125 grad: 0.0735 (0.0858) loss: 0.8608 (0.8644) time: 0.1586 data: 0.0800 max mem: 9394 +Train: [7] [4100/6250] eta: 0:05:08 lr: 0.000125 grad: 0.0820 (0.0857) loss: 0.8618 (0.8643) time: 0.0993 data: 0.0002 max mem: 9394 +Train: [7] [4200/6250] eta: 0:04:53 lr: 0.000125 grad: 0.0744 (0.0856) loss: 0.8634 (0.8642) time: 0.1421 data: 0.0611 max mem: 9394 +Train: [7] [4300/6250] eta: 0:04:38 lr: 0.000125 grad: 0.0782 (0.0855) loss: 0.8569 (0.8642) time: 0.1325 data: 0.0515 max mem: 9394 +Train: [7] [4400/6250] eta: 0:04:24 lr: 0.000125 grad: 0.0799 (0.0854) loss: 0.8642 (0.8641) time: 0.1400 data: 0.0626 max mem: 9394 +Train: [7] [4500/6250] eta: 0:04:09 lr: 0.000125 grad: 0.0696 (0.0852) loss: 0.8621 (0.8641) time: 0.1374 data: 0.0605 max mem: 9394 +Train: [7] [4600/6250] eta: 0:03:54 lr: 0.000125 grad: 0.0774 (0.0851) loss: 0.8585 (0.8640) time: 0.1297 data: 0.0515 max mem: 9394 +Train: [7] [4700/6250] eta: 0:03:41 lr: 0.000125 grad: 0.0777 (0.0849) loss: 0.8596 (0.8639) time: 0.2985 data: 0.1613 max mem: 9394 +Train: [7] [4800/6250] eta: 0:03:26 lr: 0.000125 grad: 0.0758 (0.0848) loss: 0.8547 (0.8638) time: 0.1294 data: 0.0453 max mem: 9394 +Train: [7] [4900/6250] eta: 0:03:12 lr: 0.000125 grad: 0.0749 (0.0846) loss: 0.8607 (0.8637) time: 0.1397 data: 0.0651 max mem: 9394 +Train: [7] [5000/6250] eta: 0:02:58 lr: 0.000125 grad: 0.0783 (0.0845) loss: 0.8581 (0.8636) time: 0.1575 data: 0.0108 max mem: 9394 +Train: [7] [5100/6250] eta: 0:02:43 lr: 0.000125 grad: 0.0742 (0.0844) loss: 0.8592 (0.8636) time: 0.1412 data: 0.0600 max mem: 9394 +Train: [7] [5200/6250] eta: 0:02:29 lr: 0.000125 grad: 0.0770 (0.0842) loss: 0.8559 (0.8635) time: 0.1210 data: 0.0406 max mem: 9394 +Train: [7] [5300/6250] eta: 0:02:15 lr: 0.000125 grad: 0.0698 (0.0841) loss: 0.8646 (0.8635) time: 0.1491 data: 0.0704 max mem: 9394 +Train: [7] [5400/6250] eta: 0:02:00 lr: 0.000125 grad: 0.0762 (0.0840) loss: 0.8592 (0.8634) time: 0.1517 data: 0.0774 max mem: 9394 +Train: [7] [5500/6250] eta: 0:01:46 lr: 0.000125 grad: 0.0785 (0.0839) loss: 0.8582 (0.8633) time: 0.1388 data: 0.0599 max mem: 9394 +Train: [7] [5600/6250] eta: 0:01:32 lr: 0.000125 grad: 0.0717 (0.0838) loss: 0.8620 (0.8633) time: 0.1877 data: 0.1118 max mem: 9394 +Train: [7] [5700/6250] eta: 0:01:18 lr: 0.000125 grad: 0.0745 (0.0837) loss: 0.8622 (0.8632) time: 0.1513 data: 0.0753 max mem: 9394 +Train: [7] [5800/6250] eta: 0:01:03 lr: 0.000125 grad: 0.0723 (0.0836) loss: 0.8647 (0.8631) time: 0.1456 data: 0.0699 max mem: 9394 +Train: [7] [5900/6250] eta: 0:00:49 lr: 0.000125 grad: 0.0742 (0.0834) loss: 0.8632 (0.8630) time: 0.1189 data: 0.0404 max mem: 9394 +Train: [7] [6000/6250] eta: 0:00:35 lr: 0.000125 grad: 0.0841 (0.0834) loss: 0.8591 (0.8630) time: 0.1459 data: 0.0660 max mem: 9394 +Train: [7] [6100/6250] eta: 0:00:21 lr: 0.000125 grad: 0.0728 (0.0833) loss: 0.8580 (0.8629) time: 0.1204 data: 0.0374 max mem: 9394 +Train: [7] [6200/6250] eta: 0:00:07 lr: 0.000125 grad: 0.0688 (0.0831) loss: 0.8591 (0.8628) time: 0.1443 data: 0.0709 max mem: 9394 +Train: [7] [6249/6250] eta: 0:00:00 lr: 0.000125 grad: 0.0773 (0.0831) loss: 0.8600 (0.8628) time: 0.1448 data: 0.0706 max mem: 9394 +Train: [7] Total time: 0:14:53 (0.1429 s / it) +Averaged stats: lr: 0.000125 grad: 0.0773 (0.0831) loss: 0.8600 (0.8628) +Eval (hcp-train-subset): [7] [ 0/62] eta: 0:04:52 loss: 0.8768 (0.8768) time: 4.7254 data: 4.6927 max mem: 9394 +Eval (hcp-train-subset): [7] [61/62] eta: 0:00:00 loss: 0.8636 (0.8638) time: 0.1314 data: 0.1064 max mem: 9394 +Eval (hcp-train-subset): [7] Total time: 0:00:13 (0.2194 s / it) +Averaged stats (hcp-train-subset): loss: 0.8636 (0.8638) +Eval (hcp-val): [7] [ 0/62] eta: 0:03:11 loss: 0.8547 (0.8547) time: 3.0914 data: 2.9554 max mem: 9394 +Eval (hcp-val): [7] [61/62] eta: 0:00:00 loss: 0.8567 (0.8577) time: 0.1139 data: 0.0891 max mem: 9394 +Eval (hcp-val): [7] Total time: 0:00:12 (0.2078 s / it) +Averaged stats (hcp-val): loss: 0.8567 (0.8577) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +Train: [8] [ 0/6250] eta: 8:10:31 lr: 0.000125 grad: 0.0685 (0.0685) loss: 0.8550 (0.8550) time: 4.7090 data: 4.4850 max mem: 9394 +Train: [8] [ 100/6250] eta: 0:19:22 lr: 0.000125 grad: 0.0907 (0.0929) loss: 0.8512 (0.8601) time: 0.1340 data: 0.0474 max mem: 9394 +Train: [8] [ 200/6250] eta: 0:16:47 lr: 0.000125 grad: 0.0757 (0.0923) loss: 0.8535 (0.8566) time: 0.1321 data: 0.0510 max mem: 9394 +Train: [8] [ 300/6250] eta: 0:15:15 lr: 0.000125 grad: 0.0816 (0.0899) loss: 0.8583 (0.8571) time: 0.1275 data: 0.0433 max mem: 9394 +Train: [8] [ 400/6250] eta: 0:14:22 lr: 0.000125 grad: 0.0765 (0.0883) loss: 0.8564 (0.8571) time: 0.1341 data: 0.0529 max mem: 9394 +Train: [8] [ 500/6250] eta: 0:13:42 lr: 0.000125 grad: 0.0706 (0.0882) loss: 0.8537 (0.8569) time: 0.1251 data: 0.0422 max mem: 9394 +Train: [8] [ 600/6250] eta: 0:13:11 lr: 0.000125 grad: 0.0726 (0.0868) loss: 0.8576 (0.8572) time: 0.1287 data: 0.0412 max mem: 9394 +Train: [8] [ 700/6250] eta: 0:13:11 lr: 0.000125 grad: 0.0726 (0.0856) loss: 0.8572 (0.8575) time: 0.1840 data: 0.1007 max mem: 9394 +Train: [8] [ 800/6250] eta: 0:13:17 lr: 0.000125 grad: 0.0781 (0.0848) loss: 0.8552 (0.8572) time: 0.2007 data: 0.1153 max mem: 9394 +Train: [8] [ 900/6250] eta: 0:13:13 lr: 0.000125 grad: 0.0787 (0.0838) loss: 0.8591 (0.8574) time: 0.1642 data: 0.0767 max mem: 9394 +Train: [8] [1000/6250] eta: 0:12:58 lr: 0.000125 grad: 0.0773 (0.0832) loss: 0.8571 (0.8575) time: 0.1212 data: 0.0388 max mem: 9394 +Train: [8] [1100/6250] eta: 0:12:42 lr: 0.000125 grad: 0.0682 (0.0821) loss: 0.8563 (0.8576) time: 0.1263 data: 0.0448 max mem: 9394 +Train: [8] [1200/6250] eta: 0:12:26 lr: 0.000125 grad: 0.0738 (0.0815) loss: 0.8635 (0.8576) time: 0.1452 data: 0.0614 max mem: 9394 +Train: [8] [1300/6250] eta: 0:12:24 lr: 0.000125 grad: 0.0696 (0.0812) loss: 0.8600 (0.8576) time: 0.2383 data: 0.1312 max mem: 9394 +Train: [8] [1400/6250] eta: 0:12:11 lr: 0.000125 grad: 0.0812 (0.0810) loss: 0.8528 (0.8576) time: 0.1324 data: 0.0004 max mem: 9394 +Train: [8] [1500/6250] eta: 0:11:56 lr: 0.000125 grad: 0.0746 (0.0807) loss: 0.8571 (0.8575) time: 0.1460 data: 0.0655 max mem: 9394 +Train: [8] [1600/6250] eta: 0:11:44 lr: 0.000125 grad: 0.0759 (0.0808) loss: 0.8562 (0.8575) time: 0.1335 data: 0.0297 max mem: 9394 +Train: [8] [1700/6250] eta: 0:11:27 lr: 0.000125 grad: 0.0709 (0.0806) loss: 0.8554 (0.8574) time: 0.1215 data: 0.0347 max mem: 9394 +Train: [8] [1800/6250] eta: 0:11:07 lr: 0.000125 grad: 0.0748 (0.0804) loss: 0.8503 (0.8572) time: 0.1323 data: 0.0479 max mem: 9394 +Train: [8] [1900/6250] eta: 0:11:05 lr: 0.000125 grad: 0.0744 (0.0803) loss: 0.8528 (0.8571) time: 0.1462 data: 0.0584 max mem: 9394 +Train: [8] [2000/6250] eta: 0:10:56 lr: 0.000125 grad: 0.0772 (0.0801) loss: 0.8564 (0.8570) time: 0.1034 data: 0.0028 max mem: 9394 +Train: [8] [2100/6250] eta: 0:10:38 lr: 0.000125 grad: 0.0783 (0.0801) loss: 0.8568 (0.8569) time: 0.1296 data: 0.0438 max mem: 9394 +Train: [8] [2200/6250] eta: 0:10:20 lr: 0.000125 grad: 0.0742 (0.0800) loss: 0.8499 (0.8567) time: 0.1379 data: 0.0534 max mem: 9394 +Train: [8] [2300/6250] eta: 0:10:01 lr: 0.000125 grad: 0.0788 (0.0799) loss: 0.8570 (0.8567) time: 0.1480 data: 0.0679 max mem: 9394 +Train: [8] [2400/6250] eta: 0:09:47 lr: 0.000125 grad: 0.0704 (0.0798) loss: 0.8535 (0.8565) time: 0.1658 data: 0.0850 max mem: 9394 +Train: [8] [2500/6250] eta: 0:09:30 lr: 0.000125 grad: 0.0710 (0.0797) loss: 0.8575 (0.8564) time: 0.1214 data: 0.0384 max mem: 9394 +Train: [8] [2600/6250] eta: 0:09:12 lr: 0.000125 grad: 0.0765 (0.0795) loss: 0.8539 (0.8564) time: 0.1339 data: 0.0521 max mem: 9394 +Train: [8] [2700/6250] eta: 0:08:54 lr: 0.000125 grad: 0.0729 (0.0794) loss: 0.8556 (0.8562) time: 0.1388 data: 0.0548 max mem: 9394 +Train: [8] [2800/6250] eta: 0:08:38 lr: 0.000125 grad: 0.0719 (0.0791) loss: 0.8538 (0.8561) time: 0.1152 data: 0.0366 max mem: 9394 +Train: [8] [2900/6250] eta: 0:08:22 lr: 0.000125 grad: 0.0745 (0.0790) loss: 0.8519 (0.8561) time: 0.1380 data: 0.0622 max mem: 9394 +Train: [8] [3000/6250] eta: 0:08:06 lr: 0.000125 grad: 0.0674 (0.0789) loss: 0.8490 (0.8560) time: 0.1496 data: 0.0677 max mem: 9394 +Train: [8] [3100/6250] eta: 0:07:49 lr: 0.000125 grad: 0.0741 (0.0788) loss: 0.8534 (0.8559) time: 0.1266 data: 0.0485 max mem: 9394 +Train: [8] [3200/6250] eta: 0:07:33 lr: 0.000125 grad: 0.0728 (0.0786) loss: 0.8531 (0.8558) time: 0.1319 data: 0.0530 max mem: 9394 +Train: [8] [3300/6250] eta: 0:07:17 lr: 0.000125 grad: 0.0670 (0.0786) loss: 0.8569 (0.8558) time: 0.1451 data: 0.0712 max mem: 9394 +Train: [8] [3400/6250] eta: 0:07:01 lr: 0.000125 grad: 0.0734 (0.0784) loss: 0.8484 (0.8557) time: 0.1409 data: 0.0637 max mem: 9394 +Train: [8] [3500/6250] eta: 0:06:46 lr: 0.000125 grad: 0.0734 (0.0784) loss: 0.8531 (0.8557) time: 0.1277 data: 0.0401 max mem: 9394 +Train: [8] [3600/6250] eta: 0:06:30 lr: 0.000125 grad: 0.0671 (0.0785) loss: 0.8587 (0.8557) time: 0.1404 data: 0.0624 max mem: 9394 +Train: [8] [3700/6250] eta: 0:06:15 lr: 0.000125 grad: 0.0694 (0.0783) loss: 0.8575 (0.8556) time: 0.1501 data: 0.0715 max mem: 9394 +Train: [8] [3800/6250] eta: 0:05:59 lr: 0.000125 grad: 0.0765 (0.0782) loss: 0.8565 (0.8556) time: 0.1484 data: 0.0698 max mem: 9394 +Train: [8] [3900/6250] eta: 0:05:44 lr: 0.000125 grad: 0.0783 (0.0782) loss: 0.8550 (0.8556) time: 0.1126 data: 0.0255 max mem: 9394 +Train: [8] [4000/6250] eta: 0:05:29 lr: 0.000125 grad: 0.0717 (0.0780) loss: 0.8569 (0.8556) time: 0.1427 data: 0.0638 max mem: 9394 +Train: [8] [4100/6250] eta: 0:05:13 lr: 0.000125 grad: 0.0672 (0.0779) loss: 0.8563 (0.8556) time: 0.1365 data: 0.0560 max mem: 9394 +Train: [8] [4200/6250] eta: 0:04:58 lr: 0.000125 grad: 0.0665 (0.0777) loss: 0.8570 (0.8556) time: 0.1512 data: 0.0671 max mem: 9394 +Train: [8] [4300/6250] eta: 0:04:44 lr: 0.000125 grad: 0.0707 (0.0778) loss: 0.8545 (0.8557) time: 0.1260 data: 0.0485 max mem: 9394 +Train: [8] [4400/6250] eta: 0:04:28 lr: 0.000125 grad: 0.0681 (0.0776) loss: 0.8528 (0.8557) time: 0.1270 data: 0.0419 max mem: 9394 +Train: [8] [4500/6250] eta: 0:04:13 lr: 0.000125 grad: 0.0717 (0.0775) loss: 0.8530 (0.8557) time: 0.1184 data: 0.0368 max mem: 9394 +Train: [8] [4600/6250] eta: 0:03:59 lr: 0.000125 grad: 0.0725 (0.0775) loss: 0.8516 (0.8557) time: 0.1362 data: 0.0563 max mem: 9394 +Train: [8] [4700/6250] eta: 0:03:44 lr: 0.000125 grad: 0.0661 (0.0775) loss: 0.8525 (0.8557) time: 0.1252 data: 0.0439 max mem: 9394 +Train: [8] [4800/6250] eta: 0:03:29 lr: 0.000125 grad: 0.0692 (0.0774) loss: 0.8563 (0.8557) time: 0.1331 data: 0.0498 max mem: 9394 +Train: [8] [4900/6250] eta: 0:03:14 lr: 0.000125 grad: 0.0766 (0.0773) loss: 0.8532 (0.8556) time: 0.1440 data: 0.0647 max mem: 9394 +Train: [8] [5000/6250] eta: 0:03:00 lr: 0.000125 grad: 0.0716 (0.0772) loss: 0.8558 (0.8556) time: 0.1096 data: 0.0303 max mem: 9394 +Train: [8] [5100/6250] eta: 0:02:45 lr: 0.000125 grad: 0.0682 (0.0771) loss: 0.8564 (0.8556) time: 0.1322 data: 0.0532 max mem: 9394 +Train: [8] [5200/6250] eta: 0:02:31 lr: 0.000124 grad: 0.0687 (0.0770) loss: 0.8554 (0.8556) time: 0.1277 data: 0.0470 max mem: 9394 +Train: [8] [5300/6250] eta: 0:02:16 lr: 0.000124 grad: 0.0738 (0.0770) loss: 0.8536 (0.8556) time: 0.1332 data: 0.0552 max mem: 9394 +Train: [8] [5400/6250] eta: 0:02:02 lr: 0.000124 grad: 0.0716 (0.0769) loss: 0.8540 (0.8556) time: 0.1345 data: 0.0541 max mem: 9394 +Train: [8] [5500/6250] eta: 0:01:47 lr: 0.000124 grad: 0.0719 (0.0768) loss: 0.8538 (0.8555) time: 0.1290 data: 0.0434 max mem: 9394 +Train: [8] [5600/6250] eta: 0:01:33 lr: 0.000124 grad: 0.0678 (0.0768) loss: 0.8527 (0.8555) time: 0.2202 data: 0.0791 max mem: 9394 +Train: [8] [5700/6250] eta: 0:01:19 lr: 0.000124 grad: 0.0631 (0.0767) loss: 0.8533 (0.8554) time: 0.1276 data: 0.0487 max mem: 9394 +Train: [8] [5800/6250] eta: 0:01:04 lr: 0.000124 grad: 0.0743 (0.0767) loss: 0.8476 (0.8554) time: 0.1296 data: 0.0537 max mem: 9394 +Train: [8] [5900/6250] eta: 0:00:50 lr: 0.000124 grad: 0.0678 (0.0767) loss: 0.8520 (0.8554) time: 0.1438 data: 0.0662 max mem: 9394 +Train: [8] [6000/6250] eta: 0:00:35 lr: 0.000124 grad: 0.0697 (0.0766) loss: 0.8573 (0.8554) time: 0.1322 data: 0.0509 max mem: 9394 +Train: [8] [6100/6250] eta: 0:00:21 lr: 0.000124 grad: 0.0659 (0.0766) loss: 0.8512 (0.8553) time: 0.1223 data: 0.0380 max mem: 9394 +Train: [8] [6200/6250] eta: 0:00:07 lr: 0.000124 grad: 0.0683 (0.0767) loss: 0.8511 (0.8553) time: 0.1812 data: 0.0956 max mem: 9394 +Train: [8] [6249/6250] eta: 0:00:00 lr: 0.000124 grad: 0.0696 (0.0766) loss: 0.8504 (0.8553) time: 0.1593 data: 0.0744 max mem: 9394 +Train: [8] Total time: 0:15:02 (0.1445 s / it) +Averaged stats: lr: 0.000124 grad: 0.0696 (0.0766) loss: 0.8504 (0.8553) +Eval (hcp-train-subset): [8] [ 0/62] eta: 0:04:25 loss: 0.8651 (0.8651) time: 4.2786 data: 4.2123 max mem: 9394 +Eval (hcp-train-subset): [8] [61/62] eta: 0:00:00 loss: 0.8578 (0.8590) time: 0.1296 data: 0.1050 max mem: 9394 +Eval (hcp-train-subset): [8] Total time: 0:00:13 (0.2167 s / it) +Averaged stats (hcp-train-subset): loss: 0.8578 (0.8590) +Eval (hcp-val): [8] [ 0/62] eta: 0:04:23 loss: 0.8515 (0.8515) time: 4.2467 data: 4.2178 max mem: 9394 +Eval (hcp-val): [8] [61/62] eta: 0:00:00 loss: 0.8524 (0.8531) time: 0.1181 data: 0.0909 max mem: 9394 +Eval (hcp-val): [8] Total time: 0:00:12 (0.1997 s / it) +Averaged stats (hcp-val): loss: 0.8524 (0.8531) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +Train: [9] [ 0/6250] eta: 9:15:14 lr: 0.000124 grad: 0.0646 (0.0646) loss: 0.8523 (0.8523) time: 5.3304 data: 5.2340 max mem: 9394 +Train: [9] [ 100/6250] eta: 0:19:02 lr: 0.000124 grad: 0.0683 (0.0716) loss: 0.8563 (0.8619) time: 0.1365 data: 0.0505 max mem: 9394 +Train: [9] [ 200/6250] eta: 0:16:27 lr: 0.000124 grad: 0.0719 (0.0740) loss: 0.8507 (0.8545) time: 0.1140 data: 0.0243 max mem: 9394 +Train: [9] [ 300/6250] eta: 0:15:01 lr: 0.000124 grad: 0.0730 (0.0758) loss: 0.8435 (0.8520) time: 0.1186 data: 0.0289 max mem: 9394 +Train: [9] [ 400/6250] eta: 0:14:12 lr: 0.000124 grad: 0.0710 (0.0759) loss: 0.8538 (0.8518) time: 0.1242 data: 0.0406 max mem: 9394 +Train: [9] [ 500/6250] eta: 0:13:35 lr: 0.000124 grad: 0.0698 (0.0745) loss: 0.8565 (0.8522) time: 0.1281 data: 0.0447 max mem: 9394 +Train: [9] [ 600/6250] eta: 0:13:04 lr: 0.000124 grad: 0.0662 (0.0737) loss: 0.8577 (0.8527) time: 0.1099 data: 0.0206 max mem: 9394 +Train: [9] [ 700/6250] eta: 0:13:10 lr: 0.000124 grad: 0.0685 (0.0734) loss: 0.8493 (0.8528) time: 0.1940 data: 0.1131 max mem: 9394 +Train: [9] [ 800/6250] eta: 0:13:22 lr: 0.000124 grad: 0.0690 (0.0737) loss: 0.8478 (0.8526) time: 0.1946 data: 0.1137 max mem: 9394 +Train: [9] [ 900/6250] eta: 0:13:21 lr: 0.000124 grad: 0.0654 (0.0733) loss: 0.8540 (0.8525) time: 0.1660 data: 0.0837 max mem: 9394 +Train: [9] [1000/6250] eta: 0:13:10 lr: 0.000124 grad: 0.0679 (0.0735) loss: 0.8495 (0.8524) time: 0.1507 data: 0.0721 max mem: 9394 +Train: [9] [1100/6250] eta: 0:12:56 lr: 0.000124 grad: 0.0681 (0.0736) loss: 0.8579 (0.8523) time: 0.1673 data: 0.0879 max mem: 9394 +Train: [9] [1200/6250] eta: 0:12:36 lr: 0.000124 grad: 0.0686 (0.0735) loss: 0.8541 (0.8524) time: 0.1594 data: 0.0751 max mem: 9394 +Train: [9] [1300/6250] eta: 0:12:17 lr: 0.000124 grad: 0.0756 (0.0735) loss: 0.8520 (0.8525) time: 0.1328 data: 0.0496 max mem: 9394 +Train: [9] [1400/6250] eta: 0:12:04 lr: 0.000124 grad: 0.0650 (0.0731) loss: 0.8564 (0.8526) time: 0.1636 data: 0.0744 max mem: 9394 +Train: [9] [1500/6250] eta: 0:11:56 lr: 0.000124 grad: 0.0674 (0.0728) loss: 0.8546 (0.8527) time: 0.1150 data: 0.0255 max mem: 9394 +Train: [9] [1600/6250] eta: 0:11:40 lr: 0.000124 grad: 0.0689 (0.0729) loss: 0.8551 (0.8529) time: 0.1507 data: 0.0688 max mem: 9394 +Train: [9] [1700/6250] eta: 0:11:28 lr: 0.000124 grad: 0.0619 (0.0725) loss: 0.8586 (0.8531) time: 0.0965 data: 0.0137 max mem: 9394 +Train: [9] [1800/6250] eta: 0:11:09 lr: 0.000124 grad: 0.0679 (0.0724) loss: 0.8591 (0.8533) time: 0.1326 data: 0.0489 max mem: 9394 +Train: [9] [1900/6250] eta: 0:11:01 lr: 0.000124 grad: 0.0659 (0.0722) loss: 0.8531 (0.8534) time: 0.2504 data: 0.1520 max mem: 9394 +Train: [9] [2000/6250] eta: 0:10:46 lr: 0.000124 grad: 0.0649 (0.0720) loss: 0.8542 (0.8535) time: 0.1025 data: 0.0089 max mem: 9394 +Train: [9] [2100/6250] eta: 0:10:27 lr: 0.000124 grad: 0.0650 (0.0718) loss: 0.8530 (0.8536) time: 0.1482 data: 0.0688 max mem: 9394 +Train: [9] [2200/6250] eta: 0:10:10 lr: 0.000124 grad: 0.0722 (0.0720) loss: 0.8553 (0.8537) time: 0.1393 data: 0.0600 max mem: 9394 +Train: [9] [2300/6250] eta: 0:09:54 lr: 0.000124 grad: 0.0679 (0.0720) loss: 0.8554 (0.8537) time: 0.1283 data: 0.0483 max mem: 9394 +Train: [9] [2400/6250] eta: 0:09:44 lr: 0.000124 grad: 0.0666 (0.0719) loss: 0.8560 (0.8537) time: 0.2075 data: 0.0875 max mem: 9394 +Train: [9] [2500/6250] eta: 0:09:25 lr: 0.000124 grad: 0.0664 (0.0718) loss: 0.8539 (0.8537) time: 0.1578 data: 0.0757 max mem: 9394 +Train: [9] [2600/6250] eta: 0:09:08 lr: 0.000124 grad: 0.0748 (0.0720) loss: 0.8552 (0.8538) time: 0.1554 data: 0.0787 max mem: 9394 +Train: [9] [2700/6250] eta: 0:08:54 lr: 0.000124 grad: 0.0702 (0.0719) loss: 0.8564 (0.8538) time: 0.2015 data: 0.1245 max mem: 9394 +Train: [9] [2800/6250] eta: 0:08:37 lr: 0.000124 grad: 0.0680 (0.0718) loss: 0.8572 (0.8538) time: 0.1423 data: 0.0625 max mem: 9394 +Train: [9] [2900/6250] eta: 0:08:21 lr: 0.000124 grad: 0.0675 (0.0718) loss: 0.8561 (0.8538) time: 0.1471 data: 0.0671 max mem: 9394 +Train: [9] [3000/6250] eta: 0:08:05 lr: 0.000124 grad: 0.0680 (0.0717) loss: 0.8603 (0.8539) time: 0.1177 data: 0.0257 max mem: 9394 +Train: [9] [3100/6250] eta: 0:07:49 lr: 0.000124 grad: 0.0667 (0.0716) loss: 0.8524 (0.8539) time: 0.1296 data: 0.0468 max mem: 9394 +Train: [9] [3200/6250] eta: 0:07:34 lr: 0.000124 grad: 0.0757 (0.0717) loss: 0.8533 (0.8539) time: 0.1696 data: 0.0898 max mem: 9394 +Train: [9] [3300/6250] eta: 0:07:17 lr: 0.000124 grad: 0.0706 (0.0716) loss: 0.8552 (0.8539) time: 0.1281 data: 0.0463 max mem: 9394 +Train: [9] [3400/6250] eta: 0:07:03 lr: 0.000124 grad: 0.0645 (0.0716) loss: 0.8552 (0.8540) time: 0.1655 data: 0.0843 max mem: 9394 +Train: [9] [3500/6250] eta: 0:06:47 lr: 0.000124 grad: 0.0644 (0.0714) loss: 0.8567 (0.8540) time: 0.1477 data: 0.0694 max mem: 9394 +Train: [9] [3600/6250] eta: 0:06:31 lr: 0.000124 grad: 0.0637 (0.0714) loss: 0.8588 (0.8540) time: 0.1271 data: 0.0418 max mem: 9394 +Train: [9] [3700/6250] eta: 0:06:15 lr: 0.000124 grad: 0.0672 (0.0713) loss: 0.8564 (0.8540) time: 0.1293 data: 0.0479 max mem: 9394 +Train: [9] [3800/6250] eta: 0:05:59 lr: 0.000124 grad: 0.0653 (0.0712) loss: 0.8548 (0.8540) time: 0.1194 data: 0.0298 max mem: 9394 +Train: [9] [3900/6250] eta: 0:05:44 lr: 0.000124 grad: 0.0654 (0.0711) loss: 0.8544 (0.8540) time: 0.1343 data: 0.0563 max mem: 9394 +Train: [9] [4000/6250] eta: 0:05:28 lr: 0.000124 grad: 0.0704 (0.0712) loss: 0.8523 (0.8540) time: 0.1183 data: 0.0337 max mem: 9394 +Train: [9] [4100/6250] eta: 0:05:13 lr: 0.000124 grad: 0.0646 (0.0711) loss: 0.8586 (0.8541) time: 0.1310 data: 0.0529 max mem: 9394 +Train: [9] [4200/6250] eta: 0:04:57 lr: 0.000124 grad: 0.0672 (0.0710) loss: 0.8521 (0.8541) time: 0.1339 data: 0.0575 max mem: 9394 +Train: [9] [4300/6250] eta: 0:04:42 lr: 0.000124 grad: 0.0688 (0.0710) loss: 0.8531 (0.8540) time: 0.1229 data: 0.0380 max mem: 9394 +Train: [9] [4400/6250] eta: 0:04:27 lr: 0.000124 grad: 0.0676 (0.0709) loss: 0.8553 (0.8540) time: 0.1162 data: 0.0309 max mem: 9394 +Train: [9] [4500/6250] eta: 0:04:12 lr: 0.000124 grad: 0.0647 (0.0708) loss: 0.8524 (0.8540) time: 0.1269 data: 0.0486 max mem: 9394 +Train: [9] [4600/6250] eta: 0:03:57 lr: 0.000124 grad: 0.0680 (0.0708) loss: 0.8512 (0.8540) time: 0.1359 data: 0.0574 max mem: 9394 +Train: [9] [4700/6250] eta: 0:03:43 lr: 0.000124 grad: 0.0667 (0.0707) loss: 0.8573 (0.8539) time: 0.1394 data: 0.0559 max mem: 9394 +Train: [9] [4800/6250] eta: 0:03:29 lr: 0.000124 grad: 0.0732 (0.0707) loss: 0.8498 (0.8539) time: 0.2109 data: 0.0850 max mem: 9394 +Train: [9] [4900/6250] eta: 0:03:15 lr: 0.000124 grad: 0.0637 (0.0706) loss: 0.8533 (0.8539) time: 0.1286 data: 0.0485 max mem: 9394 +Train: [9] [5000/6250] eta: 0:03:00 lr: 0.000124 grad: 0.0634 (0.0706) loss: 0.8546 (0.8539) time: 0.1095 data: 0.0261 max mem: 9394 +Train: [9] [5100/6250] eta: 0:02:45 lr: 0.000124 grad: 0.0660 (0.0705) loss: 0.8546 (0.8539) time: 0.1136 data: 0.0275 max mem: 9394 +Train: [9] [5200/6250] eta: 0:02:31 lr: 0.000124 grad: 0.0678 (0.0705) loss: 0.8477 (0.8538) time: 0.1335 data: 0.0537 max mem: 9394 +Train: [9] [5300/6250] eta: 0:02:16 lr: 0.000124 grad: 0.0678 (0.0704) loss: 0.8527 (0.8538) time: 0.1428 data: 0.0661 max mem: 9394 +Train: [9] [5400/6250] eta: 0:02:02 lr: 0.000124 grad: 0.0690 (0.0704) loss: 0.8528 (0.8538) time: 0.1400 data: 0.0630 max mem: 9394 +Train: [9] [5500/6250] eta: 0:01:48 lr: 0.000124 grad: 0.0734 (0.0704) loss: 0.8515 (0.8537) time: 0.1692 data: 0.0904 max mem: 9394 +Train: [9] [5600/6250] eta: 0:01:33 lr: 0.000124 grad: 0.0658 (0.0704) loss: 0.8486 (0.8537) time: 0.1372 data: 0.0574 max mem: 9394 +Train: [9] [5700/6250] eta: 0:01:19 lr: 0.000124 grad: 0.0684 (0.0704) loss: 0.8521 (0.8537) time: 0.1387 data: 0.0582 max mem: 9394 +Train: [9] [5800/6250] eta: 0:01:04 lr: 0.000124 grad: 0.0638 (0.0704) loss: 0.8520 (0.8536) time: 0.1331 data: 0.0411 max mem: 9394 +Train: [9] [5900/6250] eta: 0:00:50 lr: 0.000124 grad: 0.0702 (0.0704) loss: 0.8510 (0.8535) time: 0.1383 data: 0.0627 max mem: 9394 +Train: [9] [6000/6250] eta: 0:00:35 lr: 0.000124 grad: 0.0634 (0.0704) loss: 0.8495 (0.8534) time: 0.1337 data: 0.0558 max mem: 9394 +Train: [9] [6100/6250] eta: 0:00:21 lr: 0.000124 grad: 0.0669 (0.0704) loss: 0.8521 (0.8534) time: 0.1362 data: 0.0548 max mem: 9394 +Train: [9] [6200/6250] eta: 0:00:07 lr: 0.000124 grad: 0.0649 (0.0704) loss: 0.8500 (0.8533) time: 0.1805 data: 0.1061 max mem: 9394 +Train: [9] [6249/6250] eta: 0:00:00 lr: 0.000124 grad: 0.0658 (0.0704) loss: 0.8500 (0.8533) time: 0.1438 data: 0.0599 max mem: 9394 +Train: [9] Total time: 0:15:05 (0.1448 s / it) +Averaged stats: lr: 0.000124 grad: 0.0658 (0.0704) loss: 0.8500 (0.8533) +Eval (hcp-train-subset): [9] [ 0/62] eta: 0:05:47 loss: 0.8684 (0.8684) time: 5.6101 data: 5.5775 max mem: 9394 +Eval (hcp-train-subset): [9] [61/62] eta: 0:00:00 loss: 0.8566 (0.8566) time: 0.1364 data: 0.1110 max mem: 9394 +Eval (hcp-train-subset): [9] Total time: 0:00:13 (0.2182 s / it) +Averaged stats (hcp-train-subset): loss: 0.8566 (0.8566) +Making plots (hcp-train-subset): example=37 +Eval (hcp-val): [9] [ 0/62] eta: 0:05:20 loss: 0.8474 (0.8474) time: 5.1661 data: 5.1359 max mem: 9394 +Eval (hcp-val): [9] [61/62] eta: 0:00:00 loss: 0.8512 (0.8511) time: 0.0997 data: 0.0745 max mem: 9394 +Eval (hcp-val): [9] Total time: 0:00:12 (0.1947 s / it) +Averaged stats (hcp-val): loss: 0.8512 (0.8511) +Making plots (hcp-val): example=28 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +Train: [10] [ 0/6250] eta: 8:09:35 lr: 0.000124 grad: 0.0796 (0.0796) loss: 0.8497 (0.8497) time: 4.7000 data: 4.4096 max mem: 9394 +Train: [10] [ 100/6250] eta: 0:20:28 lr: 0.000124 grad: 0.0650 (0.0737) loss: 0.8522 (0.8556) time: 0.1545 data: 0.0707 max mem: 9394 +Train: [10] [ 200/6250] eta: 0:16:56 lr: 0.000124 grad: 0.0694 (0.0733) loss: 0.8526 (0.8537) time: 0.1396 data: 0.0502 max mem: 9394 +Train: [10] [ 300/6250] eta: 0:15:32 lr: 0.000124 grad: 0.0646 (0.0730) loss: 0.8515 (0.8533) time: 0.1427 data: 0.0551 max mem: 9394 +Train: [10] [ 400/6250] eta: 0:14:33 lr: 0.000124 grad: 0.0718 (0.0719) loss: 0.8530 (0.8527) time: 0.1284 data: 0.0446 max mem: 9394 +Train: [10] [ 500/6250] eta: 0:13:53 lr: 0.000124 grad: 0.0656 (0.0710) loss: 0.8552 (0.8528) time: 0.1217 data: 0.0405 max mem: 9394 +Train: [10] [ 600/6250] eta: 0:13:19 lr: 0.000124 grad: 0.0609 (0.0702) loss: 0.8560 (0.8533) time: 0.1294 data: 0.0507 max mem: 9394 +Train: [10] [ 700/6250] eta: 0:13:00 lr: 0.000124 grad: 0.0642 (0.0694) loss: 0.8552 (0.8538) time: 0.1459 data: 0.0649 max mem: 9394 +Train: [10] [ 800/6250] eta: 0:13:04 lr: 0.000124 grad: 0.0629 (0.0689) loss: 0.8523 (0.8540) time: 0.1525 data: 0.0690 max mem: 9394 +Train: [10] [ 900/6250] eta: 0:13:20 lr: 0.000124 grad: 0.0621 (0.0685) loss: 0.8555 (0.8539) time: 0.1958 data: 0.1178 max mem: 9394 +Train: [10] [1000/6250] eta: 0:13:16 lr: 0.000124 grad: 0.0670 (0.0683) loss: 0.8515 (0.8539) time: 0.1580 data: 0.0751 max mem: 9394 +Train: [10] [1100/6250] eta: 0:13:03 lr: 0.000124 grad: 0.0603 (0.0680) loss: 0.8532 (0.8538) time: 0.1727 data: 0.0954 max mem: 9394 +Train: [10] [1200/6250] eta: 0:12:49 lr: 0.000124 grad: 0.0649 (0.0678) loss: 0.8503 (0.8537) time: 0.1534 data: 0.0767 max mem: 9394 +Train: [10] [1300/6250] eta: 0:12:34 lr: 0.000124 grad: 0.0618 (0.0676) loss: 0.8532 (0.8536) time: 0.1472 data: 0.0708 max mem: 9394 +Train: [10] [1400/6250] eta: 0:12:15 lr: 0.000124 grad: 0.0657 (0.0674) loss: 0.8495 (0.8534) time: 0.1288 data: 0.0477 max mem: 9394 +Train: [10] [1500/6250] eta: 0:11:58 lr: 0.000124 grad: 0.0609 (0.0674) loss: 0.8516 (0.8531) time: 0.1390 data: 0.0534 max mem: 9394 +Train: [10] [1600/6250] eta: 0:11:48 lr: 0.000124 grad: 0.0636 (0.0674) loss: 0.8499 (0.8529) time: 0.2291 data: 0.1371 max mem: 9394 +Train: [10] [1700/6250] eta: 0:11:39 lr: 0.000124 grad: 0.0634 (0.0674) loss: 0.8492 (0.8528) time: 0.2045 data: 0.0927 max mem: 9394 +Train: [10] [1800/6250] eta: 0:11:32 lr: 0.000124 grad: 0.0678 (0.0674) loss: 0.8501 (0.8526) time: 0.1828 data: 0.1040 max mem: 9394 +Train: [10] [1900/6250] eta: 0:11:15 lr: 0.000124 grad: 0.0610 (0.0673) loss: 0.8462 (0.8524) time: 0.1766 data: 0.0916 max mem: 9394 +Train: [10] [2000/6250] eta: 0:10:58 lr: 0.000124 grad: 0.0665 (0.0673) loss: 0.8521 (0.8523) time: 0.1553 data: 0.0756 max mem: 9394 +Train: [10] [2100/6250] eta: 0:10:46 lr: 0.000124 grad: 0.0616 (0.0673) loss: 0.8543 (0.8523) time: 0.0880 data: 0.0002 max mem: 9394 +Train: [10] [2200/6250] eta: 0:10:27 lr: 0.000124 grad: 0.0639 (0.0672) loss: 0.8496 (0.8523) time: 0.1570 data: 0.0760 max mem: 9394 +Train: [10] [2300/6250] eta: 0:10:11 lr: 0.000124 grad: 0.0623 (0.0672) loss: 0.8539 (0.8522) time: 0.1434 data: 0.0611 max mem: 9394 +Train: [10] [2400/6250] eta: 0:09:58 lr: 0.000124 grad: 0.0670 (0.0672) loss: 0.8475 (0.8521) time: 0.0923 data: 0.0002 max mem: 9394 +Train: [10] [2500/6250] eta: 0:09:39 lr: 0.000124 grad: 0.0661 (0.0672) loss: 0.8517 (0.8521) time: 0.1506 data: 0.0582 max mem: 9394 +Train: [10] [2600/6250] eta: 0:09:26 lr: 0.000124 grad: 0.0647 (0.0673) loss: 0.8503 (0.8521) time: 0.1539 data: 0.0769 max mem: 9394 +Train: [10] [2700/6250] eta: 0:09:10 lr: 0.000124 grad: 0.0628 (0.0673) loss: 0.8564 (0.8522) time: 0.1339 data: 0.0481 max mem: 9394 +Train: [10] [2800/6250] eta: 0:08:57 lr: 0.000124 grad: 0.0649 (0.0673) loss: 0.8494 (0.8522) time: 0.2279 data: 0.1503 max mem: 9394 +Train: [10] [2900/6250] eta: 0:08:38 lr: 0.000124 grad: 0.0662 (0.0672) loss: 0.8531 (0.8522) time: 0.1202 data: 0.0437 max mem: 9394 +Train: [10] [3000/6250] eta: 0:08:30 lr: 0.000124 grad: 0.0611 (0.0673) loss: 0.8533 (0.8523) time: 0.5157 data: 0.4391 max mem: 9394 +Train: [10] [3100/6250] eta: 0:08:11 lr: 0.000124 grad: 0.0680 (0.0674) loss: 0.8520 (0.8522) time: 0.1435 data: 0.0693 max mem: 9394 +Train: [10] [3200/6250] eta: 0:07:54 lr: 0.000124 grad: 0.0663 (0.0674) loss: 0.8546 (0.8522) time: 0.1809 data: 0.0616 max mem: 9394 +Train: [10] [3300/6250] eta: 0:07:38 lr: 0.000124 grad: 0.0651 (0.0676) loss: 0.8508 (0.8521) time: 0.1457 data: 0.0623 max mem: 9394 +Train: [10] [3400/6250] eta: 0:07:21 lr: 0.000124 grad: 0.0647 (0.0675) loss: 0.8469 (0.8520) time: 0.1067 data: 0.0231 max mem: 9394 +Train: [10] [3500/6250] eta: 0:07:03 lr: 0.000124 grad: 0.0610 (0.0674) loss: 0.8504 (0.8519) time: 0.1216 data: 0.0436 max mem: 9394 +Train: [10] [3600/6250] eta: 0:06:46 lr: 0.000124 grad: 0.0629 (0.0675) loss: 0.8421 (0.8518) time: 0.1244 data: 0.0465 max mem: 9394 +Train: [10] [3700/6250] eta: 0:06:30 lr: 0.000124 grad: 0.0657 (0.0676) loss: 0.8469 (0.8517) time: 0.1615 data: 0.0722 max mem: 9394 +Train: [10] [3800/6250] eta: 0:06:13 lr: 0.000124 grad: 0.0645 (0.0676) loss: 0.8520 (0.8517) time: 0.1182 data: 0.0374 max mem: 9394 +Train: [10] [3900/6250] eta: 0:05:57 lr: 0.000124 grad: 0.0670 (0.0676) loss: 0.8532 (0.8516) time: 0.1138 data: 0.0357 max mem: 9394 +Train: [10] [4000/6250] eta: 0:05:42 lr: 0.000124 grad: 0.0663 (0.0676) loss: 0.8432 (0.8515) time: 0.1721 data: 0.0946 max mem: 9394 +Train: [10] [4100/6250] eta: 0:05:25 lr: 0.000124 grad: 0.0757 (0.0677) loss: 0.8491 (0.8514) time: 0.1370 data: 0.0605 max mem: 9394 +Train: [10] [4200/6250] eta: 0:05:09 lr: 0.000124 grad: 0.0682 (0.0679) loss: 0.8463 (0.8514) time: 0.1311 data: 0.0479 max mem: 9394 +Train: [10] [4300/6250] eta: 0:04:54 lr: 0.000124 grad: 0.0694 (0.0680) loss: 0.8477 (0.8514) time: 0.1832 data: 0.0539 max mem: 9394 +Train: [10] [4400/6250] eta: 0:04:38 lr: 0.000124 grad: 0.0642 (0.0680) loss: 0.8502 (0.8513) time: 0.1313 data: 0.0560 max mem: 9394 +Train: [10] [4500/6250] eta: 0:04:22 lr: 0.000124 grad: 0.0704 (0.0681) loss: 0.8482 (0.8513) time: 0.1130 data: 0.0388 max mem: 9394 +Train: [10] [4600/6250] eta: 0:04:06 lr: 0.000124 grad: 0.0661 (0.0681) loss: 0.8490 (0.8513) time: 0.1318 data: 0.0532 max mem: 9394 +Train: [10] [4700/6250] eta: 0:03:51 lr: 0.000124 grad: 0.0651 (0.0681) loss: 0.8500 (0.8512) time: 0.1537 data: 0.0746 max mem: 9394 +Train: [10] [4800/6250] eta: 0:03:36 lr: 0.000124 grad: 0.0644 (0.0681) loss: 0.8528 (0.8512) time: 0.1325 data: 0.0515 max mem: 9394 +Train: [10] [4900/6250] eta: 0:03:21 lr: 0.000124 grad: 0.0664 (0.0681) loss: 0.8472 (0.8511) time: 0.1697 data: 0.0884 max mem: 9394 +Train: [10] [5000/6250] eta: 0:03:06 lr: 0.000124 grad: 0.0627 (0.0681) loss: 0.8517 (0.8511) time: 0.1595 data: 0.0818 max mem: 9394 +Train: [10] [5100/6250] eta: 0:02:51 lr: 0.000124 grad: 0.0601 (0.0680) loss: 0.8550 (0.8511) time: 0.1514 data: 0.0732 max mem: 9394 +Train: [10] [5200/6250] eta: 0:02:35 lr: 0.000124 grad: 0.0644 (0.0679) loss: 0.8480 (0.8511) time: 0.1441 data: 0.0601 max mem: 9394 +Train: [10] [5300/6250] eta: 0:02:20 lr: 0.000124 grad: 0.0678 (0.0680) loss: 0.8477 (0.8511) time: 0.1322 data: 0.0475 max mem: 9394 +Train: [10] [5400/6250] eta: 0:02:06 lr: 0.000124 grad: 0.0658 (0.0681) loss: 0.8477 (0.8510) time: 0.1452 data: 0.0624 max mem: 9394 +Train: [10] [5500/6250] eta: 0:01:51 lr: 0.000124 grad: 0.0633 (0.0680) loss: 0.8467 (0.8510) time: 0.1577 data: 0.0729 max mem: 9394 +Train: [10] [5600/6250] eta: 0:01:36 lr: 0.000124 grad: 0.0669 (0.0681) loss: 0.8522 (0.8509) time: 0.1175 data: 0.0410 max mem: 9394 +Train: [10] [5700/6250] eta: 0:01:21 lr: 0.000124 grad: 0.0674 (0.0681) loss: 0.8451 (0.8509) time: 0.1487 data: 0.0688 max mem: 9394 +Train: [10] [5800/6250] eta: 0:01:06 lr: 0.000124 grad: 0.0654 (0.0681) loss: 0.8478 (0.8508) time: 0.1309 data: 0.0500 max mem: 9394 +Train: [10] [5900/6250] eta: 0:00:51 lr: 0.000124 grad: 0.0635 (0.0681) loss: 0.8521 (0.8507) time: 0.1312 data: 0.0528 max mem: 9394 +Train: [10] [6000/6250] eta: 0:00:36 lr: 0.000124 grad: 0.0688 (0.0681) loss: 0.8499 (0.8507) time: 0.1341 data: 0.0521 max mem: 9394 +Train: [10] [6100/6250] eta: 0:00:22 lr: 0.000124 grad: 0.0647 (0.0682) loss: 0.8427 (0.8506) time: 0.1311 data: 0.0528 max mem: 9394 +Train: [10] [6200/6250] eta: 0:00:07 lr: 0.000124 grad: 0.0677 (0.0682) loss: 0.8468 (0.8505) time: 0.1746 data: 0.0946 max mem: 9394 +Train: [10] [6249/6250] eta: 0:00:00 lr: 0.000124 grad: 0.0676 (0.0682) loss: 0.8494 (0.8505) time: 0.1514 data: 0.0709 max mem: 9394 +Train: [10] Total time: 0:15:27 (0.1484 s / it) +Averaged stats: lr: 0.000124 grad: 0.0676 (0.0682) loss: 0.8494 (0.8505) +Eval (hcp-train-subset): [10] [ 0/62] eta: 0:05:50 loss: 0.8624 (0.8624) time: 5.6599 data: 5.6288 max mem: 9394 +Eval (hcp-train-subset): [10] [61/62] eta: 0:00:00 loss: 0.8532 (0.8546) time: 0.1265 data: 0.1002 max mem: 9394 +Eval (hcp-train-subset): [10] Total time: 0:00:13 (0.2150 s / it) +Averaged stats (hcp-train-subset): loss: 0.8532 (0.8546) +Eval (hcp-val): [10] [ 0/62] eta: 0:05:03 loss: 0.8440 (0.8440) time: 4.9012 data: 4.8596 max mem: 9394 +Eval (hcp-val): [10] [61/62] eta: 0:00:00 loss: 0.8498 (0.8491) time: 0.1219 data: 0.0965 max mem: 9394 +Eval (hcp-val): [10] Total time: 0:00:12 (0.2076 s / it) +Averaged stats (hcp-val): loss: 0.8498 (0.8491) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +Train: [11] [ 0/6250] eta: 10:02:44 lr: 0.000124 grad: 0.0738 (0.0738) loss: 0.8527 (0.8527) time: 5.7864 data: 5.6952 max mem: 9394 +Train: [11] [ 100/6250] eta: 0:19:34 lr: 0.000124 grad: 0.0637 (0.0718) loss: 0.8518 (0.8521) time: 0.1436 data: 0.0557 max mem: 9394 +Train: [11] [ 200/6250] eta: 0:16:28 lr: 0.000124 grad: 0.0646 (0.0690) loss: 0.8496 (0.8521) time: 0.1327 data: 0.0483 max mem: 9394 +Train: [11] [ 300/6250] eta: 0:15:21 lr: 0.000124 grad: 0.0661 (0.0690) loss: 0.8517 (0.8513) time: 0.1325 data: 0.0400 max mem: 9394 +Train: [11] [ 400/6250] eta: 0:14:35 lr: 0.000124 grad: 0.0616 (0.0678) loss: 0.8513 (0.8516) time: 0.1436 data: 0.0531 max mem: 9394 +Train: [11] [ 500/6250] eta: 0:13:59 lr: 0.000124 grad: 0.0648 (0.0678) loss: 0.8519 (0.8515) time: 0.1449 data: 0.0673 max mem: 9394 +Train: [11] [ 600/6250] eta: 0:13:29 lr: 0.000124 grad: 0.0626 (0.0672) loss: 0.8502 (0.8513) time: 0.1244 data: 0.0434 max mem: 9394 +Train: [11] [ 700/6250] eta: 0:13:21 lr: 0.000124 grad: 0.0751 (0.0674) loss: 0.8470 (0.8509) time: 0.1444 data: 0.0644 max mem: 9394 +Train: [11] [ 800/6250] eta: 0:13:30 lr: 0.000124 grad: 0.0623 (0.0674) loss: 0.8500 (0.8505) time: 0.2009 data: 0.1188 max mem: 9394 +Train: [11] [ 900/6250] eta: 0:13:30 lr: 0.000124 grad: 0.0614 (0.0675) loss: 0.8482 (0.8502) time: 0.2112 data: 0.1255 max mem: 9394 +Train: [11] [1000/6250] eta: 0:13:16 lr: 0.000124 grad: 0.0623 (0.0674) loss: 0.8482 (0.8499) time: 0.1608 data: 0.0798 max mem: 9394 +Train: [11] [1100/6250] eta: 0:13:10 lr: 0.000124 grad: 0.0654 (0.0679) loss: 0.8415 (0.8494) time: 0.1546 data: 0.0780 max mem: 9394 +Train: [11] [1200/6250] eta: 0:12:59 lr: 0.000124 grad: 0.0612 (0.0679) loss: 0.8513 (0.8491) time: 0.1673 data: 0.0760 max mem: 9394 +Train: [11] [1300/6250] eta: 0:12:49 lr: 0.000124 grad: 0.0674 (0.0681) loss: 0.8495 (0.8489) time: 0.2169 data: 0.1393 max mem: 9394 +Train: [11] [1400/6250] eta: 0:12:34 lr: 0.000124 grad: 0.0628 (0.0680) loss: 0.8536 (0.8488) time: 0.1593 data: 0.0742 max mem: 9394 +Train: [11] [1500/6250] eta: 0:12:19 lr: 0.000124 grad: 0.0679 (0.0679) loss: 0.8502 (0.8486) time: 0.1741 data: 0.0903 max mem: 9394 +Train: [11] [1600/6250] eta: 0:11:56 lr: 0.000124 grad: 0.0631 (0.0678) loss: 0.8488 (0.8485) time: 0.1441 data: 0.0609 max mem: 9394 +Train: [11] [1700/6250] eta: 0:12:09 lr: 0.000124 grad: 0.0666 (0.0678) loss: 0.8476 (0.8483) time: 0.3648 data: 0.2213 max mem: 9394 +Train: [11] [1800/6250] eta: 0:11:53 lr: 0.000124 grad: 0.0660 (0.0677) loss: 0.8504 (0.8482) time: 0.2444 data: 0.1163 max mem: 9394 +Train: [11] [1900/6250] eta: 0:11:43 lr: 0.000124 grad: 0.0647 (0.0678) loss: 0.8441 (0.8480) time: 0.0994 data: 0.0149 max mem: 9394 +Train: [11] [2000/6250] eta: 0:11:24 lr: 0.000124 grad: 0.0653 (0.0679) loss: 0.8427 (0.8479) time: 0.1482 data: 0.0651 max mem: 9394 +Train: [11] [2100/6250] eta: 0:11:16 lr: 0.000124 grad: 0.0620 (0.0679) loss: 0.8443 (0.8478) time: 0.0955 data: 0.0002 max mem: 9394 +Train: [11] [2200/6250] eta: 0:10:54 lr: 0.000124 grad: 0.0605 (0.0678) loss: 0.8486 (0.8476) time: 0.1438 data: 0.0649 max mem: 9394 +Train: [11] [2300/6250] eta: 0:10:34 lr: 0.000124 grad: 0.0604 (0.0677) loss: 0.8483 (0.8476) time: 0.1548 data: 0.0732 max mem: 9394 +Train: [11] [2400/6250] eta: 0:10:14 lr: 0.000124 grad: 0.0613 (0.0676) loss: 0.8487 (0.8475) time: 0.1141 data: 0.0267 max mem: 9394 +Train: [11] [2500/6250] eta: 0:09:55 lr: 0.000124 grad: 0.0620 (0.0676) loss: 0.8480 (0.8475) time: 0.1523 data: 0.0724 max mem: 9394 +Train: [11] [2600/6250] eta: 0:09:36 lr: 0.000124 grad: 0.0625 (0.0676) loss: 0.8488 (0.8475) time: 0.1363 data: 0.0561 max mem: 9394 +Train: [11] [2700/6250] eta: 0:09:18 lr: 0.000124 grad: 0.0651 (0.0676) loss: 0.8478 (0.8474) time: 0.1291 data: 0.0489 max mem: 9394 +Train: [11] [2800/6250] eta: 0:09:00 lr: 0.000124 grad: 0.0647 (0.0675) loss: 0.8479 (0.8475) time: 0.1257 data: 0.0414 max mem: 9394 +Train: [11] [2900/6250] eta: 0:08:43 lr: 0.000124 grad: 0.0626 (0.0673) loss: 0.8503 (0.8475) time: 0.1401 data: 0.0598 max mem: 9394 +Train: [11] [3000/6250] eta: 0:08:26 lr: 0.000124 grad: 0.0652 (0.0673) loss: 0.8557 (0.8476) time: 0.1189 data: 0.0454 max mem: 9394 +Train: [11] [3100/6250] eta: 0:08:11 lr: 0.000124 grad: 0.0635 (0.0672) loss: 0.8453 (0.8476) time: 0.1630 data: 0.0835 max mem: 9394 +Train: [11] [3200/6250] eta: 0:07:53 lr: 0.000124 grad: 0.0693 (0.0672) loss: 0.8529 (0.8477) time: 0.1125 data: 0.0263 max mem: 9394 +Train: [11] [3300/6250] eta: 0:07:36 lr: 0.000124 grad: 0.0650 (0.0672) loss: 0.8513 (0.8478) time: 0.1310 data: 0.0486 max mem: 9394 +Train: [11] [3400/6250] eta: 0:07:19 lr: 0.000124 grad: 0.0651 (0.0672) loss: 0.8534 (0.8478) time: 0.1364 data: 0.0579 max mem: 9394 +Train: [11] [3500/6250] eta: 0:07:02 lr: 0.000124 grad: 0.0649 (0.0672) loss: 0.8442 (0.8479) time: 0.1277 data: 0.0419 max mem: 9394 +Train: [11] [3600/6250] eta: 0:06:45 lr: 0.000124 grad: 0.0658 (0.0672) loss: 0.8449 (0.8479) time: 0.1192 data: 0.0345 max mem: 9394 +Train: [11] [3700/6250] eta: 0:06:28 lr: 0.000124 grad: 0.0667 (0.0672) loss: 0.8463 (0.8478) time: 0.1133 data: 0.0336 max mem: 9394 +Train: [11] [3800/6250] eta: 0:06:12 lr: 0.000124 grad: 0.0679 (0.0673) loss: 0.8497 (0.8478) time: 0.1275 data: 0.0510 max mem: 9394 +Train: [11] [3900/6250] eta: 0:05:55 lr: 0.000124 grad: 0.0645 (0.0673) loss: 0.8492 (0.8478) time: 0.1282 data: 0.0517 max mem: 9394 +Train: [11] [4000/6250] eta: 0:05:39 lr: 0.000123 grad: 0.0643 (0.0673) loss: 0.8490 (0.8478) time: 0.1245 data: 0.0374 max mem: 9394 +Train: [11] [4100/6250] eta: 0:05:23 lr: 0.000123 grad: 0.0654 (0.0672) loss: 0.8467 (0.8478) time: 0.1441 data: 0.0636 max mem: 9394 +Train: [11] [4200/6250] eta: 0:05:07 lr: 0.000123 grad: 0.0592 (0.0672) loss: 0.8502 (0.8478) time: 0.1500 data: 0.0628 max mem: 9394 +Train: [11] [4300/6250] eta: 0:04:51 lr: 0.000123 grad: 0.0602 (0.0672) loss: 0.8508 (0.8478) time: 0.1212 data: 0.0418 max mem: 9394 +Train: [11] [4400/6250] eta: 0:04:35 lr: 0.000123 grad: 0.0619 (0.0672) loss: 0.8517 (0.8479) time: 0.1247 data: 0.0489 max mem: 9394 +Train: [11] [4500/6250] eta: 0:04:20 lr: 0.000123 grad: 0.0646 (0.0671) loss: 0.8481 (0.8479) time: 0.1247 data: 0.0498 max mem: 9394 +Train: [11] [4600/6250] eta: 0:04:05 lr: 0.000123 grad: 0.0656 (0.0671) loss: 0.8470 (0.8479) time: 0.1901 data: 0.0473 max mem: 9394 +Train: [11] [4700/6250] eta: 0:03:50 lr: 0.000123 grad: 0.0671 (0.0671) loss: 0.8486 (0.8479) time: 0.1198 data: 0.0384 max mem: 9394 +Train: [11] [4800/6250] eta: 0:03:35 lr: 0.000123 grad: 0.0675 (0.0672) loss: 0.8433 (0.8480) time: 0.1320 data: 0.0500 max mem: 9394 +Train: [11] [4900/6250] eta: 0:03:20 lr: 0.000123 grad: 0.0673 (0.0673) loss: 0.8494 (0.8480) time: 0.1354 data: 0.0544 max mem: 9394 +Train: [11] [5000/6250] eta: 0:03:05 lr: 0.000123 grad: 0.0642 (0.0674) loss: 0.8471 (0.8480) time: 0.1918 data: 0.1129 max mem: 9394 +Train: [11] [5100/6250] eta: 0:02:50 lr: 0.000123 grad: 0.0670 (0.0673) loss: 0.8516 (0.8480) time: 0.1932 data: 0.0915 max mem: 9394 +Train: [11] [5200/6250] eta: 0:02:35 lr: 0.000123 grad: 0.0631 (0.0673) loss: 0.8512 (0.8480) time: 0.1313 data: 0.0512 max mem: 9394 +Train: [11] [5300/6250] eta: 0:02:20 lr: 0.000123 grad: 0.0677 (0.0674) loss: 0.8477 (0.8480) time: 0.1424 data: 0.0642 max mem: 9394 +Train: [11] [5400/6250] eta: 0:02:05 lr: 0.000123 grad: 0.0662 (0.0674) loss: 0.8475 (0.8480) time: 0.1325 data: 0.0420 max mem: 9394 +Train: [11] [5500/6250] eta: 0:01:50 lr: 0.000123 grad: 0.0621 (0.0674) loss: 0.8454 (0.8480) time: 0.1251 data: 0.0437 max mem: 9394 +Train: [11] [5600/6250] eta: 0:01:35 lr: 0.000123 grad: 0.0640 (0.0674) loss: 0.8467 (0.8480) time: 0.1376 data: 0.0568 max mem: 9394 +Train: [11] [5700/6250] eta: 0:01:21 lr: 0.000123 grad: 0.0656 (0.0673) loss: 0.8474 (0.8480) time: 0.1152 data: 0.0341 max mem: 9394 +Train: [11] [5800/6250] eta: 0:01:06 lr: 0.000123 grad: 0.0628 (0.0673) loss: 0.8505 (0.8480) time: 0.1348 data: 0.0544 max mem: 9394 +Train: [11] [5900/6250] eta: 0:00:51 lr: 0.000123 grad: 0.0618 (0.0673) loss: 0.8505 (0.8480) time: 0.1265 data: 0.0442 max mem: 9394 +Train: [11] [6000/6250] eta: 0:00:36 lr: 0.000123 grad: 0.0605 (0.0673) loss: 0.8530 (0.8480) time: 0.1735 data: 0.0939 max mem: 9394 +Train: [11] [6100/6250] eta: 0:00:22 lr: 0.000123 grad: 0.0611 (0.0673) loss: 0.8464 (0.8479) time: 0.1294 data: 0.0449 max mem: 9394 +Train: [11] [6200/6250] eta: 0:00:07 lr: 0.000123 grad: 0.0614 (0.0673) loss: 0.8466 (0.8479) time: 0.1350 data: 0.0563 max mem: 9394 +Train: [11] [6249/6250] eta: 0:00:00 lr: 0.000123 grad: 0.0666 (0.0673) loss: 0.8463 (0.8479) time: 0.1538 data: 0.0780 max mem: 9394 +Train: [11] Total time: 0:15:22 (0.1476 s / it) +Averaged stats: lr: 0.000123 grad: 0.0666 (0.0673) loss: 0.8463 (0.8479) +Eval (hcp-train-subset): [11] [ 0/62] eta: 0:05:03 loss: 0.8644 (0.8644) time: 4.9013 data: 4.8693 max mem: 9394 +Eval (hcp-train-subset): [11] [61/62] eta: 0:00:00 loss: 0.8536 (0.8526) time: 0.1208 data: 0.0958 max mem: 9394 +Eval (hcp-train-subset): [11] Total time: 0:00:13 (0.2205 s / it) +Averaged stats (hcp-train-subset): loss: 0.8536 (0.8526) +Eval (hcp-val): [11] [ 0/62] eta: 0:05:38 loss: 0.8438 (0.8438) time: 5.4667 data: 5.4374 max mem: 9394 +Eval (hcp-val): [11] [61/62] eta: 0:00:00 loss: 0.8450 (0.8468) time: 0.1062 data: 0.0813 max mem: 9394 +Eval (hcp-val): [11] Total time: 0:00:13 (0.2150 s / it) +Averaged stats (hcp-val): loss: 0.8450 (0.8468) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +Train: [12] [ 0/6250] eta: 10:19:38 lr: 0.000123 grad: 0.0870 (0.0870) loss: 0.8770 (0.8770) time: 5.9486 data: 5.8605 max mem: 9394 +Train: [12] [ 100/6250] eta: 0:19:36 lr: 0.000123 grad: 0.0666 (0.0659) loss: 0.8450 (0.8561) time: 0.1474 data: 0.0578 max mem: 9394 +Train: [12] [ 200/6250] eta: 0:16:29 lr: 0.000123 grad: 0.0663 (0.0670) loss: 0.8503 (0.8524) time: 0.1325 data: 0.0501 max mem: 9394 +Train: [12] [ 300/6250] eta: 0:15:26 lr: 0.000123 grad: 0.0632 (0.0680) loss: 0.8540 (0.8519) time: 0.1575 data: 0.0760 max mem: 9394 +Train: [12] [ 400/6250] eta: 0:14:24 lr: 0.000123 grad: 0.0641 (0.0674) loss: 0.8482 (0.8515) time: 0.1296 data: 0.0446 max mem: 9394 +Train: [12] [ 500/6250] eta: 0:13:49 lr: 0.000123 grad: 0.0637 (0.0672) loss: 0.8443 (0.8510) time: 0.1391 data: 0.0553 max mem: 9394 +Train: [12] [ 600/6250] eta: 0:13:21 lr: 0.000123 grad: 0.0661 (0.0673) loss: 0.8456 (0.8505) time: 0.1299 data: 0.0496 max mem: 9394 +Train: [12] [ 700/6250] eta: 0:13:00 lr: 0.000123 grad: 0.0630 (0.0674) loss: 0.8492 (0.8505) time: 0.1309 data: 0.0420 max mem: 9394 +Train: [12] [ 800/6250] eta: 0:13:00 lr: 0.000123 grad: 0.0640 (0.0678) loss: 0.8487 (0.8504) time: 0.1819 data: 0.1032 max mem: 9394 +Train: [12] [ 900/6250] eta: 0:12:52 lr: 0.000123 grad: 0.0572 (0.0674) loss: 0.8476 (0.8502) time: 0.1596 data: 0.0730 max mem: 9394 +Train: [12] [1000/6250] eta: 0:12:39 lr: 0.000123 grad: 0.0602 (0.0671) loss: 0.8496 (0.8499) time: 0.1493 data: 0.0696 max mem: 9394 +Train: [12] [1100/6250] eta: 0:12:32 lr: 0.000123 grad: 0.0637 (0.0670) loss: 0.8449 (0.8495) time: 0.1822 data: 0.1082 max mem: 9394 +Train: [12] [1200/6250] eta: 0:12:17 lr: 0.000123 grad: 0.0611 (0.0669) loss: 0.8459 (0.8491) time: 0.1617 data: 0.0852 max mem: 9394 +Train: [12] [1300/6250] eta: 0:12:12 lr: 0.000123 grad: 0.0636 (0.0669) loss: 0.8451 (0.8488) time: 0.2109 data: 0.1363 max mem: 9394 +Train: [12] [1400/6250] eta: 0:11:54 lr: 0.000123 grad: 0.0669 (0.0668) loss: 0.8410 (0.8485) time: 0.1599 data: 0.0846 max mem: 9394 +Train: [12] [1500/6250] eta: 0:11:38 lr: 0.000123 grad: 0.0631 (0.0667) loss: 0.8477 (0.8483) time: 0.1434 data: 0.0608 max mem: 9394 +Train: [12] [1600/6250] eta: 0:11:23 lr: 0.000123 grad: 0.0631 (0.0667) loss: 0.8479 (0.8482) time: 0.1535 data: 0.0759 max mem: 9394 +Train: [12] [1700/6250] eta: 0:11:07 lr: 0.000123 grad: 0.0650 (0.0666) loss: 0.8455 (0.8481) time: 0.1365 data: 0.0497 max mem: 9394 +Train: [12] [1800/6250] eta: 0:10:54 lr: 0.000123 grad: 0.0643 (0.0666) loss: 0.8437 (0.8480) time: 0.1431 data: 0.0583 max mem: 9394 +Train: [12] [1900/6250] eta: 0:10:36 lr: 0.000123 grad: 0.0625 (0.0666) loss: 0.8467 (0.8478) time: 0.1314 data: 0.0430 max mem: 9394 +Train: [12] [2000/6250] eta: 0:10:24 lr: 0.000123 grad: 0.0693 (0.0667) loss: 0.8496 (0.8477) time: 0.1766 data: 0.0988 max mem: 9394 +Train: [12] [2100/6250] eta: 0:10:08 lr: 0.000123 grad: 0.0665 (0.0666) loss: 0.8421 (0.8476) time: 0.1145 data: 0.0228 max mem: 9394 +Train: [12] [2200/6250] eta: 0:09:54 lr: 0.000123 grad: 0.0648 (0.0665) loss: 0.8430 (0.8475) time: 0.1599 data: 0.0864 max mem: 9394 +Train: [12] [2300/6250] eta: 0:09:40 lr: 0.000123 grad: 0.0660 (0.0666) loss: 0.8450 (0.8474) time: 0.1878 data: 0.1059 max mem: 9394 +Train: [12] [2400/6250] eta: 0:09:27 lr: 0.000123 grad: 0.0619 (0.0665) loss: 0.8446 (0.8473) time: 0.1417 data: 0.0620 max mem: 9394 +Train: [12] [2500/6250] eta: 0:09:15 lr: 0.000123 grad: 0.0613 (0.0665) loss: 0.8482 (0.8472) time: 0.1712 data: 0.0793 max mem: 9394 +Train: [12] [2600/6250] eta: 0:08:58 lr: 0.000123 grad: 0.0628 (0.0663) loss: 0.8451 (0.8471) time: 0.1274 data: 0.0470 max mem: 9394 +Train: [12] [2700/6250] eta: 0:08:42 lr: 0.000123 grad: 0.0624 (0.0663) loss: 0.8472 (0.8470) time: 0.1303 data: 0.0500 max mem: 9394 +Train: [12] [2800/6250] eta: 0:08:28 lr: 0.000123 grad: 0.0667 (0.0666) loss: 0.8458 (0.8470) time: 0.1495 data: 0.0675 max mem: 9394 +Train: [12] [2900/6250] eta: 0:08:12 lr: 0.000123 grad: 0.0613 (0.0665) loss: 0.8469 (0.8470) time: 0.1430 data: 0.0638 max mem: 9394 +Train: [12] [3000/6250] eta: 0:07:57 lr: 0.000123 grad: 0.0639 (0.0665) loss: 0.8430 (0.8469) time: 0.1641 data: 0.0809 max mem: 9394 +Train: [12] [3100/6250] eta: 0:07:42 lr: 0.000123 grad: 0.0610 (0.0664) loss: 0.8441 (0.8468) time: 0.1442 data: 0.0570 max mem: 9394 +Train: [12] [3200/6250] eta: 0:07:26 lr: 0.000123 grad: 0.0631 (0.0665) loss: 0.8504 (0.8468) time: 0.1294 data: 0.0429 max mem: 9394 +Train: [12] [3300/6250] eta: 0:07:10 lr: 0.000123 grad: 0.0667 (0.0665) loss: 0.8442 (0.8468) time: 0.1284 data: 0.0427 max mem: 9394 +Train: [12] [3400/6250] eta: 0:06:56 lr: 0.000123 grad: 0.0634 (0.0664) loss: 0.8458 (0.8468) time: 0.1637 data: 0.0848 max mem: 9394 +Train: [12] [3500/6250] eta: 0:06:40 lr: 0.000123 grad: 0.0655 (0.0664) loss: 0.8417 (0.8467) time: 0.1342 data: 0.0545 max mem: 9394 +Train: [12] [3600/6250] eta: 0:06:24 lr: 0.000123 grad: 0.0644 (0.0663) loss: 0.8490 (0.8466) time: 0.1321 data: 0.0573 max mem: 9394 +Train: [12] [3700/6250] eta: 0:06:09 lr: 0.000123 grad: 0.0621 (0.0662) loss: 0.8454 (0.8466) time: 0.1236 data: 0.0459 max mem: 9394 +Train: [12] [3800/6250] eta: 0:05:54 lr: 0.000123 grad: 0.0626 (0.0662) loss: 0.8459 (0.8466) time: 0.1169 data: 0.0371 max mem: 9394 +Train: [12] [3900/6250] eta: 0:05:39 lr: 0.000123 grad: 0.0590 (0.0662) loss: 0.8450 (0.8465) time: 0.1228 data: 0.0408 max mem: 9394 +Train: [12] [4000/6250] eta: 0:05:25 lr: 0.000123 grad: 0.0605 (0.0661) loss: 0.8472 (0.8465) time: 0.1229 data: 0.0392 max mem: 9394 +Train: [12] [4100/6250] eta: 0:05:10 lr: 0.000123 grad: 0.0630 (0.0661) loss: 0.8437 (0.8464) time: 0.1262 data: 0.0441 max mem: 9394 +Train: [12] [4200/6250] eta: 0:04:55 lr: 0.000123 grad: 0.0643 (0.0660) loss: 0.8470 (0.8464) time: 0.1380 data: 0.0617 max mem: 9394 +Train: [12] [4300/6250] eta: 0:04:40 lr: 0.000123 grad: 0.0626 (0.0660) loss: 0.8423 (0.8463) time: 0.1312 data: 0.0420 max mem: 9394 +Train: [12] [4400/6250] eta: 0:04:25 lr: 0.000123 grad: 0.0601 (0.0660) loss: 0.8444 (0.8463) time: 0.1277 data: 0.0462 max mem: 9394 +Train: [12] [4500/6250] eta: 0:04:10 lr: 0.000123 grad: 0.0596 (0.0660) loss: 0.8466 (0.8463) time: 0.1316 data: 0.0567 max mem: 9394 +Train: [12] [4600/6250] eta: 0:03:56 lr: 0.000123 grad: 0.0598 (0.0659) loss: 0.8471 (0.8463) time: 0.1221 data: 0.0241 max mem: 9394 +Train: [12] [4700/6250] eta: 0:03:42 lr: 0.000123 grad: 0.0619 (0.0658) loss: 0.8399 (0.8463) time: 0.1328 data: 0.0479 max mem: 9394 +Train: [12] [4800/6250] eta: 0:03:28 lr: 0.000123 grad: 0.0604 (0.0658) loss: 0.8459 (0.8463) time: 0.1259 data: 0.0450 max mem: 9394 +Train: [12] [4900/6250] eta: 0:03:13 lr: 0.000123 grad: 0.0606 (0.0657) loss: 0.8460 (0.8462) time: 0.1395 data: 0.0529 max mem: 9394 +Train: [12] [5000/6250] eta: 0:02:59 lr: 0.000123 grad: 0.0638 (0.0657) loss: 0.8523 (0.8463) time: 0.1314 data: 0.0503 max mem: 9394 +Train: [12] [5100/6250] eta: 0:02:44 lr: 0.000123 grad: 0.0605 (0.0656) loss: 0.8483 (0.8463) time: 0.1438 data: 0.0620 max mem: 9394 +Train: [12] [5200/6250] eta: 0:02:30 lr: 0.000123 grad: 0.0652 (0.0656) loss: 0.8507 (0.8463) time: 0.1375 data: 0.0536 max mem: 9394 +Train: [12] [5300/6250] eta: 0:02:16 lr: 0.000123 grad: 0.0603 (0.0655) loss: 0.8498 (0.8463) time: 0.1225 data: 0.0426 max mem: 9394 +Train: [12] [5400/6250] eta: 0:02:01 lr: 0.000123 grad: 0.0624 (0.0655) loss: 0.8474 (0.8464) time: 0.1226 data: 0.0405 max mem: 9394 +Train: [12] [5500/6250] eta: 0:01:47 lr: 0.000123 grad: 0.0614 (0.0655) loss: 0.8412 (0.8463) time: 0.1449 data: 0.0633 max mem: 9394 +Train: [12] [5600/6250] eta: 0:01:33 lr: 0.000123 grad: 0.0663 (0.0655) loss: 0.8454 (0.8463) time: 0.1478 data: 0.0670 max mem: 9394 +Train: [12] [5700/6250] eta: 0:01:18 lr: 0.000123 grad: 0.0600 (0.0655) loss: 0.8455 (0.8464) time: 0.1643 data: 0.0867 max mem: 9394 +Train: [12] [5800/6250] eta: 0:01:04 lr: 0.000123 grad: 0.0594 (0.0654) loss: 0.8483 (0.8464) time: 0.1410 data: 0.0624 max mem: 9394 +Train: [12] [5900/6250] eta: 0:00:49 lr: 0.000123 grad: 0.0589 (0.0654) loss: 0.8408 (0.8464) time: 0.1265 data: 0.0443 max mem: 9394 +Train: [12] [6000/6250] eta: 0:00:35 lr: 0.000123 grad: 0.0644 (0.0653) loss: 0.8461 (0.8464) time: 0.1258 data: 0.0505 max mem: 9394 +Train: [12] [6100/6250] eta: 0:00:21 lr: 0.000123 grad: 0.0616 (0.0653) loss: 0.8452 (0.8464) time: 0.1277 data: 0.0467 max mem: 9394 +Train: [12] [6200/6250] eta: 0:00:07 lr: 0.000123 grad: 0.0611 (0.0653) loss: 0.8453 (0.8464) time: 0.1872 data: 0.0973 max mem: 9394 +Train: [12] [6249/6250] eta: 0:00:00 lr: 0.000123 grad: 0.0622 (0.0653) loss: 0.8477 (0.8464) time: 0.1441 data: 0.0708 max mem: 9394 +Train: [12] Total time: 0:14:58 (0.1437 s / it) +Averaged stats: lr: 0.000123 grad: 0.0622 (0.0653) loss: 0.8477 (0.8464) +Eval (hcp-train-subset): [12] [ 0/62] eta: 0:06:10 loss: 0.8613 (0.8613) time: 5.9810 data: 5.9493 max mem: 9394 +Eval (hcp-train-subset): [12] [61/62] eta: 0:00:00 loss: 0.8492 (0.8507) time: 0.0965 data: 0.0719 max mem: 9394 +Eval (hcp-train-subset): [12] Total time: 0:00:13 (0.2147 s / it) +Averaged stats (hcp-train-subset): loss: 0.8492 (0.8507) +Eval (hcp-val): [12] [ 0/62] eta: 0:05:29 loss: 0.8422 (0.8422) time: 5.3225 data: 5.2874 max mem: 9394 +Eval (hcp-val): [12] [61/62] eta: 0:00:00 loss: 0.8456 (0.8456) time: 0.1236 data: 0.0965 max mem: 9394 +Eval (hcp-val): [12] Total time: 0:00:13 (0.2145 s / it) +Averaged stats (hcp-val): loss: 0.8456 (0.8456) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +Train: [13] [ 0/6250] eta: 9:50:32 lr: 0.000123 grad: 0.0497 (0.0497) loss: 0.8541 (0.8541) time: 5.6692 data: 5.5778 max mem: 9394 +Train: [13] [ 100/6250] eta: 0:19:20 lr: 0.000123 grad: 0.0699 (0.0737) loss: 0.8468 (0.8492) time: 0.1450 data: 0.0580 max mem: 9394 +Train: [13] [ 200/6250] eta: 0:16:49 lr: 0.000123 grad: 0.0705 (0.0721) loss: 0.8463 (0.8480) time: 0.1608 data: 0.0800 max mem: 9394 +Train: [13] [ 300/6250] eta: 0:15:29 lr: 0.000123 grad: 0.0657 (0.0711) loss: 0.8470 (0.8486) time: 0.1525 data: 0.0667 max mem: 9394 +Train: [13] [ 400/6250] eta: 0:14:35 lr: 0.000123 grad: 0.0641 (0.0694) loss: 0.8452 (0.8480) time: 0.1398 data: 0.0554 max mem: 9394 +Train: [13] [ 500/6250] eta: 0:13:56 lr: 0.000123 grad: 0.0675 (0.0688) loss: 0.8464 (0.8481) time: 0.1212 data: 0.0263 max mem: 9394 +Train: [13] [ 600/6250] eta: 0:13:24 lr: 0.000123 grad: 0.0621 (0.0681) loss: 0.8433 (0.8481) time: 0.1177 data: 0.0261 max mem: 9394 +Train: [13] [ 700/6250] eta: 0:13:01 lr: 0.000123 grad: 0.0603 (0.0672) loss: 0.8462 (0.8479) time: 0.1360 data: 0.0563 max mem: 9394 +Train: [13] [ 800/6250] eta: 0:13:02 lr: 0.000123 grad: 0.0585 (0.0667) loss: 0.8447 (0.8478) time: 0.1074 data: 0.0110 max mem: 9394 +Train: [13] [ 900/6250] eta: 0:12:54 lr: 0.000123 grad: 0.0619 (0.0671) loss: 0.8439 (0.8473) time: 0.1621 data: 0.0838 max mem: 9394 +Train: [13] [1000/6250] eta: 0:12:43 lr: 0.000123 grad: 0.0639 (0.0671) loss: 0.8452 (0.8468) time: 0.1142 data: 0.0248 max mem: 9394 +Train: [13] [1100/6250] eta: 0:12:33 lr: 0.000123 grad: 0.0628 (0.0667) loss: 0.8456 (0.8466) time: 0.1605 data: 0.0811 max mem: 9394 +Train: [13] [1200/6250] eta: 0:12:22 lr: 0.000123 grad: 0.0637 (0.0664) loss: 0.8411 (0.8463) time: 0.1548 data: 0.0754 max mem: 9394 +Train: [13] [1300/6250] eta: 0:12:11 lr: 0.000123 grad: 0.0605 (0.0663) loss: 0.8437 (0.8461) time: 0.1915 data: 0.1103 max mem: 9394 +Train: [13] [1400/6250] eta: 0:12:00 lr: 0.000123 grad: 0.0573 (0.0661) loss: 0.8458 (0.8459) time: 0.1766 data: 0.0977 max mem: 9394 +Train: [13] [1500/6250] eta: 0:11:51 lr: 0.000123 grad: 0.0596 (0.0658) loss: 0.8401 (0.8457) time: 0.1541 data: 0.0729 max mem: 9394 +Train: [13] [1600/6250] eta: 0:11:35 lr: 0.000123 grad: 0.0595 (0.0657) loss: 0.8461 (0.8456) time: 0.1609 data: 0.0841 max mem: 9394 +Train: [13] [1700/6250] eta: 0:11:21 lr: 0.000123 grad: 0.0604 (0.0655) loss: 0.8400 (0.8455) time: 0.1591 data: 0.0764 max mem: 9394 +Train: [13] [1800/6250] eta: 0:11:07 lr: 0.000123 grad: 0.0671 (0.0653) loss: 0.8453 (0.8454) time: 0.1295 data: 0.0523 max mem: 9394 +Train: [13] [1900/6250] eta: 0:10:48 lr: 0.000123 grad: 0.0658 (0.0653) loss: 0.8427 (0.8452) time: 0.1234 data: 0.0460 max mem: 9394 +Train: [13] [2000/6250] eta: 0:10:32 lr: 0.000123 grad: 0.0611 (0.0654) loss: 0.8443 (0.8451) time: 0.1370 data: 0.0558 max mem: 9394 +Train: [13] [2100/6250] eta: 0:10:14 lr: 0.000123 grad: 0.0624 (0.0654) loss: 0.8489 (0.8451) time: 0.1509 data: 0.0696 max mem: 9394 +Train: [13] [2200/6250] eta: 0:09:59 lr: 0.000123 grad: 0.0634 (0.0654) loss: 0.8420 (0.8450) time: 0.1449 data: 0.0643 max mem: 9394 +Train: [13] [2300/6250] eta: 0:09:43 lr: 0.000123 grad: 0.0675 (0.0654) loss: 0.8466 (0.8450) time: 0.1631 data: 0.0686 max mem: 9394 +Train: [13] [2400/6250] eta: 0:09:30 lr: 0.000123 grad: 0.0620 (0.0653) loss: 0.8475 (0.8450) time: 0.1033 data: 0.0175 max mem: 9394 +Train: [13] [2500/6250] eta: 0:09:20 lr: 0.000123 grad: 0.0610 (0.0652) loss: 0.8456 (0.8450) time: 0.3361 data: 0.2148 max mem: 9394 +Train: [13] [2600/6250] eta: 0:09:09 lr: 0.000123 grad: 0.0619 (0.0651) loss: 0.8447 (0.8451) time: 0.1180 data: 0.0385 max mem: 9394 +Train: [13] [2700/6250] eta: 0:08:52 lr: 0.000123 grad: 0.0622 (0.0650) loss: 0.8466 (0.8451) time: 0.1326 data: 0.0557 max mem: 9394 +Train: [13] [2800/6250] eta: 0:08:39 lr: 0.000123 grad: 0.0625 (0.0649) loss: 0.8490 (0.8452) time: 0.0989 data: 0.0011 max mem: 9394 +Train: [13] [2900/6250] eta: 0:08:26 lr: 0.000123 grad: 0.0606 (0.0648) loss: 0.8484 (0.8452) time: 0.1928 data: 0.1105 max mem: 9394 +Train: [13] [3000/6250] eta: 0:08:09 lr: 0.000123 grad: 0.0591 (0.0647) loss: 0.8418 (0.8453) time: 0.1492 data: 0.0718 max mem: 9394 +Train: [13] [3100/6250] eta: 0:07:53 lr: 0.000123 grad: 0.0609 (0.0648) loss: 0.8412 (0.8453) time: 0.1440 data: 0.0582 max mem: 9394 +Train: [13] [3200/6250] eta: 0:07:40 lr: 0.000123 grad: 0.0654 (0.0648) loss: 0.8432 (0.8453) time: 0.0993 data: 0.0002 max mem: 9394 +Train: [13] [3300/6250] eta: 0:07:28 lr: 0.000123 grad: 0.0617 (0.0647) loss: 0.8434 (0.8453) time: 0.0949 data: 0.0002 max mem: 9394 +Train: [13] [3400/6250] eta: 0:07:11 lr: 0.000123 grad: 0.0604 (0.0647) loss: 0.8409 (0.8453) time: 0.1200 data: 0.0395 max mem: 9394 +Train: [13] [3500/6250] eta: 0:06:55 lr: 0.000123 grad: 0.0609 (0.0646) loss: 0.8469 (0.8453) time: 0.1327 data: 0.0541 max mem: 9394 +Train: [13] [3600/6250] eta: 0:06:40 lr: 0.000123 grad: 0.0636 (0.0646) loss: 0.8453 (0.8452) time: 0.1389 data: 0.0580 max mem: 9394 +Train: [13] [3700/6250] eta: 0:06:23 lr: 0.000122 grad: 0.0605 (0.0646) loss: 0.8434 (0.8452) time: 0.1399 data: 0.0646 max mem: 9394 +Train: [13] [3800/6250] eta: 0:06:07 lr: 0.000122 grad: 0.0599 (0.0645) loss: 0.8392 (0.8452) time: 0.1376 data: 0.0596 max mem: 9394 +Train: [13] [3900/6250] eta: 0:05:51 lr: 0.000122 grad: 0.0602 (0.0644) loss: 0.8451 (0.8452) time: 0.1399 data: 0.0609 max mem: 9394 +Train: [13] [4000/6250] eta: 0:05:35 lr: 0.000122 grad: 0.0623 (0.0644) loss: 0.8440 (0.8452) time: 0.1350 data: 0.0547 max mem: 9394 +Train: [13] [4100/6250] eta: 0:05:20 lr: 0.000122 grad: 0.0614 (0.0643) loss: 0.8458 (0.8452) time: 0.1362 data: 0.0509 max mem: 9394 +Train: [13] [4200/6250] eta: 0:05:04 lr: 0.000122 grad: 0.0616 (0.0643) loss: 0.8446 (0.8452) time: 0.1531 data: 0.0687 max mem: 9394 +Train: [13] [4300/6250] eta: 0:04:49 lr: 0.000122 grad: 0.0588 (0.0643) loss: 0.8459 (0.8451) time: 0.1376 data: 0.0562 max mem: 9394 +Train: [13] [4400/6250] eta: 0:04:33 lr: 0.000122 grad: 0.0606 (0.0643) loss: 0.8428 (0.8451) time: 0.1262 data: 0.0465 max mem: 9394 +Train: [13] [4500/6250] eta: 0:04:18 lr: 0.000122 grad: 0.0606 (0.0642) loss: 0.8422 (0.8450) time: 0.1216 data: 0.0420 max mem: 9394 +Train: [13] [4600/6250] eta: 0:04:02 lr: 0.000122 grad: 0.0606 (0.0642) loss: 0.8431 (0.8450) time: 0.1380 data: 0.0571 max mem: 9394 +Train: [13] [4700/6250] eta: 0:03:47 lr: 0.000122 grad: 0.0604 (0.0641) loss: 0.8439 (0.8450) time: 0.1475 data: 0.0588 max mem: 9394 +Train: [13] [4800/6250] eta: 0:03:32 lr: 0.000122 grad: 0.0608 (0.0641) loss: 0.8470 (0.8449) time: 0.1448 data: 0.0685 max mem: 9394 +Train: [13] [4900/6250] eta: 0:03:17 lr: 0.000122 grad: 0.0599 (0.0641) loss: 0.8426 (0.8449) time: 0.1003 data: 0.0181 max mem: 9394 +Train: [13] [5000/6250] eta: 0:03:02 lr: 0.000122 grad: 0.0579 (0.0641) loss: 0.8441 (0.8449) time: 0.1587 data: 0.0827 max mem: 9394 +Train: [13] [5100/6250] eta: 0:02:47 lr: 0.000122 grad: 0.0596 (0.0640) loss: 0.8451 (0.8450) time: 0.1347 data: 0.0533 max mem: 9394 +Train: [13] [5200/6250] eta: 0:02:32 lr: 0.000122 grad: 0.0593 (0.0640) loss: 0.8444 (0.8450) time: 0.1024 data: 0.0186 max mem: 9394 +Train: [13] [5300/6250] eta: 0:02:18 lr: 0.000122 grad: 0.0603 (0.0640) loss: 0.8476 (0.8450) time: 0.1327 data: 0.0543 max mem: 9394 +Train: [13] [5400/6250] eta: 0:02:03 lr: 0.000122 grad: 0.0601 (0.0640) loss: 0.8450 (0.8450) time: 0.1377 data: 0.0585 max mem: 9394 +Train: [13] [5500/6250] eta: 0:01:48 lr: 0.000122 grad: 0.0610 (0.0639) loss: 0.8431 (0.8450) time: 0.1335 data: 0.0508 max mem: 9394 +Train: [13] [5600/6250] eta: 0:01:34 lr: 0.000122 grad: 0.0608 (0.0639) loss: 0.8405 (0.8450) time: 0.1345 data: 0.0553 max mem: 9394 +Train: [13] [5700/6250] eta: 0:01:19 lr: 0.000122 grad: 0.0601 (0.0639) loss: 0.8411 (0.8449) time: 0.1452 data: 0.0637 max mem: 9394 +Train: [13] [5800/6250] eta: 0:01:04 lr: 0.000122 grad: 0.0625 (0.0639) loss: 0.8463 (0.8450) time: 0.1290 data: 0.0497 max mem: 9394 +Train: [13] [5900/6250] eta: 0:00:50 lr: 0.000122 grad: 0.0608 (0.0638) loss: 0.8481 (0.8450) time: 0.1335 data: 0.0556 max mem: 9394 +Train: [13] [6000/6250] eta: 0:00:35 lr: 0.000122 grad: 0.0609 (0.0638) loss: 0.8434 (0.8450) time: 0.1497 data: 0.0725 max mem: 9394 +Train: [13] [6100/6250] eta: 0:00:21 lr: 0.000122 grad: 0.0620 (0.0638) loss: 0.8449 (0.8450) time: 0.0897 data: 0.0002 max mem: 9394 +Train: [13] [6200/6250] eta: 0:00:07 lr: 0.000122 grad: 0.0600 (0.0638) loss: 0.8459 (0.8450) time: 0.1508 data: 0.0752 max mem: 9394 +Train: [13] [6249/6250] eta: 0:00:00 lr: 0.000122 grad: 0.0607 (0.0638) loss: 0.8440 (0.8450) time: 0.1692 data: 0.0829 max mem: 9394 +Train: [13] Total time: 0:15:09 (0.1454 s / it) +Averaged stats: lr: 0.000122 grad: 0.0607 (0.0638) loss: 0.8440 (0.8450) +Eval (hcp-train-subset): [13] [ 0/62] eta: 0:04:37 loss: 0.8594 (0.8594) time: 4.4816 data: 4.4499 max mem: 9394 +Eval (hcp-train-subset): [13] [61/62] eta: 0:00:00 loss: 0.8500 (0.8498) time: 0.1308 data: 0.1055 max mem: 9394 +Eval (hcp-train-subset): [13] Total time: 0:00:13 (0.2187 s / it) +Averaged stats (hcp-train-subset): loss: 0.8500 (0.8498) +Eval (hcp-val): [13] [ 0/62] eta: 0:05:07 loss: 0.8396 (0.8396) time: 4.9588 data: 4.9291 max mem: 9394 +Eval (hcp-val): [13] [61/62] eta: 0:00:00 loss: 0.8430 (0.8447) time: 0.1105 data: 0.0853 max mem: 9394 +Eval (hcp-val): [13] Total time: 0:00:12 (0.2021 s / it) +Averaged stats (hcp-val): loss: 0.8430 (0.8447) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +Train: [14] [ 0/6250] eta: 9:02:27 lr: 0.000122 grad: 0.0619 (0.0619) loss: 0.8714 (0.8714) time: 5.2076 data: 5.1141 max mem: 9394 +Train: [14] [ 100/6250] eta: 0:20:07 lr: 0.000122 grad: 0.0669 (0.0726) loss: 0.8484 (0.8504) time: 0.1546 data: 0.0754 max mem: 9394 +Train: [14] [ 200/6250] eta: 0:17:25 lr: 0.000122 grad: 0.0600 (0.0702) loss: 0.8470 (0.8477) time: 0.1434 data: 0.0572 max mem: 9394 +Train: [14] [ 300/6250] eta: 0:15:46 lr: 0.000122 grad: 0.0628 (0.0688) loss: 0.8395 (0.8450) time: 0.1284 data: 0.0452 max mem: 9394 +pretraining fmri mae +start: 2026-03-31 20:03:58 +cwd: /data/connor/fmri-fm +sha: 7f4cedc35609f6857314e0d1ea6657523f17ddeb, status: has uncommitted changes, branch: dev/clane9 +config: +name: input_space_v3/flat_lr1e-3_3/pretrain +notes: input_space ablation v3 flat_lr1e-3_3; use tube masking and on-disk data (input_space=flat + base_lr=1e-3 seed=5403) +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain +input_space: flat +patch_size: 16 +num_frames: 16 +t_patch_size: 4 +mask_ratio: 0.9 +pred_mask_ratio: null +masking: tube +masking_kwargs: {} +mask_patch_size: null +model: mae_vit_base +model_kwargs: + decoding: attn + pos_embed: sep + target_norm: null + pca_norm_nc: 2 + t_pred_stride: 2 + no_decode_pos: true + mask_drop_scale: false + pred_edge_pad: 0 + gauss_sigma: null + class_token: true + reg_tokens: 0 + no_embed_class: true + head_init_scale: 0.0 + decoder_depth: 4 + drop_path_rate: 0.0 +datasets: + hcp-train: + type: wds + url: /data/fmri-datasets/pretrain/hcpya-all.${input_space}.wds/hcpya-all-${input_space}-{00000..01799}.tar + clipping: random + clipping_kwargs: + oversample: 4.0 + shuffle: true + buffer_size: 2000 + samples_per_epoch: 200000 + hcp-train-subset: + type: arrow + root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/validation + split_range: + - 0 + - 2000 + shuffle: false + hcp-val: + type: arrow + root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/test + split_range: + - 0 + - 2000 + shuffle: false +train_dataset: hcp-train +eval_datasets: +- hcp-train-subset +- hcp-val +val_dataset: null +clip_vmax: 3.0 +normalize: frame +tr_scale: null +crop_scale: null +crop_aspect: null +gray_jitter: null +num_workers: 16 +epochs: 100 +batch_size: 32 +accum_iter: 1 +base_lr: 0.001 +min_lr: 0.0 +warmup_epochs: 5 +weight_decay: 0.05 +betas: +- 0.9 +- 0.95 +clip_grad: 1.0 +amp: true +amp_dtype: float16 +ckpt: null +resume: true +auto_resume: true +start_epoch: 0 +max_checkpoints: 0 +checkpoint_period: null +plot_period: 5 +device: cuda +presend_cuda: false +seed: 5403 +debug: false +wandb: true +wandb_entity: null +wandb_project: fMRI-foundation-model +rank: 0 +world_size: 1 +gpu: 0 +distributed: true +dist_backend: nccl +in_chans: 1 +img_size: +- 224 +- 560 + +train transform: +Compose( + ToTensor() + TemporalCenterCrop(num_frames=16) + Normalize(mode='frame') + Clip(vmax=3.0) + FlatUnmask((224, 560)) +) +val transform: +Compose( + ToTensor() + TemporalCenterCrop(num_frames=16) + Normalize(mode='frame') + Clip(vmax=3.0) + FlatUnmask((224, 560)) +) +mask generator: +TubeMasking( + mask_ratio=0.9 + (patchify): Patchify2D((224, 560), (16, 16), in_chans=1) +) +loading dataset: hcp-train + +type: wds +url: /data/fmri-datasets/pretrain/hcpya-all.${input_space}.wds/hcpya-all-${input_space}-{00000..01799}.tar +clipping: random +clipping_kwargs: + oversample: 4.0 +shuffle: true +buffer_size: 2000 +samples_per_epoch: 200000 + +loading dataset: hcp-train-subset + +type: arrow +root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/validation +split_range: +- 0 +- 2000 +shuffle: false + +split indices: [899, 472, 767, 116, 1265, 1852, 300, 1335, 361, 1560] +loading dataset: hcp-val + +type: arrow +root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/test +split_range: +- 0 +- 2000 +shuffle: false + +split indices: [1075, 1189, 738, 1350, 965, 1964, 1367, 1183, 1619, 1407] +model: +MaskedAutoencoderViT( + decoding=attn, t_pred_stride=2, pred_edge_pad=0, no_decode_pos=True + (encoder): MaskedEncoder( + class_token=True, reg_tokens=0, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) + (pred_patchify): StridedPatchify3D((16, 224, 560), (2, 16, 16), in_chans=1, t_stride=2) + (decoder): MaskedDecoder( + cross_decode=False, class_token=True, no_embed_class=True + (pos_embed): SeparablePosEmbed(512, (4, 14, 35)) + (proj): Linear(in_features=768, out_features=512, bias=True) + (blocks): ModuleList( + (0-3): 4 x Block( + (norm1): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=16 + (q): Linear(in_features=512, out_features=512, bias=True) + (k): Linear(in_features=512, out_features=512, bias=True) + (v): Linear(in_features=512, out_features=512, bias=True) + (proj): Linear(in_features=512, out_features=512, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=512, out_features=2048, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=2048, out_features=512, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (head): Linear(in_features=512, out_features=512, bias=True) + ) +) +num params: 99.7M +total batch size: 32 = 32 bs per gpu x 1 accum x 1 gpus +lr: 1.25e-04 = 1.00e-03 x 32 / 256 +full schedule: epochs = 100 (steps = 625000) +warmup: epochs = 5 (steps = 31250) +loaded model state from checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +loaded optimizer state, resuming training from 14 +start training for 100 epochs +Train: [14] [ 0/6250] eta: 12:47:51 lr: 0.000122 grad: 0.0397 (0.0397) loss: 0.8849 (0.8849) time: 7.3715 data: 6.3153 max mem: 9353 +Train: [14] [ 100/6250] eta: 0:20:15 lr: 0.000122 grad: 0.0607 (0.0676) loss: 0.8359 (0.8445) time: 0.1253 data: 0.0482 max mem: 9390 +Train: [14] [ 200/6250] eta: 0:17:04 lr: 0.000122 grad: 0.0600 (0.0662) loss: 0.8399 (0.8452) time: 0.1220 data: 0.0359 max mem: 9390 +Train: [14] [ 300/6250] eta: 0:16:08 lr: 0.000122 grad: 0.0626 (0.0655) loss: 0.8446 (0.8435) time: 0.1421 data: 0.0563 max mem: 9390 +Train: [14] [ 400/6250] eta: 0:15:59 lr: 0.000122 grad: 0.0627 (0.0656) loss: 0.8462 (0.8435) time: 0.1642 data: 0.0780 max mem: 9390 +Train: [14] [ 500/6250] eta: 0:16:34 lr: 0.000122 grad: 0.0645 (0.0652) loss: 0.8416 (0.8434) time: 0.2521 data: 0.1297 max mem: 9390 +Train: [14] [ 600/6250] eta: 0:16:24 lr: 0.000122 grad: 0.0614 (0.0649) loss: 0.8432 (0.8431) time: 0.2250 data: 0.1217 max mem: 9390 +Train: [14] [ 700/6250] eta: 0:15:46 lr: 0.000122 grad: 0.0594 (0.0650) loss: 0.8433 (0.8429) time: 0.2111 data: 0.1218 max mem: 9390 +Train: [14] [ 800/6250] eta: 0:15:11 lr: 0.000122 grad: 0.0601 (0.0650) loss: 0.8410 (0.8428) time: 0.1128 data: 0.0208 max mem: 9390 +Train: [14] [ 900/6250] eta: 0:14:41 lr: 0.000122 grad: 0.0641 (0.0649) loss: 0.8399 (0.8430) time: 0.1423 data: 0.0624 max mem: 9390 +Train: [14] [1000/6250] eta: 0:14:05 lr: 0.000122 grad: 0.0614 (0.0650) loss: 0.8441 (0.8430) time: 0.1333 data: 0.0499 max mem: 9390 +Train: [14] [1100/6250] eta: 0:13:36 lr: 0.000122 grad: 0.0606 (0.0648) loss: 0.8446 (0.8431) time: 0.1255 data: 0.0421 max mem: 9390 +Train: [14] [1200/6250] eta: 0:13:12 lr: 0.000122 grad: 0.0620 (0.0648) loss: 0.8376 (0.8430) time: 0.1370 data: 0.0544 max mem: 9390 +Train: [14] [1300/6250] eta: 0:12:50 lr: 0.000122 grad: 0.0624 (0.0648) loss: 0.8427 (0.8430) time: 0.1419 data: 0.0564 max mem: 9390 +Train: [14] [1400/6250] eta: 0:12:24 lr: 0.000122 grad: 0.0644 (0.0648) loss: 0.8427 (0.8430) time: 0.1131 data: 0.0338 max mem: 9390 +Train: [14] [1500/6250] eta: 0:12:03 lr: 0.000122 grad: 0.0672 (0.0649) loss: 0.8388 (0.8430) time: 0.1362 data: 0.0553 max mem: 9390 +Train: [14] [1600/6250] eta: 0:11:42 lr: 0.000122 grad: 0.0638 (0.0649) loss: 0.8416 (0.8429) time: 0.1204 data: 0.0430 max mem: 9390 +Train: [14] [1700/6250] eta: 0:11:20 lr: 0.000122 grad: 0.0652 (0.0648) loss: 0.8433 (0.8428) time: 0.1218 data: 0.0416 max mem: 9390 +Train: [14] [1800/6250] eta: 0:11:01 lr: 0.000122 grad: 0.0584 (0.0647) loss: 0.8455 (0.8427) time: 0.1354 data: 0.0610 max mem: 9390 +Train: [14] [1900/6250] eta: 0:10:44 lr: 0.000122 grad: 0.0615 (0.0646) loss: 0.8454 (0.8427) time: 0.1399 data: 0.0578 max mem: 9390 +Train: [14] [2000/6250] eta: 0:10:25 lr: 0.000122 grad: 0.0607 (0.0647) loss: 0.8476 (0.8427) time: 0.1363 data: 0.0559 max mem: 9390 +Train: [14] [2100/6250] eta: 0:10:06 lr: 0.000122 grad: 0.0636 (0.0646) loss: 0.8434 (0.8427) time: 0.1313 data: 0.0543 max mem: 9390 +Train: [14] [2200/6250] eta: 0:09:48 lr: 0.000122 grad: 0.0618 (0.0646) loss: 0.8455 (0.8428) time: 0.1100 data: 0.0322 max mem: 9390 +Train: [14] [2300/6250] eta: 0:09:31 lr: 0.000122 grad: 0.0616 (0.0646) loss: 0.8427 (0.8427) time: 0.1380 data: 0.0644 max mem: 9390 +Train: [14] [2400/6250] eta: 0:09:15 lr: 0.000122 grad: 0.0610 (0.0646) loss: 0.8420 (0.8427) time: 0.1279 data: 0.0461 max mem: 9390 +Train: [14] [2500/6250] eta: 0:08:59 lr: 0.000122 grad: 0.0606 (0.0646) loss: 0.8467 (0.8427) time: 0.1109 data: 0.0250 max mem: 9390 +Train: [14] [2600/6250] eta: 0:08:43 lr: 0.000122 grad: 0.0606 (0.0646) loss: 0.8449 (0.8428) time: 0.1239 data: 0.0474 max mem: 9390 +Train: [14] [2700/6250] eta: 0:08:27 lr: 0.000122 grad: 0.0603 (0.0645) loss: 0.8449 (0.8429) time: 0.1440 data: 0.0629 max mem: 9390 +Train: [14] [2800/6250] eta: 0:08:12 lr: 0.000122 grad: 0.0587 (0.0644) loss: 0.8474 (0.8430) time: 0.1452 data: 0.0625 max mem: 9390 +Train: [14] [2900/6250] eta: 0:07:56 lr: 0.000122 grad: 0.0589 (0.0644) loss: 0.8455 (0.8431) time: 0.1215 data: 0.0390 max mem: 9390 +Train: [14] [3000/6250] eta: 0:07:40 lr: 0.000122 grad: 0.0614 (0.0643) loss: 0.8499 (0.8432) time: 0.1321 data: 0.0553 max mem: 9390 +Train: [14] [3100/6250] eta: 0:07:25 lr: 0.000122 grad: 0.0657 (0.0643) loss: 0.8418 (0.8433) time: 0.1416 data: 0.0585 max mem: 9390 +Train: [14] [3200/6250] eta: 0:07:10 lr: 0.000122 grad: 0.0624 (0.0643) loss: 0.8469 (0.8434) time: 0.1426 data: 0.0682 max mem: 9390 +Train: [14] [3300/6250] eta: 0:06:55 lr: 0.000122 grad: 0.0617 (0.0644) loss: 0.8440 (0.8435) time: 0.1570 data: 0.0640 max mem: 9390 +Train: [14] [3400/6250] eta: 0:06:41 lr: 0.000122 grad: 0.0619 (0.0643) loss: 0.8450 (0.8435) time: 0.1338 data: 0.0517 max mem: 9390 +Train: [14] [3500/6250] eta: 0:06:26 lr: 0.000122 grad: 0.0605 (0.0644) loss: 0.8447 (0.8435) time: 0.1356 data: 0.0611 max mem: 9390 +Train: [14] [3600/6250] eta: 0:06:12 lr: 0.000122 grad: 0.0600 (0.0643) loss: 0.8437 (0.8436) time: 0.1406 data: 0.0639 max mem: 9390 +Train: [14] [3700/6250] eta: 0:05:57 lr: 0.000122 grad: 0.0643 (0.0643) loss: 0.8462 (0.8437) time: 0.1476 data: 0.0736 max mem: 9390 +Train: [14] [3800/6250] eta: 0:05:43 lr: 0.000122 grad: 0.0604 (0.0643) loss: 0.8374 (0.8437) time: 0.1373 data: 0.0533 max mem: 9390 +Train: [14] [3900/6250] eta: 0:05:28 lr: 0.000122 grad: 0.0589 (0.0642) loss: 0.8505 (0.8438) time: 0.1398 data: 0.0565 max mem: 9390 +Train: [14] [4000/6250] eta: 0:05:14 lr: 0.000122 grad: 0.0594 (0.0642) loss: 0.8459 (0.8438) time: 0.1242 data: 0.0434 max mem: 9390 +Train: [14] [4100/6250] eta: 0:04:59 lr: 0.000122 grad: 0.0652 (0.0642) loss: 0.8413 (0.8439) time: 0.1258 data: 0.0453 max mem: 9390 +Train: [14] [4200/6250] eta: 0:04:45 lr: 0.000122 grad: 0.0658 (0.0642) loss: 0.8435 (0.8439) time: 0.1288 data: 0.0477 max mem: 9390 +Train: [14] [4300/6250] eta: 0:04:31 lr: 0.000122 grad: 0.0630 (0.0642) loss: 0.8463 (0.8439) time: 0.1208 data: 0.0418 max mem: 9390 +Train: [14] [4400/6250] eta: 0:04:17 lr: 0.000122 grad: 0.0646 (0.0643) loss: 0.8419 (0.8439) time: 0.1460 data: 0.0708 max mem: 9390 +Train: [14] [4500/6250] eta: 0:04:03 lr: 0.000122 grad: 0.0589 (0.0643) loss: 0.8449 (0.8439) time: 0.1473 data: 0.0680 max mem: 9390 +Train: [14] [4600/6250] eta: 0:03:49 lr: 0.000122 grad: 0.0599 (0.0642) loss: 0.8403 (0.8439) time: 0.1300 data: 0.0550 max mem: 9390 +Train: [14] [4700/6250] eta: 0:03:35 lr: 0.000122 grad: 0.0611 (0.0642) loss: 0.8446 (0.8439) time: 0.0981 data: 0.0167 max mem: 9390 +Train: [14] [4800/6250] eta: 0:03:21 lr: 0.000122 grad: 0.0647 (0.0642) loss: 0.8438 (0.8439) time: 0.1345 data: 0.0565 max mem: 9390 +Train: [14] [4900/6250] eta: 0:03:07 lr: 0.000122 grad: 0.0638 (0.0642) loss: 0.8422 (0.8439) time: 0.1391 data: 0.0566 max mem: 9390 +Train: [14] [5000/6250] eta: 0:02:53 lr: 0.000122 grad: 0.0632 (0.0643) loss: 0.8392 (0.8438) time: 0.1465 data: 0.0712 max mem: 9390 +Train: [14] [5100/6250] eta: 0:02:39 lr: 0.000122 grad: 0.0592 (0.0643) loss: 0.8458 (0.8438) time: 0.1369 data: 0.0593 max mem: 9390 +Train: [14] [5200/6250] eta: 0:02:25 lr: 0.000122 grad: 0.0618 (0.0643) loss: 0.8370 (0.8438) time: 0.1321 data: 0.0545 max mem: 9390 +Train: [14] [5300/6250] eta: 0:02:11 lr: 0.000122 grad: 0.0563 (0.0642) loss: 0.8510 (0.8438) time: 0.1320 data: 0.0581 max mem: 9390 +Train: [14] [5400/6250] eta: 0:01:57 lr: 0.000122 grad: 0.0607 (0.0642) loss: 0.8440 (0.8439) time: 0.1286 data: 0.0509 max mem: 9390 +Train: [14] [5500/6250] eta: 0:01:43 lr: 0.000122 grad: 0.0620 (0.0642) loss: 0.8432 (0.8439) time: 0.1339 data: 0.0572 max mem: 9390 +Train: [14] [5600/6250] eta: 0:01:29 lr: 0.000122 grad: 0.0609 (0.0642) loss: 0.8449 (0.8439) time: 0.1265 data: 0.0487 max mem: 9390 +Train: [14] [5700/6250] eta: 0:01:15 lr: 0.000122 grad: 0.0635 (0.0642) loss: 0.8399 (0.8439) time: 0.1306 data: 0.0521 max mem: 9390 +Train: [14] [5800/6250] eta: 0:01:02 lr: 0.000122 grad: 0.0612 (0.0641) loss: 0.8481 (0.8439) time: 0.1422 data: 0.0656 max mem: 9390 +Train: [14] [5900/6250] eta: 0:00:48 lr: 0.000122 grad: 0.0607 (0.0641) loss: 0.8494 (0.8440) time: 0.1355 data: 0.0611 max mem: 9390 +Train: [14] [6000/6250] eta: 0:00:34 lr: 0.000122 grad: 0.0600 (0.0640) loss: 0.8450 (0.8440) time: 0.1282 data: 0.0492 max mem: 9390 +Train: [14] [6100/6250] eta: 0:00:20 lr: 0.000122 grad: 0.0583 (0.0640) loss: 0.8467 (0.8440) time: 0.1390 data: 0.0600 max mem: 9390 +Train: [14] [6200/6250] eta: 0:00:06 lr: 0.000122 grad: 0.0616 (0.0640) loss: 0.8445 (0.8440) time: 0.1326 data: 0.0607 max mem: 9390 +Train: [14] [6249/6250] eta: 0:00:00 lr: 0.000122 grad: 0.0654 (0.0640) loss: 0.8448 (0.8440) time: 0.1353 data: 0.0652 max mem: 9390 +Train: [14] Total time: 0:14:27 (0.1388 s / it) +Averaged stats: lr: 0.000122 grad: 0.0654 (0.0640) loss: 0.8448 (0.8440) +Eval (hcp-train-subset): [14] [ 0/62] eta: 0:04:32 loss: 0.8605 (0.8605) time: 4.4003 data: 4.3705 max mem: 9390 +Eval (hcp-train-subset): [14] [61/62] eta: 0:00:00 loss: 0.8482 (0.8497) time: 0.1487 data: 0.1238 max mem: 9390 +Eval (hcp-train-subset): [14] Total time: 0:00:12 (0.2058 s / it) +Averaged stats (hcp-train-subset): loss: 0.8482 (0.8497) +Making plots (hcp-train-subset): example=36 +Eval (hcp-val): [14] [ 0/62] eta: 0:03:17 loss: 0.8428 (0.8428) time: 3.1842 data: 3.1132 max mem: 9390 +Eval (hcp-val): [14] [61/62] eta: 0:00:00 loss: 0.8450 (0.8448) time: 0.1122 data: 0.0849 max mem: 9390 +Eval (hcp-val): [14] Total time: 0:00:12 (0.1954 s / it) +Averaged stats (hcp-val): loss: 0.8450 (0.8448) +Making plots (hcp-val): example=61 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +Train: [15] [ 0/6250] eta: 9:34:44 lr: 0.000122 grad: 0.0388 (0.0388) loss: 0.8861 (0.8861) time: 5.5175 data: 5.4185 max mem: 9390 +Train: [15] [ 100/6250] eta: 0:18:57 lr: 0.000122 grad: 0.0662 (0.0696) loss: 0.8295 (0.8416) time: 0.1415 data: 0.0652 max mem: 9390 +Train: [15] [ 200/6250] eta: 0:16:13 lr: 0.000122 grad: 0.0677 (0.0695) loss: 0.8421 (0.8402) time: 0.1365 data: 0.0571 max mem: 9390 +Train: [15] [ 300/6250] eta: 0:14:57 lr: 0.000122 grad: 0.0666 (0.0694) loss: 0.8441 (0.8406) time: 0.1250 data: 0.0421 max mem: 9390 +Train: [15] [ 400/6250] eta: 0:14:01 lr: 0.000122 grad: 0.0648 (0.0691) loss: 0.8420 (0.8406) time: 0.1125 data: 0.0245 max mem: 9390 +Train: [15] [ 500/6250] eta: 0:13:20 lr: 0.000122 grad: 0.0625 (0.0686) loss: 0.8404 (0.8403) time: 0.1182 data: 0.0369 max mem: 9390 +Train: [15] [ 600/6250] eta: 0:12:51 lr: 0.000122 grad: 0.0633 (0.0680) loss: 0.8370 (0.8400) time: 0.1097 data: 0.0249 max mem: 9390 +Train: [15] [ 700/6250] eta: 0:12:28 lr: 0.000122 grad: 0.0620 (0.0677) loss: 0.8363 (0.8399) time: 0.1159 data: 0.0338 max mem: 9390 +Train: [15] [ 800/6250] eta: 0:12:17 lr: 0.000122 grad: 0.0628 (0.0675) loss: 0.8409 (0.8400) time: 0.1292 data: 0.0512 max mem: 9390 +Train: [15] [ 900/6250] eta: 0:12:07 lr: 0.000122 grad: 0.0621 (0.0671) loss: 0.8437 (0.8403) time: 0.1554 data: 0.0765 max mem: 9390 +Train: [15] [1000/6250] eta: 0:11:54 lr: 0.000122 grad: 0.0587 (0.0669) loss: 0.8472 (0.8406) time: 0.1443 data: 0.0642 max mem: 9390 +Train: [15] [1100/6250] eta: 0:11:44 lr: 0.000121 grad: 0.0582 (0.0666) loss: 0.8458 (0.8407) time: 0.1635 data: 0.0858 max mem: 9390 +Train: [15] [1200/6250] eta: 0:11:33 lr: 0.000121 grad: 0.0587 (0.0662) loss: 0.8454 (0.8409) time: 0.1550 data: 0.0816 max mem: 9390 +Train: [15] [1300/6250] eta: 0:11:16 lr: 0.000121 grad: 0.0591 (0.0659) loss: 0.8461 (0.8411) time: 0.1407 data: 0.0650 max mem: 9390 +Train: [15] [1400/6250] eta: 0:11:04 lr: 0.000121 grad: 0.0607 (0.0657) loss: 0.8437 (0.8412) time: 0.1305 data: 0.0466 max mem: 9390 +Train: [15] [1500/6250] eta: 0:10:51 lr: 0.000121 grad: 0.0588 (0.0654) loss: 0.8419 (0.8414) time: 0.1408 data: 0.0632 max mem: 9390 +Train: [15] [1600/6250] eta: 0:10:38 lr: 0.000121 grad: 0.0590 (0.0653) loss: 0.8442 (0.8416) time: 0.1374 data: 0.0566 max mem: 9390 +Train: [15] [1700/6250] eta: 0:10:22 lr: 0.000121 grad: 0.0579 (0.0652) loss: 0.8457 (0.8418) time: 0.1240 data: 0.0465 max mem: 9390 +Train: [15] [1800/6250] eta: 0:10:09 lr: 0.000121 grad: 0.0589 (0.0651) loss: 0.8417 (0.8419) time: 0.1275 data: 0.0477 max mem: 9390 +Train: [15] [1900/6250] eta: 0:09:54 lr: 0.000121 grad: 0.0635 (0.0650) loss: 0.8454 (0.8420) time: 0.1462 data: 0.0652 max mem: 9390 +Train: [15] [2000/6250] eta: 0:09:39 lr: 0.000121 grad: 0.0643 (0.0650) loss: 0.8405 (0.8420) time: 0.1471 data: 0.0618 max mem: 9390 +Train: [15] [2100/6250] eta: 0:09:25 lr: 0.000121 grad: 0.0610 (0.0649) loss: 0.8439 (0.8421) time: 0.1342 data: 0.0508 max mem: 9390 +Train: [15] [2200/6250] eta: 0:09:11 lr: 0.000121 grad: 0.0624 (0.0649) loss: 0.8405 (0.8421) time: 0.1221 data: 0.0452 max mem: 9390 +Train: [15] [2300/6250] eta: 0:08:58 lr: 0.000121 grad: 0.0674 (0.0649) loss: 0.8405 (0.8421) time: 0.1368 data: 0.0626 max mem: 9390 +Train: [15] [2400/6250] eta: 0:08:44 lr: 0.000121 grad: 0.0601 (0.0649) loss: 0.8448 (0.8421) time: 0.1321 data: 0.0536 max mem: 9390 +Train: [15] [2500/6250] eta: 0:08:31 lr: 0.000121 grad: 0.0615 (0.0648) loss: 0.8450 (0.8421) time: 0.1735 data: 0.0985 max mem: 9390 +Train: [15] [2600/6250] eta: 0:08:17 lr: 0.000121 grad: 0.0612 (0.0648) loss: 0.8425 (0.8421) time: 0.1474 data: 0.0709 max mem: 9390 +Train: [15] [2700/6250] eta: 0:08:04 lr: 0.000121 grad: 0.0609 (0.0648) loss: 0.8451 (0.8422) time: 0.1480 data: 0.0748 max mem: 9390 +Train: [15] [2800/6250] eta: 0:07:50 lr: 0.000121 grad: 0.0621 (0.0649) loss: 0.8397 (0.8421) time: 0.1289 data: 0.0439 max mem: 9390 +Train: [15] [2900/6250] eta: 0:07:36 lr: 0.000121 grad: 0.0615 (0.0649) loss: 0.8429 (0.8421) time: 0.1262 data: 0.0477 max mem: 9390 +Train: [15] [3000/6250] eta: 0:07:23 lr: 0.000121 grad: 0.0642 (0.0649) loss: 0.8410 (0.8421) time: 0.1429 data: 0.0651 max mem: 9390 +Train: [15] [3100/6250] eta: 0:07:09 lr: 0.000121 grad: 0.0612 (0.0649) loss: 0.8434 (0.8421) time: 0.1216 data: 0.0443 max mem: 9390 +Train: [15] [3200/6250] eta: 0:06:55 lr: 0.000121 grad: 0.0615 (0.0648) loss: 0.8420 (0.8420) time: 0.1520 data: 0.0749 max mem: 9390 +Train: [15] [3300/6250] eta: 0:06:41 lr: 0.000121 grad: 0.0630 (0.0648) loss: 0.8331 (0.8419) time: 0.1107 data: 0.0389 max mem: 9390 +Train: [15] [3400/6250] eta: 0:06:28 lr: 0.000121 grad: 0.0635 (0.0648) loss: 0.8435 (0.8420) time: 0.1380 data: 0.0592 max mem: 9390 +Train: [15] [3500/6250] eta: 0:06:14 lr: 0.000121 grad: 0.0613 (0.0648) loss: 0.8444 (0.8420) time: 0.1214 data: 0.0447 max mem: 9390 +Train: [15] [3600/6250] eta: 0:06:00 lr: 0.000121 grad: 0.0644 (0.0648) loss: 0.8410 (0.8419) time: 0.1344 data: 0.0559 max mem: 9390 +Train: [15] [3700/6250] eta: 0:05:46 lr: 0.000121 grad: 0.0622 (0.0648) loss: 0.8376 (0.8419) time: 0.1245 data: 0.0450 max mem: 9390 +Train: [15] [3800/6250] eta: 0:05:33 lr: 0.000121 grad: 0.0607 (0.0648) loss: 0.8434 (0.8419) time: 0.1371 data: 0.0589 max mem: 9390 +Train: [15] [3900/6250] eta: 0:05:19 lr: 0.000121 grad: 0.0623 (0.0648) loss: 0.8448 (0.8419) time: 0.1219 data: 0.0397 max mem: 9390 +Train: [15] [4000/6250] eta: 0:05:06 lr: 0.000121 grad: 0.0612 (0.0647) loss: 0.8432 (0.8418) time: 0.1516 data: 0.0718 max mem: 9390 +Train: [15] [4100/6250] eta: 0:04:52 lr: 0.000121 grad: 0.0627 (0.0647) loss: 0.8352 (0.8418) time: 0.1410 data: 0.0623 max mem: 9390 +Train: [15] [4200/6250] eta: 0:04:39 lr: 0.000121 grad: 0.0659 (0.0648) loss: 0.8407 (0.8418) time: 0.1378 data: 0.0621 max mem: 9390 +Train: [15] [4300/6250] eta: 0:04:25 lr: 0.000121 grad: 0.0637 (0.0647) loss: 0.8437 (0.8418) time: 0.1073 data: 0.0324 max mem: 9390 +Train: [15] [4400/6250] eta: 0:04:12 lr: 0.000121 grad: 0.0604 (0.0647) loss: 0.8476 (0.8418) time: 0.1458 data: 0.0670 max mem: 9390 +Train: [15] [4500/6250] eta: 0:03:58 lr: 0.000121 grad: 0.0631 (0.0647) loss: 0.8436 (0.8418) time: 0.1180 data: 0.0370 max mem: 9390 +Train: [15] [4600/6250] eta: 0:03:44 lr: 0.000121 grad: 0.0646 (0.0647) loss: 0.8469 (0.8417) time: 0.1394 data: 0.0637 max mem: 9390 +Train: [15] [4700/6250] eta: 0:03:31 lr: 0.000121 grad: 0.0626 (0.0647) loss: 0.8391 (0.8417) time: 0.1291 data: 0.0534 max mem: 9390 +Train: [15] [4800/6250] eta: 0:03:17 lr: 0.000121 grad: 0.0633 (0.0647) loss: 0.8438 (0.8417) time: 0.1502 data: 0.0735 max mem: 9390 +Train: [15] [4900/6250] eta: 0:03:03 lr: 0.000121 grad: 0.0647 (0.0646) loss: 0.8378 (0.8417) time: 0.1282 data: 0.0484 max mem: 9390 +Train: [15] [5000/6250] eta: 0:02:50 lr: 0.000121 grad: 0.0610 (0.0646) loss: 0.8429 (0.8417) time: 0.1298 data: 0.0529 max mem: 9390 +Train: [15] [5100/6250] eta: 0:02:36 lr: 0.000121 grad: 0.0630 (0.0646) loss: 0.8393 (0.8417) time: 0.1258 data: 0.0455 max mem: 9390 +Train: [15] [5200/6250] eta: 0:02:22 lr: 0.000121 grad: 0.0649 (0.0646) loss: 0.8364 (0.8417) time: 0.1308 data: 0.0500 max mem: 9390 +Train: [15] [5300/6250] eta: 0:02:09 lr: 0.000121 grad: 0.0663 (0.0646) loss: 0.8402 (0.8416) time: 0.1269 data: 0.0463 max mem: 9390 +Train: [15] [5400/6250] eta: 0:01:55 lr: 0.000121 grad: 0.0627 (0.0646) loss: 0.8435 (0.8416) time: 0.1314 data: 0.0466 max mem: 9390 +Train: [15] [5500/6250] eta: 0:01:41 lr: 0.000121 grad: 0.0593 (0.0646) loss: 0.8453 (0.8417) time: 0.1257 data: 0.0469 max mem: 9390 +Train: [15] [5600/6250] eta: 0:01:28 lr: 0.000121 grad: 0.0629 (0.0646) loss: 0.8407 (0.8417) time: 0.1467 data: 0.0661 max mem: 9390 +Train: [15] [5700/6250] eta: 0:01:14 lr: 0.000121 grad: 0.0621 (0.0646) loss: 0.8438 (0.8417) time: 0.1432 data: 0.0685 max mem: 9390 +Train: [15] [5800/6250] eta: 0:01:00 lr: 0.000121 grad: 0.0637 (0.0647) loss: 0.8441 (0.8418) time: 0.1316 data: 0.0566 max mem: 9390 +Train: [15] [5900/6250] eta: 0:00:47 lr: 0.000121 grad: 0.0639 (0.0647) loss: 0.8447 (0.8417) time: 0.1283 data: 0.0485 max mem: 9390 +Train: [15] [6000/6250] eta: 0:00:33 lr: 0.000121 grad: 0.0619 (0.0647) loss: 0.8426 (0.8418) time: 0.1480 data: 0.0701 max mem: 9390 +Train: [15] [6100/6250] eta: 0:00:20 lr: 0.000121 grad: 0.0619 (0.0647) loss: 0.8401 (0.8417) time: 0.1115 data: 0.0286 max mem: 9390 +Train: [15] [6200/6250] eta: 0:00:06 lr: 0.000121 grad: 0.0652 (0.0647) loss: 0.8432 (0.8418) time: 0.1675 data: 0.0916 max mem: 9390 +Train: [15] [6249/6250] eta: 0:00:00 lr: 0.000121 grad: 0.0590 (0.0647) loss: 0.8389 (0.8418) time: 0.1352 data: 0.0520 max mem: 9390 +Train: [15] Total time: 0:14:10 (0.1360 s / it) +Averaged stats: lr: 0.000121 grad: 0.0590 (0.0647) loss: 0.8389 (0.8418) +Eval (hcp-train-subset): [15] [ 0/62] eta: 0:05:09 loss: 0.8586 (0.8586) time: 4.9851 data: 4.9536 max mem: 9390 +Eval (hcp-train-subset): [15] [61/62] eta: 0:00:00 loss: 0.8453 (0.8481) time: 0.1157 data: 0.0908 max mem: 9390 +Eval (hcp-train-subset): [15] Total time: 0:00:13 (0.2123 s / it) +Averaged stats (hcp-train-subset): loss: 0.8453 (0.8481) +Eval (hcp-val): [15] [ 0/62] eta: 0:02:41 loss: 0.8404 (0.8404) time: 2.5993 data: 2.5285 max mem: 9390 +Eval (hcp-val): [15] [61/62] eta: 0:00:00 loss: 0.8433 (0.8435) time: 0.1297 data: 0.1035 max mem: 9390 +Eval (hcp-val): [15] Total time: 0:00:11 (0.1892 s / it) +Averaged stats (hcp-val): loss: 0.8433 (0.8435) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +Train: [16] [ 0/6250] eta: 9:35:12 lr: 0.000121 grad: 0.0749 (0.0749) loss: 0.8322 (0.8322) time: 5.5220 data: 5.4135 max mem: 9390 +Train: [16] [ 100/6250] eta: 0:18:28 lr: 0.000121 grad: 0.0682 (0.0778) loss: 0.8354 (0.8409) time: 0.1343 data: 0.0555 max mem: 9390 +Train: [16] [ 200/6250] eta: 0:15:54 lr: 0.000121 grad: 0.0604 (0.0726) loss: 0.8360 (0.8387) time: 0.1287 data: 0.0520 max mem: 9390 +Train: [16] [ 300/6250] eta: 0:14:39 lr: 0.000121 grad: 0.0626 (0.0693) loss: 0.8492 (0.8394) time: 0.1408 data: 0.0590 max mem: 9390 +Train: [16] [ 400/6250] eta: 0:13:51 lr: 0.000121 grad: 0.0627 (0.0674) loss: 0.8433 (0.8402) time: 0.1155 data: 0.0322 max mem: 9390 +Train: [16] [ 500/6250] eta: 0:13:12 lr: 0.000121 grad: 0.0645 (0.0666) loss: 0.8436 (0.8404) time: 0.1040 data: 0.0195 max mem: 9390 +Train: [16] [ 600/6250] eta: 0:12:45 lr: 0.000121 grad: 0.0605 (0.0657) loss: 0.8366 (0.8403) time: 0.1141 data: 0.0193 max mem: 9390 +Train: [16] [ 700/6250] eta: 0:12:20 lr: 0.000121 grad: 0.0569 (0.0649) loss: 0.8497 (0.8408) time: 0.1300 data: 0.0492 max mem: 9390 +Train: [16] [ 800/6250] eta: 0:12:09 lr: 0.000121 grad: 0.0606 (0.0645) loss: 0.8462 (0.8410) time: 0.1538 data: 0.0751 max mem: 9390 +Train: [16] [ 900/6250] eta: 0:12:01 lr: 0.000121 grad: 0.0575 (0.0642) loss: 0.8424 (0.8411) time: 0.1381 data: 0.0451 max mem: 9390 +Train: [16] [1000/6250] eta: 0:11:52 lr: 0.000121 grad: 0.0621 (0.0640) loss: 0.8446 (0.8412) time: 0.1388 data: 0.0575 max mem: 9390 +Train: [16] [1100/6250] eta: 0:11:42 lr: 0.000121 grad: 0.0619 (0.0639) loss: 0.8452 (0.8412) time: 0.1353 data: 0.0574 max mem: 9390 +Train: [16] [1200/6250] eta: 0:11:30 lr: 0.000121 grad: 0.0628 (0.0638) loss: 0.8411 (0.8412) time: 0.1493 data: 0.0768 max mem: 9390 +Train: [16] [1300/6250] eta: 0:11:21 lr: 0.000121 grad: 0.0593 (0.0638) loss: 0.8411 (0.8413) time: 0.1516 data: 0.0716 max mem: 9390 +Train: [16] [1400/6250] eta: 0:11:05 lr: 0.000121 grad: 0.0658 (0.0638) loss: 0.8403 (0.8413) time: 0.1317 data: 0.0538 max mem: 9390 +Train: [16] [1500/6250] eta: 0:10:49 lr: 0.000121 grad: 0.0630 (0.0639) loss: 0.8408 (0.8411) time: 0.1357 data: 0.0602 max mem: 9390 +Train: [16] [1600/6250] eta: 0:10:37 lr: 0.000121 grad: 0.0611 (0.0640) loss: 0.8367 (0.8410) time: 0.1335 data: 0.0541 max mem: 9390 +Train: [16] [1700/6250] eta: 0:10:24 lr: 0.000121 grad: 0.0593 (0.0641) loss: 0.8373 (0.8409) time: 0.1387 data: 0.0584 max mem: 9390 +Train: [16] [1800/6250] eta: 0:10:09 lr: 0.000121 grad: 0.0628 (0.0640) loss: 0.8395 (0.8409) time: 0.1228 data: 0.0432 max mem: 9390 +Train: [16] [1900/6250] eta: 0:09:55 lr: 0.000121 grad: 0.0633 (0.0641) loss: 0.8409 (0.8409) time: 0.1422 data: 0.0625 max mem: 9390 +Train: [16] [2000/6250] eta: 0:09:42 lr: 0.000121 grad: 0.0590 (0.0641) loss: 0.8373 (0.8407) time: 0.1528 data: 0.0763 max mem: 9390 +Train: [16] [2100/6250] eta: 0:09:27 lr: 0.000121 grad: 0.0617 (0.0639) loss: 0.8342 (0.8407) time: 0.1394 data: 0.0584 max mem: 9390 +Train: [16] [2200/6250] eta: 0:09:14 lr: 0.000121 grad: 0.0595 (0.0638) loss: 0.8398 (0.8406) time: 0.1374 data: 0.0610 max mem: 9390 +Train: [16] [2300/6250] eta: 0:08:59 lr: 0.000121 grad: 0.0562 (0.0638) loss: 0.8429 (0.8406) time: 0.1239 data: 0.0438 max mem: 9390 +Train: [16] [2400/6250] eta: 0:08:47 lr: 0.000121 grad: 0.0611 (0.0638) loss: 0.8401 (0.8406) time: 0.1241 data: 0.0505 max mem: 9390 +Train: [16] [2500/6250] eta: 0:08:32 lr: 0.000121 grad: 0.0595 (0.0638) loss: 0.8427 (0.8405) time: 0.1369 data: 0.0621 max mem: 9390 +Train: [16] [2600/6250] eta: 0:08:18 lr: 0.000121 grad: 0.0639 (0.0637) loss: 0.8407 (0.8406) time: 0.1285 data: 0.0508 max mem: 9390 +Train: [16] [2700/6250] eta: 0:08:04 lr: 0.000121 grad: 0.0626 (0.0637) loss: 0.8337 (0.8405) time: 0.1355 data: 0.0599 max mem: 9390 +Train: [16] [2800/6250] eta: 0:07:49 lr: 0.000121 grad: 0.0601 (0.0637) loss: 0.8421 (0.8405) time: 0.1255 data: 0.0515 max mem: 9390 +Train: [16] [2900/6250] eta: 0:07:35 lr: 0.000121 grad: 0.0597 (0.0637) loss: 0.8440 (0.8406) time: 0.1308 data: 0.0524 max mem: 9390 +Train: [16] [3000/6250] eta: 0:07:21 lr: 0.000121 grad: 0.0617 (0.0637) loss: 0.8358 (0.8406) time: 0.1219 data: 0.0443 max mem: 9390 +Train: [16] [3100/6250] eta: 0:07:08 lr: 0.000121 grad: 0.0595 (0.0637) loss: 0.8416 (0.8406) time: 0.1436 data: 0.0667 max mem: 9390 +Train: [16] [3200/6250] eta: 0:06:53 lr: 0.000121 grad: 0.0586 (0.0637) loss: 0.8427 (0.8406) time: 0.1171 data: 0.0328 max mem: 9390 +Train: [16] [3300/6250] eta: 0:06:39 lr: 0.000121 grad: 0.0634 (0.0637) loss: 0.8393 (0.8407) time: 0.1308 data: 0.0537 max mem: 9390 +Train: [16] [3400/6250] eta: 0:06:25 lr: 0.000121 grad: 0.0652 (0.0637) loss: 0.8396 (0.8407) time: 0.1199 data: 0.0483 max mem: 9390 +Train: [16] [3500/6250] eta: 0:06:11 lr: 0.000120 grad: 0.0620 (0.0636) loss: 0.8368 (0.8407) time: 0.1380 data: 0.0605 max mem: 9390 +Train: [16] [3600/6250] eta: 0:05:58 lr: 0.000120 grad: 0.0605 (0.0637) loss: 0.8428 (0.8407) time: 0.1021 data: 0.0183 max mem: 9390 +Train: [16] [3700/6250] eta: 0:05:44 lr: 0.000120 grad: 0.0629 (0.0637) loss: 0.8403 (0.8408) time: 0.1357 data: 0.0585 max mem: 9390 +Train: [16] [3800/6250] eta: 0:05:30 lr: 0.000120 grad: 0.0624 (0.0637) loss: 0.8404 (0.8407) time: 0.1424 data: 0.0670 max mem: 9390 +Train: [16] [3900/6250] eta: 0:05:17 lr: 0.000120 grad: 0.0667 (0.0638) loss: 0.8407 (0.8407) time: 0.1266 data: 0.0506 max mem: 9390 +Train: [16] [4000/6250] eta: 0:05:04 lr: 0.000120 grad: 0.0588 (0.0638) loss: 0.8446 (0.8408) time: 0.1494 data: 0.0735 max mem: 9390 +Train: [16] [4100/6250] eta: 0:04:50 lr: 0.000120 grad: 0.0603 (0.0638) loss: 0.8412 (0.8408) time: 0.1404 data: 0.0656 max mem: 9390 +Train: [16] [4200/6250] eta: 0:04:36 lr: 0.000120 grad: 0.0637 (0.0638) loss: 0.8409 (0.8408) time: 0.1446 data: 0.0670 max mem: 9390 +Train: [16] [4300/6250] eta: 0:04:23 lr: 0.000120 grad: 0.0577 (0.0639) loss: 0.8398 (0.8408) time: 0.1284 data: 0.0485 max mem: 9390 +Train: [16] [4400/6250] eta: 0:04:09 lr: 0.000120 grad: 0.0625 (0.0639) loss: 0.8446 (0.8409) time: 0.1277 data: 0.0407 max mem: 9390 +Train: [16] [4500/6250] eta: 0:03:56 lr: 0.000120 grad: 0.0635 (0.0639) loss: 0.8387 (0.8409) time: 0.1296 data: 0.0456 max mem: 9390 +Train: [16] [4600/6250] eta: 0:03:42 lr: 0.000120 grad: 0.0592 (0.0639) loss: 0.8434 (0.8409) time: 0.1305 data: 0.0508 max mem: 9390 +Train: [16] [4700/6250] eta: 0:03:28 lr: 0.000120 grad: 0.0606 (0.0640) loss: 0.8420 (0.8409) time: 0.1314 data: 0.0491 max mem: 9390 +Train: [16] [4800/6250] eta: 0:03:15 lr: 0.000120 grad: 0.0593 (0.0639) loss: 0.8433 (0.8409) time: 0.1494 data: 0.0725 max mem: 9390 +Train: [16] [4900/6250] eta: 0:03:02 lr: 0.000120 grad: 0.0585 (0.0639) loss: 0.8496 (0.8410) time: 0.1310 data: 0.0504 max mem: 9390 +Train: [16] [5000/6250] eta: 0:02:48 lr: 0.000120 grad: 0.0625 (0.0639) loss: 0.8448 (0.8410) time: 0.1302 data: 0.0535 max mem: 9390 +Train: [16] [5100/6250] eta: 0:02:35 lr: 0.000120 grad: 0.0575 (0.0639) loss: 0.8462 (0.8410) time: 0.1536 data: 0.0739 max mem: 9390 +Train: [16] [5200/6250] eta: 0:02:21 lr: 0.000120 grad: 0.0611 (0.0638) loss: 0.8421 (0.8410) time: 0.1233 data: 0.0411 max mem: 9390 +Train: [16] [5300/6250] eta: 0:02:07 lr: 0.000120 grad: 0.0581 (0.0638) loss: 0.8359 (0.8410) time: 0.1352 data: 0.0585 max mem: 9390 +Train: [16] [5400/6250] eta: 0:01:54 lr: 0.000120 grad: 0.0599 (0.0638) loss: 0.8368 (0.8410) time: 0.1525 data: 0.0791 max mem: 9390 +Train: [16] [5500/6250] eta: 0:01:40 lr: 0.000120 grad: 0.0617 (0.0638) loss: 0.8340 (0.8409) time: 0.1262 data: 0.0511 max mem: 9390 +Train: [16] [5600/6250] eta: 0:01:27 lr: 0.000120 grad: 0.0576 (0.0638) loss: 0.8410 (0.8409) time: 0.1232 data: 0.0443 max mem: 9390 +Train: [16] [5700/6250] eta: 0:01:13 lr: 0.000120 grad: 0.0605 (0.0637) loss: 0.8347 (0.8409) time: 0.1402 data: 0.0646 max mem: 9390 +Train: [16] [5800/6250] eta: 0:01:00 lr: 0.000120 grad: 0.0592 (0.0637) loss: 0.8340 (0.8409) time: 0.1401 data: 0.0637 max mem: 9390 +Train: [16] [5900/6250] eta: 0:00:46 lr: 0.000120 grad: 0.0579 (0.0637) loss: 0.8404 (0.8408) time: 0.1371 data: 0.0612 max mem: 9390 +Train: [16] [6000/6250] eta: 0:00:33 lr: 0.000120 grad: 0.0615 (0.0637) loss: 0.8393 (0.8408) time: 0.1424 data: 0.0652 max mem: 9390 +Train: [16] [6100/6250] eta: 0:00:20 lr: 0.000120 grad: 0.0644 (0.0637) loss: 0.8377 (0.8407) time: 0.1460 data: 0.0704 max mem: 9390 +Train: [16] [6200/6250] eta: 0:00:06 lr: 0.000120 grad: 0.0640 (0.0638) loss: 0.8355 (0.8406) time: 0.1373 data: 0.0636 max mem: 9390 +Train: [16] [6249/6250] eta: 0:00:00 lr: 0.000120 grad: 0.0610 (0.0638) loss: 0.8386 (0.8406) time: 0.1533 data: 0.0776 max mem: 9390 +Train: [16] Total time: 0:14:05 (0.1352 s / it) +Averaged stats: lr: 0.000120 grad: 0.0610 (0.0638) loss: 0.8386 (0.8406) +Eval (hcp-train-subset): [16] [ 0/62] eta: 0:04:10 loss: 0.8548 (0.8548) time: 4.0470 data: 4.0168 max mem: 9390 +Eval (hcp-train-subset): [16] [61/62] eta: 0:00:00 loss: 0.8460 (0.8480) time: 0.1241 data: 0.0972 max mem: 9390 +Eval (hcp-train-subset): [16] Total time: 0:00:13 (0.2141 s / it) +Averaged stats (hcp-train-subset): loss: 0.8460 (0.8480) +Eval (hcp-val): [16] [ 0/62] eta: 0:03:55 loss: 0.8433 (0.8433) time: 3.7987 data: 3.7696 max mem: 9390 +Eval (hcp-val): [16] [61/62] eta: 0:00:00 loss: 0.8416 (0.8428) time: 0.1087 data: 0.0842 max mem: 9390 +Eval (hcp-val): [16] Total time: 0:00:11 (0.1890 s / it) +Averaged stats (hcp-val): loss: 0.8416 (0.8428) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +Train: [17] [ 0/6250] eta: 7:55:46 lr: 0.000120 grad: 0.0958 (0.0958) loss: 0.8711 (0.8711) time: 4.5675 data: 4.4291 max mem: 9390 +Train: [17] [ 100/6250] eta: 0:18:01 lr: 0.000120 grad: 0.0629 (0.0709) loss: 0.8492 (0.8489) time: 0.1337 data: 0.0510 max mem: 9390 +Train: [17] [ 200/6250] eta: 0:15:39 lr: 0.000120 grad: 0.0614 (0.0663) loss: 0.8389 (0.8461) time: 0.1348 data: 0.0510 max mem: 9390 +Train: [17] [ 300/6250] eta: 0:14:32 lr: 0.000120 grad: 0.0630 (0.0655) loss: 0.8382 (0.8448) time: 0.1233 data: 0.0409 max mem: 9390 +Train: [17] [ 400/6250] eta: 0:13:55 lr: 0.000120 grad: 0.0575 (0.0645) loss: 0.8454 (0.8450) time: 0.1335 data: 0.0482 max mem: 9390 +Train: [17] [ 500/6250] eta: 0:13:18 lr: 0.000120 grad: 0.0624 (0.0642) loss: 0.8495 (0.8444) time: 0.1251 data: 0.0452 max mem: 9390 +Train: [17] [ 600/6250] eta: 0:12:47 lr: 0.000120 grad: 0.0570 (0.0642) loss: 0.8497 (0.8439) time: 0.1310 data: 0.0471 max mem: 9390 +Train: [17] [ 700/6250] eta: 0:12:19 lr: 0.000120 grad: 0.0604 (0.0639) loss: 0.8465 (0.8437) time: 0.1158 data: 0.0284 max mem: 9390 +Train: [17] [ 800/6250] eta: 0:11:58 lr: 0.000120 grad: 0.0616 (0.0637) loss: 0.8404 (0.8435) time: 0.1357 data: 0.0533 max mem: 9390 +Train: [17] [ 900/6250] eta: 0:11:46 lr: 0.000120 grad: 0.0585 (0.0635) loss: 0.8450 (0.8429) time: 0.1378 data: 0.0497 max mem: 9390 +Train: [17] [1000/6250] eta: 0:11:36 lr: 0.000120 grad: 0.0610 (0.0632) loss: 0.8399 (0.8427) time: 0.1566 data: 0.0801 max mem: 9390 +Train: [17] [1100/6250] eta: 0:11:25 lr: 0.000120 grad: 0.0609 (0.0630) loss: 0.8334 (0.8424) time: 0.1501 data: 0.0637 max mem: 9390 +Train: [17] [1200/6250] eta: 0:11:14 lr: 0.000120 grad: 0.0611 (0.0629) loss: 0.8380 (0.8422) time: 0.1277 data: 0.0506 max mem: 9390 +Train: [17] [1300/6250] eta: 0:11:03 lr: 0.000120 grad: 0.0618 (0.0629) loss: 0.8373 (0.8419) time: 0.1363 data: 0.0592 max mem: 9390 +Train: [17] [1400/6250] eta: 0:10:52 lr: 0.000120 grad: 0.0631 (0.0629) loss: 0.8382 (0.8417) time: 0.1386 data: 0.0638 max mem: 9390 +Train: [17] [1500/6250] eta: 0:10:38 lr: 0.000120 grad: 0.0600 (0.0628) loss: 0.8407 (0.8414) time: 0.1389 data: 0.0603 max mem: 9390 +Train: [17] [1600/6250] eta: 0:10:24 lr: 0.000120 grad: 0.0635 (0.0629) loss: 0.8386 (0.8412) time: 0.1343 data: 0.0565 max mem: 9390 +Train: [17] [1700/6250] eta: 0:10:12 lr: 0.000120 grad: 0.0625 (0.0628) loss: 0.8453 (0.8413) time: 0.1266 data: 0.0463 max mem: 9390 +Train: [17] [1800/6250] eta: 0:09:58 lr: 0.000120 grad: 0.0633 (0.0628) loss: 0.8417 (0.8413) time: 0.1376 data: 0.0600 max mem: 9390 +Train: [17] [1900/6250] eta: 0:09:46 lr: 0.000120 grad: 0.0613 (0.0628) loss: 0.8377 (0.8413) time: 0.1474 data: 0.0662 max mem: 9390 +Train: [17] [2000/6250] eta: 0:09:33 lr: 0.000120 grad: 0.0626 (0.0628) loss: 0.8423 (0.8413) time: 0.1601 data: 0.0843 max mem: 9390 +Train: [17] [2100/6250] eta: 0:09:18 lr: 0.000120 grad: 0.0625 (0.0629) loss: 0.8397 (0.8413) time: 0.1379 data: 0.0585 max mem: 9390 +Train: [17] [2200/6250] eta: 0:09:05 lr: 0.000120 grad: 0.0624 (0.0628) loss: 0.8447 (0.8414) time: 0.1010 data: 0.0194 max mem: 9390 +Train: [17] [2300/6250] eta: 0:08:51 lr: 0.000120 grad: 0.0579 (0.0628) loss: 0.8391 (0.8414) time: 0.1392 data: 0.0616 max mem: 9390 +Train: [17] [2400/6250] eta: 0:08:37 lr: 0.000120 grad: 0.0607 (0.0627) loss: 0.8455 (0.8415) time: 0.1224 data: 0.0441 max mem: 9390 +Train: [17] [2500/6250] eta: 0:08:25 lr: 0.000120 grad: 0.0591 (0.0627) loss: 0.8467 (0.8415) time: 0.1507 data: 0.0721 max mem: 9390 +Train: [17] [2600/6250] eta: 0:08:13 lr: 0.000120 grad: 0.0610 (0.0627) loss: 0.8398 (0.8415) time: 0.1943 data: 0.1210 max mem: 9390 +Train: [17] [2700/6250] eta: 0:07:59 lr: 0.000120 grad: 0.0594 (0.0626) loss: 0.8421 (0.8415) time: 0.1375 data: 0.0626 max mem: 9390 +Train: [17] [2800/6250] eta: 0:07:45 lr: 0.000120 grad: 0.0584 (0.0626) loss: 0.8418 (0.8415) time: 0.1230 data: 0.0356 max mem: 9390 +Train: [17] [2900/6250] eta: 0:07:31 lr: 0.000120 grad: 0.0607 (0.0626) loss: 0.8462 (0.8414) time: 0.1325 data: 0.0537 max mem: 9390 +Train: [17] [3000/6250] eta: 0:07:19 lr: 0.000120 grad: 0.0598 (0.0626) loss: 0.8421 (0.8415) time: 0.1502 data: 0.0789 max mem: 9390 +Train: [17] [3100/6250] eta: 0:07:04 lr: 0.000120 grad: 0.0649 (0.0627) loss: 0.8398 (0.8415) time: 0.1271 data: 0.0518 max mem: 9390 +Train: [17] [3200/6250] eta: 0:06:51 lr: 0.000120 grad: 0.0640 (0.0627) loss: 0.8379 (0.8415) time: 0.1352 data: 0.0548 max mem: 9390 +Train: [17] [3300/6250] eta: 0:06:37 lr: 0.000120 grad: 0.0596 (0.0628) loss: 0.8428 (0.8415) time: 0.1357 data: 0.0587 max mem: 9390 +Train: [17] [3400/6250] eta: 0:06:24 lr: 0.000120 grad: 0.0600 (0.0628) loss: 0.8439 (0.8415) time: 0.1430 data: 0.0678 max mem: 9390 +Train: [17] [3500/6250] eta: 0:06:10 lr: 0.000120 grad: 0.0608 (0.0629) loss: 0.8420 (0.8414) time: 0.1300 data: 0.0479 max mem: 9390 +Train: [17] [3600/6250] eta: 0:05:57 lr: 0.000120 grad: 0.0636 (0.0629) loss: 0.8406 (0.8413) time: 0.1525 data: 0.0767 max mem: 9390 +Train: [17] [3700/6250] eta: 0:05:44 lr: 0.000120 grad: 0.0608 (0.0629) loss: 0.8391 (0.8413) time: 0.1262 data: 0.0476 max mem: 9390 +Train: [17] [3800/6250] eta: 0:05:30 lr: 0.000120 grad: 0.0641 (0.0630) loss: 0.8331 (0.8412) time: 0.1382 data: 0.0572 max mem: 9390 +Train: [17] [3900/6250] eta: 0:05:17 lr: 0.000120 grad: 0.0652 (0.0630) loss: 0.8381 (0.8412) time: 0.1532 data: 0.0760 max mem: 9390 +Train: [17] [4000/6250] eta: 0:05:03 lr: 0.000120 grad: 0.0644 (0.0631) loss: 0.8399 (0.8411) time: 0.1277 data: 0.0475 max mem: 9390 +Train: [17] [4100/6250] eta: 0:04:49 lr: 0.000120 grad: 0.0638 (0.0632) loss: 0.8376 (0.8410) time: 0.1328 data: 0.0543 max mem: 9390 +Train: [17] [4200/6250] eta: 0:04:36 lr: 0.000120 grad: 0.0624 (0.0633) loss: 0.8403 (0.8410) time: 0.1336 data: 0.0547 max mem: 9390 +Train: [17] [4300/6250] eta: 0:04:22 lr: 0.000120 grad: 0.0610 (0.0634) loss: 0.8369 (0.8409) time: 0.1536 data: 0.0688 max mem: 9390 +Train: [17] [4400/6250] eta: 0:04:09 lr: 0.000120 grad: 0.0616 (0.0634) loss: 0.8379 (0.8408) time: 0.1453 data: 0.0647 max mem: 9390 +Train: [17] [4500/6250] eta: 0:03:55 lr: 0.000120 grad: 0.0617 (0.0634) loss: 0.8393 (0.8408) time: 0.1500 data: 0.0734 max mem: 9390 +Train: [17] [4600/6250] eta: 0:03:42 lr: 0.000120 grad: 0.0596 (0.0634) loss: 0.8401 (0.8408) time: 0.1375 data: 0.0633 max mem: 9390 +Train: [17] [4700/6250] eta: 0:03:28 lr: 0.000120 grad: 0.0623 (0.0635) loss: 0.8384 (0.8408) time: 0.1265 data: 0.0400 max mem: 9390 +Train: [17] [4800/6250] eta: 0:03:15 lr: 0.000120 grad: 0.0610 (0.0635) loss: 0.8407 (0.8408) time: 0.1340 data: 0.0567 max mem: 9390 +Train: [17] [4900/6250] eta: 0:03:01 lr: 0.000119 grad: 0.0626 (0.0634) loss: 0.8387 (0.8407) time: 0.1370 data: 0.0582 max mem: 9390 +Train: [17] [5000/6250] eta: 0:02:48 lr: 0.000119 grad: 0.0587 (0.0634) loss: 0.8424 (0.8408) time: 0.1061 data: 0.0217 max mem: 9390 +Train: [17] [5100/6250] eta: 0:02:34 lr: 0.000119 grad: 0.0610 (0.0635) loss: 0.8379 (0.8407) time: 0.1391 data: 0.0658 max mem: 9390 +Train: [17] [5200/6250] eta: 0:02:21 lr: 0.000119 grad: 0.0644 (0.0635) loss: 0.8363 (0.8407) time: 0.1476 data: 0.0679 max mem: 9390 +Train: [17] [5300/6250] eta: 0:02:07 lr: 0.000119 grad: 0.0637 (0.0635) loss: 0.8384 (0.8407) time: 0.1379 data: 0.0597 max mem: 9390 +Train: [17] [5400/6250] eta: 0:01:54 lr: 0.000119 grad: 0.0608 (0.0635) loss: 0.8379 (0.8406) time: 0.1496 data: 0.0629 max mem: 9390 +Train: [17] [5500/6250] eta: 0:01:40 lr: 0.000119 grad: 0.0616 (0.0635) loss: 0.8411 (0.8406) time: 0.1268 data: 0.0487 max mem: 9390 +Train: [17] [5600/6250] eta: 0:01:27 lr: 0.000119 grad: 0.0621 (0.0635) loss: 0.8371 (0.8406) time: 0.1475 data: 0.0695 max mem: 9390 +Train: [17] [5700/6250] eta: 0:01:13 lr: 0.000119 grad: 0.0615 (0.0635) loss: 0.8414 (0.8407) time: 0.1594 data: 0.0803 max mem: 9390 +Train: [17] [5800/6250] eta: 0:01:00 lr: 0.000119 grad: 0.0614 (0.0635) loss: 0.8363 (0.8406) time: 0.1411 data: 0.0610 max mem: 9390 +Train: [17] [5900/6250] eta: 0:00:47 lr: 0.000119 grad: 0.0618 (0.0635) loss: 0.8370 (0.8405) time: 0.1234 data: 0.0427 max mem: 9390 +Train: [17] [6000/6250] eta: 0:00:33 lr: 0.000119 grad: 0.0607 (0.0635) loss: 0.8373 (0.8405) time: 0.1222 data: 0.0482 max mem: 9390 +Train: [17] [6100/6250] eta: 0:00:20 lr: 0.000119 grad: 0.0625 (0.0635) loss: 0.8390 (0.8405) time: 0.1410 data: 0.0570 max mem: 9390 +Train: [17] [6200/6250] eta: 0:00:06 lr: 0.000119 grad: 0.0690 (0.0636) loss: 0.8356 (0.8404) time: 0.1127 data: 0.0284 max mem: 9390 +Train: [17] [6249/6250] eta: 0:00:00 lr: 0.000119 grad: 0.0660 (0.0637) loss: 0.8379 (0.8404) time: 0.1407 data: 0.0659 max mem: 9390 +Train: [17] Total time: 0:14:06 (0.1354 s / it) +Averaged stats: lr: 0.000119 grad: 0.0660 (0.0637) loss: 0.8379 (0.8404) +Eval (hcp-train-subset): [17] [ 0/62] eta: 0:02:37 loss: 0.8584 (0.8584) time: 2.5447 data: 2.4837 max mem: 9390 +Eval (hcp-train-subset): [17] [61/62] eta: 0:00:00 loss: 0.8471 (0.8476) time: 0.1235 data: 0.0987 max mem: 9390 +Eval (hcp-train-subset): [17] Total time: 0:00:11 (0.1889 s / it) +Averaged stats (hcp-train-subset): loss: 0.8471 (0.8476) +Eval (hcp-val): [17] [ 0/62] eta: 0:03:06 loss: 0.8361 (0.8361) time: 3.0138 data: 2.9529 max mem: 9390 +Eval (hcp-val): [17] [61/62] eta: 0:00:00 loss: 0.8413 (0.8422) time: 0.1107 data: 0.0863 max mem: 9390 +Eval (hcp-val): [17] Total time: 0:00:11 (0.1813 s / it) +Averaged stats (hcp-val): loss: 0.8413 (0.8422) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +Train: [18] [ 0/6250] eta: 8:28:33 lr: 0.000119 grad: 0.0715 (0.0715) loss: 0.8655 (0.8655) time: 4.8822 data: 4.7835 max mem: 9390 +Train: [18] [ 100/6250] eta: 0:18:31 lr: 0.000119 grad: 0.0640 (0.0673) loss: 0.8448 (0.8475) time: 0.1504 data: 0.0698 max mem: 9390 +Train: [18] [ 200/6250] eta: 0:15:55 lr: 0.000119 grad: 0.0649 (0.0666) loss: 0.8445 (0.8453) time: 0.1326 data: 0.0512 max mem: 9390 +Train: [18] [ 300/6250] eta: 0:14:50 lr: 0.000119 grad: 0.0597 (0.0651) loss: 0.8399 (0.8445) time: 0.1354 data: 0.0481 max mem: 9390 +Train: [18] [ 400/6250] eta: 0:13:58 lr: 0.000119 grad: 0.0569 (0.0641) loss: 0.8498 (0.8442) time: 0.1315 data: 0.0522 max mem: 9390 +Train: [18] [ 500/6250] eta: 0:13:22 lr: 0.000119 grad: 0.0598 (0.0635) loss: 0.8472 (0.8442) time: 0.1271 data: 0.0414 max mem: 9390 +Train: [18] [ 600/6250] eta: 0:12:55 lr: 0.000119 grad: 0.0585 (0.0629) loss: 0.8402 (0.8440) time: 0.1304 data: 0.0437 max mem: 9390 +Train: [18] [ 700/6250] eta: 0:12:30 lr: 0.000119 grad: 0.0604 (0.0624) loss: 0.8410 (0.8439) time: 0.1193 data: 0.0387 max mem: 9390 +Train: [18] [ 800/6250] eta: 0:12:12 lr: 0.000119 grad: 0.0602 (0.0620) loss: 0.8436 (0.8434) time: 0.1278 data: 0.0480 max mem: 9390 +Train: [18] [ 900/6250] eta: 0:12:04 lr: 0.000119 grad: 0.0606 (0.0619) loss: 0.8374 (0.8430) time: 0.1257 data: 0.0380 max mem: 9390 +Train: [18] [1000/6250] eta: 0:11:50 lr: 0.000119 grad: 0.0565 (0.0618) loss: 0.8395 (0.8426) time: 0.1296 data: 0.0475 max mem: 9390 +Train: [18] [1100/6250] eta: 0:11:37 lr: 0.000119 grad: 0.0615 (0.0617) loss: 0.8386 (0.8423) time: 0.1456 data: 0.0635 max mem: 9390 +Train: [18] [1200/6250] eta: 0:11:24 lr: 0.000119 grad: 0.0611 (0.0618) loss: 0.8358 (0.8418) time: 0.1420 data: 0.0632 max mem: 9390 +Train: [18] [1300/6250] eta: 0:11:15 lr: 0.000119 grad: 0.0579 (0.0617) loss: 0.8391 (0.8415) time: 0.1558 data: 0.0717 max mem: 9390 +Train: [18] [1400/6250] eta: 0:11:04 lr: 0.000119 grad: 0.0610 (0.0619) loss: 0.8346 (0.8410) time: 0.1328 data: 0.0625 max mem: 9390 +Train: [18] [1500/6250] eta: 0:10:50 lr: 0.000119 grad: 0.0637 (0.0619) loss: 0.8390 (0.8408) time: 0.1471 data: 0.0595 max mem: 9390 +Train: [18] [1600/6250] eta: 0:10:38 lr: 0.000119 grad: 0.0607 (0.0619) loss: 0.8338 (0.8405) time: 0.1305 data: 0.0529 max mem: 9390 +Train: [18] [1700/6250] eta: 0:10:26 lr: 0.000119 grad: 0.0600 (0.0620) loss: 0.8391 (0.8403) time: 0.1776 data: 0.1020 max mem: 9390 +Train: [18] [1800/6250] eta: 0:10:11 lr: 0.000119 grad: 0.0609 (0.0621) loss: 0.8407 (0.8401) time: 0.1560 data: 0.0762 max mem: 9390 +Train: [18] [1900/6250] eta: 0:09:58 lr: 0.000119 grad: 0.0635 (0.0622) loss: 0.8359 (0.8399) time: 0.1327 data: 0.0530 max mem: 9390 +Train: [18] [2000/6250] eta: 0:09:45 lr: 0.000119 grad: 0.0615 (0.0623) loss: 0.8396 (0.8398) time: 0.1516 data: 0.0794 max mem: 9390 +Train: [18] [2100/6250] eta: 0:09:31 lr: 0.000119 grad: 0.0635 (0.0623) loss: 0.8388 (0.8397) time: 0.1686 data: 0.0937 max mem: 9390 +Train: [18] [2200/6250] eta: 0:09:15 lr: 0.000119 grad: 0.0600 (0.0623) loss: 0.8406 (0.8398) time: 0.1291 data: 0.0506 max mem: 9390 +Train: [18] [2300/6250] eta: 0:09:01 lr: 0.000119 grad: 0.0631 (0.0624) loss: 0.8420 (0.8398) time: 0.1525 data: 0.0743 max mem: 9390 +Train: [18] [2400/6250] eta: 0:08:47 lr: 0.000119 grad: 0.0600 (0.0625) loss: 0.8386 (0.8398) time: 0.1345 data: 0.0577 max mem: 9390 +Train: [18] [2500/6250] eta: 0:08:33 lr: 0.000119 grad: 0.0652 (0.0626) loss: 0.8407 (0.8397) time: 0.1327 data: 0.0546 max mem: 9390 +Train: [18] [2600/6250] eta: 0:08:19 lr: 0.000119 grad: 0.0572 (0.0625) loss: 0.8410 (0.8398) time: 0.1282 data: 0.0509 max mem: 9390 +Train: [18] [2700/6250] eta: 0:08:05 lr: 0.000119 grad: 0.0624 (0.0625) loss: 0.8455 (0.8398) time: 0.1395 data: 0.0601 max mem: 9390 +Train: [18] [2800/6250] eta: 0:07:51 lr: 0.000119 grad: 0.0604 (0.0625) loss: 0.8398 (0.8398) time: 0.1241 data: 0.0441 max mem: 9390 +Train: [18] [2900/6250] eta: 0:07:39 lr: 0.000119 grad: 0.0603 (0.0625) loss: 0.8394 (0.8397) time: 0.1602 data: 0.0840 max mem: 9390 +Train: [18] [3000/6250] eta: 0:07:25 lr: 0.000119 grad: 0.0654 (0.0626) loss: 0.8378 (0.8397) time: 0.1362 data: 0.0553 max mem: 9390 +Train: [18] [3100/6250] eta: 0:07:10 lr: 0.000119 grad: 0.0600 (0.0626) loss: 0.8392 (0.8397) time: 0.1316 data: 0.0543 max mem: 9390 +Train: [18] [3200/6250] eta: 0:06:57 lr: 0.000119 grad: 0.0620 (0.0626) loss: 0.8428 (0.8397) time: 0.1435 data: 0.0663 max mem: 9390 +Train: [18] [3300/6250] eta: 0:06:43 lr: 0.000119 grad: 0.0611 (0.0627) loss: 0.8409 (0.8397) time: 0.1425 data: 0.0671 max mem: 9390 +Train: [18] [3400/6250] eta: 0:06:29 lr: 0.000119 grad: 0.0655 (0.0628) loss: 0.8374 (0.8397) time: 0.1178 data: 0.0430 max mem: 9390 +Train: [18] [3500/6250] eta: 0:06:15 lr: 0.000119 grad: 0.0593 (0.0629) loss: 0.8423 (0.8396) time: 0.1325 data: 0.0578 max mem: 9390 +Train: [18] [3600/6250] eta: 0:06:01 lr: 0.000119 grad: 0.0630 (0.0629) loss: 0.8379 (0.8397) time: 0.1368 data: 0.0620 max mem: 9390 +Train: [18] [3700/6250] eta: 0:05:47 lr: 0.000119 grad: 0.0668 (0.0629) loss: 0.8420 (0.8396) time: 0.1314 data: 0.0553 max mem: 9390 +Train: [18] [3800/6250] eta: 0:05:33 lr: 0.000119 grad: 0.0607 (0.0630) loss: 0.8399 (0.8396) time: 0.1264 data: 0.0465 max mem: 9390 +Train: [18] [3900/6250] eta: 0:05:19 lr: 0.000119 grad: 0.0617 (0.0630) loss: 0.8353 (0.8396) time: 0.1486 data: 0.0691 max mem: 9390 +Train: [18] [4000/6250] eta: 0:05:06 lr: 0.000119 grad: 0.0648 (0.0630) loss: 0.8434 (0.8396) time: 0.1324 data: 0.0558 max mem: 9390 +Train: [18] [4100/6250] eta: 0:04:52 lr: 0.000119 grad: 0.0619 (0.0631) loss: 0.8368 (0.8395) time: 0.1335 data: 0.0530 max mem: 9390 +Train: [18] [4200/6250] eta: 0:04:39 lr: 0.000119 grad: 0.0631 (0.0631) loss: 0.8378 (0.8395) time: 0.1269 data: 0.0471 max mem: 9390 +Train: [18] [4300/6250] eta: 0:04:25 lr: 0.000119 grad: 0.0656 (0.0632) loss: 0.8353 (0.8395) time: 0.1397 data: 0.0633 max mem: 9390 +Train: [18] [4400/6250] eta: 0:04:11 lr: 0.000119 grad: 0.0628 (0.0632) loss: 0.8413 (0.8395) time: 0.1356 data: 0.0574 max mem: 9390 +Train: [18] [4500/6250] eta: 0:03:58 lr: 0.000119 grad: 0.0620 (0.0632) loss: 0.8403 (0.8395) time: 0.1726 data: 0.0965 max mem: 9390 +Train: [18] [4600/6250] eta: 0:03:44 lr: 0.000119 grad: 0.0623 (0.0632) loss: 0.8339 (0.8395) time: 0.1356 data: 0.0582 max mem: 9390 +Train: [18] [4700/6250] eta: 0:03:30 lr: 0.000119 grad: 0.0608 (0.0633) loss: 0.8426 (0.8395) time: 0.1195 data: 0.0442 max mem: 9390 +Train: [18] [4800/6250] eta: 0:03:17 lr: 0.000119 grad: 0.0588 (0.0633) loss: 0.8429 (0.8395) time: 0.1313 data: 0.0550 max mem: 9390 +Train: [18] [4900/6250] eta: 0:03:03 lr: 0.000119 grad: 0.0583 (0.0633) loss: 0.8416 (0.8395) time: 0.1291 data: 0.0502 max mem: 9390 +Train: [18] [5000/6250] eta: 0:02:49 lr: 0.000119 grad: 0.0614 (0.0633) loss: 0.8415 (0.8396) time: 0.1323 data: 0.0500 max mem: 9390 +Train: [18] [5100/6250] eta: 0:02:36 lr: 0.000119 grad: 0.0640 (0.0634) loss: 0.8369 (0.8395) time: 0.1407 data: 0.0570 max mem: 9390 +Train: [18] [5200/6250] eta: 0:02:22 lr: 0.000119 grad: 0.0645 (0.0634) loss: 0.8393 (0.8395) time: 0.1194 data: 0.0433 max mem: 9390 +Train: [18] [5300/6250] eta: 0:02:08 lr: 0.000119 grad: 0.0611 (0.0635) loss: 0.8442 (0.8395) time: 0.1247 data: 0.0471 max mem: 9390 +Train: [18] [5400/6250] eta: 0:01:55 lr: 0.000119 grad: 0.0636 (0.0635) loss: 0.8442 (0.8395) time: 0.1366 data: 0.0623 max mem: 9390 +Train: [18] [5500/6250] eta: 0:01:41 lr: 0.000119 grad: 0.0669 (0.0635) loss: 0.8388 (0.8395) time: 0.1272 data: 0.0460 max mem: 9390 +Train: [18] [5600/6250] eta: 0:01:27 lr: 0.000119 grad: 0.0619 (0.0635) loss: 0.8373 (0.8395) time: 0.1300 data: 0.0542 max mem: 9390 +Train: [18] [5700/6250] eta: 0:01:14 lr: 0.000119 grad: 0.0613 (0.0636) loss: 0.8376 (0.8395) time: 0.1240 data: 0.0401 max mem: 9390 +Train: [18] [5800/6250] eta: 0:01:00 lr: 0.000118 grad: 0.0646 (0.0636) loss: 0.8406 (0.8395) time: 0.1382 data: 0.0638 max mem: 9390 +Train: [18] [5900/6250] eta: 0:00:47 lr: 0.000118 grad: 0.0639 (0.0636) loss: 0.8395 (0.8395) time: 0.1479 data: 0.0730 max mem: 9390 +Train: [18] [6000/6250] eta: 0:00:33 lr: 0.000118 grad: 0.0613 (0.0636) loss: 0.8418 (0.8395) time: 0.1086 data: 0.0317 max mem: 9390 +Train: [18] [6100/6250] eta: 0:00:20 lr: 0.000118 grad: 0.0614 (0.0637) loss: 0.8370 (0.8395) time: 0.1286 data: 0.0510 max mem: 9390 +Train: [18] [6200/6250] eta: 0:00:06 lr: 0.000118 grad: 0.0617 (0.0637) loss: 0.8419 (0.8395) time: 0.1507 data: 0.0766 max mem: 9390 +Train: [18] [6249/6250] eta: 0:00:00 lr: 0.000118 grad: 0.0620 (0.0637) loss: 0.8357 (0.8395) time: 0.1872 data: 0.1074 max mem: 9390 +Train: [18] Total time: 0:14:12 (0.1364 s / it) +Averaged stats: lr: 0.000118 grad: 0.0620 (0.0637) loss: 0.8357 (0.8395) +Eval (hcp-train-subset): [18] [ 0/62] eta: 0:04:06 loss: 0.8581 (0.8581) time: 3.9756 data: 3.9329 max mem: 9390 +Eval (hcp-train-subset): [18] [61/62] eta: 0:00:00 loss: 0.8454 (0.8466) time: 0.1399 data: 0.1144 max mem: 9390 +Eval (hcp-train-subset): [18] Total time: 0:00:13 (0.2105 s / it) +Averaged stats (hcp-train-subset): loss: 0.8454 (0.8466) +Eval (hcp-val): [18] [ 0/62] eta: 0:04:29 loss: 0.8361 (0.8361) time: 4.3524 data: 4.3238 max mem: 9390 +Eval (hcp-val): [18] [61/62] eta: 0:00:00 loss: 0.8407 (0.8411) time: 0.1187 data: 0.0919 max mem: 9390 +Eval (hcp-val): [18] Total time: 0:00:12 (0.1959 s / it) +Averaged stats (hcp-val): loss: 0.8407 (0.8411) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +Train: [19] [ 0/6250] eta: 5:52:01 lr: 0.000118 grad: 0.0609 (0.0609) loss: 0.8386 (0.8386) time: 3.3795 data: 3.1640 max mem: 9390 +Train: [19] [ 100/6250] eta: 0:18:02 lr: 0.000118 grad: 0.0657 (0.0689) loss: 0.8405 (0.8517) time: 0.1413 data: 0.0651 max mem: 9390 +Train: [19] [ 200/6250] eta: 0:15:30 lr: 0.000118 grad: 0.0601 (0.0664) loss: 0.8418 (0.8483) time: 0.1422 data: 0.0613 max mem: 9390 +Train: [19] [ 300/6250] eta: 0:14:11 lr: 0.000118 grad: 0.0605 (0.0650) loss: 0.8398 (0.8462) time: 0.1067 data: 0.0210 max mem: 9390 +Train: [19] [ 400/6250] eta: 0:13:42 lr: 0.000118 grad: 0.0615 (0.0642) loss: 0.8387 (0.8446) time: 0.1404 data: 0.0559 max mem: 9390 +Train: [19] [ 500/6250] eta: 0:13:01 lr: 0.000118 grad: 0.0588 (0.0641) loss: 0.8412 (0.8436) time: 0.1286 data: 0.0535 max mem: 9390 +Train: [19] [ 600/6250] eta: 0:12:30 lr: 0.000118 grad: 0.0625 (0.0643) loss: 0.8410 (0.8423) time: 0.1046 data: 0.0176 max mem: 9390 +Train: [19] [ 700/6250] eta: 0:12:13 lr: 0.000118 grad: 0.0629 (0.0641) loss: 0.8346 (0.8415) time: 0.1289 data: 0.0434 max mem: 9390 +Train: [19] [ 800/6250] eta: 0:11:59 lr: 0.000118 grad: 0.0594 (0.0638) loss: 0.8378 (0.8410) time: 0.1621 data: 0.0809 max mem: 9390 +Train: [19] [ 900/6250] eta: 0:11:55 lr: 0.000118 grad: 0.0608 (0.0635) loss: 0.8387 (0.8406) time: 0.1559 data: 0.0712 max mem: 9390 +Train: [19] [1000/6250] eta: 0:11:50 lr: 0.000118 grad: 0.0622 (0.0637) loss: 0.8343 (0.8402) time: 0.1585 data: 0.0760 max mem: 9390 +Train: [19] [1100/6250] eta: 0:11:35 lr: 0.000118 grad: 0.0612 (0.0637) loss: 0.8401 (0.8400) time: 0.1217 data: 0.0383 max mem: 9390 +Train: [19] [1200/6250] eta: 0:11:25 lr: 0.000118 grad: 0.0621 (0.0636) loss: 0.8381 (0.8397) time: 0.1668 data: 0.0878 max mem: 9390 +Train: [19] [1300/6250] eta: 0:11:13 lr: 0.000118 grad: 0.0621 (0.0636) loss: 0.8284 (0.8393) time: 0.1340 data: 0.0458 max mem: 9390 +Train: [19] [1400/6250] eta: 0:11:02 lr: 0.000118 grad: 0.0630 (0.0637) loss: 0.8344 (0.8389) time: 0.1432 data: 0.0708 max mem: 9390 +Train: [19] [1500/6250] eta: 0:10:47 lr: 0.000118 grad: 0.0635 (0.0637) loss: 0.8360 (0.8386) time: 0.1317 data: 0.0550 max mem: 9390 +Train: [19] [1600/6250] eta: 0:10:34 lr: 0.000118 grad: 0.0654 (0.0638) loss: 0.8354 (0.8383) time: 0.1400 data: 0.0608 max mem: 9390 +Train: [19] [1700/6250] eta: 0:10:22 lr: 0.000118 grad: 0.0626 (0.0639) loss: 0.8371 (0.8382) time: 0.1307 data: 0.0506 max mem: 9390 +Train: [19] [1800/6250] eta: 0:10:09 lr: 0.000118 grad: 0.0639 (0.0639) loss: 0.8398 (0.8381) time: 0.1472 data: 0.0673 max mem: 9390 +Train: [19] [1900/6250] eta: 0:09:54 lr: 0.000118 grad: 0.0625 (0.0640) loss: 0.8338 (0.8380) time: 0.1281 data: 0.0497 max mem: 9390 +Train: [19] [2000/6250] eta: 0:09:41 lr: 0.000118 grad: 0.0628 (0.0640) loss: 0.8355 (0.8379) time: 0.1385 data: 0.0595 max mem: 9390 +Train: [19] [2100/6250] eta: 0:09:27 lr: 0.000118 grad: 0.0610 (0.0640) loss: 0.8357 (0.8379) time: 0.1181 data: 0.0396 max mem: 9390 +Train: [19] [2200/6250] eta: 0:09:14 lr: 0.000118 grad: 0.0609 (0.0640) loss: 0.8400 (0.8378) time: 0.1251 data: 0.0450 max mem: 9390 +Train: [19] [2300/6250] eta: 0:09:00 lr: 0.000118 grad: 0.0619 (0.0640) loss: 0.8376 (0.8377) time: 0.1341 data: 0.0586 max mem: 9390 +Train: [19] [2400/6250] eta: 0:08:46 lr: 0.000118 grad: 0.0632 (0.0640) loss: 0.8399 (0.8377) time: 0.1015 data: 0.0228 max mem: 9390 +Train: [19] [2500/6250] eta: 0:08:32 lr: 0.000118 grad: 0.0620 (0.0642) loss: 0.8363 (0.8376) time: 0.1359 data: 0.0590 max mem: 9390 +Train: [19] [2600/6250] eta: 0:08:20 lr: 0.000118 grad: 0.0640 (0.0642) loss: 0.8343 (0.8375) time: 0.1477 data: 0.0714 max mem: 9390 +Train: [19] [2700/6250] eta: 0:08:06 lr: 0.000118 grad: 0.0622 (0.0642) loss: 0.8389 (0.8375) time: 0.1131 data: 0.0368 max mem: 9390 +Train: [19] [2800/6250] eta: 0:07:51 lr: 0.000118 grad: 0.0599 (0.0643) loss: 0.8421 (0.8375) time: 0.1304 data: 0.0532 max mem: 9390 +Train: [19] [2900/6250] eta: 0:07:37 lr: 0.000118 grad: 0.0614 (0.0643) loss: 0.8360 (0.8375) time: 0.1265 data: 0.0470 max mem: 9390 +Train: [19] [3000/6250] eta: 0:07:24 lr: 0.000118 grad: 0.0616 (0.0643) loss: 0.8399 (0.8376) time: 0.1540 data: 0.0734 max mem: 9390 +Train: [19] [3100/6250] eta: 0:07:11 lr: 0.000118 grad: 0.0613 (0.0643) loss: 0.8401 (0.8376) time: 0.1457 data: 0.0622 max mem: 9390 +Train: [19] [3200/6250] eta: 0:06:57 lr: 0.000118 grad: 0.0638 (0.0643) loss: 0.8405 (0.8376) time: 0.1343 data: 0.0574 max mem: 9390 +Train: [19] [3300/6250] eta: 0:06:43 lr: 0.000118 grad: 0.0619 (0.0642) loss: 0.8384 (0.8376) time: 0.1357 data: 0.0493 max mem: 9390 +Train: [19] [3400/6250] eta: 0:06:30 lr: 0.000118 grad: 0.0643 (0.0642) loss: 0.8367 (0.8376) time: 0.1420 data: 0.0670 max mem: 9390 +Train: [19] [3500/6250] eta: 0:06:16 lr: 0.000118 grad: 0.0634 (0.0642) loss: 0.8370 (0.8377) time: 0.1407 data: 0.0631 max mem: 9390 +Train: [19] [3600/6250] eta: 0:06:02 lr: 0.000118 grad: 0.0646 (0.0642) loss: 0.8402 (0.8377) time: 0.1452 data: 0.0700 max mem: 9390 +Train: [19] [3700/6250] eta: 0:05:48 lr: 0.000118 grad: 0.0600 (0.0642) loss: 0.8416 (0.8377) time: 0.1294 data: 0.0518 max mem: 9390 +Train: [19] [3800/6250] eta: 0:05:34 lr: 0.000118 grad: 0.0637 (0.0642) loss: 0.8403 (0.8378) time: 0.1504 data: 0.0724 max mem: 9390 +Train: [19] [3900/6250] eta: 0:05:20 lr: 0.000118 grad: 0.0605 (0.0642) loss: 0.8437 (0.8378) time: 0.1314 data: 0.0493 max mem: 9390 +Train: [19] [4000/6250] eta: 0:05:06 lr: 0.000118 grad: 0.0600 (0.0642) loss: 0.8346 (0.8379) time: 0.1233 data: 0.0399 max mem: 9390 +Train: [19] [4100/6250] eta: 0:04:52 lr: 0.000118 grad: 0.0638 (0.0641) loss: 0.8369 (0.8379) time: 0.1366 data: 0.0577 max mem: 9390 +Train: [19] [4200/6250] eta: 0:04:38 lr: 0.000118 grad: 0.0648 (0.0642) loss: 0.8364 (0.8380) time: 0.1269 data: 0.0494 max mem: 9390 +Train: [19] [4300/6250] eta: 0:04:25 lr: 0.000118 grad: 0.0612 (0.0641) loss: 0.8383 (0.8380) time: 0.1357 data: 0.0539 max mem: 9390 +Train: [19] [4400/6250] eta: 0:04:11 lr: 0.000118 grad: 0.0617 (0.0642) loss: 0.8387 (0.8381) time: 0.1125 data: 0.0352 max mem: 9390 +Train: [19] [4500/6250] eta: 0:03:57 lr: 0.000118 grad: 0.0625 (0.0641) loss: 0.8434 (0.8381) time: 0.1441 data: 0.0691 max mem: 9390 +Train: [19] [4600/6250] eta: 0:03:43 lr: 0.000118 grad: 0.0628 (0.0641) loss: 0.8371 (0.8381) time: 0.1369 data: 0.0608 max mem: 9390 +Train: [19] [4700/6250] eta: 0:03:30 lr: 0.000118 grad: 0.0651 (0.0642) loss: 0.8338 (0.8381) time: 0.1436 data: 0.0573 max mem: 9390 +Train: [19] [4800/6250] eta: 0:03:17 lr: 0.000118 grad: 0.0606 (0.0642) loss: 0.8331 (0.8381) time: 0.1520 data: 0.0683 max mem: 9390 +Train: [19] [4900/6250] eta: 0:03:03 lr: 0.000118 grad: 0.0595 (0.0642) loss: 0.8347 (0.8381) time: 0.1348 data: 0.0464 max mem: 9390 +Train: [19] [5000/6250] eta: 0:02:49 lr: 0.000118 grad: 0.0638 (0.0642) loss: 0.8389 (0.8381) time: 0.1179 data: 0.0422 max mem: 9390 +Train: [19] [5100/6250] eta: 0:02:35 lr: 0.000118 grad: 0.0651 (0.0642) loss: 0.8337 (0.8380) time: 0.1331 data: 0.0554 max mem: 9390 +Train: [19] [5200/6250] eta: 0:02:22 lr: 0.000118 grad: 0.0609 (0.0643) loss: 0.8387 (0.8380) time: 0.1139 data: 0.0288 max mem: 9390 +Train: [19] [5300/6250] eta: 0:02:08 lr: 0.000118 grad: 0.0579 (0.0643) loss: 0.8422 (0.8380) time: 0.1358 data: 0.0617 max mem: 9390 +Train: [19] [5400/6250] eta: 0:01:54 lr: 0.000118 grad: 0.0581 (0.0643) loss: 0.8362 (0.8380) time: 0.1408 data: 0.0675 max mem: 9390 +Train: [19] [5500/6250] eta: 0:01:41 lr: 0.000118 grad: 0.0621 (0.0643) loss: 0.8399 (0.8380) time: 0.1405 data: 0.0623 max mem: 9390 +Train: [19] [5600/6250] eta: 0:01:27 lr: 0.000118 grad: 0.0615 (0.0643) loss: 0.8368 (0.8380) time: 0.1418 data: 0.0661 max mem: 9390 +Train: [19] [5700/6250] eta: 0:01:14 lr: 0.000118 grad: 0.0592 (0.0642) loss: 0.8366 (0.8380) time: 0.1423 data: 0.0647 max mem: 9390 +Train: [19] [5800/6250] eta: 0:01:00 lr: 0.000118 grad: 0.0630 (0.0642) loss: 0.8309 (0.8379) time: 0.1379 data: 0.0587 max mem: 9390 +Train: [19] [5900/6250] eta: 0:00:47 lr: 0.000118 grad: 0.0608 (0.0642) loss: 0.8396 (0.8379) time: 0.1263 data: 0.0489 max mem: 9390 +Train: [19] [6000/6250] eta: 0:00:33 lr: 0.000118 grad: 0.0603 (0.0642) loss: 0.8308 (0.8379) time: 0.1329 data: 0.0542 max mem: 9390 +Train: [19] [6100/6250] eta: 0:00:20 lr: 0.000117 grad: 0.0653 (0.0642) loss: 0.8310 (0.8379) time: 0.1282 data: 0.0533 max mem: 9390 +Train: [19] [6200/6250] eta: 0:00:06 lr: 0.000117 grad: 0.0591 (0.0642) loss: 0.8376 (0.8378) time: 0.1654 data: 0.0881 max mem: 9390 +Train: [19] [6249/6250] eta: 0:00:00 lr: 0.000117 grad: 0.0584 (0.0642) loss: 0.8375 (0.8378) time: 0.1559 data: 0.0755 max mem: 9390 +Train: [19] Total time: 0:14:09 (0.1359 s / it) +Averaged stats: lr: 0.000117 grad: 0.0584 (0.0642) loss: 0.8375 (0.8378) +Eval (hcp-train-subset): [19] [ 0/62] eta: 0:03:06 loss: 0.8513 (0.8513) time: 3.0004 data: 2.8989 max mem: 9390 +Eval (hcp-train-subset): [19] [61/62] eta: 0:00:00 loss: 0.8456 (0.8464) time: 0.1192 data: 0.0943 max mem: 9390 +Eval (hcp-train-subset): [19] Total time: 0:00:12 (0.2040 s / it) +Averaged stats (hcp-train-subset): loss: 0.8456 (0.8464) +Making plots (hcp-train-subset): example=38 +Eval (hcp-val): [19] [ 0/62] eta: 0:04:47 loss: 0.8357 (0.8357) time: 4.6343 data: 4.6057 max mem: 9390 +Eval (hcp-val): [19] [61/62] eta: 0:00:00 loss: 0.8393 (0.8412) time: 0.1198 data: 0.0952 max mem: 9390 +Eval (hcp-val): [19] Total time: 0:00:11 (0.1805 s / it) +Averaged stats (hcp-val): loss: 0.8393 (0.8412) +Making plots (hcp-val): example=32 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +Train: [20] [ 0/6250] eta: 8:27:38 lr: 0.000117 grad: 0.0475 (0.0475) loss: 0.8676 (0.8676) time: 4.8734 data: 4.7801 max mem: 9390 +Train: [20] [ 100/6250] eta: 0:17:47 lr: 0.000117 grad: 0.0659 (0.0793) loss: 0.8460 (0.8427) time: 0.1287 data: 0.0461 max mem: 9390 +Train: [20] [ 200/6250] eta: 0:15:43 lr: 0.000117 grad: 0.0586 (0.0726) loss: 0.8359 (0.8417) time: 0.1212 data: 0.0442 max mem: 9390 +Train: [20] [ 300/6250] eta: 0:14:39 lr: 0.000117 grad: 0.0612 (0.0700) loss: 0.8393 (0.8405) time: 0.1371 data: 0.0598 max mem: 9390 +Train: [20] [ 400/6250] eta: 0:13:48 lr: 0.000117 grad: 0.0656 (0.0689) loss: 0.8353 (0.8402) time: 0.1148 data: 0.0276 max mem: 9390 +Train: [20] [ 500/6250] eta: 0:13:18 lr: 0.000117 grad: 0.0615 (0.0683) loss: 0.8399 (0.8402) time: 0.1100 data: 0.0314 max mem: 9390 +Train: [20] [ 600/6250] eta: 0:12:48 lr: 0.000117 grad: 0.0639 (0.0679) loss: 0.8340 (0.8401) time: 0.1228 data: 0.0387 max mem: 9390 +Train: [20] [ 700/6250] eta: 0:12:24 lr: 0.000117 grad: 0.0642 (0.0672) loss: 0.8420 (0.8401) time: 0.1322 data: 0.0450 max mem: 9390 +Train: [20] [ 800/6250] eta: 0:11:59 lr: 0.000117 grad: 0.0593 (0.0666) loss: 0.8402 (0.8403) time: 0.1175 data: 0.0379 max mem: 9390 +Train: [20] [ 900/6250] eta: 0:11:39 lr: 0.000117 grad: 0.0551 (0.0660) loss: 0.8441 (0.8404) time: 0.1318 data: 0.0395 max mem: 9390 +Train: [20] [1000/6250] eta: 0:11:25 lr: 0.000117 grad: 0.0605 (0.0655) loss: 0.8410 (0.8406) time: 0.1241 data: 0.0418 max mem: 9390 +Train: [20] [1100/6250] eta: 0:11:13 lr: 0.000117 grad: 0.0658 (0.0652) loss: 0.8387 (0.8405) time: 0.1208 data: 0.0438 max mem: 9390 +Train: [20] [1200/6250] eta: 0:11:01 lr: 0.000117 grad: 0.0584 (0.0650) loss: 0.8397 (0.8403) time: 0.1331 data: 0.0542 max mem: 9390 +Train: [20] [1300/6250] eta: 0:10:46 lr: 0.000117 grad: 0.0565 (0.0646) loss: 0.8401 (0.8403) time: 0.1308 data: 0.0536 max mem: 9390 +Train: [20] [1400/6250] eta: 0:10:35 lr: 0.000117 grad: 0.0600 (0.0644) loss: 0.8412 (0.8402) time: 0.1354 data: 0.0537 max mem: 9390 +Train: [20] [1500/6250] eta: 0:10:28 lr: 0.000117 grad: 0.0593 (0.0642) loss: 0.8336 (0.8401) time: 0.1535 data: 0.0768 max mem: 9390 +Train: [20] [1600/6250] eta: 0:10:17 lr: 0.000117 grad: 0.0610 (0.0641) loss: 0.8430 (0.8400) time: 0.1512 data: 0.0682 max mem: 9390 +Train: [20] [1700/6250] eta: 0:10:04 lr: 0.000117 grad: 0.0578 (0.0640) loss: 0.8406 (0.8399) time: 0.1576 data: 0.0858 max mem: 9390 +Train: [20] [1800/6250] eta: 0:09:55 lr: 0.000117 grad: 0.0632 (0.0639) loss: 0.8362 (0.8398) time: 0.1730 data: 0.0930 max mem: 9390 +Train: [20] [1900/6250] eta: 0:09:42 lr: 0.000117 grad: 0.0600 (0.0639) loss: 0.8380 (0.8397) time: 0.1386 data: 0.0661 max mem: 9390 +Train: [20] [2000/6250] eta: 0:09:28 lr: 0.000117 grad: 0.0615 (0.0640) loss: 0.8397 (0.8396) time: 0.1405 data: 0.0607 max mem: 9390 +Train: [20] [2100/6250] eta: 0:09:17 lr: 0.000117 grad: 0.0597 (0.0642) loss: 0.8394 (0.8396) time: 0.1372 data: 0.0549 max mem: 9390 +Train: [20] [2200/6250] eta: 0:09:04 lr: 0.000117 grad: 0.0600 (0.0642) loss: 0.8386 (0.8394) time: 0.1346 data: 0.0492 max mem: 9390 +Train: [20] [2300/6250] eta: 0:08:52 lr: 0.000117 grad: 0.0618 (0.0641) loss: 0.8369 (0.8394) time: 0.1465 data: 0.0692 max mem: 9390 +Train: [20] [2400/6250] eta: 0:08:38 lr: 0.000117 grad: 0.0671 (0.0643) loss: 0.8358 (0.8392) time: 0.1429 data: 0.0667 max mem: 9390 +Train: [20] [2500/6250] eta: 0:08:24 lr: 0.000117 grad: 0.0582 (0.0643) loss: 0.8397 (0.8391) time: 0.1410 data: 0.0604 max mem: 9390 +Train: [20] [2600/6250] eta: 0:08:11 lr: 0.000117 grad: 0.0617 (0.0645) loss: 0.8399 (0.8389) time: 0.1203 data: 0.0381 max mem: 9390 +Train: [20] [2700/6250] eta: 0:07:57 lr: 0.000117 grad: 0.0627 (0.0645) loss: 0.8353 (0.8388) time: 0.1391 data: 0.0672 max mem: 9390 +Train: [20] [2800/6250] eta: 0:07:44 lr: 0.000117 grad: 0.0613 (0.0645) loss: 0.8329 (0.8387) time: 0.1520 data: 0.0728 max mem: 9390 +Train: [20] [2900/6250] eta: 0:07:30 lr: 0.000117 grad: 0.0622 (0.0645) loss: 0.8387 (0.8385) time: 0.1226 data: 0.0423 max mem: 9390 +Train: [20] [3000/6250] eta: 0:07:17 lr: 0.000117 grad: 0.0637 (0.0645) loss: 0.8362 (0.8384) time: 0.1326 data: 0.0490 max mem: 9390 +Train: [20] [3100/6250] eta: 0:07:04 lr: 0.000117 grad: 0.0616 (0.0645) loss: 0.8369 (0.8383) time: 0.1329 data: 0.0549 max mem: 9390 +Train: [20] [3200/6250] eta: 0:06:50 lr: 0.000117 grad: 0.0608 (0.0645) loss: 0.8354 (0.8383) time: 0.1343 data: 0.0620 max mem: 9390 +Train: [20] [3300/6250] eta: 0:06:37 lr: 0.000117 grad: 0.0608 (0.0645) loss: 0.8389 (0.8383) time: 0.1405 data: 0.0595 max mem: 9390 +Train: [20] [3400/6250] eta: 0:06:24 lr: 0.000117 grad: 0.0655 (0.0645) loss: 0.8389 (0.8383) time: 0.1105 data: 0.0309 max mem: 9390 +Train: [20] [3500/6250] eta: 0:06:11 lr: 0.000117 grad: 0.0669 (0.0645) loss: 0.8302 (0.8382) time: 0.1431 data: 0.0603 max mem: 9390 +Train: [20] [3600/6250] eta: 0:05:57 lr: 0.000117 grad: 0.0620 (0.0645) loss: 0.8377 (0.8381) time: 0.1504 data: 0.0683 max mem: 9390 +Train: [20] [3700/6250] eta: 0:05:44 lr: 0.000117 grad: 0.0611 (0.0645) loss: 0.8350 (0.8380) time: 0.1617 data: 0.0801 max mem: 9390 +Train: [20] [3800/6250] eta: 0:05:31 lr: 0.000117 grad: 0.0647 (0.0645) loss: 0.8362 (0.8380) time: 0.1562 data: 0.0831 max mem: 9390 +Train: [20] [3900/6250] eta: 0:05:18 lr: 0.000117 grad: 0.0655 (0.0645) loss: 0.8317 (0.8380) time: 0.1428 data: 0.0684 max mem: 9390 +Train: [20] [4000/6250] eta: 0:05:04 lr: 0.000117 grad: 0.0620 (0.0645) loss: 0.8354 (0.8379) time: 0.1389 data: 0.0609 max mem: 9390 +Train: [20] [4100/6250] eta: 0:04:50 lr: 0.000117 grad: 0.0634 (0.0646) loss: 0.8349 (0.8379) time: 0.1500 data: 0.0759 max mem: 9390 +Train: [20] [4200/6250] eta: 0:04:37 lr: 0.000117 grad: 0.0633 (0.0646) loss: 0.8434 (0.8379) time: 0.1415 data: 0.0637 max mem: 9390 +Train: [20] [4300/6250] eta: 0:04:23 lr: 0.000117 grad: 0.0611 (0.0647) loss: 0.8374 (0.8378) time: 0.1431 data: 0.0708 max mem: 9390 +Train: [20] [4400/6250] eta: 0:04:10 lr: 0.000117 grad: 0.0656 (0.0646) loss: 0.8419 (0.8378) time: 0.1377 data: 0.0591 max mem: 9390 +Train: [20] [4500/6250] eta: 0:03:56 lr: 0.000117 grad: 0.0644 (0.0647) loss: 0.8307 (0.8378) time: 0.1641 data: 0.0893 max mem: 9390 +Train: [20] [4600/6250] eta: 0:03:43 lr: 0.000117 grad: 0.0628 (0.0647) loss: 0.8374 (0.8378) time: 0.1449 data: 0.0665 max mem: 9390 +Train: [20] [4700/6250] eta: 0:03:29 lr: 0.000117 grad: 0.0603 (0.0646) loss: 0.8375 (0.8378) time: 0.1478 data: 0.0693 max mem: 9390 +Train: [20] [4800/6250] eta: 0:03:16 lr: 0.000117 grad: 0.0628 (0.0646) loss: 0.8399 (0.8378) time: 0.1516 data: 0.0747 max mem: 9390 +Train: [20] [4900/6250] eta: 0:03:03 lr: 0.000117 grad: 0.0621 (0.0646) loss: 0.8348 (0.8377) time: 0.1419 data: 0.0675 max mem: 9390 +Train: [20] [5000/6250] eta: 0:02:49 lr: 0.000117 grad: 0.0626 (0.0646) loss: 0.8358 (0.8377) time: 0.1268 data: 0.0477 max mem: 9390 +Train: [20] [5100/6250] eta: 0:02:35 lr: 0.000117 grad: 0.0643 (0.0646) loss: 0.8359 (0.8377) time: 0.1406 data: 0.0616 max mem: 9390 +Train: [20] [5200/6250] eta: 0:02:22 lr: 0.000117 grad: 0.0603 (0.0646) loss: 0.8400 (0.8377) time: 0.1408 data: 0.0544 max mem: 9390 +Train: [20] [5300/6250] eta: 0:02:08 lr: 0.000117 grad: 0.0590 (0.0646) loss: 0.8354 (0.8377) time: 0.1505 data: 0.0727 max mem: 9390 +Train: [20] [5400/6250] eta: 0:01:55 lr: 0.000117 grad: 0.0631 (0.0646) loss: 0.8392 (0.8376) time: 0.1345 data: 0.0609 max mem: 9390 +Train: [20] [5500/6250] eta: 0:01:41 lr: 0.000117 grad: 0.0631 (0.0646) loss: 0.8359 (0.8376) time: 0.1387 data: 0.0661 max mem: 9390 +Train: [20] [5600/6250] eta: 0:01:27 lr: 0.000117 grad: 0.0651 (0.0646) loss: 0.8302 (0.8376) time: 0.1421 data: 0.0614 max mem: 9390 +Train: [20] [5700/6250] eta: 0:01:14 lr: 0.000117 grad: 0.0673 (0.0646) loss: 0.8349 (0.8376) time: 0.1377 data: 0.0583 max mem: 9390 +Train: [20] [5800/6250] eta: 0:01:00 lr: 0.000117 grad: 0.0650 (0.0646) loss: 0.8391 (0.8375) time: 0.1201 data: 0.0403 max mem: 9390 +Train: [20] [5900/6250] eta: 0:00:47 lr: 0.000117 grad: 0.0641 (0.0647) loss: 0.8317 (0.8375) time: 0.1497 data: 0.0718 max mem: 9390 +Train: [20] [6000/6250] eta: 0:00:33 lr: 0.000116 grad: 0.0636 (0.0647) loss: 0.8390 (0.8375) time: 0.1429 data: 0.0627 max mem: 9390 +Train: [20] [6100/6250] eta: 0:00:20 lr: 0.000116 grad: 0.0649 (0.0648) loss: 0.8315 (0.8374) time: 0.1264 data: 0.0478 max mem: 9390 +Train: [20] [6200/6250] eta: 0:00:06 lr: 0.000116 grad: 0.0612 (0.0648) loss: 0.8377 (0.8374) time: 0.1529 data: 0.0743 max mem: 9390 +Train: [20] [6249/6250] eta: 0:00:00 lr: 0.000116 grad: 0.0680 (0.0648) loss: 0.8357 (0.8374) time: 0.1327 data: 0.0504 max mem: 9390 +Train: [20] Total time: 0:14:09 (0.1359 s / it) +Averaged stats: lr: 0.000116 grad: 0.0680 (0.0648) loss: 0.8357 (0.8374) +Eval (hcp-train-subset): [20] [ 0/62] eta: 0:02:58 loss: 0.8582 (0.8582) time: 2.8856 data: 2.8268 max mem: 9390 +Eval (hcp-train-subset): [20] [61/62] eta: 0:00:00 loss: 0.8462 (0.8466) time: 0.1434 data: 0.1167 max mem: 9390 +Eval (hcp-train-subset): [20] Total time: 0:00:13 (0.2158 s / it) +Averaged stats (hcp-train-subset): loss: 0.8462 (0.8466) +Eval (hcp-val): [20] [ 0/62] eta: 0:03:04 loss: 0.8396 (0.8396) time: 2.9731 data: 2.9089 max mem: 9390 +Eval (hcp-val): [20] [61/62] eta: 0:00:00 loss: 0.8411 (0.8420) time: 0.1208 data: 0.0944 max mem: 9390 +Eval (hcp-val): [20] Total time: 0:00:11 (0.1868 s / it) +Averaged stats (hcp-val): loss: 0.8411 (0.8420) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +Train: [21] [ 0/6250] eta: 8:27:33 lr: 0.000116 grad: 0.0795 (0.0795) loss: 0.8563 (0.8563) time: 4.8725 data: 4.7810 max mem: 9390 +Train: [21] [ 100/6250] eta: 0:17:57 lr: 0.000116 grad: 0.0599 (0.0682) loss: 0.8463 (0.8507) time: 0.1357 data: 0.0519 max mem: 9390 +Train: [21] [ 200/6250] eta: 0:15:32 lr: 0.000116 grad: 0.0606 (0.0682) loss: 0.8459 (0.8473) time: 0.1129 data: 0.0248 max mem: 9390 +Train: [21] [ 300/6250] eta: 0:14:23 lr: 0.000116 grad: 0.0698 (0.0678) loss: 0.8389 (0.8454) time: 0.1180 data: 0.0291 max mem: 9390 +Train: [21] [ 400/6250] eta: 0:13:43 lr: 0.000116 grad: 0.0702 (0.0683) loss: 0.8378 (0.8436) time: 0.1231 data: 0.0459 max mem: 9390 +Train: [21] [ 500/6250] eta: 0:13:08 lr: 0.000116 grad: 0.0644 (0.0675) loss: 0.8427 (0.8425) time: 0.1207 data: 0.0382 max mem: 9390 +Train: [21] [ 600/6250] eta: 0:12:43 lr: 0.000116 grad: 0.0621 (0.0670) loss: 0.8404 (0.8422) time: 0.1361 data: 0.0523 max mem: 9390 +Train: [21] [ 700/6250] eta: 0:12:18 lr: 0.000116 grad: 0.0621 (0.0663) loss: 0.8417 (0.8419) time: 0.1277 data: 0.0494 max mem: 9390 +Train: [21] [ 800/6250] eta: 0:12:16 lr: 0.000116 grad: 0.0608 (0.0660) loss: 0.8415 (0.8413) time: 0.1327 data: 0.0552 max mem: 9390 +Train: [21] [ 900/6250] eta: 0:12:19 lr: 0.000116 grad: 0.0626 (0.0658) loss: 0.8404 (0.8410) time: 0.1486 data: 0.0672 max mem: 9390 +Train: [21] [1000/6250] eta: 0:12:14 lr: 0.000116 grad: 0.0599 (0.0656) loss: 0.8328 (0.8408) time: 0.1448 data: 0.0606 max mem: 9390 +Train: [21] [1100/6250] eta: 0:12:02 lr: 0.000116 grad: 0.0605 (0.0655) loss: 0.8451 (0.8406) time: 0.1465 data: 0.0652 max mem: 9390 +Train: [21] [1200/6250] eta: 0:11:46 lr: 0.000116 grad: 0.0635 (0.0653) loss: 0.8425 (0.8405) time: 0.1429 data: 0.0603 max mem: 9390 +Train: [21] [1300/6250] eta: 0:11:33 lr: 0.000116 grad: 0.0615 (0.0651) loss: 0.8364 (0.8402) time: 0.1452 data: 0.0654 max mem: 9390 +Train: [21] [1400/6250] eta: 0:11:22 lr: 0.000116 grad: 0.0616 (0.0650) loss: 0.8397 (0.8400) time: 0.1355 data: 0.0538 max mem: 9390 +Train: [21] [1500/6250] eta: 0:11:10 lr: 0.000116 grad: 0.0620 (0.0649) loss: 0.8361 (0.8397) time: 0.1456 data: 0.0722 max mem: 9390 +Train: [21] [1600/6250] eta: 0:10:55 lr: 0.000116 grad: 0.0613 (0.0648) loss: 0.8321 (0.8395) time: 0.1237 data: 0.0427 max mem: 9390 +Train: [21] [1700/6250] eta: 0:10:41 lr: 0.000116 grad: 0.0618 (0.0648) loss: 0.8340 (0.8391) time: 0.1396 data: 0.0639 max mem: 9390 +Train: [21] [1800/6250] eta: 0:10:28 lr: 0.000116 grad: 0.0611 (0.0648) loss: 0.8311 (0.8389) time: 0.1423 data: 0.0671 max mem: 9390 +Train: [21] [1900/6250] eta: 0:10:14 lr: 0.000116 grad: 0.0635 (0.0648) loss: 0.8366 (0.8387) time: 0.1371 data: 0.0589 max mem: 9390 +Train: [21] [2000/6250] eta: 0:10:00 lr: 0.000116 grad: 0.0659 (0.0648) loss: 0.8343 (0.8386) time: 0.1492 data: 0.0738 max mem: 9390 +Train: [21] [2100/6250] eta: 0:09:45 lr: 0.000116 grad: 0.0631 (0.0648) loss: 0.8330 (0.8385) time: 0.1296 data: 0.0532 max mem: 9390 +Train: [21] [2200/6250] eta: 0:09:29 lr: 0.000116 grad: 0.0611 (0.0647) loss: 0.8377 (0.8385) time: 0.1377 data: 0.0619 max mem: 9390 +Train: [21] [2300/6250] eta: 0:09:15 lr: 0.000116 grad: 0.0630 (0.0646) loss: 0.8357 (0.8385) time: 0.1378 data: 0.0583 max mem: 9390 +Train: [21] [2400/6250] eta: 0:08:59 lr: 0.000116 grad: 0.0599 (0.0646) loss: 0.8400 (0.8385) time: 0.1259 data: 0.0472 max mem: 9390 +Train: [21] [2500/6250] eta: 0:08:45 lr: 0.000116 grad: 0.0595 (0.0645) loss: 0.8352 (0.8384) time: 0.1208 data: 0.0404 max mem: 9390 +Train: [21] [2600/6250] eta: 0:08:30 lr: 0.000116 grad: 0.0616 (0.0645) loss: 0.8415 (0.8385) time: 0.1255 data: 0.0539 max mem: 9390 +Train: [21] [2700/6250] eta: 0:08:15 lr: 0.000116 grad: 0.0626 (0.0644) loss: 0.8382 (0.8385) time: 0.1322 data: 0.0532 max mem: 9390 +Train: [21] [2800/6250] eta: 0:08:03 lr: 0.000116 grad: 0.0672 (0.0645) loss: 0.8367 (0.8386) time: 0.1348 data: 0.0584 max mem: 9390 +Train: [21] [2900/6250] eta: 0:07:49 lr: 0.000116 grad: 0.0613 (0.0646) loss: 0.8362 (0.8385) time: 0.1557 data: 0.0794 max mem: 9390 +Train: [21] [3000/6250] eta: 0:07:35 lr: 0.000116 grad: 0.0609 (0.0645) loss: 0.8346 (0.8384) time: 0.1520 data: 0.0710 max mem: 9390 +Train: [21] [3100/6250] eta: 0:07:20 lr: 0.000116 grad: 0.0640 (0.0646) loss: 0.8364 (0.8383) time: 0.1371 data: 0.0577 max mem: 9390 +Train: [21] [3200/6250] eta: 0:07:06 lr: 0.000116 grad: 0.0639 (0.0646) loss: 0.8337 (0.8382) time: 0.1445 data: 0.0684 max mem: 9390 +Train: [21] [3300/6250] eta: 0:06:51 lr: 0.000116 grad: 0.0598 (0.0647) loss: 0.8421 (0.8382) time: 0.1261 data: 0.0494 max mem: 9390 +Train: [21] [3400/6250] eta: 0:06:37 lr: 0.000116 grad: 0.0645 (0.0647) loss: 0.8310 (0.8381) time: 0.1322 data: 0.0480 max mem: 9390 +Train: [21] [3500/6250] eta: 0:06:22 lr: 0.000116 grad: 0.0647 (0.0647) loss: 0.8359 (0.8381) time: 0.1280 data: 0.0514 max mem: 9390 +Train: [21] [3600/6250] eta: 0:06:08 lr: 0.000116 grad: 0.0634 (0.0647) loss: 0.8345 (0.8380) time: 0.1328 data: 0.0578 max mem: 9390 +Train: [21] [3700/6250] eta: 0:05:54 lr: 0.000116 grad: 0.0620 (0.0647) loss: 0.8373 (0.8380) time: 0.1367 data: 0.0575 max mem: 9390 +Train: [21] [3800/6250] eta: 0:05:39 lr: 0.000116 grad: 0.0632 (0.0647) loss: 0.8353 (0.8380) time: 0.1307 data: 0.0482 max mem: 9390 +Train: [21] [3900/6250] eta: 0:05:25 lr: 0.000116 grad: 0.0661 (0.0648) loss: 0.8314 (0.8379) time: 0.1084 data: 0.0338 max mem: 9390 +Train: [21] [4000/6250] eta: 0:05:11 lr: 0.000116 grad: 0.0667 (0.0648) loss: 0.8362 (0.8378) time: 0.1587 data: 0.0842 max mem: 9390 +Train: [21] [4100/6250] eta: 0:04:57 lr: 0.000116 grad: 0.0631 (0.0648) loss: 0.8313 (0.8378) time: 0.1128 data: 0.0368 max mem: 9390 +Train: [21] [4200/6250] eta: 0:04:43 lr: 0.000116 grad: 0.0629 (0.0648) loss: 0.8320 (0.8378) time: 0.1566 data: 0.0813 max mem: 9390 +Train: [21] [4300/6250] eta: 0:04:29 lr: 0.000116 grad: 0.0618 (0.0648) loss: 0.8327 (0.8377) time: 0.1396 data: 0.0638 max mem: 9390 +Train: [21] [4400/6250] eta: 0:04:16 lr: 0.000116 grad: 0.0619 (0.0649) loss: 0.8382 (0.8377) time: 0.1509 data: 0.0745 max mem: 9390 +Train: [21] [4500/6250] eta: 0:04:01 lr: 0.000116 grad: 0.0602 (0.0649) loss: 0.8387 (0.8377) time: 0.1300 data: 0.0521 max mem: 9390 +Train: [21] [4600/6250] eta: 0:03:48 lr: 0.000116 grad: 0.0659 (0.0649) loss: 0.8355 (0.8377) time: 0.1093 data: 0.0286 max mem: 9390 +Train: [21] [4700/6250] eta: 0:03:34 lr: 0.000116 grad: 0.0632 (0.0649) loss: 0.8367 (0.8376) time: 0.1181 data: 0.0379 max mem: 9390 +Train: [21] [4800/6250] eta: 0:03:20 lr: 0.000116 grad: 0.0585 (0.0649) loss: 0.8384 (0.8376) time: 0.1201 data: 0.0406 max mem: 9390 +Train: [21] [4900/6250] eta: 0:03:06 lr: 0.000116 grad: 0.0663 (0.0649) loss: 0.8391 (0.8376) time: 0.1535 data: 0.0711 max mem: 9390 +Train: [21] [5000/6250] eta: 0:02:52 lr: 0.000116 grad: 0.0685 (0.0649) loss: 0.8329 (0.8376) time: 0.1058 data: 0.0273 max mem: 9390 +Train: [21] [5100/6250] eta: 0:02:38 lr: 0.000116 grad: 0.0628 (0.0650) loss: 0.8378 (0.8376) time: 0.1288 data: 0.0484 max mem: 9390 +Train: [21] [5200/6250] eta: 0:02:24 lr: 0.000116 grad: 0.0630 (0.0650) loss: 0.8414 (0.8376) time: 0.1547 data: 0.0767 max mem: 9390 +Train: [21] [5300/6250] eta: 0:02:10 lr: 0.000116 grad: 0.0635 (0.0650) loss: 0.8310 (0.8376) time: 0.1379 data: 0.0617 max mem: 9390 +Train: [21] [5400/6250] eta: 0:01:56 lr: 0.000116 grad: 0.0638 (0.0651) loss: 0.8356 (0.8375) time: 0.1255 data: 0.0540 max mem: 9390 +Train: [21] [5500/6250] eta: 0:01:42 lr: 0.000116 grad: 0.0660 (0.0651) loss: 0.8319 (0.8375) time: 0.1310 data: 0.0534 max mem: 9390 +Train: [21] [5600/6250] eta: 0:01:29 lr: 0.000115 grad: 0.0629 (0.0651) loss: 0.8333 (0.8375) time: 0.1350 data: 0.0544 max mem: 9390 +Train: [21] [5700/6250] eta: 0:01:15 lr: 0.000115 grad: 0.0636 (0.0651) loss: 0.8348 (0.8375) time: 0.1273 data: 0.0494 max mem: 9390 +Train: [21] [5800/6250] eta: 0:01:01 lr: 0.000115 grad: 0.0663 (0.0651) loss: 0.8395 (0.8375) time: 0.1375 data: 0.0626 max mem: 9390 +Train: [21] [5900/6250] eta: 0:00:47 lr: 0.000115 grad: 0.0577 (0.0650) loss: 0.8397 (0.8375) time: 0.1366 data: 0.0549 max mem: 9390 +Train: [21] [6000/6250] eta: 0:00:34 lr: 0.000115 grad: 0.0623 (0.0650) loss: 0.8404 (0.8376) time: 0.1500 data: 0.0760 max mem: 9390 +Train: [21] [6100/6250] eta: 0:00:20 lr: 0.000115 grad: 0.0645 (0.0650) loss: 0.8417 (0.8376) time: 0.1320 data: 0.0573 max mem: 9390 +Train: [21] [6200/6250] eta: 0:00:06 lr: 0.000115 grad: 0.0618 (0.0650) loss: 0.8372 (0.8376) time: 0.1706 data: 0.0956 max mem: 9390 +Train: [21] [6249/6250] eta: 0:00:00 lr: 0.000115 grad: 0.0629 (0.0649) loss: 0.8344 (0.8376) time: 0.1263 data: 0.0450 max mem: 9390 +Train: [21] Total time: 0:14:19 (0.1376 s / it) +Averaged stats: lr: 0.000115 grad: 0.0629 (0.0649) loss: 0.8344 (0.8376) +Eval (hcp-train-subset): [21] [ 0/62] eta: 0:03:19 loss: 0.8567 (0.8567) time: 3.2251 data: 3.1305 max mem: 9390 +Eval (hcp-train-subset): [21] [61/62] eta: 0:00:00 loss: 0.8461 (0.8463) time: 0.1281 data: 0.1030 max mem: 9390 +Eval (hcp-train-subset): [21] Total time: 0:00:13 (0.2110 s / it) +Averaged stats (hcp-train-subset): loss: 0.8461 (0.8463) +Eval (hcp-val): [21] [ 0/62] eta: 0:04:34 loss: 0.8405 (0.8405) time: 4.4294 data: 4.4010 max mem: 9390 +Eval (hcp-val): [21] [61/62] eta: 0:00:00 loss: 0.8393 (0.8411) time: 0.1230 data: 0.0984 max mem: 9390 +Eval (hcp-val): [21] Total time: 0:00:11 (0.1884 s / it) +Averaged stats (hcp-val): loss: 0.8393 (0.8411) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +Train: [22] [ 0/6250] eta: 9:01:28 lr: 0.000115 grad: 0.0496 (0.0496) loss: 0.8634 (0.8634) time: 5.1981 data: 5.0833 max mem: 9390 +Train: [22] [ 100/6250] eta: 0:18:06 lr: 0.000115 grad: 0.0644 (0.0703) loss: 0.8361 (0.8397) time: 0.1384 data: 0.0640 max mem: 9390 +Train: [22] [ 200/6250] eta: 0:15:28 lr: 0.000115 grad: 0.0633 (0.0702) loss: 0.8364 (0.8377) time: 0.1341 data: 0.0515 max mem: 9390 +Train: [22] [ 300/6250] eta: 0:14:21 lr: 0.000115 grad: 0.0666 (0.0686) loss: 0.8321 (0.8370) time: 0.1175 data: 0.0409 max mem: 9390 +Train: [22] [ 400/6250] eta: 0:13:37 lr: 0.000115 grad: 0.0656 (0.0683) loss: 0.8322 (0.8367) time: 0.1234 data: 0.0438 max mem: 9390 +Train: [22] [ 500/6250] eta: 0:13:07 lr: 0.000115 grad: 0.0592 (0.0675) loss: 0.8375 (0.8367) time: 0.1267 data: 0.0405 max mem: 9390 +Train: [22] [ 600/6250] eta: 0:12:38 lr: 0.000115 grad: 0.0609 (0.0671) loss: 0.8395 (0.8368) time: 0.1183 data: 0.0347 max mem: 9390 +Train: [22] [ 700/6250] eta: 0:12:31 lr: 0.000115 grad: 0.0615 (0.0665) loss: 0.8347 (0.8370) time: 0.2166 data: 0.1362 max mem: 9390 +Train: [22] [ 800/6250] eta: 0:12:33 lr: 0.000115 grad: 0.0581 (0.0661) loss: 0.8382 (0.8370) time: 0.1754 data: 0.0916 max mem: 9390 +Train: [22] [ 900/6250] eta: 0:12:35 lr: 0.000115 grad: 0.0610 (0.0656) loss: 0.8436 (0.8372) time: 0.1589 data: 0.0761 max mem: 9390 +Train: [22] [1000/6250] eta: 0:12:23 lr: 0.000115 grad: 0.0571 (0.0651) loss: 0.8414 (0.8374) time: 0.1278 data: 0.0520 max mem: 9390 +Train: [22] [1100/6250] eta: 0:12:06 lr: 0.000115 grad: 0.0623 (0.0650) loss: 0.8325 (0.8371) time: 0.1295 data: 0.0544 max mem: 9390 +Train: [22] [1200/6250] eta: 0:11:51 lr: 0.000115 grad: 0.0621 (0.0648) loss: 0.8316 (0.8369) time: 0.1440 data: 0.0676 max mem: 9390 +Train: [22] [1300/6250] eta: 0:11:35 lr: 0.000115 grad: 0.0615 (0.0648) loss: 0.8331 (0.8367) time: 0.1599 data: 0.0785 max mem: 9390 +Train: [22] [1400/6250] eta: 0:11:19 lr: 0.000115 grad: 0.0584 (0.0647) loss: 0.8361 (0.8366) time: 0.1455 data: 0.0694 max mem: 9390 +Train: [22] [1500/6250] eta: 0:11:06 lr: 0.000115 grad: 0.0627 (0.0646) loss: 0.8289 (0.8365) time: 0.1449 data: 0.0664 max mem: 9390 +Train: [22] [1600/6250] eta: 0:10:52 lr: 0.000115 grad: 0.0627 (0.0647) loss: 0.8356 (0.8364) time: 0.1169 data: 0.0377 max mem: 9390 +Train: [22] [1700/6250] eta: 0:10:38 lr: 0.000115 grad: 0.0623 (0.0647) loss: 0.8313 (0.8362) time: 0.1328 data: 0.0506 max mem: 9390 +Train: [22] [1800/6250] eta: 0:10:25 lr: 0.000115 grad: 0.0608 (0.0646) loss: 0.8342 (0.8361) time: 0.1489 data: 0.0708 max mem: 9390 +Train: [22] [1900/6250] eta: 0:10:13 lr: 0.000115 grad: 0.0623 (0.0646) loss: 0.8322 (0.8361) time: 0.1606 data: 0.0746 max mem: 9390 +Train: [22] [2000/6250] eta: 0:09:59 lr: 0.000115 grad: 0.0597 (0.0646) loss: 0.8354 (0.8360) time: 0.1333 data: 0.0577 max mem: 9390 +Train: [22] [2100/6250] eta: 0:09:44 lr: 0.000115 grad: 0.0647 (0.0647) loss: 0.8291 (0.8359) time: 0.1454 data: 0.0695 max mem: 9390 +Train: [22] [2200/6250] eta: 0:09:29 lr: 0.000115 grad: 0.0633 (0.0647) loss: 0.8282 (0.8358) time: 0.1229 data: 0.0427 max mem: 9390 +Train: [22] [2300/6250] eta: 0:09:15 lr: 0.000115 grad: 0.0619 (0.0647) loss: 0.8372 (0.8358) time: 0.1398 data: 0.0591 max mem: 9390 +Train: [22] [2400/6250] eta: 0:09:01 lr: 0.000115 grad: 0.0618 (0.0647) loss: 0.8366 (0.8358) time: 0.1522 data: 0.0782 max mem: 9390 +Train: [22] [2500/6250] eta: 0:08:46 lr: 0.000115 grad: 0.0626 (0.0646) loss: 0.8367 (0.8358) time: 0.1384 data: 0.0620 max mem: 9390 +Train: [22] [2600/6250] eta: 0:08:31 lr: 0.000115 grad: 0.0601 (0.0646) loss: 0.8350 (0.8358) time: 0.1393 data: 0.0613 max mem: 9390 +Train: [22] [2700/6250] eta: 0:08:17 lr: 0.000115 grad: 0.0619 (0.0646) loss: 0.8409 (0.8359) time: 0.1364 data: 0.0590 max mem: 9390 +Train: [22] [2800/6250] eta: 0:08:03 lr: 0.000115 grad: 0.0630 (0.0646) loss: 0.8352 (0.8359) time: 0.0972 data: 0.0137 max mem: 9390 +Train: [22] [2900/6250] eta: 0:07:48 lr: 0.000115 grad: 0.0624 (0.0646) loss: 0.8411 (0.8359) time: 0.1425 data: 0.0623 max mem: 9390 +Train: [22] [3000/6250] eta: 0:07:34 lr: 0.000115 grad: 0.0580 (0.0646) loss: 0.8397 (0.8360) time: 0.1315 data: 0.0508 max mem: 9390 +Train: [22] [3100/6250] eta: 0:07:19 lr: 0.000115 grad: 0.0631 (0.0646) loss: 0.8337 (0.8361) time: 0.1437 data: 0.0613 max mem: 9390 +Train: [22] [3200/6250] eta: 0:07:05 lr: 0.000115 grad: 0.0624 (0.0646) loss: 0.8366 (0.8361) time: 0.1422 data: 0.0641 max mem: 9390 +Train: [22] [3300/6250] eta: 0:06:51 lr: 0.000115 grad: 0.0633 (0.0646) loss: 0.8371 (0.8360) time: 0.1173 data: 0.0369 max mem: 9390 +Train: [22] [3400/6250] eta: 0:06:36 lr: 0.000115 grad: 0.0626 (0.0646) loss: 0.8385 (0.8361) time: 0.1223 data: 0.0446 max mem: 9390 +Train: [22] [3500/6250] eta: 0:06:22 lr: 0.000115 grad: 0.0627 (0.0647) loss: 0.8420 (0.8361) time: 0.1362 data: 0.0544 max mem: 9390 +Train: [22] [3600/6250] eta: 0:06:08 lr: 0.000115 grad: 0.0647 (0.0648) loss: 0.8317 (0.8360) time: 0.1327 data: 0.0582 max mem: 9390 +Train: [22] [3700/6250] eta: 0:05:54 lr: 0.000115 grad: 0.0614 (0.0650) loss: 0.8375 (0.8359) time: 0.1326 data: 0.0530 max mem: 9390 +Train: [22] [3800/6250] eta: 0:05:39 lr: 0.000115 grad: 0.0621 (0.0651) loss: 0.8340 (0.8358) time: 0.1282 data: 0.0525 max mem: 9390 +Train: [22] [3900/6250] eta: 0:05:25 lr: 0.000115 grad: 0.0649 (0.0651) loss: 0.8325 (0.8358) time: 0.1234 data: 0.0472 max mem: 9390 +Train: [22] [4000/6250] eta: 0:05:11 lr: 0.000115 grad: 0.0663 (0.0653) loss: 0.8309 (0.8357) time: 0.1372 data: 0.0585 max mem: 9390 +Train: [22] [4100/6250] eta: 0:04:57 lr: 0.000115 grad: 0.0664 (0.0653) loss: 0.8344 (0.8356) time: 0.1578 data: 0.0761 max mem: 9390 +Train: [22] [4200/6250] eta: 0:04:43 lr: 0.000115 grad: 0.0650 (0.0654) loss: 0.8361 (0.8356) time: 0.1296 data: 0.0521 max mem: 9390 +Train: [22] [4300/6250] eta: 0:04:29 lr: 0.000115 grad: 0.0700 (0.0655) loss: 0.8337 (0.8355) time: 0.1269 data: 0.0468 max mem: 9390 +Train: [22] [4400/6250] eta: 0:04:15 lr: 0.000115 grad: 0.0675 (0.0656) loss: 0.8280 (0.8354) time: 0.1409 data: 0.0618 max mem: 9390 +Train: [22] [4500/6250] eta: 0:04:01 lr: 0.000115 grad: 0.0661 (0.0657) loss: 0.8315 (0.8353) time: 0.1219 data: 0.0413 max mem: 9390 +Train: [22] [4600/6250] eta: 0:03:47 lr: 0.000115 grad: 0.0652 (0.0657) loss: 0.8318 (0.8353) time: 0.1299 data: 0.0506 max mem: 9390 +Train: [22] [4700/6250] eta: 0:03:33 lr: 0.000115 grad: 0.0639 (0.0658) loss: 0.8307 (0.8353) time: 0.1460 data: 0.0682 max mem: 9390 +Train: [22] [4800/6250] eta: 0:03:19 lr: 0.000115 grad: 0.0688 (0.0659) loss: 0.8357 (0.8352) time: 0.1277 data: 0.0476 max mem: 9390 +Train: [22] [4900/6250] eta: 0:03:05 lr: 0.000114 grad: 0.0616 (0.0659) loss: 0.8382 (0.8352) time: 0.1407 data: 0.0632 max mem: 9390 +Train: [22] [5000/6250] eta: 0:02:51 lr: 0.000114 grad: 0.0651 (0.0659) loss: 0.8422 (0.8352) time: 0.1141 data: 0.0363 max mem: 9390 +Train: [22] [5100/6250] eta: 0:02:37 lr: 0.000114 grad: 0.0650 (0.0660) loss: 0.8392 (0.8352) time: 0.1382 data: 0.0616 max mem: 9390 +Train: [22] [5200/6250] eta: 0:02:23 lr: 0.000114 grad: 0.0684 (0.0660) loss: 0.8339 (0.8352) time: 0.1412 data: 0.0613 max mem: 9390 +Train: [22] [5300/6250] eta: 0:02:10 lr: 0.000114 grad: 0.0632 (0.0660) loss: 0.8341 (0.8352) time: 0.1387 data: 0.0608 max mem: 9390 +Train: [22] [5400/6250] eta: 0:01:56 lr: 0.000114 grad: 0.0660 (0.0660) loss: 0.8360 (0.8352) time: 0.1397 data: 0.0616 max mem: 9390 +Train: [22] [5500/6250] eta: 0:01:42 lr: 0.000114 grad: 0.0670 (0.0660) loss: 0.8366 (0.8353) time: 0.1281 data: 0.0487 max mem: 9390 +Train: [22] [5600/6250] eta: 0:01:28 lr: 0.000114 grad: 0.0636 (0.0660) loss: 0.8346 (0.8353) time: 0.1218 data: 0.0413 max mem: 9390 +Train: [22] [5700/6250] eta: 0:01:15 lr: 0.000114 grad: 0.0643 (0.0660) loss: 0.8342 (0.8352) time: 0.1309 data: 0.0531 max mem: 9390 +Train: [22] [5800/6250] eta: 0:01:01 lr: 0.000114 grad: 0.0641 (0.0660) loss: 0.8392 (0.8353) time: 0.1332 data: 0.0576 max mem: 9390 +Train: [22] [5900/6250] eta: 0:00:47 lr: 0.000114 grad: 0.0678 (0.0661) loss: 0.8339 (0.8353) time: 0.1333 data: 0.0505 max mem: 9390 +Train: [22] [6000/6250] eta: 0:00:34 lr: 0.000114 grad: 0.0629 (0.0661) loss: 0.8349 (0.8353) time: 0.1283 data: 0.0488 max mem: 9390 +Train: [22] [6100/6250] eta: 0:00:20 lr: 0.000114 grad: 0.0632 (0.0661) loss: 0.8361 (0.8353) time: 0.1311 data: 0.0541 max mem: 9390 +Train: [22] [6200/6250] eta: 0:00:06 lr: 0.000114 grad: 0.0644 (0.0661) loss: 0.8395 (0.8353) time: 0.1583 data: 0.0748 max mem: 9390 +Train: [22] [6249/6250] eta: 0:00:00 lr: 0.000114 grad: 0.0689 (0.0661) loss: 0.8281 (0.8353) time: 0.1657 data: 0.0864 max mem: 9390 +Train: [22] Total time: 0:14:20 (0.1377 s / it) +Averaged stats: lr: 0.000114 grad: 0.0689 (0.0661) loss: 0.8281 (0.8353) +Eval (hcp-train-subset): [22] [ 0/62] eta: 0:04:31 loss: 0.8515 (0.8515) time: 4.3866 data: 4.3231 max mem: 9390 +Eval (hcp-train-subset): [22] [61/62] eta: 0:00:00 loss: 0.8434 (0.8454) time: 0.1124 data: 0.0869 max mem: 9390 +Eval (hcp-train-subset): [22] Total time: 0:00:12 (0.2032 s / it) +Averaged stats (hcp-train-subset): loss: 0.8434 (0.8454) +Eval (hcp-val): [22] [ 0/62] eta: 0:03:52 loss: 0.8401 (0.8401) time: 3.7500 data: 3.7212 max mem: 9390 +Eval (hcp-val): [22] [61/62] eta: 0:00:00 loss: 0.8396 (0.8411) time: 0.0977 data: 0.0715 max mem: 9390 +Eval (hcp-val): [22] Total time: 0:00:11 (0.1913 s / it) +Averaged stats (hcp-val): loss: 0.8396 (0.8411) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +Train: [23] [ 0/6250] eta: 7:59:50 lr: 0.000114 grad: 0.0806 (0.0806) loss: 0.8662 (0.8662) time: 4.6065 data: 4.4312 max mem: 9390 +Train: [23] [ 100/6250] eta: 0:18:31 lr: 0.000114 grad: 0.0661 (0.0690) loss: 0.8406 (0.8428) time: 0.1441 data: 0.0632 max mem: 9390 +Train: [23] [ 200/6250] eta: 0:15:41 lr: 0.000114 grad: 0.0634 (0.0687) loss: 0.8384 (0.8388) time: 0.1348 data: 0.0571 max mem: 9390 +Train: [23] [ 300/6250] eta: 0:14:41 lr: 0.000114 grad: 0.0658 (0.0684) loss: 0.8361 (0.8383) time: 0.1497 data: 0.0707 max mem: 9390 +Train: [23] [ 400/6250] eta: 0:13:45 lr: 0.000114 grad: 0.0665 (0.0675) loss: 0.8405 (0.8381) time: 0.1245 data: 0.0449 max mem: 9390 +Train: [23] [ 500/6250] eta: 0:13:14 lr: 0.000114 grad: 0.0598 (0.0667) loss: 0.8398 (0.8376) time: 0.1378 data: 0.0553 max mem: 9390 +Train: [23] [ 600/6250] eta: 0:12:44 lr: 0.000114 grad: 0.0696 (0.0669) loss: 0.8363 (0.8372) time: 0.1236 data: 0.0283 max mem: 9390 +Train: [23] [ 700/6250] eta: 0:12:19 lr: 0.000114 grad: 0.0640 (0.0671) loss: 0.8326 (0.8367) time: 0.1163 data: 0.0325 max mem: 9390 +Train: [23] [ 800/6250] eta: 0:12:27 lr: 0.000114 grad: 0.0646 (0.0669) loss: 0.8322 (0.8361) time: 0.1743 data: 0.0920 max mem: 9390 +Train: [23] [ 900/6250] eta: 0:12:44 lr: 0.000114 grad: 0.0617 (0.0667) loss: 0.8314 (0.8359) time: 0.1682 data: 0.0540 max mem: 9390 +Train: [23] [1000/6250] eta: 0:12:40 lr: 0.000114 grad: 0.0627 (0.0667) loss: 0.8361 (0.8356) time: 0.1965 data: 0.1158 max mem: 9390 +Train: [23] [1100/6250] eta: 0:12:25 lr: 0.000114 grad: 0.0631 (0.0663) loss: 0.8391 (0.8356) time: 0.1312 data: 0.0554 max mem: 9390 +Train: [23] [1200/6250] eta: 0:12:16 lr: 0.000114 grad: 0.0660 (0.0662) loss: 0.8337 (0.8355) time: 0.1504 data: 0.0660 max mem: 9390 +Train: [23] [1300/6250] eta: 0:12:02 lr: 0.000114 grad: 0.0622 (0.0663) loss: 0.8314 (0.8352) time: 0.1549 data: 0.0736 max mem: 9390 +Train: [23] [1400/6250] eta: 0:11:47 lr: 0.000114 grad: 0.0655 (0.0663) loss: 0.8336 (0.8353) time: 0.1434 data: 0.0655 max mem: 9390 +Train: [23] [1500/6250] eta: 0:11:30 lr: 0.000114 grad: 0.0673 (0.0664) loss: 0.8330 (0.8352) time: 0.1188 data: 0.0382 max mem: 9390 +Train: [23] [1600/6250] eta: 0:11:13 lr: 0.000114 grad: 0.0624 (0.0663) loss: 0.8358 (0.8353) time: 0.1276 data: 0.0515 max mem: 9390 +Train: [23] [1700/6250] eta: 0:10:58 lr: 0.000114 grad: 0.0611 (0.0663) loss: 0.8382 (0.8354) time: 0.1520 data: 0.0763 max mem: 9390 +Train: [23] [1800/6250] eta: 0:10:44 lr: 0.000114 grad: 0.0621 (0.0661) loss: 0.8362 (0.8355) time: 0.1460 data: 0.0697 max mem: 9390 +Train: [23] [1900/6250] eta: 0:10:29 lr: 0.000114 grad: 0.0599 (0.0661) loss: 0.8357 (0.8356) time: 0.1313 data: 0.0439 max mem: 9390 +Train: [23] [2000/6250] eta: 0:10:15 lr: 0.000114 grad: 0.0664 (0.0661) loss: 0.8341 (0.8356) time: 0.1497 data: 0.0710 max mem: 9390 +Train: [23] [2100/6250] eta: 0:10:00 lr: 0.000114 grad: 0.0647 (0.0660) loss: 0.8323 (0.8357) time: 0.1427 data: 0.0616 max mem: 9390 +Train: [23] [2200/6250] eta: 0:09:45 lr: 0.000114 grad: 0.0675 (0.0660) loss: 0.8351 (0.8358) time: 0.1460 data: 0.0625 max mem: 9390 +Train: [23] [2300/6250] eta: 0:09:29 lr: 0.000114 grad: 0.0671 (0.0660) loss: 0.8358 (0.8357) time: 0.1420 data: 0.0606 max mem: 9390 +Train: [23] [2400/6250] eta: 0:09:14 lr: 0.000114 grad: 0.0651 (0.0661) loss: 0.8338 (0.8357) time: 0.1123 data: 0.0342 max mem: 9390 +Train: [23] [2500/6250] eta: 0:08:59 lr: 0.000114 grad: 0.0694 (0.0662) loss: 0.8318 (0.8356) time: 0.1272 data: 0.0515 max mem: 9390 +Train: [23] [2600/6250] eta: 0:08:44 lr: 0.000114 grad: 0.0630 (0.0664) loss: 0.8292 (0.8355) time: 0.1436 data: 0.0664 max mem: 9390 +Train: [23] [2700/6250] eta: 0:08:29 lr: 0.000114 grad: 0.0626 (0.0664) loss: 0.8346 (0.8354) time: 0.1458 data: 0.0634 max mem: 9390 +Train: [23] [2800/6250] eta: 0:08:14 lr: 0.000114 grad: 0.0633 (0.0665) loss: 0.8283 (0.8352) time: 0.1098 data: 0.0310 max mem: 9390 +Train: [23] [2900/6250] eta: 0:07:59 lr: 0.000114 grad: 0.0656 (0.0665) loss: 0.8326 (0.8350) time: 0.1386 data: 0.0555 max mem: 9390 +Train: [23] [3000/6250] eta: 0:07:44 lr: 0.000114 grad: 0.0607 (0.0665) loss: 0.8374 (0.8349) time: 0.1385 data: 0.0598 max mem: 9390 +Train: [23] [3100/6250] eta: 0:07:29 lr: 0.000114 grad: 0.0712 (0.0666) loss: 0.8294 (0.8348) time: 0.1267 data: 0.0512 max mem: 9390 +Train: [23] [3200/6250] eta: 0:07:14 lr: 0.000114 grad: 0.0614 (0.0667) loss: 0.8326 (0.8347) time: 0.1273 data: 0.0480 max mem: 9390 +Train: [23] [3300/6250] eta: 0:06:59 lr: 0.000114 grad: 0.0699 (0.0669) loss: 0.8318 (0.8347) time: 0.1481 data: 0.0744 max mem: 9390 +Train: [23] [3400/6250] eta: 0:06:45 lr: 0.000114 grad: 0.0698 (0.0672) loss: 0.8289 (0.8346) time: 0.1293 data: 0.0500 max mem: 9390 +Train: [23] [3500/6250] eta: 0:06:30 lr: 0.000114 grad: 0.0660 (0.0673) loss: 0.8337 (0.8345) time: 0.1465 data: 0.0718 max mem: 9390 +Train: [23] [3600/6250] eta: 0:06:15 lr: 0.000114 grad: 0.0667 (0.0673) loss: 0.8359 (0.8345) time: 0.1140 data: 0.0365 max mem: 9390 +Train: [23] [3700/6250] eta: 0:06:01 lr: 0.000114 grad: 0.0658 (0.0673) loss: 0.8329 (0.8344) time: 0.1449 data: 0.0688 max mem: 9390 +Train: [23] [3800/6250] eta: 0:05:46 lr: 0.000114 grad: 0.0652 (0.0674) loss: 0.8337 (0.8344) time: 0.1363 data: 0.0624 max mem: 9390 +Train: [23] [3900/6250] eta: 0:05:32 lr: 0.000114 grad: 0.0692 (0.0675) loss: 0.8293 (0.8344) time: 0.1323 data: 0.0557 max mem: 9390 +Train: [23] [4000/6250] eta: 0:05:17 lr: 0.000113 grad: 0.0650 (0.0675) loss: 0.8359 (0.8344) time: 0.1289 data: 0.0562 max mem: 9390 +Train: [23] [4100/6250] eta: 0:05:03 lr: 0.000113 grad: 0.0681 (0.0675) loss: 0.8361 (0.8344) time: 0.1432 data: 0.0744 max mem: 9390 +Train: [23] [4200/6250] eta: 0:04:49 lr: 0.000113 grad: 0.0623 (0.0675) loss: 0.8380 (0.8344) time: 0.1362 data: 0.0565 max mem: 9390 +Train: [23] [4300/6250] eta: 0:04:34 lr: 0.000113 grad: 0.0639 (0.0675) loss: 0.8383 (0.8346) time: 0.1562 data: 0.0806 max mem: 9390 +Train: [23] [4400/6250] eta: 0:04:21 lr: 0.000113 grad: 0.0646 (0.0675) loss: 0.8386 (0.8346) time: 0.1555 data: 0.0657 max mem: 9390 +Train: [23] [4500/6250] eta: 0:04:06 lr: 0.000113 grad: 0.0658 (0.0675) loss: 0.8315 (0.8347) time: 0.1264 data: 0.0497 max mem: 9390 +Train: [23] [4600/6250] eta: 0:03:52 lr: 0.000113 grad: 0.0643 (0.0675) loss: 0.8363 (0.8347) time: 0.1188 data: 0.0399 max mem: 9390 +Train: [23] [4700/6250] eta: 0:03:37 lr: 0.000113 grad: 0.0643 (0.0675) loss: 0.8406 (0.8348) time: 0.1267 data: 0.0490 max mem: 9390 +Train: [23] [4800/6250] eta: 0:03:23 lr: 0.000113 grad: 0.0657 (0.0674) loss: 0.8407 (0.8348) time: 0.1248 data: 0.0359 max mem: 9390 +Train: [23] [4900/6250] eta: 0:03:09 lr: 0.000113 grad: 0.0667 (0.0674) loss: 0.8325 (0.8349) time: 0.1447 data: 0.0668 max mem: 9390 +Train: [23] [5000/6250] eta: 0:02:54 lr: 0.000113 grad: 0.0650 (0.0674) loss: 0.8359 (0.8349) time: 0.1166 data: 0.0298 max mem: 9390 +Train: [23] [5100/6250] eta: 0:02:40 lr: 0.000113 grad: 0.0674 (0.0674) loss: 0.8356 (0.8349) time: 0.1097 data: 0.0342 max mem: 9390 +Train: [23] [5200/6250] eta: 0:02:26 lr: 0.000113 grad: 0.0631 (0.0674) loss: 0.8401 (0.8350) time: 0.1905 data: 0.1148 max mem: 9390 +Train: [23] [5300/6250] eta: 0:02:12 lr: 0.000113 grad: 0.0653 (0.0674) loss: 0.8375 (0.8350) time: 0.1185 data: 0.0349 max mem: 9390 +Train: [23] [5400/6250] eta: 0:01:58 lr: 0.000113 grad: 0.0657 (0.0674) loss: 0.8292 (0.8350) time: 0.1393 data: 0.0521 max mem: 9390 +Train: [23] [5500/6250] eta: 0:01:44 lr: 0.000113 grad: 0.0639 (0.0674) loss: 0.8362 (0.8350) time: 0.1291 data: 0.0459 max mem: 9390 +Train: [23] [5600/6250] eta: 0:01:30 lr: 0.000113 grad: 0.0698 (0.0674) loss: 0.8353 (0.8350) time: 0.1397 data: 0.0568 max mem: 9390 +Train: [23] [5700/6250] eta: 0:01:16 lr: 0.000113 grad: 0.0645 (0.0674) loss: 0.8374 (0.8350) time: 0.1496 data: 0.0741 max mem: 9390 +Train: [23] [5800/6250] eta: 0:01:02 lr: 0.000113 grad: 0.0651 (0.0674) loss: 0.8334 (0.8350) time: 0.1118 data: 0.0304 max mem: 9390 +Train: [23] [5900/6250] eta: 0:00:48 lr: 0.000113 grad: 0.0621 (0.0675) loss: 0.8343 (0.8350) time: 0.1588 data: 0.0833 max mem: 9390 +Train: [23] [6000/6250] eta: 0:00:34 lr: 0.000113 grad: 0.0665 (0.0675) loss: 0.8327 (0.8349) time: 0.1262 data: 0.0495 max mem: 9390 +Train: [23] [6100/6250] eta: 0:00:20 lr: 0.000113 grad: 0.0650 (0.0675) loss: 0.8293 (0.8349) time: 0.1310 data: 0.0512 max mem: 9390 +Train: [23] [6200/6250] eta: 0:00:06 lr: 0.000113 grad: 0.0677 (0.0675) loss: 0.8315 (0.8349) time: 0.1654 data: 0.0791 max mem: 9390 +Train: [23] [6249/6250] eta: 0:00:00 lr: 0.000113 grad: 0.0656 (0.0675) loss: 0.8292 (0.8349) time: 0.1859 data: 0.1090 max mem: 9390 +Train: [23] Total time: 0:14:33 (0.1398 s / it) +Averaged stats: lr: 0.000113 grad: 0.0656 (0.0675) loss: 0.8292 (0.8349) +Eval (hcp-train-subset): [23] [ 0/62] eta: 0:04:47 loss: 0.8572 (0.8572) time: 4.6398 data: 4.6067 max mem: 9390 +Eval (hcp-train-subset): [23] [61/62] eta: 0:00:00 loss: 0.8451 (0.8448) time: 0.1229 data: 0.0984 max mem: 9390 +Eval (hcp-train-subset): [23] Total time: 0:00:12 (0.2014 s / it) +Averaged stats (hcp-train-subset): loss: 0.8451 (0.8448) +Eval (hcp-val): [23] [ 0/62] eta: 0:05:01 loss: 0.8347 (0.8347) time: 4.8654 data: 4.8359 max mem: 9390 +Eval (hcp-val): [23] [61/62] eta: 0:00:00 loss: 0.8397 (0.8403) time: 0.0994 data: 0.0747 max mem: 9390 +Eval (hcp-val): [23] Total time: 0:00:12 (0.1941 s / it) +Averaged stats (hcp-val): loss: 0.8397 (0.8403) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +Train: [24] [ 0/6250] eta: 7:57:50 lr: 0.000113 grad: 0.0781 (0.0781) loss: 0.8616 (0.8616) time: 4.5873 data: 4.4925 max mem: 9390 +Train: [24] [ 100/6250] eta: 0:18:04 lr: 0.000113 grad: 0.0627 (0.0716) loss: 0.8460 (0.8484) time: 0.1274 data: 0.0374 max mem: 9390 +Train: [24] [ 200/6250] eta: 0:15:30 lr: 0.000113 grad: 0.0614 (0.0678) loss: 0.8304 (0.8437) time: 0.1216 data: 0.0450 max mem: 9390 +Train: [24] [ 300/6250] eta: 0:14:26 lr: 0.000113 grad: 0.0626 (0.0668) loss: 0.8314 (0.8408) time: 0.1255 data: 0.0382 max mem: 9390 +Train: [24] [ 400/6250] eta: 0:13:51 lr: 0.000113 grad: 0.0673 (0.0668) loss: 0.8320 (0.8393) time: 0.1416 data: 0.0633 max mem: 9390 +Train: [24] [ 500/6250] eta: 0:13:12 lr: 0.000113 grad: 0.0624 (0.0664) loss: 0.8395 (0.8392) time: 0.1188 data: 0.0278 max mem: 9390 +Train: [24] [ 600/6250] eta: 0:12:45 lr: 0.000113 grad: 0.0663 (0.0663) loss: 0.8416 (0.8387) time: 0.0985 data: 0.0151 max mem: 9390 +Train: [24] [ 700/6250] eta: 0:12:22 lr: 0.000113 grad: 0.0642 (0.0661) loss: 0.8392 (0.8388) time: 0.1368 data: 0.0529 max mem: 9390 +Train: [24] [ 800/6250] eta: 0:12:18 lr: 0.000113 grad: 0.0671 (0.0660) loss: 0.8341 (0.8385) time: 0.1665 data: 0.0903 max mem: 9390 +Train: [24] [ 900/6250] eta: 0:12:21 lr: 0.000113 grad: 0.0625 (0.0660) loss: 0.8336 (0.8382) time: 0.1419 data: 0.0565 max mem: 9390 +Train: [24] [1000/6250] eta: 0:12:31 lr: 0.000113 grad: 0.0636 (0.0661) loss: 0.8387 (0.8378) time: 0.1610 data: 0.0759 max mem: 9390 +Train: [24] [1100/6250] eta: 0:12:17 lr: 0.000113 grad: 0.0654 (0.0664) loss: 0.8324 (0.8374) time: 0.1499 data: 0.0714 max mem: 9390 +Train: [24] [1200/6250] eta: 0:12:05 lr: 0.000113 grad: 0.0680 (0.0666) loss: 0.8305 (0.8369) time: 0.1562 data: 0.0823 max mem: 9390 +Train: [24] [1300/6250] eta: 0:11:52 lr: 0.000113 grad: 0.0675 (0.0666) loss: 0.8321 (0.8367) time: 0.1398 data: 0.0618 max mem: 9390 +Train: [24] [1400/6250] eta: 0:11:36 lr: 0.000113 grad: 0.0642 (0.0666) loss: 0.8298 (0.8363) time: 0.1241 data: 0.0473 max mem: 9390 +Train: [24] [1500/6250] eta: 0:11:22 lr: 0.000113 grad: 0.0662 (0.0669) loss: 0.8308 (0.8359) time: 0.1450 data: 0.0680 max mem: 9390 +Train: [24] [1600/6250] eta: 0:11:07 lr: 0.000113 grad: 0.0693 (0.0669) loss: 0.8287 (0.8357) time: 0.1276 data: 0.0493 max mem: 9390 +Train: [24] [1700/6250] eta: 0:10:51 lr: 0.000113 grad: 0.0683 (0.0671) loss: 0.8292 (0.8355) time: 0.1468 data: 0.0657 max mem: 9390 +Train: [24] [1800/6250] eta: 0:10:38 lr: 0.000113 grad: 0.0648 (0.0671) loss: 0.8345 (0.8351) time: 0.1728 data: 0.0879 max mem: 9390 +Train: [24] [1900/6250] eta: 0:10:22 lr: 0.000113 grad: 0.0662 (0.0673) loss: 0.8292 (0.8349) time: 0.1443 data: 0.0656 max mem: 9390 +Train: [24] [2000/6250] eta: 0:10:09 lr: 0.000113 grad: 0.0662 (0.0677) loss: 0.8245 (0.8345) time: 0.1235 data: 0.0444 max mem: 9390 +Train: [24] [2100/6250] eta: 0:09:53 lr: 0.000113 grad: 0.0683 (0.0678) loss: 0.8281 (0.8342) time: 0.1049 data: 0.0218 max mem: 9390 +Train: [24] [2200/6250] eta: 0:09:37 lr: 0.000113 grad: 0.0700 (0.0679) loss: 0.8336 (0.8340) time: 0.1329 data: 0.0543 max mem: 9390 +Train: [24] [2300/6250] eta: 0:09:27 lr: 0.000113 grad: 0.0646 (0.0679) loss: 0.8296 (0.8338) time: 0.1578 data: 0.0817 max mem: 9390 +Train: [24] [2400/6250] eta: 0:09:11 lr: 0.000113 grad: 0.0694 (0.0681) loss: 0.8261 (0.8336) time: 0.1515 data: 0.0684 max mem: 9390 +Train: [24] [2500/6250] eta: 0:08:57 lr: 0.000113 grad: 0.0694 (0.0682) loss: 0.8267 (0.8333) time: 0.1405 data: 0.0506 max mem: 9390 +Train: [24] [2600/6250] eta: 0:08:42 lr: 0.000113 grad: 0.0699 (0.0682) loss: 0.8198 (0.8332) time: 0.1236 data: 0.0420 max mem: 9390 +Train: [24] [2700/6250] eta: 0:08:27 lr: 0.000113 grad: 0.0707 (0.0683) loss: 0.8255 (0.8330) time: 0.1338 data: 0.0588 max mem: 9390 +Train: [24] [2800/6250] eta: 0:08:11 lr: 0.000113 grad: 0.0691 (0.0684) loss: 0.8315 (0.8329) time: 0.1311 data: 0.0519 max mem: 9390 +Train: [24] [2900/6250] eta: 0:07:56 lr: 0.000112 grad: 0.0682 (0.0685) loss: 0.8305 (0.8328) time: 0.1140 data: 0.0329 max mem: 9390 +Train: [24] [3000/6250] eta: 0:07:40 lr: 0.000112 grad: 0.0641 (0.0686) loss: 0.8369 (0.8328) time: 0.1346 data: 0.0570 max mem: 9390 +Train: [24] [3100/6250] eta: 0:07:26 lr: 0.000112 grad: 0.0655 (0.0686) loss: 0.8351 (0.8327) time: 0.1156 data: 0.0362 max mem: 9390 +Train: [24] [3200/6250] eta: 0:07:11 lr: 0.000112 grad: 0.0671 (0.0687) loss: 0.8284 (0.8326) time: 0.1315 data: 0.0545 max mem: 9390 +Train: [24] [3300/6250] eta: 0:06:56 lr: 0.000112 grad: 0.0663 (0.0686) loss: 0.8352 (0.8327) time: 0.1505 data: 0.0754 max mem: 9390 +Train: [24] [3400/6250] eta: 0:06:42 lr: 0.000112 grad: 0.0688 (0.0687) loss: 0.8304 (0.8326) time: 0.1308 data: 0.0524 max mem: 9390 +Train: [24] [3500/6250] eta: 0:06:27 lr: 0.000112 grad: 0.0723 (0.0690) loss: 0.8338 (0.8325) time: 0.1146 data: 0.0441 max mem: 9390 +Train: [24] [3600/6250] eta: 0:06:13 lr: 0.000112 grad: 0.0686 (0.0691) loss: 0.8348 (0.8325) time: 0.1255 data: 0.0486 max mem: 9390 +Train: [24] [3700/6250] eta: 0:05:58 lr: 0.000112 grad: 0.0695 (0.0692) loss: 0.8253 (0.8325) time: 0.1232 data: 0.0416 max mem: 9390 +Train: [24] [3800/6250] eta: 0:05:44 lr: 0.000112 grad: 0.0699 (0.0693) loss: 0.8349 (0.8324) time: 0.1322 data: 0.0550 max mem: 9390 +Train: [24] [3900/6250] eta: 0:05:29 lr: 0.000112 grad: 0.0648 (0.0692) loss: 0.8322 (0.8324) time: 0.1545 data: 0.0775 max mem: 9390 +Train: [24] [4000/6250] eta: 0:05:15 lr: 0.000112 grad: 0.0651 (0.0692) loss: 0.8320 (0.8324) time: 0.1342 data: 0.0604 max mem: 9390 +Train: [24] [4100/6250] eta: 0:05:01 lr: 0.000112 grad: 0.0684 (0.0692) loss: 0.8273 (0.8323) time: 0.1226 data: 0.0406 max mem: 9390 +Train: [24] [4200/6250] eta: 0:04:46 lr: 0.000112 grad: 0.0687 (0.0691) loss: 0.8318 (0.8323) time: 0.1284 data: 0.0513 max mem: 9390 +Train: [24] [4300/6250] eta: 0:04:32 lr: 0.000112 grad: 0.0662 (0.0691) loss: 0.8308 (0.8323) time: 0.1441 data: 0.0686 max mem: 9390 +Train: [24] [4400/6250] eta: 0:04:18 lr: 0.000112 grad: 0.0621 (0.0691) loss: 0.8336 (0.8322) time: 0.1433 data: 0.0622 max mem: 9390 +Train: [24] [4500/6250] eta: 0:04:04 lr: 0.000112 grad: 0.0693 (0.0691) loss: 0.8288 (0.8322) time: 0.1350 data: 0.0524 max mem: 9390 +Train: [24] [4600/6250] eta: 0:03:49 lr: 0.000112 grad: 0.0633 (0.0691) loss: 0.8340 (0.8322) time: 0.1454 data: 0.0668 max mem: 9390 +Train: [24] [4700/6250] eta: 0:03:35 lr: 0.000112 grad: 0.0685 (0.0692) loss: 0.8351 (0.8321) time: 0.1377 data: 0.0585 max mem: 9390 +Train: [24] [4800/6250] eta: 0:03:21 lr: 0.000112 grad: 0.0637 (0.0691) loss: 0.8293 (0.8321) time: 0.1369 data: 0.0491 max mem: 9390 +Train: [24] [4900/6250] eta: 0:03:07 lr: 0.000112 grad: 0.0698 (0.0692) loss: 0.8321 (0.8321) time: 0.1376 data: 0.0616 max mem: 9390 +Train: [24] [5000/6250] eta: 0:02:53 lr: 0.000112 grad: 0.0716 (0.0692) loss: 0.8267 (0.8321) time: 0.1309 data: 0.0559 max mem: 9390 +Train: [24] [5100/6250] eta: 0:02:39 lr: 0.000112 grad: 0.0669 (0.0692) loss: 0.8301 (0.8321) time: 0.1572 data: 0.0730 max mem: 9390 +Train: [24] [5200/6250] eta: 0:02:25 lr: 0.000112 grad: 0.0723 (0.0692) loss: 0.8282 (0.8320) time: 0.1253 data: 0.0474 max mem: 9390 +Train: [24] [5300/6250] eta: 0:02:11 lr: 0.000112 grad: 0.0674 (0.0692) loss: 0.8307 (0.8320) time: 0.1418 data: 0.0563 max mem: 9390 +Train: [24] [5400/6250] eta: 0:01:57 lr: 0.000112 grad: 0.0718 (0.0692) loss: 0.8264 (0.8320) time: 0.1441 data: 0.0657 max mem: 9390 +Train: [24] [5500/6250] eta: 0:01:44 lr: 0.000112 grad: 0.0736 (0.0692) loss: 0.8272 (0.8320) time: 0.1453 data: 0.0724 max mem: 9390 +Train: [24] [5600/6250] eta: 0:01:30 lr: 0.000112 grad: 0.0677 (0.0692) loss: 0.8348 (0.8319) time: 0.1505 data: 0.0701 max mem: 9390 +Train: [24] [5700/6250] eta: 0:01:16 lr: 0.000112 grad: 0.0699 (0.0692) loss: 0.8324 (0.8319) time: 0.1302 data: 0.0507 max mem: 9390 +Train: [24] [5800/6250] eta: 0:01:02 lr: 0.000112 grad: 0.0732 (0.0692) loss: 0.8213 (0.8319) time: 0.1050 data: 0.0325 max mem: 9390 +Train: [24] [5900/6250] eta: 0:00:48 lr: 0.000112 grad: 0.0638 (0.0693) loss: 0.8323 (0.8319) time: 0.1291 data: 0.0502 max mem: 9390 +Train: [24] [6000/6250] eta: 0:00:34 lr: 0.000112 grad: 0.0657 (0.0693) loss: 0.8302 (0.8319) time: 0.1287 data: 0.0484 max mem: 9390 +Train: [24] [6100/6250] eta: 0:00:20 lr: 0.000112 grad: 0.0680 (0.0692) loss: 0.8305 (0.8318) time: 0.1330 data: 0.0516 max mem: 9390 +Train: [24] [6200/6250] eta: 0:00:06 lr: 0.000112 grad: 0.0670 (0.0692) loss: 0.8287 (0.8318) time: 0.1802 data: 0.1023 max mem: 9390 +Train: [24] [6249/6250] eta: 0:00:00 lr: 0.000112 grad: 0.0679 (0.0693) loss: 0.8280 (0.8318) time: 0.1896 data: 0.1155 max mem: 9390 +Train: [24] Total time: 0:14:30 (0.1393 s / it) +Averaged stats: lr: 0.000112 grad: 0.0679 (0.0693) loss: 0.8280 (0.8318) +Eval (hcp-train-subset): [24] [ 0/62] eta: 0:05:24 loss: 0.8531 (0.8531) time: 5.2336 data: 5.2011 max mem: 9390 +Eval (hcp-train-subset): [24] [61/62] eta: 0:00:00 loss: 0.8418 (0.8439) time: 0.1107 data: 0.0844 max mem: 9390 +Eval (hcp-train-subset): [24] Total time: 0:00:12 (0.2040 s / it) +Averaged stats (hcp-train-subset): loss: 0.8418 (0.8439) +Making plots (hcp-train-subset): example=43 +Eval (hcp-val): [24] [ 0/62] eta: 0:04:33 loss: 0.8383 (0.8383) time: 4.4035 data: 4.3750 max mem: 9390 +Eval (hcp-val): [24] [61/62] eta: 0:00:00 loss: 0.8391 (0.8406) time: 0.1237 data: 0.0991 max mem: 9390 +Eval (hcp-val): [24] Total time: 0:00:11 (0.1809 s / it) +Averaged stats (hcp-val): loss: 0.8391 (0.8406) +Making plots (hcp-val): example=24 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +Train: [25] [ 0/6250] eta: 7:10:21 lr: 0.000112 grad: 0.2801 (0.2801) loss: 0.8130 (0.8130) time: 4.1315 data: 3.8839 max mem: 9390 +Train: [25] [ 100/6250] eta: 0:18:23 lr: 0.000112 grad: 0.0767 (0.0785) loss: 0.8396 (0.8409) time: 0.1353 data: 0.0567 max mem: 9390 +Train: [25] [ 200/6250] eta: 0:16:02 lr: 0.000112 grad: 0.0677 (0.0754) loss: 0.8348 (0.8357) time: 0.1413 data: 0.0639 max mem: 9390 +Train: [25] [ 300/6250] eta: 0:15:04 lr: 0.000112 grad: 0.0625 (0.0717) loss: 0.8337 (0.8342) time: 0.1427 data: 0.0633 max mem: 9390 +Train: [25] [ 400/6250] eta: 0:14:17 lr: 0.000112 grad: 0.0664 (0.0707) loss: 0.8307 (0.8340) time: 0.1392 data: 0.0586 max mem: 9390 +Train: [25] [ 500/6250] eta: 0:13:44 lr: 0.000112 grad: 0.0659 (0.0700) loss: 0.8295 (0.8333) time: 0.1205 data: 0.0360 max mem: 9390 +Train: [25] [ 600/6250] eta: 0:13:14 lr: 0.000112 grad: 0.0658 (0.0694) loss: 0.8299 (0.8327) time: 0.1190 data: 0.0372 max mem: 9390 +Train: [25] [ 700/6250] eta: 0:12:47 lr: 0.000112 grad: 0.0623 (0.0694) loss: 0.8390 (0.8325) time: 0.1111 data: 0.0284 max mem: 9390 +Train: [25] [ 800/6250] eta: 0:12:37 lr: 0.000112 grad: 0.0608 (0.0686) loss: 0.8368 (0.8329) time: 0.1474 data: 0.0685 max mem: 9390 +Train: [25] [ 900/6250] eta: 0:12:46 lr: 0.000112 grad: 0.0607 (0.0680) loss: 0.8330 (0.8330) time: 0.2055 data: 0.1199 max mem: 9390 +Train: [25] [1000/6250] eta: 0:13:17 lr: 0.000112 grad: 0.0632 (0.0675) loss: 0.8322 (0.8332) time: 0.4592 data: 0.3837 max mem: 9390 +Train: [25] [1100/6250] eta: 0:12:52 lr: 0.000112 grad: 0.0620 (0.0671) loss: 0.8327 (0.8334) time: 0.1684 data: 0.0853 max mem: 9390 +Train: [25] [1200/6250] eta: 0:12:41 lr: 0.000112 grad: 0.0657 (0.0667) loss: 0.8328 (0.8334) time: 0.1574 data: 0.0817 max mem: 9390 +Train: [25] [1300/6250] eta: 0:12:23 lr: 0.000112 grad: 0.0593 (0.0666) loss: 0.8356 (0.8335) time: 0.1505 data: 0.0717 max mem: 9390 +Train: [25] [1400/6250] eta: 0:12:07 lr: 0.000112 grad: 0.0607 (0.0665) loss: 0.8311 (0.8334) time: 0.1388 data: 0.0557 max mem: 9390 +Train: [25] [1500/6250] eta: 0:11:51 lr: 0.000112 grad: 0.0630 (0.0664) loss: 0.8343 (0.8334) time: 0.1436 data: 0.0638 max mem: 9390 +Train: [25] [1600/6250] eta: 0:11:35 lr: 0.000111 grad: 0.0646 (0.0664) loss: 0.8377 (0.8335) time: 0.1524 data: 0.0739 max mem: 9390 +Train: [25] [1700/6250] eta: 0:11:16 lr: 0.000111 grad: 0.0655 (0.0664) loss: 0.8341 (0.8335) time: 0.1519 data: 0.0637 max mem: 9390 +Train: [25] [1800/6250] eta: 0:11:01 lr: 0.000111 grad: 0.0648 (0.0665) loss: 0.8310 (0.8334) time: 0.1488 data: 0.0687 max mem: 9390 +Train: [25] [1900/6250] eta: 0:10:47 lr: 0.000111 grad: 0.0646 (0.0665) loss: 0.8335 (0.8334) time: 0.1539 data: 0.0739 max mem: 9390 +Train: [25] [2000/6250] eta: 0:10:31 lr: 0.000111 grad: 0.0605 (0.0664) loss: 0.8333 (0.8335) time: 0.1442 data: 0.0696 max mem: 9390 +Train: [25] [2100/6250] eta: 0:10:15 lr: 0.000111 grad: 0.0623 (0.0665) loss: 0.8392 (0.8335) time: 0.1377 data: 0.0576 max mem: 9390 +Train: [25] [2200/6250] eta: 0:09:59 lr: 0.000111 grad: 0.0631 (0.0666) loss: 0.8387 (0.8336) time: 0.1418 data: 0.0614 max mem: 9390 +Train: [25] [2300/6250] eta: 0:09:45 lr: 0.000111 grad: 0.0640 (0.0666) loss: 0.8395 (0.8337) time: 0.1319 data: 0.0484 max mem: 9390 +Train: [25] [2400/6250] eta: 0:09:30 lr: 0.000111 grad: 0.0651 (0.0666) loss: 0.8346 (0.8337) time: 0.1518 data: 0.0731 max mem: 9390 +Train: [25] [2500/6250] eta: 0:09:15 lr: 0.000111 grad: 0.0642 (0.0666) loss: 0.8326 (0.8338) time: 0.1424 data: 0.0682 max mem: 9390 +Train: [25] [2600/6250] eta: 0:09:00 lr: 0.000111 grad: 0.0613 (0.0667) loss: 0.8326 (0.8338) time: 0.1505 data: 0.0669 max mem: 9390 +Train: [25] [2700/6250] eta: 0:08:45 lr: 0.000111 grad: 0.0689 (0.0668) loss: 0.8347 (0.8338) time: 0.1780 data: 0.1039 max mem: 9390 +Train: [25] [2800/6250] eta: 0:08:28 lr: 0.000111 grad: 0.0636 (0.0669) loss: 0.8360 (0.8338) time: 0.1292 data: 0.0526 max mem: 9390 +Train: [25] [2900/6250] eta: 0:08:12 lr: 0.000111 grad: 0.0672 (0.0669) loss: 0.8288 (0.8338) time: 0.1514 data: 0.0701 max mem: 9390 +Train: [25] [3000/6250] eta: 0:07:57 lr: 0.000111 grad: 0.0642 (0.0669) loss: 0.8322 (0.8338) time: 0.1158 data: 0.0361 max mem: 9390 +Train: [25] [3100/6250] eta: 0:07:41 lr: 0.000111 grad: 0.0683 (0.0670) loss: 0.8317 (0.8338) time: 0.1431 data: 0.0645 max mem: 9390 +Train: [25] [3200/6250] eta: 0:07:25 lr: 0.000111 grad: 0.0717 (0.0671) loss: 0.8237 (0.8337) time: 0.1385 data: 0.0582 max mem: 9390 +Train: [25] [3300/6250] eta: 0:07:10 lr: 0.000111 grad: 0.0655 (0.0671) loss: 0.8349 (0.8337) time: 0.1471 data: 0.0645 max mem: 9390 +Train: [25] [3400/6250] eta: 0:06:54 lr: 0.000111 grad: 0.0650 (0.0672) loss: 0.8340 (0.8336) time: 0.1361 data: 0.0585 max mem: 9390 +Train: [25] [3500/6250] eta: 0:06:39 lr: 0.000111 grad: 0.0692 (0.0671) loss: 0.8382 (0.8337) time: 0.1212 data: 0.0407 max mem: 9390 +Train: [25] [3600/6250] eta: 0:06:24 lr: 0.000111 grad: 0.0648 (0.0671) loss: 0.8296 (0.8337) time: 0.1317 data: 0.0512 max mem: 9390 +Train: [25] [3700/6250] eta: 0:06:09 lr: 0.000111 grad: 0.0667 (0.0671) loss: 0.8334 (0.8337) time: 0.1336 data: 0.0557 max mem: 9390 +Train: [25] [3800/6250] eta: 0:05:54 lr: 0.000111 grad: 0.0696 (0.0672) loss: 0.8332 (0.8337) time: 0.1286 data: 0.0509 max mem: 9390 +Train: [25] [3900/6250] eta: 0:05:39 lr: 0.000111 grad: 0.0632 (0.0672) loss: 0.8368 (0.8336) time: 0.1453 data: 0.0676 max mem: 9390 +Train: [25] [4000/6250] eta: 0:05:24 lr: 0.000111 grad: 0.0637 (0.0672) loss: 0.8291 (0.8337) time: 0.1408 data: 0.0640 max mem: 9390 +Train: [25] [4100/6250] eta: 0:05:10 lr: 0.000111 grad: 0.0673 (0.0672) loss: 0.8344 (0.8337) time: 0.1237 data: 0.0449 max mem: 9390 +Train: [25] [4200/6250] eta: 0:04:55 lr: 0.000111 grad: 0.0654 (0.0673) loss: 0.8324 (0.8336) time: 0.1515 data: 0.0778 max mem: 9390 +Train: [25] [4300/6250] eta: 0:04:40 lr: 0.000111 grad: 0.0647 (0.0673) loss: 0.8370 (0.8337) time: 0.1390 data: 0.0612 max mem: 9390 +Train: [25] [4400/6250] eta: 0:04:26 lr: 0.000111 grad: 0.0628 (0.0673) loss: 0.8386 (0.8337) time: 0.1343 data: 0.0598 max mem: 9390 +Train: [25] [4500/6250] eta: 0:04:11 lr: 0.000111 grad: 0.0695 (0.0674) loss: 0.8353 (0.8337) time: 0.1262 data: 0.0479 max mem: 9390 +Train: [25] [4600/6250] eta: 0:03:56 lr: 0.000111 grad: 0.0676 (0.0675) loss: 0.8355 (0.8337) time: 0.1307 data: 0.0426 max mem: 9390 +Train: [25] [4700/6250] eta: 0:03:42 lr: 0.000111 grad: 0.0665 (0.0675) loss: 0.8303 (0.8336) time: 0.1600 data: 0.0786 max mem: 9390 +Train: [25] [4800/6250] eta: 0:03:27 lr: 0.000111 grad: 0.0679 (0.0675) loss: 0.8319 (0.8336) time: 0.1307 data: 0.0544 max mem: 9390 +Train: [25] [4900/6250] eta: 0:03:13 lr: 0.000111 grad: 0.0712 (0.0676) loss: 0.8324 (0.8336) time: 0.1359 data: 0.0602 max mem: 9390 +Train: [25] [5000/6250] eta: 0:02:58 lr: 0.000111 grad: 0.0676 (0.0676) loss: 0.8331 (0.8336) time: 0.1646 data: 0.0906 max mem: 9390 +Train: [25] [5100/6250] eta: 0:02:44 lr: 0.000111 grad: 0.0665 (0.0676) loss: 0.8362 (0.8336) time: 0.1472 data: 0.0737 max mem: 9390 +Train: [25] [5200/6250] eta: 0:02:29 lr: 0.000111 grad: 0.0619 (0.0676) loss: 0.8341 (0.8336) time: 0.1321 data: 0.0582 max mem: 9390 +Train: [25] [5300/6250] eta: 0:02:15 lr: 0.000111 grad: 0.0663 (0.0676) loss: 0.8406 (0.8337) time: 0.1507 data: 0.0717 max mem: 9390 +Train: [25] [5400/6250] eta: 0:02:01 lr: 0.000111 grad: 0.0698 (0.0677) loss: 0.8369 (0.8337) time: 0.1386 data: 0.0571 max mem: 9390 +Train: [25] [5500/6250] eta: 0:01:47 lr: 0.000111 grad: 0.0669 (0.0677) loss: 0.8366 (0.8338) time: 0.1734 data: 0.0983 max mem: 9390 +Train: [25] [5600/6250] eta: 0:01:32 lr: 0.000111 grad: 0.0671 (0.0677) loss: 0.8311 (0.8338) time: 0.1264 data: 0.0479 max mem: 9390 +Train: [25] [5700/6250] eta: 0:01:18 lr: 0.000111 grad: 0.0703 (0.0677) loss: 0.8350 (0.8338) time: 0.1416 data: 0.0645 max mem: 9390 +Train: [25] [5800/6250] eta: 0:01:04 lr: 0.000111 grad: 0.0689 (0.0678) loss: 0.8323 (0.8338) time: 0.1303 data: 0.0525 max mem: 9390 +Train: [25] [5900/6250] eta: 0:00:49 lr: 0.000111 grad: 0.0643 (0.0678) loss: 0.8305 (0.8338) time: 0.1443 data: 0.0666 max mem: 9390 +Train: [25] [6000/6250] eta: 0:00:35 lr: 0.000111 grad: 0.0726 (0.0678) loss: 0.8322 (0.8338) time: 0.1712 data: 0.0925 max mem: 9390 +Train: [25] [6100/6250] eta: 0:00:21 lr: 0.000111 grad: 0.0624 (0.0678) loss: 0.8320 (0.8337) time: 0.1758 data: 0.0881 max mem: 9390 +Train: [25] [6200/6250] eta: 0:00:07 lr: 0.000111 grad: 0.0655 (0.0679) loss: 0.8315 (0.8337) time: 0.1529 data: 0.0781 max mem: 9390 +Train: [25] [6249/6250] eta: 0:00:00 lr: 0.000111 grad: 0.0700 (0.0679) loss: 0.8288 (0.8337) time: 0.1418 data: 0.0628 max mem: 9390 +Train: [25] Total time: 0:15:02 (0.1444 s / it) +Averaged stats: lr: 0.000111 grad: 0.0700 (0.0679) loss: 0.8288 (0.8337) +Eval (hcp-train-subset): [25] [ 0/62] eta: 0:03:35 loss: 0.8547 (0.8547) time: 3.4702 data: 3.4017 max mem: 9390 +Eval (hcp-train-subset): [25] [61/62] eta: 0:00:00 loss: 0.8446 (0.8438) time: 0.1089 data: 0.0842 max mem: 9390 +Eval (hcp-train-subset): [25] Total time: 0:00:12 (0.1949 s / it) +Averaged stats (hcp-train-subset): loss: 0.8446 (0.8438) +Eval (hcp-val): [25] [ 0/62] eta: 0:04:09 loss: 0.8372 (0.8372) time: 4.0179 data: 3.9884 max mem: 9390 +Eval (hcp-val): [25] [61/62] eta: 0:00:00 loss: 0.8376 (0.8391) time: 0.1008 data: 0.0760 max mem: 9390 +Eval (hcp-val): [25] Total time: 0:00:11 (0.1839 s / it) +Averaged stats (hcp-val): loss: 0.8376 (0.8391) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +Train: [26] [ 0/6250] eta: 8:13:20 lr: 0.000111 grad: 0.0639 (0.0639) loss: 0.8492 (0.8492) time: 4.7360 data: 4.6372 max mem: 9390 +Train: [26] [ 100/6250] eta: 0:18:27 lr: 0.000111 grad: 0.0683 (0.0754) loss: 0.8438 (0.8470) time: 0.1417 data: 0.0583 max mem: 9390 +Train: [26] [ 200/6250] eta: 0:15:51 lr: 0.000110 grad: 0.0734 (0.0743) loss: 0.8341 (0.8404) time: 0.1343 data: 0.0558 max mem: 9390 +Train: [26] [ 300/6250] eta: 0:14:46 lr: 0.000110 grad: 0.0690 (0.0734) loss: 0.8347 (0.8377) time: 0.1258 data: 0.0397 max mem: 9390 +Train: [26] [ 400/6250] eta: 0:14:05 lr: 0.000110 grad: 0.0656 (0.0734) loss: 0.8381 (0.8360) time: 0.1278 data: 0.0470 max mem: 9390 +Train: [26] [ 500/6250] eta: 0:13:34 lr: 0.000110 grad: 0.0719 (0.0729) loss: 0.8372 (0.8356) time: 0.1441 data: 0.0581 max mem: 9390 +Train: [26] [ 600/6250] eta: 0:13:03 lr: 0.000110 grad: 0.0700 (0.0721) loss: 0.8404 (0.8356) time: 0.1313 data: 0.0542 max mem: 9390 +Train: [26] [ 700/6250] eta: 0:12:47 lr: 0.000110 grad: 0.0641 (0.0714) loss: 0.8431 (0.8357) time: 0.1382 data: 0.0647 max mem: 9390 +Train: [26] [ 800/6250] eta: 0:12:37 lr: 0.000110 grad: 0.0637 (0.0710) loss: 0.8254 (0.8354) time: 0.1230 data: 0.0418 max mem: 9390 +Train: [26] [ 900/6250] eta: 0:12:39 lr: 0.000110 grad: 0.0656 (0.0707) loss: 0.8346 (0.8352) time: 0.1732 data: 0.0942 max mem: 9390 +Train: [26] [1000/6250] eta: 0:12:42 lr: 0.000110 grad: 0.0630 (0.0704) loss: 0.8339 (0.8350) time: 0.1731 data: 0.0918 max mem: 9390 +Train: [26] [1100/6250] eta: 0:12:35 lr: 0.000110 grad: 0.0640 (0.0701) loss: 0.8320 (0.8347) time: 0.1610 data: 0.0833 max mem: 9390 +Train: [26] [1200/6250] eta: 0:12:20 lr: 0.000110 grad: 0.0634 (0.0698) loss: 0.8356 (0.8345) time: 0.1469 data: 0.0675 max mem: 9390 +Train: [26] [1300/6250] eta: 0:12:09 lr: 0.000110 grad: 0.0680 (0.0696) loss: 0.8231 (0.8343) time: 0.1461 data: 0.0632 max mem: 9390 +Train: [26] [1400/6250] eta: 0:11:57 lr: 0.000110 grad: 0.0673 (0.0695) loss: 0.8276 (0.8340) time: 0.1253 data: 0.0439 max mem: 9390 +Train: [26] [1500/6250] eta: 0:11:43 lr: 0.000110 grad: 0.0725 (0.0696) loss: 0.8303 (0.8338) time: 0.1103 data: 0.0338 max mem: 9390 +Train: [26] [1600/6250] eta: 0:11:26 lr: 0.000110 grad: 0.0717 (0.0697) loss: 0.8270 (0.8337) time: 0.1314 data: 0.0577 max mem: 9390 +Train: [26] [1700/6250] eta: 0:11:09 lr: 0.000110 grad: 0.0671 (0.0696) loss: 0.8327 (0.8335) time: 0.1640 data: 0.0837 max mem: 9390 +Train: [26] [1800/6250] eta: 0:10:51 lr: 0.000110 grad: 0.0668 (0.0696) loss: 0.8322 (0.8334) time: 0.1292 data: 0.0511 max mem: 9390 +Train: [26] [1900/6250] eta: 0:10:36 lr: 0.000110 grad: 0.0664 (0.0697) loss: 0.8325 (0.8333) time: 0.1067 data: 0.0268 max mem: 9390 +Train: [26] [2000/6250] eta: 0:10:21 lr: 0.000110 grad: 0.0686 (0.0697) loss: 0.8351 (0.8334) time: 0.1458 data: 0.0737 max mem: 9390 +Train: [26] [2100/6250] eta: 0:10:07 lr: 0.000110 grad: 0.0696 (0.0698) loss: 0.8299 (0.8333) time: 0.1831 data: 0.1010 max mem: 9390 +Train: [26] [2200/6250] eta: 0:09:53 lr: 0.000110 grad: 0.0675 (0.0698) loss: 0.8272 (0.8333) time: 0.1258 data: 0.0426 max mem: 9390 +Train: [26] [2300/6250] eta: 0:09:37 lr: 0.000110 grad: 0.0685 (0.0699) loss: 0.8335 (0.8332) time: 0.1412 data: 0.0545 max mem: 9390 +Train: [26] [2400/6250] eta: 0:09:22 lr: 0.000110 grad: 0.0652 (0.0700) loss: 0.8338 (0.8331) time: 0.1422 data: 0.0641 max mem: 9390 +Train: [26] [2500/6250] eta: 0:09:06 lr: 0.000110 grad: 0.0698 (0.0701) loss: 0.8328 (0.8330) time: 0.1444 data: 0.0632 max mem: 9390 +Train: [26] [2600/6250] eta: 0:08:51 lr: 0.000110 grad: 0.0690 (0.0700) loss: 0.8292 (0.8329) time: 0.1454 data: 0.0621 max mem: 9390 +Train: [26] [2700/6250] eta: 0:08:37 lr: 0.000110 grad: 0.0677 (0.0700) loss: 0.8316 (0.8329) time: 0.1699 data: 0.0920 max mem: 9390 +Train: [26] [2800/6250] eta: 0:08:23 lr: 0.000110 grad: 0.0706 (0.0699) loss: 0.8324 (0.8328) time: 0.0990 data: 0.0245 max mem: 9390 +Train: [26] [2900/6250] eta: 0:08:08 lr: 0.000110 grad: 0.0677 (0.0699) loss: 0.8227 (0.8326) time: 0.1590 data: 0.0803 max mem: 9390 +Train: [26] [3000/6250] eta: 0:07:53 lr: 0.000110 grad: 0.0712 (0.0699) loss: 0.8287 (0.8325) time: 0.1507 data: 0.0707 max mem: 9390 +Train: [26] [3100/6250] eta: 0:07:38 lr: 0.000110 grad: 0.0650 (0.0699) loss: 0.8316 (0.8324) time: 0.1255 data: 0.0404 max mem: 9390 +Train: [26] [3200/6250] eta: 0:07:23 lr: 0.000110 grad: 0.0674 (0.0701) loss: 0.8226 (0.8323) time: 0.1521 data: 0.0726 max mem: 9390 +Train: [26] [3300/6250] eta: 0:07:07 lr: 0.000110 grad: 0.0695 (0.0702) loss: 0.8289 (0.8323) time: 0.1415 data: 0.0649 max mem: 9390 +Train: [26] [3400/6250] eta: 0:06:52 lr: 0.000110 grad: 0.0676 (0.0701) loss: 0.8262 (0.8322) time: 0.1368 data: 0.0624 max mem: 9390 +Train: [26] [3500/6250] eta: 0:06:37 lr: 0.000110 grad: 0.0669 (0.0702) loss: 0.8293 (0.8322) time: 0.1409 data: 0.0618 max mem: 9390 +Train: [26] [3600/6250] eta: 0:06:23 lr: 0.000110 grad: 0.0710 (0.0702) loss: 0.8245 (0.8321) time: 0.1355 data: 0.0545 max mem: 9390 +Train: [26] [3700/6250] eta: 0:06:08 lr: 0.000110 grad: 0.0645 (0.0702) loss: 0.8361 (0.8321) time: 0.1302 data: 0.0579 max mem: 9390 +Train: [26] [3800/6250] eta: 0:05:53 lr: 0.000110 grad: 0.0678 (0.0702) loss: 0.8374 (0.8321) time: 0.1215 data: 0.0440 max mem: 9390 +Train: [26] [3900/6250] eta: 0:05:38 lr: 0.000110 grad: 0.0688 (0.0702) loss: 0.8318 (0.8320) time: 0.1440 data: 0.0581 max mem: 9390 +Train: [26] [4000/6250] eta: 0:05:24 lr: 0.000110 grad: 0.0733 (0.0702) loss: 0.8277 (0.8320) time: 0.1379 data: 0.0623 max mem: 9390 +Train: [26] [4100/6250] eta: 0:05:09 lr: 0.000110 grad: 0.0704 (0.0703) loss: 0.8322 (0.8320) time: 0.1587 data: 0.0809 max mem: 9390 +Train: [26] [4200/6250] eta: 0:04:54 lr: 0.000110 grad: 0.0694 (0.0703) loss: 0.8321 (0.8319) time: 0.1200 data: 0.0371 max mem: 9390 +Train: [26] [4300/6250] eta: 0:04:39 lr: 0.000110 grad: 0.0679 (0.0703) loss: 0.8322 (0.8319) time: 0.1375 data: 0.0569 max mem: 9390 +Train: [26] [4400/6250] eta: 0:04:24 lr: 0.000110 grad: 0.0656 (0.0704) loss: 0.8361 (0.8319) time: 0.1119 data: 0.0334 max mem: 9390 +Train: [26] [4500/6250] eta: 0:04:10 lr: 0.000110 grad: 0.0726 (0.0704) loss: 0.8279 (0.8318) time: 0.1260 data: 0.0484 max mem: 9390 +Train: [26] [4600/6250] eta: 0:03:55 lr: 0.000110 grad: 0.0678 (0.0703) loss: 0.8324 (0.8319) time: 0.1405 data: 0.0593 max mem: 9390 +Train: [26] [4700/6250] eta: 0:03:41 lr: 0.000110 grad: 0.0655 (0.0703) loss: 0.8316 (0.8319) time: 0.1501 data: 0.0689 max mem: 9390 +Train: [26] [4800/6250] eta: 0:03:26 lr: 0.000109 grad: 0.0684 (0.0703) loss: 0.8331 (0.8319) time: 0.1067 data: 0.0271 max mem: 9390 +Train: [26] [4900/6250] eta: 0:03:12 lr: 0.000109 grad: 0.0623 (0.0702) loss: 0.8384 (0.8319) time: 0.1656 data: 0.0887 max mem: 9390 +Train: [26] [5000/6250] eta: 0:02:57 lr: 0.000109 grad: 0.0713 (0.0702) loss: 0.8308 (0.8319) time: 0.1297 data: 0.0513 max mem: 9390 +Train: [26] [5100/6250] eta: 0:02:43 lr: 0.000109 grad: 0.0687 (0.0702) loss: 0.8331 (0.8319) time: 0.1383 data: 0.0593 max mem: 9390 +Train: [26] [5200/6250] eta: 0:02:29 lr: 0.000109 grad: 0.0678 (0.0702) loss: 0.8404 (0.8319) time: 0.1554 data: 0.0736 max mem: 9390 +Train: [26] [5300/6250] eta: 0:02:14 lr: 0.000109 grad: 0.0698 (0.0702) loss: 0.8350 (0.8320) time: 0.1560 data: 0.0794 max mem: 9390 +Train: [26] [5400/6250] eta: 0:02:00 lr: 0.000109 grad: 0.0659 (0.0702) loss: 0.8342 (0.8320) time: 0.1374 data: 0.0609 max mem: 9390 +Train: [26] [5500/6250] eta: 0:01:46 lr: 0.000109 grad: 0.0667 (0.0701) loss: 0.8326 (0.8320) time: 0.1338 data: 0.0557 max mem: 9390 +Train: [26] [5600/6250] eta: 0:01:32 lr: 0.000109 grad: 0.0634 (0.0701) loss: 0.8359 (0.8321) time: 0.1281 data: 0.0547 max mem: 9390 +Train: [26] [5700/6250] eta: 0:01:17 lr: 0.000109 grad: 0.0633 (0.0701) loss: 0.8307 (0.8321) time: 0.1361 data: 0.0512 max mem: 9390 +Train: [26] [5800/6250] eta: 0:01:03 lr: 0.000109 grad: 0.0655 (0.0701) loss: 0.8345 (0.8321) time: 0.1065 data: 0.0237 max mem: 9390 +Train: [26] [5900/6250] eta: 0:00:49 lr: 0.000109 grad: 0.0692 (0.0701) loss: 0.8293 (0.8321) time: 0.1494 data: 0.0737 max mem: 9390 +Train: [26] [6000/6250] eta: 0:00:35 lr: 0.000109 grad: 0.0598 (0.0700) loss: 0.8387 (0.8321) time: 0.1511 data: 0.0703 max mem: 9390 +Train: [26] [6100/6250] eta: 0:00:21 lr: 0.000109 grad: 0.0634 (0.0700) loss: 0.8378 (0.8321) time: 0.1442 data: 0.0655 max mem: 9390 +Train: [26] [6200/6250] eta: 0:00:07 lr: 0.000109 grad: 0.0666 (0.0699) loss: 0.8328 (0.8322) time: 0.1300 data: 0.0564 max mem: 9390 +Train: [26] [6249/6250] eta: 0:00:00 lr: 0.000109 grad: 0.0655 (0.0699) loss: 0.8317 (0.8322) time: 0.1522 data: 0.0696 max mem: 9390 +Train: [26] Total time: 0:14:53 (0.1430 s / it) +Averaged stats: lr: 0.000109 grad: 0.0655 (0.0699) loss: 0.8317 (0.8322) +Eval (hcp-train-subset): [26] [ 0/62] eta: 0:05:23 loss: 0.8552 (0.8552) time: 5.2166 data: 5.1872 max mem: 9390 +Eval (hcp-train-subset): [26] [61/62] eta: 0:00:00 loss: 0.8413 (0.8435) time: 0.1184 data: 0.0936 max mem: 9390 +Eval (hcp-train-subset): [26] Total time: 0:00:11 (0.1922 s / it) +Averaged stats (hcp-train-subset): loss: 0.8413 (0.8435) +Eval (hcp-val): [26] [ 0/62] eta: 0:04:21 loss: 0.8357 (0.8357) time: 4.2190 data: 4.1894 max mem: 9390 +Eval (hcp-val): [26] [61/62] eta: 0:00:00 loss: 0.8381 (0.8386) time: 0.1053 data: 0.0787 max mem: 9390 +Eval (hcp-val): [26] Total time: 0:00:11 (0.1884 s / it) +Averaged stats (hcp-val): loss: 0.8381 (0.8386) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +Train: [27] [ 0/6250] eta: 8:31:18 lr: 0.000109 grad: 0.1117 (0.1117) loss: 0.8230 (0.8230) time: 4.9085 data: 4.8051 max mem: 9390 +Train: [27] [ 100/6250] eta: 0:18:53 lr: 0.000109 grad: 0.0618 (0.0701) loss: 0.8350 (0.8358) time: 0.1389 data: 0.0588 max mem: 9390 +Train: [27] [ 200/6250] eta: 0:16:01 lr: 0.000109 grad: 0.0612 (0.0697) loss: 0.8309 (0.8321) time: 0.1142 data: 0.0315 max mem: 9390 +Train: [27] [ 300/6250] eta: 0:14:48 lr: 0.000109 grad: 0.0598 (0.0687) loss: 0.8290 (0.8319) time: 0.1200 data: 0.0392 max mem: 9390 +Train: [27] [ 400/6250] eta: 0:14:09 lr: 0.000109 grad: 0.0655 (0.0685) loss: 0.8213 (0.8319) time: 0.1279 data: 0.0424 max mem: 9390 +Train: [27] [ 500/6250] eta: 0:13:33 lr: 0.000109 grad: 0.0687 (0.0688) loss: 0.8284 (0.8317) time: 0.1175 data: 0.0377 max mem: 9390 +Train: [27] [ 600/6250] eta: 0:13:11 lr: 0.000109 grad: 0.0652 (0.0685) loss: 0.8246 (0.8314) time: 0.1436 data: 0.0611 max mem: 9390 +Train: [27] [ 700/6250] eta: 0:12:53 lr: 0.000109 grad: 0.0640 (0.0684) loss: 0.8257 (0.8310) time: 0.1337 data: 0.0605 max mem: 9390 +Train: [27] [ 800/6250] eta: 0:12:51 lr: 0.000109 grad: 0.0642 (0.0682) loss: 0.8268 (0.8305) time: 0.1404 data: 0.0623 max mem: 9390 +Train: [27] [ 900/6250] eta: 0:12:46 lr: 0.000109 grad: 0.0672 (0.0682) loss: 0.8260 (0.8300) time: 0.1713 data: 0.0951 max mem: 9390 +Train: [27] [1000/6250] eta: 0:12:48 lr: 0.000109 grad: 0.0670 (0.0686) loss: 0.8304 (0.8298) time: 0.1535 data: 0.0757 max mem: 9390 +Train: [27] [1100/6250] eta: 0:12:40 lr: 0.000109 grad: 0.0664 (0.0685) loss: 0.8272 (0.8296) time: 0.1742 data: 0.0908 max mem: 9390 +Train: [27] [1200/6250] eta: 0:12:32 lr: 0.000109 grad: 0.0692 (0.0684) loss: 0.8236 (0.8293) time: 0.1927 data: 0.1186 max mem: 9390 +Train: [27] [1300/6250] eta: 0:12:19 lr: 0.000109 grad: 0.0654 (0.0684) loss: 0.8207 (0.8289) time: 0.1611 data: 0.0868 max mem: 9390 +Train: [27] [1400/6250] eta: 0:12:03 lr: 0.000109 grad: 0.0683 (0.0684) loss: 0.8285 (0.8287) time: 0.1421 data: 0.0661 max mem: 9390 +Train: [27] [1500/6250] eta: 0:11:47 lr: 0.000109 grad: 0.0652 (0.0683) loss: 0.8288 (0.8286) time: 0.1406 data: 0.0623 max mem: 9390 +Train: [27] [1600/6250] eta: 0:11:30 lr: 0.000109 grad: 0.0668 (0.0684) loss: 0.8247 (0.8286) time: 0.1648 data: 0.0817 max mem: 9390 +Train: [27] [1700/6250] eta: 0:11:11 lr: 0.000109 grad: 0.0636 (0.0684) loss: 0.8282 (0.8285) time: 0.1415 data: 0.0623 max mem: 9390 +Train: [27] [1800/6250] eta: 0:10:53 lr: 0.000109 grad: 0.0705 (0.0687) loss: 0.8265 (0.8285) time: 0.1036 data: 0.0227 max mem: 9390 +Train: [27] [1900/6250] eta: 0:10:38 lr: 0.000109 grad: 0.0681 (0.0687) loss: 0.8275 (0.8285) time: 0.1329 data: 0.0478 max mem: 9390 +Train: [27] [2000/6250] eta: 0:10:23 lr: 0.000109 grad: 0.0690 (0.0686) loss: 0.8280 (0.8286) time: 0.1299 data: 0.0430 max mem: 9390 +Train: [27] [2100/6250] eta: 0:10:07 lr: 0.000109 grad: 0.0692 (0.0686) loss: 0.8269 (0.8285) time: 0.1209 data: 0.0453 max mem: 9390 +Train: [27] [2200/6250] eta: 0:09:52 lr: 0.000109 grad: 0.0697 (0.0687) loss: 0.8280 (0.8286) time: 0.1467 data: 0.0694 max mem: 9390 +Train: [27] [2300/6250] eta: 0:09:37 lr: 0.000109 grad: 0.0684 (0.0687) loss: 0.8292 (0.8286) time: 0.1599 data: 0.0829 max mem: 9390 +Train: [27] [2400/6250] eta: 0:09:22 lr: 0.000109 grad: 0.0678 (0.0688) loss: 0.8296 (0.8287) time: 0.1247 data: 0.0473 max mem: 9390 +Train: [27] [2500/6250] eta: 0:09:06 lr: 0.000109 grad: 0.0675 (0.0688) loss: 0.8285 (0.8287) time: 0.1459 data: 0.0708 max mem: 9390 +Train: [27] [2600/6250] eta: 0:08:50 lr: 0.000109 grad: 0.0674 (0.0689) loss: 0.8318 (0.8286) time: 0.1183 data: 0.0357 max mem: 9390 +Train: [27] [2700/6250] eta: 0:08:35 lr: 0.000109 grad: 0.0630 (0.0689) loss: 0.8277 (0.8287) time: 0.1455 data: 0.0664 max mem: 9390 +Train: [27] [2800/6250] eta: 0:08:19 lr: 0.000109 grad: 0.0709 (0.0689) loss: 0.8343 (0.8289) time: 0.1418 data: 0.0671 max mem: 9390 +Train: [27] [2900/6250] eta: 0:08:04 lr: 0.000109 grad: 0.0669 (0.0689) loss: 0.8338 (0.8290) time: 0.1068 data: 0.0258 max mem: 9390 +Train: [27] [3000/6250] eta: 0:07:49 lr: 0.000109 grad: 0.0688 (0.0689) loss: 0.8318 (0.8292) time: 0.1228 data: 0.0475 max mem: 9390 +Train: [27] [3100/6250] eta: 0:07:33 lr: 0.000108 grad: 0.0688 (0.0689) loss: 0.8340 (0.8294) time: 0.1266 data: 0.0450 max mem: 9390 +Train: [27] [3200/6250] eta: 0:07:18 lr: 0.000108 grad: 0.0673 (0.0689) loss: 0.8392 (0.8295) time: 0.1218 data: 0.0434 max mem: 9390 +Train: [27] [3300/6250] eta: 0:07:03 lr: 0.000108 grad: 0.0635 (0.0689) loss: 0.8338 (0.8295) time: 0.1282 data: 0.0494 max mem: 9390 +Train: [27] [3400/6250] eta: 0:06:48 lr: 0.000108 grad: 0.0680 (0.0689) loss: 0.8216 (0.8295) time: 0.1402 data: 0.0605 max mem: 9390 +Train: [27] [3500/6250] eta: 0:06:33 lr: 0.000108 grad: 0.0680 (0.0690) loss: 0.8304 (0.8295) time: 0.1893 data: 0.1154 max mem: 9390 +Train: [27] [3600/6250] eta: 0:06:18 lr: 0.000108 grad: 0.0686 (0.0690) loss: 0.8299 (0.8295) time: 0.1445 data: 0.0670 max mem: 9390 +Train: [27] [3700/6250] eta: 0:06:03 lr: 0.000108 grad: 0.0642 (0.0689) loss: 0.8320 (0.8296) time: 0.1302 data: 0.0581 max mem: 9390 +Train: [27] [3800/6250] eta: 0:05:48 lr: 0.000108 grad: 0.0710 (0.0689) loss: 0.8276 (0.8295) time: 0.1383 data: 0.0416 max mem: 9390 +Train: [27] [3900/6250] eta: 0:05:34 lr: 0.000108 grad: 0.0709 (0.0690) loss: 0.8348 (0.8295) time: 0.1399 data: 0.0510 max mem: 9390 +Train: [27] [4000/6250] eta: 0:05:19 lr: 0.000108 grad: 0.0709 (0.0691) loss: 0.8312 (0.8295) time: 0.1234 data: 0.0467 max mem: 9390 +Train: [27] [4100/6250] eta: 0:05:04 lr: 0.000108 grad: 0.0716 (0.0692) loss: 0.8286 (0.8295) time: 0.1610 data: 0.0845 max mem: 9390 +Train: [27] [4200/6250] eta: 0:04:49 lr: 0.000108 grad: 0.0717 (0.0693) loss: 0.8286 (0.8295) time: 0.1203 data: 0.0384 max mem: 9390 +Train: [27] [4300/6250] eta: 0:04:35 lr: 0.000108 grad: 0.0678 (0.0694) loss: 0.8315 (0.8296) time: 0.1319 data: 0.0546 max mem: 9390 +Train: [27] [4400/6250] eta: 0:04:20 lr: 0.000108 grad: 0.0704 (0.0694) loss: 0.8241 (0.8296) time: 0.1337 data: 0.0556 max mem: 9390 +Train: [27] [4500/6250] eta: 0:04:06 lr: 0.000108 grad: 0.0705 (0.0695) loss: 0.8314 (0.8296) time: 0.1394 data: 0.0600 max mem: 9390 +Train: [27] [4600/6250] eta: 0:03:52 lr: 0.000108 grad: 0.0660 (0.0695) loss: 0.8334 (0.8296) time: 0.1615 data: 0.0841 max mem: 9390 +Train: [27] [4700/6250] eta: 0:03:38 lr: 0.000108 grad: 0.0718 (0.0695) loss: 0.8337 (0.8296) time: 0.1282 data: 0.0492 max mem: 9390 +Train: [27] [4800/6250] eta: 0:03:24 lr: 0.000108 grad: 0.0674 (0.0695) loss: 0.8308 (0.8297) time: 0.1287 data: 0.0522 max mem: 9390 +Train: [27] [4900/6250] eta: 0:03:09 lr: 0.000108 grad: 0.0639 (0.0695) loss: 0.8338 (0.8297) time: 0.1387 data: 0.0642 max mem: 9390 +Train: [27] [5000/6250] eta: 0:02:55 lr: 0.000108 grad: 0.0635 (0.0695) loss: 0.8353 (0.8298) time: 0.1302 data: 0.0510 max mem: 9390 +Train: [27] [5100/6250] eta: 0:02:41 lr: 0.000108 grad: 0.0703 (0.0696) loss: 0.8302 (0.8298) time: 0.1431 data: 0.0617 max mem: 9390 +Train: [27] [5200/6250] eta: 0:02:27 lr: 0.000108 grad: 0.0670 (0.0696) loss: 0.8345 (0.8298) time: 0.1404 data: 0.0669 max mem: 9390 +Train: [27] [5300/6250] eta: 0:02:13 lr: 0.000108 grad: 0.0752 (0.0696) loss: 0.8201 (0.8298) time: 0.1371 data: 0.0564 max mem: 9390 +Train: [27] [5400/6250] eta: 0:01:59 lr: 0.000108 grad: 0.0673 (0.0697) loss: 0.8325 (0.8298) time: 0.1274 data: 0.0502 max mem: 9390 +Train: [27] [5500/6250] eta: 0:01:45 lr: 0.000108 grad: 0.0715 (0.0698) loss: 0.8217 (0.8297) time: 0.1316 data: 0.0523 max mem: 9390 +Train: [27] [5600/6250] eta: 0:01:31 lr: 0.000108 grad: 0.0741 (0.0699) loss: 0.8307 (0.8297) time: 0.1355 data: 0.0497 max mem: 9390 +Train: [27] [5700/6250] eta: 0:01:17 lr: 0.000108 grad: 0.0667 (0.0699) loss: 0.8211 (0.8297) time: 0.1653 data: 0.0841 max mem: 9390 +Train: [27] [5800/6250] eta: 0:01:03 lr: 0.000108 grad: 0.0686 (0.0699) loss: 0.8254 (0.8296) time: 0.1701 data: 0.0737 max mem: 9390 +Train: [27] [5900/6250] eta: 0:00:49 lr: 0.000108 grad: 0.0727 (0.0700) loss: 0.8239 (0.8296) time: 0.1471 data: 0.0661 max mem: 9390 +Train: [27] [6000/6250] eta: 0:00:35 lr: 0.000108 grad: 0.0721 (0.0701) loss: 0.8352 (0.8296) time: 0.1557 data: 0.0768 max mem: 9390 +Train: [27] [6100/6250] eta: 0:00:21 lr: 0.000108 grad: 0.0697 (0.0701) loss: 0.8308 (0.8296) time: 0.1295 data: 0.0566 max mem: 9390 +Train: [27] [6200/6250] eta: 0:00:07 lr: 0.000108 grad: 0.0710 (0.0701) loss: 0.8361 (0.8296) time: 0.1269 data: 0.0397 max mem: 9390 +Train: [27] [6249/6250] eta: 0:00:00 lr: 0.000108 grad: 0.0722 (0.0701) loss: 0.8346 (0.8296) time: 0.1478 data: 0.0664 max mem: 9390 +Train: [27] Total time: 0:14:50 (0.1425 s / it) +Averaged stats: lr: 0.000108 grad: 0.0722 (0.0701) loss: 0.8346 (0.8296) +Eval (hcp-train-subset): [27] [ 0/62] eta: 0:05:14 loss: 0.8518 (0.8518) time: 5.0747 data: 5.0456 max mem: 9390 +Eval (hcp-train-subset): [27] [61/62] eta: 0:00:00 loss: 0.8427 (0.8429) time: 0.1081 data: 0.0834 max mem: 9390 +Eval (hcp-train-subset): [27] Total time: 0:00:11 (0.1901 s / it) +Averaged stats (hcp-train-subset): loss: 0.8427 (0.8429) +Eval (hcp-val): [27] [ 0/62] eta: 0:04:26 loss: 0.8338 (0.8338) time: 4.2965 data: 4.2628 max mem: 9390 +Eval (hcp-val): [27] [61/62] eta: 0:00:00 loss: 0.8378 (0.8393) time: 0.1123 data: 0.0875 max mem: 9390 +Eval (hcp-val): [27] Total time: 0:00:11 (0.1872 s / it) +Averaged stats (hcp-val): loss: 0.8378 (0.8393) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +Train: [28] [ 0/6250] eta: 7:02:50 lr: 0.000108 grad: 0.0674 (0.0674) loss: 0.8619 (0.8619) time: 4.0592 data: 3.8128 max mem: 9390 +Train: [28] [ 100/6250] eta: 0:18:16 lr: 0.000108 grad: 0.0670 (0.0764) loss: 0.8377 (0.8385) time: 0.1299 data: 0.0446 max mem: 9390 +Train: [28] [ 200/6250] eta: 0:15:56 lr: 0.000108 grad: 0.0706 (0.0767) loss: 0.8323 (0.8366) time: 0.1500 data: 0.0625 max mem: 9390 +Train: [28] [ 300/6250] eta: 0:14:45 lr: 0.000108 grad: 0.0658 (0.0753) loss: 0.8262 (0.8338) time: 0.1455 data: 0.0647 max mem: 9390 +Train: [28] [ 400/6250] eta: 0:14:02 lr: 0.000108 grad: 0.0731 (0.0746) loss: 0.8273 (0.8317) time: 0.1300 data: 0.0373 max mem: 9390 +Train: [28] [ 500/6250] eta: 0:13:33 lr: 0.000108 grad: 0.0680 (0.0740) loss: 0.8337 (0.8314) time: 0.1573 data: 0.0838 max mem: 9390 +Train: [28] [ 600/6250] eta: 0:13:16 lr: 0.000108 grad: 0.0681 (0.0734) loss: 0.8321 (0.8311) time: 0.1108 data: 0.0253 max mem: 9390 +Train: [28] [ 700/6250] eta: 0:13:01 lr: 0.000108 grad: 0.0683 (0.0731) loss: 0.8327 (0.8310) time: 0.1497 data: 0.0683 max mem: 9390 +Train: [28] [ 800/6250] eta: 0:13:00 lr: 0.000108 grad: 0.0670 (0.0726) loss: 0.8290 (0.8311) time: 0.2165 data: 0.1362 max mem: 9390 +Train: [28] [ 900/6250] eta: 0:12:55 lr: 0.000108 grad: 0.0720 (0.0730) loss: 0.8334 (0.8312) time: 0.2434 data: 0.1686 max mem: 9390 +Train: [28] [1000/6250] eta: 0:12:54 lr: 0.000108 grad: 0.0662 (0.0726) loss: 0.8326 (0.8313) time: 0.1412 data: 0.0664 max mem: 9390 +Train: [28] [1100/6250] eta: 0:12:51 lr: 0.000108 grad: 0.0671 (0.0722) loss: 0.8317 (0.8313) time: 0.1381 data: 0.0584 max mem: 9390 +Train: [28] [1200/6250] eta: 0:12:39 lr: 0.000108 grad: 0.0667 (0.0721) loss: 0.8344 (0.8314) time: 0.1646 data: 0.0890 max mem: 9390 +Train: [28] [1300/6250] eta: 0:12:27 lr: 0.000107 grad: 0.0676 (0.0720) loss: 0.8278 (0.8313) time: 0.1658 data: 0.0862 max mem: 9390 +Train: [28] [1400/6250] eta: 0:12:09 lr: 0.000107 grad: 0.0686 (0.0718) loss: 0.8308 (0.8313) time: 0.1381 data: 0.0550 max mem: 9390 +Train: [28] [1500/6250] eta: 0:11:53 lr: 0.000107 grad: 0.0672 (0.0716) loss: 0.8306 (0.8313) time: 0.1461 data: 0.0638 max mem: 9390 +Train: [28] [1600/6250] eta: 0:11:36 lr: 0.000107 grad: 0.0632 (0.0715) loss: 0.8372 (0.8312) time: 0.1521 data: 0.0724 max mem: 9390 +Train: [28] [1700/6250] eta: 0:11:18 lr: 0.000107 grad: 0.0665 (0.0715) loss: 0.8314 (0.8313) time: 0.1474 data: 0.0676 max mem: 9390 +Train: [28] [1800/6250] eta: 0:11:01 lr: 0.000107 grad: 0.0671 (0.0714) loss: 0.8349 (0.8314) time: 0.1344 data: 0.0535 max mem: 9390 +Train: [28] [1900/6250] eta: 0:10:44 lr: 0.000107 grad: 0.0659 (0.0712) loss: 0.8324 (0.8314) time: 0.1363 data: 0.0591 max mem: 9390 +Train: [28] [2000/6250] eta: 0:10:28 lr: 0.000107 grad: 0.0677 (0.0711) loss: 0.8335 (0.8315) time: 0.1486 data: 0.0671 max mem: 9390 +Train: [28] [2100/6250] eta: 0:10:12 lr: 0.000107 grad: 0.0659 (0.0710) loss: 0.8309 (0.8317) time: 0.1506 data: 0.0723 max mem: 9390 +Train: [28] [2200/6250] eta: 0:09:54 lr: 0.000107 grad: 0.0656 (0.0709) loss: 0.8323 (0.8317) time: 0.1378 data: 0.0595 max mem: 9390 +Train: [28] [2300/6250] eta: 0:09:37 lr: 0.000107 grad: 0.0660 (0.0710) loss: 0.8328 (0.8318) time: 0.1380 data: 0.0592 max mem: 9390 +Train: [28] [2400/6250] eta: 0:09:21 lr: 0.000107 grad: 0.0712 (0.0710) loss: 0.8353 (0.8318) time: 0.1587 data: 0.0857 max mem: 9390 +Train: [28] [2500/6250] eta: 0:09:04 lr: 0.000107 grad: 0.0698 (0.0710) loss: 0.8303 (0.8317) time: 0.1358 data: 0.0580 max mem: 9390 +Train: [28] [2600/6250] eta: 0:08:48 lr: 0.000107 grad: 0.0696 (0.0712) loss: 0.8254 (0.8317) time: 0.1368 data: 0.0587 max mem: 9390 +Train: [28] [2700/6250] eta: 0:08:32 lr: 0.000107 grad: 0.0683 (0.0711) loss: 0.8306 (0.8317) time: 0.1377 data: 0.0590 max mem: 9390 +Train: [28] [2800/6250] eta: 0:08:16 lr: 0.000107 grad: 0.0698 (0.0712) loss: 0.8314 (0.8316) time: 0.1441 data: 0.0710 max mem: 9390 +Train: [28] [2900/6250] eta: 0:08:01 lr: 0.000107 grad: 0.0670 (0.0712) loss: 0.8342 (0.8315) time: 0.1239 data: 0.0435 max mem: 9390 +Train: [28] [3000/6250] eta: 0:07:45 lr: 0.000107 grad: 0.0653 (0.0713) loss: 0.8378 (0.8315) time: 0.1150 data: 0.0341 max mem: 9390 +Train: [28] [3100/6250] eta: 0:07:31 lr: 0.000107 grad: 0.0684 (0.0713) loss: 0.8389 (0.8315) time: 0.1549 data: 0.0705 max mem: 9390 +Train: [28] [3200/6250] eta: 0:07:16 lr: 0.000107 grad: 0.0658 (0.0713) loss: 0.8336 (0.8315) time: 0.1306 data: 0.0531 max mem: 9390 +Train: [28] [3300/6250] eta: 0:07:01 lr: 0.000107 grad: 0.0693 (0.0713) loss: 0.8328 (0.8315) time: 0.1456 data: 0.0705 max mem: 9390 +Train: [28] [3400/6250] eta: 0:06:46 lr: 0.000107 grad: 0.0695 (0.0713) loss: 0.8339 (0.8315) time: 0.1477 data: 0.0728 max mem: 9390 +Train: [28] [3500/6250] eta: 0:06:32 lr: 0.000107 grad: 0.0732 (0.0714) loss: 0.8287 (0.8314) time: 0.1593 data: 0.0833 max mem: 9390 +Train: [28] [3600/6250] eta: 0:06:17 lr: 0.000107 grad: 0.0758 (0.0715) loss: 0.8280 (0.8313) time: 0.1374 data: 0.0537 max mem: 9390 +Train: [28] [3700/6250] eta: 0:06:02 lr: 0.000107 grad: 0.0650 (0.0715) loss: 0.8329 (0.8314) time: 0.1352 data: 0.0603 max mem: 9390 +Train: [28] [3800/6250] eta: 0:05:49 lr: 0.000107 grad: 0.0697 (0.0715) loss: 0.8319 (0.8314) time: 0.2086 data: 0.1298 max mem: 9390 +Train: [28] [3900/6250] eta: 0:05:35 lr: 0.000107 grad: 0.0702 (0.0715) loss: 0.8326 (0.8314) time: 0.2646 data: 0.1849 max mem: 9390 +Train: [28] [4000/6250] eta: 0:05:21 lr: 0.000107 grad: 0.0707 (0.0715) loss: 0.8374 (0.8315) time: 0.1676 data: 0.0835 max mem: 9390 +Train: [28] [4100/6250] eta: 0:05:06 lr: 0.000107 grad: 0.0693 (0.0716) loss: 0.8371 (0.8315) time: 0.1454 data: 0.0570 max mem: 9390 +Train: [28] [4200/6250] eta: 0:04:52 lr: 0.000107 grad: 0.0661 (0.0715) loss: 0.8344 (0.8315) time: 0.1499 data: 0.0703 max mem: 9390 +Train: [28] [4300/6250] eta: 0:04:38 lr: 0.000107 grad: 0.0688 (0.0715) loss: 0.8291 (0.8315) time: 0.1545 data: 0.0719 max mem: 9390 +Train: [28] [4400/6250] eta: 0:04:24 lr: 0.000107 grad: 0.0731 (0.0716) loss: 0.8232 (0.8313) time: 0.1762 data: 0.0956 max mem: 9390 +Train: [28] [4500/6250] eta: 0:04:10 lr: 0.000107 grad: 0.0716 (0.0717) loss: 0.8281 (0.8314) time: 0.1477 data: 0.0665 max mem: 9390 +Train: [28] [4600/6250] eta: 0:03:56 lr: 0.000107 grad: 0.0680 (0.0717) loss: 0.8322 (0.8313) time: 0.1400 data: 0.0582 max mem: 9390 +Train: [28] [4700/6250] eta: 0:03:41 lr: 0.000107 grad: 0.0670 (0.0717) loss: 0.8331 (0.8314) time: 0.1451 data: 0.0657 max mem: 9390 +Train: [28] [4800/6250] eta: 0:03:27 lr: 0.000107 grad: 0.0735 (0.0717) loss: 0.8312 (0.8313) time: 0.1483 data: 0.0695 max mem: 9390 +Train: [28] [4900/6250] eta: 0:03:13 lr: 0.000107 grad: 0.0655 (0.0717) loss: 0.8354 (0.8313) time: 0.1339 data: 0.0542 max mem: 9390 +Train: [28] [5000/6250] eta: 0:02:58 lr: 0.000107 grad: 0.0714 (0.0717) loss: 0.8332 (0.8314) time: 0.1351 data: 0.0570 max mem: 9390 +Train: [28] [5100/6250] eta: 0:02:44 lr: 0.000107 grad: 0.0678 (0.0716) loss: 0.8323 (0.8314) time: 0.1570 data: 0.0763 max mem: 9390 +Train: [28] [5200/6250] eta: 0:02:30 lr: 0.000107 grad: 0.0690 (0.0716) loss: 0.8312 (0.8314) time: 0.1444 data: 0.0544 max mem: 9390 +Train: [28] [5300/6250] eta: 0:02:16 lr: 0.000107 grad: 0.0711 (0.0716) loss: 0.8275 (0.8314) time: 0.1320 data: 0.0538 max mem: 9390 +Train: [28] [5400/6250] eta: 0:02:01 lr: 0.000107 grad: 0.0678 (0.0716) loss: 0.8341 (0.8313) time: 0.1321 data: 0.0435 max mem: 9390 +Train: [28] [5500/6250] eta: 0:01:47 lr: 0.000107 grad: 0.0668 (0.0716) loss: 0.8340 (0.8313) time: 0.2065 data: 0.1269 max mem: 9390 +Train: [28] [5600/6250] eta: 0:01:33 lr: 0.000106 grad: 0.0703 (0.0716) loss: 0.8294 (0.8312) time: 0.1432 data: 0.0590 max mem: 9390 +Train: [28] [5700/6250] eta: 0:01:19 lr: 0.000106 grad: 0.0710 (0.0716) loss: 0.8269 (0.8312) time: 0.1519 data: 0.0759 max mem: 9390 +Train: [28] [5800/6250] eta: 0:01:04 lr: 0.000106 grad: 0.0664 (0.0716) loss: 0.8318 (0.8312) time: 0.1283 data: 0.0424 max mem: 9390 +Train: [28] [5900/6250] eta: 0:00:50 lr: 0.000106 grad: 0.0680 (0.0716) loss: 0.8277 (0.8311) time: 0.1492 data: 0.0717 max mem: 9390 +Train: [28] [6000/6250] eta: 0:00:35 lr: 0.000106 grad: 0.0731 (0.0716) loss: 0.8300 (0.8311) time: 0.1328 data: 0.0552 max mem: 9390 +Train: [28] [6100/6250] eta: 0:00:21 lr: 0.000106 grad: 0.0717 (0.0717) loss: 0.8276 (0.8310) time: 0.1286 data: 0.0466 max mem: 9390 +Train: [28] [6200/6250] eta: 0:00:07 lr: 0.000106 grad: 0.0662 (0.0717) loss: 0.8308 (0.8310) time: 0.1093 data: 0.0263 max mem: 9390 +Train: [28] [6249/6250] eta: 0:00:00 lr: 0.000106 grad: 0.0715 (0.0717) loss: 0.8227 (0.8310) time: 0.1151 data: 0.0284 max mem: 9390 +Train: [28] Total time: 0:15:02 (0.1444 s / it) +Averaged stats: lr: 0.000106 grad: 0.0715 (0.0717) loss: 0.8227 (0.8310) +Eval (hcp-train-subset): [28] [ 0/62] eta: 0:04:35 loss: 0.8482 (0.8482) time: 4.4396 data: 4.3998 max mem: 9390 +Eval (hcp-train-subset): [28] [61/62] eta: 0:00:00 loss: 0.8404 (0.8417) time: 0.1197 data: 0.0935 max mem: 9390 +Eval (hcp-train-subset): [28] Total time: 0:00:12 (0.1992 s / it) +Averaged stats (hcp-train-subset): loss: 0.8404 (0.8417) +Eval (hcp-val): [28] [ 0/62] eta: 0:04:24 loss: 0.8375 (0.8375) time: 4.2726 data: 4.2439 max mem: 9390 +Eval (hcp-val): [28] [61/62] eta: 0:00:00 loss: 0.8389 (0.8395) time: 0.1100 data: 0.0854 max mem: 9390 +Eval (hcp-val): [28] Total time: 0:00:11 (0.1870 s / it) +Averaged stats (hcp-val): loss: 0.8389 (0.8395) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +Train: [29] [ 0/6250] eta: 8:59:38 lr: 0.000106 grad: 0.0516 (0.0516) loss: 0.8461 (0.8461) time: 5.1806 data: 5.0596 max mem: 9390 +Train: [29] [ 100/6250] eta: 0:18:45 lr: 0.000106 grad: 0.0767 (0.0845) loss: 0.8397 (0.8370) time: 0.1289 data: 0.0409 max mem: 9390 +Train: [29] [ 200/6250] eta: 0:16:00 lr: 0.000106 grad: 0.0651 (0.0806) loss: 0.8340 (0.8339) time: 0.1255 data: 0.0373 max mem: 9390 +Train: [29] [ 300/6250] eta: 0:14:48 lr: 0.000106 grad: 0.0677 (0.0785) loss: 0.8259 (0.8329) time: 0.1313 data: 0.0411 max mem: 9390 +Train: [29] [ 400/6250] eta: 0:14:05 lr: 0.000106 grad: 0.0666 (0.0761) loss: 0.8275 (0.8322) time: 0.1328 data: 0.0485 max mem: 9390 +Train: [29] [ 500/6250] eta: 0:13:33 lr: 0.000106 grad: 0.0688 (0.0744) loss: 0.8292 (0.8317) time: 0.1162 data: 0.0270 max mem: 9390 +Train: [29] [ 600/6250] eta: 0:13:15 lr: 0.000106 grad: 0.0700 (0.0737) loss: 0.8341 (0.8320) time: 0.1393 data: 0.0566 max mem: 9390 +Train: [29] [ 700/6250] eta: 0:12:56 lr: 0.000106 grad: 0.0670 (0.0733) loss: 0.8284 (0.8318) time: 0.1266 data: 0.0448 max mem: 9390 +Train: [29] [ 800/6250] eta: 0:12:41 lr: 0.000106 grad: 0.0681 (0.0730) loss: 0.8308 (0.8316) time: 0.0938 data: 0.0061 max mem: 9390 +Train: [29] [ 900/6250] eta: 0:12:52 lr: 0.000106 grad: 0.0695 (0.0728) loss: 0.8278 (0.8315) time: 0.1945 data: 0.1199 max mem: 9390 +Train: [29] [1000/6250] eta: 0:12:50 lr: 0.000106 grad: 0.0687 (0.0725) loss: 0.8283 (0.8314) time: 0.1611 data: 0.0812 max mem: 9390 +Train: [29] [1100/6250] eta: 0:12:38 lr: 0.000106 grad: 0.0677 (0.0721) loss: 0.8333 (0.8313) time: 0.1484 data: 0.0674 max mem: 9390 +Train: [29] [1200/6250] eta: 0:12:29 lr: 0.000106 grad: 0.0687 (0.0721) loss: 0.8296 (0.8313) time: 0.1355 data: 0.0580 max mem: 9390 +Train: [29] [1300/6250] eta: 0:12:19 lr: 0.000106 grad: 0.0710 (0.0721) loss: 0.8285 (0.8314) time: 0.1624 data: 0.0848 max mem: 9390 +Train: [29] [1400/6250] eta: 0:12:02 lr: 0.000106 grad: 0.0724 (0.0721) loss: 0.8311 (0.8313) time: 0.1390 data: 0.0576 max mem: 9390 +Train: [29] [1500/6250] eta: 0:11:45 lr: 0.000106 grad: 0.0730 (0.0721) loss: 0.8216 (0.8312) time: 0.1497 data: 0.0701 max mem: 9390 +Train: [29] [1600/6250] eta: 0:11:29 lr: 0.000106 grad: 0.0693 (0.0722) loss: 0.8302 (0.8310) time: 0.1419 data: 0.0664 max mem: 9390 +Train: [29] [1700/6250] eta: 0:11:13 lr: 0.000106 grad: 0.0711 (0.0722) loss: 0.8272 (0.8309) time: 0.1688 data: 0.0903 max mem: 9390 +Train: [29] [1800/6250] eta: 0:10:57 lr: 0.000106 grad: 0.0716 (0.0722) loss: 0.8314 (0.8308) time: 0.1328 data: 0.0485 max mem: 9390 +Train: [29] [1900/6250] eta: 0:10:44 lr: 0.000106 grad: 0.0704 (0.0723) loss: 0.8327 (0.8306) time: 0.1931 data: 0.1053 max mem: 9390 +Train: [29] [2000/6250] eta: 0:10:32 lr: 0.000106 grad: 0.0719 (0.0724) loss: 0.8318 (0.8305) time: 0.1752 data: 0.0943 max mem: 9390 +Train: [29] [2100/6250] eta: 0:10:16 lr: 0.000106 grad: 0.0757 (0.0724) loss: 0.8256 (0.8305) time: 0.1501 data: 0.0728 max mem: 9390 +Train: [29] [2200/6250] eta: 0:10:05 lr: 0.000106 grad: 0.0708 (0.0725) loss: 0.8262 (0.8304) time: 0.2144 data: 0.0838 max mem: 9390 +Train: [29] [2300/6250] eta: 0:09:51 lr: 0.000106 grad: 0.0710 (0.0724) loss: 0.8345 (0.8304) time: 0.1615 data: 0.0834 max mem: 9390 +Train: [29] [2400/6250] eta: 0:09:35 lr: 0.000106 grad: 0.0635 (0.0724) loss: 0.8302 (0.8304) time: 0.1440 data: 0.0564 max mem: 9390 +Train: [29] [2500/6250] eta: 0:09:20 lr: 0.000106 grad: 0.0677 (0.0723) loss: 0.8299 (0.8303) time: 0.1531 data: 0.0723 max mem: 9390 +Train: [29] [2600/6250] eta: 0:09:04 lr: 0.000106 grad: 0.0681 (0.0723) loss: 0.8293 (0.8303) time: 0.1270 data: 0.0503 max mem: 9390 +Train: [29] [2700/6250] eta: 0:08:48 lr: 0.000106 grad: 0.0666 (0.0723) loss: 0.8245 (0.8303) time: 0.1400 data: 0.0603 max mem: 9390 +Train: [29] [2800/6250] eta: 0:08:32 lr: 0.000106 grad: 0.0680 (0.0722) loss: 0.8318 (0.8302) time: 0.1402 data: 0.0522 max mem: 9390 +Train: [29] [2900/6250] eta: 0:08:16 lr: 0.000106 grad: 0.0690 (0.0722) loss: 0.8294 (0.8302) time: 0.1345 data: 0.0595 max mem: 9390 +Train: [29] [3000/6250] eta: 0:08:01 lr: 0.000106 grad: 0.0669 (0.0722) loss: 0.8258 (0.8301) time: 0.1270 data: 0.0487 max mem: 9390 +Train: [29] [3100/6250] eta: 0:07:46 lr: 0.000106 grad: 0.0690 (0.0722) loss: 0.8239 (0.8300) time: 0.1352 data: 0.0581 max mem: 9390 +Train: [29] [3200/6250] eta: 0:07:36 lr: 0.000106 grad: 0.0683 (0.0723) loss: 0.8298 (0.8300) time: 0.3005 data: 0.2127 max mem: 9390 +Train: [29] [3300/6250] eta: 0:07:18 lr: 0.000106 grad: 0.0774 (0.0723) loss: 0.8331 (0.8301) time: 0.1540 data: 0.0740 max mem: 9390 +Train: [29] [3400/6250] eta: 0:07:03 lr: 0.000106 grad: 0.0717 (0.0724) loss: 0.8298 (0.8301) time: 0.1396 data: 0.0651 max mem: 9390 +Train: [29] [3500/6250] eta: 0:06:48 lr: 0.000105 grad: 0.0696 (0.0724) loss: 0.8321 (0.8301) time: 0.1061 data: 0.0192 max mem: 9390 +Train: [29] [3600/6250] eta: 0:06:33 lr: 0.000105 grad: 0.0726 (0.0723) loss: 0.8305 (0.8302) time: 0.1678 data: 0.0861 max mem: 9390 +Train: [29] [3700/6250] eta: 0:06:18 lr: 0.000105 grad: 0.0685 (0.0723) loss: 0.8323 (0.8302) time: 0.1600 data: 0.0711 max mem: 9390 +Train: [29] [3800/6250] eta: 0:06:04 lr: 0.000105 grad: 0.0719 (0.0723) loss: 0.8325 (0.8302) time: 0.1866 data: 0.1007 max mem: 9390 +Train: [29] [3900/6250] eta: 0:05:48 lr: 0.000105 grad: 0.0723 (0.0723) loss: 0.8316 (0.8301) time: 0.1445 data: 0.0645 max mem: 9390 +Train: [29] [4000/6250] eta: 0:05:33 lr: 0.000105 grad: 0.0677 (0.0723) loss: 0.8236 (0.8301) time: 0.1170 data: 0.0430 max mem: 9390 +Train: [29] [4100/6250] eta: 0:05:18 lr: 0.000105 grad: 0.0700 (0.0723) loss: 0.8297 (0.8301) time: 0.1392 data: 0.0577 max mem: 9390 +Train: [29] [4200/6250] eta: 0:05:03 lr: 0.000105 grad: 0.0687 (0.0723) loss: 0.8320 (0.8301) time: 0.1505 data: 0.0747 max mem: 9390 +Train: [29] [4300/6250] eta: 0:04:48 lr: 0.000105 grad: 0.0695 (0.0722) loss: 0.8315 (0.8301) time: 0.1468 data: 0.0679 max mem: 9390 +Train: [29] [4400/6250] eta: 0:04:32 lr: 0.000105 grad: 0.0715 (0.0722) loss: 0.8309 (0.8301) time: 0.1330 data: 0.0556 max mem: 9390 +Train: [29] [4500/6250] eta: 0:04:18 lr: 0.000105 grad: 0.0707 (0.0723) loss: 0.8322 (0.8301) time: 0.1714 data: 0.0922 max mem: 9390 +Train: [29] [4600/6250] eta: 0:04:03 lr: 0.000105 grad: 0.0714 (0.0723) loss: 0.8278 (0.8301) time: 0.1441 data: 0.0638 max mem: 9390 +Train: [29] [4700/6250] eta: 0:03:48 lr: 0.000105 grad: 0.0712 (0.0722) loss: 0.8305 (0.8302) time: 0.1233 data: 0.0442 max mem: 9390 +Train: [29] [4800/6250] eta: 0:03:33 lr: 0.000105 grad: 0.0678 (0.0722) loss: 0.8291 (0.8301) time: 0.1383 data: 0.0523 max mem: 9390 +Train: [29] [4900/6250] eta: 0:03:18 lr: 0.000105 grad: 0.0702 (0.0722) loss: 0.8274 (0.8301) time: 0.1461 data: 0.0642 max mem: 9390 +Train: [29] [5000/6250] eta: 0:03:03 lr: 0.000105 grad: 0.0711 (0.0722) loss: 0.8268 (0.8301) time: 0.1629 data: 0.0853 max mem: 9390 +Train: [29] [5100/6250] eta: 0:02:49 lr: 0.000105 grad: 0.0670 (0.0722) loss: 0.8299 (0.8301) time: 0.1318 data: 0.0575 max mem: 9390 +Train: [29] [5200/6250] eta: 0:02:34 lr: 0.000105 grad: 0.0717 (0.0723) loss: 0.8266 (0.8301) time: 0.1494 data: 0.0677 max mem: 9390 +Train: [29] [5300/6250] eta: 0:02:19 lr: 0.000105 grad: 0.0748 (0.0723) loss: 0.8266 (0.8301) time: 0.1724 data: 0.0885 max mem: 9390 +Train: [29] [5400/6250] eta: 0:02:05 lr: 0.000105 grad: 0.0694 (0.0723) loss: 0.8270 (0.8301) time: 0.2076 data: 0.1317 max mem: 9390 +Train: [29] [5500/6250] eta: 0:01:50 lr: 0.000105 grad: 0.0697 (0.0723) loss: 0.8330 (0.8301) time: 0.1425 data: 0.0630 max mem: 9390 +Train: [29] [5600/6250] eta: 0:01:35 lr: 0.000105 grad: 0.0743 (0.0724) loss: 0.8277 (0.8300) time: 0.1325 data: 0.0532 max mem: 9390 +Train: [29] [5700/6250] eta: 0:01:21 lr: 0.000105 grad: 0.0715 (0.0725) loss: 0.8294 (0.8300) time: 0.1249 data: 0.0497 max mem: 9390 +Train: [29] [5800/6250] eta: 0:01:06 lr: 0.000105 grad: 0.0753 (0.0725) loss: 0.8353 (0.8301) time: 0.1594 data: 0.0829 max mem: 9390 +Train: [29] [5900/6250] eta: 0:00:51 lr: 0.000105 grad: 0.0738 (0.0726) loss: 0.8269 (0.8300) time: 0.1628 data: 0.0854 max mem: 9390 +Train: [29] [6000/6250] eta: 0:00:36 lr: 0.000105 grad: 0.0747 (0.0726) loss: 0.8294 (0.8300) time: 0.1386 data: 0.0597 max mem: 9390 +Train: [29] [6100/6250] eta: 0:00:22 lr: 0.000105 grad: 0.0722 (0.0726) loss: 0.8307 (0.8300) time: 0.1502 data: 0.0671 max mem: 9390 +Train: [29] [6200/6250] eta: 0:00:07 lr: 0.000105 grad: 0.0799 (0.0727) loss: 0.8245 (0.8300) time: 0.1331 data: 0.0522 max mem: 9390 +Train: [29] [6249/6250] eta: 0:00:00 lr: 0.000105 grad: 0.0691 (0.0727) loss: 0.8319 (0.8300) time: 0.1334 data: 0.0562 max mem: 9390 +Train: [29] Total time: 0:15:28 (0.1485 s / it) +Averaged stats: lr: 0.000105 grad: 0.0691 (0.0727) loss: 0.8319 (0.8300) +Eval (hcp-train-subset): [29] [ 0/62] eta: 0:03:06 loss: 0.8522 (0.8522) time: 3.0068 data: 2.9437 max mem: 9390 +Eval (hcp-train-subset): [29] [61/62] eta: 0:00:00 loss: 0.8417 (0.8434) time: 0.1200 data: 0.0949 max mem: 9390 +Eval (hcp-train-subset): [29] Total time: 0:00:12 (0.1976 s / it) +Averaged stats (hcp-train-subset): loss: 0.8417 (0.8434) +Making plots (hcp-train-subset): example=19 +Eval (hcp-val): [29] [ 0/62] eta: 0:03:38 loss: 0.8336 (0.8336) time: 3.5234 data: 3.4619 max mem: 9390 +Eval (hcp-val): [29] [61/62] eta: 0:00:00 loss: 0.8385 (0.8394) time: 0.1064 data: 0.0815 max mem: 9390 +Eval (hcp-val): [29] Total time: 0:00:11 (0.1919 s / it) +Averaged stats (hcp-val): loss: 0.8385 (0.8394) +Making plots (hcp-val): example=27 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +Train: [30] [ 0/6250] eta: 8:48:02 lr: 0.000105 grad: 0.0941 (0.0941) loss: 0.8304 (0.8304) time: 5.0692 data: 4.9627 max mem: 9390 +Train: [30] [ 100/6250] eta: 0:18:29 lr: 0.000105 grad: 0.0697 (0.0729) loss: 0.8378 (0.8409) time: 0.1424 data: 0.0549 max mem: 9390 +Train: [30] [ 200/6250] eta: 0:16:15 lr: 0.000105 grad: 0.0707 (0.0717) loss: 0.8389 (0.8379) time: 0.1527 data: 0.0726 max mem: 9390 +Train: [30] [ 300/6250] eta: 0:15:01 lr: 0.000105 grad: 0.0667 (0.0706) loss: 0.8329 (0.8358) time: 0.1281 data: 0.0406 max mem: 9390 +Train: [30] [ 400/6250] eta: 0:14:12 lr: 0.000105 grad: 0.0687 (0.0699) loss: 0.8341 (0.8351) time: 0.1264 data: 0.0459 max mem: 9390 +Train: [30] [ 500/6250] eta: 0:13:43 lr: 0.000105 grad: 0.0682 (0.0698) loss: 0.8288 (0.8341) time: 0.1331 data: 0.0543 max mem: 9390 +Train: [30] [ 600/6250] eta: 0:13:14 lr: 0.000105 grad: 0.0645 (0.0696) loss: 0.8281 (0.8334) time: 0.1203 data: 0.0448 max mem: 9390 +Train: [30] [ 700/6250] eta: 0:12:56 lr: 0.000105 grad: 0.0662 (0.0696) loss: 0.8275 (0.8327) time: 0.1259 data: 0.0439 max mem: 9390 +Train: [30] [ 800/6250] eta: 0:12:38 lr: 0.000105 grad: 0.0688 (0.0698) loss: 0.8273 (0.8322) time: 0.1456 data: 0.0527 max mem: 9390 +Train: [30] [ 900/6250] eta: 0:12:23 lr: 0.000105 grad: 0.0661 (0.0702) loss: 0.8341 (0.8319) time: 0.1454 data: 0.0560 max mem: 9390 +Train: [30] [1000/6250] eta: 0:12:12 lr: 0.000105 grad: 0.0727 (0.0701) loss: 0.8302 (0.8318) time: 0.1283 data: 0.0461 max mem: 9390 +Train: [30] [1100/6250] eta: 0:12:02 lr: 0.000105 grad: 0.0660 (0.0701) loss: 0.8321 (0.8318) time: 0.1503 data: 0.0728 max mem: 9390 +Train: [30] [1200/6250] eta: 0:11:51 lr: 0.000105 grad: 0.0739 (0.0703) loss: 0.8265 (0.8316) time: 0.1394 data: 0.0606 max mem: 9390 +Train: [30] [1300/6250] eta: 0:11:33 lr: 0.000105 grad: 0.0691 (0.0707) loss: 0.8283 (0.8316) time: 0.1209 data: 0.0415 max mem: 9390 +Train: [30] [1400/6250] eta: 0:11:18 lr: 0.000104 grad: 0.0696 (0.0708) loss: 0.8358 (0.8315) time: 0.1347 data: 0.0595 max mem: 9390 +Train: [30] [1500/6250] eta: 0:11:05 lr: 0.000104 grad: 0.0701 (0.0708) loss: 0.8303 (0.8314) time: 0.1144 data: 0.0366 max mem: 9390 +Train: [30] [1600/6250] eta: 0:10:50 lr: 0.000104 grad: 0.0680 (0.0709) loss: 0.8279 (0.8312) time: 0.1376 data: 0.0628 max mem: 9390 +Train: [30] [1700/6250] eta: 0:10:35 lr: 0.000104 grad: 0.0677 (0.0710) loss: 0.8318 (0.8311) time: 0.1439 data: 0.0622 max mem: 9390 +Train: [30] [1800/6250] eta: 0:10:25 lr: 0.000104 grad: 0.0702 (0.0709) loss: 0.8304 (0.8310) time: 0.1811 data: 0.1006 max mem: 9390 +Train: [30] [1900/6250] eta: 0:10:12 lr: 0.000104 grad: 0.0677 (0.0710) loss: 0.8352 (0.8310) time: 0.1597 data: 0.0821 max mem: 9390 +Train: [30] [2000/6250] eta: 0:09:58 lr: 0.000104 grad: 0.0696 (0.0710) loss: 0.8303 (0.8309) time: 0.1380 data: 0.0631 max mem: 9390 +Train: [30] [2100/6250] eta: 0:09:45 lr: 0.000104 grad: 0.0695 (0.0711) loss: 0.8303 (0.8308) time: 0.1297 data: 0.0521 max mem: 9390 +Train: [30] [2200/6250] eta: 0:09:33 lr: 0.000104 grad: 0.0734 (0.0712) loss: 0.8329 (0.8308) time: 0.1372 data: 0.0553 max mem: 9390 +Train: [30] [2300/6250] eta: 0:09:20 lr: 0.000104 grad: 0.0663 (0.0711) loss: 0.8315 (0.8308) time: 0.1568 data: 0.0796 max mem: 9390 +Train: [30] [2400/6250] eta: 0:09:07 lr: 0.000104 grad: 0.0708 (0.0712) loss: 0.8316 (0.8308) time: 0.1507 data: 0.0693 max mem: 9390 +Train: [30] [2500/6250] eta: 0:08:55 lr: 0.000104 grad: 0.0641 (0.0712) loss: 0.8352 (0.8309) time: 0.1580 data: 0.0799 max mem: 9390 +Train: [30] [2600/6250] eta: 0:08:40 lr: 0.000104 grad: 0.0733 (0.0712) loss: 0.8298 (0.8308) time: 0.1327 data: 0.0558 max mem: 9390 +Train: [30] [2700/6250] eta: 0:08:26 lr: 0.000104 grad: 0.0658 (0.0712) loss: 0.8358 (0.8308) time: 0.1389 data: 0.0620 max mem: 9390 +Train: [30] [2800/6250] eta: 0:08:12 lr: 0.000104 grad: 0.0699 (0.0712) loss: 0.8306 (0.8308) time: 0.1540 data: 0.0712 max mem: 9390 +Train: [30] [2900/6250] eta: 0:07:58 lr: 0.000104 grad: 0.0720 (0.0713) loss: 0.8335 (0.8308) time: 0.1254 data: 0.0477 max mem: 9390 +Train: [30] [3000/6250] eta: 0:07:42 lr: 0.000104 grad: 0.0708 (0.0712) loss: 0.8301 (0.8308) time: 0.1281 data: 0.0499 max mem: 9390 +Train: [30] [3100/6250] eta: 0:07:29 lr: 0.000104 grad: 0.0668 (0.0713) loss: 0.8304 (0.8309) time: 0.1471 data: 0.0581 max mem: 9390 +Train: [30] [3200/6250] eta: 0:07:16 lr: 0.000104 grad: 0.0723 (0.0713) loss: 0.8280 (0.8308) time: 0.1617 data: 0.0816 max mem: 9390 +Train: [30] [3300/6250] eta: 0:07:04 lr: 0.000104 grad: 0.0754 (0.0714) loss: 0.8280 (0.8307) time: 0.1472 data: 0.0264 max mem: 9390 +Train: [30] [3400/6250] eta: 0:06:49 lr: 0.000104 grad: 0.0645 (0.0714) loss: 0.8302 (0.8307) time: 0.1491 data: 0.0709 max mem: 9390 +Train: [30] [3500/6250] eta: 0:06:35 lr: 0.000104 grad: 0.0668 (0.0714) loss: 0.8317 (0.8306) time: 0.1420 data: 0.0603 max mem: 9390 +Train: [30] [3600/6250] eta: 0:06:20 lr: 0.000104 grad: 0.0671 (0.0715) loss: 0.8316 (0.8306) time: 0.1297 data: 0.0511 max mem: 9390 +Train: [30] [3700/6250] eta: 0:06:06 lr: 0.000104 grad: 0.0711 (0.0715) loss: 0.8296 (0.8305) time: 0.1777 data: 0.0897 max mem: 9390 +Train: [30] [3800/6250] eta: 0:05:52 lr: 0.000104 grad: 0.0682 (0.0715) loss: 0.8329 (0.8305) time: 0.1432 data: 0.0649 max mem: 9390 +Train: [30] [3900/6250] eta: 0:05:38 lr: 0.000104 grad: 0.0691 (0.0715) loss: 0.8288 (0.8305) time: 0.1319 data: 0.0497 max mem: 9390 +Train: [30] [4000/6250] eta: 0:05:24 lr: 0.000104 grad: 0.0722 (0.0716) loss: 0.8288 (0.8304) time: 0.1250 data: 0.0286 max mem: 9390 +Train: [30] [4100/6250] eta: 0:05:11 lr: 0.000104 grad: 0.0729 (0.0716) loss: 0.8294 (0.8304) time: 0.0947 data: 0.0002 max mem: 9390 +Train: [30] [4200/6250] eta: 0:04:56 lr: 0.000104 grad: 0.0659 (0.0716) loss: 0.8275 (0.8303) time: 0.1418 data: 0.0625 max mem: 9390 +Train: [30] [4300/6250] eta: 0:04:42 lr: 0.000104 grad: 0.0745 (0.0716) loss: 0.8293 (0.8302) time: 0.1615 data: 0.0834 max mem: 9390 +Train: [30] [4400/6250] eta: 0:04:27 lr: 0.000104 grad: 0.0681 (0.0716) loss: 0.8321 (0.8302) time: 0.1404 data: 0.0598 max mem: 9390 +Train: [30] [4500/6250] eta: 0:04:13 lr: 0.000104 grad: 0.0663 (0.0716) loss: 0.8291 (0.8302) time: 0.1357 data: 0.0528 max mem: 9390 +Train: [30] [4600/6250] eta: 0:03:58 lr: 0.000104 grad: 0.0678 (0.0716) loss: 0.8295 (0.8302) time: 0.1528 data: 0.0768 max mem: 9390 +Train: [30] [4700/6250] eta: 0:03:43 lr: 0.000104 grad: 0.0733 (0.0717) loss: 0.8271 (0.8301) time: 0.1398 data: 0.0611 max mem: 9390 +Train: [30] [4800/6250] eta: 0:03:29 lr: 0.000104 grad: 0.0752 (0.0717) loss: 0.8266 (0.8301) time: 0.1436 data: 0.0477 max mem: 9390 +Train: [30] [4900/6250] eta: 0:03:14 lr: 0.000104 grad: 0.0683 (0.0718) loss: 0.8346 (0.8300) time: 0.1405 data: 0.0625 max mem: 9390 +Train: [30] [5000/6250] eta: 0:03:00 lr: 0.000104 grad: 0.0721 (0.0718) loss: 0.8247 (0.8300) time: 0.1355 data: 0.0585 max mem: 9390 +Train: [30] [5100/6250] eta: 0:02:45 lr: 0.000104 grad: 0.0701 (0.0719) loss: 0.8224 (0.8300) time: 0.1535 data: 0.0781 max mem: 9390 +Train: [30] [5200/6250] eta: 0:02:31 lr: 0.000104 grad: 0.0740 (0.0719) loss: 0.8317 (0.8299) time: 0.1236 data: 0.0342 max mem: 9390 +Train: [30] [5300/6250] eta: 0:02:17 lr: 0.000104 grad: 0.0707 (0.0720) loss: 0.8304 (0.8298) time: 0.1467 data: 0.0674 max mem: 9390 +Train: [30] [5400/6250] eta: 0:02:03 lr: 0.000103 grad: 0.0720 (0.0721) loss: 0.8279 (0.8298) time: 0.1477 data: 0.0694 max mem: 9390 +Train: [30] [5500/6250] eta: 0:01:48 lr: 0.000103 grad: 0.0691 (0.0721) loss: 0.8262 (0.8297) time: 0.1551 data: 0.0802 max mem: 9390 +Train: [30] [5600/6250] eta: 0:01:34 lr: 0.000103 grad: 0.0714 (0.0721) loss: 0.8306 (0.8297) time: 0.1474 data: 0.0628 max mem: 9390 +Train: [30] [5700/6250] eta: 0:01:20 lr: 0.000103 grad: 0.0702 (0.0722) loss: 0.8276 (0.8297) time: 0.1726 data: 0.0899 max mem: 9390 +Train: [30] [5800/6250] eta: 0:01:05 lr: 0.000103 grad: 0.0686 (0.0722) loss: 0.8351 (0.8298) time: 0.1444 data: 0.0621 max mem: 9390 +Train: [30] [5900/6250] eta: 0:00:50 lr: 0.000103 grad: 0.0688 (0.0721) loss: 0.8360 (0.8298) time: 0.1484 data: 0.0706 max mem: 9390 +Train: [30] [6000/6250] eta: 0:00:36 lr: 0.000103 grad: 0.0691 (0.0721) loss: 0.8347 (0.8298) time: 0.1331 data: 0.0548 max mem: 9390 +Train: [30] [6100/6250] eta: 0:00:21 lr: 0.000103 grad: 0.0698 (0.0721) loss: 0.8288 (0.8299) time: 0.1342 data: 0.0594 max mem: 9390 +Train: [30] [6200/6250] eta: 0:00:07 lr: 0.000103 grad: 0.0700 (0.0721) loss: 0.8351 (0.8299) time: 0.1352 data: 0.0546 max mem: 9390 +Train: [30] [6249/6250] eta: 0:00:00 lr: 0.000103 grad: 0.0717 (0.0721) loss: 0.8331 (0.8299) time: 0.1441 data: 0.0636 max mem: 9390 +Train: [30] Total time: 0:15:11 (0.1458 s / it) +Averaged stats: lr: 0.000103 grad: 0.0717 (0.0721) loss: 0.8331 (0.8299) +Eval (hcp-train-subset): [30] [ 0/62] eta: 0:04:48 loss: 0.8495 (0.8495) time: 4.6545 data: 4.6230 max mem: 9390 +Eval (hcp-train-subset): [30] [61/62] eta: 0:00:00 loss: 0.8409 (0.8419) time: 0.1020 data: 0.0748 max mem: 9390 +Eval (hcp-train-subset): [30] Total time: 0:00:12 (0.1994 s / it) +Averaged stats (hcp-train-subset): loss: 0.8409 (0.8419) +Eval (hcp-val): [30] [ 0/62] eta: 0:05:29 loss: 0.8334 (0.8334) time: 5.3156 data: 5.2860 max mem: 9390 +Eval (hcp-val): [30] [61/62] eta: 0:00:00 loss: 0.8372 (0.8383) time: 0.1238 data: 0.0967 max mem: 9390 +Eval (hcp-val): [30] Total time: 0:00:12 (0.2002 s / it) +Averaged stats (hcp-val): loss: 0.8372 (0.8383) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +Train: [31] [ 0/6250] eta: 8:29:36 lr: 0.000103 grad: 0.2764 (0.2764) loss: 0.8609 (0.8609) time: 4.8922 data: 4.7312 max mem: 9390 +Train: [31] [ 100/6250] eta: 0:19:03 lr: 0.000103 grad: 0.0725 (0.0839) loss: 0.8314 (0.8443) time: 0.1300 data: 0.0376 max mem: 9390 +Train: [31] [ 200/6250] eta: 0:16:25 lr: 0.000103 grad: 0.0739 (0.0790) loss: 0.8293 (0.8370) time: 0.1439 data: 0.0580 max mem: 9390 +Train: [31] [ 300/6250] eta: 0:15:05 lr: 0.000103 grad: 0.0732 (0.0782) loss: 0.8294 (0.8340) time: 0.1243 data: 0.0369 max mem: 9390 +Train: [31] [ 400/6250] eta: 0:14:17 lr: 0.000103 grad: 0.0693 (0.0773) loss: 0.8370 (0.8325) time: 0.1259 data: 0.0433 max mem: 9390 +Train: [31] [ 500/6250] eta: 0:13:49 lr: 0.000103 grad: 0.0702 (0.0763) loss: 0.8329 (0.8313) time: 0.1437 data: 0.0624 max mem: 9390 +Train: [31] [ 600/6250] eta: 0:13:22 lr: 0.000103 grad: 0.0710 (0.0755) loss: 0.8229 (0.8303) time: 0.1388 data: 0.0550 max mem: 9390 +Train: [31] [ 700/6250] eta: 0:13:01 lr: 0.000103 grad: 0.0699 (0.0751) loss: 0.8334 (0.8301) time: 0.1389 data: 0.0549 max mem: 9390 +Train: [31] [ 800/6250] eta: 0:12:39 lr: 0.000103 grad: 0.0682 (0.0749) loss: 0.8255 (0.8297) time: 0.1249 data: 0.0408 max mem: 9390 +Train: [31] [ 900/6250] eta: 0:12:31 lr: 0.000103 grad: 0.0760 (0.0750) loss: 0.8239 (0.8291) time: 0.1700 data: 0.0969 max mem: 9390 +Train: [31] [1000/6250] eta: 0:12:26 lr: 0.000103 grad: 0.0725 (0.0754) loss: 0.8213 (0.8288) time: 0.1315 data: 0.0503 max mem: 9390 +Train: [31] [1100/6250] eta: 0:12:21 lr: 0.000103 grad: 0.0690 (0.0751) loss: 0.8295 (0.8288) time: 0.1400 data: 0.0632 max mem: 9390 +Train: [31] [1200/6250] eta: 0:12:09 lr: 0.000103 grad: 0.0698 (0.0750) loss: 0.8284 (0.8285) time: 0.1675 data: 0.0857 max mem: 9390 +Train: [31] [1300/6250] eta: 0:11:57 lr: 0.000103 grad: 0.0750 (0.0750) loss: 0.8192 (0.8281) time: 0.1552 data: 0.0765 max mem: 9390 +Train: [31] [1400/6250] eta: 0:11:42 lr: 0.000103 grad: 0.0695 (0.0750) loss: 0.8303 (0.8278) time: 0.1497 data: 0.0705 max mem: 9390 +Train: [31] [1500/6250] eta: 0:11:27 lr: 0.000103 grad: 0.0739 (0.0756) loss: 0.8244 (0.8276) time: 0.1457 data: 0.0610 max mem: 9390 +Train: [31] [1600/6250] eta: 0:11:08 lr: 0.000103 grad: 0.0736 (0.0755) loss: 0.8239 (0.8273) time: 0.1334 data: 0.0491 max mem: 9390 +Train: [31] [1700/6250] eta: 0:10:50 lr: 0.000103 grad: 0.0680 (0.0760) loss: 0.8272 (0.8273) time: 0.1305 data: 0.0485 max mem: 9390 +Train: [31] [1800/6250] eta: 0:10:36 lr: 0.000103 grad: 0.0694 (0.0763) loss: 0.8302 (0.8272) time: 0.1152 data: 0.0313 max mem: 9390 +Train: [31] [1900/6250] eta: 0:10:23 lr: 0.000103 grad: 0.0705 (0.0761) loss: 0.8284 (0.8273) time: 0.1424 data: 0.0564 max mem: 9390 +Train: [31] [2000/6250] eta: 0:10:11 lr: 0.000103 grad: 0.0673 (0.0759) loss: 0.8351 (0.8274) time: 0.1580 data: 0.0838 max mem: 9390 +Train: [31] [2100/6250] eta: 0:09:56 lr: 0.000103 grad: 0.0695 (0.0757) loss: 0.8239 (0.8275) time: 0.1450 data: 0.0541 max mem: 9390 +Train: [31] [2200/6250] eta: 0:09:44 lr: 0.000103 grad: 0.0682 (0.0756) loss: 0.8282 (0.8276) time: 0.1829 data: 0.1070 max mem: 9390 +Train: [31] [2300/6250] eta: 0:09:30 lr: 0.000103 grad: 0.0739 (0.0755) loss: 0.8303 (0.8277) time: 0.1225 data: 0.0376 max mem: 9390 +Train: [31] [2400/6250] eta: 0:09:14 lr: 0.000103 grad: 0.0700 (0.0756) loss: 0.8296 (0.8279) time: 0.1194 data: 0.0380 max mem: 9390 +Train: [31] [2500/6250] eta: 0:09:00 lr: 0.000103 grad: 0.0713 (0.0755) loss: 0.8320 (0.8280) time: 0.1701 data: 0.0851 max mem: 9390 +Train: [31] [2600/6250] eta: 0:08:45 lr: 0.000103 grad: 0.0688 (0.0755) loss: 0.8316 (0.8281) time: 0.1406 data: 0.0546 max mem: 9390 +Train: [31] [2700/6250] eta: 0:08:29 lr: 0.000103 grad: 0.0752 (0.0754) loss: 0.8283 (0.8282) time: 0.1328 data: 0.0530 max mem: 9390 +Train: [31] [2800/6250] eta: 0:08:16 lr: 0.000103 grad: 0.0736 (0.0754) loss: 0.8276 (0.8282) time: 0.1636 data: 0.0782 max mem: 9390 +Train: [31] [2900/6250] eta: 0:08:02 lr: 0.000103 grad: 0.0742 (0.0754) loss: 0.8255 (0.8282) time: 0.1495 data: 0.0715 max mem: 9390 +Train: [31] [3000/6250] eta: 0:07:47 lr: 0.000103 grad: 0.0768 (0.0754) loss: 0.8236 (0.8281) time: 0.1455 data: 0.0711 max mem: 9390 +Train: [31] [3100/6250] eta: 0:07:32 lr: 0.000103 grad: 0.0718 (0.0754) loss: 0.8251 (0.8281) time: 0.1292 data: 0.0497 max mem: 9390 +Train: [31] [3200/6250] eta: 0:07:18 lr: 0.000102 grad: 0.0727 (0.0755) loss: 0.8203 (0.8280) time: 0.1600 data: 0.0752 max mem: 9390 +Train: [31] [3300/6250] eta: 0:07:04 lr: 0.000102 grad: 0.0773 (0.0755) loss: 0.8234 (0.8280) time: 0.1512 data: 0.0677 max mem: 9390 +Train: [31] [3400/6250] eta: 0:06:49 lr: 0.000102 grad: 0.0739 (0.0755) loss: 0.8332 (0.8280) time: 0.1287 data: 0.0511 max mem: 9390 +Train: [31] [3500/6250] eta: 0:06:34 lr: 0.000102 grad: 0.0724 (0.0755) loss: 0.8300 (0.8280) time: 0.1156 data: 0.0355 max mem: 9390 +Train: [31] [3600/6250] eta: 0:06:19 lr: 0.000102 grad: 0.0746 (0.0754) loss: 0.8281 (0.8280) time: 0.1688 data: 0.0844 max mem: 9390 +Train: [31] [3700/6250] eta: 0:06:06 lr: 0.000102 grad: 0.0715 (0.0754) loss: 0.8229 (0.8280) time: 0.1740 data: 0.0902 max mem: 9390 +Train: [31] [3800/6250] eta: 0:05:51 lr: 0.000102 grad: 0.0704 (0.0754) loss: 0.8289 (0.8280) time: 0.1229 data: 0.0429 max mem: 9390 +Train: [31] [3900/6250] eta: 0:05:37 lr: 0.000102 grad: 0.0684 (0.0753) loss: 0.8216 (0.8279) time: 0.1504 data: 0.0764 max mem: 9390 +Train: [31] [4000/6250] eta: 0:05:22 lr: 0.000102 grad: 0.0747 (0.0753) loss: 0.8280 (0.8279) time: 0.1464 data: 0.0693 max mem: 9390 +Train: [31] [4100/6250] eta: 0:05:07 lr: 0.000102 grad: 0.0712 (0.0752) loss: 0.8299 (0.8280) time: 0.1446 data: 0.0621 max mem: 9390 +Train: [31] [4200/6250] eta: 0:04:53 lr: 0.000102 grad: 0.0756 (0.0752) loss: 0.8227 (0.8280) time: 0.1527 data: 0.0753 max mem: 9390 +Train: [31] [4300/6250] eta: 0:04:38 lr: 0.000102 grad: 0.0695 (0.0751) loss: 0.8267 (0.8280) time: 0.1472 data: 0.0677 max mem: 9390 +Train: [31] [4400/6250] eta: 0:04:24 lr: 0.000102 grad: 0.0699 (0.0752) loss: 0.8294 (0.8280) time: 0.1697 data: 0.0924 max mem: 9390 +Train: [31] [4500/6250] eta: 0:04:10 lr: 0.000102 grad: 0.0688 (0.0751) loss: 0.8275 (0.8281) time: 0.1453 data: 0.0656 max mem: 9390 +Train: [31] [4600/6250] eta: 0:03:56 lr: 0.000102 grad: 0.0739 (0.0751) loss: 0.8301 (0.8281) time: 0.1526 data: 0.0740 max mem: 9390 +Train: [31] [4700/6250] eta: 0:03:41 lr: 0.000102 grad: 0.0677 (0.0750) loss: 0.8283 (0.8281) time: 0.1304 data: 0.0498 max mem: 9390 +Train: [31] [4800/6250] eta: 0:03:27 lr: 0.000102 grad: 0.0709 (0.0750) loss: 0.8262 (0.8282) time: 0.1386 data: 0.0570 max mem: 9390 +Train: [31] [4900/6250] eta: 0:03:12 lr: 0.000102 grad: 0.0739 (0.0750) loss: 0.8342 (0.8282) time: 0.1260 data: 0.0502 max mem: 9390 +Train: [31] [5000/6250] eta: 0:02:58 lr: 0.000102 grad: 0.0739 (0.0750) loss: 0.8218 (0.8283) time: 0.1451 data: 0.0703 max mem: 9390 +Train: [31] [5100/6250] eta: 0:02:44 lr: 0.000102 grad: 0.0678 (0.0749) loss: 0.8361 (0.8283) time: 0.1558 data: 0.0817 max mem: 9390 +Train: [31] [5200/6250] eta: 0:02:29 lr: 0.000102 grad: 0.0712 (0.0749) loss: 0.8269 (0.8283) time: 0.1209 data: 0.0472 max mem: 9390 +Train: [31] [5300/6250] eta: 0:02:16 lr: 0.000102 grad: 0.0716 (0.0748) loss: 0.8253 (0.8283) time: 0.1514 data: 0.0684 max mem: 9390 +Train: [31] [5400/6250] eta: 0:02:01 lr: 0.000102 grad: 0.0759 (0.0748) loss: 0.8293 (0.8283) time: 0.1579 data: 0.0809 max mem: 9390 +Train: [31] [5500/6250] eta: 0:01:47 lr: 0.000102 grad: 0.0672 (0.0747) loss: 0.8306 (0.8283) time: 0.1517 data: 0.0709 max mem: 9390 +Train: [31] [5600/6250] eta: 0:01:33 lr: 0.000102 grad: 0.0698 (0.0747) loss: 0.8243 (0.8283) time: 0.1460 data: 0.0587 max mem: 9390 +Train: [31] [5700/6250] eta: 0:01:19 lr: 0.000102 grad: 0.0736 (0.0747) loss: 0.8274 (0.8283) time: 0.1563 data: 0.0784 max mem: 9390 +Train: [31] [5800/6250] eta: 0:01:04 lr: 0.000102 grad: 0.0667 (0.0747) loss: 0.8325 (0.8283) time: 0.1703 data: 0.0839 max mem: 9390 +Train: [31] [5900/6250] eta: 0:00:50 lr: 0.000102 grad: 0.0666 (0.0746) loss: 0.8271 (0.8283) time: 0.1404 data: 0.0593 max mem: 9390 +Train: [31] [6000/6250] eta: 0:00:35 lr: 0.000102 grad: 0.0699 (0.0745) loss: 0.8279 (0.8283) time: 0.1267 data: 0.0438 max mem: 9390 +Train: [31] [6100/6250] eta: 0:00:21 lr: 0.000102 grad: 0.0664 (0.0745) loss: 0.8322 (0.8283) time: 0.1297 data: 0.0440 max mem: 9390 +Train: [31] [6200/6250] eta: 0:00:07 lr: 0.000102 grad: 0.0723 (0.0745) loss: 0.8274 (0.8283) time: 0.1543 data: 0.0714 max mem: 9390 +Train: [31] [6249/6250] eta: 0:00:00 lr: 0.000102 grad: 0.0723 (0.0745) loss: 0.8268 (0.8283) time: 0.1363 data: 0.0521 max mem: 9390 +Train: [31] Total time: 0:15:00 (0.1442 s / it) +Averaged stats: lr: 0.000102 grad: 0.0723 (0.0745) loss: 0.8268 (0.8283) +Eval (hcp-train-subset): [31] [ 0/62] eta: 0:04:41 loss: 0.8601 (0.8601) time: 4.5366 data: 4.5019 max mem: 9390 +Eval (hcp-train-subset): [31] [61/62] eta: 0:00:00 loss: 0.8395 (0.8422) time: 0.1027 data: 0.0763 max mem: 9390 +Eval (hcp-train-subset): [31] Total time: 0:00:12 (0.2010 s / it) +Averaged stats (hcp-train-subset): loss: 0.8395 (0.8422) +Eval (hcp-val): [31] [ 0/62] eta: 0:04:45 loss: 0.8358 (0.8358) time: 4.6111 data: 4.5828 max mem: 9390 +Eval (hcp-val): [31] [61/62] eta: 0:00:00 loss: 0.8374 (0.8391) time: 0.1354 data: 0.1102 max mem: 9390 +Eval (hcp-val): [31] Total time: 0:00:12 (0.2072 s / it) +Averaged stats (hcp-val): loss: 0.8374 (0.8391) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +Train: [32] [ 0/6250] eta: 9:54:25 lr: 0.000102 grad: 0.0749 (0.0749) loss: 0.8625 (0.8625) time: 5.7065 data: 5.6027 max mem: 9390 +Train: [32] [ 100/6250] eta: 0:19:16 lr: 0.000102 grad: 0.0761 (0.0752) loss: 0.8413 (0.8448) time: 0.1303 data: 0.0438 max mem: 9390 +Train: [32] [ 200/6250] eta: 0:16:31 lr: 0.000102 grad: 0.0760 (0.0770) loss: 0.8230 (0.8380) time: 0.1313 data: 0.0446 max mem: 9390 +Train: [32] [ 300/6250] eta: 0:15:16 lr: 0.000102 grad: 0.0708 (0.0759) loss: 0.8320 (0.8350) time: 0.1507 data: 0.0710 max mem: 9390 +Train: [32] [ 400/6250] eta: 0:14:13 lr: 0.000102 grad: 0.0732 (0.0751) loss: 0.8309 (0.8338) time: 0.1226 data: 0.0422 max mem: 9390 +Train: [32] [ 500/6250] eta: 0:13:41 lr: 0.000102 grad: 0.0679 (0.0741) loss: 0.8367 (0.8337) time: 0.1334 data: 0.0530 max mem: 9390 +Train: [32] [ 600/6250] eta: 0:13:18 lr: 0.000102 grad: 0.0723 (0.0738) loss: 0.8304 (0.8331) time: 0.1481 data: 0.0668 max mem: 9390 +Train: [32] [ 700/6250] eta: 0:13:02 lr: 0.000102 grad: 0.0697 (0.0739) loss: 0.8324 (0.8327) time: 0.1263 data: 0.0443 max mem: 9390 +Train: [32] [ 800/6250] eta: 0:12:49 lr: 0.000101 grad: 0.0755 (0.0740) loss: 0.8251 (0.8324) time: 0.1268 data: 0.0451 max mem: 9390 +Train: [32] [ 900/6250] eta: 0:12:45 lr: 0.000101 grad: 0.0651 (0.0737) loss: 0.8333 (0.8322) time: 0.1601 data: 0.0827 max mem: 9390 +Train: [32] [1000/6250] eta: 0:12:41 lr: 0.000101 grad: 0.0671 (0.0735) loss: 0.8364 (0.8323) time: 0.1739 data: 0.0977 max mem: 9390 +Train: [32] [1100/6250] eta: 0:12:29 lr: 0.000101 grad: 0.0684 (0.0734) loss: 0.8317 (0.8322) time: 0.1364 data: 0.0557 max mem: 9390 +Train: [32] [1200/6250] eta: 0:12:22 lr: 0.000101 grad: 0.0759 (0.0733) loss: 0.8381 (0.8322) time: 0.1781 data: 0.1032 max mem: 9390 +Train: [32] [1300/6250] eta: 0:12:08 lr: 0.000101 grad: 0.0727 (0.0733) loss: 0.8294 (0.8319) time: 0.1552 data: 0.0777 max mem: 9390 +Train: [32] [1400/6250] eta: 0:11:53 lr: 0.000101 grad: 0.0722 (0.0733) loss: 0.8284 (0.8316) time: 0.1554 data: 0.0760 max mem: 9390 +Train: [32] [1500/6250] eta: 0:11:35 lr: 0.000101 grad: 0.0769 (0.0734) loss: 0.8275 (0.8315) time: 0.1505 data: 0.0647 max mem: 9390 +Train: [32] [1600/6250] eta: 0:11:20 lr: 0.000101 grad: 0.0754 (0.0734) loss: 0.8273 (0.8312) time: 0.1464 data: 0.0686 max mem: 9390 +Train: [32] [1700/6250] eta: 0:11:02 lr: 0.000101 grad: 0.0744 (0.0735) loss: 0.8221 (0.8310) time: 0.1357 data: 0.0530 max mem: 9390 +Train: [32] [1800/6250] eta: 0:10:50 lr: 0.000101 grad: 0.0782 (0.0736) loss: 0.8262 (0.8308) time: 0.1278 data: 0.0505 max mem: 9390 +Train: [32] [1900/6250] eta: 0:10:37 lr: 0.000101 grad: 0.0743 (0.0739) loss: 0.8258 (0.8305) time: 0.1535 data: 0.0687 max mem: 9390 +Train: [32] [2000/6250] eta: 0:10:25 lr: 0.000101 grad: 0.0753 (0.0743) loss: 0.8233 (0.8300) time: 0.1524 data: 0.0747 max mem: 9390 +Train: [32] [2100/6250] eta: 0:10:12 lr: 0.000101 grad: 0.0764 (0.0747) loss: 0.8284 (0.8298) time: 0.1662 data: 0.0809 max mem: 9390 +Train: [32] [2200/6250] eta: 0:10:00 lr: 0.000101 grad: 0.0753 (0.0749) loss: 0.8257 (0.8296) time: 0.1457 data: 0.0631 max mem: 9390 +Train: [32] [2300/6250] eta: 0:09:44 lr: 0.000101 grad: 0.0751 (0.0749) loss: 0.8257 (0.8294) time: 0.1517 data: 0.0676 max mem: 9390 +Train: [32] [2400/6250] eta: 0:09:28 lr: 0.000101 grad: 0.0729 (0.0750) loss: 0.8327 (0.8293) time: 0.1445 data: 0.0580 max mem: 9390 +Train: [32] [2500/6250] eta: 0:09:13 lr: 0.000101 grad: 0.0748 (0.0751) loss: 0.8230 (0.8291) time: 0.1471 data: 0.0688 max mem: 9390 +Train: [32] [2600/6250] eta: 0:08:59 lr: 0.000101 grad: 0.0776 (0.0752) loss: 0.8218 (0.8289) time: 0.1447 data: 0.0559 max mem: 9390 +Train: [32] [2700/6250] eta: 0:08:44 lr: 0.000101 grad: 0.0714 (0.0752) loss: 0.8251 (0.8288) time: 0.1473 data: 0.0691 max mem: 9390 +Train: [32] [2800/6250] eta: 0:08:30 lr: 0.000101 grad: 0.0704 (0.0751) loss: 0.8323 (0.8288) time: 0.1658 data: 0.0887 max mem: 9390 +Train: [32] [2900/6250] eta: 0:08:14 lr: 0.000101 grad: 0.0689 (0.0751) loss: 0.8256 (0.8288) time: 0.1754 data: 0.0925 max mem: 9390 +Train: [32] [3000/6250] eta: 0:08:00 lr: 0.000101 grad: 0.0668 (0.0750) loss: 0.8319 (0.8288) time: 0.1634 data: 0.0823 max mem: 9390 +Train: [32] [3100/6250] eta: 0:07:46 lr: 0.000101 grad: 0.0700 (0.0750) loss: 0.8241 (0.8286) time: 0.1526 data: 0.0652 max mem: 9390 +Train: [32] [3200/6250] eta: 0:07:31 lr: 0.000101 grad: 0.0704 (0.0752) loss: 0.8325 (0.8286) time: 0.1170 data: 0.0388 max mem: 9390 +Train: [32] [3300/6250] eta: 0:07:15 lr: 0.000101 grad: 0.0719 (0.0753) loss: 0.8252 (0.8285) time: 0.1494 data: 0.0748 max mem: 9390 +Train: [32] [3400/6250] eta: 0:07:00 lr: 0.000101 grad: 0.0716 (0.0753) loss: 0.8304 (0.8285) time: 0.1523 data: 0.0690 max mem: 9390 +Train: [32] [3500/6250] eta: 0:06:45 lr: 0.000101 grad: 0.0729 (0.0753) loss: 0.8217 (0.8284) time: 0.1414 data: 0.0696 max mem: 9390 +Train: [32] [3600/6250] eta: 0:06:32 lr: 0.000101 grad: 0.0694 (0.0753) loss: 0.8282 (0.8284) time: 0.2653 data: 0.1827 max mem: 9390 +Train: [32] [3700/6250] eta: 0:06:16 lr: 0.000101 grad: 0.0729 (0.0753) loss: 0.8283 (0.8283) time: 0.1434 data: 0.0653 max mem: 9390 +Train: [32] [3800/6250] eta: 0:06:02 lr: 0.000101 grad: 0.0732 (0.0753) loss: 0.8216 (0.8282) time: 0.1518 data: 0.0610 max mem: 9390 +Train: [32] [3900/6250] eta: 0:05:48 lr: 0.000101 grad: 0.0781 (0.0752) loss: 0.8225 (0.8282) time: 0.1516 data: 0.0649 max mem: 9390 +Train: [32] [4000/6250] eta: 0:05:33 lr: 0.000101 grad: 0.0694 (0.0752) loss: 0.8294 (0.8282) time: 0.1635 data: 0.0866 max mem: 9390 +Train: [32] [4100/6250] eta: 0:05:17 lr: 0.000101 grad: 0.0687 (0.0752) loss: 0.8280 (0.8281) time: 0.1365 data: 0.0564 max mem: 9390 +Train: [32] [4200/6250] eta: 0:05:03 lr: 0.000101 grad: 0.0728 (0.0751) loss: 0.8244 (0.8281) time: 0.1438 data: 0.0615 max mem: 9390 +Train: [32] [4300/6250] eta: 0:04:49 lr: 0.000101 grad: 0.0745 (0.0751) loss: 0.8284 (0.8281) time: 0.1846 data: 0.1048 max mem: 9390 +Train: [32] [4400/6250] eta: 0:04:33 lr: 0.000101 grad: 0.0693 (0.0751) loss: 0.8314 (0.8281) time: 0.1460 data: 0.0678 max mem: 9390 +Train: [32] [4500/6250] eta: 0:04:19 lr: 0.000101 grad: 0.0711 (0.0751) loss: 0.8299 (0.8281) time: 0.1454 data: 0.0630 max mem: 9390 +Train: [32] [4600/6250] eta: 0:04:04 lr: 0.000101 grad: 0.0706 (0.0750) loss: 0.8300 (0.8281) time: 0.1599 data: 0.0829 max mem: 9390 +Train: [32] [4700/6250] eta: 0:03:49 lr: 0.000100 grad: 0.0662 (0.0750) loss: 0.8249 (0.8281) time: 0.1512 data: 0.0710 max mem: 9390 +Train: [32] [4800/6250] eta: 0:03:35 lr: 0.000100 grad: 0.0727 (0.0750) loss: 0.8312 (0.8281) time: 0.1601 data: 0.0803 max mem: 9390 +Train: [32] [4900/6250] eta: 0:03:20 lr: 0.000100 grad: 0.0723 (0.0750) loss: 0.8300 (0.8281) time: 0.1798 data: 0.1063 max mem: 9390 +Train: [32] [5000/6250] eta: 0:03:05 lr: 0.000100 grad: 0.0727 (0.0749) loss: 0.8278 (0.8281) time: 0.1525 data: 0.0757 max mem: 9390 +Train: [32] [5100/6250] eta: 0:02:50 lr: 0.000100 grad: 0.0712 (0.0749) loss: 0.8296 (0.8281) time: 0.1592 data: 0.0773 max mem: 9390 +Train: [32] [5200/6250] eta: 0:02:36 lr: 0.000100 grad: 0.0699 (0.0749) loss: 0.8294 (0.8281) time: 0.1914 data: 0.1149 max mem: 9390 +Train: [32] [5300/6250] eta: 0:02:21 lr: 0.000100 grad: 0.0721 (0.0749) loss: 0.8248 (0.8281) time: 0.1530 data: 0.0692 max mem: 9390 +Train: [32] [5400/6250] eta: 0:02:07 lr: 0.000100 grad: 0.0741 (0.0749) loss: 0.8232 (0.8280) time: 0.1673 data: 0.0865 max mem: 9390 +Train: [32] [5500/6250] eta: 0:01:52 lr: 0.000100 grad: 0.0722 (0.0748) loss: 0.8304 (0.8280) time: 0.1349 data: 0.0526 max mem: 9390 +Train: [32] [5600/6250] eta: 0:01:37 lr: 0.000100 grad: 0.0691 (0.0748) loss: 0.8331 (0.8280) time: 0.1284 data: 0.0448 max mem: 9390 +Train: [32] [5700/6250] eta: 0:01:22 lr: 0.000100 grad: 0.0743 (0.0748) loss: 0.8238 (0.8280) time: 0.1498 data: 0.0718 max mem: 9390 +Train: [32] [5800/6250] eta: 0:01:07 lr: 0.000100 grad: 0.0691 (0.0748) loss: 0.8337 (0.8280) time: 0.1492 data: 0.0660 max mem: 9390 +Train: [32] [5900/6250] eta: 0:00:52 lr: 0.000100 grad: 0.0680 (0.0748) loss: 0.8353 (0.8280) time: 0.1258 data: 0.0413 max mem: 9390 +Train: [32] [6000/6250] eta: 0:00:37 lr: 0.000100 grad: 0.0703 (0.0748) loss: 0.8246 (0.8280) time: 0.1166 data: 0.0349 max mem: 9390 +Train: [32] [6100/6250] eta: 0:00:22 lr: 0.000100 grad: 0.0700 (0.0748) loss: 0.8268 (0.8280) time: 0.1240 data: 0.0430 max mem: 9390 +Train: [32] [6200/6250] eta: 0:00:07 lr: 0.000100 grad: 0.0742 (0.0749) loss: 0.8251 (0.8279) time: 0.1400 data: 0.0591 max mem: 9390 +Train: [32] [6249/6250] eta: 0:00:00 lr: 0.000100 grad: 0.0757 (0.0749) loss: 0.8243 (0.8279) time: 0.1167 data: 0.0353 max mem: 9390 +Train: [32] Total time: 0:15:29 (0.1488 s / it) +Averaged stats: lr: 0.000100 grad: 0.0757 (0.0749) loss: 0.8243 (0.8279) +Eval (hcp-train-subset): [32] [ 0/62] eta: 0:04:01 loss: 0.8509 (0.8509) time: 3.8938 data: 3.8461 max mem: 9390 +Eval (hcp-train-subset): [32] [61/62] eta: 0:00:00 loss: 0.8415 (0.8419) time: 0.1305 data: 0.1053 max mem: 9390 +Eval (hcp-train-subset): [32] Total time: 0:00:12 (0.2024 s / it) +Averaged stats (hcp-train-subset): loss: 0.8415 (0.8419) +Eval (hcp-val): [32] [ 0/62] eta: 0:04:18 loss: 0.8352 (0.8352) time: 4.1740 data: 4.1448 max mem: 9390 +Eval (hcp-val): [32] [61/62] eta: 0:00:00 loss: 0.8369 (0.8379) time: 0.1194 data: 0.0940 max mem: 9390 +Eval (hcp-val): [32] Total time: 0:00:11 (0.1909 s / it) +Averaged stats (hcp-val): loss: 0.8369 (0.8379) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +Train: [33] [ 0/6250] eta: 10:09:01 lr: 0.000100 grad: 0.0681 (0.0681) loss: 0.8646 (0.8646) time: 5.8466 data: 5.7509 max mem: 9390 +Train: [33] [ 100/6250] eta: 0:19:32 lr: 0.000100 grad: 0.0686 (0.0782) loss: 0.8450 (0.8399) time: 0.1354 data: 0.0395 max mem: 9390 +Train: [33] [ 200/6250] eta: 0:16:36 lr: 0.000100 grad: 0.0769 (0.0761) loss: 0.8419 (0.8396) time: 0.1446 data: 0.0636 max mem: 9390 +Train: [33] [ 300/6250] eta: 0:15:22 lr: 0.000100 grad: 0.0710 (0.0770) loss: 0.8322 (0.8374) time: 0.1378 data: 0.0588 max mem: 9390 +Train: [33] [ 400/6250] eta: 0:14:29 lr: 0.000100 grad: 0.0730 (0.0777) loss: 0.8322 (0.8349) time: 0.1222 data: 0.0322 max mem: 9390 +Train: [33] [ 500/6250] eta: 0:13:55 lr: 0.000100 grad: 0.0673 (0.0768) loss: 0.8247 (0.8336) time: 0.1215 data: 0.0346 max mem: 9390 +Train: [33] [ 600/6250] eta: 0:13:25 lr: 0.000100 grad: 0.0677 (0.0760) loss: 0.8318 (0.8323) time: 0.1427 data: 0.0607 max mem: 9390 +Train: [33] [ 700/6250] eta: 0:13:02 lr: 0.000100 grad: 0.0729 (0.0755) loss: 0.8271 (0.8312) time: 0.1502 data: 0.0669 max mem: 9390 +Train: [33] [ 800/6250] eta: 0:12:37 lr: 0.000100 grad: 0.0740 (0.0751) loss: 0.8240 (0.8307) time: 0.1223 data: 0.0409 max mem: 9390 +Train: [33] [ 900/6250] eta: 0:12:21 lr: 0.000100 grad: 0.0687 (0.0749) loss: 0.8212 (0.8300) time: 0.1332 data: 0.0442 max mem: 9390 +Train: [33] [1000/6250] eta: 0:12:06 lr: 0.000100 grad: 0.0733 (0.0750) loss: 0.8236 (0.8296) time: 0.1392 data: 0.0659 max mem: 9390 +Train: [33] [1100/6250] eta: 0:11:55 lr: 0.000100 grad: 0.0723 (0.0750) loss: 0.8234 (0.8291) time: 0.1598 data: 0.0835 max mem: 9390 +Train: [33] [1200/6250] eta: 0:11:42 lr: 0.000100 grad: 0.0717 (0.0752) loss: 0.8267 (0.8286) time: 0.1296 data: 0.0437 max mem: 9390 +Train: [33] [1300/6250] eta: 0:11:26 lr: 0.000100 grad: 0.0778 (0.0754) loss: 0.8154 (0.8282) time: 0.1254 data: 0.0446 max mem: 9390 +Train: [33] [1400/6250] eta: 0:11:13 lr: 0.000100 grad: 0.0743 (0.0758) loss: 0.8264 (0.8277) time: 0.1338 data: 0.0542 max mem: 9390 +Train: [33] [1500/6250] eta: 0:10:58 lr: 0.000100 grad: 0.0728 (0.0761) loss: 0.8216 (0.8273) time: 0.1490 data: 0.0714 max mem: 9390 +Train: [33] [1600/6250] eta: 0:10:43 lr: 0.000100 grad: 0.0698 (0.0765) loss: 0.8256 (0.8271) time: 0.1217 data: 0.0458 max mem: 9390 +Train: [33] [1700/6250] eta: 0:10:30 lr: 0.000100 grad: 0.0763 (0.0767) loss: 0.8235 (0.8268) time: 0.1415 data: 0.0492 max mem: 9390 +Train: [33] [1800/6250] eta: 0:10:18 lr: 0.000100 grad: 0.0716 (0.0767) loss: 0.8242 (0.8267) time: 0.1562 data: 0.0786 max mem: 9390 +Train: [33] [1900/6250] eta: 0:10:06 lr: 0.000100 grad: 0.0728 (0.0767) loss: 0.8261 (0.8266) time: 0.1692 data: 0.0871 max mem: 9390 +Train: [33] [2000/6250] eta: 0:09:55 lr: 0.000100 grad: 0.0755 (0.0769) loss: 0.8263 (0.8264) time: 0.1427 data: 0.0610 max mem: 9390 +Train: [33] [2100/6250] eta: 0:09:42 lr: 0.000100 grad: 0.0786 (0.0771) loss: 0.8266 (0.8263) time: 0.1624 data: 0.0819 max mem: 9390 +Train: [33] [2200/6250] eta: 0:09:29 lr: 0.000099 grad: 0.0800 (0.0773) loss: 0.8200 (0.8261) time: 0.1342 data: 0.0542 max mem: 9390 +Train: [33] [2300/6250] eta: 0:09:16 lr: 0.000099 grad: 0.0737 (0.0773) loss: 0.8262 (0.8261) time: 0.1637 data: 0.0707 max mem: 9390 +Train: [33] [2400/6250] eta: 0:09:02 lr: 0.000099 grad: 0.0761 (0.0774) loss: 0.8263 (0.8260) time: 0.1079 data: 0.0309 max mem: 9390 +Train: [33] [2500/6250] eta: 0:08:48 lr: 0.000099 grad: 0.0736 (0.0774) loss: 0.8266 (0.8260) time: 0.1157 data: 0.0357 max mem: 9390 +Train: [33] [2600/6250] eta: 0:08:33 lr: 0.000099 grad: 0.0748 (0.0774) loss: 0.8278 (0.8260) time: 0.1339 data: 0.0480 max mem: 9390 +Train: [33] [2700/6250] eta: 0:08:21 lr: 0.000099 grad: 0.0703 (0.0773) loss: 0.8264 (0.8260) time: 0.1568 data: 0.0764 max mem: 9390 +Train: [33] [2800/6250] eta: 0:08:06 lr: 0.000099 grad: 0.0742 (0.0774) loss: 0.8235 (0.8260) time: 0.1158 data: 0.0345 max mem: 9390 +Train: [33] [2900/6250] eta: 0:07:52 lr: 0.000099 grad: 0.0733 (0.0773) loss: 0.8275 (0.8261) time: 0.1271 data: 0.0455 max mem: 9390 +Train: [33] [3000/6250] eta: 0:07:38 lr: 0.000099 grad: 0.0700 (0.0772) loss: 0.8288 (0.8260) time: 0.1440 data: 0.0661 max mem: 9390 +Train: [33] [3100/6250] eta: 0:07:24 lr: 0.000099 grad: 0.0699 (0.0772) loss: 0.8282 (0.8260) time: 0.1113 data: 0.0284 max mem: 9390 +Train: [33] [3200/6250] eta: 0:07:11 lr: 0.000099 grad: 0.0718 (0.0771) loss: 0.8266 (0.8260) time: 0.1500 data: 0.0729 max mem: 9390 +Train: [33] [3300/6250] eta: 0:06:57 lr: 0.000099 grad: 0.0720 (0.0770) loss: 0.8290 (0.8262) time: 0.1316 data: 0.0531 max mem: 9390 +Train: [33] [3400/6250] eta: 0:06:43 lr: 0.000099 grad: 0.0719 (0.0769) loss: 0.8226 (0.8262) time: 0.1561 data: 0.0738 max mem: 9390 +Train: [33] [3500/6250] eta: 0:06:30 lr: 0.000099 grad: 0.0742 (0.0770) loss: 0.8241 (0.8262) time: 0.1465 data: 0.0632 max mem: 9390 +Train: [33] [3600/6250] eta: 0:06:16 lr: 0.000099 grad: 0.0743 (0.0770) loss: 0.8212 (0.8262) time: 0.1612 data: 0.0837 max mem: 9390 +Train: [33] [3700/6250] eta: 0:06:02 lr: 0.000099 grad: 0.0754 (0.0770) loss: 0.8272 (0.8263) time: 0.1563 data: 0.0800 max mem: 9390 +Train: [33] [3800/6250] eta: 0:05:47 lr: 0.000099 grad: 0.0747 (0.0770) loss: 0.8313 (0.8263) time: 0.1310 data: 0.0445 max mem: 9390 +Train: [33] [3900/6250] eta: 0:05:35 lr: 0.000099 grad: 0.0764 (0.0771) loss: 0.8277 (0.8263) time: 0.2014 data: 0.1065 max mem: 9390 +Train: [33] [4000/6250] eta: 0:05:20 lr: 0.000099 grad: 0.0692 (0.0770) loss: 0.8347 (0.8264) time: 0.1495 data: 0.0677 max mem: 9390 +Train: [33] [4100/6250] eta: 0:05:07 lr: 0.000099 grad: 0.0772 (0.0770) loss: 0.8313 (0.8265) time: 0.1920 data: 0.0962 max mem: 9390 +Train: [33] [4200/6250] eta: 0:04:53 lr: 0.000099 grad: 0.0757 (0.0770) loss: 0.8291 (0.8265) time: 0.1528 data: 0.0640 max mem: 9390 +Train: [33] [4300/6250] eta: 0:04:39 lr: 0.000099 grad: 0.0728 (0.0769) loss: 0.8255 (0.8266) time: 0.1589 data: 0.0820 max mem: 9390 +Train: [33] [4400/6250] eta: 0:04:24 lr: 0.000099 grad: 0.0735 (0.0769) loss: 0.8288 (0.8266) time: 0.1233 data: 0.0421 max mem: 9390 +Train: [33] [4500/6250] eta: 0:04:10 lr: 0.000099 grad: 0.0752 (0.0769) loss: 0.8294 (0.8267) time: 0.1242 data: 0.0413 max mem: 9390 +Train: [33] [4600/6250] eta: 0:03:56 lr: 0.000099 grad: 0.0733 (0.0769) loss: 0.8257 (0.8267) time: 0.1475 data: 0.0634 max mem: 9390 +Train: [33] [4700/6250] eta: 0:03:41 lr: 0.000099 grad: 0.0744 (0.0769) loss: 0.8217 (0.8268) time: 0.1433 data: 0.0633 max mem: 9390 +Train: [33] [4800/6250] eta: 0:03:27 lr: 0.000099 grad: 0.0753 (0.0768) loss: 0.8321 (0.8268) time: 0.1659 data: 0.0901 max mem: 9390 +Train: [33] [4900/6250] eta: 0:03:13 lr: 0.000099 grad: 0.0714 (0.0768) loss: 0.8345 (0.8269) time: 0.1297 data: 0.0525 max mem: 9390 +Train: [33] [5000/6250] eta: 0:02:58 lr: 0.000099 grad: 0.0737 (0.0767) loss: 0.8253 (0.8269) time: 0.1322 data: 0.0540 max mem: 9390 +Train: [33] [5100/6250] eta: 0:02:44 lr: 0.000099 grad: 0.0754 (0.0767) loss: 0.8304 (0.8270) time: 0.1416 data: 0.0647 max mem: 9390 +Train: [33] [5200/6250] eta: 0:02:30 lr: 0.000099 grad: 0.0709 (0.0766) loss: 0.8272 (0.8271) time: 0.1741 data: 0.0891 max mem: 9390 +Train: [33] [5300/6250] eta: 0:02:16 lr: 0.000099 grad: 0.0653 (0.0766) loss: 0.8334 (0.8271) time: 0.1282 data: 0.0502 max mem: 9390 +Train: [33] [5400/6250] eta: 0:02:02 lr: 0.000099 grad: 0.0716 (0.0765) loss: 0.8263 (0.8272) time: 0.1584 data: 0.0696 max mem: 9390 +Train: [33] [5500/6250] eta: 0:01:48 lr: 0.000099 grad: 0.0778 (0.0765) loss: 0.8237 (0.8272) time: 0.1602 data: 0.0787 max mem: 9390 +Train: [33] [5600/6250] eta: 0:01:33 lr: 0.000099 grad: 0.0777 (0.0765) loss: 0.8246 (0.8272) time: 0.1202 data: 0.0383 max mem: 9390 +Train: [33] [5700/6250] eta: 0:01:19 lr: 0.000099 grad: 0.0730 (0.0765) loss: 0.8324 (0.8272) time: 0.1332 data: 0.0565 max mem: 9390 +Train: [33] [5800/6250] eta: 0:01:04 lr: 0.000099 grad: 0.0730 (0.0765) loss: 0.8292 (0.8272) time: 0.1428 data: 0.0570 max mem: 9390 +Train: [33] [5900/6250] eta: 0:00:50 lr: 0.000098 grad: 0.0736 (0.0765) loss: 0.8254 (0.8272) time: 0.1324 data: 0.0445 max mem: 9390 +Train: [33] [6000/6250] eta: 0:00:35 lr: 0.000098 grad: 0.0724 (0.0764) loss: 0.8299 (0.8273) time: 0.1452 data: 0.0657 max mem: 9390 +Train: [33] [6100/6250] eta: 0:00:21 lr: 0.000098 grad: 0.0682 (0.0763) loss: 0.8299 (0.8273) time: 0.1273 data: 0.0472 max mem: 9390 +Train: [33] [6200/6250] eta: 0:00:07 lr: 0.000098 grad: 0.0716 (0.0763) loss: 0.8302 (0.8274) time: 0.1248 data: 0.0460 max mem: 9390 +Train: [33] [6249/6250] eta: 0:00:00 lr: 0.000098 grad: 0.0699 (0.0762) loss: 0.8287 (0.8274) time: 0.1351 data: 0.0563 max mem: 9390 +Train: [33] Total time: 0:15:02 (0.1444 s / it) +Averaged stats: lr: 0.000098 grad: 0.0699 (0.0762) loss: 0.8287 (0.8274) +Eval (hcp-train-subset): [33] [ 0/62] eta: 0:03:46 loss: 0.8511 (0.8511) time: 3.6569 data: 3.5761 max mem: 9390 +Eval (hcp-train-subset): [33] [61/62] eta: 0:00:00 loss: 0.8407 (0.8427) time: 0.1178 data: 0.0930 max mem: 9390 +Eval (hcp-train-subset): [33] Total time: 0:00:11 (0.1901 s / it) +Averaged stats (hcp-train-subset): loss: 0.8407 (0.8427) +Eval (hcp-val): [33] [ 0/62] eta: 0:03:38 loss: 0.8358 (0.8358) time: 3.5248 data: 3.4191 max mem: 9390 +Eval (hcp-val): [33] [61/62] eta: 0:00:00 loss: 0.8371 (0.8385) time: 0.1050 data: 0.0803 max mem: 9390 +Eval (hcp-val): [33] Total time: 0:00:11 (0.1920 s / it) +Averaged stats (hcp-val): loss: 0.8371 (0.8385) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +Train: [34] [ 0/6250] eta: 6:36:54 lr: 0.000098 grad: 0.1297 (0.1297) loss: 0.8530 (0.8530) time: 3.8103 data: 3.5781 max mem: 9390 +Train: [34] [ 100/6250] eta: 0:19:50 lr: 0.000098 grad: 0.0755 (0.0875) loss: 0.8337 (0.8364) time: 0.1361 data: 0.0497 max mem: 9390 +Train: [34] [ 200/6250] eta: 0:17:26 lr: 0.000098 grad: 0.0740 (0.0827) loss: 0.8298 (0.8327) time: 0.1521 data: 0.0560 max mem: 9390 +Train: [34] [ 300/6250] eta: 0:16:26 lr: 0.000098 grad: 0.0743 (0.0807) loss: 0.8359 (0.8318) time: 0.1443 data: 0.0623 max mem: 9390 +Train: [34] [ 400/6250] eta: 0:15:31 lr: 0.000098 grad: 0.0765 (0.0801) loss: 0.8219 (0.8303) time: 0.1300 data: 0.0426 max mem: 9390 +Train: [34] [ 500/6250] eta: 0:14:49 lr: 0.000098 grad: 0.0727 (0.0790) loss: 0.8293 (0.8298) time: 0.1343 data: 0.0485 max mem: 9390 +Train: [34] [ 600/6250] eta: 0:14:02 lr: 0.000098 grad: 0.0703 (0.0781) loss: 0.8278 (0.8296) time: 0.1092 data: 0.0258 max mem: 9390 +Train: [34] [ 700/6250] eta: 0:13:40 lr: 0.000098 grad: 0.0689 (0.0774) loss: 0.8325 (0.8297) time: 0.1751 data: 0.0932 max mem: 9390 +Train: [34] [ 800/6250] eta: 0:13:16 lr: 0.000098 grad: 0.0715 (0.0772) loss: 0.8333 (0.8296) time: 0.1481 data: 0.0673 max mem: 9390 +Train: [34] [ 900/6250] eta: 0:13:10 lr: 0.000098 grad: 0.0719 (0.0770) loss: 0.8297 (0.8296) time: 0.1780 data: 0.0923 max mem: 9390 +Train: [34] [1000/6250] eta: 0:12:56 lr: 0.000098 grad: 0.0715 (0.0766) loss: 0.8330 (0.8298) time: 0.1502 data: 0.0729 max mem: 9390 +Train: [34] [1100/6250] eta: 0:12:41 lr: 0.000098 grad: 0.0785 (0.0765) loss: 0.8250 (0.8295) time: 0.1576 data: 0.0852 max mem: 9390 +Train: [34] [1200/6250] eta: 0:12:24 lr: 0.000098 grad: 0.0699 (0.0764) loss: 0.8301 (0.8293) time: 0.1279 data: 0.0413 max mem: 9390 +Train: [34] [1300/6250] eta: 0:12:07 lr: 0.000098 grad: 0.0722 (0.0761) loss: 0.8269 (0.8293) time: 0.1346 data: 0.0513 max mem: 9390 +Train: [34] [1400/6250] eta: 0:11:49 lr: 0.000098 grad: 0.0728 (0.0759) loss: 0.8309 (0.8291) time: 0.1477 data: 0.0663 max mem: 9390 +Train: [34] [1500/6250] eta: 0:11:31 lr: 0.000098 grad: 0.0760 (0.0758) loss: 0.8294 (0.8289) time: 0.1376 data: 0.0520 max mem: 9390 +Train: [34] [1600/6250] eta: 0:11:15 lr: 0.000098 grad: 0.0708 (0.0756) loss: 0.8278 (0.8288) time: 0.1508 data: 0.0706 max mem: 9390 +Train: [34] [1700/6250] eta: 0:11:04 lr: 0.000098 grad: 0.0673 (0.0755) loss: 0.8351 (0.8287) time: 0.1738 data: 0.0933 max mem: 9390 +Train: [34] [1800/6250] eta: 0:10:48 lr: 0.000098 grad: 0.0748 (0.0754) loss: 0.8275 (0.8286) time: 0.1204 data: 0.0353 max mem: 9390 +Train: [34] [1900/6250] eta: 0:10:32 lr: 0.000098 grad: 0.0742 (0.0755) loss: 0.8282 (0.8284) time: 0.1272 data: 0.0457 max mem: 9390 +Train: [34] [2000/6250] eta: 0:10:17 lr: 0.000098 grad: 0.0772 (0.0754) loss: 0.8243 (0.8284) time: 0.1365 data: 0.0576 max mem: 9390 +Train: [34] [2100/6250] eta: 0:10:02 lr: 0.000098 grad: 0.0739 (0.0755) loss: 0.8218 (0.8284) time: 0.1391 data: 0.0600 max mem: 9390 +Train: [34] [2200/6250] eta: 0:09:47 lr: 0.000098 grad: 0.0679 (0.0755) loss: 0.8297 (0.8284) time: 0.1192 data: 0.0432 max mem: 9390 +Train: [34] [2300/6250] eta: 0:09:32 lr: 0.000098 grad: 0.0746 (0.0754) loss: 0.8287 (0.8285) time: 0.1398 data: 0.0640 max mem: 9390 +Train: [34] [2400/6250] eta: 0:09:17 lr: 0.000098 grad: 0.0684 (0.0754) loss: 0.8349 (0.8286) time: 0.1343 data: 0.0559 max mem: 9390 +Train: [34] [2500/6250] eta: 0:09:02 lr: 0.000098 grad: 0.0705 (0.0753) loss: 0.8338 (0.8287) time: 0.1296 data: 0.0526 max mem: 9390 +Train: [34] [2600/6250] eta: 0:08:47 lr: 0.000098 grad: 0.0721 (0.0752) loss: 0.8269 (0.8288) time: 0.1366 data: 0.0589 max mem: 9390 +Train: [34] [2700/6250] eta: 0:08:32 lr: 0.000098 grad: 0.0686 (0.0752) loss: 0.8339 (0.8289) time: 0.1547 data: 0.0749 max mem: 9390 +Train: [34] [2800/6250] eta: 0:08:18 lr: 0.000098 grad: 0.0781 (0.0751) loss: 0.8261 (0.8289) time: 0.1467 data: 0.0651 max mem: 9390 +Train: [34] [2900/6250] eta: 0:08:05 lr: 0.000098 grad: 0.0736 (0.0750) loss: 0.8219 (0.8289) time: 0.1551 data: 0.0756 max mem: 9390 +Train: [34] [3000/6250] eta: 0:07:49 lr: 0.000098 grad: 0.0724 (0.0750) loss: 0.8284 (0.8289) time: 0.1418 data: 0.0632 max mem: 9390 +Train: [34] [3100/6250] eta: 0:07:35 lr: 0.000098 grad: 0.0715 (0.0749) loss: 0.8286 (0.8289) time: 0.1532 data: 0.0698 max mem: 9390 +Train: [34] [3200/6250] eta: 0:07:20 lr: 0.000098 grad: 0.0747 (0.0749) loss: 0.8278 (0.8290) time: 0.1452 data: 0.0644 max mem: 9390 +Train: [34] [3300/6250] eta: 0:07:06 lr: 0.000097 grad: 0.0740 (0.0749) loss: 0.8243 (0.8290) time: 0.1401 data: 0.0615 max mem: 9390 +Train: [34] [3400/6250] eta: 0:06:52 lr: 0.000097 grad: 0.0706 (0.0749) loss: 0.8241 (0.8290) time: 0.1303 data: 0.0485 max mem: 9390 +Train: [34] [3500/6250] eta: 0:06:38 lr: 0.000097 grad: 0.0714 (0.0749) loss: 0.8337 (0.8290) time: 0.1414 data: 0.0588 max mem: 9390 +Train: [34] [3600/6250] eta: 0:06:23 lr: 0.000097 grad: 0.0754 (0.0750) loss: 0.8303 (0.8290) time: 0.1468 data: 0.0693 max mem: 9390 +Train: [34] [3700/6250] eta: 0:06:08 lr: 0.000097 grad: 0.0737 (0.0751) loss: 0.8304 (0.8290) time: 0.1346 data: 0.0518 max mem: 9390 +Train: [34] [3800/6250] eta: 0:05:53 lr: 0.000097 grad: 0.0725 (0.0751) loss: 0.8246 (0.8291) time: 0.1224 data: 0.0424 max mem: 9390 +Train: [34] [3900/6250] eta: 0:05:40 lr: 0.000097 grad: 0.0747 (0.0751) loss: 0.8264 (0.8290) time: 0.1492 data: 0.0654 max mem: 9390 +Train: [34] [4000/6250] eta: 0:05:25 lr: 0.000097 grad: 0.0719 (0.0751) loss: 0.8304 (0.8290) time: 0.1571 data: 0.0806 max mem: 9390 +Train: [34] [4100/6250] eta: 0:05:11 lr: 0.000097 grad: 0.0753 (0.0751) loss: 0.8243 (0.8291) time: 0.1393 data: 0.0565 max mem: 9390 +Train: [34] [4200/6250] eta: 0:04:57 lr: 0.000097 grad: 0.0713 (0.0751) loss: 0.8326 (0.8291) time: 0.1448 data: 0.0686 max mem: 9390 +Train: [34] [4300/6250] eta: 0:04:42 lr: 0.000097 grad: 0.0735 (0.0751) loss: 0.8277 (0.8291) time: 0.1548 data: 0.0750 max mem: 9390 +Train: [34] [4400/6250] eta: 0:04:27 lr: 0.000097 grad: 0.0734 (0.0750) loss: 0.8292 (0.8291) time: 0.1351 data: 0.0519 max mem: 9390 +Train: [34] [4500/6250] eta: 0:04:13 lr: 0.000097 grad: 0.0720 (0.0751) loss: 0.8259 (0.8291) time: 0.1352 data: 0.0576 max mem: 9390 +Train: [34] [4600/6250] eta: 0:03:59 lr: 0.000097 grad: 0.0737 (0.0751) loss: 0.8307 (0.8291) time: 0.1446 data: 0.0611 max mem: 9390 +Train: [34] [4700/6250] eta: 0:03:44 lr: 0.000097 grad: 0.0690 (0.0751) loss: 0.8280 (0.8291) time: 0.1373 data: 0.0551 max mem: 9390 +Train: [34] [4800/6250] eta: 0:03:29 lr: 0.000097 grad: 0.0699 (0.0750) loss: 0.8342 (0.8292) time: 0.1320 data: 0.0456 max mem: 9390 +Train: [34] [4900/6250] eta: 0:03:15 lr: 0.000097 grad: 0.0705 (0.0750) loss: 0.8336 (0.8291) time: 0.1562 data: 0.0784 max mem: 9390 +Train: [34] [5000/6250] eta: 0:03:00 lr: 0.000097 grad: 0.0727 (0.0750) loss: 0.8257 (0.8291) time: 0.1498 data: 0.0692 max mem: 9390 +Train: [34] [5100/6250] eta: 0:02:46 lr: 0.000097 grad: 0.0730 (0.0751) loss: 0.8329 (0.8292) time: 0.1566 data: 0.0826 max mem: 9390 +Train: [34] [5200/6250] eta: 0:02:32 lr: 0.000097 grad: 0.0747 (0.0751) loss: 0.8355 (0.8292) time: 0.1410 data: 0.0627 max mem: 9390 +Train: [34] [5300/6250] eta: 0:02:17 lr: 0.000097 grad: 0.0747 (0.0751) loss: 0.8302 (0.8292) time: 0.1500 data: 0.0731 max mem: 9390 +Train: [34] [5400/6250] eta: 0:02:03 lr: 0.000097 grad: 0.0711 (0.0751) loss: 0.8282 (0.8292) time: 0.1656 data: 0.0812 max mem: 9390 +Train: [34] [5500/6250] eta: 0:01:49 lr: 0.000097 grad: 0.0747 (0.0751) loss: 0.8292 (0.8292) time: 0.1690 data: 0.0919 max mem: 9390 +Train: [34] [5600/6250] eta: 0:01:34 lr: 0.000097 grad: 0.0765 (0.0751) loss: 0.8273 (0.8292) time: 0.1511 data: 0.0734 max mem: 9390 +Train: [34] [5700/6250] eta: 0:01:19 lr: 0.000097 grad: 0.0726 (0.0751) loss: 0.8279 (0.8292) time: 0.1357 data: 0.0580 max mem: 9390 +Train: [34] [5800/6250] eta: 0:01:05 lr: 0.000097 grad: 0.0685 (0.0752) loss: 0.8319 (0.8292) time: 0.1426 data: 0.0613 max mem: 9390 +Train: [34] [5900/6250] eta: 0:00:50 lr: 0.000097 grad: 0.0795 (0.0752) loss: 0.8259 (0.8291) time: 0.1315 data: 0.0500 max mem: 9390 +Train: [34] [6000/6250] eta: 0:00:36 lr: 0.000097 grad: 0.0732 (0.0753) loss: 0.8293 (0.8291) time: 0.1294 data: 0.0484 max mem: 9390 +Train: [34] [6100/6250] eta: 0:00:21 lr: 0.000097 grad: 0.0765 (0.0753) loss: 0.8268 (0.8290) time: 0.1169 data: 0.0366 max mem: 9390 +Train: [34] [6200/6250] eta: 0:00:07 lr: 0.000097 grad: 0.0756 (0.0754) loss: 0.8283 (0.8290) time: 0.1295 data: 0.0535 max mem: 9390 +Train: [34] [6249/6250] eta: 0:00:00 lr: 0.000097 grad: 0.0744 (0.0754) loss: 0.8331 (0.8289) time: 0.1399 data: 0.0649 max mem: 9390 +Train: [34] Total time: 0:15:06 (0.1451 s / it) +Averaged stats: lr: 0.000097 grad: 0.0744 (0.0754) loss: 0.8331 (0.8289) +Eval (hcp-train-subset): [34] [ 0/62] eta: 0:03:39 loss: 0.8487 (0.8487) time: 3.5455 data: 3.4559 max mem: 9390 +Eval (hcp-train-subset): [34] [61/62] eta: 0:00:00 loss: 0.8412 (0.8414) time: 0.1062 data: 0.0800 max mem: 9390 +Eval (hcp-train-subset): [34] Total time: 0:00:12 (0.2022 s / it) +Averaged stats (hcp-train-subset): loss: 0.8412 (0.8414) +Making plots (hcp-train-subset): example=44 +Eval (hcp-val): [34] [ 0/62] eta: 0:03:05 loss: 0.8337 (0.8337) time: 2.9866 data: 2.9108 max mem: 9390 +Eval (hcp-val): [34] [61/62] eta: 0:00:00 loss: 0.8375 (0.8378) time: 0.1182 data: 0.0910 max mem: 9390 +Eval (hcp-val): [34] Total time: 0:00:12 (0.2023 s / it) +Averaged stats (hcp-val): loss: 0.8375 (0.8378) +Making plots (hcp-val): example=49 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +Train: [35] [ 0/6250] eta: 8:24:14 lr: 0.000097 grad: 0.1100 (0.1100) loss: 0.8611 (0.8611) time: 4.8407 data: 4.7015 max mem: 9390 +Train: [35] [ 100/6250] eta: 0:19:25 lr: 0.000097 grad: 0.0734 (0.0824) loss: 0.8385 (0.8435) time: 0.1468 data: 0.0640 max mem: 9390 +Train: [35] [ 200/6250] eta: 0:16:43 lr: 0.000097 grad: 0.0727 (0.0786) loss: 0.8313 (0.8368) time: 0.1532 data: 0.0775 max mem: 9390 +Train: [35] [ 300/6250] eta: 0:15:15 lr: 0.000097 grad: 0.0670 (0.0766) loss: 0.8327 (0.8354) time: 0.1386 data: 0.0583 max mem: 9390 +Train: [35] [ 400/6250] eta: 0:14:32 lr: 0.000097 grad: 0.0693 (0.0756) loss: 0.8309 (0.8343) time: 0.1374 data: 0.0588 max mem: 9390 +Train: [35] [ 500/6250] eta: 0:13:48 lr: 0.000097 grad: 0.0710 (0.0754) loss: 0.8274 (0.8335) time: 0.1091 data: 0.0285 max mem: 9390 +Train: [35] [ 600/6250] eta: 0:13:22 lr: 0.000097 grad: 0.0714 (0.0751) loss: 0.8227 (0.8323) time: 0.1404 data: 0.0525 max mem: 9390 +Train: [35] [ 700/6250] eta: 0:12:59 lr: 0.000096 grad: 0.0691 (0.0748) loss: 0.8309 (0.8318) time: 0.1152 data: 0.0334 max mem: 9390 +Train: [35] [ 800/6250] eta: 0:12:37 lr: 0.000096 grad: 0.0717 (0.0749) loss: 0.8352 (0.8318) time: 0.1270 data: 0.0359 max mem: 9390 +Train: [35] [ 900/6250] eta: 0:12:28 lr: 0.000096 grad: 0.0755 (0.0748) loss: 0.8292 (0.8316) time: 0.1494 data: 0.0707 max mem: 9390 +Train: [35] [1000/6250] eta: 0:12:20 lr: 0.000096 grad: 0.0702 (0.0746) loss: 0.8337 (0.8317) time: 0.1592 data: 0.0808 max mem: 9390 +Train: [35] [1100/6250] eta: 0:12:05 lr: 0.000096 grad: 0.0695 (0.0744) loss: 0.8307 (0.8315) time: 0.1230 data: 0.0446 max mem: 9390 +Train: [35] [1200/6250] eta: 0:11:51 lr: 0.000096 grad: 0.0738 (0.0744) loss: 0.8285 (0.8311) time: 0.1501 data: 0.0697 max mem: 9390 +Train: [35] [1300/6250] eta: 0:11:32 lr: 0.000096 grad: 0.0727 (0.0745) loss: 0.8315 (0.8309) time: 0.1238 data: 0.0405 max mem: 9390 +Train: [35] [1400/6250] eta: 0:11:17 lr: 0.000096 grad: 0.0733 (0.0745) loss: 0.8218 (0.8307) time: 0.1598 data: 0.0763 max mem: 9390 +Train: [35] [1500/6250] eta: 0:11:04 lr: 0.000096 grad: 0.0706 (0.0746) loss: 0.8300 (0.8303) time: 0.1548 data: 0.0776 max mem: 9390 +Train: [35] [1600/6250] eta: 0:10:52 lr: 0.000096 grad: 0.0741 (0.0747) loss: 0.8206 (0.8301) time: 0.1552 data: 0.0783 max mem: 9390 +Train: [35] [1700/6250] eta: 0:10:40 lr: 0.000096 grad: 0.0793 (0.0748) loss: 0.8222 (0.8299) time: 0.1545 data: 0.0732 max mem: 9390 +Train: [35] [1800/6250] eta: 0:10:30 lr: 0.000096 grad: 0.0727 (0.0750) loss: 0.8323 (0.8298) time: 0.1314 data: 0.0515 max mem: 9390 +Train: [35] [1900/6250] eta: 0:10:18 lr: 0.000096 grad: 0.0758 (0.0751) loss: 0.8242 (0.8296) time: 0.1410 data: 0.0539 max mem: 9390 +Train: [35] [2000/6250] eta: 0:10:05 lr: 0.000096 grad: 0.0778 (0.0753) loss: 0.8191 (0.8294) time: 0.1427 data: 0.0586 max mem: 9390 +Train: [35] [2100/6250] eta: 0:09:49 lr: 0.000096 grad: 0.0787 (0.0755) loss: 0.8226 (0.8291) time: 0.1293 data: 0.0513 max mem: 9390 +Train: [35] [2200/6250] eta: 0:09:35 lr: 0.000096 grad: 0.0773 (0.0756) loss: 0.8275 (0.8290) time: 0.1541 data: 0.0747 max mem: 9390 +Train: [35] [2300/6250] eta: 0:09:23 lr: 0.000096 grad: 0.0695 (0.0758) loss: 0.8258 (0.8288) time: 0.1836 data: 0.1021 max mem: 9390 +Train: [35] [2400/6250] eta: 0:09:09 lr: 0.000096 grad: 0.0776 (0.0758) loss: 0.8237 (0.8287) time: 0.1531 data: 0.0710 max mem: 9390 +Train: [35] [2500/6250] eta: 0:08:56 lr: 0.000096 grad: 0.0849 (0.0760) loss: 0.8180 (0.8285) time: 0.1206 data: 0.0436 max mem: 9390 +Train: [35] [2600/6250] eta: 0:08:42 lr: 0.000096 grad: 0.0716 (0.0762) loss: 0.8269 (0.8285) time: 0.1421 data: 0.0597 max mem: 9390 +Train: [35] [2700/6250] eta: 0:08:28 lr: 0.000096 grad: 0.0778 (0.0764) loss: 0.8194 (0.8283) time: 0.1523 data: 0.0750 max mem: 9390 +Train: [35] [2800/6250] eta: 0:08:14 lr: 0.000096 grad: 0.0807 (0.0766) loss: 0.8281 (0.8282) time: 0.1341 data: 0.0573 max mem: 9390 +Train: [35] [2900/6250] eta: 0:08:00 lr: 0.000096 grad: 0.0819 (0.0768) loss: 0.8265 (0.8281) time: 0.1491 data: 0.0714 max mem: 9390 +Train: [35] [3000/6250] eta: 0:07:45 lr: 0.000096 grad: 0.0795 (0.0771) loss: 0.8262 (0.8280) time: 0.1396 data: 0.0647 max mem: 9390 +Train: [35] [3100/6250] eta: 0:07:30 lr: 0.000096 grad: 0.0718 (0.0771) loss: 0.8298 (0.8279) time: 0.1296 data: 0.0493 max mem: 9390 +Train: [35] [3200/6250] eta: 0:07:16 lr: 0.000096 grad: 0.0773 (0.0772) loss: 0.8242 (0.8278) time: 0.1324 data: 0.0500 max mem: 9390 +Train: [35] [3300/6250] eta: 0:07:02 lr: 0.000096 grad: 0.0758 (0.0772) loss: 0.8258 (0.8278) time: 0.1359 data: 0.0595 max mem: 9390 +Train: [35] [3400/6250] eta: 0:06:47 lr: 0.000096 grad: 0.0715 (0.0773) loss: 0.8225 (0.8277) time: 0.1498 data: 0.0610 max mem: 9390 +Train: [35] [3500/6250] eta: 0:06:33 lr: 0.000096 grad: 0.0804 (0.0773) loss: 0.8184 (0.8276) time: 0.1330 data: 0.0512 max mem: 9390 +Train: [35] [3600/6250] eta: 0:06:18 lr: 0.000096 grad: 0.0844 (0.0774) loss: 0.8182 (0.8274) time: 0.1266 data: 0.0455 max mem: 9390 +Train: [35] [3700/6250] eta: 0:06:04 lr: 0.000096 grad: 0.0744 (0.0775) loss: 0.8247 (0.8273) time: 0.1602 data: 0.0830 max mem: 9390 +Train: [35] [3800/6250] eta: 0:05:50 lr: 0.000096 grad: 0.0767 (0.0776) loss: 0.8254 (0.8272) time: 0.1408 data: 0.0575 max mem: 9390 +Train: [35] [3900/6250] eta: 0:05:36 lr: 0.000096 grad: 0.0746 (0.0777) loss: 0.8216 (0.8271) time: 0.1297 data: 0.0498 max mem: 9390 +Train: [35] [4000/6250] eta: 0:05:22 lr: 0.000096 grad: 0.0776 (0.0778) loss: 0.8287 (0.8270) time: 0.1259 data: 0.0456 max mem: 9390 +Train: [35] [4100/6250] eta: 0:05:07 lr: 0.000096 grad: 0.0800 (0.0779) loss: 0.8241 (0.8269) time: 0.1581 data: 0.0816 max mem: 9390 +Train: [35] [4200/6250] eta: 0:04:53 lr: 0.000096 grad: 0.0736 (0.0779) loss: 0.8274 (0.8268) time: 0.1191 data: 0.0362 max mem: 9390 +Train: [35] [4300/6250] eta: 0:04:38 lr: 0.000095 grad: 0.0746 (0.0780) loss: 0.8249 (0.8267) time: 0.1493 data: 0.0676 max mem: 9390 +Train: [35] [4400/6250] eta: 0:04:24 lr: 0.000095 grad: 0.0792 (0.0781) loss: 0.8273 (0.8266) time: 0.1513 data: 0.0720 max mem: 9390 +Train: [35] [4500/6250] eta: 0:04:10 lr: 0.000095 grad: 0.0830 (0.0782) loss: 0.8157 (0.8265) time: 0.1646 data: 0.0773 max mem: 9390 +Train: [35] [4600/6250] eta: 0:03:55 lr: 0.000095 grad: 0.0764 (0.0784) loss: 0.8236 (0.8264) time: 0.1423 data: 0.0480 max mem: 9390 +Train: [35] [4700/6250] eta: 0:03:41 lr: 0.000095 grad: 0.0863 (0.0785) loss: 0.8175 (0.8263) time: 0.1469 data: 0.0663 max mem: 9390 +Train: [35] [4800/6250] eta: 0:03:27 lr: 0.000095 grad: 0.0772 (0.0786) loss: 0.8216 (0.8262) time: 0.1494 data: 0.0659 max mem: 9390 +Train: [35] [4900/6250] eta: 0:03:13 lr: 0.000095 grad: 0.0834 (0.0787) loss: 0.8149 (0.8261) time: 0.1581 data: 0.0730 max mem: 9390 +Train: [35] [5000/6250] eta: 0:02:59 lr: 0.000095 grad: 0.0791 (0.0787) loss: 0.8200 (0.8260) time: 0.1311 data: 0.0518 max mem: 9390 +Train: [35] [5100/6250] eta: 0:02:45 lr: 0.000095 grad: 0.0772 (0.0788) loss: 0.8209 (0.8259) time: 0.1372 data: 0.0521 max mem: 9390 +Train: [35] [5200/6250] eta: 0:02:31 lr: 0.000095 grad: 0.0796 (0.0790) loss: 0.8247 (0.8258) time: 0.1454 data: 0.0584 max mem: 9390 +Train: [35] [5300/6250] eta: 0:02:16 lr: 0.000095 grad: 0.0801 (0.0791) loss: 0.8202 (0.8257) time: 0.1515 data: 0.0737 max mem: 9390 +Train: [35] [5400/6250] eta: 0:02:02 lr: 0.000095 grad: 0.0783 (0.0791) loss: 0.8253 (0.8256) time: 0.1491 data: 0.0690 max mem: 9390 +Train: [35] [5500/6250] eta: 0:01:48 lr: 0.000095 grad: 0.0799 (0.0791) loss: 0.8297 (0.8256) time: 0.1537 data: 0.0696 max mem: 9390 +Train: [35] [5600/6250] eta: 0:01:33 lr: 0.000095 grad: 0.0771 (0.0791) loss: 0.8278 (0.8255) time: 0.1732 data: 0.0905 max mem: 9390 +Train: [35] [5700/6250] eta: 0:01:19 lr: 0.000095 grad: 0.0810 (0.0792) loss: 0.8258 (0.8255) time: 0.1408 data: 0.0641 max mem: 9390 +Train: [35] [5800/6250] eta: 0:01:04 lr: 0.000095 grad: 0.0787 (0.0792) loss: 0.8250 (0.8255) time: 0.1153 data: 0.0311 max mem: 9390 +Train: [35] [5900/6250] eta: 0:00:50 lr: 0.000095 grad: 0.0802 (0.0793) loss: 0.8221 (0.8254) time: 0.1284 data: 0.0503 max mem: 9390 +Train: [35] [6000/6250] eta: 0:00:35 lr: 0.000095 grad: 0.0738 (0.0793) loss: 0.8215 (0.8255) time: 0.1342 data: 0.0532 max mem: 9390 +Train: [35] [6100/6250] eta: 0:00:21 lr: 0.000095 grad: 0.0753 (0.0793) loss: 0.8273 (0.8255) time: 0.1596 data: 0.0756 max mem: 9390 +Train: [35] [6200/6250] eta: 0:00:07 lr: 0.000095 grad: 0.0783 (0.0793) loss: 0.8236 (0.8255) time: 0.1383 data: 0.0666 max mem: 9390 +Train: [35] [6249/6250] eta: 0:00:00 lr: 0.000095 grad: 0.0761 (0.0793) loss: 0.8267 (0.8255) time: 0.1145 data: 0.0345 max mem: 9390 +Train: [35] Total time: 0:15:02 (0.1443 s / it) +Averaged stats: lr: 0.000095 grad: 0.0761 (0.0793) loss: 0.8267 (0.8255) +Eval (hcp-train-subset): [35] [ 0/62] eta: 0:05:15 loss: 0.8542 (0.8542) time: 5.0956 data: 5.0656 max mem: 9390 +Eval (hcp-train-subset): [35] [61/62] eta: 0:00:00 loss: 0.8415 (0.8423) time: 0.1164 data: 0.0914 max mem: 9390 +Eval (hcp-train-subset): [35] Total time: 0:00:12 (0.2007 s / it) +Averaged stats (hcp-train-subset): loss: 0.8415 (0.8423) +Eval (hcp-val): [35] [ 0/62] eta: 0:04:12 loss: 0.8333 (0.8333) time: 4.0663 data: 4.0365 max mem: 9390 +Eval (hcp-val): [35] [61/62] eta: 0:00:00 loss: 0.8365 (0.8383) time: 0.1404 data: 0.1150 max mem: 9390 +Eval (hcp-val): [35] Total time: 0:00:12 (0.2010 s / it) +Averaged stats (hcp-val): loss: 0.8365 (0.8383) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +Train: [36] [ 0/6250] eta: 9:23:47 lr: 0.000095 grad: 0.0673 (0.0673) loss: 0.8682 (0.8682) time: 5.4124 data: 5.2923 max mem: 9390 +Train: [36] [ 100/6250] eta: 0:19:17 lr: 0.000095 grad: 0.0714 (0.0847) loss: 0.8416 (0.8452) time: 0.1437 data: 0.0574 max mem: 9390 +Train: [36] [ 200/6250] eta: 0:16:33 lr: 0.000095 grad: 0.0762 (0.0894) loss: 0.8363 (0.8372) time: 0.1102 data: 0.0296 max mem: 9390 +Train: [36] [ 300/6250] eta: 0:15:32 lr: 0.000095 grad: 0.0743 (0.0870) loss: 0.8266 (0.8334) time: 0.1281 data: 0.0453 max mem: 9390 +Train: [36] [ 400/6250] eta: 0:14:32 lr: 0.000095 grad: 0.0763 (0.0857) loss: 0.8291 (0.8317) time: 0.1383 data: 0.0567 max mem: 9390 +Train: [36] [ 500/6250] eta: 0:13:51 lr: 0.000095 grad: 0.0754 (0.0840) loss: 0.8282 (0.8313) time: 0.1339 data: 0.0504 max mem: 9390 +Train: [36] [ 600/6250] eta: 0:13:20 lr: 0.000095 grad: 0.0707 (0.0825) loss: 0.8375 (0.8312) time: 0.1265 data: 0.0443 max mem: 9390 +Train: [36] [ 700/6250] eta: 0:12:52 lr: 0.000095 grad: 0.0730 (0.0815) loss: 0.8305 (0.8311) time: 0.1153 data: 0.0295 max mem: 9390 +Train: [36] [ 800/6250] eta: 0:12:30 lr: 0.000095 grad: 0.0714 (0.0806) loss: 0.8331 (0.8313) time: 0.1039 data: 0.0245 max mem: 9390 +Train: [36] [ 900/6250] eta: 0:12:18 lr: 0.000095 grad: 0.0713 (0.0799) loss: 0.8301 (0.8313) time: 0.1552 data: 0.0779 max mem: 9390 +Train: [36] [1000/6250] eta: 0:12:07 lr: 0.000095 grad: 0.0706 (0.0791) loss: 0.8341 (0.8314) time: 0.1402 data: 0.0603 max mem: 9390 +Train: [36] [1100/6250] eta: 0:11:52 lr: 0.000095 grad: 0.0723 (0.0785) loss: 0.8316 (0.8314) time: 0.1359 data: 0.0579 max mem: 9390 +Train: [36] [1200/6250] eta: 0:11:36 lr: 0.000095 grad: 0.0740 (0.0780) loss: 0.8306 (0.8314) time: 0.1564 data: 0.0722 max mem: 9390 +Train: [36] [1300/6250] eta: 0:11:19 lr: 0.000095 grad: 0.0727 (0.0777) loss: 0.8309 (0.8315) time: 0.1254 data: 0.0491 max mem: 9390 +Train: [36] [1400/6250] eta: 0:11:05 lr: 0.000095 grad: 0.0778 (0.0776) loss: 0.8309 (0.8315) time: 0.1370 data: 0.0571 max mem: 9390 +Train: [36] [1500/6250] eta: 0:10:53 lr: 0.000095 grad: 0.0723 (0.0775) loss: 0.8322 (0.8314) time: 0.1626 data: 0.0859 max mem: 9390 +Train: [36] [1600/6250] eta: 0:10:43 lr: 0.000094 grad: 0.0769 (0.0774) loss: 0.8325 (0.8313) time: 0.1696 data: 0.0894 max mem: 9390 +Train: [36] [1700/6250] eta: 0:10:29 lr: 0.000094 grad: 0.0745 (0.0774) loss: 0.8295 (0.8312) time: 0.1443 data: 0.0675 max mem: 9390 +Train: [36] [1800/6250] eta: 0:10:18 lr: 0.000094 grad: 0.0752 (0.0774) loss: 0.8264 (0.8311) time: 0.1416 data: 0.0678 max mem: 9390 +Train: [36] [1900/6250] eta: 0:10:07 lr: 0.000094 grad: 0.0757 (0.0774) loss: 0.8313 (0.8310) time: 0.1641 data: 0.0880 max mem: 9390 +Train: [36] [2000/6250] eta: 0:09:54 lr: 0.000094 grad: 0.0757 (0.0774) loss: 0.8291 (0.8309) time: 0.1450 data: 0.0706 max mem: 9390 +Train: [36] [2100/6250] eta: 0:09:40 lr: 0.000094 grad: 0.0779 (0.0775) loss: 0.8227 (0.8306) time: 0.1297 data: 0.0465 max mem: 9390 +Train: [36] [2200/6250] eta: 0:09:27 lr: 0.000094 grad: 0.0727 (0.0774) loss: 0.8279 (0.8305) time: 0.1670 data: 0.0821 max mem: 9390 +Train: [36] [2300/6250] eta: 0:09:13 lr: 0.000094 grad: 0.0756 (0.0774) loss: 0.8264 (0.8304) time: 0.1336 data: 0.0567 max mem: 9390 +Train: [36] [2400/6250] eta: 0:09:00 lr: 0.000094 grad: 0.0804 (0.0774) loss: 0.8307 (0.8303) time: 0.1259 data: 0.0559 max mem: 9390 +Train: [36] [2500/6250] eta: 0:08:48 lr: 0.000094 grad: 0.0711 (0.0773) loss: 0.8297 (0.8303) time: 0.1700 data: 0.0827 max mem: 9390 +Train: [36] [2600/6250] eta: 0:08:35 lr: 0.000094 grad: 0.0706 (0.0773) loss: 0.8284 (0.8302) time: 0.1607 data: 0.0840 max mem: 9390 +Train: [36] [2700/6250] eta: 0:08:21 lr: 0.000094 grad: 0.0748 (0.0773) loss: 0.8308 (0.8302) time: 0.1378 data: 0.0575 max mem: 9390 +Train: [36] [2800/6250] eta: 0:08:07 lr: 0.000094 grad: 0.0691 (0.0772) loss: 0.8288 (0.8302) time: 0.1217 data: 0.0392 max mem: 9390 +Train: [36] [2900/6250] eta: 0:07:55 lr: 0.000094 grad: 0.0732 (0.0772) loss: 0.8272 (0.8301) time: 0.1578 data: 0.0624 max mem: 9390 +Train: [36] [3000/6250] eta: 0:07:42 lr: 0.000094 grad: 0.0774 (0.0772) loss: 0.8263 (0.8302) time: 0.1490 data: 0.0715 max mem: 9390 +Train: [36] [3100/6250] eta: 0:07:28 lr: 0.000094 grad: 0.0736 (0.0771) loss: 0.8321 (0.8302) time: 0.1803 data: 0.1023 max mem: 9390 +Train: [36] [3200/6250] eta: 0:07:15 lr: 0.000094 grad: 0.0777 (0.0772) loss: 0.8214 (0.8301) time: 0.1555 data: 0.0735 max mem: 9390 +Train: [36] [3300/6250] eta: 0:07:03 lr: 0.000094 grad: 0.0774 (0.0772) loss: 0.8288 (0.8300) time: 0.1902 data: 0.0954 max mem: 9390 +Train: [36] [3400/6250] eta: 0:06:49 lr: 0.000094 grad: 0.0762 (0.0772) loss: 0.8314 (0.8300) time: 0.1644 data: 0.0886 max mem: 9390 +Train: [36] [3500/6250] eta: 0:06:35 lr: 0.000094 grad: 0.0792 (0.0772) loss: 0.8285 (0.8299) time: 0.1248 data: 0.0421 max mem: 9390 +Train: [36] [3600/6250] eta: 0:06:21 lr: 0.000094 grad: 0.0849 (0.0773) loss: 0.8308 (0.8299) time: 0.1607 data: 0.0733 max mem: 9390 +Train: [36] [3700/6250] eta: 0:06:07 lr: 0.000094 grad: 0.0711 (0.0773) loss: 0.8314 (0.8299) time: 0.1553 data: 0.0774 max mem: 9390 +Train: [36] [3800/6250] eta: 0:05:53 lr: 0.000094 grad: 0.0768 (0.0773) loss: 0.8297 (0.8298) time: 0.1593 data: 0.0848 max mem: 9390 +Train: [36] [3900/6250] eta: 0:05:39 lr: 0.000094 grad: 0.0789 (0.0774) loss: 0.8267 (0.8298) time: 0.1915 data: 0.1079 max mem: 9390 +Train: [36] [4000/6250] eta: 0:05:24 lr: 0.000094 grad: 0.0775 (0.0773) loss: 0.8332 (0.8298) time: 0.1424 data: 0.0648 max mem: 9390 +Train: [36] [4100/6250] eta: 0:05:11 lr: 0.000094 grad: 0.0774 (0.0773) loss: 0.8289 (0.8298) time: 0.1343 data: 0.0581 max mem: 9390 +Train: [36] [4200/6250] eta: 0:04:56 lr: 0.000094 grad: 0.0766 (0.0774) loss: 0.8266 (0.8297) time: 0.1566 data: 0.0709 max mem: 9390 +Train: [36] [4300/6250] eta: 0:04:41 lr: 0.000094 grad: 0.0780 (0.0774) loss: 0.8262 (0.8297) time: 0.1551 data: 0.0802 max mem: 9390 +Train: [36] [4400/6250] eta: 0:04:28 lr: 0.000094 grad: 0.0758 (0.0774) loss: 0.8307 (0.8297) time: 0.1241 data: 0.0417 max mem: 9390 +Train: [36] [4500/6250] eta: 0:04:13 lr: 0.000094 grad: 0.0777 (0.0774) loss: 0.8273 (0.8297) time: 0.1848 data: 0.1024 max mem: 9390 +Train: [36] [4600/6250] eta: 0:03:59 lr: 0.000094 grad: 0.0778 (0.0774) loss: 0.8228 (0.8296) time: 0.1375 data: 0.0567 max mem: 9390 +Train: [36] [4700/6250] eta: 0:03:44 lr: 0.000094 grad: 0.0738 (0.0774) loss: 0.8314 (0.8296) time: 0.1373 data: 0.0531 max mem: 9390 +Train: [36] [4800/6250] eta: 0:03:29 lr: 0.000094 grad: 0.0768 (0.0774) loss: 0.8260 (0.8296) time: 0.1440 data: 0.0640 max mem: 9390 +Train: [36] [4900/6250] eta: 0:03:15 lr: 0.000094 grad: 0.0751 (0.0774) loss: 0.8300 (0.8296) time: 0.1438 data: 0.0596 max mem: 9390 +Train: [36] [5000/6250] eta: 0:03:01 lr: 0.000094 grad: 0.0812 (0.0774) loss: 0.8282 (0.8296) time: 0.1314 data: 0.0530 max mem: 9390 +Train: [36] [5100/6250] eta: 0:02:47 lr: 0.000093 grad: 0.0774 (0.0775) loss: 0.8287 (0.8295) time: 0.1816 data: 0.0952 max mem: 9390 +Train: [36] [5200/6250] eta: 0:02:32 lr: 0.000093 grad: 0.0766 (0.0776) loss: 0.8302 (0.8295) time: 0.1406 data: 0.0637 max mem: 9390 +Train: [36] [5300/6250] eta: 0:02:18 lr: 0.000093 grad: 0.0734 (0.0776) loss: 0.8299 (0.8295) time: 0.1683 data: 0.0817 max mem: 9390 +Train: [36] [5400/6250] eta: 0:02:04 lr: 0.000093 grad: 0.0788 (0.0776) loss: 0.8220 (0.8294) time: 0.1396 data: 0.0548 max mem: 9390 +Train: [36] [5500/6250] eta: 0:01:49 lr: 0.000093 grad: 0.0828 (0.0777) loss: 0.8267 (0.8294) time: 0.1469 data: 0.0661 max mem: 9390 +Train: [36] [5600/6250] eta: 0:01:34 lr: 0.000093 grad: 0.0713 (0.0777) loss: 0.8292 (0.8293) time: 0.1372 data: 0.0543 max mem: 9390 +Train: [36] [5700/6250] eta: 0:01:20 lr: 0.000093 grad: 0.0809 (0.0778) loss: 0.8263 (0.8292) time: 0.0924 data: 0.0022 max mem: 9390 +Train: [36] [5800/6250] eta: 0:01:05 lr: 0.000093 grad: 0.0770 (0.0779) loss: 0.8279 (0.8291) time: 0.1260 data: 0.0462 max mem: 9390 +Train: [36] [5900/6250] eta: 0:00:50 lr: 0.000093 grad: 0.0808 (0.0779) loss: 0.8209 (0.8291) time: 0.1540 data: 0.0764 max mem: 9390 +Train: [36] [6000/6250] eta: 0:00:36 lr: 0.000093 grad: 0.0723 (0.0779) loss: 0.8286 (0.8290) time: 0.1509 data: 0.0677 max mem: 9390 +Train: [36] [6100/6250] eta: 0:00:21 lr: 0.000093 grad: 0.0840 (0.0780) loss: 0.8238 (0.8289) time: 0.1337 data: 0.0550 max mem: 9390 +Train: [36] [6200/6250] eta: 0:00:07 lr: 0.000093 grad: 0.0801 (0.0781) loss: 0.8278 (0.8288) time: 0.1288 data: 0.0520 max mem: 9390 +Train: [36] [6249/6250] eta: 0:00:00 lr: 0.000093 grad: 0.0797 (0.0781) loss: 0.8218 (0.8288) time: 0.1659 data: 0.0881 max mem: 9390 +Train: [36] Total time: 0:15:08 (0.1453 s / it) +Averaged stats: lr: 0.000093 grad: 0.0797 (0.0781) loss: 0.8218 (0.8288) +Eval (hcp-train-subset): [36] [ 0/62] eta: 0:04:28 loss: 0.8531 (0.8531) time: 4.3351 data: 4.3001 max mem: 9390 +Eval (hcp-train-subset): [36] [61/62] eta: 0:00:00 loss: 0.8399 (0.8413) time: 0.1180 data: 0.0932 max mem: 9390 +Eval (hcp-train-subset): [36] Total time: 0:00:12 (0.2015 s / it) +Averaged stats (hcp-train-subset): loss: 0.8399 (0.8413) +Eval (hcp-val): [36] [ 0/62] eta: 0:03:53 loss: 0.8367 (0.8367) time: 3.7737 data: 3.7065 max mem: 9390 +Eval (hcp-val): [36] [61/62] eta: 0:00:00 loss: 0.8366 (0.8377) time: 0.1319 data: 0.1068 max mem: 9390 +Eval (hcp-val): [36] Total time: 0:00:12 (0.2036 s / it) +Averaged stats (hcp-val): loss: 0.8366 (0.8377) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +Train: [37] [ 0/6250] eta: 9:25:51 lr: 0.000093 grad: 0.0508 (0.0508) loss: 0.8680 (0.8680) time: 5.4322 data: 5.2857 max mem: 9390 +Train: [37] [ 100/6250] eta: 0:19:47 lr: 0.000093 grad: 0.0738 (0.0961) loss: 0.8286 (0.8370) time: 0.1392 data: 0.0452 max mem: 9390 +Train: [37] [ 200/6250] eta: 0:17:15 lr: 0.000093 grad: 0.0773 (0.0944) loss: 0.8221 (0.8324) time: 0.1425 data: 0.0571 max mem: 9390 +Train: [37] [ 300/6250] eta: 0:15:48 lr: 0.000093 grad: 0.0721 (0.0930) loss: 0.8262 (0.8298) time: 0.1339 data: 0.0466 max mem: 9390 +Train: [37] [ 400/6250] eta: 0:15:01 lr: 0.000093 grad: 0.0735 (0.0895) loss: 0.8254 (0.8285) time: 0.1279 data: 0.0429 max mem: 9390 +Train: [37] [ 500/6250] eta: 0:14:19 lr: 0.000093 grad: 0.0795 (0.0873) loss: 0.8301 (0.8278) time: 0.1153 data: 0.0373 max mem: 9390 +Train: [37] [ 600/6250] eta: 0:13:41 lr: 0.000093 grad: 0.0736 (0.0852) loss: 0.8295 (0.8278) time: 0.1281 data: 0.0484 max mem: 9390 +Train: [37] [ 700/6250] eta: 0:13:12 lr: 0.000093 grad: 0.0745 (0.0834) loss: 0.8302 (0.8277) time: 0.1152 data: 0.0326 max mem: 9390 +Train: [37] [ 800/6250] eta: 0:12:53 lr: 0.000093 grad: 0.0705 (0.0823) loss: 0.8284 (0.8274) time: 0.1399 data: 0.0605 max mem: 9390 +Train: [37] [ 900/6250] eta: 0:12:39 lr: 0.000093 grad: 0.0782 (0.0813) loss: 0.8262 (0.8273) time: 0.1456 data: 0.0608 max mem: 9390 +Train: [37] [1000/6250] eta: 0:12:23 lr: 0.000093 grad: 0.0697 (0.0805) loss: 0.8265 (0.8274) time: 0.1251 data: 0.0442 max mem: 9390 +Train: [37] [1100/6250] eta: 0:12:07 lr: 0.000093 grad: 0.0755 (0.0801) loss: 0.8226 (0.8274) time: 0.1445 data: 0.0626 max mem: 9390 +Train: [37] [1200/6250] eta: 0:11:53 lr: 0.000093 grad: 0.0747 (0.0797) loss: 0.8252 (0.8275) time: 0.1389 data: 0.0557 max mem: 9390 +Train: [37] [1300/6250] eta: 0:11:38 lr: 0.000093 grad: 0.0693 (0.0793) loss: 0.8204 (0.8275) time: 0.1399 data: 0.0527 max mem: 9390 +Train: [37] [1400/6250] eta: 0:11:24 lr: 0.000093 grad: 0.0744 (0.0791) loss: 0.8262 (0.8275) time: 0.1338 data: 0.0478 max mem: 9390 +Train: [37] [1500/6250] eta: 0:11:12 lr: 0.000093 grad: 0.0737 (0.0790) loss: 0.8284 (0.8274) time: 0.1492 data: 0.0690 max mem: 9390 +Train: [37] [1600/6250] eta: 0:11:00 lr: 0.000093 grad: 0.0787 (0.0789) loss: 0.8267 (0.8274) time: 0.1350 data: 0.0533 max mem: 9390 +Train: [37] [1700/6250] eta: 0:10:49 lr: 0.000093 grad: 0.0765 (0.0789) loss: 0.8232 (0.8274) time: 0.1705 data: 0.0920 max mem: 9390 +Train: [37] [1800/6250] eta: 0:10:36 lr: 0.000093 grad: 0.0786 (0.0789) loss: 0.8298 (0.8273) time: 0.1433 data: 0.0696 max mem: 9390 +Train: [37] [1900/6250] eta: 0:10:22 lr: 0.000093 grad: 0.0717 (0.0788) loss: 0.8272 (0.8272) time: 0.1410 data: 0.0641 max mem: 9390 +Train: [37] [2000/6250] eta: 0:10:10 lr: 0.000093 grad: 0.0751 (0.0787) loss: 0.8181 (0.8272) time: 0.1657 data: 0.0800 max mem: 9390 +Train: [37] [2100/6250] eta: 0:10:01 lr: 0.000093 grad: 0.0759 (0.0786) loss: 0.8259 (0.8271) time: 0.1798 data: 0.1049 max mem: 9390 +Train: [37] [2200/6250] eta: 0:09:46 lr: 0.000093 grad: 0.0712 (0.0785) loss: 0.8207 (0.8270) time: 0.1443 data: 0.0632 max mem: 9390 +Train: [37] [2300/6250] eta: 0:09:33 lr: 0.000092 grad: 0.0724 (0.0785) loss: 0.8270 (0.8270) time: 0.1372 data: 0.0600 max mem: 9390 +Train: [37] [2400/6250] eta: 0:09:19 lr: 0.000092 grad: 0.0786 (0.0785) loss: 0.8195 (0.8268) time: 0.1579 data: 0.0713 max mem: 9390 +Train: [37] [2500/6250] eta: 0:09:05 lr: 0.000092 grad: 0.0750 (0.0785) loss: 0.8223 (0.8267) time: 0.1591 data: 0.0784 max mem: 9390 +Train: [37] [2600/6250] eta: 0:08:51 lr: 0.000092 grad: 0.0740 (0.0786) loss: 0.8254 (0.8266) time: 0.1607 data: 0.0790 max mem: 9390 +Train: [37] [2700/6250] eta: 0:08:36 lr: 0.000092 grad: 0.0779 (0.0785) loss: 0.8204 (0.8264) time: 0.1462 data: 0.0679 max mem: 9390 +Train: [37] [2800/6250] eta: 0:08:21 lr: 0.000092 grad: 0.0737 (0.0786) loss: 0.8287 (0.8263) time: 0.1269 data: 0.0451 max mem: 9390 +Train: [37] [2900/6250] eta: 0:08:05 lr: 0.000092 grad: 0.0812 (0.0786) loss: 0.8146 (0.8262) time: 0.1306 data: 0.0542 max mem: 9390 +Train: [37] [3000/6250] eta: 0:07:51 lr: 0.000092 grad: 0.0763 (0.0788) loss: 0.8205 (0.8260) time: 0.1484 data: 0.0684 max mem: 9390 +Train: [37] [3100/6250] eta: 0:07:37 lr: 0.000092 grad: 0.0751 (0.0789) loss: 0.8280 (0.8260) time: 0.1730 data: 0.0949 max mem: 9390 +Train: [37] [3200/6250] eta: 0:07:23 lr: 0.000092 grad: 0.0769 (0.0789) loss: 0.8247 (0.8259) time: 0.1622 data: 0.0736 max mem: 9390 +Train: [37] [3300/6250] eta: 0:07:12 lr: 0.000092 grad: 0.0771 (0.0789) loss: 0.8218 (0.8258) time: 0.1226 data: 0.0413 max mem: 9390 +Train: [37] [3400/6250] eta: 0:06:56 lr: 0.000092 grad: 0.0769 (0.0790) loss: 0.8251 (0.8257) time: 0.1174 data: 0.0457 max mem: 9390 +Train: [37] [3500/6250] eta: 0:06:41 lr: 0.000092 grad: 0.0825 (0.0792) loss: 0.8233 (0.8255) time: 0.1395 data: 0.0541 max mem: 9390 +Train: [37] [3600/6250] eta: 0:06:27 lr: 0.000092 grad: 0.0894 (0.0793) loss: 0.8197 (0.8255) time: 0.1546 data: 0.0715 max mem: 9390 +Train: [37] [3700/6250] eta: 0:06:12 lr: 0.000092 grad: 0.0772 (0.0793) loss: 0.8212 (0.8254) time: 0.1517 data: 0.0699 max mem: 9390 +Train: [37] [3800/6250] eta: 0:05:57 lr: 0.000092 grad: 0.0832 (0.0793) loss: 0.8219 (0.8253) time: 0.1490 data: 0.0752 max mem: 9390 +Train: [37] [3900/6250] eta: 0:05:44 lr: 0.000092 grad: 0.0717 (0.0793) loss: 0.8278 (0.8253) time: 0.2670 data: 0.1736 max mem: 9390 +Train: [37] [4000/6250] eta: 0:05:28 lr: 0.000092 grad: 0.0732 (0.0793) loss: 0.8255 (0.8253) time: 0.1397 data: 0.0596 max mem: 9390 +Train: [37] [4100/6250] eta: 0:05:14 lr: 0.000092 grad: 0.0755 (0.0793) loss: 0.8250 (0.8253) time: 0.1602 data: 0.0805 max mem: 9390 +Train: [37] [4200/6250] eta: 0:04:59 lr: 0.000092 grad: 0.0771 (0.0793) loss: 0.8275 (0.8253) time: 0.1535 data: 0.0672 max mem: 9390 +Train: [37] [4300/6250] eta: 0:04:45 lr: 0.000092 grad: 0.0715 (0.0793) loss: 0.8239 (0.8254) time: 0.1416 data: 0.0521 max mem: 9390 +Train: [37] [4400/6250] eta: 0:04:30 lr: 0.000092 grad: 0.0762 (0.0792) loss: 0.8328 (0.8254) time: 0.1240 data: 0.0411 max mem: 9390 +Train: [37] [4500/6250] eta: 0:04:15 lr: 0.000092 grad: 0.0731 (0.0792) loss: 0.8245 (0.8254) time: 0.1538 data: 0.0841 max mem: 9390 +Train: [37] [4600/6250] eta: 0:04:00 lr: 0.000092 grad: 0.0745 (0.0791) loss: 0.8307 (0.8256) time: 0.1732 data: 0.0968 max mem: 9390 +Train: [37] [4700/6250] eta: 0:03:46 lr: 0.000092 grad: 0.0728 (0.0791) loss: 0.8277 (0.8256) time: 0.1581 data: 0.0757 max mem: 9390 +Train: [37] [4800/6250] eta: 0:03:31 lr: 0.000092 grad: 0.0762 (0.0791) loss: 0.8320 (0.8256) time: 0.1329 data: 0.0527 max mem: 9390 +Train: [37] [4900/6250] eta: 0:03:17 lr: 0.000092 grad: 0.0743 (0.0791) loss: 0.8289 (0.8257) time: 0.1451 data: 0.0680 max mem: 9390 +Train: [37] [5000/6250] eta: 0:03:03 lr: 0.000092 grad: 0.0741 (0.0791) loss: 0.8283 (0.8258) time: 0.1559 data: 0.0794 max mem: 9390 +Train: [37] [5100/6250] eta: 0:02:48 lr: 0.000092 grad: 0.0766 (0.0790) loss: 0.8320 (0.8258) time: 0.1931 data: 0.1137 max mem: 9390 +Train: [37] [5200/6250] eta: 0:02:34 lr: 0.000092 grad: 0.0765 (0.0791) loss: 0.8260 (0.8258) time: 0.1379 data: 0.0580 max mem: 9390 +Train: [37] [5300/6250] eta: 0:02:19 lr: 0.000092 grad: 0.0781 (0.0791) loss: 0.8248 (0.8258) time: 0.1490 data: 0.0662 max mem: 9390 +Train: [37] [5400/6250] eta: 0:02:04 lr: 0.000092 grad: 0.0711 (0.0791) loss: 0.8329 (0.8258) time: 0.1586 data: 0.0820 max mem: 9390 +Train: [37] [5500/6250] eta: 0:01:50 lr: 0.000092 grad: 0.0789 (0.0791) loss: 0.8279 (0.8258) time: 0.1377 data: 0.0586 max mem: 9390 +Train: [37] [5600/6250] eta: 0:01:35 lr: 0.000092 grad: 0.0827 (0.0791) loss: 0.8272 (0.8259) time: 0.1376 data: 0.0554 max mem: 9390 +Train: [37] [5700/6250] eta: 0:01:20 lr: 0.000091 grad: 0.0790 (0.0791) loss: 0.8235 (0.8259) time: 0.1208 data: 0.0380 max mem: 9390 +Train: [37] [5800/6250] eta: 0:01:05 lr: 0.000091 grad: 0.0746 (0.0791) loss: 0.8221 (0.8259) time: 0.1263 data: 0.0431 max mem: 9390 +Train: [37] [5900/6250] eta: 0:00:50 lr: 0.000091 grad: 0.0768 (0.0792) loss: 0.8275 (0.8258) time: 0.1211 data: 0.0357 max mem: 9390 +Train: [37] [6000/6250] eta: 0:00:36 lr: 0.000091 grad: 0.0741 (0.0793) loss: 0.8214 (0.8258) time: 0.1541 data: 0.0734 max mem: 9390 +Train: [37] [6100/6250] eta: 0:00:21 lr: 0.000091 grad: 0.0804 (0.0793) loss: 0.8218 (0.8258) time: 0.1350 data: 0.0527 max mem: 9390 +Train: [37] [6200/6250] eta: 0:00:07 lr: 0.000091 grad: 0.0775 (0.0793) loss: 0.8237 (0.8258) time: 0.1727 data: 0.0922 max mem: 9390 +Train: [37] [6249/6250] eta: 0:00:00 lr: 0.000091 grad: 0.0774 (0.0793) loss: 0.8224 (0.8258) time: 0.1385 data: 0.0611 max mem: 9390 +Train: [37] Total time: 0:15:12 (0.1460 s / it) +Averaged stats: lr: 0.000091 grad: 0.0774 (0.0793) loss: 0.8224 (0.8258) +Eval (hcp-train-subset): [37] [ 0/62] eta: 0:04:39 loss: 0.8545 (0.8545) time: 4.5074 data: 4.4775 max mem: 9390 +Eval (hcp-train-subset): [37] [61/62] eta: 0:00:00 loss: 0.8393 (0.8403) time: 0.1073 data: 0.0825 max mem: 9390 +Eval (hcp-train-subset): [37] Total time: 0:00:12 (0.1960 s / it) +Averaged stats (hcp-train-subset): loss: 0.8393 (0.8403) +Eval (hcp-val): [37] [ 0/62] eta: 0:03:20 loss: 0.8329 (0.8329) time: 3.2310 data: 3.1522 max mem: 9390 +Eval (hcp-val): [37] [61/62] eta: 0:00:00 loss: 0.8373 (0.8375) time: 0.1368 data: 0.1117 max mem: 9390 +Eval (hcp-val): [37] Total time: 0:00:12 (0.2016 s / it) +Averaged stats (hcp-val): loss: 0.8373 (0.8375) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +Train: [38] [ 0/6250] eta: 7:57:43 lr: 0.000091 grad: 0.1090 (0.1090) loss: 0.8910 (0.8910) time: 4.5862 data: 4.3490 max mem: 9390 +Train: [38] [ 100/6250] eta: 0:20:04 lr: 0.000091 grad: 0.0843 (0.0846) loss: 0.8355 (0.8428) time: 0.1636 data: 0.0764 max mem: 9390 +Train: [38] [ 200/6250] eta: 0:17:07 lr: 0.000091 grad: 0.0777 (0.0807) loss: 0.8212 (0.8353) time: 0.1552 data: 0.0708 max mem: 9390 +Train: [38] [ 300/6250] eta: 0:15:55 lr: 0.000091 grad: 0.0764 (0.0799) loss: 0.8167 (0.8320) time: 0.1449 data: 0.0670 max mem: 9390 +Train: [38] [ 400/6250] eta: 0:14:55 lr: 0.000091 grad: 0.0809 (0.0800) loss: 0.8216 (0.8292) time: 0.1240 data: 0.0399 max mem: 9390 +Train: [38] [ 500/6250] eta: 0:14:18 lr: 0.000091 grad: 0.0767 (0.0799) loss: 0.8138 (0.8269) time: 0.1347 data: 0.0537 max mem: 9390 +Train: [38] [ 600/6250] eta: 0:13:45 lr: 0.000091 grad: 0.0773 (0.0793) loss: 0.8191 (0.8261) time: 0.1491 data: 0.0670 max mem: 9390 +Train: [38] [ 700/6250] eta: 0:13:08 lr: 0.000091 grad: 0.0760 (0.0790) loss: 0.8231 (0.8258) time: 0.1136 data: 0.0285 max mem: 9390 +Train: [38] [ 800/6250] eta: 0:12:42 lr: 0.000091 grad: 0.0745 (0.0785) loss: 0.8282 (0.8256) time: 0.1278 data: 0.0479 max mem: 9390 +Train: [38] [ 900/6250] eta: 0:12:23 lr: 0.000091 grad: 0.0745 (0.0783) loss: 0.8189 (0.8254) time: 0.1292 data: 0.0520 max mem: 9390 +Train: [38] [1000/6250] eta: 0:12:10 lr: 0.000091 grad: 0.0748 (0.0781) loss: 0.8235 (0.8253) time: 0.1336 data: 0.0512 max mem: 9390 +Train: [38] [1100/6250] eta: 0:11:57 lr: 0.000091 grad: 0.0760 (0.0780) loss: 0.8094 (0.8250) time: 0.1375 data: 0.0571 max mem: 9390 +Train: [38] [1200/6250] eta: 0:11:40 lr: 0.000091 grad: 0.0748 (0.0779) loss: 0.8231 (0.8247) time: 0.1246 data: 0.0458 max mem: 9390 +Train: [38] [1300/6250] eta: 0:11:23 lr: 0.000091 grad: 0.0718 (0.0778) loss: 0.8186 (0.8243) time: 0.1351 data: 0.0571 max mem: 9390 +Train: [38] [1400/6250] eta: 0:11:08 lr: 0.000091 grad: 0.0773 (0.0779) loss: 0.8154 (0.8241) time: 0.1046 data: 0.0219 max mem: 9390 +Train: [38] [1500/6250] eta: 0:10:57 lr: 0.000091 grad: 0.0792 (0.0778) loss: 0.8210 (0.8240) time: 0.1568 data: 0.0768 max mem: 9390 +Train: [38] [1600/6250] eta: 0:10:46 lr: 0.000091 grad: 0.0806 (0.0779) loss: 0.8179 (0.8238) time: 0.1515 data: 0.0743 max mem: 9390 +Train: [38] [1700/6250] eta: 0:10:36 lr: 0.000091 grad: 0.0791 (0.0779) loss: 0.8236 (0.8237) time: 0.1352 data: 0.0537 max mem: 9390 +Train: [38] [1800/6250] eta: 0:10:21 lr: 0.000091 grad: 0.0741 (0.0780) loss: 0.8252 (0.8237) time: 0.1219 data: 0.0399 max mem: 9390 +Train: [38] [1900/6250] eta: 0:10:07 lr: 0.000091 grad: 0.0775 (0.0781) loss: 0.8171 (0.8235) time: 0.1247 data: 0.0417 max mem: 9390 +Train: [38] [2000/6250] eta: 0:09:54 lr: 0.000091 grad: 0.0771 (0.0783) loss: 0.8230 (0.8235) time: 0.1339 data: 0.0560 max mem: 9390 +Train: [38] [2100/6250] eta: 0:09:41 lr: 0.000091 grad: 0.0827 (0.0785) loss: 0.8198 (0.8234) time: 0.1300 data: 0.0497 max mem: 9390 +Train: [38] [2200/6250] eta: 0:09:29 lr: 0.000091 grad: 0.0743 (0.0785) loss: 0.8304 (0.8234) time: 0.1681 data: 0.0867 max mem: 9390 +Train: [38] [2300/6250] eta: 0:09:16 lr: 0.000091 grad: 0.0735 (0.0786) loss: 0.8282 (0.8235) time: 0.1499 data: 0.0693 max mem: 9390 +Train: [38] [2400/6250] eta: 0:09:02 lr: 0.000091 grad: 0.0737 (0.0786) loss: 0.8240 (0.8235) time: 0.1276 data: 0.0516 max mem: 9390 +Train: [38] [2500/6250] eta: 0:08:48 lr: 0.000091 grad: 0.0736 (0.0786) loss: 0.8161 (0.8235) time: 0.1556 data: 0.0756 max mem: 9390 +Train: [38] [2600/6250] eta: 0:08:35 lr: 0.000091 grad: 0.0768 (0.0786) loss: 0.8283 (0.8235) time: 0.1417 data: 0.0641 max mem: 9390 +Train: [38] [2700/6250] eta: 0:08:20 lr: 0.000091 grad: 0.0796 (0.0788) loss: 0.8238 (0.8235) time: 0.1381 data: 0.0534 max mem: 9390 +Train: [38] [2800/6250] eta: 0:08:07 lr: 0.000091 grad: 0.0768 (0.0788) loss: 0.8283 (0.8236) time: 0.1242 data: 0.0439 max mem: 9390 +Train: [38] [2900/6250] eta: 0:07:54 lr: 0.000090 grad: 0.0743 (0.0789) loss: 0.8201 (0.8236) time: 0.1480 data: 0.0695 max mem: 9390 +Train: [38] [3000/6250] eta: 0:07:40 lr: 0.000090 grad: 0.0756 (0.0790) loss: 0.8233 (0.8235) time: 0.1672 data: 0.0848 max mem: 9390 +Train: [38] [3100/6250] eta: 0:07:26 lr: 0.000090 grad: 0.0780 (0.0791) loss: 0.8222 (0.8235) time: 0.1519 data: 0.0780 max mem: 9390 +Train: [38] [3200/6250] eta: 0:07:15 lr: 0.000090 grad: 0.0787 (0.0792) loss: 0.8236 (0.8235) time: 0.1521 data: 0.0663 max mem: 9390 +Train: [38] [3300/6250] eta: 0:07:01 lr: 0.000090 grad: 0.0798 (0.0792) loss: 0.8209 (0.8235) time: 0.1662 data: 0.0863 max mem: 9390 +Train: [38] [3400/6250] eta: 0:06:47 lr: 0.000090 grad: 0.0752 (0.0792) loss: 0.8244 (0.8235) time: 0.1434 data: 0.0675 max mem: 9390 +Train: [38] [3500/6250] eta: 0:06:32 lr: 0.000090 grad: 0.0781 (0.0793) loss: 0.8189 (0.8235) time: 0.1425 data: 0.0653 max mem: 9390 +Train: [38] [3600/6250] eta: 0:06:18 lr: 0.000090 grad: 0.0778 (0.0793) loss: 0.8247 (0.8235) time: 0.1450 data: 0.0604 max mem: 9390 +Train: [38] [3700/6250] eta: 0:06:04 lr: 0.000090 grad: 0.0804 (0.0793) loss: 0.8191 (0.8235) time: 0.1395 data: 0.0585 max mem: 9390 +Train: [38] [3800/6250] eta: 0:05:49 lr: 0.000090 grad: 0.0803 (0.0794) loss: 0.8205 (0.8235) time: 0.1266 data: 0.0444 max mem: 9390 +Train: [38] [3900/6250] eta: 0:05:35 lr: 0.000090 grad: 0.0779 (0.0796) loss: 0.8231 (0.8234) time: 0.1486 data: 0.0673 max mem: 9390 +Train: [38] [4000/6250] eta: 0:05:21 lr: 0.000090 grad: 0.0775 (0.0799) loss: 0.8304 (0.8235) time: 0.1169 data: 0.0361 max mem: 9390 +Train: [38] [4100/6250] eta: 0:05:07 lr: 0.000090 grad: 0.0790 (0.0799) loss: 0.8197 (0.8234) time: 0.1570 data: 0.0735 max mem: 9390 +Train: [38] [4200/6250] eta: 0:04:52 lr: 0.000090 grad: 0.0819 (0.0799) loss: 0.8250 (0.8234) time: 0.1596 data: 0.0809 max mem: 9390 +Train: [38] [4300/6250] eta: 0:04:38 lr: 0.000090 grad: 0.0819 (0.0799) loss: 0.8141 (0.8234) time: 0.1377 data: 0.0546 max mem: 9390 +Train: [38] [4400/6250] eta: 0:04:23 lr: 0.000090 grad: 0.0851 (0.0799) loss: 0.8197 (0.8233) time: 0.1407 data: 0.0608 max mem: 9390 +Train: [38] [4500/6250] eta: 0:04:09 lr: 0.000090 grad: 0.0785 (0.0799) loss: 0.8235 (0.8233) time: 0.1477 data: 0.0661 max mem: 9390 +Train: [38] [4600/6250] eta: 0:03:54 lr: 0.000090 grad: 0.0778 (0.0800) loss: 0.8203 (0.8233) time: 0.1530 data: 0.0745 max mem: 9390 +Train: [38] [4700/6250] eta: 0:03:40 lr: 0.000090 grad: 0.0800 (0.0800) loss: 0.8200 (0.8233) time: 0.1277 data: 0.0452 max mem: 9390 +Train: [38] [4800/6250] eta: 0:03:27 lr: 0.000090 grad: 0.0807 (0.0800) loss: 0.8219 (0.8232) time: 0.1757 data: 0.0964 max mem: 9390 +Train: [38] [4900/6250] eta: 0:03:13 lr: 0.000090 grad: 0.0787 (0.0801) loss: 0.8239 (0.8232) time: 0.1752 data: 0.0961 max mem: 9390 +Train: [38] [5000/6250] eta: 0:02:59 lr: 0.000090 grad: 0.0750 (0.0801) loss: 0.8272 (0.8233) time: 0.1515 data: 0.0639 max mem: 9390 +Train: [38] [5100/6250] eta: 0:02:45 lr: 0.000090 grad: 0.0777 (0.0802) loss: 0.8219 (0.8232) time: 0.1835 data: 0.1048 max mem: 9390 +Train: [38] [5200/6250] eta: 0:02:31 lr: 0.000090 grad: 0.0774 (0.0802) loss: 0.8235 (0.8232) time: 0.1459 data: 0.0665 max mem: 9390 +Train: [38] [5300/6250] eta: 0:02:16 lr: 0.000090 grad: 0.0809 (0.0803) loss: 0.8179 (0.8231) time: 0.1347 data: 0.0478 max mem: 9390 +Train: [38] [5400/6250] eta: 0:02:02 lr: 0.000090 grad: 0.0750 (0.0803) loss: 0.8202 (0.8231) time: 0.1059 data: 0.0266 max mem: 9390 +Train: [38] [5500/6250] eta: 0:01:47 lr: 0.000090 grad: 0.0750 (0.0803) loss: 0.8234 (0.8231) time: 0.1299 data: 0.0467 max mem: 9390 +Train: [38] [5600/6250] eta: 0:01:33 lr: 0.000090 grad: 0.0770 (0.0804) loss: 0.8214 (0.8231) time: 0.1342 data: 0.0556 max mem: 9390 +Train: [38] [5700/6250] eta: 0:01:18 lr: 0.000090 grad: 0.0801 (0.0804) loss: 0.8188 (0.8230) time: 0.1241 data: 0.0400 max mem: 9390 +Train: [38] [5800/6250] eta: 0:01:04 lr: 0.000090 grad: 0.0765 (0.0805) loss: 0.8210 (0.8229) time: 0.1289 data: 0.0519 max mem: 9390 +Train: [38] [5900/6250] eta: 0:00:49 lr: 0.000090 grad: 0.0758 (0.0805) loss: 0.8248 (0.8229) time: 0.1377 data: 0.0505 max mem: 9390 +Train: [38] [6000/6250] eta: 0:00:35 lr: 0.000090 grad: 0.0758 (0.0804) loss: 0.8231 (0.8229) time: 0.1385 data: 0.0577 max mem: 9390 +Train: [38] [6100/6250] eta: 0:00:21 lr: 0.000090 grad: 0.0784 (0.0804) loss: 0.8218 (0.8228) time: 0.1171 data: 0.0406 max mem: 9390 +Train: [38] [6200/6250] eta: 0:00:07 lr: 0.000089 grad: 0.0752 (0.0804) loss: 0.8251 (0.8228) time: 0.1548 data: 0.0759 max mem: 9390 +Train: [38] [6249/6250] eta: 0:00:00 lr: 0.000089 grad: 0.0787 (0.0804) loss: 0.8205 (0.8228) time: 0.1298 data: 0.0471 max mem: 9390 +Train: [38] Total time: 0:14:54 (0.1432 s / it) +Averaged stats: lr: 0.000089 grad: 0.0787 (0.0804) loss: 0.8205 (0.8228) +Eval (hcp-train-subset): [38] [ 0/62] eta: 0:04:07 loss: 0.8570 (0.8570) time: 3.9884 data: 3.9567 max mem: 9390 +Eval (hcp-train-subset): [38] [61/62] eta: 0:00:00 loss: 0.8415 (0.8412) time: 0.1317 data: 0.1053 max mem: 9390 +Eval (hcp-train-subset): [38] Total time: 0:00:11 (0.1907 s / it) +Averaged stats (hcp-train-subset): loss: 0.8415 (0.8412) +Eval (hcp-val): [38] [ 0/62] eta: 0:04:38 loss: 0.8388 (0.8388) time: 4.4966 data: 4.4664 max mem: 9390 +Eval (hcp-val): [38] [61/62] eta: 0:00:00 loss: 0.8372 (0.8375) time: 0.1230 data: 0.0981 max mem: 9390 +Eval (hcp-val): [38] Total time: 0:00:12 (0.2090 s / it) +Averaged stats (hcp-val): loss: 0.8372 (0.8375) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +Train: [39] [ 0/6250] eta: 6:54:05 lr: 0.000089 grad: 0.1023 (0.1023) loss: 0.8742 (0.8742) time: 3.9753 data: 3.7637 max mem: 9390 +Train: [39] [ 100/6250] eta: 0:19:53 lr: 0.000089 grad: 0.0763 (0.0774) loss: 0.8342 (0.8375) time: 0.1507 data: 0.0551 max mem: 9390 +Train: [39] [ 200/6250] eta: 0:17:24 lr: 0.000089 grad: 0.0772 (0.0777) loss: 0.8279 (0.8331) time: 0.1228 data: 0.0369 max mem: 9390 +Train: [39] [ 300/6250] eta: 0:16:18 lr: 0.000089 grad: 0.0742 (0.0778) loss: 0.8337 (0.8318) time: 0.1408 data: 0.0556 max mem: 9390 +Train: [39] [ 400/6250] eta: 0:15:11 lr: 0.000089 grad: 0.0733 (0.0776) loss: 0.8231 (0.8311) time: 0.1237 data: 0.0452 max mem: 9390 +Train: [39] [ 500/6250] eta: 0:14:29 lr: 0.000089 grad: 0.0690 (0.0767) loss: 0.8382 (0.8311) time: 0.1379 data: 0.0554 max mem: 9390 +Train: [39] [ 600/6250] eta: 0:13:54 lr: 0.000089 grad: 0.0677 (0.0764) loss: 0.8371 (0.8310) time: 0.1307 data: 0.0476 max mem: 9390 +Train: [39] [ 700/6250] eta: 0:13:21 lr: 0.000089 grad: 0.0675 (0.0761) loss: 0.8293 (0.8309) time: 0.1207 data: 0.0358 max mem: 9390 +Train: [39] [ 800/6250] eta: 0:12:52 lr: 0.000089 grad: 0.0708 (0.0761) loss: 0.8323 (0.8306) time: 0.1252 data: 0.0434 max mem: 9390 +Train: [39] [ 900/6250] eta: 0:12:28 lr: 0.000089 grad: 0.0690 (0.0761) loss: 0.8343 (0.8304) time: 0.1346 data: 0.0325 max mem: 9390 +Train: [39] [1000/6250] eta: 0:12:04 lr: 0.000089 grad: 0.0730 (0.0765) loss: 0.8254 (0.8303) time: 0.1177 data: 0.0340 max mem: 9390 +Train: [39] [1100/6250] eta: 0:11:44 lr: 0.000089 grad: 0.0721 (0.0764) loss: 0.8260 (0.8300) time: 0.1271 data: 0.0501 max mem: 9390 +Train: [39] [1200/6250] eta: 0:11:24 lr: 0.000089 grad: 0.0794 (0.0764) loss: 0.8283 (0.8297) time: 0.1279 data: 0.0469 max mem: 9390 +Train: [39] [1300/6250] eta: 0:11:06 lr: 0.000089 grad: 0.0698 (0.0763) loss: 0.8276 (0.8295) time: 0.1391 data: 0.0621 max mem: 9390 +Train: [39] [1400/6250] eta: 0:10:52 lr: 0.000089 grad: 0.0752 (0.0764) loss: 0.8182 (0.8291) time: 0.1295 data: 0.0509 max mem: 9390 +Train: [39] [1500/6250] eta: 0:10:34 lr: 0.000089 grad: 0.0747 (0.0764) loss: 0.8277 (0.8288) time: 0.1183 data: 0.0344 max mem: 9390 +Train: [39] [1600/6250] eta: 0:10:23 lr: 0.000089 grad: 0.0703 (0.0763) loss: 0.8263 (0.8286) time: 0.1443 data: 0.0648 max mem: 9390 +Train: [39] [1700/6250] eta: 0:10:14 lr: 0.000089 grad: 0.0747 (0.0764) loss: 0.8252 (0.8284) time: 0.1685 data: 0.0928 max mem: 9390 +Train: [39] [1800/6250] eta: 0:10:04 lr: 0.000089 grad: 0.0776 (0.0766) loss: 0.8222 (0.8282) time: 0.1459 data: 0.0532 max mem: 9390 +Train: [39] [1900/6250] eta: 0:09:53 lr: 0.000089 grad: 0.0707 (0.0765) loss: 0.8280 (0.8282) time: 0.1478 data: 0.0546 max mem: 9390 +Train: [39] [2000/6250] eta: 0:09:40 lr: 0.000089 grad: 0.0723 (0.0765) loss: 0.8299 (0.8281) time: 0.1239 data: 0.0369 max mem: 9390 +Train: [39] [2100/6250] eta: 0:09:29 lr: 0.000089 grad: 0.0738 (0.0764) loss: 0.8233 (0.8280) time: 0.1384 data: 0.0504 max mem: 9390 +Train: [39] [2200/6250] eta: 0:09:17 lr: 0.000089 grad: 0.0740 (0.0765) loss: 0.8194 (0.8279) time: 0.1437 data: 0.0671 max mem: 9390 +Train: [39] [2300/6250] eta: 0:09:04 lr: 0.000089 grad: 0.0784 (0.0767) loss: 0.8188 (0.8277) time: 0.1397 data: 0.0597 max mem: 9390 +Train: [39] [2400/6250] eta: 0:08:51 lr: 0.000089 grad: 0.0782 (0.0767) loss: 0.8237 (0.8277) time: 0.1247 data: 0.0435 max mem: 9390 +Train: [39] [2500/6250] eta: 0:08:37 lr: 0.000089 grad: 0.0800 (0.0769) loss: 0.8300 (0.8276) time: 0.1468 data: 0.0621 max mem: 9390 +Train: [39] [2600/6250] eta: 0:08:24 lr: 0.000089 grad: 0.0758 (0.0769) loss: 0.8238 (0.8275) time: 0.1476 data: 0.0682 max mem: 9390 +Train: [39] [2700/6250] eta: 0:08:10 lr: 0.000089 grad: 0.0777 (0.0770) loss: 0.8236 (0.8275) time: 0.1395 data: 0.0592 max mem: 9390 +Train: [39] [2800/6250] eta: 0:07:58 lr: 0.000089 grad: 0.0796 (0.0771) loss: 0.8223 (0.8274) time: 0.1322 data: 0.0473 max mem: 9390 +Train: [39] [2900/6250] eta: 0:07:45 lr: 0.000089 grad: 0.0827 (0.0772) loss: 0.8265 (0.8273) time: 0.1485 data: 0.0715 max mem: 9390 +Train: [39] [3000/6250] eta: 0:07:33 lr: 0.000089 grad: 0.0796 (0.0773) loss: 0.8266 (0.8272) time: 0.1128 data: 0.0357 max mem: 9390 +Train: [39] [3100/6250] eta: 0:07:20 lr: 0.000089 grad: 0.0736 (0.0774) loss: 0.8274 (0.8271) time: 0.1506 data: 0.0752 max mem: 9390 +Train: [39] [3200/6250] eta: 0:07:06 lr: 0.000089 grad: 0.0711 (0.0774) loss: 0.8306 (0.8270) time: 0.1490 data: 0.0723 max mem: 9390 +Train: [39] [3300/6250] eta: 0:06:52 lr: 0.000088 grad: 0.0760 (0.0775) loss: 0.8271 (0.8269) time: 0.1523 data: 0.0568 max mem: 9390 +Train: [39] [3400/6250] eta: 0:06:39 lr: 0.000088 grad: 0.0791 (0.0775) loss: 0.8230 (0.8267) time: 0.1501 data: 0.0638 max mem: 9390 +Train: [39] [3500/6250] eta: 0:06:26 lr: 0.000088 grad: 0.0776 (0.0776) loss: 0.8259 (0.8266) time: 0.1457 data: 0.0656 max mem: 9390 +Train: [39] [3600/6250] eta: 0:06:11 lr: 0.000088 grad: 0.0807 (0.0777) loss: 0.8205 (0.8266) time: 0.1248 data: 0.0442 max mem: 9390 +Train: [39] [3700/6250] eta: 0:06:01 lr: 0.000088 grad: 0.0821 (0.0778) loss: 0.8256 (0.8265) time: 0.3614 data: 0.2366 max mem: 9390 +Train: [39] [3800/6250] eta: 0:05:45 lr: 0.000088 grad: 0.0795 (0.0779) loss: 0.8193 (0.8265) time: 0.1530 data: 0.0744 max mem: 9390 +Train: [39] [3900/6250] eta: 0:05:31 lr: 0.000088 grad: 0.0796 (0.0780) loss: 0.8186 (0.8264) time: 0.1565 data: 0.0732 max mem: 9390 +Train: [39] [4000/6250] eta: 0:05:18 lr: 0.000088 grad: 0.0782 (0.0781) loss: 0.8259 (0.8263) time: 0.1165 data: 0.0389 max mem: 9390 +Train: [39] [4100/6250] eta: 0:05:05 lr: 0.000088 grad: 0.0749 (0.0781) loss: 0.8213 (0.8263) time: 0.1652 data: 0.0887 max mem: 9390 +Train: [39] [4200/6250] eta: 0:04:51 lr: 0.000088 grad: 0.0785 (0.0782) loss: 0.8224 (0.8262) time: 0.1569 data: 0.0725 max mem: 9390 +Train: [39] [4300/6250] eta: 0:04:37 lr: 0.000088 grad: 0.0817 (0.0783) loss: 0.8247 (0.8261) time: 0.1462 data: 0.0701 max mem: 9390 +Train: [39] [4400/6250] eta: 0:04:22 lr: 0.000088 grad: 0.0757 (0.0783) loss: 0.8261 (0.8261) time: 0.1301 data: 0.0471 max mem: 9390 +Train: [39] [4500/6250] eta: 0:04:08 lr: 0.000088 grad: 0.0798 (0.0783) loss: 0.8258 (0.8261) time: 0.1538 data: 0.0673 max mem: 9390 +Train: [39] [4600/6250] eta: 0:03:54 lr: 0.000088 grad: 0.0746 (0.0783) loss: 0.8225 (0.8261) time: 0.1361 data: 0.0534 max mem: 9390 +Train: [39] [4700/6250] eta: 0:03:40 lr: 0.000088 grad: 0.0791 (0.0784) loss: 0.8233 (0.8261) time: 0.1297 data: 0.0536 max mem: 9390 +Train: [39] [4800/6250] eta: 0:03:27 lr: 0.000088 grad: 0.0840 (0.0784) loss: 0.8224 (0.8261) time: 0.1441 data: 0.0662 max mem: 9390 +Train: [39] [4900/6250] eta: 0:03:13 lr: 0.000088 grad: 0.0761 (0.0784) loss: 0.8280 (0.8261) time: 0.1535 data: 0.0780 max mem: 9390 +Train: [39] [5000/6250] eta: 0:02:59 lr: 0.000088 grad: 0.0787 (0.0785) loss: 0.8211 (0.8261) time: 0.1757 data: 0.0941 max mem: 9390 +Train: [39] [5100/6250] eta: 0:02:45 lr: 0.000088 grad: 0.0829 (0.0785) loss: 0.8249 (0.8261) time: 0.1501 data: 0.0753 max mem: 9390 +Train: [39] [5200/6250] eta: 0:02:30 lr: 0.000088 grad: 0.0768 (0.0785) loss: 0.8217 (0.8261) time: 0.1487 data: 0.0672 max mem: 9390 +Train: [39] [5300/6250] eta: 0:02:16 lr: 0.000088 grad: 0.0798 (0.0786) loss: 0.8236 (0.8260) time: 0.1412 data: 0.0644 max mem: 9390 +Train: [39] [5400/6250] eta: 0:02:01 lr: 0.000088 grad: 0.0738 (0.0786) loss: 0.8301 (0.8260) time: 0.1370 data: 0.0608 max mem: 9390 +Train: [39] [5500/6250] eta: 0:01:47 lr: 0.000088 grad: 0.0830 (0.0786) loss: 0.8258 (0.8260) time: 0.1419 data: 0.0620 max mem: 9390 +Train: [39] [5600/6250] eta: 0:01:32 lr: 0.000088 grad: 0.0832 (0.0787) loss: 0.8270 (0.8260) time: 0.1168 data: 0.0347 max mem: 9390 +Train: [39] [5700/6250] eta: 0:01:18 lr: 0.000088 grad: 0.0777 (0.0787) loss: 0.8228 (0.8260) time: 0.1396 data: 0.0563 max mem: 9390 +Train: [39] [5800/6250] eta: 0:01:04 lr: 0.000088 grad: 0.0794 (0.0788) loss: 0.8261 (0.8260) time: 0.1284 data: 0.0478 max mem: 9390 +Train: [39] [5900/6250] eta: 0:00:49 lr: 0.000088 grad: 0.0812 (0.0788) loss: 0.8270 (0.8260) time: 0.1176 data: 0.0265 max mem: 9390 +Train: [39] [6000/6250] eta: 0:00:35 lr: 0.000088 grad: 0.0815 (0.0788) loss: 0.8261 (0.8260) time: 0.1323 data: 0.0553 max mem: 9390 +Train: [39] [6100/6250] eta: 0:00:21 lr: 0.000088 grad: 0.0789 (0.0788) loss: 0.8242 (0.8260) time: 0.1224 data: 0.0361 max mem: 9390 +Train: [39] [6200/6250] eta: 0:00:07 lr: 0.000088 grad: 0.0812 (0.0789) loss: 0.8242 (0.8259) time: 0.1605 data: 0.0655 max mem: 9390 +Train: [39] [6249/6250] eta: 0:00:00 lr: 0.000088 grad: 0.0774 (0.0789) loss: 0.8247 (0.8259) time: 0.2678 data: 0.1832 max mem: 9390 +Train: [39] Total time: 0:14:56 (0.1435 s / it) +Averaged stats: lr: 0.000088 grad: 0.0774 (0.0789) loss: 0.8247 (0.8259) +Eval (hcp-train-subset): [39] [ 0/62] eta: 0:06:40 loss: 0.8519 (0.8519) time: 6.4670 data: 6.4396 max mem: 9390 +Eval (hcp-train-subset): [39] [61/62] eta: 0:00:00 loss: 0.8389 (0.8402) time: 0.0952 data: 0.0687 max mem: 9390 +Eval (hcp-train-subset): [39] Total time: 0:00:14 (0.2261 s / it) +Averaged stats (hcp-train-subset): loss: 0.8389 (0.8402) +Making plots (hcp-train-subset): example=46 +Eval (hcp-val): [39] [ 0/62] eta: 0:04:48 loss: 0.8325 (0.8325) time: 4.6553 data: 4.6207 max mem: 9390 +Eval (hcp-val): [39] [61/62] eta: 0:00:00 loss: 0.8356 (0.8364) time: 0.0956 data: 0.0699 max mem: 9390 +Eval (hcp-val): [39] Total time: 0:00:13 (0.2173 s / it) +Averaged stats (hcp-val): loss: 0.8356 (0.8364) +Making plots (hcp-val): example=26 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +Train: [40] [ 0/6250] eta: 10:18:58 lr: 0.000088 grad: 0.4148 (0.4148) loss: 0.8471 (0.8471) time: 5.9421 data: 5.8190 max mem: 9390 +Train: [40] [ 100/6250] eta: 0:20:50 lr: 0.000088 grad: 0.0716 (0.0880) loss: 0.8364 (0.8365) time: 0.1486 data: 0.0551 max mem: 9390 +Train: [40] [ 200/6250] eta: 0:17:58 lr: 0.000088 grad: 0.0750 (0.0875) loss: 0.8343 (0.8337) time: 0.1420 data: 0.0640 max mem: 9390 +Train: [40] [ 300/6250] eta: 0:16:30 lr: 0.000088 grad: 0.0704 (0.0844) loss: 0.8322 (0.8316) time: 0.1435 data: 0.0627 max mem: 9390 +Train: [40] [ 400/6250] eta: 0:15:32 lr: 0.000087 grad: 0.0713 (0.0822) loss: 0.8244 (0.8308) time: 0.1341 data: 0.0534 max mem: 9390 +Train: [40] [ 500/6250] eta: 0:14:36 lr: 0.000087 grad: 0.0712 (0.0806) loss: 0.8273 (0.8310) time: 0.1299 data: 0.0557 max mem: 9390 +Train: [40] [ 600/6250] eta: 0:14:02 lr: 0.000087 grad: 0.0764 (0.0801) loss: 0.8302 (0.8309) time: 0.1392 data: 0.0643 max mem: 9390 +Train: [40] [ 700/6250] eta: 0:13:27 lr: 0.000087 grad: 0.0735 (0.0792) loss: 0.8307 (0.8306) time: 0.1235 data: 0.0407 max mem: 9390 +Train: [40] [ 800/6250] eta: 0:12:57 lr: 0.000087 grad: 0.0738 (0.0785) loss: 0.8316 (0.8305) time: 0.1244 data: 0.0440 max mem: 9390 +Train: [40] [ 900/6250] eta: 0:12:31 lr: 0.000087 grad: 0.0738 (0.0781) loss: 0.8293 (0.8303) time: 0.1201 data: 0.0308 max mem: 9390 +Train: [40] [1000/6250] eta: 0:12:09 lr: 0.000087 grad: 0.0723 (0.0778) loss: 0.8321 (0.8302) time: 0.1133 data: 0.0327 max mem: 9390 +Train: [40] [1100/6250] eta: 0:11:48 lr: 0.000087 grad: 0.0758 (0.0775) loss: 0.8271 (0.8302) time: 0.1301 data: 0.0508 max mem: 9390 +Train: [40] [1200/6250] eta: 0:11:30 lr: 0.000087 grad: 0.0742 (0.0772) loss: 0.8258 (0.8299) time: 0.1210 data: 0.0475 max mem: 9390 +Train: [40] [1300/6250] eta: 0:11:13 lr: 0.000087 grad: 0.0734 (0.0770) loss: 0.8206 (0.8297) time: 0.1221 data: 0.0441 max mem: 9390 +Train: [40] [1400/6250] eta: 0:10:58 lr: 0.000087 grad: 0.0787 (0.0769) loss: 0.8226 (0.8294) time: 0.1275 data: 0.0492 max mem: 9390 +Train: [40] [1500/6250] eta: 0:10:40 lr: 0.000087 grad: 0.0788 (0.0770) loss: 0.8206 (0.8291) time: 0.1231 data: 0.0398 max mem: 9390 +Train: [40] [1600/6250] eta: 0:10:26 lr: 0.000087 grad: 0.0782 (0.0771) loss: 0.8201 (0.8288) time: 0.1126 data: 0.0286 max mem: 9390 +Train: [40] [1700/6250] eta: 0:10:15 lr: 0.000087 grad: 0.0758 (0.0771) loss: 0.8244 (0.8285) time: 0.1513 data: 0.0666 max mem: 9390 +Train: [40] [1800/6250] eta: 0:10:03 lr: 0.000087 grad: 0.0757 (0.0772) loss: 0.8260 (0.8284) time: 0.1424 data: 0.0635 max mem: 9390 +Train: [40] [1900/6250] eta: 0:09:50 lr: 0.000087 grad: 0.0779 (0.0773) loss: 0.8191 (0.8283) time: 0.1231 data: 0.0430 max mem: 9390 +Train: [40] [2000/6250] eta: 0:09:38 lr: 0.000087 grad: 0.0742 (0.0774) loss: 0.8302 (0.8281) time: 0.1313 data: 0.0450 max mem: 9390 +Train: [40] [2100/6250] eta: 0:09:26 lr: 0.000087 grad: 0.0789 (0.0775) loss: 0.8202 (0.8280) time: 0.1489 data: 0.0673 max mem: 9390 +Train: [40] [2200/6250] eta: 0:09:14 lr: 0.000087 grad: 0.0774 (0.0776) loss: 0.8257 (0.8278) time: 0.1413 data: 0.0648 max mem: 9390 +Train: [40] [2300/6250] eta: 0:09:03 lr: 0.000087 grad: 0.0798 (0.0777) loss: 0.8273 (0.8276) time: 0.1219 data: 0.0405 max mem: 9390 +Train: [40] [2400/6250] eta: 0:08:50 lr: 0.000087 grad: 0.0766 (0.0777) loss: 0.8221 (0.8275) time: 0.1313 data: 0.0541 max mem: 9390 +Train: [40] [2500/6250] eta: 0:08:37 lr: 0.000087 grad: 0.0791 (0.0778) loss: 0.8212 (0.8274) time: 0.1377 data: 0.0609 max mem: 9390 +Train: [40] [2600/6250] eta: 0:08:24 lr: 0.000087 grad: 0.0786 (0.0778) loss: 0.8261 (0.8273) time: 0.1446 data: 0.0655 max mem: 9390 +Train: [40] [2700/6250] eta: 0:08:11 lr: 0.000087 grad: 0.0765 (0.0778) loss: 0.8234 (0.8272) time: 0.1443 data: 0.0606 max mem: 9390 +Train: [40] [2800/6250] eta: 0:07:58 lr: 0.000087 grad: 0.0737 (0.0778) loss: 0.8261 (0.8271) time: 0.1421 data: 0.0616 max mem: 9390 +Train: [40] [2900/6250] eta: 0:07:44 lr: 0.000087 grad: 0.0752 (0.0779) loss: 0.8227 (0.8269) time: 0.1405 data: 0.0662 max mem: 9390 +Train: [40] [3000/6250] eta: 0:07:30 lr: 0.000087 grad: 0.0698 (0.0779) loss: 0.8225 (0.8268) time: 0.1392 data: 0.0628 max mem: 9390 +Train: [40] [3100/6250] eta: 0:07:16 lr: 0.000087 grad: 0.0725 (0.0778) loss: 0.8299 (0.8268) time: 0.1473 data: 0.0587 max mem: 9390 +Train: [40] [3200/6250] eta: 0:07:02 lr: 0.000087 grad: 0.0789 (0.0779) loss: 0.8249 (0.8267) time: 0.1292 data: 0.0469 max mem: 9390 +Train: [40] [3300/6250] eta: 0:06:49 lr: 0.000087 grad: 0.0788 (0.0780) loss: 0.8238 (0.8266) time: 0.1543 data: 0.0714 max mem: 9390 +Train: [40] [3400/6250] eta: 0:06:36 lr: 0.000087 grad: 0.0761 (0.0780) loss: 0.8209 (0.8265) time: 0.1406 data: 0.0608 max mem: 9390 +Train: [40] [3500/6250] eta: 0:06:22 lr: 0.000087 grad: 0.0729 (0.0780) loss: 0.8244 (0.8265) time: 0.1443 data: 0.0703 max mem: 9390 +Train: [40] [3600/6250] eta: 0:06:07 lr: 0.000087 grad: 0.0799 (0.0780) loss: 0.8263 (0.8265) time: 0.1301 data: 0.0552 max mem: 9390 +Train: [40] [3700/6250] eta: 0:05:54 lr: 0.000086 grad: 0.0754 (0.0780) loss: 0.8239 (0.8264) time: 0.1230 data: 0.0457 max mem: 9390 +Train: [40] [3800/6250] eta: 0:05:39 lr: 0.000086 grad: 0.0734 (0.0780) loss: 0.8313 (0.8265) time: 0.1378 data: 0.0601 max mem: 9390 +Train: [40] [3900/6250] eta: 0:05:27 lr: 0.000086 grad: 0.0778 (0.0780) loss: 0.8267 (0.8264) time: 0.1408 data: 0.0596 max mem: 9390 +Train: [40] [4000/6250] eta: 0:05:13 lr: 0.000086 grad: 0.0800 (0.0780) loss: 0.8257 (0.8264) time: 0.1196 data: 0.0417 max mem: 9390 +Train: [40] [4100/6250] eta: 0:04:59 lr: 0.000086 grad: 0.0749 (0.0780) loss: 0.8304 (0.8264) time: 0.1601 data: 0.0842 max mem: 9390 +Train: [40] [4200/6250] eta: 0:04:46 lr: 0.000086 grad: 0.0733 (0.0780) loss: 0.8253 (0.8264) time: 0.1556 data: 0.0685 max mem: 9390 +Train: [40] [4300/6250] eta: 0:04:32 lr: 0.000086 grad: 0.0782 (0.0781) loss: 0.8251 (0.8263) time: 0.1356 data: 0.0605 max mem: 9390 +Train: [40] [4400/6250] eta: 0:04:17 lr: 0.000086 grad: 0.0774 (0.0781) loss: 0.8229 (0.8262) time: 0.1239 data: 0.0497 max mem: 9390 +Train: [40] [4500/6250] eta: 0:04:04 lr: 0.000086 grad: 0.0812 (0.0781) loss: 0.8264 (0.8262) time: 0.1561 data: 0.0708 max mem: 9390 +Train: [40] [4600/6250] eta: 0:03:50 lr: 0.000086 grad: 0.0758 (0.0781) loss: 0.8268 (0.8262) time: 0.1577 data: 0.0782 max mem: 9390 +Train: [40] [4700/6250] eta: 0:03:37 lr: 0.000086 grad: 0.0833 (0.0782) loss: 0.8270 (0.8262) time: 0.1601 data: 0.0792 max mem: 9390 +Train: [40] [4800/6250] eta: 0:03:23 lr: 0.000086 grad: 0.0766 (0.0783) loss: 0.8258 (0.8262) time: 0.1546 data: 0.0781 max mem: 9390 +Train: [40] [4900/6250] eta: 0:03:09 lr: 0.000086 grad: 0.0761 (0.0783) loss: 0.8191 (0.8262) time: 0.1746 data: 0.0986 max mem: 9390 +Train: [40] [5000/6250] eta: 0:02:55 lr: 0.000086 grad: 0.0738 (0.0783) loss: 0.8279 (0.8262) time: 0.1399 data: 0.0624 max mem: 9390 +Train: [40] [5100/6250] eta: 0:02:42 lr: 0.000086 grad: 0.0786 (0.0784) loss: 0.8248 (0.8262) time: 0.1509 data: 0.0712 max mem: 9390 +Train: [40] [5200/6250] eta: 0:02:28 lr: 0.000086 grad: 0.0785 (0.0784) loss: 0.8237 (0.8261) time: 0.1431 data: 0.0632 max mem: 9390 +Train: [40] [5300/6250] eta: 0:02:14 lr: 0.000086 grad: 0.0819 (0.0784) loss: 0.8252 (0.8260) time: 0.0956 data: 0.0094 max mem: 9390 +Train: [40] [5400/6250] eta: 0:01:59 lr: 0.000086 grad: 0.0801 (0.0785) loss: 0.8272 (0.8260) time: 0.1243 data: 0.0458 max mem: 9390 +Train: [40] [5500/6250] eta: 0:01:45 lr: 0.000086 grad: 0.0778 (0.0785) loss: 0.8198 (0.8259) time: 0.1249 data: 0.0442 max mem: 9390 +Train: [40] [5600/6250] eta: 0:01:31 lr: 0.000086 grad: 0.0809 (0.0786) loss: 0.8172 (0.8259) time: 0.1079 data: 0.0229 max mem: 9390 +Train: [40] [5700/6250] eta: 0:01:17 lr: 0.000086 grad: 0.0772 (0.0787) loss: 0.8228 (0.8258) time: 0.1154 data: 0.0298 max mem: 9390 +Train: [40] [5800/6250] eta: 0:01:03 lr: 0.000086 grad: 0.0747 (0.0787) loss: 0.8264 (0.8258) time: 0.1209 data: 0.0425 max mem: 9390 +Train: [40] [5900/6250] eta: 0:00:48 lr: 0.000086 grad: 0.0811 (0.0788) loss: 0.8206 (0.8258) time: 0.1008 data: 0.0275 max mem: 9390 +Train: [40] [6000/6250] eta: 0:00:34 lr: 0.000086 grad: 0.0805 (0.0789) loss: 0.8260 (0.8258) time: 0.1331 data: 0.0429 max mem: 9390 +Train: [40] [6100/6250] eta: 0:00:20 lr: 0.000086 grad: 0.0784 (0.0789) loss: 0.8229 (0.8257) time: 0.1430 data: 0.0648 max mem: 9390 +Train: [40] [6200/6250] eta: 0:00:06 lr: 0.000086 grad: 0.0766 (0.0790) loss: 0.8263 (0.8257) time: 0.1344 data: 0.0541 max mem: 9390 +Train: [40] [6249/6250] eta: 0:00:00 lr: 0.000086 grad: 0.0761 (0.0790) loss: 0.8298 (0.8257) time: 0.1549 data: 0.0767 max mem: 9390 +Train: [40] Total time: 0:14:39 (0.1408 s / it) +Averaged stats: lr: 0.000086 grad: 0.0761 (0.0790) loss: 0.8298 (0.8257) +Eval (hcp-train-subset): [40] [ 0/62] eta: 0:03:02 loss: 0.8511 (0.8511) time: 2.9436 data: 2.8779 max mem: 9390 +Eval (hcp-train-subset): [40] [61/62] eta: 0:00:00 loss: 0.8421 (0.8404) time: 0.1175 data: 0.0926 max mem: 9390 +Eval (hcp-train-subset): [40] Total time: 0:00:12 (0.1954 s / it) +Averaged stats (hcp-train-subset): loss: 0.8421 (0.8404) +Eval (hcp-val): [40] [ 0/62] eta: 0:04:50 loss: 0.8348 (0.8348) time: 4.6931 data: 4.6643 max mem: 9390 +Eval (hcp-val): [40] [61/62] eta: 0:00:00 loss: 0.8356 (0.8366) time: 0.1495 data: 0.1244 max mem: 9390 +Eval (hcp-val): [40] Total time: 0:00:12 (0.2079 s / it) +Averaged stats (hcp-val): loss: 0.8356 (0.8366) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +Train: [41] [ 0/6250] eta: 6:31:11 lr: 0.000086 grad: 0.0517 (0.0517) loss: 0.8484 (0.8484) time: 3.7555 data: 3.5311 max mem: 9390 +Train: [41] [ 100/6250] eta: 0:20:07 lr: 0.000086 grad: 0.0775 (0.0924) loss: 0.8328 (0.8244) time: 0.1546 data: 0.0538 max mem: 9390 +Train: [41] [ 200/6250] eta: 0:17:37 lr: 0.000086 grad: 0.0760 (0.0898) loss: 0.8242 (0.8218) time: 0.1337 data: 0.0398 max mem: 9390 +Train: [41] [ 300/6250] eta: 0:16:22 lr: 0.000086 grad: 0.0771 (0.0869) loss: 0.8186 (0.8209) time: 0.1349 data: 0.0495 max mem: 9390 +Train: [41] [ 400/6250] eta: 0:15:19 lr: 0.000086 grad: 0.0682 (0.0845) loss: 0.8323 (0.8221) time: 0.1267 data: 0.0436 max mem: 9390 +Train: [41] [ 500/6250] eta: 0:14:31 lr: 0.000086 grad: 0.0762 (0.0834) loss: 0.8281 (0.8231) time: 0.1297 data: 0.0530 max mem: 9390 +Train: [41] [ 600/6250] eta: 0:13:57 lr: 0.000086 grad: 0.0776 (0.0824) loss: 0.8225 (0.8236) time: 0.1394 data: 0.0588 max mem: 9390 +Train: [41] [ 700/6250] eta: 0:13:18 lr: 0.000085 grad: 0.0736 (0.0815) loss: 0.8203 (0.8238) time: 0.1187 data: 0.0362 max mem: 9390 +Train: [41] [ 800/6250] eta: 0:12:50 lr: 0.000085 grad: 0.0749 (0.0810) loss: 0.8225 (0.8243) time: 0.1315 data: 0.0497 max mem: 9390 +Train: [41] [ 900/6250] eta: 0:12:32 lr: 0.000085 grad: 0.0739 (0.0807) loss: 0.8252 (0.8244) time: 0.1401 data: 0.0558 max mem: 9390 +Train: [41] [1000/6250] eta: 0:12:14 lr: 0.000085 grad: 0.0755 (0.0805) loss: 0.8271 (0.8245) time: 0.1281 data: 0.0513 max mem: 9390 +Train: [41] [1100/6250] eta: 0:12:02 lr: 0.000085 grad: 0.0790 (0.0801) loss: 0.8223 (0.8244) time: 0.1188 data: 0.0421 max mem: 9390 +Train: [41] [1200/6250] eta: 0:11:48 lr: 0.000085 grad: 0.0745 (0.0802) loss: 0.8206 (0.8243) time: 0.1568 data: 0.0801 max mem: 9390 +Train: [41] [1300/6250] eta: 0:11:32 lr: 0.000085 grad: 0.0768 (0.0801) loss: 0.8169 (0.8242) time: 0.1321 data: 0.0548 max mem: 9390 +Train: [41] [1400/6250] eta: 0:11:13 lr: 0.000085 grad: 0.0756 (0.0801) loss: 0.8272 (0.8242) time: 0.1289 data: 0.0501 max mem: 9390 +Train: [41] [1500/6250] eta: 0:10:57 lr: 0.000085 grad: 0.0753 (0.0801) loss: 0.8254 (0.8241) time: 0.1351 data: 0.0559 max mem: 9390 +Train: [41] [1600/6250] eta: 0:10:41 lr: 0.000085 grad: 0.0737 (0.0802) loss: 0.8274 (0.8239) time: 0.1342 data: 0.0467 max mem: 9390 +Train: [41] [1700/6250] eta: 0:10:27 lr: 0.000085 grad: 0.0817 (0.0802) loss: 0.8199 (0.8238) time: 0.1458 data: 0.0670 max mem: 9390 +Train: [41] [1800/6250] eta: 0:10:14 lr: 0.000085 grad: 0.0802 (0.0806) loss: 0.8232 (0.8236) time: 0.1224 data: 0.0463 max mem: 9390 +Train: [41] [1900/6250] eta: 0:10:04 lr: 0.000085 grad: 0.0785 (0.0809) loss: 0.8198 (0.8234) time: 0.1729 data: 0.0982 max mem: 9390 +Train: [41] [2000/6250] eta: 0:09:50 lr: 0.000085 grad: 0.0830 (0.0810) loss: 0.8163 (0.8232) time: 0.1459 data: 0.0690 max mem: 9390 +Train: [41] [2100/6250] eta: 0:09:36 lr: 0.000085 grad: 0.0843 (0.0813) loss: 0.8194 (0.8230) time: 0.1400 data: 0.0574 max mem: 9390 +Train: [41] [2200/6250] eta: 0:09:24 lr: 0.000085 grad: 0.0770 (0.0814) loss: 0.8224 (0.8229) time: 0.1476 data: 0.0755 max mem: 9390 +Train: [41] [2300/6250] eta: 0:09:11 lr: 0.000085 grad: 0.0795 (0.0814) loss: 0.8187 (0.8229) time: 0.1601 data: 0.0768 max mem: 9390 +Train: [41] [2400/6250] eta: 0:08:58 lr: 0.000085 grad: 0.0748 (0.0813) loss: 0.8270 (0.8229) time: 0.1440 data: 0.0606 max mem: 9390 +Train: [41] [2500/6250] eta: 0:08:45 lr: 0.000085 grad: 0.0823 (0.0814) loss: 0.8284 (0.8230) time: 0.1656 data: 0.0800 max mem: 9390 +Train: [41] [2600/6250] eta: 0:08:31 lr: 0.000085 grad: 0.0773 (0.0814) loss: 0.8274 (0.8230) time: 0.1419 data: 0.0558 max mem: 9390 +Train: [41] [2700/6250] eta: 0:08:17 lr: 0.000085 grad: 0.0778 (0.0814) loss: 0.8170 (0.8230) time: 0.1450 data: 0.0590 max mem: 9390 +Train: [41] [2800/6250] eta: 0:08:04 lr: 0.000085 grad: 0.0768 (0.0814) loss: 0.8178 (0.8229) time: 0.1688 data: 0.0931 max mem: 9390 +Train: [41] [2900/6250] eta: 0:07:51 lr: 0.000085 grad: 0.0791 (0.0815) loss: 0.8244 (0.8230) time: 0.1701 data: 0.0895 max mem: 9390 +Train: [41] [3000/6250] eta: 0:07:37 lr: 0.000085 grad: 0.0752 (0.0815) loss: 0.8250 (0.8230) time: 0.1494 data: 0.0733 max mem: 9390 +Train: [41] [3100/6250] eta: 0:07:23 lr: 0.000085 grad: 0.0797 (0.0815) loss: 0.8255 (0.8230) time: 0.1348 data: 0.0569 max mem: 9390 +Train: [41] [3200/6250] eta: 0:07:10 lr: 0.000085 grad: 0.0801 (0.0815) loss: 0.8281 (0.8231) time: 0.1958 data: 0.1190 max mem: 9390 +Train: [41] [3300/6250] eta: 0:06:56 lr: 0.000085 grad: 0.0810 (0.0816) loss: 0.8217 (0.8231) time: 0.1559 data: 0.0703 max mem: 9390 +Train: [41] [3400/6250] eta: 0:06:43 lr: 0.000085 grad: 0.0815 (0.0816) loss: 0.8198 (0.8231) time: 0.1178 data: 0.0271 max mem: 9390 +Train: [41] [3500/6250] eta: 0:06:29 lr: 0.000085 grad: 0.0801 (0.0816) loss: 0.8211 (0.8230) time: 0.1437 data: 0.0714 max mem: 9390 +Train: [41] [3600/6250] eta: 0:06:15 lr: 0.000085 grad: 0.0802 (0.0816) loss: 0.8280 (0.8230) time: 0.1698 data: 0.0908 max mem: 9390 +Train: [41] [3700/6250] eta: 0:06:01 lr: 0.000085 grad: 0.0828 (0.0817) loss: 0.8221 (0.8230) time: 0.1025 data: 0.0250 max mem: 9390 +Train: [41] [3800/6250] eta: 0:05:49 lr: 0.000085 grad: 0.0773 (0.0817) loss: 0.8228 (0.8230) time: 0.2684 data: 0.1479 max mem: 9390 +Train: [41] [3900/6250] eta: 0:05:34 lr: 0.000084 grad: 0.0863 (0.0818) loss: 0.8161 (0.8229) time: 0.1375 data: 0.0566 max mem: 9390 +Train: [41] [4000/6250] eta: 0:05:20 lr: 0.000084 grad: 0.0867 (0.0819) loss: 0.8192 (0.8228) time: 0.1514 data: 0.0642 max mem: 9390 +Train: [41] [4100/6250] eta: 0:05:05 lr: 0.000084 grad: 0.0815 (0.0820) loss: 0.8190 (0.8227) time: 0.1302 data: 0.0556 max mem: 9390 +Train: [41] [4200/6250] eta: 0:04:51 lr: 0.000084 grad: 0.0848 (0.0821) loss: 0.8160 (0.8226) time: 0.1377 data: 0.0618 max mem: 9390 +Train: [41] [4300/6250] eta: 0:04:36 lr: 0.000084 grad: 0.0774 (0.0821) loss: 0.8232 (0.8226) time: 0.1517 data: 0.0688 max mem: 9390 +Train: [41] [4400/6250] eta: 0:04:22 lr: 0.000084 grad: 0.0778 (0.0821) loss: 0.8216 (0.8226) time: 0.1304 data: 0.0433 max mem: 9390 +Train: [41] [4500/6250] eta: 0:04:08 lr: 0.000084 grad: 0.0796 (0.0822) loss: 0.8251 (0.8225) time: 0.1499 data: 0.0712 max mem: 9390 +Train: [41] [4600/6250] eta: 0:03:54 lr: 0.000084 grad: 0.0760 (0.0823) loss: 0.8268 (0.8225) time: 0.1766 data: 0.1008 max mem: 9390 +Train: [41] [4700/6250] eta: 0:03:41 lr: 0.000084 grad: 0.0814 (0.0823) loss: 0.8258 (0.8225) time: 0.1575 data: 0.0834 max mem: 9390 +Train: [41] [4800/6250] eta: 0:03:26 lr: 0.000084 grad: 0.0785 (0.0823) loss: 0.8302 (0.8225) time: 0.1381 data: 0.0566 max mem: 9390 +Train: [41] [4900/6250] eta: 0:03:12 lr: 0.000084 grad: 0.0809 (0.0823) loss: 0.8242 (0.8226) time: 0.1386 data: 0.0538 max mem: 9390 +Train: [41] [5000/6250] eta: 0:02:58 lr: 0.000084 grad: 0.0790 (0.0822) loss: 0.8193 (0.8225) time: 0.1461 data: 0.0695 max mem: 9390 +Train: [41] [5100/6250] eta: 0:02:44 lr: 0.000084 grad: 0.0795 (0.0822) loss: 0.8248 (0.8225) time: 0.1376 data: 0.0560 max mem: 9390 +Train: [41] [5200/6250] eta: 0:02:30 lr: 0.000084 grad: 0.0804 (0.0823) loss: 0.8234 (0.8225) time: 0.1504 data: 0.0699 max mem: 9390 +Train: [41] [5300/6250] eta: 0:02:15 lr: 0.000084 grad: 0.0817 (0.0823) loss: 0.8179 (0.8225) time: 0.1294 data: 0.0453 max mem: 9390 +Train: [41] [5400/6250] eta: 0:02:01 lr: 0.000084 grad: 0.0781 (0.0823) loss: 0.8238 (0.8224) time: 0.1486 data: 0.0705 max mem: 9390 +Train: [41] [5500/6250] eta: 0:01:46 lr: 0.000084 grad: 0.0799 (0.0823) loss: 0.8193 (0.8225) time: 0.1459 data: 0.0687 max mem: 9390 +Train: [41] [5600/6250] eta: 0:01:32 lr: 0.000084 grad: 0.0795 (0.0822) loss: 0.8224 (0.8225) time: 0.1431 data: 0.0640 max mem: 9390 +Train: [41] [5700/6250] eta: 0:01:17 lr: 0.000084 grad: 0.0837 (0.0823) loss: 0.8158 (0.8225) time: 0.1360 data: 0.0574 max mem: 9390 +Train: [41] [5800/6250] eta: 0:01:03 lr: 0.000084 grad: 0.0847 (0.0823) loss: 0.8174 (0.8225) time: 0.1389 data: 0.0587 max mem: 9390 +Train: [41] [5900/6250] eta: 0:00:49 lr: 0.000084 grad: 0.0788 (0.0824) loss: 0.8227 (0.8224) time: 0.1469 data: 0.0704 max mem: 9390 +Train: [41] [6000/6250] eta: 0:00:35 lr: 0.000084 grad: 0.0806 (0.0824) loss: 0.8214 (0.8224) time: 0.1529 data: 0.0780 max mem: 9390 +Train: [41] [6100/6250] eta: 0:00:21 lr: 0.000084 grad: 0.0869 (0.0824) loss: 0.8181 (0.8224) time: 0.1284 data: 0.0527 max mem: 9390 +Train: [41] [6200/6250] eta: 0:00:07 lr: 0.000084 grad: 0.0848 (0.0825) loss: 0.8145 (0.8223) time: 0.1086 data: 0.0246 max mem: 9390 +Train: [41] [6249/6250] eta: 0:00:00 lr: 0.000084 grad: 0.0824 (0.0825) loss: 0.8141 (0.8222) time: 0.1224 data: 0.0413 max mem: 9390 +Train: [41] Total time: 0:14:45 (0.1416 s / it) +Averaged stats: lr: 0.000084 grad: 0.0824 (0.0825) loss: 0.8141 (0.8222) +Eval (hcp-train-subset): [41] [ 0/62] eta: 0:04:32 loss: 0.8505 (0.8505) time: 4.3938 data: 4.3588 max mem: 9390 +Eval (hcp-train-subset): [41] [61/62] eta: 0:00:00 loss: 0.8375 (0.8385) time: 0.1288 data: 0.1040 max mem: 9390 +Eval (hcp-train-subset): [41] Total time: 0:00:12 (0.2025 s / it) +Averaged stats (hcp-train-subset): loss: 0.8375 (0.8385) +Eval (hcp-val): [41] [ 0/62] eta: 0:04:06 loss: 0.8349 (0.8349) time: 3.9823 data: 3.9176 max mem: 9390 +Eval (hcp-val): [41] [61/62] eta: 0:00:00 loss: 0.8355 (0.8368) time: 0.1325 data: 0.1053 max mem: 9390 +Eval (hcp-val): [41] Total time: 0:00:12 (0.2096 s / it) +Averaged stats (hcp-val): loss: 0.8355 (0.8368) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +Train: [42] [ 0/6250] eta: 7:19:58 lr: 0.000084 grad: 0.1377 (0.1377) loss: 0.8286 (0.8286) time: 4.2238 data: 3.9677 max mem: 9390 +Train: [42] [ 100/6250] eta: 0:19:50 lr: 0.000084 grad: 0.0860 (0.0999) loss: 0.8219 (0.8249) time: 0.1412 data: 0.0534 max mem: 9390 +Train: [42] [ 200/6250] eta: 0:17:32 lr: 0.000084 grad: 0.0850 (0.0943) loss: 0.8216 (0.8224) time: 0.1579 data: 0.0724 max mem: 9390 +Train: [42] [ 300/6250] eta: 0:16:00 lr: 0.000084 grad: 0.0743 (0.0903) loss: 0.8320 (0.8237) time: 0.1474 data: 0.0663 max mem: 9390 +Train: [42] [ 400/6250] eta: 0:15:06 lr: 0.000084 grad: 0.0825 (0.0877) loss: 0.8243 (0.8248) time: 0.1312 data: 0.0479 max mem: 9390 +Train: [42] [ 500/6250] eta: 0:14:25 lr: 0.000084 grad: 0.0833 (0.0867) loss: 0.8246 (0.8255) time: 0.1477 data: 0.0674 max mem: 9390 +Train: [42] [ 600/6250] eta: 0:13:43 lr: 0.000084 grad: 0.0678 (0.0864) loss: 0.8316 (0.8259) time: 0.1230 data: 0.0457 max mem: 9390 +Train: [42] [ 700/6250] eta: 0:13:13 lr: 0.000084 grad: 0.0809 (0.0856) loss: 0.8163 (0.8254) time: 0.1084 data: 0.0300 max mem: 9390 +Train: [42] [ 800/6250] eta: 0:12:48 lr: 0.000084 grad: 0.0756 (0.0851) loss: 0.8263 (0.8252) time: 0.1285 data: 0.0440 max mem: 9390 +Train: [42] [ 900/6250] eta: 0:12:37 lr: 0.000083 grad: 0.0754 (0.0846) loss: 0.8171 (0.8249) time: 0.1662 data: 0.0832 max mem: 9390 +Train: [42] [1000/6250] eta: 0:12:23 lr: 0.000083 grad: 0.0761 (0.0841) loss: 0.8293 (0.8251) time: 0.1366 data: 0.0554 max mem: 9390 +Train: [42] [1100/6250] eta: 0:12:11 lr: 0.000083 grad: 0.0735 (0.0836) loss: 0.8283 (0.8253) time: 0.1430 data: 0.0683 max mem: 9390 +Train: [42] [1200/6250] eta: 0:11:58 lr: 0.000083 grad: 0.0764 (0.0832) loss: 0.8178 (0.8254) time: 0.1585 data: 0.0785 max mem: 9390 +Train: [42] [1300/6250] eta: 0:11:44 lr: 0.000083 grad: 0.0786 (0.0830) loss: 0.8197 (0.8252) time: 0.1571 data: 0.0805 max mem: 9390 +Train: [42] [1400/6250] eta: 0:11:28 lr: 0.000083 grad: 0.0804 (0.0828) loss: 0.8340 (0.8252) time: 0.1446 data: 0.0692 max mem: 9390 +Train: [42] [1500/6250] eta: 0:11:09 lr: 0.000083 grad: 0.0858 (0.0828) loss: 0.8223 (0.8249) time: 0.1287 data: 0.0465 max mem: 9390 +Train: [42] [1600/6250] eta: 0:10:53 lr: 0.000083 grad: 0.0782 (0.0827) loss: 0.8266 (0.8248) time: 0.1233 data: 0.0417 max mem: 9390 +Train: [42] [1700/6250] eta: 0:10:35 lr: 0.000083 grad: 0.0854 (0.0828) loss: 0.8168 (0.8246) time: 0.1374 data: 0.0568 max mem: 9390 +Train: [42] [1800/6250] eta: 0:10:22 lr: 0.000083 grad: 0.0742 (0.0828) loss: 0.8248 (0.8245) time: 0.1429 data: 0.0590 max mem: 9390 +Train: [42] [1900/6250] eta: 0:10:08 lr: 0.000083 grad: 0.0761 (0.0829) loss: 0.8262 (0.8243) time: 0.1294 data: 0.0515 max mem: 9390 +Train: [42] [2000/6250] eta: 0:09:56 lr: 0.000083 grad: 0.0823 (0.0829) loss: 0.8273 (0.8241) time: 0.1476 data: 0.0634 max mem: 9390 +Train: [42] [2100/6250] eta: 0:09:47 lr: 0.000083 grad: 0.0878 (0.0830) loss: 0.8232 (0.8241) time: 0.1606 data: 0.0743 max mem: 9390 +Train: [42] [2200/6250] eta: 0:09:33 lr: 0.000083 grad: 0.0805 (0.0831) loss: 0.8351 (0.8241) time: 0.1436 data: 0.0664 max mem: 9390 +Train: [42] [2300/6250] eta: 0:09:20 lr: 0.000083 grad: 0.0796 (0.0831) loss: 0.8252 (0.8240) time: 0.1706 data: 0.0868 max mem: 9390 +Train: [42] [2400/6250] eta: 0:09:07 lr: 0.000083 grad: 0.0810 (0.0831) loss: 0.8237 (0.8240) time: 0.1739 data: 0.0794 max mem: 9390 +Train: [42] [2500/6250] eta: 0:08:54 lr: 0.000083 grad: 0.0824 (0.0832) loss: 0.8252 (0.8239) time: 0.1265 data: 0.0197 max mem: 9390 +Train: [42] [2600/6250] eta: 0:08:40 lr: 0.000083 grad: 0.0814 (0.0832) loss: 0.8266 (0.8239) time: 0.1105 data: 0.0278 max mem: 9390 +Train: [42] [2700/6250] eta: 0:08:26 lr: 0.000083 grad: 0.0838 (0.0832) loss: 0.8238 (0.8239) time: 0.1390 data: 0.0502 max mem: 9390 +Train: [42] [2800/6250] eta: 0:08:12 lr: 0.000083 grad: 0.0767 (0.0833) loss: 0.8307 (0.8239) time: 0.1214 data: 0.0429 max mem: 9390 +Train: [42] [2900/6250] eta: 0:07:58 lr: 0.000083 grad: 0.0751 (0.0832) loss: 0.8216 (0.8239) time: 0.1678 data: 0.0894 max mem: 9390 +Train: [42] [3000/6250] eta: 0:07:44 lr: 0.000083 grad: 0.0753 (0.0831) loss: 0.8176 (0.8239) time: 0.1231 data: 0.0465 max mem: 9390 +Train: [42] [3100/6250] eta: 0:07:32 lr: 0.000083 grad: 0.0786 (0.0831) loss: 0.8190 (0.8238) time: 0.1293 data: 0.0542 max mem: 9390 +Train: [42] [3200/6250] eta: 0:07:19 lr: 0.000083 grad: 0.0782 (0.0831) loss: 0.8295 (0.8239) time: 0.2094 data: 0.1264 max mem: 9390 +Train: [42] [3300/6250] eta: 0:07:04 lr: 0.000083 grad: 0.0810 (0.0831) loss: 0.8189 (0.8239) time: 0.1416 data: 0.0529 max mem: 9390 +Train: [42] [3400/6250] eta: 0:06:50 lr: 0.000083 grad: 0.0771 (0.0830) loss: 0.8251 (0.8239) time: 0.0989 data: 0.0077 max mem: 9390 +Train: [42] [3500/6250] eta: 0:06:35 lr: 0.000083 grad: 0.0826 (0.0830) loss: 0.8210 (0.8239) time: 0.1457 data: 0.0679 max mem: 9390 +Train: [42] [3600/6250] eta: 0:06:21 lr: 0.000083 grad: 0.0815 (0.0831) loss: 0.8265 (0.8238) time: 0.1444 data: 0.0694 max mem: 9390 +Train: [42] [3700/6250] eta: 0:06:06 lr: 0.000083 grad: 0.0792 (0.0831) loss: 0.8181 (0.8238) time: 0.1534 data: 0.0789 max mem: 9390 +Train: [42] [3800/6250] eta: 0:05:52 lr: 0.000083 grad: 0.0805 (0.0831) loss: 0.8266 (0.8238) time: 0.1459 data: 0.0690 max mem: 9390 +Train: [42] [3900/6250] eta: 0:05:37 lr: 0.000083 grad: 0.0846 (0.0832) loss: 0.8156 (0.8237) time: 0.1401 data: 0.0621 max mem: 9390 +Train: [42] [4000/6250] eta: 0:05:23 lr: 0.000083 grad: 0.0826 (0.0833) loss: 0.8209 (0.8236) time: 0.1501 data: 0.0760 max mem: 9390 +Train: [42] [4100/6250] eta: 0:05:09 lr: 0.000082 grad: 0.0823 (0.0834) loss: 0.8219 (0.8235) time: 0.1227 data: 0.0403 max mem: 9390 +Train: [42] [4200/6250] eta: 0:04:55 lr: 0.000082 grad: 0.0864 (0.0835) loss: 0.8222 (0.8235) time: 0.1290 data: 0.0495 max mem: 9390 +Train: [42] [4300/6250] eta: 0:04:40 lr: 0.000082 grad: 0.0843 (0.0836) loss: 0.8168 (0.8234) time: 0.1614 data: 0.0807 max mem: 9390 +Train: [42] [4400/6250] eta: 0:04:27 lr: 0.000082 grad: 0.0843 (0.0836) loss: 0.8228 (0.8233) time: 0.2116 data: 0.1294 max mem: 9390 +Train: [42] [4500/6250] eta: 0:04:12 lr: 0.000082 grad: 0.0833 (0.0837) loss: 0.8209 (0.8233) time: 0.1283 data: 0.0475 max mem: 9390 +Train: [42] [4600/6250] eta: 0:03:58 lr: 0.000082 grad: 0.0864 (0.0838) loss: 0.8203 (0.8232) time: 0.1587 data: 0.0772 max mem: 9390 +Train: [42] [4700/6250] eta: 0:03:44 lr: 0.000082 grad: 0.0829 (0.0839) loss: 0.8202 (0.8231) time: 0.1699 data: 0.0931 max mem: 9390 +Train: [42] [4800/6250] eta: 0:03:30 lr: 0.000082 grad: 0.0814 (0.0839) loss: 0.8176 (0.8230) time: 0.1731 data: 0.0940 max mem: 9390 +Train: [42] [4900/6250] eta: 0:03:16 lr: 0.000082 grad: 0.0856 (0.0839) loss: 0.8182 (0.8230) time: 0.1344 data: 0.0495 max mem: 9390 +Train: [42] [5000/6250] eta: 0:03:01 lr: 0.000082 grad: 0.0820 (0.0840) loss: 0.8246 (0.8230) time: 0.1668 data: 0.0865 max mem: 9390 +Train: [42] [5100/6250] eta: 0:02:47 lr: 0.000082 grad: 0.0822 (0.0840) loss: 0.8268 (0.8229) time: 0.1358 data: 0.0561 max mem: 9390 +Train: [42] [5200/6250] eta: 0:02:32 lr: 0.000082 grad: 0.0776 (0.0840) loss: 0.8279 (0.8229) time: 0.1221 data: 0.0381 max mem: 9390 +Train: [42] [5300/6250] eta: 0:02:17 lr: 0.000082 grad: 0.0856 (0.0840) loss: 0.8239 (0.8230) time: 0.1253 data: 0.0450 max mem: 9390 +Train: [42] [5400/6250] eta: 0:02:02 lr: 0.000082 grad: 0.0825 (0.0841) loss: 0.8234 (0.8229) time: 0.1226 data: 0.0341 max mem: 9390 +Train: [42] [5500/6250] eta: 0:01:48 lr: 0.000082 grad: 0.0835 (0.0841) loss: 0.8238 (0.8229) time: 0.1407 data: 0.0601 max mem: 9390 +Train: [42] [5600/6250] eta: 0:01:33 lr: 0.000082 grad: 0.0847 (0.0842) loss: 0.8272 (0.8230) time: 0.1441 data: 0.0695 max mem: 9390 +Train: [42] [5700/6250] eta: 0:01:19 lr: 0.000082 grad: 0.0830 (0.0842) loss: 0.8272 (0.8230) time: 0.1441 data: 0.0700 max mem: 9390 +Train: [42] [5800/6250] eta: 0:01:04 lr: 0.000082 grad: 0.0812 (0.0841) loss: 0.8269 (0.8230) time: 0.1383 data: 0.0667 max mem: 9390 +Train: [42] [5900/6250] eta: 0:00:50 lr: 0.000082 grad: 0.0772 (0.0841) loss: 0.8288 (0.8231) time: 0.1460 data: 0.0680 max mem: 9390 +Train: [42] [6000/6250] eta: 0:00:35 lr: 0.000082 grad: 0.0799 (0.0841) loss: 0.8235 (0.8231) time: 0.1373 data: 0.0573 max mem: 9390 +Train: [42] [6100/6250] eta: 0:00:21 lr: 0.000082 grad: 0.0739 (0.0840) loss: 0.8267 (0.8231) time: 0.1763 data: 0.0947 max mem: 9390 +Train: [42] [6200/6250] eta: 0:00:07 lr: 0.000082 grad: 0.0797 (0.0840) loss: 0.8210 (0.8231) time: 0.1814 data: 0.1078 max mem: 9390 +Train: [42] [6249/6250] eta: 0:00:00 lr: 0.000082 grad: 0.0826 (0.0840) loss: 0.8210 (0.8231) time: 0.1366 data: 0.0582 max mem: 9390 +Train: [42] Total time: 0:15:03 (0.1445 s / it) +Averaged stats: lr: 0.000082 grad: 0.0826 (0.0840) loss: 0.8210 (0.8231) +Eval (hcp-train-subset): [42] [ 0/62] eta: 0:04:21 loss: 0.8506 (0.8506) time: 4.2137 data: 4.1843 max mem: 9390 +Eval (hcp-train-subset): [42] [61/62] eta: 0:00:00 loss: 0.8366 (0.8394) time: 0.1228 data: 0.0979 max mem: 9390 +Eval (hcp-train-subset): [42] Total time: 0:00:12 (0.1943 s / it) +Averaged stats (hcp-train-subset): loss: 0.8366 (0.8394) +Eval (hcp-val): [42] [ 0/62] eta: 0:04:49 loss: 0.8354 (0.8354) time: 4.6763 data: 4.6461 max mem: 9390 +Eval (hcp-val): [42] [61/62] eta: 0:00:00 loss: 0.8364 (0.8368) time: 0.1308 data: 0.1042 max mem: 9390 +Eval (hcp-val): [42] Total time: 0:00:12 (0.2066 s / it) +Averaged stats (hcp-val): loss: 0.8364 (0.8368) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +Train: [43] [ 0/6250] eta: 10:18:12 lr: 0.000082 grad: 0.1643 (0.1643) loss: 0.8310 (0.8310) time: 5.9349 data: 5.8371 max mem: 9390 +Train: [43] [ 100/6250] eta: 0:20:47 lr: 0.000082 grad: 0.0761 (0.0835) loss: 0.8304 (0.8356) time: 0.1611 data: 0.0669 max mem: 9390 +Train: [43] [ 200/6250] eta: 0:17:24 lr: 0.000082 grad: 0.0766 (0.0825) loss: 0.8157 (0.8281) time: 0.1393 data: 0.0557 max mem: 9390 +Train: [43] [ 300/6250] eta: 0:16:00 lr: 0.000082 grad: 0.0819 (0.0827) loss: 0.8191 (0.8265) time: 0.1321 data: 0.0504 max mem: 9390 +Train: [43] [ 400/6250] eta: 0:15:10 lr: 0.000082 grad: 0.0792 (0.0825) loss: 0.8218 (0.8257) time: 0.1441 data: 0.0617 max mem: 9390 +Train: [43] [ 500/6250] eta: 0:14:26 lr: 0.000082 grad: 0.0801 (0.0825) loss: 0.8207 (0.8252) time: 0.1448 data: 0.0622 max mem: 9390 +Train: [43] [ 600/6250] eta: 0:13:46 lr: 0.000082 grad: 0.0762 (0.0823) loss: 0.8205 (0.8247) time: 0.1156 data: 0.0385 max mem: 9390 +Train: [43] [ 700/6250] eta: 0:13:16 lr: 0.000082 grad: 0.0775 (0.0818) loss: 0.8324 (0.8246) time: 0.1335 data: 0.0553 max mem: 9390 +Train: [43] [ 800/6250] eta: 0:12:58 lr: 0.000082 grad: 0.0735 (0.0816) loss: 0.8295 (0.8245) time: 0.1687 data: 0.0867 max mem: 9390 +Train: [43] [ 900/6250] eta: 0:12:56 lr: 0.000082 grad: 0.0753 (0.0813) loss: 0.8241 (0.8244) time: 0.1525 data: 0.0804 max mem: 9390 +Train: [43] [1000/6250] eta: 0:12:47 lr: 0.000081 grad: 0.0824 (0.0813) loss: 0.8203 (0.8242) time: 0.1059 data: 0.0209 max mem: 9390 +Train: [43] [1100/6250] eta: 0:12:33 lr: 0.000081 grad: 0.0729 (0.0813) loss: 0.8219 (0.8241) time: 0.1837 data: 0.1103 max mem: 9390 +Train: [43] [1200/6250] eta: 0:12:18 lr: 0.000081 grad: 0.0792 (0.0812) loss: 0.8188 (0.8239) time: 0.1170 data: 0.0355 max mem: 9390 +Train: [43] [1300/6250] eta: 0:12:01 lr: 0.000081 grad: 0.0806 (0.0815) loss: 0.8226 (0.8236) time: 0.1474 data: 0.0676 max mem: 9390 +Train: [43] [1400/6250] eta: 0:11:43 lr: 0.000081 grad: 0.0839 (0.0817) loss: 0.8165 (0.8232) time: 0.1270 data: 0.0469 max mem: 9390 +Train: [43] [1500/6250] eta: 0:11:26 lr: 0.000081 grad: 0.0845 (0.0820) loss: 0.8127 (0.8229) time: 0.1343 data: 0.0524 max mem: 9390 +Train: [43] [1600/6250] eta: 0:11:09 lr: 0.000081 grad: 0.0845 (0.0822) loss: 0.8208 (0.8225) time: 0.1232 data: 0.0414 max mem: 9390 +Train: [43] [1700/6250] eta: 0:10:54 lr: 0.000081 grad: 0.0853 (0.0823) loss: 0.8132 (0.8222) time: 0.1573 data: 0.0738 max mem: 9390 +Train: [43] [1800/6250] eta: 0:10:43 lr: 0.000081 grad: 0.0826 (0.0825) loss: 0.8206 (0.8220) time: 0.1468 data: 0.0651 max mem: 9390 +Train: [43] [1900/6250] eta: 0:10:34 lr: 0.000081 grad: 0.0860 (0.0829) loss: 0.8173 (0.8216) time: 0.1427 data: 0.0641 max mem: 9390 +Train: [43] [2000/6250] eta: 0:10:20 lr: 0.000081 grad: 0.0868 (0.0831) loss: 0.8157 (0.8213) time: 0.1366 data: 0.0518 max mem: 9390 +Train: [43] [2100/6250] eta: 0:10:07 lr: 0.000081 grad: 0.0835 (0.0833) loss: 0.8195 (0.8211) time: 0.1462 data: 0.0676 max mem: 9390 +Train: [43] [2200/6250] eta: 0:09:54 lr: 0.000081 grad: 0.0879 (0.0835) loss: 0.8188 (0.8210) time: 0.1650 data: 0.0783 max mem: 9390 +Train: [43] [2300/6250] eta: 0:09:42 lr: 0.000081 grad: 0.0805 (0.0836) loss: 0.8158 (0.8208) time: 0.2084 data: 0.1290 max mem: 9390 +Train: [43] [2400/6250] eta: 0:09:28 lr: 0.000081 grad: 0.0902 (0.0838) loss: 0.8131 (0.8207) time: 0.1091 data: 0.0178 max mem: 9390 +Train: [43] [2500/6250] eta: 0:09:13 lr: 0.000081 grad: 0.0831 (0.0841) loss: 0.8216 (0.8205) time: 0.1493 data: 0.0599 max mem: 9390 +Train: [43] [2600/6250] eta: 0:09:00 lr: 0.000081 grad: 0.0860 (0.0843) loss: 0.8210 (0.8204) time: 0.1503 data: 0.0666 max mem: 9390 +Train: [43] [2700/6250] eta: 0:08:45 lr: 0.000081 grad: 0.0832 (0.0846) loss: 0.8209 (0.8204) time: 0.1331 data: 0.0389 max mem: 9390 +Train: [43] [2800/6250] eta: 0:08:31 lr: 0.000081 grad: 0.0883 (0.0846) loss: 0.8109 (0.8203) time: 0.1611 data: 0.0796 max mem: 9390 +Train: [43] [2900/6250] eta: 0:08:21 lr: 0.000081 grad: 0.0841 (0.0847) loss: 0.8208 (0.8203) time: 0.3345 data: 0.2019 max mem: 9390 +Train: [43] [3000/6250] eta: 0:08:03 lr: 0.000081 grad: 0.0845 (0.0847) loss: 0.8219 (0.8203) time: 0.1378 data: 0.0566 max mem: 9390 +Train: [43] [3100/6250] eta: 0:07:48 lr: 0.000081 grad: 0.0825 (0.0848) loss: 0.8246 (0.8203) time: 0.1527 data: 0.0735 max mem: 9390 +Train: [43] [3200/6250] eta: 0:07:33 lr: 0.000081 grad: 0.0870 (0.0850) loss: 0.8179 (0.8203) time: 0.1495 data: 0.0638 max mem: 9390 +Train: [43] [3300/6250] eta: 0:07:17 lr: 0.000081 grad: 0.0813 (0.0850) loss: 0.8254 (0.8204) time: 0.1296 data: 0.0480 max mem: 9390 +Train: [43] [3400/6250] eta: 0:07:02 lr: 0.000081 grad: 0.0849 (0.0851) loss: 0.8255 (0.8203) time: 0.1561 data: 0.0753 max mem: 9390 +Train: [43] [3500/6250] eta: 0:06:47 lr: 0.000081 grad: 0.0839 (0.0852) loss: 0.8151 (0.8202) time: 0.1513 data: 0.0738 max mem: 9390 +Train: [43] [3600/6250] eta: 0:06:32 lr: 0.000081 grad: 0.0856 (0.0852) loss: 0.8185 (0.8202) time: 0.1330 data: 0.0527 max mem: 9390 +Train: [43] [3700/6250] eta: 0:06:17 lr: 0.000081 grad: 0.0870 (0.0853) loss: 0.8271 (0.8202) time: 0.1551 data: 0.0755 max mem: 9390 +Train: [43] [3800/6250] eta: 0:06:02 lr: 0.000081 grad: 0.0803 (0.0854) loss: 0.8197 (0.8202) time: 0.1305 data: 0.0384 max mem: 9390 +Train: [43] [3900/6250] eta: 0:05:47 lr: 0.000081 grad: 0.0877 (0.0854) loss: 0.8196 (0.8202) time: 0.1358 data: 0.0601 max mem: 9390 +Train: [43] [4000/6250] eta: 0:05:33 lr: 0.000081 grad: 0.0916 (0.0855) loss: 0.8085 (0.8201) time: 0.1488 data: 0.0674 max mem: 9390 +Train: [43] [4100/6250] eta: 0:05:19 lr: 0.000081 grad: 0.0858 (0.0855) loss: 0.8254 (0.8201) time: 0.2183 data: 0.0888 max mem: 9390 +Train: [43] [4200/6250] eta: 0:05:04 lr: 0.000080 grad: 0.0895 (0.0856) loss: 0.8226 (0.8201) time: 0.1551 data: 0.0800 max mem: 9390 +Train: [43] [4300/6250] eta: 0:04:49 lr: 0.000080 grad: 0.0846 (0.0857) loss: 0.8206 (0.8201) time: 0.1778 data: 0.0962 max mem: 9390 +Train: [43] [4400/6250] eta: 0:04:35 lr: 0.000080 grad: 0.0804 (0.0857) loss: 0.8160 (0.8201) time: 0.1012 data: 0.0218 max mem: 9390 +Train: [43] [4500/6250] eta: 0:04:20 lr: 0.000080 grad: 0.0826 (0.0857) loss: 0.8236 (0.8200) time: 0.1546 data: 0.0760 max mem: 9390 +Train: [43] [4600/6250] eta: 0:04:05 lr: 0.000080 grad: 0.0885 (0.0858) loss: 0.8183 (0.8200) time: 0.1640 data: 0.0877 max mem: 9390 +Train: [43] [4700/6250] eta: 0:03:51 lr: 0.000080 grad: 0.0883 (0.0858) loss: 0.8148 (0.8199) time: 0.1389 data: 0.0605 max mem: 9390 +Train: [43] [4800/6250] eta: 0:03:36 lr: 0.000080 grad: 0.0865 (0.0859) loss: 0.8197 (0.8199) time: 0.1585 data: 0.0806 max mem: 9390 +Train: [43] [4900/6250] eta: 0:03:21 lr: 0.000080 grad: 0.0924 (0.0860) loss: 0.8206 (0.8198) time: 0.1507 data: 0.0721 max mem: 9390 +Train: [43] [5000/6250] eta: 0:03:06 lr: 0.000080 grad: 0.0899 (0.0861) loss: 0.8179 (0.8197) time: 0.1502 data: 0.0655 max mem: 9390 +Train: [43] [5100/6250] eta: 0:02:51 lr: 0.000080 grad: 0.0869 (0.0862) loss: 0.8137 (0.8197) time: 0.1353 data: 0.0582 max mem: 9390 +Train: [43] [5200/6250] eta: 0:02:36 lr: 0.000080 grad: 0.0775 (0.0862) loss: 0.8251 (0.8197) time: 0.1338 data: 0.0526 max mem: 9390 +Train: [43] [5300/6250] eta: 0:02:21 lr: 0.000080 grad: 0.0856 (0.0862) loss: 0.8251 (0.8197) time: 0.1189 data: 0.0381 max mem: 9390 +Train: [43] [5400/6250] eta: 0:02:05 lr: 0.000080 grad: 0.0867 (0.0863) loss: 0.8216 (0.8197) time: 0.1163 data: 0.0257 max mem: 9390 +Train: [43] [5500/6250] eta: 0:01:50 lr: 0.000080 grad: 0.0926 (0.0863) loss: 0.8155 (0.8197) time: 0.1299 data: 0.0543 max mem: 9390 +Train: [43] [5600/6250] eta: 0:01:35 lr: 0.000080 grad: 0.0824 (0.0863) loss: 0.8204 (0.8197) time: 0.1564 data: 0.0763 max mem: 9390 +Train: [43] [5700/6250] eta: 0:01:21 lr: 0.000080 grad: 0.0851 (0.0863) loss: 0.8153 (0.8197) time: 0.1888 data: 0.1006 max mem: 9390 +Train: [43] [5800/6250] eta: 0:01:06 lr: 0.000080 grad: 0.0787 (0.0863) loss: 0.8200 (0.8197) time: 0.1489 data: 0.0692 max mem: 9390 +Train: [43] [5900/6250] eta: 0:00:51 lr: 0.000080 grad: 0.0780 (0.0864) loss: 0.8250 (0.8197) time: 0.1177 data: 0.0437 max mem: 9390 +Train: [43] [6000/6250] eta: 0:00:36 lr: 0.000080 grad: 0.0842 (0.0864) loss: 0.8200 (0.8197) time: 0.1528 data: 0.0753 max mem: 9390 +Train: [43] [6100/6250] eta: 0:00:22 lr: 0.000080 grad: 0.0892 (0.0864) loss: 0.8198 (0.8197) time: 0.1413 data: 0.0649 max mem: 9390 +Train: [43] [6200/6250] eta: 0:00:07 lr: 0.000080 grad: 0.0861 (0.0864) loss: 0.8213 (0.8197) time: 0.1583 data: 0.0772 max mem: 9390 +Train: [43] [6249/6250] eta: 0:00:00 lr: 0.000080 grad: 0.0846 (0.0864) loss: 0.8215 (0.8197) time: 0.1333 data: 0.0534 max mem: 9390 +Train: [43] Total time: 0:15:22 (0.1475 s / it) +Averaged stats: lr: 0.000080 grad: 0.0846 (0.0864) loss: 0.8215 (0.8197) +Eval (hcp-train-subset): [43] [ 0/62] eta: 0:04:52 loss: 0.8443 (0.8443) time: 4.7152 data: 4.6844 max mem: 9390 +Eval (hcp-train-subset): [43] [61/62] eta: 0:00:00 loss: 0.8392 (0.8397) time: 0.1170 data: 0.0898 max mem: 9390 +Eval (hcp-train-subset): [43] Total time: 0:00:12 (0.1998 s / it) +Averaged stats (hcp-train-subset): loss: 0.8392 (0.8397) +Eval (hcp-val): [43] [ 0/62] eta: 0:03:05 loss: 0.8397 (0.8397) time: 2.9868 data: 2.9183 max mem: 9390 +Eval (hcp-val): [43] [61/62] eta: 0:00:00 loss: 0.8360 (0.8379) time: 0.1189 data: 0.0920 max mem: 9390 +Eval (hcp-val): [43] Total time: 0:00:12 (0.1995 s / it) +Averaged stats (hcp-val): loss: 0.8360 (0.8379) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +Train: [44] [ 0/6250] eta: 10:19:04 lr: 0.000080 grad: 0.1496 (0.1496) loss: 0.8356 (0.8356) time: 5.9431 data: 5.8431 max mem: 9390 +Train: [44] [ 100/6250] eta: 0:19:56 lr: 0.000080 grad: 0.0810 (0.0960) loss: 0.8276 (0.8370) time: 0.1307 data: 0.0360 max mem: 9390 +Train: [44] [ 200/6250] eta: 0:17:09 lr: 0.000080 grad: 0.0822 (0.0913) loss: 0.8335 (0.8353) time: 0.1564 data: 0.0636 max mem: 9390 +Train: [44] [ 300/6250] eta: 0:15:59 lr: 0.000080 grad: 0.0783 (0.0890) loss: 0.8305 (0.8329) time: 0.1456 data: 0.0629 max mem: 9390 +Train: [44] [ 400/6250] eta: 0:15:11 lr: 0.000080 grad: 0.0904 (0.0878) loss: 0.8170 (0.8305) time: 0.1332 data: 0.0485 max mem: 9390 +Train: [44] [ 500/6250] eta: 0:14:24 lr: 0.000080 grad: 0.0819 (0.0876) loss: 0.8215 (0.8289) time: 0.1244 data: 0.0405 max mem: 9390 +Train: [44] [ 600/6250] eta: 0:13:48 lr: 0.000080 grad: 0.0812 (0.0874) loss: 0.8266 (0.8275) time: 0.1359 data: 0.0565 max mem: 9390 +Train: [44] [ 700/6250] eta: 0:13:15 lr: 0.000080 grad: 0.0832 (0.0868) loss: 0.8225 (0.8264) time: 0.1330 data: 0.0447 max mem: 9390 +Train: [44] [ 800/6250] eta: 0:12:45 lr: 0.000080 grad: 0.0780 (0.0865) loss: 0.8191 (0.8255) time: 0.1139 data: 0.0321 max mem: 9390 +Train: [44] [ 900/6250] eta: 0:12:31 lr: 0.000080 grad: 0.0862 (0.0864) loss: 0.8207 (0.8250) time: 0.1492 data: 0.0601 max mem: 9390 +Train: [44] [1000/6250] eta: 0:12:20 lr: 0.000080 grad: 0.0854 (0.0861) loss: 0.8202 (0.8246) time: 0.1419 data: 0.0612 max mem: 9390 +Train: [44] [1100/6250] eta: 0:12:09 lr: 0.000079 grad: 0.0833 (0.0861) loss: 0.8174 (0.8240) time: 0.1483 data: 0.0734 max mem: 9390 +Train: [44] [1200/6250] eta: 0:11:52 lr: 0.000079 grad: 0.0817 (0.0861) loss: 0.8220 (0.8238) time: 0.1328 data: 0.0534 max mem: 9390 +Train: [44] [1300/6250] eta: 0:11:39 lr: 0.000079 grad: 0.0870 (0.0861) loss: 0.8142 (0.8233) time: 0.1475 data: 0.0676 max mem: 9390 +Train: [44] [1400/6250] eta: 0:11:22 lr: 0.000079 grad: 0.0791 (0.0861) loss: 0.8177 (0.8230) time: 0.1117 data: 0.0315 max mem: 9390 +Train: [44] [1500/6250] eta: 0:11:07 lr: 0.000079 grad: 0.0857 (0.0863) loss: 0.8171 (0.8228) time: 0.1373 data: 0.0615 max mem: 9390 +Train: [44] [1600/6250] eta: 0:10:50 lr: 0.000079 grad: 0.0839 (0.0865) loss: 0.8201 (0.8226) time: 0.1350 data: 0.0539 max mem: 9390 +Train: [44] [1700/6250] eta: 0:10:36 lr: 0.000079 grad: 0.0843 (0.0865) loss: 0.8152 (0.8223) time: 0.1325 data: 0.0512 max mem: 9390 +Train: [44] [1800/6250] eta: 0:10:23 lr: 0.000079 grad: 0.0808 (0.0866) loss: 0.8288 (0.8222) time: 0.1298 data: 0.0501 max mem: 9390 +Train: [44] [1900/6250] eta: 0:10:11 lr: 0.000079 grad: 0.0867 (0.0866) loss: 0.8195 (0.8222) time: 0.1427 data: 0.0588 max mem: 9390 +Train: [44] [2000/6250] eta: 0:09:59 lr: 0.000079 grad: 0.0844 (0.0865) loss: 0.8208 (0.8221) time: 0.1473 data: 0.0666 max mem: 9390 +Train: [44] [2100/6250] eta: 0:09:47 lr: 0.000079 grad: 0.0806 (0.0865) loss: 0.8234 (0.8221) time: 0.1641 data: 0.0791 max mem: 9390 +Train: [44] [2200/6250] eta: 0:09:33 lr: 0.000079 grad: 0.0857 (0.0865) loss: 0.8253 (0.8221) time: 0.1488 data: 0.0718 max mem: 9390 +Train: [44] [2300/6250] eta: 0:09:20 lr: 0.000079 grad: 0.0851 (0.0865) loss: 0.8201 (0.8222) time: 0.1375 data: 0.0519 max mem: 9390 +Train: [44] [2400/6250] eta: 0:09:07 lr: 0.000079 grad: 0.0819 (0.0865) loss: 0.8252 (0.8222) time: 0.1357 data: 0.0570 max mem: 9390 +Train: [44] [2500/6250] eta: 0:08:53 lr: 0.000079 grad: 0.0896 (0.0865) loss: 0.8243 (0.8222) time: 0.1608 data: 0.0839 max mem: 9390 +Train: [44] [2600/6250] eta: 0:08:38 lr: 0.000079 grad: 0.0859 (0.0866) loss: 0.8225 (0.8222) time: 0.1468 data: 0.0595 max mem: 9390 +Train: [44] [2700/6250] eta: 0:08:24 lr: 0.000079 grad: 0.0865 (0.0867) loss: 0.8155 (0.8222) time: 0.1365 data: 0.0597 max mem: 9390 +Train: [44] [2800/6250] eta: 0:08:10 lr: 0.000079 grad: 0.0829 (0.0868) loss: 0.8196 (0.8222) time: 0.1226 data: 0.0466 max mem: 9390 +Train: [44] [2900/6250] eta: 0:07:56 lr: 0.000079 grad: 0.0842 (0.0869) loss: 0.8233 (0.8222) time: 0.1696 data: 0.0896 max mem: 9390 +Train: [44] [3000/6250] eta: 0:07:41 lr: 0.000079 grad: 0.0813 (0.0869) loss: 0.8219 (0.8222) time: 0.1100 data: 0.0314 max mem: 9390 +Train: [44] [3100/6250] eta: 0:07:27 lr: 0.000079 grad: 0.0811 (0.0868) loss: 0.8297 (0.8222) time: 0.1555 data: 0.0799 max mem: 9390 +Train: [44] [3200/6250] eta: 0:07:12 lr: 0.000079 grad: 0.0808 (0.0868) loss: 0.8286 (0.8223) time: 0.1294 data: 0.0472 max mem: 9390 +Train: [44] [3300/6250] eta: 0:06:58 lr: 0.000079 grad: 0.0819 (0.0868) loss: 0.8215 (0.8223) time: 0.1441 data: 0.0546 max mem: 9390 +Train: [44] [3400/6250] eta: 0:06:44 lr: 0.000079 grad: 0.0841 (0.0867) loss: 0.8191 (0.8224) time: 0.1272 data: 0.0349 max mem: 9390 +Train: [44] [3500/6250] eta: 0:06:32 lr: 0.000079 grad: 0.0823 (0.0867) loss: 0.8204 (0.8224) time: 0.1260 data: 0.0445 max mem: 9390 +Train: [44] [3600/6250] eta: 0:06:17 lr: 0.000079 grad: 0.0810 (0.0867) loss: 0.8166 (0.8224) time: 0.1319 data: 0.0564 max mem: 9390 +Train: [44] [3700/6250] eta: 0:06:03 lr: 0.000079 grad: 0.0873 (0.0866) loss: 0.8232 (0.8225) time: 0.1536 data: 0.0760 max mem: 9390 +Train: [44] [3800/6250] eta: 0:05:48 lr: 0.000079 grad: 0.0785 (0.0866) loss: 0.8281 (0.8225) time: 0.1376 data: 0.0519 max mem: 9390 +Train: [44] [3900/6250] eta: 0:05:35 lr: 0.000079 grad: 0.0801 (0.0865) loss: 0.8292 (0.8226) time: 0.2283 data: 0.1503 max mem: 9390 +Train: [44] [4000/6250] eta: 0:05:20 lr: 0.000079 grad: 0.0800 (0.0865) loss: 0.8272 (0.8227) time: 0.1378 data: 0.0584 max mem: 9390 +Train: [44] [4100/6250] eta: 0:05:06 lr: 0.000079 grad: 0.0774 (0.0864) loss: 0.8260 (0.8227) time: 0.1424 data: 0.0671 max mem: 9390 +Train: [44] [4200/6250] eta: 0:04:53 lr: 0.000078 grad: 0.0759 (0.0863) loss: 0.8288 (0.8228) time: 0.1940 data: 0.1211 max mem: 9390 +Train: [44] [4300/6250] eta: 0:04:38 lr: 0.000078 grad: 0.0831 (0.0862) loss: 0.8239 (0.8229) time: 0.1548 data: 0.0743 max mem: 9390 +Train: [44] [4400/6250] eta: 0:04:24 lr: 0.000078 grad: 0.0818 (0.0862) loss: 0.8258 (0.8229) time: 0.1721 data: 0.0822 max mem: 9390 +Train: [44] [4500/6250] eta: 0:04:11 lr: 0.000078 grad: 0.0827 (0.0861) loss: 0.8292 (0.8230) time: 0.1360 data: 0.0552 max mem: 9390 +Train: [44] [4600/6250] eta: 0:03:57 lr: 0.000078 grad: 0.0771 (0.0861) loss: 0.8194 (0.8231) time: 0.1599 data: 0.0757 max mem: 9390 +Train: [44] [4700/6250] eta: 0:03:42 lr: 0.000078 grad: 0.0823 (0.0860) loss: 0.8217 (0.8231) time: 0.1627 data: 0.0839 max mem: 9390 +Train: [44] [4800/6250] eta: 0:03:29 lr: 0.000078 grad: 0.0820 (0.0860) loss: 0.8222 (0.8231) time: 0.1540 data: 0.0653 max mem: 9390 +Train: [44] [4900/6250] eta: 0:03:14 lr: 0.000078 grad: 0.0799 (0.0860) loss: 0.8229 (0.8231) time: 0.1339 data: 0.0525 max mem: 9390 +Train: [44] [5000/6250] eta: 0:02:59 lr: 0.000078 grad: 0.0831 (0.0860) loss: 0.8252 (0.8231) time: 0.1392 data: 0.0591 max mem: 9390 +Train: [44] [5100/6250] eta: 0:02:45 lr: 0.000078 grad: 0.0794 (0.0860) loss: 0.8255 (0.8230) time: 0.1322 data: 0.0542 max mem: 9390 +Train: [44] [5200/6250] eta: 0:02:30 lr: 0.000078 grad: 0.0916 (0.0860) loss: 0.8200 (0.8230) time: 0.1310 data: 0.0525 max mem: 9390 +Train: [44] [5300/6250] eta: 0:02:16 lr: 0.000078 grad: 0.0767 (0.0860) loss: 0.8250 (0.8230) time: 0.1360 data: 0.0533 max mem: 9390 +Train: [44] [5400/6250] eta: 0:02:01 lr: 0.000078 grad: 0.0789 (0.0860) loss: 0.8254 (0.8230) time: 0.1383 data: 0.0571 max mem: 9390 +Train: [44] [5500/6250] eta: 0:01:46 lr: 0.000078 grad: 0.0860 (0.0860) loss: 0.8195 (0.8229) time: 0.1001 data: 0.0080 max mem: 9390 +Train: [44] [5600/6250] eta: 0:01:32 lr: 0.000078 grad: 0.0929 (0.0860) loss: 0.8120 (0.8229) time: 0.1127 data: 0.0319 max mem: 9390 +Train: [44] [5700/6250] eta: 0:01:17 lr: 0.000078 grad: 0.0837 (0.0860) loss: 0.8173 (0.8228) time: 0.1124 data: 0.0308 max mem: 9390 +Train: [44] [5800/6250] eta: 0:01:03 lr: 0.000078 grad: 0.0842 (0.0861) loss: 0.8181 (0.8227) time: 0.1427 data: 0.0521 max mem: 9390 +Train: [44] [5900/6250] eta: 0:00:49 lr: 0.000078 grad: 0.0802 (0.0861) loss: 0.8182 (0.8226) time: 0.1318 data: 0.0524 max mem: 9390 +Train: [44] [6000/6250] eta: 0:00:35 lr: 0.000078 grad: 0.0864 (0.0861) loss: 0.8216 (0.8226) time: 0.1296 data: 0.0454 max mem: 9390 +Train: [44] [6100/6250] eta: 0:00:21 lr: 0.000078 grad: 0.0839 (0.0861) loss: 0.8256 (0.8226) time: 0.1260 data: 0.0494 max mem: 9390 +Train: [44] [6200/6250] eta: 0:00:07 lr: 0.000078 grad: 0.0856 (0.0860) loss: 0.8252 (0.8225) time: 0.1276 data: 0.0522 max mem: 9390 +Train: [44] [6249/6250] eta: 0:00:00 lr: 0.000078 grad: 0.0837 (0.0861) loss: 0.8176 (0.8225) time: 0.1244 data: 0.0403 max mem: 9390 +Train: [44] Total time: 0:14:46 (0.1418 s / it) +Averaged stats: lr: 0.000078 grad: 0.0837 (0.0861) loss: 0.8176 (0.8225) +Eval (hcp-train-subset): [44] [ 0/62] eta: 0:03:04 loss: 0.8503 (0.8503) time: 2.9738 data: 2.8940 max mem: 9390 +Eval (hcp-train-subset): [44] [61/62] eta: 0:00:00 loss: 0.8392 (0.8399) time: 0.1172 data: 0.0924 max mem: 9390 +Eval (hcp-train-subset): [44] Total time: 0:00:12 (0.2018 s / it) +Averaged stats (hcp-train-subset): loss: 0.8392 (0.8399) +Making plots (hcp-train-subset): example=12 +Eval (hcp-val): [44] [ 0/62] eta: 0:05:10 loss: 0.8349 (0.8349) time: 5.0152 data: 4.9796 max mem: 9390 +Eval (hcp-val): [44] [61/62] eta: 0:00:00 loss: 0.8363 (0.8364) time: 0.1269 data: 0.1017 max mem: 9390 +Eval (hcp-val): [44] Total time: 0:00:12 (0.2057 s / it) +Averaged stats (hcp-val): loss: 0.8363 (0.8364) +Making plots (hcp-val): example=5 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +Train: [45] [ 0/6250] eta: 10:04:25 lr: 0.000078 grad: 0.1304 (0.1304) loss: 0.8147 (0.8147) time: 5.8026 data: 5.6707 max mem: 9390 +Train: [45] [ 100/6250] eta: 0:18:56 lr: 0.000078 grad: 0.0839 (0.0980) loss: 0.8255 (0.8326) time: 0.1358 data: 0.0533 max mem: 9390 +Train: [45] [ 200/6250] eta: 0:16:20 lr: 0.000078 grad: 0.0854 (0.0953) loss: 0.8318 (0.8296) time: 0.1526 data: 0.0665 max mem: 9390 +Train: [45] [ 300/6250] eta: 0:15:41 lr: 0.000078 grad: 0.0813 (0.0920) loss: 0.8318 (0.8292) time: 0.1284 data: 0.0351 max mem: 9390 +Train: [45] [ 400/6250] eta: 0:15:06 lr: 0.000078 grad: 0.0804 (0.0902) loss: 0.8278 (0.8286) time: 0.1320 data: 0.0527 max mem: 9390 +Train: [45] [ 500/6250] eta: 0:14:23 lr: 0.000078 grad: 0.0788 (0.0892) loss: 0.8225 (0.8276) time: 0.1317 data: 0.0509 max mem: 9390 +Train: [45] [ 600/6250] eta: 0:13:51 lr: 0.000078 grad: 0.0771 (0.0887) loss: 0.8224 (0.8268) time: 0.1451 data: 0.0670 max mem: 9390 +Train: [45] [ 700/6250] eta: 0:13:15 lr: 0.000078 grad: 0.0817 (0.0881) loss: 0.8217 (0.8262) time: 0.1312 data: 0.0463 max mem: 9390 +Train: [45] [ 800/6250] eta: 0:12:45 lr: 0.000078 grad: 0.0856 (0.0879) loss: 0.8286 (0.8261) time: 0.1075 data: 0.0237 max mem: 9390 +Train: [45] [ 900/6250] eta: 0:12:20 lr: 0.000078 grad: 0.0771 (0.0874) loss: 0.8299 (0.8260) time: 0.1312 data: 0.0531 max mem: 9390 +Train: [45] [1000/6250] eta: 0:11:58 lr: 0.000078 grad: 0.0869 (0.0873) loss: 0.8277 (0.8256) time: 0.1381 data: 0.0581 max mem: 9390 +Train: [45] [1100/6250] eta: 0:11:50 lr: 0.000077 grad: 0.0850 (0.0871) loss: 0.8246 (0.8257) time: 0.1535 data: 0.0690 max mem: 9390 +Train: [45] [1200/6250] eta: 0:11:37 lr: 0.000077 grad: 0.0830 (0.0870) loss: 0.8231 (0.8255) time: 0.1224 data: 0.0442 max mem: 9390 +Train: [45] [1300/6250] eta: 0:11:21 lr: 0.000077 grad: 0.0847 (0.0871) loss: 0.8252 (0.8253) time: 0.1358 data: 0.0555 max mem: 9390 +Train: [45] [1400/6250] eta: 0:11:05 lr: 0.000077 grad: 0.0863 (0.0871) loss: 0.8232 (0.8251) time: 0.1371 data: 0.0584 max mem: 9390 +Train: [45] [1500/6250] eta: 0:10:50 lr: 0.000077 grad: 0.0850 (0.0871) loss: 0.8206 (0.8247) time: 0.1262 data: 0.0507 max mem: 9390 +Train: [45] [1600/6250] eta: 0:10:34 lr: 0.000077 grad: 0.0867 (0.0872) loss: 0.8253 (0.8243) time: 0.1328 data: 0.0571 max mem: 9390 +Train: [45] [1700/6250] eta: 0:10:17 lr: 0.000077 grad: 0.0822 (0.0871) loss: 0.8228 (0.8241) time: 0.1313 data: 0.0570 max mem: 9390 +Train: [45] [1800/6250] eta: 0:10:02 lr: 0.000077 grad: 0.0883 (0.0872) loss: 0.8185 (0.8238) time: 0.1293 data: 0.0519 max mem: 9390 +Train: [45] [1900/6250] eta: 0:09:48 lr: 0.000077 grad: 0.0840 (0.0874) loss: 0.8184 (0.8234) time: 0.1282 data: 0.0475 max mem: 9390 +Train: [45] [2000/6250] eta: 0:09:35 lr: 0.000077 grad: 0.0855 (0.0874) loss: 0.8177 (0.8231) time: 0.1432 data: 0.0681 max mem: 9390 +Train: [45] [2100/6250] eta: 0:09:24 lr: 0.000077 grad: 0.0904 (0.0876) loss: 0.8198 (0.8229) time: 0.1461 data: 0.0625 max mem: 9390 +Train: [45] [2200/6250] eta: 0:09:13 lr: 0.000077 grad: 0.0844 (0.0876) loss: 0.8199 (0.8225) time: 0.1425 data: 0.0584 max mem: 9390 +Train: [45] [2300/6250] eta: 0:09:02 lr: 0.000077 grad: 0.0847 (0.0878) loss: 0.8145 (0.8223) time: 0.1553 data: 0.0659 max mem: 9390 +Train: [45] [2400/6250] eta: 0:08:50 lr: 0.000077 grad: 0.0896 (0.0880) loss: 0.8201 (0.8221) time: 0.1550 data: 0.0812 max mem: 9390 +Train: [45] [2500/6250] eta: 0:08:39 lr: 0.000077 grad: 0.0850 (0.0883) loss: 0.8180 (0.8221) time: 0.1298 data: 0.0353 max mem: 9390 +Train: [45] [2600/6250] eta: 0:08:27 lr: 0.000077 grad: 0.0820 (0.0883) loss: 0.8263 (0.8220) time: 0.1411 data: 0.0638 max mem: 9390 +Train: [45] [2700/6250] eta: 0:08:14 lr: 0.000077 grad: 0.0857 (0.0884) loss: 0.8151 (0.8218) time: 0.1452 data: 0.0610 max mem: 9390 +Train: [45] [2800/6250] eta: 0:08:01 lr: 0.000077 grad: 0.0822 (0.0885) loss: 0.8242 (0.8217) time: 0.1459 data: 0.0721 max mem: 9390 +Train: [45] [2900/6250] eta: 0:07:47 lr: 0.000077 grad: 0.0850 (0.0886) loss: 0.8176 (0.8216) time: 0.1333 data: 0.0554 max mem: 9390 +Train: [45] [3000/6250] eta: 0:07:34 lr: 0.000077 grad: 0.0916 (0.0887) loss: 0.8153 (0.8215) time: 0.1741 data: 0.0957 max mem: 9390 +Train: [45] [3100/6250] eta: 0:07:21 lr: 0.000077 grad: 0.0862 (0.0887) loss: 0.8226 (0.8214) time: 0.1363 data: 0.0532 max mem: 9390 +Train: [45] [3200/6250] eta: 0:07:07 lr: 0.000077 grad: 0.0879 (0.0888) loss: 0.8172 (0.8213) time: 0.1483 data: 0.0708 max mem: 9390 +Train: [45] [3300/6250] eta: 0:06:55 lr: 0.000077 grad: 0.0916 (0.0889) loss: 0.8212 (0.8212) time: 0.1879 data: 0.1153 max mem: 9390 +Train: [45] [3400/6250] eta: 0:06:40 lr: 0.000077 grad: 0.0874 (0.0891) loss: 0.8147 (0.8211) time: 0.1500 data: 0.0724 max mem: 9390 +Train: [45] [3500/6250] eta: 0:06:26 lr: 0.000077 grad: 0.0906 (0.0892) loss: 0.8139 (0.8210) time: 0.1483 data: 0.0716 max mem: 9390 +Train: [45] [3600/6250] eta: 0:06:14 lr: 0.000077 grad: 0.0848 (0.0891) loss: 0.8194 (0.8209) time: 0.0900 data: 0.0002 max mem: 9390 +Train: [45] [3700/6250] eta: 0:05:59 lr: 0.000077 grad: 0.0925 (0.0893) loss: 0.8222 (0.8209) time: 0.1352 data: 0.0596 max mem: 9390 +Train: [45] [3800/6250] eta: 0:05:45 lr: 0.000077 grad: 0.0858 (0.0893) loss: 0.8200 (0.8209) time: 0.1243 data: 0.0466 max mem: 9390 +Train: [45] [3900/6250] eta: 0:05:30 lr: 0.000077 grad: 0.0861 (0.0893) loss: 0.8248 (0.8209) time: 0.1475 data: 0.0708 max mem: 9390 +Train: [45] [4000/6250] eta: 0:05:16 lr: 0.000077 grad: 0.0817 (0.0895) loss: 0.8252 (0.8209) time: 0.1614 data: 0.0901 max mem: 9390 +Train: [45] [4100/6250] eta: 0:05:02 lr: 0.000077 grad: 0.0903 (0.0894) loss: 0.8230 (0.8210) time: 0.1147 data: 0.0377 max mem: 9390 +Train: [45] [4200/6250] eta: 0:04:48 lr: 0.000076 grad: 0.0931 (0.0895) loss: 0.8202 (0.8210) time: 0.1303 data: 0.0546 max mem: 9390 +Train: [45] [4300/6250] eta: 0:04:34 lr: 0.000076 grad: 0.0869 (0.0895) loss: 0.8269 (0.8210) time: 0.1285 data: 0.0459 max mem: 9390 +Train: [45] [4400/6250] eta: 0:04:21 lr: 0.000076 grad: 0.0873 (0.0895) loss: 0.8235 (0.8210) time: 0.2428 data: 0.1747 max mem: 9390 +Train: [45] [4500/6250] eta: 0:04:07 lr: 0.000076 grad: 0.0795 (0.0896) loss: 0.8281 (0.8209) time: 0.1312 data: 0.0529 max mem: 9390 +Train: [45] [4600/6250] eta: 0:03:54 lr: 0.000076 grad: 0.0864 (0.0895) loss: 0.8260 (0.8209) time: 0.1623 data: 0.0756 max mem: 9390 +Train: [45] [4700/6250] eta: 0:03:40 lr: 0.000076 grad: 0.0892 (0.0896) loss: 0.8189 (0.8209) time: 0.1383 data: 0.0630 max mem: 9390 +Train: [45] [4800/6250] eta: 0:03:26 lr: 0.000076 grad: 0.0876 (0.0896) loss: 0.8154 (0.8209) time: 0.1304 data: 0.0549 max mem: 9390 +Train: [45] [4900/6250] eta: 0:03:12 lr: 0.000076 grad: 0.0827 (0.0896) loss: 0.8251 (0.8209) time: 0.1468 data: 0.0689 max mem: 9390 +Train: [45] [5000/6250] eta: 0:02:57 lr: 0.000076 grad: 0.0836 (0.0896) loss: 0.8238 (0.8209) time: 0.1075 data: 0.0279 max mem: 9390 +Train: [45] [5100/6250] eta: 0:02:43 lr: 0.000076 grad: 0.0855 (0.0895) loss: 0.8202 (0.8209) time: 0.1256 data: 0.0374 max mem: 9390 +Train: [45] [5200/6250] eta: 0:02:28 lr: 0.000076 grad: 0.0876 (0.0895) loss: 0.8149 (0.8209) time: 0.1328 data: 0.0512 max mem: 9390 +Train: [45] [5300/6250] eta: 0:02:14 lr: 0.000076 grad: 0.0808 (0.0895) loss: 0.8257 (0.8209) time: 0.1286 data: 0.0508 max mem: 9390 +Train: [45] [5400/6250] eta: 0:02:00 lr: 0.000076 grad: 0.0810 (0.0894) loss: 0.8223 (0.8209) time: 0.1336 data: 0.0527 max mem: 9390 +Train: [45] [5500/6250] eta: 0:01:45 lr: 0.000076 grad: 0.0800 (0.0893) loss: 0.8228 (0.8209) time: 0.1254 data: 0.0449 max mem: 9390 +Train: [45] [5600/6250] eta: 0:01:31 lr: 0.000076 grad: 0.0792 (0.0893) loss: 0.8227 (0.8209) time: 0.1335 data: 0.0532 max mem: 9390 +Train: [45] [5700/6250] eta: 0:01:17 lr: 0.000076 grad: 0.0868 (0.0892) loss: 0.8183 (0.8210) time: 0.1315 data: 0.0469 max mem: 9390 +Train: [45] [5800/6250] eta: 0:01:03 lr: 0.000076 grad: 0.0824 (0.0892) loss: 0.8174 (0.8210) time: 0.0847 data: 0.0056 max mem: 9390 +Train: [45] [5900/6250] eta: 0:00:49 lr: 0.000076 grad: 0.0824 (0.0892) loss: 0.8177 (0.8209) time: 0.1379 data: 0.0599 max mem: 9390 +Train: [45] [6000/6250] eta: 0:00:35 lr: 0.000076 grad: 0.0813 (0.0891) loss: 0.8251 (0.8209) time: 0.1365 data: 0.0580 max mem: 9390 +Train: [45] [6100/6250] eta: 0:00:21 lr: 0.000076 grad: 0.0778 (0.0890) loss: 0.8256 (0.8209) time: 0.1329 data: 0.0594 max mem: 9390 +Train: [45] [6200/6250] eta: 0:00:06 lr: 0.000076 grad: 0.0821 (0.0889) loss: 0.8236 (0.8209) time: 0.1334 data: 0.0538 max mem: 9390 +Train: [45] [6249/6250] eta: 0:00:00 lr: 0.000076 grad: 0.0865 (0.0889) loss: 0.8221 (0.8209) time: 0.1446 data: 0.0626 max mem: 9390 +Train: [45] Total time: 0:14:41 (0.1410 s / it) +Averaged stats: lr: 0.000076 grad: 0.0865 (0.0889) loss: 0.8221 (0.8209) +Eval (hcp-train-subset): [45] [ 0/62] eta: 0:03:10 loss: 0.8520 (0.8520) time: 3.0672 data: 2.9931 max mem: 9390 +Eval (hcp-train-subset): [45] [61/62] eta: 0:00:00 loss: 0.8360 (0.8391) time: 0.1246 data: 0.0981 max mem: 9390 +Eval (hcp-train-subset): [45] Total time: 0:00:12 (0.1959 s / it) +Averaged stats (hcp-train-subset): loss: 0.8360 (0.8391) +Eval (hcp-val): [45] [ 0/62] eta: 0:04:50 loss: 0.8332 (0.8332) time: 4.6932 data: 4.6601 max mem: 9390 +Eval (hcp-val): [45] [61/62] eta: 0:00:00 loss: 0.8337 (0.8357) time: 0.1233 data: 0.0985 max mem: 9390 +Eval (hcp-val): [45] Total time: 0:00:12 (0.2019 s / it) +Averaged stats (hcp-val): loss: 0.8337 (0.8357) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +Train: [46] [ 0/6250] eta: 6:26:16 lr: 0.000076 grad: 0.0643 (0.0643) loss: 0.8828 (0.8828) time: 3.7083 data: 3.5751 max mem: 9390 +Train: [46] [ 100/6250] eta: 0:20:47 lr: 0.000076 grad: 0.0846 (0.0964) loss: 0.8287 (0.8388) time: 0.1429 data: 0.0606 max mem: 9390 +Train: [46] [ 200/6250] eta: 0:17:30 lr: 0.000076 grad: 0.0786 (0.0900) loss: 0.8270 (0.8334) time: 0.1281 data: 0.0427 max mem: 9390 +Train: [46] [ 300/6250] eta: 0:16:21 lr: 0.000076 grad: 0.0793 (0.0869) loss: 0.8324 (0.8325) time: 0.1573 data: 0.0760 max mem: 9390 +Train: [46] [ 400/6250] eta: 0:15:12 lr: 0.000076 grad: 0.0796 (0.0858) loss: 0.8298 (0.8319) time: 0.1198 data: 0.0362 max mem: 9390 +Train: [46] [ 500/6250] eta: 0:14:27 lr: 0.000076 grad: 0.0729 (0.0840) loss: 0.8315 (0.8314) time: 0.1304 data: 0.0536 max mem: 9390 +Train: [46] [ 600/6250] eta: 0:13:46 lr: 0.000076 grad: 0.0808 (0.0841) loss: 0.8208 (0.8304) time: 0.1109 data: 0.0274 max mem: 9390 +Train: [46] [ 700/6250] eta: 0:13:15 lr: 0.000076 grad: 0.0802 (0.0838) loss: 0.8242 (0.8294) time: 0.1192 data: 0.0271 max mem: 9390 +Train: [46] [ 800/6250] eta: 0:12:50 lr: 0.000076 grad: 0.0845 (0.0840) loss: 0.8261 (0.8286) time: 0.1372 data: 0.0548 max mem: 9390 +Train: [46] [ 900/6250] eta: 0:12:24 lr: 0.000076 grad: 0.0835 (0.0841) loss: 0.8253 (0.8279) time: 0.1309 data: 0.0492 max mem: 9390 +Train: [46] [1000/6250] eta: 0:12:00 lr: 0.000076 grad: 0.0805 (0.0840) loss: 0.8229 (0.8275) time: 0.1235 data: 0.0475 max mem: 9390 +Train: [46] [1100/6250] eta: 0:11:40 lr: 0.000075 grad: 0.0839 (0.0845) loss: 0.8188 (0.8270) time: 0.1125 data: 0.0238 max mem: 9390 +Train: [46] [1200/6250] eta: 0:11:20 lr: 0.000075 grad: 0.0820 (0.0847) loss: 0.8213 (0.8264) time: 0.1114 data: 0.0357 max mem: 9390 +Train: [46] [1300/6250] eta: 0:11:05 lr: 0.000075 grad: 0.0856 (0.0847) loss: 0.8238 (0.8261) time: 0.1215 data: 0.0477 max mem: 9390 +Train: [46] [1400/6250] eta: 0:10:48 lr: 0.000075 grad: 0.0855 (0.0850) loss: 0.8143 (0.8255) time: 0.1246 data: 0.0445 max mem: 9390 +Train: [46] [1500/6250] eta: 0:10:34 lr: 0.000075 grad: 0.0851 (0.0851) loss: 0.8187 (0.8251) time: 0.1197 data: 0.0461 max mem: 9390 +Train: [46] [1600/6250] eta: 0:10:18 lr: 0.000075 grad: 0.0820 (0.0852) loss: 0.8170 (0.8247) time: 0.1150 data: 0.0399 max mem: 9390 +Train: [46] [1700/6250] eta: 0:10:03 lr: 0.000075 grad: 0.0833 (0.0853) loss: 0.8183 (0.8244) time: 0.1387 data: 0.0618 max mem: 9390 +Train: [46] [1800/6250] eta: 0:09:47 lr: 0.000075 grad: 0.0830 (0.0854) loss: 0.8196 (0.8241) time: 0.1167 data: 0.0370 max mem: 9390 +Train: [46] [1900/6250] eta: 0:09:33 lr: 0.000075 grad: 0.0844 (0.0855) loss: 0.8221 (0.8239) time: 0.1224 data: 0.0425 max mem: 9390 +Train: [46] [2000/6250] eta: 0:09:20 lr: 0.000075 grad: 0.0857 (0.0856) loss: 0.8200 (0.8237) time: 0.1171 data: 0.0315 max mem: 9390 +Train: [46] [2100/6250] eta: 0:09:07 lr: 0.000075 grad: 0.0781 (0.0857) loss: 0.8171 (0.8235) time: 0.1391 data: 0.0641 max mem: 9390 +Train: [46] [2200/6250] eta: 0:08:58 lr: 0.000075 grad: 0.0845 (0.0857) loss: 0.8197 (0.8234) time: 0.1390 data: 0.0546 max mem: 9390 +Train: [46] [2300/6250] eta: 0:08:46 lr: 0.000075 grad: 0.0834 (0.0858) loss: 0.8180 (0.8232) time: 0.1369 data: 0.0588 max mem: 9390 +Train: [46] [2400/6250] eta: 0:08:32 lr: 0.000075 grad: 0.0867 (0.0859) loss: 0.8119 (0.8230) time: 0.1570 data: 0.0788 max mem: 9390 +Train: [46] [2500/6250] eta: 0:08:19 lr: 0.000075 grad: 0.0852 (0.0860) loss: 0.8217 (0.8228) time: 0.1161 data: 0.0335 max mem: 9390 +Train: [46] [2600/6250] eta: 0:08:06 lr: 0.000075 grad: 0.0893 (0.0861) loss: 0.8204 (0.8227) time: 0.1343 data: 0.0614 max mem: 9390 +Train: [46] [2700/6250] eta: 0:07:58 lr: 0.000075 grad: 0.0816 (0.0861) loss: 0.8252 (0.8226) time: 0.2938 data: 0.1477 max mem: 9390 +Train: [46] [2800/6250] eta: 0:07:44 lr: 0.000075 grad: 0.0792 (0.0861) loss: 0.8236 (0.8225) time: 0.1488 data: 0.0681 max mem: 9390 +Train: [46] [2900/6250] eta: 0:07:32 lr: 0.000075 grad: 0.0834 (0.0862) loss: 0.8219 (0.8225) time: 0.1532 data: 0.0735 max mem: 9390 +Train: [46] [3000/6250] eta: 0:07:19 lr: 0.000075 grad: 0.0813 (0.0863) loss: 0.8255 (0.8224) time: 0.1326 data: 0.0540 max mem: 9390 +Train: [46] [3100/6250] eta: 0:07:05 lr: 0.000075 grad: 0.0875 (0.0863) loss: 0.8191 (0.8223) time: 0.1381 data: 0.0630 max mem: 9390 +Train: [46] [3200/6250] eta: 0:06:52 lr: 0.000075 grad: 0.0857 (0.0863) loss: 0.8209 (0.8222) time: 0.1558 data: 0.0802 max mem: 9390 +Train: [46] [3300/6250] eta: 0:06:39 lr: 0.000075 grad: 0.0877 (0.0864) loss: 0.8147 (0.8221) time: 0.1364 data: 0.0584 max mem: 9390 +Train: [46] [3400/6250] eta: 0:06:26 lr: 0.000075 grad: 0.0892 (0.0866) loss: 0.8126 (0.8220) time: 0.1388 data: 0.0604 max mem: 9390 +Train: [46] [3500/6250] eta: 0:06:13 lr: 0.000075 grad: 0.0866 (0.0866) loss: 0.8173 (0.8219) time: 0.1565 data: 0.0790 max mem: 9390 +Train: [46] [3600/6250] eta: 0:05:59 lr: 0.000075 grad: 0.0878 (0.0866) loss: 0.8198 (0.8219) time: 0.1566 data: 0.0764 max mem: 9390 +Train: [46] [3700/6250] eta: 0:05:48 lr: 0.000075 grad: 0.0864 (0.0867) loss: 0.8104 (0.8218) time: 0.0878 data: 0.0002 max mem: 9390 +Train: [46] [3800/6250] eta: 0:05:34 lr: 0.000075 grad: 0.0863 (0.0867) loss: 0.8197 (0.8218) time: 0.1271 data: 0.0517 max mem: 9390 +Train: [46] [3900/6250] eta: 0:05:21 lr: 0.000075 grad: 0.0913 (0.0869) loss: 0.8147 (0.8218) time: 0.1263 data: 0.0439 max mem: 9390 +Train: [46] [4000/6250] eta: 0:05:06 lr: 0.000075 grad: 0.0899 (0.0870) loss: 0.8196 (0.8217) time: 0.1377 data: 0.0594 max mem: 9390 +Train: [46] [4100/6250] eta: 0:04:53 lr: 0.000075 grad: 0.0813 (0.0871) loss: 0.8228 (0.8217) time: 0.1160 data: 0.0375 max mem: 9390 +Train: [46] [4200/6250] eta: 0:04:40 lr: 0.000074 grad: 0.0845 (0.0871) loss: 0.8194 (0.8216) time: 0.1895 data: 0.1110 max mem: 9390 +Train: [46] [4300/6250] eta: 0:04:27 lr: 0.000074 grad: 0.0866 (0.0872) loss: 0.8189 (0.8215) time: 0.1524 data: 0.0775 max mem: 9390 +Train: [46] [4400/6250] eta: 0:04:13 lr: 0.000074 grad: 0.0873 (0.0872) loss: 0.8222 (0.8215) time: 0.1413 data: 0.0677 max mem: 9390 +Train: [46] [4500/6250] eta: 0:04:00 lr: 0.000074 grad: 0.0878 (0.0872) loss: 0.8189 (0.8214) time: 0.1514 data: 0.0672 max mem: 9390 +Train: [46] [4600/6250] eta: 0:03:47 lr: 0.000074 grad: 0.0854 (0.0873) loss: 0.8185 (0.8214) time: 0.1244 data: 0.0464 max mem: 9390 +Train: [46] [4700/6250] eta: 0:03:33 lr: 0.000074 grad: 0.0854 (0.0874) loss: 0.8155 (0.8212) time: 0.1604 data: 0.0780 max mem: 9390 +Train: [46] [4800/6250] eta: 0:03:20 lr: 0.000074 grad: 0.0924 (0.0875) loss: 0.8136 (0.8211) time: 0.1195 data: 0.0323 max mem: 9390 +Train: [46] [4900/6250] eta: 0:03:06 lr: 0.000074 grad: 0.0901 (0.0875) loss: 0.8209 (0.8211) time: 0.1268 data: 0.0432 max mem: 9390 +Train: [46] [5000/6250] eta: 0:02:52 lr: 0.000074 grad: 0.0934 (0.0876) loss: 0.8114 (0.8210) time: 0.1235 data: 0.0475 max mem: 9390 +Train: [46] [5100/6250] eta: 0:02:38 lr: 0.000074 grad: 0.0918 (0.0877) loss: 0.8114 (0.8209) time: 0.1288 data: 0.0518 max mem: 9390 +Train: [46] [5200/6250] eta: 0:02:24 lr: 0.000074 grad: 0.0874 (0.0878) loss: 0.8052 (0.8207) time: 0.1243 data: 0.0412 max mem: 9390 +Train: [46] [5300/6250] eta: 0:02:10 lr: 0.000074 grad: 0.0851 (0.0879) loss: 0.8198 (0.8206) time: 0.1143 data: 0.0299 max mem: 9390 +Train: [46] [5400/6250] eta: 0:01:56 lr: 0.000074 grad: 0.0824 (0.0880) loss: 0.8193 (0.8205) time: 0.1347 data: 0.0604 max mem: 9390 +Train: [46] [5500/6250] eta: 0:01:42 lr: 0.000074 grad: 0.0858 (0.0881) loss: 0.8119 (0.8204) time: 0.1028 data: 0.0151 max mem: 9390 +Train: [46] [5600/6250] eta: 0:01:29 lr: 0.000074 grad: 0.0923 (0.0881) loss: 0.8134 (0.8202) time: 0.1302 data: 0.0513 max mem: 9390 +Train: [46] [5700/6250] eta: 0:01:15 lr: 0.000074 grad: 0.0929 (0.0884) loss: 0.8166 (0.8202) time: 0.1240 data: 0.0493 max mem: 9390 +Train: [46] [5800/6250] eta: 0:01:01 lr: 0.000074 grad: 0.0895 (0.0885) loss: 0.8132 (0.8201) time: 0.1298 data: 0.0541 max mem: 9390 +Train: [46] [5900/6250] eta: 0:00:47 lr: 0.000074 grad: 0.0863 (0.0886) loss: 0.8222 (0.8200) time: 0.1476 data: 0.0673 max mem: 9390 +Train: [46] [6000/6250] eta: 0:00:34 lr: 0.000074 grad: 0.0958 (0.0887) loss: 0.8188 (0.8200) time: 0.1522 data: 0.0702 max mem: 9390 +Train: [46] [6100/6250] eta: 0:00:20 lr: 0.000074 grad: 0.0829 (0.0887) loss: 0.8250 (0.8200) time: 0.1311 data: 0.0580 max mem: 9390 +Train: [46] [6200/6250] eta: 0:00:06 lr: 0.000074 grad: 0.0863 (0.0887) loss: 0.8139 (0.8200) time: 0.1411 data: 0.0643 max mem: 9390 +Train: [46] [6249/6250] eta: 0:00:00 lr: 0.000074 grad: 0.0924 (0.0887) loss: 0.8117 (0.8199) time: 0.1277 data: 0.0566 max mem: 9390 +Train: [46] Total time: 0:14:19 (0.1375 s / it) +Averaged stats: lr: 0.000074 grad: 0.0924 (0.0887) loss: 0.8117 (0.8199) +Eval (hcp-train-subset): [46] [ 0/62] eta: 0:03:31 loss: 0.8510 (0.8510) time: 3.4177 data: 3.3338 max mem: 9390 +Eval (hcp-train-subset): [46] [61/62] eta: 0:00:00 loss: 0.8403 (0.8396) time: 0.1066 data: 0.0795 max mem: 9390 +Eval (hcp-train-subset): [46] Total time: 0:00:12 (0.1974 s / it) +Averaged stats (hcp-train-subset): loss: 0.8403 (0.8396) +Eval (hcp-val): [46] [ 0/62] eta: 0:04:29 loss: 0.8329 (0.8329) time: 4.3475 data: 4.3190 max mem: 9390 +Eval (hcp-val): [46] [61/62] eta: 0:00:00 loss: 0.8351 (0.8367) time: 0.1256 data: 0.1007 max mem: 9390 +Eval (hcp-val): [46] Total time: 0:00:12 (0.2004 s / it) +Averaged stats (hcp-val): loss: 0.8351 (0.8367) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +Train: [47] [ 0/6250] eta: 8:09:50 lr: 0.000074 grad: 0.0912 (0.0912) loss: 0.8556 (0.8556) time: 4.7025 data: 4.4668 max mem: 9390 +Train: [47] [ 100/6250] eta: 0:19:52 lr: 0.000074 grad: 0.0727 (0.0816) loss: 0.8343 (0.8437) time: 0.1529 data: 0.0649 max mem: 9390 +Train: [47] [ 200/6250] eta: 0:17:02 lr: 0.000074 grad: 0.0907 (0.0824) loss: 0.8319 (0.8388) time: 0.1350 data: 0.0474 max mem: 9390 +Train: [47] [ 300/6250] eta: 0:15:47 lr: 0.000074 grad: 0.0811 (0.0835) loss: 0.8269 (0.8356) time: 0.1401 data: 0.0584 max mem: 9390 +Train: [47] [ 400/6250] eta: 0:14:52 lr: 0.000074 grad: 0.0741 (0.0826) loss: 0.8310 (0.8344) time: 0.1280 data: 0.0471 max mem: 9390 +Train: [47] [ 500/6250] eta: 0:14:08 lr: 0.000074 grad: 0.0855 (0.0822) loss: 0.8227 (0.8335) time: 0.1308 data: 0.0379 max mem: 9390 +Train: [47] [ 600/6250] eta: 0:13:35 lr: 0.000074 grad: 0.0763 (0.0822) loss: 0.8319 (0.8325) time: 0.1309 data: 0.0497 max mem: 9390 +Train: [47] [ 700/6250] eta: 0:13:02 lr: 0.000074 grad: 0.0755 (0.0823) loss: 0.8268 (0.8318) time: 0.1367 data: 0.0552 max mem: 9390 +Train: [47] [ 800/6250] eta: 0:12:30 lr: 0.000074 grad: 0.0793 (0.0826) loss: 0.8292 (0.8313) time: 0.1061 data: 0.0263 max mem: 9390 +Train: [47] [ 900/6250] eta: 0:12:12 lr: 0.000074 grad: 0.0792 (0.0829) loss: 0.8240 (0.8305) time: 0.1296 data: 0.0548 max mem: 9390 +Train: [47] [1000/6250] eta: 0:12:05 lr: 0.000073 grad: 0.0832 (0.0831) loss: 0.8282 (0.8301) time: 0.1549 data: 0.0822 max mem: 9390 +Train: [47] [1100/6250] eta: 0:11:52 lr: 0.000073 grad: 0.0823 (0.0832) loss: 0.8183 (0.8298) time: 0.1503 data: 0.0725 max mem: 9390 +Train: [47] [1200/6250] eta: 0:11:34 lr: 0.000073 grad: 0.0851 (0.0835) loss: 0.8240 (0.8293) time: 0.1193 data: 0.0329 max mem: 9390 +Train: [47] [1300/6250] eta: 0:11:22 lr: 0.000073 grad: 0.0862 (0.0837) loss: 0.8241 (0.8288) time: 0.1459 data: 0.0714 max mem: 9390 +Train: [47] [1400/6250] eta: 0:11:07 lr: 0.000073 grad: 0.0879 (0.0843) loss: 0.8187 (0.8282) time: 0.1278 data: 0.0499 max mem: 9390 +Train: [47] [1500/6250] eta: 0:10:53 lr: 0.000073 grad: 0.0882 (0.0848) loss: 0.8248 (0.8277) time: 0.1451 data: 0.0684 max mem: 9390 +Train: [47] [1600/6250] eta: 0:10:40 lr: 0.000073 grad: 0.0900 (0.0850) loss: 0.8217 (0.8273) time: 0.1218 data: 0.0390 max mem: 9390 +Train: [47] [1700/6250] eta: 0:10:24 lr: 0.000073 grad: 0.0882 (0.0853) loss: 0.8240 (0.8269) time: 0.1312 data: 0.0483 max mem: 9390 +Train: [47] [1800/6250] eta: 0:10:09 lr: 0.000073 grad: 0.0840 (0.0856) loss: 0.8207 (0.8267) time: 0.1310 data: 0.0528 max mem: 9390 +Train: [47] [1900/6250] eta: 0:09:53 lr: 0.000073 grad: 0.0843 (0.0857) loss: 0.8221 (0.8263) time: 0.1094 data: 0.0333 max mem: 9390 +Train: [47] [2000/6250] eta: 0:09:37 lr: 0.000073 grad: 0.0929 (0.0859) loss: 0.8162 (0.8259) time: 0.1295 data: 0.0548 max mem: 9390 +Train: [47] [2100/6250] eta: 0:09:22 lr: 0.000073 grad: 0.0863 (0.0861) loss: 0.8186 (0.8256) time: 0.1390 data: 0.0579 max mem: 9390 +Train: [47] [2200/6250] eta: 0:09:08 lr: 0.000073 grad: 0.0870 (0.0862) loss: 0.8224 (0.8254) time: 0.1388 data: 0.0491 max mem: 9390 +Train: [47] [2300/6250] eta: 0:08:57 lr: 0.000073 grad: 0.0916 (0.0864) loss: 0.8256 (0.8253) time: 0.1657 data: 0.0859 max mem: 9390 +Train: [47] [2400/6250] eta: 0:08:42 lr: 0.000073 grad: 0.0863 (0.0866) loss: 0.8156 (0.8251) time: 0.1307 data: 0.0408 max mem: 9390 +Train: [47] [2500/6250] eta: 0:08:30 lr: 0.000073 grad: 0.0837 (0.0868) loss: 0.8201 (0.8249) time: 0.1523 data: 0.0678 max mem: 9390 +Train: [47] [2600/6250] eta: 0:08:17 lr: 0.000073 grad: 0.0836 (0.0869) loss: 0.8206 (0.8246) time: 0.1430 data: 0.0629 max mem: 9390 +Train: [47] [2700/6250] eta: 0:08:03 lr: 0.000073 grad: 0.0862 (0.0869) loss: 0.8227 (0.8245) time: 0.1431 data: 0.0612 max mem: 9390 +Train: [47] [2800/6250] eta: 0:07:50 lr: 0.000073 grad: 0.0843 (0.0871) loss: 0.8227 (0.8243) time: 0.1568 data: 0.0688 max mem: 9390 +Train: [47] [2900/6250] eta: 0:07:37 lr: 0.000073 grad: 0.0809 (0.0871) loss: 0.8197 (0.8243) time: 0.1226 data: 0.0401 max mem: 9390 +Train: [47] [3000/6250] eta: 0:07:22 lr: 0.000073 grad: 0.0912 (0.0872) loss: 0.8194 (0.8241) time: 0.1187 data: 0.0373 max mem: 9390 +Train: [47] [3100/6250] eta: 0:07:08 lr: 0.000073 grad: 0.0865 (0.0872) loss: 0.8226 (0.8240) time: 0.1276 data: 0.0517 max mem: 9390 +Train: [47] [3200/6250] eta: 0:06:55 lr: 0.000073 grad: 0.0843 (0.0872) loss: 0.8197 (0.8239) time: 0.1438 data: 0.0595 max mem: 9390 +Train: [47] [3300/6250] eta: 0:06:42 lr: 0.000073 grad: 0.0859 (0.0873) loss: 0.8107 (0.8238) time: 0.1426 data: 0.0614 max mem: 9390 +Train: [47] [3400/6250] eta: 0:06:29 lr: 0.000073 grad: 0.0879 (0.0874) loss: 0.8213 (0.8237) time: 0.1652 data: 0.0793 max mem: 9390 +Train: [47] [3500/6250] eta: 0:06:16 lr: 0.000073 grad: 0.1005 (0.0875) loss: 0.8232 (0.8236) time: 0.1505 data: 0.0676 max mem: 9390 +Train: [47] [3600/6250] eta: 0:06:03 lr: 0.000073 grad: 0.0937 (0.0877) loss: 0.8115 (0.8233) time: 0.1411 data: 0.0617 max mem: 9390 +Train: [47] [3700/6250] eta: 0:05:50 lr: 0.000073 grad: 0.0948 (0.0878) loss: 0.8184 (0.8232) time: 0.1560 data: 0.0736 max mem: 9390 +Train: [47] [3800/6250] eta: 0:05:37 lr: 0.000073 grad: 0.0882 (0.0879) loss: 0.8208 (0.8231) time: 0.1713 data: 0.0881 max mem: 9390 +Train: [47] [3900/6250] eta: 0:05:22 lr: 0.000073 grad: 0.0879 (0.0881) loss: 0.8134 (0.8230) time: 0.1249 data: 0.0478 max mem: 9390 +Train: [47] [4000/6250] eta: 0:05:08 lr: 0.000073 grad: 0.0841 (0.0881) loss: 0.8244 (0.8230) time: 0.1289 data: 0.0531 max mem: 9390 +Train: [47] [4100/6250] eta: 0:04:55 lr: 0.000072 grad: 0.0832 (0.0885) loss: 0.8262 (0.8230) time: 0.1521 data: 0.0665 max mem: 9390 +Train: [47] [4200/6250] eta: 0:04:41 lr: 0.000072 grad: 0.0818 (0.0885) loss: 0.8197 (0.8230) time: 0.1354 data: 0.0560 max mem: 9390 +Train: [47] [4300/6250] eta: 0:04:29 lr: 0.000072 grad: 0.0873 (0.0886) loss: 0.8199 (0.8229) time: 0.1417 data: 0.0647 max mem: 9390 +Train: [47] [4400/6250] eta: 0:04:15 lr: 0.000072 grad: 0.0918 (0.0887) loss: 0.8217 (0.8229) time: 0.1315 data: 0.0481 max mem: 9390 +Train: [47] [4500/6250] eta: 0:04:02 lr: 0.000072 grad: 0.0943 (0.0888) loss: 0.8208 (0.8229) time: 0.1622 data: 0.0848 max mem: 9390 +Train: [47] [4600/6250] eta: 0:03:49 lr: 0.000072 grad: 0.0846 (0.0888) loss: 0.8262 (0.8229) time: 0.1613 data: 0.0833 max mem: 9390 +Train: [47] [4700/6250] eta: 0:03:35 lr: 0.000072 grad: 0.0887 (0.0889) loss: 0.8246 (0.8228) time: 0.1542 data: 0.0809 max mem: 9390 +Train: [47] [4800/6250] eta: 0:03:21 lr: 0.000072 grad: 0.0980 (0.0890) loss: 0.8142 (0.8228) time: 0.1352 data: 0.0530 max mem: 9390 +Train: [47] [4900/6250] eta: 0:03:07 lr: 0.000072 grad: 0.0905 (0.0891) loss: 0.8186 (0.8228) time: 0.1304 data: 0.0521 max mem: 9390 +Train: [47] [5000/6250] eta: 0:02:53 lr: 0.000072 grad: 0.0878 (0.0892) loss: 0.8213 (0.8227) time: 0.1423 data: 0.0663 max mem: 9390 +Train: [47] [5100/6250] eta: 0:02:39 lr: 0.000072 grad: 0.0952 (0.0892) loss: 0.8185 (0.8227) time: 0.0994 data: 0.0173 max mem: 9390 +Train: [47] [5200/6250] eta: 0:02:25 lr: 0.000072 grad: 0.0924 (0.0893) loss: 0.8213 (0.8226) time: 0.1300 data: 0.0487 max mem: 9390 +Train: [47] [5300/6250] eta: 0:02:11 lr: 0.000072 grad: 0.0896 (0.0894) loss: 0.8203 (0.8225) time: 0.1100 data: 0.0214 max mem: 9390 +Train: [47] [5400/6250] eta: 0:01:57 lr: 0.000072 grad: 0.0881 (0.0894) loss: 0.8155 (0.8225) time: 0.1044 data: 0.0292 max mem: 9390 +Train: [47] [5500/6250] eta: 0:01:43 lr: 0.000072 grad: 0.0877 (0.0895) loss: 0.8183 (0.8224) time: 0.1246 data: 0.0483 max mem: 9390 +Train: [47] [5600/6250] eta: 0:01:29 lr: 0.000072 grad: 0.0885 (0.0896) loss: 0.8200 (0.8223) time: 0.1147 data: 0.0320 max mem: 9390 +Train: [47] [5700/6250] eta: 0:01:15 lr: 0.000072 grad: 0.0903 (0.0896) loss: 0.8120 (0.8222) time: 0.1174 data: 0.0423 max mem: 9390 +Train: [47] [5800/6250] eta: 0:01:01 lr: 0.000072 grad: 0.0885 (0.0896) loss: 0.8131 (0.8221) time: 0.1257 data: 0.0373 max mem: 9390 +Train: [47] [5900/6250] eta: 0:00:48 lr: 0.000072 grad: 0.0887 (0.0896) loss: 0.8141 (0.8221) time: 0.1510 data: 0.0643 max mem: 9390 +Train: [47] [6000/6250] eta: 0:00:34 lr: 0.000072 grad: 0.0839 (0.0896) loss: 0.8229 (0.8220) time: 0.1487 data: 0.0671 max mem: 9390 +Train: [47] [6100/6250] eta: 0:00:20 lr: 0.000072 grad: 0.0903 (0.0896) loss: 0.8211 (0.8220) time: 0.1404 data: 0.0598 max mem: 9390 +Train: [47] [6200/6250] eta: 0:00:06 lr: 0.000072 grad: 0.0940 (0.0896) loss: 0.8137 (0.8219) time: 0.1288 data: 0.0510 max mem: 9390 +Train: [47] [6249/6250] eta: 0:00:00 lr: 0.000072 grad: 0.0867 (0.0895) loss: 0.8221 (0.8219) time: 0.1120 data: 0.0296 max mem: 9390 +Train: [47] Total time: 0:14:25 (0.1384 s / it) +Averaged stats: lr: 0.000072 grad: 0.0867 (0.0895) loss: 0.8221 (0.8219) +Eval (hcp-train-subset): [47] [ 0/62] eta: 0:03:39 loss: 0.8475 (0.8475) time: 3.5408 data: 3.4723 max mem: 9390 +Eval (hcp-train-subset): [47] [61/62] eta: 0:00:00 loss: 0.8369 (0.8381) time: 0.1250 data: 0.1000 max mem: 9390 +Eval (hcp-train-subset): [47] Total time: 0:00:12 (0.2012 s / it) +Averaged stats (hcp-train-subset): loss: 0.8369 (0.8381) +Eval (hcp-val): [47] [ 0/62] eta: 0:05:09 loss: 0.8341 (0.8341) time: 4.9847 data: 4.9565 max mem: 9390 +Eval (hcp-val): [47] [61/62] eta: 0:00:00 loss: 0.8350 (0.8361) time: 0.1195 data: 0.0944 max mem: 9390 +Eval (hcp-val): [47] Total time: 0:00:12 (0.1968 s / it) +Averaged stats (hcp-val): loss: 0.8350 (0.8361) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +Train: [48] [ 0/6250] eta: 7:31:44 lr: 0.000072 grad: 0.1588 (0.1588) loss: 0.8131 (0.8131) time: 4.3366 data: 4.0156 max mem: 9390 +Train: [48] [ 100/6250] eta: 0:20:40 lr: 0.000072 grad: 0.0811 (0.0919) loss: 0.8313 (0.8347) time: 0.1608 data: 0.0762 max mem: 9390 +Train: [48] [ 200/6250] eta: 0:17:18 lr: 0.000072 grad: 0.0982 (0.0942) loss: 0.8202 (0.8265) time: 0.1367 data: 0.0554 max mem: 9390 +Train: [48] [ 300/6250] eta: 0:15:58 lr: 0.000072 grad: 0.0975 (0.0951) loss: 0.8090 (0.8212) time: 0.1497 data: 0.0690 max mem: 9390 +Train: [48] [ 400/6250] eta: 0:14:56 lr: 0.000072 grad: 0.0858 (0.0951) loss: 0.8175 (0.8195) time: 0.1349 data: 0.0437 max mem: 9390 +Train: [48] [ 500/6250] eta: 0:14:05 lr: 0.000072 grad: 0.0820 (0.0936) loss: 0.8210 (0.8196) time: 0.1220 data: 0.0461 max mem: 9390 +Train: [48] [ 600/6250] eta: 0:13:33 lr: 0.000072 grad: 0.0811 (0.0924) loss: 0.8253 (0.8199) time: 0.1385 data: 0.0520 max mem: 9390 +Train: [48] [ 700/6250] eta: 0:13:00 lr: 0.000072 grad: 0.0779 (0.0914) loss: 0.8173 (0.8200) time: 0.1149 data: 0.0354 max mem: 9390 +Train: [48] [ 800/6250] eta: 0:12:38 lr: 0.000072 grad: 0.0770 (0.0907) loss: 0.8233 (0.8203) time: 0.1430 data: 0.0609 max mem: 9390 +Train: [48] [ 900/6250] eta: 0:12:29 lr: 0.000071 grad: 0.0891 (0.0902) loss: 0.8227 (0.8204) time: 0.1284 data: 0.0513 max mem: 9390 +Train: [48] [1000/6250] eta: 0:12:20 lr: 0.000071 grad: 0.0797 (0.0899) loss: 0.8286 (0.8205) time: 0.1510 data: 0.0721 max mem: 9390 +Train: [48] [1100/6250] eta: 0:12:10 lr: 0.000071 grad: 0.0881 (0.0895) loss: 0.8192 (0.8203) time: 0.1639 data: 0.0850 max mem: 9390 +Train: [48] [1200/6250] eta: 0:12:00 lr: 0.000071 grad: 0.0872 (0.0894) loss: 0.8231 (0.8202) time: 0.1561 data: 0.0691 max mem: 9390 +Train: [48] [1300/6250] eta: 0:11:43 lr: 0.000071 grad: 0.0828 (0.0892) loss: 0.8138 (0.8202) time: 0.1164 data: 0.0404 max mem: 9390 +Train: [48] [1400/6250] eta: 0:11:29 lr: 0.000071 grad: 0.0815 (0.0890) loss: 0.8258 (0.8201) time: 0.1251 data: 0.0422 max mem: 9390 +Train: [48] [1500/6250] eta: 0:11:13 lr: 0.000071 grad: 0.0853 (0.0887) loss: 0.8142 (0.8201) time: 0.1608 data: 0.0841 max mem: 9390 +Train: [48] [1600/6250] eta: 0:10:58 lr: 0.000071 grad: 0.0830 (0.0886) loss: 0.8152 (0.8201) time: 0.1348 data: 0.0623 max mem: 9390 +Train: [48] [1700/6250] eta: 0:10:44 lr: 0.000071 grad: 0.0869 (0.0886) loss: 0.8184 (0.8201) time: 0.1435 data: 0.0659 max mem: 9390 +Train: [48] [1800/6250] eta: 0:10:28 lr: 0.000071 grad: 0.0841 (0.0886) loss: 0.8251 (0.8201) time: 0.1166 data: 0.0341 max mem: 9390 +Train: [48] [1900/6250] eta: 0:10:12 lr: 0.000071 grad: 0.0832 (0.0885) loss: 0.8213 (0.8202) time: 0.1289 data: 0.0497 max mem: 9390 +Train: [48] [2000/6250] eta: 0:09:55 lr: 0.000071 grad: 0.0930 (0.0884) loss: 0.8197 (0.8203) time: 0.1223 data: 0.0409 max mem: 9390 +Train: [48] [2100/6250] eta: 0:09:41 lr: 0.000071 grad: 0.0851 (0.0883) loss: 0.8202 (0.8204) time: 0.1345 data: 0.0540 max mem: 9390 +Train: [48] [2200/6250] eta: 0:09:26 lr: 0.000071 grad: 0.0848 (0.0883) loss: 0.8204 (0.8205) time: 0.1447 data: 0.0665 max mem: 9390 +Train: [48] [2300/6250] eta: 0:09:16 lr: 0.000071 grad: 0.0862 (0.0883) loss: 0.8243 (0.8205) time: 0.1950 data: 0.1163 max mem: 9390 +Train: [48] [2400/6250] eta: 0:09:02 lr: 0.000071 grad: 0.0851 (0.0882) loss: 0.8215 (0.8206) time: 0.1419 data: 0.0554 max mem: 9390 +Train: [48] [2500/6250] eta: 0:08:48 lr: 0.000071 grad: 0.0866 (0.0882) loss: 0.8193 (0.8206) time: 0.1459 data: 0.0704 max mem: 9390 +Train: [48] [2600/6250] eta: 0:08:35 lr: 0.000071 grad: 0.0915 (0.0883) loss: 0.8221 (0.8207) time: 0.1277 data: 0.0510 max mem: 9390 +Train: [48] [2700/6250] eta: 0:08:21 lr: 0.000071 grad: 0.0817 (0.0882) loss: 0.8215 (0.8207) time: 0.1433 data: 0.0621 max mem: 9390 +Train: [48] [2800/6250] eta: 0:08:07 lr: 0.000071 grad: 0.0828 (0.0882) loss: 0.8242 (0.8207) time: 0.1542 data: 0.0740 max mem: 9390 +Train: [48] [2900/6250] eta: 0:07:52 lr: 0.000071 grad: 0.0842 (0.0882) loss: 0.8183 (0.8207) time: 0.1307 data: 0.0514 max mem: 9390 +Train: [48] [3000/6250] eta: 0:07:37 lr: 0.000071 grad: 0.0875 (0.0882) loss: 0.8203 (0.8208) time: 0.1449 data: 0.0710 max mem: 9390 +Train: [48] [3100/6250] eta: 0:07:25 lr: 0.000071 grad: 0.0866 (0.0883) loss: 0.8221 (0.8207) time: 0.0887 data: 0.0002 max mem: 9390 +Train: [48] [3200/6250] eta: 0:07:10 lr: 0.000071 grad: 0.0854 (0.0883) loss: 0.8174 (0.8207) time: 0.1022 data: 0.0218 max mem: 9390 +Train: [48] [3300/6250] eta: 0:06:57 lr: 0.000071 grad: 0.0929 (0.0885) loss: 0.8181 (0.8207) time: 0.1613 data: 0.0816 max mem: 9390 +Train: [48] [3400/6250] eta: 0:06:42 lr: 0.000071 grad: 0.0843 (0.0885) loss: 0.8259 (0.8207) time: 0.1337 data: 0.0447 max mem: 9390 +Train: [48] [3500/6250] eta: 0:06:28 lr: 0.000071 grad: 0.0876 (0.0886) loss: 0.8226 (0.8207) time: 0.1404 data: 0.0596 max mem: 9390 +Train: [48] [3600/6250] eta: 0:06:14 lr: 0.000071 grad: 0.0916 (0.0887) loss: 0.8246 (0.8208) time: 0.1299 data: 0.0419 max mem: 9390 +Train: [48] [3700/6250] eta: 0:06:00 lr: 0.000071 grad: 0.0875 (0.0889) loss: 0.8187 (0.8209) time: 0.1402 data: 0.0593 max mem: 9390 +Train: [48] [3800/6250] eta: 0:05:46 lr: 0.000071 grad: 0.0886 (0.0890) loss: 0.8265 (0.8209) time: 0.1441 data: 0.0655 max mem: 9390 +Train: [48] [3900/6250] eta: 0:05:32 lr: 0.000070 grad: 0.0900 (0.0891) loss: 0.8196 (0.8210) time: 0.1551 data: 0.0767 max mem: 9390 +Train: [48] [4000/6250] eta: 0:05:17 lr: 0.000070 grad: 0.0857 (0.0891) loss: 0.8191 (0.8210) time: 0.1438 data: 0.0637 max mem: 9390 +Train: [48] [4100/6250] eta: 0:05:03 lr: 0.000070 grad: 0.0876 (0.0891) loss: 0.8183 (0.8210) time: 0.1400 data: 0.0532 max mem: 9390 +Train: [48] [4200/6250] eta: 0:04:49 lr: 0.000070 grad: 0.0874 (0.0891) loss: 0.8221 (0.8210) time: 0.1761 data: 0.1063 max mem: 9390 +Train: [48] [4300/6250] eta: 0:04:35 lr: 0.000070 grad: 0.0874 (0.0891) loss: 0.8200 (0.8210) time: 0.1499 data: 0.0755 max mem: 9390 +Train: [48] [4400/6250] eta: 0:04:21 lr: 0.000070 grad: 0.0901 (0.0892) loss: 0.8233 (0.8210) time: 0.1209 data: 0.0451 max mem: 9390 +Train: [48] [4500/6250] eta: 0:04:07 lr: 0.000070 grad: 0.0858 (0.0892) loss: 0.8283 (0.8211) time: 0.1582 data: 0.0753 max mem: 9390 +Train: [48] [4600/6250] eta: 0:03:54 lr: 0.000070 grad: 0.0874 (0.0893) loss: 0.8230 (0.8211) time: 0.1404 data: 0.0592 max mem: 9390 +Train: [48] [4700/6250] eta: 0:03:39 lr: 0.000070 grad: 0.0868 (0.0893) loss: 0.8179 (0.8211) time: 0.1210 data: 0.0434 max mem: 9390 +Train: [48] [4800/6250] eta: 0:03:25 lr: 0.000070 grad: 0.0899 (0.0893) loss: 0.8181 (0.8211) time: 0.1460 data: 0.0712 max mem: 9390 +Train: [48] [4900/6250] eta: 0:03:11 lr: 0.000070 grad: 0.0944 (0.0893) loss: 0.8197 (0.8210) time: 0.1226 data: 0.0454 max mem: 9390 +Train: [48] [5000/6250] eta: 0:02:56 lr: 0.000070 grad: 0.0863 (0.0894) loss: 0.8214 (0.8210) time: 0.1194 data: 0.0376 max mem: 9390 +Train: [48] [5100/6250] eta: 0:02:42 lr: 0.000070 grad: 0.0925 (0.0894) loss: 0.8206 (0.8209) time: 0.1318 data: 0.0489 max mem: 9390 +Train: [48] [5200/6250] eta: 0:02:27 lr: 0.000070 grad: 0.0868 (0.0895) loss: 0.8208 (0.8209) time: 0.1278 data: 0.0462 max mem: 9390 +Train: [48] [5300/6250] eta: 0:02:13 lr: 0.000070 grad: 0.0847 (0.0895) loss: 0.8185 (0.8209) time: 0.1303 data: 0.0512 max mem: 9390 +Train: [48] [5400/6250] eta: 0:01:59 lr: 0.000070 grad: 0.0865 (0.0895) loss: 0.8214 (0.8208) time: 0.1163 data: 0.0369 max mem: 9390 +Train: [48] [5500/6250] eta: 0:01:44 lr: 0.000070 grad: 0.0905 (0.0895) loss: 0.8223 (0.8208) time: 0.1352 data: 0.0569 max mem: 9390 +Train: [48] [5600/6250] eta: 0:01:30 lr: 0.000070 grad: 0.0941 (0.0896) loss: 0.8235 (0.8208) time: 0.1291 data: 0.0562 max mem: 9390 +Train: [48] [5700/6250] eta: 0:01:16 lr: 0.000070 grad: 0.0906 (0.0896) loss: 0.8170 (0.8208) time: 0.1350 data: 0.0550 max mem: 9390 +Train: [48] [5800/6250] eta: 0:01:02 lr: 0.000070 grad: 0.0875 (0.0896) loss: 0.8207 (0.8207) time: 0.1437 data: 0.0654 max mem: 9390 +Train: [48] [5900/6250] eta: 0:00:48 lr: 0.000070 grad: 0.0927 (0.0897) loss: 0.8172 (0.8207) time: 0.1377 data: 0.0605 max mem: 9390 +Train: [48] [6000/6250] eta: 0:00:34 lr: 0.000070 grad: 0.0925 (0.0897) loss: 0.8190 (0.8206) time: 0.1149 data: 0.0375 max mem: 9390 +Train: [48] [6100/6250] eta: 0:00:20 lr: 0.000070 grad: 0.0836 (0.0897) loss: 0.8176 (0.8206) time: 0.1440 data: 0.0649 max mem: 9390 +Train: [48] [6200/6250] eta: 0:00:06 lr: 0.000070 grad: 0.0900 (0.0897) loss: 0.8168 (0.8206) time: 0.1495 data: 0.0662 max mem: 9390 +Train: [48] [6249/6250] eta: 0:00:00 lr: 0.000070 grad: 0.0959 (0.0897) loss: 0.8223 (0.8206) time: 0.1405 data: 0.0584 max mem: 9390 +Train: [48] Total time: 0:14:33 (0.1398 s / it) +Averaged stats: lr: 0.000070 grad: 0.0959 (0.0897) loss: 0.8223 (0.8206) +Eval (hcp-train-subset): [48] [ 0/62] eta: 0:03:28 loss: 0.8443 (0.8443) time: 3.3590 data: 3.2968 max mem: 9390 +Eval (hcp-train-subset): [48] [61/62] eta: 0:00:00 loss: 0.8363 (0.8377) time: 0.0941 data: 0.0691 max mem: 9390 +Eval (hcp-train-subset): [48] Total time: 0:00:12 (0.1961 s / it) +Averaged stats (hcp-train-subset): loss: 0.8363 (0.8377) +Eval (hcp-val): [48] [ 0/62] eta: 0:03:09 loss: 0.8316 (0.8316) time: 3.0599 data: 3.0017 max mem: 9390 +Eval (hcp-val): [48] [61/62] eta: 0:00:00 loss: 0.8349 (0.8358) time: 0.1236 data: 0.0971 max mem: 9390 +Eval (hcp-val): [48] Total time: 0:00:11 (0.1882 s / it) +Averaged stats (hcp-val): loss: 0.8349 (0.8358) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +Train: [49] [ 0/6250] eta: 9:12:59 lr: 0.000070 grad: 0.0810 (0.0810) loss: 0.8541 (0.8541) time: 5.3087 data: 5.1801 max mem: 9390 +Train: [49] [ 100/6250] eta: 0:19:13 lr: 0.000070 grad: 0.0717 (0.0972) loss: 0.8427 (0.8355) time: 0.1469 data: 0.0604 max mem: 9390 +Train: [49] [ 200/6250] eta: 0:16:52 lr: 0.000070 grad: 0.0810 (0.0904) loss: 0.8215 (0.8318) time: 0.1490 data: 0.0526 max mem: 9390 +Train: [49] [ 300/6250] eta: 0:15:43 lr: 0.000070 grad: 0.0820 (0.0900) loss: 0.8239 (0.8290) time: 0.1427 data: 0.0580 max mem: 9390 +Train: [49] [ 400/6250] eta: 0:14:55 lr: 0.000070 grad: 0.0812 (0.0890) loss: 0.8189 (0.8272) time: 0.1226 data: 0.0369 max mem: 9390 +Train: [49] [ 500/6250] eta: 0:14:24 lr: 0.000070 grad: 0.0797 (0.0882) loss: 0.8232 (0.8263) time: 0.1446 data: 0.0612 max mem: 9390 +Train: [49] [ 600/6250] eta: 0:13:48 lr: 0.000070 grad: 0.0848 (0.0880) loss: 0.8230 (0.8251) time: 0.1404 data: 0.0616 max mem: 9390 +Train: [49] [ 700/6250] eta: 0:13:12 lr: 0.000069 grad: 0.0821 (0.0881) loss: 0.8246 (0.8239) time: 0.1250 data: 0.0355 max mem: 9390 +Train: [49] [ 800/6250] eta: 0:12:41 lr: 0.000069 grad: 0.0806 (0.0876) loss: 0.8193 (0.8234) time: 0.1208 data: 0.0361 max mem: 9390 +Train: [49] [ 900/6250] eta: 0:12:24 lr: 0.000069 grad: 0.0885 (0.0880) loss: 0.8179 (0.8227) time: 0.1414 data: 0.0641 max mem: 9390 +Train: [49] [1000/6250] eta: 0:12:19 lr: 0.000069 grad: 0.0816 (0.0879) loss: 0.8222 (0.8225) time: 0.1323 data: 0.0563 max mem: 9390 +Train: [49] [1100/6250] eta: 0:12:10 lr: 0.000069 grad: 0.0884 (0.0880) loss: 0.8185 (0.8221) time: 0.1518 data: 0.0735 max mem: 9390 +Train: [49] [1200/6250] eta: 0:11:57 lr: 0.000069 grad: 0.0842 (0.0882) loss: 0.8188 (0.8217) time: 0.1375 data: 0.0591 max mem: 9390 +Train: [49] [1300/6250] eta: 0:11:39 lr: 0.000069 grad: 0.0885 (0.0883) loss: 0.8173 (0.8213) time: 0.1437 data: 0.0611 max mem: 9390 +Train: [49] [1400/6250] eta: 0:11:21 lr: 0.000069 grad: 0.0915 (0.0884) loss: 0.8125 (0.8209) time: 0.1277 data: 0.0465 max mem: 9390 +Train: [49] [1500/6250] eta: 0:11:03 lr: 0.000069 grad: 0.0869 (0.0888) loss: 0.8029 (0.8203) time: 0.1570 data: 0.0785 max mem: 9390 +Train: [49] [1600/6250] eta: 0:10:49 lr: 0.000069 grad: 0.0839 (0.0889) loss: 0.8211 (0.8198) time: 0.1207 data: 0.0445 max mem: 9390 +Train: [49] [1700/6250] eta: 0:10:32 lr: 0.000069 grad: 0.0895 (0.0891) loss: 0.8118 (0.8193) time: 0.1328 data: 0.0533 max mem: 9390 +Train: [49] [1800/6250] eta: 0:10:18 lr: 0.000069 grad: 0.0890 (0.0892) loss: 0.8179 (0.8190) time: 0.1436 data: 0.0660 max mem: 9390 +Train: [49] [1900/6250] eta: 0:10:01 lr: 0.000069 grad: 0.0892 (0.0893) loss: 0.8155 (0.8187) time: 0.1205 data: 0.0370 max mem: 9390 +Train: [49] [2000/6250] eta: 0:09:45 lr: 0.000069 grad: 0.0954 (0.0896) loss: 0.8080 (0.8184) time: 0.1131 data: 0.0293 max mem: 9390 +Train: [49] [2100/6250] eta: 0:09:30 lr: 0.000069 grad: 0.0836 (0.0898) loss: 0.8155 (0.8182) time: 0.1204 data: 0.0366 max mem: 9390 +Train: [49] [2200/6250] eta: 0:09:15 lr: 0.000069 grad: 0.0882 (0.0898) loss: 0.8136 (0.8179) time: 0.1093 data: 0.0243 max mem: 9390 +Train: [49] [2300/6250] eta: 0:09:01 lr: 0.000069 grad: 0.0918 (0.0899) loss: 0.8152 (0.8177) time: 0.1471 data: 0.0758 max mem: 9390 +Train: [49] [2400/6250] eta: 0:08:46 lr: 0.000069 grad: 0.0877 (0.0899) loss: 0.8138 (0.8176) time: 0.1267 data: 0.0323 max mem: 9390 +Train: [49] [2500/6250] eta: 0:08:31 lr: 0.000069 grad: 0.0875 (0.0899) loss: 0.8212 (0.8175) time: 0.1187 data: 0.0281 max mem: 9390 +Train: [49] [2600/6250] eta: 0:08:18 lr: 0.000069 grad: 0.0887 (0.0900) loss: 0.8172 (0.8174) time: 0.1471 data: 0.0672 max mem: 9390 +Train: [49] [2700/6250] eta: 0:08:06 lr: 0.000069 grad: 0.0900 (0.0900) loss: 0.8110 (0.8173) time: 0.1658 data: 0.0911 max mem: 9390 +Train: [49] [2800/6250] eta: 0:07:53 lr: 0.000069 grad: 0.0924 (0.0901) loss: 0.8143 (0.8172) time: 0.1491 data: 0.0671 max mem: 9390 +Train: [49] [2900/6250] eta: 0:07:40 lr: 0.000069 grad: 0.0913 (0.0902) loss: 0.8226 (0.8171) time: 0.1629 data: 0.0818 max mem: 9390 +Train: [49] [3000/6250] eta: 0:07:26 lr: 0.000069 grad: 0.0867 (0.0902) loss: 0.8148 (0.8170) time: 0.1323 data: 0.0558 max mem: 9390 +Train: [49] [3100/6250] eta: 0:07:13 lr: 0.000069 grad: 0.0880 (0.0901) loss: 0.8128 (0.8171) time: 0.1850 data: 0.0926 max mem: 9390 +Train: [49] [3200/6250] eta: 0:07:00 lr: 0.000069 grad: 0.0898 (0.0901) loss: 0.8161 (0.8170) time: 0.1459 data: 0.0686 max mem: 9390 +Train: [49] [3300/6250] eta: 0:06:46 lr: 0.000069 grad: 0.0903 (0.0901) loss: 0.8259 (0.8171) time: 0.1471 data: 0.0671 max mem: 9390 +Train: [49] [3400/6250] eta: 0:06:32 lr: 0.000069 grad: 0.0849 (0.0902) loss: 0.8235 (0.8171) time: 0.1220 data: 0.0433 max mem: 9390 +Train: [49] [3500/6250] eta: 0:06:19 lr: 0.000069 grad: 0.0859 (0.0901) loss: 0.8150 (0.8171) time: 0.1137 data: 0.0180 max mem: 9390 +Train: [49] [3600/6250] eta: 0:06:06 lr: 0.000069 grad: 0.0890 (0.0901) loss: 0.8067 (0.8171) time: 0.1384 data: 0.0637 max mem: 9390 +Train: [49] [3700/6250] eta: 0:05:51 lr: 0.000069 grad: 0.0886 (0.0901) loss: 0.8194 (0.8172) time: 0.1348 data: 0.0493 max mem: 9390 +Train: [49] [3800/6250] eta: 0:05:38 lr: 0.000068 grad: 0.0931 (0.0902) loss: 0.8153 (0.8173) time: 0.1393 data: 0.0474 max mem: 9390 +Train: [49] [3900/6250] eta: 0:05:24 lr: 0.000068 grad: 0.0884 (0.0902) loss: 0.8190 (0.8173) time: 0.1442 data: 0.0636 max mem: 9390 +Train: [49] [4000/6250] eta: 0:05:11 lr: 0.000068 grad: 0.0909 (0.0903) loss: 0.8166 (0.8173) time: 0.1248 data: 0.0474 max mem: 9390 +Train: [49] [4100/6250] eta: 0:04:57 lr: 0.000068 grad: 0.0945 (0.0904) loss: 0.8186 (0.8173) time: 0.1416 data: 0.0632 max mem: 9390 +Train: [49] [4200/6250] eta: 0:04:44 lr: 0.000068 grad: 0.0926 (0.0905) loss: 0.8140 (0.8174) time: 0.1354 data: 0.0570 max mem: 9390 +Train: [49] [4300/6250] eta: 0:04:31 lr: 0.000068 grad: 0.0915 (0.0905) loss: 0.8137 (0.8174) time: 0.1634 data: 0.0779 max mem: 9390 +Train: [49] [4400/6250] eta: 0:04:17 lr: 0.000068 grad: 0.0925 (0.0906) loss: 0.8084 (0.8173) time: 0.1508 data: 0.0757 max mem: 9390 +Train: [49] [4500/6250] eta: 0:04:03 lr: 0.000068 grad: 0.0960 (0.0907) loss: 0.8155 (0.8173) time: 0.1405 data: 0.0551 max mem: 9390 +Train: [49] [4600/6250] eta: 0:03:50 lr: 0.000068 grad: 0.0937 (0.0908) loss: 0.8184 (0.8173) time: 0.1639 data: 0.0818 max mem: 9390 +Train: [49] [4700/6250] eta: 0:03:36 lr: 0.000068 grad: 0.0891 (0.0908) loss: 0.8116 (0.8173) time: 0.1611 data: 0.0860 max mem: 9390 +Train: [49] [4800/6250] eta: 0:03:22 lr: 0.000068 grad: 0.0931 (0.0908) loss: 0.8153 (0.8173) time: 0.1440 data: 0.0676 max mem: 9390 +Train: [49] [4900/6250] eta: 0:03:07 lr: 0.000068 grad: 0.0891 (0.0909) loss: 0.8219 (0.8173) time: 0.1329 data: 0.0459 max mem: 9390 +Train: [49] [5000/6250] eta: 0:02:53 lr: 0.000068 grad: 0.0902 (0.0910) loss: 0.8208 (0.8173) time: 0.0955 data: 0.0038 max mem: 9390 +Train: [49] [5100/6250] eta: 0:02:39 lr: 0.000068 grad: 0.0848 (0.0910) loss: 0.8140 (0.8173) time: 0.1125 data: 0.0337 max mem: 9390 +Train: [49] [5200/6250] eta: 0:02:25 lr: 0.000068 grad: 0.0872 (0.0910) loss: 0.8168 (0.8172) time: 0.1434 data: 0.0623 max mem: 9390 +Train: [49] [5300/6250] eta: 0:02:10 lr: 0.000068 grad: 0.0900 (0.0910) loss: 0.8146 (0.8172) time: 0.1124 data: 0.0306 max mem: 9390 +Train: [49] [5400/6250] eta: 0:01:56 lr: 0.000068 grad: 0.0986 (0.0911) loss: 0.8258 (0.8172) time: 0.1398 data: 0.0634 max mem: 9390 +Train: [49] [5500/6250] eta: 0:01:43 lr: 0.000068 grad: 0.0978 (0.0912) loss: 0.8138 (0.8172) time: 0.1419 data: 0.0664 max mem: 9390 +Train: [49] [5600/6250] eta: 0:01:29 lr: 0.000068 grad: 0.0941 (0.0913) loss: 0.8155 (0.8172) time: 0.1346 data: 0.0521 max mem: 9390 +Train: [49] [5700/6250] eta: 0:01:15 lr: 0.000068 grad: 0.0943 (0.0914) loss: 0.8122 (0.8171) time: 0.1016 data: 0.0080 max mem: 9390 +Train: [49] [5800/6250] eta: 0:01:01 lr: 0.000068 grad: 0.0941 (0.0915) loss: 0.8155 (0.8171) time: 0.1487 data: 0.0657 max mem: 9390 +Train: [49] [5900/6250] eta: 0:00:47 lr: 0.000068 grad: 0.0967 (0.0916) loss: 0.8191 (0.8171) time: 0.1260 data: 0.0407 max mem: 9390 +Train: [49] [6000/6250] eta: 0:00:34 lr: 0.000068 grad: 0.0928 (0.0917) loss: 0.8127 (0.8171) time: 0.1192 data: 0.0242 max mem: 9390 +Train: [49] [6100/6250] eta: 0:00:20 lr: 0.000068 grad: 0.0885 (0.0918) loss: 0.8184 (0.8170) time: 0.1270 data: 0.0493 max mem: 9390 +Train: [49] [6200/6250] eta: 0:00:06 lr: 0.000068 grad: 0.0925 (0.0918) loss: 0.8212 (0.8170) time: 0.1426 data: 0.0599 max mem: 9390 +Train: [49] [6249/6250] eta: 0:00:00 lr: 0.000068 grad: 0.0903 (0.0918) loss: 0.8195 (0.8170) time: 0.1272 data: 0.0518 max mem: 9390 +Train: [49] Total time: 0:14:20 (0.1376 s / it) +Averaged stats: lr: 0.000068 grad: 0.0903 (0.0918) loss: 0.8195 (0.8170) +Eval (hcp-train-subset): [49] [ 0/62] eta: 0:03:10 loss: 0.8493 (0.8493) time: 3.0771 data: 2.9706 max mem: 9390 +Eval (hcp-train-subset): [49] [61/62] eta: 0:00:00 loss: 0.8355 (0.8357) time: 0.1204 data: 0.0954 max mem: 9390 +Eval (hcp-train-subset): [49] Total time: 0:00:12 (0.1996 s / it) +Averaged stats (hcp-train-subset): loss: 0.8355 (0.8357) +Making plots (hcp-train-subset): example=13 +Eval (hcp-val): [49] [ 0/62] eta: 0:04:18 loss: 0.8308 (0.8308) time: 4.1757 data: 4.1453 max mem: 9390 +Eval (hcp-val): [49] [61/62] eta: 0:00:00 loss: 0.8329 (0.8355) time: 0.1316 data: 0.1065 max mem: 9390 +Eval (hcp-val): [49] Total time: 0:00:13 (0.2106 s / it) +Averaged stats (hcp-val): loss: 0.8329 (0.8355) +Making plots (hcp-val): example=22 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +Train: [50] [ 0/6250] eta: 8:56:41 lr: 0.000068 grad: 0.1254 (0.1254) loss: 0.8819 (0.8819) time: 5.1523 data: 5.0541 max mem: 9390 +Train: [50] [ 100/6250] eta: 0:19:54 lr: 0.000068 grad: 0.0845 (0.1125) loss: 0.8308 (0.8370) time: 0.1402 data: 0.0500 max mem: 9390 +Train: [50] [ 200/6250] eta: 0:17:11 lr: 0.000068 grad: 0.0839 (0.1009) loss: 0.8265 (0.8339) time: 0.1642 data: 0.0802 max mem: 9390 +Train: [50] [ 300/6250] eta: 0:15:57 lr: 0.000068 grad: 0.0876 (0.0974) loss: 0.8239 (0.8302) time: 0.1381 data: 0.0568 max mem: 9390 +Train: [50] [ 400/6250] eta: 0:15:07 lr: 0.000068 grad: 0.0837 (0.0952) loss: 0.8176 (0.8276) time: 0.1388 data: 0.0534 max mem: 9390 +Train: [50] [ 500/6250] eta: 0:14:24 lr: 0.000067 grad: 0.0825 (0.0933) loss: 0.8266 (0.8265) time: 0.1480 data: 0.0647 max mem: 9390 +Train: [50] [ 600/6250] eta: 0:13:41 lr: 0.000067 grad: 0.0865 (0.0929) loss: 0.8117 (0.8249) time: 0.1160 data: 0.0277 max mem: 9390 +Train: [50] [ 700/6250] eta: 0:13:05 lr: 0.000067 grad: 0.0875 (0.0924) loss: 0.8209 (0.8236) time: 0.1263 data: 0.0428 max mem: 9390 +Train: [50] [ 800/6250] eta: 0:12:39 lr: 0.000067 grad: 0.0875 (0.0921) loss: 0.8147 (0.8225) time: 0.1395 data: 0.0603 max mem: 9390 +Train: [50] [ 900/6250] eta: 0:12:12 lr: 0.000067 grad: 0.0822 (0.0919) loss: 0.8176 (0.8218) time: 0.1090 data: 0.0203 max mem: 9390 +Train: [50] [1000/6250] eta: 0:11:54 lr: 0.000067 grad: 0.0913 (0.0915) loss: 0.8208 (0.8215) time: 0.1247 data: 0.0482 max mem: 9390 +Train: [50] [1100/6250] eta: 0:11:40 lr: 0.000067 grad: 0.0863 (0.0913) loss: 0.8162 (0.8210) time: 0.1400 data: 0.0586 max mem: 9390 +Train: [50] [1200/6250] eta: 0:11:22 lr: 0.000067 grad: 0.0865 (0.0913) loss: 0.8170 (0.8207) time: 0.1277 data: 0.0508 max mem: 9390 +Train: [50] [1300/6250] eta: 0:11:08 lr: 0.000067 grad: 0.0811 (0.0911) loss: 0.8235 (0.8205) time: 0.1251 data: 0.0462 max mem: 9390 +Train: [50] [1400/6250] eta: 0:10:53 lr: 0.000067 grad: 0.0890 (0.0909) loss: 0.8204 (0.8202) time: 0.1286 data: 0.0429 max mem: 9390 +Train: [50] [1500/6250] eta: 0:10:39 lr: 0.000067 grad: 0.0892 (0.0910) loss: 0.8139 (0.8199) time: 0.1251 data: 0.0497 max mem: 9390 +Train: [50] [1600/6250] eta: 0:10:25 lr: 0.000067 grad: 0.0854 (0.0911) loss: 0.8152 (0.8196) time: 0.1365 data: 0.0541 max mem: 9390 +Train: [50] [1700/6250] eta: 0:10:07 lr: 0.000067 grad: 0.0829 (0.0910) loss: 0.8199 (0.8194) time: 0.1194 data: 0.0418 max mem: 9390 +Train: [50] [1800/6250] eta: 0:09:55 lr: 0.000067 grad: 0.0869 (0.0908) loss: 0.8163 (0.8193) time: 0.1449 data: 0.0657 max mem: 9390 +Train: [50] [1900/6250] eta: 0:09:42 lr: 0.000067 grad: 0.0948 (0.0910) loss: 0.8067 (0.8191) time: 0.1479 data: 0.0710 max mem: 9390 +Train: [50] [2000/6250] eta: 0:09:31 lr: 0.000067 grad: 0.0879 (0.0911) loss: 0.8145 (0.8190) time: 0.1400 data: 0.0601 max mem: 9390 +Train: [50] [2100/6250] eta: 0:09:17 lr: 0.000067 grad: 0.0888 (0.0909) loss: 0.8146 (0.8189) time: 0.1243 data: 0.0495 max mem: 9390 +Train: [50] [2200/6250] eta: 0:09:04 lr: 0.000067 grad: 0.0930 (0.0910) loss: 0.8158 (0.8188) time: 0.1401 data: 0.0657 max mem: 9390 +Train: [50] [2300/6250] eta: 0:08:49 lr: 0.000067 grad: 0.0829 (0.0911) loss: 0.8177 (0.8187) time: 0.1451 data: 0.0659 max mem: 9390 +Train: [50] [2400/6250] eta: 0:08:35 lr: 0.000067 grad: 0.0890 (0.0912) loss: 0.8118 (0.8185) time: 0.1262 data: 0.0496 max mem: 9390 +Train: [50] [2500/6250] eta: 0:08:21 lr: 0.000067 grad: 0.0990 (0.0913) loss: 0.8048 (0.8183) time: 0.1302 data: 0.0516 max mem: 9390 +Train: [50] [2600/6250] eta: 0:08:06 lr: 0.000067 grad: 0.0929 (0.0914) loss: 0.8123 (0.8182) time: 0.1220 data: 0.0427 max mem: 9390 +Train: [50] [2700/6250] eta: 0:07:52 lr: 0.000067 grad: 0.0892 (0.0915) loss: 0.8167 (0.8181) time: 0.1384 data: 0.0612 max mem: 9390 +Train: [50] [2800/6250] eta: 0:07:39 lr: 0.000067 grad: 0.0923 (0.0916) loss: 0.8160 (0.8179) time: 0.1291 data: 0.0504 max mem: 9390 +Train: [50] [2900/6250] eta: 0:07:27 lr: 0.000067 grad: 0.0911 (0.0917) loss: 0.8105 (0.8178) time: 0.1401 data: 0.0548 max mem: 9390 +Train: [50] [3000/6250] eta: 0:07:15 lr: 0.000067 grad: 0.0887 (0.0918) loss: 0.8238 (0.8178) time: 0.1256 data: 0.0484 max mem: 9390 +Train: [50] [3100/6250] eta: 0:07:03 lr: 0.000067 grad: 0.0871 (0.0918) loss: 0.8177 (0.8178) time: 0.1419 data: 0.0647 max mem: 9390 +Train: [50] [3200/6250] eta: 0:06:50 lr: 0.000067 grad: 0.0918 (0.0919) loss: 0.8222 (0.8178) time: 0.1450 data: 0.0686 max mem: 9390 +Train: [50] [3300/6250] eta: 0:06:38 lr: 0.000067 grad: 0.0913 (0.0919) loss: 0.8167 (0.8178) time: 0.1468 data: 0.0709 max mem: 9390 +Train: [50] [3400/6250] eta: 0:06:25 lr: 0.000067 grad: 0.0820 (0.0919) loss: 0.8182 (0.8178) time: 0.1467 data: 0.0617 max mem: 9390 +Train: [50] [3500/6250] eta: 0:06:12 lr: 0.000067 grad: 0.0876 (0.0919) loss: 0.8169 (0.8179) time: 0.1532 data: 0.0744 max mem: 9390 +Train: [50] [3600/6250] eta: 0:06:00 lr: 0.000066 grad: 0.0890 (0.0918) loss: 0.8174 (0.8179) time: 0.1474 data: 0.0695 max mem: 9390 +Train: [50] [3700/6250] eta: 0:05:47 lr: 0.000066 grad: 0.0853 (0.0918) loss: 0.8169 (0.8179) time: 0.1427 data: 0.0669 max mem: 9390 +Train: [50] [3800/6250] eta: 0:05:33 lr: 0.000066 grad: 0.0893 (0.0919) loss: 0.8195 (0.8180) time: 0.1241 data: 0.0437 max mem: 9390 +Train: [50] [3900/6250] eta: 0:05:20 lr: 0.000066 grad: 0.0939 (0.0919) loss: 0.8175 (0.8181) time: 0.1342 data: 0.0525 max mem: 9390 +Train: [50] [4000/6250] eta: 0:05:06 lr: 0.000066 grad: 0.0895 (0.0919) loss: 0.8124 (0.8181) time: 0.1123 data: 0.0348 max mem: 9390 +Train: [50] [4100/6250] eta: 0:04:54 lr: 0.000066 grad: 0.0895 (0.0920) loss: 0.8196 (0.8181) time: 0.1406 data: 0.0638 max mem: 9390 +Train: [50] [4200/6250] eta: 0:04:41 lr: 0.000066 grad: 0.0934 (0.0920) loss: 0.8163 (0.8181) time: 0.1555 data: 0.0826 max mem: 9390 +Train: [50] [4300/6250] eta: 0:04:27 lr: 0.000066 grad: 0.0894 (0.0920) loss: 0.8193 (0.8181) time: 0.1626 data: 0.0785 max mem: 9390 +Train: [50] [4400/6250] eta: 0:04:15 lr: 0.000066 grad: 0.0949 (0.0920) loss: 0.8120 (0.8181) time: 0.1543 data: 0.0729 max mem: 9390 +Train: [50] [4500/6250] eta: 0:04:01 lr: 0.000066 grad: 0.0878 (0.0920) loss: 0.8204 (0.8181) time: 0.1370 data: 0.0596 max mem: 9390 +Train: [50] [4600/6250] eta: 0:03:47 lr: 0.000066 grad: 0.0874 (0.0920) loss: 0.8204 (0.8182) time: 0.1199 data: 0.0457 max mem: 9390 +Train: [50] [4700/6250] eta: 0:03:33 lr: 0.000066 grad: 0.0850 (0.0920) loss: 0.8231 (0.8182) time: 0.1035 data: 0.0269 max mem: 9390 +Train: [50] [4800/6250] eta: 0:03:19 lr: 0.000066 grad: 0.0880 (0.0920) loss: 0.8184 (0.8182) time: 0.1297 data: 0.0519 max mem: 9390 +Train: [50] [4900/6250] eta: 0:03:05 lr: 0.000066 grad: 0.0906 (0.0921) loss: 0.8134 (0.8182) time: 0.1362 data: 0.0574 max mem: 9390 +Train: [50] [5000/6250] eta: 0:02:51 lr: 0.000066 grad: 0.0898 (0.0921) loss: 0.8176 (0.8181) time: 0.1365 data: 0.0565 max mem: 9390 +Train: [50] [5100/6250] eta: 0:02:37 lr: 0.000066 grad: 0.0923 (0.0921) loss: 0.8173 (0.8182) time: 0.1716 data: 0.0456 max mem: 9390 +Train: [50] [5200/6250] eta: 0:02:24 lr: 0.000066 grad: 0.0878 (0.0921) loss: 0.8183 (0.8182) time: 0.1319 data: 0.0517 max mem: 9390 +Train: [50] [5300/6250] eta: 0:02:10 lr: 0.000066 grad: 0.0950 (0.0921) loss: 0.8142 (0.8181) time: 0.1267 data: 0.0507 max mem: 9390 +Train: [50] [5400/6250] eta: 0:01:56 lr: 0.000066 grad: 0.0901 (0.0921) loss: 0.8169 (0.8182) time: 0.1375 data: 0.0573 max mem: 9390 +Train: [50] [5500/6250] eta: 0:01:42 lr: 0.000066 grad: 0.0886 (0.0921) loss: 0.8224 (0.8182) time: 0.1263 data: 0.0522 max mem: 9390 +Train: [50] [5600/6250] eta: 0:01:28 lr: 0.000066 grad: 0.0930 (0.0922) loss: 0.8142 (0.8181) time: 0.1268 data: 0.0508 max mem: 9390 +Train: [50] [5700/6250] eta: 0:01:15 lr: 0.000066 grad: 0.0859 (0.0922) loss: 0.8201 (0.8181) time: 0.1464 data: 0.0669 max mem: 9390 +Train: [50] [5800/6250] eta: 0:01:01 lr: 0.000066 grad: 0.0893 (0.0922) loss: 0.8239 (0.8182) time: 0.1389 data: 0.0660 max mem: 9390 +Train: [50] [5900/6250] eta: 0:00:47 lr: 0.000066 grad: 0.0874 (0.0922) loss: 0.8223 (0.8182) time: 0.1308 data: 0.0569 max mem: 9390 +Train: [50] [6000/6250] eta: 0:00:34 lr: 0.000066 grad: 0.0900 (0.0923) loss: 0.8192 (0.8182) time: 0.1550 data: 0.0743 max mem: 9390 +Train: [50] [6100/6250] eta: 0:00:20 lr: 0.000066 grad: 0.0941 (0.0922) loss: 0.8206 (0.8182) time: 0.1425 data: 0.0689 max mem: 9390 +Train: [50] [6200/6250] eta: 0:00:06 lr: 0.000066 grad: 0.0935 (0.0923) loss: 0.8224 (0.8183) time: 0.1347 data: 0.0562 max mem: 9390 +Train: [50] [6249/6250] eta: 0:00:00 lr: 0.000066 grad: 0.0883 (0.0923) loss: 0.8193 (0.8183) time: 0.1507 data: 0.0706 max mem: 9390 +Train: [50] Total time: 0:14:22 (0.1380 s / it) +Averaged stats: lr: 0.000066 grad: 0.0883 (0.0923) loss: 0.8193 (0.8183) +Eval (hcp-train-subset): [50] [ 0/62] eta: 0:04:32 loss: 0.8448 (0.8448) time: 4.3995 data: 4.3703 max mem: 9390 +Eval (hcp-train-subset): [50] [61/62] eta: 0:00:00 loss: 0.8362 (0.8375) time: 0.1182 data: 0.0919 max mem: 9390 +Eval (hcp-train-subset): [50] Total time: 0:00:11 (0.1861 s / it) +Averaged stats (hcp-train-subset): loss: 0.8362 (0.8375) +Eval (hcp-val): [50] [ 0/62] eta: 0:03:48 loss: 0.8304 (0.8304) time: 3.6900 data: 3.6326 max mem: 9390 +Eval (hcp-val): [50] [61/62] eta: 0:00:00 loss: 0.8342 (0.8354) time: 0.1396 data: 0.1107 max mem: 9390 +Eval (hcp-val): [50] Total time: 0:00:12 (0.1975 s / it) +Averaged stats (hcp-val): loss: 0.8342 (0.8354) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +Train: [51] [ 0/6250] eta: 10:21:27 lr: 0.000066 grad: 0.0802 (0.0802) loss: 0.8412 (0.8412) time: 5.9660 data: 5.8683 max mem: 9390 +Train: [51] [ 100/6250] eta: 0:19:23 lr: 0.000066 grad: 0.0809 (0.0981) loss: 0.8292 (0.8376) time: 0.1302 data: 0.0391 max mem: 9390 +Train: [51] [ 200/6250] eta: 0:17:16 lr: 0.000066 grad: 0.0872 (0.0938) loss: 0.8265 (0.8330) time: 0.1439 data: 0.0594 max mem: 9390 +Train: [51] [ 300/6250] eta: 0:16:01 lr: 0.000065 grad: 0.0863 (0.0927) loss: 0.8183 (0.8291) time: 0.1439 data: 0.0519 max mem: 9390 +Train: [51] [ 400/6250] eta: 0:15:11 lr: 0.000065 grad: 0.0938 (0.0919) loss: 0.8203 (0.8271) time: 0.1156 data: 0.0287 max mem: 9390 +Train: [51] [ 500/6250] eta: 0:14:31 lr: 0.000065 grad: 0.0881 (0.0920) loss: 0.8196 (0.8255) time: 0.1532 data: 0.0667 max mem: 9390 +Train: [51] [ 600/6250] eta: 0:13:52 lr: 0.000065 grad: 0.0828 (0.0915) loss: 0.8216 (0.8245) time: 0.1420 data: 0.0615 max mem: 9390 +Train: [51] [ 700/6250] eta: 0:13:19 lr: 0.000065 grad: 0.0898 (0.0910) loss: 0.8193 (0.8239) time: 0.1097 data: 0.0284 max mem: 9390 +Train: [51] [ 800/6250] eta: 0:12:55 lr: 0.000065 grad: 0.0847 (0.0907) loss: 0.8204 (0.8232) time: 0.1414 data: 0.0592 max mem: 9390 +Train: [51] [ 900/6250] eta: 0:12:44 lr: 0.000065 grad: 0.0882 (0.0903) loss: 0.8175 (0.8226) time: 0.1993 data: 0.1189 max mem: 9390 +Train: [51] [1000/6250] eta: 0:12:24 lr: 0.000065 grad: 0.0911 (0.0901) loss: 0.8195 (0.8219) time: 0.1434 data: 0.0709 max mem: 9390 +Train: [51] [1100/6250] eta: 0:12:09 lr: 0.000065 grad: 0.0858 (0.0900) loss: 0.8177 (0.8214) time: 0.1421 data: 0.0604 max mem: 9390 +Train: [51] [1200/6250] eta: 0:11:58 lr: 0.000065 grad: 0.0862 (0.0900) loss: 0.8180 (0.8210) time: 0.1490 data: 0.0717 max mem: 9390 +Train: [51] [1300/6250] eta: 0:11:44 lr: 0.000065 grad: 0.0863 (0.0899) loss: 0.8142 (0.8205) time: 0.1406 data: 0.0614 max mem: 9390 +Train: [51] [1400/6250] eta: 0:11:31 lr: 0.000065 grad: 0.0835 (0.0898) loss: 0.8206 (0.8202) time: 0.1421 data: 0.0659 max mem: 9390 +Train: [51] [1500/6250] eta: 0:11:18 lr: 0.000065 grad: 0.0911 (0.0900) loss: 0.8147 (0.8200) time: 0.1589 data: 0.0728 max mem: 9390 +Train: [51] [1600/6250] eta: 0:11:00 lr: 0.000065 grad: 0.0852 (0.0899) loss: 0.8218 (0.8199) time: 0.1254 data: 0.0461 max mem: 9390 +Train: [51] [1700/6250] eta: 0:10:43 lr: 0.000065 grad: 0.0908 (0.0898) loss: 0.8161 (0.8197) time: 0.1414 data: 0.0654 max mem: 9390 +Train: [51] [1800/6250] eta: 0:10:27 lr: 0.000065 grad: 0.0875 (0.0898) loss: 0.8258 (0.8197) time: 0.1315 data: 0.0536 max mem: 9390 +Train: [51] [1900/6250] eta: 0:10:14 lr: 0.000065 grad: 0.0887 (0.0899) loss: 0.8099 (0.8195) time: 0.1241 data: 0.0487 max mem: 9390 +Train: [51] [2000/6250] eta: 0:09:59 lr: 0.000065 grad: 0.0854 (0.0899) loss: 0.8228 (0.8193) time: 0.1637 data: 0.0866 max mem: 9390 +Train: [51] [2100/6250] eta: 0:09:42 lr: 0.000065 grad: 0.0925 (0.0899) loss: 0.8152 (0.8191) time: 0.1292 data: 0.0468 max mem: 9390 +Train: [51] [2200/6250] eta: 0:09:27 lr: 0.000065 grad: 0.0916 (0.0901) loss: 0.8197 (0.8190) time: 0.1327 data: 0.0565 max mem: 9390 +Train: [51] [2300/6250] eta: 0:09:11 lr: 0.000065 grad: 0.0897 (0.0903) loss: 0.8121 (0.8188) time: 0.1249 data: 0.0456 max mem: 9390 +Train: [51] [2400/6250] eta: 0:08:56 lr: 0.000065 grad: 0.0893 (0.0903) loss: 0.8131 (0.8187) time: 0.1096 data: 0.0325 max mem: 9390 +Train: [51] [2500/6250] eta: 0:08:40 lr: 0.000065 grad: 0.0951 (0.0904) loss: 0.8131 (0.8185) time: 0.1173 data: 0.0378 max mem: 9390 +Train: [51] [2600/6250] eta: 0:08:25 lr: 0.000065 grad: 0.0841 (0.0904) loss: 0.8166 (0.8184) time: 0.1293 data: 0.0514 max mem: 9390 +Train: [51] [2700/6250] eta: 0:08:10 lr: 0.000065 grad: 0.0891 (0.0905) loss: 0.8126 (0.8182) time: 0.1352 data: 0.0551 max mem: 9390 +Train: [51] [2800/6250] eta: 0:07:56 lr: 0.000065 grad: 0.0972 (0.0905) loss: 0.8123 (0.8180) time: 0.1382 data: 0.0559 max mem: 9390 +Train: [51] [2900/6250] eta: 0:07:41 lr: 0.000065 grad: 0.0874 (0.0905) loss: 0.8105 (0.8179) time: 0.1302 data: 0.0521 max mem: 9390 +Train: [51] [3000/6250] eta: 0:07:27 lr: 0.000065 grad: 0.0860 (0.0905) loss: 0.8172 (0.8179) time: 0.1343 data: 0.0542 max mem: 9390 +Train: [51] [3100/6250] eta: 0:07:13 lr: 0.000065 grad: 0.0914 (0.0906) loss: 0.8141 (0.8178) time: 0.1333 data: 0.0535 max mem: 9390 +Train: [51] [3200/6250] eta: 0:07:00 lr: 0.000065 grad: 0.0966 (0.0908) loss: 0.8160 (0.8177) time: 0.1489 data: 0.0750 max mem: 9390 +Train: [51] [3300/6250] eta: 0:06:46 lr: 0.000065 grad: 0.0936 (0.0909) loss: 0.8108 (0.8176) time: 0.1384 data: 0.0525 max mem: 9390 +Train: [51] [3400/6250] eta: 0:06:32 lr: 0.000064 grad: 0.0871 (0.0910) loss: 0.8194 (0.8175) time: 0.1365 data: 0.0669 max mem: 9390 +Train: [51] [3500/6250] eta: 0:06:18 lr: 0.000064 grad: 0.0883 (0.0910) loss: 0.8118 (0.8174) time: 0.1347 data: 0.0522 max mem: 9390 +Train: [51] [3600/6250] eta: 0:06:04 lr: 0.000064 grad: 0.0891 (0.0911) loss: 0.8213 (0.8174) time: 0.1378 data: 0.0587 max mem: 9390 +Train: [51] [3700/6250] eta: 0:05:50 lr: 0.000064 grad: 0.0894 (0.0911) loss: 0.8186 (0.8174) time: 0.1230 data: 0.0346 max mem: 9390 +Train: [51] [3800/6250] eta: 0:05:36 lr: 0.000064 grad: 0.0847 (0.0911) loss: 0.8186 (0.8173) time: 0.1307 data: 0.0488 max mem: 9390 +Train: [51] [3900/6250] eta: 0:05:23 lr: 0.000064 grad: 0.0889 (0.0911) loss: 0.8172 (0.8174) time: 0.1347 data: 0.0500 max mem: 9390 +Train: [51] [4000/6250] eta: 0:05:11 lr: 0.000064 grad: 0.0962 (0.0912) loss: 0.8220 (0.8174) time: 0.1654 data: 0.0841 max mem: 9390 +Train: [51] [4100/6250] eta: 0:04:57 lr: 0.000064 grad: 0.0984 (0.0913) loss: 0.8173 (0.8174) time: 0.1542 data: 0.0642 max mem: 9390 +Train: [51] [4200/6250] eta: 0:04:44 lr: 0.000064 grad: 0.0969 (0.0915) loss: 0.8179 (0.8174) time: 0.1523 data: 0.0724 max mem: 9390 +Train: [51] [4300/6250] eta: 0:04:30 lr: 0.000064 grad: 0.0970 (0.0916) loss: 0.8114 (0.8173) time: 0.1485 data: 0.0737 max mem: 9390 +Train: [51] [4400/6250] eta: 0:04:17 lr: 0.000064 grad: 0.0966 (0.0917) loss: 0.8140 (0.8173) time: 0.1262 data: 0.0379 max mem: 9390 +Train: [51] [4500/6250] eta: 0:04:03 lr: 0.000064 grad: 0.0999 (0.0918) loss: 0.8154 (0.8173) time: 0.1462 data: 0.0668 max mem: 9390 +Train: [51] [4600/6250] eta: 0:03:49 lr: 0.000064 grad: 0.0922 (0.0919) loss: 0.8168 (0.8173) time: 0.1200 data: 0.0348 max mem: 9390 +Train: [51] [4700/6250] eta: 0:03:35 lr: 0.000064 grad: 0.0969 (0.0919) loss: 0.8124 (0.8173) time: 0.1284 data: 0.0489 max mem: 9390 +Train: [51] [4800/6250] eta: 0:03:21 lr: 0.000064 grad: 0.0924 (0.0920) loss: 0.8192 (0.8173) time: 0.1444 data: 0.0679 max mem: 9390 +Train: [51] [4900/6250] eta: 0:03:06 lr: 0.000064 grad: 0.0896 (0.0920) loss: 0.8205 (0.8173) time: 0.1235 data: 0.0375 max mem: 9390 +Train: [51] [5000/6250] eta: 0:02:52 lr: 0.000064 grad: 0.0993 (0.0920) loss: 0.8191 (0.8173) time: 0.1205 data: 0.0412 max mem: 9390 +Train: [51] [5100/6250] eta: 0:02:38 lr: 0.000064 grad: 0.0876 (0.0920) loss: 0.8221 (0.8174) time: 0.1262 data: 0.0450 max mem: 9390 +Train: [51] [5200/6250] eta: 0:02:24 lr: 0.000064 grad: 0.0929 (0.0921) loss: 0.8203 (0.8175) time: 0.1169 data: 0.0324 max mem: 9390 +Train: [51] [5300/6250] eta: 0:02:10 lr: 0.000064 grad: 0.0922 (0.0921) loss: 0.8258 (0.8175) time: 0.1101 data: 0.0279 max mem: 9390 +Train: [51] [5400/6250] eta: 0:01:56 lr: 0.000064 grad: 0.0951 (0.0921) loss: 0.8249 (0.8176) time: 0.1183 data: 0.0418 max mem: 9390 +Train: [51] [5500/6250] eta: 0:01:42 lr: 0.000064 grad: 0.0865 (0.0921) loss: 0.8293 (0.8177) time: 0.1446 data: 0.0723 max mem: 9390 +Train: [51] [5600/6250] eta: 0:01:29 lr: 0.000064 grad: 0.0885 (0.0922) loss: 0.8225 (0.8178) time: 0.1378 data: 0.0603 max mem: 9390 +Train: [51] [5700/6250] eta: 0:01:15 lr: 0.000064 grad: 0.0876 (0.0922) loss: 0.8234 (0.8179) time: 0.1218 data: 0.0404 max mem: 9390 +Train: [51] [5800/6250] eta: 0:01:01 lr: 0.000064 grad: 0.0938 (0.0922) loss: 0.8186 (0.8179) time: 0.1287 data: 0.0457 max mem: 9390 +Train: [51] [5900/6250] eta: 0:00:47 lr: 0.000064 grad: 0.0915 (0.0922) loss: 0.8186 (0.8179) time: 0.1703 data: 0.0556 max mem: 9390 +Train: [51] [6000/6250] eta: 0:00:34 lr: 0.000064 grad: 0.0888 (0.0922) loss: 0.8223 (0.8180) time: 0.1334 data: 0.0470 max mem: 9390 +Train: [51] [6100/6250] eta: 0:00:20 lr: 0.000064 grad: 0.0881 (0.0922) loss: 0.8202 (0.8180) time: 0.1294 data: 0.0522 max mem: 9390 +Train: [51] [6200/6250] eta: 0:00:06 lr: 0.000064 grad: 0.0893 (0.0922) loss: 0.8218 (0.8180) time: 0.1279 data: 0.0481 max mem: 9390 +Train: [51] [6249/6250] eta: 0:00:00 lr: 0.000064 grad: 0.0951 (0.0922) loss: 0.8162 (0.8180) time: 0.1173 data: 0.0356 max mem: 9390 +Train: [51] Total time: 0:14:21 (0.1378 s / it) +Averaged stats: lr: 0.000064 grad: 0.0951 (0.0922) loss: 0.8162 (0.8180) +Eval (hcp-train-subset): [51] [ 0/62] eta: 0:04:22 loss: 0.8457 (0.8457) time: 4.2324 data: 4.2026 max mem: 9390 +Eval (hcp-train-subset): [51] [61/62] eta: 0:00:00 loss: 0.8373 (0.8369) time: 0.1023 data: 0.0774 max mem: 9390 +Eval (hcp-train-subset): [51] Total time: 0:00:11 (0.1881 s / it) +Averaged stats (hcp-train-subset): loss: 0.8373 (0.8369) +Eval (hcp-val): [51] [ 0/62] eta: 0:04:08 loss: 0.8299 (0.8299) time: 4.0096 data: 3.9740 max mem: 9390 +Eval (hcp-val): [51] [61/62] eta: 0:00:00 loss: 0.8346 (0.8351) time: 0.1182 data: 0.0910 max mem: 9390 +Eval (hcp-val): [51] Total time: 0:00:12 (0.1987 s / it) +Averaged stats (hcp-val): loss: 0.8346 (0.8351) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +Train: [52] [ 0/6250] eta: 6:21:07 lr: 0.000064 grad: 0.0776 (0.0776) loss: 0.8307 (0.8307) time: 3.6588 data: 3.4466 max mem: 9390 +Train: [52] [ 100/6250] eta: 0:20:11 lr: 0.000063 grad: 0.0999 (0.1162) loss: 0.8273 (0.8329) time: 0.1466 data: 0.0523 max mem: 9390 +Train: [52] [ 200/6250] eta: 0:17:18 lr: 0.000063 grad: 0.0938 (0.1091) loss: 0.8196 (0.8271) time: 0.1460 data: 0.0618 max mem: 9390 +Train: [52] [ 300/6250] eta: 0:16:01 lr: 0.000063 grad: 0.0869 (0.1045) loss: 0.8168 (0.8246) time: 0.1449 data: 0.0672 max mem: 9390 +Train: [52] [ 400/6250] eta: 0:14:51 lr: 0.000063 grad: 0.0875 (0.1024) loss: 0.8235 (0.8239) time: 0.1350 data: 0.0522 max mem: 9390 +Train: [52] [ 500/6250] eta: 0:14:08 lr: 0.000063 grad: 0.0889 (0.0999) loss: 0.8170 (0.8233) time: 0.1251 data: 0.0377 max mem: 9390 +Train: [52] [ 600/6250] eta: 0:13:35 lr: 0.000063 grad: 0.0833 (0.0986) loss: 0.8184 (0.8226) time: 0.1297 data: 0.0526 max mem: 9390 +Train: [52] [ 700/6250] eta: 0:13:06 lr: 0.000063 grad: 0.0786 (0.0974) loss: 0.8328 (0.8224) time: 0.1112 data: 0.0244 max mem: 9390 +Train: [52] [ 800/6250] eta: 0:12:39 lr: 0.000063 grad: 0.0852 (0.0963) loss: 0.8286 (0.8225) time: 0.1018 data: 0.0188 max mem: 9390 +Train: [52] [ 900/6250] eta: 0:12:20 lr: 0.000063 grad: 0.0901 (0.0956) loss: 0.8186 (0.8223) time: 0.1322 data: 0.0476 max mem: 9390 +Train: [52] [1000/6250] eta: 0:12:00 lr: 0.000063 grad: 0.0926 (0.0950) loss: 0.8208 (0.8219) time: 0.1591 data: 0.0811 max mem: 9390 +Train: [52] [1100/6250] eta: 0:11:42 lr: 0.000063 grad: 0.0802 (0.0944) loss: 0.8253 (0.8218) time: 0.1246 data: 0.0447 max mem: 9390 +Train: [52] [1200/6250] eta: 0:11:25 lr: 0.000063 grad: 0.0889 (0.0940) loss: 0.8149 (0.8216) time: 0.1294 data: 0.0556 max mem: 9390 +Train: [52] [1300/6250] eta: 0:11:09 lr: 0.000063 grad: 0.0892 (0.0936) loss: 0.8159 (0.8216) time: 0.1226 data: 0.0376 max mem: 9390 +Train: [52] [1400/6250] eta: 0:10:52 lr: 0.000063 grad: 0.0883 (0.0931) loss: 0.8187 (0.8215) time: 0.1236 data: 0.0426 max mem: 9390 +Train: [52] [1500/6250] eta: 0:10:37 lr: 0.000063 grad: 0.0838 (0.0929) loss: 0.8189 (0.8215) time: 0.1183 data: 0.0379 max mem: 9390 +Train: [52] [1600/6250] eta: 0:10:23 lr: 0.000063 grad: 0.0851 (0.0928) loss: 0.8233 (0.8216) time: 0.1033 data: 0.0252 max mem: 9390 +Train: [52] [1700/6250] eta: 0:10:08 lr: 0.000063 grad: 0.0885 (0.0925) loss: 0.8239 (0.8215) time: 0.1406 data: 0.0583 max mem: 9390 +Train: [52] [1800/6250] eta: 0:09:55 lr: 0.000063 grad: 0.0832 (0.0923) loss: 0.8228 (0.8216) time: 0.1402 data: 0.0651 max mem: 9390 +Train: [52] [1900/6250] eta: 0:09:42 lr: 0.000063 grad: 0.0886 (0.0921) loss: 0.8237 (0.8216) time: 0.1419 data: 0.0503 max mem: 9390 +Train: [52] [2000/6250] eta: 0:09:28 lr: 0.000063 grad: 0.0870 (0.0919) loss: 0.8235 (0.8217) time: 0.1190 data: 0.0414 max mem: 9390 +Train: [52] [2100/6250] eta: 0:09:18 lr: 0.000063 grad: 0.0897 (0.0918) loss: 0.8183 (0.8218) time: 0.2175 data: 0.1406 max mem: 9390 +Train: [52] [2200/6250] eta: 0:09:01 lr: 0.000063 grad: 0.0887 (0.0918) loss: 0.8162 (0.8217) time: 0.1223 data: 0.0405 max mem: 9390 +Train: [52] [2300/6250] eta: 0:08:47 lr: 0.000063 grad: 0.0881 (0.0917) loss: 0.8228 (0.8218) time: 0.1088 data: 0.0302 max mem: 9390 +Train: [52] [2400/6250] eta: 0:08:33 lr: 0.000063 grad: 0.0896 (0.0919) loss: 0.8288 (0.8218) time: 0.1353 data: 0.0614 max mem: 9390 +Train: [52] [2500/6250] eta: 0:08:18 lr: 0.000063 grad: 0.0880 (0.0918) loss: 0.8211 (0.8218) time: 0.1176 data: 0.0409 max mem: 9390 +Train: [52] [2600/6250] eta: 0:08:05 lr: 0.000063 grad: 0.0862 (0.0918) loss: 0.8165 (0.8218) time: 0.1342 data: 0.0557 max mem: 9390 +Train: [52] [2700/6250] eta: 0:07:52 lr: 0.000063 grad: 0.0885 (0.0918) loss: 0.8273 (0.8219) time: 0.1467 data: 0.0669 max mem: 9390 +Train: [52] [2800/6250] eta: 0:07:39 lr: 0.000063 grad: 0.0867 (0.0918) loss: 0.8228 (0.8219) time: 0.1275 data: 0.0530 max mem: 9390 +Train: [52] [2900/6250] eta: 0:07:25 lr: 0.000063 grad: 0.0844 (0.0917) loss: 0.8263 (0.8220) time: 0.1301 data: 0.0429 max mem: 9390 +Train: [52] [3000/6250] eta: 0:07:12 lr: 0.000063 grad: 0.0902 (0.0918) loss: 0.8200 (0.8220) time: 0.1537 data: 0.0798 max mem: 9390 +Train: [52] [3100/6250] eta: 0:06:59 lr: 0.000063 grad: 0.0886 (0.0918) loss: 0.8210 (0.8219) time: 0.1264 data: 0.0438 max mem: 9390 +Train: [52] [3200/6250] eta: 0:06:48 lr: 0.000062 grad: 0.0950 (0.0919) loss: 0.8215 (0.8217) time: 0.1518 data: 0.0668 max mem: 9390 +Train: [52] [3300/6250] eta: 0:06:35 lr: 0.000062 grad: 0.0936 (0.0920) loss: 0.8144 (0.8216) time: 0.1574 data: 0.0745 max mem: 9390 +Train: [52] [3400/6250] eta: 0:06:23 lr: 0.000062 grad: 0.0884 (0.0921) loss: 0.8192 (0.8215) time: 0.1554 data: 0.0729 max mem: 9390 +Train: [52] [3500/6250] eta: 0:06:10 lr: 0.000062 grad: 0.0932 (0.0922) loss: 0.8099 (0.8213) time: 0.1675 data: 0.0888 max mem: 9390 +Train: [52] [3600/6250] eta: 0:05:56 lr: 0.000062 grad: 0.0938 (0.0922) loss: 0.8199 (0.8212) time: 0.1255 data: 0.0445 max mem: 9390 +Train: [52] [3700/6250] eta: 0:05:44 lr: 0.000062 grad: 0.0920 (0.0921) loss: 0.8220 (0.8212) time: 0.1535 data: 0.0621 max mem: 9390 +Train: [52] [3800/6250] eta: 0:05:31 lr: 0.000062 grad: 0.0918 (0.0922) loss: 0.8193 (0.8210) time: 0.1465 data: 0.0631 max mem: 9390 +Train: [52] [3900/6250] eta: 0:05:18 lr: 0.000062 grad: 0.0911 (0.0922) loss: 0.8186 (0.8210) time: 0.1854 data: 0.1131 max mem: 9390 +Train: [52] [4000/6250] eta: 0:05:06 lr: 0.000062 grad: 0.0881 (0.0922) loss: 0.8200 (0.8209) time: 0.1465 data: 0.0670 max mem: 9390 +Train: [52] [4100/6250] eta: 0:04:52 lr: 0.000062 grad: 0.0925 (0.0923) loss: 0.8162 (0.8208) time: 0.1390 data: 0.0584 max mem: 9390 +Train: [52] [4200/6250] eta: 0:04:39 lr: 0.000062 grad: 0.0886 (0.0924) loss: 0.8144 (0.8207) time: 0.1521 data: 0.0707 max mem: 9390 +Train: [52] [4300/6250] eta: 0:04:26 lr: 0.000062 grad: 0.0940 (0.0925) loss: 0.8164 (0.8206) time: 0.1642 data: 0.0783 max mem: 9390 +Train: [52] [4400/6250] eta: 0:04:13 lr: 0.000062 grad: 0.0924 (0.0925) loss: 0.8172 (0.8206) time: 0.1418 data: 0.0632 max mem: 9390 +Train: [52] [4500/6250] eta: 0:03:59 lr: 0.000062 grad: 0.0927 (0.0924) loss: 0.8250 (0.8206) time: 0.1332 data: 0.0549 max mem: 9390 +Train: [52] [4600/6250] eta: 0:03:45 lr: 0.000062 grad: 0.0878 (0.0925) loss: 0.8169 (0.8205) time: 0.1419 data: 0.0613 max mem: 9390 +Train: [52] [4700/6250] eta: 0:03:31 lr: 0.000062 grad: 0.0887 (0.0924) loss: 0.8130 (0.8204) time: 0.1321 data: 0.0601 max mem: 9390 +Train: [52] [4800/6250] eta: 0:03:17 lr: 0.000062 grad: 0.0912 (0.0925) loss: 0.8157 (0.8204) time: 0.1049 data: 0.0213 max mem: 9390 +Train: [52] [4900/6250] eta: 0:03:03 lr: 0.000062 grad: 0.0911 (0.0924) loss: 0.8186 (0.8203) time: 0.1184 data: 0.0362 max mem: 9390 +Train: [52] [5000/6250] eta: 0:02:50 lr: 0.000062 grad: 0.0868 (0.0925) loss: 0.8174 (0.8202) time: 0.1261 data: 0.0478 max mem: 9390 +Train: [52] [5100/6250] eta: 0:02:36 lr: 0.000062 grad: 0.0886 (0.0924) loss: 0.8165 (0.8202) time: 0.1161 data: 0.0362 max mem: 9390 +Train: [52] [5200/6250] eta: 0:02:22 lr: 0.000062 grad: 0.0874 (0.0924) loss: 0.8207 (0.8202) time: 0.1289 data: 0.0457 max mem: 9390 +Train: [52] [5300/6250] eta: 0:02:08 lr: 0.000062 grad: 0.0922 (0.0924) loss: 0.8174 (0.8202) time: 0.1389 data: 0.0561 max mem: 9390 +Train: [52] [5400/6250] eta: 0:01:54 lr: 0.000062 grad: 0.0854 (0.0924) loss: 0.8222 (0.8202) time: 0.1104 data: 0.0341 max mem: 9390 +Train: [52] [5500/6250] eta: 0:01:41 lr: 0.000062 grad: 0.0878 (0.0923) loss: 0.8156 (0.8201) time: 0.1229 data: 0.0425 max mem: 9390 +Train: [52] [5600/6250] eta: 0:01:27 lr: 0.000062 grad: 0.0874 (0.0923) loss: 0.8125 (0.8201) time: 0.1456 data: 0.0599 max mem: 9390 +Train: [52] [5700/6250] eta: 0:01:14 lr: 0.000062 grad: 0.0867 (0.0924) loss: 0.8210 (0.8200) time: 0.1342 data: 0.0457 max mem: 9390 +Train: [52] [5800/6250] eta: 0:01:00 lr: 0.000062 grad: 0.0923 (0.0924) loss: 0.8110 (0.8200) time: 0.1351 data: 0.0549 max mem: 9390 +Train: [52] [5900/6250] eta: 0:00:47 lr: 0.000062 grad: 0.0932 (0.0923) loss: 0.8110 (0.8200) time: 0.1404 data: 0.0665 max mem: 9390 +Train: [52] [6000/6250] eta: 0:00:33 lr: 0.000062 grad: 0.0876 (0.0923) loss: 0.8208 (0.8200) time: 0.1319 data: 0.0485 max mem: 9390 +Train: [52] [6100/6250] eta: 0:00:20 lr: 0.000062 grad: 0.0896 (0.0922) loss: 0.8176 (0.8200) time: 0.2103 data: 0.1225 max mem: 9390 +Train: [52] [6200/6250] eta: 0:00:06 lr: 0.000061 grad: 0.0915 (0.0922) loss: 0.8122 (0.8200) time: 0.1459 data: 0.0703 max mem: 9390 +Train: [52] [6249/6250] eta: 0:00:00 lr: 0.000061 grad: 0.0877 (0.0922) loss: 0.8154 (0.8199) time: 0.1848 data: 0.1108 max mem: 9390 +Train: [52] Total time: 0:14:12 (0.1364 s / it) +Averaged stats: lr: 0.000061 grad: 0.0877 (0.0922) loss: 0.8154 (0.8199) +Eval (hcp-train-subset): [52] [ 0/62] eta: 0:04:32 loss: 0.8509 (0.8509) time: 4.3910 data: 4.3619 max mem: 9390 +Eval (hcp-train-subset): [52] [61/62] eta: 0:00:00 loss: 0.8371 (0.8360) time: 0.1220 data: 0.0967 max mem: 9390 +Eval (hcp-train-subset): [52] Total time: 0:00:12 (0.2030 s / it) +Averaged stats (hcp-train-subset): loss: 0.8371 (0.8360) +Eval (hcp-val): [52] [ 0/62] eta: 0:03:11 loss: 0.8350 (0.8350) time: 3.0890 data: 2.9971 max mem: 9390 +Eval (hcp-val): [52] [61/62] eta: 0:00:00 loss: 0.8349 (0.8355) time: 0.1274 data: 0.1021 max mem: 9390 +Eval (hcp-val): [52] Total time: 0:00:12 (0.2064 s / it) +Averaged stats (hcp-val): loss: 0.8349 (0.8355) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +Train: [53] [ 0/6250] eta: 10:18:23 lr: 0.000061 grad: 0.1348 (0.1348) loss: 0.8502 (0.8502) time: 5.9365 data: 5.8418 max mem: 9390 +Train: [53] [ 100/6250] eta: 0:20:10 lr: 0.000061 grad: 0.0965 (0.1098) loss: 0.8250 (0.8284) time: 0.1362 data: 0.0272 max mem: 9390 +Train: [53] [ 200/6250] eta: 0:17:27 lr: 0.000061 grad: 0.0907 (0.1034) loss: 0.8157 (0.8241) time: 0.1524 data: 0.0611 max mem: 9390 +Train: [53] [ 300/6250] eta: 0:15:54 lr: 0.000061 grad: 0.0944 (0.1003) loss: 0.8196 (0.8223) time: 0.1543 data: 0.0706 max mem: 9390 +Train: [53] [ 400/6250] eta: 0:15:06 lr: 0.000061 grad: 0.0880 (0.0984) loss: 0.8245 (0.8227) time: 0.1295 data: 0.0498 max mem: 9390 +Train: [53] [ 500/6250] eta: 0:14:24 lr: 0.000061 grad: 0.0905 (0.0969) loss: 0.8266 (0.8229) time: 0.1425 data: 0.0605 max mem: 9390 +Train: [53] [ 600/6250] eta: 0:13:48 lr: 0.000061 grad: 0.0956 (0.0962) loss: 0.8198 (0.8225) time: 0.1331 data: 0.0513 max mem: 9390 +Train: [53] [ 700/6250] eta: 0:13:15 lr: 0.000061 grad: 0.0880 (0.0958) loss: 0.8172 (0.8221) time: 0.1292 data: 0.0421 max mem: 9390 +Train: [53] [ 800/6250] eta: 0:12:50 lr: 0.000061 grad: 0.0893 (0.0961) loss: 0.8173 (0.8216) time: 0.1208 data: 0.0423 max mem: 9390 +Train: [53] [ 900/6250] eta: 0:12:28 lr: 0.000061 grad: 0.0941 (0.0959) loss: 0.8154 (0.8209) time: 0.1303 data: 0.0508 max mem: 9390 +Train: [53] [1000/6250] eta: 0:12:10 lr: 0.000061 grad: 0.0909 (0.0956) loss: 0.8144 (0.8205) time: 0.1232 data: 0.0472 max mem: 9390 +Train: [53] [1100/6250] eta: 0:12:00 lr: 0.000061 grad: 0.0867 (0.0956) loss: 0.8111 (0.8199) time: 0.1794 data: 0.0920 max mem: 9390 +Train: [53] [1200/6250] eta: 0:11:41 lr: 0.000061 grad: 0.0944 (0.0963) loss: 0.8218 (0.8194) time: 0.1412 data: 0.0650 max mem: 9390 +Train: [53] [1300/6250] eta: 0:11:23 lr: 0.000061 grad: 0.0974 (0.0962) loss: 0.8081 (0.8191) time: 0.1228 data: 0.0402 max mem: 9390 +Train: [53] [1400/6250] eta: 0:11:06 lr: 0.000061 grad: 0.0956 (0.0963) loss: 0.8106 (0.8185) time: 0.1342 data: 0.0569 max mem: 9390 +Train: [53] [1500/6250] eta: 0:10:49 lr: 0.000061 grad: 0.0959 (0.0963) loss: 0.8087 (0.8180) time: 0.1251 data: 0.0398 max mem: 9390 +Train: [53] [1600/6250] eta: 0:10:31 lr: 0.000061 grad: 0.0980 (0.0965) loss: 0.8109 (0.8175) time: 0.1233 data: 0.0463 max mem: 9390 +Train: [53] [1700/6250] eta: 0:10:18 lr: 0.000061 grad: 0.0910 (0.0965) loss: 0.8094 (0.8172) time: 0.1125 data: 0.0279 max mem: 9390 +Train: [53] [1800/6250] eta: 0:10:01 lr: 0.000061 grad: 0.0945 (0.0965) loss: 0.8124 (0.8170) time: 0.1139 data: 0.0361 max mem: 9390 +Train: [53] [1900/6250] eta: 0:09:48 lr: 0.000061 grad: 0.0960 (0.0967) loss: 0.8142 (0.8167) time: 0.1567 data: 0.0759 max mem: 9390 +Train: [53] [2000/6250] eta: 0:09:33 lr: 0.000061 grad: 0.0943 (0.0967) loss: 0.8093 (0.8165) time: 0.1681 data: 0.0913 max mem: 9390 +Train: [53] [2100/6250] eta: 0:09:17 lr: 0.000061 grad: 0.0933 (0.0967) loss: 0.8138 (0.8163) time: 0.1337 data: 0.0456 max mem: 9390 +Train: [53] [2200/6250] eta: 0:09:05 lr: 0.000061 grad: 0.0988 (0.0966) loss: 0.8044 (0.8162) time: 0.1503 data: 0.0633 max mem: 9390 +Train: [53] [2300/6250] eta: 0:08:51 lr: 0.000061 grad: 0.0938 (0.0966) loss: 0.8087 (0.8161) time: 0.1545 data: 0.0810 max mem: 9390 +Train: [53] [2400/6250] eta: 0:08:37 lr: 0.000061 grad: 0.0947 (0.0966) loss: 0.8107 (0.8159) time: 0.1271 data: 0.0489 max mem: 9390 +Train: [53] [2500/6250] eta: 0:08:25 lr: 0.000061 grad: 0.0915 (0.0965) loss: 0.8160 (0.8158) time: 0.1611 data: 0.0789 max mem: 9390 +Train: [53] [2600/6250] eta: 0:08:13 lr: 0.000061 grad: 0.0912 (0.0965) loss: 0.8168 (0.8157) time: 0.1338 data: 0.0555 max mem: 9390 +Train: [53] [2700/6250] eta: 0:07:59 lr: 0.000061 grad: 0.0944 (0.0965) loss: 0.8101 (0.8156) time: 0.1195 data: 0.0422 max mem: 9390 +Train: [53] [2800/6250] eta: 0:07:45 lr: 0.000061 grad: 0.0917 (0.0966) loss: 0.8152 (0.8155) time: 0.1432 data: 0.0693 max mem: 9390 +Train: [53] [2900/6250] eta: 0:07:32 lr: 0.000061 grad: 0.0964 (0.0966) loss: 0.8085 (0.8155) time: 0.1381 data: 0.0616 max mem: 9390 +Train: [53] [3000/6250] eta: 0:07:19 lr: 0.000060 grad: 0.0971 (0.0967) loss: 0.8206 (0.8155) time: 0.1130 data: 0.0337 max mem: 9390 +Train: [53] [3100/6250] eta: 0:07:06 lr: 0.000060 grad: 0.0915 (0.0968) loss: 0.8115 (0.8155) time: 0.1314 data: 0.0551 max mem: 9390 +Train: [53] [3200/6250] eta: 0:06:52 lr: 0.000060 grad: 0.0873 (0.0968) loss: 0.8151 (0.8155) time: 0.1508 data: 0.0714 max mem: 9390 +Train: [53] [3300/6250] eta: 0:06:39 lr: 0.000060 grad: 0.0931 (0.0967) loss: 0.8171 (0.8155) time: 0.1462 data: 0.0647 max mem: 9390 +Train: [53] [3400/6250] eta: 0:06:27 lr: 0.000060 grad: 0.0939 (0.0968) loss: 0.8131 (0.8155) time: 0.1498 data: 0.0688 max mem: 9390 +Train: [53] [3500/6250] eta: 0:06:14 lr: 0.000060 grad: 0.0965 (0.0968) loss: 0.8103 (0.8154) time: 0.1680 data: 0.0959 max mem: 9390 +Train: [53] [3600/6250] eta: 0:06:00 lr: 0.000060 grad: 0.0898 (0.0968) loss: 0.8123 (0.8154) time: 0.1196 data: 0.0339 max mem: 9390 +Train: [53] [3700/6250] eta: 0:05:47 lr: 0.000060 grad: 0.0968 (0.0967) loss: 0.8170 (0.8154) time: 0.1395 data: 0.0611 max mem: 9390 +Train: [53] [3800/6250] eta: 0:05:35 lr: 0.000060 grad: 0.0920 (0.0968) loss: 0.8198 (0.8154) time: 0.2137 data: 0.1408 max mem: 9390 +Train: [53] [3900/6250] eta: 0:05:22 lr: 0.000060 grad: 0.0949 (0.0968) loss: 0.8149 (0.8154) time: 0.1532 data: 0.0683 max mem: 9390 +Train: [53] [4000/6250] eta: 0:05:09 lr: 0.000060 grad: 0.0957 (0.0968) loss: 0.8152 (0.8155) time: 0.1564 data: 0.0755 max mem: 9390 +Train: [53] [4100/6250] eta: 0:04:57 lr: 0.000060 grad: 0.0867 (0.0968) loss: 0.8227 (0.8155) time: 0.1521 data: 0.0776 max mem: 9390 +Train: [53] [4200/6250] eta: 0:04:43 lr: 0.000060 grad: 0.0943 (0.0969) loss: 0.8179 (0.8155) time: 0.1446 data: 0.0633 max mem: 9390 +Train: [53] [4300/6250] eta: 0:04:29 lr: 0.000060 grad: 0.0973 (0.0969) loss: 0.8149 (0.8155) time: 0.1298 data: 0.0480 max mem: 9390 +Train: [53] [4400/6250] eta: 0:04:15 lr: 0.000060 grad: 0.0971 (0.0969) loss: 0.8082 (0.8155) time: 0.1362 data: 0.0546 max mem: 9390 +Train: [53] [4500/6250] eta: 0:04:01 lr: 0.000060 grad: 0.0931 (0.0969) loss: 0.8157 (0.8155) time: 0.1402 data: 0.0560 max mem: 9390 +Train: [53] [4600/6250] eta: 0:03:47 lr: 0.000060 grad: 0.0957 (0.0969) loss: 0.8142 (0.8155) time: 0.1239 data: 0.0451 max mem: 9390 +Train: [53] [4700/6250] eta: 0:03:33 lr: 0.000060 grad: 0.0942 (0.0970) loss: 0.8162 (0.8155) time: 0.1336 data: 0.0405 max mem: 9390 +Train: [53] [4800/6250] eta: 0:03:19 lr: 0.000060 grad: 0.0926 (0.0970) loss: 0.8140 (0.8155) time: 0.1547 data: 0.0757 max mem: 9390 +Train: [53] [4900/6250] eta: 0:03:04 lr: 0.000060 grad: 0.0947 (0.0971) loss: 0.8161 (0.8155) time: 0.1293 data: 0.0465 max mem: 9390 +Train: [53] [5000/6250] eta: 0:02:51 lr: 0.000060 grad: 0.0950 (0.0971) loss: 0.8179 (0.8155) time: 0.1201 data: 0.0323 max mem: 9390 +Train: [53] [5100/6250] eta: 0:02:37 lr: 0.000060 grad: 0.1022 (0.0971) loss: 0.8171 (0.8155) time: 0.1527 data: 0.0747 max mem: 9390 +Train: [53] [5200/6250] eta: 0:02:23 lr: 0.000060 grad: 0.0898 (0.0972) loss: 0.8147 (0.8155) time: 0.1533 data: 0.0765 max mem: 9390 +Train: [53] [5300/6250] eta: 0:02:09 lr: 0.000060 grad: 0.0961 (0.0972) loss: 0.8075 (0.8155) time: 0.1337 data: 0.0573 max mem: 9390 +Train: [53] [5400/6250] eta: 0:01:55 lr: 0.000060 grad: 0.0954 (0.0972) loss: 0.8173 (0.8155) time: 0.1223 data: 0.0418 max mem: 9390 +Train: [53] [5500/6250] eta: 0:01:42 lr: 0.000060 grad: 0.1037 (0.0973) loss: 0.8128 (0.8155) time: 0.1428 data: 0.0471 max mem: 9390 +Train: [53] [5600/6250] eta: 0:01:28 lr: 0.000060 grad: 0.0997 (0.0973) loss: 0.8121 (0.8155) time: 0.1615 data: 0.0719 max mem: 9390 +Train: [53] [5700/6250] eta: 0:01:14 lr: 0.000060 grad: 0.0941 (0.0973) loss: 0.8167 (0.8155) time: 0.1389 data: 0.0540 max mem: 9390 +Train: [53] [5800/6250] eta: 0:01:01 lr: 0.000060 grad: 0.0962 (0.0973) loss: 0.8195 (0.8155) time: 0.1559 data: 0.0682 max mem: 9390 +Train: [53] [5900/6250] eta: 0:00:47 lr: 0.000060 grad: 0.0983 (0.0974) loss: 0.8165 (0.8154) time: 0.1380 data: 0.0572 max mem: 9390 +Train: [53] [6000/6250] eta: 0:00:34 lr: 0.000059 grad: 0.0988 (0.0974) loss: 0.8061 (0.8154) time: 0.1458 data: 0.0681 max mem: 9390 +Train: [53] [6100/6250] eta: 0:00:20 lr: 0.000059 grad: 0.0930 (0.0974) loss: 0.8187 (0.8154) time: 0.1432 data: 0.0670 max mem: 9390 +Train: [53] [6200/6250] eta: 0:00:06 lr: 0.000059 grad: 0.0874 (0.0974) loss: 0.8155 (0.8154) time: 0.1552 data: 0.0781 max mem: 9390 +Train: [53] [6249/6250] eta: 0:00:00 lr: 0.000059 grad: 0.0904 (0.0974) loss: 0.8162 (0.8154) time: 0.1351 data: 0.0555 max mem: 9390 +Train: [53] Total time: 0:14:21 (0.1379 s / it) +Averaged stats: lr: 0.000059 grad: 0.0904 (0.0974) loss: 0.8162 (0.8154) +Eval (hcp-train-subset): [53] [ 0/62] eta: 0:04:51 loss: 0.8449 (0.8449) time: 4.7088 data: 4.6792 max mem: 9390 +Eval (hcp-train-subset): [53] [61/62] eta: 0:00:00 loss: 0.8361 (0.8358) time: 0.1257 data: 0.1006 max mem: 9390 +Eval (hcp-train-subset): [53] Total time: 0:00:12 (0.2011 s / it) +Averaged stats (hcp-train-subset): loss: 0.8361 (0.8358) +Eval (hcp-val): [53] [ 0/62] eta: 0:04:14 loss: 0.8337 (0.8337) time: 4.0981 data: 4.0660 max mem: 9390 +Eval (hcp-val): [53] [61/62] eta: 0:00:00 loss: 0.8334 (0.8344) time: 0.1356 data: 0.1104 max mem: 9390 +Eval (hcp-val): [53] Total time: 0:00:12 (0.2027 s / it) +Averaged stats (hcp-val): loss: 0.8334 (0.8344) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +Train: [54] [ 0/6250] eta: 8:27:21 lr: 0.000059 grad: 0.0509 (0.0509) loss: 0.8599 (0.8599) time: 4.8706 data: 4.6183 max mem: 9390 +Train: [54] [ 100/6250] eta: 0:19:41 lr: 0.000059 grad: 0.0846 (0.1016) loss: 0.8267 (0.8287) time: 0.1370 data: 0.0457 max mem: 9390 +Train: [54] [ 200/6250] eta: 0:16:55 lr: 0.000059 grad: 0.0849 (0.0967) loss: 0.8383 (0.8303) time: 0.1373 data: 0.0475 max mem: 9390 +Train: [54] [ 300/6250] eta: 0:15:45 lr: 0.000059 grad: 0.0903 (0.0968) loss: 0.8304 (0.8293) time: 0.1524 data: 0.0741 max mem: 9390 +Train: [54] [ 400/6250] eta: 0:14:50 lr: 0.000059 grad: 0.0870 (0.0957) loss: 0.8282 (0.8290) time: 0.1306 data: 0.0389 max mem: 9390 +Train: [54] [ 500/6250] eta: 0:14:13 lr: 0.000059 grad: 0.0853 (0.0946) loss: 0.8257 (0.8285) time: 0.1515 data: 0.0745 max mem: 9390 +Train: [54] [ 600/6250] eta: 0:13:31 lr: 0.000059 grad: 0.0884 (0.0942) loss: 0.8271 (0.8276) time: 0.1301 data: 0.0439 max mem: 9390 +Train: [54] [ 700/6250] eta: 0:13:00 lr: 0.000059 grad: 0.0865 (0.0939) loss: 0.8250 (0.8269) time: 0.1384 data: 0.0539 max mem: 9390 +Train: [54] [ 800/6250] eta: 0:12:36 lr: 0.000059 grad: 0.0957 (0.0941) loss: 0.8159 (0.8260) time: 0.1252 data: 0.0462 max mem: 9390 +Train: [54] [ 900/6250] eta: 0:12:17 lr: 0.000059 grad: 0.0894 (0.0939) loss: 0.8264 (0.8257) time: 0.1351 data: 0.0563 max mem: 9390 +Train: [54] [1000/6250] eta: 0:11:55 lr: 0.000059 grad: 0.0897 (0.0935) loss: 0.8198 (0.8253) time: 0.1102 data: 0.0211 max mem: 9390 +Train: [54] [1100/6250] eta: 0:11:43 lr: 0.000059 grad: 0.0890 (0.0933) loss: 0.8208 (0.8248) time: 0.1673 data: 0.0869 max mem: 9390 +Train: [54] [1200/6250] eta: 0:11:24 lr: 0.000059 grad: 0.0905 (0.0934) loss: 0.8177 (0.8243) time: 0.1434 data: 0.0674 max mem: 9390 +Train: [54] [1300/6250] eta: 0:11:07 lr: 0.000059 grad: 0.0890 (0.0932) loss: 0.8166 (0.8239) time: 0.1184 data: 0.0344 max mem: 9390 +Train: [54] [1400/6250] eta: 0:10:51 lr: 0.000059 grad: 0.0904 (0.0933) loss: 0.8214 (0.8235) time: 0.1419 data: 0.0572 max mem: 9390 +Train: [54] [1500/6250] eta: 0:10:38 lr: 0.000059 grad: 0.0957 (0.0935) loss: 0.8153 (0.8231) time: 0.1130 data: 0.0236 max mem: 9390 +Train: [54] [1600/6250] eta: 0:10:24 lr: 0.000059 grad: 0.0954 (0.0935) loss: 0.8147 (0.8227) time: 0.1299 data: 0.0505 max mem: 9390 +Train: [54] [1700/6250] eta: 0:10:11 lr: 0.000059 grad: 0.0908 (0.0939) loss: 0.8206 (0.8224) time: 0.1460 data: 0.0672 max mem: 9390 +Train: [54] [1800/6250] eta: 0:09:57 lr: 0.000059 grad: 0.0895 (0.0939) loss: 0.8159 (0.8222) time: 0.1382 data: 0.0627 max mem: 9390 +Train: [54] [1900/6250] eta: 0:09:43 lr: 0.000059 grad: 0.0976 (0.0941) loss: 0.8121 (0.8217) time: 0.1506 data: 0.0661 max mem: 9390 +Train: [54] [2000/6250] eta: 0:09:29 lr: 0.000059 grad: 0.0925 (0.0943) loss: 0.8127 (0.8214) time: 0.1152 data: 0.0346 max mem: 9390 +Train: [54] [2100/6250] eta: 0:09:15 lr: 0.000059 grad: 0.0917 (0.0944) loss: 0.8120 (0.8210) time: 0.1265 data: 0.0498 max mem: 9390 +Train: [54] [2200/6250] eta: 0:09:02 lr: 0.000059 grad: 0.0941 (0.0944) loss: 0.8140 (0.8207) time: 0.1275 data: 0.0497 max mem: 9390 +Train: [54] [2300/6250] eta: 0:08:48 lr: 0.000059 grad: 0.0911 (0.0945) loss: 0.8189 (0.8204) time: 0.1333 data: 0.0538 max mem: 9390 +Train: [54] [2400/6250] eta: 0:08:35 lr: 0.000059 grad: 0.0958 (0.0946) loss: 0.8114 (0.8201) time: 0.1278 data: 0.0404 max mem: 9390 +Train: [54] [2500/6250] eta: 0:08:22 lr: 0.000059 grad: 0.0976 (0.0948) loss: 0.8126 (0.8198) time: 0.1363 data: 0.0607 max mem: 9390 +Train: [54] [2600/6250] eta: 0:08:10 lr: 0.000059 grad: 0.0961 (0.0949) loss: 0.8137 (0.8195) time: 0.1590 data: 0.0812 max mem: 9390 +Train: [54] [2700/6250] eta: 0:07:56 lr: 0.000059 grad: 0.0913 (0.0951) loss: 0.8175 (0.8193) time: 0.1391 data: 0.0604 max mem: 9390 +Train: [54] [2800/6250] eta: 0:07:42 lr: 0.000058 grad: 0.0998 (0.0952) loss: 0.8100 (0.8190) time: 0.1168 data: 0.0379 max mem: 9390 +Train: [54] [2900/6250] eta: 0:07:29 lr: 0.000058 grad: 0.0949 (0.0953) loss: 0.8224 (0.8189) time: 0.1287 data: 0.0552 max mem: 9390 +Train: [54] [3000/6250] eta: 0:07:15 lr: 0.000058 grad: 0.0983 (0.0954) loss: 0.8179 (0.8187) time: 0.1148 data: 0.0287 max mem: 9390 +Train: [54] [3100/6250] eta: 0:07:01 lr: 0.000058 grad: 0.1007 (0.0956) loss: 0.8090 (0.8185) time: 0.1338 data: 0.0521 max mem: 9390 +Train: [54] [3200/6250] eta: 0:06:49 lr: 0.000058 grad: 0.0934 (0.0957) loss: 0.8153 (0.8184) time: 0.1538 data: 0.0666 max mem: 9390 +Train: [54] [3300/6250] eta: 0:06:38 lr: 0.000058 grad: 0.0909 (0.0958) loss: 0.8169 (0.8183) time: 0.1544 data: 0.0705 max mem: 9390 +Train: [54] [3400/6250] eta: 0:06:27 lr: 0.000058 grad: 0.1023 (0.0959) loss: 0.8133 (0.8183) time: 0.1971 data: 0.1180 max mem: 9390 +Train: [54] [3500/6250] eta: 0:06:14 lr: 0.000058 grad: 0.0895 (0.0961) loss: 0.8209 (0.8182) time: 0.1449 data: 0.0678 max mem: 9390 +Train: [54] [3600/6250] eta: 0:06:00 lr: 0.000058 grad: 0.0949 (0.0961) loss: 0.8196 (0.8182) time: 0.1414 data: 0.0586 max mem: 9390 +Train: [54] [3700/6250] eta: 0:05:48 lr: 0.000058 grad: 0.1002 (0.0962) loss: 0.8198 (0.8182) time: 0.1986 data: 0.1206 max mem: 9390 +Train: [54] [3800/6250] eta: 0:05:35 lr: 0.000058 grad: 0.0960 (0.0963) loss: 0.8192 (0.8181) time: 0.1314 data: 0.0533 max mem: 9390 +Train: [54] [3900/6250] eta: 0:05:21 lr: 0.000058 grad: 0.0926 (0.0963) loss: 0.8187 (0.8181) time: 0.1365 data: 0.0628 max mem: 9390 +Train: [54] [4000/6250] eta: 0:05:08 lr: 0.000058 grad: 0.0962 (0.0964) loss: 0.8146 (0.8181) time: 0.1493 data: 0.0666 max mem: 9390 +Train: [54] [4100/6250] eta: 0:04:55 lr: 0.000058 grad: 0.0919 (0.0965) loss: 0.8213 (0.8181) time: 0.1469 data: 0.0704 max mem: 9390 +Train: [54] [4200/6250] eta: 0:04:42 lr: 0.000058 grad: 0.0950 (0.0966) loss: 0.8165 (0.8181) time: 0.1454 data: 0.0650 max mem: 9390 +Train: [54] [4300/6250] eta: 0:04:28 lr: 0.000058 grad: 0.0950 (0.0967) loss: 0.8167 (0.8182) time: 0.1450 data: 0.0653 max mem: 9390 +Train: [54] [4400/6250] eta: 0:04:15 lr: 0.000058 grad: 0.0934 (0.0968) loss: 0.8194 (0.8181) time: 0.1581 data: 0.0788 max mem: 9390 +Train: [54] [4500/6250] eta: 0:04:01 lr: 0.000058 grad: 0.0932 (0.0968) loss: 0.8176 (0.8181) time: 0.1261 data: 0.0493 max mem: 9390 +Train: [54] [4600/6250] eta: 0:03:47 lr: 0.000058 grad: 0.0963 (0.0969) loss: 0.8158 (0.8181) time: 0.1404 data: 0.0586 max mem: 9390 +Train: [54] [4700/6250] eta: 0:03:33 lr: 0.000058 grad: 0.0956 (0.0969) loss: 0.8175 (0.8180) time: 0.1171 data: 0.0359 max mem: 9390 +Train: [54] [4800/6250] eta: 0:03:19 lr: 0.000058 grad: 0.0986 (0.0970) loss: 0.8173 (0.8180) time: 0.1226 data: 0.0418 max mem: 9390 +Train: [54] [4900/6250] eta: 0:03:04 lr: 0.000058 grad: 0.0960 (0.0971) loss: 0.8149 (0.8179) time: 0.1322 data: 0.0572 max mem: 9390 +Train: [54] [5000/6250] eta: 0:02:50 lr: 0.000058 grad: 0.0973 (0.0972) loss: 0.8146 (0.8178) time: 0.1263 data: 0.0454 max mem: 9390 +Train: [54] [5100/6250] eta: 0:02:36 lr: 0.000058 grad: 0.0929 (0.0972) loss: 0.8179 (0.8177) time: 0.1116 data: 0.0225 max mem: 9390 +Train: [54] [5200/6250] eta: 0:02:23 lr: 0.000058 grad: 0.0959 (0.0972) loss: 0.8162 (0.8177) time: 0.1068 data: 0.0310 max mem: 9390 +Train: [54] [5300/6250] eta: 0:02:09 lr: 0.000058 grad: 0.0966 (0.0973) loss: 0.8179 (0.8176) time: 0.1337 data: 0.0413 max mem: 9390 +Train: [54] [5400/6250] eta: 0:01:55 lr: 0.000058 grad: 0.1010 (0.0974) loss: 0.8146 (0.8175) time: 0.1328 data: 0.0549 max mem: 9390 +Train: [54] [5500/6250] eta: 0:01:41 lr: 0.000058 grad: 0.0991 (0.0975) loss: 0.8131 (0.8175) time: 0.1237 data: 0.0332 max mem: 9390 +Train: [54] [5600/6250] eta: 0:01:28 lr: 0.000058 grad: 0.0964 (0.0975) loss: 0.8111 (0.8174) time: 0.1295 data: 0.0512 max mem: 9390 +Train: [54] [5700/6250] eta: 0:01:14 lr: 0.000058 grad: 0.0949 (0.0975) loss: 0.8127 (0.8173) time: 0.1235 data: 0.0414 max mem: 9390 +Train: [54] [5800/6250] eta: 0:01:00 lr: 0.000057 grad: 0.0999 (0.0976) loss: 0.8118 (0.8173) time: 0.1328 data: 0.0523 max mem: 9390 +Train: [54] [5900/6250] eta: 0:00:47 lr: 0.000057 grad: 0.0946 (0.0976) loss: 0.8117 (0.8172) time: 0.1336 data: 0.0561 max mem: 9390 +Train: [54] [6000/6250] eta: 0:00:33 lr: 0.000057 grad: 0.0938 (0.0976) loss: 0.8135 (0.8172) time: 0.1251 data: 0.0442 max mem: 9390 +Train: [54] [6100/6250] eta: 0:00:20 lr: 0.000057 grad: 0.0916 (0.0976) loss: 0.8207 (0.8171) time: 0.1388 data: 0.0636 max mem: 9390 +Train: [54] [6200/6250] eta: 0:00:06 lr: 0.000057 grad: 0.0978 (0.0976) loss: 0.8085 (0.8171) time: 0.1297 data: 0.0500 max mem: 9390 +Train: [54] [6249/6250] eta: 0:00:00 lr: 0.000057 grad: 0.0953 (0.0976) loss: 0.8131 (0.8171) time: 0.1151 data: 0.0390 max mem: 9390 +Train: [54] Total time: 0:14:11 (0.1363 s / it) +Averaged stats: lr: 0.000057 grad: 0.0953 (0.0976) loss: 0.8131 (0.8171) +Eval (hcp-train-subset): [54] [ 0/62] eta: 0:03:32 loss: 0.8413 (0.8413) time: 3.4264 data: 3.3485 max mem: 9390 +Eval (hcp-train-subset): [54] [61/62] eta: 0:00:00 loss: 0.8353 (0.8351) time: 0.1144 data: 0.0879 max mem: 9390 +Eval (hcp-train-subset): [54] Total time: 0:00:12 (0.1960 s / it) +Averaged stats (hcp-train-subset): loss: 0.8353 (0.8351) +Making plots (hcp-train-subset): example=48 +Eval (hcp-val): [54] [ 0/62] eta: 0:03:33 loss: 0.8343 (0.8343) time: 3.4510 data: 3.3694 max mem: 9390 +Eval (hcp-val): [54] [61/62] eta: 0:00:00 loss: 0.8329 (0.8343) time: 0.0890 data: 0.0621 max mem: 9390 +Eval (hcp-val): [54] Total time: 0:00:14 (0.2342 s / it) +Averaged stats (hcp-val): loss: 0.8329 (0.8343) +Making plots (hcp-val): example=52 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +Train: [55] [ 0/6250] eta: 9:18:15 lr: 0.000057 grad: 0.1229 (0.1229) loss: 0.8560 (0.8560) time: 5.3593 data: 5.2610 max mem: 9390 +Train: [55] [ 100/6250] eta: 0:19:49 lr: 0.000057 grad: 0.0886 (0.1072) loss: 0.8259 (0.8318) time: 0.1376 data: 0.0499 max mem: 9390 +Train: [55] [ 200/6250] eta: 0:17:08 lr: 0.000057 grad: 0.0972 (0.1048) loss: 0.8144 (0.8259) time: 0.1512 data: 0.0661 max mem: 9390 +Train: [55] [ 300/6250] eta: 0:15:36 lr: 0.000057 grad: 0.0933 (0.1018) loss: 0.8164 (0.8240) time: 0.1303 data: 0.0392 max mem: 9390 +Train: [55] [ 400/6250] eta: 0:14:48 lr: 0.000057 grad: 0.0888 (0.0999) loss: 0.8160 (0.8230) time: 0.1178 data: 0.0300 max mem: 9390 +Train: [55] [ 500/6250] eta: 0:14:12 lr: 0.000057 grad: 0.0936 (0.0993) loss: 0.8081 (0.8206) time: 0.1438 data: 0.0623 max mem: 9390 +Train: [55] [ 600/6250] eta: 0:13:38 lr: 0.000057 grad: 0.0935 (0.0991) loss: 0.8289 (0.8201) time: 0.1065 data: 0.0239 max mem: 9390 +Train: [55] [ 700/6250] eta: 0:13:09 lr: 0.000057 grad: 0.0889 (0.0987) loss: 0.8175 (0.8196) time: 0.1195 data: 0.0381 max mem: 9390 +Train: [55] [ 800/6250] eta: 0:12:42 lr: 0.000057 grad: 0.0972 (0.0987) loss: 0.8106 (0.8189) time: 0.1250 data: 0.0412 max mem: 9390 +Train: [55] [ 900/6250] eta: 0:12:18 lr: 0.000057 grad: 0.0920 (0.0983) loss: 0.8199 (0.8187) time: 0.1188 data: 0.0364 max mem: 9390 +Train: [55] [1000/6250] eta: 0:11:58 lr: 0.000057 grad: 0.0950 (0.0983) loss: 0.8226 (0.8185) time: 0.1158 data: 0.0334 max mem: 9390 +Train: [55] [1100/6250] eta: 0:11:37 lr: 0.000057 grad: 0.0953 (0.0985) loss: 0.8141 (0.8182) time: 0.1194 data: 0.0398 max mem: 9390 +Train: [55] [1200/6250] eta: 0:11:17 lr: 0.000057 grad: 0.0931 (0.0985) loss: 0.8122 (0.8177) time: 0.1165 data: 0.0353 max mem: 9390 +Train: [55] [1300/6250] eta: 0:11:02 lr: 0.000057 grad: 0.0960 (0.0986) loss: 0.8069 (0.8172) time: 0.1243 data: 0.0440 max mem: 9390 +Train: [55] [1400/6250] eta: 0:10:45 lr: 0.000057 grad: 0.0879 (0.0985) loss: 0.8180 (0.8168) time: 0.1223 data: 0.0493 max mem: 9390 +Train: [55] [1500/6250] eta: 0:10:28 lr: 0.000057 grad: 0.0896 (0.0984) loss: 0.8140 (0.8164) time: 0.1188 data: 0.0445 max mem: 9390 +Train: [55] [1600/6250] eta: 0:10:12 lr: 0.000057 grad: 0.0958 (0.0984) loss: 0.8106 (0.8162) time: 0.1118 data: 0.0339 max mem: 9390 +Train: [55] [1700/6250] eta: 0:09:56 lr: 0.000057 grad: 0.0963 (0.0985) loss: 0.8158 (0.8159) time: 0.1197 data: 0.0367 max mem: 9390 +Train: [55] [1800/6250] eta: 0:09:40 lr: 0.000057 grad: 0.0877 (0.0985) loss: 0.8160 (0.8156) time: 0.1209 data: 0.0400 max mem: 9390 +Train: [55] [1900/6250] eta: 0:09:24 lr: 0.000057 grad: 0.0968 (0.0986) loss: 0.8126 (0.8155) time: 0.1281 data: 0.0520 max mem: 9390 +Train: [55] [2000/6250] eta: 0:09:09 lr: 0.000057 grad: 0.0974 (0.0985) loss: 0.8062 (0.8153) time: 0.1200 data: 0.0378 max mem: 9390 +Train: [55] [2100/6250] eta: 0:08:55 lr: 0.000057 grad: 0.0907 (0.0985) loss: 0.8191 (0.8153) time: 0.1200 data: 0.0366 max mem: 9390 +Train: [55] [2200/6250] eta: 0:08:42 lr: 0.000057 grad: 0.0985 (0.0984) loss: 0.8135 (0.8153) time: 0.1291 data: 0.0504 max mem: 9390 +Train: [55] [2300/6250] eta: 0:08:29 lr: 0.000057 grad: 0.0902 (0.0985) loss: 0.8170 (0.8154) time: 0.1456 data: 0.0667 max mem: 9390 +Train: [55] [2400/6250] eta: 0:08:17 lr: 0.000057 grad: 0.0871 (0.0984) loss: 0.8166 (0.8154) time: 0.1524 data: 0.0711 max mem: 9390 +Train: [55] [2500/6250] eta: 0:08:04 lr: 0.000057 grad: 0.1042 (0.0985) loss: 0.8119 (0.8154) time: 0.1115 data: 0.0333 max mem: 9390 +Train: [55] [2600/6250] eta: 0:07:51 lr: 0.000056 grad: 0.0881 (0.0984) loss: 0.8171 (0.8154) time: 0.1381 data: 0.0642 max mem: 9390 +Train: [55] [2700/6250] eta: 0:07:38 lr: 0.000056 grad: 0.0971 (0.0984) loss: 0.8192 (0.8155) time: 0.1467 data: 0.0522 max mem: 9390 +Train: [55] [2800/6250] eta: 0:07:25 lr: 0.000056 grad: 0.0927 (0.0984) loss: 0.8211 (0.8156) time: 0.1325 data: 0.0476 max mem: 9390 +Train: [55] [2900/6250] eta: 0:07:12 lr: 0.000056 grad: 0.0931 (0.0983) loss: 0.8205 (0.8157) time: 0.1249 data: 0.0517 max mem: 9390 +Train: [55] [3000/6250] eta: 0:07:00 lr: 0.000056 grad: 0.0942 (0.0983) loss: 0.8156 (0.8158) time: 0.1256 data: 0.0430 max mem: 9390 +Train: [55] [3100/6250] eta: 0:06:48 lr: 0.000056 grad: 0.0995 (0.0984) loss: 0.8189 (0.8159) time: 0.1576 data: 0.0695 max mem: 9390 +Train: [55] [3200/6250] eta: 0:06:35 lr: 0.000056 grad: 0.0897 (0.0983) loss: 0.8189 (0.8161) time: 0.1270 data: 0.0494 max mem: 9390 +Train: [55] [3300/6250] eta: 0:06:21 lr: 0.000056 grad: 0.0976 (0.0982) loss: 0.8183 (0.8162) time: 0.1253 data: 0.0496 max mem: 9390 +Train: [55] [3400/6250] eta: 0:06:09 lr: 0.000056 grad: 0.0904 (0.0982) loss: 0.8204 (0.8164) time: 0.1339 data: 0.0522 max mem: 9390 +Train: [55] [3500/6250] eta: 0:05:57 lr: 0.000056 grad: 0.0966 (0.0981) loss: 0.8203 (0.8165) time: 0.1271 data: 0.0451 max mem: 9390 +Train: [55] [3600/6250] eta: 0:05:45 lr: 0.000056 grad: 0.0923 (0.0981) loss: 0.8192 (0.8166) time: 0.1554 data: 0.0743 max mem: 9390 +Train: [55] [3700/6250] eta: 0:05:34 lr: 0.000056 grad: 0.0957 (0.0981) loss: 0.8197 (0.8167) time: 0.1456 data: 0.0652 max mem: 9390 +Train: [55] [3800/6250] eta: 0:05:22 lr: 0.000056 grad: 0.0881 (0.0980) loss: 0.8194 (0.8168) time: 0.1442 data: 0.0639 max mem: 9390 +Train: [55] [3900/6250] eta: 0:05:10 lr: 0.000056 grad: 0.0966 (0.0980) loss: 0.8094 (0.8169) time: 0.1664 data: 0.0894 max mem: 9390 +Train: [55] [4000/6250] eta: 0:04:58 lr: 0.000056 grad: 0.0965 (0.0981) loss: 0.8199 (0.8169) time: 0.1642 data: 0.0803 max mem: 9390 +Train: [55] [4100/6250] eta: 0:04:46 lr: 0.000056 grad: 0.0979 (0.0980) loss: 0.8148 (0.8169) time: 0.1344 data: 0.0558 max mem: 9390 +Train: [55] [4200/6250] eta: 0:04:33 lr: 0.000056 grad: 0.0966 (0.0981) loss: 0.8192 (0.8169) time: 0.1376 data: 0.0584 max mem: 9390 +Train: [55] [4300/6250] eta: 0:04:19 lr: 0.000056 grad: 0.0922 (0.0981) loss: 0.8147 (0.8170) time: 0.1441 data: 0.0614 max mem: 9390 +Train: [55] [4400/6250] eta: 0:04:06 lr: 0.000056 grad: 0.0960 (0.0981) loss: 0.8120 (0.8170) time: 0.1386 data: 0.0608 max mem: 9390 +Train: [55] [4500/6250] eta: 0:03:52 lr: 0.000056 grad: 0.0964 (0.0981) loss: 0.8205 (0.8170) time: 0.1255 data: 0.0431 max mem: 9390 +Train: [55] [4600/6250] eta: 0:03:39 lr: 0.000056 grad: 0.0924 (0.0980) loss: 0.8156 (0.8169) time: 0.1317 data: 0.0510 max mem: 9390 +Train: [55] [4700/6250] eta: 0:03:26 lr: 0.000056 grad: 0.0968 (0.0982) loss: 0.8139 (0.8168) time: 0.1312 data: 0.0537 max mem: 9390 +Train: [55] [4800/6250] eta: 0:03:12 lr: 0.000056 grad: 0.0984 (0.0982) loss: 0.8091 (0.8167) time: 0.1292 data: 0.0423 max mem: 9390 +Train: [55] [4900/6250] eta: 0:02:59 lr: 0.000056 grad: 0.0974 (0.0982) loss: 0.8136 (0.8167) time: 0.1329 data: 0.0538 max mem: 9390 +Train: [55] [5000/6250] eta: 0:02:46 lr: 0.000056 grad: 0.0929 (0.0982) loss: 0.8154 (0.8167) time: 0.1264 data: 0.0445 max mem: 9390 +Train: [55] [5100/6250] eta: 0:02:32 lr: 0.000056 grad: 0.0915 (0.0981) loss: 0.8211 (0.8168) time: 0.1318 data: 0.0501 max mem: 9390 +Train: [55] [5200/6250] eta: 0:02:19 lr: 0.000056 grad: 0.0924 (0.0980) loss: 0.8182 (0.8168) time: 0.1415 data: 0.0559 max mem: 9390 +Train: [55] [5300/6250] eta: 0:02:06 lr: 0.000056 grad: 0.0945 (0.0980) loss: 0.8156 (0.8168) time: 0.1200 data: 0.0404 max mem: 9390 +Train: [55] [5400/6250] eta: 0:01:52 lr: 0.000056 grad: 0.0917 (0.0980) loss: 0.8163 (0.8168) time: 0.1461 data: 0.0727 max mem: 9390 +Train: [55] [5500/6250] eta: 0:01:39 lr: 0.000056 grad: 0.0908 (0.0979) loss: 0.8213 (0.8169) time: 0.1325 data: 0.0428 max mem: 9390 +Train: [55] [5600/6250] eta: 0:01:26 lr: 0.000055 grad: 0.0866 (0.0978) loss: 0.8223 (0.8170) time: 0.1399 data: 0.0598 max mem: 9390 +Train: [55] [5700/6250] eta: 0:01:13 lr: 0.000055 grad: 0.0924 (0.0978) loss: 0.8234 (0.8171) time: 0.1524 data: 0.0761 max mem: 9390 +Train: [55] [5800/6250] eta: 0:01:00 lr: 0.000055 grad: 0.0948 (0.0977) loss: 0.8183 (0.8171) time: 0.1290 data: 0.0519 max mem: 9390 +Train: [55] [5900/6250] eta: 0:00:46 lr: 0.000055 grad: 0.0956 (0.0976) loss: 0.8171 (0.8172) time: 0.1306 data: 0.0477 max mem: 9390 +Train: [55] [6000/6250] eta: 0:00:33 lr: 0.000055 grad: 0.0887 (0.0976) loss: 0.8242 (0.8172) time: 0.1735 data: 0.0885 max mem: 9390 +Train: [55] [6100/6250] eta: 0:00:20 lr: 0.000055 grad: 0.0948 (0.0975) loss: 0.8177 (0.8173) time: 0.1243 data: 0.0477 max mem: 9390 +Train: [55] [6200/6250] eta: 0:00:06 lr: 0.000055 grad: 0.0942 (0.0976) loss: 0.8197 (0.8173) time: 0.1381 data: 0.0617 max mem: 9390 +Train: [55] [6249/6250] eta: 0:00:00 lr: 0.000055 grad: 0.0932 (0.0975) loss: 0.8204 (0.8173) time: 0.1633 data: 0.0880 max mem: 9390 +Train: [55] Total time: 0:14:01 (0.1347 s / it) +Averaged stats: lr: 0.000055 grad: 0.0932 (0.0975) loss: 0.8204 (0.8173) +Eval (hcp-train-subset): [55] [ 0/62] eta: 0:03:56 loss: 0.8457 (0.8457) time: 3.8207 data: 3.7315 max mem: 9390 +Eval (hcp-train-subset): [55] [61/62] eta: 0:00:00 loss: 0.8350 (0.8350) time: 0.1189 data: 0.0936 max mem: 9390 +Eval (hcp-train-subset): [55] Total time: 0:00:12 (0.2092 s / it) +Averaged stats (hcp-train-subset): loss: 0.8350 (0.8350) +Eval (hcp-val): [55] [ 0/62] eta: 0:03:23 loss: 0.8357 (0.8357) time: 3.2825 data: 3.2135 max mem: 9390 +Eval (hcp-val): [55] [61/62] eta: 0:00:00 loss: 0.8343 (0.8350) time: 0.1268 data: 0.1015 max mem: 9390 +Eval (hcp-val): [55] Total time: 0:00:12 (0.2011 s / it) +Averaged stats (hcp-val): loss: 0.8343 (0.8350) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +Train: [56] [ 0/6250] eta: 8:45:52 lr: 0.000055 grad: 0.0784 (0.0784) loss: 0.8726 (0.8726) time: 5.0484 data: 4.9379 max mem: 9390 +Train: [56] [ 100/6250] eta: 0:19:25 lr: 0.000055 grad: 0.0956 (0.1084) loss: 0.8255 (0.8303) time: 0.1234 data: 0.0348 max mem: 9390 +Train: [56] [ 200/6250] eta: 0:16:51 lr: 0.000055 grad: 0.0909 (0.1032) loss: 0.8220 (0.8288) time: 0.1561 data: 0.0741 max mem: 9390 +Train: [56] [ 300/6250] eta: 0:15:42 lr: 0.000055 grad: 0.0945 (0.1011) loss: 0.8272 (0.8280) time: 0.1012 data: 0.0110 max mem: 9390 +Train: [56] [ 400/6250] eta: 0:14:46 lr: 0.000055 grad: 0.0923 (0.1010) loss: 0.8202 (0.8261) time: 0.1316 data: 0.0524 max mem: 9390 +Train: [56] [ 500/6250] eta: 0:14:08 lr: 0.000055 grad: 0.0921 (0.0997) loss: 0.8231 (0.8245) time: 0.1404 data: 0.0524 max mem: 9390 +Train: [56] [ 600/6250] eta: 0:13:33 lr: 0.000055 grad: 0.0978 (0.0993) loss: 0.8185 (0.8235) time: 0.1395 data: 0.0493 max mem: 9390 +Train: [56] [ 700/6250] eta: 0:13:04 lr: 0.000055 grad: 0.0885 (0.0987) loss: 0.8250 (0.8230) time: 0.1206 data: 0.0390 max mem: 9390 +Train: [56] [ 800/6250] eta: 0:12:41 lr: 0.000055 grad: 0.0867 (0.0981) loss: 0.8150 (0.8225) time: 0.1211 data: 0.0377 max mem: 9390 +Train: [56] [ 900/6250] eta: 0:12:24 lr: 0.000055 grad: 0.0917 (0.0976) loss: 0.8196 (0.8221) time: 0.1454 data: 0.0706 max mem: 9390 +Train: [56] [1000/6250] eta: 0:12:03 lr: 0.000055 grad: 0.0902 (0.0971) loss: 0.8219 (0.8219) time: 0.1274 data: 0.0459 max mem: 9390 +Train: [56] [1100/6250] eta: 0:11:45 lr: 0.000055 grad: 0.0898 (0.0966) loss: 0.8212 (0.8218) time: 0.1322 data: 0.0532 max mem: 9390 +Train: [56] [1200/6250] eta: 0:11:29 lr: 0.000055 grad: 0.0931 (0.0966) loss: 0.8176 (0.8216) time: 0.1492 data: 0.0617 max mem: 9390 +Train: [56] [1300/6250] eta: 0:11:14 lr: 0.000055 grad: 0.0941 (0.0964) loss: 0.8198 (0.8214) time: 0.1509 data: 0.0596 max mem: 9390 +Train: [56] [1400/6250] eta: 0:11:01 lr: 0.000055 grad: 0.0968 (0.0964) loss: 0.8136 (0.8211) time: 0.1423 data: 0.0701 max mem: 9390 +Train: [56] [1500/6250] eta: 0:10:45 lr: 0.000055 grad: 0.0954 (0.0964) loss: 0.8194 (0.8211) time: 0.1194 data: 0.0412 max mem: 9390 +Train: [56] [1600/6250] eta: 0:10:31 lr: 0.000055 grad: 0.0911 (0.0965) loss: 0.8120 (0.8207) time: 0.1374 data: 0.0549 max mem: 9390 +Train: [56] [1700/6250] eta: 0:10:16 lr: 0.000055 grad: 0.0919 (0.0964) loss: 0.8140 (0.8205) time: 0.1239 data: 0.0436 max mem: 9390 +Train: [56] [1800/6250] eta: 0:10:00 lr: 0.000055 grad: 0.0942 (0.0966) loss: 0.8118 (0.8203) time: 0.1276 data: 0.0430 max mem: 9390 +Train: [56] [1900/6250] eta: 0:09:45 lr: 0.000055 grad: 0.0916 (0.0965) loss: 0.8173 (0.8202) time: 0.1249 data: 0.0436 max mem: 9390 +Train: [56] [2000/6250] eta: 0:09:33 lr: 0.000055 grad: 0.0950 (0.0967) loss: 0.8115 (0.8198) time: 0.1435 data: 0.0652 max mem: 9390 +Train: [56] [2100/6250] eta: 0:09:18 lr: 0.000055 grad: 0.0962 (0.0970) loss: 0.8164 (0.8195) time: 0.1263 data: 0.0524 max mem: 9390 +Train: [56] [2200/6250] eta: 0:09:03 lr: 0.000055 grad: 0.0899 (0.0970) loss: 0.8234 (0.8194) time: 0.1374 data: 0.0548 max mem: 9390 +Train: [56] [2300/6250] eta: 0:08:50 lr: 0.000055 grad: 0.0942 (0.0973) loss: 0.8194 (0.8190) time: 0.1429 data: 0.0639 max mem: 9390 +Train: [56] [2400/6250] eta: 0:08:35 lr: 0.000054 grad: 0.1012 (0.0973) loss: 0.8180 (0.8188) time: 0.1369 data: 0.0583 max mem: 9390 +Train: [56] [2500/6250] eta: 0:08:22 lr: 0.000054 grad: 0.0978 (0.0975) loss: 0.8150 (0.8186) time: 0.1418 data: 0.0651 max mem: 9390 +Train: [56] [2600/6250] eta: 0:08:09 lr: 0.000054 grad: 0.0917 (0.0975) loss: 0.8153 (0.8185) time: 0.1349 data: 0.0525 max mem: 9390 +Train: [56] [2700/6250] eta: 0:07:56 lr: 0.000054 grad: 0.0903 (0.0975) loss: 0.8138 (0.8184) time: 0.1403 data: 0.0657 max mem: 9390 +Train: [56] [2800/6250] eta: 0:07:43 lr: 0.000054 grad: 0.0920 (0.0976) loss: 0.8134 (0.8183) time: 0.1394 data: 0.0596 max mem: 9390 +Train: [56] [2900/6250] eta: 0:07:29 lr: 0.000054 grad: 0.0954 (0.0976) loss: 0.8229 (0.8182) time: 0.1253 data: 0.0493 max mem: 9390 +Train: [56] [3000/6250] eta: 0:07:16 lr: 0.000054 grad: 0.0907 (0.0977) loss: 0.8194 (0.8182) time: 0.1354 data: 0.0559 max mem: 9390 +Train: [56] [3100/6250] eta: 0:07:02 lr: 0.000054 grad: 0.1014 (0.0978) loss: 0.8118 (0.8181) time: 0.1328 data: 0.0461 max mem: 9390 +Train: [56] [3200/6250] eta: 0:06:49 lr: 0.000054 grad: 0.0949 (0.0979) loss: 0.8176 (0.8180) time: 0.1472 data: 0.0691 max mem: 9390 +Train: [56] [3300/6250] eta: 0:06:35 lr: 0.000054 grad: 0.0927 (0.0980) loss: 0.8206 (0.8181) time: 0.1119 data: 0.0381 max mem: 9390 +Train: [56] [3400/6250] eta: 0:06:21 lr: 0.000054 grad: 0.1028 (0.0981) loss: 0.8174 (0.8180) time: 0.1379 data: 0.0608 max mem: 9390 +Train: [56] [3500/6250] eta: 0:06:08 lr: 0.000054 grad: 0.1002 (0.0981) loss: 0.8183 (0.8180) time: 0.1419 data: 0.0557 max mem: 9390 +Train: [56] [3600/6250] eta: 0:05:56 lr: 0.000054 grad: 0.1005 (0.0984) loss: 0.8164 (0.8180) time: 0.2132 data: 0.1395 max mem: 9390 +Train: [56] [3700/6250] eta: 0:05:44 lr: 0.000054 grad: 0.0980 (0.0984) loss: 0.8181 (0.8179) time: 0.1294 data: 0.0552 max mem: 9390 +Train: [56] [3800/6250] eta: 0:05:31 lr: 0.000054 grad: 0.1016 (0.0985) loss: 0.8187 (0.8180) time: 0.1412 data: 0.0585 max mem: 9390 +Train: [56] [3900/6250] eta: 0:05:19 lr: 0.000054 grad: 0.0974 (0.0986) loss: 0.8160 (0.8179) time: 0.1429 data: 0.0636 max mem: 9390 +Train: [56] [4000/6250] eta: 0:05:05 lr: 0.000054 grad: 0.1012 (0.0986) loss: 0.8135 (0.8179) time: 0.1386 data: 0.0583 max mem: 9390 +Train: [56] [4100/6250] eta: 0:04:52 lr: 0.000054 grad: 0.1001 (0.0986) loss: 0.8147 (0.8178) time: 0.1354 data: 0.0505 max mem: 9390 +Train: [56] [4200/6250] eta: 0:04:39 lr: 0.000054 grad: 0.0981 (0.0987) loss: 0.8238 (0.8178) time: 0.1647 data: 0.0884 max mem: 9390 +Train: [56] [4300/6250] eta: 0:04:25 lr: 0.000054 grad: 0.1015 (0.0988) loss: 0.8190 (0.8178) time: 0.1423 data: 0.0571 max mem: 9390 +Train: [56] [4400/6250] eta: 0:04:11 lr: 0.000054 grad: 0.0993 (0.0988) loss: 0.8156 (0.8178) time: 0.1199 data: 0.0447 max mem: 9390 +Train: [56] [4500/6250] eta: 0:03:57 lr: 0.000054 grad: 0.1003 (0.0989) loss: 0.8127 (0.8177) time: 0.0999 data: 0.0198 max mem: 9390 +Train: [56] [4600/6250] eta: 0:03:43 lr: 0.000054 grad: 0.0936 (0.0990) loss: 0.8243 (0.8177) time: 0.1287 data: 0.0520 max mem: 9390 +Train: [56] [4700/6250] eta: 0:03:29 lr: 0.000054 grad: 0.0999 (0.0991) loss: 0.8153 (0.8177) time: 0.1221 data: 0.0472 max mem: 9390 +Train: [56] [4800/6250] eta: 0:03:15 lr: 0.000054 grad: 0.1072 (0.0992) loss: 0.8099 (0.8176) time: 0.1256 data: 0.0408 max mem: 9390 +Train: [56] [4900/6250] eta: 0:03:01 lr: 0.000054 grad: 0.0982 (0.0993) loss: 0.8159 (0.8176) time: 0.1237 data: 0.0481 max mem: 9390 +Train: [56] [5000/6250] eta: 0:02:48 lr: 0.000054 grad: 0.0958 (0.0994) loss: 0.8176 (0.8175) time: 0.1426 data: 0.0667 max mem: 9390 +Train: [56] [5100/6250] eta: 0:02:35 lr: 0.000054 grad: 0.0949 (0.0994) loss: 0.8117 (0.8175) time: 0.1093 data: 0.0394 max mem: 9390 +Train: [56] [5200/6250] eta: 0:02:21 lr: 0.000054 grad: 0.0944 (0.0994) loss: 0.8202 (0.8175) time: 0.1171 data: 0.0316 max mem: 9390 +Train: [56] [5300/6250] eta: 0:02:08 lr: 0.000054 grad: 0.0933 (0.0995) loss: 0.8152 (0.8175) time: 0.1307 data: 0.0334 max mem: 9390 +Train: [56] [5400/6250] eta: 0:01:54 lr: 0.000054 grad: 0.1004 (0.0995) loss: 0.8141 (0.8174) time: 0.1296 data: 0.0519 max mem: 9390 +Train: [56] [5500/6250] eta: 0:01:41 lr: 0.000053 grad: 0.1005 (0.0995) loss: 0.8157 (0.8174) time: 0.1200 data: 0.0447 max mem: 9390 +Train: [56] [5600/6250] eta: 0:01:27 lr: 0.000053 grad: 0.0949 (0.0996) loss: 0.8208 (0.8174) time: 0.1369 data: 0.0618 max mem: 9390 +Train: [56] [5700/6250] eta: 0:01:14 lr: 0.000053 grad: 0.1004 (0.0996) loss: 0.8174 (0.8174) time: 0.1506 data: 0.0778 max mem: 9390 +Train: [56] [5800/6250] eta: 0:01:00 lr: 0.000053 grad: 0.0989 (0.0997) loss: 0.8174 (0.8174) time: 0.1628 data: 0.0856 max mem: 9390 +Train: [56] [5900/6250] eta: 0:00:47 lr: 0.000053 grad: 0.0965 (0.0997) loss: 0.8264 (0.8174) time: 0.1433 data: 0.0630 max mem: 9390 +Train: [56] [6000/6250] eta: 0:00:33 lr: 0.000053 grad: 0.0998 (0.0997) loss: 0.8137 (0.8174) time: 0.1395 data: 0.0639 max mem: 9390 +Train: [56] [6100/6250] eta: 0:00:20 lr: 0.000053 grad: 0.1034 (0.0997) loss: 0.8175 (0.8173) time: 0.1125 data: 0.0362 max mem: 9390 +Train: [56] [6200/6250] eta: 0:00:06 lr: 0.000053 grad: 0.0985 (0.0997) loss: 0.8111 (0.8173) time: 0.1434 data: 0.0696 max mem: 9390 +Train: [56] [6249/6250] eta: 0:00:00 lr: 0.000053 grad: 0.0951 (0.0998) loss: 0.8155 (0.8173) time: 0.1301 data: 0.0587 max mem: 9390 +Train: [56] Total time: 0:14:12 (0.1364 s / it) +Averaged stats: lr: 0.000053 grad: 0.0951 (0.0998) loss: 0.8155 (0.8173) +Eval (hcp-train-subset): [56] [ 0/62] eta: 0:03:13 loss: 0.8475 (0.8475) time: 3.1217 data: 3.0563 max mem: 9390 +Eval (hcp-train-subset): [56] [61/62] eta: 0:00:00 loss: 0.8341 (0.8343) time: 0.1258 data: 0.0994 max mem: 9390 +Eval (hcp-train-subset): [56] Total time: 0:00:12 (0.1975 s / it) +Averaged stats (hcp-train-subset): loss: 0.8341 (0.8343) +Eval (hcp-val): [56] [ 0/62] eta: 0:03:39 loss: 0.8328 (0.8328) time: 3.5473 data: 3.4428 max mem: 9390 +Eval (hcp-val): [56] [61/62] eta: 0:00:00 loss: 0.8322 (0.8344) time: 0.1029 data: 0.0764 max mem: 9390 +Eval (hcp-val): [56] Total time: 0:00:12 (0.2067 s / it) +Averaged stats (hcp-val): loss: 0.8322 (0.8344) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +Train: [57] [ 0/6250] eta: 9:35:24 lr: 0.000053 grad: 0.0798 (0.0798) loss: 0.8532 (0.8532) time: 5.5240 data: 5.4076 max mem: 9390 +Train: [57] [ 100/6250] eta: 0:20:15 lr: 0.000053 grad: 0.0878 (0.1029) loss: 0.8331 (0.8306) time: 0.1258 data: 0.0328 max mem: 9390 +Train: [57] [ 200/6250] eta: 0:17:46 lr: 0.000053 grad: 0.0964 (0.1029) loss: 0.8160 (0.8255) time: 0.1569 data: 0.0643 max mem: 9390 +Train: [57] [ 300/6250] eta: 0:16:10 lr: 0.000053 grad: 0.1005 (0.1036) loss: 0.8189 (0.8222) time: 0.1111 data: 0.0314 max mem: 9390 +Train: [57] [ 400/6250] eta: 0:15:20 lr: 0.000053 grad: 0.1000 (0.1029) loss: 0.8005 (0.8202) time: 0.1370 data: 0.0537 max mem: 9390 +Train: [57] [ 500/6250] eta: 0:14:35 lr: 0.000053 grad: 0.0971 (0.1020) loss: 0.8162 (0.8195) time: 0.1380 data: 0.0515 max mem: 9390 +Train: [57] [ 600/6250] eta: 0:13:53 lr: 0.000053 grad: 0.0905 (0.1011) loss: 0.8175 (0.8189) time: 0.1216 data: 0.0384 max mem: 9390 +Train: [57] [ 700/6250] eta: 0:13:24 lr: 0.000053 grad: 0.0967 (0.1005) loss: 0.8130 (0.8185) time: 0.1354 data: 0.0501 max mem: 9390 +Train: [57] [ 800/6250] eta: 0:12:57 lr: 0.000053 grad: 0.0979 (0.1004) loss: 0.8154 (0.8183) time: 0.1234 data: 0.0438 max mem: 9390 +Train: [57] [ 900/6250] eta: 0:12:32 lr: 0.000053 grad: 0.0928 (0.1003) loss: 0.8197 (0.8181) time: 0.1192 data: 0.0420 max mem: 9390 +Train: [57] [1000/6250] eta: 0:12:09 lr: 0.000053 grad: 0.0878 (0.1001) loss: 0.8221 (0.8181) time: 0.1269 data: 0.0438 max mem: 9390 +Train: [57] [1100/6250] eta: 0:11:46 lr: 0.000053 grad: 0.0945 (0.0998) loss: 0.8166 (0.8181) time: 0.1262 data: 0.0518 max mem: 9390 +Train: [57] [1200/6250] eta: 0:11:30 lr: 0.000053 grad: 0.0865 (0.0994) loss: 0.8213 (0.8180) time: 0.1386 data: 0.0508 max mem: 9390 +Train: [57] [1300/6250] eta: 0:11:15 lr: 0.000053 grad: 0.0923 (0.0989) loss: 0.8157 (0.8181) time: 0.1352 data: 0.0476 max mem: 9390 +Train: [57] [1400/6250] eta: 0:11:00 lr: 0.000053 grad: 0.0917 (0.0989) loss: 0.8215 (0.8181) time: 0.1392 data: 0.0670 max mem: 9390 +Train: [57] [1500/6250] eta: 0:10:43 lr: 0.000053 grad: 0.0958 (0.0987) loss: 0.8135 (0.8181) time: 0.1045 data: 0.0201 max mem: 9390 +Train: [57] [1600/6250] eta: 0:10:29 lr: 0.000053 grad: 0.0955 (0.0985) loss: 0.8181 (0.8183) time: 0.1366 data: 0.0609 max mem: 9390 +Train: [57] [1700/6250] eta: 0:10:18 lr: 0.000053 grad: 0.0969 (0.0984) loss: 0.8110 (0.8183) time: 0.1537 data: 0.0803 max mem: 9390 +Train: [57] [1800/6250] eta: 0:10:04 lr: 0.000053 grad: 0.0976 (0.0984) loss: 0.8206 (0.8182) time: 0.1378 data: 0.0602 max mem: 9390 +Train: [57] [1900/6250] eta: 0:09:48 lr: 0.000053 grad: 0.0930 (0.0985) loss: 0.8181 (0.8181) time: 0.1203 data: 0.0415 max mem: 9390 +Train: [57] [2000/6250] eta: 0:09:33 lr: 0.000053 grad: 0.0957 (0.0986) loss: 0.8178 (0.8180) time: 0.1126 data: 0.0345 max mem: 9390 +Train: [57] [2100/6250] eta: 0:09:19 lr: 0.000053 grad: 0.0975 (0.0987) loss: 0.8188 (0.8179) time: 0.1273 data: 0.0473 max mem: 9390 +Train: [57] [2200/6250] eta: 0:09:05 lr: 0.000053 grad: 0.0988 (0.0991) loss: 0.8161 (0.8177) time: 0.1104 data: 0.0310 max mem: 9390 +Train: [57] [2300/6250] eta: 0:08:51 lr: 0.000052 grad: 0.0969 (0.0991) loss: 0.8226 (0.8177) time: 0.1457 data: 0.0667 max mem: 9390 +Train: [57] [2400/6250] eta: 0:08:38 lr: 0.000052 grad: 0.0930 (0.0992) loss: 0.8173 (0.8178) time: 0.1576 data: 0.0852 max mem: 9390 +Train: [57] [2500/6250] eta: 0:08:25 lr: 0.000052 grad: 0.0936 (0.0992) loss: 0.8135 (0.8178) time: 0.1125 data: 0.0348 max mem: 9390 +Train: [57] [2600/6250] eta: 0:08:12 lr: 0.000052 grad: 0.0971 (0.0992) loss: 0.8161 (0.8176) time: 0.1293 data: 0.0487 max mem: 9390 +Train: [57] [2700/6250] eta: 0:07:58 lr: 0.000052 grad: 0.0942 (0.0992) loss: 0.8152 (0.8175) time: 0.1499 data: 0.0613 max mem: 9390 +Train: [57] [2800/6250] eta: 0:07:46 lr: 0.000052 grad: 0.0995 (0.0993) loss: 0.8158 (0.8173) time: 0.1387 data: 0.0655 max mem: 9390 +Train: [57] [2900/6250] eta: 0:07:32 lr: 0.000052 grad: 0.1020 (0.0995) loss: 0.8090 (0.8171) time: 0.1404 data: 0.0562 max mem: 9390 +Train: [57] [3000/6250] eta: 0:07:18 lr: 0.000052 grad: 0.0958 (0.0995) loss: 0.8203 (0.8170) time: 0.1508 data: 0.0676 max mem: 9390 +Train: [57] [3100/6250] eta: 0:07:05 lr: 0.000052 grad: 0.0932 (0.0995) loss: 0.8149 (0.8169) time: 0.1295 data: 0.0482 max mem: 9390 +Train: [57] [3200/6250] eta: 0:06:51 lr: 0.000052 grad: 0.0902 (0.0996) loss: 0.8197 (0.8169) time: 0.1382 data: 0.0639 max mem: 9390 +Train: [57] [3300/6250] eta: 0:06:38 lr: 0.000052 grad: 0.0991 (0.0998) loss: 0.8183 (0.8167) time: 0.1426 data: 0.0639 max mem: 9390 +Train: [57] [3400/6250] eta: 0:06:24 lr: 0.000052 grad: 0.1009 (0.0999) loss: 0.8235 (0.8166) time: 0.1504 data: 0.0717 max mem: 9390 +Train: [57] [3500/6250] eta: 0:06:11 lr: 0.000052 grad: 0.0973 (0.0999) loss: 0.8143 (0.8166) time: 0.1370 data: 0.0592 max mem: 9390 +Train: [57] [3600/6250] eta: 0:06:00 lr: 0.000052 grad: 0.0963 (0.1000) loss: 0.8195 (0.8165) time: 0.1477 data: 0.0677 max mem: 9390 +Train: [57] [3700/6250] eta: 0:05:47 lr: 0.000052 grad: 0.0912 (0.1000) loss: 0.8194 (0.8165) time: 0.1355 data: 0.0535 max mem: 9390 +Train: [57] [3800/6250] eta: 0:05:34 lr: 0.000052 grad: 0.0983 (0.1000) loss: 0.8153 (0.8165) time: 0.1459 data: 0.0652 max mem: 9390 +Train: [57] [3900/6250] eta: 0:05:22 lr: 0.000052 grad: 0.0956 (0.1000) loss: 0.8170 (0.8165) time: 0.1515 data: 0.0683 max mem: 9390 +Train: [57] [4000/6250] eta: 0:05:09 lr: 0.000052 grad: 0.1019 (0.1000) loss: 0.8135 (0.8165) time: 0.1419 data: 0.0638 max mem: 9390 +Train: [57] [4100/6250] eta: 0:04:55 lr: 0.000052 grad: 0.0988 (0.1000) loss: 0.8174 (0.8164) time: 0.1288 data: 0.0483 max mem: 9390 +Train: [57] [4200/6250] eta: 0:04:41 lr: 0.000052 grad: 0.0973 (0.1000) loss: 0.8157 (0.8164) time: 0.1253 data: 0.0413 max mem: 9390 +Train: [57] [4300/6250] eta: 0:04:27 lr: 0.000052 grad: 0.0985 (0.1000) loss: 0.8153 (0.8164) time: 0.1312 data: 0.0506 max mem: 9390 +Train: [57] [4400/6250] eta: 0:04:13 lr: 0.000052 grad: 0.1100 (0.1000) loss: 0.8060 (0.8164) time: 0.1186 data: 0.0386 max mem: 9390 +Train: [57] [4500/6250] eta: 0:03:59 lr: 0.000052 grad: 0.0963 (0.1000) loss: 0.8226 (0.8163) time: 0.1264 data: 0.0493 max mem: 9390 +Train: [57] [4600/6250] eta: 0:03:45 lr: 0.000052 grad: 0.1000 (0.1000) loss: 0.8177 (0.8163) time: 0.1126 data: 0.0254 max mem: 9390 +Train: [57] [4700/6250] eta: 0:03:31 lr: 0.000052 grad: 0.1008 (0.1000) loss: 0.8140 (0.8163) time: 0.1534 data: 0.0760 max mem: 9390 +Train: [57] [4800/6250] eta: 0:03:17 lr: 0.000052 grad: 0.0994 (0.1001) loss: 0.8161 (0.8162) time: 0.1340 data: 0.0578 max mem: 9390 +Train: [57] [4900/6250] eta: 0:03:03 lr: 0.000052 grad: 0.1000 (0.1001) loss: 0.8156 (0.8162) time: 0.1424 data: 0.0645 max mem: 9390 +Train: [57] [5000/6250] eta: 0:02:50 lr: 0.000052 grad: 0.0971 (0.1002) loss: 0.8109 (0.8162) time: 0.1174 data: 0.0297 max mem: 9390 +Train: [57] [5100/6250] eta: 0:02:36 lr: 0.000052 grad: 0.1036 (0.1002) loss: 0.8101 (0.8162) time: 0.1163 data: 0.0371 max mem: 9390 +Train: [57] [5200/6250] eta: 0:02:22 lr: 0.000052 grad: 0.1038 (0.1003) loss: 0.8164 (0.8161) time: 0.1185 data: 0.0410 max mem: 9390 +Train: [57] [5300/6250] eta: 0:02:09 lr: 0.000052 grad: 0.0963 (0.1002) loss: 0.8213 (0.8161) time: 0.1465 data: 0.0702 max mem: 9390 +Train: [57] [5400/6250] eta: 0:01:55 lr: 0.000051 grad: 0.1020 (0.1003) loss: 0.8146 (0.8161) time: 0.1229 data: 0.0445 max mem: 9390 +Train: [57] [5500/6250] eta: 0:01:41 lr: 0.000051 grad: 0.1045 (0.1003) loss: 0.8148 (0.8161) time: 0.1515 data: 0.0735 max mem: 9390 +Train: [57] [5600/6250] eta: 0:01:28 lr: 0.000051 grad: 0.0948 (0.1003) loss: 0.8179 (0.8161) time: 0.1332 data: 0.0477 max mem: 9390 +Train: [57] [5700/6250] eta: 0:01:14 lr: 0.000051 grad: 0.0933 (0.1002) loss: 0.8157 (0.8161) time: 0.1376 data: 0.0619 max mem: 9390 +Train: [57] [5800/6250] eta: 0:01:01 lr: 0.000051 grad: 0.1015 (0.1002) loss: 0.8115 (0.8161) time: 0.1450 data: 0.0630 max mem: 9390 +Train: [57] [5900/6250] eta: 0:00:47 lr: 0.000051 grad: 0.0889 (0.1002) loss: 0.8199 (0.8162) time: 0.1582 data: 0.0807 max mem: 9390 +Train: [57] [6000/6250] eta: 0:00:33 lr: 0.000051 grad: 0.0938 (0.1002) loss: 0.8183 (0.8162) time: 0.1576 data: 0.0835 max mem: 9390 +Train: [57] [6100/6250] eta: 0:00:20 lr: 0.000051 grad: 0.0965 (0.1002) loss: 0.8214 (0.8163) time: 0.1236 data: 0.0462 max mem: 9390 +Train: [57] [6200/6250] eta: 0:00:06 lr: 0.000051 grad: 0.1002 (0.1002) loss: 0.8102 (0.8163) time: 0.1440 data: 0.0581 max mem: 9390 +Train: [57] [6249/6250] eta: 0:00:00 lr: 0.000051 grad: 0.0992 (0.1003) loss: 0.8175 (0.8163) time: 0.1311 data: 0.0561 max mem: 9390 +Train: [57] Total time: 0:14:14 (0.1367 s / it) +Averaged stats: lr: 0.000051 grad: 0.0992 (0.1003) loss: 0.8175 (0.8163) +Eval (hcp-train-subset): [57] [ 0/62] eta: 0:04:13 loss: 0.8454 (0.8454) time: 4.0870 data: 4.0522 max mem: 9390 +Eval (hcp-train-subset): [57] [61/62] eta: 0:00:00 loss: 0.8338 (0.8338) time: 0.1111 data: 0.0862 max mem: 9390 +Eval (hcp-train-subset): [57] Total time: 0:00:12 (0.1945 s / it) +Averaged stats (hcp-train-subset): loss: 0.8338 (0.8338) +Eval (hcp-val): [57] [ 0/62] eta: 0:05:19 loss: 0.8316 (0.8316) time: 5.1540 data: 5.1255 max mem: 9390 +Eval (hcp-val): [57] [61/62] eta: 0:00:00 loss: 0.8327 (0.8346) time: 0.1149 data: 0.0897 max mem: 9390 +Eval (hcp-val): [57] Total time: 0:00:13 (0.2101 s / it) +Averaged stats (hcp-val): loss: 0.8327 (0.8346) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +Train: [58] [ 0/6250] eta: 6:40:08 lr: 0.000051 grad: 0.0802 (0.0802) loss: 0.8322 (0.8322) time: 3.8413 data: 3.5512 max mem: 9390 +Train: [58] [ 100/6250] eta: 0:20:20 lr: 0.000051 grad: 0.0922 (0.1086) loss: 0.8257 (0.8281) time: 0.1530 data: 0.0522 max mem: 9390 +Train: [58] [ 200/6250] eta: 0:17:29 lr: 0.000051 grad: 0.0918 (0.1024) loss: 0.8257 (0.8250) time: 0.1347 data: 0.0434 max mem: 9390 +Train: [58] [ 300/6250] eta: 0:16:30 lr: 0.000051 grad: 0.0948 (0.0994) loss: 0.8221 (0.8240) time: 0.1603 data: 0.0797 max mem: 9390 +Train: [58] [ 400/6250] eta: 0:15:27 lr: 0.000051 grad: 0.0935 (0.0984) loss: 0.8249 (0.8243) time: 0.1385 data: 0.0570 max mem: 9390 +Train: [58] [ 500/6250] eta: 0:14:47 lr: 0.000051 grad: 0.0979 (0.0984) loss: 0.8147 (0.8238) time: 0.1363 data: 0.0535 max mem: 9390 +Train: [58] [ 600/6250] eta: 0:14:06 lr: 0.000051 grad: 0.1020 (0.0986) loss: 0.8187 (0.8227) time: 0.1293 data: 0.0338 max mem: 9390 +Train: [58] [ 700/6250] eta: 0:13:34 lr: 0.000051 grad: 0.0990 (0.0995) loss: 0.8149 (0.8214) time: 0.1372 data: 0.0571 max mem: 9390 +Train: [58] [ 800/6250] eta: 0:13:08 lr: 0.000051 grad: 0.0969 (0.1000) loss: 0.8141 (0.8206) time: 0.1266 data: 0.0462 max mem: 9390 +Train: [58] [ 900/6250] eta: 0:12:43 lr: 0.000051 grad: 0.0897 (0.0999) loss: 0.8109 (0.8199) time: 0.1496 data: 0.0646 max mem: 9390 +Train: [58] [1000/6250] eta: 0:12:21 lr: 0.000051 grad: 0.0960 (0.0999) loss: 0.8157 (0.8194) time: 0.1283 data: 0.0538 max mem: 9390 +Train: [58] [1100/6250] eta: 0:12:01 lr: 0.000051 grad: 0.0961 (0.1001) loss: 0.8137 (0.8189) time: 0.1198 data: 0.0354 max mem: 9390 +Train: [58] [1200/6250] eta: 0:11:44 lr: 0.000051 grad: 0.0961 (0.0999) loss: 0.8183 (0.8184) time: 0.1284 data: 0.0463 max mem: 9390 +Train: [58] [1300/6250] eta: 0:11:30 lr: 0.000051 grad: 0.1013 (0.1002) loss: 0.8085 (0.8180) time: 0.1317 data: 0.0556 max mem: 9390 +Train: [58] [1400/6250] eta: 0:11:14 lr: 0.000051 grad: 0.0934 (0.1001) loss: 0.8153 (0.8177) time: 0.1398 data: 0.0558 max mem: 9390 +Train: [58] [1500/6250] eta: 0:10:58 lr: 0.000051 grad: 0.0927 (0.1000) loss: 0.8140 (0.8174) time: 0.1129 data: 0.0349 max mem: 9390 +Train: [58] [1600/6250] eta: 0:10:40 lr: 0.000051 grad: 0.0972 (0.1002) loss: 0.8167 (0.8172) time: 0.1273 data: 0.0461 max mem: 9390 +Train: [58] [1700/6250] eta: 0:10:25 lr: 0.000051 grad: 0.1009 (0.1002) loss: 0.8025 (0.8168) time: 0.1311 data: 0.0516 max mem: 9390 +Train: [58] [1800/6250] eta: 0:10:10 lr: 0.000051 grad: 0.0969 (0.1003) loss: 0.8138 (0.8165) time: 0.1387 data: 0.0605 max mem: 9390 +Train: [58] [1900/6250] eta: 0:09:54 lr: 0.000051 grad: 0.1026 (0.1004) loss: 0.8101 (0.8162) time: 0.1375 data: 0.0597 max mem: 9390 +Train: [58] [2000/6250] eta: 0:09:39 lr: 0.000051 grad: 0.1000 (0.1006) loss: 0.8043 (0.8158) time: 0.1562 data: 0.0711 max mem: 9390 +Train: [58] [2100/6250] eta: 0:09:24 lr: 0.000051 grad: 0.1020 (0.1007) loss: 0.8122 (0.8155) time: 0.1209 data: 0.0487 max mem: 9390 +Train: [58] [2200/6250] eta: 0:09:09 lr: 0.000050 grad: 0.1034 (0.1009) loss: 0.8083 (0.8153) time: 0.1080 data: 0.0318 max mem: 9390 +Train: [58] [2300/6250] eta: 0:08:55 lr: 0.000050 grad: 0.1005 (0.1011) loss: 0.8127 (0.8151) time: 0.1307 data: 0.0459 max mem: 9390 +Train: [58] [2400/6250] eta: 0:08:43 lr: 0.000050 grad: 0.1041 (0.1012) loss: 0.8122 (0.8149) time: 0.1482 data: 0.0723 max mem: 9390 +Train: [58] [2500/6250] eta: 0:08:28 lr: 0.000050 grad: 0.1013 (0.1014) loss: 0.8131 (0.8146) time: 0.1328 data: 0.0500 max mem: 9390 +Train: [58] [2600/6250] eta: 0:08:14 lr: 0.000050 grad: 0.1007 (0.1015) loss: 0.8102 (0.8144) time: 0.1362 data: 0.0560 max mem: 9390 +Train: [58] [2700/6250] eta: 0:08:02 lr: 0.000050 grad: 0.0953 (0.1015) loss: 0.8192 (0.8143) time: 0.1378 data: 0.0607 max mem: 9390 +Train: [58] [2800/6250] eta: 0:07:49 lr: 0.000050 grad: 0.0978 (0.1016) loss: 0.8092 (0.8141) time: 0.1399 data: 0.0621 max mem: 9390 +Train: [58] [2900/6250] eta: 0:07:35 lr: 0.000050 grad: 0.1039 (0.1016) loss: 0.8091 (0.8141) time: 0.1427 data: 0.0634 max mem: 9390 +Train: [58] [3000/6250] eta: 0:07:21 lr: 0.000050 grad: 0.1012 (0.1018) loss: 0.8115 (0.8140) time: 0.1194 data: 0.0409 max mem: 9390 +Train: [58] [3100/6250] eta: 0:07:08 lr: 0.000050 grad: 0.1003 (0.1018) loss: 0.8105 (0.8140) time: 0.1454 data: 0.0573 max mem: 9390 +Train: [58] [3200/6250] eta: 0:06:54 lr: 0.000050 grad: 0.0981 (0.1018) loss: 0.8185 (0.8140) time: 0.1418 data: 0.0619 max mem: 9390 +Train: [58] [3300/6250] eta: 0:06:40 lr: 0.000050 grad: 0.0900 (0.1017) loss: 0.8223 (0.8141) time: 0.1192 data: 0.0394 max mem: 9390 +Train: [58] [3400/6250] eta: 0:06:26 lr: 0.000050 grad: 0.1002 (0.1017) loss: 0.8173 (0.8142) time: 0.1275 data: 0.0502 max mem: 9390 +Train: [58] [3500/6250] eta: 0:06:15 lr: 0.000050 grad: 0.1036 (0.1017) loss: 0.8148 (0.8143) time: 0.1352 data: 0.0603 max mem: 9390 +Train: [58] [3600/6250] eta: 0:06:02 lr: 0.000050 grad: 0.1003 (0.1019) loss: 0.8195 (0.8144) time: 0.1530 data: 0.0770 max mem: 9390 +Train: [58] [3700/6250] eta: 0:05:50 lr: 0.000050 grad: 0.1032 (0.1020) loss: 0.8090 (0.8144) time: 0.1732 data: 0.1006 max mem: 9390 +Train: [58] [3800/6250] eta: 0:05:37 lr: 0.000050 grad: 0.1008 (0.1021) loss: 0.8175 (0.8145) time: 0.1292 data: 0.0495 max mem: 9390 +Train: [58] [3900/6250] eta: 0:05:25 lr: 0.000050 grad: 0.0950 (0.1021) loss: 0.8177 (0.8146) time: 0.1726 data: 0.0908 max mem: 9390 +Train: [58] [4000/6250] eta: 0:05:11 lr: 0.000050 grad: 0.1028 (0.1022) loss: 0.8179 (0.8146) time: 0.1494 data: 0.0777 max mem: 9390 +Train: [58] [4100/6250] eta: 0:04:57 lr: 0.000050 grad: 0.0990 (0.1023) loss: 0.8157 (0.8147) time: 0.1371 data: 0.0565 max mem: 9390 +Train: [58] [4200/6250] eta: 0:04:43 lr: 0.000050 grad: 0.0987 (0.1022) loss: 0.8166 (0.8147) time: 0.1388 data: 0.0598 max mem: 9390 +Train: [58] [4300/6250] eta: 0:04:29 lr: 0.000050 grad: 0.1013 (0.1022) loss: 0.8115 (0.8147) time: 0.1217 data: 0.0399 max mem: 9390 +Train: [58] [4400/6250] eta: 0:04:15 lr: 0.000050 grad: 0.1013 (0.1022) loss: 0.8195 (0.8148) time: 0.1258 data: 0.0364 max mem: 9390 +Train: [58] [4500/6250] eta: 0:04:01 lr: 0.000050 grad: 0.0961 (0.1021) loss: 0.8227 (0.8148) time: 0.1184 data: 0.0366 max mem: 9390 +Train: [58] [4600/6250] eta: 0:03:47 lr: 0.000050 grad: 0.0991 (0.1021) loss: 0.8178 (0.8149) time: 0.1268 data: 0.0482 max mem: 9390 +Train: [58] [4700/6250] eta: 0:03:33 lr: 0.000050 grad: 0.0968 (0.1021) loss: 0.8187 (0.8151) time: 0.1342 data: 0.0429 max mem: 9390 +Train: [58] [4800/6250] eta: 0:03:19 lr: 0.000050 grad: 0.0932 (0.1021) loss: 0.8241 (0.8151) time: 0.1358 data: 0.0593 max mem: 9390 +Train: [58] [4900/6250] eta: 0:03:05 lr: 0.000050 grad: 0.0914 (0.1021) loss: 0.8200 (0.8152) time: 0.1384 data: 0.0536 max mem: 9390 +Train: [58] [5000/6250] eta: 0:02:52 lr: 0.000050 grad: 0.0979 (0.1021) loss: 0.8175 (0.8152) time: 0.1360 data: 0.0446 max mem: 9390 +Train: [58] [5100/6250] eta: 0:02:38 lr: 0.000050 grad: 0.0975 (0.1021) loss: 0.8229 (0.8153) time: 0.1367 data: 0.0585 max mem: 9390 +Train: [58] [5200/6250] eta: 0:02:24 lr: 0.000050 grad: 0.0935 (0.1021) loss: 0.8196 (0.8153) time: 0.1408 data: 0.0619 max mem: 9390 +Train: [58] [5300/6250] eta: 0:02:10 lr: 0.000049 grad: 0.0945 (0.1020) loss: 0.8157 (0.8153) time: 0.1374 data: 0.0628 max mem: 9390 +Train: [58] [5400/6250] eta: 0:01:57 lr: 0.000049 grad: 0.0985 (0.1020) loss: 0.8148 (0.8154) time: 0.1476 data: 0.0582 max mem: 9390 +Train: [58] [5500/6250] eta: 0:01:43 lr: 0.000049 grad: 0.1072 (0.1020) loss: 0.8107 (0.8154) time: 0.1397 data: 0.0567 max mem: 9390 +Train: [58] [5600/6250] eta: 0:01:29 lr: 0.000049 grad: 0.0938 (0.1020) loss: 0.8185 (0.8154) time: 0.1323 data: 0.0540 max mem: 9390 +Train: [58] [5700/6250] eta: 0:01:15 lr: 0.000049 grad: 0.0958 (0.1020) loss: 0.8136 (0.8154) time: 0.1393 data: 0.0581 max mem: 9390 +Train: [58] [5800/6250] eta: 0:01:02 lr: 0.000049 grad: 0.1048 (0.1021) loss: 0.8173 (0.8154) time: 0.1366 data: 0.0514 max mem: 9390 +Train: [58] [5900/6250] eta: 0:00:48 lr: 0.000049 grad: 0.0997 (0.1022) loss: 0.8190 (0.8154) time: 0.1678 data: 0.0902 max mem: 9390 +Train: [58] [6000/6250] eta: 0:00:34 lr: 0.000049 grad: 0.1001 (0.1022) loss: 0.8117 (0.8154) time: 0.1462 data: 0.0690 max mem: 9390 +Train: [58] [6100/6250] eta: 0:00:20 lr: 0.000049 grad: 0.1046 (0.1023) loss: 0.8137 (0.8153) time: 0.1438 data: 0.0660 max mem: 9390 +Train: [58] [6200/6250] eta: 0:00:06 lr: 0.000049 grad: 0.0992 (0.1023) loss: 0.8158 (0.8154) time: 0.1278 data: 0.0463 max mem: 9390 +Train: [58] [6249/6250] eta: 0:00:00 lr: 0.000049 grad: 0.1001 (0.1023) loss: 0.8126 (0.8153) time: 0.1319 data: 0.0495 max mem: 9390 +Train: [58] Total time: 0:14:29 (0.1391 s / it) +Averaged stats: lr: 0.000049 grad: 0.1001 (0.1023) loss: 0.8126 (0.8153) +Eval (hcp-train-subset): [58] [ 0/62] eta: 0:04:12 loss: 0.8464 (0.8464) time: 4.0728 data: 4.0404 max mem: 9390 +Eval (hcp-train-subset): [58] [61/62] eta: 0:00:00 loss: 0.8345 (0.8351) time: 0.1042 data: 0.0764 max mem: 9390 +Eval (hcp-train-subset): [58] Total time: 0:00:12 (0.2068 s / it) +Averaged stats (hcp-train-subset): loss: 0.8345 (0.8351) +Eval (hcp-val): [58] [ 0/62] eta: 0:04:06 loss: 0.8336 (0.8336) time: 3.9712 data: 3.8873 max mem: 9390 +Eval (hcp-val): [58] [61/62] eta: 0:00:00 loss: 0.8333 (0.8342) time: 0.1296 data: 0.1030 max mem: 9390 +Eval (hcp-val): [58] Total time: 0:00:12 (0.2030 s / it) +Averaged stats (hcp-val): loss: 0.8333 (0.8342) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +Train: [59] [ 0/6250] eta: 9:54:23 lr: 0.000049 grad: 0.1611 (0.1611) loss: 0.8510 (0.8510) time: 5.7061 data: 5.6066 max mem: 9390 +Train: [59] [ 100/6250] eta: 0:20:51 lr: 0.000049 grad: 0.1179 (0.1157) loss: 0.8131 (0.8346) time: 0.1493 data: 0.0598 max mem: 9390 +Train: [59] [ 200/6250] eta: 0:17:45 lr: 0.000049 grad: 0.1055 (0.1166) loss: 0.8106 (0.8250) time: 0.1280 data: 0.0460 max mem: 9390 +Train: [59] [ 300/6250] eta: 0:16:09 lr: 0.000049 grad: 0.1011 (0.1151) loss: 0.8067 (0.8197) time: 0.1269 data: 0.0452 max mem: 9390 +Train: [59] [ 400/6250] eta: 0:15:05 lr: 0.000049 grad: 0.1012 (0.1129) loss: 0.8159 (0.8178) time: 0.1168 data: 0.0370 max mem: 9390 +Train: [59] [ 500/6250] eta: 0:14:30 lr: 0.000049 grad: 0.1048 (0.1118) loss: 0.8085 (0.8162) time: 0.1144 data: 0.0245 max mem: 9390 +Train: [59] [ 600/6250] eta: 0:13:52 lr: 0.000049 grad: 0.1029 (0.1110) loss: 0.8199 (0.8159) time: 0.1359 data: 0.0464 max mem: 9390 +Train: [59] [ 700/6250] eta: 0:13:17 lr: 0.000049 grad: 0.0999 (0.1107) loss: 0.8173 (0.8152) time: 0.1045 data: 0.0220 max mem: 9390 +Train: [59] [ 800/6250] eta: 0:12:56 lr: 0.000049 grad: 0.0946 (0.1096) loss: 0.8081 (0.8148) time: 0.1248 data: 0.0364 max mem: 9390 +Train: [59] [ 900/6250] eta: 0:12:34 lr: 0.000049 grad: 0.0965 (0.1084) loss: 0.8129 (0.8147) time: 0.1245 data: 0.0413 max mem: 9390 +Train: [59] [1000/6250] eta: 0:12:17 lr: 0.000049 grad: 0.0975 (0.1076) loss: 0.8147 (0.8147) time: 0.1257 data: 0.0487 max mem: 9390 +Train: [59] [1100/6250] eta: 0:11:56 lr: 0.000049 grad: 0.0988 (0.1069) loss: 0.8206 (0.8148) time: 0.1301 data: 0.0514 max mem: 9390 +Train: [59] [1200/6250] eta: 0:11:36 lr: 0.000049 grad: 0.0938 (0.1061) loss: 0.8169 (0.8150) time: 0.1142 data: 0.0367 max mem: 9390 +Train: [59] [1300/6250] eta: 0:11:21 lr: 0.000049 grad: 0.1019 (0.1054) loss: 0.8120 (0.8150) time: 0.0896 data: 0.0099 max mem: 9390 +Train: [59] [1400/6250] eta: 0:11:04 lr: 0.000049 grad: 0.0916 (0.1048) loss: 0.8197 (0.8151) time: 0.1276 data: 0.0481 max mem: 9390 +Train: [59] [1500/6250] eta: 0:10:47 lr: 0.000049 grad: 0.1027 (0.1045) loss: 0.8155 (0.8151) time: 0.1227 data: 0.0450 max mem: 9390 +Train: [59] [1600/6250] eta: 0:10:30 lr: 0.000049 grad: 0.0931 (0.1043) loss: 0.8139 (0.8153) time: 0.1146 data: 0.0370 max mem: 9390 +Train: [59] [1700/6250] eta: 0:10:15 lr: 0.000049 grad: 0.1048 (0.1041) loss: 0.8094 (0.8153) time: 0.1487 data: 0.0667 max mem: 9390 +Train: [59] [1800/6250] eta: 0:09:58 lr: 0.000049 grad: 0.0974 (0.1040) loss: 0.8202 (0.8151) time: 0.1407 data: 0.0636 max mem: 9390 +Train: [59] [1900/6250] eta: 0:09:43 lr: 0.000049 grad: 0.1020 (0.1039) loss: 0.8109 (0.8150) time: 0.1311 data: 0.0508 max mem: 9390 +Train: [59] [2000/6250] eta: 0:09:28 lr: 0.000049 grad: 0.0984 (0.1039) loss: 0.8197 (0.8150) time: 0.1395 data: 0.0658 max mem: 9390 +Train: [59] [2100/6250] eta: 0:09:14 lr: 0.000048 grad: 0.1088 (0.1039) loss: 0.8084 (0.8150) time: 0.1354 data: 0.0505 max mem: 9390 +Train: [59] [2200/6250] eta: 0:08:59 lr: 0.000048 grad: 0.0966 (0.1039) loss: 0.8186 (0.8150) time: 0.1398 data: 0.0647 max mem: 9390 +Train: [59] [2300/6250] eta: 0:08:46 lr: 0.000048 grad: 0.0990 (0.1038) loss: 0.8146 (0.8149) time: 0.1303 data: 0.0555 max mem: 9390 +Train: [59] [2400/6250] eta: 0:08:33 lr: 0.000048 grad: 0.0991 (0.1037) loss: 0.8212 (0.8150) time: 0.1298 data: 0.0538 max mem: 9390 +Train: [59] [2500/6250] eta: 0:08:21 lr: 0.000048 grad: 0.0981 (0.1036) loss: 0.8089 (0.8150) time: 0.2032 data: 0.1250 max mem: 9390 +Train: [59] [2600/6250] eta: 0:08:08 lr: 0.000048 grad: 0.0986 (0.1037) loss: 0.8099 (0.8149) time: 0.1527 data: 0.0734 max mem: 9390 +Train: [59] [2700/6250] eta: 0:07:56 lr: 0.000048 grad: 0.1023 (0.1037) loss: 0.8157 (0.8148) time: 0.1301 data: 0.0501 max mem: 9390 +Train: [59] [2800/6250] eta: 0:07:42 lr: 0.000048 grad: 0.1104 (0.1037) loss: 0.8141 (0.8147) time: 0.1460 data: 0.0677 max mem: 9390 +Train: [59] [2900/6250] eta: 0:07:28 lr: 0.000048 grad: 0.0996 (0.1037) loss: 0.8127 (0.8146) time: 0.1341 data: 0.0560 max mem: 9390 +Train: [59] [3000/6250] eta: 0:07:15 lr: 0.000048 grad: 0.0976 (0.1037) loss: 0.8166 (0.8146) time: 0.1562 data: 0.0704 max mem: 9390 +Train: [59] [3100/6250] eta: 0:07:01 lr: 0.000048 grad: 0.0994 (0.1037) loss: 0.8083 (0.8145) time: 0.1315 data: 0.0552 max mem: 9390 +Train: [59] [3200/6250] eta: 0:06:48 lr: 0.000048 grad: 0.0957 (0.1037) loss: 0.8183 (0.8145) time: 0.1187 data: 0.0373 max mem: 9390 +Train: [59] [3300/6250] eta: 0:06:34 lr: 0.000048 grad: 0.1044 (0.1038) loss: 0.8113 (0.8144) time: 0.1302 data: 0.0556 max mem: 9390 +Train: [59] [3400/6250] eta: 0:06:21 lr: 0.000048 grad: 0.0992 (0.1038) loss: 0.8150 (0.8144) time: 0.1407 data: 0.0629 max mem: 9390 +Train: [59] [3500/6250] eta: 0:06:11 lr: 0.000048 grad: 0.0960 (0.1036) loss: 0.8182 (0.8144) time: 0.1629 data: 0.0786 max mem: 9390 +Train: [59] [3600/6250] eta: 0:05:58 lr: 0.000048 grad: 0.1059 (0.1036) loss: 0.8126 (0.8144) time: 0.1535 data: 0.0747 max mem: 9390 +Train: [59] [3700/6250] eta: 0:05:46 lr: 0.000048 grad: 0.0987 (0.1036) loss: 0.8093 (0.8143) time: 0.1607 data: 0.0716 max mem: 9390 +Train: [59] [3800/6250] eta: 0:05:34 lr: 0.000048 grad: 0.1010 (0.1036) loss: 0.8194 (0.8142) time: 0.1654 data: 0.0892 max mem: 9390 +Train: [59] [3900/6250] eta: 0:05:21 lr: 0.000048 grad: 0.1031 (0.1036) loss: 0.8073 (0.8142) time: 0.1393 data: 0.0574 max mem: 9390 +Train: [59] [4000/6250] eta: 0:05:07 lr: 0.000048 grad: 0.0972 (0.1037) loss: 0.8174 (0.8141) time: 0.1315 data: 0.0528 max mem: 9390 +Train: [59] [4100/6250] eta: 0:04:54 lr: 0.000048 grad: 0.0977 (0.1037) loss: 0.8095 (0.8141) time: 0.1339 data: 0.0474 max mem: 9390 +Train: [59] [4200/6250] eta: 0:04:40 lr: 0.000048 grad: 0.1004 (0.1038) loss: 0.8142 (0.8140) time: 0.1262 data: 0.0434 max mem: 9390 +Train: [59] [4300/6250] eta: 0:04:26 lr: 0.000048 grad: 0.1048 (0.1039) loss: 0.8100 (0.8139) time: 0.1244 data: 0.0387 max mem: 9390 +Train: [59] [4400/6250] eta: 0:04:12 lr: 0.000048 grad: 0.1069 (0.1039) loss: 0.8097 (0.8138) time: 0.1085 data: 0.0265 max mem: 9390 +Train: [59] [4500/6250] eta: 0:03:57 lr: 0.000048 grad: 0.0993 (0.1039) loss: 0.8038 (0.8137) time: 0.1235 data: 0.0408 max mem: 9390 +Train: [59] [4600/6250] eta: 0:03:44 lr: 0.000048 grad: 0.1048 (0.1040) loss: 0.8108 (0.8136) time: 0.0925 data: 0.0155 max mem: 9390 +Train: [59] [4700/6250] eta: 0:03:30 lr: 0.000048 grad: 0.1070 (0.1040) loss: 0.8101 (0.8136) time: 0.1282 data: 0.0454 max mem: 9390 +Train: [59] [4800/6250] eta: 0:03:16 lr: 0.000048 grad: 0.1029 (0.1041) loss: 0.8072 (0.8136) time: 0.1291 data: 0.0501 max mem: 9390 +Train: [59] [4900/6250] eta: 0:03:03 lr: 0.000048 grad: 0.1002 (0.1041) loss: 0.8110 (0.8136) time: 0.1891 data: 0.1121 max mem: 9390 +Train: [59] [5000/6250] eta: 0:02:49 lr: 0.000048 grad: 0.1039 (0.1042) loss: 0.8089 (0.8136) time: 0.1199 data: 0.0420 max mem: 9390 +Train: [59] [5100/6250] eta: 0:02:35 lr: 0.000048 grad: 0.1004 (0.1042) loss: 0.8173 (0.8136) time: 0.1365 data: 0.0595 max mem: 9390 +Train: [59] [5200/6250] eta: 0:02:22 lr: 0.000047 grad: 0.1011 (0.1042) loss: 0.8145 (0.8136) time: 0.1645 data: 0.0723 max mem: 9390 +Train: [59] [5300/6250] eta: 0:02:09 lr: 0.000047 grad: 0.1043 (0.1042) loss: 0.8182 (0.8136) time: 0.1275 data: 0.0477 max mem: 9390 +Train: [59] [5400/6250] eta: 0:01:55 lr: 0.000047 grad: 0.1047 (0.1042) loss: 0.8133 (0.8136) time: 0.1452 data: 0.0581 max mem: 9390 +Train: [59] [5500/6250] eta: 0:01:42 lr: 0.000047 grad: 0.1054 (0.1043) loss: 0.8173 (0.8136) time: 0.1348 data: 0.0566 max mem: 9390 +Train: [59] [5600/6250] eta: 0:01:28 lr: 0.000047 grad: 0.1015 (0.1043) loss: 0.8103 (0.8136) time: 0.1445 data: 0.0601 max mem: 9390 +Train: [59] [5700/6250] eta: 0:01:15 lr: 0.000047 grad: 0.1015 (0.1043) loss: 0.8081 (0.8136) time: 0.2163 data: 0.1252 max mem: 9390 +Train: [59] [5800/6250] eta: 0:01:01 lr: 0.000047 grad: 0.1076 (0.1044) loss: 0.8044 (0.8136) time: 0.0939 data: 0.0195 max mem: 9390 +Train: [59] [5900/6250] eta: 0:00:47 lr: 0.000047 grad: 0.1066 (0.1044) loss: 0.8021 (0.8135) time: 0.1549 data: 0.0734 max mem: 9390 +Train: [59] [6000/6250] eta: 0:00:34 lr: 0.000047 grad: 0.0996 (0.1045) loss: 0.8123 (0.8135) time: 0.1322 data: 0.0569 max mem: 9390 +Train: [59] [6100/6250] eta: 0:00:20 lr: 0.000047 grad: 0.1037 (0.1045) loss: 0.8151 (0.8135) time: 0.0983 data: 0.0214 max mem: 9390 +Train: [59] [6200/6250] eta: 0:00:06 lr: 0.000047 grad: 0.1075 (0.1045) loss: 0.8106 (0.8135) time: 0.1433 data: 0.0474 max mem: 9390 +Train: [59] [6249/6250] eta: 0:00:00 lr: 0.000047 grad: 0.0995 (0.1046) loss: 0.8123 (0.8135) time: 0.1407 data: 0.0538 max mem: 9390 +Train: [59] Total time: 0:14:23 (0.1381 s / it) +Averaged stats: lr: 0.000047 grad: 0.0995 (0.1046) loss: 0.8123 (0.8135) +Eval (hcp-train-subset): [59] [ 0/62] eta: 0:04:16 loss: 0.8390 (0.8390) time: 4.1314 data: 4.0935 max mem: 9390 +Eval (hcp-train-subset): [59] [61/62] eta: 0:00:00 loss: 0.8315 (0.8320) time: 0.1090 data: 0.0843 max mem: 9390 +Eval (hcp-train-subset): [59] Total time: 0:00:12 (0.1975 s / it) +Averaged stats (hcp-train-subset): loss: 0.8315 (0.8320) +Making plots (hcp-train-subset): example=26 +Eval (hcp-val): [59] [ 0/62] eta: 0:03:16 loss: 0.8318 (0.8318) time: 3.1767 data: 3.1059 max mem: 9390 +Eval (hcp-val): [59] [61/62] eta: 0:00:00 loss: 0.8327 (0.8347) time: 0.1203 data: 0.0937 max mem: 9390 +Eval (hcp-val): [59] Total time: 0:00:11 (0.1922 s / it) +Averaged stats (hcp-val): loss: 0.8327 (0.8347) +Making plots (hcp-val): example=50 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +Train: [60] [ 0/6250] eta: 10:53:31 lr: 0.000047 grad: 0.2768 (0.2768) loss: 0.8494 (0.8494) time: 6.2738 data: 6.1716 max mem: 9390 +Train: [60] [ 100/6250] eta: 0:20:25 lr: 0.000047 grad: 0.0986 (0.1049) loss: 0.8330 (0.8384) time: 0.1416 data: 0.0481 max mem: 9390 +Train: [60] [ 200/6250] eta: 0:17:42 lr: 0.000047 grad: 0.0928 (0.1055) loss: 0.8295 (0.8324) time: 0.1555 data: 0.0632 max mem: 9390 +Train: [60] [ 300/6250] eta: 0:16:11 lr: 0.000047 grad: 0.1044 (0.1050) loss: 0.8165 (0.8272) time: 0.1272 data: 0.0407 max mem: 9390 +Train: [60] [ 400/6250] eta: 0:15:19 lr: 0.000047 grad: 0.0944 (0.1047) loss: 0.8221 (0.8250) time: 0.1404 data: 0.0532 max mem: 9390 +Train: [60] [ 500/6250] eta: 0:14:33 lr: 0.000047 grad: 0.1000 (0.1039) loss: 0.8171 (0.8243) time: 0.1263 data: 0.0454 max mem: 9390 +Train: [60] [ 600/6250] eta: 0:13:58 lr: 0.000047 grad: 0.0908 (0.1032) loss: 0.8231 (0.8243) time: 0.1198 data: 0.0374 max mem: 9390 +Train: [60] [ 700/6250] eta: 0:13:26 lr: 0.000047 grad: 0.0979 (0.1025) loss: 0.8260 (0.8244) time: 0.1139 data: 0.0331 max mem: 9390 +Train: [60] [ 800/6250] eta: 0:13:01 lr: 0.000047 grad: 0.0970 (0.1021) loss: 0.8248 (0.8241) time: 0.1259 data: 0.0353 max mem: 9390 +Train: [60] [ 900/6250] eta: 0:12:39 lr: 0.000047 grad: 0.0963 (0.1019) loss: 0.8235 (0.8237) time: 0.1434 data: 0.0676 max mem: 9390 +Train: [60] [1000/6250] eta: 0:12:18 lr: 0.000047 grad: 0.0979 (0.1018) loss: 0.8138 (0.8233) time: 0.1316 data: 0.0522 max mem: 9390 +Train: [60] [1100/6250] eta: 0:11:59 lr: 0.000047 grad: 0.0926 (0.1018) loss: 0.8217 (0.8229) time: 0.1415 data: 0.0609 max mem: 9390 +Train: [60] [1200/6250] eta: 0:11:43 lr: 0.000047 grad: 0.1005 (0.1018) loss: 0.8195 (0.8223) time: 0.1427 data: 0.0582 max mem: 9390 +Train: [60] [1300/6250] eta: 0:11:25 lr: 0.000047 grad: 0.0990 (0.1017) loss: 0.8134 (0.8221) time: 0.1303 data: 0.0501 max mem: 9390 +Train: [60] [1400/6250] eta: 0:11:07 lr: 0.000047 grad: 0.1026 (0.1018) loss: 0.8135 (0.8218) time: 0.1354 data: 0.0599 max mem: 9390 +Train: [60] [1500/6250] eta: 0:10:48 lr: 0.000047 grad: 0.1020 (0.1018) loss: 0.8207 (0.8214) time: 0.1089 data: 0.0303 max mem: 9390 +Train: [60] [1600/6250] eta: 0:10:32 lr: 0.000047 grad: 0.0992 (0.1019) loss: 0.8158 (0.8211) time: 0.1322 data: 0.0562 max mem: 9390 +Train: [60] [1700/6250] eta: 0:10:17 lr: 0.000047 grad: 0.0991 (0.1019) loss: 0.8145 (0.8209) time: 0.1343 data: 0.0474 max mem: 9390 +Train: [60] [1800/6250] eta: 0:10:02 lr: 0.000047 grad: 0.1021 (0.1020) loss: 0.8158 (0.8206) time: 0.1264 data: 0.0457 max mem: 9390 +Train: [60] [1900/6250] eta: 0:09:46 lr: 0.000047 grad: 0.0954 (0.1019) loss: 0.8222 (0.8205) time: 0.1164 data: 0.0350 max mem: 9390 +Train: [60] [2000/6250] eta: 0:09:30 lr: 0.000047 grad: 0.1025 (0.1019) loss: 0.8137 (0.8203) time: 0.1269 data: 0.0510 max mem: 9390 +Train: [60] [2100/6250] eta: 0:09:15 lr: 0.000046 grad: 0.0989 (0.1021) loss: 0.8210 (0.8201) time: 0.1279 data: 0.0540 max mem: 9390 +Train: [60] [2200/6250] eta: 0:09:01 lr: 0.000046 grad: 0.0994 (0.1020) loss: 0.8160 (0.8200) time: 0.1331 data: 0.0584 max mem: 9390 +Train: [60] [2300/6250] eta: 0:08:48 lr: 0.000046 grad: 0.1045 (0.1021) loss: 0.8158 (0.8199) time: 0.1648 data: 0.0853 max mem: 9390 +Train: [60] [2400/6250] eta: 0:08:34 lr: 0.000046 grad: 0.1007 (0.1021) loss: 0.8170 (0.8197) time: 0.1355 data: 0.0623 max mem: 9390 +Train: [60] [2500/6250] eta: 0:08:21 lr: 0.000046 grad: 0.1019 (0.1020) loss: 0.8137 (0.8196) time: 0.1353 data: 0.0598 max mem: 9390 +Train: [60] [2600/6250] eta: 0:08:08 lr: 0.000046 grad: 0.0964 (0.1021) loss: 0.8114 (0.8193) time: 0.1423 data: 0.0601 max mem: 9390 +Train: [60] [2700/6250] eta: 0:07:55 lr: 0.000046 grad: 0.1006 (0.1022) loss: 0.8160 (0.8192) time: 0.1228 data: 0.0448 max mem: 9390 +Train: [60] [2800/6250] eta: 0:07:42 lr: 0.000046 grad: 0.1007 (0.1023) loss: 0.8092 (0.8190) time: 0.1577 data: 0.0790 max mem: 9390 +Train: [60] [2900/6250] eta: 0:07:28 lr: 0.000046 grad: 0.0984 (0.1025) loss: 0.8145 (0.8188) time: 0.1471 data: 0.0713 max mem: 9390 +Train: [60] [3000/6250] eta: 0:07:15 lr: 0.000046 grad: 0.1004 (0.1026) loss: 0.8176 (0.8187) time: 0.1365 data: 0.0600 max mem: 9390 +Train: [60] [3100/6250] eta: 0:07:02 lr: 0.000046 grad: 0.1032 (0.1028) loss: 0.8078 (0.8185) time: 0.1443 data: 0.0637 max mem: 9390 +Train: [60] [3200/6250] eta: 0:06:48 lr: 0.000046 grad: 0.0996 (0.1029) loss: 0.8145 (0.8183) time: 0.1248 data: 0.0466 max mem: 9390 +Train: [60] [3300/6250] eta: 0:06:35 lr: 0.000046 grad: 0.1017 (0.1030) loss: 0.8185 (0.8181) time: 0.1281 data: 0.0479 max mem: 9390 +Train: [60] [3400/6250] eta: 0:06:21 lr: 0.000046 grad: 0.0998 (0.1030) loss: 0.8152 (0.8180) time: 0.1503 data: 0.0655 max mem: 9390 +Train: [60] [3500/6250] eta: 0:06:10 lr: 0.000046 grad: 0.1054 (0.1031) loss: 0.8105 (0.8179) time: 0.1521 data: 0.0742 max mem: 9390 +Train: [60] [3600/6250] eta: 0:05:58 lr: 0.000046 grad: 0.1054 (0.1033) loss: 0.8144 (0.8177) time: 0.1651 data: 0.0868 max mem: 9390 +Train: [60] [3700/6250] eta: 0:05:46 lr: 0.000046 grad: 0.1093 (0.1034) loss: 0.8128 (0.8176) time: 0.1529 data: 0.0679 max mem: 9390 +Train: [60] [3800/6250] eta: 0:05:34 lr: 0.000046 grad: 0.1068 (0.1035) loss: 0.8136 (0.8174) time: 0.1645 data: 0.0869 max mem: 9390 +Train: [60] [3900/6250] eta: 0:05:21 lr: 0.000046 grad: 0.1064 (0.1037) loss: 0.8113 (0.8173) time: 0.1400 data: 0.0605 max mem: 9390 +Train: [60] [4000/6250] eta: 0:05:07 lr: 0.000046 grad: 0.1060 (0.1037) loss: 0.8065 (0.8172) time: 0.1286 data: 0.0481 max mem: 9390 +Train: [60] [4100/6250] eta: 0:04:54 lr: 0.000046 grad: 0.0984 (0.1038) loss: 0.8170 (0.8171) time: 0.1524 data: 0.0694 max mem: 9390 +Train: [60] [4200/6250] eta: 0:04:40 lr: 0.000046 grad: 0.1055 (0.1038) loss: 0.8087 (0.8170) time: 0.1302 data: 0.0335 max mem: 9390 +Train: [60] [4300/6250] eta: 0:04:26 lr: 0.000046 grad: 0.1061 (0.1039) loss: 0.8132 (0.8169) time: 0.1128 data: 0.0365 max mem: 9390 +Train: [60] [4400/6250] eta: 0:04:12 lr: 0.000046 grad: 0.1046 (0.1040) loss: 0.8124 (0.8168) time: 0.1197 data: 0.0421 max mem: 9390 +Train: [60] [4500/6250] eta: 0:03:58 lr: 0.000046 grad: 0.1086 (0.1041) loss: 0.8124 (0.8166) time: 0.1308 data: 0.0487 max mem: 9390 +Train: [60] [4600/6250] eta: 0:03:44 lr: 0.000046 grad: 0.0973 (0.1041) loss: 0.8168 (0.8165) time: 0.1366 data: 0.0583 max mem: 9390 +Train: [60] [4700/6250] eta: 0:03:30 lr: 0.000046 grad: 0.1131 (0.1042) loss: 0.8061 (0.8164) time: 0.1259 data: 0.0494 max mem: 9390 +Train: [60] [4800/6250] eta: 0:03:17 lr: 0.000046 grad: 0.1062 (0.1043) loss: 0.8192 (0.8164) time: 0.1239 data: 0.0459 max mem: 9390 +Train: [60] [4900/6250] eta: 0:03:03 lr: 0.000046 grad: 0.1043 (0.1044) loss: 0.8160 (0.8163) time: 0.1161 data: 0.0359 max mem: 9390 +Train: [60] [5000/6250] eta: 0:02:49 lr: 0.000046 grad: 0.0980 (0.1046) loss: 0.8168 (0.8162) time: 0.1401 data: 0.0671 max mem: 9390 +Train: [60] [5100/6250] eta: 0:02:36 lr: 0.000046 grad: 0.1083 (0.1047) loss: 0.8140 (0.8161) time: 0.1302 data: 0.0541 max mem: 9390 +Train: [60] [5200/6250] eta: 0:02:22 lr: 0.000045 grad: 0.1038 (0.1048) loss: 0.8153 (0.8159) time: 0.1210 data: 0.0453 max mem: 9390 +Train: [60] [5300/6250] eta: 0:02:08 lr: 0.000045 grad: 0.1082 (0.1049) loss: 0.8174 (0.8158) time: 0.1374 data: 0.0608 max mem: 9390 +Train: [60] [5400/6250] eta: 0:01:55 lr: 0.000045 grad: 0.1029 (0.1050) loss: 0.8117 (0.8157) time: 0.1343 data: 0.0580 max mem: 9390 +Train: [60] [5500/6250] eta: 0:01:41 lr: 0.000045 grad: 0.1059 (0.1050) loss: 0.8152 (0.8156) time: 0.1545 data: 0.0821 max mem: 9390 +Train: [60] [5600/6250] eta: 0:01:28 lr: 0.000045 grad: 0.1009 (0.1051) loss: 0.8100 (0.8155) time: 0.1489 data: 0.0760 max mem: 9390 +Train: [60] [5700/6250] eta: 0:01:14 lr: 0.000045 grad: 0.1128 (0.1052) loss: 0.8108 (0.8154) time: 0.1389 data: 0.0579 max mem: 9390 +Train: [60] [5800/6250] eta: 0:01:01 lr: 0.000045 grad: 0.1087 (0.1052) loss: 0.8158 (0.8153) time: 0.1344 data: 0.0539 max mem: 9390 +Train: [60] [5900/6250] eta: 0:00:47 lr: 0.000045 grad: 0.1114 (0.1052) loss: 0.8085 (0.8152) time: 0.1305 data: 0.0457 max mem: 9390 +Train: [60] [6000/6250] eta: 0:00:33 lr: 0.000045 grad: 0.1133 (0.1053) loss: 0.8059 (0.8152) time: 0.1115 data: 0.0299 max mem: 9390 +Train: [60] [6100/6250] eta: 0:00:20 lr: 0.000045 grad: 0.1075 (0.1054) loss: 0.8148 (0.8151) time: 0.1338 data: 0.0479 max mem: 9390 +Train: [60] [6200/6250] eta: 0:00:06 lr: 0.000045 grad: 0.1040 (0.1054) loss: 0.8105 (0.8151) time: 0.1320 data: 0.0544 max mem: 9390 +Train: [60] [6249/6250] eta: 0:00:00 lr: 0.000045 grad: 0.1009 (0.1054) loss: 0.8107 (0.8151) time: 0.1487 data: 0.0728 max mem: 9390 +Train: [60] Total time: 0:14:16 (0.1370 s / it) +Averaged stats: lr: 0.000045 grad: 0.1009 (0.1054) loss: 0.8107 (0.8151) +Eval (hcp-train-subset): [60] [ 0/62] eta: 0:05:18 loss: 0.8415 (0.8415) time: 5.1345 data: 5.1029 max mem: 9390 +Eval (hcp-train-subset): [60] [61/62] eta: 0:00:00 loss: 0.8266 (0.8300) time: 0.1341 data: 0.1089 max mem: 9390 +Eval (hcp-train-subset): [60] Total time: 0:00:12 (0.2094 s / it) +Averaged stats (hcp-train-subset): loss: 0.8266 (0.8300) +Eval (hcp-val): [60] [ 0/62] eta: 0:04:37 loss: 0.8315 (0.8315) time: 4.4800 data: 4.4508 max mem: 9390 +Eval (hcp-val): [60] [61/62] eta: 0:00:00 loss: 0.8311 (0.8337) time: 0.1126 data: 0.0860 max mem: 9390 +Eval (hcp-val): [60] Total time: 0:00:12 (0.1975 s / it) +Averaged stats (hcp-val): loss: 0.8311 (0.8337) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +Train: [61] [ 0/6250] eta: 9:33:08 lr: 0.000045 grad: 0.1805 (0.1805) loss: 0.8340 (0.8340) time: 5.5021 data: 5.3656 max mem: 9390 +Train: [61] [ 100/6250] eta: 0:21:09 lr: 0.000045 grad: 0.1081 (0.1183) loss: 0.8138 (0.8237) time: 0.1736 data: 0.0788 max mem: 9390 +Train: [61] [ 200/6250] eta: 0:17:50 lr: 0.000045 grad: 0.0956 (0.1125) loss: 0.8231 (0.8206) time: 0.1534 data: 0.0643 max mem: 9390 +Train: [61] [ 300/6250] eta: 0:16:13 lr: 0.000045 grad: 0.0952 (0.1093) loss: 0.8217 (0.8196) time: 0.1459 data: 0.0619 max mem: 9390 +Train: [61] [ 400/6250] eta: 0:15:20 lr: 0.000045 grad: 0.1005 (0.1063) loss: 0.8117 (0.8190) time: 0.1090 data: 0.0152 max mem: 9390 +Train: [61] [ 500/6250] eta: 0:14:31 lr: 0.000045 grad: 0.0943 (0.1048) loss: 0.8168 (0.8186) time: 0.1181 data: 0.0369 max mem: 9390 +Train: [61] [ 600/6250] eta: 0:13:57 lr: 0.000045 grad: 0.0933 (0.1036) loss: 0.8186 (0.8183) time: 0.1237 data: 0.0418 max mem: 9390 +Train: [61] [ 700/6250] eta: 0:13:27 lr: 0.000045 grad: 0.0973 (0.1028) loss: 0.8256 (0.8183) time: 0.1536 data: 0.0706 max mem: 9390 +Train: [61] [ 800/6250] eta: 0:12:57 lr: 0.000045 grad: 0.0990 (0.1025) loss: 0.8192 (0.8182) time: 0.1322 data: 0.0533 max mem: 9390 +Train: [61] [ 900/6250] eta: 0:12:32 lr: 0.000045 grad: 0.0968 (0.1026) loss: 0.8156 (0.8180) time: 0.1019 data: 0.0213 max mem: 9390 +Train: [61] [1000/6250] eta: 0:12:11 lr: 0.000045 grad: 0.1077 (0.1026) loss: 0.8174 (0.8178) time: 0.1217 data: 0.0430 max mem: 9390 +Train: [61] [1100/6250] eta: 0:11:51 lr: 0.000045 grad: 0.1013 (0.1026) loss: 0.8110 (0.8174) time: 0.1100 data: 0.0297 max mem: 9390 +Train: [61] [1200/6250] eta: 0:11:33 lr: 0.000045 grad: 0.0953 (0.1029) loss: 0.8114 (0.8171) time: 0.1266 data: 0.0501 max mem: 9390 +Train: [61] [1300/6250] eta: 0:11:15 lr: 0.000045 grad: 0.0996 (0.1030) loss: 0.8100 (0.8165) time: 0.1360 data: 0.0550 max mem: 9390 +Train: [61] [1400/6250] eta: 0:10:56 lr: 0.000045 grad: 0.0985 (0.1030) loss: 0.8109 (0.8162) time: 0.1287 data: 0.0518 max mem: 9390 +Train: [61] [1500/6250] eta: 0:10:42 lr: 0.000045 grad: 0.1093 (0.1033) loss: 0.8091 (0.8160) time: 0.1483 data: 0.0676 max mem: 9390 +Train: [61] [1600/6250] eta: 0:10:29 lr: 0.000045 grad: 0.1067 (0.1035) loss: 0.8120 (0.8157) time: 0.1363 data: 0.0618 max mem: 9390 +Train: [61] [1700/6250] eta: 0:10:13 lr: 0.000045 grad: 0.1015 (0.1035) loss: 0.8187 (0.8157) time: 0.1242 data: 0.0462 max mem: 9390 +Train: [61] [1800/6250] eta: 0:09:59 lr: 0.000045 grad: 0.0997 (0.1036) loss: 0.8105 (0.8154) time: 0.1394 data: 0.0581 max mem: 9390 +Train: [61] [1900/6250] eta: 0:09:43 lr: 0.000045 grad: 0.1016 (0.1038) loss: 0.8154 (0.8153) time: 0.1308 data: 0.0516 max mem: 9390 +Train: [61] [2000/6250] eta: 0:09:28 lr: 0.000045 grad: 0.0980 (0.1038) loss: 0.8140 (0.8153) time: 0.1096 data: 0.0275 max mem: 9390 +Train: [61] [2100/6250] eta: 0:09:15 lr: 0.000044 grad: 0.1020 (0.1038) loss: 0.8110 (0.8151) time: 0.1409 data: 0.0669 max mem: 9390 +Train: [61] [2200/6250] eta: 0:09:01 lr: 0.000044 grad: 0.1021 (0.1038) loss: 0.8170 (0.8150) time: 0.1494 data: 0.0738 max mem: 9390 +Train: [61] [2300/6250] eta: 0:08:49 lr: 0.000044 grad: 0.1043 (0.1040) loss: 0.8123 (0.8148) time: 0.1248 data: 0.0490 max mem: 9390 +Train: [61] [2400/6250] eta: 0:08:37 lr: 0.000044 grad: 0.1091 (0.1041) loss: 0.8155 (0.8148) time: 0.1434 data: 0.0672 max mem: 9390 +Train: [61] [2500/6250] eta: 0:08:25 lr: 0.000044 grad: 0.1013 (0.1042) loss: 0.8183 (0.8148) time: 0.1518 data: 0.0759 max mem: 9390 +Train: [61] [2600/6250] eta: 0:08:11 lr: 0.000044 grad: 0.1017 (0.1042) loss: 0.8201 (0.8148) time: 0.1523 data: 0.0698 max mem: 9390 +Train: [61] [2700/6250] eta: 0:07:59 lr: 0.000044 grad: 0.0977 (0.1042) loss: 0.8220 (0.8149) time: 0.1225 data: 0.0373 max mem: 9390 +Train: [61] [2800/6250] eta: 0:07:47 lr: 0.000044 grad: 0.1044 (0.1042) loss: 0.8112 (0.8148) time: 0.1256 data: 0.0445 max mem: 9390 +Train: [61] [2900/6250] eta: 0:07:34 lr: 0.000044 grad: 0.1025 (0.1041) loss: 0.8144 (0.8149) time: 0.1266 data: 0.0506 max mem: 9390 +Train: [61] [3000/6250] eta: 0:07:20 lr: 0.000044 grad: 0.1050 (0.1042) loss: 0.8159 (0.8148) time: 0.1441 data: 0.0616 max mem: 9390 +Train: [61] [3100/6250] eta: 0:07:07 lr: 0.000044 grad: 0.0994 (0.1042) loss: 0.8138 (0.8148) time: 0.1444 data: 0.0709 max mem: 9390 +Train: [61] [3200/6250] eta: 0:06:55 lr: 0.000044 grad: 0.0984 (0.1042) loss: 0.8206 (0.8148) time: 0.1443 data: 0.0642 max mem: 9390 +Train: [61] [3300/6250] eta: 0:06:41 lr: 0.000044 grad: 0.0974 (0.1041) loss: 0.8154 (0.8149) time: 0.1328 data: 0.0617 max mem: 9390 +Train: [61] [3400/6250] eta: 0:06:29 lr: 0.000044 grad: 0.1028 (0.1041) loss: 0.8135 (0.8149) time: 0.1857 data: 0.1045 max mem: 9390 +Train: [61] [3500/6250] eta: 0:06:16 lr: 0.000044 grad: 0.1001 (0.1041) loss: 0.8132 (0.8149) time: 0.1427 data: 0.0597 max mem: 9390 +Train: [61] [3600/6250] eta: 0:06:03 lr: 0.000044 grad: 0.1020 (0.1042) loss: 0.8184 (0.8149) time: 0.1567 data: 0.0794 max mem: 9390 +Train: [61] [3700/6250] eta: 0:05:50 lr: 0.000044 grad: 0.1049 (0.1042) loss: 0.8074 (0.8148) time: 0.1382 data: 0.0607 max mem: 9390 +Train: [61] [3800/6250] eta: 0:05:38 lr: 0.000044 grad: 0.1076 (0.1042) loss: 0.8071 (0.8148) time: 0.1948 data: 0.1176 max mem: 9390 +Train: [61] [3900/6250] eta: 0:05:25 lr: 0.000044 grad: 0.1056 (0.1042) loss: 0.8157 (0.8148) time: 0.1643 data: 0.0842 max mem: 9390 +Train: [61] [4000/6250] eta: 0:05:11 lr: 0.000044 grad: 0.1036 (0.1042) loss: 0.8104 (0.8148) time: 0.1514 data: 0.0722 max mem: 9390 +Train: [61] [4100/6250] eta: 0:04:57 lr: 0.000044 grad: 0.1074 (0.1044) loss: 0.8128 (0.8147) time: 0.1385 data: 0.0577 max mem: 9390 +Train: [61] [4200/6250] eta: 0:04:43 lr: 0.000044 grad: 0.1131 (0.1045) loss: 0.8091 (0.8147) time: 0.1357 data: 0.0567 max mem: 9390 +Train: [61] [4300/6250] eta: 0:04:29 lr: 0.000044 grad: 0.1032 (0.1045) loss: 0.8129 (0.8147) time: 0.1350 data: 0.0518 max mem: 9390 +Train: [61] [4400/6250] eta: 0:04:15 lr: 0.000044 grad: 0.0982 (0.1045) loss: 0.8120 (0.8148) time: 0.1253 data: 0.0454 max mem: 9390 +Train: [61] [4500/6250] eta: 0:04:01 lr: 0.000044 grad: 0.0976 (0.1045) loss: 0.8211 (0.8148) time: 0.1432 data: 0.0657 max mem: 9390 +Train: [61] [4600/6250] eta: 0:03:48 lr: 0.000044 grad: 0.1079 (0.1045) loss: 0.8176 (0.8149) time: 0.1570 data: 0.0716 max mem: 9390 +Train: [61] [4700/6250] eta: 0:03:34 lr: 0.000044 grad: 0.0980 (0.1046) loss: 0.8130 (0.8149) time: 0.1432 data: 0.0621 max mem: 9390 +Train: [61] [4800/6250] eta: 0:03:20 lr: 0.000044 grad: 0.1006 (0.1046) loss: 0.8175 (0.8149) time: 0.1511 data: 0.0664 max mem: 9390 +Train: [61] [4900/6250] eta: 0:03:07 lr: 0.000044 grad: 0.1050 (0.1047) loss: 0.8163 (0.8150) time: 0.1593 data: 0.0688 max mem: 9390 +Train: [61] [5000/6250] eta: 0:02:53 lr: 0.000044 grad: 0.1039 (0.1047) loss: 0.8170 (0.8150) time: 0.1479 data: 0.0748 max mem: 9390 +Train: [61] [5100/6250] eta: 0:02:39 lr: 0.000044 grad: 0.1036 (0.1048) loss: 0.8152 (0.8150) time: 0.1398 data: 0.0665 max mem: 9390 +Train: [61] [5200/6250] eta: 0:02:25 lr: 0.000044 grad: 0.1070 (0.1049) loss: 0.8207 (0.8150) time: 0.1344 data: 0.0553 max mem: 9390 +Train: [61] [5300/6250] eta: 0:02:11 lr: 0.000043 grad: 0.1095 (0.1050) loss: 0.8128 (0.8150) time: 0.1361 data: 0.0545 max mem: 9390 +Train: [61] [5400/6250] eta: 0:01:58 lr: 0.000043 grad: 0.1048 (0.1050) loss: 0.8177 (0.8151) time: 0.1437 data: 0.0676 max mem: 9390 +Train: [61] [5500/6250] eta: 0:01:44 lr: 0.000043 grad: 0.1041 (0.1050) loss: 0.8131 (0.8151) time: 0.1490 data: 0.0708 max mem: 9390 +Train: [61] [5600/6250] eta: 0:01:30 lr: 0.000043 grad: 0.0998 (0.1051) loss: 0.8195 (0.8152) time: 0.1451 data: 0.0670 max mem: 9390 +Train: [61] [5700/6250] eta: 0:01:16 lr: 0.000043 grad: 0.0972 (0.1051) loss: 0.8145 (0.8152) time: 0.1658 data: 0.0844 max mem: 9390 +Train: [61] [5800/6250] eta: 0:01:02 lr: 0.000043 grad: 0.1014 (0.1051) loss: 0.8175 (0.8152) time: 0.1468 data: 0.0663 max mem: 9390 +Train: [61] [5900/6250] eta: 0:00:48 lr: 0.000043 grad: 0.0996 (0.1051) loss: 0.8191 (0.8153) time: 0.1383 data: 0.0637 max mem: 9390 +Train: [61] [6000/6250] eta: 0:00:34 lr: 0.000043 grad: 0.1027 (0.1052) loss: 0.8126 (0.8153) time: 0.1349 data: 0.0587 max mem: 9390 +Train: [61] [6100/6250] eta: 0:00:20 lr: 0.000043 grad: 0.1016 (0.1053) loss: 0.8129 (0.8153) time: 0.1512 data: 0.0666 max mem: 9390 +Train: [61] [6200/6250] eta: 0:00:06 lr: 0.000043 grad: 0.1050 (0.1053) loss: 0.8163 (0.8153) time: 0.1386 data: 0.0625 max mem: 9390 +Train: [61] [6249/6250] eta: 0:00:00 lr: 0.000043 grad: 0.1126 (0.1054) loss: 0.8086 (0.8152) time: 0.1146 data: 0.0363 max mem: 9390 +Train: [61] Total time: 0:14:37 (0.1403 s / it) +Averaged stats: lr: 0.000043 grad: 0.1126 (0.1054) loss: 0.8086 (0.8152) +Eval (hcp-train-subset): [61] [ 0/62] eta: 0:04:35 loss: 0.8442 (0.8442) time: 4.4398 data: 4.4108 max mem: 9390 +Eval (hcp-train-subset): [61] [61/62] eta: 0:00:00 loss: 0.8293 (0.8311) time: 0.1126 data: 0.0866 max mem: 9390 +Eval (hcp-train-subset): [61] Total time: 0:00:12 (0.1980 s / it) +Averaged stats (hcp-train-subset): loss: 0.8293 (0.8311) +Eval (hcp-val): [61] [ 0/62] eta: 0:03:12 loss: 0.8328 (0.8328) time: 3.1126 data: 3.0480 max mem: 9390 +Eval (hcp-val): [61] [61/62] eta: 0:00:00 loss: 0.8336 (0.8343) time: 0.1354 data: 0.1088 max mem: 9390 +Eval (hcp-val): [61] Total time: 0:00:13 (0.2115 s / it) +Averaged stats (hcp-val): loss: 0.8336 (0.8343) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +Train: [62] [ 0/6250] eta: 9:03:33 lr: 0.000043 grad: 0.1678 (0.1678) loss: 0.8203 (0.8203) time: 5.2182 data: 5.0673 max mem: 9390 +Train: [62] [ 100/6250] eta: 0:20:30 lr: 0.000043 grad: 0.1129 (0.1127) loss: 0.8176 (0.8347) time: 0.1576 data: 0.0667 max mem: 9390 +Train: [62] [ 200/6250] eta: 0:17:53 lr: 0.000043 grad: 0.0937 (0.1088) loss: 0.8225 (0.8290) time: 0.1660 data: 0.0750 max mem: 9390 +Train: [62] [ 300/6250] eta: 0:16:22 lr: 0.000043 grad: 0.0954 (0.1062) loss: 0.8193 (0.8262) time: 0.1390 data: 0.0561 max mem: 9390 +Train: [62] [ 400/6250] eta: 0:15:19 lr: 0.000043 grad: 0.1047 (0.1047) loss: 0.8171 (0.8249) time: 0.1243 data: 0.0463 max mem: 9390 +Train: [62] [ 500/6250] eta: 0:14:35 lr: 0.000043 grad: 0.1102 (0.1050) loss: 0.8103 (0.8228) time: 0.1390 data: 0.0582 max mem: 9390 +Train: [62] [ 600/6250] eta: 0:13:59 lr: 0.000043 grad: 0.1020 (0.1048) loss: 0.8176 (0.8217) time: 0.1224 data: 0.0416 max mem: 9390 +Train: [62] [ 700/6250] eta: 0:13:29 lr: 0.000043 grad: 0.0983 (0.1045) loss: 0.8140 (0.8209) time: 0.1301 data: 0.0490 max mem: 9390 +Train: [62] [ 800/6250] eta: 0:13:02 lr: 0.000043 grad: 0.0961 (0.1041) loss: 0.8205 (0.8207) time: 0.1183 data: 0.0350 max mem: 9390 +Train: [62] [ 900/6250] eta: 0:12:41 lr: 0.000043 grad: 0.0966 (0.1039) loss: 0.8202 (0.8205) time: 0.1331 data: 0.0517 max mem: 9390 +Train: [62] [1000/6250] eta: 0:12:19 lr: 0.000043 grad: 0.1012 (0.1037) loss: 0.8203 (0.8203) time: 0.1287 data: 0.0539 max mem: 9390 +Train: [62] [1100/6250] eta: 0:12:00 lr: 0.000043 grad: 0.0990 (0.1037) loss: 0.8162 (0.8202) time: 0.1225 data: 0.0417 max mem: 9390 +Train: [62] [1200/6250] eta: 0:11:42 lr: 0.000043 grad: 0.1018 (0.1036) loss: 0.8193 (0.8202) time: 0.1476 data: 0.0704 max mem: 9390 +Train: [62] [1300/6250] eta: 0:11:20 lr: 0.000043 grad: 0.0944 (0.1034) loss: 0.8165 (0.8200) time: 0.1200 data: 0.0411 max mem: 9390 +Train: [62] [1400/6250] eta: 0:11:03 lr: 0.000043 grad: 0.1005 (0.1033) loss: 0.8175 (0.8199) time: 0.1293 data: 0.0549 max mem: 9390 +Train: [62] [1500/6250] eta: 0:10:45 lr: 0.000043 grad: 0.0959 (0.1030) loss: 0.8177 (0.8199) time: 0.1228 data: 0.0405 max mem: 9390 +Train: [62] [1600/6250] eta: 0:10:30 lr: 0.000043 grad: 0.0957 (0.1028) loss: 0.8238 (0.8199) time: 0.1125 data: 0.0203 max mem: 9390 +Train: [62] [1700/6250] eta: 0:10:13 lr: 0.000043 grad: 0.0932 (0.1028) loss: 0.8239 (0.8199) time: 0.1259 data: 0.0445 max mem: 9390 +Train: [62] [1800/6250] eta: 0:09:59 lr: 0.000043 grad: 0.0969 (0.1027) loss: 0.8184 (0.8198) time: 0.1318 data: 0.0497 max mem: 9390 +Train: [62] [1900/6250] eta: 0:09:43 lr: 0.000043 grad: 0.0994 (0.1026) loss: 0.8150 (0.8198) time: 0.1317 data: 0.0528 max mem: 9390 +Train: [62] [2000/6250] eta: 0:09:29 lr: 0.000043 grad: 0.0979 (0.1026) loss: 0.8175 (0.8198) time: 0.1449 data: 0.0694 max mem: 9390 +Train: [62] [2100/6250] eta: 0:09:15 lr: 0.000043 grad: 0.1026 (0.1025) loss: 0.8201 (0.8199) time: 0.1210 data: 0.0391 max mem: 9390 +Train: [62] [2200/6250] eta: 0:09:02 lr: 0.000042 grad: 0.0991 (0.1024) loss: 0.8174 (0.8198) time: 0.1361 data: 0.0584 max mem: 9390 +Train: [62] [2300/6250] eta: 0:08:49 lr: 0.000042 grad: 0.1006 (0.1025) loss: 0.8140 (0.8198) time: 0.1397 data: 0.0521 max mem: 9390 +Train: [62] [2400/6250] eta: 0:08:38 lr: 0.000042 grad: 0.1006 (0.1026) loss: 0.8177 (0.8197) time: 0.1337 data: 0.0592 max mem: 9390 +Train: [62] [2500/6250] eta: 0:08:26 lr: 0.000042 grad: 0.1081 (0.1026) loss: 0.8174 (0.8197) time: 0.1334 data: 0.0572 max mem: 9390 +Train: [62] [2600/6250] eta: 0:08:12 lr: 0.000042 grad: 0.1072 (0.1027) loss: 0.8117 (0.8197) time: 0.1293 data: 0.0520 max mem: 9390 +Train: [62] [2700/6250] eta: 0:08:00 lr: 0.000042 grad: 0.1045 (0.1028) loss: 0.8154 (0.8196) time: 0.1825 data: 0.1019 max mem: 9390 +Train: [62] [2800/6250] eta: 0:07:47 lr: 0.000042 grad: 0.0961 (0.1027) loss: 0.8167 (0.8195) time: 0.1699 data: 0.0869 max mem: 9390 +Train: [62] [2900/6250] eta: 0:07:36 lr: 0.000042 grad: 0.1001 (0.1028) loss: 0.8203 (0.8195) time: 0.1733 data: 0.0979 max mem: 9390 +Train: [62] [3000/6250] eta: 0:07:24 lr: 0.000042 grad: 0.0979 (0.1028) loss: 0.8180 (0.8194) time: 0.1534 data: 0.0754 max mem: 9390 +Train: [62] [3100/6250] eta: 0:07:11 lr: 0.000042 grad: 0.0969 (0.1028) loss: 0.8189 (0.8192) time: 0.1395 data: 0.0578 max mem: 9390 +Train: [62] [3200/6250] eta: 0:06:57 lr: 0.000042 grad: 0.0986 (0.1029) loss: 0.8155 (0.8191) time: 0.1568 data: 0.0818 max mem: 9390 +Train: [62] [3300/6250] eta: 0:06:45 lr: 0.000042 grad: 0.0994 (0.1028) loss: 0.8188 (0.8191) time: 0.1340 data: 0.0557 max mem: 9390 +Train: [62] [3400/6250] eta: 0:06:31 lr: 0.000042 grad: 0.0966 (0.1028) loss: 0.8198 (0.8190) time: 0.1355 data: 0.0543 max mem: 9390 +Train: [62] [3500/6250] eta: 0:06:18 lr: 0.000042 grad: 0.0989 (0.1028) loss: 0.8165 (0.8189) time: 0.1463 data: 0.0692 max mem: 9390 +Train: [62] [3600/6250] eta: 0:06:05 lr: 0.000042 grad: 0.1035 (0.1028) loss: 0.8147 (0.8187) time: 0.1569 data: 0.0815 max mem: 9390 +Train: [62] [3700/6250] eta: 0:05:52 lr: 0.000042 grad: 0.1045 (0.1029) loss: 0.8201 (0.8187) time: 0.1769 data: 0.1038 max mem: 9390 +Train: [62] [3800/6250] eta: 0:05:38 lr: 0.000042 grad: 0.1090 (0.1030) loss: 0.8067 (0.8185) time: 0.1236 data: 0.0427 max mem: 9390 +Train: [62] [3900/6250] eta: 0:05:24 lr: 0.000042 grad: 0.1070 (0.1031) loss: 0.8113 (0.8184) time: 0.1381 data: 0.0579 max mem: 9390 +Train: [62] [4000/6250] eta: 0:05:09 lr: 0.000042 grad: 0.1083 (0.1032) loss: 0.8132 (0.8183) time: 0.1346 data: 0.0484 max mem: 9390 +Train: [62] [4100/6250] eta: 0:04:55 lr: 0.000042 grad: 0.1075 (0.1033) loss: 0.8144 (0.8182) time: 0.1180 data: 0.0423 max mem: 9390 +Train: [62] [4200/6250] eta: 0:04:41 lr: 0.000042 grad: 0.1111 (0.1034) loss: 0.8064 (0.8181) time: 0.1442 data: 0.0652 max mem: 9390 +Train: [62] [4300/6250] eta: 0:04:26 lr: 0.000042 grad: 0.0938 (0.1035) loss: 0.8157 (0.8181) time: 0.1210 data: 0.0389 max mem: 9390 +Train: [62] [4400/6250] eta: 0:04:12 lr: 0.000042 grad: 0.1003 (0.1036) loss: 0.8138 (0.8180) time: 0.1295 data: 0.0522 max mem: 9390 +Train: [62] [4500/6250] eta: 0:03:59 lr: 0.000042 grad: 0.1095 (0.1036) loss: 0.8138 (0.8179) time: 0.1913 data: 0.0594 max mem: 9390 +Train: [62] [4600/6250] eta: 0:03:45 lr: 0.000042 grad: 0.0987 (0.1037) loss: 0.8164 (0.8179) time: 0.1435 data: 0.0590 max mem: 9390 +Train: [62] [4700/6250] eta: 0:03:31 lr: 0.000042 grad: 0.1028 (0.1037) loss: 0.8158 (0.8178) time: 0.1427 data: 0.0560 max mem: 9390 +Train: [62] [4800/6250] eta: 0:03:18 lr: 0.000042 grad: 0.1048 (0.1037) loss: 0.8164 (0.8177) time: 0.1334 data: 0.0526 max mem: 9390 +Train: [62] [4900/6250] eta: 0:03:04 lr: 0.000042 grad: 0.1000 (0.1037) loss: 0.8224 (0.8177) time: 0.1413 data: 0.0653 max mem: 9390 +Train: [62] [5000/6250] eta: 0:02:50 lr: 0.000042 grad: 0.1081 (0.1037) loss: 0.8173 (0.8177) time: 0.1365 data: 0.0542 max mem: 9390 +Train: [62] [5100/6250] eta: 0:02:37 lr: 0.000042 grad: 0.1013 (0.1037) loss: 0.8186 (0.8177) time: 0.1559 data: 0.0797 max mem: 9390 +Train: [62] [5200/6250] eta: 0:02:23 lr: 0.000042 grad: 0.1014 (0.1037) loss: 0.8160 (0.8177) time: 0.1182 data: 0.0403 max mem: 9390 +Train: [62] [5300/6250] eta: 0:02:09 lr: 0.000042 grad: 0.0981 (0.1038) loss: 0.8135 (0.8176) time: 0.1385 data: 0.0630 max mem: 9390 +Train: [62] [5400/6250] eta: 0:01:56 lr: 0.000041 grad: 0.1032 (0.1038) loss: 0.8153 (0.8176) time: 0.1597 data: 0.0819 max mem: 9390 +Train: [62] [5500/6250] eta: 0:01:42 lr: 0.000041 grad: 0.1061 (0.1039) loss: 0.8135 (0.8175) time: 0.1223 data: 0.0448 max mem: 9390 +Train: [62] [5600/6250] eta: 0:01:28 lr: 0.000041 grad: 0.1049 (0.1039) loss: 0.8110 (0.8174) time: 0.1286 data: 0.0550 max mem: 9390 +Train: [62] [5700/6250] eta: 0:01:15 lr: 0.000041 grad: 0.0931 (0.1039) loss: 0.8196 (0.8174) time: 0.1357 data: 0.0583 max mem: 9390 +Train: [62] [5800/6250] eta: 0:01:01 lr: 0.000041 grad: 0.1071 (0.1039) loss: 0.8132 (0.8173) time: 0.1454 data: 0.0668 max mem: 9390 +Train: [62] [5900/6250] eta: 0:00:47 lr: 0.000041 grad: 0.1067 (0.1039) loss: 0.8179 (0.8173) time: 0.1287 data: 0.0476 max mem: 9390 +Train: [62] [6000/6250] eta: 0:00:34 lr: 0.000041 grad: 0.1004 (0.1039) loss: 0.8208 (0.8174) time: 0.1272 data: 0.0482 max mem: 9390 +Train: [62] [6100/6250] eta: 0:00:20 lr: 0.000041 grad: 0.1025 (0.1040) loss: 0.8212 (0.8174) time: 0.1384 data: 0.0610 max mem: 9390 +Train: [62] [6200/6250] eta: 0:00:06 lr: 0.000041 grad: 0.1077 (0.1040) loss: 0.8151 (0.8173) time: 0.1854 data: 0.1120 max mem: 9390 +Train: [62] [6249/6250] eta: 0:00:00 lr: 0.000041 grad: 0.0999 (0.1040) loss: 0.8225 (0.8174) time: 0.1395 data: 0.0559 max mem: 9390 +Train: [62] Total time: 0:14:20 (0.1377 s / it) +Averaged stats: lr: 0.000041 grad: 0.0999 (0.1040) loss: 0.8225 (0.8174) +Eval (hcp-train-subset): [62] [ 0/62] eta: 0:04:03 loss: 0.8455 (0.8455) time: 3.9273 data: 3.8427 max mem: 9390 +Eval (hcp-train-subset): [62] [61/62] eta: 0:00:00 loss: 0.8307 (0.8318) time: 0.1250 data: 0.0985 max mem: 9390 +Eval (hcp-train-subset): [62] Total time: 0:00:12 (0.1987 s / it) +Averaged stats (hcp-train-subset): loss: 0.8307 (0.8318) +Eval (hcp-val): [62] [ 0/62] eta: 0:04:59 loss: 0.8307 (0.8307) time: 4.8279 data: 4.7993 max mem: 9390 +Eval (hcp-val): [62] [61/62] eta: 0:00:00 loss: 0.8326 (0.8333) time: 0.1328 data: 0.1078 max mem: 9390 +Eval (hcp-val): [62] Total time: 0:00:12 (0.2046 s / it) +Averaged stats (hcp-val): loss: 0.8326 (0.8333) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +Train: [63] [ 0/6250] eta: 8:33:54 lr: 0.000041 grad: 0.0874 (0.0874) loss: 0.8600 (0.8600) time: 4.9335 data: 4.7245 max mem: 9390 +Train: [63] [ 100/6250] eta: 0:20:08 lr: 0.000041 grad: 0.1084 (0.1379) loss: 0.8111 (0.8216) time: 0.1422 data: 0.0496 max mem: 9390 +Train: [63] [ 200/6250] eta: 0:17:24 lr: 0.000041 grad: 0.1038 (0.1264) loss: 0.8195 (0.8186) time: 0.1346 data: 0.0461 max mem: 9390 +Train: [63] [ 300/6250] eta: 0:16:02 lr: 0.000041 grad: 0.0977 (0.1200) loss: 0.8203 (0.8174) time: 0.1347 data: 0.0475 max mem: 9390 +Train: [63] [ 400/6250] eta: 0:15:11 lr: 0.000041 grad: 0.0998 (0.1167) loss: 0.8152 (0.8160) time: 0.1506 data: 0.0708 max mem: 9390 +Train: [63] [ 500/6250] eta: 0:14:32 lr: 0.000041 grad: 0.1013 (0.1139) loss: 0.8154 (0.8164) time: 0.1424 data: 0.0599 max mem: 9390 +Train: [63] [ 600/6250] eta: 0:13:48 lr: 0.000041 grad: 0.1038 (0.1121) loss: 0.8123 (0.8168) time: 0.1305 data: 0.0501 max mem: 9390 +Train: [63] [ 700/6250] eta: 0:13:14 lr: 0.000041 grad: 0.0986 (0.1103) loss: 0.8281 (0.8176) time: 0.1075 data: 0.0244 max mem: 9390 +Train: [63] [ 800/6250] eta: 0:12:50 lr: 0.000041 grad: 0.0950 (0.1089) loss: 0.8221 (0.8181) time: 0.1301 data: 0.0503 max mem: 9390 +Train: [63] [ 900/6250] eta: 0:12:27 lr: 0.000041 grad: 0.1011 (0.1081) loss: 0.8166 (0.8182) time: 0.1283 data: 0.0407 max mem: 9390 +Train: [63] [1000/6250] eta: 0:12:04 lr: 0.000041 grad: 0.0969 (0.1075) loss: 0.8170 (0.8184) time: 0.1215 data: 0.0458 max mem: 9390 +Train: [63] [1100/6250] eta: 0:11:44 lr: 0.000041 grad: 0.0972 (0.1071) loss: 0.8189 (0.8181) time: 0.1189 data: 0.0436 max mem: 9390 +Train: [63] [1200/6250] eta: 0:11:22 lr: 0.000041 grad: 0.0974 (0.1065) loss: 0.8213 (0.8180) time: 0.1170 data: 0.0370 max mem: 9390 +Train: [63] [1300/6250] eta: 0:11:04 lr: 0.000041 grad: 0.1072 (0.1061) loss: 0.8128 (0.8177) time: 0.1225 data: 0.0469 max mem: 9390 +Train: [63] [1400/6250] eta: 0:10:49 lr: 0.000041 grad: 0.1000 (0.1058) loss: 0.8176 (0.8177) time: 0.1314 data: 0.0516 max mem: 9390 +Train: [63] [1500/6250] eta: 0:10:33 lr: 0.000041 grad: 0.1002 (0.1055) loss: 0.8168 (0.8177) time: 0.1239 data: 0.0378 max mem: 9390 +Train: [63] [1600/6250] eta: 0:10:18 lr: 0.000041 grad: 0.1060 (0.1054) loss: 0.8140 (0.8177) time: 0.1444 data: 0.0681 max mem: 9390 +Train: [63] [1700/6250] eta: 0:10:01 lr: 0.000041 grad: 0.1030 (0.1054) loss: 0.8173 (0.8176) time: 0.1335 data: 0.0534 max mem: 9390 +Train: [63] [1800/6250] eta: 0:09:45 lr: 0.000041 grad: 0.1039 (0.1052) loss: 0.8170 (0.8177) time: 0.1072 data: 0.0321 max mem: 9390 +Train: [63] [1900/6250] eta: 0:09:31 lr: 0.000041 grad: 0.0965 (0.1051) loss: 0.8209 (0.8177) time: 0.1155 data: 0.0351 max mem: 9390 +Train: [63] [2000/6250] eta: 0:09:17 lr: 0.000041 grad: 0.0958 (0.1050) loss: 0.8214 (0.8178) time: 0.1206 data: 0.0433 max mem: 9390 +Train: [63] [2100/6250] eta: 0:09:05 lr: 0.000041 grad: 0.0951 (0.1049) loss: 0.8246 (0.8179) time: 0.1505 data: 0.0671 max mem: 9390 +Train: [63] [2200/6250] eta: 0:08:54 lr: 0.000041 grad: 0.0949 (0.1047) loss: 0.8221 (0.8180) time: 0.1408 data: 0.0616 max mem: 9390 +Train: [63] [2300/6250] eta: 0:08:44 lr: 0.000041 grad: 0.1014 (0.1045) loss: 0.8200 (0.8181) time: 0.1597 data: 0.0615 max mem: 9390 +Train: [63] [2400/6250] eta: 0:08:32 lr: 0.000040 grad: 0.1028 (0.1044) loss: 0.8162 (0.8182) time: 0.1074 data: 0.0263 max mem: 9390 +Train: [63] [2500/6250] eta: 0:08:20 lr: 0.000040 grad: 0.0966 (0.1042) loss: 0.8231 (0.8182) time: 0.1499 data: 0.0725 max mem: 9390 +Train: [63] [2600/6250] eta: 0:08:09 lr: 0.000040 grad: 0.1041 (0.1041) loss: 0.8132 (0.8182) time: 0.1639 data: 0.0813 max mem: 9390 +Train: [63] [2700/6250] eta: 0:07:56 lr: 0.000040 grad: 0.1079 (0.1041) loss: 0.8165 (0.8181) time: 0.1534 data: 0.0726 max mem: 9390 +Train: [63] [2800/6250] eta: 0:07:43 lr: 0.000040 grad: 0.1049 (0.1041) loss: 0.8120 (0.8180) time: 0.1474 data: 0.0695 max mem: 9390 +Train: [63] [2900/6250] eta: 0:07:29 lr: 0.000040 grad: 0.0977 (0.1041) loss: 0.8122 (0.8179) time: 0.1234 data: 0.0430 max mem: 9390 +Train: [63] [3000/6250] eta: 0:07:15 lr: 0.000040 grad: 0.0975 (0.1041) loss: 0.8143 (0.8178) time: 0.1329 data: 0.0473 max mem: 9390 +Train: [63] [3100/6250] eta: 0:07:02 lr: 0.000040 grad: 0.1003 (0.1041) loss: 0.8164 (0.8178) time: 0.1102 data: 0.0326 max mem: 9390 +Train: [63] [3200/6250] eta: 0:06:50 lr: 0.000040 grad: 0.1063 (0.1042) loss: 0.8137 (0.8177) time: 0.1415 data: 0.0634 max mem: 9390 +Train: [63] [3300/6250] eta: 0:06:38 lr: 0.000040 grad: 0.1033 (0.1042) loss: 0.8189 (0.8177) time: 0.1470 data: 0.0725 max mem: 9390 +Train: [63] [3400/6250] eta: 0:06:26 lr: 0.000040 grad: 0.1041 (0.1042) loss: 0.8201 (0.8176) time: 0.1603 data: 0.0819 max mem: 9390 +Train: [63] [3500/6250] eta: 0:06:14 lr: 0.000040 grad: 0.1161 (0.1046) loss: 0.8122 (0.8175) time: 0.1544 data: 0.0774 max mem: 9390 +Train: [63] [3600/6250] eta: 0:06:01 lr: 0.000040 grad: 0.1100 (0.1048) loss: 0.8127 (0.8174) time: 0.1549 data: 0.0729 max mem: 9390 +Train: [63] [3700/6250] eta: 0:05:48 lr: 0.000040 grad: 0.1041 (0.1048) loss: 0.8121 (0.8173) time: 0.1385 data: 0.0478 max mem: 9390 +Train: [63] [3800/6250] eta: 0:05:34 lr: 0.000040 grad: 0.1106 (0.1050) loss: 0.8084 (0.8171) time: 0.1293 data: 0.0435 max mem: 9390 +Train: [63] [3900/6250] eta: 0:05:20 lr: 0.000040 grad: 0.1045 (0.1051) loss: 0.8125 (0.8170) time: 0.1231 data: 0.0430 max mem: 9390 +Train: [63] [4000/6250] eta: 0:05:06 lr: 0.000040 grad: 0.1073 (0.1052) loss: 0.8178 (0.8169) time: 0.1598 data: 0.0836 max mem: 9390 +Train: [63] [4100/6250] eta: 0:04:53 lr: 0.000040 grad: 0.1092 (0.1053) loss: 0.8127 (0.8168) time: 0.0932 data: 0.0002 max mem: 9390 +Train: [63] [4200/6250] eta: 0:04:39 lr: 0.000040 grad: 0.1159 (0.1054) loss: 0.8123 (0.8166) time: 0.1398 data: 0.0609 max mem: 9390 +Train: [63] [4300/6250] eta: 0:04:26 lr: 0.000040 grad: 0.1097 (0.1055) loss: 0.8136 (0.8165) time: 0.1423 data: 0.0655 max mem: 9390 +Train: [63] [4400/6250] eta: 0:04:13 lr: 0.000040 grad: 0.1047 (0.1056) loss: 0.8144 (0.8163) time: 0.1986 data: 0.0901 max mem: 9390 +Train: [63] [4500/6250] eta: 0:03:59 lr: 0.000040 grad: 0.1036 (0.1056) loss: 0.8125 (0.8163) time: 0.1522 data: 0.0705 max mem: 9390 +Train: [63] [4600/6250] eta: 0:03:46 lr: 0.000040 grad: 0.1117 (0.1057) loss: 0.8116 (0.8162) time: 0.1566 data: 0.0746 max mem: 9390 +Train: [63] [4700/6250] eta: 0:03:33 lr: 0.000040 grad: 0.1050 (0.1057) loss: 0.8155 (0.8160) time: 0.1625 data: 0.0854 max mem: 9390 +Train: [63] [4800/6250] eta: 0:03:19 lr: 0.000040 grad: 0.1095 (0.1058) loss: 0.8039 (0.8159) time: 0.1380 data: 0.0559 max mem: 9390 +Train: [63] [4900/6250] eta: 0:03:05 lr: 0.000040 grad: 0.1036 (0.1058) loss: 0.8085 (0.8159) time: 0.1499 data: 0.0666 max mem: 9390 +Train: [63] [5000/6250] eta: 0:02:52 lr: 0.000040 grad: 0.1113 (0.1060) loss: 0.8071 (0.8157) time: 0.1415 data: 0.0480 max mem: 9390 +Train: [63] [5100/6250] eta: 0:02:39 lr: 0.000040 grad: 0.1056 (0.1061) loss: 0.8182 (0.8156) time: 0.1885 data: 0.0694 max mem: 9390 +Train: [63] [5200/6250] eta: 0:02:25 lr: 0.000040 grad: 0.1139 (0.1062) loss: 0.8100 (0.8155) time: 0.1313 data: 0.0543 max mem: 9390 +Train: [63] [5300/6250] eta: 0:02:11 lr: 0.000040 grad: 0.1123 (0.1064) loss: 0.8176 (0.8154) time: 0.1253 data: 0.0446 max mem: 9390 +Train: [63] [5400/6250] eta: 0:01:57 lr: 0.000040 grad: 0.1068 (0.1064) loss: 0.8129 (0.8153) time: 0.1306 data: 0.0504 max mem: 9390 +Train: [63] [5500/6250] eta: 0:01:43 lr: 0.000040 grad: 0.1044 (0.1067) loss: 0.8075 (0.8151) time: 0.1433 data: 0.0646 max mem: 9390 +Train: [63] [5600/6250] eta: 0:01:30 lr: 0.000039 grad: 0.1101 (0.1068) loss: 0.8084 (0.8150) time: 0.1333 data: 0.0574 max mem: 9390 +Train: [63] [5700/6250] eta: 0:01:16 lr: 0.000039 grad: 0.1103 (0.1069) loss: 0.8091 (0.8149) time: 0.1624 data: 0.0874 max mem: 9390 +Train: [63] [5800/6250] eta: 0:01:02 lr: 0.000039 grad: 0.1041 (0.1070) loss: 0.8158 (0.8148) time: 0.1406 data: 0.0663 max mem: 9390 +Train: [63] [5900/6250] eta: 0:00:48 lr: 0.000039 grad: 0.1122 (0.1071) loss: 0.8119 (0.8147) time: 0.1244 data: 0.0443 max mem: 9390 +Train: [63] [6000/6250] eta: 0:00:34 lr: 0.000039 grad: 0.1076 (0.1072) loss: 0.8082 (0.8146) time: 0.1276 data: 0.0496 max mem: 9390 +Train: [63] [6100/6250] eta: 0:00:20 lr: 0.000039 grad: 0.1083 (0.1073) loss: 0.8190 (0.8145) time: 0.1563 data: 0.0798 max mem: 9390 +Train: [63] [6200/6250] eta: 0:00:06 lr: 0.000039 grad: 0.1019 (0.1074) loss: 0.8143 (0.8144) time: 0.1399 data: 0.0655 max mem: 9390 +Train: [63] [6249/6250] eta: 0:00:00 lr: 0.000039 grad: 0.1096 (0.1074) loss: 0.8110 (0.8144) time: 0.1385 data: 0.0529 max mem: 9390 +Train: [63] Total time: 0:14:32 (0.1397 s / it) +Averaged stats: lr: 0.000039 grad: 0.1096 (0.1074) loss: 0.8110 (0.8144) +Eval (hcp-train-subset): [63] [ 0/62] eta: 0:04:21 loss: 0.8357 (0.8357) time: 4.2254 data: 4.1947 max mem: 9390 +Eval (hcp-train-subset): [63] [61/62] eta: 0:00:00 loss: 0.8278 (0.8299) time: 0.1193 data: 0.0926 max mem: 9390 +Eval (hcp-train-subset): [63] Total time: 0:00:12 (0.2039 s / it) +Averaged stats (hcp-train-subset): loss: 0.8278 (0.8299) +Eval (hcp-val): [63] [ 0/62] eta: 0:04:58 loss: 0.8267 (0.8267) time: 4.8074 data: 4.7784 max mem: 9390 +Eval (hcp-val): [63] [61/62] eta: 0:00:00 loss: 0.8307 (0.8326) time: 0.1207 data: 0.0960 max mem: 9390 +Eval (hcp-val): [63] Total time: 0:00:12 (0.2056 s / it) +Averaged stats (hcp-val): loss: 0.8307 (0.8326) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +Train: [64] [ 0/6250] eta: 10:54:47 lr: 0.000039 grad: 0.2022 (0.2022) loss: 0.8635 (0.8635) time: 6.2859 data: 6.1888 max mem: 9390 +Train: [64] [ 100/6250] eta: 0:21:19 lr: 0.000039 grad: 0.0977 (0.1179) loss: 0.8239 (0.8219) time: 0.1841 data: 0.0976 max mem: 9390 +Train: [64] [ 200/6250] eta: 0:17:33 lr: 0.000039 grad: 0.0984 (0.1151) loss: 0.8274 (0.8198) time: 0.1406 data: 0.0488 max mem: 9390 +Train: [64] [ 300/6250] eta: 0:16:04 lr: 0.000039 grad: 0.1052 (0.1132) loss: 0.8168 (0.8192) time: 0.1389 data: 0.0524 max mem: 9390 +Train: [64] [ 400/6250] eta: 0:14:59 lr: 0.000039 grad: 0.1027 (0.1114) loss: 0.8240 (0.8190) time: 0.1355 data: 0.0545 max mem: 9390 +Train: [64] [ 500/6250] eta: 0:14:14 lr: 0.000039 grad: 0.0992 (0.1096) loss: 0.8241 (0.8196) time: 0.1246 data: 0.0370 max mem: 9390 +Train: [64] [ 600/6250] eta: 0:13:39 lr: 0.000039 grad: 0.0990 (0.1082) loss: 0.8300 (0.8204) time: 0.1141 data: 0.0239 max mem: 9390 +Train: [64] [ 700/6250] eta: 0:13:09 lr: 0.000039 grad: 0.0924 (0.1070) loss: 0.8271 (0.8210) time: 0.1250 data: 0.0347 max mem: 9390 +Train: [64] [ 800/6250] eta: 0:12:45 lr: 0.000039 grad: 0.1052 (0.1065) loss: 0.8218 (0.8213) time: 0.1138 data: 0.0343 max mem: 9390 +Train: [64] [ 900/6250] eta: 0:12:32 lr: 0.000039 grad: 0.0939 (0.1057) loss: 0.8229 (0.8215) time: 0.1651 data: 0.0848 max mem: 9390 +Train: [64] [1000/6250] eta: 0:12:19 lr: 0.000039 grad: 0.1004 (0.1055) loss: 0.8148 (0.8212) time: 0.1300 data: 0.0504 max mem: 9390 +Train: [64] [1100/6250] eta: 0:12:00 lr: 0.000039 grad: 0.0973 (0.1050) loss: 0.8223 (0.8212) time: 0.1231 data: 0.0466 max mem: 9390 +Train: [64] [1200/6250] eta: 0:11:45 lr: 0.000039 grad: 0.1018 (0.1049) loss: 0.8164 (0.8210) time: 0.1306 data: 0.0515 max mem: 9390 +Train: [64] [1300/6250] eta: 0:11:33 lr: 0.000039 grad: 0.1091 (0.1047) loss: 0.8112 (0.8207) time: 0.0848 data: 0.0002 max mem: 9390 +Train: [64] [1400/6250] eta: 0:11:13 lr: 0.000039 grad: 0.0992 (0.1046) loss: 0.8119 (0.8204) time: 0.1339 data: 0.0572 max mem: 9390 +Train: [64] [1500/6250] eta: 0:10:56 lr: 0.000039 grad: 0.1016 (0.1045) loss: 0.8210 (0.8203) time: 0.1358 data: 0.0630 max mem: 9390 +Train: [64] [1600/6250] eta: 0:10:39 lr: 0.000039 grad: 0.0961 (0.1044) loss: 0.8163 (0.8202) time: 0.1310 data: 0.0520 max mem: 9390 +Train: [64] [1700/6250] eta: 0:10:23 lr: 0.000039 grad: 0.0959 (0.1043) loss: 0.8199 (0.8200) time: 0.1113 data: 0.0319 max mem: 9390 +Train: [64] [1800/6250] eta: 0:10:06 lr: 0.000039 grad: 0.1002 (0.1045) loss: 0.8167 (0.8198) time: 0.1166 data: 0.0394 max mem: 9390 +Train: [64] [1900/6250] eta: 0:09:51 lr: 0.000039 grad: 0.1019 (0.1048) loss: 0.8164 (0.8196) time: 0.1280 data: 0.0512 max mem: 9390 +Train: [64] [2000/6250] eta: 0:09:37 lr: 0.000039 grad: 0.1099 (0.1049) loss: 0.8138 (0.8194) time: 0.1442 data: 0.0690 max mem: 9390 +Train: [64] [2100/6250] eta: 0:09:26 lr: 0.000039 grad: 0.1058 (0.1052) loss: 0.8183 (0.8194) time: 0.1586 data: 0.0853 max mem: 9390 +Train: [64] [2200/6250] eta: 0:09:13 lr: 0.000039 grad: 0.1046 (0.1052) loss: 0.8180 (0.8193) time: 0.1422 data: 0.0634 max mem: 9390 +Train: [64] [2300/6250] eta: 0:08:59 lr: 0.000039 grad: 0.1035 (0.1053) loss: 0.8150 (0.8191) time: 0.1393 data: 0.0589 max mem: 9390 +Train: [64] [2400/6250] eta: 0:08:47 lr: 0.000039 grad: 0.1031 (0.1053) loss: 0.8157 (0.8190) time: 0.1452 data: 0.0654 max mem: 9390 +Train: [64] [2500/6250] eta: 0:08:35 lr: 0.000039 grad: 0.1088 (0.1054) loss: 0.8105 (0.8189) time: 0.1642 data: 0.0895 max mem: 9390 +Train: [64] [2600/6250] eta: 0:08:21 lr: 0.000039 grad: 0.1069 (0.1054) loss: 0.8157 (0.8189) time: 0.1583 data: 0.0797 max mem: 9390 +Train: [64] [2700/6250] eta: 0:08:07 lr: 0.000038 grad: 0.0989 (0.1054) loss: 0.8188 (0.8188) time: 0.1581 data: 0.0685 max mem: 9390 +Train: [64] [2800/6250] eta: 0:07:55 lr: 0.000038 grad: 0.0989 (0.1053) loss: 0.8219 (0.8188) time: 0.1369 data: 0.0512 max mem: 9390 +Train: [64] [2900/6250] eta: 0:07:42 lr: 0.000038 grad: 0.0999 (0.1054) loss: 0.8146 (0.8188) time: 0.1462 data: 0.0566 max mem: 9390 +Train: [64] [3000/6250] eta: 0:07:28 lr: 0.000038 grad: 0.1082 (0.1055) loss: 0.8138 (0.8187) time: 0.1158 data: 0.0414 max mem: 9390 +Train: [64] [3100/6250] eta: 0:07:16 lr: 0.000038 grad: 0.1050 (0.1057) loss: 0.8156 (0.8185) time: 0.1338 data: 0.0608 max mem: 9390 +Train: [64] [3200/6250] eta: 0:07:03 lr: 0.000038 grad: 0.1064 (0.1058) loss: 0.8114 (0.8184) time: 0.1550 data: 0.0675 max mem: 9390 +Train: [64] [3300/6250] eta: 0:06:51 lr: 0.000038 grad: 0.1073 (0.1058) loss: 0.8148 (0.8182) time: 0.1496 data: 0.0696 max mem: 9390 +Train: [64] [3400/6250] eta: 0:06:37 lr: 0.000038 grad: 0.1055 (0.1059) loss: 0.8173 (0.8181) time: 0.1199 data: 0.0453 max mem: 9390 +Train: [64] [3500/6250] eta: 0:06:23 lr: 0.000038 grad: 0.1105 (0.1060) loss: 0.8156 (0.8180) time: 0.1376 data: 0.0551 max mem: 9390 +Train: [64] [3600/6250] eta: 0:06:09 lr: 0.000038 grad: 0.1047 (0.1061) loss: 0.8104 (0.8179) time: 0.1232 data: 0.0467 max mem: 9390 +Train: [64] [3700/6250] eta: 0:05:55 lr: 0.000038 grad: 0.1056 (0.1061) loss: 0.8106 (0.8178) time: 0.1296 data: 0.0484 max mem: 9390 +Train: [64] [3800/6250] eta: 0:05:41 lr: 0.000038 grad: 0.1036 (0.1062) loss: 0.8139 (0.8176) time: 0.1119 data: 0.0302 max mem: 9390 +Train: [64] [3900/6250] eta: 0:05:26 lr: 0.000038 grad: 0.1058 (0.1063) loss: 0.8102 (0.8175) time: 0.1506 data: 0.0726 max mem: 9390 +Train: [64] [4000/6250] eta: 0:05:12 lr: 0.000038 grad: 0.1128 (0.1064) loss: 0.8113 (0.8174) time: 0.1355 data: 0.0538 max mem: 9390 +Train: [64] [4100/6250] eta: 0:04:57 lr: 0.000038 grad: 0.1174 (0.1065) loss: 0.8128 (0.8172) time: 0.1271 data: 0.0478 max mem: 9390 +Train: [64] [4200/6250] eta: 0:04:43 lr: 0.000038 grad: 0.1057 (0.1067) loss: 0.8124 (0.8171) time: 0.1304 data: 0.0490 max mem: 9390 +Train: [64] [4300/6250] eta: 0:04:28 lr: 0.000038 grad: 0.1065 (0.1068) loss: 0.8166 (0.8170) time: 0.1245 data: 0.0469 max mem: 9390 +Train: [64] [4400/6250] eta: 0:04:14 lr: 0.000038 grad: 0.1065 (0.1069) loss: 0.8147 (0.8170) time: 0.1313 data: 0.0488 max mem: 9390 +Train: [64] [4500/6250] eta: 0:04:00 lr: 0.000038 grad: 0.1085 (0.1071) loss: 0.8083 (0.8169) time: 0.1281 data: 0.0456 max mem: 9390 +Train: [64] [4600/6250] eta: 0:03:46 lr: 0.000038 grad: 0.1043 (0.1072) loss: 0.8129 (0.8168) time: 0.1287 data: 0.0490 max mem: 9390 +Train: [64] [4700/6250] eta: 0:03:32 lr: 0.000038 grad: 0.1035 (0.1072) loss: 0.8158 (0.8168) time: 0.1328 data: 0.0554 max mem: 9390 +Train: [64] [4800/6250] eta: 0:03:19 lr: 0.000038 grad: 0.1099 (0.1073) loss: 0.8095 (0.8167) time: 0.1565 data: 0.0755 max mem: 9390 +Train: [64] [4900/6250] eta: 0:03:05 lr: 0.000038 grad: 0.1115 (0.1074) loss: 0.8080 (0.8166) time: 0.1269 data: 0.0430 max mem: 9390 +Train: [64] [5000/6250] eta: 0:02:51 lr: 0.000038 grad: 0.1064 (0.1074) loss: 0.8206 (0.8166) time: 0.1222 data: 0.0392 max mem: 9390 +Train: [64] [5100/6250] eta: 0:02:37 lr: 0.000038 grad: 0.0970 (0.1075) loss: 0.8187 (0.8166) time: 0.1219 data: 0.0450 max mem: 9390 +Train: [64] [5200/6250] eta: 0:02:23 lr: 0.000038 grad: 0.0997 (0.1074) loss: 0.8133 (0.8166) time: 0.1462 data: 0.0686 max mem: 9390 +Train: [64] [5300/6250] eta: 0:02:10 lr: 0.000038 grad: 0.1035 (0.1074) loss: 0.8134 (0.8166) time: 0.1281 data: 0.0491 max mem: 9390 +Train: [64] [5400/6250] eta: 0:01:56 lr: 0.000038 grad: 0.1037 (0.1074) loss: 0.8192 (0.8166) time: 0.1625 data: 0.0758 max mem: 9390 +Train: [64] [5500/6250] eta: 0:01:42 lr: 0.000038 grad: 0.1057 (0.1074) loss: 0.8128 (0.8166) time: 0.1320 data: 0.0536 max mem: 9390 +Train: [64] [5600/6250] eta: 0:01:29 lr: 0.000038 grad: 0.1013 (0.1073) loss: 0.8179 (0.8166) time: 0.1032 data: 0.0264 max mem: 9390 +Train: [64] [5700/6250] eta: 0:01:15 lr: 0.000038 grad: 0.1066 (0.1074) loss: 0.8096 (0.8166) time: 0.1339 data: 0.0551 max mem: 9390 +Train: [64] [5800/6250] eta: 0:01:01 lr: 0.000038 grad: 0.1083 (0.1074) loss: 0.8150 (0.8165) time: 0.1387 data: 0.0580 max mem: 9390 +Train: [64] [5900/6250] eta: 0:00:47 lr: 0.000037 grad: 0.1067 (0.1075) loss: 0.8140 (0.8165) time: 0.1340 data: 0.0567 max mem: 9390 +Train: [64] [6000/6250] eta: 0:00:34 lr: 0.000037 grad: 0.1047 (0.1075) loss: 0.8153 (0.8164) time: 0.2006 data: 0.0738 max mem: 9390 +Train: [64] [6100/6250] eta: 0:00:20 lr: 0.000037 grad: 0.1055 (0.1075) loss: 0.8124 (0.8164) time: 0.1272 data: 0.0527 max mem: 9390 +Train: [64] [6200/6250] eta: 0:00:06 lr: 0.000037 grad: 0.1033 (0.1075) loss: 0.8177 (0.8164) time: 0.1424 data: 0.0558 max mem: 9390 +Train: [64] [6249/6250] eta: 0:00:00 lr: 0.000037 grad: 0.1005 (0.1075) loss: 0.8144 (0.8164) time: 0.1424 data: 0.0630 max mem: 9390 +Train: [64] Total time: 0:14:25 (0.1386 s / it) +Averaged stats: lr: 0.000037 grad: 0.1005 (0.1075) loss: 0.8144 (0.8164) +Eval (hcp-train-subset): [64] [ 0/62] eta: 0:03:00 loss: 0.8399 (0.8399) time: 2.9126 data: 2.8289 max mem: 9390 +Eval (hcp-train-subset): [64] [61/62] eta: 0:00:00 loss: 0.8285 (0.8309) time: 0.1250 data: 0.0983 max mem: 9390 +Eval (hcp-train-subset): [64] Total time: 0:00:12 (0.1974 s / it) +Averaged stats (hcp-train-subset): loss: 0.8285 (0.8309) +Making plots (hcp-train-subset): example=52 +Eval (hcp-val): [64] [ 0/62] eta: 0:03:41 loss: 0.8305 (0.8305) time: 3.5786 data: 3.5039 max mem: 9390 +Eval (hcp-val): [64] [61/62] eta: 0:00:00 loss: 0.8330 (0.8332) time: 0.1371 data: 0.1122 max mem: 9390 +Eval (hcp-val): [64] Total time: 0:00:13 (0.2126 s / it) +Averaged stats (hcp-val): loss: 0.8330 (0.8332) +Making plots (hcp-val): example=40 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +Train: [65] [ 0/6250] eta: 6:48:28 lr: 0.000037 grad: 0.0727 (0.0727) loss: 0.8650 (0.8650) time: 3.9213 data: 3.7316 max mem: 9390 +Train: [65] [ 100/6250] eta: 0:21:29 lr: 0.000037 grad: 0.0964 (0.1149) loss: 0.8361 (0.8327) time: 0.1701 data: 0.0800 max mem: 9390 +Train: [65] [ 200/6250] eta: 0:17:45 lr: 0.000037 grad: 0.1070 (0.1147) loss: 0.8248 (0.8278) time: 0.1353 data: 0.0495 max mem: 9390 +Train: [65] [ 300/6250] eta: 0:16:30 lr: 0.000037 grad: 0.0998 (0.1118) loss: 0.8256 (0.8252) time: 0.1454 data: 0.0643 max mem: 9390 +Train: [65] [ 400/6250] eta: 0:15:31 lr: 0.000037 grad: 0.0969 (0.1110) loss: 0.8204 (0.8237) time: 0.1396 data: 0.0560 max mem: 9390 +Train: [65] [ 500/6250] eta: 0:14:49 lr: 0.000037 grad: 0.1016 (0.1102) loss: 0.8211 (0.8229) time: 0.1421 data: 0.0532 max mem: 9390 +Train: [65] [ 600/6250] eta: 0:14:09 lr: 0.000037 grad: 0.1025 (0.1089) loss: 0.8209 (0.8226) time: 0.1159 data: 0.0290 max mem: 9390 +Train: [65] [ 700/6250] eta: 0:13:33 lr: 0.000037 grad: 0.1020 (0.1084) loss: 0.8167 (0.8219) time: 0.1364 data: 0.0471 max mem: 9390 +Train: [65] [ 800/6250] eta: 0:13:08 lr: 0.000037 grad: 0.0962 (0.1077) loss: 0.8171 (0.8216) time: 0.1262 data: 0.0426 max mem: 9390 +Train: [65] [ 900/6250] eta: 0:12:39 lr: 0.000037 grad: 0.0989 (0.1075) loss: 0.8189 (0.8211) time: 0.1205 data: 0.0389 max mem: 9390 +Train: [65] [1000/6250] eta: 0:12:14 lr: 0.000037 grad: 0.0986 (0.1074) loss: 0.8164 (0.8206) time: 0.1249 data: 0.0475 max mem: 9390 +Train: [65] [1100/6250] eta: 0:11:51 lr: 0.000037 grad: 0.1047 (0.1070) loss: 0.8150 (0.8201) time: 0.1165 data: 0.0348 max mem: 9390 +Train: [65] [1200/6250] eta: 0:11:28 lr: 0.000037 grad: 0.1002 (0.1070) loss: 0.8183 (0.8198) time: 0.1130 data: 0.0307 max mem: 9390 +Train: [65] [1300/6250] eta: 0:11:11 lr: 0.000037 grad: 0.1035 (0.1069) loss: 0.8123 (0.8194) time: 0.1339 data: 0.0568 max mem: 9390 +Train: [65] [1400/6250] eta: 0:10:53 lr: 0.000037 grad: 0.1072 (0.1068) loss: 0.8129 (0.8192) time: 0.1205 data: 0.0389 max mem: 9390 +Train: [65] [1500/6250] eta: 0:10:36 lr: 0.000037 grad: 0.1022 (0.1071) loss: 0.8118 (0.8187) time: 0.1215 data: 0.0424 max mem: 9390 +Train: [65] [1600/6250] eta: 0:10:20 lr: 0.000037 grad: 0.1062 (0.1072) loss: 0.8110 (0.8184) time: 0.1248 data: 0.0494 max mem: 9390 +Train: [65] [1700/6250] eta: 0:10:04 lr: 0.000037 grad: 0.0994 (0.1071) loss: 0.8106 (0.8182) time: 0.1348 data: 0.0570 max mem: 9390 +Train: [65] [1800/6250] eta: 0:09:49 lr: 0.000037 grad: 0.1028 (0.1071) loss: 0.8136 (0.8180) time: 0.1428 data: 0.0728 max mem: 9390 +Train: [65] [1900/6250] eta: 0:09:33 lr: 0.000037 grad: 0.0986 (0.1070) loss: 0.8182 (0.8179) time: 0.1272 data: 0.0407 max mem: 9390 +Train: [65] [2000/6250] eta: 0:09:22 lr: 0.000037 grad: 0.1064 (0.1071) loss: 0.8152 (0.8177) time: 0.1408 data: 0.0630 max mem: 9390 +Train: [65] [2100/6250] eta: 0:09:09 lr: 0.000037 grad: 0.1025 (0.1071) loss: 0.8128 (0.8175) time: 0.1334 data: 0.0553 max mem: 9390 +Train: [65] [2200/6250] eta: 0:08:55 lr: 0.000037 grad: 0.1039 (0.1072) loss: 0.8134 (0.8172) time: 0.1244 data: 0.0464 max mem: 9390 +Train: [65] [2300/6250] eta: 0:08:44 lr: 0.000037 grad: 0.1015 (0.1073) loss: 0.8162 (0.8169) time: 0.1461 data: 0.0619 max mem: 9390 +Train: [65] [2400/6250] eta: 0:08:31 lr: 0.000037 grad: 0.1065 (0.1073) loss: 0.8152 (0.8167) time: 0.1296 data: 0.0459 max mem: 9390 +Train: [65] [2500/6250] eta: 0:08:19 lr: 0.000037 grad: 0.1080 (0.1074) loss: 0.8085 (0.8165) time: 0.1432 data: 0.0589 max mem: 9390 +Train: [65] [2600/6250] eta: 0:08:07 lr: 0.000037 grad: 0.1067 (0.1077) loss: 0.8119 (0.8163) time: 0.1230 data: 0.0471 max mem: 9390 +Train: [65] [2700/6250] eta: 0:07:54 lr: 0.000037 grad: 0.1101 (0.1078) loss: 0.8093 (0.8161) time: 0.1332 data: 0.0555 max mem: 9390 +Train: [65] [2800/6250] eta: 0:07:41 lr: 0.000037 grad: 0.1069 (0.1080) loss: 0.8159 (0.8159) time: 0.1365 data: 0.0628 max mem: 9390 +Train: [65] [2900/6250] eta: 0:07:28 lr: 0.000037 grad: 0.1042 (0.1082) loss: 0.8136 (0.8158) time: 0.1381 data: 0.0606 max mem: 9390 +Train: [65] [3000/6250] eta: 0:07:16 lr: 0.000036 grad: 0.1059 (0.1082) loss: 0.8206 (0.8158) time: 0.1166 data: 0.0432 max mem: 9390 +Train: [65] [3100/6250] eta: 0:07:02 lr: 0.000036 grad: 0.1054 (0.1081) loss: 0.8153 (0.8158) time: 0.1483 data: 0.0706 max mem: 9390 +Train: [65] [3200/6250] eta: 0:06:50 lr: 0.000036 grad: 0.1057 (0.1082) loss: 0.8213 (0.8158) time: 0.1392 data: 0.0640 max mem: 9390 +Train: [65] [3300/6250] eta: 0:06:38 lr: 0.000036 grad: 0.1067 (0.1082) loss: 0.8111 (0.8158) time: 0.1570 data: 0.0731 max mem: 9390 +Train: [65] [3400/6250] eta: 0:06:24 lr: 0.000036 grad: 0.1054 (0.1082) loss: 0.8139 (0.8158) time: 0.1086 data: 0.0299 max mem: 9390 +Train: [65] [3500/6250] eta: 0:06:12 lr: 0.000036 grad: 0.1130 (0.1083) loss: 0.8051 (0.8157) time: 0.1617 data: 0.0866 max mem: 9390 +Train: [65] [3600/6250] eta: 0:05:58 lr: 0.000036 grad: 0.1031 (0.1084) loss: 0.8132 (0.8156) time: 0.1401 data: 0.0585 max mem: 9390 +Train: [65] [3700/6250] eta: 0:05:44 lr: 0.000036 grad: 0.1019 (0.1084) loss: 0.8105 (0.8155) time: 0.1313 data: 0.0458 max mem: 9390 +Train: [65] [3800/6250] eta: 0:05:30 lr: 0.000036 grad: 0.1089 (0.1085) loss: 0.8130 (0.8154) time: 0.1234 data: 0.0352 max mem: 9390 +Train: [65] [3900/6250] eta: 0:05:16 lr: 0.000036 grad: 0.1003 (0.1084) loss: 0.8150 (0.8154) time: 0.1184 data: 0.0431 max mem: 9390 +Train: [65] [4000/6250] eta: 0:05:02 lr: 0.000036 grad: 0.1057 (0.1085) loss: 0.8098 (0.8154) time: 0.1460 data: 0.0622 max mem: 9390 +Train: [65] [4100/6250] eta: 0:04:49 lr: 0.000036 grad: 0.1008 (0.1085) loss: 0.8099 (0.8153) time: 0.1198 data: 0.0427 max mem: 9390 +Train: [65] [4200/6250] eta: 0:04:35 lr: 0.000036 grad: 0.1121 (0.1086) loss: 0.8008 (0.8152) time: 0.1337 data: 0.0558 max mem: 9390 +Train: [65] [4300/6250] eta: 0:04:22 lr: 0.000036 grad: 0.1051 (0.1086) loss: 0.8112 (0.8151) time: 0.1292 data: 0.0508 max mem: 9390 +Train: [65] [4400/6250] eta: 0:04:08 lr: 0.000036 grad: 0.1043 (0.1087) loss: 0.8185 (0.8150) time: 0.1539 data: 0.0796 max mem: 9390 +Train: [65] [4500/6250] eta: 0:03:55 lr: 0.000036 grad: 0.1049 (0.1087) loss: 0.8118 (0.8150) time: 0.1466 data: 0.0636 max mem: 9390 +Train: [65] [4600/6250] eta: 0:03:42 lr: 0.000036 grad: 0.1136 (0.1088) loss: 0.8110 (0.8149) time: 0.1329 data: 0.0497 max mem: 9390 +Train: [65] [4700/6250] eta: 0:03:28 lr: 0.000036 grad: 0.1167 (0.1090) loss: 0.8103 (0.8148) time: 0.1528 data: 0.0726 max mem: 9390 +Train: [65] [4800/6250] eta: 0:03:15 lr: 0.000036 grad: 0.1120 (0.1091) loss: 0.8184 (0.8148) time: 0.1334 data: 0.0576 max mem: 9390 +Train: [65] [4900/6250] eta: 0:03:02 lr: 0.000036 grad: 0.1126 (0.1092) loss: 0.8125 (0.8147) time: 0.1119 data: 0.0176 max mem: 9390 +Train: [65] [5000/6250] eta: 0:02:48 lr: 0.000036 grad: 0.1127 (0.1093) loss: 0.8095 (0.8146) time: 0.1289 data: 0.0511 max mem: 9390 +Train: [65] [5100/6250] eta: 0:02:35 lr: 0.000036 grad: 0.1126 (0.1094) loss: 0.8128 (0.8145) time: 0.1272 data: 0.0516 max mem: 9390 +Train: [65] [5200/6250] eta: 0:02:22 lr: 0.000036 grad: 0.1127 (0.1095) loss: 0.8115 (0.8144) time: 0.0948 data: 0.0161 max mem: 9390 +Train: [65] [5300/6250] eta: 0:02:08 lr: 0.000036 grad: 0.1095 (0.1096) loss: 0.8173 (0.8144) time: 0.1497 data: 0.0705 max mem: 9390 +Train: [65] [5400/6250] eta: 0:01:55 lr: 0.000036 grad: 0.1197 (0.1097) loss: 0.8085 (0.8144) time: 0.1254 data: 0.0374 max mem: 9390 +Train: [65] [5500/6250] eta: 0:01:41 lr: 0.000036 grad: 0.1106 (0.1098) loss: 0.8096 (0.8143) time: 0.1441 data: 0.0694 max mem: 9390 +Train: [65] [5600/6250] eta: 0:01:28 lr: 0.000036 grad: 0.1043 (0.1098) loss: 0.8120 (0.8143) time: 0.1243 data: 0.0417 max mem: 9390 +Train: [65] [5700/6250] eta: 0:01:14 lr: 0.000036 grad: 0.1077 (0.1099) loss: 0.8099 (0.8143) time: 0.1170 data: 0.0413 max mem: 9390 +Train: [65] [5800/6250] eta: 0:01:01 lr: 0.000036 grad: 0.1060 (0.1099) loss: 0.8117 (0.8142) time: 0.1329 data: 0.0506 max mem: 9390 +Train: [65] [5900/6250] eta: 0:00:47 lr: 0.000036 grad: 0.1117 (0.1100) loss: 0.8117 (0.8142) time: 0.1246 data: 0.0473 max mem: 9390 +Train: [65] [6000/6250] eta: 0:00:33 lr: 0.000036 grad: 0.1091 (0.1100) loss: 0.8106 (0.8142) time: 0.1725 data: 0.0660 max mem: 9390 +Train: [65] [6100/6250] eta: 0:00:20 lr: 0.000036 grad: 0.1031 (0.1100) loss: 0.8206 (0.8141) time: 0.1954 data: 0.1183 max mem: 9390 +Train: [65] [6200/6250] eta: 0:00:06 lr: 0.000036 grad: 0.1025 (0.1100) loss: 0.8171 (0.8141) time: 0.1488 data: 0.0745 max mem: 9390 +Train: [65] [6249/6250] eta: 0:00:00 lr: 0.000036 grad: 0.1093 (0.1101) loss: 0.8130 (0.8141) time: 0.1257 data: 0.0331 max mem: 9390 +Train: [65] Total time: 0:14:18 (0.1374 s / it) +Averaged stats: lr: 0.000036 grad: 0.1093 (0.1101) loss: 0.8130 (0.8141) +Eval (hcp-train-subset): [65] [ 0/62] eta: 0:05:33 loss: 0.8389 (0.8389) time: 5.3799 data: 5.3464 max mem: 9390 +Eval (hcp-train-subset): [65] [61/62] eta: 0:00:00 loss: 0.8291 (0.8310) time: 0.1309 data: 0.1043 max mem: 9390 +Eval (hcp-train-subset): [65] Total time: 0:00:13 (0.2101 s / it) +Averaged stats (hcp-train-subset): loss: 0.8291 (0.8310) +Eval (hcp-val): [65] [ 0/62] eta: 0:05:00 loss: 0.8296 (0.8296) time: 4.8439 data: 4.8154 max mem: 9390 +Eval (hcp-val): [65] [61/62] eta: 0:00:00 loss: 0.8308 (0.8321) time: 0.1286 data: 0.1038 max mem: 9390 +Eval (hcp-val): [65] Total time: 0:00:12 (0.2024 s / it) +Averaged stats (hcp-val): loss: 0.8308 (0.8321) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +Train: [66] [ 0/6250] eta: 7:36:47 lr: 0.000036 grad: 0.0714 (0.0714) loss: 0.8643 (0.8643) time: 4.3851 data: 4.1019 max mem: 9390 +Train: [66] [ 100/6250] eta: 0:21:23 lr: 0.000035 grad: 0.1043 (0.1114) loss: 0.8253 (0.8294) time: 0.1552 data: 0.0603 max mem: 9390 +Train: [66] [ 200/6250] eta: 0:17:55 lr: 0.000035 grad: 0.1062 (0.1124) loss: 0.8067 (0.8227) time: 0.1445 data: 0.0580 max mem: 9390 +Train: [66] [ 300/6250] eta: 0:16:36 lr: 0.000035 grad: 0.1034 (0.1112) loss: 0.8207 (0.8203) time: 0.1402 data: 0.0615 max mem: 9390 +Train: [66] [ 400/6250] eta: 0:15:40 lr: 0.000035 grad: 0.1091 (0.1112) loss: 0.8169 (0.8193) time: 0.1455 data: 0.0593 max mem: 9390 +Train: [66] [ 500/6250] eta: 0:14:49 lr: 0.000035 grad: 0.1143 (0.1123) loss: 0.8075 (0.8177) time: 0.1184 data: 0.0350 max mem: 9390 +Train: [66] [ 600/6250] eta: 0:14:12 lr: 0.000035 grad: 0.1009 (0.1123) loss: 0.8145 (0.8165) time: 0.1411 data: 0.0622 max mem: 9390 +Train: [66] [ 700/6250] eta: 0:13:35 lr: 0.000035 grad: 0.1104 (0.1123) loss: 0.8091 (0.8155) time: 0.1320 data: 0.0476 max mem: 9390 +Train: [66] [ 800/6250] eta: 0:13:07 lr: 0.000035 grad: 0.1079 (0.1121) loss: 0.8163 (0.8150) time: 0.1361 data: 0.0537 max mem: 9390 +Train: [66] [ 900/6250] eta: 0:12:42 lr: 0.000035 grad: 0.1086 (0.1119) loss: 0.8175 (0.8146) time: 0.1218 data: 0.0327 max mem: 9390 +Train: [66] [1000/6250] eta: 0:12:21 lr: 0.000035 grad: 0.1097 (0.1118) loss: 0.8113 (0.8143) time: 0.1526 data: 0.0729 max mem: 9390 +Train: [66] [1100/6250] eta: 0:12:03 lr: 0.000035 grad: 0.1051 (0.1117) loss: 0.8160 (0.8139) time: 0.1425 data: 0.0649 max mem: 9390 +Train: [66] [1200/6250] eta: 0:11:48 lr: 0.000035 grad: 0.1076 (0.1116) loss: 0.8077 (0.8136) time: 0.1333 data: 0.0548 max mem: 9390 +Train: [66] [1300/6250] eta: 0:11:27 lr: 0.000035 grad: 0.1040 (0.1115) loss: 0.8085 (0.8135) time: 0.1247 data: 0.0478 max mem: 9390 +Train: [66] [1400/6250] eta: 0:11:12 lr: 0.000035 grad: 0.1113 (0.1115) loss: 0.8129 (0.8133) time: 0.1473 data: 0.0704 max mem: 9390 +Train: [66] [1500/6250] eta: 0:10:57 lr: 0.000035 grad: 0.1030 (0.1115) loss: 0.8092 (0.8129) time: 0.1264 data: 0.0517 max mem: 9390 +Train: [66] [1600/6250] eta: 0:10:40 lr: 0.000035 grad: 0.1133 (0.1116) loss: 0.8076 (0.8126) time: 0.1143 data: 0.0345 max mem: 9390 +Train: [66] [1700/6250] eta: 0:10:25 lr: 0.000035 grad: 0.1117 (0.1116) loss: 0.8087 (0.8124) time: 0.1098 data: 0.0249 max mem: 9390 +Train: [66] [1800/6250] eta: 0:10:09 lr: 0.000035 grad: 0.1072 (0.1115) loss: 0.8080 (0.8123) time: 0.1183 data: 0.0363 max mem: 9390 +Train: [66] [1900/6250] eta: 0:09:57 lr: 0.000035 grad: 0.1099 (0.1115) loss: 0.8066 (0.8123) time: 0.1754 data: 0.0892 max mem: 9390 +Train: [66] [2000/6250] eta: 0:09:45 lr: 0.000035 grad: 0.1077 (0.1118) loss: 0.8069 (0.8122) time: 0.1471 data: 0.0622 max mem: 9390 +Train: [66] [2100/6250] eta: 0:09:33 lr: 0.000035 grad: 0.1032 (0.1118) loss: 0.8131 (0.8121) time: 0.1661 data: 0.0814 max mem: 9390 +Train: [66] [2200/6250] eta: 0:09:21 lr: 0.000035 grad: 0.1074 (0.1118) loss: 0.8149 (0.8120) time: 0.1500 data: 0.0659 max mem: 9390 +Train: [66] [2300/6250] eta: 0:09:11 lr: 0.000035 grad: 0.1087 (0.1116) loss: 0.8148 (0.8120) time: 0.1338 data: 0.0379 max mem: 9390 +Train: [66] [2400/6250] eta: 0:08:57 lr: 0.000035 grad: 0.1085 (0.1115) loss: 0.8115 (0.8120) time: 0.1481 data: 0.0681 max mem: 9390 +Train: [66] [2500/6250] eta: 0:08:42 lr: 0.000035 grad: 0.1106 (0.1115) loss: 0.8056 (0.8120) time: 0.1412 data: 0.0540 max mem: 9390 +Train: [66] [2600/6250] eta: 0:08:28 lr: 0.000035 grad: 0.1107 (0.1115) loss: 0.8161 (0.8121) time: 0.1503 data: 0.0743 max mem: 9390 +Train: [66] [2700/6250] eta: 0:08:14 lr: 0.000035 grad: 0.1092 (0.1115) loss: 0.8171 (0.8121) time: 0.1359 data: 0.0567 max mem: 9390 +Train: [66] [2800/6250] eta: 0:08:01 lr: 0.000035 grad: 0.1089 (0.1116) loss: 0.8155 (0.8121) time: 0.1395 data: 0.0558 max mem: 9390 +Train: [66] [2900/6250] eta: 0:07:45 lr: 0.000035 grad: 0.1100 (0.1116) loss: 0.8117 (0.8122) time: 0.1208 data: 0.0415 max mem: 9390 +Train: [66] [3000/6250] eta: 0:07:31 lr: 0.000035 grad: 0.1097 (0.1116) loss: 0.8168 (0.8122) time: 0.1271 data: 0.0421 max mem: 9390 +Train: [66] [3100/6250] eta: 0:07:18 lr: 0.000035 grad: 0.1038 (0.1116) loss: 0.8118 (0.8123) time: 0.1519 data: 0.0675 max mem: 9390 +Train: [66] [3200/6250] eta: 0:07:04 lr: 0.000035 grad: 0.1052 (0.1115) loss: 0.8187 (0.8124) time: 0.1452 data: 0.0596 max mem: 9390 +Train: [66] [3300/6250] eta: 0:06:51 lr: 0.000035 grad: 0.1059 (0.1116) loss: 0.8156 (0.8125) time: 0.1505 data: 0.0667 max mem: 9390 +Train: [66] [3400/6250] eta: 0:06:37 lr: 0.000035 grad: 0.1044 (0.1115) loss: 0.8139 (0.8125) time: 0.1313 data: 0.0478 max mem: 9390 +Train: [66] [3500/6250] eta: 0:06:23 lr: 0.000034 grad: 0.1111 (0.1115) loss: 0.8096 (0.8126) time: 0.1295 data: 0.0518 max mem: 9390 +Train: [66] [3600/6250] eta: 0:06:08 lr: 0.000034 grad: 0.1074 (0.1114) loss: 0.8061 (0.8126) time: 0.1363 data: 0.0624 max mem: 9390 +Train: [66] [3700/6250] eta: 0:05:54 lr: 0.000034 grad: 0.1105 (0.1114) loss: 0.8124 (0.8126) time: 0.1252 data: 0.0433 max mem: 9390 +Train: [66] [3800/6250] eta: 0:05:39 lr: 0.000034 grad: 0.1097 (0.1114) loss: 0.8075 (0.8125) time: 0.1483 data: 0.0695 max mem: 9390 +Train: [66] [3900/6250] eta: 0:05:24 lr: 0.000034 grad: 0.1114 (0.1114) loss: 0.8107 (0.8125) time: 0.1244 data: 0.0460 max mem: 9390 +Train: [66] [4000/6250] eta: 0:05:10 lr: 0.000034 grad: 0.1121 (0.1114) loss: 0.8098 (0.8125) time: 0.1115 data: 0.0259 max mem: 9390 +Train: [66] [4100/6250] eta: 0:04:56 lr: 0.000034 grad: 0.1134 (0.1115) loss: 0.8149 (0.8125) time: 0.1294 data: 0.0429 max mem: 9390 +Train: [66] [4200/6250] eta: 0:04:42 lr: 0.000034 grad: 0.1067 (0.1115) loss: 0.8167 (0.8125) time: 0.1295 data: 0.0483 max mem: 9390 +Train: [66] [4300/6250] eta: 0:04:28 lr: 0.000034 grad: 0.1073 (0.1115) loss: 0.8114 (0.8125) time: 0.1442 data: 0.0565 max mem: 9390 +Train: [66] [4400/6250] eta: 0:04:14 lr: 0.000034 grad: 0.1142 (0.1116) loss: 0.8101 (0.8125) time: 0.1518 data: 0.0708 max mem: 9390 +Train: [66] [4500/6250] eta: 0:04:00 lr: 0.000034 grad: 0.1083 (0.1117) loss: 0.8128 (0.8124) time: 0.1234 data: 0.0386 max mem: 9390 +Train: [66] [4600/6250] eta: 0:03:46 lr: 0.000034 grad: 0.1145 (0.1118) loss: 0.8064 (0.8124) time: 0.1563 data: 0.0760 max mem: 9390 +Train: [66] [4700/6250] eta: 0:03:33 lr: 0.000034 grad: 0.1149 (0.1120) loss: 0.8128 (0.8124) time: 0.1965 data: 0.1225 max mem: 9390 +Train: [66] [4800/6250] eta: 0:03:19 lr: 0.000034 grad: 0.1132 (0.1121) loss: 0.8140 (0.8123) time: 0.1344 data: 0.0498 max mem: 9390 +Train: [66] [4900/6250] eta: 0:03:06 lr: 0.000034 grad: 0.1114 (0.1121) loss: 0.8082 (0.8124) time: 0.1214 data: 0.0450 max mem: 9390 +Train: [66] [5000/6250] eta: 0:02:52 lr: 0.000034 grad: 0.1163 (0.1123) loss: 0.8043 (0.8124) time: 0.1377 data: 0.0598 max mem: 9390 +Train: [66] [5100/6250] eta: 0:02:38 lr: 0.000034 grad: 0.1173 (0.1124) loss: 0.8075 (0.8124) time: 0.1411 data: 0.0551 max mem: 9390 +Train: [66] [5200/6250] eta: 0:02:24 lr: 0.000034 grad: 0.1157 (0.1124) loss: 0.8126 (0.8124) time: 0.1491 data: 0.0745 max mem: 9390 +Train: [66] [5300/6250] eta: 0:02:10 lr: 0.000034 grad: 0.1098 (0.1125) loss: 0.8147 (0.8124) time: 0.1396 data: 0.0489 max mem: 9390 +Train: [66] [5400/6250] eta: 0:01:57 lr: 0.000034 grad: 0.1095 (0.1125) loss: 0.8138 (0.8124) time: 0.1281 data: 0.0503 max mem: 9390 +Train: [66] [5500/6250] eta: 0:01:43 lr: 0.000034 grad: 0.1105 (0.1125) loss: 0.8066 (0.8123) time: 0.1539 data: 0.0731 max mem: 9390 +Train: [66] [5600/6250] eta: 0:01:29 lr: 0.000034 grad: 0.1107 (0.1125) loss: 0.8080 (0.8123) time: 0.1416 data: 0.0669 max mem: 9390 +Train: [66] [5700/6250] eta: 0:01:15 lr: 0.000034 grad: 0.1085 (0.1126) loss: 0.8143 (0.8123) time: 0.1234 data: 0.0360 max mem: 9390 +Train: [66] [5800/6250] eta: 0:01:01 lr: 0.000034 grad: 0.0995 (0.1125) loss: 0.8183 (0.8123) time: 0.1341 data: 0.0556 max mem: 9390 +Train: [66] [5900/6250] eta: 0:00:48 lr: 0.000034 grad: 0.1189 (0.1125) loss: 0.8187 (0.8123) time: 0.1480 data: 0.0607 max mem: 9390 +Train: [66] [6000/6250] eta: 0:00:34 lr: 0.000034 grad: 0.1146 (0.1125) loss: 0.8111 (0.8123) time: 0.1366 data: 0.0558 max mem: 9390 +Train: [66] [6100/6250] eta: 0:00:20 lr: 0.000034 grad: 0.1145 (0.1126) loss: 0.8147 (0.8123) time: 0.1306 data: 0.0493 max mem: 9390 +Train: [66] [6200/6250] eta: 0:00:06 lr: 0.000034 grad: 0.1090 (0.1126) loss: 0.8134 (0.8123) time: 0.2335 data: 0.1434 max mem: 9390 +Train: [66] [6249/6250] eta: 0:00:00 lr: 0.000034 grad: 0.1124 (0.1126) loss: 0.8059 (0.8123) time: 0.1340 data: 0.0468 max mem: 9390 +Train: [66] Total time: 0:14:31 (0.1395 s / it) +Averaged stats: lr: 0.000034 grad: 0.1124 (0.1126) loss: 0.8059 (0.8123) +Eval (hcp-train-subset): [66] [ 0/62] eta: 0:04:50 loss: 0.8348 (0.8348) time: 4.6808 data: 4.6512 max mem: 9390 +Eval (hcp-train-subset): [66] [61/62] eta: 0:00:00 loss: 0.8280 (0.8309) time: 0.1203 data: 0.0939 max mem: 9390 +Eval (hcp-train-subset): [66] Total time: 0:00:12 (0.2043 s / it) +Averaged stats (hcp-train-subset): loss: 0.8280 (0.8309) +Eval (hcp-val): [66] [ 0/62] eta: 0:03:59 loss: 0.8301 (0.8301) time: 3.8644 data: 3.7781 max mem: 9390 +Eval (hcp-val): [66] [61/62] eta: 0:00:00 loss: 0.8303 (0.8328) time: 0.1423 data: 0.1174 max mem: 9390 +Eval (hcp-val): [66] Total time: 0:00:13 (0.2114 s / it) +Averaged stats (hcp-val): loss: 0.8303 (0.8328) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +Train: [67] [ 0/6250] eta: 10:47:48 lr: 0.000034 grad: 0.1805 (0.1805) loss: 0.8072 (0.8072) time: 6.2190 data: 6.1244 max mem: 9390 +Train: [67] [ 100/6250] eta: 0:20:18 lr: 0.000034 grad: 0.1050 (0.1277) loss: 0.8180 (0.8235) time: 0.1517 data: 0.0537 max mem: 9390 +Train: [67] [ 200/6250] eta: 0:17:24 lr: 0.000034 grad: 0.0951 (0.1201) loss: 0.8307 (0.8243) time: 0.1635 data: 0.0774 max mem: 9390 +Train: [67] [ 300/6250] eta: 0:16:01 lr: 0.000034 grad: 0.1067 (0.1159) loss: 0.8223 (0.8236) time: 0.1269 data: 0.0424 max mem: 9390 +Train: [67] [ 400/6250] eta: 0:15:10 lr: 0.000034 grad: 0.1084 (0.1146) loss: 0.8207 (0.8231) time: 0.1507 data: 0.0635 max mem: 9390 +Train: [67] [ 500/6250] eta: 0:14:31 lr: 0.000034 grad: 0.1078 (0.1135) loss: 0.8212 (0.8223) time: 0.1465 data: 0.0626 max mem: 9390 +Train: [67] [ 600/6250] eta: 0:13:54 lr: 0.000033 grad: 0.1148 (0.1127) loss: 0.8124 (0.8215) time: 0.1342 data: 0.0437 max mem: 9390 +Train: [67] [ 700/6250] eta: 0:13:24 lr: 0.000033 grad: 0.1072 (0.1117) loss: 0.8235 (0.8212) time: 0.1384 data: 0.0549 max mem: 9390 +Train: [67] [ 800/6250] eta: 0:13:03 lr: 0.000033 grad: 0.1006 (0.1113) loss: 0.8256 (0.8209) time: 0.1223 data: 0.0344 max mem: 9390 +Train: [67] [ 900/6250] eta: 0:12:46 lr: 0.000033 grad: 0.1071 (0.1110) loss: 0.8104 (0.8202) time: 0.1042 data: 0.0067 max mem: 9390 +Train: [67] [1000/6250] eta: 0:12:21 lr: 0.000033 grad: 0.1021 (0.1107) loss: 0.8162 (0.8200) time: 0.1158 data: 0.0339 max mem: 9390 +Train: [67] [1100/6250] eta: 0:12:02 lr: 0.000033 grad: 0.1042 (0.1104) loss: 0.8149 (0.8197) time: 0.1215 data: 0.0384 max mem: 9390 +Train: [67] [1200/6250] eta: 0:11:46 lr: 0.000033 grad: 0.1035 (0.1101) loss: 0.8143 (0.8192) time: 0.1136 data: 0.0403 max mem: 9390 +Train: [67] [1300/6250] eta: 0:11:29 lr: 0.000033 grad: 0.1030 (0.1099) loss: 0.8175 (0.8188) time: 0.1214 data: 0.0420 max mem: 9390 +Train: [67] [1400/6250] eta: 0:11:13 lr: 0.000033 grad: 0.1063 (0.1100) loss: 0.8142 (0.8184) time: 0.1465 data: 0.0711 max mem: 9390 +Train: [67] [1500/6250] eta: 0:10:55 lr: 0.000033 grad: 0.1039 (0.1099) loss: 0.8109 (0.8179) time: 0.1158 data: 0.0389 max mem: 9390 +Train: [67] [1600/6250] eta: 0:10:38 lr: 0.000033 grad: 0.1020 (0.1098) loss: 0.8095 (0.8176) time: 0.1084 data: 0.0280 max mem: 9390 +Train: [67] [1700/6250] eta: 0:10:22 lr: 0.000033 grad: 0.1092 (0.1099) loss: 0.8158 (0.8174) time: 0.1261 data: 0.0408 max mem: 9390 +Train: [67] [1800/6250] eta: 0:10:06 lr: 0.000033 grad: 0.1115 (0.1100) loss: 0.8103 (0.8170) time: 0.1254 data: 0.0443 max mem: 9390 +Train: [67] [1900/6250] eta: 0:09:50 lr: 0.000033 grad: 0.1160 (0.1102) loss: 0.8060 (0.8166) time: 0.1267 data: 0.0532 max mem: 9390 +Train: [67] [2000/6250] eta: 0:09:37 lr: 0.000033 grad: 0.1023 (0.1103) loss: 0.8149 (0.8164) time: 0.1278 data: 0.0495 max mem: 9390 +Train: [67] [2100/6250] eta: 0:09:23 lr: 0.000033 grad: 0.1087 (0.1103) loss: 0.8193 (0.8161) time: 0.1382 data: 0.0626 max mem: 9390 +Train: [67] [2200/6250] eta: 0:09:10 lr: 0.000033 grad: 0.1100 (0.1104) loss: 0.8080 (0.8159) time: 0.1314 data: 0.0484 max mem: 9390 +Train: [67] [2300/6250] eta: 0:08:57 lr: 0.000033 grad: 0.1109 (0.1105) loss: 0.8068 (0.8157) time: 0.1259 data: 0.0439 max mem: 9390 +Train: [67] [2400/6250] eta: 0:08:43 lr: 0.000033 grad: 0.1108 (0.1106) loss: 0.8266 (0.8156) time: 0.1143 data: 0.0316 max mem: 9390 +Train: [67] [2500/6250] eta: 0:08:30 lr: 0.000033 grad: 0.1083 (0.1107) loss: 0.8165 (0.8155) time: 0.1388 data: 0.0639 max mem: 9390 +Train: [67] [2600/6250] eta: 0:08:16 lr: 0.000033 grad: 0.1113 (0.1109) loss: 0.8085 (0.8153) time: 0.1375 data: 0.0607 max mem: 9390 +Train: [67] [2700/6250] eta: 0:08:03 lr: 0.000033 grad: 0.1192 (0.1111) loss: 0.8111 (0.8152) time: 0.1422 data: 0.0663 max mem: 9390 +Train: [67] [2800/6250] eta: 0:07:49 lr: 0.000033 grad: 0.1110 (0.1112) loss: 0.8204 (0.8151) time: 0.1416 data: 0.0650 max mem: 9390 +Train: [67] [2900/6250] eta: 0:07:35 lr: 0.000033 grad: 0.1049 (0.1113) loss: 0.8173 (0.8150) time: 0.1306 data: 0.0570 max mem: 9390 +Train: [67] [3000/6250] eta: 0:07:24 lr: 0.000033 grad: 0.1159 (0.1113) loss: 0.8150 (0.8150) time: 0.1494 data: 0.0722 max mem: 9390 +Train: [67] [3100/6250] eta: 0:07:12 lr: 0.000033 grad: 0.1089 (0.1114) loss: 0.8153 (0.8149) time: 0.1518 data: 0.0754 max mem: 9390 +Train: [67] [3200/6250] eta: 0:06:59 lr: 0.000033 grad: 0.1109 (0.1116) loss: 0.8092 (0.8148) time: 0.1432 data: 0.0654 max mem: 9390 +Train: [67] [3300/6250] eta: 0:06:46 lr: 0.000033 grad: 0.1086 (0.1118) loss: 0.8163 (0.8147) time: 0.1203 data: 0.0394 max mem: 9390 +Train: [67] [3400/6250] eta: 0:06:32 lr: 0.000033 grad: 0.1094 (0.1117) loss: 0.8131 (0.8147) time: 0.1552 data: 0.0754 max mem: 9390 +Train: [67] [3500/6250] eta: 0:06:19 lr: 0.000033 grad: 0.1061 (0.1118) loss: 0.8075 (0.8147) time: 0.1648 data: 0.0884 max mem: 9390 +Train: [67] [3600/6250] eta: 0:06:04 lr: 0.000033 grad: 0.1069 (0.1119) loss: 0.8140 (0.8146) time: 0.1271 data: 0.0374 max mem: 9390 +Train: [67] [3700/6250] eta: 0:05:50 lr: 0.000033 grad: 0.1103 (0.1119) loss: 0.8128 (0.8146) time: 0.1324 data: 0.0471 max mem: 9390 +Train: [67] [3800/6250] eta: 0:05:36 lr: 0.000033 grad: 0.1115 (0.1120) loss: 0.8085 (0.8145) time: 0.1306 data: 0.0478 max mem: 9390 +Train: [67] [3900/6250] eta: 0:05:21 lr: 0.000033 grad: 0.1114 (0.1121) loss: 0.8073 (0.8144) time: 0.1232 data: 0.0413 max mem: 9390 +Train: [67] [4000/6250] eta: 0:05:06 lr: 0.000032 grad: 0.1129 (0.1122) loss: 0.8127 (0.8142) time: 0.1139 data: 0.0300 max mem: 9390 +Train: [67] [4100/6250] eta: 0:04:53 lr: 0.000032 grad: 0.1117 (0.1123) loss: 0.8191 (0.8142) time: 0.1051 data: 0.0237 max mem: 9390 +Train: [67] [4200/6250] eta: 0:04:39 lr: 0.000032 grad: 0.1142 (0.1124) loss: 0.8122 (0.8141) time: 0.1339 data: 0.0580 max mem: 9390 +Train: [67] [4300/6250] eta: 0:04:25 lr: 0.000032 grad: 0.1150 (0.1124) loss: 0.8139 (0.8141) time: 0.1342 data: 0.0570 max mem: 9390 +Train: [67] [4400/6250] eta: 0:04:13 lr: 0.000032 grad: 0.1100 (0.1126) loss: 0.8171 (0.8141) time: 0.2342 data: 0.1547 max mem: 9390 +Train: [67] [4500/6250] eta: 0:03:58 lr: 0.000032 grad: 0.1158 (0.1126) loss: 0.8087 (0.8141) time: 0.1334 data: 0.0535 max mem: 9390 +Train: [67] [4600/6250] eta: 0:03:45 lr: 0.000032 grad: 0.1163 (0.1127) loss: 0.8098 (0.8140) time: 0.1403 data: 0.0535 max mem: 9390 +Train: [67] [4700/6250] eta: 0:03:32 lr: 0.000032 grad: 0.1149 (0.1128) loss: 0.8075 (0.8140) time: 0.1595 data: 0.0654 max mem: 9390 +Train: [67] [4800/6250] eta: 0:03:18 lr: 0.000032 grad: 0.1078 (0.1129) loss: 0.8128 (0.8139) time: 0.1230 data: 0.0394 max mem: 9390 +Train: [67] [4900/6250] eta: 0:03:04 lr: 0.000032 grad: 0.1180 (0.1130) loss: 0.8029 (0.8139) time: 0.1210 data: 0.0409 max mem: 9390 +Train: [67] [5000/6250] eta: 0:02:50 lr: 0.000032 grad: 0.1147 (0.1130) loss: 0.8160 (0.8139) time: 0.1361 data: 0.0556 max mem: 9390 +Train: [67] [5100/6250] eta: 0:02:37 lr: 0.000032 grad: 0.1136 (0.1130) loss: 0.8168 (0.8139) time: 0.1328 data: 0.0538 max mem: 9390 +Train: [67] [5200/6250] eta: 0:02:23 lr: 0.000032 grad: 0.1198 (0.1132) loss: 0.8030 (0.8138) time: 0.1435 data: 0.0685 max mem: 9390 +Train: [67] [5300/6250] eta: 0:02:10 lr: 0.000032 grad: 0.1141 (0.1133) loss: 0.8096 (0.8137) time: 0.1308 data: 0.0557 max mem: 9390 +Train: [67] [5400/6250] eta: 0:01:56 lr: 0.000032 grad: 0.1202 (0.1134) loss: 0.8152 (0.8137) time: 0.1361 data: 0.0560 max mem: 9390 +Train: [67] [5500/6250] eta: 0:01:42 lr: 0.000032 grad: 0.1083 (0.1135) loss: 0.8133 (0.8136) time: 0.1301 data: 0.0519 max mem: 9390 +Train: [67] [5600/6250] eta: 0:01:29 lr: 0.000032 grad: 0.1127 (0.1136) loss: 0.8122 (0.8135) time: 0.1215 data: 0.0351 max mem: 9390 +Train: [67] [5700/6250] eta: 0:01:15 lr: 0.000032 grad: 0.1200 (0.1136) loss: 0.8097 (0.8135) time: 0.1337 data: 0.0564 max mem: 9390 +Train: [67] [5800/6250] eta: 0:01:01 lr: 0.000032 grad: 0.1026 (0.1136) loss: 0.8134 (0.8134) time: 0.1042 data: 0.0300 max mem: 9390 +Train: [67] [5900/6250] eta: 0:00:47 lr: 0.000032 grad: 0.1064 (0.1136) loss: 0.8158 (0.8134) time: 0.1348 data: 0.0543 max mem: 9390 +Train: [67] [6000/6250] eta: 0:00:34 lr: 0.000032 grad: 0.1064 (0.1135) loss: 0.8101 (0.8134) time: 0.1243 data: 0.0402 max mem: 9390 +Train: [67] [6100/6250] eta: 0:00:20 lr: 0.000032 grad: 0.1134 (0.1135) loss: 0.8126 (0.8134) time: 0.1486 data: 0.0655 max mem: 9390 +Train: [67] [6200/6250] eta: 0:00:06 lr: 0.000032 grad: 0.1132 (0.1135) loss: 0.8084 (0.8134) time: 0.1260 data: 0.0504 max mem: 9390 +Train: [67] [6249/6250] eta: 0:00:00 lr: 0.000032 grad: 0.1051 (0.1135) loss: 0.8209 (0.8134) time: 0.1488 data: 0.0732 max mem: 9390 +Train: [67] Total time: 0:14:23 (0.1381 s / it) +Averaged stats: lr: 0.000032 grad: 0.1051 (0.1135) loss: 0.8209 (0.8134) +Eval (hcp-train-subset): [67] [ 0/62] eta: 0:04:26 loss: 0.8373 (0.8373) time: 4.2933 data: 4.2492 max mem: 9390 +Eval (hcp-train-subset): [67] [61/62] eta: 0:00:00 loss: 0.8274 (0.8294) time: 0.1211 data: 0.0963 max mem: 9390 +Eval (hcp-train-subset): [67] Total time: 0:00:12 (0.1970 s / it) +Averaged stats (hcp-train-subset): loss: 0.8274 (0.8294) +Eval (hcp-val): [67] [ 0/62] eta: 0:04:19 loss: 0.8277 (0.8277) time: 4.1919 data: 4.1639 max mem: 9390 +Eval (hcp-val): [67] [61/62] eta: 0:00:00 loss: 0.8312 (0.8322) time: 0.1322 data: 0.1075 max mem: 9390 +Eval (hcp-val): [67] Total time: 0:00:12 (0.2006 s / it) +Averaged stats (hcp-val): loss: 0.8312 (0.8322) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +Train: [68] [ 0/6250] eta: 9:34:46 lr: 0.000032 grad: 0.0758 (0.0758) loss: 0.8558 (0.8558) time: 5.5178 data: 5.4012 max mem: 9390 +Train: [68] [ 100/6250] eta: 0:21:16 lr: 0.000032 grad: 0.1056 (0.1449) loss: 0.8236 (0.8264) time: 0.1585 data: 0.0684 max mem: 9390 +Train: [68] [ 200/6250] eta: 0:17:48 lr: 0.000032 grad: 0.1171 (0.1298) loss: 0.8259 (0.8242) time: 0.1310 data: 0.0431 max mem: 9390 +Train: [68] [ 300/6250] eta: 0:16:55 lr: 0.000032 grad: 0.1176 (0.1258) loss: 0.8151 (0.8214) time: 0.1374 data: 0.0488 max mem: 9390 +Train: [68] [ 400/6250] eta: 0:16:03 lr: 0.000032 grad: 0.1064 (0.1218) loss: 0.8171 (0.8208) time: 0.1393 data: 0.0522 max mem: 9390 +Train: [68] [ 500/6250] eta: 0:15:25 lr: 0.000032 grad: 0.1043 (0.1196) loss: 0.8112 (0.8197) time: 0.1432 data: 0.0643 max mem: 9390 +Train: [68] [ 600/6250] eta: 0:14:44 lr: 0.000032 grad: 0.1067 (0.1181) loss: 0.8144 (0.8191) time: 0.1462 data: 0.0596 max mem: 9390 +Train: [68] [ 700/6250] eta: 0:14:10 lr: 0.000032 grad: 0.1032 (0.1169) loss: 0.8189 (0.8186) time: 0.1386 data: 0.0526 max mem: 9390 +Train: [68] [ 800/6250] eta: 0:13:41 lr: 0.000032 grad: 0.1001 (0.1161) loss: 0.8169 (0.8183) time: 0.1303 data: 0.0548 max mem: 9390 +Train: [68] [ 900/6250] eta: 0:13:11 lr: 0.000032 grad: 0.1015 (0.1150) loss: 0.8235 (0.8183) time: 0.1450 data: 0.0657 max mem: 9390 +Train: [68] [1000/6250] eta: 0:12:46 lr: 0.000032 grad: 0.1046 (0.1144) loss: 0.8180 (0.8179) time: 0.1080 data: 0.0305 max mem: 9390 +Train: [68] [1100/6250] eta: 0:12:18 lr: 0.000032 grad: 0.1123 (0.1138) loss: 0.8150 (0.8177) time: 0.1141 data: 0.0322 max mem: 9390 +Train: [68] [1200/6250] eta: 0:11:56 lr: 0.000032 grad: 0.1125 (0.1135) loss: 0.8138 (0.8173) time: 0.1307 data: 0.0450 max mem: 9390 +Train: [68] [1300/6250] eta: 0:11:38 lr: 0.000031 grad: 0.1045 (0.1134) loss: 0.8109 (0.8169) time: 0.1315 data: 0.0463 max mem: 9390 +Train: [68] [1400/6250] eta: 0:11:17 lr: 0.000031 grad: 0.1081 (0.1132) loss: 0.8175 (0.8166) time: 0.1182 data: 0.0411 max mem: 9390 +Train: [68] [1500/6250] eta: 0:10:59 lr: 0.000031 grad: 0.1086 (0.1131) loss: 0.8141 (0.8163) time: 0.1176 data: 0.0415 max mem: 9390 +Train: [68] [1600/6250] eta: 0:10:39 lr: 0.000031 grad: 0.1144 (0.1131) loss: 0.8169 (0.8161) time: 0.1166 data: 0.0303 max mem: 9390 +Train: [68] [1700/6250] eta: 0:10:25 lr: 0.000031 grad: 0.1077 (0.1130) loss: 0.8141 (0.8160) time: 0.1425 data: 0.0630 max mem: 9390 +Train: [68] [1800/6250] eta: 0:10:07 lr: 0.000031 grad: 0.1091 (0.1129) loss: 0.8108 (0.8160) time: 0.1039 data: 0.0283 max mem: 9390 +Train: [68] [1900/6250] eta: 0:09:52 lr: 0.000031 grad: 0.1158 (0.1129) loss: 0.8173 (0.8158) time: 0.1307 data: 0.0527 max mem: 9390 +Train: [68] [2000/6250] eta: 0:09:39 lr: 0.000031 grad: 0.1088 (0.1128) loss: 0.8094 (0.8158) time: 0.1383 data: 0.0560 max mem: 9390 +Train: [68] [2100/6250] eta: 0:09:26 lr: 0.000031 grad: 0.1107 (0.1128) loss: 0.8102 (0.8156) time: 0.1492 data: 0.0724 max mem: 9390 +Train: [68] [2200/6250] eta: 0:09:13 lr: 0.000031 grad: 0.1055 (0.1129) loss: 0.8104 (0.8153) time: 0.1451 data: 0.0636 max mem: 9390 +Train: [68] [2300/6250] eta: 0:08:58 lr: 0.000031 grad: 0.1113 (0.1129) loss: 0.8159 (0.8152) time: 0.1348 data: 0.0541 max mem: 9390 +Train: [68] [2400/6250] eta: 0:08:46 lr: 0.000031 grad: 0.1107 (0.1130) loss: 0.8134 (0.8151) time: 0.1679 data: 0.0810 max mem: 9390 +Train: [68] [2500/6250] eta: 0:08:34 lr: 0.000031 grad: 0.1046 (0.1130) loss: 0.8174 (0.8149) time: 0.1082 data: 0.0181 max mem: 9390 +Train: [68] [2600/6250] eta: 0:08:21 lr: 0.000031 grad: 0.1106 (0.1130) loss: 0.8101 (0.8149) time: 0.1345 data: 0.0547 max mem: 9390 +Train: [68] [2700/6250] eta: 0:08:07 lr: 0.000031 grad: 0.1064 (0.1130) loss: 0.8150 (0.8148) time: 0.1224 data: 0.0433 max mem: 9390 +Train: [68] [2800/6250] eta: 0:07:53 lr: 0.000031 grad: 0.1089 (0.1131) loss: 0.8224 (0.8149) time: 0.1554 data: 0.0825 max mem: 9390 +Train: [68] [2900/6250] eta: 0:07:41 lr: 0.000031 grad: 0.1053 (0.1132) loss: 0.8140 (0.8150) time: 0.1258 data: 0.0507 max mem: 9390 +Train: [68] [3000/6250] eta: 0:07:28 lr: 0.000031 grad: 0.1128 (0.1133) loss: 0.8047 (0.8149) time: 0.1810 data: 0.0904 max mem: 9390 +Train: [68] [3100/6250] eta: 0:07:16 lr: 0.000031 grad: 0.1122 (0.1134) loss: 0.8123 (0.8148) time: 0.1618 data: 0.0886 max mem: 9390 +Train: [68] [3200/6250] eta: 0:07:02 lr: 0.000031 grad: 0.1098 (0.1133) loss: 0.8155 (0.8147) time: 0.1352 data: 0.0490 max mem: 9390 +Train: [68] [3300/6250] eta: 0:06:48 lr: 0.000031 grad: 0.1096 (0.1133) loss: 0.8186 (0.8148) time: 0.1263 data: 0.0494 max mem: 9390 +Train: [68] [3400/6250] eta: 0:06:34 lr: 0.000031 grad: 0.1107 (0.1134) loss: 0.8141 (0.8148) time: 0.1238 data: 0.0490 max mem: 9390 +Train: [68] [3500/6250] eta: 0:06:19 lr: 0.000031 grad: 0.1037 (0.1134) loss: 0.8189 (0.8149) time: 0.1221 data: 0.0428 max mem: 9390 +Train: [68] [3600/6250] eta: 0:06:05 lr: 0.000031 grad: 0.1088 (0.1133) loss: 0.8161 (0.8149) time: 0.1430 data: 0.0585 max mem: 9390 +Train: [68] [3700/6250] eta: 0:05:50 lr: 0.000031 grad: 0.1135 (0.1132) loss: 0.8145 (0.8150) time: 0.1308 data: 0.0408 max mem: 9390 +Train: [68] [3800/6250] eta: 0:05:36 lr: 0.000031 grad: 0.1111 (0.1133) loss: 0.8169 (0.8150) time: 0.1313 data: 0.0477 max mem: 9390 +Train: [68] [3900/6250] eta: 0:05:21 lr: 0.000031 grad: 0.1132 (0.1133) loss: 0.8173 (0.8151) time: 0.1273 data: 0.0441 max mem: 9390 +Train: [68] [4000/6250] eta: 0:05:07 lr: 0.000031 grad: 0.1152 (0.1133) loss: 0.8119 (0.8151) time: 0.1253 data: 0.0509 max mem: 9390 +Train: [68] [4100/6250] eta: 0:04:53 lr: 0.000031 grad: 0.1167 (0.1133) loss: 0.8166 (0.8151) time: 0.1424 data: 0.0639 max mem: 9390 +Train: [68] [4200/6250] eta: 0:04:39 lr: 0.000031 grad: 0.1084 (0.1134) loss: 0.8215 (0.8151) time: 0.1225 data: 0.0420 max mem: 9390 +Train: [68] [4300/6250] eta: 0:04:25 lr: 0.000031 grad: 0.1087 (0.1134) loss: 0.8189 (0.8152) time: 0.1368 data: 0.0589 max mem: 9390 +Train: [68] [4400/6250] eta: 0:04:12 lr: 0.000031 grad: 0.1082 (0.1135) loss: 0.8204 (0.8153) time: 0.1433 data: 0.0595 max mem: 9390 +Train: [68] [4500/6250] eta: 0:03:58 lr: 0.000031 grad: 0.1094 (0.1135) loss: 0.8146 (0.8153) time: 0.1429 data: 0.0605 max mem: 9390 +Train: [68] [4600/6250] eta: 0:03:44 lr: 0.000031 grad: 0.1061 (0.1135) loss: 0.8189 (0.8153) time: 0.1439 data: 0.0669 max mem: 9390 +Train: [68] [4700/6250] eta: 0:03:30 lr: 0.000031 grad: 0.1104 (0.1135) loss: 0.8184 (0.8153) time: 0.1333 data: 0.0510 max mem: 9390 +Train: [68] [4800/6250] eta: 0:03:17 lr: 0.000030 grad: 0.1141 (0.1136) loss: 0.8177 (0.8153) time: 0.1299 data: 0.0517 max mem: 9390 +Train: [68] [4900/6250] eta: 0:03:03 lr: 0.000030 grad: 0.1187 (0.1137) loss: 0.8160 (0.8153) time: 0.1374 data: 0.0595 max mem: 9390 +Train: [68] [5000/6250] eta: 0:02:50 lr: 0.000030 grad: 0.1115 (0.1137) loss: 0.8216 (0.8154) time: 0.1163 data: 0.0374 max mem: 9390 +Train: [68] [5100/6250] eta: 0:02:36 lr: 0.000030 grad: 0.1127 (0.1137) loss: 0.8141 (0.8154) time: 0.1270 data: 0.0438 max mem: 9390 +Train: [68] [5200/6250] eta: 0:02:23 lr: 0.000030 grad: 0.1080 (0.1137) loss: 0.8165 (0.8154) time: 0.1355 data: 0.0466 max mem: 9390 +Train: [68] [5300/6250] eta: 0:02:09 lr: 0.000030 grad: 0.1065 (0.1137) loss: 0.8181 (0.8155) time: 0.1381 data: 0.0654 max mem: 9390 +Train: [68] [5400/6250] eta: 0:01:56 lr: 0.000030 grad: 0.1080 (0.1137) loss: 0.8117 (0.8155) time: 0.1512 data: 0.0692 max mem: 9390 +Train: [68] [5500/6250] eta: 0:01:42 lr: 0.000030 grad: 0.1090 (0.1138) loss: 0.8182 (0.8155) time: 0.1443 data: 0.0650 max mem: 9390 +Train: [68] [5600/6250] eta: 0:01:28 lr: 0.000030 grad: 0.1140 (0.1139) loss: 0.8193 (0.8155) time: 0.1354 data: 0.0527 max mem: 9390 +Train: [68] [5700/6250] eta: 0:01:15 lr: 0.000030 grad: 0.1151 (0.1139) loss: 0.8146 (0.8155) time: 0.1213 data: 0.0391 max mem: 9390 +Train: [68] [5800/6250] eta: 0:01:01 lr: 0.000030 grad: 0.1146 (0.1140) loss: 0.8146 (0.8155) time: 0.1596 data: 0.0559 max mem: 9390 +Train: [68] [5900/6250] eta: 0:00:48 lr: 0.000030 grad: 0.1127 (0.1140) loss: 0.8176 (0.8154) time: 0.1585 data: 0.0770 max mem: 9390 +Train: [68] [6000/6250] eta: 0:00:34 lr: 0.000030 grad: 0.1192 (0.1141) loss: 0.8139 (0.8153) time: 0.1380 data: 0.0634 max mem: 9390 +Train: [68] [6100/6250] eta: 0:00:20 lr: 0.000030 grad: 0.1160 (0.1143) loss: 0.8105 (0.8153) time: 0.1228 data: 0.0445 max mem: 9390 +Train: [68] [6200/6250] eta: 0:00:06 lr: 0.000030 grad: 0.1155 (0.1144) loss: 0.8117 (0.8152) time: 0.1360 data: 0.0593 max mem: 9390 +Train: [68] [6249/6250] eta: 0:00:00 lr: 0.000030 grad: 0.1081 (0.1144) loss: 0.8194 (0.8152) time: 0.1268 data: 0.0471 max mem: 9390 +Train: [68] Total time: 0:14:25 (0.1386 s / it) +Averaged stats: lr: 0.000030 grad: 0.1081 (0.1144) loss: 0.8194 (0.8152) +Eval (hcp-train-subset): [68] [ 0/62] eta: 0:03:55 loss: 0.8380 (0.8380) time: 3.8064 data: 3.7497 max mem: 9390 +Eval (hcp-train-subset): [68] [61/62] eta: 0:00:00 loss: 0.8297 (0.8311) time: 0.1070 data: 0.0805 max mem: 9390 +Eval (hcp-train-subset): [68] Total time: 0:00:12 (0.1981 s / it) +Averaged stats (hcp-train-subset): loss: 0.8297 (0.8311) +Eval (hcp-val): [68] [ 0/62] eta: 0:03:38 loss: 0.8314 (0.8314) time: 3.5276 data: 3.4680 max mem: 9390 +Eval (hcp-val): [68] [61/62] eta: 0:00:00 loss: 0.8306 (0.8325) time: 0.1166 data: 0.0915 max mem: 9390 +Eval (hcp-val): [68] Total time: 0:00:12 (0.1992 s / it) +Averaged stats (hcp-val): loss: 0.8306 (0.8325) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +Train: [69] [ 0/6250] eta: 8:16:42 lr: 0.000030 grad: 0.1771 (0.1771) loss: 0.8553 (0.8553) time: 4.7685 data: 4.5456 max mem: 9390 +Train: [69] [ 100/6250] eta: 0:20:37 lr: 0.000030 grad: 0.1165 (0.1436) loss: 0.8223 (0.8238) time: 0.1382 data: 0.0366 max mem: 9390 +Train: [69] [ 200/6250] eta: 0:18:05 lr: 0.000030 grad: 0.1334 (0.1382) loss: 0.8013 (0.8180) time: 0.1619 data: 0.0553 max mem: 9390 +Train: [69] [ 300/6250] eta: 0:17:05 lr: 0.000030 grad: 0.1264 (0.1335) loss: 0.8010 (0.8144) time: 0.1625 data: 0.0655 max mem: 9390 +Train: [69] [ 400/6250] eta: 0:16:08 lr: 0.000030 grad: 0.1076 (0.1298) loss: 0.8192 (0.8133) time: 0.1716 data: 0.0894 max mem: 9390 +Train: [69] [ 500/6250] eta: 0:15:21 lr: 0.000030 grad: 0.1131 (0.1273) loss: 0.8079 (0.8133) time: 0.1260 data: 0.0476 max mem: 9390 +Train: [69] [ 600/6250] eta: 0:14:39 lr: 0.000030 grad: 0.1280 (0.1260) loss: 0.8141 (0.8129) time: 0.1151 data: 0.0245 max mem: 9390 +Train: [69] [ 700/6250] eta: 0:14:03 lr: 0.000030 grad: 0.1109 (0.1253) loss: 0.8109 (0.8118) time: 0.1245 data: 0.0371 max mem: 9390 +Train: [69] [ 800/6250] eta: 0:13:32 lr: 0.000030 grad: 0.1057 (0.1244) loss: 0.8106 (0.8112) time: 0.1329 data: 0.0487 max mem: 9390 +Train: [69] [ 900/6250] eta: 0:13:05 lr: 0.000030 grad: 0.1222 (0.1237) loss: 0.8035 (0.8108) time: 0.1381 data: 0.0553 max mem: 9390 +Train: [69] [1000/6250] eta: 0:12:41 lr: 0.000030 grad: 0.1086 (0.1228) loss: 0.8104 (0.8106) time: 0.1350 data: 0.0554 max mem: 9390 +Train: [69] [1100/6250] eta: 0:12:20 lr: 0.000030 grad: 0.1106 (0.1223) loss: 0.8117 (0.8103) time: 0.1320 data: 0.0569 max mem: 9390 +Train: [69] [1200/6250] eta: 0:12:00 lr: 0.000030 grad: 0.1156 (0.1218) loss: 0.8062 (0.8101) time: 0.1258 data: 0.0399 max mem: 9390 +Train: [69] [1300/6250] eta: 0:11:42 lr: 0.000030 grad: 0.1089 (0.1211) loss: 0.8122 (0.8101) time: 0.1296 data: 0.0506 max mem: 9390 +Train: [69] [1400/6250] eta: 0:11:24 lr: 0.000030 grad: 0.1174 (0.1207) loss: 0.8146 (0.8102) time: 0.1413 data: 0.0667 max mem: 9390 +Train: [69] [1500/6250] eta: 0:11:06 lr: 0.000030 grad: 0.1124 (0.1202) loss: 0.8085 (0.8102) time: 0.1398 data: 0.0577 max mem: 9390 +Train: [69] [1600/6250] eta: 0:10:45 lr: 0.000030 grad: 0.1228 (0.1199) loss: 0.8114 (0.8102) time: 0.1235 data: 0.0471 max mem: 9390 +Train: [69] [1700/6250] eta: 0:10:27 lr: 0.000030 grad: 0.1117 (0.1196) loss: 0.8115 (0.8102) time: 0.1201 data: 0.0396 max mem: 9390 +Train: [69] [1800/6250] eta: 0:10:10 lr: 0.000030 grad: 0.1111 (0.1194) loss: 0.8202 (0.8105) time: 0.1173 data: 0.0272 max mem: 9390 +Train: [69] [1900/6250] eta: 0:09:56 lr: 0.000030 grad: 0.1094 (0.1192) loss: 0.8128 (0.8105) time: 0.1268 data: 0.0404 max mem: 9390 +Train: [69] [2000/6250] eta: 0:09:42 lr: 0.000030 grad: 0.1152 (0.1190) loss: 0.8136 (0.8106) time: 0.1475 data: 0.0667 max mem: 9390 +Train: [69] [2100/6250] eta: 0:09:33 lr: 0.000029 grad: 0.1169 (0.1189) loss: 0.8110 (0.8107) time: 0.1243 data: 0.0297 max mem: 9390 +Train: [69] [2200/6250] eta: 0:09:20 lr: 0.000029 grad: 0.1102 (0.1187) loss: 0.8174 (0.8107) time: 0.1671 data: 0.0827 max mem: 9390 +Train: [69] [2300/6250] eta: 0:09:08 lr: 0.000029 grad: 0.1180 (0.1186) loss: 0.8112 (0.8108) time: 0.1642 data: 0.0879 max mem: 9390 +Train: [69] [2400/6250] eta: 0:08:52 lr: 0.000029 grad: 0.1126 (0.1185) loss: 0.8155 (0.8108) time: 0.1298 data: 0.0579 max mem: 9390 +Train: [69] [2500/6250] eta: 0:08:38 lr: 0.000029 grad: 0.1198 (0.1185) loss: 0.8061 (0.8107) time: 0.1400 data: 0.0490 max mem: 9390 +Train: [69] [2600/6250] eta: 0:08:23 lr: 0.000029 grad: 0.1172 (0.1184) loss: 0.8095 (0.8107) time: 0.1538 data: 0.0769 max mem: 9390 +Train: [69] [2700/6250] eta: 0:08:09 lr: 0.000029 grad: 0.1097 (0.1183) loss: 0.8169 (0.8108) time: 0.1434 data: 0.0633 max mem: 9390 +Train: [69] [2800/6250] eta: 0:07:57 lr: 0.000029 grad: 0.1191 (0.1183) loss: 0.8059 (0.8107) time: 0.1462 data: 0.0692 max mem: 9390 +Train: [69] [2900/6250] eta: 0:07:44 lr: 0.000029 grad: 0.1106 (0.1182) loss: 0.8078 (0.8106) time: 0.1648 data: 0.0761 max mem: 9390 +Train: [69] [3000/6250] eta: 0:07:31 lr: 0.000029 grad: 0.1157 (0.1181) loss: 0.8052 (0.8106) time: 0.1455 data: 0.0650 max mem: 9390 +Train: [69] [3100/6250] eta: 0:07:17 lr: 0.000029 grad: 0.1169 (0.1181) loss: 0.8115 (0.8106) time: 0.1483 data: 0.0699 max mem: 9390 +Train: [69] [3200/6250] eta: 0:07:03 lr: 0.000029 grad: 0.1160 (0.1180) loss: 0.8074 (0.8106) time: 0.1359 data: 0.0580 max mem: 9390 +Train: [69] [3300/6250] eta: 0:06:49 lr: 0.000029 grad: 0.1127 (0.1179) loss: 0.8129 (0.8107) time: 0.1249 data: 0.0440 max mem: 9390 +Train: [69] [3400/6250] eta: 0:06:33 lr: 0.000029 grad: 0.1143 (0.1178) loss: 0.8037 (0.8107) time: 0.1251 data: 0.0489 max mem: 9390 +Train: [69] [3500/6250] eta: 0:06:18 lr: 0.000029 grad: 0.1098 (0.1177) loss: 0.8170 (0.8108) time: 0.1242 data: 0.0491 max mem: 9390 +Train: [69] [3600/6250] eta: 0:06:03 lr: 0.000029 grad: 0.1049 (0.1175) loss: 0.8125 (0.8108) time: 0.1225 data: 0.0391 max mem: 9390 +Train: [69] [3700/6250] eta: 0:05:49 lr: 0.000029 grad: 0.1187 (0.1175) loss: 0.8117 (0.8109) time: 0.1238 data: 0.0298 max mem: 9390 +Train: [69] [3800/6250] eta: 0:05:34 lr: 0.000029 grad: 0.1184 (0.1174) loss: 0.8079 (0.8109) time: 0.1311 data: 0.0494 max mem: 9390 +Train: [69] [3900/6250] eta: 0:05:20 lr: 0.000029 grad: 0.1058 (0.1174) loss: 0.8131 (0.8110) time: 0.1255 data: 0.0386 max mem: 9390 +Train: [69] [4000/6250] eta: 0:05:06 lr: 0.000029 grad: 0.1172 (0.1173) loss: 0.8082 (0.8110) time: 0.1241 data: 0.0420 max mem: 9390 +Train: [69] [4100/6250] eta: 0:04:52 lr: 0.000029 grad: 0.1096 (0.1173) loss: 0.8180 (0.8109) time: 0.1009 data: 0.0212 max mem: 9390 +Train: [69] [4200/6250] eta: 0:04:38 lr: 0.000029 grad: 0.1102 (0.1171) loss: 0.8132 (0.8110) time: 0.1325 data: 0.0551 max mem: 9390 +Train: [69] [4300/6250] eta: 0:04:24 lr: 0.000029 grad: 0.1108 (0.1171) loss: 0.8168 (0.8110) time: 0.1262 data: 0.0441 max mem: 9390 +Train: [69] [4400/6250] eta: 0:04:11 lr: 0.000029 grad: 0.1112 (0.1169) loss: 0.8127 (0.8111) time: 0.1445 data: 0.0708 max mem: 9390 +Train: [69] [4500/6250] eta: 0:03:57 lr: 0.000029 grad: 0.1079 (0.1168) loss: 0.8164 (0.8112) time: 0.1636 data: 0.0829 max mem: 9390 +Train: [69] [4600/6250] eta: 0:03:43 lr: 0.000029 grad: 0.1099 (0.1166) loss: 0.8174 (0.8113) time: 0.1194 data: 0.0363 max mem: 9390 +Train: [69] [4700/6250] eta: 0:03:30 lr: 0.000029 grad: 0.1080 (0.1165) loss: 0.8109 (0.8113) time: 0.1649 data: 0.0837 max mem: 9390 +Train: [69] [4800/6250] eta: 0:03:16 lr: 0.000029 grad: 0.1093 (0.1163) loss: 0.8138 (0.8115) time: 0.1194 data: 0.0382 max mem: 9390 +Train: [69] [4900/6250] eta: 0:03:03 lr: 0.000029 grad: 0.1030 (0.1162) loss: 0.8188 (0.8116) time: 0.1352 data: 0.0598 max mem: 9390 +Train: [69] [5000/6250] eta: 0:02:49 lr: 0.000029 grad: 0.1124 (0.1161) loss: 0.8203 (0.8117) time: 0.1231 data: 0.0446 max mem: 9390 +Train: [69] [5100/6250] eta: 0:02:35 lr: 0.000029 grad: 0.1094 (0.1159) loss: 0.8192 (0.8118) time: 0.1468 data: 0.0645 max mem: 9390 +Train: [69] [5200/6250] eta: 0:02:22 lr: 0.000029 grad: 0.1054 (0.1158) loss: 0.8186 (0.8120) time: 0.1420 data: 0.0563 max mem: 9390 +Train: [69] [5300/6250] eta: 0:02:08 lr: 0.000029 grad: 0.1057 (0.1157) loss: 0.8156 (0.8121) time: 0.1233 data: 0.0458 max mem: 9390 +Train: [69] [5400/6250] eta: 0:01:55 lr: 0.000029 grad: 0.1127 (0.1157) loss: 0.8144 (0.8121) time: 0.1435 data: 0.0597 max mem: 9390 +Train: [69] [5500/6250] eta: 0:01:41 lr: 0.000029 grad: 0.1151 (0.1157) loss: 0.8123 (0.8121) time: 0.1473 data: 0.0584 max mem: 9390 +Train: [69] [5600/6250] eta: 0:01:28 lr: 0.000028 grad: 0.1095 (0.1156) loss: 0.8231 (0.8122) time: 0.1341 data: 0.0388 max mem: 9390 +Train: [69] [5700/6250] eta: 0:01:14 lr: 0.000028 grad: 0.1100 (0.1156) loss: 0.8171 (0.8122) time: 0.1489 data: 0.0641 max mem: 9390 +Train: [69] [5800/6250] eta: 0:01:01 lr: 0.000028 grad: 0.1135 (0.1156) loss: 0.8181 (0.8123) time: 0.1330 data: 0.0562 max mem: 9390 +Train: [69] [5900/6250] eta: 0:00:47 lr: 0.000028 grad: 0.1074 (0.1156) loss: 0.8169 (0.8123) time: 0.1446 data: 0.0667 max mem: 9390 +Train: [69] [6000/6250] eta: 0:00:34 lr: 0.000028 grad: 0.1168 (0.1155) loss: 0.8187 (0.8123) time: 0.1260 data: 0.0489 max mem: 9390 +Train: [69] [6100/6250] eta: 0:00:20 lr: 0.000028 grad: 0.1101 (0.1155) loss: 0.8100 (0.8124) time: 0.1163 data: 0.0280 max mem: 9390 +Train: [69] [6200/6250] eta: 0:00:06 lr: 0.000028 grad: 0.1138 (0.1155) loss: 0.8152 (0.8124) time: 0.1406 data: 0.0640 max mem: 9390 +Train: [69] [6249/6250] eta: 0:00:00 lr: 0.000028 grad: 0.1181 (0.1155) loss: 0.8110 (0.8124) time: 0.1378 data: 0.0511 max mem: 9390 +Train: [69] Total time: 0:14:18 (0.1374 s / it) +Averaged stats: lr: 0.000028 grad: 0.1181 (0.1155) loss: 0.8110 (0.8124) +Eval (hcp-train-subset): [69] [ 0/62] eta: 0:03:23 loss: 0.8378 (0.8378) time: 3.2851 data: 3.2154 max mem: 9390 +Eval (hcp-train-subset): [69] [61/62] eta: 0:00:00 loss: 0.8297 (0.8296) time: 0.1186 data: 0.0937 max mem: 9390 +Eval (hcp-train-subset): [69] Total time: 0:00:12 (0.2048 s / it) +Averaged stats (hcp-train-subset): loss: 0.8297 (0.8296) +Making plots (hcp-train-subset): example=13 +Eval (hcp-val): [69] [ 0/62] eta: 0:03:50 loss: 0.8272 (0.8272) time: 3.7133 data: 3.6241 max mem: 9390 +Eval (hcp-val): [69] [61/62] eta: 0:00:00 loss: 0.8305 (0.8326) time: 0.1320 data: 0.1052 max mem: 9390 +Eval (hcp-val): [69] Total time: 0:00:13 (0.2168 s / it) +Averaged stats (hcp-val): loss: 0.8305 (0.8326) +Making plots (hcp-val): example=51 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +Train: [70] [ 0/6250] eta: 10:48:54 lr: 0.000028 grad: 0.3932 (0.3932) loss: 0.7728 (0.7728) time: 6.2295 data: 6.1201 max mem: 9390 +Train: [70] [ 100/6250] eta: 0:21:06 lr: 0.000028 grad: 0.1120 (0.1503) loss: 0.8156 (0.8197) time: 0.1399 data: 0.0431 max mem: 9390 +Train: [70] [ 200/6250] eta: 0:17:45 lr: 0.000028 grad: 0.1120 (0.1358) loss: 0.8142 (0.8179) time: 0.1410 data: 0.0390 max mem: 9390 +Train: [70] [ 300/6250] eta: 0:16:21 lr: 0.000028 grad: 0.1146 (0.1304) loss: 0.8050 (0.8169) time: 0.1324 data: 0.0420 max mem: 9390 +Train: [70] [ 400/6250] eta: 0:15:26 lr: 0.000028 grad: 0.1248 (0.1280) loss: 0.8107 (0.8157) time: 0.1364 data: 0.0556 max mem: 9390 +Train: [70] [ 500/6250] eta: 0:14:43 lr: 0.000028 grad: 0.1189 (0.1271) loss: 0.8068 (0.8144) time: 0.1310 data: 0.0466 max mem: 9390 +Train: [70] [ 600/6250] eta: 0:14:05 lr: 0.000028 grad: 0.1176 (0.1259) loss: 0.8182 (0.8135) time: 0.1345 data: 0.0503 max mem: 9390 +Train: [70] [ 700/6250] eta: 0:13:34 lr: 0.000028 grad: 0.1105 (0.1241) loss: 0.8141 (0.8135) time: 0.1270 data: 0.0411 max mem: 9390 +Train: [70] [ 800/6250] eta: 0:13:07 lr: 0.000028 grad: 0.1022 (0.1229) loss: 0.8139 (0.8134) time: 0.1374 data: 0.0583 max mem: 9390 +Train: [70] [ 900/6250] eta: 0:12:38 lr: 0.000028 grad: 0.1057 (0.1220) loss: 0.8166 (0.8134) time: 0.1283 data: 0.0462 max mem: 9390 +Train: [70] [1000/6250] eta: 0:12:19 lr: 0.000028 grad: 0.1114 (0.1207) loss: 0.8108 (0.8139) time: 0.1294 data: 0.0490 max mem: 9390 +Train: [70] [1100/6250] eta: 0:12:02 lr: 0.000028 grad: 0.1160 (0.1200) loss: 0.8151 (0.8140) time: 0.1247 data: 0.0425 max mem: 9390 +Train: [70] [1200/6250] eta: 0:11:44 lr: 0.000028 grad: 0.1133 (0.1194) loss: 0.8061 (0.8138) time: 0.1282 data: 0.0521 max mem: 9390 +Train: [70] [1300/6250] eta: 0:11:26 lr: 0.000028 grad: 0.1020 (0.1186) loss: 0.8155 (0.8138) time: 0.1345 data: 0.0584 max mem: 9390 +Train: [70] [1400/6250] eta: 0:11:08 lr: 0.000028 grad: 0.1107 (0.1180) loss: 0.8111 (0.8139) time: 0.1152 data: 0.0360 max mem: 9390 +Train: [70] [1500/6250] eta: 0:10:51 lr: 0.000028 grad: 0.1086 (0.1175) loss: 0.8191 (0.8139) time: 0.1304 data: 0.0547 max mem: 9390 +Train: [70] [1600/6250] eta: 0:10:33 lr: 0.000028 grad: 0.1108 (0.1171) loss: 0.8159 (0.8138) time: 0.1222 data: 0.0478 max mem: 9390 +Train: [70] [1700/6250] eta: 0:10:16 lr: 0.000028 grad: 0.1115 (0.1170) loss: 0.8171 (0.8138) time: 0.1158 data: 0.0386 max mem: 9390 +Train: [70] [1800/6250] eta: 0:10:01 lr: 0.000028 grad: 0.1117 (0.1167) loss: 0.8148 (0.8137) time: 0.1405 data: 0.0600 max mem: 9390 +Train: [70] [1900/6250] eta: 0:09:50 lr: 0.000028 grad: 0.1090 (0.1168) loss: 0.8007 (0.8137) time: 0.1440 data: 0.0525 max mem: 9390 +Train: [70] [2000/6250] eta: 0:09:40 lr: 0.000028 grad: 0.1134 (0.1167) loss: 0.8142 (0.8136) time: 0.1823 data: 0.1011 max mem: 9390 +Train: [70] [2100/6250] eta: 0:09:28 lr: 0.000028 grad: 0.1128 (0.1166) loss: 0.8171 (0.8135) time: 0.1576 data: 0.0842 max mem: 9390 +Train: [70] [2200/6250] eta: 0:09:14 lr: 0.000028 grad: 0.1049 (0.1164) loss: 0.8177 (0.8135) time: 0.1362 data: 0.0554 max mem: 9390 +Train: [70] [2300/6250] eta: 0:09:01 lr: 0.000028 grad: 0.1100 (0.1164) loss: 0.8176 (0.8135) time: 0.1637 data: 0.0814 max mem: 9390 +Train: [70] [2400/6250] eta: 0:08:48 lr: 0.000028 grad: 0.1167 (0.1165) loss: 0.8031 (0.8134) time: 0.1470 data: 0.0678 max mem: 9390 +Train: [70] [2500/6250] eta: 0:08:34 lr: 0.000028 grad: 0.1134 (0.1165) loss: 0.8122 (0.8133) time: 0.1449 data: 0.0682 max mem: 9390 +Train: [70] [2600/6250] eta: 0:08:21 lr: 0.000028 grad: 0.1153 (0.1165) loss: 0.8152 (0.8134) time: 0.1152 data: 0.0284 max mem: 9390 +Train: [70] [2700/6250] eta: 0:08:09 lr: 0.000028 grad: 0.1141 (0.1164) loss: 0.8175 (0.8133) time: 0.1183 data: 0.0431 max mem: 9390 +Train: [70] [2800/6250] eta: 0:07:55 lr: 0.000028 grad: 0.1160 (0.1164) loss: 0.8157 (0.8133) time: 0.1352 data: 0.0542 max mem: 9390 +Train: [70] [2900/6250] eta: 0:07:43 lr: 0.000028 grad: 0.1145 (0.1163) loss: 0.8129 (0.8134) time: 0.1607 data: 0.0780 max mem: 9390 +Train: [70] [3000/6250] eta: 0:07:31 lr: 0.000027 grad: 0.1149 (0.1163) loss: 0.8151 (0.8134) time: 0.1722 data: 0.0880 max mem: 9390 +Train: [70] [3100/6250] eta: 0:07:18 lr: 0.000027 grad: 0.1161 (0.1164) loss: 0.8150 (0.8134) time: 0.1359 data: 0.0559 max mem: 9390 +Train: [70] [3200/6250] eta: 0:07:04 lr: 0.000027 grad: 0.1125 (0.1164) loss: 0.8145 (0.8134) time: 0.1473 data: 0.0684 max mem: 9390 +Train: [70] [3300/6250] eta: 0:06:50 lr: 0.000027 grad: 0.1194 (0.1165) loss: 0.8094 (0.8134) time: 0.1339 data: 0.0479 max mem: 9390 +Train: [70] [3400/6250] eta: 0:06:35 lr: 0.000027 grad: 0.1114 (0.1166) loss: 0.8156 (0.8133) time: 0.1321 data: 0.0548 max mem: 9390 +Train: [70] [3500/6250] eta: 0:06:21 lr: 0.000027 grad: 0.1163 (0.1166) loss: 0.8134 (0.8133) time: 0.1248 data: 0.0452 max mem: 9390 +Train: [70] [3600/6250] eta: 0:06:06 lr: 0.000027 grad: 0.1179 (0.1165) loss: 0.8116 (0.8133) time: 0.1153 data: 0.0263 max mem: 9390 +Train: [70] [3700/6250] eta: 0:05:52 lr: 0.000027 grad: 0.1124 (0.1165) loss: 0.8134 (0.8133) time: 0.1295 data: 0.0490 max mem: 9390 +Train: [70] [3800/6250] eta: 0:05:38 lr: 0.000027 grad: 0.1156 (0.1165) loss: 0.8186 (0.8133) time: 0.1337 data: 0.0561 max mem: 9390 +Train: [70] [3900/6250] eta: 0:05:24 lr: 0.000027 grad: 0.1106 (0.1165) loss: 0.8124 (0.8133) time: 0.1375 data: 0.0573 max mem: 9390 +Train: [70] [4000/6250] eta: 0:05:10 lr: 0.000027 grad: 0.1107 (0.1166) loss: 0.8105 (0.8133) time: 0.1462 data: 0.0641 max mem: 9390 +Train: [70] [4100/6250] eta: 0:04:56 lr: 0.000027 grad: 0.1128 (0.1166) loss: 0.8137 (0.8133) time: 0.1389 data: 0.0593 max mem: 9390 +Train: [70] [4200/6250] eta: 0:04:42 lr: 0.000027 grad: 0.1161 (0.1165) loss: 0.8103 (0.8133) time: 0.1573 data: 0.0706 max mem: 9390 +Train: [70] [4300/6250] eta: 0:04:28 lr: 0.000027 grad: 0.1095 (0.1165) loss: 0.8177 (0.8133) time: 0.1424 data: 0.0621 max mem: 9390 +Train: [70] [4400/6250] eta: 0:04:15 lr: 0.000027 grad: 0.1122 (0.1165) loss: 0.8169 (0.8132) time: 0.1419 data: 0.0635 max mem: 9390 +Train: [70] [4500/6250] eta: 0:04:01 lr: 0.000027 grad: 0.1096 (0.1165) loss: 0.8142 (0.8132) time: 0.1492 data: 0.0683 max mem: 9390 +Train: [70] [4600/6250] eta: 0:03:47 lr: 0.000027 grad: 0.1114 (0.1165) loss: 0.8097 (0.8131) time: 0.1334 data: 0.0518 max mem: 9390 +Train: [70] [4700/6250] eta: 0:03:33 lr: 0.000027 grad: 0.1166 (0.1166) loss: 0.8073 (0.8131) time: 0.1403 data: 0.0608 max mem: 9390 +Train: [70] [4800/6250] eta: 0:03:19 lr: 0.000027 grad: 0.1220 (0.1166) loss: 0.8163 (0.8130) time: 0.1391 data: 0.0500 max mem: 9390 +Train: [70] [4900/6250] eta: 0:03:05 lr: 0.000027 grad: 0.1112 (0.1166) loss: 0.8129 (0.8130) time: 0.1319 data: 0.0545 max mem: 9390 +Train: [70] [5000/6250] eta: 0:02:52 lr: 0.000027 grad: 0.1225 (0.1167) loss: 0.8073 (0.8129) time: 0.1275 data: 0.0541 max mem: 9390 +Train: [70] [5100/6250] eta: 0:02:38 lr: 0.000027 grad: 0.1192 (0.1168) loss: 0.8137 (0.8129) time: 0.1200 data: 0.0417 max mem: 9390 +Train: [70] [5200/6250] eta: 0:02:24 lr: 0.000027 grad: 0.1177 (0.1168) loss: 0.8093 (0.8129) time: 0.1380 data: 0.0511 max mem: 9390 +Train: [70] [5300/6250] eta: 0:02:11 lr: 0.000027 grad: 0.1138 (0.1169) loss: 0.8105 (0.8128) time: 0.1224 data: 0.0482 max mem: 9390 +Train: [70] [5400/6250] eta: 0:01:57 lr: 0.000027 grad: 0.1161 (0.1170) loss: 0.8066 (0.8128) time: 0.1399 data: 0.0634 max mem: 9390 +Train: [70] [5500/6250] eta: 0:01:43 lr: 0.000027 grad: 0.1155 (0.1170) loss: 0.8142 (0.8128) time: 0.1217 data: 0.0263 max mem: 9390 +Train: [70] [5600/6250] eta: 0:01:29 lr: 0.000027 grad: 0.1196 (0.1171) loss: 0.8138 (0.8127) time: 0.1194 data: 0.0359 max mem: 9390 +Train: [70] [5700/6250] eta: 0:01:15 lr: 0.000027 grad: 0.1142 (0.1171) loss: 0.8070 (0.8127) time: 0.1298 data: 0.0459 max mem: 9390 +Train: [70] [5800/6250] eta: 0:01:02 lr: 0.000027 grad: 0.1131 (0.1171) loss: 0.8117 (0.8126) time: 0.1259 data: 0.0396 max mem: 9390 +Train: [70] [5900/6250] eta: 0:00:48 lr: 0.000027 grad: 0.1140 (0.1170) loss: 0.8150 (0.8127) time: 0.1549 data: 0.0762 max mem: 9390 +Train: [70] [6000/6250] eta: 0:00:34 lr: 0.000027 grad: 0.1123 (0.1170) loss: 0.8100 (0.8126) time: 0.1108 data: 0.0224 max mem: 9390 +Train: [70] [6100/6250] eta: 0:00:20 lr: 0.000027 grad: 0.1132 (0.1170) loss: 0.8107 (0.8126) time: 0.1492 data: 0.0666 max mem: 9390 +Train: [70] [6200/6250] eta: 0:00:06 lr: 0.000027 grad: 0.1143 (0.1171) loss: 0.8115 (0.8125) time: 0.1042 data: 0.0215 max mem: 9390 +Train: [70] [6249/6250] eta: 0:00:00 lr: 0.000027 grad: 0.1179 (0.1171) loss: 0.8065 (0.8125) time: 0.1552 data: 0.0787 max mem: 9390 +Train: [70] Total time: 0:14:31 (0.1394 s / it) +Averaged stats: lr: 0.000027 grad: 0.1179 (0.1171) loss: 0.8065 (0.8125) +Eval (hcp-train-subset): [70] [ 0/62] eta: 0:04:10 loss: 0.8396 (0.8396) time: 4.0351 data: 3.9304 max mem: 9390 +Eval (hcp-train-subset): [70] [61/62] eta: 0:00:00 loss: 0.8285 (0.8300) time: 0.1297 data: 0.1045 max mem: 9390 +Eval (hcp-train-subset): [70] Total time: 0:00:13 (0.2112 s / it) +Averaged stats (hcp-train-subset): loss: 0.8285 (0.8300) +Eval (hcp-val): [70] [ 0/62] eta: 0:04:06 loss: 0.8293 (0.8293) time: 3.9746 data: 3.8864 max mem: 9390 +Eval (hcp-val): [70] [61/62] eta: 0:00:00 loss: 0.8314 (0.8322) time: 0.1250 data: 0.0999 max mem: 9390 +Eval (hcp-val): [70] Total time: 0:00:13 (0.2098 s / it) +Averaged stats (hcp-val): loss: 0.8314 (0.8322) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +Train: [71] [ 0/6250] eta: 7:59:22 lr: 0.000027 grad: 0.0783 (0.0783) loss: 0.8455 (0.8455) time: 4.6020 data: 4.2814 max mem: 9390 +Train: [71] [ 100/6250] eta: 0:20:45 lr: 0.000027 grad: 0.1252 (0.1443) loss: 0.8078 (0.8165) time: 0.1501 data: 0.0495 max mem: 9390 +Train: [71] [ 200/6250] eta: 0:17:51 lr: 0.000027 grad: 0.1251 (0.1375) loss: 0.8103 (0.8133) time: 0.1586 data: 0.0588 max mem: 9390 +Train: [71] [ 300/6250] eta: 0:16:29 lr: 0.000027 grad: 0.1180 (0.1337) loss: 0.8043 (0.8122) time: 0.1260 data: 0.0404 max mem: 9390 +Train: [71] [ 400/6250] eta: 0:15:23 lr: 0.000026 grad: 0.1156 (0.1308) loss: 0.8173 (0.8123) time: 0.1190 data: 0.0379 max mem: 9390 +Train: [71] [ 500/6250] eta: 0:14:33 lr: 0.000026 grad: 0.1101 (0.1279) loss: 0.8158 (0.8130) time: 0.1231 data: 0.0372 max mem: 9390 +Train: [71] [ 600/6250] eta: 0:13:51 lr: 0.000026 grad: 0.1164 (0.1265) loss: 0.8099 (0.8131) time: 0.1273 data: 0.0303 max mem: 9390 +Train: [71] [ 700/6250] eta: 0:13:15 lr: 0.000026 grad: 0.1186 (0.1251) loss: 0.8152 (0.8132) time: 0.1159 data: 0.0311 max mem: 9390 +Train: [71] [ 800/6250] eta: 0:12:52 lr: 0.000026 grad: 0.1246 (0.1246) loss: 0.8117 (0.8129) time: 0.1402 data: 0.0524 max mem: 9390 +Train: [71] [ 900/6250] eta: 0:12:41 lr: 0.000026 grad: 0.1177 (0.1241) loss: 0.8134 (0.8128) time: 0.1469 data: 0.0596 max mem: 9390 +Train: [71] [1000/6250] eta: 0:12:28 lr: 0.000026 grad: 0.1088 (0.1238) loss: 0.8113 (0.8126) time: 0.1447 data: 0.0717 max mem: 9390 +Train: [71] [1100/6250] eta: 0:12:21 lr: 0.000026 grad: 0.1165 (0.1234) loss: 0.8056 (0.8123) time: 0.1724 data: 0.0911 max mem: 9390 +Train: [71] [1200/6250] eta: 0:12:05 lr: 0.000026 grad: 0.1184 (0.1230) loss: 0.8040 (0.8121) time: 0.1489 data: 0.0647 max mem: 9390 +Train: [71] [1300/6250] eta: 0:11:44 lr: 0.000026 grad: 0.1104 (0.1227) loss: 0.8089 (0.8119) time: 0.1276 data: 0.0446 max mem: 9390 +Train: [71] [1400/6250] eta: 0:11:29 lr: 0.000026 grad: 0.1151 (0.1225) loss: 0.8153 (0.8117) time: 0.1567 data: 0.0775 max mem: 9390 +Train: [71] [1500/6250] eta: 0:11:15 lr: 0.000026 grad: 0.1153 (0.1222) loss: 0.8079 (0.8116) time: 0.1410 data: 0.0518 max mem: 9390 +Train: [71] [1600/6250] eta: 0:10:59 lr: 0.000026 grad: 0.1198 (0.1222) loss: 0.8075 (0.8113) time: 0.1391 data: 0.0669 max mem: 9390 +Train: [71] [1700/6250] eta: 0:10:44 lr: 0.000026 grad: 0.1121 (0.1217) loss: 0.8105 (0.8114) time: 0.1482 data: 0.0715 max mem: 9390 +Train: [71] [1800/6250] eta: 0:10:30 lr: 0.000026 grad: 0.1181 (0.1216) loss: 0.8053 (0.8113) time: 0.1347 data: 0.0582 max mem: 9390 +Train: [71] [1900/6250] eta: 0:10:17 lr: 0.000026 grad: 0.1155 (0.1215) loss: 0.8053 (0.8112) time: 0.1268 data: 0.0469 max mem: 9390 +Train: [71] [2000/6250] eta: 0:10:02 lr: 0.000026 grad: 0.1115 (0.1213) loss: 0.8048 (0.8111) time: 0.1409 data: 0.0567 max mem: 9390 +Train: [71] [2100/6250] eta: 0:09:47 lr: 0.000026 grad: 0.1175 (0.1212) loss: 0.8053 (0.8109) time: 0.1549 data: 0.0772 max mem: 9390 +Train: [71] [2200/6250] eta: 0:09:32 lr: 0.000026 grad: 0.1177 (0.1211) loss: 0.8098 (0.8108) time: 0.1330 data: 0.0555 max mem: 9390 +Train: [71] [2300/6250] eta: 0:09:17 lr: 0.000026 grad: 0.1154 (0.1210) loss: 0.8085 (0.8106) time: 0.1525 data: 0.0704 max mem: 9390 +Train: [71] [2400/6250] eta: 0:09:02 lr: 0.000026 grad: 0.1176 (0.1209) loss: 0.8087 (0.8105) time: 0.1282 data: 0.0491 max mem: 9390 +Train: [71] [2500/6250] eta: 0:08:47 lr: 0.000026 grad: 0.1167 (0.1211) loss: 0.8070 (0.8103) time: 0.1376 data: 0.0625 max mem: 9390 +Train: [71] [2600/6250] eta: 0:08:36 lr: 0.000026 grad: 0.1259 (0.1211) loss: 0.8032 (0.8102) time: 0.1467 data: 0.0686 max mem: 9390 +Train: [71] [2700/6250] eta: 0:08:22 lr: 0.000026 grad: 0.1137 (0.1210) loss: 0.8120 (0.8101) time: 0.1425 data: 0.0584 max mem: 9390 +Train: [71] [2800/6250] eta: 0:08:08 lr: 0.000026 grad: 0.1122 (0.1210) loss: 0.8126 (0.8100) time: 0.1446 data: 0.0638 max mem: 9390 +Train: [71] [2900/6250] eta: 0:07:54 lr: 0.000026 grad: 0.1148 (0.1209) loss: 0.8081 (0.8099) time: 0.1421 data: 0.0622 max mem: 9390 +Train: [71] [3000/6250] eta: 0:07:39 lr: 0.000026 grad: 0.1207 (0.1210) loss: 0.8053 (0.8098) time: 0.1418 data: 0.0633 max mem: 9390 +Train: [71] [3100/6250] eta: 0:07:25 lr: 0.000026 grad: 0.1141 (0.1209) loss: 0.8108 (0.8098) time: 0.1579 data: 0.0820 max mem: 9390 +Train: [71] [3200/6250] eta: 0:07:09 lr: 0.000026 grad: 0.1207 (0.1209) loss: 0.8147 (0.8098) time: 0.0966 data: 0.0170 max mem: 9390 +Train: [71] [3300/6250] eta: 0:06:53 lr: 0.000026 grad: 0.1105 (0.1209) loss: 0.8108 (0.8097) time: 0.1134 data: 0.0202 max mem: 9390 +Train: [71] [3400/6250] eta: 0:06:38 lr: 0.000026 grad: 0.1194 (0.1208) loss: 0.8071 (0.8097) time: 0.1364 data: 0.0539 max mem: 9390 +Train: [71] [3500/6250] eta: 0:06:22 lr: 0.000026 grad: 0.1151 (0.1208) loss: 0.8130 (0.8098) time: 0.1135 data: 0.0291 max mem: 9390 +Train: [71] [3600/6250] eta: 0:06:07 lr: 0.000026 grad: 0.1250 (0.1207) loss: 0.8105 (0.8098) time: 0.1418 data: 0.0645 max mem: 9390 +Train: [71] [3700/6250] eta: 0:05:53 lr: 0.000026 grad: 0.1171 (0.1207) loss: 0.8133 (0.8098) time: 0.1346 data: 0.0577 max mem: 9390 +Train: [71] [3800/6250] eta: 0:05:38 lr: 0.000026 grad: 0.1186 (0.1207) loss: 0.8115 (0.8099) time: 0.1349 data: 0.0512 max mem: 9390 +Train: [71] [3900/6250] eta: 0:05:24 lr: 0.000026 grad: 0.1150 (0.1206) loss: 0.8174 (0.8100) time: 0.1358 data: 0.0537 max mem: 9390 +Train: [71] [4000/6250] eta: 0:05:10 lr: 0.000026 grad: 0.1171 (0.1207) loss: 0.8067 (0.8100) time: 0.1397 data: 0.0620 max mem: 9390 +Train: [71] [4100/6250] eta: 0:04:56 lr: 0.000026 grad: 0.1216 (0.1207) loss: 0.8061 (0.8100) time: 0.1588 data: 0.0796 max mem: 9390 +Train: [71] [4200/6250] eta: 0:04:42 lr: 0.000025 grad: 0.1183 (0.1207) loss: 0.8124 (0.8101) time: 0.1376 data: 0.0594 max mem: 9390 +Train: [71] [4300/6250] eta: 0:04:28 lr: 0.000025 grad: 0.1164 (0.1207) loss: 0.8072 (0.8101) time: 0.1535 data: 0.0731 max mem: 9390 +Train: [71] [4400/6250] eta: 0:04:14 lr: 0.000025 grad: 0.1152 (0.1207) loss: 0.8133 (0.8101) time: 0.1299 data: 0.0479 max mem: 9390 +Train: [71] [4500/6250] eta: 0:04:00 lr: 0.000025 grad: 0.1181 (0.1208) loss: 0.8008 (0.8100) time: 0.1361 data: 0.0548 max mem: 9390 +Train: [71] [4600/6250] eta: 0:03:47 lr: 0.000025 grad: 0.1159 (0.1208) loss: 0.8067 (0.8099) time: 0.1563 data: 0.0672 max mem: 9390 +Train: [71] [4700/6250] eta: 0:03:32 lr: 0.000025 grad: 0.1120 (0.1208) loss: 0.8078 (0.8099) time: 0.1306 data: 0.0474 max mem: 9390 +Train: [71] [4800/6250] eta: 0:03:19 lr: 0.000025 grad: 0.1149 (0.1207) loss: 0.8091 (0.8099) time: 0.1086 data: 0.0262 max mem: 9390 +Train: [71] [4900/6250] eta: 0:03:05 lr: 0.000025 grad: 0.1177 (0.1207) loss: 0.8068 (0.8099) time: 0.1123 data: 0.0167 max mem: 9390 +Train: [71] [5000/6250] eta: 0:02:51 lr: 0.000025 grad: 0.1199 (0.1206) loss: 0.8043 (0.8099) time: 0.1243 data: 0.0425 max mem: 9390 +Train: [71] [5100/6250] eta: 0:02:38 lr: 0.000025 grad: 0.1166 (0.1206) loss: 0.8073 (0.8098) time: 0.1306 data: 0.0512 max mem: 9390 +Train: [71] [5200/6250] eta: 0:02:24 lr: 0.000025 grad: 0.1150 (0.1206) loss: 0.8069 (0.8098) time: 0.1550 data: 0.0781 max mem: 9390 +Train: [71] [5300/6250] eta: 0:02:10 lr: 0.000025 grad: 0.1161 (0.1206) loss: 0.8047 (0.8098) time: 0.1277 data: 0.0428 max mem: 9390 +Train: [71] [5400/6250] eta: 0:01:56 lr: 0.000025 grad: 0.1191 (0.1206) loss: 0.8089 (0.8098) time: 0.1377 data: 0.0631 max mem: 9390 +Train: [71] [5500/6250] eta: 0:01:43 lr: 0.000025 grad: 0.1140 (0.1205) loss: 0.8122 (0.8098) time: 0.1489 data: 0.0776 max mem: 9390 +Train: [71] [5600/6250] eta: 0:01:29 lr: 0.000025 grad: 0.1161 (0.1206) loss: 0.8102 (0.8098) time: 0.1453 data: 0.0630 max mem: 9390 +Train: [71] [5700/6250] eta: 0:01:15 lr: 0.000025 grad: 0.1186 (0.1206) loss: 0.8024 (0.8097) time: 0.1352 data: 0.0474 max mem: 9390 +Train: [71] [5800/6250] eta: 0:01:01 lr: 0.000025 grad: 0.1184 (0.1206) loss: 0.8035 (0.8097) time: 0.1527 data: 0.0587 max mem: 9390 +Train: [71] [5900/6250] eta: 0:00:48 lr: 0.000025 grad: 0.1214 (0.1206) loss: 0.8092 (0.8096) time: 0.1360 data: 0.0624 max mem: 9390 +Train: [71] [6000/6250] eta: 0:00:34 lr: 0.000025 grad: 0.1091 (0.1205) loss: 0.8125 (0.8096) time: 0.1391 data: 0.0611 max mem: 9390 +Train: [71] [6100/6250] eta: 0:00:20 lr: 0.000025 grad: 0.1130 (0.1205) loss: 0.8091 (0.8096) time: 0.1324 data: 0.0528 max mem: 9390 +Train: [71] [6200/6250] eta: 0:00:06 lr: 0.000025 grad: 0.1143 (0.1205) loss: 0.8112 (0.8096) time: 0.1358 data: 0.0653 max mem: 9390 +Train: [71] [6249/6250] eta: 0:00:00 lr: 0.000025 grad: 0.1165 (0.1204) loss: 0.8016 (0.8096) time: 0.1320 data: 0.0493 max mem: 9390 +Train: [71] Total time: 0:14:25 (0.1384 s / it) +Averaged stats: lr: 0.000025 grad: 0.1165 (0.1204) loss: 0.8016 (0.8096) +Eval (hcp-train-subset): [71] [ 0/62] eta: 0:04:00 loss: 0.8389 (0.8389) time: 3.8736 data: 3.8152 max mem: 9390 +Eval (hcp-train-subset): [71] [61/62] eta: 0:00:00 loss: 0.8265 (0.8281) time: 0.1065 data: 0.0800 max mem: 9390 +Eval (hcp-train-subset): [71] Total time: 0:00:12 (0.1978 s / it) +Averaged stats (hcp-train-subset): loss: 0.8265 (0.8281) +Eval (hcp-val): [71] [ 0/62] eta: 0:04:56 loss: 0.8317 (0.8317) time: 4.7804 data: 4.7517 max mem: 9390 +Eval (hcp-val): [71] [61/62] eta: 0:00:00 loss: 0.8310 (0.8319) time: 0.1198 data: 0.0949 max mem: 9390 +Eval (hcp-val): [71] Total time: 0:00:12 (0.2065 s / it) +Averaged stats (hcp-val): loss: 0.8310 (0.8319) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +Train: [72] [ 0/6250] eta: 9:08:58 lr: 0.000025 grad: 0.1574 (0.1574) loss: 0.8554 (0.8554) time: 5.2702 data: 5.1564 max mem: 9390 +Train: [72] [ 100/6250] eta: 0:20:22 lr: 0.000025 grad: 0.1373 (0.1396) loss: 0.8032 (0.8235) time: 0.1340 data: 0.0451 max mem: 9390 +Train: [72] [ 200/6250] eta: 0:17:35 lr: 0.000025 grad: 0.1235 (0.1380) loss: 0.8044 (0.8163) time: 0.1477 data: 0.0594 max mem: 9390 +Train: [72] [ 300/6250] eta: 0:16:07 lr: 0.000025 grad: 0.1234 (0.1344) loss: 0.8090 (0.8142) time: 0.1569 data: 0.0724 max mem: 9390 +Train: [72] [ 400/6250] eta: 0:15:19 lr: 0.000025 grad: 0.1134 (0.1305) loss: 0.8134 (0.8143) time: 0.1300 data: 0.0478 max mem: 9390 +Train: [72] [ 500/6250] eta: 0:14:35 lr: 0.000025 grad: 0.1178 (0.1279) loss: 0.8166 (0.8150) time: 0.1317 data: 0.0549 max mem: 9390 +Train: [72] [ 600/6250] eta: 0:13:59 lr: 0.000025 grad: 0.1181 (0.1265) loss: 0.8156 (0.8148) time: 0.1288 data: 0.0436 max mem: 9390 +Train: [72] [ 700/6250] eta: 0:13:27 lr: 0.000025 grad: 0.1173 (0.1259) loss: 0.8049 (0.8140) time: 0.1205 data: 0.0401 max mem: 9390 +Train: [72] [ 800/6250] eta: 0:12:58 lr: 0.000025 grad: 0.1217 (0.1254) loss: 0.8108 (0.8134) time: 0.1307 data: 0.0344 max mem: 9390 +Train: [72] [ 900/6250] eta: 0:12:31 lr: 0.000025 grad: 0.1203 (0.1249) loss: 0.8097 (0.8129) time: 0.1338 data: 0.0524 max mem: 9390 +Train: [72] [1000/6250] eta: 0:12:10 lr: 0.000025 grad: 0.1202 (0.1248) loss: 0.8123 (0.8124) time: 0.1257 data: 0.0480 max mem: 9390 +Train: [72] [1100/6250] eta: 0:11:56 lr: 0.000025 grad: 0.1224 (0.1245) loss: 0.8087 (0.8118) time: 0.1311 data: 0.0534 max mem: 9390 +Train: [72] [1200/6250] eta: 0:11:39 lr: 0.000025 grad: 0.1243 (0.1244) loss: 0.8028 (0.8112) time: 0.1257 data: 0.0485 max mem: 9390 +Train: [72] [1300/6250] eta: 0:11:20 lr: 0.000025 grad: 0.1218 (0.1245) loss: 0.8109 (0.8106) time: 0.1247 data: 0.0441 max mem: 9390 +Train: [72] [1400/6250] eta: 0:11:05 lr: 0.000025 grad: 0.1185 (0.1245) loss: 0.8041 (0.8101) time: 0.1284 data: 0.0506 max mem: 9390 +Train: [72] [1500/6250] eta: 0:10:49 lr: 0.000025 grad: 0.1166 (0.1244) loss: 0.8086 (0.8097) time: 0.1239 data: 0.0395 max mem: 9390 +Train: [72] [1600/6250] eta: 0:10:34 lr: 0.000025 grad: 0.1195 (0.1245) loss: 0.8063 (0.8094) time: 0.1263 data: 0.0430 max mem: 9390 +Train: [72] [1700/6250] eta: 0:10:24 lr: 0.000024 grad: 0.1155 (0.1244) loss: 0.8082 (0.8092) time: 0.1676 data: 0.0783 max mem: 9390 +Train: [72] [1800/6250] eta: 0:10:09 lr: 0.000024 grad: 0.1104 (0.1241) loss: 0.8121 (0.8091) time: 0.1238 data: 0.0476 max mem: 9390 +Train: [72] [1900/6250] eta: 0:09:56 lr: 0.000024 grad: 0.1181 (0.1240) loss: 0.8047 (0.8090) time: 0.1584 data: 0.0830 max mem: 9390 +Train: [72] [2000/6250] eta: 0:09:43 lr: 0.000024 grad: 0.1206 (0.1238) loss: 0.8085 (0.8090) time: 0.1596 data: 0.0798 max mem: 9390 +Train: [72] [2100/6250] eta: 0:09:29 lr: 0.000024 grad: 0.1134 (0.1236) loss: 0.8092 (0.8088) time: 0.1491 data: 0.0574 max mem: 9390 +Train: [72] [2200/6250] eta: 0:09:16 lr: 0.000024 grad: 0.1158 (0.1235) loss: 0.8170 (0.8088) time: 0.1469 data: 0.0693 max mem: 9390 +Train: [72] [2300/6250] eta: 0:09:06 lr: 0.000024 grad: 0.1189 (0.1233) loss: 0.8065 (0.8088) time: 0.2602 data: 0.1824 max mem: 9390 +Train: [72] [2400/6250] eta: 0:08:53 lr: 0.000024 grad: 0.1173 (0.1233) loss: 0.8106 (0.8089) time: 0.1663 data: 0.0794 max mem: 9390 +Train: [72] [2500/6250] eta: 0:08:41 lr: 0.000024 grad: 0.1207 (0.1231) loss: 0.8065 (0.8089) time: 0.1742 data: 0.0909 max mem: 9390 +Train: [72] [2600/6250] eta: 0:08:30 lr: 0.000024 grad: 0.1175 (0.1231) loss: 0.8052 (0.8089) time: 0.1442 data: 0.0649 max mem: 9390 +Train: [72] [2700/6250] eta: 0:08:17 lr: 0.000024 grad: 0.1312 (0.1231) loss: 0.8084 (0.8089) time: 0.1414 data: 0.0676 max mem: 9390 +Train: [72] [2800/6250] eta: 0:08:02 lr: 0.000024 grad: 0.1179 (0.1229) loss: 0.8068 (0.8090) time: 0.1364 data: 0.0507 max mem: 9390 +Train: [72] [2900/6250] eta: 0:07:47 lr: 0.000024 grad: 0.1210 (0.1228) loss: 0.8104 (0.8091) time: 0.1225 data: 0.0443 max mem: 9390 +Train: [72] [3000/6250] eta: 0:07:31 lr: 0.000024 grad: 0.1206 (0.1228) loss: 0.8089 (0.8092) time: 0.1206 data: 0.0442 max mem: 9390 +Train: [72] [3100/6250] eta: 0:07:16 lr: 0.000024 grad: 0.1230 (0.1229) loss: 0.8120 (0.8092) time: 0.1393 data: 0.0578 max mem: 9390 +Train: [72] [3200/6250] eta: 0:07:00 lr: 0.000024 grad: 0.1273 (0.1230) loss: 0.8046 (0.8092) time: 0.1246 data: 0.0427 max mem: 9390 +Train: [72] [3300/6250] eta: 0:06:45 lr: 0.000024 grad: 0.1324 (0.1230) loss: 0.8076 (0.8091) time: 0.1209 data: 0.0352 max mem: 9390 +Train: [72] [3400/6250] eta: 0:06:29 lr: 0.000024 grad: 0.1230 (0.1231) loss: 0.8079 (0.8091) time: 0.1137 data: 0.0292 max mem: 9390 +Train: [72] [3500/6250] eta: 0:06:14 lr: 0.000024 grad: 0.1184 (0.1231) loss: 0.8146 (0.8091) time: 0.1382 data: 0.0555 max mem: 9390 +Train: [72] [3600/6250] eta: 0:05:59 lr: 0.000024 grad: 0.1117 (0.1231) loss: 0.8145 (0.8090) time: 0.1250 data: 0.0417 max mem: 9390 +Train: [72] [3700/6250] eta: 0:05:45 lr: 0.000024 grad: 0.1204 (0.1231) loss: 0.8115 (0.8090) time: 0.1325 data: 0.0596 max mem: 9390 +Train: [72] [3800/6250] eta: 0:05:31 lr: 0.000024 grad: 0.1226 (0.1231) loss: 0.8039 (0.8089) time: 0.1392 data: 0.0628 max mem: 9390 +Train: [72] [3900/6250] eta: 0:05:17 lr: 0.000024 grad: 0.1220 (0.1231) loss: 0.8053 (0.8089) time: 0.1008 data: 0.0190 max mem: 9390 +Train: [72] [4000/6250] eta: 0:05:03 lr: 0.000024 grad: 0.1204 (0.1230) loss: 0.8097 (0.8089) time: 0.1201 data: 0.0360 max mem: 9390 +Train: [72] [4100/6250] eta: 0:04:49 lr: 0.000024 grad: 0.1174 (0.1229) loss: 0.8098 (0.8089) time: 0.1297 data: 0.0479 max mem: 9390 +Train: [72] [4200/6250] eta: 0:04:36 lr: 0.000024 grad: 0.1134 (0.1229) loss: 0.8162 (0.8089) time: 0.1663 data: 0.0892 max mem: 9390 +Train: [72] [4300/6250] eta: 0:04:22 lr: 0.000024 grad: 0.1161 (0.1228) loss: 0.8083 (0.8090) time: 0.1359 data: 0.0587 max mem: 9390 +Train: [72] [4400/6250] eta: 0:04:09 lr: 0.000024 grad: 0.1130 (0.1226) loss: 0.8150 (0.8090) time: 0.1262 data: 0.0423 max mem: 9390 +Train: [72] [4500/6250] eta: 0:03:55 lr: 0.000024 grad: 0.1210 (0.1226) loss: 0.8122 (0.8091) time: 0.1256 data: 0.0488 max mem: 9390 +Train: [72] [4600/6250] eta: 0:03:42 lr: 0.000024 grad: 0.1078 (0.1224) loss: 0.8181 (0.8091) time: 0.1582 data: 0.0830 max mem: 9390 +Train: [72] [4700/6250] eta: 0:03:28 lr: 0.000024 grad: 0.1149 (0.1223) loss: 0.8140 (0.8092) time: 0.1436 data: 0.0672 max mem: 9390 +Train: [72] [4800/6250] eta: 0:03:15 lr: 0.000024 grad: 0.1190 (0.1222) loss: 0.8146 (0.8093) time: 0.1135 data: 0.0358 max mem: 9390 +Train: [72] [4900/6250] eta: 0:03:02 lr: 0.000024 grad: 0.1176 (0.1222) loss: 0.8144 (0.8094) time: 0.1268 data: 0.0511 max mem: 9390 +Train: [72] [5000/6250] eta: 0:02:48 lr: 0.000024 grad: 0.1120 (0.1221) loss: 0.8095 (0.8094) time: 0.1424 data: 0.0662 max mem: 9390 +Train: [72] [5100/6250] eta: 0:02:35 lr: 0.000024 grad: 0.1225 (0.1220) loss: 0.8115 (0.8095) time: 0.1357 data: 0.0606 max mem: 9390 +Train: [72] [5200/6250] eta: 0:02:21 lr: 0.000024 grad: 0.1167 (0.1220) loss: 0.8181 (0.8095) time: 0.1417 data: 0.0665 max mem: 9390 +Train: [72] [5300/6250] eta: 0:02:08 lr: 0.000024 grad: 0.1191 (0.1219) loss: 0.8193 (0.8096) time: 0.1401 data: 0.0589 max mem: 9390 +Train: [72] [5400/6250] eta: 0:01:55 lr: 0.000024 grad: 0.1136 (0.1219) loss: 0.8143 (0.8097) time: 0.1555 data: 0.0767 max mem: 9390 +Train: [72] [5500/6250] eta: 0:01:41 lr: 0.000023 grad: 0.1242 (0.1219) loss: 0.8117 (0.8098) time: 0.1565 data: 0.0768 max mem: 9390 +Train: [72] [5600/6250] eta: 0:01:28 lr: 0.000023 grad: 0.1237 (0.1219) loss: 0.8187 (0.8099) time: 0.1215 data: 0.0396 max mem: 9390 +Train: [72] [5700/6250] eta: 0:01:14 lr: 0.000023 grad: 0.1143 (0.1218) loss: 0.8163 (0.8100) time: 0.1531 data: 0.0783 max mem: 9390 +Train: [72] [5800/6250] eta: 0:01:01 lr: 0.000023 grad: 0.1176 (0.1218) loss: 0.8107 (0.8101) time: 0.1425 data: 0.0592 max mem: 9390 +Train: [72] [5900/6250] eta: 0:00:47 lr: 0.000023 grad: 0.1240 (0.1218) loss: 0.8093 (0.8102) time: 0.1486 data: 0.0606 max mem: 9390 +Train: [72] [6000/6250] eta: 0:00:33 lr: 0.000023 grad: 0.1194 (0.1217) loss: 0.8216 (0.8103) time: 0.1199 data: 0.0360 max mem: 9390 +Train: [72] [6100/6250] eta: 0:00:20 lr: 0.000023 grad: 0.1192 (0.1217) loss: 0.8179 (0.8104) time: 0.1228 data: 0.0448 max mem: 9390 +Train: [72] [6200/6250] eta: 0:00:06 lr: 0.000023 grad: 0.1181 (0.1217) loss: 0.8082 (0.8105) time: 0.1659 data: 0.0859 max mem: 9390 +Train: [72] [6249/6250] eta: 0:00:00 lr: 0.000023 grad: 0.1155 (0.1217) loss: 0.8171 (0.8105) time: 0.1385 data: 0.0601 max mem: 9390 +Train: [72] Total time: 0:14:19 (0.1375 s / it) +Averaged stats: lr: 0.000023 grad: 0.1155 (0.1217) loss: 0.8171 (0.8105) +Eval (hcp-train-subset): [72] [ 0/62] eta: 0:03:36 loss: 0.8371 (0.8371) time: 3.4842 data: 3.4110 max mem: 9390 +Eval (hcp-train-subset): [72] [61/62] eta: 0:00:00 loss: 0.8275 (0.8279) time: 0.1218 data: 0.0971 max mem: 9390 +Eval (hcp-train-subset): [72] Total time: 0:00:12 (0.1995 s / it) +Averaged stats (hcp-train-subset): loss: 0.8275 (0.8279) +Eval (hcp-val): [72] [ 0/62] eta: 0:04:23 loss: 0.8293 (0.8293) time: 4.2554 data: 4.2268 max mem: 9390 +Eval (hcp-val): [72] [61/62] eta: 0:00:00 loss: 0.8298 (0.8312) time: 0.1432 data: 0.1181 max mem: 9390 +Eval (hcp-val): [72] Total time: 0:00:13 (0.2106 s / it) +Averaged stats (hcp-val): loss: 0.8298 (0.8312) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +Train: [73] [ 0/6250] eta: 9:30:49 lr: 0.000023 grad: 0.1501 (0.1501) loss: 0.8299 (0.8299) time: 5.4799 data: 5.3169 max mem: 9390 +Train: [73] [ 100/6250] eta: 0:20:50 lr: 0.000023 grad: 0.1184 (0.1393) loss: 0.8256 (0.8257) time: 0.1500 data: 0.0423 max mem: 9390 +Train: [73] [ 200/6250] eta: 0:17:48 lr: 0.000023 grad: 0.1172 (0.1322) loss: 0.8195 (0.8227) time: 0.1346 data: 0.0423 max mem: 9390 +Train: [73] [ 300/6250] eta: 0:16:41 lr: 0.000023 grad: 0.1204 (0.1307) loss: 0.8178 (0.8201) time: 0.1650 data: 0.0813 max mem: 9390 +Train: [73] [ 400/6250] eta: 0:15:41 lr: 0.000023 grad: 0.1193 (0.1301) loss: 0.8170 (0.8181) time: 0.1498 data: 0.0690 max mem: 9390 +Train: [73] [ 500/6250] eta: 0:14:57 lr: 0.000023 grad: 0.1179 (0.1292) loss: 0.8114 (0.8172) time: 0.1406 data: 0.0571 max mem: 9390 +Train: [73] [ 600/6250] eta: 0:14:13 lr: 0.000023 grad: 0.1181 (0.1274) loss: 0.8178 (0.8169) time: 0.1277 data: 0.0422 max mem: 9390 +Train: [73] [ 700/6250] eta: 0:13:36 lr: 0.000023 grad: 0.1179 (0.1262) loss: 0.8169 (0.8169) time: 0.1122 data: 0.0223 max mem: 9390 +Train: [73] [ 800/6250] eta: 0:13:06 lr: 0.000023 grad: 0.1156 (0.1251) loss: 0.8166 (0.8171) time: 0.1388 data: 0.0552 max mem: 9390 +Train: [73] [ 900/6250] eta: 0:12:38 lr: 0.000023 grad: 0.1099 (0.1241) loss: 0.8201 (0.8171) time: 0.1255 data: 0.0382 max mem: 9390 +Train: [73] [1000/6250] eta: 0:12:09 lr: 0.000023 grad: 0.1152 (0.1231) loss: 0.8121 (0.8172) time: 0.1131 data: 0.0373 max mem: 9390 +Train: [73] [1100/6250] eta: 0:11:45 lr: 0.000023 grad: 0.1129 (0.1224) loss: 0.8174 (0.8171) time: 0.1169 data: 0.0312 max mem: 9390 +Train: [73] [1200/6250] eta: 0:11:23 lr: 0.000023 grad: 0.1213 (0.1219) loss: 0.8118 (0.8170) time: 0.1173 data: 0.0394 max mem: 9390 +Train: [73] [1300/6250] eta: 0:11:07 lr: 0.000023 grad: 0.1047 (0.1212) loss: 0.8111 (0.8169) time: 0.1252 data: 0.0471 max mem: 9390 +Train: [73] [1400/6250] eta: 0:10:51 lr: 0.000023 grad: 0.1131 (0.1206) loss: 0.8137 (0.8169) time: 0.1555 data: 0.0718 max mem: 9390 +Train: [73] [1500/6250] eta: 0:10:35 lr: 0.000023 grad: 0.1105 (0.1203) loss: 0.8118 (0.8169) time: 0.1344 data: 0.0533 max mem: 9390 +Train: [73] [1600/6250] eta: 0:10:23 lr: 0.000023 grad: 0.1163 (0.1199) loss: 0.8144 (0.8169) time: 0.1490 data: 0.0689 max mem: 9390 +Train: [73] [1700/6250] eta: 0:10:11 lr: 0.000023 grad: 0.1080 (0.1195) loss: 0.8186 (0.8168) time: 0.1381 data: 0.0529 max mem: 9390 +Train: [73] [1800/6250] eta: 0:09:59 lr: 0.000023 grad: 0.1073 (0.1193) loss: 0.8217 (0.8167) time: 0.0908 data: 0.0002 max mem: 9390 +Train: [73] [1900/6250] eta: 0:09:45 lr: 0.000023 grad: 0.1120 (0.1192) loss: 0.8177 (0.8165) time: 0.1301 data: 0.0472 max mem: 9390 +Train: [73] [2000/6250] eta: 0:09:32 lr: 0.000023 grad: 0.1137 (0.1191) loss: 0.8151 (0.8165) time: 0.1433 data: 0.0648 max mem: 9390 +Train: [73] [2100/6250] eta: 0:09:17 lr: 0.000023 grad: 0.1166 (0.1189) loss: 0.8157 (0.8164) time: 0.1243 data: 0.0488 max mem: 9390 +Train: [73] [2200/6250] eta: 0:09:04 lr: 0.000023 grad: 0.1182 (0.1189) loss: 0.8124 (0.8163) time: 0.1366 data: 0.0480 max mem: 9390 +Train: [73] [2300/6250] eta: 0:08:55 lr: 0.000023 grad: 0.1177 (0.1188) loss: 0.8026 (0.8162) time: 0.1837 data: 0.1093 max mem: 9390 +Train: [73] [2400/6250] eta: 0:08:42 lr: 0.000023 grad: 0.1223 (0.1189) loss: 0.8129 (0.8161) time: 0.1555 data: 0.0830 max mem: 9390 +Train: [73] [2500/6250] eta: 0:08:28 lr: 0.000023 grad: 0.1165 (0.1188) loss: 0.8155 (0.8160) time: 0.1314 data: 0.0574 max mem: 9390 +Train: [73] [2600/6250] eta: 0:08:16 lr: 0.000023 grad: 0.1223 (0.1189) loss: 0.8110 (0.8159) time: 0.1450 data: 0.0638 max mem: 9390 +Train: [73] [2700/6250] eta: 0:08:03 lr: 0.000023 grad: 0.1228 (0.1189) loss: 0.8100 (0.8157) time: 0.1467 data: 0.0601 max mem: 9390 +Train: [73] [2800/6250] eta: 0:07:51 lr: 0.000023 grad: 0.1153 (0.1191) loss: 0.8084 (0.8156) time: 0.1536 data: 0.0683 max mem: 9390 +Train: [73] [2900/6250] eta: 0:07:37 lr: 0.000023 grad: 0.1163 (0.1191) loss: 0.8132 (0.8154) time: 0.1369 data: 0.0530 max mem: 9390 +Train: [73] [3000/6250] eta: 0:07:22 lr: 0.000023 grad: 0.1161 (0.1192) loss: 0.8209 (0.8154) time: 0.1268 data: 0.0430 max mem: 9390 +Train: [73] [3100/6250] eta: 0:07:07 lr: 0.000023 grad: 0.1271 (0.1194) loss: 0.8087 (0.8153) time: 0.1319 data: 0.0525 max mem: 9390 +Train: [73] [3200/6250] eta: 0:06:52 lr: 0.000022 grad: 0.1151 (0.1195) loss: 0.8146 (0.8152) time: 0.1229 data: 0.0423 max mem: 9390 +Train: [73] [3300/6250] eta: 0:06:37 lr: 0.000022 grad: 0.1242 (0.1196) loss: 0.8091 (0.8151) time: 0.0912 data: 0.0065 max mem: 9390 +Train: [73] [3400/6250] eta: 0:06:22 lr: 0.000022 grad: 0.1214 (0.1197) loss: 0.8063 (0.8150) time: 0.1304 data: 0.0537 max mem: 9390 +Train: [73] [3500/6250] eta: 0:06:08 lr: 0.000022 grad: 0.1192 (0.1198) loss: 0.8096 (0.8149) time: 0.1355 data: 0.0553 max mem: 9390 +Train: [73] [3600/6250] eta: 0:05:53 lr: 0.000022 grad: 0.1167 (0.1199) loss: 0.8109 (0.8148) time: 0.1213 data: 0.0452 max mem: 9390 +Train: [73] [3700/6250] eta: 0:05:39 lr: 0.000022 grad: 0.1247 (0.1201) loss: 0.8114 (0.8147) time: 0.1241 data: 0.0485 max mem: 9390 +Train: [73] [3800/6250] eta: 0:05:26 lr: 0.000022 grad: 0.1228 (0.1201) loss: 0.8136 (0.8147) time: 0.1350 data: 0.0509 max mem: 9390 +Train: [73] [3900/6250] eta: 0:05:13 lr: 0.000022 grad: 0.1230 (0.1201) loss: 0.8110 (0.8147) time: 0.1527 data: 0.0798 max mem: 9390 +Train: [73] [4000/6250] eta: 0:05:00 lr: 0.000022 grad: 0.1190 (0.1202) loss: 0.8130 (0.8146) time: 0.1491 data: 0.0666 max mem: 9390 +Train: [73] [4100/6250] eta: 0:04:46 lr: 0.000022 grad: 0.1218 (0.1203) loss: 0.8097 (0.8146) time: 0.1463 data: 0.0676 max mem: 9390 +Train: [73] [4200/6250] eta: 0:04:32 lr: 0.000022 grad: 0.1155 (0.1203) loss: 0.8163 (0.8146) time: 0.1298 data: 0.0512 max mem: 9390 +Train: [73] [4300/6250] eta: 0:04:19 lr: 0.000022 grad: 0.1209 (0.1203) loss: 0.8103 (0.8146) time: 0.1214 data: 0.0371 max mem: 9390 +Train: [73] [4400/6250] eta: 0:04:06 lr: 0.000022 grad: 0.1142 (0.1204) loss: 0.8132 (0.8146) time: 0.1423 data: 0.0559 max mem: 9390 +Train: [73] [4500/6250] eta: 0:03:53 lr: 0.000022 grad: 0.1221 (0.1204) loss: 0.8106 (0.8145) time: 0.1382 data: 0.0599 max mem: 9390 +Train: [73] [4600/6250] eta: 0:03:39 lr: 0.000022 grad: 0.1173 (0.1205) loss: 0.8144 (0.8145) time: 0.1359 data: 0.0622 max mem: 9390 +Train: [73] [4700/6250] eta: 0:03:26 lr: 0.000022 grad: 0.1204 (0.1205) loss: 0.8153 (0.8145) time: 0.1355 data: 0.0575 max mem: 9390 +Train: [73] [4800/6250] eta: 0:03:13 lr: 0.000022 grad: 0.1208 (0.1205) loss: 0.8114 (0.8145) time: 0.1267 data: 0.0413 max mem: 9390 +Train: [73] [4900/6250] eta: 0:02:59 lr: 0.000022 grad: 0.1204 (0.1206) loss: 0.8109 (0.8144) time: 0.1332 data: 0.0566 max mem: 9390 +Train: [73] [5000/6250] eta: 0:02:46 lr: 0.000022 grad: 0.1189 (0.1206) loss: 0.8069 (0.8143) time: 0.1163 data: 0.0215 max mem: 9390 +Train: [73] [5100/6250] eta: 0:02:33 lr: 0.000022 grad: 0.1175 (0.1207) loss: 0.8128 (0.8142) time: 0.1429 data: 0.0699 max mem: 9390 +Train: [73] [5200/6250] eta: 0:02:20 lr: 0.000022 grad: 0.1183 (0.1208) loss: 0.8112 (0.8141) time: 0.1388 data: 0.0611 max mem: 9390 +Train: [73] [5300/6250] eta: 0:02:06 lr: 0.000022 grad: 0.1136 (0.1208) loss: 0.8154 (0.8140) time: 0.1586 data: 0.0824 max mem: 9390 +Train: [73] [5400/6250] eta: 0:01:53 lr: 0.000022 grad: 0.1190 (0.1209) loss: 0.8089 (0.8139) time: 0.1378 data: 0.0479 max mem: 9390 +Train: [73] [5500/6250] eta: 0:01:40 lr: 0.000022 grad: 0.1280 (0.1210) loss: 0.8076 (0.8138) time: 0.1341 data: 0.0564 max mem: 9390 +Train: [73] [5600/6250] eta: 0:01:27 lr: 0.000022 grad: 0.1229 (0.1211) loss: 0.8059 (0.8137) time: 0.1413 data: 0.0604 max mem: 9390 +Train: [73] [5700/6250] eta: 0:01:13 lr: 0.000022 grad: 0.1243 (0.1212) loss: 0.8024 (0.8136) time: 0.1378 data: 0.0640 max mem: 9390 +Train: [73] [5800/6250] eta: 0:01:00 lr: 0.000022 grad: 0.1154 (0.1213) loss: 0.8174 (0.8134) time: 0.1363 data: 0.0538 max mem: 9390 +Train: [73] [5900/6250] eta: 0:00:46 lr: 0.000022 grad: 0.1180 (0.1214) loss: 0.8092 (0.8134) time: 0.1411 data: 0.0605 max mem: 9390 +Train: [73] [6000/6250] eta: 0:00:33 lr: 0.000022 grad: 0.1165 (0.1214) loss: 0.8018 (0.8132) time: 0.1367 data: 0.0567 max mem: 9390 +Train: [73] [6100/6250] eta: 0:00:20 lr: 0.000022 grad: 0.1186 (0.1215) loss: 0.8091 (0.8131) time: 0.1222 data: 0.0411 max mem: 9390 +Train: [73] [6200/6250] eta: 0:00:06 lr: 0.000022 grad: 0.1265 (0.1215) loss: 0.8013 (0.8129) time: 0.1394 data: 0.0573 max mem: 9390 +Train: [73] [6249/6250] eta: 0:00:00 lr: 0.000022 grad: 0.1204 (0.1216) loss: 0.8016 (0.8128) time: 0.1348 data: 0.0470 max mem: 9390 +Train: [73] Total time: 0:14:04 (0.1352 s / it) +Averaged stats: lr: 0.000022 grad: 0.1204 (0.1216) loss: 0.8016 (0.8128) +Eval (hcp-train-subset): [73] [ 0/62] eta: 0:03:52 loss: 0.8410 (0.8410) time: 3.7455 data: 3.6761 max mem: 9390 +Eval (hcp-train-subset): [73] [61/62] eta: 0:00:00 loss: 0.8293 (0.8292) time: 0.1162 data: 0.0908 max mem: 9390 +Eval (hcp-train-subset): [73] Total time: 0:00:12 (0.2039 s / it) +Averaged stats (hcp-train-subset): loss: 0.8293 (0.8292) +Eval (hcp-val): [73] [ 0/62] eta: 0:03:50 loss: 0.8271 (0.8271) time: 3.7251 data: 3.6391 max mem: 9390 +Eval (hcp-val): [73] [61/62] eta: 0:00:00 loss: 0.8312 (0.8316) time: 0.1453 data: 0.1190 max mem: 9390 +Eval (hcp-val): [73] Total time: 0:00:12 (0.2089 s / it) +Averaged stats (hcp-val): loss: 0.8312 (0.8316) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +Train: [74] [ 0/6250] eta: 9:17:23 lr: 0.000022 grad: 0.2421 (0.2421) loss: 0.8043 (0.8043) time: 5.3509 data: 5.1986 max mem: 9390 +Train: [74] [ 100/6250] eta: 0:20:39 lr: 0.000022 grad: 0.1317 (0.1367) loss: 0.8235 (0.8288) time: 0.1392 data: 0.0453 max mem: 9390 +Train: [74] [ 200/6250] eta: 0:18:01 lr: 0.000022 grad: 0.1155 (0.1355) loss: 0.8113 (0.8216) time: 0.1439 data: 0.0522 max mem: 9390 +Train: [74] [ 300/6250] eta: 0:16:38 lr: 0.000022 grad: 0.1144 (0.1329) loss: 0.8241 (0.8182) time: 0.1364 data: 0.0491 max mem: 9390 +Train: [74] [ 400/6250] eta: 0:15:34 lr: 0.000022 grad: 0.1200 (0.1316) loss: 0.8125 (0.8155) time: 0.1345 data: 0.0509 max mem: 9390 +Train: [74] [ 500/6250] eta: 0:14:40 lr: 0.000022 grad: 0.1208 (0.1300) loss: 0.8115 (0.8149) time: 0.1085 data: 0.0166 max mem: 9390 +Train: [74] [ 600/6250] eta: 0:14:01 lr: 0.000022 grad: 0.1160 (0.1289) loss: 0.8136 (0.8145) time: 0.1186 data: 0.0375 max mem: 9390 +Train: [74] [ 700/6250] eta: 0:13:31 lr: 0.000022 grad: 0.1198 (0.1280) loss: 0.8179 (0.8144) time: 0.1376 data: 0.0557 max mem: 9390 +Train: [74] [ 800/6250] eta: 0:13:01 lr: 0.000022 grad: 0.1308 (0.1275) loss: 0.8049 (0.8140) time: 0.1380 data: 0.0569 max mem: 9390 +Train: [74] [ 900/6250] eta: 0:12:32 lr: 0.000021 grad: 0.1170 (0.1268) loss: 0.8167 (0.8138) time: 0.1089 data: 0.0228 max mem: 9390 +Train: [74] [1000/6250] eta: 0:12:09 lr: 0.000021 grad: 0.1175 (0.1261) loss: 0.8111 (0.8137) time: 0.1247 data: 0.0458 max mem: 9390 +Train: [74] [1100/6250] eta: 0:11:46 lr: 0.000021 grad: 0.1242 (0.1260) loss: 0.8088 (0.8134) time: 0.1061 data: 0.0319 max mem: 9390 +Train: [74] [1200/6250] eta: 0:11:26 lr: 0.000021 grad: 0.1205 (0.1255) loss: 0.8075 (0.8131) time: 0.1086 data: 0.0286 max mem: 9390 +Train: [74] [1300/6250] eta: 0:11:10 lr: 0.000021 grad: 0.1119 (0.1254) loss: 0.8171 (0.8128) time: 0.1425 data: 0.0630 max mem: 9390 +Train: [74] [1400/6250] eta: 0:10:53 lr: 0.000021 grad: 0.1279 (0.1256) loss: 0.8076 (0.8125) time: 0.1264 data: 0.0447 max mem: 9390 +Train: [74] [1500/6250] eta: 0:10:39 lr: 0.000021 grad: 0.1200 (0.1252) loss: 0.8121 (0.8124) time: 0.1415 data: 0.0595 max mem: 9390 +Train: [74] [1600/6250] eta: 0:10:26 lr: 0.000021 grad: 0.1258 (0.1251) loss: 0.8009 (0.8121) time: 0.1456 data: 0.0545 max mem: 9390 +Train: [74] [1700/6250] eta: 0:10:18 lr: 0.000021 grad: 0.1154 (0.1250) loss: 0.8148 (0.8119) time: 0.1272 data: 0.0489 max mem: 9390 +Train: [74] [1800/6250] eta: 0:10:06 lr: 0.000021 grad: 0.1242 (0.1249) loss: 0.8061 (0.8116) time: 0.1371 data: 0.0557 max mem: 9390 +Train: [74] [1900/6250] eta: 0:09:52 lr: 0.000021 grad: 0.1225 (0.1247) loss: 0.8139 (0.8115) time: 0.1306 data: 0.0520 max mem: 9390 +Train: [74] [2000/6250] eta: 0:09:38 lr: 0.000021 grad: 0.1143 (0.1244) loss: 0.8091 (0.8113) time: 0.1233 data: 0.0405 max mem: 9390 +Train: [74] [2100/6250] eta: 0:09:26 lr: 0.000021 grad: 0.1198 (0.1242) loss: 0.8108 (0.8113) time: 0.1623 data: 0.0692 max mem: 9390 +Train: [74] [2200/6250] eta: 0:09:17 lr: 0.000021 grad: 0.1137 (0.1239) loss: 0.8083 (0.8113) time: 0.1940 data: 0.1172 max mem: 9390 +Train: [74] [2300/6250] eta: 0:09:03 lr: 0.000021 grad: 0.1144 (0.1236) loss: 0.8121 (0.8113) time: 0.1310 data: 0.0514 max mem: 9390 +Train: [74] [2400/6250] eta: 0:08:50 lr: 0.000021 grad: 0.1097 (0.1233) loss: 0.8167 (0.8114) time: 0.1422 data: 0.0589 max mem: 9390 +Train: [74] [2500/6250] eta: 0:08:37 lr: 0.000021 grad: 0.1157 (0.1232) loss: 0.8083 (0.8114) time: 0.1480 data: 0.0684 max mem: 9390 +Train: [74] [2600/6250] eta: 0:08:25 lr: 0.000021 grad: 0.1158 (0.1230) loss: 0.8141 (0.8114) time: 0.1338 data: 0.0524 max mem: 9390 +Train: [74] [2700/6250] eta: 0:08:11 lr: 0.000021 grad: 0.1205 (0.1229) loss: 0.8041 (0.8114) time: 0.1298 data: 0.0469 max mem: 9390 +Train: [74] [2800/6250] eta: 0:07:57 lr: 0.000021 grad: 0.1114 (0.1228) loss: 0.8126 (0.8115) time: 0.1415 data: 0.0614 max mem: 9390 +Train: [74] [2900/6250] eta: 0:07:42 lr: 0.000021 grad: 0.1132 (0.1227) loss: 0.8132 (0.8115) time: 0.0998 data: 0.0189 max mem: 9390 +Train: [74] [3000/6250] eta: 0:07:26 lr: 0.000021 grad: 0.1144 (0.1228) loss: 0.8141 (0.8115) time: 0.1053 data: 0.0173 max mem: 9390 +Train: [74] [3100/6250] eta: 0:07:11 lr: 0.000021 grad: 0.1171 (0.1228) loss: 0.8075 (0.8115) time: 0.1293 data: 0.0425 max mem: 9390 +Train: [74] [3200/6250] eta: 0:06:55 lr: 0.000021 grad: 0.1235 (0.1228) loss: 0.8171 (0.8115) time: 0.1061 data: 0.0290 max mem: 9390 +Train: [74] [3300/6250] eta: 0:06:40 lr: 0.000021 grad: 0.1140 (0.1227) loss: 0.8123 (0.8116) time: 0.1206 data: 0.0441 max mem: 9390 +Train: [74] [3400/6250] eta: 0:06:26 lr: 0.000021 grad: 0.1197 (0.1227) loss: 0.8103 (0.8116) time: 0.1419 data: 0.0662 max mem: 9390 +Train: [74] [3500/6250] eta: 0:06:12 lr: 0.000021 grad: 0.1196 (0.1227) loss: 0.8149 (0.8116) time: 0.1491 data: 0.0608 max mem: 9390 +Train: [74] [3600/6250] eta: 0:05:59 lr: 0.000021 grad: 0.1194 (0.1226) loss: 0.8018 (0.8115) time: 0.1312 data: 0.0537 max mem: 9390 +Train: [74] [3700/6250] eta: 0:05:45 lr: 0.000021 grad: 0.1162 (0.1227) loss: 0.8141 (0.8115) time: 0.1351 data: 0.0587 max mem: 9390 +Train: [74] [3800/6250] eta: 0:05:31 lr: 0.000021 grad: 0.1159 (0.1226) loss: 0.8155 (0.8115) time: 0.1179 data: 0.0313 max mem: 9390 +Train: [74] [3900/6250] eta: 0:05:18 lr: 0.000021 grad: 0.1197 (0.1226) loss: 0.8066 (0.8115) time: 0.0854 data: 0.0002 max mem: 9390 +Train: [74] [4000/6250] eta: 0:05:04 lr: 0.000021 grad: 0.1165 (0.1226) loss: 0.8099 (0.8115) time: 0.1435 data: 0.0706 max mem: 9390 +Train: [74] [4100/6250] eta: 0:04:51 lr: 0.000021 grad: 0.1162 (0.1225) loss: 0.8148 (0.8115) time: 0.1587 data: 0.0817 max mem: 9390 +Train: [74] [4200/6250] eta: 0:04:37 lr: 0.000021 grad: 0.1202 (0.1225) loss: 0.8155 (0.8116) time: 0.1294 data: 0.0421 max mem: 9390 +Train: [74] [4300/6250] eta: 0:04:23 lr: 0.000021 grad: 0.1207 (0.1225) loss: 0.8064 (0.8116) time: 0.1418 data: 0.0631 max mem: 9390 +Train: [74] [4400/6250] eta: 0:04:10 lr: 0.000021 grad: 0.1206 (0.1224) loss: 0.8118 (0.8117) time: 0.1853 data: 0.0850 max mem: 9390 +Train: [74] [4500/6250] eta: 0:03:57 lr: 0.000021 grad: 0.1080 (0.1224) loss: 0.8169 (0.8117) time: 0.1235 data: 0.0483 max mem: 9390 +Train: [74] [4600/6250] eta: 0:03:43 lr: 0.000021 grad: 0.1168 (0.1224) loss: 0.8105 (0.8116) time: 0.1296 data: 0.0561 max mem: 9390 +Train: [74] [4700/6250] eta: 0:03:30 lr: 0.000021 grad: 0.1164 (0.1224) loss: 0.8123 (0.8116) time: 0.1522 data: 0.0630 max mem: 9390 +Train: [74] [4800/6250] eta: 0:03:16 lr: 0.000021 grad: 0.1241 (0.1224) loss: 0.8030 (0.8115) time: 0.1250 data: 0.0518 max mem: 9390 +Train: [74] [4900/6250] eta: 0:03:03 lr: 0.000020 grad: 0.1205 (0.1225) loss: 0.8080 (0.8114) time: 0.1357 data: 0.0591 max mem: 9390 +Train: [74] [5000/6250] eta: 0:02:49 lr: 0.000020 grad: 0.1239 (0.1226) loss: 0.8058 (0.8114) time: 0.1553 data: 0.0798 max mem: 9390 +Train: [74] [5100/6250] eta: 0:02:36 lr: 0.000020 grad: 0.1276 (0.1226) loss: 0.8034 (0.8113) time: 0.1624 data: 0.0842 max mem: 9390 +Train: [74] [5200/6250] eta: 0:02:22 lr: 0.000020 grad: 0.1214 (0.1228) loss: 0.8119 (0.8112) time: 0.1375 data: 0.0588 max mem: 9390 +Train: [74] [5300/6250] eta: 0:02:08 lr: 0.000020 grad: 0.1215 (0.1229) loss: 0.8090 (0.8111) time: 0.1241 data: 0.0442 max mem: 9390 +Train: [74] [5400/6250] eta: 0:01:55 lr: 0.000020 grad: 0.1214 (0.1229) loss: 0.8063 (0.8111) time: 0.1468 data: 0.0691 max mem: 9390 +Train: [74] [5500/6250] eta: 0:01:41 lr: 0.000020 grad: 0.1240 (0.1230) loss: 0.8115 (0.8110) time: 0.1670 data: 0.0830 max mem: 9390 +Train: [74] [5600/6250] eta: 0:01:28 lr: 0.000020 grad: 0.1212 (0.1230) loss: 0.8121 (0.8110) time: 0.1153 data: 0.0379 max mem: 9390 +Train: [74] [5700/6250] eta: 0:01:14 lr: 0.000020 grad: 0.1231 (0.1231) loss: 0.8073 (0.8109) time: 0.1244 data: 0.0491 max mem: 9390 +Train: [74] [5800/6250] eta: 0:01:01 lr: 0.000020 grad: 0.1242 (0.1231) loss: 0.8038 (0.8109) time: 0.1201 data: 0.0394 max mem: 9390 +Train: [74] [5900/6250] eta: 0:00:47 lr: 0.000020 grad: 0.1320 (0.1233) loss: 0.8034 (0.8108) time: 0.1519 data: 0.0763 max mem: 9390 +Train: [74] [6000/6250] eta: 0:00:33 lr: 0.000020 grad: 0.1258 (0.1233) loss: 0.8094 (0.8107) time: 0.1179 data: 0.0401 max mem: 9390 +Train: [74] [6100/6250] eta: 0:00:20 lr: 0.000020 grad: 0.1177 (0.1234) loss: 0.8079 (0.8107) time: 0.1117 data: 0.0328 max mem: 9390 +Train: [74] [6200/6250] eta: 0:00:06 lr: 0.000020 grad: 0.1267 (0.1234) loss: 0.8115 (0.8107) time: 0.1302 data: 0.0516 max mem: 9390 +Train: [74] [6249/6250] eta: 0:00:00 lr: 0.000020 grad: 0.1199 (0.1234) loss: 0.8120 (0.8107) time: 0.1301 data: 0.0520 max mem: 9390 +Train: [74] Total time: 0:14:11 (0.1363 s / it) +Averaged stats: lr: 0.000020 grad: 0.1199 (0.1234) loss: 0.8120 (0.8107) +Eval (hcp-train-subset): [74] [ 0/62] eta: 0:04:56 loss: 0.8375 (0.8375) time: 4.7775 data: 4.7486 max mem: 9390 +Eval (hcp-train-subset): [74] [61/62] eta: 0:00:00 loss: 0.8226 (0.8253) time: 0.1400 data: 0.1151 max mem: 9390 +Eval (hcp-train-subset): [74] Total time: 0:00:12 (0.2055 s / it) +Averaged stats (hcp-train-subset): loss: 0.8226 (0.8253) +Making plots (hcp-train-subset): example=29 +Eval (hcp-val): [74] [ 0/62] eta: 0:04:58 loss: 0.8305 (0.8305) time: 4.8175 data: 4.7884 max mem: 9390 +Eval (hcp-val): [74] [61/62] eta: 0:00:00 loss: 0.8302 (0.8313) time: 0.1347 data: 0.1077 max mem: 9390 +Eval (hcp-val): [74] Total time: 0:00:12 (0.2063 s / it) +Averaged stats (hcp-val): loss: 0.8302 (0.8313) +Making plots (hcp-val): example=61 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +Train: [75] [ 0/6250] eta: 10:02:59 lr: 0.000020 grad: 0.2154 (0.2154) loss: 0.8587 (0.8587) time: 5.7887 data: 5.6771 max mem: 9390 +Train: [75] [ 100/6250] eta: 0:20:25 lr: 0.000020 grad: 0.1246 (0.1187) loss: 0.8374 (0.8405) time: 0.1577 data: 0.0705 max mem: 9390 +Train: [75] [ 200/6250] eta: 0:17:23 lr: 0.000020 grad: 0.1138 (0.1231) loss: 0.8301 (0.8323) time: 0.1408 data: 0.0547 max mem: 9390 +Train: [75] [ 300/6250] eta: 0:15:59 lr: 0.000020 grad: 0.1263 (0.1249) loss: 0.8142 (0.8278) time: 0.1308 data: 0.0445 max mem: 9390 +Train: [75] [ 400/6250] eta: 0:15:06 lr: 0.000020 grad: 0.1079 (0.1230) loss: 0.8304 (0.8265) time: 0.1400 data: 0.0625 max mem: 9390 +Train: [75] [ 500/6250] eta: 0:14:16 lr: 0.000020 grad: 0.1142 (0.1217) loss: 0.8233 (0.8258) time: 0.1191 data: 0.0397 max mem: 9390 +Train: [75] [ 600/6250] eta: 0:13:37 lr: 0.000020 grad: 0.1178 (0.1214) loss: 0.8204 (0.8250) time: 0.1292 data: 0.0480 max mem: 9390 +Train: [75] [ 700/6250] eta: 0:13:05 lr: 0.000020 grad: 0.1093 (0.1208) loss: 0.8229 (0.8243) time: 0.1117 data: 0.0314 max mem: 9390 +Train: [75] [ 800/6250] eta: 0:12:40 lr: 0.000020 grad: 0.1100 (0.1202) loss: 0.8257 (0.8241) time: 0.1153 data: 0.0294 max mem: 9390 +Train: [75] [ 900/6250] eta: 0:12:15 lr: 0.000020 grad: 0.1117 (0.1197) loss: 0.8169 (0.8237) time: 0.1107 data: 0.0267 max mem: 9390 +Train: [75] [1000/6250] eta: 0:11:51 lr: 0.000020 grad: 0.1153 (0.1195) loss: 0.8153 (0.8231) time: 0.1150 data: 0.0367 max mem: 9390 +Train: [75] [1100/6250] eta: 0:11:26 lr: 0.000020 grad: 0.1216 (0.1193) loss: 0.8172 (0.8227) time: 0.1036 data: 0.0260 max mem: 9390 +Train: [75] [1200/6250] eta: 0:11:07 lr: 0.000020 grad: 0.1147 (0.1191) loss: 0.8173 (0.8222) time: 0.1271 data: 0.0497 max mem: 9390 +Train: [75] [1300/6250] eta: 0:10:47 lr: 0.000020 grad: 0.1166 (0.1191) loss: 0.8144 (0.8217) time: 0.1145 data: 0.0421 max mem: 9390 +Train: [75] [1400/6250] eta: 0:10:31 lr: 0.000020 grad: 0.1134 (0.1189) loss: 0.8191 (0.8213) time: 0.1296 data: 0.0516 max mem: 9390 +Train: [75] [1500/6250] eta: 0:10:15 lr: 0.000020 grad: 0.1179 (0.1189) loss: 0.8200 (0.8210) time: 0.1265 data: 0.0410 max mem: 9390 +Train: [75] [1600/6250] eta: 0:10:02 lr: 0.000020 grad: 0.1100 (0.1187) loss: 0.8198 (0.8208) time: 0.1418 data: 0.0659 max mem: 9390 +Train: [75] [1700/6250] eta: 0:09:50 lr: 0.000020 grad: 0.1147 (0.1189) loss: 0.8140 (0.8205) time: 0.1553 data: 0.0766 max mem: 9390 +Train: [75] [1800/6250] eta: 0:09:37 lr: 0.000020 grad: 0.1126 (0.1188) loss: 0.8227 (0.8203) time: 0.1333 data: 0.0605 max mem: 9390 +Train: [75] [1900/6250] eta: 0:09:23 lr: 0.000020 grad: 0.1182 (0.1189) loss: 0.8159 (0.8201) time: 0.1006 data: 0.0189 max mem: 9390 +Train: [75] [2000/6250] eta: 0:09:11 lr: 0.000020 grad: 0.1125 (0.1188) loss: 0.8182 (0.8199) time: 0.1065 data: 0.0261 max mem: 9390 +Train: [75] [2100/6250] eta: 0:09:00 lr: 0.000020 grad: 0.1154 (0.1187) loss: 0.8179 (0.8198) time: 0.1313 data: 0.0447 max mem: 9390 +Train: [75] [2200/6250] eta: 0:08:54 lr: 0.000020 grad: 0.1167 (0.1189) loss: 0.8139 (0.8196) time: 0.1651 data: 0.0841 max mem: 9390 +Train: [75] [2300/6250] eta: 0:08:43 lr: 0.000020 grad: 0.1199 (0.1190) loss: 0.8110 (0.8193) time: 0.1383 data: 0.0593 max mem: 9390 +Train: [75] [2400/6250] eta: 0:08:32 lr: 0.000020 grad: 0.1126 (0.1193) loss: 0.8149 (0.8190) time: 0.1533 data: 0.0773 max mem: 9390 +Train: [75] [2500/6250] eta: 0:08:21 lr: 0.000020 grad: 0.1231 (0.1194) loss: 0.8145 (0.8187) time: 0.1394 data: 0.0625 max mem: 9390 +Train: [75] [2600/6250] eta: 0:08:08 lr: 0.000020 grad: 0.1198 (0.1194) loss: 0.8134 (0.8184) time: 0.1261 data: 0.0460 max mem: 9390 +Train: [75] [2700/6250] eta: 0:07:55 lr: 0.000020 grad: 0.1229 (0.1197) loss: 0.8085 (0.8181) time: 0.1318 data: 0.0537 max mem: 9390 +Train: [75] [2800/6250] eta: 0:07:41 lr: 0.000019 grad: 0.1155 (0.1198) loss: 0.8112 (0.8179) time: 0.1263 data: 0.0496 max mem: 9390 +Train: [75] [2900/6250] eta: 0:07:26 lr: 0.000019 grad: 0.1205 (0.1199) loss: 0.8114 (0.8178) time: 0.1328 data: 0.0548 max mem: 9390 +Train: [75] [3000/6250] eta: 0:07:11 lr: 0.000019 grad: 0.1166 (0.1200) loss: 0.8184 (0.8176) time: 0.1134 data: 0.0383 max mem: 9390 +Train: [75] [3100/6250] eta: 0:06:56 lr: 0.000019 grad: 0.1195 (0.1202) loss: 0.8091 (0.8175) time: 0.1286 data: 0.0489 max mem: 9390 +Train: [75] [3200/6250] eta: 0:06:42 lr: 0.000019 grad: 0.1294 (0.1203) loss: 0.8112 (0.8174) time: 0.1100 data: 0.0297 max mem: 9390 +Train: [75] [3300/6250] eta: 0:06:27 lr: 0.000019 grad: 0.1320 (0.1206) loss: 0.8086 (0.8171) time: 0.1043 data: 0.0274 max mem: 9390 +Train: [75] [3400/6250] eta: 0:06:13 lr: 0.000019 grad: 0.1292 (0.1207) loss: 0.8128 (0.8170) time: 0.1340 data: 0.0534 max mem: 9390 +Train: [75] [3500/6250] eta: 0:06:00 lr: 0.000019 grad: 0.1150 (0.1208) loss: 0.8126 (0.8169) time: 0.1397 data: 0.0651 max mem: 9390 +Train: [75] [3600/6250] eta: 0:05:47 lr: 0.000019 grad: 0.1196 (0.1210) loss: 0.8142 (0.8167) time: 0.1228 data: 0.0387 max mem: 9390 +Train: [75] [3700/6250] eta: 0:05:34 lr: 0.000019 grad: 0.1213 (0.1212) loss: 0.8061 (0.8165) time: 0.1181 data: 0.0382 max mem: 9390 +Train: [75] [3800/6250] eta: 0:05:20 lr: 0.000019 grad: 0.1189 (0.1214) loss: 0.8118 (0.8163) time: 0.1369 data: 0.0587 max mem: 9390 +Train: [75] [3900/6250] eta: 0:05:07 lr: 0.000019 grad: 0.1252 (0.1215) loss: 0.8085 (0.8162) time: 0.1372 data: 0.0565 max mem: 9390 +Train: [75] [4000/6250] eta: 0:04:54 lr: 0.000019 grad: 0.1240 (0.1216) loss: 0.8136 (0.8161) time: 0.1317 data: 0.0499 max mem: 9390 +Train: [75] [4100/6250] eta: 0:04:41 lr: 0.000019 grad: 0.1205 (0.1216) loss: 0.8131 (0.8160) time: 0.1257 data: 0.0462 max mem: 9390 +Train: [75] [4200/6250] eta: 0:04:28 lr: 0.000019 grad: 0.1250 (0.1217) loss: 0.8149 (0.8159) time: 0.1349 data: 0.0578 max mem: 9390 +Train: [75] [4300/6250] eta: 0:04:15 lr: 0.000019 grad: 0.1216 (0.1218) loss: 0.8113 (0.8158) time: 0.1230 data: 0.0417 max mem: 9390 +Train: [75] [4400/6250] eta: 0:04:02 lr: 0.000019 grad: 0.1184 (0.1219) loss: 0.8173 (0.8157) time: 0.1440 data: 0.0687 max mem: 9390 +Train: [75] [4500/6250] eta: 0:03:49 lr: 0.000019 grad: 0.1178 (0.1220) loss: 0.8178 (0.8156) time: 0.1177 data: 0.0429 max mem: 9390 +Train: [75] [4600/6250] eta: 0:03:36 lr: 0.000019 grad: 0.1207 (0.1220) loss: 0.8109 (0.8154) time: 0.1241 data: 0.0418 max mem: 9390 +Train: [75] [4700/6250] eta: 0:03:23 lr: 0.000019 grad: 0.1266 (0.1221) loss: 0.8076 (0.8153) time: 0.1239 data: 0.0454 max mem: 9390 +Train: [75] [4800/6250] eta: 0:03:10 lr: 0.000019 grad: 0.1237 (0.1222) loss: 0.8032 (0.8152) time: 0.1389 data: 0.0594 max mem: 9390 +Train: [75] [4900/6250] eta: 0:02:57 lr: 0.000019 grad: 0.1180 (0.1223) loss: 0.8159 (0.8151) time: 0.1442 data: 0.0658 max mem: 9390 +Train: [75] [5000/6250] eta: 0:02:44 lr: 0.000019 grad: 0.1234 (0.1224) loss: 0.8104 (0.8151) time: 0.1580 data: 0.0801 max mem: 9390 +Train: [75] [5100/6250] eta: 0:02:31 lr: 0.000019 grad: 0.1222 (0.1224) loss: 0.8113 (0.8150) time: 0.1382 data: 0.0609 max mem: 9390 +Train: [75] [5200/6250] eta: 0:02:18 lr: 0.000019 grad: 0.1236 (0.1225) loss: 0.8130 (0.8149) time: 0.1527 data: 0.0738 max mem: 9390 +Train: [75] [5300/6250] eta: 0:02:05 lr: 0.000019 grad: 0.1268 (0.1226) loss: 0.8135 (0.8148) time: 0.1358 data: 0.0604 max mem: 9390 +Train: [75] [5400/6250] eta: 0:01:52 lr: 0.000019 grad: 0.1212 (0.1227) loss: 0.8073 (0.8147) time: 0.1430 data: 0.0650 max mem: 9390 +Train: [75] [5500/6250] eta: 0:01:39 lr: 0.000019 grad: 0.1153 (0.1227) loss: 0.8181 (0.8146) time: 0.1437 data: 0.0589 max mem: 9390 +Train: [75] [5600/6250] eta: 0:01:26 lr: 0.000019 grad: 0.1211 (0.1228) loss: 0.8137 (0.8145) time: 0.1433 data: 0.0657 max mem: 9390 +Train: [75] [5700/6250] eta: 0:01:12 lr: 0.000019 grad: 0.1254 (0.1229) loss: 0.8128 (0.8145) time: 0.1343 data: 0.0494 max mem: 9390 +Train: [75] [5800/6250] eta: 0:00:59 lr: 0.000019 grad: 0.1267 (0.1229) loss: 0.8059 (0.8144) time: 0.1362 data: 0.0619 max mem: 9390 +Train: [75] [5900/6250] eta: 0:00:46 lr: 0.000019 grad: 0.1197 (0.1230) loss: 0.8103 (0.8143) time: 0.1295 data: 0.0512 max mem: 9390 +Train: [75] [6000/6250] eta: 0:00:33 lr: 0.000019 grad: 0.1247 (0.1231) loss: 0.8099 (0.8142) time: 0.1441 data: 0.0684 max mem: 9390 +Train: [75] [6100/6250] eta: 0:00:19 lr: 0.000019 grad: 0.1195 (0.1232) loss: 0.8134 (0.8141) time: 0.1245 data: 0.0449 max mem: 9390 +Train: [75] [6200/6250] eta: 0:00:06 lr: 0.000019 grad: 0.1191 (0.1233) loss: 0.8104 (0.8141) time: 0.1473 data: 0.0622 max mem: 9390 +Train: [75] [6249/6250] eta: 0:00:00 lr: 0.000019 grad: 0.1256 (0.1233) loss: 0.8086 (0.8140) time: 0.1613 data: 0.0779 max mem: 9390 +Train: [75] Total time: 0:13:57 (0.1341 s / it) +Averaged stats: lr: 0.000019 grad: 0.1256 (0.1233) loss: 0.8086 (0.8140) +Eval (hcp-train-subset): [75] [ 0/62] eta: 0:03:27 loss: 0.8430 (0.8430) time: 3.3453 data: 3.2803 max mem: 9390 +Eval (hcp-train-subset): [75] [61/62] eta: 0:00:00 loss: 0.8239 (0.8258) time: 0.1137 data: 0.0888 max mem: 9390 +Eval (hcp-train-subset): [75] Total time: 0:00:12 (0.2003 s / it) +Averaged stats (hcp-train-subset): loss: 0.8239 (0.8258) +Eval (hcp-val): [75] [ 0/62] eta: 0:04:35 loss: 0.8275 (0.8275) time: 4.4511 data: 4.4225 max mem: 9390 +Eval (hcp-val): [75] [61/62] eta: 0:00:00 loss: 0.8293 (0.8315) time: 0.1282 data: 0.1033 max mem: 9390 +Eval (hcp-val): [75] Total time: 0:00:12 (0.2042 s / it) +Averaged stats (hcp-val): loss: 0.8293 (0.8315) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +Train: [76] [ 0/6250] eta: 10:05:53 lr: 0.000019 grad: 0.1493 (0.1493) loss: 0.8256 (0.8256) time: 5.8166 data: 5.7266 max mem: 9390 +Train: [76] [ 100/6250] eta: 0:20:40 lr: 0.000019 grad: 0.1235 (0.1475) loss: 0.8324 (0.8306) time: 0.1468 data: 0.0581 max mem: 9390 +Train: [76] [ 200/6250] eta: 0:17:52 lr: 0.000019 grad: 0.1335 (0.1457) loss: 0.8185 (0.8209) time: 0.1736 data: 0.0767 max mem: 9390 +Train: [76] [ 300/6250] eta: 0:16:43 lr: 0.000019 grad: 0.1243 (0.1407) loss: 0.8206 (0.8185) time: 0.1348 data: 0.0478 max mem: 9390 +Train: [76] [ 400/6250] eta: 0:15:50 lr: 0.000019 grad: 0.1280 (0.1388) loss: 0.8167 (0.8173) time: 0.1285 data: 0.0414 max mem: 9390 +Train: [76] [ 500/6250] eta: 0:15:04 lr: 0.000019 grad: 0.1244 (0.1370) loss: 0.8137 (0.8163) time: 0.1558 data: 0.0767 max mem: 9390 +Train: [76] [ 600/6250] eta: 0:14:19 lr: 0.000019 grad: 0.1210 (0.1350) loss: 0.8137 (0.8158) time: 0.1209 data: 0.0339 max mem: 9390 +Train: [76] [ 700/6250] eta: 0:13:44 lr: 0.000019 grad: 0.1284 (0.1346) loss: 0.8078 (0.8150) time: 0.1390 data: 0.0547 max mem: 9390 +Train: [76] [ 800/6250] eta: 0:13:10 lr: 0.000018 grad: 0.1216 (0.1339) loss: 0.8103 (0.8145) time: 0.1291 data: 0.0359 max mem: 9390 +Train: [76] [ 900/6250] eta: 0:12:43 lr: 0.000018 grad: 0.1183 (0.1332) loss: 0.8166 (0.8142) time: 0.1208 data: 0.0365 max mem: 9390 +Train: [76] [1000/6250] eta: 0:12:17 lr: 0.000018 grad: 0.1206 (0.1323) loss: 0.8172 (0.8140) time: 0.1254 data: 0.0491 max mem: 9390 +Train: [76] [1100/6250] eta: 0:11:58 lr: 0.000018 grad: 0.1187 (0.1315) loss: 0.8150 (0.8138) time: 0.1205 data: 0.0423 max mem: 9390 +Train: [76] [1200/6250] eta: 0:11:40 lr: 0.000018 grad: 0.1164 (0.1304) loss: 0.8132 (0.8138) time: 0.1047 data: 0.0211 max mem: 9390 +Train: [76] [1300/6250] eta: 0:11:21 lr: 0.000018 grad: 0.1150 (0.1297) loss: 0.8167 (0.8139) time: 0.1119 data: 0.0312 max mem: 9390 +Train: [76] [1400/6250] eta: 0:11:04 lr: 0.000018 grad: 0.1186 (0.1292) loss: 0.8187 (0.8139) time: 0.1234 data: 0.0373 max mem: 9390 +Train: [76] [1500/6250] eta: 0:10:50 lr: 0.000018 grad: 0.1220 (0.1287) loss: 0.8100 (0.8137) time: 0.1445 data: 0.0691 max mem: 9390 +Train: [76] [1600/6250] eta: 0:10:36 lr: 0.000018 grad: 0.1216 (0.1281) loss: 0.8156 (0.8138) time: 0.1606 data: 0.0849 max mem: 9390 +Train: [76] [1700/6250] eta: 0:10:24 lr: 0.000018 grad: 0.1200 (0.1279) loss: 0.8059 (0.8136) time: 0.1341 data: 0.0475 max mem: 9390 +Train: [76] [1800/6250] eta: 0:10:09 lr: 0.000018 grad: 0.1254 (0.1277) loss: 0.8044 (0.8135) time: 0.1470 data: 0.0715 max mem: 9390 +Train: [76] [1900/6250] eta: 0:09:54 lr: 0.000018 grad: 0.1235 (0.1274) loss: 0.8021 (0.8133) time: 0.1219 data: 0.0417 max mem: 9390 +Train: [76] [2000/6250] eta: 0:09:40 lr: 0.000018 grad: 0.1142 (0.1272) loss: 0.8147 (0.8132) time: 0.1376 data: 0.0541 max mem: 9390 +Train: [76] [2100/6250] eta: 0:09:31 lr: 0.000018 grad: 0.1254 (0.1270) loss: 0.8060 (0.8131) time: 0.1660 data: 0.0894 max mem: 9390 +Train: [76] [2200/6250] eta: 0:09:18 lr: 0.000018 grad: 0.1217 (0.1269) loss: 0.8153 (0.8130) time: 0.1443 data: 0.0673 max mem: 9390 +Train: [76] [2300/6250] eta: 0:09:09 lr: 0.000018 grad: 0.1261 (0.1268) loss: 0.8022 (0.8128) time: 0.2346 data: 0.1593 max mem: 9390 +Train: [76] [2400/6250] eta: 0:08:56 lr: 0.000018 grad: 0.1233 (0.1270) loss: 0.8002 (0.8126) time: 0.1712 data: 0.0887 max mem: 9390 +Train: [76] [2500/6250] eta: 0:08:41 lr: 0.000018 grad: 0.1288 (0.1270) loss: 0.8087 (0.8123) time: 0.1463 data: 0.0663 max mem: 9390 +Train: [76] [2600/6250] eta: 0:08:27 lr: 0.000018 grad: 0.1244 (0.1270) loss: 0.8096 (0.8121) time: 0.1377 data: 0.0573 max mem: 9390 +Train: [76] [2700/6250] eta: 0:08:13 lr: 0.000018 grad: 0.1285 (0.1269) loss: 0.8025 (0.8120) time: 0.1164 data: 0.0363 max mem: 9390 +Train: [76] [2800/6250] eta: 0:07:58 lr: 0.000018 grad: 0.1260 (0.1270) loss: 0.8076 (0.8118) time: 0.1381 data: 0.0597 max mem: 9390 +Train: [76] [2900/6250] eta: 0:07:41 lr: 0.000018 grad: 0.1260 (0.1270) loss: 0.8087 (0.8118) time: 0.1118 data: 0.0277 max mem: 9390 +Train: [76] [3000/6250] eta: 0:07:25 lr: 0.000018 grad: 0.1271 (0.1270) loss: 0.8121 (0.8117) time: 0.1239 data: 0.0467 max mem: 9390 +Train: [76] [3100/6250] eta: 0:07:09 lr: 0.000018 grad: 0.1287 (0.1271) loss: 0.8091 (0.8115) time: 0.1081 data: 0.0289 max mem: 9390 +Train: [76] [3200/6250] eta: 0:06:54 lr: 0.000018 grad: 0.1216 (0.1271) loss: 0.8099 (0.8114) time: 0.1222 data: 0.0413 max mem: 9390 +Train: [76] [3300/6250] eta: 0:06:39 lr: 0.000018 grad: 0.1276 (0.1272) loss: 0.8160 (0.8114) time: 0.1347 data: 0.0581 max mem: 9390 +Train: [76] [3400/6250] eta: 0:06:24 lr: 0.000018 grad: 0.1295 (0.1274) loss: 0.8106 (0.8114) time: 0.1202 data: 0.0392 max mem: 9390 +Train: [76] [3500/6250] eta: 0:06:11 lr: 0.000018 grad: 0.1274 (0.1275) loss: 0.8094 (0.8114) time: 0.1442 data: 0.0674 max mem: 9390 +Train: [76] [3600/6250] eta: 0:05:58 lr: 0.000018 grad: 0.1278 (0.1275) loss: 0.8080 (0.8113) time: 0.1331 data: 0.0488 max mem: 9390 +Train: [76] [3700/6250] eta: 0:05:44 lr: 0.000018 grad: 0.1225 (0.1276) loss: 0.8095 (0.8112) time: 0.1272 data: 0.0467 max mem: 9390 +Train: [76] [3800/6250] eta: 0:05:30 lr: 0.000018 grad: 0.1263 (0.1277) loss: 0.8138 (0.8112) time: 0.1129 data: 0.0319 max mem: 9390 +Train: [76] [3900/6250] eta: 0:05:17 lr: 0.000018 grad: 0.1284 (0.1277) loss: 0.8064 (0.8112) time: 0.1556 data: 0.0793 max mem: 9390 +Train: [76] [4000/6250] eta: 0:05:03 lr: 0.000018 grad: 0.1332 (0.1278) loss: 0.8067 (0.8112) time: 0.1464 data: 0.0598 max mem: 9390 +Train: [76] [4100/6250] eta: 0:04:50 lr: 0.000018 grad: 0.1301 (0.1279) loss: 0.8130 (0.8111) time: 0.1307 data: 0.0556 max mem: 9390 +Train: [76] [4200/6250] eta: 0:04:36 lr: 0.000018 grad: 0.1288 (0.1279) loss: 0.8139 (0.8111) time: 0.1236 data: 0.0403 max mem: 9390 +Train: [76] [4300/6250] eta: 0:04:23 lr: 0.000018 grad: 0.1221 (0.1278) loss: 0.8074 (0.8112) time: 0.1098 data: 0.0199 max mem: 9390 +Train: [76] [4400/6250] eta: 0:04:11 lr: 0.000018 grad: 0.1211 (0.1279) loss: 0.8117 (0.8112) time: 0.1370 data: 0.0627 max mem: 9390 +Train: [76] [4500/6250] eta: 0:03:57 lr: 0.000018 grad: 0.1348 (0.1279) loss: 0.8080 (0.8111) time: 0.1244 data: 0.0472 max mem: 9390 +Train: [76] [4600/6250] eta: 0:03:44 lr: 0.000018 grad: 0.1305 (0.1280) loss: 0.8158 (0.8111) time: 0.1215 data: 0.0397 max mem: 9390 +Train: [76] [4700/6250] eta: 0:03:30 lr: 0.000018 grad: 0.1207 (0.1280) loss: 0.8123 (0.8110) time: 0.1343 data: 0.0509 max mem: 9390 +Train: [76] [4800/6250] eta: 0:03:17 lr: 0.000018 grad: 0.1268 (0.1280) loss: 0.8117 (0.8110) time: 0.1348 data: 0.0531 max mem: 9390 +Train: [76] [4900/6250] eta: 0:03:04 lr: 0.000018 grad: 0.1258 (0.1281) loss: 0.8145 (0.8110) time: 0.2426 data: 0.1622 max mem: 9390 +Train: [76] [5000/6250] eta: 0:02:50 lr: 0.000018 grad: 0.1261 (0.1281) loss: 0.8180 (0.8110) time: 0.1298 data: 0.0398 max mem: 9390 +Train: [76] [5100/6250] eta: 0:02:37 lr: 0.000017 grad: 0.1220 (0.1281) loss: 0.8212 (0.8110) time: 0.1278 data: 0.0472 max mem: 9390 +Train: [76] [5200/6250] eta: 0:02:23 lr: 0.000017 grad: 0.1233 (0.1281) loss: 0.8158 (0.8110) time: 0.1219 data: 0.0453 max mem: 9390 +Train: [76] [5300/6250] eta: 0:02:09 lr: 0.000017 grad: 0.1265 (0.1282) loss: 0.8151 (0.8110) time: 0.1138 data: 0.0356 max mem: 9390 +Train: [76] [5400/6250] eta: 0:01:56 lr: 0.000017 grad: 0.1269 (0.1282) loss: 0.8155 (0.8111) time: 0.1400 data: 0.0592 max mem: 9390 +Train: [76] [5500/6250] eta: 0:01:42 lr: 0.000017 grad: 0.1333 (0.1283) loss: 0.8097 (0.8110) time: 0.1115 data: 0.0303 max mem: 9390 +Train: [76] [5600/6250] eta: 0:01:28 lr: 0.000017 grad: 0.1232 (0.1283) loss: 0.8119 (0.8110) time: 0.1476 data: 0.0696 max mem: 9390 +Train: [76] [5700/6250] eta: 0:01:15 lr: 0.000017 grad: 0.1362 (0.1283) loss: 0.8075 (0.8110) time: 0.1254 data: 0.0514 max mem: 9390 +Train: [76] [5800/6250] eta: 0:01:01 lr: 0.000017 grad: 0.1231 (0.1283) loss: 0.8045 (0.8110) time: 0.1249 data: 0.0477 max mem: 9390 +Train: [76] [5900/6250] eta: 0:00:47 lr: 0.000017 grad: 0.1253 (0.1282) loss: 0.8111 (0.8110) time: 0.1296 data: 0.0543 max mem: 9390 +Train: [76] [6000/6250] eta: 0:00:34 lr: 0.000017 grad: 0.1250 (0.1282) loss: 0.8047 (0.8110) time: 0.1666 data: 0.0779 max mem: 9390 +Train: [76] [6100/6250] eta: 0:00:20 lr: 0.000017 grad: 0.1176 (0.1282) loss: 0.8114 (0.8110) time: 0.1409 data: 0.0623 max mem: 9390 +Train: [76] [6200/6250] eta: 0:00:06 lr: 0.000017 grad: 0.1281 (0.1282) loss: 0.8068 (0.8110) time: 0.1343 data: 0.0501 max mem: 9390 +Train: [76] [6249/6250] eta: 0:00:00 lr: 0.000017 grad: 0.1133 (0.1282) loss: 0.8153 (0.8110) time: 0.1484 data: 0.0676 max mem: 9390 +Train: [76] Total time: 0:14:22 (0.1380 s / it) +Averaged stats: lr: 0.000017 grad: 0.1133 (0.1282) loss: 0.8153 (0.8110) +Eval (hcp-train-subset): [76] [ 0/62] eta: 0:04:36 loss: 0.8330 (0.8330) time: 4.4518 data: 4.4203 max mem: 9390 +Eval (hcp-train-subset): [76] [61/62] eta: 0:00:00 loss: 0.8206 (0.8245) time: 0.1171 data: 0.0922 max mem: 9390 +Eval (hcp-train-subset): [76] Total time: 0:00:12 (0.2058 s / it) +Averaged stats (hcp-train-subset): loss: 0.8206 (0.8245) +Eval (hcp-val): [76] [ 0/62] eta: 0:03:30 loss: 0.8254 (0.8254) time: 3.3886 data: 3.2907 max mem: 9390 +Eval (hcp-val): [76] [61/62] eta: 0:00:00 loss: 0.8313 (0.8313) time: 0.1178 data: 0.0927 max mem: 9390 +Eval (hcp-val): [76] Total time: 0:00:12 (0.2076 s / it) +Averaged stats (hcp-val): loss: 0.8313 (0.8313) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +Train: [77] [ 0/6250] eta: 10:28:24 lr: 0.000017 grad: 0.1579 (0.1579) loss: 0.8132 (0.8132) time: 6.0328 data: 5.9396 max mem: 9390 +Train: [77] [ 100/6250] eta: 0:20:24 lr: 0.000017 grad: 0.1437 (0.1616) loss: 0.8174 (0.8220) time: 0.1451 data: 0.0517 max mem: 9390 +Train: [77] [ 200/6250] eta: 0:17:29 lr: 0.000017 grad: 0.1148 (0.1540) loss: 0.8075 (0.8164) time: 0.1270 data: 0.0361 max mem: 9390 +Train: [77] [ 300/6250] eta: 0:16:15 lr: 0.000017 grad: 0.1374 (0.1507) loss: 0.8038 (0.8143) time: 0.1161 data: 0.0349 max mem: 9390 +Train: [77] [ 400/6250] eta: 0:15:13 lr: 0.000017 grad: 0.1175 (0.1455) loss: 0.8165 (0.8140) time: 0.1186 data: 0.0303 max mem: 9390 +Train: [77] [ 500/6250] eta: 0:14:25 lr: 0.000017 grad: 0.1224 (0.1426) loss: 0.8147 (0.8134) time: 0.1301 data: 0.0498 max mem: 9390 +Train: [77] [ 600/6250] eta: 0:13:45 lr: 0.000017 grad: 0.1180 (0.1402) loss: 0.8098 (0.8136) time: 0.1357 data: 0.0549 max mem: 9390 +Train: [77] [ 700/6250] eta: 0:13:09 lr: 0.000017 grad: 0.1170 (0.1379) loss: 0.8186 (0.8137) time: 0.1160 data: 0.0286 max mem: 9390 +Train: [77] [ 800/6250] eta: 0:12:41 lr: 0.000017 grad: 0.1249 (0.1368) loss: 0.8119 (0.8137) time: 0.1348 data: 0.0483 max mem: 9390 +Train: [77] [ 900/6250] eta: 0:12:16 lr: 0.000017 grad: 0.1244 (0.1355) loss: 0.8127 (0.8134) time: 0.1250 data: 0.0452 max mem: 9390 +Train: [77] [1000/6250] eta: 0:11:52 lr: 0.000017 grad: 0.1184 (0.1345) loss: 0.8115 (0.8131) time: 0.1185 data: 0.0415 max mem: 9390 +Train: [77] [1100/6250] eta: 0:11:33 lr: 0.000017 grad: 0.1295 (0.1337) loss: 0.8086 (0.8130) time: 0.1200 data: 0.0409 max mem: 9390 +Train: [77] [1200/6250] eta: 0:11:15 lr: 0.000017 grad: 0.1195 (0.1331) loss: 0.8085 (0.8126) time: 0.1005 data: 0.0149 max mem: 9390 +Train: [77] [1300/6250] eta: 0:10:57 lr: 0.000017 grad: 0.1198 (0.1328) loss: 0.8110 (0.8122) time: 0.1280 data: 0.0466 max mem: 9390 +Train: [77] [1400/6250] eta: 0:10:39 lr: 0.000017 grad: 0.1231 (0.1320) loss: 0.8073 (0.8121) time: 0.1095 data: 0.0331 max mem: 9390 +Train: [77] [1500/6250] eta: 0:10:24 lr: 0.000017 grad: 0.1202 (0.1317) loss: 0.8081 (0.8118) time: 0.1364 data: 0.0536 max mem: 9390 +Train: [77] [1600/6250] eta: 0:10:09 lr: 0.000017 grad: 0.1277 (0.1318) loss: 0.8057 (0.8115) time: 0.1154 data: 0.0367 max mem: 9390 +Train: [77] [1700/6250] eta: 0:09:56 lr: 0.000017 grad: 0.1314 (0.1316) loss: 0.8040 (0.8111) time: 0.1268 data: 0.0494 max mem: 9390 +Train: [77] [1800/6250] eta: 0:09:43 lr: 0.000017 grad: 0.1223 (0.1314) loss: 0.8081 (0.8109) time: 0.1177 data: 0.0367 max mem: 9390 +Train: [77] [1900/6250] eta: 0:09:31 lr: 0.000017 grad: 0.1237 (0.1311) loss: 0.8056 (0.8107) time: 0.1415 data: 0.0606 max mem: 9390 +Train: [77] [2000/6250] eta: 0:09:22 lr: 0.000017 grad: 0.1212 (0.1310) loss: 0.8124 (0.8106) time: 0.1950 data: 0.1260 max mem: 9390 +Train: [77] [2100/6250] eta: 0:09:12 lr: 0.000017 grad: 0.1273 (0.1310) loss: 0.8059 (0.8104) time: 0.1527 data: 0.0712 max mem: 9390 +Train: [77] [2200/6250] eta: 0:09:02 lr: 0.000017 grad: 0.1256 (0.1312) loss: 0.8075 (0.8102) time: 0.1417 data: 0.0685 max mem: 9390 +Train: [77] [2300/6250] eta: 0:08:52 lr: 0.000017 grad: 0.1262 (0.1311) loss: 0.8050 (0.8100) time: 0.1554 data: 0.0716 max mem: 9390 +Train: [77] [2400/6250] eta: 0:08:41 lr: 0.000017 grad: 0.1280 (0.1310) loss: 0.8115 (0.8099) time: 0.1400 data: 0.0637 max mem: 9390 +Train: [77] [2500/6250] eta: 0:08:29 lr: 0.000017 grad: 0.1223 (0.1308) loss: 0.8106 (0.8099) time: 0.1698 data: 0.0835 max mem: 9390 +Train: [77] [2600/6250] eta: 0:08:17 lr: 0.000017 grad: 0.1327 (0.1307) loss: 0.8089 (0.8099) time: 0.1600 data: 0.0625 max mem: 9390 +Train: [77] [2700/6250] eta: 0:08:05 lr: 0.000017 grad: 0.1181 (0.1304) loss: 0.8126 (0.8100) time: 0.1368 data: 0.0532 max mem: 9390 +Train: [77] [2800/6250] eta: 0:07:55 lr: 0.000017 grad: 0.1201 (0.1301) loss: 0.8122 (0.8101) time: 0.2051 data: 0.1278 max mem: 9390 +Train: [77] [2900/6250] eta: 0:07:47 lr: 0.000017 grad: 0.1194 (0.1298) loss: 0.8122 (0.8103) time: 0.1964 data: 0.0983 max mem: 9390 +Train: [77] [3000/6250] eta: 0:07:42 lr: 0.000017 grad: 0.1284 (0.1296) loss: 0.8111 (0.8104) time: 0.1437 data: 0.0635 max mem: 9390 +Train: [77] [3100/6250] eta: 0:07:38 lr: 0.000017 grad: 0.1194 (0.1294) loss: 0.8101 (0.8105) time: 0.3152 data: 0.2093 max mem: 9390 +Train: [77] [3200/6250] eta: 0:07:28 lr: 0.000017 grad: 0.1165 (0.1292) loss: 0.8150 (0.8106) time: 0.2317 data: 0.1142 max mem: 9390 +Train: [77] [3300/6250] eta: 0:07:28 lr: 0.000016 grad: 0.1146 (0.1290) loss: 0.8169 (0.8106) time: 0.4236 data: 0.3340 max mem: 9390 +Train: [77] [3400/6250] eta: 0:07:18 lr: 0.000016 grad: 0.1228 (0.1289) loss: 0.8142 (0.8107) time: 0.2431 data: 0.1554 max mem: 9390 +Train: [77] [3500/6250] eta: 0:07:09 lr: 0.000016 grad: 0.1210 (0.1287) loss: 0.8159 (0.8108) time: 0.2241 data: 0.1272 max mem: 9390 +Train: [77] [3600/6250] eta: 0:07:03 lr: 0.000016 grad: 0.1199 (0.1285) loss: 0.8148 (0.8108) time: 0.3475 data: 0.2429 max mem: 9390 +Train: [77] [3700/6250] eta: 0:06:50 lr: 0.000016 grad: 0.1157 (0.1283) loss: 0.8083 (0.8109) time: 0.1797 data: 0.0769 max mem: 9390 +Train: [77] [3800/6250] eta: 0:06:37 lr: 0.000016 grad: 0.1204 (0.1282) loss: 0.8129 (0.8109) time: 0.1940 data: 0.0995 max mem: 9390 +Train: [77] [3900/6250] eta: 0:06:24 lr: 0.000016 grad: 0.1219 (0.1282) loss: 0.8177 (0.8110) time: 0.3519 data: 0.2334 max mem: 9390 +Train: [77] [4000/6250] eta: 0:06:10 lr: 0.000016 grad: 0.1264 (0.1281) loss: 0.8102 (0.8110) time: 0.2459 data: 0.1379 max mem: 9390 +Train: [77] [4100/6250] eta: 0:05:54 lr: 0.000016 grad: 0.1205 (0.1280) loss: 0.8106 (0.8111) time: 0.1832 data: 0.0863 max mem: 9390 +Train: [77] [4200/6250] eta: 0:05:38 lr: 0.000016 grad: 0.1201 (0.1280) loss: 0.8120 (0.8111) time: 0.1630 data: 0.0776 max mem: 9390 +Train: [77] [4300/6250] eta: 0:05:23 lr: 0.000016 grad: 0.1263 (0.1280) loss: 0.8085 (0.8111) time: 0.1296 data: 0.0237 max mem: 9390 +Train: [77] [4400/6250] eta: 0:05:07 lr: 0.000016 grad: 0.1193 (0.1281) loss: 0.8095 (0.8110) time: 0.1927 data: 0.1023 max mem: 9390 +Train: [77] [4500/6250] eta: 0:04:53 lr: 0.000016 grad: 0.1251 (0.1281) loss: 0.8185 (0.8111) time: 0.0993 data: 0.0002 max mem: 9390 +Train: [77] [4600/6250] eta: 0:04:38 lr: 0.000016 grad: 0.1233 (0.1281) loss: 0.8121 (0.8111) time: 0.2817 data: 0.1782 max mem: 9390 +Train: [77] [4700/6250] eta: 0:04:22 lr: 0.000016 grad: 0.1252 (0.1280) loss: 0.8168 (0.8111) time: 0.2143 data: 0.1085 max mem: 9390 +Train: [77] [4800/6250] eta: 0:04:06 lr: 0.000016 grad: 0.1253 (0.1280) loss: 0.8121 (0.8111) time: 0.2738 data: 0.1773 max mem: 9390 +Train: [77] [4900/6250] eta: 0:03:49 lr: 0.000016 grad: 0.1230 (0.1280) loss: 0.8108 (0.8111) time: 0.1680 data: 0.0829 max mem: 9390 +Train: [77] [5000/6250] eta: 0:03:32 lr: 0.000016 grad: 0.1221 (0.1279) loss: 0.8141 (0.8111) time: 0.1699 data: 0.0717 max mem: 9390 +Train: [77] [5100/6250] eta: 0:03:17 lr: 0.000016 grad: 0.1237 (0.1279) loss: 0.8179 (0.8111) time: 0.2255 data: 0.1175 max mem: 9390 +Train: [77] [5200/6250] eta: 0:03:00 lr: 0.000016 grad: 0.1218 (0.1279) loss: 0.8114 (0.8111) time: 0.2247 data: 0.1291 max mem: 9390 +Train: [77] [5300/6250] eta: 0:02:43 lr: 0.000016 grad: 0.1238 (0.1278) loss: 0.8088 (0.8111) time: 0.1379 data: 0.0376 max mem: 9390 +Train: [77] [5400/6250] eta: 0:02:27 lr: 0.000016 grad: 0.1289 (0.1279) loss: 0.8048 (0.8111) time: 0.2285 data: 0.1350 max mem: 9390 +Train: [77] [5500/6250] eta: 0:02:09 lr: 0.000016 grad: 0.1266 (0.1279) loss: 0.8151 (0.8111) time: 0.1645 data: 0.0787 max mem: 9390 +Train: [77] [5600/6250] eta: 0:01:52 lr: 0.000016 grad: 0.1211 (0.1279) loss: 0.8108 (0.8112) time: 0.1879 data: 0.1068 max mem: 9390 +Train: [77] [5700/6250] eta: 0:01:35 lr: 0.000016 grad: 0.1279 (0.1278) loss: 0.8043 (0.8112) time: 0.1667 data: 0.0702 max mem: 9390 +Train: [77] [5800/6250] eta: 0:01:18 lr: 0.000016 grad: 0.1227 (0.1278) loss: 0.8164 (0.8113) time: 0.1476 data: 0.0626 max mem: 9390 +Train: [77] [5900/6250] eta: 0:01:01 lr: 0.000016 grad: 0.1227 (0.1278) loss: 0.8188 (0.8113) time: 0.1744 data: 0.0630 max mem: 9390 +Train: [77] [6000/6250] eta: 0:00:43 lr: 0.000016 grad: 0.1221 (0.1278) loss: 0.8132 (0.8113) time: 0.2122 data: 0.1096 max mem: 9390 +Train: [77] [6100/6250] eta: 0:00:26 lr: 0.000016 grad: 0.1243 (0.1278) loss: 0.8066 (0.8113) time: 0.2063 data: 0.1213 max mem: 9390 +Train: [77] [6200/6250] eta: 0:00:08 lr: 0.000016 grad: 0.1215 (0.1278) loss: 0.8165 (0.8114) time: 0.3023 data: 0.2169 max mem: 9390 +Train: [77] [6249/6250] eta: 0:00:00 lr: 0.000016 grad: 0.1300 (0.1278) loss: 0.8102 (0.8113) time: 0.1168 data: 0.0210 max mem: 9390 +Train: [77] Total time: 0:18:24 (0.1767 s / it) +Averaged stats: lr: 0.000016 grad: 0.1300 (0.1278) loss: 0.8102 (0.8113) +Eval (hcp-train-subset): [77] [ 0/62] eta: 0:06:08 loss: 0.8375 (0.8375) time: 5.9474 data: 5.9042 max mem: 9390 +Eval (hcp-train-subset): [77] [61/62] eta: 0:00:00 loss: 0.8222 (0.8244) time: 0.0985 data: 0.0730 max mem: 9390 +Eval (hcp-train-subset): [77] Total time: 0:00:16 (0.2632 s / it) +Averaged stats (hcp-train-subset): loss: 0.8222 (0.8244) +Eval (hcp-val): [77] [ 0/62] eta: 0:05:19 loss: 0.8282 (0.8282) time: 5.1606 data: 5.0637 max mem: 9390 +Eval (hcp-val): [77] [61/62] eta: 0:00:00 loss: 0.8299 (0.8304) time: 0.1418 data: 0.1141 max mem: 9390 +Eval (hcp-val): [77] Total time: 0:00:15 (0.2486 s / it) +Averaged stats (hcp-val): loss: 0.8299 (0.8304) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +Train: [78] [ 0/6250] eta: 11:44:31 lr: 0.000016 grad: 0.2008 (0.2008) loss: 0.8474 (0.8474) time: 6.7634 data: 6.6592 max mem: 9390 +Train: [78] [ 100/6250] eta: 0:24:01 lr: 0.000016 grad: 0.1220 (0.1518) loss: 0.8173 (0.8167) time: 0.1294 data: 0.0071 max mem: 9390 +Train: [78] [ 200/6250] eta: 0:20:45 lr: 0.000016 grad: 0.1280 (0.1460) loss: 0.8188 (0.8146) time: 0.1699 data: 0.0632 max mem: 9390 +Train: [78] [ 300/6250] eta: 0:19:21 lr: 0.000016 grad: 0.1163 (0.1412) loss: 0.8105 (0.8140) time: 0.1506 data: 0.0584 max mem: 9390 +Train: [78] [ 400/6250] eta: 0:18:44 lr: 0.000016 grad: 0.1187 (0.1377) loss: 0.8069 (0.8143) time: 0.1883 data: 0.0939 max mem: 9390 +Train: [78] [ 500/6250] eta: 0:18:18 lr: 0.000016 grad: 0.1190 (0.1355) loss: 0.8121 (0.8138) time: 0.1293 data: 0.0003 max mem: 9390 +Train: [78] [ 600/6250] eta: 0:17:36 lr: 0.000016 grad: 0.1176 (0.1342) loss: 0.8159 (0.8140) time: 0.1665 data: 0.0812 max mem: 9390 +Train: [78] [ 700/6250] eta: 0:17:11 lr: 0.000016 grad: 0.1271 (0.1337) loss: 0.8183 (0.8140) time: 0.2030 data: 0.0993 max mem: 9390 +Train: [78] [ 800/6250] eta: 0:16:51 lr: 0.000016 grad: 0.1251 (0.1330) loss: 0.8149 (0.8140) time: 0.2257 data: 0.1411 max mem: 9390 +Train: [78] [ 900/6250] eta: 0:16:26 lr: 0.000016 grad: 0.1221 (0.1321) loss: 0.8155 (0.8142) time: 0.1955 data: 0.1123 max mem: 9390 +Train: [78] [1000/6250] eta: 0:15:57 lr: 0.000016 grad: 0.1242 (0.1320) loss: 0.8102 (0.8140) time: 0.1632 data: 0.0735 max mem: 9390 +Train: [78] [1100/6250] eta: 0:15:37 lr: 0.000016 grad: 0.1146 (0.1315) loss: 0.8138 (0.8139) time: 0.1631 data: 0.0698 max mem: 9390 +Train: [78] [1200/6250] eta: 0:15:16 lr: 0.000016 grad: 0.1267 (0.1311) loss: 0.8121 (0.8137) time: 0.1263 data: 0.0354 max mem: 9390 +Train: [78] [1300/6250] eta: 0:14:55 lr: 0.000016 grad: 0.1152 (0.1308) loss: 0.8146 (0.8134) time: 0.1927 data: 0.1060 max mem: 9390 +Train: [78] [1400/6250] eta: 0:14:38 lr: 0.000016 grad: 0.1320 (0.1306) loss: 0.8077 (0.8130) time: 0.1781 data: 0.0937 max mem: 9390 +Train: [78] [1500/6250] eta: 0:14:30 lr: 0.000015 grad: 0.1261 (0.1304) loss: 0.8131 (0.8128) time: 0.1716 data: 0.0645 max mem: 9390 +Train: [78] [1600/6250] eta: 0:14:30 lr: 0.000015 grad: 0.1246 (0.1302) loss: 0.8112 (0.8126) time: 0.2162 data: 0.1073 max mem: 9390 +Train: [78] [1700/6250] eta: 0:14:09 lr: 0.000015 grad: 0.1300 (0.1301) loss: 0.8061 (0.8123) time: 0.1730 data: 0.0817 max mem: 9390 +Train: [78] [1800/6250] eta: 0:13:52 lr: 0.000015 grad: 0.1299 (0.1301) loss: 0.8008 (0.8119) time: 0.1690 data: 0.0933 max mem: 9390 +Train: [78] [1900/6250] eta: 0:13:29 lr: 0.000015 grad: 0.1243 (0.1299) loss: 0.8097 (0.8116) time: 0.1615 data: 0.0719 max mem: 9390 +Train: [78] [2000/6250] eta: 0:13:22 lr: 0.000015 grad: 0.1195 (0.1297) loss: 0.8148 (0.8116) time: 0.3844 data: 0.2988 max mem: 9390 +Train: [78] [2100/6250] eta: 0:13:01 lr: 0.000015 grad: 0.1206 (0.1297) loss: 0.8082 (0.8114) time: 0.1823 data: 0.1026 max mem: 9390 +Train: [78] [2200/6250] eta: 0:12:43 lr: 0.000015 grad: 0.1267 (0.1295) loss: 0.8105 (0.8113) time: 0.1674 data: 0.0870 max mem: 9390 +Train: [78] [2300/6250] eta: 0:12:26 lr: 0.000015 grad: 0.1242 (0.1294) loss: 0.8096 (0.8112) time: 0.1837 data: 0.0875 max mem: 9390 +Train: [78] [2400/6250] eta: 0:12:07 lr: 0.000015 grad: 0.1280 (0.1295) loss: 0.8028 (0.8110) time: 0.1893 data: 0.0997 max mem: 9390 +Train: [78] [2500/6250] eta: 0:11:47 lr: 0.000015 grad: 0.1330 (0.1296) loss: 0.8004 (0.8108) time: 0.2183 data: 0.1371 max mem: 9390 +Train: [78] [2600/6250] eta: 0:11:27 lr: 0.000015 grad: 0.1291 (0.1298) loss: 0.8061 (0.8106) time: 0.1686 data: 0.0838 max mem: 9390 +Train: [78] [2700/6250] eta: 0:11:06 lr: 0.000015 grad: 0.1284 (0.1298) loss: 0.8113 (0.8105) time: 0.1525 data: 0.0741 max mem: 9390 +Train: [78] [2800/6250] eta: 0:10:49 lr: 0.000015 grad: 0.1289 (0.1299) loss: 0.8057 (0.8103) time: 0.1380 data: 0.0379 max mem: 9390 +Train: [78] [2900/6250] eta: 0:10:28 lr: 0.000015 grad: 0.1338 (0.1299) loss: 0.8059 (0.8102) time: 0.2185 data: 0.1300 max mem: 9390 +Train: [78] [3000/6250] eta: 0:10:07 lr: 0.000015 grad: 0.1325 (0.1300) loss: 0.7984 (0.8101) time: 0.1233 data: 0.0005 max mem: 9390 +Train: [78] [3100/6250] eta: 0:09:47 lr: 0.000015 grad: 0.1316 (0.1302) loss: 0.7993 (0.8099) time: 0.1952 data: 0.0901 max mem: 9390 +Train: [78] [3200/6250] eta: 0:09:26 lr: 0.000015 grad: 0.1225 (0.1303) loss: 0.8125 (0.8098) time: 0.1875 data: 0.1004 max mem: 9390 +Train: [78] [3300/6250] eta: 0:09:10 lr: 0.000015 grad: 0.1384 (0.1303) loss: 0.8012 (0.8097) time: 0.1387 data: 0.0543 max mem: 9390 +Train: [78] [3400/6250] eta: 0:08:54 lr: 0.000015 grad: 0.1271 (0.1304) loss: 0.8026 (0.8096) time: 0.1710 data: 0.0683 max mem: 9390 +Train: [78] [3500/6250] eta: 0:08:39 lr: 0.000015 grad: 0.1237 (0.1305) loss: 0.8105 (0.8096) time: 0.2219 data: 0.1056 max mem: 9390 +Train: [78] [3600/6250] eta: 0:08:25 lr: 0.000015 grad: 0.1281 (0.1304) loss: 0.8068 (0.8095) time: 0.1692 data: 0.0457 max mem: 9390 +Train: [78] [3700/6250] eta: 0:08:08 lr: 0.000015 grad: 0.1315 (0.1305) loss: 0.8142 (0.8095) time: 0.2458 data: 0.1364 max mem: 9390 +Train: [78] [3800/6250] eta: 0:07:50 lr: 0.000015 grad: 0.1234 (0.1305) loss: 0.8119 (0.8095) time: 0.1255 data: 0.0352 max mem: 9390 +Train: [78] [3900/6250] eta: 0:07:33 lr: 0.000015 grad: 0.1211 (0.1305) loss: 0.8166 (0.8096) time: 0.3767 data: 0.2681 max mem: 9390 +Train: [78] [4000/6250] eta: 0:07:16 lr: 0.000015 grad: 0.1282 (0.1305) loss: 0.8116 (0.8096) time: 0.2311 data: 0.1157 max mem: 9390 +Train: [78] [4100/6250] eta: 0:06:57 lr: 0.000015 grad: 0.1239 (0.1305) loss: 0.8158 (0.8096) time: 0.1053 data: 0.0002 max mem: 9390 +Train: [78] [4200/6250] eta: 0:06:37 lr: 0.000015 grad: 0.1225 (0.1306) loss: 0.8058 (0.8095) time: 0.2156 data: 0.1107 max mem: 9390 +Train: [78] [4300/6250] eta: 0:06:17 lr: 0.000015 grad: 0.1262 (0.1306) loss: 0.8122 (0.8096) time: 0.1521 data: 0.0546 max mem: 9390 +Train: [78] [4400/6250] eta: 0:05:57 lr: 0.000015 grad: 0.1241 (0.1306) loss: 0.8169 (0.8097) time: 0.1697 data: 0.0795 max mem: 9390 +Train: [78] [4500/6250] eta: 0:05:39 lr: 0.000015 grad: 0.1277 (0.1306) loss: 0.8110 (0.8097) time: 0.2142 data: 0.1258 max mem: 9390 +Train: [78] [4600/6250] eta: 0:05:19 lr: 0.000015 grad: 0.1241 (0.1306) loss: 0.8139 (0.8097) time: 0.2106 data: 0.1106 max mem: 9390 +Train: [78] [4700/6250] eta: 0:05:00 lr: 0.000015 grad: 0.1244 (0.1307) loss: 0.8080 (0.8097) time: 0.1803 data: 0.0778 max mem: 9390 +Train: [78] [4800/6250] eta: 0:04:43 lr: 0.000015 grad: 0.1201 (0.1307) loss: 0.8158 (0.8098) time: 0.1559 data: 0.0287 max mem: 9390 +Train: [78] [4900/6250] eta: 0:04:22 lr: 0.000015 grad: 0.1274 (0.1308) loss: 0.8162 (0.8098) time: 0.1759 data: 0.0924 max mem: 9390 +Train: [78] [5000/6250] eta: 0:04:02 lr: 0.000015 grad: 0.1252 (0.1307) loss: 0.8151 (0.8098) time: 0.1688 data: 0.0706 max mem: 9390 +Train: [78] [5100/6250] eta: 0:03:43 lr: 0.000015 grad: 0.1283 (0.1308) loss: 0.8106 (0.8099) time: 0.2085 data: 0.1213 max mem: 9390 +Train: [78] [5200/6250] eta: 0:03:24 lr: 0.000015 grad: 0.1277 (0.1308) loss: 0.8116 (0.8099) time: 0.1496 data: 0.0004 max mem: 9390 +Train: [78] [5300/6250] eta: 0:03:04 lr: 0.000015 grad: 0.1231 (0.1308) loss: 0.8122 (0.8099) time: 0.2156 data: 0.1277 max mem: 9390 +Train: [78] [5400/6250] eta: 0:02:45 lr: 0.000015 grad: 0.1335 (0.1308) loss: 0.8118 (0.8099) time: 0.0963 data: 0.0002 max mem: 9390 +Train: [78] [5500/6250] eta: 0:02:25 lr: 0.000015 grad: 0.1254 (0.1308) loss: 0.8051 (0.8099) time: 0.1823 data: 0.0903 max mem: 9390 +Train: [78] [5600/6250] eta: 0:02:06 lr: 0.000015 grad: 0.1214 (0.1307) loss: 0.8100 (0.8099) time: 0.1800 data: 0.0926 max mem: 9390 +Train: [78] [5700/6250] eta: 0:01:47 lr: 0.000015 grad: 0.1227 (0.1307) loss: 0.8172 (0.8099) time: 0.1542 data: 0.0577 max mem: 9390 +Train: [78] [5800/6250] eta: 0:01:27 lr: 0.000015 grad: 0.1260 (0.1306) loss: 0.8121 (0.8100) time: 0.1702 data: 0.0837 max mem: 9390 +Train: [78] [5900/6250] eta: 0:01:08 lr: 0.000015 grad: 0.1211 (0.1306) loss: 0.8112 (0.8100) time: 0.3125 data: 0.2123 max mem: 9390 +Train: [78] [6000/6250] eta: 0:00:48 lr: 0.000015 grad: 0.1278 (0.1306) loss: 0.8153 (0.8100) time: 0.1760 data: 0.0902 max mem: 9390 +Train: [78] [6100/6250] eta: 0:00:29 lr: 0.000015 grad: 0.1281 (0.1305) loss: 0.8121 (0.8101) time: 0.1980 data: 0.1172 max mem: 9390 +Train: [78] [6200/6250] eta: 0:00:09 lr: 0.000014 grad: 0.1305 (0.1305) loss: 0.8087 (0.8101) time: 0.2584 data: 0.1680 max mem: 9390 +Train: [78] [6249/6250] eta: 0:00:00 lr: 0.000014 grad: 0.1317 (0.1305) loss: 0.8074 (0.8101) time: 0.0998 data: 0.0002 max mem: 9390 +Train: [78] Total time: 0:20:23 (0.1957 s / it) +Averaged stats: lr: 0.000014 grad: 0.1317 (0.1305) loss: 0.8074 (0.8101) +Eval (hcp-train-subset): [78] [ 0/62] eta: 0:06:05 loss: 0.8390 (0.8390) time: 5.8949 data: 5.8125 max mem: 9390 +Eval (hcp-train-subset): [78] [61/62] eta: 0:00:00 loss: 0.8214 (0.8237) time: 0.1599 data: 0.1342 max mem: 9390 +Eval (hcp-train-subset): [78] Total time: 0:00:17 (0.2784 s / it) +Averaged stats (hcp-train-subset): loss: 0.8214 (0.8237) +Eval (hcp-val): [78] [ 0/62] eta: 0:04:32 loss: 0.8279 (0.8279) time: 4.4028 data: 4.3329 max mem: 9390 +Eval (hcp-val): [78] [61/62] eta: 0:00:00 loss: 0.8288 (0.8302) time: 0.1198 data: 0.0924 max mem: 9390 +Eval (hcp-val): [78] Total time: 0:00:17 (0.2787 s / it) +Averaged stats (hcp-val): loss: 0.8288 (0.8302) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +Train: [79] [ 0/6250] eta: 12:08:58 lr: 0.000014 grad: 0.1195 (0.1195) loss: 0.8273 (0.8273) time: 6.9982 data: 6.8370 max mem: 9390 +Train: [79] [ 100/6250] eta: 0:29:02 lr: 0.000014 grad: 0.1298 (0.1494) loss: 0.8194 (0.8291) time: 0.2975 data: 0.1843 max mem: 9390 +Train: [79] [ 200/6250] eta: 0:24:18 lr: 0.000014 grad: 0.1155 (0.1427) loss: 0.8149 (0.8228) time: 0.1978 data: 0.0880 max mem: 9390 +Train: [79] [ 300/6250] eta: 0:23:00 lr: 0.000014 grad: 0.1309 (0.1416) loss: 0.8157 (0.8196) time: 0.1826 data: 0.0754 max mem: 9390 +Train: [79] [ 400/6250] eta: 0:21:06 lr: 0.000014 grad: 0.1238 (0.1391) loss: 0.8104 (0.8192) time: 0.1661 data: 0.0702 max mem: 9390 +Train: [79] [ 500/6250] eta: 0:19:58 lr: 0.000014 grad: 0.1297 (0.1382) loss: 0.8095 (0.8188) time: 0.1547 data: 0.0538 max mem: 9390 +Train: [79] [ 600/6250] eta: 0:19:31 lr: 0.000014 grad: 0.1265 (0.1370) loss: 0.8196 (0.8188) time: 0.1908 data: 0.0954 max mem: 9390 +Train: [79] [ 700/6250] eta: 0:19:05 lr: 0.000014 grad: 0.1316 (0.1364) loss: 0.8149 (0.8186) time: 0.1809 data: 0.0645 max mem: 9390 +Train: [79] [ 800/6250] eta: 0:19:14 lr: 0.000014 grad: 0.1307 (0.1362) loss: 0.8179 (0.8182) time: 0.3193 data: 0.2112 max mem: 9390 +Train: [79] [ 900/6250] eta: 0:18:43 lr: 0.000014 grad: 0.1216 (0.1354) loss: 0.8099 (0.8178) time: 0.1923 data: 0.0877 max mem: 9390 +Train: [79] [1000/6250] eta: 0:18:08 lr: 0.000014 grad: 0.1249 (0.1349) loss: 0.8194 (0.8172) time: 0.1691 data: 0.0682 max mem: 9390 +Train: [79] [1100/6250] eta: 0:18:03 lr: 0.000014 grad: 0.1288 (0.1343) loss: 0.8100 (0.8168) time: 0.2061 data: 0.1154 max mem: 9390 +Train: [79] [1200/6250] eta: 0:17:43 lr: 0.000014 grad: 0.1400 (0.1341) loss: 0.8097 (0.8164) time: 0.2057 data: 0.1251 max mem: 9390 +Train: [79] [1300/6250] eta: 0:17:25 lr: 0.000014 grad: 0.1271 (0.1338) loss: 0.8105 (0.8160) time: 0.2288 data: 0.1355 max mem: 9390 +Train: [79] [1400/6250] eta: 0:17:00 lr: 0.000014 grad: 0.1277 (0.1333) loss: 0.8128 (0.8158) time: 0.1740 data: 0.0830 max mem: 9390 +Train: [79] [1500/6250] eta: 0:17:10 lr: 0.000014 grad: 0.1296 (0.1333) loss: 0.8148 (0.8155) time: 0.2220 data: 0.1129 max mem: 9390 +Train: [79] [1600/6250] eta: 0:16:45 lr: 0.000014 grad: 0.1231 (0.1332) loss: 0.8118 (0.8150) time: 0.1484 data: 0.0267 max mem: 9390 +Train: [79] [1700/6250] eta: 0:16:13 lr: 0.000014 grad: 0.1260 (0.1331) loss: 0.8138 (0.8147) time: 0.1536 data: 0.0584 max mem: 9390 +Train: [79] [1800/6250] eta: 0:15:46 lr: 0.000014 grad: 0.1282 (0.1331) loss: 0.8079 (0.8145) time: 0.1799 data: 0.0923 max mem: 9390 +Train: [79] [1900/6250] eta: 0:15:18 lr: 0.000014 grad: 0.1237 (0.1328) loss: 0.8120 (0.8142) time: 0.2256 data: 0.1431 max mem: 9390 +Train: [79] [2000/6250] eta: 0:14:54 lr: 0.000014 grad: 0.1260 (0.1326) loss: 0.8097 (0.8140) time: 0.1529 data: 0.0770 max mem: 9390 +Train: [79] [2100/6250] eta: 0:14:27 lr: 0.000014 grad: 0.1270 (0.1324) loss: 0.8080 (0.8137) time: 0.1539 data: 0.0729 max mem: 9390 +Train: [79] [2200/6250] eta: 0:14:01 lr: 0.000014 grad: 0.1252 (0.1323) loss: 0.8083 (0.8135) time: 0.2040 data: 0.1141 max mem: 9390 +Train: [79] [2300/6250] eta: 0:13:36 lr: 0.000014 grad: 0.1230 (0.1322) loss: 0.8057 (0.8133) time: 0.1709 data: 0.0704 max mem: 9390 +Train: [79] [2400/6250] eta: 0:13:15 lr: 0.000014 grad: 0.1334 (0.1322) loss: 0.8123 (0.8132) time: 0.2654 data: 0.1940 max mem: 9390 +Train: [79] [2500/6250] eta: 0:12:53 lr: 0.000014 grad: 0.1281 (0.1320) loss: 0.8122 (0.8131) time: 0.2503 data: 0.1515 max mem: 9390 +Train: [79] [2600/6250] eta: 0:12:25 lr: 0.000014 grad: 0.1311 (0.1319) loss: 0.8051 (0.8131) time: 0.1678 data: 0.0762 max mem: 9390 +Train: [79] [2700/6250] eta: 0:12:01 lr: 0.000014 grad: 0.1199 (0.1318) loss: 0.8117 (0.8130) time: 0.1691 data: 0.0736 max mem: 9390 +Train: [79] [2800/6250] eta: 0:11:37 lr: 0.000014 grad: 0.1213 (0.1316) loss: 0.8092 (0.8130) time: 0.1847 data: 0.0969 max mem: 9390 +Train: [79] [2900/6250] eta: 0:11:13 lr: 0.000014 grad: 0.1200 (0.1315) loss: 0.8157 (0.8129) time: 0.1608 data: 0.0790 max mem: 9390 +Train: [79] [3000/6250] eta: 0:10:49 lr: 0.000014 grad: 0.1317 (0.1314) loss: 0.8019 (0.8129) time: 0.1825 data: 0.0980 max mem: 9390 +Train: [79] [3100/6250] eta: 0:10:31 lr: 0.000014 grad: 0.1218 (0.1312) loss: 0.8165 (0.8129) time: 0.3196 data: 0.2252 max mem: 9390 +Train: [79] [3200/6250] eta: 0:10:13 lr: 0.000014 grad: 0.1166 (0.1311) loss: 0.8130 (0.8130) time: 0.3928 data: 0.2775 max mem: 9390 +Train: [79] [3300/6250] eta: 0:09:52 lr: 0.000014 grad: 0.1342 (0.1310) loss: 0.8093 (0.8130) time: 0.2411 data: 0.1293 max mem: 9390 +Train: [79] [3400/6250] eta: 0:09:33 lr: 0.000014 grad: 0.1229 (0.1308) loss: 0.8146 (0.8131) time: 0.1658 data: 0.0506 max mem: 9390 +Train: [79] [3500/6250] eta: 0:09:15 lr: 0.000014 grad: 0.1175 (0.1307) loss: 0.8124 (0.8131) time: 0.1974 data: 0.0985 max mem: 9390 +Train: [79] [3600/6250] eta: 0:08:55 lr: 0.000014 grad: 0.1272 (0.1307) loss: 0.8121 (0.8132) time: 0.1864 data: 0.0512 max mem: 9390 +Train: [79] [3700/6250] eta: 0:08:37 lr: 0.000014 grad: 0.1201 (0.1306) loss: 0.8142 (0.8133) time: 0.2682 data: 0.1572 max mem: 9390 +Train: [79] [3800/6250] eta: 0:08:14 lr: 0.000014 grad: 0.1180 (0.1306) loss: 0.8130 (0.8133) time: 0.2253 data: 0.1358 max mem: 9390 +Train: [79] [3900/6250] eta: 0:07:54 lr: 0.000014 grad: 0.1219 (0.1306) loss: 0.8100 (0.8133) time: 0.2778 data: 0.1879 max mem: 9390 +Train: [79] [4000/6250] eta: 0:07:34 lr: 0.000014 grad: 0.1374 (0.1307) loss: 0.8114 (0.8133) time: 0.1512 data: 0.0691 max mem: 9390 +Train: [79] [4100/6250] eta: 0:07:14 lr: 0.000014 grad: 0.1286 (0.1307) loss: 0.8109 (0.8133) time: 0.1708 data: 0.0544 max mem: 9390 +Train: [79] [4200/6250] eta: 0:06:54 lr: 0.000014 grad: 0.1273 (0.1306) loss: 0.8117 (0.8133) time: 0.1925 data: 0.0669 max mem: 9390 +Train: [79] [4300/6250] eta: 0:06:32 lr: 0.000014 grad: 0.1253 (0.1306) loss: 0.8154 (0.8133) time: 0.1767 data: 0.0925 max mem: 9390 +Train: [79] [4400/6250] eta: 0:06:13 lr: 0.000014 grad: 0.1274 (0.1306) loss: 0.8072 (0.8133) time: 0.1671 data: 0.0599 max mem: 9390 +Train: [79] [4500/6250] eta: 0:05:52 lr: 0.000014 grad: 0.1331 (0.1306) loss: 0.8068 (0.8133) time: 0.1063 data: 0.0003 max mem: 9390 +Train: [79] [4600/6250] eta: 0:05:33 lr: 0.000014 grad: 0.1254 (0.1306) loss: 0.8140 (0.8133) time: 0.2989 data: 0.2147 max mem: 9390 +Train: [79] [4700/6250] eta: 0:05:14 lr: 0.000013 grad: 0.1263 (0.1307) loss: 0.8131 (0.8133) time: 0.1098 data: 0.0004 max mem: 9390 +Train: [79] [4800/6250] eta: 0:04:53 lr: 0.000013 grad: 0.1406 (0.1308) loss: 0.8136 (0.8133) time: 0.1590 data: 0.0703 max mem: 9390 +Train: [79] [4900/6250] eta: 0:04:33 lr: 0.000013 grad: 0.1302 (0.1309) loss: 0.8051 (0.8132) time: 0.1727 data: 0.0754 max mem: 9390 +Train: [79] [5000/6250] eta: 0:04:13 lr: 0.000013 grad: 0.1207 (0.1310) loss: 0.8065 (0.8132) time: 0.1740 data: 0.0866 max mem: 9390 +Train: [79] [5100/6250] eta: 0:03:52 lr: 0.000013 grad: 0.1245 (0.1310) loss: 0.8111 (0.8131) time: 0.1761 data: 0.0860 max mem: 9390 +Train: [79] [5200/6250] eta: 0:03:31 lr: 0.000013 grad: 0.1273 (0.1310) loss: 0.8075 (0.8131) time: 0.1472 data: 0.0646 max mem: 9390 +Train: [79] [5300/6250] eta: 0:03:11 lr: 0.000013 grad: 0.1347 (0.1312) loss: 0.8060 (0.8130) time: 0.1761 data: 0.0902 max mem: 9390 +Train: [79] [5400/6250] eta: 0:02:50 lr: 0.000013 grad: 0.1248 (0.1311) loss: 0.8146 (0.8130) time: 0.1481 data: 0.0263 max mem: 9390 +Train: [79] [5500/6250] eta: 0:02:30 lr: 0.000013 grad: 0.1352 (0.1312) loss: 0.8128 (0.8129) time: 0.1846 data: 0.1019 max mem: 9390 +Train: [79] [5600/6250] eta: 0:02:10 lr: 0.000013 grad: 0.1316 (0.1312) loss: 0.8137 (0.8129) time: 0.2222 data: 0.1333 max mem: 9390 +Train: [79] [5700/6250] eta: 0:01:50 lr: 0.000013 grad: 0.1314 (0.1313) loss: 0.8073 (0.8129) time: 0.1576 data: 0.0672 max mem: 9390 +Train: [79] [5800/6250] eta: 0:01:30 lr: 0.000013 grad: 0.1346 (0.1314) loss: 0.8081 (0.8127) time: 0.3219 data: 0.2202 max mem: 9390 +Train: [79] [5900/6250] eta: 0:01:10 lr: 0.000013 grad: 0.1350 (0.1316) loss: 0.8052 (0.8126) time: 0.2014 data: 0.0966 max mem: 9390 +Train: [79] [6000/6250] eta: 0:00:50 lr: 0.000013 grad: 0.1358 (0.1317) loss: 0.8056 (0.8125) time: 0.1657 data: 0.0578 max mem: 9390 +Train: [79] [6100/6250] eta: 0:00:30 lr: 0.000013 grad: 0.1226 (0.1317) loss: 0.8171 (0.8124) time: 0.2358 data: 0.1439 max mem: 9390 +Train: [79] [6200/6250] eta: 0:00:10 lr: 0.000013 grad: 0.1291 (0.1318) loss: 0.8101 (0.8124) time: 0.1450 data: 0.0504 max mem: 9390 +Train: [79] [6249/6250] eta: 0:00:00 lr: 0.000013 grad: 0.1379 (0.1319) loss: 0.8061 (0.8123) time: 0.2947 data: 0.1968 max mem: 9390 +Train: [79] Total time: 0:21:04 (0.2023 s / it) +Averaged stats: lr: 0.000013 grad: 0.1379 (0.1319) loss: 0.8061 (0.8123) +Eval (hcp-train-subset): [79] [ 0/62] eta: 0:07:05 loss: 0.8395 (0.8395) time: 6.8665 data: 6.8358 max mem: 9390 +Eval (hcp-train-subset): [79] [61/62] eta: 0:00:00 loss: 0.8211 (0.8234) time: 0.1487 data: 0.1231 max mem: 9390 +Eval (hcp-train-subset): [79] Total time: 0:00:16 (0.2709 s / it) +Averaged stats (hcp-train-subset): loss: 0.8211 (0.8234) +Making plots (hcp-train-subset): example=39 +Eval (hcp-val): [79] [ 0/62] eta: 0:04:50 loss: 0.8312 (0.8312) time: 4.6792 data: 4.5511 max mem: 9390 +Eval (hcp-val): [79] [61/62] eta: 0:00:00 loss: 0.8293 (0.8309) time: 0.1135 data: 0.0879 max mem: 9390 +Eval (hcp-val): [79] Total time: 0:00:17 (0.2881 s / it) +Averaged stats (hcp-val): loss: 0.8293 (0.8309) +Making plots (hcp-val): example=1 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +Train: [80] [ 0/6250] eta: 12:35:03 lr: 0.000013 grad: 0.1372 (0.1372) loss: 0.8416 (0.8416) time: 7.2485 data: 7.0698 max mem: 9390 +Train: [80] [ 100/6250] eta: 0:25:31 lr: 0.000013 grad: 0.1210 (0.1277) loss: 0.8241 (0.8313) time: 0.1378 data: 0.0211 max mem: 9390 +Train: [80] [ 200/6250] eta: 0:25:29 lr: 0.000013 grad: 0.1158 (0.1319) loss: 0.8212 (0.8267) time: 0.4319 data: 0.2872 max mem: 9390 +Train: [80] [ 300/6250] eta: 0:22:00 lr: 0.000013 grad: 0.1214 (0.1310) loss: 0.8154 (0.8250) time: 0.1549 data: 0.0481 max mem: 9390 +Train: [80] [ 400/6250] eta: 0:20:44 lr: 0.000013 grad: 0.1244 (0.1312) loss: 0.8208 (0.8237) time: 0.1894 data: 0.0784 max mem: 9390 +Train: [80] [ 500/6250] eta: 0:19:28 lr: 0.000013 grad: 0.1341 (0.1324) loss: 0.8118 (0.8215) time: 0.1872 data: 0.0930 max mem: 9390 +Train: [80] [ 600/6250] eta: 0:18:51 lr: 0.000013 grad: 0.1351 (0.1328) loss: 0.8071 (0.8201) time: 0.1298 data: 0.0292 max mem: 9390 +Train: [80] [ 700/6250] eta: 0:18:36 lr: 0.000013 grad: 0.1329 (0.1329) loss: 0.8098 (0.8189) time: 0.2533 data: 0.1553 max mem: 9390 +Train: [80] [ 800/6250] eta: 0:17:59 lr: 0.000013 grad: 0.1252 (0.1324) loss: 0.8122 (0.8183) time: 0.1098 data: 0.0058 max mem: 9390 +Train: [80] [ 900/6250] eta: 0:18:33 lr: 0.000013 grad: 0.1187 (0.1318) loss: 0.8224 (0.8183) time: 0.2584 data: 0.1474 max mem: 9390 +Train: [80] [1000/6250] eta: 0:18:22 lr: 0.000013 grad: 0.1143 (0.1318) loss: 0.8156 (0.8180) time: 0.3970 data: 0.2757 max mem: 9390 +Train: [80] [1100/6250] eta: 0:17:55 lr: 0.000013 grad: 0.1208 (0.1314) loss: 0.8220 (0.8178) time: 0.2507 data: 0.1462 max mem: 9390 +Train: [80] [1200/6250] eta: 0:17:45 lr: 0.000013 grad: 0.1218 (0.1313) loss: 0.8154 (0.8175) time: 0.4509 data: 0.3498 max mem: 9390 +Train: [80] [1300/6250] eta: 0:17:24 lr: 0.000013 grad: 0.1255 (0.1313) loss: 0.8151 (0.8173) time: 0.1701 data: 0.0797 max mem: 9390 +Train: [80] [1400/6250] eta: 0:17:07 lr: 0.000013 grad: 0.1247 (0.1310) loss: 0.8239 (0.8172) time: 0.3386 data: 0.2374 max mem: 9390 +Train: [80] [1500/6250] eta: 0:16:55 lr: 0.000013 grad: 0.1333 (0.1307) loss: 0.8057 (0.8172) time: 0.3760 data: 0.1901 max mem: 9390 +Train: [80] [1600/6250] eta: 0:16:34 lr: 0.000013 grad: 0.1179 (0.1305) loss: 0.8181 (0.8170) time: 0.2699 data: 0.1602 max mem: 9390 +Train: [80] [1700/6250] eta: 0:16:08 lr: 0.000013 grad: 0.1295 (0.1304) loss: 0.8152 (0.8170) time: 0.2362 data: 0.1376 max mem: 9390 +Train: [80] [1800/6250] eta: 0:15:43 lr: 0.000013 grad: 0.1299 (0.1303) loss: 0.8180 (0.8169) time: 0.1344 data: 0.0547 max mem: 9390 +Train: [80] [1900/6250] eta: 0:15:18 lr: 0.000013 grad: 0.1250 (0.1304) loss: 0.8085 (0.8167) time: 0.1669 data: 0.0791 max mem: 9390 +Train: [80] [2000/6250] eta: 0:14:49 lr: 0.000013 grad: 0.1280 (0.1305) loss: 0.8097 (0.8165) time: 0.1622 data: 0.0775 max mem: 9390 +Train: [80] [2100/6250] eta: 0:14:20 lr: 0.000013 grad: 0.1312 (0.1306) loss: 0.8137 (0.8164) time: 0.1693 data: 0.0796 max mem: 9390 +Train: [80] [2200/6250] eta: 0:13:55 lr: 0.000013 grad: 0.1334 (0.1308) loss: 0.8118 (0.8162) time: 0.1960 data: 0.1084 max mem: 9390 +Train: [80] [2300/6250] eta: 0:13:34 lr: 0.000013 grad: 0.1251 (0.1308) loss: 0.8135 (0.8160) time: 0.2053 data: 0.1309 max mem: 9390 +Train: [80] [2400/6250] eta: 0:13:08 lr: 0.000013 grad: 0.1295 (0.1310) loss: 0.8124 (0.8158) time: 0.1572 data: 0.0682 max mem: 9390 +Train: [80] [2500/6250] eta: 0:12:44 lr: 0.000013 grad: 0.1340 (0.1311) loss: 0.8106 (0.8157) time: 0.1744 data: 0.0709 max mem: 9390 +Train: [80] [2600/6250] eta: 0:12:20 lr: 0.000013 grad: 0.1316 (0.1312) loss: 0.8104 (0.8156) time: 0.1728 data: 0.0863 max mem: 9390 +Train: [80] [2700/6250] eta: 0:11:55 lr: 0.000013 grad: 0.1324 (0.1314) loss: 0.8136 (0.8154) time: 0.1485 data: 0.0536 max mem: 9390 +Train: [80] [2800/6250] eta: 0:11:31 lr: 0.000013 grad: 0.1298 (0.1315) loss: 0.8128 (0.8153) time: 0.1621 data: 0.0684 max mem: 9390 +Train: [80] [2900/6250] eta: 0:11:06 lr: 0.000013 grad: 0.1329 (0.1316) loss: 0.8138 (0.8152) time: 0.1556 data: 0.0553 max mem: 9390 +Train: [80] [3000/6250] eta: 0:10:43 lr: 0.000013 grad: 0.1302 (0.1318) loss: 0.8113 (0.8150) time: 0.1339 data: 0.0490 max mem: 9390 +Train: [80] [3100/6250] eta: 0:10:22 lr: 0.000013 grad: 0.1321 (0.1319) loss: 0.8050 (0.8148) time: 0.1959 data: 0.1064 max mem: 9390 +Train: [80] [3200/6250] eta: 0:10:02 lr: 0.000013 grad: 0.1345 (0.1320) loss: 0.8078 (0.8146) time: 0.1797 data: 0.0936 max mem: 9390 +Train: [80] [3300/6250] eta: 0:09:45 lr: 0.000013 grad: 0.1306 (0.1322) loss: 0.8148 (0.8144) time: 0.3376 data: 0.2407 max mem: 9390 +pretraining fmri mae +start: 2026-04-01 13:10:42 +cwd: /data/connor/fmri-fm +sha: 7f4cedc35609f6857314e0d1ea6657523f17ddeb, status: has uncommitted changes, branch: dev/clane9 +config: +name: input_space_v3/flat_lr1e-3_3/pretrain +notes: input_space ablation v3 flat_lr1e-3_3; use tube masking and on-disk data (input_space=flat + base_lr=1e-3 seed=5403) +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain +input_space: flat +patch_size: 16 +num_frames: 16 +t_patch_size: 4 +mask_ratio: 0.9 +pred_mask_ratio: null +masking: tube +masking_kwargs: {} +mask_patch_size: null +model: mae_vit_base +model_kwargs: + decoding: attn + pos_embed: sep + target_norm: null + pca_norm_nc: 2 + t_pred_stride: 2 + no_decode_pos: true + mask_drop_scale: false + pred_edge_pad: 0 + gauss_sigma: null + class_token: true + reg_tokens: 0 + no_embed_class: true + head_init_scale: 0.0 + decoder_depth: 4 + drop_path_rate: 0.0 +datasets: + hcp-train: + type: wds + url: /data/fmri-datasets/pretrain/hcpya-all.${input_space}.wds/hcpya-all-${input_space}-{00000..01799}.tar + clipping: random + clipping_kwargs: + oversample: 4.0 + shuffle: true + buffer_size: 2000 + samples_per_epoch: 200000 + hcp-train-subset: + type: arrow + root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/validation + split_range: + - 0 + - 2000 + shuffle: false + hcp-val: + type: arrow + root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/test + split_range: + - 0 + - 2000 + shuffle: false +train_dataset: hcp-train +eval_datasets: +- hcp-train-subset +- hcp-val +val_dataset: null +clip_vmax: 3.0 +normalize: frame +tr_scale: null +crop_scale: null +crop_aspect: null +gray_jitter: null +num_workers: 16 +epochs: 100 +batch_size: 32 +accum_iter: 1 +base_lr: 0.001 +min_lr: 0.0 +warmup_epochs: 5 +weight_decay: 0.05 +betas: +- 0.9 +- 0.95 +clip_grad: 1.0 +amp: true +amp_dtype: float16 +ckpt: null +resume: true +auto_resume: true +start_epoch: 0 +max_checkpoints: 0 +checkpoint_period: null +plot_period: 5 +device: cuda +presend_cuda: false +seed: 5403 +debug: false +wandb: true +wandb_entity: null +wandb_project: fMRI-foundation-model +rank: 0 +world_size: 1 +gpu: 0 +distributed: true +dist_backend: nccl +in_chans: 1 +img_size: +- 224 +- 560 + +train transform: +Compose( + ToTensor() + TemporalCenterCrop(num_frames=16) + Normalize(mode='frame') + Clip(vmax=3.0) + FlatUnmask((224, 560)) +) +val transform: +Compose( + ToTensor() + TemporalCenterCrop(num_frames=16) + Normalize(mode='frame') + Clip(vmax=3.0) + FlatUnmask((224, 560)) +) +mask generator: +TubeMasking( + mask_ratio=0.9 + (patchify): Patchify2D((224, 560), (16, 16), in_chans=1) +) +loading dataset: hcp-train + +type: wds +url: /data/fmri-datasets/pretrain/hcpya-all.${input_space}.wds/hcpya-all-${input_space}-{00000..01799}.tar +clipping: random +clipping_kwargs: + oversample: 4.0 +shuffle: true +buffer_size: 2000 +samples_per_epoch: 200000 + +loading dataset: hcp-train-subset + +type: arrow +root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/validation +split_range: +- 0 +- 2000 +shuffle: false + +split indices: [899, 472, 767, 116, 1265, 1852, 300, 1335, 361, 1560] +loading dataset: hcp-val + +type: arrow +root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/test +split_range: +- 0 +- 2000 +shuffle: false + +split indices: [1075, 1189, 738, 1350, 965, 1964, 1367, 1183, 1619, 1407] +model: +MaskedAutoencoderViT( + decoding=attn, t_pred_stride=2, pred_edge_pad=0, no_decode_pos=True + (encoder): MaskedEncoder( + class_token=True, reg_tokens=0, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) + (pred_patchify): StridedPatchify3D((16, 224, 560), (2, 16, 16), in_chans=1, t_stride=2) + (decoder): MaskedDecoder( + cross_decode=False, class_token=True, no_embed_class=True + (pos_embed): SeparablePosEmbed(512, (4, 14, 35)) + (proj): Linear(in_features=768, out_features=512, bias=True) + (blocks): ModuleList( + (0-3): 4 x Block( + (norm1): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=16 + (q): Linear(in_features=512, out_features=512, bias=True) + (k): Linear(in_features=512, out_features=512, bias=True) + (v): Linear(in_features=512, out_features=512, bias=True) + (proj): Linear(in_features=512, out_features=512, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=512, out_features=2048, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=2048, out_features=512, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (head): Linear(in_features=512, out_features=512, bias=True) + ) +) +num params: 99.7M +total batch size: 32 = 32 bs per gpu x 1 accum x 1 gpus +lr: 1.25e-04 = 1.00e-03 x 32 / 256 +full schedule: epochs = 100 (steps = 625000) +warmup: epochs = 5 (steps = 31250) +loaded model state from checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +loaded optimizer state, resuming training from 80 +start training for 100 epochs +Train: [80] [ 0/6250] eta: 1 day, 16:20:08 lr: 0.000013 grad: 0.3015 (0.3015) loss: 0.7846 (0.7846) time: 23.2333 data: 21.2715 max mem: 9353 +Train: [80] [ 100/6250] eta: 1:45:40 lr: 0.000013 grad: 0.1576 (0.1612) loss: 0.8236 (0.8231) time: 0.0964 data: 0.0002 max mem: 9390 +Train: [80] [ 200/6250] eta: 1:38:02 lr: 0.000013 grad: 0.1526 (0.1597) loss: 0.8065 (0.8170) time: 0.3036 data: 0.2129 max mem: 9390 +Train: [80] [ 300/6250] eta: 1:27:20 lr: 0.000013 grad: 0.1384 (0.1557) loss: 0.8065 (0.8148) time: 0.9032 data: 0.8005 max mem: 9390 +Train: [80] [ 400/6250] eta: 1:25:16 lr: 0.000013 grad: 0.1402 (0.1516) loss: 0.8081 (0.8137) time: 0.6367 data: 0.5342 max mem: 9390 +Train: [80] [ 500/6250] eta: 1:17:45 lr: 0.000013 grad: 0.1219 (0.1486) loss: 0.8178 (0.8137) time: 0.1964 data: 0.0777 max mem: 9390 +Train: [80] [ 600/6250] eta: 1:15:04 lr: 0.000013 grad: 0.1201 (0.1453) loss: 0.8140 (0.8140) time: 0.3372 data: 0.2203 max mem: 9390 +Train: [80] [ 700/6250] eta: 1:16:54 lr: 0.000013 grad: 0.1222 (0.1425) loss: 0.8139 (0.8144) time: 0.7287 data: 0.6341 max mem: 9390 +Train: [80] [ 800/6250] eta: 1:11:44 lr: 0.000013 grad: 0.1215 (0.1408) loss: 0.8182 (0.8147) time: 0.2658 data: 0.1688 max mem: 9390 +Train: [80] [ 900/6250] eta: 1:05:48 lr: 0.000013 grad: 0.1140 (0.1387) loss: 0.8198 (0.8152) time: 0.1657 data: 0.0823 max mem: 9390 +Train: [80] [1000/6250] eta: 1:00:59 lr: 0.000013 grad: 0.1198 (0.1374) loss: 0.8197 (0.8155) time: 0.1776 data: 0.0634 max mem: 9390 +Train: [80] [1100/6250] eta: 0:56:59 lr: 0.000013 grad: 0.1303 (0.1374) loss: 0.8198 (0.8156) time: 0.4265 data: 0.3039 max mem: 9390 +Train: [80] [1200/6250] eta: 0:53:34 lr: 0.000013 grad: 0.1241 (0.1365) loss: 0.8156 (0.8156) time: 0.8555 data: 0.7539 max mem: 9390 +Train: [80] [1300/6250] eta: 0:49:39 lr: 0.000013 grad: 0.1294 (0.1359) loss: 0.8154 (0.8154) time: 0.2267 data: 0.1212 max mem: 9390 +Train: [80] [1400/6250] eta: 0:46:13 lr: 0.000013 grad: 0.1237 (0.1355) loss: 0.8124 (0.8153) time: 0.1224 data: 0.0258 max mem: 9390 +Train: [80] [1500/6250] eta: 0:43:14 lr: 0.000013 grad: 0.1245 (0.1353) loss: 0.8079 (0.8153) time: 0.1785 data: 0.0899 max mem: 9390 +Train: [80] [1600/6250] eta: 0:40:37 lr: 0.000013 grad: 0.1359 (0.1354) loss: 0.8185 (0.8150) time: 0.1806 data: 0.0972 max mem: 9390 +Train: [80] [1700/6250] eta: 0:38:20 lr: 0.000013 grad: 0.1384 (0.1353) loss: 0.8104 (0.8148) time: 0.2511 data: 0.1592 max mem: 9390 +Train: [80] [1800/6250] eta: 0:36:19 lr: 0.000013 grad: 0.1336 (0.1352) loss: 0.8100 (0.8147) time: 0.3544 data: 0.2526 max mem: 9390 +Train: [80] [1900/6250] eta: 0:34:55 lr: 0.000013 grad: 0.1250 (0.1352) loss: 0.8151 (0.8145) time: 0.1068 data: 0.0003 max mem: 9390 +Train: [80] [2000/6250] eta: 0:34:14 lr: 0.000013 grad: 0.1271 (0.1349) loss: 0.8203 (0.8145) time: 1.7498 data: 1.6691 max mem: 9390 +Train: [80] [2100/6250] eta: 0:32:50 lr: 0.000013 grad: 0.1301 (0.1347) loss: 0.8169 (0.8144) time: 0.8050 data: 0.6814 max mem: 9390 +Train: [80] [2200/6250] eta: 0:32:22 lr: 0.000013 grad: 0.1290 (0.1345) loss: 0.8173 (0.8143) time: 0.9873 data: 0.8856 max mem: 9390 +Train: [80] [2300/6250] eta: 0:31:17 lr: 0.000013 grad: 0.1330 (0.1343) loss: 0.8132 (0.8143) time: 0.2186 data: 0.1281 max mem: 9390 +Train: [80] [2400/6250] eta: 0:30:00 lr: 0.000013 grad: 0.1340 (0.1342) loss: 0.8137 (0.8142) time: 0.7007 data: 0.6004 max mem: 9390 +Train: [80] [2500/6250] eta: 0:29:31 lr: 0.000013 grad: 0.1234 (0.1340) loss: 0.8134 (0.8143) time: 0.3441 data: 0.2318 max mem: 9390 +Train: [80] [2600/6250] eta: 0:28:43 lr: 0.000013 grad: 0.1317 (0.1338) loss: 0.8132 (0.8142) time: 0.0991 data: 0.0002 max mem: 9390 +Train: [80] [2700/6250] eta: 0:27:47 lr: 0.000013 grad: 0.1278 (0.1336) loss: 0.8072 (0.8142) time: 0.7067 data: 0.5945 max mem: 9390 +Train: [80] [2800/6250] eta: 0:26:49 lr: 0.000013 grad: 0.1329 (0.1338) loss: 0.8113 (0.8140) time: 0.2243 data: 0.1225 max mem: 9390 +Train: [80] [2900/6250] eta: 0:26:09 lr: 0.000013 grad: 0.1280 (0.1340) loss: 0.8113 (0.8138) time: 1.0762 data: 0.9460 max mem: 9390 +Train: [80] [3000/6250] eta: 0:25:26 lr: 0.000013 grad: 0.1364 (0.1341) loss: 0.8119 (0.8136) time: 0.4303 data: 0.3458 max mem: 9390 +Train: [80] [3100/6250] eta: 0:24:52 lr: 0.000013 grad: 0.1272 (0.1341) loss: 0.8132 (0.8133) time: 0.1272 data: 0.0003 max mem: 9390 +Train: [80] [3200/6250] eta: 0:23:43 lr: 0.000013 grad: 0.1310 (0.1340) loss: 0.8122 (0.8132) time: 0.2912 data: 0.1923 max mem: 9390 +Train: [80] [3300/6250] eta: 0:22:42 lr: 0.000013 grad: 0.1343 (0.1340) loss: 0.8077 (0.8131) time: 0.2009 data: 0.1039 max mem: 9390 +Train: [80] [3400/6250] eta: 0:21:30 lr: 0.000012 grad: 0.1295 (0.1339) loss: 0.8064 (0.8130) time: 0.1494 data: 0.0645 max mem: 9390 +Train: [80] [3500/6250] eta: 0:20:23 lr: 0.000012 grad: 0.1299 (0.1339) loss: 0.8128 (0.8129) time: 0.1684 data: 0.0861 max mem: 9390 +Train: [80] [3600/6250] eta: 0:19:16 lr: 0.000012 grad: 0.1289 (0.1339) loss: 0.8128 (0.8128) time: 0.1228 data: 0.0389 max mem: 9390 +Train: [80] [3700/6250] eta: 0:18:12 lr: 0.000012 grad: 0.1241 (0.1338) loss: 0.8072 (0.8127) time: 0.1370 data: 0.0520 max mem: 9390 +Train: [80] [3800/6250] eta: 0:17:12 lr: 0.000012 grad: 0.1318 (0.1338) loss: 0.8146 (0.8127) time: 0.1556 data: 0.0751 max mem: 9390 +Train: [80] [3900/6250] eta: 0:16:13 lr: 0.000012 grad: 0.1254 (0.1337) loss: 0.8115 (0.8126) time: 0.1437 data: 0.0586 max mem: 9390 +Train: [80] [4000/6250] eta: 0:15:17 lr: 0.000012 grad: 0.1332 (0.1337) loss: 0.8070 (0.8126) time: 0.1433 data: 0.0583 max mem: 9390 +Train: [80] [4100/6250] eta: 0:14:23 lr: 0.000012 grad: 0.1233 (0.1336) loss: 0.8135 (0.8126) time: 0.1497 data: 0.0703 max mem: 9390 +Train: [80] [4200/6250] eta: 0:13:30 lr: 0.000012 grad: 0.1323 (0.1336) loss: 0.8057 (0.8125) time: 0.1535 data: 0.0769 max mem: 9390 +Train: [80] [4300/6250] eta: 0:12:39 lr: 0.000012 grad: 0.1279 (0.1336) loss: 0.8080 (0.8125) time: 0.1378 data: 0.0509 max mem: 9390 +Train: [80] [4400/6250] eta: 0:11:50 lr: 0.000012 grad: 0.1228 (0.1335) loss: 0.8131 (0.8124) time: 0.1649 data: 0.0837 max mem: 9390 +Train: [80] [4500/6250] eta: 0:11:03 lr: 0.000012 grad: 0.1270 (0.1334) loss: 0.8003 (0.8124) time: 0.1461 data: 0.0720 max mem: 9390 +Train: [80] [4600/6250] eta: 0:10:16 lr: 0.000012 grad: 0.1304 (0.1334) loss: 0.8071 (0.8123) time: 0.1449 data: 0.0638 max mem: 9390 +Train: [80] [4700/6250] eta: 0:09:31 lr: 0.000012 grad: 0.1308 (0.1333) loss: 0.8096 (0.8122) time: 0.1431 data: 0.0605 max mem: 9390 +Train: [80] [4800/6250] eta: 0:08:48 lr: 0.000012 grad: 0.1284 (0.1332) loss: 0.8102 (0.8121) time: 0.1420 data: 0.0532 max mem: 9390 +Train: [80] [4900/6250] eta: 0:08:06 lr: 0.000012 grad: 0.1410 (0.1333) loss: 0.8100 (0.8121) time: 0.1425 data: 0.0631 max mem: 9390 +Train: [80] [5000/6250] eta: 0:07:24 lr: 0.000012 grad: 0.1259 (0.1332) loss: 0.8096 (0.8120) time: 0.1297 data: 0.0573 max mem: 9390 +Train: [80] [5100/6250] eta: 0:06:44 lr: 0.000012 grad: 0.1316 (0.1333) loss: 0.8123 (0.8120) time: 0.1683 data: 0.0797 max mem: 9390 +Train: [80] [5200/6250] eta: 0:06:05 lr: 0.000012 grad: 0.1273 (0.1333) loss: 0.8110 (0.8119) time: 0.1596 data: 0.0623 max mem: 9390 +Train: [80] [5300/6250] eta: 0:05:27 lr: 0.000012 grad: 0.1237 (0.1334) loss: 0.8097 (0.8119) time: 0.1468 data: 0.0560 max mem: 9390 +Train: [80] [5400/6250] eta: 0:04:49 lr: 0.000012 grad: 0.1252 (0.1334) loss: 0.8140 (0.8118) time: 0.1412 data: 0.0591 max mem: 9390 +Train: [80] [5500/6250] eta: 0:04:12 lr: 0.000012 grad: 0.1379 (0.1334) loss: 0.8025 (0.8118) time: 0.1499 data: 0.0575 max mem: 9390 +Train: [80] [5600/6250] eta: 0:03:36 lr: 0.000012 grad: 0.1312 (0.1334) loss: 0.8053 (0.8117) time: 0.1481 data: 0.0611 max mem: 9390 +Train: [80] [5700/6250] eta: 0:03:01 lr: 0.000012 grad: 0.1257 (0.1334) loss: 0.8089 (0.8116) time: 0.1702 data: 0.0789 max mem: 9390 +Train: [80] [5800/6250] eta: 0:02:27 lr: 0.000012 grad: 0.1298 (0.1334) loss: 0.8050 (0.8116) time: 0.1479 data: 0.0670 max mem: 9390 +Train: [80] [5900/6250] eta: 0:01:53 lr: 0.000012 grad: 0.1252 (0.1333) loss: 0.8132 (0.8116) time: 0.1411 data: 0.0613 max mem: 9390 +Train: [80] [6000/6250] eta: 0:01:20 lr: 0.000012 grad: 0.1290 (0.1333) loss: 0.8128 (0.8116) time: 0.1460 data: 0.0669 max mem: 9390 +Train: [80] [6100/6250] eta: 0:00:47 lr: 0.000012 grad: 0.1300 (0.1332) loss: 0.8115 (0.8116) time: 0.1547 data: 0.0655 max mem: 9390 +Train: [80] [6200/6250] eta: 0:00:15 lr: 0.000012 grad: 0.1310 (0.1333) loss: 0.8081 (0.8116) time: 0.1268 data: 0.0378 max mem: 9390 +Train: [80] [6249/6250] eta: 0:00:00 lr: 0.000012 grad: 0.1304 (0.1333) loss: 0.8070 (0.8116) time: 0.1604 data: 0.0698 max mem: 9390 +Train: [80] Total time: 0:32:55 (0.3161 s / it) +Averaged stats: lr: 0.000012 grad: 0.1304 (0.1333) loss: 0.8070 (0.8116) +Eval (hcp-train-subset): [80] [ 0/62] eta: 0:03:49 loss: 0.8323 (0.8323) time: 3.6938 data: 3.6259 max mem: 9390 +Eval (hcp-train-subset): [80] [61/62] eta: 0:00:00 loss: 0.8203 (0.8225) time: 0.1166 data: 0.0920 max mem: 9390 +Eval (hcp-train-subset): [80] Total time: 0:00:12 (0.2000 s / it) +Averaged stats (hcp-train-subset): loss: 0.8203 (0.8225) +Eval (hcp-val): [80] [ 0/62] eta: 0:04:25 loss: 0.8303 (0.8303) time: 4.2856 data: 4.2588 max mem: 9390 +Eval (hcp-val): [80] [61/62] eta: 0:00:00 loss: 0.8298 (0.8301) time: 0.1261 data: 0.0998 max mem: 9390 +Eval (hcp-val): [80] Total time: 0:00:12 (0.1994 s / it) +Averaged stats (hcp-val): loss: 0.8298 (0.8301) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +Train: [81] [ 0/6250] eta: 9:30:39 lr: 0.000012 grad: 0.1182 (0.1182) loss: 0.8493 (0.8493) time: 5.4784 data: 5.3765 max mem: 9390 +Train: [81] [ 100/6250] eta: 0:21:19 lr: 0.000012 grad: 0.1358 (0.1582) loss: 0.8332 (0.8288) time: 0.1624 data: 0.0652 max mem: 9390 +Train: [81] [ 200/6250] eta: 0:18:36 lr: 0.000012 grad: 0.1309 (0.1491) loss: 0.8284 (0.8270) time: 0.1589 data: 0.0612 max mem: 9390 +Train: [81] [ 300/6250] eta: 0:17:31 lr: 0.000012 grad: 0.1347 (0.1453) loss: 0.8186 (0.8246) time: 0.1639 data: 0.0782 max mem: 9390 +Train: [81] [ 400/6250] eta: 0:16:21 lr: 0.000012 grad: 0.1305 (0.1431) loss: 0.8220 (0.8233) time: 0.1527 data: 0.0697 max mem: 9390 +Train: [81] [ 500/6250] eta: 0:15:31 lr: 0.000012 grad: 0.1284 (0.1417) loss: 0.8201 (0.8226) time: 0.1416 data: 0.0498 max mem: 9390 +Train: [81] [ 600/6250] eta: 0:15:02 lr: 0.000012 grad: 0.1339 (0.1400) loss: 0.8157 (0.8220) time: 0.1517 data: 0.0549 max mem: 9390 +Train: [81] [ 700/6250] eta: 0:14:29 lr: 0.000012 grad: 0.1266 (0.1384) loss: 0.8213 (0.8216) time: 0.1169 data: 0.0320 max mem: 9390 +Train: [81] [ 800/6250] eta: 0:13:57 lr: 0.000012 grad: 0.1256 (0.1377) loss: 0.8176 (0.8210) time: 0.1391 data: 0.0561 max mem: 9390 +Train: [81] [ 900/6250] eta: 0:13:31 lr: 0.000012 grad: 0.1351 (0.1368) loss: 0.8149 (0.8204) time: 0.1267 data: 0.0356 max mem: 9390 +Train: [81] [1000/6250] eta: 0:13:05 lr: 0.000012 grad: 0.1225 (0.1362) loss: 0.8171 (0.8198) time: 0.1331 data: 0.0468 max mem: 9390 +Train: [81] [1100/6250] eta: 0:12:39 lr: 0.000012 grad: 0.1251 (0.1355) loss: 0.8114 (0.8194) time: 0.1394 data: 0.0625 max mem: 9390 +Train: [81] [1200/6250] eta: 0:12:14 lr: 0.000012 grad: 0.1405 (0.1354) loss: 0.8132 (0.8189) time: 0.1302 data: 0.0546 max mem: 9390 +Train: [81] [1300/6250] eta: 0:11:51 lr: 0.000012 grad: 0.1283 (0.1353) loss: 0.8131 (0.8183) time: 0.1350 data: 0.0533 max mem: 9390 +Train: [81] [1400/6250] eta: 0:11:30 lr: 0.000012 grad: 0.1340 (0.1351) loss: 0.8074 (0.8179) time: 0.1277 data: 0.0457 max mem: 9390 +Train: [81] [1500/6250] eta: 0:11:08 lr: 0.000012 grad: 0.1287 (0.1350) loss: 0.8173 (0.8174) time: 0.1110 data: 0.0278 max mem: 9390 +Train: [81] [1600/6250] eta: 0:10:48 lr: 0.000012 grad: 0.1309 (0.1349) loss: 0.8111 (0.8170) time: 0.1109 data: 0.0282 max mem: 9390 +Train: [81] [1700/6250] eta: 0:10:29 lr: 0.000012 grad: 0.1238 (0.1347) loss: 0.8119 (0.8166) time: 0.1338 data: 0.0506 max mem: 9390 +Train: [81] [1800/6250] eta: 0:10:10 lr: 0.000012 grad: 0.1320 (0.1347) loss: 0.8062 (0.8162) time: 0.1290 data: 0.0461 max mem: 9390 +Train: [81] [1900/6250] eta: 0:09:59 lr: 0.000012 grad: 0.1311 (0.1347) loss: 0.8108 (0.8158) time: 0.1963 data: 0.1098 max mem: 9390 +Train: [81] [2000/6250] eta: 0:10:10 lr: 0.000012 grad: 0.1342 (0.1346) loss: 0.8072 (0.8154) time: 0.1437 data: 0.0489 max mem: 9390 +Train: [81] [2100/6250] eta: 0:10:07 lr: 0.000012 grad: 0.1281 (0.1344) loss: 0.8139 (0.8151) time: 0.2587 data: 0.1357 max mem: 9390 +Train: [81] [2200/6250] eta: 0:10:04 lr: 0.000012 grad: 0.1239 (0.1342) loss: 0.8090 (0.8149) time: 0.2611 data: 0.1118 max mem: 9390 +Train: [81] [2300/6250] eta: 0:10:09 lr: 0.000011 grad: 0.1283 (0.1340) loss: 0.8102 (0.8147) time: 0.3784 data: 0.2921 max mem: 9390 +Train: [81] [2400/6250] eta: 0:10:12 lr: 0.000011 grad: 0.1220 (0.1338) loss: 0.8124 (0.8146) time: 0.0978 data: 0.0002 max mem: 9390 +Train: [81] [2500/6250] eta: 0:10:33 lr: 0.000011 grad: 0.1280 (0.1339) loss: 0.8099 (0.8144) time: 0.3531 data: 0.2732 max mem: 9390 +Train: [81] [2600/6250] eta: 0:10:51 lr: 0.000011 grad: 0.1335 (0.1340) loss: 0.8111 (0.8143) time: 0.1879 data: 0.0493 max mem: 9390 +Train: [81] [2700/6250] eta: 0:10:38 lr: 0.000011 grad: 0.1205 (0.1339) loss: 0.8100 (0.8142) time: 0.1632 data: 0.0640 max mem: 9390 +Train: [81] [2800/6250] eta: 0:10:22 lr: 0.000011 grad: 0.1375 (0.1339) loss: 0.8130 (0.8140) time: 0.0899 data: 0.0002 max mem: 9390 +Train: [81] [2900/6250] eta: 0:10:01 lr: 0.000011 grad: 0.1303 (0.1338) loss: 0.8156 (0.8139) time: 0.1548 data: 0.0585 max mem: 9390 +Train: [81] [3000/6250] eta: 0:09:43 lr: 0.000011 grad: 0.1360 (0.1338) loss: 0.8099 (0.8138) time: 0.1210 data: 0.0321 max mem: 9390 +Train: [81] [3100/6250] eta: 0:09:27 lr: 0.000011 grad: 0.1372 (0.1338) loss: 0.8112 (0.8137) time: 0.3846 data: 0.2592 max mem: 9390 +Train: [81] [3200/6250] eta: 0:09:05 lr: 0.000011 grad: 0.1338 (0.1339) loss: 0.8140 (0.8136) time: 0.1682 data: 0.0838 max mem: 9390 +Train: [81] [3300/6250] eta: 0:08:49 lr: 0.000011 grad: 0.1384 (0.1339) loss: 0.8115 (0.8135) time: 0.3594 data: 0.2497 max mem: 9390 +Train: [81] [3400/6250] eta: 0:08:29 lr: 0.000011 grad: 0.1252 (0.1339) loss: 0.8169 (0.8133) time: 0.1314 data: 0.0353 max mem: 9390 +Train: [81] [3500/6250] eta: 0:08:10 lr: 0.000011 grad: 0.1309 (0.1338) loss: 0.8085 (0.8132) time: 0.1505 data: 0.0695 max mem: 9390 +Train: [81] [3600/6250] eta: 0:07:52 lr: 0.000011 grad: 0.1371 (0.1340) loss: 0.8049 (0.8131) time: 0.1497 data: 0.0511 max mem: 9390 +Train: [81] [3700/6250] eta: 0:07:33 lr: 0.000011 grad: 0.1380 (0.1339) loss: 0.8095 (0.8130) time: 0.1775 data: 0.0941 max mem: 9390 +Train: [81] [3800/6250] eta: 0:07:15 lr: 0.000011 grad: 0.1272 (0.1339) loss: 0.8038 (0.8128) time: 0.2072 data: 0.1208 max mem: 9390 +Train: [81] [3900/6250] eta: 0:07:00 lr: 0.000011 grad: 0.1287 (0.1340) loss: 0.8056 (0.8127) time: 0.1148 data: 0.0274 max mem: 9390 +Train: [81] [4000/6250] eta: 0:06:41 lr: 0.000011 grad: 0.1364 (0.1340) loss: 0.8080 (0.8126) time: 0.0878 data: 0.0002 max mem: 9390 +Train: [81] [4100/6250] eta: 0:06:23 lr: 0.000011 grad: 0.1255 (0.1340) loss: 0.8157 (0.8126) time: 0.1025 data: 0.0053 max mem: 9390 +Train: [81] [4200/6250] eta: 0:06:05 lr: 0.000011 grad: 0.1318 (0.1340) loss: 0.8077 (0.8126) time: 0.1738 data: 0.0869 max mem: 9390 +Train: [81] [4300/6250] eta: 0:05:49 lr: 0.000011 grad: 0.1343 (0.1340) loss: 0.8136 (0.8125) time: 0.1061 data: 0.0002 max mem: 9390 +Train: [81] [4400/6250] eta: 0:05:34 lr: 0.000011 grad: 0.1232 (0.1339) loss: 0.8058 (0.8124) time: 0.5246 data: 0.4321 max mem: 9390 +Train: [81] [4500/6250] eta: 0:05:16 lr: 0.000011 grad: 0.1291 (0.1339) loss: 0.8100 (0.8123) time: 0.1997 data: 0.1064 max mem: 9390 +Train: [81] [4600/6250] eta: 0:04:58 lr: 0.000011 grad: 0.1331 (0.1338) loss: 0.8100 (0.8123) time: 0.1512 data: 0.0560 max mem: 9390 +Train: [81] [4700/6250] eta: 0:04:39 lr: 0.000011 grad: 0.1252 (0.1338) loss: 0.8054 (0.8122) time: 0.1905 data: 0.1078 max mem: 9390 +Train: [81] [4800/6250] eta: 0:04:22 lr: 0.000011 grad: 0.1311 (0.1339) loss: 0.8066 (0.8121) time: 0.3467 data: 0.2542 max mem: 9390 +Train: [81] [4900/6250] eta: 0:04:03 lr: 0.000011 grad: 0.1326 (0.1339) loss: 0.8083 (0.8120) time: 0.1661 data: 0.0629 max mem: 9390 +Train: [81] [5000/6250] eta: 0:03:45 lr: 0.000011 grad: 0.1244 (0.1338) loss: 0.8159 (0.8120) time: 0.2370 data: 0.1536 max mem: 9390 +Train: [81] [5100/6250] eta: 0:03:28 lr: 0.000011 grad: 0.1337 (0.1339) loss: 0.8086 (0.8119) time: 0.1262 data: 0.0249 max mem: 9390 +Train: [81] [5200/6250] eta: 0:03:10 lr: 0.000011 grad: 0.1314 (0.1339) loss: 0.8065 (0.8118) time: 0.2096 data: 0.1216 max mem: 9390 +Train: [81] [5300/6250] eta: 0:02:53 lr: 0.000011 grad: 0.1335 (0.1340) loss: 0.8071 (0.8118) time: 0.4847 data: 0.3871 max mem: 9390 +Train: [81] [5400/6250] eta: 0:02:35 lr: 0.000011 grad: 0.1303 (0.1340) loss: 0.8138 (0.8117) time: 0.1144 data: 0.0167 max mem: 9390 +Train: [81] [5500/6250] eta: 0:02:17 lr: 0.000011 grad: 0.1347 (0.1340) loss: 0.8109 (0.8117) time: 0.2667 data: 0.1891 max mem: 9390 +Train: [81] [5600/6250] eta: 0:01:59 lr: 0.000011 grad: 0.1248 (0.1341) loss: 0.8132 (0.8116) time: 0.1997 data: 0.1151 max mem: 9390 +Train: [81] [5700/6250] eta: 0:01:41 lr: 0.000011 grad: 0.1467 (0.1341) loss: 0.8053 (0.8115) time: 0.2253 data: 0.1441 max mem: 9390 +Train: [81] [5800/6250] eta: 0:01:22 lr: 0.000011 grad: 0.1385 (0.1342) loss: 0.8054 (0.8115) time: 0.1375 data: 0.0579 max mem: 9390 +Train: [81] [5900/6250] eta: 0:01:04 lr: 0.000011 grad: 0.1375 (0.1342) loss: 0.8032 (0.8114) time: 0.1674 data: 0.0938 max mem: 9390 +Train: [81] [6000/6250] eta: 0:00:45 lr: 0.000011 grad: 0.1298 (0.1342) loss: 0.8120 (0.8114) time: 0.1097 data: 0.0042 max mem: 9390 +Train: [81] [6100/6250] eta: 0:00:27 lr: 0.000011 grad: 0.1400 (0.1342) loss: 0.8130 (0.8114) time: 0.1197 data: 0.0350 max mem: 9390 +Train: [81] [6200/6250] eta: 0:00:09 lr: 0.000011 grad: 0.1343 (0.1343) loss: 0.8088 (0.8113) time: 0.1663 data: 0.0882 max mem: 9390 +Train: [81] [6249/6250] eta: 0:00:00 lr: 0.000011 grad: 0.1395 (0.1343) loss: 0.8048 (0.8113) time: 0.1830 data: 0.0997 max mem: 9390 +Train: [81] Total time: 0:19:08 (0.1837 s / it) +Averaged stats: lr: 0.000011 grad: 0.1395 (0.1343) loss: 0.8048 (0.8113) +Eval (hcp-train-subset): [81] [ 0/62] eta: 0:04:41 loss: 0.8346 (0.8346) time: 4.5472 data: 4.5183 max mem: 9390 +Eval (hcp-train-subset): [81] [61/62] eta: 0:00:00 loss: 0.8196 (0.8220) time: 0.2691 data: 0.2432 max mem: 9390 +Eval (hcp-train-subset): [81] Total time: 0:00:17 (0.2898 s / it) +Averaged stats (hcp-train-subset): loss: 0.8196 (0.8220) +Eval (hcp-val): [81] [ 0/62] eta: 0:05:20 loss: 0.8270 (0.8270) time: 5.1642 data: 5.1205 max mem: 9390 +Eval (hcp-val): [81] [61/62] eta: 0:00:00 loss: 0.8288 (0.8306) time: 0.1357 data: 0.1086 max mem: 9390 +Eval (hcp-val): [81] Total time: 0:00:15 (0.2535 s / it) +Averaged stats (hcp-val): loss: 0.8288 (0.8306) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +Train: [82] [ 0/6250] eta: 11:48:22 lr: 0.000011 grad: 0.1987 (0.1987) loss: 0.8267 (0.8267) time: 6.8003 data: 6.7060 max mem: 9390 +Train: [82] [ 100/6250] eta: 0:26:03 lr: 0.000011 grad: 0.1358 (0.1414) loss: 0.8239 (0.8276) time: 0.1720 data: 0.0723 max mem: 9390 +Train: [82] [ 200/6250] eta: 0:22:50 lr: 0.000011 grad: 0.1407 (0.1423) loss: 0.8259 (0.8264) time: 0.1910 data: 0.0879 max mem: 9390 +Train: [82] [ 300/6250] eta: 0:21:48 lr: 0.000011 grad: 0.1211 (0.1419) loss: 0.8164 (0.8240) time: 0.2089 data: 0.1041 max mem: 9390 +Train: [82] [ 400/6250] eta: 0:19:58 lr: 0.000011 grad: 0.1495 (0.1421) loss: 0.8131 (0.8214) time: 0.1590 data: 0.0605 max mem: 9390 +Train: [82] [ 500/6250] eta: 0:19:00 lr: 0.000011 grad: 0.1326 (0.1428) loss: 0.8141 (0.8196) time: 0.2115 data: 0.1269 max mem: 9390 +Train: [82] [ 600/6250] eta: 0:18:25 lr: 0.000011 grad: 0.1340 (0.1417) loss: 0.8142 (0.8182) time: 0.1904 data: 0.1064 max mem: 9390 +Train: [82] [ 700/6250] eta: 0:18:07 lr: 0.000011 grad: 0.1409 (0.1411) loss: 0.8080 (0.8168) time: 0.1889 data: 0.0896 max mem: 9390 +Train: [82] [ 800/6250] eta: 0:18:58 lr: 0.000011 grad: 0.1491 (0.1409) loss: 0.8112 (0.8162) time: 0.3610 data: 0.2646 max mem: 9390 +Train: [82] [ 900/6250] eta: 0:19:46 lr: 0.000011 grad: 0.1353 (0.1411) loss: 0.8102 (0.8156) time: 0.1856 data: 0.0913 max mem: 9390 +Train: [82] [1000/6250] eta: 0:19:01 lr: 0.000011 grad: 0.1355 (0.1410) loss: 0.8034 (0.8149) time: 0.1203 data: 0.0242 max mem: 9390 +Train: [82] [1100/6250] eta: 0:18:50 lr: 0.000011 grad: 0.1384 (0.1411) loss: 0.8034 (0.8140) time: 0.2705 data: 0.1774 max mem: 9390 +Train: [82] [1200/6250] eta: 0:18:46 lr: 0.000011 grad: 0.1430 (0.1412) loss: 0.8028 (0.8134) time: 0.3394 data: 0.2493 max mem: 9390 +Train: [82] [1300/6250] eta: 0:18:24 lr: 0.000011 grad: 0.1341 (0.1413) loss: 0.8035 (0.8128) time: 0.4769 data: 0.3642 max mem: 9390 +Train: [82] [1400/6250] eta: 0:17:57 lr: 0.000010 grad: 0.1281 (0.1410) loss: 0.8078 (0.8124) time: 0.1366 data: 0.0443 max mem: 9390 +Train: [82] [1500/6250] eta: 0:17:34 lr: 0.000010 grad: 0.1334 (0.1410) loss: 0.8089 (0.8121) time: 0.2006 data: 0.0839 max mem: 9390 +Train: [82] [1600/6250] eta: 0:17:09 lr: 0.000010 grad: 0.1357 (0.1408) loss: 0.8060 (0.8117) time: 0.1037 data: 0.0002 max mem: 9390 +Train: [82] [1700/6250] eta: 0:16:54 lr: 0.000010 grad: 0.1368 (0.1403) loss: 0.8128 (0.8117) time: 0.1421 data: 0.0487 max mem: 9390 +Train: [82] [1800/6250] eta: 0:16:47 lr: 0.000010 grad: 0.1352 (0.1399) loss: 0.8067 (0.8116) time: 0.6550 data: 0.5637 max mem: 9390 +Train: [82] [1900/6250] eta: 0:16:22 lr: 0.000010 grad: 0.1406 (0.1396) loss: 0.8089 (0.8115) time: 0.2835 data: 0.1920 max mem: 9390 +Train: [82] [2000/6250] eta: 0:15:49 lr: 0.000010 grad: 0.1255 (0.1393) loss: 0.8122 (0.8114) time: 0.1709 data: 0.0646 max mem: 9390 +Train: [82] [2100/6250] eta: 0:15:40 lr: 0.000010 grad: 0.1252 (0.1390) loss: 0.8094 (0.8113) time: 0.2401 data: 0.1531 max mem: 9390 +Train: [82] [2200/6250] eta: 0:15:13 lr: 0.000010 grad: 0.1268 (0.1387) loss: 0.8095 (0.8113) time: 0.1416 data: 0.0451 max mem: 9390 +Train: [82] [2300/6250] eta: 0:14:54 lr: 0.000010 grad: 0.1325 (0.1384) loss: 0.7989 (0.8110) time: 0.1092 data: 0.0003 max mem: 9390 +Train: [82] [2400/6250] eta: 0:14:48 lr: 0.000010 grad: 0.1354 (0.1382) loss: 0.8074 (0.8109) time: 0.1067 data: 0.0002 max mem: 9390 +Train: [82] [2500/6250] eta: 0:14:24 lr: 0.000010 grad: 0.1326 (0.1382) loss: 0.8065 (0.8107) time: 0.1832 data: 0.0692 max mem: 9390 +Train: [82] [2600/6250] eta: 0:14:03 lr: 0.000010 grad: 0.1354 (0.1380) loss: 0.8035 (0.8106) time: 0.1626 data: 0.0650 max mem: 9390 +Train: [82] [2700/6250] eta: 0:13:49 lr: 0.000010 grad: 0.1394 (0.1380) loss: 0.8053 (0.8104) time: 0.1531 data: 0.0630 max mem: 9390 +Train: [82] [2800/6250] eta: 0:13:20 lr: 0.000010 grad: 0.1317 (0.1380) loss: 0.8042 (0.8102) time: 0.2685 data: 0.1658 max mem: 9390 +Train: [82] [2900/6250] eta: 0:13:11 lr: 0.000010 grad: 0.1417 (0.1381) loss: 0.7998 (0.8101) time: 0.2729 data: 0.1874 max mem: 9390 +Train: [82] [3000/6250] eta: 0:12:41 lr: 0.000010 grad: 0.1352 (0.1380) loss: 0.7957 (0.8098) time: 0.1001 data: 0.0003 max mem: 9390 +Train: [82] [3100/6250] eta: 0:12:12 lr: 0.000010 grad: 0.1342 (0.1381) loss: 0.8046 (0.8097) time: 0.1585 data: 0.0270 max mem: 9390 +Train: [82] [3200/6250] eta: 0:11:46 lr: 0.000010 grad: 0.1294 (0.1379) loss: 0.8115 (0.8097) time: 0.1242 data: 0.0277 max mem: 9390 +Train: [82] [3300/6250] eta: 0:11:25 lr: 0.000010 grad: 0.1402 (0.1379) loss: 0.8039 (0.8096) time: 0.3552 data: 0.2629 max mem: 9390 +Train: [82] [3400/6250] eta: 0:10:59 lr: 0.000010 grad: 0.1323 (0.1380) loss: 0.8059 (0.8094) time: 0.2532 data: 0.1580 max mem: 9390 +Train: [82] [3500/6250] eta: 0:10:33 lr: 0.000010 grad: 0.1343 (0.1381) loss: 0.8022 (0.8092) time: 0.0944 data: 0.0002 max mem: 9390 +Train: [82] [3600/6250] eta: 0:10:09 lr: 0.000010 grad: 0.1335 (0.1381) loss: 0.8126 (0.8091) time: 0.1067 data: 0.0070 max mem: 9390 +Train: [82] [3700/6250] eta: 0:09:45 lr: 0.000010 grad: 0.1340 (0.1381) loss: 0.8033 (0.8090) time: 0.1667 data: 0.0756 max mem: 9390 +Train: [82] [3800/6250] eta: 0:09:22 lr: 0.000010 grad: 0.1347 (0.1382) loss: 0.8107 (0.8090) time: 0.3534 data: 0.2632 max mem: 9390 +Train: [82] [3900/6250] eta: 0:09:01 lr: 0.000010 grad: 0.1331 (0.1382) loss: 0.8097 (0.8090) time: 0.1569 data: 0.0698 max mem: 9390 +Train: [82] [4000/6250] eta: 0:08:38 lr: 0.000010 grad: 0.1319 (0.1381) loss: 0.8083 (0.8090) time: 0.1246 data: 0.0120 max mem: 9390 +Train: [82] [4100/6250] eta: 0:08:17 lr: 0.000010 grad: 0.1289 (0.1380) loss: 0.8115 (0.8091) time: 0.6803 data: 0.5965 max mem: 9390 +Train: [82] [4200/6250] eta: 0:07:53 lr: 0.000010 grad: 0.1283 (0.1378) loss: 0.8076 (0.8091) time: 0.1019 data: 0.0003 max mem: 9390 +Train: [82] [4300/6250] eta: 0:07:29 lr: 0.000010 grad: 0.1289 (0.1377) loss: 0.8149 (0.8092) time: 0.2176 data: 0.1253 max mem: 9390 +Train: [82] [4400/6250] eta: 0:07:03 lr: 0.000010 grad: 0.1243 (0.1376) loss: 0.8167 (0.8093) time: 0.1829 data: 0.0912 max mem: 9390 +Train: [82] [4500/6250] eta: 0:06:43 lr: 0.000010 grad: 0.1307 (0.1375) loss: 0.8113 (0.8093) time: 0.2058 data: 0.1002 max mem: 9390 +Train: [82] [4600/6250] eta: 0:06:21 lr: 0.000010 grad: 0.1294 (0.1373) loss: 0.8081 (0.8094) time: 0.4580 data: 0.3637 max mem: 9390 +Train: [82] [4700/6250] eta: 0:05:56 lr: 0.000010 grad: 0.1310 (0.1372) loss: 0.8137 (0.8095) time: 0.1622 data: 0.0849 max mem: 9390 +Train: [82] [4800/6250] eta: 0:05:31 lr: 0.000010 grad: 0.1304 (0.1372) loss: 0.8138 (0.8096) time: 0.1726 data: 0.0895 max mem: 9390 +Train: [82] [4900/6250] eta: 0:05:10 lr: 0.000010 grad: 0.1330 (0.1372) loss: 0.8088 (0.8096) time: 0.4700 data: 0.3849 max mem: 9390 +Train: [82] [5000/6250] eta: 0:04:45 lr: 0.000010 grad: 0.1297 (0.1371) loss: 0.8117 (0.8097) time: 0.1446 data: 0.0579 max mem: 9390 +Train: [82] [5100/6250] eta: 0:04:24 lr: 0.000010 grad: 0.1282 (0.1370) loss: 0.8077 (0.8097) time: 0.1717 data: 0.0536 max mem: 9390 +Train: [82] [5200/6250] eta: 0:04:00 lr: 0.000010 grad: 0.1338 (0.1370) loss: 0.8096 (0.8097) time: 0.1730 data: 0.0879 max mem: 9390 +Train: [82] [5300/6250] eta: 0:03:35 lr: 0.000010 grad: 0.1333 (0.1369) loss: 0.8124 (0.8098) time: 0.1487 data: 0.0681 max mem: 9390 +Train: [82] [5400/6250] eta: 0:03:12 lr: 0.000010 grad: 0.1348 (0.1368) loss: 0.8053 (0.8098) time: 0.1325 data: 0.0549 max mem: 9390 +Train: [82] [5500/6250] eta: 0:02:48 lr: 0.000010 grad: 0.1261 (0.1368) loss: 0.8144 (0.8099) time: 0.1668 data: 0.0921 max mem: 9390 +Train: [82] [5600/6250] eta: 0:02:25 lr: 0.000010 grad: 0.1325 (0.1367) loss: 0.8156 (0.8100) time: 0.1626 data: 0.0754 max mem: 9390 +Train: [82] [5700/6250] eta: 0:02:02 lr: 0.000010 grad: 0.1350 (0.1367) loss: 0.8106 (0.8100) time: 0.3006 data: 0.2081 max mem: 9390 +Train: [82] [5800/6250] eta: 0:01:41 lr: 0.000010 grad: 0.1323 (0.1366) loss: 0.8169 (0.8101) time: 0.3108 data: 0.2273 max mem: 9390 +Train: [82] [5900/6250] eta: 0:01:19 lr: 0.000010 grad: 0.1295 (0.1365) loss: 0.8138 (0.8102) time: 0.5509 data: 0.4387 max mem: 9390 +Train: [82] [6000/6250] eta: 0:00:56 lr: 0.000010 grad: 0.1247 (0.1365) loss: 0.8204 (0.8103) time: 0.1119 data: 0.0002 max mem: 9390 +Train: [82] [6100/6250] eta: 0:00:34 lr: 0.000010 grad: 0.1348 (0.1365) loss: 0.8135 (0.8103) time: 0.2025 data: 0.1073 max mem: 9390 +Train: [82] [6200/6250] eta: 0:00:11 lr: 0.000010 grad: 0.1256 (0.1365) loss: 0.8096 (0.8103) time: 0.1537 data: 0.0609 max mem: 9390 +Train: [82] [6249/6250] eta: 0:00:00 lr: 0.000010 grad: 0.1236 (0.1365) loss: 0.8139 (0.8103) time: 0.3173 data: 0.2265 max mem: 9390 +Train: [82] Total time: 0:24:11 (0.2322 s / it) +Averaged stats: lr: 0.000010 grad: 0.1236 (0.1365) loss: 0.8139 (0.8103) +Eval (hcp-train-subset): [82] [ 0/62] eta: 0:04:28 loss: 0.8293 (0.8293) time: 4.3374 data: 4.2695 max mem: 9390 +Eval (hcp-train-subset): [82] [61/62] eta: 0:00:00 loss: 0.8189 (0.8216) time: 0.1223 data: 0.0958 max mem: 9390 +Eval (hcp-train-subset): [82] Total time: 0:00:13 (0.2146 s / it) +Averaged stats (hcp-train-subset): loss: 0.8189 (0.8216) +Eval (hcp-val): [82] [ 0/62] eta: 0:05:20 loss: 0.8305 (0.8305) time: 5.1671 data: 5.1390 max mem: 9390 +Eval (hcp-val): [82] [61/62] eta: 0:00:00 loss: 0.8283 (0.8304) time: 0.1165 data: 0.0914 max mem: 9390 +Eval (hcp-val): [82] Total time: 0:00:13 (0.2219 s / it) +Averaged stats (hcp-val): loss: 0.8283 (0.8304) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +Train: [83] [ 0/6250] eta: 8:57:49 lr: 0.000010 grad: 0.0802 (0.0802) loss: 0.8447 (0.8447) time: 5.1632 data: 4.8324 max mem: 9390 +Train: [83] [ 100/6250] eta: 0:25:08 lr: 0.000010 grad: 0.1325 (0.1663) loss: 0.8178 (0.8178) time: 0.1718 data: 0.0744 max mem: 9390 +Train: [83] [ 200/6250] eta: 0:21:29 lr: 0.000010 grad: 0.1419 (0.1634) loss: 0.8029 (0.8118) time: 0.2055 data: 0.1158 max mem: 9390 +Train: [83] [ 300/6250] eta: 0:19:49 lr: 0.000010 grad: 0.1475 (0.1584) loss: 0.8018 (0.8096) time: 0.1482 data: 0.0485 max mem: 9390 +Train: [83] [ 400/6250] eta: 0:18:31 lr: 0.000010 grad: 0.1402 (0.1560) loss: 0.8093 (0.8079) time: 0.1391 data: 0.0467 max mem: 9390 +Train: [83] [ 500/6250] eta: 0:17:33 lr: 0.000010 grad: 0.1401 (0.1539) loss: 0.8113 (0.8068) time: 0.1261 data: 0.0251 max mem: 9390 +Train: [83] [ 600/6250] eta: 0:17:13 lr: 0.000010 grad: 0.1379 (0.1517) loss: 0.8101 (0.8067) time: 0.1790 data: 0.0915 max mem: 9390 +Train: [83] [ 700/6250] eta: 0:17:02 lr: 0.000009 grad: 0.1352 (0.1497) loss: 0.8120 (0.8070) time: 0.1661 data: 0.0749 max mem: 9390 +Train: [83] [ 800/6250] eta: 0:18:02 lr: 0.000009 grad: 0.1358 (0.1475) loss: 0.8127 (0.8077) time: 0.1565 data: 0.0348 max mem: 9390 +Train: [83] [ 900/6250] eta: 0:17:42 lr: 0.000009 grad: 0.1249 (0.1458) loss: 0.8186 (0.8086) time: 0.2026 data: 0.1185 max mem: 9390 +Train: [83] [1000/6250] eta: 0:17:06 lr: 0.000009 grad: 0.1395 (0.1453) loss: 0.8129 (0.8088) time: 0.1646 data: 0.0818 max mem: 9390 +Train: [83] [1100/6250] eta: 0:16:47 lr: 0.000009 grad: 0.1283 (0.1443) loss: 0.8197 (0.8092) time: 0.2856 data: 0.1961 max mem: 9390 +Train: [83] [1200/6250] eta: 0:16:17 lr: 0.000009 grad: 0.1317 (0.1439) loss: 0.8128 (0.8094) time: 0.1063 data: 0.0174 max mem: 9390 +Train: [83] [1300/6250] eta: 0:15:53 lr: 0.000009 grad: 0.1349 (0.1433) loss: 0.8153 (0.8095) time: 0.1298 data: 0.0544 max mem: 9390 +Train: [83] [1400/6250] eta: 0:15:21 lr: 0.000009 grad: 0.1335 (0.1429) loss: 0.8102 (0.8097) time: 0.1065 data: 0.0152 max mem: 9390 +Train: [83] [1500/6250] eta: 0:15:14 lr: 0.000009 grad: 0.1195 (0.1423) loss: 0.8164 (0.8100) time: 0.1085 data: 0.0005 max mem: 9390 +Train: [83] [1600/6250] eta: 0:15:49 lr: 0.000009 grad: 0.1278 (0.1420) loss: 0.8148 (0.8102) time: 0.1600 data: 0.0391 max mem: 9390 +Train: [83] [1700/6250] eta: 0:15:23 lr: 0.000009 grad: 0.1244 (0.1414) loss: 0.8162 (0.8105) time: 0.1877 data: 0.0542 max mem: 9390 +Train: [83] [1800/6250] eta: 0:15:14 lr: 0.000009 grad: 0.1341 (0.1409) loss: 0.8128 (0.8106) time: 0.1587 data: 0.0329 max mem: 9390 +Train: [83] [1900/6250] eta: 0:14:59 lr: 0.000009 grad: 0.1333 (0.1405) loss: 0.8163 (0.8108) time: 0.3842 data: 0.2361 max mem: 9390 +Train: [83] [2000/6250] eta: 0:14:30 lr: 0.000009 grad: 0.1264 (0.1401) loss: 0.8150 (0.8110) time: 0.1531 data: 0.0513 max mem: 9390 +Train: [83] [2100/6250] eta: 0:14:13 lr: 0.000009 grad: 0.1259 (0.1397) loss: 0.8099 (0.8112) time: 0.1968 data: 0.1067 max mem: 9390 +Train: [83] [2200/6250] eta: 0:13:51 lr: 0.000009 grad: 0.1294 (0.1395) loss: 0.8100 (0.8112) time: 0.0980 data: 0.0002 max mem: 9390 +Train: [83] [2300/6250] eta: 0:13:31 lr: 0.000009 grad: 0.1376 (0.1394) loss: 0.8017 (0.8112) time: 0.1691 data: 0.0792 max mem: 9390 +Train: [83] [2400/6250] eta: 0:13:13 lr: 0.000009 grad: 0.1361 (0.1393) loss: 0.8094 (0.8112) time: 0.3367 data: 0.2411 max mem: 9390 +Train: [83] [2500/6250] eta: 0:12:50 lr: 0.000009 grad: 0.1322 (0.1392) loss: 0.8080 (0.8111) time: 0.2165 data: 0.1309 max mem: 9390 +Train: [83] [2600/6250] eta: 0:12:55 lr: 0.000009 grad: 0.1232 (0.1391) loss: 0.8194 (0.8112) time: 0.5798 data: 0.4505 max mem: 9390 +Train: [83] [2700/6250] eta: 0:12:27 lr: 0.000009 grad: 0.1303 (0.1390) loss: 0.8150 (0.8112) time: 0.1106 data: 0.0002 max mem: 9390 +Train: [83] [2800/6250] eta: 0:12:05 lr: 0.000009 grad: 0.1350 (0.1389) loss: 0.8085 (0.8113) time: 0.1462 data: 0.0531 max mem: 9390 +Train: [83] [2900/6250] eta: 0:12:05 lr: 0.000009 grad: 0.1368 (0.1391) loss: 0.8150 (0.8113) time: 1.1112 data: 1.0131 max mem: 9390 +Train: [83] [3000/6250] eta: 0:11:37 lr: 0.000009 grad: 0.1460 (0.1391) loss: 0.8126 (0.8113) time: 0.1060 data: 0.0212 max mem: 9390 +Train: [83] [3100/6250] eta: 0:11:13 lr: 0.000009 grad: 0.1345 (0.1393) loss: 0.8122 (0.8112) time: 0.1683 data: 0.0826 max mem: 9390 +Train: [83] [3200/6250] eta: 0:10:53 lr: 0.000009 grad: 0.1400 (0.1393) loss: 0.8120 (0.8113) time: 0.3107 data: 0.2180 max mem: 9390 +Train: [83] [3300/6250] eta: 0:10:29 lr: 0.000009 grad: 0.1400 (0.1394) loss: 0.8089 (0.8114) time: 0.1688 data: 0.0538 max mem: 9390 +Train: [83] [3400/6250] eta: 0:10:12 lr: 0.000009 grad: 0.1453 (0.1395) loss: 0.8067 (0.8114) time: 0.1050 data: 0.0002 max mem: 9390 +Train: [83] [3500/6250] eta: 0:09:49 lr: 0.000009 grad: 0.1374 (0.1396) loss: 0.8148 (0.8114) time: 0.1357 data: 0.0003 max mem: 9390 +Train: [83] [3600/6250] eta: 0:09:35 lr: 0.000009 grad: 0.1342 (0.1395) loss: 0.8145 (0.8114) time: 0.3613 data: 0.2578 max mem: 9390 +Train: [83] [3700/6250] eta: 0:09:16 lr: 0.000009 grad: 0.1299 (0.1396) loss: 0.8114 (0.8115) time: 0.4356 data: 0.3418 max mem: 9390 +Train: [83] [3800/6250] eta: 0:08:58 lr: 0.000009 grad: 0.1325 (0.1396) loss: 0.8111 (0.8115) time: 0.1464 data: 0.0552 max mem: 9390 +Train: [83] [3900/6250] eta: 0:08:40 lr: 0.000009 grad: 0.1366 (0.1396) loss: 0.8123 (0.8115) time: 0.1123 data: 0.0003 max mem: 9390 +Train: [83] [4000/6250] eta: 0:08:29 lr: 0.000009 grad: 0.1346 (0.1395) loss: 0.8116 (0.8116) time: 0.3340 data: 0.2320 max mem: 9390 +Train: [83] [4100/6250] eta: 0:08:13 lr: 0.000009 grad: 0.1338 (0.1394) loss: 0.8140 (0.8117) time: 0.6536 data: 0.5520 max mem: 9390 +Train: [83] [4200/6250] eta: 0:07:54 lr: 0.000009 grad: 0.1396 (0.1394) loss: 0.8144 (0.8117) time: 0.1092 data: 0.0002 max mem: 9390 +Train: [83] [4300/6250] eta: 0:07:27 lr: 0.000009 grad: 0.1408 (0.1394) loss: 0.8114 (0.8117) time: 0.1940 data: 0.1081 max mem: 9390 +Train: [83] [4400/6250] eta: 0:07:05 lr: 0.000009 grad: 0.1410 (0.1393) loss: 0.8063 (0.8117) time: 0.1299 data: 0.0384 max mem: 9390 +Train: [83] [4500/6250] eta: 0:06:48 lr: 0.000009 grad: 0.1392 (0.1393) loss: 0.8176 (0.8117) time: 0.1293 data: 0.0426 max mem: 9390 +Train: [83] [4600/6250] eta: 0:06:22 lr: 0.000009 grad: 0.1354 (0.1393) loss: 0.8043 (0.8117) time: 0.1561 data: 0.0623 max mem: 9390 +Train: [83] [4700/6250] eta: 0:05:56 lr: 0.000009 grad: 0.1295 (0.1393) loss: 0.8130 (0.8117) time: 0.1343 data: 0.0487 max mem: 9390 +Train: [83] [4800/6250] eta: 0:05:31 lr: 0.000009 grad: 0.1360 (0.1393) loss: 0.8051 (0.8117) time: 0.1973 data: 0.1138 max mem: 9390 +Train: [83] [4900/6250] eta: 0:05:06 lr: 0.000009 grad: 0.1457 (0.1393) loss: 0.8053 (0.8117) time: 0.2034 data: 0.1196 max mem: 9390 +Train: [83] [5000/6250] eta: 0:04:42 lr: 0.000009 grad: 0.1288 (0.1393) loss: 0.8109 (0.8116) time: 0.1731 data: 0.0835 max mem: 9390 +Train: [83] [5100/6250] eta: 0:04:18 lr: 0.000009 grad: 0.1371 (0.1393) loss: 0.8045 (0.8116) time: 0.2051 data: 0.1245 max mem: 9390 +Train: [83] [5200/6250] eta: 0:03:54 lr: 0.000009 grad: 0.1332 (0.1393) loss: 0.8109 (0.8116) time: 0.1770 data: 0.0958 max mem: 9390 +Train: [83] [5300/6250] eta: 0:03:31 lr: 0.000009 grad: 0.1374 (0.1394) loss: 0.8042 (0.8115) time: 0.1248 data: 0.0393 max mem: 9390 +Train: [83] [5400/6250] eta: 0:03:08 lr: 0.000009 grad: 0.1440 (0.1394) loss: 0.8124 (0.8115) time: 0.1488 data: 0.0624 max mem: 9390 +Train: [83] [5500/6250] eta: 0:02:45 lr: 0.000009 grad: 0.1299 (0.1394) loss: 0.8062 (0.8114) time: 0.1425 data: 0.0498 max mem: 9390 +Train: [83] [5600/6250] eta: 0:02:22 lr: 0.000009 grad: 0.1380 (0.1394) loss: 0.8081 (0.8114) time: 0.1659 data: 0.0770 max mem: 9390 +Train: [83] [5700/6250] eta: 0:02:00 lr: 0.000009 grad: 0.1308 (0.1394) loss: 0.8141 (0.8114) time: 0.1662 data: 0.0854 max mem: 9390 +Train: [83] [5800/6250] eta: 0:01:37 lr: 0.000009 grad: 0.1390 (0.1394) loss: 0.8093 (0.8113) time: 0.1600 data: 0.0744 max mem: 9390 +Train: [83] [5900/6250] eta: 0:01:15 lr: 0.000009 grad: 0.1443 (0.1395) loss: 0.8047 (0.8112) time: 0.1316 data: 0.0439 max mem: 9390 +Train: [83] [6000/6250] eta: 0:00:53 lr: 0.000009 grad: 0.1351 (0.1396) loss: 0.8102 (0.8112) time: 0.1654 data: 0.0840 max mem: 9390 +Train: [83] [6100/6250] eta: 0:00:32 lr: 0.000009 grad: 0.1277 (0.1396) loss: 0.8134 (0.8111) time: 0.1408 data: 0.0534 max mem: 9390 +Train: [83] [6200/6250] eta: 0:00:10 lr: 0.000009 grad: 0.1417 (0.1396) loss: 0.8066 (0.8111) time: 0.1377 data: 0.0611 max mem: 9390 +Train: [83] [6249/6250] eta: 0:00:00 lr: 0.000009 grad: 0.1395 (0.1396) loss: 0.8110 (0.8110) time: 0.1165 data: 0.0339 max mem: 9390 +Train: [83] Total time: 0:22:16 (0.2138 s / it) +Averaged stats: lr: 0.000009 grad: 0.1395 (0.1396) loss: 0.8110 (0.8110) +Eval (hcp-train-subset): [83] [ 0/62] eta: 0:04:26 loss: 0.8341 (0.8341) time: 4.3022 data: 4.2733 max mem: 9390 +Eval (hcp-train-subset): [83] [61/62] eta: 0:00:00 loss: 0.8168 (0.8207) time: 0.1366 data: 0.1119 max mem: 9390 +Eval (hcp-train-subset): [83] Total time: 0:00:14 (0.2400 s / it) +Averaged stats (hcp-train-subset): loss: 0.8168 (0.8207) +Eval (hcp-val): [83] [ 0/62] eta: 0:03:25 loss: 0.8257 (0.8257) time: 3.3136 data: 3.2507 max mem: 9390 +Eval (hcp-val): [83] [61/62] eta: 0:00:00 loss: 0.8283 (0.8297) time: 0.1354 data: 0.1105 max mem: 9390 +Eval (hcp-val): [83] Total time: 0:00:12 (0.2047 s / it) +Averaged stats (hcp-val): loss: 0.8283 (0.8297) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +Train: [84] [ 0/6250] eta: 7:13:22 lr: 0.000009 grad: 0.1089 (0.1089) loss: 0.8572 (0.8572) time: 4.1604 data: 3.8805 max mem: 9390 +Train: [84] [ 100/6250] eta: 0:21:37 lr: 0.000009 grad: 0.1450 (0.1586) loss: 0.8160 (0.8134) time: 0.1878 data: 0.0827 max mem: 9390 +Train: [84] [ 200/6250] eta: 0:19:21 lr: 0.000009 grad: 0.1237 (0.1483) loss: 0.8242 (0.8135) time: 0.1642 data: 0.0722 max mem: 9390 +Train: [84] [ 300/6250] eta: 0:17:53 lr: 0.000008 grad: 0.1361 (0.1453) loss: 0.8139 (0.8141) time: 0.1626 data: 0.0749 max mem: 9390 +Train: [84] [ 400/6250] eta: 0:17:21 lr: 0.000008 grad: 0.1364 (0.1461) loss: 0.8078 (0.8121) time: 0.2042 data: 0.1125 max mem: 9390 +Train: [84] [ 500/6250] eta: 0:16:36 lr: 0.000008 grad: 0.1533 (0.1468) loss: 0.8007 (0.8108) time: 0.1543 data: 0.0432 max mem: 9390 +Train: [84] [ 600/6250] eta: 0:15:59 lr: 0.000008 grad: 0.1345 (0.1462) loss: 0.8082 (0.8104) time: 0.1305 data: 0.0374 max mem: 9390 +Train: [84] [ 700/6250] eta: 0:15:33 lr: 0.000008 grad: 0.1314 (0.1451) loss: 0.8050 (0.8106) time: 0.1857 data: 0.0974 max mem: 9390 +Train: [84] [ 800/6250] eta: 0:15:40 lr: 0.000008 grad: 0.1330 (0.1439) loss: 0.8154 (0.8110) time: 0.2827 data: 0.1902 max mem: 9390 +Train: [84] [ 900/6250] eta: 0:15:50 lr: 0.000008 grad: 0.1323 (0.1431) loss: 0.8114 (0.8114) time: 0.1952 data: 0.0981 max mem: 9390 +Train: [84] [1000/6250] eta: 0:16:09 lr: 0.000008 grad: 0.1233 (0.1422) loss: 0.8136 (0.8118) time: 0.3607 data: 0.2759 max mem: 9390 +Train: [84] [1100/6250] eta: 0:15:51 lr: 0.000008 grad: 0.1281 (0.1415) loss: 0.8171 (0.8120) time: 0.1297 data: 0.0390 max mem: 9390 +Train: [84] [1200/6250] eta: 0:15:33 lr: 0.000008 grad: 0.1380 (0.1409) loss: 0.8125 (0.8121) time: 0.1173 data: 0.0300 max mem: 9390 +Train: [84] [1300/6250] eta: 0:15:11 lr: 0.000008 grad: 0.1243 (0.1402) loss: 0.8114 (0.8122) time: 0.0892 data: 0.0003 max mem: 9390 +Train: [84] [1400/6250] eta: 0:14:46 lr: 0.000008 grad: 0.1279 (0.1397) loss: 0.8096 (0.8121) time: 0.1030 data: 0.0004 max mem: 9390 +Train: [84] [1500/6250] eta: 0:14:44 lr: 0.000008 grad: 0.1303 (0.1393) loss: 0.8135 (0.8122) time: 0.2631 data: 0.1790 max mem: 9390 +Train: [84] [1600/6250] eta: 0:14:33 lr: 0.000008 grad: 0.1292 (0.1388) loss: 0.8110 (0.8124) time: 0.2022 data: 0.1196 max mem: 9390 +Train: [84] [1700/6250] eta: 0:14:02 lr: 0.000008 grad: 0.1402 (0.1385) loss: 0.8073 (0.8124) time: 0.1113 data: 0.0224 max mem: 9390 +Train: [84] [1800/6250] eta: 0:13:41 lr: 0.000008 grad: 0.1307 (0.1382) loss: 0.8139 (0.8124) time: 0.1694 data: 0.0850 max mem: 9390 +Train: [84] [1900/6250] eta: 0:13:21 lr: 0.000008 grad: 0.1355 (0.1382) loss: 0.8087 (0.8124) time: 0.1495 data: 0.0560 max mem: 9390 +Train: [84] [2000/6250] eta: 0:13:12 lr: 0.000008 grad: 0.1274 (0.1380) loss: 0.8085 (0.8125) time: 0.4946 data: 0.3995 max mem: 9390 +Train: [84] [2100/6250] eta: 0:12:56 lr: 0.000008 grad: 0.1317 (0.1379) loss: 0.8133 (0.8125) time: 0.1722 data: 0.0850 max mem: 9390 +Train: [84] [2200/6250] eta: 0:12:36 lr: 0.000008 grad: 0.1202 (0.1376) loss: 0.8171 (0.8125) time: 0.1002 data: 0.0003 max mem: 9390 +Train: [84] [2300/6250] eta: 0:12:17 lr: 0.000008 grad: 0.1304 (0.1374) loss: 0.8068 (0.8124) time: 0.3019 data: 0.2146 max mem: 9390 +Train: [84] [2400/6250] eta: 0:11:52 lr: 0.000008 grad: 0.1356 (0.1374) loss: 0.8093 (0.8124) time: 0.1901 data: 0.1093 max mem: 9390 +Train: [84] [2500/6250] eta: 0:11:36 lr: 0.000008 grad: 0.1291 (0.1374) loss: 0.8130 (0.8123) time: 0.3512 data: 0.2359 max mem: 9390 +Train: [84] [2600/6250] eta: 0:11:12 lr: 0.000008 grad: 0.1287 (0.1373) loss: 0.8125 (0.8122) time: 0.1569 data: 0.0695 max mem: 9390 +Train: [84] [2700/6250] eta: 0:10:51 lr: 0.000008 grad: 0.1364 (0.1373) loss: 0.8061 (0.8121) time: 0.1409 data: 0.0488 max mem: 9390 +Train: [84] [2800/6250] eta: 0:10:37 lr: 0.000008 grad: 0.1323 (0.1371) loss: 0.8126 (0.8120) time: 0.1251 data: 0.0361 max mem: 9390 +Train: [84] [2900/6250] eta: 0:10:17 lr: 0.000008 grad: 0.1285 (0.1371) loss: 0.8125 (0.8119) time: 0.1335 data: 0.0368 max mem: 9390 +Train: [84] [3000/6250] eta: 0:09:56 lr: 0.000008 grad: 0.1304 (0.1370) loss: 0.8127 (0.8118) time: 0.2341 data: 0.1521 max mem: 9390 +Train: [84] [3100/6250] eta: 0:09:42 lr: 0.000008 grad: 0.1296 (0.1368) loss: 0.8128 (0.8118) time: 0.1402 data: 0.0514 max mem: 9390 +Train: [84] [3200/6250] eta: 0:09:22 lr: 0.000008 grad: 0.1382 (0.1368) loss: 0.8058 (0.8118) time: 0.1324 data: 0.0445 max mem: 9390 +Train: [84] [3300/6250] eta: 0:09:01 lr: 0.000008 grad: 0.1337 (0.1367) loss: 0.8143 (0.8118) time: 0.1398 data: 0.0556 max mem: 9390 +Train: [84] [3400/6250] eta: 0:08:43 lr: 0.000008 grad: 0.1322 (0.1367) loss: 0.8168 (0.8118) time: 0.2156 data: 0.1380 max mem: 9390 +Train: [84] [3500/6250] eta: 0:08:21 lr: 0.000008 grad: 0.1242 (0.1365) loss: 0.8090 (0.8118) time: 0.1352 data: 0.0533 max mem: 9390 +Train: [84] [3600/6250] eta: 0:08:00 lr: 0.000008 grad: 0.1382 (0.1364) loss: 0.8119 (0.8119) time: 0.1449 data: 0.0644 max mem: 9390 +Train: [84] [3700/6250] eta: 0:07:39 lr: 0.000008 grad: 0.1363 (0.1363) loss: 0.8152 (0.8120) time: 0.1625 data: 0.0859 max mem: 9390 +Train: [84] [3800/6250] eta: 0:07:19 lr: 0.000008 grad: 0.1267 (0.1363) loss: 0.8118 (0.8121) time: 0.1508 data: 0.0653 max mem: 9390 +Train: [84] [3900/6250] eta: 0:06:59 lr: 0.000008 grad: 0.1277 (0.1362) loss: 0.8151 (0.8121) time: 0.1446 data: 0.0596 max mem: 9390 +Train: [84] [4000/6250] eta: 0:06:41 lr: 0.000008 grad: 0.1351 (0.1362) loss: 0.8099 (0.8122) time: 0.1729 data: 0.0877 max mem: 9390 +Train: [84] [4100/6250] eta: 0:06:21 lr: 0.000008 grad: 0.1302 (0.1362) loss: 0.8144 (0.8122) time: 0.1406 data: 0.0592 max mem: 9390 +Train: [84] [4200/6250] eta: 0:06:02 lr: 0.000008 grad: 0.1284 (0.1362) loss: 0.8119 (0.8123) time: 0.1470 data: 0.0647 max mem: 9390 +Train: [84] [4300/6250] eta: 0:05:43 lr: 0.000008 grad: 0.1354 (0.1363) loss: 0.8105 (0.8122) time: 0.1477 data: 0.0644 max mem: 9390 +Train: [84] [4400/6250] eta: 0:05:24 lr: 0.000008 grad: 0.1409 (0.1363) loss: 0.8145 (0.8123) time: 0.1489 data: 0.0683 max mem: 9390 +Train: [84] [4500/6250] eta: 0:05:05 lr: 0.000008 grad: 0.1322 (0.1362) loss: 0.8075 (0.8123) time: 0.1344 data: 0.0511 max mem: 9390 +Train: [84] [4600/6250] eta: 0:04:47 lr: 0.000008 grad: 0.1379 (0.1362) loss: 0.8061 (0.8123) time: 0.1404 data: 0.0530 max mem: 9390 +Train: [84] [4700/6250] eta: 0:04:29 lr: 0.000008 grad: 0.1310 (0.1362) loss: 0.8186 (0.8123) time: 0.1683 data: 0.0822 max mem: 9390 +Train: [84] [4800/6250] eta: 0:04:11 lr: 0.000008 grad: 0.1402 (0.1362) loss: 0.8075 (0.8123) time: 0.1591 data: 0.0743 max mem: 9390 +Train: [84] [4900/6250] eta: 0:03:53 lr: 0.000008 grad: 0.1293 (0.1363) loss: 0.8130 (0.8123) time: 0.1599 data: 0.0613 max mem: 9390 +Train: [84] [5000/6250] eta: 0:03:35 lr: 0.000008 grad: 0.1406 (0.1363) loss: 0.8141 (0.8123) time: 0.1529 data: 0.0639 max mem: 9390 +Train: [84] [5100/6250] eta: 0:03:17 lr: 0.000008 grad: 0.1503 (0.1364) loss: 0.8057 (0.8123) time: 0.1367 data: 0.0384 max mem: 9390 +Train: [84] [5200/6250] eta: 0:02:59 lr: 0.000008 grad: 0.1348 (0.1365) loss: 0.8084 (0.8122) time: 0.1628 data: 0.0770 max mem: 9390 +Train: [84] [5300/6250] eta: 0:02:42 lr: 0.000008 grad: 0.1362 (0.1365) loss: 0.8168 (0.8122) time: 0.1136 data: 0.0256 max mem: 9390 +Train: [84] [5400/6250] eta: 0:02:24 lr: 0.000008 grad: 0.1418 (0.1366) loss: 0.8120 (0.8122) time: 0.1410 data: 0.0596 max mem: 9390 +Train: [84] [5500/6250] eta: 0:02:07 lr: 0.000008 grad: 0.1324 (0.1366) loss: 0.8146 (0.8122) time: 0.1379 data: 0.0545 max mem: 9390 +Train: [84] [5600/6250] eta: 0:01:49 lr: 0.000008 grad: 0.1311 (0.1367) loss: 0.8170 (0.8121) time: 0.1416 data: 0.0618 max mem: 9390 +Train: [84] [5700/6250] eta: 0:01:32 lr: 0.000008 grad: 0.1296 (0.1367) loss: 0.8151 (0.8122) time: 0.1477 data: 0.0557 max mem: 9390 +Train: [84] [5800/6250] eta: 0:01:15 lr: 0.000008 grad: 0.1404 (0.1367) loss: 0.8005 (0.8121) time: 0.1407 data: 0.0510 max mem: 9390 +Train: [84] [5900/6250] eta: 0:00:58 lr: 0.000008 grad: 0.1335 (0.1368) loss: 0.8098 (0.8122) time: 0.1458 data: 0.0603 max mem: 9390 +Train: [84] [6000/6250] eta: 0:00:41 lr: 0.000008 grad: 0.1395 (0.1368) loss: 0.8082 (0.8121) time: 0.1612 data: 0.0840 max mem: 9390 +Train: [84] [6100/6250] eta: 0:00:25 lr: 0.000008 grad: 0.1358 (0.1368) loss: 0.8153 (0.8121) time: 0.1268 data: 0.0392 max mem: 9390 +Train: [84] [6200/6250] eta: 0:00:08 lr: 0.000008 grad: 0.1283 (0.1368) loss: 0.8120 (0.8121) time: 0.1200 data: 0.0424 max mem: 9390 +Train: [84] [6249/6250] eta: 0:00:00 lr: 0.000008 grad: 0.1404 (0.1368) loss: 0.8141 (0.8121) time: 0.1384 data: 0.0611 max mem: 9390 +Train: [84] Total time: 0:17:29 (0.1680 s / it) +Averaged stats: lr: 0.000008 grad: 0.1404 (0.1368) loss: 0.8141 (0.8121) +Eval (hcp-train-subset): [84] [ 0/62] eta: 0:04:53 loss: 0.8306 (0.8306) time: 4.7360 data: 4.7088 max mem: 9390 +Eval (hcp-train-subset): [84] [61/62] eta: 0:00:00 loss: 0.8195 (0.8208) time: 0.1172 data: 0.0923 max mem: 9390 +Eval (hcp-train-subset): [84] Total time: 0:00:11 (0.1882 s / it) +Averaged stats (hcp-train-subset): loss: 0.8195 (0.8208) +Making plots (hcp-train-subset): example=39 +Eval (hcp-val): [84] [ 0/62] eta: 0:04:14 loss: 0.8247 (0.8247) time: 4.1070 data: 4.0768 max mem: 9390 +Eval (hcp-val): [84] [61/62] eta: 0:00:00 loss: 0.8282 (0.8295) time: 0.1402 data: 0.1136 max mem: 9390 +Eval (hcp-val): [84] Total time: 0:00:12 (0.2027 s / it) +Averaged stats (hcp-val): loss: 0.8282 (0.8295) +Making plots (hcp-val): example=55 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +Train: [85] [ 0/6250] eta: 9:52:42 lr: 0.000008 grad: 0.2134 (0.2134) loss: 0.8289 (0.8289) time: 5.6901 data: 5.5925 max mem: 9390 +Train: [85] [ 100/6250] eta: 0:21:26 lr: 0.000008 grad: 0.1405 (0.1713) loss: 0.8227 (0.8191) time: 0.1747 data: 0.0912 max mem: 9390 +Train: [85] [ 200/6250] eta: 0:18:36 lr: 0.000008 grad: 0.1935 (0.1698) loss: 0.8080 (0.8152) time: 0.1709 data: 0.0963 max mem: 9390 +Train: [85] [ 300/6250] eta: 0:17:05 lr: 0.000007 grad: 0.1341 (0.1623) loss: 0.8197 (0.8141) time: 0.1684 data: 0.0847 max mem: 9390 +Train: [85] [ 400/6250] eta: 0:16:24 lr: 0.000007 grad: 0.1427 (0.1587) loss: 0.8197 (0.8133) time: 0.1661 data: 0.0785 max mem: 9390 +Train: [85] [ 500/6250] eta: 0:15:39 lr: 0.000007 grad: 0.1318 (0.1557) loss: 0.8127 (0.8127) time: 0.1394 data: 0.0507 max mem: 9390 +Train: [85] [ 600/6250] eta: 0:15:23 lr: 0.000007 grad: 0.1374 (0.1533) loss: 0.8129 (0.8118) time: 0.1752 data: 0.0867 max mem: 9390 +Train: [85] [ 700/6250] eta: 0:15:02 lr: 0.000007 grad: 0.1410 (0.1516) loss: 0.7988 (0.8113) time: 0.1502 data: 0.0644 max mem: 9390 +Train: [85] [ 800/6250] eta: 0:14:53 lr: 0.000007 grad: 0.1533 (0.1512) loss: 0.8067 (0.8106) time: 0.1687 data: 0.0660 max mem: 9390 +Train: [85] [ 900/6250] eta: 0:14:52 lr: 0.000007 grad: 0.1348 (0.1504) loss: 0.8071 (0.8102) time: 0.2198 data: 0.1241 max mem: 9390 +Train: [85] [1000/6250] eta: 0:14:42 lr: 0.000007 grad: 0.1312 (0.1495) loss: 0.8171 (0.8101) time: 0.2568 data: 0.1351 max mem: 9390 +Train: [85] [1100/6250] eta: 0:14:43 lr: 0.000007 grad: 0.1317 (0.1489) loss: 0.8114 (0.8100) time: 0.1287 data: 0.0454 max mem: 9390 +Train: [85] [1200/6250] eta: 0:14:24 lr: 0.000007 grad: 0.1321 (0.1481) loss: 0.8111 (0.8100) time: 0.0931 data: 0.0149 max mem: 9390 +Train: [85] [1300/6250] eta: 0:14:09 lr: 0.000007 grad: 0.1324 (0.1475) loss: 0.8138 (0.8099) time: 0.1400 data: 0.0643 max mem: 9390 +Train: [85] [1400/6250] eta: 0:13:59 lr: 0.000007 grad: 0.1366 (0.1474) loss: 0.8068 (0.8097) time: 0.1165 data: 0.0211 max mem: 9390 +Train: [85] [1500/6250] eta: 0:13:45 lr: 0.000007 grad: 0.1399 (0.1468) loss: 0.8010 (0.8095) time: 0.1682 data: 0.0743 max mem: 9390 +Train: [85] [1600/6250] eta: 0:13:20 lr: 0.000007 grad: 0.1398 (0.1465) loss: 0.8143 (0.8095) time: 0.1441 data: 0.0588 max mem: 9390 +Train: [85] [1700/6250] eta: 0:13:07 lr: 0.000007 grad: 0.1315 (0.1461) loss: 0.8129 (0.8095) time: 0.2243 data: 0.1384 max mem: 9390 +Train: [85] [1800/6250] eta: 0:12:48 lr: 0.000007 grad: 0.1400 (0.1456) loss: 0.8140 (0.8095) time: 0.1700 data: 0.0720 max mem: 9390 +Train: [85] [1900/6250] eta: 0:12:34 lr: 0.000007 grad: 0.1441 (0.1454) loss: 0.8093 (0.8096) time: 0.0935 data: 0.0002 max mem: 9390 +Train: [85] [2000/6250] eta: 0:12:11 lr: 0.000007 grad: 0.1334 (0.1451) loss: 0.8098 (0.8096) time: 0.1641 data: 0.0789 max mem: 9390 +Train: [85] [2100/6250] eta: 0:11:54 lr: 0.000007 grad: 0.1286 (0.1446) loss: 0.8162 (0.8098) time: 0.1267 data: 0.0398 max mem: 9390 +Train: [85] [2200/6250] eta: 0:11:41 lr: 0.000007 grad: 0.1379 (0.1443) loss: 0.8086 (0.8099) time: 0.4153 data: 0.3220 max mem: 9390 +Train: [85] [2300/6250] eta: 0:11:17 lr: 0.000007 grad: 0.1247 (0.1439) loss: 0.8171 (0.8102) time: 0.1370 data: 0.0505 max mem: 9390 +Train: [85] [2400/6250] eta: 0:10:55 lr: 0.000007 grad: 0.1264 (0.1435) loss: 0.8048 (0.8103) time: 0.1455 data: 0.0596 max mem: 9390 +Train: [85] [2500/6250] eta: 0:10:41 lr: 0.000007 grad: 0.1318 (0.1431) loss: 0.8137 (0.8104) time: 0.1212 data: 0.0356 max mem: 9390 +Train: [85] [2600/6250] eta: 0:10:30 lr: 0.000007 grad: 0.1287 (0.1429) loss: 0.8174 (0.8105) time: 0.4661 data: 0.3233 max mem: 9390 +Train: [85] [2700/6250] eta: 0:10:11 lr: 0.000007 grad: 0.1333 (0.1425) loss: 0.8137 (0.8105) time: 0.1691 data: 0.0354 max mem: 9390 +Train: [85] [2800/6250] eta: 0:09:56 lr: 0.000007 grad: 0.1338 (0.1421) loss: 0.8118 (0.8106) time: 0.2809 data: 0.1972 max mem: 9390 +Train: [85] [2900/6250] eta: 0:09:43 lr: 0.000007 grad: 0.1310 (0.1418) loss: 0.8155 (0.8107) time: 0.3198 data: 0.2098 max mem: 9390 +Train: [85] [3000/6250] eta: 0:09:25 lr: 0.000007 grad: 0.1278 (0.1417) loss: 0.8120 (0.8108) time: 0.1801 data: 0.0887 max mem: 9390 +Train: [85] [3100/6250] eta: 0:09:06 lr: 0.000007 grad: 0.1345 (0.1416) loss: 0.8109 (0.8108) time: 0.1378 data: 0.0592 max mem: 9390 +Train: [85] [3200/6250] eta: 0:08:48 lr: 0.000007 grad: 0.1429 (0.1416) loss: 0.8109 (0.8108) time: 0.1108 data: 0.0227 max mem: 9390 +Train: [85] [3300/6250] eta: 0:08:27 lr: 0.000007 grad: 0.1304 (0.1415) loss: 0.8076 (0.8107) time: 0.1249 data: 0.0382 max mem: 9390 +Train: [85] [3400/6250] eta: 0:08:09 lr: 0.000007 grad: 0.1391 (0.1415) loss: 0.8060 (0.8106) time: 0.1708 data: 0.0859 max mem: 9390 +Train: [85] [3500/6250] eta: 0:07:53 lr: 0.000007 grad: 0.1356 (0.1414) loss: 0.8035 (0.8106) time: 0.1867 data: 0.1060 max mem: 9390 +Train: [85] [3600/6250] eta: 0:07:39 lr: 0.000007 grad: 0.1367 (0.1414) loss: 0.8027 (0.8105) time: 0.1430 data: 0.0336 max mem: 9390 +Train: [85] [3700/6250] eta: 0:07:25 lr: 0.000007 grad: 0.1337 (0.1413) loss: 0.8101 (0.8105) time: 0.3103 data: 0.2303 max mem: 9390 +Train: [85] [3800/6250] eta: 0:07:07 lr: 0.000007 grad: 0.1330 (0.1413) loss: 0.8093 (0.8104) time: 0.2411 data: 0.1197 max mem: 9390 +Train: [85] [3900/6250] eta: 0:07:05 lr: 0.000007 grad: 0.1268 (0.1413) loss: 0.8112 (0.8103) time: 0.8981 data: 0.7911 max mem: 9390 +Train: [85] [4000/6250] eta: 0:06:51 lr: 0.000007 grad: 0.1319 (0.1412) loss: 0.8122 (0.8102) time: 0.0997 data: 0.0007 max mem: 9390 +Train: [85] [4100/6250] eta: 0:06:35 lr: 0.000007 grad: 0.1392 (0.1412) loss: 0.8112 (0.8102) time: 0.1823 data: 0.0973 max mem: 9390 +Train: [85] [4200/6250] eta: 0:06:16 lr: 0.000007 grad: 0.1457 (0.1413) loss: 0.8068 (0.8101) time: 0.2090 data: 0.1139 max mem: 9390 +Train: [85] [4300/6250] eta: 0:05:57 lr: 0.000007 grad: 0.1395 (0.1413) loss: 0.8031 (0.8100) time: 0.2018 data: 0.1216 max mem: 9390 +Train: [85] [4400/6250] eta: 0:05:39 lr: 0.000007 grad: 0.1399 (0.1413) loss: 0.8094 (0.8100) time: 0.1539 data: 0.0749 max mem: 9390 +Train: [85] [4500/6250] eta: 0:05:21 lr: 0.000007 grad: 0.1369 (0.1413) loss: 0.8061 (0.8100) time: 0.2503 data: 0.1542 max mem: 9390 +Train: [85] [4600/6250] eta: 0:05:06 lr: 0.000007 grad: 0.1331 (0.1412) loss: 0.8090 (0.8100) time: 0.1125 data: 0.0003 max mem: 9390 +Train: [85] [4700/6250] eta: 0:04:48 lr: 0.000007 grad: 0.1417 (0.1412) loss: 0.8101 (0.8099) time: 0.2239 data: 0.1233 max mem: 9390 +Train: [85] [4800/6250] eta: 0:04:31 lr: 0.000007 grad: 0.1363 (0.1413) loss: 0.8150 (0.8099) time: 0.1945 data: 0.1033 max mem: 9390 +Train: [85] [4900/6250] eta: 0:04:14 lr: 0.000007 grad: 0.1372 (0.1413) loss: 0.8110 (0.8099) time: 0.1442 data: 0.0373 max mem: 9390 +Train: [85] [5000/6250] eta: 0:03:58 lr: 0.000007 grad: 0.1358 (0.1413) loss: 0.8131 (0.8100) time: 0.1458 data: 0.0454 max mem: 9390 +Train: [85] [5100/6250] eta: 0:03:40 lr: 0.000007 grad: 0.1383 (0.1413) loss: 0.8099 (0.8099) time: 0.1024 data: 0.0002 max mem: 9390 +Train: [85] [5200/6250] eta: 0:03:22 lr: 0.000007 grad: 0.1320 (0.1412) loss: 0.8141 (0.8100) time: 0.0976 data: 0.0002 max mem: 9390 +Train: [85] [5300/6250] eta: 0:03:04 lr: 0.000007 grad: 0.1314 (0.1412) loss: 0.8110 (0.8100) time: 0.1079 data: 0.0017 max mem: 9390 +Train: [85] [5400/6250] eta: 0:02:46 lr: 0.000007 grad: 0.1351 (0.1411) loss: 0.8162 (0.8100) time: 0.1093 data: 0.0002 max mem: 9390 +Train: [85] [5500/6250] eta: 0:02:31 lr: 0.000007 grad: 0.1319 (0.1410) loss: 0.8090 (0.8101) time: 0.5542 data: 0.4350 max mem: 9390 +Train: [85] [5600/6250] eta: 0:02:14 lr: 0.000007 grad: 0.1312 (0.1409) loss: 0.8144 (0.8101) time: 0.1245 data: 0.0297 max mem: 9390 +Train: [85] [5700/6250] eta: 0:01:56 lr: 0.000007 grad: 0.1286 (0.1409) loss: 0.8134 (0.8101) time: 1.2094 data: 1.1095 max mem: 9390 +Train: [85] [5800/6250] eta: 0:01:37 lr: 0.000007 grad: 0.1356 (0.1409) loss: 0.8106 (0.8101) time: 1.3500 data: 1.2665 max mem: 9390 +Train: [85] [5900/6250] eta: 0:01:15 lr: 0.000007 grad: 0.1356 (0.1409) loss: 0.8127 (0.8102) time: 0.1685 data: 0.0843 max mem: 9390 +Train: [85] [6000/6250] eta: 0:00:53 lr: 0.000007 grad: 0.1318 (0.1408) loss: 0.8143 (0.8102) time: 0.1336 data: 0.0529 max mem: 9390 +Train: [85] [6100/6250] eta: 0:00:32 lr: 0.000007 grad: 0.1371 (0.1408) loss: 0.8104 (0.8103) time: 0.1367 data: 0.0545 max mem: 9390 +Train: [85] [6200/6250] eta: 0:00:10 lr: 0.000007 grad: 0.1345 (0.1408) loss: 0.8151 (0.8103) time: 0.1043 data: 0.0134 max mem: 9390 +Train: [85] [6249/6250] eta: 0:00:00 lr: 0.000007 grad: 0.1380 (0.1408) loss: 0.8168 (0.8104) time: 0.1072 data: 0.0006 max mem: 9390 +Train: [85] Total time: 0:22:10 (0.2129 s / it) +Averaged stats: lr: 0.000007 grad: 0.1380 (0.1408) loss: 0.8168 (0.8104) +Eval (hcp-train-subset): [85] [ 0/62] eta: 0:04:21 loss: 0.8261 (0.8261) time: 4.2117 data: 4.1532 max mem: 9390 +Eval (hcp-train-subset): [85] [61/62] eta: 0:00:00 loss: 0.8177 (0.8197) time: 0.1264 data: 0.1015 max mem: 9390 +Eval (hcp-train-subset): [85] Total time: 0:00:12 (0.2093 s / it) +Averaged stats (hcp-train-subset): loss: 0.8177 (0.8197) +Eval (hcp-val): [85] [ 0/62] eta: 0:04:55 loss: 0.8259 (0.8259) time: 4.7633 data: 4.7348 max mem: 9390 +Eval (hcp-val): [85] [61/62] eta: 0:00:00 loss: 0.8265 (0.8296) time: 0.1423 data: 0.1100 max mem: 9390 +Eval (hcp-val): [85] Total time: 0:00:13 (0.2144 s / it) +Averaged stats (hcp-val): loss: 0.8265 (0.8296) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +Train: [86] [ 0/6250] eta: 7:09:02 lr: 0.000007 grad: 0.0717 (0.0717) loss: 0.8493 (0.8493) time: 4.1189 data: 3.7880 max mem: 9390 +Train: [86] [ 100/6250] eta: 0:25:10 lr: 0.000007 grad: 0.1528 (0.1735) loss: 0.8121 (0.8182) time: 0.1498 data: 0.0711 max mem: 9390 +Train: [86] [ 200/6250] eta: 0:20:50 lr: 0.000007 grad: 0.1643 (0.1690) loss: 0.8062 (0.8149) time: 0.1686 data: 0.0890 max mem: 9390 +Train: [86] [ 300/6250] eta: 0:19:21 lr: 0.000007 grad: 0.1494 (0.1663) loss: 0.8053 (0.8126) time: 0.1764 data: 0.0904 max mem: 9390 +Train: [86] [ 400/6250] eta: 0:18:16 lr: 0.000007 grad: 0.1568 (0.1639) loss: 0.8005 (0.8110) time: 0.1542 data: 0.0637 max mem: 9390 +Train: [86] [ 500/6250] eta: 0:17:43 lr: 0.000007 grad: 0.1393 (0.1623) loss: 0.8101 (0.8099) time: 0.1750 data: 0.0596 max mem: 9390 +Train: [86] [ 600/6250] eta: 0:17:34 lr: 0.000006 grad: 0.1490 (0.1599) loss: 0.8096 (0.8092) time: 0.2645 data: 0.1592 max mem: 9390 +Train: [86] [ 700/6250] eta: 0:18:12 lr: 0.000006 grad: 0.1439 (0.1588) loss: 0.8042 (0.8088) time: 0.1946 data: 0.0570 max mem: 9390 +Train: [86] [ 800/6250] eta: 0:20:10 lr: 0.000006 grad: 0.1501 (0.1576) loss: 0.8068 (0.8084) time: 0.1642 data: 0.0719 max mem: 9390 +Train: [86] [ 900/6250] eta: 0:20:33 lr: 0.000006 grad: 0.1394 (0.1564) loss: 0.8058 (0.8081) time: 0.2917 data: 0.2038 max mem: 9390 +Train: [86] [1000/6250] eta: 0:19:48 lr: 0.000006 grad: 0.1470 (0.1552) loss: 0.8037 (0.8078) time: 0.1133 data: 0.0191 max mem: 9390 +Train: [86] [1100/6250] eta: 0:19:26 lr: 0.000006 grad: 0.1352 (0.1540) loss: 0.8083 (0.8076) time: 0.3160 data: 0.2295 max mem: 9390 +Train: [86] [1200/6250] eta: 0:20:16 lr: 0.000006 grad: 0.1400 (0.1529) loss: 0.8048 (0.8076) time: 0.6547 data: 0.5691 max mem: 9390 +Train: [86] [1300/6250] eta: 0:19:45 lr: 0.000006 grad: 0.1399 (0.1519) loss: 0.8001 (0.8075) time: 0.3271 data: 0.1947 max mem: 9390 +Train: [86] [1400/6250] eta: 0:19:02 lr: 0.000006 grad: 0.1413 (0.1512) loss: 0.8035 (0.8072) time: 0.0896 data: 0.0002 max mem: 9390 +Train: [86] [1500/6250] eta: 0:18:47 lr: 0.000006 grad: 0.1413 (0.1505) loss: 0.8097 (0.8071) time: 0.0968 data: 0.0002 max mem: 9390 +Train: [86] [1600/6250] eta: 0:18:20 lr: 0.000006 grad: 0.1354 (0.1502) loss: 0.8088 (0.8071) time: 0.2445 data: 0.1454 max mem: 9390 +Train: [86] [1700/6250] eta: 0:18:34 lr: 0.000006 grad: 0.1388 (0.1497) loss: 0.8055 (0.8070) time: 0.7876 data: 0.6895 max mem: 9390 +Train: [86] [1800/6250] eta: 0:18:07 lr: 0.000006 grad: 0.1416 (0.1493) loss: 0.8063 (0.8070) time: 0.1065 data: 0.0002 max mem: 9390 +Train: [86] [1900/6250] eta: 0:18:06 lr: 0.000006 grad: 0.1345 (0.1489) loss: 0.8109 (0.8069) time: 0.4864 data: 0.3886 max mem: 9390 +Train: [86] [2000/6250] eta: 0:17:34 lr: 0.000006 grad: 0.1412 (0.1486) loss: 0.8074 (0.8070) time: 0.3327 data: 0.2436 max mem: 9390 +Train: [86] [2100/6250] eta: 0:17:01 lr: 0.000006 grad: 0.1379 (0.1482) loss: 0.8060 (0.8070) time: 0.2152 data: 0.1094 max mem: 9390 +Train: [86] [2200/6250] eta: 0:16:52 lr: 0.000006 grad: 0.1355 (0.1477) loss: 0.8060 (0.8072) time: 0.2552 data: 0.1491 max mem: 9390 +Train: [86] [2300/6250] eta: 0:16:29 lr: 0.000006 grad: 0.1358 (0.1473) loss: 0.8083 (0.8073) time: 0.1138 data: 0.0155 max mem: 9390 +Train: [86] [2400/6250] eta: 0:16:14 lr: 0.000006 grad: 0.1328 (0.1470) loss: 0.8083 (0.8075) time: 0.3149 data: 0.2301 max mem: 9390 +Train: [86] [2500/6250] eta: 0:16:10 lr: 0.000006 grad: 0.1408 (0.1466) loss: 0.8104 (0.8076) time: 0.3953 data: 0.3047 max mem: 9390 +Train: [86] [2600/6250] eta: 0:15:40 lr: 0.000006 grad: 0.1280 (0.1463) loss: 0.8123 (0.8076) time: 0.1850 data: 0.0935 max mem: 9390 +Train: [86] [2700/6250] eta: 0:15:05 lr: 0.000006 grad: 0.1392 (0.1460) loss: 0.8111 (0.8077) time: 0.1872 data: 0.0511 max mem: 9390 +pretraining fmri mae +start: 2026-04-01 15:51:38 +cwd: /data/connor/fmri-fm +sha: 7f4cedc35609f6857314e0d1ea6657523f17ddeb, status: has uncommitted changes, branch: dev/clane9 +config: +name: input_space_v3/flat_lr1e-3_3/pretrain +notes: input_space ablation v3 flat_lr1e-3_3; use tube masking and on-disk data (input_space=flat + base_lr=1e-3 seed=5403) +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain +input_space: flat +patch_size: 16 +num_frames: 16 +t_patch_size: 4 +mask_ratio: 0.9 +pred_mask_ratio: null +masking: tube +masking_kwargs: {} +mask_patch_size: null +model: mae_vit_base +model_kwargs: + decoding: attn + pos_embed: sep + target_norm: null + pca_norm_nc: 2 + t_pred_stride: 2 + no_decode_pos: true + mask_drop_scale: false + pred_edge_pad: 0 + gauss_sigma: null + class_token: true + reg_tokens: 0 + no_embed_class: true + head_init_scale: 0.0 + decoder_depth: 4 + drop_path_rate: 0.0 +datasets: + hcp-train: + type: wds + url: /data/fmri-datasets/pretrain/hcpya-all.${input_space}.wds/hcpya-all-${input_space}-{00000..01799}.tar + clipping: random + clipping_kwargs: + oversample: 4.0 + shuffle: true + buffer_size: 2000 + samples_per_epoch: 200000 + hcp-train-subset: + type: arrow + root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/validation + split_range: + - 0 + - 2000 + shuffle: false + hcp-val: + type: arrow + root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/test + split_range: + - 0 + - 2000 + shuffle: false +train_dataset: hcp-train +eval_datasets: +- hcp-train-subset +- hcp-val +val_dataset: null +clip_vmax: 3.0 +normalize: frame +tr_scale: null +crop_scale: null +crop_aspect: null +gray_jitter: null +num_workers: 16 +epochs: 100 +batch_size: 32 +accum_iter: 1 +base_lr: 0.001 +min_lr: 0.0 +warmup_epochs: 5 +weight_decay: 0.05 +betas: +- 0.9 +- 0.95 +clip_grad: 1.0 +amp: true +amp_dtype: float16 +ckpt: null +resume: true +auto_resume: true +start_epoch: 0 +max_checkpoints: 0 +checkpoint_period: null +plot_period: 5 +device: cuda +presend_cuda: false +seed: 5403 +debug: false +wandb: true +wandb_entity: null +wandb_project: fMRI-foundation-model +rank: 0 +world_size: 1 +gpu: 0 +distributed: true +dist_backend: nccl +in_chans: 1 +img_size: +- 224 +- 560 + +train transform: +Compose( + ToTensor() + TemporalCenterCrop(num_frames=16) + Normalize(mode='frame') + Clip(vmax=3.0) + FlatUnmask((224, 560)) +) +val transform: +Compose( + ToTensor() + TemporalCenterCrop(num_frames=16) + Normalize(mode='frame') + Clip(vmax=3.0) + FlatUnmask((224, 560)) +) +mask generator: +TubeMasking( + mask_ratio=0.9 + (patchify): Patchify2D((224, 560), (16, 16), in_chans=1) +) +loading dataset: hcp-train + +type: wds +url: /data/fmri-datasets/pretrain/hcpya-all.${input_space}.wds/hcpya-all-${input_space}-{00000..01799}.tar +clipping: random +clipping_kwargs: + oversample: 4.0 +shuffle: true +buffer_size: 2000 +samples_per_epoch: 200000 + +loading dataset: hcp-train-subset + +type: arrow +root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/validation +split_range: +- 0 +- 2000 +shuffle: false + +split indices: [899, 472, 767, 116, 1265, 1852, 300, 1335, 361, 1560] +loading dataset: hcp-val + +type: arrow +root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/test +split_range: +- 0 +- 2000 +shuffle: false + +split indices: [1075, 1189, 738, 1350, 965, 1964, 1367, 1183, 1619, 1407] +model: +MaskedAutoencoderViT( + decoding=attn, t_pred_stride=2, pred_edge_pad=0, no_decode_pos=True + (encoder): MaskedEncoder( + class_token=True, reg_tokens=0, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) + (pred_patchify): StridedPatchify3D((16, 224, 560), (2, 16, 16), in_chans=1, t_stride=2) + (decoder): MaskedDecoder( + cross_decode=False, class_token=True, no_embed_class=True + (pos_embed): SeparablePosEmbed(512, (4, 14, 35)) + (proj): Linear(in_features=768, out_features=512, bias=True) + (blocks): ModuleList( + (0-3): 4 x Block( + (norm1): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=16 + (q): Linear(in_features=512, out_features=512, bias=True) + (k): Linear(in_features=512, out_features=512, bias=True) + (v): Linear(in_features=512, out_features=512, bias=True) + (proj): Linear(in_features=512, out_features=512, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=512, out_features=2048, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=2048, out_features=512, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (head): Linear(in_features=512, out_features=512, bias=True) + ) +) +num params: 99.7M +total batch size: 32 = 32 bs per gpu x 1 accum x 1 gpus +lr: 1.25e-04 = 1.00e-03 x 32 / 256 +full schedule: epochs = 100 (steps = 625000) +warmup: epochs = 5 (steps = 31250) +loaded model state from checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +loaded optimizer state, resuming training from 86 +start training for 100 epochs +Train: [86] [ 0/6250] eta: 10:46:54 lr: 0.000007 grad: 0.2432 (0.2432) loss: 0.8316 (0.8316) time: 6.2103 data: 4.5412 max mem: 9353 +Train: [86] [ 100/6250] eta: 0:22:30 lr: 0.000007 grad: 0.1568 (0.1854) loss: 0.8135 (0.8135) time: 0.1481 data: 0.0620 max mem: 9390 +Train: [86] [ 200/6250] eta: 0:18:44 lr: 0.000007 grad: 0.1383 (0.1724) loss: 0.8221 (0.8124) time: 0.1418 data: 0.0579 max mem: 9390 +Train: [86] [ 300/6250] eta: 0:17:10 lr: 0.000007 grad: 0.1376 (0.1656) loss: 0.8087 (0.8115) time: 0.1581 data: 0.0688 max mem: 9390 +Train: [86] [ 400/6250] eta: 0:16:09 lr: 0.000007 grad: 0.1338 (0.1595) loss: 0.8089 (0.8112) time: 0.1545 data: 0.0730 max mem: 9390 +Train: [86] [ 500/6250] eta: 0:15:23 lr: 0.000007 grad: 0.1387 (0.1562) loss: 0.8145 (0.8115) time: 0.1469 data: 0.0602 max mem: 9390 +Train: [86] [ 600/6250] eta: 0:15:01 lr: 0.000006 grad: 0.1412 (0.1537) loss: 0.8113 (0.8116) time: 0.1820 data: 0.0886 max mem: 9390 +Train: [86] [ 700/6250] eta: 0:14:44 lr: 0.000006 grad: 0.1431 (0.1525) loss: 0.8041 (0.8110) time: 0.1635 data: 0.0720 max mem: 9390 +Train: [86] [ 800/6250] eta: 0:14:29 lr: 0.000006 grad: 0.1376 (0.1511) loss: 0.8052 (0.8106) time: 0.1893 data: 0.1098 max mem: 9390 +Train: [86] [ 900/6250] eta: 0:14:11 lr: 0.000006 grad: 0.1384 (0.1501) loss: 0.8054 (0.8103) time: 0.1830 data: 0.1049 max mem: 9390 +Train: [86] [1000/6250] eta: 0:13:51 lr: 0.000006 grad: 0.1339 (0.1497) loss: 0.8131 (0.8101) time: 0.1606 data: 0.0741 max mem: 9390 +Train: [86] [1100/6250] eta: 0:13:32 lr: 0.000006 grad: 0.1408 (0.1490) loss: 0.7988 (0.8097) time: 0.1568 data: 0.0753 max mem: 9390 +Train: [86] [1200/6250] eta: 0:13:16 lr: 0.000006 grad: 0.1468 (0.1485) loss: 0.8066 (0.8095) time: 0.1751 data: 0.0954 max mem: 9390 +Train: [86] [1300/6250] eta: 0:12:57 lr: 0.000006 grad: 0.1342 (0.1478) loss: 0.8113 (0.8094) time: 0.1283 data: 0.0464 max mem: 9390 +Train: [86] [1400/6250] eta: 0:12:41 lr: 0.000006 grad: 0.1350 (0.1473) loss: 0.8017 (0.8093) time: 0.1464 data: 0.0677 max mem: 9390 +Train: [86] [1500/6250] eta: 0:12:23 lr: 0.000006 grad: 0.1347 (0.1470) loss: 0.8071 (0.8092) time: 0.1549 data: 0.0717 max mem: 9390 +Train: [86] [1600/6250] eta: 0:12:06 lr: 0.000006 grad: 0.1339 (0.1465) loss: 0.8076 (0.8092) time: 0.1496 data: 0.0622 max mem: 9390 +Train: [86] [1700/6250] eta: 0:11:47 lr: 0.000006 grad: 0.1376 (0.1463) loss: 0.8071 (0.8092) time: 0.1488 data: 0.0703 max mem: 9390 +Train: [86] [1800/6250] eta: 0:11:29 lr: 0.000006 grad: 0.1333 (0.1459) loss: 0.8039 (0.8092) time: 0.1536 data: 0.0691 max mem: 9390 +Train: [86] [1900/6250] eta: 0:11:10 lr: 0.000006 grad: 0.1335 (0.1455) loss: 0.8077 (0.8092) time: 0.1257 data: 0.0408 max mem: 9390 +Train: [86] [2000/6250] eta: 0:10:53 lr: 0.000006 grad: 0.1353 (0.1450) loss: 0.8102 (0.8093) time: 0.1302 data: 0.0433 max mem: 9390 +Train: [86] [2100/6250] eta: 0:10:59 lr: 0.000006 grad: 0.1246 (0.1448) loss: 0.8126 (0.8093) time: 0.4061 data: 0.3315 max mem: 9390 +Train: [86] [2200/6250] eta: 0:10:58 lr: 0.000006 grad: 0.1378 (0.1447) loss: 0.8148 (0.8094) time: 0.3044 data: 0.2100 max mem: 9390 +Train: [86] [2300/6250] eta: 0:10:44 lr: 0.000006 grad: 0.1349 (0.1444) loss: 0.8091 (0.8095) time: 0.1887 data: 0.1001 max mem: 9390 +Train: [86] [2400/6250] eta: 0:10:31 lr: 0.000006 grad: 0.1390 (0.1441) loss: 0.8092 (0.8097) time: 0.1995 data: 0.1084 max mem: 9390 +Train: [86] [2500/6250] eta: 0:10:15 lr: 0.000006 grad: 0.1401 (0.1439) loss: 0.8106 (0.8098) time: 0.1622 data: 0.0663 max mem: 9390 +Train: [86] [2600/6250] eta: 0:10:01 lr: 0.000006 grad: 0.1426 (0.1438) loss: 0.8155 (0.8100) time: 0.1788 data: 0.0856 max mem: 9390 +Train: [86] [2700/6250] eta: 0:09:45 lr: 0.000006 grad: 0.1455 (0.1435) loss: 0.8024 (0.8100) time: 0.1519 data: 0.0702 max mem: 9390 +Train: [86] [2800/6250] eta: 0:09:30 lr: 0.000006 grad: 0.1353 (0.1433) loss: 0.8087 (0.8101) time: 0.1766 data: 0.0833 max mem: 9390 +Train: [86] [2900/6250] eta: 0:09:14 lr: 0.000006 grad: 0.1344 (0.1432) loss: 0.8128 (0.8102) time: 0.1676 data: 0.0794 max mem: 9390 +Train: [86] [3000/6250] eta: 0:08:59 lr: 0.000006 grad: 0.1302 (0.1430) loss: 0.8189 (0.8102) time: 0.1652 data: 0.0639 max mem: 9390 +Train: [86] [3100/6250] eta: 0:08:43 lr: 0.000006 grad: 0.1357 (0.1429) loss: 0.8109 (0.8103) time: 0.1837 data: 0.0972 max mem: 9390 +Train: [86] [3200/6250] eta: 0:08:27 lr: 0.000006 grad: 0.1369 (0.1429) loss: 0.8087 (0.8104) time: 0.1520 data: 0.0709 max mem: 9390 +Train: [86] [3300/6250] eta: 0:08:11 lr: 0.000006 grad: 0.1405 (0.1426) loss: 0.8128 (0.8105) time: 0.1614 data: 0.0718 max mem: 9390 +Train: [86] [3400/6250] eta: 0:07:55 lr: 0.000006 grad: 0.1388 (0.1425) loss: 0.8168 (0.8106) time: 0.1594 data: 0.0636 max mem: 9390 +Train: [86] [3500/6250] eta: 0:07:39 lr: 0.000006 grad: 0.1321 (0.1425) loss: 0.8059 (0.8105) time: 0.1759 data: 0.0905 max mem: 9390 +Train: [86] [3600/6250] eta: 0:07:23 lr: 0.000006 grad: 0.1401 (0.1423) loss: 0.8087 (0.8106) time: 0.1614 data: 0.0652 max mem: 9390 +Train: [86] [3700/6250] eta: 0:07:06 lr: 0.000006 grad: 0.1427 (0.1422) loss: 0.8156 (0.8107) time: 0.1498 data: 0.0541 max mem: 9390 +Train: [86] [3800/6250] eta: 0:06:50 lr: 0.000006 grad: 0.1369 (0.1422) loss: 0.8154 (0.8107) time: 0.1552 data: 0.0637 max mem: 9390 +Train: [86] [3900/6250] eta: 0:06:34 lr: 0.000006 grad: 0.1324 (0.1420) loss: 0.8111 (0.8107) time: 0.2043 data: 0.1128 max mem: 9390 +Train: [86] [4000/6250] eta: 0:06:17 lr: 0.000006 grad: 0.1333 (0.1420) loss: 0.8070 (0.8106) time: 0.1329 data: 0.0496 max mem: 9390 +Train: [86] [4100/6250] eta: 0:06:00 lr: 0.000006 grad: 0.1310 (0.1418) loss: 0.8050 (0.8106) time: 0.1785 data: 0.0891 max mem: 9390 +Train: [86] [4200/6250] eta: 0:05:44 lr: 0.000006 grad: 0.1400 (0.1418) loss: 0.8125 (0.8106) time: 0.1765 data: 0.0922 max mem: 9390 +Train: [86] [4300/6250] eta: 0:05:27 lr: 0.000006 grad: 0.1392 (0.1418) loss: 0.8161 (0.8106) time: 0.1425 data: 0.0493 max mem: 9390 +Train: [86] [4400/6250] eta: 0:05:10 lr: 0.000006 grad: 0.1294 (0.1417) loss: 0.8138 (0.8107) time: 0.1836 data: 0.0961 max mem: 9390 +Train: [86] [4500/6250] eta: 0:04:54 lr: 0.000006 grad: 0.1347 (0.1416) loss: 0.8104 (0.8107) time: 0.1916 data: 0.1016 max mem: 9390 +Train: [86] [4600/6250] eta: 0:04:37 lr: 0.000006 grad: 0.1406 (0.1416) loss: 0.8135 (0.8108) time: 0.1588 data: 0.0723 max mem: 9390 +Train: [86] [4700/6250] eta: 0:04:21 lr: 0.000006 grad: 0.1310 (0.1415) loss: 0.8126 (0.8108) time: 0.2019 data: 0.1228 max mem: 9390 +Train: [86] [4800/6250] eta: 0:04:04 lr: 0.000006 grad: 0.1361 (0.1414) loss: 0.8100 (0.8109) time: 0.2069 data: 0.1172 max mem: 9390 +Train: [86] [4900/6250] eta: 0:03:47 lr: 0.000006 grad: 0.1337 (0.1414) loss: 0.8141 (0.8109) time: 0.1873 data: 0.0970 max mem: 9390 +Train: [86] [5000/6250] eta: 0:03:30 lr: 0.000006 grad: 0.1365 (0.1414) loss: 0.8109 (0.8109) time: 0.1989 data: 0.0972 max mem: 9390 +Train: [86] [5100/6250] eta: 0:03:14 lr: 0.000006 grad: 0.1322 (0.1413) loss: 0.8100 (0.8109) time: 0.1946 data: 0.1015 max mem: 9390 +Train: [86] [5200/6250] eta: 0:02:57 lr: 0.000006 grad: 0.1419 (0.1412) loss: 0.8162 (0.8109) time: 0.1797 data: 0.0876 max mem: 9390 +Train: [86] [5300/6250] eta: 0:02:40 lr: 0.000006 grad: 0.1386 (0.1412) loss: 0.8153 (0.8110) time: 0.1864 data: 0.0972 max mem: 9390 +Train: [86] [5400/6250] eta: 0:02:23 lr: 0.000006 grad: 0.1315 (0.1411) loss: 0.8181 (0.8111) time: 0.1861 data: 0.0969 max mem: 9390 +Train: [86] [5500/6250] eta: 0:02:06 lr: 0.000006 grad: 0.1330 (0.1411) loss: 0.8109 (0.8111) time: 0.1685 data: 0.0840 max mem: 9390 +Train: [86] [5600/6250] eta: 0:01:49 lr: 0.000006 grad: 0.1467 (0.1412) loss: 0.8049 (0.8110) time: 0.1666 data: 0.0787 max mem: 9390 +Train: [86] [5700/6250] eta: 0:01:33 lr: 0.000006 grad: 0.1406 (0.1412) loss: 0.8080 (0.8111) time: 0.1531 data: 0.0601 max mem: 9390 +Train: [86] [5800/6250] eta: 0:01:16 lr: 0.000006 grad: 0.1360 (0.1412) loss: 0.8131 (0.8110) time: 0.1629 data: 0.0692 max mem: 9390 +Train: [86] [5900/6250] eta: 0:00:59 lr: 0.000006 grad: 0.1363 (0.1412) loss: 0.8139 (0.8111) time: 0.1684 data: 0.0775 max mem: 9390 +Train: [86] [6000/6250] eta: 0:00:42 lr: 0.000006 grad: 0.1387 (0.1411) loss: 0.8127 (0.8111) time: 0.1685 data: 0.0824 max mem: 9390 +Train: [86] [6100/6250] eta: 0:00:25 lr: 0.000006 grad: 0.1333 (0.1411) loss: 0.8175 (0.8111) time: 0.2223 data: 0.1371 max mem: 9390 +Train: [86] [6200/6250] eta: 0:00:08 lr: 0.000006 grad: 0.1296 (0.1411) loss: 0.8116 (0.8111) time: 0.1972 data: 0.1115 max mem: 9390 +Train: [86] [6249/6250] eta: 0:00:00 lr: 0.000006 grad: 0.1422 (0.1411) loss: 0.8119 (0.8111) time: 0.1754 data: 0.0889 max mem: 9390 +Train: [86] Total time: 0:17:47 (0.1709 s / it) +Averaged stats: lr: 0.000006 grad: 0.1422 (0.1411) loss: 0.8119 (0.8111) +Eval (hcp-train-subset): [86] [ 0/62] eta: 0:05:30 loss: 0.8298 (0.8298) time: 5.3280 data: 5.2969 max mem: 9390 +Eval (hcp-train-subset): [86] [61/62] eta: 0:00:00 loss: 0.8160 (0.8192) time: 0.1264 data: 0.1013 max mem: 9390 +Eval (hcp-train-subset): [86] Total time: 0:00:14 (0.2362 s / it) +Averaged stats (hcp-train-subset): loss: 0.8160 (0.8192) +Eval (hcp-val): [86] [ 0/62] eta: 0:04:19 loss: 0.8283 (0.8283) time: 4.1884 data: 4.1251 max mem: 9390 +Eval (hcp-val): [86] [61/62] eta: 0:00:00 loss: 0.8292 (0.8297) time: 0.1529 data: 0.1179 max mem: 9390 +Eval (hcp-val): [86] Total time: 0:00:14 (0.2285 s / it) +Averaged stats (hcp-val): loss: 0.8292 (0.8297) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +Train: [87] [ 0/6250] eta: 11:41:07 lr: 0.000006 grad: 0.1780 (0.1780) loss: 0.7737 (0.7737) time: 6.7307 data: 6.6329 max mem: 9390 +Train: [87] [ 100/6250] eta: 0:23:39 lr: 0.000006 grad: 0.1452 (0.1686) loss: 0.8161 (0.8238) time: 0.1869 data: 0.0942 max mem: 9390 +Train: [87] [ 200/6250] eta: 0:20:48 lr: 0.000006 grad: 0.1526 (0.1634) loss: 0.8004 (0.8185) time: 0.2037 data: 0.0974 max mem: 9390 +Train: [87] [ 300/6250] eta: 0:18:58 lr: 0.000006 grad: 0.1469 (0.1600) loss: 0.8098 (0.8158) time: 0.1615 data: 0.0639 max mem: 9390 +Train: [87] [ 400/6250] eta: 0:18:07 lr: 0.000006 grad: 0.1239 (0.1550) loss: 0.8159 (0.8160) time: 0.1874 data: 0.0833 max mem: 9390 +Train: [87] [ 500/6250] eta: 0:17:27 lr: 0.000006 grad: 0.1259 (0.1514) loss: 0.8114 (0.8157) time: 0.1735 data: 0.0766 max mem: 9390 +Train: [87] [ 600/6250] eta: 0:16:52 lr: 0.000006 grad: 0.1277 (0.1494) loss: 0.8170 (0.8157) time: 0.1708 data: 0.0765 max mem: 9390 +Train: [87] [ 700/6250] eta: 0:16:34 lr: 0.000006 grad: 0.1321 (0.1477) loss: 0.8090 (0.8152) time: 0.1938 data: 0.0989 max mem: 9390 +Train: [87] [ 800/6250] eta: 0:16:24 lr: 0.000006 grad: 0.1348 (0.1470) loss: 0.8107 (0.8148) time: 0.1453 data: 0.0527 max mem: 9390 +Train: [87] [ 900/6250] eta: 0:16:06 lr: 0.000006 grad: 0.1328 (0.1463) loss: 0.8187 (0.8147) time: 0.1973 data: 0.0942 max mem: 9390 +Train: [87] [1000/6250] eta: 0:15:45 lr: 0.000006 grad: 0.1322 (0.1459) loss: 0.8205 (0.8146) time: 0.1691 data: 0.0663 max mem: 9390 +Train: [87] [1100/6250] eta: 0:15:22 lr: 0.000006 grad: 0.1418 (0.1454) loss: 0.8129 (0.8145) time: 0.1616 data: 0.0733 max mem: 9390 +Train: [87] [1200/6250] eta: 0:15:04 lr: 0.000006 grad: 0.1315 (0.1449) loss: 0.8130 (0.8142) time: 0.2033 data: 0.1094 max mem: 9390 +Train: [87] [1300/6250] eta: 0:14:46 lr: 0.000006 grad: 0.1393 (0.1443) loss: 0.8112 (0.8139) time: 0.1805 data: 0.0751 max mem: 9390 +Train: [87] [1400/6250] eta: 0:14:28 lr: 0.000005 grad: 0.1335 (0.1437) loss: 0.8141 (0.8136) time: 0.1903 data: 0.0985 max mem: 9390 +Train: [87] [1500/6250] eta: 0:14:09 lr: 0.000005 grad: 0.1366 (0.1433) loss: 0.8104 (0.8134) time: 0.1658 data: 0.0618 max mem: 9390 +Train: [87] [1600/6250] eta: 0:13:48 lr: 0.000005 grad: 0.1399 (0.1430) loss: 0.8133 (0.8132) time: 0.1683 data: 0.0659 max mem: 9390 +Train: [87] [1700/6250] eta: 0:13:30 lr: 0.000005 grad: 0.1360 (0.1427) loss: 0.8101 (0.8130) time: 0.1868 data: 0.0962 max mem: 9390 +Train: [87] [1800/6250] eta: 0:13:09 lr: 0.000005 grad: 0.1293 (0.1425) loss: 0.8162 (0.8128) time: 0.1725 data: 0.0787 max mem: 9390 +Train: [87] [1900/6250] eta: 0:12:51 lr: 0.000005 grad: 0.1430 (0.1425) loss: 0.8048 (0.8126) time: 0.1947 data: 0.1076 max mem: 9390 +Train: [87] [2000/6250] eta: 0:12:31 lr: 0.000005 grad: 0.1374 (0.1424) loss: 0.8161 (0.8125) time: 0.1724 data: 0.0798 max mem: 9390 +Train: [87] [2100/6250] eta: 0:12:12 lr: 0.000005 grad: 0.1431 (0.1425) loss: 0.8089 (0.8123) time: 0.1875 data: 0.1000 max mem: 9390 +Train: [87] [2200/6250] eta: 0:11:54 lr: 0.000005 grad: 0.1318 (0.1425) loss: 0.8153 (0.8122) time: 0.1569 data: 0.0621 max mem: 9390 +Train: [87] [2300/6250] eta: 0:11:35 lr: 0.000005 grad: 0.1357 (0.1426) loss: 0.8115 (0.8121) time: 0.1699 data: 0.0751 max mem: 9390 +Train: [87] [2400/6250] eta: 0:11:16 lr: 0.000005 grad: 0.1366 (0.1427) loss: 0.8100 (0.8119) time: 0.1616 data: 0.0734 max mem: 9390 +Train: [87] [2500/6250] eta: 0:10:59 lr: 0.000005 grad: 0.1413 (0.1427) loss: 0.8120 (0.8119) time: 0.1845 data: 0.0988 max mem: 9390 +Train: [87] [2600/6250] eta: 0:10:40 lr: 0.000005 grad: 0.1480 (0.1429) loss: 0.8092 (0.8117) time: 0.1500 data: 0.0547 max mem: 9390 +Train: [87] [2700/6250] eta: 0:10:23 lr: 0.000005 grad: 0.1426 (0.1432) loss: 0.8089 (0.8115) time: 0.1677 data: 0.0731 max mem: 9390 +Train: [87] [2800/6250] eta: 0:10:05 lr: 0.000005 grad: 0.1427 (0.1432) loss: 0.8138 (0.8114) time: 0.1796 data: 0.0850 max mem: 9390 +Train: [87] [2900/6250] eta: 0:09:46 lr: 0.000005 grad: 0.1448 (0.1433) loss: 0.8063 (0.8112) time: 0.1700 data: 0.0817 max mem: 9390 +Train: [87] [3000/6250] eta: 0:09:28 lr: 0.000005 grad: 0.1365 (0.1433) loss: 0.8120 (0.8112) time: 0.1624 data: 0.0689 max mem: 9390 +Train: [87] [3100/6250] eta: 0:09:11 lr: 0.000005 grad: 0.1361 (0.1434) loss: 0.8080 (0.8111) time: 0.1853 data: 0.1002 max mem: 9390 +Train: [87] [3200/6250] eta: 0:08:53 lr: 0.000005 grad: 0.1331 (0.1432) loss: 0.8106 (0.8110) time: 0.1682 data: 0.0795 max mem: 9390 +Train: [87] [3300/6250] eta: 0:08:36 lr: 0.000005 grad: 0.1347 (0.1431) loss: 0.8159 (0.8110) time: 0.1708 data: 0.0821 max mem: 9390 +Train: [87] [3400/6250] eta: 0:08:19 lr: 0.000005 grad: 0.1335 (0.1430) loss: 0.8096 (0.8110) time: 0.1879 data: 0.1047 max mem: 9390 +Train: [87] [3500/6250] eta: 0:08:01 lr: 0.000005 grad: 0.1545 (0.1431) loss: 0.8094 (0.8110) time: 0.1846 data: 0.0924 max mem: 9390 +Train: [87] [3600/6250] eta: 0:07:43 lr: 0.000005 grad: 0.1406 (0.1431) loss: 0.8119 (0.8109) time: 0.1800 data: 0.0843 max mem: 9390 +Train: [87] [3700/6250] eta: 0:07:26 lr: 0.000005 grad: 0.1417 (0.1432) loss: 0.8117 (0.8109) time: 0.1825 data: 0.0922 max mem: 9390 +Train: [87] [3800/6250] eta: 0:07:08 lr: 0.000005 grad: 0.1432 (0.1431) loss: 0.8026 (0.8108) time: 0.1543 data: 0.0668 max mem: 9390 +Train: [87] [3900/6250] eta: 0:06:51 lr: 0.000005 grad: 0.1332 (0.1430) loss: 0.8090 (0.8108) time: 0.1690 data: 0.0795 max mem: 9390 +Train: [87] [4000/6250] eta: 0:06:33 lr: 0.000005 grad: 0.1328 (0.1428) loss: 0.8152 (0.8108) time: 0.1782 data: 0.0924 max mem: 9390 +Train: [87] [4100/6250] eta: 0:06:16 lr: 0.000005 grad: 0.1351 (0.1428) loss: 0.8108 (0.8109) time: 0.1785 data: 0.0870 max mem: 9390 +Train: [87] [4200/6250] eta: 0:05:58 lr: 0.000005 grad: 0.1350 (0.1427) loss: 0.8144 (0.8109) time: 0.1976 data: 0.1094 max mem: 9390 +Train: [87] [4300/6250] eta: 0:05:41 lr: 0.000005 grad: 0.1359 (0.1427) loss: 0.8081 (0.8109) time: 0.1728 data: 0.0871 max mem: 9390 +Train: [87] [4400/6250] eta: 0:05:24 lr: 0.000005 grad: 0.1381 (0.1425) loss: 0.8104 (0.8109) time: 0.2215 data: 0.1347 max mem: 9390 +Train: [87] [4500/6250] eta: 0:05:06 lr: 0.000005 grad: 0.1328 (0.1425) loss: 0.8214 (0.8110) time: 0.1918 data: 0.1122 max mem: 9390 +pretraining fmri mae +start: 2026-04-02 10:08:31 +cwd: /data/connor/fmri-fm +sha: 7f4cedc35609f6857314e0d1ea6657523f17ddeb, status: has uncommitted changes, branch: dev/clane9 +config: +name: input_space_v3/flat_lr1e-3_3/pretrain +notes: input_space ablation v3 flat_lr1e-3_3; use tube masking and on-disk data (input_space=flat + base_lr=1e-3 seed=5403) +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain +input_space: flat +patch_size: 16 +num_frames: 16 +t_patch_size: 4 +mask_ratio: 0.9 +pred_mask_ratio: null +masking: tube +masking_kwargs: {} +mask_patch_size: null +model: mae_vit_base +model_kwargs: + decoding: attn + pos_embed: sep + target_norm: null + pca_norm_nc: 2 + t_pred_stride: 2 + no_decode_pos: true + mask_drop_scale: false + pred_edge_pad: 0 + gauss_sigma: null + class_token: true + reg_tokens: 0 + no_embed_class: true + head_init_scale: 0.0 + decoder_depth: 4 + drop_path_rate: 0.0 +datasets: + hcp-train: + type: wds + url: /data/fmri-datasets/pretrain/hcpya-all.${input_space}.wds/hcpya-all-${input_space}-{00000..01799}.tar + clipping: random + clipping_kwargs: + oversample: 4.0 + shuffle: true + buffer_size: 2000 + samples_per_epoch: 200000 + hcp-train-subset: + type: arrow + root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/validation + split_range: + - 0 + - 2000 + shuffle: false + hcp-val: + type: arrow + root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/test + split_range: + - 0 + - 2000 + shuffle: false +train_dataset: hcp-train +eval_datasets: +- hcp-train-subset +- hcp-val +val_dataset: null +clip_vmax: 3.0 +normalize: frame +tr_scale: null +crop_scale: null +crop_aspect: null +gray_jitter: null +num_workers: 16 +epochs: 100 +batch_size: 32 +accum_iter: 1 +base_lr: 0.001 +min_lr: 0.0 +warmup_epochs: 5 +weight_decay: 0.05 +betas: +- 0.9 +- 0.95 +clip_grad: 1.0 +amp: true +amp_dtype: float16 +ckpt: null +resume: true +auto_resume: true +start_epoch: 0 +max_checkpoints: 0 +checkpoint_period: null +plot_period: 5 +device: cuda +presend_cuda: false +seed: 5403 +debug: false +wandb: true +wandb_entity: null +wandb_project: fMRI-foundation-model +rank: 0 +world_size: 1 +gpu: 0 +distributed: true +dist_backend: nccl +in_chans: 1 +img_size: +- 224 +- 560 + +train transform: +Compose( + ToTensor() + TemporalCenterCrop(num_frames=16) + Normalize(mode='frame') + Clip(vmax=3.0) + FlatUnmask((224, 560)) +) +val transform: +Compose( + ToTensor() + TemporalCenterCrop(num_frames=16) + Normalize(mode='frame') + Clip(vmax=3.0) + FlatUnmask((224, 560)) +) +mask generator: +TubeMasking( + mask_ratio=0.9 + (patchify): Patchify2D((224, 560), (16, 16), in_chans=1) +) +loading dataset: hcp-train + +type: wds +url: /data/fmri-datasets/pretrain/hcpya-all.${input_space}.wds/hcpya-all-${input_space}-{00000..01799}.tar +clipping: random +clipping_kwargs: + oversample: 4.0 +shuffle: true +buffer_size: 2000 +samples_per_epoch: 200000 + +loading dataset: hcp-train-subset + +type: arrow +root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/validation +split_range: +- 0 +- 2000 +shuffle: false + +split indices: [899, 472, 767, 116, 1265, 1852, 300, 1335, 361, 1560] +loading dataset: hcp-val + +type: arrow +root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/test +split_range: +- 0 +- 2000 +shuffle: false + +split indices: [1075, 1189, 738, 1350, 965, 1964, 1367, 1183, 1619, 1407] +model: +MaskedAutoencoderViT( + decoding=attn, t_pred_stride=2, pred_edge_pad=0, no_decode_pos=True + (encoder): MaskedEncoder( + class_token=True, reg_tokens=0, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) + (pred_patchify): StridedPatchify3D((16, 224, 560), (2, 16, 16), in_chans=1, t_stride=2) + (decoder): MaskedDecoder( + cross_decode=False, class_token=True, no_embed_class=True + (pos_embed): SeparablePosEmbed(512, (4, 14, 35)) + (proj): Linear(in_features=768, out_features=512, bias=True) + (blocks): ModuleList( + (0-3): 4 x Block( + (norm1): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=16 + (q): Linear(in_features=512, out_features=512, bias=True) + (k): Linear(in_features=512, out_features=512, bias=True) + (v): Linear(in_features=512, out_features=512, bias=True) + (proj): Linear(in_features=512, out_features=512, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=512, out_features=2048, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=2048, out_features=512, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (head): Linear(in_features=512, out_features=512, bias=True) + ) +) +num params: 99.7M +total batch size: 32 = 32 bs per gpu x 1 accum x 1 gpus +lr: 1.25e-04 = 1.00e-03 x 32 / 256 +full schedule: epochs = 100 (steps = 625000) +warmup: epochs = 5 (steps = 31250) +loaded model state from checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +loaded optimizer state, resuming training from 87 +start training for 100 epochs +Train: [87] [ 0/6250] eta: 10:02:41 lr: 0.000006 grad: 0.0814 (0.0814) loss: 0.8543 (0.8543) time: 5.7859 data: 3.8596 max mem: 9353 +Train: [87] [ 100/6250] eta: 0:23:19 lr: 0.000006 grad: 0.1245 (0.1426) loss: 0.8297 (0.8307) time: 0.1452 data: 0.0362 max mem: 9390 +Train: [87] [ 200/6250] eta: 0:19:48 lr: 0.000006 grad: 0.1429 (0.1422) loss: 0.8187 (0.8255) time: 0.1599 data: 0.0653 max mem: 9390 +Train: [87] [ 300/6250] eta: 0:18:31 lr: 0.000006 grad: 0.1413 (0.1437) loss: 0.8091 (0.8212) time: 0.1552 data: 0.0616 max mem: 9390 +Train: [87] [ 400/6250] eta: 0:17:35 lr: 0.000006 grad: 0.1505 (0.1463) loss: 0.8119 (0.8180) time: 0.1635 data: 0.0654 max mem: 9390 +Train: [87] [ 500/6250] eta: 0:17:03 lr: 0.000006 grad: 0.1382 (0.1453) loss: 0.8095 (0.8166) time: 0.1594 data: 0.0590 max mem: 9390 +Train: [87] [ 600/6250] eta: 0:16:34 lr: 0.000006 grad: 0.1369 (0.1450) loss: 0.8091 (0.8152) time: 0.1429 data: 0.0446 max mem: 9390 +Train: [87] [ 700/6250] eta: 0:16:08 lr: 0.000006 grad: 0.1259 (0.1441) loss: 0.8139 (0.8149) time: 0.1681 data: 0.0784 max mem: 9390 +Train: [87] [ 800/6250] eta: 0:15:44 lr: 0.000006 grad: 0.1401 (0.1439) loss: 0.8095 (0.8147) time: 0.1800 data: 0.0866 max mem: 9390 +Train: [87] [ 900/6250] eta: 0:15:18 lr: 0.000006 grad: 0.1328 (0.1434) loss: 0.8146 (0.8145) time: 0.1771 data: 0.0753 max mem: 9390 +Train: [87] [1000/6250] eta: 0:14:53 lr: 0.000006 grad: 0.1376 (0.1431) loss: 0.8113 (0.8143) time: 0.1810 data: 0.0833 max mem: 9390 +Train: [87] [1100/6250] eta: 0:14:29 lr: 0.000006 grad: 0.1423 (0.1428) loss: 0.8078 (0.8140) time: 0.1569 data: 0.0608 max mem: 9390 +Train: [87] [1200/6250] eta: 0:14:06 lr: 0.000006 grad: 0.1387 (0.1428) loss: 0.8091 (0.8137) time: 0.1454 data: 0.0509 max mem: 9390 +Train: [87] [1300/6250] eta: 0:13:46 lr: 0.000006 grad: 0.1549 (0.1432) loss: 0.8055 (0.8134) time: 0.1625 data: 0.0709 max mem: 9390 +Train: [87] [1400/6250] eta: 0:13:28 lr: 0.000005 grad: 0.1502 (0.1434) loss: 0.8056 (0.8130) time: 0.1645 data: 0.0743 max mem: 9390 +Train: [87] [1500/6250] eta: 0:13:08 lr: 0.000005 grad: 0.1428 (0.1435) loss: 0.8036 (0.8125) time: 0.1615 data: 0.0685 max mem: 9390 +Train: [87] [1600/6250] eta: 0:12:48 lr: 0.000005 grad: 0.1368 (0.1434) loss: 0.8128 (0.8124) time: 0.1510 data: 0.0609 max mem: 9390 +Train: [87] [1700/6250] eta: 0:12:29 lr: 0.000005 grad: 0.1398 (0.1435) loss: 0.8108 (0.8121) time: 0.1474 data: 0.0571 max mem: 9390 +Train: [87] [1800/6250] eta: 0:12:11 lr: 0.000005 grad: 0.1558 (0.1438) loss: 0.8022 (0.8119) time: 0.1390 data: 0.0456 max mem: 9390 +Train: [87] [1900/6250] eta: 0:11:53 lr: 0.000005 grad: 0.1429 (0.1438) loss: 0.8055 (0.8117) time: 0.1514 data: 0.0672 max mem: 9390 +Train: [87] [2000/6250] eta: 0:11:35 lr: 0.000005 grad: 0.1385 (0.1441) loss: 0.8094 (0.8116) time: 0.1645 data: 0.0725 max mem: 9390 +Train: [87] [2100/6250] eta: 0:11:17 lr: 0.000005 grad: 0.1439 (0.1444) loss: 0.8084 (0.8114) time: 0.1777 data: 0.0912 max mem: 9390 +Train: [87] [2200/6250] eta: 0:10:58 lr: 0.000005 grad: 0.1439 (0.1445) loss: 0.8099 (0.8113) time: 0.1656 data: 0.0751 max mem: 9390 +Train: [87] [2300/6250] eta: 0:10:42 lr: 0.000005 grad: 0.1394 (0.1447) loss: 0.8115 (0.8113) time: 0.1496 data: 0.0627 max mem: 9390 +Train: [87] [2400/6250] eta: 0:10:25 lr: 0.000005 grad: 0.1491 (0.1448) loss: 0.8079 (0.8112) time: 0.1589 data: 0.0697 max mem: 9390 +Train: [87] [2500/6250] eta: 0:10:08 lr: 0.000005 grad: 0.1456 (0.1448) loss: 0.8149 (0.8112) time: 0.1591 data: 0.0713 max mem: 9390 +Train: [87] [2600/6250] eta: 0:09:50 lr: 0.000005 grad: 0.1370 (0.1450) loss: 0.8073 (0.8111) time: 0.1558 data: 0.0688 max mem: 9390 +Train: [87] [2700/6250] eta: 0:09:34 lr: 0.000005 grad: 0.1377 (0.1451) loss: 0.8080 (0.8110) time: 0.1768 data: 0.0949 max mem: 9390 +Train: [87] [2800/6250] eta: 0:09:18 lr: 0.000005 grad: 0.1306 (0.1449) loss: 0.8119 (0.8110) time: 0.1423 data: 0.0499 max mem: 9390 +Train: [87] [2900/6250] eta: 0:09:02 lr: 0.000005 grad: 0.1330 (0.1448) loss: 0.8136 (0.8109) time: 0.1775 data: 0.0934 max mem: 9390 +Train: [87] [3000/6250] eta: 0:08:45 lr: 0.000005 grad: 0.1399 (0.1447) loss: 0.8086 (0.8108) time: 0.1479 data: 0.0560 max mem: 9390 +Train: [87] [3100/6250] eta: 0:08:28 lr: 0.000005 grad: 0.1496 (0.1448) loss: 0.8103 (0.8107) time: 0.1433 data: 0.0590 max mem: 9390 +Train: [87] [3200/6250] eta: 0:08:11 lr: 0.000005 grad: 0.1441 (0.1448) loss: 0.8063 (0.8106) time: 0.1638 data: 0.0823 max mem: 9390 +Train: [87] [3300/6250] eta: 0:07:55 lr: 0.000005 grad: 0.1362 (0.1447) loss: 0.8022 (0.8105) time: 0.1651 data: 0.0809 max mem: 9390 +Train: [87] [3400/6250] eta: 0:07:38 lr: 0.000005 grad: 0.1377 (0.1446) loss: 0.8138 (0.8104) time: 0.1755 data: 0.0879 max mem: 9390 +Train: [87] [3500/6250] eta: 0:07:22 lr: 0.000005 grad: 0.1396 (0.1446) loss: 0.8111 (0.8104) time: 0.1527 data: 0.0679 max mem: 9390 +Train: [87] [3600/6250] eta: 0:07:06 lr: 0.000005 grad: 0.1337 (0.1446) loss: 0.8091 (0.8102) time: 0.1511 data: 0.0632 max mem: 9390 +Train: [87] [3700/6250] eta: 0:06:50 lr: 0.000005 grad: 0.1456 (0.1445) loss: 0.8068 (0.8102) time: 0.1523 data: 0.0650 max mem: 9390 +Train: [87] [3800/6250] eta: 0:06:33 lr: 0.000005 grad: 0.1310 (0.1444) loss: 0.8143 (0.8102) time: 0.1454 data: 0.0629 max mem: 9390 +Train: [87] [3900/6250] eta: 0:06:17 lr: 0.000005 grad: 0.1265 (0.1444) loss: 0.8169 (0.8102) time: 0.1554 data: 0.0650 max mem: 9390 +Train: [87] [4000/6250] eta: 0:06:01 lr: 0.000005 grad: 0.1498 (0.1444) loss: 0.8039 (0.8102) time: 0.1850 data: 0.1049 max mem: 9390 +Train: [87] [4100/6250] eta: 0:05:45 lr: 0.000005 grad: 0.1393 (0.1442) loss: 0.8101 (0.8103) time: 0.1788 data: 0.0950 max mem: 9390 +Train: [87] [4200/6250] eta: 0:05:29 lr: 0.000005 grad: 0.1242 (0.1440) loss: 0.8191 (0.8104) time: 0.1490 data: 0.0533 max mem: 9390 +Train: [87] [4300/6250] eta: 0:05:13 lr: 0.000005 grad: 0.1383 (0.1439) loss: 0.8106 (0.8104) time: 0.1573 data: 0.0653 max mem: 9390 +Train: [87] [4400/6250] eta: 0:04:57 lr: 0.000005 grad: 0.1306 (0.1438) loss: 0.8178 (0.8104) time: 0.1412 data: 0.0592 max mem: 9390 +Train: [87] [4500/6250] eta: 0:04:41 lr: 0.000005 grad: 0.1435 (0.1438) loss: 0.8105 (0.8105) time: 0.1611 data: 0.0709 max mem: 9390 +Train: [87] [4600/6250] eta: 0:04:25 lr: 0.000005 grad: 0.1314 (0.1438) loss: 0.8148 (0.8105) time: 0.1414 data: 0.0535 max mem: 9390 +Train: [87] [4700/6250] eta: 0:04:08 lr: 0.000005 grad: 0.1381 (0.1437) loss: 0.8098 (0.8106) time: 0.1749 data: 0.0917 max mem: 9390 +Train: [87] [4800/6250] eta: 0:03:52 lr: 0.000005 grad: 0.1426 (0.1436) loss: 0.8091 (0.8107) time: 0.1438 data: 0.0580 max mem: 9390 +Train: [87] [4900/6250] eta: 0:03:36 lr: 0.000005 grad: 0.1313 (0.1435) loss: 0.8133 (0.8107) time: 0.1709 data: 0.0761 max mem: 9390 +Train: [87] [5000/6250] eta: 0:03:20 lr: 0.000005 grad: 0.1367 (0.1435) loss: 0.8184 (0.8107) time: 0.1606 data: 0.0727 max mem: 9390 +Train: [87] [5100/6250] eta: 0:03:04 lr: 0.000005 grad: 0.1332 (0.1435) loss: 0.8106 (0.8107) time: 0.1607 data: 0.0735 max mem: 9390 +Train: [87] [5200/6250] eta: 0:02:48 lr: 0.000005 grad: 0.1368 (0.1434) loss: 0.8075 (0.8107) time: 0.1652 data: 0.0759 max mem: 9390 +Train: [87] [5300/6250] eta: 0:02:32 lr: 0.000005 grad: 0.1399 (0.1433) loss: 0.8146 (0.8108) time: 0.1734 data: 0.0860 max mem: 9390 +Train: [87] [5400/6250] eta: 0:02:16 lr: 0.000005 grad: 0.1391 (0.1432) loss: 0.8178 (0.8108) time: 0.1483 data: 0.0672 max mem: 9390 +Train: [87] [5500/6250] eta: 0:02:00 lr: 0.000005 grad: 0.1348 (0.1430) loss: 0.8192 (0.8109) time: 0.1546 data: 0.0735 max mem: 9390 +Train: [87] [5600/6250] eta: 0:01:44 lr: 0.000005 grad: 0.1341 (0.1429) loss: 0.8135 (0.8110) time: 0.1602 data: 0.0766 max mem: 9390 +Train: [87] [5700/6250] eta: 0:01:28 lr: 0.000005 grad: 0.1311 (0.1428) loss: 0.8178 (0.8111) time: 0.1348 data: 0.0391 max mem: 9390 +Train: [87] [5800/6250] eta: 0:01:12 lr: 0.000005 grad: 0.1334 (0.1427) loss: 0.8139 (0.8111) time: 0.1713 data: 0.0887 max mem: 9390 +Train: [87] [5900/6250] eta: 0:00:56 lr: 0.000005 grad: 0.1416 (0.1426) loss: 0.8088 (0.8112) time: 0.1711 data: 0.0829 max mem: 9390 +Train: [87] [6000/6250] eta: 0:00:40 lr: 0.000005 grad: 0.1366 (0.1426) loss: 0.8079 (0.8112) time: 0.1966 data: 0.1073 max mem: 9390 +Train: [87] [6100/6250] eta: 0:00:24 lr: 0.000005 grad: 0.1368 (0.1426) loss: 0.8080 (0.8111) time: 0.1390 data: 0.0519 max mem: 9390 +Train: [87] [6200/6250] eta: 0:00:08 lr: 0.000005 grad: 0.1359 (0.1426) loss: 0.8042 (0.8111) time: 0.1426 data: 0.0648 max mem: 9390 +Train: [87] [6249/6250] eta: 0:00:00 lr: 0.000005 grad: 0.1379 (0.1425) loss: 0.8108 (0.8111) time: 0.1411 data: 0.0502 max mem: 9390 +Train: [87] Total time: 0:16:49 (0.1615 s / it) +Averaged stats: lr: 0.000005 grad: 0.1379 (0.1425) loss: 0.8108 (0.8111) +Eval (hcp-train-subset): [87] [ 0/62] eta: 0:03:05 loss: 0.8271 (0.8271) time: 2.9937 data: 2.9164 max mem: 9390 +Eval (hcp-train-subset): [87] [61/62] eta: 0:00:00 loss: 0.8159 (0.8185) time: 0.1044 data: 0.0791 max mem: 9390 +Eval (hcp-train-subset): [87] Total time: 0:00:12 (0.1972 s / it) +Averaged stats (hcp-train-subset): loss: 0.8159 (0.8185) +Eval (hcp-val): [87] [ 0/62] eta: 0:02:38 loss: 0.8292 (0.8292) time: 2.5539 data: 2.4934 max mem: 9390 +Eval (hcp-val): [87] [61/62] eta: 0:00:00 loss: 0.8292 (0.8298) time: 0.1250 data: 0.0978 max mem: 9390 +Eval (hcp-val): [87] Total time: 0:00:12 (0.1985 s / it) +Averaged stats (hcp-val): loss: 0.8292 (0.8298) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +Train: [88] [ 0/6250] eta: 7:01:36 lr: 0.000005 grad: 0.1026 (0.1026) loss: 0.8668 (0.8668) time: 4.0475 data: 3.8153 max mem: 9390 +Train: [88] [ 100/6250] eta: 0:21:37 lr: 0.000005 grad: 0.1439 (0.1834) loss: 0.8001 (0.8075) time: 0.1469 data: 0.0546 max mem: 9390 +Train: [88] [ 200/6250] eta: 0:19:05 lr: 0.000005 grad: 0.1547 (0.1717) loss: 0.7976 (0.8053) time: 0.1647 data: 0.0726 max mem: 9390 +Train: [88] [ 300/6250] eta: 0:17:39 lr: 0.000005 grad: 0.1355 (0.1648) loss: 0.8159 (0.8059) time: 0.1479 data: 0.0523 max mem: 9390 +Train: [88] [ 400/6250] eta: 0:17:05 lr: 0.000005 grad: 0.1446 (0.1626) loss: 0.8142 (0.8059) time: 0.1707 data: 0.0767 max mem: 9390 +Train: [88] [ 500/6250] eta: 0:16:30 lr: 0.000005 grad: 0.1393 (0.1593) loss: 0.8135 (0.8073) time: 0.1644 data: 0.0783 max mem: 9390 +Train: [88] [ 600/6250] eta: 0:16:06 lr: 0.000005 grad: 0.1380 (0.1575) loss: 0.8125 (0.8083) time: 0.1664 data: 0.0797 max mem: 9390 +Train: [88] [ 700/6250] eta: 0:15:52 lr: 0.000005 grad: 0.1360 (0.1553) loss: 0.8160 (0.8087) time: 0.1711 data: 0.0761 max mem: 9390 +Train: [88] [ 800/6250] eta: 0:15:30 lr: 0.000005 grad: 0.1409 (0.1543) loss: 0.8041 (0.8086) time: 0.1586 data: 0.0655 max mem: 9390 +Train: [88] [ 900/6250] eta: 0:15:15 lr: 0.000005 grad: 0.1369 (0.1537) loss: 0.8145 (0.8083) time: 0.1722 data: 0.0816 max mem: 9390 +Train: [88] [1000/6250] eta: 0:14:54 lr: 0.000005 grad: 0.1363 (0.1528) loss: 0.8181 (0.8085) time: 0.1544 data: 0.0720 max mem: 9390 +Train: [88] [1100/6250] eta: 0:14:32 lr: 0.000005 grad: 0.1332 (0.1522) loss: 0.8083 (0.8083) time: 0.1630 data: 0.0723 max mem: 9390 +Train: [88] [1200/6250] eta: 0:14:13 lr: 0.000005 grad: 0.1365 (0.1517) loss: 0.8007 (0.8081) time: 0.1634 data: 0.0772 max mem: 9390 +Train: [88] [1300/6250] eta: 0:13:51 lr: 0.000005 grad: 0.1300 (0.1510) loss: 0.8124 (0.8081) time: 0.1422 data: 0.0583 max mem: 9390 +Train: [88] [1400/6250] eta: 0:13:30 lr: 0.000005 grad: 0.1402 (0.1504) loss: 0.8096 (0.8082) time: 0.1369 data: 0.0418 max mem: 9390 +Train: [88] [1500/6250] eta: 0:13:10 lr: 0.000005 grad: 0.1298 (0.1497) loss: 0.8125 (0.8085) time: 0.1704 data: 0.0801 max mem: 9390 +Train: [88] [1600/6250] eta: 0:12:51 lr: 0.000005 grad: 0.1427 (0.1493) loss: 0.8051 (0.8085) time: 0.1686 data: 0.0880 max mem: 9390 +Train: [88] [1700/6250] eta: 0:12:33 lr: 0.000005 grad: 0.1412 (0.1487) loss: 0.8073 (0.8085) time: 0.1502 data: 0.0655 max mem: 9390 +Train: [88] [1800/6250] eta: 0:12:14 lr: 0.000005 grad: 0.1384 (0.1484) loss: 0.8128 (0.8085) time: 0.1389 data: 0.0517 max mem: 9390 +Train: [88] [1900/6250] eta: 0:11:57 lr: 0.000005 grad: 0.1320 (0.1480) loss: 0.8109 (0.8086) time: 0.1580 data: 0.0689 max mem: 9390 +Train: [88] [2000/6250] eta: 0:11:39 lr: 0.000005 grad: 0.1487 (0.1476) loss: 0.8131 (0.8086) time: 0.1498 data: 0.0567 max mem: 9390 +Train: [88] [2100/6250] eta: 0:11:22 lr: 0.000005 grad: 0.1407 (0.1475) loss: 0.8081 (0.8087) time: 0.1755 data: 0.0856 max mem: 9390 +Train: [88] [2200/6250] eta: 0:11:06 lr: 0.000005 grad: 0.1338 (0.1471) loss: 0.8113 (0.8089) time: 0.1346 data: 0.0489 max mem: 9390 +Train: [88] [2300/6250] eta: 0:10:49 lr: 0.000005 grad: 0.1336 (0.1468) loss: 0.8148 (0.8090) time: 0.1469 data: 0.0548 max mem: 9390 +Train: [88] [2400/6250] eta: 0:10:32 lr: 0.000005 grad: 0.1333 (0.1464) loss: 0.8127 (0.8091) time: 0.1651 data: 0.0728 max mem: 9390 +Train: [88] [2500/6250] eta: 0:10:16 lr: 0.000005 grad: 0.1400 (0.1462) loss: 0.8104 (0.8091) time: 0.1549 data: 0.0677 max mem: 9390 +Train: [88] [2600/6250] eta: 0:09:59 lr: 0.000005 grad: 0.1368 (0.1460) loss: 0.8104 (0.8091) time: 0.1422 data: 0.0580 max mem: 9390 +Train: [88] [2700/6250] eta: 0:09:43 lr: 0.000005 grad: 0.1385 (0.1459) loss: 0.8087 (0.8091) time: 0.1571 data: 0.0729 max mem: 9390 +Train: [88] [2800/6250] eta: 0:09:26 lr: 0.000005 grad: 0.1406 (0.1458) loss: 0.8025 (0.8091) time: 0.1407 data: 0.0454 max mem: 9390 +Train: [88] [2900/6250] eta: 0:09:10 lr: 0.000004 grad: 0.1419 (0.1456) loss: 0.8056 (0.8091) time: 0.1893 data: 0.1018 max mem: 9390 +Train: [88] [3000/6250] eta: 0:08:53 lr: 0.000004 grad: 0.1443 (0.1455) loss: 0.8100 (0.8091) time: 0.1686 data: 0.0775 max mem: 9390 +Train: [88] [3100/6250] eta: 0:08:36 lr: 0.000004 grad: 0.1353 (0.1453) loss: 0.8135 (0.8091) time: 0.1632 data: 0.0739 max mem: 9390 +Train: [88] [3200/6250] eta: 0:08:19 lr: 0.000004 grad: 0.1504 (0.1452) loss: 0.8069 (0.8091) time: 0.1456 data: 0.0605 max mem: 9390 +Train: [88] [3300/6250] eta: 0:08:03 lr: 0.000004 grad: 0.1410 (0.1451) loss: 0.8060 (0.8091) time: 0.1486 data: 0.0599 max mem: 9390 +Train: [88] [3400/6250] eta: 0:07:47 lr: 0.000004 grad: 0.1388 (0.1450) loss: 0.8138 (0.8091) time: 0.1743 data: 0.0929 max mem: 9390 +Train: [88] [3500/6250] eta: 0:07:29 lr: 0.000004 grad: 0.1373 (0.1448) loss: 0.8154 (0.8092) time: 0.1396 data: 0.0502 max mem: 9390 +Train: [88] [3600/6250] eta: 0:07:13 lr: 0.000004 grad: 0.1313 (0.1445) loss: 0.8096 (0.8092) time: 0.1569 data: 0.0717 max mem: 9390 +Train: [88] [3700/6250] eta: 0:06:56 lr: 0.000004 grad: 0.1423 (0.1444) loss: 0.8026 (0.8092) time: 0.1463 data: 0.0632 max mem: 9390 +Train: [88] [3800/6250] eta: 0:06:40 lr: 0.000004 grad: 0.1350 (0.1443) loss: 0.8105 (0.8093) time: 0.1632 data: 0.0830 max mem: 9390 +Train: [88] [3900/6250] eta: 0:06:23 lr: 0.000004 grad: 0.1297 (0.1442) loss: 0.8201 (0.8094) time: 0.1686 data: 0.0826 max mem: 9390 +Train: [88] [4000/6250] eta: 0:06:07 lr: 0.000004 grad: 0.1366 (0.1440) loss: 0.8090 (0.8094) time: 0.1514 data: 0.0661 max mem: 9390 +Train: [88] [4100/6250] eta: 0:05:51 lr: 0.000004 grad: 0.1276 (0.1438) loss: 0.8088 (0.8095) time: 0.1513 data: 0.0675 max mem: 9390 +Train: [88] [4200/6250] eta: 0:05:35 lr: 0.000004 grad: 0.1307 (0.1436) loss: 0.8168 (0.8096) time: 0.1883 data: 0.1040 max mem: 9390 +Train: [88] [4300/6250] eta: 0:05:19 lr: 0.000004 grad: 0.1333 (0.1435) loss: 0.8112 (0.8096) time: 0.1554 data: 0.0657 max mem: 9390 +Train: [88] [4400/6250] eta: 0:05:02 lr: 0.000004 grad: 0.1366 (0.1434) loss: 0.8145 (0.8097) time: 0.1621 data: 0.0738 max mem: 9390 +Train: [88] [4500/6250] eta: 0:04:46 lr: 0.000004 grad: 0.1342 (0.1434) loss: 0.8089 (0.8097) time: 0.1633 data: 0.0799 max mem: 9390 +Train: [88] [4600/6250] eta: 0:04:29 lr: 0.000004 grad: 0.1351 (0.1433) loss: 0.8116 (0.8097) time: 0.1749 data: 0.0912 max mem: 9390 +Train: [88] [4700/6250] eta: 0:04:13 lr: 0.000004 grad: 0.1323 (0.1432) loss: 0.8088 (0.8096) time: 0.1798 data: 0.0917 max mem: 9390 +Train: [88] [4800/6250] eta: 0:03:56 lr: 0.000004 grad: 0.1422 (0.1432) loss: 0.8129 (0.8096) time: 0.1679 data: 0.0903 max mem: 9390 +Train: [88] [4900/6250] eta: 0:03:40 lr: 0.000004 grad: 0.1347 (0.1431) loss: 0.8150 (0.8097) time: 0.1463 data: 0.0666 max mem: 9390 +Train: [88] [5000/6250] eta: 0:03:24 lr: 0.000004 grad: 0.1351 (0.1430) loss: 0.8117 (0.8097) time: 0.1846 data: 0.1016 max mem: 9390 +Train: [88] [5100/6250] eta: 0:03:07 lr: 0.000004 grad: 0.1422 (0.1430) loss: 0.8121 (0.8097) time: 0.1580 data: 0.0748 max mem: 9390 +Train: [88] [5200/6250] eta: 0:02:50 lr: 0.000004 grad: 0.1429 (0.1430) loss: 0.8115 (0.8098) time: 0.1624 data: 0.0595 max mem: 9390 +Train: [88] [5300/6250] eta: 0:02:34 lr: 0.000004 grad: 0.1389 (0.1430) loss: 0.8176 (0.8099) time: 0.1468 data: 0.0562 max mem: 9390 +Train: [88] [5400/6250] eta: 0:02:18 lr: 0.000004 grad: 0.1361 (0.1429) loss: 0.8167 (0.8099) time: 0.1629 data: 0.0658 max mem: 9390 +Train: [88] [5500/6250] eta: 0:02:01 lr: 0.000004 grad: 0.1415 (0.1429) loss: 0.8111 (0.8099) time: 0.1747 data: 0.0733 max mem: 9390 +Train: [88] [5600/6250] eta: 0:01:45 lr: 0.000004 grad: 0.1322 (0.1428) loss: 0.8159 (0.8100) time: 0.1735 data: 0.0830 max mem: 9390 +Train: [88] [5700/6250] eta: 0:01:29 lr: 0.000004 grad: 0.1327 (0.1428) loss: 0.8201 (0.8100) time: 0.1515 data: 0.0470 max mem: 9390 +Train: [88] [5800/6250] eta: 0:01:13 lr: 0.000004 grad: 0.1315 (0.1427) loss: 0.8192 (0.8101) time: 0.1302 data: 0.0320 max mem: 9390 +Train: [88] [5900/6250] eta: 0:00:56 lr: 0.000004 grad: 0.1361 (0.1427) loss: 0.8140 (0.8101) time: 0.1404 data: 0.0402 max mem: 9390 +Train: [88] [6000/6250] eta: 0:00:40 lr: 0.000004 grad: 0.1431 (0.1427) loss: 0.8142 (0.8102) time: 0.1667 data: 0.0800 max mem: 9390 +Train: [88] [6100/6250] eta: 0:00:24 lr: 0.000004 grad: 0.1385 (0.1427) loss: 0.8144 (0.8102) time: 0.1443 data: 0.0545 max mem: 9390 +Train: [88] [6200/6250] eta: 0:00:08 lr: 0.000004 grad: 0.1423 (0.1428) loss: 0.8132 (0.8102) time: 0.1693 data: 0.0849 max mem: 9390 +Train: [88] [6249/6250] eta: 0:00:00 lr: 0.000004 grad: 0.1315 (0.1427) loss: 0.8137 (0.8102) time: 0.1385 data: 0.0522 max mem: 9390 +Train: [88] Total time: 0:16:58 (0.1630 s / it) +Averaged stats: lr: 0.000004 grad: 0.1315 (0.1427) loss: 0.8137 (0.8102) +Eval (hcp-train-subset): [88] [ 0/62] eta: 0:04:10 loss: 0.8272 (0.8272) time: 4.0372 data: 3.9298 max mem: 9390 +Eval (hcp-train-subset): [88] [61/62] eta: 0:00:00 loss: 0.8136 (0.8185) time: 0.1209 data: 0.0962 max mem: 9390 +Eval (hcp-train-subset): [88] Total time: 0:00:12 (0.2093 s / it) +Averaged stats (hcp-train-subset): loss: 0.8136 (0.8185) +Eval (hcp-val): [88] [ 0/62] eta: 0:02:23 loss: 0.8258 (0.8258) time: 2.3201 data: 2.2604 max mem: 9390 +Eval (hcp-val): [88] [61/62] eta: 0:00:00 loss: 0.8271 (0.8292) time: 0.1139 data: 0.0872 max mem: 9390 +Eval (hcp-val): [88] Total time: 0:00:12 (0.1951 s / it) +Averaged stats (hcp-val): loss: 0.8271 (0.8292) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +Train: [89] [ 0/6250] eta: 5:49:13 lr: 0.000004 grad: 0.1169 (0.1169) loss: 0.8561 (0.8561) time: 3.3526 data: 3.1160 max mem: 9390 +Train: [89] [ 100/6250] eta: 0:21:20 lr: 0.000004 grad: 0.1322 (0.1492) loss: 0.8286 (0.8237) time: 0.1650 data: 0.0707 max mem: 9390 +Train: [89] [ 200/6250] eta: 0:18:58 lr: 0.000004 grad: 0.1661 (0.1519) loss: 0.8028 (0.8186) time: 0.1584 data: 0.0596 max mem: 9390 +Train: [89] [ 300/6250] eta: 0:17:56 lr: 0.000004 grad: 0.1429 (0.1531) loss: 0.8025 (0.8156) time: 0.1820 data: 0.0837 max mem: 9390 +Train: [89] [ 400/6250] eta: 0:17:19 lr: 0.000004 grad: 0.1530 (0.1530) loss: 0.8159 (0.8148) time: 0.1673 data: 0.0789 max mem: 9390 +Train: [89] [ 500/6250] eta: 0:17:02 lr: 0.000004 grad: 0.1378 (0.1513) loss: 0.8101 (0.8146) time: 0.2080 data: 0.1190 max mem: 9390 +Train: [89] [ 600/6250] eta: 0:16:27 lr: 0.000004 grad: 0.1364 (0.1498) loss: 0.8088 (0.8143) time: 0.1563 data: 0.0695 max mem: 9390 +Train: [89] [ 700/6250] eta: 0:16:04 lr: 0.000004 grad: 0.1376 (0.1483) loss: 0.8140 (0.8145) time: 0.1543 data: 0.0576 max mem: 9390 +Train: [89] [ 800/6250] eta: 0:15:42 lr: 0.000004 grad: 0.1339 (0.1472) loss: 0.8124 (0.8147) time: 0.1590 data: 0.0607 max mem: 9390 +Train: [89] [ 900/6250] eta: 0:15:18 lr: 0.000004 grad: 0.1326 (0.1466) loss: 0.8161 (0.8150) time: 0.1567 data: 0.0649 max mem: 9390 +Train: [89] [1000/6250] eta: 0:14:55 lr: 0.000004 grad: 0.1369 (0.1457) loss: 0.8137 (0.8150) time: 0.1319 data: 0.0473 max mem: 9390 +Train: [89] [1100/6250] eta: 0:14:31 lr: 0.000004 grad: 0.1409 (0.1454) loss: 0.8112 (0.8151) time: 0.1493 data: 0.0582 max mem: 9390 +Train: [89] [1200/6250] eta: 0:14:15 lr: 0.000004 grad: 0.1425 (0.1451) loss: 0.8155 (0.8151) time: 0.1553 data: 0.0554 max mem: 9390 +Train: [89] [1300/6250] eta: 0:13:55 lr: 0.000004 grad: 0.1265 (0.1444) loss: 0.8134 (0.8153) time: 0.1500 data: 0.0588 max mem: 9390 +Train: [89] [1400/6250] eta: 0:13:36 lr: 0.000004 grad: 0.1304 (0.1436) loss: 0.8177 (0.8154) time: 0.1964 data: 0.1142 max mem: 9390 +Train: [89] [1500/6250] eta: 0:13:15 lr: 0.000004 grad: 0.1350 (0.1432) loss: 0.8136 (0.8154) time: 0.1417 data: 0.0542 max mem: 9390 +Train: [89] [1600/6250] eta: 0:12:56 lr: 0.000004 grad: 0.1361 (0.1429) loss: 0.8129 (0.8154) time: 0.1569 data: 0.0711 max mem: 9390 +Train: [89] [1700/6250] eta: 0:12:40 lr: 0.000004 grad: 0.1330 (0.1427) loss: 0.8181 (0.8153) time: 0.1773 data: 0.0848 max mem: 9390 +Train: [89] [1800/6250] eta: 0:12:20 lr: 0.000004 grad: 0.1324 (0.1425) loss: 0.8170 (0.8153) time: 0.1665 data: 0.0817 max mem: 9390 +Train: [89] [1900/6250] eta: 0:12:03 lr: 0.000004 grad: 0.1415 (0.1425) loss: 0.8140 (0.8154) time: 0.1717 data: 0.0851 max mem: 9390 +Train: [89] [2000/6250] eta: 0:11:45 lr: 0.000004 grad: 0.1325 (0.1424) loss: 0.8111 (0.8153) time: 0.1667 data: 0.0722 max mem: 9390 +Train: [89] [2100/6250] eta: 0:11:29 lr: 0.000004 grad: 0.1434 (0.1425) loss: 0.8111 (0.8152) time: 0.1506 data: 0.0575 max mem: 9390 +Train: [89] [2200/6250] eta: 0:11:12 lr: 0.000004 grad: 0.1461 (0.1428) loss: 0.8077 (0.8149) time: 0.1613 data: 0.0766 max mem: 9390 +Train: [89] [2300/6250] eta: 0:10:54 lr: 0.000004 grad: 0.1466 (0.1429) loss: 0.8031 (0.8147) time: 0.1631 data: 0.0736 max mem: 9390 +Train: [89] [2400/6250] eta: 0:10:38 lr: 0.000004 grad: 0.1412 (0.1432) loss: 0.8100 (0.8145) time: 0.1722 data: 0.0837 max mem: 9390 +Train: [89] [2500/6250] eta: 0:10:20 lr: 0.000004 grad: 0.1496 (0.1436) loss: 0.8084 (0.8141) time: 0.1701 data: 0.0875 max mem: 9390 +Train: [89] [2600/6250] eta: 0:10:02 lr: 0.000004 grad: 0.1458 (0.1437) loss: 0.8080 (0.8139) time: 0.1614 data: 0.0729 max mem: 9390 +Train: [89] [2700/6250] eta: 0:09:46 lr: 0.000004 grad: 0.1435 (0.1438) loss: 0.8114 (0.8137) time: 0.1860 data: 0.1014 max mem: 9390 +Train: [89] [2800/6250] eta: 0:09:29 lr: 0.000004 grad: 0.1486 (0.1440) loss: 0.8091 (0.8136) time: 0.1617 data: 0.0738 max mem: 9390 +Train: [89] [2900/6250] eta: 0:09:12 lr: 0.000004 grad: 0.1419 (0.1440) loss: 0.8162 (0.8135) time: 0.1542 data: 0.0691 max mem: 9390 +Train: [89] [3000/6250] eta: 0:08:56 lr: 0.000004 grad: 0.1418 (0.1443) loss: 0.8076 (0.8134) time: 0.1725 data: 0.0859 max mem: 9390 +Train: [89] [3100/6250] eta: 0:08:39 lr: 0.000004 grad: 0.1419 (0.1445) loss: 0.8114 (0.8132) time: 0.1802 data: 0.0970 max mem: 9390 +Train: [89] [3200/6250] eta: 0:08:22 lr: 0.000004 grad: 0.1481 (0.1446) loss: 0.8085 (0.8130) time: 0.1524 data: 0.0675 max mem: 9390 +Train: [89] [3300/6250] eta: 0:08:06 lr: 0.000004 grad: 0.1379 (0.1447) loss: 0.8087 (0.8128) time: 0.1671 data: 0.0795 max mem: 9390 +Train: [89] [3400/6250] eta: 0:07:49 lr: 0.000004 grad: 0.1461 (0.1448) loss: 0.8069 (0.8126) time: 0.1820 data: 0.0951 max mem: 9390 +Train: [89] [3500/6250] eta: 0:07:32 lr: 0.000004 grad: 0.1446 (0.1449) loss: 0.8003 (0.8125) time: 0.1217 data: 0.0317 max mem: 9390 +Train: [89] [3600/6250] eta: 0:07:15 lr: 0.000004 grad: 0.1435 (0.1451) loss: 0.8077 (0.8122) time: 0.1621 data: 0.0761 max mem: 9390 +Train: [89] [3700/6250] eta: 0:06:59 lr: 0.000004 grad: 0.1411 (0.1452) loss: 0.8066 (0.8121) time: 0.1485 data: 0.0636 max mem: 9390 +Train: [89] [3800/6250] eta: 0:06:42 lr: 0.000004 grad: 0.1331 (0.1453) loss: 0.8094 (0.8120) time: 0.1618 data: 0.0716 max mem: 9390 +Train: [89] [3900/6250] eta: 0:06:26 lr: 0.000004 grad: 0.1397 (0.1453) loss: 0.8001 (0.8118) time: 0.1851 data: 0.1017 max mem: 9390 +Train: [89] [4000/6250] eta: 0:06:09 lr: 0.000004 grad: 0.1440 (0.1454) loss: 0.8107 (0.8117) time: 0.1719 data: 0.0941 max mem: 9390 +Train: [89] [4100/6250] eta: 0:05:52 lr: 0.000004 grad: 0.1335 (0.1454) loss: 0.8127 (0.8116) time: 0.1685 data: 0.0813 max mem: 9390 +Train: [89] [4200/6250] eta: 0:05:36 lr: 0.000004 grad: 0.1442 (0.1455) loss: 0.8166 (0.8116) time: 0.1358 data: 0.0488 max mem: 9390 +Train: [89] [4300/6250] eta: 0:05:20 lr: 0.000004 grad: 0.1463 (0.1455) loss: 0.8081 (0.8115) time: 0.1696 data: 0.0820 max mem: 9390 +Train: [89] [4400/6250] eta: 0:05:03 lr: 0.000004 grad: 0.1451 (0.1455) loss: 0.8014 (0.8115) time: 0.1631 data: 0.0746 max mem: 9390 +Train: [89] [4500/6250] eta: 0:04:46 lr: 0.000004 grad: 0.1389 (0.1454) loss: 0.8134 (0.8115) time: 0.1789 data: 0.0879 max mem: 9390 +Train: [89] [4600/6250] eta: 0:04:30 lr: 0.000004 grad: 0.1416 (0.1454) loss: 0.8068 (0.8115) time: 0.1592 data: 0.0743 max mem: 9390 +Train: [89] [4700/6250] eta: 0:04:13 lr: 0.000004 grad: 0.1387 (0.1453) loss: 0.8072 (0.8115) time: 0.1654 data: 0.0756 max mem: 9390 +Train: [89] [4800/6250] eta: 0:03:57 lr: 0.000004 grad: 0.1345 (0.1453) loss: 0.8075 (0.8115) time: 0.1766 data: 0.0861 max mem: 9390 +Train: [89] [4900/6250] eta: 0:03:40 lr: 0.000004 grad: 0.1345 (0.1452) loss: 0.8087 (0.8114) time: 0.1793 data: 0.0962 max mem: 9390 +Train: [89] [5000/6250] eta: 0:03:24 lr: 0.000004 grad: 0.1395 (0.1452) loss: 0.8071 (0.8114) time: 0.1563 data: 0.0519 max mem: 9390 +Train: [89] [5100/6250] eta: 0:03:08 lr: 0.000004 grad: 0.1438 (0.1453) loss: 0.8073 (0.8113) time: 0.1619 data: 0.0814 max mem: 9390 +Train: [89] [5200/6250] eta: 0:02:51 lr: 0.000003 grad: 0.1388 (0.1452) loss: 0.8128 (0.8113) time: 0.1659 data: 0.0752 max mem: 9390 +Train: [89] [5300/6250] eta: 0:02:35 lr: 0.000003 grad: 0.1278 (0.1451) loss: 0.8217 (0.8113) time: 0.1721 data: 0.0862 max mem: 9390 +Train: [89] [5400/6250] eta: 0:02:19 lr: 0.000003 grad: 0.1424 (0.1451) loss: 0.8069 (0.8113) time: 0.1658 data: 0.0842 max mem: 9390 +Train: [89] [5500/6250] eta: 0:02:02 lr: 0.000003 grad: 0.1351 (0.1451) loss: 0.8186 (0.8113) time: 0.1572 data: 0.0720 max mem: 9390 +Train: [89] [5600/6250] eta: 0:01:46 lr: 0.000003 grad: 0.1405 (0.1450) loss: 0.8113 (0.8113) time: 0.1532 data: 0.0636 max mem: 9390 +Train: [89] [5700/6250] eta: 0:01:29 lr: 0.000003 grad: 0.1455 (0.1450) loss: 0.8157 (0.8112) time: 0.1573 data: 0.0657 max mem: 9390 +Train: [89] [5800/6250] eta: 0:01:13 lr: 0.000003 grad: 0.1379 (0.1450) loss: 0.8082 (0.8112) time: 0.1638 data: 0.0737 max mem: 9390 +Train: [89] [5900/6250] eta: 0:00:57 lr: 0.000003 grad: 0.1369 (0.1450) loss: 0.8109 (0.8112) time: 0.1650 data: 0.0762 max mem: 9390 +Train: [89] [6000/6250] eta: 0:00:40 lr: 0.000003 grad: 0.1493 (0.1450) loss: 0.8079 (0.8111) time: 0.1843 data: 0.1013 max mem: 9390 +Train: [89] [6100/6250] eta: 0:00:24 lr: 0.000003 grad: 0.1340 (0.1449) loss: 0.8075 (0.8111) time: 0.1717 data: 0.0859 max mem: 9390 +Train: [89] [6200/6250] eta: 0:00:08 lr: 0.000003 grad: 0.1425 (0.1450) loss: 0.8144 (0.8110) time: 0.1954 data: 0.1092 max mem: 9390 +Train: [89] [6249/6250] eta: 0:00:00 lr: 0.000003 grad: 0.1425 (0.1449) loss: 0.8082 (0.8111) time: 0.1565 data: 0.0723 max mem: 9390 +Train: [89] Total time: 0:17:09 (0.1648 s / it) +Averaged stats: lr: 0.000003 grad: 0.1425 (0.1449) loss: 0.8082 (0.8111) +Eval (hcp-train-subset): [89] [ 0/62] eta: 0:03:24 loss: 0.8260 (0.8260) time: 3.2996 data: 3.2328 max mem: 9390 +Eval (hcp-train-subset): [89] [61/62] eta: 0:00:00 loss: 0.8136 (0.8179) time: 0.0906 data: 0.0644 max mem: 9390 +Eval (hcp-train-subset): [89] Total time: 0:00:12 (0.2075 s / it) +Averaged stats (hcp-train-subset): loss: 0.8136 (0.8179) +Making plots (hcp-train-subset): example=62 +Eval (hcp-val): [89] [ 0/62] eta: 0:03:06 loss: 0.8301 (0.8301) time: 3.0022 data: 2.9474 max mem: 9390 +Eval (hcp-val): [89] [61/62] eta: 0:00:00 loss: 0.8275 (0.8291) time: 0.1173 data: 0.0923 max mem: 9390 +Eval (hcp-val): [89] Total time: 0:00:12 (0.2093 s / it) +Averaged stats (hcp-val): loss: 0.8275 (0.8291) +Making plots (hcp-val): example=17 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +Train: [90] [ 0/6250] eta: 8:40:46 lr: 0.000003 grad: 0.0915 (0.0915) loss: 0.8230 (0.8230) time: 4.9995 data: 4.7456 max mem: 9390 +Train: [90] [ 100/6250] eta: 0:21:12 lr: 0.000003 grad: 0.1710 (0.1914) loss: 0.8117 (0.8153) time: 0.1517 data: 0.0592 max mem: 9390 +Train: [90] [ 200/6250] eta: 0:18:43 lr: 0.000003 grad: 0.1526 (0.1760) loss: 0.8095 (0.8130) time: 0.1347 data: 0.0316 max mem: 9390 +Train: [90] [ 300/6250] eta: 0:17:41 lr: 0.000003 grad: 0.1516 (0.1686) loss: 0.8141 (0.8119) time: 0.1645 data: 0.0710 max mem: 9390 +Train: [90] [ 400/6250] eta: 0:17:00 lr: 0.000003 grad: 0.1395 (0.1632) loss: 0.8079 (0.8112) time: 0.1726 data: 0.0807 max mem: 9390 +Train: [90] [ 500/6250] eta: 0:16:33 lr: 0.000003 grad: 0.1428 (0.1594) loss: 0.8132 (0.8116) time: 0.1545 data: 0.0619 max mem: 9390 +Train: [90] [ 600/6250] eta: 0:16:15 lr: 0.000003 grad: 0.1467 (0.1576) loss: 0.8142 (0.8117) time: 0.2033 data: 0.1086 max mem: 9390 +Train: [90] [ 700/6250] eta: 0:15:53 lr: 0.000003 grad: 0.1432 (0.1555) loss: 0.8156 (0.8121) time: 0.1184 data: 0.0214 max mem: 9390 +Train: [90] [ 800/6250] eta: 0:15:36 lr: 0.000003 grad: 0.1437 (0.1546) loss: 0.8080 (0.8122) time: 0.1849 data: 0.0969 max mem: 9390 +Train: [90] [ 900/6250] eta: 0:15:19 lr: 0.000003 grad: 0.1346 (0.1532) loss: 0.8211 (0.8125) time: 0.1606 data: 0.0682 max mem: 9390 +Train: [90] [1000/6250] eta: 0:14:59 lr: 0.000003 grad: 0.1377 (0.1527) loss: 0.8128 (0.8124) time: 0.1845 data: 0.1039 max mem: 9390 +Train: [90] [1100/6250] eta: 0:14:34 lr: 0.000003 grad: 0.1420 (0.1518) loss: 0.8107 (0.8126) time: 0.1653 data: 0.0871 max mem: 9390 +Train: [90] [1200/6250] eta: 0:14:13 lr: 0.000003 grad: 0.1417 (0.1514) loss: 0.8088 (0.8126) time: 0.1651 data: 0.0743 max mem: 9390 +Train: [90] [1300/6250] eta: 0:13:56 lr: 0.000003 grad: 0.1462 (0.1510) loss: 0.8133 (0.8126) time: 0.1660 data: 0.0727 max mem: 9390 +Train: [90] [1400/6250] eta: 0:13:36 lr: 0.000003 grad: 0.1473 (0.1504) loss: 0.8110 (0.8126) time: 0.1476 data: 0.0582 max mem: 9390 +Train: [90] [1500/6250] eta: 0:13:17 lr: 0.000003 grad: 0.1442 (0.1499) loss: 0.8128 (0.8126) time: 0.1700 data: 0.0850 max mem: 9390 +Train: [90] [1600/6250] eta: 0:13:01 lr: 0.000003 grad: 0.1346 (0.1493) loss: 0.8163 (0.8128) time: 0.1694 data: 0.0771 max mem: 9390 +Train: [90] [1700/6250] eta: 0:12:42 lr: 0.000003 grad: 0.1419 (0.1491) loss: 0.8085 (0.8127) time: 0.1677 data: 0.0798 max mem: 9390 +Train: [90] [1800/6250] eta: 0:12:25 lr: 0.000003 grad: 0.1384 (0.1490) loss: 0.8152 (0.8128) time: 0.1677 data: 0.0802 max mem: 9390 +Train: [90] [1900/6250] eta: 0:12:08 lr: 0.000003 grad: 0.1379 (0.1488) loss: 0.8114 (0.8128) time: 0.1887 data: 0.0929 max mem: 9390 +Train: [90] [2000/6250] eta: 0:11:50 lr: 0.000003 grad: 0.1311 (0.1484) loss: 0.8197 (0.8130) time: 0.1686 data: 0.0835 max mem: 9390 +Train: [90] [2100/6250] eta: 0:11:34 lr: 0.000003 grad: 0.1483 (0.1484) loss: 0.8082 (0.8131) time: 0.1751 data: 0.0878 max mem: 9390 +Train: [90] [2200/6250] eta: 0:11:16 lr: 0.000003 grad: 0.1341 (0.1482) loss: 0.8127 (0.8131) time: 0.1578 data: 0.0703 max mem: 9390 +Train: [90] [2300/6250] eta: 0:10:58 lr: 0.000003 grad: 0.1343 (0.1479) loss: 0.8191 (0.8132) time: 0.1402 data: 0.0472 max mem: 9390 +Train: [90] [2400/6250] eta: 0:10:40 lr: 0.000003 grad: 0.1428 (0.1479) loss: 0.8177 (0.8133) time: 0.1384 data: 0.0566 max mem: 9390 +Train: [90] [2500/6250] eta: 0:10:23 lr: 0.000003 grad: 0.1456 (0.1478) loss: 0.8150 (0.8133) time: 0.1465 data: 0.0640 max mem: 9390 +Train: [90] [2600/6250] eta: 0:10:07 lr: 0.000003 grad: 0.1402 (0.1477) loss: 0.8138 (0.8133) time: 0.1678 data: 0.0801 max mem: 9390 +Train: [90] [2700/6250] eta: 0:09:50 lr: 0.000003 grad: 0.1422 (0.1477) loss: 0.8060 (0.8133) time: 0.1571 data: 0.0660 max mem: 9390 +Train: [90] [2800/6250] eta: 0:09:32 lr: 0.000003 grad: 0.1401 (0.1477) loss: 0.8159 (0.8133) time: 0.1600 data: 0.0663 max mem: 9390 +Train: [90] [2900/6250] eta: 0:09:15 lr: 0.000003 grad: 0.1474 (0.1476) loss: 0.8139 (0.8134) time: 0.1631 data: 0.0815 max mem: 9390 +Train: [90] [3000/6250] eta: 0:08:58 lr: 0.000003 grad: 0.1423 (0.1474) loss: 0.8164 (0.8135) time: 0.1564 data: 0.0728 max mem: 9390 +Train: [90] [3100/6250] eta: 0:08:42 lr: 0.000003 grad: 0.1323 (0.1473) loss: 0.8156 (0.8136) time: 0.1755 data: 0.0900 max mem: 9390 +Train: [90] [3200/6250] eta: 0:08:25 lr: 0.000003 grad: 0.1412 (0.1473) loss: 0.8165 (0.8136) time: 0.1691 data: 0.0879 max mem: 9390 +Train: [90] [3300/6250] eta: 0:08:09 lr: 0.000003 grad: 0.1379 (0.1470) loss: 0.8208 (0.8138) time: 0.1951 data: 0.1174 max mem: 9390 +Train: [90] [3400/6250] eta: 0:07:52 lr: 0.000003 grad: 0.1329 (0.1469) loss: 0.8188 (0.8139) time: 0.1620 data: 0.0780 max mem: 9390 +Train: [90] [3500/6250] eta: 0:07:37 lr: 0.000003 grad: 0.1479 (0.1467) loss: 0.8084 (0.8140) time: 0.2069 data: 0.1235 max mem: 9390 +Train: [90] [3600/6250] eta: 0:07:20 lr: 0.000003 grad: 0.1387 (0.1467) loss: 0.8169 (0.8141) time: 0.1763 data: 0.0968 max mem: 9390 +Train: [90] [3700/6250] eta: 0:07:04 lr: 0.000003 grad: 0.1493 (0.1467) loss: 0.8126 (0.8141) time: 0.1512 data: 0.0605 max mem: 9390 +Train: [90] [3800/6250] eta: 0:06:46 lr: 0.000003 grad: 0.1494 (0.1467) loss: 0.8103 (0.8140) time: 0.1639 data: 0.0829 max mem: 9390 +Train: [90] [3900/6250] eta: 0:06:29 lr: 0.000003 grad: 0.1416 (0.1468) loss: 0.8138 (0.8140) time: 0.1454 data: 0.0619 max mem: 9390 +Train: [90] [4000/6250] eta: 0:06:12 lr: 0.000003 grad: 0.1386 (0.1468) loss: 0.8090 (0.8140) time: 0.1732 data: 0.0823 max mem: 9390 +Train: [90] [4100/6250] eta: 0:05:55 lr: 0.000003 grad: 0.1326 (0.1467) loss: 0.8136 (0.8139) time: 0.1646 data: 0.0712 max mem: 9390 +Train: [90] [4200/6250] eta: 0:05:38 lr: 0.000003 grad: 0.1366 (0.1465) loss: 0.8182 (0.8139) time: 0.1585 data: 0.0680 max mem: 9390 +Train: [90] [4300/6250] eta: 0:05:22 lr: 0.000003 grad: 0.1317 (0.1463) loss: 0.8176 (0.8140) time: 0.1486 data: 0.0554 max mem: 9390 +Train: [90] [4400/6250] eta: 0:05:05 lr: 0.000003 grad: 0.1396 (0.1461) loss: 0.8181 (0.8140) time: 0.1500 data: 0.0525 max mem: 9390 +Train: [90] [4500/6250] eta: 0:04:48 lr: 0.000003 grad: 0.1421 (0.1461) loss: 0.8117 (0.8140) time: 0.1639 data: 0.0648 max mem: 9390 +Train: [90] [4600/6250] eta: 0:04:31 lr: 0.000003 grad: 0.1530 (0.1461) loss: 0.8079 (0.8140) time: 0.1450 data: 0.0224 max mem: 9390 +Train: [90] [4700/6250] eta: 0:04:15 lr: 0.000003 grad: 0.1465 (0.1460) loss: 0.8142 (0.8140) time: 0.1591 data: 0.0681 max mem: 9390 +Train: [90] [4800/6250] eta: 0:03:58 lr: 0.000003 grad: 0.1402 (0.1460) loss: 0.8086 (0.8139) time: 0.1441 data: 0.0428 max mem: 9390 +Train: [90] [4900/6250] eta: 0:03:41 lr: 0.000003 grad: 0.1444 (0.1461) loss: 0.8045 (0.8138) time: 0.1856 data: 0.0926 max mem: 9390 +Train: [90] [5000/6250] eta: 0:03:24 lr: 0.000003 grad: 0.1383 (0.1460) loss: 0.8069 (0.8138) time: 0.1726 data: 0.0816 max mem: 9390 +Train: [90] [5100/6250] eta: 0:03:08 lr: 0.000003 grad: 0.1436 (0.1460) loss: 0.8080 (0.8138) time: 0.1532 data: 0.0655 max mem: 9390 +Train: [90] [5200/6250] eta: 0:02:52 lr: 0.000003 grad: 0.1348 (0.1459) loss: 0.8127 (0.8138) time: 0.1769 data: 0.0893 max mem: 9390 +Train: [90] [5300/6250] eta: 0:02:35 lr: 0.000003 grad: 0.1385 (0.1459) loss: 0.8087 (0.8138) time: 0.1583 data: 0.0681 max mem: 9390 +Train: [90] [5400/6250] eta: 0:02:19 lr: 0.000003 grad: 0.1467 (0.1458) loss: 0.8090 (0.8138) time: 0.1581 data: 0.0602 max mem: 9390 +Train: [90] [5500/6250] eta: 0:02:02 lr: 0.000003 grad: 0.1470 (0.1457) loss: 0.8121 (0.8138) time: 0.1757 data: 0.0757 max mem: 9390 +Train: [90] [5600/6250] eta: 0:01:46 lr: 0.000003 grad: 0.1360 (0.1457) loss: 0.8114 (0.8138) time: 0.1664 data: 0.0726 max mem: 9390 +Train: [90] [5700/6250] eta: 0:01:30 lr: 0.000003 grad: 0.1443 (0.1457) loss: 0.8088 (0.8137) time: 0.1569 data: 0.0684 max mem: 9390 +Train: [90] [5800/6250] eta: 0:01:13 lr: 0.000003 grad: 0.1366 (0.1457) loss: 0.8130 (0.8137) time: 0.1727 data: 0.0692 max mem: 9390 +Train: [90] [5900/6250] eta: 0:00:57 lr: 0.000003 grad: 0.1333 (0.1457) loss: 0.8106 (0.8136) time: 0.1497 data: 0.0592 max mem: 9390 +Train: [90] [6000/6250] eta: 0:00:40 lr: 0.000003 grad: 0.1413 (0.1457) loss: 0.8110 (0.8136) time: 0.1606 data: 0.0683 max mem: 9390 +Train: [90] [6100/6250] eta: 0:00:24 lr: 0.000003 grad: 0.1395 (0.1456) loss: 0.8118 (0.8136) time: 0.1703 data: 0.0875 max mem: 9390 +Train: [90] [6200/6250] eta: 0:00:08 lr: 0.000003 grad: 0.1412 (0.1457) loss: 0.8123 (0.8136) time: 0.1723 data: 0.0859 max mem: 9390 +Train: [90] [6249/6250] eta: 0:00:00 lr: 0.000003 grad: 0.1370 (0.1456) loss: 0.8102 (0.8135) time: 0.1648 data: 0.0831 max mem: 9390 +Train: [90] Total time: 0:17:12 (0.1653 s / it) +Averaged stats: lr: 0.000003 grad: 0.1370 (0.1456) loss: 0.8102 (0.8135) +Eval (hcp-train-subset): [90] [ 0/62] eta: 0:04:30 loss: 0.8273 (0.8273) time: 4.3570 data: 4.3269 max mem: 9390 +Eval (hcp-train-subset): [90] [61/62] eta: 0:00:00 loss: 0.8127 (0.8176) time: 0.1219 data: 0.0971 max mem: 9390 +Eval (hcp-train-subset): [90] Total time: 0:00:12 (0.2091 s / it) +Averaged stats (hcp-train-subset): loss: 0.8127 (0.8176) +Eval (hcp-val): [90] [ 0/62] eta: 0:05:27 loss: 0.8249 (0.8249) time: 5.2854 data: 5.2544 max mem: 9390 +Eval (hcp-val): [90] [61/62] eta: 0:00:00 loss: 0.8278 (0.8287) time: 0.1356 data: 0.1099 max mem: 9390 +Eval (hcp-val): [90] Total time: 0:00:13 (0.2246 s / it) +Averaged stats (hcp-val): loss: 0.8278 (0.8287) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +Train: [91] [ 0/6250] eta: 7:37:09 lr: 0.000003 grad: 0.3361 (0.3361) loss: 0.7863 (0.7863) time: 4.3887 data: 4.1046 max mem: 9390 +Train: [91] [ 100/6250] eta: 0:22:02 lr: 0.000003 grad: 0.1706 (0.1596) loss: 0.8168 (0.8257) time: 0.1562 data: 0.0605 max mem: 9390 +Train: [91] [ 200/6250] eta: 0:19:16 lr: 0.000003 grad: 0.1497 (0.1614) loss: 0.8267 (0.8229) time: 0.1690 data: 0.0750 max mem: 9390 +Train: [91] [ 300/6250] eta: 0:17:59 lr: 0.000003 grad: 0.1556 (0.1599) loss: 0.8224 (0.8217) time: 0.1611 data: 0.0665 max mem: 9390 +Train: [91] [ 400/6250] eta: 0:17:25 lr: 0.000003 grad: 0.1409 (0.1595) loss: 0.8232 (0.8205) time: 0.1901 data: 0.0941 max mem: 9390 +Train: [91] [ 500/6250] eta: 0:16:47 lr: 0.000003 grad: 0.1445 (0.1579) loss: 0.8117 (0.8193) time: 0.1626 data: 0.0687 max mem: 9390 +Train: [91] [ 600/6250] eta: 0:16:21 lr: 0.000003 grad: 0.1392 (0.1555) loss: 0.8195 (0.8191) time: 0.1856 data: 0.0968 max mem: 9390 +Train: [91] [ 700/6250] eta: 0:16:09 lr: 0.000003 grad: 0.1453 (0.1543) loss: 0.8100 (0.8185) time: 0.1994 data: 0.1054 max mem: 9390 +Train: [91] [ 800/6250] eta: 0:15:50 lr: 0.000003 grad: 0.1445 (0.1530) loss: 0.8113 (0.8180) time: 0.1642 data: 0.0689 max mem: 9390 +Train: [91] [ 900/6250] eta: 0:15:30 lr: 0.000003 grad: 0.1446 (0.1529) loss: 0.8157 (0.8172) time: 0.1548 data: 0.0633 max mem: 9390 +Train: [91] [1000/6250] eta: 0:15:08 lr: 0.000003 grad: 0.1323 (0.1521) loss: 0.8160 (0.8168) time: 0.1835 data: 0.0951 max mem: 9390 +Train: [91] [1100/6250] eta: 0:14:46 lr: 0.000003 grad: 0.1425 (0.1512) loss: 0.8139 (0.8165) time: 0.1663 data: 0.0818 max mem: 9390 +Train: [91] [1200/6250] eta: 0:14:24 lr: 0.000003 grad: 0.1397 (0.1510) loss: 0.8158 (0.8163) time: 0.1732 data: 0.0922 max mem: 9390 +Train: [91] [1300/6250] eta: 0:14:04 lr: 0.000003 grad: 0.1397 (0.1505) loss: 0.8100 (0.8160) time: 0.1705 data: 0.0839 max mem: 9390 +Train: [91] [1400/6250] eta: 0:13:44 lr: 0.000003 grad: 0.1424 (0.1505) loss: 0.8159 (0.8156) time: 0.1634 data: 0.0731 max mem: 9390 +Train: [91] [1500/6250] eta: 0:13:29 lr: 0.000003 grad: 0.1489 (0.1505) loss: 0.8120 (0.8152) time: 0.1921 data: 0.1086 max mem: 9390 +Train: [91] [1600/6250] eta: 0:13:06 lr: 0.000003 grad: 0.1393 (0.1503) loss: 0.8133 (0.8149) time: 0.1782 data: 0.0911 max mem: 9390 +Train: [91] [1700/6250] eta: 0:12:48 lr: 0.000003 grad: 0.1325 (0.1501) loss: 0.8150 (0.8146) time: 0.1592 data: 0.0627 max mem: 9390 +Train: [91] [1800/6250] eta: 0:12:29 lr: 0.000003 grad: 0.1483 (0.1498) loss: 0.8087 (0.8143) time: 0.1686 data: 0.0733 max mem: 9390 +Train: [91] [1900/6250] eta: 0:12:12 lr: 0.000003 grad: 0.1428 (0.1496) loss: 0.8026 (0.8141) time: 0.1746 data: 0.0848 max mem: 9390 +Train: [91] [2000/6250] eta: 0:11:53 lr: 0.000003 grad: 0.1531 (0.1498) loss: 0.8105 (0.8138) time: 0.1505 data: 0.0731 max mem: 9390 +Train: [91] [2100/6250] eta: 0:11:36 lr: 0.000003 grad: 0.1453 (0.1497) loss: 0.8141 (0.8135) time: 0.1570 data: 0.0681 max mem: 9390 +Train: [91] [2200/6250] eta: 0:11:19 lr: 0.000003 grad: 0.1380 (0.1494) loss: 0.8117 (0.8133) time: 0.1766 data: 0.0946 max mem: 9390 +Train: [91] [2300/6250] eta: 0:11:01 lr: 0.000003 grad: 0.1439 (0.1492) loss: 0.8092 (0.8132) time: 0.1400 data: 0.0555 max mem: 9390 +Train: [91] [2400/6250] eta: 0:10:44 lr: 0.000003 grad: 0.1360 (0.1490) loss: 0.8118 (0.8130) time: 0.1597 data: 0.0769 max mem: 9390 +Train: [91] [2500/6250] eta: 0:10:25 lr: 0.000003 grad: 0.1375 (0.1489) loss: 0.8047 (0.8129) time: 0.1504 data: 0.0657 max mem: 9390 +Train: [91] [2600/6250] eta: 0:10:08 lr: 0.000003 grad: 0.1337 (0.1488) loss: 0.8055 (0.8128) time: 0.1552 data: 0.0695 max mem: 9390 +Train: [91] [2700/6250] eta: 0:09:51 lr: 0.000002 grad: 0.1401 (0.1487) loss: 0.8083 (0.8127) time: 0.1473 data: 0.0624 max mem: 9390 +Train: [91] [2800/6250] eta: 0:09:34 lr: 0.000002 grad: 0.1482 (0.1486) loss: 0.8085 (0.8125) time: 0.1583 data: 0.0693 max mem: 9390 +Train: [91] [2900/6250] eta: 0:09:17 lr: 0.000002 grad: 0.1414 (0.1485) loss: 0.8109 (0.8124) time: 0.1658 data: 0.0758 max mem: 9390 +Train: [91] [3000/6250] eta: 0:08:59 lr: 0.000002 grad: 0.1434 (0.1484) loss: 0.8043 (0.8123) time: 0.1515 data: 0.0625 max mem: 9390 +Train: [91] [3100/6250] eta: 0:08:43 lr: 0.000002 grad: 0.1391 (0.1483) loss: 0.8124 (0.8122) time: 0.1765 data: 0.0930 max mem: 9390 +Train: [91] [3200/6250] eta: 0:08:27 lr: 0.000002 grad: 0.1378 (0.1481) loss: 0.8128 (0.8121) time: 0.2108 data: 0.1292 max mem: 9390 +Train: [91] [3300/6250] eta: 0:08:09 lr: 0.000002 grad: 0.1469 (0.1480) loss: 0.8020 (0.8121) time: 0.1621 data: 0.0751 max mem: 9390 +Train: [91] [3400/6250] eta: 0:07:53 lr: 0.000002 grad: 0.1457 (0.1480) loss: 0.8105 (0.8120) time: 0.1522 data: 0.0637 max mem: 9390 +Train: [91] [3500/6250] eta: 0:07:36 lr: 0.000002 grad: 0.1324 (0.1480) loss: 0.8120 (0.8121) time: 0.1754 data: 0.0906 max mem: 9390 +Train: [91] [3600/6250] eta: 0:07:19 lr: 0.000002 grad: 0.1314 (0.1480) loss: 0.8135 (0.8120) time: 0.1750 data: 0.0923 max mem: 9390 +Train: [91] [3700/6250] eta: 0:07:02 lr: 0.000002 grad: 0.1409 (0.1479) loss: 0.8101 (0.8121) time: 0.1771 data: 0.0979 max mem: 9390 +Train: [91] [3800/6250] eta: 0:06:45 lr: 0.000002 grad: 0.1446 (0.1478) loss: 0.8076 (0.8120) time: 0.1499 data: 0.0560 max mem: 9390 +Train: [91] [3900/6250] eta: 0:06:29 lr: 0.000002 grad: 0.1355 (0.1477) loss: 0.8169 (0.8120) time: 0.1646 data: 0.0731 max mem: 9390 +Train: [91] [4000/6250] eta: 0:06:12 lr: 0.000002 grad: 0.1329 (0.1475) loss: 0.8173 (0.8120) time: 0.1610 data: 0.0705 max mem: 9390 +Train: [91] [4100/6250] eta: 0:05:56 lr: 0.000002 grad: 0.1401 (0.1473) loss: 0.8083 (0.8120) time: 0.1601 data: 0.0745 max mem: 9390 +Train: [91] [4200/6250] eta: 0:05:39 lr: 0.000002 grad: 0.1454 (0.1472) loss: 0.8081 (0.8120) time: 0.1523 data: 0.0615 max mem: 9390 +Train: [91] [4300/6250] eta: 0:05:23 lr: 0.000002 grad: 0.1387 (0.1471) loss: 0.8114 (0.8120) time: 0.1648 data: 0.0749 max mem: 9390 +Train: [91] [4400/6250] eta: 0:05:06 lr: 0.000002 grad: 0.1353 (0.1469) loss: 0.8113 (0.8120) time: 0.1577 data: 0.0722 max mem: 9390 +Train: [91] [4500/6250] eta: 0:04:50 lr: 0.000002 grad: 0.1442 (0.1467) loss: 0.8137 (0.8120) time: 0.1620 data: 0.0778 max mem: 9390 +Train: [91] [4600/6250] eta: 0:04:33 lr: 0.000002 grad: 0.1287 (0.1465) loss: 0.8200 (0.8121) time: 0.1442 data: 0.0544 max mem: 9390 +Train: [91] [4700/6250] eta: 0:04:16 lr: 0.000002 grad: 0.1417 (0.1464) loss: 0.8141 (0.8121) time: 0.1429 data: 0.0498 max mem: 9390 +Train: [91] [4800/6250] eta: 0:04:00 lr: 0.000002 grad: 0.1369 (0.1463) loss: 0.8135 (0.8121) time: 0.1528 data: 0.0606 max mem: 9390 +Train: [91] [4900/6250] eta: 0:03:43 lr: 0.000002 grad: 0.1360 (0.1462) loss: 0.8122 (0.8121) time: 0.1738 data: 0.0816 max mem: 9390 +Train: [91] [5000/6250] eta: 0:03:27 lr: 0.000002 grad: 0.1382 (0.1462) loss: 0.8157 (0.8121) time: 0.1883 data: 0.0999 max mem: 9390 +Train: [91] [5100/6250] eta: 0:03:10 lr: 0.000002 grad: 0.1356 (0.1460) loss: 0.8153 (0.8122) time: 0.1594 data: 0.0655 max mem: 9390 +Train: [91] [5200/6250] eta: 0:02:53 lr: 0.000002 grad: 0.1394 (0.1459) loss: 0.8135 (0.8122) time: 0.1820 data: 0.1004 max mem: 9390 +Train: [91] [5300/6250] eta: 0:02:37 lr: 0.000002 grad: 0.1421 (0.1458) loss: 0.8122 (0.8122) time: 0.2155 data: 0.1281 max mem: 9390 +Train: [91] [5400/6250] eta: 0:02:20 lr: 0.000002 grad: 0.1366 (0.1457) loss: 0.8179 (0.8123) time: 0.1664 data: 0.0874 max mem: 9390 +Train: [91] [5500/6250] eta: 0:02:04 lr: 0.000002 grad: 0.1395 (0.1457) loss: 0.8159 (0.8123) time: 0.1691 data: 0.0854 max mem: 9390 +Train: [91] [5600/6250] eta: 0:01:47 lr: 0.000002 grad: 0.1435 (0.1456) loss: 0.8140 (0.8124) time: 0.1749 data: 0.0934 max mem: 9390 +Train: [91] [5700/6250] eta: 0:01:31 lr: 0.000002 grad: 0.1407 (0.1456) loss: 0.8132 (0.8125) time: 0.1681 data: 0.0848 max mem: 9390 +Train: [91] [5800/6250] eta: 0:01:14 lr: 0.000002 grad: 0.1305 (0.1455) loss: 0.8201 (0.8125) time: 0.1574 data: 0.0619 max mem: 9390 +Train: [91] [5900/6250] eta: 0:00:57 lr: 0.000002 grad: 0.1375 (0.1455) loss: 0.8182 (0.8126) time: 0.1550 data: 0.0715 max mem: 9390 +Train: [91] [6000/6250] eta: 0:00:41 lr: 0.000002 grad: 0.1296 (0.1454) loss: 0.8193 (0.8126) time: 0.1712 data: 0.0851 max mem: 9390 +Train: [91] [6100/6250] eta: 0:00:24 lr: 0.000002 grad: 0.1388 (0.1453) loss: 0.8188 (0.8127) time: 0.1829 data: 0.0988 max mem: 9390 +Train: [91] [6200/6250] eta: 0:00:08 lr: 0.000002 grad: 0.1428 (0.1453) loss: 0.8133 (0.8127) time: 0.1627 data: 0.0727 max mem: 9390 +Train: [91] [6249/6250] eta: 0:00:00 lr: 0.000002 grad: 0.1418 (0.1453) loss: 0.8096 (0.8127) time: 0.1572 data: 0.0742 max mem: 9390 +Train: [91] Total time: 0:17:22 (0.1669 s / it) +Averaged stats: lr: 0.000002 grad: 0.1418 (0.1453) loss: 0.8096 (0.8127) +Eval (hcp-train-subset): [91] [ 0/62] eta: 0:03:13 loss: 0.8242 (0.8242) time: 3.1274 data: 3.0557 max mem: 9390 +Eval (hcp-train-subset): [91] [61/62] eta: 0:00:00 loss: 0.8129 (0.8164) time: 0.1158 data: 0.0911 max mem: 9390 +Eval (hcp-train-subset): [91] Total time: 0:00:12 (0.2030 s / it) +Averaged stats (hcp-train-subset): loss: 0.8129 (0.8164) +Eval (hcp-val): [91] [ 0/62] eta: 0:04:16 loss: 0.8233 (0.8233) time: 4.1362 data: 4.0753 max mem: 9390 +Eval (hcp-val): [91] [61/62] eta: 0:00:00 loss: 0.8271 (0.8284) time: 0.1352 data: 0.1080 max mem: 9390 +Eval (hcp-val): [91] Total time: 0:00:13 (0.2188 s / it) +Averaged stats (hcp-val): loss: 0.8271 (0.8284) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +Train: [92] [ 0/6250] eta: 9:30:27 lr: 0.000002 grad: 0.2188 (0.2188) loss: 0.8366 (0.8366) time: 5.4765 data: 5.3802 max mem: 9390 +Train: [92] [ 100/6250] eta: 0:22:31 lr: 0.000002 grad: 0.1284 (0.1728) loss: 0.8203 (0.8243) time: 0.1777 data: 0.0860 max mem: 9390 +Train: [92] [ 200/6250] eta: 0:19:26 lr: 0.000002 grad: 0.1452 (0.1679) loss: 0.8218 (0.8204) time: 0.1481 data: 0.0644 max mem: 9390 +Train: [92] [ 300/6250] eta: 0:17:56 lr: 0.000002 grad: 0.1368 (0.1617) loss: 0.8242 (0.8205) time: 0.1531 data: 0.0659 max mem: 9390 +Train: [92] [ 400/6250] eta: 0:17:16 lr: 0.000002 grad: 0.1305 (0.1578) loss: 0.8196 (0.8202) time: 0.1737 data: 0.0760 max mem: 9390 +Train: [92] [ 500/6250] eta: 0:16:39 lr: 0.000002 grad: 0.1395 (0.1563) loss: 0.8143 (0.8192) time: 0.1555 data: 0.0600 max mem: 9390 +Train: [92] [ 600/6250] eta: 0:16:11 lr: 0.000002 grad: 0.1405 (0.1548) loss: 0.8127 (0.8184) time: 0.1665 data: 0.0741 max mem: 9390 +Train: [92] [ 700/6250] eta: 0:15:56 lr: 0.000002 grad: 0.1367 (0.1535) loss: 0.8185 (0.8179) time: 0.1762 data: 0.0822 max mem: 9390 +Train: [92] [ 800/6250] eta: 0:15:41 lr: 0.000002 grad: 0.1385 (0.1526) loss: 0.8130 (0.8172) time: 0.1662 data: 0.0835 max mem: 9390 +Train: [92] [ 900/6250] eta: 0:15:21 lr: 0.000002 grad: 0.1408 (0.1519) loss: 0.8139 (0.8170) time: 0.1718 data: 0.0765 max mem: 9390 +Train: [92] [1000/6250] eta: 0:14:59 lr: 0.000002 grad: 0.1445 (0.1513) loss: 0.8189 (0.8169) time: 0.1735 data: 0.0893 max mem: 9390 +Train: [92] [1100/6250] eta: 0:14:40 lr: 0.000002 grad: 0.1442 (0.1508) loss: 0.8130 (0.8164) time: 0.1677 data: 0.0867 max mem: 9390 +Train: [92] [1200/6250] eta: 0:14:23 lr: 0.000002 grad: 0.1416 (0.1504) loss: 0.8107 (0.8161) time: 0.1565 data: 0.0637 max mem: 9390 +Train: [92] [1300/6250] eta: 0:14:04 lr: 0.000002 grad: 0.1383 (0.1500) loss: 0.8091 (0.8159) time: 0.1728 data: 0.0816 max mem: 9390 +Train: [92] [1400/6250] eta: 0:13:47 lr: 0.000002 grad: 0.1435 (0.1499) loss: 0.8089 (0.8156) time: 0.1872 data: 0.0973 max mem: 9390 +Train: [92] [1500/6250] eta: 0:13:29 lr: 0.000002 grad: 0.1349 (0.1497) loss: 0.8079 (0.8153) time: 0.1929 data: 0.1064 max mem: 9390 +Train: [92] [1600/6250] eta: 0:13:11 lr: 0.000002 grad: 0.1283 (0.1492) loss: 0.8110 (0.8149) time: 0.1671 data: 0.0767 max mem: 9390 +Train: [92] [1700/6250] eta: 0:12:52 lr: 0.000002 grad: 0.1345 (0.1489) loss: 0.8136 (0.8148) time: 0.1773 data: 0.0973 max mem: 9390 +Train: [92] [1800/6250] eta: 0:12:36 lr: 0.000002 grad: 0.1339 (0.1484) loss: 0.8126 (0.8149) time: 0.1618 data: 0.0716 max mem: 9390 +Train: [92] [1900/6250] eta: 0:12:19 lr: 0.000002 grad: 0.1434 (0.1480) loss: 0.8112 (0.8149) time: 0.1643 data: 0.0835 max mem: 9390 +Train: [92] [2000/6250] eta: 0:12:01 lr: 0.000002 grad: 0.1410 (0.1478) loss: 0.8124 (0.8148) time: 0.1750 data: 0.0828 max mem: 9390 +Train: [92] [2100/6250] eta: 0:11:45 lr: 0.000002 grad: 0.1526 (0.1477) loss: 0.8123 (0.8148) time: 0.2119 data: 0.1284 max mem: 9390 +Train: [92] [2200/6250] eta: 0:11:28 lr: 0.000002 grad: 0.1390 (0.1475) loss: 0.8158 (0.8148) time: 0.1816 data: 0.0994 max mem: 9390 +Train: [92] [2300/6250] eta: 0:11:11 lr: 0.000002 grad: 0.1403 (0.1473) loss: 0.8191 (0.8148) time: 0.1445 data: 0.0549 max mem: 9390 +Train: [92] [2400/6250] eta: 0:10:58 lr: 0.000002 grad: 0.1341 (0.1471) loss: 0.8142 (0.8148) time: 0.1870 data: 0.1051 max mem: 9390 +Train: [92] [2500/6250] eta: 0:10:45 lr: 0.000002 grad: 0.1384 (0.1467) loss: 0.8091 (0.8149) time: 0.1780 data: 0.0988 max mem: 9390 +Train: [92] [2600/6250] eta: 0:10:27 lr: 0.000002 grad: 0.1452 (0.1465) loss: 0.8073 (0.8149) time: 0.1688 data: 0.0964 max mem: 9390 +Train: [92] [2700/6250] eta: 0:10:09 lr: 0.000002 grad: 0.1472 (0.1466) loss: 0.8130 (0.8149) time: 0.1895 data: 0.0980 max mem: 9390 +Train: [92] [2800/6250] eta: 0:09:49 lr: 0.000002 grad: 0.1375 (0.1464) loss: 0.8157 (0.8149) time: 0.1603 data: 0.0769 max mem: 9390 +Train: [92] [2900/6250] eta: 0:09:32 lr: 0.000002 grad: 0.1384 (0.1463) loss: 0.8141 (0.8150) time: 0.1718 data: 0.0808 max mem: 9390 +Train: [92] [3000/6250] eta: 0:09:14 lr: 0.000002 grad: 0.1501 (0.1462) loss: 0.8141 (0.8150) time: 0.1557 data: 0.0579 max mem: 9390 +Train: [92] [3100/6250] eta: 0:08:57 lr: 0.000002 grad: 0.1424 (0.1461) loss: 0.8156 (0.8149) time: 0.1556 data: 0.0639 max mem: 9390 +Train: [92] [3200/6250] eta: 0:08:38 lr: 0.000002 grad: 0.1452 (0.1462) loss: 0.8078 (0.8148) time: 0.1895 data: 0.1010 max mem: 9390 +Train: [92] [3300/6250] eta: 0:08:20 lr: 0.000002 grad: 0.1385 (0.1461) loss: 0.8098 (0.8147) time: 0.1780 data: 0.0889 max mem: 9390 +Train: [92] [3400/6250] eta: 0:08:02 lr: 0.000002 grad: 0.1362 (0.1461) loss: 0.8101 (0.8146) time: 0.1657 data: 0.0757 max mem: 9390 +Train: [92] [3500/6250] eta: 0:07:44 lr: 0.000002 grad: 0.1375 (0.1461) loss: 0.8049 (0.8145) time: 0.1639 data: 0.0730 max mem: 9390 +Train: [92] [3600/6250] eta: 0:07:27 lr: 0.000002 grad: 0.1389 (0.1461) loss: 0.8122 (0.8143) time: 0.1491 data: 0.0648 max mem: 9390 +Train: [92] [3700/6250] eta: 0:07:09 lr: 0.000002 grad: 0.1551 (0.1462) loss: 0.8116 (0.8142) time: 0.1709 data: 0.0795 max mem: 9390 +Train: [92] [3800/6250] eta: 0:06:52 lr: 0.000002 grad: 0.1491 (0.1462) loss: 0.8046 (0.8142) time: 0.1780 data: 0.0925 max mem: 9390 +Train: [92] [3900/6250] eta: 0:06:35 lr: 0.000002 grad: 0.1423 (0.1461) loss: 0.8101 (0.8141) time: 0.1782 data: 0.0818 max mem: 9390 +Train: [92] [4000/6250] eta: 0:06:18 lr: 0.000002 grad: 0.1387 (0.1461) loss: 0.8181 (0.8141) time: 0.1641 data: 0.0777 max mem: 9390 +Train: [92] [4100/6250] eta: 0:06:01 lr: 0.000002 grad: 0.1419 (0.1460) loss: 0.8092 (0.8141) time: 0.1576 data: 0.0625 max mem: 9390 +Train: [92] [4200/6250] eta: 0:05:44 lr: 0.000002 grad: 0.1378 (0.1460) loss: 0.8124 (0.8141) time: 0.1457 data: 0.0557 max mem: 9390 +Train: [92] [4300/6250] eta: 0:05:27 lr: 0.000002 grad: 0.1353 (0.1460) loss: 0.8095 (0.8141) time: 0.1803 data: 0.0868 max mem: 9390 +Train: [92] [4400/6250] eta: 0:05:10 lr: 0.000002 grad: 0.1295 (0.1459) loss: 0.8134 (0.8140) time: 0.1931 data: 0.0971 max mem: 9390 +Train: [92] [4500/6250] eta: 0:04:53 lr: 0.000002 grad: 0.1435 (0.1459) loss: 0.8073 (0.8140) time: 0.1547 data: 0.0744 max mem: 9390 +Train: [92] [4600/6250] eta: 0:04:37 lr: 0.000002 grad: 0.1441 (0.1460) loss: 0.8130 (0.8140) time: 0.1629 data: 0.0752 max mem: 9390 +Train: [92] [4700/6250] eta: 0:04:20 lr: 0.000002 grad: 0.1408 (0.1462) loss: 0.8111 (0.8139) time: 0.1201 data: 0.0308 max mem: 9390 +Train: [92] [4800/6250] eta: 0:04:03 lr: 0.000002 grad: 0.1422 (0.1463) loss: 0.8135 (0.8139) time: 0.1554 data: 0.0672 max mem: 9390 +Train: [92] [4900/6250] eta: 0:03:46 lr: 0.000002 grad: 0.1502 (0.1464) loss: 0.8093 (0.8138) time: 0.1743 data: 0.0873 max mem: 9390 +Train: [92] [5000/6250] eta: 0:03:29 lr: 0.000002 grad: 0.1393 (0.1465) loss: 0.8157 (0.8138) time: 0.1661 data: 0.0822 max mem: 9390 +Train: [92] [5100/6250] eta: 0:03:13 lr: 0.000002 grad: 0.1421 (0.1466) loss: 0.8117 (0.8137) time: 0.1751 data: 0.0915 max mem: 9390 +Train: [92] [5200/6250] eta: 0:02:56 lr: 0.000002 grad: 0.1436 (0.1467) loss: 0.8095 (0.8136) time: 0.1602 data: 0.0736 max mem: 9390 +Train: [92] [5300/6250] eta: 0:02:39 lr: 0.000002 grad: 0.1388 (0.1468) loss: 0.8158 (0.8135) time: 0.1558 data: 0.0712 max mem: 9390 +Train: [92] [5400/6250] eta: 0:02:22 lr: 0.000002 grad: 0.1565 (0.1469) loss: 0.7985 (0.8133) time: 0.1920 data: 0.1144 max mem: 9390 +Train: [92] [5500/6250] eta: 0:02:05 lr: 0.000002 grad: 0.1471 (0.1471) loss: 0.8063 (0.8132) time: 0.1817 data: 0.0915 max mem: 9390 +Train: [92] [5600/6250] eta: 0:01:48 lr: 0.000002 grad: 0.1412 (0.1471) loss: 0.8064 (0.8131) time: 0.1420 data: 0.0502 max mem: 9390 +Train: [92] [5700/6250] eta: 0:01:32 lr: 0.000002 grad: 0.1433 (0.1473) loss: 0.8055 (0.8130) time: 0.1637 data: 0.0786 max mem: 9390 +Train: [92] [5800/6250] eta: 0:01:15 lr: 0.000002 grad: 0.1496 (0.1474) loss: 0.8029 (0.8128) time: 0.1589 data: 0.0720 max mem: 9390 +Train: [92] [5900/6250] eta: 0:00:58 lr: 0.000002 grad: 0.1514 (0.1474) loss: 0.8101 (0.8127) time: 0.1829 data: 0.0951 max mem: 9390 +Train: [92] [6000/6250] eta: 0:00:41 lr: 0.000002 grad: 0.1375 (0.1474) loss: 0.8115 (0.8126) time: 0.1754 data: 0.0871 max mem: 9390 +Train: [92] [6100/6250] eta: 0:00:25 lr: 0.000002 grad: 0.1426 (0.1474) loss: 0.8114 (0.8126) time: 0.1774 data: 0.0931 max mem: 9390 +Train: [92] [6200/6250] eta: 0:00:08 lr: 0.000002 grad: 0.1496 (0.1475) loss: 0.8073 (0.8125) time: 0.2177 data: 0.1399 max mem: 9390 +Train: [92] [6249/6250] eta: 0:00:00 lr: 0.000002 grad: 0.1506 (0.1475) loss: 0.8034 (0.8125) time: 0.1601 data: 0.0797 max mem: 9390 +Train: [92] Total time: 0:17:34 (0.1688 s / it) +Averaged stats: lr: 0.000002 grad: 0.1506 (0.1475) loss: 0.8034 (0.8125) +Eval (hcp-train-subset): [92] [ 0/62] eta: 0:03:55 loss: 0.8216 (0.8216) time: 3.8060 data: 3.7338 max mem: 9390 +Eval (hcp-train-subset): [92] [61/62] eta: 0:00:00 loss: 0.8120 (0.8164) time: 0.1100 data: 0.0850 max mem: 9390 +Eval (hcp-train-subset): [92] Total time: 0:00:13 (0.2149 s / it) +Averaged stats (hcp-train-subset): loss: 0.8120 (0.8164) +Eval (hcp-val): [92] [ 0/62] eta: 0:03:55 loss: 0.8241 (0.8241) time: 3.7978 data: 3.7657 max mem: 9390 +Eval (hcp-val): [92] [61/62] eta: 0:00:00 loss: 0.8257 (0.8283) time: 0.1388 data: 0.1130 max mem: 9390 +Eval (hcp-val): [92] Total time: 0:00:13 (0.2153 s / it) +Averaged stats (hcp-val): loss: 0.8257 (0.8283) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +Train: [93] [ 0/6250] eta: 7:15:49 lr: 0.000002 grad: 0.1947 (0.1947) loss: 0.8074 (0.8074) time: 4.1839 data: 3.9356 max mem: 9390 +Train: [93] [ 100/6250] eta: 0:21:47 lr: 0.000002 grad: 0.1826 (0.1826) loss: 0.8235 (0.8154) time: 0.1636 data: 0.0607 max mem: 9390 +Train: [93] [ 200/6250] eta: 0:19:22 lr: 0.000002 grad: 0.1355 (0.1760) loss: 0.8099 (0.8128) time: 0.1734 data: 0.0712 max mem: 9390 +Train: [93] [ 300/6250] eta: 0:18:10 lr: 0.000002 grad: 0.1472 (0.1719) loss: 0.8096 (0.8118) time: 0.1808 data: 0.0897 max mem: 9390 +Train: [93] [ 400/6250] eta: 0:17:28 lr: 0.000002 grad: 0.1734 (0.1713) loss: 0.8051 (0.8103) time: 0.1582 data: 0.0554 max mem: 9390 +Train: [93] [ 500/6250] eta: 0:16:46 lr: 0.000002 grad: 0.1446 (0.1675) loss: 0.8121 (0.8102) time: 0.1505 data: 0.0522 max mem: 9390 +Train: [93] [ 600/6250] eta: 0:16:17 lr: 0.000002 grad: 0.1542 (0.1660) loss: 0.7975 (0.8096) time: 0.1632 data: 0.0636 max mem: 9390 +Train: [93] [ 700/6250] eta: 0:16:10 lr: 0.000002 grad: 0.1524 (0.1647) loss: 0.8053 (0.8093) time: 0.1942 data: 0.1027 max mem: 9390 +Train: [93] [ 800/6250] eta: 0:15:52 lr: 0.000002 grad: 0.1507 (0.1634) loss: 0.8070 (0.8092) time: 0.1730 data: 0.0826 max mem: 9390 +Train: [93] [ 900/6250] eta: 0:15:35 lr: 0.000002 grad: 0.1403 (0.1618) loss: 0.8103 (0.8091) time: 0.1649 data: 0.0754 max mem: 9390 +Train: [93] [1000/6250] eta: 0:15:13 lr: 0.000002 grad: 0.1539 (0.1611) loss: 0.8101 (0.8089) time: 0.1671 data: 0.0824 max mem: 9390 +Train: [93] [1100/6250] eta: 0:14:51 lr: 0.000002 grad: 0.1351 (0.1598) loss: 0.8174 (0.8088) time: 0.1597 data: 0.0759 max mem: 9390 +Train: [93] [1200/6250] eta: 0:14:31 lr: 0.000002 grad: 0.1438 (0.1586) loss: 0.8103 (0.8088) time: 0.1485 data: 0.0550 max mem: 9390 +Train: [93] [1300/6250] eta: 0:14:13 lr: 0.000002 grad: 0.1363 (0.1576) loss: 0.8090 (0.8088) time: 0.1673 data: 0.0812 max mem: 9390 +Train: [93] [1400/6250] eta: 0:13:53 lr: 0.000002 grad: 0.1457 (0.1572) loss: 0.8104 (0.8089) time: 0.1615 data: 0.0713 max mem: 9390 +Train: [93] [1500/6250] eta: 0:13:33 lr: 0.000002 grad: 0.1403 (0.1565) loss: 0.8109 (0.8088) time: 0.1567 data: 0.0698 max mem: 9390 +Train: [93] [1600/6250] eta: 0:13:14 lr: 0.000002 grad: 0.1357 (0.1558) loss: 0.8070 (0.8087) time: 0.1604 data: 0.0705 max mem: 9390 +Train: [93] [1700/6250] eta: 0:12:55 lr: 0.000002 grad: 0.1424 (0.1553) loss: 0.8098 (0.8087) time: 0.1535 data: 0.0616 max mem: 9390 +Train: [93] [1800/6250] eta: 0:12:37 lr: 0.000002 grad: 0.1466 (0.1550) loss: 0.8088 (0.8086) time: 0.1434 data: 0.0578 max mem: 9390 +Train: [93] [1900/6250] eta: 0:12:18 lr: 0.000002 grad: 0.1532 (0.1549) loss: 0.8054 (0.8085) time: 0.1701 data: 0.0916 max mem: 9390 +Train: [93] [2000/6250] eta: 0:11:58 lr: 0.000002 grad: 0.1462 (0.1548) loss: 0.8031 (0.8084) time: 0.1643 data: 0.0741 max mem: 9390 +Train: [93] [2100/6250] eta: 0:11:39 lr: 0.000002 grad: 0.1401 (0.1546) loss: 0.8074 (0.8085) time: 0.1586 data: 0.0719 max mem: 9390 +Train: [93] [2200/6250] eta: 0:11:21 lr: 0.000002 grad: 0.1376 (0.1542) loss: 0.8167 (0.8085) time: 0.1327 data: 0.0473 max mem: 9390 +Train: [93] [2300/6250] eta: 0:11:04 lr: 0.000001 grad: 0.1453 (0.1543) loss: 0.8075 (0.8085) time: 0.1708 data: 0.0839 max mem: 9390 +Train: [93] [2400/6250] eta: 0:10:47 lr: 0.000001 grad: 0.1455 (0.1541) loss: 0.8031 (0.8085) time: 0.1560 data: 0.0730 max mem: 9390 +Train: [93] [2500/6250] eta: 0:10:30 lr: 0.000001 grad: 0.1478 (0.1541) loss: 0.8035 (0.8085) time: 0.1709 data: 0.0848 max mem: 9390 +Train: [93] [2600/6250] eta: 0:10:12 lr: 0.000001 grad: 0.1445 (0.1541) loss: 0.8128 (0.8085) time: 0.1564 data: 0.0667 max mem: 9390 +Train: [93] [2700/6250] eta: 0:09:56 lr: 0.000001 grad: 0.1494 (0.1540) loss: 0.8093 (0.8085) time: 0.1767 data: 0.0930 max mem: 9390 +Train: [93] [2800/6250] eta: 0:09:39 lr: 0.000001 grad: 0.1469 (0.1539) loss: 0.8107 (0.8085) time: 0.1772 data: 0.0875 max mem: 9390 +Train: [93] [2900/6250] eta: 0:09:21 lr: 0.000001 grad: 0.1407 (0.1538) loss: 0.8106 (0.8086) time: 0.1651 data: 0.0776 max mem: 9390 +Train: [93] [3000/6250] eta: 0:09:04 lr: 0.000001 grad: 0.1501 (0.1536) loss: 0.8042 (0.8086) time: 0.1573 data: 0.0649 max mem: 9390 +Train: [93] [3100/6250] eta: 0:08:47 lr: 0.000001 grad: 0.1463 (0.1536) loss: 0.8050 (0.8086) time: 0.1574 data: 0.0727 max mem: 9390 +Train: [93] [3200/6250] eta: 0:08:30 lr: 0.000001 grad: 0.1414 (0.1535) loss: 0.8085 (0.8086) time: 0.1495 data: 0.0656 max mem: 9390 +Train: [93] [3300/6250] eta: 0:08:13 lr: 0.000001 grad: 0.1508 (0.1536) loss: 0.8077 (0.8086) time: 0.1734 data: 0.0887 max mem: 9390 +Train: [93] [3400/6250] eta: 0:07:56 lr: 0.000001 grad: 0.1459 (0.1535) loss: 0.8053 (0.8087) time: 0.1802 data: 0.0948 max mem: 9390 +Train: [93] [3500/6250] eta: 0:07:39 lr: 0.000001 grad: 0.1446 (0.1533) loss: 0.8106 (0.8088) time: 0.1607 data: 0.0734 max mem: 9390 +Train: [93] [3600/6250] eta: 0:07:22 lr: 0.000001 grad: 0.1448 (0.1534) loss: 0.8187 (0.8088) time: 0.1434 data: 0.0610 max mem: 9390 +Train: [93] [3700/6250] eta: 0:07:06 lr: 0.000001 grad: 0.1483 (0.1533) loss: 0.8080 (0.8088) time: 0.1858 data: 0.1046 max mem: 9390 +Train: [93] [3800/6250] eta: 0:06:49 lr: 0.000001 grad: 0.1471 (0.1532) loss: 0.8032 (0.8088) time: 0.1585 data: 0.0762 max mem: 9390 +Train: [93] [3900/6250] eta: 0:06:32 lr: 0.000001 grad: 0.1473 (0.1532) loss: 0.8013 (0.8087) time: 0.1676 data: 0.0739 max mem: 9390 +Train: [93] [4000/6250] eta: 0:06:16 lr: 0.000001 grad: 0.1426 (0.1530) loss: 0.8086 (0.8087) time: 0.2176 data: 0.0837 max mem: 9390 +Train: [93] [4100/6250] eta: 0:05:59 lr: 0.000001 grad: 0.1489 (0.1528) loss: 0.8166 (0.8087) time: 0.1712 data: 0.0890 max mem: 9390 +Train: [93] [4200/6250] eta: 0:05:43 lr: 0.000001 grad: 0.1468 (0.1527) loss: 0.8081 (0.8087) time: 0.1717 data: 0.0849 max mem: 9390 +Train: [93] [4300/6250] eta: 0:05:26 lr: 0.000001 grad: 0.1405 (0.1526) loss: 0.8088 (0.8087) time: 0.1523 data: 0.0690 max mem: 9390 +Train: [93] [4400/6250] eta: 0:05:09 lr: 0.000001 grad: 0.1470 (0.1526) loss: 0.8055 (0.8087) time: 0.1387 data: 0.0562 max mem: 9390 +Train: [93] [4500/6250] eta: 0:04:52 lr: 0.000001 grad: 0.1493 (0.1526) loss: 0.8091 (0.8087) time: 0.1726 data: 0.0859 max mem: 9390 +Train: [93] [4600/6250] eta: 0:04:36 lr: 0.000001 grad: 0.1443 (0.1525) loss: 0.8054 (0.8087) time: 0.1696 data: 0.0747 max mem: 9390 +Train: [93] [4700/6250] eta: 0:04:19 lr: 0.000001 grad: 0.1475 (0.1526) loss: 0.8126 (0.8087) time: 0.1655 data: 0.0792 max mem: 9390 +Train: [93] [4800/6250] eta: 0:04:02 lr: 0.000001 grad: 0.1423 (0.1525) loss: 0.8122 (0.8087) time: 0.1724 data: 0.0917 max mem: 9390 +Train: [93] [4900/6250] eta: 0:03:45 lr: 0.000001 grad: 0.1401 (0.1524) loss: 0.8141 (0.8087) time: 0.1649 data: 0.0772 max mem: 9390 +Train: [93] [5000/6250] eta: 0:03:29 lr: 0.000001 grad: 0.1346 (0.1522) loss: 0.8075 (0.8087) time: 0.1593 data: 0.0701 max mem: 9390 +Train: [93] [5100/6250] eta: 0:03:12 lr: 0.000001 grad: 0.1481 (0.1521) loss: 0.8115 (0.8088) time: 0.1715 data: 0.0910 max mem: 9390 +Train: [93] [5200/6250] eta: 0:02:55 lr: 0.000001 grad: 0.1352 (0.1520) loss: 0.8141 (0.8088) time: 0.1490 data: 0.0646 max mem: 9390 +Train: [93] [5300/6250] eta: 0:02:38 lr: 0.000001 grad: 0.1395 (0.1519) loss: 0.8158 (0.8088) time: 0.1743 data: 0.0810 max mem: 9390 +Train: [93] [5400/6250] eta: 0:02:22 lr: 0.000001 grad: 0.1422 (0.1518) loss: 0.8092 (0.8089) time: 0.1692 data: 0.0851 max mem: 9390 +Train: [93] [5500/6250] eta: 0:02:05 lr: 0.000001 grad: 0.1510 (0.1519) loss: 0.8046 (0.8088) time: 0.1696 data: 0.0801 max mem: 9390 +Train: [93] [5600/6250] eta: 0:01:48 lr: 0.000001 grad: 0.1416 (0.1517) loss: 0.8153 (0.8089) time: 0.1705 data: 0.0835 max mem: 9390 +Train: [93] [5700/6250] eta: 0:01:31 lr: 0.000001 grad: 0.1395 (0.1516) loss: 0.8171 (0.8089) time: 0.2058 data: 0.1148 max mem: 9390 +Train: [93] [5800/6250] eta: 0:01:15 lr: 0.000001 grad: 0.1369 (0.1515) loss: 0.8113 (0.8090) time: 0.1498 data: 0.0620 max mem: 9390 +Train: [93] [5900/6250] eta: 0:00:58 lr: 0.000001 grad: 0.1417 (0.1514) loss: 0.8106 (0.8090) time: 0.2199 data: 0.1377 max mem: 9390 +Train: [93] [6000/6250] eta: 0:00:41 lr: 0.000001 grad: 0.1409 (0.1513) loss: 0.8084 (0.8090) time: 0.1688 data: 0.0832 max mem: 9390 +Train: [93] [6100/6250] eta: 0:00:25 lr: 0.000001 grad: 0.1380 (0.1512) loss: 0.8083 (0.8091) time: 0.1618 data: 0.0745 max mem: 9390 +Train: [93] [6200/6250] eta: 0:00:08 lr: 0.000001 grad: 0.1387 (0.1512) loss: 0.8145 (0.8091) time: 0.2179 data: 0.1432 max mem: 9390 +Train: [93] [6249/6250] eta: 0:00:00 lr: 0.000001 grad: 0.1516 (0.1512) loss: 0.8045 (0.8091) time: 0.1549 data: 0.0749 max mem: 9390 +Train: [93] Total time: 0:17:32 (0.1683 s / it) +Averaged stats: lr: 0.000001 grad: 0.1516 (0.1512) loss: 0.8045 (0.8091) +Eval (hcp-train-subset): [93] [ 0/62] eta: 0:02:40 loss: 0.8247 (0.8247) time: 2.5922 data: 2.5099 max mem: 9390 +Eval (hcp-train-subset): [93] [61/62] eta: 0:00:00 loss: 0.8136 (0.8157) time: 0.1206 data: 0.0935 max mem: 9390 +Eval (hcp-train-subset): [93] Total time: 0:00:13 (0.2160 s / it) +Averaged stats (hcp-train-subset): loss: 0.8136 (0.8157) +Eval (hcp-val): [93] [ 0/62] eta: 0:02:57 loss: 0.8276 (0.8276) time: 2.8555 data: 2.7745 max mem: 9390 +Eval (hcp-val): [93] [61/62] eta: 0:00:00 loss: 0.8288 (0.8289) time: 0.1321 data: 0.1053 max mem: 9390 +Eval (hcp-val): [93] Total time: 0:00:12 (0.2081 s / it) +Averaged stats (hcp-val): loss: 0.8288 (0.8289) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +Train: [94] [ 0/6250] eta: 6:46:55 lr: 0.000001 grad: nan (nan) loss: 0.8319 (0.8319) time: 3.9065 data: 3.5880 max mem: 9390 +Train: [94] [ 100/6250] eta: 0:21:55 lr: 0.000001 grad: 0.1809 (0.2354) loss: 0.8221 (0.8115) time: 0.1646 data: 0.0705 max mem: 9390 +Train: [94] [ 200/6250] eta: 0:19:32 lr: 0.000001 grad: 0.1455 (0.1982) loss: 0.8071 (0.8143) time: 0.1719 data: 0.0855 max mem: 9390 +Train: [94] [ 300/6250] eta: 0:18:12 lr: 0.000001 grad: 0.1725 (0.1855) loss: 0.8092 (0.8145) time: 0.1672 data: 0.0690 max mem: 9390 +Train: [94] [ 400/6250] eta: 0:17:23 lr: 0.000001 grad: 0.1575 (0.1790) loss: 0.8121 (0.8134) time: 0.1468 data: 0.0390 max mem: 9390 +Train: [94] [ 500/6250] eta: 0:16:52 lr: 0.000001 grad: 0.1544 (0.1756) loss: 0.8141 (0.8127) time: 0.1527 data: 0.0497 max mem: 9390 +Train: [94] [ 600/6250] eta: 0:16:18 lr: 0.000001 grad: 0.1512 (0.1730) loss: 0.8115 (0.8124) time: 0.1635 data: 0.0692 max mem: 9390 +Train: [94] [ 700/6250] eta: 0:15:58 lr: 0.000001 grad: 0.1537 (0.1700) loss: 0.8102 (0.8125) time: 0.1817 data: 0.0835 max mem: 9390 +Train: [94] [ 800/6250] eta: 0:15:39 lr: 0.000001 grad: 0.1456 (0.1679) loss: 0.8196 (0.8127) time: 0.1593 data: 0.0704 max mem: 9390 +Train: [94] [ 900/6250] eta: 0:15:21 lr: 0.000001 grad: 0.1363 (0.1659) loss: 0.8104 (0.8130) time: 0.1848 data: 0.1062 max mem: 9390 +Train: [94] [1000/6250] eta: 0:15:00 lr: 0.000001 grad: 0.1426 (0.1640) loss: 0.8177 (0.8133) time: 0.1784 data: 0.0892 max mem: 9390 +Train: [94] [1100/6250] eta: 0:14:41 lr: 0.000001 grad: 0.1434 (0.1623) loss: 0.8157 (0.8136) time: 0.1591 data: 0.0686 max mem: 9390 +Train: [94] [1200/6250] eta: 0:14:31 lr: 0.000001 grad: 0.1473 (0.1608) loss: 0.8201 (0.8140) time: 0.1932 data: 0.0984 max mem: 9390 +Train: [94] [1300/6250] eta: 0:14:22 lr: 0.000001 grad: 0.1442 (0.1597) loss: 0.8187 (0.8143) time: 0.1882 data: 0.0958 max mem: 9390 +Train: [94] [1400/6250] eta: 0:14:18 lr: 0.000001 grad: 0.1413 (0.1588) loss: 0.8089 (0.8144) time: 0.1531 data: 0.0662 max mem: 9390 +Train: [94] [1500/6250] eta: 0:13:54 lr: 0.000001 grad: 0.1378 (0.1579) loss: 0.8087 (0.8145) time: 0.1863 data: 0.0938 max mem: 9390 +Train: [94] [1600/6250] eta: 0:13:36 lr: 0.000001 grad: 0.1378 (0.1573) loss: 0.8155 (0.8146) time: 0.1519 data: 0.0702 max mem: 9390 +Train: [94] [1700/6250] eta: 0:13:16 lr: 0.000001 grad: 0.1417 (0.1566) loss: 0.8170 (0.8147) time: 0.1748 data: 0.0805 max mem: 9390 +Train: [94] [1800/6250] eta: 0:12:55 lr: 0.000001 grad: 0.1495 (0.1562) loss: 0.8142 (0.8147) time: 0.1546 data: 0.0565 max mem: 9390 +Train: [94] [1900/6250] eta: 0:12:37 lr: 0.000001 grad: 0.1414 (0.1557) loss: 0.8161 (0.8148) time: 0.1613 data: 0.0688 max mem: 9390 +Train: [94] [2000/6250] eta: 0:12:15 lr: 0.000001 grad: 0.1452 (0.1552) loss: 0.8173 (0.8149) time: 0.1483 data: 0.0452 max mem: 9390 +Train: [94] [2100/6250] eta: 0:11:56 lr: 0.000001 grad: 0.1527 (0.1549) loss: 0.8164 (0.8150) time: 0.1577 data: 0.0542 max mem: 9390 +Train: [94] [2200/6250] eta: 0:11:37 lr: 0.000001 grad: 0.1447 (0.1547) loss: 0.8187 (0.8150) time: 0.1501 data: 0.0519 max mem: 9390 +Train: [94] [2300/6250] eta: 0:11:17 lr: 0.000001 grad: 0.1368 (0.1543) loss: 0.8079 (0.8150) time: 0.1323 data: 0.0288 max mem: 9390 +Train: [94] [2400/6250] eta: 0:10:58 lr: 0.000001 grad: 0.1417 (0.1542) loss: 0.8158 (0.8150) time: 0.1449 data: 0.0491 max mem: 9390 +Train: [94] [2500/6250] eta: 0:10:38 lr: 0.000001 grad: 0.1471 (0.1539) loss: 0.8172 (0.8150) time: 0.1357 data: 0.0418 max mem: 9390 +Train: [94] [2600/6250] eta: 0:10:21 lr: 0.000001 grad: 0.1405 (0.1535) loss: 0.8151 (0.8151) time: 0.1487 data: 0.0577 max mem: 9390 +Train: [94] [2700/6250] eta: 0:10:04 lr: 0.000001 grad: 0.1370 (0.1532) loss: 0.8134 (0.8151) time: 0.1765 data: 0.0834 max mem: 9390 +Train: [94] [2800/6250] eta: 0:09:46 lr: 0.000001 grad: 0.1391 (0.1530) loss: 0.8141 (0.8151) time: 0.1771 data: 0.0745 max mem: 9390 +Train: [94] [2900/6250] eta: 0:09:28 lr: 0.000001 grad: 0.1454 (0.1529) loss: 0.8137 (0.8150) time: 0.1618 data: 0.0731 max mem: 9390 +Train: [94] [3000/6250] eta: 0:09:11 lr: 0.000001 grad: 0.1450 (0.1529) loss: 0.8057 (0.8148) time: 0.1785 data: 0.0886 max mem: 9390 +Train: [94] [3100/6250] eta: 0:08:54 lr: 0.000001 grad: 0.1473 (0.1527) loss: 0.8134 (0.8148) time: 0.1680 data: 0.0752 max mem: 9390 +Train: [94] [3200/6250] eta: 0:08:38 lr: 0.000001 grad: 0.1426 (0.1526) loss: 0.8108 (0.8147) time: 0.1614 data: 0.0730 max mem: 9390 +Train: [94] [3300/6250] eta: 0:08:20 lr: 0.000001 grad: 0.1396 (0.1525) loss: 0.8108 (0.8147) time: 0.1944 data: 0.1147 max mem: 9390 +Train: [94] [3400/6250] eta: 0:08:03 lr: 0.000001 grad: 0.1302 (0.1524) loss: 0.8179 (0.8146) time: 0.1742 data: 0.0884 max mem: 9390 +Train: [94] [3500/6250] eta: 0:07:46 lr: 0.000001 grad: 0.1400 (0.1522) loss: 0.8133 (0.8146) time: 0.1608 data: 0.0697 max mem: 9390 +Train: [94] [3600/6250] eta: 0:07:29 lr: 0.000001 grad: 0.1370 (0.1520) loss: 0.8100 (0.8146) time: 0.1576 data: 0.0704 max mem: 9390 +Train: [94] [3700/6250] eta: 0:07:12 lr: 0.000001 grad: 0.1446 (0.1520) loss: 0.8068 (0.8145) time: 0.1582 data: 0.0760 max mem: 9390 +Train: [94] [3800/6250] eta: 0:06:55 lr: 0.000001 grad: 0.1415 (0.1519) loss: 0.8031 (0.8145) time: 0.1623 data: 0.0667 max mem: 9390 +Train: [94] [3900/6250] eta: 0:06:38 lr: 0.000001 grad: 0.1488 (0.1519) loss: 0.8119 (0.8145) time: 0.1830 data: 0.0975 max mem: 9390 +Train: [94] [4000/6250] eta: 0:06:21 lr: 0.000001 grad: 0.1471 (0.1518) loss: 0.8111 (0.8144) time: 0.1629 data: 0.0809 max mem: 9390 +Train: [94] [4100/6250] eta: 0:06:03 lr: 0.000001 grad: 0.1498 (0.1518) loss: 0.8060 (0.8143) time: 0.1362 data: 0.0516 max mem: 9390 +Train: [94] [4200/6250] eta: 0:05:46 lr: 0.000001 grad: 0.1475 (0.1518) loss: 0.8066 (0.8142) time: 0.1685 data: 0.0843 max mem: 9390 +Train: [94] [4300/6250] eta: 0:05:29 lr: 0.000001 grad: 0.1438 (0.1518) loss: 0.8132 (0.8141) time: 0.1469 data: 0.0612 max mem: 9390 +Train: [94] [4400/6250] eta: 0:05:12 lr: 0.000001 grad: 0.1407 (0.1519) loss: 0.8085 (0.8140) time: 0.1357 data: 0.0554 max mem: 9390 +Train: [94] [4500/6250] eta: 0:04:55 lr: 0.000001 grad: 0.1504 (0.1518) loss: 0.8121 (0.8139) time: 0.1717 data: 0.0866 max mem: 9390 +Train: [94] [4600/6250] eta: 0:04:38 lr: 0.000001 grad: 0.1523 (0.1519) loss: 0.8114 (0.8137) time: 0.1529 data: 0.0666 max mem: 9390 +Train: [94] [4700/6250] eta: 0:04:21 lr: 0.000001 grad: 0.1466 (0.1518) loss: 0.8085 (0.8136) time: 0.1544 data: 0.0714 max mem: 9390 +Train: [94] [4800/6250] eta: 0:04:04 lr: 0.000001 grad: 0.1543 (0.1518) loss: 0.8033 (0.8135) time: 0.1499 data: 0.0613 max mem: 9390 +Train: [94] [4900/6250] eta: 0:03:47 lr: 0.000001 grad: 0.1427 (0.1518) loss: 0.8108 (0.8134) time: 0.1692 data: 0.0838 max mem: 9390 +Train: [94] [5000/6250] eta: 0:03:30 lr: 0.000001 grad: 0.1486 (0.1517) loss: 0.8076 (0.8133) time: 0.1816 data: 0.0958 max mem: 9390 +Train: [94] [5100/6250] eta: 0:03:13 lr: 0.000001 grad: 0.1517 (0.1517) loss: 0.8137 (0.8132) time: 0.1680 data: 0.0821 max mem: 9390 +Train: [94] [5200/6250] eta: 0:02:57 lr: 0.000001 grad: 0.1532 (0.1518) loss: 0.8029 (0.8131) time: 0.1641 data: 0.0722 max mem: 9390 +Train: [94] [5300/6250] eta: 0:02:40 lr: 0.000001 grad: 0.1537 (0.1519) loss: 0.8084 (0.8130) time: 0.1678 data: 0.0841 max mem: 9390 +Train: [94] [5400/6250] eta: 0:02:23 lr: 0.000001 grad: 0.1473 (0.1519) loss: 0.8108 (0.8129) time: 0.1624 data: 0.0740 max mem: 9390 +Train: [94] [5500/6250] eta: 0:02:06 lr: 0.000001 grad: 0.1501 (0.1520) loss: 0.8150 (0.8128) time: 0.1592 data: 0.0763 max mem: 9390 +Train: [94] [5600/6250] eta: 0:01:49 lr: 0.000001 grad: 0.1544 (0.1520) loss: 0.8061 (0.8128) time: 0.1847 data: 0.1051 max mem: 9390 +Train: [94] [5700/6250] eta: 0:01:32 lr: 0.000001 grad: 0.1431 (0.1520) loss: 0.8105 (0.8127) time: 0.1818 data: 0.0980 max mem: 9390 +Train: [94] [5800/6250] eta: 0:01:15 lr: 0.000001 grad: 0.1454 (0.1520) loss: 0.8074 (0.8126) time: 0.1672 data: 0.0828 max mem: 9390 +Train: [94] [5900/6250] eta: 0:00:59 lr: 0.000001 grad: 0.1455 (0.1519) loss: 0.8111 (0.8125) time: 0.1697 data: 0.0820 max mem: 9390 +Train: [94] [6000/6250] eta: 0:00:42 lr: 0.000001 grad: 0.1484 (0.1520) loss: 0.8066 (0.8124) time: 0.1707 data: 0.0873 max mem: 9390 +Train: [94] [6100/6250] eta: 0:00:25 lr: 0.000001 grad: 0.1548 (0.1519) loss: 0.8056 (0.8123) time: 0.1687 data: 0.0794 max mem: 9390 +Train: [94] [6200/6250] eta: 0:00:08 lr: 0.000001 grad: 0.1431 (0.1519) loss: 0.8092 (0.8123) time: 0.1585 data: 0.0781 max mem: 9390 +Train: [94] [6249/6250] eta: 0:00:00 lr: 0.000001 grad: 0.1380 (0.1519) loss: 0.8070 (0.8122) time: 0.1988 data: 0.1215 max mem: 9390 +Train: [94] Total time: 0:17:41 (0.1699 s / it) +Averaged stats: lr: 0.000001 grad: 0.1380 (0.1519) loss: 0.8070 (0.8122) +Eval (hcp-train-subset): [94] [ 0/62] eta: 0:04:44 loss: 0.8236 (0.8236) time: 4.5943 data: 4.5657 max mem: 9390 +Eval (hcp-train-subset): [94] [61/62] eta: 0:00:00 loss: 0.8131 (0.8151) time: 0.1212 data: 0.0947 max mem: 9390 +Eval (hcp-train-subset): [94] Total time: 0:00:13 (0.2186 s / it) +Averaged stats (hcp-train-subset): loss: 0.8131 (0.8151) +Making plots (hcp-train-subset): example=17 +Eval (hcp-val): [94] [ 0/62] eta: 0:04:17 loss: 0.8271 (0.8271) time: 4.1607 data: 4.0735 max mem: 9390 +Eval (hcp-val): [94] [61/62] eta: 0:00:00 loss: 0.8262 (0.8280) time: 0.1334 data: 0.1086 max mem: 9390 +Eval (hcp-val): [94] Total time: 0:00:13 (0.2111 s / it) +Averaged stats (hcp-val): loss: 0.8262 (0.8280) +Making plots (hcp-val): example=13 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +Train: [95] [ 0/6250] eta: 7:28:41 lr: 0.000001 grad: 0.1053 (0.1053) loss: 0.8585 (0.8585) time: 4.3074 data: 4.0341 max mem: 9390 +Train: [95] [ 100/6250] eta: 0:21:57 lr: 0.000001 grad: 0.1956 (0.1788) loss: 0.8206 (0.8262) time: 0.1517 data: 0.0581 max mem: 9390 +Train: [95] [ 200/6250] eta: 0:19:37 lr: 0.000001 grad: 0.1601 (0.1809) loss: 0.8159 (0.8176) time: 0.1815 data: 0.0912 max mem: 9390 +Train: [95] [ 300/6250] eta: 0:18:10 lr: 0.000001 grad: 0.1660 (0.1786) loss: 0.8101 (0.8160) time: 0.1549 data: 0.0699 max mem: 9390 +Train: [95] [ 400/6250] eta: 0:17:39 lr: 0.000001 grad: 0.1818 (0.1776) loss: 0.7980 (0.8145) time: 0.1873 data: 0.0893 max mem: 9390 +Train: [95] [ 500/6250] eta: 0:16:58 lr: 0.000001 grad: 0.1597 (0.1766) loss: 0.8091 (0.8136) time: 0.1446 data: 0.0413 max mem: 9390 +Train: [95] [ 600/6250] eta: 0:16:26 lr: 0.000001 grad: 0.1693 (0.1763) loss: 0.8145 (0.8133) time: 0.1713 data: 0.0736 max mem: 9390 +Train: [95] [ 700/6250] eta: 0:16:07 lr: 0.000001 grad: 0.1590 (0.1745) loss: 0.8107 (0.8135) time: 0.2095 data: 0.1147 max mem: 9390 +Train: [95] [ 800/6250] eta: 0:15:49 lr: 0.000001 grad: 0.1460 (0.1722) loss: 0.8196 (0.8138) time: 0.1616 data: 0.0691 max mem: 9390 +Train: [95] [ 900/6250] eta: 0:15:31 lr: 0.000001 grad: 0.1617 (0.1706) loss: 0.8146 (0.8137) time: 0.1705 data: 0.0802 max mem: 9390 +Train: [95] [1000/6250] eta: 0:15:13 lr: 0.000001 grad: 0.1429 (0.1692) loss: 0.8165 (0.8134) time: 0.1669 data: 0.0752 max mem: 9390 +Train: [95] [1100/6250] eta: 0:14:53 lr: 0.000001 grad: 0.1441 (0.1684) loss: 0.8081 (0.8131) time: 0.1546 data: 0.0657 max mem: 9390 +Train: [95] [1200/6250] eta: 0:14:33 lr: 0.000001 grad: 0.1522 (0.1679) loss: 0.8118 (0.8127) time: 0.1607 data: 0.0676 max mem: 9390 +Train: [95] [1300/6250] eta: 0:14:14 lr: 0.000001 grad: 0.1513 (0.1670) loss: 0.8206 (0.8126) time: 0.1830 data: 0.0931 max mem: 9390 +Train: [95] [1400/6250] eta: 0:13:58 lr: 0.000001 grad: 0.1540 (0.1662) loss: 0.8100 (0.8124) time: 0.1733 data: 0.0842 max mem: 9390 +Train: [95] [1500/6250] eta: 0:13:46 lr: 0.000001 grad: 0.1535 (0.1658) loss: 0.8049 (0.8123) time: 0.1662 data: 0.0808 max mem: 9390 +Train: [95] [1600/6250] eta: 0:13:31 lr: 0.000001 grad: 0.1376 (0.1648) loss: 0.8030 (0.8122) time: 0.1855 data: 0.0997 max mem: 9390 +Train: [95] [1700/6250] eta: 0:13:16 lr: 0.000001 grad: 0.1494 (0.1640) loss: 0.8108 (0.8122) time: 0.1884 data: 0.0983 max mem: 9390 +Train: [95] [1800/6250] eta: 0:13:00 lr: 0.000001 grad: 0.1472 (0.1632) loss: 0.8077 (0.8120) time: 0.1976 data: 0.1047 max mem: 9390 +Train: [95] [1900/6250] eta: 0:12:42 lr: 0.000001 grad: 0.1507 (0.1625) loss: 0.8098 (0.8119) time: 0.1732 data: 0.0888 max mem: 9390 +Train: [95] [2000/6250] eta: 0:12:27 lr: 0.000001 grad: 0.1391 (0.1621) loss: 0.8147 (0.8118) time: 0.1743 data: 0.0872 max mem: 9390 +Train: [95] [2100/6250] eta: 0:12:12 lr: 0.000001 grad: 0.1454 (0.1614) loss: 0.8083 (0.8117) time: 0.1850 data: 0.1023 max mem: 9390 +Train: [95] [2200/6250] eta: 0:11:54 lr: 0.000001 grad: 0.1477 (0.1610) loss: 0.8097 (0.8114) time: 0.1542 data: 0.0716 max mem: 9390 +Train: [95] [2300/6250] eta: 0:11:37 lr: 0.000001 grad: 0.1409 (0.1606) loss: 0.8030 (0.8113) time: 0.1844 data: 0.0918 max mem: 9390 +Train: [95] [2400/6250] eta: 0:11:19 lr: 0.000001 grad: 0.1542 (0.1604) loss: 0.8074 (0.8110) time: 0.1769 data: 0.0822 max mem: 9390 +Train: [95] [2500/6250] eta: 0:11:01 lr: 0.000001 grad: 0.1402 (0.1602) loss: 0.8031 (0.8108) time: 0.1742 data: 0.0817 max mem: 9390 +Train: [95] [2600/6250] eta: 0:10:44 lr: 0.000001 grad: 0.1596 (0.1600) loss: 0.8085 (0.8107) time: 0.1665 data: 0.0769 max mem: 9390 +Train: [95] [2700/6250] eta: 0:10:29 lr: 0.000001 grad: 0.1490 (0.1598) loss: 0.8069 (0.8106) time: 0.2251 data: 0.1434 max mem: 9390 +Train: [95] [2800/6250] eta: 0:10:12 lr: 0.000001 grad: 0.1508 (0.1598) loss: 0.8136 (0.8104) time: 0.2026 data: 0.1097 max mem: 9390 +Train: [95] [2900/6250] eta: 0:09:54 lr: 0.000001 grad: 0.1489 (0.1595) loss: 0.8108 (0.8104) time: 0.1701 data: 0.0838 max mem: 9390 +Train: [95] [3000/6250] eta: 0:09:37 lr: 0.000001 grad: 0.1481 (0.1593) loss: 0.8104 (0.8103) time: 0.1777 data: 0.0977 max mem: 9390 +Train: [95] [3100/6250] eta: 0:09:19 lr: 0.000001 grad: 0.1565 (0.1592) loss: 0.8072 (0.8102) time: 0.1551 data: 0.0700 max mem: 9390 +Train: [95] [3200/6250] eta: 0:09:02 lr: 0.000001 grad: 0.1593 (0.1591) loss: 0.8058 (0.8101) time: 0.1790 data: 0.0895 max mem: 9390 +Train: [95] [3300/6250] eta: 0:08:45 lr: 0.000001 grad: 0.1437 (0.1590) loss: 0.8118 (0.8100) time: 0.2016 data: 0.1114 max mem: 9390 +Train: [95] [3400/6250] eta: 0:08:27 lr: 0.000001 grad: 0.1532 (0.1589) loss: 0.8105 (0.8100) time: 0.1669 data: 0.0813 max mem: 9390 +Train: [95] [3500/6250] eta: 0:08:09 lr: 0.000001 grad: 0.1465 (0.1588) loss: 0.8096 (0.8100) time: 0.1781 data: 0.0845 max mem: 9390 +Train: [95] [3600/6250] eta: 0:07:51 lr: 0.000001 grad: 0.1478 (0.1586) loss: 0.8144 (0.8099) time: 0.1843 data: 0.1043 max mem: 9390 +Train: [95] [3700/6250] eta: 0:07:34 lr: 0.000001 grad: 0.1515 (0.1584) loss: 0.8095 (0.8100) time: 0.1822 data: 0.0662 max mem: 9390 +Train: [95] [3800/6250] eta: 0:07:16 lr: 0.000001 grad: 0.1502 (0.1583) loss: 0.8123 (0.8100) time: 0.1890 data: 0.1032 max mem: 9390 +Train: [95] [3900/6250] eta: 0:06:59 lr: 0.000001 grad: 0.1463 (0.1580) loss: 0.8147 (0.8101) time: 0.1731 data: 0.0808 max mem: 9390 +Train: [95] [4000/6250] eta: 0:06:41 lr: 0.000001 grad: 0.1521 (0.1578) loss: 0.8131 (0.8102) time: 0.1693 data: 0.0148 max mem: 9390 +Train: [95] [4100/6250] eta: 0:06:24 lr: 0.000001 grad: 0.1628 (0.1578) loss: 0.8075 (0.8102) time: 0.2013 data: 0.1108 max mem: 9390 +Train: [95] [4200/6250] eta: 0:06:06 lr: 0.000001 grad: 0.1477 (0.1577) loss: 0.8161 (0.8102) time: 0.1871 data: 0.0996 max mem: 9390 +Train: [95] [4300/6250] eta: 0:05:48 lr: 0.000001 grad: 0.1476 (0.1577) loss: 0.8047 (0.8102) time: 0.1977 data: 0.1043 max mem: 9390 +Train: [95] [4400/6250] eta: 0:05:30 lr: 0.000001 grad: 0.1528 (0.1577) loss: 0.8086 (0.8102) time: 0.1776 data: 0.0761 max mem: 9390 +Train: [95] [4500/6250] eta: 0:05:13 lr: 0.000001 grad: 0.1462 (0.1577) loss: 0.8074 (0.8101) time: 0.1837 data: 0.0990 max mem: 9390 +Train: [95] [4600/6250] eta: 0:04:54 lr: 0.000001 grad: 0.1499 (0.1576) loss: 0.8094 (0.8100) time: 0.1745 data: 0.0835 max mem: 9390 +Train: [95] [4700/6250] eta: 0:04:36 lr: 0.000001 grad: 0.1572 (0.1576) loss: 0.8038 (0.8100) time: 0.1821 data: 0.0758 max mem: 9390 +Train: [95] [4800/6250] eta: 0:04:19 lr: 0.000001 grad: 0.1560 (0.1575) loss: 0.8134 (0.8099) time: 0.2030 data: 0.1167 max mem: 9390 +Train: [95] [4900/6250] eta: 0:04:01 lr: 0.000001 grad: 0.1313 (0.1574) loss: 0.8104 (0.8099) time: 0.1857 data: 0.0870 max mem: 9390 +Train: [95] [5000/6250] eta: 0:03:44 lr: 0.000001 grad: 0.1334 (0.1573) loss: 0.8121 (0.8099) time: 0.2074 data: 0.1229 max mem: 9390 +Train: [95] [5100/6250] eta: 0:03:26 lr: 0.000001 grad: 0.1490 (0.1571) loss: 0.8102 (0.8099) time: 0.1956 data: 0.1206 max mem: 9390 +Train: [95] [5200/6250] eta: 0:03:08 lr: 0.000001 grad: 0.1531 (0.1570) loss: 0.8064 (0.8099) time: 0.1779 data: 0.0772 max mem: 9390 +Train: [95] [5300/6250] eta: 0:02:50 lr: 0.000001 grad: 0.1470 (0.1569) loss: 0.8111 (0.8100) time: 0.1662 data: 0.0819 max mem: 9390 +Train: [95] [5400/6250] eta: 0:02:32 lr: 0.000001 grad: 0.1472 (0.1567) loss: 0.8113 (0.8100) time: 0.1647 data: 0.0745 max mem: 9390 +Train: [95] [5500/6250] eta: 0:02:14 lr: 0.000001 grad: 0.1527 (0.1566) loss: 0.8164 (0.8100) time: 0.1505 data: 0.0481 max mem: 9390 +Train: [95] [5600/6250] eta: 0:01:56 lr: 0.000001 grad: 0.1403 (0.1565) loss: 0.8124 (0.8101) time: 0.1697 data: 0.0698 max mem: 9390 +Train: [95] [5700/6250] eta: 0:01:38 lr: 0.000001 grad: 0.1466 (0.1565) loss: 0.8128 (0.8101) time: 0.1940 data: 0.1200 max mem: 9390 +Train: [95] [5800/6250] eta: 0:01:20 lr: 0.000001 grad: 0.1498 (0.1565) loss: 0.8115 (0.8100) time: 0.1982 data: 0.1056 max mem: 9390 +Train: [95] [5900/6250] eta: 0:01:02 lr: 0.000001 grad: 0.1307 (0.1563) loss: 0.8169 (0.8101) time: 0.1921 data: 0.1016 max mem: 9390 +Train: [95] [6000/6250] eta: 0:00:44 lr: 0.000001 grad: 0.1413 (0.1562) loss: 0.8132 (0.8101) time: 0.1970 data: 0.1143 max mem: 9390 +Train: [95] [6100/6250] eta: 0:00:26 lr: 0.000001 grad: 0.1451 (0.1561) loss: 0.8176 (0.8102) time: 0.1662 data: 0.0794 max mem: 9390 +Train: [95] [6200/6250] eta: 0:00:08 lr: 0.000001 grad: 0.1507 (0.1560) loss: 0.8160 (0.8102) time: 0.1997 data: 0.1165 max mem: 9390 +Train: [95] [6249/6250] eta: 0:00:00 lr: 0.000001 grad: 0.1460 (0.1559) loss: 0.8137 (0.8103) time: 0.1721 data: 0.0941 max mem: 9390 +Train: [95] Total time: 0:18:49 (0.1808 s / it) +Averaged stats: lr: 0.000001 grad: 0.1460 (0.1559) loss: 0.8137 (0.8103) +Eval (hcp-train-subset): [95] [ 0/62] eta: 0:05:27 loss: 0.8211 (0.8211) time: 5.2863 data: 5.2211 max mem: 9390 +Eval (hcp-train-subset): [95] [61/62] eta: 0:00:00 loss: 0.8100 (0.8147) time: 0.1369 data: 0.1118 max mem: 9390 +Eval (hcp-train-subset): [95] Total time: 0:00:13 (0.2210 s / it) +Averaged stats (hcp-train-subset): loss: 0.8100 (0.8147) +Eval (hcp-val): [95] [ 0/62] eta: 0:04:19 loss: 0.8265 (0.8265) time: 4.1839 data: 4.1483 max mem: 9390 +Eval (hcp-val): [95] [61/62] eta: 0:00:00 loss: 0.8252 (0.8276) time: 0.1216 data: 0.0952 max mem: 9390 +Eval (hcp-val): [95] Total time: 0:00:12 (0.2043 s / it) +Averaged stats (hcp-val): loss: 0.8252 (0.8276) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +Train: [96] [ 0/6250] eta: 9:48:33 lr: 0.000001 grad: 0.1712 (0.1712) loss: 0.7675 (0.7675) time: 5.6502 data: 5.4688 max mem: 9390 +Train: [96] [ 100/6250] eta: 0:22:28 lr: 0.000001 grad: 0.1585 (0.1621) loss: 0.8215 (0.8233) time: 0.1491 data: 0.0651 max mem: 9390 +Train: [96] [ 200/6250] eta: 0:19:36 lr: 0.000001 grad: 0.1437 (0.1599) loss: 0.8190 (0.8216) time: 0.1667 data: 0.0745 max mem: 9390 +Train: [96] [ 300/6250] eta: 0:18:42 lr: 0.000001 grad: 0.1385 (0.1575) loss: 0.8244 (0.8218) time: 0.1636 data: 0.0838 max mem: 9390 +Train: [96] [ 400/6250] eta: 0:18:03 lr: 0.000001 grad: 0.1306 (0.1560) loss: 0.8125 (0.8209) time: 0.1475 data: 0.0627 max mem: 9390 +Train: [96] [ 500/6250] eta: 0:17:33 lr: 0.000001 grad: 0.1543 (0.1560) loss: 0.8182 (0.8200) time: 0.1700 data: 0.0716 max mem: 9390 +Train: [96] [ 600/6250] eta: 0:17:01 lr: 0.000001 grad: 0.1384 (0.1556) loss: 0.8158 (0.8184) time: 0.2048 data: 0.0934 max mem: 9390 +Train: [96] [ 700/6250] eta: 0:16:41 lr: 0.000001 grad: 0.1575 (0.1554) loss: 0.8083 (0.8173) time: 0.1578 data: 0.0590 max mem: 9390 +Train: [96] [ 800/6250] eta: 0:16:17 lr: 0.000001 grad: 0.1493 (0.1549) loss: 0.8167 (0.8164) time: 0.1960 data: 0.0825 max mem: 9390 +Train: [96] [ 900/6250] eta: 0:15:49 lr: 0.000001 grad: 0.1490 (0.1543) loss: 0.8103 (0.8158) time: 0.1585 data: 0.0653 max mem: 9390 +Train: [96] [1000/6250] eta: 0:15:22 lr: 0.000001 grad: 0.1400 (0.1537) loss: 0.8125 (0.8154) time: 0.1492 data: 0.0547 max mem: 9390 +Train: [96] [1100/6250] eta: 0:15:08 lr: 0.000000 grad: 0.1400 (0.1531) loss: 0.8142 (0.8152) time: 0.1939 data: 0.0924 max mem: 9390 +Train: [96] [1200/6250] eta: 0:14:54 lr: 0.000000 grad: 0.1433 (0.1529) loss: 0.8125 (0.8149) time: 0.1625 data: 0.0730 max mem: 9390 +Train: [96] [1300/6250] eta: 0:14:33 lr: 0.000000 grad: 0.1482 (0.1527) loss: 0.8021 (0.8143) time: 0.1339 data: 0.0470 max mem: 9390 +Train: [96] [1400/6250] eta: 0:14:14 lr: 0.000000 grad: 0.1545 (0.1526) loss: 0.8174 (0.8139) time: 0.1829 data: 0.0953 max mem: 9390 +Train: [96] [1500/6250] eta: 0:13:53 lr: 0.000000 grad: 0.1450 (0.1523) loss: 0.8179 (0.8137) time: 0.1753 data: 0.0836 max mem: 9390 +Train: [96] [1600/6250] eta: 0:13:34 lr: 0.000000 grad: 0.1415 (0.1522) loss: 0.8183 (0.8134) time: 0.1815 data: 0.0822 max mem: 9390 +Train: [96] [1700/6250] eta: 0:13:16 lr: 0.000000 grad: 0.1323 (0.1517) loss: 0.8149 (0.8134) time: 0.1871 data: 0.0900 max mem: 9390 +Train: [96] [1800/6250] eta: 0:12:58 lr: 0.000000 grad: 0.1419 (0.1513) loss: 0.8192 (0.8133) time: 0.1792 data: 0.0898 max mem: 9390 +Train: [96] [1900/6250] eta: 0:12:38 lr: 0.000000 grad: 0.1325 (0.1509) loss: 0.8123 (0.8131) time: 0.1606 data: 0.0590 max mem: 9390 +Train: [96] [2000/6250] eta: 0:12:20 lr: 0.000000 grad: 0.1399 (0.1506) loss: 0.8159 (0.8131) time: 0.1744 data: 0.0978 max mem: 9390 +Train: [96] [2100/6250] eta: 0:12:05 lr: 0.000000 grad: 0.1444 (0.1506) loss: 0.8143 (0.8130) time: 0.1960 data: 0.0980 max mem: 9390 +Train: [96] [2200/6250] eta: 0:11:48 lr: 0.000000 grad: 0.1391 (0.1504) loss: 0.8127 (0.8130) time: 0.1758 data: 0.0831 max mem: 9390 +Train: [96] [2300/6250] eta: 0:11:29 lr: 0.000000 grad: 0.1344 (0.1501) loss: 0.8183 (0.8131) time: 0.1508 data: 0.0592 max mem: 9390 +Train: [96] [2400/6250] eta: 0:11:09 lr: 0.000000 grad: 0.1356 (0.1500) loss: 0.8090 (0.8130) time: 0.1598 data: 0.0723 max mem: 9390 +Train: [96] [2500/6250] eta: 0:10:50 lr: 0.000000 grad: 0.1436 (0.1499) loss: 0.8151 (0.8130) time: 0.1517 data: 0.0671 max mem: 9390 +Train: [96] [2600/6250] eta: 0:10:32 lr: 0.000000 grad: 0.1482 (0.1498) loss: 0.8130 (0.8129) time: 0.1825 data: 0.0947 max mem: 9390 +Train: [96] [2700/6250] eta: 0:10:14 lr: 0.000000 grad: 0.1388 (0.1498) loss: 0.8123 (0.8128) time: 0.1680 data: 0.0783 max mem: 9390 +Train: [96] [2800/6250] eta: 0:09:56 lr: 0.000000 grad: 0.1448 (0.1498) loss: 0.8075 (0.8128) time: 0.1775 data: 0.0828 max mem: 9390 +Train: [96] [2900/6250] eta: 0:09:38 lr: 0.000000 grad: 0.1374 (0.1497) loss: 0.8158 (0.8127) time: 0.1754 data: 0.0880 max mem: 9390 +Train: [96] [3000/6250] eta: 0:09:21 lr: 0.000000 grad: 0.1354 (0.1495) loss: 0.8164 (0.8129) time: 0.1656 data: 0.0770 max mem: 9390 +Train: [96] [3100/6250] eta: 0:09:03 lr: 0.000000 grad: 0.1409 (0.1493) loss: 0.8132 (0.8129) time: 0.1563 data: 0.0650 max mem: 9390 +Train: [96] [3200/6250] eta: 0:08:45 lr: 0.000000 grad: 0.1442 (0.1491) loss: 0.8121 (0.8130) time: 0.1534 data: 0.0659 max mem: 9390 +Train: [96] [3300/6250] eta: 0:08:27 lr: 0.000000 grad: 0.1423 (0.1490) loss: 0.8192 (0.8131) time: 0.1687 data: 0.0790 max mem: 9390 +Train: [96] [3400/6250] eta: 0:08:09 lr: 0.000000 grad: 0.1535 (0.1490) loss: 0.8166 (0.8132) time: 0.1646 data: 0.0797 max mem: 9390 +Train: [96] [3500/6250] eta: 0:07:51 lr: 0.000000 grad: 0.1456 (0.1490) loss: 0.8148 (0.8132) time: 0.1684 data: 0.0811 max mem: 9390 +Train: [96] [3600/6250] eta: 0:07:34 lr: 0.000000 grad: 0.1395 (0.1490) loss: 0.8129 (0.8132) time: 0.1795 data: 0.0818 max mem: 9390 +Train: [96] [3700/6250] eta: 0:07:16 lr: 0.000000 grad: 0.1429 (0.1489) loss: 0.8154 (0.8133) time: 0.1551 data: 0.0615 max mem: 9390 +Train: [96] [3800/6250] eta: 0:06:58 lr: 0.000000 grad: 0.1349 (0.1488) loss: 0.8191 (0.8134) time: 0.1544 data: 0.0647 max mem: 9390 +Train: [96] [3900/6250] eta: 0:06:41 lr: 0.000000 grad: 0.1342 (0.1487) loss: 0.8183 (0.8135) time: 0.1745 data: 0.0881 max mem: 9390 +Train: [96] [4000/6250] eta: 0:06:23 lr: 0.000000 grad: 0.1362 (0.1485) loss: 0.8108 (0.8136) time: 0.1185 data: 0.0322 max mem: 9390 +Train: [96] [4100/6250] eta: 0:06:06 lr: 0.000000 grad: 0.1370 (0.1484) loss: 0.8207 (0.8138) time: 0.1363 data: 0.0440 max mem: 9390 +Train: [96] [4200/6250] eta: 0:05:49 lr: 0.000000 grad: 0.1368 (0.1484) loss: 0.8203 (0.8138) time: 0.1733 data: 0.0838 max mem: 9390 +Train: [96] [4300/6250] eta: 0:05:32 lr: 0.000000 grad: 0.1420 (0.1483) loss: 0.8166 (0.8139) time: 0.1780 data: 0.0925 max mem: 9390 +Train: [96] [4400/6250] eta: 0:05:14 lr: 0.000000 grad: 0.1453 (0.1483) loss: 0.8176 (0.8139) time: 0.1530 data: 0.0698 max mem: 9390 +Train: [96] [4500/6250] eta: 0:04:57 lr: 0.000000 grad: 0.1282 (0.1483) loss: 0.8215 (0.8140) time: 0.1677 data: 0.0781 max mem: 9390 +Train: [96] [4600/6250] eta: 0:04:40 lr: 0.000000 grad: 0.1411 (0.1483) loss: 0.8227 (0.8140) time: 0.1702 data: 0.0831 max mem: 9390 +Train: [96] [4700/6250] eta: 0:04:23 lr: 0.000000 grad: 0.1403 (0.1483) loss: 0.8184 (0.8140) time: 0.1480 data: 0.0589 max mem: 9390 +Train: [96] [4800/6250] eta: 0:04:05 lr: 0.000000 grad: 0.1567 (0.1484) loss: 0.8154 (0.8140) time: 0.1406 data: 0.0530 max mem: 9390 +Train: [96] [4900/6250] eta: 0:03:48 lr: 0.000000 grad: 0.1383 (0.1483) loss: 0.8142 (0.8140) time: 0.1563 data: 0.0724 max mem: 9390 +Train: [96] [5000/6250] eta: 0:03:31 lr: 0.000000 grad: 0.1454 (0.1483) loss: 0.8159 (0.8140) time: 0.1577 data: 0.0735 max mem: 9390 +Train: [96] [5100/6250] eta: 0:03:14 lr: 0.000000 grad: 0.1470 (0.1483) loss: 0.8135 (0.8140) time: 0.1476 data: 0.0591 max mem: 9390 +Train: [96] [5200/6250] eta: 0:02:57 lr: 0.000000 grad: 0.1524 (0.1484) loss: 0.8083 (0.8140) time: 0.1887 data: 0.1053 max mem: 9390 +Train: [96] [5300/6250] eta: 0:02:40 lr: 0.000000 grad: 0.1513 (0.1487) loss: 0.8132 (0.8139) time: 0.1419 data: 0.0525 max mem: 9390 +Train: [96] [5400/6250] eta: 0:02:23 lr: 0.000000 grad: 0.1390 (0.1487) loss: 0.8130 (0.8138) time: 0.1691 data: 0.0813 max mem: 9390 +Train: [96] [5500/6250] eta: 0:02:06 lr: 0.000000 grad: 0.1481 (0.1488) loss: 0.8096 (0.8138) time: 0.1870 data: 0.0938 max mem: 9390 +Train: [96] [5600/6250] eta: 0:01:49 lr: 0.000000 grad: 0.1466 (0.1489) loss: 0.8135 (0.8137) time: 0.1712 data: 0.0882 max mem: 9390 +Train: [96] [5700/6250] eta: 0:01:32 lr: 0.000000 grad: 0.1381 (0.1489) loss: 0.8187 (0.8137) time: 0.1673 data: 0.0793 max mem: 9390 +Train: [96] [5800/6250] eta: 0:01:15 lr: 0.000000 grad: 0.1407 (0.1490) loss: 0.8163 (0.8137) time: 0.1316 data: 0.0414 max mem: 9390 +Train: [96] [5900/6250] eta: 0:00:59 lr: 0.000000 grad: 0.1473 (0.1490) loss: 0.8176 (0.8137) time: 0.1615 data: 0.0690 max mem: 9390 +Train: [96] [6000/6250] eta: 0:00:42 lr: 0.000000 grad: 0.1614 (0.1491) loss: 0.8124 (0.8137) time: 0.1628 data: 0.0731 max mem: 9390 +Train: [96] [6100/6250] eta: 0:00:25 lr: 0.000000 grad: 0.1400 (0.1492) loss: 0.8122 (0.8137) time: 0.1898 data: 0.1029 max mem: 9390 +Train: [96] [6200/6250] eta: 0:00:08 lr: 0.000000 grad: 0.1406 (0.1493) loss: 0.8072 (0.8137) time: 0.1956 data: 0.1143 max mem: 9390 +Train: [96] [6249/6250] eta: 0:00:00 lr: 0.000000 grad: 0.1465 (0.1493) loss: 0.8161 (0.8137) time: 0.1753 data: 0.0888 max mem: 9390 +Train: [96] Total time: 0:17:40 (0.1696 s / it) +Averaged stats: lr: 0.000000 grad: 0.1465 (0.1493) loss: 0.8161 (0.8137) +Eval (hcp-train-subset): [96] [ 0/62] eta: 0:04:06 loss: 0.8244 (0.8244) time: 3.9724 data: 3.9419 max mem: 9390 +Eval (hcp-train-subset): [96] [61/62] eta: 0:00:00 loss: 0.8119 (0.8147) time: 0.1129 data: 0.0880 max mem: 9390 +Eval (hcp-train-subset): [96] Total time: 0:00:13 (0.2173 s / it) +Averaged stats (hcp-train-subset): loss: 0.8119 (0.8147) +Eval (hcp-val): [96] [ 0/62] eta: 0:04:28 loss: 0.8234 (0.8234) time: 4.3317 data: 4.3016 max mem: 9390 +Eval (hcp-val): [96] [61/62] eta: 0:00:00 loss: 0.8269 (0.8279) time: 0.1496 data: 0.1236 max mem: 9390 +Eval (hcp-val): [96] Total time: 0:00:13 (0.2119 s / it) +Averaged stats (hcp-val): loss: 0.8269 (0.8279) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +Train: [97] [ 0/6250] eta: 10:46:11 lr: 0.000000 grad: 0.2545 (0.2545) loss: 0.7763 (0.7763) time: 6.2034 data: 6.0884 max mem: 9390 +Train: [97] [ 100/6250] eta: 0:22:37 lr: 0.000000 grad: 0.1585 (0.1751) loss: 0.8178 (0.8222) time: 0.1684 data: 0.0739 max mem: 9390 +Train: [97] [ 200/6250] eta: 0:19:58 lr: 0.000000 grad: 0.1731 (0.1724) loss: 0.8057 (0.8205) time: 0.1768 data: 0.0850 max mem: 9390 +Train: [97] [ 300/6250] eta: 0:18:42 lr: 0.000000 grad: 0.1667 (0.1737) loss: 0.8083 (0.8170) time: 0.1553 data: 0.0588 max mem: 9390 +Train: [97] [ 400/6250] eta: 0:17:47 lr: 0.000000 grad: 0.1670 (0.1731) loss: 0.8031 (0.8143) time: 0.1772 data: 0.0841 max mem: 9390 +Train: [97] [ 500/6250] eta: 0:17:20 lr: 0.000000 grad: 0.1481 (0.1712) loss: 0.8072 (0.8128) time: 0.2065 data: 0.1149 max mem: 9390 +Train: [97] [ 600/6250] eta: 0:16:42 lr: 0.000000 grad: 0.1427 (0.1694) loss: 0.8112 (0.8128) time: 0.1841 data: 0.0882 max mem: 9390 +Train: [97] [ 700/6250] eta: 0:16:25 lr: 0.000000 grad: 0.1539 (0.1685) loss: 0.8144 (0.8126) time: 0.2022 data: 0.1130 max mem: 9390 +Train: [97] [ 800/6250] eta: 0:16:05 lr: 0.000000 grad: 0.1438 (0.1670) loss: 0.8158 (0.8125) time: 0.1884 data: 0.0972 max mem: 9390 +Train: [97] [ 900/6250] eta: 0:15:45 lr: 0.000000 grad: 0.1584 (0.1661) loss: 0.8111 (0.8126) time: 0.1961 data: 0.1029 max mem: 9390 +Train: [97] [1000/6250] eta: 0:15:23 lr: 0.000000 grad: 0.1484 (0.1652) loss: 0.8127 (0.8127) time: 0.1840 data: 0.0936 max mem: 9390 +Train: [97] [1100/6250] eta: 0:14:59 lr: 0.000000 grad: 0.1436 (0.1639) loss: 0.8150 (0.8129) time: 0.1683 data: 0.0827 max mem: 9390 +Train: [97] [1200/6250] eta: 0:14:35 lr: 0.000000 grad: 0.1548 (0.1631) loss: 0.8142 (0.8130) time: 0.1577 data: 0.0694 max mem: 9390 +Train: [97] [1300/6250] eta: 0:14:16 lr: 0.000000 grad: 0.1483 (0.1622) loss: 0.8131 (0.8131) time: 0.1810 data: 0.0916 max mem: 9390 +Train: [97] [1400/6250] eta: 0:13:56 lr: 0.000000 grad: 0.1476 (0.1615) loss: 0.8160 (0.8131) time: 0.1736 data: 0.0918 max mem: 9390 +Train: [97] [1500/6250] eta: 0:13:34 lr: 0.000000 grad: 0.1445 (0.1610) loss: 0.8168 (0.8132) time: 0.1633 data: 0.0718 max mem: 9390 +Train: [97] [1600/6250] eta: 0:13:15 lr: 0.000000 grad: 0.1597 (0.1605) loss: 0.8097 (0.8131) time: 0.1547 data: 0.0651 max mem: 9390 +Train: [97] [1700/6250] eta: 0:12:59 lr: 0.000000 grad: 0.1478 (0.1600) loss: 0.8143 (0.8129) time: 0.1494 data: 0.0532 max mem: 9390 +Train: [97] [1800/6250] eta: 0:12:39 lr: 0.000000 grad: 0.1507 (0.1597) loss: 0.8103 (0.8127) time: 0.1666 data: 0.0806 max mem: 9390 +Train: [97] [1900/6250] eta: 0:12:20 lr: 0.000000 grad: 0.1498 (0.1596) loss: 0.8105 (0.8124) time: 0.1632 data: 0.0704 max mem: 9390 +Train: [97] [2000/6250] eta: 0:12:01 lr: 0.000000 grad: 0.1651 (0.1592) loss: 0.8163 (0.8123) time: 0.1746 data: 0.0860 max mem: 9390 +Train: [97] [2100/6250] eta: 0:11:42 lr: 0.000000 grad: 0.1475 (0.1592) loss: 0.8079 (0.8122) time: 0.1659 data: 0.0839 max mem: 9390 +Train: [97] [2200/6250] eta: 0:11:24 lr: 0.000000 grad: 0.1517 (0.1589) loss: 0.8098 (0.8122) time: 0.1525 data: 0.0673 max mem: 9390 +Train: [97] [2300/6250] eta: 0:11:07 lr: 0.000000 grad: 0.1510 (0.1586) loss: 0.8080 (0.8122) time: 0.1531 data: 0.0649 max mem: 9390 +Train: [97] [2400/6250] eta: 0:10:50 lr: 0.000000 grad: 0.1473 (0.1588) loss: 0.8093 (0.8120) time: 0.1523 data: 0.0673 max mem: 9390 +Train: [97] [2500/6250] eta: 0:10:32 lr: 0.000000 grad: 0.1464 (0.1587) loss: 0.8166 (0.8119) time: 0.1405 data: 0.0501 max mem: 9390 +Train: [97] [2600/6250] eta: 0:10:14 lr: 0.000000 grad: 0.1402 (0.1585) loss: 0.8155 (0.8120) time: 0.1455 data: 0.0570 max mem: 9390 +Train: [97] [2700/6250] eta: 0:09:57 lr: 0.000000 grad: 0.1427 (0.1582) loss: 0.8191 (0.8121) time: 0.1798 data: 0.0955 max mem: 9390 +Train: [97] [2800/6250] eta: 0:09:39 lr: 0.000000 grad: 0.1393 (0.1579) loss: 0.8150 (0.8122) time: 0.1588 data: 0.0718 max mem: 9390 +Train: [97] [2900/6250] eta: 0:09:22 lr: 0.000000 grad: 0.1544 (0.1577) loss: 0.8143 (0.8123) time: 0.1738 data: 0.0894 max mem: 9390 +Train: [97] [3000/6250] eta: 0:09:06 lr: 0.000000 grad: 0.1443 (0.1574) loss: 0.8147 (0.8123) time: 0.1555 data: 0.0623 max mem: 9390 +Train: [97] [3100/6250] eta: 0:08:48 lr: 0.000000 grad: 0.1418 (0.1571) loss: 0.8175 (0.8125) time: 0.1634 data: 0.0730 max mem: 9390 +Train: [97] [3200/6250] eta: 0:08:32 lr: 0.000000 grad: 0.1532 (0.1569) loss: 0.8140 (0.8125) time: 0.1856 data: 0.1099 max mem: 9390 +Train: [97] [3300/6250] eta: 0:08:15 lr: 0.000000 grad: 0.1500 (0.1566) loss: 0.8179 (0.8126) time: 0.1633 data: 0.0740 max mem: 9390 +Train: [97] [3400/6250] eta: 0:07:58 lr: 0.000000 grad: 0.1398 (0.1565) loss: 0.8124 (0.8126) time: 0.1667 data: 0.0782 max mem: 9390 +Train: [97] [3500/6250] eta: 0:07:41 lr: 0.000000 grad: 0.1492 (0.1563) loss: 0.8113 (0.8126) time: 0.1872 data: 0.1003 max mem: 9390 +Train: [97] [3600/6250] eta: 0:07:24 lr: 0.000000 grad: 0.1460 (0.1561) loss: 0.8100 (0.8126) time: 0.1883 data: 0.1023 max mem: 9390 +Train: [97] [3700/6250] eta: 0:07:07 lr: 0.000000 grad: 0.1502 (0.1560) loss: 0.8081 (0.8126) time: 0.1538 data: 0.0670 max mem: 9390 +Train: [97] [3800/6250] eta: 0:06:50 lr: 0.000000 grad: 0.1466 (0.1559) loss: 0.8185 (0.8127) time: 0.1422 data: 0.0542 max mem: 9390 +Train: [97] [3900/6250] eta: 0:06:33 lr: 0.000000 grad: 0.1420 (0.1558) loss: 0.8112 (0.8126) time: 0.1726 data: 0.0900 max mem: 9390 +Train: [97] [4000/6250] eta: 0:06:16 lr: 0.000000 grad: 0.1553 (0.1557) loss: 0.8107 (0.8126) time: 0.1568 data: 0.0661 max mem: 9390 +Train: [97] [4100/6250] eta: 0:06:00 lr: 0.000000 grad: 0.1445 (0.1557) loss: 0.8132 (0.8126) time: 0.1822 data: 0.0957 max mem: 9390 +Train: [97] [4200/6250] eta: 0:05:43 lr: 0.000000 grad: 0.1339 (0.1555) loss: 0.8243 (0.8126) time: 0.1623 data: 0.0704 max mem: 9390 +Train: [97] [4300/6250] eta: 0:05:26 lr: 0.000000 grad: 0.1425 (0.1554) loss: 0.8191 (0.8127) time: 0.1699 data: 0.0831 max mem: 9390 +Train: [97] [4400/6250] eta: 0:05:09 lr: 0.000000 grad: 0.1479 (0.1555) loss: 0.8174 (0.8127) time: 0.1714 data: 0.0758 max mem: 9390 +Train: [97] [4500/6250] eta: 0:04:53 lr: 0.000000 grad: 0.1466 (0.1555) loss: 0.8129 (0.8127) time: 0.1895 data: 0.1049 max mem: 9390 +Train: [97] [4600/6250] eta: 0:04:36 lr: 0.000000 grad: 0.1444 (0.1554) loss: 0.8148 (0.8127) time: 0.1817 data: 0.0981 max mem: 9390 +Train: [97] [4700/6250] eta: 0:04:19 lr: 0.000000 grad: 0.1468 (0.1553) loss: 0.8154 (0.8127) time: 0.1659 data: 0.0787 max mem: 9390 +Train: [97] [4800/6250] eta: 0:04:02 lr: 0.000000 grad: 0.1459 (0.1552) loss: 0.8100 (0.8127) time: 0.1446 data: 0.0540 max mem: 9390 +Train: [97] [4900/6250] eta: 0:03:45 lr: 0.000000 grad: 0.1512 (0.1551) loss: 0.8114 (0.8126) time: 0.1589 data: 0.0709 max mem: 9390 +Train: [97] [5000/6250] eta: 0:03:29 lr: 0.000000 grad: 0.1436 (0.1550) loss: 0.8146 (0.8126) time: 0.1747 data: 0.0901 max mem: 9390 +Train: [97] [5100/6250] eta: 0:03:12 lr: 0.000000 grad: 0.1475 (0.1549) loss: 0.8155 (0.8126) time: 0.1781 data: 0.0978 max mem: 9390 +Train: [97] [5200/6250] eta: 0:02:55 lr: 0.000000 grad: 0.1546 (0.1549) loss: 0.8079 (0.8125) time: 0.1625 data: 0.0722 max mem: 9390 +Train: [97] [5300/6250] eta: 0:02:38 lr: 0.000000 grad: 0.1437 (0.1548) loss: 0.8204 (0.8126) time: 0.1796 data: 0.0917 max mem: 9390 +Train: [97] [5400/6250] eta: 0:02:22 lr: 0.000000 grad: 0.1477 (0.1547) loss: 0.8103 (0.8126) time: 0.1708 data: 0.0891 max mem: 9390 +Train: [97] [5500/6250] eta: 0:02:05 lr: 0.000000 grad: 0.1391 (0.1546) loss: 0.8134 (0.8126) time: 0.1682 data: 0.0781 max mem: 9390 +Train: [97] [5600/6250] eta: 0:01:48 lr: 0.000000 grad: 0.1417 (0.1546) loss: 0.8143 (0.8126) time: 0.2047 data: 0.1118 max mem: 9390 +Train: [97] [5700/6250] eta: 0:01:31 lr: 0.000000 grad: 0.1422 (0.1545) loss: 0.8186 (0.8126) time: 0.1729 data: 0.0785 max mem: 9390 +Train: [97] [5800/6250] eta: 0:01:15 lr: 0.000000 grad: 0.1467 (0.1544) loss: 0.8145 (0.8126) time: 0.1440 data: 0.0599 max mem: 9390 +Train: [97] [5900/6250] eta: 0:00:58 lr: 0.000000 grad: 0.1353 (0.1543) loss: 0.8184 (0.8126) time: 0.1780 data: 0.0861 max mem: 9390 +Train: [97] [6000/6250] eta: 0:00:41 lr: 0.000000 grad: 0.1526 (0.1542) loss: 0.8125 (0.8126) time: 0.1700 data: 0.0893 max mem: 9390 +Train: [97] [6100/6250] eta: 0:00:24 lr: 0.000000 grad: 0.1440 (0.1541) loss: 0.8116 (0.8126) time: 0.1710 data: 0.0747 max mem: 9390 +Train: [97] [6200/6250] eta: 0:00:08 lr: 0.000000 grad: 0.1515 (0.1540) loss: 0.8107 (0.8127) time: 0.1747 data: 0.0821 max mem: 9390 +Train: [97] [6249/6250] eta: 0:00:00 lr: 0.000000 grad: 0.1448 (0.1540) loss: 0.8130 (0.8127) time: 0.1807 data: 0.0953 max mem: 9390 +Train: [97] Total time: 0:17:30 (0.1680 s / it) +Averaged stats: lr: 0.000000 grad: 0.1448 (0.1540) loss: 0.8130 (0.8127) +Eval (hcp-train-subset): [97] [ 0/62] eta: 0:05:48 loss: 0.8194 (0.8194) time: 5.6272 data: 5.5952 max mem: 9390 +Eval (hcp-train-subset): [97] [61/62] eta: 0:00:00 loss: 0.8098 (0.8143) time: 0.1252 data: 0.0979 max mem: 9390 +Eval (hcp-train-subset): [97] Total time: 0:00:13 (0.2248 s / it) +Averaged stats (hcp-train-subset): loss: 0.8098 (0.8143) +Eval (hcp-val): [97] [ 0/62] eta: 0:04:21 loss: 0.8235 (0.8235) time: 4.2232 data: 4.1941 max mem: 9390 +Eval (hcp-val): [97] [61/62] eta: 0:00:00 loss: 0.8273 (0.8278) time: 0.1337 data: 0.1084 max mem: 9390 +Eval (hcp-val): [97] Total time: 0:00:12 (0.2078 s / it) +Averaged stats (hcp-val): loss: 0.8273 (0.8278) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +Train: [98] [ 0/6250] eta: 8:51:12 lr: 0.000000 grad: 0.0782 (0.0782) loss: 0.8606 (0.8606) time: 5.0996 data: 4.7857 max mem: 9390 +Train: [98] [ 100/6250] eta: 0:22:08 lr: 0.000000 grad: 0.1512 (0.1738) loss: 0.8249 (0.8292) time: 0.1711 data: 0.0781 max mem: 9390 +Train: [98] [ 200/6250] eta: 0:19:48 lr: 0.000000 grad: 0.1380 (0.1673) loss: 0.8240 (0.8253) time: 0.1841 data: 0.0839 max mem: 9390 +Train: [98] [ 300/6250] eta: 0:18:32 lr: 0.000000 grad: 0.1404 (0.1628) loss: 0.8179 (0.8234) time: 0.1791 data: 0.0737 max mem: 9390 +Train: [98] [ 400/6250] eta: 0:17:39 lr: 0.000000 grad: 0.1376 (0.1599) loss: 0.8185 (0.8218) time: 0.1608 data: 0.0497 max mem: 9390 +Train: [98] [ 500/6250] eta: 0:17:04 lr: 0.000000 grad: 0.1524 (0.1593) loss: 0.8167 (0.8200) time: 0.1329 data: 0.0048 max mem: 9390 +Train: [98] [ 600/6250] eta: 0:16:54 lr: 0.000000 grad: 0.1601 (0.1596) loss: 0.8087 (0.8183) time: 0.1697 data: 0.0733 max mem: 9390 +Train: [98] [ 700/6250] eta: 0:16:46 lr: 0.000000 grad: 0.1557 (0.1601) loss: 0.8157 (0.8167) time: 0.1830 data: 0.0894 max mem: 9390 +Train: [98] [ 800/6250] eta: 0:16:32 lr: 0.000000 grad: 0.1555 (0.1601) loss: 0.8112 (0.8156) time: 0.1850 data: 0.0895 max mem: 9390 +Train: [98] [ 900/6250] eta: 0:16:17 lr: 0.000000 grad: 0.1541 (0.1597) loss: 0.8053 (0.8149) time: 0.2082 data: 0.1125 max mem: 9390 +Train: [98] [1000/6250] eta: 0:15:54 lr: 0.000000 grad: 0.1486 (0.1592) loss: 0.8160 (0.8145) time: 0.1867 data: 0.0962 max mem: 9390 +Train: [98] [1100/6250] eta: 0:15:27 lr: 0.000000 grad: 0.1473 (0.1586) loss: 0.8134 (0.8144) time: 0.1647 data: 0.0748 max mem: 9390 +Train: [98] [1200/6250] eta: 0:15:07 lr: 0.000000 grad: 0.1509 (0.1582) loss: 0.8127 (0.8141) time: 0.2007 data: 0.1115 max mem: 9390 +Train: [98] [1300/6250] eta: 0:14:45 lr: 0.000000 grad: 0.1442 (0.1575) loss: 0.8112 (0.8139) time: 0.1766 data: 0.0862 max mem: 9390 +Train: [98] [1400/6250] eta: 0:14:24 lr: 0.000000 grad: 0.1437 (0.1571) loss: 0.8145 (0.8137) time: 0.1480 data: 0.0543 max mem: 9390 +Train: [98] [1500/6250] eta: 0:14:03 lr: 0.000000 grad: 0.1501 (0.1566) loss: 0.8100 (0.8136) time: 0.1839 data: 0.0786 max mem: 9390 +Train: [98] [1600/6250] eta: 0:13:40 lr: 0.000000 grad: 0.1452 (0.1563) loss: 0.8153 (0.8138) time: 0.1833 data: 0.0907 max mem: 9390 +Train: [98] [1700/6250] eta: 0:13:19 lr: 0.000000 grad: 0.1433 (0.1560) loss: 0.8101 (0.8137) time: 0.1834 data: 0.1049 max mem: 9390 +Train: [98] [1800/6250] eta: 0:12:57 lr: 0.000000 grad: 0.1506 (0.1557) loss: 0.8140 (0.8137) time: 0.1710 data: 0.0925 max mem: 9390 +Train: [98] [1900/6250] eta: 0:12:37 lr: 0.000000 grad: 0.1464 (0.1555) loss: 0.8107 (0.8137) time: 0.1753 data: 0.0915 max mem: 9390 +Train: [98] [2000/6250] eta: 0:12:18 lr: 0.000000 grad: 0.1476 (0.1554) loss: 0.8154 (0.8138) time: 0.1714 data: 0.0862 max mem: 9390 +Train: [98] [2100/6250] eta: 0:12:00 lr: 0.000000 grad: 0.1477 (0.1553) loss: 0.8162 (0.8138) time: 0.1213 data: 0.0284 max mem: 9390 +Train: [98] [2200/6250] eta: 0:11:41 lr: 0.000000 grad: 0.1433 (0.1550) loss: 0.8146 (0.8138) time: 0.1394 data: 0.0623 max mem: 9390 +Train: [98] [2300/6250] eta: 0:11:24 lr: 0.000000 grad: 0.1469 (0.1546) loss: 0.8186 (0.8138) time: 0.1866 data: 0.0922 max mem: 9390 +Train: [98] [2400/6250] eta: 0:11:04 lr: 0.000000 grad: 0.1429 (0.1545) loss: 0.8153 (0.8139) time: 0.1624 data: 0.0819 max mem: 9390 +Train: [98] [2500/6250] eta: 0:10:44 lr: 0.000000 grad: 0.1513 (0.1543) loss: 0.8142 (0.8139) time: 0.1587 data: 0.0724 max mem: 9390 +Train: [98] [2600/6250] eta: 0:10:27 lr: 0.000000 grad: 0.1461 (0.1541) loss: 0.8159 (0.8140) time: 0.1729 data: 0.0907 max mem: 9390 +Train: [98] [2700/6250] eta: 0:10:10 lr: 0.000000 grad: 0.1537 (0.1538) loss: 0.8209 (0.8141) time: 0.1447 data: 0.0581 max mem: 9390 +Train: [98] [2800/6250] eta: 0:09:51 lr: 0.000000 grad: 0.1389 (0.1535) loss: 0.8218 (0.8143) time: 0.1447 data: 0.0478 max mem: 9390 +Train: [98] [2900/6250] eta: 0:09:34 lr: 0.000000 grad: 0.1408 (0.1533) loss: 0.8161 (0.8143) time: 0.1866 data: 0.1024 max mem: 9390 +Train: [98] [3000/6250] eta: 0:09:15 lr: 0.000000 grad: 0.1300 (0.1530) loss: 0.8236 (0.8145) time: 0.1506 data: 0.0597 max mem: 9390 +Train: [98] [3100/6250] eta: 0:08:57 lr: 0.000000 grad: 0.1349 (0.1527) loss: 0.8145 (0.8146) time: 0.1567 data: 0.0685 max mem: 9390 +Train: [98] [3200/6250] eta: 0:08:40 lr: 0.000000 grad: 0.1400 (0.1524) loss: 0.8167 (0.8147) time: 0.1565 data: 0.0602 max mem: 9390 +Train: [98] [3300/6250] eta: 0:08:23 lr: 0.000000 grad: 0.1345 (0.1521) loss: 0.8223 (0.8148) time: 0.1663 data: 0.0813 max mem: 9390 +Train: [98] [3400/6250] eta: 0:08:06 lr: 0.000000 grad: 0.1354 (0.1519) loss: 0.8135 (0.8149) time: 0.1701 data: 0.0838 max mem: 9390 +Train: [98] [3500/6250] eta: 0:07:48 lr: 0.000000 grad: 0.1490 (0.1519) loss: 0.8126 (0.8149) time: 0.1772 data: 0.0853 max mem: 9390 +Train: [98] [3600/6250] eta: 0:07:31 lr: 0.000000 grad: 0.1503 (0.1519) loss: 0.8078 (0.8148) time: 0.1740 data: 0.0874 max mem: 9390 +Train: [98] [3700/6250] eta: 0:07:14 lr: 0.000000 grad: 0.1423 (0.1519) loss: 0.8221 (0.8148) time: 0.1747 data: 0.0890 max mem: 9390 +Train: [98] [3800/6250] eta: 0:06:56 lr: 0.000000 grad: 0.1439 (0.1519) loss: 0.8134 (0.8148) time: 0.1715 data: 0.0777 max mem: 9390 +Train: [98] [3900/6250] eta: 0:06:40 lr: 0.000000 grad: 0.1507 (0.1519) loss: 0.8167 (0.8148) time: 0.1954 data: 0.1154 max mem: 9390 +Train: [98] [4000/6250] eta: 0:06:22 lr: 0.000000 grad: 0.1409 (0.1519) loss: 0.8182 (0.8148) time: 0.1537 data: 0.0629 max mem: 9390 +Train: [98] [4100/6250] eta: 0:06:05 lr: 0.000000 grad: 0.1405 (0.1518) loss: 0.8144 (0.8148) time: 0.1708 data: 0.0874 max mem: 9390 +Train: [98] [4200/6250] eta: 0:05:48 lr: 0.000000 grad: 0.1499 (0.1517) loss: 0.8068 (0.8148) time: 0.1668 data: 0.0815 max mem: 9390 +Train: [98] [4300/6250] eta: 0:05:31 lr: 0.000000 grad: 0.1462 (0.1517) loss: 0.8193 (0.8148) time: 0.1670 data: 0.0802 max mem: 9390 +Train: [98] [4400/6250] eta: 0:05:14 lr: 0.000000 grad: 0.1408 (0.1516) loss: 0.8172 (0.8147) time: 0.1772 data: 0.1003 max mem: 9390 +Train: [98] [4500/6250] eta: 0:04:57 lr: 0.000000 grad: 0.1495 (0.1515) loss: 0.8192 (0.8147) time: 0.1947 data: 0.1075 max mem: 9390 +Train: [98] [4600/6250] eta: 0:04:40 lr: 0.000000 grad: 0.1387 (0.1514) loss: 0.8167 (0.8147) time: 0.1754 data: 0.0813 max mem: 9390 +Train: [98] [4700/6250] eta: 0:04:23 lr: 0.000000 grad: 0.1426 (0.1513) loss: 0.8195 (0.8147) time: 0.1833 data: 0.0572 max mem: 9390 +Train: [98] [4800/6250] eta: 0:04:06 lr: 0.000000 grad: 0.1417 (0.1512) loss: 0.8158 (0.8147) time: 0.1787 data: 0.0839 max mem: 9390 +Train: [98] [4900/6250] eta: 0:03:49 lr: 0.000000 grad: 0.1444 (0.1512) loss: 0.8078 (0.8147) time: 0.1756 data: 0.0869 max mem: 9390 +Train: [98] [5000/6250] eta: 0:03:32 lr: 0.000000 grad: 0.1488 (0.1512) loss: 0.8139 (0.8147) time: 0.1687 data: 0.0849 max mem: 9390 +Train: [98] [5100/6250] eta: 0:03:15 lr: 0.000000 grad: 0.1433 (0.1511) loss: 0.8198 (0.8148) time: 0.1560 data: 0.0681 max mem: 9390 +Train: [98] [5200/6250] eta: 0:02:58 lr: 0.000000 grad: 0.1462 (0.1511) loss: 0.8173 (0.8148) time: 0.1549 data: 0.0482 max mem: 9390 +Train: [98] [5300/6250] eta: 0:02:41 lr: 0.000000 grad: 0.1412 (0.1510) loss: 0.8179 (0.8149) time: 0.1294 data: 0.0387 max mem: 9390 +Train: [98] [5400/6250] eta: 0:02:24 lr: 0.000000 grad: 0.1487 (0.1511) loss: 0.8113 (0.8149) time: 0.2381 data: 0.0667 max mem: 9390 +Train: [98] [5500/6250] eta: 0:02:07 lr: 0.000000 grad: 0.1310 (0.1509) loss: 0.8156 (0.8149) time: 0.2011 data: 0.1123 max mem: 9390 +Train: [98] [5600/6250] eta: 0:01:51 lr: 0.000000 grad: 0.1400 (0.1509) loss: 0.8219 (0.8150) time: 0.1315 data: 0.0378 max mem: 9390 +Train: [98] [5700/6250] eta: 0:01:34 lr: 0.000000 grad: 0.1449 (0.1508) loss: 0.8245 (0.8150) time: 0.1540 data: 0.0574 max mem: 9390 +Train: [98] [5800/6250] eta: 0:01:17 lr: 0.000000 grad: 0.1482 (0.1508) loss: 0.8173 (0.8151) time: 0.1543 data: 0.0626 max mem: 9390 +Train: [98] [5900/6250] eta: 0:01:00 lr: 0.000000 grad: 0.1418 (0.1507) loss: 0.8257 (0.8152) time: 0.1680 data: 0.0816 max mem: 9390 +Train: [98] [6000/6250] eta: 0:00:42 lr: 0.000000 grad: 0.1427 (0.1506) loss: 0.8186 (0.8153) time: 0.1705 data: 0.0847 max mem: 9390 +Train: [98] [6100/6250] eta: 0:00:25 lr: 0.000000 grad: 0.1393 (0.1505) loss: 0.8218 (0.8153) time: 0.2059 data: 0.1169 max mem: 9390 +Train: [98] [6200/6250] eta: 0:00:08 lr: 0.000000 grad: 0.1525 (0.1506) loss: 0.8132 (0.8153) time: 0.1866 data: 0.0585 max mem: 9390 +Train: [98] [6249/6250] eta: 0:00:00 lr: 0.000000 grad: 0.1471 (0.1506) loss: 0.8175 (0.8153) time: 0.1783 data: 0.0950 max mem: 9390 +Train: [98] Total time: 0:18:02 (0.1732 s / it) +Averaged stats: lr: 0.000000 grad: 0.1471 (0.1506) loss: 0.8175 (0.8153) +Eval (hcp-train-subset): [98] [ 0/62] eta: 0:05:32 loss: 0.8221 (0.8221) time: 5.3632 data: 5.3329 max mem: 9390 +Eval (hcp-train-subset): [98] [61/62] eta: 0:00:00 loss: 0.8143 (0.8145) time: 0.1094 data: 0.0842 max mem: 9390 +Eval (hcp-train-subset): [98] Total time: 0:00:12 (0.2093 s / it) +Averaged stats (hcp-train-subset): loss: 0.8143 (0.8145) +Eval (hcp-val): [98] [ 0/62] eta: 0:03:29 loss: 0.8253 (0.8253) time: 3.3832 data: 3.3324 max mem: 9390 +Eval (hcp-val): [98] [61/62] eta: 0:00:00 loss: 0.8257 (0.8277) time: 0.1107 data: 0.0852 max mem: 9390 +Eval (hcp-val): [98] Total time: 0:00:13 (0.2139 s / it) +Averaged stats (hcp-val): loss: 0.8257 (0.8277) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +Train: [99] [ 0/6250] eta: 6:45:01 lr: 0.000000 grad: 0.3049 (0.3049) loss: 0.7456 (0.7456) time: 3.8883 data: 3.7179 max mem: 9390 +Train: [99] [ 100/6250] eta: 0:19:54 lr: 0.000000 grad: 0.1579 (0.1941) loss: 0.8230 (0.8147) time: 0.1508 data: 0.0658 max mem: 9390 +Train: [99] [ 200/6250] eta: 0:16:59 lr: 0.000000 grad: 0.1663 (0.1924) loss: 0.8180 (0.8140) time: 0.1444 data: 0.0583 max mem: 9390 +Train: [99] [ 300/6250] eta: 0:15:59 lr: 0.000000 grad: 0.1793 (0.1869) loss: 0.8192 (0.8135) time: 0.1420 data: 0.0579 max mem: 9390 +Train: [99] [ 400/6250] eta: 0:15:22 lr: 0.000000 grad: 0.1482 (0.1822) loss: 0.8168 (0.8139) time: 0.1467 data: 0.0619 max mem: 9390 +Train: [99] [ 500/6250] eta: 0:14:49 lr: 0.000000 grad: 0.1503 (0.1769) loss: 0.8239 (0.8150) time: 0.1340 data: 0.0520 max mem: 9390 +Train: [99] [ 600/6250] eta: 0:14:24 lr: 0.000000 grad: 0.1523 (0.1735) loss: 0.8209 (0.8160) time: 0.1532 data: 0.0607 max mem: 9390 +Train: [99] [ 700/6250] eta: 0:13:59 lr: 0.000000 grad: 0.1563 (0.1709) loss: 0.8176 (0.8163) time: 0.1174 data: 0.0328 max mem: 9390 +Train: [99] [ 800/6250] eta: 0:13:38 lr: 0.000000 grad: 0.1531 (0.1693) loss: 0.8200 (0.8165) time: 0.1349 data: 0.0382 max mem: 9390 +Train: [99] [ 900/6250] eta: 0:13:17 lr: 0.000000 grad: 0.1421 (0.1668) loss: 0.8138 (0.8166) time: 0.1608 data: 0.0596 max mem: 9390 +Train: [99] [1000/6250] eta: 0:12:51 lr: 0.000000 grad: 0.1331 (0.1647) loss: 0.8200 (0.8167) time: 0.1212 data: 0.0415 max mem: 9390 +Train: [99] [1100/6250] eta: 0:12:28 lr: 0.000000 grad: 0.1489 (0.1633) loss: 0.8206 (0.8167) time: 0.1216 data: 0.0319 max mem: 9390 +Train: [99] [1200/6250] eta: 0:12:15 lr: 0.000000 grad: 0.1399 (0.1618) loss: 0.8177 (0.8169) time: 0.1573 data: 0.0672 max mem: 9390 +Train: [99] [1300/6250] eta: 0:12:08 lr: 0.000000 grad: 0.1408 (0.1604) loss: 0.8187 (0.8170) time: 0.1584 data: 0.0701 max mem: 9390 +Train: [99] [1400/6250] eta: 0:11:54 lr: 0.000000 grad: 0.1332 (0.1591) loss: 0.8205 (0.8173) time: 0.1634 data: 0.0750 max mem: 9390 +Train: [99] [1500/6250] eta: 0:11:37 lr: 0.000000 grad: 0.1463 (0.1582) loss: 0.8200 (0.8173) time: 0.1530 data: 0.0614 max mem: 9390 +Train: [99] [1600/6250] eta: 0:11:20 lr: 0.000000 grad: 0.1412 (0.1576) loss: 0.8175 (0.8172) time: 0.1280 data: 0.0384 max mem: 9390 +Train: [99] [1700/6250] eta: 0:11:03 lr: 0.000000 grad: 0.1401 (0.1571) loss: 0.8161 (0.8172) time: 0.1326 data: 0.0344 max mem: 9390 +Train: [99] [1800/6250] eta: 0:10:48 lr: 0.000000 grad: 0.1430 (0.1567) loss: 0.8113 (0.8171) time: 0.1422 data: 0.0577 max mem: 9390 +Train: [99] [1900/6250] eta: 0:10:33 lr: 0.000000 grad: 0.1500 (0.1564) loss: 0.8139 (0.8172) time: 0.1418 data: 0.0558 max mem: 9390 +Train: [99] [2000/6250] eta: 0:10:18 lr: 0.000000 grad: 0.1561 (0.1561) loss: 0.8192 (0.8172) time: 0.1412 data: 0.0578 max mem: 9390 +Train: [99] [2100/6250] eta: 0:10:03 lr: 0.000000 grad: 0.1453 (0.1559) loss: 0.8093 (0.8171) time: 0.1415 data: 0.0518 max mem: 9390 +Train: [99] [2200/6250] eta: 0:09:50 lr: 0.000000 grad: 0.1450 (0.1557) loss: 0.8161 (0.8171) time: 0.1615 data: 0.0807 max mem: 9390 +Train: [99] [2300/6250] eta: 0:09:36 lr: 0.000000 grad: 0.1425 (0.1554) loss: 0.8203 (0.8171) time: 0.1642 data: 0.0875 max mem: 9390 +Train: [99] [2400/6250] eta: 0:09:21 lr: 0.000000 grad: 0.1507 (0.1550) loss: 0.8158 (0.8172) time: 0.1390 data: 0.0461 max mem: 9390 +Train: [99] [2500/6250] eta: 0:09:07 lr: 0.000000 grad: 0.1493 (0.1547) loss: 0.8148 (0.8171) time: 0.1419 data: 0.0574 max mem: 9390 +Train: [99] [2600/6250] eta: 0:08:52 lr: 0.000000 grad: 0.1365 (0.1543) loss: 0.8170 (0.8171) time: 0.1401 data: 0.0523 max mem: 9390 +Train: [99] [2700/6250] eta: 0:08:38 lr: 0.000000 grad: 0.1507 (0.1539) loss: 0.8162 (0.8172) time: 0.1471 data: 0.0656 max mem: 9390 +Train: [99] [2800/6250] eta: 0:08:24 lr: 0.000000 grad: 0.1357 (0.1535) loss: 0.8187 (0.8173) time: 0.1355 data: 0.0546 max mem: 9390 +Train: [99] [2900/6250] eta: 0:08:09 lr: 0.000000 grad: 0.1423 (0.1531) loss: 0.8226 (0.8173) time: 0.1660 data: 0.0812 max mem: 9390 +Train: [99] [3000/6250] eta: 0:07:55 lr: 0.000000 grad: 0.1413 (0.1528) loss: 0.8129 (0.8173) time: 0.1510 data: 0.0720 max mem: 9390 +Train: [99] [3100/6250] eta: 0:07:40 lr: 0.000000 grad: 0.1417 (0.1527) loss: 0.8140 (0.8173) time: 0.1452 data: 0.0654 max mem: 9390 +Train: [99] [3200/6250] eta: 0:07:26 lr: 0.000000 grad: 0.1441 (0.1526) loss: 0.8194 (0.8173) time: 0.1345 data: 0.0511 max mem: 9390 +Train: [99] [3300/6250] eta: 0:07:11 lr: 0.000000 grad: 0.1459 (0.1524) loss: 0.8191 (0.8174) time: 0.1453 data: 0.0638 max mem: 9390 +Train: [99] [3400/6250] eta: 0:06:57 lr: 0.000000 grad: 0.1440 (0.1523) loss: 0.8186 (0.8174) time: 0.1648 data: 0.0779 max mem: 9390 +Train: [99] [3500/6250] eta: 0:06:42 lr: 0.000000 grad: 0.1449 (0.1523) loss: 0.8167 (0.8173) time: 0.1451 data: 0.0664 max mem: 9390 +Train: [99] [3600/6250] eta: 0:06:27 lr: 0.000000 grad: 0.1469 (0.1522) loss: 0.8181 (0.8174) time: 0.1485 data: 0.0647 max mem: 9390 +Train: [99] [3700/6250] eta: 0:06:12 lr: 0.000000 grad: 0.1453 (0.1522) loss: 0.8248 (0.8174) time: 0.1459 data: 0.0607 max mem: 9390 +Train: [99] [3800/6250] eta: 0:05:58 lr: 0.000000 grad: 0.1409 (0.1522) loss: 0.8215 (0.8175) time: 0.1547 data: 0.0733 max mem: 9390 +Train: [99] [3900/6250] eta: 0:05:43 lr: 0.000000 grad: 0.1334 (0.1521) loss: 0.8238 (0.8175) time: 0.1575 data: 0.0717 max mem: 9390 +Train: [99] [4000/6250] eta: 0:05:28 lr: 0.000000 grad: 0.1289 (0.1519) loss: 0.8261 (0.8176) time: 0.1604 data: 0.0769 max mem: 9390 +Train: [99] [4100/6250] eta: 0:05:14 lr: 0.000000 grad: 0.1408 (0.1517) loss: 0.8225 (0.8177) time: 0.1346 data: 0.0453 max mem: 9390 +Train: [99] [4200/6250] eta: 0:05:01 lr: 0.000000 grad: 0.1255 (0.1514) loss: 0.8299 (0.8178) time: 0.1954 data: 0.1064 max mem: 9390 +Train: [99] [4300/6250] eta: 0:04:46 lr: 0.000000 grad: 0.1364 (0.1513) loss: 0.8235 (0.8178) time: 0.1307 data: 0.0463 max mem: 9390 +Train: [99] [4400/6250] eta: 0:04:33 lr: 0.000000 grad: 0.1280 (0.1511) loss: 0.8260 (0.8179) time: 0.1607 data: 0.0785 max mem: 9390 +Train: [99] [4500/6250] eta: 0:04:18 lr: 0.000000 grad: 0.1371 (0.1511) loss: 0.8190 (0.8180) time: 0.1611 data: 0.0795 max mem: 9390 +Train: [99] [4600/6250] eta: 0:04:04 lr: 0.000000 grad: 0.1397 (0.1509) loss: 0.8214 (0.8180) time: 0.1680 data: 0.0776 max mem: 9390 +Train: [99] [4700/6250] eta: 0:03:49 lr: 0.000000 grad: 0.1415 (0.1508) loss: 0.8219 (0.8180) time: 0.1655 data: 0.0685 max mem: 9390 +Train: [99] [4800/6250] eta: 0:03:35 lr: 0.000000 grad: 0.1363 (0.1508) loss: 0.8223 (0.8180) time: 0.1572 data: 0.0795 max mem: 9390 +Train: [99] [4900/6250] eta: 0:03:20 lr: 0.000000 grad: 0.1475 (0.1507) loss: 0.8186 (0.8179) time: 0.1487 data: 0.0655 max mem: 9390 +Train: [99] [5000/6250] eta: 0:03:05 lr: 0.000000 grad: 0.1417 (0.1506) loss: 0.8185 (0.8179) time: 0.1348 data: 0.0565 max mem: 9390 +Train: [99] [5100/6250] eta: 0:02:50 lr: 0.000000 grad: 0.1399 (0.1505) loss: 0.8170 (0.8179) time: 0.1468 data: 0.0596 max mem: 9390 +Train: [99] [5200/6250] eta: 0:02:35 lr: 0.000000 grad: 0.1490 (0.1505) loss: 0.8197 (0.8179) time: 0.1211 data: 0.0418 max mem: 9390 +Train: [99] [5300/6250] eta: 0:02:20 lr: 0.000000 grad: 0.1465 (0.1504) loss: 0.8138 (0.8178) time: 0.1470 data: 0.0628 max mem: 9390 +Train: [99] [5400/6250] eta: 0:02:05 lr: 0.000000 grad: 0.1384 (0.1504) loss: 0.8198 (0.8178) time: 0.1421 data: 0.0616 max mem: 9390 +Train: [99] [5500/6250] eta: 0:01:50 lr: 0.000000 grad: 0.1477 (0.1504) loss: 0.8157 (0.8178) time: 0.1289 data: 0.0519 max mem: 9390 +Train: [99] [5600/6250] eta: 0:01:36 lr: 0.000000 grad: 0.1535 (0.1504) loss: 0.8162 (0.8178) time: 0.1239 data: 0.0389 max mem: 9390 +Train: [99] [5700/6250] eta: 0:01:21 lr: 0.000000 grad: 0.1434 (0.1504) loss: 0.8151 (0.8177) time: 0.1252 data: 0.0409 max mem: 9390 +Train: [99] [5800/6250] eta: 0:01:06 lr: 0.000000 grad: 0.1333 (0.1504) loss: 0.8243 (0.8177) time: 0.1312 data: 0.0443 max mem: 9390 +Train: [99] [5900/6250] eta: 0:00:51 lr: 0.000000 grad: 0.1382 (0.1504) loss: 0.8218 (0.8177) time: 0.1467 data: 0.0665 max mem: 9390 +Train: [99] [6000/6250] eta: 0:00:36 lr: 0.000000 grad: 0.1461 (0.1504) loss: 0.8167 (0.8177) time: 0.1455 data: 0.0654 max mem: 9390 +Train: [99] [6100/6250] eta: 0:00:22 lr: 0.000000 grad: 0.1560 (0.1505) loss: 0.8157 (0.8177) time: 0.1316 data: 0.0370 max mem: 9390 +Train: [99] [6200/6250] eta: 0:00:07 lr: 0.000000 grad: 0.1488 (0.1505) loss: 0.8170 (0.8176) time: 0.1712 data: 0.0905 max mem: 9390 +Train: [99] [6249/6250] eta: 0:00:00 lr: 0.000000 grad: 0.1509 (0.1505) loss: 0.8151 (0.8176) time: 0.1361 data: 0.0542 max mem: 9390 +Train: [99] Total time: 0:15:27 (0.1483 s / it) +Averaged stats: lr: 0.000000 grad: 0.1509 (0.1505) loss: 0.8151 (0.8176) +Eval (hcp-train-subset): [99] [ 0/62] eta: 0:05:32 loss: 0.8217 (0.8217) time: 5.3708 data: 5.3414 max mem: 9390 +Eval (hcp-train-subset): [99] [61/62] eta: 0:00:00 loss: 0.8105 (0.8143) time: 0.1200 data: 0.0952 max mem: 9390 +Eval (hcp-train-subset): [99] Total time: 0:00:13 (0.2113 s / it) +Averaged stats (hcp-train-subset): loss: 0.8105 (0.8143) +Making plots (hcp-train-subset): example=10 +Eval (hcp-val): [99] [ 0/62] eta: 0:05:40 loss: 0.8240 (0.8240) time: 5.4868 data: 5.4556 max mem: 9390 +Eval (hcp-val): [99] [61/62] eta: 0:00:00 loss: 0.8268 (0.8278) time: 0.1344 data: 0.1075 max mem: 9390 +Eval (hcp-val): [99] Total time: 0:00:13 (0.2185 s / it) +Averaged stats (hcp-val): loss: 0.8268 (0.8278) +Making plots (hcp-val): example=50 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_3/pretrain/checkpoint-last.pth +done! training time: 3:52:59 diff --git a/input_space_v3/flat_lr1e-3_4/eval_v2/aabc_age__patch__logistic/config.yaml b/input_space_v3/flat_lr1e-3_4/eval_v2/aabc_age__patch__logistic/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..bb59590cd91b52c8e54a09a300f912865715c997 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_4/eval_v2/aabc_age__patch__logistic/config.yaml @@ -0,0 +1,30 @@ +output_root: experiments/input_space_v3/output +name_prefix: eval_logistic +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_4; eval v2 (aabc_age patch logistic) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: input_space_v3/flat_lr1e-3_4/eval_v2/aabc_age__patch__logistic +model: flat_mae +representation: patch +dataset: aabc_age +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/eval_v2/aabc_age__patch__logistic +remote_dir: null diff --git a/input_space_v3/flat_lr1e-3_4/eval_v2/aabc_age__patch__logistic/eval_table.csv b/input_space_v3/flat_lr1e-3_4/eval_v2/aabc_age__patch__logistic/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..3bde8149061dabc839b7a985caeae593e4eee412 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_4/eval_v2/aabc_age__patch__logistic/eval_table.csv @@ -0,0 +1,203 @@ +model,repr,clf,dataset,trial,C,split,acc,acc_std,f1,f1_std,bacc,bacc_std +flat_mae,patch,logistic,aabc_age,,0.005994842503189409,train,0.6673228346456693,0.021218413994504515,0.6662364610671427,0.02126090875571434,0.6674695303861673,0.02123240406551999 +flat_mae,patch,logistic,aabc_age,,0.005994842503189409,test,0.4807692307692308,0.06142175230978626,0.4513689346706425,0.06698800410794296,0.47046703296703296,0.06156247720838732 +flat_mae,patch,logistic,aabc_age,1,0.005994842503189409,train,0.6732283464566929,0.01984532226177321,0.6746289118178075,0.01988269667215657,0.6745219260475384,0.01989047060489475 +flat_mae,patch,logistic,aabc_age,1,0.005994842503189409,test,0.46153846153846156,0.058022695008890054,0.42975738682569803,0.05513428608916521,0.4548992673992674,0.05705275276614616 +flat_mae,patch,logistic,aabc_age,2,0.000774263682681127,train,0.5413385826771654,0.02101566395135454,0.5344609873989558,0.02180864122698473,0.5414227668784728,0.021124640091743172 +flat_mae,patch,logistic,aabc_age,2,0.000774263682681127,test,0.46153846153846156,0.06802204437320344,0.4574891774891775,0.0666692789630134,0.4567307692307693,0.06742752211470947 +flat_mae,patch,logistic,aabc_age,3,0.046415888336127774,train,0.8287401574803149,0.016262022980145573,0.8296492319555561,0.01620577716533221,0.8303592663059635,0.016205472413068415 +flat_mae,patch,logistic,aabc_age,3,0.046415888336127774,test,0.6153846153846154,0.0670990612726336,0.6118518518518519,0.0668335478719623,0.612408424908425,0.0672037833962049 +flat_mae,patch,logistic,aabc_age,4,0.3593813663804626,train,0.9881889763779528,0.004745432228812671,0.9878679483620676,0.004886215819438607,0.9877532657957878,0.0049202909557514215 +flat_mae,patch,logistic,aabc_age,4,0.3593813663804626,test,0.5384615384615384,0.06080888433609996,0.5324756852343059,0.061389748390063566,0.5409798534798536,0.06112499016660267 +flat_mae,patch,logistic,aabc_age,5,0.3593813663804626,train,0.984251968503937,0.005509385011654778,0.9840422872422935,0.00556857953825886,0.9841561434936295,0.005531622775504387 +flat_mae,patch,logistic,aabc_age,5,0.3593813663804626,test,0.4807692307692308,0.06421325187199547,0.4708222811671088,0.06514378376080822,0.4787087912087912,0.06442242623548348 +flat_mae,patch,logistic,aabc_age,6,0.005994842503189409,train,0.6653543307086615,0.020772457569820362,0.6658950208594464,0.020882801426603054,0.6661398686968847,0.02080619180369717 +flat_mae,patch,logistic,aabc_age,6,0.005994842503189409,test,0.5192307692307693,0.06863638002343869,0.512962962962963,0.07019419831567665,0.516025641025641,0.06838091209486596 +flat_mae,patch,logistic,aabc_age,7,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,7,166.81005372000556,test,0.5,0.06648325855912188,0.5015207780725022,0.06551915364198985,0.4954212454212454,0.06661137990224329 +flat_mae,patch,logistic,aabc_age,8,0.3593813663804626,train,0.9901574803149606,0.004393480295316931,0.9900366871187589,0.0044360094905189044,0.9900369493794461,0.004425277758192437 +flat_mae,patch,logistic,aabc_age,8,0.3593813663804626,test,0.5576923076923077,0.06329951344494572,0.552848575712144,0.0651348490914023,0.5606684981684982,0.06349260506763364 +flat_mae,patch,logistic,aabc_age,9,0.005994842503189409,train,0.6732283464566929,0.02098502753733627,0.6719418641060433,0.021224390601338076,0.6738368569340741,0.0209842171645537 +flat_mae,patch,logistic,aabc_age,9,0.005994842503189409,test,0.4807692307692308,0.06535062464897971,0.4726399462606359,0.06491178837798812,0.47870879120879123,0.06532947961052876 +flat_mae,patch,logistic,aabc_age,10,0.000774263682681127,train,0.5610236220472441,0.020003832402982716,0.5534458513102625,0.020564441769970788,0.56054620446538,0.01995410535636909 +flat_mae,patch,logistic,aabc_age,10,0.000774263682681127,test,0.4423076923076923,0.06425010072978082,0.4415292353823088,0.06481380232458177,0.44184981684981683,0.06415966987207432 +flat_mae,patch,logistic,aabc_age,11,0.046415888336127774,train,0.8208661417322834,0.016983455695927564,0.8204430283542141,0.017227004322566866,0.8228651016803193,0.016890444109513153 +flat_mae,patch,logistic,aabc_age,11,0.046415888336127774,test,0.6730769230769231,0.06426897758086665,0.677915506532448,0.06432523640481037,0.674908424908425,0.06424154360248845 +flat_mae,patch,logistic,aabc_age,12,0.005994842503189409,train,0.6889763779527559,0.020627043061229366,0.6867532265727379,0.020993211705471224,0.6891456043376443,0.020613439980357442 +flat_mae,patch,logistic,aabc_age,12,0.005994842503189409,test,0.46153846153846156,0.06577407764416639,0.4574884792626728,0.06770309159557743,0.46130952380952384,0.06593619003497556 +flat_mae,patch,logistic,aabc_age,13,0.005994842503189409,train,0.6673228346456693,0.01984615327310559,0.6651999720579893,0.020185940849747556,0.6672033740642782,0.019829200587289812 +flat_mae,patch,logistic,aabc_age,13,0.005994842503189409,test,0.4230769230769231,0.06376482308233822,0.4139663954101048,0.06314379181576388,0.4194139194139194,0.06333959379550484 +flat_mae,patch,logistic,aabc_age,14,0.3593813663804626,train,0.9881889763779528,0.00472358916763399,0.9879909136086664,0.0048103532237196685,0.9879208470067454,0.004840335249442479 +flat_mae,patch,logistic,aabc_age,14,0.3593813663804626,test,0.5384615384615384,0.06588742191696306,0.5357142857142857,0.0667542785199311,0.5428113553113554,0.0659733962921931 +flat_mae,patch,logistic,aabc_age,15,0.005994842503189409,train,0.6791338582677166,0.020949592078864356,0.6783719120827768,0.02125978627403598,0.6792825270575329,0.021006132882414905 +flat_mae,patch,logistic,aabc_age,15,0.005994842503189409,test,0.4230769230769231,0.06881714042713521,0.4372159090909091,0.06787975670908246,0.42422161172161177,0.06920073049765091 +flat_mae,patch,logistic,aabc_age,16,0.005994842503189409,train,0.655511811023622,0.020143843812661166,0.6532716275659824,0.02059840302757258,0.6558768980550032,0.020160902784626733 +flat_mae,patch,logistic,aabc_age,16,0.005994842503189409,test,0.46153846153846156,0.0679200169186143,0.4635573553092735,0.06669114023863902,0.4581043956043956,0.06745786351590514 +flat_mae,patch,logistic,aabc_age,17,0.000774263682681127,train,0.5531496062992126,0.02084901391823514,0.5470002284040073,0.021564966152508552,0.5531843786501058,0.020784121133069114 +flat_mae,patch,logistic,aabc_age,17,0.000774263682681127,test,0.4230769230769231,0.061661607554083814,0.39890109890109887,0.05783283963940749,0.41781135531135527,0.06060155422615813 +flat_mae,patch,logistic,aabc_age,18,0.005994842503189409,train,0.6653543307086615,0.019946056507248257,0.6649155336563288,0.020050940327019855,0.6657223541348206,0.01988713838528978 +flat_mae,patch,logistic,aabc_age,18,0.005994842503189409,test,0.5192307692307693,0.06552988387349219,0.5187240295935949,0.06397454151432118,0.5144230769230769,0.0651666604817252 +flat_mae,patch,logistic,aabc_age,19,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,19,2.782559402207126,test,0.46153846153846156,0.06655925642151221,0.4642567110309046,0.06832633761367016,0.46130952380952384,0.06683569745737158 +flat_mae,patch,logistic,aabc_age,20,0.000774263682681127,train,0.5511811023622047,0.022482693587357848,0.5449587467554382,0.02285474974960679,0.5509506817366687,0.022362772594372814 +flat_mae,patch,logistic,aabc_age,20,0.000774263682681127,test,0.5576923076923077,0.061921117981436714,0.534471853257432,0.06881360398808928,0.5528846153846154,0.06189097076504942 +flat_mae,patch,logistic,aabc_age,21,0.046415888336127774,train,0.8228346456692913,0.016870623572822648,0.8231239322754679,0.017018596095751487,0.8234258634148399,0.016932490169163577 +flat_mae,patch,logistic,aabc_age,21,0.046415888336127774,test,0.4423076923076923,0.06344153530902973,0.43002901519030545,0.06427285256702801,0.44459706959706957,0.06386426333885377 +flat_mae,patch,logistic,aabc_age,22,0.005994842503189409,train,0.6732283464566929,0.02021804807687765,0.6712741133265864,0.020498481070969563,0.6737368835936317,0.020264959571857873 +flat_mae,patch,logistic,aabc_age,22,0.005994842503189409,test,0.36538461538461536,0.06583666133949505,0.3600210084033614,0.06504252354169933,0.3651556776556777,0.06592571097571771 +flat_mae,patch,logistic,aabc_age,23,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,23,2.782559402207126,test,0.5,0.06648925481547495,0.4990322580645161,0.06605810077417204,0.5041208791208791,0.06702525484537834 +flat_mae,patch,logistic,aabc_age,24,0.046415888336127774,train,0.8287401574803149,0.0166748174832313,0.8285421854853594,0.01682672174344897,0.8297418050630143,0.01664190683054938 +flat_mae,patch,logistic,aabc_age,24,0.046415888336127774,test,0.38461538461538464,0.06266629946596014,0.39673466838009563,0.061197254317959526,0.3855311355311355,0.0628725071636741 +flat_mae,patch,logistic,aabc_age,25,0.3593813663804626,train,0.9901574803149606,0.004351736707939105,0.9900168137552741,0.004423286294695965,0.9898193814982672,0.004502899774622598 +flat_mae,patch,logistic,aabc_age,25,0.3593813663804626,test,0.36538461538461536,0.06385888427299459,0.38339080459770114,0.061871396754807975,0.36469780219780223,0.06378954920935768 +flat_mae,patch,logistic,aabc_age,26,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,26,166.81005372000556,test,0.5192307692307693,0.06953995063075477,0.5173789173789174,0.0695156198687675,0.5190018315018315,0.0696038583826886 +flat_mae,patch,logistic,aabc_age,27,0.005994842503189409,train,0.6712598425196851,0.019295790905145434,0.6701846399214819,0.019418548583994874,0.672038295782995,0.019326509706094872 +flat_mae,patch,logistic,aabc_age,27,0.005994842503189409,test,0.4230769230769231,0.06389530082451778,0.41254208754208754,0.064818024032729,0.4198717948717949,0.0636812590205268 +flat_mae,patch,logistic,aabc_age,28,0.3593813663804626,train,0.9881889763779528,0.004805528970489856,0.9881270302728089,0.004853018548676168,0.9880208203471881,0.004907532730148702 +flat_mae,patch,logistic,aabc_age,28,0.3593813663804626,test,0.5192307692307693,0.06378588443577808,0.5109076109076109,0.06523139683333375,0.5187728937728937,0.06399732832925407 +flat_mae,patch,logistic,aabc_age,29,0.3593813663804626,train,0.984251968503937,0.005573301546065866,0.9841225921222153,0.005627795232750144,0.9838885889422293,0.0057065631717352445 +flat_mae,patch,logistic,aabc_age,29,0.3593813663804626,test,0.5769230769230769,0.0641118083078074,0.5755570291777188,0.06503603415902622,0.5782967032967032,0.0643466551362433 +flat_mae,patch,logistic,aabc_age,30,0.005994842503189409,train,0.6673228346456693,0.020377595257850645,0.6651280402590112,0.02069062294376466,0.6678560777078151,0.020371380346889876 +flat_mae,patch,logistic,aabc_age,30,0.005994842503189409,test,0.5384615384615384,0.06761494705380429,0.5373578595317725,0.06648771016796089,0.5425824175824177,0.06780277899356701 +flat_mae,patch,logistic,aabc_age,31,0.046415888336127774,train,0.8287401574803149,0.01646104894690083,0.8289592997374707,0.016514980785656372,0.8298917650736782,0.016397725356760026 +flat_mae,patch,logistic,aabc_age,31,0.046415888336127774,test,0.5961538461538461,0.05866940525031795,0.572872992784005,0.06114939323821019,0.5885989010989011,0.05828253052267649 +flat_mae,patch,logistic,aabc_age,32,0.046415888336127774,train,0.8307086614173228,0.01584199330695175,0.8310283570781651,0.015898878880070837,0.8324929898789579,0.015748024582968482 +flat_mae,patch,logistic,aabc_age,32,0.046415888336127774,test,0.5384615384615384,0.06891513518805695,0.5318840579710145,0.06782333448805451,0.5322802197802198,0.06868313241805386 +flat_mae,patch,logistic,aabc_age,33,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,33,166.81005372000556,test,0.40384615384615385,0.06838137052092132,0.4026078088578089,0.06863538214254236,0.402014652014652,0.06839563343581948 +flat_mae,patch,logistic,aabc_age,34,0.3593813663804626,train,0.9803149606299213,0.006144760004764309,0.9800818973196757,0.006226648830295999,0.9800738987588922,0.006238937450961219 +flat_mae,patch,logistic,aabc_age,34,0.3593813663804626,test,0.46153846153846156,0.064223571683326,0.46054376657824936,0.0674609216306421,0.46886446886446886,0.06418213026902736 +flat_mae,patch,logistic,aabc_age,35,0.046415888336127774,train,0.8228346456692913,0.016190667134970204,0.8224805305297296,0.016428844352606532,0.8236934179662402,0.01619457536063237 +flat_mae,patch,logistic,aabc_age,35,0.046415888336127774,test,0.36538461538461536,0.06294398514768658,0.3621351766513057,0.06157119658622337,0.3630952380952381,0.06261526239695116 +flat_mae,patch,logistic,aabc_age,36,0.3593813663804626,train,0.9822834645669292,0.005888504381332126,0.9822026841725098,0.005921286046300732,0.9820900277911502,0.0059558273813769685 +flat_mae,patch,logistic,aabc_age,36,0.3593813663804626,test,0.5384615384615384,0.06459105540142399,0.5345238095238095,0.06609687814272953,0.5412087912087913,0.0648941685115264 +flat_mae,patch,logistic,aabc_age,37,0.005994842503189409,train,0.6692913385826772,0.02141206657362129,0.6679635133733153,0.02186250373128202,0.6699721800805157,0.0215100328779224 +flat_mae,patch,logistic,aabc_age,37,0.005994842503189409,test,0.5192307692307693,0.06586475294475318,0.5157990157990158,0.06806450914685719,0.5146520146520146,0.06578527489258351 +flat_mae,patch,logistic,aabc_age,38,9.999999999999999e-05,train,0.4940944881889764,0.019553289420510666,0.46133688886909463,0.020282890267589712,0.49108331303498926,0.019446133322209215 +flat_mae,patch,logistic,aabc_age,38,9.999999999999999e-05,test,0.5,0.062111514525781696,0.46413308913308915,0.06041298118322393,0.49061355311355315,0.061102615066612104 +flat_mae,patch,logistic,aabc_age,39,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,39,166.81005372000556,test,0.4230769230769231,0.0650945943455964,0.4257575757575758,0.06525339735850032,0.42284798534798534,0.06502581577710059 +flat_mae,patch,logistic,aabc_age,40,0.005994842503189409,train,0.6751968503937008,0.020575339527920147,0.6752558067860979,0.02054955441669024,0.6765880417500177,0.020537416174435347 +flat_mae,patch,logistic,aabc_age,40,0.005994842503189409,test,0.5576923076923077,0.05876453615965305,0.5380587484035759,0.06276590141143555,0.5556318681318682,0.05871182509810279 +flat_mae,patch,logistic,aabc_age,41,0.3593813663804626,train,0.9862204724409449,0.00493283049228668,0.9859317653890824,0.005043124591269438,0.9856871500933084,0.00512362949272975 +flat_mae,patch,logistic,aabc_age,41,0.3593813663804626,test,0.4807692307692308,0.05799636542376482,0.44816990341287016,0.06273068064481893,0.47573260073260076,0.05749226364488999 +flat_mae,patch,logistic,aabc_age,42,0.005994842503189409,train,0.6791338582677166,0.019936264617758603,0.6783824003770615,0.02007366012011653,0.679985217371291,0.019955045339365225 +flat_mae,patch,logistic,aabc_age,42,0.005994842503189409,test,0.46153846153846156,0.06364392207090987,0.4381950664278251,0.06573186312060156,0.4700091575091575,0.0645870812638822 +flat_mae,patch,logistic,aabc_age,43,0.005994842503189409,train,0.6712598425196851,0.020427949838450973,0.6708459989810664,0.020495008409117457,0.6716031600206371,0.020406230487860666 +flat_mae,patch,logistic,aabc_age,43,0.005994842503189409,test,0.5,0.07077073576995027,0.5046786546786546,0.07184474608633598,0.4967948717948718,0.07076052905267642 +flat_mae,patch,logistic,aabc_age,44,0.046415888336127774,train,0.8405511811023622,0.015875031213614433,0.8401780406103427,0.015959355809872528,0.8411682544127321,0.015849172984561444 +flat_mae,patch,logistic,aabc_age,44,0.046415888336127774,test,0.5,0.07203996055773325,0.5038591901319812,0.07227391051125866,0.4983974358974359,0.07208224737096779 +flat_mae,patch,logistic,aabc_age,45,0.005994842503189409,train,0.6633858267716536,0.01919121696520618,0.6616511249790196,0.019507448764965112,0.6643089420758781,0.019193391468335458 +flat_mae,patch,logistic,aabc_age,45,0.005994842503189409,test,0.4423076923076923,0.06353467813284165,0.4460439560439561,0.06228299113620787,0.4432234432234432,0.06381462459321155 +flat_mae,patch,logistic,aabc_age,46,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,46,21.54434690031882,test,0.4230769230769231,0.06861360596176914,0.4239764492753623,0.06952302338384599,0.4198717948717949,0.0688004917299711 +flat_mae,patch,logistic,aabc_age,47,0.005994842503189409,train,0.6712598425196851,0.020167373848519195,0.668838673828323,0.020524843707238442,0.6717707412315949,0.020185394725327852 +flat_mae,patch,logistic,aabc_age,47,0.005994842503189409,test,0.5,0.06695936240002402,0.5033866995073891,0.06788524263019614,0.5011446886446886,0.06700161688214507 +flat_mae,patch,logistic,aabc_age,48,0.005994842503189409,train,0.6771653543307087,0.02125034200087307,0.6743410744417417,0.02188530550261818,0.6770664513443897,0.021351077650515454 +flat_mae,patch,logistic,aabc_age,48,0.005994842503189409,test,0.40384615384615385,0.0640872532997238,0.39855828488795286,0.06663590218293329,0.4017857142857143,0.06418370178325516 +flat_mae,patch,logistic,aabc_age,49,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,49,21.54434690031882,test,0.3269230769230769,0.06183078406415502,0.3223389355742297,0.05917847469182315,0.3216575091575092,0.060889890707972974 +flat_mae,patch,logistic,aabc_age,50,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,50,166.81005372000556,test,0.46153846153846156,0.06316947946670666,0.4598597475455821,0.06482425128494712,0.45993589743589747,0.06366823834178918 +flat_mae,patch,logistic,aabc_age,51,0.046415888336127774,train,0.8228346456692913,0.016583215550853694,0.8233137926652301,0.01662228464071138,0.8246460416311047,0.016376282731465002 +flat_mae,patch,logistic,aabc_age,51,0.046415888336127774,test,0.5192307692307693,0.06488427340204438,0.5011322463768116,0.06200959809416161,0.51007326007326,0.06429907089122472 +flat_mae,patch,logistic,aabc_age,52,0.046415888336127774,train,0.8346456692913385,0.01579809512756584,0.834766017713584,0.015836620861500155,0.8350198939755155,0.015763676722443356 +flat_mae,patch,logistic,aabc_age,52,0.046415888336127774,test,0.5,0.07087261470266847,0.5063636363636363,0.07153000971477359,0.5,0.07094505825920273 +flat_mae,patch,logistic,aabc_age,53,0.000774263682681127,train,0.5334645669291339,0.021682157185849402,0.525117066986642,0.022137094163105477,0.5327231683061975,0.021682346330799483 +flat_mae,patch,logistic,aabc_age,53,0.000774263682681127,test,0.5384615384615384,0.0621859684700352,0.5222832722832722,0.06375587861041981,0.5350274725274725,0.0620360393644066 +flat_mae,patch,logistic,aabc_age,54,0.005994842503189409,train,0.6732283464566929,0.019428754912578287,0.6729437716867913,0.019590752423383595,0.6750746563506326,0.01939107159789884 +flat_mae,patch,logistic,aabc_age,54,0.005994842503189409,test,0.4230769230769231,0.06032579202490385,0.4077875529488433,0.06081360166182579,0.42536630036630035,0.06089937479872156 +flat_mae,patch,logistic,aabc_age,55,0.005994842503189409,train,0.6751968503937008,0.019653885189712644,0.6731265141477134,0.020092798842223165,0.6751003089823528,0.01963769573744989 +flat_mae,patch,logistic,aabc_age,55,0.005994842503189409,test,0.5384615384615384,0.0626344234899401,0.5457849940608561,0.06055327210293257,0.5425824175824175,0.06303357329162877 +flat_mae,patch,logistic,aabc_age,56,0.000774263682681127,train,0.5846456692913385,0.022013111937075017,0.5780319003630245,0.02254729240985967,0.583584305576067,0.021998068636842456 +flat_mae,patch,logistic,aabc_age,56,0.000774263682681127,test,0.40384615384615385,0.06765098170347411,0.3901112030144288,0.06707207236555582,0.4001831501831502,0.06725143246117919 +flat_mae,patch,logistic,aabc_age,57,0.046415888336127774,train,0.8366141732283464,0.016941769227181956,0.8366802565320093,0.01705155699691246,0.8359481836018788,0.016966515951515375 +flat_mae,patch,logistic,aabc_age,57,0.046415888336127774,test,0.4423076923076923,0.061430241381692605,0.42857142857142855,0.05860489115789958,0.440018315018315,0.061139146955317115 +flat_mae,patch,logistic,aabc_age,58,0.046415888336127774,train,0.8248031496062992,0.01592352998294078,0.8247525344085611,0.01606668868236646,0.825224424565919,0.015964227563198922 +flat_mae,patch,logistic,aabc_age,58,0.046415888336127774,test,0.4423076923076923,0.05849567576189062,0.4239684062892153,0.06303512994044862,0.4416208791208791,0.05853628218971281 +flat_mae,patch,logistic,aabc_age,59,0.3593813663804626,train,0.9921259842519685,0.0038082813716969442,0.992073977738019,0.0038370521099280845,0.9918355105305252,0.003946920723109907 +flat_mae,patch,logistic,aabc_age,59,0.3593813663804626,test,0.4423076923076923,0.07208536811210711,0.4510188087774295,0.07036128290750994,0.4391025641025641,0.07192140253191502 +flat_mae,patch,logistic,aabc_age,60,0.005994842503189409,train,0.6653543307086615,0.021678174609189513,0.6637840973401244,0.021893119899092803,0.6661075032269572,0.021647895260059613 +flat_mae,patch,logistic,aabc_age,60,0.005994842503189409,test,0.4423076923076923,0.06238005057756183,0.44278117715617715,0.06270351955832057,0.44024725274725274,0.06247326727729716 +flat_mae,patch,logistic,aabc_age,61,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,61,2.782559402207126,test,0.46153846153846156,0.06587373613532206,0.4604500891265597,0.06651078006017344,0.45535714285714285,0.06591485681689109 +flat_mae,patch,logistic,aabc_age,62,0.046415888336127774,train,0.812992125984252,0.016253595490190228,0.8133549782756243,0.016408872775775216,0.8148005855512871,0.01619331959360194 +flat_mae,patch,logistic,aabc_age,62,0.046415888336127774,test,0.5384615384615384,0.06400669112581699,0.5206959706959706,0.061240156591357495,0.5306776556776557,0.06345267910102838 +flat_mae,patch,logistic,aabc_age,63,0.005994842503189409,train,0.687007874015748,0.019264359650170183,0.687897722266279,0.019362537183051167,0.6875969765376715,0.019293854673839313 +flat_mae,patch,logistic,aabc_age,63,0.005994842503189409,test,0.46153846153846156,0.05969419108844797,0.4400228937728938,0.06030763473239976,0.4578754578754579,0.05937281379908385 +flat_mae,patch,logistic,aabc_age,64,0.3593813663804626,train,0.9921259842519685,0.0038725010642385793,0.991968873541782,0.003953302329026867,0.9918854972007465,0.003989745911914051 +flat_mae,patch,logistic,aabc_age,64,0.3593813663804626,test,0.34615384615384615,0.061785310197594846,0.3543947286934664,0.06196768497903255,0.3456959706959707,0.061687321065751345 +flat_mae,patch,logistic,aabc_age,65,0.046415888336127774,train,0.8169291338582677,0.016159323523819713,0.8171859637152634,0.016199881367146444,0.8187152490750668,0.01601987278686519 +flat_mae,patch,logistic,aabc_age,65,0.046415888336127774,test,0.46153846153846156,0.06754655418486216,0.45454545454545453,0.06756552894178838,0.4553571428571428,0.06720324248397239 +flat_mae,patch,logistic,aabc_age,66,0.005994842503189409,train,0.6653543307086615,0.019636216620367745,0.6653634239744833,0.019725985723548518,0.6666925989999789,0.019583067183648068 +flat_mae,patch,logistic,aabc_age,66,0.005994842503189409,test,0.4423076923076923,0.06504258959742042,0.4455128205128205,0.06301910824479973,0.4461996336996337,0.06568272948965478 +flat_mae,patch,logistic,aabc_age,67,0.046415888336127774,train,0.8307086614173228,0.01665086443709675,0.8302996600260772,0.01678923854663405,0.8306201080191566,0.016712554784959595 +flat_mae,patch,logistic,aabc_age,67,0.046415888336127774,test,0.4423076923076923,0.06292499291797982,0.4246498599439776,0.060305631139080704,0.4356684981684982,0.06197006970247393 +flat_mae,patch,logistic,aabc_age,68,0.3593813663804626,train,0.984251968503937,0.005480083034281513,0.9840576344181615,0.005547582709002112,0.9841561434936295,0.005531680379056619 +flat_mae,patch,logistic,aabc_age,68,0.3593813663804626,test,0.40384615384615385,0.060307447016769614,0.3938228438228438,0.058712274140929735,0.4059065934065934,0.06110441472713985 +flat_mae,patch,logistic,aabc_age,69,0.005994842503189409,train,0.6830708661417323,0.01991331577312753,0.6814134715870619,0.02017668182650842,0.6829472572302063,0.019936798205387123 +flat_mae,patch,logistic,aabc_age,69,0.005994842503189409,test,0.40384615384615385,0.06912747636190462,0.41154422788605693,0.06919491969647079,0.40636446886446886,0.06960132863631073 +flat_mae,patch,logistic,aabc_age,70,0.3593813663804626,train,0.9940944881889764,0.00358908313682415,0.9938758210559914,0.0037230235871455225,0.9938516395627832,0.003732442785215758 +flat_mae,patch,logistic,aabc_age,70,0.3593813663804626,test,0.40384615384615385,0.06921763764349911,0.40170940170940167,0.06929866477058474,0.40636446886446886,0.06990620821985759 +flat_mae,patch,logistic,aabc_age,71,0.000774263682681127,train,0.5570866141732284,0.021510039513297028,0.5534658472849467,0.021562466859205816,0.55649632520057,0.02142054176676251 +flat_mae,patch,logistic,aabc_age,71,0.000774263682681127,test,0.4807692307692308,0.06252302534446692,0.4784382284382284,0.06155192303592383,0.47870879120879123,0.06228922488168949 +flat_mae,patch,logistic,aabc_age,72,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,72,2.782559402207126,test,0.5769230769230769,0.06280988266942349,0.5705801768046368,0.0646502546441943,0.5737179487179487,0.06293512857638722 +flat_mae,patch,logistic,aabc_age,73,0.3593813663804626,train,0.9901574803149606,0.004256302471890526,0.9901675366974525,0.004260117227026039,0.9900369493794461,0.004318807015845286 +flat_mae,patch,logistic,aabc_age,73,0.3593813663804626,test,0.4423076923076923,0.06743055818777415,0.4603916791604198,0.0661380006233578,0.44207875457875456,0.06766897444553473 +flat_mae,patch,logistic,aabc_age,74,0.005994842503189409,train,0.6692913385826772,0.020113486609851787,0.6674454868187637,0.020383577657124858,0.6692694897667577,0.020105444398211547 +flat_mae,patch,logistic,aabc_age,74,0.005994842503189409,test,0.4807692307692308,0.06869123093307174,0.4873863636363637,0.06930743755770757,0.48054029304029305,0.06880534223264967 +flat_mae,patch,logistic,aabc_age,75,0.005994842503189409,train,0.6653543307086615,0.020314579133328136,0.6641624453503758,0.020368074026564053,0.6663250711081361,0.020291347894793154 +flat_mae,patch,logistic,aabc_age,75,0.005994842503189409,test,0.5,0.06770996273263216,0.5036117330944917,0.06703733101258302,0.5011446886446886,0.0680457248040162 +flat_mae,patch,logistic,aabc_age,76,0.005994842503189409,train,0.6771653543307087,0.02003412172350129,0.6764382211927352,0.0203264742546975,0.6777515204578539,0.02004620745909594 +flat_mae,patch,logistic,aabc_age,76,0.005994842503189409,test,0.5192307692307693,0.06628136189692577,0.5246794871794872,0.06532330837209929,0.5190018315018315,0.06663221228798709 +flat_mae,patch,logistic,aabc_age,77,0.046415888336127774,train,0.8208661417322834,0.017456834978946633,0.82114425849166,0.017570180780025986,0.8214597210528032,0.017344898590149666 +flat_mae,patch,logistic,aabc_age,77,0.046415888336127774,test,0.46153846153846156,0.06748099666752562,0.4591823406478579,0.06816639924901696,0.4626831501831502,0.067870503155683 +flat_mae,patch,logistic,aabc_age,78,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,78,2.782559402207126,test,0.5384615384615384,0.06688039089591606,0.5379105090311986,0.06656276092557085,0.5366300366300366,0.06686026496924591 +flat_mae,patch,logistic,aabc_age,79,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,79,21.54434690031882,test,0.4423076923076923,0.06653717206398382,0.44144361385740694,0.06509853936754989,0.43887362637362637,0.0661289259030701 +flat_mae,patch,logistic,aabc_age,80,0.005994842503189409,train,0.6633858267716536,0.020951634027968728,0.6636685128574467,0.021207190766588814,0.6649440245191212,0.021032586137464712 +flat_mae,patch,logistic,aabc_age,80,0.005994842503189409,test,0.46153846153846156,0.0595402876881542,0.45875139353400224,0.05708948653682306,0.4652014652014652,0.06035814790138314 +flat_mae,patch,logistic,aabc_age,81,0.046415888336127774,train,0.8267716535433071,0.01567309928801839,0.8266417981055114,0.015881299955215842,0.8282607851335567,0.01563142054385874 +flat_mae,patch,logistic,aabc_age,81,0.046415888336127774,test,0.5384615384615384,0.06122999612963814,0.5320831342570473,0.06390259114981099,0.5325091575091575,0.061366710342893385 +flat_mae,patch,logistic,aabc_age,82,0.005994842503189409,train,0.6712598425196851,0.020856637264876524,0.6702802093625302,0.021062460660786687,0.6725234182155742,0.02084220719336721 +flat_mae,patch,logistic,aabc_age,82,0.005994842503189409,test,0.5769230769230769,0.06301614097728167,0.5608196627933469,0.064526381116307,0.5707417582417582,0.06295671406687693 +flat_mae,patch,logistic,aabc_age,83,0.005994842503189409,train,0.6791338582677166,0.021289813738319504,0.6791121357380829,0.0214427469783988,0.6793825003979754,0.02128084691579178 +flat_mae,patch,logistic,aabc_age,83,0.005994842503189409,test,0.46153846153846156,0.06223047209209274,0.45105820105820105,0.062148154131435075,0.4608516483516484,0.0621189175340598 +flat_mae,patch,logistic,aabc_age,84,0.3593813663804626,train,0.9921259842519685,0.0036888293149620493,0.991968873541782,0.003768345640422847,0.9918854972007465,0.0038018122522592386 +flat_mae,patch,logistic,aabc_age,84,0.3593813663804626,test,0.5384615384615384,0.060017699559005336,0.529831125492972,0.05858272647415644,0.532051282051282,0.05954008769211302 +flat_mae,patch,logistic,aabc_age,85,0.005994842503189409,train,0.6712598425196851,0.01990333917426472,0.6724626203912064,0.019941015362311673,0.6720206745827012,0.019859233886513044 +flat_mae,patch,logistic,aabc_age,85,0.005994842503189409,test,0.4230769230769231,0.062305840428320124,0.414080459770115,0.06289341512237494,0.42239010989010994,0.06217192246166591 +flat_mae,patch,logistic,aabc_age,86,0.046415888336127774,train,0.8366141732283464,0.01567849757248993,0.8372302856491638,0.015646792127065375,0.8375711321105739,0.015580442458404797 +flat_mae,patch,logistic,aabc_age,86,0.046415888336127774,test,0.5384615384615384,0.0604399428059833,0.514081419429467,0.06122515815933077,0.5306776556776557,0.05983221053352019 +flat_mae,patch,logistic,aabc_age,87,0.046415888336127774,train,0.8385826771653543,0.01616168538241446,0.8381199072328782,0.016409133639176777,0.8394872878023893,0.016128633303715178 +flat_mae,patch,logistic,aabc_age,87,0.046415888336127774,test,0.4807692307692308,0.06648106684252825,0.47540652750547807,0.06692750950014986,0.48328754578754574,0.06689059155117949 +flat_mae,patch,logistic,aabc_age,88,0.3593813663804626,train,0.9822834645669292,0.0056406538303596715,0.9820900717970121,0.00571760425639775,0.9818724599099713,0.005793126151804994 +flat_mae,patch,logistic,aabc_age,88,0.3593813663804626,test,0.5,0.0637306183555152,0.4956394180532111,0.06461637356953384,0.5041208791208791,0.06408077436438259 +flat_mae,patch,logistic,aabc_age,89,9.999999999999999e-05,train,0.5098425196850394,0.020663103685741598,0.4835811909388966,0.021296166077560536,0.5061568713570865,0.020584935766117165 +flat_mae,patch,logistic,aabc_age,89,9.999999999999999e-05,test,0.38461538461538464,0.06697057333118549,0.3693687430478309,0.06819441732477594,0.3823260073260073,0.06666975230319133 +flat_mae,patch,logistic,aabc_age,90,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,90,21.54434690031882,test,0.5961538461538461,0.06236483609426941,0.5884762164372359,0.06547766520192251,0.594551282051282,0.062470899669501964 +flat_mae,patch,logistic,aabc_age,91,0.3593813663804626,train,0.984251968503937,0.0057539555278094,0.984156045150669,0.005803208244318628,0.9841561434936295,0.005805608593249254 +flat_mae,patch,logistic,aabc_age,91,0.3593813663804626,test,0.4423076923076923,0.06146316306700447,0.4331709956709956,0.06365077165313215,0.4432234432234432,0.061762697931132614 +flat_mae,patch,logistic,aabc_age,92,0.3593813663804626,train,0.9881889763779528,0.004791354757702747,0.9880955895049299,0.004825477283215789,0.9877532657957877,0.004969503294676485 +flat_mae,patch,logistic,aabc_age,92,0.3593813663804626,test,0.5192307692307693,0.05662315738867554,0.49064842578710643,0.06337872003748748,0.5215201465201466,0.057141632459638596 +flat_mae,patch,logistic,aabc_age,93,0.046415888336127774,train,0.8248031496062992,0.017192676730988288,0.824709081739575,0.01732979624821437,0.826077074890341,0.017202522431792315 +flat_mae,patch,logistic,aabc_age,93,0.046415888336127774,test,0.4230769230769231,0.06786336559980313,0.43040293040293043,0.06536863548612276,0.423992673992674,0.0681703454470473 +flat_mae,patch,logistic,aabc_age,94,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,94,2.782559402207126,test,0.4230769230769231,0.06584474971543865,0.4178302731751008,0.0670618344460979,0.4226190476190476,0.06574187256542417 +flat_mae,patch,logistic,aabc_age,95,0.046415888336127774,train,0.8208661417322834,0.017022290386923253,0.8211095476339378,0.017126368861312698,0.8225799259286253,0.016953300023200984 +flat_mae,patch,logistic,aabc_age,95,0.046415888336127774,test,0.5,0.06049284763825072,0.47771883289124667,0.05921468754823437,0.4935897435897436,0.05977148572017967 +flat_mae,patch,logistic,aabc_age,96,0.3593813663804626,train,0.9862204724409449,0.005311866991168151,0.9860689123315768,0.005363952556050384,0.9859547046447086,0.0054104752460144385 +flat_mae,patch,logistic,aabc_age,96,0.3593813663804626,test,0.4807692307692308,0.06720083825907154,0.49259057971014497,0.06510253699153584,0.4789377289377289,0.06723422857870358 +flat_mae,patch,logistic,aabc_age,97,0.005994842503189409,train,0.6791338582677166,0.02024054727173916,0.6782728853642337,0.02048842055201509,0.6792825270575329,0.02022946236289833 +flat_mae,patch,logistic,aabc_age,97,0.005994842503189409,test,0.40384615384615385,0.06134916799925801,0.3825396825396825,0.05960683967407292,0.39720695970695974,0.06033209346767356 +flat_mae,patch,logistic,aabc_age,98,0.046415888336127774,train,0.8267716535433071,0.01622857902693746,0.8274983788532999,0.016200208906597905,0.828093203922599,0.0160748633737923 +flat_mae,patch,logistic,aabc_age,98,0.046415888336127774,test,0.46153846153846156,0.06651923910867917,0.4672505017332603,0.06430804975054018,0.4567307692307693,0.06649606644104135 +flat_mae,patch,logistic,aabc_age,99,0.046415888336127774,train,0.8326771653543307,0.016048547523428887,0.8325759773197672,0.016144613287686006,0.833588860716279,0.015993334700649352 +flat_mae,patch,logistic,aabc_age,99,0.046415888336127774,test,0.46153846153846156,0.06904859578500967,0.46095238095238095,0.06782319165737775,0.4610805860805861,0.06940556999979519 +flat_mae,patch,logistic,aabc_age,100,0.3593813663804626,train,0.9960629921259843,0.002749441237570683,0.9960256812008625,0.0027830878927365688,0.9959177552652626,0.0028485888562210875 +flat_mae,patch,logistic,aabc_age,100,0.3593813663804626,test,0.4807692307692308,0.06634608695648803,0.48582228116710874,0.06550616155108914,0.480540293040293,0.06628520331715196 diff --git a/input_space_v3/flat_lr1e-3_4/eval_v2/aabc_age__patch__logistic/log.txt b/input_space_v3/flat_lr1e-3_4/eval_v2/aabc_age__patch__logistic/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..3ec1b0c2ca80f528a467589d4e2a5d54f150d3c4 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_4/eval_v2/aabc_age__patch__logistic/log.txt @@ -0,0 +1,245 @@ +fMRI foundation model logistic probe eval +version: 0.1.dev86+gf97f52698 +sha: bcce2b486277d3a5b520775efd9cdf1a2affce36, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-04-08 22:23:55 +config: +output_root: experiments/input_space_v3/output +name_prefix: eval_logistic +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_4; eval v2 (aabc_age patch logistic) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: input_space_v3/flat_lr1e-3_4/eval_v2/aabc_age__patch__logistic +model: flat_mae +representation: patch +dataset: aabc_age +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/eval_v2/aabc_age__patch__logistic +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=True, reg_tokens=0, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: aabc_age (flat) +train (n=455): +HFDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'segment', 'bold', 'mean', 'std'], + num_rows: 471 +}), + labels=[0 1 2 3], + counts=[110 127 109 109] +) + +validation (n=53): +HFDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'segment', 'bold', 'mean', 'std'], + num_rows: 58 +}), + labels=[0 1 2 3], + counts=[14 13 12 14] +) + +test (n=52): +HFDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'segment', 'bold', 'mean', 'std'], + num_rows: 55 +}), + labels=[0 1 2 3], + counts=[13 13 12 14] +) + +extracting features for all splits +extract (train) [ 0/228] eta: 0:23:31 time: 6.1914 data: 5.4520 max mem: 3205 +extract (train) [ 20/228] eta: 0:01:58 time: 0.2876 data: 0.0989 max mem: 3393 +extract (train) [ 40/228] eta: 0:01:17 time: 0.2499 data: 0.0830 max mem: 3393 +extract (train) [ 60/228] eta: 0:01:00 time: 0.2518 data: 0.0869 max mem: 3393 +extract (train) [ 80/228] eta: 0:00:48 time: 0.2364 data: 0.0756 max mem: 3393 +extract (train) [100/228] eta: 0:00:40 time: 0.2597 data: 0.0901 max mem: 3393 +extract (train) [120/228] eta: 0:00:32 time: 0.2429 data: 0.0811 max mem: 3393 +extract (train) [140/228] eta: 0:00:25 time: 0.2138 data: 0.0654 max mem: 3393 +extract (train) [160/228] eta: 0:00:19 time: 0.2629 data: 0.0907 max mem: 3393 +extract (train) [180/228] eta: 0:00:13 time: 0.2496 data: 0.0852 max mem: 3393 +extract (train) [200/228] eta: 0:00:07 time: 0.2463 data: 0.0860 max mem: 3393 +extract (train) [220/228] eta: 0:00:02 time: 0.2032 data: 0.0601 max mem: 3393 +extract (train) [227/228] eta: 0:00:00 time: 0.2011 data: 0.0611 max mem: 3393 +extract (train) Total time: 0:01:02 (0.2726 s / it) +extract (validation) [ 0/27] eta: 0:02:26 time: 5.4173 data: 5.2058 max mem: 3393 +extract (validation) [20/27] eta: 0:00:03 time: 0.2336 data: 0.0705 max mem: 3393 +extract (validation) [26/27] eta: 0:00:00 time: 0.2010 data: 0.0588 max mem: 3393 +extract (validation) Total time: 0:00:11 (0.4270 s / it) +extract (test) [ 0/26] eta: 0:02:20 time: 5.4147 data: 5.2627 max mem: 3393 +extract (test) [20/26] eta: 0:00:02 time: 0.2123 data: 0.0588 max mem: 3393 +extract (test) [25/26] eta: 0:00:00 time: 0.2086 data: 0.0585 max mem: 3393 +extract (test) Total time: 0:00:10 (0.4230 s / it) +feature extraction time: 0:01:24 +train features: (455, 768) +validation features: (53, 768) +test features: (52, 768) +evaluating fixed splits +eval results (fixed splits): + +| model | repr | clf | dataset | trial | C | split | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|----------:|:--------|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | aabc_age | | 0.0059948 | train | 0.66732 | 0.021218 | 0.66624 | 0.021261 | 0.66747 | 0.021232 | +| flat_mae | patch | logistic | aabc_age | | 0.0059948 | test | 0.48077 | 0.061422 | 0.45137 | 0.066988 | 0.47047 | 0.061562 | + + +evaluating random splits (n=100) +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 1, "C": 0.005994842503189409, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.058022695008890054, "f1": 0.42975738682569803, "f1_std": 0.05513428608916521, "bacc": 0.4548992673992674, "bacc_std": 0.05705275276614616} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 2, "C": 0.000774263682681127, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.06802204437320344, "f1": 0.4574891774891775, "f1_std": 0.0666692789630134, "bacc": 0.4567307692307693, "bacc_std": 0.06742752211470947} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 3, "C": 0.046415888336127774, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.0670990612726336, "f1": 0.6118518518518519, "f1_std": 0.0668335478719623, "bacc": 0.612408424908425, "bacc_std": 0.0672037833962049} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 4, "C": 0.3593813663804626, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.06080888433609996, "f1": 0.5324756852343059, "f1_std": 0.061389748390063566, "bacc": 0.5409798534798536, "bacc_std": 0.06112499016660267} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 5, "C": 0.3593813663804626, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.06421325187199547, "f1": 0.4708222811671088, "f1_std": 0.06514378376080822, "bacc": 0.4787087912087912, "bacc_std": 0.06442242623548348} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 6, "C": 0.005994842503189409, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.06863638002343869, "f1": 0.512962962962963, "f1_std": 0.07019419831567665, "bacc": 0.516025641025641, "bacc_std": 0.06838091209486596} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 7, "C": 166.81005372000556, "split": "test", "acc": 0.5, "acc_std": 0.06648325855912188, "f1": 0.5015207780725022, "f1_std": 0.06551915364198985, "bacc": 0.4954212454212454, "bacc_std": 0.06661137990224329} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 8, "C": 0.3593813663804626, "split": "test", "acc": 0.5576923076923077, "acc_std": 0.06329951344494572, "f1": 0.552848575712144, "f1_std": 0.0651348490914023, "bacc": 0.5606684981684982, "bacc_std": 0.06349260506763364} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 9, "C": 0.005994842503189409, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.06535062464897971, "f1": 0.4726399462606359, "f1_std": 0.06491178837798812, "bacc": 0.47870879120879123, "bacc_std": 0.06532947961052876} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 10, "C": 0.000774263682681127, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.06425010072978082, "f1": 0.4415292353823088, "f1_std": 0.06481380232458177, "bacc": 0.44184981684981683, "bacc_std": 0.06415966987207432} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 11, "C": 0.046415888336127774, "split": "test", "acc": 0.6730769230769231, "acc_std": 0.06426897758086665, "f1": 0.677915506532448, "f1_std": 0.06432523640481037, "bacc": 0.674908424908425, "bacc_std": 0.06424154360248845} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 12, "C": 0.005994842503189409, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.06577407764416639, "f1": 0.4574884792626728, "f1_std": 0.06770309159557743, "bacc": 0.46130952380952384, "bacc_std": 0.06593619003497556} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 13, "C": 0.005994842503189409, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.06376482308233822, "f1": 0.4139663954101048, "f1_std": 0.06314379181576388, "bacc": 0.4194139194139194, "bacc_std": 0.06333959379550484} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 14, "C": 0.3593813663804626, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.06588742191696306, "f1": 0.5357142857142857, "f1_std": 0.0667542785199311, "bacc": 0.5428113553113554, "bacc_std": 0.0659733962921931} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 15, "C": 0.005994842503189409, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.06881714042713521, "f1": 0.4372159090909091, "f1_std": 0.06787975670908246, "bacc": 0.42422161172161177, "bacc_std": 0.06920073049765091} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 16, "C": 0.005994842503189409, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.0679200169186143, "f1": 0.4635573553092735, "f1_std": 0.06669114023863902, "bacc": 0.4581043956043956, "bacc_std": 0.06745786351590514} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 17, "C": 0.000774263682681127, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.061661607554083814, "f1": 0.39890109890109887, "f1_std": 0.05783283963940749, "bacc": 0.41781135531135527, "bacc_std": 0.06060155422615813} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 18, "C": 0.005994842503189409, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.06552988387349219, "f1": 0.5187240295935949, "f1_std": 0.06397454151432118, "bacc": 0.5144230769230769, "bacc_std": 0.0651666604817252} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 19, "C": 2.782559402207126, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.06655925642151221, "f1": 0.4642567110309046, "f1_std": 0.06832633761367016, "bacc": 0.46130952380952384, "bacc_std": 0.06683569745737158} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 20, "C": 0.000774263682681127, "split": "test", "acc": 0.5576923076923077, "acc_std": 0.061921117981436714, "f1": 0.534471853257432, "f1_std": 0.06881360398808928, "bacc": 0.5528846153846154, "bacc_std": 0.06189097076504942} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 21, "C": 0.046415888336127774, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.06344153530902973, "f1": 0.43002901519030545, "f1_std": 0.06427285256702801, "bacc": 0.44459706959706957, "bacc_std": 0.06386426333885377} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 22, "C": 0.005994842503189409, "split": "test", "acc": 0.36538461538461536, "acc_std": 0.06583666133949505, "f1": 0.3600210084033614, "f1_std": 0.06504252354169933, "bacc": 0.3651556776556777, "bacc_std": 0.06592571097571771} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 23, "C": 2.782559402207126, "split": "test", "acc": 0.5, "acc_std": 0.06648925481547495, "f1": 0.4990322580645161, "f1_std": 0.06605810077417204, "bacc": 0.5041208791208791, "bacc_std": 0.06702525484537834} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 24, "C": 0.046415888336127774, "split": "test", "acc": 0.38461538461538464, "acc_std": 0.06266629946596014, "f1": 0.39673466838009563, "f1_std": 0.061197254317959526, "bacc": 0.3855311355311355, "bacc_std": 0.0628725071636741} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 25, "C": 0.3593813663804626, "split": "test", "acc": 0.36538461538461536, "acc_std": 0.06385888427299459, "f1": 0.38339080459770114, "f1_std": 0.061871396754807975, "bacc": 0.36469780219780223, "bacc_std": 0.06378954920935768} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 26, "C": 166.81005372000556, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.06953995063075477, "f1": 0.5173789173789174, "f1_std": 0.0695156198687675, "bacc": 0.5190018315018315, "bacc_std": 0.0696038583826886} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 27, "C": 0.005994842503189409, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.06389530082451778, "f1": 0.41254208754208754, "f1_std": 0.064818024032729, "bacc": 0.4198717948717949, "bacc_std": 0.0636812590205268} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 28, "C": 0.3593813663804626, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.06378588443577808, "f1": 0.5109076109076109, "f1_std": 0.06523139683333375, "bacc": 0.5187728937728937, "bacc_std": 0.06399732832925407} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 29, "C": 0.3593813663804626, "split": "test", "acc": 0.5769230769230769, "acc_std": 0.0641118083078074, "f1": 0.5755570291777188, "f1_std": 0.06503603415902622, "bacc": 0.5782967032967032, "bacc_std": 0.0643466551362433} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 30, "C": 0.005994842503189409, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.06761494705380429, "f1": 0.5373578595317725, "f1_std": 0.06648771016796089, "bacc": 0.5425824175824177, "bacc_std": 0.06780277899356701} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 31, "C": 0.046415888336127774, "split": "test", "acc": 0.5961538461538461, "acc_std": 0.05866940525031795, "f1": 0.572872992784005, "f1_std": 0.06114939323821019, "bacc": 0.5885989010989011, "bacc_std": 0.05828253052267649} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 32, "C": 0.046415888336127774, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.06891513518805695, "f1": 0.5318840579710145, "f1_std": 0.06782333448805451, "bacc": 0.5322802197802198, "bacc_std": 0.06868313241805386} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 33, "C": 166.81005372000556, "split": "test", "acc": 0.40384615384615385, "acc_std": 0.06838137052092132, "f1": 0.4026078088578089, "f1_std": 0.06863538214254236, "bacc": 0.402014652014652, "bacc_std": 0.06839563343581948} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 34, "C": 0.3593813663804626, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.064223571683326, "f1": 0.46054376657824936, "f1_std": 0.0674609216306421, "bacc": 0.46886446886446886, "bacc_std": 0.06418213026902736} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 35, "C": 0.046415888336127774, "split": "test", "acc": 0.36538461538461536, "acc_std": 0.06294398514768658, "f1": 0.3621351766513057, "f1_std": 0.06157119658622337, "bacc": 0.3630952380952381, "bacc_std": 0.06261526239695116} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 36, "C": 0.3593813663804626, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.06459105540142399, "f1": 0.5345238095238095, "f1_std": 0.06609687814272953, "bacc": 0.5412087912087913, "bacc_std": 0.0648941685115264} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 37, "C": 0.005994842503189409, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.06586475294475318, "f1": 0.5157990157990158, "f1_std": 0.06806450914685719, "bacc": 0.5146520146520146, "bacc_std": 0.06578527489258351} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 38, "C": 9.999999999999999e-05, "split": "test", "acc": 0.5, "acc_std": 0.062111514525781696, "f1": 0.46413308913308915, "f1_std": 0.06041298118322393, "bacc": 0.49061355311355315, "bacc_std": 0.061102615066612104} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 39, "C": 166.81005372000556, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.0650945943455964, "f1": 0.4257575757575758, "f1_std": 0.06525339735850032, "bacc": 0.42284798534798534, "bacc_std": 0.06502581577710059} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 40, "C": 0.005994842503189409, "split": "test", "acc": 0.5576923076923077, "acc_std": 0.05876453615965305, "f1": 0.5380587484035759, "f1_std": 0.06276590141143555, "bacc": 0.5556318681318682, "bacc_std": 0.05871182509810279} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 41, "C": 0.3593813663804626, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.05799636542376482, "f1": 0.44816990341287016, "f1_std": 0.06273068064481893, "bacc": 0.47573260073260076, "bacc_std": 0.05749226364488999} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 42, "C": 0.005994842503189409, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.06364392207090987, "f1": 0.4381950664278251, "f1_std": 0.06573186312060156, "bacc": 0.4700091575091575, "bacc_std": 0.0645870812638822} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 43, "C": 0.005994842503189409, "split": "test", "acc": 0.5, "acc_std": 0.07077073576995027, "f1": 0.5046786546786546, "f1_std": 0.07184474608633598, "bacc": 0.4967948717948718, "bacc_std": 0.07076052905267642} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 44, "C": 0.046415888336127774, "split": "test", "acc": 0.5, "acc_std": 0.07203996055773325, "f1": 0.5038591901319812, "f1_std": 0.07227391051125866, "bacc": 0.4983974358974359, "bacc_std": 0.07208224737096779} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 45, "C": 0.005994842503189409, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.06353467813284165, "f1": 0.4460439560439561, "f1_std": 0.06228299113620787, "bacc": 0.4432234432234432, "bacc_std": 0.06381462459321155} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 46, "C": 21.54434690031882, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.06861360596176914, "f1": 0.4239764492753623, "f1_std": 0.06952302338384599, "bacc": 0.4198717948717949, "bacc_std": 0.0688004917299711} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 47, "C": 0.005994842503189409, "split": "test", "acc": 0.5, "acc_std": 0.06695936240002402, "f1": 0.5033866995073891, "f1_std": 0.06788524263019614, "bacc": 0.5011446886446886, "bacc_std": 0.06700161688214507} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 48, "C": 0.005994842503189409, "split": "test", "acc": 0.40384615384615385, "acc_std": 0.0640872532997238, "f1": 0.39855828488795286, "f1_std": 0.06663590218293329, "bacc": 0.4017857142857143, "bacc_std": 0.06418370178325516} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 49, "C": 21.54434690031882, "split": "test", "acc": 0.3269230769230769, "acc_std": 0.06183078406415502, "f1": 0.3223389355742297, "f1_std": 0.05917847469182315, "bacc": 0.3216575091575092, "bacc_std": 0.060889890707972974} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 50, "C": 166.81005372000556, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.06316947946670666, "f1": 0.4598597475455821, "f1_std": 0.06482425128494712, "bacc": 0.45993589743589747, "bacc_std": 0.06366823834178918} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 51, "C": 0.046415888336127774, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.06488427340204438, "f1": 0.5011322463768116, "f1_std": 0.06200959809416161, "bacc": 0.51007326007326, "bacc_std": 0.06429907089122472} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 52, "C": 0.046415888336127774, "split": "test", "acc": 0.5, "acc_std": 0.07087261470266847, "f1": 0.5063636363636363, "f1_std": 0.07153000971477359, "bacc": 0.5, "bacc_std": 0.07094505825920273} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 53, "C": 0.000774263682681127, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.0621859684700352, "f1": 0.5222832722832722, "f1_std": 0.06375587861041981, "bacc": 0.5350274725274725, "bacc_std": 0.0620360393644066} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 54, "C": 0.005994842503189409, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.06032579202490385, "f1": 0.4077875529488433, "f1_std": 0.06081360166182579, "bacc": 0.42536630036630035, "bacc_std": 0.06089937479872156} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 55, "C": 0.005994842503189409, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.0626344234899401, "f1": 0.5457849940608561, "f1_std": 0.06055327210293257, "bacc": 0.5425824175824175, "bacc_std": 0.06303357329162877} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 56, "C": 0.000774263682681127, "split": "test", "acc": 0.40384615384615385, "acc_std": 0.06765098170347411, "f1": 0.3901112030144288, "f1_std": 0.06707207236555582, "bacc": 0.4001831501831502, "bacc_std": 0.06725143246117919} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 57, "C": 0.046415888336127774, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.061430241381692605, "f1": 0.42857142857142855, "f1_std": 0.05860489115789958, "bacc": 0.440018315018315, "bacc_std": 0.061139146955317115} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 58, "C": 0.046415888336127774, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.05849567576189062, "f1": 0.4239684062892153, "f1_std": 0.06303512994044862, "bacc": 0.4416208791208791, "bacc_std": 0.05853628218971281} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 59, "C": 0.3593813663804626, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.07208536811210711, "f1": 0.4510188087774295, "f1_std": 0.07036128290750994, "bacc": 0.4391025641025641, "bacc_std": 0.07192140253191502} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 60, "C": 0.005994842503189409, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.06238005057756183, "f1": 0.44278117715617715, "f1_std": 0.06270351955832057, "bacc": 0.44024725274725274, "bacc_std": 0.06247326727729716} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 61, "C": 2.782559402207126, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.06587373613532206, "f1": 0.4604500891265597, "f1_std": 0.06651078006017344, "bacc": 0.45535714285714285, "bacc_std": 0.06591485681689109} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 62, "C": 0.046415888336127774, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.06400669112581699, "f1": 0.5206959706959706, "f1_std": 0.061240156591357495, "bacc": 0.5306776556776557, "bacc_std": 0.06345267910102838} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 63, "C": 0.005994842503189409, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.05969419108844797, "f1": 0.4400228937728938, "f1_std": 0.06030763473239976, "bacc": 0.4578754578754579, "bacc_std": 0.05937281379908385} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 64, "C": 0.3593813663804626, "split": "test", "acc": 0.34615384615384615, "acc_std": 0.061785310197594846, "f1": 0.3543947286934664, "f1_std": 0.06196768497903255, "bacc": 0.3456959706959707, "bacc_std": 0.061687321065751345} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 65, "C": 0.046415888336127774, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.06754655418486216, "f1": 0.45454545454545453, "f1_std": 0.06756552894178838, "bacc": 0.4553571428571428, "bacc_std": 0.06720324248397239} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 66, "C": 0.005994842503189409, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.06504258959742042, "f1": 0.4455128205128205, "f1_std": 0.06301910824479973, "bacc": 0.4461996336996337, "bacc_std": 0.06568272948965478} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 67, "C": 0.046415888336127774, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.06292499291797982, "f1": 0.4246498599439776, "f1_std": 0.060305631139080704, "bacc": 0.4356684981684982, "bacc_std": 0.06197006970247393} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 68, "C": 0.3593813663804626, "split": "test", "acc": 0.40384615384615385, "acc_std": 0.060307447016769614, "f1": 0.3938228438228438, "f1_std": 0.058712274140929735, "bacc": 0.4059065934065934, "bacc_std": 0.06110441472713985} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 69, "C": 0.005994842503189409, "split": "test", "acc": 0.40384615384615385, "acc_std": 0.06912747636190462, "f1": 0.41154422788605693, "f1_std": 0.06919491969647079, "bacc": 0.40636446886446886, "bacc_std": 0.06960132863631073} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 70, "C": 0.3593813663804626, "split": "test", "acc": 0.40384615384615385, "acc_std": 0.06921763764349911, "f1": 0.40170940170940167, "f1_std": 0.06929866477058474, "bacc": 0.40636446886446886, "bacc_std": 0.06990620821985759} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 71, "C": 0.000774263682681127, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.06252302534446692, "f1": 0.4784382284382284, "f1_std": 0.06155192303592383, "bacc": 0.47870879120879123, "bacc_std": 0.06228922488168949} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 72, "C": 2.782559402207126, "split": "test", "acc": 0.5769230769230769, "acc_std": 0.06280988266942349, "f1": 0.5705801768046368, "f1_std": 0.0646502546441943, "bacc": 0.5737179487179487, "bacc_std": 0.06293512857638722} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 73, "C": 0.3593813663804626, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.06743055818777415, "f1": 0.4603916791604198, "f1_std": 0.0661380006233578, "bacc": 0.44207875457875456, "bacc_std": 0.06766897444553473} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 74, "C": 0.005994842503189409, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.06869123093307174, "f1": 0.4873863636363637, "f1_std": 0.06930743755770757, "bacc": 0.48054029304029305, "bacc_std": 0.06880534223264967} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 75, "C": 0.005994842503189409, "split": "test", "acc": 0.5, "acc_std": 0.06770996273263216, "f1": 0.5036117330944917, "f1_std": 0.06703733101258302, "bacc": 0.5011446886446886, "bacc_std": 0.0680457248040162} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 76, "C": 0.005994842503189409, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.06628136189692577, "f1": 0.5246794871794872, "f1_std": 0.06532330837209929, "bacc": 0.5190018315018315, "bacc_std": 0.06663221228798709} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 77, "C": 0.046415888336127774, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.06748099666752562, "f1": 0.4591823406478579, "f1_std": 0.06816639924901696, "bacc": 0.4626831501831502, "bacc_std": 0.067870503155683} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 78, "C": 2.782559402207126, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.06688039089591606, "f1": 0.5379105090311986, "f1_std": 0.06656276092557085, "bacc": 0.5366300366300366, "bacc_std": 0.06686026496924591} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 79, "C": 21.54434690031882, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.06653717206398382, "f1": 0.44144361385740694, "f1_std": 0.06509853936754989, "bacc": 0.43887362637362637, "bacc_std": 0.0661289259030701} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 80, "C": 0.005994842503189409, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.0595402876881542, "f1": 0.45875139353400224, "f1_std": 0.05708948653682306, "bacc": 0.4652014652014652, "bacc_std": 0.06035814790138314} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 81, "C": 0.046415888336127774, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.06122999612963814, "f1": 0.5320831342570473, "f1_std": 0.06390259114981099, "bacc": 0.5325091575091575, "bacc_std": 0.061366710342893385} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 82, "C": 0.005994842503189409, "split": "test", "acc": 0.5769230769230769, "acc_std": 0.06301614097728167, "f1": 0.5608196627933469, "f1_std": 0.064526381116307, "bacc": 0.5707417582417582, "bacc_std": 0.06295671406687693} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 83, "C": 0.005994842503189409, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.06223047209209274, "f1": 0.45105820105820105, "f1_std": 0.062148154131435075, "bacc": 0.4608516483516484, "bacc_std": 0.0621189175340598} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 84, "C": 0.3593813663804626, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.060017699559005336, "f1": 0.529831125492972, "f1_std": 0.05858272647415644, "bacc": 0.532051282051282, "bacc_std": 0.05954008769211302} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 85, "C": 0.005994842503189409, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.062305840428320124, "f1": 0.414080459770115, "f1_std": 0.06289341512237494, "bacc": 0.42239010989010994, "bacc_std": 0.06217192246166591} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 86, "C": 0.046415888336127774, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.0604399428059833, "f1": 0.514081419429467, "f1_std": 0.06122515815933077, "bacc": 0.5306776556776557, "bacc_std": 0.05983221053352019} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 87, "C": 0.046415888336127774, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.06648106684252825, "f1": 0.47540652750547807, "f1_std": 0.06692750950014986, "bacc": 0.48328754578754574, "bacc_std": 0.06689059155117949} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 88, "C": 0.3593813663804626, "split": "test", "acc": 0.5, "acc_std": 0.0637306183555152, "f1": 0.4956394180532111, "f1_std": 0.06461637356953384, "bacc": 0.5041208791208791, "bacc_std": 0.06408077436438259} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 89, "C": 9.999999999999999e-05, "split": "test", "acc": 0.38461538461538464, "acc_std": 0.06697057333118549, "f1": 0.3693687430478309, "f1_std": 0.06819441732477594, "bacc": 0.3823260073260073, "bacc_std": 0.06666975230319133} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 90, "C": 21.54434690031882, "split": "test", "acc": 0.5961538461538461, "acc_std": 0.06236483609426941, "f1": 0.5884762164372359, "f1_std": 0.06547766520192251, "bacc": 0.594551282051282, "bacc_std": 0.062470899669501964} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 91, "C": 0.3593813663804626, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.06146316306700447, "f1": 0.4331709956709956, "f1_std": 0.06365077165313215, "bacc": 0.4432234432234432, "bacc_std": 0.061762697931132614} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 92, "C": 0.3593813663804626, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.05662315738867554, "f1": 0.49064842578710643, "f1_std": 0.06337872003748748, "bacc": 0.5215201465201466, "bacc_std": 0.057141632459638596} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 93, "C": 0.046415888336127774, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.06786336559980313, "f1": 0.43040293040293043, "f1_std": 0.06536863548612276, "bacc": 0.423992673992674, "bacc_std": 0.0681703454470473} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 94, "C": 2.782559402207126, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.06584474971543865, "f1": 0.4178302731751008, "f1_std": 0.0670618344460979, "bacc": 0.4226190476190476, "bacc_std": 0.06574187256542417} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 95, "C": 0.046415888336127774, "split": "test", "acc": 0.5, "acc_std": 0.06049284763825072, "f1": 0.47771883289124667, "f1_std": 0.05921468754823437, "bacc": 0.4935897435897436, "bacc_std": 0.05977148572017967} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 96, "C": 0.3593813663804626, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.06720083825907154, "f1": 0.49259057971014497, "f1_std": 0.06510253699153584, "bacc": 0.4789377289377289, "bacc_std": 0.06723422857870358} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 97, "C": 0.005994842503189409, "split": "test", "acc": 0.40384615384615385, "acc_std": 0.06134916799925801, "f1": 0.3825396825396825, "f1_std": 0.05960683967407292, "bacc": 0.39720695970695974, "bacc_std": 0.06033209346767356} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 98, "C": 0.046415888336127774, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.06651923910867917, "f1": 0.4672505017332603, "f1_std": 0.06430804975054018, "bacc": 0.4567307692307693, "bacc_std": 0.06649606644104135} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 99, "C": 0.046415888336127774, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.06904859578500967, "f1": 0.46095238095238095, "f1_std": 0.06782319165737775, "bacc": 0.4610805860805861, "bacc_std": 0.06940556999979519} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 100, "C": 0.3593813663804626, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.06634608695648803, "f1": 0.48582228116710874, "f1_std": 0.06550616155108914, "bacc": 0.480540293040293, "bacc_std": 0.06628520331715196} +eval results (random splits): + +| model | repr | clf | dataset | split | n_trials | C | C_std | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|-----------:|-------:|--------:|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | aabc_age | train | 100 | 9.4574 | 36.527 | 0.81173 | 0.15798 | 0.81037 | 0.16019 | 0.81202 | 0.15794 | +| flat_mae | patch | logistic | aabc_age | test | 100 | 9.4574 | 36.527 | 0.47635 | 0.0619 | 0.47086 | 0.061049 | 0.47486 | 0.061721 | + + +done! total time: 0:06:16 diff --git a/input_space_v3/flat_lr1e-3_4/eval_v2/aabc_sex__patch__logistic/config.yaml b/input_space_v3/flat_lr1e-3_4/eval_v2/aabc_sex__patch__logistic/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..965aec96d8c91fdea34061258fc9a104586eab85 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_4/eval_v2/aabc_sex__patch__logistic/config.yaml @@ -0,0 +1,30 @@ +output_root: experiments/input_space_v3/output +name_prefix: eval_logistic +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_4; eval v2 (aabc_sex patch logistic) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: input_space_v3/flat_lr1e-3_4/eval_v2/aabc_sex__patch__logistic +model: flat_mae +representation: patch +dataset: aabc_sex +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/eval_v2/aabc_sex__patch__logistic +remote_dir: null diff --git a/input_space_v3/flat_lr1e-3_4/eval_v2/aabc_sex__patch__logistic/eval_table.csv b/input_space_v3/flat_lr1e-3_4/eval_v2/aabc_sex__patch__logistic/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..60734aecc622fed1df54a0f8866be167e456cb54 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_4/eval_v2/aabc_sex__patch__logistic/eval_table.csv @@ -0,0 +1,203 @@ +model,repr,clf,dataset,trial,C,split,acc,acc_std,f1,f1_std,bacc,bacc_std +flat_mae,patch,logistic,aabc_sex,,0.3593813663804626,train,0.9886578449905482,0.004434252373957125,0.9883991228070176,0.004530817686473903,0.9889783372365339,0.004378308342808693 +flat_mae,patch,logistic,aabc_sex,,0.3593813663804626,test,0.9272727272727272,0.035302236952979314,0.9252717391304348,0.036009483847222745,0.9318181818181819,0.034355789147302154 +flat_mae,patch,logistic,aabc_sex,1,0.3593813663804626,train,0.9924385633270322,0.004157456393785107,0.9922477212110554,0.004263266066657868,0.9922477212110554,0.004335492357145647 +flat_mae,patch,logistic,aabc_sex,1,0.3593813663804626,test,0.8,0.052178194362608475,0.795677136102668,0.05333235833584939,0.7975543478260869,0.053158746978290095 +flat_mae,patch,logistic,aabc_sex,2,0.005994842503189409,train,0.9035916824196597,0.013261028419109786,0.900308545034642,0.01383683409321652,0.8972053694422463,0.014238170581427541 +flat_mae,patch,logistic,aabc_sex,2,0.005994842503189409,test,0.8909090909090909,0.042825974971171465,0.8879076086956521,0.0439291054385546,0.8879076086956521,0.04377227955192134 +flat_mae,patch,logistic,aabc_sex,3,0.046415888336127774,train,0.9338374291115312,0.010823884284120459,0.9320413294426397,0.01115303180332327,0.9312553122893402,0.011415785878538408 +flat_mae,patch,logistic,aabc_sex,3,0.046415888336127774,test,0.8727272727272727,0.04386719250775453,0.8663658451926415,0.04733267711660905,0.8600543478260869,0.04814919389149477 +flat_mae,patch,logistic,aabc_sex,4,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,4,21.54434690031882,test,0.8545454545454545,0.046204589947659996,0.8521505376344086,0.04671876605989599,0.8566576086956521,0.046008012861455234 +flat_mae,patch,logistic,aabc_sex,5,0.046415888336127774,train,0.9319470699432892,0.011228415212563155,0.9301434985474073,0.011522213759268336,0.9296213253612357,0.011621834877152721 +flat_mae,patch,logistic,aabc_sex,5,0.046415888336127774,test,0.8545454545454545,0.04592856832549595,0.8484848484848485,0.04882702424295088,0.8444293478260869,0.049314894617676394 +flat_mae,patch,logistic,aabc_sex,6,0.3593813663804626,train,0.9886578449905482,0.004703821403843632,0.9883855386416862,0.004809182718114452,0.9889797473548463,0.004584816642863919 +flat_mae,patch,logistic,aabc_sex,6,0.3593813663804626,test,0.9090909090909091,0.038440956120237395,0.9071259709557582,0.039237064514256674,0.9096467391304348,0.03901810369328504 +flat_mae,patch,logistic,aabc_sex,7,0.046415888336127774,train,0.9319470699432892,0.010842818081557161,0.9301434985474073,0.011116563042704135,0.9296213253612357,0.011137861314027442 +flat_mae,patch,logistic,aabc_sex,7,0.046415888336127774,test,0.8727272727272727,0.045114524607697146,0.8683760683760684,0.04719487456324605,0.8661684782608696,0.047761048658995865 +flat_mae,patch,logistic,aabc_sex,8,0.046415888336127774,train,0.9376181474480151,0.010185159066183246,0.9360045457044925,0.010442626185882334,0.9357396172220757,0.010489694774491035 +flat_mae,patch,logistic,aabc_sex,8,0.046415888336127774,test,0.8545454545454545,0.045858265295012704,0.8521505376344086,0.04638234499419379,0.8566576086956521,0.04609714182836298 +flat_mae,patch,logistic,aabc_sex,9,0.046415888336127774,train,0.9300567107750473,0.01144801200140798,0.9283347429856068,0.011722427493671818,0.9285955039713942,0.01180020611751183 +flat_mae,patch,logistic,aabc_sex,9,0.046415888336127774,test,0.8909090909090909,0.04157182771426019,0.8863636363636364,0.04404846208860855,0.8817934782608696,0.04506940067136007 +flat_mae,patch,logistic,aabc_sex,10,0.046415888336127774,train,0.9319470699432892,0.010643760253168448,0.9300552388787683,0.01098718975043972,0.9290131598229725,0.011321190358993002 +flat_mae,patch,logistic,aabc_sex,10,0.046415888336127774,test,0.8727272727272727,0.04533803249020235,0.8711943793911007,0.04563335251515353,0.8783967391304348,0.044102688171025146 +flat_mae,patch,logistic,aabc_sex,11,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,11,2.782559402207126,test,0.9090909090909091,0.03764547979187317,0.905982905982906,0.039365429011470186,0.9035326086956521,0.04024355613698382 +flat_mae,patch,logistic,aabc_sex,12,0.3593813663804626,train,0.9886578449905482,0.004760191640983498,0.9883715818165831,0.004880631898727487,0.9883715818165831,0.004958938241335763 +flat_mae,patch,logistic,aabc_sex,12,0.3593813663804626,test,0.8,0.053141831120841435,0.790003471017008,0.05739460418818507,0.7853260869565217,0.05686894979855295 +flat_mae,patch,logistic,aabc_sex,13,0.3593813663804626,train,0.9810964083175804,0.005926540998588184,0.9806193030276386,0.006079583733961012,0.9806193030276386,0.006183073497615624 +flat_mae,patch,logistic,aabc_sex,13,0.3593813663804626,test,0.8545454545454545,0.04894491422098083,0.8521505376344086,0.04943395361828602,0.8566576086956521,0.04844967291701355 +flat_mae,patch,logistic,aabc_sex,14,0.046415888336127774,train,0.9357277882797732,0.009727990317617273,0.9341056302939711,0.00996031014613654,0.9341056302939711,0.010002957080107323 +flat_mae,patch,logistic,aabc_sex,14,0.046415888336127774,test,0.9090909090909091,0.03995892105526408,0.9071259709557582,0.04076255349689286,0.9096467391304348,0.04035061649584788 +flat_mae,patch,logistic,aabc_sex,15,0.005994842503189409,train,0.9017013232514177,0.012405607308756329,0.8982812684889363,0.012998957194888909,0.8949632169758786,0.0134443647900606 +flat_mae,patch,logistic,aabc_sex,15,0.005994842503189409,test,0.8727272727272727,0.04215052130497309,0.8663658451926415,0.045507150402806285,0.8600543478260869,0.046229144189007164 +flat_mae,patch,logistic,aabc_sex,16,0.005994842503189409,train,0.9054820415879017,0.01245133307199731,0.9023322107999527,0.012987012369073321,0.899447521908614,0.013370789093936564 +flat_mae,patch,logistic,aabc_sex,16,0.005994842503189409,test,0.8727272727272727,0.045633161785542026,0.8683760683760684,0.04795182163546548,0.8661684782608696,0.048671965435813695 +flat_mae,patch,logistic,aabc_sex,17,0.046415888336127774,train,0.9338374291115312,0.010873227623314196,0.9322085406620606,0.011148800585978275,0.9324716433658665,0.011297789374140794 +flat_mae,patch,logistic,aabc_sex,17,0.046415888336127774,test,0.8545454545454545,0.047161884035576036,0.84593837535014,0.05170675746903805,0.8383152173913043,0.051663474322057305 +flat_mae,patch,logistic,aabc_sex,18,0.005994842503189409,train,0.9054820415879017,0.012762600853513198,0.9023322107999527,0.013279582259994496,0.899447521908614,0.013611092222217437 +flat_mae,patch,logistic,aabc_sex,18,0.005994842503189409,test,0.8545454545454545,0.04743948210941931,0.8533333333333333,0.047504402777797196,0.8627717391304348,0.04568570674191256 +flat_mae,patch,logistic,aabc_sex,19,0.046415888336127774,train,0.941398865784499,0.009343912855147171,0.9398080346491953,0.009616886255253476,0.9390075910782849,0.009839857565176994 +flat_mae,patch,logistic,aabc_sex,19,0.046415888336127774,test,0.8181818181818182,0.04966665742230022,0.8151881720430108,0.05026301861719371,0.8192934782608696,0.04980479489707276 +flat_mae,patch,logistic,aabc_sex,20,0.046415888336127774,train,0.9262759924385633,0.011438346984922796,0.9242746242360844,0.01176876335379172,0.9235030335003956,0.01198350477282959 +flat_mae,patch,logistic,aabc_sex,20,0.046415888336127774,test,0.8727272727272727,0.04478878253896073,0.8699763593380614,0.04591324273825621,0.8722826086956521,0.045925498328536 +flat_mae,patch,logistic,aabc_sex,21,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,21,2.782559402207126,test,0.8181818181818182,0.05046469676748993,0.8106060606060606,0.05393697406578509,0.8070652173913043,0.05399752751318542 +flat_mae,patch,logistic,aabc_sex,22,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,22,166.81005372000556,test,0.8909090909090909,0.04323855029259143,0.8879076086956521,0.044759243312750524,0.8879076086956521,0.04506684599014458 +flat_mae,patch,logistic,aabc_sex,23,0.046415888336127774,train,0.9338374291115312,0.01070874770708428,0.9320413294426397,0.011030355670002856,0.9312553122893402,0.011303624109037872 +flat_mae,patch,logistic,aabc_sex,23,0.046415888336127774,test,0.8909090909090909,0.041831318094864275,0.8891129032258065,0.042279658695552606,0.8940217391304348,0.04152363688167574 +flat_mae,patch,logistic,aabc_sex,24,0.046415888336127774,train,0.9357277882797732,0.010924172192985315,0.9341056302939711,0.011205313921330817,0.9341056302939711,0.011323402006986758 +flat_mae,patch,logistic,aabc_sex,24,0.046415888336127774,test,0.8727272727272727,0.04666326000946293,0.8683760683760684,0.048744319286790204,0.8661684782608696,0.04914993818889417 +flat_mae,patch,logistic,aabc_sex,25,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,25,2.782559402207126,test,0.8909090909090909,0.0409172678696581,0.8879076086956521,0.04214600344618968,0.8879076086956521,0.04218684517362692 +flat_mae,patch,logistic,aabc_sex,26,0.046415888336127774,train,0.945179584120983,0.009454989252592834,0.9438299336914217,0.009668526523978847,0.9441000615492834,0.009609697031256834 +flat_mae,patch,logistic,aabc_sex,26,0.046415888336127774,test,0.8181818181818182,0.049909922165622636,0.8106060606060606,0.05327790408854357,0.8070652173913043,0.05330290661673652 +flat_mae,patch,logistic,aabc_sex,27,0.046415888336127774,train,0.9262759924385633,0.011546232094221447,0.9242746242360844,0.011899123256617105,0.9235030335003956,0.012173191030723412 +flat_mae,patch,logistic,aabc_sex,27,0.046415888336127774,test,0.9090909090909091,0.03767685130112311,0.905982905982906,0.03919191866849352,0.9035326086956521,0.039684224645481235 +flat_mae,patch,logistic,aabc_sex,28,0.3593813663804626,train,0.9886578449905482,0.004570818107504442,0.9883572497579012,0.004697850675688472,0.98776341627832,0.004943557382682007 +flat_mae,patch,logistic,aabc_sex,28,0.3593813663804626,test,0.8363636363636363,0.049275290104432976,0.8281846581048247,0.053673476715623634,0.8226902173913043,0.05372114537063825 +flat_mae,patch,logistic,aabc_sex,29,0.3593813663804626,train,0.9867674858223062,0.0048350805513404345,0.9864252066645893,0.00496639465340488,0.9861294293502154,0.005190375672153664 +flat_mae,patch,logistic,aabc_sex,29,0.3593813663804626,test,0.8363636363636363,0.049963477570212106,0.8328267477203647,0.0509023912309622,0.8349184782608696,0.050830618887802395 +flat_mae,patch,logistic,aabc_sex,30,0.005994842503189409,train,0.9017013232514177,0.012564434006822585,0.8984254992319508,0.013097640499664717,0.8955713825141417,0.013452054781472064 +flat_mae,patch,logistic,aabc_sex,30,0.005994842503189409,test,0.8545454545454545,0.0488725649347953,0.8505434782608696,0.05061717565126853,0.8505434782608696,0.05092625112086522 +flat_mae,patch,logistic,aabc_sex,31,0.005994842503189409,train,0.9130434782608695,0.011759745558301811,0.9102702144606035,0.012216236139154416,0.9078079662358216,0.01253000990131415 +flat_mae,patch,logistic,aabc_sex,31,0.005994842503189409,test,0.8181818181818182,0.049714011859903325,0.8131793478260869,0.05104185291514886,0.8131793478260869,0.050788697668920496 +flat_mae,patch,logistic,aabc_sex,32,0.3593813663804626,train,0.9905482041587902,0.004067172658290021,0.9903037190461352,0.0041782111583275805,0.9900055687446877,0.004419064440698218 +flat_mae,patch,logistic,aabc_sex,32,0.3593813663804626,test,0.8727272727272727,0.041224818008509266,0.8663658451926415,0.0445785671742003,0.8600543478260869,0.045066559353642975 +flat_mae,patch,logistic,aabc_sex,33,0.3593813663804626,train,0.9867674858223062,0.005038232407565827,0.9864417081324122,0.005158800491904458,0.9867375948884786,0.005110054665113507 +flat_mae,patch,logistic,aabc_sex,33,0.3593813663804626,test,0.9090909090909091,0.0394951780716215,0.905982905982906,0.04116368776055438,0.9035326086956521,0.0420005026510902 +flat_mae,patch,logistic,aabc_sex,34,0.3593813663804626,train,0.9867674858223062,0.00490340949330186,0.9864577733405013,0.005008822003401749,0.9873457604267417,0.004764624031042552 +flat_mae,patch,logistic,aabc_sex,34,0.3593813663804626,test,0.8727272727272727,0.0453055740645929,0.8683760683760684,0.04693834167895322,0.8661684782608696,0.04715632927381747 +flat_mae,patch,logistic,aabc_sex,35,0.005994842503189409,train,0.9035916824196597,0.01249124335492207,0.900308545034642,0.013037873254363445,0.8972053694422463,0.013421386797303553 +flat_mae,patch,logistic,aabc_sex,35,0.005994842503189409,test,0.8727272727272727,0.046215578211480667,0.8683760683760684,0.04807612640322762,0.8661684782608696,0.04838216585993931 +flat_mae,patch,logistic,aabc_sex,36,0.046415888336127774,train,0.9319470699432892,0.00998372752741024,0.9302294908994988,0.01024955078732721,0.9302294908994988,0.010439131444390069 +flat_mae,patch,logistic,aabc_sex,36,0.046415888336127774,test,0.9818181818181818,0.018143086017762634,0.9814251941911516,0.01835817997708103,0.984375,0.015591714546514762 +flat_mae,patch,logistic,aabc_sex,37,0.3593813663804626,train,0.9924385633270322,0.00406853603219959,0.9922381665052675,0.004183296176720566,0.9916395556727923,0.004524778270558783 +flat_mae,patch,logistic,aabc_sex,37,0.3593813663804626,test,0.7636363636363637,0.05901981737497335,0.7585275244849713,0.06047429600018259,0.7601902173913043,0.06034440323376556 +flat_mae,patch,logistic,aabc_sex,38,0.046415888336127774,train,0.941398865784499,0.010451702673336925,0.9398830580860384,0.010742364226138243,0.939615756616548,0.010933428344661104 +flat_mae,patch,logistic,aabc_sex,38,0.046415888336127774,test,0.8545454545454545,0.04432038129740205,0.84593837535014,0.04837640565224341,0.8383152173913043,0.04849532676542577 +flat_mae,patch,logistic,aabc_sex,39,0.046415888336127774,train,0.943289224952741,0.00980893219195222,0.9419276932084308,0.010041840138963488,0.9424660746211788,0.01012486556988205 +flat_mae,patch,logistic,aabc_sex,39,0.046415888336127774,test,0.8545454545454545,0.046336805070399806,0.8505434782608696,0.04774946750553563,0.8505434782608696,0.04798161809090987 +flat_mae,patch,logistic,aabc_sex,40,0.3593813663804626,train,0.9867674858223062,0.004967328695135314,0.9864417081324122,0.005085560653638499,0.9867375948884786,0.00500715048015192 +flat_mae,patch,logistic,aabc_sex,40,0.3593813663804626,test,0.8545454545454545,0.044957809422826324,0.8484848484848485,0.047609691706065875,0.8444293478260869,0.04807609932086562 +flat_mae,patch,logistic,aabc_sex,41,0.046415888336127774,train,0.9395085066162571,0.010696674482612563,0.9379053320421398,0.010987388088317477,0.9373736041501802,0.011126652156690802 +flat_mae,patch,logistic,aabc_sex,41,0.046415888336127774,test,0.8909090909090909,0.04036894314009142,0.8863636363636364,0.04291588350114167,0.8817934782608696,0.043790072789991356 +flat_mae,patch,logistic,aabc_sex,42,0.3593813663804626,train,0.9886578449905482,0.004672837861657569,0.9883572497579012,0.004803943316037097,0.98776341627832,0.005085602773586662 +flat_mae,patch,logistic,aabc_sex,42,0.3593813663804626,test,0.8181818181818182,0.05356382151421432,0.8151881720430108,0.05429539519956123,0.8192934782608696,0.053883914374925 +flat_mae,patch,logistic,aabc_sex,43,0.005994842503189409,train,0.9017013232514177,0.012581614310738109,0.8982812684889363,0.013143619183764927,0.8949632169758786,0.013561030430832023 +flat_mae,patch,logistic,aabc_sex,43,0.005994842503189409,test,0.8727272727272727,0.044475254518246535,0.8699763593380614,0.04548574076674774,0.8722826086956521,0.04534236254015082 +flat_mae,patch,logistic,aabc_sex,44,0.046415888336127774,train,0.945179584120983,0.010085805802695413,0.943691387252473,0.010370867632192797,0.9428837304727571,0.0105391652335549 +flat_mae,patch,logistic,aabc_sex,44,0.046415888336127774,test,0.8363636363636363,0.048848302879576824,0.8307692307692308,0.05111915878842647,0.8288043478260869,0.051358920016188095 +flat_mae,patch,logistic,aabc_sex,45,0.3593813663804626,train,0.9886578449905482,0.004604722479457112,0.9883572497579012,0.004734738686854117,0.98776341627832,0.005019565964527005 +flat_mae,patch,logistic,aabc_sex,45,0.3593813663804626,test,0.9272727272727272,0.03268706621158683,0.9260752688172043,0.033039000985195445,0.9313858695652174,0.031513128509099216 +flat_mae,patch,logistic,aabc_sex,46,0.046415888336127774,train,0.9357277882797732,0.011078062142017238,0.9339410589410589,0.011422008728165955,0.9328892992174448,0.011691165406332834 +flat_mae,patch,logistic,aabc_sex,46,0.046415888336127774,test,0.8909090909090909,0.04302449811463847,0.8891129032258065,0.04341260667220993,0.8940217391304348,0.04214063680050588 +flat_mae,patch,logistic,aabc_sex,47,0.005994842503189409,train,0.9017013232514177,0.012686355724025978,0.8984254992319508,0.013215439864955715,0.8955713825141417,0.013578540967110534 +flat_mae,patch,logistic,aabc_sex,47,0.005994842503189409,test,0.8545454545454545,0.04417958842110063,0.84593837535014,0.04852819167835517,0.8383152173913043,0.04881317694160748 +flat_mae,patch,logistic,aabc_sex,48,0.005994842503189409,train,0.9017013232514177,0.012802197845191201,0.8982812684889363,0.01337402247988072,0.8949632169758786,0.013779315874965259 +flat_mae,patch,logistic,aabc_sex,48,0.005994842503189409,test,0.9090909090909091,0.037959456405203075,0.905982905982906,0.03961412854866127,0.9035326086956521,0.04038021936568441 +flat_mae,patch,logistic,aabc_sex,49,0.005994842503189409,train,0.8979206049149339,0.013082596610316868,0.8943690095846646,0.013658825333362925,0.8910870775814063,0.014013637339987646 +flat_mae,patch,logistic,aabc_sex,49,0.005994842503189409,test,0.8909090909090909,0.040163303015201685,0.8891129032258065,0.04061507112909471,0.8940217391304348,0.03976208663406389 +flat_mae,patch,logistic,aabc_sex,50,0.046415888336127774,train,0.9395085066162571,0.01032908855770212,0.9379053320421398,0.010614429410797896,0.9373736041501802,0.010772409196533057 +flat_mae,patch,logistic,aabc_sex,50,0.046415888336127774,test,0.8909090909090909,0.04261562201434377,0.8863636363636364,0.04498333568900711,0.8817934782608696,0.045880089454211424 +flat_mae,patch,logistic,aabc_sex,51,0.046415888336127774,train,0.9338374291115312,0.010736545146445817,0.9320413294426397,0.011071736448329265,0.9312553122893402,0.011387352448204508 +flat_mae,patch,logistic,aabc_sex,51,0.046415888336127774,test,0.8727272727272727,0.04218963877345609,0.8639095086603039,0.04776262382504826,0.8539402173913043,0.04830248845015457 +flat_mae,patch,logistic,aabc_sex,52,0.3593813663804626,train,0.9848771266540642,0.00560071791270066,0.9844954424221108,0.005741775407067458,0.9844954424221108,0.005790661083703466 +flat_mae,patch,logistic,aabc_sex,52,0.3593813663804626,test,0.8545454545454545,0.04841554289056798,0.8533333333333333,0.048436810824366086,0.8627717391304348,0.046543999330586214 +flat_mae,patch,logistic,aabc_sex,53,0.046415888336127774,train,0.9300567107750473,0.011452406181916775,0.9281579768393621,0.011777817192014305,0.9273791728948679,0.011910197711984568 +flat_mae,patch,logistic,aabc_sex,53,0.046415888336127774,test,0.8727272727272727,0.0450412629918481,0.8683760683760684,0.04721119310016523,0.8661684782608696,0.04782460616763301 +flat_mae,patch,logistic,aabc_sex,54,0.046415888336127774,train,0.9376181474480151,0.010252044326036573,0.9357586819802679,0.010620717070269249,0.9339151206072862,0.011041198508497618 +flat_mae,patch,logistic,aabc_sex,54,0.046415888336127774,test,0.8181818181818182,0.052438078398390035,0.8151881720430108,0.052933455074335736,0.8192934782608696,0.05218737193013163 +flat_mae,patch,logistic,aabc_sex,55,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,55,166.81005372000556,test,0.8181818181818182,0.052136832049889115,0.8151881720430108,0.052837862244596835,0.8192934782608696,0.05237272991254551 +flat_mae,patch,logistic,aabc_sex,56,0.3593813663804626,train,0.996219281663516,0.002541092767773241,0.9961238606055277,0.002605455719528111,0.9961238606055277,0.0026489130589664694 +flat_mae,patch,logistic,aabc_sex,56,0.3593813663804626,test,0.8545454545454545,0.046759097757981746,0.8505434782608696,0.04837743093584775,0.8505434782608696,0.04869409677615898 +flat_mae,patch,logistic,aabc_sex,57,0.046415888336127774,train,0.9376181474480151,0.010423724997881755,0.9359246820459175,0.01074352842493871,0.9351314516838125,0.011014653902703765 +flat_mae,patch,logistic,aabc_sex,57,0.046415888336127774,test,0.8727272727272727,0.04418053121956519,0.8683760683760684,0.046173424430027775,0.8661684782608696,0.04655488225626282 +flat_mae,patch,logistic,aabc_sex,58,0.046415888336127774,train,0.943289224952741,0.00977964485754409,0.9417126990656403,0.010076397783112803,0.9406415780063895,0.010332085952033223 +flat_mae,patch,logistic,aabc_sex,58,0.046415888336127774,test,0.8,0.05297990886932187,0.795677136102668,0.054041794647281365,0.7975543478260869,0.05382640879522031 +flat_mae,patch,logistic,aabc_sex,59,0.005994842503189409,train,0.9035916824196597,0.012859277974033844,0.9004483312116013,0.013344531991776173,0.8978135349805094,0.013585922110955771 +flat_mae,patch,logistic,aabc_sex,59,0.005994842503189409,test,0.9272727272727272,0.033619435543759395,0.9252717391304348,0.034638595839659024,0.9252717391304348,0.03489629992152492 +flat_mae,patch,logistic,aabc_sex,60,0.005994842503189409,train,0.9035916824196597,0.012535810176585626,0.9005847953216375,0.013017547991796805,0.8984217005187725,0.013348723826775953 +flat_mae,patch,logistic,aabc_sex,60,0.005994842503189409,test,0.8545454545454545,0.04709015092404764,0.84593837535014,0.05165062940017399,0.8383152173913043,0.051938669802953974 +flat_mae,patch,logistic,aabc_sex,61,0.046415888336127774,train,0.9319470699432892,0.010614476312712128,0.9301434985474073,0.010912463719403447,0.9296213253612357,0.011103154070038364 +flat_mae,patch,logistic,aabc_sex,61,0.046415888336127774,test,0.9454545454545454,0.03015332718782238,0.9442755825734549,0.030663073855244673,0.9470108695652174,0.029618817644883864 +flat_mae,patch,logistic,aabc_sex,62,0.3593813663804626,train,0.9810964083175804,0.005963969034165512,0.9806193030276386,0.006117316073617112,0.9806193030276386,0.006207181875910034 +flat_mae,patch,logistic,aabc_sex,62,0.3593813663804626,test,0.9636363636363636,0.024080416239778583,0.9626358695652174,0.024821458262904956,0.9626358695652174,0.02523260674077854 +flat_mae,patch,logistic,aabc_sex,63,0.005994842503189409,train,0.9017013232514177,0.01277783186462266,0.8984254992319508,0.013334351177359042,0.8955713825141417,0.013722895954467589 +flat_mae,patch,logistic,aabc_sex,63,0.005994842503189409,test,0.9272727272727272,0.03528254783626294,0.9242424242424243,0.03760366176950332,0.9191576086956521,0.03965654948728789 +flat_mae,patch,logistic,aabc_sex,64,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,64,2.782559402207126,test,0.8181818181818182,0.052271686946169474,0.8151881720430108,0.05307985146253851,0.8192934782608696,0.053161638702155 +flat_mae,patch,logistic,aabc_sex,65,0.046415888336127774,train,0.9395085066162571,0.010369307747310635,0.938056206088993,0.01061413986812363,0.9385899352267065,0.010659189016481555 +flat_mae,patch,logistic,aabc_sex,65,0.046415888336127774,test,0.9454545454545454,0.03146114486733814,0.9435897435897436,0.03285559681805133,0.9408967391304348,0.03405552747591683 +flat_mae,patch,logistic,aabc_sex,66,0.005994842503189409,train,0.9073724007561437,0.012509488610299739,0.9046113762737312,0.012899607719758571,0.9029060054515079,0.01303025304775172 +flat_mae,patch,logistic,aabc_sex,66,0.005994842503189409,test,0.8727272727272727,0.03986454751731581,0.8639095086603039,0.04495239187599646,0.8539402173913043,0.045512887181104 +flat_mae,patch,logistic,aabc_sex,67,0.046415888336127774,train,0.9319470699432892,0.01113732886271871,0.9301434985474073,0.011449871159149388,0.9296213253612357,0.011649821331401725 +flat_mae,patch,logistic,aabc_sex,67,0.046415888336127774,test,0.8909090909090909,0.041541519606770154,0.8879076086956521,0.04268668487912302,0.8879076086956521,0.04275528441824081 +flat_mae,patch,logistic,aabc_sex,68,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,68,2.782559402207126,test,0.9090909090909091,0.03816933129149199,0.9045470322804582,0.041405673981038706,0.8974184782608696,0.043092593570285095 +flat_mae,patch,logistic,aabc_sex,69,0.046415888336127774,train,0.9319470699432892,0.01131575756139277,0.9301434985474073,0.011613609274699706,0.9296213253612357,0.011710948612704488 +flat_mae,patch,logistic,aabc_sex,69,0.046415888336127774,test,0.9454545454545454,0.03176798117758153,0.9435897435897436,0.0332397410130046,0.9408967391304348,0.03471989492666549 +flat_mae,patch,logistic,aabc_sex,70,0.046415888336127774,train,0.9357277882797732,0.010563894665897787,0.9340244152947736,0.010879655830304896,0.9334974647557079,0.011163960605730435 +flat_mae,patch,logistic,aabc_sex,70,0.046415888336127774,test,0.9090909090909091,0.03734803921302766,0.9086075108009306,0.03718323790034284,0.921875,0.03209597119869564 +flat_mae,patch,logistic,aabc_sex,71,0.005994842503189409,train,0.9035916824196597,0.012466900799842664,0.900308545034642,0.01300577354109656,0.8972053694422463,0.013359026318011643 +flat_mae,patch,logistic,aabc_sex,71,0.005994842503189409,test,0.8545454545454545,0.04429017763241351,0.84593837535014,0.04870379047304653,0.8383152173913043,0.04842836700820749 +flat_mae,patch,logistic,aabc_sex,72,0.3593813663804626,train,0.9848771266540642,0.004835625953446055,0.9845140515222482,0.004945466482700263,0.9851036079603739,0.004809055364007546 +flat_mae,patch,logistic,aabc_sex,72,0.3593813663804626,test,0.9272727272727272,0.033851869828845374,0.9252717391304348,0.03485021955819774,0.9252717391304348,0.035199719082972855 +flat_mae,patch,logistic,aabc_sex,73,0.046415888336127774,train,0.9357277882797732,0.010629680385382874,0.9340244152947736,0.010942252101493171,0.9334974647557079,0.011193218359526434 +flat_mae,patch,logistic,aabc_sex,73,0.046415888336127774,test,0.9636363636363636,0.023659401360289593,0.9621212121212122,0.02518793750033282,0.9565217391304348,0.02828841466991147 +flat_mae,patch,logistic,aabc_sex,74,0.005994842503189409,train,0.8998109640831758,0.012540010116870956,0.8963990762124712,0.013078064054674673,0.893329230047774,0.0134047619618936 +flat_mae,patch,logistic,aabc_sex,74,0.005994842503189409,test,0.9090909090909091,0.03945050670572994,0.905982905982906,0.04122527157904843,0.9035326086956521,0.04222734334658748 +flat_mae,patch,logistic,aabc_sex,75,0.046415888336127774,train,0.9376181474480151,0.010660006044103217,0.9360045457044925,0.010950359708266258,0.9357396172220757,0.01111943051331902 +flat_mae,patch,logistic,aabc_sex,75,0.046415888336127774,test,0.8545454545454545,0.04448892888560509,0.8505434782608696,0.046038237860097385,0.8505434782608696,0.04632335721126338 +flat_mae,patch,logistic,aabc_sex,76,0.046415888336127774,train,0.9376181474480151,0.010489293524369064,0.9359246820459175,0.01081432682836034,0.9351314516838125,0.01110486259105226 +flat_mae,patch,logistic,aabc_sex,76,0.046415888336127774,test,0.8545454545454545,0.048452126837129864,0.8505434782608696,0.04969502772815456,0.8505434782608696,0.04924217885754998 +flat_mae,patch,logistic,aabc_sex,77,0.3593813663804626,train,0.9867674858223062,0.0050538800974181545,0.9864417081324122,0.005175923242967212,0.9867375948884786,0.005130457158077821 +flat_mae,patch,logistic,aabc_sex,77,0.3593813663804626,test,0.8727272727272727,0.04530132722044557,0.8663658451926415,0.048700449815947025,0.8600543478260869,0.04937443774954454 +flat_mae,patch,logistic,aabc_sex,78,0.3593813663804626,train,0.9867674858223062,0.0051771978552396835,0.9864417081324122,0.0053015181765272805,0.9867375948884786,0.005260978627364505 +flat_mae,patch,logistic,aabc_sex,78,0.3593813663804626,test,0.9818181818181818,0.019191561506502055,0.9811965811965813,0.020181552612944558,0.9782608695652174,0.02294643223603506 +flat_mae,patch,logistic,aabc_sex,79,0.046415888336127774,train,0.9376181474480151,0.010036919992548039,0.9360823383385143,0.010288204977050417,0.9363477827603388,0.010395116274881142 +flat_mae,patch,logistic,aabc_sex,79,0.046415888336127774,test,0.9272727272727272,0.03294481235577197,0.9229691876750701,0.03657081921134348,0.9130434782608696,0.039390536512336045 +flat_mae,patch,logistic,aabc_sex,80,0.3593813663804626,train,0.9810964083175804,0.005846378195681464,0.9806425644028103,0.005982102085988667,0.9812274685659017,0.005904624458337401 +flat_mae,patch,logistic,aabc_sex,80,0.3593813663804626,test,0.8545454545454545,0.048540428749038605,0.8521505376344086,0.04896732500668355,0.8566576086956521,0.04809916357757175 +flat_mae,patch,logistic,aabc_sex,81,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,81,2.782559402207126,test,0.8727272727272727,0.04646201327628786,0.8699763593380614,0.0473691746957686,0.8722826086956521,0.04722860085495779 +flat_mae,patch,logistic,aabc_sex,82,0.3593813663804626,train,0.9848771266540642,0.005125996020913475,0.9845140515222482,0.005243465225200518,0.9851036079603739,0.005133185719687042 +flat_mae,patch,logistic,aabc_sex,82,0.3593813663804626,test,0.9090909090909091,0.03585380784784349,0.9045470322804582,0.0386490359895269,0.8974184782608696,0.040520596997251974 +flat_mae,patch,logistic,aabc_sex,83,0.3593813663804626,train,0.9886578449905482,0.0044484437068222586,0.9883715818165831,0.004563362587419262,0.9883715818165831,0.004679681727065676 +flat_mae,patch,logistic,aabc_sex,83,0.3593813663804626,test,0.8727272727272727,0.03960497506105484,0.8609606356085229,0.04781755373244435,0.8478260869565217,0.0473537745295221 +flat_mae,patch,logistic,aabc_sex,84,0.3593813663804626,train,0.9905482041587902,0.004636930434293072,0.9903155058088658,0.0047477783071794115,0.9906137342829509,0.004648231819524211 +flat_mae,patch,logistic,aabc_sex,84,0.3593813663804626,test,0.8363636363636363,0.05211327776112592,0.8307692307692308,0.05417916613446853,0.8288043478260869,0.054431711264186826 +flat_mae,patch,logistic,aabc_sex,85,0.046415888336127774,train,0.9319470699432892,0.010936469365578655,0.9300552388787683,0.011273397065129838,0.9290131598229725,0.011536032428933196 +flat_mae,patch,logistic,aabc_sex,85,0.046415888336127774,test,0.8909090909090909,0.04127634745837055,0.8891129032258065,0.04166717265125409,0.8940217391304348,0.04056960115051435 +flat_mae,patch,logistic,aabc_sex,86,0.046415888336127774,train,0.9357277882797732,0.011246487526840947,0.9339410589410589,0.011576196079682499,0.9328892992174448,0.011743771292045712 +flat_mae,patch,logistic,aabc_sex,86,0.046415888336127774,test,0.9272727272727272,0.036329074484392834,0.9252717391304348,0.0374580915279366,0.9252717391304348,0.038001370718860755 +flat_mae,patch,logistic,aabc_sex,87,0.046415888336127774,train,0.9357277882797732,0.010679372271169864,0.9341056302939711,0.010945809717111364,0.9341056302939711,0.011015180447656168 +flat_mae,patch,logistic,aabc_sex,87,0.046415888336127774,test,0.9272727272727272,0.03397585919832586,0.9242424242424243,0.03616813579667084,0.9191576086956521,0.037972201182934096 +flat_mae,patch,logistic,aabc_sex,88,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,88,21.54434690031882,test,0.8727272727272727,0.045220502919555414,0.8663658451926415,0.04886143290737041,0.8600543478260869,0.04984775350067716 +flat_mae,patch,logistic,aabc_sex,89,0.046415888336127774,train,0.9376181474480151,0.010743145823861143,0.9361580743195058,0.010985321046018903,0.936955948298602,0.011026778879812571 +flat_mae,patch,logistic,aabc_sex,89,0.046415888336127774,test,0.8727272727272727,0.041474381219261856,0.8639095086603039,0.04699052471235816,0.8539402173913043,0.047492092382123076 +flat_mae,patch,logistic,aabc_sex,90,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,90,2.782559402207126,test,0.7636363636363637,0.0569575280362482,0.7585275244849713,0.05835717434350748,0.7601902173913043,0.05844868615011177 +flat_mae,patch,logistic,aabc_sex,91,0.005994842503189409,train,0.9092627599243857,0.013058153986015526,0.9062389223679547,0.013618010087299107,0.9033236613030862,0.013983744079652744 +flat_mae,patch,logistic,aabc_sex,91,0.005994842503189409,test,0.8727272727272727,0.045198756656635856,0.8699763593380614,0.04603638883899907,0.8722826086956521,0.04555174178155055 +flat_mae,patch,logistic,aabc_sex,92,0.046415888336127774,train,0.9338374291115312,0.011244230076051466,0.9320413294426397,0.011585921726096562,0.9312553122893402,0.011851209381888326 +flat_mae,patch,logistic,aabc_sex,92,0.046415888336127774,test,0.9090909090909091,0.03795109510718645,0.9045470322804582,0.041034562652099586,0.8974184782608696,0.04273976405756128 +flat_mae,patch,logistic,aabc_sex,93,0.046415888336127774,train,0.9395085066162571,0.01038665306455141,0.9379053320421398,0.0106767642593667,0.9373736041501802,0.01082644623829614 +flat_mae,patch,logistic,aabc_sex,93,0.046415888336127774,test,0.8909090909090909,0.039519945795793786,0.8821428571428571,0.04585014304081009,0.8695652173913043,0.047252109103666486 +flat_mae,patch,logistic,aabc_sex,94,0.3593813663804626,train,0.9867674858223062,0.005120605808192668,0.9864252066645893,0.005254114406963119,0.9861294293502154,0.005372277929191906 +flat_mae,patch,logistic,aabc_sex,94,0.3593813663804626,test,0.8727272727272727,0.042557511888993434,0.8663658451926415,0.04578814872072915,0.8600543478260869,0.04647862252634516 +flat_mae,patch,logistic,aabc_sex,95,0.046415888336127774,train,0.9376181474480151,0.009880065951343147,0.9359246820459175,0.010170361967531547,0.9351314516838125,0.010385983873989922 +flat_mae,patch,logistic,aabc_sex,95,0.046415888336127774,test,0.9090909090909091,0.03858618773988331,0.9071259709557582,0.039310523325167386,0.9096467391304348,0.03882445226517596 +flat_mae,patch,logistic,aabc_sex,96,0.005994842503189409,train,0.9017013232514177,0.012388127531588822,0.8985663293902475,0.012888080360081194,0.8961795480524049,0.013212998976802458 +flat_mae,patch,logistic,aabc_sex,96,0.005994842503189409,test,0.8909090909090909,0.04229258184763426,0.8863636363636364,0.04476186392515482,0.8817934782608696,0.04562786091954106 +flat_mae,patch,logistic,aabc_sex,97,0.3593813663804626,train,0.9848771266540642,0.0057013069551947555,0.9844954424221108,0.005845931567195043,0.9844954424221108,0.0059022330096889074 +flat_mae,patch,logistic,aabc_sex,97,0.3593813663804626,test,0.8909090909090909,0.04085246990722423,0.8863636363636364,0.04345619604777548,0.8817934782608696,0.04468242887336844 +flat_mae,patch,logistic,aabc_sex,98,0.005994842503189409,train,0.9035916824196597,0.012579782802281416,0.900308545034642,0.013127180007249767,0.8972053694422463,0.013468784347735156 +flat_mae,patch,logistic,aabc_sex,98,0.005994842503189409,test,0.8181818181818182,0.047332479719148814,0.8035714285714286,0.05390690874759854,0.7948369565217391,0.05263342048913958 +flat_mae,patch,logistic,aabc_sex,99,0.005994842503189409,train,0.9017013232514177,0.013682573750040549,0.8985663293902475,0.014184420729213571,0.8961795480524049,0.014414511217030822 +flat_mae,patch,logistic,aabc_sex,99,0.005994842503189409,test,0.8727272727272727,0.04426628663250854,0.8663658451926415,0.048245934766743444,0.8600543478260869,0.04913660330949244 +flat_mae,patch,logistic,aabc_sex,100,0.3593813663804626,train,0.9848771266540642,0.005349415850532778,0.9844954424221108,0.005485413717496474,0.9844954424221108,0.005576893613339633 +flat_mae,patch,logistic,aabc_sex,100,0.3593813663804626,test,0.9090909090909091,0.03755502849538603,0.9071259709557582,0.038290537681601504,0.9096467391304348,0.03780358574953191 diff --git a/input_space_v3/flat_lr1e-3_4/eval_v2/aabc_sex__patch__logistic/log.txt b/input_space_v3/flat_lr1e-3_4/eval_v2/aabc_sex__patch__logistic/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..c6b5fa48509e039cfcfd70dffd5bf65cf74759da --- /dev/null +++ b/input_space_v3/flat_lr1e-3_4/eval_v2/aabc_sex__patch__logistic/log.txt @@ -0,0 +1,245 @@ +fMRI foundation model logistic probe eval +version: 0.1.dev86+gf97f52698 +sha: bcce2b486277d3a5b520775efd9cdf1a2affce36, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-04-08 22:26:32 +config: +output_root: experiments/input_space_v3/output +name_prefix: eval_logistic +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_4; eval v2 (aabc_sex patch logistic) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: input_space_v3/flat_lr1e-3_4/eval_v2/aabc_sex__patch__logistic +model: flat_mae +representation: patch +dataset: aabc_sex +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/eval_v2/aabc_sex__patch__logistic +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=True, reg_tokens=0, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: aabc_sex (flat) +train (n=471): +HFDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'segment', 'bold', 'mean', 'std'], + num_rows: 471 +}), + labels=[0 1], + counts=[269 202] +) + +validation (n=58): +HFDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'segment', 'bold', 'mean', 'std'], + num_rows: 58 +}), + labels=[0 1], + counts=[36 22] +) + +test (n=55): +HFDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'segment', 'bold', 'mean', 'std'], + num_rows: 55 +}), + labels=[0 1], + counts=[33 22] +) + +extracting features for all splits +extract (train) [ 0/236] eta: 0:21:20 time: 5.4275 data: 4.5248 max mem: 3205 +extract (train) [ 20/236] eta: 0:01:51 time: 0.2705 data: 0.0968 max mem: 3393 +extract (train) [ 40/236] eta: 0:01:16 time: 0.2556 data: 0.0934 max mem: 3393 +extract (train) [ 60/236] eta: 0:00:59 time: 0.2394 data: 0.0816 max mem: 3393 +extract (train) [ 80/236] eta: 0:00:49 time: 0.2431 data: 0.0833 max mem: 3393 +extract (train) [100/236] eta: 0:00:41 time: 0.2440 data: 0.0830 max mem: 3393 +extract (train) [120/236] eta: 0:00:33 time: 0.2454 data: 0.0856 max mem: 3393 +extract (train) [140/236] eta: 0:00:27 time: 0.2594 data: 0.0931 max mem: 3393 +extract (train) [160/236] eta: 0:00:21 time: 0.2415 data: 0.0833 max mem: 3393 +extract (train) [180/236] eta: 0:00:15 time: 0.2428 data: 0.0837 max mem: 3393 +extract (train) [200/236] eta: 0:00:09 time: 0.2581 data: 0.0919 max mem: 3393 +extract (train) [220/236] eta: 0:00:04 time: 0.2287 data: 0.0749 max mem: 3393 +extract (train) [235/236] eta: 0:00:00 time: 0.1976 data: 0.0609 max mem: 3393 +extract (train) Total time: 0:01:03 (0.2690 s / it) +extract (validation) [ 0/29] eta: 0:02:36 time: 5.4053 data: 5.2532 max mem: 3393 +extract (validation) [20/29] eta: 0:00:04 time: 0.2028 data: 0.0623 max mem: 3393 +extract (validation) [28/29] eta: 0:00:00 time: 0.1908 data: 0.0563 max mem: 3393 +extract (validation) Total time: 0:00:11 (0.3881 s / it) +extract (test) [ 0/28] eta: 0:02:30 time: 5.3691 data: 5.1949 max mem: 3393 +extract (test) [20/28] eta: 0:00:03 time: 0.2462 data: 0.0838 max mem: 3393 +extract (test) [27/28] eta: 0:00:00 time: 0.2077 data: 0.0674 max mem: 3393 +extract (test) Total time: 0:00:12 (0.4289 s / it) +feature extraction time: 0:01:26 +train features: (471, 768) +validation features: (58, 768) +test features: (55, 768) +evaluating fixed splits +eval results (fixed splits): + +| model | repr | clf | dataset | trial | C | split | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|--------:|:--------|--------:|----------:|--------:|----------:|--------:|-----------:| +| flat_mae | patch | logistic | aabc_sex | | 0.35938 | train | 0.98866 | 0.0044343 | 0.9884 | 0.0045308 | 0.98898 | 0.0043783 | +| flat_mae | patch | logistic | aabc_sex | | 0.35938 | test | 0.92727 | 0.035302 | 0.92527 | 0.036009 | 0.93182 | 0.034356 | + + +evaluating random splits (n=100) +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 1, "C": 0.3593813663804626, "split": "test", "acc": 0.8, "acc_std": 0.052178194362608475, "f1": 0.795677136102668, "f1_std": 0.05333235833584939, "bacc": 0.7975543478260869, "bacc_std": 0.053158746978290095} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 2, "C": 0.005994842503189409, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.042825974971171465, "f1": 0.8879076086956521, "f1_std": 0.0439291054385546, "bacc": 0.8879076086956521, "bacc_std": 0.04377227955192134} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 3, "C": 0.046415888336127774, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.04386719250775453, "f1": 0.8663658451926415, "f1_std": 0.04733267711660905, "bacc": 0.8600543478260869, "bacc_std": 0.04814919389149477} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 4, "C": 21.54434690031882, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.046204589947659996, "f1": 0.8521505376344086, "f1_std": 0.04671876605989599, "bacc": 0.8566576086956521, "bacc_std": 0.046008012861455234} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 5, "C": 0.046415888336127774, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.04592856832549595, "f1": 0.8484848484848485, "f1_std": 0.04882702424295088, "bacc": 0.8444293478260869, "bacc_std": 0.049314894617676394} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 6, "C": 0.3593813663804626, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.038440956120237395, "f1": 0.9071259709557582, "f1_std": 0.039237064514256674, "bacc": 0.9096467391304348, "bacc_std": 0.03901810369328504} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 7, "C": 0.046415888336127774, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.045114524607697146, "f1": 0.8683760683760684, "f1_std": 0.04719487456324605, "bacc": 0.8661684782608696, "bacc_std": 0.047761048658995865} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 8, "C": 0.046415888336127774, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.045858265295012704, "f1": 0.8521505376344086, "f1_std": 0.04638234499419379, "bacc": 0.8566576086956521, "bacc_std": 0.04609714182836298} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 9, "C": 0.046415888336127774, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.04157182771426019, "f1": 0.8863636363636364, "f1_std": 0.04404846208860855, "bacc": 0.8817934782608696, "bacc_std": 0.04506940067136007} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 10, "C": 0.046415888336127774, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.04533803249020235, "f1": 0.8711943793911007, "f1_std": 0.04563335251515353, "bacc": 0.8783967391304348, "bacc_std": 0.044102688171025146} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 11, "C": 2.782559402207126, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.03764547979187317, "f1": 0.905982905982906, "f1_std": 0.039365429011470186, "bacc": 0.9035326086956521, "bacc_std": 0.04024355613698382} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 12, "C": 0.3593813663804626, "split": "test", "acc": 0.8, "acc_std": 0.053141831120841435, "f1": 0.790003471017008, "f1_std": 0.05739460418818507, "bacc": 0.7853260869565217, "bacc_std": 0.05686894979855295} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 13, "C": 0.3593813663804626, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.04894491422098083, "f1": 0.8521505376344086, "f1_std": 0.04943395361828602, "bacc": 0.8566576086956521, "bacc_std": 0.04844967291701355} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 14, "C": 0.046415888336127774, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.03995892105526408, "f1": 0.9071259709557582, "f1_std": 0.04076255349689286, "bacc": 0.9096467391304348, "bacc_std": 0.04035061649584788} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 15, "C": 0.005994842503189409, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.04215052130497309, "f1": 0.8663658451926415, "f1_std": 0.045507150402806285, "bacc": 0.8600543478260869, "bacc_std": 0.046229144189007164} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 16, "C": 0.005994842503189409, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.045633161785542026, "f1": 0.8683760683760684, "f1_std": 0.04795182163546548, "bacc": 0.8661684782608696, "bacc_std": 0.048671965435813695} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 17, "C": 0.046415888336127774, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.047161884035576036, "f1": 0.84593837535014, "f1_std": 0.05170675746903805, "bacc": 0.8383152173913043, "bacc_std": 0.051663474322057305} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 18, "C": 0.005994842503189409, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.04743948210941931, "f1": 0.8533333333333333, "f1_std": 0.047504402777797196, "bacc": 0.8627717391304348, "bacc_std": 0.04568570674191256} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 19, "C": 0.046415888336127774, "split": "test", "acc": 0.8181818181818182, "acc_std": 0.04966665742230022, "f1": 0.8151881720430108, "f1_std": 0.05026301861719371, "bacc": 0.8192934782608696, "bacc_std": 0.04980479489707276} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 20, "C": 0.046415888336127774, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.04478878253896073, "f1": 0.8699763593380614, "f1_std": 0.04591324273825621, "bacc": 0.8722826086956521, "bacc_std": 0.045925498328536} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 21, "C": 2.782559402207126, "split": "test", "acc": 0.8181818181818182, "acc_std": 0.05046469676748993, "f1": 0.8106060606060606, "f1_std": 0.05393697406578509, "bacc": 0.8070652173913043, "bacc_std": 0.05399752751318542} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 22, "C": 166.81005372000556, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.04323855029259143, "f1": 0.8879076086956521, "f1_std": 0.044759243312750524, "bacc": 0.8879076086956521, "bacc_std": 0.04506684599014458} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 23, "C": 0.046415888336127774, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.041831318094864275, "f1": 0.8891129032258065, "f1_std": 0.042279658695552606, "bacc": 0.8940217391304348, "bacc_std": 0.04152363688167574} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 24, "C": 0.046415888336127774, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.04666326000946293, "f1": 0.8683760683760684, "f1_std": 0.048744319286790204, "bacc": 0.8661684782608696, "bacc_std": 0.04914993818889417} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 25, "C": 2.782559402207126, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.0409172678696581, "f1": 0.8879076086956521, "f1_std": 0.04214600344618968, "bacc": 0.8879076086956521, "bacc_std": 0.04218684517362692} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 26, "C": 0.046415888336127774, "split": "test", "acc": 0.8181818181818182, "acc_std": 0.049909922165622636, "f1": 0.8106060606060606, "f1_std": 0.05327790408854357, "bacc": 0.8070652173913043, "bacc_std": 0.05330290661673652} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 27, "C": 0.046415888336127774, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.03767685130112311, "f1": 0.905982905982906, "f1_std": 0.03919191866849352, "bacc": 0.9035326086956521, "bacc_std": 0.039684224645481235} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 28, "C": 0.3593813663804626, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.049275290104432976, "f1": 0.8281846581048247, "f1_std": 0.053673476715623634, "bacc": 0.8226902173913043, "bacc_std": 0.05372114537063825} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 29, "C": 0.3593813663804626, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.049963477570212106, "f1": 0.8328267477203647, "f1_std": 0.0509023912309622, "bacc": 0.8349184782608696, "bacc_std": 0.050830618887802395} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 30, "C": 0.005994842503189409, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.0488725649347953, "f1": 0.8505434782608696, "f1_std": 0.05061717565126853, "bacc": 0.8505434782608696, "bacc_std": 0.05092625112086522} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 31, "C": 0.005994842503189409, "split": "test", "acc": 0.8181818181818182, "acc_std": 0.049714011859903325, "f1": 0.8131793478260869, "f1_std": 0.05104185291514886, "bacc": 0.8131793478260869, "bacc_std": 0.050788697668920496} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 32, "C": 0.3593813663804626, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.041224818008509266, "f1": 0.8663658451926415, "f1_std": 0.0445785671742003, "bacc": 0.8600543478260869, "bacc_std": 0.045066559353642975} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 33, "C": 0.3593813663804626, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.0394951780716215, "f1": 0.905982905982906, "f1_std": 0.04116368776055438, "bacc": 0.9035326086956521, "bacc_std": 0.0420005026510902} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 34, "C": 0.3593813663804626, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.0453055740645929, "f1": 0.8683760683760684, "f1_std": 0.04693834167895322, "bacc": 0.8661684782608696, "bacc_std": 0.04715632927381747} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 35, "C": 0.005994842503189409, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.046215578211480667, "f1": 0.8683760683760684, "f1_std": 0.04807612640322762, "bacc": 0.8661684782608696, "bacc_std": 0.04838216585993931} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 36, "C": 0.046415888336127774, "split": "test", "acc": 0.9818181818181818, "acc_std": 0.018143086017762634, "f1": 0.9814251941911516, "f1_std": 0.01835817997708103, "bacc": 0.984375, "bacc_std": 0.015591714546514762} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 37, "C": 0.3593813663804626, "split": "test", "acc": 0.7636363636363637, "acc_std": 0.05901981737497335, "f1": 0.7585275244849713, "f1_std": 0.06047429600018259, "bacc": 0.7601902173913043, "bacc_std": 0.06034440323376556} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 38, "C": 0.046415888336127774, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.04432038129740205, "f1": 0.84593837535014, "f1_std": 0.04837640565224341, "bacc": 0.8383152173913043, "bacc_std": 0.04849532676542577} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 39, "C": 0.046415888336127774, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.046336805070399806, "f1": 0.8505434782608696, "f1_std": 0.04774946750553563, "bacc": 0.8505434782608696, "bacc_std": 0.04798161809090987} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 40, "C": 0.3593813663804626, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.044957809422826324, "f1": 0.8484848484848485, "f1_std": 0.047609691706065875, "bacc": 0.8444293478260869, "bacc_std": 0.04807609932086562} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 41, "C": 0.046415888336127774, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.04036894314009142, "f1": 0.8863636363636364, "f1_std": 0.04291588350114167, "bacc": 0.8817934782608696, "bacc_std": 0.043790072789991356} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 42, "C": 0.3593813663804626, "split": "test", "acc": 0.8181818181818182, "acc_std": 0.05356382151421432, "f1": 0.8151881720430108, "f1_std": 0.05429539519956123, "bacc": 0.8192934782608696, "bacc_std": 0.053883914374925} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 43, "C": 0.005994842503189409, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.044475254518246535, "f1": 0.8699763593380614, "f1_std": 0.04548574076674774, "bacc": 0.8722826086956521, "bacc_std": 0.04534236254015082} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 44, "C": 0.046415888336127774, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.048848302879576824, "f1": 0.8307692307692308, "f1_std": 0.05111915878842647, "bacc": 0.8288043478260869, "bacc_std": 0.051358920016188095} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 45, "C": 0.3593813663804626, "split": "test", "acc": 0.9272727272727272, "acc_std": 0.03268706621158683, "f1": 0.9260752688172043, "f1_std": 0.033039000985195445, "bacc": 0.9313858695652174, "bacc_std": 0.031513128509099216} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 46, "C": 0.046415888336127774, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.04302449811463847, "f1": 0.8891129032258065, "f1_std": 0.04341260667220993, "bacc": 0.8940217391304348, "bacc_std": 0.04214063680050588} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 47, "C": 0.005994842503189409, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.04417958842110063, "f1": 0.84593837535014, "f1_std": 0.04852819167835517, "bacc": 0.8383152173913043, "bacc_std": 0.04881317694160748} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 48, "C": 0.005994842503189409, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.037959456405203075, "f1": 0.905982905982906, "f1_std": 0.03961412854866127, "bacc": 0.9035326086956521, "bacc_std": 0.04038021936568441} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 49, "C": 0.005994842503189409, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.040163303015201685, "f1": 0.8891129032258065, "f1_std": 0.04061507112909471, "bacc": 0.8940217391304348, "bacc_std": 0.03976208663406389} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 50, "C": 0.046415888336127774, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.04261562201434377, "f1": 0.8863636363636364, "f1_std": 0.04498333568900711, "bacc": 0.8817934782608696, "bacc_std": 0.045880089454211424} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 51, "C": 0.046415888336127774, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.04218963877345609, "f1": 0.8639095086603039, "f1_std": 0.04776262382504826, "bacc": 0.8539402173913043, "bacc_std": 0.04830248845015457} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 52, "C": 0.3593813663804626, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.04841554289056798, "f1": 0.8533333333333333, "f1_std": 0.048436810824366086, "bacc": 0.8627717391304348, "bacc_std": 0.046543999330586214} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 53, "C": 0.046415888336127774, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.0450412629918481, "f1": 0.8683760683760684, "f1_std": 0.04721119310016523, "bacc": 0.8661684782608696, "bacc_std": 0.04782460616763301} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 54, "C": 0.046415888336127774, "split": "test", "acc": 0.8181818181818182, "acc_std": 0.052438078398390035, "f1": 0.8151881720430108, "f1_std": 0.052933455074335736, "bacc": 0.8192934782608696, "bacc_std": 0.05218737193013163} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 55, "C": 166.81005372000556, "split": "test", "acc": 0.8181818181818182, "acc_std": 0.052136832049889115, "f1": 0.8151881720430108, "f1_std": 0.052837862244596835, "bacc": 0.8192934782608696, "bacc_std": 0.05237272991254551} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 56, "C": 0.3593813663804626, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.046759097757981746, "f1": 0.8505434782608696, "f1_std": 0.04837743093584775, "bacc": 0.8505434782608696, "bacc_std": 0.04869409677615898} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 57, "C": 0.046415888336127774, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.04418053121956519, "f1": 0.8683760683760684, "f1_std": 0.046173424430027775, "bacc": 0.8661684782608696, "bacc_std": 0.04655488225626282} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 58, "C": 0.046415888336127774, "split": "test", "acc": 0.8, "acc_std": 0.05297990886932187, "f1": 0.795677136102668, "f1_std": 0.054041794647281365, "bacc": 0.7975543478260869, "bacc_std": 0.05382640879522031} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 59, "C": 0.005994842503189409, "split": "test", "acc": 0.9272727272727272, "acc_std": 0.033619435543759395, "f1": 0.9252717391304348, "f1_std": 0.034638595839659024, "bacc": 0.9252717391304348, "bacc_std": 0.03489629992152492} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 60, "C": 0.005994842503189409, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.04709015092404764, "f1": 0.84593837535014, "f1_std": 0.05165062940017399, "bacc": 0.8383152173913043, "bacc_std": 0.051938669802953974} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 61, "C": 0.046415888336127774, "split": "test", "acc": 0.9454545454545454, "acc_std": 0.03015332718782238, "f1": 0.9442755825734549, "f1_std": 0.030663073855244673, "bacc": 0.9470108695652174, "bacc_std": 0.029618817644883864} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 62, "C": 0.3593813663804626, "split": "test", "acc": 0.9636363636363636, "acc_std": 0.024080416239778583, "f1": 0.9626358695652174, "f1_std": 0.024821458262904956, "bacc": 0.9626358695652174, "bacc_std": 0.02523260674077854} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 63, "C": 0.005994842503189409, "split": "test", "acc": 0.9272727272727272, "acc_std": 0.03528254783626294, "f1": 0.9242424242424243, "f1_std": 0.03760366176950332, "bacc": 0.9191576086956521, "bacc_std": 0.03965654948728789} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 64, "C": 2.782559402207126, "split": "test", "acc": 0.8181818181818182, "acc_std": 0.052271686946169474, "f1": 0.8151881720430108, "f1_std": 0.05307985146253851, "bacc": 0.8192934782608696, "bacc_std": 0.053161638702155} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 65, "C": 0.046415888336127774, "split": "test", "acc": 0.9454545454545454, "acc_std": 0.03146114486733814, "f1": 0.9435897435897436, "f1_std": 0.03285559681805133, "bacc": 0.9408967391304348, "bacc_std": 0.03405552747591683} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 66, "C": 0.005994842503189409, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.03986454751731581, "f1": 0.8639095086603039, "f1_std": 0.04495239187599646, "bacc": 0.8539402173913043, "bacc_std": 0.045512887181104} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 67, "C": 0.046415888336127774, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.041541519606770154, "f1": 0.8879076086956521, "f1_std": 0.04268668487912302, "bacc": 0.8879076086956521, "bacc_std": 0.04275528441824081} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 68, "C": 2.782559402207126, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.03816933129149199, "f1": 0.9045470322804582, "f1_std": 0.041405673981038706, "bacc": 0.8974184782608696, "bacc_std": 0.043092593570285095} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 69, "C": 0.046415888336127774, "split": "test", "acc": 0.9454545454545454, "acc_std": 0.03176798117758153, "f1": 0.9435897435897436, "f1_std": 0.0332397410130046, "bacc": 0.9408967391304348, "bacc_std": 0.03471989492666549} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 70, "C": 0.046415888336127774, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.03734803921302766, "f1": 0.9086075108009306, "f1_std": 0.03718323790034284, "bacc": 0.921875, "bacc_std": 0.03209597119869564} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 71, "C": 0.005994842503189409, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.04429017763241351, "f1": 0.84593837535014, "f1_std": 0.04870379047304653, "bacc": 0.8383152173913043, "bacc_std": 0.04842836700820749} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 72, "C": 0.3593813663804626, "split": "test", "acc": 0.9272727272727272, "acc_std": 0.033851869828845374, "f1": 0.9252717391304348, "f1_std": 0.03485021955819774, "bacc": 0.9252717391304348, "bacc_std": 0.035199719082972855} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 73, "C": 0.046415888336127774, "split": "test", "acc": 0.9636363636363636, "acc_std": 0.023659401360289593, "f1": 0.9621212121212122, "f1_std": 0.02518793750033282, "bacc": 0.9565217391304348, "bacc_std": 0.02828841466991147} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 74, "C": 0.005994842503189409, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.03945050670572994, "f1": 0.905982905982906, "f1_std": 0.04122527157904843, "bacc": 0.9035326086956521, "bacc_std": 0.04222734334658748} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 75, "C": 0.046415888336127774, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.04448892888560509, "f1": 0.8505434782608696, "f1_std": 0.046038237860097385, "bacc": 0.8505434782608696, "bacc_std": 0.04632335721126338} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 76, "C": 0.046415888336127774, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.048452126837129864, "f1": 0.8505434782608696, "f1_std": 0.04969502772815456, "bacc": 0.8505434782608696, "bacc_std": 0.04924217885754998} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 77, "C": 0.3593813663804626, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.04530132722044557, "f1": 0.8663658451926415, "f1_std": 0.048700449815947025, "bacc": 0.8600543478260869, "bacc_std": 0.04937443774954454} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 78, "C": 0.3593813663804626, "split": "test", "acc": 0.9818181818181818, "acc_std": 0.019191561506502055, "f1": 0.9811965811965813, "f1_std": 0.020181552612944558, "bacc": 0.9782608695652174, "bacc_std": 0.02294643223603506} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 79, "C": 0.046415888336127774, "split": "test", "acc": 0.9272727272727272, "acc_std": 0.03294481235577197, "f1": 0.9229691876750701, "f1_std": 0.03657081921134348, "bacc": 0.9130434782608696, "bacc_std": 0.039390536512336045} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 80, "C": 0.3593813663804626, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.048540428749038605, "f1": 0.8521505376344086, "f1_std": 0.04896732500668355, "bacc": 0.8566576086956521, "bacc_std": 0.04809916357757175} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 81, "C": 2.782559402207126, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.04646201327628786, "f1": 0.8699763593380614, "f1_std": 0.0473691746957686, "bacc": 0.8722826086956521, "bacc_std": 0.04722860085495779} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 82, "C": 0.3593813663804626, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.03585380784784349, "f1": 0.9045470322804582, "f1_std": 0.0386490359895269, "bacc": 0.8974184782608696, "bacc_std": 0.040520596997251974} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 83, "C": 0.3593813663804626, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.03960497506105484, "f1": 0.8609606356085229, "f1_std": 0.04781755373244435, "bacc": 0.8478260869565217, "bacc_std": 0.0473537745295221} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 84, "C": 0.3593813663804626, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.05211327776112592, "f1": 0.8307692307692308, "f1_std": 0.05417916613446853, "bacc": 0.8288043478260869, "bacc_std": 0.054431711264186826} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 85, "C": 0.046415888336127774, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.04127634745837055, "f1": 0.8891129032258065, "f1_std": 0.04166717265125409, "bacc": 0.8940217391304348, "bacc_std": 0.04056960115051435} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 86, "C": 0.046415888336127774, "split": "test", "acc": 0.9272727272727272, "acc_std": 0.036329074484392834, "f1": 0.9252717391304348, "f1_std": 0.0374580915279366, "bacc": 0.9252717391304348, "bacc_std": 0.038001370718860755} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 87, "C": 0.046415888336127774, "split": "test", "acc": 0.9272727272727272, "acc_std": 0.03397585919832586, "f1": 0.9242424242424243, "f1_std": 0.03616813579667084, "bacc": 0.9191576086956521, "bacc_std": 0.037972201182934096} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 88, "C": 21.54434690031882, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.045220502919555414, "f1": 0.8663658451926415, "f1_std": 0.04886143290737041, "bacc": 0.8600543478260869, "bacc_std": 0.04984775350067716} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 89, "C": 0.046415888336127774, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.041474381219261856, "f1": 0.8639095086603039, "f1_std": 0.04699052471235816, "bacc": 0.8539402173913043, "bacc_std": 0.047492092382123076} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 90, "C": 2.782559402207126, "split": "test", "acc": 0.7636363636363637, "acc_std": 0.0569575280362482, "f1": 0.7585275244849713, "f1_std": 0.05835717434350748, "bacc": 0.7601902173913043, "bacc_std": 0.05844868615011177} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 91, "C": 0.005994842503189409, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.045198756656635856, "f1": 0.8699763593380614, "f1_std": 0.04603638883899907, "bacc": 0.8722826086956521, "bacc_std": 0.04555174178155055} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 92, "C": 0.046415888336127774, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.03795109510718645, "f1": 0.9045470322804582, "f1_std": 0.041034562652099586, "bacc": 0.8974184782608696, "bacc_std": 0.04273976405756128} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 93, "C": 0.046415888336127774, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.039519945795793786, "f1": 0.8821428571428571, "f1_std": 0.04585014304081009, "bacc": 0.8695652173913043, "bacc_std": 0.047252109103666486} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 94, "C": 0.3593813663804626, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.042557511888993434, "f1": 0.8663658451926415, "f1_std": 0.04578814872072915, "bacc": 0.8600543478260869, "bacc_std": 0.04647862252634516} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 95, "C": 0.046415888336127774, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.03858618773988331, "f1": 0.9071259709557582, "f1_std": 0.039310523325167386, "bacc": 0.9096467391304348, "bacc_std": 0.03882445226517596} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 96, "C": 0.005994842503189409, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.04229258184763426, "f1": 0.8863636363636364, "f1_std": 0.04476186392515482, "bacc": 0.8817934782608696, "bacc_std": 0.04562786091954106} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 97, "C": 0.3593813663804626, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.04085246990722423, "f1": 0.8863636363636364, "f1_std": 0.04345619604777548, "bacc": 0.8817934782608696, "bacc_std": 0.04468242887336844} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 98, "C": 0.005994842503189409, "split": "test", "acc": 0.8181818181818182, "acc_std": 0.047332479719148814, "f1": 0.8035714285714286, "f1_std": 0.05390690874759854, "bacc": 0.7948369565217391, "bacc_std": 0.05263342048913958} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 99, "C": 0.005994842503189409, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.04426628663250854, "f1": 0.8663658451926415, "f1_std": 0.048245934766743444, "bacc": 0.8600543478260869, "bacc_std": 0.04913660330949244} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 100, "C": 0.3593813663804626, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.03755502849538603, "f1": 0.9071259709557582, "f1_std": 0.038290537681601504, "bacc": 0.9096467391304348, "bacc_std": 0.03780358574953191} +eval results (random splits): + +| model | repr | clf | dataset | split | n_trials | C | C_std | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|-----------:|-------:|--------:|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | aabc_sex | train | 100 | 4.0761 | 23.565 | 0.94949 | 0.034633 | 0.94802 | 0.035742 | 0.94724 | 0.036655 | +| flat_mae | patch | logistic | aabc_sex | test | 100 | 4.0761 | 23.565 | 0.876 | 0.042099 | 0.87171 | 0.043376 | 0.87026 | 0.043473 | + + +done! total time: 0:05:23 diff --git a/input_space_v3/flat_lr1e-3_4/eval_v2/abide_dx__patch__logistic/config.yaml b/input_space_v3/flat_lr1e-3_4/eval_v2/abide_dx__patch__logistic/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..376001357a20554ca5b28f7c4d172ffcd471c8a9 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_4/eval_v2/abide_dx__patch__logistic/config.yaml @@ -0,0 +1,30 @@ +output_root: experiments/input_space_v3/output +name_prefix: eval_logistic +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_4; eval v2 (abide_dx patch logistic) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: input_space_v3/flat_lr1e-3_4/eval_v2/abide_dx__patch__logistic +model: flat_mae +representation: patch +dataset: abide_dx +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/eval_v2/abide_dx__patch__logistic +remote_dir: null diff --git a/input_space_v3/flat_lr1e-3_4/eval_v2/abide_dx__patch__logistic/eval_table.csv b/input_space_v3/flat_lr1e-3_4/eval_v2/abide_dx__patch__logistic/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..e67dad76f15fd0985129e9c0e8350e599ac226d6 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_4/eval_v2/abide_dx__patch__logistic/eval_table.csv @@ -0,0 +1,203 @@ +model,repr,clf,dataset,trial,C,split,acc,acc_std,f1,f1_std,bacc,bacc_std +flat_mae,patch,logistic,abide_dx,,0.046415888336127774,train,0.7962962962962963,0.014618680590019122,0.7914512158386222,0.015102355462983115,0.7889963228051743,0.01501304620326284 +flat_mae,patch,logistic,abide_dx,,0.046415888336127774,test,0.6290322580645161,0.04644367091604805,0.6242424242424243,0.04755279101812896,0.6239853364755171,0.04707554509374439 +flat_mae,patch,logistic,abide_dx,1,0.005994842503189409,train,0.7094017094017094,0.016537193057798265,0.7000427289559892,0.017410521543003436,0.6986341823551125,0.017011997160260802 +flat_mae,patch,logistic,abide_dx,1,0.005994842503189409,test,0.6612903225806451,0.04075222713729059,0.6539994685091681,0.04228737927116954,0.6533613445378151,0.04158101834876175 +flat_mae,patch,logistic,abide_dx,2,0.3593813663804626,train,0.8903133903133903,0.012002324904720802,0.8887583219287324,0.012200460049945731,0.8875230712440014,0.012277409389205702 +flat_mae,patch,logistic,abide_dx,2,0.3593813663804626,test,0.5967741935483871,0.04471088766224962,0.5941345902068604,0.04513592471823754,0.5945378151260504,0.04520855195373101 +flat_mae,patch,logistic,abide_dx,3,0.3593813663804626,train,0.8945868945868946,0.01165568675129044,0.892903970642807,0.01190006877295713,0.8911037283130306,0.012039700533761 +flat_mae,patch,logistic,abide_dx,3,0.3593813663804626,test,0.6129032258064516,0.04323101497266883,0.607905138339921,0.04352570552880119,0.6076680672268908,0.04328722218644109 +flat_mae,patch,logistic,abide_dx,4,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,4,1291.5496650148827,test,0.6693548387096774,0.0405584199869994,0.667603792088918,0.0410012301511435,0.66859243697479,0.04136338690584094 +flat_mae,patch,logistic,abide_dx,5,10000.0,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,5,10000.0,test,0.6048387096774194,0.04336887733538816,0.602745995423341,0.04371452264285463,0.6034663865546219,0.04374561599742388 +flat_mae,patch,logistic,abide_dx,6,0.3593813663804626,train,0.886039886039886,0.012527378803311508,0.8839592700343825,0.012843376225469803,0.8815799187892212,0.012971289652324143 +flat_mae,patch,logistic,abide_dx,6,0.3593813663804626,test,0.6209677419354839,0.04326806732873798,0.6118548118548119,0.04440477002810697,0.6118697478991597,0.04360774890544062 +flat_mae,patch,logistic,abide_dx,7,0.005994842503189409,train,0.7136752136752137,0.016754003035760107,0.7049081589332509,0.017703023942702574,0.7033960871170173,0.017360667863948267 +flat_mae,patch,logistic,abide_dx,7,0.005994842503189409,test,0.6612903225806451,0.04150589830581597,0.6481081081081081,0.04427472683340092,0.6486344537815126,0.04243955462403348 +flat_mae,patch,logistic,abide_dx,8,0.046415888336127774,train,0.7877492877492878,0.014909270440848802,0.78378970563005,0.015331847093371436,0.7820967146548542,0.015324555372930166 +flat_mae,patch,logistic,abide_dx,8,0.046415888336127774,test,0.6532258064516129,0.04242303430626174,0.6465831510572015,0.04342280246520486,0.6460084033613445,0.04296492680685404 +flat_mae,patch,logistic,abide_dx,9,10000.0,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,9,10000.0,test,0.6209677419354839,0.042281377464942954,0.6097756946769334,0.04408816341794222,0.6102941176470589,0.04293046120769825 +flat_mae,patch,logistic,abide_dx,10,0.046415888336127774,train,0.8034188034188035,0.015021722730680826,0.7998297408093097,0.015491231086045384,0.7980804724990771,0.015534117946218852 +flat_mae,patch,logistic,abide_dx,10,0.046415888336127774,test,0.6048387096774194,0.044971953336370184,0.5989703649924097,0.04569538291014515,0.5987394957983193,0.04531392877718877 +flat_mae,patch,logistic,abide_dx,11,2.782559402207126,train,0.9857549857549858,0.004538391788326614,0.9856035437430786,0.004586651792298003,0.9856035437430786,0.004599022567347786 +flat_mae,patch,logistic,abide_dx,11,2.782559402207126,test,0.5483870967741935,0.04339421934581466,0.5407407407407407,0.04431418054305846,0.5409663865546219,0.04380830645145373 +flat_mae,patch,logistic,abide_dx,12,0.046415888336127774,train,0.7948717948717948,0.015065656369186201,0.7904477611940299,0.015507057976343707,0.7882613510520486,0.015419160690495981 +flat_mae,patch,logistic,abide_dx,12,0.046415888336127774,test,0.6209677419354839,0.04466750792587394,0.6189604445897352,0.04473844803620251,0.6197478991596639,0.044732044610621226 +flat_mae,patch,logistic,abide_dx,13,0.3593813663804626,train,0.8774928774928775,0.012629681686646367,0.8757133328392499,0.012806653712647583,0.8744186046511628,0.01279178515823809 +flat_mae,patch,logistic,abide_dx,13,0.3593813663804626,test,0.6370967741935484,0.04186314791037172,0.6301451580831179,0.04314769505970364,0.6297268907563025,0.04272028403335686 +flat_mae,patch,logistic,abide_dx,14,0.3593813663804626,train,0.8803418803418803,0.011927730407435529,0.878922772407336,0.012053904046576575,0.8784791435954227,0.012050986933880731 +flat_mae,patch,logistic,abide_dx,14,0.3593813663804626,test,0.6693548387096774,0.041898280643908443,0.6644445911160979,0.042994094355152175,0.6638655462184874,0.04266913190831841 +flat_mae,patch,logistic,abide_dx,15,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,15,21.54434690031882,test,0.6048387096774194,0.0435711380236787,0.6017043592264831,0.04392370218671205,0.601890756302521,0.04392061568432181 +flat_mae,patch,logistic,abide_dx,16,2.782559402207126,train,0.9843304843304843,0.004478335244553388,0.9841591876506488,0.0045287466883790015,0.984016242155777,0.004588840263320855 +flat_mae,patch,logistic,abide_dx,16,2.782559402207126,test,0.6451612903225806,0.04158108310788161,0.6375232527238905,0.04318484822120767,0.6370798319327731,0.042603889685637275 +flat_mae,patch,logistic,abide_dx,17,0.3593813663804626,train,0.896011396011396,0.010605649499220412,0.8941537317594572,0.010872316347866532,0.8918050941306754,0.011039436854232518 +flat_mae,patch,logistic,abide_dx,17,0.3593813663804626,test,0.5806451612903226,0.0427449907611605,0.5752305665349143,0.043686464825369975,0.5751050420168067,0.043429531897924256 +flat_mae,patch,logistic,abide_dx,18,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,18,166.81005372000556,test,0.6451612903225806,0.04290639086069751,0.6375232527238905,0.044328363519900105,0.6370798319327731,0.04361640988087078 +flat_mae,patch,logistic,abide_dx,19,0.3593813663804626,train,0.8874643874643875,0.011678769868262275,0.8860939666238767,0.011822150825633078,0.8855297157622739,0.011832315359474453 +flat_mae,patch,logistic,abide_dx,19,0.3593813663804626,test,0.6370967741935484,0.044034869354213635,0.626380984265149,0.04595575576870355,0.6265756302521008,0.04477228311205918 +flat_mae,patch,logistic,abide_dx,20,0.3593813663804626,train,0.8917378917378918,0.011939293638034988,0.8900094833628829,0.012224881098582302,0.8882244370616463,0.012447367838902152 +flat_mae,patch,logistic,abide_dx,20,0.3593813663804626,test,0.5483870967741935,0.0433817930563332,0.5363247863247864,0.04515001851193473,0.5378151260504201,0.04406581182297077 +flat_mae,patch,logistic,abide_dx,21,0.046415888336127774,train,0.7977207977207977,0.014829320916936044,0.7943404634581106,0.015209293440578508,0.7929125138427464,0.015260169307523629 +flat_mae,patch,logistic,abide_dx,21,0.046415888336127774,test,0.6209677419354839,0.04270382963572132,0.6097756946769334,0.044739615625882155,0.6102941176470589,0.04343297629297334 +flat_mae,patch,logistic,abide_dx,22,0.3593813663804626,train,0.9017094017094017,0.0114078894650117,0.9001037363652675,0.011677618803777429,0.8981543004798819,0.011871413644242457 +flat_mae,patch,logistic,abide_dx,22,0.3593813663804626,test,0.6129032258064516,0.043209000103061244,0.6045708211533352,0.044340277345591275,0.6045168067226891,0.043626279715271055 +flat_mae,patch,logistic,abide_dx,23,0.3593813663804626,train,0.896011396011396,0.011336314797214695,0.8942341230447264,0.011627813983730369,0.8921004060538944,0.011816802294793668 +flat_mae,patch,logistic,abide_dx,23,0.3593813663804626,test,0.6854838709677419,0.04197973781596039,0.6761968530297957,0.044223131000956366,0.6754201680672269,0.04314002275414597 +flat_mae,patch,logistic,abide_dx,24,0.3593813663804626,train,0.8974358974358975,0.01124516113335809,0.8958731623706242,0.011457676186579698,0.8942783314876339,0.011560558703939298 +flat_mae,patch,logistic,abide_dx,24,0.3593813663804626,test,0.6451612903225806,0.04371691107862016,0.6428384393820372,0.04398774617239939,0.6433823529411764,0.04386731418891198 +flat_mae,patch,logistic,abide_dx,25,2.782559402207126,train,0.9871794871794872,0.004161981684422069,0.9870314607156713,0.004215082950634728,0.9866002214839424,0.004396592256372547 +flat_mae,patch,logistic,abide_dx,25,2.782559402207126,test,0.6129032258064516,0.04306634042287961,0.6025641025641025,0.04450273372235099,0.6029411764705883,0.04354376470556692 +flat_mae,patch,logistic,abide_dx,26,0.3593813663804626,train,0.8888888888888888,0.01103216125293957,0.8872748832728081,0.011250979428848389,0.8859357696566998,0.011389977627513998 +flat_mae,patch,logistic,abide_dx,26,0.3593813663804626,test,0.6451612903225806,0.04044389492663421,0.6336287939833467,0.04289433665267536,0.6339285714285714,0.041434907609027 +flat_mae,patch,logistic,abide_dx,27,2.782559402207126,train,0.9886039886039886,0.004007521276783632,0.988482834994463,0.00405036178178272,0.988482834994463,0.004069341540273015 +flat_mae,patch,logistic,abide_dx,27,2.782559402207126,test,0.6290322580645161,0.04417641238296944,0.6210470369386127,0.0456099966296783,0.6207983193277311,0.04487972862094829 +flat_mae,patch,logistic,abide_dx,28,0.046415888336127774,train,0.8105413105413105,0.014373946429393195,0.80685360833273,0.014777029852775157,0.8048357327427095,0.01478823223643042 +flat_mae,patch,logistic,abide_dx,28,0.046415888336127774,test,0.6370967741935484,0.042147799998873685,0.6351748937561295,0.042455716980180566,0.6360294117647058,0.04249102920231667 +flat_mae,patch,logistic,abide_dx,29,0.3593813663804626,train,0.8917378917378918,0.011806200087255877,0.8903134020279438,0.011993155265176768,0.889405684754522,0.012085378881735373 +flat_mae,patch,logistic,abide_dx,29,0.3593813663804626,test,0.6290322580645161,0.043433165971956886,0.6274817136886102,0.04357381496639475,0.6286764705882353,0.043687259569286055 +flat_mae,patch,logistic,abide_dx,30,0.046415888336127774,train,0.801994301994302,0.01488610804384675,0.7978089651328317,0.015351894902580371,0.7956072351421188,0.015331044070423879 +flat_mae,patch,logistic,abide_dx,30,0.046415888336127774,test,0.6935483870967742,0.041216197956451935,0.6869519000797236,0.042651036781073445,0.6859243697478992,0.0418692831792085 +flat_mae,patch,logistic,abide_dx,31,0.3593813663804626,train,0.8874643874643875,0.012190036916447402,0.8854540384794126,0.012511266299476725,0.8831672203765227,0.012689238062585774 +flat_mae,patch,logistic,abide_dx,31,0.3593813663804626,test,0.6451612903225806,0.04508951381400503,0.6336287939833467,0.047508776749286205,0.6339285714285714,0.045956746642532936 +flat_mae,patch,logistic,abide_dx,32,0.3593813663804626,train,0.886039886039886,0.011318649092281752,0.8845404231873093,0.011469954110273288,0.8836471022517534,0.01149609931758437 +flat_mae,patch,logistic,abide_dx,32,0.3593813663804626,test,0.6935483870967742,0.043206480393233423,0.6895915678524374,0.0435832649292186,0.6890756302521008,0.04336312231460434 +flat_mae,patch,logistic,abide_dx,33,0.3593813663804626,train,0.9002849002849003,0.010881036764188775,0.898905529953917,0.011055816778267981,0.8977482465854558,0.011149653211315802 +flat_mae,patch,logistic,abide_dx,33,0.3593813663804626,test,0.6532258064516129,0.0393177078935973,0.6448884448884449,0.04060688021795231,0.6444327731092437,0.03986638567117156 +flat_mae,patch,logistic,abide_dx,34,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,34,21.54434690031882,test,0.6854838709677419,0.040355522028200495,0.6819885579009667,0.04113670079796081,0.6817226890756303,0.04112481661674398 +flat_mae,patch,logistic,abide_dx,35,0.3593813663804626,train,0.8888888888888888,0.011712104484239578,0.8873518762343646,0.011901307982758447,0.8862310815799188,0.011989652325439243 +flat_mae,patch,logistic,abide_dx,35,0.3593813663804626,test,0.6048387096774194,0.043389387156238614,0.602745995423341,0.04363031636844909,0.6034663865546219,0.04371843029315158 +flat_mae,patch,logistic,abide_dx,36,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,36,21.54434690031882,test,0.5967741935483871,0.04257415334188521,0.5915678524374176,0.04308092881376521,0.5913865546218487,0.0428266656519097 +flat_mae,patch,logistic,abide_dx,37,0.3593813663804626,train,0.8988603988603988,0.011774561700729751,0.8975631110462571,0.011954720785929095,0.8967515688445922,0.012066950190959377 +flat_mae,patch,logistic,abide_dx,37,0.3593813663804626,test,0.6370967741935484,0.04420903896162536,0.6330637206549615,0.04482622590756497,0.6328781512605042,0.04466316661113086 +flat_mae,patch,logistic,abide_dx,38,0.3593813663804626,train,0.9017094017094017,0.010864160133486794,0.9005124518613608,0.011019424328048909,0.8999261720191953,0.011124773772063229 +flat_mae,patch,logistic,abide_dx,38,0.3593813663804626,test,0.6209677419354839,0.042636434005233384,0.6179613241560145,0.04301107820939371,0.618172268907563,0.0430089354821714 +flat_mae,patch,logistic,abide_dx,39,0.046415888336127774,train,0.8091168091168092,0.01571778604973387,0.8057810628897055,0.016017205159737053,0.8041343669250646,0.01596961836993684 +flat_mae,patch,logistic,abide_dx,39,0.046415888336127774,test,0.532258064516129,0.04444024329057264,0.5262187088274045,0.044801343847736874,0.5262605042016807,0.04457816780004468 +flat_mae,patch,logistic,abide_dx,40,0.046415888336127774,train,0.7962962962962963,0.015831434845484094,0.7924961604368937,0.016238027851498353,0.790734588409007,0.016199543971747877 +flat_mae,patch,logistic,abide_dx,40,0.046415888336127774,test,0.5887096774193549,0.04116824190464357,0.5765651155005022,0.04334704864576026,0.5777310924369747,0.04202541797261388 +flat_mae,patch,logistic,abide_dx,41,0.046415888336127774,train,0.8034188034188035,0.014992425367579727,0.7996724484478523,0.015451203984172431,0.7977851605758582,0.015503157002085361 +flat_mae,patch,logistic,abide_dx,41,0.046415888336127774,test,0.6290322580645161,0.039749750488421665,0.6210470369386127,0.041218635024784664,0.6207983193277311,0.04052892666663992 +flat_mae,patch,logistic,abide_dx,42,0.3593813663804626,train,0.9031339031339032,0.01145167708011258,0.9016579866833674,0.011704478368747525,0.9000369139904023,0.01194863327753388 +flat_mae,patch,logistic,abide_dx,42,0.3593813663804626,test,0.5564516129032258,0.04724775842702776,0.5550336008351275,0.04738246649807175,0.5561974789915967,0.04746633006788804 +flat_mae,patch,logistic,abide_dx,43,0.046415888336127774,train,0.7977207977207977,0.014555247454022249,0.7938658527506885,0.014874663993391369,0.7920265780730897,0.014811112971700931 +flat_mae,patch,logistic,abide_dx,43,0.046415888336127774,test,0.6612903225806451,0.04371453073876829,0.6555555555555556,0.04483887919023059,0.654936974789916,0.044371788748482854 +flat_mae,patch,logistic,abide_dx,44,0.046415888336127774,train,0.8076923076923077,0.01417152095696562,0.8039491513151771,0.014554662149876758,0.8019564414913252,0.014544140913227564 +flat_mae,patch,logistic,abide_dx,44,0.046415888336127774,test,0.5725806451612904,0.04264628371955111,0.5573516535327002,0.04532402144048034,0.5598739495798319,0.04342348046436083 +flat_mae,patch,logistic,abide_dx,45,0.005994842503189409,train,0.7037037037037037,0.016850208116196766,0.6950885399264952,0.017526251024338774,0.6937615356220007,0.017208779208855125 +flat_mae,patch,logistic,abide_dx,45,0.005994842503189409,test,0.5887096774193549,0.04176409144261437,0.5712833028269271,0.04443326958163723,0.5745798319327731,0.04243866815564399 +flat_mae,patch,logistic,abide_dx,46,0.005994842503189409,train,0.707977207977208,0.016616845202511124,0.7004888830614194,0.017316160812376163,0.6991140642303433,0.01708510127272315 +flat_mae,patch,logistic,abide_dx,46,0.005994842503189409,test,0.5564516129032258,0.043833487310291415,0.5498646953996436,0.044566537816004524,0.5498949579831933,0.04425533011374791 +flat_mae,patch,logistic,abide_dx,47,0.3593813663804626,train,0.8931623931623932,0.01134182953061298,0.8914958731336362,0.011562670906428391,0.8898117386489479,0.011649323173480518 +flat_mae,patch,logistic,abide_dx,47,0.3593813663804626,test,0.5806451612903226,0.04504709063424387,0.5788923719958203,0.04521948999411249,0.5798319327731092,0.04531844805896603 +flat_mae,patch,logistic,abide_dx,48,0.3593813663804626,train,0.8917378917378918,0.012066943411085386,0.8901652708811977,0.012274537685389903,0.8888150609080843,0.012357709423871405 +flat_mae,patch,logistic,abide_dx,48,0.3593813663804626,test,0.6048387096774194,0.0433107344551286,0.5953379953379954,0.044503126135863776,0.5955882352941176,0.04366926382837147 +flat_mae,patch,logistic,abide_dx,49,0.3593813663804626,train,0.8903133903133903,0.011978441306949118,0.8885215608713855,0.012247837226242711,0.8866371354743448,0.012404191315941235 +flat_mae,patch,logistic,abide_dx,49,0.3593813663804626,test,0.6048387096774194,0.04206022081275724,0.6004471624909581,0.042739806336062454,0.6003151260504203,0.04262847522208488 +flat_mae,patch,logistic,abide_dx,50,0.3593813663804626,train,0.9002849002849003,0.0112164265235957,0.8990384615384615,0.011368908938183752,0.8983388704318938,0.011435762170054738 +flat_mae,patch,logistic,abide_dx,50,0.3593813663804626,test,0.5887096774193549,0.044706360720436246,0.5826018084614877,0.045597432783155416,0.5824579831932774,0.04524985042741168 +flat_mae,patch,logistic,abide_dx,51,0.005994842503189409,train,0.7122507122507122,0.016494633849724546,0.7032892534315367,0.01731446029029028,0.7018087855297157,0.016960127387452312 +flat_mae,patch,logistic,abide_dx,51,0.005994842503189409,test,0.5645161290322581,0.042885088938672336,0.5411184210526316,0.04633467716118664,0.5477941176470589,0.04355161056464932 +flat_mae,patch,logistic,abide_dx,52,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,52,166.81005372000556,test,0.5806451612903226,0.04394803477592569,0.5766806722689075,0.04444916353780629,0.5766806722689075,0.04443443294076792 +flat_mae,patch,logistic,abide_dx,53,0.046415888336127774,train,0.7934472934472935,0.015118454210998259,0.7895940088346125,0.015490061827132237,0.7878552971576227,0.015442864536074321 +flat_mae,patch,logistic,abide_dx,53,0.046415888336127774,test,0.5806451612903226,0.04635298669611662,0.5716183895827798,0.04762310306732199,0.571953781512605,0.046826112915536205 +flat_mae,patch,logistic,abide_dx,54,0.3593813663804626,train,0.8931623931623932,0.011809774570225733,0.8920582331993202,0.011933031297538758,0.8921742340346992,0.011960707944330465 +flat_mae,patch,logistic,abide_dx,54,0.3593813663804626,test,0.6612903225806451,0.04154935132120981,0.6569169960474308,0.04227549138260596,0.6565126050420168,0.04202709919893152 +flat_mae,patch,logistic,abide_dx,55,2.782559402207126,train,0.9914529914529915,0.0034686431257840906,0.9913569505548625,0.0035104983577978004,0.9910668143226282,0.0036535680322745344 +flat_mae,patch,logistic,abide_dx,55,2.782559402207126,test,0.6048387096774194,0.043251975107229244,0.5989703649924097,0.04383594134799062,0.5987394957983193,0.04356985514123794 +flat_mae,patch,logistic,abide_dx,56,0.005994842503189409,train,0.6994301994301995,0.01754745492674228,0.6914349995312842,0.018185009469683037,0.6901808785529715,0.017903202502196323 +flat_mae,patch,logistic,abide_dx,56,0.005994842503189409,test,0.6774193548387096,0.038673622321623136,0.6669352672575879,0.04076957558442832,0.6664915966386555,0.03959334341581953 +flat_mae,patch,logistic,abide_dx,57,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,57,166.81005372000556,test,0.6290322580645161,0.042031329675583734,0.6210470369386127,0.0432349177616727,0.6207983193277311,0.04261216848019545 +flat_mae,patch,logistic,abide_dx,58,0.3593813663804626,train,0.905982905982906,0.01070244557926361,0.9044117647058824,0.010945636632054128,0.9023255813953488,0.011097757753617913 +flat_mae,patch,logistic,abide_dx,58,0.3593813663804626,test,0.6129032258064516,0.042927021657057376,0.607905138339921,0.043680523796633654,0.6076680672268908,0.0433179091821631 +flat_mae,patch,logistic,abide_dx,59,0.005994842503189409,train,0.6994301994301995,0.016467543052578342,0.6899105040037683,0.0172312851549345,0.6887043189368771,0.016862161138924244 +flat_mae,patch,logistic,abide_dx,59,0.005994842503189409,test,0.6209677419354839,0.043066316260552184,0.6189604445897352,0.04319770406385825,0.6197478991596639,0.04330936639171262 +flat_mae,patch,logistic,abide_dx,60,0.046415888336127774,train,0.782051282051282,0.01575255773318661,0.7776287103806809,0.016105775785175268,0.7757475083056479,0.015995622226745013 +flat_mae,patch,logistic,abide_dx,60,0.046415888336127774,test,0.6048387096774194,0.04151130382767403,0.5972691721349506,0.04301941423179908,0.5971638655462186,0.04235326031334011 +flat_mae,patch,logistic,abide_dx,61,0.3593813663804626,train,0.9002849002849003,0.010857600318648108,0.8987655745269958,0.01106257386174411,0.8971576227390181,0.01117259625075259 +flat_mae,patch,logistic,abide_dx,61,0.3593813663804626,test,0.5806451612903226,0.04403130980900248,0.5752305665349143,0.04470847799821994,0.5751050420168067,0.044370042284403464 +flat_mae,patch,logistic,abide_dx,62,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,62,1291.5496650148827,test,0.5806451612903226,0.0436602505923844,0.5788923719958203,0.04398510224997375,0.5798319327731092,0.044311076265064676 +flat_mae,patch,logistic,abide_dx,63,0.046415888336127774,train,0.8076923076923077,0.014781740419818003,0.8039491513151771,0.015106153027243052,0.8019564414913252,0.015031212115298316 +flat_mae,patch,logistic,abide_dx,63,0.046415888336127774,test,0.6209677419354839,0.04587652522933254,0.6189604445897352,0.04619548490563489,0.6197478991596639,0.04622762002733167 +flat_mae,patch,logistic,abide_dx,64,2.782559402207126,train,0.9772079772079773,0.005650155206857225,0.9769518681462999,0.005718785951460501,0.9766703580657069,0.005825577693890629 +flat_mae,patch,logistic,abide_dx,64,2.782559402207126,test,0.6774193548387096,0.03987305558788632,0.6732542819499341,0.04067292977259738,0.6727941176470589,0.04051136726330269 +flat_mae,patch,logistic,abide_dx,65,0.3593813663804626,train,0.8874643874643875,0.011671850769642132,0.8860209263754129,0.01185235164587337,0.8852344038390549,0.011954284004094764 +flat_mae,patch,logistic,abide_dx,65,0.3593813663804626,test,0.6532258064516129,0.03951807434316459,0.63853298081486,0.04220804014042799,0.6397058823529411,0.04052657276211348 +flat_mae,patch,logistic,abide_dx,66,0.046415888336127774,train,0.801994301994302,0.01395974300338579,0.7987597007937998,0.014254271969471497,0.7973791066814322,0.014275115081557094 +flat_mae,patch,logistic,abide_dx,66,0.046415888336127774,test,0.5403225806451613,0.042751076320191754,0.5366764995083579,0.04295328093929486,0.5367647058823529,0.042983513433507065 +flat_mae,patch,logistic,abide_dx,67,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,67,1291.5496650148827,test,0.5725806451612904,0.043588544805871245,0.5662332519305657,0.044510150741133916,0.5661764705882353,0.044095013652043956 +flat_mae,patch,logistic,abide_dx,68,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,68,1291.5496650148827,test,0.6854838709677419,0.04085582885342958,0.6779220779220779,0.04209491973376067,0.6769957983193278,0.04143892976936977 +flat_mae,patch,logistic,abide_dx,69,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,69,21.54434690031882,test,0.6532258064516129,0.043457683317614,0.6448884448884449,0.04492721153315774,0.6444327731092437,0.04401724533559756 +flat_mae,patch,logistic,abide_dx,70,0.3593813663804626,train,0.8903133903133903,0.012006814838589001,0.8882671633121735,0.01231763589776201,0.8857511997046881,0.012467044804114872 +flat_mae,patch,logistic,abide_dx,70,0.3593813663804626,test,0.6048387096774194,0.04306765422902485,0.5953379953379954,0.04415220175761734,0.5955882352941176,0.04351695778941927 +flat_mae,patch,logistic,abide_dx,71,0.3593813663804626,train,0.8988603988603988,0.011543820288465144,0.8974265046355845,0.0117382338110785,0.8961609449981542,0.011816615687600064 +flat_mae,patch,logistic,abide_dx,71,0.3593813663804626,test,0.6370967741935484,0.041802282249282736,0.6317074780542539,0.042740573084028996,0.6313025210084033,0.04233991389773561 +flat_mae,patch,logistic,abide_dx,72,2.782559402207126,train,0.9743589743589743,0.005681082418486606,0.9740708516645873,0.005746594677502021,0.9737910668143226,0.005798854444729144 +flat_mae,patch,logistic,abide_dx,72,2.782559402207126,test,0.6693548387096774,0.040908593318324686,0.665680278818965,0.04144989489617444,0.6654411764705883,0.04137245019441476 +flat_mae,patch,logistic,abide_dx,73,0.046415888336127774,train,0.792022792022792,0.01596436680929411,0.7885472370766489,0.016278841013940077,0.7871539313399778,0.016255709739637365 +flat_mae,patch,logistic,abide_dx,73,0.046415888336127774,test,0.5483870967741935,0.04190848696763883,0.5337093741606231,0.044590940496131604,0.5362394957983193,0.04281551178688363 +flat_mae,patch,logistic,abide_dx,74,0.046415888336127774,train,0.7891737891737892,0.014921166315372431,0.7853246495636075,0.015248097105100819,0.7836840162421558,0.015199726874286825 +flat_mae,patch,logistic,abide_dx,74,0.046415888336127774,test,0.5806451612903226,0.0437418046434431,0.5752305665349143,0.04436169983398945,0.5751050420168067,0.04409406896710775 +flat_mae,patch,logistic,abide_dx,75,0.046415888336127774,train,0.7777777777777778,0.015090868773477189,0.7735427678106157,0.015538041997498515,0.7718715393133998,0.015537809538589019 +flat_mae,patch,logistic,abide_dx,75,0.046415888336127774,test,0.6854838709677419,0.04051457196001235,0.6761968530297957,0.0423222640167611,0.6754201680672269,0.041305498302634636 +flat_mae,patch,logistic,abide_dx,76,0.3593813663804626,train,0.886039886039886,0.011842258609253293,0.8843844956644186,0.012068797839253888,0.8830564784053156,0.012204800374680228 +flat_mae,patch,logistic,abide_dx,76,0.3593813663804626,test,0.6612903225806451,0.04220593620556892,0.6569169960474308,0.043109335768229666,0.6565126050420168,0.04287928627568209 +flat_mae,patch,logistic,abide_dx,77,0.3593813663804626,train,0.8888888888888888,0.0118101542954609,0.8871959259015096,0.012042516935027624,0.885640457733481,0.01215907697718687 +flat_mae,patch,logistic,abide_dx,77,0.3593813663804626,test,0.5483870967741935,0.045375482843582414,0.5454307410316837,0.04554380116537438,0.5456932773109244,0.04561301144641273 +flat_mae,patch,logistic,abide_dx,78,2.782559402207126,train,0.9886039886039886,0.00391247660103252,0.9884759340731499,0.003958327939040141,0.988187523071244,0.00404745123950289 +flat_mae,patch,logistic,abide_dx,78,2.782559402207126,test,0.6048387096774194,0.04321718739298347,0.6035753898349319,0.04340313312504794,0.6050420168067226,0.04364351386541886 +flat_mae,patch,logistic,abide_dx,79,0.3593813663804626,train,0.8974358974358975,0.011795079618852568,0.8960863808685784,0.011973501225443247,0.8951642672572906,0.012057882597020227 +flat_mae,patch,logistic,abide_dx,79,0.3593813663804626,test,0.5725806451612904,0.04400431584168887,0.5703170970905524,0.044413429740129365,0.5709033613445378,0.04459509896023174 +flat_mae,patch,logistic,abide_dx,80,0.3593813663804626,train,0.8945868945868946,0.011177905377289224,0.8929807502142528,0.01139886328866,0.8913990402362495,0.011534710381461442 +flat_mae,patch,logistic,abide_dx,80,0.3593813663804626,test,0.6774193548387096,0.042851809476873295,0.6743697478991597,0.04319592910306698,0.6743697478991597,0.04309254610322907 +flat_mae,patch,logistic,abide_dx,81,0.3593813663804626,train,0.8874643874643875,0.011697403062177479,0.8859459159309234,0.011887498650213707,0.8849390919158362,0.011986369287955963 +flat_mae,patch,logistic,abide_dx,81,0.3593813663804626,test,0.6048387096774194,0.04590480977930405,0.5972691721349506,0.04705678371299374,0.5971638655462186,0.046452527886770394 +flat_mae,patch,logistic,abide_dx,82,0.046415888336127774,train,0.7948717948717948,0.014810552750939792,0.7902686373934621,0.015314899208729053,0.7879660391288299,0.015283381468532444 +flat_mae,patch,logistic,abide_dx,82,0.046415888336127774,test,0.5967741935483871,0.04232860401669397,0.58994708994709,0.0429642677360154,0.5898109243697479,0.04254136241586129 +flat_mae,patch,logistic,abide_dx,83,0.3593813663804626,train,0.896011396011396,0.011322086079916069,0.8944641345692461,0.011550945493103516,0.8929863418235511,0.011710184381488454 +flat_mae,patch,logistic,abide_dx,83,0.3593813663804626,test,0.6451612903225806,0.04344469135666592,0.6405797101449275,0.04425067155850372,0.6402310924369747,0.04393354147844788 +flat_mae,patch,logistic,abide_dx,84,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,84,21.54434690031882,test,0.6693548387096774,0.04381261239874785,0.667603792088918,0.043909589744842686,0.66859243697479,0.0437255133261203 +flat_mae,patch,logistic,abide_dx,85,0.046415888336127774,train,0.8005698005698005,0.014232306582599842,0.7966059602649007,0.014644078472919412,0.7946105574012551,0.014627434530960085 +flat_mae,patch,logistic,abide_dx,85,0.046415888336127774,test,0.6209677419354839,0.04318822391235177,0.6179613241560145,0.04364061491914901,0.618172268907563,0.0435962521743453 +flat_mae,patch,logistic,abide_dx,86,2.782559402207126,train,0.9829059829059829,0.00482938421789896,0.9827242524916944,0.004880067238068709,0.9827242524916944,0.004883678559037771 +flat_mae,patch,logistic,abide_dx,86,2.782559402207126,test,0.6451612903225806,0.04512457897278803,0.6405797101449275,0.04571410415238654,0.6402310924369747,0.04544158113307934 +flat_mae,patch,logistic,abide_dx,87,0.3593813663804626,train,0.8931623931623932,0.011357270331661996,0.8916477161643497,0.011558631566106902,0.8904023624953858,0.011668639168383042 +flat_mae,patch,logistic,abide_dx,87,0.3593813663804626,test,0.6048387096774194,0.04483572454672225,0.6035753898349319,0.0448353143756143,0.6050420168067226,0.04499623088358909 +flat_mae,patch,logistic,abide_dx,88,10000.0,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,88,10000.0,test,0.6451612903225806,0.04274332316676125,0.6405797101449275,0.0433514899261993,0.6402310924369747,0.04313013697913881 +flat_mae,patch,logistic,abide_dx,89,0.3593813663804626,train,0.8903133903133903,0.011637990422791978,0.8886813474223556,0.011860402036734172,0.8872277593207826,0.011988043935245376 +flat_mae,patch,logistic,abide_dx,89,0.3593813663804626,test,0.6129032258064516,0.042881934445276486,0.610369206598586,0.04342461987102719,0.6108193277310925,0.043504813525320284 +flat_mae,patch,logistic,abide_dx,90,0.3593813663804626,train,0.9031339031339032,0.010621765427472962,0.9017939433838051,0.010811083403038131,0.9006275378368402,0.010955607277756699 +flat_mae,patch,logistic,abide_dx,90,0.3593813663804626,test,0.5967741935483871,0.04025897887195718,0.571704890853827,0.0441733862391947,0.578781512605042,0.041002459123704864 +flat_mae,patch,logistic,abide_dx,91,0.3593813663804626,train,0.896011396011396,0.011131180647354409,0.8943126486183265,0.011375502666809747,0.8923957179771134,0.011546568390720687 +flat_mae,patch,logistic,abide_dx,91,0.3593813663804626,test,0.6612903225806451,0.04145951663069385,0.6598746081504703,0.041603293345618714,0.6612394957983193,0.041569254577998725 +flat_mae,patch,logistic,abide_dx,92,2.782559402207126,train,0.9843304843304843,0.005130629373181543,0.9841685408692337,0.005182566060800705,0.984311554078996,0.005168824535382726 +flat_mae,patch,logistic,abide_dx,92,2.782559402207126,test,0.5645161290322581,0.04465882925219715,0.5626959247648903,0.044962957133648215,0.5635504201680672,0.04501177763120222 +flat_mae,patch,logistic,abide_dx,93,0.046415888336127774,train,0.8005698005698005,0.014547784943732878,0.7976728674127325,0.014794659139842075,0.7966777408637873,0.01482629790875814 +flat_mae,patch,logistic,abide_dx,93,0.046415888336127774,test,0.5241935483870968,0.0442655729312327,0.5171275823377994,0.044525729440611506,0.5173319327731093,0.044291285883532365 +flat_mae,patch,logistic,abide_dx,94,0.046415888336127774,train,0.7948717948717948,0.015856812508642126,0.7902686373934621,0.016367973305051627,0.7879660391288299,0.016296951551586846 +flat_mae,patch,logistic,abide_dx,94,0.046415888336127774,test,0.5725806451612904,0.04469637131514029,0.5691904293674206,0.04502471038014162,0.569327731092437,0.045000578119692644 +flat_mae,patch,logistic,abide_dx,95,0.3593813663804626,train,0.8931623931623932,0.011181070935733688,0.8917208062635349,0.011373297905259904,0.8906976744186046,0.011504248679834208 +flat_mae,patch,logistic,abide_dx,95,0.3593813663804626,test,0.6370967741935484,0.04267588018095892,0.6317074780542539,0.04369149890904836,0.6313025210084033,0.043401821925464795 +flat_mae,patch,logistic,abide_dx,96,0.3593813663804626,train,0.9045584045584045,0.011285728486466064,0.9031383152895821,0.011515532439652918,0.9016242155777039,0.011704988898420629 +flat_mae,patch,logistic,abide_dx,96,0.3593813663804626,test,0.6451612903225806,0.04264578046009931,0.6391534391534391,0.04348308551950178,0.6386554621848739,0.04288171610764215 +flat_mae,patch,logistic,abide_dx,97,0.005994842503189409,train,0.698005698005698,0.017006475509391956,0.6862292012784941,0.018111008555310365,0.6853451458102621,0.017525704148429935 +flat_mae,patch,logistic,abide_dx,97,0.005994842503189409,test,0.6854838709677419,0.04137466184852905,0.6761968530297957,0.043574483071261175,0.6754201680672269,0.04250664183085925 +flat_mae,patch,logistic,abide_dx,98,0.3593813663804626,train,0.9002849002849003,0.011197725088910915,0.8989728702888957,0.011364972572614035,0.8980435585086748,0.011423562739325368 +flat_mae,patch,logistic,abide_dx,98,0.3593813663804626,test,0.6370967741935484,0.04191829362307763,0.6283716283716283,0.043593731499573074,0.6281512605042017,0.042730601824935294 +flat_mae,patch,logistic,abide_dx,99,0.3593813663804626,train,0.8874643874643875,0.011045029221963973,0.8853650117098923,0.011358399334285814,0.8828719084533039,0.011536410508363036 +flat_mae,patch,logistic,abide_dx,99,0.3593813663804626,test,0.6209677419354839,0.04206741034967062,0.6167554415729598,0.04284965658192576,0.6165966386554622,0.04264711579455564 +flat_mae,patch,logistic,abide_dx,100,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,100,21.54434690031882,test,0.5806451612903226,0.042011729693525256,0.5735449735449736,0.043033949166352316,0.5735294117647058,0.042630441082356633 diff --git a/input_space_v3/flat_lr1e-3_4/eval_v2/abide_dx__patch__logistic/log.txt b/input_space_v3/flat_lr1e-3_4/eval_v2/abide_dx__patch__logistic/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..321dae737ef9b8afc797f43df9cd1dfdf736afaa --- /dev/null +++ b/input_space_v3/flat_lr1e-3_4/eval_v2/abide_dx__patch__logistic/log.txt @@ -0,0 +1,252 @@ +fMRI foundation model logistic probe eval +version: 0.1.dev86+gf97f52698 +sha: bcce2b486277d3a5b520775efd9cdf1a2affce36, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-04-08 22:19:46 +config: +output_root: experiments/input_space_v3/output +name_prefix: eval_logistic +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_4; eval v2 (abide_dx patch logistic) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: input_space_v3/flat_lr1e-3_4/eval_v2/abide_dx__patch__logistic +model: flat_mae +representation: patch +dataset: abide_dx +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/eval_v2/abide_dx__patch__logistic +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=True, reg_tokens=0, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: abide_dx (flat) +train (n=578): +HFDataset( + dataset=Dataset({ + features: ['sub', 'site', 'dataset', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 578 +}), + labels=['Autism' 'Control'], + counts=[260 318] +) + +validation (n=124): +HFDataset( + dataset=Dataset({ + features: ['sub', 'site', 'dataset', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 124 +}), + labels=['Autism' 'Control'], + counts=[54 70] +) + +test (n=124): +HFDataset( + dataset=Dataset({ + features: ['sub', 'site', 'dataset', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 124 +}), + labels=['Autism' 'Control'], + counts=[57 67] +) + +extracting features for all splits +extract (train) [ 0/289] eta: 0:23:13 time: 4.8230 data: 3.7907 max mem: 2698 +extract (train) [ 20/289] eta: 0:01:51 time: 0.1950 data: 0.0649 max mem: 2851 +extract (train) [ 40/289] eta: 0:01:13 time: 0.1699 data: 0.0523 max mem: 2851 +extract (train) [ 60/289] eta: 0:00:59 time: 0.1926 data: 0.0655 max mem: 2851 +extract (train) [ 80/289] eta: 0:00:51 time: 0.1937 data: 0.0665 max mem: 2851 +extract (train) [100/289] eta: 0:00:43 time: 0.1696 data: 0.0537 max mem: 2851 +extract (train) [120/289] eta: 0:00:37 time: 0.1873 data: 0.0617 max mem: 2851 +extract (train) [140/289] eta: 0:00:32 time: 0.1778 data: 0.0580 max mem: 2851 +extract (train) [160/289] eta: 0:00:27 time: 0.1884 data: 0.0646 max mem: 2851 +extract (train) [180/289] eta: 0:00:22 time: 0.1732 data: 0.0550 max mem: 2851 +extract (train) [200/289] eta: 0:00:18 time: 0.1850 data: 0.0616 max mem: 2851 +extract (train) [220/289] eta: 0:00:14 time: 0.1730 data: 0.0550 max mem: 2851 +extract (train) [240/289] eta: 0:00:09 time: 0.1705 data: 0.0547 max mem: 2851 +extract (train) [260/289] eta: 0:00:05 time: 0.1677 data: 0.0525 max mem: 2851 +extract (train) [280/289] eta: 0:00:01 time: 0.1586 data: 0.0478 max mem: 2851 +extract (train) [288/289] eta: 0:00:00 time: 0.1598 data: 0.0477 max mem: 2851 +extract (train) Total time: 0:00:56 (0.1957 s / it) +extract (validation) [ 0/62] eta: 0:04:15 time: 4.1157 data: 3.8324 max mem: 2851 +extract (validation) [20/62] eta: 0:00:17 time: 0.2295 data: 0.0806 max mem: 2851 +extract (validation) [40/62] eta: 0:00:06 time: 0.1762 data: 0.0569 max mem: 2851 +extract (validation) [60/62] eta: 0:00:00 time: 0.1656 data: 0.0520 max mem: 2851 +extract (validation) [61/62] eta: 0:00:00 time: 0.1646 data: 0.0516 max mem: 2851 +extract (validation) Total time: 0:00:16 (0.2584 s / it) +extract (test) [ 0/62] eta: 0:03:54 time: 3.7784 data: 3.5355 max mem: 2851 +extract (test) [20/62] eta: 0:00:16 time: 0.2136 data: 0.0718 max mem: 2851 +extract (test) [40/62] eta: 0:00:06 time: 0.1708 data: 0.0556 max mem: 2851 +extract (test) [60/62] eta: 0:00:00 time: 0.1698 data: 0.0553 max mem: 2851 +extract (test) [61/62] eta: 0:00:00 time: 0.1702 data: 0.0556 max mem: 2851 +extract (test) Total time: 0:00:15 (0.2485 s / it) +feature extraction time: 0:01:28 +train features: (578, 768) +validation features: (124, 768) +test features: (124, 768) +evaluating fixed splits +eval results (fixed splits): + +| model | repr | clf | dataset | trial | C | split | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|---------:|:--------|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | abide_dx | | 0.046416 | train | 0.7963 | 0.014619 | 0.79145 | 0.015102 | 0.789 | 0.015013 | +| flat_mae | patch | logistic | abide_dx | | 0.046416 | test | 0.62903 | 0.046444 | 0.62424 | 0.047553 | 0.62399 | 0.047076 | + + +evaluating random splits (n=100) +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 1, "C": 0.005994842503189409, "split": "test", "acc": 0.6612903225806451, "acc_std": 0.04075222713729059, "f1": 0.6539994685091681, "f1_std": 0.04228737927116954, "bacc": 0.6533613445378151, "bacc_std": 0.04158101834876175} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 2, "C": 0.3593813663804626, "split": "test", "acc": 0.5967741935483871, "acc_std": 0.04471088766224962, "f1": 0.5941345902068604, "f1_std": 0.04513592471823754, "bacc": 0.5945378151260504, "bacc_std": 0.04520855195373101} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 3, "C": 0.3593813663804626, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.04323101497266883, "f1": 0.607905138339921, "f1_std": 0.04352570552880119, "bacc": 0.6076680672268908, "bacc_std": 0.04328722218644109} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 4, "C": 1291.5496650148827, "split": "test", "acc": 0.6693548387096774, "acc_std": 0.0405584199869994, "f1": 0.667603792088918, "f1_std": 0.0410012301511435, "bacc": 0.66859243697479, "bacc_std": 0.04136338690584094} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 5, "C": 10000.0, "split": "test", "acc": 0.6048387096774194, "acc_std": 0.04336887733538816, "f1": 0.602745995423341, "f1_std": 0.04371452264285463, "bacc": 0.6034663865546219, "bacc_std": 0.04374561599742388} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 6, "C": 0.3593813663804626, "split": "test", "acc": 0.6209677419354839, "acc_std": 0.04326806732873798, "f1": 0.6118548118548119, "f1_std": 0.04440477002810697, "bacc": 0.6118697478991597, "bacc_std": 0.04360774890544062} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 7, "C": 0.005994842503189409, "split": "test", "acc": 0.6612903225806451, "acc_std": 0.04150589830581597, "f1": 0.6481081081081081, "f1_std": 0.04427472683340092, "bacc": 0.6486344537815126, "bacc_std": 0.04243955462403348} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 8, "C": 0.046415888336127774, "split": "test", "acc": 0.6532258064516129, "acc_std": 0.04242303430626174, "f1": 0.6465831510572015, "f1_std": 0.04342280246520486, "bacc": 0.6460084033613445, "bacc_std": 0.04296492680685404} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 9, "C": 10000.0, "split": "test", "acc": 0.6209677419354839, "acc_std": 0.042281377464942954, "f1": 0.6097756946769334, "f1_std": 0.04408816341794222, "bacc": 0.6102941176470589, "bacc_std": 0.04293046120769825} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 10, "C": 0.046415888336127774, "split": "test", "acc": 0.6048387096774194, "acc_std": 0.044971953336370184, "f1": 0.5989703649924097, "f1_std": 0.04569538291014515, "bacc": 0.5987394957983193, "bacc_std": 0.04531392877718877} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 11, "C": 2.782559402207126, "split": "test", "acc": 0.5483870967741935, "acc_std": 0.04339421934581466, "f1": 0.5407407407407407, "f1_std": 0.04431418054305846, "bacc": 0.5409663865546219, "bacc_std": 0.04380830645145373} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 12, "C": 0.046415888336127774, "split": "test", "acc": 0.6209677419354839, "acc_std": 0.04466750792587394, "f1": 0.6189604445897352, "f1_std": 0.04473844803620251, "bacc": 0.6197478991596639, "bacc_std": 0.044732044610621226} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 13, "C": 0.3593813663804626, "split": "test", "acc": 0.6370967741935484, "acc_std": 0.04186314791037172, "f1": 0.6301451580831179, "f1_std": 0.04314769505970364, "bacc": 0.6297268907563025, "bacc_std": 0.04272028403335686} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 14, "C": 0.3593813663804626, "split": "test", "acc": 0.6693548387096774, "acc_std": 0.041898280643908443, "f1": 0.6644445911160979, "f1_std": 0.042994094355152175, "bacc": 0.6638655462184874, "bacc_std": 0.04266913190831841} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 15, "C": 21.54434690031882, "split": "test", "acc": 0.6048387096774194, "acc_std": 0.0435711380236787, "f1": 0.6017043592264831, "f1_std": 0.04392370218671205, "bacc": 0.601890756302521, "bacc_std": 0.04392061568432181} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 16, "C": 2.782559402207126, "split": "test", "acc": 0.6451612903225806, "acc_std": 0.04158108310788161, "f1": 0.6375232527238905, "f1_std": 0.04318484822120767, "bacc": 0.6370798319327731, "bacc_std": 0.042603889685637275} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 17, "C": 0.3593813663804626, "split": "test", "acc": 0.5806451612903226, "acc_std": 0.0427449907611605, "f1": 0.5752305665349143, "f1_std": 0.043686464825369975, "bacc": 0.5751050420168067, "bacc_std": 0.043429531897924256} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 18, "C": 166.81005372000556, "split": "test", "acc": 0.6451612903225806, "acc_std": 0.04290639086069751, "f1": 0.6375232527238905, "f1_std": 0.044328363519900105, "bacc": 0.6370798319327731, "bacc_std": 0.04361640988087078} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 19, "C": 0.3593813663804626, "split": "test", "acc": 0.6370967741935484, "acc_std": 0.044034869354213635, "f1": 0.626380984265149, "f1_std": 0.04595575576870355, "bacc": 0.6265756302521008, "bacc_std": 0.04477228311205918} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 20, "C": 0.3593813663804626, "split": "test", "acc": 0.5483870967741935, "acc_std": 0.0433817930563332, "f1": 0.5363247863247864, "f1_std": 0.04515001851193473, "bacc": 0.5378151260504201, "bacc_std": 0.04406581182297077} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 21, "C": 0.046415888336127774, "split": "test", "acc": 0.6209677419354839, "acc_std": 0.04270382963572132, "f1": 0.6097756946769334, "f1_std": 0.044739615625882155, "bacc": 0.6102941176470589, "bacc_std": 0.04343297629297334} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 22, "C": 0.3593813663804626, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.043209000103061244, "f1": 0.6045708211533352, "f1_std": 0.044340277345591275, "bacc": 0.6045168067226891, "bacc_std": 0.043626279715271055} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 23, "C": 0.3593813663804626, "split": "test", "acc": 0.6854838709677419, "acc_std": 0.04197973781596039, "f1": 0.6761968530297957, "f1_std": 0.044223131000956366, "bacc": 0.6754201680672269, "bacc_std": 0.04314002275414597} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 24, "C": 0.3593813663804626, "split": "test", "acc": 0.6451612903225806, "acc_std": 0.04371691107862016, "f1": 0.6428384393820372, "f1_std": 0.04398774617239939, "bacc": 0.6433823529411764, "bacc_std": 0.04386731418891198} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 25, "C": 2.782559402207126, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.04306634042287961, "f1": 0.6025641025641025, "f1_std": 0.04450273372235099, "bacc": 0.6029411764705883, "bacc_std": 0.04354376470556692} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 26, "C": 0.3593813663804626, "split": "test", "acc": 0.6451612903225806, "acc_std": 0.04044389492663421, "f1": 0.6336287939833467, "f1_std": 0.04289433665267536, "bacc": 0.6339285714285714, "bacc_std": 0.041434907609027} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 27, "C": 2.782559402207126, "split": "test", "acc": 0.6290322580645161, "acc_std": 0.04417641238296944, "f1": 0.6210470369386127, "f1_std": 0.0456099966296783, "bacc": 0.6207983193277311, "bacc_std": 0.04487972862094829} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 28, "C": 0.046415888336127774, "split": "test", "acc": 0.6370967741935484, "acc_std": 0.042147799998873685, "f1": 0.6351748937561295, "f1_std": 0.042455716980180566, "bacc": 0.6360294117647058, "bacc_std": 0.04249102920231667} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 29, "C": 0.3593813663804626, "split": "test", "acc": 0.6290322580645161, "acc_std": 0.043433165971956886, "f1": 0.6274817136886102, "f1_std": 0.04357381496639475, "bacc": 0.6286764705882353, "bacc_std": 0.043687259569286055} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 30, "C": 0.046415888336127774, "split": "test", "acc": 0.6935483870967742, "acc_std": 0.041216197956451935, "f1": 0.6869519000797236, "f1_std": 0.042651036781073445, "bacc": 0.6859243697478992, "bacc_std": 0.0418692831792085} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 31, "C": 0.3593813663804626, "split": "test", "acc": 0.6451612903225806, "acc_std": 0.04508951381400503, "f1": 0.6336287939833467, "f1_std": 0.047508776749286205, "bacc": 0.6339285714285714, "bacc_std": 0.045956746642532936} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 32, "C": 0.3593813663804626, "split": "test", "acc": 0.6935483870967742, "acc_std": 0.043206480393233423, "f1": 0.6895915678524374, "f1_std": 0.0435832649292186, "bacc": 0.6890756302521008, "bacc_std": 0.04336312231460434} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 33, "C": 0.3593813663804626, "split": "test", "acc": 0.6532258064516129, "acc_std": 0.0393177078935973, "f1": 0.6448884448884449, "f1_std": 0.04060688021795231, "bacc": 0.6444327731092437, "bacc_std": 0.03986638567117156} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 34, "C": 21.54434690031882, "split": "test", "acc": 0.6854838709677419, "acc_std": 0.040355522028200495, "f1": 0.6819885579009667, "f1_std": 0.04113670079796081, "bacc": 0.6817226890756303, "bacc_std": 0.04112481661674398} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 35, "C": 0.3593813663804626, "split": "test", "acc": 0.6048387096774194, "acc_std": 0.043389387156238614, "f1": 0.602745995423341, "f1_std": 0.04363031636844909, "bacc": 0.6034663865546219, "bacc_std": 0.04371843029315158} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 36, "C": 21.54434690031882, "split": "test", "acc": 0.5967741935483871, "acc_std": 0.04257415334188521, "f1": 0.5915678524374176, "f1_std": 0.04308092881376521, "bacc": 0.5913865546218487, "bacc_std": 0.0428266656519097} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 37, "C": 0.3593813663804626, "split": "test", "acc": 0.6370967741935484, "acc_std": 0.04420903896162536, "f1": 0.6330637206549615, "f1_std": 0.04482622590756497, "bacc": 0.6328781512605042, "bacc_std": 0.04466316661113086} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 38, "C": 0.3593813663804626, "split": "test", "acc": 0.6209677419354839, "acc_std": 0.042636434005233384, "f1": 0.6179613241560145, "f1_std": 0.04301107820939371, "bacc": 0.618172268907563, "bacc_std": 0.0430089354821714} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 39, "C": 0.046415888336127774, "split": "test", "acc": 0.532258064516129, "acc_std": 0.04444024329057264, "f1": 0.5262187088274045, "f1_std": 0.044801343847736874, "bacc": 0.5262605042016807, "bacc_std": 0.04457816780004468} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 40, "C": 0.046415888336127774, "split": "test", "acc": 0.5887096774193549, "acc_std": 0.04116824190464357, "f1": 0.5765651155005022, "f1_std": 0.04334704864576026, "bacc": 0.5777310924369747, "bacc_std": 0.04202541797261388} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 41, "C": 0.046415888336127774, "split": "test", "acc": 0.6290322580645161, "acc_std": 0.039749750488421665, "f1": 0.6210470369386127, "f1_std": 0.041218635024784664, "bacc": 0.6207983193277311, "bacc_std": 0.04052892666663992} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 42, "C": 0.3593813663804626, "split": "test", "acc": 0.5564516129032258, "acc_std": 0.04724775842702776, "f1": 0.5550336008351275, "f1_std": 0.04738246649807175, "bacc": 0.5561974789915967, "bacc_std": 0.04746633006788804} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 43, "C": 0.046415888336127774, "split": "test", "acc": 0.6612903225806451, "acc_std": 0.04371453073876829, "f1": 0.6555555555555556, "f1_std": 0.04483887919023059, "bacc": 0.654936974789916, "bacc_std": 0.044371788748482854} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 44, "C": 0.046415888336127774, "split": "test", "acc": 0.5725806451612904, "acc_std": 0.04264628371955111, "f1": 0.5573516535327002, "f1_std": 0.04532402144048034, "bacc": 0.5598739495798319, "bacc_std": 0.04342348046436083} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 45, "C": 0.005994842503189409, "split": "test", "acc": 0.5887096774193549, "acc_std": 0.04176409144261437, "f1": 0.5712833028269271, "f1_std": 0.04443326958163723, "bacc": 0.5745798319327731, "bacc_std": 0.04243866815564399} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 46, "C": 0.005994842503189409, "split": "test", "acc": 0.5564516129032258, "acc_std": 0.043833487310291415, "f1": 0.5498646953996436, "f1_std": 0.044566537816004524, "bacc": 0.5498949579831933, "bacc_std": 0.04425533011374791} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 47, "C": 0.3593813663804626, "split": "test", "acc": 0.5806451612903226, "acc_std": 0.04504709063424387, "f1": 0.5788923719958203, "f1_std": 0.04521948999411249, "bacc": 0.5798319327731092, "bacc_std": 0.04531844805896603} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 48, "C": 0.3593813663804626, "split": "test", "acc": 0.6048387096774194, "acc_std": 0.0433107344551286, "f1": 0.5953379953379954, "f1_std": 0.044503126135863776, "bacc": 0.5955882352941176, "bacc_std": 0.04366926382837147} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 49, "C": 0.3593813663804626, "split": "test", "acc": 0.6048387096774194, "acc_std": 0.04206022081275724, "f1": 0.6004471624909581, "f1_std": 0.042739806336062454, "bacc": 0.6003151260504203, "bacc_std": 0.04262847522208488} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 50, "C": 0.3593813663804626, "split": "test", "acc": 0.5887096774193549, "acc_std": 0.044706360720436246, "f1": 0.5826018084614877, "f1_std": 0.045597432783155416, "bacc": 0.5824579831932774, "bacc_std": 0.04524985042741168} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 51, "C": 0.005994842503189409, "split": "test", "acc": 0.5645161290322581, "acc_std": 0.042885088938672336, "f1": 0.5411184210526316, "f1_std": 0.04633467716118664, "bacc": 0.5477941176470589, "bacc_std": 0.04355161056464932} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 52, "C": 166.81005372000556, "split": "test", "acc": 0.5806451612903226, "acc_std": 0.04394803477592569, "f1": 0.5766806722689075, "f1_std": 0.04444916353780629, "bacc": 0.5766806722689075, "bacc_std": 0.04443443294076792} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 53, "C": 0.046415888336127774, "split": "test", "acc": 0.5806451612903226, "acc_std": 0.04635298669611662, "f1": 0.5716183895827798, "f1_std": 0.04762310306732199, "bacc": 0.571953781512605, "bacc_std": 0.046826112915536205} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 54, "C": 0.3593813663804626, "split": "test", "acc": 0.6612903225806451, "acc_std": 0.04154935132120981, "f1": 0.6569169960474308, "f1_std": 0.04227549138260596, "bacc": 0.6565126050420168, "bacc_std": 0.04202709919893152} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 55, "C": 2.782559402207126, "split": "test", "acc": 0.6048387096774194, "acc_std": 0.043251975107229244, "f1": 0.5989703649924097, "f1_std": 0.04383594134799062, "bacc": 0.5987394957983193, "bacc_std": 0.04356985514123794} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 56, "C": 0.005994842503189409, "split": "test", "acc": 0.6774193548387096, "acc_std": 0.038673622321623136, "f1": 0.6669352672575879, "f1_std": 0.04076957558442832, "bacc": 0.6664915966386555, "bacc_std": 0.03959334341581953} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 57, "C": 166.81005372000556, "split": "test", "acc": 0.6290322580645161, "acc_std": 0.042031329675583734, "f1": 0.6210470369386127, "f1_std": 0.0432349177616727, "bacc": 0.6207983193277311, "bacc_std": 0.04261216848019545} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 58, "C": 0.3593813663804626, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.042927021657057376, "f1": 0.607905138339921, "f1_std": 0.043680523796633654, "bacc": 0.6076680672268908, "bacc_std": 0.0433179091821631} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 59, "C": 0.005994842503189409, "split": "test", "acc": 0.6209677419354839, "acc_std": 0.043066316260552184, "f1": 0.6189604445897352, "f1_std": 0.04319770406385825, "bacc": 0.6197478991596639, "bacc_std": 0.04330936639171262} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 60, "C": 0.046415888336127774, "split": "test", "acc": 0.6048387096774194, "acc_std": 0.04151130382767403, "f1": 0.5972691721349506, "f1_std": 0.04301941423179908, "bacc": 0.5971638655462186, "bacc_std": 0.04235326031334011} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 61, "C": 0.3593813663804626, "split": "test", "acc": 0.5806451612903226, "acc_std": 0.04403130980900248, "f1": 0.5752305665349143, "f1_std": 0.04470847799821994, "bacc": 0.5751050420168067, "bacc_std": 0.044370042284403464} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 62, "C": 1291.5496650148827, "split": "test", "acc": 0.5806451612903226, "acc_std": 0.0436602505923844, "f1": 0.5788923719958203, "f1_std": 0.04398510224997375, "bacc": 0.5798319327731092, "bacc_std": 0.044311076265064676} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 63, "C": 0.046415888336127774, "split": "test", "acc": 0.6209677419354839, "acc_std": 0.04587652522933254, "f1": 0.6189604445897352, "f1_std": 0.04619548490563489, "bacc": 0.6197478991596639, "bacc_std": 0.04622762002733167} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 64, "C": 2.782559402207126, "split": "test", "acc": 0.6774193548387096, "acc_std": 0.03987305558788632, "f1": 0.6732542819499341, "f1_std": 0.04067292977259738, "bacc": 0.6727941176470589, "bacc_std": 0.04051136726330269} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 65, "C": 0.3593813663804626, "split": "test", "acc": 0.6532258064516129, "acc_std": 0.03951807434316459, "f1": 0.63853298081486, "f1_std": 0.04220804014042799, "bacc": 0.6397058823529411, "bacc_std": 0.04052657276211348} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 66, "C": 0.046415888336127774, "split": "test", "acc": 0.5403225806451613, "acc_std": 0.042751076320191754, "f1": 0.5366764995083579, "f1_std": 0.04295328093929486, "bacc": 0.5367647058823529, "bacc_std": 0.042983513433507065} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 67, "C": 1291.5496650148827, "split": "test", "acc": 0.5725806451612904, "acc_std": 0.043588544805871245, "f1": 0.5662332519305657, "f1_std": 0.044510150741133916, "bacc": 0.5661764705882353, "bacc_std": 0.044095013652043956} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 68, "C": 1291.5496650148827, "split": "test", "acc": 0.6854838709677419, "acc_std": 0.04085582885342958, "f1": 0.6779220779220779, "f1_std": 0.04209491973376067, "bacc": 0.6769957983193278, "bacc_std": 0.04143892976936977} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 69, "C": 21.54434690031882, "split": "test", "acc": 0.6532258064516129, "acc_std": 0.043457683317614, "f1": 0.6448884448884449, "f1_std": 0.04492721153315774, "bacc": 0.6444327731092437, "bacc_std": 0.04401724533559756} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 70, "C": 0.3593813663804626, "split": "test", "acc": 0.6048387096774194, "acc_std": 0.04306765422902485, "f1": 0.5953379953379954, "f1_std": 0.04415220175761734, "bacc": 0.5955882352941176, "bacc_std": 0.04351695778941927} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 71, "C": 0.3593813663804626, "split": "test", "acc": 0.6370967741935484, "acc_std": 0.041802282249282736, "f1": 0.6317074780542539, "f1_std": 0.042740573084028996, "bacc": 0.6313025210084033, "bacc_std": 0.04233991389773561} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 72, "C": 2.782559402207126, "split": "test", "acc": 0.6693548387096774, "acc_std": 0.040908593318324686, "f1": 0.665680278818965, "f1_std": 0.04144989489617444, "bacc": 0.6654411764705883, "bacc_std": 0.04137245019441476} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 73, "C": 0.046415888336127774, "split": "test", "acc": 0.5483870967741935, "acc_std": 0.04190848696763883, "f1": 0.5337093741606231, "f1_std": 0.044590940496131604, "bacc": 0.5362394957983193, "bacc_std": 0.04281551178688363} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 74, "C": 0.046415888336127774, "split": "test", "acc": 0.5806451612903226, "acc_std": 0.0437418046434431, "f1": 0.5752305665349143, "f1_std": 0.04436169983398945, "bacc": 0.5751050420168067, "bacc_std": 0.04409406896710775} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 75, "C": 0.046415888336127774, "split": "test", "acc": 0.6854838709677419, "acc_std": 0.04051457196001235, "f1": 0.6761968530297957, "f1_std": 0.0423222640167611, "bacc": 0.6754201680672269, "bacc_std": 0.041305498302634636} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 76, "C": 0.3593813663804626, "split": "test", "acc": 0.6612903225806451, "acc_std": 0.04220593620556892, "f1": 0.6569169960474308, "f1_std": 0.043109335768229666, "bacc": 0.6565126050420168, "bacc_std": 0.04287928627568209} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 77, "C": 0.3593813663804626, "split": "test", "acc": 0.5483870967741935, "acc_std": 0.045375482843582414, "f1": 0.5454307410316837, "f1_std": 0.04554380116537438, "bacc": 0.5456932773109244, "bacc_std": 0.04561301144641273} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 78, "C": 2.782559402207126, "split": "test", "acc": 0.6048387096774194, "acc_std": 0.04321718739298347, "f1": 0.6035753898349319, "f1_std": 0.04340313312504794, "bacc": 0.6050420168067226, "bacc_std": 0.04364351386541886} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 79, "C": 0.3593813663804626, "split": "test", "acc": 0.5725806451612904, "acc_std": 0.04400431584168887, "f1": 0.5703170970905524, "f1_std": 0.044413429740129365, "bacc": 0.5709033613445378, "bacc_std": 0.04459509896023174} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 80, "C": 0.3593813663804626, "split": "test", "acc": 0.6774193548387096, "acc_std": 0.042851809476873295, "f1": 0.6743697478991597, "f1_std": 0.04319592910306698, "bacc": 0.6743697478991597, "bacc_std": 0.04309254610322907} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 81, "C": 0.3593813663804626, "split": "test", "acc": 0.6048387096774194, "acc_std": 0.04590480977930405, "f1": 0.5972691721349506, "f1_std": 0.04705678371299374, "bacc": 0.5971638655462186, "bacc_std": 0.046452527886770394} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 82, "C": 0.046415888336127774, "split": "test", "acc": 0.5967741935483871, "acc_std": 0.04232860401669397, "f1": 0.58994708994709, "f1_std": 0.0429642677360154, "bacc": 0.5898109243697479, "bacc_std": 0.04254136241586129} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 83, "C": 0.3593813663804626, "split": "test", "acc": 0.6451612903225806, "acc_std": 0.04344469135666592, "f1": 0.6405797101449275, "f1_std": 0.04425067155850372, "bacc": 0.6402310924369747, "bacc_std": 0.04393354147844788} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 84, "C": 21.54434690031882, "split": "test", "acc": 0.6693548387096774, "acc_std": 0.04381261239874785, "f1": 0.667603792088918, "f1_std": 0.043909589744842686, "bacc": 0.66859243697479, "bacc_std": 0.0437255133261203} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 85, "C": 0.046415888336127774, "split": "test", "acc": 0.6209677419354839, "acc_std": 0.04318822391235177, "f1": 0.6179613241560145, "f1_std": 0.04364061491914901, "bacc": 0.618172268907563, "bacc_std": 0.0435962521743453} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 86, "C": 2.782559402207126, "split": "test", "acc": 0.6451612903225806, "acc_std": 0.04512457897278803, "f1": 0.6405797101449275, "f1_std": 0.04571410415238654, "bacc": 0.6402310924369747, "bacc_std": 0.04544158113307934} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 87, "C": 0.3593813663804626, "split": "test", "acc": 0.6048387096774194, "acc_std": 0.04483572454672225, "f1": 0.6035753898349319, "f1_std": 0.0448353143756143, "bacc": 0.6050420168067226, "bacc_std": 0.04499623088358909} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 88, "C": 10000.0, "split": "test", "acc": 0.6451612903225806, "acc_std": 0.04274332316676125, "f1": 0.6405797101449275, "f1_std": 0.0433514899261993, "bacc": 0.6402310924369747, "bacc_std": 0.04313013697913881} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 89, "C": 0.3593813663804626, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.042881934445276486, "f1": 0.610369206598586, "f1_std": 0.04342461987102719, "bacc": 0.6108193277310925, "bacc_std": 0.043504813525320284} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 90, "C": 0.3593813663804626, "split": "test", "acc": 0.5967741935483871, "acc_std": 0.04025897887195718, "f1": 0.571704890853827, "f1_std": 0.0441733862391947, "bacc": 0.578781512605042, "bacc_std": 0.041002459123704864} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 91, "C": 0.3593813663804626, "split": "test", "acc": 0.6612903225806451, "acc_std": 0.04145951663069385, "f1": 0.6598746081504703, "f1_std": 0.041603293345618714, "bacc": 0.6612394957983193, "bacc_std": 0.041569254577998725} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 92, "C": 2.782559402207126, "split": "test", "acc": 0.5645161290322581, "acc_std": 0.04465882925219715, "f1": 0.5626959247648903, "f1_std": 0.044962957133648215, "bacc": 0.5635504201680672, "bacc_std": 0.04501177763120222} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 93, "C": 0.046415888336127774, "split": "test", "acc": 0.5241935483870968, "acc_std": 0.0442655729312327, "f1": 0.5171275823377994, "f1_std": 0.044525729440611506, "bacc": 0.5173319327731093, "bacc_std": 0.044291285883532365} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 94, "C": 0.046415888336127774, "split": "test", "acc": 0.5725806451612904, "acc_std": 0.04469637131514029, "f1": 0.5691904293674206, "f1_std": 0.04502471038014162, "bacc": 0.569327731092437, "bacc_std": 0.045000578119692644} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 95, "C": 0.3593813663804626, "split": "test", "acc": 0.6370967741935484, "acc_std": 0.04267588018095892, "f1": 0.6317074780542539, "f1_std": 0.04369149890904836, "bacc": 0.6313025210084033, "bacc_std": 0.043401821925464795} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 96, "C": 0.3593813663804626, "split": "test", "acc": 0.6451612903225806, "acc_std": 0.04264578046009931, "f1": 0.6391534391534391, "f1_std": 0.04348308551950178, "bacc": 0.6386554621848739, "bacc_std": 0.04288171610764215} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 97, "C": 0.005994842503189409, "split": "test", "acc": 0.6854838709677419, "acc_std": 0.04137466184852905, "f1": 0.6761968530297957, "f1_std": 0.043574483071261175, "bacc": 0.6754201680672269, "bacc_std": 0.04250664183085925} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 98, "C": 0.3593813663804626, "split": "test", "acc": 0.6370967741935484, "acc_std": 0.04191829362307763, "f1": 0.6283716283716283, "f1_std": 0.043593731499573074, "bacc": 0.6281512605042017, "bacc_std": 0.042730601824935294} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 99, "C": 0.3593813663804626, "split": "test", "acc": 0.6209677419354839, "acc_std": 0.04206741034967062, "f1": 0.6167554415729598, "f1_std": 0.04284965658192576, "bacc": 0.6165966386554622, "bacc_std": 0.04264711579455564} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 100, "C": 21.54434690031882, "split": "test", "acc": 0.5806451612903226, "acc_std": 0.042011729693525256, "f1": 0.5735449735449736, "f1_std": 0.043033949166352316, "bacc": 0.5735294117647058, "bacc_std": 0.042630441082356633} +eval results (random splits): + +| model | repr | clf | dataset | split | n_trials | C | C_std | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|-----------:|-------:|--------:|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | abide_dx | train | 100 | 358.41 | 1723 | 0.8835 | 0.086661 | 0.88123 | 0.088926 | 0.88009 | 0.089447 | +| flat_mae | patch | logistic | abide_dx | test | 100 | 358.41 | 1723 | 0.61919 | 0.040454 | 0.61268 | 0.041023 | 0.61299 | 0.040526 | + + +done! total time: 0:05:58 diff --git a/input_space_v3/flat_lr1e-3_4/eval_v2/adhd200_dx__patch__logistic/config.yaml b/input_space_v3/flat_lr1e-3_4/eval_v2/adhd200_dx__patch__logistic/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..d358d5f951b31a7b890931d83b6d5514eea62aaf --- /dev/null +++ b/input_space_v3/flat_lr1e-3_4/eval_v2/adhd200_dx__patch__logistic/config.yaml @@ -0,0 +1,30 @@ +output_root: experiments/input_space_v3/output +name_prefix: eval_logistic +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_4; eval v2 (adhd200_dx patch logistic) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: input_space_v3/flat_lr1e-3_4/eval_v2/adhd200_dx__patch__logistic +model: flat_mae +representation: patch +dataset: adhd200_dx +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/eval_v2/adhd200_dx__patch__logistic +remote_dir: null diff --git a/input_space_v3/flat_lr1e-3_4/eval_v2/adhd200_dx__patch__logistic/eval_table.csv b/input_space_v3/flat_lr1e-3_4/eval_v2/adhd200_dx__patch__logistic/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..41660f6a12fe83bbaeab9ed70a1e3753cc5aaf2b --- /dev/null +++ b/input_space_v3/flat_lr1e-3_4/eval_v2/adhd200_dx__patch__logistic/eval_table.csv @@ -0,0 +1,203 @@ +model,repr,clf,dataset,trial,C,split,acc,acc_std,f1,f1_std,bacc,bacc_std +flat_mae,patch,logistic,adhd200_dx,,0.005994842503189409,train,0.7643835616438356,0.021343299964353257,0.7566666666666667,0.02234847886457943,0.7539537155767234,0.022167162828687255 +flat_mae,patch,logistic,adhd200_dx,,0.005994842503189409,test,0.5692307692307692,0.05897375607272648,0.545,0.06409840261214313,0.5477799227799228,0.06079038699127795 +flat_mae,patch,logistic,adhd200_dx,1,0.005994842503189409,train,0.7698630136986301,0.021359041868585883,0.7597178683385579,0.022898081120630815,0.7559382060206387,0.022481564411107716 +flat_mae,patch,logistic,adhd200_dx,1,0.005994842503189409,test,0.5692307692307692,0.05823466911033781,0.5512820512820513,0.06101740765976957,0.5521235521235521,0.059345337654677005 +flat_mae,patch,logistic,adhd200_dx,2,0.005994842503189409,train,0.736986301369863,0.02262726838430923,0.7272387594968239,0.023776896852722985,0.724659583562313,0.02340042052823318 +flat_mae,patch,logistic,adhd200_dx,2,0.005994842503189409,test,0.7076923076923077,0.05308237207258236,0.6834145091002307,0.06098463999828951,0.6824324324324325,0.05633519538357175 +flat_mae,patch,logistic,adhd200_dx,3,0.005994842503189409,train,0.7863013698630137,0.021573448231697736,0.7788497390007457,0.022735811408926544,0.7755236001709714,0.022623311453640185 +flat_mae,patch,logistic,adhd200_dx,3,0.005994842503189409,test,0.5538461538461539,0.05729690141048295,0.5321419707123356,0.06066492252765309,0.5342664092664092,0.05843324979509744 +flat_mae,patch,logistic,adhd200_dx,4,0.005994842503189409,train,0.7698630136986301,0.0206901990934126,0.7608125819134994,0.02186777103562122,0.7573731452647005,0.02150933526739855 +flat_mae,patch,logistic,adhd200_dx,4,0.005994842503189409,test,0.6307692307692307,0.056910468458081974,0.6264367816091954,0.057617826974017024,0.627895752895753,0.057765173254212016 +flat_mae,patch,logistic,adhd200_dx,5,0.005994842503189409,train,0.7835616438356164,0.022150507195938942,0.7762456448020858,0.023469299590233077,0.773096415704952,0.02335087641084025 +flat_mae,patch,logistic,adhd200_dx,5,0.005994842503189409,test,0.5692307692307692,0.060759656499919136,0.564176245210728,0.06182452978685377,0.5651544401544402,0.06229613399002149 +flat_mae,patch,logistic,adhd200_dx,6,0.005994842503189409,train,0.7643835616438356,0.02120217736493292,0.7556513887159049,0.02232918991588402,0.7525187763326616,0.022005605287739205 +flat_mae,patch,logistic,adhd200_dx,6,0.005994842503189409,test,0.6923076923076923,0.055543157696190684,0.6794871794871795,0.05916235256033133,0.6776061776061776,0.057807195213041195 +flat_mae,patch,logistic,adhd200_dx,7,0.005994842503189409,train,0.7561643835616438,0.023413669777399518,0.74891985685688,0.02446490637798243,0.7466721621786652,0.024344353824018554 +flat_mae,patch,logistic,adhd200_dx,7,0.005994842503189409,test,0.7384615384615385,0.05210250252368661,0.7292330311198236,0.05466814307189587,0.7268339768339769,0.054148122875282145 +flat_mae,patch,logistic,adhd200_dx,8,0.005994842503189409,train,0.7643835616438356,0.020901793440691704,0.757148604320109,0.02188824374700306,0.7546711851987543,0.02175506428656418 +flat_mae,patch,logistic,adhd200_dx,8,0.005994842503189409,test,0.6,0.06262762307159384,0.5833333333333333,0.06558189053927652,0.5834942084942085,0.06357056370155993 +flat_mae,patch,logistic,adhd200_dx,9,0.005994842503189409,train,0.7698630136986301,0.02262454738756999,0.7623255813953489,0.02366235576045211,0.7595255541307931,0.023479528171170355 +flat_mae,patch,logistic,adhd200_dx,9,0.005994842503189409,test,0.5846153846153846,0.06206647324112846,0.5699583435432491,0.0641473728132606,0.5699806949806949,0.0628752729087681 +flat_mae,patch,logistic,adhd200_dx,10,0.005994842503189409,train,0.7479452054794521,0.02311672892765119,0.7391561024111359,0.024230295848982772,0.7365207302924833,0.02389948883743276 +flat_mae,patch,logistic,adhd200_dx,10,0.005994842503189409,test,0.5846153846153846,0.057334199342113285,0.5644080416976918,0.06142299946985614,0.5656370656370656,0.05904952375618707 +flat_mae,patch,logistic,adhd200_dx,11,0.005994842503189409,train,0.7534246575342466,0.02171488529091503,0.7419400452488687,0.023442635068659196,0.7385052207363986,0.022898775162681826 +flat_mae,patch,logistic,adhd200_dx,11,0.005994842503189409,test,0.5846153846153846,0.05567250816768069,0.5501153550371699,0.062241879408880194,0.556949806949807,0.057205255400809916 +flat_mae,patch,logistic,adhd200_dx,12,0.005994842503189409,train,0.7506849315068493,0.021980236435715107,0.7422576414808837,0.022973758520549576,0.7396653843805336,0.022733824476368063 +flat_mae,patch,logistic,adhd200_dx,12,0.005994842503189409,test,0.5538461538461539,0.05696048666769025,0.5250692869740489,0.06324942661927546,0.5299227799227799,0.05889424510685927 +flat_mae,patch,logistic,adhd200_dx,13,0.005994842503189409,train,0.7616438356164383,0.022565698166047254,0.7550241080038573,0.0232974011053261,0.7529614703547658,0.023196420366544283 +flat_mae,patch,logistic,adhd200_dx,13,0.005994842503189409,test,0.6461538461538462,0.05838274852594546,0.6336682185738789,0.061543638302394336,0.6327220077220077,0.06048191849300948 +flat_mae,patch,logistic,adhd200_dx,14,0.046415888336127774,train,0.8164383561643835,0.018752872101288603,0.810615740848299,0.019540642269046435,0.8072449166514013,0.01948931729406962 +flat_mae,patch,logistic,adhd200_dx,14,0.046415888336127774,test,0.6461538461538462,0.05639484638000934,0.6375757575757576,0.05840845807223114,0.6370656370656371,0.057989912661457296 +flat_mae,patch,logistic,adhd200_dx,15,0.005994842503189409,train,0.7589041095890411,0.022925063496329785,0.7494227048617612,0.024466323262335173,0.746229468156561,0.024104810277716507 +flat_mae,patch,logistic,adhd200_dx,15,0.005994842503189409,test,0.6153846153846154,0.06083115831944356,0.6094688776736361,0.06154781990674974,0.61003861003861,0.06171520194557334 +flat_mae,patch,logistic,adhd200_dx,16,0.005994842503189409,train,0.7643835616438356,0.02096165010214347,0.7580620298433839,0.02175307860704154,0.7561061244428161,0.021719951277036516 +flat_mae,patch,logistic,adhd200_dx,16,0.005994842503189409,test,0.6,0.06253579519342001,0.5953065134099617,0.06313227976787619,0.5965250965250966,0.06339327491473806 +flat_mae,patch,logistic,adhd200_dx,17,0.005994842503189409,train,0.7835616438356164,0.02004904775810451,0.7762456448020858,0.021022219924501734,0.773096415704952,0.020916844331726248 +flat_mae,patch,logistic,adhd200_dx,17,0.005994842503189409,test,0.5538461538461539,0.059631777398796736,0.5167905665214048,0.06543089233523129,0.5255791505791506,0.06063748064592794 +flat_mae,patch,logistic,adhd200_dx,18,0.005994842503189409,train,0.7561643835616438,0.021837081472311563,0.7473969875817451,0.023062706191282027,0.7445197533125725,0.022779108227639712 +flat_mae,patch,logistic,adhd200_dx,18,0.005994842503189409,test,0.6307692307692307,0.05924028694759283,0.6235521235521235,0.06008567840419021,0.6235521235521235,0.05967511019774278 +flat_mae,patch,logistic,adhd200_dx,19,0.005994842503189409,train,0.7479452054794521,0.023115139121276863,0.7374429223744292,0.024595470777586895,0.7343683214263906,0.024155077206467628 +flat_mae,patch,logistic,adhd200_dx,19,0.005994842503189409,test,0.7692307692307693,0.054894196242090014,0.7580044676098288,0.05933688466919537,0.7538610038610039,0.05798112713891719 +flat_mae,patch,logistic,adhd200_dx,20,0.005994842503189409,train,0.7643835616438356,0.020316197421038,0.7566666666666667,0.021375215930115897,0.7539537155767234,0.02127244268228809 +flat_mae,patch,logistic,adhd200_dx,20,0.005994842503189409,test,0.676923076923077,0.05565311838341871,0.6612062546537603,0.06021123053146866,0.6597490347490347,0.05808298357542373 +flat_mae,patch,logistic,adhd200_dx,21,0.046415888336127774,train,0.8301369863013699,0.019279932289264567,0.8242138951031568,0.02032283121440479,0.8200983086035294,0.0202891276577036 +flat_mae,patch,logistic,adhd200_dx,21,0.046415888336127774,test,0.7076923076923077,0.05768392964808284,0.7074153044302298,0.057791113500653,0.7171814671814671,0.05722536227865714 +flat_mae,patch,logistic,adhd200_dx,22,0.005994842503189409,train,0.7506849315068493,0.022284375740397985,0.74059090447591,0.023783289636856896,0.737512975514441,0.02342019550818163 +flat_mae,patch,logistic,adhd200_dx,22,0.005994842503189409,test,0.6923076923076923,0.05736700905407786,0.6862934362934363,0.05892624371385294,0.6862934362934363,0.058918894716479445 +flat_mae,patch,logistic,adhd200_dx,23,0.005994842503189409,train,0.7534246575342466,0.021052419184911957,0.7442863370282725,0.0223861987258902,0.7413750992245222,0.022066456330060318 +flat_mae,patch,logistic,adhd200_dx,23,0.005994842503189409,test,0.6615384615384615,0.052113767218728395,0.6366869918699187,0.0582879703838755,0.6375482625482626,0.054471985443560016 +flat_mae,patch,logistic,adhd200_dx,24,0.046415888336127774,train,0.8273972602739726,0.019499006427045433,0.8226036644165864,0.02020420962582218,0.8198235330036027,0.02025035549512066 +flat_mae,patch,logistic,adhd200_dx,24,0.046415888336127774,test,0.6307692307692307,0.06301919309404756,0.6153846153846154,0.06621388076842159,0.6148648648648649,0.06441334475767777 +flat_mae,patch,logistic,adhd200_dx,25,0.005994842503189409,train,0.7589041095890411,0.02035666217426343,0.7457573454913881,0.022250659764167655,0.7419246504243756,0.021555831806406966 +flat_mae,patch,logistic,adhd200_dx,25,0.005994842503189409,test,0.6307692307692307,0.062220976694587524,0.6235521235521235,0.0637627926279106,0.6235521235521235,0.06349457923724686 +flat_mae,patch,logistic,adhd200_dx,26,0.005994842503189409,train,0.7643835616438356,0.021306755430717854,0.7539968652037617,0.022820485560427345,0.7503663674665689,0.022392116675688755 +flat_mae,patch,logistic,adhd200_dx,26,0.005994842503189409,test,0.6153846153846154,0.05749569780663758,0.6018132810585641,0.06018816616100299,0.6013513513513513,0.05884401611884117 +flat_mae,patch,logistic,adhd200_dx,27,0.005994842503189409,train,0.7506849315068493,0.022307389716284886,0.7427766032417196,0.0233331115390733,0.7403828540025645,0.023156703225099447 +flat_mae,patch,logistic,adhd200_dx,27,0.005994842503189409,test,0.6923076923076923,0.05395554602397758,0.6832358674463938,0.056122007249314064,0.6819498069498069,0.05531608713920772 +flat_mae,patch,logistic,adhd200_dx,28,0.000774263682681127,train,0.6794520547945205,0.023309315324500177,0.6664740200404558,0.024594911897674262,0.6650790743115345,0.024010721811186752 +flat_mae,patch,logistic,adhd200_dx,28,0.000774263682681127,test,0.5846153846153846,0.056078356001529855,0.5501153550371699,0.0627863767871707,0.556949806949807,0.05780843305862313 +flat_mae,patch,logistic,adhd200_dx,29,0.000774263682681127,train,0.6821917808219178,0.024590087969472707,0.6657298048379966,0.02627307900637128,0.6646363802894303,0.025290188963404413 +flat_mae,patch,logistic,adhd200_dx,29,0.000774263682681127,test,0.6307692307692307,0.059968236168095074,0.6153846153846154,0.06372240903198029,0.6148648648648649,0.06187803028717662 +flat_mae,patch,logistic,adhd200_dx,30,0.005994842503189409,train,0.7506849315068493,0.021588876989849827,0.7427766032417196,0.022637790693832892,0.7403828540025645,0.02243596767236567 +flat_mae,patch,logistic,adhd200_dx,30,0.005994842503189409,test,0.6,0.06023194615217166,0.5833333333333333,0.06281258200440287,0.5834942084942085,0.06146055346751933 +flat_mae,patch,logistic,adhd200_dx,31,0.000774263682681127,train,0.6958904109589041,0.02225850547242595,0.6780154018548983,0.023950424912052782,0.6767723026195274,0.022874606583255866 +flat_mae,patch,logistic,adhd200_dx,31,0.000774263682681127,test,0.6,0.05707303324916554,0.5626293995859213,0.06461236731735141,0.5704633204633205,0.0589357876725277 +flat_mae,patch,logistic,adhd200_dx,32,0.046415888336127774,train,0.8246575342465754,0.019495813408951096,0.8196194712132444,0.02023888484274509,0.8166788789155524,0.02023023373275867 +flat_mae,patch,logistic,adhd200_dx,32,0.046415888336127774,test,0.5692307692307692,0.06453570911890014,0.564176245210728,0.06492092289557823,0.5651544401544402,0.06491054591470921 +flat_mae,patch,logistic,adhd200_dx,33,0.005994842503189409,train,0.7589041095890411,0.021811316638295025,0.7510077519379845,0.02298912379973626,0.7483818770226537,0.022872961012510937 +flat_mae,patch,logistic,adhd200_dx,33,0.005994842503189409,test,0.5538461538461539,0.05918799654415785,0.5469838981014179,0.060370661165122214,0.5472972972972974,0.06033964536711476 +flat_mae,patch,logistic,adhd200_dx,34,0.005994842503189409,train,0.7561643835616438,0.021410890717601484,0.7498479143083758,0.02224676867906032,0.748107101422727,0.022240364970293577 +flat_mae,patch,logistic,adhd200_dx,34,0.005994842503189409,test,0.676923076923077,0.0591098946452319,0.6655231560891939,0.06233025036140078,0.6640926640926641,0.0611789897695685 +flat_mae,patch,logistic,adhd200_dx,35,0.005994842503189409,train,0.7506849315068493,0.021123230104926623,0.7393859504586148,0.022499527500273123,0.7360780362703792,0.021956632536671836 +flat_mae,patch,logistic,adhd200_dx,35,0.005994842503189409,test,0.6307692307692307,0.05732540562593094,0.6153846153846154,0.06013106124668067,0.6148648648648649,0.058629372106941746 +flat_mae,patch,logistic,adhd200_dx,36,0.000774263682681127,train,0.6876712328767123,0.02298988722499802,0.6767803877703207,0.024167181579601633,0.6752305061977163,0.023832808428055945 +flat_mae,patch,logistic,adhd200_dx,36,0.000774263682681127,test,0.6153846153846154,0.05788358854187607,0.6018132810585641,0.06079418397993015,0.6013513513513513,0.059353186285667485 +flat_mae,patch,logistic,adhd200_dx,37,0.005994842503189409,train,0.7534246575342466,0.021575563556162268,0.7425548589341693,0.023028269491866156,0.7392226903584295,0.022556403393365582 +flat_mae,patch,logistic,adhd200_dx,37,0.005994842503189409,test,0.6615384615384615,0.04991876003618575,0.6299171842650104,0.05898935687215366,0.6332046332046332,0.05287040436049961 +flat_mae,patch,logistic,adhd200_dx,38,0.005994842503189409,train,0.7534246575342466,0.023272775252001925,0.7442863370282725,0.024607059612197606,0.7413750992245222,0.02429931523101714 +flat_mae,patch,logistic,adhd200_dx,38,0.005994842503189409,test,0.6615384615384615,0.05569379513525764,0.6474358974358974,0.058383078261371374,0.6462355212355213,0.05677072664304426 +flat_mae,patch,logistic,adhd200_dx,39,0.005994842503189409,train,0.7589041095890411,0.020998441354376566,0.7494227048617612,0.022212162071346176,0.746229468156561,0.021867291224061745 +flat_mae,patch,logistic,adhd200_dx,39,0.005994842503189409,test,0.6461538461538462,0.057099692742103296,0.6167649320687003,0.06335848314966813,0.6196911196911197,0.05871068535172852 +flat_mae,patch,logistic,adhd200_dx,40,0.005994842503189409,train,0.7671232876712328,0.021412952693784234,0.7597363876433645,0.022394518293443876,0.7570983696647737,0.022262288011244805 +flat_mae,patch,logistic,adhd200_dx,40,0.005994842503189409,test,0.7076923076923077,0.05405420028126711,0.6934723256391164,0.05846954231563569,0.6911196911196911,0.05657352692565806 +flat_mae,patch,logistic,adhd200_dx,41,0.005994842503189409,train,0.7643835616438356,0.021411462846504605,0.7551176433876303,0.02274694501479822,0.7518013067106307,0.02245265408536949 +flat_mae,patch,logistic,adhd200_dx,41,0.005994842503189409,test,0.6,0.0610177973843135,0.5921814671814671,0.06212907679964382,0.5921814671814671,0.06178787670559743 +flat_mae,patch,logistic,adhd200_dx,42,0.005994842503189409,train,0.7616438356164383,0.02211881188025665,0.7508415130758186,0.02357822169674124,0.7472217133785186,0.023079782341765314 +flat_mae,patch,logistic,adhd200_dx,42,0.005994842503189409,test,0.5846153846153846,0.06329238248378215,0.5830363506771205,0.06307294659546958,0.5873552123552124,0.06267798276913743 +flat_mae,patch,logistic,adhd200_dx,43,0.005994842503189409,train,0.7506849315068493,0.022009806920451368,0.74059090447591,0.023501222453520834,0.737512975514441,0.02308506023859063 +flat_mae,patch,logistic,adhd200_dx,43,0.005994842503189409,test,0.6153846153846154,0.05941170366640212,0.5966741126830479,0.062283073806634136,0.597007722007722,0.060372186972537704 +flat_mae,patch,logistic,adhd200_dx,44,0.005994842503189409,train,0.7534246575342466,0.02148141660012341,0.7431506849315068,0.023001352762979578,0.7399401599804604,0.02257752319694389 +flat_mae,patch,logistic,adhd200_dx,44,0.005994842503189409,test,0.676923076923077,0.05752993766562459,0.6690909090909091,0.0593653714613639,0.6684362934362934,0.05895380477747002 +flat_mae,patch,logistic,adhd200_dx,45,0.005994842503189409,train,0.7863013698630137,0.02168504071485754,0.7788497390007457,0.022840319707149805,0.7755236001709714,0.02273536504663095 +flat_mae,patch,logistic,adhd200_dx,45,0.005994842503189409,test,0.5846153846153846,0.059451210168780785,0.5644080416976918,0.06303352315569263,0.5656370656370656,0.060779112778003304 +flat_mae,patch,logistic,adhd200_dx,46,0.005994842503189409,train,0.7506849315068493,0.021791543152661116,0.7411650107149814,0.02304578593378026,0.7382304451364718,0.022743050430856917 +flat_mae,patch,logistic,adhd200_dx,46,0.005994842503189409,test,0.6153846153846154,0.060790305985207446,0.5966741126830479,0.06385913991367025,0.597007722007722,0.06168084991290848 +flat_mae,patch,logistic,adhd200_dx,47,0.005994842503189409,train,0.7698630136986301,0.020876625318914065,0.7623255813953489,0.021857370361163465,0.7595255541307931,0.02167007521662772 +flat_mae,patch,logistic,adhd200_dx,47,0.005994842503189409,test,0.6,0.056976066811856296,0.5833333333333333,0.06007159584324916,0.5834942084942085,0.05818985881978718 +flat_mae,patch,logistic,adhd200_dx,48,0.005994842503189409,train,0.7205479452054795,0.022471141351906154,0.7095581351806777,0.023790810636931278,0.7072265982780729,0.023325010607896164 +flat_mae,patch,logistic,adhd200_dx,48,0.005994842503189409,test,0.7230769230769231,0.054284248589903265,0.7176640926640927,0.05511855840158738,0.7176640926640927,0.054803202913940814 +flat_mae,patch,logistic,adhd200_dx,49,0.005994842503189409,train,0.7643835616438356,0.021271497531753263,0.7539968652037617,0.022877678229589613,0.7503663674665689,0.02240554625117869 +flat_mae,patch,logistic,adhd200_dx,49,0.005994842503189409,test,0.5846153846153846,0.058470760406250974,0.5699583435432491,0.061317764340931766,0.5699806949806949,0.05979410288568595 +flat_mae,patch,logistic,adhd200_dx,50,0.046415888336127774,train,0.8246575342465754,0.020076116369691567,0.8202745122176403,0.020694785413342444,0.8181138181596141,0.02078924909344989 +flat_mae,patch,logistic,adhd200_dx,50,0.046415888336127774,test,0.6461538461538462,0.060411997711180034,0.6407113674597452,0.061238374104680054,0.6414092664092663,0.06117699854468939 +flat_mae,patch,logistic,adhd200_dx,51,0.005994842503189409,train,0.7452054794520548,0.02160337400585508,0.738129218900675,0.022487365874479137,0.7362459546925566,0.022417936218536723 +flat_mae,patch,logistic,adhd200_dx,51,0.005994842503189409,test,0.6461538461538462,0.06133631413732539,0.6407113674597452,0.06231654147769663,0.6414092664092663,0.06229662167030346 +flat_mae,patch,logistic,adhd200_dx,52,0.005994842503189409,train,0.7643835616438356,0.021574830870211965,0.7539968652037617,0.023115468382300445,0.7503663674665689,0.022679265082462083 +flat_mae,patch,logistic,adhd200_dx,52,0.005994842503189409,test,0.7076923076923077,0.05431096089531818,0.6888384983623079,0.060273320210553726,0.6867760617760618,0.057272799947293625 +flat_mae,patch,logistic,adhd200_dx,53,0.005994842503189409,train,0.7589041095890411,0.02145073492676836,0.7504971414367387,0.022561380253550225,0.7476644074006228,0.022353193661703602 +flat_mae,patch,logistic,adhd200_dx,53,0.005994842503189409,test,0.6,0.055441432395235815,0.5626293995859213,0.062368743041143294,0.5704633204633205,0.057010853111860646 +flat_mae,patch,logistic,adhd200_dx,54,0.000774263682681127,train,0.6986301369863014,0.023070382898551053,0.6916282642089093,0.023800200820136935,0.6906790010380411,0.02371672658749391 +flat_mae,patch,logistic,adhd200_dx,54,0.000774263682681127,test,0.5384615384615384,0.06265543228855956,0.5248538011695907,0.06503639175259468,0.525096525096525,0.06401778324357316 +flat_mae,patch,logistic,adhd200_dx,55,0.005994842503189409,train,0.7698630136986301,0.022191104336044615,0.7618381804623415,0.02336523600705216,0.7588080845087622,0.023204601026764374 +flat_mae,patch,logistic,adhd200_dx,55,0.005994842503189409,test,0.5538461538461539,0.06081310198288741,0.5521501544309813,0.061121650181704276,0.555984555984556,0.061705274741522625 +flat_mae,patch,logistic,adhd200_dx,56,0.005994842503189409,train,0.7452054794520548,0.021775755420038637,0.7336581691500129,0.02325441710136125,0.7305061977163094,0.02268481515454884 +flat_mae,patch,logistic,adhd200_dx,56,0.005994842503189409,test,0.6923076923076923,0.05829121748173526,0.6862934362934363,0.059884184058497186,0.6862934362934363,0.05966351983052461 +flat_mae,patch,logistic,adhd200_dx,57,0.005994842503189409,train,0.7534246575342466,0.022218339595347327,0.7442863370282725,0.023365175971876186,0.7413750992245222,0.023006281285453 +flat_mae,patch,logistic,adhd200_dx,57,0.005994842503189409,test,0.5692307692307692,0.0594847700661479,0.5512820512820513,0.06286142482319798,0.5521235521235521,0.06083633882266286 +flat_mae,patch,logistic,adhd200_dx,58,0.005994842503189409,train,0.7835616438356164,0.020342353396673247,0.7762456448020858,0.02134619936368094,0.773096415704952,0.021218217961893427 +flat_mae,patch,logistic,adhd200_dx,58,0.005994842503189409,test,0.6153846153846154,0.05773242502622148,0.606060606060606,0.05915160127975713,0.6056949806949807,0.0585478230467917 +flat_mae,patch,logistic,adhd200_dx,59,0.005994842503189409,train,0.7643835616438356,0.022767040864958038,0.7551176433876303,0.024043108367083385,0.7518013067106307,0.023678152453624014 +flat_mae,patch,logistic,adhd200_dx,59,0.005994842503189409,test,0.6,0.05971351724703406,0.5833333333333333,0.06281910597882166,0.5834942084942085,0.06110696631020378 +flat_mae,patch,logistic,adhd200_dx,60,0.005994842503189409,train,0.7753424657534247,0.021609444499440612,0.7688874474919694,0.02238623297457452,0.7665323319289247,0.022278984738486787 +flat_mae,patch,logistic,adhd200_dx,60,0.005994842503189409,test,0.676923076923077,0.05642526606838088,0.6655231560891939,0.05949259860813072,0.6640926640926641,0.05831950620125641 +flat_mae,patch,logistic,adhd200_dx,61,0.005994842503189409,train,0.7589041095890411,0.021782334056237217,0.7494227048617612,0.02295733371303302,0.746229468156561,0.022613150894324526 +flat_mae,patch,logistic,adhd200_dx,61,0.005994842503189409,test,0.5692307692307692,0.06190104720415006,0.5512820512820513,0.06528209149796527,0.5521235521235521,0.06332149956628073 +flat_mae,patch,logistic,adhd200_dx,62,0.005994842503189409,train,0.7671232876712328,0.021364183298607824,0.7582310539645432,0.02255322721755022,0.754945960798681,0.022232089228443247 +flat_mae,patch,logistic,adhd200_dx,62,0.005994842503189409,test,0.6,0.05722775839888321,0.5921814671814671,0.05886317861610063,0.5921814671814671,0.05869520254608574 +flat_mae,patch,logistic,adhd200_dx,63,0.005994842503189409,train,0.7452054794520548,0.02337856620610545,0.7371233417745046,0.024478492696358038,0.7348110154484948,0.024301784342296726 +flat_mae,patch,logistic,adhd200_dx,63,0.005994842503189409,test,0.6307692307692307,0.05770411366382652,0.6198830409356726,0.059795477520609014,0.6192084942084942,0.05892124357184523 +flat_mae,patch,logistic,adhd200_dx,64,0.005994842503189409,train,0.7561643835616438,0.02054303429899769,0.7457122952038764,0.021942473511392457,0.7423673444464798,0.021561933448586205 +flat_mae,patch,logistic,adhd200_dx,64,0.005994842503189409,test,0.676923076923077,0.05748347022503449,0.6690909090909091,0.05907753597271104,0.6684362934362934,0.05851374340106606 +flat_mae,patch,logistic,adhd200_dx,65,0.005994842503189409,train,0.7452054794520548,0.02201954197834302,0.734283634314163,0.02354717973243848,0.7312236673383403,0.023110931745339864 +flat_mae,patch,logistic,adhd200_dx,65,0.005994842503189409,test,0.6923076923076923,0.05648455619687028,0.6832358674463938,0.059097216457051606,0.6819498069498069,0.05849397348061152 +flat_mae,patch,logistic,adhd200_dx,66,0.005994842503189409,train,0.7589041095890411,0.022304987758102385,0.7499688628720886,0.023443072054297118,0.7469469377785919,0.023070895661159697 +flat_mae,patch,logistic,adhd200_dx,66,0.005994842503189409,test,0.6461538461538462,0.05548417547202671,0.6233308138070043,0.0607298654303357,0.6240347490347491,0.05743654736888971 +flat_mae,patch,logistic,adhd200_dx,67,0.005994842503189409,train,0.7534246575342466,0.021972463361700535,0.7458531905675558,0.0230091102669953,0.7435275080906149,0.02287395509793228 +flat_mae,patch,logistic,adhd200_dx,67,0.005994842503189409,test,0.676923076923077,0.05837320451985791,0.6612062546537603,0.06269135347590363,0.6597490347490347,0.06031664859574043 +flat_mae,patch,logistic,adhd200_dx,68,0.005994842503189409,train,0.7561643835616438,0.022187488845908092,0.743203611038648,0.02422794229788709,0.7394974659583562,0.023474253197195948 +flat_mae,patch,logistic,adhd200_dx,68,0.005994842503189409,test,0.7230769230769231,0.052827274648097854,0.7115384615384616,0.0559675669661284,0.708976833976834,0.05472850109786505 +flat_mae,patch,logistic,adhd200_dx,69,0.005994842503189409,train,0.7589041095890411,0.021533616359421165,0.751976772918211,0.022477491786791662,0.7498168162667155,0.022373182291522374 +flat_mae,patch,logistic,adhd200_dx,69,0.005994842503189409,test,0.5846153846153846,0.054596746548927357,0.5411764705882354,0.06398892345140886,0.5526061776061776,0.056728363265298856 +flat_mae,patch,logistic,adhd200_dx,70,0.005994842503189409,train,0.7452054794520548,0.022084367138508306,0.7354763296317943,0.023397441259272626,0.7326586065824021,0.023051544780376593 +flat_mae,patch,logistic,adhd200_dx,70,0.005994842503189409,test,0.5384615384615384,0.06076183791448018,0.5357142857142857,0.06110414190727916,0.5381274131274132,0.06155035668518762 +flat_mae,patch,logistic,adhd200_dx,71,0.005994842503189409,train,0.7643835616438356,0.02110417485438559,0.754566210045662,0.022442929797115253,0.7510838370885998,0.0220495794788056 +flat_mae,patch,logistic,adhd200_dx,71,0.005994842503189409,test,0.6923076923076923,0.05893399376677077,0.6832358674463938,0.061669390799744664,0.6819498069498069,0.060794802391271184 +flat_mae,patch,logistic,adhd200_dx,72,0.005994842503189409,train,0.7589041095890411,0.022194148360095096,0.7504971414367387,0.023168973374287444,0.7476644074006228,0.02284959740707894 +flat_mae,patch,logistic,adhd200_dx,72,0.005994842503189409,test,0.676923076923077,0.0554907018172025,0.6612062546537603,0.0596615062354922,0.6597490347490347,0.057537275342234295 +flat_mae,patch,logistic,adhd200_dx,73,0.005994842503189409,train,0.7698630136986301,0.021997675716112382,0.7623255813953489,0.02293637785822132,0.7595255541307931,0.022748728013882693 +flat_mae,patch,logistic,adhd200_dx,73,0.005994842503189409,test,0.6153846153846154,0.06350113263677938,0.61207925519217,0.063971113688209,0.6143822393822393,0.06414738052600293 +flat_mae,patch,logistic,adhd200_dx,74,0.005994842503189409,train,0.7534246575342466,0.020594439453061438,0.7431506849315068,0.02181576849736158,0.7399401599804604,0.02139911634453675 +flat_mae,patch,logistic,adhd200_dx,74,0.005994842503189409,test,0.6307692307692307,0.05948203249174588,0.6153846153846154,0.06224411046113453,0.6148648648648649,0.060478736771852795 +flat_mae,patch,logistic,adhd200_dx,75,0.046415888336127774,train,0.8301369863013699,0.018782496253413085,0.8242138951031568,0.01975811719947009,0.8200983086035294,0.0197859143738032 +flat_mae,patch,logistic,adhd200_dx,75,0.046415888336127774,test,0.49230769230769234,0.06361821033627503,0.4879446168536643,0.06367751120056546,0.4888996138996139,0.0640084391223475 +flat_mae,patch,logistic,adhd200_dx,76,0.046415888336127774,train,0.8082191780821918,0.020745853133049323,0.802708796639486,0.021607036552174257,0.799963363253343,0.02164198495685616 +flat_mae,patch,logistic,adhd200_dx,76,0.046415888336127774,test,0.5692307692307692,0.05876732981218764,0.5512820512820513,0.06171207680861565,0.5521235521235521,0.05981431028061214 +flat_mae,patch,logistic,adhd200_dx,77,0.005994842503189409,train,0.7397260273972602,0.021151686398322073,0.7285693038693062,0.022709111062121295,0.7256518287842706,0.022230320717808675 +flat_mae,patch,logistic,adhd200_dx,77,0.005994842503189409,test,0.7076923076923077,0.05280846265335369,0.6834145091002307,0.061239571855799466,0.6824324324324325,0.05604652490834303 +flat_mae,patch,logistic,adhd200_dx,78,0.005994842503189409,train,0.7780821917808219,0.02143809549493589,0.7696084161309176,0.02269569545856624,0.7660896379068205,0.0224508969617468 +flat_mae,patch,logistic,adhd200_dx,78,0.005994842503189409,test,0.6307692307692307,0.058283607771921965,0.6153846153846154,0.0618961648645442,0.6148648648648649,0.060080556947396675 +flat_mae,patch,logistic,adhd200_dx,79,0.005994842503189409,train,0.7726027397260274,0.021105121623766772,0.7658466080800117,0.022023879220638632,0.7633876778408744,0.021921833942351122 +flat_mae,patch,logistic,adhd200_dx,79,0.005994842503189409,test,0.6,0.05823278321890615,0.5833333333333333,0.06182649278149465,0.5834942084942085,0.059841954182076565 +flat_mae,patch,logistic,adhd200_dx,80,0.005994842503189409,train,0.7616438356164383,0.02171541069696039,0.7530734597709193,0.022816392620260622,0.7500915918666422,0.022535264837603527 +flat_mae,patch,logistic,adhd200_dx,80,0.005994842503189409,test,0.6,0.05977136715318587,0.570630081300813,0.06686351306486094,0.5748069498069498,0.06191794814552674 +flat_mae,patch,logistic,adhd200_dx,81,0.005994842503189409,train,0.7643835616438356,0.02193216721431006,0.7576136644427971,0.02276359676419541,0.7553886548207852,0.022676768508544415 +flat_mae,patch,logistic,adhd200_dx,81,0.005994842503189409,test,0.6153846153846154,0.0545934603882165,0.5905769715293525,0.05974953508299354,0.5926640926640927,0.056106886145996425 +flat_mae,patch,logistic,adhd200_dx,82,0.005994842503189409,train,0.7643835616438356,0.02153483494612572,0.7556513887159049,0.02279898305425189,0.7525187763326616,0.022500024598790556 +flat_mae,patch,logistic,adhd200_dx,82,0.005994842503189409,test,0.6923076923076923,0.05525711820594732,0.6886973180076628,0.05575221341943116,0.6906370656370657,0.05577227770989988 +flat_mae,patch,logistic,adhd200_dx,83,0.005994842503189409,train,0.736986301369863,0.021632804541107352,0.7278150633855331,0.022531870318590056,0.7253770531843439,0.022170933367881406 +flat_mae,patch,logistic,adhd200_dx,83,0.005994842503189409,test,0.7230769230769231,0.0565083520035211,0.7115384615384616,0.06019050932663844,0.708976833976834,0.05889830508575462 +flat_mae,patch,logistic,adhd200_dx,84,0.005994842503189409,train,0.7479452054794521,0.020986576056001256,0.7380328278100231,0.022201296716061233,0.7350857910484215,0.021811987273288386 +flat_mae,patch,logistic,adhd200_dx,84,0.005994842503189409,test,0.6307692307692307,0.06082144592184297,0.6285714285714286,0.06105000547784311,0.6322393822393823,0.06131632445911314 +flat_mae,patch,logistic,adhd200_dx,85,0.046415888336127774,train,0.821917808219178,0.020284807175303347,0.8166268617494068,0.02108066194532579,0.8135342248275019,0.021076136025532224 +flat_mae,patch,logistic,adhd200_dx,85,0.046415888336127774,test,0.5692307692307692,0.05930796966911099,0.5512820512820513,0.06187423988816779,0.5521235521235521,0.06014734002958052 +flat_mae,patch,logistic,adhd200_dx,86,0.005994842503189409,train,0.7671232876712328,0.021460589984889297,0.7565692943844204,0.023093711708414778,0.7527935519325883,0.02265482599813898 +flat_mae,patch,logistic,adhd200_dx,86,0.005994842503189409,test,0.5384615384615384,0.06079254859353275,0.5125,0.06401946542785866,0.5164092664092664,0.061436579274149625 +flat_mae,patch,logistic,adhd200_dx,87,0.005994842503189409,train,0.7534246575342466,0.02235507921083707,0.7425548589341693,0.02392474374909082,0.7392226903584295,0.023437390586783548 +flat_mae,patch,logistic,adhd200_dx,87,0.005994842503189409,test,0.6307692307692307,0.06030426991859036,0.6153846153846154,0.06354323326076174,0.6148648648648649,0.06184709112603137 +flat_mae,patch,logistic,adhd200_dx,88,0.000774263682681127,train,0.6904109589041096,0.023958437145445075,0.680590727102355,0.024881173608311522,0.6790926299077975,0.02460106108333037 +flat_mae,patch,logistic,adhd200_dx,88,0.000774263682681127,test,0.6307692307692307,0.06094808344599234,0.6235521235521235,0.062423165694250556,0.6235521235521235,0.062189370858899695 +flat_mae,patch,logistic,adhd200_dx,89,0.005994842503189409,train,0.7643835616438356,0.020866858494968818,0.7556513887159049,0.02200516090178222,0.7525187763326616,0.021699750837943867 +flat_mae,patch,logistic,adhd200_dx,89,0.005994842503189409,test,0.6153846153846154,0.05851702629888079,0.6018132810585641,0.06130873329648783,0.6013513513513513,0.059986090101061075 +flat_mae,patch,logistic,adhd200_dx,90,0.005994842503189409,train,0.7424657534246575,0.02253665723875418,0.7329212853406402,0.02357582464977944,0.7302314221163827,0.023181675125616204 +flat_mae,patch,logistic,adhd200_dx,90,0.005994842503189409,test,0.6461538461538462,0.05883517041792698,0.6336682185738789,0.06157986287112086,0.6327220077220077,0.06021029717175913 +flat_mae,patch,logistic,adhd200_dx,91,0.005994842503189409,train,0.7616438356164383,0.02054546103705135,0.7530734597709193,0.021545268402090385,0.7500915918666422,0.021312672336296634 +flat_mae,patch,logistic,adhd200_dx,91,0.005994842503189409,test,0.6307692307692307,0.04985409243526933,0.5962732919254659,0.05714740416761842,0.6018339768339769,0.051746730640877196 +flat_mae,patch,logistic,adhd200_dx,92,0.005994842503189409,train,0.7643835616438356,0.020115523740757636,0.754566210045662,0.021383507267107266,0.7510838370885998,0.02106637578582802 +flat_mae,patch,logistic,adhd200_dx,92,0.005994842503189409,test,0.6153846153846154,0.056692013359010494,0.5834401435529352,0.06300169814337812,0.5883204633204633,0.058287362817184545 +flat_mae,patch,logistic,adhd200_dx,93,0.005994842503189409,train,0.7616438356164383,0.021954109663831607,0.7530734597709193,0.023053858699703476,0.7500915918666422,0.022809919074381423 +flat_mae,patch,logistic,adhd200_dx,93,0.005994842503189409,test,0.6153846153846154,0.05282097485483759,0.5751633986928104,0.06195081087998022,0.583976833976834,0.05495307212854429 +flat_mae,patch,logistic,adhd200_dx,94,0.005994842503189409,train,0.7506849315068493,0.020947769627218987,0.7417205153925708,0.022142674028111847,0.7389479147585027,0.02187472184862625 +flat_mae,patch,logistic,adhd200_dx,94,0.005994842503189409,test,0.676923076923077,0.05458451131721933,0.6500897205844656,0.06234467331848489,0.6510617760617761,0.05746096559314624 +flat_mae,patch,logistic,adhd200_dx,95,0.005994842503189409,train,0.7698630136986301,0.022976679946303185,0.7627963111963855,0.02396725598750461,0.760243023752824,0.023809406951266734 +flat_mae,patch,logistic,adhd200_dx,95,0.005994842503189409,test,0.5692307692307692,0.05976499143464702,0.5512820512820513,0.0634432060720491,0.5521235521235521,0.06125580405415924 +flat_mae,patch,logistic,adhd200_dx,96,0.005994842503189409,train,0.7616438356164383,0.021965577396341373,0.7540831261761494,0.022951256416457844,0.751526531110704,0.022791602070857273 +flat_mae,patch,logistic,adhd200_dx,96,0.005994842503189409,test,0.6615384615384615,0.05941470740162996,0.6575670498084292,0.060211233195574185,0.6592664092664093,0.060522043578688615 +flat_mae,patch,logistic,adhd200_dx,97,0.046415888336127774,train,0.8547945205479452,0.0189937126020351,0.8515451733955445,0.019558617825587057,0.849835134640044,0.019715549498771183 +flat_mae,patch,logistic,adhd200_dx,97,0.046415888336127774,test,0.6,0.05457329689259951,0.5533826638477801,0.06387625718521175,0.5661196911196912,0.05642727206461918 +flat_mae,patch,logistic,adhd200_dx,98,0.005994842503189409,train,0.7561643835616438,0.02195315232441107,0.7457122952038764,0.023159238735079,0.7423673444464798,0.022683237649038096 +flat_mae,patch,logistic,adhd200_dx,98,0.005994842503189409,test,0.6923076923076923,0.055047271777786726,0.675,0.059884941248904984,0.6732625482625483,0.057118539416352976 +flat_mae,patch,logistic,adhd200_dx,99,0.005994842503189409,train,0.7616438356164383,0.02271482115313183,0.7545621072645906,0.023623469238996626,0.7522440007327349,0.02349939049839262 +flat_mae,patch,logistic,adhd200_dx,99,0.005994842503189409,test,0.6307692307692307,0.056184783890555305,0.6198830409356726,0.058110150039346165,0.6192084942084942,0.05732455078922899 +flat_mae,patch,logistic,adhd200_dx,100,0.005994842503189409,train,0.7534246575342466,0.021751011908569345,0.7431506849315068,0.023265169161102876,0.7399401599804604,0.022835428263285096 +flat_mae,patch,logistic,adhd200_dx,100,0.005994842503189409,test,0.6615384615384615,0.05400504030827331,0.6425000000000001,0.0583921459321074,0.6418918918918919,0.05595758716693383 diff --git a/input_space_v3/flat_lr1e-3_4/eval_v2/adhd200_dx__patch__logistic/log.txt b/input_space_v3/flat_lr1e-3_4/eval_v2/adhd200_dx__patch__logistic/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..d71b89652081f57947333bddd180280736affa03 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_4/eval_v2/adhd200_dx__patch__logistic/log.txt @@ -0,0 +1,241 @@ +fMRI foundation model logistic probe eval +version: 0.1.dev86+gf97f52698 +sha: bcce2b486277d3a5b520775efd9cdf1a2affce36, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-04-08 22:21:20 +config: +output_root: experiments/input_space_v3/output +name_prefix: eval_logistic +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_4; eval v2 (adhd200_dx patch logistic) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: input_space_v3/flat_lr1e-3_4/eval_v2/adhd200_dx__patch__logistic +model: flat_mae +representation: patch +dataset: adhd200_dx +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/eval_v2/adhd200_dx__patch__logistic +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=True, reg_tokens=0, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: adhd200_dx (flat) +train (n=301): +HFDataset( + dataset=Dataset({ + features: ['sub', 'site', 'gender', 'dx', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 301 +}), + labels=['ADHD' 'Control'], + counts=[131 170] +) + +validation (n=64): +HFDataset( + dataset=Dataset({ + features: ['sub', 'site', 'gender', 'dx', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 64 +}), + labels=['ADHD' 'Control'], + counts=[28 36] +) + +test (n=65): +HFDataset( + dataset=Dataset({ + features: ['sub', 'site', 'gender', 'dx', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 65 +}), + labels=['ADHD' 'Control'], + counts=[28 37] +) + +extracting features for all splits +extract (train) [ 0/151] eta: 0:12:35 time: 5.0008 data: 3.8577 max mem: 2698 +extract (train) [ 20/151] eta: 0:00:58 time: 0.2173 data: 0.0764 max mem: 2851 +extract (train) [ 40/151] eta: 0:00:35 time: 0.1941 data: 0.0670 max mem: 2851 +extract (train) [ 60/151] eta: 0:00:25 time: 0.2034 data: 0.0711 max mem: 2851 +extract (train) [ 80/151] eta: 0:00:18 time: 0.1739 data: 0.0555 max mem: 2851 +extract (train) [100/151] eta: 0:00:12 time: 0.1755 data: 0.0565 max mem: 2851 +extract (train) [120/151] eta: 0:00:07 time: 0.1729 data: 0.0536 max mem: 2851 +extract (train) [140/151] eta: 0:00:02 time: 0.1698 data: 0.0539 max mem: 2851 +extract (train) [150/151] eta: 0:00:00 time: 0.1654 data: 0.0532 max mem: 2851 +extract (train) Total time: 0:00:33 (0.2192 s / it) +extract (validation) [ 0/32] eta: 0:02:09 time: 4.0603 data: 3.8947 max mem: 2851 +extract (validation) [20/32] eta: 0:00:04 time: 0.2007 data: 0.0677 max mem: 2851 +extract (validation) [31/32] eta: 0:00:00 time: 0.1704 data: 0.0535 max mem: 2851 +extract (validation) Total time: 0:00:10 (0.3196 s / it) +extract (test) [ 0/33] eta: 0:02:00 time: 3.6582 data: 3.4565 max mem: 2851 +extract (test) [20/33] eta: 0:00:04 time: 0.2110 data: 0.0768 max mem: 2851 +extract (test) [32/33] eta: 0:00:00 time: 0.1624 data: 0.0496 max mem: 2851 +extract (test) Total time: 0:00:10 (0.3064 s / it) +feature extraction time: 0:00:53 +train features: (301, 768) +validation features: (64, 768) +test features: (65, 768) +evaluating fixed splits +eval results (fixed splits): + +| model | repr | clf | dataset | trial | C | split | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:-----------|:--------|----------:|:--------|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | adhd200_dx | | 0.0059948 | train | 0.76438 | 0.021343 | 0.75667 | 0.022348 | 0.75395 | 0.022167 | +| flat_mae | patch | logistic | adhd200_dx | | 0.0059948 | test | 0.56923 | 0.058974 | 0.545 | 0.064098 | 0.54778 | 0.06079 | + + +evaluating random splits (n=100) +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 1, "C": 0.005994842503189409, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.05823466911033781, "f1": 0.5512820512820513, "f1_std": 0.06101740765976957, "bacc": 0.5521235521235521, "bacc_std": 0.059345337654677005} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 2, "C": 0.005994842503189409, "split": "test", "acc": 0.7076923076923077, "acc_std": 0.05308237207258236, "f1": 0.6834145091002307, "f1_std": 0.06098463999828951, "bacc": 0.6824324324324325, "bacc_std": 0.05633519538357175} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 3, "C": 0.005994842503189409, "split": "test", "acc": 0.5538461538461539, "acc_std": 0.05729690141048295, "f1": 0.5321419707123356, "f1_std": 0.06066492252765309, "bacc": 0.5342664092664092, "bacc_std": 0.05843324979509744} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 4, "C": 0.005994842503189409, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.056910468458081974, "f1": 0.6264367816091954, "f1_std": 0.057617826974017024, "bacc": 0.627895752895753, "bacc_std": 0.057765173254212016} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 5, "C": 0.005994842503189409, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.060759656499919136, "f1": 0.564176245210728, "f1_std": 0.06182452978685377, "bacc": 0.5651544401544402, "bacc_std": 0.06229613399002149} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 6, "C": 0.005994842503189409, "split": "test", "acc": 0.6923076923076923, "acc_std": 0.055543157696190684, "f1": 0.6794871794871795, "f1_std": 0.05916235256033133, "bacc": 0.6776061776061776, "bacc_std": 0.057807195213041195} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 7, "C": 0.005994842503189409, "split": "test", "acc": 0.7384615384615385, "acc_std": 0.05210250252368661, "f1": 0.7292330311198236, "f1_std": 0.05466814307189587, "bacc": 0.7268339768339769, "bacc_std": 0.054148122875282145} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 8, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.06262762307159384, "f1": 0.5833333333333333, "f1_std": 0.06558189053927652, "bacc": 0.5834942084942085, "bacc_std": 0.06357056370155993} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 9, "C": 0.005994842503189409, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.06206647324112846, "f1": 0.5699583435432491, "f1_std": 0.0641473728132606, "bacc": 0.5699806949806949, "bacc_std": 0.0628752729087681} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 10, "C": 0.005994842503189409, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.057334199342113285, "f1": 0.5644080416976918, "f1_std": 0.06142299946985614, "bacc": 0.5656370656370656, "bacc_std": 0.05904952375618707} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 11, "C": 0.005994842503189409, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.05567250816768069, "f1": 0.5501153550371699, "f1_std": 0.062241879408880194, "bacc": 0.556949806949807, "bacc_std": 0.057205255400809916} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 12, "C": 0.005994842503189409, "split": "test", "acc": 0.5538461538461539, "acc_std": 0.05696048666769025, "f1": 0.5250692869740489, "f1_std": 0.06324942661927546, "bacc": 0.5299227799227799, "bacc_std": 0.05889424510685927} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 13, "C": 0.005994842503189409, "split": "test", "acc": 0.6461538461538462, "acc_std": 0.05838274852594546, "f1": 0.6336682185738789, "f1_std": 0.061543638302394336, "bacc": 0.6327220077220077, "bacc_std": 0.06048191849300948} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 14, "C": 0.046415888336127774, "split": "test", "acc": 0.6461538461538462, "acc_std": 0.05639484638000934, "f1": 0.6375757575757576, "f1_std": 0.05840845807223114, "bacc": 0.6370656370656371, "bacc_std": 0.057989912661457296} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 15, "C": 0.005994842503189409, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.06083115831944356, "f1": 0.6094688776736361, "f1_std": 0.06154781990674974, "bacc": 0.61003861003861, "bacc_std": 0.06171520194557334} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 16, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.06253579519342001, "f1": 0.5953065134099617, "f1_std": 0.06313227976787619, "bacc": 0.5965250965250966, "bacc_std": 0.06339327491473806} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 17, "C": 0.005994842503189409, "split": "test", "acc": 0.5538461538461539, "acc_std": 0.059631777398796736, "f1": 0.5167905665214048, "f1_std": 0.06543089233523129, "bacc": 0.5255791505791506, "bacc_std": 0.06063748064592794} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 18, "C": 0.005994842503189409, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.05924028694759283, "f1": 0.6235521235521235, "f1_std": 0.06008567840419021, "bacc": 0.6235521235521235, "bacc_std": 0.05967511019774278} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 19, "C": 0.005994842503189409, "split": "test", "acc": 0.7692307692307693, "acc_std": 0.054894196242090014, "f1": 0.7580044676098288, "f1_std": 0.05933688466919537, "bacc": 0.7538610038610039, "bacc_std": 0.05798112713891719} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 20, "C": 0.005994842503189409, "split": "test", "acc": 0.676923076923077, "acc_std": 0.05565311838341871, "f1": 0.6612062546537603, "f1_std": 0.06021123053146866, "bacc": 0.6597490347490347, "bacc_std": 0.05808298357542373} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 21, "C": 0.046415888336127774, "split": "test", "acc": 0.7076923076923077, "acc_std": 0.05768392964808284, "f1": 0.7074153044302298, "f1_std": 0.057791113500653, "bacc": 0.7171814671814671, "bacc_std": 0.05722536227865714} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 22, "C": 0.005994842503189409, "split": "test", "acc": 0.6923076923076923, "acc_std": 0.05736700905407786, "f1": 0.6862934362934363, "f1_std": 0.05892624371385294, "bacc": 0.6862934362934363, "bacc_std": 0.058918894716479445} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 23, "C": 0.005994842503189409, "split": "test", "acc": 0.6615384615384615, "acc_std": 0.052113767218728395, "f1": 0.6366869918699187, "f1_std": 0.0582879703838755, "bacc": 0.6375482625482626, "bacc_std": 0.054471985443560016} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 24, "C": 0.046415888336127774, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.06301919309404756, "f1": 0.6153846153846154, "f1_std": 0.06621388076842159, "bacc": 0.6148648648648649, "bacc_std": 0.06441334475767777} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 25, "C": 0.005994842503189409, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.062220976694587524, "f1": 0.6235521235521235, "f1_std": 0.0637627926279106, "bacc": 0.6235521235521235, "bacc_std": 0.06349457923724686} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 26, "C": 0.005994842503189409, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.05749569780663758, "f1": 0.6018132810585641, "f1_std": 0.06018816616100299, "bacc": 0.6013513513513513, "bacc_std": 0.05884401611884117} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 27, "C": 0.005994842503189409, "split": "test", "acc": 0.6923076923076923, "acc_std": 0.05395554602397758, "f1": 0.6832358674463938, "f1_std": 0.056122007249314064, "bacc": 0.6819498069498069, "bacc_std": 0.05531608713920772} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 28, "C": 0.000774263682681127, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.056078356001529855, "f1": 0.5501153550371699, "f1_std": 0.0627863767871707, "bacc": 0.556949806949807, "bacc_std": 0.05780843305862313} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 29, "C": 0.000774263682681127, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.059968236168095074, "f1": 0.6153846153846154, "f1_std": 0.06372240903198029, "bacc": 0.6148648648648649, "bacc_std": 0.06187803028717662} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 30, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.06023194615217166, "f1": 0.5833333333333333, "f1_std": 0.06281258200440287, "bacc": 0.5834942084942085, "bacc_std": 0.06146055346751933} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 31, "C": 0.000774263682681127, "split": "test", "acc": 0.6, "acc_std": 0.05707303324916554, "f1": 0.5626293995859213, "f1_std": 0.06461236731735141, "bacc": 0.5704633204633205, "bacc_std": 0.0589357876725277} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 32, "C": 0.046415888336127774, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.06453570911890014, "f1": 0.564176245210728, "f1_std": 0.06492092289557823, "bacc": 0.5651544401544402, "bacc_std": 0.06491054591470921} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 33, "C": 0.005994842503189409, "split": "test", "acc": 0.5538461538461539, "acc_std": 0.05918799654415785, "f1": 0.5469838981014179, "f1_std": 0.060370661165122214, "bacc": 0.5472972972972974, "bacc_std": 0.06033964536711476} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 34, "C": 0.005994842503189409, "split": "test", "acc": 0.676923076923077, "acc_std": 0.0591098946452319, "f1": 0.6655231560891939, "f1_std": 0.06233025036140078, "bacc": 0.6640926640926641, "bacc_std": 0.0611789897695685} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 35, "C": 0.005994842503189409, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.05732540562593094, "f1": 0.6153846153846154, "f1_std": 0.06013106124668067, "bacc": 0.6148648648648649, "bacc_std": 0.058629372106941746} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 36, "C": 0.000774263682681127, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.05788358854187607, "f1": 0.6018132810585641, "f1_std": 0.06079418397993015, "bacc": 0.6013513513513513, "bacc_std": 0.059353186285667485} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 37, "C": 0.005994842503189409, "split": "test", "acc": 0.6615384615384615, "acc_std": 0.04991876003618575, "f1": 0.6299171842650104, "f1_std": 0.05898935687215366, "bacc": 0.6332046332046332, "bacc_std": 0.05287040436049961} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 38, "C": 0.005994842503189409, "split": "test", "acc": 0.6615384615384615, "acc_std": 0.05569379513525764, "f1": 0.6474358974358974, "f1_std": 0.058383078261371374, "bacc": 0.6462355212355213, "bacc_std": 0.05677072664304426} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 39, "C": 0.005994842503189409, "split": "test", "acc": 0.6461538461538462, "acc_std": 0.057099692742103296, "f1": 0.6167649320687003, "f1_std": 0.06335848314966813, "bacc": 0.6196911196911197, "bacc_std": 0.05871068535172852} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 40, "C": 0.005994842503189409, "split": "test", "acc": 0.7076923076923077, "acc_std": 0.05405420028126711, "f1": 0.6934723256391164, "f1_std": 0.05846954231563569, "bacc": 0.6911196911196911, "bacc_std": 0.05657352692565806} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 41, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.0610177973843135, "f1": 0.5921814671814671, "f1_std": 0.06212907679964382, "bacc": 0.5921814671814671, "bacc_std": 0.06178787670559743} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 42, "C": 0.005994842503189409, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.06329238248378215, "f1": 0.5830363506771205, "f1_std": 0.06307294659546958, "bacc": 0.5873552123552124, "bacc_std": 0.06267798276913743} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 43, "C": 0.005994842503189409, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.05941170366640212, "f1": 0.5966741126830479, "f1_std": 0.062283073806634136, "bacc": 0.597007722007722, "bacc_std": 0.060372186972537704} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 44, "C": 0.005994842503189409, "split": "test", "acc": 0.676923076923077, "acc_std": 0.05752993766562459, "f1": 0.6690909090909091, "f1_std": 0.0593653714613639, "bacc": 0.6684362934362934, "bacc_std": 0.05895380477747002} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 45, "C": 0.005994842503189409, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.059451210168780785, "f1": 0.5644080416976918, "f1_std": 0.06303352315569263, "bacc": 0.5656370656370656, "bacc_std": 0.060779112778003304} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 46, "C": 0.005994842503189409, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.060790305985207446, "f1": 0.5966741126830479, "f1_std": 0.06385913991367025, "bacc": 0.597007722007722, "bacc_std": 0.06168084991290848} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 47, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.056976066811856296, "f1": 0.5833333333333333, "f1_std": 0.06007159584324916, "bacc": 0.5834942084942085, "bacc_std": 0.05818985881978718} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 48, "C": 0.005994842503189409, "split": "test", "acc": 0.7230769230769231, "acc_std": 0.054284248589903265, "f1": 0.7176640926640927, "f1_std": 0.05511855840158738, "bacc": 0.7176640926640927, "bacc_std": 0.054803202913940814} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 49, "C": 0.005994842503189409, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.058470760406250974, "f1": 0.5699583435432491, "f1_std": 0.061317764340931766, "bacc": 0.5699806949806949, "bacc_std": 0.05979410288568595} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 50, "C": 0.046415888336127774, "split": "test", "acc": 0.6461538461538462, "acc_std": 0.060411997711180034, "f1": 0.6407113674597452, "f1_std": 0.061238374104680054, "bacc": 0.6414092664092663, "bacc_std": 0.06117699854468939} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 51, "C": 0.005994842503189409, "split": "test", "acc": 0.6461538461538462, "acc_std": 0.06133631413732539, "f1": 0.6407113674597452, "f1_std": 0.06231654147769663, "bacc": 0.6414092664092663, "bacc_std": 0.06229662167030346} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 52, "C": 0.005994842503189409, "split": "test", "acc": 0.7076923076923077, "acc_std": 0.05431096089531818, "f1": 0.6888384983623079, "f1_std": 0.060273320210553726, "bacc": 0.6867760617760618, "bacc_std": 0.057272799947293625} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 53, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.055441432395235815, "f1": 0.5626293995859213, "f1_std": 0.062368743041143294, "bacc": 0.5704633204633205, "bacc_std": 0.057010853111860646} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 54, "C": 0.000774263682681127, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.06265543228855956, "f1": 0.5248538011695907, "f1_std": 0.06503639175259468, "bacc": 0.525096525096525, "bacc_std": 0.06401778324357316} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 55, "C": 0.005994842503189409, "split": "test", "acc": 0.5538461538461539, "acc_std": 0.06081310198288741, "f1": 0.5521501544309813, "f1_std": 0.061121650181704276, "bacc": 0.555984555984556, "bacc_std": 0.061705274741522625} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 56, "C": 0.005994842503189409, "split": "test", "acc": 0.6923076923076923, "acc_std": 0.05829121748173526, "f1": 0.6862934362934363, "f1_std": 0.059884184058497186, "bacc": 0.6862934362934363, "bacc_std": 0.05966351983052461} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 57, "C": 0.005994842503189409, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.0594847700661479, "f1": 0.5512820512820513, "f1_std": 0.06286142482319798, "bacc": 0.5521235521235521, "bacc_std": 0.06083633882266286} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 58, "C": 0.005994842503189409, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.05773242502622148, "f1": 0.606060606060606, "f1_std": 0.05915160127975713, "bacc": 0.6056949806949807, "bacc_std": 0.0585478230467917} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 59, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.05971351724703406, "f1": 0.5833333333333333, "f1_std": 0.06281910597882166, "bacc": 0.5834942084942085, "bacc_std": 0.06110696631020378} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 60, "C": 0.005994842503189409, "split": "test", "acc": 0.676923076923077, "acc_std": 0.05642526606838088, "f1": 0.6655231560891939, "f1_std": 0.05949259860813072, "bacc": 0.6640926640926641, "bacc_std": 0.05831950620125641} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 61, "C": 0.005994842503189409, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.06190104720415006, "f1": 0.5512820512820513, "f1_std": 0.06528209149796527, "bacc": 0.5521235521235521, "bacc_std": 0.06332149956628073} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 62, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.05722775839888321, "f1": 0.5921814671814671, "f1_std": 0.05886317861610063, "bacc": 0.5921814671814671, "bacc_std": 0.05869520254608574} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 63, "C": 0.005994842503189409, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.05770411366382652, "f1": 0.6198830409356726, "f1_std": 0.059795477520609014, "bacc": 0.6192084942084942, "bacc_std": 0.05892124357184523} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 64, "C": 0.005994842503189409, "split": "test", "acc": 0.676923076923077, "acc_std": 0.05748347022503449, "f1": 0.6690909090909091, "f1_std": 0.05907753597271104, "bacc": 0.6684362934362934, "bacc_std": 0.05851374340106606} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 65, "C": 0.005994842503189409, "split": "test", "acc": 0.6923076923076923, "acc_std": 0.05648455619687028, "f1": 0.6832358674463938, "f1_std": 0.059097216457051606, "bacc": 0.6819498069498069, "bacc_std": 0.05849397348061152} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 66, "C": 0.005994842503189409, "split": "test", "acc": 0.6461538461538462, "acc_std": 0.05548417547202671, "f1": 0.6233308138070043, "f1_std": 0.0607298654303357, "bacc": 0.6240347490347491, "bacc_std": 0.05743654736888971} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 67, "C": 0.005994842503189409, "split": "test", "acc": 0.676923076923077, "acc_std": 0.05837320451985791, "f1": 0.6612062546537603, "f1_std": 0.06269135347590363, "bacc": 0.6597490347490347, "bacc_std": 0.06031664859574043} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 68, "C": 0.005994842503189409, "split": "test", "acc": 0.7230769230769231, "acc_std": 0.052827274648097854, "f1": 0.7115384615384616, "f1_std": 0.0559675669661284, "bacc": 0.708976833976834, "bacc_std": 0.05472850109786505} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 69, "C": 0.005994842503189409, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.054596746548927357, "f1": 0.5411764705882354, "f1_std": 0.06398892345140886, "bacc": 0.5526061776061776, "bacc_std": 0.056728363265298856} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 70, "C": 0.005994842503189409, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.06076183791448018, "f1": 0.5357142857142857, "f1_std": 0.06110414190727916, "bacc": 0.5381274131274132, "bacc_std": 0.06155035668518762} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 71, "C": 0.005994842503189409, "split": "test", "acc": 0.6923076923076923, "acc_std": 0.05893399376677077, "f1": 0.6832358674463938, "f1_std": 0.061669390799744664, "bacc": 0.6819498069498069, "bacc_std": 0.060794802391271184} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 72, "C": 0.005994842503189409, "split": "test", "acc": 0.676923076923077, "acc_std": 0.0554907018172025, "f1": 0.6612062546537603, "f1_std": 0.0596615062354922, "bacc": 0.6597490347490347, "bacc_std": 0.057537275342234295} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 73, "C": 0.005994842503189409, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.06350113263677938, "f1": 0.61207925519217, "f1_std": 0.063971113688209, "bacc": 0.6143822393822393, "bacc_std": 0.06414738052600293} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 74, "C": 0.005994842503189409, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.05948203249174588, "f1": 0.6153846153846154, "f1_std": 0.06224411046113453, "bacc": 0.6148648648648649, "bacc_std": 0.060478736771852795} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 75, "C": 0.046415888336127774, "split": "test", "acc": 0.49230769230769234, "acc_std": 0.06361821033627503, "f1": 0.4879446168536643, "f1_std": 0.06367751120056546, "bacc": 0.4888996138996139, "bacc_std": 0.0640084391223475} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 76, "C": 0.046415888336127774, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.05876732981218764, "f1": 0.5512820512820513, "f1_std": 0.06171207680861565, "bacc": 0.5521235521235521, "bacc_std": 0.05981431028061214} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 77, "C": 0.005994842503189409, "split": "test", "acc": 0.7076923076923077, "acc_std": 0.05280846265335369, "f1": 0.6834145091002307, "f1_std": 0.061239571855799466, "bacc": 0.6824324324324325, "bacc_std": 0.05604652490834303} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 78, "C": 0.005994842503189409, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.058283607771921965, "f1": 0.6153846153846154, "f1_std": 0.0618961648645442, "bacc": 0.6148648648648649, "bacc_std": 0.060080556947396675} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 79, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.05823278321890615, "f1": 0.5833333333333333, "f1_std": 0.06182649278149465, "bacc": 0.5834942084942085, "bacc_std": 0.059841954182076565} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 80, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.05977136715318587, "f1": 0.570630081300813, "f1_std": 0.06686351306486094, "bacc": 0.5748069498069498, "bacc_std": 0.06191794814552674} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 81, "C": 0.005994842503189409, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.0545934603882165, "f1": 0.5905769715293525, "f1_std": 0.05974953508299354, "bacc": 0.5926640926640927, "bacc_std": 0.056106886145996425} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 82, "C": 0.005994842503189409, "split": "test", "acc": 0.6923076923076923, "acc_std": 0.05525711820594732, "f1": 0.6886973180076628, "f1_std": 0.05575221341943116, "bacc": 0.6906370656370657, "bacc_std": 0.05577227770989988} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 83, "C": 0.005994842503189409, "split": "test", "acc": 0.7230769230769231, "acc_std": 0.0565083520035211, "f1": 0.7115384615384616, "f1_std": 0.06019050932663844, "bacc": 0.708976833976834, "bacc_std": 0.05889830508575462} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 84, "C": 0.005994842503189409, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.06082144592184297, "f1": 0.6285714285714286, "f1_std": 0.06105000547784311, "bacc": 0.6322393822393823, "bacc_std": 0.06131632445911314} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 85, "C": 0.046415888336127774, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.05930796966911099, "f1": 0.5512820512820513, "f1_std": 0.06187423988816779, "bacc": 0.5521235521235521, "bacc_std": 0.06014734002958052} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 86, "C": 0.005994842503189409, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.06079254859353275, "f1": 0.5125, "f1_std": 0.06401946542785866, "bacc": 0.5164092664092664, "bacc_std": 0.061436579274149625} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 87, "C": 0.005994842503189409, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.06030426991859036, "f1": 0.6153846153846154, "f1_std": 0.06354323326076174, "bacc": 0.6148648648648649, "bacc_std": 0.06184709112603137} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 88, "C": 0.000774263682681127, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.06094808344599234, "f1": 0.6235521235521235, "f1_std": 0.062423165694250556, "bacc": 0.6235521235521235, "bacc_std": 0.062189370858899695} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 89, "C": 0.005994842503189409, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.05851702629888079, "f1": 0.6018132810585641, "f1_std": 0.06130873329648783, "bacc": 0.6013513513513513, "bacc_std": 0.059986090101061075} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 90, "C": 0.005994842503189409, "split": "test", "acc": 0.6461538461538462, "acc_std": 0.05883517041792698, "f1": 0.6336682185738789, "f1_std": 0.06157986287112086, "bacc": 0.6327220077220077, "bacc_std": 0.06021029717175913} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 91, "C": 0.005994842503189409, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.04985409243526933, "f1": 0.5962732919254659, "f1_std": 0.05714740416761842, "bacc": 0.6018339768339769, "bacc_std": 0.051746730640877196} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 92, "C": 0.005994842503189409, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.056692013359010494, "f1": 0.5834401435529352, "f1_std": 0.06300169814337812, "bacc": 0.5883204633204633, "bacc_std": 0.058287362817184545} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 93, "C": 0.005994842503189409, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.05282097485483759, "f1": 0.5751633986928104, "f1_std": 0.06195081087998022, "bacc": 0.583976833976834, "bacc_std": 0.05495307212854429} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 94, "C": 0.005994842503189409, "split": "test", "acc": 0.676923076923077, "acc_std": 0.05458451131721933, "f1": 0.6500897205844656, "f1_std": 0.06234467331848489, "bacc": 0.6510617760617761, "bacc_std": 0.05746096559314624} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 95, "C": 0.005994842503189409, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.05976499143464702, "f1": 0.5512820512820513, "f1_std": 0.0634432060720491, "bacc": 0.5521235521235521, "bacc_std": 0.06125580405415924} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 96, "C": 0.005994842503189409, "split": "test", "acc": 0.6615384615384615, "acc_std": 0.05941470740162996, "f1": 0.6575670498084292, "f1_std": 0.060211233195574185, "bacc": 0.6592664092664093, "bacc_std": 0.060522043578688615} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 97, "C": 0.046415888336127774, "split": "test", "acc": 0.6, "acc_std": 0.05457329689259951, "f1": 0.5533826638477801, "f1_std": 0.06387625718521175, "bacc": 0.5661196911196912, "bacc_std": 0.05642727206461918} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 98, "C": 0.005994842503189409, "split": "test", "acc": 0.6923076923076923, "acc_std": 0.055047271777786726, "f1": 0.675, "f1_std": 0.059884941248904984, "bacc": 0.6732625482625483, "bacc_std": 0.057118539416352976} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 99, "C": 0.005994842503189409, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.056184783890555305, "f1": 0.6198830409356726, "f1_std": 0.058110150039346165, "bacc": 0.6192084942084942, "bacc_std": 0.05732455078922899} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 100, "C": 0.005994842503189409, "split": "test", "acc": 0.6615384615384615, "acc_std": 0.05400504030827331, "f1": 0.6425000000000001, "f1_std": 0.0583921459321074, "bacc": 0.6418918918918919, "bacc_std": 0.05595758716693383} +eval results (random splits): + +| model | repr | clf | dataset | split | n_trials | C | C_std | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:-----------|:--------|-----------:|----------:|---------:|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | adhd200_dx | train | 100 | 0.0093195 | 0.011791 | 0.76099 | 0.028859 | 0.75215 | 0.030501 | 0.7493 | 0.03023 | +| flat_mae | patch | logistic | adhd200_dx | test | 100 | 0.0093195 | 0.011791 | 0.62908 | 0.052703 | 0.61332 | 0.055568 | 0.61442 | 0.054047 | + + +done! total time: 0:04:46 diff --git a/input_space_v3/flat_lr1e-3_4/eval_v2/adni_ad_vs_cn__patch__logistic/config.yaml b/input_space_v3/flat_lr1e-3_4/eval_v2/adni_ad_vs_cn__patch__logistic/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..81ec7482c763003016cdf13106b2efa72bb869af --- /dev/null +++ b/input_space_v3/flat_lr1e-3_4/eval_v2/adni_ad_vs_cn__patch__logistic/config.yaml @@ -0,0 +1,30 @@ +output_root: experiments/input_space_v3/output +name_prefix: eval_logistic +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_4; eval v2 (adni_ad_vs_cn patch logistic) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: input_space_v3/flat_lr1e-3_4/eval_v2/adni_ad_vs_cn__patch__logistic +model: flat_mae +representation: patch +dataset: adni_ad_vs_cn +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/eval_v2/adni_ad_vs_cn__patch__logistic +remote_dir: null diff --git a/input_space_v3/flat_lr1e-3_4/eval_v2/adni_ad_vs_cn__patch__logistic/eval_table.csv b/input_space_v3/flat_lr1e-3_4/eval_v2/adni_ad_vs_cn__patch__logistic/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..9f79a06b615f92915afd79e996aefabfeaf71173 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_4/eval_v2/adni_ad_vs_cn__patch__logistic/eval_table.csv @@ -0,0 +1,203 @@ +model,repr,clf,dataset,trial,C,split,acc,acc_std,f1,f1_std,bacc,bacc_std +flat_mae,patch,logistic,adni_ad_vs_cn,,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,,2.782559402207126,test,0.6829268292682927,0.06933825048534775,0.5547201336675021,0.08460092300008507,0.5572916666666666,0.08685729145776339 +flat_mae,patch,logistic,adni_ad_vs_cn,1,0.3593813663804626,train,0.9701897018970189,0.008711757163550188,0.957433644095347,0.012660334501910316,0.9481880187361328,0.015650500956610587 +flat_mae,patch,logistic,adni_ad_vs_cn,1,0.3593813663804626,test,0.7560975609756098,0.053634939379001566,0.6117424242424243,0.09037889030930249,0.6016129032258064,0.07808965364402315 +flat_mae,patch,logistic,adni_ad_vs_cn,2,0.3593813663804626,train,0.975609756097561,0.007334308717984832,0.9651729815325566,0.010702825749902077,0.9557687566768016,0.014111270757603822 +flat_mae,patch,logistic,adni_ad_vs_cn,2,0.3593813663804626,test,0.8048780487804879,0.06020648586254404,0.7354838709677419,0.08224946292289437,0.7354838709677419,0.08616609876559822 +flat_mae,patch,logistic,adni_ad_vs_cn,3,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,3,2.782559402207126,test,0.6829268292682927,0.06521197760078735,0.5547201336675021,0.08693342296115793,0.5532258064516129,0.0845620345042651 +flat_mae,patch,logistic,adni_ad_vs_cn,4,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,4,166.81005372000556,test,0.8780487804878049,0.049259694975486094,0.8287385129490392,0.07199643251243089,0.8177419354838709,0.07647474020680443 +flat_mae,patch,logistic,adni_ad_vs_cn,5,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,5,166.81005372000556,test,0.6829268292682927,0.0624843395014049,0.5547201336675021,0.08277599888209665,0.5532258064516129,0.08076173890118632 +flat_mae,patch,logistic,adni_ad_vs_cn,6,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,6,21.54434690031882,test,0.7560975609756098,0.050897384254731844,0.6117424242424243,0.09058148808232096,0.6016129032258064,0.0766746751989041 +flat_mae,patch,logistic,adni_ad_vs_cn,7,0.3593813663804626,train,0.981029810298103,0.007357349753688149,0.9729123189697663,0.010775090107884173,0.9633494946174705,0.014659352039536132 +flat_mae,patch,logistic,adni_ad_vs_cn,7,0.3593813663804626,test,0.7804878048780488,0.06254290139711734,0.6917293233082706,0.08884730087102158,0.685483870967742,0.08860572742414635 +flat_mae,patch,logistic,adni_ad_vs_cn,8,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,8,2.782559402207126,test,0.8048780487804879,0.053305512771664516,0.7152777777777778,0.08167474747829302,0.7016129032258065,0.07953341898001998 +flat_mae,patch,logistic,adni_ad_vs_cn,9,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,9,2.782559402207126,test,0.6585365853658537,0.0675226799978996,0.5370967741935484,0.08236769294058414,0.5370967741935484,0.08120154881316372 +flat_mae,patch,logistic,adni_ad_vs_cn,10,0.046415888336127774,train,0.8997289972899729,0.013532567473134405,0.8444297580930026,0.023502102873303315,0.8132139041827595,0.02619489852316833 +flat_mae,patch,logistic,adni_ad_vs_cn,10,0.046415888336127774,test,0.8048780487804879,0.04373025856972101,0.6554621848739496,0.09681735297536274,0.6338709677419355,0.07645135674382021 +flat_mae,patch,logistic,adni_ad_vs_cn,11,0.3593813663804626,train,0.9701897018970189,0.008774001418276578,0.957433644095347,0.01277433022218709,0.9481880187361328,0.01573659229917705 +flat_mae,patch,logistic,adni_ad_vs_cn,11,0.3593813663804626,test,0.7560975609756098,0.052940899557195324,0.6117424242424243,0.08715208656837461,0.6016129032258064,0.07545419122875437 +flat_mae,patch,logistic,adni_ad_vs_cn,12,0.3593813663804626,train,0.981029810298103,0.0073097443976051606,0.9731387984733936,0.010483981297005675,0.9673966636535458,0.013186598491944836 +flat_mae,patch,logistic,adni_ad_vs_cn,12,0.3593813663804626,test,0.7560975609756098,0.06680503388257766,0.7054597701149425,0.07709636707298852,0.7370967741935484,0.08460241464636714 +flat_mae,patch,logistic,adni_ad_vs_cn,13,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,13,21.54434690031882,test,0.7804878048780488,0.053143850891395936,0.6660633484162897,0.0862869080597797,0.6516129032258065,0.08062898186087256 +flat_mae,patch,logistic,adni_ad_vs_cn,14,0.046415888336127774,train,0.8970189701897019,0.01356473468270353,0.8377684191040355,0.024144474772121335,0.8033527816583121,0.026190237102423818 +flat_mae,patch,logistic,adni_ad_vs_cn,14,0.046415888336127774,test,0.7317073170731707,0.05496890040648148,0.5918552036199095,0.08556576468701314,0.5854838709677419,0.07563467400994765 +flat_mae,patch,logistic,adni_ad_vs_cn,15,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,15,166.81005372000556,test,0.8048780487804879,0.05790757574765888,0.7354838709677419,0.08129928799373015,0.7354838709677419,0.08499625994097747 +flat_mae,patch,logistic,adni_ad_vs_cn,16,0.3593813663804626,train,0.983739837398374,0.006149781804823891,0.9766829555986183,0.009057382231896007,0.9651162790697674,0.013193427244069853 +flat_mae,patch,logistic,adni_ad_vs_cn,16,0.3593813663804626,test,0.8292682926829268,0.05780847987131921,0.7602339181286549,0.08687878346208856,0.7516129032258064,0.08864463891474013 +flat_mae,patch,logistic,adni_ad_vs_cn,17,0.046415888336127774,train,0.9024390243902439,0.013793563011933687,0.850862223818933,0.022691160854264713,0.8230750267072069,0.024852237564500772 +flat_mae,patch,logistic,adni_ad_vs_cn,17,0.046415888336127774,test,0.7804878048780488,0.04922961534249257,0.6328358208955224,0.09724127242740907,0.6177419354838709,0.07827355350269749 +flat_mae,patch,logistic,adni_ad_vs_cn,18,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,18,21.54434690031882,test,0.8292682926829268,0.04755061800914636,0.7144278606965174,0.09737151304708817,0.6838709677419355,0.08329232375597488 +flat_mae,patch,logistic,adni_ad_vs_cn,19,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,19,21.54434690031882,test,0.7073170731707317,0.06801168671663453,0.6272727272727273,0.08273262526997624,0.6370967741935484,0.08883297068398141 +flat_mae,patch,logistic,adni_ad_vs_cn,20,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,20,2.782559402207126,test,0.7073170731707317,0.07556214078995811,0.646551724137931,0.08345672846791478,0.6709677419354838,0.09205159272497676 +flat_mae,patch,logistic,adni_ad_vs_cn,21,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,21,21.54434690031882,test,0.8536585365853658,0.05421307687032501,0.8016129032258064,0.07559751872013261,0.8016129032258064,0.0802131226597383 +flat_mae,patch,logistic,adni_ad_vs_cn,22,0.046415888336127774,train,0.9051490514905149,0.012956197145926093,0.8528389603582457,0.022009623113546126,0.8207946421234283,0.024268991797747903 +flat_mae,patch,logistic,adni_ad_vs_cn,22,0.046415888336127774,test,0.8048780487804879,0.04999795355716889,0.6893939393939394,0.08850356218810088,0.667741935483871,0.07850917587894059 +flat_mae,patch,logistic,adni_ad_vs_cn,23,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,23,2.782559402207126,test,0.5853658536585366,0.07045326185414946,0.4863669859985261,0.07827506968658328,0.4887096774193548,0.0851054271200501 +flat_mae,patch,logistic,adni_ad_vs_cn,24,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,24,2.782559402207126,test,0.6585365853658537,0.07501100454662234,0.6057692307692308,0.07889197417046628,0.6387096774193548,0.09071736304796724 +flat_mae,patch,logistic,adni_ad_vs_cn,25,0.046415888336127774,train,0.8915989159891599,0.013481507509144487,0.8274410774410774,0.024503232991153756,0.7917248746815679,0.0263985622201957 +flat_mae,patch,logistic,adni_ad_vs_cn,25,0.046415888336127774,test,0.7560975609756098,0.052960065994340735,0.6117424242424243,0.09195864341335616,0.6016129032258064,0.07907789307876958 +flat_mae,patch,logistic,adni_ad_vs_cn,26,0.046415888336127774,train,0.9024390243902439,0.013899592412098444,0.8463069233617179,0.024465801617710527,0.8109335195989811,0.026834519815187807 +flat_mae,patch,logistic,adni_ad_vs_cn,26,0.046415888336127774,test,0.7317073170731707,0.0590707336711048,0.5918552036199095,0.0882160445210422,0.5854838709677419,0.07876616191123474 +flat_mae,patch,logistic,adni_ad_vs_cn,27,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,27,166.81005372000556,test,0.7804878048780488,0.056139432941502504,0.6660633484162897,0.09048227208903092,0.6516129032258065,0.08360181353180356 +flat_mae,patch,logistic,adni_ad_vs_cn,28,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,28,2.782559402207126,test,0.7073170731707317,0.06273367974746852,0.5729166666666666,0.08553658097539353,0.5693548387096774,0.07992731681311996 +flat_mae,patch,logistic,adni_ad_vs_cn,29,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,29,21.54434690031882,test,0.7804878048780488,0.05706431033995467,0.6660633484162897,0.09353680754631567,0.6516129032258065,0.0858413218014263 +flat_mae,patch,logistic,adni_ad_vs_cn,30,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,30,1291.5496650148827,test,0.7073170731707317,0.05887259254933548,0.5729166666666666,0.08377782720147349,0.5693548387096774,0.07750055043274036 +flat_mae,patch,logistic,adni_ad_vs_cn,31,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,31,21.54434690031882,test,0.7073170731707317,0.06129407566866593,0.5729166666666666,0.08695795305052266,0.5693548387096774,0.08035254241030715 +flat_mae,patch,logistic,adni_ad_vs_cn,32,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,32,21.54434690031882,test,0.6829268292682927,0.07632877631661385,0.6259649122807017,0.08252326890431093,0.6548387096774193,0.09159522654316804 +flat_mae,patch,logistic,adni_ad_vs_cn,33,0.046415888336127774,train,0.9132791327913279,0.012718107231048797,0.8647732478240953,0.022022810112450882,0.8301421645163941,0.0245845439685677 +flat_mae,patch,logistic,adni_ad_vs_cn,33,0.046415888336127774,test,0.7560975609756098,0.06323998464062762,0.6893939393939394,0.07830457358449151,0.7032258064516128,0.08416285900935465 +flat_mae,patch,logistic,adni_ad_vs_cn,34,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,34,21.54434690031882,test,0.6585365853658537,0.07464696207519315,0.5876436781609196,0.08440793560500627,0.6048387096774194,0.09381875784522638 +flat_mae,patch,logistic,adni_ad_vs_cn,35,0.046415888336127774,train,0.8861788617886179,0.013009941156671388,0.816877776727479,0.02361733354895421,0.7800969677048237,0.024284526551414103 +flat_mae,patch,logistic,adni_ad_vs_cn,35,0.046415888336127774,test,0.8048780487804879,0.04324009860424898,0.6554621848739496,0.09572130709541071,0.6338709677419355,0.07446203622457337 +flat_mae,patch,logistic,adni_ad_vs_cn,36,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,36,21.54434690031882,test,0.7073170731707317,0.061094518204744354,0.5729166666666666,0.08704158967118233,0.5693548387096774,0.08174018507686158 +flat_mae,patch,logistic,adni_ad_vs_cn,37,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,37,166.81005372000556,test,0.7317073170731707,0.06039528723178355,0.6232247284878863,0.08273737628301407,0.6193548387096774,0.08146610404469212 +flat_mae,patch,logistic,adni_ad_vs_cn,38,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,38,166.81005372000556,test,0.7073170731707317,0.0698802238626281,0.6272727272727273,0.08624489185971264,0.6370967741935484,0.09154497117908214 +flat_mae,patch,logistic,adni_ad_vs_cn,39,0.3593813663804626,train,0.986449864498645,0.005393158199070236,0.9808134274809954,0.007731360090134551,0.9749774015942148,0.010418389157576681 +flat_mae,patch,logistic,adni_ad_vs_cn,39,0.3593813663804626,test,0.6341463414634146,0.06885723101416966,0.5199063231850116,0.07887331349456275,0.5209677419354839,0.08069941813550424 +flat_mae,patch,logistic,adni_ad_vs_cn,40,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,40,166.81005372000556,test,0.6341463414634146,0.0625209827954464,0.48621553884711777,0.0727557918029534,0.48709677419354835,0.07018509762934277 +flat_mae,patch,logistic,adni_ad_vs_cn,41,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,41,21.54434690031882,test,0.6829268292682927,0.07118783124293906,0.6072218128224024,0.08244170882460862,0.6209677419354839,0.08941715371074796 +flat_mae,patch,logistic,adni_ad_vs_cn,42,0.046415888336127774,train,0.8970189701897019,0.013654254716621976,0.8377684191040355,0.02428551640830775,0.8033527816583121,0.026323732233208733 +flat_mae,patch,logistic,adni_ad_vs_cn,42,0.046415888336127774,test,0.8048780487804879,0.04354477616467226,0.6554621848739496,0.09251605065182525,0.6338709677419355,0.07412721438575073 +flat_mae,patch,logistic,adni_ad_vs_cn,43,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,43,166.81005372000556,test,0.8048780487804879,0.058728850915062934,0.7515151515151515,0.07259696783853459,0.7693548387096774,0.0784234605684665 +flat_mae,patch,logistic,adni_ad_vs_cn,44,0.3593813663804626,train,0.983739837398374,0.00640414668727963,0.9766829555986183,0.009488864009253473,0.9651162790697674,0.013739128648873132 +flat_mae,patch,logistic,adni_ad_vs_cn,44,0.3593813663804626,test,0.8048780487804879,0.04981753738924528,0.6893939393939394,0.09059879818580999,0.667741935483871,0.0818061384445008 +flat_mae,patch,logistic,adni_ad_vs_cn,45,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,45,166.81005372000556,test,0.8048780487804879,0.05699304360736643,0.7354838709677419,0.0781641023733493,0.7354838709677419,0.08166790929703667 +flat_mae,patch,logistic,adni_ad_vs_cn,46,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,46,21.54434690031882,test,0.8536585365853658,0.045864529069530195,0.7670454545454546,0.0860473493350337,0.7338709677419355,0.08267464477491057 +flat_mae,patch,logistic,adni_ad_vs_cn,47,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,47,1291.5496650148827,test,0.8048780487804879,0.06093462036927684,0.7354838709677419,0.0820079902371227,0.7354838709677419,0.08563925372979647 +flat_mae,patch,logistic,adni_ad_vs_cn,48,0.3593813663804626,train,0.975609756097561,0.007693033314870899,0.9651729815325566,0.011185590626470855,0.9557687566768016,0.014067613770920365 +flat_mae,patch,logistic,adni_ad_vs_cn,48,0.3593813663804626,test,0.7317073170731707,0.06138740945228381,0.6479313036690086,0.08000537743493004,0.6532258064516129,0.08452750379008189 +flat_mae,patch,logistic,adni_ad_vs_cn,49,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,49,2.782559402207126,test,0.7560975609756098,0.0661802021397995,0.6893939393939394,0.08237019908131336,0.7032258064516128,0.08791187314672855 +flat_mae,patch,logistic,adni_ad_vs_cn,50,0.046415888336127774,train,0.8915989159891599,0.014130632235359462,0.8292299148463532,0.02509763808203647,0.7957720437176432,0.02704835346654203 +flat_mae,patch,logistic,adni_ad_vs_cn,50,0.046415888336127774,test,0.7560975609756098,0.061903553777273565,0.6693548387096775,0.08255056539173806,0.6693548387096775,0.08220617534801503 +flat_mae,patch,logistic,adni_ad_vs_cn,51,0.046415888336127774,train,0.8997289972899729,0.013228668004952123,0.8412164912484736,0.02348646222400004,0.805119566110609,0.02522036576523265 +flat_mae,patch,logistic,adni_ad_vs_cn,51,0.046415888336127774,test,0.7073170731707317,0.05966282416836626,0.5729166666666666,0.0866065769205364,0.5693548387096774,0.08105735145417638 +flat_mae,patch,logistic,adni_ad_vs_cn,52,0.046415888336127774,train,0.8997289972899729,0.014366324748713452,0.8428467833834041,0.024986630450534425,0.8091667351466842,0.026800847965850763 +flat_mae,patch,logistic,adni_ad_vs_cn,52,0.046415888336127774,test,0.7073170731707317,0.06311333676657278,0.5729166666666666,0.08991499887737524,0.5693548387096774,0.08371301074847566 +flat_mae,patch,logistic,adni_ad_vs_cn,53,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,53,21.54434690031882,test,0.7560975609756098,0.051801662662605254,0.6117424242424243,0.09120163534140602,0.6016129032258064,0.07805102116094567 +flat_mae,patch,logistic,adni_ad_vs_cn,54,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,54,166.81005372000556,test,0.7560975609756098,0.06555986860273298,0.6893939393939394,0.08160515995704963,0.7032258064516128,0.08781837254055198 +flat_mae,patch,logistic,adni_ad_vs_cn,55,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,55,166.81005372000556,test,0.8048780487804879,0.059214991590224336,0.7354838709677419,0.08006605940040067,0.7354838709677419,0.08220698325406187 +flat_mae,patch,logistic,adni_ad_vs_cn,56,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,56,166.81005372000556,test,0.7317073170731707,0.056999556444416316,0.5918552036199095,0.08427338677633092,0.5854838709677419,0.07531072338805445 +flat_mae,patch,logistic,adni_ad_vs_cn,57,0.046415888336127774,train,0.8997289972899729,0.013685905173253169,0.8444297580930026,0.02370666432300767,0.8132139041827595,0.026279538163857145 +flat_mae,patch,logistic,adni_ad_vs_cn,57,0.046415888336127774,test,0.8048780487804879,0.05127465092502961,0.6893939393939394,0.09403560129720698,0.667741935483871,0.0825189325862356 +flat_mae,patch,logistic,adni_ad_vs_cn,58,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,58,2.782559402207126,test,0.7804878048780488,0.05837887290710252,0.6917293233082706,0.08529732916203077,0.685483870967742,0.08554472204234932 +flat_mae,patch,logistic,adni_ad_vs_cn,59,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,59,2.782559402207126,test,0.6829268292682927,0.06857799287296353,0.6072218128224024,0.08066433166644141,0.6209677419354839,0.08786570605012983 +flat_mae,patch,logistic,adni_ad_vs_cn,60,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,60,166.81005372000556,test,0.8292682926829268,0.0577634100512561,0.7885040530582166,0.06806549217910705,0.8193548387096774,0.07104510292288711 +flat_mae,patch,logistic,adni_ad_vs_cn,61,0.3593813663804626,train,0.986449864498645,0.006007344647727933,0.9808134274809954,0.008644376398489247,0.9749774015942148,0.011645681622061045 +flat_mae,patch,logistic,adni_ad_vs_cn,61,0.3593813663804626,test,0.6829268292682927,0.06518130117300198,0.5547201336675021,0.08517232566509907,0.5532258064516129,0.08095918699182134 +flat_mae,patch,logistic,adni_ad_vs_cn,62,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,62,2.782559402207126,test,0.7317073170731707,0.06250931637881141,0.6232247284878863,0.0825123239931771,0.6193548387096774,0.08045628177983113 +flat_mae,patch,logistic,adni_ad_vs_cn,63,10000.0,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,63,10000.0,test,0.8048780487804879,0.05945491045453229,0.7515151515151515,0.07397912788878307,0.7693548387096774,0.07891223137223836 +flat_mae,patch,logistic,adni_ad_vs_cn,64,0.046415888336127774,train,0.9051490514905149,0.014482749942657405,0.851341551849166,0.025411502317792614,0.8167474730873532,0.02781915939512681 +flat_mae,patch,logistic,adni_ad_vs_cn,64,0.046415888336127774,test,0.7804878048780488,0.0571696287248967,0.6660633484162897,0.0918928832053071,0.6516129032258065,0.08427944518287354 +flat_mae,patch,logistic,adni_ad_vs_cn,65,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,65,2.782559402207126,test,0.7073170731707317,0.07179975790334657,0.646551724137931,0.08130775871070269,0.6709677419354838,0.09081215818887886 +flat_mae,patch,logistic,adni_ad_vs_cn,66,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,66,21.54434690031882,test,0.6585365853658537,0.07329217564046675,0.5876436781609196,0.08153976276512911,0.6048387096774194,0.08959995929415977 +flat_mae,patch,logistic,adni_ad_vs_cn,67,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,67,2.782559402207126,test,0.7804878048780488,0.06089313446608004,0.6917293233082706,0.08699612246559218,0.685483870967742,0.086221739401809 +flat_mae,patch,logistic,adni_ad_vs_cn,68,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,68,21.54434690031882,test,0.6097560975609756,0.07314267754875121,0.5030303030303029,0.08199877875955233,0.5048387096774194,0.08672545525374786 +flat_mae,patch,logistic,adni_ad_vs_cn,69,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,69,21.54434690031882,test,0.8048780487804879,0.06309584034159192,0.7515151515151515,0.07760569982280682,0.7693548387096774,0.08275948402225301 +flat_mae,patch,logistic,adni_ad_vs_cn,70,0.3593813663804626,train,0.978319783197832,0.00756251793382541,0.969172932330827,0.01097346123287285,0.9615827101651737,0.014497236229933553 +flat_mae,patch,logistic,adni_ad_vs_cn,70,0.3593813663804626,test,0.8048780487804879,0.0505890113228852,0.6893939393939394,0.09289890476310037,0.667741935483871,0.08275910027580011 +flat_mae,patch,logistic,adni_ad_vs_cn,71,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,71,21.54434690031882,test,0.7317073170731707,0.0584896356433501,0.6232247284878863,0.08081694232791681,0.6193548387096774,0.07944767314371172 +flat_mae,patch,logistic,adni_ad_vs_cn,72,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,72,1291.5496650148827,test,0.6829268292682927,0.060556609176303684,0.5176470588235295,0.08324548597045199,0.5193548387096775,0.0744423834917822 +flat_mae,patch,logistic,adni_ad_vs_cn,73,0.046415888336127774,train,0.8970189701897019,0.013348143228072417,0.8360690235690236,0.024253553994224384,0.7993056126222369,0.02621205586538423 +flat_mae,patch,logistic,adni_ad_vs_cn,73,0.046415888336127774,test,0.7560975609756098,0.05795768626151001,0.6440972222222222,0.0855339561882319,0.635483870967742,0.08048374814135045 +flat_mae,patch,logistic,adni_ad_vs_cn,74,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,74,166.81005372000556,test,0.7560975609756098,0.05410510405086151,0.6117424242424243,0.09234966724676702,0.6016129032258064,0.0802444187652703 +flat_mae,patch,logistic,adni_ad_vs_cn,75,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,75,21.54434690031882,test,0.7804878048780488,0.058281129582715197,0.6917293233082706,0.08571990481221156,0.685483870967742,0.08633116452812689 +flat_mae,patch,logistic,adni_ad_vs_cn,76,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,76,21.54434690031882,test,0.7073170731707317,0.060916088021908635,0.603225806451613,0.08321204041357219,0.603225806451613,0.08333932842812687 +flat_mae,patch,logistic,adni_ad_vs_cn,77,0.046415888336127774,train,0.8997289972899729,0.014257741809420656,0.8444297580930026,0.024610836524871692,0.8132139041827595,0.02697946460435788 +flat_mae,patch,logistic,adni_ad_vs_cn,77,0.046415888336127774,test,0.8292682926829268,0.03664875808760064,0.6800445930880714,0.10006373649275727,0.65,0.07512995407958134 +flat_mae,patch,logistic,adni_ad_vs_cn,78,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,78,166.81005372000556,test,0.6829268292682927,0.07174871875974152,0.6072218128224024,0.08088205236220525,0.6209677419354839,0.08747616080783048 +flat_mae,patch,logistic,adni_ad_vs_cn,79,0.3593813663804626,train,0.983739837398374,0.005971109170474878,0.9770712510356255,0.008492315213677552,0.9732106171419179,0.010578426801993673 +flat_mae,patch,logistic,adni_ad_vs_cn,79,0.3593813663804626,test,0.8048780487804879,0.06541417944222752,0.764367816091954,0.07361423284727173,0.8032258064516129,0.07703887932855587 +flat_mae,patch,logistic,adni_ad_vs_cn,80,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,80,2.782559402207126,test,0.7804878048780488,0.06097543414608858,0.6917293233082706,0.0901094828119332,0.685483870967742,0.0885381276153009 +flat_mae,patch,logistic,adni_ad_vs_cn,81,0.046415888336127774,train,0.9214092140921409,0.01306034686777303,0.8780665671539749,0.022603885255202412,0.8435368559454351,0.026162278708758476 +flat_mae,patch,logistic,adni_ad_vs_cn,81,0.046415888336127774,test,0.8048780487804879,0.04130468901855684,0.6554621848739496,0.09487346662853427,0.6338709677419355,0.07383286409871806 +flat_mae,patch,logistic,adni_ad_vs_cn,82,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,82,21.54434690031882,test,0.7073170731707317,0.06517219218459927,0.5729166666666666,0.09370732649328964,0.5693548387096774,0.08736047320657192 +flat_mae,patch,logistic,adni_ad_vs_cn,83,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,83,166.81005372000556,test,0.7317073170731707,0.06809747361794662,0.6479313036690086,0.08434513806573422,0.6532258064516129,0.08791250948312887 +flat_mae,patch,logistic,adni_ad_vs_cn,84,0.3593813663804626,train,0.9728997289972899,0.008257848796418816,0.9611382593310305,0.012150200432812563,0.9499548031884295,0.01588785129759267 +flat_mae,patch,logistic,adni_ad_vs_cn,84,0.3593813663804626,test,0.7804878048780488,0.060543856798801365,0.6917293233082706,0.08731284832690744,0.685483870967742,0.08831527197074936 +flat_mae,patch,logistic,adni_ad_vs_cn,85,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,85,166.81005372000556,test,0.9024390243902439,0.045352187818414186,0.8677419354838709,0.06322890223282873,0.8677419354838709,0.06934741775751853 +flat_mae,patch,logistic,adni_ad_vs_cn,86,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,86,166.81005372000556,test,0.6341463414634146,0.06370395538883927,0.5199063231850116,0.07462385763158666,0.5209677419354839,0.07764970677020255 +flat_mae,patch,logistic,adni_ad_vs_cn,87,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,87,166.81005372000556,test,0.8536585365853658,0.05167794840143674,0.8016129032258064,0.07263894030355361,0.8016129032258064,0.07810897234552563 +flat_mae,patch,logistic,adni_ad_vs_cn,88,10000.0,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,88,10000.0,test,0.7560975609756098,0.06457864160707003,0.7054597701149425,0.07457312214888025,0.7370967741935484,0.08250724964205484 +flat_mae,patch,logistic,adni_ad_vs_cn,89,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,89,2.782559402207126,test,0.7073170731707317,0.0700168416894576,0.6272727272727273,0.08438243913544687,0.6370967741935484,0.09053611458254916 +flat_mae,patch,logistic,adni_ad_vs_cn,90,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,90,166.81005372000556,test,0.7073170731707317,0.0674267575841411,0.6272727272727273,0.08057799175803532,0.6370967741935484,0.08658083120983807 +flat_mae,patch,logistic,adni_ad_vs_cn,91,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,91,21.54434690031882,test,0.6097560975609756,0.06739655964684559,0.47096774193548385,0.07455727163712558,0.47096774193548385,0.0758643372678803 +flat_mae,patch,logistic,adni_ad_vs_cn,92,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,92,21.54434690031882,test,0.6829268292682927,0.07289670639808277,0.5839188134270101,0.09115909247685451,0.5870967741935484,0.09448606061406202 +flat_mae,patch,logistic,adni_ad_vs_cn,93,0.3593813663804626,train,0.983739837398374,0.006387894320619008,0.9768796992481203,0.0092516480514423,0.9691634481058427,0.012506507238248886 +flat_mae,patch,logistic,adni_ad_vs_cn,93,0.3593813663804626,test,0.6097560975609756,0.07902768737475808,0.5494505494505495,0.08316769218818686,0.5725806451612903,0.09596556549443125 +flat_mae,patch,logistic,adni_ad_vs_cn,94,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,94,2.782559402207126,test,0.6585365853658537,0.06653592375037626,0.5370967741935484,0.08080459943301056,0.5370967741935484,0.08004749338155527 +flat_mae,patch,logistic,adni_ad_vs_cn,95,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,95,166.81005372000556,test,0.7317073170731707,0.06110875220030991,0.6232247284878863,0.08558680669456915,0.6193548387096774,0.0830949273487414 +flat_mae,patch,logistic,adni_ad_vs_cn,96,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,96,21.54434690031882,test,0.7560975609756098,0.0623737463647492,0.6693548387096775,0.08419604024673814,0.6693548387096775,0.08613681226188322 +flat_mae,patch,logistic,adni_ad_vs_cn,97,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,97,166.81005372000556,test,0.7804878048780488,0.060373692518878364,0.7119437939110069,0.07900710437116268,0.7193548387096774,0.08454240043542632 +flat_mae,patch,logistic,adni_ad_vs_cn,98,0.005994842503189409,train,0.8373983739837398,0.012805348064960346,0.705397061954439,0.029679940985229056,0.6713986358780508,0.0247483482384738 +flat_mae,patch,logistic,adni_ad_vs_cn,98,0.005994842503189409,test,0.7073170731707317,0.052288746666558646,0.5340909090909092,0.08550980875454949,0.535483870967742,0.07195768759020724 +flat_mae,patch,logistic,adni_ad_vs_cn,99,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,99,21.54434690031882,test,0.7317073170731707,0.05990585515006988,0.5918552036199095,0.09134900606526576,0.5854838709677419,0.08112144587116854 +flat_mae,patch,logistic,adni_ad_vs_cn,100,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,100,2.782559402207126,test,0.6585365853658537,0.0685307870127735,0.5651515151515152,0.0835335939464926,0.5709677419354839,0.08858518484478897 diff --git a/input_space_v3/flat_lr1e-3_4/eval_v2/adni_ad_vs_cn__patch__logistic/log.txt b/input_space_v3/flat_lr1e-3_4/eval_v2/adni_ad_vs_cn__patch__logistic/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..c803a725f2fe2b5bc9a3a39257f9eacb4def6ce6 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_4/eval_v2/adni_ad_vs_cn__patch__logistic/log.txt @@ -0,0 +1,240 @@ +fMRI foundation model logistic probe eval +version: 0.1.dev86+gf97f52698 +sha: bcce2b486277d3a5b520775efd9cdf1a2affce36, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-04-08 22:22:30 +config: +output_root: experiments/input_space_v3/output +name_prefix: eval_logistic +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_4; eval v2 (adni_ad_vs_cn patch logistic) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: input_space_v3/flat_lr1e-3_4/eval_v2/adni_ad_vs_cn__patch__logistic +model: flat_mae +representation: patch +dataset: adni_ad_vs_cn +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/eval_v2/adni_ad_vs_cn__patch__logistic +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=True, reg_tokens=0, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: adni_ad_vs_cn (flat) +train (n=328): +ADNIDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'bold', 'mean', 'std'], + num_rows: 525 +}), + labels=[0 1], + counts=[251 77] +) + +validation (n=41): +ADNIDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'bold', 'mean', 'std'], + num_rows: 66 +}), + labels=[0 1], + counts=[31 10] +) + +test (n=41): +ADNIDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'bold', 'mean', 'std'], + num_rows: 66 +}), + labels=[0 1], + counts=[32 9] +) + +extracting features for all splits +extract (train) [ 0/164] eta: 0:13:46 time: 5.0411 data: 4.0655 max mem: 2698 +extract (train) [ 20/164] eta: 0:01:04 time: 0.2156 data: 0.0795 max mem: 2851 +extract (train) [ 40/164] eta: 0:00:39 time: 0.1935 data: 0.0677 max mem: 2851 +extract (train) [ 60/164] eta: 0:00:28 time: 0.1846 data: 0.0660 max mem: 2851 +extract (train) [ 80/164] eta: 0:00:21 time: 0.1763 data: 0.0612 max mem: 2851 +extract (train) [100/164] eta: 0:00:15 time: 0.1950 data: 0.0686 max mem: 2851 +extract (train) [120/164] eta: 0:00:10 time: 0.2003 data: 0.0709 max mem: 2851 +extract (train) [140/164] eta: 0:00:05 time: 0.1794 data: 0.0607 max mem: 2851 +extract (train) [160/164] eta: 0:00:00 time: 0.1690 data: 0.0557 max mem: 2851 +extract (train) [163/164] eta: 0:00:00 time: 0.1681 data: 0.0545 max mem: 2851 +extract (train) Total time: 0:00:36 (0.2208 s / it) +extract (validation) [ 0/21] eta: 0:01:23 time: 3.9961 data: 3.8549 max mem: 2851 +extract (validation) [20/21] eta: 0:00:00 time: 0.1641 data: 0.0495 max mem: 2851 +extract (validation) Total time: 0:00:07 (0.3634 s / it) +extract (test) [ 0/21] eta: 0:01:25 time: 4.0927 data: 3.9335 max mem: 2851 +extract (test) [20/21] eta: 0:00:00 time: 0.1632 data: 0.0525 max mem: 2851 +extract (test) Total time: 0:00:07 (0.3688 s / it) +feature extraction time: 0:00:51 +train features: (328, 768) +validation features: (41, 768) +test features: (41, 768) +evaluating fixed splits +eval results (fixed splits): + +| model | repr | clf | dataset | trial | C | split | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:--------------|:--------|-------:|:--------|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | adni_ad_vs_cn | | 2.7826 | train | 1 | 0 | 1 | 0 | 1 | 0 | +| flat_mae | patch | logistic | adni_ad_vs_cn | | 2.7826 | test | 0.68293 | 0.069338 | 0.55472 | 0.084601 | 0.55729 | 0.086857 | + + +evaluating random splits (n=100) +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 1, "C": 0.3593813663804626, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.053634939379001566, "f1": 0.6117424242424243, "f1_std": 0.09037889030930249, "bacc": 0.6016129032258064, "bacc_std": 0.07808965364402315} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 2, "C": 0.3593813663804626, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.06020648586254404, "f1": 0.7354838709677419, "f1_std": 0.08224946292289437, "bacc": 0.7354838709677419, "bacc_std": 0.08616609876559822} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 3, "C": 2.782559402207126, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.06521197760078735, "f1": 0.5547201336675021, "f1_std": 0.08693342296115793, "bacc": 0.5532258064516129, "bacc_std": 0.0845620345042651} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 4, "C": 166.81005372000556, "split": "test", "acc": 0.8780487804878049, "acc_std": 0.049259694975486094, "f1": 0.8287385129490392, "f1_std": 0.07199643251243089, "bacc": 0.8177419354838709, "bacc_std": 0.07647474020680443} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 5, "C": 166.81005372000556, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.0624843395014049, "f1": 0.5547201336675021, "f1_std": 0.08277599888209665, "bacc": 0.5532258064516129, "bacc_std": 0.08076173890118632} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 6, "C": 21.54434690031882, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.050897384254731844, "f1": 0.6117424242424243, "f1_std": 0.09058148808232096, "bacc": 0.6016129032258064, "bacc_std": 0.0766746751989041} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 7, "C": 0.3593813663804626, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.06254290139711734, "f1": 0.6917293233082706, "f1_std": 0.08884730087102158, "bacc": 0.685483870967742, "bacc_std": 0.08860572742414635} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 8, "C": 2.782559402207126, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.053305512771664516, "f1": 0.7152777777777778, "f1_std": 0.08167474747829302, "bacc": 0.7016129032258065, "bacc_std": 0.07953341898001998} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 9, "C": 2.782559402207126, "split": "test", "acc": 0.6585365853658537, "acc_std": 0.0675226799978996, "f1": 0.5370967741935484, "f1_std": 0.08236769294058414, "bacc": 0.5370967741935484, "bacc_std": 0.08120154881316372} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 10, "C": 0.046415888336127774, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.04373025856972101, "f1": 0.6554621848739496, "f1_std": 0.09681735297536274, "bacc": 0.6338709677419355, "bacc_std": 0.07645135674382021} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 11, "C": 0.3593813663804626, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.052940899557195324, "f1": 0.6117424242424243, "f1_std": 0.08715208656837461, "bacc": 0.6016129032258064, "bacc_std": 0.07545419122875437} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 12, "C": 0.3593813663804626, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.06680503388257766, "f1": 0.7054597701149425, "f1_std": 0.07709636707298852, "bacc": 0.7370967741935484, "bacc_std": 0.08460241464636714} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 13, "C": 21.54434690031882, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.053143850891395936, "f1": 0.6660633484162897, "f1_std": 0.0862869080597797, "bacc": 0.6516129032258065, "bacc_std": 0.08062898186087256} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 14, "C": 0.046415888336127774, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.05496890040648148, "f1": 0.5918552036199095, "f1_std": 0.08556576468701314, "bacc": 0.5854838709677419, "bacc_std": 0.07563467400994765} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 15, "C": 166.81005372000556, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.05790757574765888, "f1": 0.7354838709677419, "f1_std": 0.08129928799373015, "bacc": 0.7354838709677419, "bacc_std": 0.08499625994097747} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 16, "C": 0.3593813663804626, "split": "test", "acc": 0.8292682926829268, "acc_std": 0.05780847987131921, "f1": 0.7602339181286549, "f1_std": 0.08687878346208856, "bacc": 0.7516129032258064, "bacc_std": 0.08864463891474013} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 17, "C": 0.046415888336127774, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.04922961534249257, "f1": 0.6328358208955224, "f1_std": 0.09724127242740907, "bacc": 0.6177419354838709, "bacc_std": 0.07827355350269749} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 18, "C": 21.54434690031882, "split": "test", "acc": 0.8292682926829268, "acc_std": 0.04755061800914636, "f1": 0.7144278606965174, "f1_std": 0.09737151304708817, "bacc": 0.6838709677419355, "bacc_std": 0.08329232375597488} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 19, "C": 21.54434690031882, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.06801168671663453, "f1": 0.6272727272727273, "f1_std": 0.08273262526997624, "bacc": 0.6370967741935484, "bacc_std": 0.08883297068398141} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 20, "C": 2.782559402207126, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.07556214078995811, "f1": 0.646551724137931, "f1_std": 0.08345672846791478, "bacc": 0.6709677419354838, "bacc_std": 0.09205159272497676} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 21, "C": 21.54434690031882, "split": "test", "acc": 0.8536585365853658, "acc_std": 0.05421307687032501, "f1": 0.8016129032258064, "f1_std": 0.07559751872013261, "bacc": 0.8016129032258064, "bacc_std": 0.0802131226597383} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 22, "C": 0.046415888336127774, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.04999795355716889, "f1": 0.6893939393939394, "f1_std": 0.08850356218810088, "bacc": 0.667741935483871, "bacc_std": 0.07850917587894059} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 23, "C": 2.782559402207126, "split": "test", "acc": 0.5853658536585366, "acc_std": 0.07045326185414946, "f1": 0.4863669859985261, "f1_std": 0.07827506968658328, "bacc": 0.4887096774193548, "bacc_std": 0.0851054271200501} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 24, "C": 2.782559402207126, "split": "test", "acc": 0.6585365853658537, "acc_std": 0.07501100454662234, "f1": 0.6057692307692308, "f1_std": 0.07889197417046628, "bacc": 0.6387096774193548, "bacc_std": 0.09071736304796724} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 25, "C": 0.046415888336127774, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.052960065994340735, "f1": 0.6117424242424243, "f1_std": 0.09195864341335616, "bacc": 0.6016129032258064, "bacc_std": 0.07907789307876958} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 26, "C": 0.046415888336127774, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.0590707336711048, "f1": 0.5918552036199095, "f1_std": 0.0882160445210422, "bacc": 0.5854838709677419, "bacc_std": 0.07876616191123474} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 27, "C": 166.81005372000556, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.056139432941502504, "f1": 0.6660633484162897, "f1_std": 0.09048227208903092, "bacc": 0.6516129032258065, "bacc_std": 0.08360181353180356} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 28, "C": 2.782559402207126, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.06273367974746852, "f1": 0.5729166666666666, "f1_std": 0.08553658097539353, "bacc": 0.5693548387096774, "bacc_std": 0.07992731681311996} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 29, "C": 21.54434690031882, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.05706431033995467, "f1": 0.6660633484162897, "f1_std": 0.09353680754631567, "bacc": 0.6516129032258065, "bacc_std": 0.0858413218014263} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 30, "C": 1291.5496650148827, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.05887259254933548, "f1": 0.5729166666666666, "f1_std": 0.08377782720147349, "bacc": 0.5693548387096774, "bacc_std": 0.07750055043274036} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 31, "C": 21.54434690031882, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.06129407566866593, "f1": 0.5729166666666666, "f1_std": 0.08695795305052266, "bacc": 0.5693548387096774, "bacc_std": 0.08035254241030715} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 32, "C": 21.54434690031882, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.07632877631661385, "f1": 0.6259649122807017, "f1_std": 0.08252326890431093, "bacc": 0.6548387096774193, "bacc_std": 0.09159522654316804} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 33, "C": 0.046415888336127774, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.06323998464062762, "f1": 0.6893939393939394, "f1_std": 0.07830457358449151, "bacc": 0.7032258064516128, "bacc_std": 0.08416285900935465} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 34, "C": 21.54434690031882, "split": "test", "acc": 0.6585365853658537, "acc_std": 0.07464696207519315, "f1": 0.5876436781609196, "f1_std": 0.08440793560500627, "bacc": 0.6048387096774194, "bacc_std": 0.09381875784522638} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 35, "C": 0.046415888336127774, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.04324009860424898, "f1": 0.6554621848739496, "f1_std": 0.09572130709541071, "bacc": 0.6338709677419355, "bacc_std": 0.07446203622457337} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 36, "C": 21.54434690031882, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.061094518204744354, "f1": 0.5729166666666666, "f1_std": 0.08704158967118233, "bacc": 0.5693548387096774, "bacc_std": 0.08174018507686158} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 37, "C": 166.81005372000556, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.06039528723178355, "f1": 0.6232247284878863, "f1_std": 0.08273737628301407, "bacc": 0.6193548387096774, "bacc_std": 0.08146610404469212} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 38, "C": 166.81005372000556, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.0698802238626281, "f1": 0.6272727272727273, "f1_std": 0.08624489185971264, "bacc": 0.6370967741935484, "bacc_std": 0.09154497117908214} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 39, "C": 0.3593813663804626, "split": "test", "acc": 0.6341463414634146, "acc_std": 0.06885723101416966, "f1": 0.5199063231850116, "f1_std": 0.07887331349456275, "bacc": 0.5209677419354839, "bacc_std": 0.08069941813550424} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 40, "C": 166.81005372000556, "split": "test", "acc": 0.6341463414634146, "acc_std": 0.0625209827954464, "f1": 0.48621553884711777, "f1_std": 0.0727557918029534, "bacc": 0.48709677419354835, "bacc_std": 0.07018509762934277} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 41, "C": 21.54434690031882, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.07118783124293906, "f1": 0.6072218128224024, "f1_std": 0.08244170882460862, "bacc": 0.6209677419354839, "bacc_std": 0.08941715371074796} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 42, "C": 0.046415888336127774, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.04354477616467226, "f1": 0.6554621848739496, "f1_std": 0.09251605065182525, "bacc": 0.6338709677419355, "bacc_std": 0.07412721438575073} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 43, "C": 166.81005372000556, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.058728850915062934, "f1": 0.7515151515151515, "f1_std": 0.07259696783853459, "bacc": 0.7693548387096774, "bacc_std": 0.0784234605684665} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 44, "C": 0.3593813663804626, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.04981753738924528, "f1": 0.6893939393939394, "f1_std": 0.09059879818580999, "bacc": 0.667741935483871, "bacc_std": 0.0818061384445008} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 45, "C": 166.81005372000556, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.05699304360736643, "f1": 0.7354838709677419, "f1_std": 0.0781641023733493, "bacc": 0.7354838709677419, "bacc_std": 0.08166790929703667} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 46, "C": 21.54434690031882, "split": "test", "acc": 0.8536585365853658, "acc_std": 0.045864529069530195, "f1": 0.7670454545454546, "f1_std": 0.0860473493350337, "bacc": 0.7338709677419355, "bacc_std": 0.08267464477491057} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 47, "C": 1291.5496650148827, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.06093462036927684, "f1": 0.7354838709677419, "f1_std": 0.0820079902371227, "bacc": 0.7354838709677419, "bacc_std": 0.08563925372979647} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 48, "C": 0.3593813663804626, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.06138740945228381, "f1": 0.6479313036690086, "f1_std": 0.08000537743493004, "bacc": 0.6532258064516129, "bacc_std": 0.08452750379008189} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 49, "C": 2.782559402207126, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.0661802021397995, "f1": 0.6893939393939394, "f1_std": 0.08237019908131336, "bacc": 0.7032258064516128, "bacc_std": 0.08791187314672855} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 50, "C": 0.046415888336127774, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.061903553777273565, "f1": 0.6693548387096775, "f1_std": 0.08255056539173806, "bacc": 0.6693548387096775, "bacc_std": 0.08220617534801503} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 51, "C": 0.046415888336127774, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.05966282416836626, "f1": 0.5729166666666666, "f1_std": 0.0866065769205364, "bacc": 0.5693548387096774, "bacc_std": 0.08105735145417638} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 52, "C": 0.046415888336127774, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.06311333676657278, "f1": 0.5729166666666666, "f1_std": 0.08991499887737524, "bacc": 0.5693548387096774, "bacc_std": 0.08371301074847566} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 53, "C": 21.54434690031882, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.051801662662605254, "f1": 0.6117424242424243, "f1_std": 0.09120163534140602, "bacc": 0.6016129032258064, "bacc_std": 0.07805102116094567} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 54, "C": 166.81005372000556, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.06555986860273298, "f1": 0.6893939393939394, "f1_std": 0.08160515995704963, "bacc": 0.7032258064516128, "bacc_std": 0.08781837254055198} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 55, "C": 166.81005372000556, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.059214991590224336, "f1": 0.7354838709677419, "f1_std": 0.08006605940040067, "bacc": 0.7354838709677419, "bacc_std": 0.08220698325406187} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 56, "C": 166.81005372000556, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.056999556444416316, "f1": 0.5918552036199095, "f1_std": 0.08427338677633092, "bacc": 0.5854838709677419, "bacc_std": 0.07531072338805445} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 57, "C": 0.046415888336127774, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.05127465092502961, "f1": 0.6893939393939394, "f1_std": 0.09403560129720698, "bacc": 0.667741935483871, "bacc_std": 0.0825189325862356} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 58, "C": 2.782559402207126, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.05837887290710252, "f1": 0.6917293233082706, "f1_std": 0.08529732916203077, "bacc": 0.685483870967742, "bacc_std": 0.08554472204234932} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 59, "C": 2.782559402207126, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.06857799287296353, "f1": 0.6072218128224024, "f1_std": 0.08066433166644141, "bacc": 0.6209677419354839, "bacc_std": 0.08786570605012983} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 60, "C": 166.81005372000556, "split": "test", "acc": 0.8292682926829268, "acc_std": 0.0577634100512561, "f1": 0.7885040530582166, "f1_std": 0.06806549217910705, "bacc": 0.8193548387096774, "bacc_std": 0.07104510292288711} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 61, "C": 0.3593813663804626, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.06518130117300198, "f1": 0.5547201336675021, "f1_std": 0.08517232566509907, "bacc": 0.5532258064516129, "bacc_std": 0.08095918699182134} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 62, "C": 2.782559402207126, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.06250931637881141, "f1": 0.6232247284878863, "f1_std": 0.0825123239931771, "bacc": 0.6193548387096774, "bacc_std": 0.08045628177983113} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 63, "C": 10000.0, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.05945491045453229, "f1": 0.7515151515151515, "f1_std": 0.07397912788878307, "bacc": 0.7693548387096774, "bacc_std": 0.07891223137223836} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 64, "C": 0.046415888336127774, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.0571696287248967, "f1": 0.6660633484162897, "f1_std": 0.0918928832053071, "bacc": 0.6516129032258065, "bacc_std": 0.08427944518287354} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 65, "C": 2.782559402207126, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.07179975790334657, "f1": 0.646551724137931, "f1_std": 0.08130775871070269, "bacc": 0.6709677419354838, "bacc_std": 0.09081215818887886} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 66, "C": 21.54434690031882, "split": "test", "acc": 0.6585365853658537, "acc_std": 0.07329217564046675, "f1": 0.5876436781609196, "f1_std": 0.08153976276512911, "bacc": 0.6048387096774194, "bacc_std": 0.08959995929415977} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 67, "C": 2.782559402207126, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.06089313446608004, "f1": 0.6917293233082706, "f1_std": 0.08699612246559218, "bacc": 0.685483870967742, "bacc_std": 0.086221739401809} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 68, "C": 21.54434690031882, "split": "test", "acc": 0.6097560975609756, "acc_std": 0.07314267754875121, "f1": 0.5030303030303029, "f1_std": 0.08199877875955233, "bacc": 0.5048387096774194, "bacc_std": 0.08672545525374786} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 69, "C": 21.54434690031882, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.06309584034159192, "f1": 0.7515151515151515, "f1_std": 0.07760569982280682, "bacc": 0.7693548387096774, "bacc_std": 0.08275948402225301} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 70, "C": 0.3593813663804626, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.0505890113228852, "f1": 0.6893939393939394, "f1_std": 0.09289890476310037, "bacc": 0.667741935483871, "bacc_std": 0.08275910027580011} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 71, "C": 21.54434690031882, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.0584896356433501, "f1": 0.6232247284878863, "f1_std": 0.08081694232791681, "bacc": 0.6193548387096774, "bacc_std": 0.07944767314371172} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 72, "C": 1291.5496650148827, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.060556609176303684, "f1": 0.5176470588235295, "f1_std": 0.08324548597045199, "bacc": 0.5193548387096775, "bacc_std": 0.0744423834917822} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 73, "C": 0.046415888336127774, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.05795768626151001, "f1": 0.6440972222222222, "f1_std": 0.0855339561882319, "bacc": 0.635483870967742, "bacc_std": 0.08048374814135045} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 74, "C": 166.81005372000556, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.05410510405086151, "f1": 0.6117424242424243, "f1_std": 0.09234966724676702, "bacc": 0.6016129032258064, "bacc_std": 0.0802444187652703} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 75, "C": 21.54434690031882, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.058281129582715197, "f1": 0.6917293233082706, "f1_std": 0.08571990481221156, "bacc": 0.685483870967742, "bacc_std": 0.08633116452812689} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 76, "C": 21.54434690031882, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.060916088021908635, "f1": 0.603225806451613, "f1_std": 0.08321204041357219, "bacc": 0.603225806451613, "bacc_std": 0.08333932842812687} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 77, "C": 0.046415888336127774, "split": "test", "acc": 0.8292682926829268, "acc_std": 0.03664875808760064, "f1": 0.6800445930880714, "f1_std": 0.10006373649275727, "bacc": 0.65, "bacc_std": 0.07512995407958134} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 78, "C": 166.81005372000556, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.07174871875974152, "f1": 0.6072218128224024, "f1_std": 0.08088205236220525, "bacc": 0.6209677419354839, "bacc_std": 0.08747616080783048} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 79, "C": 0.3593813663804626, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.06541417944222752, "f1": 0.764367816091954, "f1_std": 0.07361423284727173, "bacc": 0.8032258064516129, "bacc_std": 0.07703887932855587} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 80, "C": 2.782559402207126, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.06097543414608858, "f1": 0.6917293233082706, "f1_std": 0.0901094828119332, "bacc": 0.685483870967742, "bacc_std": 0.0885381276153009} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 81, "C": 0.046415888336127774, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.04130468901855684, "f1": 0.6554621848739496, "f1_std": 0.09487346662853427, "bacc": 0.6338709677419355, "bacc_std": 0.07383286409871806} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 82, "C": 21.54434690031882, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.06517219218459927, "f1": 0.5729166666666666, "f1_std": 0.09370732649328964, "bacc": 0.5693548387096774, "bacc_std": 0.08736047320657192} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 83, "C": 166.81005372000556, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.06809747361794662, "f1": 0.6479313036690086, "f1_std": 0.08434513806573422, "bacc": 0.6532258064516129, "bacc_std": 0.08791250948312887} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 84, "C": 0.3593813663804626, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.060543856798801365, "f1": 0.6917293233082706, "f1_std": 0.08731284832690744, "bacc": 0.685483870967742, "bacc_std": 0.08831527197074936} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 85, "C": 166.81005372000556, "split": "test", "acc": 0.9024390243902439, "acc_std": 0.045352187818414186, "f1": 0.8677419354838709, "f1_std": 0.06322890223282873, "bacc": 0.8677419354838709, "bacc_std": 0.06934741775751853} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 86, "C": 166.81005372000556, "split": "test", "acc": 0.6341463414634146, "acc_std": 0.06370395538883927, "f1": 0.5199063231850116, "f1_std": 0.07462385763158666, "bacc": 0.5209677419354839, "bacc_std": 0.07764970677020255} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 87, "C": 166.81005372000556, "split": "test", "acc": 0.8536585365853658, "acc_std": 0.05167794840143674, "f1": 0.8016129032258064, "f1_std": 0.07263894030355361, "bacc": 0.8016129032258064, "bacc_std": 0.07810897234552563} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 88, "C": 10000.0, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.06457864160707003, "f1": 0.7054597701149425, "f1_std": 0.07457312214888025, "bacc": 0.7370967741935484, "bacc_std": 0.08250724964205484} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 89, "C": 2.782559402207126, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.0700168416894576, "f1": 0.6272727272727273, "f1_std": 0.08438243913544687, "bacc": 0.6370967741935484, "bacc_std": 0.09053611458254916} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 90, "C": 166.81005372000556, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.0674267575841411, "f1": 0.6272727272727273, "f1_std": 0.08057799175803532, "bacc": 0.6370967741935484, "bacc_std": 0.08658083120983807} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 91, "C": 21.54434690031882, "split": "test", "acc": 0.6097560975609756, "acc_std": 0.06739655964684559, "f1": 0.47096774193548385, "f1_std": 0.07455727163712558, "bacc": 0.47096774193548385, "bacc_std": 0.0758643372678803} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 92, "C": 21.54434690031882, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.07289670639808277, "f1": 0.5839188134270101, "f1_std": 0.09115909247685451, "bacc": 0.5870967741935484, "bacc_std": 0.09448606061406202} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 93, "C": 0.3593813663804626, "split": "test", "acc": 0.6097560975609756, "acc_std": 0.07902768737475808, "f1": 0.5494505494505495, "f1_std": 0.08316769218818686, "bacc": 0.5725806451612903, "bacc_std": 0.09596556549443125} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 94, "C": 2.782559402207126, "split": "test", "acc": 0.6585365853658537, "acc_std": 0.06653592375037626, "f1": 0.5370967741935484, "f1_std": 0.08080459943301056, "bacc": 0.5370967741935484, "bacc_std": 0.08004749338155527} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 95, "C": 166.81005372000556, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.06110875220030991, "f1": 0.6232247284878863, "f1_std": 0.08558680669456915, "bacc": 0.6193548387096774, "bacc_std": 0.0830949273487414} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 96, "C": 21.54434690031882, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.0623737463647492, "f1": 0.6693548387096775, "f1_std": 0.08419604024673814, "bacc": 0.6693548387096775, "bacc_std": 0.08613681226188322} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 97, "C": 166.81005372000556, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.060373692518878364, "f1": 0.7119437939110069, "f1_std": 0.07900710437116268, "bacc": 0.7193548387096774, "bacc_std": 0.08454240043542632} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 98, "C": 0.005994842503189409, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.052288746666558646, "f1": 0.5340909090909092, "f1_std": 0.08550980875454949, "bacc": 0.535483870967742, "bacc_std": 0.07195768759020724} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 99, "C": 21.54434690031882, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.05990585515006988, "f1": 0.5918552036199095, "f1_std": 0.09134900606526576, "bacc": 0.5854838709677419, "bacc_std": 0.08112144587116854} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 100, "C": 2.782559402207126, "split": "test", "acc": 0.6585365853658537, "acc_std": 0.0685307870127735, "f1": 0.5651515151515152, "f1_std": 0.0835335939464926, "bacc": 0.5709677419354839, "bacc_std": 0.08858518484478897} +eval results (random splits): + +| model | repr | clf | dataset | split | n_trials | C | C_std | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:--------------|:--------|-----------:|-------:|--------:|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | adni_ad_vs_cn | train | 100 | 281.15 | 1413.2 | 0.97859 | 0.03972 | 0.96643 | 0.063896 | 0.95917 | 0.076442 | +| flat_mae | patch | logistic | adni_ad_vs_cn | test | 100 | 281.15 | 1413.2 | 0.74439 | 0.064155 | 0.64368 | 0.079332 | 0.64332 | 0.080368 | + + +done! total time: 0:05:03 diff --git a/input_space_v3/flat_lr1e-3_4/eval_v2/hcpya_task21__patch__attn/config.yaml b/input_space_v3/flat_lr1e-3_4/eval_v2/hcpya_task21__patch__attn/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..a0bcd8a748e2e61189382e69b40b7054404b3624 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_4/eval_v2/hcpya_task21__patch__attn/config.yaml @@ -0,0 +1,96 @@ +output_root: experiments/input_space_v3/output +name_prefix: eval_probe +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_4; eval v2 (hcpya_task21 patch attn) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +dataset_kwargs: {} +classifier_kwargs: + embed_dim: null + dropout: 0.0 + xavier_init: true + norm: true +lr_scale_grid: +- 0.02 +- 0.023 +- 0.028 +- 0.033 +- 0.038 +- 0.045 +- 0.053 +- 0.062 +- 0.074 +- 0.087 +- 0.1 +- 0.12 +- 0.14 +- 0.17 +- 0.2 +- 0.23 +- 0.27 +- 0.32 +- 0.38 +- 0.44 +- 0.52 +- 0.61 +- 0.72 +- 0.85 +- 1 +- 1.2 +- 1.4 +- 1.6 +- 1.9 +- 2.3 +- 2.7 +- 3.1 +- 3.7 +- 4.3 +- 5.1 +- 6 +- 7.1 +- 8.3 +- 9.8 +- 12 +- 14 +- 16 +- 19 +- 22 +- 26 +- 31 +- 36 +- 43 +- 50 +wd_scale_grid: +- 1.0 +num_workers: 8 +prefetch_factor: null +balanced_sampling: false +epochs: 20 +steps_per_epoch: 200 +batch_size: 64 +accum_iter: 2 +lr: 0.0003 +warmup_epochs: 5 +no_decay: false +weight_decay: 0.05 +clip_grad: 1.0 +metrics: +- acc +- f1 +cv_metric: acc +early_stopping: true +amp: true +device: cuda +seed: 4466 +debug: false +wandb: false +wandb_entity: null +wandb_project: fMRI-fm-eval +name: input_space_v3/flat_lr1e-3_4/eval_v2/hcpya_task21__patch__attn +model: flat_mae +representation: patch +classifier: attn +dataset: hcpya_task21 +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/eval_v2/hcpya_task21__patch__attn +remote_dir: null diff --git a/input_space_v3/flat_lr1e-3_4/eval_v2/hcpya_task21__patch__attn/eval_log.json b/input_space_v3/flat_lr1e-3_4/eval_v2/hcpya_task21__patch__attn/eval_log.json new file mode 100644 index 0000000000000000000000000000000000000000..ff37c1801b27be7681d57d78159cca530529e52b --- /dev/null +++ b/input_space_v3/flat_lr1e-3_4/eval_v2/hcpya_task21__patch__attn/eval_log.json @@ -0,0 +1 @@ +{"eval/epoch": 11, "eval/id_best": 32, "eval/lr_best": 0.0011099999999999999, "eval/wd_best": 0.05, "eval/train/loss": 0.00023677601711824536, "eval/train/acc": 1.0, "eval/train/acc_std": 0.0, "eval/train/f1": 1.0, "eval/train/f1_std": 0.0, "eval/validation/loss": 0.04388963431119919, "eval/validation/acc": 0.9915674603174603, "eval/validation/acc_std": 0.0014629807810532807, "eval/validation/f1": 0.9899431728392762, "eval/validation/f1_std": 0.001958870768061016, "eval/test/loss": 0.04777013882994652, "eval/test/acc": 0.9880952380952381, "eval/test/acc_std": 0.001416649993232545, "eval/test/f1": 0.9871945083157289, "eval/test/f1_std": 0.0017303826732366098} diff --git a/input_space_v3/flat_lr1e-3_4/eval_v2/hcpya_task21__patch__attn/eval_log_best.json b/input_space_v3/flat_lr1e-3_4/eval_v2/hcpya_task21__patch__attn/eval_log_best.json new file mode 100644 index 0000000000000000000000000000000000000000..64a7041704c3c9bf3623899e1470a640668e2ba0 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_4/eval_v2/hcpya_task21__patch__attn/eval_log_best.json @@ -0,0 +1 @@ +{"eval/best/epoch": 11, "eval/best/id_best": 32, "eval/best/lr_best": 0.0011099999999999999, "eval/best/wd_best": 0.05, "eval/best/train/loss": 0.00023677601711824536, "eval/best/train/acc": 1.0, "eval/best/train/acc_std": 0.0, "eval/best/train/f1": 1.0, "eval/best/train/f1_std": 0.0, "eval/best/validation/loss": 0.04388963431119919, "eval/best/validation/acc": 0.9915674603174603, "eval/best/validation/acc_std": 0.0014629807810532807, "eval/best/validation/f1": 0.9899431728392762, "eval/best/validation/f1_std": 0.001958870768061016, "eval/best/test/loss": 0.04777013882994652, "eval/best/test/acc": 0.9880952380952381, "eval/best/test/acc_std": 0.001416649993232545, "eval/best/test/f1": 0.9871945083157289, "eval/best/test/f1_std": 0.0017303826732366098} diff --git a/input_space_v3/flat_lr1e-3_4/eval_v2/hcpya_task21__patch__attn/eval_log_last.json b/input_space_v3/flat_lr1e-3_4/eval_v2/hcpya_task21__patch__attn/eval_log_last.json new file mode 100644 index 0000000000000000000000000000000000000000..d5a181ef00162ec611f375f5003d48c129400707 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_4/eval_v2/hcpya_task21__patch__attn/eval_log_last.json @@ -0,0 +1 @@ +{"eval/last/epoch": 19, "eval/last/id_best": 20, "eval/last/lr_best": 0.000156, "eval/last/wd_best": 0.05, "eval/last/train/loss": 0.01778648979961872, "eval/last/train/acc": 0.9956839833675457, "eval/last/train/acc_std": 0.0004852238326540055, "eval/last/train/f1": 0.9956583066485106, "eval/last/train/f1_std": 0.0005235209356897572, "eval/last/validation/loss": 0.031747955828905106, "eval/last/validation/acc": 0.9908234126984127, "eval/last/validation/acc_std": 0.0015291340963360046, "eval/last/validation/f1": 0.9895320331172237, "eval/last/validation/f1_std": 0.0018895067927594117, "eval/last/test/loss": 0.03688132017850876, "eval/last/test/acc": 0.9898809523809524, "eval/last/test/acc_std": 0.001364780040549714, "eval/last/test/f1": 0.9888161530327021, "eval/last/test/f1_std": 0.0016926874786506846} diff --git a/input_space_v3/flat_lr1e-3_4/eval_v2/hcpya_task21__patch__attn/eval_table.csv b/input_space_v3/flat_lr1e-3_4/eval_v2/hcpya_task21__patch__attn/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..019a90270dd91809d1ea206c2e172cebff2d4df4 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_4/eval_v2/hcpya_task21__patch__attn/eval_table.csv @@ -0,0 +1,4 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,patch,attn,hcpya_task21,best,11,0.0011099999999999999,0.05,32,"[3.7, 1.0]",train,0.00023677601711824536,1.0,0.0,1.0,0.0 +flat_mae,patch,attn,hcpya_task21,best,11,0.0011099999999999999,0.05,32,"[3.7, 1.0]",validation,0.04388963431119919,0.9915674603174603,0.0014629807810532807,0.9899431728392762,0.001958870768061016 +flat_mae,patch,attn,hcpya_task21,best,11,0.0011099999999999999,0.05,32,"[3.7, 1.0]",test,0.04777013882994652,0.9880952380952381,0.001416649993232545,0.9871945083157289,0.0017303826732366098 diff --git a/input_space_v3/flat_lr1e-3_4/eval_v2/hcpya_task21__patch__attn/eval_table_best.csv b/input_space_v3/flat_lr1e-3_4/eval_v2/hcpya_task21__patch__attn/eval_table_best.csv new file mode 100644 index 0000000000000000000000000000000000000000..019a90270dd91809d1ea206c2e172cebff2d4df4 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_4/eval_v2/hcpya_task21__patch__attn/eval_table_best.csv @@ -0,0 +1,4 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,patch,attn,hcpya_task21,best,11,0.0011099999999999999,0.05,32,"[3.7, 1.0]",train,0.00023677601711824536,1.0,0.0,1.0,0.0 +flat_mae,patch,attn,hcpya_task21,best,11,0.0011099999999999999,0.05,32,"[3.7, 1.0]",validation,0.04388963431119919,0.9915674603174603,0.0014629807810532807,0.9899431728392762,0.001958870768061016 +flat_mae,patch,attn,hcpya_task21,best,11,0.0011099999999999999,0.05,32,"[3.7, 1.0]",test,0.04777013882994652,0.9880952380952381,0.001416649993232545,0.9871945083157289,0.0017303826732366098 diff --git a/input_space_v3/flat_lr1e-3_4/eval_v2/hcpya_task21__patch__attn/eval_table_last.csv b/input_space_v3/flat_lr1e-3_4/eval_v2/hcpya_task21__patch__attn/eval_table_last.csv new file mode 100644 index 0000000000000000000000000000000000000000..28674401e991d675cdf32656a3ca2cb56878045a --- /dev/null +++ b/input_space_v3/flat_lr1e-3_4/eval_v2/hcpya_task21__patch__attn/eval_table_last.csv @@ -0,0 +1,4 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,patch,attn,hcpya_task21,last,19,0.000156,0.05,20,"[0.52, 1.0]",train,0.01778648979961872,0.9956839833675457,0.0004852238326540055,0.9956583066485106,0.0005235209356897572 +flat_mae,patch,attn,hcpya_task21,last,19,0.000156,0.05,20,"[0.52, 1.0]",validation,0.031747955828905106,0.9908234126984127,0.0015291340963360046,0.9895320331172237,0.0018895067927594117 +flat_mae,patch,attn,hcpya_task21,last,19,0.000156,0.05,20,"[0.52, 1.0]",test,0.03688132017850876,0.9898809523809524,0.001364780040549714,0.9888161530327021,0.0016926874786506846 diff --git a/input_space_v3/flat_lr1e-3_4/eval_v2/hcpya_task21__patch__attn/log.txt b/input_space_v3/flat_lr1e-3_4/eval_v2/hcpya_task21__patch__attn/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..0df618dc346379a22430d42987abdf43b8a7df03 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_4/eval_v2/hcpya_task21__patch__attn/log.txt @@ -0,0 +1,885 @@ +fMRI foundation model probe eval +version: 0.1.dev86+gf97f52698 +sha: bcce2b486277d3a5b520775efd9cdf1a2affce36, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-04-08 20:31:09 +config: +output_root: experiments/input_space_v3/output +name_prefix: eval_probe +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_4; eval v2 (hcpya_task21 patch attn) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +dataset_kwargs: {} +classifier_kwargs: + embed_dim: null + dropout: 0.0 + xavier_init: true + norm: true +lr_scale_grid: +- 0.02 +- 0.023 +- 0.028 +- 0.033 +- 0.038 +- 0.045 +- 0.053 +- 0.062 +- 0.074 +- 0.087 +- 0.1 +- 0.12 +- 0.14 +- 0.17 +- 0.2 +- 0.23 +- 0.27 +- 0.32 +- 0.38 +- 0.44 +- 0.52 +- 0.61 +- 0.72 +- 0.85 +- 1 +- 1.2 +- 1.4 +- 1.6 +- 1.9 +- 2.3 +- 2.7 +- 3.1 +- 3.7 +- 4.3 +- 5.1 +- 6 +- 7.1 +- 8.3 +- 9.8 +- 12 +- 14 +- 16 +- 19 +- 22 +- 26 +- 31 +- 36 +- 43 +- 50 +wd_scale_grid: +- 1.0 +num_workers: 8 +prefetch_factor: null +balanced_sampling: false +epochs: 20 +steps_per_epoch: 200 +batch_size: 64 +accum_iter: 2 +lr: 0.0003 +warmup_epochs: 5 +no_decay: false +weight_decay: 0.05 +clip_grad: 1.0 +metrics: +- acc +- f1 +cv_metric: acc +early_stopping: true +amp: true +device: cuda +seed: 4466 +debug: false +wandb: false +wandb_entity: null +wandb_project: fMRI-fm-eval +name: input_space_v3/flat_lr1e-3_4/eval_v2/hcpya_task21__patch__attn +model: flat_mae +representation: patch +classifier: attn +dataset: hcpya_task21 +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/eval_v2/hcpya_task21__patch__attn +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=True, reg_tokens=0, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: hcpya_task21 (flat) +train (n=18999): +HFDataset( + dataset=Dataset({ + features: ['sub', 'task', 'cond', 'cond_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 18999 +}), + labels=[ 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20], + counts=[ 832 1248 3201 1660 832 832 832 832 832 1248 1247 1243 832 416 + 416 416 416 416 416 416 416] +) + +validation (n=4032): +HFDataset( + dataset=Dataset({ + features: ['sub', 'task', 'cond', 'cond_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 4032 +}), + labels=[ 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20], + counts=[176 264 688 352 176 176 176 176 176 264 264 264 176 88 88 88 88 88 + 88 88 88] +) + +test (n=5040): +HFDataset( + dataset=Dataset({ + features: ['sub', 'task', 'cond', 'cond_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 5040 +}), + labels=[ 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20], + counts=[220 330 860 440 220 220 220 220 220 330 330 330 220 110 110 110 110 110 + 110 110 110] +) + +running backbone on example batch to get embedding dim +embedding feature dim (patch): 768 +initializing sweep of classifier heads +classifiers: +ModuleList( + (0-48): 49 x AttnPoolClassifier( + (kv): Linear(in_features=768, out_features=1536, bias=True) + (linear): Linear(in_features=768, out_features=21, bias=True) + ) +) +classifier params (train): 58.7M (58.7M) +setting up optimizer +total batch size: 128 = 64 bs per gpu x 2 accum +lr: 3.00e-04 +full schedule: epochs = 20 (steps = 4000) (decay = True) +warmup: epochs = 5 (steps = 1000) +start training for 20 epochs +train: [0] [ 0/400] eta: 0:24:39 lr: nan time: 3.6979 data: 3.2063 max mem: 21740 +train: [0] [ 20/400] eta: 0:03:55 lr: 0.000003 loss: 3.0785 (3.0780) grad: 0.2673 (0.2728) time: 0.4663 data: 0.0025 max mem: 22446 +train: [0] [ 40/400] eta: 0:03:13 lr: 0.000006 loss: 3.0430 (3.0403) grad: 0.2673 (0.2715) time: 0.4533 data: 0.0036 max mem: 22446 +train: [0] [ 60/400] eta: 0:02:55 lr: 0.000009 loss: 2.9278 (2.9825) grad: 0.2662 (0.2676) time: 0.4675 data: 0.0036 max mem: 22446 +train: [0] [ 80/400] eta: 0:02:41 lr: 0.000012 loss: 2.8015 (2.9225) grad: 0.2530 (0.2609) time: 0.4720 data: 0.0035 max mem: 22446 +train: [0] [100/400] eta: 0:02:29 lr: 0.000015 loss: 2.6502 (2.8550) grad: 0.2342 (0.2565) time: 0.4785 data: 0.0034 max mem: 22446 +train: [0] [120/400] eta: 0:02:18 lr: 0.000018 loss: 2.5248 (2.7865) grad: 0.2350 (0.2518) time: 0.4658 data: 0.0034 max mem: 22446 +train: [0] [140/400] eta: 0:02:07 lr: 0.000021 loss: 2.3830 (2.7208) grad: 0.2327 (0.2501) time: 0.4576 data: 0.0034 max mem: 22446 +train: [0] [160/400] eta: 0:01:56 lr: 0.000024 loss: 2.2681 (2.6614) grad: 0.2231 (0.2453) time: 0.4574 data: 0.0034 max mem: 22446 +train: [0] [180/400] eta: 0:01:45 lr: 0.000027 loss: 2.1726 (2.6017) grad: 0.2073 (0.2410) time: 0.4541 data: 0.0034 max mem: 22446 +train: [0] [200/400] eta: 0:01:35 lr: 0.000030 loss: 2.1079 (2.5454) grad: 0.2097 (0.2380) time: 0.4518 data: 0.0034 max mem: 22446 +train: [0] [220/400] eta: 0:01:25 lr: 0.000033 loss: 1.9796 (2.4923) grad: 0.1991 (0.2343) time: 0.4653 data: 0.0035 max mem: 22446 +train: [0] [240/400] eta: 0:01:16 lr: 0.000036 loss: 1.8910 (2.4388) grad: 0.1998 (0.2321) time: 0.4694 data: 0.0035 max mem: 22446 +train: [0] [260/400] eta: 0:01:06 lr: 0.000039 loss: 1.8251 (2.3904) grad: 0.1998 (0.2297) time: 0.4631 data: 0.0035 max mem: 22446 +train: [0] [280/400] eta: 0:00:56 lr: 0.000042 loss: 1.8053 (2.3474) grad: 0.1869 (0.2264) time: 0.4610 data: 0.0033 max mem: 22446 +train: [0] [300/400] eta: 0:00:48 lr: 0.000045 loss: 1.7576 (2.3055) grad: 0.1759 (0.2232) time: 0.6204 data: 0.1767 max mem: 22446 +train: [0] [320/400] eta: 0:00:38 lr: 0.000048 loss: 1.6964 (2.2646) grad: 0.1754 (0.2205) time: 0.4709 data: 0.0037 max mem: 22446 +train: [0] [340/400] eta: 0:00:28 lr: 0.000051 loss: 1.6180 (2.2258) grad: 0.1842 (0.2185) time: 0.4701 data: 0.0031 max mem: 22446 +train: [0] [360/400] eta: 0:00:19 lr: 0.000054 loss: 1.5854 (2.1900) grad: 0.1810 (0.2162) time: 0.4730 data: 0.0037 max mem: 22446 +train: [0] [380/400] eta: 0:00:09 lr: 0.000057 loss: 1.5569 (2.1554) grad: 0.1727 (0.2138) time: 0.4515 data: 0.0035 max mem: 22446 +train: [0] [399/400] eta: 0:00:00 lr: 0.000060 loss: 1.5084 (2.1208) grad: 0.1724 (0.2120) time: 0.4650 data: 0.0036 max mem: 22446 +train: [0] Total time: 0:03:12 (0.4801 s / it) +train: [0] Summary: lr: 0.000060 loss: 1.5084 (2.1208) grad: 0.1724 (0.2120) +eval (validation): [0] [ 0/63] eta: 0:03:32 time: 3.3792 data: 3.1273 max mem: 22446 +eval (validation): [0] [20/63] eta: 0:00:22 time: 0.3744 data: 0.0044 max mem: 22446 +eval (validation): [0] [40/63] eta: 0:00:09 time: 0.3358 data: 0.0028 max mem: 22446 +eval (validation): [0] [60/63] eta: 0:00:01 time: 0.3475 data: 0.0032 max mem: 22446 +eval (validation): [0] [62/63] eta: 0:00:00 time: 0.3473 data: 0.0032 max mem: 22446 +eval (validation): [0] Total time: 0:00:25 (0.4044 s / it) +cv: [0] best hparam: (22, 1.0) (043) ('043_lr2.2e+01_wd1.0e+00') loss: 0.049 acc: 0.985 f1: 0.982 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/eval_v2/hcpya_task21__patch__attn/checkpoint-best.pth +train: [1] [ 0/400] eta: 0:23:05 lr: nan time: 3.4645 data: 3.0676 max mem: 22446 +train: [1] [ 20/400] eta: 0:03:54 lr: 0.000063 loss: 1.4396 (1.4488) grad: 0.1640 (0.1708) time: 0.4742 data: 0.0034 max mem: 22446 +train: [1] [ 40/400] eta: 0:03:12 lr: 0.000066 loss: 1.4218 (1.4264) grad: 0.1706 (0.1709) time: 0.4485 data: 0.0036 max mem: 22446 +train: [1] [ 60/400] eta: 0:02:52 lr: 0.000069 loss: 1.3850 (1.4063) grad: 0.1666 (0.1673) time: 0.4505 data: 0.0035 max mem: 22446 +train: [1] [ 80/400] eta: 0:02:38 lr: 0.000072 loss: 1.3510 (1.3899) grad: 0.1550 (0.1652) time: 0.4603 data: 0.0035 max mem: 22446 +train: [1] [100/400] eta: 0:02:26 lr: 0.000075 loss: 1.3270 (1.3778) grad: 0.1560 (0.1646) time: 0.4533 data: 0.0035 max mem: 22446 +train: [1] [120/400] eta: 0:02:15 lr: 0.000078 loss: 1.3007 (1.3592) grad: 0.1534 (0.1634) time: 0.4573 data: 0.0035 max mem: 22446 +train: [1] [140/400] eta: 0:02:04 lr: 0.000081 loss: 1.2554 (1.3439) grad: 0.1531 (0.1618) time: 0.4562 data: 0.0035 max mem: 22446 +train: [1] [160/400] eta: 0:01:54 lr: 0.000084 loss: 1.2370 (1.3285) grad: 0.1497 (0.1605) time: 0.4564 data: 0.0037 max mem: 22446 +train: [1] [180/400] eta: 0:01:44 lr: 0.000087 loss: 1.2132 (1.3140) grad: 0.1506 (0.1596) time: 0.4521 data: 0.0034 max mem: 22446 +train: [1] [200/400] eta: 0:01:34 lr: 0.000090 loss: 1.1674 (1.2992) grad: 0.1450 (0.1587) time: 0.4546 data: 0.0034 max mem: 22446 +train: [1] [220/400] eta: 0:01:24 lr: 0.000093 loss: 1.1446 (1.2841) grad: 0.1524 (0.1588) time: 0.4521 data: 0.0035 max mem: 22446 +train: [1] [240/400] eta: 0:01:15 lr: 0.000096 loss: 1.1263 (1.2705) grad: 0.1524 (0.1578) time: 0.4619 data: 0.0035 max mem: 22446 +train: [1] [260/400] eta: 0:01:05 lr: 0.000099 loss: 1.1201 (1.2583) grad: 0.1468 (0.1569) time: 0.4552 data: 0.0037 max mem: 22446 +train: [1] [280/400] eta: 0:00:56 lr: 0.000102 loss: 1.0842 (1.2449) grad: 0.1410 (0.1563) time: 0.4520 data: 0.0036 max mem: 22446 +train: [1] [300/400] eta: 0:00:47 lr: 0.000105 loss: 1.0641 (1.2326) grad: 0.1364 (0.1549) time: 0.6264 data: 0.1781 max mem: 22446 +train: [1] [320/400] eta: 0:00:38 lr: 0.000108 loss: 1.0545 (1.2211) grad: 0.1363 (0.1541) time: 0.4649 data: 0.0033 max mem: 22446 +train: [1] [340/400] eta: 0:00:28 lr: 0.000111 loss: 1.0182 (1.2084) grad: 0.1374 (0.1531) time: 0.4728 data: 0.0036 max mem: 22446 +train: [1] [360/400] eta: 0:00:19 lr: 0.000114 loss: 1.0088 (1.1979) grad: 0.1304 (0.1519) time: 0.4739 data: 0.0037 max mem: 22446 +train: [1] [380/400] eta: 0:00:09 lr: 0.000117 loss: 0.9889 (1.1867) grad: 0.1366 (0.1511) time: 0.4472 data: 0.0034 max mem: 22446 +train: [1] [399/400] eta: 0:00:00 lr: 0.000120 loss: 0.9711 (1.1762) grad: 0.1336 (0.1501) time: 0.4710 data: 0.0034 max mem: 22446 +train: [1] Total time: 0:03:09 (0.4749 s / it) +train: [1] Summary: lr: 0.000120 loss: 0.9711 (1.1762) grad: 0.1336 (0.1501) +eval (validation): [1] [ 0/63] eta: 0:03:30 time: 3.3334 data: 3.0559 max mem: 22446 +eval (validation): [1] [20/63] eta: 0:00:21 time: 0.3597 data: 0.0043 max mem: 22446 +eval (validation): [1] [40/63] eta: 0:00:09 time: 0.3347 data: 0.0030 max mem: 22446 +eval (validation): [1] [60/63] eta: 0:00:01 time: 0.3353 data: 0.0033 max mem: 22446 +eval (validation): [1] [62/63] eta: 0:00:00 time: 0.3345 data: 0.0033 max mem: 22446 +eval (validation): [1] Total time: 0:00:24 (0.3950 s / it) +cv: [1] best hparam: (6, 1.0) (035) ('035_lr6.0e+00_wd1.0e+00') loss: 0.038 acc: 0.990 f1: 0.988 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/eval_v2/hcpya_task21__patch__attn/checkpoint-best.pth +train: [2] [ 0/400] eta: 0:22:18 lr: nan time: 3.3472 data: 3.0140 max mem: 22446 +train: [2] [ 20/400] eta: 0:03:39 lr: 0.000123 loss: 0.9182 (0.9358) grad: 0.1472 (0.1558) time: 0.4379 data: 0.0028 max mem: 22446 +train: [2] [ 40/400] eta: 0:03:05 lr: 0.000126 loss: 0.9357 (0.9415) grad: 0.1609 (0.1610) time: 0.4519 data: 0.0030 max mem: 22446 +train: [2] [ 60/400] eta: 0:02:49 lr: 0.000129 loss: 0.9447 (0.9358) grad: 0.1595 (0.1629) time: 0.4671 data: 0.0034 max mem: 22446 +train: [2] [ 80/400] eta: 0:02:35 lr: 0.000132 loss: 0.9391 (0.9337) grad: 0.1575 (0.1639) time: 0.4469 data: 0.0034 max mem: 22446 +train: [2] [100/400] eta: 0:02:23 lr: 0.000135 loss: 0.9277 (0.9324) grad: 0.1644 (0.1720) time: 0.4440 data: 0.0034 max mem: 22446 +train: [2] [120/400] eta: 0:02:12 lr: 0.000138 loss: 0.9182 (0.9307) grad: 0.1703 (0.1754) time: 0.4451 data: 0.0034 max mem: 22446 +train: [2] [140/400] eta: 0:02:02 lr: 0.000141 loss: 0.8828 (0.9258) grad: 0.1785 (0.1776) time: 0.4498 data: 0.0035 max mem: 22446 +train: [2] [160/400] eta: 0:01:52 lr: 0.000144 loss: 0.8732 (0.9239) grad: 0.1763 (0.1775) time: 0.4505 data: 0.0033 max mem: 22446 +train: [2] [180/400] eta: 0:01:42 lr: 0.000147 loss: 0.8698 (0.9168) grad: 0.1722 (0.1816) time: 0.4529 data: 0.0034 max mem: 22446 +train: [2] [200/400] eta: 0:01:32 lr: 0.000150 loss: 0.8315 (0.9081) grad: 0.1722 (0.1815) time: 0.4468 data: 0.0033 max mem: 22446 +train: [2] [220/400] eta: 0:01:23 lr: 0.000153 loss: 0.8352 (0.9065) grad: 0.1610 (0.1808) time: 0.4431 data: 0.0033 max mem: 22446 +train: [2] [240/400] eta: 0:01:13 lr: 0.000156 loss: 0.8902 (0.9023) grad: 0.1906 (0.1844) time: 0.4691 data: 0.0034 max mem: 22446 +train: [2] [260/400] eta: 0:01:04 lr: 0.000159 loss: 0.8414 (0.9005) grad: 0.2117 (0.1875) time: 0.4585 data: 0.0035 max mem: 22446 +train: [2] [280/400] eta: 0:00:55 lr: 0.000162 loss: 0.8325 (0.8971) grad: 0.1952 (0.1892) time: 0.4536 data: 0.0034 max mem: 22446 +train: [2] [300/400] eta: 0:00:47 lr: 0.000165 loss: 0.8108 (0.8909) grad: 0.1810 (0.1895) time: 0.6300 data: 0.1755 max mem: 22446 +train: [2] [320/400] eta: 0:00:37 lr: 0.000168 loss: 0.7960 (0.8867) grad: 0.1903 (0.1911) time: 0.4443 data: 0.0030 max mem: 22446 +train: [2] [340/400] eta: 0:00:28 lr: 0.000171 loss: 0.8045 (0.8827) grad: 0.2049 (0.1944) time: 0.4656 data: 0.0037 max mem: 22446 +train: [2] [360/400] eta: 0:00:18 lr: 0.000174 loss: 0.8297 (0.8811) grad: 0.1879 (0.1950) time: 0.4695 data: 0.0038 max mem: 22446 +train: [2] [380/400] eta: 0:00:09 lr: 0.000177 loss: 0.7530 (0.8746) grad: 0.2039 (0.1958) time: 0.4512 data: 0.0036 max mem: 22446 +train: [2] [399/400] eta: 0:00:00 lr: 0.000180 loss: 0.7061 (0.8659) grad: 0.2016 (0.1965) time: 0.4660 data: 0.0035 max mem: 22446 +train: [2] Total time: 0:03:07 (0.4697 s / it) +train: [2] Summary: lr: 0.000180 loss: 0.7061 (0.8659) grad: 0.2016 (0.1965) +eval (validation): [2] [ 0/63] eta: 0:03:34 time: 3.4081 data: 3.1199 max mem: 22446 +eval (validation): [2] [20/63] eta: 0:00:22 time: 0.3682 data: 0.0035 max mem: 22446 +eval (validation): [2] [40/63] eta: 0:00:09 time: 0.3185 data: 0.0032 max mem: 22446 +eval (validation): [2] [60/63] eta: 0:00:01 time: 0.3221 data: 0.0033 max mem: 22446 +eval (validation): [2] [62/63] eta: 0:00:00 time: 0.3237 data: 0.0034 max mem: 22446 +eval (validation): [2] Total time: 0:00:24 (0.3891 s / it) +cv: [2] best hparam: (3.7, 1.0) (032) ('032_lr3.7e+00_wd1.0e+00') loss: 0.038 acc: 0.990 f1: 0.988 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/eval_v2/hcpya_task21__patch__attn/checkpoint-best.pth +train: [3] [ 0/400] eta: 0:22:14 lr: nan time: 3.3358 data: 3.0042 max mem: 22446 +train: [3] [ 20/400] eta: 0:03:38 lr: 0.000183 loss: 0.6416 (0.7016) grad: 0.1957 (0.2179) time: 0.4373 data: 0.0024 max mem: 22446 +train: [3] [ 40/400] eta: 0:03:05 lr: 0.000186 loss: 0.7327 (0.7426) grad: 0.1968 (0.2235) time: 0.4526 data: 0.0038 max mem: 22446 +train: [3] [ 60/400] eta: 0:02:47 lr: 0.000189 loss: 0.7438 (0.7639) grad: 0.2298 (0.2365) time: 0.4457 data: 0.0036 max mem: 22446 +train: [3] [ 80/400] eta: 0:02:33 lr: 0.000192 loss: 0.7438 (0.7665) grad: 0.2325 (0.2385) time: 0.4445 data: 0.0036 max mem: 22446 +train: [3] [100/400] eta: 0:02:22 lr: 0.000195 loss: 0.7387 (0.7635) grad: 0.2246 (0.2369) time: 0.4471 data: 0.0036 max mem: 22446 +train: [3] [120/400] eta: 0:02:11 lr: 0.000198 loss: 0.7637 (0.7658) grad: 0.2199 (0.2359) time: 0.4471 data: 0.0035 max mem: 22446 +train: [3] [140/400] eta: 0:02:01 lr: 0.000201 loss: 0.7728 (0.7780) grad: 0.2311 (0.2394) time: 0.4448 data: 0.0035 max mem: 22446 +train: [3] [160/400] eta: 0:01:51 lr: 0.000204 loss: 0.7710 (0.7740) grad: 0.2544 (0.2456) time: 0.4467 data: 0.0035 max mem: 22446 +train: [3] [180/400] eta: 0:01:41 lr: 0.000207 loss: 0.7081 (0.7736) grad: 0.2654 (0.2481) time: 0.4555 data: 0.0033 max mem: 22446 +train: [3] [200/400] eta: 0:01:32 lr: 0.000210 loss: 0.7180 (0.7769) grad: 0.2611 (0.2507) time: 0.4548 data: 0.0034 max mem: 22446 +train: [3] [220/400] eta: 0:01:22 lr: 0.000213 loss: 0.7482 (0.7749) grad: 0.2611 (0.2547) time: 0.4469 data: 0.0033 max mem: 22446 +train: [3] [240/400] eta: 0:01:13 lr: 0.000216 loss: 0.7603 (0.7904) grad: 0.2761 (0.2562) time: 0.4618 data: 0.0036 max mem: 22446 +train: [3] [260/400] eta: 0:01:04 lr: 0.000219 loss: 0.7734 (0.7861) grad: 0.2717 (0.2578) time: 0.4513 data: 0.0035 max mem: 22446 +train: [3] [280/400] eta: 0:00:55 lr: 0.000222 loss: 0.7734 (0.7845) grad: 0.2971 (0.2589) time: 0.4435 data: 0.0034 max mem: 22446 +train: [3] [300/400] eta: 0:00:47 lr: 0.000225 loss: 0.7263 (0.7835) grad: 0.3140 (0.2657) time: 0.6387 data: 0.1780 max mem: 22446 +train: [3] [320/400] eta: 0:00:37 lr: 0.000228 loss: 0.6970 (0.7809) grad: 0.3193 (0.2690) time: 0.4517 data: 0.0026 max mem: 22446 +train: [3] [340/400] eta: 0:00:28 lr: 0.000231 loss: 0.6938 (0.7750) grad: 0.3145 (0.2742) time: 0.4584 data: 0.0035 max mem: 22446 +train: [3] [360/400] eta: 0:00:18 lr: 0.000234 loss: 0.6349 (0.7657) grad: 0.3213 (0.2777) time: 0.4734 data: 0.0037 max mem: 22446 +train: [3] [380/400] eta: 0:00:09 lr: 0.000237 loss: 0.6214 (0.7642) grad: 0.2990 (0.2784) time: 0.4551 data: 0.0035 max mem: 22446 +train: [3] [399/400] eta: 0:00:00 lr: 0.000240 loss: 0.6602 (0.7641) grad: 0.2830 (0.2796) time: 0.4574 data: 0.0034 max mem: 22446 +train: [3] Total time: 0:03:07 (0.4683 s / it) +train: [3] Summary: lr: 0.000240 loss: 0.6602 (0.7641) grad: 0.2830 (0.2796) +eval (validation): [3] [ 0/63] eta: 0:03:33 time: 3.3925 data: 3.1240 max mem: 22446 +eval (validation): [3] [20/63] eta: 0:00:20 time: 0.3378 data: 0.0034 max mem: 22446 +eval (validation): [3] [40/63] eta: 0:00:09 time: 0.3404 data: 0.0028 max mem: 22446 +eval (validation): [3] [60/63] eta: 0:00:01 time: 0.3212 data: 0.0032 max mem: 22446 +eval (validation): [3] [62/63] eta: 0:00:00 time: 0.3229 data: 0.0031 max mem: 22446 +eval (validation): [3] Total time: 0:00:24 (0.3869 s / it) +cv: [3] best hparam: (1.2, 1.0) (025) ('025_lr1.2e+00_wd1.0e+00') loss: 0.042 acc: 0.988 f1: 0.986 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [4] [ 0/400] eta: 0:22:52 lr: nan time: 3.4303 data: 3.0466 max mem: 22446 +train: [4] [ 20/400] eta: 0:03:45 lr: 0.000243 loss: 0.6798 (0.7393) grad: 0.3023 (0.3627) time: 0.4505 data: 0.0038 max mem: 22446 +train: [4] [ 40/400] eta: 0:03:07 lr: 0.000246 loss: 0.7905 (0.7957) grad: 0.3263 (0.3547) time: 0.4431 data: 0.0032 max mem: 22446 +train: [4] [ 60/400] eta: 0:02:49 lr: 0.000249 loss: 0.7785 (0.7733) grad: 0.3593 (0.3735) time: 0.4586 data: 0.0035 max mem: 22446 +train: [4] [ 80/400] eta: 0:02:36 lr: 0.000252 loss: 0.7327 (0.7624) grad: 0.3593 (0.3645) time: 0.4529 data: 0.0036 max mem: 22446 +train: [4] [100/400] eta: 0:02:24 lr: 0.000255 loss: 0.7064 (0.7510) grad: 0.3314 (0.3688) time: 0.4556 data: 0.0034 max mem: 22446 +train: [4] [120/400] eta: 0:02:13 lr: 0.000258 loss: 0.6583 (0.7561) grad: 0.3216 (0.3624) time: 0.4558 data: 0.0034 max mem: 22446 +train: [4] [140/400] eta: 0:02:03 lr: 0.000261 loss: 0.6368 (0.7418) grad: 0.3391 (0.3638) time: 0.4554 data: 0.0034 max mem: 22446 +train: [4] [160/400] eta: 0:01:53 lr: 0.000264 loss: 0.6382 (0.7484) grad: 0.3391 (0.3645) time: 0.4600 data: 0.0034 max mem: 22446 +train: [4] [180/400] eta: 0:01:43 lr: 0.000267 loss: 0.6808 (0.7393) grad: 0.3277 (0.3667) time: 0.4587 data: 0.0034 max mem: 22446 +train: [4] [200/400] eta: 0:01:34 lr: 0.000270 loss: 0.6808 (0.7423) grad: 0.3800 (0.3804) time: 0.4618 data: 0.0034 max mem: 22446 +train: [4] [220/400] eta: 0:01:24 lr: 0.000273 loss: 0.7225 (0.7555) grad: 0.3998 (0.3800) time: 0.4498 data: 0.0033 max mem: 22446 +train: [4] [240/400] eta: 0:01:15 lr: 0.000276 loss: 0.7225 (0.7617) grad: 0.3796 (0.3816) time: 0.4758 data: 0.0038 max mem: 22446 +train: [4] [260/400] eta: 0:01:05 lr: 0.000279 loss: 0.7753 (0.7793) grad: 0.3796 (0.3839) time: 0.4496 data: 0.0035 max mem: 22446 +train: [4] [280/400] eta: 0:00:55 lr: 0.000282 loss: 0.9249 (0.7881) grad: 0.4076 (0.3888) time: 0.4402 data: 0.0034 max mem: 22446 +train: [4] [300/400] eta: 0:00:47 lr: 0.000285 loss: 0.6482 (0.7906) grad: 0.3787 (0.3942) time: 0.6191 data: 0.1764 max mem: 22446 +train: [4] [320/400] eta: 0:00:37 lr: 0.000288 loss: 0.5175 (0.7755) grad: 0.3669 (0.3933) time: 0.4415 data: 0.0031 max mem: 22446 +train: [4] [340/400] eta: 0:00:28 lr: 0.000291 loss: 0.5652 (0.7646) grad: 0.3669 (0.3929) time: 0.4907 data: 0.0038 max mem: 22446 +train: [4] [360/400] eta: 0:00:19 lr: 0.000294 loss: 0.5717 (0.7643) grad: 0.3979 (0.3951) time: 0.4904 data: 0.0036 max mem: 22446 +train: [4] [380/400] eta: 0:00:09 lr: 0.000297 loss: 0.8617 (0.7779) grad: 0.4424 (0.4016) time: 0.4507 data: 0.0036 max mem: 22446 +train: [4] [399/400] eta: 0:00:00 lr: 0.000300 loss: 0.8617 (0.7797) grad: 0.4206 (0.4034) time: 0.4553 data: 0.0033 max mem: 22446 +train: [4] Total time: 0:03:09 (0.4736 s / it) +train: [4] Summary: lr: 0.000300 loss: 0.8617 (0.7797) grad: 0.4206 (0.4034) +eval (validation): [4] [ 0/63] eta: 0:03:33 time: 3.3935 data: 3.1547 max mem: 22446 +eval (validation): [4] [20/63] eta: 0:00:20 time: 0.3425 data: 0.0038 max mem: 22446 +eval (validation): [4] [40/63] eta: 0:00:09 time: 0.3263 data: 0.0027 max mem: 22446 +eval (validation): [4] [60/63] eta: 0:00:01 time: 0.3351 data: 0.0033 max mem: 22446 +eval (validation): [4] [62/63] eta: 0:00:00 time: 0.3326 data: 0.0032 max mem: 22446 +eval (validation): [4] Total time: 0:00:24 (0.3879 s / it) +cv: [4] best hparam: (0.85, 1.0) (023) ('023_lr8.5e-01_wd1.0e+00') loss: 0.043 acc: 0.989 f1: 0.988 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [5] [ 0/400] eta: 0:22:28 lr: nan time: 3.3710 data: 2.9959 max mem: 22446 +train: [5] [ 20/400] eta: 0:03:44 lr: 0.000300 loss: 0.6203 (0.6474) grad: 0.3773 (0.4655) time: 0.4508 data: 0.0027 max mem: 22446 +train: [5] [ 40/400] eta: 0:03:07 lr: 0.000300 loss: 0.6312 (0.7574) grad: 0.4175 (0.4557) time: 0.4501 data: 0.0032 max mem: 22446 +train: [5] [ 60/400] eta: 0:02:49 lr: 0.000300 loss: 0.7059 (0.7573) grad: 0.4214 (0.4491) time: 0.4478 data: 0.0036 max mem: 22446 +train: [5] [ 80/400] eta: 0:02:35 lr: 0.000300 loss: 0.7466 (0.7646) grad: 0.4193 (0.4392) time: 0.4476 data: 0.0035 max mem: 22446 +train: [5] [100/400] eta: 0:02:23 lr: 0.000300 loss: 0.7036 (0.7801) grad: 0.4299 (0.4484) time: 0.4447 data: 0.0036 max mem: 22446 +train: [5] [120/400] eta: 0:02:12 lr: 0.000300 loss: 0.7564 (0.8144) grad: 0.4819 (0.4523) time: 0.4513 data: 0.0035 max mem: 22446 +train: [5] [140/400] eta: 0:02:02 lr: 0.000300 loss: 0.8422 (0.8199) grad: 0.4260 (0.4499) time: 0.4605 data: 0.0034 max mem: 22446 +train: [5] [160/400] eta: 0:01:52 lr: 0.000299 loss: 0.7868 (0.8330) grad: 0.4276 (0.4575) time: 0.4582 data: 0.0035 max mem: 22446 +train: [5] [180/400] eta: 0:01:42 lr: 0.000299 loss: 0.7372 (0.8242) grad: 0.5196 (0.4741) time: 0.4565 data: 0.0035 max mem: 22446 +train: [5] [200/400] eta: 0:01:33 lr: 0.000299 loss: 0.6748 (0.8363) grad: 0.5196 (0.4774) time: 0.4440 data: 0.0035 max mem: 22446 +train: [5] [220/400] eta: 0:01:23 lr: 0.000299 loss: 0.6748 (0.8280) grad: 0.4609 (0.4769) time: 0.4407 data: 0.0033 max mem: 22446 +train: [5] [240/400] eta: 0:01:14 lr: 0.000299 loss: 0.5987 (0.8127) grad: 0.4168 (0.4707) time: 0.4550 data: 0.0035 max mem: 22446 +train: [5] [260/400] eta: 0:01:04 lr: 0.000299 loss: 0.6242 (0.8264) grad: 0.4698 (0.4731) time: 0.4582 data: 0.0035 max mem: 22446 +train: [5] [280/400] eta: 0:00:55 lr: 0.000298 loss: 0.7544 (0.8278) grad: 0.4698 (0.4727) time: 0.4479 data: 0.0034 max mem: 22446 +train: [5] [300/400] eta: 0:00:47 lr: 0.000298 loss: 0.8076 (0.8274) grad: 0.4212 (0.4738) time: 0.6405 data: 0.1777 max mem: 22446 +train: [5] [320/400] eta: 0:00:37 lr: 0.000298 loss: 0.6530 (0.8110) grad: 0.4052 (0.4690) time: 0.4518 data: 0.0031 max mem: 22446 +train: [5] [340/400] eta: 0:00:28 lr: 0.000298 loss: 0.4851 (0.8050) grad: 0.3822 (0.4644) time: 0.4576 data: 0.0035 max mem: 22446 +train: [5] [360/400] eta: 0:00:18 lr: 0.000297 loss: 0.6463 (0.8016) grad: 0.4008 (0.4614) time: 0.4600 data: 0.0033 max mem: 22446 +train: [5] [380/400] eta: 0:00:09 lr: 0.000297 loss: 0.7081 (0.8020) grad: 0.4213 (0.4606) time: 0.4569 data: 0.0034 max mem: 22446 +train: [5] [399/400] eta: 0:00:00 lr: 0.000297 loss: 0.5118 (0.7861) grad: 0.3919 (0.4555) time: 0.4531 data: 0.0033 max mem: 22446 +train: [5] Total time: 0:03:07 (0.4693 s / it) +train: [5] Summary: lr: 0.000297 loss: 0.5118 (0.7861) grad: 0.3919 (0.4555) +eval (validation): [5] [ 0/63] eta: 0:03:37 time: 3.4555 data: 3.1580 max mem: 22446 +eval (validation): [5] [20/63] eta: 0:00:21 time: 0.3468 data: 0.0038 max mem: 22446 +eval (validation): [5] [40/63] eta: 0:00:09 time: 0.3397 data: 0.0037 max mem: 22446 +eval (validation): [5] [60/63] eta: 0:00:01 time: 0.3342 data: 0.0026 max mem: 22446 +eval (validation): [5] [62/63] eta: 0:00:00 time: 0.3343 data: 0.0029 max mem: 22446 +eval (validation): [5] Total time: 0:00:24 (0.3939 s / it) +cv: [5] best hparam: (1, 1.0) (024) ('024_lr1.0e+00_wd1.0e+00') loss: 0.034 acc: 0.991 f1: 0.990 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/eval_v2/hcpya_task21__patch__attn/checkpoint-best.pth +train: [6] [ 0/400] eta: 0:22:26 lr: nan time: 3.3668 data: 2.9777 max mem: 22446 +train: [6] [ 20/400] eta: 0:03:49 lr: 0.000296 loss: 0.4219 (0.4940) grad: 0.3535 (0.3510) time: 0.4648 data: 0.0035 max mem: 22446 +train: [6] [ 40/400] eta: 0:03:11 lr: 0.000296 loss: 0.4831 (0.5703) grad: 0.3535 (0.3557) time: 0.4588 data: 0.0037 max mem: 22446 +train: [6] [ 60/400] eta: 0:02:51 lr: 0.000296 loss: 0.4822 (0.5669) grad: 0.3796 (0.3737) time: 0.4483 data: 0.0035 max mem: 22446 +train: [6] [ 80/400] eta: 0:02:36 lr: 0.000295 loss: 0.4822 (0.5898) grad: 0.3903 (0.3850) time: 0.4462 data: 0.0036 max mem: 22446 +train: [6] [100/400] eta: 0:02:24 lr: 0.000295 loss: 0.4639 (0.5840) grad: 0.3549 (0.3814) time: 0.4497 data: 0.0035 max mem: 22446 +train: [6] [120/400] eta: 0:02:13 lr: 0.000295 loss: 0.4220 (0.5705) grad: 0.3549 (0.3812) time: 0.4476 data: 0.0035 max mem: 22446 +train: [6] [140/400] eta: 0:02:02 lr: 0.000294 loss: 0.3944 (0.5770) grad: 0.3862 (0.3872) time: 0.4445 data: 0.0036 max mem: 22446 +train: [6] [160/400] eta: 0:01:52 lr: 0.000294 loss: 0.4194 (0.5688) grad: 0.3969 (0.3877) time: 0.4468 data: 0.0035 max mem: 22446 +train: [6] [180/400] eta: 0:01:42 lr: 0.000293 loss: 0.4323 (0.5812) grad: 0.3969 (0.3898) time: 0.4483 data: 0.0035 max mem: 22446 +WARNING: classifier 48 (50, 1.0) diverged (loss=66.62 > 60.89) at step 1298. Freezing. +train: [6] [200/400] eta: 0:01:33 lr: 0.000293 loss: 0.5069 (0.6170) grad: 0.3978 (0.3896) time: 0.4606 data: 0.0037 max mem: 22446 +train: [6] [220/400] eta: 0:01:23 lr: 0.000292 loss: 0.4185 (0.6026) grad: 0.3579 (0.3841) time: 0.4452 data: 0.0034 max mem: 22446 +train: [6] [240/400] eta: 0:01:14 lr: 0.000292 loss: 0.4185 (0.5945) grad: 0.2939 (0.3756) time: 0.4582 data: 0.0034 max mem: 22446 +train: [6] [260/400] eta: 0:01:04 lr: 0.000291 loss: 0.4603 (0.5846) grad: 0.3023 (0.3743) time: 0.4605 data: 0.0035 max mem: 22446 +train: [6] [280/400] eta: 0:00:55 lr: 0.000291 loss: 0.4976 (0.5921) grad: 0.3645 (0.3735) time: 0.4468 data: 0.0035 max mem: 22446 +train: [6] [300/400] eta: 0:00:47 lr: 0.000290 loss: 0.5361 (0.5860) grad: 0.3002 (0.3687) time: 0.6348 data: 0.1748 max mem: 22446 +train: [6] [320/400] eta: 0:00:37 lr: 0.000290 loss: 0.4378 (0.5753) grad: 0.2810 (0.3627) time: 0.4442 data: 0.0028 max mem: 22446 +train: [6] [340/400] eta: 0:00:28 lr: 0.000289 loss: 0.3865 (0.5715) grad: 0.2710 (0.3575) time: 0.4612 data: 0.0037 max mem: 22446 +train: [6] [360/400] eta: 0:00:18 lr: 0.000288 loss: 0.4002 (0.5645) grad: 0.2774 (0.3529) time: 0.4672 data: 0.0036 max mem: 22446 +train: [6] [380/400] eta: 0:00:09 lr: 0.000288 loss: 0.3703 (0.5563) grad: 0.2774 (0.3487) time: 0.4569 data: 0.0036 max mem: 22446 +train: [6] [399/400] eta: 0:00:00 lr: 0.000287 loss: 0.3381 (0.5461) grad: 0.2558 (0.3445) time: 0.4601 data: 0.0034 max mem: 22446 +train: [6] Total time: 0:03:07 (0.4700 s / it) +train: [6] Summary: lr: 0.000287 loss: 0.3381 (0.5461) grad: 0.2558 (0.3445) +eval (validation): [6] [ 0/63] eta: 0:03:34 time: 3.4090 data: 3.1234 max mem: 22446 +eval (validation): [6] [20/63] eta: 0:00:22 time: 0.3736 data: 0.0038 max mem: 22446 +eval (validation): [6] [40/63] eta: 0:00:09 time: 0.3316 data: 0.0032 max mem: 22446 +eval (validation): [6] [60/63] eta: 0:00:01 time: 0.3393 data: 0.0032 max mem: 22446 +eval (validation): [6] [62/63] eta: 0:00:00 time: 0.3353 data: 0.0032 max mem: 22446 +eval (validation): [6] Total time: 0:00:25 (0.4014 s / it) +cv: [6] best hparam: (1.6, 1.0) (027) ('027_lr1.6e+00_wd1.0e+00') loss: 0.033 acc: 0.990 f1: 0.989 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [7] [ 0/400] eta: 0:22:16 lr: nan time: 3.3423 data: 3.0028 max mem: 22446 +train: [7] [ 20/400] eta: 0:03:44 lr: 0.000286 loss: 0.4114 (0.4719) grad: 0.2352 (0.2594) time: 0.4526 data: 0.0041 max mem: 22446 +train: [7] [ 40/400] eta: 0:03:07 lr: 0.000286 loss: 0.3823 (0.4218) grad: 0.2248 (0.2381) time: 0.4452 data: 0.0036 max mem: 22446 +train: [7] [ 60/400] eta: 0:02:48 lr: 0.000285 loss: 0.4520 (0.4639) grad: 0.2174 (0.2374) time: 0.4475 data: 0.0037 max mem: 22446 +train: [7] [ 80/400] eta: 0:02:35 lr: 0.000284 loss: 0.4162 (0.4454) grad: 0.2466 (0.2462) time: 0.4508 data: 0.0035 max mem: 22446 +train: [7] [100/400] eta: 0:02:23 lr: 0.000284 loss: 0.3371 (0.4409) grad: 0.2527 (0.2505) time: 0.4537 data: 0.0036 max mem: 22446 +train: [7] [120/400] eta: 0:02:12 lr: 0.000283 loss: 0.3910 (0.4357) grad: 0.2457 (0.2523) time: 0.4556 data: 0.0035 max mem: 22446 +train: [7] [140/400] eta: 0:02:02 lr: 0.000282 loss: 0.3910 (0.4400) grad: 0.2661 (0.2583) time: 0.4453 data: 0.0035 max mem: 22446 +train: [7] [160/400] eta: 0:01:52 lr: 0.000282 loss: 0.3878 (0.4440) grad: 0.3367 (0.2710) time: 0.4508 data: 0.0036 max mem: 22446 +train: [7] [180/400] eta: 0:01:42 lr: 0.000281 loss: 0.3430 (0.4354) grad: 0.2560 (0.2669) time: 0.4526 data: 0.0035 max mem: 22446 +train: [7] [200/400] eta: 0:01:32 lr: 0.000280 loss: 0.2992 (0.4268) grad: 0.2381 (0.2674) time: 0.4491 data: 0.0035 max mem: 22446 +train: [7] [220/400] eta: 0:01:23 lr: 0.000279 loss: 0.3117 (0.4249) grad: 0.2488 (0.2668) time: 0.4382 data: 0.0033 max mem: 22446 +train: [7] [240/400] eta: 0:01:13 lr: 0.000278 loss: 0.3419 (0.4247) grad: 0.2690 (0.2677) time: 0.4524 data: 0.0033 max mem: 22446 +train: [7] [260/400] eta: 0:01:04 lr: 0.000278 loss: 0.3693 (0.4221) grad: 0.2397 (0.2667) time: 0.4636 data: 0.0034 max mem: 22446 +train: [7] [280/400] eta: 0:00:55 lr: 0.000277 loss: 0.3798 (0.4259) grad: 0.2397 (0.2652) time: 0.4361 data: 0.0034 max mem: 22446 +train: [7] [300/400] eta: 0:00:47 lr: 0.000276 loss: 0.3798 (0.4260) grad: 0.2485 (0.2666) time: 0.6159 data: 0.1782 max mem: 22446 +train: [7] [320/400] eta: 0:00:37 lr: 0.000275 loss: 0.3560 (0.4252) grad: 0.2432 (0.2637) time: 0.4414 data: 0.0034 max mem: 22446 +train: [7] [340/400] eta: 0:00:28 lr: 0.000274 loss: 0.3100 (0.4198) grad: 0.2128 (0.2598) time: 0.4536 data: 0.0033 max mem: 22446 +train: [7] [360/400] eta: 0:00:18 lr: 0.000273 loss: 0.3025 (0.4145) grad: 0.1976 (0.2575) time: 0.4686 data: 0.0035 max mem: 22446 +train: [7] [380/400] eta: 0:00:09 lr: 0.000272 loss: 0.2804 (0.4077) grad: 0.1883 (0.2540) time: 0.4558 data: 0.0035 max mem: 22446 +train: [7] [399/400] eta: 0:00:00 lr: 0.000271 loss: 0.2676 (0.4027) grad: 0.1869 (0.2523) time: 0.4448 data: 0.0034 max mem: 22446 +train: [7] Total time: 0:03:06 (0.4663 s / it) +train: [7] Summary: lr: 0.000271 loss: 0.2676 (0.4027) grad: 0.1869 (0.2523) +eval (validation): [7] [ 0/63] eta: 0:03:31 time: 3.3517 data: 3.0693 max mem: 22446 +eval (validation): [7] [20/63] eta: 0:00:21 time: 0.3693 data: 0.0045 max mem: 22446 +eval (validation): [7] [40/63] eta: 0:00:09 time: 0.3476 data: 0.0031 max mem: 22446 +eval (validation): [7] [60/63] eta: 0:00:01 time: 0.3257 data: 0.0032 max mem: 22446 +eval (validation): [7] [62/63] eta: 0:00:00 time: 0.3270 data: 0.0031 max mem: 22446 +eval (validation): [7] Total time: 0:00:25 (0.3993 s / it) +cv: [7] best hparam: (1, 1.0) (024) ('024_lr1.0e+00_wd1.0e+00') loss: 0.034 acc: 0.990 f1: 0.988 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [8] [ 0/400] eta: 0:23:38 lr: nan time: 3.5458 data: 3.2027 max mem: 22446 +train: [8] [ 20/400] eta: 0:03:49 lr: 0.000270 loss: 0.2493 (0.2489) grad: 0.1538 (0.1654) time: 0.4570 data: 0.0025 max mem: 22446 +train: [8] [ 40/400] eta: 0:03:10 lr: 0.000270 loss: 0.2619 (0.2661) grad: 0.1548 (0.1638) time: 0.4493 data: 0.0031 max mem: 22446 +train: [8] [ 60/400] eta: 0:02:50 lr: 0.000269 loss: 0.2626 (0.2682) grad: 0.1694 (0.1613) time: 0.4486 data: 0.0036 max mem: 22446 +train: [8] [ 80/400] eta: 0:02:37 lr: 0.000268 loss: 0.2585 (0.2801) grad: 0.1694 (0.1715) time: 0.4562 data: 0.0035 max mem: 22446 +train: [8] [100/400] eta: 0:02:24 lr: 0.000267 loss: 0.2582 (0.2757) grad: 0.1582 (0.1688) time: 0.4498 data: 0.0035 max mem: 22446 +train: [8] [120/400] eta: 0:02:13 lr: 0.000266 loss: 0.2440 (0.2934) grad: 0.1508 (0.1755) time: 0.4425 data: 0.0036 max mem: 22446 +train: [8] [140/400] eta: 0:02:02 lr: 0.000265 loss: 0.2482 (0.2944) grad: 0.1899 (0.1779) time: 0.4448 data: 0.0034 max mem: 22446 +train: [8] [160/400] eta: 0:01:52 lr: 0.000264 loss: 0.2383 (0.2926) grad: 0.1607 (0.1770) time: 0.4472 data: 0.0034 max mem: 22446 +train: [8] [180/400] eta: 0:01:42 lr: 0.000263 loss: 0.2502 (0.2903) grad: 0.1545 (0.1777) time: 0.4474 data: 0.0036 max mem: 22446 +train: [8] [200/400] eta: 0:01:33 lr: 0.000262 loss: 0.2566 (0.2870) grad: 0.1444 (0.1749) time: 0.4540 data: 0.0036 max mem: 22446 +train: [8] [220/400] eta: 0:01:23 lr: 0.000260 loss: 0.2438 (0.2855) grad: 0.1440 (0.1731) time: 0.4488 data: 0.0035 max mem: 22446 +train: [8] [240/400] eta: 0:01:13 lr: 0.000259 loss: 0.2538 (0.2872) grad: 0.1706 (0.1736) time: 0.4467 data: 0.0034 max mem: 22446 +train: [8] [260/400] eta: 0:01:04 lr: 0.000258 loss: 0.2538 (0.2886) grad: 0.1706 (0.1742) time: 0.4622 data: 0.0036 max mem: 22446 +train: [8] [280/400] eta: 0:00:55 lr: 0.000257 loss: 0.2580 (0.2919) grad: 0.1725 (0.1742) time: 0.4581 data: 0.0035 max mem: 22446 +train: [8] [300/400] eta: 0:00:47 lr: 0.000256 loss: 0.3097 (0.2954) grad: 0.2030 (0.1769) time: 0.6070 data: 0.1791 max mem: 22446 +train: [8] [320/400] eta: 0:00:37 lr: 0.000255 loss: 0.2561 (0.2937) grad: 0.1939 (0.1753) time: 0.4381 data: 0.0033 max mem: 22446 +train: [8] [340/400] eta: 0:00:28 lr: 0.000254 loss: 0.2346 (0.2913) grad: 0.1246 (0.1737) time: 0.4416 data: 0.0035 max mem: 22446 +train: [8] [360/400] eta: 0:00:18 lr: 0.000253 loss: 0.2206 (0.2871) grad: 0.1338 (0.1729) time: 0.4580 data: 0.0036 max mem: 22446 +train: [8] [380/400] eta: 0:00:09 lr: 0.000252 loss: 0.1998 (0.2845) grad: 0.1364 (0.1709) time: 0.4659 data: 0.0036 max mem: 22446 +train: [8] [399/400] eta: 0:00:00 lr: 0.000250 loss: 0.2152 (0.2833) grad: 0.1410 (0.1701) time: 0.4511 data: 0.0034 max mem: 22446 +train: [8] Total time: 0:03:06 (0.4667 s / it) +train: [8] Summary: lr: 0.000250 loss: 0.2152 (0.2833) grad: 0.1410 (0.1701) +eval (validation): [8] [ 0/63] eta: 0:03:31 time: 3.3576 data: 3.0406 max mem: 22446 +eval (validation): [8] [20/63] eta: 0:00:23 time: 0.4029 data: 0.0032 max mem: 22446 +eval (validation): [8] [40/63] eta: 0:00:10 time: 0.3404 data: 0.0037 max mem: 22446 +eval (validation): [8] [60/63] eta: 0:00:01 time: 0.3114 data: 0.0029 max mem: 22446 +eval (validation): [8] [62/63] eta: 0:00:00 time: 0.3087 data: 0.0030 max mem: 22446 +eval (validation): [8] Total time: 0:00:25 (0.4028 s / it) +cv: [8] best hparam: (1.6, 1.0) (027) ('027_lr1.6e+00_wd1.0e+00') loss: 0.037 acc: 0.990 f1: 0.989 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [9] [ 0/400] eta: 0:22:54 lr: nan time: 3.4363 data: 3.0530 max mem: 22446 +train: [9] [ 20/400] eta: 0:03:52 lr: 0.000249 loss: 0.2343 (0.2499) grad: 0.1430 (0.1582) time: 0.4708 data: 0.0032 max mem: 22446 +train: [9] [ 40/400] eta: 0:03:10 lr: 0.000248 loss: 0.2343 (0.2525) grad: 0.1452 (0.1636) time: 0.4407 data: 0.0035 max mem: 22446 +train: [9] [ 60/400] eta: 0:02:50 lr: 0.000247 loss: 0.2341 (0.2504) grad: 0.1410 (0.1567) time: 0.4463 data: 0.0036 max mem: 22446 +train: [9] [ 80/400] eta: 0:02:36 lr: 0.000246 loss: 0.2335 (0.2456) grad: 0.1259 (0.1470) time: 0.4453 data: 0.0035 max mem: 22446 +train: [9] [100/400] eta: 0:02:23 lr: 0.000244 loss: 0.2204 (0.2430) grad: 0.1232 (0.1450) time: 0.4453 data: 0.0034 max mem: 22446 +train: [9] [120/400] eta: 0:02:12 lr: 0.000243 loss: 0.2269 (0.2447) grad: 0.1280 (0.1434) time: 0.4422 data: 0.0035 max mem: 22446 +train: [9] [140/400] eta: 0:02:02 lr: 0.000242 loss: 0.2185 (0.2417) grad: 0.1280 (0.1389) time: 0.4473 data: 0.0035 max mem: 22446 +train: [9] [160/400] eta: 0:01:51 lr: 0.000241 loss: 0.2053 (0.2388) grad: 0.1085 (0.1367) time: 0.4422 data: 0.0034 max mem: 22446 +train: [9] [180/400] eta: 0:01:41 lr: 0.000240 loss: 0.1886 (0.2349) grad: 0.1061 (0.1339) time: 0.4378 data: 0.0034 max mem: 22446 +train: [9] [200/400] eta: 0:01:32 lr: 0.000238 loss: 0.1877 (0.2333) grad: 0.1085 (0.1347) time: 0.4444 data: 0.0034 max mem: 22446 +train: [9] [220/400] eta: 0:01:22 lr: 0.000237 loss: 0.2097 (0.2331) grad: 0.1350 (0.1345) time: 0.4412 data: 0.0033 max mem: 22446 +train: [9] [240/400] eta: 0:01:13 lr: 0.000236 loss: 0.2122 (0.2314) grad: 0.1256 (0.1340) time: 0.4282 data: 0.0032 max mem: 22446 +train: [9] [260/400] eta: 0:01:03 lr: 0.000234 loss: 0.2083 (0.2306) grad: 0.1256 (0.1333) time: 0.4597 data: 0.0033 max mem: 22446 +train: [9] [280/400] eta: 0:00:54 lr: 0.000233 loss: 0.2111 (0.2307) grad: 0.1258 (0.1324) time: 0.4406 data: 0.0034 max mem: 22446 +train: [9] [300/400] eta: 0:00:46 lr: 0.000232 loss: 0.2051 (0.2309) grad: 0.1088 (0.1316) time: 0.6130 data: 0.1720 max mem: 22446 +train: [9] [320/400] eta: 0:00:37 lr: 0.000230 loss: 0.1908 (0.2284) grad: 0.1088 (0.1314) time: 0.4431 data: 0.0030 max mem: 22446 +train: [9] [340/400] eta: 0:00:27 lr: 0.000229 loss: 0.2030 (0.2295) grad: 0.1370 (0.1322) time: 0.4473 data: 0.0034 max mem: 22446 +train: [9] [360/400] eta: 0:00:18 lr: 0.000228 loss: 0.2030 (0.2280) grad: 0.1250 (0.1307) time: 0.4539 data: 0.0035 max mem: 22446 +train: [9] [380/400] eta: 0:00:09 lr: 0.000226 loss: 0.2001 (0.2268) grad: 0.1058 (0.1293) time: 0.4711 data: 0.0036 max mem: 22446 +train: [9] [399/400] eta: 0:00:00 lr: 0.000225 loss: 0.1953 (0.2253) grad: 0.0948 (0.1281) time: 0.4511 data: 0.0035 max mem: 22446 +train: [9] Total time: 0:03:05 (0.4633 s / it) +train: [9] Summary: lr: 0.000225 loss: 0.1953 (0.2253) grad: 0.0948 (0.1281) +eval (validation): [9] [ 0/63] eta: 0:03:15 time: 3.0981 data: 2.8540 max mem: 22446 +eval (validation): [9] [20/63] eta: 0:00:22 time: 0.3980 data: 0.0046 max mem: 22446 +eval (validation): [9] [40/63] eta: 0:00:10 time: 0.3506 data: 0.0036 max mem: 22446 +eval (validation): [9] [60/63] eta: 0:00:01 time: 0.3213 data: 0.0032 max mem: 22446 +eval (validation): [9] [62/63] eta: 0:00:00 time: 0.3149 data: 0.0032 max mem: 22446 +eval (validation): [9] Total time: 0:00:25 (0.4028 s / it) +cv: [9] best hparam: (0.72, 1.0) (022) ('022_lr7.2e-01_wd1.0e+00') loss: 0.031 acc: 0.991 f1: 0.989 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [10] [ 0/400] eta: 0:22:32 lr: nan time: 3.3819 data: 3.0046 max mem: 22446 +train: [10] [ 20/400] eta: 0:03:41 lr: 0.000224 loss: 0.2076 (0.2184) grad: 0.0932 (0.0995) time: 0.4422 data: 0.0025 max mem: 22446 +train: [10] [ 40/400] eta: 0:03:04 lr: 0.000222 loss: 0.1993 (0.2084) grad: 0.0932 (0.1024) time: 0.4386 data: 0.0035 max mem: 22446 +train: [10] [ 60/400] eta: 0:02:45 lr: 0.000221 loss: 0.1934 (0.2040) grad: 0.0855 (0.0966) time: 0.4340 data: 0.0036 max mem: 22446 +train: [10] [ 80/400] eta: 0:02:32 lr: 0.000220 loss: 0.1860 (0.2045) grad: 0.0961 (0.1040) time: 0.4425 data: 0.0037 max mem: 22446 +train: [10] [100/400] eta: 0:02:20 lr: 0.000218 loss: 0.1914 (0.2057) grad: 0.1309 (0.1079) time: 0.4404 data: 0.0035 max mem: 22446 +train: [10] [120/400] eta: 0:02:09 lr: 0.000217 loss: 0.2019 (0.2059) grad: 0.1137 (0.1088) time: 0.4418 data: 0.0036 max mem: 22446 +train: [10] [140/400] eta: 0:02:00 lr: 0.000215 loss: 0.2017 (0.2072) grad: 0.1052 (0.1091) time: 0.4472 data: 0.0036 max mem: 22446 +train: [10] [160/400] eta: 0:01:50 lr: 0.000214 loss: 0.1813 (0.2046) grad: 0.1052 (0.1082) time: 0.4380 data: 0.0036 max mem: 22446 +train: [10] [180/400] eta: 0:01:40 lr: 0.000213 loss: 0.1799 (0.2030) grad: 0.1059 (0.1071) time: 0.4436 data: 0.0036 max mem: 22446 +train: [10] [200/400] eta: 0:01:31 lr: 0.000211 loss: 0.1879 (0.2027) grad: 0.1059 (0.1075) time: 0.4472 data: 0.0035 max mem: 22446 +train: [10] [220/400] eta: 0:01:21 lr: 0.000210 loss: 0.1848 (0.2011) grad: 0.0931 (0.1050) time: 0.4402 data: 0.0034 max mem: 22446 +train: [10] [240/400] eta: 0:01:12 lr: 0.000208 loss: 0.1868 (0.2009) grad: 0.0766 (0.1048) time: 0.4345 data: 0.0034 max mem: 22446 +train: [10] [260/400] eta: 0:01:03 lr: 0.000207 loss: 0.1949 (0.2006) grad: 0.1139 (0.1064) time: 0.4603 data: 0.0037 max mem: 22446 +train: [10] [280/400] eta: 0:00:54 lr: 0.000205 loss: 0.1920 (0.1999) grad: 0.0974 (0.1046) time: 0.4486 data: 0.0036 max mem: 22446 +train: [10] [300/400] eta: 0:00:46 lr: 0.000204 loss: 0.1787 (0.1989) grad: 0.0901 (0.1040) time: 0.5983 data: 0.1728 max mem: 22446 +train: [10] [320/400] eta: 0:00:37 lr: 0.000202 loss: 0.1622 (0.1974) grad: 0.0849 (0.1023) time: 0.4734 data: 0.0032 max mem: 22446 +train: [10] [340/400] eta: 0:00:27 lr: 0.000201 loss: 0.1611 (0.1956) grad: 0.0700 (0.1012) time: 0.4396 data: 0.0032 max mem: 22446 +train: [10] [360/400] eta: 0:00:18 lr: 0.000199 loss: 0.1620 (0.1954) grad: 0.0799 (0.1004) time: 0.4388 data: 0.0036 max mem: 22446 +train: [10] [380/400] eta: 0:00:09 lr: 0.000198 loss: 0.1666 (0.1949) grad: 0.0839 (0.0994) time: 0.4650 data: 0.0035 max mem: 22446 +train: [10] [399/400] eta: 0:00:00 lr: 0.000196 loss: 0.1711 (0.1943) grad: 0.0728 (0.0981) time: 0.4442 data: 0.0033 max mem: 22446 +train: [10] Total time: 0:03:04 (0.4606 s / it) +train: [10] Summary: lr: 0.000196 loss: 0.1711 (0.1943) grad: 0.0728 (0.0981) +eval (validation): [10] [ 0/63] eta: 0:03:17 time: 3.1319 data: 2.8463 max mem: 22446 +eval (validation): [10] [20/63] eta: 0:00:22 time: 0.3999 data: 0.0036 max mem: 22446 +eval (validation): [10] [40/63] eta: 0:00:10 time: 0.3627 data: 0.0034 max mem: 22446 +eval (validation): [10] [60/63] eta: 0:00:01 time: 0.3261 data: 0.0033 max mem: 22446 +eval (validation): [10] [62/63] eta: 0:00:00 time: 0.3232 data: 0.0033 max mem: 22446 +eval (validation): [10] Total time: 0:00:25 (0.4091 s / it) +cv: [10] best hparam: (9.8, 1.0) (038) ('038_lr9.8e+00_wd1.0e+00') loss: 0.125 acc: 0.991 f1: 0.990 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [11] [ 0/400] eta: 0:22:22 lr: nan time: 3.3563 data: 3.0151 max mem: 22446 +train: [11] [ 20/400] eta: 0:03:39 lr: 0.000195 loss: 0.1684 (0.1786) grad: 0.0622 (0.0630) time: 0.4394 data: 0.0022 max mem: 22446 +train: [11] [ 40/400] eta: 0:03:04 lr: 0.000193 loss: 0.1684 (0.1764) grad: 0.0622 (0.0658) time: 0.4418 data: 0.0036 max mem: 22446 +train: [11] [ 60/400] eta: 0:02:45 lr: 0.000192 loss: 0.1800 (0.1776) grad: 0.0749 (0.0716) time: 0.4362 data: 0.0037 max mem: 22446 +train: [11] [ 80/400] eta: 0:02:32 lr: 0.000190 loss: 0.1723 (0.1748) grad: 0.0739 (0.0700) time: 0.4450 data: 0.0035 max mem: 22446 +train: [11] [100/400] eta: 0:02:20 lr: 0.000189 loss: 0.1620 (0.1738) grad: 0.0568 (0.0699) time: 0.4411 data: 0.0036 max mem: 22446 +train: [11] [120/400] eta: 0:02:10 lr: 0.000187 loss: 0.1660 (0.1736) grad: 0.0719 (0.0719) time: 0.4376 data: 0.0036 max mem: 22446 +train: [11] [140/400] eta: 0:01:59 lr: 0.000186 loss: 0.1744 (0.1746) grad: 0.0675 (0.0723) time: 0.4426 data: 0.0036 max mem: 22446 +train: [11] [160/400] eta: 0:01:50 lr: 0.000184 loss: 0.1687 (0.1747) grad: 0.0675 (0.0724) time: 0.4397 data: 0.0034 max mem: 22446 +train: [11] [180/400] eta: 0:01:40 lr: 0.000183 loss: 0.1667 (0.1750) grad: 0.0914 (0.0755) time: 0.4404 data: 0.0034 max mem: 22446 +train: [11] [200/400] eta: 0:01:30 lr: 0.000181 loss: 0.1588 (0.1745) grad: 0.0985 (0.0779) time: 0.4398 data: 0.0035 max mem: 22446 +train: [11] [220/400] eta: 0:01:21 lr: 0.000180 loss: 0.1582 (0.1733) grad: 0.0790 (0.0773) time: 0.4479 data: 0.0035 max mem: 22446 +train: [11] [240/400] eta: 0:01:12 lr: 0.000178 loss: 0.1589 (0.1729) grad: 0.0683 (0.0768) time: 0.4403 data: 0.0034 max mem: 22446 +train: [11] [260/400] eta: 0:01:03 lr: 0.000177 loss: 0.1650 (0.1726) grad: 0.0681 (0.0753) time: 0.4382 data: 0.0034 max mem: 22446 +train: [11] [280/400] eta: 0:00:54 lr: 0.000175 loss: 0.1703 (0.1729) grad: 0.0592 (0.0756) time: 0.4569 data: 0.0037 max mem: 22446 +train: [11] [300/400] eta: 0:00:46 lr: 0.000174 loss: 0.1753 (0.1727) grad: 0.0660 (0.0754) time: 0.5901 data: 0.1680 max mem: 22446 +train: [11] [320/400] eta: 0:00:36 lr: 0.000172 loss: 0.1656 (0.1722) grad: 0.0630 (0.0742) time: 0.4586 data: 0.0029 max mem: 22446 +train: [11] [340/400] eta: 0:00:27 lr: 0.000170 loss: 0.1653 (0.1718) grad: 0.0639 (0.0738) time: 0.4560 data: 0.0036 max mem: 22446 +train: [11] [360/400] eta: 0:00:18 lr: 0.000169 loss: 0.1578 (0.1712) grad: 0.0660 (0.0733) time: 0.4492 data: 0.0034 max mem: 22446 +train: [11] [380/400] eta: 0:00:09 lr: 0.000167 loss: 0.1575 (0.1708) grad: 0.0566 (0.0726) time: 0.4765 data: 0.0037 max mem: 22446 +train: [11] [399/400] eta: 0:00:00 lr: 0.000166 loss: 0.1618 (0.1708) grad: 0.0566 (0.0721) time: 0.4516 data: 0.0036 max mem: 22446 +train: [11] Total time: 0:03:04 (0.4609 s / it) +train: [11] Summary: lr: 0.000166 loss: 0.1618 (0.1708) grad: 0.0566 (0.0721) +eval (validation): [11] [ 0/63] eta: 0:03:18 time: 3.1483 data: 2.8625 max mem: 22446 +eval (validation): [11] [20/63] eta: 0:00:22 time: 0.3843 data: 0.0031 max mem: 22446 +eval (validation): [11] [40/63] eta: 0:00:10 time: 0.3970 data: 0.0038 max mem: 22446 +eval (validation): [11] [60/63] eta: 0:00:01 time: 0.3335 data: 0.0033 max mem: 22446 +eval (validation): [11] [62/63] eta: 0:00:00 time: 0.3233 data: 0.0032 max mem: 22446 +eval (validation): [11] Total time: 0:00:26 (0.4181 s / it) +cv: [11] best hparam: (3.7, 1.0) (032) ('032_lr3.7e+00_wd1.0e+00') loss: 0.044 acc: 0.992 f1: 0.990 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/eval_v2/hcpya_task21__patch__attn/checkpoint-best.pth +train: [12] [ 0/400] eta: 0:22:31 lr: nan time: 3.3786 data: 2.9920 max mem: 22446 +train: [12] [ 20/400] eta: 0:03:42 lr: 0.000164 loss: 0.1637 (0.1655) grad: 0.0571 (0.0634) time: 0.4472 data: 0.0029 max mem: 22446 +train: [12] [ 40/400] eta: 0:03:05 lr: 0.000163 loss: 0.1627 (0.1626) grad: 0.0577 (0.0641) time: 0.4427 data: 0.0032 max mem: 22446 +train: [12] [ 60/400] eta: 0:02:47 lr: 0.000161 loss: 0.1560 (0.1604) grad: 0.0552 (0.0611) time: 0.4396 data: 0.0035 max mem: 22446 +train: [12] [ 80/400] eta: 0:02:33 lr: 0.000160 loss: 0.1548 (0.1591) grad: 0.0487 (0.0594) time: 0.4463 data: 0.0035 max mem: 22446 +train: [12] [100/400] eta: 0:02:22 lr: 0.000158 loss: 0.1566 (0.1606) grad: 0.0486 (0.0582) time: 0.4466 data: 0.0033 max mem: 22446 +train: [12] [120/400] eta: 0:02:11 lr: 0.000156 loss: 0.1637 (0.1636) grad: 0.0513 (0.0591) time: 0.4526 data: 0.0034 max mem: 22446 +train: [12] [140/400] eta: 0:02:01 lr: 0.000155 loss: 0.1626 (0.1640) grad: 0.0645 (0.0606) time: 0.4470 data: 0.0034 max mem: 22446 +train: [12] [160/400] eta: 0:01:51 lr: 0.000153 loss: 0.1530 (0.1629) grad: 0.0614 (0.0605) time: 0.4499 data: 0.0034 max mem: 22446 +train: [12] [180/400] eta: 0:01:41 lr: 0.000152 loss: 0.1509 (0.1625) grad: 0.0515 (0.0598) time: 0.4460 data: 0.0035 max mem: 22446 +train: [12] [200/400] eta: 0:01:32 lr: 0.000150 loss: 0.1551 (0.1620) grad: 0.0534 (0.0598) time: 0.4433 data: 0.0034 max mem: 22446 +train: [12] [220/400] eta: 0:01:22 lr: 0.000149 loss: 0.1569 (0.1625) grad: 0.0599 (0.0601) time: 0.4458 data: 0.0035 max mem: 22446 +train: [12] [240/400] eta: 0:01:13 lr: 0.000147 loss: 0.1628 (0.1630) grad: 0.0656 (0.0605) time: 0.4354 data: 0.0034 max mem: 22446 +train: [12] [260/400] eta: 0:01:04 lr: 0.000145 loss: 0.1588 (0.1622) grad: 0.0576 (0.0597) time: 0.4615 data: 0.0035 max mem: 22446 +train: [12] [280/400] eta: 0:00:54 lr: 0.000144 loss: 0.1502 (0.1615) grad: 0.0526 (0.0597) time: 0.4523 data: 0.0036 max mem: 22446 +train: [12] [300/400] eta: 0:00:46 lr: 0.000142 loss: 0.1589 (0.1618) grad: 0.0526 (0.0596) time: 0.5993 data: 0.1717 max mem: 22446 +train: [12] [320/400] eta: 0:00:37 lr: 0.000141 loss: 0.1594 (0.1615) grad: 0.0492 (0.0592) time: 0.4483 data: 0.0034 max mem: 22446 +train: [12] [340/400] eta: 0:00:27 lr: 0.000139 loss: 0.1559 (0.1613) grad: 0.0488 (0.0585) time: 0.4436 data: 0.0035 max mem: 22446 +train: [12] [360/400] eta: 0:00:18 lr: 0.000138 loss: 0.1559 (0.1612) grad: 0.0452 (0.0583) time: 0.4445 data: 0.0036 max mem: 22446 +train: [12] [380/400] eta: 0:00:09 lr: 0.000136 loss: 0.1533 (0.1614) grad: 0.0450 (0.0580) time: 0.4702 data: 0.0035 max mem: 22446 +train: [12] [399/400] eta: 0:00:00 lr: 0.000134 loss: 0.1496 (0.1611) grad: 0.0438 (0.0574) time: 0.4539 data: 0.0036 max mem: 22446 +train: [12] Total time: 0:03:05 (0.4634 s / it) +train: [12] Summary: lr: 0.000134 loss: 0.1496 (0.1611) grad: 0.0438 (0.0574) +eval (validation): [12] [ 0/63] eta: 0:03:07 time: 2.9806 data: 2.7423 max mem: 22446 +eval (validation): [12] [20/63] eta: 0:00:22 time: 0.4061 data: 0.0044 max mem: 22446 +eval (validation): [12] [40/63] eta: 0:00:10 time: 0.3400 data: 0.0032 max mem: 22446 +eval (validation): [12] [60/63] eta: 0:00:01 time: 0.3226 data: 0.0032 max mem: 22446 +eval (validation): [12] [62/63] eta: 0:00:00 time: 0.3186 data: 0.0030 max mem: 22446 +eval (validation): [12] Total time: 0:00:25 (0.3994 s / it) +cv: [12] best hparam: (9.8, 1.0) (038) ('038_lr9.8e+00_wd1.0e+00') loss: 0.116 acc: 0.991 f1: 0.989 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [13] [ 0/400] eta: 0:22:08 lr: nan time: 3.3212 data: 2.9443 max mem: 22446 +train: [13] [ 20/400] eta: 0:03:49 lr: 0.000133 loss: 0.1657 (0.1576) grad: 0.0460 (0.0510) time: 0.4675 data: 0.0028 max mem: 22446 +train: [13] [ 40/400] eta: 0:03:09 lr: 0.000131 loss: 0.1442 (0.1506) grad: 0.0424 (0.0483) time: 0.4456 data: 0.0034 max mem: 22446 +train: [13] [ 60/400] eta: 0:02:49 lr: 0.000130 loss: 0.1398 (0.1495) grad: 0.0433 (0.0477) time: 0.4423 data: 0.0036 max mem: 22446 +train: [13] [ 80/400] eta: 0:02:34 lr: 0.000128 loss: 0.1497 (0.1506) grad: 0.0450 (0.0483) time: 0.4381 data: 0.0036 max mem: 22446 +train: [13] [100/400] eta: 0:02:22 lr: 0.000127 loss: 0.1475 (0.1500) grad: 0.0441 (0.0482) time: 0.4433 data: 0.0035 max mem: 22446 +train: [13] [120/400] eta: 0:02:11 lr: 0.000125 loss: 0.1455 (0.1506) grad: 0.0450 (0.0491) time: 0.4354 data: 0.0035 max mem: 22446 +train: [13] [140/400] eta: 0:02:00 lr: 0.000124 loss: 0.1455 (0.1513) grad: 0.0456 (0.0496) time: 0.4417 data: 0.0034 max mem: 22446 +train: [13] [160/400] eta: 0:01:51 lr: 0.000122 loss: 0.1396 (0.1504) grad: 0.0413 (0.0484) time: 0.4433 data: 0.0035 max mem: 22446 +train: [13] [180/400] eta: 0:01:41 lr: 0.000120 loss: 0.1478 (0.1511) grad: 0.0390 (0.0486) time: 0.4473 data: 0.0036 max mem: 22446 +train: [13] [200/400] eta: 0:01:31 lr: 0.000119 loss: 0.1554 (0.1517) grad: 0.0490 (0.0487) time: 0.4447 data: 0.0035 max mem: 22446 +train: [13] [220/400] eta: 0:01:22 lr: 0.000117 loss: 0.1522 (0.1519) grad: 0.0451 (0.0488) time: 0.4483 data: 0.0034 max mem: 22446 +train: [13] [240/400] eta: 0:01:12 lr: 0.000116 loss: 0.1454 (0.1515) grad: 0.0433 (0.0484) time: 0.4291 data: 0.0034 max mem: 22446 +train: [13] [260/400] eta: 0:01:03 lr: 0.000114 loss: 0.1454 (0.1514) grad: 0.0440 (0.0486) time: 0.4605 data: 0.0034 max mem: 22446 +train: [13] [280/400] eta: 0:00:54 lr: 0.000113 loss: 0.1464 (0.1510) grad: 0.0518 (0.0491) time: 0.4449 data: 0.0035 max mem: 22446 +train: [13] [300/400] eta: 0:00:46 lr: 0.000111 loss: 0.1440 (0.1509) grad: 0.0472 (0.0490) time: 0.5962 data: 0.1667 max mem: 22446 +train: [13] [320/400] eta: 0:00:37 lr: 0.000110 loss: 0.1486 (0.1510) grad: 0.0441 (0.0487) time: 0.4519 data: 0.0033 max mem: 22446 +train: [13] [340/400] eta: 0:00:27 lr: 0.000108 loss: 0.1486 (0.1506) grad: 0.0416 (0.0485) time: 0.4458 data: 0.0035 max mem: 22446 +train: [13] [360/400] eta: 0:00:18 lr: 0.000107 loss: 0.1357 (0.1499) grad: 0.0416 (0.0480) time: 0.4446 data: 0.0037 max mem: 22446 +train: [13] [380/400] eta: 0:00:09 lr: 0.000105 loss: 0.1406 (0.1497) grad: 0.0393 (0.0477) time: 0.4637 data: 0.0036 max mem: 22446 +train: [13] [399/400] eta: 0:00:00 lr: 0.000104 loss: 0.1500 (0.1499) grad: 0.0405 (0.0476) time: 0.4512 data: 0.0033 max mem: 22446 +train: [13] Total time: 0:03:04 (0.4617 s / it) +train: [13] Summary: lr: 0.000104 loss: 0.1500 (0.1499) grad: 0.0405 (0.0476) +eval (validation): [13] [ 0/63] eta: 0:03:16 time: 3.1128 data: 2.8716 max mem: 22446 +eval (validation): [13] [20/63] eta: 0:00:23 time: 0.4115 data: 0.0044 max mem: 22446 +eval (validation): [13] [40/63] eta: 0:00:10 time: 0.3365 data: 0.0029 max mem: 22446 +eval (validation): [13] [60/63] eta: 0:00:01 time: 0.3223 data: 0.0031 max mem: 22446 +eval (validation): [13] [62/63] eta: 0:00:00 time: 0.3177 data: 0.0031 max mem: 22446 +eval (validation): [13] Total time: 0:00:25 (0.4029 s / it) +cv: [13] best hparam: (0.52, 1.0) (020) ('020_lr5.2e-01_wd1.0e+00') loss: 0.032 acc: 0.990 f1: 0.989 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [14] [ 0/400] eta: 0:21:58 lr: nan time: 3.2964 data: 2.9515 max mem: 22446 +train: [14] [ 20/400] eta: 0:03:43 lr: 0.000102 loss: 0.1473 (0.1469) grad: 0.0396 (0.0396) time: 0.4534 data: 0.0027 max mem: 22446 +train: [14] [ 40/400] eta: 0:03:05 lr: 0.000101 loss: 0.1466 (0.1465) grad: 0.0429 (0.0444) time: 0.4401 data: 0.0033 max mem: 22446 +train: [14] [ 60/400] eta: 0:02:48 lr: 0.000099 loss: 0.1455 (0.1447) grad: 0.0435 (0.0443) time: 0.4493 data: 0.0035 max mem: 22446 +train: [14] [ 80/400] eta: 0:02:33 lr: 0.000098 loss: 0.1355 (0.1444) grad: 0.0422 (0.0450) time: 0.4373 data: 0.0034 max mem: 22446 +train: [14] [100/400] eta: 0:02:21 lr: 0.000096 loss: 0.1363 (0.1443) grad: 0.0417 (0.0454) time: 0.4436 data: 0.0034 max mem: 22446 +train: [14] [120/400] eta: 0:02:11 lr: 0.000095 loss: 0.1439 (0.1463) grad: 0.0406 (0.0448) time: 0.4420 data: 0.0034 max mem: 22446 +train: [14] [140/400] eta: 0:02:00 lr: 0.000093 loss: 0.1492 (0.1475) grad: 0.0434 (0.0463) time: 0.4494 data: 0.0034 max mem: 22446 +train: [14] [160/400] eta: 0:01:50 lr: 0.000092 loss: 0.1405 (0.1467) grad: 0.0420 (0.0456) time: 0.4403 data: 0.0035 max mem: 22446 +train: [14] [180/400] eta: 0:01:41 lr: 0.000090 loss: 0.1321 (0.1458) grad: 0.0396 (0.0451) time: 0.4394 data: 0.0034 max mem: 22446 +train: [14] [200/400] eta: 0:01:31 lr: 0.000089 loss: 0.1375 (0.1459) grad: 0.0395 (0.0446) time: 0.4412 data: 0.0034 max mem: 22446 +train: [14] [220/400] eta: 0:01:22 lr: 0.000088 loss: 0.1412 (0.1457) grad: 0.0395 (0.0443) time: 0.4427 data: 0.0034 max mem: 22446 +train: [14] [240/400] eta: 0:01:12 lr: 0.000086 loss: 0.1424 (0.1454) grad: 0.0385 (0.0441) time: 0.4295 data: 0.0033 max mem: 22446 +train: [14] [260/400] eta: 0:01:03 lr: 0.000085 loss: 0.1383 (0.1446) grad: 0.0396 (0.0441) time: 0.4583 data: 0.0034 max mem: 22446 +train: [14] [280/400] eta: 0:00:54 lr: 0.000083 loss: 0.1405 (0.1455) grad: 0.0447 (0.0441) time: 0.4416 data: 0.0034 max mem: 22446 +train: [14] [300/400] eta: 0:00:46 lr: 0.000082 loss: 0.1501 (0.1455) grad: 0.0431 (0.0443) time: 0.5913 data: 0.1687 max mem: 22446 +train: [14] [320/400] eta: 0:00:36 lr: 0.000081 loss: 0.1424 (0.1451) grad: 0.0402 (0.0440) time: 0.4568 data: 0.0033 max mem: 22446 +train: [14] [340/400] eta: 0:00:27 lr: 0.000079 loss: 0.1438 (0.1456) grad: 0.0382 (0.0438) time: 0.4397 data: 0.0034 max mem: 22446 +train: [14] [360/400] eta: 0:00:18 lr: 0.000078 loss: 0.1498 (0.1457) grad: 0.0421 (0.0441) time: 0.4427 data: 0.0035 max mem: 22446 +train: [14] [380/400] eta: 0:00:09 lr: 0.000076 loss: 0.1498 (0.1459) grad: 0.0434 (0.0441) time: 0.4674 data: 0.0035 max mem: 22446 +train: [14] [399/400] eta: 0:00:00 lr: 0.000075 loss: 0.1455 (0.1459) grad: 0.0424 (0.0441) time: 0.4504 data: 0.0034 max mem: 22446 +train: [14] Total time: 0:03:04 (0.4602 s / it) +train: [14] Summary: lr: 0.000075 loss: 0.1455 (0.1459) grad: 0.0424 (0.0441) +eval (validation): [14] [ 0/63] eta: 0:03:19 time: 3.1712 data: 2.8893 max mem: 22446 +eval (validation): [14] [20/63] eta: 0:00:22 time: 0.3977 data: 0.0031 max mem: 22446 +eval (validation): [14] [40/63] eta: 0:00:10 time: 0.3724 data: 0.0036 max mem: 22446 +eval (validation): [14] [60/63] eta: 0:00:01 time: 0.3217 data: 0.0032 max mem: 22446 +eval (validation): [14] [62/63] eta: 0:00:00 time: 0.3184 data: 0.0032 max mem: 22446 +eval (validation): [14] Total time: 0:00:25 (0.4109 s / it) +cv: [14] best hparam: (9.8, 1.0) (038) ('038_lr9.8e+00_wd1.0e+00') loss: 0.124 acc: 0.991 f1: 0.988 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [15] [ 0/400] eta: 0:22:35 lr: nan time: 3.3879 data: 2.9908 max mem: 22446 +train: [15] [ 20/400] eta: 0:03:49 lr: 0.000074 loss: 0.1457 (0.1468) grad: 0.0394 (0.0434) time: 0.4636 data: 0.0036 max mem: 22446 +train: [15] [ 40/400] eta: 0:03:08 lr: 0.000072 loss: 0.1477 (0.1461) grad: 0.0412 (0.0443) time: 0.4386 data: 0.0034 max mem: 22446 +train: [15] [ 60/400] eta: 0:02:48 lr: 0.000071 loss: 0.1372 (0.1419) grad: 0.0428 (0.0427) time: 0.4393 data: 0.0035 max mem: 22446 +train: [15] [ 80/400] eta: 0:02:34 lr: 0.000070 loss: 0.1323 (0.1414) grad: 0.0373 (0.0418) time: 0.4384 data: 0.0036 max mem: 22446 +train: [15] [100/400] eta: 0:02:23 lr: 0.000068 loss: 0.1325 (0.1403) grad: 0.0374 (0.0417) time: 0.4580 data: 0.0036 max mem: 22446 +train: [15] [120/400] eta: 0:02:11 lr: 0.000067 loss: 0.1300 (0.1395) grad: 0.0383 (0.0415) time: 0.4445 data: 0.0035 max mem: 22446 +train: [15] [140/400] eta: 0:02:01 lr: 0.000066 loss: 0.1366 (0.1399) grad: 0.0408 (0.0412) time: 0.4378 data: 0.0035 max mem: 22446 +train: [15] [160/400] eta: 0:01:51 lr: 0.000064 loss: 0.1364 (0.1394) grad: 0.0419 (0.0414) time: 0.4406 data: 0.0035 max mem: 22446 +train: [15] [180/400] eta: 0:01:41 lr: 0.000063 loss: 0.1348 (0.1397) grad: 0.0395 (0.0412) time: 0.4378 data: 0.0033 max mem: 22446 +train: [15] [200/400] eta: 0:01:31 lr: 0.000062 loss: 0.1443 (0.1406) grad: 0.0395 (0.0413) time: 0.4421 data: 0.0034 max mem: 22446 +train: [15] [220/400] eta: 0:01:22 lr: 0.000061 loss: 0.1407 (0.1401) grad: 0.0419 (0.0413) time: 0.4431 data: 0.0035 max mem: 22446 +train: [15] [240/400] eta: 0:01:12 lr: 0.000059 loss: 0.1359 (0.1400) grad: 0.0413 (0.0414) time: 0.4314 data: 0.0033 max mem: 22446 +train: [15] [260/400] eta: 0:01:03 lr: 0.000058 loss: 0.1362 (0.1403) grad: 0.0393 (0.0410) time: 0.4568 data: 0.0033 max mem: 22446 +train: [15] [280/400] eta: 0:00:54 lr: 0.000057 loss: 0.1318 (0.1403) grad: 0.0364 (0.0411) time: 0.4544 data: 0.0036 max mem: 22446 +train: [15] [300/400] eta: 0:00:46 lr: 0.000056 loss: 0.1341 (0.1402) grad: 0.0381 (0.0410) time: 0.6055 data: 0.1718 max mem: 22446 +train: [15] [320/400] eta: 0:00:37 lr: 0.000054 loss: 0.1341 (0.1399) grad: 0.0384 (0.0411) time: 0.4450 data: 0.0033 max mem: 22446 +train: [15] [340/400] eta: 0:00:27 lr: 0.000053 loss: 0.1332 (0.1401) grad: 0.0400 (0.0414) time: 0.4391 data: 0.0030 max mem: 22446 +train: [15] [360/400] eta: 0:00:18 lr: 0.000052 loss: 0.1331 (0.1403) grad: 0.0405 (0.0414) time: 0.4460 data: 0.0034 max mem: 22446 +train: [15] [380/400] eta: 0:00:09 lr: 0.000051 loss: 0.1331 (0.1399) grad: 0.0393 (0.0412) time: 0.4725 data: 0.0036 max mem: 22446 +train: [15] [399/400] eta: 0:00:00 lr: 0.000050 loss: 0.1372 (0.1403) grad: 0.0372 (0.0411) time: 0.4478 data: 0.0037 max mem: 22446 +train: [15] Total time: 0:03:04 (0.4617 s / it) +train: [15] Summary: lr: 0.000050 loss: 0.1372 (0.1403) grad: 0.0372 (0.0411) +eval (validation): [15] [ 0/63] eta: 0:03:16 time: 3.1139 data: 2.8599 max mem: 22446 +eval (validation): [15] [20/63] eta: 0:00:21 time: 0.3628 data: 0.0032 max mem: 22446 +eval (validation): [15] [40/63] eta: 0:00:09 time: 0.3294 data: 0.0033 max mem: 22446 +eval (validation): [15] [60/63] eta: 0:00:01 time: 0.3205 data: 0.0027 max mem: 22446 +eval (validation): [15] [62/63] eta: 0:00:00 time: 0.3190 data: 0.0030 max mem: 22446 +eval (validation): [15] Total time: 0:00:24 (0.3854 s / it) +cv: [15] best hparam: (9.8, 1.0) (038) ('038_lr9.8e+00_wd1.0e+00') loss: 0.118 acc: 0.991 f1: 0.988 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [16] [ 0/400] eta: 0:22:12 lr: nan time: 3.3317 data: 2.9550 max mem: 22446 +train: [16] [ 20/400] eta: 0:03:41 lr: 0.000048 loss: 0.1362 (0.1421) grad: 0.0378 (0.0403) time: 0.4455 data: 0.0033 max mem: 22446 +train: [16] [ 40/400] eta: 0:03:04 lr: 0.000047 loss: 0.1372 (0.1413) grad: 0.0378 (0.0403) time: 0.4376 data: 0.0037 max mem: 22446 +train: [16] [ 60/400] eta: 0:02:46 lr: 0.000046 loss: 0.1399 (0.1402) grad: 0.0358 (0.0390) time: 0.4405 data: 0.0038 max mem: 22446 +train: [16] [ 80/400] eta: 0:02:33 lr: 0.000045 loss: 0.1399 (0.1406) grad: 0.0353 (0.0388) time: 0.4465 data: 0.0036 max mem: 22446 +train: [16] [100/400] eta: 0:02:21 lr: 0.000044 loss: 0.1361 (0.1405) grad: 0.0373 (0.0389) time: 0.4451 data: 0.0034 max mem: 22446 +train: [16] [120/400] eta: 0:02:10 lr: 0.000043 loss: 0.1318 (0.1400) grad: 0.0376 (0.0393) time: 0.4435 data: 0.0035 max mem: 22446 +train: [16] [140/400] eta: 0:02:00 lr: 0.000042 loss: 0.1335 (0.1402) grad: 0.0406 (0.0400) time: 0.4462 data: 0.0034 max mem: 22446 +train: [16] [160/400] eta: 0:01:50 lr: 0.000041 loss: 0.1402 (0.1399) grad: 0.0394 (0.0401) time: 0.4392 data: 0.0035 max mem: 22446 +train: [16] [180/400] eta: 0:01:40 lr: 0.000040 loss: 0.1383 (0.1401) grad: 0.0393 (0.0398) time: 0.4403 data: 0.0035 max mem: 22446 +train: [16] [200/400] eta: 0:01:31 lr: 0.000039 loss: 0.1381 (0.1410) grad: 0.0398 (0.0405) time: 0.4440 data: 0.0034 max mem: 22446 +train: [16] [220/400] eta: 0:01:22 lr: 0.000038 loss: 0.1407 (0.1409) grad: 0.0398 (0.0401) time: 0.4394 data: 0.0036 max mem: 22446 +train: [16] [240/400] eta: 0:01:12 lr: 0.000036 loss: 0.1354 (0.1403) grad: 0.0360 (0.0397) time: 0.4318 data: 0.0034 max mem: 22446 +train: [16] [260/400] eta: 0:01:03 lr: 0.000035 loss: 0.1354 (0.1406) grad: 0.0372 (0.0398) time: 0.4554 data: 0.0033 max mem: 22446 +train: [16] [280/400] eta: 0:00:54 lr: 0.000034 loss: 0.1368 (0.1403) grad: 0.0400 (0.0402) time: 0.4537 data: 0.0035 max mem: 22446 +train: [16] [300/400] eta: 0:00:46 lr: 0.000033 loss: 0.1332 (0.1405) grad: 0.0410 (0.0404) time: 0.5973 data: 0.1700 max mem: 22446 +train: [16] [320/400] eta: 0:00:37 lr: 0.000032 loss: 0.1367 (0.1404) grad: 0.0433 (0.0405) time: 0.4742 data: 0.0035 max mem: 22446 +train: [16] [340/400] eta: 0:00:27 lr: 0.000031 loss: 0.1437 (0.1407) grad: 0.0419 (0.0407) time: 0.4434 data: 0.0033 max mem: 22446 +train: [16] [360/400] eta: 0:00:18 lr: 0.000031 loss: 0.1366 (0.1404) grad: 0.0365 (0.0405) time: 0.4422 data: 0.0036 max mem: 22446 +train: [16] [380/400] eta: 0:00:09 lr: 0.000030 loss: 0.1323 (0.1400) grad: 0.0365 (0.0404) time: 0.4758 data: 0.0035 max mem: 22446 +train: [16] [399/400] eta: 0:00:00 lr: 0.000029 loss: 0.1304 (0.1399) grad: 0.0416 (0.0406) time: 0.4512 data: 0.0034 max mem: 22446 +train: [16] Total time: 0:03:04 (0.4621 s / it) +train: [16] Summary: lr: 0.000029 loss: 0.1304 (0.1399) grad: 0.0416 (0.0406) +eval (validation): [16] [ 0/63] eta: 0:03:16 time: 3.1177 data: 2.8822 max mem: 22446 +eval (validation): [16] [20/63] eta: 0:00:20 time: 0.3552 data: 0.0030 max mem: 22446 +eval (validation): [16] [40/63] eta: 0:00:09 time: 0.3391 data: 0.0032 max mem: 22446 +eval (validation): [16] [60/63] eta: 0:00:01 time: 0.3312 data: 0.0034 max mem: 22446 +eval (validation): [16] [62/63] eta: 0:00:00 time: 0.3270 data: 0.0033 max mem: 22446 +eval (validation): [16] Total time: 0:00:24 (0.3888 s / it) +cv: [16] best hparam: (9.8, 1.0) (038) ('038_lr9.8e+00_wd1.0e+00') loss: 0.117 acc: 0.991 f1: 0.988 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [17] [ 0/400] eta: 0:21:44 lr: nan time: 3.2622 data: 2.9234 max mem: 22446 +train: [17] [ 20/400] eta: 0:03:43 lr: 0.000028 loss: 0.1272 (0.1343) grad: 0.0376 (0.0393) time: 0.4538 data: 0.0029 max mem: 22446 +train: [17] [ 40/400] eta: 0:03:05 lr: 0.000027 loss: 0.1350 (0.1390) grad: 0.0381 (0.0405) time: 0.4386 data: 0.0032 max mem: 22446 +train: [17] [ 60/400] eta: 0:02:47 lr: 0.000026 loss: 0.1433 (0.1416) grad: 0.0380 (0.0396) time: 0.4499 data: 0.0037 max mem: 22446 +train: [17] [ 80/400] eta: 0:02:34 lr: 0.000025 loss: 0.1443 (0.1423) grad: 0.0380 (0.0396) time: 0.4449 data: 0.0036 max mem: 22446 +train: [17] [100/400] eta: 0:02:22 lr: 0.000024 loss: 0.1376 (0.1411) grad: 0.0381 (0.0394) time: 0.4437 data: 0.0036 max mem: 22446 +train: [17] [120/400] eta: 0:02:11 lr: 0.000023 loss: 0.1370 (0.1409) grad: 0.0366 (0.0391) time: 0.4409 data: 0.0035 max mem: 22446 +train: [17] [140/400] eta: 0:02:00 lr: 0.000023 loss: 0.1409 (0.1409) grad: 0.0363 (0.0396) time: 0.4428 data: 0.0034 max mem: 22446 +train: [17] [160/400] eta: 0:01:50 lr: 0.000022 loss: 0.1377 (0.1404) grad: 0.0381 (0.0397) time: 0.4374 data: 0.0035 max mem: 22446 +train: [17] [180/400] eta: 0:01:41 lr: 0.000021 loss: 0.1351 (0.1399) grad: 0.0397 (0.0395) time: 0.4407 data: 0.0036 max mem: 22446 +train: [17] [200/400] eta: 0:01:31 lr: 0.000020 loss: 0.1299 (0.1396) grad: 0.0383 (0.0395) time: 0.4446 data: 0.0036 max mem: 22446 +train: [17] [220/400] eta: 0:01:22 lr: 0.000019 loss: 0.1313 (0.1394) grad: 0.0376 (0.0394) time: 0.4494 data: 0.0035 max mem: 22446 +train: [17] [240/400] eta: 0:01:12 lr: 0.000019 loss: 0.1316 (0.1393) grad: 0.0362 (0.0396) time: 0.4384 data: 0.0034 max mem: 22446 +train: [17] [260/400] eta: 0:01:03 lr: 0.000018 loss: 0.1371 (0.1395) grad: 0.0400 (0.0396) time: 0.4438 data: 0.0034 max mem: 22446 +train: [17] [280/400] eta: 0:00:54 lr: 0.000017 loss: 0.1375 (0.1394) grad: 0.0377 (0.0394) time: 0.4604 data: 0.0035 max mem: 22446 +train: [17] [300/400] eta: 0:00:46 lr: 0.000016 loss: 0.1335 (0.1393) grad: 0.0377 (0.0396) time: 0.6087 data: 0.1699 max mem: 22446 +train: [17] [320/400] eta: 0:00:37 lr: 0.000016 loss: 0.1322 (0.1393) grad: 0.0418 (0.0397) time: 0.4533 data: 0.0044 max mem: 22446 +train: [17] [340/400] eta: 0:00:27 lr: 0.000015 loss: 0.1357 (0.1392) grad: 0.0372 (0.0395) time: 0.4570 data: 0.0035 max mem: 22446 +train: [17] [360/400] eta: 0:00:18 lr: 0.000014 loss: 0.1334 (0.1388) grad: 0.0357 (0.0393) time: 0.4508 data: 0.0034 max mem: 22446 +train: [17] [380/400] eta: 0:00:09 lr: 0.000014 loss: 0.1331 (0.1390) grad: 0.0357 (0.0392) time: 0.4730 data: 0.0035 max mem: 22446 +train: [17] [399/400] eta: 0:00:00 lr: 0.000013 loss: 0.1331 (0.1388) grad: 0.0377 (0.0392) time: 0.4535 data: 0.0034 max mem: 22446 +train: [17] Total time: 0:03:05 (0.4636 s / it) +train: [17] Summary: lr: 0.000013 loss: 0.1331 (0.1388) grad: 0.0377 (0.0392) +eval (validation): [17] [ 0/63] eta: 0:03:17 time: 3.1411 data: 2.8615 max mem: 22446 +eval (validation): [17] [20/63] eta: 0:00:22 time: 0.3830 data: 0.0033 max mem: 22446 +eval (validation): [17] [40/63] eta: 0:00:10 time: 0.3515 data: 0.0034 max mem: 22446 +eval (validation): [17] [60/63] eta: 0:00:01 time: 0.3289 data: 0.0033 max mem: 22446 +eval (validation): [17] [62/63] eta: 0:00:00 time: 0.3279 data: 0.0033 max mem: 22446 +eval (validation): [17] Total time: 0:00:25 (0.4019 s / it) +cv: [17] best hparam: (0.52, 1.0) (020) ('020_lr5.2e-01_wd1.0e+00') loss: 0.032 acc: 0.991 f1: 0.990 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [18] [ 0/400] eta: 0:22:18 lr: nan time: 3.3458 data: 2.9598 max mem: 22446 +train: [18] [ 20/400] eta: 0:03:44 lr: 0.000012 loss: 0.1279 (0.1361) grad: 0.0333 (0.0378) time: 0.4534 data: 0.0034 max mem: 22446 +train: [18] [ 40/400] eta: 0:03:06 lr: 0.000012 loss: 0.1336 (0.1400) grad: 0.0355 (0.0387) time: 0.4429 data: 0.0036 max mem: 22446 +train: [18] [ 60/400] eta: 0:02:47 lr: 0.000011 loss: 0.1337 (0.1390) grad: 0.0385 (0.0388) time: 0.4391 data: 0.0038 max mem: 22446 +train: [18] [ 80/400] eta: 0:02:33 lr: 0.000011 loss: 0.1384 (0.1397) grad: 0.0385 (0.0389) time: 0.4455 data: 0.0037 max mem: 22446 +train: [18] [100/400] eta: 0:02:22 lr: 0.000010 loss: 0.1354 (0.1397) grad: 0.0386 (0.0390) time: 0.4443 data: 0.0035 max mem: 22446 +train: [18] [120/400] eta: 0:02:11 lr: 0.000009 loss: 0.1293 (0.1377) grad: 0.0379 (0.0387) time: 0.4409 data: 0.0036 max mem: 22446 +train: [18] [140/400] eta: 0:02:00 lr: 0.000009 loss: 0.1348 (0.1385) grad: 0.0380 (0.0391) time: 0.4442 data: 0.0036 max mem: 22446 +train: [18] [160/400] eta: 0:01:51 lr: 0.000008 loss: 0.1372 (0.1382) grad: 0.0380 (0.0391) time: 0.4566 data: 0.0037 max mem: 22446 +train: [18] [180/400] eta: 0:01:41 lr: 0.000008 loss: 0.1314 (0.1377) grad: 0.0391 (0.0394) time: 0.4450 data: 0.0035 max mem: 22446 +train: [18] [200/400] eta: 0:01:32 lr: 0.000007 loss: 0.1316 (0.1375) grad: 0.0397 (0.0394) time: 0.4466 data: 0.0035 max mem: 22446 +train: [18] [220/400] eta: 0:01:22 lr: 0.000007 loss: 0.1316 (0.1374) grad: 0.0384 (0.0393) time: 0.4419 data: 0.0035 max mem: 22446 +train: [18] [240/400] eta: 0:01:13 lr: 0.000006 loss: 0.1338 (0.1373) grad: 0.0392 (0.0393) time: 0.4395 data: 0.0035 max mem: 22446 +train: [18] [260/400] eta: 0:01:03 lr: 0.000006 loss: 0.1348 (0.1376) grad: 0.0377 (0.0392) time: 0.4504 data: 0.0035 max mem: 22446 +train: [18] [280/400] eta: 0:00:54 lr: 0.000006 loss: 0.1362 (0.1378) grad: 0.0405 (0.0394) time: 0.4635 data: 0.0037 max mem: 22446 +train: [18] [300/400] eta: 0:00:46 lr: 0.000005 loss: 0.1362 (0.1374) grad: 0.0407 (0.0396) time: 0.5959 data: 0.1701 max mem: 22446 +train: [18] [320/400] eta: 0:00:37 lr: 0.000005 loss: 0.1350 (0.1372) grad: 0.0389 (0.0396) time: 0.4452 data: 0.0034 max mem: 22446 +train: [18] [340/400] eta: 0:00:27 lr: 0.000004 loss: 0.1343 (0.1374) grad: 0.0370 (0.0395) time: 0.4541 data: 0.0035 max mem: 22446 +train: [18] [360/400] eta: 0:00:18 lr: 0.000004 loss: 0.1326 (0.1371) grad: 0.0367 (0.0396) time: 0.4524 data: 0.0037 max mem: 22446 +train: [18] [380/400] eta: 0:00:09 lr: 0.000004 loss: 0.1315 (0.1367) grad: 0.0358 (0.0394) time: 0.4673 data: 0.0037 max mem: 22446 +train: [18] [399/400] eta: 0:00:00 lr: 0.000003 loss: 0.1281 (0.1364) grad: 0.0363 (0.0394) time: 0.4557 data: 0.0036 max mem: 22446 +train: [18] Total time: 0:03:05 (0.4637 s / it) +train: [18] Summary: lr: 0.000003 loss: 0.1281 (0.1364) grad: 0.0363 (0.0394) +eval (validation): [18] [ 0/63] eta: 0:03:20 time: 3.1782 data: 2.9353 max mem: 22446 +eval (validation): [18] [20/63] eta: 0:00:21 time: 0.3694 data: 0.0032 max mem: 22446 +eval (validation): [18] [40/63] eta: 0:00:10 time: 0.3638 data: 0.0032 max mem: 22446 +eval (validation): [18] [60/63] eta: 0:00:01 time: 0.3251 data: 0.0034 max mem: 22446 +eval (validation): [18] [62/63] eta: 0:00:00 time: 0.3179 data: 0.0034 max mem: 22446 +eval (validation): [18] Total time: 0:00:25 (0.4022 s / it) +cv: [18] best hparam: (0.44, 1.0) (019) ('019_lr4.4e-01_wd1.0e+00') loss: 0.032 acc: 0.991 f1: 0.989 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [19] [ 0/400] eta: 0:22:11 lr: nan time: 3.3295 data: 2.9307 max mem: 22446 +train: [19] [ 20/400] eta: 0:03:48 lr: 0.000003 loss: 0.1347 (0.1360) grad: 0.0359 (0.0368) time: 0.4656 data: 0.0036 max mem: 22446 +train: [19] [ 40/400] eta: 0:03:09 lr: 0.000003 loss: 0.1347 (0.1369) grad: 0.0366 (0.0390) time: 0.4479 data: 0.0035 max mem: 22446 +train: [19] [ 60/400] eta: 0:02:49 lr: 0.000002 loss: 0.1333 (0.1365) grad: 0.0379 (0.0383) time: 0.4445 data: 0.0035 max mem: 22446 +train: [19] [ 80/400] eta: 0:02:36 lr: 0.000002 loss: 0.1333 (0.1376) grad: 0.0380 (0.0390) time: 0.4522 data: 0.0034 max mem: 22446 +train: [19] [100/400] eta: 0:02:23 lr: 0.000002 loss: 0.1372 (0.1387) grad: 0.0374 (0.0385) time: 0.4431 data: 0.0035 max mem: 22446 +train: [19] [120/400] eta: 0:02:12 lr: 0.000002 loss: 0.1324 (0.1377) grad: 0.0363 (0.0384) time: 0.4394 data: 0.0035 max mem: 22446 +train: [19] [140/400] eta: 0:02:01 lr: 0.000001 loss: 0.1303 (0.1370) grad: 0.0368 (0.0385) time: 0.4414 data: 0.0036 max mem: 22446 +train: [19] [160/400] eta: 0:01:51 lr: 0.000001 loss: 0.1341 (0.1372) grad: 0.0353 (0.0382) time: 0.4436 data: 0.0035 max mem: 22446 +train: [19] [180/400] eta: 0:01:41 lr: 0.000001 loss: 0.1359 (0.1375) grad: 0.0365 (0.0383) time: 0.4438 data: 0.0034 max mem: 22446 +train: [19] [200/400] eta: 0:01:32 lr: 0.000001 loss: 0.1347 (0.1375) grad: 0.0378 (0.0385) time: 0.4402 data: 0.0034 max mem: 22446 +train: [19] [220/400] eta: 0:01:22 lr: 0.000001 loss: 0.1347 (0.1380) grad: 0.0378 (0.0386) time: 0.4397 data: 0.0035 max mem: 22446 +train: [19] [240/400] eta: 0:01:13 lr: 0.000001 loss: 0.1347 (0.1376) grad: 0.0377 (0.0385) time: 0.4423 data: 0.0034 max mem: 22446 +train: [19] [260/400] eta: 0:01:03 lr: 0.000000 loss: 0.1303 (0.1373) grad: 0.0378 (0.0384) time: 0.4445 data: 0.0034 max mem: 22446 +train: [19] [280/400] eta: 0:00:54 lr: 0.000000 loss: 0.1340 (0.1377) grad: 0.0396 (0.0386) time: 0.4770 data: 0.0037 max mem: 22446 +train: [19] [300/400] eta: 0:00:46 lr: 0.000000 loss: 0.1379 (0.1377) grad: 0.0384 (0.0387) time: 0.5979 data: 0.1706 max mem: 22446 +train: [19] [320/400] eta: 0:00:37 lr: 0.000000 loss: 0.1352 (0.1376) grad: 0.0404 (0.0389) time: 0.4559 data: 0.0032 max mem: 22446 +train: [19] [340/400] eta: 0:00:27 lr: 0.000000 loss: 0.1307 (0.1372) grad: 0.0404 (0.0389) time: 0.4429 data: 0.0035 max mem: 22446 +train: [19] [360/400] eta: 0:00:18 lr: 0.000000 loss: 0.1306 (0.1373) grad: 0.0388 (0.0391) time: 0.4437 data: 0.0036 max mem: 22446 +train: [19] [380/400] eta: 0:00:09 lr: 0.000000 loss: 0.1306 (0.1372) grad: 0.0392 (0.0390) time: 0.4693 data: 0.0037 max mem: 22446 +train: [19] [399/400] eta: 0:00:00 lr: 0.000000 loss: 0.1306 (0.1370) grad: 0.0364 (0.0390) time: 0.4633 data: 0.0034 max mem: 22446 +train: [19] Total time: 0:03:05 (0.4644 s / it) +train: [19] Summary: lr: 0.000000 loss: 0.1306 (0.1370) grad: 0.0364 (0.0390) +eval (validation): [19] [ 0/63] eta: 0:03:22 time: 3.2077 data: 2.9341 max mem: 22446 +eval (validation): [19] [20/63] eta: 0:00:21 time: 0.3748 data: 0.0029 max mem: 22446 +eval (validation): [19] [40/63] eta: 0:00:10 time: 0.3833 data: 0.0036 max mem: 22446 +eval (validation): [19] [60/63] eta: 0:00:01 time: 0.3445 data: 0.0033 max mem: 22446 +eval (validation): [19] [62/63] eta: 0:00:00 time: 0.3392 data: 0.0033 max mem: 22446 +eval (validation): [19] Total time: 0:00:26 (0.4156 s / it) +cv: [19] best hparam: (0.52, 1.0) (020) ('020_lr5.2e-01_wd1.0e+00') loss: 0.032 acc: 0.991 f1: 0.990 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +evaluating last checkpoint: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +eval model info: +{"score": 0.9908234126984127, "hparam": [0.52, 1.0], "hparam_id": 20, "epoch": 19, "is_best": false, "best_score": 0.9915674603174603} +eval (train): [20] [ 0/297] eta: 0:14:56 time: 3.0198 data: 2.7471 max mem: 22446 +eval (train): [20] [ 20/297] eta: 0:02:13 time: 0.3556 data: 0.0031 max mem: 22446 +eval (train): [20] [ 40/297] eta: 0:01:50 time: 0.3752 data: 0.0035 max mem: 22446 +eval (train): [20] [ 60/297] eta: 0:01:36 time: 0.3629 data: 0.0034 max mem: 22446 +eval (train): [20] [ 80/297] eta: 0:01:26 time: 0.3728 data: 0.0038 max mem: 22446 +eval (train): [20] [100/297] eta: 0:01:17 time: 0.3641 data: 0.0038 max mem: 22446 +eval (train): [20] [120/297] eta: 0:01:08 time: 0.3598 data: 0.0036 max mem: 22446 +eval (train): [20] [140/297] eta: 0:01:00 time: 0.3568 data: 0.0035 max mem: 22446 +eval (train): [20] [160/297] eta: 0:00:52 time: 0.3693 data: 0.0037 max mem: 22446 +eval (train): [20] [180/297] eta: 0:00:44 time: 0.3751 data: 0.0036 max mem: 22446 +eval (train): [20] [200/297] eta: 0:00:36 time: 0.3670 data: 0.0037 max mem: 22446 +eval (train): [20] [220/297] eta: 0:00:29 time: 0.3614 data: 0.0036 max mem: 22446 +eval (train): [20] [240/297] eta: 0:00:21 time: 0.3356 data: 0.0033 max mem: 22446 +eval (train): [20] [260/297] eta: 0:00:13 time: 0.3658 data: 0.0034 max mem: 22446 +eval (train): [20] [280/297] eta: 0:00:06 time: 0.3744 data: 0.0035 max mem: 22446 +eval (train): [20] [296/297] eta: 0:00:00 time: 0.3429 data: 0.0034 max mem: 22446 +eval (train): [20] Total time: 0:01:50 (0.3735 s / it) +eval (validation): [20] [ 0/63] eta: 0:02:48 time: 2.6673 data: 2.4227 max mem: 22446 +eval (validation): [20] [20/63] eta: 0:00:22 time: 0.4051 data: 0.0040 max mem: 22446 +eval (validation): [20] [40/63] eta: 0:00:10 time: 0.3846 data: 0.0033 max mem: 22446 +eval (validation): [20] [60/63] eta: 0:00:01 time: 0.3510 data: 0.0035 max mem: 22446 +eval (validation): [20] [62/63] eta: 0:00:00 time: 0.3461 data: 0.0035 max mem: 22446 +eval (validation): [20] Total time: 0:00:26 (0.4190 s / it) +eval (test): [20] [ 0/79] eta: 0:03:53 time: 2.9566 data: 2.7229 max mem: 22446 +eval (test): [20] [20/79] eta: 0:00:28 time: 0.3623 data: 0.0186 max mem: 22446 +eval (test): [20] [40/79] eta: 0:00:16 time: 0.3738 data: 0.0034 max mem: 22446 +eval (test): [20] [60/79] eta: 0:00:07 time: 0.3588 data: 0.0036 max mem: 22446 +eval (test): [20] [78/79] eta: 0:00:00 time: 0.3295 data: 0.0034 max mem: 22446 +eval (test): [20] Total time: 0:00:31 (0.3931 s / it) +evaluating best checkpoint: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/eval_v2/hcpya_task21__patch__attn/checkpoint-best.pth +eval model info: +{"score": 0.9915674603174603, "hparam": [3.7, 1.0], "hparam_id": 32, "epoch": 11, "is_best": true, "best_score": 0.9915674603174603} +eval (train): [20] [ 0/297] eta: 0:14:59 time: 3.0285 data: 2.7575 max mem: 22446 +eval (train): [20] [ 20/297] eta: 0:02:22 time: 0.3873 data: 0.0034 max mem: 22446 +eval (train): [20] [ 40/297] eta: 0:01:56 time: 0.3873 data: 0.0034 max mem: 22446 +eval (train): [20] [ 60/297] eta: 0:01:40 time: 0.3645 data: 0.0036 max mem: 22446 +eval (train): [20] [ 80/297] eta: 0:01:29 time: 0.3780 data: 0.0039 max mem: 22446 +eval (train): [20] [100/297] eta: 0:01:20 time: 0.3828 data: 0.0037 max mem: 22446 +eval (train): [20] [120/297] eta: 0:01:11 time: 0.3832 data: 0.0037 max mem: 22446 +eval (train): [20] [140/297] eta: 0:01:03 time: 0.3993 data: 0.0038 max mem: 22446 +eval (train): [20] [160/297] eta: 0:00:54 time: 0.3953 data: 0.0035 max mem: 22446 +eval (train): [20] [180/297] eta: 0:00:46 time: 0.3824 data: 0.0038 max mem: 22446 +eval (train): [20] [200/297] eta: 0:00:38 time: 0.3943 data: 0.0035 max mem: 22446 +eval (train): [20] [220/297] eta: 0:00:30 time: 0.3755 data: 0.0037 max mem: 22446 +eval (train): [20] [240/297] eta: 0:00:22 time: 0.3501 data: 0.0033 max mem: 22446 +eval (train): [20] [260/297] eta: 0:00:14 time: 0.3793 data: 0.0035 max mem: 22446 +eval (train): [20] [280/297] eta: 0:00:06 time: 0.3957 data: 0.0039 max mem: 22446 +eval (train): [20] [296/297] eta: 0:00:00 time: 0.3452 data: 0.0035 max mem: 22446 +eval (train): [20] Total time: 0:01:55 (0.3903 s / it) +eval (validation): [20] [ 0/63] eta: 0:03:05 time: 2.9498 data: 2.6493 max mem: 22446 +eval (validation): [20] [20/63] eta: 0:00:22 time: 0.3993 data: 0.0205 max mem: 22446 +eval (validation): [20] [40/63] eta: 0:00:10 time: 0.3684 data: 0.0035 max mem: 22446 +eval (validation): [20] [60/63] eta: 0:00:01 time: 0.3515 data: 0.0036 max mem: 22446 +eval (validation): [20] [62/63] eta: 0:00:00 time: 0.3364 data: 0.0030 max mem: 22446 +eval (validation): [20] Total time: 0:00:26 (0.4162 s / it) +eval (test): [20] [ 0/79] eta: 0:03:55 time: 2.9819 data: 2.7227 max mem: 22446 +eval (test): [20] [20/79] eta: 0:00:28 time: 0.3662 data: 0.0032 max mem: 22446 +eval (test): [20] [40/79] eta: 0:00:16 time: 0.3612 data: 0.0030 max mem: 22446 +eval (test): [20] [60/79] eta: 0:00:07 time: 0.3481 data: 0.0036 max mem: 22446 +eval (test): [20] [78/79] eta: 0:00:00 time: 0.3245 data: 0.0029 max mem: 22446 +eval (test): [20] Total time: 0:00:30 (0.3867 s / it) +eval results: + +| model | repr | clf | dataset | ckpt | epoch | lr | wd | hparam_id | hparam | split | loss | acc | acc_std | f1 | f1_std | +|:---------|:-------|:------|:-------------|:-------|--------:|--------:|-----:|------------:|:-----------|:-----------|-----------:|--------:|----------:|--------:|----------:| +| flat_mae | patch | attn | hcpya_task21 | best | 11 | 0.00111 | 0.05 | 32 | [3.7, 1.0] | train | 0.00023678 | 1 | 0 | 1 | 0 | +| flat_mae | patch | attn | hcpya_task21 | best | 11 | 0.00111 | 0.05 | 32 | [3.7, 1.0] | validation | 0.04389 | 0.99157 | 0.001463 | 0.98994 | 0.0019589 | +| flat_mae | patch | attn | hcpya_task21 | best | 11 | 0.00111 | 0.05 | 32 | [3.7, 1.0] | test | 0.04777 | 0.9881 | 0.0014166 | 0.98719 | 0.0017304 | + + +done! total time: 1:18:27 diff --git a/input_space_v3/flat_lr1e-3_4/eval_v2/hcpya_task21__patch__attn/train_log.json b/input_space_v3/flat_lr1e-3_4/eval_v2/hcpya_task21__patch__attn/train_log.json new file mode 100644 index 0000000000000000000000000000000000000000..4f0614c3d694643510939a2eb1963c11230a51f1 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_4/eval_v2/hcpya_task21__patch__attn/train_log.json @@ -0,0 +1,20 @@ +{"epoch": 0, "train/lr": 2.987987987987988e-05, "train/loss": 2.120753738284111, "train/grad": 0.21204376749694348, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.07088623046875, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.067728271484375, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.062806396484375, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.057706298828125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.052796630859375, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.0458447265625, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.03800048828125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.029261474609375, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.017796630859375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.005499267578125, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.993497314453125, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.975362548828125, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.9576556396484377, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.931923828125, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.9071685791015627, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.883338623046875, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.8528277587890627, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.8166558837890623, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.7754861450195314, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.736593017578125, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.6873410034179686, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.635182342529297, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.5747697448730467, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.507976379394531, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.435881118774414, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.3471749114990232, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.2661430740356447, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.191946449279785, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.091943759918213, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.9758234786987305, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.87493643283844, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.7858080959320068, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.6696924033761025, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.5712508348375558, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.4626201516017319, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.3636857328936458, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.2670878628455102, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.183337921993807, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.1006848116870969, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.0077712820097804, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.9421269868407398, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.8894686243776232, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.8267576523590833, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.7773947505000979, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.7260329474974424, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.6766874709073454, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.6382098312862218, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.5967836647946387, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.5635798831284046, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.039909009113907816, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.039845784483477475, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.03974005285650492, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.03963352059014141, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.03952625086531043, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.03938092897646129, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.039214352685958145, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.03903195220977068, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.03878886467777193, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.03853052571415901, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.038272163476794956, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.03788278262130916, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.03750167524442077, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.036944041829556226, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.036406552474945786, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.035893584247678516, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.035252841524779796, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.03452917982824147, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.03377522099763155, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.03313324559479952, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.03241184037178755, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.03173499359749257, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.031040521832183005, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.03034441233612597, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.029651689352467658, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.02884284093976021, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.02812734358012676, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.02748557339888066, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.02663892916403711, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.025686179837211966, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0248842766135931, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.02419088324997574, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.023276610733009875, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.02249392293393612, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.021617393798660487, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.02072428143816069, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.019883116940036416, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.019341192129068076, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.018645189825911075, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.017829949971055612, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.016859917870606297, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.016206337087787688, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.015534308293717913, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.015018545186612754, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.01479414501285646, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.014806392060709186, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.014658047828706913, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.01444429888855666, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.01448572403693106, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.0301620960235596, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.021182060241699, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.006267547607422, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.9913086891174316, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.9766855239868164, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.9564855098724365, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.933788299560547, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.9086287021636963, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.875791549682617, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.8413245677948, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.807976722717285, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.7581756114959717, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.710675001144409, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.6430611610412598, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.579813241958618, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.5202691555023193, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.4459431171417236, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.3592708110809326, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.262183904647827, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.17069411277771, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.0554563999176025, "validation/loss_021_lr6.1e-01_wd1.0e+00": 1.9334262609481812, "validation/loss_022_lr7.2e-01_wd1.0e+00": 1.7940568923950195, "validation/loss_023_lr8.5e-01_wd1.0e+00": 1.642810344696045, "validation/loss_024_lr1.0e+00_wd1.0e+00": 1.4859139919281006, "validation/loss_025_lr1.2e+00_wd1.0e+00": 1.305116891860962, "validation/loss_026_lr1.4e+00_wd1.0e+00": 1.153694748878479, "validation/loss_027_lr1.6e+00_wd1.0e+00": 1.026617407798767, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.8695787191390991, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.6994472742080688, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.5556809902191162, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.4325488209724426, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.2938556671142578, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.2108028382062912, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.15172870457172394, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.10704322159290314, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.08082852512598038, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.07426764070987701, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.07321280241012573, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.06919120252132416, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.06085781008005142, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.054705314338207245, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.05044499412178993, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.04874896630644798, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.048934441059827805, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.04921352118253708, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.051700856536626816, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.0580899752676487, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.07345551997423172, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.0716765873015873, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.07762896825396826, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.09052579365079365, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.11681547619047619, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.1396329365079365, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.16592261904761904, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.19890873015873015, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.22271825396825398, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.23115079365079366, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.21850198412698413, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.2065972222222222, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.1865079365079365, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.17881944444444445, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.17633928571428573, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.17733134920634921, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.18303571428571427, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.21626984126984128, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.3040674603174603, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.3821924603174603, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.4290674603174603, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.4833829365079365, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.5300099206349206, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.5572916666666666, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.5974702380952381, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.6478174603174603, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.7115575396825397, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.7686011904761905, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.8229166666666666, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.8720238095238095, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.8841765873015873, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.8878968253968254, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.8960813492063492, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9216269841269841, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9459325396825397, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9466765873015873, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9714781746031746, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9769345238095238, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9756944444444444, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9737103174603174, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9759424603174603, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9816468253968254, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9828869047619048, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9841269841269841, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9851190476190477, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9851190476190477, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9848710317460317, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.984375, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.982390873015873, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9774305555555556, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.016730221364745106, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.018154851397869362, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.021924640680596196, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.03278551560763111, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.042000773124400856, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.047340975253064736, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.05507095352032796, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.05740433883235073, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.05454636547166695, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.04677293688385874, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.03898465354028683, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.03023459310896754, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.023477112245607317, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.021301313883656792, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.022555574949443238, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.0284822655691195, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.06196625480629453, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.12462226221562776, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.16957644823965798, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.20705155088522226, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.24669562848000232, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.2753511963575199, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.29961790559379853, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.3623003435352521, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.4577067892612113, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.5721176684857318, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.6681037590790693, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.7639493208028911, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.8435077014069323, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.8592349934849791, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.8599141978001079, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.8723988286023884, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9115575774584364, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9400707989024123, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9387013487536043, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9678122438234295, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9736111919585588, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9725602249846338, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9703618377420407, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9722905802283988, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9780897995459809, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.979009980255989, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9795789522320223, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9816195460320793, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9821358769676346, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9825068611813638, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.982156794346115, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9793562897524742, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.97156116997106, "id_best": 43, "lr_best": 0.006599999999999999, "wd_best": 0.05, "train/loss_best": 0.7773947505000979, "validation/loss_best": 0.04874896630644798, "validation/acc_best": 0.9851190476190477, "validation/f1_best": 0.9816195460320793} +{"epoch": 1, "train/lr": 8.993993993993998e-05, "train/loss": 1.1761528816819191, "train/grad": 0.15008958496153355, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.953428955078125, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.934111328125, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.9027587890625, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.8723297119140625, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.8426800537109376, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.802520751953125, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.7585546875, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.7112591552734373, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.6514071655273437, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.5902557373046875, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.5322146606445313, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.448161315917969, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.3691366577148436, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.2580767822265626, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.154507598876953, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.057260513305664, "train/loss_016_lr2.7e-01_wd1.0e+00": 1.9364619445800781, "train/loss_017_lr3.2e-01_wd1.0e+00": 1.798060302734375, "train/loss_018_lr3.8e-01_wd1.0e+00": 1.649273281097412, "train/loss_019_lr4.4e-01_wd1.0e+00": 1.5168897056579589, "train/loss_020_lr5.2e-01_wd1.0e+00": 1.361733980178833, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.2106907176971435, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.051894061565399, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.894375878572464, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.7473103287816047, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.5969143669307232, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.4842451895028353, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.3986979549191892, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.3055522930622101, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.2227403427194804, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.16978698679246007, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.13558168954215943, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.10493962520733476, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.0887959775235504, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.0772913035005331, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.07034957122057676, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.06573477385565639, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.06284296910278499, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.060605749497190116, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.058064573490992186, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.057370173661038276, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.05742628952488303, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.057803764333948494, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.06345141051337123, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.06505023119971157, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.07399157435633243, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.08342258509248496, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.11040937361307442, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.15506946749053896, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.03706432964652777, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.036660351511091, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.03600677768699825, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.035369062507525084, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.03474940638057888, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.033917544865980746, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.03301485951989889, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.03207212178967893, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.03094245322979987, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.029888036269694565, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.028993036802858113, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.027868432216346262, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.026978825815021992, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.025943438513204454, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.025141324205324053, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.024477267526090144, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.02371912538073957, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.022880474869161845, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.021964038326404988, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.021121661835350095, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.02010612021200359, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.01910145841073245, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.01802883530035615, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.01688111390452832, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.015692748753353955, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.014361828751862048, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.013179964758455754, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.012225788957439363, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.011135159769328312, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.009983313962584362, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.009237661637598649, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.008738974338630214, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.008249520634708461, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.008050362948561087, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0077939431543927636, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.007484195589786396, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.007257719468907453, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0071482490986818446, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.00707219282456208, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0068636230545234865, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.007000511295627803, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.007239656713791192, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.007521721257944591, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.00820832792931469, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.00859676081163343, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.009787774070282466, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.010831441842601635, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.01349247008067323, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.018666634140536188, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.8612120151519775, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.8300013542175293, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.7796790599823, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.73146390914917, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.6853740215301514, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.6239213943481445, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.5578417778015137, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.4881300926208496, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.40129017829895, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.3134546279907227, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.230403184890747, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.109886646270752, "validation/loss_012_lr1.4e-01_wd1.0e+00": 1.9965474605560303, "validation/loss_013_lr1.7e-01_wd1.0e+00": 1.8377931118011475, "validation/loss_014_lr2.0e-01_wd1.0e+00": 1.691543698310852, "validation/loss_015_lr2.3e-01_wd1.0e+00": 1.557995080947876, "validation/loss_016_lr2.7e-01_wd1.0e+00": 1.398402214050293, "validation/loss_017_lr3.2e-01_wd1.0e+00": 1.227311134338379, "validation/loss_018_lr3.8e-01_wd1.0e+00": 1.057143211364746, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.9157086610794067, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.7562549710273743, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.6017040014266968, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.4420841634273529, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.304768443107605, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.20972684025764465, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.13969507813453674, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.10133935511112213, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.08251781761646271, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.06991563737392426, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.061345137655735016, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.05631162226200104, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.052714668214321136, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.04785646125674248, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.04412123188376427, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.040418751537799835, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.03763110935688019, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.035662781447172165, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.034815605729818344, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.03474312648177147, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.034979525953531265, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.041697848588228226, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.05312749370932579, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.05707067251205444, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.056757379323244095, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.096378393471241, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.13538067042827606, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.10254106670618057, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.29572102427482605, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.2939745783805847, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.23487103174603174, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.2279265873015873, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.21279761904761904, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.1949404761904762, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.18700396825396826, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.1840277777777778, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.1902281746031746, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.21502976190476192, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.28695436507936506, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.36086309523809523, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.4117063492063492, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.4851190476190476, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.5302579365079365, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.5662202380952381, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.6036706349206349, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.6376488095238095, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.6713789682539683, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.7366071428571429, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.8139880952380952, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.8561507936507936, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.8871527777777778, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9027777777777778, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9213789682539683, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9399801587301587, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9623015873015873, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9759424603174603, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9791666666666666, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9811507936507936, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9816468253968254, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9836309523809523, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9836309523809523, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9846230158730159, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9853670634920635, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9868551587301587, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9885912698412699, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9895833333333334, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9888392857142857, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9888392857142857, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9888392857142857, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9885912698412699, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9851190476190477, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9806547619047619, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9811507936507936, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9848710317460317, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9791666666666666, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9689980158730159, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9759424603174603, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9513888888888888, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9657738095238095, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.054601548882686576, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.049070532190532014, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.04311834850222463, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.032399290925244524, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.029981170883828106, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.02845685826369803, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.03392991401392331, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.0560999205990606, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.11028849226254156, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.15544416465945146, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.1950242315348251, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.25601913366720047, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.2830921547406112, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.31723564845898217, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.38328256664788424, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.4347803292030913, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.5006769322815656, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.6233287620319212, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.7477377143247113, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.8164011256700138, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.8635140361231161, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.8849833229878487, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9095834885156738, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9329419303891924, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9580348218624748, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.972034331525497, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9752866985438273, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9771266855861747, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9779524831330323, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9802281103861926, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9805032957231351, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9818398729907669, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9827861528088692, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9846931949905986, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9866739362778008, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9880783605822426, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9873968801262911, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.987309314257125, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9870495436364524, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9867705953670332, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9819864924014271, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9783441275121527, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9786538262585835, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9806382548844984, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.973883476185358, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9524698494416061, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9723782950456448, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9377718503387042, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9564385550333571, "id_best": 35, "lr_best": 0.0018, "wd_best": 0.05, "train/loss_best": 0.07034957122057676, "validation/loss_best": 0.03763110935688019, "validation/acc_best": 0.9895833333333334, "validation/f1_best": 0.9880783605822426} +{"epoch": 2, "train/lr": 0.00014999999999999988, "train/loss": 0.8658587715029716, "train/grad": 0.19651596821844577, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.7446441650390625, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.7008135986328123, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.6318280029296877, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.566865234375, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.5057186889648437, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.425084533691406, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.3388177490234376, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.247490234375, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.133140869140625, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.0172076416015625, "train/loss_010_lr1.0e-01_wd1.0e+00": 1.9084683227539063, "train/loss_011_lr1.2e-01_wd1.0e+00": 1.753733139038086, "train/loss_012_lr1.4e-01_wd1.0e+00": 1.613729591369629, "train/loss_013_lr1.7e-01_wd1.0e+00": 1.4287567520141602, "train/loss_014_lr2.0e-01_wd1.0e+00": 1.2701560211181642, "train/loss_015_lr2.3e-01_wd1.0e+00": 1.1332032585144043, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.9761729001998901, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.8101948118209839, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.6464043426513671, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.5162148481607437, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.3854665045440197, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.2826058427244425, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.2016027808189392, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.14655925007537007, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.11201562186703086, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.08874991367571056, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.07733407621271908, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.07123725170269608, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.065773162888363, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.06151926832273603, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.059059462677687406, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.057291391864418985, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.05518344715237618, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.05358884272165596, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.051988712335005405, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.05034902452491224, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.04862089101225138, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.04955227595753968, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.05024630871601403, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.053196602882817384, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.056686258148401975, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.06156866669654846, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.07046409687027336, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.09261886792257429, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.16662922537885605, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.3241438402235508, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.5598374573141336, "train/loss_047_lr4.3e+01_wd1.0e+00": 1.030007844530046, "train/loss_048_lr5.0e+01_wd1.0e+00": 1.6745391807053238, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.03324931661598384, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.03234837752766907, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.030966546153649688, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.029760142425075173, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.028732391940429806, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.027566479509696363, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.026548295076936484, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.025697676502168178, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.02485959989950061, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.024158237781375647, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.02355244488455355, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.022688966318964957, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.021852392181754113, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.02063961133360863, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.019524207301437856, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.01853373795747757, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.01740894213784486, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.01623839181382209, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.0150264867185615, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.013965440671890974, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.012757931295782328, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.011608613086864353, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.010372742351610214, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.009238132887985558, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.008361171884462237, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0076776385912671686, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0072879173833644015, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.007084248871542513, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.006942558758892119, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.00686947405920364, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.006867594893556088, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.006852359366603195, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.006806706616771407, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.006776374893961474, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0067310360400006175, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.006675977994455025, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.006660976307757665, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.006866582753136754, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.00698640285874717, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.007631609368727368, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.008030412051739403, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.008771640079794451, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.009776066625927343, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.012702379908587318, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.018514236692280975, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.03564525812340435, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.04919460174257665, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.07241464520151696, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.10240638204886636, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.621717691421509, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.565601348876953, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.4782495498657227, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.3971893787384033, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.3210110664367676, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.2203547954559326, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.1121323108673096, "validation/loss_007_lr6.2e-02_wd1.0e+00": 1.9973140954971313, "validation/loss_008_lr7.4e-02_wd1.0e+00": 1.8537858724594116, "validation/loss_009_lr8.7e-02_wd1.0e+00": 1.7099779844284058, "validation/loss_010_lr1.0e-01_wd1.0e+00": 1.5779982805252075, "validation/loss_011_lr1.2e-01_wd1.0e+00": 1.3973239660263062, "validation/loss_012_lr1.4e-01_wd1.0e+00": 1.2421437501907349, "validation/loss_013_lr1.7e-01_wd1.0e+00": 1.0491887331008911, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.891021728515625, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.7556280493736267, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.5973632335662842, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.43193772435188293, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.2930234968662262, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.20922639966011047, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.14409978687763214, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.10335515439510345, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.0804673284292221, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.06803703308105469, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.060167647898197174, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.05411587655544281, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.050649769604206085, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.04888240620493889, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.04743247851729393, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.04397288337349892, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.04068765044212341, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.03901826590299606, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.03812362998723984, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.03897006809711456, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.04036002606153488, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.03880033269524574, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.04505365714430809, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.05024294927716255, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.06854724138975143, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.09149815887212753, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.1411207914352417, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.11263304948806763, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.1610967516899109, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.4799875319004059, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.3361281454563141, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.7722578644752502, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.8385941982269287, "validation/loss_047_lr4.3e+01_wd1.0e+00": 1.4776735305786133, "validation/loss_048_lr5.0e+01_wd1.0e+00": 2.150791645050049, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.17559523809523808, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.1783234126984127, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.20014880952380953, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.2663690476190476, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.3472222222222222, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.4069940476190476, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.4677579365079365, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.5238095238095238, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.5577876984126984, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.5877976190476191, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.6272321428571429, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.6986607142857143, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.7725694444444444, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.8377976190476191, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.8692956349206349, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.8881448412698413, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9050099206349206, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9253472222222222, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9439484126984127, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9635416666666666, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9754464285714286, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9786706349206349, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9816468253968254, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9833829365079365, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9841269841269841, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9848710317460317, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9856150793650794, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9858630952380952, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9853670634920635, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9875992063492064, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9888392857142857, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9893353174603174, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9898313492063492, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9890873015873016, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9878472222222222, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9873511904761905, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9861111111111112, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9851190476190477, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9791666666666666, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.980406746031746, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9685019841269841, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9737103174603174, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9682539682539683, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9479166666666666, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.964781746031746, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9680059523809523, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.966765873015873, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9694940476190477, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9744543650793651, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.020155442042122267, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.02380977022055037, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.048589514060351675, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.1013044758026109, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.14857110446352703, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.19212363950300346, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.24699765075733765, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.2829081274350191, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.3097998014473817, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.34717362662847107, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.4173330811859534, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.5552373439771664, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.6896271843390358, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.7880961225043416, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.8340237808653465, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.8603277655163166, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.8853989850708912, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9154970299910501, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9378005110362378, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9590717840460223, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9719726035448077, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9748630181246456, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9783214167648382, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9802716013105686, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9814256154957952, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9828704866058015, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9839512735888976, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9841442742410879, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9840575886956567, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9865565671542103, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9883657318023386, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9886048080415331, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9884795891674059, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.987536843646357, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9859503200653206, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9852530749112447, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9847915825021202, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9842918169580301, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9794336677987265, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9797114851828698, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9682211885015128, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9681707463438142, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9563362463208975, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9094147122946866, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9555029527958454, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9667214799316513, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9584034855811202, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9643580747118724, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9648249450214957, "id_best": 32, "lr_best": 0.0011099999999999999, "wd_best": 0.05, "train/loss_best": 0.05518344715237618, "validation/loss_best": 0.03812362998723984, "validation/acc_best": 0.9898313492063492, "validation/f1_best": 0.9884795891674059} +{"epoch": 3, "train/lr": 0.0002100600600600602, "train/loss": 0.7641099597513675, "train/grad": 0.27956787310540676, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.4993191528320313, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.432591857910156, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.3282830810546873, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.230516204833984, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.1379295349121095, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.0153810119628908, "train/loss_006_lr5.3e-02_wd1.0e+00": 1.8842569732666015, "train/loss_007_lr6.2e-02_wd1.0e+00": 1.7474040222167968, "train/loss_008_lr7.4e-02_wd1.0e+00": 1.5820254898071289, "train/loss_009_lr8.7e-02_wd1.0e+00": 1.4236056518554687, "train/loss_010_lr1.0e-01_wd1.0e+00": 1.2847282981872559, "train/loss_011_lr1.2e-01_wd1.0e+00": 1.1031489276885986, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.950762128829956, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.759524941444397, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.6015150713920593, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.4739122301340103, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.3468780826032162, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.2420032113045454, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.16887770373374222, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.12786567885428668, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.09841629393398761, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.08222611467353999, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.07229552246630191, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.06572487123310566, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.060811432311311364, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.05622336591593921, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.05275605795904994, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0499208927154541, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.04657683310098946, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0431658092699945, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.040849370285868644, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.039130734456703065, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.037434922074899075, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.03624013594351709, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.03504092822782695, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.034556865096092224, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.04045232919044792, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.04502702496945858, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.053940291590988634, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.06888917015865445, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.07940469712018966, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.1289301452692598, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.19452940674498678, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.47208481051959095, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.44126817016862335, "train/loss_045_lr3.1e+01_wd1.0e+00": 1.1763655318692328, "train/loss_046_lr3.6e+01_wd1.0e+00": 1.7763149490207433, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.426296566221863, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.345986289251596, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.02811954070813954, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.02717761980369687, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.026021282905712723, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.025218670507892966, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.024621937545016407, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.023955638343468307, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.023289778092876075, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.022559005273506044, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.02157845873385668, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.02051864893641323, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.01950892563443631, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.018132238988764583, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.01699546169023961, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.015645385161042212, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.014508366212248802, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.013461299231275916, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.012168045612052083, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.010719373149331659, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.009281567493453623, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.008228861365932972, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.007347911081742495, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.006849147739121691, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.006577829533489421, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.006428735860390588, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.006308486772468314, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.006166061072144657, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.006042750955093652, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.005936427459819243, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.005786085071740672, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.005618430245085619, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.005492023179540411, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.005417048551607877, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.005349160901096184, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.005313612422178267, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0052534411023953, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.005314476780185941, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.006135832339496119, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0069282657087023835, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.008203455466718879, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.010324895457815729, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.01053215724099573, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.016478355782091968, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.023188395815668627, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0419626792329791, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.04000931635781387, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.08063225915183292, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.09820489111699399, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.12964888581657089, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.14695835185289752, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.357628345489502, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.2783961296081543, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.1541686058044434, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.0377132892608643, "validation/loss_004_lr3.8e-02_wd1.0e+00": 1.9277751445770264, "validation/loss_005_lr4.5e-02_wd1.0e+00": 1.7836991548538208, "validation/loss_006_lr5.3e-02_wd1.0e+00": 1.6324763298034668, "validation/loss_007_lr6.2e-02_wd1.0e+00": 1.4794822931289673, "validation/loss_008_lr7.4e-02_wd1.0e+00": 1.302005648612976, "validation/loss_009_lr8.7e-02_wd1.0e+00": 1.1398718357086182, "validation/loss_010_lr1.0e-01_wd1.0e+00": 1.0031092166900635, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.8262966275215149, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.6751717329025269, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.48269617557525635, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.3396104872226715, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.2475314438343048, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.17264828085899353, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.1191389262676239, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.08901478350162506, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.07522714883089066, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.06552614271640778, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.058960627764463425, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.053730376064777374, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.0495150163769722, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.04584858939051628, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.04234534129500389, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.040280621498823166, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.0396554209291935, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.04124295338988304, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.04627827927470207, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.052934881299734116, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.05891132354736328, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.06628573685884476, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.07192110270261765, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.0725935697555542, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.07533112913370132, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.09086882323026657, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.11078150570392609, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.08661787956953049, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.16034629940986633, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.16213399171829224, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.2626860737800598, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.4585590660572052, "validation/loss_043_lr2.2e+01_wd1.0e+00": 1.257837176322937, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.5367302298545837, "validation/loss_045_lr3.1e+01_wd1.0e+00": 1.6454567909240723, "validation/loss_046_lr3.6e+01_wd1.0e+00": 2.7493433952331543, "validation/loss_047_lr4.3e+01_wd1.0e+00": 6.156582832336426, "validation/loss_048_lr5.0e+01_wd1.0e+00": 5.546276092529297, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.3308531746031746, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.37896825396825395, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.455109126984127, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.519593253968254, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.5466269841269841, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.5726686507936508, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.6101190476190477, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.6560019841269841, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.7261904761904762, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.8030753968253969, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.8427579365079365, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.8747519841269841, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.8876488095238095, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9084821428571429, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9293154761904762, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9466765873015873, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9682539682539683, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9784226190476191, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.980406746031746, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9813988095238095, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9828869047619048, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.984375, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9853670634920635, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9861111111111112, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9868551587301587, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9875992063492064, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9875992063492064, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9873511904761905, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9861111111111112, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9848710317460317, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9828869047619048, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9821428571428571, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9813988095238095, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9809027777777778, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.982390873015873, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9813988095238095, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9784226190476191, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9759424603174603, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9833829365079365, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9697420634920635, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9680059523809523, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9682539682539683, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.970734126984127, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9449404761904762, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9786706349206349, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9712301587301587, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9670138888888888, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9518849206349206, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9670138888888888, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.13792341125419774, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.16780196316991414, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.23569668105943145, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.277857153167428, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.2952343479402214, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.3225845018734359, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.3941722289620788, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.48324679276630755, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.6311431895191049, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.753208005254743, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.8092364746625148, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.8507408276186885, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.8653345700525088, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.8921914871926431, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9206752571404435, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9418559364152446, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9653867382779886, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9759341163436605, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9775833775231846, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9785767265830042, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9803412611620914, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9815538513403579, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9828123153469787, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9836161459781921, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9846356363647246, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9860435521209738, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9859618240226473, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9857873157594481, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9848550801815362, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9842826975158286, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9827899418874884, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9826478321929464, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9824622580827044, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9821572051669282, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9831726770409175, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9815593106082806, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9794588749045323, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9751749717084441, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9806500776881716, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9573448534346211, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9532555394394503, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9627477943802847, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9615114750235387, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9434353215425482, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9754297656707972, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9694188525141068, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9592331974177462, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9152517455640696, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9565693928983237, "id_best": 25, "lr_best": 0.00035999999999999997, "wd_best": 0.05, "train/loss_best": 0.05622336591593921, "validation/loss_best": 0.04234534129500389, "validation/acc_best": 0.9875992063492064, "validation/f1_best": 0.9860435521209738} +{"epoch": 4, "train/lr": 0.0002701201201201201, "train/loss": 0.7796913674473762, "train/grad": 0.40343819446861745, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.225943603515625, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.1341856384277342, "train/loss_002_lr2.8e-02_wd1.0e+00": 1.9903221130371094, "train/loss_003_lr3.3e-02_wd1.0e+00": 1.8565516662597656, "train/loss_004_lr3.8e-02_wd1.0e+00": 1.7321292877197265, "train/loss_005_lr4.5e-02_wd1.0e+00": 1.5732601165771485, "train/loss_006_lr5.3e-02_wd1.0e+00": 1.4124853515625, "train/loss_007_lr6.2e-02_wd1.0e+00": 1.2558421325683593, "train/loss_008_lr7.4e-02_wd1.0e+00": 1.080001335144043, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.9208435153961182, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.7841879510879517, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.605053448677063, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.46120468974113465, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.3099953103065491, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.21835148341953756, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.16307541996240615, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.12080370569601655, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.09433530061505735, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.07962675193324685, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.07180598750710487, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.0653587098326534, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.06056460790336132, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.05651821967214346, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.05291080900467932, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.049618822457268834, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.046383482357487085, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.04406597430817783, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.04247751056216657, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.04063630542717874, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.038282278571277854, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.035783639969304205, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.033785596126690506, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.03229319130070508, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.0305133406445384, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.030026976531371475, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.029268339471891523, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.03088893965817988, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.0419865579996258, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.06768345437012613, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.14161417508497834, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.3154234645888209, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.4165344341471791, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.7113082988467068, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.5341336836107076, "train/loss_044_lr2.6e+01_wd1.0e+00": 1.4610800124239176, "train/loss_045_lr3.1e+01_wd1.0e+00": 1.7534265425894409, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.600812443802133, "train/loss_047_lr4.3e+01_wd1.0e+00": 4.244125463999808, "train/loss_048_lr5.0e+01_wd1.0e+00": 6.1073678057082, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.02522121929563582, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.02463679140433669, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.023879884211346507, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.023216840410605073, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.022566086538136007, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.021641581868752837, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.020584308840334416, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.019453201782889663, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.018130133184604345, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.016954947100020944, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.015998502196744084, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.014735043183900415, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.013513727569952607, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.011782786103431135, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.01030563972890377, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.00905064121587202, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.007839444885030388, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.006957296615000814, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.006542557573411613, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.006367021513869986, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.006240364010445774, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.006159414037247188, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.00611200720013585, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.006069613491999917, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.006027394229604397, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.00600962259224616, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.006039836739364546, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.006123340676131192, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.006184089109301567, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.006090852954657749, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.00590426004724577, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.005729930112865986, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0056015384239435665, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.005519783280324191, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.005554099400469568, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0055413501994189575, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.005915333262310014, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0071598960612755036, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.01123228828966603, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.02041968955820039, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.03056875082617637, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.036678136061717624, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.05429654055470508, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.047500757877247536, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.09221413366994526, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.09505812897041867, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.135371087232849, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.1832413203654732, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.22835384856909513, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.0768117904663086, "validation/loss_001_lr2.3e-02_wd1.0e+00": 1.9713666439056396, "validation/loss_002_lr2.8e-02_wd1.0e+00": 1.8074342012405396, "validation/loss_003_lr3.3e-02_wd1.0e+00": 1.6574995517730713, "validation/loss_004_lr3.8e-02_wd1.0e+00": 1.5212703943252563, "validation/loss_005_lr4.5e-02_wd1.0e+00": 1.3524757623672485, "validation/loss_006_lr5.3e-02_wd1.0e+00": 1.1884185075759888, "validation/loss_007_lr6.2e-02_wd1.0e+00": 1.0339099168777466, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.8628906011581421, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.7053754925727844, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.5674251317977905, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.3943759500980377, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.27824732661247253, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.17975524067878723, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.12520679831504822, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.09607428312301636, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.07778609544038773, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.06657969206571579, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.059073515236377716, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.054447926580905914, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.05052195116877556, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.047589968889951706, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.045012302696704865, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.042588699609041214, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.04080747812986374, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.04102573171257973, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.04444023594260216, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.04867890849709511, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.04868992418050766, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.045464593917131424, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.044135890901088715, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.0437641479074955, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.04663558304309845, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.04871128126978874, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.05042855069041252, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.04901948198676109, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.05720655620098114, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.07501311600208282, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.27212339639663696, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.23436833918094635, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.6045299768447876, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.3045453727245331, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.7353916764259338, "validation/loss_043_lr2.2e+01_wd1.0e+00": 1.284616470336914, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.704519510269165, "validation/loss_045_lr3.1e+01_wd1.0e+00": 1.9396499395370483, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.5624616146087646, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.936450242996216, "validation/loss_048_lr5.0e+01_wd1.0e+00": 15.189515113830566, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.4992559523809524, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.5381944444444444, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.5716765873015873, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.6066468253968254, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.6540178571428571, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.7155257936507936, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.7899305555555556, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.8447420634920635, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.8752480158730159, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.8953373015873016, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9055059523809523, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9273313492063492, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.951140873015873, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9712301587301587, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9779265873015873, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.980406746031746, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9831349206349206, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9836309523809523, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9846230158730159, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9861111111111112, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9868551587301587, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9873511904761905, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9878472222222222, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9890873015873016, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9888392857142857, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9871031746031746, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9856150793650794, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.984375, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9846230158730159, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9856150793650794, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9866071428571429, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9868551587301587, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9861111111111112, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.986359126984127, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9856150793650794, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9878472222222222, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9856150793650794, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.980406746031746, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9680059523809523, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9799107142857143, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9709821428571429, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9816468253968254, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.972718253968254, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9677579365079365, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9627976190476191, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9769345238095238, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9742063492063492, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9774305555555556, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9481646825396826, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.26475616273997704, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.28860941148500324, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.3183980376724925, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.3886746685577357, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.48485833584148774, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.5992035272336957, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.72318519500785, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.7964553576381644, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.8422545500999655, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.8722193279914433, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.889757747858125, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9193084366447256, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9460214120761318, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9682937814703122, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.975068788189653, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9776088379456592, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9814948577687397, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9822098433487189, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9826549614361022, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9839211953763554, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9847996484676096, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9848914118775434, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9859800198401949, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9876830396152966, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9878085082161716, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9863192859148658, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9847853978552921, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9838682186989912, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9841182145364675, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9846354289378271, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9854660872225771, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9849878845631297, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9843226615039737, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9840332584887589, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9837779130774758, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9861792976174694, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9826556753229392, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9806263156784509, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9618923131243504, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9739239625017534, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9550163677925699, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9757252047769592, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9690902554534284, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.960986536226661, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.948455133535308, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9723930751999668, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9685588353967555, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9712466611813201, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9250911331877085, "id_best": 23, "lr_best": 0.00025499999999999996, "wd_best": 0.05, "train/loss_best": 0.05291080900467932, "validation/loss_best": 0.042588699609041214, "validation/acc_best": 0.9890873015873016, "validation/f1_best": 0.9876830396152966} +{"epoch": 5, "train/lr": 0.00029891323817685334, "train/loss": 0.7860509853065014, "train/grad": 0.45545900538563727, "train/loss_000_lr2.0e-02_wd1.0e+00": 1.9490371704101563, "train/loss_001_lr2.3e-02_wd1.0e+00": 1.8320376586914062, "train/loss_002_lr2.8e-02_wd1.0e+00": 1.6532613372802734, "train/loss_003_lr3.3e-02_wd1.0e+00": 1.494104766845703, "train/loss_004_lr3.8e-02_wd1.0e+00": 1.3537513732910156, "train/loss_005_lr4.5e-02_wd1.0e+00": 1.1851580810546876, "train/loss_006_lr5.3e-02_wd1.0e+00": 1.0242788887023926, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.872255687713623, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.6998542976379395, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.5415704035758973, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.4144302499294281, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.2805139023065567, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.20089786604046822, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.13473146121948956, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.1025395817309618, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.0868712876085192, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.07607433612458409, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.06855916255153716, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.06289838100783526, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.05890278314240277, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.05496050482615829, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.05148124338127673, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.04802597437985241, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.044777844604104756, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.0416632083337754, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.03803609855473042, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.03517108667641878, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.03278030916117132, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.02956434323452413, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.02642104059457779, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.024150739507749677, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.022248267009854317, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.02019356846809387, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.017847209144383668, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.02113776996731758, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.02581523882225156, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.038052332885563374, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.060564998053014275, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.15322639443911612, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.25446320560760793, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.29797892975620927, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.42514654658734796, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.5355534451082349, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.6890657411701977, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.40095161261037, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.397251528063789, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.743912388533354, "train/loss_047_lr4.3e+01_wd1.0e+00": 4.758224432962015, "train/loss_048_lr5.0e+01_wd1.0e+00": 8.136104302899913, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.023550750641152262, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.022975622937083245, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.022010737983509897, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.02101917175576091, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.0200367789901793, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.01875923258718103, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.017507952717132867, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.01636722486000508, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.015175085258670151, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.014040639260783791, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.01288264497416094, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.01120668679010123, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.009885878800414503, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.008252312616677955, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.007232507220469415, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.006727399018127471, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.0064371059602126475, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.006263050692505203, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.006142774379695765, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.006048887277138419, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.0059570837725186725, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.005890582740539685, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.005838745630462654, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.005816369231324643, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.005768485566950404, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.005641490784473718, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0055088895178050734, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.005335022445942741, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.005041638701513875, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.004867399549111724, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.004832859602611279, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0046745596435357585, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.004577474039542721, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.004525407127948711, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.00519029852875974, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.005813910119450157, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.008346528629299427, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.010817861339528462, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.01966487294215767, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.025861726362906692, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.030976368485894724, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.040543606966618774, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.04391622465762163, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.049713832879260206, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.1354375892970448, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.13549090370165234, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.1650902295857668, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.1826277577473792, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.26457721420447344, "validation/loss_000_lr2.0e-02_wd1.0e+00": 1.8082363605499268, "validation/loss_001_lr2.3e-02_wd1.0e+00": 1.6816089153289795, "validation/loss_002_lr2.8e-02_wd1.0e+00": 1.4918756484985352, "validation/loss_003_lr3.3e-02_wd1.0e+00": 1.3277925252914429, "validation/loss_004_lr3.8e-02_wd1.0e+00": 1.1870572566986084, "validation/loss_005_lr4.5e-02_wd1.0e+00": 1.0215688943862915, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.8643113374710083, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.7129576206207275, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.5389007329940796, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.3877274990081787, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.28329378366470337, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.18748697638511658, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.13247334957122803, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.09181033074855804, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.07519920915365219, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.06627700477838516, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.05920594558119774, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.05367050692439079, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.049493204802274704, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.04644276946783066, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.04345419257879257, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.04076719284057617, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.0380919948220253, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.035841867327690125, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.034220486879348755, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.033304475247859955, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.03312881663441658, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.033426057547330856, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.034083832055330276, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.03547219559550285, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.03656802326440811, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.037239812314510345, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.039437536150217056, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.042136698961257935, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.05342736840248108, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.0666126236319542, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.09322281926870346, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.16445711255073547, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.275435209274292, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.2720111906528473, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.360313355922699, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.7535071969032288, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.9452349543571472, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.8501872420310974, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.828045129776001, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.527820110321045, "validation/loss_046_lr3.6e+01_wd1.0e+00": 6.734611511230469, "validation/loss_047_lr4.3e+01_wd1.0e+00": 5.5990400314331055, "validation/loss_048_lr5.0e+01_wd1.0e+00": 8.299257278442383, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.576140873015873, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.6051587301587301, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.6661706349206349, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.7217261904761905, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.7904265873015873, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.8449900793650794, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.871031746031746, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.8898809523809523, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9079861111111112, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.925843253968254, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9451884920634921, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.96875, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9781746031746031, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9818948412698413, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.984375, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.984375, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9861111111111112, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9856150793650794, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.986359126984127, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9868551587301587, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9878472222222222, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9893353174603174, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9888392857142857, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9898313492063492, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9908234126984127, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9905753968253969, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9905753968253969, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9903273809523809, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9898313492063492, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9893353174603174, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9890873015873016, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9893353174603174, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9895833333333334, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9885912698412699, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9875992063492064, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9853670634920635, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9836309523809523, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9789186507936508, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9776785714285714, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9826388888888888, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9826388888888888, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9749503968253969, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9774305555555556, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9786706349206349, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9729662698412699, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9697420634920635, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.957093253968254, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9719742063492064, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9737103174603174, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.32444350243832, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.38415893085684644, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.5015377210778238, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.6053427153740689, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.7226855482947334, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.8002944515782592, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.8407182939477754, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.8675281976727192, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.891829663076763, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9171353206414183, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9380962925587537, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9653145340800997, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.975238298563171, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9797519573710515, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.982340581209355, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9825204449396181, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9843417879952028, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9836203402853607, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9845818125723375, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9851380452803069, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9864251943145206, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.987973878811929, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9882038030222996, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.988490033937863, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9897909009448004, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.989058201454756, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.988736955434585, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9879636179195, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9870776322965304, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9863678369351999, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9865126488172028, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9866919991862042, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9876455430242652, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9865774601549165, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9847236048865088, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9787328111765334, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9805908863085145, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9732917998994224, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9712305876004638, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9803315391053027, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9795720156889567, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9698996395328331, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9738282142921887, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.971812286950003, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9679720587493718, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9636809512327245, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9516179479044402, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9647847203086641, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9633637794040891, "id_best": 24, "lr_best": 0.0003, "wd_best": 0.05, "train/loss_best": 0.0416632083337754, "validation/loss_best": 0.034220486879348755, "validation/acc_best": 0.9908234126984127, "validation/f1_best": 0.9897909009448004} +{"epoch": 6, "train/lr": 0.0002924170901991409, "train/loss": 0.5461118783801794, "train/grad": 0.34450915865600107, "train/loss_000_lr2.0e-02_wd1.0e+00": 1.6994229125976563, "train/loss_001_lr2.3e-02_wd1.0e+00": 1.5663578033447265, "train/loss_002_lr2.8e-02_wd1.0e+00": 1.3716793060302734, "train/loss_003_lr3.3e-02_wd1.0e+00": 1.2074914169311524, "train/loss_004_lr3.8e-02_wd1.0e+00": 1.0686269187927246, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.9051072597503662, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.7469606304168701, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.5934887027740479, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.42683749318122866, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.3020060628652573, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.22316161364316942, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.15136814959347247, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.11298408798873424, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.08749275907874107, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.0761910106241703, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.06962280681356788, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.06378483222797512, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.0587129488773644, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.05432341809384525, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.05083335523493588, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.04698193623684346, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.04317599546164274, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.0392507566511631, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.03538136536255479, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.03179276240058243, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.02806873621419072, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.025048114070668818, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.02256741070188582, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.019618767565116286, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.016479633813723922, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.01373755139298737, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.011580732250586152, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.011062777694314718, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.012928782124072313, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.016445316122844816, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.017926672752946616, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.05121875022538006, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.052104617580771444, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.08652974903583527, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.14119001530110836, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.1869939258135855, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.32958393707871436, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.2798696927074343, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.5358837344869971, "train/loss_044_lr2.6e+01_wd1.0e+00": 1.1109462037030609, "train/loss_045_lr3.1e+01_wd1.0e+00": 1.627253510132432, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.9264061599690465, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.3558831756561993, "train/loss_048_lr5.0e+01_wd1.0e+00": 4.847118287691846, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.022230697246268392, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.021429100083187224, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.020091050290502607, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.018849554425105452, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.017771875699982047, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.01655223420355469, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.015475560682825745, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.014461045865900815, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.013071056052576751, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.011536940110381692, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.010264021358452738, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.00870662170695141, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.007569475172786042, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.0067841458541806786, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.006511251787887886, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.006371629645582288, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.0062593306688359, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.006150653522927314, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.006061094258329831, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.005980745336273685, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.005837104642414488, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.005638384037301876, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.005417669020825997, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.005207997249672189, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.00503788840433117, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.004856984235229902, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.004673680846171919, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.004500297926133498, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.004292335816135164, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.003990869615226984, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0035228224903403314, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.003069937562395353, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.003005480352367158, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.003380053902401414, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.004050218605098053, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.004777691616227458, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.009302876718400056, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.00907679788504879, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.014725883580015324, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.017411956553073295, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.022078692502969545, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.03469852807799736, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.03007811604582244, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.04898063263873936, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0852384723638933, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.11656395846166427, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.1530454817432464, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.16108887894264337, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.10293259226084053, "validation/loss_000_lr2.0e-02_wd1.0e+00": 1.5807015895843506, "validation/loss_001_lr2.3e-02_wd1.0e+00": 1.4436358213424683, "validation/loss_002_lr2.8e-02_wd1.0e+00": 1.2476918697357178, "validation/loss_003_lr3.3e-02_wd1.0e+00": 1.0862277746200562, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.9507669806480408, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.7901731133460999, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.6319759488105774, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.4795932471752167, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.3275896906852722, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.2268015593290329, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.16487036645412445, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.11016270518302917, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.08534488826990128, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.06912469863891602, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.06092304736375809, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.055816106498241425, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.051159635186195374, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.04729541391134262, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.043947793543338776, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.041503239423036575, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.038878295570611954, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.0368301086127758, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.03515012562274933, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.03392491862177849, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.033245790749788284, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.03273357078433037, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.03253508731722832, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.032854847609996796, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.034100744873285294, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.035645049065351486, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.0378568209707737, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.041654448956251144, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.047457948327064514, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.04766093194484711, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.0655544102191925, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.0622086301445961, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.10184012353420258, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.14415176212787628, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.1972719430923462, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.27495869994163513, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.41864728927612305, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.5154837369918823, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.6226772665977478, "validation/loss_043_lr2.2e+01_wd1.0e+00": 1.203100562095642, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.006422758102417, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.3306145668029785, "validation/loss_046_lr3.6e+01_wd1.0e+00": 4.104762554168701, "validation/loss_047_lr4.3e+01_wd1.0e+00": 4.910586833953857, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.0445220470428467, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.6416170634920635, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.6800595238095238, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.7589285714285714, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.8298611111111112, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.8683035714285714, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.892609126984127, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9079861111111112, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.9213789682539683, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9449404761904762, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9630456349206349, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.972718253968254, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9794146825396826, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9818948412698413, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9828869047619048, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9846230158730159, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9851190476190477, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9856150793650794, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9868551587301587, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9875992063492064, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9873511904761905, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9890873015873016, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9895833333333334, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9893353174603174, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9890873015873016, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9900793650793651, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9900793650793651, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9900793650793651, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9903273809523809, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9895833333333334, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9890873015873016, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9885912698412699, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9880952380952381, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.988343253968254, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9875992063492064, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9873511904761905, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9871031746031746, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9848710317460317, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9813988095238095, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9836309523809523, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9838789682539683, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9826388888888888, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9853670634920635, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9801587301587301, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9771825396825397, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9809027777777778, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9670138888888888, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9779265873015873, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9732142857142857, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.04365079365079365, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.4550926001375177, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.5293608670820132, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.685582882522445, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.7951021066023708, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.8463996278343062, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.8782553384342657, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.8956355584106748, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9123005833276397, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9396878668815608, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9600647229467376, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9695101718047299, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9763671977792795, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.978904564472486, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9803476862843816, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9829561370965558, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9830075521567851, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9840172031161272, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9859297320695937, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9865637166076804, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9858714127839414, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9875737814683522, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9883337561818069, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9877052103374343, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9877774787172432, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9888604305532821, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9888604305532821, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9889645614121628, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.989275501104457, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9886394000803869, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.987531135864701, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9869030720766561, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9866336315135549, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9870041944965463, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.98599436749824, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9842907394501643, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9851494698032343, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9825737565544328, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9764725508614495, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9802900901778513, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.980810950081785, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9799454196459697, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9810450660195554, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9769053267029127, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9719170916557774, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9776381726931288, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9560909715671058, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9742425835133995, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.968945230901066, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.003983342386384211, "id_best": 27, "lr_best": 0.00047999999999999996, "wd_best": 0.05, "train/loss_best": 0.02256741070188582, "validation/loss_best": 0.032854847609996796, "validation/acc_best": 0.9903273809523809, "validation/f1_best": 0.989275501104457} +{"epoch": 7, "train/lr": 0.00027969249556793234, "train/loss": 0.40271715484559534, "train/grad": 0.252299708686769, "train/loss_000_lr2.0e-02_wd1.0e+00": 1.4861908721923829, "train/loss_001_lr2.3e-02_wd1.0e+00": 1.347779541015625, "train/loss_002_lr2.8e-02_wd1.0e+00": 1.1535315704345703, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.9951823997497559, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.8616231536865234, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.700971188545227, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.5434010457992554, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.4003838121891022, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.2725447589159012, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.19113519728183748, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.14174145694822074, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.10224063644185662, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.08528071557171643, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.07315801167860628, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.06635363384149968, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.06163095468655229, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.05702137623913586, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.05254720391705632, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.04831504383124411, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.044871666748076675, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.0409929183870554, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.03731998224742711, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.03364988137967884, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.030059982538223267, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.02672809984534979, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.023165912963449956, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.020272668907418846, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.017740194611251356, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.014631938748061657, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.011264050817117096, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.008483450682833791, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.006946846041828394, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.004537989916279912, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.009642929723486304, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.006230360250920057, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.028636517403647303, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.027931369738653303, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.04732646752148867, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.05805556159466505, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.08146632288582623, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.15248659077100457, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.14822815075516702, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.2019623089581728, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.3584729964658618, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.7120756861101836, "train/loss_045_lr3.1e+01_wd1.0e+00": 1.2439314014371485, "train/loss_046_lr3.6e+01_wd1.0e+00": 1.9577070973441004, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.690414037629962, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.046875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.021166678005829453, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.02018589125946164, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.018685608566738666, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.017436431627720593, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.01643591433763504, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.01531851414591074, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.014212316521443426, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.012899239007383585, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.011198535810690373, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.009708284689113498, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.008452617232687771, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.007202762076631188, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.0067386923835147175, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.0064681985729839655, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.006316603624727577, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.0061957116518169646, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.006058053877786733, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.005884075989597477, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.005701778714428656, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.0055457445263164115, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.005363748723466415, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.005181625378027093, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0049820398425799795, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.004758949259412475, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0045480358845088635, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.004309234966931399, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0040716644024359995, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.003819664781331085, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0034481528093601808, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0029142042125022273, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.002398083984335244, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0020894604532622906, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0017162028487655333, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0025736424720071227, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0023508028045898756, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.007002004961266266, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.00699338694635351, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.009420764670875315, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.010935345270949916, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.01357097353972013, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.020024107119924067, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.021036586955803592, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.025993840218692336, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.03568905271515676, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.06768741791548401, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0878761707776187, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.12176300106190105, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.1276821012033208, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 1.3946667909622192, "validation/loss_001_lr2.3e-02_wd1.0e+00": 1.255887746810913, "validation/loss_002_lr2.8e-02_wd1.0e+00": 1.0644307136535645, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.9089587926864624, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.7764288783073425, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.6149564385414124, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.4582659900188446, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.32636016607284546, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.21812883019447327, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.15009468793869019, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.1100684106349945, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.08198689669370651, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.06958218663930893, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.05971013009548187, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.054014090448617935, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.05029407888650894, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.04686816409230232, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.04372767359018326, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.041017211973667145, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.03897044435143471, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.0370696522295475, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.035632818937301636, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.0345151461660862, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.03399234637618065, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.03392494469881058, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.03395633026957512, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.03457523137331009, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.03582557290792465, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.037868600338697433, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.04019376263022423, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.04104933515191078, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.040551453828811646, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.04298067465424538, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.04481545835733414, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.05185137316584587, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.10423015058040619, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.09244376420974731, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.16449995338916779, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.2088003307580948, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.3474351167678833, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.2927614152431488, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.5145341157913208, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.8315829038619995, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.7440103888511658, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.0348737239837646, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.550828218460083, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.542234182357788, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.010175943374634, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.0445220470428467, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.6927083333333334, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.7512400793650794, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.8395337301587301, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.8752480158730159, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.8921130952380952, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.910218253968254, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9250992063492064, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.9444444444444444, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9637896825396826, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9756944444444444, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9796626984126984, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9811507936507936, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9831349206349206, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9848710317460317, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9856150793650794, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9868551587301587, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9873511904761905, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.988343253968254, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.988343253968254, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9888392857142857, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9895833333333334, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9893353174603174, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9895833333333334, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9895833333333334, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9898313492063492, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9895833333333334, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9895833333333334, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9898313492063492, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9893353174603174, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9893353174603174, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9893353174603174, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.988343253968254, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9895833333333334, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9898313492063492, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9885912698412699, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9838789682539683, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9873511904761905, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9789186507936508, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9858630952380952, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9826388888888888, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9868551587301587, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9861111111111112, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9791666666666666, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9833829365079365, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9774305555555556, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9809027777777778, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9742063492063492, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9831349206349206, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.04365079365079365, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.5526050731060782, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.6685651055897466, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.8028152763129222, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.8527527748403169, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.875975013778061, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.8992959483659436, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.9180054380708181, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9388050781976605, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9602515473926052, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.972929682560518, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.976765697237252, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9784875105033064, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9812576755105069, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9833361386862093, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9838456069640412, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9857403960106298, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9863141143712036, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9875952082057302, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9871628606203833, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9875673460522744, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9884115952826581, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.987821807813494, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9881898252111887, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9881180043435054, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9882021314059608, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9883794704581554, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9885469536694957, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9887307045668271, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9876035946419671, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9875635026483678, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9879303112173302, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9866648438514675, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9886967715019905, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9873768677782626, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9861959403885746, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9785157843242839, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.98510988453383, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9736712896021716, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9810681958652154, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9789195228093026, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9841351466687349, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9829929461013781, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9757972432542393, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.981037328796376, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9766434805720668, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9762110462060363, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9705945156666919, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9797531987015169, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.003983342386384211, "id_best": 24, "lr_best": 0.0003, "wd_best": 0.05, "train/loss_best": 0.02672809984534979, "validation/loss_best": 0.03392494469881058, "validation/acc_best": 0.9898313492063492, "validation/f1_best": 0.9882021314059608} +{"epoch": 8, "train/lr": 0.0002612959497061927, "train/loss": 0.28328387513756753, "train/grad": 0.17013852208852767, "train/loss_000_lr2.0e-02_wd1.0e+00": 1.3105405807495116, "train/loss_001_lr2.3e-02_wd1.0e+00": 1.173387222290039, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.9854226875305175, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.832089614868164, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.7000658416748047, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.5398793125152588, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.39288035869598387, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.2796745979785919, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.18973468393087387, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.13343010663986207, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.10329524867236614, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.0828035761602223, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.07296098502352834, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.06454185243695974, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.05913750374689698, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.055103941438719634, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.05091245333664119, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.04668840760365128, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.04242803693749011, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.038838023208081725, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.03487763091921806, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.031360290134325626, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.027960538929328323, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.024841024596244096, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.02179900811985135, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.01822659431025386, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.014858010550960898, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.011969052273780107, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.008567783618345856, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.005513317957520485, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0034863515850156544, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.0023157955892384053, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.002085731402039528, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.006075099296867848, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.003223361689597368, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.027490837695077062, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.01296771719120443, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.03005050351843238, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.023669713605195285, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.056344660157337786, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.04330173472873867, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.09430495916865766, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.15988299962133168, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.15656826978549362, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.3731610925216228, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.5201557778008282, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.7233704666979611, "train/loss_047_lr4.3e+01_wd1.0e+00": 1.2417917193751782, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.046875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.019724662816151976, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.018637598752975465, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.01710153416264802, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.01589446034282446, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.014926447225734591, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.01375551123637706, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.012394026252441109, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.010896603816654533, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.009315664684399962, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.007908477417659014, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.006946409948868677, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.006344624086050316, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.006111617520218715, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.0059273426030995325, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.005807620647246949, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.005702281824778765, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.005570996680762619, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.005410817616502754, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.005224746133462759, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.005045109630009393, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.004837851301854244, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.0046381970361835554, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.004418034009213443, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.00418234839955403, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.003917284203635063, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0035489651749594487, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0031684803521056892, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.002788357060708222, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0022666232104529625, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0016574455037880397, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0011807159099043929, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0008710503643897027, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0007276541224291577, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0019525300941677414, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0010411613564662047, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.005258886065992385, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.004481817719785326, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.00799283886328392, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.006444119078657432, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.011792690053916073, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.010318199971023033, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.015222868427573966, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.019857699592683402, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.020552035484997525, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0362644090562668, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.051257428900162105, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.06305379352387762, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.09008739262397032, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 1.2471426725387573, "validation/loss_001_lr2.3e-02_wd1.0e+00": 1.111274242401123, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.9258559346199036, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.7732513546943665, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.64058917760849, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.479983389377594, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.3395036458969116, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.23767580091953278, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.15748897194862366, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.10908162593841553, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.08592747896909714, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.0699927881360054, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.0616496279835701, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.05441131070256233, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.04988929629325867, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.04665288329124451, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.04351552948355675, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.040559686720371246, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.03804812207818031, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.0361747071146965, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.034484829753637314, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.03361263871192932, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.03343204781413078, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.03335089236497879, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.03327460214495659, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.03403741866350174, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.03508502244949341, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.037145908921957016, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.04235469922423363, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.04575004056096077, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.04174395650625229, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.04079257324337959, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.04554998129606247, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.05148798227310181, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.049377720803022385, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.07764210551977158, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.10145482420921326, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.1570497751235962, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.12469042092561722, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.3568130135536194, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.34675028920173645, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.581384003162384, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.769768238067627, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.49935105443000793, "validation/loss_044_lr2.6e+01_wd1.0e+00": 1.8893154859542847, "validation/loss_045_lr3.1e+01_wd1.0e+00": 1.7320669889450073, "validation/loss_046_lr3.6e+01_wd1.0e+00": 2.4860777854919434, "validation/loss_047_lr4.3e+01_wd1.0e+00": 2.845527172088623, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.0445220470428467, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.7542162698412699, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.8196924603174603, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.8663194444444444, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.8844246031746031, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.8993055555555556, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.9174107142857143, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9357638888888888, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.9603174603174603, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9747023809523809, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9786706349206349, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9816468253968254, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9828869047619048, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9846230158730159, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9848710317460317, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9858630952380952, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9871031746031746, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9878472222222222, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9885912698412699, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9895833333333334, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9895833333333334, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9898313492063492, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9898313492063492, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9895833333333334, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9900793650793651, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9893353174603174, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9900793650793651, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9900793650793651, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9903273809523809, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9890873015873016, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9875992063492064, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9890873015873016, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9893353174603174, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9890873015873016, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9898313492063492, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9875992063492064, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9871031746031746, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9885912698412699, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9833829365079365, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9900793650793651, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.982390873015873, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9868551587301587, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9838789682539683, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9831349206349206, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9868551587301587, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9816468253968254, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.984375, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9781746031746031, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9799107142857143, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.04365079365079365, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.6735825696535889, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.7726152325161915, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.8378827830751212, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.8646732650954654, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.8834067954835453, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.907918660541081, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.9303243738394432, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.956668629748244, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9715819011824351, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9748632599803466, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.978491584539883, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9802922990936642, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9825436270824683, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9826414874505888, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.984187107129374, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9856154932538232, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9863698331864561, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9873083683470041, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9887991916184888, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9884026605291003, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9883998384502581, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9882192585536296, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9876277399077276, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9886603235404815, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9876228449992855, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9884971979972891, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9886466922091307, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9891330891264649, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9882502023397501, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9863075830895625, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9870252300972803, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9879344902321336, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9881618001371892, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9880126394949096, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9864389705584996, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9846180578385425, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9858994095976377, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9809594154217619, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9888759962696769, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9807844636625738, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9835447240625113, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9824473153443327, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9805173040004472, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9850179125202788, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9773167090746766, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9816430377999236, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.97709434123879, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9799768445087051, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.003983342386384211, "id_best": 27, "lr_best": 0.00047999999999999996, "wd_best": 0.05, "train/loss_best": 0.011969052273780107, "validation/loss_best": 0.037145908921957016, "validation/acc_best": 0.9903273809523809, "validation/f1_best": 0.9891330891264649} +{"epoch": 9, "train/lr": 0.00023803200426111704, "train/loss": 0.22525068037211896, "train/grad": 0.12807592403143644, "train/loss_000_lr2.0e-02_wd1.0e+00": 1.1914948272705077, "train/loss_001_lr2.3e-02_wd1.0e+00": 1.0571434593200684, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.8734770965576172, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.7209083461761474, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.5878953289985657, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.4314780056476593, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.30367559850215914, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.21428281247615813, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.14414498828351496, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.1047531819716096, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.08679019317030906, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.07370337406173348, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.06647304022684693, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.05967553896829486, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.05506305671297014, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.05143970673903823, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.04751991645433009, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.04344480813480914, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.039338632384315134, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.03595041866414249, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.032283110963180664, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.02894896020181477, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.02562633778899908, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.02240900047123432, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.019063756233081222, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.015183506179600953, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.011859329668805003, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.009037129683420062, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.005725187733769416, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.002924691867083311, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0018842378258705139, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.001366633241996169, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.0011978248972445726, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.0008350514527410269, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.0019167393166571855, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.009336129054427147, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.008962886547669769, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.03861273650079965, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.014775757091119885, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.025736734913662077, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.048520699767395856, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.058955237315967676, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.06950532510876656, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.08336773946881294, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.18423220141790808, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.15684572430327534, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.2853658296260983, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.6372777607943862, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.046875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.01888316583354026, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.01781244930345565, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.016388578582555057, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.01528756390325725, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.014342418275773525, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.01300270966719836, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.011389679790008813, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.009896462375763804, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.008317096366081387, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.007121504306560382, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.006599817977985367, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.006294236703542993, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.006158026288030669, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.006028114318614826, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.005925917153945193, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.005825546093110461, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.0056906375632388515, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.005502134925918654, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.005279870324302465, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.0050844078086083756, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.004843399310193491, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.004606825931405183, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.004338003273005597, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.004072233890401549, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.003736223207088187, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0032967170253687074, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0028769116672265225, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.002474620736011275, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0018830734839866635, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0010593523808074678, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.000718076445468796, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0005031814174435567, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0004504541987807897, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0004477127170662243, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0007079821884360627, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0029411997609283345, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0037562410392589208, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.00840746967315142, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.004157699717252889, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.006236180251476362, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.010979029870128984, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.012159672787958256, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.013516053614506614, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0157773523200804, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.029345261337490977, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.028580214365229485, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0441112394181052, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.054118622215158244, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 1.1319531202316284, "validation/loss_001_lr2.3e-02_wd1.0e+00": 1.0000383853912354, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.8187317848205566, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.6668074131011963, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.533871591091156, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.38168787956237793, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.26401692628860474, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.18361571431159973, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.12076479941606522, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.08862198144197464, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.07416610419750214, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.06307844817638397, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.056695692241191864, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.05088813975453377, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.047250695526599884, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.04429326951503754, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.04134386405348778, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.03831394389271736, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.03587651625275612, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.034073274582624435, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.032556354999542236, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.03173176199197769, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.03134872764348984, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.03131389245390892, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.03172210976481438, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.032899849116802216, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.034852951765060425, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.03692071884870529, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.03844796493649483, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.03877777233719826, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.0400342233479023, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.040037885308265686, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.04530468210577965, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.04348039627075195, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.04582934081554413, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.06903321295976639, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.11552181094884872, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.18668803572654724, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.15268439054489136, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.20321552455425262, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.3304998278617859, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.5180814266204834, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.6216216683387756, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.5377787351608276, "validation/loss_044_lr2.6e+01_wd1.0e+00": 1.4410187005996704, "validation/loss_045_lr3.1e+01_wd1.0e+00": 1.5023256540298462, "validation/loss_046_lr3.6e+01_wd1.0e+00": 1.6789829730987549, "validation/loss_047_lr4.3e+01_wd1.0e+00": 1.7143467664718628, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.0445220470428467, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.816468253968254, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.8563988095238095, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.886656746031746, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.904265873015873, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9154265873015873, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.9342757936507936, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9538690476190477, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.9704861111111112, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9791666666666666, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9811507936507936, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9833829365079365, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9848710317460317, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9853670634920635, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9861111111111112, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.986359126984127, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9873511904761905, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9880952380952381, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9893353174603174, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9898313492063492, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9898313492063492, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9903273809523809, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9905753968253969, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9908234126984127, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9903273809523809, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9905753968253969, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9905753968253969, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9903273809523809, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9900793650793651, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9898313492063492, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9903273809523809, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9893353174603174, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9898313492063492, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9905753968253969, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9903273809523809, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9878472222222222, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9880952380952381, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9868551587301587, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9851190476190477, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9888392857142857, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9875992063492064, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9853670634920635, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9851190476190477, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9858630952380952, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9848710317460317, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9828869047619048, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.982390873015873, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.980406746031746, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9831349206349206, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.04365079365079365, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.7655528882435823, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.8245143768455194, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.8698404576857639, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.8927194845547343, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.9059011743340848, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.9291618103248364, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.9493725860872972, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.966972957749105, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9764042236465258, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9782993620527721, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9809340040543786, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9829236396551237, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9835701796754303, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9850525664964606, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9861136562239814, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9867288241936135, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9868818048936348, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9884619483848903, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9887751176502829, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9884140099667191, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9886850616597235, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9892241256153296, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9892614407830975, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9890844230860552, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9894428197154226, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9890874421868956, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9888177121316852, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9882777791386295, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.988097570262816, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9888686715859671, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9877953066348394, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9880564782493279, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9887754967481942, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9887917541490869, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9862561131994655, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.98648357088829, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9841789298981214, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9833437496855107, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9874599036281466, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9848792072894254, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9819857167768034, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9826288978287275, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9821183687055217, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.981448003191884, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9794334311075839, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9799110256909034, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9786469876058116, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.982580075317001, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.003983342386384211, "id_best": 22, "lr_best": 0.00021599999999999996, "wd_best": 0.05, "train/loss_best": 0.02562633778899908, "validation/loss_best": 0.03134872764348984, "validation/acc_best": 0.9908234126984127, "validation/f1_best": 0.9892614407830975} +{"epoch": 10, "train/lr": 0.00021091808096876188, "train/loss": 0.1942994101345539, "train/grad": 0.0980628452822566, "train/loss_000_lr2.0e-02_wd1.0e+00": 1.0910476875305175, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.9609435081481934, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.7811647415161133, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.6290915489196778, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.4972641706466675, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.35279036581516265, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.24615779519081116, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.17325373768806457, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.11796847928315402, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.09150347128510475, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.07928036307916045, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.06922583718784153, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.06313703984953463, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.0570863831974566, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.05273031785152853, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.04917372087948024, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.04523653735406697, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.041136768739670516, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.036947876894846556, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.03335709448903799, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.029305654214695095, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.025491461250931026, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.021562984539195897, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.017726464653387664, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.014098979188129307, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.010305802784860135, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.007236331813037396, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.004933534292504192, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.00274484776891768, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.001441583102568984, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0008818954695016146, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.0005641634669154883, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.0005173251032829284, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.0003067862242460251, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.001758910259231925, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.00022395303472876548, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.004319905685260892, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.01810206296853721, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.004882818898186088, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.018670076178386806, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.030481522269546986, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.021711839651688932, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.04754204162396491, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.04832894813269377, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.1267177273426205, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.13943329449743033, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.16143188058398664, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.2445760437846184, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.046875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.017951313816010953, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.016941129877232015, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.015668387301266195, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.014679616913199425, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.01374554964248091, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.012307523749768734, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.010784948531072586, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.009379501678049565, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.007765712497057393, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.006848139663925394, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.006477000008453615, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.006203808546997607, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.0060406729212263595, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.005864549481775612, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.0057239052318618635, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.005601536760514137, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.00544132198614534, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.005249978274514433, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.005032663183228579, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.004818256467697211, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.004541981044167187, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.004237351385381771, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0038866645566304216, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.003481019775063032, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0030602357296447735, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0025628067566867683, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0020894140496238835, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.001657979579977109, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0010810146651783726, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0005962580722916755, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.00036909776125867213, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.00022789623706557906, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0002110619340987796, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.00018687468588666435, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.000503931489577667, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.00031980323476094697, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0017415445789818306, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.004876918308908002, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0014948288917468369, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.004075880076435512, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.007547756536600531, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.007084333214584312, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.008025527041904157, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.010791409193346417, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.021994941544651436, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.02047203712829055, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.029404494581382026, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.030537468462621037, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 1.0428712368011475, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.9139514565467834, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.7351090908050537, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.5827713012695312, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.4522456228733063, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.31434208154678345, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.2158128321170807, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.1486329883337021, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.09988056123256683, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.0780811607837677, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.06762807071208954, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.05871608853340149, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.053447175770998, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.04826943576335907, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.044835977256298065, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.04222138598561287, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.039615027606487274, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.03713928535580635, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.03508203849196434, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.03366680070757866, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.032560668885707855, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.03211978077888489, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.0322311669588089, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.03272758051753044, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.03378486633300781, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.035334836691617966, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.03680427372455597, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.03779935836791992, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.03942951560020447, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.040942125022411346, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.041496504098176956, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.04136749729514122, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.0450320728123188, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.0458952896296978, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.05191599205136299, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.061914149671792984, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.09980804473161697, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.15323996543884277, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.12521427869796753, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.2103872150182724, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.3374648690223694, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.4348987340927124, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.5416322946548462, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.5110203623771667, "validation/loss_044_lr2.6e+01_wd1.0e+00": 1.2746812105178833, "validation/loss_045_lr3.1e+01_wd1.0e+00": 1.379884958267212, "validation/loss_046_lr3.6e+01_wd1.0e+00": 1.4104689359664917, "validation/loss_047_lr4.3e+01_wd1.0e+00": 1.5883733034133911, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.0445220470428467, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.8435019841269841, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.8712797619047619, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.8950892857142857, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.9092261904761905, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9236111111111112, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.9424603174603174, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9640376984126984, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.9756944444444444, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.980406746031746, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9821428571428571, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9838789682539683, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9853670634920635, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.986359126984127, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9871031746031746, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9875992063492064, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.988343253968254, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9885912698412699, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9893353174603174, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9888392857142857, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9893353174603174, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9900793650793651, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9900793650793651, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9898313492063492, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9900793650793651, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9895833333333334, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9895833333333334, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9893353174603174, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9900793650793651, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9893353174603174, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9893353174603174, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9890873015873016, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9898313492063492, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9898313492063492, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9895833333333334, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.988343253968254, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9895833333333334, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9888392857142857, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9851190476190477, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9908234126984127, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9846230158730159, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9866071428571429, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.988343253968254, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9861111111111112, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9868551587301587, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9848710317460317, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9826388888888888, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9831349206349206, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9856150793650794, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.04365079365079365, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.8070397296619175, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.8463993328735372, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.8804202621667043, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.8963854188452712, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.9158710859062305, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.937051140587963, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.9614037007771159, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9726506355727805, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9774033462236441, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9789462224679727, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9812382109335583, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9828797030249128, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9845156385377236, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9853014804079192, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9862204192801426, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9871923203815085, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9879715040702999, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9885986210269428, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.987655426742114, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9876596769756053, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9880639006807252, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9883752819693383, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.987828216605285, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9882275951081942, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9876895734511593, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9876895734511593, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9875096846562944, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9882004242289766, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9872634880198911, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9871579275203599, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9873372873339376, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9878747863642171, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9882396954961374, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9881388627435573, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9869838674642525, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9875183712775805, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9863513707488328, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.983097112128553, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9900166919877711, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9816443292530612, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9842278330619355, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9872624647654288, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9832705823442377, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9838840001443588, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9823430507049341, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9809469325490385, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.981995240750716, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9823699374857574, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.003983342386384211, "id_best": 38, "lr_best": 0.00294, "wd_best": 0.05, "train/loss_best": 0.004882818898186088, "validation/loss_best": 0.12521427869796753, "validation/acc_best": 0.9908234126984127, "validation/f1_best": 0.9900166919877711} +{"epoch": 11, "train/lr": 0.00018113997589164516, "train/loss": 0.17082401022315025, "train/grad": 0.07210005098953844, "train/loss_000_lr2.0e-02_wd1.0e+00": 1.0073695373535156, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.8804527568817139, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.7029568862915039, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.5520131850242614, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.4254411327838898, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.2969565600156784, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.20680651262402536, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.1453757458180189, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.10298336438834667, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.08455759985372424, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.07545837785117328, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.06742617092095315, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.062198632210493085, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.056705109365284445, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.05253460040315985, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.04898768994957209, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.044989242134615776, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.04074545950628817, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.03638797891326249, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.032668166030198335, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.028404897386208175, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.024462114060297607, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.02030914372764528, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.016282181972637772, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.012266299733892084, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.0079452617559582, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.004757109209895134, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0028317317832261325, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.001469746958464384, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0008740829955786466, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0005968754645437002, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.00040319360792636874, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.00025939865969121456, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.0001519099436700344, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.0002694978378713131, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.896588459610939e-05, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.0023736673220992087, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.005939259994775057, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.001678933184593916, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.006027519525960087, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.006350308628752827, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.02209666374139488, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.006420718440786004, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.022324331272393465, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.05898019199259579, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.044281880939379334, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.05066564982756972, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.05202545782551169, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.046875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.017305424539372324, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.01629066079389304, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.014972057370468974, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.013858186923898756, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.012693370152264833, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.010977422436699271, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.00939307594904676, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.00805782332085073, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.006844525327906013, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.006351281863171607, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.0061588022951036695, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.006007598733413033, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.005891095278202556, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.005753024896839634, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.005620976811624132, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.005484528112574481, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.0053115861100377516, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.0051193494809558615, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.004914355728542433, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.0047218972316477445, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.0044908359809778635, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.004235746687772917, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0038938652332581114, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.003478058047476225, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.00299021054583136, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0023189697725320003, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.00166419968707487, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0011062861555546988, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0006079086354657193, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0003695671460900485, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0002567000265207753, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.00017192940047607407, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0001243833109356274, "train/grad_033_lr4.3e+00_wd1.0e+00": 7.610607547690052e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.00016845377518961868, "train/grad_035_lr6.0e+00_wd1.0e+00": 3.977166492086681e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0013478092376929818, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0023659448723152804, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0007819207741298454, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0022140664641505606, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.002547459888840511, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.005297972509047833, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.003702192621455766, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.004852966086099121, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.015008634747910685, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.012091650661602853, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.012439516063299072, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.014180074090545789, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.9743857383728027, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.8477289080619812, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.669762372970581, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.5179242491722107, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.3922480344772339, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.26872891187667847, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.18335027992725372, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.12526050209999084, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.08768527954816818, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.07134521752595901, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.06298315525054932, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.055484339594841, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.050895389169454575, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.04643627256155014, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.04341254010796547, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.041145723313093185, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.038780227303504944, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.03665278106927872, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.03478952869772911, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.03362894430756569, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.032797783613204956, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.03255116567015648, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.03268918767571449, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.03319384157657623, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.03403117507696152, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.03551488742232323, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.03778102993965149, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.03890329226851463, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.039827946573495865, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.04091262444853783, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.04094686731696129, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.04121548682451248, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.04388963431119919, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.04494840279221535, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.0480245016515255, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.06157602369785309, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.09879937767982483, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.17819812893867493, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.115361288189888, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.2275112122297287, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.2692570090293884, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.4104517698287964, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.4094075858592987, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.3965950608253479, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.8421583771705627, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.9860270619392395, "validation/loss_046_lr3.6e+01_wd1.0e+00": 1.4094865322113037, "validation/loss_047_lr4.3e+01_wd1.0e+00": 1.3038922548294067, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.0445220470428467, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.8588789682539683, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.8787202380952381, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.8983134920634921, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.9131944444444444, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9273313492063492, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.9508928571428571, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9685019841269841, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.9776785714285714, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9806547619047619, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9833829365079365, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9846230158730159, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9848710317460317, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9853670634920635, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9858630952380952, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9878472222222222, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9888392857142857, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9893353174603174, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9890873015873016, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.988343253968254, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9885912698412699, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9885912698412699, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9895833333333334, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9895833333333334, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9893353174603174, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9895833333333334, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9898313492063492, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9895833333333334, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9893353174603174, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9898313492063492, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9893353174603174, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9893353174603174, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9895833333333334, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9915674603174603, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9900793650793651, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9900793650793651, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9895833333333334, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9878472222222222, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9848710317460317, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9910714285714286, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9846230158730159, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9893353174603174, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9866071428571429, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9880952380952381, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9861111111111112, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.986359126984127, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9841269841269841, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9833829365079365, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9856150793650794, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.04365079365079365, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.8275519930514516, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.8565371212366282, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.8855963017510046, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.9028927327956984, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.919593035745909, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.9461631643344541, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.9647225217318772, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9749464094241483, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9782097743330156, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9809273619966754, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9826418912810523, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9828006353352604, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.983893939573155, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.984277860718688, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9867649561274955, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9879562909166657, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9884658344417124, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.988192726200299, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9869622299207657, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9870941973050114, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9870932781899046, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9883517297690625, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9883517297690625, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9878544751683493, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9880691078284825, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9878667048790656, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9877039675843191, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9875277069228293, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.988288599934362, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9875550232504771, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9876542085777638, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.987703362489359, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9899431728392762, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9886549298861821, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9888183177386379, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9876097237998932, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9842935646694222, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9805859670124132, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9889099207834294, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9802275026588114, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9876775363486897, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9848921195814885, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9843618794428683, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.983613792872484, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9845669951956397, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9793303167067087, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.980513067870744, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9836602174882048, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.003983342386384211, "id_best": 32, "lr_best": 0.0011099999999999999, "wd_best": 0.05, "train/loss_best": 0.00025939865969121456, "validation/loss_best": 0.04388963431119919, "validation/acc_best": 0.9915674603174603, "validation/f1_best": 0.9899431728392762} +{"epoch": 12, "train/lr": 0.0001499999999999999, "train/loss": 0.16112343154847622, "train/grad": 0.057444565482437614, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.9573060035705566, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.8316418361663819, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.6538818836212158, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.5030018424987793, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.3811465334892273, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.2643245154619217, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.1836403349786997, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.1290319235995412, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.09530499313026666, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.08062089741230011, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.07280823482200503, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.06529812499880791, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.0602427523303777, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.054575297217816114, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.05028608664870262, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.04657892513088882, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.042305152993649245, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.03780049992725253, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.03330809133127332, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.029481252143159508, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.02524277651682496, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.0213030194491148, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.017311475668102504, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.01337236183695495, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.009451764402911067, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.005494606764987111, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.0031379639264196156, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0019011329021304845, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0010999639332294464, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0006792067922651768, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.00047947492450475695, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.00035833610221743586, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.00024762016721069813, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.0001451650634407997, "train/loss_034_lr5.1e+00_wd1.0e+00": 9.846975095570087e-05, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.729435615241528e-05, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.752600401639938e-05, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.0016694639902561904, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.0015119783394038676, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.008449591165408492, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.004744124915450811, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.004843873754143715, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.011358781345188617, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.009474232569336891, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.021365321716293694, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.021553335478529334, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.026611370099708438, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.06360789781436324, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.046875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.01683472958859056, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.015915749561972916, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.014714933671057225, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.013605614230036735, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.012381957485340536, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.010731437087524682, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.009235520490910858, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.007803024996537716, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.006729917787015438, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.006354712905595079, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.006188482524594292, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.0060253865417325865, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.005900164248305373, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.0057202720124041664, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.0055556911672465506, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.005389542940538377, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.005173239391297102, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.004919240887393244, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.0046503704352653585, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.004408241752244067, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.004116228904749732, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.0038015086208179126, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.003411535077611916, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.002956236104510026, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.002417376351513667, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0017066070913278964, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0011365845113323304, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0007493270056511392, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.00044302523541773554, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.00025819344322371764, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.00017875894746794075, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.00013542524083277386, "train/grad_032_lr3.7e+00_wd1.0e+00": 9.855272910499479e-05, "train/grad_033_lr4.3e+00_wd1.0e+00": 6.764657916392026e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 5.00761142347983e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 2.930665498656282e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 5.984088877232764e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.001365419232876415, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0004814545617401078, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0019094553819336386, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0014313503250333256, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.001628066450579033, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.003285627310959393, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.004360883623750839, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.00436279796676034, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.004037144407925687, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0096101696936912, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.008027779479712756, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.9221826195716858, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.7969310879707336, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.619109570980072, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.46878233551979065, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.3495020270347595, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.237595334649086, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.16079431772232056, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.11018095910549164, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.08041088283061981, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.06711053103208542, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.059925634413957596, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.053250912576913834, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.04910478740930557, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.044891513884067535, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.04194703325629234, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.039789967238903046, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.03739658370614052, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.03535541519522667, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.033632952719926834, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.0325743705034256, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.03200191631913185, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.03207879140973091, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.032782357186079025, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.03422661870718002, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.03603622689843178, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.037926897406578064, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.03963436186313629, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.04065067693591118, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.04119367152452469, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.04214346781373024, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.042087748646736145, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.0422276109457016, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.0444098562002182, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.04554086923599243, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.047589804977178574, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.0599466897547245, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.0941164568066597, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.1902286261320114, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.11622834950685501, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.17530417442321777, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.309163898229599, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.3804170489311218, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.4213162362575531, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.4594077467918396, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.7453259825706482, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.8413577079772949, "validation/loss_046_lr3.6e+01_wd1.0e+00": 1.2010695934295654, "validation/loss_047_lr4.3e+01_wd1.0e+00": 1.0597048997879028, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.0445220470428467, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.8707837301587301, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.888640873015873, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.9074900793650794, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.9231150793650794, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9372519841269841, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.9590773809523809, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9737103174603174, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.9799107142857143, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9821428571428571, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9833829365079365, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9846230158730159, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9848710317460317, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9853670634920635, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9875992063492064, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9880952380952381, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9890873015873016, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9890873015873016, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9893353174603174, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9893353174603174, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9895833333333334, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9900793650793651, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9900793650793651, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9895833333333334, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9893353174603174, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9890873015873016, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9888392857142857, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9885912698412699, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9885912698412699, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9893353174603174, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9898313492063492, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9888392857142857, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9898313492063492, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9905753968253969, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9903273809523809, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9903273809523809, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9895833333333334, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9888392857142857, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9836309523809523, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9908234126984127, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9868551587301587, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9878472222222222, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9871031746031746, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9885912698412699, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9851190476190477, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9861111111111112, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9851190476190477, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9831349206349206, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9871031746031746, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.04365079365079365, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.8457817035399092, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.8731800968389094, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.8978619670774454, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.916218861491472, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.9315880336525715, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.9557140095557027, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.9704039292129482, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9769458383554651, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9792118723512059, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9812796188556417, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.983058926150729, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9829927338907423, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9837650431068605, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9867545537457173, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9873619869654869, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.988282558160408, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.987890353897044, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9880212539703374, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9879134007365926, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9882759231827662, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9886365396069744, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9886365396069744, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9877283873981944, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9874225452358687, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9869220712824502, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9866117961777754, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9864513396420274, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9864513396420274, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9870797804455972, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9876001559534823, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9864220151131524, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.988234739857579, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9887766502032759, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9888352022495532, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9889982719579743, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9876097237998932, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9860720028977525, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9818411660964489, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.989270829681345, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9844009143253859, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9863502251269535, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9844356910333352, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9862189207661929, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9823341657457841, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9836762838517357, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9822595047235823, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.980276842546122, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9851682777876443, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.003983342386384211, "id_best": 38, "lr_best": 0.00294, "wd_best": 0.05, "train/loss_best": 0.0015119783394038676, "validation/loss_best": 0.11622834950685501, "validation/acc_best": 0.9908234126984127, "validation/f1_best": 0.989270829681345} +{"epoch": 13, "train/lr": 0.00011886002410835478, "train/loss": 0.14986751656979322, "train/grad": 0.04759276702068746, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.9020515060424805, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.776446681022644, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.597994818687439, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.4489754951000214, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.33409523248672485, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.22915882170200347, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.15734750121831895, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.11069032825529575, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.08445567656308413, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.07271293845959008, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.0659728367254138, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.05927722948603332, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.05461322925053537, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.04933571208268404, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.045166269233450296, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.04167484952136874, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.03774200724437833, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.033598519880324605, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.029506396688520908, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.025991908758878707, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.022053025411441923, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.01838364449329674, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.014660015106201171, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.010964733613654971, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.007487681647762656, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.0043153410498052835, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.0024911658838391304, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0015451468620449305, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0008816585037857294, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0005624992679804563, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0004033107403665781, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.00031413920223712923, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.00021742492914199828, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.0001367013342678547, "train/loss_034_lr5.1e+00_wd1.0e+00": 8.605701848864556e-05, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.450055606663227e-05, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.020374871790409e-05, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.0017039264366030694, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.00017614447511732578, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.0009881647489964963, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.001734093464910984, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.003191743241623044, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.0076356119755655524, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.0020291260723024605, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.0057715499587357045, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.009928622897714377, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.011806728141382337, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.010302543211728334, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.046875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.016347477375529707, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.015435220105573536, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.014207577779889107, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.013022285439074039, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.011737169658299535, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.010165506650228053, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.008748140546958893, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.0073586602648720145, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.0064864481985569, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.006178066879510879, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.006022926652804017, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.005871128648286685, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.005747135762940161, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.005586157764773816, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.005422610596870072, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.005261627981672064, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.005050379624590278, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.00480962151021231, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.00454364020813955, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.004284463979129214, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.00394947347624111, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.0035826113303483, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.003151311143737985, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0026537875139911195, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0020830287223361664, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0013868602445654687, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.00089341110233363, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0005865619293763302, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.00034123675508453745, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.00021971649331135269, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0001553186254295724, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.00011893147232058254, "train/grad_032_lr3.7e+00_wd1.0e+00": 8.489290292573059e-05, "train/grad_033_lr4.3e+00_wd1.0e+00": 6.0547977460601034e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 4.2454005248373503e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 2.75259249356985e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 1.6700675955032412e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0007086564709313365, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.00012839150965203688, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0007245921414191889, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0008239319734478081, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0008770597686170148, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0016212053909313332, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0009010219693910643, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0012982819095593032, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0021505400720140534, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.003437725437536367, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.004267405874404257, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.8831843137741089, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.7588741779327393, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.581440806388855, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.43326860666275024, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.31964558362960815, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.21615862846374512, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.14517247676849365, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.10032042115926743, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.07571971416473389, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.06420733779668808, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.05774927884340286, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.05166070535778999, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.04777194932103157, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.043878618627786636, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.04106886684894562, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.039015993475914, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.03696157783269882, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.03505660966038704, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.03359870985150337, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.032651737332344055, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.03217054530978203, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.03198067098855972, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.032190896570682526, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.033184781670570374, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.03453374281525612, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.036609649658203125, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.038519080728292465, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.039926402270793915, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.040949929505586624, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.042388513684272766, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.04259197786450386, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.042596906423568726, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.04483496770262718, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.045346084982156754, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.04780138283967972, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.0585193932056427, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.09180136770009995, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.15478666126728058, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.12081614136695862, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.19434502720832825, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.260722815990448, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.3329477906227112, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.34781429171562195, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.3697901666164398, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.8411612510681152, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.7776188850402832, "validation/loss_046_lr3.6e+01_wd1.0e+00": 1.0583537817001343, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.8295946717262268, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.0445220470428467, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.8757440476190477, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.8931051587301587, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.9112103174603174, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.9246031746031746, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9424603174603174, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.9625496031746031, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9756944444444444, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.980406746031746, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9833829365079365, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9846230158730159, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9856150793650794, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9851190476190477, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9856150793650794, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9875992063492064, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.988343253968254, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9888392857142857, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9888392857142857, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9880952380952381, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9888392857142857, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9893353174603174, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9903273809523809, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9903273809523809, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9900793650793651, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9898313492063492, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9895833333333334, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9898313492063492, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9895833333333334, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9895833333333334, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9898313492063492, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9898313492063492, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9895833333333334, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9898313492063492, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9903273809523809, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9903273809523809, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9900793650793651, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9895833333333334, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9893353174603174, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9858630952380952, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9898313492063492, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9866071428571429, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9885912698412699, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9868551587301587, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9885912698412699, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9866071428571429, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.984375, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.986359126984127, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9851190476190477, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9875992063492064, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.04365079365079365, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.8540967537947323, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.8787172873595039, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.9014793614968798, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.9179242177902422, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.9376205668742905, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.959512346787771, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.9726719032449684, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.977663304036852, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.981481627268111, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9828355633909102, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.983887550713546, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9838951400608688, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9847969967837845, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.986543727007068, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9870617227887027, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9879323158490297, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9875216104541982, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9865730807101346, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9873294006799915, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.987689824596756, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9888136354668005, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9889447142757974, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9884398957090929, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9876467057242075, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9874705281902194, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.988005694779607, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9878436600552063, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9878462180723964, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9879253775414656, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9882800458210904, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9879296250803838, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9881095999395377, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9885984036765441, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9888352022495532, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9886407775424805, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9876097237998932, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9868477876160479, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9834656285853816, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9862498932272697, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9842319447779592, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9873352953712956, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9842430986572788, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.985989824772618, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9839802380026668, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9802625171685106, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9837872306965086, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9831104321031319, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.986416096461729, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.003983342386384211, "id_best": 20, "lr_best": 0.000156, "wd_best": 0.05, "train/loss_best": 0.022053025411441923, "validation/loss_best": 0.03217054530978203, "validation/acc_best": 0.9903273809523809, "validation/f1_best": 0.9888136354668005} +{"epoch": 14, "train/lr": 8.9081919031238e-05, "train/loss": 0.14588073756545783, "train/grad": 0.04406142768450081, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.8731775856018067, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.7488545560836792, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.5718301153182983, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.425726078748703, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.31614580631256106, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.21725395917892457, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.14907792203128337, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.10685829970985651, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.08381107495166361, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.07280289229936898, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.06623006475158036, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.059616647297516465, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.05494415448978543, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.04964283250272274, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.04544864548370242, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.04184398592449725, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.03782640092074871, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.03357066011056304, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.029386191815137862, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.02580627621151507, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.02180968045257032, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.018045808114111425, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.014134763209149241, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.010166905913501978, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.0065876849181950095, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.0035221932083368303, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.00200656714849174, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.001282532438635826, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0007964068651199341, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0005231886636465788, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0003781730867922306, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.0002921624667942524, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.00020651714876294137, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.00013054095208644867, "train/loss_034_lr5.1e+00_wd1.0e+00": 8.97073931992054e-05, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.745152615010738e-05, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.071385107934475e-05, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.0527763515710831e-05, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.895945847034454e-06, "train/loss_039_lr1.2e+01_wd1.0e+00": 6.453542038798333e-05, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.00021419214084744453, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.1756839230656623e-05, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.0023345323186367752, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.0004891596734523773, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.001841349033638835, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.003883678987622261, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.002541003869846463, "train/loss_047_lr4.3e+01_wd1.0e+00": 1.1484501883387565e-05, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.046875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.016375152370892467, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.015456284265965223, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.014186323033645748, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.012931511620990932, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.011615865752100945, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.01007180638378486, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.008610687444452196, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.0072616354061756285, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.006557324993191287, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.006310208974173293, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.006175920306704938, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.006031400296487846, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.005895957006141543, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.005697054384509102, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.005503803246247116, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.0053140330340829675, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.0050861984156654215, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.004812609785294626, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.004516674481274094, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.004229315433476586, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.0038774626280064697, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.0035033763773390093, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.003051972847461002, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0025270458024169782, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0019063942023058189, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0011944193870476738, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0007371626190888492, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.00048575625825833415, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.000303901616357507, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.00019883775109860835, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.00014502621181236463, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.00011253176784407514, "train/grad_032_lr3.7e+00_wd1.0e+00": 8.157491731225264e-05, "train/grad_033_lr4.3e+00_wd1.0e+00": 5.762235412362315e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 4.2386660402939925e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 2.697464236967484e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 1.0668657439582008e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 1.606096291750245e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.00014519405523905106, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0001379315866797685, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.00030638229517634393, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0001571446705881369, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0006962391388541834, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0003296328537291098, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0009261460965369569, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0014420735339922596, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.001965137937132232, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0005110319157060284, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.855219304561615, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.7314881682395935, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.5544382929801941, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.4083061218261719, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.2992614209651947, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.20155592262744904, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.13465654850006104, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.09446106106042862, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.07287994772195816, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.06253639608621597, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.056446678936481476, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.05068816617131233, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.04690937325358391, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.04312451183795929, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.0404803492128849, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.038423553109169006, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.036288071423769, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.03453816473484039, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.03324732929468155, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.032606128603219986, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.03240205720067024, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.032668158411979675, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.03333554044365883, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.03429711237549782, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.03577042743563652, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.03763335943222046, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.039648957550525665, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.04105310142040253, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.0421106293797493, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.04324587062001228, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.0432819239795208, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.043438754975795746, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.04535848647356033, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.04534950107336044, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.04794168844819069, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.05820513516664505, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.0900593250989914, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.1501433402299881, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.12381494790315628, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.1518544703722, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.25749072432518005, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.34927472472190857, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.31353890895843506, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.3378889560699463, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.6603841781616211, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.7357271909713745, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.954341471195221, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.7477921843528748, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.0445220470428467, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.8821924603174603, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.8973214285714286, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.9134424603174603, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.9283234126984127, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9444444444444444, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.9660218253968254, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9769345238095238, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.9809027777777778, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9828869047619048, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9846230158730159, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9851190476190477, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9858630952380952, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.986359126984127, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9878472222222222, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9885912698412699, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9893353174603174, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9895833333333334, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9893353174603174, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9903273809523809, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9903273809523809, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9900793650793651, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9903273809523809, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9903273809523809, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9898313492063492, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9893353174603174, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9893353174603174, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9890873015873016, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9893353174603174, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9895833333333334, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9895833333333334, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9895833333333334, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9898313492063492, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9895833333333334, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9903273809523809, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9898313492063492, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9900793650793651, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9893353174603174, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9851190476190477, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9905753968253969, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9873511904761905, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9880952380952381, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.986359126984127, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9890873015873016, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9868551587301587, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.986359126984127, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9868551587301587, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.984375, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9878472222222222, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.04365079365079365, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.8632741332881492, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.8843787352972428, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.9048930742801028, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.9212988159364327, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.9398375540055849, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.9624607094763769, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.9738455868543587, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9785806965878626, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9803989659463396, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9822847690977642, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9831587259357949, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9840606534719741, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9846219698085444, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9867548791566049, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9877487242360721, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9886420338629558, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.98860103742017, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9878696875676428, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9889968626116847, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.988818138556559, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.988239256076787, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9884069277153807, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9886311526577336, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9880066268027458, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9874642805167458, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9874675831361621, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9871715020561335, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9875316798525066, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.987799334843353, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9879169802509219, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9881099672617637, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9878845869027929, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9884218038811047, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9888352022495532, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9884604581700126, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9884220953500825, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9870116124510101, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9829315573248132, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9879011457287153, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9847701277697425, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9855483558539186, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9836998223454985, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9868233639132178, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9839798101736486, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9842269978724499, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9842860167092065, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.982956480015639, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9862014793992674, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.003983342386384211, "id_best": 38, "lr_best": 0.00294, "wd_best": 0.05, "train/loss_best": 3.895945847034454e-06, "validation/loss_best": 0.12381494790315628, "validation/acc_best": 0.9905753968253969, "validation/f1_best": 0.9879011457287153} +{"epoch": 15, "train/lr": 6.196799573888289e-05, "train/loss": 0.14025708358734845, "train/grad": 0.04108051717281341, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.8441429996490478, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.7197532272338867, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.5421647334098816, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.397805780172348, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.2922723615169525, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.19845917850732803, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.13421204268932344, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.0962252544797957, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.07612823024392128, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.06620597346685826, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.06026281577534973, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.05405615767464042, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.049672522842884065, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.04454558733850718, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.04051053182221949, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.03709229671396315, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.03319546848535538, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.029181698486208916, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.02516451194882393, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.021771454336121678, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.017926097828894854, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.014357615560293198, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.010701840817928314, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.0072772116959095, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.004500544779002667, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.002466311492025852, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.0014842955395579338, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0009988055098801851, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0006352444179356098, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0004253363236784935, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0003117782529443502, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.00024558632634580135, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.00017426775768399237, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.00010926470160484314, "train/loss_034_lr5.1e+00_wd1.0e+00": 7.815636694431304e-05, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.9529156163334845e-05, "train/loss_036_lr7.1e+00_wd1.0e+00": 9.509539231657983e-06, "train/loss_037_lr8.3e+00_wd1.0e+00": 4.864251241087913e-06, "train/loss_038_lr9.8e+00_wd1.0e+00": 5.290284752845764e-06, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.032330423593521e-06, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.417108207941055e-05, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.1269468814134597e-06, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.0009575601574033499, "train/loss_043_lr2.2e+01_wd1.0e+00": 1.5596114099025725e-06, "train/loss_044_lr2.6e+01_wd1.0e+00": 5.7590454816818236e-05, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.00010257165879011154, "train/loss_046_lr3.6e+01_wd1.0e+00": 1.992657780647278e-07, "train/loss_047_lr4.3e+01_wd1.0e+00": 1.0486692190170288e-08, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.046875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.016067101918160916, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.015195324141532183, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.013955017905682326, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.01267749045509845, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.01133449116256088, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.009749303283169865, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.008295360777992755, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.007102462373441085, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.00653885857318528, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.006297401536721736, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.006161682130768895, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.005993831034284085, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.005847377524769399, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.00563316866842797, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.005427785704087001, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.005237903922970872, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.005013979217910674, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.004771587810100755, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.004517837929888628, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.004277393520969781, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.003948453192206216, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.0035688571420905645, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0030657813451398395, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.002442035395979474, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0017449002710054628, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0010783550065025338, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0006712604138738243, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.00044847536761153604, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0002793024308994063, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.00018470483296368912, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0001333481880828913, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.00010423962537970511, "train/grad_032_lr3.7e+00_wd1.0e+00": 7.522847846303194e-05, "train/grad_033_lr4.3e+00_wd1.0e+00": 5.478450509599497e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 3.9430524725503344e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 2.5045140430073333e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 1.126178516973303e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 7.870548493376277e-06, "train/grad_038_lr9.8e+00_wd1.0e+00": 1.3761902371148823e-05, "train/grad_039_lr1.2e+01_wd1.0e+00": 7.562981382033589e-06, "train/grad_040_lr1.4e+01_wd1.0e+00": 3.8390953219631324e-05, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.00010258261337061114, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0001471289315355407, "train/grad_043_lr2.2e+01_wd1.0e+00": 4.5201113435221824e-05, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.00011454872391795867, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0003254276919247588, "train/grad_046_lr3.6e+01_wd1.0e+00": 6.760374759341148e-06, "train/grad_047_lr4.3e+01_wd1.0e+00": 2.0898993991930762e-05, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.8362442255020142, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.712848424911499, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.5360350012779236, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.3916866183280945, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.2861146628856659, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.19195321202278137, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.12774233520030975, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.09060543775558472, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.07085800170898438, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.061239685863256454, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.05547088012099266, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.05002083256840706, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.04639827460050583, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.04274939373135567, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.0400816835463047, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.038067031651735306, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.03603396192193031, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.034286659210920334, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.03307465463876724, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.03226044774055481, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.03209695592522621, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.032332196831703186, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.03301941975951195, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.03412410244345665, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.03556662052869797, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.0374169796705246, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.03949151933193207, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.040667008608579636, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.041858870536088943, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.042971715331077576, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.043161146342754364, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.043295640498399734, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.0448819100856781, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.04554038494825363, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.04744339734315872, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.0574258491396904, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.08862535655498505, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.14749054610729218, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.11816896498203278, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.14893952012062073, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.25077250599861145, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.31841009855270386, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.3102688491344452, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.3288727104663849, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.627921462059021, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.6963233351707458, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.9106629490852356, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.7002464532852173, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.0445220470428467, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.8831845238095238, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.8973214285714286, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.9149305555555556, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.9300595238095238, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9459325396825397, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.9677579365079365, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9774305555555556, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.9813988095238095, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9836309523809523, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9848710317460317, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9851190476190477, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9853670634920635, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9866071428571429, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9878472222222222, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9885912698412699, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9890873015873016, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9885912698412699, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9885912698412699, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9895833333333334, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9898313492063492, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9900793650793651, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9900793650793651, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9900793650793651, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9890873015873016, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9893353174603174, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9890873015873016, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9890873015873016, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9898313492063492, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9895833333333334, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9900793650793651, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9893353174603174, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9898313492063492, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9900793650793651, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9900793650793651, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9903273809523809, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9900793650793651, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9893353174603174, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9851190476190477, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9905753968253969, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9873511904761905, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.988343253968254, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9868551587301587, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9890873015873016, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9868551587301587, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9873511904761905, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9866071428571429, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9848710317460317, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.988343253968254, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.04365079365079365, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.8658192831079329, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.8843688029521265, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.906206151408043, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.9232624067767387, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.9411004482733997, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.9646982106972614, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.9748835138383091, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9788886634776003, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9816616039623076, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9830637295647611, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9831666949010246, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9837109125880994, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9855399444458984, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9867711048774865, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9877533040687856, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9882889388712266, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9874816225859481, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9869370278169062, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9879172024671745, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9880978942944212, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9882785381675495, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9886707227402342, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9883743878689532, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9871526230107626, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9873365043271652, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9871715020561335, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9871715020561335, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9883389425521655, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9877978170110399, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9881445676150351, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9873883434892343, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9878845869027929, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9884176118957132, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9886553225834783, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9889982719579743, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9884220953500825, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9870116124510101, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9829315573248132, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9879011457287153, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9847701277697425, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9857290207584034, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9842396318449418, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9867689553937262, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9839802140989621, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9850732166258506, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9840726226735802, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9833166467547331, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9869641813839232, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.003983342386384211, "id_best": 38, "lr_best": 0.00294, "wd_best": 0.05, "train/loss_best": 5.290284752845764e-06, "validation/loss_best": 0.11816896498203278, "validation/acc_best": 0.9905753968253969, "validation/f1_best": 0.9879011457287153} +{"epoch": 16, "train/lr": 3.870405029380728e-05, "train/loss": 0.13991975411772728, "train/grad": 0.04062297632917762, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.8343267726898194, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.7107765579223633, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.5340065455436707, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.39093721032142636, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.28749885559082033, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.19608811125159264, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.13356352563947438, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.09745490664616227, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.07845780454576015, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.06887360547669232, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.06288455142639578, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.05666645222343505, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.05215251488611102, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.04684114383533597, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.04251470310613513, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.038914430253207684, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.03479021042585373, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.03046952693723142, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.026123447939753533, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.02252519404515624, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.018462193440645935, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.014699284620583057, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.010933481203392149, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.0074542287085205316, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.004644662942737341, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.0025170559901744128, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.0014989221654832362, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0010026620049029588, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0006502067483961583, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0004380846582353115, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0003233195282518864, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.00025580918416380884, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.0001837371289730072, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.0001144659798592329, "train/loss_034_lr5.1e+00_wd1.0e+00": 8.249243721365929e-05, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.677763976156712e-05, "train/loss_036_lr7.1e+00_wd1.0e+00": 9.56457108259201e-06, "train/loss_037_lr8.3e+00_wd1.0e+00": 4.769405350089073e-06, "train/loss_038_lr9.8e+00_wd1.0e+00": 4.903273656964302e-06, "train/loss_039_lr1.2e+01_wd1.0e+00": 4.633879289031029e-06, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.043928787112236e-06, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.0228343307971954e-06, "train/loss_042_lr1.9e+01_wd1.0e+00": 4.1970983147621157e-07, "train/loss_043_lr2.2e+01_wd1.0e+00": 1.4781486243009568e-06, "train/loss_044_lr2.6e+01_wd1.0e+00": 8.130446076393127e-08, "train/loss_045_lr3.1e+01_wd1.0e+00": 1.421002671122551e-06, "train/loss_046_lr3.6e+01_wd1.0e+00": 9.844079613685608e-08, "train/loss_047_lr4.3e+01_wd1.0e+00": 1.938268542289734e-07, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.046875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.016102193612605332, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.01522674667648971, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.013980649067088962, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.012672907738015056, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.011329763710964471, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.009820481580682099, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.008353539465460927, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.007138451486825943, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.0065523420670069756, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.00631113511219155, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.006151793327298947, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.005973422130336985, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.0058129982213722545, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.005579384625016246, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.00534596317098476, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.005134266651584767, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.004868511183012743, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.004570330320784705, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.004255663125877618, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.003975376905873418, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.003617137626206386, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.0032200570096028967, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0027340199230457074, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.00214532801459427, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0015135772593203002, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0009131949205766432, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0005665231195962406, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0003845867190102581, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0002518770965616568, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.00017008517408612534, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.00012574455784488236, "train/grad_031_lr3.1e+00_wd1.0e+00": 9.899757185849011e-05, "train/grad_032_lr3.7e+00_wd1.0e+00": 7.320367972170061e-05, "train/grad_033_lr4.3e+00_wd1.0e+00": 5.363346282933889e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 3.7471096374588344e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 2.5501396189855363e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 1.0108445258419918e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 6.475449054536592e-06, "train/grad_038_lr9.8e+00_wd1.0e+00": 6.7742340747108555e-06, "train/grad_039_lr1.2e+01_wd1.0e+00": 6.7034643587388795e-06, "train/grad_040_lr1.4e+01_wd1.0e+00": 1.9567381085274517e-06, "train/grad_041_lr1.6e+01_wd1.0e+00": 5.387460965081457e-06, "train/grad_042_lr1.9e+01_wd1.0e+00": 6.993600268786583e-07, "train/grad_043_lr2.2e+01_wd1.0e+00": 3.301452797466358e-06, "train/grad_044_lr2.6e+01_wd1.0e+00": 2.033822739507485e-06, "train/grad_045_lr3.1e+01_wd1.0e+00": 3.939046706003513e-06, "train/grad_046_lr3.6e+01_wd1.0e+00": 7.670660459789391e-07, "train/grad_047_lr4.3e+01_wd1.0e+00": 1.3712908388472482e-05, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.8245756030082703, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.701411247253418, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.5247668027877808, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.38153478503227234, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.27795061469078064, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.18613214790821075, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.12359415739774704, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.08836715668439865, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.06971220672130585, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.06043442711234093, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.054914552718400955, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.04953848570585251, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.046063441783189774, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.042397044599056244, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.039798226207494736, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.03786034137010574, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.03592587634921074, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.03427939862012863, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.0329582579433918, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.03243584185838699, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.03224058821797371, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.032393909990787506, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.0332096628844738, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.034462910145521164, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.035868093371391296, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.037797711789608, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.0397263839840889, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.041112761944532394, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.042187485843896866, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.043320514261722565, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.04347444698214531, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.04363106191158295, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.04518522322177887, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.04552767053246498, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.047849882394075394, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.057285815477371216, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.08821681141853333, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.14586447179317474, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.11665745079517365, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.14667657017707825, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.24651150405406952, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.31246858835220337, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.30284616351127625, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.32188019156455994, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.6091193556785583, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.6733735203742981, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.8794916272163391, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.6735498905181885, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.0445220470428467, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.8844246031746031, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.8990575396825397, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.9159226190476191, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.9327876984126984, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9481646825396826, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.9697420634920635, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9776785714285714, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.9811507936507936, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9838789682539683, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9848710317460317, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9853670634920635, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9853670634920635, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9861111111111112, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9878472222222222, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9890873015873016, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9890873015873016, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9890873015873016, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9890873015873016, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9895833333333334, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9900793650793651, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9903273809523809, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9898313492063492, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9900793650793651, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9898313492063492, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9898313492063492, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9893353174603174, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9893353174603174, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9895833333333334, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9898313492063492, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9898313492063492, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9893353174603174, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9898313492063492, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9895833333333334, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9903273809523809, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9903273809523809, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9900793650793651, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9893353174603174, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9853670634920635, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9905753968253969, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9875992063492064, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.988343253968254, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.986359126984127, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9890873015873016, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9871031746031746, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9875992063492064, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9866071428571429, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9846230158730159, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.988343253968254, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.04365079365079365, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.8669490279117708, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.8868319847700195, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.9073724329285968, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.9269594641751817, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.9437535615656072, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.9662545291713475, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.9749644885724245, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9786598455021546, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9821903090992509, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9830637295647611, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9837077674304915, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9837109125880994, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9848127449444822, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9867711048774865, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9882322540426038, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9882889388712266, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9878359442771955, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9874712094853175, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9879211960941474, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9882817216496792, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9887749134595154, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.987910505605171, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.988313262869376, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9880541091627665, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9880513911493352, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9877064788337309, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9877064788337309, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9879787196301127, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9883389425521655, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9879795653440033, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9872572646802373, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9880684076670787, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9880587976723805, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9888352022495532, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9889982719579743, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9884220953500825, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9870116124510101, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9831546691861287, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9879011457287153, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9849503791078972, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9857290207584034, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9838809972679632, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9867689553937262, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9842515324919896, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9852538706226793, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9840726226735802, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9827659741766185, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9869586978501486, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.003983342386384211, "id_best": 38, "lr_best": 0.00294, "wd_best": 0.05, "train/loss_best": 4.903273656964302e-06, "validation/loss_best": 0.11665745079517365, "validation/acc_best": 0.9905753968253969, "validation/f1_best": 0.9879011457287153} +{"epoch": 17, "train/lr": 2.030750443206766e-05, "train/loss": 0.13881800133734942, "train/grad": 0.03919145077466965, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.8260653400421143, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.7025340461730957, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.5260266637802125, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.38394827842712403, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.2819353187084198, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.191648368537426, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.1300632679462433, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.09531591346487403, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.0770258742570877, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.0676452790107578, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.0617807646933943, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.05569488946348429, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.051289471620693805, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.04621317834593355, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.04210796779952943, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.0386336343549192, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.034649440301582214, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.030482786083593963, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.026293027186766266, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.02270834722556174, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.018684928016737105, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.01486572291702032, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.011004310362040996, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.007368571572005749, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.004463084433227777, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.0023664457630366087, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.0014132550545036793, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0009541699010878801, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0006182226352393627, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0004189690481871367, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0003104890510439873, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.00024595499038696287, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.00017821057699620723, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.00010754827409982681, "train/loss_034_lr5.1e+00_wd1.0e+00": 7.63075239956379e-05, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.470456227660179e-05, "train/loss_036_lr7.1e+00_wd1.0e+00": 9.990539401769638e-06, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.803027793765068e-06, "train/loss_038_lr9.8e+00_wd1.0e+00": 5.745477974414825e-06, "train/loss_039_lr1.2e+01_wd1.0e+00": 4.206197336316109e-06, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.6288459300994873e-06, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.1064112186431885e-06, "train/loss_042_lr1.9e+01_wd1.0e+00": 6.036367267370224e-07, "train/loss_043_lr2.2e+01_wd1.0e+00": 1.3357214629650116e-06, "train/loss_044_lr2.6e+01_wd1.0e+00": 6.12279400229454e-07, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.87655571103096e-06, "train/loss_046_lr3.6e+01_wd1.0e+00": 4.5218504965305326e-07, "train/loss_047_lr4.3e+01_wd1.0e+00": 1.0848790407180787e-06, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.046875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.015531772514805198, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.014672938897274435, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.013482340667396784, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.01223746087634936, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.010942265270277857, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.009395994448568671, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.007912573276553304, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.006805316361133009, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.0062852972687687724, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.00607193166622892, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.005939297212753445, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.005786531603662297, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.0056464900681748986, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.005433318163268268, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.005220304558170028, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.00502723413577769, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.004782899002893828, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.004518357800261583, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.004225451251259073, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.003940298874804285, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.0035638625426508952, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.0031453812592371834, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0026343282852030825, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0020354793861770302, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0014027675377656123, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0008245633483784331, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0005142743276883266, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0003536452062689932, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.00023343077124991397, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.00015978268827893772, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.00011914814767806092, "train/grad_031_lr3.1e+00_wd1.0e+00": 9.289942440773302e-05, "train/grad_032_lr3.7e+00_wd1.0e+00": 6.837572540689507e-05, "train/grad_033_lr4.3e+00_wd1.0e+00": 4.951719301288904e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 3.547746785670824e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 2.3350930255663372e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 1.0357829533987617e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 5.729163568757743e-06, "train/grad_038_lr9.8e+00_wd1.0e+00": 7.036724980242311e-06, "train/grad_039_lr1.2e+01_wd1.0e+00": 5.815006186370655e-06, "train/grad_040_lr1.4e+01_wd1.0e+00": 2.174170390346371e-06, "train/grad_041_lr1.6e+01_wd1.0e+00": 2.7358761704850196e-06, "train/grad_042_lr1.9e+01_wd1.0e+00": 1.0923573349085887e-06, "train/grad_043_lr2.2e+01_wd1.0e+00": 4.839527778903768e-06, "train/grad_044_lr2.6e+01_wd1.0e+00": 3.0898509071536774e-06, "train/grad_045_lr3.1e+01_wd1.0e+00": 9.963880537849482e-06, "train/grad_046_lr3.6e+01_wd1.0e+00": 1.133703687768153e-06, "train/grad_047_lr4.3e+01_wd1.0e+00": 4.773476238714093e-06, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.818392813205719, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.6952119469642639, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.5189675092697144, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.3762878477573395, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.27383410930633545, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.18316428363323212, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.12158672511577606, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.08728348463773727, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.06913570314645767, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.05998273566365242, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.05457618460059166, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.04918482527136803, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.04571546986699104, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.04212960600852966, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.039526138454675674, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.03756370395421982, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.03551018610596657, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.033796414732933044, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.03254519775509834, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.03186545893549919, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.03169284388422966, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.031874705106019974, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.032681290060281754, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.03387366980314255, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.03555537015199661, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.03765561059117317, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.03968888521194458, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.041042327880859375, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.04211917519569397, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.043013155460357666, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.04325032979249954, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.04341936111450195, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.0451047383248806, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.04542256146669388, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.04787465184926987, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.05695418640971184, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.08781874924898148, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.14480522274971008, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.11610874533653259, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.1452348530292511, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.24443237483501434, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.3085400462150574, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.29954543709754944, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.3174010217189789, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.6003872752189636, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.6620042324066162, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.8641855120658875, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.6562284827232361, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.0445220470428467, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.8836805555555556, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.8993055555555556, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.9161706349206349, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.9325396825396826, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9479166666666666, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.9702380952380952, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9781746031746031, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.9816468253968254, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9846230158730159, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9848710317460317, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9853670634920635, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9858630952380952, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9868551587301587, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9880952380952381, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9885912698412699, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9895833333333334, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9890873015873016, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9893353174603174, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9905753968253969, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9905753968253969, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9908234126984127, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9903273809523809, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9900793650793651, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9898313492063492, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9898313492063492, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9893353174603174, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9893353174603174, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9898313492063492, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9895833333333334, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9898313492063492, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9890873015873016, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9893353174603174, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9898313492063492, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9900793650793651, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9900793650793651, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9900793650793651, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9893353174603174, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9853670634920635, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9905753968253969, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9875992063492064, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.988343253968254, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9866071428571429, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9890873015873016, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9871031746031746, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9873511904761905, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9868551587301587, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9846230158730159, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.988343253968254, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.04365079365079365, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.8670010684146167, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.8872860020766418, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.9075837720157145, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.9268585122387969, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.9432057464040152, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.9667964781834276, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.9753148639456564, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9792120494240425, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9827300681364177, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9830637295647611, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.983706545046594, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9846085372289527, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9857658884605152, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9869508600265353, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9877053952701238, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9886451832129006, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9878354950807975, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9874789837478131, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9889947064857998, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9889945045660431, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9895320331172237, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9888014833217804, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9884150110286931, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9877363144730635, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9880481019988927, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9877064788337309, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9877064788337309, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9883389425521655, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9877978170110399, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9879795653440033, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9870770552396765, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9873471409386406, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9885997816138514, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9886549298861821, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9886407775424805, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9884220953500825, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9870116124510101, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9831546691861287, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9879011457287153, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9849503791078972, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9857290207584034, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9840603257919337, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9867689553937262, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9842515324919896, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9849063381196105, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9842384214574553, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9827659741766185, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9869586978501486, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.003983342386384211, "id_best": 20, "lr_best": 0.000156, "wd_best": 0.05, "train/loss_best": 0.018684928016737105, "validation/loss_best": 0.03169284388422966, "validation/acc_best": 0.9908234126984127, "validation/f1_best": 0.9895320331172237} +{"epoch": 18, "train/lr": 7.5829098008590064e-06, "train/loss": 0.13643380317837, "train/grad": 0.03937154030427337, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.8118170356750488, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.6897269487380981, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.5152370476722717, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.3749766004085541, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.27436011463403703, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.18508297741413116, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.12452156454324723, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.09096644714474678, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.0731403307057917, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.06397699524648487, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.05823209243826568, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.05224220398813486, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.047928283279761674, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.04293372679501772, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.03892803248949349, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.03560812411829829, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.031760054854676124, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.027807061532512306, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.023820591662079095, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.020454708207398652, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.016671466780826448, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.013108563432469965, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.009532361291348934, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.0062193214148283, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.003673753486946225, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.001945443907752633, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.001174670970067382, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0008005460817366839, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0005235634837299585, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0003565523400902748, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.00026821114122867586, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.0002101600170135498, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.0001521795429289341, "train/loss_033_lr4.3e+00_wd1.0e+00": 9.842622093856335e-05, "train/loss_034_lr5.1e+00_wd1.0e+00": 6.939325481653214e-05, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.990531735122204e-05, "train/loss_036_lr7.1e+00_wd1.0e+00": 7.74621032178402e-06, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.5827048122882844e-06, "train/loss_038_lr9.8e+00_wd1.0e+00": 4.930691793560982e-06, "train/loss_039_lr1.2e+01_wd1.0e+00": 4.240181297063827e-06, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.0066479444503785e-06, "train/loss_041_lr1.6e+01_wd1.0e+00": 6.785988807678223e-07, "train/loss_042_lr1.9e+01_wd1.0e+00": 8.484162390232086e-07, "train/loss_043_lr2.2e+01_wd1.0e+00": 1.3516191393136978e-06, "train/loss_044_lr2.6e+01_wd1.0e+00": 5.959346890449524e-07, "train/loss_045_lr3.1e+01_wd1.0e+00": 8.095987141132355e-08, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.0349398255348206e-07, "train/loss_047_lr4.3e+01_wd1.0e+00": 7.976498454809189e-07, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.046875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.01579345058184117, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.014930492020212113, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.013696045926772059, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.012410753294825555, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.011113828609231859, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.009590193103067577, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.008016147193266078, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.006795368925668299, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.00623564466368407, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.005999654242768884, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.005844236146076582, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.005664365914999508, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.00550051502767019, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.00527549912862014, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.005064985582139343, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.00487155035865726, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.004629397882381454, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.004352896947821137, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.004046999247511849, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.003755936784436926, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.0033739859824709127, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.002947765094722854, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0024359085391188274, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0018594093986030202, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0012790685797699553, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0007637912520021928, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0004804239358873019, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0003333080870925187, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0002214415236403511, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0001514655696087175, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.00011254589198983922, "train/grad_031_lr3.1e+00_wd1.0e+00": 8.879852300879065e-05, "train/grad_032_lr3.7e+00_wd1.0e+00": 6.617243607706769e-05, "train/grad_033_lr4.3e+00_wd1.0e+00": 4.704574377797144e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 3.5314119653833134e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 2.4626792565616284e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 9.986506150280184e-06, "train/grad_037_lr8.3e+00_wd1.0e+00": 5.8146612183624955e-06, "train/grad_038_lr9.8e+00_wd1.0e+00": 6.081338492628357e-06, "train/grad_039_lr1.2e+01_wd1.0e+00": 5.714414047629069e-06, "train/grad_040_lr1.4e+01_wd1.0e+00": 1.7735830453595374e-06, "train/grad_041_lr1.6e+01_wd1.0e+00": 3.365333986347569e-06, "train/grad_042_lr1.9e+01_wd1.0e+00": 1.525390912131088e-06, "train/grad_043_lr2.2e+01_wd1.0e+00": 3.812942452915063e-06, "train/grad_044_lr2.6e+01_wd1.0e+00": 1.7553079769605759e-06, "train/grad_045_lr3.1e+01_wd1.0e+00": 1.6060924027134568e-06, "train/grad_046_lr3.6e+01_wd1.0e+00": 1.1152549330516775e-06, "train/grad_047_lr4.3e+01_wd1.0e+00": 3.4042437507908082e-06, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.8161441683769226, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.692879319190979, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.5166908502578735, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.3743463158607483, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.2722146809101105, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.1819426715373993, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.12076642364263535, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.08674297481775284, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.06888735294342041, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.05983664095401764, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.05442681536078453, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.04909820482134819, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.045674409717321396, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.04207257926464081, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.03942708298563957, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.03744565322995186, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.0354405902326107, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.033719927072525024, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.03251228481531143, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.03192204236984253, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.031739138066768646, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.0320102833211422, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.03277543559670448, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.03402748331427574, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.035727307200431824, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.03776194900274277, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.03964965045452118, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.041086796671152115, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.04214337095618248, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.04315841570496559, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.0433226116001606, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.04342656210064888, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.045124590396881104, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.045442625880241394, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.04775797575712204, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.05686353147029877, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.08756787329912186, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.14467626810073853, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.11555607616901398, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.14463721215724945, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.2435319721698761, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.30834662914276123, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.29740387201309204, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.315717488527298, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.5977863073348999, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.6592859625816345, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.855941653251648, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.6507238745689392, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.0445220470428467, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.8859126984126984, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.9012896825396826, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.9176587301587301, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.9345238095238095, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9489087301587301, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.970734126984127, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9786706349206349, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.9813988095238095, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9846230158730159, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9851190476190477, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9851190476190477, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9853670634920635, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9866071428571429, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9880952380952381, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.988343253968254, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9895833333333334, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9893353174603174, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9893353174603174, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9903273809523809, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9908234126984127, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9908234126984127, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9903273809523809, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9898313492063492, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9895833333333334, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9898313492063492, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9893353174603174, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9893353174603174, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9898313492063492, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9895833333333334, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9898313492063492, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9890873015873016, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9895833333333334, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9898313492063492, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9900793650793651, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9903273809523809, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9900793650793651, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9895833333333334, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9856150793650794, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9905753968253969, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9873511904761905, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.988343253968254, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.986359126984127, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9890873015873016, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9871031746031746, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9873511904761905, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9871031746031746, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9846230158730159, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.988343253968254, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.04365079365079365, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.869525160235733, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.8896247444129677, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.9091756902922408, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.9291298467066712, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.9442846450212938, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.9672464548036454, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.9756859477516938, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9790322327175078, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9827300681364177, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9836048894565208, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9835268685409911, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9842490774286801, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9852184358365634, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9869508600265353, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9875256111117878, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9886451832129006, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9880128616250364, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9874789837478131, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9888142154679278, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9891747949468637, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9895320331172237, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9888014833217804, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9880503672698722, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.987509383328401, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9880481019988927, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9877064788337309, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9877064788337309, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9883389425521655, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9877978170110399, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9879795653440033, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9870770552396765, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9877043511648766, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9885990224675951, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9886549298861821, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9889982719579743, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9884220953500825, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9871918212999583, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.983256705034791, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9879011457287153, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9847701277697425, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9857290207584034, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9838809972679632, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9867689553937262, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9842515324919896, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9849063381196105, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9844180088435719, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9827659741766185, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9869586978501486, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.003983342386384211, "id_best": 19, "lr_best": 0.00013199999999999998, "wd_best": 0.05, "train/loss_best": 0.020454708207398652, "validation/loss_best": 0.03192204236984253, "validation/acc_best": 0.9908234126984127, "validation/f1_best": 0.9891747949468637} +{"epoch": 19, "train/lr": 1.0867618231465446e-06, "train/loss": 0.13704226952046156, "train/grad": 0.039035050896927714, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.8161475563049316, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.6933654260635376, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.5177689480781555, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.37652054071426394, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.2754572916030884, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.18617074504494668, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.12583250541239976, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.09249058794230222, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.07478422251529991, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.06561081278137863, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.05980007409118116, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.053636852577328684, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.04916464218869805, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.043942562323063615, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.03972651980817318, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.03617830189876258, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.03219530559144914, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.028060277542099357, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.02404365566559136, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.020707338452339172, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.017036052215844394, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.013542042532935738, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.009856425942853093, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.0063803080469369885, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.003767940457910299, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.0020318817626684906, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.0012416217662394047, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0008555574156343937, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0005664861481636763, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0003860569186508656, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.000288303904235363, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.00022718556225299837, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.00016615633852779866, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.00011280459351837635, "train/loss_034_lr5.1e+00_wd1.0e+00": 7.412920705974102e-05, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.393925726413727e-05, "train/loss_036_lr7.1e+00_wd1.0e+00": 7.857372984290124e-06, "train/loss_037_lr8.3e+00_wd1.0e+00": 4.199361428618431e-06, "train/loss_038_lr9.8e+00_wd1.0e+00": 4.032459110021591e-06, "train/loss_039_lr1.2e+01_wd1.0e+00": 4.7644227743148806e-06, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.0623782873153687e-06, "train/loss_041_lr1.6e+01_wd1.0e+00": 7.360987365245819e-07, "train/loss_042_lr1.9e+01_wd1.0e+00": 4.0670856833457946e-07, "train/loss_043_lr2.2e+01_wd1.0e+00": 1.069614663720131e-06, "train/loss_044_lr2.6e+01_wd1.0e+00": 7.488764822483062e-08, "train/loss_045_lr3.1e+01_wd1.0e+00": 5.247071385383606e-07, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.6351772248744964e-07, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.047659993171692e-07, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.046875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.01547966776881367, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.01460609064437449, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.01337768452707678, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.01210925588849932, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.010825557094067335, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.009330147872678935, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.007891527451574802, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.0068400114739779385, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.006384204907808453, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.00618959053652361, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.006061513988533988, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.005890953306225129, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.005732529514934867, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.0054901156370760875, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.005263356393261347, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.005050005767261609, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.004796947758586611, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.004511388846440241, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.0042029880799236705, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.0038962493068538605, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.0035051479570392986, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.0030744852597126737, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0025533756185905075, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0019446607682766625, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0013127978408738273, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.000771462352204253, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.00048571052528131983, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.00033633697386903805, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.00022196542013261933, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.00015047038398734004, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.00011161622564941354, "train/grad_031_lr3.1e+00_wd1.0e+00": 8.847624866575643e-05, "train/grad_032_lr3.7e+00_wd1.0e+00": 6.549796412400611e-05, "train/grad_033_lr4.3e+00_wd1.0e+00": 4.827367615007461e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 3.506761482185539e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 2.3249668355944665e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 9.735715988423571e-06, "train/grad_037_lr8.3e+00_wd1.0e+00": 5.545500204238247e-06, "train/grad_038_lr9.8e+00_wd1.0e+00": 6.056461465236062e-06, "train/grad_039_lr1.2e+01_wd1.0e+00": 6.057642411792563e-06, "train/grad_040_lr1.4e+01_wd1.0e+00": 2.8249176562073256e-06, "train/grad_041_lr1.6e+01_wd1.0e+00": 2.646840515937881e-06, "train/grad_042_lr1.9e+01_wd1.0e+00": 1.2526152165634148e-06, "train/grad_043_lr2.2e+01_wd1.0e+00": 5.103939065122518e-06, "train/grad_044_lr2.6e+01_wd1.0e+00": 1.7618042641679988e-06, "train/grad_045_lr3.1e+01_wd1.0e+00": 1.8282238831882696e-06, "train/grad_046_lr3.6e+01_wd1.0e+00": 7.011590007137991e-07, "train/grad_047_lr4.3e+01_wd1.0e+00": 5.289297392516703e-06, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.8157781362533569, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.6926337480545044, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.5164443850517273, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.37409815192222595, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.27198103070259094, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.18177011609077454, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.12065716832876205, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.08672191947698593, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.06885077804327011, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.05982006713747978, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.05447175353765488, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.049108851701021194, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.04566136375069618, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.04205689579248428, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.03938892111182213, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.037426017224788666, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.03540433198213577, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.03374115377664566, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.03252400457859039, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.03192928805947304, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.031747955828905106, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.03202712908387184, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.03280671313405037, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.03411461412906647, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.0357644222676754, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.03779700770974159, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.0397009439766407, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.04110733047127724, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.042187631130218506, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.04320456460118294, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.04334469139575958, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.04348684102296829, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.045109041035175323, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.04545500874519348, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.04782094061374664, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.0568796768784523, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.0875527486205101, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.14455212652683258, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.11554057896137238, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.14474926888942719, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.2435683310031891, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.30786317586898804, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.29705002903938293, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.31528380513191223, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.5985309481620789, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.6586556434631348, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.8575633764266968, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.6509127020835876, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.0445220470428467, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.8851686507936508, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.9017857142857143, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.9169146825396826, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.9342757936507936, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.949156746031746, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.9702380952380952, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9786706349206349, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.9813988095238095, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9846230158730159, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9851190476190477, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9851190476190477, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9853670634920635, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.986359126984127, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9878472222222222, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9885912698412699, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9895833333333334, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9890873015873016, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9893353174603174, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9903273809523809, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9905753968253969, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9908234126984127, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9903273809523809, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9900793650793651, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9895833333333334, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9895833333333334, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9893353174603174, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9893353174603174, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9898313492063492, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9895833333333334, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9898313492063492, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9890873015873016, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9895833333333334, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9898313492063492, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9900793650793651, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9903273809523809, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9900793650793651, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9895833333333334, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9853670634920635, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9905753968253969, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9873511904761905, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.988343253968254, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.986359126984127, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9890873015873016, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9871031746031746, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9873511904761905, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9868551587301587, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9846230158730159, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.988343253968254, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.04365079365079365, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.8687557389226668, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.8904110066825539, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.908446083826655, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.928867129107894, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.9445596303986235, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.9667964781834276, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.9756859477516938, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9790322327175078, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9827300681364177, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9836048894565208, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9835268685409911, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9842490774286801, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.985038691142765, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9867711048774865, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9876958574278278, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9886451832129006, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9878354950807975, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9878306580888637, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9888142154679278, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9889970563396265, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9895320331172237, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9888014833217804, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9882302881947671, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.987509383328401, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9878678721438383, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9877064788337309, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9877064788337309, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9883389425521655, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9877978170110399, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9879795653440033, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9870770552396765, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9877043511648766, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9885990224675951, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9886549298861821, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9889982719579743, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9884220953500825, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9871918212999583, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9831546691861287, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9879011457287153, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9847701277697425, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9857290207584034, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9838809972679632, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9867689553937262, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9842515324919896, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9849063381196105, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9842384214574553, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9827659741766185, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9869586978501486, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.003983342386384211, "id_best": 20, "lr_best": 0.000156, "wd_best": 0.05, "train/loss_best": 0.017036052215844394, "validation/loss_best": 0.031747955828905106, "validation/acc_best": 0.9908234126984127, "validation/f1_best": 0.9895320331172237} diff --git a/input_space_v3/flat_lr1e-3_4/eval_v2/nsd_cococlip__patch__attn/config.yaml b/input_space_v3/flat_lr1e-3_4/eval_v2/nsd_cococlip__patch__attn/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..0d3750af8b7673b0a52aeea25381234660dd2483 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_4/eval_v2/nsd_cococlip__patch__attn/config.yaml @@ -0,0 +1,96 @@ +output_root: experiments/input_space_v3/output +name_prefix: eval_probe +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_4; eval v2 (nsd_cococlip patch attn) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +dataset_kwargs: {} +classifier_kwargs: + embed_dim: null + dropout: 0.0 + xavier_init: true + norm: true +lr_scale_grid: +- 0.02 +- 0.023 +- 0.028 +- 0.033 +- 0.038 +- 0.045 +- 0.053 +- 0.062 +- 0.074 +- 0.087 +- 0.1 +- 0.12 +- 0.14 +- 0.17 +- 0.2 +- 0.23 +- 0.27 +- 0.32 +- 0.38 +- 0.44 +- 0.52 +- 0.61 +- 0.72 +- 0.85 +- 1 +- 1.2 +- 1.4 +- 1.6 +- 1.9 +- 2.3 +- 2.7 +- 3.1 +- 3.7 +- 4.3 +- 5.1 +- 6 +- 7.1 +- 8.3 +- 9.8 +- 12 +- 14 +- 16 +- 19 +- 22 +- 26 +- 31 +- 36 +- 43 +- 50 +wd_scale_grid: +- 1.0 +num_workers: 8 +prefetch_factor: null +balanced_sampling: false +epochs: 20 +steps_per_epoch: 200 +batch_size: 64 +accum_iter: 2 +lr: 0.0003 +warmup_epochs: 5 +no_decay: false +weight_decay: 0.05 +clip_grad: 1.0 +metrics: +- acc +- f1 +cv_metric: acc +early_stopping: true +amp: true +device: cuda +seed: 4466 +debug: false +wandb: false +wandb_entity: null +wandb_project: fMRI-fm-eval +name: input_space_v3/flat_lr1e-3_4/eval_v2/nsd_cococlip__patch__attn +model: flat_mae +representation: patch +classifier: attn +dataset: nsd_cococlip +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/eval_v2/nsd_cococlip__patch__attn +remote_dir: null diff --git a/input_space_v3/flat_lr1e-3_4/eval_v2/nsd_cococlip__patch__attn/eval_log.json b/input_space_v3/flat_lr1e-3_4/eval_v2/nsd_cococlip__patch__attn/eval_log.json new file mode 100644 index 0000000000000000000000000000000000000000..77c7d9665bf381032946d9e3845e69d38e2c4341 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_4/eval_v2/nsd_cococlip__patch__attn/eval_log.json @@ -0,0 +1 @@ +{"eval/epoch": 5, "eval/id_best": 25, "eval/lr_best": 0.00035999999999999997, "eval/wd_best": 0.05, "eval/train/loss": 2.083367109298706, "eval/train/acc": 0.3687882233627339, "eval/train/acc_std": 0.00239416401518703, "eval/train/f1": 0.3057046529680396, "eval/train/f1_std": 0.0025342350004406437, "eval/validation/loss": 2.3359625339508057, "eval/validation/acc": 0.29494278331487633, "eval/validation/acc_std": 0.005419045456037518, "eval/validation/f1": 0.2233933979537852, "eval/validation/f1_std": 0.005170180524790467, "eval/test/loss": 2.2779901027679443, "eval/test/acc": 0.2987012987012987, "eval/test/acc_std": 0.005307889945249517, "eval/test/f1": 0.23023843126408305, "eval/test/f1_std": 0.005287250650942963, "eval/testid/loss": 2.284707546234131, "eval/testid/acc": 0.30460767302872566, "eval/testid/acc_std": 0.005512740817533758, "eval/testid/f1": 0.24010281874325012, "eval/testid/f1_std": 0.00552167205119188} diff --git a/input_space_v3/flat_lr1e-3_4/eval_v2/nsd_cococlip__patch__attn/eval_log_best.json b/input_space_v3/flat_lr1e-3_4/eval_v2/nsd_cococlip__patch__attn/eval_log_best.json new file mode 100644 index 0000000000000000000000000000000000000000..3fdaa84930bd60e7253e657d83fd74f19472f3ea --- /dev/null +++ b/input_space_v3/flat_lr1e-3_4/eval_v2/nsd_cococlip__patch__attn/eval_log_best.json @@ -0,0 +1 @@ +{"eval/best/epoch": 5, "eval/best/id_best": 25, "eval/best/lr_best": 0.00035999999999999997, "eval/best/wd_best": 0.05, "eval/best/train/loss": 2.083367109298706, "eval/best/train/acc": 0.3687882233627339, "eval/best/train/acc_std": 0.00239416401518703, "eval/best/train/f1": 0.3057046529680396, "eval/best/train/f1_std": 0.0025342350004406437, "eval/best/validation/loss": 2.3359625339508057, "eval/best/validation/acc": 0.29494278331487633, "eval/best/validation/acc_std": 0.005419045456037518, "eval/best/validation/f1": 0.2233933979537852, "eval/best/validation/f1_std": 0.005170180524790467, "eval/best/test/loss": 2.2779901027679443, "eval/best/test/acc": 0.2987012987012987, "eval/best/test/acc_std": 0.005307889945249517, "eval/best/test/f1": 0.23023843126408305, "eval/best/test/f1_std": 0.005287250650942963, "eval/best/testid/loss": 2.284707546234131, "eval/best/testid/acc": 0.30460767302872566, "eval/best/testid/acc_std": 0.005512740817533758, "eval/best/testid/f1": 0.24010281874325012, "eval/best/testid/f1_std": 0.00552167205119188} diff --git a/input_space_v3/flat_lr1e-3_4/eval_v2/nsd_cococlip__patch__attn/eval_log_last.json b/input_space_v3/flat_lr1e-3_4/eval_v2/nsd_cococlip__patch__attn/eval_log_last.json new file mode 100644 index 0000000000000000000000000000000000000000..12495f4d85f30111a53790268c0436638a1d5f47 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_4/eval_v2/nsd_cococlip__patch__attn/eval_log_last.json @@ -0,0 +1 @@ +{"eval/last/epoch": 19, "eval/last/id_best": 17, "eval/last/lr_best": 9.599999999999999e-05, "eval/last/wd_best": 0.05, "eval/last/train/loss": 2.116112232208252, "eval/last/train/acc": 0.3662681705030886, "eval/last/train/acc_std": 0.002520620144245288, "eval/last/train/f1": 0.3050600427874218, "eval/last/train/f1_std": 0.002590899011999935, "eval/last/validation/loss": 2.350001811981201, "eval/last/validation/acc": 0.2929125138427464, "eval/last/validation/acc_std": 0.005518170971958832, "eval/last/validation/f1": 0.23290211406267125, "eval/last/validation/f1_std": 0.005434079958469674, "eval/last/test/loss": 2.2581374645233154, "eval/last/test/acc": 0.3122448979591837, "eval/last/test/acc_std": 0.005397253111142254, "eval/last/test/f1": 0.23987499135870238, "eval/last/test/f1_std": 0.00538180411619799, "eval/last/testid/loss": 2.282243251800537, "eval/last/testid/acc": 0.3100057836899942, "eval/last/testid/acc_std": 0.005648926145238937, "eval/last/testid/f1": 0.24665934136131096, "eval/last/testid/f1_std": 0.005512548278612956} diff --git a/input_space_v3/flat_lr1e-3_4/eval_v2/nsd_cococlip__patch__attn/eval_table.csv b/input_space_v3/flat_lr1e-3_4/eval_v2/nsd_cococlip__patch__attn/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..c3f6b09be5af159f5d61d6a7aadc9c2c29caa6b6 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_4/eval_v2/nsd_cococlip__patch__attn/eval_table.csv @@ -0,0 +1,5 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,patch,attn,nsd_cococlip,best,5,0.00035999999999999997,0.05,25,"[1.2, 1.0]",train,2.083367109298706,0.3687882233627339,0.00239416401518703,0.3057046529680396,0.0025342350004406437 +flat_mae,patch,attn,nsd_cococlip,best,5,0.00035999999999999997,0.05,25,"[1.2, 1.0]",validation,2.3359625339508057,0.29494278331487633,0.005419045456037518,0.2233933979537852,0.005170180524790467 +flat_mae,patch,attn,nsd_cococlip,best,5,0.00035999999999999997,0.05,25,"[1.2, 1.0]",test,2.2779901027679443,0.2987012987012987,0.005307889945249517,0.23023843126408305,0.005287250650942963 +flat_mae,patch,attn,nsd_cococlip,best,5,0.00035999999999999997,0.05,25,"[1.2, 1.0]",testid,2.284707546234131,0.30460767302872566,0.005512740817533758,0.24010281874325012,0.00552167205119188 diff --git a/input_space_v3/flat_lr1e-3_4/eval_v2/nsd_cococlip__patch__attn/eval_table_best.csv b/input_space_v3/flat_lr1e-3_4/eval_v2/nsd_cococlip__patch__attn/eval_table_best.csv new file mode 100644 index 0000000000000000000000000000000000000000..c3f6b09be5af159f5d61d6a7aadc9c2c29caa6b6 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_4/eval_v2/nsd_cococlip__patch__attn/eval_table_best.csv @@ -0,0 +1,5 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,patch,attn,nsd_cococlip,best,5,0.00035999999999999997,0.05,25,"[1.2, 1.0]",train,2.083367109298706,0.3687882233627339,0.00239416401518703,0.3057046529680396,0.0025342350004406437 +flat_mae,patch,attn,nsd_cococlip,best,5,0.00035999999999999997,0.05,25,"[1.2, 1.0]",validation,2.3359625339508057,0.29494278331487633,0.005419045456037518,0.2233933979537852,0.005170180524790467 +flat_mae,patch,attn,nsd_cococlip,best,5,0.00035999999999999997,0.05,25,"[1.2, 1.0]",test,2.2779901027679443,0.2987012987012987,0.005307889945249517,0.23023843126408305,0.005287250650942963 +flat_mae,patch,attn,nsd_cococlip,best,5,0.00035999999999999997,0.05,25,"[1.2, 1.0]",testid,2.284707546234131,0.30460767302872566,0.005512740817533758,0.24010281874325012,0.00552167205119188 diff --git a/input_space_v3/flat_lr1e-3_4/eval_v2/nsd_cococlip__patch__attn/eval_table_last.csv b/input_space_v3/flat_lr1e-3_4/eval_v2/nsd_cococlip__patch__attn/eval_table_last.csv new file mode 100644 index 0000000000000000000000000000000000000000..4d9d749080c6d77f9b477d32b2296cdaa0901dae --- /dev/null +++ b/input_space_v3/flat_lr1e-3_4/eval_v2/nsd_cococlip__patch__attn/eval_table_last.csv @@ -0,0 +1,5 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,patch,attn,nsd_cococlip,last,19,9.599999999999999e-05,0.05,17,"[0.32, 1.0]",train,2.116112232208252,0.3662681705030886,0.002520620144245288,0.3050600427874218,0.002590899011999935 +flat_mae,patch,attn,nsd_cococlip,last,19,9.599999999999999e-05,0.05,17,"[0.32, 1.0]",validation,2.350001811981201,0.2929125138427464,0.005518170971958832,0.23290211406267125,0.005434079958469674 +flat_mae,patch,attn,nsd_cococlip,last,19,9.599999999999999e-05,0.05,17,"[0.32, 1.0]",test,2.2581374645233154,0.3122448979591837,0.005397253111142254,0.23987499135870238,0.00538180411619799 +flat_mae,patch,attn,nsd_cococlip,last,19,9.599999999999999e-05,0.05,17,"[0.32, 1.0]",testid,2.282243251800537,0.3100057836899942,0.005648926145238937,0.24665934136131096,0.005512548278612956 diff --git a/input_space_v3/flat_lr1e-3_4/eval_v2/nsd_cococlip__patch__attn/log.txt b/input_space_v3/flat_lr1e-3_4/eval_v2/nsd_cococlip__patch__attn/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..b3673e778893f740f49a548f79dcd05bf5a6122e --- /dev/null +++ b/input_space_v3/flat_lr1e-3_4/eval_v2/nsd_cococlip__patch__attn/log.txt @@ -0,0 +1,962 @@ +fMRI foundation model probe eval +version: 0.1.dev86+gf97f52698 +sha: bcce2b486277d3a5b520775efd9cdf1a2affce36, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-04-08 20:31:09 +config: +output_root: experiments/input_space_v3/output +name_prefix: eval_probe +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_4; eval v2 (nsd_cococlip patch attn) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +dataset_kwargs: {} +classifier_kwargs: + embed_dim: null + dropout: 0.0 + xavier_init: true + norm: true +lr_scale_grid: +- 0.02 +- 0.023 +- 0.028 +- 0.033 +- 0.038 +- 0.045 +- 0.053 +- 0.062 +- 0.074 +- 0.087 +- 0.1 +- 0.12 +- 0.14 +- 0.17 +- 0.2 +- 0.23 +- 0.27 +- 0.32 +- 0.38 +- 0.44 +- 0.52 +- 0.61 +- 0.72 +- 0.85 +- 1 +- 1.2 +- 1.4 +- 1.6 +- 1.9 +- 2.3 +- 2.7 +- 3.1 +- 3.7 +- 4.3 +- 5.1 +- 6 +- 7.1 +- 8.3 +- 9.8 +- 12 +- 14 +- 16 +- 19 +- 22 +- 26 +- 31 +- 36 +- 43 +- 50 +wd_scale_grid: +- 1.0 +num_workers: 8 +prefetch_factor: null +balanced_sampling: false +epochs: 20 +steps_per_epoch: 200 +batch_size: 64 +accum_iter: 2 +lr: 0.0003 +warmup_epochs: 5 +no_decay: false +weight_decay: 0.05 +clip_grad: 1.0 +metrics: +- acc +- f1 +cv_metric: acc +early_stopping: true +amp: true +device: cuda +seed: 4466 +debug: false +wandb: false +wandb_entity: null +wandb_project: fMRI-fm-eval +name: input_space_v3/flat_lr1e-3_4/eval_v2/nsd_cococlip__patch__attn +model: flat_mae +representation: patch +classifier: attn +dataset: nsd_cococlip +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/eval_v2/nsd_cococlip__patch__attn +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=True, reg_tokens=0, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: nsd_cococlip (flat) +train (n=32539): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'run', 'trial_id', 'nsd_id', 'category_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 32539 +}), + labels=[ 3 4 5 6 10 11 17 18 19 20 22 23 25 30 31 33 36 37 38 53 55 59 61 74], + counts=[1286 1180 1639 1868 834 824 1026 1042 913 1853 1503 2092 1001 1410 + 794 1241 1904 1872 2267 1428 889 904 1447 1322] +) + +validation (n=5418): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'run', 'trial_id', 'nsd_id', 'category_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 5418 +}), + labels=[ 3 4 5 6 10 11 17 18 19 20 22 23 25 30 31 33 36 37 38 53 55 59 61 74], + counts=[197 161 276 345 126 142 143 185 112 295 285 387 169 250 159 193 316 334 + 343 215 172 141 226 246] +) + +test (n=5390): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'run', 'trial_id', 'nsd_id', 'category_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 5390 +}), + labels=[ 3 4 5 6 10 11 17 18 19 20 22 23 25 30 31 33 36 37 38 53 55 59 61 74], + counts=[202 172 274 298 144 180 134 182 186 293 218 343 165 185 140 177 346 333 + 345 271 165 140 251 246] +) + +testid (n=5187): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'run', 'trial_id', 'nsd_id', 'category_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 5187 +}), + labels=[ 3 4 5 6 10 11 17 18 19 20 22 23 25 30 31 33 36 37 38 53 55 59 61 74], + counts=[197 159 267 273 123 153 175 184 139 310 215 386 153 230 118 192 330 306 + 349 223 143 127 249 186] +) + +running backbone on example batch to get embedding dim +embedding feature dim (patch): 768 +initializing sweep of classifier heads +classifiers: +ModuleList( + (0-48): 49 x AttnPoolClassifier( + (kv): Linear(in_features=768, out_features=1536, bias=True) + (linear): Linear(in_features=768, out_features=24, bias=True) + ) +) +classifier params (train): 58.8M (58.8M) +setting up optimizer +total batch size: 128 = 64 bs per gpu x 2 accum +lr: 3.00e-04 +full schedule: epochs = 20 (steps = 4000) (decay = True) +warmup: epochs = 5 (steps = 1000) +start training for 20 epochs +train: [0] [ 0/400] eta: 0:23:15 lr: nan time: 3.4884 data: 2.9949 max mem: 21740 +train: [0] [ 20/400] eta: 0:03:47 lr: 0.000003 loss: 3.1773 (3.1762) grad: 0.1657 (0.1662) time: 0.4537 data: 0.0034 max mem: 22448 +train: [0] [ 40/400] eta: 0:03:09 lr: 0.000006 loss: 3.1735 (3.1702) grad: 0.1646 (0.1660) time: 0.4514 data: 0.0042 max mem: 22448 +train: [0] [ 60/400] eta: 0:02:49 lr: 0.000009 loss: 3.1656 (3.1695) grad: 0.1600 (0.1653) time: 0.4454 data: 0.0041 max mem: 22448 +train: [0] [ 80/400] eta: 0:02:35 lr: 0.000012 loss: 3.1629 (3.1679) grad: 0.1595 (0.1643) time: 0.4467 data: 0.0042 max mem: 22448 +train: [0] [100/400] eta: 0:02:24 lr: 0.000015 loss: 3.1563 (3.1675) grad: 0.1560 (0.1630) time: 0.4554 data: 0.0044 max mem: 22448 +train: [0] [120/400] eta: 0:02:14 lr: 0.000018 loss: 3.1563 (3.1656) grad: 0.1467 (0.1608) time: 0.4698 data: 0.0040 max mem: 22448 +train: [0] [140/400] eta: 0:02:03 lr: 0.000021 loss: 3.1517 (3.1641) grad: 0.1474 (0.1605) time: 0.4500 data: 0.0041 max mem: 22448 +train: [0] [160/400] eta: 0:01:52 lr: 0.000024 loss: 3.1517 (3.1616) grad: 0.1652 (0.1618) time: 0.4427 data: 0.0040 max mem: 22448 +train: [0] [180/400] eta: 0:01:42 lr: 0.000027 loss: 3.1343 (3.1600) grad: 0.1608 (0.1616) time: 0.4456 data: 0.0041 max mem: 22448 +train: [0] [200/400] eta: 0:01:33 lr: 0.000030 loss: 3.1508 (3.1599) grad: 0.1525 (0.1602) time: 0.4500 data: 0.0042 max mem: 22448 +train: [0] [220/400] eta: 0:01:23 lr: 0.000033 loss: 3.1573 (3.1593) grad: 0.1508 (0.1595) time: 0.4506 data: 0.0041 max mem: 22448 +train: [0] [240/400] eta: 0:01:14 lr: 0.000036 loss: 3.1526 (3.1578) grad: 0.1523 (0.1589) time: 0.4532 data: 0.0041 max mem: 22448 +train: [0] [260/400] eta: 0:01:04 lr: 0.000039 loss: 3.1295 (3.1560) grad: 0.1499 (0.1582) time: 0.4549 data: 0.0040 max mem: 22448 +train: [0] [280/400] eta: 0:00:55 lr: 0.000042 loss: 3.1218 (3.1531) grad: 0.1505 (0.1578) time: 0.4518 data: 0.0040 max mem: 22448 +train: [0] [300/400] eta: 0:00:46 lr: 0.000045 loss: 3.1057 (3.1488) grad: 0.1520 (0.1577) time: 0.4569 data: 0.0040 max mem: 22448 +train: [0] [320/400] eta: 0:00:36 lr: 0.000048 loss: 3.0960 (3.1458) grad: 0.1595 (0.1584) time: 0.4563 data: 0.0041 max mem: 22448 +train: [0] [340/400] eta: 0:00:27 lr: 0.000051 loss: 3.0979 (3.1427) grad: 0.1641 (0.1584) time: 0.4625 data: 0.0044 max mem: 22448 +train: [0] [360/400] eta: 0:00:18 lr: 0.000054 loss: 3.0801 (3.1387) grad: 0.1654 (0.1591) time: 0.4670 data: 0.0043 max mem: 22448 +train: [0] [380/400] eta: 0:00:09 lr: 0.000057 loss: 3.0766 (3.1356) grad: 0.1720 (0.1600) time: 0.4619 data: 0.0043 max mem: 22448 +train: [0] [399/400] eta: 0:00:00 lr: 0.000060 loss: 3.0847 (3.1332) grad: 0.1784 (0.1607) time: 0.4521 data: 0.0042 max mem: 22448 +train: [0] Total time: 0:03:04 (0.4618 s / it) +train: [0] Summary: lr: 0.000060 loss: 3.0847 (3.1332) grad: 0.1784 (0.1607) +eval (validation): [0] [ 0/85] eta: 0:04:46 time: 3.3667 data: 3.1137 max mem: 22448 +eval (validation): [0] [20/85] eta: 0:00:32 time: 0.3597 data: 0.0041 max mem: 22448 +eval (validation): [0] [40/85] eta: 0:00:18 time: 0.3269 data: 0.0036 max mem: 22448 +eval (validation): [0] [60/85] eta: 0:00:09 time: 0.3365 data: 0.0042 max mem: 22448 +eval (validation): [0] [80/85] eta: 0:00:01 time: 0.3279 data: 0.0039 max mem: 22448 +eval (validation): [0] [84/85] eta: 0:00:00 time: 0.3209 data: 0.0038 max mem: 22448 +eval (validation): [0] Total time: 0:00:31 (0.3749 s / it) +cv: [0] best hparam: (31, 1.0) (045) ('045_lr3.1e+01_wd1.0e+00') loss: 2.601 acc: 0.238 f1: 0.167 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/eval_v2/nsd_cococlip__patch__attn/checkpoint-best.pth +train: [1] [ 0/400] eta: 0:21:38 lr: nan time: 3.2472 data: 2.8988 max mem: 22448 +train: [1] [ 20/400] eta: 0:03:49 lr: 0.000063 loss: 3.0164 (3.0278) grad: 0.1737 (0.1698) time: 0.4705 data: 0.0039 max mem: 22448 +train: [1] [ 40/400] eta: 0:03:11 lr: 0.000066 loss: 3.0296 (3.0263) grad: 0.1640 (0.1663) time: 0.4561 data: 0.0038 max mem: 22448 +train: [1] [ 60/400] eta: 0:02:50 lr: 0.000069 loss: 3.0126 (3.0162) grad: 0.1640 (0.1681) time: 0.4409 data: 0.0039 max mem: 22448 +train: [1] [ 80/400] eta: 0:02:36 lr: 0.000072 loss: 3.0041 (3.0171) grad: 0.1721 (0.1715) time: 0.4460 data: 0.0039 max mem: 22448 +train: [1] [100/400] eta: 0:02:24 lr: 0.000075 loss: 3.0056 (3.0110) grad: 0.1768 (0.1731) time: 0.4525 data: 0.0043 max mem: 22448 +train: [1] [120/400] eta: 0:02:12 lr: 0.000078 loss: 3.0003 (3.0080) grad: 0.1785 (0.1742) time: 0.4393 data: 0.0041 max mem: 22448 +train: [1] [140/400] eta: 0:02:02 lr: 0.000081 loss: 2.9953 (3.0066) grad: 0.1785 (0.1754) time: 0.4438 data: 0.0040 max mem: 22448 +train: [1] [160/400] eta: 0:01:51 lr: 0.000084 loss: 2.9830 (3.0059) grad: 0.1772 (0.1757) time: 0.4386 data: 0.0041 max mem: 22448 +train: [1] [180/400] eta: 0:01:41 lr: 0.000087 loss: 2.9976 (3.0071) grad: 0.1802 (0.1771) time: 0.4443 data: 0.0041 max mem: 22448 +train: [1] [200/400] eta: 0:01:32 lr: 0.000090 loss: 2.9880 (3.0044) grad: 0.1822 (0.1780) time: 0.4463 data: 0.0039 max mem: 22448 +train: [1] [220/400] eta: 0:01:22 lr: 0.000093 loss: 2.9456 (2.9971) grad: 0.2004 (0.1803) time: 0.4448 data: 0.0039 max mem: 22448 +train: [1] [240/400] eta: 0:01:13 lr: 0.000096 loss: 2.9345 (2.9941) grad: 0.1988 (0.1812) time: 0.4395 data: 0.0040 max mem: 22448 +train: [1] [260/400] eta: 0:01:03 lr: 0.000099 loss: 2.9633 (2.9929) grad: 0.1891 (0.1823) time: 0.4364 data: 0.0038 max mem: 22448 +train: [1] [280/400] eta: 0:00:54 lr: 0.000102 loss: 2.9645 (2.9896) grad: 0.1888 (0.1828) time: 0.4425 data: 0.0039 max mem: 22448 +train: [1] [300/400] eta: 0:00:45 lr: 0.000105 loss: 2.9336 (2.9881) grad: 0.1895 (0.1836) time: 0.4493 data: 0.0039 max mem: 22448 +train: [1] [320/400] eta: 0:00:36 lr: 0.000108 loss: 2.9180 (2.9835) grad: 0.1917 (0.1841) time: 0.4407 data: 0.0038 max mem: 22448 +train: [1] [340/400] eta: 0:00:27 lr: 0.000111 loss: 2.9054 (2.9792) grad: 0.1918 (0.1845) time: 0.4543 data: 0.0038 max mem: 22448 +train: [1] [360/400] eta: 0:00:18 lr: 0.000114 loss: 2.9209 (2.9768) grad: 0.1873 (0.1849) time: 0.4529 data: 0.0039 max mem: 22448 +train: [1] [380/400] eta: 0:00:09 lr: 0.000117 loss: 2.9098 (2.9730) grad: 0.1894 (0.1859) time: 0.4525 data: 0.0039 max mem: 22448 +train: [1] [399/400] eta: 0:00:00 lr: 0.000120 loss: 2.9098 (2.9715) grad: 0.2052 (0.1873) time: 0.4462 data: 0.0039 max mem: 22448 +train: [1] Total time: 0:03:01 (0.4542 s / it) +train: [1] Summary: lr: 0.000120 loss: 2.9098 (2.9715) grad: 0.2052 (0.1873) +eval (validation): [1] [ 0/85] eta: 0:04:44 time: 3.3522 data: 3.0585 max mem: 22448 +eval (validation): [1] [20/85] eta: 0:00:34 time: 0.3859 data: 0.0227 max mem: 22448 +eval (validation): [1] [40/85] eta: 0:00:19 time: 0.3347 data: 0.0037 max mem: 22448 +eval (validation): [1] [60/85] eta: 0:00:10 time: 0.3384 data: 0.0044 max mem: 22448 +eval (validation): [1] [80/85] eta: 0:00:01 time: 0.3215 data: 0.0043 max mem: 22448 +eval (validation): [1] [84/85] eta: 0:00:00 time: 0.3152 data: 0.0042 max mem: 22448 +eval (validation): [1] Total time: 0:00:32 (0.3816 s / it) +cv: [1] best hparam: (12, 1.0) (039) ('039_lr1.2e+01_wd1.0e+00') loss: 2.444 acc: 0.262 f1: 0.197 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/eval_v2/nsd_cococlip__patch__attn/checkpoint-best.pth +train: [2] [ 0/400] eta: 0:23:06 lr: nan time: 3.4667 data: 3.0685 max mem: 22448 +train: [2] [ 20/400] eta: 0:03:44 lr: 0.000123 loss: 2.9375 (2.9209) grad: 0.2375 (0.2320) time: 0.4458 data: 0.0036 max mem: 22448 +train: [2] [ 40/400] eta: 0:03:08 lr: 0.000126 loss: 2.9375 (2.9241) grad: 0.2379 (0.2361) time: 0.4518 data: 0.0039 max mem: 22448 +train: [2] [ 60/400] eta: 0:02:48 lr: 0.000129 loss: 2.9514 (2.9422) grad: 0.2535 (0.2801) time: 0.4433 data: 0.0040 max mem: 22448 +train: [2] [ 80/400] eta: 0:02:34 lr: 0.000132 loss: 3.0438 (3.0485) grad: 0.5383 (0.4694) time: 0.4446 data: 0.0040 max mem: 22448 +WARNING: classifier 48 (50, 1.0) diverged (loss=68.56 > 63.56) at step 445. Freezing. +train: [2] [100/400] eta: 0:02:23 lr: 0.000135 loss: 3.3392 (3.0989) grad: 0.9549 (0.5482) time: 0.4522 data: 0.0040 max mem: 22448 +train: [2] [120/400] eta: 0:02:12 lr: 0.000138 loss: 2.8901 (3.0597) grad: 0.2098 (0.4914) time: 0.4434 data: 0.0039 max mem: 22448 +train: [2] [140/400] eta: 0:02:01 lr: 0.000141 loss: 2.8901 (3.0384) grad: 0.2061 (0.4518) time: 0.4402 data: 0.0040 max mem: 22448 +train: [2] [160/400] eta: 0:01:51 lr: 0.000144 loss: 2.8650 (3.0140) grad: 0.2117 (0.4221) time: 0.4383 data: 0.0040 max mem: 22448 +train: [2] [180/400] eta: 0:01:41 lr: 0.000147 loss: 2.8249 (2.9934) grad: 0.2117 (0.3991) time: 0.4351 data: 0.0039 max mem: 22448 +train: [2] [200/400] eta: 0:01:31 lr: 0.000150 loss: 2.8390 (2.9790) grad: 0.2179 (0.3814) time: 0.4422 data: 0.0040 max mem: 22448 +train: [2] [220/400] eta: 0:01:22 lr: 0.000153 loss: 2.8837 (2.9717) grad: 0.2308 (0.3718) time: 0.4406 data: 0.0040 max mem: 22448 +train: [2] [240/400] eta: 0:01:12 lr: 0.000156 loss: 2.9389 (2.9878) grad: 0.3414 (0.4086) time: 0.4342 data: 0.0038 max mem: 22448 +WARNING: classifier 47 (43, 1.0) diverged (loss=67.27 > 63.56) at step 526. Freezing. +train: [2] [260/400] eta: 0:01:03 lr: 0.000159 loss: 3.0012 (3.0208) grad: 0.8012 (0.4536) time: 0.4416 data: 0.0039 max mem: 22448 +train: [2] [280/400] eta: 0:00:54 lr: 0.000162 loss: 2.8741 (3.0081) grad: 0.2310 (0.4375) time: 0.4433 data: 0.0041 max mem: 22448 +train: [2] [300/400] eta: 0:00:45 lr: 0.000165 loss: 2.8208 (2.9958) grad: 0.2176 (0.4226) time: 0.4436 data: 0.0039 max mem: 22448 +train: [2] [320/400] eta: 0:00:36 lr: 0.000168 loss: 2.8030 (2.9847) grad: 0.2082 (0.4093) time: 0.4456 data: 0.0038 max mem: 22448 +train: [2] [340/400] eta: 0:00:27 lr: 0.000171 loss: 2.8254 (2.9776) grad: 0.2089 (0.3981) time: 0.4479 data: 0.0040 max mem: 22448 +train: [2] [360/400] eta: 0:00:18 lr: 0.000174 loss: 2.8460 (2.9707) grad: 0.2218 (0.3883) time: 0.4468 data: 0.0040 max mem: 22448 +train: [2] [380/400] eta: 0:00:09 lr: 0.000177 loss: 2.8540 (2.9645) grad: 0.2300 (0.3802) time: 0.4543 data: 0.0042 max mem: 22448 +train: [2] [399/400] eta: 0:00:00 lr: 0.000180 loss: 2.8540 (2.9576) grad: 0.2328 (0.3726) time: 0.4538 data: 0.0041 max mem: 22448 +train: [2] Total time: 0:03:00 (0.4523 s / it) +train: [2] Summary: lr: 0.000180 loss: 2.8540 (2.9576) grad: 0.2328 (0.3726) +eval (validation): [2] [ 0/85] eta: 0:04:54 time: 3.4653 data: 3.1671 max mem: 22448 +eval (validation): [2] [20/85] eta: 0:00:31 time: 0.3287 data: 0.0107 max mem: 22448 +eval (validation): [2] [40/85] eta: 0:00:18 time: 0.3191 data: 0.0035 max mem: 22448 +eval (validation): [2] [60/85] eta: 0:00:09 time: 0.3431 data: 0.0041 max mem: 22448 +eval (validation): [2] [80/85] eta: 0:00:01 time: 0.3300 data: 0.0040 max mem: 22448 +eval (validation): [2] [84/85] eta: 0:00:00 time: 0.3197 data: 0.0039 max mem: 22448 +eval (validation): [2] Total time: 0:00:31 (0.3687 s / it) +cv: [2] best hparam: (3.7, 1.0) (032) ('032_lr3.7e+00_wd1.0e+00') loss: 2.405 acc: 0.277 f1: 0.208 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/eval_v2/nsd_cococlip__patch__attn/checkpoint-best.pth +train: [3] [ 0/400] eta: 0:22:09 lr: nan time: 3.3231 data: 2.9833 max mem: 22448 +train: [3] [ 20/400] eta: 0:03:42 lr: 0.000183 loss: 2.7944 (2.8006) grad: 0.2431 (0.2471) time: 0.4475 data: 0.0039 max mem: 22448 +train: [3] [ 40/400] eta: 0:03:06 lr: 0.000186 loss: 2.8395 (2.8451) grad: 0.2684 (0.2899) time: 0.4459 data: 0.0037 max mem: 22448 +train: [3] [ 60/400] eta: 0:02:47 lr: 0.000189 loss: 2.9132 (2.9304) grad: 0.3711 (0.4910) time: 0.4441 data: 0.0041 max mem: 22448 +WARNING: classifier 46 (36, 1.0) diverged (loss=69.11 > 63.56) at step 633. Freezing. +train: [3] [ 80/400] eta: 0:02:33 lr: 0.000192 loss: 2.9665 (2.9790) grad: 0.4121 (0.5257) time: 0.4432 data: 0.0042 max mem: 22448 +train: [3] [100/400] eta: 0:02:22 lr: 0.000195 loss: 2.8338 (2.9475) grad: 0.2529 (0.4701) time: 0.4489 data: 0.0043 max mem: 22448 +train: [3] [120/400] eta: 0:02:11 lr: 0.000198 loss: 2.8167 (2.9325) grad: 0.2778 (0.4552) time: 0.4422 data: 0.0041 max mem: 22448 +train: [3] [140/400] eta: 0:02:00 lr: 0.000201 loss: 2.9841 (2.9978) grad: 0.5380 (0.6055) time: 0.4343 data: 0.0040 max mem: 22448 +WARNING: classifier 45 (31, 1.0) diverged (loss=91.59 > 63.56) at step 675. Freezing. +train: [3] [160/400] eta: 0:01:50 lr: 0.000204 loss: 3.4601 (3.0490) grad: 1.2921 (0.6631) time: 0.4503 data: 0.0042 max mem: 22448 +train: [3] [180/400] eta: 0:01:41 lr: 0.000207 loss: 2.8357 (3.0207) grad: 0.2259 (0.6142) time: 0.4362 data: 0.0041 max mem: 22448 +train: [3] [200/400] eta: 0:01:31 lr: 0.000210 loss: 2.8110 (3.0020) grad: 0.2251 (0.5758) time: 0.4364 data: 0.0042 max mem: 22448 +train: [3] [220/400] eta: 0:01:22 lr: 0.000213 loss: 2.8184 (2.9842) grad: 0.2336 (0.5451) time: 0.4421 data: 0.0040 max mem: 22448 +train: [3] [240/400] eta: 0:01:12 lr: 0.000216 loss: 2.8056 (2.9698) grad: 0.2348 (0.5192) time: 0.4381 data: 0.0040 max mem: 22448 +train: [3] [260/400] eta: 0:01:03 lr: 0.000219 loss: 2.8060 (2.9566) grad: 0.2230 (0.4964) time: 0.4376 data: 0.0040 max mem: 22448 +train: [3] [280/400] eta: 0:00:54 lr: 0.000222 loss: 2.7985 (2.9440) grad: 0.2230 (0.4767) time: 0.4327 data: 0.0040 max mem: 22448 +train: [3] [300/400] eta: 0:00:45 lr: 0.000225 loss: 2.7985 (2.9338) grad: 0.2127 (0.4592) time: 0.4373 data: 0.0042 max mem: 22448 +train: [3] [320/400] eta: 0:00:36 lr: 0.000228 loss: 2.7801 (2.9243) grad: 0.2205 (0.4449) time: 0.4413 data: 0.0041 max mem: 22448 +train: [3] [340/400] eta: 0:00:26 lr: 0.000231 loss: 2.7801 (2.9169) grad: 0.2370 (0.4333) time: 0.4463 data: 0.0043 max mem: 22448 +train: [3] [360/400] eta: 0:00:17 lr: 0.000234 loss: 2.8148 (2.9133) grad: 0.2482 (0.4248) time: 0.4402 data: 0.0042 max mem: 22448 +train: [3] [380/400] eta: 0:00:08 lr: 0.000237 loss: 2.8839 (2.9130) grad: 0.3681 (0.4316) time: 0.4460 data: 0.0040 max mem: 22448 +train: [3] [399/400] eta: 0:00:00 lr: 0.000240 loss: 3.0749 (2.9431) grad: 0.8058 (0.4906) time: 0.4473 data: 0.0040 max mem: 22448 +train: [3] Total time: 0:02:59 (0.4494 s / it) +train: [3] Summary: lr: 0.000240 loss: 3.0749 (2.9431) grad: 0.8058 (0.4906) +eval (validation): [3] [ 0/85] eta: 0:04:46 time: 3.3692 data: 3.0819 max mem: 22448 +eval (validation): [3] [20/85] eta: 0:00:31 time: 0.3421 data: 0.0042 max mem: 22448 +eval (validation): [3] [40/85] eta: 0:00:18 time: 0.3210 data: 0.0039 max mem: 22448 +eval (validation): [3] [60/85] eta: 0:00:09 time: 0.3381 data: 0.0045 max mem: 22448 +eval (validation): [3] [80/85] eta: 0:00:01 time: 0.3281 data: 0.0039 max mem: 22448 +eval (validation): [3] [84/85] eta: 0:00:00 time: 0.3167 data: 0.0037 max mem: 22448 +eval (validation): [3] Total time: 0:00:31 (0.3694 s / it) +cv: [3] best hparam: (3.1, 1.0) (031) ('031_lr3.1e+00_wd1.0e+00') loss: 2.393 acc: 0.281 f1: 0.208 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/eval_v2/nsd_cococlip__patch__attn/checkpoint-best.pth +train: [4] [ 0/400] eta: 0:22:40 lr: nan time: 3.4008 data: 3.0155 max mem: 22448 +WARNING: classifier 43 (22, 1.0) diverged (loss=91.45 > 63.56) at step 804. Freezing. +train: [4] [ 20/400] eta: 0:03:48 lr: 0.000243 loss: 2.7939 (3.2001) grad: 0.2380 (0.8994) time: 0.4616 data: 0.0031 max mem: 22448 +train: [4] [ 40/400] eta: 0:03:08 lr: 0.000246 loss: 2.7601 (2.9787) grad: 0.2233 (0.5601) time: 0.4416 data: 0.0042 max mem: 22448 +train: [4] [ 60/400] eta: 0:02:47 lr: 0.000249 loss: 2.7525 (2.9088) grad: 0.2193 (0.4471) time: 0.4331 data: 0.0040 max mem: 22448 +train: [4] [ 80/400] eta: 0:02:34 lr: 0.000252 loss: 2.7299 (2.8686) grad: 0.2115 (0.3883) time: 0.4441 data: 0.0040 max mem: 22448 +train: [4] [100/400] eta: 0:02:21 lr: 0.000255 loss: 2.7827 (2.8534) grad: 0.2116 (0.3550) time: 0.4366 data: 0.0040 max mem: 22448 +train: [4] [120/400] eta: 0:02:10 lr: 0.000258 loss: 2.7504 (2.8336) grad: 0.2218 (0.3332) time: 0.4376 data: 0.0041 max mem: 22448 +train: [4] [140/400] eta: 0:02:00 lr: 0.000261 loss: 2.7121 (2.8224) grad: 0.2363 (0.3212) time: 0.4312 data: 0.0041 max mem: 22448 +train: [4] [160/400] eta: 0:01:50 lr: 0.000264 loss: 2.7563 (2.8149) grad: 0.2495 (0.3121) time: 0.4346 data: 0.0041 max mem: 22448 +train: [4] [180/400] eta: 0:01:40 lr: 0.000267 loss: 2.7563 (2.8108) grad: 0.2495 (0.3055) time: 0.4354 data: 0.0040 max mem: 22448 +train: [4] [200/400] eta: 0:01:30 lr: 0.000270 loss: 2.7495 (2.8023) grad: 0.2467 (0.2993) time: 0.4333 data: 0.0041 max mem: 22448 +train: [4] [220/400] eta: 0:01:21 lr: 0.000273 loss: 2.7422 (2.7997) grad: 0.2444 (0.2946) time: 0.4304 data: 0.0041 max mem: 22448 +train: [4] [240/400] eta: 0:01:12 lr: 0.000276 loss: 2.7456 (2.7959) grad: 0.2444 (0.2904) time: 0.4366 data: 0.0041 max mem: 22448 +train: [4] [260/400] eta: 0:01:02 lr: 0.000279 loss: 2.7763 (2.7949) grad: 0.2410 (0.2870) time: 0.4279 data: 0.0041 max mem: 22448 +train: [4] [280/400] eta: 0:00:53 lr: 0.000282 loss: 2.7858 (2.7933) grad: 0.2410 (0.2848) time: 0.4224 data: 0.0040 max mem: 22448 +train: [4] [300/400] eta: 0:00:44 lr: 0.000285 loss: 2.7656 (2.7912) grad: 0.2427 (0.2822) time: 0.4333 data: 0.0043 max mem: 22448 +train: [4] [320/400] eta: 0:00:35 lr: 0.000288 loss: 2.7502 (2.7889) grad: 0.2430 (0.2806) time: 0.4427 data: 0.0042 max mem: 22448 +train: [4] [340/400] eta: 0:00:26 lr: 0.000291 loss: 2.8063 (2.7994) grad: 0.2848 (0.3030) time: 0.4443 data: 0.0042 max mem: 22448 +WARNING: classifier 44 (26, 1.0) diverged (loss=69.40 > 63.56) at step 975. Freezing. +train: [4] [360/400] eta: 0:00:17 lr: 0.000294 loss: 2.9295 (2.8197) grad: 0.5847 (0.3336) time: 0.4370 data: 0.0043 max mem: 22448 +train: [4] [380/400] eta: 0:00:08 lr: 0.000297 loss: 2.7691 (2.8152) grad: 0.2285 (0.3279) time: 0.4580 data: 0.0040 max mem: 22448 +train: [4] [399/400] eta: 0:00:00 lr: 0.000300 loss: 2.7267 (2.8110) grad: 0.2269 (0.3230) time: 0.4449 data: 0.0042 max mem: 22448 +train: [4] Total time: 0:02:58 (0.4460 s / it) +train: [4] Summary: lr: 0.000300 loss: 2.7267 (2.8110) grad: 0.2269 (0.3230) +eval (validation): [4] [ 0/85] eta: 0:04:46 time: 3.3703 data: 3.0845 max mem: 22448 +eval (validation): [4] [20/85] eta: 0:00:32 time: 0.3554 data: 0.0045 max mem: 22448 +eval (validation): [4] [40/85] eta: 0:00:18 time: 0.3355 data: 0.0040 max mem: 22448 +eval (validation): [4] [60/85] eta: 0:00:09 time: 0.3394 data: 0.0042 max mem: 22448 +eval (validation): [4] [80/85] eta: 0:00:01 time: 0.3353 data: 0.0041 max mem: 22448 +eval (validation): [4] [84/85] eta: 0:00:00 time: 0.3267 data: 0.0040 max mem: 22448 +eval (validation): [4] Total time: 0:00:32 (0.3784 s / it) +cv: [4] best hparam: (1, 1.0) (024) ('024_lr1.0e+00_wd1.0e+00') loss: 2.409 acc: 0.279 f1: 0.209 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [5] [ 0/400] eta: 0:22:56 lr: nan time: 3.4409 data: 3.0527 max mem: 22448 +train: [5] [ 20/400] eta: 0:03:47 lr: 0.000300 loss: 2.6292 (2.6478) grad: 0.2305 (0.2323) time: 0.4566 data: 0.0028 max mem: 22448 +train: [5] [ 40/400] eta: 0:03:09 lr: 0.000300 loss: 2.6789 (2.6901) grad: 0.2305 (0.2331) time: 0.4479 data: 0.0043 max mem: 22448 +train: [5] [ 60/400] eta: 0:02:47 lr: 0.000300 loss: 2.7007 (2.7012) grad: 0.2363 (0.2362) time: 0.4298 data: 0.0042 max mem: 22448 +train: [5] [ 80/400] eta: 0:02:33 lr: 0.000300 loss: 2.7007 (2.6949) grad: 0.2338 (0.2348) time: 0.4374 data: 0.0041 max mem: 22448 +train: [5] [100/400] eta: 0:02:22 lr: 0.000300 loss: 2.6925 (2.6999) grad: 0.2338 (0.2374) time: 0.4520 data: 0.0043 max mem: 22448 +train: [5] [120/400] eta: 0:02:11 lr: 0.000300 loss: 2.6918 (2.6935) grad: 0.2342 (0.2365) time: 0.4367 data: 0.0040 max mem: 22448 +train: [5] [140/400] eta: 0:02:00 lr: 0.000300 loss: 2.6515 (2.6870) grad: 0.2258 (0.2345) time: 0.4402 data: 0.0040 max mem: 22448 +train: [5] [160/400] eta: 0:01:50 lr: 0.000299 loss: 2.6636 (2.6856) grad: 0.2222 (0.2344) time: 0.4339 data: 0.0041 max mem: 22448 +train: [5] [180/400] eta: 0:01:40 lr: 0.000299 loss: 2.6791 (2.6888) grad: 0.2286 (0.2344) time: 0.4363 data: 0.0042 max mem: 22448 +train: [5] [200/400] eta: 0:01:31 lr: 0.000299 loss: 2.6878 (2.6881) grad: 0.2334 (0.2346) time: 0.4364 data: 0.0041 max mem: 22448 +train: [5] [220/400] eta: 0:01:21 lr: 0.000299 loss: 2.6635 (2.6864) grad: 0.2334 (0.2337) time: 0.4335 data: 0.0042 max mem: 22448 +train: [5] [240/400] eta: 0:01:12 lr: 0.000299 loss: 2.6523 (2.6845) grad: 0.2310 (0.2340) time: 0.4355 data: 0.0040 max mem: 22448 +train: [5] [260/400] eta: 0:01:03 lr: 0.000299 loss: 2.6523 (2.6820) grad: 0.2344 (0.2337) time: 0.4333 data: 0.0042 max mem: 22448 +train: [5] [280/400] eta: 0:00:53 lr: 0.000298 loss: 2.6590 (2.6823) grad: 0.2344 (0.2340) time: 0.4312 data: 0.0041 max mem: 22448 +train: [5] [300/400] eta: 0:00:44 lr: 0.000298 loss: 2.6274 (2.6785) grad: 0.2344 (0.2339) time: 0.4352 data: 0.0041 max mem: 22448 +train: [5] [320/400] eta: 0:00:35 lr: 0.000298 loss: 2.6581 (2.6792) grad: 0.2373 (0.2347) time: 0.4322 data: 0.0040 max mem: 22448 +train: [5] [340/400] eta: 0:00:26 lr: 0.000298 loss: 2.6787 (2.6784) grad: 0.2388 (0.2349) time: 0.4547 data: 0.0042 max mem: 22448 +train: [5] [360/400] eta: 0:00:17 lr: 0.000297 loss: 2.6678 (2.6778) grad: 0.2377 (0.2349) time: 0.4452 data: 0.0042 max mem: 22448 +train: [5] [380/400] eta: 0:00:08 lr: 0.000297 loss: 2.6273 (2.6768) grad: 0.2325 (0.2349) time: 0.4448 data: 0.0041 max mem: 22448 +train: [5] [399/400] eta: 0:00:00 lr: 0.000297 loss: 2.5874 (2.6728) grad: 0.2262 (0.2342) time: 0.4322 data: 0.0040 max mem: 22448 +train: [5] Total time: 0:02:58 (0.4471 s / it) +train: [5] Summary: lr: 0.000297 loss: 2.5874 (2.6728) grad: 0.2262 (0.2342) +eval (validation): [5] [ 0/85] eta: 0:04:52 time: 3.4412 data: 3.1412 max mem: 22448 +eval (validation): [5] [20/85] eta: 0:00:31 time: 0.3331 data: 0.0039 max mem: 22448 +eval (validation): [5] [40/85] eta: 0:00:18 time: 0.3401 data: 0.0035 max mem: 22448 +eval (validation): [5] [60/85] eta: 0:00:09 time: 0.3395 data: 0.0044 max mem: 22448 +eval (validation): [5] [80/85] eta: 0:00:01 time: 0.3332 data: 0.0041 max mem: 22448 +eval (validation): [5] [84/85] eta: 0:00:00 time: 0.3206 data: 0.0040 max mem: 22448 +eval (validation): [5] Total time: 0:00:31 (0.3748 s / it) +cv: [5] best hparam: (1.2, 1.0) (025) ('025_lr1.2e+00_wd1.0e+00') loss: 2.336 acc: 0.295 f1: 0.223 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/eval_v2/nsd_cococlip__patch__attn/checkpoint-best.pth +train: [6] [ 0/400] eta: 0:22:14 lr: nan time: 3.3350 data: 3.0018 max mem: 22448 +train: [6] [ 20/400] eta: 0:03:41 lr: 0.000296 loss: 2.6153 (2.6032) grad: 0.2244 (0.2289) time: 0.4463 data: 0.0047 max mem: 22448 +train: [6] [ 40/400] eta: 0:03:05 lr: 0.000296 loss: 2.6153 (2.6216) grad: 0.2363 (0.2329) time: 0.4407 data: 0.0041 max mem: 22448 +train: [6] [ 60/400] eta: 0:02:46 lr: 0.000296 loss: 2.6030 (2.6118) grad: 0.2322 (0.2331) time: 0.4404 data: 0.0041 max mem: 22448 +train: [6] [ 80/400] eta: 0:02:32 lr: 0.000295 loss: 2.5963 (2.6011) grad: 0.2331 (0.2350) time: 0.4335 data: 0.0039 max mem: 22448 +train: [6] [100/400] eta: 0:02:21 lr: 0.000295 loss: 2.6079 (2.6010) grad: 0.2381 (0.2360) time: 0.4509 data: 0.0043 max mem: 22448 +train: [6] [120/400] eta: 0:02:10 lr: 0.000295 loss: 2.6112 (2.6033) grad: 0.2428 (0.2370) time: 0.4322 data: 0.0041 max mem: 22448 +train: [6] [140/400] eta: 0:01:59 lr: 0.000294 loss: 2.6338 (2.6106) grad: 0.2440 (0.2379) time: 0.4322 data: 0.0041 max mem: 22448 +train: [6] [160/400] eta: 0:01:49 lr: 0.000294 loss: 2.6421 (2.6140) grad: 0.2438 (0.2383) time: 0.4320 data: 0.0041 max mem: 22448 +train: [6] [180/400] eta: 0:01:39 lr: 0.000293 loss: 2.5897 (2.6122) grad: 0.2446 (0.2395) time: 0.4271 data: 0.0040 max mem: 22448 +train: [6] [200/400] eta: 0:01:30 lr: 0.000293 loss: 2.5923 (2.6138) grad: 0.2466 (0.2401) time: 0.4295 data: 0.0041 max mem: 22448 +train: [6] [220/400] eta: 0:01:21 lr: 0.000292 loss: 2.6107 (2.6106) grad: 0.2455 (0.2407) time: 0.4429 data: 0.0041 max mem: 22448 +train: [6] [240/400] eta: 0:01:11 lr: 0.000292 loss: 2.6079 (2.6123) grad: 0.2474 (0.2414) time: 0.4360 data: 0.0043 max mem: 22448 +train: [6] [260/400] eta: 0:01:02 lr: 0.000291 loss: 2.5978 (2.6079) grad: 0.2442 (0.2414) time: 0.4390 data: 0.0042 max mem: 22448 +train: [6] [280/400] eta: 0:00:53 lr: 0.000291 loss: 2.5919 (2.6087) grad: 0.2422 (0.2420) time: 0.4312 data: 0.0041 max mem: 22448 +train: [6] [300/400] eta: 0:00:44 lr: 0.000290 loss: 2.6736 (2.6116) grad: 0.2427 (0.2423) time: 0.4436 data: 0.0040 max mem: 22448 +train: [6] [320/400] eta: 0:00:35 lr: 0.000290 loss: 2.6764 (2.6124) grad: 0.2494 (0.2430) time: 0.4361 data: 0.0041 max mem: 22448 +train: [6] [340/400] eta: 0:00:26 lr: 0.000289 loss: 2.6295 (2.6143) grad: 0.2474 (0.2430) time: 0.4473 data: 0.0043 max mem: 22448 +train: [6] [360/400] eta: 0:00:17 lr: 0.000288 loss: 2.6007 (2.6121) grad: 0.2451 (0.2430) time: 0.4403 data: 0.0044 max mem: 22448 +train: [6] [380/400] eta: 0:00:08 lr: 0.000288 loss: 2.5846 (2.6139) grad: 0.2444 (0.2430) time: 0.4523 data: 0.0045 max mem: 22448 +train: [6] [399/400] eta: 0:00:00 lr: 0.000287 loss: 2.6198 (2.6140) grad: 0.2302 (0.2422) time: 0.4324 data: 0.0042 max mem: 22448 +train: [6] Total time: 0:02:58 (0.4458 s / it) +train: [6] Summary: lr: 0.000287 loss: 2.6198 (2.6140) grad: 0.2302 (0.2422) +eval (validation): [6] [ 0/85] eta: 0:04:41 time: 3.3124 data: 3.0663 max mem: 22448 +eval (validation): [6] [20/85] eta: 0:00:31 time: 0.3431 data: 0.0041 max mem: 22448 +eval (validation): [6] [40/85] eta: 0:00:18 time: 0.3420 data: 0.0036 max mem: 22448 +eval (validation): [6] [60/85] eta: 0:00:09 time: 0.3430 data: 0.0042 max mem: 22448 +eval (validation): [6] [80/85] eta: 0:00:01 time: 0.3345 data: 0.0041 max mem: 22448 +eval (validation): [6] [84/85] eta: 0:00:00 time: 0.3274 data: 0.0040 max mem: 22448 +eval (validation): [6] Total time: 0:00:32 (0.3770 s / it) +cv: [6] best hparam: (0.72, 1.0) (022) ('022_lr7.2e-01_wd1.0e+00') loss: 2.345 acc: 0.292 f1: 0.235 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [7] [ 0/400] eta: 0:22:07 lr: nan time: 3.3200 data: 2.9496 max mem: 22448 +train: [7] [ 20/400] eta: 0:03:38 lr: 0.000286 loss: 2.5277 (2.5356) grad: 0.2341 (0.2396) time: 0.4374 data: 0.0047 max mem: 22448 +train: [7] [ 40/400] eta: 0:03:03 lr: 0.000286 loss: 2.5215 (2.5356) grad: 0.2349 (0.2400) time: 0.4405 data: 0.0040 max mem: 22448 +train: [7] [ 60/400] eta: 0:02:45 lr: 0.000285 loss: 2.5215 (2.5249) grad: 0.2427 (0.2436) time: 0.4437 data: 0.0042 max mem: 22448 +train: [7] [ 80/400] eta: 0:02:31 lr: 0.000284 loss: 2.5392 (2.5389) grad: 0.2427 (0.2422) time: 0.4300 data: 0.0041 max mem: 22448 +train: [7] [100/400] eta: 0:02:20 lr: 0.000284 loss: 2.5144 (2.5304) grad: 0.2385 (0.2421) time: 0.4470 data: 0.0041 max mem: 22448 +train: [7] [120/400] eta: 0:02:09 lr: 0.000283 loss: 2.5140 (2.5295) grad: 0.2434 (0.2432) time: 0.4335 data: 0.0042 max mem: 22448 +train: [7] [140/400] eta: 0:01:59 lr: 0.000282 loss: 2.5276 (2.5308) grad: 0.2455 (0.2433) time: 0.4386 data: 0.0041 max mem: 22448 +train: [7] [160/400] eta: 0:01:49 lr: 0.000282 loss: 2.5409 (2.5328) grad: 0.2412 (0.2434) time: 0.4319 data: 0.0042 max mem: 22448 +train: [7] [180/400] eta: 0:01:39 lr: 0.000281 loss: 2.6066 (2.5408) grad: 0.2495 (0.2448) time: 0.4278 data: 0.0042 max mem: 22448 +train: [7] [200/400] eta: 0:01:30 lr: 0.000280 loss: 2.5775 (2.5413) grad: 0.2561 (0.2455) time: 0.4393 data: 0.0042 max mem: 22448 +train: [7] [220/400] eta: 0:01:21 lr: 0.000279 loss: 2.5472 (2.5401) grad: 0.2530 (0.2461) time: 0.4427 data: 0.0041 max mem: 22448 +train: [7] [240/400] eta: 0:01:11 lr: 0.000278 loss: 2.5707 (2.5419) grad: 0.2460 (0.2460) time: 0.4302 data: 0.0042 max mem: 22448 +train: [7] [260/400] eta: 0:01:02 lr: 0.000278 loss: 2.5278 (2.5398) grad: 0.2342 (0.2451) time: 0.4273 data: 0.0041 max mem: 22448 +train: [7] [280/400] eta: 0:00:53 lr: 0.000277 loss: 2.4899 (2.5369) grad: 0.2377 (0.2452) time: 0.4326 data: 0.0041 max mem: 22448 +train: [7] [300/400] eta: 0:00:44 lr: 0.000276 loss: 2.4863 (2.5359) grad: 0.2452 (0.2457) time: 0.4268 data: 0.0041 max mem: 22448 +train: [7] [320/400] eta: 0:00:35 lr: 0.000275 loss: 2.5162 (2.5360) grad: 0.2490 (0.2455) time: 0.4394 data: 0.0042 max mem: 22448 +train: [7] [340/400] eta: 0:00:26 lr: 0.000274 loss: 2.4912 (2.5341) grad: 0.2396 (0.2452) time: 0.4488 data: 0.0042 max mem: 22448 +train: [7] [360/400] eta: 0:00:17 lr: 0.000273 loss: 2.5075 (2.5346) grad: 0.2396 (0.2450) time: 0.4420 data: 0.0042 max mem: 22448 +train: [7] [380/400] eta: 0:00:08 lr: 0.000272 loss: 2.5408 (2.5345) grad: 0.2413 (0.2455) time: 0.4534 data: 0.0042 max mem: 22448 +train: [7] [399/400] eta: 0:00:00 lr: 0.000271 loss: 2.5596 (2.5357) grad: 0.2518 (0.2462) time: 0.4440 data: 0.0041 max mem: 22448 +train: [7] Total time: 0:02:58 (0.4453 s / it) +train: [7] Summary: lr: 0.000271 loss: 2.5596 (2.5357) grad: 0.2518 (0.2462) +eval (validation): [7] [ 0/85] eta: 0:04:34 time: 3.2300 data: 3.0029 max mem: 22448 +eval (validation): [7] [20/85] eta: 0:00:31 time: 0.3477 data: 0.0103 max mem: 22448 +eval (validation): [7] [40/85] eta: 0:00:18 time: 0.3521 data: 0.0035 max mem: 22448 +eval (validation): [7] [60/85] eta: 0:00:09 time: 0.3426 data: 0.0043 max mem: 22448 +eval (validation): [7] [80/85] eta: 0:00:01 time: 0.3258 data: 0.0042 max mem: 22448 +eval (validation): [7] [84/85] eta: 0:00:00 time: 0.3199 data: 0.0041 max mem: 22448 +eval (validation): [7] Total time: 0:00:32 (0.3778 s / it) +cv: [7] best hparam: (0.61, 1.0) (021) ('021_lr6.1e-01_wd1.0e+00') loss: 2.362 acc: 0.286 f1: 0.226 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [8] [ 0/400] eta: 0:22:40 lr: nan time: 3.4006 data: 3.0322 max mem: 22448 +train: [8] [ 20/400] eta: 0:03:48 lr: 0.000270 loss: 2.3669 (2.4103) grad: 0.2251 (0.2313) time: 0.4623 data: 0.0036 max mem: 22448 +train: [8] [ 40/400] eta: 0:03:08 lr: 0.000270 loss: 2.4439 (2.4404) grad: 0.2394 (0.2373) time: 0.4389 data: 0.0044 max mem: 22448 +train: [8] [ 60/400] eta: 0:02:49 lr: 0.000269 loss: 2.4810 (2.4499) grad: 0.2418 (0.2377) time: 0.4465 data: 0.0043 max mem: 22448 +train: [8] [ 80/400] eta: 0:02:34 lr: 0.000268 loss: 2.5034 (2.4627) grad: 0.2406 (0.2410) time: 0.4345 data: 0.0040 max mem: 22448 +train: [8] [100/400] eta: 0:02:22 lr: 0.000267 loss: 2.5039 (2.4618) grad: 0.2557 (0.2455) time: 0.4435 data: 0.0043 max mem: 22448 +train: [8] [120/400] eta: 0:02:11 lr: 0.000266 loss: 2.4809 (2.4634) grad: 0.2687 (0.2503) time: 0.4388 data: 0.0041 max mem: 22448 +train: [8] [140/400] eta: 0:02:00 lr: 0.000265 loss: 2.4809 (2.4712) grad: 0.2727 (0.2530) time: 0.4463 data: 0.0042 max mem: 22448 +train: [8] [160/400] eta: 0:01:50 lr: 0.000264 loss: 2.4954 (2.4730) grad: 0.2734 (0.2563) time: 0.4383 data: 0.0040 max mem: 22448 +train: [8] [180/400] eta: 0:01:41 lr: 0.000263 loss: 2.4489 (2.4674) grad: 0.2607 (0.2561) time: 0.4390 data: 0.0041 max mem: 22448 +train: [8] [200/400] eta: 0:01:31 lr: 0.000262 loss: 2.4889 (2.4717) grad: 0.2576 (0.2567) time: 0.4378 data: 0.0041 max mem: 22448 +train: [8] [220/400] eta: 0:01:21 lr: 0.000260 loss: 2.5088 (2.4743) grad: 0.2585 (0.2565) time: 0.4329 data: 0.0041 max mem: 22448 +train: [8] [240/400] eta: 0:01:12 lr: 0.000259 loss: 2.4870 (2.4740) grad: 0.2553 (0.2563) time: 0.4352 data: 0.0041 max mem: 22448 +train: [8] [260/400] eta: 0:01:03 lr: 0.000258 loss: 2.4870 (2.4764) grad: 0.2474 (0.2560) time: 0.4336 data: 0.0039 max mem: 22448 +train: [8] [280/400] eta: 0:00:54 lr: 0.000257 loss: 2.4954 (2.4769) grad: 0.2471 (0.2562) time: 0.4265 data: 0.0041 max mem: 22448 +train: [8] [300/400] eta: 0:00:44 lr: 0.000256 loss: 2.4649 (2.4763) grad: 0.2527 (0.2561) time: 0.4464 data: 0.0041 max mem: 22448 +train: [8] [320/400] eta: 0:00:35 lr: 0.000255 loss: 2.4406 (2.4748) grad: 0.2465 (0.2551) time: 0.4452 data: 0.0039 max mem: 22448 +train: [8] [340/400] eta: 0:00:26 lr: 0.000254 loss: 2.4406 (2.4741) grad: 0.2465 (0.2556) time: 0.4413 data: 0.0041 max mem: 22448 +train: [8] [360/400] eta: 0:00:17 lr: 0.000253 loss: 2.4414 (2.4737) grad: 0.2536 (0.2552) time: 0.4448 data: 0.0043 max mem: 22448 +train: [8] [380/400] eta: 0:00:08 lr: 0.000252 loss: 2.4517 (2.4744) grad: 0.2495 (0.2550) time: 0.4427 data: 0.0044 max mem: 22448 +train: [8] [399/400] eta: 0:00:00 lr: 0.000250 loss: 2.4559 (2.4741) grad: 0.2525 (0.2554) time: 0.4393 data: 0.0042 max mem: 22448 +train: [8] Total time: 0:02:59 (0.4484 s / it) +train: [8] Summary: lr: 0.000250 loss: 2.4559 (2.4741) grad: 0.2525 (0.2554) +eval (validation): [8] [ 0/85] eta: 0:04:21 time: 3.0728 data: 2.8417 max mem: 22448 +eval (validation): [8] [20/85] eta: 0:00:30 time: 0.3357 data: 0.0034 max mem: 22448 +eval (validation): [8] [40/85] eta: 0:00:18 time: 0.3398 data: 0.0043 max mem: 22448 +eval (validation): [8] [60/85] eta: 0:00:09 time: 0.3440 data: 0.0042 max mem: 22448 +eval (validation): [8] [80/85] eta: 0:00:01 time: 0.3273 data: 0.0040 max mem: 22448 +eval (validation): [8] [84/85] eta: 0:00:00 time: 0.3180 data: 0.0039 max mem: 22448 +eval (validation): [8] Total time: 0:00:31 (0.3707 s / it) +cv: [8] best hparam: (0.44, 1.0) (019) ('019_lr4.4e-01_wd1.0e+00') loss: 2.386 acc: 0.276 f1: 0.220 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [9] [ 0/400] eta: 0:22:06 lr: nan time: 3.3169 data: 2.9875 max mem: 22448 +train: [9] [ 20/400] eta: 0:03:39 lr: 0.000249 loss: 2.4407 (2.4342) grad: 0.2538 (0.2601) time: 0.4411 data: 0.0048 max mem: 22448 +train: [9] [ 40/400] eta: 0:03:05 lr: 0.000248 loss: 2.4431 (2.4393) grad: 0.2521 (0.2533) time: 0.4494 data: 0.0038 max mem: 22448 +train: [9] [ 60/400] eta: 0:02:48 lr: 0.000247 loss: 2.4236 (2.4253) grad: 0.2447 (0.2509) time: 0.4545 data: 0.0043 max mem: 22448 +train: [9] [ 80/400] eta: 0:02:33 lr: 0.000246 loss: 2.3887 (2.4324) grad: 0.2455 (0.2508) time: 0.4286 data: 0.0040 max mem: 22448 +train: [9] [100/400] eta: 0:02:21 lr: 0.000244 loss: 2.4143 (2.4333) grad: 0.2527 (0.2514) time: 0.4436 data: 0.0042 max mem: 22448 +train: [9] [120/400] eta: 0:02:10 lr: 0.000243 loss: 2.4061 (2.4294) grad: 0.2527 (0.2516) time: 0.4393 data: 0.0043 max mem: 22448 +train: [9] [140/400] eta: 0:02:00 lr: 0.000242 loss: 2.4271 (2.4301) grad: 0.2534 (0.2532) time: 0.4357 data: 0.0041 max mem: 22448 +train: [9] [160/400] eta: 0:01:50 lr: 0.000241 loss: 2.4284 (2.4290) grad: 0.2582 (0.2543) time: 0.4338 data: 0.0042 max mem: 22448 +train: [9] [180/400] eta: 0:01:40 lr: 0.000240 loss: 2.4159 (2.4319) grad: 0.2525 (0.2551) time: 0.4392 data: 0.0041 max mem: 22448 +train: [9] [200/400] eta: 0:01:30 lr: 0.000238 loss: 2.3965 (2.4291) grad: 0.2568 (0.2559) time: 0.4397 data: 0.0040 max mem: 22448 +train: [9] [220/400] eta: 0:01:21 lr: 0.000237 loss: 2.4009 (2.4276) grad: 0.2616 (0.2567) time: 0.4345 data: 0.0040 max mem: 22448 +train: [9] [240/400] eta: 0:01:12 lr: 0.000236 loss: 2.4400 (2.4307) grad: 0.2597 (0.2560) time: 0.4383 data: 0.0041 max mem: 22448 +train: [9] [260/400] eta: 0:01:03 lr: 0.000234 loss: 2.4609 (2.4298) grad: 0.2491 (0.2553) time: 0.4355 data: 0.0041 max mem: 22448 +train: [9] [280/400] eta: 0:00:54 lr: 0.000233 loss: 2.4202 (2.4291) grad: 0.2530 (0.2558) time: 0.4488 data: 0.0042 max mem: 22448 +train: [9] [300/400] eta: 0:00:44 lr: 0.000232 loss: 2.4317 (2.4300) grad: 0.2607 (0.2564) time: 0.4339 data: 0.0040 max mem: 22448 +train: [9] [320/400] eta: 0:00:35 lr: 0.000230 loss: 2.4183 (2.4314) grad: 0.2621 (0.2563) time: 0.4275 data: 0.0040 max mem: 22448 +train: [9] [340/400] eta: 0:00:26 lr: 0.000229 loss: 2.4029 (2.4292) grad: 0.2623 (0.2567) time: 0.4391 data: 0.0042 max mem: 22448 +train: [9] [360/400] eta: 0:00:17 lr: 0.000228 loss: 2.4182 (2.4298) grad: 0.2678 (0.2575) time: 0.4457 data: 0.0041 max mem: 22448 +train: [9] [380/400] eta: 0:00:08 lr: 0.000226 loss: 2.4132 (2.4284) grad: 0.2634 (0.2573) time: 0.4449 data: 0.0040 max mem: 22448 +train: [9] [399/400] eta: 0:00:00 lr: 0.000225 loss: 2.4132 (2.4290) grad: 0.2575 (0.2577) time: 0.4317 data: 0.0040 max mem: 22448 +train: [9] Total time: 0:02:58 (0.4468 s / it) +train: [9] Summary: lr: 0.000225 loss: 2.4132 (2.4290) grad: 0.2575 (0.2577) +eval (validation): [9] [ 0/85] eta: 0:04:28 time: 3.1593 data: 2.9252 max mem: 22448 +eval (validation): [9] [20/85] eta: 0:00:31 time: 0.3570 data: 0.0050 max mem: 22448 +eval (validation): [9] [40/85] eta: 0:00:18 time: 0.3397 data: 0.0040 max mem: 22448 +eval (validation): [9] [60/85] eta: 0:00:09 time: 0.3339 data: 0.0042 max mem: 22448 +eval (validation): [9] [80/85] eta: 0:00:01 time: 0.3179 data: 0.0040 max mem: 22448 +eval (validation): [9] [84/85] eta: 0:00:00 time: 0.3077 data: 0.0039 max mem: 22448 +eval (validation): [9] Total time: 0:00:31 (0.3717 s / it) +cv: [9] best hparam: (0.44, 1.0) (019) ('019_lr4.4e-01_wd1.0e+00') loss: 2.350 acc: 0.290 f1: 0.227 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [10] [ 0/400] eta: 0:22:51 lr: nan time: 3.4292 data: 3.0553 max mem: 22448 +train: [10] [ 20/400] eta: 0:03:48 lr: 0.000224 loss: 2.3690 (2.3612) grad: 0.2593 (0.2629) time: 0.4611 data: 0.0032 max mem: 22448 +train: [10] [ 40/400] eta: 0:03:09 lr: 0.000222 loss: 2.3690 (2.3578) grad: 0.2537 (0.2582) time: 0.4470 data: 0.0040 max mem: 22448 +train: [10] [ 60/400] eta: 0:02:49 lr: 0.000221 loss: 2.3798 (2.3737) grad: 0.2498 (0.2550) time: 0.4446 data: 0.0043 max mem: 22448 +train: [10] [ 80/400] eta: 0:02:34 lr: 0.000220 loss: 2.3550 (2.3644) grad: 0.2457 (0.2531) time: 0.4336 data: 0.0043 max mem: 22448 +train: [10] [100/400] eta: 0:02:22 lr: 0.000218 loss: 2.3507 (2.3588) grad: 0.2465 (0.2532) time: 0.4471 data: 0.0042 max mem: 22448 +train: [10] [120/400] eta: 0:02:11 lr: 0.000217 loss: 2.3514 (2.3600) grad: 0.2533 (0.2535) time: 0.4383 data: 0.0043 max mem: 22448 +train: [10] [140/400] eta: 0:02:01 lr: 0.000215 loss: 2.3608 (2.3650) grad: 0.2521 (0.2532) time: 0.4434 data: 0.0041 max mem: 22448 +train: [10] [160/400] eta: 0:01:51 lr: 0.000214 loss: 2.3772 (2.3660) grad: 0.2482 (0.2533) time: 0.4411 data: 0.0040 max mem: 22448 +train: [10] [180/400] eta: 0:01:41 lr: 0.000213 loss: 2.3863 (2.3699) grad: 0.2495 (0.2541) time: 0.4307 data: 0.0041 max mem: 22448 +train: [10] [200/400] eta: 0:01:31 lr: 0.000211 loss: 2.3908 (2.3715) grad: 0.2558 (0.2553) time: 0.4367 data: 0.0042 max mem: 22448 +train: [10] [220/400] eta: 0:01:21 lr: 0.000210 loss: 2.3949 (2.3715) grad: 0.2646 (0.2561) time: 0.4373 data: 0.0041 max mem: 22448 +train: [10] [240/400] eta: 0:01:12 lr: 0.000208 loss: 2.3741 (2.3710) grad: 0.2564 (0.2558) time: 0.4353 data: 0.0042 max mem: 22448 +train: [10] [260/400] eta: 0:01:03 lr: 0.000207 loss: 2.3693 (2.3690) grad: 0.2524 (0.2556) time: 0.4391 data: 0.0042 max mem: 22448 +train: [10] [280/400] eta: 0:00:54 lr: 0.000205 loss: 2.3809 (2.3702) grad: 0.2498 (0.2556) time: 0.4352 data: 0.0041 max mem: 22448 +train: [10] [300/400] eta: 0:00:45 lr: 0.000204 loss: 2.3124 (2.3666) grad: 0.2489 (0.2551) time: 0.4390 data: 0.0042 max mem: 22448 +train: [10] [320/400] eta: 0:00:36 lr: 0.000202 loss: 2.2899 (2.3648) grad: 0.2527 (0.2552) time: 0.4451 data: 0.0041 max mem: 22448 +train: [10] [340/400] eta: 0:00:27 lr: 0.000201 loss: 2.3461 (2.3635) grad: 0.2614 (0.2556) time: 0.4569 data: 0.0041 max mem: 22448 +train: [10] [360/400] eta: 0:00:18 lr: 0.000199 loss: 2.3292 (2.3618) grad: 0.2541 (0.2555) time: 0.4640 data: 0.0042 max mem: 22448 +train: [10] [380/400] eta: 0:00:09 lr: 0.000198 loss: 2.3169 (2.3604) grad: 0.2541 (0.2555) time: 0.4524 data: 0.0041 max mem: 22448 +train: [10] [399/400] eta: 0:00:00 lr: 0.000196 loss: 2.3377 (2.3618) grad: 0.2614 (0.2560) time: 0.4391 data: 0.0041 max mem: 22448 +train: [10] Total time: 0:03:00 (0.4511 s / it) +train: [10] Summary: lr: 0.000196 loss: 2.3377 (2.3618) grad: 0.2614 (0.2560) +eval (validation): [10] [ 0/85] eta: 0:04:35 time: 3.2453 data: 2.9567 max mem: 22448 +eval (validation): [10] [20/85] eta: 0:00:31 time: 0.3420 data: 0.0040 max mem: 22448 +eval (validation): [10] [40/85] eta: 0:00:18 time: 0.3454 data: 0.0041 max mem: 22448 +eval (validation): [10] [60/85] eta: 0:00:09 time: 0.3519 data: 0.0041 max mem: 22448 +eval (validation): [10] [80/85] eta: 0:00:01 time: 0.3257 data: 0.0039 max mem: 22448 +eval (validation): [10] [84/85] eta: 0:00:00 time: 0.3192 data: 0.0038 max mem: 22448 +eval (validation): [10] Total time: 0:00:32 (0.3768 s / it) +cv: [10] best hparam: (0.38, 1.0) (018) ('018_lr3.8e-01_wd1.0e+00') loss: 2.355 acc: 0.288 f1: 0.228 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [11] [ 0/400] eta: 0:22:36 lr: nan time: 3.3911 data: 3.0156 max mem: 22448 +train: [11] [ 20/400] eta: 0:03:48 lr: 0.000195 loss: 2.2650 (2.2976) grad: 0.2525 (0.2518) time: 0.4622 data: 0.0050 max mem: 22448 +train: [11] [ 40/400] eta: 0:03:09 lr: 0.000193 loss: 2.3121 (2.3183) grad: 0.2525 (0.2520) time: 0.4462 data: 0.0041 max mem: 22448 +train: [11] [ 60/400] eta: 0:02:50 lr: 0.000192 loss: 2.3011 (2.3029) grad: 0.2547 (0.2542) time: 0.4491 data: 0.0042 max mem: 22448 +train: [11] [ 80/400] eta: 0:02:34 lr: 0.000190 loss: 2.3011 (2.3126) grad: 0.2574 (0.2567) time: 0.4338 data: 0.0040 max mem: 22448 +train: [11] [100/400] eta: 0:02:23 lr: 0.000189 loss: 2.3315 (2.3106) grad: 0.2575 (0.2570) time: 0.4501 data: 0.0041 max mem: 22448 +train: [11] [120/400] eta: 0:02:11 lr: 0.000187 loss: 2.2472 (2.2983) grad: 0.2570 (0.2576) time: 0.4403 data: 0.0041 max mem: 22448 +train: [11] [140/400] eta: 0:02:01 lr: 0.000186 loss: 2.2856 (2.3010) grad: 0.2570 (0.2583) time: 0.4505 data: 0.0042 max mem: 22448 +train: [11] [160/400] eta: 0:01:51 lr: 0.000184 loss: 2.3267 (2.3034) grad: 0.2634 (0.2590) time: 0.4293 data: 0.0041 max mem: 22448 +train: [11] [180/400] eta: 0:01:41 lr: 0.000183 loss: 2.2845 (2.3039) grad: 0.2689 (0.2608) time: 0.4323 data: 0.0041 max mem: 22448 +train: [11] [200/400] eta: 0:01:31 lr: 0.000181 loss: 2.3051 (2.3069) grad: 0.2611 (0.2605) time: 0.4268 data: 0.0041 max mem: 22448 +train: [11] [220/400] eta: 0:01:21 lr: 0.000180 loss: 2.3640 (2.3137) grad: 0.2580 (0.2601) time: 0.4324 data: 0.0040 max mem: 22448 +train: [11] [240/400] eta: 0:01:12 lr: 0.000178 loss: 2.3784 (2.3147) grad: 0.2555 (0.2602) time: 0.4326 data: 0.0041 max mem: 22448 +train: [11] [260/400] eta: 0:01:03 lr: 0.000177 loss: 2.3104 (2.3140) grad: 0.2632 (0.2610) time: 0.4389 data: 0.0041 max mem: 22448 +train: [11] [280/400] eta: 0:00:54 lr: 0.000175 loss: 2.3351 (2.3152) grad: 0.2632 (0.2612) time: 0.4330 data: 0.0040 max mem: 22448 +train: [11] [300/400] eta: 0:00:44 lr: 0.000174 loss: 2.3351 (2.3190) grad: 0.2623 (0.2616) time: 0.4301 data: 0.0040 max mem: 22448 +train: [11] [320/400] eta: 0:00:35 lr: 0.000172 loss: 2.3306 (2.3201) grad: 0.2618 (0.2618) time: 0.4332 data: 0.0040 max mem: 22448 +train: [11] [340/400] eta: 0:00:26 lr: 0.000170 loss: 2.3413 (2.3207) grad: 0.2618 (0.2622) time: 0.4472 data: 0.0041 max mem: 22448 +train: [11] [360/400] eta: 0:00:17 lr: 0.000169 loss: 2.3296 (2.3202) grad: 0.2550 (0.2622) time: 0.4624 data: 0.0040 max mem: 22448 +train: [11] [380/400] eta: 0:00:08 lr: 0.000167 loss: 2.2772 (2.3173) grad: 0.2549 (0.2618) time: 0.4462 data: 0.0042 max mem: 22448 +train: [11] [399/400] eta: 0:00:00 lr: 0.000166 loss: 2.3136 (2.3197) grad: 0.2542 (0.2614) time: 0.4344 data: 0.0039 max mem: 22448 +train: [11] Total time: 0:02:59 (0.4483 s / it) +train: [11] Summary: lr: 0.000166 loss: 2.3136 (2.3197) grad: 0.2542 (0.2614) +eval (validation): [11] [ 0/85] eta: 0:04:26 time: 3.1360 data: 2.9026 max mem: 22448 +eval (validation): [11] [20/85] eta: 0:00:32 time: 0.3724 data: 0.0049 max mem: 22448 +eval (validation): [11] [40/85] eta: 0:00:19 time: 0.3412 data: 0.0043 max mem: 22448 +eval (validation): [11] [60/85] eta: 0:00:09 time: 0.3491 data: 0.0042 max mem: 22448 +eval (validation): [11] [80/85] eta: 0:00:01 time: 0.3367 data: 0.0040 max mem: 22448 +eval (validation): [11] [84/85] eta: 0:00:00 time: 0.3269 data: 0.0039 max mem: 22448 +eval (validation): [11] Total time: 0:00:32 (0.3838 s / it) +cv: [11] best hparam: (0.38, 1.0) (018) ('018_lr3.8e-01_wd1.0e+00') loss: 2.363 acc: 0.290 f1: 0.228 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [12] [ 0/400] eta: 0:22:48 lr: nan time: 3.4213 data: 3.0862 max mem: 22448 +train: [12] [ 20/400] eta: 0:03:47 lr: 0.000164 loss: 2.1936 (2.2150) grad: 0.2507 (0.2488) time: 0.4578 data: 0.0041 max mem: 22448 +train: [12] [ 40/400] eta: 0:03:09 lr: 0.000163 loss: 2.2282 (2.2335) grad: 0.2517 (0.2511) time: 0.4487 data: 0.0042 max mem: 22448 +train: [12] [ 60/400] eta: 0:02:50 lr: 0.000161 loss: 2.2414 (2.2358) grad: 0.2486 (0.2496) time: 0.4521 data: 0.0043 max mem: 22448 +train: [12] [ 80/400] eta: 0:02:34 lr: 0.000160 loss: 2.2414 (2.2419) grad: 0.2484 (0.2494) time: 0.4300 data: 0.0041 max mem: 22448 +train: [12] [100/400] eta: 0:02:23 lr: 0.000158 loss: 2.2772 (2.2435) grad: 0.2526 (0.2500) time: 0.4503 data: 0.0041 max mem: 22448 +train: [12] [120/400] eta: 0:02:11 lr: 0.000156 loss: 2.2462 (2.2487) grad: 0.2483 (0.2486) time: 0.4387 data: 0.0041 max mem: 22448 +train: [12] [140/400] eta: 0:02:01 lr: 0.000155 loss: 2.2324 (2.2463) grad: 0.2489 (0.2514) time: 0.4356 data: 0.0041 max mem: 22448 +train: [12] [160/400] eta: 0:01:50 lr: 0.000153 loss: 2.2415 (2.2491) grad: 0.2682 (0.2538) time: 0.4340 data: 0.0041 max mem: 22448 +train: [12] [180/400] eta: 0:01:41 lr: 0.000152 loss: 2.2242 (2.2494) grad: 0.2661 (0.2546) time: 0.4398 data: 0.0041 max mem: 22448 +train: [12] [200/400] eta: 0:01:31 lr: 0.000150 loss: 2.2929 (2.2563) grad: 0.2598 (0.2552) time: 0.4331 data: 0.0040 max mem: 22448 +train: [12] [220/400] eta: 0:01:21 lr: 0.000149 loss: 2.2941 (2.2602) grad: 0.2510 (0.2551) time: 0.4348 data: 0.0041 max mem: 22448 +train: [12] [240/400] eta: 0:01:12 lr: 0.000147 loss: 2.2657 (2.2584) grad: 0.2612 (0.2567) time: 0.4298 data: 0.0041 max mem: 22448 +train: [12] [260/400] eta: 0:01:03 lr: 0.000145 loss: 2.2354 (2.2588) grad: 0.2626 (0.2566) time: 0.4292 data: 0.0040 max mem: 22448 +train: [12] [280/400] eta: 0:00:54 lr: 0.000144 loss: 2.2200 (2.2556) grad: 0.2556 (0.2569) time: 0.4394 data: 0.0040 max mem: 22448 +train: [12] [300/400] eta: 0:00:44 lr: 0.000142 loss: 2.2265 (2.2569) grad: 0.2583 (0.2577) time: 0.4359 data: 0.0042 max mem: 22448 +train: [12] [320/400] eta: 0:00:35 lr: 0.000141 loss: 2.2335 (2.2593) grad: 0.2640 (0.2579) time: 0.4414 data: 0.0041 max mem: 22448 +train: [12] [340/400] eta: 0:00:26 lr: 0.000139 loss: 2.2474 (2.2590) grad: 0.2622 (0.2578) time: 0.4559 data: 0.0041 max mem: 22448 +train: [12] [360/400] eta: 0:00:17 lr: 0.000138 loss: 2.2306 (2.2579) grad: 0.2575 (0.2577) time: 0.4517 data: 0.0040 max mem: 22448 +train: [12] [380/400] eta: 0:00:08 lr: 0.000136 loss: 2.2321 (2.2588) grad: 0.2575 (0.2578) time: 0.4360 data: 0.0041 max mem: 22448 +train: [12] [399/400] eta: 0:00:00 lr: 0.000134 loss: 2.2377 (2.2589) grad: 0.2606 (0.2582) time: 0.4394 data: 0.0040 max mem: 22448 +train: [12] Total time: 0:02:59 (0.4484 s / it) +train: [12] Summary: lr: 0.000134 loss: 2.2377 (2.2589) grad: 0.2606 (0.2582) +eval (validation): [12] [ 0/85] eta: 0:04:34 time: 3.2331 data: 2.9571 max mem: 22448 +eval (validation): [12] [20/85] eta: 0:00:33 time: 0.3726 data: 0.0046 max mem: 22448 +eval (validation): [12] [40/85] eta: 0:00:19 time: 0.3417 data: 0.0046 max mem: 22448 +eval (validation): [12] [60/85] eta: 0:00:09 time: 0.3335 data: 0.0043 max mem: 22448 +eval (validation): [12] [80/85] eta: 0:00:01 time: 0.3274 data: 0.0040 max mem: 22448 +eval (validation): [12] [84/85] eta: 0:00:00 time: 0.3204 data: 0.0038 max mem: 22448 +eval (validation): [12] Total time: 0:00:32 (0.3790 s / it) +cv: [12] best hparam: (0.38, 1.0) (018) ('018_lr3.8e-01_wd1.0e+00') loss: 2.371 acc: 0.283 f1: 0.227 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [13] [ 0/400] eta: 0:22:43 lr: nan time: 3.4090 data: 3.0812 max mem: 22448 +train: [13] [ 20/400] eta: 0:03:47 lr: 0.000133 loss: 2.2107 (2.2135) grad: 0.2556 (0.2575) time: 0.4573 data: 0.0042 max mem: 22448 +train: [13] [ 40/400] eta: 0:03:08 lr: 0.000131 loss: 2.2298 (2.2118) grad: 0.2556 (0.2574) time: 0.4470 data: 0.0038 max mem: 22448 +train: [13] [ 60/400] eta: 0:02:49 lr: 0.000130 loss: 2.2299 (2.2199) grad: 0.2563 (0.2589) time: 0.4450 data: 0.0043 max mem: 22448 +train: [13] [ 80/400] eta: 0:02:33 lr: 0.000128 loss: 2.2218 (2.2167) grad: 0.2553 (0.2591) time: 0.4231 data: 0.0041 max mem: 22448 +train: [13] [100/400] eta: 0:02:21 lr: 0.000127 loss: 2.1765 (2.2079) grad: 0.2534 (0.2579) time: 0.4430 data: 0.0043 max mem: 22448 +train: [13] [120/400] eta: 0:02:10 lr: 0.000125 loss: 2.1980 (2.2037) grad: 0.2534 (0.2583) time: 0.4322 data: 0.0042 max mem: 22448 +train: [13] [140/400] eta: 0:01:59 lr: 0.000124 loss: 2.2278 (2.2128) grad: 0.2643 (0.2596) time: 0.4351 data: 0.0041 max mem: 22448 +train: [13] [160/400] eta: 0:01:49 lr: 0.000122 loss: 2.2359 (2.2126) grad: 0.2683 (0.2604) time: 0.4295 data: 0.0040 max mem: 22448 +train: [13] [180/400] eta: 0:01:40 lr: 0.000120 loss: 2.2329 (2.2183) grad: 0.2661 (0.2607) time: 0.4378 data: 0.0042 max mem: 22448 +train: [13] [200/400] eta: 0:01:30 lr: 0.000119 loss: 2.1925 (2.2119) grad: 0.2561 (0.2601) time: 0.4337 data: 0.0042 max mem: 22448 +train: [13] [220/400] eta: 0:01:21 lr: 0.000117 loss: 2.1734 (2.2146) grad: 0.2593 (0.2605) time: 0.4333 data: 0.0042 max mem: 22448 +train: [13] [240/400] eta: 0:01:11 lr: 0.000116 loss: 2.2374 (2.2141) grad: 0.2625 (0.2602) time: 0.4323 data: 0.0040 max mem: 22448 +train: [13] [260/400] eta: 0:01:02 lr: 0.000114 loss: 2.2013 (2.2151) grad: 0.2516 (0.2591) time: 0.4412 data: 0.0041 max mem: 22448 +train: [13] [280/400] eta: 0:00:53 lr: 0.000113 loss: 2.1708 (2.2132) grad: 0.2473 (0.2583) time: 0.4388 data: 0.0042 max mem: 22448 +train: [13] [300/400] eta: 0:00:44 lr: 0.000111 loss: 2.1911 (2.2126) grad: 0.2454 (0.2573) time: 0.4382 data: 0.0041 max mem: 22448 +train: [13] [320/400] eta: 0:00:35 lr: 0.000110 loss: 2.2202 (2.2136) grad: 0.2517 (0.2576) time: 0.4320 data: 0.0040 max mem: 22448 +train: [13] [340/400] eta: 0:00:26 lr: 0.000108 loss: 2.2161 (2.2137) grad: 0.2543 (0.2570) time: 0.4458 data: 0.0042 max mem: 22448 +train: [13] [360/400] eta: 0:00:17 lr: 0.000107 loss: 2.2092 (2.2137) grad: 0.2579 (0.2572) time: 0.4448 data: 0.0042 max mem: 22448 +train: [13] [380/400] eta: 0:00:08 lr: 0.000105 loss: 2.1973 (2.2134) grad: 0.2628 (0.2575) time: 0.4422 data: 0.0042 max mem: 22448 +train: [13] [399/400] eta: 0:00:00 lr: 0.000104 loss: 2.2073 (2.2137) grad: 0.2558 (0.2576) time: 0.4360 data: 0.0041 max mem: 22448 +train: [13] Total time: 0:02:58 (0.4461 s / it) +train: [13] Summary: lr: 0.000104 loss: 2.2073 (2.2137) grad: 0.2558 (0.2576) +eval (validation): [13] [ 0/85] eta: 0:04:38 time: 3.2737 data: 2.9975 max mem: 22448 +eval (validation): [13] [20/85] eta: 0:00:31 time: 0.3396 data: 0.0039 max mem: 22448 +eval (validation): [13] [40/85] eta: 0:00:18 time: 0.3373 data: 0.0040 max mem: 22448 +eval (validation): [13] [60/85] eta: 0:00:09 time: 0.3337 data: 0.0040 max mem: 22448 +eval (validation): [13] [80/85] eta: 0:00:01 time: 0.3203 data: 0.0039 max mem: 22448 +eval (validation): [13] [84/85] eta: 0:00:00 time: 0.3128 data: 0.0037 max mem: 22448 +eval (validation): [13] Total time: 0:00:31 (0.3692 s / it) +cv: [13] best hparam: (0.32, 1.0) (017) ('017_lr3.2e-01_wd1.0e+00') loss: 2.361 acc: 0.291 f1: 0.229 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [14] [ 0/400] eta: 0:23:39 lr: nan time: 3.5480 data: 3.2115 max mem: 22448 +train: [14] [ 20/400] eta: 0:03:52 lr: 0.000102 loss: 2.1135 (2.1191) grad: 0.2477 (0.2476) time: 0.4648 data: 0.0029 max mem: 22448 +train: [14] [ 40/400] eta: 0:03:10 lr: 0.000101 loss: 2.1235 (2.1339) grad: 0.2391 (0.2478) time: 0.4453 data: 0.0041 max mem: 22448 +train: [14] [ 60/400] eta: 0:02:50 lr: 0.000099 loss: 2.1467 (2.1418) grad: 0.2515 (0.2504) time: 0.4419 data: 0.0043 max mem: 22448 +train: [14] [ 80/400] eta: 0:02:34 lr: 0.000098 loss: 2.1589 (2.1500) grad: 0.2515 (0.2497) time: 0.4309 data: 0.0042 max mem: 22448 +train: [14] [100/400] eta: 0:02:22 lr: 0.000096 loss: 2.1615 (2.1570) grad: 0.2511 (0.2511) time: 0.4456 data: 0.0041 max mem: 22448 +train: [14] [120/400] eta: 0:02:11 lr: 0.000095 loss: 2.1312 (2.1547) grad: 0.2537 (0.2521) time: 0.4374 data: 0.0042 max mem: 22448 +train: [14] [140/400] eta: 0:02:00 lr: 0.000093 loss: 2.1256 (2.1533) grad: 0.2613 (0.2534) time: 0.4333 data: 0.0042 max mem: 22448 +train: [14] [160/400] eta: 0:01:50 lr: 0.000092 loss: 2.1181 (2.1511) grad: 0.2581 (0.2531) time: 0.4316 data: 0.0043 max mem: 22448 +train: [14] [180/400] eta: 0:01:40 lr: 0.000090 loss: 2.1149 (2.1486) grad: 0.2508 (0.2532) time: 0.4321 data: 0.0042 max mem: 22448 +train: [14] [200/400] eta: 0:01:31 lr: 0.000089 loss: 2.1215 (2.1498) grad: 0.2545 (0.2541) time: 0.4419 data: 0.0042 max mem: 22448 +train: [14] [220/400] eta: 0:01:21 lr: 0.000088 loss: 2.1616 (2.1518) grad: 0.2612 (0.2549) time: 0.4437 data: 0.0042 max mem: 22448 +train: [14] [240/400] eta: 0:01:12 lr: 0.000086 loss: 2.1740 (2.1557) grad: 0.2588 (0.2553) time: 0.4587 data: 0.0043 max mem: 22448 +train: [14] [260/400] eta: 0:01:03 lr: 0.000085 loss: 2.1817 (2.1577) grad: 0.2587 (0.2553) time: 0.4314 data: 0.0041 max mem: 22448 +train: [14] [280/400] eta: 0:00:54 lr: 0.000083 loss: 2.1603 (2.1578) grad: 0.2528 (0.2549) time: 0.4304 data: 0.0040 max mem: 22448 +train: [14] [300/400] eta: 0:00:45 lr: 0.000082 loss: 2.1929 (2.1620) grad: 0.2577 (0.2552) time: 0.4366 data: 0.0040 max mem: 22448 +train: [14] [320/400] eta: 0:00:35 lr: 0.000081 loss: 2.2091 (2.1637) grad: 0.2607 (0.2556) time: 0.4339 data: 0.0038 max mem: 22448 +train: [14] [340/400] eta: 0:00:26 lr: 0.000079 loss: 2.1941 (2.1635) grad: 0.2648 (0.2564) time: 0.4458 data: 0.0041 max mem: 22448 +train: [14] [360/400] eta: 0:00:17 lr: 0.000078 loss: 2.1615 (2.1640) grad: 0.2552 (0.2561) time: 0.4494 data: 0.0041 max mem: 22448 +train: [14] [380/400] eta: 0:00:08 lr: 0.000076 loss: 2.1615 (2.1633) grad: 0.2540 (0.2562) time: 0.4430 data: 0.0041 max mem: 22448 +train: [14] [399/400] eta: 0:00:00 lr: 0.000075 loss: 2.1685 (2.1636) grad: 0.2562 (0.2564) time: 0.4373 data: 0.0040 max mem: 22448 +train: [14] Total time: 0:02:59 (0.4489 s / it) +train: [14] Summary: lr: 0.000075 loss: 2.1685 (2.1636) grad: 0.2562 (0.2564) +eval (validation): [14] [ 0/85] eta: 0:04:36 time: 3.2530 data: 2.9827 max mem: 22448 +eval (validation): [14] [20/85] eta: 0:00:31 time: 0.3521 data: 0.0037 max mem: 22448 +eval (validation): [14] [40/85] eta: 0:00:18 time: 0.3322 data: 0.0040 max mem: 22448 +eval (validation): [14] [60/85] eta: 0:00:09 time: 0.3251 data: 0.0041 max mem: 22448 +eval (validation): [14] [80/85] eta: 0:00:01 time: 0.3341 data: 0.0041 max mem: 22448 +eval (validation): [14] [84/85] eta: 0:00:00 time: 0.3259 data: 0.0040 max mem: 22448 +eval (validation): [14] Total time: 0:00:31 (0.3724 s / it) +cv: [14] best hparam: (0.38, 1.0) (018) ('018_lr3.8e-01_wd1.0e+00') loss: 2.352 acc: 0.292 f1: 0.236 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [15] [ 0/400] eta: 0:23:13 lr: nan time: 3.4838 data: 3.0931 max mem: 22448 +train: [15] [ 20/400] eta: 0:03:53 lr: 0.000074 loss: 2.1194 (2.1122) grad: 0.2396 (0.2457) time: 0.4701 data: 0.0044 max mem: 22448 +train: [15] [ 40/400] eta: 0:03:10 lr: 0.000072 loss: 2.1194 (2.1104) grad: 0.2428 (0.2460) time: 0.4418 data: 0.0040 max mem: 22448 +train: [15] [ 60/400] eta: 0:02:51 lr: 0.000071 loss: 2.0734 (2.1092) grad: 0.2484 (0.2492) time: 0.4528 data: 0.0042 max mem: 22448 +train: [15] [ 80/400] eta: 0:02:35 lr: 0.000070 loss: 2.0734 (2.1036) grad: 0.2458 (0.2480) time: 0.4315 data: 0.0042 max mem: 22448 +train: [15] [100/400] eta: 0:02:23 lr: 0.000068 loss: 2.0504 (2.0980) grad: 0.2420 (0.2483) time: 0.4526 data: 0.0042 max mem: 22448 +train: [15] [120/400] eta: 0:02:12 lr: 0.000067 loss: 2.1069 (2.1034) grad: 0.2526 (0.2497) time: 0.4354 data: 0.0040 max mem: 22448 +train: [15] [140/400] eta: 0:02:01 lr: 0.000066 loss: 2.1161 (2.1116) grad: 0.2576 (0.2514) time: 0.4286 data: 0.0042 max mem: 22448 +train: [15] [160/400] eta: 0:01:51 lr: 0.000064 loss: 2.1037 (2.1108) grad: 0.2486 (0.2517) time: 0.4428 data: 0.0041 max mem: 22448 +train: [15] [180/400] eta: 0:01:41 lr: 0.000063 loss: 2.1071 (2.1189) grad: 0.2614 (0.2527) time: 0.4370 data: 0.0045 max mem: 22448 +train: [15] [200/400] eta: 0:01:31 lr: 0.000062 loss: 2.1544 (2.1186) grad: 0.2589 (0.2523) time: 0.4352 data: 0.0041 max mem: 22448 +train: [15] [220/400] eta: 0:01:22 lr: 0.000061 loss: 2.1300 (2.1171) grad: 0.2447 (0.2524) time: 0.4441 data: 0.0040 max mem: 22448 +train: [15] [240/400] eta: 0:01:12 lr: 0.000059 loss: 2.1163 (2.1170) grad: 0.2560 (0.2524) time: 0.4450 data: 0.0041 max mem: 22448 +train: [15] [260/400] eta: 0:01:03 lr: 0.000058 loss: 2.1522 (2.1223) grad: 0.2520 (0.2522) time: 0.4329 data: 0.0040 max mem: 22448 +train: [15] [280/400] eta: 0:00:54 lr: 0.000057 loss: 2.1492 (2.1203) grad: 0.2444 (0.2514) time: 0.4379 data: 0.0041 max mem: 22448 +train: [15] [300/400] eta: 0:00:45 lr: 0.000056 loss: 2.1055 (2.1200) grad: 0.2435 (0.2514) time: 0.4322 data: 0.0039 max mem: 22448 +train: [15] [320/400] eta: 0:00:36 lr: 0.000054 loss: 2.1130 (2.1209) grad: 0.2505 (0.2514) time: 0.4459 data: 0.0041 max mem: 22448 +train: [15] [340/400] eta: 0:00:27 lr: 0.000053 loss: 2.1281 (2.1220) grad: 0.2516 (0.2515) time: 0.4489 data: 0.0041 max mem: 22448 +train: [15] [360/400] eta: 0:00:18 lr: 0.000052 loss: 2.1277 (2.1227) grad: 0.2516 (0.2517) time: 0.4584 data: 0.0041 max mem: 22448 +train: [15] [380/400] eta: 0:00:09 lr: 0.000051 loss: 2.0814 (2.1200) grad: 0.2433 (0.2513) time: 0.4418 data: 0.0041 max mem: 22448 +train: [15] [399/400] eta: 0:00:00 lr: 0.000050 loss: 2.0788 (2.1204) grad: 0.2413 (0.2510) time: 0.4381 data: 0.0039 max mem: 22448 +train: [15] Total time: 0:03:00 (0.4506 s / it) +train: [15] Summary: lr: 0.000050 loss: 2.0788 (2.1204) grad: 0.2413 (0.2510) +eval (validation): [15] [ 0/85] eta: 0:04:36 time: 3.2563 data: 2.9794 max mem: 22448 +eval (validation): [15] [20/85] eta: 0:00:31 time: 0.3410 data: 0.0060 max mem: 22448 +eval (validation): [15] [40/85] eta: 0:00:18 time: 0.3422 data: 0.0038 max mem: 22448 +eval (validation): [15] [60/85] eta: 0:00:09 time: 0.3351 data: 0.0044 max mem: 22448 +eval (validation): [15] [80/85] eta: 0:00:01 time: 0.3260 data: 0.0040 max mem: 22448 +eval (validation): [15] [84/85] eta: 0:00:00 time: 0.3201 data: 0.0039 max mem: 22448 +eval (validation): [15] Total time: 0:00:31 (0.3722 s / it) +cv: [15] best hparam: (0.32, 1.0) (017) ('017_lr3.2e-01_wd1.0e+00') loss: 2.356 acc: 0.292 f1: 0.229 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [16] [ 0/400] eta: 0:22:26 lr: nan time: 3.3654 data: 2.9923 max mem: 22448 +train: [16] [ 20/400] eta: 0:03:46 lr: 0.000048 loss: 2.0654 (2.0869) grad: 0.2309 (0.2359) time: 0.4578 data: 0.0030 max mem: 22448 +train: [16] [ 40/400] eta: 0:03:09 lr: 0.000047 loss: 2.0654 (2.0750) grad: 0.2343 (0.2353) time: 0.4548 data: 0.0042 max mem: 22448 +train: [16] [ 60/400] eta: 0:02:50 lr: 0.000046 loss: 2.0612 (2.0722) grad: 0.2372 (0.2374) time: 0.4506 data: 0.0042 max mem: 22448 +train: [16] [ 80/400] eta: 0:02:34 lr: 0.000045 loss: 2.0865 (2.0848) grad: 0.2435 (0.2409) time: 0.4287 data: 0.0040 max mem: 22448 +train: [16] [100/400] eta: 0:02:23 lr: 0.000044 loss: 2.0865 (2.0820) grad: 0.2542 (0.2429) time: 0.4474 data: 0.0043 max mem: 22448 +train: [16] [120/400] eta: 0:02:11 lr: 0.000043 loss: 2.0312 (2.0800) grad: 0.2433 (0.2437) time: 0.4350 data: 0.0041 max mem: 22448 +train: [16] [140/400] eta: 0:02:00 lr: 0.000042 loss: 2.0404 (2.0802) grad: 0.2401 (0.2434) time: 0.4371 data: 0.0041 max mem: 22448 +train: [16] [160/400] eta: 0:01:50 lr: 0.000041 loss: 2.0896 (2.0871) grad: 0.2472 (0.2448) time: 0.4338 data: 0.0041 max mem: 22448 +train: [16] [180/400] eta: 0:01:40 lr: 0.000040 loss: 2.0860 (2.0875) grad: 0.2472 (0.2448) time: 0.4358 data: 0.0043 max mem: 22448 +train: [16] [200/400] eta: 0:01:31 lr: 0.000039 loss: 2.0638 (2.0834) grad: 0.2412 (0.2438) time: 0.4311 data: 0.0042 max mem: 22448 +train: [16] [220/400] eta: 0:01:21 lr: 0.000038 loss: 2.0638 (2.0862) grad: 0.2354 (0.2437) time: 0.4314 data: 0.0042 max mem: 22448 +train: [16] [240/400] eta: 0:01:12 lr: 0.000036 loss: 2.0781 (2.0864) grad: 0.2384 (0.2441) time: 0.4382 data: 0.0041 max mem: 22448 +train: [16] [260/400] eta: 0:01:03 lr: 0.000035 loss: 2.0704 (2.0901) grad: 0.2483 (0.2447) time: 0.4306 data: 0.0042 max mem: 22448 +train: [16] [280/400] eta: 0:00:53 lr: 0.000034 loss: 2.0926 (2.0899) grad: 0.2463 (0.2447) time: 0.4304 data: 0.0040 max mem: 22448 +train: [16] [300/400] eta: 0:00:44 lr: 0.000033 loss: 2.1114 (2.0927) grad: 0.2448 (0.2450) time: 0.4386 data: 0.0040 max mem: 22448 +train: [16] [320/400] eta: 0:00:35 lr: 0.000032 loss: 2.1316 (2.0961) grad: 0.2499 (0.2454) time: 0.4358 data: 0.0040 max mem: 22448 +train: [16] [340/400] eta: 0:00:26 lr: 0.000031 loss: 2.0805 (2.0953) grad: 0.2454 (0.2453) time: 0.4497 data: 0.0040 max mem: 22448 +train: [16] [360/400] eta: 0:00:17 lr: 0.000031 loss: 2.0702 (2.0949) grad: 0.2405 (0.2455) time: 0.4566 data: 0.0041 max mem: 22448 +train: [16] [380/400] eta: 0:00:08 lr: 0.000030 loss: 2.0931 (2.0947) grad: 0.2496 (0.2461) time: 0.4389 data: 0.0042 max mem: 22448 +train: [16] [399/400] eta: 0:00:00 lr: 0.000029 loss: 2.0779 (2.0945) grad: 0.2498 (0.2466) time: 0.4380 data: 0.0040 max mem: 22448 +train: [16] Total time: 0:02:59 (0.4477 s / it) +train: [16] Summary: lr: 0.000029 loss: 2.0779 (2.0945) grad: 0.2498 (0.2466) +eval (validation): [16] [ 0/85] eta: 0:04:28 time: 3.1633 data: 2.9319 max mem: 22448 +eval (validation): [16] [20/85] eta: 0:00:31 time: 0.3471 data: 0.0100 max mem: 22448 +eval (validation): [16] [40/85] eta: 0:00:18 time: 0.3342 data: 0.0038 max mem: 22448 +eval (validation): [16] [60/85] eta: 0:00:09 time: 0.3360 data: 0.0037 max mem: 22448 +eval (validation): [16] [80/85] eta: 0:00:01 time: 0.3294 data: 0.0039 max mem: 22448 +eval (validation): [16] [84/85] eta: 0:00:00 time: 0.3233 data: 0.0038 max mem: 22448 +eval (validation): [16] Total time: 0:00:31 (0.3725 s / it) +cv: [16] best hparam: (0.32, 1.0) (017) ('017_lr3.2e-01_wd1.0e+00') loss: 2.356 acc: 0.292 f1: 0.231 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [17] [ 0/400] eta: 0:22:06 lr: nan time: 3.3166 data: 2.9427 max mem: 22448 +train: [17] [ 20/400] eta: 0:03:34 lr: 0.000028 loss: 2.0476 (2.0370) grad: 0.2234 (0.2300) time: 0.4275 data: 0.0041 max mem: 22448 +train: [17] [ 40/400] eta: 0:03:03 lr: 0.000027 loss: 2.0476 (2.0619) grad: 0.2342 (0.2348) time: 0.4503 data: 0.0041 max mem: 22448 +train: [17] [ 60/400] eta: 0:02:45 lr: 0.000026 loss: 2.0643 (2.0713) grad: 0.2323 (0.2337) time: 0.4447 data: 0.0041 max mem: 22448 +train: [17] [ 80/400] eta: 0:02:32 lr: 0.000025 loss: 2.0444 (2.0568) grad: 0.2313 (0.2345) time: 0.4383 data: 0.0040 max mem: 22448 +train: [17] [100/400] eta: 0:02:20 lr: 0.000024 loss: 2.0320 (2.0584) grad: 0.2318 (0.2338) time: 0.4443 data: 0.0039 max mem: 22448 +train: [17] [120/400] eta: 0:02:10 lr: 0.000023 loss: 2.0608 (2.0596) grad: 0.2348 (0.2349) time: 0.4405 data: 0.0040 max mem: 22448 +train: [17] [140/400] eta: 0:01:59 lr: 0.000023 loss: 2.0613 (2.0578) grad: 0.2361 (0.2352) time: 0.4364 data: 0.0041 max mem: 22448 +train: [17] [160/400] eta: 0:01:49 lr: 0.000022 loss: 2.0671 (2.0584) grad: 0.2364 (0.2363) time: 0.4348 data: 0.0041 max mem: 22448 +train: [17] [180/400] eta: 0:01:40 lr: 0.000021 loss: 2.0671 (2.0568) grad: 0.2364 (0.2358) time: 0.4374 data: 0.0040 max mem: 22448 +train: [17] [200/400] eta: 0:01:30 lr: 0.000020 loss: 2.0429 (2.0560) grad: 0.2334 (0.2357) time: 0.4475 data: 0.0041 max mem: 22448 +train: [17] [220/400] eta: 0:01:21 lr: 0.000019 loss: 2.0642 (2.0575) grad: 0.2399 (0.2365) time: 0.4340 data: 0.0042 max mem: 22448 +train: [17] [240/400] eta: 0:01:12 lr: 0.000019 loss: 2.0642 (2.0562) grad: 0.2404 (0.2372) time: 0.4418 data: 0.0041 max mem: 22448 +train: [17] [260/400] eta: 0:01:03 lr: 0.000018 loss: 2.0370 (2.0556) grad: 0.2433 (0.2376) time: 0.4371 data: 0.0040 max mem: 22448 +train: [17] [280/400] eta: 0:00:53 lr: 0.000017 loss: 2.0741 (2.0573) grad: 0.2367 (0.2375) time: 0.4326 data: 0.0042 max mem: 22448 +train: [17] [300/400] eta: 0:00:44 lr: 0.000016 loss: 2.0917 (2.0588) grad: 0.2349 (0.2373) time: 0.4469 data: 0.0041 max mem: 22448 +train: [17] [320/400] eta: 0:00:35 lr: 0.000016 loss: 2.0557 (2.0581) grad: 0.2249 (0.2366) time: 0.4433 data: 0.0042 max mem: 22448 +train: [17] [340/400] eta: 0:00:26 lr: 0.000015 loss: 2.0382 (2.0579) grad: 0.2309 (0.2369) time: 0.4495 data: 0.0041 max mem: 22448 +train: [17] [360/400] eta: 0:00:17 lr: 0.000014 loss: 2.0801 (2.0593) grad: 0.2374 (0.2371) time: 0.4580 data: 0.0041 max mem: 22448 +train: [17] [380/400] eta: 0:00:08 lr: 0.000014 loss: 2.0667 (2.0588) grad: 0.2427 (0.2378) time: 0.4414 data: 0.0040 max mem: 22448 +train: [17] [399/400] eta: 0:00:00 lr: 0.000013 loss: 2.0357 (2.0570) grad: 0.2341 (0.2374) time: 0.4299 data: 0.0040 max mem: 22448 +train: [17] Total time: 0:02:59 (0.4483 s / it) +train: [17] Summary: lr: 0.000013 loss: 2.0357 (2.0570) grad: 0.2341 (0.2374) +eval (validation): [17] [ 0/85] eta: 0:04:35 time: 3.2366 data: 3.0086 max mem: 22448 +eval (validation): [17] [20/85] eta: 0:00:31 time: 0.3391 data: 0.0030 max mem: 22448 +eval (validation): [17] [40/85] eta: 0:00:18 time: 0.3441 data: 0.0040 max mem: 22448 +eval (validation): [17] [60/85] eta: 0:00:09 time: 0.3442 data: 0.0044 max mem: 22448 +eval (validation): [17] [80/85] eta: 0:00:01 time: 0.3264 data: 0.0042 max mem: 22448 +eval (validation): [17] [84/85] eta: 0:00:00 time: 0.3204 data: 0.0040 max mem: 22448 +eval (validation): [17] Total time: 0:00:31 (0.3746 s / it) +cv: [17] best hparam: (0.32, 1.0) (017) ('017_lr3.2e-01_wd1.0e+00') loss: 2.347 acc: 0.294 f1: 0.234 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [18] [ 0/400] eta: 0:22:27 lr: nan time: 3.3693 data: 3.0433 max mem: 22448 +train: [18] [ 20/400] eta: 0:03:37 lr: 0.000012 loss: 2.0621 (2.0806) grad: 0.2367 (0.2324) time: 0.4332 data: 0.0030 max mem: 22448 +train: [18] [ 40/400] eta: 0:03:05 lr: 0.000012 loss: 2.0586 (2.0421) grad: 0.2367 (0.2327) time: 0.4569 data: 0.0043 max mem: 22448 +train: [18] [ 60/400] eta: 0:02:47 lr: 0.000011 loss: 2.0086 (2.0395) grad: 0.2397 (0.2366) time: 0.4441 data: 0.0041 max mem: 22448 +train: [18] [ 80/400] eta: 0:02:32 lr: 0.000011 loss: 2.0269 (2.0402) grad: 0.2390 (0.2346) time: 0.4324 data: 0.0041 max mem: 22448 +train: [18] [100/400] eta: 0:02:20 lr: 0.000010 loss: 2.0509 (2.0426) grad: 0.2284 (0.2344) time: 0.4335 data: 0.0041 max mem: 22448 +train: [18] [120/400] eta: 0:02:09 lr: 0.000009 loss: 2.0302 (2.0374) grad: 0.2327 (0.2342) time: 0.4374 data: 0.0041 max mem: 22448 +train: [18] [140/400] eta: 0:01:59 lr: 0.000009 loss: 2.0222 (2.0403) grad: 0.2345 (0.2344) time: 0.4386 data: 0.0040 max mem: 22448 +train: [18] [160/400] eta: 0:01:49 lr: 0.000008 loss: 2.0300 (2.0410) grad: 0.2338 (0.2335) time: 0.4388 data: 0.0041 max mem: 22448 +train: [18] [180/400] eta: 0:01:40 lr: 0.000008 loss: 2.0248 (2.0395) grad: 0.2328 (0.2340) time: 0.4444 data: 0.0042 max mem: 22448 +train: [18] [200/400] eta: 0:01:30 lr: 0.000007 loss: 2.0248 (2.0386) grad: 0.2328 (0.2341) time: 0.4371 data: 0.0039 max mem: 22448 +train: [18] [220/400] eta: 0:01:21 lr: 0.000007 loss: 2.0492 (2.0411) grad: 0.2343 (0.2344) time: 0.4326 data: 0.0040 max mem: 22448 +train: [18] [240/400] eta: 0:01:12 lr: 0.000006 loss: 2.0797 (2.0454) grad: 0.2355 (0.2346) time: 0.4330 data: 0.0040 max mem: 22448 +train: [18] [260/400] eta: 0:01:02 lr: 0.000006 loss: 2.0714 (2.0453) grad: 0.2352 (0.2344) time: 0.4347 data: 0.0041 max mem: 22448 +train: [18] [280/400] eta: 0:00:53 lr: 0.000006 loss: 2.0575 (2.0457) grad: 0.2352 (0.2344) time: 0.4386 data: 0.0041 max mem: 22448 +train: [18] [300/400] eta: 0:00:44 lr: 0.000005 loss: 2.0575 (2.0444) grad: 0.2275 (0.2340) time: 0.4347 data: 0.0041 max mem: 22448 +train: [18] [320/400] eta: 0:00:35 lr: 0.000005 loss: 2.0423 (2.0473) grad: 0.2262 (0.2340) time: 0.4386 data: 0.0042 max mem: 22448 +train: [18] [340/400] eta: 0:00:26 lr: 0.000004 loss: 2.0360 (2.0444) grad: 0.2298 (0.2337) time: 0.4460 data: 0.0041 max mem: 22448 +train: [18] [360/400] eta: 0:00:17 lr: 0.000004 loss: 2.0151 (2.0441) grad: 0.2300 (0.2335) time: 0.4539 data: 0.0042 max mem: 22448 +train: [18] [380/400] eta: 0:00:08 lr: 0.000004 loss: 2.0245 (2.0435) grad: 0.2323 (0.2335) time: 0.4401 data: 0.0042 max mem: 22448 +train: [18] [399/400] eta: 0:00:00 lr: 0.000003 loss: 2.0376 (2.0423) grad: 0.2313 (0.2337) time: 0.4401 data: 0.0040 max mem: 22448 +train: [18] Total time: 0:02:58 (0.4471 s / it) +train: [18] Summary: lr: 0.000003 loss: 2.0376 (2.0423) grad: 0.2313 (0.2337) +eval (validation): [18] [ 0/85] eta: 0:04:34 time: 3.2260 data: 2.9870 max mem: 22448 +eval (validation): [18] [20/85] eta: 0:00:32 time: 0.3661 data: 0.0050 max mem: 22448 +eval (validation): [18] [40/85] eta: 0:00:19 time: 0.3390 data: 0.0033 max mem: 22448 +eval (validation): [18] [60/85] eta: 0:00:09 time: 0.3280 data: 0.0043 max mem: 22448 +eval (validation): [18] [80/85] eta: 0:00:01 time: 0.3180 data: 0.0041 max mem: 22448 +eval (validation): [18] [84/85] eta: 0:00:00 time: 0.3153 data: 0.0040 max mem: 22448 +eval (validation): [18] Total time: 0:00:31 (0.3737 s / it) +cv: [18] best hparam: (0.32, 1.0) (017) ('017_lr3.2e-01_wd1.0e+00') loss: 2.351 acc: 0.293 f1: 0.233 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [19] [ 0/400] eta: 0:22:06 lr: nan time: 3.3165 data: 2.9874 max mem: 22448 +train: [19] [ 20/400] eta: 0:03:38 lr: 0.000003 loss: 2.0199 (2.0295) grad: 0.2228 (0.2285) time: 0.4379 data: 0.0042 max mem: 22448 +train: [19] [ 40/400] eta: 0:03:05 lr: 0.000003 loss: 2.0199 (2.0153) grad: 0.2260 (0.2296) time: 0.4539 data: 0.0042 max mem: 22448 +train: [19] [ 60/400] eta: 0:02:48 lr: 0.000002 loss: 2.0227 (2.0317) grad: 0.2287 (0.2298) time: 0.4562 data: 0.0042 max mem: 22448 +train: [19] [ 80/400] eta: 0:02:34 lr: 0.000002 loss: 2.0592 (2.0373) grad: 0.2260 (0.2291) time: 0.4462 data: 0.0042 max mem: 22448 +train: [19] [100/400] eta: 0:02:22 lr: 0.000002 loss: 2.0492 (2.0365) grad: 0.2280 (0.2299) time: 0.4353 data: 0.0039 max mem: 22448 +train: [19] [120/400] eta: 0:02:11 lr: 0.000002 loss: 2.0243 (2.0380) grad: 0.2297 (0.2305) time: 0.4464 data: 0.0041 max mem: 22448 +train: [19] [140/400] eta: 0:02:00 lr: 0.000001 loss: 2.0275 (2.0392) grad: 0.2258 (0.2300) time: 0.4319 data: 0.0041 max mem: 22448 +train: [19] [160/400] eta: 0:01:50 lr: 0.000001 loss: 2.0220 (2.0351) grad: 0.2255 (0.2295) time: 0.4305 data: 0.0041 max mem: 22448 +train: [19] [180/400] eta: 0:01:40 lr: 0.000001 loss: 1.9941 (2.0321) grad: 0.2282 (0.2305) time: 0.4391 data: 0.0041 max mem: 22448 +train: [19] [200/400] eta: 0:01:31 lr: 0.000001 loss: 2.0067 (2.0310) grad: 0.2361 (0.2302) time: 0.4387 data: 0.0040 max mem: 22448 +train: [19] [220/400] eta: 0:01:21 lr: 0.000001 loss: 2.0277 (2.0301) grad: 0.2253 (0.2297) time: 0.4357 data: 0.0042 max mem: 22448 +train: [19] [240/400] eta: 0:01:12 lr: 0.000001 loss: 2.0205 (2.0292) grad: 0.2253 (0.2300) time: 0.4328 data: 0.0040 max mem: 22448 +train: [19] [260/400] eta: 0:01:03 lr: 0.000000 loss: 2.0061 (2.0283) grad: 0.2307 (0.2300) time: 0.4396 data: 0.0040 max mem: 22448 +train: [19] [280/400] eta: 0:00:53 lr: 0.000000 loss: 2.0327 (2.0304) grad: 0.2286 (0.2299) time: 0.4320 data: 0.0041 max mem: 22448 +train: [19] [300/400] eta: 0:00:44 lr: 0.000000 loss: 2.0470 (2.0306) grad: 0.2284 (0.2297) time: 0.4273 data: 0.0040 max mem: 22448 +train: [19] [320/400] eta: 0:00:35 lr: 0.000000 loss: 2.0442 (2.0332) grad: 0.2311 (0.2300) time: 0.4334 data: 0.0039 max mem: 22448 +train: [19] [340/400] eta: 0:00:26 lr: 0.000000 loss: 2.0603 (2.0348) grad: 0.2299 (0.2298) time: 0.4408 data: 0.0040 max mem: 22448 +train: [19] [360/400] eta: 0:00:17 lr: 0.000000 loss: 2.0603 (2.0354) grad: 0.2232 (0.2295) time: 0.4589 data: 0.0041 max mem: 22448 +train: [19] [380/400] eta: 0:00:08 lr: 0.000000 loss: 2.0195 (2.0359) grad: 0.2232 (0.2294) time: 0.4470 data: 0.0040 max mem: 22448 +train: [19] [399/400] eta: 0:00:00 lr: 0.000000 loss: 2.0313 (2.0382) grad: 0.2236 (0.2294) time: 0.4336 data: 0.0040 max mem: 22448 +train: [19] Total time: 0:02:58 (0.4474 s / it) +train: [19] Summary: lr: 0.000000 loss: 2.0313 (2.0382) grad: 0.2236 (0.2294) +eval (validation): [19] [ 0/85] eta: 0:04:30 time: 3.1819 data: 2.8966 max mem: 22448 +eval (validation): [19] [20/85] eta: 0:00:35 time: 0.4153 data: 0.0060 max mem: 22448 +eval (validation): [19] [40/85] eta: 0:00:20 time: 0.3435 data: 0.0038 max mem: 22448 +eval (validation): [19] [60/85] eta: 0:00:10 time: 0.3426 data: 0.0042 max mem: 22448 +eval (validation): [19] [80/85] eta: 0:00:01 time: 0.3406 data: 0.0040 max mem: 22448 +eval (validation): [19] [84/85] eta: 0:00:00 time: 0.3325 data: 0.0037 max mem: 22448 +eval (validation): [19] Total time: 0:00:33 (0.3949 s / it) +cv: [19] best hparam: (0.32, 1.0) (017) ('017_lr3.2e-01_wd1.0e+00') loss: 2.350 acc: 0.293 f1: 0.233 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +evaluating last checkpoint: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +eval model info: +{"score": 0.2929125138427464, "hparam": [0.32, 1.0], "hparam_id": 17, "epoch": 19, "is_best": false, "best_score": 0.29494278331487633} +eval (train): [20] [ 0/509] eta: 0:25:56 time: 3.0571 data: 2.8242 max mem: 22448 +eval (train): [20] [ 20/509] eta: 0:04:04 time: 0.3712 data: 0.0044 max mem: 22448 +eval (train): [20] [ 40/509] eta: 0:03:25 time: 0.3739 data: 0.0039 max mem: 22448 +eval (train): [20] [ 60/509] eta: 0:03:05 time: 0.3588 data: 0.0049 max mem: 22448 +eval (train): [20] [ 80/509] eta: 0:02:50 time: 0.3553 data: 0.0042 max mem: 22448 +eval (train): [20] [100/509] eta: 0:02:38 time: 0.3503 data: 0.0044 max mem: 22448 +eval (train): [20] [120/509] eta: 0:02:28 time: 0.3456 data: 0.0040 max mem: 22448 +eval (train): [20] [140/509] eta: 0:02:19 time: 0.3605 data: 0.0043 max mem: 22448 +eval (train): [20] [160/509] eta: 0:02:11 time: 0.3673 data: 0.0043 max mem: 22448 +eval (train): [20] [180/509] eta: 0:02:03 time: 0.3640 data: 0.0043 max mem: 22448 +eval (train): [20] [200/509] eta: 0:01:55 time: 0.3621 data: 0.0044 max mem: 22448 +eval (train): [20] [220/509] eta: 0:01:47 time: 0.3660 data: 0.0044 max mem: 22448 +eval (train): [20] [240/509] eta: 0:01:40 time: 0.3572 data: 0.0044 max mem: 22448 +eval (train): [20] [260/509] eta: 0:01:32 time: 0.3781 data: 0.0045 max mem: 22448 +eval (train): [20] [280/509] eta: 0:01:25 time: 0.3565 data: 0.0040 max mem: 22448 +eval (train): [20] [300/509] eta: 0:01:17 time: 0.3965 data: 0.0046 max mem: 22448 +eval (train): [20] [320/509] eta: 0:01:10 time: 0.3603 data: 0.0042 max mem: 22448 +eval (train): [20] [340/509] eta: 0:01:02 time: 0.3458 data: 0.0042 max mem: 22448 +eval (train): [20] [360/509] eta: 0:00:55 time: 0.3509 data: 0.0044 max mem: 22448 +eval (train): [20] [380/509] eta: 0:00:47 time: 0.3706 data: 0.0044 max mem: 22448 +eval (train): [20] [400/509] eta: 0:00:40 time: 0.3518 data: 0.0041 max mem: 22448 +eval (train): [20] [420/509] eta: 0:00:32 time: 0.3430 data: 0.0040 max mem: 22448 +eval (train): [20] [440/509] eta: 0:00:25 time: 0.3469 data: 0.0042 max mem: 22448 +eval (train): [20] [460/509] eta: 0:00:17 time: 0.3620 data: 0.0042 max mem: 22448 +eval (train): [20] [480/509] eta: 0:00:10 time: 0.3527 data: 0.0041 max mem: 22448 +eval (train): [20] [500/509] eta: 0:00:03 time: 0.3523 data: 0.0043 max mem: 22448 +eval (train): [20] [508/509] eta: 0:00:00 time: 0.3312 data: 0.0039 max mem: 22448 +eval (train): [20] Total time: 0:03:06 (0.3659 s / it) +eval (validation): [20] [ 0/85] eta: 0:04:19 time: 3.0547 data: 2.7674 max mem: 22448 +eval (validation): [20] [20/85] eta: 0:00:34 time: 0.4083 data: 0.0269 max mem: 22448 +eval (validation): [20] [40/85] eta: 0:00:20 time: 0.3823 data: 0.0043 max mem: 22448 +eval (validation): [20] [60/85] eta: 0:00:10 time: 0.3691 data: 0.0046 max mem: 22448 +eval (validation): [20] [80/85] eta: 0:00:02 time: 0.3449 data: 0.0042 max mem: 22448 +eval (validation): [20] [84/85] eta: 0:00:00 time: 0.3266 data: 0.0039 max mem: 22448 +eval (validation): [20] Total time: 0:00:34 (0.4078 s / it) +eval (test): [20] [ 0/85] eta: 0:04:22 time: 3.0931 data: 2.8517 max mem: 22448 +eval (test): [20] [20/85] eta: 0:00:30 time: 0.3396 data: 0.0032 max mem: 22448 +eval (test): [20] [40/85] eta: 0:00:18 time: 0.3709 data: 0.0044 max mem: 22448 +eval (test): [20] [60/85] eta: 0:00:10 time: 0.3796 data: 0.0045 max mem: 22448 +eval (test): [20] [80/85] eta: 0:00:01 time: 0.3270 data: 0.0039 max mem: 22448 +eval (test): [20] [84/85] eta: 0:00:00 time: 0.3151 data: 0.0039 max mem: 22448 +eval (test): [20] Total time: 0:00:32 (0.3855 s / it) +eval (testid): [20] [ 0/82] eta: 0:04:09 time: 3.0426 data: 2.7929 max mem: 22448 +eval (testid): [20] [20/82] eta: 0:00:30 time: 0.3696 data: 0.0048 max mem: 22448 +eval (testid): [20] [40/82] eta: 0:00:17 time: 0.3359 data: 0.0039 max mem: 22448 +eval (testid): [20] [60/82] eta: 0:00:08 time: 0.3830 data: 0.0042 max mem: 22448 +eval (testid): [20] [80/82] eta: 0:00:00 time: 0.3387 data: 0.0040 max mem: 22448 +eval (testid): [20] [81/82] eta: 0:00:00 time: 0.3285 data: 0.0036 max mem: 22448 +eval (testid): [20] Total time: 0:00:31 (0.3900 s / it) +evaluating best checkpoint: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/eval_v2/nsd_cococlip__patch__attn/checkpoint-best.pth +eval model info: +{"score": 0.29494278331487633, "hparam": [1.2, 1.0], "hparam_id": 25, "epoch": 5, "is_best": true, "best_score": 0.29494278331487633} +eval (train): [20] [ 0/509] eta: 0:27:22 time: 3.2270 data: 2.9205 max mem: 22448 +eval (train): [20] [ 20/509] eta: 0:04:08 time: 0.3723 data: 0.0097 max mem: 22448 +eval (train): [20] [ 40/509] eta: 0:03:19 time: 0.3365 data: 0.0044 max mem: 22448 +eval (train): [20] [ 60/509] eta: 0:03:01 time: 0.3651 data: 0.0026 max mem: 22448 +eval (train): [20] [ 80/509] eta: 0:02:48 time: 0.3509 data: 0.0041 max mem: 22448 +eval (train): [20] [100/509] eta: 0:02:37 time: 0.3590 data: 0.0043 max mem: 22448 +eval (train): [20] [120/509] eta: 0:02:27 time: 0.3563 data: 0.0043 max mem: 22448 +eval (train): [20] [140/509] eta: 0:02:18 time: 0.3416 data: 0.0042 max mem: 22448 +eval (train): [20] [160/509] eta: 0:02:11 time: 0.3796 data: 0.0047 max mem: 22448 +eval (train): [20] [180/509] eta: 0:02:03 time: 0.3771 data: 0.0044 max mem: 22448 +eval (train): [20] [200/509] eta: 0:01:55 time: 0.3715 data: 0.0042 max mem: 22448 +eval (train): [20] [220/509] eta: 0:01:47 time: 0.3521 data: 0.0039 max mem: 22448 +eval (train): [20] [240/509] eta: 0:01:39 time: 0.3517 data: 0.0041 max mem: 22448 +eval (train): [20] [260/509] eta: 0:01:32 time: 0.3590 data: 0.0042 max mem: 22448 +eval (train): [20] [280/509] eta: 0:01:24 time: 0.3460 data: 0.0042 max mem: 22448 +eval (train): [20] [300/509] eta: 0:01:17 time: 0.3674 data: 0.0043 max mem: 22448 +eval (train): [20] [320/509] eta: 0:01:09 time: 0.3742 data: 0.0042 max mem: 22448 +eval (train): [20] [340/509] eta: 0:01:02 time: 0.3917 data: 0.0043 max mem: 22448 +eval (train): [20] [360/509] eta: 0:00:55 time: 0.3719 data: 0.0042 max mem: 22448 +eval (train): [20] [380/509] eta: 0:00:47 time: 0.3706 data: 0.0040 max mem: 22448 +eval (train): [20] [400/509] eta: 0:00:40 time: 0.3377 data: 0.0038 max mem: 22448 +eval (train): [20] [420/509] eta: 0:00:32 time: 0.3368 data: 0.0038 max mem: 22448 +eval (train): [20] [440/509] eta: 0:00:25 time: 0.3465 data: 0.0039 max mem: 22448 +eval (train): [20] [460/509] eta: 0:00:17 time: 0.3683 data: 0.0042 max mem: 22448 +eval (train): [20] [480/509] eta: 0:00:10 time: 0.3675 data: 0.0042 max mem: 22448 +eval (train): [20] [500/509] eta: 0:00:03 time: 0.3506 data: 0.0040 max mem: 22448 +eval (train): [20] [508/509] eta: 0:00:00 time: 0.3360 data: 0.0038 max mem: 22448 +eval (train): [20] Total time: 0:03:06 (0.3660 s / it) +eval (validation): [20] [ 0/85] eta: 0:04:17 time: 3.0331 data: 2.7533 max mem: 22448 +eval (validation): [20] [20/85] eta: 0:00:32 time: 0.3743 data: 0.0041 max mem: 22448 +eval (validation): [20] [40/85] eta: 0:00:19 time: 0.3595 data: 0.0041 max mem: 22448 +eval (validation): [20] [60/85] eta: 0:00:10 time: 0.3760 data: 0.0038 max mem: 22448 +eval (validation): [20] [80/85] eta: 0:00:01 time: 0.3381 data: 0.0040 max mem: 22448 +eval (validation): [20] [84/85] eta: 0:00:00 time: 0.3315 data: 0.0039 max mem: 22448 +eval (validation): [20] Total time: 0:00:33 (0.3939 s / it) +eval (test): [20] [ 0/85] eta: 0:04:17 time: 3.0286 data: 2.7594 max mem: 22448 +eval (test): [20] [20/85] eta: 0:00:32 time: 0.3745 data: 0.0043 max mem: 22448 +eval (test): [20] [40/85] eta: 0:00:19 time: 0.3467 data: 0.0032 max mem: 22448 +eval (test): [20] [60/85] eta: 0:00:09 time: 0.3312 data: 0.0037 max mem: 22448 +eval (test): [20] [80/85] eta: 0:00:01 time: 0.3228 data: 0.0038 max mem: 22448 +eval (test): [20] [84/85] eta: 0:00:00 time: 0.3112 data: 0.0036 max mem: 22448 +eval (test): [20] Total time: 0:00:31 (0.3746 s / it) +eval (testid): [20] [ 0/82] eta: 0:03:43 time: 2.7220 data: 2.4539 max mem: 22448 +eval (testid): [20] [20/82] eta: 0:00:28 time: 0.3470 data: 0.0040 max mem: 22448 +eval (testid): [20] [40/82] eta: 0:00:16 time: 0.3325 data: 0.0034 max mem: 22448 +eval (testid): [20] [60/82] eta: 0:00:08 time: 0.3266 data: 0.0036 max mem: 22448 +eval (testid): [20] [80/82] eta: 0:00:00 time: 0.3239 data: 0.0035 max mem: 22448 +eval (testid): [20] [81/82] eta: 0:00:00 time: 0.3120 data: 0.0034 max mem: 22448 +eval (testid): [20] Total time: 0:00:29 (0.3622 s / it) +eval results: + +| model | repr | clf | dataset | ckpt | epoch | lr | wd | hparam_id | hparam | split | loss | acc | acc_std | f1 | f1_std | +|:---------|:-------|:------|:-------------|:-------|--------:|--------:|-----:|------------:|:-----------|:-----------|-------:|--------:|----------:|--------:|----------:| +| flat_mae | patch | attn | nsd_cococlip | best | 5 | 0.00036 | 0.05 | 25 | [1.2, 1.0] | train | 2.0834 | 0.36879 | 0.0023942 | 0.3057 | 0.0025342 | +| flat_mae | patch | attn | nsd_cococlip | best | 5 | 0.00036 | 0.05 | 25 | [1.2, 1.0] | validation | 2.336 | 0.29494 | 0.005419 | 0.22339 | 0.0051702 | +| flat_mae | patch | attn | nsd_cococlip | best | 5 | 0.00036 | 0.05 | 25 | [1.2, 1.0] | test | 2.278 | 0.2987 | 0.0053079 | 0.23024 | 0.0052873 | +| flat_mae | patch | attn | nsd_cococlip | best | 5 | 0.00036 | 0.05 | 25 | [1.2, 1.0] | testid | 2.2847 | 0.30461 | 0.0055127 | 0.2401 | 0.0055217 | + + +done! total time: 1:22:24 diff --git a/input_space_v3/flat_lr1e-3_4/eval_v2/nsd_cococlip__patch__attn/train_log.json b/input_space_v3/flat_lr1e-3_4/eval_v2/nsd_cococlip__patch__attn/train_log.json new file mode 100644 index 0000000000000000000000000000000000000000..93e08b1691944b09582691a71306aac2918351db --- /dev/null +++ b/input_space_v3/flat_lr1e-3_4/eval_v2/nsd_cococlip__patch__attn/train_log.json @@ -0,0 +1,20 @@ +{"epoch": 0, "train/lr": 2.987987987987988e-05, "train/loss": 3.1331557726860044, "train/grad": 0.16073589641600847, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.1767138671875, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.17594482421875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.174693603515625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.17349609375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.17241943359375, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.1709765625, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.169422607421875, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.16780029296875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.16591064453125, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.164078369140625, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.16232421875, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.16014892578125, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.158380126953125, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.156016845703125, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.15425048828125, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.152833251953125, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.15122314453125, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.149671630859375, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.148270263671875, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.1472021484375, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.14609130859375, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.14496337890625, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.14411865234375, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.143309326171875, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.142657470703125, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.142147216796875, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.141954345703125, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.141812744140625, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.1418115234375, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.141966552734375, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.14224853515625, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.1426416015625, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.14305908203125, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.143487548828125, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.14415771484375, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.14477294921875, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.145789794921875, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.1469110107421874, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.1475421142578126, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.1423785400390627, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.129294128417969, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.1136669921875, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.0876722717285157, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.0625128173828124, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.038560791015625, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.0188778686523436, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.9991335678100586, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.9808295440673827, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.9684891510009765, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.024109268854372205, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.024046292887069286, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.023943262258544564, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.023846687693148853, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.023753686444833874, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.02363038337789476, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.02349941022694111, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.023363741217181086, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.023199419039301575, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.02304144362453371, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.02290062533225864, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.022718110657297074, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.02256563681177795, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.02238100930582732, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.022239416101947428, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.02212596966419369, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.02200977860484272, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.021901252982206642, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.02180680482182652, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.0217353587038815, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.021666858871467413, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.021611304357647895, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.02156512418296188, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.021527774431742728, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.021502640298567712, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.02148364291526377, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.021479520392604173, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.021477995347231625, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.021484858896583317, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.021496098153293133, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.021499110478907825, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.021493133855983615, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.021462596445344387, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.02141521544661373, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.02132878564763814, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.021210647402331233, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.02105514459311962, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0208972773142159, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.020752719324082135, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.020849460340104996, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0213300023926422, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.022053782674483956, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.02301845750771463, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.023780140331946312, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.024747846042737366, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.026119834445416927, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.027175617907196283, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.028487869556993246, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.02951063323765993, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1631224155426025, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1609315872192383, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1574864387512207, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1543357372283936, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1514813899993896, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1478586196899414, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.144273042678833, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1407835483551025, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.136997699737549, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1338024139404297, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.131333112716675, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.128612518310547, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1268038749694824, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1252336502075195, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1244235038757324, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.123997211456299, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.123788833618164, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1237409114837646, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1238598823547363, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.124113082885742, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.1245932579040527, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.1253626346588135, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.1265811920166016, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.1281275749206543, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.129892587661743, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.1320879459381104, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.1338095664978027, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.135037422180176, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.1359400749206543, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.1351513862609863, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.133298873901367, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.131326198577881, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.128973960876465, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.1272172927856445, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.1262753009796143, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.127317190170288, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.1291444301605225, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.1262457370758057, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.0960733890533447, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.935523509979248, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.7887156009674072, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.7174673080444336, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.6679656505584717, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.6434144973754883, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.6112115383148193, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.600707769393921, "validation/loss_046_lr3.6e+01_wd1.0e+00": 2.6053147315979004, "validation/loss_047_lr4.3e+01_wd1.0e+00": 2.6668286323547363, "validation/loss_048_lr5.0e+01_wd1.0e+00": 2.686548948287964, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.05167958656330749, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.054078995939461055, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.05795496493170912, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.059431524547803614, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.059616094499815434, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06109265411590993, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.059616094499815434, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.059431524547803614, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.060723514211886306, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06201550387596899, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06275378368401624, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06423034330011074, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06275378368401624, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06164636397194537, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06478405315614617, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06570690291620525, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06607604282022887, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06755260243632337, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.06902916205241787, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.06902916205241787, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.06718346253229975, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.05906238464377999, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.05629383536360281, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.053156146179401995, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.051125876707272054, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.05094130675526024, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.05094130675526024, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.05094130675526024, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.05352528608342562, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.05740125507567368, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.0681063122923588, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.07419712070874862, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.07493540051679587, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.07622739018087855, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.07475083056478406, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.07198228128460686, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.06847545219638243, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.07954964931709117, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.13270579549649317, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.1773717238833518, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.19952011812476927, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.20284237726098192, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.20948689553340716, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.23163528977482467, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.23791066814322628, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.2336655592469546, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.2070874861572536, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.21040974529346623, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.017702261736841456, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.019043493802764305, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.020031565509834724, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.019111003743844213, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.017663734238429304, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.016632086264854625, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.01460611995588173, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.012658702679545138, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.011122177997432868, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.010537114993017705, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.010295372249693426, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.011243298722086908, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.011685050003861464, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.012150200738871809, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.012811058263037247, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.012810059667290886, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.012455750148693422, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.01189279493097808, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.0114817097202701, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.011375381548184705, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.01213164013904968, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.01316477947164508, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.013050605421612854, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.011757123825017287, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.008263114455780027, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.004487056255203828, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.004043600562587904, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.004045022863172705, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.004051435617403559, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.007226474886464639, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.008720866780528936, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.010345144278277369, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.013274790747634874, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.015578472625486164, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.021172416093743426, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.01992215262399787, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.017188731909719698, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.0135195050429234, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.02311054716262784, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.06219469152779489, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.09356179205785294, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.11440752697936384, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.12509652221619605, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.13348894724620947, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.16180281628965834, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.16743231481022677, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.16042343519562333, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.13995026157252646, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.13779700700568429, "id_best": 45, "lr_best": 0.0093, "wd_best": 0.05, "train/loss_best": 3.0188778686523436, "validation/loss_best": 2.600707769393921, "validation/acc_best": 0.23791066814322628, "validation/f1_best": 0.16743231481022677} +{"epoch": 1, "train/lr": 8.993993993993998e-05, "train/loss": 2.971511117219925, "train/grad": 0.18727656036615373, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.15062744140625, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.14807373046875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.1444970703125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.141708984375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.1394189453125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.13697021484375, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.13486328125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.13321533203125, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.131727294921875, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.1307080078125, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.130018310546875, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.129517822265625, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.129197998046875, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.129014892578125, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.128963623046875, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.128919677734375, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.1289794921875, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.128890380859375, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.128790283203125, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.12873779296875, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.128631591796875, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.1285791015625, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.1283544921875, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.1282470703125, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.128240966796875, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.128150634765625, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.1281982421875, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.128201904296875, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.127801513671875, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.1231317138671875, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.1017684936523438, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.06220703125, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.999122543334961, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.9422293090820313, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.871519966125488, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.8025927734375, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.737989387512207, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.686920471191406, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.6389088249206543, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.5960469818115235, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.5728342580795287, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.5579395627975465, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.536492791175842, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.5276565885543825, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.5372818183898924, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.5599534797668455, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.5915394616127014, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.6409439754486086, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.6797219383716584, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.02165701661258936, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.02143038821872324, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.021115882615558804, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.0208669747505337, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.02067071553785354, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.02046440615784377, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.020299260108731686, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.02017464654520154, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.020075576403178273, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.02001765443943441, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.019989463267847896, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.019977890169247985, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.019984532706439496, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.02000900556333363, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.02003786276560277, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.020067071453668178, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.020101084313355385, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.020139837446622552, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.02017959368880838, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.02021367081440985, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.02024985456839204, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.020280421515926718, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.02030097278300673, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.020300407293252647, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.020265279891900717, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.020172341223806144, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.020046557136811315, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.01989657983649522, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.01964818113017827, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.019393680142238735, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.019603016320616007, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.02027471947018057, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.021502429810352622, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.022683992735110223, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.024146654196083545, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.025635051373392344, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.027166013377718626, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.02877919951453805, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.030814626491628586, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.033026870032772424, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.03421802907250822, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.03599300122819841, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.03736906387843192, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.03821837383322418, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.03951177115552127, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.04100345281884074, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.04416482599452138, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.04852386855520308, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.051326480861753225, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.135509967803955, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.132897138595581, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1297779083251953, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.127732038497925, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1264047622680664, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1253089904785156, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1247076988220215, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1244308948516846, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1243197917938232, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.124316453933716, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.124316453933716, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.124290943145752, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.12416410446167, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.123919725418091, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1235969066619873, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1232926845550537, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.122924327850342, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1227171421051025, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.122751235961914, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.1230432987213135, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.123706817626953, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.1247711181640625, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.126465320587158, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.1292035579681396, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.1330230236053467, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.138291120529175, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.14227032661438, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.144144058227539, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.139003276824951, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.0730061531066895, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.8785297870635986, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.735189199447632, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.6268999576568604, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.586102247238159, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.5624406337738037, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.5318949222564697, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.4819953441619873, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.442548990249634, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.4580795764923096, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.4440512657165527, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.4775750637054443, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.5206146240234375, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.5181667804718018, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.586754560470581, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.665191173553467, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.7567739486694336, "validation/loss_046_lr3.6e+01_wd1.0e+00": 2.831887722015381, "validation/loss_047_lr4.3e+01_wd1.0e+00": 2.9360687732696533, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.106316566467285, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06459948320413436, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06275378368401624, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06459948320413436, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06441491325212255, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06441491325212255, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06496862310815799, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06533776301218161, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06681432262827612, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06589147286821706, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.0664451827242525, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.0651531930601698, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.06589147286821706, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.06718346253229975, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.06699889258028793, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.06718346253229975, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.06607604282022887, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.06626061277224068, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.07069029162052418, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.07308970099667775, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.07290513104466592, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.07733480989294943, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.10225175341454411, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.14599483204134367, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.17995570321151716, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.20671834625322996, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.2174234034699151, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.22277593207825766, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.23163528977482467, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.24713916574381692, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.2591362126245847, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.2574750830564784, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.2617201919527501, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.24603174603174602, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.23329641934293097, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.24658545588778147, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.23588039867109634, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.2146548541897379, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.21668512366186785, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.2024732373569583, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.18032484311554078, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.16925064599483206, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.01146506116059714, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.010382987338221294, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.00900237972596641, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.009153294472538554, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.008703032870139814, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.008549244063329289, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.008361076991513434, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.00804426853909642, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.007827899111308939, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.007840209585793635, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.007688157903284303, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.00834432616484025, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.009622167071309534, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.010584936191652695, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.011281048405496373, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.012220045072147176, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.011930732584392083, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.013078127168527498, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.012941524913211303, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.014148091582299502, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.015041916786987816, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.015156201484506623, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.014563542006853948, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.011938352204187699, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.012269319740110814, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.014249220988351421, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.015805455016938166, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.016865059039037098, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.02043951805599725, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.03867669361642193, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.06693885563368157, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.09690664735171477, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.12819636755265307, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.1453061924103426, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.15621403045005441, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.16008222901361005, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.17939291547875225, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.1937663732729592, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.19380365640091268, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.19719133622713278, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.17882184373763088, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.17375576318232203, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.18342370564063573, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.1767875190582556, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.1596634356977569, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.14991747824721122, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.13306626628250237, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.09854452899474475, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.09744643693332744, "id_best": 39, "lr_best": 0.0036, "wd_best": 0.05, "train/loss_best": 2.5960469818115235, "validation/loss_best": 2.4440512657165527, "validation/acc_best": 0.2617201919527501, "validation/f1_best": 0.19719133622713278} +{"epoch": 2, "train/lr": 0.00014999999999999988, "train/loss": 2.9575859725475313, "train/grad": 0.37258580811321734, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.13639892578125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.135169677734375, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.133961181640625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.13334716796875, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.13308837890625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.13291015625, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.13283935546875, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.1327294921875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.132623291015625, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.132470703125, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.132432861328125, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.132135009765625, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.131956787109375, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.131517333984375, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.131246337890625, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.1308984375, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.130418701171875, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.1300341796875, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.129554443359375, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.12916259765625, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.12864501953125, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.127945556640625, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.126849365234375, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.12423095703125, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.113297119140625, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.059550018310547, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.9767276000976564, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.8927548217773436, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.7812859344482423, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.66083984375, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.5756718826293947, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.520199346542358, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.4620949172973634, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.4246676635742186, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.3903184032440183, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.3675330209732057, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.3546434020996094, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.3527959871292112, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.354464633464813, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.37602490901947, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.3837428998947146, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.4057626342773437, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.427173937559128, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.4417456936836244, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.508769929409027, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.5929704082012175, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.7119383692741392, "train/loss_047_lr4.3e+01_wd1.0e+00": 5.0545593976974486, "train/loss_048_lr5.0e+01_wd1.0e+00": 5.579617927074432, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.020333631597459316, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.020235267607495187, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.02014997280202806, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.02011924030724913, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.020113268089480697, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.02012223655823618, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.020141148706898093, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.02016293699387461, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.020188650111667813, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.02021216440014541, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.020232018996030093, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.020257957591675223, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.0202810339583084, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.020310502806678413, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.020333763537928463, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.02034956100862473, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.02036361045204103, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.02036902844440192, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.020354415168985725, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.020320321721956133, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.02024646880570799, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.02013142602518201, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0199545996170491, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.019718991620466114, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.019625934823416173, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.02058212399482727, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.02227885528933257, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.02367962433490902, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.02573575926013291, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.028050292506814, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.02968275628052652, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.030686883898451926, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.031706024575978514, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.032885885667055845, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0341618699580431, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.03537272859364748, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.036792653053998946, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.03807871289551258, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.03869416139088571, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.03979578956961632, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.04106371627189219, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0425188557524234, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.045931175891309975, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0466175907664001, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.050135757979005574, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.05519524162635207, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0642201853170991, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.12351958798244596, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.11443733349442482, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1255133152008057, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1249661445617676, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1245923042297363, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.124485492706299, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.124497413635254, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1245646476745605, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1246156692504883, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.124690055847168, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.124844551086426, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1250431537628174, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1252613067626953, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.125688076019287, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1261563301086426, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1267828941345215, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.127271890640259, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.127559185028076, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1275479793548584, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.126927137374878, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1255617141723633, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.123701810836792, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.120859146118164, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.117345094680786, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.1118428707122803, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.0961570739746094, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.004561185836792, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.731842517852783, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.625744104385376, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.5624303817749023, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.496724843978882, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.451507568359375, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.425306797027588, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.4115025997161865, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.405155658721924, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.4411890506744385, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.438955783843994, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.431401252746582, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.4596211910247803, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.4821393489837646, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.483393907546997, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.5338246822357178, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.5528652667999268, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.5745184421539307, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.6318368911743164, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.605436325073242, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.6500213146209717, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.8789443969726562, "validation/loss_046_lr3.6e+01_wd1.0e+00": 2.985464334487915, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06275378368401624, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.062200073827980804, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06183093392395718, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06201550387596899, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.062384643779992616, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.062384643779992616, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.0636766334440753, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.0651531930601698, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06552233296419344, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.0651531930601698, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06404577334809892, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06423034330011074, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06386120339608711, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06404577334809892, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06459948320413436, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.06441491325212255, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.06478405315614617, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.0664451827242525, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.0710594315245478, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.07918050941306755, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.11314138058324105, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.19010705057216684, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.2159468438538206, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.2353266888150609, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.25341454411221853, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.2631967515688446, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.26559616094499816, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.27002583979328165, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.2766703580657069, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.26707272056109266, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.26854928017718716, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.26411960132890366, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.2587670727205611, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.2517534145441122, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.24880029531192321, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.23864894795127353, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.23163528977482467, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.22997416020671835, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.22739018087855298, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.23440383905500184, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.23938722775932078, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.21059431524547803, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.19933554817275748, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.008892619689614497, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.009275281563041487, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.009612418514554685, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.009755618834444651, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.009698659609264146, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.009944456645931184, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.010074489743835468, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.009939668082932188, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.009630560673132456, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.010547795918889038, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.010961608010724808, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.011975472983646292, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.011808336625991777, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.01059851167737739, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.009841626022192277, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.00963056150001581, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.008741164187899898, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.00852160742596955, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.009121751674728942, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.008971535703694302, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.008341411859800462, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.009422307727579338, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.013244571784277447, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.017069830214164736, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.04085163216084641, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.09958060026409826, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.13243135436686718, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.15603455610714864, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.17570625506641302, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.18874164399657414, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.1890696976227638, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.196497498342722, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.20798653334578643, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.19950989477104272, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.19865370388720485, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.1927414358990859, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.1970795639920999, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.18880574334749264, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.18651394705653024, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.18132500099875506, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.17216087927938242, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.16039090388801366, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.17431619356389336, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.17085955459923344, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.15520049450298593, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.1558330756606511, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.15032594768657861, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 32, "lr_best": 0.0011099999999999999, "wd_best": 0.05, "train/loss_best": 2.4620949172973634, "validation/loss_best": 2.405155658721924, "validation/acc_best": 0.2766703580657069, "validation/f1_best": 0.20798653334578643} +{"epoch": 3, "train/lr": 0.0002100600600600602, "train/loss": 2.943050329685211, "train/grad": 0.49056767754256725, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.1307666015625, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.130482177734375, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.1301708984375, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.12990478515625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.12970458984375, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.129493408203125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.129150390625, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.128916015625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.128529052734375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.128189697265625, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.127666015625, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.127130126953125, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.126632080078125, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.12576171875, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.125076904296875, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.12440185546875, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.123385009765625, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.1222705078125, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.120552978515625, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.118087158203125, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.1098333740234376, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.0698760986328124, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.9626060485839845, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.826108627319336, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.692547416687012, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.5745144653320313, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.5112493515014647, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.4624926090240478, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.4059659671783447, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.3581589317321776, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.327420711517334, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.3041976833343507, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.277481155395508, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.2571310567855836, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.2446226477622986, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.239819657802582, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.2441691851615904, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.2501338815689085, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.2817941224575042, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.3400258731842043, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.388381608724594, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.436196492910385, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.483236985206604, "train/loss_043_lr2.2e+01_wd1.0e+00": 4.775084663629531, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.773939731121063, "train/loss_045_lr3.1e+01_wd1.0e+00": 6.028634197711945, "train/loss_046_lr3.6e+01_wd1.0e+00": 4.703825263977051, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.020025385669432582, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.020035727089270948, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.0200577062740922, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.02007663560565561, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.020092278928495945, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.0201101447455585, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.020128468670882284, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.02014523801859468, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.020165363904088737, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.02018135585822165, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.020194849465042353, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.020210348786786198, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.020217719408683478, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.020216576089151204, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.020201928368769585, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.020174651299603285, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.020124453078024088, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.02003504494205117, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.01989382375497371, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.019723516311496495, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.019551637792028488, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.020185596663504838, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.02223426030948758, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.025012607933022082, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.027715642852708697, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.02965876866132021, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.030528747271746398, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.03143505255691707, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.032826618095859884, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.03411318484693766, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.03501574457623065, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.035776127343997356, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.03714702744036913, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.03851563121192157, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.040020904233679176, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.04105593735352159, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.042827769443392755, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.04322772974148393, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.04424742555245757, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.04573121992871165, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.04861639661714435, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.050841145608574154, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.055380343776196245, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.16493298748508095, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.07675909670069814, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.1608469824306667, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.08333817806094884, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.124371290206909, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1243133544921875, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.124223232269287, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.124037504196167, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.123866558074951, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1235761642456055, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.123203754425049, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.122805595397949, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1222646236419678, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1217093467712402, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.121229648590088, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1205976009368896, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1200807094573975, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1196064949035645, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.119450330734253, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1195030212402344, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.119699478149414, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1197667121887207, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1184139251708984, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.112367868423462, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.0653247833251953, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.8696117401123047, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.682831048965454, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.5939135551452637, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.530442476272583, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.4742624759674072, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.4547224044799805, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.451179265975952, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.439694881439209, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.409815549850464, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.3993916511535645, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.392503261566162, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.4099860191345215, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.4430620670318604, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.4929733276367188, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.5078506469726562, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.580177068710327, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.6309447288513184, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.625155448913574, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.658489465713501, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.6811413764953613, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.6840548515319824, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.747469425201416, "validation/loss_043_lr2.2e+01_wd1.0e+00": 58.21435546875, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.934278726577759, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06275378368401624, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06275378368401624, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06423034330011074, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06404577334809892, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06441491325212255, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06607604282022887, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06847545219638243, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.07161314138058324, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.07124400147655961, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.07050572166851236, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.07198228128460686, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.07087486157253599, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06995201181247693, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.07013658176448874, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.09523809523809523, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.14839424141749724, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.19121447028423771, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.21963824289405684, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.23255813953488372, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.25249169435215946, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.2558139534883721, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.2576596530084902, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.2596899224806202, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.2779623477297896, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.27999261720191954, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.2807308970099668, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.2763012181616833, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.2742709486895533, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.2705795496493171, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.2606127722406792, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.23994093761535623, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.23901808785529716, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.23477297895902546, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.23735695828719083, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.2248062015503876, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.21797711332595054, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.22609819121447028, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.027500922849760058, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.21539313399778517, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.011239735750938321, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.011187605596988455, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.011107828839747445, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.011265408865226352, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.010953308925535648, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.010087947699205345, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.009999036629548133, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.010142559799812552, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.010053118047611168, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.009891316168562004, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.010481476788108091, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.011873293868505367, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.0137207425164827, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.014655175327624304, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.0142657117672034, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.014602454273500811, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.01625475785905975, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.01666574305571017, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.017134345196004527, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.018732699781162043, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.04309775153264242, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.07714970606793714, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.11470523879104914, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.14333344473971782, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.15863678021077673, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.18191938162953347, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.18955393248109817, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.19628325646347186, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.19835919996198834, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.20918148269723913, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.20721891324489547, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.20804983003948316, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.19765620330200362, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.20121963293960687, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.19484744059284523, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.18647947542322652, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.18106070653212547, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.18481759693687785, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.19203241625146064, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.17457367912060326, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.17218143969701302, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.16011110219758048, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.169950038628316, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.006097978069929271, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.15516476763095727, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 31, "lr_best": 0.0009299999999999999, "wd_best": 0.05, "train/loss_best": 2.3041976833343507, "validation/loss_best": 2.392503261566162, "validation/acc_best": 0.2807308970099668, "validation/f1_best": 0.20804983003948316} +{"epoch": 4, "train/lr": 0.0002701201201201201, "train/loss": 2.8109676837921143, "train/grad": 0.3229973694682121, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.1330029296875, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.132850341796875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.132484130859375, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.13220703125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.131822509765625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.1312939453125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.13084716796875, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.130325927734375, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.129598388671875, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.12889404296875, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.12817626953125, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.127144775390625, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.126204833984375, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.12483642578125, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.12341796875, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.121873779296875, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.11917724609375, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.11093505859375, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.063753662109375, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.952958831787109, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.7923056793212893, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.6488775634765624, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.554070472717285, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.483408126831055, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.4236855125427246, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.3664369583129883, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.3254868507385256, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.292561206817627, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.2530597448349, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.219078903198242, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.198088502883911, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.1853202867507933, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.16830632686615, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.1599085092544557, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.164692248106003, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.1739150893688204, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.1941706240177155, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.2237854850292207, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.2850217378139495, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.3627779614925384, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.4415267026424408, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.5087118434906004, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.6207238936424258, "train/loss_043_lr2.2e+01_wd1.0e+00": 4.324893550872803, "train/loss_044_lr2.6e+01_wd1.0e+00": 4.3673000752925875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.019847956150770188, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.019859325005672872, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.019874326796270908, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.01988468221388757, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.019895312297157942, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.019905629605054855, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.019915838977321982, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.01992675388697535, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.01994020022917539, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.0199473716923967, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.019949833056889476, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.019944355846382676, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.0199227399751544, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.019867970300838353, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.019785625236108897, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.019682103786617517, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.01951702104881406, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.019338079411536455, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.019961248743347825, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.021977979303337634, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.025248899017460646, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.027949228482320905, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.029591033291071652, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.030613985499367117, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.031747757429257034, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.03290511282160878, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.03384595680981874, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.034806332923471926, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.03571275999769569, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0364616350736469, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.03703513005748391, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.037550337919965385, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.03894747525453567, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.040987221132963894, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.04267458813264966, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0442171673104167, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.04582959828898311, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.04748464284464717, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.049631846882402894, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.052043740991503, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.05782040446996689, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.061044411342591046, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0697320730984211, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.03800898849964142, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.12974188638851047, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.125135898590088, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.125180244445801, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.125253677368164, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.125291585922241, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.125257730484009, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1251606941223145, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1249747276306152, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.124681234359741, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.124173879623413, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.123488187789917, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1228060722351074, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.121680974960327, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.120767831802368, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.119687080383301, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1188714504241943, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1179449558258057, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.114009380340576, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.082958459854126, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.8871238231658936, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.6968796253204346, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.6047191619873047, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.550147771835327, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.4935367107391357, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.4328362941741943, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.4092185497283936, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.404998302459717, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.416935920715332, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.427584409713745, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.450124740600586, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.44160795211792, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.452580213546753, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.467531442642212, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.5331273078918457, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.551429033279419, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.5405805110931396, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.5592052936553955, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.559356212615967, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.6088411808013916, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.684624433517456, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.623934030532837, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.82122802734375, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.026067018508911, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.844160318374634, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06293835363602805, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.062384643779992616, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.062200073827980804, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06183093392395718, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06256921373200443, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.0636766334440753, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06441491325212255, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06478405315614617, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06626061277224068, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06607604282022887, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06699889258028793, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06699889258028793, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.08397932816537468, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.14470284237726097, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.1893687707641196, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.21373200442967885, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.2321889996308601, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.24603174603174602, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.2691029900332226, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.27906976744186046, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.27722406792174237, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.26688815060908083, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.26411960132890366, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.2596899224806202, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.2606127722406792, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.2602436323366556, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.25507567368032485, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.24898486526393504, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.2497231450719823, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.24658545588778147, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.24067921742340348, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.24307862679955702, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.24381690660760427, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.21926910299003322, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.24363233665559247, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.2264673311184939, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.2131782945736434, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.2188999630860096, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.008434039162170953, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.007832492832670635, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.007710568954883443, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.00738231314121218, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.0070547916972470695, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.0069021000669086145, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.006959628186811919, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.007660622487023289, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.008120364328273809, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.009030720037553867, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.008753424075295326, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.01031990496805135, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.010859851841318768, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.012151961706875178, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.012135780303063748, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.012820557440147354, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.012761093012623265, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.033815005333559876, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.07378713980436781, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.11183981454092451, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.13653529117129498, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.15771727975040734, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.1736303713701092, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.19914033979350873, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.20931696117138013, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.21079107848714054, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.20386612123059109, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.2041058506582197, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.20347328112552202, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.20826650660319146, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.21032014031985233, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.20646196335165565, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.2037648473281178, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.1966276158065269, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.1976314690409683, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.18438636128966676, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.19179632399143562, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.195633518486695, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.17338711835268125, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.18392483835009676, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.1638292350912541, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.15383182234533466, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.1690263245972833, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 24, "lr_best": 0.0003, "wd_best": 0.05, "train/loss_best": 2.4236855125427246, "validation/loss_best": 2.4092185497283936, "validation/acc_best": 0.27906976744186046, "validation/f1_best": 0.20931696117138013} +{"epoch": 5, "train/lr": 0.00029891323817685334, "train/loss": 2.672805691957474, "train/grad": 0.23416964903473855, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.12575927734375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.125462646484375, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.1249951171875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.124525146484375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.1240966796875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.123614501953125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.122918701171875, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.122412109375, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.1214697265625, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.12064697265625, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.119716796875, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.118333740234375, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.117059326171875, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.114666748046875, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.11074951171875, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.1001849365234375, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.03719970703125, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.8582672119140624, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.6698434448242185, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.5696801376342773, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.4894878387451174, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.4230375480651856, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.3597467613220213, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.3026647758483887, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.255406723022461, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.207754125595093, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.172421779632568, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.1450746345520018, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.114843716621399, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.0950253677368162, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.0816499376296997, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.077227885723114, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.0659739351272584, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.0574357986450194, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.055232299566269, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.0752650761604308, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.102615340948105, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.1400591480731963, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.193929309844971, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.26977077960968, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.3276886343955994, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.3847713553905487, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.4875454688072205, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.171875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.02013127817772329, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.020142128928564488, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.020158429867587983, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.02017269565258175, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.02018636147491634, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.020201486004516482, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.020214858800172805, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.02022709170822054, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.020235353652387857, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.020233933781273663, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.020222551319748164, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.020194662217982114, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.020145566603168845, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.020038572833873333, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.01989987801760435, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.019839655603282155, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.02088032259605825, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.023968151723966002, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.027456812681630253, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.02934904315508902, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.03070784568786621, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.03199973379261792, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.033274674396961926, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.03419382281601429, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.03456596485339105, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.03541327839717269, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.03627509719692171, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.036932055493816736, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.037840727036818865, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.03915381369180977, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0401661816611886, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.04129642957821488, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0431259536370635, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.04506358386948705, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.046100709103047845, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.047529417388141156, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.04943382009863853, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0509960151463747, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.052013529893010856, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.052758218497037886, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.055595211554318666, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.05744157180190086, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.06509342409670353, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1230716705322266, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.122742176055908, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1222567558288574, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.121776580810547, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1213366985321045, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1207451820373535, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.120105028152466, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1193976402282715, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.118469476699829, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1174449920654297, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.116398334503174, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.114746570587158, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.112990617752075, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.109560012817383, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.101501941680908, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.0664494037628174, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.8749372959136963, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.658071279525757, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.5623810291290283, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.501274585723877, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.4495809078216553, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.414308786392212, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.385024070739746, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.35701584815979, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.342139959335327, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.3359625339508057, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.367441177368164, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.4195609092712402, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.463050603866577, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.464477300643921, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.472537040710449, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.487912178039551, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.5330185890197754, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.6418604850769043, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.768049716949463, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.741586923599243, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.7762744426727295, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.7167396545410156, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.802353620529175, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.729252815246582, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.7025225162506104, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.8001625537872314, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.0201897621154785, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06423034330011074, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06423034330011074, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06404577334809892, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06404577334809892, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06626061277224068, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.067921742340347, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06884459210040605, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.07161314138058324, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.09394610557401255, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.14599483204134367, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.1939830195644149, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.22111480251015134, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.24455518641565152, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.2572905131044666, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.2709486895533407, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.2823920265780731, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.2897748246585456, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.29365079365079366, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.29494278331487633, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.28922111480251017, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.27851605758582504, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.2766703580657069, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.2751937984496124, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.26947212993724623, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.26578073089701, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.2631967515688446, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.24381690660760427, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.2249907715023994, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.2220376522702104, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.21557770394979697, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.2235142118863049, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.21705426356589147, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.22129937246216316, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.2364341085271318, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.20191952750092285, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.20302694721299372, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.007800081429368178, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.007528562480806897, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.007415423847370667, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.006716761323162113, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.006717342697660173, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.006887009262467408, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.006998719806440699, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.0072670691096806605, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.00750712880973402, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.007743807016182737, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.007941792226876106, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.009192700999680241, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.0098988553266638, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.010989668961290376, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.015197812927159061, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.038690985500624255, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.06921206301762733, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.10798435652692841, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.13684682376151003, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.16303866023621547, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.18210563641336228, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.1960591906153992, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.21167062706172168, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.21631461365963522, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.2213800300149893, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.2233933979537852, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.22032811387541829, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.21049475278027438, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.21146671049251517, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.21379972814069773, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.21410805907225935, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.20949198514943498, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.19494834636215574, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.1800749274066585, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.17737402071205843, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.18726307013584345, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.1863433622228773, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.17840575270130457, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.17336319180948367, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.1825547281200696, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.17332043032587122, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.16886079650914274, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.15733736713664115, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 25, "lr_best": 0.00035999999999999997, "wd_best": 0.05, "train/loss_best": 2.207754125595093, "validation/loss_best": 2.3359625339508057, "validation/acc_best": 0.29494278331487633, "validation/f1_best": 0.2233933979537852} +{"epoch": 6, "train/lr": 0.0002924170901991409, "train/loss": 2.61403715133667, "train/grad": 0.24222064234316348, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.1302587890625, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.12991455078125, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.129088134765625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.12852294921875, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.127838134765625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.1268994140625, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.12595947265625, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.1249169921875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.123568115234375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.122113037109375, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.120635986328125, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.11833740234375, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.115435791015625, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.106510009765625, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.064422607421875, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.929060363769531, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.718126220703125, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.5863004302978516, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.5000878143310548, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.4365906143188476, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.3683418083190917, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.306875953674316, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.249794769287109, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.196010780334473, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.161769390106201, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.1204664134979248, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.085113513469696, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.0564627695083617, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.025544961690903, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.0039034032821657, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.9910118556022645, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.9878666448593139, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.9761903035640715, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.9764850890636445, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.991397738456726, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.009827100634575, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.0400374472141265, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.074908448457718, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.1364717984199526, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.2520344150066376, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.288235330581665, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.3811155104637147, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.412120884656906, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.171875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.02011548597365618, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.020120096965692936, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.020126289958134293, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.020128570781089365, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.020131780477240683, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.020132184927351773, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.020128909959457816, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.02011985819786787, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.020098270177841188, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.020062547610141337, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.02001563228201121, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.01991932487115264, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.01979231254197657, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.019590106788091362, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.020103527680039406, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.022534460620954634, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.026312983436509965, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.028879854660481215, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.030491000153124333, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.031716570742428306, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.03302460856735706, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.03400701366364956, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.03471148720011115, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.035314853666350246, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.035686708511784675, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.03688072509132326, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.03802178946323693, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.038758019395172594, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0398400442302227, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.040575386807322505, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.041283348519355056, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.04250138763338327, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.04400895446538925, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.045960132647305724, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.048063548374921085, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.04863136122003198, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.05075977608561516, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.05189241796731949, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.05299924835562706, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.05643379127606749, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.05747467968612909, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.061287226397544144, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.06319878198206424, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1226041316986084, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.122312307357788, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.121856451034546, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1214892864227295, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.121105194091797, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.120634078979492, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.12011456489563, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1195435523986816, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1187450885772705, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.117816209793091, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1167240142822266, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1143288612365723, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.110076427459717, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.088618755340576, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.9576542377471924, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.7264795303344727, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.5997323989868164, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.5172336101531982, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.456500291824341, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.413830280303955, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.377788543701172, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.3553600311279297, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.3451361656188965, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.3463335037231445, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.366475820541382, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.3846027851104736, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.439824342727661, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.4814000129699707, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.525118350982666, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.522975444793701, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.547272205352783, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.5785439014434814, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.600954294204712, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.6615829467773438, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.681476593017578, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.6711528301239014, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.7889232635498047, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.7155957221984863, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.781071186065674, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.801189422607422, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.8635642528533936, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.757392406463623, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.8494317531585693, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06441491325212255, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06404577334809892, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06404577334809892, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06404577334809892, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06441491325212255, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.0651531930601698, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06570690291620525, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.067921742340347, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06736803248431156, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.0664451827242525, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06902916205241787, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.07290513104466592, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.08970099667774087, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.13805832410483573, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.18549280177187155, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.2201919527500923, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.24197120708748615, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.262827611664821, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.2757475083056478, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.2862679955703212, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.2914359542266519, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.2916205241786637, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.28811369509043927, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.28165374677002586, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.28036175710594313, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.2713178294573643, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.26393503137689184, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.2563676633444075, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.26264304171280917, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.2552602436323367, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.2517534145441122, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.24510889627168697, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.23994093761535623, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.24178663713547435, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.23606496862310816, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.2222222222222222, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.23089700996677742, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.2172388335179033, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.21686969361387967, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.20837947582133629, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.2222222222222222, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.2235142118863049, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.007826771562180616, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.007906094781951664, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.007733743319314827, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.007674228760954443, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.007880442388019963, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.008358437532416151, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.009105311948786788, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.009864571345732183, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.01146610477595625, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.012472434993454197, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.012715320077262346, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.01577334264908332, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.019954464532321324, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.03409871169143044, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.06790901152672317, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.10449693947209715, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.14311483306811343, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.1690076741874266, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.19287994661441468, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.20913138939236, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.2240703463402595, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.23243872698971202, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.23464040659350135, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.23111081469000552, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.22734160265435485, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.2266617240394703, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.2170764258603267, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.21050310922193263, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.20457001671710473, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.2123630084129194, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.20833393911898943, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.20506478506523318, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.19889961873797946, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.1901044360847318, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.19170421374167881, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.19490112278913077, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.18315815703815974, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.1920415035564904, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.17755010202477897, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.17079370740533992, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.16155110751611843, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.1716122092926203, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.1782422645895887, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 22, "lr_best": 0.00021599999999999996, "wd_best": 0.05, "train/loss_best": 2.249794769287109, "validation/loss_best": 2.3451361656188965, "validation/acc_best": 0.2916205241786637, "validation/f1_best": 0.23464040659350135} +{"epoch": 7, "train/lr": 0.00027969249556793234, "train/loss": 2.5357487201690674, "train/grad": 0.24621002025902272, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.128365478515625, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.12783935546875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.127003173828125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.126103515625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.12525390625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.124146728515625, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.122847900390625, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.121383056640625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.1195166015625, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.1172314453125, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.11495361328125, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.110216064453125, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.1008648681640625, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.0282757568359373, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.8174046325683593, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.6499650573730467, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.5455422973632813, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.4578473663330076, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.3773897552490233, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.315688591003418, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.2506497955322264, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.1929945850372317, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.1363953018188475, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.0843442106246948, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.044127388000488, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.9989031720161439, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.964413855075836, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.9363283622264862, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.9018510270118714, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.8764334583282472, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.8736067461967467, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.8754123038053512, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.8693998116254806, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.8609845495224, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.8615831011533737, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.8918177407979966, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.919433400630951, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.9655739051103591, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.0369871217012405, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.1362313997745512, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.1944669687747957, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.2696038341522216, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.321058371067047, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.171875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.019605918675661086, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.01960856725461781, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.019611380170099436, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.019610144551843404, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.019607429448515176, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.019599906452931463, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.01958487233147025, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.019559727385640144, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.0195151023613289, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.01945169730577618, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.019376848982647063, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.019227245030924676, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.019091001534834503, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.020143063459545373, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.02379297576844692, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.026910022562369705, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.028974710833281278, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.03064282360486686, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.032261992702260614, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.033240889832377433, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.03404844082891941, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.03480365146882832, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.03560790533199906, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.03643841150216758, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.03697608546353877, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.038055952722206715, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.03918699825182557, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0400223352946341, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.04176737051457167, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.04283558428287506, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.043897038623690605, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.044601290859282015, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.04604626607149839, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.048265751115977765, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.04906017003580928, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.05008046505972743, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.051170788407325744, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.05299671305343509, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.05434929128736257, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.05392356771975756, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.05720122745260596, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.057949470095336436, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.061578717809170486, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1222856044769287, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1219863891601562, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1215028762817383, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1211178302764893, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1207172870635986, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.120232105255127, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1196835041046143, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1191580295562744, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.118468999862671, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.117555856704712, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.116260051727295, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.111776828765869, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.095263957977295, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.929959297180176, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.6852786540985107, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.5908355712890625, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.5125746726989746, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.449169635772705, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.404475212097168, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.380070447921753, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.364497423171997, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.361680746078491, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.377200126647949, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.3953661918640137, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.4371206760406494, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.4556081295013428, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.4723305702209473, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.515805721282959, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.5746326446533203, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.591733455657959, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.6012916564941406, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.596320629119873, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.5999298095703125, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.6651272773742676, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.7525322437286377, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.80523681640625, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.749014139175415, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.8250350952148438, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.791285514831543, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.6832082271575928, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.789358377456665, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.78487229347229, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.893315315246582, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06404577334809892, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06404577334809892, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06423034330011074, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06404577334809892, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06441491325212255, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.0651531930601698, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06589147286821706, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06718346253229975, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06718346253229975, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06699889258028793, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06884459210040605, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.07954964931709117, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.14322628276116647, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.19767441860465115, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.22425249169435216, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.24510889627168697, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.26245847176079734, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.2751937984496124, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.2798080472499077, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.2783314876338132, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.28608342561830935, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.2807308970099668, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.2777777777777778, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.27113325950535255, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.27260981912144705, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.27297895902547065, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.268733850129199, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.26098191214470284, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.2515688445921004, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.2517534145441122, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.2517534145441122, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.25212255444813586, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.24713916574381692, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.23994093761535623, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.23292727943890734, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.23717238833517904, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.22739018087855298, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.23108157991878922, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.2364341085271318, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.22277593207825766, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.23569582871908454, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.22739018087855298, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.008397194032485405, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.008185947065345846, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.008496905200175606, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.008977050411141656, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.009477688841230023, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.010169370584115649, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.01088561232777297, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.01105251530136826, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.011706899011647653, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.01214361778049699, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.012213529446800575, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.013786640655679703, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.019322253987558543, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.06478167144760279, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.11504812386355513, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.1417516130171847, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.16630501623369012, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.1893991742285492, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.20714292092963393, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.21399334685768667, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.21781366555545334, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.22647012463149627, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.22477119831253392, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.2226305009021797, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.21808509098992482, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.22357782206966315, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.22552618800822688, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.22040901129287907, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.21320617761715796, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.20068294905667472, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.20672031881448147, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.21246550812732545, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.20693589720140493, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.1983849777336412, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.18690745692651276, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.18700243651690238, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.18754047411121078, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.18546174424736606, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.18676164723607871, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.18835599590560506, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.1624095642543415, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.1647381022307999, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.15265569564139733, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 21, "lr_best": 0.00018299999999999998, "wd_best": 0.05, "train/loss_best": 2.1929945850372317, "validation/loss_best": 2.361680746078491, "validation/acc_best": 0.28608342561830935, "validation/f1_best": 0.22647012463149627} +{"epoch": 8, "train/lr": 0.0002612959497061927, "train/loss": 2.4741443538665773, "train/grad": 0.25540643781423567, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.124656982421875, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.124031982421875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.123135986328125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.12215087890625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.121314697265625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.12007080078125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.118746337890625, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.117239990234375, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.115179443359375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.11256103515625, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.109146728515625, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.09879638671875, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.0532891845703123, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.8127267456054685, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.627357177734375, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.540797080993652, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.4590371322631834, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.3773513221740723, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.3027102661132814, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.2451031494140623, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.180123291015625, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.121214189529419, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.064641122817993, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.0108322048187257, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.9741002535820007, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.9265412020683288, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.8853184378147125, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.8547926968336106, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.8173901945352555, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.788294451236725, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.776230548620224, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.7732933753728866, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.7614929062128066, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.7446099478006363, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.7630370002985, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.7917607933282853, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.8224875259399413, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.8628378129005432, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.9296246457099915, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.0508907890319823, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.1031852561235427, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.1492477643489836, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.2244758677482603, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.171875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.020276228464208543, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.02027944223023951, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.020283669028431178, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.020285296230576934, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.020283892173320054, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.02027480554766953, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.020256732027046382, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.020228649051859976, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.020173975052312016, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.020095461336895822, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.01999830218963325, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.01985188855789602, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.020381181468255818, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.02438212583772838, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.02800558162853122, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.029883731259033083, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.03157669140025973, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.033441636990755794, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.03479707122780382, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.03532096836715937, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.03593029420822859, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.03653179951943457, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.03735559559427202, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.03800943545997143, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.03885347183793783, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.04029093587771058, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.04163538012653589, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.042712305895984175, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.04466753616929054, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.04545830188319087, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.04638770330697298, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.047130325883626936, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.048326376210898164, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.04998436644673347, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.051416845861822366, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.051905826386064294, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.05324438763782382, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.053982121553272006, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.053725089840590955, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.054401391092687844, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.057542637325823306, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.05595612237229943, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.06063712388277054, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.122253179550171, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1218767166137695, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1212174892425537, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1205811500549316, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1199707984924316, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1190974712371826, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1181564331054688, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.116988182067871, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1152641773223877, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1128008365631104, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1088249683380127, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.0913188457489014, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.994833469390869, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.7041897773742676, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.5892860889434814, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.524771213531494, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.469162702560425, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.424168348312378, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.3954169750213623, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.3862338066101074, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.3920533657073975, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.4110238552093506, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.4304287433624268, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.446490526199341, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.483219623565674, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.5175254344940186, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.5635786056518555, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.5777699947357178, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.6020257472991943, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.6306800842285156, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.685971975326538, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.703585147857666, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.7446625232696533, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.865222692489624, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.950841188430786, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.98905873298645, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.1208136081695557, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.056429386138916, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.9840545654296875, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.8775277137756348, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.039634943008423, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.9569671154022217, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.8299050331115723, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06423034330011074, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06496862310815799, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.0651531930601698, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06662975267626431, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.0664451827242525, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06829088224437062, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06995201181247693, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.07235142118863049, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.08490217792543374, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.12476928755998523, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.18899963086009597, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.22462163159837578, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.24160206718346253, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.25396825396825395, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.2672572905131045, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.2737172388335179, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.27593207825765964, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.27260981912144705, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.2709486895533407, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.26651901070505724, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.2709486895533407, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.26135105204872644, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.2619047619047619, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.2572905131044666, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.25544481358434845, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.25083056478405313, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.25378368401624213, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.24215577703949798, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.24289405684754523, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.23385012919896642, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.23458840900701367, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.23883351790328536, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.2233296419342931, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.2144702842377261, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.21650055370985605, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.21225544481358435, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.2292358803986711, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.20487264673311184, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.22000738279808046, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.21686969361387967, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.008222703353715699, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.008457656853143888, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.00864854982564467, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.009464092396374616, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.010581936102702255, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.01166025315825784, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.013402141177911102, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.014183775332180536, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.016884198450799106, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.018402403820008996, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.021237531843220202, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.03412267684167205, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.05772411604576418, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.10882382794603841, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.14688121230015697, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.1696417778552849, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.18499149321731712, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.20313821307015703, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.21518588278562692, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.21972593419005318, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.2196584792616401, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.22020822451270652, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.2170000834353111, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.21988587209801533, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.2074546536382326, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.21269173980182798, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.2098788133483889, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.2103419190481209, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.20809522338806255, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.2100911912264606, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.1950244532534915, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.1952009677664834, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.18274891885267963, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.18172966972101035, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.18084950161811464, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.17540034732660245, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.16357785581458453, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.16776637194788804, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.16276465434934997, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.16960158838489536, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.15124945495885733, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.16654861942315927, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.16485144144138755, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 19, "lr_best": 0.00013199999999999998, "wd_best": 0.05, "train/loss_best": 2.2451031494140623, "validation/loss_best": 2.3862338066101074, "validation/acc_best": 0.27593207825765964, "validation/f1_best": 0.21972593419005318} +{"epoch": 9, "train/lr": 0.00023803200426111704, "train/loss": 2.429022650718689, "train/grad": 0.25770046904683114, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.123236083984375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.12248291015625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.121258544921875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.1201025390625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.118907470703125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.117423095703125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.115657958984375, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.1135791015625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.110848388671875, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.10705322265625, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.1008740234375, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.067659912109375, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.921006774902344, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.659531555175781, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.5509168243408205, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.4780940628051757, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.4014612579345704, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.323049545288086, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.2534147834777833, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.197117338180542, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.1316925621032716, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.075085153579712, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.0169424200057984, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.960699737071991, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.9212655901908875, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.8694377422332764, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.8271568703651428, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.7943729972839355, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.746066507101059, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.7111420029401778, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.6942066019773483, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.6915252476930618, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.67725361764431, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.650654005408287, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.6577613162994385, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.7023050862550735, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.7420193594694138, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.7978590023517609, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.872298970222473, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.9791927748918534, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.0436676079034806, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.1256407254934313, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.1789406061172487, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.171875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.020171460555866362, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.02017311504576355, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.020171943502500653, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.020168055295944214, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.020158855514600872, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.020142988921143114, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.02011502839624882, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.020073976605199276, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.020001442232169212, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.01989997916854918, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.019789493097923695, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.019997736839577555, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.02258084778673947, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.02710193273611367, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.029345612609758973, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.03084478828124702, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.032466723835095766, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.03418813742697239, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.03511149742640555, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.03555873727425933, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.03639907703734934, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.03706260280683637, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.03800370002165437, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.03892406812869012, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0397793712746352, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.040980459228157996, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.04228628568351269, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.043368355464190246, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.04488870047032833, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.04621491523459554, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.04667169488966465, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.04727432733401656, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.049062334205955266, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.050027127284556626, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.05116567438468337, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.05278071667999029, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.05373391410335898, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.055181871335953474, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.05478198740631342, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.05365055976435542, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.05612776374444366, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.05680502507835627, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.06010471878573299, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1215991973876953, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1211535930633545, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1204888820648193, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.119819402694702, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.119171380996704, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1182804107666016, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1172072887420654, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.115844964981079, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1136088371276855, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1096909046173096, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1013848781585693, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.0389456748962402, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.8294854164123535, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.617457866668701, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.532285451889038, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.47676420211792, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.423269510269165, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.3808531761169434, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.3553757667541504, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.350335121154785, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.3551788330078125, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.372443914413452, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.3923144340515137, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.4095802307128906, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.4621737003326416, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.4974279403686523, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.5540552139282227, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.5911996364593506, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.626732587814331, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.6449172496795654, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.680812120437622, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.7067928314208984, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.7355003356933594, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.817207098007202, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.86906361579895, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.9265246391296387, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.935624837875366, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.904766321182251, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.862642526626587, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.841679334640503, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.8340866565704346, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.7336173057556152, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.775099992752075, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06459948320413436, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06552233296419344, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06699889258028793, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06755260243632337, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06718346253229975, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.0681063122923588, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.0695828719084533, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.07050572166851236, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.07345884090070137, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.07973421926910298, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.11609449981543005, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.1638981173864895, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.21428571428571427, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.23606496862310816, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.25452196382428943, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.2737172388335179, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.2851605758582503, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.28922111480251017, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.2901439645625692, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.2836840162421558, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.2812846068660022, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.2794389073458841, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.2792543373938723, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.26836471022517533, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.26116648209671467, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.2593207825765965, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.2513842746400886, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.2454780361757106, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.24197120708748615, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.23329641934293097, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.23440383905500184, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.24603174603174602, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.2321889996308601, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.22517534145441123, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.2264673311184939, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.22702104097452935, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.23588039867109634, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.2222222222222222, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.22277593207825766, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.23145071982281284, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.2220376522702104, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.22739018087855298, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.008427153842424148, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.008866225925185045, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.009547148979981419, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.010250987512385882, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.011275346530138057, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.011460237414196751, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.012551478674575449, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.01409874348874301, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.017037809272132654, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.01961527146572101, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.025084781991062444, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.05560232598343536, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.08359286623063171, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.12826213914490667, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.15399080083350722, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.17582241062176565, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.19558454058348687, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.21478542841840673, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.22261395040128273, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.2273477870550588, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.22633062113558555, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.22652159561498433, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.22799101267478314, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.22621795324974459, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.21717476715322556, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.2173230620719265, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.2170390040176214, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.21085902178036423, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.2100974804095759, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.21071039157154936, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.20116598273882613, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.20392662496465286, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.20585153201588524, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.1949212071122665, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.18448956250721693, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.17750062662800092, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.17688239612084866, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.1901357145688893, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.18749867427231923, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.18739574232620884, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.18308926025309677, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.18482670747103377, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.1766498987296535, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 19, "lr_best": 0.00013199999999999998, "wd_best": 0.05, "train/loss_best": 2.197117338180542, "validation/loss_best": 2.350335121154785, "validation/acc_best": 0.2901439645625692, "validation/f1_best": 0.2273477870550588} +{"epoch": 10, "train/lr": 0.00021091808096876188, "train/loss": 2.3617596220970154, "train/grad": 0.2559771820902824, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.12322021484375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.122406005859375, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.1209375, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.119619140625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.11827880859375, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.116470947265625, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.11459228515625, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.112191162109375, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.108603515625, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.10285400390625, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.0901318359375, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.99190185546875, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.7665419006347656, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.580032958984375, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.4869955444335936, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.4176955032348633, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.338322944641113, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.25997163772583, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.1891796588897705, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.1313213872909547, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.066904263496399, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.0087107181549073, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.9462616157531738, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.8840937614440918, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.839350266456604, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.7805256563425065, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.7241749334335328, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.6833799201250077, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.6365063780546187, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.5936768937110901, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.5798354613780976, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.5622058868408204, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.5496046549081803, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.5270980298519135, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.5340404391288758, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.5865368819236756, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.6254868710041046, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.686764572262764, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.7387544149160385, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.8559159076213836, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.8959639245271682, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.9620659673213958, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.0158478522300722, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.171875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.01986430329736322, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.019863822609186173, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.019859296660870315, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.019851935524493457, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.019841205924749375, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.019817475848831236, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.019784023226238786, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.01973602289799601, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.01965199544094503, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.019542455319315196, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.0194899687031284, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.020951408538967372, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.024444605987519026, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.028219461860135197, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.03015334458090365, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.031599243115633724, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.03346141073852778, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.034851562315598134, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.0356391557212919, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.036060140896588565, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.036937405616045, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.03754491456784308, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.03843878493644297, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.03918620996177197, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.039907141216099264, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.04117593698203564, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.042262672055512665, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.04314887436106801, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.04487211782485247, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.04635907404124737, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.04705262428149581, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.04816010843962431, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.049639991205185655, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.05165745265781879, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.05207575522363186, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.05310848267748952, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.053879083022475245, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.05456975473091006, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.05393765712156892, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.05296174334362149, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.05322728279978037, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.052173850890249014, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.054191834572702643, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1215980052948, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.121209144592285, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1205177307128906, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1198713779449463, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1191787719726562, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1181464195251465, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.116884708404541, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1151647567749023, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.111978769302368, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.105509042739868, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.0868239402770996, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.9367830753326416, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.706789255142212, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.572253465652466, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.5015292167663574, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.4557666778564453, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.411062479019165, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.3765671253204346, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.355222463607788, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.3532872200012207, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.359398126602173, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.377018451690674, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.407468318939209, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.44901442527771, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.5230700969696045, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.5667338371276855, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.606868267059326, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.679988145828247, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.764796018600464, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.78825306892395, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.8699498176574707, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.9233734607696533, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.9433417320251465, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.0205483436584473, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.01629638671875, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.0259833335876465, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.031764507293701, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.020066261291504, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.056706190109253, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.865293264389038, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.9250082969665527, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.8514351844787598, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.9539740085601807, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06423034330011074, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06404577334809892, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06459948320413436, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06441491325212255, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06459948320413436, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06552233296419344, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.07142857142857142, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.08231819859726837, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.13842746400885936, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.19232188999630861, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.2249907715023994, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.24658545588778147, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.26264304171280917, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.27722406792174237, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.28552971576227393, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.28811369509043927, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.28811369509043927, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.28313030638612036, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.2853451458102621, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.27500922849760057, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.2678110003691399, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.2572905131044666, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.2499077150239941, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.2530454042081949, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.24141749723145073, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.2355112587670727, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.23385012919896642, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.2248062015503876, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.22535991140642303, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.21760797342192692, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.2146548541897379, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.22277593207825766, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.21520856404577335, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.21244001476559615, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.2207456626061277, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.21354743447766703, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.22886674049464747, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.2188999630860096, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.2188999630860096, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.2115171650055371, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.008484029212305762, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.00951892732984372, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.009423169233518965, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.01001389472030652, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.01051229611423695, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.011013907612790655, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.011420412072028888, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.012317158403568484, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.013230522363174154, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.018565169568206502, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.02793808898022383, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.06391396010086242, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.10971177030810736, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.1450430754363307, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.17202998453631632, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.1913408988851839, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.21111072219239993, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.220287850066899, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.22787748271661704, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.23201270673267863, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.2290604142597538, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.23414665673923116, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.22375771092395216, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.21473698843667663, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.20532685395158276, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.19995669594075463, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.206347601832063, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.19875291674949339, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.19627516036339568, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.19682533954754397, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.19209696331048884, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.18771646722068583, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.18080969260265342, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.17493239199502153, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.18435769313384395, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.18018254141962975, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.1821389169557709, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.1763277332616394, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.1713175259886132, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.18673676937745717, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.18595326431655793, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.17874808111940718, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.1723819524250164, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 18, "lr_best": 0.00011399999999999999, "wd_best": 0.05, "train/loss_best": 2.1891796588897705, "validation/loss_best": 2.355222463607788, "validation/acc_best": 0.28811369509043927, "validation/f1_best": 0.22787748271661704} +{"epoch": 11, "train/lr": 0.00018113997589164516, "train/loss": 2.319663324356079, "train/grad": 0.26136354759335517, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.128001708984375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.12698974609375, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.125611572265625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.124300537109375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.122857666015625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.12102783203125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.118773193359375, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.11606689453125, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.111446533203125, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.102601318359375, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.0759716796875, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.896251525878906, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.6788665771484377, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.5438473510742186, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.4582369232177737, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.3879111862182616, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.3103068923950194, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.2348298835754394, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.1633952236175538, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.1063618087768554, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.0381044340133667, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.9757448530197144, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.910973722934723, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.8478284645080567, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.8046994805335999, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.738817588686943, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.6755071729421616, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.6311487656831742, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.574514660835266, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.5286438900232315, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.5125821256637573, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.497107326388359, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.4607505315542222, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.4166562473773956, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.4253483933210374, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.460578939318657, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.4908245140314103, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.5546215879917145, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.629168107509613, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.7444546437263488, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.827767897248268, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.899388234615326, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.9333682709932327, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.171875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.019964550724253058, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.019961287332698703, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.019955495856702327, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.01994621612597257, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.01993539784103632, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.019911481640301643, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.01987498427275568, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.019819475430995225, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.019724613633006812, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.01962080005090684, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.01978929476812482, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.022727303123101592, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.02623880454339087, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.029279560232535005, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.031173237254843115, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.03282442642375827, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.03467800574377179, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.03591402283869684, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.036648723259568215, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.0370028068125248, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.037842545639723536, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.03844216271303594, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.039486906034871934, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.040448324847966434, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.04137067902833223, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.04270716207101941, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.04442010387778282, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.04573180420324206, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.04742249928414822, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.04914885625243187, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.04971954757347703, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.050497747212648394, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.05078580092638731, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.05111828997731209, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.05236495954915881, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.05300735965371132, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.05307814717292786, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.05322678171098232, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.05391396351158619, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.05211113300174475, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.05431675394997001, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.053344027362763884, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.05494976751506329, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1213598251342773, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1208410263061523, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.119950294494629, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.119100570678711, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1182398796081543, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1169936656951904, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1154539585113525, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.113340377807617, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.108999252319336, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.0983316898345947, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.0583393573760986, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.8355839252471924, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.647998332977295, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.54244327545166, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.4814698696136475, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.4419491291046143, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.4055590629577637, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.378040075302124, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.3634021282196045, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.366628408432007, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.3796534538269043, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.401982307434082, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.4273431301116943, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.4517574310302734, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.5002987384796143, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.531423807144165, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.6058754920959473, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.6395483016967773, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.7007896900177, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.7651355266571045, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.838589906692505, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.8787646293640137, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.8966598510742188, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.9831883907318115, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.9697721004486084, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.0444908142089844, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.1357719898223877, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.04060959815979, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.991481065750122, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.739473342895508, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.821660041809082, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.790447235107422, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.731825590133667, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06293835363602805, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.0651531930601698, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06552233296419344, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06607604282022887, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06662975267626431, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06755260243632337, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06718346253229975, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.07087486157253599, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.07936507936507936, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.10963455149501661, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.1642672572905131, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.2041343669250646, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.23477297895902546, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.25544481358434845, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.2672572905131045, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.2823920265780731, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.2886674049464747, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.290328534514581, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.2886674049464747, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.28183831672203763, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.2809154669619786, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.2753783684016242, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.27353266888150607, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.26596530084902176, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.2643041712809155, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.2591362126245847, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.257844222960502, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.25193798449612403, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.24363233665559247, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.2395717977113326, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.2321889996308601, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.23717238833517904, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.2292358803986711, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.23938722775932078, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.23846437799926173, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.23329641934293097, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.23274270948689554, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.23015873015873015, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.2395717977113326, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.22296050203026946, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.2355112587670727, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.23938722775932078, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.008834067074851957, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.009354650829427212, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.00994797446812678, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.010326154645508134, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.010678418799267363, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.011080335121886185, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.01201899644425738, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.013064736384135708, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.017113185409920448, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.02729327751077143, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.04966341581811918, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.08264405148983651, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.11906501497083273, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.15367846038848712, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.1764871010271427, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.1928353896273731, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.21029024501272642, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.22106037706257334, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.22785282602691523, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.23002915550205735, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.23038084505226375, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.23235670679129294, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.22630815559722448, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.22398480556439307, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.22137316003276153, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.2203401849478163, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.21503826033635998, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.21615171396194402, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.21025731221041175, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.20284410173343684, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.19993173609032863, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.19147047941053708, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.2000328080900822, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.18763326716782483, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.19961892400875672, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.19078827931511877, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.1851422651199226, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.18801720344282816, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.1850039921556624, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.21331948717863627, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.19712960587938788, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.1918208562621592, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.20441623344536217, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 18, "lr_best": 0.00011399999999999999, "wd_best": 0.05, "train/loss_best": 2.1633952236175538, "validation/loss_best": 2.3634021282196045, "validation/acc_best": 0.290328534514581, "validation/f1_best": 0.22785282602691523} +{"epoch": 12, "train/lr": 0.0001499999999999999, "train/loss": 2.258937475681305, "train/grad": 0.2582301987707615, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.11957275390625, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.11860107421875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.117010498046875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.1154296875, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.113680419921875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.111456298828125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.108759765625, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.105462646484375, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.099205322265625, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.08496826171875, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.0311663818359373, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.791101989746094, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.614654998779297, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.495789604187012, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.4124589157104492, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.3421418952941893, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.2656674194335937, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.1897174739837646, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.117468891143799, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.059259490966797, "train/loss_020_lr5.2e-01_wd1.0e+00": 1.9914317989349366, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.928437967300415, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.8581911706924439, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.789741380214691, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.7399656879901886, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.6674888598918916, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.596756334900856, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.5450568795204163, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.4736151087284088, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.4153481864929198, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.3888672959804536, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.3646236497163773, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.3384763377904891, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.2944291853904724, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.2953019469976426, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.3336971029639244, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.3871575582027436, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.432839943766594, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.5061136025190354, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.6281451845169068, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.7002020454406739, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.760325785279274, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.8069015991687776, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.171875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.01994347270578146, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.01994127659127116, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.01993490128777921, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.019924986409023404, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.019911674009636046, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.01988419098779559, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.019842073703184724, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.019781759646721183, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.019680813802406192, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.019619088005274534, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.020265060751698913, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.02406192330643535, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.02752629560418427, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.03025416805408895, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.03208194945007563, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.0338111159671098, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.03545544324442744, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.0364426673296839, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.03707401362247765, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.037414721632376316, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.03838587712496519, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.03908678725361824, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.040016168132424354, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.040835631638765336, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.041635819375514985, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.04288290785625577, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.044088799823075536, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.04500996494665742, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.046372730880975724, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.04752349888905883, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0480711280927062, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.048649842031300065, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.04991431392729282, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.05113693203777075, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.051699359882622954, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.05194685004651547, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.05282813105732202, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.05199735403060913, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.05224558861926198, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.050433559790253636, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.05220911046490073, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.05041646622121334, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.05257619291543961, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.121428966522217, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1209423542022705, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.120088815689087, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.119262456893921, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.118375778198242, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.117083787918091, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.115398406982422, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.112895965576172, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1073098182678223, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.090618371963501, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.0191798210144043, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.7642743587493896, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.6194047927856445, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.5253512859344482, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.4696176052093506, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.433680534362793, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.4001879692077637, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.3768234252929688, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.370708465576172, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.381523847579956, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.4018354415893555, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.4338648319244385, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.4673314094543457, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.504796266555786, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.566915273666382, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.599515199661255, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.656461715698242, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.7060415744781494, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.797783374786377, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.823441505432129, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.9496278762817383, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.9950368404388428, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.0762381553649902, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.1656014919281006, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.127145528793335, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.140911340713501, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.099423408508301, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.0344724655151367, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.0860629081726074, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.8828461170196533, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.9102652072906494, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.884366512298584, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.8889245986938477, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06423034330011074, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06459948320413436, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06533776301218161, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06552233296419344, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06626061277224068, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.0695828719084533, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.08342561830933924, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.12236987818383167, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.17331118493909192, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.20930232558139536, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.23661867847914358, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.2582133628645257, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.2702104097452935, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.27888519748984864, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.2822074566260613, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.2827611664820967, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.2807308970099668, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.2794389073458841, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.27500922849760057, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.2672572905131045, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.2631967515688446, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.2558139534883721, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.2622739018087855, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.2652270210409745, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.2596899224806202, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.24584717607973422, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.2484311554078996, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.2410483573274271, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.24234034699150978, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.2336655592469546, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.2364341085271318, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.23994093761535623, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.2382798080472499, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.23846437799926173, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.23477297895902546, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.23089700996677742, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.24215577703949798, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.23606496862310816, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.2294204503506829, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.23440383905500184, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.008061972505443675, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.00808759085507504, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.008201826966534107, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.008391945413343458, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.008579744835731604, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.00911538464192301, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.010002432182464336, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.010985212536922704, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.014965615676493208, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.032569898808803066, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.0563466882599366, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.0914875807003489, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.12461440548809032, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.15790393834776517, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.18211784553546104, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.19950356662932536, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.21075025185189397, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.2210280334284075, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.22725096697841798, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.2276488859146244, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.22921954338205355, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.22533361988340642, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.21700487322820572, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.21049034917614806, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.20454813652421897, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.20746165243425832, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.21155321762676868, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.2065754213521683, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.1937457210789774, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.19645939320337072, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.18727340291750028, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.19226048071884386, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.1824599155058582, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.18413869446540618, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.19059576619117938, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.1900152950526094, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.19417012422854893, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.19358537214060023, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.18429612288719852, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.19468765410426878, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.18195889913996188, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.1871845938103762, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.1905041613600896, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 18, "lr_best": 0.00011399999999999999, "wd_best": 0.05, "train/loss_best": 2.117468891143799, "validation/loss_best": 2.370708465576172, "validation/acc_best": 0.2827611664820967, "validation/f1_best": 0.22725096697841798} +{"epoch": 13, "train/lr": 0.00011886002410835478, "train/loss": 2.213690729737282, "train/grad": 0.25760986693203447, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.123629150390625, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.122518310546875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.1207958984375, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.119095458984375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.11742919921875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.11507080078125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.1121533203125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.108419189453125, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.10100341796875, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.080494384765625, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.9965753173828125, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.7358766174316407, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.591140823364258, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.4793585968017577, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.397025661468506, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.3269159507751467, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.251219644546509, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.1742547607421874, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.09940110206604, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.0398569679260254, "train/loss_020_lr5.2e-01_wd1.0e+00": 1.9653304076194764, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.8974808621406556, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.8234932589530946, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.7500678861141206, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.6973206788301467, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.6199192041158677, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.540845907330513, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.4829509419202804, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.4087750816345215, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.3400386893749237, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.306990504860878, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.2776991969347, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.232667927145958, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.177719306051731, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.180479012131691, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.2080840438604354, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.232412216067314, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.3001618844270706, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.375425722002983, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.5027105671167373, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.568092822432518, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.6489666515588761, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.6897307187318802, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.171875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.020303897075355053, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.020301385219208896, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.020291967173106967, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.020278626950457693, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.02026268407702446, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.020230397279374302, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.020182878491468728, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.020113823995925487, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.02000529272016138, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.020014654104597865, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.021208656774833797, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.025123650012537836, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.028209951287135483, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.030752187399193644, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.03262555794790387, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.03439794067293406, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.03587420536205173, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.036774984048679474, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.037329709585756064, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.0376071388553828, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.0384686600137502, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.039114250922575595, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.040097371377050876, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0410152174346149, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.041905156672000884, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.04320095220580697, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.04489473856985569, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.04594943946227431, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.04695563798770309, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.047809953838586806, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.04828216373920441, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.04855665922164917, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.049626350924372675, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.05020737456157803, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.050767252780497076, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.05100190913304686, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.051179493796080354, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.05138466764241457, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.05161792861297727, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.05061519600450993, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.05052754115313292, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.04868220906704664, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.051149171963334086, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.121133804321289, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1205313205718994, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.119473457336426, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1184029579162598, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1173105239868164, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.115661144256592, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1135029792785645, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.110414743423462, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1031789779663086, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.078880548477173, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.9762134552001953, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.7153685092926025, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.596467971801758, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.5090529918670654, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.454817533493042, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.4195377826690674, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.3853886127471924, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.361319065093994, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.3572919368743896, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.370512008666992, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.394287347793579, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.428337812423706, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.4631898403167725, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.4867160320281982, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.5529627799987793, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.598442554473877, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.6627914905548096, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.7143542766571045, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.7920892238616943, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.8695003986358643, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.9830892086029053, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.0507819652557373, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.1569998264312744, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.2439560890197754, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.269508123397827, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.243971109390259, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.2675259113311768, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.185523509979248, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.2805023193359375, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.0046327114105225, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.1136586666107178, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.9840097427368164, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.9242405891418457, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06459948320413436, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06607604282022887, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06681432262827612, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06662975267626431, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06662975267626431, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.067921742340347, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06847545219638243, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.073827980804725, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.09043927648578812, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.12956810631229235, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.18955334071613142, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.21982281284606867, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.24455518641565152, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.26596530084902176, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.27464008859357697, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.2853451458102621, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.2912513842746401, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.2899593946105574, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.28811369509043927, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.28608342561830935, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.27906976744186046, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.2777777777777778, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.2692875599852344, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.2643041712809155, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.26098191214470284, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.26098191214470284, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.25544481358434845, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.24160206718346253, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.23421926910299004, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.22757475083056478, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.22185308231819859, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.21926910299003322, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.21686969361387967, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.22406792174234036, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.22978959025470652, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.2292358803986711, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.23421926910299004, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.2233296419342931, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.23809523809523808, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.21945367294204504, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.23126614987080105, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.23588039867109634, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.008706845501605788, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.009425887019359687, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.010865623382138178, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.011904351413037563, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.01196329989123312, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.0123646116950409, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.014127643931452279, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.015884272481829, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.021433834094878132, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.038585362001945935, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.0575993368009699, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.10635885878679326, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.13551457894519184, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.1649067220221082, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.19127557454817268, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.20395293627245978, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.21887862230911384, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.22861292364840322, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.23363475767783548, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.234202050052557, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.2356816593200195, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.22704693158600708, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.22669987179229856, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.21735322739729726, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.21397041819594267, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.2107546927981987, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.2113257639385341, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.20769601169286075, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.19810307292388207, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.19694496149003338, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.18914285433702027, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.18583068922566284, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.18274571324332745, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.1791860335519132, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.18390598161985916, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.18989395304966186, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.18637544425574268, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.18371833804608706, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.17330225187707135, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.1900398319439173, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.1703943715485607, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.18036986571830912, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.18532779138492472, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 17, "lr_best": 9.599999999999999e-05, "wd_best": 0.05, "train/loss_best": 2.1742547607421874, "validation/loss_best": 2.361319065093994, "validation/acc_best": 0.2912513842746401, "validation/f1_best": 0.22861292364840322} +{"epoch": 14, "train/lr": 8.9081919031238e-05, "train/loss": 2.1635861945152284, "train/grad": 0.2564090418070555, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.12099853515625, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.119798583984375, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.117957763671875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.116185302734375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.114415283203125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.111900634765625, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.108900146484375, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.104703369140625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.0959197998046877, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.0680596923828123, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.9573333740234373, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.689911651611328, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.5591513824462893, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.4484435653686525, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.364213409423828, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.2946091079711914, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.2199951362609864, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.1436070919036867, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.0696844100952148, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.0097219514846802, "train/loss_020_lr5.2e-01_wd1.0e+00": 1.9350787687301636, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.8655260682106019, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.7895546746253967, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.716153444647789, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.6564807486534119, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.569468167424202, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.4854267650842667, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.422726076245308, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.3370167464017868, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.2620247077941895, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.2227787232398988, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.1774206227064132, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.1192156559228896, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.071826753616333, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.056603388786316, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.073967407643795, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.1050361949205398, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.1570171320438385, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.2508117473125457, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.3766826850175857, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.4279863879084587, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.531793087720871, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.5383690792322158, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.171875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.01987734724767506, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.019873070595785976, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.019862492913380266, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.019848867622204124, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.0198310227971524, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.01979942688718438, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.019750342057086527, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.019682445023208858, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.01958600036799908, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.019713795436546208, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.021428202399984, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.025518395556136966, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.02836179613135755, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.03080109169706702, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.03272263888269663, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.03446940907277167, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.0358721233624965, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.036791039984673264, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.03735347971320152, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.037633949536830184, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.03854129041545093, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.0392117054387927, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.040155482720583675, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.04116163002327085, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.041887548491358756, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.043192702997475865, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0444771233573556, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.045418718606233595, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.046789246276021004, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.047794984709471466, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0479177350178361, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.04834328869357705, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.04846962511539459, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.04950716756284237, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.04976328989490866, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.050372978542000055, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.05089440625160933, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.05058322537690401, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.05190072692930699, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.05092559043318033, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0508290976472199, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.05024539910256862, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.049928131885826586, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.120584726333618, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.119926929473877, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1188111305236816, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.117703437805176, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1165785789489746, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1148695945739746, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1126298904418945, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.109271287918091, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1007163524627686, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.0685319900512695, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.94144606590271, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.685732841491699, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.5805726051330566, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.4962058067321777, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.443157434463501, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.40932035446167, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.376657247543335, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.355092763900757, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.3516674041748047, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.3625664710998535, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.3813889026641846, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.410677909851074, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.4422249794006348, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.4802405834198, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.5520641803741455, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.6091551780700684, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.6692118644714355, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.7302637100219727, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.8189167976379395, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.874443769454956, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.999033212661743, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.0675673484802246, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.140699625015259, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.239025354385376, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.3003904819488525, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.2948994636535645, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.357644557952881, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.3518569469451904, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.370565176010132, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.150723457336426, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.1416451930999756, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.0553436279296875, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.9985342025756836, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.0651531930601698, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.0664451827242525, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06681432262827612, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06736803248431156, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06755260243632337, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.0681063122923588, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06884459210040605, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06939830195644149, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.07456626061277224, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.09985234403839055, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.13658176448874124, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.19601328903654486, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.22314507198228128, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.24732373569582872, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.26559616094499816, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.2768549280177187, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.2866371354743448, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.2882982650424511, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.2918050941306755, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.28959025470653377, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.28922111480251017, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.2851605758582503, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.27740863787375414, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.27611664820967147, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.2619047619047619, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.2572905131044666, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.25599852344038393, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.24750830564784054, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.2410483573274271, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.2369878183831672, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.22997416020671835, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.2187153931339978, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.21945367294204504, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.22093023255813954, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.2187153931339978, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.21779254337393872, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.21668512366186785, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.2174234034699151, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.20911775562938353, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.21926910299003322, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.2117017349575489, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.2233296419342931, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.22462163159837578, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.009418675370600442, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.009839598639348418, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.01004360889154049, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.010043310061052569, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.010807223163689325, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.01133333053193532, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.012894336920693328, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.014241728303745434, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.01999775559993594, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.04247502606508317, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.06131243563010533, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.11110655567866394, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.13959062069383946, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.16845083571749916, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.19097357590569133, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.20779947774477722, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.22033257577691315, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.22661550048183354, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.23588514026867058, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.23410068723665267, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.24017354326044357, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.23596140693195192, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.22913858479608232, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.22547284103866108, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.21457075955726493, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.21175456837509468, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.21348793663559115, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.2057152014657433, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.2046518465681526, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.205170626241719, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.1969012981305501, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.18923263252791142, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.19316323209714345, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.19144781124165786, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.19243751392507966, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.19273795915875316, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.1866459509546484, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.18255840582973928, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.17666331157301016, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.18564153976233047, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.17747155606340748, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.1820957588291177, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.19416568550175595, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 18, "lr_best": 0.00011399999999999999, "wd_best": 0.05, "train/loss_best": 2.0696844100952148, "validation/loss_best": 2.3516674041748047, "validation/acc_best": 0.2918050941306755, "validation/f1_best": 0.23588514026867058} +{"epoch": 15, "train/lr": 6.196799573888289e-05, "train/loss": 2.120410929322243, "train/grad": 0.2509787858277559, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.117230224609375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.116036376953125, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.11427978515625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.112462158203125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.11069091796875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.1082568359375, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.105137939453125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.100706787109375, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.09110107421875, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.0574334716796874, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.92962890625, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.668140716552734, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.550648956298828, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.4417903518676756, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.3571057510375977, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.2867339134216307, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.210519218444824, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.1312738704681395, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.054162425994873, "train/loss_019_lr4.4e-01_wd1.0e+00": 1.9913350105285645, "train/loss_020_lr5.2e-01_wd1.0e+00": 1.9133830738067628, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.8411755502223968, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.7615638369321822, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.6835889947414397, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.6224114328622818, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.5291193813085555, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.4427891951799392, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.3728092449903488, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.283062557578087, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.1982115918397904, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.1429897218942642, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.0998746767640113, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.0352262637019158, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.9706197547912597, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.9544666874408722, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.9647889843583107, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.9843159788846969, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.0435989433526993, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.096396110355854, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.2233362102508545, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.2682045024633408, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.3769720441102982, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.4053074526786804, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.171875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.020313206734135746, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.020307359141297637, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.02029547929763794, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.02027699628379196, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.020255751395598053, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.02021691428963095, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.020160619490779935, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.02008139804005623, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.019975455831736325, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.02018220318481326, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.02214088449254632, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.02618395185098052, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.028900787914171815, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.03135122084058821, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.033371381480246785, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.03506024081259966, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.036332320533692834, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.037143222773447636, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.03760975639335811, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.03782103421166539, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.03872391529381275, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.039351433888077735, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.040355346221476796, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.04115494638681412, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.04181793224066496, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.042947008162736895, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.04406252922490239, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.04469322118908167, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.04560614954680205, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0460306884534657, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.046334415581077336, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.04623074375092983, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.04639097739011049, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.04684904837980866, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.047340752352029086, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.047313208933919666, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0482232866063714, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.04876901125535369, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.04934110289439559, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.04855163222178817, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.048792416993528605, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0482541448622942, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.04847744569182396, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1206467151641846, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1200151443481445, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1189467906951904, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.117891550064087, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1167571544647217, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.115111827850342, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1128244400024414, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.109231948852539, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.099581718444824, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.06086802482605, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.918944835662842, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.669405698776245, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.5705995559692383, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.4884707927703857, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.4368326663970947, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.404771566390991, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.3743703365325928, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.3556559085845947, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.3552725315093994, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.368281364440918, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.39001727104187, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.4240682125091553, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.4594082832336426, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.491239070892334, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.559065580368042, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.601349353790283, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.669496774673462, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.73374080657959, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.8329615592956543, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.898668050765991, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.0163493156433105, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.0587923526763916, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.1390345096588135, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.2576823234558105, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.330711603164673, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.3405921459198, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.346947193145752, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.309354066848755, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.3369853496551514, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.09281849861145, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.1562013626098633, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.102485418319702, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.0220654010772705, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06478405315614617, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06496862310815799, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06607604282022887, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.0664451827242525, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.0664451827242525, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06662975267626431, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06773717238833518, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06976744186046512, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.07751937984496124, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.10409745293466224, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.14304171280915468, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.20155038759689922, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.22572905131044665, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.2502768549280177, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.27113325950535255, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.27851605758582504, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.28792912513842744, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.29198966408268734, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.290328534514581, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.2871908453303802, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.28959025470653377, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.2823920265780731, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.2763012181616833, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.2707641196013289, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.2587670727205611, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.260797342192691, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.2606127722406792, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.2467700258397933, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.2397563676633444, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.23477297895902546, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.2279438907345884, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.22868217054263565, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.22240679217423404, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.2203765227021041, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.21760797342192692, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.21686969361387967, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.21779254337393872, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.21982281284606867, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.21816168327796234, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.22905131044665927, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.21705426356589147, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.22111480251015134, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.21982281284606867, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.009383362874917459, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.009487016746319877, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.010080088799535297, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.010385496084518157, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.011201042012108251, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.01233901470266635, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.014058448009670195, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.016749891992960148, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.023403729575740596, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.046096213867867365, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.06562953408722583, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.11795776624712366, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.14318763561521594, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.17267614957682698, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.19683289671624168, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.2092590203999222, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.22253291478995596, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.2292863352556065, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.23208616372384058, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.23190376267664994, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.23935000779026527, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.23097204168721727, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.22662280577707097, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.21968073714420502, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.21191395846661867, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.21689828487891608, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.21808638125388344, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.20763504650237374, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.2043762895311926, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.20096565886404716, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.19673249989999442, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.19980400363084397, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.1985987705228728, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.19331167855980844, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.19116619753194328, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.19134625820427767, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.19494280808532616, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.19356232366985995, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.19512022513685467, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.19744127081998383, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.1896158796329228, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.1934598639059242, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.19102936179240468, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 17, "lr_best": 9.599999999999999e-05, "wd_best": 0.05, "train/loss_best": 2.1312738704681395, "validation/loss_best": 2.3556559085845947, "validation/acc_best": 0.29198966408268734, "validation/f1_best": 0.2292863352556065} +{"epoch": 16, "train/lr": 3.870405029380728e-05, "train/loss": 2.094466809630394, "train/grad": 0.24658706411719322, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.124974365234375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.12363525390625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.121607666015625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.119615478515625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.1177587890625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.11497314453125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.1114599609375, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.10680908203125, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.0958984375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.056544189453125, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.9169781494140623, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.6635531616210937, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.5532713317871094, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.4479486083984376, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.3646063804626465, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.2955197525024413, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.220866584777832, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.142019519805908, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.0662550115585328, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.0036061668395995, "train/loss_020_lr5.2e-01_wd1.0e+00": 1.9231668281555176, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.8485585522651673, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.7651577454805374, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.6821844178438186, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.6188227051496507, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.5186752611398697, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.42418810069561, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.3516012704372407, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.2577641004323958, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.1651184898614884, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.1004975143074989, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.0461942407488822, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.977452811896801, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.9071138912439346, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.8754605913162231, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.8755882054567337, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.8852772209048271, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.9367973759770394, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.9786462804675102, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.089640374183655, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.1279881954193116, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.2213816830515862, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.2524498018622399, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.171875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.02025429897941649, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.020246902597136796, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.020228859474882482, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.020209556757472456, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.0201859129127115, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.020145143889822067, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.020086192735470833, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.020005441773682832, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.019909290401265024, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.020213471571914852, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.022410646975040437, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.026440229872241615, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.029064143607392907, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.03148483132943511, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.033530754577368496, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.03521469118073583, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.03647187741473317, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.03728477719239891, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.03775042347609997, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.03794107254594564, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.038785371128469706, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.03938446780666709, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.040331310033798216, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.04109642894938588, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.041861915104091166, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.042877003252506256, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.04385755190625787, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.04442771272733807, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.045267453398555514, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.04554750042036176, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.04550383696332574, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.045338656548410655, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.04510146031156182, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.045376014560461045, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.04564203415066004, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.04559174092486501, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.045922823045402766, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.04646054780110717, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.046055870149284604, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.046794873811304566, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.04651506293565035, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0466935664229095, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.04722475638613105, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1205954551696777, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1199543476104736, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1188831329345703, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1178112030029297, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1166820526123047, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1149449348449707, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.112581968307495, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1088027954101562, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.0984277725219727, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.05542254447937, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.905137300491333, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.660958766937256, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.5658347606658936, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.4845001697540283, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.4333620071411133, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.4019367694854736, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.3726584911346436, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.3557889461517334, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.3592283725738525, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.375318765640259, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.4013853073120117, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.4395389556884766, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.4789960384368896, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.510806083679199, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.5790481567382812, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.6276071071624756, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.6953186988830566, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.7715940475463867, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.8871312141418457, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.9538774490356445, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.078700304031372, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.1297073364257812, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.2225170135498047, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.3179240226745605, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.4026148319244385, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.413696527481079, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.4493491649627686, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.4418907165527344, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.455338478088379, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.2623002529144287, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.3510048389434814, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.2689101696014404, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.1171576976776123, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06441491325212255, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06459948320413436, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.0651531930601698, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06607604282022887, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06589147286821706, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06662975267626431, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06718346253229975, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06866002214839424, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.07567368032484312, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.10686600221483943, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.14544112218530822, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.20339608711701734, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.2277593207825766, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.2515688445921004, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.2692875599852344, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.2811000369139904, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.290328534514581, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.29198966408268734, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.2899593946105574, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.28460686600221485, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.28497600590623845, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.2796234772978959, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.2751937984496124, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.26799557032115173, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.2617201919527501, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.25839793281653745, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.25858250276854927, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.24455518641565152, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.2353266888150609, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.23089700996677742, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.2235142118863049, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.21945367294204504, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.21797711332595054, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.21650055370985605, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.2144702842377261, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.21982281284606867, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.22185308231819859, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.2203765227021041, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.21502399409376152, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.2235142118863049, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.2100406053894426, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.2159468438538206, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.22720561092654115, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.008899447662408176, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.009237003662619743, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.009372592588989061, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.010294217554303722, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.010687657894994767, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.011683669816918036, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.013345830591434451, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.014384417782404367, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.021560389834720667, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.047697135921606716, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.06846615943740715, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.11991759133173963, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.144879907215971, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.17461691821045258, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.19771907841947298, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.213037578139917, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.22413827211593573, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.23142011255891637, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.23431403429090622, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.23095833013680425, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.2347932890309273, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.22887469780260897, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.2259603506192749, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.2183642353667973, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.2146162172094772, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.214556307397491, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.21771336932406513, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.20655184847349706, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.1996711941294098, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.19789941505864025, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.19220136936812304, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.18908711512612272, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.19260238894176052, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.18607660560771835, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.18482384128784113, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.18974393199004513, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.19080993243853947, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.18612561157429672, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.18582444615205554, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.19463288372831097, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.17827913615854749, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.1831374433141469, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.19520653892837012, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 17, "lr_best": 9.599999999999999e-05, "wd_best": 0.05, "train/loss_best": 2.142019519805908, "validation/loss_best": 2.3557889461517334, "validation/acc_best": 0.29198966408268734, "validation/f1_best": 0.23142011255891637} +{"epoch": 17, "train/lr": 2.030750443206766e-05, "train/loss": 2.0569606798887254, "train/grad": 0.23744550943374634, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.12098876953125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.119805908203125, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.1178466796875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.11594482421875, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.11410888671875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.1114697265625, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.1080517578125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.10341796875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.0922784423828125, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.050068359375, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.903711242675781, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.6468714904785156, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.536142578125, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.430883598327637, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.346256065368652, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.276611213684082, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.200531177520752, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.120537042617798, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.0427282190322877, "train/loss_019_lr4.4e-01_wd1.0e+00": 1.9793724060058593, "train/loss_020_lr5.2e-01_wd1.0e+00": 1.901770739555359, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.8277873706817627, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.7423556208610536, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.6568649107217788, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.5879032301902771, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.4909128582477569, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.3922739332914353, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.3178979760408402, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.21556399166584, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.1196731853485107, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.050250495672226, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.992724997997284, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.9170170444250106, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.8422713109850883, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.8025717687606811, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.7927049767971038, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.7889603739976883, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.8223499831557274, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.8572460624575615, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.9503255221247673, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.9836594033241272, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.0765504756569861, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.092562608718872, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.171875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.020028265258297324, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.020018789782188833, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.020000784546136855, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.019979177759960293, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.01995489272288978, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.019912179647944867, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.019851659908890724, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.01977133330423385, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.019682039823383093, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.02003863736987114, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.022316826237365604, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.02633284905925393, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.02889045424759388, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.03126844323240221, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.03327260505408049, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.03488186664879322, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.036069576600566505, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.03683853066526353, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.03727872427552938, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.0374685578327626, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.0383517843298614, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.038934826664626596, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.03987683605402708, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.04052207738161087, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.04114010229706764, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.04213954294100404, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.043141449186950925, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.04361106274649501, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.04415163323283196, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.04409212535247207, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.04369290640577674, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0433546738512814, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.043236083406955006, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.043006002474576234, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.04277943581342697, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.04212520020082593, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0423764637298882, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0424774550460279, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.04252372978255153, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.04343591859564185, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.04357416758313775, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.043639236316084865, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.04349926121532917, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1205637454986572, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.119903326034546, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.118849277496338, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1177382469177246, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.116596221923828, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1148202419281006, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1123976707458496, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1084461212158203, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.097594976425171, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.052095651626587, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.897569179534912, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.655850410461426, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.56211256980896, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.4808123111724854, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.4286906719207764, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.396075963973999, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.365365982055664, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.346698760986328, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.347296953201294, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.3616955280303955, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.383817195892334, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.417682409286499, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.4538967609405518, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.4867568016052246, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.55204701423645, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.5961546897888184, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.6640851497650146, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.731579303741455, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.8334391117095947, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.9168670177459717, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.045762062072754, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.106920003890991, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.2203516960144043, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.3182902336120605, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.397367477416992, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.4221255779266357, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.4751474857330322, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.455749750137329, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.507511854171753, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.301663398742676, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.393712282180786, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.2362279891967773, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.1245925426483154, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06423034330011074, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06441491325212255, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06552233296419344, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.0664451827242525, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.0664451827242525, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06662975267626431, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06736803248431156, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.07069029162052418, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.07715023994093761, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.10741971207087486, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.14765596160945, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.20468807678110004, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.22739018087855298, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.25341454411221853, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.2702104097452935, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.2825765965300849, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.29088224437061644, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.29365079365079366, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.29328165374677, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.2886674049464747, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.28811369509043927, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.2842377260981912, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.2794389073458841, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.27260981912144705, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.26208933185677374, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.2622739018087855, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.26098191214470284, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.24916943521594684, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.24067921742340348, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.23292727943890734, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.2279438907345884, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.22517534145441123, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.22056109265411591, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.2117017349575489, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.21668512366186785, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.21668512366186785, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.21797711332595054, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.21613141380583242, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.21834625322997417, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.22296050203026946, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.21133259505352528, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.22443706164636398, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.23403469915097821, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.00893170437489333, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.00926018982815622, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.010186457016827811, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.011187973296198127, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.011342269887621832, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.01238260797819177, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.013807918012279062, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.017139798005617143, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.023245318681864663, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.0487872310528763, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.07119154445134686, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.12127225347120722, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.1455729569838708, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.1746476650969826, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.19808832425987322, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.21598831874317578, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.2246422667119109, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.23421812902627828, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.23812964985032573, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.23567259135824736, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.23827413263432914, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.2350061617986666, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.23062864733662655, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.2239859070015405, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.21730946573790536, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.21962862427744623, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.22028105932442874, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.20999387656726656, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.20581923128322288, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.2012805050967912, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.19799665392289356, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.19533806028426684, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.19470595772373636, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.18443343845680826, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.19047037814697101, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.19028607099817782, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.1891633081216089, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.18714138977909045, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.18948479405951338, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.19124430710203774, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.17963372625201782, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.19127322426525803, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.20290696079415313, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 17, "lr_best": 9.599999999999999e-05, "wd_best": 0.05, "train/loss_best": 2.120537042617798, "validation/loss_best": 2.346698760986328, "validation/acc_best": 0.29365079365079366, "validation/f1_best": 0.23421812902627828} +{"epoch": 18, "train/lr": 7.5829098008590064e-06, "train/loss": 2.042342923283577, "train/grad": 0.2336635208874941, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.122303466796875, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.1210400390625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.1190283203125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.11720703125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.1152490234375, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.11255126953125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.109053955078125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.10432373046875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.092969970703125, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.049658203125, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.9023117065429687, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.650613555908203, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.5402906799316405, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.4335057067871095, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.3481917572021485, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.277461624145508, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.2008423805236816, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.1209777545928956, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.042314863204956, "train/loss_019_lr4.4e-01_wd1.0e+00": 1.9777277994155884, "train/loss_020_lr5.2e-01_wd1.0e+00": 1.896259331703186, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.8202111172676085, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.734729869365692, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.6518127661943436, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.5813793170452117, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.4830810803174972, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.3850913614034652, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.3061419987678529, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.1994607853889465, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.0981773027777673, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.0354770490527152, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.9711161747574806, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.8891595098376274, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.8147465559840202, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.7727298644185067, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.7601498702168464, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.7552794755995274, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.7768283012509346, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.8070386642217636, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.8759394305944442, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.9081455516815186, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.9784058839082718, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.9845710909366607, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.171875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.020147710070014, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.02013630339410156, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.020117551959119736, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.020095118139870465, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.020070109986700117, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.020027424050495027, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.019967294735834, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.01988757916726172, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.0197999574104324, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.020179380825720728, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.02247730859555304, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.026452882038429378, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.028990852627903223, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.03136177652515471, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.033390176538378, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.03502884437330067, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.03623492846265435, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.037000508941709996, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.037435438698157665, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.037616046322509644, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.03842287259176373, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.03896489042788744, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.03985708087682724, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.04053771490231156, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.041118079088628294, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.041981205586344, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.042979764807969334, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.04337927799671888, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.04398018771782517, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0437198337353766, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.04334228007122874, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.04289977915585041, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.042348801307380196, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.04168608326464891, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.04112601375207305, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.04073235884308815, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0408309836499393, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.040902938563376665, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.040593386515975, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.04073244340717792, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.040840696357190606, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.04113635445013642, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.041299747563898564, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1205573081970215, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1199092864990234, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1188387870788574, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1177260875701904, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.116581439971924, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.114795207977295, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1123533248901367, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1083922386169434, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.097404718399048, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.0510289669036865, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.8951356410980225, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.65472149848938, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.5618245601654053, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.481236457824707, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.4298689365386963, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.3982181549072266, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.3682374954223633, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.350510597229004, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.3521182537078857, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.366814613342285, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.390038013458252, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.424316644668579, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.4613521099090576, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.4931492805480957, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.560736894607544, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.6064162254333496, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.677180767059326, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.746286392211914, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.8526551723480225, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.9357495307922363, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.0743093490600586, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.136263132095337, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.240631580352783, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.3455820083618164, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.4361796379089355, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.4654324054718018, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.5023179054260254, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.5027952194213867, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.551886558532715, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.3201894760131836, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.41772723197937, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.296696901321411, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.194005012512207, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06404577334809892, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06459948320413436, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06552233296419344, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06626061277224068, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06662975267626431, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06662975267626431, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06718346253229975, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.0710594315245478, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.07622739018087855, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.1094499815430048, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.14728682170542637, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.20358065706902917, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.22757475083056478, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.25212255444813586, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.2709486895533407, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.28183831672203763, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.29069767441860467, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.29346622369878184, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.29346622369878184, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.2882982650424511, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.2882982650424511, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.28183831672203763, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.27851605758582504, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.27113325950535255, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.2593207825765965, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.26208933185677374, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.2602436323366556, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.24861572535991142, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.24031007751937986, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.23126614987080105, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.22757475083056478, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.2233296419342931, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.21816168327796234, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.2131782945736434, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.21483942414174972, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.2157622739018088, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.2188999630860096, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.21631598375784422, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.21410114433370248, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.22000738279808046, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.21059431524547803, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.21779254337393872, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.23126614987080105, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.008859481432993626, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.009219288754517297, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.010192371673714253, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.01079168592675137, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.011310882421636517, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.012271982981783369, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.013621843520622401, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.017228194260789625, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.02293240749767003, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.049583425839789225, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.0708919511495709, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.12027983535307736, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.14553016229408486, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.17298532014623355, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.198209944924988, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.21432027091410957, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.22443302647855068, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.2333109034198976, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.23730297451111917, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.2346952124385159, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.23791657953226206, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.23215447691524768, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.22959582357920308, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.22244686306795766, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.21391810958741062, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.22049533985365502, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.21884501070708073, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.20955634163923445, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.20425906437352445, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.19789707941672452, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.19638403374025173, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.19360159145405842, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.19215909142027118, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.18397147226151855, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.18638056807788597, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.1862857360475099, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.18799432048895762, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.18646659061419735, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.18198690410282684, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.1892079241122532, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.17843348477331356, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.1866726579723644, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.20158905264250118, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 17, "lr_best": 9.599999999999999e-05, "wd_best": 0.05, "train/loss_best": 2.1209777545928956, "validation/loss_best": 2.350510597229004, "validation/acc_best": 0.29346622369878184, "validation/f1_best": 0.2333109034198976} +{"epoch": 19, "train/lr": 1.0867618231465446e-06, "train/loss": 2.03822489798069, "train/grad": 0.22942182734608652, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.123125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.121981201171875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.1201513671875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.118272705078125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.116453857421875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.11377197265625, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.11038818359375, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.1055615234375, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.09410888671875, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.0503863525390624, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.9023736572265624, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.651497802734375, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.5453733444213866, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.4414249801635743, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.356306343078613, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.2867137718200685, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.212735500335693, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.1342838859558104, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.0561933612823484, "train/loss_019_lr4.4e-01_wd1.0e+00": 1.992533802986145, "train/loss_020_lr5.2e-01_wd1.0e+00": 1.9078973722457886, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.8310049152374268, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.7442336082458496, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.660350056886673, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.5886860477924347, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.4839315336942673, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.383224225640297, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.3028227055072785, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.1957456463575362, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.0962367129325867, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.0237922921776772, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.9590990701317788, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.8739073240756988, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.7929090133309364, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.7595051872730255, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.7397680273652076, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.7350110143423081, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.7583160933852195, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.7695451411604881, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.8493419107794762, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.8616426110267639, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.9311604025959969, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.9400037088990212, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.171875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.019762331298552455, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.01975382826756686, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.0197347210906446, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.01971296393778175, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.01968715901952237, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.019643732313998043, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.019584305086173117, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.019503698660992087, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.01941675449255854, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.01979949928354472, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.022086054468527436, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.026026623100042345, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.028539443351328374, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.030898872865363955, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.032912320839241144, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.03452363590709865, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.035745172230526805, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.03654921534471214, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.037040970399975774, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.03726858151145279, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.038078319570049646, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.0386607962846756, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.039542686361819505, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.04024529453366995, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0408069789968431, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.04170302178710699, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.042458439338952304, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.04283568821847439, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.04324296770617366, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.04303477309644222, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.04280048586428165, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.042243376486003396, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.04161121370270848, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.04084256790578365, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.040112809427082535, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.039572620578110215, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.03957444675266743, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.03959242003038525, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.039471810050308705, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.039572605434805154, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.039562230613082644, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.03980783747509122, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0396171397715807, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.120551586151123, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.119901180267334, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.118812322616577, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1177072525024414, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.116563081741333, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.114783763885498, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.112321615219116, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1083545684814453, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.097357749938965, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.050840377807617, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.8947432041168213, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.6544153690338135, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.5615670680999756, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.481006145477295, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.4295411109924316, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.3978970050811768, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.367794990539551, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.350001811981201, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.3514819145202637, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.366089105606079, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.3896117210388184, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.424342393875122, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.462080478668213, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.494159698486328, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.5625364780426025, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.6084046363830566, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.6793410778045654, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.7482259273529053, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.8568952083587646, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.9365031719207764, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.0719549655914307, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.1330647468566895, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.2378368377685547, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.3512871265411377, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.4340803623199463, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.4646482467651367, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.5059025287628174, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.5055952072143555, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.5501530170440674, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.313755989074707, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.418220281600952, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.307105541229248, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.196719169616699, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06404577334809892, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06441491325212255, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06552233296419344, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06626061277224068, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06662975267626431, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06626061277224068, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06755260243632337, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.0710594315245478, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.07622739018087855, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.10908084163898117, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.14802510151347362, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.2039497969730528, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.22739018087855298, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.25212255444813586, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.2702104097452935, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.28146917681801403, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.29069767441860467, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.2929125138427464, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.2929125138427464, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.2877445551864157, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.2870062753783684, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.28294573643410853, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.27851605758582504, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.2713178294573643, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.26116648209671467, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.2604282022886674, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.2591362126245847, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.24898486526393504, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.24197120708748615, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.23274270948689554, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.22757475083056478, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.22425249169435216, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.21834625322997417, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.2115171650055371, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.2146548541897379, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.2174234034699151, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.2174234034699151, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.21483942414174972, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.21354743447766703, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.2203765227021041, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.21336286452565523, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.21668512366186785, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.22960502030269472, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.008845215938344125, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.009192843055784118, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.010178257635542648, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.010784501412451492, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.011303847134865602, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.012048841001916041, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.013784394915444335, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.017405724953764693, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.022991938251672922, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.04928003705637904, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.07186728777845063, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.12062094691003983, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.14550189296088858, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.1730378089054414, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.1974996705857758, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.2135429887125674, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.2245031137794079, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.23290211406267125, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.23684826878797116, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.23447589025939478, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.23689721900617264, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.23314626758942578, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.22914040589824713, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.2225776926183595, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.21521814139409387, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.21877744411951708, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.21747176158063208, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.20902573241458966, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.20540646801941156, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.19952318773675548, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.19651496693631945, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.1944496825279647, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.19238545897066475, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.18218448472379892, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.18706249838643407, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.18803098556328235, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.18653467588460348, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.18424776728815218, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.1837506449583374, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.19070185858403865, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.1807268609290417, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.18676737193134116, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.2013988486342062, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 17, "lr_best": 9.599999999999999e-05, "wd_best": 0.05, "train/loss_best": 2.1342838859558104, "validation/loss_best": 2.350001811981201, "validation/acc_best": 0.2929125138427464, "validation/f1_best": 0.23290211406267125} diff --git a/input_space_v3/flat_lr1e-3_4/eval_v2/ppmi_dx__patch__logistic/config.yaml b/input_space_v3/flat_lr1e-3_4/eval_v2/ppmi_dx__patch__logistic/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..781e4235249be4e26e3e5f195171d2de01bd8896 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_4/eval_v2/ppmi_dx__patch__logistic/config.yaml @@ -0,0 +1,30 @@ +output_root: experiments/input_space_v3/output +name_prefix: eval_logistic +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_4; eval v2 (ppmi_dx patch logistic) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: input_space_v3/flat_lr1e-3_4/eval_v2/ppmi_dx__patch__logistic +model: flat_mae +representation: patch +dataset: ppmi_dx +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/eval_v2/ppmi_dx__patch__logistic +remote_dir: null diff --git a/input_space_v3/flat_lr1e-3_4/eval_v2/ppmi_dx__patch__logistic/eval_table.csv b/input_space_v3/flat_lr1e-3_4/eval_v2/ppmi_dx__patch__logistic/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..9e0be5ed393ebc34840a7acf18c4612ddb303ba8 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_4/eval_v2/ppmi_dx__patch__logistic/eval_table.csv @@ -0,0 +1,203 @@ +model,repr,clf,dataset,trial,C,split,acc,acc_std,f1,f1_std,bacc,bacc_std +flat_mae,patch,logistic,ppmi_dx,,2.782559402207126,train,0.998220640569395,0.001734363461272658,0.9981248853077089,0.0018246734456279512,0.9985507246376812,0.0014126264713554201 +flat_mae,patch,logistic,ppmi_dx,,2.782559402207126,test,0.61,0.047393919441211026,0.568536342515765,0.05114137577778904,0.5677820677820677,0.04952738025693009 +flat_mae,patch,logistic,ppmi_dx,1,0.3593813663804626,train,0.9199288256227758,0.011236096750610537,0.914218554435094,0.012147917144945463,0.9088792549775209,0.012646352312102684 +flat_mae,patch,logistic,ppmi_dx,1,0.3593813663804626,test,0.62,0.047298050699791,0.5876736111111112,0.052049451353273525,0.5865874363327674,0.050483704414186564 +flat_mae,patch,logistic,ppmi_dx,2,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,2,2.782559402207126,test,0.64,0.04851778642930858,0.6305418719211823,0.04852823468990463,0.6383701188455009,0.049273440614128264 +flat_mae,patch,logistic,ppmi_dx,3,0.3593813663804626,train,0.9092526690391459,0.011861929053672329,0.9025880673611228,0.013029760752742205,0.896729822307857,0.014053561098128694 +flat_mae,patch,logistic,ppmi_dx,3,0.3593813663804626,test,0.58,0.04965430494931934,0.5625,0.05091703274413319,0.564516129032258,0.051525848214614194 +flat_mae,patch,logistic,ppmi_dx,4,0.005994842503189409,train,0.7206405693950177,0.01681822220444415,0.6716935498874439,0.02172370340094279,0.6670145579105117,0.019293767647720103 +flat_mae,patch,logistic,ppmi_dx,4,0.005994842503189409,test,0.64,0.04387370966763582,0.592944369063772,0.04981413557752603,0.5925297113752122,0.04657547166768381 +flat_mae,patch,logistic,ppmi_dx,5,0.3593813663804626,train,0.9181494661921709,0.01144014428471293,0.9120500782472614,0.012549062570324067,0.9056947120530936,0.013424520823354236 +flat_mae,patch,logistic,ppmi_dx,5,0.3593813663804626,test,0.6,0.04975013969829632,0.5755517826825127,0.05210910550949219,0.5755517826825127,0.051784109272281255 +flat_mae,patch,logistic,ppmi_dx,6,0.005994842503189409,train,0.7224199288256228,0.01646485769331022,0.6783623156504512,0.020659505101314177,0.6728082851637764,0.018740797116224835 +flat_mae,patch,logistic,ppmi_dx,6,0.005994842503189409,test,0.63,0.04397153169949849,0.5713127099988413,0.0533487410213919,0.5742784380305602,0.047867037197004976 +flat_mae,patch,logistic,ppmi_dx,7,0.005994842503189409,train,0.7402135231316725,0.01608260415499701,0.694200954084675,0.020693079902524048,0.6872591522157996,0.018530784762682866 +flat_mae,patch,logistic,ppmi_dx,7,0.005994842503189409,test,0.59,0.0462430275825448,0.5464100011063171,0.0521141469170177,0.5471137521222411,0.0495106673275224 +flat_mae,patch,logistic,ppmi_dx,8,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,8,2.782559402207126,test,0.61,0.04598902042879365,0.5793334052421529,0.049091985491988815,0.5785229202037352,0.048346130000912466 +flat_mae,patch,logistic,ppmi_dx,9,0.005994842503189409,train,0.7117437722419929,0.01691553973736353,0.665991635483161,0.02116412112242919,0.6615285806037251,0.019165302441272798 +flat_mae,patch,logistic,ppmi_dx,9,0.005994842503189409,test,0.71,0.03832463437529443,0.6514004087029691,0.05029713966789227,0.648981324278438,0.043828940838985524 +flat_mae,patch,logistic,ppmi_dx,10,10000.0,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,10,10000.0,test,0.56,0.04747248044920341,0.537620849096259,0.04885940103266343,0.5382003395585738,0.04923646638581833 +flat_mae,patch,logistic,ppmi_dx,11,0.046415888336127774,train,0.800711743772242,0.015611980397793383,0.7779314432480491,0.018234379326923834,0.7677023121387283,0.017919872103290373 +flat_mae,patch,logistic,ppmi_dx,11,0.046415888336127774,test,0.66,0.043930508760996606,0.6155585707824514,0.051802594702960926,0.6137521222410866,0.04805280901816001 +flat_mae,patch,logistic,ppmi_dx,12,0.046415888336127774,train,0.798932384341637,0.01582874424944634,0.7762321046641508,0.018463176246769485,0.766257225433526,0.018184205152385363 +flat_mae,patch,logistic,ppmi_dx,12,0.046415888336127774,test,0.6,0.04096270987129636,0.5238095238095238,0.048314422023334296,0.5348047538200339,0.04263348963992996 +flat_mae,patch,logistic,ppmi_dx,13,0.046415888336127774,train,0.8042704626334519,0.015815889523480127,0.7835191618108471,0.018217319470575682,0.774071397987583,0.01803059971931351 +flat_mae,patch,logistic,ppmi_dx,13,0.046415888336127774,test,0.6,0.045559187876870674,0.5659722222222222,0.049580392606025966,0.565365025466893,0.04825482420423608 +flat_mae,patch,logistic,ppmi_dx,14,0.046415888336127774,train,0.800711743772242,0.015333866287601675,0.7811556915374452,0.01736028828311852,0.7729206807964033,0.017225697437699736 +flat_mae,patch,logistic,ppmi_dx,14,0.046415888336127774,test,0.56,0.04634294336789583,0.5164835164835164,0.049466502719712646,0.5178268251273345,0.04750846659103203 +flat_mae,patch,logistic,ppmi_dx,15,0.005994842503189409,train,0.708185053380783,0.016147335760817994,0.6618680754273976,0.020302154064086315,0.657768679083708,0.01835454959214433 +flat_mae,patch,logistic,ppmi_dx,15,0.005994842503189409,test,0.66,0.044476960327792185,0.6212121212121212,0.05051869699747855,0.6188455008488964,0.04795259521723697 +flat_mae,patch,logistic,ppmi_dx,16,0.3593813663804626,train,0.9234875444839857,0.01080483016100067,0.917534286777026,0.011855569141314488,0.9100299721687005,0.01267891083649517 +flat_mae,patch,logistic,ppmi_dx,16,0.3593813663804626,test,0.54,0.04942263044395755,0.5332792207792207,0.049223815283742534,0.5424448217317488,0.05121875276398102 +flat_mae,patch,logistic,ppmi_dx,17,0.005994842503189409,train,0.7188612099644128,0.017046699821305147,0.667982830050403,0.02192795809842584,0.6638300149860843,0.019431696215620412 +flat_mae,patch,logistic,ppmi_dx,17,0.005994842503189409,test,0.62,0.04219703781072791,0.5634191176470589,0.04949735058638369,0.566213921901528,0.04503301474064197 +flat_mae,patch,logistic,ppmi_dx,18,0.046415888336127774,train,0.8131672597864769,0.015620171801238744,0.793106349857478,0.018054255746356693,0.7830362877328195,0.01793492445879502 +flat_mae,patch,logistic,ppmi_dx,18,0.046415888336127774,test,0.6,0.04489658784362126,0.554367201426025,0.05005106576642534,0.5551782682512734,0.04735658780668714 +flat_mae,patch,logistic,ppmi_dx,19,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,19,1291.5496650148827,test,0.51,0.05131329652244143,0.49541756770672435,0.052087133287020214,0.49787775891341257,0.05347407391553084 +flat_mae,patch,logistic,ppmi_dx,20,0.046415888336127774,train,0.7953736654804271,0.01595016681990526,0.7728415022055076,0.01860743853560901,0.7633670520231214,0.018321771185653705 +flat_mae,patch,logistic,ppmi_dx,20,0.046415888336127774,test,0.64,0.042427745638909456,0.5989304812834224,0.04819669460458728,0.597623089983022,0.045378013470464905 +flat_mae,patch,logistic,ppmi_dx,21,0.046415888336127774,train,0.7864768683274022,0.016399328320918744,0.7608408868462488,0.019394491653167575,0.7509232498394348,0.01881229604508761 +flat_mae,patch,logistic,ppmi_dx,21,0.046415888336127774,test,0.67,0.04513362826097631,0.6296711929076422,0.05260436775518508,0.6269100169779287,0.04945728400450095 +flat_mae,patch,logistic,ppmi_dx,22,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,22,166.81005372000556,test,0.57,0.047425714543905394,0.5459824728117411,0.048322654654671955,0.5462648556876061,0.04856133823157859 +flat_mae,patch,logistic,ppmi_dx,23,10000.0,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,23,10000.0,test,0.53,0.04935511726254938,0.5083167695365624,0.050650903265566136,0.5089134125636672,0.051187008478380175 +flat_mae,patch,logistic,ppmi_dx,24,0.005994842503189409,train,0.7135231316725978,0.01690607777880175,0.6705372585431573,0.02072039276069991,0.6655828516377649,0.01898680176204887 +flat_mae,patch,logistic,ppmi_dx,24,0.005994842503189409,test,0.6,0.043882734645871835,0.5238095238095238,0.05233813221418533,0.5348047538200339,0.045801863661114606 +flat_mae,patch,logistic,ppmi_dx,25,0.046415888336127774,train,0.802491103202847,0.01550245252762925,0.7818162740674676,0.017865096906623034,0.7726263112823806,0.017725466877470265 +flat_mae,patch,logistic,ppmi_dx,25,0.046415888336127774,test,0.62,0.039267385958324255,0.5476190476190476,0.04921351211512041,0.5560271646859083,0.04242716212423138 +flat_mae,patch,logistic,ppmi_dx,26,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,26,21.54434690031882,test,0.6,0.049169010565599136,0.5833333333333333,0.050159632192458774,0.5857385398981324,0.05072257011450952 +flat_mae,patch,logistic,ppmi_dx,27,0.005994842503189409,train,0.7153024911032029,0.017056613548825563,0.660381919265168,0.022468609420983943,0.6574609291372298,0.01955452073816665 +flat_mae,patch,logistic,ppmi_dx,27,0.005994842503189409,test,0.65,0.04283118023122874,0.5872154735228211,0.05329529096700738,0.5904074702886248,0.04690936049188944 +flat_mae,patch,logistic,ppmi_dx,28,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,28,166.81005372000556,test,0.61,0.04852720474125828,0.5793334052421529,0.05200523196507221,0.5785229202037352,0.05086440792743379 +flat_mae,patch,logistic,ppmi_dx,29,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,29,166.81005372000556,test,0.58,0.04729486652904308,0.5442708333333334,0.05097609517317862,0.5441426146010186,0.049708373621830546 +flat_mae,patch,logistic,ppmi_dx,30,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,30,2.782559402207126,test,0.62,0.04752839572297807,0.5924495924495925,0.05005700360111766,0.5916808149405772,0.04947948295636848 +flat_mae,patch,logistic,ppmi_dx,31,0.005994842503189409,train,0.7313167259786477,0.01673119325088425,0.6872288748097286,0.021504730561934773,0.6809034467994005,0.019507755729806994 +flat_mae,patch,logistic,ppmi_dx,31,0.005994842503189409,test,0.65,0.046383078811135424,0.6011396011396011,0.05435982251430951,0.6005942275042444,0.049839297286400505 +flat_mae,patch,logistic,ppmi_dx,32,0.3593813663804626,train,0.905693950177936,0.012456977545161958,0.8995491074891324,0.013451692670135199,0.8964488332262899,0.014164240527598395 +flat_mae,patch,logistic,ppmi_dx,32,0.3593813663804626,test,0.63,0.04946271322925988,0.5906626839252129,0.05494710519654508,0.5895585738539898,0.052582131435417484 +flat_mae,patch,logistic,ppmi_dx,33,0.3593813663804626,train,0.9092526690391459,0.011732915827412564,0.9023916796926881,0.012787651117487291,0.8958600941982444,0.013324328086301324 +flat_mae,patch,logistic,ppmi_dx,33,0.3593813663804626,test,0.58,0.049671174739480434,0.5625,0.05118829158122612,0.564516129032258,0.051874332988105475 +flat_mae,patch,logistic,ppmi_dx,34,0.046415888336127774,train,0.8078291814946619,0.016114710109598286,0.785314091680815,0.018898507844901657,0.7743523870691501,0.0185851421903146 +flat_mae,patch,logistic,ppmi_dx,34,0.046415888336127774,test,0.69,0.046400323274735915,0.6693333333333333,0.0502734960864657,0.6685059422750425,0.050456539288698136 +flat_mae,patch,logistic,ppmi_dx,35,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,35,1291.5496650148827,test,0.52,0.04674357282022845,0.5,0.04752019847524233,0.5008488964346349,0.04820086405351377 +flat_mae,patch,logistic,ppmi_dx,36,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,36,21.54434690031882,test,0.67,0.04585753591286823,0.6515679442508711,0.047989542654726616,0.652376910016978,0.04845011025173079 +flat_mae,patch,logistic,ppmi_dx,37,0.046415888336127774,train,0.791814946619217,0.01581513400339354,0.7700225591521956,0.018288853032725347,0.7613466067223293,0.018058619112767526 +flat_mae,patch,logistic,ppmi_dx,37,0.046415888336127774,test,0.61,0.0490424265305052,0.5882166613873931,0.05129910723429107,0.5887096774193548,0.05150028770354294 +flat_mae,patch,logistic,ppmi_dx,38,0.005994842503189409,train,0.7313167259786477,0.01569427255743324,0.6832124472250946,0.020672540094762784,0.6774245343609505,0.018387203072937577 +flat_mae,patch,logistic,ppmi_dx,38,0.005994842503189409,test,0.6,0.046828414451057385,0.554367201426025,0.05333705066985593,0.5551782682512734,0.050247978686448536 +flat_mae,patch,logistic,ppmi_dx,39,0.3593813663804626,train,0.9092526690391459,0.011572045417905316,0.9023916796926881,0.01265063380236597,0.8958600941982444,0.013352626734054445 +flat_mae,patch,logistic,ppmi_dx,39,0.3593813663804626,test,0.68,0.04677867462850994,0.6637242538881883,0.04855402559439483,0.6655348047538201,0.049084462352573875 +flat_mae,patch,logistic,ppmi_dx,40,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,40,166.81005372000556,test,0.66,0.045907576716703306,0.6392190152801358,0.048589915685371084,0.6392190152801358,0.04863241038103311 +flat_mae,patch,logistic,ppmi_dx,41,2.782559402207126,train,0.998220640569395,0.0017177372304111958,0.9981184064710746,0.0018196218203710374,0.9976851851851851,0.0022346488969701207 +flat_mae,patch,logistic,ppmi_dx,41,2.782559402207126,test,0.64,0.04713597352341415,0.6305418719211823,0.04736135987393273,0.6383701188455009,0.04827750855226095 +flat_mae,patch,logistic,ppmi_dx,42,0.3593813663804626,train,0.9217081850533808,0.010953971934697269,0.916206947964813,0.011863707705449785,0.9111940697923357,0.012509579148938762 +flat_mae,patch,logistic,ppmi_dx,42,0.3593813663804626,test,0.66,0.039894540979938595,0.609375,0.04807233293655128,0.6086587436332768,0.04406572034579519 +flat_mae,patch,logistic,ppmi_dx,43,2.782559402207126,train,0.99644128113879,0.002457513757461407,0.9962334964144495,0.0026082681911239977,0.9953703703703703,0.003197043360401175 +flat_mae,patch,logistic,ppmi_dx,43,2.782559402207126,test,0.56,0.048114962329820016,0.5280995280995281,0.04983419637964619,0.5280135823429541,0.04903220662512763 +flat_mae,patch,logistic,ppmi_dx,44,0.005994842503189409,train,0.701067615658363,0.01645540364945813,0.6446090609331948,0.02149521689848223,0.6432910511667738,0.018717024017493894 +flat_mae,patch,logistic,ppmi_dx,44,0.005994842503189409,test,0.64,0.040620192023179805,0.5714285714285714,0.05152690848647162,0.5772495755517827,0.044695370770915045 +flat_mae,patch,logistic,ppmi_dx,45,0.3593813663804626,train,0.9128113879003559,0.012114210930044856,0.9064081431508828,0.01318893814996876,0.9004897238278742,0.013839500754190957 +flat_mae,patch,logistic,ppmi_dx,45,0.3593813663804626,test,0.66,0.04745919931899399,0.6392190152801358,0.05021315755009506,0.6392190152801358,0.050343956688798965 +flat_mae,patch,logistic,ppmi_dx,46,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,46,1291.5496650148827,test,0.55,0.049280953724537425,0.529239460194581,0.05084919232462651,0.5301358234295416,0.051420043984339664 +flat_mae,patch,logistic,ppmi_dx,47,2.782559402207126,train,0.99644128113879,0.0023876086397859246,0.9962400984799828,0.0025224594744998343,0.9962400984799828,0.002592595302239243 +flat_mae,patch,logistic,ppmi_dx,47,2.782559402207126,test,0.73,0.04341768763994693,0.712,0.04622337355571245,0.7109507640067911,0.046231358560916216 +flat_mae,patch,logistic,ppmi_dx,48,0.005994842503189409,train,0.699288256227758,0.0155906701615638,0.6442811503990592,0.020182036818399664,0.6427156925711839,0.01766472085466146 +flat_mae,patch,logistic,ppmi_dx,48,0.005994842503189409,test,0.71,0.04121619099334629,0.6695156695156695,0.04977702463357366,0.6642614601018676,0.04626786956118335 +flat_mae,patch,logistic,ppmi_dx,49,0.3593813663804626,train,0.9039145907473309,0.012231400594247342,0.8969605606258149,0.013289011513246332,0.8915248340826376,0.013872301782389499 +flat_mae,patch,logistic,ppmi_dx,49,0.3593813663804626,test,0.59,0.044616337814751224,0.539894512400404,0.05031765672193286,0.5420203735144312,0.04687457409850877 +flat_mae,patch,logistic,ppmi_dx,50,0.3593813663804626,train,0.9145907473309609,0.011383887193224883,0.9080397076469946,0.012511243063500687,0.9010650824234638,0.01330891709669873 +flat_mae,patch,logistic,ppmi_dx,50,0.3593813663804626,test,0.63,0.044693641605937647,0.5960257670051315,0.048295608930419405,0.5946519524617997,0.046881496663451934 +flat_mae,patch,logistic,ppmi_dx,51,0.046415888336127774,train,0.806049822064057,0.015970319778921462,0.7846932499165247,0.018524441260014183,0.7746467565831727,0.018214561656812032 +flat_mae,patch,logistic,ppmi_dx,51,0.046415888336127774,test,0.6,0.04545096258606631,0.554367201426025,0.050193452269867905,0.5551782682512734,0.04731728394369378 +flat_mae,patch,logistic,ppmi_dx,52,0.3593813663804626,train,0.9270462633451957,0.01110022772440928,0.9218435718186413,0.012066120839649426,0.9163990580175552,0.012775957911917369 +flat_mae,patch,logistic,ppmi_dx,52,0.3593813663804626,test,0.61,0.04666895756281685,0.5741893219783819,0.051241688401817025,0.5734295415959253,0.0497047781055278 +flat_mae,patch,logistic,ppmi_dx,53,0.3593813663804626,train,0.9199288256227758,0.011528422925546409,0.9136986722085154,0.012661572315001673,0.9062700706486834,0.01350165180620303 +flat_mae,patch,logistic,ppmi_dx,53,0.3593813663804626,test,0.66,0.045597276234441896,0.6392190152801358,0.0477876686311327,0.6392190152801358,0.047639926411118 +flat_mae,patch,logistic,ppmi_dx,54,0.046415888336127774,train,0.8096085409252669,0.01590603025132765,0.7891655184261919,0.018331910390436537,0.7792763862128024,0.018047041579748783 +flat_mae,patch,logistic,ppmi_dx,54,0.046415888336127774,test,0.55,0.04827608517682435,0.5146154675870995,0.04995768217592488,0.514855687606112,0.04886694707061412 +flat_mae,patch,logistic,ppmi_dx,55,0.005994842503189409,train,0.7170818505338078,0.015509758688705709,0.6619261108904149,0.021057768120171568,0.658906015842432,0.018202011071767343 +flat_mae,patch,logistic,ppmi_dx,55,0.005994842503189409,test,0.68,0.042975602380885825,0.6323529411764706,0.05126133691246785,0.6298811544991512,0.04697402593861429 +flat_mae,patch,logistic,ppmi_dx,56,0.046415888336127774,train,0.802491103202847,0.015514086203629698,0.7807426673461857,0.018134324252952944,0.7708868550631557,0.017996317091346987 +flat_mae,patch,logistic,ppmi_dx,56,0.046415888336127774,test,0.64,0.047691588356858064,0.6138996138996139,0.050528586781598356,0.6129032258064516,0.04990172887948452 +flat_mae,patch,logistic,ppmi_dx,57,0.3593813663804626,train,0.9288256227758007,0.010442818406727322,0.9238244981498298,0.0113080889343302,0.9187138728323699,0.012023373443064396 +flat_mae,patch,logistic,ppmi_dx,57,0.3593813663804626,test,0.65,0.04773598642533743,0.6224786970121885,0.05188805598397396,0.6209677419354839,0.051148880989393325 +flat_mae,patch,logistic,ppmi_dx,58,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,58,166.81005372000556,test,0.63,0.04609240718383019,0.6009060511271707,0.05010351122643653,0.5997453310696095,0.049417288687227244 +flat_mae,patch,logistic,ppmi_dx,59,0.3593813663804626,train,0.9252669039145908,0.011355587497317226,0.9200157230573214,0.012340611909245541,0.9149539713123528,0.013158647203174589 +flat_mae,patch,logistic,ppmi_dx,59,0.3593813663804626,test,0.62,0.04864208465927422,0.6006725514922235,0.05095520321012889,0.6018675721561969,0.05134860280255502 +flat_mae,patch,logistic,ppmi_dx,60,2.782559402207126,train,0.99644128113879,0.0026271541507642336,0.9962400984799828,0.0027751854526483523,0.9962400984799828,0.0028155214520795163 +flat_mae,patch,logistic,ppmi_dx,60,2.782559402207126,test,0.64,0.046585229418776075,0.6179966044142615,0.049128709923584986,0.6179966044142615,0.049137047664563976 +flat_mae,patch,logistic,ppmi_dx,61,10000.0,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,61,10000.0,test,0.62,0.04823026435755873,0.5967741935483871,0.050854684846121025,0.5967741935483871,0.05090417614141443 +flat_mae,patch,logistic,ppmi_dx,62,0.005994842503189409,train,0.7135231316725978,0.016126807182604057,0.663329054343175,0.020590276667354246,0.6594947548704775,0.018301735457613027 +flat_mae,patch,logistic,ppmi_dx,62,0.005994842503189409,test,0.66,0.03988024072143999,0.5952380952380952,0.051454860644789276,0.5984719864176571,0.044189426823912685 +flat_mae,patch,logistic,ppmi_dx,63,0.005994842503189409,train,0.7330960854092526,0.015048153269832158,0.6878332740846071,0.01936433666748462,0.6814788053949904,0.01736126198965561 +flat_mae,patch,logistic,ppmi_dx,63,0.005994842503189409,test,0.58,0.042384978471151774,0.5,0.05165033434002893,0.5135823429541596,0.04481748011939001 +flat_mae,patch,logistic,ppmi_dx,64,0.046415888336127774,train,0.8096085409252669,0.015331057917263951,0.7911687590074838,0.017488205900600524,0.7827552986512524,0.017563328767006368 +flat_mae,patch,logistic,ppmi_dx,64,0.046415888336127774,test,0.56,0.046729566657524216,0.5164835164835164,0.050528393791093286,0.5178268251273345,0.04866532443855817 +flat_mae,patch,logistic,ppmi_dx,65,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,65,1291.5496650148827,test,0.61,0.04893417619619237,0.6010230179028133,0.04920133314213618,0.6090831918505942,0.05052980995001287 +flat_mae,patch,logistic,ppmi_dx,66,0.005994842503189409,train,0.7188612099644128,0.017415633842149794,0.6742387555946878,0.02167039423254885,0.6690483836437593,0.019649005789742335 +flat_mae,patch,logistic,ppmi_dx,66,0.005994842503189409,test,0.57,0.044296275238444136,0.50997150997151,0.04995604460897377,0.515704584040747,0.045875315451596003 +flat_mae,patch,logistic,ppmi_dx,67,2.782559402207126,train,0.994661921708185,0.003069875149409259,0.9943452231222015,0.0032636235354650206,0.9930555555555556,0.003993680171222231 +flat_mae,patch,logistic,ppmi_dx,67,2.782559402207126,test,0.6,0.04810985761774815,0.5833333333333333,0.04995428129076531,0.5857385398981324,0.05104144476653092 +flat_mae,patch,logistic,ppmi_dx,68,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,68,1291.5496650148827,test,0.63,0.04703702371536703,0.6189887756152817,0.04755477082443265,0.6252122241086587,0.04872158445127203 +flat_mae,patch,logistic,ppmi_dx,69,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,69,166.81005372000556,test,0.63,0.045391629184244976,0.6161427533976553,0.04602523368337439,0.6201188455008488,0.046622016214506394 +flat_mae,patch,logistic,ppmi_dx,70,0.046415888336127774,train,0.802491103202847,0.015396959089715402,0.7807426673461857,0.018007627818497265,0.7708868550631557,0.017826197581498095 +flat_mae,patch,logistic,ppmi_dx,70,0.046415888336127774,test,0.59,0.04375274162838255,0.539894512400404,0.048218014567157234,0.5420203735144312,0.04522896620030593 +flat_mae,patch,logistic,ppmi_dx,71,0.046415888336127774,train,0.8042704626334519,0.014957482495233121,0.7824465090090089,0.01747963772695776,0.772331941768358,0.017302320930621572 +flat_mae,patch,logistic,ppmi_dx,71,0.046415888336127774,test,0.62,0.0425021222999511,0.5558672276764843,0.0504768063972549,0.5611205432937181,0.045110980153174635 +flat_mae,patch,logistic,ppmi_dx,72,0.005994842503189409,train,0.7170818505338078,0.016334207891334752,0.6642128403133984,0.021239397037149263,0.660645472061657,0.01861466756799455 +flat_mae,patch,logistic,ppmi_dx,72,0.005994842503189409,test,0.62,0.04538526633170725,0.5766488413547237,0.04994218721047119,0.5764006791171477,0.047317824783160725 +flat_mae,patch,logistic,ppmi_dx,73,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,73,1291.5496650148827,test,0.6,0.04987850839790621,0.5894909688013137,0.050345980749928715,0.5959252971137521,0.051350058308926944 +flat_mae,patch,logistic,ppmi_dx,74,0.005994842503189409,train,0.7330960854092526,0.016890011139302462,0.6858228980322003,0.021683606221414947,0.6797393491757653,0.019407336875930013 +flat_mae,patch,logistic,ppmi_dx,74,0.005994842503189409,test,0.56,0.04462912053805228,0.5024875621890548,0.049693122374499486,0.5076400679117148,0.04624676461292729 +flat_mae,patch,logistic,ppmi_dx,75,10000.0,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,75,10000.0,test,0.66,0.04587668688996624,0.6458333333333333,0.047115339423441205,0.6494057724957556,0.04758088294256994 +flat_mae,patch,logistic,ppmi_dx,76,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,76,21.54434690031882,test,0.57,0.049557768311335404,0.5501621508525996,0.05101314906189665,0.551358234295416,0.05174522341161498 +flat_mae,patch,logistic,ppmi_dx,77,2.782559402207126,train,0.99644128113879,0.002507508260166147,0.9962400984799828,0.002648810236460271,0.9962400984799828,0.002690527546409099 +flat_mae,patch,logistic,ppmi_dx,77,2.782559402207126,test,0.56,0.0474736811296533,0.5280995280995281,0.050352896895572354,0.5280135823429541,0.04962049112082636 +flat_mae,patch,logistic,ppmi_dx,78,0.005994842503189409,train,0.7241992882562278,0.016944683558057796,0.6779369627507164,0.021774427803492858,0.6725139156497538,0.019595962964796466 +flat_mae,patch,logistic,ppmi_dx,78,0.005994842503189409,test,0.6,0.041471585453175044,0.5143273433705683,0.05107348367947676,0.5297113752122241,0.04369158348354373 +flat_mae,patch,logistic,ppmi_dx,79,0.046415888336127774,train,0.8113879003558719,0.015095318612541226,0.7898279730740463,0.01763779162923399,0.7789820166987798,0.01747305121546019 +flat_mae,patch,logistic,ppmi_dx,79,0.046415888336127774,test,0.67,0.04314672641116588,0.6239316239316239,0.05190951110493285,0.6218166383701189,0.04747207761906044 +flat_mae,patch,logistic,ppmi_dx,80,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,80,1291.5496650148827,test,0.56,0.04756006307817515,0.5331069609507639,0.049590085593935726,0.5331069609507639,0.0493841075477599 +flat_mae,patch,logistic,ppmi_dx,81,0.3593813663804626,train,0.895017793594306,0.01285983869152711,0.8873077642020835,0.013971685475340697,0.8816902162277884,0.014454764932645105 +flat_mae,patch,logistic,ppmi_dx,81,0.3593813663804626,test,0.58,0.045238474775350236,0.5543293718166383,0.0476192043975315,0.5543293718166383,0.04753141155594379 +flat_mae,patch,logistic,ppmi_dx,82,0.046415888336127774,train,0.7846975088967971,0.016543364049882794,0.7597807003599651,0.019612568913018876,0.750347891243845,0.01922249421284669 +flat_mae,patch,logistic,ppmi_dx,82,0.046415888336127774,test,0.62,0.04544683047254232,0.5824175824175825,0.05094637909964512,0.5814940577249575,0.04864499004119412 +flat_mae,patch,logistic,ppmi_dx,83,0.3593813663804626,train,0.9128113879003559,0.011307969037441051,0.9065935370515469,0.012312204470817172,0.9013594519374866,0.013102705937173161 +flat_mae,patch,logistic,ppmi_dx,83,0.3593813663804626,test,0.53,0.04796556681620681,0.49304282170208175,0.05039089849247147,0.4936332767402377,0.04956618904628858 +flat_mae,patch,logistic,ppmi_dx,84,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,84,21.54434690031882,test,0.6,0.04864787354037173,0.586606035551881,0.04996174551450363,0.5908319185059423,0.05148149025005648 +flat_mae,patch,logistic,ppmi_dx,85,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,85,166.81005372000556,test,0.63,0.04568082310992218,0.6053333333333333,0.048099530831192644,0.6048387096774194,0.04767318366258757 +flat_mae,patch,logistic,ppmi_dx,86,10000.0,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,86,10000.0,test,0.59,0.04594394845896464,0.5523528769516323,0.049416858332719645,0.5522071307300509,0.047706879945515625 +flat_mae,patch,logistic,ppmi_dx,87,0.046415888336127774,train,0.7846975088967971,0.016540831475101752,0.7615796984071889,0.019100676299996743,0.7529570755726824,0.018819840168478846 +flat_mae,patch,logistic,ppmi_dx,87,0.046415888336127774,test,0.6,0.04707695827047453,0.554367201426025,0.052770596677267176,0.5551782682512734,0.04997164158428638 +flat_mae,patch,logistic,ppmi_dx,88,0.005994842503189409,train,0.7241992882562278,0.016692317153627755,0.6779369627507164,0.021080417076565775,0.6725139156497538,0.018960285765917906 +flat_mae,patch,logistic,ppmi_dx,88,0.005994842503189409,test,0.62,0.042450177855928944,0.5476190476190476,0.05221704684854594,0.5560271646859083,0.04519718696045576 +flat_mae,patch,logistic,ppmi_dx,89,0.3593813663804626,train,0.900355871886121,0.012312408180169156,0.8924916307986609,0.01353910492733582,0.8851557482337828,0.014219668994563025 +flat_mae,patch,logistic,ppmi_dx,89,0.3593813663804626,test,0.63,0.0471771809246801,0.6009060511271707,0.05081394152256589,0.5997453310696095,0.049934867080921354 +flat_mae,patch,logistic,ppmi_dx,90,0.005994842503189409,train,0.708185053380783,0.015533518807973544,0.6586977129991705,0.019134099470923392,0.6551594947548705,0.017195217067290425 +flat_mae,patch,logistic,ppmi_dx,90,0.005994842503189409,test,0.63,0.04306989203608479,0.5847828526540231,0.04942980747137949,0.5844651952461799,0.04613697479383344 +flat_mae,patch,logistic,ppmi_dx,91,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,91,21.54434690031882,test,0.62,0.048339979313193754,0.6006725514922235,0.05016560959018808,0.6018675721561969,0.05047632457516007 +flat_mae,patch,logistic,ppmi_dx,92,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,92,21.54434690031882,test,0.58,0.04657835978219929,0.5495495495495495,0.04890292209346623,0.5492359932088284,0.048195071051957535 +flat_mae,patch,logistic,ppmi_dx,93,0.3593813663804626,train,0.9128113879003559,0.011871645030280265,0.9062194569596415,0.01295904660467904,0.8996199957182616,0.013600044731220642 +flat_mae,patch,logistic,ppmi_dx,93,0.3593813663804626,test,0.56,0.045750908187707044,0.5331069609507639,0.0475495597460503,0.5331069609507639,0.04750557029548722 +flat_mae,patch,logistic,ppmi_dx,94,0.046415888336127774,train,0.7882562277580071,0.016319173045002452,0.766091320847105,0.01872368715993037,0.7575867052023122,0.01835770235809345 +flat_mae,patch,logistic,ppmi_dx,94,0.046415888336127774,test,0.69,0.04550521288819556,0.6656239887822242,0.04968565719542421,0.6634125636672326,0.049147535864312024 +flat_mae,patch,logistic,ppmi_dx,95,0.046415888336127774,train,0.8113879003558719,0.015487035444717013,0.7918954796338993,0.01789918180560416,0.7824609291372298,0.017912065202277772 +flat_mae,patch,logistic,ppmi_dx,95,0.046415888336127774,test,0.6,0.04059424097085693,0.5238095238095238,0.048790728683175515,0.5348047538200339,0.04261723768214771 +flat_mae,patch,logistic,ppmi_dx,96,0.005994842503189409,train,0.7295373665480427,0.016986424962187777,0.6884927870239363,0.021549710765720244,0.6820675444230357,0.019796411174489655 +flat_mae,patch,logistic,ppmi_dx,96,0.005994842503189409,test,0.54,0.04190873894547532,0.4875222816399287,0.045279152480338404,0.4915110356536503,0.042896420994033846 +flat_mae,patch,logistic,ppmi_dx,97,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,97,1291.5496650148827,test,0.55,0.05039563076299373,0.5477841422972565,0.050145370305178925,0.5657894736842105,0.051591211674435686 +flat_mae,patch,logistic,ppmi_dx,98,0.3593813663804626,train,0.9110320284697508,0.011538305585702801,0.9047806226872874,0.012481297607739038,0.8999143652322843,0.013100521212339629 +flat_mae,patch,logistic,ppmi_dx,98,0.3593813663804626,test,0.59,0.04472806277942294,0.5464100011063171,0.051291200850262855,0.5471137521222411,0.04847007553790394 +flat_mae,patch,logistic,ppmi_dx,99,0.046415888336127774,train,0.8113879003558719,0.015360253062587566,0.7903575450450451,0.017783852899143995,0.7798517448083921,0.017570935154585045 +flat_mae,patch,logistic,ppmi_dx,99,0.046415888336127774,test,0.59,0.04442220615863197,0.5523528769516323,0.048646302652127445,0.5522071307300509,0.04675420137765336 +flat_mae,patch,logistic,ppmi_dx,100,0.046415888336127774,train,0.7829181494661922,0.015568164669231187,0.7599030703720304,0.017958806149477164,0.7515119888674802,0.017655305200657785 +flat_mae,patch,logistic,ppmi_dx,100,0.046415888336127774,test,0.59,0.046644510931083835,0.5626666666666666,0.050046566083895856,0.5623938879456706,0.04968779821996857 diff --git a/input_space_v3/flat_lr1e-3_4/eval_v2/ppmi_dx__patch__logistic/log.txt b/input_space_v3/flat_lr1e-3_4/eval_v2/ppmi_dx__patch__logistic/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..a65a0172582232ba0ec900834171c4a024822e33 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_4/eval_v2/ppmi_dx__patch__logistic/log.txt @@ -0,0 +1,247 @@ +fMRI foundation model logistic probe eval +version: 0.1.dev86+gf97f52698 +sha: bcce2b486277d3a5b520775efd9cdf1a2affce36, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-04-08 22:23:30 +config: +output_root: experiments/input_space_v3/output +name_prefix: eval_logistic +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_4; eval v2 (ppmi_dx patch logistic) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: input_space_v3/flat_lr1e-3_4/eval_v2/ppmi_dx__patch__logistic +model: flat_mae +representation: patch +dataset: ppmi_dx +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/eval_v2/ppmi_dx__patch__logistic +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=True, reg_tokens=0, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: ppmi_dx (flat) +train (n=463): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'dir', 'sex', 'age', 'age_bin', 'dx', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 463 +}), + labels=['PD' 'Prodromal'], + counts=[178 285] +) + +validation (n=99): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'dir', 'sex', 'age', 'age_bin', 'dx', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 99 +}), + labels=['PD' 'Prodromal'], + counts=[39 60] +) + +test (n=100): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'dir', 'sex', 'age', 'age_bin', 'dx', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 100 +}), + labels=['PD' 'Prodromal'], + counts=[37 63] +) + +extracting features for all splits +extract (train) [ 0/232] eta: 0:19:05 time: 4.9381 data: 3.8702 max mem: 2698 +extract (train) [ 20/232] eta: 0:01:37 time: 0.2380 data: 0.0962 max mem: 2851 +extract (train) [ 40/232] eta: 0:01:02 time: 0.1869 data: 0.0663 max mem: 2851 +extract (train) [ 60/232] eta: 0:00:48 time: 0.1853 data: 0.0649 max mem: 2851 +extract (train) [ 80/232] eta: 0:00:39 time: 0.2011 data: 0.0718 max mem: 2851 +extract (train) [100/232] eta: 0:00:32 time: 0.1986 data: 0.0731 max mem: 2851 +extract (train) [120/232] eta: 0:00:26 time: 0.1869 data: 0.0626 max mem: 2851 +extract (train) [140/232] eta: 0:00:21 time: 0.1898 data: 0.0689 max mem: 2851 +extract (train) [160/232] eta: 0:00:16 time: 0.1941 data: 0.0639 max mem: 2851 +extract (train) [180/232] eta: 0:00:11 time: 0.1951 data: 0.0673 max mem: 2851 +extract (train) [200/232] eta: 0:00:06 time: 0.1712 data: 0.0569 max mem: 2851 +extract (train) [220/232] eta: 0:00:02 time: 0.1674 data: 0.0540 max mem: 2851 +extract (train) [231/232] eta: 0:00:00 time: 0.1663 data: 0.0546 max mem: 2851 +extract (train) Total time: 0:00:49 (0.2135 s / it) +extract (validation) [ 0/50] eta: 0:03:35 time: 4.3193 data: 4.1006 max mem: 2851 +extract (validation) [20/50] eta: 0:00:12 time: 0.2330 data: 0.0865 max mem: 2851 +extract (validation) [40/50] eta: 0:00:02 time: 0.1597 data: 0.0492 max mem: 2851 +extract (validation) [49/50] eta: 0:00:00 time: 0.1608 data: 0.0527 max mem: 2851 +extract (validation) Total time: 0:00:14 (0.2801 s / it) +extract (test) [ 0/50] eta: 0:03:16 time: 3.9283 data: 3.6908 max mem: 2851 +extract (test) [20/50] eta: 0:00:12 time: 0.2335 data: 0.0816 max mem: 2851 +extract (test) [40/50] eta: 0:00:02 time: 0.1596 data: 0.0497 max mem: 2851 +extract (test) [49/50] eta: 0:00:00 time: 0.1645 data: 0.0529 max mem: 2851 +extract (test) Total time: 0:00:13 (0.2738 s / it) +feature extraction time: 0:01:17 +train features: (463, 768) +validation features: (99, 768) +test features: (100, 768) +evaluating fixed splits +eval results (fixed splits): + +| model | repr | clf | dataset | trial | C | split | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|-------:|:--------|--------:|----------:|--------:|----------:|--------:|-----------:| +| flat_mae | patch | logistic | ppmi_dx | | 2.7826 | train | 0.99822 | 0.0017344 | 0.99812 | 0.0018247 | 0.99855 | 0.0014126 | +| flat_mae | patch | logistic | ppmi_dx | | 2.7826 | test | 0.61 | 0.047394 | 0.56854 | 0.051141 | 0.56778 | 0.049527 | + + +evaluating random splits (n=100) +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 1, "C": 0.3593813663804626, "split": "test", "acc": 0.62, "acc_std": 0.047298050699791, "f1": 0.5876736111111112, "f1_std": 0.052049451353273525, "bacc": 0.5865874363327674, "bacc_std": 0.050483704414186564} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 2, "C": 2.782559402207126, "split": "test", "acc": 0.64, "acc_std": 0.04851778642930858, "f1": 0.6305418719211823, "f1_std": 0.04852823468990463, "bacc": 0.6383701188455009, "bacc_std": 0.049273440614128264} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 3, "C": 0.3593813663804626, "split": "test", "acc": 0.58, "acc_std": 0.04965430494931934, "f1": 0.5625, "f1_std": 0.05091703274413319, "bacc": 0.564516129032258, "bacc_std": 0.051525848214614194} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 4, "C": 0.005994842503189409, "split": "test", "acc": 0.64, "acc_std": 0.04387370966763582, "f1": 0.592944369063772, "f1_std": 0.04981413557752603, "bacc": 0.5925297113752122, "bacc_std": 0.04657547166768381} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 5, "C": 0.3593813663804626, "split": "test", "acc": 0.6, "acc_std": 0.04975013969829632, "f1": 0.5755517826825127, "f1_std": 0.05210910550949219, "bacc": 0.5755517826825127, "bacc_std": 0.051784109272281255} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 6, "C": 0.005994842503189409, "split": "test", "acc": 0.63, "acc_std": 0.04397153169949849, "f1": 0.5713127099988413, "f1_std": 0.0533487410213919, "bacc": 0.5742784380305602, "bacc_std": 0.047867037197004976} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 7, "C": 0.005994842503189409, "split": "test", "acc": 0.59, "acc_std": 0.0462430275825448, "f1": 0.5464100011063171, "f1_std": 0.0521141469170177, "bacc": 0.5471137521222411, "bacc_std": 0.0495106673275224} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 8, "C": 2.782559402207126, "split": "test", "acc": 0.61, "acc_std": 0.04598902042879365, "f1": 0.5793334052421529, "f1_std": 0.049091985491988815, "bacc": 0.5785229202037352, "bacc_std": 0.048346130000912466} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 9, "C": 0.005994842503189409, "split": "test", "acc": 0.71, "acc_std": 0.03832463437529443, "f1": 0.6514004087029691, "f1_std": 0.05029713966789227, "bacc": 0.648981324278438, "bacc_std": 0.043828940838985524} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 10, "C": 10000.0, "split": "test", "acc": 0.56, "acc_std": 0.04747248044920341, "f1": 0.537620849096259, "f1_std": 0.04885940103266343, "bacc": 0.5382003395585738, "bacc_std": 0.04923646638581833} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 11, "C": 0.046415888336127774, "split": "test", "acc": 0.66, "acc_std": 0.043930508760996606, "f1": 0.6155585707824514, "f1_std": 0.051802594702960926, "bacc": 0.6137521222410866, "bacc_std": 0.04805280901816001} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 12, "C": 0.046415888336127774, "split": "test", "acc": 0.6, "acc_std": 0.04096270987129636, "f1": 0.5238095238095238, "f1_std": 0.048314422023334296, "bacc": 0.5348047538200339, "bacc_std": 0.04263348963992996} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 13, "C": 0.046415888336127774, "split": "test", "acc": 0.6, "acc_std": 0.045559187876870674, "f1": 0.5659722222222222, "f1_std": 0.049580392606025966, "bacc": 0.565365025466893, "bacc_std": 0.04825482420423608} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 14, "C": 0.046415888336127774, "split": "test", "acc": 0.56, "acc_std": 0.04634294336789583, "f1": 0.5164835164835164, "f1_std": 0.049466502719712646, "bacc": 0.5178268251273345, "bacc_std": 0.04750846659103203} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 15, "C": 0.005994842503189409, "split": "test", "acc": 0.66, "acc_std": 0.044476960327792185, "f1": 0.6212121212121212, "f1_std": 0.05051869699747855, "bacc": 0.6188455008488964, "bacc_std": 0.04795259521723697} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 16, "C": 0.3593813663804626, "split": "test", "acc": 0.54, "acc_std": 0.04942263044395755, "f1": 0.5332792207792207, "f1_std": 0.049223815283742534, "bacc": 0.5424448217317488, "bacc_std": 0.05121875276398102} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 17, "C": 0.005994842503189409, "split": "test", "acc": 0.62, "acc_std": 0.04219703781072791, "f1": 0.5634191176470589, "f1_std": 0.04949735058638369, "bacc": 0.566213921901528, "bacc_std": 0.04503301474064197} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 18, "C": 0.046415888336127774, "split": "test", "acc": 0.6, "acc_std": 0.04489658784362126, "f1": 0.554367201426025, "f1_std": 0.05005106576642534, "bacc": 0.5551782682512734, "bacc_std": 0.04735658780668714} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 19, "C": 1291.5496650148827, "split": "test", "acc": 0.51, "acc_std": 0.05131329652244143, "f1": 0.49541756770672435, "f1_std": 0.052087133287020214, "bacc": 0.49787775891341257, "bacc_std": 0.05347407391553084} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 20, "C": 0.046415888336127774, "split": "test", "acc": 0.64, "acc_std": 0.042427745638909456, "f1": 0.5989304812834224, "f1_std": 0.04819669460458728, "bacc": 0.597623089983022, "bacc_std": 0.045378013470464905} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 21, "C": 0.046415888336127774, "split": "test", "acc": 0.67, "acc_std": 0.04513362826097631, "f1": 0.6296711929076422, "f1_std": 0.05260436775518508, "bacc": 0.6269100169779287, "bacc_std": 0.04945728400450095} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 22, "C": 166.81005372000556, "split": "test", "acc": 0.57, "acc_std": 0.047425714543905394, "f1": 0.5459824728117411, "f1_std": 0.048322654654671955, "bacc": 0.5462648556876061, "bacc_std": 0.04856133823157859} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 23, "C": 10000.0, "split": "test", "acc": 0.53, "acc_std": 0.04935511726254938, "f1": 0.5083167695365624, "f1_std": 0.050650903265566136, "bacc": 0.5089134125636672, "bacc_std": 0.051187008478380175} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 24, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.043882734645871835, "f1": 0.5238095238095238, "f1_std": 0.05233813221418533, "bacc": 0.5348047538200339, "bacc_std": 0.045801863661114606} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 25, "C": 0.046415888336127774, "split": "test", "acc": 0.62, "acc_std": 0.039267385958324255, "f1": 0.5476190476190476, "f1_std": 0.04921351211512041, "bacc": 0.5560271646859083, "bacc_std": 0.04242716212423138} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 26, "C": 21.54434690031882, "split": "test", "acc": 0.6, "acc_std": 0.049169010565599136, "f1": 0.5833333333333333, "f1_std": 0.050159632192458774, "bacc": 0.5857385398981324, "bacc_std": 0.05072257011450952} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 27, "C": 0.005994842503189409, "split": "test", "acc": 0.65, "acc_std": 0.04283118023122874, "f1": 0.5872154735228211, "f1_std": 0.05329529096700738, "bacc": 0.5904074702886248, "bacc_std": 0.04690936049188944} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 28, "C": 166.81005372000556, "split": "test", "acc": 0.61, "acc_std": 0.04852720474125828, "f1": 0.5793334052421529, "f1_std": 0.05200523196507221, "bacc": 0.5785229202037352, "bacc_std": 0.05086440792743379} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 29, "C": 166.81005372000556, "split": "test", "acc": 0.58, "acc_std": 0.04729486652904308, "f1": 0.5442708333333334, "f1_std": 0.05097609517317862, "bacc": 0.5441426146010186, "bacc_std": 0.049708373621830546} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 30, "C": 2.782559402207126, "split": "test", "acc": 0.62, "acc_std": 0.04752839572297807, "f1": 0.5924495924495925, "f1_std": 0.05005700360111766, "bacc": 0.5916808149405772, "bacc_std": 0.04947948295636848} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 31, "C": 0.005994842503189409, "split": "test", "acc": 0.65, "acc_std": 0.046383078811135424, "f1": 0.6011396011396011, "f1_std": 0.05435982251430951, "bacc": 0.6005942275042444, "bacc_std": 0.049839297286400505} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 32, "C": 0.3593813663804626, "split": "test", "acc": 0.63, "acc_std": 0.04946271322925988, "f1": 0.5906626839252129, "f1_std": 0.05494710519654508, "bacc": 0.5895585738539898, "bacc_std": 0.052582131435417484} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 33, "C": 0.3593813663804626, "split": "test", "acc": 0.58, "acc_std": 0.049671174739480434, "f1": 0.5625, "f1_std": 0.05118829158122612, "bacc": 0.564516129032258, "bacc_std": 0.051874332988105475} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 34, "C": 0.046415888336127774, "split": "test", "acc": 0.69, "acc_std": 0.046400323274735915, "f1": 0.6693333333333333, "f1_std": 0.0502734960864657, "bacc": 0.6685059422750425, "bacc_std": 0.050456539288698136} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 35, "C": 1291.5496650148827, "split": "test", "acc": 0.52, "acc_std": 0.04674357282022845, "f1": 0.5, "f1_std": 0.04752019847524233, "bacc": 0.5008488964346349, "bacc_std": 0.04820086405351377} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 36, "C": 21.54434690031882, "split": "test", "acc": 0.67, "acc_std": 0.04585753591286823, "f1": 0.6515679442508711, "f1_std": 0.047989542654726616, "bacc": 0.652376910016978, "bacc_std": 0.04845011025173079} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 37, "C": 0.046415888336127774, "split": "test", "acc": 0.61, "acc_std": 0.0490424265305052, "f1": 0.5882166613873931, "f1_std": 0.05129910723429107, "bacc": 0.5887096774193548, "bacc_std": 0.05150028770354294} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 38, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.046828414451057385, "f1": 0.554367201426025, "f1_std": 0.05333705066985593, "bacc": 0.5551782682512734, "bacc_std": 0.050247978686448536} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 39, "C": 0.3593813663804626, "split": "test", "acc": 0.68, "acc_std": 0.04677867462850994, "f1": 0.6637242538881883, "f1_std": 0.04855402559439483, "bacc": 0.6655348047538201, "bacc_std": 0.049084462352573875} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 40, "C": 166.81005372000556, "split": "test", "acc": 0.66, "acc_std": 0.045907576716703306, "f1": 0.6392190152801358, "f1_std": 0.048589915685371084, "bacc": 0.6392190152801358, "bacc_std": 0.04863241038103311} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 41, "C": 2.782559402207126, "split": "test", "acc": 0.64, "acc_std": 0.04713597352341415, "f1": 0.6305418719211823, "f1_std": 0.04736135987393273, "bacc": 0.6383701188455009, "bacc_std": 0.04827750855226095} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 42, "C": 0.3593813663804626, "split": "test", "acc": 0.66, "acc_std": 0.039894540979938595, "f1": 0.609375, "f1_std": 0.04807233293655128, "bacc": 0.6086587436332768, "bacc_std": 0.04406572034579519} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 43, "C": 2.782559402207126, "split": "test", "acc": 0.56, "acc_std": 0.048114962329820016, "f1": 0.5280995280995281, "f1_std": 0.04983419637964619, "bacc": 0.5280135823429541, "bacc_std": 0.04903220662512763} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 44, "C": 0.005994842503189409, "split": "test", "acc": 0.64, "acc_std": 0.040620192023179805, "f1": 0.5714285714285714, "f1_std": 0.05152690848647162, "bacc": 0.5772495755517827, "bacc_std": 0.044695370770915045} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 45, "C": 0.3593813663804626, "split": "test", "acc": 0.66, "acc_std": 0.04745919931899399, "f1": 0.6392190152801358, "f1_std": 0.05021315755009506, "bacc": 0.6392190152801358, "bacc_std": 0.050343956688798965} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 46, "C": 1291.5496650148827, "split": "test", "acc": 0.55, "acc_std": 0.049280953724537425, "f1": 0.529239460194581, "f1_std": 0.05084919232462651, "bacc": 0.5301358234295416, "bacc_std": 0.051420043984339664} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 47, "C": 2.782559402207126, "split": "test", "acc": 0.73, "acc_std": 0.04341768763994693, "f1": 0.712, "f1_std": 0.04622337355571245, "bacc": 0.7109507640067911, "bacc_std": 0.046231358560916216} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 48, "C": 0.005994842503189409, "split": "test", "acc": 0.71, "acc_std": 0.04121619099334629, "f1": 0.6695156695156695, "f1_std": 0.04977702463357366, "bacc": 0.6642614601018676, "bacc_std": 0.04626786956118335} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 49, "C": 0.3593813663804626, "split": "test", "acc": 0.59, "acc_std": 0.044616337814751224, "f1": 0.539894512400404, "f1_std": 0.05031765672193286, "bacc": 0.5420203735144312, "bacc_std": 0.04687457409850877} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 50, "C": 0.3593813663804626, "split": "test", "acc": 0.63, "acc_std": 0.044693641605937647, "f1": 0.5960257670051315, "f1_std": 0.048295608930419405, "bacc": 0.5946519524617997, "bacc_std": 0.046881496663451934} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 51, "C": 0.046415888336127774, "split": "test", "acc": 0.6, "acc_std": 0.04545096258606631, "f1": 0.554367201426025, "f1_std": 0.050193452269867905, "bacc": 0.5551782682512734, "bacc_std": 0.04731728394369378} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 52, "C": 0.3593813663804626, "split": "test", "acc": 0.61, "acc_std": 0.04666895756281685, "f1": 0.5741893219783819, "f1_std": 0.051241688401817025, "bacc": 0.5734295415959253, "bacc_std": 0.0497047781055278} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 53, "C": 0.3593813663804626, "split": "test", "acc": 0.66, "acc_std": 0.045597276234441896, "f1": 0.6392190152801358, "f1_std": 0.0477876686311327, "bacc": 0.6392190152801358, "bacc_std": 0.047639926411118} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 54, "C": 0.046415888336127774, "split": "test", "acc": 0.55, "acc_std": 0.04827608517682435, "f1": 0.5146154675870995, "f1_std": 0.04995768217592488, "bacc": 0.514855687606112, "bacc_std": 0.04886694707061412} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 55, "C": 0.005994842503189409, "split": "test", "acc": 0.68, "acc_std": 0.042975602380885825, "f1": 0.6323529411764706, "f1_std": 0.05126133691246785, "bacc": 0.6298811544991512, "bacc_std": 0.04697402593861429} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 56, "C": 0.046415888336127774, "split": "test", "acc": 0.64, "acc_std": 0.047691588356858064, "f1": 0.6138996138996139, "f1_std": 0.050528586781598356, "bacc": 0.6129032258064516, "bacc_std": 0.04990172887948452} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 57, "C": 0.3593813663804626, "split": "test", "acc": 0.65, "acc_std": 0.04773598642533743, "f1": 0.6224786970121885, "f1_std": 0.05188805598397396, "bacc": 0.6209677419354839, "bacc_std": 0.051148880989393325} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 58, "C": 166.81005372000556, "split": "test", "acc": 0.63, "acc_std": 0.04609240718383019, "f1": 0.6009060511271707, "f1_std": 0.05010351122643653, "bacc": 0.5997453310696095, "bacc_std": 0.049417288687227244} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 59, "C": 0.3593813663804626, "split": "test", "acc": 0.62, "acc_std": 0.04864208465927422, "f1": 0.6006725514922235, "f1_std": 0.05095520321012889, "bacc": 0.6018675721561969, "bacc_std": 0.05134860280255502} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 60, "C": 2.782559402207126, "split": "test", "acc": 0.64, "acc_std": 0.046585229418776075, "f1": 0.6179966044142615, "f1_std": 0.049128709923584986, "bacc": 0.6179966044142615, "bacc_std": 0.049137047664563976} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 61, "C": 10000.0, "split": "test", "acc": 0.62, "acc_std": 0.04823026435755873, "f1": 0.5967741935483871, "f1_std": 0.050854684846121025, "bacc": 0.5967741935483871, "bacc_std": 0.05090417614141443} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 62, "C": 0.005994842503189409, "split": "test", "acc": 0.66, "acc_std": 0.03988024072143999, "f1": 0.5952380952380952, "f1_std": 0.051454860644789276, "bacc": 0.5984719864176571, "bacc_std": 0.044189426823912685} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 63, "C": 0.005994842503189409, "split": "test", "acc": 0.58, "acc_std": 0.042384978471151774, "f1": 0.5, "f1_std": 0.05165033434002893, "bacc": 0.5135823429541596, "bacc_std": 0.04481748011939001} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 64, "C": 0.046415888336127774, "split": "test", "acc": 0.56, "acc_std": 0.046729566657524216, "f1": 0.5164835164835164, "f1_std": 0.050528393791093286, "bacc": 0.5178268251273345, "bacc_std": 0.04866532443855817} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 65, "C": 1291.5496650148827, "split": "test", "acc": 0.61, "acc_std": 0.04893417619619237, "f1": 0.6010230179028133, "f1_std": 0.04920133314213618, "bacc": 0.6090831918505942, "bacc_std": 0.05052980995001287} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 66, "C": 0.005994842503189409, "split": "test", "acc": 0.57, "acc_std": 0.044296275238444136, "f1": 0.50997150997151, "f1_std": 0.04995604460897377, "bacc": 0.515704584040747, "bacc_std": 0.045875315451596003} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 67, "C": 2.782559402207126, "split": "test", "acc": 0.6, "acc_std": 0.04810985761774815, "f1": 0.5833333333333333, "f1_std": 0.04995428129076531, "bacc": 0.5857385398981324, "bacc_std": 0.05104144476653092} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 68, "C": 1291.5496650148827, "split": "test", "acc": 0.63, "acc_std": 0.04703702371536703, "f1": 0.6189887756152817, "f1_std": 0.04755477082443265, "bacc": 0.6252122241086587, "bacc_std": 0.04872158445127203} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 69, "C": 166.81005372000556, "split": "test", "acc": 0.63, "acc_std": 0.045391629184244976, "f1": 0.6161427533976553, "f1_std": 0.04602523368337439, "bacc": 0.6201188455008488, "bacc_std": 0.046622016214506394} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 70, "C": 0.046415888336127774, "split": "test", "acc": 0.59, "acc_std": 0.04375274162838255, "f1": 0.539894512400404, "f1_std": 0.048218014567157234, "bacc": 0.5420203735144312, "bacc_std": 0.04522896620030593} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 71, "C": 0.046415888336127774, "split": "test", "acc": 0.62, "acc_std": 0.0425021222999511, "f1": 0.5558672276764843, "f1_std": 0.0504768063972549, "bacc": 0.5611205432937181, "bacc_std": 0.045110980153174635} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 72, "C": 0.005994842503189409, "split": "test", "acc": 0.62, "acc_std": 0.04538526633170725, "f1": 0.5766488413547237, "f1_std": 0.04994218721047119, "bacc": 0.5764006791171477, "bacc_std": 0.047317824783160725} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 73, "C": 1291.5496650148827, "split": "test", "acc": 0.6, "acc_std": 0.04987850839790621, "f1": 0.5894909688013137, "f1_std": 0.050345980749928715, "bacc": 0.5959252971137521, "bacc_std": 0.051350058308926944} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 74, "C": 0.005994842503189409, "split": "test", "acc": 0.56, "acc_std": 0.04462912053805228, "f1": 0.5024875621890548, "f1_std": 0.049693122374499486, "bacc": 0.5076400679117148, "bacc_std": 0.04624676461292729} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 75, "C": 10000.0, "split": "test", "acc": 0.66, "acc_std": 0.04587668688996624, "f1": 0.6458333333333333, "f1_std": 0.047115339423441205, "bacc": 0.6494057724957556, "bacc_std": 0.04758088294256994} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 76, "C": 21.54434690031882, "split": "test", "acc": 0.57, "acc_std": 0.049557768311335404, "f1": 0.5501621508525996, "f1_std": 0.05101314906189665, "bacc": 0.551358234295416, "bacc_std": 0.05174522341161498} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 77, "C": 2.782559402207126, "split": "test", "acc": 0.56, "acc_std": 0.0474736811296533, "f1": 0.5280995280995281, "f1_std": 0.050352896895572354, "bacc": 0.5280135823429541, "bacc_std": 0.04962049112082636} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 78, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.041471585453175044, "f1": 0.5143273433705683, "f1_std": 0.05107348367947676, "bacc": 0.5297113752122241, "bacc_std": 0.04369158348354373} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 79, "C": 0.046415888336127774, "split": "test", "acc": 0.67, "acc_std": 0.04314672641116588, "f1": 0.6239316239316239, "f1_std": 0.05190951110493285, "bacc": 0.6218166383701189, "bacc_std": 0.04747207761906044} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 80, "C": 1291.5496650148827, "split": "test", "acc": 0.56, "acc_std": 0.04756006307817515, "f1": 0.5331069609507639, "f1_std": 0.049590085593935726, "bacc": 0.5331069609507639, "bacc_std": 0.0493841075477599} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 81, "C": 0.3593813663804626, "split": "test", "acc": 0.58, "acc_std": 0.045238474775350236, "f1": 0.5543293718166383, "f1_std": 0.0476192043975315, "bacc": 0.5543293718166383, "bacc_std": 0.04753141155594379} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 82, "C": 0.046415888336127774, "split": "test", "acc": 0.62, "acc_std": 0.04544683047254232, "f1": 0.5824175824175825, "f1_std": 0.05094637909964512, "bacc": 0.5814940577249575, "bacc_std": 0.04864499004119412} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 83, "C": 0.3593813663804626, "split": "test", "acc": 0.53, "acc_std": 0.04796556681620681, "f1": 0.49304282170208175, "f1_std": 0.05039089849247147, "bacc": 0.4936332767402377, "bacc_std": 0.04956618904628858} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 84, "C": 21.54434690031882, "split": "test", "acc": 0.6, "acc_std": 0.04864787354037173, "f1": 0.586606035551881, "f1_std": 0.04996174551450363, "bacc": 0.5908319185059423, "bacc_std": 0.05148149025005648} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 85, "C": 166.81005372000556, "split": "test", "acc": 0.63, "acc_std": 0.04568082310992218, "f1": 0.6053333333333333, "f1_std": 0.048099530831192644, "bacc": 0.6048387096774194, "bacc_std": 0.04767318366258757} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 86, "C": 10000.0, "split": "test", "acc": 0.59, "acc_std": 0.04594394845896464, "f1": 0.5523528769516323, "f1_std": 0.049416858332719645, "bacc": 0.5522071307300509, "bacc_std": 0.047706879945515625} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 87, "C": 0.046415888336127774, "split": "test", "acc": 0.6, "acc_std": 0.04707695827047453, "f1": 0.554367201426025, "f1_std": 0.052770596677267176, "bacc": 0.5551782682512734, "bacc_std": 0.04997164158428638} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 88, "C": 0.005994842503189409, "split": "test", "acc": 0.62, "acc_std": 0.042450177855928944, "f1": 0.5476190476190476, "f1_std": 0.05221704684854594, "bacc": 0.5560271646859083, "bacc_std": 0.04519718696045576} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 89, "C": 0.3593813663804626, "split": "test", "acc": 0.63, "acc_std": 0.0471771809246801, "f1": 0.6009060511271707, "f1_std": 0.05081394152256589, "bacc": 0.5997453310696095, "bacc_std": 0.049934867080921354} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 90, "C": 0.005994842503189409, "split": "test", "acc": 0.63, "acc_std": 0.04306989203608479, "f1": 0.5847828526540231, "f1_std": 0.04942980747137949, "bacc": 0.5844651952461799, "bacc_std": 0.04613697479383344} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 91, "C": 21.54434690031882, "split": "test", "acc": 0.62, "acc_std": 0.048339979313193754, "f1": 0.6006725514922235, "f1_std": 0.05016560959018808, "bacc": 0.6018675721561969, "bacc_std": 0.05047632457516007} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 92, "C": 21.54434690031882, "split": "test", "acc": 0.58, "acc_std": 0.04657835978219929, "f1": 0.5495495495495495, "f1_std": 0.04890292209346623, "bacc": 0.5492359932088284, "bacc_std": 0.048195071051957535} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 93, "C": 0.3593813663804626, "split": "test", "acc": 0.56, "acc_std": 0.045750908187707044, "f1": 0.5331069609507639, "f1_std": 0.0475495597460503, "bacc": 0.5331069609507639, "bacc_std": 0.04750557029548722} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 94, "C": 0.046415888336127774, "split": "test", "acc": 0.69, "acc_std": 0.04550521288819556, "f1": 0.6656239887822242, "f1_std": 0.04968565719542421, "bacc": 0.6634125636672326, "bacc_std": 0.049147535864312024} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 95, "C": 0.046415888336127774, "split": "test", "acc": 0.6, "acc_std": 0.04059424097085693, "f1": 0.5238095238095238, "f1_std": 0.048790728683175515, "bacc": 0.5348047538200339, "bacc_std": 0.04261723768214771} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 96, "C": 0.005994842503189409, "split": "test", "acc": 0.54, "acc_std": 0.04190873894547532, "f1": 0.4875222816399287, "f1_std": 0.045279152480338404, "bacc": 0.4915110356536503, "bacc_std": 0.042896420994033846} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 97, "C": 1291.5496650148827, "split": "test", "acc": 0.55, "acc_std": 0.05039563076299373, "f1": 0.5477841422972565, "f1_std": 0.050145370305178925, "bacc": 0.5657894736842105, "bacc_std": 0.051591211674435686} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 98, "C": 0.3593813663804626, "split": "test", "acc": 0.59, "acc_std": 0.04472806277942294, "f1": 0.5464100011063171, "f1_std": 0.051291200850262855, "bacc": 0.5471137521222411, "bacc_std": 0.04847007553790394} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 99, "C": 0.046415888336127774, "split": "test", "acc": 0.59, "acc_std": 0.04442220615863197, "f1": 0.5523528769516323, "f1_std": 0.048646302652127445, "bacc": 0.5522071307300509, "bacc_std": 0.04675420137765336} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 100, "C": 0.046415888336127774, "split": "test", "acc": 0.59, "acc_std": 0.046644510931083835, "f1": 0.5626666666666666, "f1_std": 0.050046566083895856, "bacc": 0.5623938879456706, "bacc_std": 0.04968779821996857} +eval results (random splits): + +| model | repr | clf | dataset | split | n_trials | C | C_std | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|-----------:|-------:|--------:|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | ppmi_dx | train | 100 | 616.63 | 2191.6 | 0.87504 | 0.11177 | 0.85814 | 0.12979 | 0.85373 | 0.13214 | +| flat_mae | patch | logistic | ppmi_dx | test | 100 | 616.63 | 2191.6 | 0.6117 | 0.043718 | 0.57612 | 0.046521 | 0.57796 | 0.045152 | + + +done! total time: 0:05:41 diff --git a/input_space_v3/flat_lr1e-3_4/pretrain/config.yaml b/input_space_v3/flat_lr1e-3_4/pretrain/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..884f297c8e34a95faf735ee48e0d8460e409663d --- /dev/null +++ b/input_space_v3/flat_lr1e-3_4/pretrain/config.yaml @@ -0,0 +1,102 @@ +name: input_space_v3/flat_lr1e-3_4/pretrain +notes: input_space ablation v3 flat_lr1e-3_4; use tube masking and on-disk data (input_space=flat + base_lr=1e-3 seed=5404) +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain +input_space: flat +patch_size: 16 +num_frames: 16 +t_patch_size: 4 +mask_ratio: 0.9 +pred_mask_ratio: null +masking: tube +masking_kwargs: {} +mask_patch_size: null +model: mae_vit_base +model_kwargs: + decoding: attn + pos_embed: sep + target_norm: null + pca_norm_nc: 2 + t_pred_stride: 2 + no_decode_pos: true + mask_drop_scale: false + pred_edge_pad: 0 + gauss_sigma: null + class_token: true + reg_tokens: 0 + no_embed_class: true + head_init_scale: 0.0 + decoder_depth: 4 + drop_path_rate: 0.0 +datasets: + hcp-train: + type: wds + url: /data/fmri-datasets/pretrain/hcpya-all.${input_space}.wds/hcpya-all-${input_space}-{00000..01799}.tar + clipping: random + clipping_kwargs: + oversample: 4.0 + shuffle: true + buffer_size: 2000 + samples_per_epoch: 200000 + hcp-train-subset: + type: arrow + root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/validation + split_range: + - 0 + - 2000 + shuffle: false + hcp-val: + type: arrow + root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/test + split_range: + - 0 + - 2000 + shuffle: false +train_dataset: hcp-train +eval_datasets: +- hcp-train-subset +- hcp-val +val_dataset: null +clip_vmax: 3.0 +normalize: frame +tr_scale: null +crop_scale: null +crop_aspect: null +gray_jitter: null +num_workers: 16 +epochs: 100 +batch_size: 32 +accum_iter: 1 +base_lr: 0.001 +min_lr: 0.0 +warmup_epochs: 5 +weight_decay: 0.05 +betas: +- 0.9 +- 0.95 +clip_grad: 1.0 +amp: true +amp_dtype: float16 +ckpt: null +resume: true +auto_resume: true +start_epoch: 0 +max_checkpoints: 0 +checkpoint_period: null +plot_period: 5 +device: cuda +presend_cuda: false +seed: 5404 +debug: false +wandb: true +wandb_entity: null +wandb_project: fMRI-foundation-model +rank: 0 +world_size: 1 +gpu: 0 +distributed: true +dist_backend: nccl +in_chans: 1 +img_size: +- 224 +- 560 diff --git a/input_space_v3/flat_lr1e-3_4/pretrain/log.json b/input_space_v3/flat_lr1e-3_4/pretrain/log.json new file mode 100644 index 0000000000000000000000000000000000000000..aa02ffe11bf56d4e4f398ccd9d7e32ee48019dc1 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_4/pretrain/log.json @@ -0,0 +1,100 @@ +{"epoch": 0, "train/lr": 1.2502400076802458e-05, "train/grad": 0.05533447358638048, "train/loss": 0.9930924163722992, "eval/hcp-train-subset/loss": 0.9912968556727132, "eval/hcp-val/loss": 0.989311215377623} +{"epoch": 1, "train/lr": 3.750320010240327e-05, "train/grad": 0.08391206737577915, "train/loss": 0.9878561900901794, "eval/hcp-train-subset/loss": 0.9886729823004815, "eval/hcp-val/loss": 0.9867541674644716} +{"epoch": 2, "train/lr": 6.250400012800409e-05, "train/grad": 0.1383059476794396, "train/loss": 0.9842744696521759, "eval/hcp-train-subset/loss": 0.9832060558180655, "eval/hcp-val/loss": 0.9807951546484425} +{"epoch": 3, "train/lr": 8.75048001536049e-05, "train/grad": 0.19060097027367853, "train/loss": 0.9763669386959076, "eval/hcp-train-subset/loss": 0.9726549502341978, "eval/hcp-val/loss": 0.9695684188796628} +{"epoch": 4, "train/lr": 0.00011250559953918529, "train/grad": 0.22382276319653124, "train/loss": 0.9403738222026825, "eval/hcp-train-subset/loss": 0.921580389622719, "eval/hcp-val/loss": 0.9161708979837356} +{"epoch": 5, "train/lr": 0.00012498860637884563, "train/grad": 0.1545719953823868, "train/loss": 0.8947214577960968, "eval/hcp-train-subset/loss": 0.8816276779097896, "eval/hcp-val/loss": 0.8751786860727495} +{"epoch": 6, "train/lr": 0.0001249202705377922, "train/grad": 0.10154224222981029, "train/loss": 0.8701003664970398, "eval/hcp-train-subset/loss": 0.8688244387026756, "eval/hcp-val/loss": 0.8631981072887298} +{"epoch": 7, "train/lr": 0.0001247836790473516, "train/grad": 0.08226887091271762, "train/loss": 0.8611033162212371, "eval/hcp-train-subset/loss": 0.8614417131870024, "eval/hcp-val/loss": 0.8559990169540528} +{"epoch": 8, "train/lr": 0.000124578981268311, "train/grad": 0.07651515462329651, "train/loss": 0.8553389493083954, "eval/hcp-train-subset/loss": 0.8587204650525124, "eval/hcp-val/loss": 0.8531090001906118} +{"epoch": 9, "train/lr": 0.00012430640103468907, "train/grad": 0.0717336810068746, "train/loss": 0.8513933673477173, "eval/hcp-train-subset/loss": 0.8567620996505984, "eval/hcp-val/loss": 0.8510793168698588} +{"epoch": 10, "train/lr": 0.00012396623640896796, "train/grad": 0.0668356239912566, "train/loss": 0.8498458914852143, "eval/hcp-train-subset/loss": 0.853909344442429, "eval/hcp-val/loss": 0.8485763515195539} +{"epoch": 11, "train/lr": 0.0001235588593561712, "train/grad": 0.06692646450283203, "train/loss": 0.8475174546337128, "eval/hcp-train-subset/loss": 0.8521621746401633, "eval/hcp-val/loss": 0.8470978967605098} +{"epoch": 12, "train/lr": 0.00012308471533712604, "train/grad": 0.0654907862872367, "train/loss": 0.8460949534702301, "eval/hcp-train-subset/loss": 0.8510863723293427, "eval/hcp-val/loss": 0.8458763111022211} +{"epoch": 13, "train/lr": 0.00012254432282135565, "train/grad": 0.06634134563690608, "train/loss": 0.8423127371692658, "eval/hcp-train-subset/loss": 0.8508973121643066, "eval/hcp-val/loss": 0.8444965279871418} +{"epoch": 14, "train/lr": 0.00012193827272014171, "train/grad": 0.06556032114052876, "train/loss": 0.8419490751361847, "eval/hcp-train-subset/loss": 0.8488847382606999, "eval/hcp-val/loss": 0.8441805493447089} +{"epoch": 15, "train/lr": 0.00012126722774037197, "train/grad": 0.06550764944404364, "train/loss": 0.8404914642429352, "eval/hcp-train-subset/loss": 0.8478023640571102, "eval/hcp-val/loss": 0.8429637147534278} +{"epoch": 16, "train/lr": 0.00012053192165988122, "train/grad": 0.0651132609829989, "train/loss": 0.840811936674118, "eval/hcp-train-subset/loss": 0.848435640335083, "eval/hcp-val/loss": 0.8438753552975193} +{"epoch": 17, "train/lr": 0.00011973315852507104, "train/grad": 0.06523762673919326, "train/loss": 0.8388416962909698, "eval/hcp-train-subset/loss": 0.8469950239504537, "eval/hcp-val/loss": 0.8424061921335035} +{"epoch": 18, "train/lr": 0.00011887181177170142, "train/grad": 0.06429995705734126, "train/loss": 0.8391895041179657, "eval/hcp-train-subset/loss": 0.8480640765159361, "eval/hcp-val/loss": 0.8430174579543452} +{"epoch": 19, "train/lr": 0.00011794882326980209, "train/grad": 0.06525909814270507, "train/loss": 0.8379783389377594, "eval/hcp-train-subset/loss": 0.8465355192461321, "eval/hcp-val/loss": 0.8422796005202878} +{"epoch": 20, "train/lr": 0.00011696520229374954, "train/grad": 0.06641525229577466, "train/loss": 0.8372295559692383, "eval/hcp-train-subset/loss": 0.8441942218811281, "eval/hcp-val/loss": 0.8405599863298477} +{"epoch": 21, "train/lr": 0.00011592202441863837, "train/grad": 0.06594362728654317, "train/loss": 0.835794668636322, "eval/hcp-train-subset/loss": 0.8448022623215953, "eval/hcp-val/loss": 0.8410233682201754} +{"epoch": 22, "train/lr": 0.00011482043034415979, "train/grad": 0.06862620031543115, "train/loss": 0.8336268263626099, "eval/hcp-train-subset/loss": 0.8442424343478295, "eval/hcp-val/loss": 0.8407128482095657} +{"epoch": 23, "train/lr": 0.00011366162464726024, "train/grad": 0.06962583993565143, "train/loss": 0.8332118748378754, "eval/hcp-train-subset/loss": 0.8442149210360742, "eval/hcp-val/loss": 0.8404594207963636} +{"epoch": 24, "train/lr": 0.0001124468744649569, "train/grad": 0.06823224373184453, "train/loss": 0.8329527437400818, "eval/hcp-train-subset/loss": 0.8442787951038729, "eval/hcp-val/loss": 0.8396805399848569} +{"epoch": 25, "train/lr": 0.0001111775081087387, "train/grad": 0.06879111554201754, "train/loss": 0.8314972941207885, "eval/hcp-train-subset/loss": 0.8443817794322968, "eval/hcp-val/loss": 0.8396993962026411} +{"epoch": 26, "train/lr": 0.0001098549136120796, "train/grad": 0.07020146504614536, "train/loss": 0.8313671863651275, "eval/hcp-train-subset/loss": 0.8445488743243679, "eval/hcp-val/loss": 0.8408727645874023} +{"epoch": 27, "train/lr": 0.00010848053721264312, "train/grad": 0.07132602783358834, "train/loss": 0.8316064676380157, "eval/hcp-train-subset/loss": 0.8420806902070199, "eval/hcp-val/loss": 0.8401183303325407} +{"epoch": 28, "train/lr": 0.00010705588177084458, "train/grad": 0.07164048944017458, "train/loss": 0.830835812292099, "eval/hcp-train-subset/loss": 0.843340245946761, "eval/hcp-val/loss": 0.83995109604251} +{"epoch": 29, "train/lr": 0.00010558250512649171, "train/grad": 0.07027064665624927, "train/loss": 0.8319271492481232, "eval/hcp-train-subset/loss": 0.8423013600610918, "eval/hcp-val/loss": 0.8393549678787109} +{"epoch": 30, "train/lr": 0.00010406201839531515, "train/grad": 0.07370320322269036, "train/loss": 0.8291786096477508, "eval/hcp-train-subset/loss": 0.8422604299360706, "eval/hcp-val/loss": 0.8388674182276572} +{"epoch": 31, "train/lr": 0.00010249608420723018, "train/grad": 0.07450212833737518, "train/loss": 0.8292374034404755, "eval/hcp-train-subset/loss": 0.8425175547599792, "eval/hcp-val/loss": 0.8393969516600331} +{"epoch": 32, "train/lr": 0.00010088641488828097, "train/grad": 0.07553913724571752, "train/loss": 0.8266897689437867, "eval/hcp-train-subset/loss": 0.8428657977811752, "eval/hcp-val/loss": 0.8391075961051448} +{"epoch": 33, "train/lr": 9.923477058823526e-05, "train/grad": 0.07523614289978384, "train/loss": 0.827858913936615, "eval/hcp-train-subset/loss": 0.8425159492800313, "eval/hcp-val/loss": 0.8388157111983146} +{"epoch": 34, "train/lr": 9.754295735588547e-05, "train/grad": 0.07562385809818872, "train/loss": 0.8277278977489472, "eval/hcp-train-subset/loss": 0.8406776516668258, "eval/hcp-val/loss": 0.8386756893127195} +{"epoch": 35, "train/lr": 9.581282516416285e-05, "train/grad": 0.07664324662063586, "train/loss": 0.8280160926151275, "eval/hcp-train-subset/loss": 0.8420304819460838, "eval/hcp-val/loss": 0.8383946611035255} +{"epoch": 36, "train/lr": 9.404626588721676e-05, "train/grad": 0.07846873772191063, "train/loss": 0.8259001286125183, "eval/hcp-train-subset/loss": 0.8414395038158663, "eval/hcp-val/loss": 0.838596070966413} +{"epoch": 37, "train/lr": 9.224521123168153e-05, "train/grad": 0.07763620031555608, "train/loss": 0.8297320222568512, "eval/hcp-train-subset/loss": 0.8416743009321151, "eval/hcp-val/loss": 0.8382650036965648} +{"epoch": 38, "train/lr": 9.041163062437843e-05, "train/grad": 0.07885176537882789, "train/loss": 0.8280405394363404, "eval/hcp-train-subset/loss": 0.8406265253020871, "eval/hcp-val/loss": 0.8380139623918841} +{"epoch": 39, "train/lr": 8.85475290587822e-05, "train/grad": 0.08151843017755575, "train/loss": 0.8230533289146423, "eval/hcp-train-subset/loss": 0.8393497178631444, "eval/hcp-val/loss": 0.8378531038761139} +{"epoch": 40, "train/lr": 8.665494490258622e-05, "train/grad": 0.07939945536675312, "train/loss": 0.8258130892562866, "eval/hcp-train-subset/loss": 0.8399407267570496, "eval/hcp-val/loss": 0.8370935791923154} +{"epoch": 41, "train/lr": 8.473594766877838e-05, "train/grad": 0.07936728923019885, "train/loss": 0.8260231077289582, "eval/hcp-train-subset/loss": 0.8391206360632374, "eval/hcp-val/loss": 0.8363639250878365} +{"epoch": 42, "train/lr": 8.279263575265999e-05, "train/grad": 0.08190966816619039, "train/loss": 0.8235299810218811, "eval/hcp-train-subset/loss": 0.8399032633150777, "eval/hcp-val/loss": 0.8369301538313588} +{"epoch": 43, "train/lr": 8.082713413727944e-05, "train/grad": 0.084200338860197, "train/loss": 0.8235112336540222, "eval/hcp-train-subset/loss": 0.8387547616035708, "eval/hcp-val/loss": 0.8375832111604752} +{"epoch": 44, "train/lr": 7.884159206979602e-05, "train/grad": 0.0830977411395944, "train/loss": 0.8249004804515838, "eval/hcp-train-subset/loss": 0.8396103391724248, "eval/hcp-val/loss": 0.8363674984824273} +{"epoch": 45, "train/lr": 7.683818071130916e-05, "train/grad": 0.0854039743295829, "train/loss": 0.8222189091587067, "eval/hcp-train-subset/loss": 0.8384868146911744, "eval/hcp-val/loss": 0.836184028656252} +{"epoch": 46, "train/lr": 7.481909076272522e-05, "train/grad": 0.0876212709329345, "train/loss": 0.8217266815948486, "eval/hcp-train-subset/loss": 0.8385413731298139, "eval/hcp-val/loss": 0.8369255854237464} +{"epoch": 47, "train/lr": 7.278653006925963e-05, "train/grad": 0.08814526077898913, "train/loss": 0.8215711711788177, "eval/hcp-train-subset/loss": 0.8369505213152978, "eval/hcp-val/loss": 0.8363799808486816} +{"epoch": 48, "train/lr": 7.074272120618864e-05, "train/grad": 0.088685040117722, "train/loss": 0.822554184217453, "eval/hcp-train-subset/loss": 0.8367213645289021, "eval/hcp-val/loss": 0.8361171176356654} +{"epoch": 49, "train/lr": 6.868989904849677e-05, "train/grad": 0.09037731971146393, "train/loss": 0.8199715783977508, "eval/hcp-train-subset/loss": 0.8377106564660226, "eval/hcp-val/loss": 0.8361673124374882} +{"epoch": 50, "train/lr": 6.6630308327075e-05, "train/grad": 0.09039561191076696, "train/loss": 0.8214357493591309, "eval/hcp-train-subset/loss": 0.8380205621642451, "eval/hcp-val/loss": 0.8364362043719138} +{"epoch": 51, "train/lr": 6.456620117413798e-05, "train/grad": 0.09169149294939183, "train/loss": 0.8218050577449798, "eval/hcp-train-subset/loss": 0.8360304409457792, "eval/hcp-val/loss": 0.8357712770662} +{"epoch": 52, "train/lr": 6.249983466055255e-05, "train/grad": 0.09271776657867634, "train/loss": 0.8211146333503723, "eval/hcp-train-subset/loss": 0.8358399983375303, "eval/hcp-val/loss": 0.8358760726067328} +{"epoch": 53, "train/lr": 6.0433468327763305e-05, "train/grad": 0.09387991521170681, "train/loss": 0.8192809750270843, "eval/hcp-train-subset/loss": 0.8340433259164134, "eval/hcp-val/loss": 0.8349214657660453} +{"epoch": 54, "train/lr": 5.83693617170174e-05, "train/grad": 0.0953246072562042, "train/loss": 0.8170196450519561, "eval/hcp-train-subset/loss": 0.8351905874667629, "eval/hcp-val/loss": 0.8346621701794286} +{"epoch": 55, "train/lr": 5.6309771898588165e-05, "train/grad": 0.09631874774929694, "train/loss": 0.8167040483379364, "eval/hcp-train-subset/loss": 0.8356035188321145, "eval/hcp-val/loss": 0.8355199819610964} +{"epoch": 56, "train/lr": 5.4256951003704155e-05, "train/grad": 0.09293519399772837, "train/loss": 0.821392041349411, "eval/hcp-train-subset/loss": 0.8346059274288916, "eval/hcp-val/loss": 0.8348350938289396} +{"epoch": 57, "train/lr": 5.221314376187425e-05, "train/grad": 0.09683102945094778, "train/loss": 0.8187312764167786, "eval/hcp-train-subset/loss": 0.8318045302744834, "eval/hcp-val/loss": 0.8339386793874926} +{"epoch": 58, "train/lr": 5.018058504631059e-05, "train/grad": 0.09818152143262786, "train/loss": 0.8187781263637542, "eval/hcp-train-subset/loss": 0.8346268544273991, "eval/hcp-val/loss": 0.8350284868671048} +{"epoch": 59, "train/lr": 4.816149743012713e-05, "train/grad": 0.09884940604709838, "train/loss": 0.8174002976226806, "eval/hcp-train-subset/loss": 0.8337448835372925, "eval/hcp-val/loss": 0.8341850311525406} +{"epoch": 60, "train/lr": 4.615808875598772e-05, "train/grad": 0.10174455646027199, "train/loss": 0.8166092649364471, "eval/hcp-train-subset/loss": 0.833458169814079, "eval/hcp-val/loss": 0.833863720778496} +{"epoch": 61, "train/lr": 4.417254972186445e-05, "train/grad": 0.10422802601103232, "train/loss": 0.8160079890727997, "eval/hcp-train-subset/loss": 0.8307790592793496, "eval/hcp-val/loss": 0.8337717863821215} +{"epoch": 62, "train/lr": 4.220705148553925e-05, "train/grad": 0.10718155963629919, "train/loss": 0.8150474112701416, "eval/hcp-train-subset/loss": 0.8307391837719948, "eval/hcp-val/loss": 0.8335160305423122} +{"epoch": 63, "train/lr": 4.026374329047657e-05, "train/grad": 0.10594841130686, "train/loss": 0.8159284983634949, "eval/hcp-train-subset/loss": 0.8303468554250656, "eval/hcp-val/loss": 0.8336086725035021} +{"epoch": 64, "train/lr": 3.834475011565652e-05, "train/grad": 0.10957480089502855, "train/loss": 0.814084182844162, "eval/hcp-train-subset/loss": 0.8297987782186077, "eval/hcp-val/loss": 0.832929907306548} +{"epoch": 65, "train/lr": 3.6452170351940815e-05, "train/grad": 0.10848905169378953, "train/loss": 0.8152549633312225, "eval/hcp-train-subset/loss": 0.8295287893664453, "eval/hcp-val/loss": 0.8328039290443543} +{"epoch": 66, "train/lr": 3.458807350751516e-05, "train/grad": 0.11183716048787433, "train/loss": 0.8129189240264892, "eval/hcp-train-subset/loss": 0.8286280478200605, "eval/hcp-val/loss": 0.8327211593427966} +{"epoch": 67, "train/lr": 3.2754497944910164e-05, "train/grad": 0.11547506357752815, "train/loss": 0.8131504543972016, "eval/hcp-train-subset/loss": 0.8273537985740169, "eval/hcp-val/loss": 0.8324306847587708} +{"epoch": 68, "train/lr": 3.0953448652083367e-05, "train/grad": 0.11392314264416695, "train/loss": 0.8127087122917175, "eval/hcp-train-subset/loss": 0.827389657497406, "eval/hcp-val/loss": 0.8329645914416159} +{"epoch": 69, "train/lr": 2.9186895049993948e-05, "train/grad": 0.11387722740793335, "train/loss": 0.815506285572052, "eval/hcp-train-subset/loss": 0.8288525410236851, "eval/hcp-val/loss": 0.8322332020728819} +{"epoch": 70, "train/lr": 2.7456768839068717e-05, "train/grad": 0.116186565609241, "train/loss": 0.813529797153473, "eval/hcp-train-subset/loss": 0.826981246471405, "eval/hcp-val/loss": 0.8322053320946232} +{"epoch": 71, "train/lr": 2.5764961886919063e-05, "train/grad": 0.11739886305610937, "train/loss": 0.8131012540912628, "eval/hcp-train-subset/loss": 0.8269004177662634, "eval/hcp-val/loss": 0.8324553312793854} +{"epoch": 72, "train/lr": 2.411332415960724e-05, "train/grad": 0.11864937675130928, "train/loss": 0.8142891863727569, "eval/hcp-train-subset/loss": 0.8270934108764895, "eval/hcp-val/loss": 0.8317270769226935} +{"epoch": 73, "train/lr": 2.2503661698739544e-05, "train/grad": 0.12064065124300546, "train/loss": 0.8127869230175019, "eval/hcp-train-subset/loss": 0.8263399947074151, "eval/hcp-val/loss": 0.8315378100641312} +{"epoch": 74, "train/lr": 2.0937734646583902e-05, "train/grad": 0.12314410275027213, "train/loss": 0.8117776647186279, "eval/hcp-train-subset/loss": 0.8261025913300053, "eval/hcp-val/loss": 0.831335808000257} +{"epoch": 75, "train/lr": 1.9417255321381202e-05, "train/grad": 0.12343440479291083, "train/loss": 0.8121683115768432, "eval/hcp-train-subset/loss": 0.8259463242946132, "eval/hcp-val/loss": 0.8313401591393256} +{"epoch": 76, "train/lr": 1.7943886344950134e-05, "train/grad": 0.12488923412205105, "train/loss": 0.812081906003952, "eval/hcp-train-subset/loss": 0.8253614662155029, "eval/hcp-val/loss": 0.8305431402498676} +{"epoch": 77, "train/lr": 1.651923882463461e-05, "train/grad": 0.12988775098164507, "train/loss": 0.8101835238933563, "eval/hcp-train-subset/loss": 0.8239582142522258, "eval/hcp-val/loss": 0.8305532403530613} +{"epoch": 78, "train/lr": 1.5144870591581508e-05, "train/grad": 0.12789787794563967, "train/loss": 0.8130846866512299, "eval/hcp-train-subset/loss": 0.8244169162165734, "eval/hcp-val/loss": 0.8309613110557679} +{"epoch": 79, "train/lr": 1.3822284497275662e-05, "train/grad": 0.1297247505107867, "train/loss": 0.8126776402664184, "eval/hcp-train-subset/loss": 0.8228157268416497, "eval/hcp-val/loss": 0.8302075564861298} +{"epoch": 80, "train/lr": 1.2552926770192975e-05, "train/grad": 0.13102408653929917, "train/loss": 0.8107955012130738, "eval/hcp-train-subset/loss": 0.8227700841042304, "eval/hcp-val/loss": 0.8300800400395547} +{"epoch": 81, "train/lr": 1.1338185434371453e-05, "train/grad": 0.13466219021398315, "train/loss": 0.8102515483760834, "eval/hcp-train-subset/loss": 0.8231111870658013, "eval/hcp-val/loss": 0.8296898353484369} +{"epoch": 82, "train/lr": 1.0179388791627326e-05, "train/grad": 0.13684671390536385, "train/loss": 0.811048924369812, "eval/hcp-train-subset/loss": 0.8218667161080145, "eval/hcp-val/loss": 0.8298823919988447} +{"epoch": 83, "train/lr": 9.07780396907607e-06, "train/grad": 0.13511031216175012, "train/loss": 0.8136550590705871, "eval/hcp-train-subset/loss": 0.8206104088214136, "eval/hcp-val/loss": 0.8291463073222868} +{"epoch": 84, "train/lr": 8.034635533547902e-06, "train/grad": 0.13814551328632838, "train/loss": 0.8102368741035462, "eval/hcp-train-subset/loss": 0.8204471411243561, "eval/hcp-val/loss": 0.8294311002377541} +{"epoch": 85, "train/lr": 7.051024174411275e-06, "train/grad": 0.13886085227394188, "train/loss": 0.813468326253891, "eval/hcp-train-subset/loss": 0.8191520071798756, "eval/hcp-val/loss": 0.8296191403942723} +{"epoch": 86, "train/lr": 6.1280454562463606e-06, "train/grad": 0.13890911901565053, "train/loss": 0.8116354944610595, "eval/hcp-train-subset/loss": 0.8191223817486917, "eval/hcp-val/loss": 0.8288726249048787} +{"epoch": 87, "train/lr": 5.266708642730326e-06, "train/grad": 0.14258445226219982, "train/loss": 0.8109496323108674, "eval/hcp-train-subset/loss": 0.8182844461933259, "eval/hcp-val/loss": 0.8292660434399882} +{"epoch": 88, "train/lr": 4.467955593022733e-06, "train/grad": 0.14485077574498484, "train/loss": 0.8106742863845825, "eval/hcp-train-subset/loss": 0.8182434151249547, "eval/hcp-val/loss": 0.8291077892626485} +{"epoch": 89, "train/lr": 3.732659731856291e-06, "train/grad": 0.14622608963495523, "train/loss": 0.8113765619659424, "eval/hcp-train-subset/loss": 0.8178033444189257, "eval/hcp-val/loss": 0.8287414975704686} +{"epoch": 90, "train/lr": 3.0616250944596583e-06, "train/grad": 0.14511858881507078, "train/loss": 0.811128380689621, "eval/hcp-train-subset/loss": 0.8160856202725442, "eval/hcp-val/loss": 0.8287822556111121} +{"epoch": 91, "train/lr": 2.4555854473568305e-06, "train/grad": 0.14607864440713517, "train/loss": 0.8135742104530335, "eval/hcp-train-subset/loss": 0.816473675350989, "eval/hcp-val/loss": 0.8281112313270569} +{"epoch": 92, "train/lr": 1.915203486004091e-06, "train/grad": 0.14914563545902354, "train/loss": 0.8124710460948944, "eval/hcp-train-subset/loss": 0.815940244543937, "eval/hcp-val/loss": 0.8282924698245141} +{"epoch": 93, "train/lr": 1.4410701101423926e-06, "train/grad": 0.14650368764662636, "train/loss": 0.8135040009593963, "eval/hcp-train-subset/loss": 0.8151557368616904, "eval/hcp-val/loss": 0.8281238559753664} +{"epoch": 94, "train/lr": 1.0337037776570775e-06, "train/grad": 0.150536280335885, "train/loss": 0.81380213722229, "eval/hcp-train-subset/loss": 0.8149403477868726, "eval/hcp-val/loss": 0.8280085729014489} +{"epoch": 95, "train/lr": 6.935499376518293e-07, "train/grad": 0.1543823159373587, "train/loss": 0.8122116066455841, "eval/hcp-train-subset/loss": 0.8145508352787264, "eval/hcp-val/loss": 0.8274498726091077} +{"epoch": 96, "train/lr": 4.209805433566085e-07, "train/grad": 0.14665534054232437, "train/loss": 0.8160019293308258, "eval/hcp-train-subset/loss": 0.8144899943182545, "eval/hcp-val/loss": 0.8274029474104604} +{"epoch": 97, "train/lr": 2.1629364540224422e-07, "train/grad": 0.14873642263821923, "train/loss": 0.8173686455726623, "eval/hcp-train-subset/loss": 0.8140766860977295, "eval/hcp-val/loss": 0.8272898764379563} +{"epoch": 98, "train/lr": 7.971306590647406e-08, "train/grad": 0.15106605988304814, "train/loss": 0.8144064181232452, "eval/hcp-train-subset/loss": 0.8140392111193749, "eval/hcp-val/loss": 0.8276606009852502} +{"epoch": 99, "train/lr": 1.1388153727718725e-08, "train/grad": 0.15178605175020218, "train/loss": 0.8177568831157684, "eval/hcp-train-subset/loss": 0.8143749035173847, "eval/hcp-val/loss": 0.8276983268799321} diff --git a/input_space_v3/flat_lr1e-3_4/pretrain/log.txt b/input_space_v3/flat_lr1e-3_4/pretrain/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..5cf0d8c61463e93393f4f047e98aa0c2aecf9cf2 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_4/pretrain/log.txt @@ -0,0 +1,9667 @@ +pretraining fmri mae +start: 2026-03-31 13:08:55 +cwd: /data/connor/fmri-fm +sha: ae0eae57a44753a80f371738f3276b064d5077cb, status: clean, branch: dev/clane9 +config: +name: input_space_v3/flat_lr1e-3_4/pretrain +notes: input_space ablation v3 flat_lr1e-3_4; use tube masking and on-disk data (input_space=flat + base_lr=1e-3 seed=5404) +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain +input_space: flat +patch_size: 16 +num_frames: 16 +t_patch_size: 4 +mask_ratio: 0.9 +pred_mask_ratio: null +masking: tube +masking_kwargs: {} +mask_patch_size: null +model: mae_vit_base +model_kwargs: + decoding: attn + pos_embed: sep + target_norm: null + pca_norm_nc: 2 + t_pred_stride: 2 + no_decode_pos: true + mask_drop_scale: false + pred_edge_pad: 0 + gauss_sigma: null + class_token: true + reg_tokens: 0 + no_embed_class: true + head_init_scale: 0.0 + decoder_depth: 4 + drop_path_rate: 0.0 +datasets: + hcp-train: + type: wds + url: /data/fmri-datasets/pretrain/hcpya-all.${input_space}.wds/hcpya-all-${input_space}-{00000..01799}.tar + clipping: random + clipping_kwargs: + oversample: 4.0 + shuffle: true + buffer_size: 2000 + samples_per_epoch: 200000 + hcp-train-subset: + type: arrow + root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/validation + split_range: + - 0 + - 2000 + shuffle: false + hcp-val: + type: arrow + root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/test + split_range: + - 0 + - 2000 + shuffle: false +train_dataset: hcp-train +eval_datasets: +- hcp-train-subset +- hcp-val +val_dataset: null +clip_vmax: 3.0 +normalize: frame +tr_scale: null +crop_scale: null +crop_aspect: null +gray_jitter: null +num_workers: 16 +epochs: 100 +batch_size: 32 +accum_iter: 1 +base_lr: 0.001 +min_lr: 0.0 +warmup_epochs: 5 +weight_decay: 0.05 +betas: +- 0.9 +- 0.95 +clip_grad: 1.0 +amp: true +amp_dtype: float16 +ckpt: null +resume: true +auto_resume: true +start_epoch: 0 +max_checkpoints: 0 +checkpoint_period: null +plot_period: 5 +device: cuda +presend_cuda: false +seed: 5404 +debug: false +wandb: true +wandb_entity: null +wandb_project: fMRI-foundation-model +rank: 0 +world_size: 1 +gpu: 0 +distributed: true +dist_backend: nccl +in_chans: 1 +img_size: +- 224 +- 560 + +train transform: +Compose( + ToTensor() + TemporalCenterCrop(num_frames=16) + Normalize(mode='frame') + Clip(vmax=3.0) + FlatUnmask((224, 560)) +) +val transform: +Compose( + ToTensor() + TemporalCenterCrop(num_frames=16) + Normalize(mode='frame') + Clip(vmax=3.0) + FlatUnmask((224, 560)) +) +mask generator: +TubeMasking( + mask_ratio=0.9 + (patchify): Patchify2D((224, 560), (16, 16), in_chans=1) +) +loading dataset: hcp-train + +type: wds +url: /data/fmri-datasets/pretrain/hcpya-all.${input_space}.wds/hcpya-all-${input_space}-{00000..01799}.tar +clipping: random +clipping_kwargs: + oversample: 4.0 +shuffle: true +buffer_size: 2000 +samples_per_epoch: 200000 + +loading dataset: hcp-train-subset + +type: arrow +root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/validation +split_range: +- 0 +- 2000 +shuffle: false + +split indices: [899, 472, 767, 116, 1265, 1852, 300, 1335, 361, 1560] +loading dataset: hcp-val + +type: arrow +root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/test +split_range: +- 0 +- 2000 +shuffle: false + +split indices: [1075, 1189, 738, 1350, 965, 1964, 1367, 1183, 1619, 1407] +model: +MaskedAutoencoderViT( + decoding=attn, t_pred_stride=2, pred_edge_pad=0, no_decode_pos=True + (encoder): MaskedEncoder( + class_token=True, reg_tokens=0, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) + (pred_patchify): StridedPatchify3D((16, 224, 560), (2, 16, 16), in_chans=1, t_stride=2) + (decoder): MaskedDecoder( + cross_decode=False, class_token=True, no_embed_class=True + (pos_embed): SeparablePosEmbed(512, (4, 14, 35)) + (proj): Linear(in_features=768, out_features=512, bias=True) + (blocks): ModuleList( + (0-3): 4 x Block( + (norm1): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=16 + (q): Linear(in_features=512, out_features=512, bias=True) + (k): Linear(in_features=512, out_features=512, bias=True) + (v): Linear(in_features=512, out_features=512, bias=True) + (proj): Linear(in_features=512, out_features=512, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=512, out_features=2048, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=2048, out_features=512, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (head): Linear(in_features=512, out_features=512, bias=True) + ) +) +num params: 99.7M +total batch size: 32 = 32 bs per gpu x 1 accum x 1 gpus +lr: 1.25e-04 = 1.00e-03 x 32 / 256 +full schedule: epochs = 100 (steps = 625000) +warmup: epochs = 5 (steps = 31250) +start training for 100 epochs +Train: [0] [ 0/6250] eta: 16:16:47 lr: 0.000000 grad: 0.0126 (0.0126) loss: 0.9957 (0.9957) time: 9.3772 data: 7.7146 max mem: 8589 +Train: [0] [ 100/6250] eta: 0:58:27 lr: 0.000000 grad: 0.0144 (0.0168) loss: 0.9963 (0.9959) time: 0.3456 data: 0.2478 max mem: 9394 +Train: [0] [ 200/6250] eta: 0:46:06 lr: 0.000001 grad: 0.0134 (0.0154) loss: 0.9955 (0.9959) time: 0.3597 data: 0.1211 max mem: 9394 +Train: [0] [ 300/6250] eta: 0:39:29 lr: 0.000001 grad: 0.0134 (0.0148) loss: 0.9959 (0.9959) time: 0.1708 data: 0.0003 max mem: 9394 +Train: [0] [ 400/6250] eta: 0:38:13 lr: 0.000002 grad: 0.0129 (0.0144) loss: 0.9962 (0.9959) time: 0.8328 data: 0.6270 max mem: 9394 +Train: [0] [ 500/6250] eta: 0:34:24 lr: 0.000002 grad: 0.0126 (0.0141) loss: 0.9955 (0.9959) time: 0.1515 data: 0.0598 max mem: 9394 +Train: [0] [ 600/6250] eta: 0:31:52 lr: 0.000002 grad: 0.0126 (0.0139) loss: 0.9950 (0.9959) time: 0.3076 data: 0.1746 max mem: 9394 +Train: [0] [ 700/6250] eta: 0:29:58 lr: 0.000003 grad: 0.0125 (0.0137) loss: 0.9958 (0.9959) time: 0.3546 data: 0.1903 max mem: 9394 +Train: [0] [ 800/6250] eta: 0:29:24 lr: 0.000003 grad: 0.0127 (0.0136) loss: 0.9953 (0.9959) time: 0.2210 data: 0.0004 max mem: 9394 +Train: [0] [ 900/6250] eta: 0:28:27 lr: 0.000004 grad: 0.0126 (0.0135) loss: 0.9964 (0.9959) time: 0.1313 data: 0.0495 max mem: 9394 +Train: [0] [1000/6250] eta: 0:26:17 lr: 0.000004 grad: 0.0130 (0.0135) loss: 0.9963 (0.9959) time: 0.1082 data: 0.0189 max mem: 9394 +Train: [0] [1100/6250] eta: 0:24:36 lr: 0.000004 grad: 0.0142 (0.0135) loss: 0.9953 (0.9959) time: 0.1173 data: 0.0388 max mem: 9394 +Train: [0] [1200/6250] eta: 0:23:12 lr: 0.000005 grad: 0.0151 (0.0136) loss: 0.9954 (0.9958) time: 0.1430 data: 0.0598 max mem: 9394 +Train: [0] [1300/6250] eta: 0:21:50 lr: 0.000005 grad: 0.0142 (0.0137) loss: 0.9959 (0.9958) time: 0.1338 data: 0.0476 max mem: 9394 +Train: [0] [1400/6250] eta: 0:20:45 lr: 0.000006 grad: 0.0203 (0.0141) loss: 0.9952 (0.9958) time: 0.1540 data: 0.0637 max mem: 9394 +Train: [0] [1500/6250] eta: 0:19:41 lr: 0.000006 grad: 0.0241 (0.0146) loss: 0.9960 (0.9958) time: 0.1435 data: 0.0599 max mem: 9394 +Train: [0] [1600/6250] eta: 0:18:49 lr: 0.000006 grad: 0.0325 (0.0154) loss: 0.9952 (0.9958) time: 0.1697 data: 0.0857 max mem: 9394 +Train: [0] [1700/6250] eta: 0:18:00 lr: 0.000007 grad: 0.0327 (0.0163) loss: 0.9949 (0.9957) time: 0.1884 data: 0.1051 max mem: 9394 +Train: [0] [1800/6250] eta: 0:17:11 lr: 0.000007 grad: 0.0438 (0.0176) loss: 0.9948 (0.9957) time: 0.1578 data: 0.0749 max mem: 9394 +Train: [0] [1900/6250] eta: 0:16:27 lr: 0.000008 grad: 0.0391 (0.0191) loss: 0.9939 (0.9957) time: 0.1498 data: 0.0689 max mem: 9394 +Train: [0] [2000/6250] eta: 0:15:56 lr: 0.000008 grad: 0.0504 (0.0206) loss: 0.9950 (0.9956) time: 0.0904 data: 0.0002 max mem: 9394 +Train: [0] [2100/6250] eta: 0:15:14 lr: 0.000008 grad: 0.0461 (0.0222) loss: 0.9952 (0.9956) time: 0.1458 data: 0.0642 max mem: 9394 +Train: [0] [2200/6250] eta: 0:14:37 lr: 0.000009 grad: 0.0485 (0.0233) loss: 0.9941 (0.9955) time: 0.1438 data: 0.0591 max mem: 9394 +Train: [0] [2300/6250] eta: 0:14:04 lr: 0.000009 grad: 0.0546 (0.0248) loss: 0.9941 (0.9954) time: 0.0945 data: 0.0002 max mem: 9394 +Train: [0] [2400/6250] eta: 0:13:28 lr: 0.000010 grad: 0.0537 (0.0261) loss: 0.9934 (0.9954) time: 0.1317 data: 0.0471 max mem: 9394 +Train: [0] [2500/6250] eta: 0:13:05 lr: 0.000010 grad: 0.0569 (0.0274) loss: 0.9926 (0.9953) time: 0.1800 data: 0.0908 max mem: 9394 +Train: [0] [2600/6250] eta: 0:12:35 lr: 0.000010 grad: 0.0495 (0.0286) loss: 0.9940 (0.9953) time: 0.2168 data: 0.0781 max mem: 9394 +Train: [0] [2700/6250] eta: 0:12:14 lr: 0.000011 grad: 0.0551 (0.0298) loss: 0.9932 (0.9952) time: 0.0885 data: 0.0002 max mem: 9394 +Train: [0] [2800/6250] eta: 0:11:43 lr: 0.000011 grad: 0.0493 (0.0310) loss: 0.9938 (0.9952) time: 0.1165 data: 0.0359 max mem: 9394 +Train: [0] [2900/6250] eta: 0:11:16 lr: 0.000012 grad: 0.0644 (0.0321) loss: 0.9925 (0.9951) time: 0.2078 data: 0.0407 max mem: 9394 +Train: [0] [3000/6250] eta: 0:10:56 lr: 0.000012 grad: 0.0629 (0.0334) loss: 0.9926 (0.9950) time: 0.1421 data: 0.0578 max mem: 9394 +Train: [0] [3100/6250] eta: 0:10:29 lr: 0.000012 grad: 0.0464 (0.0345) loss: 0.9942 (0.9950) time: 0.1592 data: 0.0773 max mem: 9394 +Train: [0] [3200/6250] eta: 0:10:03 lr: 0.000013 grad: 0.0666 (0.0358) loss: 0.9930 (0.9949) time: 0.1513 data: 0.0678 max mem: 9394 +Train: [0] [3300/6250] eta: 0:09:42 lr: 0.000013 grad: 0.0527 (0.0367) loss: 0.9940 (0.9948) time: 0.3277 data: 0.2018 max mem: 9394 +Train: [0] [3400/6250] eta: 0:09:15 lr: 0.000014 grad: 0.0622 (0.0377) loss: 0.9936 (0.9948) time: 0.1262 data: 0.0485 max mem: 9394 +Train: [0] [3500/6250] eta: 0:08:51 lr: 0.000014 grad: 0.0696 (0.0388) loss: 0.9927 (0.9947) time: 0.1293 data: 0.0456 max mem: 9394 +Train: [0] [3600/6250] eta: 0:08:29 lr: 0.000014 grad: 0.0619 (0.0397) loss: 0.9924 (0.9946) time: 0.1672 data: 0.0839 max mem: 9394 +Train: [0] [3700/6250] eta: 0:08:06 lr: 0.000015 grad: 0.0674 (0.0405) loss: 0.9932 (0.9946) time: 0.1464 data: 0.0608 max mem: 9394 +Train: [0] [3800/6250] eta: 0:07:43 lr: 0.000015 grad: 0.0620 (0.0412) loss: 0.9921 (0.9945) time: 0.1432 data: 0.0630 max mem: 9394 +Train: [0] [3900/6250] eta: 0:07:21 lr: 0.000016 grad: 0.0551 (0.0419) loss: 0.9919 (0.9945) time: 0.1376 data: 0.0558 max mem: 9394 +Train: [0] [4000/6250] eta: 0:06:59 lr: 0.000016 grad: 0.0700 (0.0426) loss: 0.9926 (0.9944) time: 0.1249 data: 0.0435 max mem: 9394 +Train: [0] [4100/6250] eta: 0:06:38 lr: 0.000016 grad: 0.0702 (0.0434) loss: 0.9903 (0.9943) time: 0.1627 data: 0.0646 max mem: 9394 +Train: [0] [4200/6250] eta: 0:06:17 lr: 0.000017 grad: 0.0661 (0.0443) loss: 0.9927 (0.9943) time: 0.1251 data: 0.0405 max mem: 9394 +Train: [0] [4300/6250] eta: 0:05:56 lr: 0.000017 grad: 0.0806 (0.0452) loss: 0.9910 (0.9942) time: 0.1372 data: 0.0533 max mem: 9394 +Train: [0] [4400/6250] eta: 0:05:36 lr: 0.000018 grad: 0.0687 (0.0458) loss: 0.9908 (0.9942) time: 0.1262 data: 0.0419 max mem: 9394 +Train: [0] [4500/6250] eta: 0:05:16 lr: 0.000018 grad: 0.0724 (0.0466) loss: 0.9903 (0.9941) time: 0.1252 data: 0.0389 max mem: 9394 +Train: [0] [4600/6250] eta: 0:04:57 lr: 0.000018 grad: 0.0710 (0.0473) loss: 0.9902 (0.9940) time: 0.1288 data: 0.0270 max mem: 9394 +Train: [0] [4700/6250] eta: 0:04:38 lr: 0.000019 grad: 0.0711 (0.0479) loss: 0.9914 (0.9940) time: 0.1314 data: 0.0493 max mem: 9394 +Train: [0] [4800/6250] eta: 0:04:18 lr: 0.000019 grad: 0.0712 (0.0485) loss: 0.9909 (0.9939) time: 0.1293 data: 0.0416 max mem: 9394 +Train: [0] [4900/6250] eta: 0:03:59 lr: 0.000020 grad: 0.0660 (0.0492) loss: 0.9911 (0.9938) time: 0.1477 data: 0.0634 max mem: 9394 +Train: [0] [5000/6250] eta: 0:03:40 lr: 0.000020 grad: 0.0725 (0.0498) loss: 0.9897 (0.9938) time: 0.1319 data: 0.0460 max mem: 9394 +Train: [0] [5100/6250] eta: 0:03:22 lr: 0.000020 grad: 0.0646 (0.0503) loss: 0.9903 (0.9937) time: 0.1186 data: 0.0308 max mem: 9394 +Train: [0] [5200/6250] eta: 0:03:03 lr: 0.000021 grad: 0.0704 (0.0509) loss: 0.9900 (0.9936) time: 0.1333 data: 0.0498 max mem: 9394 +Train: [0] [5300/6250] eta: 0:02:46 lr: 0.000021 grad: 0.0684 (0.0514) loss: 0.9903 (0.9936) time: 0.1034 data: 0.0158 max mem: 9394 +Train: [0] [5400/6250] eta: 0:02:28 lr: 0.000022 grad: 0.0707 (0.0519) loss: 0.9900 (0.9935) time: 0.1425 data: 0.0579 max mem: 9394 +Train: [0] [5500/6250] eta: 0:02:10 lr: 0.000022 grad: 0.0708 (0.0522) loss: 0.9905 (0.9935) time: 0.1378 data: 0.0577 max mem: 9394 +Train: [0] [5600/6250] eta: 0:01:52 lr: 0.000022 grad: 0.0799 (0.0528) loss: 0.9904 (0.9934) time: 0.1270 data: 0.0515 max mem: 9394 +Train: [0] [5700/6250] eta: 0:01:34 lr: 0.000023 grad: 0.0685 (0.0533) loss: 0.9911 (0.9934) time: 0.1445 data: 0.0647 max mem: 9394 +Train: [0] [5800/6250] eta: 0:01:17 lr: 0.000023 grad: 0.0757 (0.0537) loss: 0.9899 (0.9933) time: 0.1365 data: 0.0550 max mem: 9394 +Train: [0] [5900/6250] eta: 0:00:59 lr: 0.000024 grad: 0.0766 (0.0542) loss: 0.9906 (0.9933) time: 0.1372 data: 0.0592 max mem: 9394 +Train: [0] [6000/6250] eta: 0:00:42 lr: 0.000024 grad: 0.0742 (0.0546) loss: 0.9913 (0.9932) time: 0.1466 data: 0.0613 max mem: 9394 +Train: [0] [6100/6250] eta: 0:00:25 lr: 0.000024 grad: 0.0667 (0.0549) loss: 0.9895 (0.9932) time: 0.1700 data: 0.0921 max mem: 9394 +Train: [0] [6200/6250] eta: 0:00:08 lr: 0.000025 grad: 0.0623 (0.0552) loss: 0.9916 (0.9931) time: 0.1446 data: 0.0634 max mem: 9394 +Train: [0] [6249/6250] eta: 0:00:00 lr: 0.000025 grad: 0.0639 (0.0553) loss: 0.9908 (0.9931) time: 0.1806 data: 0.1064 max mem: 9394 +Train: [0] Total time: 0:17:45 (0.1706 s / it) +Averaged stats: lr: 0.000025 grad: 0.0639 (0.0553) loss: 0.9908 (0.9931) +Eval (hcp-train-subset): [0] [ 0/62] eta: 0:04:59 loss: 0.9896 (0.9896) time: 4.8261 data: 4.7982 max mem: 9394 +Eval (hcp-train-subset): [0] [61/62] eta: 0:00:00 loss: 0.9917 (0.9913) time: 0.1077 data: 0.0829 max mem: 9394 +Eval (hcp-train-subset): [0] Total time: 0:00:12 (0.1963 s / it) +Averaged stats (hcp-train-subset): loss: 0.9917 (0.9913) +Eval (hcp-val): [0] [ 0/62] eta: 0:04:51 loss: 0.9852 (0.9852) time: 4.7015 data: 4.6716 max mem: 9394 +Eval (hcp-val): [0] [61/62] eta: 0:00:00 loss: 0.9895 (0.9893) time: 0.1277 data: 0.1025 max mem: 9394 +Eval (hcp-val): [0] Total time: 0:00:13 (0.2140 s / it) +Averaged stats (hcp-val): loss: 0.9895 (0.9893) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +Train: [1] [ 0/6250] eta: 7:55:30 lr: 0.000025 grad: 0.0848 (0.0848) loss: 0.9857 (0.9857) time: 4.5649 data: 4.3914 max mem: 9394 +Train: [1] [ 100/6250] eta: 0:19:08 lr: 0.000025 grad: 0.0958 (0.0962) loss: 0.9873 (0.9885) time: 0.1427 data: 0.0517 max mem: 9394 +Train: [1] [ 200/6250] eta: 0:17:04 lr: 0.000026 grad: 0.0790 (0.0953) loss: 0.9897 (0.9888) time: 0.1760 data: 0.0904 max mem: 9394 +Train: [1] [ 300/6250] eta: 0:15:41 lr: 0.000026 grad: 0.0726 (0.0897) loss: 0.9902 (0.9893) time: 0.1255 data: 0.0350 max mem: 9394 +Train: [1] [ 400/6250] eta: 0:14:53 lr: 0.000027 grad: 0.0768 (0.0872) loss: 0.9901 (0.9895) time: 0.1313 data: 0.0409 max mem: 9394 +Train: [1] [ 500/6250] eta: 0:14:16 lr: 0.000027 grad: 0.0710 (0.0854) loss: 0.9899 (0.9895) time: 0.1604 data: 0.0712 max mem: 9394 +Train: [1] [ 600/6250] eta: 0:13:48 lr: 0.000027 grad: 0.0608 (0.0833) loss: 0.9905 (0.9897) time: 0.1280 data: 0.0458 max mem: 9394 +Train: [1] [ 700/6250] eta: 0:13:53 lr: 0.000028 grad: 0.0862 (0.0833) loss: 0.9886 (0.9896) time: 0.2181 data: 0.0987 max mem: 9394 +Train: [1] [ 800/6250] eta: 0:14:16 lr: 0.000028 grad: 0.0631 (0.0828) loss: 0.9906 (0.9896) time: 0.3089 data: 0.2260 max mem: 9394 +Train: [1] [ 900/6250] eta: 0:14:27 lr: 0.000029 grad: 0.0724 (0.0828) loss: 0.9897 (0.9895) time: 0.2372 data: 0.0545 max mem: 9394 +Train: [1] [1000/6250] eta: 0:14:43 lr: 0.000029 grad: 0.0647 (0.0822) loss: 0.9899 (0.9895) time: 0.1195 data: 0.0249 max mem: 9394 +Train: [1] [1100/6250] eta: 0:14:30 lr: 0.000029 grad: 0.0720 (0.0819) loss: 0.9894 (0.9895) time: 0.1346 data: 0.0431 max mem: 9394 +Train: [1] [1200/6250] eta: 0:13:59 lr: 0.000030 grad: 0.0688 (0.0817) loss: 0.9897 (0.9894) time: 0.1408 data: 0.0608 max mem: 9394 +Train: [1] [1300/6250] eta: 0:13:42 lr: 0.000030 grad: 0.0720 (0.0814) loss: 0.9887 (0.9894) time: 0.2397 data: 0.1117 max mem: 9394 +Train: [1] [1400/6250] eta: 0:13:28 lr: 0.000031 grad: 0.0712 (0.0815) loss: 0.9884 (0.9894) time: 0.1398 data: 0.0571 max mem: 9394 +Train: [1] [1500/6250] eta: 0:13:02 lr: 0.000031 grad: 0.0782 (0.0818) loss: 0.9896 (0.9893) time: 0.1220 data: 0.0290 max mem: 9394 +Train: [1] [1600/6250] eta: 0:12:37 lr: 0.000031 grad: 0.0818 (0.0821) loss: 0.9890 (0.9892) time: 0.1355 data: 0.0550 max mem: 9394 +Train: [1] [1700/6250] eta: 0:12:13 lr: 0.000032 grad: 0.0831 (0.0826) loss: 0.9896 (0.9892) time: 0.1316 data: 0.0543 max mem: 9394 +Train: [1] [1800/6250] eta: 0:11:52 lr: 0.000032 grad: 0.0802 (0.0829) loss: 0.9882 (0.9891) time: 0.1414 data: 0.0577 max mem: 9394 +Train: [1] [1900/6250] eta: 0:11:29 lr: 0.000033 grad: 0.0840 (0.0834) loss: 0.9883 (0.9890) time: 0.1340 data: 0.0509 max mem: 9394 +Train: [1] [2000/6250] eta: 0:11:25 lr: 0.000033 grad: 0.0747 (0.0835) loss: 0.9888 (0.9890) time: 0.0983 data: 0.0002 max mem: 9394 +Train: [1] [2100/6250] eta: 0:11:03 lr: 0.000033 grad: 0.0783 (0.0833) loss: 0.9897 (0.9890) time: 0.1384 data: 0.0597 max mem: 9394 +Train: [1] [2200/6250] eta: 0:10:44 lr: 0.000034 grad: 0.0838 (0.0835) loss: 0.9879 (0.9890) time: 0.1298 data: 0.0487 max mem: 9394 +Train: [1] [2300/6250] eta: 0:10:23 lr: 0.000034 grad: 0.0808 (0.0836) loss: 0.9884 (0.9889) time: 0.1291 data: 0.0469 max mem: 9394 +Train: [1] [2400/6250] eta: 0:10:10 lr: 0.000035 grad: 0.0795 (0.0837) loss: 0.9882 (0.9889) time: 0.1259 data: 0.0401 max mem: 9394 +Train: [1] [2500/6250] eta: 0:09:50 lr: 0.000035 grad: 0.0844 (0.0836) loss: 0.9871 (0.9889) time: 0.1283 data: 0.0455 max mem: 9394 +Train: [1] [2600/6250] eta: 0:09:31 lr: 0.000035 grad: 0.0719 (0.0835) loss: 0.9888 (0.9889) time: 0.1257 data: 0.0426 max mem: 9394 +Train: [1] [2700/6250] eta: 0:09:14 lr: 0.000036 grad: 0.0846 (0.0837) loss: 0.9876 (0.9888) time: 0.1633 data: 0.0821 max mem: 9394 +Train: [1] [2800/6250] eta: 0:09:00 lr: 0.000036 grad: 0.0760 (0.0840) loss: 0.9863 (0.9887) time: 0.1422 data: 0.0449 max mem: 9394 +Train: [1] [2900/6250] eta: 0:08:42 lr: 0.000037 grad: 0.0766 (0.0839) loss: 0.9865 (0.9887) time: 0.1486 data: 0.0744 max mem: 9394 +Train: [1] [3000/6250] eta: 0:08:27 lr: 0.000037 grad: 0.0730 (0.0841) loss: 0.9883 (0.9886) time: 0.1305 data: 0.0380 max mem: 9394 +Train: [1] [3100/6250] eta: 0:08:09 lr: 0.000037 grad: 0.0841 (0.0842) loss: 0.9879 (0.9886) time: 0.1223 data: 0.0380 max mem: 9394 +Train: [1] [3200/6250] eta: 0:07:52 lr: 0.000038 grad: 0.0728 (0.0841) loss: 0.9894 (0.9886) time: 0.1613 data: 0.0735 max mem: 9394 +Train: [1] [3300/6250] eta: 0:07:36 lr: 0.000038 grad: 0.0887 (0.0842) loss: 0.9860 (0.9885) time: 0.1563 data: 0.0760 max mem: 9394 +Train: [1] [3400/6250] eta: 0:07:19 lr: 0.000039 grad: 0.0786 (0.0843) loss: 0.9871 (0.9885) time: 0.1250 data: 0.0367 max mem: 9394 +Train: [1] [3500/6250] eta: 0:07:02 lr: 0.000039 grad: 0.0736 (0.0843) loss: 0.9877 (0.9885) time: 0.1246 data: 0.0443 max mem: 9394 +Train: [1] [3600/6250] eta: 0:06:46 lr: 0.000039 grad: 0.0836 (0.0844) loss: 0.9864 (0.9884) time: 0.1474 data: 0.0673 max mem: 9394 +Train: [1] [3700/6250] eta: 0:06:30 lr: 0.000040 grad: 0.0803 (0.0843) loss: 0.9895 (0.9884) time: 0.1334 data: 0.0526 max mem: 9394 +Train: [1] [3800/6250] eta: 0:06:13 lr: 0.000040 grad: 0.0793 (0.0843) loss: 0.9881 (0.9884) time: 0.1378 data: 0.0479 max mem: 9394 +Train: [1] [3900/6250] eta: 0:05:57 lr: 0.000041 grad: 0.0840 (0.0842) loss: 0.9891 (0.9884) time: 0.1646 data: 0.0803 max mem: 9394 +Train: [1] [4000/6250] eta: 0:05:41 lr: 0.000041 grad: 0.0729 (0.0842) loss: 0.9888 (0.9884) time: 0.1353 data: 0.0522 max mem: 9394 +Train: [1] [4100/6250] eta: 0:05:25 lr: 0.000041 grad: 0.0764 (0.0841) loss: 0.9874 (0.9884) time: 0.1409 data: 0.0594 max mem: 9394 +Train: [1] [4200/6250] eta: 0:05:09 lr: 0.000042 grad: 0.0663 (0.0840) loss: 0.9893 (0.9883) time: 0.1490 data: 0.0692 max mem: 9394 +Train: [1] [4300/6250] eta: 0:04:54 lr: 0.000042 grad: 0.0733 (0.0839) loss: 0.9883 (0.9883) time: 0.1462 data: 0.0624 max mem: 9394 +Train: [1] [4400/6250] eta: 0:04:38 lr: 0.000043 grad: 0.0801 (0.0839) loss: 0.9880 (0.9883) time: 0.1554 data: 0.0711 max mem: 9394 +Train: [1] [4500/6250] eta: 0:04:22 lr: 0.000043 grad: 0.0694 (0.0839) loss: 0.9869 (0.9883) time: 0.1286 data: 0.0405 max mem: 9394 +Train: [1] [4600/6250] eta: 0:04:07 lr: 0.000043 grad: 0.0780 (0.0838) loss: 0.9866 (0.9882) time: 0.1472 data: 0.0647 max mem: 9394 +Train: [1] [4700/6250] eta: 0:03:52 lr: 0.000044 grad: 0.0695 (0.0838) loss: 0.9879 (0.9882) time: 0.1636 data: 0.0822 max mem: 9394 +Train: [1] [4800/6250] eta: 0:03:37 lr: 0.000044 grad: 0.0698 (0.0838) loss: 0.9869 (0.9882) time: 0.1652 data: 0.0859 max mem: 9394 +Train: [1] [4900/6250] eta: 0:03:21 lr: 0.000045 grad: 0.0611 (0.0838) loss: 0.9888 (0.9882) time: 0.1326 data: 0.0451 max mem: 9394 +Train: [1] [5000/6250] eta: 0:03:06 lr: 0.000045 grad: 0.0838 (0.0838) loss: 0.9872 (0.9882) time: 0.1327 data: 0.0548 max mem: 9394 +Train: [1] [5100/6250] eta: 0:02:51 lr: 0.000045 grad: 0.0820 (0.0837) loss: 0.9856 (0.9881) time: 0.1718 data: 0.0735 max mem: 9394 +Train: [1] [5200/6250] eta: 0:02:36 lr: 0.000046 grad: 0.0820 (0.0838) loss: 0.9878 (0.9881) time: 0.1466 data: 0.0635 max mem: 9394 +Train: [1] [5300/6250] eta: 0:02:21 lr: 0.000046 grad: 0.0741 (0.0838) loss: 0.9880 (0.9881) time: 0.1423 data: 0.0600 max mem: 9394 +Train: [1] [5400/6250] eta: 0:02:06 lr: 0.000047 grad: 0.0839 (0.0839) loss: 0.9877 (0.9881) time: 0.1364 data: 0.0560 max mem: 9394 +Train: [1] [5500/6250] eta: 0:01:51 lr: 0.000047 grad: 0.0788 (0.0839) loss: 0.9867 (0.9880) time: 0.1541 data: 0.0695 max mem: 9394 +Train: [1] [5600/6250] eta: 0:01:36 lr: 0.000047 grad: 0.0730 (0.0839) loss: 0.9881 (0.9880) time: 0.1288 data: 0.0453 max mem: 9394 +Train: [1] [5700/6250] eta: 0:01:21 lr: 0.000048 grad: 0.0766 (0.0839) loss: 0.9870 (0.9880) time: 0.1469 data: 0.0669 max mem: 9394 +Train: [1] [5800/6250] eta: 0:01:06 lr: 0.000048 grad: 0.0737 (0.0839) loss: 0.9863 (0.9880) time: 0.1402 data: 0.0620 max mem: 9394 +Train: [1] [5900/6250] eta: 0:00:51 lr: 0.000049 grad: 0.0815 (0.0840) loss: 0.9882 (0.9879) time: 0.1274 data: 0.0364 max mem: 9394 +Train: [1] [6000/6250] eta: 0:00:37 lr: 0.000049 grad: 0.0805 (0.0840) loss: 0.9869 (0.9879) time: 0.1380 data: 0.0611 max mem: 9394 +Train: [1] [6100/6250] eta: 0:00:22 lr: 0.000049 grad: 0.0759 (0.0839) loss: 0.9873 (0.9879) time: 0.0981 data: 0.0002 max mem: 9394 +Train: [1] [6200/6250] eta: 0:00:07 lr: 0.000050 grad: 0.0788 (0.0839) loss: 0.9866 (0.9879) time: 0.0933 data: 0.0002 max mem: 9394 +Train: [1] [6249/6250] eta: 0:00:00 lr: 0.000050 grad: 0.0700 (0.0839) loss: 0.9869 (0.9879) time: 0.1310 data: 0.0395 max mem: 9394 +Train: [1] Total time: 0:15:36 (0.1499 s / it) +Averaged stats: lr: 0.000050 grad: 0.0700 (0.0839) loss: 0.9869 (0.9879) +Eval (hcp-train-subset): [1] [ 0/62] eta: 0:03:26 loss: 0.9858 (0.9858) time: 3.3282 data: 3.2141 max mem: 9394 +Eval (hcp-train-subset): [1] [61/62] eta: 0:00:00 loss: 0.9889 (0.9887) time: 0.1139 data: 0.0890 max mem: 9394 +Eval (hcp-train-subset): [1] Total time: 0:00:13 (0.2148 s / it) +Averaged stats (hcp-train-subset): loss: 0.9889 (0.9887) +Eval (hcp-val): [1] [ 0/62] eta: 0:04:06 loss: 0.9801 (0.9801) time: 3.9688 data: 3.9287 max mem: 9394 +Eval (hcp-val): [1] [61/62] eta: 0:00:00 loss: 0.9855 (0.9868) time: 0.1440 data: 0.1178 max mem: 9394 +Eval (hcp-val): [1] Total time: 0:00:14 (0.2287 s / it) +Averaged stats (hcp-val): loss: 0.9855 (0.9868) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +Train: [2] [ 0/6250] eta: 9:01:19 lr: 0.000050 grad: 0.0856 (0.0856) loss: 0.9918 (0.9918) time: 5.1967 data: 5.0895 max mem: 9394 +Train: [2] [ 100/6250] eta: 0:19:48 lr: 0.000050 grad: 0.0752 (0.0846) loss: 0.9881 (0.9869) time: 0.1325 data: 0.0453 max mem: 9394 +Train: [2] [ 200/6250] eta: 0:17:10 lr: 0.000051 grad: 0.0779 (0.0866) loss: 0.9859 (0.9861) time: 0.1612 data: 0.0808 max mem: 9394 +Train: [2] [ 300/6250] eta: 0:15:50 lr: 0.000051 grad: 0.0696 (0.0844) loss: 0.9880 (0.9863) time: 0.1346 data: 0.0500 max mem: 9394 +Train: [2] [ 400/6250] eta: 0:14:58 lr: 0.000052 grad: 0.0802 (0.0834) loss: 0.9854 (0.9865) time: 0.1166 data: 0.0288 max mem: 9394 +Train: [2] [ 500/6250] eta: 0:14:13 lr: 0.000052 grad: 0.0914 (0.0834) loss: 0.9844 (0.9865) time: 0.1331 data: 0.0486 max mem: 9394 +Train: [2] [ 600/6250] eta: 0:13:45 lr: 0.000052 grad: 0.0708 (0.0833) loss: 0.9872 (0.9866) time: 0.1331 data: 0.0425 max mem: 9394 +Train: [2] [ 700/6250] eta: 0:13:25 lr: 0.000053 grad: 0.0774 (0.0831) loss: 0.9893 (0.9867) time: 0.1350 data: 0.0461 max mem: 9394 +Train: [2] [ 800/6250] eta: 0:13:12 lr: 0.000053 grad: 0.0757 (0.0823) loss: 0.9876 (0.9869) time: 0.1327 data: 0.0417 max mem: 9394 +Train: [2] [ 900/6250] eta: 0:13:00 lr: 0.000054 grad: 0.0838 (0.0821) loss: 0.9865 (0.9869) time: 0.1691 data: 0.0784 max mem: 9394 +Train: [2] [1000/6250] eta: 0:12:50 lr: 0.000054 grad: 0.0720 (0.0821) loss: 0.9882 (0.9869) time: 0.1563 data: 0.0742 max mem: 9394 +Train: [2] [1100/6250] eta: 0:12:32 lr: 0.000054 grad: 0.0796 (0.0822) loss: 0.9866 (0.9869) time: 0.1433 data: 0.0622 max mem: 9394 +Train: [2] [1200/6250] eta: 0:12:13 lr: 0.000055 grad: 0.0827 (0.0822) loss: 0.9869 (0.9868) time: 0.1345 data: 0.0527 max mem: 9394 +Train: [2] [1300/6250] eta: 0:11:55 lr: 0.000055 grad: 0.0866 (0.0822) loss: 0.9868 (0.9868) time: 0.1430 data: 0.0617 max mem: 9394 +Train: [2] [1400/6250] eta: 0:11:37 lr: 0.000056 grad: 0.0806 (0.0824) loss: 0.9870 (0.9868) time: 0.1399 data: 0.0519 max mem: 9394 +Train: [2] [1500/6250] eta: 0:11:24 lr: 0.000056 grad: 0.0850 (0.0827) loss: 0.9860 (0.9867) time: 0.1234 data: 0.0348 max mem: 9394 +Train: [2] [1600/6250] eta: 0:11:07 lr: 0.000056 grad: 0.0783 (0.0827) loss: 0.9866 (0.9867) time: 0.1327 data: 0.0489 max mem: 9394 +Train: [2] [1700/6250] eta: 0:10:50 lr: 0.000057 grad: 0.0897 (0.0828) loss: 0.9875 (0.9867) time: 0.1288 data: 0.0520 max mem: 9394 +Train: [2] [1800/6250] eta: 0:10:35 lr: 0.000057 grad: 0.0726 (0.0827) loss: 0.9866 (0.9867) time: 0.1316 data: 0.0511 max mem: 9394 +Train: [2] [1900/6250] eta: 0:10:23 lr: 0.000058 grad: 0.0778 (0.0828) loss: 0.9861 (0.9866) time: 0.1277 data: 0.0259 max mem: 9394 +Train: [2] [2000/6250] eta: 0:10:06 lr: 0.000058 grad: 0.0738 (0.0828) loss: 0.9848 (0.9866) time: 0.1385 data: 0.0564 max mem: 9394 +Train: [2] [2100/6250] eta: 0:09:51 lr: 0.000058 grad: 0.0811 (0.0831) loss: 0.9872 (0.9866) time: 0.1367 data: 0.0554 max mem: 9394 +Train: [2] [2200/6250] eta: 0:09:35 lr: 0.000059 grad: 0.0843 (0.0831) loss: 0.9866 (0.9865) time: 0.1225 data: 0.0354 max mem: 9394 +Train: [2] [2300/6250] eta: 0:09:19 lr: 0.000059 grad: 0.0804 (0.0831) loss: 0.9870 (0.9865) time: 0.1311 data: 0.0464 max mem: 9394 +Train: [2] [2400/6250] eta: 0:09:04 lr: 0.000060 grad: 0.0748 (0.0832) loss: 0.9867 (0.9865) time: 0.1353 data: 0.0529 max mem: 9394 +Train: [2] [2500/6250] eta: 0:08:49 lr: 0.000060 grad: 0.0906 (0.0834) loss: 0.9856 (0.9864) time: 0.1355 data: 0.0513 max mem: 9394 +Train: [2] [2600/6250] eta: 0:08:33 lr: 0.000060 grad: 0.0826 (0.0838) loss: 0.9854 (0.9864) time: 0.1242 data: 0.0385 max mem: 9394 +Train: [2] [2700/6250] eta: 0:08:18 lr: 0.000061 grad: 0.0846 (0.0840) loss: 0.9857 (0.9863) time: 0.1324 data: 0.0478 max mem: 9394 +Train: [2] [2800/6250] eta: 0:08:04 lr: 0.000061 grad: 0.0819 (0.0841) loss: 0.9848 (0.9863) time: 0.1176 data: 0.0388 max mem: 9394 +Train: [2] [2900/6250] eta: 0:07:50 lr: 0.000062 grad: 0.0863 (0.0847) loss: 0.9856 (0.9863) time: 0.1380 data: 0.0568 max mem: 9394 +Train: [2] [3000/6250] eta: 0:07:36 lr: 0.000062 grad: 0.0862 (0.0849) loss: 0.9866 (0.9863) time: 0.1580 data: 0.0820 max mem: 9394 +Train: [2] [3100/6250] eta: 0:07:27 lr: 0.000062 grad: 0.0915 (0.0853) loss: 0.9849 (0.9862) time: 0.3661 data: 0.2804 max mem: 9394 +Train: [2] [3200/6250] eta: 0:07:11 lr: 0.000063 grad: 0.0845 (0.0856) loss: 0.9850 (0.9862) time: 0.1401 data: 0.0576 max mem: 9394 +Train: [2] [3300/6250] eta: 0:06:59 lr: 0.000063 grad: 0.1056 (0.0862) loss: 0.9844 (0.9861) time: 0.1421 data: 0.0582 max mem: 9394 +Train: [2] [3400/6250] eta: 0:06:43 lr: 0.000064 grad: 0.0991 (0.0869) loss: 0.9866 (0.9861) time: 0.1381 data: 0.0560 max mem: 9394 +Train: [2] [3500/6250] eta: 0:06:30 lr: 0.000064 grad: 0.1002 (0.0875) loss: 0.9878 (0.9861) time: 0.1966 data: 0.1196 max mem: 9394 +Train: [2] [3600/6250] eta: 0:06:17 lr: 0.000064 grad: 0.1184 (0.0885) loss: 0.9856 (0.9860) time: 0.1060 data: 0.0074 max mem: 9394 +Train: [2] [3700/6250] eta: 0:06:02 lr: 0.000065 grad: 0.1340 (0.0901) loss: 0.9842 (0.9860) time: 0.1420 data: 0.0560 max mem: 9394 +Train: [2] [3800/6250] eta: 0:05:48 lr: 0.000065 grad: 0.1049 (0.0912) loss: 0.9843 (0.9860) time: 0.1408 data: 0.0608 max mem: 9394 +Train: [2] [3900/6250] eta: 0:05:33 lr: 0.000066 grad: 0.0984 (0.0927) loss: 0.9842 (0.9859) time: 0.1434 data: 0.0588 max mem: 9394 +Train: [2] [4000/6250] eta: 0:05:19 lr: 0.000066 grad: 0.1953 (0.0950) loss: 0.9846 (0.9859) time: 0.1395 data: 0.0548 max mem: 9394 +Train: [2] [4100/6250] eta: 0:05:04 lr: 0.000066 grad: 0.1958 (0.0970) loss: 0.9855 (0.9858) time: 0.1464 data: 0.0626 max mem: 9394 +Train: [2] [4200/6250] eta: 0:04:50 lr: 0.000067 grad: 0.1890 (0.0994) loss: 0.9835 (0.9858) time: 0.1300 data: 0.0507 max mem: 9394 +Train: [2] [4300/6250] eta: 0:04:36 lr: 0.000067 grad: 0.1734 (0.1022) loss: 0.9853 (0.9857) time: 0.1441 data: 0.0644 max mem: 9394 +Train: [2] [4400/6250] eta: 0:04:21 lr: 0.000068 grad: 0.2259 (0.1050) loss: 0.9854 (0.9856) time: 0.1280 data: 0.0437 max mem: 9394 +Train: [2] [4500/6250] eta: 0:04:07 lr: 0.000068 grad: 0.1453 (0.1070) loss: 0.9836 (0.9856) time: 0.1606 data: 0.0803 max mem: 9394 +Train: [2] [4600/6250] eta: 0:03:53 lr: 0.000068 grad: 0.1422 (0.1092) loss: 0.9840 (0.9855) time: 0.1849 data: 0.1089 max mem: 9394 +Train: [2] [4700/6250] eta: 0:03:39 lr: 0.000069 grad: 0.2477 (0.1116) loss: 0.9827 (0.9854) time: 0.1346 data: 0.0522 max mem: 9394 +Train: [2] [4800/6250] eta: 0:03:24 lr: 0.000069 grad: 0.1749 (0.1141) loss: 0.9826 (0.9853) time: 0.1226 data: 0.0335 max mem: 9394 +Train: [2] [4900/6250] eta: 0:03:10 lr: 0.000070 grad: 0.1375 (0.1160) loss: 0.9805 (0.9852) time: 0.1230 data: 0.0401 max mem: 9394 +Train: [2] [5000/6250] eta: 0:02:56 lr: 0.000070 grad: 0.2046 (0.1181) loss: 0.9804 (0.9851) time: 0.1529 data: 0.0711 max mem: 9394 +Train: [2] [5100/6250] eta: 0:02:42 lr: 0.000070 grad: 0.1666 (0.1202) loss: 0.9822 (0.9850) time: 0.1605 data: 0.0699 max mem: 9394 +Train: [2] [5200/6250] eta: 0:02:28 lr: 0.000071 grad: 0.2342 (0.1222) loss: 0.9818 (0.9850) time: 0.1154 data: 0.0271 max mem: 9394 +Train: [2] [5300/6250] eta: 0:02:13 lr: 0.000071 grad: 0.2557 (0.1243) loss: 0.9821 (0.9849) time: 0.1139 data: 0.0288 max mem: 9394 +Train: [2] [5400/6250] eta: 0:01:59 lr: 0.000072 grad: 0.2360 (0.1262) loss: 0.9803 (0.9848) time: 0.1374 data: 0.0634 max mem: 9394 +Train: [2] [5500/6250] eta: 0:01:45 lr: 0.000072 grad: 0.1458 (0.1276) loss: 0.9808 (0.9848) time: 0.1422 data: 0.0581 max mem: 9394 +Train: [2] [5600/6250] eta: 0:01:31 lr: 0.000072 grad: 0.2342 (0.1297) loss: 0.9809 (0.9847) time: 0.1465 data: 0.0644 max mem: 9394 +Train: [2] [5700/6250] eta: 0:01:17 lr: 0.000073 grad: 0.1626 (0.1314) loss: 0.9815 (0.9846) time: 0.1328 data: 0.0517 max mem: 9394 +Train: [2] [5800/6250] eta: 0:01:03 lr: 0.000073 grad: 0.2682 (0.1325) loss: 0.9806 (0.9845) time: 0.1505 data: 0.0601 max mem: 9394 +Train: [2] [5900/6250] eta: 0:00:49 lr: 0.000074 grad: 0.2030 (0.1342) loss: 0.9820 (0.9845) time: 0.1348 data: 0.0527 max mem: 9394 +Train: [2] [6000/6250] eta: 0:00:35 lr: 0.000074 grad: 0.1428 (0.1353) loss: 0.9801 (0.9844) time: 0.1539 data: 0.0724 max mem: 9394 +Train: [2] [6100/6250] eta: 0:00:21 lr: 0.000074 grad: 0.1490 (0.1368) loss: 0.9806 (0.9844) time: 0.1773 data: 0.1007 max mem: 9394 +Train: [2] [6200/6250] eta: 0:00:07 lr: 0.000075 grad: 0.1261 (0.1380) loss: 0.9822 (0.9843) time: 0.1135 data: 0.0286 max mem: 9394 +Train: [2] [6249/6250] eta: 0:00:00 lr: 0.000075 grad: 0.1122 (0.1383) loss: 0.9807 (0.9843) time: 0.1281 data: 0.0441 max mem: 9394 +Train: [2] Total time: 0:14:43 (0.1414 s / it) +Averaged stats: lr: 0.000075 grad: 0.1122 (0.1383) loss: 0.9807 (0.9843) +Eval (hcp-train-subset): [2] [ 0/62] eta: 0:04:10 loss: 0.9784 (0.9784) time: 4.0337 data: 3.9835 max mem: 9394 +Eval (hcp-train-subset): [2] [61/62] eta: 0:00:00 loss: 0.9847 (0.9832) time: 0.1428 data: 0.1153 max mem: 9394 +Eval (hcp-train-subset): [2] Total time: 0:00:14 (0.2336 s / it) +Averaged stats (hcp-train-subset): loss: 0.9847 (0.9832) +Eval (hcp-val): [2] [ 0/62] eta: 0:03:11 loss: 0.9806 (0.9806) time: 3.0921 data: 3.0381 max mem: 9394 +Eval (hcp-val): [2] [61/62] eta: 0:00:00 loss: 0.9811 (0.9808) time: 0.1299 data: 0.1014 max mem: 9394 +Eval (hcp-val): [2] Total time: 0:00:12 (0.2029 s / it) +Averaged stats (hcp-val): loss: 0.9811 (0.9808) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +Train: [3] [ 0/6250] eta: 8:55:56 lr: 0.000075 grad: 0.2483 (0.2483) loss: 0.9730 (0.9730) time: 5.1450 data: 5.0149 max mem: 9394 +Train: [3] [ 100/6250] eta: 0:20:28 lr: 0.000075 grad: 0.1424 (0.2608) loss: 0.9825 (0.9795) time: 0.1464 data: 0.0583 max mem: 9394 +Train: [3] [ 200/6250] eta: 0:17:18 lr: 0.000076 grad: 0.2231 (0.2462) loss: 0.9816 (0.9798) time: 0.1541 data: 0.0695 max mem: 9394 +Train: [3] [ 300/6250] eta: 0:15:52 lr: 0.000076 grad: 0.1035 (0.2267) loss: 0.9812 (0.9801) time: 0.1355 data: 0.0537 max mem: 9394 +Train: [3] [ 400/6250] eta: 0:14:59 lr: 0.000077 grad: 0.1709 (0.2157) loss: 0.9824 (0.9800) time: 0.1289 data: 0.0407 max mem: 9394 +Train: [3] [ 500/6250] eta: 0:14:13 lr: 0.000077 grad: 0.2456 (0.2150) loss: 0.9812 (0.9800) time: 0.1352 data: 0.0481 max mem: 9394 +Train: [3] [ 600/6250] eta: 0:13:54 lr: 0.000077 grad: 0.1399 (0.2161) loss: 0.9788 (0.9798) time: 0.1636 data: 0.0660 max mem: 9394 +Train: [3] [ 700/6250] eta: 0:13:29 lr: 0.000078 grad: 0.1461 (0.2137) loss: 0.9795 (0.9797) time: 0.1339 data: 0.0472 max mem: 9394 +Train: [3] [ 800/6250] eta: 0:13:17 lr: 0.000078 grad: 0.1554 (0.2150) loss: 0.9806 (0.9797) time: 0.1244 data: 0.0421 max mem: 9394 +Train: [3] [ 900/6250] eta: 0:13:04 lr: 0.000079 grad: 0.1132 (0.2106) loss: 0.9780 (0.9797) time: 0.1472 data: 0.0598 max mem: 9394 +Train: [3] [1000/6250] eta: 0:12:46 lr: 0.000079 grad: 0.1536 (0.2094) loss: 0.9771 (0.9797) time: 0.1536 data: 0.0715 max mem: 9394 +Train: [3] [1100/6250] eta: 0:12:30 lr: 0.000079 grad: 0.1364 (0.2078) loss: 0.9779 (0.9795) time: 0.1313 data: 0.0474 max mem: 9394 +Train: [3] [1200/6250] eta: 0:12:10 lr: 0.000080 grad: 0.1151 (0.2065) loss: 0.9772 (0.9795) time: 0.1287 data: 0.0456 max mem: 9394 +Train: [3] [1300/6250] eta: 0:11:54 lr: 0.000080 grad: 0.1642 (0.2065) loss: 0.9793 (0.9795) time: 0.1053 data: 0.0192 max mem: 9394 +Train: [3] [1400/6250] eta: 0:11:38 lr: 0.000081 grad: 0.2238 (0.2078) loss: 0.9809 (0.9795) time: 0.1416 data: 0.0623 max mem: 9394 +Train: [3] [1500/6250] eta: 0:11:23 lr: 0.000081 grad: 0.1593 (0.2075) loss: 0.9785 (0.9794) time: 0.1332 data: 0.0508 max mem: 9394 +Train: [3] [1600/6250] eta: 0:11:07 lr: 0.000081 grad: 0.2335 (0.2073) loss: 0.9798 (0.9793) time: 0.1269 data: 0.0465 max mem: 9394 +Train: [3] [1700/6250] eta: 0:10:52 lr: 0.000082 grad: 0.2113 (0.2083) loss: 0.9807 (0.9793) time: 0.1633 data: 0.0794 max mem: 9394 +Train: [3] [1800/6250] eta: 0:10:37 lr: 0.000082 grad: 0.1231 (0.2087) loss: 0.9772 (0.9792) time: 0.1293 data: 0.0435 max mem: 9394 +Train: [3] [1900/6250] eta: 0:10:21 lr: 0.000083 grad: 0.1705 (0.2075) loss: 0.9785 (0.9791) time: 0.1388 data: 0.0614 max mem: 9394 +Train: [3] [2000/6250] eta: 0:10:06 lr: 0.000083 grad: 0.1346 (0.2068) loss: 0.9787 (0.9791) time: 0.1315 data: 0.0515 max mem: 9394 +Train: [3] [2100/6250] eta: 0:09:52 lr: 0.000083 grad: 0.1542 (0.2054) loss: 0.9784 (0.9790) time: 0.1331 data: 0.0388 max mem: 9394 +Train: [3] [2200/6250] eta: 0:09:37 lr: 0.000084 grad: 0.2670 (0.2054) loss: 0.9795 (0.9790) time: 0.1507 data: 0.0736 max mem: 9394 +Train: [3] [2300/6250] eta: 0:09:23 lr: 0.000084 grad: 0.1275 (0.2048) loss: 0.9798 (0.9790) time: 0.1531 data: 0.0676 max mem: 9394 +Train: [3] [2400/6250] eta: 0:09:10 lr: 0.000085 grad: 0.1874 (0.2037) loss: 0.9774 (0.9789) time: 0.0961 data: 0.0092 max mem: 9394 +Train: [3] [2500/6250] eta: 0:08:55 lr: 0.000085 grad: 0.1908 (0.2038) loss: 0.9772 (0.9788) time: 0.1375 data: 0.0580 max mem: 9394 +Train: [3] [2600/6250] eta: 0:08:40 lr: 0.000085 grad: 0.1645 (0.2024) loss: 0.9791 (0.9788) time: 0.1388 data: 0.0600 max mem: 9394 +Train: [3] [2700/6250] eta: 0:08:24 lr: 0.000086 grad: 0.1849 (0.2020) loss: 0.9775 (0.9787) time: 0.1420 data: 0.0584 max mem: 9394 +Train: [3] [2800/6250] eta: 0:08:09 lr: 0.000086 grad: 0.1349 (0.2012) loss: 0.9768 (0.9787) time: 0.1434 data: 0.0577 max mem: 9394 +Train: [3] [2900/6250] eta: 0:07:54 lr: 0.000087 grad: 0.1694 (0.2011) loss: 0.9797 (0.9786) time: 0.1317 data: 0.0451 max mem: 9394 +Train: [3] [3000/6250] eta: 0:07:41 lr: 0.000087 grad: 0.1855 (0.2009) loss: 0.9801 (0.9785) time: 0.1517 data: 0.0721 max mem: 9394 +Train: [3] [3100/6250] eta: 0:07:26 lr: 0.000087 grad: 0.1770 (0.2004) loss: 0.9792 (0.9785) time: 0.1239 data: 0.0482 max mem: 9394 +Train: [3] [3200/6250] eta: 0:07:12 lr: 0.000088 grad: 0.1948 (0.2007) loss: 0.9757 (0.9784) time: 0.1309 data: 0.0494 max mem: 9394 +Train: [3] [3300/6250] eta: 0:06:57 lr: 0.000088 grad: 0.1350 (0.2003) loss: 0.9760 (0.9784) time: 0.1192 data: 0.0336 max mem: 9394 +Train: [3] [3400/6250] eta: 0:06:42 lr: 0.000089 grad: 0.2445 (0.2006) loss: 0.9797 (0.9783) time: 0.1378 data: 0.0487 max mem: 9394 +Train: [3] [3500/6250] eta: 0:06:28 lr: 0.000089 grad: 0.1695 (0.2007) loss: 0.9770 (0.9782) time: 0.1315 data: 0.0486 max mem: 9394 +Train: [3] [3600/6250] eta: 0:06:14 lr: 0.000089 grad: 0.1497 (0.1999) loss: 0.9763 (0.9781) time: 0.1398 data: 0.0564 max mem: 9394 +Train: [3] [3700/6250] eta: 0:05:59 lr: 0.000090 grad: 0.1585 (0.1998) loss: 0.9744 (0.9780) time: 0.1489 data: 0.0709 max mem: 9394 +Train: [3] [3800/6250] eta: 0:05:45 lr: 0.000090 grad: 0.1370 (0.1998) loss: 0.9743 (0.9780) time: 0.1397 data: 0.0620 max mem: 9394 +Train: [3] [3900/6250] eta: 0:05:30 lr: 0.000091 grad: 0.1246 (0.1991) loss: 0.9770 (0.9779) time: 0.1322 data: 0.0515 max mem: 9394 +Train: [3] [4000/6250] eta: 0:05:16 lr: 0.000091 grad: 0.1611 (0.1984) loss: 0.9764 (0.9779) time: 0.1059 data: 0.0236 max mem: 9394 +Train: [3] [4100/6250] eta: 0:05:02 lr: 0.000091 grad: 0.1565 (0.1982) loss: 0.9768 (0.9778) time: 0.1489 data: 0.0674 max mem: 9394 +Train: [3] [4200/6250] eta: 0:04:47 lr: 0.000092 grad: 0.1329 (0.1978) loss: 0.9761 (0.9778) time: 0.1361 data: 0.0573 max mem: 9394 +Train: [3] [4300/6250] eta: 0:04:33 lr: 0.000092 grad: 0.1708 (0.1974) loss: 0.9771 (0.9777) time: 0.1216 data: 0.0375 max mem: 9394 +Train: [3] [4400/6250] eta: 0:04:18 lr: 0.000093 grad: 0.1409 (0.1967) loss: 0.9786 (0.9777) time: 0.1113 data: 0.0213 max mem: 9394 +Train: [3] [4500/6250] eta: 0:04:04 lr: 0.000093 grad: 0.1594 (0.1961) loss: 0.9768 (0.9777) time: 0.1412 data: 0.0591 max mem: 9394 +Train: [3] [4600/6250] eta: 0:03:50 lr: 0.000093 grad: 0.1172 (0.1953) loss: 0.9756 (0.9776) time: 0.0975 data: 0.0078 max mem: 9394 +Train: [3] [4700/6250] eta: 0:03:36 lr: 0.000094 grad: 0.1596 (0.1950) loss: 0.9773 (0.9776) time: 0.1533 data: 0.0718 max mem: 9394 +Train: [3] [4800/6250] eta: 0:03:22 lr: 0.000094 grad: 0.1478 (0.1948) loss: 0.9759 (0.9776) time: 0.1458 data: 0.0631 max mem: 9394 +Train: [3] [4900/6250] eta: 0:03:08 lr: 0.000095 grad: 0.1220 (0.1940) loss: 0.9741 (0.9775) time: 0.1247 data: 0.0412 max mem: 9394 +Train: [3] [5000/6250] eta: 0:02:54 lr: 0.000095 grad: 0.1446 (0.1934) loss: 0.9730 (0.9774) time: 0.1229 data: 0.0328 max mem: 9394 +Train: [3] [5100/6250] eta: 0:02:40 lr: 0.000095 grad: 0.1881 (0.1933) loss: 0.9751 (0.9774) time: 0.1419 data: 0.0592 max mem: 9394 +Train: [3] [5200/6250] eta: 0:02:26 lr: 0.000096 grad: 0.1560 (0.1930) loss: 0.9730 (0.9773) time: 0.1114 data: 0.0253 max mem: 9394 +Train: [3] [5300/6250] eta: 0:02:12 lr: 0.000096 grad: 0.1404 (0.1924) loss: 0.9731 (0.9772) time: 0.1216 data: 0.0349 max mem: 9394 +Train: [3] [5400/6250] eta: 0:01:58 lr: 0.000097 grad: 0.1809 (0.1921) loss: 0.9730 (0.9772) time: 0.1327 data: 0.0503 max mem: 9394 +Train: [3] [5500/6250] eta: 0:01:44 lr: 0.000097 grad: 0.1795 (0.1920) loss: 0.9722 (0.9771) time: 0.1470 data: 0.0671 max mem: 9394 +Train: [3] [5600/6250] eta: 0:01:30 lr: 0.000097 grad: 0.1587 (0.1916) loss: 0.9704 (0.9770) time: 0.1183 data: 0.0385 max mem: 9394 +Train: [3] [5700/6250] eta: 0:01:16 lr: 0.000098 grad: 0.1544 (0.1916) loss: 0.9741 (0.9769) time: 0.1068 data: 0.0237 max mem: 9394 +Train: [3] [5800/6250] eta: 0:01:02 lr: 0.000098 grad: 0.1677 (0.1912) loss: 0.9696 (0.9768) time: 0.1585 data: 0.0795 max mem: 9394 +Train: [3] [5900/6250] eta: 0:00:48 lr: 0.000099 grad: 0.1694 (0.1912) loss: 0.9705 (0.9768) time: 0.1388 data: 0.0548 max mem: 9394 +Train: [3] [6000/6250] eta: 0:00:34 lr: 0.000099 grad: 0.2047 (0.1911) loss: 0.9708 (0.9767) time: 0.1266 data: 0.0436 max mem: 9394 +Train: [3] [6100/6250] eta: 0:00:20 lr: 0.000099 grad: 0.1918 (0.1911) loss: 0.9713 (0.9766) time: 0.1311 data: 0.0465 max mem: 9394 +Train: [3] [6200/6250] eta: 0:00:06 lr: 0.000100 grad: 0.1314 (0.1907) loss: 0.9689 (0.9764) time: 0.1360 data: 0.0517 max mem: 9394 +Train: [3] [6249/6250] eta: 0:00:00 lr: 0.000100 grad: 0.1572 (0.1906) loss: 0.9707 (0.9764) time: 0.1330 data: 0.0497 max mem: 9394 +Train: [3] Total time: 0:14:33 (0.1398 s / it) +Averaged stats: lr: 0.000100 grad: 0.1572 (0.1906) loss: 0.9707 (0.9764) +Eval (hcp-train-subset): [3] [ 0/62] eta: 0:03:10 loss: 0.9766 (0.9766) time: 3.0653 data: 2.9924 max mem: 9394 +Eval (hcp-train-subset): [3] [61/62] eta: 0:00:00 loss: 0.9729 (0.9727) time: 0.2089 data: 0.1817 max mem: 9394 +Eval (hcp-train-subset): [3] Total time: 0:00:15 (0.2471 s / it) +Averaged stats (hcp-train-subset): loss: 0.9729 (0.9727) +Eval (hcp-val): [3] [ 0/62] eta: 0:05:09 loss: 0.9648 (0.9648) time: 4.9989 data: 4.9683 max mem: 9394 +Eval (hcp-val): [3] [61/62] eta: 0:00:00 loss: 0.9696 (0.9696) time: 0.1122 data: 0.0857 max mem: 9394 +Eval (hcp-val): [3] Total time: 0:00:12 (0.2040 s / it) +Averaged stats (hcp-val): loss: 0.9696 (0.9696) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +Train: [4] [ 0/6250] eta: 6:55:16 lr: 0.000100 grad: 0.1161 (0.1161) loss: 0.9699 (0.9699) time: 3.9866 data: 3.7257 max mem: 9394 +Train: [4] [ 100/6250] eta: 0:20:48 lr: 0.000100 grad: 0.1587 (0.1580) loss: 0.9660 (0.9693) time: 0.1599 data: 0.0692 max mem: 9394 +Train: [4] [ 200/6250] eta: 0:17:48 lr: 0.000101 grad: 0.1392 (0.1695) loss: 0.9691 (0.9678) time: 0.1594 data: 0.0684 max mem: 9394 +Train: [4] [ 300/6250] eta: 0:16:10 lr: 0.000101 grad: 0.1761 (0.1818) loss: 0.9669 (0.9670) time: 0.1342 data: 0.0482 max mem: 9394 +Train: [4] [ 400/6250] eta: 0:15:10 lr: 0.000102 grad: 0.1806 (0.1855) loss: 0.9662 (0.9668) time: 0.1436 data: 0.0551 max mem: 9394 +Train: [4] [ 500/6250] eta: 0:14:27 lr: 0.000102 grad: 0.1639 (0.1885) loss: 0.9611 (0.9662) time: 0.1527 data: 0.0648 max mem: 9394 +Train: [4] [ 600/6250] eta: 0:14:10 lr: 0.000102 grad: 0.1610 (0.1892) loss: 0.9646 (0.9661) time: 0.1590 data: 0.0517 max mem: 9394 +Train: [4] [ 700/6250] eta: 0:13:47 lr: 0.000103 grad: 0.1579 (0.1897) loss: 0.9654 (0.9659) time: 0.1318 data: 0.0381 max mem: 9394 +Train: [4] [ 800/6250] eta: 0:13:29 lr: 0.000103 grad: 0.1617 (0.1886) loss: 0.9628 (0.9655) time: 0.1597 data: 0.0739 max mem: 9394 +Train: [4] [ 900/6250] eta: 0:13:21 lr: 0.000104 grad: 0.2021 (0.1901) loss: 0.9617 (0.9650) time: 0.1071 data: 0.0002 max mem: 9394 +Train: [4] [1000/6250] eta: 0:13:07 lr: 0.000104 grad: 0.1665 (0.1908) loss: 0.9619 (0.9646) time: 0.0945 data: 0.0002 max mem: 9394 +Train: [4] [1100/6250] eta: 0:12:56 lr: 0.000104 grad: 0.2043 (0.1926) loss: 0.9603 (0.9642) time: 0.1644 data: 0.0749 max mem: 9394 +Train: [4] [1200/6250] eta: 0:12:34 lr: 0.000105 grad: 0.1991 (0.1951) loss: 0.9602 (0.9639) time: 0.1366 data: 0.0504 max mem: 9394 +Train: [4] [1300/6250] eta: 0:12:14 lr: 0.000105 grad: 0.1896 (0.1970) loss: 0.9556 (0.9633) time: 0.1444 data: 0.0617 max mem: 9394 +Train: [4] [1400/6250] eta: 0:11:57 lr: 0.000106 grad: 0.1789 (0.1974) loss: 0.9580 (0.9628) time: 0.1462 data: 0.0615 max mem: 9394 +Train: [4] [1500/6250] eta: 0:11:39 lr: 0.000106 grad: 0.2572 (0.2011) loss: 0.9552 (0.9623) time: 0.1456 data: 0.0661 max mem: 9394 +Train: [4] [1600/6250] eta: 0:11:24 lr: 0.000106 grad: 0.1976 (0.2038) loss: 0.9547 (0.9618) time: 0.1798 data: 0.0956 max mem: 9394 +Train: [4] [1700/6250] eta: 0:11:06 lr: 0.000107 grad: 0.1885 (0.2055) loss: 0.9515 (0.9613) time: 0.1253 data: 0.0434 max mem: 9394 +Train: [4] [1800/6250] eta: 0:10:50 lr: 0.000107 grad: 0.1932 (0.2081) loss: 0.9531 (0.9608) time: 0.1347 data: 0.0539 max mem: 9394 +Train: [4] [1900/6250] eta: 0:10:34 lr: 0.000108 grad: 0.2187 (0.2087) loss: 0.9503 (0.9603) time: 0.1453 data: 0.0587 max mem: 9394 +Train: [4] [2000/6250] eta: 0:10:19 lr: 0.000108 grad: 0.2222 (0.2103) loss: 0.9520 (0.9598) time: 0.1507 data: 0.0739 max mem: 9394 +Train: [4] [2100/6250] eta: 0:10:02 lr: 0.000108 grad: 0.2295 (0.2121) loss: 0.9477 (0.9592) time: 0.1322 data: 0.0471 max mem: 9394 +Train: [4] [2200/6250] eta: 0:09:47 lr: 0.000109 grad: 0.2694 (0.2151) loss: 0.9480 (0.9587) time: 0.1394 data: 0.0529 max mem: 9394 +Train: [4] [2300/6250] eta: 0:09:32 lr: 0.000109 grad: 0.3420 (0.2169) loss: 0.9469 (0.9582) time: 0.1153 data: 0.0268 max mem: 9394 +Train: [4] [2400/6250] eta: 0:09:16 lr: 0.000110 grad: 0.2296 (0.2177) loss: 0.9463 (0.9577) time: 0.1278 data: 0.0466 max mem: 9394 +Train: [4] [2500/6250] eta: 0:09:01 lr: 0.000110 grad: 0.2121 (0.2192) loss: 0.9441 (0.9572) time: 0.1721 data: 0.0900 max mem: 9394 +Train: [4] [2600/6250] eta: 0:08:45 lr: 0.000110 grad: 0.2173 (0.2208) loss: 0.9425 (0.9567) time: 0.1323 data: 0.0531 max mem: 9394 +Train: [4] [2700/6250] eta: 0:08:30 lr: 0.000111 grad: 0.2218 (0.2219) loss: 0.9409 (0.9561) time: 0.1507 data: 0.0672 max mem: 9394 +Train: [4] [2800/6250] eta: 0:08:14 lr: 0.000111 grad: 0.2229 (0.2242) loss: 0.9445 (0.9556) time: 0.1260 data: 0.0445 max mem: 9394 +Train: [4] [2900/6250] eta: 0:07:59 lr: 0.000112 grad: 0.2635 (0.2261) loss: 0.9392 (0.9552) time: 0.1304 data: 0.0422 max mem: 9394 +Train: [4] [3000/6250] eta: 0:07:44 lr: 0.000112 grad: 0.2194 (0.2270) loss: 0.9377 (0.9547) time: 0.1314 data: 0.0448 max mem: 9394 +Train: [4] [3100/6250] eta: 0:07:29 lr: 0.000112 grad: 0.2038 (0.2273) loss: 0.9376 (0.9542) time: 0.1324 data: 0.0489 max mem: 9394 +Train: [4] [3200/6250] eta: 0:07:14 lr: 0.000113 grad: 0.2553 (0.2281) loss: 0.9408 (0.9537) time: 0.1496 data: 0.0639 max mem: 9394 +Train: [4] [3300/6250] eta: 0:06:59 lr: 0.000113 grad: 0.2000 (0.2288) loss: 0.9365 (0.9533) time: 0.1177 data: 0.0290 max mem: 9394 +Train: [4] [3400/6250] eta: 0:06:45 lr: 0.000114 grad: 0.1862 (0.2289) loss: 0.9388 (0.9528) time: 0.1636 data: 0.0829 max mem: 9394 +Train: [4] [3500/6250] eta: 0:06:30 lr: 0.000114 grad: 0.2350 (0.2304) loss: 0.9336 (0.9523) time: 0.1398 data: 0.0598 max mem: 9394 +Train: [4] [3600/6250] eta: 0:06:15 lr: 0.000114 grad: 0.1812 (0.2300) loss: 0.9363 (0.9518) time: 0.1370 data: 0.0568 max mem: 9394 +Train: [4] [3700/6250] eta: 0:06:00 lr: 0.000115 grad: 0.2762 (0.2304) loss: 0.9337 (0.9513) time: 0.1455 data: 0.0637 max mem: 9394 +Train: [4] [3800/6250] eta: 0:05:46 lr: 0.000115 grad: 0.1858 (0.2306) loss: 0.9311 (0.9509) time: 0.1190 data: 0.0306 max mem: 9394 +Train: [4] [3900/6250] eta: 0:05:32 lr: 0.000116 grad: 0.2438 (0.2310) loss: 0.9306 (0.9504) time: 0.1477 data: 0.0577 max mem: 9394 +Train: [4] [4000/6250] eta: 0:05:17 lr: 0.000116 grad: 0.1804 (0.2307) loss: 0.9328 (0.9499) time: 0.1406 data: 0.0580 max mem: 9394 +Train: [4] [4100/6250] eta: 0:05:03 lr: 0.000116 grad: 0.2671 (0.2316) loss: 0.9282 (0.9495) time: 0.1336 data: 0.0480 max mem: 9394 +Train: [4] [4200/6250] eta: 0:04:49 lr: 0.000117 grad: 0.2068 (0.2313) loss: 0.9297 (0.9490) time: 0.1402 data: 0.0535 max mem: 9394 +Train: [4] [4300/6250] eta: 0:04:35 lr: 0.000117 grad: 0.2112 (0.2311) loss: 0.9317 (0.9486) time: 0.1215 data: 0.0419 max mem: 9394 +Train: [4] [4400/6250] eta: 0:04:20 lr: 0.000118 grad: 0.2756 (0.2312) loss: 0.9293 (0.9482) time: 0.1473 data: 0.0669 max mem: 9394 +Train: [4] [4500/6250] eta: 0:04:06 lr: 0.000118 grad: 0.2122 (0.2305) loss: 0.9300 (0.9477) time: 0.1781 data: 0.0961 max mem: 9394 +Train: [4] [4600/6250] eta: 0:03:52 lr: 0.000118 grad: 0.3162 (0.2307) loss: 0.9243 (0.9473) time: 0.1338 data: 0.0487 max mem: 9394 +Train: [4] [4700/6250] eta: 0:03:38 lr: 0.000119 grad: 0.1685 (0.2301) loss: 0.9305 (0.9469) time: 0.1270 data: 0.0306 max mem: 9394 +Train: [4] [4800/6250] eta: 0:03:24 lr: 0.000119 grad: 0.1711 (0.2299) loss: 0.9276 (0.9464) time: 0.1498 data: 0.0705 max mem: 9394 +Train: [4] [4900/6250] eta: 0:03:10 lr: 0.000120 grad: 0.2146 (0.2295) loss: 0.9267 (0.9461) time: 0.1320 data: 0.0513 max mem: 9394 +Train: [4] [5000/6250] eta: 0:02:56 lr: 0.000120 grad: 0.1964 (0.2293) loss: 0.9250 (0.9456) time: 0.2500 data: 0.1506 max mem: 9394 +Train: [4] [5100/6250] eta: 0:02:42 lr: 0.000120 grad: 0.2480 (0.2295) loss: 0.9242 (0.9452) time: 0.1070 data: 0.0240 max mem: 9394 +Train: [4] [5200/6250] eta: 0:02:27 lr: 0.000121 grad: 0.1603 (0.2290) loss: 0.9247 (0.9448) time: 0.1400 data: 0.0622 max mem: 9394 +Train: [4] [5300/6250] eta: 0:02:13 lr: 0.000121 grad: 0.1762 (0.2281) loss: 0.9224 (0.9443) time: 0.1248 data: 0.0437 max mem: 9394 +Train: [4] [5400/6250] eta: 0:01:59 lr: 0.000122 grad: 0.2152 (0.2276) loss: 0.9185 (0.9439) time: 0.1503 data: 0.0673 max mem: 9394 +Train: [4] [5500/6250] eta: 0:01:45 lr: 0.000122 grad: 0.1900 (0.2273) loss: 0.9196 (0.9434) time: 0.1476 data: 0.0640 max mem: 9394 +Train: [4] [5600/6250] eta: 0:01:31 lr: 0.000122 grad: 0.2293 (0.2273) loss: 0.9182 (0.9430) time: 0.1406 data: 0.0546 max mem: 9394 +Train: [4] [5700/6250] eta: 0:01:17 lr: 0.000123 grad: 0.2067 (0.2268) loss: 0.9173 (0.9426) time: 0.1282 data: 0.0446 max mem: 9394 +Train: [4] [5800/6250] eta: 0:01:03 lr: 0.000123 grad: 0.1761 (0.2261) loss: 0.9205 (0.9422) time: 0.1396 data: 0.0518 max mem: 9394 +Train: [4] [5900/6250] eta: 0:00:49 lr: 0.000124 grad: 0.1757 (0.2256) loss: 0.9159 (0.9418) time: 0.1439 data: 0.0611 max mem: 9394 +Train: [4] [6000/6250] eta: 0:00:35 lr: 0.000124 grad: 0.1778 (0.2254) loss: 0.9140 (0.9413) time: 0.1308 data: 0.0442 max mem: 9394 +Train: [4] [6100/6250] eta: 0:00:21 lr: 0.000124 grad: 0.1822 (0.2248) loss: 0.9200 (0.9409) time: 0.1308 data: 0.0512 max mem: 9394 +Train: [4] [6200/6250] eta: 0:00:07 lr: 0.000125 grad: 0.1544 (0.2242) loss: 0.9184 (0.9406) time: 0.1268 data: 0.0452 max mem: 9394 +Train: [4] [6249/6250] eta: 0:00:00 lr: 0.000125 grad: 0.1477 (0.2238) loss: 0.9161 (0.9404) time: 0.1180 data: 0.0370 max mem: 9394 +Train: [4] Total time: 0:14:39 (0.1407 s / it) +Averaged stats: lr: 0.000125 grad: 0.1477 (0.2238) loss: 0.9161 (0.9404) +Eval (hcp-train-subset): [4] [ 0/62] eta: 0:03:02 loss: 0.9266 (0.9266) time: 2.9377 data: 2.8604 max mem: 9394 +Eval (hcp-train-subset): [4] [61/62] eta: 0:00:00 loss: 0.9236 (0.9216) time: 0.1594 data: 0.1326 max mem: 9394 +Eval (hcp-train-subset): [4] Total time: 0:00:14 (0.2411 s / it) +Averaged stats (hcp-train-subset): loss: 0.9236 (0.9216) +Making plots (hcp-train-subset): example=43 +Eval (hcp-val): [4] [ 0/62] eta: 0:04:16 loss: 0.9127 (0.9127) time: 4.1375 data: 4.1045 max mem: 9394 +Eval (hcp-val): [4] [61/62] eta: 0:00:00 loss: 0.9172 (0.9162) time: 0.1293 data: 0.1027 max mem: 9394 +Eval (hcp-val): [4] Total time: 0:00:12 (0.1994 s / it) +Averaged stats (hcp-val): loss: 0.9172 (0.9162) +Making plots (hcp-val): example=58 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +Train: [5] [ 0/6250] eta: 7:22:16 lr: 0.000125 grad: 0.2098 (0.2098) loss: 0.8854 (0.8854) time: 4.2458 data: 3.9732 max mem: 9394 +Train: [5] [ 100/6250] eta: 0:19:42 lr: 0.000125 grad: 0.1540 (0.2519) loss: 0.9175 (0.9155) time: 0.1651 data: 0.0801 max mem: 9394 +Train: [5] [ 200/6250] eta: 0:17:03 lr: 0.000125 grad: 0.1655 (0.2165) loss: 0.9146 (0.9147) time: 0.1361 data: 0.0501 max mem: 9394 +Train: [5] [ 300/6250] eta: 0:15:32 lr: 0.000125 grad: 0.2031 (0.2119) loss: 0.9169 (0.9149) time: 0.1233 data: 0.0371 max mem: 9394 +Train: [5] [ 400/6250] eta: 0:14:44 lr: 0.000125 grad: 0.2259 (0.2087) loss: 0.9150 (0.9151) time: 0.1398 data: 0.0550 max mem: 9394 +Train: [5] [ 500/6250] eta: 0:14:08 lr: 0.000125 grad: 0.1720 (0.2022) loss: 0.9141 (0.9150) time: 0.1444 data: 0.0472 max mem: 9394 +Train: [5] [ 600/6250] eta: 0:14:01 lr: 0.000125 grad: 0.1440 (0.2009) loss: 0.9134 (0.9149) time: 0.1552 data: 0.0568 max mem: 9394 +Train: [5] [ 700/6250] eta: 0:13:40 lr: 0.000125 grad: 0.1701 (0.1978) loss: 0.9159 (0.9148) time: 0.1439 data: 0.0579 max mem: 9394 +Train: [5] [ 800/6250] eta: 0:13:30 lr: 0.000125 grad: 0.1659 (0.1996) loss: 0.9161 (0.9146) time: 0.1568 data: 0.0687 max mem: 9394 +Train: [5] [ 900/6250] eta: 0:13:15 lr: 0.000125 grad: 0.1627 (0.1958) loss: 0.9073 (0.9144) time: 0.1729 data: 0.0901 max mem: 9394 +Train: [5] [1000/6250] eta: 0:13:00 lr: 0.000125 grad: 0.1476 (0.1926) loss: 0.9120 (0.9142) time: 0.1467 data: 0.0657 max mem: 9394 +Train: [5] [1100/6250] eta: 0:12:41 lr: 0.000125 grad: 0.1715 (0.1935) loss: 0.9086 (0.9140) time: 0.1236 data: 0.0363 max mem: 9394 +Train: [5] [1200/6250] eta: 0:12:24 lr: 0.000125 grad: 0.1588 (0.1916) loss: 0.9095 (0.9137) time: 0.1351 data: 0.0436 max mem: 9394 +Train: [5] [1300/6250] eta: 0:12:06 lr: 0.000125 grad: 0.1553 (0.1906) loss: 0.9092 (0.9134) time: 0.1444 data: 0.0661 max mem: 9394 +Train: [5] [1400/6250] eta: 0:11:48 lr: 0.000125 grad: 0.1552 (0.1891) loss: 0.9109 (0.9132) time: 0.1395 data: 0.0579 max mem: 9394 +Train: [5] [1500/6250] eta: 0:11:30 lr: 0.000125 grad: 0.1770 (0.1884) loss: 0.9074 (0.9129) time: 0.1430 data: 0.0329 max mem: 9394 +Train: [5] [1600/6250] eta: 0:11:20 lr: 0.000125 grad: 0.1564 (0.1868) loss: 0.9056 (0.9125) time: 0.1316 data: 0.0394 max mem: 9394 +Train: [5] [1700/6250] eta: 0:11:02 lr: 0.000125 grad: 0.1527 (0.1859) loss: 0.9060 (0.9122) time: 0.1392 data: 0.0584 max mem: 9394 +Train: [5] [1800/6250] eta: 0:10:46 lr: 0.000125 grad: 0.1507 (0.1852) loss: 0.9047 (0.9118) time: 0.1370 data: 0.0595 max mem: 9394 +Train: [5] [1900/6250] eta: 0:10:31 lr: 0.000125 grad: 0.1768 (0.1849) loss: 0.9018 (0.9113) time: 0.1199 data: 0.0345 max mem: 9394 +Train: [5] [2000/6250] eta: 0:10:15 lr: 0.000125 grad: 0.1688 (0.1839) loss: 0.9001 (0.9108) time: 0.1487 data: 0.0662 max mem: 9394 +Train: [5] [2100/6250] eta: 0:10:00 lr: 0.000125 grad: 0.1500 (0.1829) loss: 0.8982 (0.9103) time: 0.1348 data: 0.0501 max mem: 9394 +Train: [5] [2200/6250] eta: 0:09:45 lr: 0.000125 grad: 0.1669 (0.1824) loss: 0.8994 (0.9098) time: 0.1399 data: 0.0600 max mem: 9394 +Train: [5] [2300/6250] eta: 0:09:29 lr: 0.000125 grad: 0.1751 (0.1823) loss: 0.8975 (0.9094) time: 0.1324 data: 0.0516 max mem: 9394 +Train: [5] [2400/6250] eta: 0:09:13 lr: 0.000125 grad: 0.1530 (0.1814) loss: 0.8995 (0.9089) time: 0.1306 data: 0.0499 max mem: 9394 +Train: [5] [2500/6250] eta: 0:08:58 lr: 0.000125 grad: 0.1449 (0.1805) loss: 0.8968 (0.9084) time: 0.1411 data: 0.0563 max mem: 9394 +Train: [5] [2600/6250] eta: 0:08:42 lr: 0.000125 grad: 0.1475 (0.1800) loss: 0.8961 (0.9080) time: 0.1400 data: 0.0552 max mem: 9394 +Train: [5] [2700/6250] eta: 0:08:27 lr: 0.000125 grad: 0.1357 (0.1789) loss: 0.8981 (0.9076) time: 0.1481 data: 0.0669 max mem: 9394 +Train: [5] [2800/6250] eta: 0:08:11 lr: 0.000125 grad: 0.1499 (0.1786) loss: 0.8916 (0.9071) time: 0.1495 data: 0.0686 max mem: 9394 +Train: [5] [2900/6250] eta: 0:07:56 lr: 0.000125 grad: 0.1433 (0.1778) loss: 0.8916 (0.9067) time: 0.1387 data: 0.0604 max mem: 9394 +Train: [5] [3000/6250] eta: 0:07:41 lr: 0.000125 grad: 0.1580 (0.1770) loss: 0.8924 (0.9062) time: 0.1266 data: 0.0436 max mem: 9394 +Train: [5] [3100/6250] eta: 0:07:26 lr: 0.000125 grad: 0.1753 (0.1767) loss: 0.8902 (0.9057) time: 0.1306 data: 0.0457 max mem: 9394 +Train: [5] [3200/6250] eta: 0:07:11 lr: 0.000125 grad: 0.1375 (0.1763) loss: 0.8889 (0.9052) time: 0.1244 data: 0.0418 max mem: 9394 +Train: [5] [3300/6250] eta: 0:06:56 lr: 0.000125 grad: 0.1518 (0.1758) loss: 0.8905 (0.9048) time: 0.1497 data: 0.0721 max mem: 9394 +Train: [5] [3400/6250] eta: 0:06:41 lr: 0.000125 grad: 0.1424 (0.1753) loss: 0.8876 (0.9043) time: 0.1158 data: 0.0325 max mem: 9394 +Train: [5] [3500/6250] eta: 0:06:26 lr: 0.000125 grad: 0.1446 (0.1747) loss: 0.8887 (0.9039) time: 0.1284 data: 0.0481 max mem: 9394 +Train: [5] [3600/6250] eta: 0:06:12 lr: 0.000125 grad: 0.1781 (0.1742) loss: 0.8907 (0.9035) time: 0.1269 data: 0.0448 max mem: 9394 +Train: [5] [3700/6250] eta: 0:05:57 lr: 0.000125 grad: 0.1403 (0.1735) loss: 0.8910 (0.9031) time: 0.1334 data: 0.0518 max mem: 9394 +Train: [5] [3800/6250] eta: 0:05:43 lr: 0.000125 grad: 0.1331 (0.1725) loss: 0.8859 (0.9027) time: 0.1330 data: 0.0500 max mem: 9394 +Train: [5] [3900/6250] eta: 0:05:29 lr: 0.000125 grad: 0.1209 (0.1717) loss: 0.8881 (0.9024) time: 0.1331 data: 0.0561 max mem: 9394 +Train: [5] [4000/6250] eta: 0:05:15 lr: 0.000125 grad: 0.1383 (0.1709) loss: 0.8875 (0.9020) time: 0.1451 data: 0.0603 max mem: 9394 +Train: [5] [4100/6250] eta: 0:05:00 lr: 0.000125 grad: 0.1289 (0.1702) loss: 0.8888 (0.9016) time: 0.1295 data: 0.0452 max mem: 9394 +Train: [5] [4200/6250] eta: 0:04:46 lr: 0.000125 grad: 0.1297 (0.1693) loss: 0.8835 (0.9012) time: 0.1441 data: 0.0643 max mem: 9394 +Train: [5] [4300/6250] eta: 0:04:32 lr: 0.000125 grad: 0.1344 (0.1685) loss: 0.8826 (0.9009) time: 0.1405 data: 0.0574 max mem: 9394 +Train: [5] [4400/6250] eta: 0:04:18 lr: 0.000125 grad: 0.1199 (0.1675) loss: 0.8889 (0.9005) time: 0.1805 data: 0.0994 max mem: 9394 +Train: [5] [4500/6250] eta: 0:04:04 lr: 0.000125 grad: 0.1194 (0.1668) loss: 0.8871 (0.9002) time: 0.1388 data: 0.0581 max mem: 9394 +Train: [5] [4600/6250] eta: 0:03:50 lr: 0.000125 grad: 0.1181 (0.1659) loss: 0.8832 (0.8998) time: 0.1483 data: 0.0725 max mem: 9394 +Train: [5] [4700/6250] eta: 0:03:36 lr: 0.000125 grad: 0.1099 (0.1650) loss: 0.8884 (0.8995) time: 0.1321 data: 0.0480 max mem: 9394 +Train: [5] [4800/6250] eta: 0:03:22 lr: 0.000125 grad: 0.1237 (0.1645) loss: 0.8853 (0.8992) time: 0.1439 data: 0.0622 max mem: 9394 +Train: [5] [4900/6250] eta: 0:03:08 lr: 0.000125 grad: 0.1160 (0.1638) loss: 0.8795 (0.8989) time: 0.1214 data: 0.0401 max mem: 9394 +Train: [5] [5000/6250] eta: 0:02:54 lr: 0.000125 grad: 0.1360 (0.1631) loss: 0.8833 (0.8985) time: 0.1439 data: 0.0640 max mem: 9394 +Train: [5] [5100/6250] eta: 0:02:40 lr: 0.000125 grad: 0.1243 (0.1623) loss: 0.8843 (0.8982) time: 0.1469 data: 0.0631 max mem: 9394 +Train: [5] [5200/6250] eta: 0:02:26 lr: 0.000125 grad: 0.1032 (0.1614) loss: 0.8817 (0.8979) time: 0.1283 data: 0.0455 max mem: 9394 +Train: [5] [5300/6250] eta: 0:02:12 lr: 0.000125 grad: 0.1140 (0.1606) loss: 0.8771 (0.8975) time: 0.1397 data: 0.0541 max mem: 9394 +Train: [5] [5400/6250] eta: 0:01:58 lr: 0.000125 grad: 0.1247 (0.1600) loss: 0.8777 (0.8972) time: 0.1435 data: 0.0643 max mem: 9394 +Train: [5] [5500/6250] eta: 0:01:44 lr: 0.000125 grad: 0.1090 (0.1593) loss: 0.8838 (0.8969) time: 0.1395 data: 0.0598 max mem: 9394 +Train: [5] [5600/6250] eta: 0:01:30 lr: 0.000125 grad: 0.1162 (0.1585) loss: 0.8762 (0.8967) time: 0.1294 data: 0.0469 max mem: 9394 +Train: [5] [5700/6250] eta: 0:01:17 lr: 0.000125 grad: 0.1090 (0.1578) loss: 0.8777 (0.8964) time: 0.1215 data: 0.0318 max mem: 9394 +Train: [5] [5800/6250] eta: 0:01:02 lr: 0.000125 grad: 0.1310 (0.1572) loss: 0.8727 (0.8961) time: 0.1403 data: 0.0606 max mem: 9394 +Train: [5] [5900/6250] eta: 0:00:48 lr: 0.000125 grad: 0.1254 (0.1567) loss: 0.8800 (0.8958) time: 0.1086 data: 0.0258 max mem: 9394 +Train: [5] [6000/6250] eta: 0:00:34 lr: 0.000125 grad: 0.1283 (0.1561) loss: 0.8780 (0.8955) time: 0.1067 data: 0.0212 max mem: 9394 +Train: [5] [6100/6250] eta: 0:00:20 lr: 0.000125 grad: 0.1198 (0.1555) loss: 0.8786 (0.8952) time: 0.0963 data: 0.0068 max mem: 9394 +Train: [5] [6200/6250] eta: 0:00:06 lr: 0.000125 grad: 0.1125 (0.1549) loss: 0.8755 (0.8949) time: 0.1334 data: 0.0514 max mem: 9394 +Train: [5] [6249/6250] eta: 0:00:00 lr: 0.000125 grad: 0.1166 (0.1546) loss: 0.8723 (0.8947) time: 0.1569 data: 0.0763 max mem: 9394 +Train: [5] Total time: 0:14:38 (0.1405 s / it) +Averaged stats: lr: 0.000125 grad: 0.1166 (0.1546) loss: 0.8723 (0.8947) +Eval (hcp-train-subset): [5] [ 0/62] eta: 0:03:26 loss: 0.8896 (0.8896) time: 3.3311 data: 3.2573 max mem: 9394 +Eval (hcp-train-subset): [5] [61/62] eta: 0:00:00 loss: 0.8851 (0.8816) time: 0.1417 data: 0.1140 max mem: 9394 +Eval (hcp-train-subset): [5] Total time: 0:00:14 (0.2279 s / it) +Averaged stats (hcp-train-subset): loss: 0.8851 (0.8816) +Eval (hcp-val): [5] [ 0/62] eta: 0:03:48 loss: 0.8739 (0.8739) time: 3.6785 data: 3.6164 max mem: 9394 +Eval (hcp-val): [5] [61/62] eta: 0:00:00 loss: 0.8754 (0.8752) time: 0.1067 data: 0.0819 max mem: 9394 +Eval (hcp-val): [5] Total time: 0:00:12 (0.2062 s / it) +Averaged stats (hcp-val): loss: 0.8754 (0.8752) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +Train: [6] [ 0/6250] eta: 5:50:26 lr: 0.000125 grad: 0.0785 (0.0785) loss: 0.8977 (0.8977) time: 3.3643 data: 3.1786 max mem: 9394 +Train: [6] [ 100/6250] eta: 0:19:45 lr: 0.000125 grad: 0.1135 (0.1471) loss: 0.8774 (0.8820) time: 0.1375 data: 0.0570 max mem: 9394 +Train: [6] [ 200/6250] eta: 0:17:11 lr: 0.000125 grad: 0.1127 (0.1314) loss: 0.8839 (0.8800) time: 0.1410 data: 0.0535 max mem: 9394 +Train: [6] [ 300/6250] eta: 0:16:03 lr: 0.000125 grad: 0.1094 (0.1281) loss: 0.8724 (0.8795) time: 0.1573 data: 0.0687 max mem: 9394 +Train: [6] [ 400/6250] eta: 0:15:29 lr: 0.000125 grad: 0.1288 (0.1271) loss: 0.8795 (0.8790) time: 0.1501 data: 0.0559 max mem: 9394 +Train: [6] [ 500/6250] eta: 0:15:09 lr: 0.000125 grad: 0.1175 (0.1247) loss: 0.8721 (0.8784) time: 0.1460 data: 0.0440 max mem: 9394 +Train: [6] [ 600/6250] eta: 0:14:44 lr: 0.000125 grad: 0.1223 (0.1252) loss: 0.8778 (0.8778) time: 0.1632 data: 0.0799 max mem: 9394 +Train: [6] [ 700/6250] eta: 0:14:18 lr: 0.000125 grad: 0.1207 (0.1234) loss: 0.8716 (0.8773) time: 0.1544 data: 0.0759 max mem: 9394 +Train: [6] [ 800/6250] eta: 0:14:04 lr: 0.000125 grad: 0.1178 (0.1230) loss: 0.8722 (0.8766) time: 0.1627 data: 0.0623 max mem: 9394 +Train: [6] [ 900/6250] eta: 0:14:11 lr: 0.000125 grad: 0.1070 (0.1215) loss: 0.8719 (0.8763) time: 0.1020 data: 0.0002 max mem: 9394 +Train: [6] [1000/6250] eta: 0:13:44 lr: 0.000125 grad: 0.1076 (0.1202) loss: 0.8748 (0.8761) time: 0.1510 data: 0.0692 max mem: 9394 +Train: [6] [1100/6250] eta: 0:13:21 lr: 0.000125 grad: 0.1112 (0.1197) loss: 0.8728 (0.8760) time: 0.1640 data: 0.0459 max mem: 9394 +Train: [6] [1200/6250] eta: 0:13:18 lr: 0.000125 grad: 0.0952 (0.1183) loss: 0.8715 (0.8757) time: 0.0988 data: 0.0002 max mem: 9394 +Train: [6] [1300/6250] eta: 0:12:52 lr: 0.000125 grad: 0.0975 (0.1177) loss: 0.8730 (0.8755) time: 0.1266 data: 0.0462 max mem: 9394 +Train: [6] [1400/6250] eta: 0:12:31 lr: 0.000125 grad: 0.0961 (0.1173) loss: 0.8716 (0.8753) time: 0.1381 data: 0.0608 max mem: 9394 +Train: [6] [1500/6250] eta: 0:12:11 lr: 0.000125 grad: 0.0965 (0.1171) loss: 0.8639 (0.8751) time: 0.1550 data: 0.0773 max mem: 9394 +Train: [6] [1600/6250] eta: 0:11:54 lr: 0.000125 grad: 0.0928 (0.1164) loss: 0.8692 (0.8749) time: 0.1591 data: 0.0644 max mem: 9394 +Train: [6] [1700/6250] eta: 0:11:34 lr: 0.000125 grad: 0.1143 (0.1161) loss: 0.8719 (0.8746) time: 0.1212 data: 0.0361 max mem: 9394 +Train: [6] [1800/6250] eta: 0:11:17 lr: 0.000125 grad: 0.0977 (0.1152) loss: 0.8707 (0.8744) time: 0.1249 data: 0.0423 max mem: 9394 +Train: [6] [1900/6250] eta: 0:11:00 lr: 0.000125 grad: 0.1071 (0.1150) loss: 0.8716 (0.8742) time: 0.1537 data: 0.0701 max mem: 9394 +Train: [6] [2000/6250] eta: 0:10:39 lr: 0.000125 grad: 0.0915 (0.1142) loss: 0.8718 (0.8741) time: 0.1195 data: 0.0336 max mem: 9394 +Train: [6] [2100/6250] eta: 0:10:21 lr: 0.000125 grad: 0.0995 (0.1136) loss: 0.8740 (0.8739) time: 0.1227 data: 0.0449 max mem: 9394 +Train: [6] [2200/6250] eta: 0:10:04 lr: 0.000125 grad: 0.0947 (0.1132) loss: 0.8732 (0.8737) time: 0.1191 data: 0.0359 max mem: 9394 +Train: [6] [2300/6250] eta: 0:09:49 lr: 0.000125 grad: 0.0968 (0.1128) loss: 0.8670 (0.8735) time: 0.1650 data: 0.0871 max mem: 9394 +Train: [6] [2400/6250] eta: 0:09:31 lr: 0.000125 grad: 0.0910 (0.1122) loss: 0.8656 (0.8733) time: 0.1414 data: 0.0542 max mem: 9394 +Train: [6] [2500/6250] eta: 0:09:15 lr: 0.000125 grad: 0.0949 (0.1122) loss: 0.8706 (0.8732) time: 0.1529 data: 0.0761 max mem: 9394 +Train: [6] [2600/6250] eta: 0:08:58 lr: 0.000125 grad: 0.0924 (0.1117) loss: 0.8770 (0.8730) time: 0.1307 data: 0.0478 max mem: 9394 +Train: [6] [2700/6250] eta: 0:08:41 lr: 0.000125 grad: 0.0912 (0.1112) loss: 0.8666 (0.8728) time: 0.1203 data: 0.0353 max mem: 9394 +Train: [6] [2800/6250] eta: 0:08:26 lr: 0.000125 grad: 0.1051 (0.1111) loss: 0.8694 (0.8727) time: 0.1518 data: 0.0594 max mem: 9394 +Train: [6] [2900/6250] eta: 0:08:10 lr: 0.000125 grad: 0.0949 (0.1106) loss: 0.8709 (0.8726) time: 0.1325 data: 0.0447 max mem: 9394 +Train: [6] [3000/6250] eta: 0:07:55 lr: 0.000125 grad: 0.0925 (0.1104) loss: 0.8760 (0.8725) time: 0.1265 data: 0.0392 max mem: 9394 +Train: [6] [3100/6250] eta: 0:07:39 lr: 0.000125 grad: 0.1013 (0.1102) loss: 0.8698 (0.8725) time: 0.1218 data: 0.0338 max mem: 9394 +Train: [6] [3200/6250] eta: 0:07:24 lr: 0.000125 grad: 0.1013 (0.1097) loss: 0.8686 (0.8724) time: 0.1244 data: 0.0451 max mem: 9394 +Train: [6] [3300/6250] eta: 0:07:12 lr: 0.000125 grad: 0.0915 (0.1096) loss: 0.8716 (0.8724) time: 0.1444 data: 0.0648 max mem: 9394 +Train: [6] [3400/6250] eta: 0:06:56 lr: 0.000125 grad: 0.0858 (0.1093) loss: 0.8701 (0.8724) time: 0.1182 data: 0.0364 max mem: 9394 +Train: [6] [3500/6250] eta: 0:06:40 lr: 0.000125 grad: 0.0894 (0.1088) loss: 0.8704 (0.8723) time: 0.1461 data: 0.0633 max mem: 9394 +Train: [6] [3600/6250] eta: 0:06:25 lr: 0.000125 grad: 0.0890 (0.1083) loss: 0.8647 (0.8722) time: 0.1559 data: 0.0699 max mem: 9394 +Train: [6] [3700/6250] eta: 0:06:09 lr: 0.000125 grad: 0.0873 (0.1078) loss: 0.8720 (0.8721) time: 0.1391 data: 0.0602 max mem: 9394 +Train: [6] [3800/6250] eta: 0:05:54 lr: 0.000125 grad: 0.0845 (0.1075) loss: 0.8728 (0.8720) time: 0.1597 data: 0.0754 max mem: 9394 +Train: [6] [3900/6250] eta: 0:05:39 lr: 0.000125 grad: 0.0933 (0.1073) loss: 0.8628 (0.8719) time: 0.1369 data: 0.0497 max mem: 9394 +Train: [6] [4000/6250] eta: 0:05:25 lr: 0.000125 grad: 0.0832 (0.1068) loss: 0.8680 (0.8718) time: 0.1523 data: 0.0768 max mem: 9394 +Train: [6] [4100/6250] eta: 0:05:10 lr: 0.000125 grad: 0.0902 (0.1065) loss: 0.8668 (0.8718) time: 0.1479 data: 0.0622 max mem: 9394 +Train: [6] [4200/6250] eta: 0:04:55 lr: 0.000125 grad: 0.0831 (0.1060) loss: 0.8697 (0.8717) time: 0.1211 data: 0.0421 max mem: 9394 +Train: [6] [4300/6250] eta: 0:04:40 lr: 0.000125 grad: 0.0908 (0.1057) loss: 0.8676 (0.8716) time: 0.1491 data: 0.0672 max mem: 9394 +Train: [6] [4400/6250] eta: 0:04:25 lr: 0.000125 grad: 0.0895 (0.1055) loss: 0.8667 (0.8716) time: 0.1579 data: 0.0723 max mem: 9394 +Train: [6] [4500/6250] eta: 0:04:11 lr: 0.000125 grad: 0.0857 (0.1051) loss: 0.8699 (0.8716) time: 0.1363 data: 0.0535 max mem: 9394 +Train: [6] [4600/6250] eta: 0:03:56 lr: 0.000125 grad: 0.0898 (0.1048) loss: 0.8703 (0.8715) time: 0.1270 data: 0.0388 max mem: 9394 +Train: [6] [4700/6250] eta: 0:03:42 lr: 0.000125 grad: 0.0816 (0.1045) loss: 0.8716 (0.8715) time: 0.1504 data: 0.0666 max mem: 9394 +Train: [6] [4800/6250] eta: 0:03:27 lr: 0.000125 grad: 0.0840 (0.1042) loss: 0.8674 (0.8714) time: 0.1402 data: 0.0583 max mem: 9394 +Train: [6] [4900/6250] eta: 0:03:13 lr: 0.000125 grad: 0.0870 (0.1041) loss: 0.8690 (0.8713) time: 0.1517 data: 0.0734 max mem: 9394 +Train: [6] [5000/6250] eta: 0:02:59 lr: 0.000125 grad: 0.0859 (0.1038) loss: 0.8642 (0.8712) time: 0.1453 data: 0.0628 max mem: 9394 +Train: [6] [5100/6250] eta: 0:02:44 lr: 0.000125 grad: 0.0842 (0.1036) loss: 0.8679 (0.8711) time: 0.1360 data: 0.0552 max mem: 9394 +Train: [6] [5200/6250] eta: 0:02:30 lr: 0.000125 grad: 0.0813 (0.1033) loss: 0.8634 (0.8710) time: 0.1273 data: 0.0386 max mem: 9394 +Train: [6] [5300/6250] eta: 0:02:15 lr: 0.000125 grad: 0.0966 (0.1034) loss: 0.8657 (0.8709) time: 0.0866 data: 0.0018 max mem: 9394 +Train: [6] [5400/6250] eta: 0:02:01 lr: 0.000125 grad: 0.0798 (0.1032) loss: 0.8604 (0.8708) time: 0.1365 data: 0.0558 max mem: 9394 +Train: [6] [5500/6250] eta: 0:01:46 lr: 0.000125 grad: 0.0895 (0.1030) loss: 0.8663 (0.8707) time: 0.1316 data: 0.0497 max mem: 9394 +Train: [6] [5600/6250] eta: 0:01:32 lr: 0.000125 grad: 0.0815 (0.1028) loss: 0.8652 (0.8706) time: 0.1311 data: 0.0473 max mem: 9394 +Train: [6] [5700/6250] eta: 0:01:18 lr: 0.000125 grad: 0.0850 (0.1025) loss: 0.8619 (0.8705) time: 0.1281 data: 0.0444 max mem: 9394 +Train: [6] [5800/6250] eta: 0:01:04 lr: 0.000125 grad: 0.0960 (0.1024) loss: 0.8650 (0.8705) time: 0.1421 data: 0.0639 max mem: 9394 +Train: [6] [5900/6250] eta: 0:00:49 lr: 0.000125 grad: 0.0919 (0.1023) loss: 0.8657 (0.8703) time: 0.1517 data: 0.0596 max mem: 9394 +Train: [6] [6000/6250] eta: 0:00:35 lr: 0.000125 grad: 0.0779 (0.1020) loss: 0.8690 (0.8703) time: 0.1078 data: 0.0162 max mem: 9394 +Train: [6] [6100/6250] eta: 0:00:21 lr: 0.000125 grad: 0.0844 (0.1019) loss: 0.8642 (0.8702) time: 0.1318 data: 0.0443 max mem: 9394 +Train: [6] [6200/6250] eta: 0:00:07 lr: 0.000125 grad: 0.0877 (0.1016) loss: 0.8666 (0.8702) time: 0.1413 data: 0.0580 max mem: 9394 +Train: [6] [6249/6250] eta: 0:00:00 lr: 0.000125 grad: 0.0969 (0.1015) loss: 0.8680 (0.8701) time: 0.1361 data: 0.0534 max mem: 9394 +Train: [6] Total time: 0:14:52 (0.1428 s / it) +Averaged stats: lr: 0.000125 grad: 0.0969 (0.1015) loss: 0.8680 (0.8701) +Eval (hcp-train-subset): [6] [ 0/62] eta: 0:03:37 loss: 0.8764 (0.8764) time: 3.5060 data: 3.4092 max mem: 9394 +Eval (hcp-train-subset): [6] [61/62] eta: 0:00:00 loss: 0.8688 (0.8688) time: 0.1298 data: 0.1024 max mem: 9394 +Eval (hcp-train-subset): [6] Total time: 0:00:13 (0.2154 s / it) +Averaged stats (hcp-train-subset): loss: 0.8688 (0.8688) +Eval (hcp-val): [6] [ 0/62] eta: 0:04:45 loss: 0.8586 (0.8586) time: 4.5982 data: 4.5701 max mem: 9394 +Eval (hcp-val): [6] [61/62] eta: 0:00:00 loss: 0.8616 (0.8632) time: 0.1342 data: 0.1091 max mem: 9394 +Eval (hcp-val): [6] Total time: 0:00:12 (0.2051 s / it) +Averaged stats (hcp-val): loss: 0.8616 (0.8632) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +Train: [7] [ 0/6250] eta: 11:57:03 lr: 0.000125 grad: 0.1107 (0.1107) loss: 0.8698 (0.8698) time: 6.8838 data: 6.7938 max mem: 9394 +Train: [7] [ 100/6250] eta: 0:19:49 lr: 0.000125 grad: 0.0777 (0.1201) loss: 0.8657 (0.8712) time: 0.1310 data: 0.0496 max mem: 9394 +Train: [7] [ 200/6250] eta: 0:16:52 lr: 0.000125 grad: 0.0919 (0.1101) loss: 0.8570 (0.8646) time: 0.1428 data: 0.0582 max mem: 9394 +Train: [7] [ 300/6250] eta: 0:16:21 lr: 0.000125 grad: 0.0884 (0.1037) loss: 0.8622 (0.8626) time: 0.1912 data: 0.0802 max mem: 9394 +Train: [7] [ 400/6250] eta: 0:16:13 lr: 0.000125 grad: 0.0840 (0.0995) loss: 0.8569 (0.8618) time: 0.1738 data: 0.0783 max mem: 9394 +Train: [7] [ 500/6250] eta: 0:15:53 lr: 0.000125 grad: 0.0801 (0.0968) loss: 0.8594 (0.8616) time: 0.1587 data: 0.0609 max mem: 9394 +Train: [7] [ 600/6250] eta: 0:15:25 lr: 0.000125 grad: 0.0862 (0.0947) loss: 0.8609 (0.8615) time: 0.1469 data: 0.0570 max mem: 9394 +Train: [7] [ 700/6250] eta: 0:14:57 lr: 0.000125 grad: 0.0844 (0.0940) loss: 0.8662 (0.8620) time: 0.1446 data: 0.0416 max mem: 9394 +Train: [7] [ 800/6250] eta: 0:14:36 lr: 0.000125 grad: 0.0765 (0.0932) loss: 0.8699 (0.8623) time: 0.1838 data: 0.0978 max mem: 9394 +Train: [7] [ 900/6250] eta: 0:14:31 lr: 0.000125 grad: 0.0797 (0.0927) loss: 0.8621 (0.8624) time: 0.1585 data: 0.0790 max mem: 9394 +Train: [7] [1000/6250] eta: 0:14:33 lr: 0.000125 grad: 0.0836 (0.0926) loss: 0.8646 (0.8627) time: 0.3352 data: 0.2551 max mem: 9394 +Train: [7] [1100/6250] eta: 0:14:00 lr: 0.000125 grad: 0.0823 (0.0919) loss: 0.8627 (0.8628) time: 0.1209 data: 0.0278 max mem: 9394 +Train: [7] [1200/6250] eta: 0:13:49 lr: 0.000125 grad: 0.0783 (0.0913) loss: 0.8594 (0.8627) time: 0.2577 data: 0.1407 max mem: 9394 +Train: [7] [1300/6250] eta: 0:13:27 lr: 0.000125 grad: 0.0765 (0.0908) loss: 0.8620 (0.8627) time: 0.0987 data: 0.0002 max mem: 9394 +Train: [7] [1400/6250] eta: 0:13:03 lr: 0.000125 grad: 0.0762 (0.0903) loss: 0.8656 (0.8626) time: 0.1295 data: 0.0427 max mem: 9394 +Train: [7] [1500/6250] eta: 0:12:39 lr: 0.000125 grad: 0.0785 (0.0899) loss: 0.8598 (0.8625) time: 0.1433 data: 0.0640 max mem: 9394 +Train: [7] [1600/6250] eta: 0:12:16 lr: 0.000125 grad: 0.0825 (0.0902) loss: 0.8589 (0.8624) time: 0.1460 data: 0.0623 max mem: 9394 +Train: [7] [1700/6250] eta: 0:11:58 lr: 0.000125 grad: 0.0891 (0.0899) loss: 0.8588 (0.8622) time: 0.1672 data: 0.0915 max mem: 9394 +Train: [7] [1800/6250] eta: 0:11:38 lr: 0.000125 grad: 0.0848 (0.0896) loss: 0.8584 (0.8621) time: 0.1590 data: 0.0762 max mem: 9394 +Train: [7] [1900/6250] eta: 0:11:25 lr: 0.000125 grad: 0.0850 (0.0894) loss: 0.8568 (0.8620) time: 0.1437 data: 0.0514 max mem: 9394 +Train: [7] [2000/6250] eta: 0:11:04 lr: 0.000125 grad: 0.0779 (0.0892) loss: 0.8618 (0.8619) time: 0.1265 data: 0.0383 max mem: 9394 +Train: [7] [2100/6250] eta: 0:10:44 lr: 0.000125 grad: 0.0822 (0.0890) loss: 0.8615 (0.8619) time: 0.1408 data: 0.0512 max mem: 9394 +Train: [7] [2200/6250] eta: 0:10:25 lr: 0.000125 grad: 0.0926 (0.0888) loss: 0.8599 (0.8618) time: 0.1300 data: 0.0472 max mem: 9394 +Train: [7] [2300/6250] eta: 0:10:07 lr: 0.000125 grad: 0.0848 (0.0885) loss: 0.8593 (0.8618) time: 0.1469 data: 0.0387 max mem: 9394 +Train: [7] [2400/6250] eta: 0:09:50 lr: 0.000125 grad: 0.0829 (0.0884) loss: 0.8648 (0.8618) time: 0.1509 data: 0.0644 max mem: 9394 +Train: [7] [2500/6250] eta: 0:09:33 lr: 0.000125 grad: 0.0779 (0.0882) loss: 0.8607 (0.8617) time: 0.1359 data: 0.0531 max mem: 9394 +Train: [7] [2600/6250] eta: 0:09:15 lr: 0.000125 grad: 0.0854 (0.0880) loss: 0.8611 (0.8617) time: 0.1169 data: 0.0256 max mem: 9394 +Train: [7] [2700/6250] eta: 0:08:57 lr: 0.000125 grad: 0.0819 (0.0878) loss: 0.8636 (0.8618) time: 0.1368 data: 0.0543 max mem: 9394 +Train: [7] [2800/6250] eta: 0:08:39 lr: 0.000125 grad: 0.0769 (0.0875) loss: 0.8599 (0.8618) time: 0.1304 data: 0.0490 max mem: 9394 +Train: [7] [2900/6250] eta: 0:08:23 lr: 0.000125 grad: 0.0754 (0.0872) loss: 0.8612 (0.8618) time: 0.1582 data: 0.0556 max mem: 9394 +Train: [7] [3000/6250] eta: 0:08:06 lr: 0.000125 grad: 0.0761 (0.0869) loss: 0.8589 (0.8619) time: 0.1409 data: 0.0585 max mem: 9394 +Train: [7] [3100/6250] eta: 0:07:49 lr: 0.000125 grad: 0.0733 (0.0867) loss: 0.8616 (0.8619) time: 0.1267 data: 0.0401 max mem: 9394 +Train: [7] [3200/6250] eta: 0:07:33 lr: 0.000125 grad: 0.0704 (0.0864) loss: 0.8663 (0.8619) time: 0.1279 data: 0.0457 max mem: 9394 +Train: [7] [3300/6250] eta: 0:07:17 lr: 0.000125 grad: 0.0816 (0.0862) loss: 0.8632 (0.8619) time: 0.1421 data: 0.0601 max mem: 9394 +Train: [7] [3400/6250] eta: 0:07:02 lr: 0.000125 grad: 0.0830 (0.0860) loss: 0.8617 (0.8620) time: 0.1639 data: 0.0785 max mem: 9394 +Train: [7] [3500/6250] eta: 0:06:46 lr: 0.000125 grad: 0.0706 (0.0857) loss: 0.8623 (0.8620) time: 0.1472 data: 0.0656 max mem: 9394 +Train: [7] [3600/6250] eta: 0:06:33 lr: 0.000125 grad: 0.0721 (0.0856) loss: 0.8611 (0.8620) time: 0.2548 data: 0.0837 max mem: 9394 +Train: [7] [3700/6250] eta: 0:06:17 lr: 0.000125 grad: 0.0742 (0.0854) loss: 0.8580 (0.8620) time: 0.1268 data: 0.0427 max mem: 9394 +Train: [7] [3800/6250] eta: 0:06:01 lr: 0.000125 grad: 0.0762 (0.0852) loss: 0.8576 (0.8620) time: 0.1152 data: 0.0321 max mem: 9394 +Train: [7] [3900/6250] eta: 0:05:47 lr: 0.000125 grad: 0.0888 (0.0852) loss: 0.8572 (0.8619) time: 0.1141 data: 0.0280 max mem: 9394 +Train: [7] [4000/6250] eta: 0:05:31 lr: 0.000125 grad: 0.0770 (0.0850) loss: 0.8577 (0.8619) time: 0.1309 data: 0.0509 max mem: 9394 +Train: [7] [4100/6250] eta: 0:05:16 lr: 0.000125 grad: 0.0761 (0.0848) loss: 0.8597 (0.8619) time: 0.1217 data: 0.0402 max mem: 9394 +Train: [7] [4200/6250] eta: 0:05:01 lr: 0.000125 grad: 0.0750 (0.0847) loss: 0.8587 (0.8618) time: 0.1806 data: 0.0441 max mem: 9394 +Train: [7] [4300/6250] eta: 0:04:47 lr: 0.000125 grad: 0.0883 (0.0846) loss: 0.8563 (0.8618) time: 0.1388 data: 0.0542 max mem: 9394 +Train: [7] [4400/6250] eta: 0:04:32 lr: 0.000125 grad: 0.0769 (0.0844) loss: 0.8645 (0.8617) time: 0.1348 data: 0.0521 max mem: 9394 +Train: [7] [4500/6250] eta: 0:04:18 lr: 0.000125 grad: 0.0870 (0.0843) loss: 0.8602 (0.8617) time: 0.3213 data: 0.1926 max mem: 9394 +Train: [7] [4600/6250] eta: 0:04:02 lr: 0.000125 grad: 0.0799 (0.0842) loss: 0.8633 (0.8617) time: 0.1243 data: 0.0470 max mem: 9394 +Train: [7] [4700/6250] eta: 0:03:47 lr: 0.000125 grad: 0.0719 (0.0841) loss: 0.8601 (0.8617) time: 0.1399 data: 0.0554 max mem: 9394 +Train: [7] [4800/6250] eta: 0:03:32 lr: 0.000125 grad: 0.0749 (0.0840) loss: 0.8607 (0.8617) time: 0.1328 data: 0.0520 max mem: 9394 +Train: [7] [4900/6250] eta: 0:03:18 lr: 0.000125 grad: 0.0750 (0.0838) loss: 0.8590 (0.8616) time: 0.0967 data: 0.0002 max mem: 9394 +Train: [7] [5000/6250] eta: 0:03:03 lr: 0.000125 grad: 0.0771 (0.0837) loss: 0.8637 (0.8616) time: 0.1372 data: 0.0472 max mem: 9394 +Train: [7] [5100/6250] eta: 0:02:48 lr: 0.000125 grad: 0.0751 (0.0836) loss: 0.8603 (0.8616) time: 0.1449 data: 0.0640 max mem: 9394 +Train: [7] [5200/6250] eta: 0:02:33 lr: 0.000125 grad: 0.0686 (0.0835) loss: 0.8618 (0.8615) time: 0.1393 data: 0.0585 max mem: 9394 +Train: [7] [5300/6250] eta: 0:02:18 lr: 0.000125 grad: 0.0702 (0.0833) loss: 0.8595 (0.8615) time: 0.1489 data: 0.0650 max mem: 9394 +Train: [7] [5400/6250] eta: 0:02:03 lr: 0.000125 grad: 0.0756 (0.0832) loss: 0.8613 (0.8615) time: 0.1472 data: 0.0650 max mem: 9394 +Train: [7] [5500/6250] eta: 0:01:49 lr: 0.000125 grad: 0.0724 (0.0831) loss: 0.8589 (0.8614) time: 0.1161 data: 0.0286 max mem: 9394 +Train: [7] [5600/6250] eta: 0:01:34 lr: 0.000125 grad: 0.0776 (0.0829) loss: 0.8565 (0.8614) time: 0.1223 data: 0.0290 max mem: 9394 +Train: [7] [5700/6250] eta: 0:01:19 lr: 0.000125 grad: 0.0696 (0.0828) loss: 0.8613 (0.8613) time: 0.1265 data: 0.0468 max mem: 9394 +Train: [7] [5800/6250] eta: 0:01:05 lr: 0.000125 grad: 0.0746 (0.0827) loss: 0.8563 (0.8613) time: 0.1431 data: 0.0533 max mem: 9394 +Train: [7] [5900/6250] eta: 0:00:50 lr: 0.000125 grad: 0.0747 (0.0825) loss: 0.8576 (0.8613) time: 0.1187 data: 0.0320 max mem: 9394 +Train: [7] [6000/6250] eta: 0:00:36 lr: 0.000125 grad: 0.0746 (0.0825) loss: 0.8556 (0.8612) time: 0.1342 data: 0.0486 max mem: 9394 +Train: [7] [6100/6250] eta: 0:00:21 lr: 0.000125 grad: 0.0758 (0.0824) loss: 0.8540 (0.8611) time: 0.1313 data: 0.0497 max mem: 9394 +Train: [7] [6200/6250] eta: 0:00:07 lr: 0.000125 grad: 0.0695 (0.0823) loss: 0.8605 (0.8611) time: 0.1242 data: 0.0376 max mem: 9394 +Train: [7] [6249/6250] eta: 0:00:00 lr: 0.000125 grad: 0.0720 (0.0823) loss: 0.8575 (0.8611) time: 0.1232 data: 0.0413 max mem: 9394 +Train: [7] Total time: 0:15:08 (0.1454 s / it) +Averaged stats: lr: 0.000125 grad: 0.0720 (0.0823) loss: 0.8575 (0.8611) +Eval (hcp-train-subset): [7] [ 0/62] eta: 0:04:23 loss: 0.8709 (0.8709) time: 4.2538 data: 4.2233 max mem: 9394 +Eval (hcp-train-subset): [7] [61/62] eta: 0:00:00 loss: 0.8619 (0.8614) time: 0.1382 data: 0.1125 max mem: 9394 +Eval (hcp-train-subset): [7] Total time: 0:00:13 (0.2204 s / it) +Averaged stats (hcp-train-subset): loss: 0.8619 (0.8614) +Eval (hcp-val): [7] [ 0/62] eta: 0:03:13 loss: 0.8520 (0.8520) time: 3.1147 data: 3.0650 max mem: 9394 +Eval (hcp-val): [7] [61/62] eta: 0:00:00 loss: 0.8545 (0.8560) time: 0.1309 data: 0.1046 max mem: 9394 +Eval (hcp-val): [7] Total time: 0:00:12 (0.2086 s / it) +Averaged stats (hcp-val): loss: 0.8545 (0.8560) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +Train: [8] [ 0/6250] eta: 9:56:28 lr: 0.000125 grad: 0.0662 (0.0662) loss: 0.8882 (0.8882) time: 5.7262 data: 5.6213 max mem: 9394 +Train: [8] [ 100/6250] eta: 0:21:26 lr: 0.000125 grad: 0.0903 (0.0966) loss: 0.8535 (0.8577) time: 0.1638 data: 0.0767 max mem: 9394 +Train: [8] [ 200/6250] eta: 0:19:06 lr: 0.000125 grad: 0.0795 (0.0896) loss: 0.8585 (0.8566) time: 0.1706 data: 0.0812 max mem: 9394 +Train: [8] [ 300/6250] eta: 0:18:00 lr: 0.000125 grad: 0.0828 (0.0863) loss: 0.8537 (0.8566) time: 0.1802 data: 0.0846 max mem: 9394 +Train: [8] [ 400/6250] eta: 0:17:29 lr: 0.000125 grad: 0.0769 (0.0847) loss: 0.8608 (0.8568) time: 0.1750 data: 0.0710 max mem: 9394 +Train: [8] [ 500/6250] eta: 0:16:43 lr: 0.000125 grad: 0.0728 (0.0839) loss: 0.8562 (0.8567) time: 0.1431 data: 0.0395 max mem: 9394 +Train: [8] [ 600/6250] eta: 0:16:03 lr: 0.000125 grad: 0.0727 (0.0828) loss: 0.8533 (0.8566) time: 0.1596 data: 0.0688 max mem: 9394 +Train: [8] [ 700/6250] eta: 0:15:30 lr: 0.000125 grad: 0.0736 (0.0826) loss: 0.8604 (0.8564) time: 0.1678 data: 0.0844 max mem: 9394 +Train: [8] [ 800/6250] eta: 0:15:17 lr: 0.000125 grad: 0.0703 (0.0822) loss: 0.8603 (0.8564) time: 0.1332 data: 0.0234 max mem: 9394 +Train: [8] [ 900/6250] eta: 0:15:03 lr: 0.000125 grad: 0.0736 (0.0820) loss: 0.8550 (0.8566) time: 0.1228 data: 0.0320 max mem: 9394 +Train: [8] [1000/6250] eta: 0:14:38 lr: 0.000125 grad: 0.0733 (0.0817) loss: 0.8552 (0.8567) time: 0.1254 data: 0.0282 max mem: 9394 +Train: [8] [1100/6250] eta: 0:14:21 lr: 0.000125 grad: 0.0731 (0.0814) loss: 0.8621 (0.8570) time: 0.1616 data: 0.0698 max mem: 9394 +Train: [8] [1200/6250] eta: 0:13:54 lr: 0.000125 grad: 0.0707 (0.0807) loss: 0.8603 (0.8571) time: 0.1417 data: 0.0555 max mem: 9394 +Train: [8] [1300/6250] eta: 0:13:28 lr: 0.000125 grad: 0.0708 (0.0803) loss: 0.8540 (0.8572) time: 0.1395 data: 0.0519 max mem: 9394 +Train: [8] [1400/6250] eta: 0:13:43 lr: 0.000125 grad: 0.0711 (0.0802) loss: 0.8574 (0.8574) time: 0.1019 data: 0.0002 max mem: 9394 +Train: [8] [1500/6250] eta: 0:13:14 lr: 0.000125 grad: 0.0795 (0.0800) loss: 0.8565 (0.8575) time: 0.1346 data: 0.0472 max mem: 9394 +Train: [8] [1600/6250] eta: 0:12:52 lr: 0.000125 grad: 0.0725 (0.0796) loss: 0.8579 (0.8576) time: 0.1151 data: 0.0184 max mem: 9394 +Train: [8] [1700/6250] eta: 0:12:29 lr: 0.000125 grad: 0.0706 (0.0793) loss: 0.8598 (0.8577) time: 0.1449 data: 0.0566 max mem: 9394 +Train: [8] [1800/6250] eta: 0:12:16 lr: 0.000125 grad: 0.0733 (0.0791) loss: 0.8561 (0.8577) time: 0.2725 data: 0.1872 max mem: 9394 +Train: [8] [1900/6250] eta: 0:11:52 lr: 0.000125 grad: 0.0725 (0.0793) loss: 0.8597 (0.8577) time: 0.1345 data: 0.0528 max mem: 9394 +Train: [8] [2000/6250] eta: 0:11:32 lr: 0.000125 grad: 0.0693 (0.0791) loss: 0.8550 (0.8577) time: 0.1576 data: 0.0749 max mem: 9394 +Train: [8] [2100/6250] eta: 0:11:10 lr: 0.000125 grad: 0.0725 (0.0790) loss: 0.8590 (0.8577) time: 0.1484 data: 0.0698 max mem: 9394 +Train: [8] [2200/6250] eta: 0:10:50 lr: 0.000125 grad: 0.0738 (0.0792) loss: 0.8597 (0.8576) time: 0.1266 data: 0.0438 max mem: 9394 +Train: [8] [2300/6250] eta: 0:10:29 lr: 0.000125 grad: 0.0842 (0.0793) loss: 0.8518 (0.8574) time: 0.1561 data: 0.0764 max mem: 9394 +Train: [8] [2400/6250] eta: 0:10:10 lr: 0.000125 grad: 0.0685 (0.0790) loss: 0.8570 (0.8573) time: 0.1495 data: 0.0648 max mem: 9394 +Train: [8] [2500/6250] eta: 0:09:51 lr: 0.000125 grad: 0.0724 (0.0788) loss: 0.8557 (0.8572) time: 0.1266 data: 0.0463 max mem: 9394 +Train: [8] [2600/6250] eta: 0:09:32 lr: 0.000125 grad: 0.0765 (0.0787) loss: 0.8575 (0.8571) time: 0.1383 data: 0.0561 max mem: 9394 +Train: [8] [2700/6250] eta: 0:09:14 lr: 0.000125 grad: 0.0732 (0.0786) loss: 0.8566 (0.8570) time: 0.1470 data: 0.0642 max mem: 9394 +Train: [8] [2800/6250] eta: 0:08:56 lr: 0.000125 grad: 0.0705 (0.0785) loss: 0.8568 (0.8570) time: 0.1317 data: 0.0513 max mem: 9394 +Train: [8] [2900/6250] eta: 0:08:39 lr: 0.000125 grad: 0.0736 (0.0785) loss: 0.8602 (0.8569) time: 0.1521 data: 0.0684 max mem: 9394 +Train: [8] [3000/6250] eta: 0:08:21 lr: 0.000125 grad: 0.0693 (0.0784) loss: 0.8560 (0.8569) time: 0.1328 data: 0.0428 max mem: 9394 +Train: [8] [3100/6250] eta: 0:08:05 lr: 0.000125 grad: 0.0693 (0.0782) loss: 0.8538 (0.8569) time: 0.1641 data: 0.0684 max mem: 9394 +Train: [8] [3200/6250] eta: 0:07:48 lr: 0.000125 grad: 0.0727 (0.0781) loss: 0.8580 (0.8568) time: 0.1295 data: 0.0440 max mem: 9394 +Train: [8] [3300/6250] eta: 0:07:32 lr: 0.000125 grad: 0.0669 (0.0779) loss: 0.8566 (0.8568) time: 0.1451 data: 0.0585 max mem: 9394 +Train: [8] [3400/6250] eta: 0:07:15 lr: 0.000125 grad: 0.0712 (0.0777) loss: 0.8575 (0.8568) time: 0.1357 data: 0.0535 max mem: 9394 +Train: [8] [3500/6250] eta: 0:06:59 lr: 0.000125 grad: 0.0727 (0.0777) loss: 0.8541 (0.8568) time: 0.1473 data: 0.0654 max mem: 9394 +Train: [8] [3600/6250] eta: 0:06:43 lr: 0.000125 grad: 0.0740 (0.0777) loss: 0.8553 (0.8568) time: 0.1569 data: 0.0619 max mem: 9394 +Train: [8] [3700/6250] eta: 0:06:27 lr: 0.000125 grad: 0.0787 (0.0777) loss: 0.8574 (0.8567) time: 0.1457 data: 0.0649 max mem: 9394 +Train: [8] [3800/6250] eta: 0:06:11 lr: 0.000125 grad: 0.0734 (0.0777) loss: 0.8594 (0.8567) time: 0.1322 data: 0.0479 max mem: 9394 +Train: [8] [3900/6250] eta: 0:05:55 lr: 0.000125 grad: 0.0696 (0.0777) loss: 0.8548 (0.8566) time: 0.1314 data: 0.0462 max mem: 9394 +Train: [8] [4000/6250] eta: 0:05:40 lr: 0.000125 grad: 0.0726 (0.0776) loss: 0.8509 (0.8566) time: 0.1341 data: 0.0510 max mem: 9394 +Train: [8] [4100/6250] eta: 0:05:24 lr: 0.000125 grad: 0.0676 (0.0776) loss: 0.8563 (0.8566) time: 0.1463 data: 0.0626 max mem: 9394 +Train: [8] [4200/6250] eta: 0:05:08 lr: 0.000125 grad: 0.0721 (0.0776) loss: 0.8507 (0.8565) time: 0.1377 data: 0.0618 max mem: 9394 +Train: [8] [4300/6250] eta: 0:04:53 lr: 0.000125 grad: 0.0698 (0.0776) loss: 0.8585 (0.8564) time: 0.1528 data: 0.0745 max mem: 9394 +Train: [8] [4400/6250] eta: 0:04:37 lr: 0.000125 grad: 0.0743 (0.0776) loss: 0.8484 (0.8563) time: 0.1271 data: 0.0455 max mem: 9394 +Train: [8] [4500/6250] eta: 0:04:22 lr: 0.000125 grad: 0.0706 (0.0775) loss: 0.8516 (0.8562) time: 0.1269 data: 0.0384 max mem: 9394 +Train: [8] [4600/6250] eta: 0:04:07 lr: 0.000125 grad: 0.0707 (0.0773) loss: 0.8530 (0.8561) time: 0.1519 data: 0.0676 max mem: 9394 +Train: [8] [4700/6250] eta: 0:03:51 lr: 0.000125 grad: 0.0752 (0.0773) loss: 0.8475 (0.8560) time: 0.1355 data: 0.0489 max mem: 9394 +Train: [8] [4800/6250] eta: 0:03:36 lr: 0.000125 grad: 0.0695 (0.0773) loss: 0.8489 (0.8559) time: 0.1595 data: 0.0710 max mem: 9394 +Train: [8] [4900/6250] eta: 0:03:21 lr: 0.000125 grad: 0.0716 (0.0773) loss: 0.8549 (0.8558) time: 0.1550 data: 0.0733 max mem: 9394 +Train: [8] [5000/6250] eta: 0:03:07 lr: 0.000125 grad: 0.0799 (0.0774) loss: 0.8503 (0.8557) time: 0.2553 data: 0.1749 max mem: 9394 +Train: [8] [5100/6250] eta: 0:02:51 lr: 0.000125 grad: 0.0791 (0.0773) loss: 0.8509 (0.8556) time: 0.1436 data: 0.0598 max mem: 9394 +Train: [8] [5200/6250] eta: 0:02:36 lr: 0.000124 grad: 0.0674 (0.0772) loss: 0.8517 (0.8556) time: 0.1218 data: 0.0405 max mem: 9394 +Train: [8] [5300/6250] eta: 0:02:21 lr: 0.000124 grad: 0.0707 (0.0772) loss: 0.8524 (0.8555) time: 0.1327 data: 0.0531 max mem: 9394 +Train: [8] [5400/6250] eta: 0:02:06 lr: 0.000124 grad: 0.0758 (0.0772) loss: 0.8477 (0.8554) time: 0.1571 data: 0.0716 max mem: 9394 +Train: [8] [5500/6250] eta: 0:01:51 lr: 0.000124 grad: 0.0694 (0.0771) loss: 0.8544 (0.8554) time: 0.1168 data: 0.0313 max mem: 9394 +Train: [8] [5600/6250] eta: 0:01:36 lr: 0.000124 grad: 0.0689 (0.0771) loss: 0.8563 (0.8554) time: 0.1419 data: 0.0603 max mem: 9394 +Train: [8] [5700/6250] eta: 0:01:21 lr: 0.000124 grad: 0.0722 (0.0770) loss: 0.8490 (0.8553) time: 0.1407 data: 0.0520 max mem: 9394 +Train: [8] [5800/6250] eta: 0:01:06 lr: 0.000124 grad: 0.0683 (0.0769) loss: 0.8563 (0.8553) time: 0.1291 data: 0.0382 max mem: 9394 +Train: [8] [5900/6250] eta: 0:00:51 lr: 0.000124 grad: 0.0678 (0.0768) loss: 0.8539 (0.8553) time: 0.1397 data: 0.0514 max mem: 9394 +Train: [8] [6000/6250] eta: 0:00:36 lr: 0.000124 grad: 0.0704 (0.0767) loss: 0.8536 (0.8553) time: 0.1127 data: 0.0243 max mem: 9394 +Train: [8] [6100/6250] eta: 0:00:22 lr: 0.000124 grad: 0.0652 (0.0767) loss: 0.8579 (0.8553) time: 0.1372 data: 0.0520 max mem: 9394 +Train: [8] [6200/6250] eta: 0:00:07 lr: 0.000124 grad: 0.0686 (0.0765) loss: 0.8562 (0.8553) time: 0.1438 data: 0.0529 max mem: 9394 +Train: [8] [6249/6250] eta: 0:00:00 lr: 0.000124 grad: 0.0681 (0.0765) loss: 0.8552 (0.8553) time: 0.1489 data: 0.0650 max mem: 9394 +Train: [8] Total time: 0:15:24 (0.1480 s / it) +Averaged stats: lr: 0.000124 grad: 0.0681 (0.0765) loss: 0.8552 (0.8553) +Eval (hcp-train-subset): [8] [ 0/62] eta: 0:05:22 loss: 0.8664 (0.8664) time: 5.2030 data: 5.1652 max mem: 9394 +Eval (hcp-train-subset): [8] [61/62] eta: 0:00:00 loss: 0.8592 (0.8587) time: 0.1472 data: 0.1200 max mem: 9394 +Eval (hcp-train-subset): [8] Total time: 0:00:13 (0.2240 s / it) +Averaged stats (hcp-train-subset): loss: 0.8592 (0.8587) +Eval (hcp-val): [8] [ 0/62] eta: 0:04:22 loss: 0.8523 (0.8523) time: 4.2366 data: 4.2085 max mem: 9394 +Eval (hcp-val): [8] [61/62] eta: 0:00:00 loss: 0.8525 (0.8531) time: 0.1333 data: 0.1074 max mem: 9394 +Eval (hcp-val): [8] Total time: 0:00:12 (0.2041 s / it) +Averaged stats (hcp-val): loss: 0.8525 (0.8531) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +Train: [9] [ 0/6250] eta: 8:49:11 lr: 0.000124 grad: 0.0480 (0.0480) loss: 0.8671 (0.8671) time: 5.0803 data: 4.8693 max mem: 9394 +Train: [9] [ 100/6250] eta: 0:22:25 lr: 0.000124 grad: 0.0676 (0.0777) loss: 0.8555 (0.8624) time: 0.1792 data: 0.0865 max mem: 9394 +Train: [9] [ 200/6250] eta: 0:19:48 lr: 0.000124 grad: 0.0758 (0.0788) loss: 0.8477 (0.8587) time: 0.1734 data: 0.0855 max mem: 9394 +Train: [9] [ 300/6250] eta: 0:18:26 lr: 0.000124 grad: 0.0796 (0.0790) loss: 0.8520 (0.8574) time: 0.1755 data: 0.0826 max mem: 9394 +Train: [9] [ 400/6250] eta: 0:17:17 lr: 0.000124 grad: 0.0724 (0.0779) loss: 0.8491 (0.8558) time: 0.1574 data: 0.0686 max mem: 9394 +Train: [9] [ 500/6250] eta: 0:16:17 lr: 0.000124 grad: 0.0655 (0.0771) loss: 0.8568 (0.8546) time: 0.1426 data: 0.0531 max mem: 9394 +Train: [9] [ 600/6250] eta: 0:15:42 lr: 0.000124 grad: 0.0743 (0.0765) loss: 0.8514 (0.8538) time: 0.1455 data: 0.0551 max mem: 9394 +Train: [9] [ 700/6250] eta: 0:15:13 lr: 0.000124 grad: 0.0749 (0.0762) loss: 0.8520 (0.8533) time: 0.1517 data: 0.0659 max mem: 9394 +Train: [9] [ 800/6250] eta: 0:14:59 lr: 0.000124 grad: 0.0715 (0.0760) loss: 0.8469 (0.8526) time: 0.2016 data: 0.0799 max mem: 9394 +Train: [9] [ 900/6250] eta: 0:14:43 lr: 0.000124 grad: 0.0675 (0.0756) loss: 0.8502 (0.8522) time: 0.1350 data: 0.0060 max mem: 9394 +Train: [9] [1000/6250] eta: 0:14:27 lr: 0.000124 grad: 0.0683 (0.0752) loss: 0.8534 (0.8521) time: 0.1967 data: 0.0883 max mem: 9394 +Train: [9] [1100/6250] eta: 0:14:03 lr: 0.000124 grad: 0.0762 (0.0753) loss: 0.8501 (0.8519) time: 0.1632 data: 0.0823 max mem: 9394 +Train: [9] [1200/6250] eta: 0:13:42 lr: 0.000124 grad: 0.0672 (0.0749) loss: 0.8526 (0.8517) time: 0.1726 data: 0.0487 max mem: 9394 +Train: [9] [1300/6250] eta: 0:13:36 lr: 0.000124 grad: 0.0736 (0.0747) loss: 0.8485 (0.8515) time: 0.1182 data: 0.0344 max mem: 9394 +Train: [9] [1400/6250] eta: 0:13:11 lr: 0.000124 grad: 0.0718 (0.0747) loss: 0.8492 (0.8514) time: 0.1472 data: 0.0665 max mem: 9394 +Train: [9] [1500/6250] eta: 0:12:47 lr: 0.000124 grad: 0.0769 (0.0747) loss: 0.8461 (0.8512) time: 0.1400 data: 0.0637 max mem: 9394 +Train: [9] [1600/6250] eta: 0:12:28 lr: 0.000124 grad: 0.0815 (0.0750) loss: 0.8496 (0.8511) time: 0.1450 data: 0.0681 max mem: 9394 +Train: [9] [1700/6250] eta: 0:12:15 lr: 0.000124 grad: 0.0720 (0.0747) loss: 0.8553 (0.8512) time: 0.1788 data: 0.0780 max mem: 9394 +Train: [9] [1800/6250] eta: 0:11:53 lr: 0.000124 grad: 0.0752 (0.0747) loss: 0.8545 (0.8512) time: 0.1705 data: 0.0911 max mem: 9394 +Train: [9] [1900/6250] eta: 0:11:32 lr: 0.000124 grad: 0.0717 (0.0745) loss: 0.8473 (0.8513) time: 0.1404 data: 0.0553 max mem: 9394 +Train: [9] [2000/6250] eta: 0:11:14 lr: 0.000124 grad: 0.0696 (0.0746) loss: 0.8478 (0.8513) time: 0.1697 data: 0.0727 max mem: 9394 +Train: [9] [2100/6250] eta: 0:10:56 lr: 0.000124 grad: 0.0742 (0.0746) loss: 0.8566 (0.8513) time: 0.1507 data: 0.0664 max mem: 9394 +Train: [9] [2200/6250] eta: 0:10:36 lr: 0.000124 grad: 0.0677 (0.0745) loss: 0.8554 (0.8514) time: 0.1547 data: 0.0561 max mem: 9394 +Train: [9] [2300/6250] eta: 0:10:20 lr: 0.000124 grad: 0.0651 (0.0743) loss: 0.8519 (0.8514) time: 0.1162 data: 0.0249 max mem: 9394 +Train: [9] [2400/6250] eta: 0:10:02 lr: 0.000124 grad: 0.0687 (0.0742) loss: 0.8504 (0.8515) time: 0.1478 data: 0.0648 max mem: 9394 +Train: [9] [2500/6250] eta: 0:09:44 lr: 0.000124 grad: 0.0701 (0.0742) loss: 0.8522 (0.8515) time: 0.1313 data: 0.0442 max mem: 9394 +Train: [9] [2600/6250] eta: 0:09:27 lr: 0.000124 grad: 0.0670 (0.0740) loss: 0.8573 (0.8515) time: 0.1353 data: 0.0531 max mem: 9394 +Train: [9] [2700/6250] eta: 0:09:10 lr: 0.000124 grad: 0.0722 (0.0740) loss: 0.8485 (0.8514) time: 0.1438 data: 0.0594 max mem: 9394 +Train: [9] [2800/6250] eta: 0:08:52 lr: 0.000124 grad: 0.0651 (0.0738) loss: 0.8531 (0.8515) time: 0.1537 data: 0.0718 max mem: 9394 +Train: [9] [2900/6250] eta: 0:08:34 lr: 0.000124 grad: 0.0675 (0.0737) loss: 0.8523 (0.8515) time: 0.1287 data: 0.0459 max mem: 9394 +Train: [9] [3000/6250] eta: 0:08:18 lr: 0.000124 grad: 0.0653 (0.0736) loss: 0.8483 (0.8515) time: 0.1582 data: 0.0766 max mem: 9394 +Train: [9] [3100/6250] eta: 0:08:01 lr: 0.000124 grad: 0.0693 (0.0736) loss: 0.8517 (0.8515) time: 0.1493 data: 0.0604 max mem: 9394 +Train: [9] [3200/6250] eta: 0:07:44 lr: 0.000124 grad: 0.0693 (0.0735) loss: 0.8457 (0.8515) time: 0.1176 data: 0.0332 max mem: 9394 +Train: [9] [3300/6250] eta: 0:07:28 lr: 0.000124 grad: 0.0741 (0.0734) loss: 0.8493 (0.8515) time: 0.1418 data: 0.0573 max mem: 9394 +Train: [9] [3400/6250] eta: 0:07:11 lr: 0.000124 grad: 0.0680 (0.0733) loss: 0.8480 (0.8514) time: 0.1425 data: 0.0575 max mem: 9394 +Train: [9] [3500/6250] eta: 0:06:55 lr: 0.000124 grad: 0.0718 (0.0734) loss: 0.8517 (0.8514) time: 0.1501 data: 0.0744 max mem: 9394 +Train: [9] [3600/6250] eta: 0:06:39 lr: 0.000124 grad: 0.0685 (0.0734) loss: 0.8500 (0.8514) time: 0.1465 data: 0.0652 max mem: 9394 +Train: [9] [3700/6250] eta: 0:06:23 lr: 0.000124 grad: 0.0636 (0.0733) loss: 0.8505 (0.8514) time: 0.1282 data: 0.0432 max mem: 9394 +Train: [9] [3800/6250] eta: 0:06:07 lr: 0.000124 grad: 0.0688 (0.0733) loss: 0.8517 (0.8514) time: 0.1621 data: 0.0814 max mem: 9394 +Train: [9] [3900/6250] eta: 0:05:53 lr: 0.000124 grad: 0.0694 (0.0732) loss: 0.8478 (0.8514) time: 0.2166 data: 0.1366 max mem: 9394 +Train: [9] [4000/6250] eta: 0:05:37 lr: 0.000124 grad: 0.0697 (0.0732) loss: 0.8537 (0.8514) time: 0.1457 data: 0.0610 max mem: 9394 +Train: [9] [4100/6250] eta: 0:05:23 lr: 0.000124 grad: 0.0677 (0.0731) loss: 0.8508 (0.8514) time: 0.1248 data: 0.0397 max mem: 9394 +Train: [9] [4200/6250] eta: 0:05:08 lr: 0.000124 grad: 0.0685 (0.0730) loss: 0.8501 (0.8514) time: 0.1439 data: 0.0567 max mem: 9394 +Train: [9] [4300/6250] eta: 0:04:52 lr: 0.000124 grad: 0.0687 (0.0729) loss: 0.8502 (0.8514) time: 0.1502 data: 0.0652 max mem: 9394 +Train: [9] [4400/6250] eta: 0:04:36 lr: 0.000124 grad: 0.0686 (0.0729) loss: 0.8533 (0.8514) time: 0.1436 data: 0.0625 max mem: 9394 +Train: [9] [4500/6250] eta: 0:04:21 lr: 0.000124 grad: 0.0638 (0.0728) loss: 0.8474 (0.8514) time: 0.1550 data: 0.0739 max mem: 9394 +Train: [9] [4600/6250] eta: 0:04:06 lr: 0.000124 grad: 0.0664 (0.0727) loss: 0.8525 (0.8514) time: 0.1261 data: 0.0413 max mem: 9394 +Train: [9] [4700/6250] eta: 0:03:50 lr: 0.000124 grad: 0.0670 (0.0726) loss: 0.8543 (0.8514) time: 0.1384 data: 0.0525 max mem: 9394 +Train: [9] [4800/6250] eta: 0:03:35 lr: 0.000124 grad: 0.0645 (0.0726) loss: 0.8533 (0.8514) time: 0.1447 data: 0.0638 max mem: 9394 +Train: [9] [4900/6250] eta: 0:03:20 lr: 0.000124 grad: 0.0636 (0.0725) loss: 0.8496 (0.8514) time: 0.1115 data: 0.0295 max mem: 9394 +Train: [9] [5000/6250] eta: 0:03:05 lr: 0.000124 grad: 0.0674 (0.0725) loss: 0.8479 (0.8514) time: 0.0911 data: 0.0002 max mem: 9394 +Train: [9] [5100/6250] eta: 0:02:50 lr: 0.000124 grad: 0.0651 (0.0724) loss: 0.8505 (0.8515) time: 0.1461 data: 0.0638 max mem: 9394 +Train: [9] [5200/6250] eta: 0:02:35 lr: 0.000124 grad: 0.0696 (0.0723) loss: 0.8572 (0.8515) time: 0.1435 data: 0.0673 max mem: 9394 +Train: [9] [5300/6250] eta: 0:02:20 lr: 0.000124 grad: 0.0718 (0.0723) loss: 0.8504 (0.8515) time: 0.1333 data: 0.0429 max mem: 9394 +Train: [9] [5400/6250] eta: 0:02:05 lr: 0.000124 grad: 0.0655 (0.0723) loss: 0.8460 (0.8515) time: 0.1443 data: 0.0610 max mem: 9394 +Train: [9] [5500/6250] eta: 0:01:50 lr: 0.000124 grad: 0.0672 (0.0722) loss: 0.8448 (0.8515) time: 0.1401 data: 0.0560 max mem: 9394 +Train: [9] [5600/6250] eta: 0:01:36 lr: 0.000124 grad: 0.0658 (0.0721) loss: 0.8499 (0.8514) time: 0.1384 data: 0.0479 max mem: 9394 +Train: [9] [5700/6250] eta: 0:01:21 lr: 0.000124 grad: 0.0645 (0.0721) loss: 0.8513 (0.8514) time: 0.1428 data: 0.0615 max mem: 9394 +Train: [9] [5800/6250] eta: 0:01:06 lr: 0.000124 grad: 0.0628 (0.0720) loss: 0.8530 (0.8514) time: 0.1263 data: 0.0455 max mem: 9394 +Train: [9] [5900/6250] eta: 0:00:51 lr: 0.000124 grad: 0.0687 (0.0720) loss: 0.8455 (0.8514) time: 0.1257 data: 0.0347 max mem: 9394 +Train: [9] [6000/6250] eta: 0:00:36 lr: 0.000124 grad: 0.0624 (0.0719) loss: 0.8487 (0.8514) time: 0.1456 data: 0.0640 max mem: 9394 +Train: [9] [6100/6250] eta: 0:00:22 lr: 0.000124 grad: 0.0638 (0.0718) loss: 0.8544 (0.8514) time: 0.1019 data: 0.0171 max mem: 9394 +Train: [9] [6200/6250] eta: 0:00:07 lr: 0.000124 grad: 0.0645 (0.0718) loss: 0.8516 (0.8514) time: 0.1439 data: 0.0640 max mem: 9394 +Train: [9] [6249/6250] eta: 0:00:00 lr: 0.000124 grad: 0.0641 (0.0717) loss: 0.8504 (0.8514) time: 0.1169 data: 0.0326 max mem: 9394 +Train: [9] Total time: 0:15:24 (0.1478 s / it) +Averaged stats: lr: 0.000124 grad: 0.0641 (0.0717) loss: 0.8504 (0.8514) +Eval (hcp-train-subset): [9] [ 0/62] eta: 0:05:33 loss: 0.8627 (0.8627) time: 5.3790 data: 5.3513 max mem: 9394 +Eval (hcp-train-subset): [9] [61/62] eta: 0:00:00 loss: 0.8573 (0.8568) time: 0.0991 data: 0.0727 max mem: 9394 +Eval (hcp-train-subset): [9] Total time: 0:00:12 (0.2014 s / it) +Averaged stats (hcp-train-subset): loss: 0.8573 (0.8568) +Making plots (hcp-train-subset): example=62 +Eval (hcp-val): [9] [ 0/62] eta: 0:04:13 loss: 0.8492 (0.8492) time: 4.0941 data: 4.0303 max mem: 9394 +Eval (hcp-val): [9] [61/62] eta: 0:00:00 loss: 0.8512 (0.8511) time: 0.1640 data: 0.1374 max mem: 9394 +Eval (hcp-val): [9] Total time: 0:00:14 (0.2305 s / it) +Averaged stats (hcp-val): loss: 0.8512 (0.8511) +Making plots (hcp-val): example=1 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +Train: [10] [ 0/6250] eta: 11:09:16 lr: 0.000124 grad: 0.0623 (0.0623) loss: 0.8679 (0.8679) time: 6.4251 data: 6.3312 max mem: 9394 +Train: [10] [ 100/6250] eta: 0:23:18 lr: 0.000124 grad: 0.0688 (0.0773) loss: 0.8510 (0.8560) time: 0.1667 data: 0.0859 max mem: 9394 +Train: [10] [ 200/6250] eta: 0:19:56 lr: 0.000124 grad: 0.0684 (0.0755) loss: 0.8544 (0.8539) time: 0.1772 data: 0.0897 max mem: 9394 +Train: [10] [ 300/6250] eta: 0:18:16 lr: 0.000124 grad: 0.0711 (0.0747) loss: 0.8505 (0.8526) time: 0.1586 data: 0.0783 max mem: 9394 +Train: [10] [ 400/6250] eta: 0:17:19 lr: 0.000124 grad: 0.0678 (0.0733) loss: 0.8529 (0.8522) time: 0.1580 data: 0.0721 max mem: 9394 +Train: [10] [ 500/6250] eta: 0:16:30 lr: 0.000124 grad: 0.0649 (0.0725) loss: 0.8549 (0.8517) time: 0.1567 data: 0.0651 max mem: 9394 +Train: [10] [ 600/6250] eta: 0:15:44 lr: 0.000124 grad: 0.0648 (0.0715) loss: 0.8509 (0.8516) time: 0.1478 data: 0.0550 max mem: 9394 +Train: [10] [ 700/6250] eta: 0:15:14 lr: 0.000124 grad: 0.0691 (0.0707) loss: 0.8427 (0.8515) time: 0.1447 data: 0.0596 max mem: 9394 +Train: [10] [ 800/6250] eta: 0:15:03 lr: 0.000124 grad: 0.0631 (0.0700) loss: 0.8509 (0.8518) time: 0.2218 data: 0.1223 max mem: 9394 +Train: [10] [ 900/6250] eta: 0:15:05 lr: 0.000124 grad: 0.0685 (0.0697) loss: 0.8477 (0.8519) time: 0.2290 data: 0.0823 max mem: 9394 +Train: [10] [1000/6250] eta: 0:15:06 lr: 0.000124 grad: 0.0651 (0.0698) loss: 0.8542 (0.8519) time: 0.1072 data: 0.0080 max mem: 9394 +Train: [10] [1100/6250] eta: 0:14:37 lr: 0.000124 grad: 0.0597 (0.0696) loss: 0.8543 (0.8520) time: 0.1308 data: 0.0392 max mem: 9394 +Train: [10] [1200/6250] eta: 0:14:12 lr: 0.000124 grad: 0.0647 (0.0694) loss: 0.8511 (0.8521) time: 0.1499 data: 0.0637 max mem: 9394 +Train: [10] [1300/6250] eta: 0:14:03 lr: 0.000124 grad: 0.0636 (0.0691) loss: 0.8521 (0.8519) time: 0.1300 data: 0.0433 max mem: 9394 +Train: [10] [1400/6250] eta: 0:13:36 lr: 0.000124 grad: 0.0642 (0.0691) loss: 0.8544 (0.8519) time: 0.1661 data: 0.0773 max mem: 9394 +Train: [10] [1500/6250] eta: 0:13:14 lr: 0.000124 grad: 0.0658 (0.0690) loss: 0.8521 (0.8519) time: 0.1557 data: 0.0764 max mem: 9394 +Train: [10] [1600/6250] eta: 0:12:59 lr: 0.000124 grad: 0.0641 (0.0688) loss: 0.8545 (0.8519) time: 0.1545 data: 0.0594 max mem: 9394 +Train: [10] [1700/6250] eta: 0:12:43 lr: 0.000124 grad: 0.0652 (0.0686) loss: 0.8481 (0.8517) time: 0.2952 data: 0.1898 max mem: 9394 +Train: [10] [1800/6250] eta: 0:12:20 lr: 0.000124 grad: 0.0679 (0.0685) loss: 0.8517 (0.8518) time: 0.1509 data: 0.0693 max mem: 9394 +Train: [10] [1900/6250] eta: 0:12:01 lr: 0.000124 grad: 0.0653 (0.0683) loss: 0.8441 (0.8518) time: 0.1283 data: 0.0235 max mem: 9394 +Train: [10] [2000/6250] eta: 0:11:43 lr: 0.000124 grad: 0.0608 (0.0683) loss: 0.8467 (0.8516) time: 0.1353 data: 0.0488 max mem: 9394 +Train: [10] [2100/6250] eta: 0:11:21 lr: 0.000124 grad: 0.0592 (0.0681) loss: 0.8495 (0.8516) time: 0.1252 data: 0.0337 max mem: 9394 +Train: [10] [2200/6250] eta: 0:11:15 lr: 0.000124 grad: 0.0648 (0.0680) loss: 0.8523 (0.8516) time: 0.1335 data: 0.0395 max mem: 9394 +Train: [10] [2300/6250] eta: 0:10:51 lr: 0.000124 grad: 0.0622 (0.0678) loss: 0.8517 (0.8517) time: 0.1421 data: 0.0644 max mem: 9394 +Train: [10] [2400/6250] eta: 0:10:38 lr: 0.000124 grad: 0.0647 (0.0677) loss: 0.8520 (0.8516) time: 0.2889 data: 0.1972 max mem: 9394 +Train: [10] [2500/6250] eta: 0:10:15 lr: 0.000124 grad: 0.0623 (0.0675) loss: 0.8528 (0.8516) time: 0.1530 data: 0.0648 max mem: 9394 +Train: [10] [2600/6250] eta: 0:09:56 lr: 0.000124 grad: 0.0625 (0.0674) loss: 0.8572 (0.8517) time: 0.0973 data: 0.0128 max mem: 9394 +Train: [10] [2700/6250] eta: 0:09:35 lr: 0.000124 grad: 0.0636 (0.0673) loss: 0.8520 (0.8517) time: 0.1394 data: 0.0561 max mem: 9394 +Train: [10] [2800/6250] eta: 0:09:17 lr: 0.000124 grad: 0.0641 (0.0671) loss: 0.8513 (0.8518) time: 0.1307 data: 0.0452 max mem: 9394 +Train: [10] [2900/6250] eta: 0:09:01 lr: 0.000124 grad: 0.0689 (0.0672) loss: 0.8497 (0.8518) time: 0.1082 data: 0.0236 max mem: 9394 +Train: [10] [3000/6250] eta: 0:08:42 lr: 0.000124 grad: 0.0679 (0.0673) loss: 0.8510 (0.8517) time: 0.1390 data: 0.0590 max mem: 9394 +Train: [10] [3100/6250] eta: 0:08:24 lr: 0.000124 grad: 0.0611 (0.0672) loss: 0.8497 (0.8517) time: 0.1288 data: 0.0454 max mem: 9394 +Train: [10] [3200/6250] eta: 0:08:05 lr: 0.000124 grad: 0.0617 (0.0671) loss: 0.8491 (0.8516) time: 0.1406 data: 0.0610 max mem: 9394 +Train: [10] [3300/6250] eta: 0:07:48 lr: 0.000124 grad: 0.0623 (0.0670) loss: 0.8508 (0.8516) time: 0.1494 data: 0.0664 max mem: 9394 +Train: [10] [3400/6250] eta: 0:07:30 lr: 0.000124 grad: 0.0624 (0.0669) loss: 0.8492 (0.8515) time: 0.1497 data: 0.0739 max mem: 9394 +Train: [10] [3500/6250] eta: 0:07:13 lr: 0.000124 grad: 0.0637 (0.0669) loss: 0.8516 (0.8515) time: 0.1457 data: 0.0644 max mem: 9394 +Train: [10] [3600/6250] eta: 0:06:56 lr: 0.000124 grad: 0.0640 (0.0669) loss: 0.8493 (0.8514) time: 0.1632 data: 0.0795 max mem: 9394 +Train: [10] [3700/6250] eta: 0:06:38 lr: 0.000124 grad: 0.0669 (0.0668) loss: 0.8428 (0.8513) time: 0.1338 data: 0.0523 max mem: 9394 +Train: [10] [3800/6250] eta: 0:06:21 lr: 0.000124 grad: 0.0647 (0.0668) loss: 0.8479 (0.8513) time: 0.1499 data: 0.0728 max mem: 9394 +Train: [10] [3900/6250] eta: 0:06:05 lr: 0.000124 grad: 0.0613 (0.0667) loss: 0.8512 (0.8513) time: 0.1279 data: 0.0487 max mem: 9394 +Train: [10] [4000/6250] eta: 0:05:48 lr: 0.000124 grad: 0.0632 (0.0667) loss: 0.8522 (0.8513) time: 0.1530 data: 0.0688 max mem: 9394 +Train: [10] [4100/6250] eta: 0:05:32 lr: 0.000124 grad: 0.0638 (0.0666) loss: 0.8532 (0.8512) time: 0.1350 data: 0.0531 max mem: 9394 +Train: [10] [4200/6250] eta: 0:05:17 lr: 0.000124 grad: 0.0661 (0.0666) loss: 0.8465 (0.8512) time: 0.1469 data: 0.0651 max mem: 9394 +Train: [10] [4300/6250] eta: 0:05:00 lr: 0.000124 grad: 0.0690 (0.0666) loss: 0.8443 (0.8511) time: 0.1282 data: 0.0515 max mem: 9394 +Train: [10] [4400/6250] eta: 0:04:44 lr: 0.000124 grad: 0.0680 (0.0666) loss: 0.8457 (0.8511) time: 0.1555 data: 0.0762 max mem: 9394 +Train: [10] [4500/6250] eta: 0:04:28 lr: 0.000124 grad: 0.0674 (0.0666) loss: 0.8473 (0.8510) time: 0.1438 data: 0.0634 max mem: 9394 +Train: [10] [4600/6250] eta: 0:04:14 lr: 0.000124 grad: 0.0634 (0.0666) loss: 0.8462 (0.8510) time: 0.1208 data: 0.0408 max mem: 9394 +Train: [10] [4700/6250] eta: 0:03:57 lr: 0.000124 grad: 0.0631 (0.0666) loss: 0.8523 (0.8509) time: 0.1405 data: 0.0561 max mem: 9394 +Train: [10] [4800/6250] eta: 0:03:42 lr: 0.000124 grad: 0.0646 (0.0666) loss: 0.8444 (0.8509) time: 0.1436 data: 0.0620 max mem: 9394 +Train: [10] [4900/6250] eta: 0:03:26 lr: 0.000124 grad: 0.0670 (0.0666) loss: 0.8432 (0.8508) time: 0.1309 data: 0.0498 max mem: 9394 +Train: [10] [5000/6250] eta: 0:03:10 lr: 0.000124 grad: 0.0702 (0.0666) loss: 0.8439 (0.8508) time: 0.1166 data: 0.0259 max mem: 9394 +Train: [10] [5100/6250] eta: 0:02:55 lr: 0.000124 grad: 0.0688 (0.0667) loss: 0.8478 (0.8507) time: 0.1323 data: 0.0489 max mem: 9394 +Train: [10] [5200/6250] eta: 0:02:39 lr: 0.000124 grad: 0.0657 (0.0667) loss: 0.8417 (0.8506) time: 0.1506 data: 0.0722 max mem: 9394 +Train: [10] [5300/6250] eta: 0:02:24 lr: 0.000124 grad: 0.0639 (0.0667) loss: 0.8467 (0.8505) time: 0.1195 data: 0.0368 max mem: 9394 +Train: [10] [5400/6250] eta: 0:02:09 lr: 0.000124 grad: 0.0685 (0.0668) loss: 0.8383 (0.8504) time: 0.1474 data: 0.0660 max mem: 9394 +Train: [10] [5500/6250] eta: 0:01:53 lr: 0.000124 grad: 0.0661 (0.0668) loss: 0.8467 (0.8503) time: 0.1091 data: 0.0258 max mem: 9394 +Train: [10] [5600/6250] eta: 0:01:38 lr: 0.000124 grad: 0.0675 (0.0668) loss: 0.8413 (0.8503) time: 0.1832 data: 0.1009 max mem: 9394 +Train: [10] [5700/6250] eta: 0:01:23 lr: 0.000124 grad: 0.0629 (0.0668) loss: 0.8457 (0.8502) time: 0.1472 data: 0.0674 max mem: 9394 +Train: [10] [5800/6250] eta: 0:01:08 lr: 0.000124 grad: 0.0664 (0.0668) loss: 0.8480 (0.8501) time: 0.1257 data: 0.0389 max mem: 9394 +Train: [10] [5900/6250] eta: 0:00:52 lr: 0.000124 grad: 0.0582 (0.0668) loss: 0.8449 (0.8500) time: 0.1731 data: 0.0903 max mem: 9394 +Train: [10] [6000/6250] eta: 0:00:37 lr: 0.000124 grad: 0.0706 (0.0668) loss: 0.8447 (0.8500) time: 0.1396 data: 0.0552 max mem: 9394 +Train: [10] [6100/6250] eta: 0:00:22 lr: 0.000124 grad: 0.0653 (0.0668) loss: 0.8439 (0.8499) time: 0.1315 data: 0.0455 max mem: 9394 +Train: [10] [6200/6250] eta: 0:00:07 lr: 0.000124 grad: 0.0659 (0.0668) loss: 0.8434 (0.8499) time: 0.1651 data: 0.0889 max mem: 9394 +Train: [10] [6249/6250] eta: 0:00:00 lr: 0.000124 grad: 0.0632 (0.0668) loss: 0.8448 (0.8498) time: 0.1553 data: 0.0686 max mem: 9394 +Train: [10] Total time: 0:15:47 (0.1515 s / it) +Averaged stats: lr: 0.000124 grad: 0.0632 (0.0668) loss: 0.8448 (0.8498) +Eval (hcp-train-subset): [10] [ 0/62] eta: 0:04:05 loss: 0.8633 (0.8633) time: 3.9613 data: 3.8879 max mem: 9394 +Eval (hcp-train-subset): [10] [61/62] eta: 0:00:00 loss: 0.8532 (0.8539) time: 0.1492 data: 0.1214 max mem: 9394 +Eval (hcp-train-subset): [10] Total time: 0:00:14 (0.2393 s / it) +Averaged stats (hcp-train-subset): loss: 0.8532 (0.8539) +Eval (hcp-val): [10] [ 0/62] eta: 0:03:20 loss: 0.8448 (0.8448) time: 3.2384 data: 3.1321 max mem: 9394 +Eval (hcp-val): [10] [61/62] eta: 0:00:00 loss: 0.8487 (0.8486) time: 0.1239 data: 0.0960 max mem: 9394 +Eval (hcp-val): [10] Total time: 0:00:13 (0.2235 s / it) +Averaged stats (hcp-val): loss: 0.8487 (0.8486) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +Train: [11] [ 0/6250] eta: 9:54:07 lr: 0.000124 grad: 0.0672 (0.0672) loss: 0.8387 (0.8387) time: 5.7036 data: 5.5886 max mem: 9394 +Train: [11] [ 100/6250] eta: 0:21:06 lr: 0.000124 grad: 0.0677 (0.0725) loss: 0.8413 (0.8490) time: 0.1648 data: 0.0727 max mem: 9394 +Train: [11] [ 200/6250] eta: 0:19:00 lr: 0.000124 grad: 0.0635 (0.0712) loss: 0.8553 (0.8484) time: 0.1492 data: 0.0596 max mem: 9394 +Train: [11] [ 300/6250] eta: 0:18:17 lr: 0.000124 grad: 0.0659 (0.0710) loss: 0.8417 (0.8481) time: 0.2060 data: 0.1077 max mem: 9394 +Train: [11] [ 400/6250] eta: 0:17:31 lr: 0.000124 grad: 0.0630 (0.0705) loss: 0.8423 (0.8476) time: 0.1526 data: 0.0518 max mem: 9394 +Train: [11] [ 500/6250] eta: 0:16:54 lr: 0.000124 grad: 0.0675 (0.0698) loss: 0.8478 (0.8475) time: 0.1513 data: 0.0597 max mem: 9394 +Train: [11] [ 600/6250] eta: 0:16:11 lr: 0.000124 grad: 0.0628 (0.0692) loss: 0.8492 (0.8481) time: 0.1579 data: 0.0662 max mem: 9394 +Train: [11] [ 700/6250] eta: 0:15:47 lr: 0.000124 grad: 0.0676 (0.0685) loss: 0.8452 (0.8485) time: 0.2183 data: 0.0648 max mem: 9394 +Train: [11] [ 800/6250] eta: 0:16:04 lr: 0.000124 grad: 0.0656 (0.0679) loss: 0.8487 (0.8487) time: 0.2958 data: 0.1998 max mem: 9394 +Train: [11] [ 900/6250] eta: 0:16:09 lr: 0.000124 grad: 0.0770 (0.0680) loss: 0.8494 (0.8490) time: 0.3426 data: 0.2195 max mem: 9394 +Train: [11] [1000/6250] eta: 0:15:46 lr: 0.000124 grad: 0.0624 (0.0678) loss: 0.8482 (0.8490) time: 0.1710 data: 0.0873 max mem: 9394 +Train: [11] [1100/6250] eta: 0:15:11 lr: 0.000124 grad: 0.0655 (0.0679) loss: 0.8457 (0.8490) time: 0.1516 data: 0.0708 max mem: 9394 +Train: [11] [1200/6250] eta: 0:15:07 lr: 0.000124 grad: 0.0664 (0.0678) loss: 0.8499 (0.8489) time: 0.1515 data: 0.0663 max mem: 9394 +Train: [11] [1300/6250] eta: 0:14:30 lr: 0.000124 grad: 0.0625 (0.0676) loss: 0.8457 (0.8489) time: 0.1327 data: 0.0494 max mem: 9394 +Train: [11] [1400/6250] eta: 0:14:04 lr: 0.000124 grad: 0.0669 (0.0675) loss: 0.8489 (0.8488) time: 0.1220 data: 0.0342 max mem: 9394 +Train: [11] [1500/6250] eta: 0:13:39 lr: 0.000124 grad: 0.0637 (0.0674) loss: 0.8471 (0.8488) time: 0.1668 data: 0.0803 max mem: 9394 +Train: [11] [1600/6250] eta: 0:13:13 lr: 0.000124 grad: 0.0658 (0.0673) loss: 0.8512 (0.8487) time: 0.1492 data: 0.0668 max mem: 9394 +Train: [11] [1700/6250] eta: 0:12:49 lr: 0.000124 grad: 0.0696 (0.0676) loss: 0.8469 (0.8486) time: 0.1312 data: 0.0471 max mem: 9394 +Train: [11] [1800/6250] eta: 0:12:25 lr: 0.000124 grad: 0.0660 (0.0677) loss: 0.8444 (0.8485) time: 0.1496 data: 0.0663 max mem: 9394 +Train: [11] [1900/6250] eta: 0:12:03 lr: 0.000124 grad: 0.0670 (0.0677) loss: 0.8501 (0.8485) time: 0.1508 data: 0.0701 max mem: 9394 +Train: [11] [2000/6250] eta: 0:11:45 lr: 0.000124 grad: 0.0675 (0.0677) loss: 0.8505 (0.8485) time: 0.1944 data: 0.1104 max mem: 9394 +Train: [11] [2100/6250] eta: 0:11:26 lr: 0.000124 grad: 0.0630 (0.0678) loss: 0.8415 (0.8484) time: 0.1328 data: 0.0499 max mem: 9394 +Train: [11] [2200/6250] eta: 0:11:04 lr: 0.000124 grad: 0.0646 (0.0678) loss: 0.8465 (0.8484) time: 0.1462 data: 0.0653 max mem: 9394 +Train: [11] [2300/6250] eta: 0:10:43 lr: 0.000124 grad: 0.0624 (0.0678) loss: 0.8466 (0.8484) time: 0.1497 data: 0.0711 max mem: 9394 +Train: [11] [2400/6250] eta: 0:10:24 lr: 0.000124 grad: 0.0659 (0.0678) loss: 0.8495 (0.8483) time: 0.1565 data: 0.0752 max mem: 9394 +Train: [11] [2500/6250] eta: 0:10:04 lr: 0.000124 grad: 0.0633 (0.0677) loss: 0.8428 (0.8483) time: 0.1442 data: 0.0674 max mem: 9394 +Train: [11] [2600/6250] eta: 0:09:46 lr: 0.000124 grad: 0.0703 (0.0678) loss: 0.8421 (0.8482) time: 0.1299 data: 0.0435 max mem: 9394 +Train: [11] [2700/6250] eta: 0:09:27 lr: 0.000124 grad: 0.0661 (0.0677) loss: 0.8478 (0.8482) time: 0.1444 data: 0.0624 max mem: 9394 +Train: [11] [2800/6250] eta: 0:09:09 lr: 0.000124 grad: 0.0684 (0.0677) loss: 0.8453 (0.8482) time: 0.1353 data: 0.0396 max mem: 9394 +Train: [11] [2900/6250] eta: 0:08:50 lr: 0.000124 grad: 0.0669 (0.0677) loss: 0.8483 (0.8481) time: 0.1243 data: 0.0384 max mem: 9394 +Train: [11] [3000/6250] eta: 0:08:32 lr: 0.000124 grad: 0.0648 (0.0676) loss: 0.8473 (0.8481) time: 0.1276 data: 0.0464 max mem: 9394 +Train: [11] [3100/6250] eta: 0:08:14 lr: 0.000124 grad: 0.0662 (0.0677) loss: 0.8438 (0.8481) time: 0.1394 data: 0.0631 max mem: 9394 +Train: [11] [3200/6250] eta: 0:07:57 lr: 0.000124 grad: 0.0624 (0.0676) loss: 0.8492 (0.8482) time: 0.1510 data: 0.0706 max mem: 9394 +Train: [11] [3300/6250] eta: 0:07:39 lr: 0.000124 grad: 0.0677 (0.0675) loss: 0.8462 (0.8482) time: 0.1406 data: 0.0585 max mem: 9394 +Train: [11] [3400/6250] eta: 0:07:23 lr: 0.000124 grad: 0.0663 (0.0675) loss: 0.8512 (0.8482) time: 0.1398 data: 0.0609 max mem: 9394 +Train: [11] [3500/6250] eta: 0:07:06 lr: 0.000124 grad: 0.0636 (0.0675) loss: 0.8431 (0.8482) time: 0.1634 data: 0.0767 max mem: 9394 +Train: [11] [3600/6250] eta: 0:06:52 lr: 0.000124 grad: 0.0648 (0.0674) loss: 0.8437 (0.8482) time: 0.1509 data: 0.0582 max mem: 9394 +Train: [11] [3700/6250] eta: 0:06:35 lr: 0.000124 grad: 0.0634 (0.0674) loss: 0.8477 (0.8481) time: 0.1592 data: 0.0780 max mem: 9394 +Train: [11] [3800/6250] eta: 0:06:19 lr: 0.000124 grad: 0.0624 (0.0673) loss: 0.8497 (0.8481) time: 0.1033 data: 0.0227 max mem: 9394 +Train: [11] [3900/6250] eta: 0:06:02 lr: 0.000124 grad: 0.0646 (0.0673) loss: 0.8481 (0.8481) time: 0.1217 data: 0.0377 max mem: 9394 +Train: [11] [4000/6250] eta: 0:05:46 lr: 0.000123 grad: 0.0633 (0.0673) loss: 0.8463 (0.8481) time: 0.1461 data: 0.0617 max mem: 9394 +Train: [11] [4100/6250] eta: 0:05:31 lr: 0.000123 grad: 0.0643 (0.0673) loss: 0.8411 (0.8480) time: 0.1777 data: 0.0933 max mem: 9394 +Train: [11] [4200/6250] eta: 0:05:14 lr: 0.000123 grad: 0.0657 (0.0673) loss: 0.8480 (0.8480) time: 0.1267 data: 0.0437 max mem: 9394 +Train: [11] [4300/6250] eta: 0:04:59 lr: 0.000123 grad: 0.0621 (0.0672) loss: 0.8434 (0.8479) time: 0.1598 data: 0.0765 max mem: 9394 +Train: [11] [4400/6250] eta: 0:04:43 lr: 0.000123 grad: 0.0670 (0.0672) loss: 0.8492 (0.8479) time: 0.1502 data: 0.0734 max mem: 9394 +Train: [11] [4500/6250] eta: 0:04:27 lr: 0.000123 grad: 0.0643 (0.0672) loss: 0.8484 (0.8479) time: 0.1373 data: 0.0567 max mem: 9394 +Train: [11] [4600/6250] eta: 0:04:11 lr: 0.000123 grad: 0.0634 (0.0672) loss: 0.8429 (0.8478) time: 0.1507 data: 0.0688 max mem: 9394 +Train: [11] [4700/6250] eta: 0:03:56 lr: 0.000123 grad: 0.0684 (0.0672) loss: 0.8481 (0.8478) time: 0.1263 data: 0.0465 max mem: 9394 +Train: [11] [4800/6250] eta: 0:03:40 lr: 0.000123 grad: 0.0699 (0.0673) loss: 0.8449 (0.8478) time: 0.1293 data: 0.0481 max mem: 9394 +Train: [11] [4900/6250] eta: 0:03:25 lr: 0.000123 grad: 0.0657 (0.0672) loss: 0.8493 (0.8478) time: 0.1454 data: 0.0624 max mem: 9394 +Train: [11] [5000/6250] eta: 0:03:09 lr: 0.000123 grad: 0.0647 (0.0672) loss: 0.8469 (0.8478) time: 0.1645 data: 0.0891 max mem: 9394 +Train: [11] [5100/6250] eta: 0:02:54 lr: 0.000123 grad: 0.0642 (0.0672) loss: 0.8441 (0.8477) time: 0.1325 data: 0.0486 max mem: 9394 +Train: [11] [5200/6250] eta: 0:02:38 lr: 0.000123 grad: 0.0645 (0.0671) loss: 0.8475 (0.8477) time: 0.1313 data: 0.0514 max mem: 9394 +Train: [11] [5300/6250] eta: 0:02:23 lr: 0.000123 grad: 0.0625 (0.0671) loss: 0.8419 (0.8477) time: 0.1848 data: 0.0865 max mem: 9394 +Train: [11] [5400/6250] eta: 0:02:08 lr: 0.000123 grad: 0.0628 (0.0671) loss: 0.8461 (0.8477) time: 0.1468 data: 0.0655 max mem: 9394 +Train: [11] [5500/6250] eta: 0:01:53 lr: 0.000123 grad: 0.0635 (0.0671) loss: 0.8463 (0.8476) time: 0.1466 data: 0.0666 max mem: 9394 +Train: [11] [5600/6250] eta: 0:01:38 lr: 0.000123 grad: 0.0648 (0.0671) loss: 0.8477 (0.8476) time: 0.1404 data: 0.0571 max mem: 9394 +Train: [11] [5700/6250] eta: 0:01:23 lr: 0.000123 grad: 0.0658 (0.0670) loss: 0.8441 (0.8476) time: 0.1466 data: 0.0654 max mem: 9394 +Train: [11] [5800/6250] eta: 0:01:07 lr: 0.000123 grad: 0.0645 (0.0670) loss: 0.8468 (0.8476) time: 0.1536 data: 0.0768 max mem: 9394 +Train: [11] [5900/6250] eta: 0:00:52 lr: 0.000123 grad: 0.0612 (0.0670) loss: 0.8455 (0.8476) time: 0.1396 data: 0.0554 max mem: 9394 +Train: [11] [6000/6250] eta: 0:00:37 lr: 0.000123 grad: 0.0648 (0.0669) loss: 0.8459 (0.8476) time: 0.1410 data: 0.0554 max mem: 9394 +Train: [11] [6100/6250] eta: 0:00:22 lr: 0.000123 grad: 0.0622 (0.0669) loss: 0.8496 (0.8475) time: 0.1294 data: 0.0468 max mem: 9394 +Train: [11] [6200/6250] eta: 0:00:07 lr: 0.000123 grad: 0.0680 (0.0669) loss: 0.8484 (0.8475) time: 0.1609 data: 0.0682 max mem: 9394 +Train: [11] [6249/6250] eta: 0:00:00 lr: 0.000123 grad: 0.0658 (0.0669) loss: 0.8452 (0.8475) time: 0.1400 data: 0.0566 max mem: 9394 +Train: [11] Total time: 0:15:46 (0.1514 s / it) +Averaged stats: lr: 0.000123 grad: 0.0658 (0.0669) loss: 0.8452 (0.8475) +Eval (hcp-train-subset): [11] [ 0/62] eta: 0:05:42 loss: 0.8621 (0.8621) time: 5.5183 data: 5.4850 max mem: 9394 +Eval (hcp-train-subset): [11] [61/62] eta: 0:00:00 loss: 0.8520 (0.8522) time: 0.1402 data: 0.1145 max mem: 9394 +Eval (hcp-train-subset): [11] Total time: 0:00:14 (0.2355 s / it) +Averaged stats (hcp-train-subset): loss: 0.8520 (0.8522) +Eval (hcp-val): [11] [ 0/62] eta: 0:05:05 loss: 0.8426 (0.8426) time: 4.9198 data: 4.8916 max mem: 9394 +Eval (hcp-val): [11] [61/62] eta: 0:00:00 loss: 0.8479 (0.8471) time: 0.1131 data: 0.0878 max mem: 9394 +Eval (hcp-val): [11] Total time: 0:00:12 (0.2064 s / it) +Averaged stats (hcp-val): loss: 0.8479 (0.8471) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +Train: [12] [ 0/6250] eta: 10:59:29 lr: 0.000123 grad: 0.1086 (0.1086) loss: 0.8656 (0.8656) time: 6.3311 data: 6.2444 max mem: 9394 +Train: [12] [ 100/6250] eta: 0:20:06 lr: 0.000123 grad: 0.0610 (0.0665) loss: 0.8622 (0.8621) time: 0.1356 data: 0.0421 max mem: 9394 +Train: [12] [ 200/6250] eta: 0:18:49 lr: 0.000123 grad: 0.0680 (0.0673) loss: 0.8482 (0.8587) time: 0.2727 data: 0.1858 max mem: 9394 +Train: [12] [ 300/6250] eta: 0:17:30 lr: 0.000123 grad: 0.0638 (0.0677) loss: 0.8463 (0.8559) time: 0.1564 data: 0.0728 max mem: 9394 +Train: [12] [ 400/6250] eta: 0:16:32 lr: 0.000123 grad: 0.0646 (0.0671) loss: 0.8560 (0.8544) time: 0.1279 data: 0.0503 max mem: 9394 +Train: [12] [ 500/6250] eta: 0:16:21 lr: 0.000123 grad: 0.0646 (0.0668) loss: 0.8457 (0.8531) time: 0.1836 data: 0.0862 max mem: 9394 +Train: [12] [ 600/6250] eta: 0:15:59 lr: 0.000123 grad: 0.0615 (0.0664) loss: 0.8473 (0.8523) time: 0.1755 data: 0.0920 max mem: 9394 +Train: [12] [ 700/6250] eta: 0:15:18 lr: 0.000123 grad: 0.0656 (0.0660) loss: 0.8485 (0.8517) time: 0.1357 data: 0.0443 max mem: 9394 +Train: [12] [ 800/6250] eta: 0:14:47 lr: 0.000123 grad: 0.0696 (0.0659) loss: 0.8421 (0.8512) time: 0.1698 data: 0.0862 max mem: 9394 +Train: [12] [ 900/6250] eta: 0:14:23 lr: 0.000123 grad: 0.0620 (0.0660) loss: 0.8454 (0.8505) time: 0.1492 data: 0.0610 max mem: 9394 +Train: [12] [1000/6250] eta: 0:14:04 lr: 0.000123 grad: 0.0674 (0.0660) loss: 0.8421 (0.8498) time: 0.1645 data: 0.0493 max mem: 9394 +Train: [12] [1100/6250] eta: 0:13:40 lr: 0.000123 grad: 0.0655 (0.0661) loss: 0.8391 (0.8492) time: 0.1317 data: 0.0462 max mem: 9394 +Train: [12] [1200/6250] eta: 0:13:25 lr: 0.000123 grad: 0.0664 (0.0663) loss: 0.8428 (0.8487) time: 0.1356 data: 0.0547 max mem: 9394 +Train: [12] [1300/6250] eta: 0:13:04 lr: 0.000123 grad: 0.0687 (0.0665) loss: 0.8426 (0.8482) time: 0.1538 data: 0.0488 max mem: 9394 +Train: [12] [1400/6250] eta: 0:12:47 lr: 0.000123 grad: 0.0708 (0.0668) loss: 0.8415 (0.8478) time: 0.1462 data: 0.0661 max mem: 9394 +Train: [12] [1500/6250] eta: 0:12:25 lr: 0.000123 grad: 0.0656 (0.0668) loss: 0.8407 (0.8475) time: 0.1127 data: 0.0296 max mem: 9394 +Train: [12] [1600/6250] eta: 0:12:05 lr: 0.000123 grad: 0.0651 (0.0670) loss: 0.8455 (0.8473) time: 0.1529 data: 0.0656 max mem: 9394 +Train: [12] [1700/6250] eta: 0:11:46 lr: 0.000123 grad: 0.0640 (0.0672) loss: 0.8484 (0.8471) time: 0.1456 data: 0.0674 max mem: 9394 +Train: [12] [1800/6250] eta: 0:11:27 lr: 0.000123 grad: 0.0649 (0.0672) loss: 0.8489 (0.8470) time: 0.1477 data: 0.0677 max mem: 9394 +Train: [12] [1900/6250] eta: 0:11:07 lr: 0.000123 grad: 0.0659 (0.0672) loss: 0.8435 (0.8469) time: 0.1447 data: 0.0412 max mem: 9394 +Train: [12] [2000/6250] eta: 0:10:50 lr: 0.000123 grad: 0.0649 (0.0672) loss: 0.8483 (0.8469) time: 0.1444 data: 0.0614 max mem: 9394 +Train: [12] [2100/6250] eta: 0:10:32 lr: 0.000123 grad: 0.0655 (0.0672) loss: 0.8433 (0.8469) time: 0.1322 data: 0.0461 max mem: 9394 +Train: [12] [2200/6250] eta: 0:10:14 lr: 0.000123 grad: 0.0645 (0.0672) loss: 0.8460 (0.8468) time: 0.1470 data: 0.0668 max mem: 9394 +Train: [12] [2300/6250] eta: 0:09:57 lr: 0.000123 grad: 0.0621 (0.0672) loss: 0.8465 (0.8468) time: 0.1389 data: 0.0591 max mem: 9394 +Train: [12] [2400/6250] eta: 0:09:40 lr: 0.000123 grad: 0.0640 (0.0672) loss: 0.8446 (0.8467) time: 0.1218 data: 0.0311 max mem: 9394 +Train: [12] [2500/6250] eta: 0:09:23 lr: 0.000123 grad: 0.0678 (0.0673) loss: 0.8455 (0.8466) time: 0.1223 data: 0.0410 max mem: 9394 +Train: [12] [2600/6250] eta: 0:09:07 lr: 0.000123 grad: 0.0611 (0.0672) loss: 0.8436 (0.8465) time: 0.1325 data: 0.0490 max mem: 9394 +Train: [12] [2700/6250] eta: 0:08:51 lr: 0.000123 grad: 0.0633 (0.0672) loss: 0.8428 (0.8464) time: 0.1360 data: 0.0556 max mem: 9394 +Train: [12] [2800/6250] eta: 0:08:36 lr: 0.000123 grad: 0.0649 (0.0671) loss: 0.8454 (0.8463) time: 0.1913 data: 0.1097 max mem: 9394 +Train: [12] [2900/6250] eta: 0:08:19 lr: 0.000123 grad: 0.0631 (0.0670) loss: 0.8472 (0.8463) time: 0.1405 data: 0.0568 max mem: 9394 +Train: [12] [3000/6250] eta: 0:08:03 lr: 0.000123 grad: 0.0623 (0.0669) loss: 0.8496 (0.8462) time: 0.1406 data: 0.0563 max mem: 9394 +Train: [12] [3100/6250] eta: 0:07:47 lr: 0.000123 grad: 0.0658 (0.0668) loss: 0.8400 (0.8462) time: 0.1341 data: 0.0508 max mem: 9394 +Train: [12] [3200/6250] eta: 0:07:32 lr: 0.000123 grad: 0.0613 (0.0667) loss: 0.8428 (0.8462) time: 0.1415 data: 0.0608 max mem: 9394 +Train: [12] [3300/6250] eta: 0:07:16 lr: 0.000123 grad: 0.0610 (0.0666) loss: 0.8462 (0.8462) time: 0.1570 data: 0.0723 max mem: 9394 +Train: [12] [3400/6250] eta: 0:07:00 lr: 0.000123 grad: 0.0633 (0.0666) loss: 0.8519 (0.8462) time: 0.1269 data: 0.0436 max mem: 9394 +Train: [12] [3500/6250] eta: 0:06:48 lr: 0.000123 grad: 0.0619 (0.0666) loss: 0.8448 (0.8462) time: 0.1496 data: 0.0715 max mem: 9394 +Train: [12] [3600/6250] eta: 0:06:31 lr: 0.000123 grad: 0.0637 (0.0665) loss: 0.8485 (0.8462) time: 0.1320 data: 0.0498 max mem: 9394 +Train: [12] [3700/6250] eta: 0:06:16 lr: 0.000123 grad: 0.0588 (0.0664) loss: 0.8498 (0.8463) time: 0.1296 data: 0.0455 max mem: 9394 +Train: [12] [3800/6250] eta: 0:06:01 lr: 0.000123 grad: 0.0633 (0.0664) loss: 0.8483 (0.8464) time: 0.1311 data: 0.0427 max mem: 9394 +Train: [12] [3900/6250] eta: 0:05:46 lr: 0.000123 grad: 0.0637 (0.0663) loss: 0.8489 (0.8464) time: 0.1425 data: 0.0602 max mem: 9394 +Train: [12] [4000/6250] eta: 0:05:31 lr: 0.000123 grad: 0.0620 (0.0663) loss: 0.8482 (0.8464) time: 0.1706 data: 0.0938 max mem: 9394 +Train: [12] [4100/6250] eta: 0:05:15 lr: 0.000123 grad: 0.0607 (0.0663) loss: 0.8530 (0.8465) time: 0.1230 data: 0.0444 max mem: 9394 +Train: [12] [4200/6250] eta: 0:05:00 lr: 0.000123 grad: 0.0646 (0.0662) loss: 0.8463 (0.8464) time: 0.1527 data: 0.0720 max mem: 9394 +Train: [12] [4300/6250] eta: 0:04:45 lr: 0.000123 grad: 0.0622 (0.0661) loss: 0.8473 (0.8465) time: 0.1626 data: 0.0830 max mem: 9394 +Train: [12] [4400/6250] eta: 0:04:30 lr: 0.000123 grad: 0.0635 (0.0661) loss: 0.8479 (0.8465) time: 0.1382 data: 0.0403 max mem: 9394 +Train: [12] [4500/6250] eta: 0:04:16 lr: 0.000123 grad: 0.0618 (0.0661) loss: 0.8450 (0.8465) time: 0.1422 data: 0.0576 max mem: 9394 +Train: [12] [4600/6250] eta: 0:04:01 lr: 0.000123 grad: 0.0671 (0.0660) loss: 0.8433 (0.8465) time: 0.1431 data: 0.0570 max mem: 9394 +Train: [12] [4700/6250] eta: 0:03:46 lr: 0.000123 grad: 0.0600 (0.0660) loss: 0.8484 (0.8464) time: 0.1415 data: 0.0604 max mem: 9394 +Train: [12] [4800/6250] eta: 0:03:31 lr: 0.000123 grad: 0.0675 (0.0660) loss: 0.8458 (0.8464) time: 0.1183 data: 0.0357 max mem: 9394 +Train: [12] [4900/6250] eta: 0:03:16 lr: 0.000123 grad: 0.0635 (0.0660) loss: 0.8442 (0.8464) time: 0.1327 data: 0.0534 max mem: 9394 +Train: [12] [5000/6250] eta: 0:03:01 lr: 0.000123 grad: 0.0600 (0.0660) loss: 0.8423 (0.8464) time: 0.1282 data: 0.0449 max mem: 9394 +Train: [12] [5100/6250] eta: 0:02:46 lr: 0.000123 grad: 0.0567 (0.0659) loss: 0.8491 (0.8464) time: 0.1185 data: 0.0367 max mem: 9394 +Train: [12] [5200/6250] eta: 0:02:32 lr: 0.000123 grad: 0.0635 (0.0659) loss: 0.8424 (0.8463) time: 0.1327 data: 0.0558 max mem: 9394 +Train: [12] [5300/6250] eta: 0:02:17 lr: 0.000123 grad: 0.0648 (0.0658) loss: 0.8452 (0.8463) time: 0.1468 data: 0.0653 max mem: 9394 +Train: [12] [5400/6250] eta: 0:02:03 lr: 0.000123 grad: 0.0629 (0.0658) loss: 0.8479 (0.8463) time: 0.1338 data: 0.0518 max mem: 9394 +Train: [12] [5500/6250] eta: 0:01:48 lr: 0.000123 grad: 0.0627 (0.0657) loss: 0.8444 (0.8463) time: 0.1398 data: 0.0607 max mem: 9394 +Train: [12] [5600/6250] eta: 0:01:34 lr: 0.000123 grad: 0.0628 (0.0657) loss: 0.8427 (0.8462) time: 0.1394 data: 0.0596 max mem: 9394 +Train: [12] [5700/6250] eta: 0:01:19 lr: 0.000123 grad: 0.0607 (0.0657) loss: 0.8478 (0.8462) time: 0.1320 data: 0.0519 max mem: 9394 +Train: [12] [5800/6250] eta: 0:01:05 lr: 0.000123 grad: 0.0592 (0.0656) loss: 0.8438 (0.8462) time: 0.1685 data: 0.0781 max mem: 9394 +Train: [12] [5900/6250] eta: 0:00:50 lr: 0.000123 grad: 0.0634 (0.0656) loss: 0.8455 (0.8462) time: 0.1057 data: 0.0251 max mem: 9394 +Train: [12] [6000/6250] eta: 0:00:36 lr: 0.000123 grad: 0.0631 (0.0656) loss: 0.8443 (0.8462) time: 0.1374 data: 0.0536 max mem: 9394 +Train: [12] [6100/6250] eta: 0:00:21 lr: 0.000123 grad: 0.0651 (0.0655) loss: 0.8447 (0.8461) time: 0.1714 data: 0.0460 max mem: 9394 +Train: [12] [6200/6250] eta: 0:00:07 lr: 0.000123 grad: 0.0661 (0.0655) loss: 0.8433 (0.8461) time: 0.1315 data: 0.0450 max mem: 9394 +Train: [12] [6249/6250] eta: 0:00:00 lr: 0.000123 grad: 0.0631 (0.0655) loss: 0.8385 (0.8461) time: 0.1437 data: 0.0606 max mem: 9394 +Train: [12] Total time: 0:15:13 (0.1461 s / it) +Averaged stats: lr: 0.000123 grad: 0.0631 (0.0655) loss: 0.8385 (0.8461) +Eval (hcp-train-subset): [12] [ 0/62] eta: 0:02:50 loss: 0.8609 (0.8609) time: 2.7553 data: 2.6977 max mem: 9394 +Eval (hcp-train-subset): [12] [61/62] eta: 0:00:00 loss: 0.8523 (0.8511) time: 0.1266 data: 0.1018 max mem: 9394 +Eval (hcp-train-subset): [12] Total time: 0:00:12 (0.2027 s / it) +Averaged stats (hcp-train-subset): loss: 0.8523 (0.8511) +Eval (hcp-val): [12] [ 0/62] eta: 0:05:52 loss: 0.8461 (0.8461) time: 5.6882 data: 5.6589 max mem: 9394 +Eval (hcp-val): [12] [61/62] eta: 0:00:00 loss: 0.8439 (0.8459) time: 0.1514 data: 0.1256 max mem: 9394 +Eval (hcp-val): [12] Total time: 0:00:14 (0.2378 s / it) +Averaged stats (hcp-val): loss: 0.8439 (0.8459) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +Train: [13] [ 0/6250] eta: 9:35:06 lr: 0.000123 grad: 0.1008 (0.1008) loss: 0.8773 (0.8773) time: 5.5210 data: 5.4123 max mem: 9394 +Train: [13] [ 100/6250] eta: 0:21:06 lr: 0.000123 grad: 0.0652 (0.0711) loss: 0.8545 (0.8561) time: 0.1529 data: 0.0590 max mem: 9394 +Train: [13] [ 200/6250] eta: 0:18:20 lr: 0.000123 grad: 0.0599 (0.0672) loss: 0.8520 (0.8548) time: 0.1657 data: 0.0767 max mem: 9394 +Train: [13] [ 300/6250] eta: 0:17:50 lr: 0.000123 grad: 0.0652 (0.0666) loss: 0.8454 (0.8524) time: 0.1623 data: 0.0805 max mem: 9394 +Train: [13] [ 400/6250] eta: 0:17:18 lr: 0.000123 grad: 0.0628 (0.0659) loss: 0.8489 (0.8515) time: 0.1769 data: 0.0819 max mem: 9394 +Train: [13] [ 500/6250] eta: 0:16:45 lr: 0.000123 grad: 0.0610 (0.0656) loss: 0.8462 (0.8506) time: 0.1565 data: 0.0720 max mem: 9394 +Train: [13] [ 600/6250] eta: 0:16:02 lr: 0.000123 grad: 0.0633 (0.0653) loss: 0.8470 (0.8500) time: 0.1361 data: 0.0446 max mem: 9394 +Train: [13] [ 700/6250] eta: 0:15:26 lr: 0.000123 grad: 0.0600 (0.0649) loss: 0.8500 (0.8495) time: 0.1109 data: 0.0126 max mem: 9394 +Train: [13] [ 800/6250] eta: 0:14:47 lr: 0.000123 grad: 0.0671 (0.0648) loss: 0.8460 (0.8490) time: 0.1344 data: 0.0426 max mem: 9394 +Train: [13] [ 900/6250] eta: 0:14:23 lr: 0.000123 grad: 0.0662 (0.0650) loss: 0.8473 (0.8486) time: 0.1550 data: 0.0650 max mem: 9394 +Train: [13] [1000/6250] eta: 0:13:57 lr: 0.000123 grad: 0.0627 (0.0651) loss: 0.8405 (0.8482) time: 0.1334 data: 0.0495 max mem: 9394 +Train: [13] [1100/6250] eta: 0:13:39 lr: 0.000123 grad: 0.0655 (0.0653) loss: 0.8349 (0.8479) time: 0.2044 data: 0.1090 max mem: 9394 +Train: [13] [1200/6250] eta: 0:13:18 lr: 0.000123 grad: 0.0623 (0.0653) loss: 0.8441 (0.8475) time: 0.1521 data: 0.0704 max mem: 9394 +Train: [13] [1300/6250] eta: 0:13:37 lr: 0.000123 grad: 0.0635 (0.0654) loss: 0.8442 (0.8471) time: 0.2693 data: 0.1828 max mem: 9394 +Train: [13] [1400/6250] eta: 0:13:11 lr: 0.000123 grad: 0.0631 (0.0655) loss: 0.8413 (0.8468) time: 0.1513 data: 0.0691 max mem: 9394 +Train: [13] [1500/6250] eta: 0:12:56 lr: 0.000123 grad: 0.0648 (0.0655) loss: 0.8449 (0.8466) time: 0.2916 data: 0.2052 max mem: 9394 +Train: [13] [1600/6250] eta: 0:12:30 lr: 0.000123 grad: 0.0666 (0.0657) loss: 0.8374 (0.8463) time: 0.1246 data: 0.0352 max mem: 9394 +Train: [13] [1700/6250] eta: 0:12:13 lr: 0.000123 grad: 0.0667 (0.0658) loss: 0.8443 (0.8461) time: 0.1320 data: 0.0544 max mem: 9394 +Train: [13] [1800/6250] eta: 0:11:51 lr: 0.000123 grad: 0.0671 (0.0660) loss: 0.8460 (0.8459) time: 0.1505 data: 0.0723 max mem: 9394 +Train: [13] [1900/6250] eta: 0:11:32 lr: 0.000123 grad: 0.0609 (0.0660) loss: 0.8441 (0.8458) time: 0.1639 data: 0.0800 max mem: 9394 +Train: [13] [2000/6250] eta: 0:11:20 lr: 0.000123 grad: 0.0643 (0.0660) loss: 0.8455 (0.8457) time: 0.1637 data: 0.0537 max mem: 9394 +Train: [13] [2100/6250] eta: 0:11:05 lr: 0.000123 grad: 0.0715 (0.0660) loss: 0.8455 (0.8455) time: 0.1305 data: 0.0471 max mem: 9394 +Train: [13] [2200/6250] eta: 0:10:44 lr: 0.000123 grad: 0.0647 (0.0661) loss: 0.8444 (0.8454) time: 0.1317 data: 0.0530 max mem: 9394 +Train: [13] [2300/6250] eta: 0:10:24 lr: 0.000123 grad: 0.0652 (0.0661) loss: 0.8451 (0.8452) time: 0.1413 data: 0.0596 max mem: 9394 +Train: [13] [2400/6250] eta: 0:10:06 lr: 0.000123 grad: 0.0658 (0.0662) loss: 0.8398 (0.8451) time: 0.1549 data: 0.0724 max mem: 9394 +Train: [13] [2500/6250] eta: 0:09:46 lr: 0.000123 grad: 0.0624 (0.0662) loss: 0.8456 (0.8450) time: 0.1354 data: 0.0590 max mem: 9394 +Train: [13] [2600/6250] eta: 0:09:28 lr: 0.000123 grad: 0.0661 (0.0663) loss: 0.8431 (0.8449) time: 0.1544 data: 0.0728 max mem: 9394 +Train: [13] [2700/6250] eta: 0:09:11 lr: 0.000123 grad: 0.0610 (0.0663) loss: 0.8437 (0.8448) time: 0.1487 data: 0.0686 max mem: 9394 +Train: [13] [2800/6250] eta: 0:08:53 lr: 0.000123 grad: 0.0644 (0.0664) loss: 0.8422 (0.8447) time: 0.1442 data: 0.0627 max mem: 9394 +Train: [13] [2900/6250] eta: 0:08:36 lr: 0.000123 grad: 0.0658 (0.0665) loss: 0.8385 (0.8446) time: 0.1380 data: 0.0582 max mem: 9394 +Train: [13] [3000/6250] eta: 0:08:19 lr: 0.000123 grad: 0.0640 (0.0665) loss: 0.8426 (0.8445) time: 0.1435 data: 0.0695 max mem: 9394 +Train: [13] [3100/6250] eta: 0:08:03 lr: 0.000123 grad: 0.0655 (0.0665) loss: 0.8402 (0.8444) time: 0.1357 data: 0.0527 max mem: 9394 +Train: [13] [3200/6250] eta: 0:07:46 lr: 0.000123 grad: 0.0623 (0.0665) loss: 0.8430 (0.8444) time: 0.1303 data: 0.0467 max mem: 9394 +Train: [13] [3300/6250] eta: 0:07:29 lr: 0.000123 grad: 0.0628 (0.0664) loss: 0.8454 (0.8444) time: 0.1323 data: 0.0453 max mem: 9394 +Train: [13] [3400/6250] eta: 0:07:13 lr: 0.000123 grad: 0.0642 (0.0665) loss: 0.8367 (0.8443) time: 0.1344 data: 0.0490 max mem: 9394 +Train: [13] [3500/6250] eta: 0:06:57 lr: 0.000123 grad: 0.0611 (0.0666) loss: 0.8454 (0.8443) time: 0.1471 data: 0.0639 max mem: 9394 +Train: [13] [3600/6250] eta: 0:06:41 lr: 0.000123 grad: 0.0658 (0.0665) loss: 0.8375 (0.8442) time: 0.1400 data: 0.0576 max mem: 9394 +Train: [13] [3700/6250] eta: 0:06:25 lr: 0.000122 grad: 0.0628 (0.0664) loss: 0.8464 (0.8442) time: 0.1380 data: 0.0554 max mem: 9394 +Train: [13] [3800/6250] eta: 0:06:10 lr: 0.000122 grad: 0.0595 (0.0664) loss: 0.8433 (0.8441) time: 0.1513 data: 0.0700 max mem: 9394 +Train: [13] [3900/6250] eta: 0:05:53 lr: 0.000122 grad: 0.0639 (0.0664) loss: 0.8435 (0.8441) time: 0.1137 data: 0.0324 max mem: 9394 +Train: [13] [4000/6250] eta: 0:05:38 lr: 0.000122 grad: 0.0646 (0.0663) loss: 0.8452 (0.8441) time: 0.1446 data: 0.0664 max mem: 9394 +Train: [13] [4100/6250] eta: 0:05:22 lr: 0.000122 grad: 0.0643 (0.0663) loss: 0.8463 (0.8441) time: 0.1391 data: 0.0568 max mem: 9394 +Train: [13] [4200/6250] eta: 0:05:07 lr: 0.000122 grad: 0.0646 (0.0662) loss: 0.8499 (0.8442) time: 0.1529 data: 0.0723 max mem: 9394 +Train: [13] [4300/6250] eta: 0:04:51 lr: 0.000122 grad: 0.0592 (0.0662) loss: 0.8454 (0.8442) time: 0.1381 data: 0.0579 max mem: 9394 +Train: [13] [4400/6250] eta: 0:04:36 lr: 0.000122 grad: 0.0626 (0.0661) loss: 0.8443 (0.8442) time: 0.1375 data: 0.0578 max mem: 9394 +Train: [13] [4500/6250] eta: 0:04:20 lr: 0.000122 grad: 0.0638 (0.0660) loss: 0.8448 (0.8443) time: 0.1390 data: 0.0557 max mem: 9394 +Train: [13] [4600/6250] eta: 0:04:05 lr: 0.000122 grad: 0.0612 (0.0659) loss: 0.8429 (0.8443) time: 0.1477 data: 0.0646 max mem: 9394 +Train: [13] [4700/6250] eta: 0:03:50 lr: 0.000122 grad: 0.0595 (0.0659) loss: 0.8431 (0.8443) time: 0.1550 data: 0.0716 max mem: 9394 +Train: [13] [4800/6250] eta: 0:03:36 lr: 0.000122 grad: 0.0623 (0.0658) loss: 0.8447 (0.8442) time: 0.1251 data: 0.0365 max mem: 9394 +Train: [13] [4900/6250] eta: 0:03:20 lr: 0.000122 grad: 0.0600 (0.0658) loss: 0.8482 (0.8442) time: 0.1241 data: 0.0415 max mem: 9394 +Train: [13] [5000/6250] eta: 0:03:05 lr: 0.000122 grad: 0.0629 (0.0657) loss: 0.8419 (0.8442) time: 0.1492 data: 0.0726 max mem: 9394 +Train: [13] [5100/6250] eta: 0:02:50 lr: 0.000122 grad: 0.0609 (0.0658) loss: 0.8443 (0.8442) time: 0.1412 data: 0.0592 max mem: 9394 +Train: [13] [5200/6250] eta: 0:02:35 lr: 0.000122 grad: 0.0659 (0.0657) loss: 0.8427 (0.8442) time: 0.1407 data: 0.0586 max mem: 9394 +Train: [13] [5300/6250] eta: 0:02:21 lr: 0.000122 grad: 0.0609 (0.0657) loss: 0.8419 (0.8442) time: 0.1136 data: 0.0335 max mem: 9394 +Train: [13] [5400/6250] eta: 0:02:06 lr: 0.000122 grad: 0.0611 (0.0657) loss: 0.8374 (0.8442) time: 0.1362 data: 0.0600 max mem: 9394 +Train: [13] [5500/6250] eta: 0:01:51 lr: 0.000122 grad: 0.0584 (0.0656) loss: 0.8449 (0.8442) time: 0.1425 data: 0.0647 max mem: 9394 +pretraining fmri mae +start: 2026-03-31 20:04:03 +cwd: /data/connor/fmri-fm +sha: 7f4cedc35609f6857314e0d1ea6657523f17ddeb, status: has uncommitted changes, branch: dev/clane9 +config: +name: input_space_v3/flat_lr1e-3_4/pretrain +notes: input_space ablation v3 flat_lr1e-3_4; use tube masking and on-disk data (input_space=flat + base_lr=1e-3 seed=5404) +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain +input_space: flat +patch_size: 16 +num_frames: 16 +t_patch_size: 4 +mask_ratio: 0.9 +pred_mask_ratio: null +masking: tube +masking_kwargs: {} +mask_patch_size: null +model: mae_vit_base +model_kwargs: + decoding: attn + pos_embed: sep + target_norm: null + pca_norm_nc: 2 + t_pred_stride: 2 + no_decode_pos: true + mask_drop_scale: false + pred_edge_pad: 0 + gauss_sigma: null + class_token: true + reg_tokens: 0 + no_embed_class: true + head_init_scale: 0.0 + decoder_depth: 4 + drop_path_rate: 0.0 +datasets: + hcp-train: + type: wds + url: /data/fmri-datasets/pretrain/hcpya-all.${input_space}.wds/hcpya-all-${input_space}-{00000..01799}.tar + clipping: random + clipping_kwargs: + oversample: 4.0 + shuffle: true + buffer_size: 2000 + samples_per_epoch: 200000 + hcp-train-subset: + type: arrow + root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/validation + split_range: + - 0 + - 2000 + shuffle: false + hcp-val: + type: arrow + root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/test + split_range: + - 0 + - 2000 + shuffle: false +train_dataset: hcp-train +eval_datasets: +- hcp-train-subset +- hcp-val +val_dataset: null +clip_vmax: 3.0 +normalize: frame +tr_scale: null +crop_scale: null +crop_aspect: null +gray_jitter: null +num_workers: 16 +epochs: 100 +batch_size: 32 +accum_iter: 1 +base_lr: 0.001 +min_lr: 0.0 +warmup_epochs: 5 +weight_decay: 0.05 +betas: +- 0.9 +- 0.95 +clip_grad: 1.0 +amp: true +amp_dtype: float16 +ckpt: null +resume: true +auto_resume: true +start_epoch: 0 +max_checkpoints: 0 +checkpoint_period: null +plot_period: 5 +device: cuda +presend_cuda: false +seed: 5404 +debug: false +wandb: true +wandb_entity: null +wandb_project: fMRI-foundation-model +rank: 0 +world_size: 1 +gpu: 0 +distributed: true +dist_backend: nccl +in_chans: 1 +img_size: +- 224 +- 560 + +train transform: +Compose( + ToTensor() + TemporalCenterCrop(num_frames=16) + Normalize(mode='frame') + Clip(vmax=3.0) + FlatUnmask((224, 560)) +) +val transform: +Compose( + ToTensor() + TemporalCenterCrop(num_frames=16) + Normalize(mode='frame') + Clip(vmax=3.0) + FlatUnmask((224, 560)) +) +mask generator: +TubeMasking( + mask_ratio=0.9 + (patchify): Patchify2D((224, 560), (16, 16), in_chans=1) +) +loading dataset: hcp-train + +type: wds +url: /data/fmri-datasets/pretrain/hcpya-all.${input_space}.wds/hcpya-all-${input_space}-{00000..01799}.tar +clipping: random +clipping_kwargs: + oversample: 4.0 +shuffle: true +buffer_size: 2000 +samples_per_epoch: 200000 + +loading dataset: hcp-train-subset + +type: arrow +root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/validation +split_range: +- 0 +- 2000 +shuffle: false + +split indices: [899, 472, 767, 116, 1265, 1852, 300, 1335, 361, 1560] +loading dataset: hcp-val + +type: arrow +root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/test +split_range: +- 0 +- 2000 +shuffle: false + +split indices: [1075, 1189, 738, 1350, 965, 1964, 1367, 1183, 1619, 1407] +model: +MaskedAutoencoderViT( + decoding=attn, t_pred_stride=2, pred_edge_pad=0, no_decode_pos=True + (encoder): MaskedEncoder( + class_token=True, reg_tokens=0, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) + (pred_patchify): StridedPatchify3D((16, 224, 560), (2, 16, 16), in_chans=1, t_stride=2) + (decoder): MaskedDecoder( + cross_decode=False, class_token=True, no_embed_class=True + (pos_embed): SeparablePosEmbed(512, (4, 14, 35)) + (proj): Linear(in_features=768, out_features=512, bias=True) + (blocks): ModuleList( + (0-3): 4 x Block( + (norm1): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=16 + (q): Linear(in_features=512, out_features=512, bias=True) + (k): Linear(in_features=512, out_features=512, bias=True) + (v): Linear(in_features=512, out_features=512, bias=True) + (proj): Linear(in_features=512, out_features=512, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=512, out_features=2048, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=2048, out_features=512, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (head): Linear(in_features=512, out_features=512, bias=True) + ) +) +num params: 99.7M +total batch size: 32 = 32 bs per gpu x 1 accum x 1 gpus +lr: 1.25e-04 = 1.00e-03 x 32 / 256 +full schedule: epochs = 100 (steps = 625000) +warmup: epochs = 5 (steps = 31250) +loaded model state from checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +loaded optimizer state, resuming training from 13 +start training for 100 epochs +Train: [13] [ 0/6250] eta: 11:46:04 lr: 0.000123 grad: 0.0456 (0.0456) loss: 0.8649 (0.8649) time: 6.7784 data: 5.5868 max mem: 9353 +Train: [13] [ 100/6250] eta: 0:21:43 lr: 0.000123 grad: 0.0696 (0.0702) loss: 0.8376 (0.8459) time: 0.1210 data: 0.0402 max mem: 9390 +Train: [13] [ 200/6250] eta: 0:18:43 lr: 0.000123 grad: 0.0659 (0.0685) loss: 0.8418 (0.8437) time: 0.1503 data: 0.0501 max mem: 9390 +Train: [13] [ 300/6250] eta: 0:18:23 lr: 0.000123 grad: 0.0639 (0.0677) loss: 0.8464 (0.8430) time: 0.2034 data: 0.0395 max mem: 9390 +Train: [13] [ 400/6250] eta: 0:18:08 lr: 0.000123 grad: 0.0620 (0.0673) loss: 0.8457 (0.8430) time: 0.2398 data: 0.1490 max mem: 9390 +Train: [13] [ 500/6250] eta: 0:17:20 lr: 0.000123 grad: 0.0690 (0.0675) loss: 0.8446 (0.8428) time: 0.1535 data: 0.0605 max mem: 9390 +Train: [13] [ 600/6250] eta: 0:16:57 lr: 0.000123 grad: 0.0666 (0.0676) loss: 0.8407 (0.8428) time: 0.1128 data: 0.0119 max mem: 9390 +Train: [13] [ 700/6250] eta: 0:16:24 lr: 0.000123 grad: 0.0645 (0.0676) loss: 0.8401 (0.8428) time: 0.1054 data: 0.0134 max mem: 9390 +Train: [13] [ 800/6250] eta: 0:15:43 lr: 0.000123 grad: 0.0654 (0.0681) loss: 0.8441 (0.8426) time: 0.1266 data: 0.0419 max mem: 9390 +Train: [13] [ 900/6250] eta: 0:15:10 lr: 0.000123 grad: 0.0612 (0.0677) loss: 0.8484 (0.8428) time: 0.1580 data: 0.0783 max mem: 9390 +Train: [13] [1000/6250] eta: 0:14:31 lr: 0.000123 grad: 0.0583 (0.0675) loss: 0.8448 (0.8430) time: 0.1238 data: 0.0456 max mem: 9390 +Train: [13] [1100/6250] eta: 0:13:58 lr: 0.000123 grad: 0.0661 (0.0674) loss: 0.8422 (0.8431) time: 0.1446 data: 0.0634 max mem: 9390 +Train: [13] [1200/6250] eta: 0:13:28 lr: 0.000123 grad: 0.0617 (0.0672) loss: 0.8455 (0.8432) time: 0.1295 data: 0.0486 max mem: 9390 +Train: [13] [1300/6250] eta: 0:13:05 lr: 0.000123 grad: 0.0621 (0.0669) loss: 0.8400 (0.8432) time: 0.1208 data: 0.0413 max mem: 9390 +Train: [13] [1400/6250] eta: 0:12:42 lr: 0.000123 grad: 0.0598 (0.0668) loss: 0.8425 (0.8432) time: 0.1596 data: 0.0791 max mem: 9390 +Train: [13] [1500/6250] eta: 0:12:15 lr: 0.000123 grad: 0.0625 (0.0666) loss: 0.8490 (0.8434) time: 0.1043 data: 0.0201 max mem: 9390 +Train: [13] [1600/6250] eta: 0:11:53 lr: 0.000123 grad: 0.0600 (0.0666) loss: 0.8503 (0.8435) time: 0.1328 data: 0.0598 max mem: 9390 +Train: [13] [1700/6250] eta: 0:11:30 lr: 0.000123 grad: 0.0627 (0.0665) loss: 0.8387 (0.8435) time: 0.1243 data: 0.0451 max mem: 9390 +Train: [13] [1800/6250] eta: 0:11:11 lr: 0.000123 grad: 0.0618 (0.0665) loss: 0.8408 (0.8433) time: 0.1266 data: 0.0473 max mem: 9390 +Train: [13] [1900/6250] eta: 0:10:51 lr: 0.000123 grad: 0.0648 (0.0664) loss: 0.8473 (0.8433) time: 0.1417 data: 0.0640 max mem: 9390 +Train: [13] [2000/6250] eta: 0:10:32 lr: 0.000123 grad: 0.0601 (0.0663) loss: 0.8480 (0.8434) time: 0.1165 data: 0.0362 max mem: 9390 +Train: [13] [2100/6250] eta: 0:10:13 lr: 0.000123 grad: 0.0627 (0.0663) loss: 0.8459 (0.8436) time: 0.1390 data: 0.0612 max mem: 9390 +Train: [13] [2200/6250] eta: 0:09:55 lr: 0.000123 grad: 0.0647 (0.0663) loss: 0.8395 (0.8435) time: 0.1204 data: 0.0388 max mem: 9390 +Train: [13] [2300/6250] eta: 0:09:37 lr: 0.000123 grad: 0.0595 (0.0661) loss: 0.8433 (0.8436) time: 0.1275 data: 0.0451 max mem: 9390 +Train: [13] [2400/6250] eta: 0:09:21 lr: 0.000123 grad: 0.0625 (0.0660) loss: 0.8390 (0.8435) time: 0.1341 data: 0.0562 max mem: 9390 +Train: [13] [2500/6250] eta: 0:09:04 lr: 0.000123 grad: 0.0693 (0.0661) loss: 0.8384 (0.8435) time: 0.1549 data: 0.0746 max mem: 9390 +Train: [13] [2600/6250] eta: 0:08:47 lr: 0.000123 grad: 0.0622 (0.0661) loss: 0.8393 (0.8434) time: 0.1265 data: 0.0434 max mem: 9390 +Train: [13] [2700/6250] eta: 0:08:32 lr: 0.000123 grad: 0.0660 (0.0661) loss: 0.8408 (0.8433) time: 0.1392 data: 0.0606 max mem: 9390 +Train: [13] [2800/6250] eta: 0:08:16 lr: 0.000123 grad: 0.0648 (0.0661) loss: 0.8431 (0.8433) time: 0.1188 data: 0.0326 max mem: 9390 +Train: [13] [2900/6250] eta: 0:08:00 lr: 0.000123 grad: 0.0640 (0.0661) loss: 0.8444 (0.8432) time: 0.1339 data: 0.0532 max mem: 9390 +Train: [13] [3000/6250] eta: 0:07:45 lr: 0.000123 grad: 0.0639 (0.0663) loss: 0.8400 (0.8432) time: 0.1227 data: 0.0394 max mem: 9390 +Train: [13] [3100/6250] eta: 0:07:30 lr: 0.000123 grad: 0.0620 (0.0662) loss: 0.8412 (0.8431) time: 0.1111 data: 0.0318 max mem: 9390 +Train: [13] [3200/6250] eta: 0:07:15 lr: 0.000123 grad: 0.0690 (0.0664) loss: 0.8412 (0.8430) time: 0.1399 data: 0.0525 max mem: 9390 +Train: [13] [3300/6250] eta: 0:07:01 lr: 0.000123 grad: 0.0656 (0.0665) loss: 0.8414 (0.8430) time: 0.1474 data: 0.0686 max mem: 9390 +Train: [13] [3400/6250] eta: 0:06:46 lr: 0.000123 grad: 0.0620 (0.0664) loss: 0.8435 (0.8428) time: 0.1265 data: 0.0495 max mem: 9390 +Train: [13] [3500/6250] eta: 0:06:31 lr: 0.000123 grad: 0.0642 (0.0665) loss: 0.8423 (0.8428) time: 0.1165 data: 0.0393 max mem: 9390 +Train: [13] [3600/6250] eta: 0:06:17 lr: 0.000123 grad: 0.0631 (0.0665) loss: 0.8404 (0.8427) time: 0.1408 data: 0.0607 max mem: 9390 +Train: [13] [3700/6250] eta: 0:06:02 lr: 0.000122 grad: 0.0618 (0.0665) loss: 0.8446 (0.8426) time: 0.1432 data: 0.0662 max mem: 9390 +Train: [13] [3800/6250] eta: 0:05:47 lr: 0.000122 grad: 0.0635 (0.0665) loss: 0.8441 (0.8426) time: 0.1416 data: 0.0610 max mem: 9390 +Train: [13] [3900/6250] eta: 0:05:33 lr: 0.000122 grad: 0.0629 (0.0665) loss: 0.8371 (0.8426) time: 0.1209 data: 0.0404 max mem: 9390 +Train: [13] [4000/6250] eta: 0:05:18 lr: 0.000122 grad: 0.0659 (0.0665) loss: 0.8400 (0.8426) time: 0.1298 data: 0.0521 max mem: 9390 +Train: [13] [4100/6250] eta: 0:05:04 lr: 0.000122 grad: 0.0614 (0.0665) loss: 0.8439 (0.8426) time: 0.1622 data: 0.0871 max mem: 9390 +Train: [13] [4200/6250] eta: 0:04:49 lr: 0.000122 grad: 0.0619 (0.0665) loss: 0.8392 (0.8426) time: 0.1351 data: 0.0522 max mem: 9390 +Train: [13] [4300/6250] eta: 0:04:35 lr: 0.000122 grad: 0.0640 (0.0665) loss: 0.8432 (0.8425) time: 0.1585 data: 0.0771 max mem: 9390 +Train: [13] [4400/6250] eta: 0:04:21 lr: 0.000122 grad: 0.0667 (0.0665) loss: 0.8410 (0.8425) time: 0.1350 data: 0.0519 max mem: 9390 +Train: [13] [4500/6250] eta: 0:04:06 lr: 0.000122 grad: 0.0669 (0.0666) loss: 0.8421 (0.8424) time: 0.1488 data: 0.0637 max mem: 9390 +Train: [13] [4600/6250] eta: 0:03:52 lr: 0.000122 grad: 0.0623 (0.0665) loss: 0.8403 (0.8424) time: 0.1466 data: 0.0710 max mem: 9390 +Train: [13] [4700/6250] eta: 0:03:38 lr: 0.000122 grad: 0.0659 (0.0665) loss: 0.8462 (0.8424) time: 0.1472 data: 0.0717 max mem: 9390 +Train: [13] [4800/6250] eta: 0:03:24 lr: 0.000122 grad: 0.0598 (0.0665) loss: 0.8412 (0.8424) time: 0.1367 data: 0.0576 max mem: 9390 +Train: [13] [4900/6250] eta: 0:03:10 lr: 0.000122 grad: 0.0664 (0.0665) loss: 0.8400 (0.8424) time: 0.1276 data: 0.0512 max mem: 9390 +Train: [13] [5000/6250] eta: 0:02:55 lr: 0.000122 grad: 0.0629 (0.0665) loss: 0.8447 (0.8424) time: 0.1593 data: 0.0774 max mem: 9390 +Train: [13] [5100/6250] eta: 0:02:41 lr: 0.000122 grad: 0.0650 (0.0665) loss: 0.8390 (0.8424) time: 0.1377 data: 0.0601 max mem: 9390 +Train: [13] [5200/6250] eta: 0:02:27 lr: 0.000122 grad: 0.0657 (0.0665) loss: 0.8422 (0.8424) time: 0.1263 data: 0.0459 max mem: 9390 +Train: [13] [5300/6250] eta: 0:02:13 lr: 0.000122 grad: 0.0657 (0.0666) loss: 0.8421 (0.8423) time: 0.1442 data: 0.0683 max mem: 9390 +Train: [13] [5400/6250] eta: 0:01:59 lr: 0.000122 grad: 0.0648 (0.0665) loss: 0.8418 (0.8423) time: 0.1218 data: 0.0354 max mem: 9390 +Train: [13] [5500/6250] eta: 0:01:45 lr: 0.000122 grad: 0.0646 (0.0665) loss: 0.8441 (0.8423) time: 0.1358 data: 0.0572 max mem: 9390 +Train: [13] [5600/6250] eta: 0:01:30 lr: 0.000122 grad: 0.0620 (0.0665) loss: 0.8442 (0.8423) time: 0.1101 data: 0.0291 max mem: 9390 +Train: [13] [5700/6250] eta: 0:01:16 lr: 0.000122 grad: 0.0667 (0.0665) loss: 0.8429 (0.8423) time: 0.1304 data: 0.0545 max mem: 9390 +Train: [13] [5800/6250] eta: 0:01:02 lr: 0.000122 grad: 0.0622 (0.0664) loss: 0.8416 (0.8424) time: 0.1551 data: 0.0783 max mem: 9390 +Train: [13] [5900/6250] eta: 0:00:48 lr: 0.000122 grad: 0.0627 (0.0664) loss: 0.8419 (0.8423) time: 0.1325 data: 0.0520 max mem: 9390 +Train: [13] [6000/6250] eta: 0:00:34 lr: 0.000122 grad: 0.0628 (0.0664) loss: 0.8411 (0.8423) time: 0.1226 data: 0.0385 max mem: 9390 +Train: [13] [6100/6250] eta: 0:00:20 lr: 0.000122 grad: 0.0639 (0.0664) loss: 0.8421 (0.8423) time: 0.1503 data: 0.0739 max mem: 9390 +Train: [13] [6200/6250] eta: 0:00:07 lr: 0.000122 grad: 0.0614 (0.0664) loss: 0.8453 (0.8423) time: 0.1612 data: 0.0683 max mem: 9390 +Train: [13] [6249/6250] eta: 0:00:00 lr: 0.000122 grad: 0.0628 (0.0663) loss: 0.8411 (0.8423) time: 0.1367 data: 0.0471 max mem: 9390 +Train: [13] Total time: 0:14:41 (0.1411 s / it) +Averaged stats: lr: 0.000122 grad: 0.0628 (0.0663) loss: 0.8411 (0.8423) +Eval (hcp-train-subset): [13] [ 0/62] eta: 0:04:24 loss: 0.8598 (0.8598) time: 4.2668 data: 4.2385 max mem: 9390 +Eval (hcp-train-subset): [13] [61/62] eta: 0:00:00 loss: 0.8528 (0.8509) time: 0.1140 data: 0.0895 max mem: 9390 +Eval (hcp-train-subset): [13] Total time: 0:00:12 (0.1962 s / it) +Averaged stats (hcp-train-subset): loss: 0.8528 (0.8509) +Eval (hcp-val): [13] [ 0/62] eta: 0:04:39 loss: 0.8416 (0.8416) time: 4.5067 data: 4.4780 max mem: 9390 +Eval (hcp-val): [13] [61/62] eta: 0:00:00 loss: 0.8449 (0.8445) time: 0.1234 data: 0.0968 max mem: 9390 +Eval (hcp-val): [13] Total time: 0:00:12 (0.1945 s / it) +Averaged stats (hcp-val): loss: 0.8449 (0.8445) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +Train: [14] [ 0/6250] eta: 8:02:39 lr: 0.000122 grad: 0.0644 (0.0644) loss: 0.8705 (0.8705) time: 4.6335 data: 4.5290 max mem: 9390 +Train: [14] [ 100/6250] eta: 0:18:40 lr: 0.000122 grad: 0.0642 (0.0680) loss: 0.8519 (0.8571) time: 0.1388 data: 0.0578 max mem: 9390 +Train: [14] [ 200/6250] eta: 0:16:13 lr: 0.000122 grad: 0.0752 (0.0696) loss: 0.8427 (0.8512) time: 0.1154 data: 0.0377 max mem: 9390 +Train: [14] [ 300/6250] eta: 0:15:14 lr: 0.000122 grad: 0.0610 (0.0687) loss: 0.8411 (0.8494) time: 0.1430 data: 0.0631 max mem: 9390 +Train: [14] [ 400/6250] eta: 0:14:28 lr: 0.000122 grad: 0.0637 (0.0680) loss: 0.8445 (0.8478) time: 0.1366 data: 0.0526 max mem: 9390 +Train: [14] [ 500/6250] eta: 0:13:44 lr: 0.000122 grad: 0.0596 (0.0677) loss: 0.8491 (0.8471) time: 0.1287 data: 0.0475 max mem: 9390 +Train: [14] [ 600/6250] eta: 0:13:18 lr: 0.000122 grad: 0.0622 (0.0668) loss: 0.8430 (0.8470) time: 0.1344 data: 0.0516 max mem: 9390 +Train: [14] [ 700/6250] eta: 0:13:02 lr: 0.000122 grad: 0.0597 (0.0664) loss: 0.8484 (0.8467) time: 0.1365 data: 0.0502 max mem: 9390 +Train: [14] [ 800/6250] eta: 0:12:49 lr: 0.000122 grad: 0.0640 (0.0661) loss: 0.8460 (0.8464) time: 0.1462 data: 0.0498 max mem: 9390 +Train: [14] [ 900/6250] eta: 0:12:36 lr: 0.000122 grad: 0.0619 (0.0659) loss: 0.8453 (0.8462) time: 0.1479 data: 0.0661 max mem: 9390 +Train: [14] [1000/6250] eta: 0:12:21 lr: 0.000122 grad: 0.0640 (0.0659) loss: 0.8386 (0.8457) time: 0.1505 data: 0.0716 max mem: 9390 +Train: [14] [1100/6250] eta: 0:12:04 lr: 0.000122 grad: 0.0665 (0.0660) loss: 0.8385 (0.8450) time: 0.1328 data: 0.0525 max mem: 9390 +Train: [14] [1200/6250] eta: 0:11:48 lr: 0.000122 grad: 0.0690 (0.0661) loss: 0.8342 (0.8444) time: 0.1044 data: 0.0237 max mem: 9390 +Train: [14] [1300/6250] eta: 0:11:34 lr: 0.000122 grad: 0.0665 (0.0660) loss: 0.8395 (0.8440) time: 0.1428 data: 0.0646 max mem: 9390 +Train: [14] [1400/6250] eta: 0:11:19 lr: 0.000122 grad: 0.0676 (0.0661) loss: 0.8378 (0.8436) time: 0.1188 data: 0.0386 max mem: 9390 +Train: [14] [1500/6250] eta: 0:11:04 lr: 0.000122 grad: 0.0660 (0.0661) loss: 0.8402 (0.8432) time: 0.0990 data: 0.0153 max mem: 9390 +Train: [14] [1600/6250] eta: 0:10:49 lr: 0.000122 grad: 0.0651 (0.0665) loss: 0.8347 (0.8428) time: 0.1357 data: 0.0546 max mem: 9390 +Train: [14] [1700/6250] eta: 0:10:34 lr: 0.000122 grad: 0.0656 (0.0667) loss: 0.8392 (0.8425) time: 0.1383 data: 0.0576 max mem: 9390 +Train: [14] [1800/6250] eta: 0:10:19 lr: 0.000122 grad: 0.0639 (0.0669) loss: 0.8388 (0.8422) time: 0.1459 data: 0.0665 max mem: 9390 +Train: [14] [1900/6250] eta: 0:10:03 lr: 0.000122 grad: 0.0642 (0.0669) loss: 0.8356 (0.8419) time: 0.1263 data: 0.0482 max mem: 9390 +Train: [14] [2000/6250] eta: 0:09:46 lr: 0.000122 grad: 0.0657 (0.0669) loss: 0.8369 (0.8418) time: 0.1159 data: 0.0257 max mem: 9390 +Train: [14] [2100/6250] eta: 0:09:32 lr: 0.000122 grad: 0.0620 (0.0669) loss: 0.8423 (0.8416) time: 0.1500 data: 0.0700 max mem: 9390 +Train: [14] [2200/6250] eta: 0:09:17 lr: 0.000122 grad: 0.0653 (0.0670) loss: 0.8438 (0.8416) time: 0.1197 data: 0.0419 max mem: 9390 +Train: [14] [2300/6250] eta: 0:09:02 lr: 0.000122 grad: 0.0620 (0.0671) loss: 0.8389 (0.8414) time: 0.1298 data: 0.0475 max mem: 9390 +Train: [14] [2400/6250] eta: 0:08:48 lr: 0.000122 grad: 0.0677 (0.0671) loss: 0.8381 (0.8413) time: 0.1267 data: 0.0517 max mem: 9390 +Train: [14] [2500/6250] eta: 0:08:33 lr: 0.000122 grad: 0.0644 (0.0670) loss: 0.8412 (0.8414) time: 0.0995 data: 0.0203 max mem: 9390 +Train: [14] [2600/6250] eta: 0:08:20 lr: 0.000122 grad: 0.0690 (0.0670) loss: 0.8402 (0.8414) time: 0.1403 data: 0.0598 max mem: 9390 +Train: [14] [2700/6250] eta: 0:08:05 lr: 0.000122 grad: 0.0637 (0.0669) loss: 0.8378 (0.8414) time: 0.1300 data: 0.0471 max mem: 9390 +Train: [14] [2800/6250] eta: 0:07:51 lr: 0.000122 grad: 0.0654 (0.0669) loss: 0.8400 (0.8414) time: 0.1322 data: 0.0550 max mem: 9390 +Train: [14] [2900/6250] eta: 0:07:38 lr: 0.000122 grad: 0.0618 (0.0668) loss: 0.8456 (0.8414) time: 0.1284 data: 0.0457 max mem: 9390 +Train: [14] [3000/6250] eta: 0:07:24 lr: 0.000122 grad: 0.0707 (0.0669) loss: 0.8416 (0.8415) time: 0.1422 data: 0.0606 max mem: 9390 +Train: [14] [3100/6250] eta: 0:07:10 lr: 0.000122 grad: 0.0614 (0.0668) loss: 0.8474 (0.8416) time: 0.1506 data: 0.0760 max mem: 9390 +Train: [14] [3200/6250] eta: 0:06:56 lr: 0.000122 grad: 0.0653 (0.0667) loss: 0.8432 (0.8416) time: 0.1325 data: 0.0557 max mem: 9390 +Train: [14] [3300/6250] eta: 0:06:42 lr: 0.000122 grad: 0.0644 (0.0666) loss: 0.8426 (0.8417) time: 0.1283 data: 0.0507 max mem: 9390 +Train: [14] [3400/6250] eta: 0:06:29 lr: 0.000122 grad: 0.0641 (0.0666) loss: 0.8436 (0.8418) time: 0.1281 data: 0.0527 max mem: 9390 +Train: [14] [3500/6250] eta: 0:06:15 lr: 0.000122 grad: 0.0641 (0.0665) loss: 0.8394 (0.8418) time: 0.1444 data: 0.0646 max mem: 9390 +Train: [14] [3600/6250] eta: 0:06:01 lr: 0.000122 grad: 0.0623 (0.0665) loss: 0.8394 (0.8418) time: 0.1269 data: 0.0477 max mem: 9390 +Train: [14] [3700/6250] eta: 0:05:47 lr: 0.000122 grad: 0.0615 (0.0665) loss: 0.8437 (0.8418) time: 0.1344 data: 0.0586 max mem: 9390 +Train: [14] [3800/6250] eta: 0:05:34 lr: 0.000122 grad: 0.0605 (0.0664) loss: 0.8449 (0.8418) time: 0.1321 data: 0.0571 max mem: 9390 +Train: [14] [3900/6250] eta: 0:05:20 lr: 0.000122 grad: 0.0642 (0.0664) loss: 0.8438 (0.8419) time: 0.1277 data: 0.0479 max mem: 9390 +Train: [14] [4000/6250] eta: 0:05:06 lr: 0.000122 grad: 0.0626 (0.0663) loss: 0.8424 (0.8419) time: 0.1117 data: 0.0343 max mem: 9390 +Train: [14] [4100/6250] eta: 0:04:53 lr: 0.000122 grad: 0.0615 (0.0663) loss: 0.8429 (0.8419) time: 0.1424 data: 0.0632 max mem: 9390 +Train: [14] [4200/6250] eta: 0:04:39 lr: 0.000122 grad: 0.0621 (0.0663) loss: 0.8407 (0.8419) time: 0.1306 data: 0.0553 max mem: 9390 +Train: [14] [4300/6250] eta: 0:04:25 lr: 0.000122 grad: 0.0619 (0.0662) loss: 0.8415 (0.8419) time: 0.1361 data: 0.0554 max mem: 9390 +Train: [14] [4400/6250] eta: 0:04:12 lr: 0.000122 grad: 0.0652 (0.0662) loss: 0.8432 (0.8419) time: 0.1546 data: 0.0686 max mem: 9390 +Train: [14] [4500/6250] eta: 0:03:58 lr: 0.000122 grad: 0.0720 (0.0662) loss: 0.8415 (0.8419) time: 0.1117 data: 0.0321 max mem: 9390 +Train: [14] [4600/6250] eta: 0:03:45 lr: 0.000122 grad: 0.0613 (0.0662) loss: 0.8479 (0.8419) time: 0.1605 data: 0.0871 max mem: 9390 +Train: [14] [4700/6250] eta: 0:03:31 lr: 0.000122 grad: 0.0619 (0.0661) loss: 0.8470 (0.8419) time: 0.1378 data: 0.0595 max mem: 9390 +Train: [14] [4800/6250] eta: 0:03:17 lr: 0.000122 grad: 0.0657 (0.0660) loss: 0.8368 (0.8419) time: 0.1333 data: 0.0567 max mem: 9390 +Train: [14] [4900/6250] eta: 0:03:04 lr: 0.000122 grad: 0.0602 (0.0660) loss: 0.8415 (0.8419) time: 0.1528 data: 0.0798 max mem: 9390 +Train: [14] [5000/6250] eta: 0:02:50 lr: 0.000122 grad: 0.0604 (0.0660) loss: 0.8378 (0.8419) time: 0.1164 data: 0.0381 max mem: 9390 +Train: [14] [5100/6250] eta: 0:02:36 lr: 0.000122 grad: 0.0656 (0.0660) loss: 0.8381 (0.8419) time: 0.1299 data: 0.0490 max mem: 9390 +Train: [14] [5200/6250] eta: 0:02:22 lr: 0.000122 grad: 0.0653 (0.0659) loss: 0.8389 (0.8419) time: 0.1566 data: 0.0788 max mem: 9390 +Train: [14] [5300/6250] eta: 0:02:09 lr: 0.000122 grad: 0.0598 (0.0659) loss: 0.8449 (0.8419) time: 0.1464 data: 0.0665 max mem: 9390 +Train: [14] [5400/6250] eta: 0:01:55 lr: 0.000122 grad: 0.0593 (0.0658) loss: 0.8414 (0.8419) time: 0.1454 data: 0.0676 max mem: 9390 +Train: [14] [5500/6250] eta: 0:01:42 lr: 0.000122 grad: 0.0653 (0.0658) loss: 0.8405 (0.8419) time: 0.1432 data: 0.0643 max mem: 9390 +Train: [14] [5600/6250] eta: 0:01:28 lr: 0.000122 grad: 0.0608 (0.0657) loss: 0.8427 (0.8419) time: 0.1347 data: 0.0529 max mem: 9390 +Train: [14] [5700/6250] eta: 0:01:14 lr: 0.000122 grad: 0.0651 (0.0657) loss: 0.8437 (0.8420) time: 0.1155 data: 0.0334 max mem: 9390 +Train: [14] [5800/6250] eta: 0:01:01 lr: 0.000122 grad: 0.0644 (0.0656) loss: 0.8382 (0.8419) time: 0.1382 data: 0.0596 max mem: 9390 +Train: [14] [5900/6250] eta: 0:00:47 lr: 0.000122 grad: 0.0614 (0.0656) loss: 0.8415 (0.8420) time: 0.1184 data: 0.0403 max mem: 9390 +Train: [14] [6000/6250] eta: 0:00:34 lr: 0.000122 grad: 0.0632 (0.0656) loss: 0.8443 (0.8420) time: 0.1295 data: 0.0416 max mem: 9390 +Train: [14] [6100/6250] eta: 0:00:20 lr: 0.000122 grad: 0.0638 (0.0656) loss: 0.8412 (0.8420) time: 0.1529 data: 0.0750 max mem: 9390 +Train: [14] [6200/6250] eta: 0:00:06 lr: 0.000122 grad: 0.0661 (0.0656) loss: 0.8410 (0.8419) time: 0.1411 data: 0.0556 max mem: 9390 +Train: [14] [6249/6250] eta: 0:00:00 lr: 0.000122 grad: 0.0641 (0.0656) loss: 0.8430 (0.8419) time: 0.1402 data: 0.0591 max mem: 9390 +Train: [14] Total time: 0:14:20 (0.1377 s / it) +Averaged stats: lr: 0.000122 grad: 0.0641 (0.0656) loss: 0.8430 (0.8419) +Eval (hcp-train-subset): [14] [ 0/62] eta: 0:03:02 loss: 0.8572 (0.8572) time: 2.9449 data: 2.8990 max mem: 9390 +Eval (hcp-train-subset): [14] [61/62] eta: 0:00:00 loss: 0.8470 (0.8489) time: 0.1159 data: 0.0914 max mem: 9390 +Eval (hcp-train-subset): [14] Total time: 0:00:11 (0.1815 s / it) +Averaged stats (hcp-train-subset): loss: 0.8470 (0.8489) +Making plots (hcp-train-subset): example=7 +Eval (hcp-val): [14] [ 0/62] eta: 0:04:21 loss: 0.8431 (0.8431) time: 4.2245 data: 4.1949 max mem: 9390 +Eval (hcp-val): [14] [61/62] eta: 0:00:00 loss: 0.8430 (0.8442) time: 0.1216 data: 0.0968 max mem: 9390 +Eval (hcp-val): [14] Total time: 0:00:12 (0.1979 s / it) +Averaged stats (hcp-val): loss: 0.8430 (0.8442) +Making plots (hcp-val): example=17 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +Train: [15] [ 0/6250] eta: 9:05:24 lr: 0.000122 grad: 0.0511 (0.0511) loss: 0.8678 (0.8678) time: 5.2359 data: 5.1431 max mem: 9390 +Train: [15] [ 100/6250] eta: 0:18:49 lr: 0.000122 grad: 0.0616 (0.0675) loss: 0.8397 (0.8453) time: 0.1573 data: 0.0699 max mem: 9390 +Train: [15] [ 200/6250] eta: 0:16:19 lr: 0.000122 grad: 0.0638 (0.0666) loss: 0.8333 (0.8437) time: 0.1489 data: 0.0678 max mem: 9390 +Train: [15] [ 300/6250] eta: 0:15:03 lr: 0.000122 grad: 0.0694 (0.0663) loss: 0.8399 (0.8429) time: 0.1265 data: 0.0425 max mem: 9390 +Train: [15] [ 400/6250] eta: 0:14:17 lr: 0.000122 grad: 0.0595 (0.0661) loss: 0.8427 (0.8427) time: 0.1151 data: 0.0259 max mem: 9390 +Train: [15] [ 500/6250] eta: 0:13:54 lr: 0.000122 grad: 0.0593 (0.0657) loss: 0.8444 (0.8425) time: 0.1410 data: 0.0475 max mem: 9390 +Train: [15] [ 600/6250] eta: 0:13:48 lr: 0.000122 grad: 0.0633 (0.0653) loss: 0.8447 (0.8427) time: 0.1767 data: 0.0692 max mem: 9390 +Train: [15] [ 700/6250] eta: 0:13:30 lr: 0.000122 grad: 0.0636 (0.0653) loss: 0.8385 (0.8425) time: 0.1255 data: 0.0410 max mem: 9390 +Train: [15] [ 800/6250] eta: 0:13:16 lr: 0.000122 grad: 0.0649 (0.0655) loss: 0.8437 (0.8423) time: 0.1585 data: 0.0788 max mem: 9390 +Train: [15] [ 900/6250] eta: 0:12:58 lr: 0.000122 grad: 0.0632 (0.0655) loss: 0.8393 (0.8419) time: 0.1544 data: 0.0753 max mem: 9390 +Train: [15] [1000/6250] eta: 0:12:40 lr: 0.000122 grad: 0.0646 (0.0654) loss: 0.8380 (0.8418) time: 0.1248 data: 0.0463 max mem: 9390 +Train: [15] [1100/6250] eta: 0:12:23 lr: 0.000121 grad: 0.0622 (0.0652) loss: 0.8401 (0.8417) time: 0.1329 data: 0.0536 max mem: 9390 +Train: [15] [1200/6250] eta: 0:12:04 lr: 0.000121 grad: 0.0615 (0.0653) loss: 0.8430 (0.8415) time: 0.1342 data: 0.0562 max mem: 9390 +Train: [15] [1300/6250] eta: 0:11:48 lr: 0.000121 grad: 0.0688 (0.0653) loss: 0.8386 (0.8414) time: 0.1467 data: 0.0688 max mem: 9390 +Train: [15] [1400/6250] eta: 0:11:33 lr: 0.000121 grad: 0.0631 (0.0652) loss: 0.8418 (0.8415) time: 0.1218 data: 0.0370 max mem: 9390 +Train: [15] [1500/6250] eta: 0:11:17 lr: 0.000121 grad: 0.0657 (0.0652) loss: 0.8470 (0.8415) time: 0.1347 data: 0.0580 max mem: 9390 +Train: [15] [1600/6250] eta: 0:10:59 lr: 0.000121 grad: 0.0650 (0.0654) loss: 0.8432 (0.8415) time: 0.1181 data: 0.0372 max mem: 9390 +Train: [15] [1700/6250] eta: 0:10:43 lr: 0.000121 grad: 0.0629 (0.0654) loss: 0.8366 (0.8415) time: 0.1419 data: 0.0629 max mem: 9390 +Train: [15] [1800/6250] eta: 0:10:26 lr: 0.000121 grad: 0.0637 (0.0654) loss: 0.8452 (0.8415) time: 0.1207 data: 0.0354 max mem: 9390 +Train: [15] [1900/6250] eta: 0:10:11 lr: 0.000121 grad: 0.0655 (0.0655) loss: 0.8395 (0.8414) time: 0.1258 data: 0.0490 max mem: 9390 +Train: [15] [2000/6250] eta: 0:09:56 lr: 0.000121 grad: 0.0675 (0.0655) loss: 0.8428 (0.8414) time: 0.1327 data: 0.0555 max mem: 9390 +Train: [15] [2100/6250] eta: 0:09:42 lr: 0.000121 grad: 0.0662 (0.0655) loss: 0.8411 (0.8413) time: 0.1383 data: 0.0551 max mem: 9390 +Train: [15] [2200/6250] eta: 0:09:26 lr: 0.000121 grad: 0.0614 (0.0655) loss: 0.8392 (0.8414) time: 0.1093 data: 0.0261 max mem: 9390 +Train: [15] [2300/6250] eta: 0:09:11 lr: 0.000121 grad: 0.0638 (0.0656) loss: 0.8367 (0.8413) time: 0.1078 data: 0.0282 max mem: 9390 +Train: [15] [2400/6250] eta: 0:08:56 lr: 0.000121 grad: 0.0650 (0.0657) loss: 0.8390 (0.8412) time: 0.1396 data: 0.0591 max mem: 9390 +Train: [15] [2500/6250] eta: 0:08:40 lr: 0.000121 grad: 0.0676 (0.0657) loss: 0.8343 (0.8410) time: 0.1186 data: 0.0334 max mem: 9390 +Train: [15] [2600/6250] eta: 0:08:26 lr: 0.000121 grad: 0.0662 (0.0658) loss: 0.8371 (0.8410) time: 0.1232 data: 0.0414 max mem: 9390 +Train: [15] [2700/6250] eta: 0:08:12 lr: 0.000121 grad: 0.0630 (0.0659) loss: 0.8350 (0.8408) time: 0.1302 data: 0.0526 max mem: 9390 +Train: [15] [2800/6250] eta: 0:07:58 lr: 0.000121 grad: 0.0669 (0.0660) loss: 0.8391 (0.8407) time: 0.1350 data: 0.0488 max mem: 9390 +Train: [15] [2900/6250] eta: 0:07:43 lr: 0.000121 grad: 0.0644 (0.0660) loss: 0.8385 (0.8406) time: 0.1486 data: 0.0654 max mem: 9390 +Train: [15] [3000/6250] eta: 0:07:28 lr: 0.000121 grad: 0.0656 (0.0660) loss: 0.8374 (0.8405) time: 0.1318 data: 0.0506 max mem: 9390 +Train: [15] [3100/6250] eta: 0:07:14 lr: 0.000121 grad: 0.0634 (0.0660) loss: 0.8414 (0.8405) time: 0.1199 data: 0.0403 max mem: 9390 +Train: [15] [3200/6250] eta: 0:07:00 lr: 0.000121 grad: 0.0614 (0.0660) loss: 0.8422 (0.8405) time: 0.1475 data: 0.0688 max mem: 9390 +Train: [15] [3300/6250] eta: 0:06:46 lr: 0.000121 grad: 0.0682 (0.0660) loss: 0.8341 (0.8405) time: 0.1466 data: 0.0713 max mem: 9390 +Train: [15] [3400/6250] eta: 0:06:32 lr: 0.000121 grad: 0.0617 (0.0660) loss: 0.8401 (0.8404) time: 0.1103 data: 0.0283 max mem: 9390 +Train: [15] [3500/6250] eta: 0:06:18 lr: 0.000121 grad: 0.0675 (0.0660) loss: 0.8311 (0.8404) time: 0.1362 data: 0.0578 max mem: 9390 +Train: [15] [3600/6250] eta: 0:06:04 lr: 0.000121 grad: 0.0651 (0.0660) loss: 0.8406 (0.8403) time: 0.1329 data: 0.0510 max mem: 9390 +Train: [15] [3700/6250] eta: 0:05:50 lr: 0.000121 grad: 0.0658 (0.0660) loss: 0.8363 (0.8403) time: 0.1542 data: 0.0786 max mem: 9390 +Train: [15] [3800/6250] eta: 0:05:36 lr: 0.000121 grad: 0.0642 (0.0660) loss: 0.8370 (0.8403) time: 0.1418 data: 0.0676 max mem: 9390 +Train: [15] [3900/6250] eta: 0:05:22 lr: 0.000121 grad: 0.0615 (0.0661) loss: 0.8420 (0.8403) time: 0.1152 data: 0.0351 max mem: 9390 +Train: [15] [4000/6250] eta: 0:05:09 lr: 0.000121 grad: 0.0645 (0.0661) loss: 0.8391 (0.8403) time: 0.1291 data: 0.0516 max mem: 9390 +Train: [15] [4100/6250] eta: 0:04:55 lr: 0.000121 grad: 0.0674 (0.0661) loss: 0.8331 (0.8402) time: 0.1353 data: 0.0565 max mem: 9390 +Train: [15] [4200/6250] eta: 0:04:41 lr: 0.000121 grad: 0.0611 (0.0661) loss: 0.8411 (0.8402) time: 0.1312 data: 0.0483 max mem: 9390 +Train: [15] [4300/6250] eta: 0:04:27 lr: 0.000121 grad: 0.0662 (0.0660) loss: 0.8385 (0.8402) time: 0.1375 data: 0.0599 max mem: 9390 +Train: [15] [4400/6250] eta: 0:04:13 lr: 0.000121 grad: 0.0633 (0.0660) loss: 0.8406 (0.8402) time: 0.1389 data: 0.0597 max mem: 9390 +Train: [15] [4500/6250] eta: 0:03:59 lr: 0.000121 grad: 0.0593 (0.0660) loss: 0.8434 (0.8402) time: 0.1321 data: 0.0479 max mem: 9390 +Train: [15] [4600/6250] eta: 0:03:46 lr: 0.000121 grad: 0.0629 (0.0660) loss: 0.8379 (0.8402) time: 0.1425 data: 0.0651 max mem: 9390 +Train: [15] [4700/6250] eta: 0:03:32 lr: 0.000121 grad: 0.0640 (0.0659) loss: 0.8388 (0.8402) time: 0.1553 data: 0.0781 max mem: 9390 +Train: [15] [4800/6250] eta: 0:03:18 lr: 0.000121 grad: 0.0621 (0.0659) loss: 0.8399 (0.8402) time: 0.1589 data: 0.0797 max mem: 9390 +Train: [15] [4900/6250] eta: 0:03:05 lr: 0.000121 grad: 0.0601 (0.0659) loss: 0.8413 (0.8402) time: 0.1391 data: 0.0628 max mem: 9390 +Train: [15] [5000/6250] eta: 0:02:51 lr: 0.000121 grad: 0.0616 (0.0659) loss: 0.8408 (0.8403) time: 0.1450 data: 0.0663 max mem: 9390 +Train: [15] [5100/6250] eta: 0:02:37 lr: 0.000121 grad: 0.0599 (0.0658) loss: 0.8434 (0.8403) time: 0.1375 data: 0.0613 max mem: 9390 +Train: [15] [5200/6250] eta: 0:02:24 lr: 0.000121 grad: 0.0640 (0.0658) loss: 0.8386 (0.8403) time: 0.1266 data: 0.0438 max mem: 9390 +Train: [15] [5300/6250] eta: 0:02:10 lr: 0.000121 grad: 0.0660 (0.0657) loss: 0.8394 (0.8404) time: 0.1657 data: 0.0915 max mem: 9390 +Train: [15] [5400/6250] eta: 0:01:56 lr: 0.000121 grad: 0.0633 (0.0657) loss: 0.8348 (0.8404) time: 0.1233 data: 0.0373 max mem: 9390 +Train: [15] [5500/6250] eta: 0:01:42 lr: 0.000121 grad: 0.0613 (0.0657) loss: 0.8440 (0.8404) time: 0.1268 data: 0.0467 max mem: 9390 +Train: [15] [5600/6250] eta: 0:01:29 lr: 0.000121 grad: 0.0602 (0.0657) loss: 0.8460 (0.8404) time: 0.1278 data: 0.0434 max mem: 9390 +Train: [15] [5700/6250] eta: 0:01:15 lr: 0.000121 grad: 0.0616 (0.0656) loss: 0.8425 (0.8404) time: 0.1482 data: 0.0694 max mem: 9390 +Train: [15] [5800/6250] eta: 0:01:01 lr: 0.000121 grad: 0.0615 (0.0656) loss: 0.8380 (0.8404) time: 0.1457 data: 0.0671 max mem: 9390 +Train: [15] [5900/6250] eta: 0:00:48 lr: 0.000121 grad: 0.0615 (0.0656) loss: 0.8428 (0.8404) time: 0.1440 data: 0.0659 max mem: 9390 +Train: [15] [6000/6250] eta: 0:00:34 lr: 0.000121 grad: 0.0620 (0.0656) loss: 0.8385 (0.8404) time: 0.1378 data: 0.0577 max mem: 9390 +Train: [15] [6100/6250] eta: 0:00:20 lr: 0.000121 grad: 0.0588 (0.0655) loss: 0.8395 (0.8404) time: 0.1626 data: 0.0752 max mem: 9390 +Train: [15] [6200/6250] eta: 0:00:06 lr: 0.000121 grad: 0.0606 (0.0655) loss: 0.8439 (0.8405) time: 0.1556 data: 0.0769 max mem: 9390 +Train: [15] [6249/6250] eta: 0:00:00 lr: 0.000121 grad: 0.0626 (0.0655) loss: 0.8467 (0.8405) time: 0.1531 data: 0.0736 max mem: 9390 +Train: [15] Total time: 0:14:25 (0.1386 s / it) +Averaged stats: lr: 0.000121 grad: 0.0626 (0.0655) loss: 0.8467 (0.8405) +Eval (hcp-train-subset): [15] [ 0/62] eta: 0:03:42 loss: 0.8559 (0.8559) time: 3.5919 data: 3.5285 max mem: 9390 +Eval (hcp-train-subset): [15] [61/62] eta: 0:00:00 loss: 0.8472 (0.8478) time: 0.1043 data: 0.0779 max mem: 9390 +Eval (hcp-train-subset): [15] Total time: 0:00:12 (0.1942 s / it) +Averaged stats (hcp-train-subset): loss: 0.8472 (0.8478) +Eval (hcp-val): [15] [ 0/62] eta: 0:04:06 loss: 0.8370 (0.8370) time: 3.9784 data: 3.9484 max mem: 9390 +Eval (hcp-val): [15] [61/62] eta: 0:00:00 loss: 0.8405 (0.8430) time: 0.1133 data: 0.0862 max mem: 9390 +Eval (hcp-val): [15] Total time: 0:00:11 (0.1822 s / it) +Averaged stats (hcp-val): loss: 0.8405 (0.8430) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +Train: [16] [ 0/6250] eta: 9:35:54 lr: 0.000121 grad: 0.0889 (0.0889) loss: 0.8057 (0.8057) time: 5.5287 data: 5.4333 max mem: 9390 +Train: [16] [ 100/6250] eta: 0:18:33 lr: 0.000121 grad: 0.0606 (0.0709) loss: 0.8502 (0.8437) time: 0.1377 data: 0.0580 max mem: 9390 +Train: [16] [ 200/6250] eta: 0:15:53 lr: 0.000121 grad: 0.0593 (0.0671) loss: 0.8442 (0.8440) time: 0.1268 data: 0.0489 max mem: 9390 +Train: [16] [ 300/6250] eta: 0:14:47 lr: 0.000121 grad: 0.0657 (0.0662) loss: 0.8376 (0.8430) time: 0.1229 data: 0.0401 max mem: 9390 +Train: [16] [ 400/6250] eta: 0:14:08 lr: 0.000121 grad: 0.0604 (0.0662) loss: 0.8479 (0.8430) time: 0.1523 data: 0.0657 max mem: 9390 +Train: [16] [ 500/6250] eta: 0:13:56 lr: 0.000121 grad: 0.0642 (0.0660) loss: 0.8377 (0.8432) time: 0.1359 data: 0.0529 max mem: 9390 +Train: [16] [ 600/6250] eta: 0:13:34 lr: 0.000121 grad: 0.0604 (0.0659) loss: 0.8487 (0.8430) time: 0.1510 data: 0.0676 max mem: 9390 +Train: [16] [ 700/6250] eta: 0:13:18 lr: 0.000121 grad: 0.0609 (0.0655) loss: 0.8382 (0.8429) time: 0.1311 data: 0.0458 max mem: 9390 +Train: [16] [ 800/6250] eta: 0:13:08 lr: 0.000121 grad: 0.0649 (0.0656) loss: 0.8377 (0.8425) time: 0.1437 data: 0.0626 max mem: 9390 +Train: [16] [ 900/6250] eta: 0:12:54 lr: 0.000121 grad: 0.0699 (0.0662) loss: 0.8409 (0.8421) time: 0.1606 data: 0.0819 max mem: 9390 +Train: [16] [1000/6250] eta: 0:12:35 lr: 0.000121 grad: 0.0645 (0.0661) loss: 0.8355 (0.8419) time: 0.1179 data: 0.0390 max mem: 9390 +Train: [16] [1100/6250] eta: 0:12:15 lr: 0.000121 grad: 0.0652 (0.0659) loss: 0.8373 (0.8416) time: 0.1318 data: 0.0519 max mem: 9390 +Train: [16] [1200/6250] eta: 0:11:56 lr: 0.000121 grad: 0.0647 (0.0659) loss: 0.8404 (0.8414) time: 0.1428 data: 0.0616 max mem: 9390 +Train: [16] [1300/6250] eta: 0:11:40 lr: 0.000121 grad: 0.0657 (0.0658) loss: 0.8450 (0.8413) time: 0.1408 data: 0.0625 max mem: 9390 +Train: [16] [1400/6250] eta: 0:11:25 lr: 0.000121 grad: 0.0633 (0.0658) loss: 0.8388 (0.8413) time: 0.1223 data: 0.0413 max mem: 9390 +Train: [16] [1500/6250] eta: 0:11:10 lr: 0.000121 grad: 0.0651 (0.0657) loss: 0.8382 (0.8412) time: 0.1525 data: 0.0711 max mem: 9390 +Train: [16] [1600/6250] eta: 0:10:53 lr: 0.000121 grad: 0.0644 (0.0657) loss: 0.8412 (0.8411) time: 0.1278 data: 0.0481 max mem: 9390 +Train: [16] [1700/6250] eta: 0:10:38 lr: 0.000121 grad: 0.0630 (0.0657) loss: 0.8414 (0.8412) time: 0.1454 data: 0.0640 max mem: 9390 +Train: [16] [1800/6250] eta: 0:10:22 lr: 0.000121 grad: 0.0643 (0.0656) loss: 0.8341 (0.8411) time: 0.1177 data: 0.0384 max mem: 9390 +Train: [16] [1900/6250] eta: 0:10:08 lr: 0.000121 grad: 0.0654 (0.0655) loss: 0.8405 (0.8411) time: 0.1403 data: 0.0580 max mem: 9390 +Train: [16] [2000/6250] eta: 0:09:52 lr: 0.000121 grad: 0.0636 (0.0654) loss: 0.8437 (0.8411) time: 0.1355 data: 0.0545 max mem: 9390 +Train: [16] [2100/6250] eta: 0:09:39 lr: 0.000121 grad: 0.0646 (0.0654) loss: 0.8380 (0.8410) time: 0.1383 data: 0.0576 max mem: 9390 +Train: [16] [2200/6250] eta: 0:09:24 lr: 0.000121 grad: 0.0630 (0.0654) loss: 0.8408 (0.8409) time: 0.1283 data: 0.0522 max mem: 9390 +Train: [16] [2300/6250] eta: 0:09:09 lr: 0.000121 grad: 0.0615 (0.0653) loss: 0.8399 (0.8409) time: 0.1420 data: 0.0606 max mem: 9390 +Train: [16] [2400/6250] eta: 0:08:54 lr: 0.000121 grad: 0.0659 (0.0653) loss: 0.8391 (0.8409) time: 0.1345 data: 0.0521 max mem: 9390 +Train: [16] [2500/6250] eta: 0:08:41 lr: 0.000121 grad: 0.0637 (0.0653) loss: 0.8479 (0.8408) time: 0.1671 data: 0.0915 max mem: 9390 +Train: [16] [2600/6250] eta: 0:08:26 lr: 0.000121 grad: 0.0650 (0.0653) loss: 0.8385 (0.8408) time: 0.1244 data: 0.0377 max mem: 9390 +Train: [16] [2700/6250] eta: 0:08:11 lr: 0.000121 grad: 0.0625 (0.0652) loss: 0.8399 (0.8408) time: 0.1280 data: 0.0488 max mem: 9390 +Train: [16] [2800/6250] eta: 0:07:56 lr: 0.000121 grad: 0.0626 (0.0652) loss: 0.8409 (0.8408) time: 0.1170 data: 0.0418 max mem: 9390 +Train: [16] [2900/6250] eta: 0:07:42 lr: 0.000121 grad: 0.0604 (0.0652) loss: 0.8458 (0.8409) time: 0.1363 data: 0.0580 max mem: 9390 +Train: [16] [3000/6250] eta: 0:07:28 lr: 0.000121 grad: 0.0646 (0.0651) loss: 0.8367 (0.8409) time: 0.1340 data: 0.0545 max mem: 9390 +Train: [16] [3100/6250] eta: 0:07:13 lr: 0.000121 grad: 0.0601 (0.0650) loss: 0.8397 (0.8409) time: 0.1384 data: 0.0608 max mem: 9390 +Train: [16] [3200/6250] eta: 0:06:59 lr: 0.000121 grad: 0.0637 (0.0650) loss: 0.8412 (0.8409) time: 0.1341 data: 0.0542 max mem: 9390 +Train: [16] [3300/6250] eta: 0:06:45 lr: 0.000121 grad: 0.0677 (0.0650) loss: 0.8422 (0.8409) time: 0.1174 data: 0.0370 max mem: 9390 +Train: [16] [3400/6250] eta: 0:06:31 lr: 0.000121 grad: 0.0673 (0.0650) loss: 0.8406 (0.8409) time: 0.1324 data: 0.0504 max mem: 9390 +Train: [16] [3500/6250] eta: 0:06:17 lr: 0.000120 grad: 0.0632 (0.0651) loss: 0.8400 (0.8409) time: 0.1463 data: 0.0680 max mem: 9390 +Train: [16] [3600/6250] eta: 0:06:03 lr: 0.000120 grad: 0.0635 (0.0651) loss: 0.8355 (0.8409) time: 0.1388 data: 0.0621 max mem: 9390 +Train: [16] [3700/6250] eta: 0:05:49 lr: 0.000120 grad: 0.0667 (0.0650) loss: 0.8389 (0.8409) time: 0.1330 data: 0.0528 max mem: 9390 +Train: [16] [3800/6250] eta: 0:05:35 lr: 0.000120 grad: 0.0606 (0.0650) loss: 0.8467 (0.8409) time: 0.1421 data: 0.0601 max mem: 9390 +Train: [16] [3900/6250] eta: 0:05:21 lr: 0.000120 grad: 0.0607 (0.0650) loss: 0.8417 (0.8409) time: 0.1433 data: 0.0601 max mem: 9390 +Train: [16] [4000/6250] eta: 0:05:07 lr: 0.000120 grad: 0.0612 (0.0651) loss: 0.8416 (0.8409) time: 0.1321 data: 0.0545 max mem: 9390 +Train: [16] [4100/6250] eta: 0:04:53 lr: 0.000120 grad: 0.0633 (0.0651) loss: 0.8449 (0.8410) time: 0.1427 data: 0.0679 max mem: 9390 +Train: [16] [4200/6250] eta: 0:04:39 lr: 0.000120 grad: 0.0620 (0.0651) loss: 0.8436 (0.8410) time: 0.1433 data: 0.0594 max mem: 9390 +Train: [16] [4300/6250] eta: 0:04:26 lr: 0.000120 grad: 0.0607 (0.0651) loss: 0.8438 (0.8410) time: 0.1381 data: 0.0632 max mem: 9390 +Train: [16] [4400/6250] eta: 0:04:12 lr: 0.000120 grad: 0.0613 (0.0651) loss: 0.8416 (0.8411) time: 0.1907 data: 0.1165 max mem: 9390 +Train: [16] [4500/6250] eta: 0:03:58 lr: 0.000120 grad: 0.0614 (0.0650) loss: 0.8459 (0.8412) time: 0.1215 data: 0.0430 max mem: 9390 +Train: [16] [4600/6250] eta: 0:03:44 lr: 0.000120 grad: 0.0652 (0.0650) loss: 0.8412 (0.8412) time: 0.1273 data: 0.0441 max mem: 9390 +Train: [16] [4700/6250] eta: 0:03:30 lr: 0.000120 grad: 0.0640 (0.0650) loss: 0.8400 (0.8413) time: 0.1206 data: 0.0415 max mem: 9390 +Train: [16] [4800/6250] eta: 0:03:17 lr: 0.000120 grad: 0.0634 (0.0650) loss: 0.8404 (0.8413) time: 0.1384 data: 0.0555 max mem: 9390 +Train: [16] [4900/6250] eta: 0:03:03 lr: 0.000120 grad: 0.0613 (0.0650) loss: 0.8466 (0.8413) time: 0.1439 data: 0.0687 max mem: 9390 +Train: [16] [5000/6250] eta: 0:02:50 lr: 0.000120 grad: 0.0612 (0.0650) loss: 0.8447 (0.8414) time: 0.1443 data: 0.0636 max mem: 9390 +Train: [16] [5100/6250] eta: 0:02:36 lr: 0.000120 grad: 0.0621 (0.0649) loss: 0.8423 (0.8414) time: 0.1484 data: 0.0673 max mem: 9390 +Train: [16] [5200/6250] eta: 0:02:22 lr: 0.000120 grad: 0.0598 (0.0649) loss: 0.8458 (0.8414) time: 0.1410 data: 0.0595 max mem: 9390 +Train: [16] [5300/6250] eta: 0:02:09 lr: 0.000120 grad: 0.0676 (0.0649) loss: 0.8339 (0.8414) time: 0.1470 data: 0.0734 max mem: 9390 +Train: [16] [5400/6250] eta: 0:01:55 lr: 0.000120 grad: 0.0636 (0.0649) loss: 0.8402 (0.8413) time: 0.1341 data: 0.0541 max mem: 9390 +Train: [16] [5500/6250] eta: 0:01:41 lr: 0.000120 grad: 0.0598 (0.0649) loss: 0.8340 (0.8413) time: 0.1222 data: 0.0442 max mem: 9390 +Train: [16] [5600/6250] eta: 0:01:28 lr: 0.000120 grad: 0.0606 (0.0649) loss: 0.8418 (0.8413) time: 0.1378 data: 0.0573 max mem: 9390 +Train: [16] [5700/6250] eta: 0:01:14 lr: 0.000120 grad: 0.0610 (0.0650) loss: 0.8416 (0.8412) time: 0.1377 data: 0.0591 max mem: 9390 +Train: [16] [5800/6250] eta: 0:01:01 lr: 0.000120 grad: 0.0636 (0.0650) loss: 0.8383 (0.8411) time: 0.1267 data: 0.0481 max mem: 9390 +Train: [16] [5900/6250] eta: 0:00:47 lr: 0.000120 grad: 0.0584 (0.0651) loss: 0.8357 (0.8410) time: 0.1320 data: 0.0541 max mem: 9390 +Train: [16] [6000/6250] eta: 0:00:34 lr: 0.000120 grad: 0.0661 (0.0651) loss: 0.8385 (0.8410) time: 0.1541 data: 0.0690 max mem: 9390 +Train: [16] [6100/6250] eta: 0:00:20 lr: 0.000120 grad: 0.0621 (0.0651) loss: 0.8404 (0.8409) time: 0.1514 data: 0.0795 max mem: 9390 +Train: [16] [6200/6250] eta: 0:00:06 lr: 0.000120 grad: 0.0607 (0.0651) loss: 0.8409 (0.8408) time: 0.1533 data: 0.0727 max mem: 9390 +Train: [16] [6249/6250] eta: 0:00:00 lr: 0.000120 grad: 0.0630 (0.0651) loss: 0.8399 (0.8408) time: 0.1288 data: 0.0487 max mem: 9390 +Train: [16] Total time: 0:14:17 (0.1373 s / it) +Averaged stats: lr: 0.000120 grad: 0.0630 (0.0651) loss: 0.8399 (0.8408) +Eval (hcp-train-subset): [16] [ 0/62] eta: 0:02:59 loss: 0.8625 (0.8625) time: 2.8942 data: 2.8430 max mem: 9390 +Eval (hcp-train-subset): [16] [61/62] eta: 0:00:00 loss: 0.8476 (0.8484) time: 0.1200 data: 0.0937 max mem: 9390 +Eval (hcp-train-subset): [16] Total time: 0:00:11 (0.1847 s / it) +Averaged stats (hcp-train-subset): loss: 0.8476 (0.8484) +Eval (hcp-val): [16] [ 0/62] eta: 0:02:58 loss: 0.8404 (0.8404) time: 2.8785 data: 2.8062 max mem: 9390 +Eval (hcp-val): [16] [61/62] eta: 0:00:00 loss: 0.8422 (0.8439) time: 0.1099 data: 0.0837 max mem: 9390 +Eval (hcp-val): [16] Total time: 0:00:11 (0.1811 s / it) +Averaged stats (hcp-val): loss: 0.8422 (0.8439) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +Train: [17] [ 0/6250] eta: 8:08:13 lr: 0.000120 grad: 0.0771 (0.0771) loss: 0.8646 (0.8646) time: 4.6869 data: 4.5606 max mem: 9390 +Train: [17] [ 100/6250] eta: 0:18:41 lr: 0.000120 grad: 0.0671 (0.0746) loss: 0.8503 (0.8494) time: 0.1506 data: 0.0679 max mem: 9390 +Train: [17] [ 200/6250] eta: 0:16:00 lr: 0.000120 grad: 0.0673 (0.0731) loss: 0.8359 (0.8437) time: 0.1146 data: 0.0345 max mem: 9390 +Train: [17] [ 300/6250] eta: 0:15:05 lr: 0.000120 grad: 0.0649 (0.0718) loss: 0.8392 (0.8413) time: 0.1489 data: 0.0659 max mem: 9390 +Train: [17] [ 400/6250] eta: 0:14:48 lr: 0.000120 grad: 0.0700 (0.0710) loss: 0.8405 (0.8406) time: 0.1454 data: 0.0562 max mem: 9390 +Train: [17] [ 500/6250] eta: 0:14:27 lr: 0.000120 grad: 0.0656 (0.0700) loss: 0.8442 (0.8402) time: 0.1200 data: 0.0356 max mem: 9390 +Train: [17] [ 600/6250] eta: 0:14:03 lr: 0.000120 grad: 0.0652 (0.0695) loss: 0.8362 (0.8403) time: 0.1177 data: 0.0381 max mem: 9390 +Train: [17] [ 700/6250] eta: 0:13:43 lr: 0.000120 grad: 0.0625 (0.0690) loss: 0.8408 (0.8401) time: 0.1502 data: 0.0696 max mem: 9390 +Train: [17] [ 800/6250] eta: 0:13:26 lr: 0.000120 grad: 0.0584 (0.0682) loss: 0.8391 (0.8402) time: 0.1515 data: 0.0704 max mem: 9390 +Train: [17] [ 900/6250] eta: 0:13:15 lr: 0.000120 grad: 0.0642 (0.0679) loss: 0.8388 (0.8401) time: 0.1627 data: 0.0792 max mem: 9390 +Train: [17] [1000/6250] eta: 0:12:53 lr: 0.000120 grad: 0.0625 (0.0676) loss: 0.8427 (0.8403) time: 0.1280 data: 0.0494 max mem: 9390 +Train: [17] [1100/6250] eta: 0:12:32 lr: 0.000120 grad: 0.0595 (0.0673) loss: 0.8386 (0.8403) time: 0.1393 data: 0.0644 max mem: 9390 +Train: [17] [1200/6250] eta: 0:12:16 lr: 0.000120 grad: 0.0622 (0.0671) loss: 0.8367 (0.8401) time: 0.1350 data: 0.0548 max mem: 9390 +Train: [17] [1300/6250] eta: 0:11:58 lr: 0.000120 grad: 0.0613 (0.0670) loss: 0.8380 (0.8401) time: 0.1244 data: 0.0475 max mem: 9390 +Train: [17] [1400/6250] eta: 0:11:40 lr: 0.000120 grad: 0.0598 (0.0669) loss: 0.8386 (0.8400) time: 0.1329 data: 0.0552 max mem: 9390 +Train: [17] [1500/6250] eta: 0:11:24 lr: 0.000120 grad: 0.0658 (0.0667) loss: 0.8423 (0.8399) time: 0.1405 data: 0.0631 max mem: 9390 +Train: [17] [1600/6250] eta: 0:11:07 lr: 0.000120 grad: 0.0615 (0.0666) loss: 0.8441 (0.8398) time: 0.1276 data: 0.0510 max mem: 9390 +Train: [17] [1700/6250] eta: 0:10:49 lr: 0.000120 grad: 0.0644 (0.0664) loss: 0.8377 (0.8398) time: 0.1259 data: 0.0463 max mem: 9390 +Train: [17] [1800/6250] eta: 0:10:33 lr: 0.000120 grad: 0.0603 (0.0663) loss: 0.8400 (0.8397) time: 0.1205 data: 0.0391 max mem: 9390 +Train: [17] [1900/6250] eta: 0:10:18 lr: 0.000120 grad: 0.0621 (0.0661) loss: 0.8425 (0.8398) time: 0.1346 data: 0.0557 max mem: 9390 +Train: [17] [2000/6250] eta: 0:10:02 lr: 0.000120 grad: 0.0633 (0.0659) loss: 0.8405 (0.8399) time: 0.1323 data: 0.0537 max mem: 9390 +Train: [17] [2100/6250] eta: 0:09:46 lr: 0.000120 grad: 0.0649 (0.0658) loss: 0.8395 (0.8399) time: 0.1214 data: 0.0405 max mem: 9390 +Train: [17] [2200/6250] eta: 0:09:30 lr: 0.000120 grad: 0.0614 (0.0657) loss: 0.8398 (0.8399) time: 0.1279 data: 0.0483 max mem: 9390 +Train: [17] [2300/6250] eta: 0:09:14 lr: 0.000120 grad: 0.0609 (0.0656) loss: 0.8314 (0.8399) time: 0.1134 data: 0.0278 max mem: 9390 +Train: [17] [2400/6250] eta: 0:09:00 lr: 0.000120 grad: 0.0629 (0.0656) loss: 0.8385 (0.8399) time: 0.1689 data: 0.0941 max mem: 9390 +Train: [17] [2500/6250] eta: 0:08:44 lr: 0.000120 grad: 0.0649 (0.0655) loss: 0.8373 (0.8398) time: 0.1257 data: 0.0412 max mem: 9390 +Train: [17] [2600/6250] eta: 0:08:30 lr: 0.000120 grad: 0.0622 (0.0654) loss: 0.8386 (0.8398) time: 0.1331 data: 0.0537 max mem: 9390 +Train: [17] [2700/6250] eta: 0:08:15 lr: 0.000120 grad: 0.0618 (0.0655) loss: 0.8398 (0.8397) time: 0.1327 data: 0.0578 max mem: 9390 +Train: [17] [2800/6250] eta: 0:08:01 lr: 0.000120 grad: 0.0618 (0.0655) loss: 0.8431 (0.8396) time: 0.1332 data: 0.0568 max mem: 9390 +Train: [17] [2900/6250] eta: 0:07:46 lr: 0.000120 grad: 0.0624 (0.0655) loss: 0.8382 (0.8395) time: 0.1436 data: 0.0592 max mem: 9390 +Train: [17] [3000/6250] eta: 0:07:32 lr: 0.000120 grad: 0.0710 (0.0657) loss: 0.8333 (0.8394) time: 0.1231 data: 0.0464 max mem: 9390 +Train: [17] [3100/6250] eta: 0:07:17 lr: 0.000120 grad: 0.0634 (0.0657) loss: 0.8390 (0.8393) time: 0.1394 data: 0.0620 max mem: 9390 +Train: [17] [3200/6250] eta: 0:07:02 lr: 0.000120 grad: 0.0648 (0.0657) loss: 0.8437 (0.8392) time: 0.1241 data: 0.0442 max mem: 9390 +Train: [17] [3300/6250] eta: 0:06:48 lr: 0.000120 grad: 0.0636 (0.0658) loss: 0.8358 (0.8391) time: 0.1367 data: 0.0564 max mem: 9390 +Train: [17] [3400/6250] eta: 0:06:33 lr: 0.000120 grad: 0.0646 (0.0658) loss: 0.8293 (0.8390) time: 0.1243 data: 0.0438 max mem: 9390 +Train: [17] [3500/6250] eta: 0:06:18 lr: 0.000120 grad: 0.0627 (0.0658) loss: 0.8418 (0.8389) time: 0.1241 data: 0.0428 max mem: 9390 +Train: [17] [3600/6250] eta: 0:06:04 lr: 0.000120 grad: 0.0638 (0.0658) loss: 0.8374 (0.8389) time: 0.1381 data: 0.0569 max mem: 9390 +Train: [17] [3700/6250] eta: 0:05:50 lr: 0.000120 grad: 0.0671 (0.0659) loss: 0.8383 (0.8388) time: 0.1275 data: 0.0393 max mem: 9390 +Train: [17] [3800/6250] eta: 0:05:36 lr: 0.000120 grad: 0.0657 (0.0658) loss: 0.8388 (0.8388) time: 0.1304 data: 0.0562 max mem: 9390 +Train: [17] [3900/6250] eta: 0:05:21 lr: 0.000120 grad: 0.0646 (0.0658) loss: 0.8391 (0.8389) time: 0.1221 data: 0.0380 max mem: 9390 +Train: [17] [4000/6250] eta: 0:05:08 lr: 0.000120 grad: 0.0600 (0.0658) loss: 0.8429 (0.8389) time: 0.1328 data: 0.0550 max mem: 9390 +Train: [17] [4100/6250] eta: 0:04:54 lr: 0.000120 grad: 0.0638 (0.0657) loss: 0.8415 (0.8389) time: 0.1386 data: 0.0546 max mem: 9390 +Train: [17] [4200/6250] eta: 0:04:40 lr: 0.000120 grad: 0.0615 (0.0657) loss: 0.8391 (0.8390) time: 0.1408 data: 0.0663 max mem: 9390 +Train: [17] [4300/6250] eta: 0:04:26 lr: 0.000120 grad: 0.0629 (0.0657) loss: 0.8441 (0.8390) time: 0.1474 data: 0.0717 max mem: 9390 +Train: [17] [4400/6250] eta: 0:04:12 lr: 0.000120 grad: 0.0618 (0.0657) loss: 0.8387 (0.8390) time: 0.1486 data: 0.0662 max mem: 9390 +Train: [17] [4500/6250] eta: 0:03:58 lr: 0.000120 grad: 0.0623 (0.0656) loss: 0.8347 (0.8390) time: 0.1283 data: 0.0479 max mem: 9390 +Train: [17] [4600/6250] eta: 0:03:44 lr: 0.000120 grad: 0.0647 (0.0656) loss: 0.8365 (0.8390) time: 0.1213 data: 0.0400 max mem: 9390 +Train: [17] [4700/6250] eta: 0:03:31 lr: 0.000120 grad: 0.0602 (0.0656) loss: 0.8454 (0.8390) time: 0.1266 data: 0.0482 max mem: 9390 +Train: [17] [4800/6250] eta: 0:03:17 lr: 0.000120 grad: 0.0603 (0.0655) loss: 0.8428 (0.8391) time: 0.1503 data: 0.0742 max mem: 9390 +Train: [17] [4900/6250] eta: 0:03:04 lr: 0.000119 grad: 0.0620 (0.0655) loss: 0.8391 (0.8391) time: 0.1152 data: 0.0355 max mem: 9390 +Train: [17] [5000/6250] eta: 0:02:50 lr: 0.000119 grad: 0.0632 (0.0654) loss: 0.8391 (0.8391) time: 0.1273 data: 0.0463 max mem: 9390 +Train: [17] [5100/6250] eta: 0:02:36 lr: 0.000119 grad: 0.0622 (0.0654) loss: 0.8424 (0.8391) time: 0.1357 data: 0.0542 max mem: 9390 +Train: [17] [5200/6250] eta: 0:02:23 lr: 0.000119 grad: 0.0621 (0.0653) loss: 0.8384 (0.8391) time: 0.1409 data: 0.0606 max mem: 9390 +Train: [17] [5300/6250] eta: 0:02:09 lr: 0.000119 grad: 0.0624 (0.0653) loss: 0.8372 (0.8391) time: 0.1201 data: 0.0439 max mem: 9390 +Train: [17] [5400/6250] eta: 0:01:56 lr: 0.000119 grad: 0.0620 (0.0652) loss: 0.8415 (0.8391) time: 0.1425 data: 0.0654 max mem: 9390 +Train: [17] [5500/6250] eta: 0:01:42 lr: 0.000119 grad: 0.0603 (0.0652) loss: 0.8387 (0.8391) time: 0.1315 data: 0.0516 max mem: 9390 +Train: [17] [5600/6250] eta: 0:01:28 lr: 0.000119 grad: 0.0635 (0.0652) loss: 0.8355 (0.8391) time: 0.1383 data: 0.0598 max mem: 9390 +Train: [17] [5700/6250] eta: 0:01:14 lr: 0.000119 grad: 0.0673 (0.0652) loss: 0.8388 (0.8390) time: 0.1338 data: 0.0568 max mem: 9390 +Train: [17] [5800/6250] eta: 0:01:01 lr: 0.000119 grad: 0.0644 (0.0652) loss: 0.8311 (0.8390) time: 0.1307 data: 0.0494 max mem: 9390 +Train: [17] [5900/6250] eta: 0:00:47 lr: 0.000119 grad: 0.0644 (0.0652) loss: 0.8373 (0.8389) time: 0.1333 data: 0.0480 max mem: 9390 +Train: [17] [6000/6250] eta: 0:00:34 lr: 0.000119 grad: 0.0634 (0.0653) loss: 0.8384 (0.8389) time: 0.1589 data: 0.0796 max mem: 9390 +Train: [17] [6100/6250] eta: 0:00:20 lr: 0.000119 grad: 0.0641 (0.0652) loss: 0.8383 (0.8389) time: 0.1331 data: 0.0591 max mem: 9390 +Train: [17] [6200/6250] eta: 0:00:06 lr: 0.000119 grad: 0.0611 (0.0652) loss: 0.8376 (0.8388) time: 0.1629 data: 0.0897 max mem: 9390 +Train: [17] [6249/6250] eta: 0:00:00 lr: 0.000119 grad: 0.0707 (0.0652) loss: 0.8365 (0.8388) time: 0.1105 data: 0.0268 max mem: 9390 +Train: [17] Total time: 0:14:23 (0.1381 s / it) +Averaged stats: lr: 0.000119 grad: 0.0707 (0.0652) loss: 0.8365 (0.8388) +Eval (hcp-train-subset): [17] [ 0/62] eta: 0:03:06 loss: 0.8572 (0.8572) time: 3.0120 data: 2.9470 max mem: 9390 +Eval (hcp-train-subset): [17] [61/62] eta: 0:00:00 loss: 0.8478 (0.8470) time: 0.1139 data: 0.0872 max mem: 9390 +Eval (hcp-train-subset): [17] Total time: 0:00:11 (0.1879 s / it) +Averaged stats (hcp-train-subset): loss: 0.8478 (0.8470) +Eval (hcp-val): [17] [ 0/62] eta: 0:04:38 loss: 0.8386 (0.8386) time: 4.4996 data: 4.4696 max mem: 9390 +Eval (hcp-val): [17] [61/62] eta: 0:00:00 loss: 0.8412 (0.8424) time: 0.1014 data: 0.0751 max mem: 9390 +Eval (hcp-val): [17] Total time: 0:00:11 (0.1823 s / it) +Averaged stats (hcp-val): loss: 0.8412 (0.8424) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +Train: [18] [ 0/6250] eta: 7:34:44 lr: 0.000119 grad: 0.1084 (0.1084) loss: 0.8523 (0.8523) time: 4.3655 data: 4.1001 max mem: 9390 +Train: [18] [ 100/6250] eta: 0:17:59 lr: 0.000119 grad: 0.0618 (0.0688) loss: 0.8429 (0.8439) time: 0.1334 data: 0.0531 max mem: 9390 +Train: [18] [ 200/6250] eta: 0:15:57 lr: 0.000119 grad: 0.0605 (0.0662) loss: 0.8385 (0.8432) time: 0.1412 data: 0.0548 max mem: 9390 +Train: [18] [ 300/6250] eta: 0:15:28 lr: 0.000119 grad: 0.0646 (0.0654) loss: 0.8367 (0.8411) time: 0.1387 data: 0.0457 max mem: 9390 +Train: [18] [ 400/6250] eta: 0:15:08 lr: 0.000119 grad: 0.0624 (0.0654) loss: 0.8352 (0.8401) time: 0.1349 data: 0.0380 max mem: 9390 +Train: [18] [ 500/6250] eta: 0:14:39 lr: 0.000119 grad: 0.0616 (0.0651) loss: 0.8372 (0.8399) time: 0.1316 data: 0.0447 max mem: 9390 +Train: [18] [ 600/6250] eta: 0:14:16 lr: 0.000119 grad: 0.0635 (0.0650) loss: 0.8377 (0.8397) time: 0.1413 data: 0.0596 max mem: 9390 +Train: [18] [ 700/6250] eta: 0:14:03 lr: 0.000119 grad: 0.0595 (0.0648) loss: 0.8435 (0.8395) time: 0.1436 data: 0.0587 max mem: 9390 +Train: [18] [ 800/6250] eta: 0:13:44 lr: 0.000119 grad: 0.0578 (0.0646) loss: 0.8455 (0.8395) time: 0.1701 data: 0.0919 max mem: 9390 +Train: [18] [ 900/6250] eta: 0:13:25 lr: 0.000119 grad: 0.0611 (0.0645) loss: 0.8385 (0.8397) time: 0.1267 data: 0.0494 max mem: 9390 +Train: [18] [1000/6250] eta: 0:13:06 lr: 0.000119 grad: 0.0596 (0.0641) loss: 0.8401 (0.8400) time: 0.1253 data: 0.0434 max mem: 9390 +Train: [18] [1100/6250] eta: 0:12:45 lr: 0.000119 grad: 0.0570 (0.0639) loss: 0.8424 (0.8401) time: 0.1358 data: 0.0514 max mem: 9390 +Train: [18] [1200/6250] eta: 0:12:25 lr: 0.000119 grad: 0.0604 (0.0638) loss: 0.8376 (0.8401) time: 0.1440 data: 0.0639 max mem: 9390 +Train: [18] [1300/6250] eta: 0:12:08 lr: 0.000119 grad: 0.0576 (0.0638) loss: 0.8439 (0.8400) time: 0.1422 data: 0.0620 max mem: 9390 +Train: [18] [1400/6250] eta: 0:11:51 lr: 0.000119 grad: 0.0624 (0.0637) loss: 0.8391 (0.8399) time: 0.1441 data: 0.0670 max mem: 9390 +Train: [18] [1500/6250] eta: 0:11:32 lr: 0.000119 grad: 0.0582 (0.0636) loss: 0.8434 (0.8399) time: 0.1368 data: 0.0495 max mem: 9390 +Train: [18] [1600/6250] eta: 0:11:13 lr: 0.000119 grad: 0.0602 (0.0636) loss: 0.8377 (0.8398) time: 0.1162 data: 0.0297 max mem: 9390 +Train: [18] [1700/6250] eta: 0:10:57 lr: 0.000119 grad: 0.0578 (0.0636) loss: 0.8406 (0.8397) time: 0.1352 data: 0.0528 max mem: 9390 +Train: [18] [1800/6250] eta: 0:10:41 lr: 0.000119 grad: 0.0643 (0.0636) loss: 0.8373 (0.8397) time: 0.1402 data: 0.0610 max mem: 9390 +Train: [18] [1900/6250] eta: 0:10:25 lr: 0.000119 grad: 0.0601 (0.0636) loss: 0.8399 (0.8397) time: 0.1324 data: 0.0520 max mem: 9390 +Train: [18] [2000/6250] eta: 0:10:10 lr: 0.000119 grad: 0.0594 (0.0636) loss: 0.8391 (0.8397) time: 0.1475 data: 0.0706 max mem: 9390 +Train: [18] [2100/6250] eta: 0:09:54 lr: 0.000119 grad: 0.0579 (0.0636) loss: 0.8416 (0.8397) time: 0.1327 data: 0.0507 max mem: 9390 +Train: [18] [2200/6250] eta: 0:09:38 lr: 0.000119 grad: 0.0644 (0.0636) loss: 0.8372 (0.8398) time: 0.1255 data: 0.0481 max mem: 9390 +Train: [18] [2300/6250] eta: 0:09:23 lr: 0.000119 grad: 0.0603 (0.0636) loss: 0.8399 (0.8397) time: 0.1375 data: 0.0616 max mem: 9390 +Train: [18] [2400/6250] eta: 0:09:07 lr: 0.000119 grad: 0.0645 (0.0636) loss: 0.8345 (0.8397) time: 0.1154 data: 0.0342 max mem: 9390 +Train: [18] [2500/6250] eta: 0:08:52 lr: 0.000119 grad: 0.0584 (0.0635) loss: 0.8458 (0.8398) time: 0.1498 data: 0.0709 max mem: 9390 +Train: [18] [2600/6250] eta: 0:08:38 lr: 0.000119 grad: 0.0586 (0.0635) loss: 0.8417 (0.8399) time: 0.1543 data: 0.0767 max mem: 9390 +Train: [18] [2700/6250] eta: 0:08:22 lr: 0.000119 grad: 0.0614 (0.0634) loss: 0.8405 (0.8400) time: 0.1249 data: 0.0408 max mem: 9390 +Train: [18] [2800/6250] eta: 0:08:07 lr: 0.000119 grad: 0.0599 (0.0634) loss: 0.8402 (0.8400) time: 0.1488 data: 0.0703 max mem: 9390 +Train: [18] [2900/6250] eta: 0:07:52 lr: 0.000119 grad: 0.0566 (0.0634) loss: 0.8382 (0.8400) time: 0.1322 data: 0.0534 max mem: 9390 +Train: [18] [3000/6250] eta: 0:07:37 lr: 0.000119 grad: 0.0596 (0.0633) loss: 0.8443 (0.8401) time: 0.1002 data: 0.0184 max mem: 9390 +Train: [18] [3100/6250] eta: 0:07:22 lr: 0.000119 grad: 0.0608 (0.0632) loss: 0.8431 (0.8402) time: 0.1462 data: 0.0678 max mem: 9390 +Train: [18] [3200/6250] eta: 0:07:07 lr: 0.000119 grad: 0.0622 (0.0632) loss: 0.8372 (0.8402) time: 0.1380 data: 0.0542 max mem: 9390 +Train: [18] [3300/6250] eta: 0:06:52 lr: 0.000119 grad: 0.0617 (0.0632) loss: 0.8365 (0.8401) time: 0.1433 data: 0.0662 max mem: 9390 +Train: [18] [3400/6250] eta: 0:06:38 lr: 0.000119 grad: 0.0635 (0.0631) loss: 0.8413 (0.8401) time: 0.1538 data: 0.0746 max mem: 9390 +Train: [18] [3500/6250] eta: 0:06:23 lr: 0.000119 grad: 0.0660 (0.0631) loss: 0.8382 (0.8401) time: 0.1267 data: 0.0443 max mem: 9390 +Train: [18] [3600/6250] eta: 0:06:09 lr: 0.000119 grad: 0.0595 (0.0632) loss: 0.8413 (0.8401) time: 0.1339 data: 0.0546 max mem: 9390 +Train: [18] [3700/6250] eta: 0:05:54 lr: 0.000119 grad: 0.0612 (0.0631) loss: 0.8366 (0.8401) time: 0.1329 data: 0.0546 max mem: 9390 +Train: [18] [3800/6250] eta: 0:05:40 lr: 0.000119 grad: 0.0627 (0.0631) loss: 0.8392 (0.8401) time: 0.1412 data: 0.0614 max mem: 9390 +Train: [18] [3900/6250] eta: 0:05:26 lr: 0.000119 grad: 0.0571 (0.0631) loss: 0.8411 (0.8401) time: 0.1413 data: 0.0603 max mem: 9390 +Train: [18] [4000/6250] eta: 0:05:11 lr: 0.000119 grad: 0.0635 (0.0631) loss: 0.8397 (0.8401) time: 0.1346 data: 0.0547 max mem: 9390 +Train: [18] [4100/6250] eta: 0:04:57 lr: 0.000119 grad: 0.0590 (0.0631) loss: 0.8360 (0.8401) time: 0.1213 data: 0.0426 max mem: 9390 +Train: [18] [4200/6250] eta: 0:04:44 lr: 0.000119 grad: 0.0629 (0.0631) loss: 0.8351 (0.8401) time: 0.1341 data: 0.0556 max mem: 9390 +Train: [18] [4300/6250] eta: 0:04:30 lr: 0.000119 grad: 0.0614 (0.0631) loss: 0.8413 (0.8400) time: 0.1094 data: 0.0262 max mem: 9390 +Train: [18] [4400/6250] eta: 0:04:16 lr: 0.000119 grad: 0.0618 (0.0631) loss: 0.8398 (0.8400) time: 0.1263 data: 0.0453 max mem: 9390 +Train: [18] [4500/6250] eta: 0:04:02 lr: 0.000119 grad: 0.0612 (0.0632) loss: 0.8345 (0.8399) time: 0.1613 data: 0.0820 max mem: 9390 +Train: [18] [4600/6250] eta: 0:03:48 lr: 0.000119 grad: 0.0651 (0.0632) loss: 0.8322 (0.8398) time: 0.1275 data: 0.0426 max mem: 9390 +Train: [18] [4700/6250] eta: 0:03:34 lr: 0.000119 grad: 0.0624 (0.0633) loss: 0.8346 (0.8397) time: 0.1400 data: 0.0627 max mem: 9390 +Train: [18] [4800/6250] eta: 0:03:20 lr: 0.000119 grad: 0.0660 (0.0633) loss: 0.8368 (0.8396) time: 0.1250 data: 0.0473 max mem: 9390 +Train: [18] [4900/6250] eta: 0:03:06 lr: 0.000119 grad: 0.0588 (0.0634) loss: 0.8419 (0.8396) time: 0.1260 data: 0.0511 max mem: 9390 +Train: [18] [5000/6250] eta: 0:02:52 lr: 0.000119 grad: 0.0632 (0.0635) loss: 0.8369 (0.8396) time: 0.1246 data: 0.0447 max mem: 9390 +Train: [18] [5100/6250] eta: 0:02:38 lr: 0.000119 grad: 0.0641 (0.0635) loss: 0.8419 (0.8395) time: 0.1393 data: 0.0572 max mem: 9390 +Train: [18] [5200/6250] eta: 0:02:24 lr: 0.000119 grad: 0.0645 (0.0636) loss: 0.8344 (0.8395) time: 0.1294 data: 0.0374 max mem: 9390 +Train: [18] [5300/6250] eta: 0:02:10 lr: 0.000119 grad: 0.0689 (0.0637) loss: 0.8328 (0.8393) time: 0.1381 data: 0.0608 max mem: 9390 +Train: [18] [5400/6250] eta: 0:01:57 lr: 0.000119 grad: 0.0662 (0.0637) loss: 0.8371 (0.8393) time: 0.1591 data: 0.0780 max mem: 9390 +Train: [18] [5500/6250] eta: 0:01:43 lr: 0.000119 grad: 0.0637 (0.0638) loss: 0.8410 (0.8393) time: 0.1180 data: 0.0303 max mem: 9390 +Train: [18] [5600/6250] eta: 0:01:29 lr: 0.000119 grad: 0.0659 (0.0639) loss: 0.8426 (0.8393) time: 0.1408 data: 0.0622 max mem: 9390 +Train: [18] [5700/6250] eta: 0:01:15 lr: 0.000119 grad: 0.0675 (0.0639) loss: 0.8380 (0.8392) time: 0.1265 data: 0.0453 max mem: 9390 +Train: [18] [5800/6250] eta: 0:01:01 lr: 0.000118 grad: 0.0685 (0.0640) loss: 0.8325 (0.8392) time: 0.1757 data: 0.0957 max mem: 9390 +Train: [18] [5900/6250] eta: 0:00:48 lr: 0.000118 grad: 0.0649 (0.0641) loss: 0.8412 (0.8392) time: 0.1586 data: 0.0748 max mem: 9390 +Train: [18] [6000/6250] eta: 0:00:34 lr: 0.000118 grad: 0.0641 (0.0641) loss: 0.8417 (0.8392) time: 0.1471 data: 0.0704 max mem: 9390 +Train: [18] [6100/6250] eta: 0:00:20 lr: 0.000118 grad: 0.0628 (0.0642) loss: 0.8365 (0.8392) time: 0.1421 data: 0.0641 max mem: 9390 +Train: [18] [6200/6250] eta: 0:00:06 lr: 0.000118 grad: 0.0633 (0.0643) loss: 0.8447 (0.8392) time: 0.1523 data: 0.0753 max mem: 9390 +Train: [18] [6249/6250] eta: 0:00:00 lr: 0.000118 grad: 0.0640 (0.0643) loss: 0.8396 (0.8392) time: 0.1345 data: 0.0514 max mem: 9390 +Train: [18] Total time: 0:14:27 (0.1388 s / it) +Averaged stats: lr: 0.000118 grad: 0.0640 (0.0643) loss: 0.8396 (0.8392) +Eval (hcp-train-subset): [18] [ 0/62] eta: 0:03:25 loss: 0.8594 (0.8594) time: 3.3071 data: 3.2341 max mem: 9390 +Eval (hcp-train-subset): [18] [61/62] eta: 0:00:00 loss: 0.8459 (0.8481) time: 0.1180 data: 0.0913 max mem: 9390 +Eval (hcp-train-subset): [18] Total time: 0:00:11 (0.1891 s / it) +Averaged stats (hcp-train-subset): loss: 0.8459 (0.8481) +Eval (hcp-val): [18] [ 0/62] eta: 0:03:21 loss: 0.8428 (0.8428) time: 3.2429 data: 3.1910 max mem: 9390 +Eval (hcp-val): [18] [61/62] eta: 0:00:00 loss: 0.8427 (0.8430) time: 0.1055 data: 0.0809 max mem: 9390 +Eval (hcp-val): [18] Total time: 0:00:10 (0.1770 s / it) +Averaged stats (hcp-val): loss: 0.8427 (0.8430) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +Train: [19] [ 0/6250] eta: 8:56:16 lr: 0.000118 grad: 0.0762 (0.0762) loss: 0.8536 (0.8536) time: 5.1482 data: 5.0271 max mem: 9390 +Train: [19] [ 100/6250] eta: 0:18:15 lr: 0.000118 grad: 0.0711 (0.0803) loss: 0.8244 (0.8335) time: 0.1321 data: 0.0434 max mem: 9390 +Train: [19] [ 200/6250] eta: 0:15:41 lr: 0.000118 grad: 0.0690 (0.0751) loss: 0.8331 (0.8327) time: 0.1070 data: 0.0171 max mem: 9390 +Train: [19] [ 300/6250] eta: 0:14:57 lr: 0.000118 grad: 0.0613 (0.0736) loss: 0.8343 (0.8342) time: 0.1305 data: 0.0522 max mem: 9390 +Train: [19] [ 400/6250] eta: 0:14:29 lr: 0.000118 grad: 0.0641 (0.0718) loss: 0.8401 (0.8354) time: 0.1181 data: 0.0263 max mem: 9390 +Train: [19] [ 500/6250] eta: 0:13:56 lr: 0.000118 grad: 0.0625 (0.0704) loss: 0.8383 (0.8359) time: 0.1330 data: 0.0418 max mem: 9390 +Train: [19] [ 600/6250] eta: 0:13:32 lr: 0.000118 grad: 0.0625 (0.0696) loss: 0.8376 (0.8362) time: 0.1180 data: 0.0331 max mem: 9390 +Train: [19] [ 700/6250] eta: 0:13:17 lr: 0.000118 grad: 0.0631 (0.0689) loss: 0.8393 (0.8365) time: 0.1704 data: 0.0869 max mem: 9390 +Train: [19] [ 800/6250] eta: 0:12:58 lr: 0.000118 grad: 0.0688 (0.0684) loss: 0.8348 (0.8368) time: 0.1363 data: 0.0541 max mem: 9390 +Train: [19] [ 900/6250] eta: 0:12:48 lr: 0.000118 grad: 0.0633 (0.0682) loss: 0.8379 (0.8369) time: 0.1627 data: 0.0826 max mem: 9390 +Train: [19] [1000/6250] eta: 0:12:30 lr: 0.000118 grad: 0.0641 (0.0679) loss: 0.8429 (0.8371) time: 0.1450 data: 0.0668 max mem: 9390 +Train: [19] [1100/6250] eta: 0:12:10 lr: 0.000118 grad: 0.0657 (0.0678) loss: 0.8367 (0.8371) time: 0.1322 data: 0.0499 max mem: 9390 +Train: [19] [1200/6250] eta: 0:11:54 lr: 0.000118 grad: 0.0673 (0.0677) loss: 0.8369 (0.8371) time: 0.1282 data: 0.0434 max mem: 9390 +Train: [19] [1300/6250] eta: 0:11:38 lr: 0.000118 grad: 0.0639 (0.0675) loss: 0.8378 (0.8373) time: 0.1485 data: 0.0705 max mem: 9390 +Train: [19] [1400/6250] eta: 0:11:21 lr: 0.000118 grad: 0.0594 (0.0673) loss: 0.8415 (0.8373) time: 0.1154 data: 0.0393 max mem: 9390 +Train: [19] [1500/6250] eta: 0:11:07 lr: 0.000118 grad: 0.0628 (0.0671) loss: 0.8393 (0.8374) time: 0.1378 data: 0.0555 max mem: 9390 +Train: [19] [1600/6250] eta: 0:10:51 lr: 0.000118 grad: 0.0599 (0.0668) loss: 0.8416 (0.8375) time: 0.1370 data: 0.0584 max mem: 9390 +Train: [19] [1700/6250] eta: 0:10:36 lr: 0.000118 grad: 0.0615 (0.0667) loss: 0.8427 (0.8376) time: 0.1559 data: 0.0775 max mem: 9390 +Train: [19] [1800/6250] eta: 0:10:19 lr: 0.000118 grad: 0.0613 (0.0665) loss: 0.8387 (0.8377) time: 0.1226 data: 0.0382 max mem: 9390 +Train: [19] [1900/6250] eta: 0:10:10 lr: 0.000118 grad: 0.0629 (0.0664) loss: 0.8403 (0.8379) time: 0.2161 data: 0.1367 max mem: 9390 +Train: [19] [2000/6250] eta: 0:09:53 lr: 0.000118 grad: 0.0613 (0.0663) loss: 0.8408 (0.8380) time: 0.1376 data: 0.0486 max mem: 9390 +Train: [19] [2100/6250] eta: 0:09:38 lr: 0.000118 grad: 0.0655 (0.0663) loss: 0.8397 (0.8380) time: 0.1305 data: 0.0498 max mem: 9390 +Train: [19] [2200/6250] eta: 0:09:24 lr: 0.000118 grad: 0.0596 (0.0662) loss: 0.8376 (0.8381) time: 0.1535 data: 0.0714 max mem: 9390 +Train: [19] [2300/6250] eta: 0:09:10 lr: 0.000118 grad: 0.0661 (0.0662) loss: 0.8403 (0.8382) time: 0.1070 data: 0.0192 max mem: 9390 +Train: [19] [2400/6250] eta: 0:08:56 lr: 0.000118 grad: 0.0658 (0.0661) loss: 0.8396 (0.8382) time: 0.1353 data: 0.0599 max mem: 9390 +Train: [19] [2500/6250] eta: 0:08:41 lr: 0.000118 grad: 0.0595 (0.0661) loss: 0.8378 (0.8381) time: 0.1302 data: 0.0471 max mem: 9390 +Train: [19] [2600/6250] eta: 0:08:26 lr: 0.000118 grad: 0.0674 (0.0661) loss: 0.8349 (0.8381) time: 0.1226 data: 0.0445 max mem: 9390 +Train: [19] [2700/6250] eta: 0:08:12 lr: 0.000118 grad: 0.0601 (0.0661) loss: 0.8433 (0.8381) time: 0.1333 data: 0.0557 max mem: 9390 +Train: [19] [2800/6250] eta: 0:07:58 lr: 0.000118 grad: 0.0652 (0.0661) loss: 0.8351 (0.8380) time: 0.1341 data: 0.0576 max mem: 9390 +Train: [19] [2900/6250] eta: 0:07:46 lr: 0.000118 grad: 0.0648 (0.0660) loss: 0.8342 (0.8379) time: 0.1338 data: 0.0549 max mem: 9390 +Train: [19] [3000/6250] eta: 0:07:31 lr: 0.000118 grad: 0.0634 (0.0661) loss: 0.8395 (0.8378) time: 0.1488 data: 0.0695 max mem: 9390 +Train: [19] [3100/6250] eta: 0:07:16 lr: 0.000118 grad: 0.0642 (0.0661) loss: 0.8368 (0.8377) time: 0.1260 data: 0.0442 max mem: 9390 +Train: [19] [3200/6250] eta: 0:07:02 lr: 0.000118 grad: 0.0667 (0.0661) loss: 0.8330 (0.8376) time: 0.1205 data: 0.0424 max mem: 9390 +Train: [19] [3300/6250] eta: 0:06:47 lr: 0.000118 grad: 0.0592 (0.0660) loss: 0.8388 (0.8376) time: 0.1372 data: 0.0551 max mem: 9390 +Train: [19] [3400/6250] eta: 0:06:33 lr: 0.000118 grad: 0.0649 (0.0661) loss: 0.8278 (0.8375) time: 0.1320 data: 0.0527 max mem: 9390 +Train: [19] [3500/6250] eta: 0:06:18 lr: 0.000118 grad: 0.0632 (0.0660) loss: 0.8414 (0.8376) time: 0.1313 data: 0.0501 max mem: 9390 +Train: [19] [3600/6250] eta: 0:06:04 lr: 0.000118 grad: 0.0628 (0.0660) loss: 0.8363 (0.8375) time: 0.1060 data: 0.0269 max mem: 9390 +Train: [19] [3700/6250] eta: 0:05:50 lr: 0.000118 grad: 0.0624 (0.0660) loss: 0.8358 (0.8374) time: 0.1392 data: 0.0589 max mem: 9390 +Train: [19] [3800/6250] eta: 0:05:36 lr: 0.000118 grad: 0.0606 (0.0659) loss: 0.8361 (0.8374) time: 0.1277 data: 0.0462 max mem: 9390 +Train: [19] [3900/6250] eta: 0:05:22 lr: 0.000118 grad: 0.0635 (0.0659) loss: 0.8422 (0.8375) time: 0.1564 data: 0.0345 max mem: 9390 +Train: [19] [4000/6250] eta: 0:05:09 lr: 0.000118 grad: 0.0589 (0.0658) loss: 0.8424 (0.8375) time: 0.1885 data: 0.1094 max mem: 9390 +Train: [19] [4100/6250] eta: 0:04:55 lr: 0.000118 grad: 0.0599 (0.0657) loss: 0.8395 (0.8375) time: 0.1133 data: 0.0297 max mem: 9390 +Train: [19] [4200/6250] eta: 0:04:41 lr: 0.000118 grad: 0.0591 (0.0656) loss: 0.8419 (0.8376) time: 0.1294 data: 0.0485 max mem: 9390 +Train: [19] [4300/6250] eta: 0:04:27 lr: 0.000118 grad: 0.0583 (0.0655) loss: 0.8437 (0.8376) time: 0.1276 data: 0.0458 max mem: 9390 +Train: [19] [4400/6250] eta: 0:04:14 lr: 0.000118 grad: 0.0596 (0.0654) loss: 0.8416 (0.8377) time: 0.1321 data: 0.0495 max mem: 9390 +Train: [19] [4500/6250] eta: 0:04:00 lr: 0.000118 grad: 0.0600 (0.0653) loss: 0.8378 (0.8377) time: 0.1427 data: 0.0636 max mem: 9390 +Train: [19] [4600/6250] eta: 0:03:46 lr: 0.000118 grad: 0.0581 (0.0653) loss: 0.8368 (0.8378) time: 0.1273 data: 0.0439 max mem: 9390 +Train: [19] [4700/6250] eta: 0:03:32 lr: 0.000118 grad: 0.0646 (0.0652) loss: 0.8402 (0.8378) time: 0.1470 data: 0.0671 max mem: 9390 +Train: [19] [4800/6250] eta: 0:03:19 lr: 0.000118 grad: 0.0616 (0.0652) loss: 0.8382 (0.8378) time: 0.1431 data: 0.0625 max mem: 9390 +Train: [19] [4900/6250] eta: 0:03:05 lr: 0.000118 grad: 0.0621 (0.0652) loss: 0.8386 (0.8378) time: 0.1351 data: 0.0559 max mem: 9390 +Train: [19] [5000/6250] eta: 0:02:51 lr: 0.000118 grad: 0.0596 (0.0652) loss: 0.8351 (0.8379) time: 0.1221 data: 0.0423 max mem: 9390 +Train: [19] [5100/6250] eta: 0:02:37 lr: 0.000118 grad: 0.0599 (0.0652) loss: 0.8407 (0.8379) time: 0.1220 data: 0.0378 max mem: 9390 +Train: [19] [5200/6250] eta: 0:02:23 lr: 0.000118 grad: 0.0588 (0.0651) loss: 0.8416 (0.8380) time: 0.1313 data: 0.0504 max mem: 9390 +Train: [19] [5300/6250] eta: 0:02:10 lr: 0.000118 grad: 0.0628 (0.0651) loss: 0.8351 (0.8380) time: 0.1411 data: 0.0669 max mem: 9390 +Train: [19] [5400/6250] eta: 0:01:56 lr: 0.000118 grad: 0.0590 (0.0651) loss: 0.8418 (0.8380) time: 0.1456 data: 0.0685 max mem: 9390 +Train: [19] [5500/6250] eta: 0:01:42 lr: 0.000118 grad: 0.0622 (0.0651) loss: 0.8361 (0.8380) time: 0.1572 data: 0.0796 max mem: 9390 +Train: [19] [5600/6250] eta: 0:01:29 lr: 0.000118 grad: 0.0649 (0.0651) loss: 0.8434 (0.8380) time: 0.1518 data: 0.0706 max mem: 9390 +Train: [19] [5700/6250] eta: 0:01:15 lr: 0.000118 grad: 0.0647 (0.0651) loss: 0.8408 (0.8380) time: 0.1280 data: 0.0443 max mem: 9390 +Train: [19] [5800/6250] eta: 0:01:01 lr: 0.000118 grad: 0.0607 (0.0651) loss: 0.8432 (0.8380) time: 0.1161 data: 0.0359 max mem: 9390 +Train: [19] [5900/6250] eta: 0:00:48 lr: 0.000118 grad: 0.0623 (0.0652) loss: 0.8425 (0.8380) time: 0.1516 data: 0.0745 max mem: 9390 +Train: [19] [6000/6250] eta: 0:00:34 lr: 0.000118 grad: 0.0625 (0.0652) loss: 0.8378 (0.8380) time: 0.1013 data: 0.0247 max mem: 9390 +Train: [19] [6100/6250] eta: 0:00:20 lr: 0.000117 grad: 0.0617 (0.0652) loss: 0.8397 (0.8380) time: 0.1513 data: 0.0683 max mem: 9390 +Train: [19] [6200/6250] eta: 0:00:06 lr: 0.000117 grad: 0.0645 (0.0653) loss: 0.8338 (0.8380) time: 0.1453 data: 0.0721 max mem: 9390 +Train: [19] [6249/6250] eta: 0:00:00 lr: 0.000117 grad: 0.0676 (0.0653) loss: 0.8316 (0.8380) time: 0.1244 data: 0.0456 max mem: 9390 +Train: [19] Total time: 0:14:28 (0.1389 s / it) +Averaged stats: lr: 0.000117 grad: 0.0676 (0.0653) loss: 0.8316 (0.8380) +Eval (hcp-train-subset): [19] [ 0/62] eta: 0:04:02 loss: 0.8569 (0.8569) time: 3.9064 data: 3.8764 max mem: 9390 +Eval (hcp-train-subset): [19] [61/62] eta: 0:00:00 loss: 0.8447 (0.8465) time: 0.0962 data: 0.0694 max mem: 9390 +Eval (hcp-train-subset): [19] Total time: 0:00:11 (0.1842 s / it) +Averaged stats (hcp-train-subset): loss: 0.8447 (0.8465) +Making plots (hcp-train-subset): example=45 +Eval (hcp-val): [19] [ 0/62] eta: 0:04:29 loss: 0.8409 (0.8409) time: 4.3411 data: 4.3110 max mem: 9390 +Eval (hcp-val): [19] [61/62] eta: 0:00:00 loss: 0.8408 (0.8423) time: 0.1096 data: 0.0847 max mem: 9390 +Eval (hcp-val): [19] Total time: 0:00:11 (0.1826 s / it) +Averaged stats (hcp-val): loss: 0.8408 (0.8423) +Making plots (hcp-val): example=32 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +Train: [20] [ 0/6250] eta: 10:25:02 lr: 0.000117 grad: 0.1116 (0.1116) loss: 0.8285 (0.8285) time: 6.0003 data: 5.8546 max mem: 9390 +Train: [20] [ 100/6250] eta: 0:20:53 lr: 0.000117 grad: 0.0719 (0.0749) loss: 0.8424 (0.8415) time: 0.1539 data: 0.0707 max mem: 9390 +Train: [20] [ 200/6250] eta: 0:17:55 lr: 0.000117 grad: 0.0637 (0.0701) loss: 0.8388 (0.8394) time: 0.1606 data: 0.0769 max mem: 9390 +Train: [20] [ 300/6250] eta: 0:16:42 lr: 0.000117 grad: 0.0631 (0.0689) loss: 0.8423 (0.8388) time: 0.1526 data: 0.0642 max mem: 9390 +Train: [20] [ 400/6250] eta: 0:15:58 lr: 0.000117 grad: 0.0612 (0.0678) loss: 0.8323 (0.8382) time: 0.1375 data: 0.0543 max mem: 9390 +Train: [20] [ 500/6250] eta: 0:15:21 lr: 0.000117 grad: 0.0625 (0.0672) loss: 0.8382 (0.8384) time: 0.1650 data: 0.0844 max mem: 9390 +Train: [20] [ 600/6250] eta: 0:14:45 lr: 0.000117 grad: 0.0659 (0.0669) loss: 0.8323 (0.8383) time: 0.1228 data: 0.0381 max mem: 9390 +Train: [20] [ 700/6250] eta: 0:14:19 lr: 0.000117 grad: 0.0654 (0.0667) loss: 0.8417 (0.8386) time: 0.1521 data: 0.0699 max mem: 9390 +Train: [20] [ 800/6250] eta: 0:14:02 lr: 0.000117 grad: 0.0616 (0.0664) loss: 0.8429 (0.8387) time: 0.1668 data: 0.0919 max mem: 9390 +Train: [20] [ 900/6250] eta: 0:13:37 lr: 0.000117 grad: 0.0649 (0.0659) loss: 0.8337 (0.8387) time: 0.1552 data: 0.0715 max mem: 9390 +Train: [20] [1000/6250] eta: 0:13:17 lr: 0.000117 grad: 0.0622 (0.0657) loss: 0.8467 (0.8389) time: 0.1386 data: 0.0575 max mem: 9390 +Train: [20] [1100/6250] eta: 0:12:59 lr: 0.000117 grad: 0.0626 (0.0656) loss: 0.8375 (0.8390) time: 0.1710 data: 0.0952 max mem: 9390 +Train: [20] [1200/6250] eta: 0:12:37 lr: 0.000117 grad: 0.0640 (0.0656) loss: 0.8413 (0.8389) time: 0.1432 data: 0.0704 max mem: 9390 +Train: [20] [1300/6250] eta: 0:12:17 lr: 0.000117 grad: 0.0642 (0.0655) loss: 0.8398 (0.8388) time: 0.1245 data: 0.0456 max mem: 9390 +Train: [20] [1400/6250] eta: 0:11:57 lr: 0.000117 grad: 0.0602 (0.0655) loss: 0.8404 (0.8390) time: 0.1349 data: 0.0526 max mem: 9390 +Train: [20] [1500/6250] eta: 0:11:41 lr: 0.000117 grad: 0.0618 (0.0655) loss: 0.8404 (0.8390) time: 0.1220 data: 0.0396 max mem: 9390 +Train: [20] [1600/6250] eta: 0:11:24 lr: 0.000117 grad: 0.0632 (0.0655) loss: 0.8423 (0.8391) time: 0.1399 data: 0.0561 max mem: 9390 +Train: [20] [1700/6250] eta: 0:11:07 lr: 0.000117 grad: 0.0616 (0.0655) loss: 0.8375 (0.8391) time: 0.1408 data: 0.0587 max mem: 9390 +Train: [20] [1800/6250] eta: 0:10:50 lr: 0.000117 grad: 0.0618 (0.0655) loss: 0.8313 (0.8390) time: 0.1360 data: 0.0525 max mem: 9390 +Train: [20] [1900/6250] eta: 0:10:34 lr: 0.000117 grad: 0.0660 (0.0655) loss: 0.8433 (0.8391) time: 0.1542 data: 0.0752 max mem: 9390 +Train: [20] [2000/6250] eta: 0:10:18 lr: 0.000117 grad: 0.0639 (0.0654) loss: 0.8415 (0.8392) time: 0.1479 data: 0.0665 max mem: 9390 +Train: [20] [2100/6250] eta: 0:10:02 lr: 0.000117 grad: 0.0612 (0.0654) loss: 0.8368 (0.8392) time: 0.1565 data: 0.0735 max mem: 9390 +Train: [20] [2200/6250] eta: 0:09:47 lr: 0.000117 grad: 0.0675 (0.0653) loss: 0.8392 (0.8392) time: 0.1456 data: 0.0647 max mem: 9390 +Train: [20] [2300/6250] eta: 0:09:32 lr: 0.000117 grad: 0.0641 (0.0652) loss: 0.8370 (0.8393) time: 0.1322 data: 0.0538 max mem: 9390 +Train: [20] [2400/6250] eta: 0:09:17 lr: 0.000117 grad: 0.0661 (0.0653) loss: 0.8324 (0.8393) time: 0.1483 data: 0.0730 max mem: 9390 +Train: [20] [2500/6250] eta: 0:09:01 lr: 0.000117 grad: 0.0660 (0.0652) loss: 0.8380 (0.8393) time: 0.1376 data: 0.0584 max mem: 9390 +Train: [20] [2600/6250] eta: 0:08:45 lr: 0.000117 grad: 0.0642 (0.0652) loss: 0.8356 (0.8393) time: 0.1449 data: 0.0666 max mem: 9390 +Train: [20] [2700/6250] eta: 0:08:30 lr: 0.000117 grad: 0.0628 (0.0653) loss: 0.8375 (0.8393) time: 0.1383 data: 0.0631 max mem: 9390 +Train: [20] [2800/6250] eta: 0:08:14 lr: 0.000117 grad: 0.0634 (0.0654) loss: 0.8439 (0.8393) time: 0.1363 data: 0.0537 max mem: 9390 +Train: [20] [2900/6250] eta: 0:07:59 lr: 0.000117 grad: 0.0595 (0.0654) loss: 0.8351 (0.8393) time: 0.1224 data: 0.0446 max mem: 9390 +Train: [20] [3000/6250] eta: 0:07:44 lr: 0.000117 grad: 0.0625 (0.0654) loss: 0.8357 (0.8393) time: 0.1339 data: 0.0515 max mem: 9390 +Train: [20] [3100/6250] eta: 0:07:30 lr: 0.000117 grad: 0.0671 (0.0653) loss: 0.8368 (0.8392) time: 0.1367 data: 0.0575 max mem: 9390 +Train: [20] [3200/6250] eta: 0:07:14 lr: 0.000117 grad: 0.0596 (0.0653) loss: 0.8420 (0.8392) time: 0.1386 data: 0.0641 max mem: 9390 +Train: [20] [3300/6250] eta: 0:07:00 lr: 0.000117 grad: 0.0620 (0.0653) loss: 0.8366 (0.8392) time: 0.1360 data: 0.0395 max mem: 9390 +Train: [20] [3400/6250] eta: 0:06:46 lr: 0.000117 grad: 0.0599 (0.0652) loss: 0.8366 (0.8392) time: 0.1569 data: 0.0765 max mem: 9390 +Train: [20] [3500/6250] eta: 0:06:30 lr: 0.000117 grad: 0.0621 (0.0652) loss: 0.8388 (0.8391) time: 0.1307 data: 0.0515 max mem: 9390 +Train: [20] [3600/6250] eta: 0:06:16 lr: 0.000117 grad: 0.0630 (0.0653) loss: 0.8333 (0.8390) time: 0.1216 data: 0.0428 max mem: 9390 +Train: [20] [3700/6250] eta: 0:06:01 lr: 0.000117 grad: 0.0613 (0.0653) loss: 0.8383 (0.8390) time: 0.1447 data: 0.0615 max mem: 9390 +Train: [20] [3800/6250] eta: 0:05:46 lr: 0.000117 grad: 0.0649 (0.0653) loss: 0.8351 (0.8389) time: 0.1380 data: 0.0641 max mem: 9390 +Train: [20] [3900/6250] eta: 0:05:32 lr: 0.000117 grad: 0.0642 (0.0653) loss: 0.8378 (0.8388) time: 0.1364 data: 0.0573 max mem: 9390 +Train: [20] [4000/6250] eta: 0:05:17 lr: 0.000117 grad: 0.0611 (0.0653) loss: 0.8391 (0.8388) time: 0.1498 data: 0.0740 max mem: 9390 +Train: [20] [4100/6250] eta: 0:05:03 lr: 0.000117 grad: 0.0643 (0.0653) loss: 0.8367 (0.8387) time: 0.1257 data: 0.0433 max mem: 9390 +Train: [20] [4200/6250] eta: 0:04:48 lr: 0.000117 grad: 0.0643 (0.0654) loss: 0.8296 (0.8386) time: 0.1303 data: 0.0500 max mem: 9390 +Train: [20] [4300/6250] eta: 0:04:34 lr: 0.000117 grad: 0.0639 (0.0655) loss: 0.8399 (0.8385) time: 0.1222 data: 0.0455 max mem: 9390 +Train: [20] [4400/6250] eta: 0:04:20 lr: 0.000117 grad: 0.0651 (0.0656) loss: 0.8410 (0.8385) time: 0.1196 data: 0.0394 max mem: 9390 +Train: [20] [4500/6250] eta: 0:04:05 lr: 0.000117 grad: 0.0615 (0.0656) loss: 0.8390 (0.8384) time: 0.1225 data: 0.0426 max mem: 9390 +Train: [20] [4600/6250] eta: 0:03:51 lr: 0.000117 grad: 0.0650 (0.0657) loss: 0.8279 (0.8383) time: 0.1217 data: 0.0405 max mem: 9390 +Train: [20] [4700/6250] eta: 0:03:37 lr: 0.000117 grad: 0.0639 (0.0657) loss: 0.8390 (0.8383) time: 0.1316 data: 0.0539 max mem: 9390 +Train: [20] [4800/6250] eta: 0:03:23 lr: 0.000117 grad: 0.0664 (0.0658) loss: 0.8317 (0.8382) time: 0.1219 data: 0.0382 max mem: 9390 +Train: [20] [4900/6250] eta: 0:03:09 lr: 0.000117 grad: 0.0693 (0.0659) loss: 0.8352 (0.8381) time: 0.1402 data: 0.0540 max mem: 9390 +Train: [20] [5000/6250] eta: 0:02:54 lr: 0.000117 grad: 0.0800 (0.0660) loss: 0.8282 (0.8380) time: 0.1345 data: 0.0571 max mem: 9390 +Train: [20] [5100/6250] eta: 0:02:40 lr: 0.000117 grad: 0.0671 (0.0660) loss: 0.8361 (0.8379) time: 0.1290 data: 0.0486 max mem: 9390 +Train: [20] [5200/6250] eta: 0:02:26 lr: 0.000117 grad: 0.0666 (0.0661) loss: 0.8338 (0.8378) time: 0.1396 data: 0.0611 max mem: 9390 +Train: [20] [5300/6250] eta: 0:02:12 lr: 0.000117 grad: 0.0680 (0.0661) loss: 0.8355 (0.8378) time: 0.1329 data: 0.0547 max mem: 9390 +Train: [20] [5400/6250] eta: 0:01:58 lr: 0.000117 grad: 0.0628 (0.0661) loss: 0.8349 (0.8377) time: 0.1516 data: 0.0765 max mem: 9390 +Train: [20] [5500/6250] eta: 0:01:44 lr: 0.000117 grad: 0.0672 (0.0661) loss: 0.8364 (0.8377) time: 0.1553 data: 0.0768 max mem: 9390 +Train: [20] [5600/6250] eta: 0:01:30 lr: 0.000117 grad: 0.0689 (0.0662) loss: 0.8343 (0.8376) time: 0.1358 data: 0.0469 max mem: 9390 +Train: [20] [5700/6250] eta: 0:01:16 lr: 0.000117 grad: 0.0706 (0.0663) loss: 0.8329 (0.8376) time: 0.1338 data: 0.0518 max mem: 9390 +Train: [20] [5800/6250] eta: 0:01:02 lr: 0.000117 grad: 0.0681 (0.0663) loss: 0.8322 (0.8375) time: 0.1279 data: 0.0512 max mem: 9390 +Train: [20] [5900/6250] eta: 0:00:48 lr: 0.000117 grad: 0.0634 (0.0663) loss: 0.8387 (0.8375) time: 0.1957 data: 0.1242 max mem: 9390 +Train: [20] [6000/6250] eta: 0:00:35 lr: 0.000116 grad: 0.0679 (0.0664) loss: 0.8327 (0.8374) time: 0.1643 data: 0.0797 max mem: 9390 +Train: [20] [6100/6250] eta: 0:00:21 lr: 0.000116 grad: 0.0651 (0.0664) loss: 0.8355 (0.8373) time: 0.1396 data: 0.0633 max mem: 9390 +Train: [20] [6200/6250] eta: 0:00:07 lr: 0.000116 grad: 0.0676 (0.0664) loss: 0.8351 (0.8373) time: 0.1437 data: 0.0697 max mem: 9390 +Train: [20] [6249/6250] eta: 0:00:00 lr: 0.000116 grad: 0.0637 (0.0664) loss: 0.8344 (0.8372) time: 0.1531 data: 0.0779 max mem: 9390 +Train: [20] Total time: 0:14:44 (0.1415 s / it) +Averaged stats: lr: 0.000116 grad: 0.0637 (0.0664) loss: 0.8344 (0.8372) +Eval (hcp-train-subset): [20] [ 0/62] eta: 0:05:36 loss: 0.8531 (0.8531) time: 5.4293 data: 5.3980 max mem: 9390 +Eval (hcp-train-subset): [20] [61/62] eta: 0:00:00 loss: 0.8423 (0.8442) time: 0.1146 data: 0.0897 max mem: 9390 +Eval (hcp-train-subset): [20] Total time: 0:00:13 (0.2114 s / it) +Averaged stats (hcp-train-subset): loss: 0.8423 (0.8442) +Eval (hcp-val): [20] [ 0/62] eta: 0:03:56 loss: 0.8378 (0.8378) time: 3.8223 data: 3.7518 max mem: 9390 +Eval (hcp-val): [20] [61/62] eta: 0:00:00 loss: 0.8396 (0.8406) time: 0.1194 data: 0.0947 max mem: 9390 +Eval (hcp-val): [20] Total time: 0:00:12 (0.2068 s / it) +Averaged stats (hcp-val): loss: 0.8396 (0.8406) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +Train: [21] [ 0/6250] eta: 10:01:49 lr: 0.000116 grad: 0.0468 (0.0468) loss: 0.8728 (0.8728) time: 5.7775 data: 5.6534 max mem: 9390 +Train: [21] [ 100/6250] eta: 0:19:42 lr: 0.000116 grad: 0.0668 (0.0744) loss: 0.8434 (0.8395) time: 0.1232 data: 0.0448 max mem: 9390 +Train: [21] [ 200/6250] eta: 0:17:23 lr: 0.000116 grad: 0.0649 (0.0718) loss: 0.8344 (0.8375) time: 0.1701 data: 0.0833 max mem: 9390 +Train: [21] [ 300/6250] eta: 0:16:03 lr: 0.000116 grad: 0.0701 (0.0708) loss: 0.8274 (0.8372) time: 0.1235 data: 0.0395 max mem: 9390 +Train: [21] [ 400/6250] eta: 0:15:11 lr: 0.000116 grad: 0.0685 (0.0703) loss: 0.8323 (0.8367) time: 0.1443 data: 0.0567 max mem: 9390 +Train: [21] [ 500/6250] eta: 0:14:42 lr: 0.000116 grad: 0.0628 (0.0692) loss: 0.8354 (0.8367) time: 0.1435 data: 0.0575 max mem: 9390 +Train: [21] [ 600/6250] eta: 0:14:19 lr: 0.000116 grad: 0.0609 (0.0682) loss: 0.8370 (0.8370) time: 0.1512 data: 0.0666 max mem: 9390 +Train: [21] [ 700/6250] eta: 0:14:01 lr: 0.000116 grad: 0.0585 (0.0674) loss: 0.8421 (0.8374) time: 0.1594 data: 0.0792 max mem: 9390 +Train: [21] [ 800/6250] eta: 0:13:42 lr: 0.000116 grad: 0.0609 (0.0668) loss: 0.8408 (0.8377) time: 0.1312 data: 0.0532 max mem: 9390 +Train: [21] [ 900/6250] eta: 0:13:23 lr: 0.000116 grad: 0.0643 (0.0666) loss: 0.8363 (0.8376) time: 0.1415 data: 0.0623 max mem: 9390 +Train: [21] [1000/6250] eta: 0:13:06 lr: 0.000116 grad: 0.0605 (0.0666) loss: 0.8357 (0.8376) time: 0.1459 data: 0.0629 max mem: 9390 +Train: [21] [1100/6250] eta: 0:12:44 lr: 0.000116 grad: 0.0601 (0.0661) loss: 0.8394 (0.8377) time: 0.1349 data: 0.0571 max mem: 9390 +Train: [21] [1200/6250] eta: 0:12:26 lr: 0.000116 grad: 0.0649 (0.0660) loss: 0.8349 (0.8378) time: 0.1422 data: 0.0643 max mem: 9390 +Train: [21] [1300/6250] eta: 0:12:08 lr: 0.000116 grad: 0.0624 (0.0660) loss: 0.8391 (0.8378) time: 0.1256 data: 0.0353 max mem: 9390 +Train: [21] [1400/6250] eta: 0:11:50 lr: 0.000116 grad: 0.0629 (0.0659) loss: 0.8381 (0.8378) time: 0.1489 data: 0.0712 max mem: 9390 +Train: [21] [1500/6250] eta: 0:11:32 lr: 0.000116 grad: 0.0625 (0.0657) loss: 0.8357 (0.8378) time: 0.1337 data: 0.0561 max mem: 9390 +Train: [21] [1600/6250] eta: 0:11:16 lr: 0.000116 grad: 0.0598 (0.0658) loss: 0.8403 (0.8378) time: 0.1415 data: 0.0675 max mem: 9390 +Train: [21] [1700/6250] eta: 0:11:00 lr: 0.000116 grad: 0.0644 (0.0658) loss: 0.8365 (0.8378) time: 0.1470 data: 0.0685 max mem: 9390 +Train: [21] [1800/6250] eta: 0:10:45 lr: 0.000116 grad: 0.0595 (0.0656) loss: 0.8409 (0.8379) time: 0.1557 data: 0.0744 max mem: 9390 +Train: [21] [1900/6250] eta: 0:10:28 lr: 0.000116 grad: 0.0642 (0.0655) loss: 0.8381 (0.8379) time: 0.1314 data: 0.0513 max mem: 9390 +Train: [21] [2000/6250] eta: 0:10:12 lr: 0.000116 grad: 0.0621 (0.0655) loss: 0.8386 (0.8378) time: 0.1373 data: 0.0611 max mem: 9390 +Train: [21] [2100/6250] eta: 0:09:56 lr: 0.000116 grad: 0.0627 (0.0653) loss: 0.8338 (0.8379) time: 0.1517 data: 0.0695 max mem: 9390 +Train: [21] [2200/6250] eta: 0:09:40 lr: 0.000116 grad: 0.0621 (0.0652) loss: 0.8366 (0.8379) time: 0.1378 data: 0.0595 max mem: 9390 +Train: [21] [2300/6250] eta: 0:09:24 lr: 0.000116 grad: 0.0611 (0.0652) loss: 0.8333 (0.8379) time: 0.1454 data: 0.0663 max mem: 9390 +Train: [21] [2400/6250] eta: 0:09:09 lr: 0.000116 grad: 0.0621 (0.0651) loss: 0.8408 (0.8379) time: 0.1303 data: 0.0511 max mem: 9390 +Train: [21] [2500/6250] eta: 0:08:53 lr: 0.000116 grad: 0.0634 (0.0650) loss: 0.8389 (0.8379) time: 0.1306 data: 0.0483 max mem: 9390 +Train: [21] [2600/6250] eta: 0:08:38 lr: 0.000116 grad: 0.0608 (0.0650) loss: 0.8356 (0.8379) time: 0.1266 data: 0.0428 max mem: 9390 +Train: [21] [2700/6250] eta: 0:08:23 lr: 0.000116 grad: 0.0619 (0.0650) loss: 0.8347 (0.8377) time: 0.1432 data: 0.0623 max mem: 9390 +Train: [21] [2800/6250] eta: 0:08:08 lr: 0.000116 grad: 0.0617 (0.0650) loss: 0.8330 (0.8376) time: 0.1539 data: 0.0750 max mem: 9390 +Train: [21] [2900/6250] eta: 0:07:54 lr: 0.000116 grad: 0.0616 (0.0650) loss: 0.8325 (0.8375) time: 0.1390 data: 0.0611 max mem: 9390 +Train: [21] [3000/6250] eta: 0:07:39 lr: 0.000116 grad: 0.0601 (0.0650) loss: 0.8341 (0.8373) time: 0.1349 data: 0.0600 max mem: 9390 +Train: [21] [3100/6250] eta: 0:07:24 lr: 0.000116 grad: 0.0645 (0.0651) loss: 0.8371 (0.8372) time: 0.1262 data: 0.0419 max mem: 9390 +Train: [21] [3200/6250] eta: 0:07:09 lr: 0.000116 grad: 0.0630 (0.0652) loss: 0.8333 (0.8371) time: 0.1274 data: 0.0503 max mem: 9390 +Train: [21] [3300/6250] eta: 0:06:55 lr: 0.000116 grad: 0.0649 (0.0652) loss: 0.8322 (0.8370) time: 0.1528 data: 0.0696 max mem: 9390 +Train: [21] [3400/6250] eta: 0:06:40 lr: 0.000116 grad: 0.0596 (0.0653) loss: 0.8327 (0.8368) time: 0.1402 data: 0.0573 max mem: 9390 +Train: [21] [3500/6250] eta: 0:06:26 lr: 0.000116 grad: 0.0629 (0.0653) loss: 0.8339 (0.8367) time: 0.1402 data: 0.0633 max mem: 9390 +Train: [21] [3600/6250] eta: 0:06:11 lr: 0.000116 grad: 0.0625 (0.0654) loss: 0.8294 (0.8366) time: 0.1224 data: 0.0418 max mem: 9390 +Train: [21] [3700/6250] eta: 0:05:57 lr: 0.000116 grad: 0.0653 (0.0654) loss: 0.8339 (0.8366) time: 0.1480 data: 0.0673 max mem: 9390 +Train: [21] [3800/6250] eta: 0:05:42 lr: 0.000116 grad: 0.0628 (0.0654) loss: 0.8370 (0.8365) time: 0.1393 data: 0.0617 max mem: 9390 +Train: [21] [3900/6250] eta: 0:05:28 lr: 0.000116 grad: 0.0636 (0.0655) loss: 0.8372 (0.8365) time: 0.1230 data: 0.0408 max mem: 9390 +Train: [21] [4000/6250] eta: 0:05:14 lr: 0.000116 grad: 0.0682 (0.0656) loss: 0.8362 (0.8365) time: 0.1343 data: 0.0532 max mem: 9390 +Train: [21] [4100/6250] eta: 0:04:59 lr: 0.000116 grad: 0.0632 (0.0656) loss: 0.8352 (0.8364) time: 0.1187 data: 0.0366 max mem: 9390 +Train: [21] [4200/6250] eta: 0:04:45 lr: 0.000116 grad: 0.0648 (0.0656) loss: 0.8321 (0.8364) time: 0.1288 data: 0.0488 max mem: 9390 +Train: [21] [4300/6250] eta: 0:04:31 lr: 0.000116 grad: 0.0668 (0.0657) loss: 0.8323 (0.8363) time: 0.1124 data: 0.0336 max mem: 9390 +Train: [21] [4400/6250] eta: 0:04:17 lr: 0.000116 grad: 0.0627 (0.0657) loss: 0.8385 (0.8363) time: 0.1499 data: 0.0759 max mem: 9390 +Train: [21] [4500/6250] eta: 0:04:03 lr: 0.000116 grad: 0.0609 (0.0657) loss: 0.8370 (0.8363) time: 0.1266 data: 0.0475 max mem: 9390 +Train: [21] [4600/6250] eta: 0:03:49 lr: 0.000116 grad: 0.0634 (0.0657) loss: 0.8346 (0.8363) time: 0.1567 data: 0.0816 max mem: 9390 +Train: [21] [4700/6250] eta: 0:03:35 lr: 0.000116 grad: 0.0659 (0.0657) loss: 0.8315 (0.8362) time: 0.1393 data: 0.0599 max mem: 9390 +Train: [21] [4800/6250] eta: 0:03:21 lr: 0.000116 grad: 0.0652 (0.0657) loss: 0.8371 (0.8362) time: 0.1313 data: 0.0486 max mem: 9390 +Train: [21] [4900/6250] eta: 0:03:07 lr: 0.000116 grad: 0.0606 (0.0657) loss: 0.8377 (0.8363) time: 0.1286 data: 0.0421 max mem: 9390 +Train: [21] [5000/6250] eta: 0:02:53 lr: 0.000116 grad: 0.0633 (0.0657) loss: 0.8318 (0.8362) time: 0.1224 data: 0.0422 max mem: 9390 +Train: [21] [5100/6250] eta: 0:02:39 lr: 0.000116 grad: 0.0630 (0.0657) loss: 0.8361 (0.8362) time: 0.1293 data: 0.0469 max mem: 9390 +Train: [21] [5200/6250] eta: 0:02:25 lr: 0.000116 grad: 0.0664 (0.0657) loss: 0.8330 (0.8362) time: 0.1511 data: 0.0608 max mem: 9390 +Train: [21] [5300/6250] eta: 0:02:12 lr: 0.000116 grad: 0.0664 (0.0657) loss: 0.8341 (0.8361) time: 0.1423 data: 0.0569 max mem: 9390 +Train: [21] [5400/6250] eta: 0:01:58 lr: 0.000116 grad: 0.0663 (0.0657) loss: 0.8338 (0.8361) time: 0.1518 data: 0.0705 max mem: 9390 +Train: [21] [5500/6250] eta: 0:01:44 lr: 0.000116 grad: 0.0714 (0.0658) loss: 0.8265 (0.8360) time: 0.1340 data: 0.0562 max mem: 9390 +Train: [21] [5600/6250] eta: 0:01:30 lr: 0.000115 grad: 0.0664 (0.0658) loss: 0.8376 (0.8360) time: 0.1332 data: 0.0571 max mem: 9390 +Train: [21] [5700/6250] eta: 0:01:16 lr: 0.000115 grad: 0.0675 (0.0659) loss: 0.8332 (0.8360) time: 0.1413 data: 0.0545 max mem: 9390 +Train: [21] [5800/6250] eta: 0:01:02 lr: 0.000115 grad: 0.0682 (0.0659) loss: 0.8311 (0.8359) time: 0.1336 data: 0.0440 max mem: 9390 +Train: [21] [5900/6250] eta: 0:00:48 lr: 0.000115 grad: 0.0639 (0.0659) loss: 0.8326 (0.8359) time: 0.1387 data: 0.0574 max mem: 9390 +Train: [21] [6000/6250] eta: 0:00:34 lr: 0.000115 grad: 0.0663 (0.0659) loss: 0.8354 (0.8358) time: 0.1750 data: 0.0899 max mem: 9390 +Train: [21] [6100/6250] eta: 0:00:20 lr: 0.000115 grad: 0.0647 (0.0659) loss: 0.8368 (0.8358) time: 0.1399 data: 0.0564 max mem: 9390 +Train: [21] [6200/6250] eta: 0:00:06 lr: 0.000115 grad: 0.0614 (0.0660) loss: 0.8326 (0.8358) time: 0.1801 data: 0.0949 max mem: 9390 +Train: [21] [6249/6250] eta: 0:00:00 lr: 0.000115 grad: 0.0605 (0.0659) loss: 0.8377 (0.8358) time: 0.1810 data: 0.0939 max mem: 9390 +Train: [21] Total time: 0:14:41 (0.1410 s / it) +Averaged stats: lr: 0.000115 grad: 0.0605 (0.0659) loss: 0.8377 (0.8358) +Eval (hcp-train-subset): [21] [ 0/62] eta: 0:04:48 loss: 0.8531 (0.8531) time: 4.6589 data: 4.6225 max mem: 9390 +Eval (hcp-train-subset): [21] [61/62] eta: 0:00:00 loss: 0.8462 (0.8448) time: 0.1318 data: 0.1051 max mem: 9390 +Eval (hcp-train-subset): [21] Total time: 0:00:13 (0.2123 s / it) +Averaged stats (hcp-train-subset): loss: 0.8462 (0.8448) +Eval (hcp-val): [21] [ 0/62] eta: 0:04:43 loss: 0.8398 (0.8398) time: 4.5721 data: 4.5418 max mem: 9390 +Eval (hcp-val): [21] [61/62] eta: 0:00:00 loss: 0.8399 (0.8410) time: 0.1190 data: 0.0942 max mem: 9390 +Eval (hcp-val): [21] Total time: 0:00:12 (0.2065 s / it) +Averaged stats (hcp-val): loss: 0.8399 (0.8410) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +Train: [22] [ 0/6250] eta: 7:13:04 lr: 0.000115 grad: 0.0555 (0.0555) loss: 0.8561 (0.8561) time: 4.1575 data: 3.9918 max mem: 9390 +Train: [22] [ 100/6250] eta: 0:20:10 lr: 0.000115 grad: 0.0710 (0.0742) loss: 0.8320 (0.8400) time: 0.1534 data: 0.0701 max mem: 9390 +Train: [22] [ 200/6250] eta: 0:17:44 lr: 0.000115 grad: 0.0634 (0.0717) loss: 0.8399 (0.8378) time: 0.1596 data: 0.0724 max mem: 9390 +Train: [22] [ 300/6250] eta: 0:16:20 lr: 0.000115 grad: 0.0623 (0.0703) loss: 0.8346 (0.8365) time: 0.1349 data: 0.0447 max mem: 9390 +Train: [22] [ 400/6250] eta: 0:15:33 lr: 0.000115 grad: 0.0610 (0.0689) loss: 0.8403 (0.8366) time: 0.1496 data: 0.0639 max mem: 9390 +Train: [22] [ 500/6250] eta: 0:14:55 lr: 0.000115 grad: 0.0630 (0.0683) loss: 0.8424 (0.8373) time: 0.1405 data: 0.0586 max mem: 9390 +Train: [22] [ 600/6250] eta: 0:14:24 lr: 0.000115 grad: 0.0623 (0.0683) loss: 0.8415 (0.8375) time: 0.1108 data: 0.0286 max mem: 9390 +Train: [22] [ 700/6250] eta: 0:14:08 lr: 0.000115 grad: 0.0612 (0.0676) loss: 0.8400 (0.8379) time: 0.1628 data: 0.0791 max mem: 9390 +Train: [22] [ 800/6250] eta: 0:13:51 lr: 0.000115 grad: 0.0631 (0.0671) loss: 0.8405 (0.8379) time: 0.1484 data: 0.0687 max mem: 9390 +Train: [22] [ 900/6250] eta: 0:13:37 lr: 0.000115 grad: 0.0610 (0.0667) loss: 0.8357 (0.8376) time: 0.1686 data: 0.0862 max mem: 9390 +Train: [22] [1000/6250] eta: 0:13:17 lr: 0.000115 grad: 0.0631 (0.0665) loss: 0.8377 (0.8376) time: 0.1615 data: 0.0834 max mem: 9390 +Train: [22] [1100/6250] eta: 0:12:57 lr: 0.000115 grad: 0.0620 (0.0663) loss: 0.8339 (0.8372) time: 0.1438 data: 0.0606 max mem: 9390 +Train: [22] [1200/6250] eta: 0:12:40 lr: 0.000115 grad: 0.0633 (0.0663) loss: 0.8371 (0.8369) time: 0.1549 data: 0.0782 max mem: 9390 +Train: [22] [1300/6250] eta: 0:12:20 lr: 0.000115 grad: 0.0649 (0.0664) loss: 0.8386 (0.8367) time: 0.1334 data: 0.0545 max mem: 9390 +Train: [22] [1400/6250] eta: 0:12:03 lr: 0.000115 grad: 0.0667 (0.0666) loss: 0.8337 (0.8363) time: 0.1602 data: 0.0838 max mem: 9390 +Train: [22] [1500/6250] eta: 0:11:44 lr: 0.000115 grad: 0.0683 (0.0668) loss: 0.8317 (0.8361) time: 0.1348 data: 0.0534 max mem: 9390 +Train: [22] [1600/6250] eta: 0:11:26 lr: 0.000115 grad: 0.0620 (0.0668) loss: 0.8306 (0.8358) time: 0.1501 data: 0.0647 max mem: 9390 +Train: [22] [1700/6250] eta: 0:11:12 lr: 0.000115 grad: 0.0643 (0.0669) loss: 0.8330 (0.8356) time: 0.1620 data: 0.0845 max mem: 9390 +Train: [22] [1800/6250] eta: 0:10:54 lr: 0.000115 grad: 0.0645 (0.0669) loss: 0.8296 (0.8354) time: 0.1471 data: 0.0640 max mem: 9390 +Train: [22] [1900/6250] eta: 0:10:36 lr: 0.000115 grad: 0.0660 (0.0670) loss: 0.8289 (0.8352) time: 0.1312 data: 0.0418 max mem: 9390 +Train: [22] [2000/6250] eta: 0:10:19 lr: 0.000115 grad: 0.0660 (0.0672) loss: 0.8355 (0.8350) time: 0.1398 data: 0.0593 max mem: 9390 +Train: [22] [2100/6250] eta: 0:10:02 lr: 0.000115 grad: 0.0696 (0.0673) loss: 0.8306 (0.8349) time: 0.1308 data: 0.0536 max mem: 9390 +Train: [22] [2200/6250] eta: 0:09:46 lr: 0.000115 grad: 0.0632 (0.0675) loss: 0.8414 (0.8349) time: 0.1382 data: 0.0615 max mem: 9390 +Train: [22] [2300/6250] eta: 0:09:30 lr: 0.000115 grad: 0.0646 (0.0675) loss: 0.8345 (0.8348) time: 0.1521 data: 0.0766 max mem: 9390 +Train: [22] [2400/6250] eta: 0:09:14 lr: 0.000115 grad: 0.0640 (0.0676) loss: 0.8340 (0.8348) time: 0.1346 data: 0.0581 max mem: 9390 +Train: [22] [2500/6250] eta: 0:08:59 lr: 0.000115 grad: 0.0654 (0.0676) loss: 0.8339 (0.8348) time: 0.1646 data: 0.0843 max mem: 9390 +Train: [22] [2600/6250] eta: 0:08:44 lr: 0.000115 grad: 0.0669 (0.0677) loss: 0.8340 (0.8347) time: 0.1535 data: 0.0684 max mem: 9390 +Train: [22] [2700/6250] eta: 0:08:28 lr: 0.000115 grad: 0.0730 (0.0678) loss: 0.8350 (0.8346) time: 0.1178 data: 0.0406 max mem: 9390 +Train: [22] [2800/6250] eta: 0:08:13 lr: 0.000115 grad: 0.0683 (0.0678) loss: 0.8340 (0.8345) time: 0.1181 data: 0.0446 max mem: 9390 +Train: [22] [2900/6250] eta: 0:07:58 lr: 0.000115 grad: 0.0684 (0.0679) loss: 0.8274 (0.8344) time: 0.1370 data: 0.0582 max mem: 9390 +Train: [22] [3000/6250] eta: 0:07:42 lr: 0.000115 grad: 0.0655 (0.0679) loss: 0.8370 (0.8343) time: 0.1245 data: 0.0453 max mem: 9390 +Train: [22] [3100/6250] eta: 0:07:28 lr: 0.000115 grad: 0.0639 (0.0679) loss: 0.8378 (0.8343) time: 0.1444 data: 0.0673 max mem: 9390 +Train: [22] [3200/6250] eta: 0:07:13 lr: 0.000115 grad: 0.0667 (0.0679) loss: 0.8341 (0.8343) time: 0.1427 data: 0.0630 max mem: 9390 +Train: [22] [3300/6250] eta: 0:06:58 lr: 0.000115 grad: 0.0633 (0.0679) loss: 0.8339 (0.8343) time: 0.1364 data: 0.0549 max mem: 9390 +Train: [22] [3400/6250] eta: 0:06:44 lr: 0.000115 grad: 0.0624 (0.0680) loss: 0.8378 (0.8343) time: 0.1453 data: 0.0634 max mem: 9390 +Train: [22] [3500/6250] eta: 0:06:29 lr: 0.000115 grad: 0.0642 (0.0679) loss: 0.8338 (0.8343) time: 0.1328 data: 0.0474 max mem: 9390 +Train: [22] [3600/6250] eta: 0:06:15 lr: 0.000115 grad: 0.0630 (0.0679) loss: 0.8324 (0.8342) time: 0.1380 data: 0.0540 max mem: 9390 +Train: [22] [3700/6250] eta: 0:06:00 lr: 0.000115 grad: 0.0652 (0.0679) loss: 0.8334 (0.8342) time: 0.1466 data: 0.0738 max mem: 9390 +Train: [22] [3800/6250] eta: 0:05:46 lr: 0.000115 grad: 0.0660 (0.0679) loss: 0.8308 (0.8342) time: 0.1233 data: 0.0426 max mem: 9390 +Train: [22] [3900/6250] eta: 0:05:31 lr: 0.000115 grad: 0.0661 (0.0679) loss: 0.8287 (0.8341) time: 0.1469 data: 0.0696 max mem: 9390 +Train: [22] [4000/6250] eta: 0:05:17 lr: 0.000115 grad: 0.0707 (0.0679) loss: 0.8345 (0.8340) time: 0.1309 data: 0.0529 max mem: 9390 +Train: [22] [4100/6250] eta: 0:05:03 lr: 0.000115 grad: 0.0662 (0.0679) loss: 0.8330 (0.8339) time: 0.1519 data: 0.0695 max mem: 9390 +Train: [22] [4200/6250] eta: 0:04:48 lr: 0.000115 grad: 0.0658 (0.0679) loss: 0.8304 (0.8339) time: 0.1409 data: 0.0615 max mem: 9390 +Train: [22] [4300/6250] eta: 0:04:34 lr: 0.000115 grad: 0.0669 (0.0680) loss: 0.8296 (0.8339) time: 0.1382 data: 0.0608 max mem: 9390 +Train: [22] [4400/6250] eta: 0:04:20 lr: 0.000115 grad: 0.0634 (0.0680) loss: 0.8363 (0.8338) time: 0.1563 data: 0.0802 max mem: 9390 +Train: [22] [4500/6250] eta: 0:04:06 lr: 0.000115 grad: 0.0682 (0.0681) loss: 0.8351 (0.8337) time: 0.1342 data: 0.0554 max mem: 9390 +Train: [22] [4600/6250] eta: 0:03:52 lr: 0.000115 grad: 0.0669 (0.0681) loss: 0.8346 (0.8337) time: 0.1524 data: 0.0679 max mem: 9390 +Train: [22] [4700/6250] eta: 0:03:37 lr: 0.000115 grad: 0.0648 (0.0682) loss: 0.8342 (0.8336) time: 0.1294 data: 0.0499 max mem: 9390 +Train: [22] [4800/6250] eta: 0:03:23 lr: 0.000115 grad: 0.0649 (0.0683) loss: 0.8267 (0.8335) time: 0.1248 data: 0.0418 max mem: 9390 +Train: [22] [4900/6250] eta: 0:03:09 lr: 0.000114 grad: 0.0686 (0.0684) loss: 0.8308 (0.8335) time: 0.1191 data: 0.0363 max mem: 9390 +Train: [22] [5000/6250] eta: 0:02:55 lr: 0.000114 grad: 0.0688 (0.0685) loss: 0.8333 (0.8335) time: 0.1279 data: 0.0519 max mem: 9390 +Train: [22] [5100/6250] eta: 0:02:41 lr: 0.000114 grad: 0.0682 (0.0685) loss: 0.8327 (0.8334) time: 0.1446 data: 0.0691 max mem: 9390 +Train: [22] [5200/6250] eta: 0:02:27 lr: 0.000114 grad: 0.0676 (0.0686) loss: 0.8296 (0.8334) time: 0.1537 data: 0.0662 max mem: 9390 +Train: [22] [5300/6250] eta: 0:02:13 lr: 0.000114 grad: 0.0634 (0.0686) loss: 0.8350 (0.8334) time: 0.1361 data: 0.0537 max mem: 9390 +Train: [22] [5400/6250] eta: 0:01:59 lr: 0.000114 grad: 0.0667 (0.0686) loss: 0.8335 (0.8335) time: 0.1261 data: 0.0475 max mem: 9390 +Train: [22] [5500/6250] eta: 0:01:45 lr: 0.000114 grad: 0.0641 (0.0686) loss: 0.8365 (0.8335) time: 0.1275 data: 0.0505 max mem: 9390 +Train: [22] [5600/6250] eta: 0:01:31 lr: 0.000114 grad: 0.0739 (0.0687) loss: 0.8346 (0.8335) time: 0.1241 data: 0.0427 max mem: 9390 +Train: [22] [5700/6250] eta: 0:01:17 lr: 0.000114 grad: 0.0703 (0.0687) loss: 0.8326 (0.8336) time: 0.1195 data: 0.0428 max mem: 9390 +Train: [22] [5800/6250] eta: 0:01:02 lr: 0.000114 grad: 0.0706 (0.0687) loss: 0.8288 (0.8336) time: 0.1429 data: 0.0639 max mem: 9390 +Train: [22] [5900/6250] eta: 0:00:48 lr: 0.000114 grad: 0.0609 (0.0687) loss: 0.8340 (0.8336) time: 0.1208 data: 0.0440 max mem: 9390 +Train: [22] [6000/6250] eta: 0:00:34 lr: 0.000114 grad: 0.0637 (0.0686) loss: 0.8366 (0.8336) time: 0.1330 data: 0.0475 max mem: 9390 +Train: [22] [6100/6250] eta: 0:00:20 lr: 0.000114 grad: 0.0677 (0.0686) loss: 0.8342 (0.8336) time: 0.1551 data: 0.0721 max mem: 9390 +Train: [22] [6200/6250] eta: 0:00:07 lr: 0.000114 grad: 0.0634 (0.0686) loss: 0.8392 (0.8336) time: 0.1218 data: 0.0414 max mem: 9390 +Train: [22] [6249/6250] eta: 0:00:00 lr: 0.000114 grad: 0.0620 (0.0686) loss: 0.8368 (0.8336) time: 0.1499 data: 0.0719 max mem: 9390 +Train: [22] Total time: 0:14:46 (0.1418 s / it) +Averaged stats: lr: 0.000114 grad: 0.0620 (0.0686) loss: 0.8368 (0.8336) +Eval (hcp-train-subset): [22] [ 0/62] eta: 0:04:38 loss: 0.8513 (0.8513) time: 4.4938 data: 4.4612 max mem: 9390 +Eval (hcp-train-subset): [22] [61/62] eta: 0:00:00 loss: 0.8427 (0.8442) time: 0.1200 data: 0.0931 max mem: 9390 +Eval (hcp-train-subset): [22] Total time: 0:00:13 (0.2207 s / it) +Averaged stats (hcp-train-subset): loss: 0.8427 (0.8442) +Eval (hcp-val): [22] [ 0/62] eta: 0:05:18 loss: 0.8414 (0.8414) time: 5.1388 data: 5.0753 max mem: 9390 +Eval (hcp-val): [22] [61/62] eta: 0:00:00 loss: 0.8406 (0.8407) time: 0.1162 data: 0.0914 max mem: 9390 +Eval (hcp-val): [22] Total time: 0:00:12 (0.2053 s / it) +Averaged stats (hcp-val): loss: 0.8406 (0.8407) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +Train: [23] [ 0/6250] eta: 8:39:54 lr: 0.000114 grad: 0.0894 (0.0894) loss: 0.8582 (0.8582) time: 4.9911 data: 4.8044 max mem: 9390 +Train: [23] [ 100/6250] eta: 0:19:51 lr: 0.000114 grad: 0.0693 (0.0813) loss: 0.8383 (0.8424) time: 0.1435 data: 0.0514 max mem: 9390 +Train: [23] [ 200/6250] eta: 0:17:18 lr: 0.000114 grad: 0.0751 (0.0791) loss: 0.8298 (0.8357) time: 0.1416 data: 0.0561 max mem: 9390 +Train: [23] [ 300/6250] eta: 0:16:08 lr: 0.000114 grad: 0.0666 (0.0779) loss: 0.8246 (0.8316) time: 0.1313 data: 0.0376 max mem: 9390 +Train: [23] [ 400/6250] eta: 0:15:19 lr: 0.000114 grad: 0.0705 (0.0766) loss: 0.8140 (0.8300) time: 0.1375 data: 0.0568 max mem: 9390 +Train: [23] [ 500/6250] eta: 0:14:40 lr: 0.000114 grad: 0.0675 (0.0752) loss: 0.8247 (0.8294) time: 0.1325 data: 0.0490 max mem: 9390 +Train: [23] [ 600/6250] eta: 0:14:18 lr: 0.000114 grad: 0.0674 (0.0738) loss: 0.8290 (0.8297) time: 0.1488 data: 0.0626 max mem: 9390 +Train: [23] [ 700/6250] eta: 0:14:01 lr: 0.000114 grad: 0.0635 (0.0730) loss: 0.8313 (0.8301) time: 0.1268 data: 0.0443 max mem: 9390 +Train: [23] [ 800/6250] eta: 0:13:43 lr: 0.000114 grad: 0.0675 (0.0727) loss: 0.8325 (0.8305) time: 0.1306 data: 0.0454 max mem: 9390 +Train: [23] [ 900/6250] eta: 0:13:29 lr: 0.000114 grad: 0.0670 (0.0725) loss: 0.8302 (0.8307) time: 0.1508 data: 0.0682 max mem: 9390 +Train: [23] [1000/6250] eta: 0:13:09 lr: 0.000114 grad: 0.0679 (0.0722) loss: 0.8298 (0.8307) time: 0.1430 data: 0.0564 max mem: 9390 +Train: [23] [1100/6250] eta: 0:12:54 lr: 0.000114 grad: 0.0696 (0.0719) loss: 0.8289 (0.8307) time: 0.1289 data: 0.0448 max mem: 9390 +Train: [23] [1200/6250] eta: 0:12:33 lr: 0.000114 grad: 0.0666 (0.0716) loss: 0.8305 (0.8307) time: 0.1430 data: 0.0620 max mem: 9390 +Train: [23] [1300/6250] eta: 0:12:14 lr: 0.000114 grad: 0.0700 (0.0713) loss: 0.8304 (0.8305) time: 0.1497 data: 0.0713 max mem: 9390 +Train: [23] [1400/6250] eta: 0:11:56 lr: 0.000114 grad: 0.0688 (0.0711) loss: 0.8296 (0.8306) time: 0.1374 data: 0.0587 max mem: 9390 +Train: [23] [1500/6250] eta: 0:11:37 lr: 0.000114 grad: 0.0673 (0.0710) loss: 0.8301 (0.8306) time: 0.1395 data: 0.0555 max mem: 9390 +Train: [23] [1600/6250] eta: 0:11:20 lr: 0.000114 grad: 0.0678 (0.0709) loss: 0.8332 (0.8307) time: 0.1270 data: 0.0395 max mem: 9390 +Train: [23] [1700/6250] eta: 0:11:05 lr: 0.000114 grad: 0.0694 (0.0709) loss: 0.8360 (0.8308) time: 0.1370 data: 0.0589 max mem: 9390 +Train: [23] [1800/6250] eta: 0:10:48 lr: 0.000114 grad: 0.0629 (0.0707) loss: 0.8390 (0.8310) time: 0.1429 data: 0.0625 max mem: 9390 +Train: [23] [1900/6250] eta: 0:10:33 lr: 0.000114 grad: 0.0683 (0.0706) loss: 0.8321 (0.8310) time: 0.1448 data: 0.0604 max mem: 9390 +Train: [23] [2000/6250] eta: 0:10:16 lr: 0.000114 grad: 0.0765 (0.0707) loss: 0.8332 (0.8310) time: 0.1395 data: 0.0554 max mem: 9390 +Train: [23] [2100/6250] eta: 0:10:01 lr: 0.000114 grad: 0.0686 (0.0707) loss: 0.8301 (0.8310) time: 0.1439 data: 0.0652 max mem: 9390 +Train: [23] [2200/6250] eta: 0:09:46 lr: 0.000114 grad: 0.0642 (0.0706) loss: 0.8370 (0.8312) time: 0.1326 data: 0.0512 max mem: 9390 +Train: [23] [2300/6250] eta: 0:09:29 lr: 0.000114 grad: 0.0694 (0.0706) loss: 0.8337 (0.8312) time: 0.1360 data: 0.0545 max mem: 9390 +Train: [23] [2400/6250] eta: 0:09:14 lr: 0.000114 grad: 0.0648 (0.0705) loss: 0.8346 (0.8312) time: 0.1460 data: 0.0722 max mem: 9390 +Train: [23] [2500/6250] eta: 0:08:58 lr: 0.000114 grad: 0.0698 (0.0705) loss: 0.8377 (0.8313) time: 0.1317 data: 0.0493 max mem: 9390 +Train: [23] [2600/6250] eta: 0:08:43 lr: 0.000114 grad: 0.0608 (0.0704) loss: 0.8403 (0.8314) time: 0.1318 data: 0.0474 max mem: 9390 +Train: [23] [2700/6250] eta: 0:08:28 lr: 0.000114 grad: 0.0661 (0.0703) loss: 0.8347 (0.8315) time: 0.1571 data: 0.0805 max mem: 9390 +Train: [23] [2800/6250] eta: 0:08:14 lr: 0.000114 grad: 0.0671 (0.0702) loss: 0.8357 (0.8316) time: 0.1405 data: 0.0629 max mem: 9390 +Train: [23] [2900/6250] eta: 0:07:59 lr: 0.000114 grad: 0.0639 (0.0701) loss: 0.8327 (0.8316) time: 0.1458 data: 0.0647 max mem: 9390 +Train: [23] [3000/6250] eta: 0:07:44 lr: 0.000114 grad: 0.0654 (0.0700) loss: 0.8321 (0.8317) time: 0.1354 data: 0.0548 max mem: 9390 +Train: [23] [3100/6250] eta: 0:07:29 lr: 0.000114 grad: 0.0669 (0.0700) loss: 0.8353 (0.8318) time: 0.1482 data: 0.0665 max mem: 9390 +Train: [23] [3200/6250] eta: 0:07:15 lr: 0.000114 grad: 0.0724 (0.0700) loss: 0.8334 (0.8318) time: 0.1369 data: 0.0637 max mem: 9390 +Train: [23] [3300/6250] eta: 0:07:00 lr: 0.000114 grad: 0.0644 (0.0700) loss: 0.8345 (0.8319) time: 0.1416 data: 0.0638 max mem: 9390 +Train: [23] [3400/6250] eta: 0:06:45 lr: 0.000114 grad: 0.0690 (0.0700) loss: 0.8322 (0.8318) time: 0.1332 data: 0.0545 max mem: 9390 +Train: [23] [3500/6250] eta: 0:06:30 lr: 0.000114 grad: 0.0674 (0.0700) loss: 0.8293 (0.8319) time: 0.1288 data: 0.0505 max mem: 9390 +Train: [23] [3600/6250] eta: 0:06:16 lr: 0.000114 grad: 0.0748 (0.0700) loss: 0.8268 (0.8318) time: 0.1324 data: 0.0513 max mem: 9390 +Train: [23] [3700/6250] eta: 0:06:01 lr: 0.000114 grad: 0.0712 (0.0700) loss: 0.8296 (0.8318) time: 0.1221 data: 0.0442 max mem: 9390 +Train: [23] [3800/6250] eta: 0:05:46 lr: 0.000114 grad: 0.0721 (0.0701) loss: 0.8312 (0.8318) time: 0.1439 data: 0.0648 max mem: 9390 +Train: [23] [3900/6250] eta: 0:05:32 lr: 0.000114 grad: 0.0658 (0.0701) loss: 0.8343 (0.8319) time: 0.1351 data: 0.0463 max mem: 9390 +Train: [23] [4000/6250] eta: 0:05:17 lr: 0.000113 grad: 0.0712 (0.0701) loss: 0.8335 (0.8319) time: 0.1339 data: 0.0513 max mem: 9390 +Train: [23] [4100/6250] eta: 0:05:03 lr: 0.000113 grad: 0.0662 (0.0701) loss: 0.8373 (0.8319) time: 0.1290 data: 0.0497 max mem: 9390 +Train: [23] [4200/6250] eta: 0:04:49 lr: 0.000113 grad: 0.0672 (0.0701) loss: 0.8352 (0.8319) time: 0.1429 data: 0.0631 max mem: 9390 +Train: [23] [4300/6250] eta: 0:04:34 lr: 0.000113 grad: 0.0651 (0.0701) loss: 0.8298 (0.8319) time: 0.1360 data: 0.0525 max mem: 9390 +Train: [23] [4400/6250] eta: 0:04:20 lr: 0.000113 grad: 0.0667 (0.0700) loss: 0.8317 (0.8321) time: 0.1314 data: 0.0503 max mem: 9390 +Train: [23] [4500/6250] eta: 0:04:05 lr: 0.000113 grad: 0.0618 (0.0700) loss: 0.8395 (0.8322) time: 0.1309 data: 0.0478 max mem: 9390 +Train: [23] [4600/6250] eta: 0:03:51 lr: 0.000113 grad: 0.0639 (0.0699) loss: 0.8407 (0.8323) time: 0.1491 data: 0.0707 max mem: 9390 +Train: [23] [4700/6250] eta: 0:03:37 lr: 0.000113 grad: 0.0675 (0.0699) loss: 0.8364 (0.8324) time: 0.1334 data: 0.0548 max mem: 9390 +Train: [23] [4800/6250] eta: 0:03:23 lr: 0.000113 grad: 0.0689 (0.0699) loss: 0.8334 (0.8325) time: 0.1384 data: 0.0591 max mem: 9390 +Train: [23] [4900/6250] eta: 0:03:09 lr: 0.000113 grad: 0.0679 (0.0699) loss: 0.8336 (0.8326) time: 0.1254 data: 0.0429 max mem: 9390 +Train: [23] [5000/6250] eta: 0:02:55 lr: 0.000113 grad: 0.0671 (0.0699) loss: 0.8367 (0.8327) time: 0.1476 data: 0.0707 max mem: 9390 +Train: [23] [5100/6250] eta: 0:02:41 lr: 0.000113 grad: 0.0657 (0.0698) loss: 0.8368 (0.8328) time: 0.1424 data: 0.0506 max mem: 9390 +Train: [23] [5200/6250] eta: 0:02:27 lr: 0.000113 grad: 0.0667 (0.0698) loss: 0.8388 (0.8329) time: 0.1426 data: 0.0678 max mem: 9390 +Train: [23] [5300/6250] eta: 0:02:13 lr: 0.000113 grad: 0.0677 (0.0698) loss: 0.8285 (0.8329) time: 0.1442 data: 0.0623 max mem: 9390 +Train: [23] [5400/6250] eta: 0:01:59 lr: 0.000113 grad: 0.0664 (0.0697) loss: 0.8345 (0.8330) time: 0.1232 data: 0.0435 max mem: 9390 +Train: [23] [5500/6250] eta: 0:01:45 lr: 0.000113 grad: 0.0645 (0.0697) loss: 0.8356 (0.8331) time: 0.1563 data: 0.0746 max mem: 9390 +Train: [23] [5600/6250] eta: 0:01:31 lr: 0.000113 grad: 0.0649 (0.0697) loss: 0.8330 (0.8331) time: 0.1502 data: 0.0697 max mem: 9390 +Train: [23] [5700/6250] eta: 0:01:17 lr: 0.000113 grad: 0.0639 (0.0697) loss: 0.8359 (0.8332) time: 0.1418 data: 0.0657 max mem: 9390 +Train: [23] [5800/6250] eta: 0:01:02 lr: 0.000113 grad: 0.0742 (0.0697) loss: 0.8303 (0.8332) time: 0.1361 data: 0.0540 max mem: 9390 +Train: [23] [5900/6250] eta: 0:00:48 lr: 0.000113 grad: 0.0658 (0.0697) loss: 0.8345 (0.8332) time: 0.1419 data: 0.0653 max mem: 9390 +Train: [23] [6000/6250] eta: 0:00:34 lr: 0.000113 grad: 0.0652 (0.0697) loss: 0.8345 (0.8332) time: 0.1611 data: 0.0802 max mem: 9390 +Train: [23] [6100/6250] eta: 0:00:21 lr: 0.000113 grad: 0.0635 (0.0697) loss: 0.8343 (0.8332) time: 0.1589 data: 0.0785 max mem: 9390 +Train: [23] [6200/6250] eta: 0:00:07 lr: 0.000113 grad: 0.0685 (0.0696) loss: 0.8281 (0.8332) time: 0.1431 data: 0.0674 max mem: 9390 +Train: [23] [6249/6250] eta: 0:00:00 lr: 0.000113 grad: 0.0689 (0.0696) loss: 0.8292 (0.8332) time: 0.1708 data: 0.0848 max mem: 9390 +Train: [23] Total time: 0:14:45 (0.1418 s / it) +Averaged stats: lr: 0.000113 grad: 0.0689 (0.0696) loss: 0.8292 (0.8332) +Eval (hcp-train-subset): [23] [ 0/62] eta: 0:06:00 loss: 0.8532 (0.8532) time: 5.8106 data: 5.7803 max mem: 9390 +Eval (hcp-train-subset): [23] [61/62] eta: 0:00:00 loss: 0.8432 (0.8442) time: 0.1140 data: 0.0874 max mem: 9390 +Eval (hcp-train-subset): [23] Total time: 0:00:14 (0.2306 s / it) +Averaged stats (hcp-train-subset): loss: 0.8432 (0.8442) +Eval (hcp-val): [23] [ 0/62] eta: 0:05:30 loss: 0.8395 (0.8395) time: 5.3290 data: 5.2997 max mem: 9390 +Eval (hcp-val): [23] [61/62] eta: 0:00:00 loss: 0.8402 (0.8405) time: 0.0954 data: 0.0686 max mem: 9390 +Eval (hcp-val): [23] Total time: 0:00:12 (0.2000 s / it) +Averaged stats (hcp-val): loss: 0.8402 (0.8405) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +Train: [24] [ 0/6250] eta: 10:07:27 lr: 0.000113 grad: 0.0977 (0.0977) loss: 0.8429 (0.8429) time: 5.8316 data: 5.7243 max mem: 9390 +Train: [24] [ 100/6250] eta: 0:20:22 lr: 0.000113 grad: 0.0639 (0.0751) loss: 0.8411 (0.8397) time: 0.1490 data: 0.0593 max mem: 9390 +Train: [24] [ 200/6250] eta: 0:17:10 lr: 0.000113 grad: 0.0600 (0.0729) loss: 0.8456 (0.8387) time: 0.1379 data: 0.0553 max mem: 9390 +Train: [24] [ 300/6250] eta: 0:15:58 lr: 0.000113 grad: 0.0659 (0.0696) loss: 0.8341 (0.8379) time: 0.1365 data: 0.0464 max mem: 9390 +Train: [24] [ 400/6250] eta: 0:15:04 lr: 0.000113 grad: 0.0637 (0.0679) loss: 0.8292 (0.8362) time: 0.1279 data: 0.0244 max mem: 9390 +Train: [24] [ 500/6250] eta: 0:14:29 lr: 0.000113 grad: 0.0623 (0.0673) loss: 0.8365 (0.8353) time: 0.1230 data: 0.0333 max mem: 9390 +Train: [24] [ 600/6250] eta: 0:14:12 lr: 0.000113 grad: 0.0609 (0.0669) loss: 0.8384 (0.8352) time: 0.1506 data: 0.0670 max mem: 9390 +Train: [24] [ 700/6250] eta: 0:13:59 lr: 0.000113 grad: 0.0627 (0.0664) loss: 0.8347 (0.8351) time: 0.1466 data: 0.0626 max mem: 9390 +Train: [24] [ 800/6250] eta: 0:13:42 lr: 0.000113 grad: 0.0622 (0.0661) loss: 0.8324 (0.8353) time: 0.1518 data: 0.0710 max mem: 9390 +Train: [24] [ 900/6250] eta: 0:13:25 lr: 0.000113 grad: 0.0615 (0.0657) loss: 0.8404 (0.8356) time: 0.1662 data: 0.0857 max mem: 9390 +Train: [24] [1000/6250] eta: 0:13:04 lr: 0.000113 grad: 0.0602 (0.0653) loss: 0.8376 (0.8358) time: 0.1559 data: 0.0749 max mem: 9390 +Train: [24] [1100/6250] eta: 0:12:46 lr: 0.000113 grad: 0.0613 (0.0650) loss: 0.8400 (0.8360) time: 0.1392 data: 0.0612 max mem: 9390 +Train: [24] [1200/6250] eta: 0:12:28 lr: 0.000113 grad: 0.0632 (0.0649) loss: 0.8331 (0.8360) time: 0.1130 data: 0.0320 max mem: 9390 +Train: [24] [1300/6250] eta: 0:12:12 lr: 0.000113 grad: 0.0632 (0.0649) loss: 0.8366 (0.8360) time: 0.1352 data: 0.0599 max mem: 9390 +Train: [24] [1400/6250] eta: 0:11:54 lr: 0.000113 grad: 0.0626 (0.0649) loss: 0.8323 (0.8359) time: 0.1361 data: 0.0589 max mem: 9390 +Train: [24] [1500/6250] eta: 0:11:35 lr: 0.000113 grad: 0.0652 (0.0649) loss: 0.8384 (0.8359) time: 0.1291 data: 0.0526 max mem: 9390 +Train: [24] [1600/6250] eta: 0:11:20 lr: 0.000113 grad: 0.0625 (0.0649) loss: 0.8342 (0.8358) time: 0.1305 data: 0.0592 max mem: 9390 +Train: [24] [1700/6250] eta: 0:11:04 lr: 0.000113 grad: 0.0634 (0.0650) loss: 0.8357 (0.8357) time: 0.1610 data: 0.0809 max mem: 9390 +Train: [24] [1800/6250] eta: 0:10:48 lr: 0.000113 grad: 0.0667 (0.0651) loss: 0.8273 (0.8355) time: 0.1330 data: 0.0564 max mem: 9390 +Train: [24] [1900/6250] eta: 0:10:32 lr: 0.000113 grad: 0.0676 (0.0652) loss: 0.8362 (0.8353) time: 0.1387 data: 0.0592 max mem: 9390 +Train: [24] [2000/6250] eta: 0:10:16 lr: 0.000113 grad: 0.0664 (0.0653) loss: 0.8257 (0.8353) time: 0.1355 data: 0.0531 max mem: 9390 +Train: [24] [2100/6250] eta: 0:10:01 lr: 0.000113 grad: 0.0654 (0.0653) loss: 0.8361 (0.8353) time: 0.1553 data: 0.0732 max mem: 9390 +Train: [24] [2200/6250] eta: 0:09:46 lr: 0.000113 grad: 0.0685 (0.0654) loss: 0.8273 (0.8351) time: 0.1500 data: 0.0709 max mem: 9390 +Train: [24] [2300/6250] eta: 0:09:29 lr: 0.000113 grad: 0.0627 (0.0654) loss: 0.8351 (0.8351) time: 0.1361 data: 0.0469 max mem: 9390 +Train: [24] [2400/6250] eta: 0:09:14 lr: 0.000113 grad: 0.0622 (0.0654) loss: 0.8326 (0.8350) time: 0.1416 data: 0.0584 max mem: 9390 +Train: [24] [2500/6250] eta: 0:09:00 lr: 0.000113 grad: 0.0638 (0.0655) loss: 0.8316 (0.8349) time: 0.1347 data: 0.0534 max mem: 9390 +Train: [24] [2600/6250] eta: 0:08:45 lr: 0.000113 grad: 0.0633 (0.0655) loss: 0.8317 (0.8348) time: 0.1408 data: 0.0649 max mem: 9390 +Train: [24] [2700/6250] eta: 0:08:29 lr: 0.000113 grad: 0.0679 (0.0657) loss: 0.8362 (0.8348) time: 0.1156 data: 0.0329 max mem: 9390 +Train: [24] [2800/6250] eta: 0:08:15 lr: 0.000113 grad: 0.0646 (0.0656) loss: 0.8309 (0.8348) time: 0.1535 data: 0.0729 max mem: 9390 +Train: [24] [2900/6250] eta: 0:08:02 lr: 0.000112 grad: 0.0660 (0.0657) loss: 0.8340 (0.8347) time: 0.1383 data: 0.0595 max mem: 9390 +Train: [24] [3000/6250] eta: 0:07:48 lr: 0.000112 grad: 0.0661 (0.0657) loss: 0.8304 (0.8347) time: 0.1348 data: 0.0617 max mem: 9390 +Train: [24] [3100/6250] eta: 0:07:33 lr: 0.000112 grad: 0.0696 (0.0659) loss: 0.8359 (0.8346) time: 0.1659 data: 0.0909 max mem: 9390 +Train: [24] [3200/6250] eta: 0:07:18 lr: 0.000112 grad: 0.0672 (0.0660) loss: 0.8279 (0.8345) time: 0.1455 data: 0.0687 max mem: 9390 +Train: [24] [3300/6250] eta: 0:07:03 lr: 0.000112 grad: 0.0669 (0.0661) loss: 0.8336 (0.8344) time: 0.1205 data: 0.0368 max mem: 9390 +Train: [24] [3400/6250] eta: 0:06:48 lr: 0.000112 grad: 0.0690 (0.0662) loss: 0.8270 (0.8343) time: 0.1317 data: 0.0522 max mem: 9390 +Train: [24] [3500/6250] eta: 0:06:34 lr: 0.000112 grad: 0.0726 (0.0664) loss: 0.8287 (0.8342) time: 0.1050 data: 0.0269 max mem: 9390 +Train: [24] [3600/6250] eta: 0:06:19 lr: 0.000112 grad: 0.0675 (0.0666) loss: 0.8320 (0.8341) time: 0.1413 data: 0.0563 max mem: 9390 +Train: [24] [3700/6250] eta: 0:06:04 lr: 0.000112 grad: 0.0652 (0.0666) loss: 0.8314 (0.8340) time: 0.1487 data: 0.0729 max mem: 9390 +Train: [24] [3800/6250] eta: 0:05:50 lr: 0.000112 grad: 0.0654 (0.0667) loss: 0.8258 (0.8339) time: 0.1326 data: 0.0550 max mem: 9390 +Train: [24] [3900/6250] eta: 0:05:35 lr: 0.000112 grad: 0.0655 (0.0669) loss: 0.8320 (0.8338) time: 0.1181 data: 0.0334 max mem: 9390 +Train: [24] [4000/6250] eta: 0:05:21 lr: 0.000112 grad: 0.0683 (0.0669) loss: 0.8386 (0.8338) time: 0.1424 data: 0.0624 max mem: 9390 +Train: [24] [4100/6250] eta: 0:05:06 lr: 0.000112 grad: 0.0707 (0.0670) loss: 0.8283 (0.8337) time: 0.1459 data: 0.0708 max mem: 9390 +Train: [24] [4200/6250] eta: 0:04:51 lr: 0.000112 grad: 0.0680 (0.0671) loss: 0.8328 (0.8336) time: 0.1315 data: 0.0505 max mem: 9390 +Train: [24] [4300/6250] eta: 0:04:37 lr: 0.000112 grad: 0.0710 (0.0672) loss: 0.8289 (0.8335) time: 0.1343 data: 0.0552 max mem: 9390 +Train: [24] [4400/6250] eta: 0:04:22 lr: 0.000112 grad: 0.0696 (0.0673) loss: 0.8351 (0.8335) time: 0.1391 data: 0.0592 max mem: 9390 +Train: [24] [4500/6250] eta: 0:04:08 lr: 0.000112 grad: 0.0722 (0.0674) loss: 0.8255 (0.8334) time: 0.1390 data: 0.0622 max mem: 9390 +Train: [24] [4600/6250] eta: 0:03:53 lr: 0.000112 grad: 0.0681 (0.0675) loss: 0.8327 (0.8334) time: 0.1275 data: 0.0469 max mem: 9390 +Train: [24] [4700/6250] eta: 0:03:39 lr: 0.000112 grad: 0.0689 (0.0675) loss: 0.8309 (0.8334) time: 0.1338 data: 0.0553 max mem: 9390 +Train: [24] [4800/6250] eta: 0:03:24 lr: 0.000112 grad: 0.0710 (0.0676) loss: 0.8390 (0.8333) time: 0.1454 data: 0.0670 max mem: 9390 +Train: [24] [4900/6250] eta: 0:03:10 lr: 0.000112 grad: 0.0661 (0.0676) loss: 0.8312 (0.8333) time: 0.1255 data: 0.0432 max mem: 9390 +Train: [24] [5000/6250] eta: 0:02:56 lr: 0.000112 grad: 0.0659 (0.0677) loss: 0.8316 (0.8333) time: 0.1306 data: 0.0466 max mem: 9390 +Train: [24] [5100/6250] eta: 0:02:42 lr: 0.000112 grad: 0.0701 (0.0677) loss: 0.8285 (0.8332) time: 0.1490 data: 0.0714 max mem: 9390 +Train: [24] [5200/6250] eta: 0:02:28 lr: 0.000112 grad: 0.0697 (0.0677) loss: 0.8310 (0.8332) time: 0.1358 data: 0.0585 max mem: 9390 +Train: [24] [5300/6250] eta: 0:02:13 lr: 0.000112 grad: 0.0696 (0.0678) loss: 0.8315 (0.8332) time: 0.1407 data: 0.0624 max mem: 9390 +Train: [24] [5400/6250] eta: 0:01:59 lr: 0.000112 grad: 0.0661 (0.0678) loss: 0.8321 (0.8332) time: 0.1448 data: 0.0628 max mem: 9390 +Train: [24] [5500/6250] eta: 0:01:45 lr: 0.000112 grad: 0.0657 (0.0678) loss: 0.8320 (0.8332) time: 0.1397 data: 0.0601 max mem: 9390 +Train: [24] [5600/6250] eta: 0:01:31 lr: 0.000112 grad: 0.0701 (0.0678) loss: 0.8338 (0.8332) time: 0.1447 data: 0.0663 max mem: 9390 +Train: [24] [5700/6250] eta: 0:01:17 lr: 0.000112 grad: 0.0715 (0.0679) loss: 0.8261 (0.8332) time: 0.1347 data: 0.0539 max mem: 9390 +Train: [24] [5800/6250] eta: 0:01:03 lr: 0.000112 grad: 0.0719 (0.0679) loss: 0.8292 (0.8332) time: 0.1347 data: 0.0542 max mem: 9390 +Train: [24] [5900/6250] eta: 0:00:49 lr: 0.000112 grad: 0.0711 (0.0680) loss: 0.8336 (0.8331) time: 0.1565 data: 0.0789 max mem: 9390 +Train: [24] [6000/6250] eta: 0:00:35 lr: 0.000112 grad: 0.0661 (0.0681) loss: 0.8323 (0.8331) time: 0.1565 data: 0.0780 max mem: 9390 +Train: [24] [6100/6250] eta: 0:00:21 lr: 0.000112 grad: 0.0660 (0.0681) loss: 0.8307 (0.8330) time: 0.1790 data: 0.0986 max mem: 9390 +Train: [24] [6200/6250] eta: 0:00:07 lr: 0.000112 grad: 0.0690 (0.0682) loss: 0.8271 (0.8330) time: 0.1745 data: 0.0892 max mem: 9390 +Train: [24] [6249/6250] eta: 0:00:00 lr: 0.000112 grad: 0.0714 (0.0682) loss: 0.8308 (0.8330) time: 0.1414 data: 0.0645 max mem: 9390 +Train: [24] Total time: 0:14:51 (0.1426 s / it) +Averaged stats: lr: 0.000112 grad: 0.0714 (0.0682) loss: 0.8308 (0.8330) +Eval (hcp-train-subset): [24] [ 0/62] eta: 0:05:33 loss: 0.8556 (0.8556) time: 5.3754 data: 5.3447 max mem: 9390 +Eval (hcp-train-subset): [24] [61/62] eta: 0:00:00 loss: 0.8421 (0.8443) time: 0.1102 data: 0.0853 max mem: 9390 +Eval (hcp-train-subset): [24] Total time: 0:00:13 (0.2149 s / it) +Averaged stats (hcp-train-subset): loss: 0.8421 (0.8443) +Making plots (hcp-train-subset): example=36 +Eval (hcp-val): [24] [ 0/62] eta: 0:03:27 loss: 0.8353 (0.8353) time: 3.3469 data: 3.2705 max mem: 9390 +Eval (hcp-val): [24] [61/62] eta: 0:00:00 loss: 0.8404 (0.8397) time: 0.1112 data: 0.0864 max mem: 9390 +Eval (hcp-val): [24] Total time: 0:00:12 (0.2013 s / it) +Averaged stats (hcp-val): loss: 0.8404 (0.8397) +Making plots (hcp-val): example=17 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +Train: [25] [ 0/6250] eta: 6:35:19 lr: 0.000112 grad: 0.0519 (0.0519) loss: 0.8764 (0.8764) time: 3.7951 data: 3.5603 max mem: 9390 +Train: [25] [ 100/6250] eta: 0:20:16 lr: 0.000112 grad: 0.0706 (0.0688) loss: 0.8497 (0.8445) time: 0.1576 data: 0.0688 max mem: 9390 +Train: [25] [ 200/6250] eta: 0:17:24 lr: 0.000112 grad: 0.0684 (0.0703) loss: 0.8296 (0.8387) time: 0.1326 data: 0.0487 max mem: 9390 +Train: [25] [ 300/6250] eta: 0:16:16 lr: 0.000112 grad: 0.0638 (0.0694) loss: 0.8300 (0.8369) time: 0.1414 data: 0.0559 max mem: 9390 +Train: [25] [ 400/6250] eta: 0:15:19 lr: 0.000112 grad: 0.0652 (0.0688) loss: 0.8334 (0.8355) time: 0.1362 data: 0.0493 max mem: 9390 +Train: [25] [ 500/6250] eta: 0:14:43 lr: 0.000112 grad: 0.0686 (0.0685) loss: 0.8250 (0.8343) time: 0.1437 data: 0.0565 max mem: 9390 +Train: [25] [ 600/6250] eta: 0:14:07 lr: 0.000112 grad: 0.0666 (0.0680) loss: 0.8325 (0.8340) time: 0.1248 data: 0.0439 max mem: 9390 +Train: [25] [ 700/6250] eta: 0:13:50 lr: 0.000112 grad: 0.0619 (0.0677) loss: 0.8373 (0.8340) time: 0.1645 data: 0.0788 max mem: 9390 +Train: [25] [ 800/6250] eta: 0:13:32 lr: 0.000112 grad: 0.0608 (0.0671) loss: 0.8415 (0.8345) time: 0.1418 data: 0.0580 max mem: 9390 +Train: [25] [ 900/6250] eta: 0:13:15 lr: 0.000112 grad: 0.0681 (0.0670) loss: 0.8370 (0.8346) time: 0.1214 data: 0.0397 max mem: 9390 +Train: [25] [1000/6250] eta: 0:13:00 lr: 0.000112 grad: 0.0594 (0.0668) loss: 0.8339 (0.8347) time: 0.1480 data: 0.0693 max mem: 9390 +Train: [25] [1100/6250] eta: 0:12:42 lr: 0.000112 grad: 0.0644 (0.0666) loss: 0.8358 (0.8347) time: 0.1348 data: 0.0584 max mem: 9390 +Train: [25] [1200/6250] eta: 0:12:21 lr: 0.000112 grad: 0.0628 (0.0665) loss: 0.8302 (0.8345) time: 0.1179 data: 0.0403 max mem: 9390 +Train: [25] [1300/6250] eta: 0:12:04 lr: 0.000112 grad: 0.0670 (0.0665) loss: 0.8298 (0.8343) time: 0.1374 data: 0.0541 max mem: 9390 +Train: [25] [1400/6250] eta: 0:11:49 lr: 0.000112 grad: 0.0649 (0.0663) loss: 0.8315 (0.8343) time: 0.1575 data: 0.0814 max mem: 9390 +Train: [25] [1500/6250] eta: 0:11:32 lr: 0.000112 grad: 0.0654 (0.0664) loss: 0.8330 (0.8341) time: 0.1300 data: 0.0462 max mem: 9390 +Train: [25] [1600/6250] eta: 0:11:17 lr: 0.000111 grad: 0.0662 (0.0664) loss: 0.8386 (0.8341) time: 0.1551 data: 0.0775 max mem: 9390 +Train: [25] [1700/6250] eta: 0:11:01 lr: 0.000111 grad: 0.0647 (0.0664) loss: 0.8312 (0.8338) time: 0.1448 data: 0.0662 max mem: 9390 +Train: [25] [1800/6250] eta: 0:10:45 lr: 0.000111 grad: 0.0640 (0.0663) loss: 0.8341 (0.8337) time: 0.1361 data: 0.0562 max mem: 9390 +Train: [25] [1900/6250] eta: 0:10:30 lr: 0.000111 grad: 0.0608 (0.0664) loss: 0.8306 (0.8336) time: 0.1633 data: 0.0860 max mem: 9390 +Train: [25] [2000/6250] eta: 0:10:14 lr: 0.000111 grad: 0.0669 (0.0665) loss: 0.8310 (0.8335) time: 0.1334 data: 0.0528 max mem: 9390 +Train: [25] [2100/6250] eta: 0:09:58 lr: 0.000111 grad: 0.0742 (0.0666) loss: 0.8288 (0.8334) time: 0.1316 data: 0.0508 max mem: 9390 +Train: [25] [2200/6250] eta: 0:09:42 lr: 0.000111 grad: 0.0615 (0.0666) loss: 0.8333 (0.8333) time: 0.1254 data: 0.0460 max mem: 9390 +Train: [25] [2300/6250] eta: 0:09:27 lr: 0.000111 grad: 0.0675 (0.0666) loss: 0.8317 (0.8333) time: 0.1219 data: 0.0444 max mem: 9390 +Train: [25] [2400/6250] eta: 0:09:12 lr: 0.000111 grad: 0.0665 (0.0667) loss: 0.8332 (0.8333) time: 0.1363 data: 0.0524 max mem: 9390 +Train: [25] [2500/6250] eta: 0:08:56 lr: 0.000111 grad: 0.0681 (0.0668) loss: 0.8291 (0.8331) time: 0.1350 data: 0.0534 max mem: 9390 +Train: [25] [2600/6250] eta: 0:08:42 lr: 0.000111 grad: 0.0681 (0.0670) loss: 0.8311 (0.8330) time: 0.1329 data: 0.0532 max mem: 9390 +Train: [25] [2700/6250] eta: 0:08:27 lr: 0.000111 grad: 0.0669 (0.0671) loss: 0.8291 (0.8329) time: 0.1444 data: 0.0646 max mem: 9390 +Train: [25] [2800/6250] eta: 0:08:13 lr: 0.000111 grad: 0.0693 (0.0673) loss: 0.8318 (0.8328) time: 0.1225 data: 0.0472 max mem: 9390 +Train: [25] [2900/6250] eta: 0:07:57 lr: 0.000111 grad: 0.0644 (0.0674) loss: 0.8311 (0.8327) time: 0.1354 data: 0.0537 max mem: 9390 +Train: [25] [3000/6250] eta: 0:07:42 lr: 0.000111 grad: 0.0660 (0.0676) loss: 0.8302 (0.8326) time: 0.1257 data: 0.0435 max mem: 9390 +Train: [25] [3100/6250] eta: 0:07:28 lr: 0.000111 grad: 0.0715 (0.0677) loss: 0.8331 (0.8324) time: 0.1495 data: 0.0718 max mem: 9390 +Train: [25] [3200/6250] eta: 0:07:12 lr: 0.000111 grad: 0.0651 (0.0678) loss: 0.8366 (0.8324) time: 0.1437 data: 0.0639 max mem: 9390 +Train: [25] [3300/6250] eta: 0:06:58 lr: 0.000111 grad: 0.0650 (0.0678) loss: 0.8271 (0.8324) time: 0.1516 data: 0.0683 max mem: 9390 +Train: [25] [3400/6250] eta: 0:06:43 lr: 0.000111 grad: 0.0646 (0.0678) loss: 0.8318 (0.8324) time: 0.1319 data: 0.0519 max mem: 9390 +Train: [25] [3500/6250] eta: 0:06:29 lr: 0.000111 grad: 0.0655 (0.0680) loss: 0.8311 (0.8324) time: 0.1652 data: 0.0860 max mem: 9390 +Train: [25] [3600/6250] eta: 0:06:14 lr: 0.000111 grad: 0.0613 (0.0680) loss: 0.8342 (0.8324) time: 0.1526 data: 0.0739 max mem: 9390 +Train: [25] [3700/6250] eta: 0:06:00 lr: 0.000111 grad: 0.0699 (0.0680) loss: 0.8300 (0.8324) time: 0.1611 data: 0.0834 max mem: 9390 +Train: [25] [3800/6250] eta: 0:05:45 lr: 0.000111 grad: 0.0715 (0.0681) loss: 0.8291 (0.8324) time: 0.1251 data: 0.0414 max mem: 9390 +Train: [25] [3900/6250] eta: 0:05:31 lr: 0.000111 grad: 0.0705 (0.0682) loss: 0.8335 (0.8323) time: 0.1278 data: 0.0498 max mem: 9390 +Train: [25] [4000/6250] eta: 0:05:17 lr: 0.000111 grad: 0.0716 (0.0682) loss: 0.8350 (0.8323) time: 0.1317 data: 0.0510 max mem: 9390 +Train: [25] [4100/6250] eta: 0:05:03 lr: 0.000111 grad: 0.0697 (0.0683) loss: 0.8313 (0.8323) time: 0.1379 data: 0.0527 max mem: 9390 +Train: [25] [4200/6250] eta: 0:04:48 lr: 0.000111 grad: 0.0692 (0.0683) loss: 0.8288 (0.8322) time: 0.1397 data: 0.0540 max mem: 9390 +Train: [25] [4300/6250] eta: 0:04:34 lr: 0.000111 grad: 0.0661 (0.0683) loss: 0.8313 (0.8322) time: 0.1077 data: 0.0225 max mem: 9390 +Train: [25] [4400/6250] eta: 0:04:19 lr: 0.000111 grad: 0.0643 (0.0684) loss: 0.8326 (0.8322) time: 0.1136 data: 0.0374 max mem: 9390 +Train: [25] [4500/6250] eta: 0:04:05 lr: 0.000111 grad: 0.0663 (0.0683) loss: 0.8300 (0.8322) time: 0.1377 data: 0.0582 max mem: 9390 +Train: [25] [4600/6250] eta: 0:03:51 lr: 0.000111 grad: 0.0673 (0.0684) loss: 0.8251 (0.8321) time: 0.1433 data: 0.0642 max mem: 9390 +Train: [25] [4700/6250] eta: 0:03:37 lr: 0.000111 grad: 0.0691 (0.0684) loss: 0.8289 (0.8320) time: 0.1374 data: 0.0553 max mem: 9390 +Train: [25] [4800/6250] eta: 0:03:22 lr: 0.000111 grad: 0.0673 (0.0685) loss: 0.8300 (0.8319) time: 0.1253 data: 0.0440 max mem: 9390 +Train: [25] [4900/6250] eta: 0:03:08 lr: 0.000111 grad: 0.0712 (0.0685) loss: 0.8273 (0.8318) time: 0.1318 data: 0.0512 max mem: 9390 +Train: [25] [5000/6250] eta: 0:02:54 lr: 0.000111 grad: 0.0661 (0.0686) loss: 0.8301 (0.8317) time: 0.1329 data: 0.0562 max mem: 9390 +Train: [25] [5100/6250] eta: 0:02:40 lr: 0.000111 grad: 0.0635 (0.0686) loss: 0.8324 (0.8317) time: 0.1272 data: 0.0515 max mem: 9390 +Train: [25] [5200/6250] eta: 0:02:27 lr: 0.000111 grad: 0.0660 (0.0686) loss: 0.8315 (0.8316) time: 0.1856 data: 0.1076 max mem: 9390 +Train: [25] [5300/6250] eta: 0:02:13 lr: 0.000111 grad: 0.0692 (0.0687) loss: 0.8275 (0.8316) time: 0.1373 data: 0.0603 max mem: 9390 +Train: [25] [5400/6250] eta: 0:01:59 lr: 0.000111 grad: 0.0666 (0.0687) loss: 0.8338 (0.8315) time: 0.1430 data: 0.0595 max mem: 9390 +Train: [25] [5500/6250] eta: 0:01:45 lr: 0.000111 grad: 0.0682 (0.0688) loss: 0.8339 (0.8315) time: 0.1286 data: 0.0474 max mem: 9390 +Train: [25] [5600/6250] eta: 0:01:30 lr: 0.000111 grad: 0.0696 (0.0688) loss: 0.8327 (0.8314) time: 0.1346 data: 0.0561 max mem: 9390 +Train: [25] [5700/6250] eta: 0:01:16 lr: 0.000111 grad: 0.0683 (0.0688) loss: 0.8314 (0.8314) time: 0.1214 data: 0.0451 max mem: 9390 +Train: [25] [5800/6250] eta: 0:01:02 lr: 0.000111 grad: 0.0625 (0.0688) loss: 0.8351 (0.8314) time: 0.1453 data: 0.0702 max mem: 9390 +Train: [25] [5900/6250] eta: 0:00:48 lr: 0.000111 grad: 0.0653 (0.0687) loss: 0.8335 (0.8315) time: 0.1501 data: 0.0670 max mem: 9390 +Train: [25] [6000/6250] eta: 0:00:34 lr: 0.000111 grad: 0.0624 (0.0688) loss: 0.8347 (0.8315) time: 0.1290 data: 0.0527 max mem: 9390 +Train: [25] [6100/6250] eta: 0:00:20 lr: 0.000111 grad: 0.0665 (0.0688) loss: 0.8313 (0.8315) time: 0.1274 data: 0.0395 max mem: 9390 +Train: [25] [6200/6250] eta: 0:00:07 lr: 0.000111 grad: 0.0695 (0.0688) loss: 0.8349 (0.8315) time: 0.1691 data: 0.0822 max mem: 9390 +Train: [25] [6249/6250] eta: 0:00:00 lr: 0.000111 grad: 0.0646 (0.0688) loss: 0.8339 (0.8315) time: 0.1437 data: 0.0681 max mem: 9390 +Train: [25] Total time: 0:14:42 (0.1412 s / it) +Averaged stats: lr: 0.000111 grad: 0.0646 (0.0688) loss: 0.8339 (0.8315) +Eval (hcp-train-subset): [25] [ 0/62] eta: 0:06:02 loss: 0.8549 (0.8549) time: 5.8458 data: 5.8132 max mem: 9390 +Eval (hcp-train-subset): [25] [61/62] eta: 0:00:00 loss: 0.8444 (0.8444) time: 0.1394 data: 0.1141 max mem: 9390 +Eval (hcp-train-subset): [25] Total time: 0:00:14 (0.2390 s / it) +Averaged stats (hcp-train-subset): loss: 0.8444 (0.8444) +Eval (hcp-val): [25] [ 0/62] eta: 0:05:03 loss: 0.8393 (0.8393) time: 4.8965 data: 4.8656 max mem: 9390 +Eval (hcp-val): [25] [61/62] eta: 0:00:00 loss: 0.8381 (0.8397) time: 0.1210 data: 0.0963 max mem: 9390 +Eval (hcp-val): [25] Total time: 0:00:12 (0.2053 s / it) +Averaged stats (hcp-val): loss: 0.8381 (0.8397) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +Train: [26] [ 0/6250] eta: 7:43:52 lr: 0.000111 grad: 0.2882 (0.2882) loss: 0.8381 (0.8381) time: 4.4531 data: 4.2547 max mem: 9390 +Train: [26] [ 100/6250] eta: 0:20:29 lr: 0.000111 grad: 0.0615 (0.0799) loss: 0.8421 (0.8411) time: 0.1550 data: 0.0680 max mem: 9390 +Train: [26] [ 200/6250] eta: 0:17:42 lr: 0.000110 grad: 0.0670 (0.0765) loss: 0.8344 (0.8366) time: 0.1569 data: 0.0742 max mem: 9390 +Train: [26] [ 300/6250] eta: 0:16:29 lr: 0.000110 grad: 0.0675 (0.0734) loss: 0.8337 (0.8343) time: 0.1422 data: 0.0566 max mem: 9390 +Train: [26] [ 400/6250] eta: 0:15:30 lr: 0.000110 grad: 0.0681 (0.0727) loss: 0.8309 (0.8336) time: 0.1262 data: 0.0406 max mem: 9390 +Train: [26] [ 500/6250] eta: 0:14:51 lr: 0.000110 grad: 0.0648 (0.0717) loss: 0.8346 (0.8333) time: 0.1515 data: 0.0683 max mem: 9390 +Train: [26] [ 600/6250] eta: 0:14:16 lr: 0.000110 grad: 0.0673 (0.0716) loss: 0.8308 (0.8330) time: 0.1337 data: 0.0461 max mem: 9390 +Train: [26] [ 700/6250] eta: 0:13:53 lr: 0.000110 grad: 0.0666 (0.0715) loss: 0.8305 (0.8325) time: 0.1194 data: 0.0358 max mem: 9390 +Train: [26] [ 800/6250] eta: 0:13:36 lr: 0.000110 grad: 0.0673 (0.0713) loss: 0.8326 (0.8323) time: 0.1446 data: 0.0587 max mem: 9390 +Train: [26] [ 900/6250] eta: 0:13:19 lr: 0.000110 grad: 0.0624 (0.0708) loss: 0.8350 (0.8323) time: 0.1487 data: 0.0703 max mem: 9390 +Train: [26] [1000/6250] eta: 0:13:02 lr: 0.000110 grad: 0.0655 (0.0705) loss: 0.8314 (0.8322) time: 0.1396 data: 0.0662 max mem: 9390 +Train: [26] [1100/6250] eta: 0:12:47 lr: 0.000110 grad: 0.0640 (0.0703) loss: 0.8300 (0.8321) time: 0.1471 data: 0.0680 max mem: 9390 +Train: [26] [1200/6250] eta: 0:12:27 lr: 0.000110 grad: 0.0670 (0.0700) loss: 0.8300 (0.8321) time: 0.1257 data: 0.0425 max mem: 9390 +Train: [26] [1300/6250] eta: 0:12:12 lr: 0.000110 grad: 0.0651 (0.0698) loss: 0.8290 (0.8322) time: 0.1339 data: 0.0550 max mem: 9390 +Train: [26] [1400/6250] eta: 0:11:55 lr: 0.000110 grad: 0.0696 (0.0699) loss: 0.8362 (0.8322) time: 0.1687 data: 0.0931 max mem: 9390 +Train: [26] [1500/6250] eta: 0:11:38 lr: 0.000110 grad: 0.0632 (0.0698) loss: 0.8346 (0.8322) time: 0.1565 data: 0.0781 max mem: 9390 +Train: [26] [1600/6250] eta: 0:11:20 lr: 0.000110 grad: 0.0671 (0.0696) loss: 0.8315 (0.8323) time: 0.1432 data: 0.0661 max mem: 9390 +Train: [26] [1700/6250] eta: 0:11:04 lr: 0.000110 grad: 0.0690 (0.0695) loss: 0.8324 (0.8324) time: 0.1149 data: 0.0407 max mem: 9390 +Train: [26] [1800/6250] eta: 0:10:48 lr: 0.000110 grad: 0.0674 (0.0695) loss: 0.8341 (0.8323) time: 0.1297 data: 0.0504 max mem: 9390 +Train: [26] [1900/6250] eta: 0:10:32 lr: 0.000110 grad: 0.0616 (0.0695) loss: 0.8321 (0.8322) time: 0.1461 data: 0.0682 max mem: 9390 +Train: [26] [2000/6250] eta: 0:10:16 lr: 0.000110 grad: 0.0667 (0.0695) loss: 0.8305 (0.8322) time: 0.1342 data: 0.0492 max mem: 9390 +Train: [26] [2100/6250] eta: 0:10:00 lr: 0.000110 grad: 0.0706 (0.0696) loss: 0.8331 (0.8322) time: 0.1538 data: 0.0776 max mem: 9390 +Train: [26] [2200/6250] eta: 0:09:45 lr: 0.000110 grad: 0.0688 (0.0696) loss: 0.8301 (0.8322) time: 0.1098 data: 0.0285 max mem: 9390 +Train: [26] [2300/6250] eta: 0:09:29 lr: 0.000110 grad: 0.0630 (0.0696) loss: 0.8333 (0.8323) time: 0.1335 data: 0.0557 max mem: 9390 +Train: [26] [2400/6250] eta: 0:09:13 lr: 0.000110 grad: 0.0657 (0.0694) loss: 0.8316 (0.8323) time: 0.1392 data: 0.0630 max mem: 9390 +Train: [26] [2500/6250] eta: 0:08:59 lr: 0.000110 grad: 0.0646 (0.0694) loss: 0.8348 (0.8324) time: 0.1412 data: 0.0582 max mem: 9390 +Train: [26] [2600/6250] eta: 0:08:43 lr: 0.000110 grad: 0.0695 (0.0695) loss: 0.8398 (0.8325) time: 0.1263 data: 0.0414 max mem: 9390 +Train: [26] [2700/6250] eta: 0:08:28 lr: 0.000110 grad: 0.0657 (0.0694) loss: 0.8308 (0.8325) time: 0.1309 data: 0.0568 max mem: 9390 +Train: [26] [2800/6250] eta: 0:08:13 lr: 0.000110 grad: 0.0711 (0.0695) loss: 0.8300 (0.8325) time: 0.1377 data: 0.0584 max mem: 9390 +Train: [26] [2900/6250] eta: 0:07:58 lr: 0.000110 grad: 0.0688 (0.0694) loss: 0.8303 (0.8325) time: 0.1441 data: 0.0635 max mem: 9390 +Train: [26] [3000/6250] eta: 0:07:43 lr: 0.000110 grad: 0.0704 (0.0695) loss: 0.8284 (0.8325) time: 0.1539 data: 0.0717 max mem: 9390 +Train: [26] [3100/6250] eta: 0:07:28 lr: 0.000110 grad: 0.0669 (0.0695) loss: 0.8324 (0.8324) time: 0.1340 data: 0.0537 max mem: 9390 +Train: [26] [3200/6250] eta: 0:07:13 lr: 0.000110 grad: 0.0704 (0.0696) loss: 0.8289 (0.8323) time: 0.1004 data: 0.0257 max mem: 9390 +Train: [26] [3300/6250] eta: 0:06:59 lr: 0.000110 grad: 0.0675 (0.0696) loss: 0.8310 (0.8323) time: 0.1474 data: 0.0679 max mem: 9390 +Train: [26] [3400/6250] eta: 0:06:44 lr: 0.000110 grad: 0.0690 (0.0697) loss: 0.8327 (0.8321) time: 0.1484 data: 0.0722 max mem: 9390 +Train: [26] [3500/6250] eta: 0:06:29 lr: 0.000110 grad: 0.0695 (0.0697) loss: 0.8285 (0.8320) time: 0.1394 data: 0.0592 max mem: 9390 +Train: [26] [3600/6250] eta: 0:06:14 lr: 0.000110 grad: 0.0670 (0.0697) loss: 0.8265 (0.8319) time: 0.1328 data: 0.0439 max mem: 9390 +Train: [26] [3700/6250] eta: 0:06:00 lr: 0.000110 grad: 0.0663 (0.0698) loss: 0.8254 (0.8318) time: 0.1261 data: 0.0427 max mem: 9390 +Train: [26] [3800/6250] eta: 0:05:45 lr: 0.000110 grad: 0.0675 (0.0698) loss: 0.8259 (0.8317) time: 0.1264 data: 0.0440 max mem: 9390 +Train: [26] [3900/6250] eta: 0:05:30 lr: 0.000110 grad: 0.0685 (0.0698) loss: 0.8228 (0.8316) time: 0.1173 data: 0.0383 max mem: 9390 +Train: [26] [4000/6250] eta: 0:05:16 lr: 0.000110 grad: 0.0701 (0.0698) loss: 0.8247 (0.8315) time: 0.1479 data: 0.0715 max mem: 9390 +Train: [26] [4100/6250] eta: 0:05:01 lr: 0.000110 grad: 0.0664 (0.0699) loss: 0.8300 (0.8314) time: 0.1147 data: 0.0326 max mem: 9390 +Train: [26] [4200/6250] eta: 0:04:47 lr: 0.000110 grad: 0.0735 (0.0699) loss: 0.8298 (0.8313) time: 0.1520 data: 0.0742 max mem: 9390 +Train: [26] [4300/6250] eta: 0:04:33 lr: 0.000110 grad: 0.0682 (0.0700) loss: 0.8275 (0.8312) time: 0.1538 data: 0.0743 max mem: 9390 +Train: [26] [4400/6250] eta: 0:04:18 lr: 0.000110 grad: 0.0687 (0.0700) loss: 0.8295 (0.8312) time: 0.1286 data: 0.0419 max mem: 9390 +Train: [26] [4500/6250] eta: 0:04:04 lr: 0.000110 grad: 0.0754 (0.0700) loss: 0.8216 (0.8312) time: 0.1420 data: 0.0607 max mem: 9390 +Train: [26] [4600/6250] eta: 0:03:50 lr: 0.000110 grad: 0.0691 (0.0700) loss: 0.8279 (0.8312) time: 0.1244 data: 0.0429 max mem: 9390 +Train: [26] [4700/6250] eta: 0:03:36 lr: 0.000110 grad: 0.0716 (0.0701) loss: 0.8248 (0.8311) time: 0.1472 data: 0.0723 max mem: 9390 +Train: [26] [4800/6250] eta: 0:03:23 lr: 0.000109 grad: 0.0710 (0.0701) loss: 0.8285 (0.8311) time: 0.1471 data: 0.0668 max mem: 9390 +Train: [26] [4900/6250] eta: 0:03:09 lr: 0.000109 grad: 0.0715 (0.0701) loss: 0.8289 (0.8311) time: 0.1338 data: 0.0520 max mem: 9390 +Train: [26] [5000/6250] eta: 0:02:55 lr: 0.000109 grad: 0.0750 (0.0701) loss: 0.8272 (0.8311) time: 0.1380 data: 0.0603 max mem: 9390 +Train: [26] [5100/6250] eta: 0:02:41 lr: 0.000109 grad: 0.0715 (0.0701) loss: 0.8350 (0.8311) time: 0.1285 data: 0.0456 max mem: 9390 +Train: [26] [5200/6250] eta: 0:02:27 lr: 0.000109 grad: 0.0684 (0.0702) loss: 0.8296 (0.8311) time: 0.1492 data: 0.0717 max mem: 9390 +Train: [26] [5300/6250] eta: 0:02:13 lr: 0.000109 grad: 0.0639 (0.0702) loss: 0.8326 (0.8311) time: 0.1413 data: 0.0665 max mem: 9390 +Train: [26] [5400/6250] eta: 0:01:59 lr: 0.000109 grad: 0.0687 (0.0701) loss: 0.8348 (0.8311) time: 0.1376 data: 0.0594 max mem: 9390 +Train: [26] [5500/6250] eta: 0:01:45 lr: 0.000109 grad: 0.0699 (0.0701) loss: 0.8274 (0.8311) time: 0.1351 data: 0.0597 max mem: 9390 +Train: [26] [5600/6250] eta: 0:01:31 lr: 0.000109 grad: 0.0685 (0.0701) loss: 0.8297 (0.8312) time: 0.1415 data: 0.0628 max mem: 9390 +Train: [26] [5700/6250] eta: 0:01:17 lr: 0.000109 grad: 0.0713 (0.0701) loss: 0.8271 (0.8312) time: 0.1374 data: 0.0606 max mem: 9390 +Train: [26] [5800/6250] eta: 0:01:02 lr: 0.000109 grad: 0.0663 (0.0701) loss: 0.8377 (0.8312) time: 0.1273 data: 0.0410 max mem: 9390 +Train: [26] [5900/6250] eta: 0:00:48 lr: 0.000109 grad: 0.0690 (0.0701) loss: 0.8332 (0.8313) time: 0.1281 data: 0.0497 max mem: 9390 +Train: [26] [6000/6250] eta: 0:00:34 lr: 0.000109 grad: 0.0678 (0.0701) loss: 0.8310 (0.8313) time: 0.1526 data: 0.0721 max mem: 9390 +Train: [26] [6100/6250] eta: 0:00:20 lr: 0.000109 grad: 0.0649 (0.0701) loss: 0.8296 (0.8313) time: 0.1361 data: 0.0495 max mem: 9390 +Train: [26] [6200/6250] eta: 0:00:07 lr: 0.000109 grad: 0.0733 (0.0702) loss: 0.8305 (0.8314) time: 0.1814 data: 0.1033 max mem: 9390 +Train: [26] [6249/6250] eta: 0:00:00 lr: 0.000109 grad: 0.0688 (0.0702) loss: 0.8215 (0.8314) time: 0.1592 data: 0.0713 max mem: 9390 +Train: [26] Total time: 0:14:44 (0.1415 s / it) +Averaged stats: lr: 0.000109 grad: 0.0688 (0.0702) loss: 0.8215 (0.8314) +Eval (hcp-train-subset): [26] [ 0/62] eta: 0:04:41 loss: 0.8573 (0.8573) time: 4.5478 data: 4.5171 max mem: 9390 +Eval (hcp-train-subset): [26] [61/62] eta: 0:00:00 loss: 0.8455 (0.8445) time: 0.1317 data: 0.1070 max mem: 9390 +Eval (hcp-train-subset): [26] Total time: 0:00:13 (0.2229 s / it) +Averaged stats (hcp-train-subset): loss: 0.8455 (0.8445) +Eval (hcp-val): [26] [ 0/62] eta: 0:04:51 loss: 0.8392 (0.8392) time: 4.7066 data: 4.6761 max mem: 9390 +Eval (hcp-val): [26] [61/62] eta: 0:00:00 loss: 0.8392 (0.8409) time: 0.1194 data: 0.0925 max mem: 9390 +Eval (hcp-val): [26] Total time: 0:00:13 (0.2204 s / it) +Averaged stats (hcp-val): loss: 0.8392 (0.8409) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +Train: [27] [ 0/6250] eta: 8:27:39 lr: 0.000109 grad: 0.0500 (0.0500) loss: 0.8779 (0.8779) time: 4.8735 data: 4.6256 max mem: 9390 +Train: [27] [ 100/6250] eta: 0:20:23 lr: 0.000109 grad: 0.0673 (0.0767) loss: 0.8301 (0.8440) time: 0.1606 data: 0.0670 max mem: 9390 +Train: [27] [ 200/6250] eta: 0:17:36 lr: 0.000109 grad: 0.0653 (0.0730) loss: 0.8342 (0.8392) time: 0.1291 data: 0.0469 max mem: 9390 +Train: [27] [ 300/6250] eta: 0:16:15 lr: 0.000109 grad: 0.0668 (0.0728) loss: 0.8259 (0.8369) time: 0.1353 data: 0.0507 max mem: 9390 +Train: [27] [ 400/6250] eta: 0:15:33 lr: 0.000109 grad: 0.0625 (0.0719) loss: 0.8342 (0.8353) time: 0.1426 data: 0.0585 max mem: 9390 +Train: [27] [ 500/6250] eta: 0:14:52 lr: 0.000109 grad: 0.0627 (0.0709) loss: 0.8382 (0.8349) time: 0.1350 data: 0.0372 max mem: 9390 +Train: [27] [ 600/6250] eta: 0:14:18 lr: 0.000109 grad: 0.0682 (0.0706) loss: 0.8303 (0.8341) time: 0.1404 data: 0.0401 max mem: 9390 +Train: [27] [ 700/6250] eta: 0:13:58 lr: 0.000109 grad: 0.0667 (0.0703) loss: 0.8314 (0.8338) time: 0.1560 data: 0.0683 max mem: 9390 +Train: [27] [ 800/6250] eta: 0:13:43 lr: 0.000109 grad: 0.0638 (0.0698) loss: 0.8276 (0.8335) time: 0.1622 data: 0.0819 max mem: 9390 +Train: [27] [ 900/6250] eta: 0:13:23 lr: 0.000109 grad: 0.0664 (0.0695) loss: 0.8328 (0.8332) time: 0.1439 data: 0.0570 max mem: 9390 +Train: [27] [1000/6250] eta: 0:13:08 lr: 0.000109 grad: 0.0639 (0.0693) loss: 0.8355 (0.8332) time: 0.1492 data: 0.0687 max mem: 9390 +Train: [27] [1100/6250] eta: 0:12:51 lr: 0.000109 grad: 0.0707 (0.0694) loss: 0.8313 (0.8330) time: 0.1715 data: 0.0905 max mem: 9390 +Train: [27] [1200/6250] eta: 0:12:28 lr: 0.000109 grad: 0.0691 (0.0694) loss: 0.8346 (0.8329) time: 0.1211 data: 0.0411 max mem: 9390 +Train: [27] [1300/6250] eta: 0:12:12 lr: 0.000109 grad: 0.0704 (0.0696) loss: 0.8334 (0.8329) time: 0.1407 data: 0.0588 max mem: 9390 +Train: [27] [1400/6250] eta: 0:11:53 lr: 0.000109 grad: 0.0718 (0.0699) loss: 0.8272 (0.8327) time: 0.1225 data: 0.0401 max mem: 9390 +Train: [27] [1500/6250] eta: 0:11:35 lr: 0.000109 grad: 0.0710 (0.0701) loss: 0.8305 (0.8325) time: 0.1430 data: 0.0558 max mem: 9390 +Train: [27] [1600/6250] eta: 0:11:18 lr: 0.000109 grad: 0.0693 (0.0701) loss: 0.8324 (0.8325) time: 0.1224 data: 0.0400 max mem: 9390 +Train: [27] [1700/6250] eta: 0:11:00 lr: 0.000109 grad: 0.0758 (0.0701) loss: 0.8273 (0.8324) time: 0.1293 data: 0.0503 max mem: 9390 +Train: [27] [1800/6250] eta: 0:10:45 lr: 0.000109 grad: 0.0670 (0.0701) loss: 0.8308 (0.8324) time: 0.1403 data: 0.0601 max mem: 9390 +Train: [27] [1900/6250] eta: 0:10:29 lr: 0.000109 grad: 0.0734 (0.0703) loss: 0.8272 (0.8323) time: 0.1346 data: 0.0522 max mem: 9390 +Train: [27] [2000/6250] eta: 0:10:13 lr: 0.000109 grad: 0.0668 (0.0703) loss: 0.8331 (0.8323) time: 0.1268 data: 0.0450 max mem: 9390 +Train: [27] [2100/6250] eta: 0:09:55 lr: 0.000109 grad: 0.0674 (0.0703) loss: 0.8359 (0.8324) time: 0.1155 data: 0.0350 max mem: 9390 +Train: [27] [2200/6250] eta: 0:09:38 lr: 0.000109 grad: 0.0640 (0.0702) loss: 0.8320 (0.8324) time: 0.1362 data: 0.0570 max mem: 9390 +Train: [27] [2300/6250] eta: 0:09:23 lr: 0.000109 grad: 0.0700 (0.0703) loss: 0.8299 (0.8324) time: 0.1369 data: 0.0613 max mem: 9390 +Train: [27] [2400/6250] eta: 0:09:07 lr: 0.000109 grad: 0.0691 (0.0702) loss: 0.8297 (0.8325) time: 0.1297 data: 0.0447 max mem: 9390 +Train: [27] [2500/6250] eta: 0:08:52 lr: 0.000109 grad: 0.0642 (0.0702) loss: 0.8374 (0.8326) time: 0.1365 data: 0.0562 max mem: 9390 +Train: [27] [2600/6250] eta: 0:08:36 lr: 0.000109 grad: 0.0697 (0.0703) loss: 0.8280 (0.8326) time: 0.1300 data: 0.0452 max mem: 9390 +Train: [27] [2700/6250] eta: 0:08:22 lr: 0.000109 grad: 0.0684 (0.0702) loss: 0.8319 (0.8326) time: 0.1507 data: 0.0671 max mem: 9390 +Train: [27] [2800/6250] eta: 0:08:07 lr: 0.000109 grad: 0.0711 (0.0703) loss: 0.8315 (0.8326) time: 0.1300 data: 0.0443 max mem: 9390 +Train: [27] [2900/6250] eta: 0:07:52 lr: 0.000109 grad: 0.0684 (0.0703) loss: 0.8286 (0.8326) time: 0.1362 data: 0.0513 max mem: 9390 +Train: [27] [3000/6250] eta: 0:07:38 lr: 0.000109 grad: 0.0741 (0.0704) loss: 0.8278 (0.8326) time: 0.1241 data: 0.0417 max mem: 9390 +Train: [27] [3100/6250] eta: 0:07:23 lr: 0.000108 grad: 0.0705 (0.0705) loss: 0.8276 (0.8325) time: 0.1320 data: 0.0541 max mem: 9390 +Train: [27] [3200/6250] eta: 0:07:10 lr: 0.000108 grad: 0.0742 (0.0706) loss: 0.8267 (0.8325) time: 0.1240 data: 0.0376 max mem: 9390 +Train: [27] [3300/6250] eta: 0:06:55 lr: 0.000108 grad: 0.0754 (0.0707) loss: 0.8260 (0.8324) time: 0.1202 data: 0.0308 max mem: 9390 +Train: [27] [3400/6250] eta: 0:06:41 lr: 0.000108 grad: 0.0687 (0.0707) loss: 0.8306 (0.8323) time: 0.1258 data: 0.0450 max mem: 9390 +Train: [27] [3500/6250] eta: 0:06:26 lr: 0.000108 grad: 0.0653 (0.0707) loss: 0.8373 (0.8324) time: 0.1484 data: 0.0739 max mem: 9390 +Train: [27] [3600/6250] eta: 0:06:12 lr: 0.000108 grad: 0.0679 (0.0708) loss: 0.8279 (0.8323) time: 0.1445 data: 0.0627 max mem: 9390 +Train: [27] [3700/6250] eta: 0:05:58 lr: 0.000108 grad: 0.0730 (0.0708) loss: 0.8327 (0.8322) time: 0.1228 data: 0.0387 max mem: 9390 +Train: [27] [3800/6250] eta: 0:05:44 lr: 0.000108 grad: 0.0729 (0.0709) loss: 0.8297 (0.8322) time: 0.1377 data: 0.0520 max mem: 9390 +Train: [27] [3900/6250] eta: 0:05:30 lr: 0.000108 grad: 0.0707 (0.0709) loss: 0.8291 (0.8322) time: 0.1413 data: 0.0636 max mem: 9390 +Train: [27] [4000/6250] eta: 0:05:15 lr: 0.000108 grad: 0.0687 (0.0709) loss: 0.8259 (0.8321) time: 0.1449 data: 0.0667 max mem: 9390 +Train: [27] [4100/6250] eta: 0:05:01 lr: 0.000108 grad: 0.0711 (0.0710) loss: 0.8301 (0.8321) time: 0.1370 data: 0.0600 max mem: 9390 +Train: [27] [4200/6250] eta: 0:04:47 lr: 0.000108 grad: 0.0721 (0.0711) loss: 0.8300 (0.8320) time: 0.1598 data: 0.0858 max mem: 9390 +Train: [27] [4300/6250] eta: 0:04:33 lr: 0.000108 grad: 0.0647 (0.0711) loss: 0.8323 (0.8320) time: 0.1153 data: 0.0327 max mem: 9390 +Train: [27] [4400/6250] eta: 0:04:19 lr: 0.000108 grad: 0.0671 (0.0711) loss: 0.8343 (0.8320) time: 0.1353 data: 0.0500 max mem: 9390 +Train: [27] [4500/6250] eta: 0:04:05 lr: 0.000108 grad: 0.0672 (0.0711) loss: 0.8289 (0.8319) time: 0.1092 data: 0.0313 max mem: 9390 +Train: [27] [4600/6250] eta: 0:03:52 lr: 0.000108 grad: 0.0743 (0.0711) loss: 0.8320 (0.8319) time: 0.1490 data: 0.0640 max mem: 9390 +Train: [27] [4700/6250] eta: 0:03:38 lr: 0.000108 grad: 0.0715 (0.0712) loss: 0.8302 (0.8319) time: 0.1380 data: 0.0592 max mem: 9390 +Train: [27] [4800/6250] eta: 0:03:24 lr: 0.000108 grad: 0.0699 (0.0712) loss: 0.8325 (0.8318) time: 0.1379 data: 0.0557 max mem: 9390 +Train: [27] [4900/6250] eta: 0:03:10 lr: 0.000108 grad: 0.0680 (0.0712) loss: 0.8355 (0.8318) time: 0.1450 data: 0.0592 max mem: 9390 +Train: [27] [5000/6250] eta: 0:02:56 lr: 0.000108 grad: 0.0739 (0.0712) loss: 0.8301 (0.8318) time: 0.1460 data: 0.0637 max mem: 9390 +Train: [27] [5100/6250] eta: 0:02:42 lr: 0.000108 grad: 0.0686 (0.0712) loss: 0.8359 (0.8317) time: 0.1306 data: 0.0449 max mem: 9390 +Train: [27] [5200/6250] eta: 0:02:28 lr: 0.000108 grad: 0.0659 (0.0712) loss: 0.8312 (0.8317) time: 0.1487 data: 0.0654 max mem: 9390 +Train: [27] [5300/6250] eta: 0:02:14 lr: 0.000108 grad: 0.0725 (0.0712) loss: 0.8305 (0.8317) time: 0.1567 data: 0.0721 max mem: 9390 +Train: [27] [5400/6250] eta: 0:02:00 lr: 0.000108 grad: 0.0678 (0.0713) loss: 0.8369 (0.8317) time: 0.1109 data: 0.0304 max mem: 9390 +Train: [27] [5500/6250] eta: 0:01:46 lr: 0.000108 grad: 0.0732 (0.0713) loss: 0.8265 (0.8316) time: 0.1461 data: 0.0599 max mem: 9390 +Train: [27] [5600/6250] eta: 0:01:31 lr: 0.000108 grad: 0.0710 (0.0713) loss: 0.8296 (0.8315) time: 0.1330 data: 0.0525 max mem: 9390 +Train: [27] [5700/6250] eta: 0:01:17 lr: 0.000108 grad: 0.0686 (0.0714) loss: 0.8309 (0.8315) time: 0.1502 data: 0.0725 max mem: 9390 +Train: [27] [5800/6250] eta: 0:01:03 lr: 0.000108 grad: 0.0697 (0.0714) loss: 0.8295 (0.8316) time: 0.1222 data: 0.0412 max mem: 9390 +Train: [27] [5900/6250] eta: 0:00:49 lr: 0.000108 grad: 0.0693 (0.0713) loss: 0.8301 (0.8316) time: 0.1466 data: 0.0714 max mem: 9390 +Train: [27] [6000/6250] eta: 0:00:35 lr: 0.000108 grad: 0.0679 (0.0713) loss: 0.8293 (0.8316) time: 0.1364 data: 0.0563 max mem: 9390 +Train: [27] [6100/6250] eta: 0:00:21 lr: 0.000108 grad: 0.0662 (0.0713) loss: 0.8372 (0.8316) time: 0.1457 data: 0.0643 max mem: 9390 +Train: [27] [6200/6250] eta: 0:00:07 lr: 0.000108 grad: 0.0674 (0.0713) loss: 0.8334 (0.8316) time: 0.1615 data: 0.0740 max mem: 9390 +Train: [27] [6249/6250] eta: 0:00:00 lr: 0.000108 grad: 0.0772 (0.0713) loss: 0.8278 (0.8316) time: 0.1788 data: 0.0986 max mem: 9390 +Train: [27] Total time: 0:14:53 (0.1430 s / it) +Averaged stats: lr: 0.000108 grad: 0.0772 (0.0713) loss: 0.8278 (0.8316) +Eval (hcp-train-subset): [27] [ 0/62] eta: 0:03:51 loss: 0.8504 (0.8504) time: 3.7331 data: 3.6564 max mem: 9390 +Eval (hcp-train-subset): [27] [61/62] eta: 0:00:00 loss: 0.8406 (0.8421) time: 0.1241 data: 0.0979 max mem: 9390 +Eval (hcp-train-subset): [27] Total time: 0:00:12 (0.2091 s / it) +Averaged stats (hcp-train-subset): loss: 0.8406 (0.8421) +Eval (hcp-val): [27] [ 0/62] eta: 0:03:27 loss: 0.8357 (0.8357) time: 3.3475 data: 3.2943 max mem: 9390 +Eval (hcp-val): [27] [61/62] eta: 0:00:00 loss: 0.8399 (0.8401) time: 0.1224 data: 0.0975 max mem: 9390 +Eval (hcp-val): [27] Total time: 0:00:13 (0.2100 s / it) +Averaged stats (hcp-val): loss: 0.8399 (0.8401) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +Train: [28] [ 0/6250] eta: 7:43:14 lr: 0.000108 grad: 0.0513 (0.0513) loss: 0.8595 (0.8595) time: 4.4471 data: 4.2588 max mem: 9390 +Train: [28] [ 100/6250] eta: 0:20:02 lr: 0.000108 grad: 0.0684 (0.0874) loss: 0.8217 (0.8318) time: 0.1470 data: 0.0593 max mem: 9390 +Train: [28] [ 200/6250] eta: 0:17:33 lr: 0.000108 grad: 0.0765 (0.0837) loss: 0.8240 (0.8272) time: 0.1358 data: 0.0504 max mem: 9390 +Train: [28] [ 300/6250] eta: 0:16:22 lr: 0.000108 grad: 0.0693 (0.0808) loss: 0.8291 (0.8265) time: 0.1410 data: 0.0510 max mem: 9390 +Train: [28] [ 400/6250] eta: 0:15:22 lr: 0.000108 grad: 0.0694 (0.0788) loss: 0.8349 (0.8268) time: 0.1354 data: 0.0531 max mem: 9390 +Train: [28] [ 500/6250] eta: 0:14:46 lr: 0.000108 grad: 0.0686 (0.0774) loss: 0.8266 (0.8269) time: 0.1426 data: 0.0606 max mem: 9390 +Train: [28] [ 600/6250] eta: 0:14:11 lr: 0.000108 grad: 0.0688 (0.0764) loss: 0.8366 (0.8276) time: 0.1352 data: 0.0396 max mem: 9390 +Train: [28] [ 700/6250] eta: 0:13:44 lr: 0.000108 grad: 0.0635 (0.0756) loss: 0.8300 (0.8278) time: 0.1539 data: 0.0698 max mem: 9390 +Train: [28] [ 800/6250] eta: 0:13:22 lr: 0.000108 grad: 0.0695 (0.0751) loss: 0.8260 (0.8278) time: 0.1143 data: 0.0304 max mem: 9390 +Train: [28] [ 900/6250] eta: 0:13:12 lr: 0.000108 grad: 0.0666 (0.0743) loss: 0.8242 (0.8281) time: 0.1617 data: 0.0742 max mem: 9390 +Train: [28] [1000/6250] eta: 0:12:57 lr: 0.000108 grad: 0.0596 (0.0736) loss: 0.8344 (0.8284) time: 0.1301 data: 0.0484 max mem: 9390 +Train: [28] [1100/6250] eta: 0:12:44 lr: 0.000108 grad: 0.0652 (0.0730) loss: 0.8319 (0.8288) time: 0.1409 data: 0.0616 max mem: 9390 +Train: [28] [1200/6250] eta: 0:12:37 lr: 0.000108 grad: 0.0703 (0.0728) loss: 0.8211 (0.8288) time: 0.1340 data: 0.0549 max mem: 9390 +Train: [28] [1300/6250] eta: 0:12:19 lr: 0.000107 grad: 0.0656 (0.0728) loss: 0.8323 (0.8289) time: 0.1246 data: 0.0410 max mem: 9390 +Train: [28] [1400/6250] eta: 0:12:01 lr: 0.000107 grad: 0.0681 (0.0725) loss: 0.8287 (0.8290) time: 0.1180 data: 0.0348 max mem: 9390 +Train: [28] [1500/6250] eta: 0:11:44 lr: 0.000107 grad: 0.0731 (0.0723) loss: 0.8212 (0.8291) time: 0.1340 data: 0.0560 max mem: 9390 +Train: [28] [1600/6250] eta: 0:11:28 lr: 0.000107 grad: 0.0668 (0.0721) loss: 0.8306 (0.8293) time: 0.1372 data: 0.0534 max mem: 9390 +Train: [28] [1700/6250] eta: 0:11:12 lr: 0.000107 grad: 0.0687 (0.0720) loss: 0.8321 (0.8294) time: 0.1514 data: 0.0710 max mem: 9390 +Train: [28] [1800/6250] eta: 0:10:55 lr: 0.000107 grad: 0.0692 (0.0720) loss: 0.8298 (0.8295) time: 0.1436 data: 0.0613 max mem: 9390 +Train: [28] [1900/6250] eta: 0:10:40 lr: 0.000107 grad: 0.0645 (0.0718) loss: 0.8271 (0.8296) time: 0.1403 data: 0.0612 max mem: 9390 +Train: [28] [2000/6250] eta: 0:10:25 lr: 0.000107 grad: 0.0653 (0.0716) loss: 0.8299 (0.8298) time: 0.1352 data: 0.0505 max mem: 9390 +Train: [28] [2100/6250] eta: 0:10:10 lr: 0.000107 grad: 0.0717 (0.0715) loss: 0.8292 (0.8299) time: 0.1576 data: 0.0783 max mem: 9390 +Train: [28] [2200/6250] eta: 0:09:59 lr: 0.000107 grad: 0.0706 (0.0714) loss: 0.8356 (0.8301) time: 0.1435 data: 0.0623 max mem: 9390 +Train: [28] [2300/6250] eta: 0:09:43 lr: 0.000107 grad: 0.0667 (0.0714) loss: 0.8310 (0.8302) time: 0.1481 data: 0.0719 max mem: 9390 +Train: [28] [2400/6250] eta: 0:09:28 lr: 0.000107 grad: 0.0672 (0.0714) loss: 0.8324 (0.8302) time: 0.1497 data: 0.0734 max mem: 9390 +Train: [28] [2500/6250] eta: 0:09:12 lr: 0.000107 grad: 0.0651 (0.0713) loss: 0.8334 (0.8303) time: 0.1319 data: 0.0482 max mem: 9390 +Train: [28] [2600/6250] eta: 0:08:57 lr: 0.000107 grad: 0.0669 (0.0713) loss: 0.8328 (0.8303) time: 0.1476 data: 0.0709 max mem: 9390 +Train: [28] [2700/6250] eta: 0:08:41 lr: 0.000107 grad: 0.0632 (0.0712) loss: 0.8354 (0.8304) time: 0.1382 data: 0.0604 max mem: 9390 +Train: [28] [2800/6250] eta: 0:08:27 lr: 0.000107 grad: 0.0656 (0.0712) loss: 0.8273 (0.8305) time: 0.1763 data: 0.0968 max mem: 9390 +Train: [28] [2900/6250] eta: 0:08:11 lr: 0.000107 grad: 0.0664 (0.0712) loss: 0.8330 (0.8306) time: 0.1682 data: 0.0934 max mem: 9390 +Train: [28] [3000/6250] eta: 0:07:56 lr: 0.000107 grad: 0.0711 (0.0713) loss: 0.8292 (0.8306) time: 0.1513 data: 0.0716 max mem: 9390 +Train: [28] [3100/6250] eta: 0:07:40 lr: 0.000107 grad: 0.0675 (0.0713) loss: 0.8371 (0.8307) time: 0.1331 data: 0.0506 max mem: 9390 +Train: [28] [3200/6250] eta: 0:07:25 lr: 0.000107 grad: 0.0656 (0.0712) loss: 0.8381 (0.8307) time: 0.1386 data: 0.0590 max mem: 9390 +Train: [28] [3300/6250] eta: 0:07:10 lr: 0.000107 grad: 0.0711 (0.0712) loss: 0.8311 (0.8308) time: 0.1410 data: 0.0645 max mem: 9390 +Train: [28] [3400/6250] eta: 0:06:55 lr: 0.000107 grad: 0.0688 (0.0713) loss: 0.8323 (0.8308) time: 0.1406 data: 0.0646 max mem: 9390 +Train: [28] [3500/6250] eta: 0:06:40 lr: 0.000107 grad: 0.0710 (0.0713) loss: 0.8313 (0.8308) time: 0.1587 data: 0.0799 max mem: 9390 +Train: [28] [3600/6250] eta: 0:06:26 lr: 0.000107 grad: 0.0693 (0.0714) loss: 0.8340 (0.8308) time: 0.1589 data: 0.0691 max mem: 9390 +Train: [28] [3700/6250] eta: 0:06:10 lr: 0.000107 grad: 0.0707 (0.0714) loss: 0.8289 (0.8308) time: 0.1322 data: 0.0546 max mem: 9390 +Train: [28] [3800/6250] eta: 0:05:55 lr: 0.000107 grad: 0.0765 (0.0716) loss: 0.8304 (0.8307) time: 0.1341 data: 0.0557 max mem: 9390 +Train: [28] [3900/6250] eta: 0:05:40 lr: 0.000107 grad: 0.0718 (0.0716) loss: 0.8352 (0.8307) time: 0.1333 data: 0.0576 max mem: 9390 +Train: [28] [4000/6250] eta: 0:05:25 lr: 0.000107 grad: 0.0705 (0.0717) loss: 0.8306 (0.8307) time: 0.1401 data: 0.0618 max mem: 9390 +Train: [28] [4100/6250] eta: 0:05:10 lr: 0.000107 grad: 0.0712 (0.0718) loss: 0.8279 (0.8308) time: 0.1300 data: 0.0449 max mem: 9390 +Train: [28] [4200/6250] eta: 0:04:56 lr: 0.000107 grad: 0.0705 (0.0718) loss: 0.8287 (0.8307) time: 0.1572 data: 0.0754 max mem: 9390 +Train: [28] [4300/6250] eta: 0:04:41 lr: 0.000107 grad: 0.0757 (0.0718) loss: 0.8287 (0.8307) time: 0.1425 data: 0.0535 max mem: 9390 +Train: [28] [4400/6250] eta: 0:04:27 lr: 0.000107 grad: 0.0697 (0.0718) loss: 0.8362 (0.8307) time: 0.1420 data: 0.0654 max mem: 9390 +Train: [28] [4500/6250] eta: 0:04:13 lr: 0.000107 grad: 0.0747 (0.0719) loss: 0.8300 (0.8307) time: 0.1520 data: 0.0727 max mem: 9390 +Train: [28] [4600/6250] eta: 0:03:58 lr: 0.000107 grad: 0.0675 (0.0718) loss: 0.8314 (0.8307) time: 0.1500 data: 0.0696 max mem: 9390 +Train: [28] [4700/6250] eta: 0:03:44 lr: 0.000107 grad: 0.0679 (0.0718) loss: 0.8303 (0.8307) time: 0.1317 data: 0.0537 max mem: 9390 +Train: [28] [4800/6250] eta: 0:03:30 lr: 0.000107 grad: 0.0661 (0.0718) loss: 0.8320 (0.8307) time: 0.1925 data: 0.1073 max mem: 9390 +Train: [28] [4900/6250] eta: 0:03:16 lr: 0.000107 grad: 0.0668 (0.0717) loss: 0.8250 (0.8307) time: 0.1517 data: 0.0768 max mem: 9390 +Train: [28] [5000/6250] eta: 0:03:01 lr: 0.000107 grad: 0.0694 (0.0718) loss: 0.8300 (0.8307) time: 0.1673 data: 0.0867 max mem: 9390 +Train: [28] [5100/6250] eta: 0:02:47 lr: 0.000107 grad: 0.0683 (0.0717) loss: 0.8292 (0.8307) time: 0.1194 data: 0.0312 max mem: 9390 +Train: [28] [5200/6250] eta: 0:02:32 lr: 0.000107 grad: 0.0683 (0.0718) loss: 0.8355 (0.8307) time: 0.1314 data: 0.0470 max mem: 9390 +Train: [28] [5300/6250] eta: 0:02:18 lr: 0.000107 grad: 0.0668 (0.0717) loss: 0.8308 (0.8306) time: 0.1644 data: 0.0866 max mem: 9390 +Train: [28] [5400/6250] eta: 0:02:03 lr: 0.000107 grad: 0.0713 (0.0717) loss: 0.8310 (0.8306) time: 0.1685 data: 0.0897 max mem: 9390 +Train: [28] [5500/6250] eta: 0:01:49 lr: 0.000107 grad: 0.0668 (0.0717) loss: 0.8312 (0.8307) time: 0.1570 data: 0.0771 max mem: 9390 +Train: [28] [5600/6250] eta: 0:01:34 lr: 0.000106 grad: 0.0689 (0.0716) loss: 0.8386 (0.8307) time: 0.1555 data: 0.0785 max mem: 9390 +Train: [28] [5700/6250] eta: 0:01:20 lr: 0.000106 grad: 0.0708 (0.0716) loss: 0.8315 (0.8307) time: 0.1322 data: 0.0508 max mem: 9390 +Train: [28] [5800/6250] eta: 0:01:05 lr: 0.000106 grad: 0.0679 (0.0716) loss: 0.8339 (0.8307) time: 0.1428 data: 0.0666 max mem: 9390 +Train: [28] [5900/6250] eta: 0:00:50 lr: 0.000106 grad: 0.0646 (0.0716) loss: 0.8323 (0.8307) time: 0.1259 data: 0.0428 max mem: 9390 +Train: [28] [6000/6250] eta: 0:00:36 lr: 0.000106 grad: 0.0698 (0.0716) loss: 0.8303 (0.8308) time: 0.1277 data: 0.0447 max mem: 9390 +Train: [28] [6100/6250] eta: 0:00:21 lr: 0.000106 grad: 0.0674 (0.0717) loss: 0.8361 (0.8308) time: 0.1383 data: 0.0600 max mem: 9390 +Train: [28] [6200/6250] eta: 0:00:07 lr: 0.000106 grad: 0.0671 (0.0716) loss: 0.8366 (0.8308) time: 0.1630 data: 0.0877 max mem: 9390 +Train: [28] [6249/6250] eta: 0:00:00 lr: 0.000106 grad: 0.0726 (0.0716) loss: 0.8296 (0.8308) time: 0.1710 data: 0.0907 max mem: 9390 +Train: [28] Total time: 0:15:11 (0.1458 s / it) +Averaged stats: lr: 0.000106 grad: 0.0726 (0.0716) loss: 0.8296 (0.8308) +Eval (hcp-train-subset): [28] [ 0/62] eta: 0:04:25 loss: 0.8554 (0.8554) time: 4.2882 data: 4.2550 max mem: 9390 +Eval (hcp-train-subset): [28] [61/62] eta: 0:00:00 loss: 0.8428 (0.8433) time: 0.1058 data: 0.0804 max mem: 9390 +Eval (hcp-train-subset): [28] Total time: 0:00:13 (0.2117 s / it) +Averaged stats (hcp-train-subset): loss: 0.8428 (0.8433) +Eval (hcp-val): [28] [ 0/62] eta: 0:02:54 loss: 0.8361 (0.8361) time: 2.8087 data: 2.7464 max mem: 9390 +Eval (hcp-val): [28] [61/62] eta: 0:00:00 loss: 0.8389 (0.8400) time: 0.1213 data: 0.0968 max mem: 9390 +Eval (hcp-val): [28] Total time: 0:00:12 (0.2050 s / it) +Averaged stats (hcp-val): loss: 0.8389 (0.8400) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +Train: [29] [ 0/6250] eta: 6:42:11 lr: 0.000106 grad: 0.1717 (0.1717) loss: 0.8141 (0.8141) time: 3.8610 data: 3.6169 max mem: 9390 +Train: [29] [ 100/6250] eta: 0:19:44 lr: 0.000106 grad: 0.0768 (0.0905) loss: 0.8182 (0.8286) time: 0.1409 data: 0.0501 max mem: 9390 +Train: [29] [ 200/6250] eta: 0:17:07 lr: 0.000106 grad: 0.0653 (0.0812) loss: 0.8341 (0.8311) time: 0.1451 data: 0.0614 max mem: 9390 +Train: [29] [ 300/6250] eta: 0:15:43 lr: 0.000106 grad: 0.0657 (0.0771) loss: 0.8334 (0.8310) time: 0.1133 data: 0.0310 max mem: 9390 +Train: [29] [ 400/6250] eta: 0:14:52 lr: 0.000106 grad: 0.0665 (0.0749) loss: 0.8300 (0.8307) time: 0.1201 data: 0.0286 max mem: 9390 +Train: [29] [ 500/6250] eta: 0:14:09 lr: 0.000106 grad: 0.0746 (0.0740) loss: 0.8312 (0.8308) time: 0.1257 data: 0.0310 max mem: 9390 +Train: [29] [ 600/6250] eta: 0:13:40 lr: 0.000106 grad: 0.0686 (0.0734) loss: 0.8292 (0.8308) time: 0.1405 data: 0.0529 max mem: 9390 +Train: [29] [ 700/6250] eta: 0:13:08 lr: 0.000106 grad: 0.0667 (0.0729) loss: 0.8251 (0.8307) time: 0.1181 data: 0.0303 max mem: 9390 +Train: [29] [ 800/6250] eta: 0:12:55 lr: 0.000106 grad: 0.0653 (0.0723) loss: 0.8365 (0.8311) time: 0.1465 data: 0.0602 max mem: 9390 +Train: [29] [ 900/6250] eta: 0:12:45 lr: 0.000106 grad: 0.0688 (0.0718) loss: 0.8348 (0.8314) time: 0.1563 data: 0.0715 max mem: 9390 +Train: [29] [1000/6250] eta: 0:12:32 lr: 0.000106 grad: 0.0668 (0.0716) loss: 0.8349 (0.8317) time: 0.1458 data: 0.0676 max mem: 9390 +Train: [29] [1100/6250] eta: 0:12:17 lr: 0.000106 grad: 0.0670 (0.0714) loss: 0.8334 (0.8318) time: 0.1508 data: 0.0704 max mem: 9390 +Train: [29] [1200/6250] eta: 0:12:03 lr: 0.000106 grad: 0.0685 (0.0714) loss: 0.8300 (0.8318) time: 0.1403 data: 0.0616 max mem: 9390 +Train: [29] [1300/6250] eta: 0:11:47 lr: 0.000106 grad: 0.0687 (0.0712) loss: 0.8258 (0.8319) time: 0.1425 data: 0.0598 max mem: 9390 +Train: [29] [1400/6250] eta: 0:11:32 lr: 0.000106 grad: 0.0684 (0.0711) loss: 0.8286 (0.8319) time: 0.0963 data: 0.0136 max mem: 9390 +Train: [29] [1500/6250] eta: 0:11:18 lr: 0.000106 grad: 0.0658 (0.0710) loss: 0.8344 (0.8319) time: 0.1406 data: 0.0606 max mem: 9390 +Train: [29] [1600/6250] eta: 0:11:04 lr: 0.000106 grad: 0.0622 (0.0709) loss: 0.8304 (0.8319) time: 0.1267 data: 0.0462 max mem: 9390 +Train: [29] [1700/6250] eta: 0:10:48 lr: 0.000106 grad: 0.0689 (0.0711) loss: 0.8324 (0.8321) time: 0.1506 data: 0.0777 max mem: 9390 +Train: [29] [1800/6250] eta: 0:10:33 lr: 0.000106 grad: 0.0633 (0.0709) loss: 0.8267 (0.8321) time: 0.1297 data: 0.0504 max mem: 9390 +Train: [29] [1900/6250] eta: 0:10:21 lr: 0.000106 grad: 0.0648 (0.0708) loss: 0.8292 (0.8321) time: 0.0964 data: 0.0180 max mem: 9390 +Train: [29] [2000/6250] eta: 0:10:06 lr: 0.000106 grad: 0.0653 (0.0707) loss: 0.8298 (0.8321) time: 0.1448 data: 0.0672 max mem: 9390 +Train: [29] [2100/6250] eta: 0:09:52 lr: 0.000106 grad: 0.0677 (0.0706) loss: 0.8338 (0.8321) time: 0.1458 data: 0.0650 max mem: 9390 +Train: [29] [2200/6250] eta: 0:09:40 lr: 0.000106 grad: 0.0672 (0.0705) loss: 0.8306 (0.8321) time: 0.0976 data: 0.0076 max mem: 9390 +Train: [29] [2300/6250] eta: 0:09:31 lr: 0.000106 grad: 0.0684 (0.0704) loss: 0.8343 (0.8321) time: 0.1885 data: 0.1105 max mem: 9390 +Train: [29] [2400/6250] eta: 0:09:18 lr: 0.000106 grad: 0.0646 (0.0703) loss: 0.8334 (0.8322) time: 0.1513 data: 0.0717 max mem: 9390 +Train: [29] [2500/6250] eta: 0:09:02 lr: 0.000106 grad: 0.0652 (0.0701) loss: 0.8344 (0.8323) time: 0.1415 data: 0.0672 max mem: 9390 +Train: [29] [2600/6250] eta: 0:08:47 lr: 0.000106 grad: 0.0620 (0.0700) loss: 0.8344 (0.8323) time: 0.1433 data: 0.0635 max mem: 9390 +Train: [29] [2700/6250] eta: 0:08:33 lr: 0.000106 grad: 0.0595 (0.0698) loss: 0.8410 (0.8324) time: 0.1496 data: 0.0701 max mem: 9390 +Train: [29] [2800/6250] eta: 0:08:19 lr: 0.000106 grad: 0.0661 (0.0698) loss: 0.8353 (0.8325) time: 0.1391 data: 0.0590 max mem: 9390 +Train: [29] [2900/6250] eta: 0:08:05 lr: 0.000106 grad: 0.0616 (0.0696) loss: 0.8400 (0.8326) time: 0.1509 data: 0.0626 max mem: 9390 +Train: [29] [3000/6250] eta: 0:07:52 lr: 0.000106 grad: 0.0644 (0.0696) loss: 0.8315 (0.8327) time: 0.1180 data: 0.0246 max mem: 9390 +Train: [29] [3100/6250] eta: 0:07:40 lr: 0.000106 grad: 0.0673 (0.0695) loss: 0.8342 (0.8328) time: 0.1861 data: 0.1011 max mem: 9390 +Train: [29] [3200/6250] eta: 0:07:24 lr: 0.000106 grad: 0.0654 (0.0695) loss: 0.8346 (0.8329) time: 0.1061 data: 0.0249 max mem: 9390 +Train: [29] [3300/6250] eta: 0:07:09 lr: 0.000106 grad: 0.0658 (0.0695) loss: 0.8375 (0.8329) time: 0.1382 data: 0.0623 max mem: 9390 +Train: [29] [3400/6250] eta: 0:06:55 lr: 0.000106 grad: 0.0676 (0.0695) loss: 0.8274 (0.8329) time: 0.1351 data: 0.0551 max mem: 9390 +Train: [29] [3500/6250] eta: 0:06:40 lr: 0.000105 grad: 0.0654 (0.0695) loss: 0.8347 (0.8330) time: 0.1324 data: 0.0478 max mem: 9390 +Train: [29] [3600/6250] eta: 0:06:24 lr: 0.000105 grad: 0.0706 (0.0695) loss: 0.8281 (0.8329) time: 0.1358 data: 0.0566 max mem: 9390 +Train: [29] [3700/6250] eta: 0:06:09 lr: 0.000105 grad: 0.0644 (0.0695) loss: 0.8336 (0.8329) time: 0.1575 data: 0.0766 max mem: 9390 +Train: [29] [3800/6250] eta: 0:05:54 lr: 0.000105 grad: 0.0676 (0.0695) loss: 0.8359 (0.8329) time: 0.1431 data: 0.0592 max mem: 9390 +Train: [29] [3900/6250] eta: 0:05:39 lr: 0.000105 grad: 0.0700 (0.0695) loss: 0.8329 (0.8329) time: 0.1331 data: 0.0546 max mem: 9390 +Train: [29] [4000/6250] eta: 0:05:24 lr: 0.000105 grad: 0.0672 (0.0694) loss: 0.8309 (0.8330) time: 0.1396 data: 0.0640 max mem: 9390 +Train: [29] [4100/6250] eta: 0:05:10 lr: 0.000105 grad: 0.0693 (0.0694) loss: 0.8325 (0.8330) time: 0.1263 data: 0.0447 max mem: 9390 +Train: [29] [4200/6250] eta: 0:04:56 lr: 0.000105 grad: 0.0644 (0.0695) loss: 0.8345 (0.8330) time: 0.1495 data: 0.0650 max mem: 9390 +Train: [29] [4300/6250] eta: 0:04:41 lr: 0.000105 grad: 0.0700 (0.0695) loss: 0.8316 (0.8330) time: 0.1333 data: 0.0534 max mem: 9390 +Train: [29] [4400/6250] eta: 0:04:28 lr: 0.000105 grad: 0.0708 (0.0696) loss: 0.8271 (0.8330) time: 0.2717 data: 0.1958 max mem: 9390 +Train: [29] [4500/6250] eta: 0:04:13 lr: 0.000105 grad: 0.0695 (0.0696) loss: 0.8352 (0.8330) time: 0.1972 data: 0.1211 max mem: 9390 +Train: [29] [4600/6250] eta: 0:03:58 lr: 0.000105 grad: 0.0699 (0.0696) loss: 0.8312 (0.8330) time: 0.1246 data: 0.0419 max mem: 9390 +Train: [29] [4700/6250] eta: 0:03:44 lr: 0.000105 grad: 0.0736 (0.0696) loss: 0.8282 (0.8329) time: 0.1378 data: 0.0597 max mem: 9390 +Train: [29] [4800/6250] eta: 0:03:29 lr: 0.000105 grad: 0.0672 (0.0696) loss: 0.8270 (0.8328) time: 0.1525 data: 0.0685 max mem: 9390 +Train: [29] [4900/6250] eta: 0:03:15 lr: 0.000105 grad: 0.0657 (0.0696) loss: 0.8333 (0.8328) time: 0.2011 data: 0.1181 max mem: 9390 +Train: [29] [5000/6250] eta: 0:03:01 lr: 0.000105 grad: 0.0708 (0.0697) loss: 0.8299 (0.8327) time: 0.1511 data: 0.0733 max mem: 9390 +Train: [29] [5100/6250] eta: 0:02:46 lr: 0.000105 grad: 0.0733 (0.0697) loss: 0.8285 (0.8327) time: 0.1232 data: 0.0423 max mem: 9390 +Train: [29] [5200/6250] eta: 0:02:31 lr: 0.000105 grad: 0.0703 (0.0698) loss: 0.8274 (0.8326) time: 0.1218 data: 0.0397 max mem: 9390 +Train: [29] [5300/6250] eta: 0:02:17 lr: 0.000105 grad: 0.0711 (0.0698) loss: 0.8331 (0.8325) time: 0.1479 data: 0.0679 max mem: 9390 +Train: [29] [5400/6250] eta: 0:02:02 lr: 0.000105 grad: 0.0712 (0.0699) loss: 0.8274 (0.8325) time: 0.1302 data: 0.0489 max mem: 9390 +Train: [29] [5500/6250] eta: 0:01:48 lr: 0.000105 grad: 0.0727 (0.0699) loss: 0.8241 (0.8324) time: 0.1511 data: 0.0733 max mem: 9390 +Train: [29] [5600/6250] eta: 0:01:33 lr: 0.000105 grad: 0.0655 (0.0700) loss: 0.8272 (0.8323) time: 0.1448 data: 0.0610 max mem: 9390 +Train: [29] [5700/6250] eta: 0:01:19 lr: 0.000105 grad: 0.0643 (0.0700) loss: 0.8323 (0.8323) time: 0.1592 data: 0.0705 max mem: 9390 +Train: [29] [5800/6250] eta: 0:01:04 lr: 0.000105 grad: 0.0702 (0.0700) loss: 0.8263 (0.8323) time: 0.1402 data: 0.0618 max mem: 9390 +Train: [29] [5900/6250] eta: 0:00:50 lr: 0.000105 grad: 0.0735 (0.0701) loss: 0.8302 (0.8322) time: 0.1351 data: 0.0588 max mem: 9390 +Train: [29] [6000/6250] eta: 0:00:36 lr: 0.000105 grad: 0.0724 (0.0702) loss: 0.8239 (0.8321) time: 0.1370 data: 0.0583 max mem: 9390 +Train: [29] [6100/6250] eta: 0:00:21 lr: 0.000105 grad: 0.0728 (0.0702) loss: 0.8259 (0.8321) time: 0.1138 data: 0.0341 max mem: 9390 +Train: [29] [6200/6250] eta: 0:00:07 lr: 0.000105 grad: 0.0693 (0.0703) loss: 0.8279 (0.8320) time: 0.1417 data: 0.0603 max mem: 9390 +Train: [29] [6249/6250] eta: 0:00:00 lr: 0.000105 grad: 0.0708 (0.0703) loss: 0.8272 (0.8319) time: 0.1528 data: 0.0656 max mem: 9390 +Train: [29] Total time: 0:15:04 (0.1447 s / it) +Averaged stats: lr: 0.000105 grad: 0.0708 (0.0703) loss: 0.8272 (0.8319) +Eval (hcp-train-subset): [29] [ 0/62] eta: 0:04:19 loss: 0.8522 (0.8522) time: 4.1899 data: 4.1584 max mem: 9390 +Eval (hcp-train-subset): [29] [61/62] eta: 0:00:00 loss: 0.8419 (0.8423) time: 0.1413 data: 0.1164 max mem: 9390 +Eval (hcp-train-subset): [29] Total time: 0:00:13 (0.2153 s / it) +Averaged stats (hcp-train-subset): loss: 0.8419 (0.8423) +Making plots (hcp-train-subset): example=10 +Eval (hcp-val): [29] [ 0/62] eta: 0:03:11 loss: 0.8397 (0.8397) time: 3.0930 data: 2.9947 max mem: 9390 +Eval (hcp-val): [29] [61/62] eta: 0:00:00 loss: 0.8383 (0.8394) time: 0.1128 data: 0.0884 max mem: 9390 +Eval (hcp-val): [29] Total time: 0:00:12 (0.2030 s / it) +Averaged stats (hcp-val): loss: 0.8383 (0.8394) +Making plots (hcp-val): example=41 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +Train: [30] [ 0/6250] eta: 10:08:09 lr: 0.000105 grad: 0.1311 (0.1311) loss: 0.8611 (0.8611) time: 5.8384 data: 5.7348 max mem: 9390 +Train: [30] [ 100/6250] eta: 0:20:34 lr: 0.000105 grad: 0.0663 (0.0795) loss: 0.8238 (0.8358) time: 0.1611 data: 0.0709 max mem: 9390 +Train: [30] [ 200/6250] eta: 0:17:36 lr: 0.000105 grad: 0.0675 (0.0772) loss: 0.8359 (0.8323) time: 0.1684 data: 0.0815 max mem: 9390 +Train: [30] [ 300/6250] eta: 0:16:20 lr: 0.000105 grad: 0.0658 (0.0753) loss: 0.8359 (0.8322) time: 0.1201 data: 0.0324 max mem: 9390 +Train: [30] [ 400/6250] eta: 0:15:33 lr: 0.000105 grad: 0.0673 (0.0740) loss: 0.8289 (0.8323) time: 0.1270 data: 0.0338 max mem: 9390 +Train: [30] [ 500/6250] eta: 0:14:53 lr: 0.000105 grad: 0.0666 (0.0736) loss: 0.8305 (0.8318) time: 0.1342 data: 0.0488 max mem: 9390 +Train: [30] [ 600/6250] eta: 0:14:16 lr: 0.000105 grad: 0.0672 (0.0728) loss: 0.8339 (0.8321) time: 0.1334 data: 0.0503 max mem: 9390 +Train: [30] [ 700/6250] eta: 0:13:51 lr: 0.000105 grad: 0.0729 (0.0725) loss: 0.8305 (0.8319) time: 0.1263 data: 0.0366 max mem: 9390 +Train: [30] [ 800/6250] eta: 0:13:25 lr: 0.000105 grad: 0.0705 (0.0723) loss: 0.8344 (0.8318) time: 0.1420 data: 0.0561 max mem: 9390 +Train: [30] [ 900/6250] eta: 0:13:09 lr: 0.000105 grad: 0.0680 (0.0722) loss: 0.8326 (0.8317) time: 0.1514 data: 0.0785 max mem: 9390 +Train: [30] [1000/6250] eta: 0:12:53 lr: 0.000105 grad: 0.0668 (0.0718) loss: 0.8341 (0.8319) time: 0.1715 data: 0.0927 max mem: 9390 +Train: [30] [1100/6250] eta: 0:12:35 lr: 0.000105 grad: 0.0685 (0.0717) loss: 0.8351 (0.8318) time: 0.1282 data: 0.0446 max mem: 9390 +Train: [30] [1200/6250] eta: 0:12:18 lr: 0.000105 grad: 0.0714 (0.0717) loss: 0.8278 (0.8317) time: 0.1466 data: 0.0639 max mem: 9390 +Train: [30] [1300/6250] eta: 0:12:01 lr: 0.000105 grad: 0.0721 (0.0717) loss: 0.8339 (0.8317) time: 0.1612 data: 0.0775 max mem: 9390 +Train: [30] [1400/6250] eta: 0:11:46 lr: 0.000104 grad: 0.0689 (0.0717) loss: 0.8341 (0.8316) time: 0.1392 data: 0.0580 max mem: 9390 +Train: [30] [1500/6250] eta: 0:11:30 lr: 0.000104 grad: 0.0698 (0.0717) loss: 0.8292 (0.8313) time: 0.1425 data: 0.0631 max mem: 9390 +Train: [30] [1600/6250] eta: 0:11:16 lr: 0.000104 grad: 0.0695 (0.0718) loss: 0.8274 (0.8311) time: 0.1395 data: 0.0586 max mem: 9390 +Train: [30] [1700/6250] eta: 0:11:01 lr: 0.000104 grad: 0.0668 (0.0717) loss: 0.8292 (0.8310) time: 0.1418 data: 0.0594 max mem: 9390 +Train: [30] [1800/6250] eta: 0:10:47 lr: 0.000104 grad: 0.0711 (0.0716) loss: 0.8258 (0.8310) time: 0.1379 data: 0.0595 max mem: 9390 +Train: [30] [1900/6250] eta: 0:10:33 lr: 0.000104 grad: 0.0674 (0.0716) loss: 0.8295 (0.8310) time: 0.1654 data: 0.0834 max mem: 9390 +Train: [30] [2000/6250] eta: 0:10:19 lr: 0.000104 grad: 0.0724 (0.0716) loss: 0.8266 (0.8309) time: 0.1398 data: 0.0605 max mem: 9390 +Train: [30] [2100/6250] eta: 0:10:03 lr: 0.000104 grad: 0.0704 (0.0717) loss: 0.8314 (0.8308) time: 0.1449 data: 0.0647 max mem: 9390 +Train: [30] [2200/6250] eta: 0:09:50 lr: 0.000104 grad: 0.0684 (0.0717) loss: 0.8279 (0.8307) time: 0.1301 data: 0.0492 max mem: 9390 +Train: [30] [2300/6250] eta: 0:09:35 lr: 0.000104 grad: 0.0668 (0.0718) loss: 0.8358 (0.8308) time: 0.1272 data: 0.0394 max mem: 9390 +Train: [30] [2400/6250] eta: 0:09:21 lr: 0.000104 grad: 0.0720 (0.0719) loss: 0.8321 (0.8308) time: 0.1476 data: 0.0700 max mem: 9390 +Train: [30] [2500/6250] eta: 0:09:05 lr: 0.000104 grad: 0.0743 (0.0720) loss: 0.8267 (0.8307) time: 0.1273 data: 0.0471 max mem: 9390 +Train: [30] [2600/6250] eta: 0:08:49 lr: 0.000104 grad: 0.0692 (0.0722) loss: 0.8311 (0.8307) time: 0.1464 data: 0.0679 max mem: 9390 +Train: [30] [2700/6250] eta: 0:08:35 lr: 0.000104 grad: 0.0700 (0.0722) loss: 0.8328 (0.8307) time: 0.1565 data: 0.0676 max mem: 9390 +Train: [30] [2800/6250] eta: 0:08:20 lr: 0.000104 grad: 0.0717 (0.0723) loss: 0.8322 (0.8307) time: 0.0908 data: 0.0088 max mem: 9390 +Train: [30] [2900/6250] eta: 0:08:05 lr: 0.000104 grad: 0.0697 (0.0724) loss: 0.8312 (0.8306) time: 0.1533 data: 0.0707 max mem: 9390 +Train: [30] [3000/6250] eta: 0:07:50 lr: 0.000104 grad: 0.0693 (0.0724) loss: 0.8309 (0.8306) time: 0.1431 data: 0.0648 max mem: 9390 +Train: [30] [3100/6250] eta: 0:07:35 lr: 0.000104 grad: 0.0735 (0.0725) loss: 0.8271 (0.8306) time: 0.1452 data: 0.0707 max mem: 9390 +Train: [30] [3200/6250] eta: 0:07:21 lr: 0.000104 grad: 0.0699 (0.0725) loss: 0.8307 (0.8306) time: 0.1771 data: 0.1005 max mem: 9390 +Train: [30] [3300/6250] eta: 0:07:05 lr: 0.000104 grad: 0.0792 (0.0726) loss: 0.8258 (0.8305) time: 0.1345 data: 0.0532 max mem: 9390 +Train: [30] [3400/6250] eta: 0:06:52 lr: 0.000104 grad: 0.0771 (0.0727) loss: 0.8234 (0.8305) time: 0.1789 data: 0.1010 max mem: 9390 +Train: [30] [3500/6250] eta: 0:06:36 lr: 0.000104 grad: 0.0726 (0.0728) loss: 0.8254 (0.8305) time: 0.1185 data: 0.0393 max mem: 9390 +Train: [30] [3600/6250] eta: 0:06:21 lr: 0.000104 grad: 0.0705 (0.0728) loss: 0.8288 (0.8304) time: 0.1482 data: 0.0675 max mem: 9390 +Train: [30] [3700/6250] eta: 0:06:06 lr: 0.000104 grad: 0.0726 (0.0728) loss: 0.8288 (0.8304) time: 0.1327 data: 0.0515 max mem: 9390 +Train: [30] [3800/6250] eta: 0:05:52 lr: 0.000104 grad: 0.0711 (0.0729) loss: 0.8307 (0.8304) time: 0.1454 data: 0.0576 max mem: 9390 +Train: [30] [3900/6250] eta: 0:05:37 lr: 0.000104 grad: 0.0736 (0.0729) loss: 0.8236 (0.8303) time: 0.1230 data: 0.0403 max mem: 9390 +Train: [30] [4000/6250] eta: 0:05:22 lr: 0.000104 grad: 0.0718 (0.0729) loss: 0.8329 (0.8303) time: 0.1306 data: 0.0469 max mem: 9390 +Train: [30] [4100/6250] eta: 0:05:08 lr: 0.000104 grad: 0.0709 (0.0729) loss: 0.8223 (0.8303) time: 0.1411 data: 0.0600 max mem: 9390 +Train: [30] [4200/6250] eta: 0:04:53 lr: 0.000104 grad: 0.0703 (0.0729) loss: 0.8308 (0.8302) time: 0.1630 data: 0.0784 max mem: 9390 +Train: [30] [4300/6250] eta: 0:04:39 lr: 0.000104 grad: 0.0698 (0.0731) loss: 0.8237 (0.8302) time: 0.1885 data: 0.1092 max mem: 9390 +Train: [30] [4400/6250] eta: 0:04:25 lr: 0.000104 grad: 0.0714 (0.0731) loss: 0.8313 (0.8301) time: 0.1678 data: 0.0867 max mem: 9390 +Train: [30] [4500/6250] eta: 0:04:11 lr: 0.000104 grad: 0.0744 (0.0731) loss: 0.8323 (0.8301) time: 0.1258 data: 0.0444 max mem: 9390 +Train: [30] [4600/6250] eta: 0:03:57 lr: 0.000104 grad: 0.0721 (0.0731) loss: 0.8309 (0.8301) time: 0.1611 data: 0.0861 max mem: 9390 +Train: [30] [4700/6250] eta: 0:03:43 lr: 0.000104 grad: 0.0726 (0.0731) loss: 0.8302 (0.8300) time: 0.1627 data: 0.0857 max mem: 9390 +Train: [30] [4800/6250] eta: 0:03:29 lr: 0.000104 grad: 0.0760 (0.0731) loss: 0.8312 (0.8300) time: 0.1507 data: 0.0667 max mem: 9390 +Train: [30] [4900/6250] eta: 0:03:15 lr: 0.000104 grad: 0.0715 (0.0731) loss: 0.8288 (0.8299) time: 0.1304 data: 0.0479 max mem: 9390 +Train: [30] [5000/6250] eta: 0:03:01 lr: 0.000104 grad: 0.0713 (0.0731) loss: 0.8314 (0.8299) time: 0.1386 data: 0.0546 max mem: 9390 +Train: [30] [5100/6250] eta: 0:02:46 lr: 0.000104 grad: 0.0757 (0.0732) loss: 0.8289 (0.8298) time: 0.1585 data: 0.0796 max mem: 9390 +Train: [30] [5200/6250] eta: 0:02:31 lr: 0.000104 grad: 0.0782 (0.0732) loss: 0.8279 (0.8297) time: 0.1636 data: 0.0871 max mem: 9390 +Train: [30] [5300/6250] eta: 0:02:17 lr: 0.000104 grad: 0.0696 (0.0733) loss: 0.8298 (0.8296) time: 0.1485 data: 0.0657 max mem: 9390 +Train: [30] [5400/6250] eta: 0:02:02 lr: 0.000103 grad: 0.0728 (0.0733) loss: 0.8285 (0.8296) time: 0.1220 data: 0.0408 max mem: 9390 +Train: [30] [5500/6250] eta: 0:01:48 lr: 0.000103 grad: 0.0734 (0.0733) loss: 0.8328 (0.8296) time: 0.1450 data: 0.0623 max mem: 9390 +Train: [30] [5600/6250] eta: 0:01:33 lr: 0.000103 grad: 0.0719 (0.0734) loss: 0.8285 (0.8295) time: 0.1453 data: 0.0688 max mem: 9390 +Train: [30] [5700/6250] eta: 0:01:19 lr: 0.000103 grad: 0.0707 (0.0734) loss: 0.8243 (0.8295) time: 0.1580 data: 0.0783 max mem: 9390 +Train: [30] [5800/6250] eta: 0:01:04 lr: 0.000103 grad: 0.0710 (0.0734) loss: 0.8319 (0.8294) time: 0.1212 data: 0.0456 max mem: 9390 +Train: [30] [5900/6250] eta: 0:00:50 lr: 0.000103 grad: 0.0697 (0.0735) loss: 0.8308 (0.8294) time: 0.1201 data: 0.0383 max mem: 9390 +Train: [30] [6000/6250] eta: 0:00:35 lr: 0.000103 grad: 0.0754 (0.0735) loss: 0.8255 (0.8293) time: 0.1339 data: 0.0495 max mem: 9390 +Train: [30] [6100/6250] eta: 0:00:21 lr: 0.000103 grad: 0.0727 (0.0736) loss: 0.8305 (0.8293) time: 0.1359 data: 0.0514 max mem: 9390 +Train: [30] [6200/6250] eta: 0:00:07 lr: 0.000103 grad: 0.0735 (0.0737) loss: 0.8205 (0.8292) time: 0.1234 data: 0.0451 max mem: 9390 +Train: [30] [6249/6250] eta: 0:00:00 lr: 0.000103 grad: 0.0782 (0.0737) loss: 0.8209 (0.8292) time: 0.2182 data: 0.1453 max mem: 9390 +Train: [30] Total time: 0:15:04 (0.1448 s / it) +Averaged stats: lr: 0.000103 grad: 0.0782 (0.0737) loss: 0.8209 (0.8292) +Eval (hcp-train-subset): [30] [ 0/62] eta: 0:03:49 loss: 0.8488 (0.8488) time: 3.7002 data: 3.6083 max mem: 9390 +Eval (hcp-train-subset): [30] [61/62] eta: 0:00:00 loss: 0.8414 (0.8423) time: 0.1731 data: 0.1477 max mem: 9390 +Eval (hcp-train-subset): [30] Total time: 0:00:14 (0.2357 s / it) +Averaged stats (hcp-train-subset): loss: 0.8414 (0.8423) +Eval (hcp-val): [30] [ 0/62] eta: 0:04:11 loss: 0.8354 (0.8354) time: 4.0602 data: 3.9609 max mem: 9390 +Eval (hcp-val): [30] [61/62] eta: 0:00:00 loss: 0.8372 (0.8389) time: 0.1023 data: 0.0762 max mem: 9390 +Eval (hcp-val): [30] Total time: 0:00:12 (0.2024 s / it) +Averaged stats (hcp-val): loss: 0.8372 (0.8389) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +Train: [31] [ 0/6250] eta: 9:49:07 lr: 0.000103 grad: 0.0581 (0.0581) loss: 0.8535 (0.8535) time: 5.6556 data: 5.5300 max mem: 9390 +Train: [31] [ 100/6250] eta: 0:20:10 lr: 0.000103 grad: 0.0680 (0.0805) loss: 0.8441 (0.8422) time: 0.1570 data: 0.0694 max mem: 9390 +Train: [31] [ 200/6250] eta: 0:17:06 lr: 0.000103 grad: 0.0651 (0.0778) loss: 0.8414 (0.8403) time: 0.1264 data: 0.0389 max mem: 9390 +Train: [31] [ 300/6250] eta: 0:16:05 lr: 0.000103 grad: 0.0704 (0.0765) loss: 0.8313 (0.8395) time: 0.1189 data: 0.0321 max mem: 9390 +Train: [31] [ 400/6250] eta: 0:15:23 lr: 0.000103 grad: 0.0707 (0.0755) loss: 0.8364 (0.8384) time: 0.1596 data: 0.0720 max mem: 9390 +Train: [31] [ 500/6250] eta: 0:14:43 lr: 0.000103 grad: 0.0683 (0.0748) loss: 0.8282 (0.8368) time: 0.1340 data: 0.0412 max mem: 9390 +Train: [31] [ 600/6250] eta: 0:14:13 lr: 0.000103 grad: 0.0657 (0.0738) loss: 0.8328 (0.8362) time: 0.1422 data: 0.0500 max mem: 9390 +Train: [31] [ 700/6250] eta: 0:13:53 lr: 0.000103 grad: 0.0700 (0.0735) loss: 0.8359 (0.8356) time: 0.1730 data: 0.0948 max mem: 9390 +Train: [31] [ 800/6250] eta: 0:13:36 lr: 0.000103 grad: 0.0658 (0.0731) loss: 0.8329 (0.8353) time: 0.1129 data: 0.0302 max mem: 9390 +Train: [31] [ 900/6250] eta: 0:13:25 lr: 0.000103 grad: 0.0701 (0.0727) loss: 0.8324 (0.8352) time: 0.1581 data: 0.0715 max mem: 9390 +Train: [31] [1000/6250] eta: 0:13:04 lr: 0.000103 grad: 0.0677 (0.0724) loss: 0.8353 (0.8350) time: 0.1258 data: 0.0454 max mem: 9390 +Train: [31] [1100/6250] eta: 0:12:46 lr: 0.000103 grad: 0.0662 (0.0720) loss: 0.8359 (0.8349) time: 0.1256 data: 0.0453 max mem: 9390 +Train: [31] [1200/6250] eta: 0:12:33 lr: 0.000103 grad: 0.0644 (0.0719) loss: 0.8338 (0.8347) time: 0.1108 data: 0.0296 max mem: 9390 +Train: [31] [1300/6250] eta: 0:12:11 lr: 0.000103 grad: 0.0698 (0.0716) loss: 0.8275 (0.8344) time: 0.1491 data: 0.0705 max mem: 9390 +Train: [31] [1400/6250] eta: 0:11:51 lr: 0.000103 grad: 0.0662 (0.0715) loss: 0.8291 (0.8342) time: 0.1199 data: 0.0433 max mem: 9390 +Train: [31] [1500/6250] eta: 0:11:32 lr: 0.000103 grad: 0.0674 (0.0715) loss: 0.8317 (0.8340) time: 0.1350 data: 0.0544 max mem: 9390 +Train: [31] [1600/6250] eta: 0:11:17 lr: 0.000103 grad: 0.0658 (0.0714) loss: 0.8319 (0.8337) time: 0.1378 data: 0.0581 max mem: 9390 +Train: [31] [1700/6250] eta: 0:11:02 lr: 0.000103 grad: 0.0707 (0.0715) loss: 0.8268 (0.8335) time: 0.1523 data: 0.0691 max mem: 9390 +Train: [31] [1800/6250] eta: 0:10:44 lr: 0.000103 grad: 0.0688 (0.0714) loss: 0.8263 (0.8332) time: 0.1383 data: 0.0601 max mem: 9390 +Train: [31] [1900/6250] eta: 0:10:28 lr: 0.000103 grad: 0.0702 (0.0716) loss: 0.8269 (0.8330) time: 0.1151 data: 0.0314 max mem: 9390 +Train: [31] [2000/6250] eta: 0:10:14 lr: 0.000103 grad: 0.0705 (0.0717) loss: 0.8319 (0.8327) time: 0.1574 data: 0.0722 max mem: 9390 +Train: [31] [2100/6250] eta: 0:09:59 lr: 0.000103 grad: 0.0713 (0.0718) loss: 0.8319 (0.8324) time: 0.1295 data: 0.0432 max mem: 9390 +Train: [31] [2200/6250] eta: 0:09:43 lr: 0.000103 grad: 0.0763 (0.0721) loss: 0.8268 (0.8320) time: 0.1292 data: 0.0494 max mem: 9390 +Train: [31] [2300/6250] eta: 0:09:29 lr: 0.000103 grad: 0.0745 (0.0722) loss: 0.8268 (0.8317) time: 0.1528 data: 0.0674 max mem: 9390 +Train: [31] [2400/6250] eta: 0:09:14 lr: 0.000103 grad: 0.0751 (0.0723) loss: 0.8218 (0.8314) time: 0.1332 data: 0.0539 max mem: 9390 +Train: [31] [2500/6250] eta: 0:08:58 lr: 0.000103 grad: 0.0702 (0.0725) loss: 0.8254 (0.8311) time: 0.1248 data: 0.0450 max mem: 9390 +Train: [31] [2600/6250] eta: 0:08:43 lr: 0.000103 grad: 0.0781 (0.0725) loss: 0.8247 (0.8308) time: 0.1392 data: 0.0576 max mem: 9390 +Train: [31] [2700/6250] eta: 0:08:29 lr: 0.000103 grad: 0.0730 (0.0726) loss: 0.8282 (0.8307) time: 0.1814 data: 0.0782 max mem: 9390 +Train: [31] [2800/6250] eta: 0:08:14 lr: 0.000103 grad: 0.0804 (0.0727) loss: 0.8236 (0.8306) time: 0.1410 data: 0.0562 max mem: 9390 +Train: [31] [2900/6250] eta: 0:07:59 lr: 0.000103 grad: 0.0762 (0.0728) loss: 0.8289 (0.8305) time: 0.1333 data: 0.0515 max mem: 9390 +Train: [31] [3000/6250] eta: 0:07:45 lr: 0.000103 grad: 0.0773 (0.0729) loss: 0.8192 (0.8303) time: 0.1990 data: 0.1245 max mem: 9390 +Train: [31] [3100/6250] eta: 0:07:30 lr: 0.000103 grad: 0.0671 (0.0730) loss: 0.8281 (0.8302) time: 0.1604 data: 0.0741 max mem: 9390 +Train: [31] [3200/6250] eta: 0:07:15 lr: 0.000102 grad: 0.0757 (0.0730) loss: 0.8268 (0.8301) time: 0.1397 data: 0.0640 max mem: 9390 +Train: [31] [3300/6250] eta: 0:07:01 lr: 0.000102 grad: 0.0734 (0.0731) loss: 0.8293 (0.8300) time: 0.1582 data: 0.0794 max mem: 9390 +Train: [31] [3400/6250] eta: 0:06:47 lr: 0.000102 grad: 0.0722 (0.0732) loss: 0.8275 (0.8300) time: 0.1617 data: 0.0810 max mem: 9390 +Train: [31] [3500/6250] eta: 0:06:33 lr: 0.000102 grad: 0.0718 (0.0732) loss: 0.8363 (0.8299) time: 0.1338 data: 0.0530 max mem: 9390 +Train: [31] [3600/6250] eta: 0:06:18 lr: 0.000102 grad: 0.0762 (0.0734) loss: 0.8291 (0.8299) time: 0.1442 data: 0.0637 max mem: 9390 +Train: [31] [3700/6250] eta: 0:06:04 lr: 0.000102 grad: 0.0724 (0.0735) loss: 0.8295 (0.8298) time: 0.1357 data: 0.0507 max mem: 9390 +Train: [31] [3800/6250] eta: 0:05:49 lr: 0.000102 grad: 0.0752 (0.0735) loss: 0.8294 (0.8298) time: 0.1453 data: 0.0639 max mem: 9390 +Train: [31] [3900/6250] eta: 0:05:36 lr: 0.000102 grad: 0.0775 (0.0736) loss: 0.8268 (0.8298) time: 0.1475 data: 0.0411 max mem: 9390 +Train: [31] [4000/6250] eta: 0:05:22 lr: 0.000102 grad: 0.0748 (0.0737) loss: 0.8253 (0.8298) time: 0.1538 data: 0.0743 max mem: 9390 +Train: [31] [4100/6250] eta: 0:05:07 lr: 0.000102 grad: 0.0725 (0.0737) loss: 0.8284 (0.8297) time: 0.1384 data: 0.0603 max mem: 9390 +Train: [31] [4200/6250] eta: 0:04:52 lr: 0.000102 grad: 0.0769 (0.0738) loss: 0.8229 (0.8296) time: 0.1325 data: 0.0600 max mem: 9390 +Train: [31] [4300/6250] eta: 0:04:38 lr: 0.000102 grad: 0.0843 (0.0740) loss: 0.8254 (0.8296) time: 0.1304 data: 0.0467 max mem: 9390 +Train: [31] [4400/6250] eta: 0:04:24 lr: 0.000102 grad: 0.0743 (0.0740) loss: 0.8329 (0.8296) time: 0.1678 data: 0.0901 max mem: 9390 +Train: [31] [4500/6250] eta: 0:04:10 lr: 0.000102 grad: 0.0705 (0.0740) loss: 0.8295 (0.8296) time: 0.1427 data: 0.0613 max mem: 9390 +Train: [31] [4600/6250] eta: 0:03:56 lr: 0.000102 grad: 0.0757 (0.0741) loss: 0.8270 (0.8296) time: 0.1317 data: 0.0512 max mem: 9390 +Train: [31] [4700/6250] eta: 0:03:42 lr: 0.000102 grad: 0.0742 (0.0741) loss: 0.8267 (0.8295) time: 0.1427 data: 0.0645 max mem: 9390 +Train: [31] [4800/6250] eta: 0:03:28 lr: 0.000102 grad: 0.0746 (0.0742) loss: 0.8301 (0.8295) time: 0.1487 data: 0.0659 max mem: 9390 +Train: [31] [4900/6250] eta: 0:03:13 lr: 0.000102 grad: 0.0759 (0.0742) loss: 0.8297 (0.8295) time: 0.1477 data: 0.0664 max mem: 9390 +Train: [31] [5000/6250] eta: 0:02:59 lr: 0.000102 grad: 0.0717 (0.0742) loss: 0.8291 (0.8295) time: 0.1472 data: 0.0671 max mem: 9390 +Train: [31] [5100/6250] eta: 0:02:45 lr: 0.000102 grad: 0.0714 (0.0743) loss: 0.8359 (0.8296) time: 0.1376 data: 0.0583 max mem: 9390 +Train: [31] [5200/6250] eta: 0:02:30 lr: 0.000102 grad: 0.0746 (0.0744) loss: 0.8243 (0.8295) time: 0.1323 data: 0.0563 max mem: 9390 +Train: [31] [5300/6250] eta: 0:02:16 lr: 0.000102 grad: 0.0738 (0.0744) loss: 0.8267 (0.8295) time: 0.1406 data: 0.0523 max mem: 9390 +Train: [31] [5400/6250] eta: 0:02:01 lr: 0.000102 grad: 0.0743 (0.0744) loss: 0.8281 (0.8295) time: 0.1231 data: 0.0442 max mem: 9390 +Train: [31] [5500/6250] eta: 0:01:47 lr: 0.000102 grad: 0.0731 (0.0744) loss: 0.8281 (0.8294) time: 0.1351 data: 0.0516 max mem: 9390 +Train: [31] [5600/6250] eta: 0:01:33 lr: 0.000102 grad: 0.0745 (0.0745) loss: 0.8263 (0.8294) time: 0.1091 data: 0.0191 max mem: 9390 +Train: [31] [5700/6250] eta: 0:01:18 lr: 0.000102 grad: 0.0697 (0.0745) loss: 0.8233 (0.8293) time: 0.1340 data: 0.0595 max mem: 9390 +Train: [31] [5800/6250] eta: 0:01:04 lr: 0.000102 grad: 0.0727 (0.0745) loss: 0.8280 (0.8293) time: 0.1597 data: 0.0801 max mem: 9390 +Train: [31] [5900/6250] eta: 0:00:50 lr: 0.000102 grad: 0.0735 (0.0745) loss: 0.8300 (0.8292) time: 0.1378 data: 0.0572 max mem: 9390 +Train: [31] [6000/6250] eta: 0:00:35 lr: 0.000102 grad: 0.0754 (0.0745) loss: 0.8306 (0.8292) time: 0.1404 data: 0.0580 max mem: 9390 +Train: [31] [6100/6250] eta: 0:00:21 lr: 0.000102 grad: 0.0701 (0.0745) loss: 0.8292 (0.8292) time: 0.1497 data: 0.0677 max mem: 9390 +Train: [31] [6200/6250] eta: 0:00:07 lr: 0.000102 grad: 0.0767 (0.0745) loss: 0.8264 (0.8292) time: 0.1332 data: 0.0543 max mem: 9390 +Train: [31] [6249/6250] eta: 0:00:00 lr: 0.000102 grad: 0.0760 (0.0745) loss: 0.8257 (0.8292) time: 0.1288 data: 0.0504 max mem: 9390 +Train: [31] Total time: 0:14:58 (0.1437 s / it) +Averaged stats: lr: 0.000102 grad: 0.0760 (0.0745) loss: 0.8257 (0.8292) +Eval (hcp-train-subset): [31] [ 0/62] eta: 0:06:17 loss: 0.8565 (0.8565) time: 6.0931 data: 6.0569 max mem: 9390 +Eval (hcp-train-subset): [31] [61/62] eta: 0:00:00 loss: 0.8421 (0.8425) time: 0.1494 data: 0.1243 max mem: 9390 +Eval (hcp-train-subset): [31] Total time: 0:00:14 (0.2275 s / it) +Averaged stats (hcp-train-subset): loss: 0.8421 (0.8425) +Eval (hcp-val): [31] [ 0/62] eta: 0:04:22 loss: 0.8378 (0.8378) time: 4.2271 data: 4.1968 max mem: 9390 +Eval (hcp-val): [31] [61/62] eta: 0:00:00 loss: 0.8380 (0.8394) time: 0.1152 data: 0.0905 max mem: 9390 +Eval (hcp-val): [31] Total time: 0:00:12 (0.2071 s / it) +Averaged stats (hcp-val): loss: 0.8380 (0.8394) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +Train: [32] [ 0/6250] eta: 9:26:36 lr: 0.000102 grad: 0.1024 (0.1024) loss: 0.8493 (0.8493) time: 5.4394 data: 5.3283 max mem: 9390 +Train: [32] [ 100/6250] eta: 0:19:41 lr: 0.000102 grad: 0.0712 (0.0884) loss: 0.8332 (0.8272) time: 0.1455 data: 0.0588 max mem: 9390 +Train: [32] [ 200/6250] eta: 0:16:44 lr: 0.000102 grad: 0.0679 (0.0813) loss: 0.8359 (0.8287) time: 0.1334 data: 0.0466 max mem: 9390 +Train: [32] [ 300/6250] eta: 0:15:47 lr: 0.000102 grad: 0.0714 (0.0786) loss: 0.8321 (0.8290) time: 0.1623 data: 0.0784 max mem: 9390 +Train: [32] [ 400/6250] eta: 0:15:06 lr: 0.000102 grad: 0.0731 (0.0775) loss: 0.8312 (0.8291) time: 0.1683 data: 0.0933 max mem: 9390 +Train: [32] [ 500/6250] eta: 0:14:31 lr: 0.000102 grad: 0.0743 (0.0768) loss: 0.8233 (0.8291) time: 0.1439 data: 0.0547 max mem: 9390 +Train: [32] [ 600/6250] eta: 0:13:53 lr: 0.000102 grad: 0.0645 (0.0763) loss: 0.8237 (0.8290) time: 0.1262 data: 0.0398 max mem: 9390 +Train: [32] [ 700/6250] eta: 0:13:25 lr: 0.000102 grad: 0.0688 (0.0761) loss: 0.8194 (0.8282) time: 0.1248 data: 0.0398 max mem: 9390 +Train: [32] [ 800/6250] eta: 0:13:00 lr: 0.000101 grad: 0.0730 (0.0756) loss: 0.8256 (0.8279) time: 0.1226 data: 0.0320 max mem: 9390 +Train: [32] [ 900/6250] eta: 0:12:47 lr: 0.000101 grad: 0.0657 (0.0754) loss: 0.8317 (0.8277) time: 0.1214 data: 0.0287 max mem: 9390 +Train: [32] [1000/6250] eta: 0:12:35 lr: 0.000101 grad: 0.0713 (0.0754) loss: 0.8302 (0.8274) time: 0.1476 data: 0.0666 max mem: 9390 +Train: [32] [1100/6250] eta: 0:12:19 lr: 0.000101 grad: 0.0738 (0.0753) loss: 0.8269 (0.8271) time: 0.1499 data: 0.0583 max mem: 9390 +Train: [32] [1200/6250] eta: 0:12:05 lr: 0.000101 grad: 0.0805 (0.0755) loss: 0.8216 (0.8268) time: 0.1161 data: 0.0265 max mem: 9390 +Train: [32] [1300/6250] eta: 0:11:50 lr: 0.000101 grad: 0.0713 (0.0754) loss: 0.8313 (0.8267) time: 0.1404 data: 0.0624 max mem: 9390 +Train: [32] [1400/6250] eta: 0:11:35 lr: 0.000101 grad: 0.0699 (0.0754) loss: 0.8229 (0.8265) time: 0.1598 data: 0.0822 max mem: 9390 +Train: [32] [1500/6250] eta: 0:11:18 lr: 0.000101 grad: 0.0781 (0.0755) loss: 0.8220 (0.8264) time: 0.1247 data: 0.0429 max mem: 9390 +Train: [32] [1600/6250] eta: 0:11:04 lr: 0.000101 grad: 0.0825 (0.0757) loss: 0.8212 (0.8264) time: 0.1485 data: 0.0644 max mem: 9390 +Train: [32] [1700/6250] eta: 0:10:51 lr: 0.000101 grad: 0.0686 (0.0760) loss: 0.8331 (0.8265) time: 0.1407 data: 0.0649 max mem: 9390 +Train: [32] [1800/6250] eta: 0:10:36 lr: 0.000101 grad: 0.0738 (0.0762) loss: 0.8272 (0.8264) time: 0.1358 data: 0.0553 max mem: 9390 +Train: [32] [1900/6250] eta: 0:10:20 lr: 0.000101 grad: 0.0731 (0.0761) loss: 0.8279 (0.8264) time: 0.1406 data: 0.0601 max mem: 9390 +Train: [32] [2000/6250] eta: 0:10:05 lr: 0.000101 grad: 0.0753 (0.0760) loss: 0.8192 (0.8263) time: 0.1339 data: 0.0560 max mem: 9390 +Train: [32] [2100/6250] eta: 0:09:50 lr: 0.000101 grad: 0.0683 (0.0760) loss: 0.8287 (0.8264) time: 0.1322 data: 0.0502 max mem: 9390 +Train: [32] [2200/6250] eta: 0:09:35 lr: 0.000101 grad: 0.0696 (0.0760) loss: 0.8305 (0.8266) time: 0.1232 data: 0.0405 max mem: 9390 +Train: [32] [2300/6250] eta: 0:09:20 lr: 0.000101 grad: 0.0723 (0.0759) loss: 0.8298 (0.8266) time: 0.1399 data: 0.0614 max mem: 9390 +Train: [32] [2400/6250] eta: 0:09:06 lr: 0.000101 grad: 0.0743 (0.0758) loss: 0.8298 (0.8266) time: 0.1418 data: 0.0615 max mem: 9390 +Train: [32] [2500/6250] eta: 0:08:52 lr: 0.000101 grad: 0.0714 (0.0757) loss: 0.8312 (0.8268) time: 0.1311 data: 0.0501 max mem: 9390 +Train: [32] [2600/6250] eta: 0:08:36 lr: 0.000101 grad: 0.0737 (0.0756) loss: 0.8324 (0.8269) time: 0.1111 data: 0.0280 max mem: 9390 +Train: [32] [2700/6250] eta: 0:08:23 lr: 0.000101 grad: 0.0739 (0.0757) loss: 0.8231 (0.8269) time: 0.1383 data: 0.0619 max mem: 9390 +Train: [32] [2800/6250] eta: 0:08:07 lr: 0.000101 grad: 0.0717 (0.0756) loss: 0.8305 (0.8270) time: 0.1330 data: 0.0469 max mem: 9390 +Train: [32] [2900/6250] eta: 0:07:53 lr: 0.000101 grad: 0.0676 (0.0756) loss: 0.8336 (0.8271) time: 0.1522 data: 0.0728 max mem: 9390 +Train: [32] [3000/6250] eta: 0:07:39 lr: 0.000101 grad: 0.0714 (0.0755) loss: 0.8325 (0.8271) time: 0.1319 data: 0.0513 max mem: 9390 +Train: [32] [3100/6250] eta: 0:07:25 lr: 0.000101 grad: 0.0729 (0.0755) loss: 0.8279 (0.8272) time: 0.1453 data: 0.0688 max mem: 9390 +Train: [32] [3200/6250] eta: 0:07:11 lr: 0.000101 grad: 0.0708 (0.0755) loss: 0.8327 (0.8272) time: 0.1519 data: 0.0717 max mem: 9390 +Train: [32] [3300/6250] eta: 0:06:57 lr: 0.000101 grad: 0.0727 (0.0754) loss: 0.8232 (0.8273) time: 0.1443 data: 0.0625 max mem: 9390 +Train: [32] [3400/6250] eta: 0:06:44 lr: 0.000101 grad: 0.0703 (0.0754) loss: 0.8273 (0.8272) time: 0.1346 data: 0.0511 max mem: 9390 +Train: [32] [3500/6250] eta: 0:06:30 lr: 0.000101 grad: 0.0728 (0.0754) loss: 0.8206 (0.8272) time: 0.1388 data: 0.0612 max mem: 9390 +Train: [32] [3600/6250] eta: 0:06:16 lr: 0.000101 grad: 0.0725 (0.0753) loss: 0.8297 (0.8272) time: 0.1355 data: 0.0533 max mem: 9390 +Train: [32] [3700/6250] eta: 0:06:02 lr: 0.000101 grad: 0.0702 (0.0753) loss: 0.8300 (0.8272) time: 0.1576 data: 0.0769 max mem: 9390 +Train: [32] [3800/6250] eta: 0:05:47 lr: 0.000101 grad: 0.0711 (0.0752) loss: 0.8242 (0.8271) time: 0.1409 data: 0.0597 max mem: 9390 +Train: [32] [3900/6250] eta: 0:05:33 lr: 0.000101 grad: 0.0696 (0.0752) loss: 0.8301 (0.8271) time: 0.1613 data: 0.0801 max mem: 9390 +Train: [32] [4000/6250] eta: 0:05:19 lr: 0.000101 grad: 0.0724 (0.0752) loss: 0.8254 (0.8271) time: 0.1551 data: 0.0770 max mem: 9390 +Train: [32] [4100/6250] eta: 0:05:05 lr: 0.000101 grad: 0.0767 (0.0753) loss: 0.8288 (0.8271) time: 0.1605 data: 0.0818 max mem: 9390 +Train: [32] [4200/6250] eta: 0:04:50 lr: 0.000101 grad: 0.0713 (0.0753) loss: 0.8275 (0.8271) time: 0.1421 data: 0.0677 max mem: 9390 +Train: [32] [4300/6250] eta: 0:04:36 lr: 0.000101 grad: 0.0762 (0.0753) loss: 0.8253 (0.8271) time: 0.1246 data: 0.0398 max mem: 9390 +Train: [32] [4400/6250] eta: 0:04:22 lr: 0.000101 grad: 0.0764 (0.0754) loss: 0.8211 (0.8270) time: 0.1518 data: 0.0701 max mem: 9390 +Train: [32] [4500/6250] eta: 0:04:08 lr: 0.000101 grad: 0.0745 (0.0754) loss: 0.8241 (0.8270) time: 0.1572 data: 0.0761 max mem: 9390 +Train: [32] [4600/6250] eta: 0:03:54 lr: 0.000101 grad: 0.0751 (0.0755) loss: 0.8285 (0.8269) time: 0.1450 data: 0.0615 max mem: 9390 +Train: [32] [4700/6250] eta: 0:03:40 lr: 0.000100 grad: 0.0677 (0.0755) loss: 0.8254 (0.8269) time: 0.1496 data: 0.0651 max mem: 9390 +Train: [32] [4800/6250] eta: 0:03:26 lr: 0.000100 grad: 0.0767 (0.0755) loss: 0.8212 (0.8268) time: 0.1506 data: 0.0674 max mem: 9390 +Train: [32] [4900/6250] eta: 0:03:13 lr: 0.000100 grad: 0.0724 (0.0756) loss: 0.8267 (0.8268) time: 0.1150 data: 0.0375 max mem: 9390 +Train: [32] [5000/6250] eta: 0:02:58 lr: 0.000100 grad: 0.0752 (0.0756) loss: 0.8241 (0.8268) time: 0.1200 data: 0.0352 max mem: 9390 +Train: [32] [5100/6250] eta: 0:02:44 lr: 0.000100 grad: 0.0710 (0.0756) loss: 0.8278 (0.8268) time: 0.1654 data: 0.0842 max mem: 9390 +Train: [32] [5200/6250] eta: 0:02:30 lr: 0.000100 grad: 0.0694 (0.0755) loss: 0.8298 (0.8268) time: 0.1269 data: 0.0400 max mem: 9390 +Train: [32] [5300/6250] eta: 0:02:15 lr: 0.000100 grad: 0.0682 (0.0755) loss: 0.8283 (0.8268) time: 0.1181 data: 0.0396 max mem: 9390 +Train: [32] [5400/6250] eta: 0:02:01 lr: 0.000100 grad: 0.0735 (0.0755) loss: 0.8297 (0.8268) time: 0.1294 data: 0.0464 max mem: 9390 +Train: [32] [5500/6250] eta: 0:01:46 lr: 0.000100 grad: 0.0707 (0.0755) loss: 0.8307 (0.8268) time: 0.1380 data: 0.0541 max mem: 9390 +Train: [32] [5600/6250] eta: 0:01:32 lr: 0.000100 grad: 0.0712 (0.0755) loss: 0.8283 (0.8268) time: 0.1380 data: 0.0558 max mem: 9390 +Train: [32] [5700/6250] eta: 0:01:18 lr: 0.000100 grad: 0.0752 (0.0755) loss: 0.8253 (0.8268) time: 0.1731 data: 0.0821 max mem: 9390 +Train: [32] [5800/6250] eta: 0:01:04 lr: 0.000100 grad: 0.0754 (0.0756) loss: 0.8255 (0.8267) time: 0.1302 data: 0.0476 max mem: 9390 +Train: [32] [5900/6250] eta: 0:00:49 lr: 0.000100 grad: 0.0711 (0.0755) loss: 0.8254 (0.8268) time: 0.1079 data: 0.0245 max mem: 9390 +Train: [32] [6000/6250] eta: 0:00:35 lr: 0.000100 grad: 0.0734 (0.0756) loss: 0.8274 (0.8267) time: 0.1430 data: 0.0586 max mem: 9390 +Train: [32] [6100/6250] eta: 0:00:21 lr: 0.000100 grad: 0.0730 (0.0756) loss: 0.8264 (0.8267) time: 0.1359 data: 0.0584 max mem: 9390 +Train: [32] [6200/6250] eta: 0:00:07 lr: 0.000100 grad: 0.0738 (0.0756) loss: 0.8277 (0.8267) time: 0.1365 data: 0.0564 max mem: 9390 +Train: [32] [6249/6250] eta: 0:00:00 lr: 0.000100 grad: 0.0783 (0.0755) loss: 0.8250 (0.8267) time: 0.1559 data: 0.0731 max mem: 9390 +Train: [32] Total time: 0:14:55 (0.1433 s / it) +Averaged stats: lr: 0.000100 grad: 0.0783 (0.0755) loss: 0.8250 (0.8267) +Eval (hcp-train-subset): [32] [ 0/62] eta: 0:03:50 loss: 0.8533 (0.8533) time: 3.7201 data: 3.6426 max mem: 9390 +Eval (hcp-train-subset): [32] [61/62] eta: 0:00:00 loss: 0.8428 (0.8429) time: 0.1563 data: 0.1296 max mem: 9390 +Eval (hcp-train-subset): [32] Total time: 0:00:14 (0.2326 s / it) +Averaged stats (hcp-train-subset): loss: 0.8428 (0.8429) +Eval (hcp-val): [32] [ 0/62] eta: 0:05:19 loss: 0.8415 (0.8415) time: 5.1510 data: 5.1214 max mem: 9390 +Eval (hcp-val): [32] [61/62] eta: 0:00:00 loss: 0.8378 (0.8391) time: 0.1295 data: 0.1032 max mem: 9390 +Eval (hcp-val): [32] Total time: 0:00:12 (0.2064 s / it) +Averaged stats (hcp-val): loss: 0.8378 (0.8391) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +Train: [33] [ 0/6250] eta: 8:39:15 lr: 0.000100 grad: 0.1658 (0.1658) loss: 0.8532 (0.8532) time: 4.9849 data: 4.8346 max mem: 9390 +Train: [33] [ 100/6250] eta: 0:20:44 lr: 0.000100 grad: 0.0736 (0.0833) loss: 0.8256 (0.8348) time: 0.1638 data: 0.0740 max mem: 9390 +Train: [33] [ 200/6250] eta: 0:17:50 lr: 0.000100 grad: 0.0722 (0.0799) loss: 0.8310 (0.8330) time: 0.1408 data: 0.0555 max mem: 9390 +Train: [33] [ 300/6250] eta: 0:16:42 lr: 0.000100 grad: 0.0755 (0.0780) loss: 0.8282 (0.8332) time: 0.1445 data: 0.0568 max mem: 9390 +Train: [33] [ 400/6250] eta: 0:15:51 lr: 0.000100 grad: 0.0725 (0.0766) loss: 0.8303 (0.8329) time: 0.1489 data: 0.0664 max mem: 9390 +Train: [33] [ 500/6250] eta: 0:15:08 lr: 0.000100 grad: 0.0677 (0.0756) loss: 0.8344 (0.8332) time: 0.1535 data: 0.0606 max mem: 9390 +Train: [33] [ 600/6250] eta: 0:14:25 lr: 0.000100 grad: 0.0701 (0.0749) loss: 0.8357 (0.8331) time: 0.1177 data: 0.0274 max mem: 9390 +Train: [33] [ 700/6250] eta: 0:13:53 lr: 0.000100 grad: 0.0738 (0.0746) loss: 0.8301 (0.8329) time: 0.1235 data: 0.0329 max mem: 9390 +Train: [33] [ 800/6250] eta: 0:13:25 lr: 0.000100 grad: 0.0717 (0.0743) loss: 0.8318 (0.8325) time: 0.1331 data: 0.0461 max mem: 9390 +Train: [33] [ 900/6250] eta: 0:13:14 lr: 0.000100 grad: 0.0742 (0.0742) loss: 0.8342 (0.8321) time: 0.1870 data: 0.0644 max mem: 9390 +Train: [33] [1000/6250] eta: 0:12:59 lr: 0.000100 grad: 0.0663 (0.0741) loss: 0.8283 (0.8319) time: 0.1361 data: 0.0493 max mem: 9390 +Train: [33] [1100/6250] eta: 0:12:37 lr: 0.000100 grad: 0.0732 (0.0741) loss: 0.8232 (0.8316) time: 0.1215 data: 0.0335 max mem: 9390 +Train: [33] [1200/6250] eta: 0:12:24 lr: 0.000100 grad: 0.0702 (0.0738) loss: 0.8283 (0.8314) time: 0.1714 data: 0.0927 max mem: 9390 +Train: [33] [1300/6250] eta: 0:12:02 lr: 0.000100 grad: 0.0736 (0.0739) loss: 0.8255 (0.8312) time: 0.1359 data: 0.0566 max mem: 9390 +Train: [33] [1400/6250] eta: 0:11:47 lr: 0.000100 grad: 0.0712 (0.0738) loss: 0.8287 (0.8309) time: 0.1711 data: 0.0927 max mem: 9390 +Train: [33] [1500/6250] eta: 0:11:29 lr: 0.000100 grad: 0.0719 (0.0738) loss: 0.8209 (0.8305) time: 0.1374 data: 0.0491 max mem: 9390 +Train: [33] [1600/6250] eta: 0:11:14 lr: 0.000100 grad: 0.0689 (0.0738) loss: 0.8257 (0.8304) time: 0.1971 data: 0.1130 max mem: 9390 +Train: [33] [1700/6250] eta: 0:10:56 lr: 0.000100 grad: 0.0714 (0.0736) loss: 0.8301 (0.8303) time: 0.1452 data: 0.0660 max mem: 9390 +Train: [33] [1800/6250] eta: 0:10:39 lr: 0.000100 grad: 0.0700 (0.0737) loss: 0.8292 (0.8301) time: 0.1494 data: 0.0710 max mem: 9390 +Train: [33] [1900/6250] eta: 0:10:23 lr: 0.000100 grad: 0.0654 (0.0736) loss: 0.8287 (0.8301) time: 0.1446 data: 0.0621 max mem: 9390 +Train: [33] [2000/6250] eta: 0:10:07 lr: 0.000100 grad: 0.0696 (0.0736) loss: 0.8262 (0.8300) time: 0.1496 data: 0.0706 max mem: 9390 +Train: [33] [2100/6250] eta: 0:09:53 lr: 0.000100 grad: 0.0707 (0.0739) loss: 0.8215 (0.8299) time: 0.1438 data: 0.0632 max mem: 9390 +Train: [33] [2200/6250] eta: 0:09:36 lr: 0.000099 grad: 0.0735 (0.0741) loss: 0.8268 (0.8298) time: 0.1409 data: 0.0626 max mem: 9390 +Train: [33] [2300/6250] eta: 0:09:21 lr: 0.000099 grad: 0.0734 (0.0743) loss: 0.8234 (0.8296) time: 0.1419 data: 0.0640 max mem: 9390 +Train: [33] [2400/6250] eta: 0:09:07 lr: 0.000099 grad: 0.0744 (0.0743) loss: 0.8283 (0.8295) time: 0.1602 data: 0.0822 max mem: 9390 +Train: [33] [2500/6250] eta: 0:08:51 lr: 0.000099 grad: 0.0722 (0.0744) loss: 0.8256 (0.8293) time: 0.1497 data: 0.0730 max mem: 9390 +Train: [33] [2600/6250] eta: 0:08:36 lr: 0.000099 grad: 0.0730 (0.0745) loss: 0.8270 (0.8293) time: 0.1401 data: 0.0624 max mem: 9390 +Train: [33] [2700/6250] eta: 0:08:22 lr: 0.000099 grad: 0.0725 (0.0746) loss: 0.8275 (0.8292) time: 0.1500 data: 0.0742 max mem: 9390 +Train: [33] [2800/6250] eta: 0:08:07 lr: 0.000099 grad: 0.0778 (0.0748) loss: 0.8206 (0.8291) time: 0.1395 data: 0.0616 max mem: 9390 +Train: [33] [2900/6250] eta: 0:07:53 lr: 0.000099 grad: 0.0695 (0.0748) loss: 0.8257 (0.8289) time: 0.1234 data: 0.0424 max mem: 9390 +Train: [33] [3000/6250] eta: 0:07:38 lr: 0.000099 grad: 0.0695 (0.0748) loss: 0.8318 (0.8289) time: 0.1288 data: 0.0492 max mem: 9390 +Train: [33] [3100/6250] eta: 0:07:23 lr: 0.000099 grad: 0.0726 (0.0749) loss: 0.8280 (0.8288) time: 0.1343 data: 0.0448 max mem: 9390 +Train: [33] [3200/6250] eta: 0:07:10 lr: 0.000099 grad: 0.0692 (0.0749) loss: 0.8345 (0.8288) time: 0.1330 data: 0.0519 max mem: 9390 +Train: [33] [3300/6250] eta: 0:06:56 lr: 0.000099 grad: 0.0727 (0.0749) loss: 0.8314 (0.8288) time: 0.1419 data: 0.0615 max mem: 9390 +Train: [33] [3400/6250] eta: 0:06:41 lr: 0.000099 grad: 0.0732 (0.0749) loss: 0.8243 (0.8288) time: 0.1552 data: 0.0826 max mem: 9390 +Train: [33] [3500/6250] eta: 0:06:28 lr: 0.000099 grad: 0.0761 (0.0749) loss: 0.8319 (0.8289) time: 0.1539 data: 0.0712 max mem: 9390 +Train: [33] [3600/6250] eta: 0:06:14 lr: 0.000099 grad: 0.0700 (0.0748) loss: 0.8344 (0.8290) time: 0.1323 data: 0.0538 max mem: 9390 +Train: [33] [3700/6250] eta: 0:05:59 lr: 0.000099 grad: 0.0696 (0.0748) loss: 0.8303 (0.8290) time: 0.1165 data: 0.0309 max mem: 9390 +Train: [33] [3800/6250] eta: 0:05:45 lr: 0.000099 grad: 0.0703 (0.0748) loss: 0.8256 (0.8290) time: 0.1330 data: 0.0565 max mem: 9390 +Train: [33] [3900/6250] eta: 0:05:32 lr: 0.000099 grad: 0.0712 (0.0748) loss: 0.8301 (0.8290) time: 0.1812 data: 0.0923 max mem: 9390 +Train: [33] [4000/6250] eta: 0:05:17 lr: 0.000099 grad: 0.0755 (0.0748) loss: 0.8281 (0.8289) time: 0.1331 data: 0.0573 max mem: 9390 +Train: [33] [4100/6250] eta: 0:05:03 lr: 0.000099 grad: 0.0809 (0.0749) loss: 0.8269 (0.8289) time: 0.1262 data: 0.0416 max mem: 9390 +Train: [33] [4200/6250] eta: 0:04:49 lr: 0.000099 grad: 0.0691 (0.0749) loss: 0.8337 (0.8289) time: 0.1400 data: 0.0629 max mem: 9390 +Train: [33] [4300/6250] eta: 0:04:35 lr: 0.000099 grad: 0.0708 (0.0749) loss: 0.8312 (0.8289) time: 0.1332 data: 0.0530 max mem: 9390 +Train: [33] [4400/6250] eta: 0:04:21 lr: 0.000099 grad: 0.0741 (0.0749) loss: 0.8290 (0.8288) time: 0.1419 data: 0.0646 max mem: 9390 +Train: [33] [4500/6250] eta: 0:04:07 lr: 0.000099 grad: 0.0719 (0.0749) loss: 0.8255 (0.8288) time: 0.1293 data: 0.0521 max mem: 9390 +Train: [33] [4600/6250] eta: 0:03:53 lr: 0.000099 grad: 0.0739 (0.0748) loss: 0.8265 (0.8288) time: 0.1378 data: 0.0609 max mem: 9390 +Train: [33] [4700/6250] eta: 0:03:39 lr: 0.000099 grad: 0.0741 (0.0748) loss: 0.8235 (0.8288) time: 0.1534 data: 0.0743 max mem: 9390 +Train: [33] [4800/6250] eta: 0:03:25 lr: 0.000099 grad: 0.0731 (0.0750) loss: 0.8209 (0.8287) time: 0.1509 data: 0.0684 max mem: 9390 +Train: [33] [4900/6250] eta: 0:03:11 lr: 0.000099 grad: 0.0731 (0.0750) loss: 0.8245 (0.8287) time: 0.1250 data: 0.0453 max mem: 9390 +Train: [33] [5000/6250] eta: 0:02:57 lr: 0.000099 grad: 0.0732 (0.0750) loss: 0.8303 (0.8286) time: 0.1476 data: 0.0662 max mem: 9390 +Train: [33] [5100/6250] eta: 0:02:43 lr: 0.000099 grad: 0.0687 (0.0751) loss: 0.8293 (0.8286) time: 0.1599 data: 0.0793 max mem: 9390 +Train: [33] [5200/6250] eta: 0:02:29 lr: 0.000099 grad: 0.0699 (0.0751) loss: 0.8261 (0.8285) time: 0.1168 data: 0.0330 max mem: 9390 +Train: [33] [5300/6250] eta: 0:02:14 lr: 0.000099 grad: 0.0765 (0.0751) loss: 0.8230 (0.8285) time: 0.1632 data: 0.0814 max mem: 9390 +Train: [33] [5400/6250] eta: 0:02:00 lr: 0.000099 grad: 0.0754 (0.0750) loss: 0.8245 (0.8284) time: 0.1594 data: 0.0796 max mem: 9390 +Train: [33] [5500/6250] eta: 0:01:46 lr: 0.000099 grad: 0.0725 (0.0751) loss: 0.8301 (0.8284) time: 0.1372 data: 0.0546 max mem: 9390 +Train: [33] [5600/6250] eta: 0:01:31 lr: 0.000099 grad: 0.0745 (0.0751) loss: 0.8205 (0.8283) time: 0.1470 data: 0.0658 max mem: 9390 +Train: [33] [5700/6250] eta: 0:01:17 lr: 0.000099 grad: 0.0788 (0.0751) loss: 0.8209 (0.8281) time: 0.1579 data: 0.0744 max mem: 9390 +Train: [33] [5800/6250] eta: 0:01:03 lr: 0.000099 grad: 0.0757 (0.0752) loss: 0.8257 (0.8280) time: 0.1209 data: 0.0381 max mem: 9390 +Train: [33] [5900/6250] eta: 0:00:49 lr: 0.000098 grad: 0.0733 (0.0752) loss: 0.8229 (0.8280) time: 0.1267 data: 0.0449 max mem: 9390 +Train: [33] [6000/6250] eta: 0:00:35 lr: 0.000098 grad: 0.0730 (0.0752) loss: 0.8242 (0.8279) time: 0.1284 data: 0.0494 max mem: 9390 +Train: [33] [6100/6250] eta: 0:00:21 lr: 0.000098 grad: 0.0690 (0.0752) loss: 0.8335 (0.8279) time: 0.1186 data: 0.0366 max mem: 9390 +Train: [33] [6200/6250] eta: 0:00:07 lr: 0.000098 grad: 0.0681 (0.0752) loss: 0.8248 (0.8279) time: 0.1428 data: 0.0648 max mem: 9390 +Train: [33] [6249/6250] eta: 0:00:00 lr: 0.000098 grad: 0.0732 (0.0752) loss: 0.8291 (0.8279) time: 0.1402 data: 0.0527 max mem: 9390 +Train: [33] Total time: 0:14:48 (0.1421 s / it) +Averaged stats: lr: 0.000098 grad: 0.0732 (0.0752) loss: 0.8291 (0.8279) +Eval (hcp-train-subset): [33] [ 0/62] eta: 0:05:31 loss: 0.8523 (0.8523) time: 5.3486 data: 5.3163 max mem: 9390 +Eval (hcp-train-subset): [33] [61/62] eta: 0:00:00 loss: 0.8413 (0.8425) time: 0.1555 data: 0.1305 max mem: 9390 +Eval (hcp-train-subset): [33] Total time: 0:00:14 (0.2396 s / it) +Averaged stats (hcp-train-subset): loss: 0.8413 (0.8425) +Eval (hcp-val): [33] [ 0/62] eta: 0:04:38 loss: 0.8335 (0.8335) time: 4.4904 data: 4.4594 max mem: 9390 +Eval (hcp-val): [33] [61/62] eta: 0:00:00 loss: 0.8386 (0.8388) time: 0.1239 data: 0.0992 max mem: 9390 +Eval (hcp-val): [33] Total time: 0:00:13 (0.2097 s / it) +Averaged stats (hcp-val): loss: 0.8386 (0.8388) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +Train: [34] [ 0/6250] eta: 7:08:16 lr: 0.000098 grad: 0.0431 (0.0431) loss: 0.8703 (0.8703) time: 4.1114 data: 3.8441 max mem: 9390 +Train: [34] [ 100/6250] eta: 0:19:23 lr: 0.000098 grad: 0.0723 (0.0842) loss: 0.8257 (0.8344) time: 0.1494 data: 0.0526 max mem: 9390 +Train: [34] [ 200/6250] eta: 0:17:23 lr: 0.000098 grad: 0.0768 (0.0814) loss: 0.8251 (0.8306) time: 0.1525 data: 0.0657 max mem: 9390 +Train: [34] [ 300/6250] eta: 0:16:19 lr: 0.000098 grad: 0.0680 (0.0788) loss: 0.8366 (0.8308) time: 0.1428 data: 0.0451 max mem: 9390 +Train: [34] [ 400/6250] eta: 0:15:41 lr: 0.000098 grad: 0.0687 (0.0766) loss: 0.8370 (0.8321) time: 0.1509 data: 0.0652 max mem: 9390 +Train: [34] [ 500/6250] eta: 0:15:03 lr: 0.000098 grad: 0.0713 (0.0759) loss: 0.8294 (0.8319) time: 0.1304 data: 0.0412 max mem: 9390 +Train: [34] [ 600/6250] eta: 0:14:27 lr: 0.000098 grad: 0.0681 (0.0753) loss: 0.8332 (0.8315) time: 0.1294 data: 0.0457 max mem: 9390 +Train: [34] [ 700/6250] eta: 0:13:55 lr: 0.000098 grad: 0.0674 (0.0748) loss: 0.8334 (0.8313) time: 0.1389 data: 0.0477 max mem: 9390 +Train: [34] [ 800/6250] eta: 0:13:29 lr: 0.000098 grad: 0.0671 (0.0742) loss: 0.8309 (0.8315) time: 0.1405 data: 0.0530 max mem: 9390 +Train: [34] [ 900/6250] eta: 0:13:16 lr: 0.000098 grad: 0.0675 (0.0738) loss: 0.8310 (0.8315) time: 0.1369 data: 0.0517 max mem: 9390 +Train: [34] [1000/6250] eta: 0:12:59 lr: 0.000098 grad: 0.0702 (0.0734) loss: 0.8282 (0.8315) time: 0.1551 data: 0.0768 max mem: 9390 +Train: [34] [1100/6250] eta: 0:12:47 lr: 0.000098 grad: 0.0690 (0.0731) loss: 0.8343 (0.8316) time: 0.1541 data: 0.0802 max mem: 9390 +Train: [34] [1200/6250] eta: 0:12:32 lr: 0.000098 grad: 0.0671 (0.0729) loss: 0.8279 (0.8315) time: 0.1645 data: 0.0837 max mem: 9390 +Train: [34] [1300/6250] eta: 0:12:14 lr: 0.000098 grad: 0.0747 (0.0731) loss: 0.8279 (0.8313) time: 0.1649 data: 0.0848 max mem: 9390 +Train: [34] [1400/6250] eta: 0:11:56 lr: 0.000098 grad: 0.0703 (0.0731) loss: 0.8276 (0.8312) time: 0.1336 data: 0.0522 max mem: 9390 +Train: [34] [1500/6250] eta: 0:11:39 lr: 0.000098 grad: 0.0725 (0.0732) loss: 0.8291 (0.8311) time: 0.1424 data: 0.0588 max mem: 9390 +Train: [34] [1600/6250] eta: 0:11:22 lr: 0.000098 grad: 0.0700 (0.0733) loss: 0.8279 (0.8310) time: 0.1140 data: 0.0334 max mem: 9390 +Train: [34] [1700/6250] eta: 0:11:07 lr: 0.000098 grad: 0.0718 (0.0734) loss: 0.8370 (0.8308) time: 0.1604 data: 0.0810 max mem: 9390 +Train: [34] [1800/6250] eta: 0:10:50 lr: 0.000098 grad: 0.0763 (0.0736) loss: 0.8255 (0.8305) time: 0.1411 data: 0.0589 max mem: 9390 +Train: [34] [1900/6250] eta: 0:10:32 lr: 0.000098 grad: 0.0720 (0.0737) loss: 0.8266 (0.8303) time: 0.1367 data: 0.0546 max mem: 9390 +Train: [34] [2000/6250] eta: 0:10:15 lr: 0.000098 grad: 0.0731 (0.0738) loss: 0.8215 (0.8301) time: 0.1195 data: 0.0385 max mem: 9390 +Train: [34] [2100/6250] eta: 0:09:59 lr: 0.000098 grad: 0.0732 (0.0740) loss: 0.8287 (0.8299) time: 0.1436 data: 0.0608 max mem: 9390 +Train: [34] [2200/6250] eta: 0:09:41 lr: 0.000098 grad: 0.0678 (0.0741) loss: 0.8273 (0.8299) time: 0.1361 data: 0.0489 max mem: 9390 +Train: [34] [2300/6250] eta: 0:09:26 lr: 0.000098 grad: 0.0726 (0.0742) loss: 0.8308 (0.8298) time: 0.1157 data: 0.0335 max mem: 9390 +Train: [34] [2400/6250] eta: 0:09:10 lr: 0.000098 grad: 0.0741 (0.0742) loss: 0.8177 (0.8297) time: 0.1383 data: 0.0532 max mem: 9390 +Train: [34] [2500/6250] eta: 0:08:56 lr: 0.000098 grad: 0.0761 (0.0742) loss: 0.8219 (0.8296) time: 0.1054 data: 0.0268 max mem: 9390 +Train: [34] [2600/6250] eta: 0:08:40 lr: 0.000098 grad: 0.0704 (0.0742) loss: 0.8266 (0.8296) time: 0.1346 data: 0.0541 max mem: 9390 +Train: [34] [2700/6250] eta: 0:08:25 lr: 0.000098 grad: 0.0748 (0.0742) loss: 0.8302 (0.8295) time: 0.1314 data: 0.0566 max mem: 9390 +Train: [34] [2800/6250] eta: 0:08:11 lr: 0.000098 grad: 0.0762 (0.0743) loss: 0.8312 (0.8295) time: 0.1397 data: 0.0572 max mem: 9390 +Train: [34] [2900/6250] eta: 0:07:56 lr: 0.000098 grad: 0.0704 (0.0743) loss: 0.8289 (0.8294) time: 0.1294 data: 0.0464 max mem: 9390 +Train: [34] [3000/6250] eta: 0:07:41 lr: 0.000098 grad: 0.0740 (0.0743) loss: 0.8260 (0.8294) time: 0.1372 data: 0.0589 max mem: 9390 +Train: [34] [3100/6250] eta: 0:07:26 lr: 0.000098 grad: 0.0647 (0.0743) loss: 0.8309 (0.8294) time: 0.1254 data: 0.0487 max mem: 9390 +Train: [34] [3200/6250] eta: 0:07:12 lr: 0.000098 grad: 0.0716 (0.0743) loss: 0.8358 (0.8294) time: 0.1684 data: 0.0904 max mem: 9390 +Train: [34] [3300/6250] eta: 0:06:58 lr: 0.000097 grad: 0.0710 (0.0743) loss: 0.8271 (0.8293) time: 0.1266 data: 0.0448 max mem: 9390 +Train: [34] [3400/6250] eta: 0:06:44 lr: 0.000097 grad: 0.0731 (0.0743) loss: 0.8267 (0.8293) time: 0.1785 data: 0.1024 max mem: 9390 +Train: [34] [3500/6250] eta: 0:06:29 lr: 0.000097 grad: 0.0783 (0.0744) loss: 0.8216 (0.8292) time: 0.1305 data: 0.0406 max mem: 9390 +Train: [34] [3600/6250] eta: 0:06:15 lr: 0.000097 grad: 0.0757 (0.0745) loss: 0.8263 (0.8291) time: 0.1372 data: 0.0581 max mem: 9390 +Train: [34] [3700/6250] eta: 0:06:00 lr: 0.000097 grad: 0.0758 (0.0745) loss: 0.8179 (0.8291) time: 0.1335 data: 0.0510 max mem: 9390 +Train: [34] [3800/6250] eta: 0:05:46 lr: 0.000097 grad: 0.0742 (0.0746) loss: 0.8261 (0.8290) time: 0.1508 data: 0.0742 max mem: 9390 +Train: [34] [3900/6250] eta: 0:05:32 lr: 0.000097 grad: 0.0728 (0.0747) loss: 0.8284 (0.8289) time: 0.1316 data: 0.0490 max mem: 9390 +Train: [34] [4000/6250] eta: 0:05:18 lr: 0.000097 grad: 0.0724 (0.0747) loss: 0.8279 (0.8289) time: 0.1556 data: 0.0787 max mem: 9390 +Train: [34] [4100/6250] eta: 0:05:03 lr: 0.000097 grad: 0.0776 (0.0747) loss: 0.8298 (0.8288) time: 0.1108 data: 0.0299 max mem: 9390 +Train: [34] [4200/6250] eta: 0:04:49 lr: 0.000097 grad: 0.0741 (0.0747) loss: 0.8310 (0.8288) time: 0.1393 data: 0.0524 max mem: 9390 +Train: [34] [4300/6250] eta: 0:04:35 lr: 0.000097 grad: 0.0740 (0.0748) loss: 0.8256 (0.8288) time: 0.1271 data: 0.0411 max mem: 9390 +Train: [34] [4400/6250] eta: 0:04:21 lr: 0.000097 grad: 0.0735 (0.0749) loss: 0.8237 (0.8287) time: 0.1521 data: 0.0750 max mem: 9390 +Train: [34] [4500/6250] eta: 0:04:07 lr: 0.000097 grad: 0.0785 (0.0749) loss: 0.8208 (0.8286) time: 0.1159 data: 0.0336 max mem: 9390 +Train: [34] [4600/6250] eta: 0:03:53 lr: 0.000097 grad: 0.0716 (0.0749) loss: 0.8272 (0.8286) time: 0.1596 data: 0.0850 max mem: 9390 +Train: [34] [4700/6250] eta: 0:03:39 lr: 0.000097 grad: 0.0783 (0.0750) loss: 0.8254 (0.8286) time: 0.1499 data: 0.0730 max mem: 9390 +Train: [34] [4800/6250] eta: 0:03:25 lr: 0.000097 grad: 0.0705 (0.0750) loss: 0.8299 (0.8285) time: 0.1570 data: 0.0763 max mem: 9390 +Train: [34] [4900/6250] eta: 0:03:11 lr: 0.000097 grad: 0.0733 (0.0749) loss: 0.8300 (0.8286) time: 0.1631 data: 0.0793 max mem: 9390 +Train: [34] [5000/6250] eta: 0:02:57 lr: 0.000097 grad: 0.0745 (0.0750) loss: 0.8219 (0.8285) time: 0.1562 data: 0.0760 max mem: 9390 +Train: [34] [5100/6250] eta: 0:02:43 lr: 0.000097 grad: 0.0789 (0.0750) loss: 0.8213 (0.8285) time: 0.1437 data: 0.0594 max mem: 9390 +Train: [34] [5200/6250] eta: 0:02:29 lr: 0.000097 grad: 0.0772 (0.0751) loss: 0.8223 (0.8284) time: 0.1454 data: 0.0652 max mem: 9390 +Train: [34] [5300/6250] eta: 0:02:15 lr: 0.000097 grad: 0.0775 (0.0751) loss: 0.8248 (0.8284) time: 0.1416 data: 0.0623 max mem: 9390 +Train: [34] [5400/6250] eta: 0:02:01 lr: 0.000097 grad: 0.0715 (0.0752) loss: 0.8261 (0.8283) time: 0.1300 data: 0.0471 max mem: 9390 +Train: [34] [5500/6250] eta: 0:01:46 lr: 0.000097 grad: 0.0714 (0.0752) loss: 0.8247 (0.8283) time: 0.1425 data: 0.0670 max mem: 9390 +Train: [34] [5600/6250] eta: 0:01:32 lr: 0.000097 grad: 0.0725 (0.0753) loss: 0.8271 (0.8281) time: 0.1223 data: 0.0393 max mem: 9390 +Train: [34] [5700/6250] eta: 0:01:18 lr: 0.000097 grad: 0.0820 (0.0753) loss: 0.8274 (0.8281) time: 0.1159 data: 0.0338 max mem: 9390 +Train: [34] [5800/6250] eta: 0:01:03 lr: 0.000097 grad: 0.0739 (0.0754) loss: 0.8281 (0.8280) time: 0.1546 data: 0.0671 max mem: 9390 +Train: [34] [5900/6250] eta: 0:00:49 lr: 0.000097 grad: 0.0779 (0.0754) loss: 0.8250 (0.8279) time: 0.1277 data: 0.0460 max mem: 9390 +Train: [34] [6000/6250] eta: 0:00:35 lr: 0.000097 grad: 0.0758 (0.0755) loss: 0.8237 (0.8278) time: 0.1224 data: 0.0409 max mem: 9390 +Train: [34] [6100/6250] eta: 0:00:21 lr: 0.000097 grad: 0.0731 (0.0756) loss: 0.8263 (0.8278) time: 0.1231 data: 0.0431 max mem: 9390 +Train: [34] [6200/6250] eta: 0:00:07 lr: 0.000097 grad: 0.0720 (0.0756) loss: 0.8332 (0.8277) time: 0.1510 data: 0.0727 max mem: 9390 +Train: [34] [6249/6250] eta: 0:00:00 lr: 0.000097 grad: 0.0746 (0.0756) loss: 0.8280 (0.8277) time: 0.1210 data: 0.0421 max mem: 9390 +Train: [34] Total time: 0:14:50 (0.1425 s / it) +Averaged stats: lr: 0.000097 grad: 0.0746 (0.0756) loss: 0.8280 (0.8277) +Eval (hcp-train-subset): [34] [ 0/62] eta: 0:05:55 loss: 0.8483 (0.8483) time: 5.7341 data: 5.7027 max mem: 9390 +Eval (hcp-train-subset): [34] [61/62] eta: 0:00:00 loss: 0.8386 (0.8407) time: 0.1547 data: 0.1300 max mem: 9390 +Eval (hcp-train-subset): [34] Total time: 0:00:14 (0.2390 s / it) +Averaged stats (hcp-train-subset): loss: 0.8386 (0.8407) +Making plots (hcp-train-subset): example=8 +Eval (hcp-val): [34] [ 0/62] eta: 0:04:09 loss: 0.8360 (0.8360) time: 4.0294 data: 3.9600 max mem: 9390 +Eval (hcp-val): [34] [61/62] eta: 0:00:00 loss: 0.8379 (0.8387) time: 0.1225 data: 0.0977 max mem: 9390 +Eval (hcp-val): [34] Total time: 0:00:12 (0.2035 s / it) +Averaged stats (hcp-val): loss: 0.8379 (0.8387) +Making plots (hcp-val): example=20 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +Train: [35] [ 0/6250] eta: 8:03:02 lr: 0.000097 grad: 0.0718 (0.0718) loss: 0.8336 (0.8336) time: 4.6371 data: 4.4700 max mem: 9390 +Train: [35] [ 100/6250] eta: 0:19:22 lr: 0.000097 grad: 0.0679 (0.0813) loss: 0.8269 (0.8272) time: 0.1426 data: 0.0559 max mem: 9390 +Train: [35] [ 200/6250] eta: 0:16:29 lr: 0.000097 grad: 0.0699 (0.0766) loss: 0.8304 (0.8294) time: 0.1290 data: 0.0409 max mem: 9390 +Train: [35] [ 300/6250] eta: 0:15:48 lr: 0.000097 grad: 0.0643 (0.0745) loss: 0.8335 (0.8302) time: 0.1360 data: 0.0552 max mem: 9390 +Train: [35] [ 400/6250] eta: 0:15:02 lr: 0.000097 grad: 0.0662 (0.0731) loss: 0.8340 (0.8310) time: 0.1304 data: 0.0503 max mem: 9390 +Train: [35] [ 500/6250] eta: 0:14:36 lr: 0.000097 grad: 0.0699 (0.0725) loss: 0.8336 (0.8319) time: 0.1413 data: 0.0520 max mem: 9390 +Train: [35] [ 600/6250] eta: 0:14:05 lr: 0.000097 grad: 0.0736 (0.0724) loss: 0.8295 (0.8323) time: 0.1195 data: 0.0425 max mem: 9390 +Train: [35] [ 700/6250] eta: 0:13:40 lr: 0.000096 grad: 0.0663 (0.0720) loss: 0.8345 (0.8325) time: 0.1210 data: 0.0370 max mem: 9390 +Train: [35] [ 800/6250] eta: 0:13:14 lr: 0.000096 grad: 0.0700 (0.0720) loss: 0.8385 (0.8324) time: 0.1388 data: 0.0566 max mem: 9390 +Train: [35] [ 900/6250] eta: 0:12:57 lr: 0.000096 grad: 0.0662 (0.0720) loss: 0.8329 (0.8324) time: 0.1222 data: 0.0385 max mem: 9390 +Train: [35] [1000/6250] eta: 0:12:43 lr: 0.000096 grad: 0.0727 (0.0719) loss: 0.8287 (0.8322) time: 0.1578 data: 0.0829 max mem: 9390 +Train: [35] [1100/6250] eta: 0:12:29 lr: 0.000096 grad: 0.0710 (0.0720) loss: 0.8302 (0.8319) time: 0.1642 data: 0.0863 max mem: 9390 +Train: [35] [1200/6250] eta: 0:12:12 lr: 0.000096 grad: 0.0752 (0.0724) loss: 0.8277 (0.8315) time: 0.1583 data: 0.0804 max mem: 9390 +Train: [35] [1300/6250] eta: 0:11:58 lr: 0.000096 grad: 0.0688 (0.0724) loss: 0.8252 (0.8312) time: 0.1566 data: 0.0779 max mem: 9390 +Train: [35] [1400/6250] eta: 0:11:40 lr: 0.000096 grad: 0.0719 (0.0725) loss: 0.8259 (0.8311) time: 0.1464 data: 0.0682 max mem: 9390 +Train: [35] [1500/6250] eta: 0:11:25 lr: 0.000096 grad: 0.0710 (0.0726) loss: 0.8315 (0.8307) time: 0.1356 data: 0.0541 max mem: 9390 +Train: [35] [1600/6250] eta: 0:11:09 lr: 0.000096 grad: 0.0751 (0.0726) loss: 0.8279 (0.8306) time: 0.1448 data: 0.0613 max mem: 9390 +Train: [35] [1700/6250] eta: 0:10:54 lr: 0.000096 grad: 0.0712 (0.0726) loss: 0.8286 (0.8304) time: 0.1329 data: 0.0498 max mem: 9390 +Train: [35] [1800/6250] eta: 0:10:42 lr: 0.000096 grad: 0.0770 (0.0728) loss: 0.8275 (0.8302) time: 0.1146 data: 0.0370 max mem: 9390 +Train: [35] [1900/6250] eta: 0:10:26 lr: 0.000096 grad: 0.0723 (0.0730) loss: 0.8287 (0.8300) time: 0.1272 data: 0.0468 max mem: 9390 +Train: [35] [2000/6250] eta: 0:10:12 lr: 0.000096 grad: 0.0696 (0.0731) loss: 0.8330 (0.8298) time: 0.1485 data: 0.0725 max mem: 9390 +Train: [35] [2100/6250] eta: 0:09:55 lr: 0.000096 grad: 0.0737 (0.0733) loss: 0.8258 (0.8297) time: 0.1477 data: 0.0699 max mem: 9390 +Train: [35] [2200/6250] eta: 0:09:39 lr: 0.000096 grad: 0.0721 (0.0735) loss: 0.8283 (0.8296) time: 0.1448 data: 0.0670 max mem: 9390 +Train: [35] [2300/6250] eta: 0:09:23 lr: 0.000096 grad: 0.0755 (0.0735) loss: 0.8261 (0.8295) time: 0.1384 data: 0.0573 max mem: 9390 +Train: [35] [2400/6250] eta: 0:09:08 lr: 0.000096 grad: 0.0719 (0.0736) loss: 0.8281 (0.8294) time: 0.1370 data: 0.0624 max mem: 9390 +Train: [35] [2500/6250] eta: 0:08:53 lr: 0.000096 grad: 0.0724 (0.0738) loss: 0.8272 (0.8294) time: 0.1409 data: 0.0593 max mem: 9390 +Train: [35] [2600/6250] eta: 0:08:38 lr: 0.000096 grad: 0.0753 (0.0739) loss: 0.8263 (0.8292) time: 0.1342 data: 0.0525 max mem: 9390 +Train: [35] [2700/6250] eta: 0:08:24 lr: 0.000096 grad: 0.0711 (0.0740) loss: 0.8255 (0.8291) time: 0.1637 data: 0.0776 max mem: 9390 +Train: [35] [2800/6250] eta: 0:08:10 lr: 0.000096 grad: 0.0764 (0.0740) loss: 0.8267 (0.8291) time: 0.0985 data: 0.0173 max mem: 9390 +Train: [35] [2900/6250] eta: 0:07:56 lr: 0.000096 grad: 0.0708 (0.0740) loss: 0.8299 (0.8291) time: 0.1399 data: 0.0623 max mem: 9390 +Train: [35] [3000/6250] eta: 0:07:41 lr: 0.000096 grad: 0.0775 (0.0741) loss: 0.8230 (0.8291) time: 0.1309 data: 0.0537 max mem: 9390 +Train: [35] [3100/6250] eta: 0:07:27 lr: 0.000096 grad: 0.0788 (0.0742) loss: 0.8288 (0.8290) time: 0.1279 data: 0.0485 max mem: 9390 +Train: [35] [3200/6250] eta: 0:07:12 lr: 0.000096 grad: 0.0763 (0.0743) loss: 0.8314 (0.8290) time: 0.1454 data: 0.0680 max mem: 9390 +Train: [35] [3300/6250] eta: 0:06:58 lr: 0.000096 grad: 0.0724 (0.0744) loss: 0.8314 (0.8291) time: 0.1526 data: 0.0675 max mem: 9390 +Train: [35] [3400/6250] eta: 0:06:44 lr: 0.000096 grad: 0.0768 (0.0745) loss: 0.8246 (0.8291) time: 0.1339 data: 0.0554 max mem: 9390 +Train: [35] [3500/6250] eta: 0:06:30 lr: 0.000096 grad: 0.0711 (0.0745) loss: 0.8309 (0.8291) time: 0.1414 data: 0.0583 max mem: 9390 +Train: [35] [3600/6250] eta: 0:06:15 lr: 0.000096 grad: 0.0733 (0.0746) loss: 0.8285 (0.8291) time: 0.1269 data: 0.0518 max mem: 9390 +Train: [35] [3700/6250] eta: 0:06:01 lr: 0.000096 grad: 0.0759 (0.0746) loss: 0.8306 (0.8290) time: 0.1435 data: 0.0670 max mem: 9390 +Train: [35] [3800/6250] eta: 0:05:46 lr: 0.000096 grad: 0.0760 (0.0747) loss: 0.8227 (0.8290) time: 0.1326 data: 0.0519 max mem: 9390 +Train: [35] [3900/6250] eta: 0:05:33 lr: 0.000096 grad: 0.0728 (0.0748) loss: 0.8289 (0.8291) time: 0.1697 data: 0.0931 max mem: 9390 +Train: [35] [4000/6250] eta: 0:05:18 lr: 0.000096 grad: 0.0746 (0.0749) loss: 0.8286 (0.8291) time: 0.1382 data: 0.0600 max mem: 9390 +Train: [35] [4100/6250] eta: 0:05:04 lr: 0.000096 grad: 0.0698 (0.0750) loss: 0.8341 (0.8291) time: 0.1304 data: 0.0549 max mem: 9390 +Train: [35] [4200/6250] eta: 0:04:50 lr: 0.000096 grad: 0.0769 (0.0751) loss: 0.8288 (0.8291) time: 0.1311 data: 0.0494 max mem: 9390 +Train: [35] [4300/6250] eta: 0:04:36 lr: 0.000095 grad: 0.0774 (0.0752) loss: 0.8311 (0.8291) time: 0.1441 data: 0.0597 max mem: 9390 +Train: [35] [4400/6250] eta: 0:04:21 lr: 0.000095 grad: 0.0796 (0.0752) loss: 0.8274 (0.8291) time: 0.1288 data: 0.0495 max mem: 9390 +Train: [35] [4500/6250] eta: 0:04:07 lr: 0.000095 grad: 0.0754 (0.0753) loss: 0.8308 (0.8291) time: 0.1421 data: 0.0669 max mem: 9390 +Train: [35] [4600/6250] eta: 0:03:53 lr: 0.000095 grad: 0.0760 (0.0754) loss: 0.8158 (0.8290) time: 0.1631 data: 0.0823 max mem: 9390 +Train: [35] [4700/6250] eta: 0:03:39 lr: 0.000095 grad: 0.0826 (0.0755) loss: 0.8255 (0.8289) time: 0.1469 data: 0.0670 max mem: 9390 +Train: [35] [4800/6250] eta: 0:03:26 lr: 0.000095 grad: 0.0771 (0.0756) loss: 0.8254 (0.8288) time: 0.1595 data: 0.0732 max mem: 9390 +Train: [35] [4900/6250] eta: 0:03:11 lr: 0.000095 grad: 0.0717 (0.0757) loss: 0.8257 (0.8287) time: 0.1412 data: 0.0609 max mem: 9390 +Train: [35] [5000/6250] eta: 0:02:57 lr: 0.000095 grad: 0.0740 (0.0757) loss: 0.8267 (0.8287) time: 0.1463 data: 0.0676 max mem: 9390 +Train: [35] [5100/6250] eta: 0:02:43 lr: 0.000095 grad: 0.0747 (0.0757) loss: 0.8257 (0.8286) time: 0.1439 data: 0.0677 max mem: 9390 +Train: [35] [5200/6250] eta: 0:02:29 lr: 0.000095 grad: 0.0786 (0.0758) loss: 0.8205 (0.8286) time: 0.1438 data: 0.0630 max mem: 9390 +Train: [35] [5300/6250] eta: 0:02:15 lr: 0.000095 grad: 0.0826 (0.0759) loss: 0.8244 (0.8285) time: 0.1215 data: 0.0415 max mem: 9390 +Train: [35] [5400/6250] eta: 0:02:00 lr: 0.000095 grad: 0.0810 (0.0760) loss: 0.8225 (0.8285) time: 0.1200 data: 0.0324 max mem: 9390 +Train: [35] [5500/6250] eta: 0:01:46 lr: 0.000095 grad: 0.0799 (0.0761) loss: 0.8240 (0.8284) time: 0.1304 data: 0.0490 max mem: 9390 +Train: [35] [5600/6250] eta: 0:01:32 lr: 0.000095 grad: 0.0808 (0.0761) loss: 0.8303 (0.8283) time: 0.1355 data: 0.0578 max mem: 9390 +Train: [35] [5700/6250] eta: 0:01:17 lr: 0.000095 grad: 0.0737 (0.0762) loss: 0.8301 (0.8283) time: 0.1316 data: 0.0510 max mem: 9390 +Train: [35] [5800/6250] eta: 0:01:03 lr: 0.000095 grad: 0.0771 (0.0763) loss: 0.8239 (0.8283) time: 0.1654 data: 0.0784 max mem: 9390 +Train: [35] [5900/6250] eta: 0:00:49 lr: 0.000095 grad: 0.0832 (0.0764) loss: 0.8222 (0.8282) time: 0.1545 data: 0.0797 max mem: 9390 +Train: [35] [6000/6250] eta: 0:00:35 lr: 0.000095 grad: 0.0849 (0.0765) loss: 0.8222 (0.8281) time: 0.1212 data: 0.0446 max mem: 9390 +Train: [35] [6100/6250] eta: 0:00:21 lr: 0.000095 grad: 0.0724 (0.0766) loss: 0.8295 (0.8281) time: 0.1309 data: 0.0545 max mem: 9390 +Train: [35] [6200/6250] eta: 0:00:07 lr: 0.000095 grad: 0.0751 (0.0766) loss: 0.8244 (0.8281) time: 0.1388 data: 0.0626 max mem: 9390 +Train: [35] [6249/6250] eta: 0:00:00 lr: 0.000095 grad: 0.0799 (0.0766) loss: 0.8234 (0.8280) time: 0.1347 data: 0.0529 max mem: 9390 +Train: [35] Total time: 0:14:48 (0.1422 s / it) +Averaged stats: lr: 0.000095 grad: 0.0799 (0.0766) loss: 0.8234 (0.8280) +Eval (hcp-train-subset): [35] [ 0/62] eta: 0:03:24 loss: 0.8504 (0.8504) time: 3.2918 data: 3.2091 max mem: 9390 +Eval (hcp-train-subset): [35] [61/62] eta: 0:00:00 loss: 0.8403 (0.8420) time: 0.1483 data: 0.1216 max mem: 9390 +Eval (hcp-train-subset): [35] Total time: 0:00:13 (0.2258 s / it) +Averaged stats (hcp-train-subset): loss: 0.8403 (0.8420) +Eval (hcp-val): [35] [ 0/62] eta: 0:04:23 loss: 0.8332 (0.8332) time: 4.2498 data: 4.2040 max mem: 9390 +Eval (hcp-val): [35] [61/62] eta: 0:00:00 loss: 0.8373 (0.8384) time: 0.1249 data: 0.1001 max mem: 9390 +Eval (hcp-val): [35] Total time: 0:00:13 (0.2154 s / it) +Averaged stats (hcp-val): loss: 0.8373 (0.8384) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +Train: [36] [ 0/6250] eta: 10:35:13 lr: 0.000095 grad: 0.1314 (0.1314) loss: 0.8462 (0.8462) time: 6.0982 data: 5.9483 max mem: 9390 +Train: [36] [ 100/6250] eta: 0:19:48 lr: 0.000095 grad: 0.0741 (0.0778) loss: 0.8288 (0.8338) time: 0.1643 data: 0.0793 max mem: 9390 +Train: [36] [ 200/6250] eta: 0:17:05 lr: 0.000095 grad: 0.0705 (0.0767) loss: 0.8299 (0.8305) time: 0.1350 data: 0.0474 max mem: 9390 +Train: [36] [ 300/6250] eta: 0:15:59 lr: 0.000095 grad: 0.0705 (0.0750) loss: 0.8246 (0.8297) time: 0.1221 data: 0.0416 max mem: 9390 +Train: [36] [ 400/6250] eta: 0:15:16 lr: 0.000095 grad: 0.0752 (0.0748) loss: 0.8266 (0.8291) time: 0.1244 data: 0.0391 max mem: 9390 +Train: [36] [ 500/6250] eta: 0:14:42 lr: 0.000095 grad: 0.0741 (0.0746) loss: 0.8273 (0.8288) time: 0.1406 data: 0.0517 max mem: 9390 +Train: [36] [ 600/6250] eta: 0:14:12 lr: 0.000095 grad: 0.0751 (0.0744) loss: 0.8295 (0.8284) time: 0.1478 data: 0.0520 max mem: 9390 +Train: [36] [ 700/6250] eta: 0:13:41 lr: 0.000095 grad: 0.0730 (0.0750) loss: 0.8222 (0.8283) time: 0.1393 data: 0.0599 max mem: 9390 +Train: [36] [ 800/6250] eta: 0:13:24 lr: 0.000095 grad: 0.0790 (0.0752) loss: 0.8272 (0.8286) time: 0.1491 data: 0.0715 max mem: 9390 +Train: [36] [ 900/6250] eta: 0:13:11 lr: 0.000095 grad: 0.0718 (0.0753) loss: 0.8288 (0.8286) time: 0.1454 data: 0.0667 max mem: 9390 +Train: [36] [1000/6250] eta: 0:12:55 lr: 0.000095 grad: 0.0734 (0.0752) loss: 0.8338 (0.8286) time: 0.1474 data: 0.0693 max mem: 9390 +Train: [36] [1100/6250] eta: 0:12:35 lr: 0.000095 grad: 0.0697 (0.0753) loss: 0.8275 (0.8284) time: 0.1272 data: 0.0463 max mem: 9390 +Train: [36] [1200/6250] eta: 0:12:13 lr: 0.000095 grad: 0.0754 (0.0755) loss: 0.8277 (0.8284) time: 0.1215 data: 0.0353 max mem: 9390 +Train: [36] [1300/6250] eta: 0:12:00 lr: 0.000095 grad: 0.0769 (0.0757) loss: 0.8220 (0.8282) time: 0.1431 data: 0.0585 max mem: 9390 +Train: [36] [1400/6250] eta: 0:11:42 lr: 0.000095 grad: 0.0719 (0.0758) loss: 0.8288 (0.8280) time: 0.1424 data: 0.0633 max mem: 9390 +Train: [36] [1500/6250] eta: 0:11:27 lr: 0.000095 grad: 0.0745 (0.0757) loss: 0.8317 (0.8280) time: 0.1642 data: 0.0903 max mem: 9390 +Train: [36] [1600/6250] eta: 0:11:21 lr: 0.000094 grad: 0.0746 (0.0759) loss: 0.8274 (0.8279) time: 0.2296 data: 0.1138 max mem: 9390 +Train: [36] [1700/6250] eta: 0:11:01 lr: 0.000094 grad: 0.0701 (0.0757) loss: 0.8314 (0.8281) time: 0.1434 data: 0.0581 max mem: 9390 +Train: [36] [1800/6250] eta: 0:10:45 lr: 0.000094 grad: 0.0776 (0.0757) loss: 0.8294 (0.8281) time: 0.1332 data: 0.0557 max mem: 9390 +Train: [36] [1900/6250] eta: 0:10:30 lr: 0.000094 grad: 0.0797 (0.0762) loss: 0.8298 (0.8282) time: 0.1463 data: 0.0634 max mem: 9390 +Train: [36] [2000/6250] eta: 0:10:12 lr: 0.000094 grad: 0.0743 (0.0761) loss: 0.8272 (0.8282) time: 0.1300 data: 0.0510 max mem: 9390 +Train: [36] [2100/6250] eta: 0:09:59 lr: 0.000094 grad: 0.0755 (0.0768) loss: 0.8309 (0.8282) time: 0.1582 data: 0.0789 max mem: 9390 +Train: [36] [2200/6250] eta: 0:09:43 lr: 0.000094 grad: 0.0782 (0.0768) loss: 0.8259 (0.8282) time: 0.1323 data: 0.0524 max mem: 9390 +Train: [36] [2300/6250] eta: 0:09:28 lr: 0.000094 grad: 0.0794 (0.0767) loss: 0.8255 (0.8280) time: 0.1387 data: 0.0588 max mem: 9390 +Train: [36] [2400/6250] eta: 0:09:13 lr: 0.000094 grad: 0.0771 (0.0770) loss: 0.8216 (0.8279) time: 0.1413 data: 0.0628 max mem: 9390 +Train: [36] [2500/6250] eta: 0:08:58 lr: 0.000094 grad: 0.0732 (0.0770) loss: 0.8301 (0.8277) time: 0.1491 data: 0.0720 max mem: 9390 +Train: [36] [2600/6250] eta: 0:08:43 lr: 0.000094 grad: 0.0735 (0.0770) loss: 0.8229 (0.8276) time: 0.1358 data: 0.0403 max mem: 9390 +Train: [36] [2700/6250] eta: 0:08:29 lr: 0.000094 grad: 0.0746 (0.0770) loss: 0.8229 (0.8275) time: 0.1180 data: 0.0353 max mem: 9390 +Train: [36] [2800/6250] eta: 0:08:16 lr: 0.000094 grad: 0.0777 (0.0770) loss: 0.8284 (0.8275) time: 0.1640 data: 0.0899 max mem: 9390 +Train: [36] [2900/6250] eta: 0:08:02 lr: 0.000094 grad: 0.0755 (0.0771) loss: 0.8258 (0.8274) time: 0.1023 data: 0.0163 max mem: 9390 +Train: [36] [3000/6250] eta: 0:07:47 lr: 0.000094 grad: 0.0763 (0.0771) loss: 0.8175 (0.8272) time: 0.1295 data: 0.0483 max mem: 9390 +Train: [36] [3100/6250] eta: 0:07:32 lr: 0.000094 grad: 0.0745 (0.0772) loss: 0.8256 (0.8271) time: 0.1679 data: 0.0904 max mem: 9390 +Train: [36] [3200/6250] eta: 0:07:18 lr: 0.000094 grad: 0.0776 (0.0772) loss: 0.8207 (0.8270) time: 0.1562 data: 0.0825 max mem: 9390 +Train: [36] [3300/6250] eta: 0:07:03 lr: 0.000094 grad: 0.0793 (0.0773) loss: 0.8231 (0.8268) time: 0.1415 data: 0.0577 max mem: 9390 +Train: [36] [3400/6250] eta: 0:06:48 lr: 0.000094 grad: 0.0742 (0.0774) loss: 0.8235 (0.8267) time: 0.1326 data: 0.0534 max mem: 9390 +Train: [36] [3500/6250] eta: 0:06:35 lr: 0.000094 grad: 0.0750 (0.0775) loss: 0.8218 (0.8266) time: 0.1971 data: 0.1176 max mem: 9390 +Train: [36] [3600/6250] eta: 0:06:19 lr: 0.000094 grad: 0.0829 (0.0776) loss: 0.8279 (0.8265) time: 0.1343 data: 0.0522 max mem: 9390 +Train: [36] [3700/6250] eta: 0:06:05 lr: 0.000094 grad: 0.0759 (0.0776) loss: 0.8237 (0.8265) time: 0.1544 data: 0.0746 max mem: 9390 +Train: [36] [3800/6250] eta: 0:05:51 lr: 0.000094 grad: 0.0760 (0.0776) loss: 0.8212 (0.8265) time: 0.1223 data: 0.0439 max mem: 9390 +Train: [36] [3900/6250] eta: 0:05:36 lr: 0.000094 grad: 0.0723 (0.0776) loss: 0.8316 (0.8264) time: 0.1284 data: 0.0449 max mem: 9390 +Train: [36] [4000/6250] eta: 0:05:22 lr: 0.000094 grad: 0.0796 (0.0777) loss: 0.8209 (0.8263) time: 0.1632 data: 0.0755 max mem: 9390 +Train: [36] [4100/6250] eta: 0:05:08 lr: 0.000094 grad: 0.0781 (0.0777) loss: 0.8252 (0.8263) time: 0.1314 data: 0.0454 max mem: 9390 +Train: [36] [4200/6250] eta: 0:04:54 lr: 0.000094 grad: 0.0793 (0.0778) loss: 0.8198 (0.8262) time: 0.1312 data: 0.0547 max mem: 9390 +Train: [36] [4300/6250] eta: 0:04:39 lr: 0.000094 grad: 0.0792 (0.0779) loss: 0.8256 (0.8261) time: 0.1284 data: 0.0482 max mem: 9390 +Train: [36] [4400/6250] eta: 0:04:25 lr: 0.000094 grad: 0.0755 (0.0779) loss: 0.8262 (0.8261) time: 0.1475 data: 0.0653 max mem: 9390 +Train: [36] [4500/6250] eta: 0:04:12 lr: 0.000094 grad: 0.0790 (0.0780) loss: 0.8235 (0.8261) time: 0.2042 data: 0.1155 max mem: 9390 +Train: [36] [4600/6250] eta: 0:03:58 lr: 0.000094 grad: 0.0824 (0.0781) loss: 0.8215 (0.8260) time: 0.1695 data: 0.0819 max mem: 9390 +Train: [36] [4700/6250] eta: 0:03:44 lr: 0.000094 grad: 0.0761 (0.0781) loss: 0.8239 (0.8260) time: 0.1694 data: 0.0882 max mem: 9390 +Train: [36] [4800/6250] eta: 0:03:30 lr: 0.000094 grad: 0.0776 (0.0781) loss: 0.8199 (0.8259) time: 0.1467 data: 0.0678 max mem: 9390 +Train: [36] [4900/6250] eta: 0:03:15 lr: 0.000094 grad: 0.0767 (0.0781) loss: 0.8288 (0.8259) time: 0.1258 data: 0.0458 max mem: 9390 +Train: [36] [5000/6250] eta: 0:03:01 lr: 0.000094 grad: 0.0785 (0.0781) loss: 0.8263 (0.8259) time: 0.1638 data: 0.0805 max mem: 9390 +Train: [36] [5100/6250] eta: 0:02:47 lr: 0.000093 grad: 0.0746 (0.0781) loss: 0.8339 (0.8259) time: 0.1541 data: 0.0746 max mem: 9390 +Train: [36] [5200/6250] eta: 0:02:32 lr: 0.000093 grad: 0.0742 (0.0781) loss: 0.8252 (0.8259) time: 0.1363 data: 0.0609 max mem: 9390 +Train: [36] [5300/6250] eta: 0:02:17 lr: 0.000093 grad: 0.0750 (0.0781) loss: 0.8256 (0.8259) time: 0.1438 data: 0.0602 max mem: 9390 +Train: [36] [5400/6250] eta: 0:02:03 lr: 0.000093 grad: 0.0776 (0.0781) loss: 0.8246 (0.8259) time: 0.1404 data: 0.0644 max mem: 9390 +Train: [36] [5500/6250] eta: 0:01:48 lr: 0.000093 grad: 0.0769 (0.0782) loss: 0.8262 (0.8259) time: 0.1315 data: 0.0569 max mem: 9390 +Train: [36] [5600/6250] eta: 0:01:34 lr: 0.000093 grad: 0.0776 (0.0782) loss: 0.8236 (0.8259) time: 0.1679 data: 0.0828 max mem: 9390 +Train: [36] [5700/6250] eta: 0:01:19 lr: 0.000093 grad: 0.0801 (0.0782) loss: 0.8240 (0.8259) time: 0.1499 data: 0.0703 max mem: 9390 +Train: [36] [5800/6250] eta: 0:01:05 lr: 0.000093 grad: 0.0772 (0.0782) loss: 0.8222 (0.8259) time: 0.1417 data: 0.0650 max mem: 9390 +Train: [36] [5900/6250] eta: 0:00:50 lr: 0.000093 grad: 0.0765 (0.0784) loss: 0.8275 (0.8258) time: 0.1316 data: 0.0439 max mem: 9390 +Train: [36] [6000/6250] eta: 0:00:36 lr: 0.000093 grad: 0.0779 (0.0784) loss: 0.8275 (0.8259) time: 0.1260 data: 0.0402 max mem: 9390 +Train: [36] [6100/6250] eta: 0:00:21 lr: 0.000093 grad: 0.0792 (0.0784) loss: 0.8270 (0.8259) time: 0.1444 data: 0.0555 max mem: 9390 +Train: [36] [6200/6250] eta: 0:00:07 lr: 0.000093 grad: 0.0789 (0.0784) loss: 0.8255 (0.8259) time: 0.1396 data: 0.0573 max mem: 9390 +Train: [36] [6249/6250] eta: 0:00:00 lr: 0.000093 grad: 0.0800 (0.0785) loss: 0.8228 (0.8259) time: 0.1524 data: 0.0664 max mem: 9390 +Train: [36] Total time: 0:15:08 (0.1453 s / it) +Averaged stats: lr: 0.000093 grad: 0.0800 (0.0785) loss: 0.8228 (0.8259) +Eval (hcp-train-subset): [36] [ 0/62] eta: 0:05:22 loss: 0.8529 (0.8529) time: 5.1944 data: 5.1621 max mem: 9390 +Eval (hcp-train-subset): [36] [61/62] eta: 0:00:00 loss: 0.8395 (0.8414) time: 0.1297 data: 0.1019 max mem: 9390 +Eval (hcp-train-subset): [36] Total time: 0:00:13 (0.2201 s / it) +Averaged stats (hcp-train-subset): loss: 0.8395 (0.8414) +Eval (hcp-val): [36] [ 0/62] eta: 0:05:15 loss: 0.8382 (0.8382) time: 5.0813 data: 5.0514 max mem: 9390 +Eval (hcp-val): [36] [61/62] eta: 0:00:00 loss: 0.8376 (0.8386) time: 0.1977 data: 0.1715 max mem: 9390 +Eval (hcp-val): [36] Total time: 0:00:14 (0.2302 s / it) +Averaged stats (hcp-val): loss: 0.8376 (0.8386) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +Train: [37] [ 0/6250] eta: 9:18:42 lr: 0.000093 grad: 0.1329 (0.1329) loss: 0.8065 (0.8065) time: 5.3636 data: 5.2370 max mem: 9390 +Train: [37] [ 100/6250] eta: 0:19:38 lr: 0.000093 grad: 0.0737 (0.0860) loss: 0.8396 (0.8349) time: 0.1230 data: 0.0299 max mem: 9390 +Train: [37] [ 200/6250] eta: 0:16:45 lr: 0.000093 grad: 0.0736 (0.0847) loss: 0.8323 (0.8328) time: 0.1438 data: 0.0577 max mem: 9390 +Train: [37] [ 300/6250] eta: 0:15:39 lr: 0.000093 grad: 0.0760 (0.0825) loss: 0.8318 (0.8325) time: 0.1410 data: 0.0551 max mem: 9390 +Train: [37] [ 400/6250] eta: 0:15:08 lr: 0.000093 grad: 0.0769 (0.0821) loss: 0.8373 (0.8332) time: 0.1202 data: 0.0362 max mem: 9390 +Train: [37] [ 500/6250] eta: 0:14:37 lr: 0.000093 grad: 0.0752 (0.0809) loss: 0.8323 (0.8330) time: 0.1284 data: 0.0389 max mem: 9390 +Train: [37] [ 600/6250] eta: 0:14:13 lr: 0.000093 grad: 0.0756 (0.0798) loss: 0.8350 (0.8331) time: 0.1408 data: 0.0510 max mem: 9390 +Train: [37] [ 700/6250] eta: 0:13:46 lr: 0.000093 grad: 0.0694 (0.0790) loss: 0.8359 (0.8329) time: 0.1398 data: 0.0525 max mem: 9390 +Train: [37] [ 800/6250] eta: 0:13:20 lr: 0.000093 grad: 0.0719 (0.0781) loss: 0.8304 (0.8331) time: 0.1394 data: 0.0542 max mem: 9390 +Train: [37] [ 900/6250] eta: 0:13:02 lr: 0.000093 grad: 0.0710 (0.0775) loss: 0.8339 (0.8332) time: 0.1487 data: 0.0636 max mem: 9390 +Train: [37] [1000/6250] eta: 0:12:45 lr: 0.000093 grad: 0.0665 (0.0767) loss: 0.8340 (0.8333) time: 0.1586 data: 0.0744 max mem: 9390 +Train: [37] [1100/6250] eta: 0:12:33 lr: 0.000093 grad: 0.0677 (0.0761) loss: 0.8379 (0.8333) time: 0.1617 data: 0.0871 max mem: 9390 +Train: [37] [1200/6250] eta: 0:12:17 lr: 0.000093 grad: 0.0686 (0.0757) loss: 0.8364 (0.8333) time: 0.1559 data: 0.0740 max mem: 9390 +Train: [37] [1300/6250] eta: 0:12:00 lr: 0.000093 grad: 0.0718 (0.0756) loss: 0.8369 (0.8333) time: 0.1365 data: 0.0522 max mem: 9390 +Train: [37] [1400/6250] eta: 0:11:48 lr: 0.000093 grad: 0.0750 (0.0757) loss: 0.8261 (0.8333) time: 0.1717 data: 0.0898 max mem: 9390 +Train: [37] [1500/6250] eta: 0:11:33 lr: 0.000093 grad: 0.0718 (0.0757) loss: 0.8333 (0.8333) time: 0.1619 data: 0.0791 max mem: 9390 +Train: [37] [1600/6250] eta: 0:11:21 lr: 0.000093 grad: 0.0750 (0.0758) loss: 0.8336 (0.8331) time: 0.1961 data: 0.1140 max mem: 9390 +Train: [37] [1700/6250] eta: 0:11:03 lr: 0.000093 grad: 0.0744 (0.0758) loss: 0.8311 (0.8330) time: 0.1382 data: 0.0599 max mem: 9390 +Train: [37] [1800/6250] eta: 0:10:48 lr: 0.000093 grad: 0.0756 (0.0760) loss: 0.8264 (0.8327) time: 0.1484 data: 0.0697 max mem: 9390 +Train: [37] [1900/6250] eta: 0:10:32 lr: 0.000093 grad: 0.0708 (0.0761) loss: 0.8307 (0.8326) time: 0.1114 data: 0.0318 max mem: 9390 +Train: [37] [2000/6250] eta: 0:10:17 lr: 0.000093 grad: 0.0725 (0.0762) loss: 0.8269 (0.8324) time: 0.1435 data: 0.0646 max mem: 9390 +Train: [37] [2100/6250] eta: 0:10:01 lr: 0.000093 grad: 0.0753 (0.0762) loss: 0.8248 (0.8323) time: 0.1306 data: 0.0534 max mem: 9390 +Train: [37] [2200/6250] eta: 0:09:46 lr: 0.000093 grad: 0.0727 (0.0761) loss: 0.8320 (0.8322) time: 0.1621 data: 0.0846 max mem: 9390 +Train: [37] [2300/6250] eta: 0:09:32 lr: 0.000092 grad: 0.0741 (0.0761) loss: 0.8295 (0.8321) time: 0.1654 data: 0.0849 max mem: 9390 +Train: [37] [2400/6250] eta: 0:09:16 lr: 0.000092 grad: 0.0733 (0.0762) loss: 0.8311 (0.8320) time: 0.1427 data: 0.0568 max mem: 9390 +Train: [37] [2500/6250] eta: 0:09:01 lr: 0.000092 grad: 0.0751 (0.0762) loss: 0.8311 (0.8319) time: 0.1358 data: 0.0578 max mem: 9390 +Train: [37] [2600/6250] eta: 0:08:53 lr: 0.000092 grad: 0.0738 (0.0762) loss: 0.8223 (0.8318) time: 0.3714 data: 0.2442 max mem: 9390 +Train: [37] [2700/6250] eta: 0:08:37 lr: 0.000092 grad: 0.0718 (0.0762) loss: 0.8252 (0.8316) time: 0.1521 data: 0.0734 max mem: 9390 +Train: [37] [2800/6250] eta: 0:08:23 lr: 0.000092 grad: 0.0737 (0.0762) loss: 0.8265 (0.8315) time: 0.1742 data: 0.0906 max mem: 9390 +Train: [37] [2900/6250] eta: 0:08:09 lr: 0.000092 grad: 0.0753 (0.0762) loss: 0.8283 (0.8314) time: 0.1659 data: 0.0875 max mem: 9390 +Train: [37] [3000/6250] eta: 0:07:54 lr: 0.000092 grad: 0.0769 (0.0763) loss: 0.8319 (0.8313) time: 0.1387 data: 0.0650 max mem: 9390 +Train: [37] [3100/6250] eta: 0:07:38 lr: 0.000092 grad: 0.0727 (0.0762) loss: 0.8307 (0.8312) time: 0.1118 data: 0.0338 max mem: 9390 +Train: [37] [3200/6250] eta: 0:07:24 lr: 0.000092 grad: 0.0745 (0.0763) loss: 0.8295 (0.8312) time: 0.1797 data: 0.0988 max mem: 9390 +Train: [37] [3300/6250] eta: 0:07:10 lr: 0.000092 grad: 0.0779 (0.0764) loss: 0.8271 (0.8311) time: 0.1180 data: 0.0420 max mem: 9390 +Train: [37] [3400/6250] eta: 0:06:54 lr: 0.000092 grad: 0.0772 (0.0764) loss: 0.8217 (0.8310) time: 0.1505 data: 0.0625 max mem: 9390 +Train: [37] [3500/6250] eta: 0:06:39 lr: 0.000092 grad: 0.0752 (0.0765) loss: 0.8300 (0.8309) time: 0.1331 data: 0.0559 max mem: 9390 +Train: [37] [3600/6250] eta: 0:06:25 lr: 0.000092 grad: 0.0795 (0.0765) loss: 0.8287 (0.8309) time: 0.1449 data: 0.0647 max mem: 9390 +Train: [37] [3700/6250] eta: 0:06:10 lr: 0.000092 grad: 0.0805 (0.0767) loss: 0.8229 (0.8307) time: 0.1622 data: 0.0825 max mem: 9390 +Train: [37] [3800/6250] eta: 0:05:55 lr: 0.000092 grad: 0.0757 (0.0768) loss: 0.8268 (0.8307) time: 0.1308 data: 0.0537 max mem: 9390 +Train: [37] [3900/6250] eta: 0:05:40 lr: 0.000092 grad: 0.0799 (0.0768) loss: 0.8256 (0.8306) time: 0.1544 data: 0.0794 max mem: 9390 +Train: [37] [4000/6250] eta: 0:05:25 lr: 0.000092 grad: 0.0771 (0.0769) loss: 0.8253 (0.8305) time: 0.1492 data: 0.0736 max mem: 9390 +Train: [37] [4100/6250] eta: 0:05:11 lr: 0.000092 grad: 0.0760 (0.0770) loss: 0.8252 (0.8304) time: 0.1409 data: 0.0609 max mem: 9390 +Train: [37] [4200/6250] eta: 0:04:57 lr: 0.000092 grad: 0.0786 (0.0771) loss: 0.8227 (0.8303) time: 0.1602 data: 0.0796 max mem: 9390 +Train: [37] [4300/6250] eta: 0:04:43 lr: 0.000092 grad: 0.0770 (0.0771) loss: 0.8223 (0.8302) time: 0.1765 data: 0.0987 max mem: 9390 +Train: [37] [4400/6250] eta: 0:04:28 lr: 0.000092 grad: 0.0768 (0.0772) loss: 0.8292 (0.8301) time: 0.1487 data: 0.0728 max mem: 9390 +Train: [37] [4500/6250] eta: 0:04:14 lr: 0.000092 grad: 0.0718 (0.0772) loss: 0.8318 (0.8301) time: 0.1392 data: 0.0616 max mem: 9390 +Train: [37] [4600/6250] eta: 0:04:00 lr: 0.000092 grad: 0.0723 (0.0772) loss: 0.8278 (0.8300) time: 0.1554 data: 0.0730 max mem: 9390 +Train: [37] [4700/6250] eta: 0:03:45 lr: 0.000092 grad: 0.0774 (0.0772) loss: 0.8217 (0.8300) time: 0.1708 data: 0.0911 max mem: 9390 +Train: [37] [4800/6250] eta: 0:03:31 lr: 0.000092 grad: 0.0712 (0.0773) loss: 0.8266 (0.8300) time: 0.1499 data: 0.0699 max mem: 9390 +Train: [37] [4900/6250] eta: 0:03:16 lr: 0.000092 grad: 0.0732 (0.0773) loss: 0.8361 (0.8300) time: 0.1655 data: 0.0868 max mem: 9390 +Train: [37] [5000/6250] eta: 0:03:01 lr: 0.000092 grad: 0.0844 (0.0774) loss: 0.8267 (0.8299) time: 0.1316 data: 0.0437 max mem: 9390 +Train: [37] [5100/6250] eta: 0:02:46 lr: 0.000092 grad: 0.0761 (0.0774) loss: 0.8234 (0.8299) time: 0.1266 data: 0.0508 max mem: 9390 +Train: [37] [5200/6250] eta: 0:02:32 lr: 0.000092 grad: 0.0796 (0.0774) loss: 0.8292 (0.8299) time: 0.1362 data: 0.0565 max mem: 9390 +Train: [37] [5300/6250] eta: 0:02:17 lr: 0.000092 grad: 0.0766 (0.0774) loss: 0.8255 (0.8299) time: 0.1138 data: 0.0335 max mem: 9390 +Train: [37] [5400/6250] eta: 0:02:03 lr: 0.000092 grad: 0.0757 (0.0774) loss: 0.8264 (0.8299) time: 0.1312 data: 0.0511 max mem: 9390 +Train: [37] [5500/6250] eta: 0:01:48 lr: 0.000092 grad: 0.0773 (0.0774) loss: 0.8299 (0.8299) time: 0.1714 data: 0.0980 max mem: 9390 +Train: [37] [5600/6250] eta: 0:01:34 lr: 0.000092 grad: 0.0800 (0.0775) loss: 0.8297 (0.8298) time: 0.1357 data: 0.0548 max mem: 9390 +Train: [37] [5700/6250] eta: 0:01:19 lr: 0.000091 grad: 0.0781 (0.0776) loss: 0.8339 (0.8298) time: 0.3278 data: 0.2501 max mem: 9390 +Train: [37] [5800/6250] eta: 0:01:05 lr: 0.000091 grad: 0.0739 (0.0776) loss: 0.8273 (0.8298) time: 0.1130 data: 0.0297 max mem: 9390 +Train: [37] [5900/6250] eta: 0:00:50 lr: 0.000091 grad: 0.0705 (0.0776) loss: 0.8307 (0.8298) time: 0.1344 data: 0.0570 max mem: 9390 +Train: [37] [6000/6250] eta: 0:00:36 lr: 0.000091 grad: 0.0756 (0.0776) loss: 0.8273 (0.8298) time: 0.1322 data: 0.0541 max mem: 9390 +Train: [37] [6100/6250] eta: 0:00:21 lr: 0.000091 grad: 0.0752 (0.0776) loss: 0.8283 (0.8297) time: 0.1291 data: 0.0456 max mem: 9390 +Train: [37] [6200/6250] eta: 0:00:07 lr: 0.000091 grad: 0.0811 (0.0776) loss: 0.8281 (0.8297) time: 0.1413 data: 0.0618 max mem: 9390 +Train: [37] [6249/6250] eta: 0:00:00 lr: 0.000091 grad: 0.0749 (0.0776) loss: 0.8285 (0.8297) time: 0.1428 data: 0.0649 max mem: 9390 +Train: [37] Total time: 0:15:07 (0.1453 s / it) +Averaged stats: lr: 0.000091 grad: 0.0749 (0.0776) loss: 0.8285 (0.8297) +Eval (hcp-train-subset): [37] [ 0/62] eta: 0:03:17 loss: 0.8528 (0.8528) time: 3.1795 data: 3.0886 max mem: 9390 +Eval (hcp-train-subset): [37] [61/62] eta: 0:00:00 loss: 0.8411 (0.8417) time: 0.1366 data: 0.1095 max mem: 9390 +Eval (hcp-train-subset): [37] Total time: 0:00:13 (0.2174 s / it) +Averaged stats (hcp-train-subset): loss: 0.8411 (0.8417) +Eval (hcp-val): [37] [ 0/62] eta: 0:04:44 loss: 0.8384 (0.8384) time: 4.5854 data: 4.5549 max mem: 9390 +Eval (hcp-val): [37] [61/62] eta: 0:00:00 loss: 0.8378 (0.8383) time: 0.1387 data: 0.1138 max mem: 9390 +Eval (hcp-val): [37] Total time: 0:00:13 (0.2138 s / it) +Averaged stats (hcp-val): loss: 0.8378 (0.8383) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +Train: [38] [ 0/6250] eta: 6:34:19 lr: 0.000091 grad: 0.1193 (0.1193) loss: 0.8243 (0.8243) time: 3.7855 data: 3.5099 max mem: 9390 +Train: [38] [ 100/6250] eta: 0:20:06 lr: 0.000091 grad: 0.0792 (0.0885) loss: 0.8299 (0.8272) time: 0.1527 data: 0.0640 max mem: 9390 +Train: [38] [ 200/6250] eta: 0:16:46 lr: 0.000091 grad: 0.0868 (0.0895) loss: 0.8228 (0.8226) time: 0.1291 data: 0.0430 max mem: 9390 +Train: [38] [ 300/6250] eta: 0:15:45 lr: 0.000091 grad: 0.0864 (0.0900) loss: 0.8120 (0.8196) time: 0.1343 data: 0.0502 max mem: 9390 +Train: [38] [ 400/6250] eta: 0:14:54 lr: 0.000091 grad: 0.0828 (0.0887) loss: 0.8247 (0.8203) time: 0.1463 data: 0.0643 max mem: 9390 +Train: [38] [ 500/6250] eta: 0:14:05 lr: 0.000091 grad: 0.0776 (0.0870) loss: 0.8300 (0.8214) time: 0.1198 data: 0.0303 max mem: 9390 +Train: [38] [ 600/6250] eta: 0:13:31 lr: 0.000091 grad: 0.0754 (0.0852) loss: 0.8251 (0.8228) time: 0.0969 data: 0.0169 max mem: 9390 +Train: [38] [ 700/6250] eta: 0:13:03 lr: 0.000091 grad: 0.0717 (0.0837) loss: 0.8313 (0.8241) time: 0.1286 data: 0.0414 max mem: 9390 +Train: [38] [ 800/6250] eta: 0:12:33 lr: 0.000091 grad: 0.0731 (0.0823) loss: 0.8312 (0.8253) time: 0.1181 data: 0.0317 max mem: 9390 +Train: [38] [ 900/6250] eta: 0:12:12 lr: 0.000091 grad: 0.0744 (0.0814) loss: 0.8312 (0.8265) time: 0.1223 data: 0.0429 max mem: 9390 +Train: [38] [1000/6250] eta: 0:12:00 lr: 0.000091 grad: 0.0680 (0.0805) loss: 0.8325 (0.8272) time: 0.1195 data: 0.0376 max mem: 9390 +Train: [38] [1100/6250] eta: 0:11:49 lr: 0.000091 grad: 0.0705 (0.0799) loss: 0.8327 (0.8276) time: 0.1040 data: 0.0222 max mem: 9390 +Train: [38] [1200/6250] eta: 0:11:44 lr: 0.000091 grad: 0.0727 (0.0793) loss: 0.8343 (0.8280) time: 0.1513 data: 0.0752 max mem: 9390 +Train: [38] [1300/6250] eta: 0:11:29 lr: 0.000091 grad: 0.0752 (0.0791) loss: 0.8257 (0.8282) time: 0.1252 data: 0.0462 max mem: 9390 +Train: [38] [1400/6250] eta: 0:11:16 lr: 0.000091 grad: 0.0709 (0.0789) loss: 0.8289 (0.8283) time: 0.1351 data: 0.0567 max mem: 9390 +Train: [38] [1500/6250] eta: 0:10:59 lr: 0.000091 grad: 0.0749 (0.0787) loss: 0.8290 (0.8285) time: 0.1197 data: 0.0366 max mem: 9390 +Train: [38] [1600/6250] eta: 0:10:46 lr: 0.000091 grad: 0.0763 (0.0787) loss: 0.8310 (0.8285) time: 0.1353 data: 0.0560 max mem: 9390 +Train: [38] [1700/6250] eta: 0:10:32 lr: 0.000091 grad: 0.0760 (0.0786) loss: 0.8294 (0.8285) time: 0.1480 data: 0.0672 max mem: 9390 +Train: [38] [1800/6250] eta: 0:10:21 lr: 0.000091 grad: 0.0752 (0.0788) loss: 0.8359 (0.8286) time: 0.1509 data: 0.0671 max mem: 9390 +Train: [38] [1900/6250] eta: 0:10:05 lr: 0.000091 grad: 0.0773 (0.0788) loss: 0.8255 (0.8285) time: 0.1217 data: 0.0436 max mem: 9390 +Train: [38] [2000/6250] eta: 0:09:50 lr: 0.000091 grad: 0.0739 (0.0788) loss: 0.8290 (0.8285) time: 0.1317 data: 0.0508 max mem: 9390 +Train: [38] [2100/6250] eta: 0:09:37 lr: 0.000091 grad: 0.0694 (0.0786) loss: 0.8296 (0.8285) time: 0.1190 data: 0.0405 max mem: 9390 +Train: [38] [2200/6250] eta: 0:09:24 lr: 0.000091 grad: 0.0758 (0.0786) loss: 0.8276 (0.8285) time: 0.1239 data: 0.0456 max mem: 9390 +Train: [38] [2300/6250] eta: 0:09:10 lr: 0.000091 grad: 0.0733 (0.0786) loss: 0.8307 (0.8285) time: 0.1711 data: 0.0912 max mem: 9390 +Train: [38] [2400/6250] eta: 0:08:57 lr: 0.000091 grad: 0.0802 (0.0786) loss: 0.8162 (0.8283) time: 0.1356 data: 0.0534 max mem: 9390 +Train: [38] [2500/6250] eta: 0:08:43 lr: 0.000091 grad: 0.0753 (0.0786) loss: 0.8217 (0.8282) time: 0.1431 data: 0.0655 max mem: 9390 +Train: [38] [2600/6250] eta: 0:08:28 lr: 0.000091 grad: 0.0732 (0.0787) loss: 0.8247 (0.8281) time: 0.1186 data: 0.0419 max mem: 9390 +Train: [38] [2700/6250] eta: 0:08:15 lr: 0.000091 grad: 0.0768 (0.0787) loss: 0.8305 (0.8282) time: 0.1853 data: 0.0976 max mem: 9390 +Train: [38] [2800/6250] eta: 0:08:02 lr: 0.000091 grad: 0.0763 (0.0787) loss: 0.8262 (0.8281) time: 0.1307 data: 0.0507 max mem: 9390 +Train: [38] [2900/6250] eta: 0:07:48 lr: 0.000090 grad: 0.0798 (0.0786) loss: 0.8268 (0.8282) time: 0.1394 data: 0.0588 max mem: 9390 +Train: [38] [3000/6250] eta: 0:07:34 lr: 0.000090 grad: 0.0746 (0.0786) loss: 0.8276 (0.8282) time: 0.1405 data: 0.0592 max mem: 9390 +Train: [38] [3100/6250] eta: 0:07:22 lr: 0.000090 grad: 0.0775 (0.0786) loss: 0.8266 (0.8282) time: 0.2174 data: 0.0950 max mem: 9390 +Train: [38] [3200/6250] eta: 0:07:09 lr: 0.000090 grad: 0.0781 (0.0786) loss: 0.8283 (0.8283) time: 0.1226 data: 0.0421 max mem: 9390 +Train: [38] [3300/6250] eta: 0:06:56 lr: 0.000090 grad: 0.0771 (0.0787) loss: 0.8240 (0.8283) time: 0.1509 data: 0.0446 max mem: 9390 +Train: [38] [3400/6250] eta: 0:06:43 lr: 0.000090 grad: 0.0817 (0.0787) loss: 0.8251 (0.8282) time: 0.1096 data: 0.0292 max mem: 9390 +Train: [38] [3500/6250] eta: 0:06:30 lr: 0.000090 grad: 0.0792 (0.0788) loss: 0.8268 (0.8282) time: 0.2254 data: 0.1469 max mem: 9390 +Train: [38] [3600/6250] eta: 0:06:15 lr: 0.000090 grad: 0.0719 (0.0788) loss: 0.8294 (0.8281) time: 0.1353 data: 0.0561 max mem: 9390 +Train: [38] [3700/6250] eta: 0:06:00 lr: 0.000090 grad: 0.0801 (0.0788) loss: 0.8266 (0.8280) time: 0.1202 data: 0.0416 max mem: 9390 +Train: [38] [3800/6250] eta: 0:05:46 lr: 0.000090 grad: 0.0761 (0.0788) loss: 0.8269 (0.8280) time: 0.1409 data: 0.0541 max mem: 9390 +Train: [38] [3900/6250] eta: 0:05:32 lr: 0.000090 grad: 0.0725 (0.0788) loss: 0.8269 (0.8280) time: 0.1271 data: 0.0463 max mem: 9390 +Train: [38] [4000/6250] eta: 0:05:18 lr: 0.000090 grad: 0.0716 (0.0787) loss: 0.8340 (0.8280) time: 0.1595 data: 0.0736 max mem: 9390 +Train: [38] [4100/6250] eta: 0:05:03 lr: 0.000090 grad: 0.0763 (0.0787) loss: 0.8181 (0.8279) time: 0.1340 data: 0.0541 max mem: 9390 +Train: [38] [4200/6250] eta: 0:04:51 lr: 0.000090 grad: 0.0745 (0.0787) loss: 0.8290 (0.8279) time: 0.3067 data: 0.2268 max mem: 9390 +Train: [38] [4300/6250] eta: 0:04:36 lr: 0.000090 grad: 0.0750 (0.0786) loss: 0.8302 (0.8279) time: 0.1512 data: 0.0639 max mem: 9390 +Train: [38] [4400/6250] eta: 0:04:23 lr: 0.000090 grad: 0.0713 (0.0786) loss: 0.8295 (0.8279) time: 0.1587 data: 0.0802 max mem: 9390 +Train: [38] [4500/6250] eta: 0:04:08 lr: 0.000090 grad: 0.0794 (0.0786) loss: 0.8273 (0.8279) time: 0.1425 data: 0.0545 max mem: 9390 +Train: [38] [4600/6250] eta: 0:03:55 lr: 0.000090 grad: 0.0753 (0.0785) loss: 0.8301 (0.8280) time: 0.1706 data: 0.0977 max mem: 9390 +Train: [38] [4700/6250] eta: 0:03:40 lr: 0.000090 grad: 0.0804 (0.0786) loss: 0.8313 (0.8280) time: 0.1411 data: 0.0618 max mem: 9390 +Train: [38] [4800/6250] eta: 0:03:26 lr: 0.000090 grad: 0.0750 (0.0786) loss: 0.8282 (0.8280) time: 0.1332 data: 0.0495 max mem: 9390 +Train: [38] [4900/6250] eta: 0:03:12 lr: 0.000090 grad: 0.0753 (0.0786) loss: 0.8268 (0.8280) time: 0.1311 data: 0.0455 max mem: 9390 +Train: [38] [5000/6250] eta: 0:02:57 lr: 0.000090 grad: 0.0734 (0.0786) loss: 0.8365 (0.8280) time: 0.1249 data: 0.0407 max mem: 9390 +Train: [38] [5100/6250] eta: 0:02:43 lr: 0.000090 grad: 0.0746 (0.0786) loss: 0.8243 (0.8280) time: 0.1343 data: 0.0414 max mem: 9390 +Train: [38] [5200/6250] eta: 0:02:29 lr: 0.000090 grad: 0.0770 (0.0786) loss: 0.8285 (0.8280) time: 0.1403 data: 0.0601 max mem: 9390 +Train: [38] [5300/6250] eta: 0:02:15 lr: 0.000090 grad: 0.0786 (0.0786) loss: 0.8313 (0.8280) time: 0.1335 data: 0.0532 max mem: 9390 +Train: [38] [5400/6250] eta: 0:02:00 lr: 0.000090 grad: 0.0743 (0.0786) loss: 0.8261 (0.8280) time: 0.1357 data: 0.0564 max mem: 9390 +Train: [38] [5500/6250] eta: 0:01:46 lr: 0.000090 grad: 0.0714 (0.0786) loss: 0.8291 (0.8280) time: 0.1533 data: 0.0748 max mem: 9390 +Train: [38] [5600/6250] eta: 0:01:32 lr: 0.000090 grad: 0.0797 (0.0786) loss: 0.8309 (0.8281) time: 0.2501 data: 0.1486 max mem: 9390 +Train: [38] [5700/6250] eta: 0:01:18 lr: 0.000090 grad: 0.0759 (0.0786) loss: 0.8291 (0.8281) time: 0.1368 data: 0.0589 max mem: 9390 +Train: [38] [5800/6250] eta: 0:01:04 lr: 0.000090 grad: 0.0716 (0.0786) loss: 0.8360 (0.8281) time: 0.1381 data: 0.0555 max mem: 9390 +Train: [38] [5900/6250] eta: 0:00:50 lr: 0.000090 grad: 0.0808 (0.0786) loss: 0.8289 (0.8281) time: 0.1712 data: 0.0887 max mem: 9390 +Train: [38] [6000/6250] eta: 0:00:35 lr: 0.000090 grad: 0.0781 (0.0787) loss: 0.8239 (0.8281) time: 0.1266 data: 0.0424 max mem: 9390 +Train: [38] [6100/6250] eta: 0:00:21 lr: 0.000090 grad: 0.0811 (0.0788) loss: 0.8287 (0.8281) time: 0.1566 data: 0.0784 max mem: 9390 +Train: [38] [6200/6250] eta: 0:00:07 lr: 0.000089 grad: 0.0741 (0.0788) loss: 0.8259 (0.8281) time: 0.1630 data: 0.0862 max mem: 9390 +Train: [38] [6249/6250] eta: 0:00:00 lr: 0.000089 grad: 0.0771 (0.0789) loss: 0.8212 (0.8280) time: 0.1363 data: 0.0513 max mem: 9390 +Train: [38] Total time: 0:15:01 (0.1443 s / it) +Averaged stats: lr: 0.000089 grad: 0.0771 (0.0789) loss: 0.8212 (0.8280) +Eval (hcp-train-subset): [38] [ 0/62] eta: 0:04:40 loss: 0.8489 (0.8489) time: 4.5234 data: 4.4915 max mem: 9390 +Eval (hcp-train-subset): [38] [61/62] eta: 0:00:00 loss: 0.8400 (0.8406) time: 0.1382 data: 0.1128 max mem: 9390 +Eval (hcp-train-subset): [38] Total time: 0:00:13 (0.2101 s / it) +Averaged stats (hcp-train-subset): loss: 0.8400 (0.8406) +Eval (hcp-val): [38] [ 0/62] eta: 0:03:28 loss: 0.8342 (0.8342) time: 3.3585 data: 3.2801 max mem: 9390 +Eval (hcp-val): [38] [61/62] eta: 0:00:00 loss: 0.8363 (0.8380) time: 0.1197 data: 0.0944 max mem: 9390 +Eval (hcp-val): [38] Total time: 0:00:12 (0.2014 s / it) +Averaged stats (hcp-val): loss: 0.8363 (0.8380) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +Train: [39] [ 0/6250] eta: 9:46:31 lr: 0.000089 grad: 0.0497 (0.0497) loss: 0.8665 (0.8665) time: 5.6306 data: 5.4767 max mem: 9390 +Train: [39] [ 100/6250] eta: 0:20:26 lr: 0.000089 grad: 0.0856 (0.1267) loss: 0.8220 (0.8250) time: 0.1491 data: 0.0585 max mem: 9390 +Train: [39] [ 200/6250] eta: 0:16:57 lr: 0.000089 grad: 0.0770 (0.1103) loss: 0.8276 (0.8220) time: 0.1365 data: 0.0523 max mem: 9390 +Train: [39] [ 300/6250] eta: 0:15:47 lr: 0.000089 grad: 0.0823 (0.1039) loss: 0.8164 (0.8190) time: 0.1404 data: 0.0555 max mem: 9390 +Train: [39] [ 400/6250] eta: 0:15:01 lr: 0.000089 grad: 0.0728 (0.0990) loss: 0.8259 (0.8187) time: 0.1518 data: 0.0717 max mem: 9390 +Train: [39] [ 500/6250] eta: 0:14:25 lr: 0.000089 grad: 0.0754 (0.0947) loss: 0.8239 (0.8200) time: 0.1366 data: 0.0462 max mem: 9390 +Train: [39] [ 600/6250] eta: 0:13:55 lr: 0.000089 grad: 0.0759 (0.0920) loss: 0.8260 (0.8212) time: 0.1171 data: 0.0305 max mem: 9390 +Train: [39] [ 700/6250] eta: 0:13:21 lr: 0.000089 grad: 0.0739 (0.0897) loss: 0.8256 (0.8222) time: 0.1246 data: 0.0460 max mem: 9390 +Train: [39] [ 800/6250] eta: 0:13:00 lr: 0.000089 grad: 0.0733 (0.0882) loss: 0.8277 (0.8229) time: 0.1127 data: 0.0273 max mem: 9390 +Train: [39] [ 900/6250] eta: 0:12:39 lr: 0.000089 grad: 0.0713 (0.0870) loss: 0.8288 (0.8233) time: 0.1330 data: 0.0499 max mem: 9390 +Train: [39] [1000/6250] eta: 0:12:20 lr: 0.000089 grad: 0.0762 (0.0858) loss: 0.8244 (0.8238) time: 0.1211 data: 0.0362 max mem: 9390 +Train: [39] [1100/6250] eta: 0:12:05 lr: 0.000089 grad: 0.0749 (0.0851) loss: 0.8198 (0.8238) time: 0.1293 data: 0.0435 max mem: 9390 +Train: [39] [1200/6250] eta: 0:11:53 lr: 0.000089 grad: 0.0726 (0.0845) loss: 0.8233 (0.8239) time: 0.1488 data: 0.0701 max mem: 9390 +Train: [39] [1300/6250] eta: 0:11:39 lr: 0.000089 grad: 0.0781 (0.0840) loss: 0.8235 (0.8240) time: 0.1433 data: 0.0649 max mem: 9390 +Train: [39] [1400/6250] eta: 0:11:23 lr: 0.000089 grad: 0.0796 (0.0835) loss: 0.8330 (0.8242) time: 0.1328 data: 0.0519 max mem: 9390 +Train: [39] [1500/6250] eta: 0:11:08 lr: 0.000089 grad: 0.0800 (0.0832) loss: 0.8213 (0.8242) time: 0.1372 data: 0.0544 max mem: 9390 +Train: [39] [1600/6250] eta: 0:10:54 lr: 0.000089 grad: 0.0734 (0.0829) loss: 0.8251 (0.8243) time: 0.1555 data: 0.0712 max mem: 9390 +Train: [39] [1700/6250] eta: 0:10:40 lr: 0.000089 grad: 0.0732 (0.0826) loss: 0.8259 (0.8242) time: 0.1399 data: 0.0607 max mem: 9390 +Train: [39] [1800/6250] eta: 0:10:29 lr: 0.000089 grad: 0.0820 (0.0824) loss: 0.8219 (0.8242) time: 0.1800 data: 0.1023 max mem: 9390 +Train: [39] [1900/6250] eta: 0:10:13 lr: 0.000089 grad: 0.0796 (0.0822) loss: 0.8218 (0.8241) time: 0.1414 data: 0.0589 max mem: 9390 +Train: [39] [2000/6250] eta: 0:10:01 lr: 0.000089 grad: 0.0825 (0.0821) loss: 0.8176 (0.8240) time: 0.1395 data: 0.0609 max mem: 9390 +Train: [39] [2100/6250] eta: 0:09:45 lr: 0.000089 grad: 0.0745 (0.0820) loss: 0.8239 (0.8241) time: 0.1303 data: 0.0481 max mem: 9390 +Train: [39] [2200/6250] eta: 0:09:29 lr: 0.000089 grad: 0.0771 (0.0819) loss: 0.8315 (0.8241) time: 0.1303 data: 0.0511 max mem: 9390 +Train: [39] [2300/6250] eta: 0:09:15 lr: 0.000089 grad: 0.0808 (0.0819) loss: 0.8225 (0.8240) time: 0.1329 data: 0.0515 max mem: 9390 +Train: [39] [2400/6250] eta: 0:09:00 lr: 0.000089 grad: 0.0758 (0.0817) loss: 0.8197 (0.8240) time: 0.1344 data: 0.0512 max mem: 9390 +Train: [39] [2500/6250] eta: 0:08:46 lr: 0.000089 grad: 0.0756 (0.0816) loss: 0.8230 (0.8239) time: 0.1532 data: 0.0740 max mem: 9390 +Train: [39] [2600/6250] eta: 0:08:32 lr: 0.000089 grad: 0.0735 (0.0815) loss: 0.8149 (0.8239) time: 0.1246 data: 0.0432 max mem: 9390 +Train: [39] [2700/6250] eta: 0:08:20 lr: 0.000089 grad: 0.0812 (0.0815) loss: 0.8245 (0.8237) time: 0.1486 data: 0.0652 max mem: 9390 +Train: [39] [2800/6250] eta: 0:08:05 lr: 0.000089 grad: 0.0815 (0.0815) loss: 0.8237 (0.8238) time: 0.1303 data: 0.0461 max mem: 9390 +Train: [39] [2900/6250] eta: 0:07:51 lr: 0.000089 grad: 0.0792 (0.0815) loss: 0.8252 (0.8237) time: 0.1237 data: 0.0392 max mem: 9390 +Train: [39] [3000/6250] eta: 0:07:36 lr: 0.000089 grad: 0.0765 (0.0815) loss: 0.8231 (0.8236) time: 0.1260 data: 0.0457 max mem: 9390 +Train: [39] [3100/6250] eta: 0:07:21 lr: 0.000089 grad: 0.0750 (0.0814) loss: 0.8233 (0.8236) time: 0.1420 data: 0.0576 max mem: 9390 +Train: [39] [3200/6250] eta: 0:07:08 lr: 0.000089 grad: 0.0747 (0.0813) loss: 0.8189 (0.8236) time: 0.1476 data: 0.0724 max mem: 9390 +Train: [39] [3300/6250] eta: 0:06:55 lr: 0.000088 grad: 0.0758 (0.0813) loss: 0.8239 (0.8235) time: 0.1313 data: 0.0521 max mem: 9390 +Train: [39] [3400/6250] eta: 0:06:41 lr: 0.000088 grad: 0.0770 (0.0813) loss: 0.8176 (0.8235) time: 0.1372 data: 0.0580 max mem: 9390 +Train: [39] [3500/6250] eta: 0:06:27 lr: 0.000088 grad: 0.0781 (0.0813) loss: 0.8205 (0.8234) time: 0.1383 data: 0.0527 max mem: 9390 +Train: [39] [3600/6250] eta: 0:06:13 lr: 0.000088 grad: 0.0798 (0.0813) loss: 0.8281 (0.8234) time: 0.1598 data: 0.0579 max mem: 9390 +Train: [39] [3700/6250] eta: 0:05:59 lr: 0.000088 grad: 0.0812 (0.0812) loss: 0.8182 (0.8233) time: 0.1327 data: 0.0524 max mem: 9390 +Train: [39] [3800/6250] eta: 0:05:45 lr: 0.000088 grad: 0.0789 (0.0813) loss: 0.8151 (0.8233) time: 0.1541 data: 0.0750 max mem: 9390 +Train: [39] [3900/6250] eta: 0:05:31 lr: 0.000088 grad: 0.0793 (0.0813) loss: 0.8194 (0.8233) time: 0.1468 data: 0.0646 max mem: 9390 +Train: [39] [4000/6250] eta: 0:05:16 lr: 0.000088 grad: 0.0725 (0.0814) loss: 0.8283 (0.8233) time: 0.1373 data: 0.0550 max mem: 9390 +Train: [39] [4100/6250] eta: 0:05:03 lr: 0.000088 grad: 0.0809 (0.0813) loss: 0.8160 (0.8233) time: 0.1546 data: 0.0710 max mem: 9390 +Train: [39] [4200/6250] eta: 0:04:49 lr: 0.000088 grad: 0.0770 (0.0814) loss: 0.8204 (0.8233) time: 0.1688 data: 0.0879 max mem: 9390 +Train: [39] [4300/6250] eta: 0:04:35 lr: 0.000088 grad: 0.0775 (0.0814) loss: 0.8169 (0.8232) time: 0.1413 data: 0.0648 max mem: 9390 +Train: [39] [4400/6250] eta: 0:04:21 lr: 0.000088 grad: 0.0854 (0.0814) loss: 0.8199 (0.8232) time: 0.1454 data: 0.0658 max mem: 9390 +Train: [39] [4500/6250] eta: 0:04:07 lr: 0.000088 grad: 0.0793 (0.0814) loss: 0.8161 (0.8232) time: 0.1764 data: 0.0911 max mem: 9390 +Train: [39] [4600/6250] eta: 0:03:53 lr: 0.000088 grad: 0.0751 (0.0814) loss: 0.8209 (0.8231) time: 0.1477 data: 0.0682 max mem: 9390 +Train: [39] [4700/6250] eta: 0:03:39 lr: 0.000088 grad: 0.0833 (0.0813) loss: 0.8270 (0.8231) time: 0.1814 data: 0.0962 max mem: 9390 +Train: [39] [4800/6250] eta: 0:03:25 lr: 0.000088 grad: 0.0759 (0.0813) loss: 0.8199 (0.8231) time: 0.1424 data: 0.0632 max mem: 9390 +Train: [39] [4900/6250] eta: 0:03:11 lr: 0.000088 grad: 0.0816 (0.0813) loss: 0.8211 (0.8231) time: 0.1371 data: 0.0597 max mem: 9390 +Train: [39] [5000/6250] eta: 0:02:56 lr: 0.000088 grad: 0.0763 (0.0813) loss: 0.8206 (0.8230) time: 0.1636 data: 0.0846 max mem: 9390 +Train: [39] [5100/6250] eta: 0:02:42 lr: 0.000088 grad: 0.0798 (0.0813) loss: 0.8209 (0.8230) time: 0.1469 data: 0.0607 max mem: 9390 +Train: [39] [5200/6250] eta: 0:02:28 lr: 0.000088 grad: 0.0754 (0.0813) loss: 0.8257 (0.8230) time: 0.1271 data: 0.0495 max mem: 9390 +Train: [39] [5300/6250] eta: 0:02:14 lr: 0.000088 grad: 0.0756 (0.0813) loss: 0.8208 (0.8230) time: 0.1587 data: 0.0740 max mem: 9390 +Train: [39] [5400/6250] eta: 0:02:00 lr: 0.000088 grad: 0.0813 (0.0813) loss: 0.8199 (0.8230) time: 0.1349 data: 0.0535 max mem: 9390 +Train: [39] [5500/6250] eta: 0:01:46 lr: 0.000088 grad: 0.0754 (0.0813) loss: 0.8232 (0.8230) time: 0.1319 data: 0.0572 max mem: 9390 +Train: [39] [5600/6250] eta: 0:01:32 lr: 0.000088 grad: 0.0802 (0.0813) loss: 0.8260 (0.8230) time: 0.1153 data: 0.0371 max mem: 9390 +Train: [39] [5700/6250] eta: 0:01:17 lr: 0.000088 grad: 0.0755 (0.0814) loss: 0.8243 (0.8230) time: 0.1428 data: 0.0648 max mem: 9390 +Train: [39] [5800/6250] eta: 0:01:03 lr: 0.000088 grad: 0.0792 (0.0814) loss: 0.8300 (0.8230) time: 0.1634 data: 0.0842 max mem: 9390 +Train: [39] [5900/6250] eta: 0:00:49 lr: 0.000088 grad: 0.0876 (0.0814) loss: 0.8280 (0.8230) time: 0.1387 data: 0.0637 max mem: 9390 +Train: [39] [6000/6250] eta: 0:00:35 lr: 0.000088 grad: 0.0819 (0.0815) loss: 0.8192 (0.8230) time: 0.1517 data: 0.0698 max mem: 9390 +Train: [39] [6100/6250] eta: 0:00:21 lr: 0.000088 grad: 0.0812 (0.0815) loss: 0.8310 (0.8230) time: 0.1389 data: 0.0638 max mem: 9390 +Train: [39] [6200/6250] eta: 0:00:07 lr: 0.000088 grad: 0.0859 (0.0815) loss: 0.8154 (0.8230) time: 0.1362 data: 0.0538 max mem: 9390 +Train: [39] [6249/6250] eta: 0:00:00 lr: 0.000088 grad: 0.0805 (0.0815) loss: 0.8323 (0.8231) time: 0.1191 data: 0.0339 max mem: 9390 +Train: [39] Total time: 0:14:50 (0.1425 s / it) +Averaged stats: lr: 0.000088 grad: 0.0805 (0.0815) loss: 0.8323 (0.8231) +Eval (hcp-train-subset): [39] [ 0/62] eta: 0:03:09 loss: 0.8537 (0.8537) time: 3.0602 data: 2.9808 max mem: 9390 +Eval (hcp-train-subset): [39] [61/62] eta: 0:00:00 loss: 0.8408 (0.8393) time: 0.1176 data: 0.0890 max mem: 9390 +Eval (hcp-train-subset): [39] Total time: 0:00:12 (0.1975 s / it) +Averaged stats (hcp-train-subset): loss: 0.8408 (0.8393) +Making plots (hcp-train-subset): example=51 +Eval (hcp-val): [39] [ 0/62] eta: 0:05:10 loss: 0.8366 (0.8366) time: 5.0130 data: 4.9818 max mem: 9390 +Eval (hcp-val): [39] [61/62] eta: 0:00:00 loss: 0.8361 (0.8379) time: 0.1140 data: 0.0889 max mem: 9390 +Eval (hcp-val): [39] Total time: 0:00:12 (0.1982 s / it) +Averaged stats (hcp-val): loss: 0.8361 (0.8379) +Making plots (hcp-val): example=25 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +Train: [40] [ 0/6250] eta: 11:26:46 lr: 0.000088 grad: 0.0754 (0.0754) loss: 0.8337 (0.8337) time: 6.5930 data: 6.4960 max mem: 9390 +Train: [40] [ 100/6250] eta: 0:21:59 lr: 0.000088 grad: 0.0780 (0.0823) loss: 0.8303 (0.8360) time: 0.1517 data: 0.0668 max mem: 9390 +Train: [40] [ 200/6250] eta: 0:18:24 lr: 0.000088 grad: 0.0760 (0.0803) loss: 0.8366 (0.8333) time: 0.1413 data: 0.0627 max mem: 9390 +Train: [40] [ 300/6250] eta: 0:16:57 lr: 0.000088 grad: 0.0706 (0.0789) loss: 0.8363 (0.8330) time: 0.1613 data: 0.0784 max mem: 9390 +Train: [40] [ 400/6250] eta: 0:15:52 lr: 0.000087 grad: 0.0748 (0.0787) loss: 0.8313 (0.8326) time: 0.1089 data: 0.0171 max mem: 9390 +Train: [40] [ 500/6250] eta: 0:15:15 lr: 0.000087 grad: 0.0726 (0.0785) loss: 0.8350 (0.8326) time: 0.1389 data: 0.0597 max mem: 9390 +Train: [40] [ 600/6250] eta: 0:14:38 lr: 0.000087 grad: 0.0736 (0.0781) loss: 0.8308 (0.8324) time: 0.1189 data: 0.0307 max mem: 9390 +Train: [40] [ 700/6250] eta: 0:14:05 lr: 0.000087 grad: 0.0700 (0.0780) loss: 0.8327 (0.8319) time: 0.1507 data: 0.0679 max mem: 9390 +Train: [40] [ 800/6250] eta: 0:13:33 lr: 0.000087 grad: 0.0774 (0.0778) loss: 0.8266 (0.8314) time: 0.1226 data: 0.0424 max mem: 9390 +Train: [40] [ 900/6250] eta: 0:13:08 lr: 0.000087 grad: 0.0753 (0.0775) loss: 0.8272 (0.8310) time: 0.1193 data: 0.0259 max mem: 9390 +Train: [40] [1000/6250] eta: 0:12:45 lr: 0.000087 grad: 0.0739 (0.0772) loss: 0.8260 (0.8306) time: 0.1272 data: 0.0510 max mem: 9390 +Train: [40] [1100/6250] eta: 0:12:28 lr: 0.000087 grad: 0.0784 (0.0772) loss: 0.8233 (0.8302) time: 0.1289 data: 0.0470 max mem: 9390 +Train: [40] [1200/6250] eta: 0:12:16 lr: 0.000087 grad: 0.0763 (0.0770) loss: 0.8254 (0.8299) time: 0.1404 data: 0.0579 max mem: 9390 +Train: [40] [1300/6250] eta: 0:12:03 lr: 0.000087 grad: 0.0781 (0.0770) loss: 0.8251 (0.8296) time: 0.1489 data: 0.0677 max mem: 9390 +Train: [40] [1400/6250] eta: 0:11:46 lr: 0.000087 grad: 0.0750 (0.0769) loss: 0.8256 (0.8293) time: 0.1404 data: 0.0600 max mem: 9390 +Train: [40] [1500/6250] eta: 0:11:32 lr: 0.000087 grad: 0.0749 (0.0770) loss: 0.8259 (0.8290) time: 0.1486 data: 0.0720 max mem: 9390 +Train: [40] [1600/6250] eta: 0:11:17 lr: 0.000087 grad: 0.0760 (0.0771) loss: 0.8241 (0.8286) time: 0.1525 data: 0.0733 max mem: 9390 +Train: [40] [1700/6250] eta: 0:11:00 lr: 0.000087 grad: 0.0784 (0.0773) loss: 0.8257 (0.8283) time: 0.1263 data: 0.0374 max mem: 9390 +Train: [40] [1800/6250] eta: 0:10:46 lr: 0.000087 grad: 0.0808 (0.0774) loss: 0.8215 (0.8280) time: 0.1647 data: 0.0826 max mem: 9390 +Train: [40] [1900/6250] eta: 0:10:29 lr: 0.000087 grad: 0.0774 (0.0773) loss: 0.8196 (0.8278) time: 0.1246 data: 0.0433 max mem: 9390 +Train: [40] [2000/6250] eta: 0:10:15 lr: 0.000087 grad: 0.0777 (0.0774) loss: 0.8248 (0.8276) time: 0.1375 data: 0.0525 max mem: 9390 +Train: [40] [2100/6250] eta: 0:09:59 lr: 0.000087 grad: 0.0750 (0.0775) loss: 0.8246 (0.8274) time: 0.1354 data: 0.0538 max mem: 9390 +Train: [40] [2200/6250] eta: 0:09:44 lr: 0.000087 grad: 0.0755 (0.0776) loss: 0.8198 (0.8273) time: 0.1321 data: 0.0498 max mem: 9390 +Train: [40] [2300/6250] eta: 0:09:28 lr: 0.000087 grad: 0.0744 (0.0778) loss: 0.8234 (0.8271) time: 0.1283 data: 0.0504 max mem: 9390 +Train: [40] [2400/6250] eta: 0:09:13 lr: 0.000087 grad: 0.0815 (0.0779) loss: 0.8222 (0.8270) time: 0.1527 data: 0.0707 max mem: 9390 +Train: [40] [2500/6250] eta: 0:08:59 lr: 0.000087 grad: 0.0772 (0.0780) loss: 0.8203 (0.8269) time: 0.1440 data: 0.0655 max mem: 9390 +Train: [40] [2600/6250] eta: 0:08:48 lr: 0.000087 grad: 0.0805 (0.0780) loss: 0.8242 (0.8268) time: 0.2743 data: 0.1700 max mem: 9390 +Train: [40] [2700/6250] eta: 0:08:31 lr: 0.000087 grad: 0.0825 (0.0781) loss: 0.8219 (0.8266) time: 0.1413 data: 0.0590 max mem: 9390 +Train: [40] [2800/6250] eta: 0:08:15 lr: 0.000087 grad: 0.0828 (0.0782) loss: 0.8214 (0.8265) time: 0.1373 data: 0.0588 max mem: 9390 +Train: [40] [2900/6250] eta: 0:08:00 lr: 0.000087 grad: 0.0770 (0.0784) loss: 0.8236 (0.8264) time: 0.1408 data: 0.0637 max mem: 9390 +Train: [40] [3000/6250] eta: 0:07:44 lr: 0.000087 grad: 0.0734 (0.0784) loss: 0.8218 (0.8263) time: 0.1315 data: 0.0458 max mem: 9390 +Train: [40] [3100/6250] eta: 0:07:34 lr: 0.000087 grad: 0.0746 (0.0784) loss: 0.8208 (0.8262) time: 0.2304 data: 0.1418 max mem: 9390 +Train: [40] [3200/6250] eta: 0:07:17 lr: 0.000087 grad: 0.0748 (0.0784) loss: 0.8185 (0.8262) time: 0.1399 data: 0.0621 max mem: 9390 +Train: [40] [3300/6250] eta: 0:07:02 lr: 0.000087 grad: 0.0790 (0.0785) loss: 0.8301 (0.8262) time: 0.1140 data: 0.0345 max mem: 9390 +Train: [40] [3400/6250] eta: 0:06:47 lr: 0.000087 grad: 0.0754 (0.0785) loss: 0.8274 (0.8262) time: 0.1402 data: 0.0622 max mem: 9390 +Train: [40] [3500/6250] eta: 0:06:33 lr: 0.000087 grad: 0.0767 (0.0785) loss: 0.8194 (0.8262) time: 0.1313 data: 0.0584 max mem: 9390 +Train: [40] [3600/6250] eta: 0:06:18 lr: 0.000087 grad: 0.0728 (0.0785) loss: 0.8287 (0.8262) time: 0.1380 data: 0.0637 max mem: 9390 +Train: [40] [3700/6250] eta: 0:06:03 lr: 0.000086 grad: 0.0787 (0.0785) loss: 0.8264 (0.8262) time: 0.1217 data: 0.0433 max mem: 9390 +Train: [40] [3800/6250] eta: 0:05:49 lr: 0.000086 grad: 0.0742 (0.0785) loss: 0.8260 (0.8262) time: 0.1732 data: 0.0772 max mem: 9390 +Train: [40] [3900/6250] eta: 0:05:35 lr: 0.000086 grad: 0.0720 (0.0785) loss: 0.8327 (0.8263) time: 0.1448 data: 0.0601 max mem: 9390 +Train: [40] [4000/6250] eta: 0:05:20 lr: 0.000086 grad: 0.0732 (0.0784) loss: 0.8302 (0.8264) time: 0.1559 data: 0.0751 max mem: 9390 +Train: [40] [4100/6250] eta: 0:05:06 lr: 0.000086 grad: 0.0782 (0.0784) loss: 0.8272 (0.8264) time: 0.1486 data: 0.0709 max mem: 9390 +Train: [40] [4200/6250] eta: 0:04:52 lr: 0.000086 grad: 0.0773 (0.0784) loss: 0.8270 (0.8264) time: 0.1406 data: 0.0612 max mem: 9390 +Train: [40] [4300/6250] eta: 0:04:38 lr: 0.000086 grad: 0.0762 (0.0783) loss: 0.8293 (0.8265) time: 0.1452 data: 0.0677 max mem: 9390 +Train: [40] [4400/6250] eta: 0:04:24 lr: 0.000086 grad: 0.0744 (0.0783) loss: 0.8242 (0.8265) time: 0.1426 data: 0.0667 max mem: 9390 +Train: [40] [4500/6250] eta: 0:04:09 lr: 0.000086 grad: 0.0785 (0.0783) loss: 0.8277 (0.8266) time: 0.1297 data: 0.0470 max mem: 9390 +Train: [40] [4600/6250] eta: 0:03:55 lr: 0.000086 grad: 0.0767 (0.0783) loss: 0.8335 (0.8266) time: 0.1401 data: 0.0614 max mem: 9390 +Train: [40] [4700/6250] eta: 0:03:40 lr: 0.000086 grad: 0.0748 (0.0784) loss: 0.8310 (0.8266) time: 0.1411 data: 0.0615 max mem: 9390 +Train: [40] [4800/6250] eta: 0:03:26 lr: 0.000086 grad: 0.0811 (0.0785) loss: 0.8237 (0.8266) time: 0.1212 data: 0.0431 max mem: 9390 +Train: [40] [4900/6250] eta: 0:03:12 lr: 0.000086 grad: 0.0813 (0.0785) loss: 0.8287 (0.8266) time: 0.1146 data: 0.0348 max mem: 9390 +Train: [40] [5000/6250] eta: 0:02:57 lr: 0.000086 grad: 0.0824 (0.0786) loss: 0.8233 (0.8266) time: 0.1344 data: 0.0525 max mem: 9390 +Train: [40] [5100/6250] eta: 0:02:43 lr: 0.000086 grad: 0.0806 (0.0786) loss: 0.8267 (0.8266) time: 0.1353 data: 0.0483 max mem: 9390 +Train: [40] [5200/6250] eta: 0:02:29 lr: 0.000086 grad: 0.0767 (0.0787) loss: 0.8227 (0.8265) time: 0.1297 data: 0.0513 max mem: 9390 +Train: [40] [5300/6250] eta: 0:02:14 lr: 0.000086 grad: 0.0804 (0.0787) loss: 0.8255 (0.8265) time: 0.1360 data: 0.0440 max mem: 9390 +Train: [40] [5400/6250] eta: 0:02:00 lr: 0.000086 grad: 0.0814 (0.0788) loss: 0.8219 (0.8264) time: 0.1551 data: 0.0746 max mem: 9390 +Train: [40] [5500/6250] eta: 0:01:46 lr: 0.000086 grad: 0.0827 (0.0789) loss: 0.8163 (0.8263) time: 0.1408 data: 0.0632 max mem: 9390 +Train: [40] [5600/6250] eta: 0:01:32 lr: 0.000086 grad: 0.0824 (0.0790) loss: 0.8187 (0.8263) time: 0.1536 data: 0.0750 max mem: 9390 +Train: [40] [5700/6250] eta: 0:01:18 lr: 0.000086 grad: 0.0783 (0.0790) loss: 0.8253 (0.8262) time: 0.1361 data: 0.0561 max mem: 9390 +Train: [40] [5800/6250] eta: 0:01:03 lr: 0.000086 grad: 0.0850 (0.0791) loss: 0.8170 (0.8261) time: 0.1556 data: 0.0786 max mem: 9390 +Train: [40] [5900/6250] eta: 0:00:49 lr: 0.000086 grad: 0.0785 (0.0791) loss: 0.8216 (0.8260) time: 0.1343 data: 0.0543 max mem: 9390 +Train: [40] [6000/6250] eta: 0:00:35 lr: 0.000086 grad: 0.0865 (0.0792) loss: 0.8140 (0.8260) time: 0.1260 data: 0.0534 max mem: 9390 +Train: [40] [6100/6250] eta: 0:00:21 lr: 0.000086 grad: 0.0851 (0.0793) loss: 0.8208 (0.8259) time: 0.1602 data: 0.0840 max mem: 9390 +Train: [40] [6200/6250] eta: 0:00:07 lr: 0.000086 grad: 0.0824 (0.0794) loss: 0.8170 (0.8258) time: 0.1448 data: 0.0617 max mem: 9390 +Train: [40] [6249/6250] eta: 0:00:00 lr: 0.000086 grad: 0.0805 (0.0794) loss: 0.8239 (0.8258) time: 0.1292 data: 0.0439 max mem: 9390 +Train: [40] Total time: 0:14:52 (0.1428 s / it) +Averaged stats: lr: 0.000086 grad: 0.0805 (0.0794) loss: 0.8239 (0.8258) +Eval (hcp-train-subset): [40] [ 0/62] eta: 0:04:40 loss: 0.8481 (0.8481) time: 4.5263 data: 4.4946 max mem: 9390 +Eval (hcp-train-subset): [40] [61/62] eta: 0:00:00 loss: 0.8375 (0.8399) time: 0.1219 data: 0.0953 max mem: 9390 +Eval (hcp-train-subset): [40] Total time: 0:00:13 (0.2168 s / it) +Averaged stats (hcp-train-subset): loss: 0.8375 (0.8399) +Eval (hcp-val): [40] [ 0/62] eta: 0:05:10 loss: 0.8383 (0.8383) time: 5.0083 data: 4.9774 max mem: 9390 +Eval (hcp-val): [40] [61/62] eta: 0:00:00 loss: 0.8361 (0.8371) time: 0.1238 data: 0.0988 max mem: 9390 +Eval (hcp-val): [40] Total time: 0:00:12 (0.2056 s / it) +Averaged stats (hcp-val): loss: 0.8361 (0.8371) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +Train: [41] [ 0/6250] eta: 9:58:50 lr: 0.000086 grad: 0.1811 (0.1811) loss: 0.8313 (0.8313) time: 5.7489 data: 5.6497 max mem: 9390 +Train: [41] [ 100/6250] eta: 0:20:42 lr: 0.000086 grad: 0.0802 (0.0844) loss: 0.8323 (0.8366) time: 0.1512 data: 0.0502 max mem: 9390 +Train: [41] [ 200/6250] eta: 0:17:49 lr: 0.000086 grad: 0.0719 (0.0808) loss: 0.8402 (0.8345) time: 0.1409 data: 0.0596 max mem: 9390 +Train: [41] [ 300/6250] eta: 0:16:28 lr: 0.000086 grad: 0.0749 (0.0793) loss: 0.8273 (0.8334) time: 0.1422 data: 0.0466 max mem: 9390 +Train: [41] [ 400/6250] eta: 0:15:39 lr: 0.000086 grad: 0.0725 (0.0784) loss: 0.8333 (0.8324) time: 0.1402 data: 0.0613 max mem: 9390 +Train: [41] [ 500/6250] eta: 0:15:02 lr: 0.000086 grad: 0.0709 (0.0781) loss: 0.8341 (0.8316) time: 0.1514 data: 0.0693 max mem: 9390 +Train: [41] [ 600/6250] eta: 0:14:31 lr: 0.000086 grad: 0.0739 (0.0777) loss: 0.8377 (0.8314) time: 0.1441 data: 0.0552 max mem: 9390 +Train: [41] [ 700/6250] eta: 0:14:01 lr: 0.000085 grad: 0.0728 (0.0777) loss: 0.8300 (0.8305) time: 0.1501 data: 0.0653 max mem: 9390 +Train: [41] [ 800/6250] eta: 0:13:33 lr: 0.000085 grad: 0.0751 (0.0777) loss: 0.8268 (0.8296) time: 0.1513 data: 0.0657 max mem: 9390 +Train: [41] [ 900/6250] eta: 0:13:12 lr: 0.000085 grad: 0.0737 (0.0776) loss: 0.8310 (0.8292) time: 0.1654 data: 0.0840 max mem: 9390 +Train: [41] [1000/6250] eta: 0:12:46 lr: 0.000085 grad: 0.0748 (0.0776) loss: 0.8201 (0.8287) time: 0.1479 data: 0.0667 max mem: 9390 +Train: [41] [1100/6250] eta: 0:12:24 lr: 0.000085 grad: 0.0750 (0.0775) loss: 0.8284 (0.8283) time: 0.1294 data: 0.0454 max mem: 9390 +Train: [41] [1200/6250] eta: 0:12:08 lr: 0.000085 grad: 0.0739 (0.0775) loss: 0.8303 (0.8278) time: 0.1277 data: 0.0413 max mem: 9390 +Train: [41] [1300/6250] eta: 0:11:56 lr: 0.000085 grad: 0.0763 (0.0776) loss: 0.8228 (0.8274) time: 0.1182 data: 0.0353 max mem: 9390 +Train: [41] [1400/6250] eta: 0:11:42 lr: 0.000085 grad: 0.0745 (0.0776) loss: 0.8232 (0.8272) time: 0.1457 data: 0.0654 max mem: 9390 +Train: [41] [1500/6250] eta: 0:11:26 lr: 0.000085 grad: 0.0760 (0.0776) loss: 0.8317 (0.8272) time: 0.1590 data: 0.0812 max mem: 9390 +Train: [41] [1600/6250] eta: 0:11:09 lr: 0.000085 grad: 0.0747 (0.0778) loss: 0.8252 (0.8271) time: 0.1291 data: 0.0544 max mem: 9390 +Train: [41] [1700/6250] eta: 0:10:56 lr: 0.000085 grad: 0.0719 (0.0779) loss: 0.8306 (0.8270) time: 0.1758 data: 0.0873 max mem: 9390 +Train: [41] [1800/6250] eta: 0:10:41 lr: 0.000085 grad: 0.0732 (0.0778) loss: 0.8222 (0.8271) time: 0.1393 data: 0.0594 max mem: 9390 +Train: [41] [1900/6250] eta: 0:10:25 lr: 0.000085 grad: 0.0735 (0.0778) loss: 0.8238 (0.8269) time: 0.1364 data: 0.0498 max mem: 9390 +Train: [41] [2000/6250] eta: 0:10:11 lr: 0.000085 grad: 0.0731 (0.0777) loss: 0.8317 (0.8269) time: 0.1732 data: 0.0866 max mem: 9390 +Train: [41] [2100/6250] eta: 0:09:56 lr: 0.000085 grad: 0.0736 (0.0777) loss: 0.8249 (0.8269) time: 0.1379 data: 0.0590 max mem: 9390 +Train: [41] [2200/6250] eta: 0:09:41 lr: 0.000085 grad: 0.0762 (0.0778) loss: 0.8237 (0.8269) time: 0.1661 data: 0.0613 max mem: 9390 +Train: [41] [2300/6250] eta: 0:09:31 lr: 0.000085 grad: 0.0731 (0.0777) loss: 0.8323 (0.8269) time: 0.0978 data: 0.0002 max mem: 9390 +Train: [41] [2400/6250] eta: 0:09:17 lr: 0.000085 grad: 0.0738 (0.0776) loss: 0.8334 (0.8270) time: 0.1559 data: 0.0534 max mem: 9390 +Train: [41] [2500/6250] eta: 0:09:02 lr: 0.000085 grad: 0.0764 (0.0776) loss: 0.8277 (0.8271) time: 0.1417 data: 0.0599 max mem: 9390 +Train: [41] [2600/6250] eta: 0:08:46 lr: 0.000085 grad: 0.0753 (0.0776) loss: 0.8246 (0.8270) time: 0.1303 data: 0.0512 max mem: 9390 +Train: [41] [2700/6250] eta: 0:08:31 lr: 0.000085 grad: 0.0758 (0.0776) loss: 0.8286 (0.8270) time: 0.1244 data: 0.0435 max mem: 9390 +Train: [41] [2800/6250] eta: 0:08:16 lr: 0.000085 grad: 0.0794 (0.0777) loss: 0.8226 (0.8269) time: 0.1347 data: 0.0551 max mem: 9390 +Train: [41] [2900/6250] eta: 0:08:01 lr: 0.000085 grad: 0.0799 (0.0781) loss: 0.8272 (0.8269) time: 0.1163 data: 0.0360 max mem: 9390 +Train: [41] [3000/6250] eta: 0:07:46 lr: 0.000085 grad: 0.0762 (0.0780) loss: 0.8245 (0.8269) time: 0.1212 data: 0.0431 max mem: 9390 +Train: [41] [3100/6250] eta: 0:07:31 lr: 0.000085 grad: 0.0719 (0.0781) loss: 0.8262 (0.8268) time: 0.1426 data: 0.0627 max mem: 9390 +Train: [41] [3200/6250] eta: 0:07:19 lr: 0.000085 grad: 0.0809 (0.0782) loss: 0.8241 (0.8268) time: 0.1395 data: 0.0583 max mem: 9390 +Train: [41] [3300/6250] eta: 0:07:03 lr: 0.000085 grad: 0.0767 (0.0783) loss: 0.8291 (0.8268) time: 0.1335 data: 0.0497 max mem: 9390 +Train: [41] [3400/6250] eta: 0:06:49 lr: 0.000085 grad: 0.0850 (0.0784) loss: 0.8171 (0.8266) time: 0.1389 data: 0.0590 max mem: 9390 +Train: [41] [3500/6250] eta: 0:06:35 lr: 0.000085 grad: 0.0760 (0.0784) loss: 0.8273 (0.8267) time: 0.1346 data: 0.0553 max mem: 9390 +Train: [41] [3600/6250] eta: 0:06:21 lr: 0.000085 grad: 0.0774 (0.0784) loss: 0.8249 (0.8266) time: 0.1779 data: 0.0535 max mem: 9390 +Train: [41] [3700/6250] eta: 0:06:08 lr: 0.000085 grad: 0.0791 (0.0784) loss: 0.8270 (0.8266) time: 0.1447 data: 0.0667 max mem: 9390 +Train: [41] [3800/6250] eta: 0:05:53 lr: 0.000085 grad: 0.0731 (0.0784) loss: 0.8236 (0.8266) time: 0.1359 data: 0.0562 max mem: 9390 +Train: [41] [3900/6250] eta: 0:05:39 lr: 0.000084 grad: 0.0750 (0.0784) loss: 0.8250 (0.8266) time: 0.1443 data: 0.0641 max mem: 9390 +Train: [41] [4000/6250] eta: 0:05:25 lr: 0.000084 grad: 0.0738 (0.0783) loss: 0.8294 (0.8266) time: 0.1753 data: 0.0939 max mem: 9390 +Train: [41] [4100/6250] eta: 0:05:11 lr: 0.000084 grad: 0.0776 (0.0784) loss: 0.8263 (0.8266) time: 0.1632 data: 0.0834 max mem: 9390 +Train: [41] [4200/6250] eta: 0:04:57 lr: 0.000084 grad: 0.0774 (0.0783) loss: 0.8290 (0.8266) time: 0.1381 data: 0.0530 max mem: 9390 +Train: [41] [4300/6250] eta: 0:04:43 lr: 0.000084 grad: 0.0776 (0.0784) loss: 0.8257 (0.8266) time: 0.1679 data: 0.0816 max mem: 9390 +Train: [41] [4400/6250] eta: 0:04:28 lr: 0.000084 grad: 0.0760 (0.0784) loss: 0.8272 (0.8266) time: 0.1452 data: 0.0692 max mem: 9390 +Train: [41] [4500/6250] eta: 0:04:14 lr: 0.000084 grad: 0.0752 (0.0785) loss: 0.8315 (0.8266) time: 0.1047 data: 0.0245 max mem: 9390 +Train: [41] [4600/6250] eta: 0:03:59 lr: 0.000084 grad: 0.0772 (0.0785) loss: 0.8289 (0.8265) time: 0.1568 data: 0.0787 max mem: 9390 +Train: [41] [4700/6250] eta: 0:03:44 lr: 0.000084 grad: 0.0758 (0.0786) loss: 0.8288 (0.8265) time: 0.1340 data: 0.0589 max mem: 9390 +Train: [41] [4800/6250] eta: 0:03:30 lr: 0.000084 grad: 0.0805 (0.0786) loss: 0.8215 (0.8264) time: 0.1478 data: 0.0738 max mem: 9390 +Train: [41] [4900/6250] eta: 0:03:15 lr: 0.000084 grad: 0.0755 (0.0787) loss: 0.8256 (0.8264) time: 0.1313 data: 0.0514 max mem: 9390 +Train: [41] [5000/6250] eta: 0:03:00 lr: 0.000084 grad: 0.0799 (0.0788) loss: 0.8268 (0.8264) time: 0.1462 data: 0.0669 max mem: 9390 +Train: [41] [5100/6250] eta: 0:02:46 lr: 0.000084 grad: 0.0779 (0.0788) loss: 0.8233 (0.8263) time: 0.1402 data: 0.0602 max mem: 9390 +Train: [41] [5200/6250] eta: 0:02:31 lr: 0.000084 grad: 0.0808 (0.0789) loss: 0.8263 (0.8263) time: 0.1253 data: 0.0472 max mem: 9390 +Train: [41] [5300/6250] eta: 0:02:17 lr: 0.000084 grad: 0.0740 (0.0789) loss: 0.8305 (0.8263) time: 0.1805 data: 0.0906 max mem: 9390 +Train: [41] [5400/6250] eta: 0:02:03 lr: 0.000084 grad: 0.0810 (0.0790) loss: 0.8324 (0.8263) time: 0.1743 data: 0.0780 max mem: 9390 +Train: [41] [5500/6250] eta: 0:01:48 lr: 0.000084 grad: 0.0825 (0.0791) loss: 0.8272 (0.8262) time: 0.1630 data: 0.0873 max mem: 9390 +Train: [41] [5600/6250] eta: 0:01:34 lr: 0.000084 grad: 0.0793 (0.0792) loss: 0.8243 (0.8262) time: 0.1410 data: 0.0561 max mem: 9390 +Train: [41] [5700/6250] eta: 0:01:19 lr: 0.000084 grad: 0.0793 (0.0792) loss: 0.8253 (0.8262) time: 0.1380 data: 0.0604 max mem: 9390 +Train: [41] [5800/6250] eta: 0:01:04 lr: 0.000084 grad: 0.0791 (0.0793) loss: 0.8230 (0.8261) time: 0.1331 data: 0.0497 max mem: 9390 +Train: [41] [5900/6250] eta: 0:00:50 lr: 0.000084 grad: 0.0770 (0.0793) loss: 0.8252 (0.8261) time: 0.1352 data: 0.0560 max mem: 9390 +Train: [41] [6000/6250] eta: 0:00:36 lr: 0.000084 grad: 0.0795 (0.0793) loss: 0.8272 (0.8261) time: 0.1310 data: 0.0531 max mem: 9390 +Train: [41] [6100/6250] eta: 0:00:21 lr: 0.000084 grad: 0.0770 (0.0793) loss: 0.8265 (0.8260) time: 0.1414 data: 0.0635 max mem: 9390 +Train: [41] [6200/6250] eta: 0:00:07 lr: 0.000084 grad: 0.0851 (0.0793) loss: 0.8264 (0.8260) time: 0.1376 data: 0.0528 max mem: 9390 +Train: [41] [6249/6250] eta: 0:00:00 lr: 0.000084 grad: 0.0833 (0.0794) loss: 0.8270 (0.8260) time: 0.1268 data: 0.0367 max mem: 9390 +Train: [41] Total time: 0:15:04 (0.1448 s / it) +Averaged stats: lr: 0.000084 grad: 0.0833 (0.0794) loss: 0.8270 (0.8260) +Eval (hcp-train-subset): [41] [ 0/62] eta: 0:03:19 loss: 0.8499 (0.8499) time: 3.2131 data: 3.1359 max mem: 9390 +Eval (hcp-train-subset): [41] [61/62] eta: 0:00:00 loss: 0.8375 (0.8391) time: 0.1338 data: 0.1084 max mem: 9390 +Eval (hcp-train-subset): [41] Total time: 0:00:13 (0.2125 s / it) +Averaged stats (hcp-train-subset): loss: 0.8375 (0.8391) +Eval (hcp-val): [41] [ 0/62] eta: 0:03:30 loss: 0.8356 (0.8356) time: 3.4001 data: 3.3244 max mem: 9390 +Eval (hcp-val): [41] [61/62] eta: 0:00:00 loss: 0.8353 (0.8364) time: 0.1203 data: 0.0953 max mem: 9390 +Eval (hcp-val): [41] Total time: 0:00:12 (0.2044 s / it) +Averaged stats (hcp-val): loss: 0.8353 (0.8364) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +Train: [42] [ 0/6250] eta: 8:01:13 lr: 0.000084 grad: 0.0600 (0.0600) loss: 0.8627 (0.8627) time: 4.6198 data: 4.3899 max mem: 9390 +Train: [42] [ 100/6250] eta: 0:21:32 lr: 0.000084 grad: 0.0813 (0.0935) loss: 0.8269 (0.8358) time: 0.1962 data: 0.0714 max mem: 9390 +Train: [42] [ 200/6250] eta: 0:18:09 lr: 0.000084 grad: 0.0761 (0.0924) loss: 0.8188 (0.8300) time: 0.1430 data: 0.0614 max mem: 9390 +Train: [42] [ 300/6250] eta: 0:16:47 lr: 0.000084 grad: 0.0842 (0.0907) loss: 0.8211 (0.8283) time: 0.1585 data: 0.0820 max mem: 9390 +Train: [42] [ 400/6250] eta: 0:15:58 lr: 0.000084 grad: 0.0806 (0.0886) loss: 0.8254 (0.8266) time: 0.1283 data: 0.0433 max mem: 9390 +Train: [42] [ 500/6250] eta: 0:15:20 lr: 0.000084 grad: 0.0796 (0.0869) loss: 0.8234 (0.8253) time: 0.1409 data: 0.0593 max mem: 9390 +Train: [42] [ 600/6250] eta: 0:14:43 lr: 0.000084 grad: 0.0751 (0.0851) loss: 0.8238 (0.8252) time: 0.1251 data: 0.0344 max mem: 9390 +Train: [42] [ 700/6250] eta: 0:14:13 lr: 0.000084 grad: 0.0766 (0.0841) loss: 0.8271 (0.8255) time: 0.1226 data: 0.0375 max mem: 9390 +Train: [42] [ 800/6250] eta: 0:13:45 lr: 0.000084 grad: 0.0749 (0.0832) loss: 0.8248 (0.8256) time: 0.1320 data: 0.0437 max mem: 9390 +Train: [42] [ 900/6250] eta: 0:13:16 lr: 0.000083 grad: 0.0685 (0.0821) loss: 0.8236 (0.8257) time: 0.1280 data: 0.0453 max mem: 9390 +Train: [42] [1000/6250] eta: 0:12:54 lr: 0.000083 grad: 0.0712 (0.0813) loss: 0.8254 (0.8259) time: 0.1306 data: 0.0518 max mem: 9390 +Train: [42] [1100/6250] eta: 0:12:44 lr: 0.000083 grad: 0.0752 (0.0808) loss: 0.8267 (0.8261) time: 0.1967 data: 0.0958 max mem: 9390 +Train: [42] [1200/6250] eta: 0:12:27 lr: 0.000083 grad: 0.0746 (0.0804) loss: 0.8263 (0.8261) time: 0.1442 data: 0.0675 max mem: 9390 +Train: [42] [1300/6250] eta: 0:12:11 lr: 0.000083 grad: 0.0756 (0.0800) loss: 0.8252 (0.8261) time: 0.1389 data: 0.0638 max mem: 9390 +Train: [42] [1400/6250] eta: 0:11:54 lr: 0.000083 grad: 0.0737 (0.0797) loss: 0.8288 (0.8262) time: 0.1206 data: 0.0404 max mem: 9390 +Train: [42] [1500/6250] eta: 0:11:37 lr: 0.000083 grad: 0.0783 (0.0795) loss: 0.8246 (0.8262) time: 0.1480 data: 0.0660 max mem: 9390 +Train: [42] [1600/6250] eta: 0:11:24 lr: 0.000083 grad: 0.0779 (0.0794) loss: 0.8192 (0.8262) time: 0.1267 data: 0.0450 max mem: 9390 +Train: [42] [1700/6250] eta: 0:11:07 lr: 0.000083 grad: 0.0698 (0.0792) loss: 0.8230 (0.8260) time: 0.1324 data: 0.0545 max mem: 9390 +Train: [42] [1800/6250] eta: 0:10:55 lr: 0.000083 grad: 0.0757 (0.0791) loss: 0.8190 (0.8259) time: 0.1635 data: 0.0862 max mem: 9390 +Train: [42] [1900/6250] eta: 0:10:36 lr: 0.000083 grad: 0.0759 (0.0789) loss: 0.8220 (0.8259) time: 0.1268 data: 0.0441 max mem: 9390 +Train: [42] [2000/6250] eta: 0:10:20 lr: 0.000083 grad: 0.0754 (0.0788) loss: 0.8265 (0.8258) time: 0.1392 data: 0.0564 max mem: 9390 +Train: [42] [2100/6250] eta: 0:10:06 lr: 0.000083 grad: 0.0778 (0.0788) loss: 0.8251 (0.8258) time: 0.1614 data: 0.0708 max mem: 9390 +Train: [42] [2200/6250] eta: 0:09:59 lr: 0.000083 grad: 0.0771 (0.0788) loss: 0.8196 (0.8256) time: 0.2312 data: 0.1274 max mem: 9390 +Train: [42] [2300/6250] eta: 0:09:41 lr: 0.000083 grad: 0.0814 (0.0787) loss: 0.8147 (0.8255) time: 0.1361 data: 0.0570 max mem: 9390 +Train: [42] [2400/6250] eta: 0:09:26 lr: 0.000083 grad: 0.0811 (0.0788) loss: 0.8177 (0.8254) time: 0.1487 data: 0.0700 max mem: 9390 +Train: [42] [2500/6250] eta: 0:09:11 lr: 0.000083 grad: 0.0780 (0.0791) loss: 0.8230 (0.8253) time: 0.1463 data: 0.0702 max mem: 9390 +Train: [42] [2600/6250] eta: 0:08:55 lr: 0.000083 grad: 0.0821 (0.0791) loss: 0.8208 (0.8252) time: 0.1234 data: 0.0450 max mem: 9390 +Train: [42] [2700/6250] eta: 0:08:40 lr: 0.000083 grad: 0.0788 (0.0792) loss: 0.8224 (0.8252) time: 0.1754 data: 0.0952 max mem: 9390 +Train: [42] [2800/6250] eta: 0:08:26 lr: 0.000083 grad: 0.0778 (0.0792) loss: 0.8260 (0.8251) time: 0.1278 data: 0.0484 max mem: 9390 +Train: [42] [2900/6250] eta: 0:08:12 lr: 0.000083 grad: 0.0793 (0.0792) loss: 0.8212 (0.8250) time: 0.1428 data: 0.0580 max mem: 9390 +Train: [42] [3000/6250] eta: 0:07:58 lr: 0.000083 grad: 0.0800 (0.0793) loss: 0.8257 (0.8250) time: 0.1646 data: 0.0712 max mem: 9390 +Train: [42] [3100/6250] eta: 0:07:43 lr: 0.000083 grad: 0.0780 (0.0794) loss: 0.8251 (0.8249) time: 0.1278 data: 0.0461 max mem: 9390 +Train: [42] [3200/6250] eta: 0:07:27 lr: 0.000083 grad: 0.0761 (0.0795) loss: 0.8206 (0.8248) time: 0.1357 data: 0.0564 max mem: 9390 +Train: [42] [3300/6250] eta: 0:07:14 lr: 0.000083 grad: 0.0796 (0.0795) loss: 0.8197 (0.8247) time: 0.1752 data: 0.0840 max mem: 9390 +Train: [42] [3400/6250] eta: 0:07:01 lr: 0.000083 grad: 0.0872 (0.0797) loss: 0.8148 (0.8246) time: 0.2074 data: 0.1236 max mem: 9390 +Train: [42] [3500/6250] eta: 0:06:45 lr: 0.000083 grad: 0.0767 (0.0797) loss: 0.8254 (0.8245) time: 0.1360 data: 0.0573 max mem: 9390 +Train: [42] [3600/6250] eta: 0:06:30 lr: 0.000083 grad: 0.0808 (0.0799) loss: 0.8237 (0.8244) time: 0.1593 data: 0.0750 max mem: 9390 +Train: [42] [3700/6250] eta: 0:06:15 lr: 0.000083 grad: 0.0832 (0.0800) loss: 0.8257 (0.8243) time: 0.1511 data: 0.0654 max mem: 9390 +Train: [42] [3800/6250] eta: 0:06:00 lr: 0.000083 grad: 0.0849 (0.0801) loss: 0.8234 (0.8243) time: 0.1489 data: 0.0670 max mem: 9390 +Train: [42] [3900/6250] eta: 0:05:45 lr: 0.000083 grad: 0.0878 (0.0803) loss: 0.8199 (0.8241) time: 0.1507 data: 0.0670 max mem: 9390 +Train: [42] [4000/6250] eta: 0:05:31 lr: 0.000083 grad: 0.0843 (0.0804) loss: 0.8239 (0.8241) time: 0.2151 data: 0.1260 max mem: 9390 +Train: [42] [4100/6250] eta: 0:05:16 lr: 0.000082 grad: 0.0809 (0.0806) loss: 0.8178 (0.8240) time: 0.1395 data: 0.0572 max mem: 9390 +Train: [42] [4200/6250] eta: 0:05:01 lr: 0.000082 grad: 0.0782 (0.0806) loss: 0.8232 (0.8240) time: 0.1538 data: 0.0725 max mem: 9390 +Train: [42] [4300/6250] eta: 0:04:46 lr: 0.000082 grad: 0.0865 (0.0808) loss: 0.8133 (0.8239) time: 0.1559 data: 0.0772 max mem: 9390 +Train: [42] [4400/6250] eta: 0:04:32 lr: 0.000082 grad: 0.0847 (0.0809) loss: 0.8232 (0.8239) time: 0.1534 data: 0.0679 max mem: 9390 +Train: [42] [4500/6250] eta: 0:04:17 lr: 0.000082 grad: 0.0856 (0.0810) loss: 0.8197 (0.8238) time: 0.1214 data: 0.0395 max mem: 9390 +Train: [42] [4600/6250] eta: 0:04:02 lr: 0.000082 grad: 0.0824 (0.0811) loss: 0.8222 (0.8237) time: 0.1559 data: 0.0680 max mem: 9390 +Train: [42] [4700/6250] eta: 0:03:47 lr: 0.000082 grad: 0.0871 (0.0812) loss: 0.8225 (0.8237) time: 0.1317 data: 0.0498 max mem: 9390 +Train: [42] [4800/6250] eta: 0:03:32 lr: 0.000082 grad: 0.0819 (0.0812) loss: 0.8214 (0.8236) time: 0.1330 data: 0.0477 max mem: 9390 +Train: [42] [4900/6250] eta: 0:03:17 lr: 0.000082 grad: 0.0821 (0.0813) loss: 0.8200 (0.8236) time: 0.1270 data: 0.0376 max mem: 9390 +Train: [42] [5000/6250] eta: 0:03:02 lr: 0.000082 grad: 0.0821 (0.0813) loss: 0.8230 (0.8235) time: 0.1247 data: 0.0302 max mem: 9390 +Train: [42] [5100/6250] eta: 0:02:47 lr: 0.000082 grad: 0.0818 (0.0814) loss: 0.8216 (0.8235) time: 0.1340 data: 0.0564 max mem: 9390 +Train: [42] [5200/6250] eta: 0:02:33 lr: 0.000082 grad: 0.0780 (0.0814) loss: 0.8225 (0.8235) time: 0.1333 data: 0.0496 max mem: 9390 +Train: [42] [5300/6250] eta: 0:02:18 lr: 0.000082 grad: 0.0820 (0.0814) loss: 0.8268 (0.8235) time: 0.1514 data: 0.0648 max mem: 9390 +Train: [42] [5400/6250] eta: 0:02:03 lr: 0.000082 grad: 0.0864 (0.0815) loss: 0.8224 (0.8235) time: 0.1467 data: 0.0677 max mem: 9390 +Train: [42] [5500/6250] eta: 0:01:49 lr: 0.000082 grad: 0.0801 (0.0815) loss: 0.8272 (0.8236) time: 0.1651 data: 0.0843 max mem: 9390 +Train: [42] [5600/6250] eta: 0:01:34 lr: 0.000082 grad: 0.0845 (0.0815) loss: 0.8174 (0.8236) time: 0.1245 data: 0.0410 max mem: 9390 +Train: [42] [5700/6250] eta: 0:01:19 lr: 0.000082 grad: 0.0802 (0.0815) loss: 0.8262 (0.8236) time: 0.1626 data: 0.0740 max mem: 9390 +Train: [42] [5800/6250] eta: 0:01:05 lr: 0.000082 grad: 0.0864 (0.0816) loss: 0.8205 (0.8236) time: 0.1238 data: 0.0401 max mem: 9390 +Train: [42] [5900/6250] eta: 0:00:50 lr: 0.000082 grad: 0.0802 (0.0817) loss: 0.8284 (0.8236) time: 0.1219 data: 0.0409 max mem: 9390 +Train: [42] [6000/6250] eta: 0:00:36 lr: 0.000082 grad: 0.0779 (0.0818) loss: 0.8216 (0.8235) time: 0.1272 data: 0.0447 max mem: 9390 +Train: [42] [6100/6250] eta: 0:00:21 lr: 0.000082 grad: 0.0803 (0.0818) loss: 0.8241 (0.8235) time: 0.1242 data: 0.0371 max mem: 9390 +Train: [42] [6200/6250] eta: 0:00:07 lr: 0.000082 grad: 0.0869 (0.0819) loss: 0.8258 (0.8235) time: 0.1515 data: 0.0661 max mem: 9390 +Train: [42] [6249/6250] eta: 0:00:00 lr: 0.000082 grad: 0.0865 (0.0819) loss: 0.8195 (0.8235) time: 0.1590 data: 0.0695 max mem: 9390 +Train: [42] Total time: 0:15:10 (0.1457 s / it) +Averaged stats: lr: 0.000082 grad: 0.0865 (0.0819) loss: 0.8195 (0.8235) +Eval (hcp-train-subset): [42] [ 0/62] eta: 0:03:41 loss: 0.8497 (0.8497) time: 3.5757 data: 3.4959 max mem: 9390 +Eval (hcp-train-subset): [42] [61/62] eta: 0:00:00 loss: 0.8390 (0.8399) time: 0.1252 data: 0.0987 max mem: 9390 +Eval (hcp-train-subset): [42] Total time: 0:00:11 (0.1908 s / it) +Averaged stats (hcp-train-subset): loss: 0.8390 (0.8399) +Eval (hcp-val): [42] [ 0/62] eta: 0:03:13 loss: 0.8324 (0.8324) time: 3.1230 data: 3.0597 max mem: 9390 +Eval (hcp-val): [42] [61/62] eta: 0:00:00 loss: 0.8345 (0.8369) time: 0.1164 data: 0.0900 max mem: 9390 +Eval (hcp-val): [42] Total time: 0:00:11 (0.1900 s / it) +Averaged stats (hcp-val): loss: 0.8345 (0.8369) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +Train: [43] [ 0/6250] eta: 8:25:21 lr: 0.000082 grad: 0.1286 (0.1286) loss: 0.8620 (0.8620) time: 4.8514 data: 4.5317 max mem: 9390 +Train: [43] [ 100/6250] eta: 0:20:54 lr: 0.000082 grad: 0.0879 (0.0981) loss: 0.8224 (0.8335) time: 0.1662 data: 0.0539 max mem: 9390 +Train: [43] [ 200/6250] eta: 0:18:10 lr: 0.000082 grad: 0.0745 (0.0923) loss: 0.8240 (0.8274) time: 0.1572 data: 0.0722 max mem: 9390 +Train: [43] [ 300/6250] eta: 0:17:13 lr: 0.000082 grad: 0.0765 (0.0877) loss: 0.8317 (0.8286) time: 0.1714 data: 0.0764 max mem: 9390 +Train: [43] [ 400/6250] eta: 0:16:15 lr: 0.000082 grad: 0.0787 (0.0856) loss: 0.8340 (0.8290) time: 0.1504 data: 0.0686 max mem: 9390 +Train: [43] [ 500/6250] eta: 0:15:24 lr: 0.000082 grad: 0.0786 (0.0855) loss: 0.8228 (0.8281) time: 0.1467 data: 0.0591 max mem: 9390 +Train: [43] [ 600/6250] eta: 0:14:43 lr: 0.000082 grad: 0.0792 (0.0846) loss: 0.8281 (0.8281) time: 0.1179 data: 0.0339 max mem: 9390 +Train: [43] [ 700/6250] eta: 0:14:07 lr: 0.000082 grad: 0.0749 (0.0836) loss: 0.8265 (0.8283) time: 0.1306 data: 0.0404 max mem: 9390 +Train: [43] [ 800/6250] eta: 0:13:35 lr: 0.000082 grad: 0.0773 (0.0830) loss: 0.8347 (0.8284) time: 0.1269 data: 0.0374 max mem: 9390 +Train: [43] [ 900/6250] eta: 0:13:08 lr: 0.000082 grad: 0.0765 (0.0823) loss: 0.8303 (0.8287) time: 0.1424 data: 0.0568 max mem: 9390 +Train: [43] [1000/6250] eta: 0:12:43 lr: 0.000081 grad: 0.0714 (0.0817) loss: 0.8324 (0.8289) time: 0.1288 data: 0.0517 max mem: 9390 +Train: [43] [1100/6250] eta: 0:12:25 lr: 0.000081 grad: 0.0768 (0.0814) loss: 0.8269 (0.8287) time: 0.1316 data: 0.0503 max mem: 9390 +Train: [43] [1200/6250] eta: 0:12:12 lr: 0.000081 grad: 0.0783 (0.0813) loss: 0.8282 (0.8285) time: 0.1702 data: 0.0839 max mem: 9390 +Train: [43] [1300/6250] eta: 0:11:54 lr: 0.000081 grad: 0.0772 (0.0812) loss: 0.8203 (0.8281) time: 0.1274 data: 0.0458 max mem: 9390 +Train: [43] [1400/6250] eta: 0:11:39 lr: 0.000081 grad: 0.0791 (0.0813) loss: 0.8192 (0.8279) time: 0.1661 data: 0.0945 max mem: 9390 +Train: [43] [1500/6250] eta: 0:11:25 lr: 0.000081 grad: 0.0791 (0.0813) loss: 0.8241 (0.8277) time: 0.1367 data: 0.0568 max mem: 9390 +Train: [43] [1600/6250] eta: 0:11:11 lr: 0.000081 grad: 0.0817 (0.0813) loss: 0.8151 (0.8274) time: 0.1452 data: 0.0701 max mem: 9390 +Train: [43] [1700/6250] eta: 0:10:57 lr: 0.000081 grad: 0.0742 (0.0813) loss: 0.8218 (0.8270) time: 0.1366 data: 0.0621 max mem: 9390 +Train: [43] [1800/6250] eta: 0:10:41 lr: 0.000081 grad: 0.0774 (0.0813) loss: 0.8219 (0.8268) time: 0.1362 data: 0.0579 max mem: 9390 +Train: [43] [1900/6250] eta: 0:10:25 lr: 0.000081 grad: 0.0806 (0.0815) loss: 0.8216 (0.8265) time: 0.1398 data: 0.0600 max mem: 9390 +Train: [43] [2000/6250] eta: 0:10:09 lr: 0.000081 grad: 0.0835 (0.0815) loss: 0.8234 (0.8262) time: 0.1450 data: 0.0678 max mem: 9390 +Train: [43] [2100/6250] eta: 0:09:55 lr: 0.000081 grad: 0.0753 (0.0815) loss: 0.8189 (0.8259) time: 0.1097 data: 0.0276 max mem: 9390 +Train: [43] [2200/6250] eta: 0:09:41 lr: 0.000081 grad: 0.0814 (0.0816) loss: 0.8233 (0.8258) time: 0.1572 data: 0.0699 max mem: 9390 +Train: [43] [2300/6250] eta: 0:09:26 lr: 0.000081 grad: 0.0840 (0.0818) loss: 0.8232 (0.8255) time: 0.1383 data: 0.0530 max mem: 9390 +Train: [43] [2400/6250] eta: 0:09:11 lr: 0.000081 grad: 0.0811 (0.0820) loss: 0.8216 (0.8254) time: 0.1327 data: 0.0490 max mem: 9390 +Train: [43] [2500/6250] eta: 0:08:56 lr: 0.000081 grad: 0.0835 (0.0821) loss: 0.8254 (0.8252) time: 0.1496 data: 0.0675 max mem: 9390 +Train: [43] [2600/6250] eta: 0:08:41 lr: 0.000081 grad: 0.0817 (0.0821) loss: 0.8215 (0.8252) time: 0.1336 data: 0.0518 max mem: 9390 +Train: [43] [2700/6250] eta: 0:08:27 lr: 0.000081 grad: 0.0822 (0.0822) loss: 0.8222 (0.8251) time: 0.1686 data: 0.0843 max mem: 9390 +Train: [43] [2800/6250] eta: 0:08:14 lr: 0.000081 grad: 0.0852 (0.0823) loss: 0.8235 (0.8250) time: 0.1285 data: 0.0426 max mem: 9390 +Train: [43] [2900/6250] eta: 0:08:00 lr: 0.000081 grad: 0.0863 (0.0825) loss: 0.8244 (0.8249) time: 0.1421 data: 0.0599 max mem: 9390 +Train: [43] [3000/6250] eta: 0:07:44 lr: 0.000081 grad: 0.0832 (0.0827) loss: 0.8220 (0.8247) time: 0.1399 data: 0.0612 max mem: 9390 +Train: [43] [3100/6250] eta: 0:07:29 lr: 0.000081 grad: 0.0832 (0.0827) loss: 0.8176 (0.8245) time: 0.1268 data: 0.0443 max mem: 9390 +Train: [43] [3200/6250] eta: 0:07:14 lr: 0.000081 grad: 0.0843 (0.0831) loss: 0.8150 (0.8243) time: 0.1511 data: 0.0597 max mem: 9390 +Train: [43] [3300/6250] eta: 0:07:00 lr: 0.000081 grad: 0.0819 (0.0832) loss: 0.8204 (0.8242) time: 0.1222 data: 0.0405 max mem: 9390 +Train: [43] [3400/6250] eta: 0:06:46 lr: 0.000081 grad: 0.0814 (0.0832) loss: 0.8191 (0.8241) time: 0.1406 data: 0.0503 max mem: 9390 +Train: [43] [3500/6250] eta: 0:06:32 lr: 0.000081 grad: 0.0786 (0.0833) loss: 0.8220 (0.8240) time: 0.1793 data: 0.0884 max mem: 9390 +Train: [43] [3600/6250] eta: 0:06:18 lr: 0.000081 grad: 0.0839 (0.0834) loss: 0.8152 (0.8239) time: 0.1020 data: 0.0166 max mem: 9390 +Train: [43] [3700/6250] eta: 0:06:04 lr: 0.000081 grad: 0.0855 (0.0835) loss: 0.8176 (0.8238) time: 0.1670 data: 0.0839 max mem: 9390 +Train: [43] [3800/6250] eta: 0:05:52 lr: 0.000081 grad: 0.0882 (0.0836) loss: 0.8198 (0.8236) time: 0.0888 data: 0.0002 max mem: 9390 +Train: [43] [3900/6250] eta: 0:05:36 lr: 0.000081 grad: 0.0799 (0.0836) loss: 0.8197 (0.8236) time: 0.1382 data: 0.0625 max mem: 9390 +Train: [43] [4000/6250] eta: 0:05:22 lr: 0.000081 grad: 0.0826 (0.0838) loss: 0.8220 (0.8235) time: 0.1501 data: 0.0736 max mem: 9390 +Train: [43] [4100/6250] eta: 0:05:07 lr: 0.000081 grad: 0.0872 (0.0838) loss: 0.8197 (0.8233) time: 0.1336 data: 0.0507 max mem: 9390 +Train: [43] [4200/6250] eta: 0:04:52 lr: 0.000080 grad: 0.0839 (0.0839) loss: 0.8136 (0.8233) time: 0.1450 data: 0.0631 max mem: 9390 +Train: [43] [4300/6250] eta: 0:04:38 lr: 0.000080 grad: 0.0827 (0.0840) loss: 0.8220 (0.8232) time: 0.1505 data: 0.0696 max mem: 9390 +Train: [43] [4400/6250] eta: 0:04:24 lr: 0.000080 grad: 0.0825 (0.0841) loss: 0.8235 (0.8231) time: 0.1255 data: 0.0371 max mem: 9390 +Train: [43] [4500/6250] eta: 0:04:09 lr: 0.000080 grad: 0.0848 (0.0842) loss: 0.8134 (0.8231) time: 0.1343 data: 0.0517 max mem: 9390 +Train: [43] [4600/6250] eta: 0:03:55 lr: 0.000080 grad: 0.0860 (0.0843) loss: 0.8167 (0.8230) time: 0.1235 data: 0.0511 max mem: 9390 +Train: [43] [4700/6250] eta: 0:03:40 lr: 0.000080 grad: 0.0799 (0.0842) loss: 0.8213 (0.8230) time: 0.1311 data: 0.0357 max mem: 9390 +Train: [43] [4800/6250] eta: 0:03:26 lr: 0.000080 grad: 0.0809 (0.0843) loss: 0.8251 (0.8230) time: 0.1429 data: 0.0628 max mem: 9390 +Train: [43] [4900/6250] eta: 0:03:11 lr: 0.000080 grad: 0.0909 (0.0844) loss: 0.8195 (0.8229) time: 0.1346 data: 0.0493 max mem: 9390 +Train: [43] [5000/6250] eta: 0:02:57 lr: 0.000080 grad: 0.0820 (0.0844) loss: 0.8228 (0.8229) time: 0.1421 data: 0.0578 max mem: 9390 +Train: [43] [5100/6250] eta: 0:02:43 lr: 0.000080 grad: 0.0807 (0.0844) loss: 0.8240 (0.8229) time: 0.1567 data: 0.0756 max mem: 9390 +Train: [43] [5200/6250] eta: 0:02:29 lr: 0.000080 grad: 0.0815 (0.0843) loss: 0.8190 (0.8229) time: 0.1750 data: 0.0765 max mem: 9390 +Train: [43] [5300/6250] eta: 0:02:14 lr: 0.000080 grad: 0.0838 (0.0844) loss: 0.8222 (0.8229) time: 0.1417 data: 0.0509 max mem: 9390 +Train: [43] [5400/6250] eta: 0:02:00 lr: 0.000080 grad: 0.0747 (0.0843) loss: 0.8315 (0.8230) time: 0.1425 data: 0.0621 max mem: 9390 +Train: [43] [5500/6250] eta: 0:01:46 lr: 0.000080 grad: 0.0810 (0.0843) loss: 0.8259 (0.8231) time: 0.1514 data: 0.0775 max mem: 9390 +Train: [43] [5600/6250] eta: 0:01:32 lr: 0.000080 grad: 0.0842 (0.0843) loss: 0.8228 (0.8231) time: 0.1561 data: 0.0689 max mem: 9390 +Train: [43] [5700/6250] eta: 0:01:18 lr: 0.000080 grad: 0.0816 (0.0842) loss: 0.8252 (0.8232) time: 0.1567 data: 0.0710 max mem: 9390 +Train: [43] [5800/6250] eta: 0:01:03 lr: 0.000080 grad: 0.0831 (0.0842) loss: 0.8237 (0.8233) time: 0.1380 data: 0.0619 max mem: 9390 +Train: [43] [5900/6250] eta: 0:00:49 lr: 0.000080 grad: 0.0852 (0.0842) loss: 0.8276 (0.8234) time: 0.1417 data: 0.0560 max mem: 9390 +Train: [43] [6000/6250] eta: 0:00:35 lr: 0.000080 grad: 0.0764 (0.0842) loss: 0.8270 (0.8234) time: 0.1478 data: 0.0583 max mem: 9390 +Train: [43] [6100/6250] eta: 0:00:21 lr: 0.000080 grad: 0.0773 (0.0842) loss: 0.8241 (0.8235) time: 0.1456 data: 0.0629 max mem: 9390 +Train: [43] [6200/6250] eta: 0:00:07 lr: 0.000080 grad: 0.0798 (0.0842) loss: 0.8264 (0.8235) time: 0.1417 data: 0.0635 max mem: 9390 +Train: [43] [6249/6250] eta: 0:00:00 lr: 0.000080 grad: 0.0815 (0.0842) loss: 0.8230 (0.8235) time: 0.1431 data: 0.0635 max mem: 9390 +Train: [43] Total time: 0:14:51 (0.1427 s / it) +Averaged stats: lr: 0.000080 grad: 0.0815 (0.0842) loss: 0.8230 (0.8235) +Eval (hcp-train-subset): [43] [ 0/62] eta: 0:03:20 loss: 0.8496 (0.8496) time: 3.2311 data: 3.1441 max mem: 9390 +Eval (hcp-train-subset): [43] [61/62] eta: 0:00:00 loss: 0.8368 (0.8388) time: 0.1244 data: 0.0980 max mem: 9390 +Eval (hcp-train-subset): [43] Total time: 0:00:12 (0.2086 s / it) +Averaged stats (hcp-train-subset): loss: 0.8368 (0.8388) +Eval (hcp-val): [43] [ 0/62] eta: 0:03:10 loss: 0.8351 (0.8351) time: 3.0805 data: 2.9889 max mem: 9390 +Eval (hcp-val): [43] [61/62] eta: 0:00:00 loss: 0.8354 (0.8376) time: 0.1177 data: 0.0928 max mem: 9390 +Eval (hcp-val): [43] Total time: 0:00:12 (0.2034 s / it) +Averaged stats (hcp-val): loss: 0.8354 (0.8376) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +Train: [44] [ 0/6250] eta: 9:08:15 lr: 0.000080 grad: 0.1076 (0.1076) loss: 0.7505 (0.7505) time: 5.2633 data: 5.1612 max mem: 9390 +Train: [44] [ 100/6250] eta: 0:19:08 lr: 0.000080 grad: 0.0833 (0.0884) loss: 0.8244 (0.8298) time: 0.1310 data: 0.0329 max mem: 9390 +Train: [44] [ 200/6250] eta: 0:16:15 lr: 0.000080 grad: 0.0785 (0.0873) loss: 0.8273 (0.8275) time: 0.0930 data: 0.0002 max mem: 9390 +Train: [44] [ 300/6250] eta: 0:15:31 lr: 0.000080 grad: 0.0757 (0.0861) loss: 0.8322 (0.8270) time: 0.1361 data: 0.0540 max mem: 9390 +Train: [44] [ 400/6250] eta: 0:14:47 lr: 0.000080 grad: 0.0743 (0.0851) loss: 0.8288 (0.8269) time: 0.1335 data: 0.0543 max mem: 9390 +Train: [44] [ 500/6250] eta: 0:14:09 lr: 0.000080 grad: 0.0724 (0.0843) loss: 0.8265 (0.8267) time: 0.1386 data: 0.0553 max mem: 9390 +Train: [44] [ 600/6250] eta: 0:13:47 lr: 0.000080 grad: 0.0818 (0.0836) loss: 0.8212 (0.8263) time: 0.1544 data: 0.0764 max mem: 9390 +Train: [44] [ 700/6250] eta: 0:13:19 lr: 0.000080 grad: 0.0779 (0.0833) loss: 0.8315 (0.8264) time: 0.1247 data: 0.0377 max mem: 9390 +Train: [44] [ 800/6250] eta: 0:12:55 lr: 0.000080 grad: 0.0762 (0.0827) loss: 0.8309 (0.8267) time: 0.1259 data: 0.0410 max mem: 9390 +Train: [44] [ 900/6250] eta: 0:12:30 lr: 0.000080 grad: 0.0764 (0.0823) loss: 0.8237 (0.8267) time: 0.1231 data: 0.0396 max mem: 9390 +Train: [44] [1000/6250] eta: 0:12:04 lr: 0.000080 grad: 0.0797 (0.0822) loss: 0.8255 (0.8267) time: 0.1100 data: 0.0247 max mem: 9390 +Train: [44] [1100/6250] eta: 0:11:40 lr: 0.000079 grad: 0.0797 (0.0820) loss: 0.8294 (0.8267) time: 0.1276 data: 0.0490 max mem: 9390 +Train: [44] [1200/6250] eta: 0:11:19 lr: 0.000079 grad: 0.0806 (0.0821) loss: 0.8222 (0.8265) time: 0.1121 data: 0.0286 max mem: 9390 +Train: [44] [1300/6250] eta: 0:11:02 lr: 0.000079 grad: 0.0792 (0.0820) loss: 0.8268 (0.8266) time: 0.1308 data: 0.0545 max mem: 9390 +Train: [44] [1400/6250] eta: 0:10:49 lr: 0.000079 grad: 0.0811 (0.0820) loss: 0.8231 (0.8265) time: 0.1444 data: 0.0692 max mem: 9390 +Train: [44] [1500/6250] eta: 0:10:37 lr: 0.000079 grad: 0.0869 (0.0822) loss: 0.8228 (0.8263) time: 0.1394 data: 0.0551 max mem: 9390 +Train: [44] [1600/6250] eta: 0:10:29 lr: 0.000079 grad: 0.0814 (0.0823) loss: 0.8290 (0.8264) time: 0.1965 data: 0.1203 max mem: 9390 +Train: [44] [1700/6250] eta: 0:10:16 lr: 0.000079 grad: 0.0818 (0.0823) loss: 0.8256 (0.8263) time: 0.1465 data: 0.0688 max mem: 9390 +Train: [44] [1800/6250] eta: 0:10:07 lr: 0.000079 grad: 0.0817 (0.0823) loss: 0.8269 (0.8263) time: 0.1923 data: 0.1123 max mem: 9390 +Train: [44] [1900/6250] eta: 0:09:55 lr: 0.000079 grad: 0.0766 (0.0823) loss: 0.8258 (0.8263) time: 0.1104 data: 0.0347 max mem: 9390 +Train: [44] [2000/6250] eta: 0:09:41 lr: 0.000079 grad: 0.0816 (0.0823) loss: 0.8203 (0.8262) time: 0.1356 data: 0.0503 max mem: 9390 +Train: [44] [2100/6250] eta: 0:09:28 lr: 0.000079 grad: 0.0814 (0.0823) loss: 0.8209 (0.8260) time: 0.1347 data: 0.0558 max mem: 9390 +Train: [44] [2200/6250] eta: 0:09:15 lr: 0.000079 grad: 0.0821 (0.0824) loss: 0.8239 (0.8258) time: 0.1409 data: 0.0550 max mem: 9390 +Train: [44] [2300/6250] eta: 0:09:02 lr: 0.000079 grad: 0.0779 (0.0824) loss: 0.8233 (0.8258) time: 0.1447 data: 0.0681 max mem: 9390 +Train: [44] [2400/6250] eta: 0:08:49 lr: 0.000079 grad: 0.0771 (0.0824) loss: 0.8263 (0.8257) time: 0.1444 data: 0.0648 max mem: 9390 +Train: [44] [2500/6250] eta: 0:08:34 lr: 0.000079 grad: 0.0808 (0.0824) loss: 0.8236 (0.8256) time: 0.1245 data: 0.0415 max mem: 9390 +Train: [44] [2600/6250] eta: 0:08:21 lr: 0.000079 grad: 0.0825 (0.0824) loss: 0.8271 (0.8255) time: 0.1580 data: 0.0808 max mem: 9390 +Train: [44] [2700/6250] eta: 0:08:08 lr: 0.000079 grad: 0.0832 (0.0825) loss: 0.8247 (0.8256) time: 0.1340 data: 0.0625 max mem: 9390 +Train: [44] [2800/6250] eta: 0:07:53 lr: 0.000079 grad: 0.0827 (0.0825) loss: 0.8255 (0.8255) time: 0.1284 data: 0.0487 max mem: 9390 +Train: [44] [2900/6250] eta: 0:07:40 lr: 0.000079 grad: 0.0780 (0.0826) loss: 0.8244 (0.8254) time: 0.1384 data: 0.0599 max mem: 9390 +Train: [44] [3000/6250] eta: 0:07:29 lr: 0.000079 grad: 0.0837 (0.0827) loss: 0.8247 (0.8254) time: 0.1816 data: 0.1000 max mem: 9390 +Train: [44] [3100/6250] eta: 0:07:14 lr: 0.000079 grad: 0.0772 (0.0827) loss: 0.8189 (0.8253) time: 0.1207 data: 0.0409 max mem: 9390 +Train: [44] [3200/6250] eta: 0:06:59 lr: 0.000079 grad: 0.0771 (0.0827) loss: 0.8268 (0.8252) time: 0.1286 data: 0.0499 max mem: 9390 +Train: [44] [3300/6250] eta: 0:06:46 lr: 0.000079 grad: 0.0825 (0.0827) loss: 0.8236 (0.8253) time: 0.1567 data: 0.0780 max mem: 9390 +Train: [44] [3400/6250] eta: 0:06:31 lr: 0.000079 grad: 0.0818 (0.0827) loss: 0.8237 (0.8253) time: 0.1543 data: 0.0783 max mem: 9390 +Train: [44] [3500/6250] eta: 0:06:17 lr: 0.000079 grad: 0.0901 (0.0828) loss: 0.8225 (0.8252) time: 0.1272 data: 0.0449 max mem: 9390 +Train: [44] [3600/6250] eta: 0:06:04 lr: 0.000079 grad: 0.0785 (0.0827) loss: 0.8323 (0.8253) time: 0.1307 data: 0.0511 max mem: 9390 +Train: [44] [3700/6250] eta: 0:05:50 lr: 0.000079 grad: 0.0809 (0.0828) loss: 0.8248 (0.8253) time: 0.1736 data: 0.0941 max mem: 9390 +Train: [44] [3800/6250] eta: 0:05:39 lr: 0.000079 grad: 0.0808 (0.0828) loss: 0.8242 (0.8252) time: 0.1689 data: 0.0841 max mem: 9390 +Train: [44] [3900/6250] eta: 0:05:25 lr: 0.000079 grad: 0.0830 (0.0829) loss: 0.8302 (0.8252) time: 0.1575 data: 0.0714 max mem: 9390 +Train: [44] [4000/6250] eta: 0:05:11 lr: 0.000079 grad: 0.0814 (0.0829) loss: 0.8238 (0.8252) time: 0.1328 data: 0.0521 max mem: 9390 +Train: [44] [4100/6250] eta: 0:04:58 lr: 0.000079 grad: 0.0805 (0.0829) loss: 0.8256 (0.8252) time: 0.1526 data: 0.0705 max mem: 9390 +Train: [44] [4200/6250] eta: 0:04:45 lr: 0.000078 grad: 0.0761 (0.0829) loss: 0.8276 (0.8252) time: 0.1587 data: 0.0741 max mem: 9390 +Train: [44] [4300/6250] eta: 0:04:31 lr: 0.000078 grad: 0.0811 (0.0829) loss: 0.8265 (0.8252) time: 0.1241 data: 0.0395 max mem: 9390 +Train: [44] [4400/6250] eta: 0:04:17 lr: 0.000078 grad: 0.0822 (0.0829) loss: 0.8247 (0.8252) time: 0.1488 data: 0.0727 max mem: 9390 +Train: [44] [4500/6250] eta: 0:04:03 lr: 0.000078 grad: 0.0806 (0.0829) loss: 0.8257 (0.8252) time: 0.1419 data: 0.0553 max mem: 9390 +Train: [44] [4600/6250] eta: 0:03:49 lr: 0.000078 grad: 0.0741 (0.0829) loss: 0.8254 (0.8252) time: 0.1682 data: 0.0795 max mem: 9390 +Train: [44] [4700/6250] eta: 0:03:35 lr: 0.000078 grad: 0.0774 (0.0828) loss: 0.8188 (0.8252) time: 0.1475 data: 0.0682 max mem: 9390 +Train: [44] [4800/6250] eta: 0:03:21 lr: 0.000078 grad: 0.0810 (0.0828) loss: 0.8215 (0.8252) time: 0.1518 data: 0.0764 max mem: 9390 +Train: [44] [4900/6250] eta: 0:03:07 lr: 0.000078 grad: 0.0765 (0.0828) loss: 0.8251 (0.8252) time: 0.1364 data: 0.0541 max mem: 9390 +Train: [44] [5000/6250] eta: 0:02:53 lr: 0.000078 grad: 0.0810 (0.0827) loss: 0.8227 (0.8252) time: 0.1387 data: 0.0626 max mem: 9390 +Train: [44] [5100/6250] eta: 0:02:39 lr: 0.000078 grad: 0.0824 (0.0827) loss: 0.8225 (0.8252) time: 0.1356 data: 0.0499 max mem: 9390 +Train: [44] [5200/6250] eta: 0:02:25 lr: 0.000078 grad: 0.0798 (0.0827) loss: 0.8223 (0.8252) time: 0.1371 data: 0.0602 max mem: 9390 +Train: [44] [5300/6250] eta: 0:02:11 lr: 0.000078 grad: 0.0786 (0.0827) loss: 0.8268 (0.8252) time: 0.1227 data: 0.0323 max mem: 9390 +Train: [44] [5400/6250] eta: 0:01:57 lr: 0.000078 grad: 0.0858 (0.0827) loss: 0.8208 (0.8252) time: 0.1634 data: 0.0855 max mem: 9390 +Train: [44] [5500/6250] eta: 0:01:43 lr: 0.000078 grad: 0.0817 (0.0827) loss: 0.8219 (0.8251) time: 0.1236 data: 0.0439 max mem: 9390 +Train: [44] [5600/6250] eta: 0:01:29 lr: 0.000078 grad: 0.0829 (0.0828) loss: 0.8235 (0.8251) time: 0.1454 data: 0.0698 max mem: 9390 +Train: [44] [5700/6250] eta: 0:01:16 lr: 0.000078 grad: 0.0828 (0.0828) loss: 0.8163 (0.8251) time: 0.1320 data: 0.0537 max mem: 9390 +Train: [44] [5800/6250] eta: 0:01:02 lr: 0.000078 grad: 0.0804 (0.0828) loss: 0.8245 (0.8250) time: 0.1572 data: 0.0700 max mem: 9390 +Train: [44] [5900/6250] eta: 0:00:48 lr: 0.000078 grad: 0.0821 (0.0829) loss: 0.8276 (0.8250) time: 0.1709 data: 0.0894 max mem: 9390 +Train: [44] [6000/6250] eta: 0:00:34 lr: 0.000078 grad: 0.0800 (0.0829) loss: 0.8217 (0.8250) time: 0.1432 data: 0.0639 max mem: 9390 +Train: [44] [6100/6250] eta: 0:00:20 lr: 0.000078 grad: 0.0853 (0.0830) loss: 0.8232 (0.8250) time: 0.1339 data: 0.0605 max mem: 9390 +Train: [44] [6200/6250] eta: 0:00:06 lr: 0.000078 grad: 0.0803 (0.0831) loss: 0.8284 (0.8249) time: 0.1232 data: 0.0428 max mem: 9390 +Train: [44] [6249/6250] eta: 0:00:00 lr: 0.000078 grad: 0.0852 (0.0831) loss: 0.8230 (0.8249) time: 0.1515 data: 0.0796 max mem: 9390 +Train: [44] Total time: 0:14:31 (0.1394 s / it) +Averaged stats: lr: 0.000078 grad: 0.0852 (0.0831) loss: 0.8230 (0.8249) +Eval (hcp-train-subset): [44] [ 0/62] eta: 0:05:21 loss: 0.8476 (0.8476) time: 5.1918 data: 5.1612 max mem: 9390 +Eval (hcp-train-subset): [44] [61/62] eta: 0:00:00 loss: 0.8378 (0.8396) time: 0.1370 data: 0.1117 max mem: 9390 +Eval (hcp-train-subset): [44] Total time: 0:00:13 (0.2115 s / it) +Averaged stats (hcp-train-subset): loss: 0.8378 (0.8396) +Making plots (hcp-train-subset): example=21 +Eval (hcp-val): [44] [ 0/62] eta: 0:04:48 loss: 0.8326 (0.8326) time: 4.6553 data: 4.6230 max mem: 9390 +Eval (hcp-val): [44] [61/62] eta: 0:00:00 loss: 0.8361 (0.8364) time: 0.1086 data: 0.0835 max mem: 9390 +Eval (hcp-val): [44] Total time: 0:00:12 (0.1975 s / it) +Averaged stats (hcp-val): loss: 0.8361 (0.8364) +Making plots (hcp-val): example=42 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +Train: [45] [ 0/6250] eta: 9:09:14 lr: 0.000078 grad: 0.0688 (0.0688) loss: 0.8370 (0.8370) time: 5.2728 data: 5.1766 max mem: 9390 +Train: [45] [ 100/6250] eta: 0:19:17 lr: 0.000078 grad: 0.0789 (0.0853) loss: 0.8236 (0.8349) time: 0.1467 data: 0.0555 max mem: 9390 +Train: [45] [ 200/6250] eta: 0:16:27 lr: 0.000078 grad: 0.0804 (0.0823) loss: 0.8195 (0.8314) time: 0.1392 data: 0.0509 max mem: 9390 +Train: [45] [ 300/6250] eta: 0:15:50 lr: 0.000078 grad: 0.0818 (0.0825) loss: 0.8215 (0.8291) time: 0.1371 data: 0.0514 max mem: 9390 +Train: [45] [ 400/6250] eta: 0:15:05 lr: 0.000078 grad: 0.0793 (0.0820) loss: 0.8171 (0.8277) time: 0.1452 data: 0.0625 max mem: 9390 +Train: [45] [ 500/6250] eta: 0:14:21 lr: 0.000078 grad: 0.0767 (0.0816) loss: 0.8257 (0.8271) time: 0.1250 data: 0.0421 max mem: 9390 +Train: [45] [ 600/6250] eta: 0:13:56 lr: 0.000078 grad: 0.0747 (0.0814) loss: 0.8288 (0.8267) time: 0.1348 data: 0.0536 max mem: 9390 +Train: [45] [ 700/6250] eta: 0:13:35 lr: 0.000078 grad: 0.0789 (0.0814) loss: 0.8209 (0.8261) time: 0.1584 data: 0.0768 max mem: 9390 +Train: [45] [ 800/6250] eta: 0:13:10 lr: 0.000078 grad: 0.0852 (0.0812) loss: 0.8226 (0.8260) time: 0.1495 data: 0.0706 max mem: 9390 +Train: [45] [ 900/6250] eta: 0:12:46 lr: 0.000078 grad: 0.0736 (0.0812) loss: 0.8268 (0.8259) time: 0.1332 data: 0.0483 max mem: 9390 +Train: [45] [1000/6250] eta: 0:12:19 lr: 0.000078 grad: 0.0780 (0.0812) loss: 0.8238 (0.8260) time: 0.0969 data: 0.0097 max mem: 9390 +Train: [45] [1100/6250] eta: 0:11:58 lr: 0.000077 grad: 0.0787 (0.0812) loss: 0.8246 (0.8257) time: 0.1258 data: 0.0392 max mem: 9390 +Train: [45] [1200/6250] eta: 0:11:37 lr: 0.000077 grad: 0.0932 (0.0815) loss: 0.8227 (0.8253) time: 0.1451 data: 0.0645 max mem: 9390 +Train: [45] [1300/6250] eta: 0:11:17 lr: 0.000077 grad: 0.0804 (0.0816) loss: 0.8227 (0.8251) time: 0.1186 data: 0.0433 max mem: 9390 +Train: [45] [1400/6250] eta: 0:11:03 lr: 0.000077 grad: 0.0785 (0.0817) loss: 0.8237 (0.8248) time: 0.1540 data: 0.0646 max mem: 9390 +Train: [45] [1500/6250] eta: 0:10:52 lr: 0.000077 grad: 0.0880 (0.0819) loss: 0.8144 (0.8246) time: 0.1445 data: 0.0684 max mem: 9390 +Train: [45] [1600/6250] eta: 0:10:39 lr: 0.000077 grad: 0.0859 (0.0821) loss: 0.8166 (0.8243) time: 0.1442 data: 0.0676 max mem: 9390 +Train: [45] [1700/6250] eta: 0:10:23 lr: 0.000077 grad: 0.0859 (0.0826) loss: 0.8143 (0.8238) time: 0.1157 data: 0.0407 max mem: 9390 +Train: [45] [1800/6250] eta: 0:10:08 lr: 0.000077 grad: 0.0847 (0.0828) loss: 0.8116 (0.8234) time: 0.1289 data: 0.0460 max mem: 9390 +Train: [45] [1900/6250] eta: 0:09:54 lr: 0.000077 grad: 0.0868 (0.0832) loss: 0.8210 (0.8232) time: 0.1374 data: 0.0571 max mem: 9390 +Train: [45] [2000/6250] eta: 0:09:51 lr: 0.000077 grad: 0.0880 (0.0834) loss: 0.8123 (0.8229) time: 0.0954 data: 0.0002 max mem: 9390 +Train: [45] [2100/6250] eta: 0:09:35 lr: 0.000077 grad: 0.0843 (0.0837) loss: 0.8187 (0.8226) time: 0.1482 data: 0.0731 max mem: 9390 +Train: [45] [2200/6250] eta: 0:09:21 lr: 0.000077 grad: 0.0860 (0.0840) loss: 0.8109 (0.8223) time: 0.1509 data: 0.0688 max mem: 9390 +Train: [45] [2300/6250] eta: 0:09:06 lr: 0.000077 grad: 0.0822 (0.0841) loss: 0.8106 (0.8220) time: 0.1369 data: 0.0531 max mem: 9390 +Train: [45] [2400/6250] eta: 0:08:53 lr: 0.000077 grad: 0.0901 (0.0844) loss: 0.8150 (0.8216) time: 0.1504 data: 0.0683 max mem: 9390 +Train: [45] [2500/6250] eta: 0:08:38 lr: 0.000077 grad: 0.0864 (0.0847) loss: 0.8145 (0.8213) time: 0.1322 data: 0.0534 max mem: 9390 +Train: [45] [2600/6250] eta: 0:08:25 lr: 0.000077 grad: 0.0862 (0.0849) loss: 0.8141 (0.8212) time: 0.1372 data: 0.0528 max mem: 9390 +Train: [45] [2700/6250] eta: 0:08:12 lr: 0.000077 grad: 0.0844 (0.0850) loss: 0.8231 (0.8211) time: 0.1701 data: 0.0954 max mem: 9390 +Train: [45] [2800/6250] eta: 0:07:59 lr: 0.000077 grad: 0.0841 (0.0851) loss: 0.8211 (0.8210) time: 0.1367 data: 0.0614 max mem: 9390 +Train: [45] [2900/6250] eta: 0:07:45 lr: 0.000077 grad: 0.0816 (0.0851) loss: 0.8204 (0.8209) time: 0.1567 data: 0.0782 max mem: 9390 +Train: [45] [3000/6250] eta: 0:07:34 lr: 0.000077 grad: 0.0849 (0.0852) loss: 0.8183 (0.8209) time: 0.1321 data: 0.0453 max mem: 9390 +Train: [45] [3100/6250] eta: 0:07:20 lr: 0.000077 grad: 0.0782 (0.0853) loss: 0.8252 (0.8210) time: 0.1253 data: 0.0470 max mem: 9390 +Train: [45] [3200/6250] eta: 0:07:06 lr: 0.000077 grad: 0.0862 (0.0855) loss: 0.8278 (0.8210) time: 0.1388 data: 0.0629 max mem: 9390 +Train: [45] [3300/6250] eta: 0:06:52 lr: 0.000077 grad: 0.0776 (0.0854) loss: 0.8219 (0.8211) time: 0.1576 data: 0.0787 max mem: 9390 +Train: [45] [3400/6250] eta: 0:06:38 lr: 0.000077 grad: 0.0777 (0.0853) loss: 0.8288 (0.8213) time: 0.1479 data: 0.0669 max mem: 9390 +Train: [45] [3500/6250] eta: 0:06:26 lr: 0.000077 grad: 0.0860 (0.0853) loss: 0.8283 (0.8215) time: 0.1891 data: 0.0977 max mem: 9390 +Train: [45] [3600/6250] eta: 0:06:11 lr: 0.000077 grad: 0.0777 (0.0852) loss: 0.8312 (0.8216) time: 0.1263 data: 0.0520 max mem: 9390 +Train: [45] [3700/6250] eta: 0:05:57 lr: 0.000077 grad: 0.0766 (0.0851) loss: 0.8300 (0.8217) time: 0.1634 data: 0.0888 max mem: 9390 +Train: [45] [3800/6250] eta: 0:05:43 lr: 0.000077 grad: 0.0813 (0.0851) loss: 0.8228 (0.8218) time: 0.1306 data: 0.0481 max mem: 9390 +Train: [45] [3900/6250] eta: 0:05:30 lr: 0.000077 grad: 0.0813 (0.0851) loss: 0.8277 (0.8219) time: 0.1414 data: 0.0616 max mem: 9390 +Train: [45] [4000/6250] eta: 0:05:16 lr: 0.000077 grad: 0.0834 (0.0850) loss: 0.8216 (0.8219) time: 0.1615 data: 0.0800 max mem: 9390 +Train: [45] [4100/6250] eta: 0:05:02 lr: 0.000077 grad: 0.0833 (0.0851) loss: 0.8242 (0.8219) time: 0.1298 data: 0.0505 max mem: 9390 +Train: [45] [4200/6250] eta: 0:04:48 lr: 0.000076 grad: 0.0848 (0.0851) loss: 0.8250 (0.8219) time: 0.1262 data: 0.0478 max mem: 9390 +Train: [45] [4300/6250] eta: 0:04:34 lr: 0.000076 grad: 0.0812 (0.0852) loss: 0.8213 (0.8219) time: 0.1174 data: 0.0374 max mem: 9390 +Train: [45] [4400/6250] eta: 0:04:20 lr: 0.000076 grad: 0.0871 (0.0852) loss: 0.8217 (0.8219) time: 0.1558 data: 0.0669 max mem: 9390 +Train: [45] [4500/6250] eta: 0:04:05 lr: 0.000076 grad: 0.0758 (0.0852) loss: 0.8298 (0.8220) time: 0.1326 data: 0.0498 max mem: 9390 +Train: [45] [4600/6250] eta: 0:03:51 lr: 0.000076 grad: 0.0820 (0.0852) loss: 0.8225 (0.8220) time: 0.1150 data: 0.0307 max mem: 9390 +Train: [45] [4700/6250] eta: 0:03:37 lr: 0.000076 grad: 0.0823 (0.0852) loss: 0.8229 (0.8220) time: 0.1267 data: 0.0408 max mem: 9390 +Train: [45] [4800/6250] eta: 0:03:23 lr: 0.000076 grad: 0.0849 (0.0852) loss: 0.8224 (0.8220) time: 0.1331 data: 0.0590 max mem: 9390 +Train: [45] [4900/6250] eta: 0:03:09 lr: 0.000076 grad: 0.0819 (0.0852) loss: 0.8228 (0.8221) time: 0.1247 data: 0.0474 max mem: 9390 +Train: [45] [5000/6250] eta: 0:02:54 lr: 0.000076 grad: 0.0822 (0.0852) loss: 0.8235 (0.8220) time: 0.1158 data: 0.0351 max mem: 9390 +Train: [45] [5100/6250] eta: 0:02:40 lr: 0.000076 grad: 0.0822 (0.0852) loss: 0.8244 (0.8221) time: 0.1528 data: 0.0717 max mem: 9390 +Train: [45] [5200/6250] eta: 0:02:26 lr: 0.000076 grad: 0.0822 (0.0852) loss: 0.8202 (0.8221) time: 0.1235 data: 0.0352 max mem: 9390 +Train: [45] [5300/6250] eta: 0:02:12 lr: 0.000076 grad: 0.0874 (0.0852) loss: 0.8149 (0.8221) time: 0.1487 data: 0.0726 max mem: 9390 +Train: [45] [5400/6250] eta: 0:01:58 lr: 0.000076 grad: 0.0847 (0.0851) loss: 0.8233 (0.8221) time: 0.1377 data: 0.0480 max mem: 9390 +Train: [45] [5500/6250] eta: 0:01:44 lr: 0.000076 grad: 0.0832 (0.0851) loss: 0.8228 (0.8221) time: 0.1418 data: 0.0646 max mem: 9390 +Train: [45] [5600/6250] eta: 0:01:30 lr: 0.000076 grad: 0.0862 (0.0851) loss: 0.8263 (0.8221) time: 0.1373 data: 0.0640 max mem: 9390 +Train: [45] [5700/6250] eta: 0:01:17 lr: 0.000076 grad: 0.0873 (0.0851) loss: 0.8224 (0.8222) time: 0.1720 data: 0.0959 max mem: 9390 +Train: [45] [5800/6250] eta: 0:01:03 lr: 0.000076 grad: 0.0873 (0.0852) loss: 0.8235 (0.8222) time: 0.1321 data: 0.0493 max mem: 9390 +Train: [45] [5900/6250] eta: 0:00:49 lr: 0.000076 grad: 0.0825 (0.0852) loss: 0.8288 (0.8222) time: 0.1690 data: 0.0937 max mem: 9390 +Train: [45] [6000/6250] eta: 0:00:35 lr: 0.000076 grad: 0.0833 (0.0852) loss: 0.8239 (0.8222) time: 0.1418 data: 0.0633 max mem: 9390 +Train: [45] [6100/6250] eta: 0:00:21 lr: 0.000076 grad: 0.0879 (0.0853) loss: 0.8243 (0.8223) time: 0.1603 data: 0.0759 max mem: 9390 +Train: [45] [6200/6250] eta: 0:00:07 lr: 0.000076 grad: 0.0905 (0.0854) loss: 0.8195 (0.8222) time: 0.1255 data: 0.0506 max mem: 9390 +Train: [45] [6249/6250] eta: 0:00:00 lr: 0.000076 grad: 0.0885 (0.0854) loss: 0.8249 (0.8222) time: 0.1330 data: 0.0532 max mem: 9390 +Train: [45] Total time: 0:14:41 (0.1410 s / it) +Averaged stats: lr: 0.000076 grad: 0.0885 (0.0854) loss: 0.8249 (0.8222) +Eval (hcp-train-subset): [45] [ 0/62] eta: 0:04:32 loss: 0.8499 (0.8499) time: 4.3951 data: 4.3432 max mem: 9390 +Eval (hcp-train-subset): [45] [61/62] eta: 0:00:00 loss: 0.8374 (0.8385) time: 0.1304 data: 0.1050 max mem: 9390 +Eval (hcp-train-subset): [45] Total time: 0:00:13 (0.2151 s / it) +Averaged stats (hcp-train-subset): loss: 0.8374 (0.8385) +Eval (hcp-val): [45] [ 0/62] eta: 0:06:57 loss: 0.8336 (0.8336) time: 6.7288 data: 6.7023 max mem: 9390 +Eval (hcp-val): [45] [61/62] eta: 0:00:00 loss: 0.8365 (0.8362) time: 0.1294 data: 0.1041 max mem: 9390 +Eval (hcp-val): [45] Total time: 0:00:14 (0.2402 s / it) +Averaged stats (hcp-val): loss: 0.8365 (0.8362) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +Train: [46] [ 0/6250] eta: 11:16:51 lr: 0.000076 grad: 0.2158 (0.2158) loss: 0.8180 (0.8180) time: 6.4978 data: 6.3567 max mem: 9390 +Train: [46] [ 100/6250] eta: 0:20:12 lr: 0.000076 grad: 0.0857 (0.0895) loss: 0.8287 (0.8363) time: 0.1435 data: 0.0474 max mem: 9390 +Train: [46] [ 200/6250] eta: 0:17:35 lr: 0.000076 grad: 0.0860 (0.0881) loss: 0.8321 (0.8347) time: 0.1474 data: 0.0592 max mem: 9390 +Train: [46] [ 300/6250] eta: 0:15:56 lr: 0.000076 grad: 0.0801 (0.0888) loss: 0.8310 (0.8333) time: 0.1338 data: 0.0511 max mem: 9390 +Train: [46] [ 400/6250] eta: 0:15:31 lr: 0.000076 grad: 0.0870 (0.0893) loss: 0.8271 (0.8317) time: 0.1714 data: 0.0906 max mem: 9390 +Train: [46] [ 500/6250] eta: 0:14:49 lr: 0.000076 grad: 0.0851 (0.0894) loss: 0.8232 (0.8301) time: 0.1521 data: 0.0716 max mem: 9390 +Train: [46] [ 600/6250] eta: 0:14:17 lr: 0.000076 grad: 0.0829 (0.0891) loss: 0.8204 (0.8287) time: 0.1599 data: 0.0731 max mem: 9390 +Train: [46] [ 700/6250] eta: 0:13:47 lr: 0.000076 grad: 0.0862 (0.0887) loss: 0.8186 (0.8280) time: 0.1312 data: 0.0454 max mem: 9390 +Train: [46] [ 800/6250] eta: 0:13:29 lr: 0.000076 grad: 0.0819 (0.0881) loss: 0.8209 (0.8277) time: 0.1508 data: 0.0666 max mem: 9390 +Train: [46] [ 900/6250] eta: 0:13:04 lr: 0.000076 grad: 0.0827 (0.0878) loss: 0.8198 (0.8273) time: 0.1326 data: 0.0466 max mem: 9390 +Train: [46] [1000/6250] eta: 0:12:37 lr: 0.000076 grad: 0.0885 (0.0878) loss: 0.8211 (0.8271) time: 0.1298 data: 0.0463 max mem: 9390 +Train: [46] [1100/6250] eta: 0:12:13 lr: 0.000075 grad: 0.0833 (0.0874) loss: 0.8259 (0.8269) time: 0.1282 data: 0.0427 max mem: 9390 +Train: [46] [1200/6250] eta: 0:11:50 lr: 0.000075 grad: 0.0815 (0.0872) loss: 0.8217 (0.8265) time: 0.1131 data: 0.0290 max mem: 9390 +Train: [46] [1300/6250] eta: 0:11:27 lr: 0.000075 grad: 0.0856 (0.0874) loss: 0.8171 (0.8261) time: 0.1213 data: 0.0369 max mem: 9390 +Train: [46] [1400/6250] eta: 0:11:12 lr: 0.000075 grad: 0.0862 (0.0875) loss: 0.8128 (0.8256) time: 0.1482 data: 0.0711 max mem: 9390 +Train: [46] [1500/6250] eta: 0:10:56 lr: 0.000075 grad: 0.0798 (0.0876) loss: 0.8291 (0.8252) time: 0.1103 data: 0.0271 max mem: 9390 +Train: [46] [1600/6250] eta: 0:10:44 lr: 0.000075 grad: 0.0814 (0.0877) loss: 0.8247 (0.8249) time: 0.1354 data: 0.0576 max mem: 9390 +Train: [46] [1700/6250] eta: 0:10:29 lr: 0.000075 grad: 0.0825 (0.0877) loss: 0.8217 (0.8246) time: 0.1306 data: 0.0444 max mem: 9390 +Train: [46] [1800/6250] eta: 0:10:15 lr: 0.000075 grad: 0.0857 (0.0877) loss: 0.8261 (0.8244) time: 0.1315 data: 0.0452 max mem: 9390 +Train: [46] [1900/6250] eta: 0:10:00 lr: 0.000075 grad: 0.0862 (0.0877) loss: 0.8260 (0.8243) time: 0.1409 data: 0.0607 max mem: 9390 +Train: [46] [2000/6250] eta: 0:09:46 lr: 0.000075 grad: 0.0875 (0.0876) loss: 0.8193 (0.8241) time: 0.1391 data: 0.0600 max mem: 9390 +Train: [46] [2100/6250] eta: 0:09:30 lr: 0.000075 grad: 0.0882 (0.0877) loss: 0.8193 (0.8240) time: 0.1417 data: 0.0623 max mem: 9390 +Train: [46] [2200/6250] eta: 0:09:18 lr: 0.000075 grad: 0.0804 (0.0875) loss: 0.8203 (0.8239) time: 0.1526 data: 0.0608 max mem: 9390 +Train: [46] [2300/6250] eta: 0:09:04 lr: 0.000075 grad: 0.0833 (0.0875) loss: 0.8224 (0.8239) time: 0.1368 data: 0.0517 max mem: 9390 +Train: [46] [2400/6250] eta: 0:08:49 lr: 0.000075 grad: 0.0811 (0.0874) loss: 0.8226 (0.8238) time: 0.1286 data: 0.0484 max mem: 9390 +Train: [46] [2500/6250] eta: 0:08:36 lr: 0.000075 grad: 0.0825 (0.0874) loss: 0.8234 (0.8237) time: 0.1319 data: 0.0408 max mem: 9390 +Train: [46] [2600/6250] eta: 0:08:23 lr: 0.000075 grad: 0.0847 (0.0875) loss: 0.8207 (0.8236) time: 0.1694 data: 0.0896 max mem: 9390 +Train: [46] [2700/6250] eta: 0:08:10 lr: 0.000075 grad: 0.0797 (0.0874) loss: 0.8253 (0.8236) time: 0.1377 data: 0.0588 max mem: 9390 +Train: [46] [2800/6250] eta: 0:07:56 lr: 0.000075 grad: 0.0845 (0.0874) loss: 0.8225 (0.8235) time: 0.1264 data: 0.0472 max mem: 9390 +Train: [46] [2900/6250] eta: 0:07:43 lr: 0.000075 grad: 0.0753 (0.0872) loss: 0.8252 (0.8236) time: 0.1257 data: 0.0446 max mem: 9390 +Train: [46] [3000/6250] eta: 0:07:29 lr: 0.000075 grad: 0.0890 (0.0872) loss: 0.8241 (0.8236) time: 0.1278 data: 0.0486 max mem: 9390 +Train: [46] [3100/6250] eta: 0:07:15 lr: 0.000075 grad: 0.0863 (0.0872) loss: 0.8217 (0.8235) time: 0.1407 data: 0.0553 max mem: 9390 +Train: [46] [3200/6250] eta: 0:07:01 lr: 0.000075 grad: 0.0874 (0.0872) loss: 0.8188 (0.8234) time: 0.1272 data: 0.0480 max mem: 9390 +Train: [46] [3300/6250] eta: 0:06:47 lr: 0.000075 grad: 0.0842 (0.0872) loss: 0.8206 (0.8233) time: 0.1609 data: 0.0835 max mem: 9390 +Train: [46] [3400/6250] eta: 0:06:33 lr: 0.000075 grad: 0.0865 (0.0873) loss: 0.8215 (0.8232) time: 0.1195 data: 0.0402 max mem: 9390 +Train: [46] [3500/6250] eta: 0:06:19 lr: 0.000075 grad: 0.0832 (0.0874) loss: 0.8217 (0.8231) time: 0.1437 data: 0.0637 max mem: 9390 +Train: [46] [3600/6250] eta: 0:06:06 lr: 0.000075 grad: 0.0831 (0.0875) loss: 0.8222 (0.8230) time: 0.1412 data: 0.0593 max mem: 9390 +Train: [46] [3700/6250] eta: 0:05:52 lr: 0.000075 grad: 0.0847 (0.0875) loss: 0.8189 (0.8228) time: 0.1354 data: 0.0541 max mem: 9390 +Train: [46] [3800/6250] eta: 0:05:38 lr: 0.000075 grad: 0.0859 (0.0876) loss: 0.8156 (0.8227) time: 0.1378 data: 0.0580 max mem: 9390 +Train: [46] [3900/6250] eta: 0:05:25 lr: 0.000075 grad: 0.0891 (0.0876) loss: 0.8166 (0.8226) time: 0.1461 data: 0.0689 max mem: 9390 +Train: [46] [4000/6250] eta: 0:05:11 lr: 0.000075 grad: 0.0892 (0.0877) loss: 0.8172 (0.8225) time: 0.1274 data: 0.0484 max mem: 9390 +Train: [46] [4100/6250] eta: 0:04:58 lr: 0.000075 grad: 0.0887 (0.0876) loss: 0.8146 (0.8223) time: 0.1418 data: 0.0643 max mem: 9390 +Train: [46] [4200/6250] eta: 0:04:44 lr: 0.000074 grad: 0.0899 (0.0877) loss: 0.8152 (0.8222) time: 0.1381 data: 0.0495 max mem: 9390 +Train: [46] [4300/6250] eta: 0:04:30 lr: 0.000074 grad: 0.0864 (0.0877) loss: 0.8203 (0.8221) time: 0.1406 data: 0.0607 max mem: 9390 +Train: [46] [4400/6250] eta: 0:04:16 lr: 0.000074 grad: 0.0862 (0.0877) loss: 0.8207 (0.8220) time: 0.1312 data: 0.0485 max mem: 9390 +Train: [46] [4500/6250] eta: 0:04:02 lr: 0.000074 grad: 0.0871 (0.0877) loss: 0.8145 (0.8218) time: 0.1435 data: 0.0611 max mem: 9390 +Train: [46] [4600/6250] eta: 0:03:48 lr: 0.000074 grad: 0.0869 (0.0876) loss: 0.8179 (0.8218) time: 0.1418 data: 0.0585 max mem: 9390 +Train: [46] [4700/6250] eta: 0:03:34 lr: 0.000074 grad: 0.0831 (0.0876) loss: 0.8199 (0.8217) time: 0.1200 data: 0.0421 max mem: 9390 +Train: [46] [4800/6250] eta: 0:03:20 lr: 0.000074 grad: 0.0782 (0.0877) loss: 0.8217 (0.8216) time: 0.1339 data: 0.0503 max mem: 9390 +Train: [46] [4900/6250] eta: 0:03:06 lr: 0.000074 grad: 0.0846 (0.0877) loss: 0.8192 (0.8215) time: 0.1391 data: 0.0569 max mem: 9390 +Train: [46] [5000/6250] eta: 0:02:52 lr: 0.000074 grad: 0.0915 (0.0877) loss: 0.8213 (0.8215) time: 0.1318 data: 0.0517 max mem: 9390 +Train: [46] [5100/6250] eta: 0:02:38 lr: 0.000074 grad: 0.0877 (0.0878) loss: 0.8165 (0.8214) time: 0.1460 data: 0.0692 max mem: 9390 +Train: [46] [5200/6250] eta: 0:02:25 lr: 0.000074 grad: 0.0818 (0.0877) loss: 0.8214 (0.8214) time: 0.1266 data: 0.0485 max mem: 9390 +Train: [46] [5300/6250] eta: 0:02:11 lr: 0.000074 grad: 0.0870 (0.0877) loss: 0.8206 (0.8214) time: 0.1233 data: 0.0442 max mem: 9390 +Train: [46] [5400/6250] eta: 0:01:57 lr: 0.000074 grad: 0.0823 (0.0877) loss: 0.8237 (0.8214) time: 0.1334 data: 0.0502 max mem: 9390 +Train: [46] [5500/6250] eta: 0:01:43 lr: 0.000074 grad: 0.0897 (0.0877) loss: 0.8244 (0.8215) time: 0.1283 data: 0.0497 max mem: 9390 +Train: [46] [5600/6250] eta: 0:01:29 lr: 0.000074 grad: 0.0832 (0.0876) loss: 0.8263 (0.8215) time: 0.1228 data: 0.0446 max mem: 9390 +Train: [46] [5700/6250] eta: 0:01:16 lr: 0.000074 grad: 0.0908 (0.0877) loss: 0.8248 (0.8216) time: 0.0791 data: 0.0002 max mem: 9390 +Train: [46] [5800/6250] eta: 0:01:02 lr: 0.000074 grad: 0.0914 (0.0877) loss: 0.8283 (0.8216) time: 0.1561 data: 0.0776 max mem: 9390 +Train: [46] [5900/6250] eta: 0:00:48 lr: 0.000074 grad: 0.0848 (0.0877) loss: 0.8202 (0.8216) time: 0.1493 data: 0.0674 max mem: 9390 +Train: [46] [6000/6250] eta: 0:00:34 lr: 0.000074 grad: 0.0797 (0.0877) loss: 0.8240 (0.8217) time: 0.1536 data: 0.0702 max mem: 9390 +Train: [46] [6100/6250] eta: 0:00:20 lr: 0.000074 grad: 0.0873 (0.0877) loss: 0.8220 (0.8217) time: 0.1305 data: 0.0498 max mem: 9390 +Train: [46] [6200/6250] eta: 0:00:06 lr: 0.000074 grad: 0.0823 (0.0876) loss: 0.8270 (0.8217) time: 0.0942 data: 0.0116 max mem: 9390 +Train: [46] [6249/6250] eta: 0:00:00 lr: 0.000074 grad: 0.0795 (0.0876) loss: 0.8254 (0.8217) time: 0.1435 data: 0.0607 max mem: 9390 +Train: [46] Total time: 0:14:30 (0.1392 s / it) +Averaged stats: lr: 0.000074 grad: 0.0795 (0.0876) loss: 0.8254 (0.8217) +Eval (hcp-train-subset): [46] [ 0/62] eta: 0:04:00 loss: 0.8509 (0.8509) time: 3.8756 data: 3.7947 max mem: 9390 +Eval (hcp-train-subset): [46] [61/62] eta: 0:00:00 loss: 0.8369 (0.8385) time: 0.1108 data: 0.0842 max mem: 9390 +Eval (hcp-train-subset): [46] Total time: 0:00:11 (0.1935 s / it) +Averaged stats (hcp-train-subset): loss: 0.8369 (0.8385) +Eval (hcp-val): [46] [ 0/62] eta: 0:03:05 loss: 0.8331 (0.8331) time: 2.9919 data: 2.9126 max mem: 9390 +Eval (hcp-val): [46] [61/62] eta: 0:00:00 loss: 0.8358 (0.8369) time: 0.1341 data: 0.1090 max mem: 9390 +Eval (hcp-val): [46] Total time: 0:00:13 (0.2189 s / it) +Averaged stats (hcp-val): loss: 0.8358 (0.8369) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +Train: [47] [ 0/6250] eta: 7:53:51 lr: 0.000074 grad: 0.1252 (0.1252) loss: 0.8514 (0.8514) time: 4.5490 data: 4.2595 max mem: 9390 +Train: [47] [ 100/6250] eta: 0:20:49 lr: 0.000074 grad: 0.0783 (0.0819) loss: 0.8318 (0.8404) time: 0.1528 data: 0.0541 max mem: 9390 +Train: [47] [ 200/6250] eta: 0:17:46 lr: 0.000074 grad: 0.0721 (0.0840) loss: 0.8360 (0.8353) time: 0.1575 data: 0.0786 max mem: 9390 +Train: [47] [ 300/6250] eta: 0:16:27 lr: 0.000074 grad: 0.0809 (0.0856) loss: 0.8255 (0.8319) time: 0.1382 data: 0.0481 max mem: 9390 +Train: [47] [ 400/6250] eta: 0:15:33 lr: 0.000074 grad: 0.0824 (0.0855) loss: 0.8167 (0.8293) time: 0.1469 data: 0.0543 max mem: 9390 +Train: [47] [ 500/6250] eta: 0:15:09 lr: 0.000074 grad: 0.0903 (0.0851) loss: 0.8107 (0.8279) time: 0.1631 data: 0.0865 max mem: 9390 +Train: [47] [ 600/6250] eta: 0:14:38 lr: 0.000074 grad: 0.0792 (0.0851) loss: 0.8280 (0.8266) time: 0.1487 data: 0.0662 max mem: 9390 +Train: [47] [ 700/6250] eta: 0:14:10 lr: 0.000074 grad: 0.0827 (0.0851) loss: 0.8223 (0.8260) time: 0.1544 data: 0.0736 max mem: 9390 +Train: [47] [ 800/6250] eta: 0:13:45 lr: 0.000074 grad: 0.0806 (0.0852) loss: 0.8186 (0.8255) time: 0.1307 data: 0.0435 max mem: 9390 +Train: [47] [ 900/6250] eta: 0:13:20 lr: 0.000074 grad: 0.0816 (0.0851) loss: 0.8339 (0.8251) time: 0.1207 data: 0.0378 max mem: 9390 +Train: [47] [1000/6250] eta: 0:12:57 lr: 0.000073 grad: 0.0794 (0.0850) loss: 0.8275 (0.8249) time: 0.1481 data: 0.0664 max mem: 9390 +Train: [47] [1100/6250] eta: 0:12:32 lr: 0.000073 grad: 0.0830 (0.0851) loss: 0.8165 (0.8247) time: 0.1450 data: 0.0612 max mem: 9390 +Train: [47] [1200/6250] eta: 0:12:08 lr: 0.000073 grad: 0.0850 (0.0851) loss: 0.8161 (0.8245) time: 0.1251 data: 0.0466 max mem: 9390 +Train: [47] [1300/6250] eta: 0:11:49 lr: 0.000073 grad: 0.0782 (0.0851) loss: 0.8190 (0.8240) time: 0.1522 data: 0.0701 max mem: 9390 +Train: [47] [1400/6250] eta: 0:11:36 lr: 0.000073 grad: 0.0852 (0.0854) loss: 0.8199 (0.8237) time: 0.1115 data: 0.0284 max mem: 9390 +Train: [47] [1500/6250] eta: 0:11:19 lr: 0.000073 grad: 0.0826 (0.0855) loss: 0.8194 (0.8235) time: 0.1255 data: 0.0475 max mem: 9390 +Train: [47] [1600/6250] eta: 0:11:03 lr: 0.000073 grad: 0.0843 (0.0856) loss: 0.8213 (0.8233) time: 0.1417 data: 0.0544 max mem: 9390 +Train: [47] [1700/6250] eta: 0:10:48 lr: 0.000073 grad: 0.0842 (0.0858) loss: 0.8162 (0.8231) time: 0.1309 data: 0.0516 max mem: 9390 +Train: [47] [1800/6250] eta: 0:10:32 lr: 0.000073 grad: 0.0862 (0.0859) loss: 0.8245 (0.8230) time: 0.1357 data: 0.0574 max mem: 9390 +Train: [47] [1900/6250] eta: 0:10:14 lr: 0.000073 grad: 0.0853 (0.0860) loss: 0.8182 (0.8228) time: 0.1229 data: 0.0445 max mem: 9390 +Train: [47] [2000/6250] eta: 0:09:59 lr: 0.000073 grad: 0.0892 (0.0861) loss: 0.8164 (0.8226) time: 0.1357 data: 0.0493 max mem: 9390 +Train: [47] [2100/6250] eta: 0:09:45 lr: 0.000073 grad: 0.0823 (0.0863) loss: 0.8222 (0.8226) time: 0.1624 data: 0.0836 max mem: 9390 +Train: [47] [2200/6250] eta: 0:09:35 lr: 0.000073 grad: 0.0842 (0.0865) loss: 0.8170 (0.8224) time: 0.1908 data: 0.1049 max mem: 9390 +Train: [47] [2300/6250] eta: 0:09:18 lr: 0.000073 grad: 0.0793 (0.0867) loss: 0.8250 (0.8224) time: 0.1281 data: 0.0471 max mem: 9390 +Train: [47] [2400/6250] eta: 0:09:05 lr: 0.000073 grad: 0.0942 (0.0868) loss: 0.8187 (0.8223) time: 0.1492 data: 0.0639 max mem: 9390 +Train: [47] [2500/6250] eta: 0:08:49 lr: 0.000073 grad: 0.0927 (0.0870) loss: 0.8225 (0.8222) time: 0.1195 data: 0.0373 max mem: 9390 +Train: [47] [2600/6250] eta: 0:08:33 lr: 0.000073 grad: 0.0855 (0.0871) loss: 0.8197 (0.8220) time: 0.1305 data: 0.0476 max mem: 9390 +Train: [47] [2700/6250] eta: 0:08:17 lr: 0.000073 grad: 0.0938 (0.0870) loss: 0.8216 (0.8220) time: 0.1237 data: 0.0491 max mem: 9390 +Train: [47] [2800/6250] eta: 0:08:03 lr: 0.000073 grad: 0.0841 (0.0871) loss: 0.8186 (0.8220) time: 0.1266 data: 0.0381 max mem: 9390 +Train: [47] [2900/6250] eta: 0:07:49 lr: 0.000073 grad: 0.0848 (0.0871) loss: 0.8267 (0.8219) time: 0.1398 data: 0.0585 max mem: 9390 +Train: [47] [3000/6250] eta: 0:07:36 lr: 0.000073 grad: 0.0868 (0.0872) loss: 0.8136 (0.8218) time: 0.1366 data: 0.0570 max mem: 9390 +Train: [47] [3100/6250] eta: 0:07:21 lr: 0.000073 grad: 0.0894 (0.0873) loss: 0.8196 (0.8218) time: 0.1366 data: 0.0627 max mem: 9390 +Train: [47] [3200/6250] eta: 0:07:07 lr: 0.000073 grad: 0.0808 (0.0873) loss: 0.8290 (0.8218) time: 0.1467 data: 0.0640 max mem: 9390 +Train: [47] [3300/6250] eta: 0:06:52 lr: 0.000073 grad: 0.0860 (0.0873) loss: 0.8203 (0.8218) time: 0.1240 data: 0.0386 max mem: 9390 +Train: [47] [3400/6250] eta: 0:06:39 lr: 0.000073 grad: 0.0836 (0.0873) loss: 0.8194 (0.8219) time: 0.1753 data: 0.0885 max mem: 9390 +Train: [47] [3500/6250] eta: 0:06:24 lr: 0.000073 grad: 0.0842 (0.0873) loss: 0.8257 (0.8220) time: 0.1493 data: 0.0663 max mem: 9390 +Train: [47] [3600/6250] eta: 0:06:11 lr: 0.000073 grad: 0.0904 (0.0873) loss: 0.8193 (0.8220) time: 0.1540 data: 0.0754 max mem: 9390 +Train: [47] [3700/6250] eta: 0:05:58 lr: 0.000073 grad: 0.0828 (0.0873) loss: 0.8220 (0.8220) time: 0.1408 data: 0.0682 max mem: 9390 +Train: [47] [3800/6250] eta: 0:05:43 lr: 0.000073 grad: 0.0874 (0.0873) loss: 0.8250 (0.8220) time: 0.1343 data: 0.0573 max mem: 9390 +Train: [47] [3900/6250] eta: 0:05:29 lr: 0.000073 grad: 0.0854 (0.0873) loss: 0.8187 (0.8220) time: 0.1726 data: 0.0977 max mem: 9390 +Train: [47] [4000/6250] eta: 0:05:15 lr: 0.000073 grad: 0.0835 (0.0873) loss: 0.8155 (0.8221) time: 0.1568 data: 0.0721 max mem: 9390 +Train: [47] [4100/6250] eta: 0:05:01 lr: 0.000072 grad: 0.0831 (0.0873) loss: 0.8272 (0.8220) time: 0.1369 data: 0.0539 max mem: 9390 +Train: [47] [4200/6250] eta: 0:04:47 lr: 0.000072 grad: 0.0848 (0.0873) loss: 0.8240 (0.8220) time: 0.1211 data: 0.0393 max mem: 9390 +Train: [47] [4300/6250] eta: 0:04:33 lr: 0.000072 grad: 0.0861 (0.0874) loss: 0.8207 (0.8219) time: 0.1490 data: 0.0555 max mem: 9390 +Train: [47] [4400/6250] eta: 0:04:19 lr: 0.000072 grad: 0.0904 (0.0874) loss: 0.8147 (0.8219) time: 0.1644 data: 0.0892 max mem: 9390 +Train: [47] [4500/6250] eta: 0:04:04 lr: 0.000072 grad: 0.0861 (0.0875) loss: 0.8234 (0.8218) time: 0.1409 data: 0.0638 max mem: 9390 +Train: [47] [4600/6250] eta: 0:03:51 lr: 0.000072 grad: 0.0904 (0.0875) loss: 0.8215 (0.8217) time: 0.1415 data: 0.0682 max mem: 9390 +Train: [47] [4700/6250] eta: 0:03:36 lr: 0.000072 grad: 0.0851 (0.0876) loss: 0.8158 (0.8217) time: 0.1239 data: 0.0387 max mem: 9390 +Train: [47] [4800/6250] eta: 0:03:22 lr: 0.000072 grad: 0.0900 (0.0876) loss: 0.8130 (0.8216) time: 0.1315 data: 0.0565 max mem: 9390 +Train: [47] [4900/6250] eta: 0:03:08 lr: 0.000072 grad: 0.0956 (0.0877) loss: 0.8160 (0.8216) time: 0.1616 data: 0.0830 max mem: 9390 +Train: [47] [5000/6250] eta: 0:02:54 lr: 0.000072 grad: 0.0924 (0.0878) loss: 0.8221 (0.8215) time: 0.1504 data: 0.0689 max mem: 9390 +Train: [47] [5100/6250] eta: 0:02:40 lr: 0.000072 grad: 0.0841 (0.0878) loss: 0.8169 (0.8215) time: 0.1474 data: 0.0699 max mem: 9390 +Train: [47] [5200/6250] eta: 0:02:26 lr: 0.000072 grad: 0.0891 (0.0878) loss: 0.8126 (0.8214) time: 0.1610 data: 0.0864 max mem: 9390 +Train: [47] [5300/6250] eta: 0:02:12 lr: 0.000072 grad: 0.0909 (0.0879) loss: 0.8188 (0.8214) time: 0.1494 data: 0.0636 max mem: 9390 +Train: [47] [5400/6250] eta: 0:01:58 lr: 0.000072 grad: 0.0844 (0.0879) loss: 0.8208 (0.8214) time: 0.1419 data: 0.0478 max mem: 9390 +Train: [47] [5500/6250] eta: 0:01:45 lr: 0.000072 grad: 0.0826 (0.0879) loss: 0.8269 (0.8214) time: 0.1382 data: 0.0596 max mem: 9390 +Train: [47] [5600/6250] eta: 0:01:30 lr: 0.000072 grad: 0.0866 (0.0879) loss: 0.8200 (0.8214) time: 0.1461 data: 0.0628 max mem: 9390 +Train: [47] [5700/6250] eta: 0:01:16 lr: 0.000072 grad: 0.0846 (0.0880) loss: 0.8270 (0.8214) time: 0.1372 data: 0.0603 max mem: 9390 +Train: [47] [5800/6250] eta: 0:01:02 lr: 0.000072 grad: 0.0875 (0.0880) loss: 0.8228 (0.8214) time: 0.1228 data: 0.0413 max mem: 9390 +Train: [47] [5900/6250] eta: 0:00:48 lr: 0.000072 grad: 0.0877 (0.0881) loss: 0.8201 (0.8215) time: 0.1319 data: 0.0534 max mem: 9390 +Train: [47] [6000/6250] eta: 0:00:34 lr: 0.000072 grad: 0.0869 (0.0881) loss: 0.8259 (0.8215) time: 0.1391 data: 0.0641 max mem: 9390 +Train: [47] [6100/6250] eta: 0:00:20 lr: 0.000072 grad: 0.0871 (0.0882) loss: 0.8185 (0.8215) time: 0.1229 data: 0.0521 max mem: 9390 +Train: [47] [6200/6250] eta: 0:00:06 lr: 0.000072 grad: 0.0811 (0.0882) loss: 0.8201 (0.8215) time: 0.1700 data: 0.0927 max mem: 9390 +Train: [47] [6249/6250] eta: 0:00:00 lr: 0.000072 grad: 0.0889 (0.0881) loss: 0.8217 (0.8216) time: 0.1325 data: 0.0541 max mem: 9390 +Train: [47] Total time: 0:14:38 (0.1406 s / it) +Averaged stats: lr: 0.000072 grad: 0.0889 (0.0881) loss: 0.8217 (0.8216) +Eval (hcp-train-subset): [47] [ 0/62] eta: 0:03:14 loss: 0.8450 (0.8450) time: 3.1317 data: 3.0290 max mem: 9390 +Eval (hcp-train-subset): [47] [61/62] eta: 0:00:00 loss: 0.8355 (0.8370) time: 0.1346 data: 0.1095 max mem: 9390 +Eval (hcp-train-subset): [47] Total time: 0:00:13 (0.2163 s / it) +Averaged stats (hcp-train-subset): loss: 0.8355 (0.8370) +Eval (hcp-val): [47] [ 0/62] eta: 0:05:01 loss: 0.8335 (0.8335) time: 4.8593 data: 4.8296 max mem: 9390 +Eval (hcp-val): [47] [61/62] eta: 0:00:00 loss: 0.8348 (0.8364) time: 0.1364 data: 0.1115 max mem: 9390 +Eval (hcp-val): [47] Total time: 0:00:13 (0.2194 s / it) +Averaged stats (hcp-val): loss: 0.8348 (0.8364) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +Train: [48] [ 0/6250] eta: 10:44:09 lr: 0.000072 grad: 0.1949 (0.1949) loss: 0.8229 (0.8229) time: 6.1840 data: 6.0785 max mem: 9390 +Train: [48] [ 100/6250] eta: 0:20:27 lr: 0.000072 grad: 0.0881 (0.0916) loss: 0.8316 (0.8405) time: 0.1614 data: 0.0761 max mem: 9390 +Train: [48] [ 200/6250] eta: 0:17:28 lr: 0.000072 grad: 0.0826 (0.0914) loss: 0.8306 (0.8336) time: 0.1524 data: 0.0606 max mem: 9390 +Train: [48] [ 300/6250] eta: 0:16:02 lr: 0.000072 grad: 0.0795 (0.0898) loss: 0.8187 (0.8311) time: 0.1274 data: 0.0467 max mem: 9390 +Train: [48] [ 400/6250] eta: 0:15:15 lr: 0.000072 grad: 0.0853 (0.0888) loss: 0.8302 (0.8301) time: 0.1461 data: 0.0560 max mem: 9390 +Train: [48] [ 500/6250] eta: 0:14:34 lr: 0.000072 grad: 0.0808 (0.0885) loss: 0.8269 (0.8286) time: 0.1578 data: 0.0716 max mem: 9390 +Train: [48] [ 600/6250] eta: 0:14:27 lr: 0.000072 grad: 0.0805 (0.0877) loss: 0.8276 (0.8282) time: 0.1456 data: 0.0563 max mem: 9390 +Train: [48] [ 700/6250] eta: 0:14:05 lr: 0.000072 grad: 0.0797 (0.0877) loss: 0.8260 (0.8276) time: 0.1267 data: 0.0471 max mem: 9390 +Train: [48] [ 800/6250] eta: 0:13:41 lr: 0.000072 grad: 0.0787 (0.0875) loss: 0.8306 (0.8274) time: 0.1333 data: 0.0417 max mem: 9390 +Train: [48] [ 900/6250] eta: 0:13:18 lr: 0.000071 grad: 0.0830 (0.0872) loss: 0.8195 (0.8274) time: 0.1455 data: 0.0514 max mem: 9390 +Train: [48] [1000/6250] eta: 0:12:49 lr: 0.000071 grad: 0.0823 (0.0867) loss: 0.8316 (0.8274) time: 0.1257 data: 0.0432 max mem: 9390 +Train: [48] [1100/6250] eta: 0:12:21 lr: 0.000071 grad: 0.0827 (0.0865) loss: 0.8218 (0.8273) time: 0.1233 data: 0.0385 max mem: 9390 +Train: [48] [1200/6250] eta: 0:11:58 lr: 0.000071 grad: 0.0801 (0.0863) loss: 0.8244 (0.8272) time: 0.1104 data: 0.0255 max mem: 9390 +Train: [48] [1300/6250] eta: 0:11:34 lr: 0.000071 grad: 0.0909 (0.0863) loss: 0.8230 (0.8270) time: 0.1198 data: 0.0310 max mem: 9390 +Train: [48] [1400/6250] eta: 0:11:16 lr: 0.000071 grad: 0.0879 (0.0863) loss: 0.8232 (0.8269) time: 0.1422 data: 0.0606 max mem: 9390 +Train: [48] [1500/6250] eta: 0:10:58 lr: 0.000071 grad: 0.0806 (0.0864) loss: 0.8270 (0.8268) time: 0.1458 data: 0.0704 max mem: 9390 +Train: [48] [1600/6250] eta: 0:10:44 lr: 0.000071 grad: 0.0791 (0.0865) loss: 0.8263 (0.8267) time: 0.1317 data: 0.0474 max mem: 9390 +Train: [48] [1700/6250] eta: 0:10:29 lr: 0.000071 grad: 0.0859 (0.0865) loss: 0.8261 (0.8265) time: 0.1421 data: 0.0598 max mem: 9390 +Train: [48] [1800/6250] eta: 0:10:17 lr: 0.000071 grad: 0.0868 (0.0866) loss: 0.8238 (0.8265) time: 0.1418 data: 0.0488 max mem: 9390 +Train: [48] [1900/6250] eta: 0:10:02 lr: 0.000071 grad: 0.0798 (0.0870) loss: 0.8307 (0.8264) time: 0.1187 data: 0.0386 max mem: 9390 +Train: [48] [2000/6250] eta: 0:09:48 lr: 0.000071 grad: 0.0864 (0.0872) loss: 0.8242 (0.8262) time: 0.1232 data: 0.0447 max mem: 9390 +Train: [48] [2100/6250] eta: 0:09:33 lr: 0.000071 grad: 0.0820 (0.0871) loss: 0.8257 (0.8261) time: 0.1172 data: 0.0318 max mem: 9390 +Train: [48] [2200/6250] eta: 0:09:21 lr: 0.000071 grad: 0.0866 (0.0871) loss: 0.8306 (0.8261) time: 0.1352 data: 0.0576 max mem: 9390 +Train: [48] [2300/6250] eta: 0:09:06 lr: 0.000071 grad: 0.0804 (0.0871) loss: 0.8258 (0.8261) time: 0.1459 data: 0.0652 max mem: 9390 +Train: [48] [2400/6250] eta: 0:08:52 lr: 0.000071 grad: 0.0848 (0.0871) loss: 0.8221 (0.8261) time: 0.1256 data: 0.0406 max mem: 9390 +Train: [48] [2500/6250] eta: 0:08:38 lr: 0.000071 grad: 0.0780 (0.0871) loss: 0.8267 (0.8261) time: 0.1492 data: 0.0726 max mem: 9390 +Train: [48] [2600/6250] eta: 0:08:25 lr: 0.000071 grad: 0.0828 (0.0871) loss: 0.8194 (0.8260) time: 0.1207 data: 0.0422 max mem: 9390 +Train: [48] [2700/6250] eta: 0:08:12 lr: 0.000071 grad: 0.0830 (0.0870) loss: 0.8290 (0.8260) time: 0.1462 data: 0.0663 max mem: 9390 +Train: [48] [2800/6250] eta: 0:07:58 lr: 0.000071 grad: 0.0851 (0.0871) loss: 0.8240 (0.8260) time: 0.1381 data: 0.0547 max mem: 9390 +Train: [48] [2900/6250] eta: 0:07:45 lr: 0.000071 grad: 0.0855 (0.0871) loss: 0.8217 (0.8260) time: 0.1848 data: 0.0973 max mem: 9390 +Train: [48] [3000/6250] eta: 0:07:30 lr: 0.000071 grad: 0.0839 (0.0872) loss: 0.8273 (0.8259) time: 0.1342 data: 0.0586 max mem: 9390 +Train: [48] [3100/6250] eta: 0:07:16 lr: 0.000071 grad: 0.0826 (0.0873) loss: 0.8215 (0.8257) time: 0.1367 data: 0.0554 max mem: 9390 +Train: [48] [3200/6250] eta: 0:07:04 lr: 0.000071 grad: 0.0855 (0.0873) loss: 0.8239 (0.8256) time: 0.1558 data: 0.0643 max mem: 9390 +Train: [48] [3300/6250] eta: 0:06:50 lr: 0.000071 grad: 0.0869 (0.0873) loss: 0.8220 (0.8255) time: 0.1624 data: 0.0810 max mem: 9390 +Train: [48] [3400/6250] eta: 0:06:36 lr: 0.000071 grad: 0.0873 (0.0873) loss: 0.8227 (0.8253) time: 0.1444 data: 0.0634 max mem: 9390 +Train: [48] [3500/6250] eta: 0:06:22 lr: 0.000071 grad: 0.0871 (0.0874) loss: 0.8190 (0.8252) time: 0.1439 data: 0.0739 max mem: 9390 +Train: [48] [3600/6250] eta: 0:06:09 lr: 0.000071 grad: 0.0842 (0.0874) loss: 0.8173 (0.8250) time: 0.1663 data: 0.0873 max mem: 9390 +Train: [48] [3700/6250] eta: 0:05:55 lr: 0.000071 grad: 0.0833 (0.0874) loss: 0.8270 (0.8249) time: 0.1200 data: 0.0396 max mem: 9390 +Train: [48] [3800/6250] eta: 0:05:41 lr: 0.000071 grad: 0.0876 (0.0874) loss: 0.8192 (0.8248) time: 0.1308 data: 0.0524 max mem: 9390 +Train: [48] [3900/6250] eta: 0:05:27 lr: 0.000070 grad: 0.0803 (0.0874) loss: 0.8278 (0.8247) time: 0.1435 data: 0.0562 max mem: 9390 +Train: [48] [4000/6250] eta: 0:05:12 lr: 0.000070 grad: 0.0857 (0.0874) loss: 0.8165 (0.8246) time: 0.1261 data: 0.0367 max mem: 9390 +Train: [48] [4100/6250] eta: 0:04:59 lr: 0.000070 grad: 0.0858 (0.0875) loss: 0.8272 (0.8245) time: 0.1313 data: 0.0499 max mem: 9390 +Train: [48] [4200/6250] eta: 0:04:44 lr: 0.000070 grad: 0.0871 (0.0875) loss: 0.8217 (0.8244) time: 0.1292 data: 0.0531 max mem: 9390 +Train: [48] [4300/6250] eta: 0:04:31 lr: 0.000070 grad: 0.0871 (0.0876) loss: 0.8181 (0.8242) time: 0.1312 data: 0.0435 max mem: 9390 +Train: [48] [4400/6250] eta: 0:04:16 lr: 0.000070 grad: 0.0865 (0.0876) loss: 0.8302 (0.8242) time: 0.1193 data: 0.0372 max mem: 9390 +Train: [48] [4500/6250] eta: 0:04:02 lr: 0.000070 grad: 0.0867 (0.0876) loss: 0.8254 (0.8241) time: 0.1381 data: 0.0605 max mem: 9390 +Train: [48] [4600/6250] eta: 0:03:48 lr: 0.000070 grad: 0.0902 (0.0877) loss: 0.8223 (0.8240) time: 0.1270 data: 0.0470 max mem: 9390 +Train: [48] [4700/6250] eta: 0:03:34 lr: 0.000070 grad: 0.0849 (0.0877) loss: 0.8206 (0.8238) time: 0.1547 data: 0.0770 max mem: 9390 +Train: [48] [4800/6250] eta: 0:03:20 lr: 0.000070 grad: 0.0927 (0.0877) loss: 0.8182 (0.8238) time: 0.1344 data: 0.0542 max mem: 9390 +Train: [48] [4900/6250] eta: 0:03:06 lr: 0.000070 grad: 0.0886 (0.0878) loss: 0.8218 (0.8237) time: 0.1198 data: 0.0420 max mem: 9390 +Train: [48] [5000/6250] eta: 0:02:52 lr: 0.000070 grad: 0.0905 (0.0878) loss: 0.8225 (0.8236) time: 0.1159 data: 0.0358 max mem: 9390 +Train: [48] [5100/6250] eta: 0:02:38 lr: 0.000070 grad: 0.0909 (0.0879) loss: 0.8202 (0.8236) time: 0.1178 data: 0.0362 max mem: 9390 +Train: [48] [5200/6250] eta: 0:02:24 lr: 0.000070 grad: 0.0867 (0.0880) loss: 0.8220 (0.8235) time: 0.1267 data: 0.0440 max mem: 9390 +Train: [48] [5300/6250] eta: 0:02:11 lr: 0.000070 grad: 0.0868 (0.0881) loss: 0.8293 (0.8235) time: 0.0988 data: 0.0084 max mem: 9390 +Train: [48] [5400/6250] eta: 0:01:57 lr: 0.000070 grad: 0.0921 (0.0881) loss: 0.8202 (0.8234) time: 0.1272 data: 0.0445 max mem: 9390 +Train: [48] [5500/6250] eta: 0:01:43 lr: 0.000070 grad: 0.0794 (0.0882) loss: 0.8189 (0.8233) time: 0.1439 data: 0.0607 max mem: 9390 +Train: [48] [5600/6250] eta: 0:01:30 lr: 0.000070 grad: 0.0891 (0.0882) loss: 0.8188 (0.8232) time: 0.1649 data: 0.0924 max mem: 9390 +Train: [48] [5700/6250] eta: 0:01:16 lr: 0.000070 grad: 0.0844 (0.0883) loss: 0.8180 (0.8231) time: 0.1575 data: 0.0798 max mem: 9390 +Train: [48] [5800/6250] eta: 0:01:02 lr: 0.000070 grad: 0.0966 (0.0884) loss: 0.8079 (0.8230) time: 0.1101 data: 0.0313 max mem: 9390 +Train: [48] [5900/6250] eta: 0:00:48 lr: 0.000070 grad: 0.0841 (0.0884) loss: 0.8152 (0.8230) time: 0.1826 data: 0.1039 max mem: 9390 +Train: [48] [6000/6250] eta: 0:00:34 lr: 0.000070 grad: 0.0918 (0.0885) loss: 0.8128 (0.8228) time: 0.1395 data: 0.0574 max mem: 9390 +Train: [48] [6100/6250] eta: 0:00:20 lr: 0.000070 grad: 0.0901 (0.0886) loss: 0.8156 (0.8227) time: 0.1492 data: 0.0608 max mem: 9390 +Train: [48] [6200/6250] eta: 0:00:06 lr: 0.000070 grad: 0.0951 (0.0887) loss: 0.8140 (0.8226) time: 0.1207 data: 0.0385 max mem: 9390 +Train: [48] [6249/6250] eta: 0:00:00 lr: 0.000070 grad: 0.0904 (0.0887) loss: 0.8199 (0.8226) time: 0.1281 data: 0.0473 max mem: 9390 +Train: [48] Total time: 0:14:31 (0.1395 s / it) +Averaged stats: lr: 0.000070 grad: 0.0904 (0.0887) loss: 0.8199 (0.8226) +Eval (hcp-train-subset): [48] [ 0/62] eta: 0:04:17 loss: 0.8502 (0.8502) time: 4.1552 data: 4.1109 max mem: 9390 +Eval (hcp-train-subset): [48] [61/62] eta: 0:00:00 loss: 0.8344 (0.8367) time: 0.1371 data: 0.1118 max mem: 9390 +Eval (hcp-train-subset): [48] Total time: 0:00:12 (0.1998 s / it) +Averaged stats (hcp-train-subset): loss: 0.8344 (0.8367) +Eval (hcp-val): [48] [ 0/62] eta: 0:04:39 loss: 0.8357 (0.8357) time: 4.5089 data: 4.4790 max mem: 9390 +Eval (hcp-val): [48] [61/62] eta: 0:00:00 loss: 0.8342 (0.8361) time: 0.1396 data: 0.1128 max mem: 9390 +Eval (hcp-val): [48] Total time: 0:00:13 (0.2133 s / it) +Averaged stats (hcp-val): loss: 0.8342 (0.8361) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +Train: [49] [ 0/6250] eta: 9:36:23 lr: 0.000070 grad: 0.1849 (0.1849) loss: 0.8383 (0.8383) time: 5.5333 data: 5.4027 max mem: 9390 +Train: [49] [ 100/6250] eta: 0:19:46 lr: 0.000070 grad: 0.0915 (0.0960) loss: 0.8277 (0.8347) time: 0.1476 data: 0.0591 max mem: 9390 +Train: [49] [ 200/6250] eta: 0:17:09 lr: 0.000070 grad: 0.0925 (0.0964) loss: 0.8272 (0.8297) time: 0.1501 data: 0.0606 max mem: 9390 +Train: [49] [ 300/6250] eta: 0:15:56 lr: 0.000070 grad: 0.0858 (0.0964) loss: 0.8307 (0.8269) time: 0.1403 data: 0.0485 max mem: 9390 +Train: [49] [ 400/6250] eta: 0:15:02 lr: 0.000070 grad: 0.0814 (0.0947) loss: 0.8262 (0.8248) time: 0.1225 data: 0.0351 max mem: 9390 +Train: [49] [ 500/6250] eta: 0:14:25 lr: 0.000070 grad: 0.0844 (0.0932) loss: 0.8218 (0.8240) time: 0.1280 data: 0.0439 max mem: 9390 +Train: [49] [ 600/6250] eta: 0:13:50 lr: 0.000070 grad: 0.0788 (0.0922) loss: 0.8225 (0.8230) time: 0.1302 data: 0.0461 max mem: 9390 +Train: [49] [ 700/6250] eta: 0:13:54 lr: 0.000069 grad: 0.0840 (0.0913) loss: 0.8221 (0.8222) time: 0.1461 data: 0.0599 max mem: 9390 +Train: [49] [ 800/6250] eta: 0:13:41 lr: 0.000069 grad: 0.0852 (0.0912) loss: 0.8256 (0.8219) time: 0.1447 data: 0.0666 max mem: 9390 +Train: [49] [ 900/6250] eta: 0:13:24 lr: 0.000069 grad: 0.0794 (0.0906) loss: 0.8250 (0.8217) time: 0.1895 data: 0.0998 max mem: 9390 +Train: [49] [1000/6250] eta: 0:13:00 lr: 0.000069 grad: 0.0878 (0.0900) loss: 0.8229 (0.8217) time: 0.1252 data: 0.0415 max mem: 9390 +Train: [49] [1100/6250] eta: 0:12:37 lr: 0.000069 grad: 0.0837 (0.0896) loss: 0.8223 (0.8216) time: 0.1421 data: 0.0605 max mem: 9390 +Train: [49] [1200/6250] eta: 0:12:13 lr: 0.000069 grad: 0.0806 (0.0894) loss: 0.8247 (0.8214) time: 0.1336 data: 0.0399 max mem: 9390 +Train: [49] [1300/6250] eta: 0:11:50 lr: 0.000069 grad: 0.0852 (0.0893) loss: 0.8198 (0.8213) time: 0.1238 data: 0.0394 max mem: 9390 +Train: [49] [1400/6250] eta: 0:11:30 lr: 0.000069 grad: 0.0836 (0.0893) loss: 0.8188 (0.8212) time: 0.1161 data: 0.0310 max mem: 9390 +Train: [49] [1500/6250] eta: 0:11:08 lr: 0.000069 grad: 0.0816 (0.0893) loss: 0.8259 (0.8212) time: 0.1258 data: 0.0426 max mem: 9390 +Train: [49] [1600/6250] eta: 0:10:49 lr: 0.000069 grad: 0.0852 (0.0892) loss: 0.8275 (0.8212) time: 0.1346 data: 0.0570 max mem: 9390 +Train: [49] [1700/6250] eta: 0:10:34 lr: 0.000069 grad: 0.0894 (0.0892) loss: 0.8200 (0.8211) time: 0.1309 data: 0.0525 max mem: 9390 +Train: [49] [1800/6250] eta: 0:10:20 lr: 0.000069 grad: 0.0930 (0.0893) loss: 0.8205 (0.8210) time: 0.1366 data: 0.0547 max mem: 9390 +Train: [49] [1900/6250] eta: 0:10:04 lr: 0.000069 grad: 0.0863 (0.0893) loss: 0.8228 (0.8209) time: 0.1600 data: 0.0789 max mem: 9390 +Train: [49] [2000/6250] eta: 0:09:49 lr: 0.000069 grad: 0.0837 (0.0894) loss: 0.8169 (0.8207) time: 0.1318 data: 0.0478 max mem: 9390 +Train: [49] [2100/6250] eta: 0:09:38 lr: 0.000069 grad: 0.0882 (0.0895) loss: 0.8210 (0.8205) time: 0.1346 data: 0.0532 max mem: 9390 +Train: [49] [2200/6250] eta: 0:09:22 lr: 0.000069 grad: 0.0837 (0.0896) loss: 0.8206 (0.8204) time: 0.1275 data: 0.0445 max mem: 9390 +Train: [49] [2300/6250] eta: 0:09:07 lr: 0.000069 grad: 0.0834 (0.0896) loss: 0.8227 (0.8203) time: 0.1379 data: 0.0552 max mem: 9390 +Train: [49] [2400/6250] eta: 0:08:52 lr: 0.000069 grad: 0.0819 (0.0896) loss: 0.8218 (0.8201) time: 0.1023 data: 0.0233 max mem: 9390 +Train: [49] [2500/6250] eta: 0:08:40 lr: 0.000069 grad: 0.0886 (0.0897) loss: 0.8170 (0.8200) time: 0.0896 data: 0.0002 max mem: 9390 +Train: [49] [2600/6250] eta: 0:08:26 lr: 0.000069 grad: 0.0861 (0.0897) loss: 0.8178 (0.8199) time: 0.1223 data: 0.0440 max mem: 9390 +Train: [49] [2700/6250] eta: 0:08:12 lr: 0.000069 grad: 0.0884 (0.0898) loss: 0.8157 (0.8198) time: 0.1354 data: 0.0590 max mem: 9390 +Train: [49] [2800/6250] eta: 0:07:58 lr: 0.000069 grad: 0.0798 (0.0900) loss: 0.8205 (0.8198) time: 0.1330 data: 0.0493 max mem: 9390 +Train: [49] [2900/6250] eta: 0:07:44 lr: 0.000069 grad: 0.0875 (0.0900) loss: 0.8218 (0.8197) time: 0.1307 data: 0.0472 max mem: 9390 +Train: [49] [3000/6250] eta: 0:07:30 lr: 0.000069 grad: 0.0865 (0.0900) loss: 0.8165 (0.8197) time: 0.1179 data: 0.0425 max mem: 9390 +Train: [49] [3100/6250] eta: 0:07:17 lr: 0.000069 grad: 0.0847 (0.0900) loss: 0.8175 (0.8197) time: 0.1651 data: 0.0890 max mem: 9390 +Train: [49] [3200/6250] eta: 0:07:03 lr: 0.000069 grad: 0.0871 (0.0900) loss: 0.8157 (0.8197) time: 0.1411 data: 0.0631 max mem: 9390 +Train: [49] [3300/6250] eta: 0:06:51 lr: 0.000069 grad: 0.0846 (0.0900) loss: 0.8164 (0.8197) time: 0.1650 data: 0.0920 max mem: 9390 +Train: [49] [3400/6250] eta: 0:06:38 lr: 0.000069 grad: 0.0898 (0.0900) loss: 0.8200 (0.8197) time: 0.1426 data: 0.0648 max mem: 9390 +Train: [49] [3500/6250] eta: 0:06:24 lr: 0.000069 grad: 0.0875 (0.0899) loss: 0.8160 (0.8197) time: 0.1398 data: 0.0549 max mem: 9390 +Train: [49] [3600/6250] eta: 0:06:10 lr: 0.000069 grad: 0.0858 (0.0899) loss: 0.8154 (0.8197) time: 0.1325 data: 0.0547 max mem: 9390 +Train: [49] [3700/6250] eta: 0:05:56 lr: 0.000069 grad: 0.0852 (0.0898) loss: 0.8203 (0.8198) time: 0.1482 data: 0.0655 max mem: 9390 +Train: [49] [3800/6250] eta: 0:05:41 lr: 0.000068 grad: 0.0922 (0.0898) loss: 0.8218 (0.8198) time: 0.1476 data: 0.0675 max mem: 9390 +Train: [49] [3900/6250] eta: 0:05:26 lr: 0.000068 grad: 0.0877 (0.0898) loss: 0.8201 (0.8198) time: 0.1187 data: 0.0382 max mem: 9390 +Train: [49] [4000/6250] eta: 0:05:13 lr: 0.000068 grad: 0.0860 (0.0898) loss: 0.8190 (0.8198) time: 0.1430 data: 0.0618 max mem: 9390 +Train: [49] [4100/6250] eta: 0:04:58 lr: 0.000068 grad: 0.0889 (0.0899) loss: 0.8171 (0.8198) time: 0.1285 data: 0.0448 max mem: 9390 +Train: [49] [4200/6250] eta: 0:04:45 lr: 0.000068 grad: 0.0877 (0.0899) loss: 0.8140 (0.8198) time: 0.1247 data: 0.0447 max mem: 9390 +Train: [49] [4300/6250] eta: 0:04:31 lr: 0.000068 grad: 0.0921 (0.0900) loss: 0.8171 (0.8198) time: 0.1315 data: 0.0518 max mem: 9390 +Train: [49] [4400/6250] eta: 0:04:17 lr: 0.000068 grad: 0.0887 (0.0900) loss: 0.8194 (0.8197) time: 0.1565 data: 0.0721 max mem: 9390 +Train: [49] [4500/6250] eta: 0:04:03 lr: 0.000068 grad: 0.0882 (0.0900) loss: 0.8192 (0.8197) time: 0.1339 data: 0.0553 max mem: 9390 +Train: [49] [4600/6250] eta: 0:03:50 lr: 0.000068 grad: 0.0874 (0.0900) loss: 0.8260 (0.8197) time: 0.1284 data: 0.0353 max mem: 9390 +Train: [49] [4700/6250] eta: 0:03:35 lr: 0.000068 grad: 0.0917 (0.0900) loss: 0.8217 (0.8197) time: 0.1263 data: 0.0502 max mem: 9390 +Train: [49] [4800/6250] eta: 0:03:21 lr: 0.000068 grad: 0.0839 (0.0901) loss: 0.8224 (0.8197) time: 0.1039 data: 0.0210 max mem: 9390 +Train: [49] [4900/6250] eta: 0:03:07 lr: 0.000068 grad: 0.0854 (0.0901) loss: 0.8240 (0.8198) time: 0.1272 data: 0.0465 max mem: 9390 +Train: [49] [5000/6250] eta: 0:02:53 lr: 0.000068 grad: 0.0924 (0.0901) loss: 0.8146 (0.8198) time: 0.1225 data: 0.0432 max mem: 9390 +Train: [49] [5100/6250] eta: 0:02:39 lr: 0.000068 grad: 0.0874 (0.0901) loss: 0.8217 (0.8198) time: 0.1186 data: 0.0329 max mem: 9390 +Train: [49] [5200/6250] eta: 0:02:25 lr: 0.000068 grad: 0.0889 (0.0901) loss: 0.8198 (0.8198) time: 0.1336 data: 0.0540 max mem: 9390 +Train: [49] [5300/6250] eta: 0:02:11 lr: 0.000068 grad: 0.0932 (0.0901) loss: 0.8186 (0.8198) time: 0.1471 data: 0.0690 max mem: 9390 +Train: [49] [5400/6250] eta: 0:01:58 lr: 0.000068 grad: 0.0913 (0.0901) loss: 0.8246 (0.8198) time: 0.1240 data: 0.0451 max mem: 9390 +Train: [49] [5500/6250] eta: 0:01:44 lr: 0.000068 grad: 0.0892 (0.0901) loss: 0.8193 (0.8198) time: 0.1758 data: 0.0919 max mem: 9390 +Train: [49] [5600/6250] eta: 0:01:30 lr: 0.000068 grad: 0.0875 (0.0902) loss: 0.8259 (0.8199) time: 0.1784 data: 0.1054 max mem: 9390 +Train: [49] [5700/6250] eta: 0:01:16 lr: 0.000068 grad: 0.0871 (0.0902) loss: 0.8184 (0.8199) time: 0.1473 data: 0.0692 max mem: 9390 +Train: [49] [5800/6250] eta: 0:01:02 lr: 0.000068 grad: 0.0897 (0.0902) loss: 0.8212 (0.8199) time: 0.1418 data: 0.0640 max mem: 9390 +Train: [49] [5900/6250] eta: 0:00:48 lr: 0.000068 grad: 0.0862 (0.0902) loss: 0.8220 (0.8199) time: 0.1611 data: 0.0794 max mem: 9390 +Train: [49] [6000/6250] eta: 0:00:34 lr: 0.000068 grad: 0.0897 (0.0902) loss: 0.8238 (0.8200) time: 0.1089 data: 0.0245 max mem: 9390 +Train: [49] [6100/6250] eta: 0:00:20 lr: 0.000068 grad: 0.0876 (0.0903) loss: 0.8208 (0.8200) time: 0.1302 data: 0.0446 max mem: 9390 +Train: [49] [6200/6250] eta: 0:00:06 lr: 0.000068 grad: 0.0932 (0.0904) loss: 0.8170 (0.8200) time: 0.1349 data: 0.0578 max mem: 9390 +Train: [49] [6249/6250] eta: 0:00:00 lr: 0.000068 grad: 0.0881 (0.0904) loss: 0.8161 (0.8200) time: 0.1453 data: 0.0544 max mem: 9390 +Train: [49] Total time: 0:14:36 (0.1402 s / it) +Averaged stats: lr: 0.000068 grad: 0.0881 (0.0904) loss: 0.8161 (0.8200) +Eval (hcp-train-subset): [49] [ 0/62] eta: 0:04:12 loss: 0.8491 (0.8491) time: 4.0731 data: 4.0174 max mem: 9390 +Eval (hcp-train-subset): [49] [61/62] eta: 0:00:00 loss: 0.8347 (0.8377) time: 0.1332 data: 0.1083 max mem: 9390 +Eval (hcp-train-subset): [49] Total time: 0:00:13 (0.2131 s / it) +Averaged stats (hcp-train-subset): loss: 0.8347 (0.8377) +Making plots (hcp-train-subset): example=28 +Eval (hcp-val): [49] [ 0/62] eta: 0:04:08 loss: 0.8334 (0.8334) time: 4.0080 data: 3.9213 max mem: 9390 +Eval (hcp-val): [49] [61/62] eta: 0:00:00 loss: 0.8356 (0.8362) time: 0.1292 data: 0.1041 max mem: 9390 +Eval (hcp-val): [49] Total time: 0:00:13 (0.2167 s / it) +Averaged stats (hcp-val): loss: 0.8356 (0.8362) +Making plots (hcp-val): example=11 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +Train: [50] [ 0/6250] eta: 8:17:50 lr: 0.000068 grad: 0.1327 (0.1327) loss: 0.8537 (0.8537) time: 4.7794 data: 4.4884 max mem: 9390 +Train: [50] [ 100/6250] eta: 0:20:14 lr: 0.000068 grad: 0.0919 (0.0899) loss: 0.8344 (0.8324) time: 0.1457 data: 0.0497 max mem: 9390 +Train: [50] [ 200/6250] eta: 0:17:47 lr: 0.000068 grad: 0.0841 (0.0901) loss: 0.8332 (0.8292) time: 0.1689 data: 0.0789 max mem: 9390 +Train: [50] [ 300/6250] eta: 0:16:15 lr: 0.000068 grad: 0.0825 (0.0881) loss: 0.8309 (0.8294) time: 0.1428 data: 0.0437 max mem: 9390 +Train: [50] [ 400/6250] eta: 0:15:20 lr: 0.000068 grad: 0.0824 (0.0880) loss: 0.8226 (0.8283) time: 0.1378 data: 0.0565 max mem: 9390 +Train: [50] [ 500/6250] eta: 0:14:36 lr: 0.000067 grad: 0.0861 (0.0879) loss: 0.8289 (0.8275) time: 0.1283 data: 0.0431 max mem: 9390 +Train: [50] [ 600/6250] eta: 0:14:03 lr: 0.000067 grad: 0.0751 (0.0875) loss: 0.8270 (0.8272) time: 0.1289 data: 0.0364 max mem: 9390 +Train: [50] [ 700/6250] eta: 0:13:57 lr: 0.000067 grad: 0.0877 (0.0873) loss: 0.8235 (0.8272) time: 0.1505 data: 0.0634 max mem: 9390 +Train: [50] [ 800/6250] eta: 0:13:42 lr: 0.000067 grad: 0.0811 (0.0869) loss: 0.8260 (0.8269) time: 0.1546 data: 0.0719 max mem: 9390 +Train: [50] [ 900/6250] eta: 0:13:14 lr: 0.000067 grad: 0.0853 (0.0865) loss: 0.8244 (0.8269) time: 0.1175 data: 0.0356 max mem: 9390 +Train: [50] [1000/6250] eta: 0:12:55 lr: 0.000067 grad: 0.0844 (0.0863) loss: 0.8275 (0.8269) time: 0.1257 data: 0.0448 max mem: 9390 +Train: [50] [1100/6250] eta: 0:12:31 lr: 0.000067 grad: 0.0860 (0.0863) loss: 0.8273 (0.8267) time: 0.1106 data: 0.0330 max mem: 9390 +Train: [50] [1200/6250] eta: 0:12:07 lr: 0.000067 grad: 0.0852 (0.0864) loss: 0.8258 (0.8264) time: 0.1402 data: 0.0624 max mem: 9390 +Train: [50] [1300/6250] eta: 0:11:44 lr: 0.000067 grad: 0.0863 (0.0864) loss: 0.8218 (0.8262) time: 0.1075 data: 0.0228 max mem: 9390 +Train: [50] [1400/6250] eta: 0:11:24 lr: 0.000067 grad: 0.0809 (0.0865) loss: 0.8262 (0.8259) time: 0.1322 data: 0.0445 max mem: 9390 +Train: [50] [1500/6250] eta: 0:11:05 lr: 0.000067 grad: 0.0831 (0.0865) loss: 0.8272 (0.8257) time: 0.1326 data: 0.0412 max mem: 9390 +Train: [50] [1600/6250] eta: 0:10:45 lr: 0.000067 grad: 0.0875 (0.0866) loss: 0.8159 (0.8254) time: 0.1133 data: 0.0296 max mem: 9390 +Train: [50] [1700/6250] eta: 0:10:27 lr: 0.000067 grad: 0.0840 (0.0869) loss: 0.8243 (0.8250) time: 0.1291 data: 0.0513 max mem: 9390 +Train: [50] [1800/6250] eta: 0:10:12 lr: 0.000067 grad: 0.0886 (0.0871) loss: 0.8222 (0.8245) time: 0.1325 data: 0.0531 max mem: 9390 +Train: [50] [1900/6250] eta: 0:09:56 lr: 0.000067 grad: 0.0903 (0.0873) loss: 0.8136 (0.8241) time: 0.1347 data: 0.0595 max mem: 9390 +Train: [50] [2000/6250] eta: 0:09:41 lr: 0.000067 grad: 0.0884 (0.0875) loss: 0.8174 (0.8238) time: 0.1387 data: 0.0567 max mem: 9390 +Train: [50] [2100/6250] eta: 0:09:28 lr: 0.000067 grad: 0.0893 (0.0877) loss: 0.8177 (0.8235) time: 0.1149 data: 0.0380 max mem: 9390 +Train: [50] [2200/6250] eta: 0:09:13 lr: 0.000067 grad: 0.0881 (0.0878) loss: 0.8149 (0.8232) time: 0.1407 data: 0.0609 max mem: 9390 +Train: [50] [2300/6250] eta: 0:08:58 lr: 0.000067 grad: 0.0855 (0.0878) loss: 0.8213 (0.8229) time: 0.1360 data: 0.0569 max mem: 9390 +Train: [50] [2400/6250] eta: 0:08:43 lr: 0.000067 grad: 0.0875 (0.0879) loss: 0.8175 (0.8228) time: 0.1447 data: 0.0661 max mem: 9390 +Train: [50] [2500/6250] eta: 0:08:28 lr: 0.000067 grad: 0.0836 (0.0877) loss: 0.8195 (0.8227) time: 0.1309 data: 0.0579 max mem: 9390 +Train: [50] [2600/6250] eta: 0:08:16 lr: 0.000067 grad: 0.0775 (0.0877) loss: 0.8305 (0.8227) time: 0.1572 data: 0.0739 max mem: 9390 +Train: [50] [2700/6250] eta: 0:08:01 lr: 0.000067 grad: 0.0867 (0.0878) loss: 0.8230 (0.8226) time: 0.1381 data: 0.0597 max mem: 9390 +Train: [50] [2800/6250] eta: 0:07:48 lr: 0.000067 grad: 0.0853 (0.0878) loss: 0.8271 (0.8225) time: 0.1261 data: 0.0413 max mem: 9390 +Train: [50] [2900/6250] eta: 0:07:37 lr: 0.000067 grad: 0.0860 (0.0879) loss: 0.8214 (0.8225) time: 0.1461 data: 0.0582 max mem: 9390 +Train: [50] [3000/6250] eta: 0:07:23 lr: 0.000067 grad: 0.0903 (0.0879) loss: 0.8279 (0.8225) time: 0.1242 data: 0.0381 max mem: 9390 +Train: [50] [3100/6250] eta: 0:07:12 lr: 0.000067 grad: 0.0894 (0.0880) loss: 0.8216 (0.8225) time: 0.1245 data: 0.0442 max mem: 9390 +Train: [50] [3200/6250] eta: 0:06:58 lr: 0.000067 grad: 0.0906 (0.0880) loss: 0.8237 (0.8225) time: 0.1536 data: 0.0729 max mem: 9390 +Train: [50] [3300/6250] eta: 0:06:46 lr: 0.000067 grad: 0.0951 (0.0882) loss: 0.8193 (0.8225) time: 0.1298 data: 0.0517 max mem: 9390 +Train: [50] [3400/6250] eta: 0:06:32 lr: 0.000067 grad: 0.0933 (0.0883) loss: 0.8167 (0.8224) time: 0.1569 data: 0.0819 max mem: 9390 +Train: [50] [3500/6250] eta: 0:06:18 lr: 0.000067 grad: 0.0825 (0.0884) loss: 0.8230 (0.8224) time: 0.1258 data: 0.0479 max mem: 9390 +Train: [50] [3600/6250] eta: 0:06:04 lr: 0.000066 grad: 0.0940 (0.0885) loss: 0.8150 (0.8224) time: 0.1375 data: 0.0566 max mem: 9390 +Train: [50] [3700/6250] eta: 0:05:50 lr: 0.000066 grad: 0.0850 (0.0886) loss: 0.8217 (0.8223) time: 0.1392 data: 0.0564 max mem: 9390 +Train: [50] [3800/6250] eta: 0:05:36 lr: 0.000066 grad: 0.0873 (0.0887) loss: 0.8221 (0.8223) time: 0.1286 data: 0.0539 max mem: 9390 +Train: [50] [3900/6250] eta: 0:05:22 lr: 0.000066 grad: 0.0852 (0.0888) loss: 0.8178 (0.8222) time: 0.1695 data: 0.0798 max mem: 9390 +Train: [50] [4000/6250] eta: 0:05:09 lr: 0.000066 grad: 0.0912 (0.0888) loss: 0.8235 (0.8223) time: 0.1690 data: 0.0296 max mem: 9390 +Train: [50] [4100/6250] eta: 0:04:55 lr: 0.000066 grad: 0.0921 (0.0889) loss: 0.8118 (0.8222) time: 0.1194 data: 0.0285 max mem: 9390 +Train: [50] [4200/6250] eta: 0:04:41 lr: 0.000066 grad: 0.0926 (0.0890) loss: 0.8135 (0.8221) time: 0.1380 data: 0.0583 max mem: 9390 +Train: [50] [4300/6250] eta: 0:04:28 lr: 0.000066 grad: 0.0867 (0.0890) loss: 0.8231 (0.8220) time: 0.1361 data: 0.0605 max mem: 9390 +Train: [50] [4400/6250] eta: 0:04:14 lr: 0.000066 grad: 0.0924 (0.0891) loss: 0.8185 (0.8220) time: 0.1436 data: 0.0578 max mem: 9390 +Train: [50] [4500/6250] eta: 0:04:01 lr: 0.000066 grad: 0.0919 (0.0893) loss: 0.8149 (0.8220) time: 0.1493 data: 0.0659 max mem: 9390 +Train: [50] [4600/6250] eta: 0:03:47 lr: 0.000066 grad: 0.0900 (0.0894) loss: 0.8191 (0.8219) time: 0.1476 data: 0.0664 max mem: 9390 +Train: [50] [4700/6250] eta: 0:03:33 lr: 0.000066 grad: 0.0849 (0.0894) loss: 0.8222 (0.8219) time: 0.1552 data: 0.0661 max mem: 9390 +Train: [50] [4800/6250] eta: 0:03:19 lr: 0.000066 grad: 0.0877 (0.0894) loss: 0.8209 (0.8218) time: 0.1168 data: 0.0322 max mem: 9390 +Train: [50] [4900/6250] eta: 0:03:06 lr: 0.000066 grad: 0.0835 (0.0895) loss: 0.8217 (0.8218) time: 0.1389 data: 0.0610 max mem: 9390 +Train: [50] [5000/6250] eta: 0:02:52 lr: 0.000066 grad: 0.0902 (0.0896) loss: 0.8240 (0.8218) time: 0.1554 data: 0.0811 max mem: 9390 +Train: [50] [5100/6250] eta: 0:02:38 lr: 0.000066 grad: 0.0937 (0.0897) loss: 0.8148 (0.8217) time: 0.1374 data: 0.0582 max mem: 9390 +Train: [50] [5200/6250] eta: 0:02:24 lr: 0.000066 grad: 0.0995 (0.0898) loss: 0.8185 (0.8216) time: 0.1354 data: 0.0445 max mem: 9390 +Train: [50] [5300/6250] eta: 0:02:11 lr: 0.000066 grad: 0.0886 (0.0899) loss: 0.8169 (0.8215) time: 0.1609 data: 0.0839 max mem: 9390 +Train: [50] [5400/6250] eta: 0:01:57 lr: 0.000066 grad: 0.0875 (0.0900) loss: 0.8196 (0.8215) time: 0.1239 data: 0.0419 max mem: 9390 +Train: [50] [5500/6250] eta: 0:01:43 lr: 0.000066 grad: 0.0920 (0.0901) loss: 0.8201 (0.8214) time: 0.1550 data: 0.0699 max mem: 9390 +Train: [50] [5600/6250] eta: 0:01:30 lr: 0.000066 grad: 0.0879 (0.0901) loss: 0.8226 (0.8214) time: 0.1388 data: 0.0562 max mem: 9390 +Train: [50] [5700/6250] eta: 0:01:16 lr: 0.000066 grad: 0.0864 (0.0902) loss: 0.8183 (0.8214) time: 0.1574 data: 0.0713 max mem: 9390 +Train: [50] [5800/6250] eta: 0:01:02 lr: 0.000066 grad: 0.0899 (0.0902) loss: 0.8209 (0.8214) time: 0.1187 data: 0.0370 max mem: 9390 +Train: [50] [5900/6250] eta: 0:00:48 lr: 0.000066 grad: 0.0927 (0.0903) loss: 0.8162 (0.8214) time: 0.1370 data: 0.0581 max mem: 9390 +Train: [50] [6000/6250] eta: 0:00:34 lr: 0.000066 grad: 0.0893 (0.0904) loss: 0.8252 (0.8214) time: 0.1274 data: 0.0495 max mem: 9390 +Train: [50] [6100/6250] eta: 0:00:20 lr: 0.000066 grad: 0.0869 (0.0904) loss: 0.8221 (0.8214) time: 0.1650 data: 0.0806 max mem: 9390 +Train: [50] [6200/6250] eta: 0:00:06 lr: 0.000066 grad: 0.0826 (0.0904) loss: 0.8230 (0.8214) time: 0.1513 data: 0.0702 max mem: 9390 +Train: [50] [6249/6250] eta: 0:00:00 lr: 0.000066 grad: 0.0853 (0.0904) loss: 0.8247 (0.8214) time: 0.1360 data: 0.0477 max mem: 9390 +Train: [50] Total time: 0:14:30 (0.1393 s / it) +Averaged stats: lr: 0.000066 grad: 0.0853 (0.0904) loss: 0.8247 (0.8214) +Eval (hcp-train-subset): [50] [ 0/62] eta: 0:03:13 loss: 0.8465 (0.8465) time: 3.1245 data: 3.0293 max mem: 9390 +Eval (hcp-train-subset): [50] [61/62] eta: 0:00:00 loss: 0.8396 (0.8380) time: 0.1322 data: 0.1071 max mem: 9390 +Eval (hcp-train-subset): [50] Total time: 0:00:12 (0.2094 s / it) +Averaged stats (hcp-train-subset): loss: 0.8396 (0.8380) +Eval (hcp-val): [50] [ 0/62] eta: 0:05:30 loss: 0.8360 (0.8360) time: 5.3237 data: 5.2925 max mem: 9390 +Eval (hcp-val): [50] [61/62] eta: 0:00:00 loss: 0.8357 (0.8364) time: 0.1229 data: 0.0962 max mem: 9390 +Eval (hcp-val): [50] Total time: 0:00:12 (0.2095 s / it) +Averaged stats (hcp-val): loss: 0.8357 (0.8364) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +Train: [51] [ 0/6250] eta: 8:17:46 lr: 0.000066 grad: 0.0965 (0.0965) loss: 0.8569 (0.8569) time: 4.7786 data: 4.5596 max mem: 9390 +Train: [51] [ 100/6250] eta: 0:19:07 lr: 0.000066 grad: 0.0888 (0.1134) loss: 0.8325 (0.8353) time: 0.1638 data: 0.0684 max mem: 9390 +Train: [51] [ 200/6250] eta: 0:16:45 lr: 0.000066 grad: 0.0900 (0.1049) loss: 0.8266 (0.8299) time: 0.1412 data: 0.0567 max mem: 9390 +Train: [51] [ 300/6250] eta: 0:15:28 lr: 0.000065 grad: 0.0871 (0.1011) loss: 0.8255 (0.8282) time: 0.1342 data: 0.0560 max mem: 9390 +Train: [51] [ 400/6250] eta: 0:14:40 lr: 0.000065 grad: 0.0875 (0.0992) loss: 0.8279 (0.8274) time: 0.1187 data: 0.0350 max mem: 9390 +Train: [51] [ 500/6250] eta: 0:14:02 lr: 0.000065 grad: 0.0918 (0.0977) loss: 0.8201 (0.8267) time: 0.1045 data: 0.0107 max mem: 9390 +Train: [51] [ 600/6250] eta: 0:13:30 lr: 0.000065 grad: 0.0861 (0.0966) loss: 0.8239 (0.8260) time: 0.1286 data: 0.0409 max mem: 9390 +Train: [51] [ 700/6250] eta: 0:13:00 lr: 0.000065 grad: 0.0831 (0.0955) loss: 0.8302 (0.8259) time: 0.1223 data: 0.0386 max mem: 9390 +Train: [51] [ 800/6250] eta: 0:13:01 lr: 0.000065 grad: 0.0821 (0.0946) loss: 0.8223 (0.8256) time: 0.1634 data: 0.0719 max mem: 9390 +Train: [51] [ 900/6250] eta: 0:12:49 lr: 0.000065 grad: 0.0812 (0.0939) loss: 0.8207 (0.8253) time: 0.1406 data: 0.0592 max mem: 9390 +Train: [51] [1000/6250] eta: 0:12:32 lr: 0.000065 grad: 0.0871 (0.0935) loss: 0.8215 (0.8250) time: 0.1738 data: 0.0892 max mem: 9390 +Train: [51] [1100/6250] eta: 0:12:09 lr: 0.000065 grad: 0.0846 (0.0928) loss: 0.8213 (0.8246) time: 0.1356 data: 0.0556 max mem: 9390 +Train: [51] [1200/6250] eta: 0:11:46 lr: 0.000065 grad: 0.0845 (0.0924) loss: 0.8257 (0.8244) time: 0.1252 data: 0.0398 max mem: 9390 +Train: [51] [1300/6250] eta: 0:11:27 lr: 0.000065 grad: 0.0923 (0.0922) loss: 0.8243 (0.8240) time: 0.1209 data: 0.0433 max mem: 9390 +Train: [51] [1400/6250] eta: 0:11:08 lr: 0.000065 grad: 0.0898 (0.0920) loss: 0.8164 (0.8236) time: 0.1163 data: 0.0303 max mem: 9390 +Train: [51] [1500/6250] eta: 0:10:49 lr: 0.000065 grad: 0.0836 (0.0920) loss: 0.8192 (0.8233) time: 0.1314 data: 0.0501 max mem: 9390 +Train: [51] [1600/6250] eta: 0:10:30 lr: 0.000065 grad: 0.0833 (0.0919) loss: 0.8228 (0.8230) time: 0.1203 data: 0.0376 max mem: 9390 +Train: [51] [1700/6250] eta: 0:10:12 lr: 0.000065 grad: 0.0906 (0.0919) loss: 0.8153 (0.8228) time: 0.1209 data: 0.0396 max mem: 9390 +Train: [51] [1800/6250] eta: 0:09:58 lr: 0.000065 grad: 0.0855 (0.0919) loss: 0.8220 (0.8226) time: 0.1499 data: 0.0755 max mem: 9390 +Train: [51] [1900/6250] eta: 0:09:45 lr: 0.000065 grad: 0.0841 (0.0917) loss: 0.8180 (0.8225) time: 0.1143 data: 0.0365 max mem: 9390 +Train: [51] [2000/6250] eta: 0:09:30 lr: 0.000065 grad: 0.0823 (0.0914) loss: 0.8212 (0.8226) time: 0.1265 data: 0.0469 max mem: 9390 +Train: [51] [2100/6250] eta: 0:09:17 lr: 0.000065 grad: 0.0802 (0.0912) loss: 0.8259 (0.8226) time: 0.1405 data: 0.0606 max mem: 9390 +Train: [51] [2200/6250] eta: 0:09:06 lr: 0.000065 grad: 0.0832 (0.0910) loss: 0.8222 (0.8227) time: 0.2211 data: 0.1316 max mem: 9390 +Train: [51] [2300/6250] eta: 0:08:52 lr: 0.000065 grad: 0.0844 (0.0908) loss: 0.8183 (0.8228) time: 0.1458 data: 0.0684 max mem: 9390 +Train: [51] [2400/6250] eta: 0:08:40 lr: 0.000065 grad: 0.0849 (0.0905) loss: 0.8261 (0.8230) time: 0.1567 data: 0.0752 max mem: 9390 +Train: [51] [2500/6250] eta: 0:08:27 lr: 0.000065 grad: 0.0851 (0.0904) loss: 0.8262 (0.8231) time: 0.1556 data: 0.0672 max mem: 9390 +Train: [51] [2600/6250] eta: 0:08:13 lr: 0.000065 grad: 0.0891 (0.0903) loss: 0.8238 (0.8232) time: 0.1139 data: 0.0268 max mem: 9390 +Train: [51] [2700/6250] eta: 0:08:01 lr: 0.000065 grad: 0.0863 (0.0902) loss: 0.8238 (0.8233) time: 0.1833 data: 0.0979 max mem: 9390 +Train: [51] [2800/6250] eta: 0:07:47 lr: 0.000065 grad: 0.0831 (0.0901) loss: 0.8305 (0.8234) time: 0.1530 data: 0.0773 max mem: 9390 +Train: [51] [2900/6250] eta: 0:07:33 lr: 0.000065 grad: 0.0883 (0.0902) loss: 0.8282 (0.8235) time: 0.1341 data: 0.0541 max mem: 9390 +Train: [51] [3000/6250] eta: 0:07:20 lr: 0.000065 grad: 0.0870 (0.0902) loss: 0.8253 (0.8236) time: 0.1572 data: 0.0864 max mem: 9390 +Train: [51] [3100/6250] eta: 0:07:07 lr: 0.000065 grad: 0.0909 (0.0902) loss: 0.8212 (0.8236) time: 0.1403 data: 0.0629 max mem: 9390 +Train: [51] [3200/6250] eta: 0:06:54 lr: 0.000065 grad: 0.0916 (0.0903) loss: 0.8240 (0.8236) time: 0.1401 data: 0.0644 max mem: 9390 +Train: [51] [3300/6250] eta: 0:06:41 lr: 0.000065 grad: 0.0868 (0.0904) loss: 0.8233 (0.8236) time: 0.1606 data: 0.0782 max mem: 9390 +Train: [51] [3400/6250] eta: 0:06:28 lr: 0.000064 grad: 0.0895 (0.0904) loss: 0.8222 (0.8235) time: 0.1247 data: 0.0436 max mem: 9390 +Train: [51] [3500/6250] eta: 0:06:14 lr: 0.000064 grad: 0.0850 (0.0904) loss: 0.8252 (0.8236) time: 0.1284 data: 0.0436 max mem: 9390 +Train: [51] [3600/6250] eta: 0:06:01 lr: 0.000064 grad: 0.0900 (0.0903) loss: 0.8233 (0.8235) time: 0.1320 data: 0.0580 max mem: 9390 +Train: [51] [3700/6250] eta: 0:05:46 lr: 0.000064 grad: 0.0858 (0.0903) loss: 0.8239 (0.8235) time: 0.1368 data: 0.0561 max mem: 9390 +Train: [51] [3800/6250] eta: 0:05:32 lr: 0.000064 grad: 0.0890 (0.0903) loss: 0.8271 (0.8235) time: 0.1331 data: 0.0468 max mem: 9390 +Train: [51] [3900/6250] eta: 0:05:18 lr: 0.000064 grad: 0.0901 (0.0903) loss: 0.8224 (0.8235) time: 0.1265 data: 0.0514 max mem: 9390 +Train: [51] [4000/6250] eta: 0:05:05 lr: 0.000064 grad: 0.0850 (0.0903) loss: 0.8241 (0.8235) time: 0.1259 data: 0.0432 max mem: 9390 +Train: [51] [4100/6250] eta: 0:04:51 lr: 0.000064 grad: 0.0865 (0.0903) loss: 0.8194 (0.8234) time: 0.1273 data: 0.0482 max mem: 9390 +Train: [51] [4200/6250] eta: 0:04:37 lr: 0.000064 grad: 0.0923 (0.0904) loss: 0.8244 (0.8234) time: 0.1173 data: 0.0439 max mem: 9390 +Train: [51] [4300/6250] eta: 0:04:23 lr: 0.000064 grad: 0.0950 (0.0904) loss: 0.8181 (0.8233) time: 0.1299 data: 0.0528 max mem: 9390 +Train: [51] [4400/6250] eta: 0:04:10 lr: 0.000064 grad: 0.0965 (0.0905) loss: 0.8212 (0.8232) time: 0.1297 data: 0.0469 max mem: 9390 +Train: [51] [4500/6250] eta: 0:03:56 lr: 0.000064 grad: 0.0902 (0.0905) loss: 0.8205 (0.8232) time: 0.1401 data: 0.0606 max mem: 9390 +Train: [51] [4600/6250] eta: 0:03:43 lr: 0.000064 grad: 0.0887 (0.0905) loss: 0.8210 (0.8231) time: 0.1477 data: 0.0740 max mem: 9390 +Train: [51] [4700/6250] eta: 0:03:29 lr: 0.000064 grad: 0.0964 (0.0906) loss: 0.8191 (0.8230) time: 0.1360 data: 0.0587 max mem: 9390 +Train: [51] [4800/6250] eta: 0:03:17 lr: 0.000064 grad: 0.0940 (0.0907) loss: 0.8193 (0.8229) time: 0.2825 data: 0.1362 max mem: 9390 +Train: [51] [4900/6250] eta: 0:03:03 lr: 0.000064 grad: 0.0944 (0.0907) loss: 0.8210 (0.8229) time: 0.1354 data: 0.0551 max mem: 9390 +Train: [51] [5000/6250] eta: 0:02:49 lr: 0.000064 grad: 0.0895 (0.0908) loss: 0.8208 (0.8228) time: 0.1425 data: 0.0664 max mem: 9390 +Train: [51] [5100/6250] eta: 0:02:36 lr: 0.000064 grad: 0.0866 (0.0909) loss: 0.8166 (0.8227) time: 0.1608 data: 0.0824 max mem: 9390 +Train: [51] [5200/6250] eta: 0:02:23 lr: 0.000064 grad: 0.0947 (0.0910) loss: 0.8160 (0.8226) time: 0.1305 data: 0.0543 max mem: 9390 +Train: [51] [5300/6250] eta: 0:02:09 lr: 0.000064 grad: 0.0931 (0.0911) loss: 0.8181 (0.8225) time: 0.1600 data: 0.0716 max mem: 9390 +Train: [51] [5400/6250] eta: 0:01:56 lr: 0.000064 grad: 0.0976 (0.0912) loss: 0.8146 (0.8224) time: 0.1418 data: 0.0638 max mem: 9390 +Train: [51] [5500/6250] eta: 0:01:42 lr: 0.000064 grad: 0.0918 (0.0913) loss: 0.8232 (0.8223) time: 0.1504 data: 0.0714 max mem: 9390 +Train: [51] [5600/6250] eta: 0:01:28 lr: 0.000064 grad: 0.0926 (0.0913) loss: 0.8164 (0.8222) time: 0.1540 data: 0.0808 max mem: 9390 +Train: [51] [5700/6250] eta: 0:01:15 lr: 0.000064 grad: 0.0879 (0.0914) loss: 0.8210 (0.8221) time: 0.1138 data: 0.0346 max mem: 9390 +Train: [51] [5800/6250] eta: 0:01:01 lr: 0.000064 grad: 0.0911 (0.0915) loss: 0.8134 (0.8220) time: 0.1405 data: 0.0629 max mem: 9390 +Train: [51] [5900/6250] eta: 0:00:47 lr: 0.000064 grad: 0.0906 (0.0915) loss: 0.8254 (0.8219) time: 0.1315 data: 0.0512 max mem: 9390 +Train: [51] [6000/6250] eta: 0:00:34 lr: 0.000064 grad: 0.0947 (0.0916) loss: 0.8220 (0.8219) time: 0.1271 data: 0.0448 max mem: 9390 +Train: [51] [6100/6250] eta: 0:00:20 lr: 0.000064 grad: 0.0946 (0.0916) loss: 0.8213 (0.8219) time: 0.1572 data: 0.0754 max mem: 9390 +Train: [51] [6200/6250] eta: 0:00:06 lr: 0.000064 grad: 0.0984 (0.0917) loss: 0.8174 (0.8218) time: 0.1366 data: 0.0571 max mem: 9390 +Train: [51] [6249/6250] eta: 0:00:00 lr: 0.000064 grad: 0.0859 (0.0917) loss: 0.8229 (0.8218) time: 0.1238 data: 0.0466 max mem: 9390 +Train: [51] Total time: 0:14:19 (0.1375 s / it) +Averaged stats: lr: 0.000064 grad: 0.0859 (0.0917) loss: 0.8229 (0.8218) +Eval (hcp-train-subset): [51] [ 0/62] eta: 0:04:54 loss: 0.8492 (0.8492) time: 4.7477 data: 4.7183 max mem: 9390 +Eval (hcp-train-subset): [51] [61/62] eta: 0:00:00 loss: 0.8335 (0.8360) time: 0.1111 data: 0.0865 max mem: 9390 +Eval (hcp-train-subset): [51] Total time: 0:00:11 (0.1912 s / it) +Averaged stats (hcp-train-subset): loss: 0.8335 (0.8360) +Eval (hcp-val): [51] [ 0/62] eta: 0:03:10 loss: 0.8343 (0.8343) time: 3.0677 data: 2.9937 max mem: 9390 +Eval (hcp-val): [51] [61/62] eta: 0:00:00 loss: 0.8332 (0.8358) time: 0.1129 data: 0.0861 max mem: 9390 +Eval (hcp-val): [51] Total time: 0:00:12 (0.1960 s / it) +Averaged stats (hcp-val): loss: 0.8332 (0.8358) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +Train: [52] [ 0/6250] eta: 8:54:26 lr: 0.000064 grad: 0.1484 (0.1484) loss: 0.8167 (0.8167) time: 5.1307 data: 4.9606 max mem: 9390 +Train: [52] [ 100/6250] eta: 0:20:06 lr: 0.000063 grad: 0.0839 (0.0930) loss: 0.8293 (0.8339) time: 0.1453 data: 0.0458 max mem: 9390 +Train: [52] [ 200/6250] eta: 0:16:55 lr: 0.000063 grad: 0.0836 (0.0911) loss: 0.8314 (0.8308) time: 0.1238 data: 0.0293 max mem: 9390 +Train: [52] [ 300/6250] eta: 0:15:46 lr: 0.000063 grad: 0.0886 (0.0914) loss: 0.8174 (0.8293) time: 0.1389 data: 0.0518 max mem: 9390 +Train: [52] [ 400/6250] eta: 0:14:54 lr: 0.000063 grad: 0.0846 (0.0925) loss: 0.8234 (0.8280) time: 0.1287 data: 0.0478 max mem: 9390 +Train: [52] [ 500/6250] eta: 0:14:07 lr: 0.000063 grad: 0.0827 (0.0923) loss: 0.8295 (0.8274) time: 0.1212 data: 0.0313 max mem: 9390 +Train: [52] [ 600/6250] eta: 0:13:35 lr: 0.000063 grad: 0.0851 (0.0924) loss: 0.8215 (0.8264) time: 0.1397 data: 0.0495 max mem: 9390 +Train: [52] [ 700/6250] eta: 0:13:01 lr: 0.000063 grad: 0.0833 (0.0918) loss: 0.8239 (0.8263) time: 0.1080 data: 0.0218 max mem: 9390 +Train: [52] [ 800/6250] eta: 0:12:40 lr: 0.000063 grad: 0.0907 (0.0917) loss: 0.8253 (0.8259) time: 0.1478 data: 0.0680 max mem: 9390 +Train: [52] [ 900/6250] eta: 0:12:33 lr: 0.000063 grad: 0.0818 (0.0912) loss: 0.8270 (0.8260) time: 0.1250 data: 0.0356 max mem: 9390 +Train: [52] [1000/6250] eta: 0:12:16 lr: 0.000063 grad: 0.0840 (0.0911) loss: 0.8256 (0.8259) time: 0.1246 data: 0.0497 max mem: 9390 +Train: [52] [1100/6250] eta: 0:11:59 lr: 0.000063 grad: 0.0872 (0.0909) loss: 0.8262 (0.8259) time: 0.1279 data: 0.0446 max mem: 9390 +Train: [52] [1200/6250] eta: 0:11:41 lr: 0.000063 grad: 0.0891 (0.0908) loss: 0.8222 (0.8257) time: 0.1318 data: 0.0533 max mem: 9390 +Train: [52] [1300/6250] eta: 0:11:22 lr: 0.000063 grad: 0.0889 (0.0908) loss: 0.8227 (0.8255) time: 0.1295 data: 0.0473 max mem: 9390 +Train: [52] [1400/6250] eta: 0:11:02 lr: 0.000063 grad: 0.0870 (0.0909) loss: 0.8239 (0.8253) time: 0.1117 data: 0.0255 max mem: 9390 +Train: [52] [1500/6250] eta: 0:10:44 lr: 0.000063 grad: 0.0855 (0.0908) loss: 0.8239 (0.8252) time: 0.1259 data: 0.0448 max mem: 9390 +Train: [52] [1600/6250] eta: 0:10:26 lr: 0.000063 grad: 0.0847 (0.0906) loss: 0.8222 (0.8251) time: 0.1198 data: 0.0339 max mem: 9390 +Train: [52] [1700/6250] eta: 0:10:09 lr: 0.000063 grad: 0.0829 (0.0904) loss: 0.8245 (0.8250) time: 0.1190 data: 0.0335 max mem: 9390 +Train: [52] [1800/6250] eta: 0:09:53 lr: 0.000063 grad: 0.0917 (0.0904) loss: 0.8240 (0.8249) time: 0.1432 data: 0.0643 max mem: 9390 +Train: [52] [1900/6250] eta: 0:09:38 lr: 0.000063 grad: 0.0893 (0.0903) loss: 0.8210 (0.8249) time: 0.1145 data: 0.0349 max mem: 9390 +Train: [52] [2000/6250] eta: 0:09:25 lr: 0.000063 grad: 0.0964 (0.0902) loss: 0.8229 (0.8249) time: 0.0989 data: 0.0186 max mem: 9390 +Train: [52] [2100/6250] eta: 0:09:12 lr: 0.000063 grad: 0.0842 (0.0901) loss: 0.8219 (0.8248) time: 0.1367 data: 0.0549 max mem: 9390 +Train: [52] [2200/6250] eta: 0:08:58 lr: 0.000063 grad: 0.0931 (0.0903) loss: 0.8192 (0.8248) time: 0.1411 data: 0.0599 max mem: 9390 +Train: [52] [2300/6250] eta: 0:08:49 lr: 0.000063 grad: 0.0869 (0.0904) loss: 0.8173 (0.8247) time: 0.1731 data: 0.0923 max mem: 9390 +Train: [52] [2400/6250] eta: 0:08:34 lr: 0.000063 grad: 0.0877 (0.0905) loss: 0.8237 (0.8246) time: 0.1363 data: 0.0561 max mem: 9390 +Train: [52] [2500/6250] eta: 0:08:21 lr: 0.000063 grad: 0.0908 (0.0906) loss: 0.8198 (0.8244) time: 0.1399 data: 0.0556 max mem: 9390 +Train: [52] [2600/6250] eta: 0:08:08 lr: 0.000063 grad: 0.0838 (0.0907) loss: 0.8234 (0.8243) time: 0.1078 data: 0.0244 max mem: 9390 +Train: [52] [2700/6250] eta: 0:07:56 lr: 0.000063 grad: 0.0872 (0.0907) loss: 0.8249 (0.8242) time: 0.1434 data: 0.0645 max mem: 9390 +Train: [52] [2800/6250] eta: 0:07:44 lr: 0.000063 grad: 0.0929 (0.0908) loss: 0.8236 (0.8241) time: 0.1522 data: 0.0733 max mem: 9390 +Train: [52] [2900/6250] eta: 0:07:32 lr: 0.000063 grad: 0.0870 (0.0908) loss: 0.8247 (0.8240) time: 0.1262 data: 0.0544 max mem: 9390 +Train: [52] [3000/6250] eta: 0:07:20 lr: 0.000063 grad: 0.0944 (0.0909) loss: 0.8201 (0.8239) time: 0.1329 data: 0.0516 max mem: 9390 +Train: [52] [3100/6250] eta: 0:07:06 lr: 0.000063 grad: 0.0862 (0.0910) loss: 0.8229 (0.8238) time: 0.1381 data: 0.0581 max mem: 9390 +Train: [52] [3200/6250] eta: 0:06:53 lr: 0.000062 grad: 0.0882 (0.0911) loss: 0.8227 (0.8237) time: 0.1201 data: 0.0425 max mem: 9390 +Train: [52] [3300/6250] eta: 0:06:40 lr: 0.000062 grad: 0.0955 (0.0912) loss: 0.8182 (0.8236) time: 0.1688 data: 0.0936 max mem: 9390 +Train: [52] [3400/6250] eta: 0:06:26 lr: 0.000062 grad: 0.0929 (0.0914) loss: 0.8222 (0.8235) time: 0.1199 data: 0.0436 max mem: 9390 +Train: [52] [3500/6250] eta: 0:06:12 lr: 0.000062 grad: 0.0944 (0.0915) loss: 0.8145 (0.8233) time: 0.1375 data: 0.0618 max mem: 9390 +Train: [52] [3600/6250] eta: 0:05:58 lr: 0.000062 grad: 0.0935 (0.0915) loss: 0.8230 (0.8232) time: 0.1411 data: 0.0616 max mem: 9390 +Train: [52] [3700/6250] eta: 0:05:45 lr: 0.000062 grad: 0.0905 (0.0916) loss: 0.8160 (0.8231) time: 0.1300 data: 0.0486 max mem: 9390 +Train: [52] [3800/6250] eta: 0:05:31 lr: 0.000062 grad: 0.0939 (0.0916) loss: 0.8196 (0.8230) time: 0.1349 data: 0.0518 max mem: 9390 +Train: [52] [3900/6250] eta: 0:05:17 lr: 0.000062 grad: 0.0914 (0.0916) loss: 0.8251 (0.8229) time: 0.1440 data: 0.0656 max mem: 9390 +Train: [52] [4000/6250] eta: 0:05:04 lr: 0.000062 grad: 0.0904 (0.0917) loss: 0.8217 (0.8228) time: 0.1172 data: 0.0348 max mem: 9390 +Train: [52] [4100/6250] eta: 0:04:50 lr: 0.000062 grad: 0.0919 (0.0917) loss: 0.8145 (0.8227) time: 0.1166 data: 0.0401 max mem: 9390 +Train: [52] [4200/6250] eta: 0:04:37 lr: 0.000062 grad: 0.0841 (0.0917) loss: 0.8213 (0.8226) time: 0.1538 data: 0.0742 max mem: 9390 +Train: [52] [4300/6250] eta: 0:04:24 lr: 0.000062 grad: 0.0858 (0.0917) loss: 0.8238 (0.8225) time: 0.1526 data: 0.0629 max mem: 9390 +Train: [52] [4400/6250] eta: 0:04:10 lr: 0.000062 grad: 0.0880 (0.0918) loss: 0.8200 (0.8224) time: 0.1408 data: 0.0587 max mem: 9390 +Train: [52] [4500/6250] eta: 0:03:57 lr: 0.000062 grad: 0.0954 (0.0918) loss: 0.8173 (0.8223) time: 0.1248 data: 0.0491 max mem: 9390 +Train: [52] [4600/6250] eta: 0:03:43 lr: 0.000062 grad: 0.0901 (0.0918) loss: 0.8128 (0.8223) time: 0.1322 data: 0.0511 max mem: 9390 +Train: [52] [4700/6250] eta: 0:03:30 lr: 0.000062 grad: 0.0912 (0.0918) loss: 0.8171 (0.8222) time: 0.1503 data: 0.0731 max mem: 9390 +Train: [52] [4800/6250] eta: 0:03:16 lr: 0.000062 grad: 0.0922 (0.0919) loss: 0.8165 (0.8221) time: 0.1444 data: 0.0642 max mem: 9390 +Train: [52] [4900/6250] eta: 0:03:03 lr: 0.000062 grad: 0.0916 (0.0919) loss: 0.8210 (0.8220) time: 0.1422 data: 0.0565 max mem: 9390 +Train: [52] [5000/6250] eta: 0:02:49 lr: 0.000062 grad: 0.0895 (0.0919) loss: 0.8176 (0.8220) time: 0.0903 data: 0.0066 max mem: 9390 +Train: [52] [5100/6250] eta: 0:02:36 lr: 0.000062 grad: 0.0950 (0.0920) loss: 0.8198 (0.8219) time: 0.1719 data: 0.0968 max mem: 9390 +Train: [52] [5200/6250] eta: 0:02:22 lr: 0.000062 grad: 0.0894 (0.0921) loss: 0.8205 (0.8218) time: 0.1438 data: 0.0614 max mem: 9390 +Train: [52] [5300/6250] eta: 0:02:09 lr: 0.000062 grad: 0.0941 (0.0922) loss: 0.8188 (0.8217) time: 0.1356 data: 0.0493 max mem: 9390 +Train: [52] [5400/6250] eta: 0:01:55 lr: 0.000062 grad: 0.0934 (0.0923) loss: 0.8203 (0.8216) time: 0.1260 data: 0.0408 max mem: 9390 +Train: [52] [5500/6250] eta: 0:01:42 lr: 0.000062 grad: 0.0917 (0.0924) loss: 0.8160 (0.8215) time: 0.1151 data: 0.0312 max mem: 9390 +Train: [52] [5600/6250] eta: 0:01:28 lr: 0.000062 grad: 0.0897 (0.0925) loss: 0.8247 (0.8214) time: 0.1490 data: 0.0734 max mem: 9390 +Train: [52] [5700/6250] eta: 0:01:14 lr: 0.000062 grad: 0.0933 (0.0926) loss: 0.8182 (0.8214) time: 0.1105 data: 0.0311 max mem: 9390 +Train: [52] [5800/6250] eta: 0:01:01 lr: 0.000062 grad: 0.0863 (0.0926) loss: 0.8239 (0.8213) time: 0.1213 data: 0.0426 max mem: 9390 +Train: [52] [5900/6250] eta: 0:00:47 lr: 0.000062 grad: 0.0942 (0.0927) loss: 0.8154 (0.8212) time: 0.1346 data: 0.0522 max mem: 9390 +Train: [52] [6000/6250] eta: 0:00:33 lr: 0.000062 grad: 0.0949 (0.0927) loss: 0.8229 (0.8212) time: 0.1218 data: 0.0427 max mem: 9390 +Train: [52] [6100/6250] eta: 0:00:20 lr: 0.000062 grad: 0.0931 (0.0927) loss: 0.8207 (0.8211) time: 0.1330 data: 0.0593 max mem: 9390 +Train: [52] [6200/6250] eta: 0:00:06 lr: 0.000061 grad: 0.0911 (0.0927) loss: 0.8243 (0.8211) time: 0.1312 data: 0.0549 max mem: 9390 +Train: [52] [6249/6250] eta: 0:00:00 lr: 0.000061 grad: 0.0862 (0.0927) loss: 0.8282 (0.8211) time: 0.1321 data: 0.0512 max mem: 9390 +Train: [52] Total time: 0:14:13 (0.1366 s / it) +Averaged stats: lr: 0.000061 grad: 0.0862 (0.0927) loss: 0.8282 (0.8211) +Eval (hcp-train-subset): [52] [ 0/62] eta: 0:03:53 loss: 0.8457 (0.8457) time: 3.7735 data: 3.6768 max mem: 9390 +Eval (hcp-train-subset): [52] [61/62] eta: 0:00:00 loss: 0.8354 (0.8358) time: 0.1203 data: 0.0939 max mem: 9390 +Eval (hcp-train-subset): [52] Total time: 0:00:12 (0.2091 s / it) +Averaged stats (hcp-train-subset): loss: 0.8354 (0.8358) +Eval (hcp-val): [52] [ 0/62] eta: 0:05:30 loss: 0.8336 (0.8336) time: 5.3335 data: 5.3012 max mem: 9390 +Eval (hcp-val): [52] [61/62] eta: 0:00:00 loss: 0.8335 (0.8359) time: 0.1076 data: 0.0829 max mem: 9390 +Eval (hcp-val): [52] Total time: 0:00:13 (0.2097 s / it) +Averaged stats (hcp-val): loss: 0.8335 (0.8359) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +Train: [53] [ 0/6250] eta: 9:59:19 lr: 0.000061 grad: 0.2282 (0.2282) loss: 0.8666 (0.8666) time: 5.7535 data: 5.6465 max mem: 9390 +Train: [53] [ 100/6250] eta: 0:19:55 lr: 0.000061 grad: 0.0961 (0.1073) loss: 0.8276 (0.8313) time: 0.1548 data: 0.0604 max mem: 9390 +Train: [53] [ 200/6250] eta: 0:17:02 lr: 0.000061 grad: 0.0998 (0.1039) loss: 0.8171 (0.8256) time: 0.1498 data: 0.0675 max mem: 9390 +Train: [53] [ 300/6250] eta: 0:15:44 lr: 0.000061 grad: 0.0903 (0.1027) loss: 0.8145 (0.8220) time: 0.1340 data: 0.0499 max mem: 9390 +Train: [53] [ 400/6250] eta: 0:14:54 lr: 0.000061 grad: 0.0866 (0.1006) loss: 0.8152 (0.8209) time: 0.1181 data: 0.0289 max mem: 9390 +Train: [53] [ 500/6250] eta: 0:14:11 lr: 0.000061 grad: 0.0875 (0.0985) loss: 0.8161 (0.8207) time: 0.1402 data: 0.0458 max mem: 9390 +Train: [53] [ 600/6250] eta: 0:13:34 lr: 0.000061 grad: 0.0866 (0.0970) loss: 0.8204 (0.8207) time: 0.1240 data: 0.0335 max mem: 9390 +Train: [53] [ 700/6250] eta: 0:13:04 lr: 0.000061 grad: 0.0859 (0.0962) loss: 0.8198 (0.8206) time: 0.1261 data: 0.0413 max mem: 9390 +Train: [53] [ 800/6250] eta: 0:12:46 lr: 0.000061 grad: 0.0911 (0.0958) loss: 0.8209 (0.8204) time: 0.1551 data: 0.0723 max mem: 9390 +Train: [53] [ 900/6250] eta: 0:12:38 lr: 0.000061 grad: 0.0888 (0.0954) loss: 0.8267 (0.8204) time: 0.1457 data: 0.0575 max mem: 9390 +Train: [53] [1000/6250] eta: 0:12:25 lr: 0.000061 grad: 0.0908 (0.0950) loss: 0.8229 (0.8203) time: 0.1377 data: 0.0588 max mem: 9390 +Train: [53] [1100/6250] eta: 0:12:08 lr: 0.000061 grad: 0.0898 (0.0945) loss: 0.8148 (0.8202) time: 0.1382 data: 0.0566 max mem: 9390 +Train: [53] [1200/6250] eta: 0:11:50 lr: 0.000061 grad: 0.0897 (0.0941) loss: 0.8210 (0.8203) time: 0.1168 data: 0.0410 max mem: 9390 +Train: [53] [1300/6250] eta: 0:11:34 lr: 0.000061 grad: 0.0913 (0.0939) loss: 0.8193 (0.8202) time: 0.1367 data: 0.0601 max mem: 9390 +Train: [53] [1400/6250] eta: 0:11:15 lr: 0.000061 grad: 0.0890 (0.0938) loss: 0.8230 (0.8202) time: 0.1100 data: 0.0214 max mem: 9390 +Train: [53] [1500/6250] eta: 0:10:54 lr: 0.000061 grad: 0.0893 (0.0937) loss: 0.8231 (0.8202) time: 0.1287 data: 0.0453 max mem: 9390 +Train: [53] [1600/6250] eta: 0:10:33 lr: 0.000061 grad: 0.0889 (0.0940) loss: 0.8189 (0.8203) time: 0.1058 data: 0.0189 max mem: 9390 +Train: [53] [1700/6250] eta: 0:10:15 lr: 0.000061 grad: 0.0893 (0.0940) loss: 0.8228 (0.8203) time: 0.0943 data: 0.0003 max mem: 9390 +Train: [53] [1800/6250] eta: 0:09:58 lr: 0.000061 grad: 0.0878 (0.0938) loss: 0.8183 (0.8203) time: 0.1122 data: 0.0277 max mem: 9390 +Train: [53] [1900/6250] eta: 0:09:42 lr: 0.000061 grad: 0.0929 (0.0939) loss: 0.8182 (0.8202) time: 0.1252 data: 0.0382 max mem: 9390 +Train: [53] [2000/6250] eta: 0:09:30 lr: 0.000061 grad: 0.0844 (0.0937) loss: 0.8228 (0.8202) time: 0.1336 data: 0.0578 max mem: 9390 +Train: [53] [2100/6250] eta: 0:09:16 lr: 0.000061 grad: 0.0943 (0.0938) loss: 0.8117 (0.8201) time: 0.1373 data: 0.0563 max mem: 9390 +Train: [53] [2200/6250] eta: 0:09:03 lr: 0.000061 grad: 0.0861 (0.0937) loss: 0.8236 (0.8200) time: 0.1376 data: 0.0555 max mem: 9390 +Train: [53] [2300/6250] eta: 0:08:49 lr: 0.000061 grad: 0.0862 (0.0936) loss: 0.8188 (0.8198) time: 0.1077 data: 0.0288 max mem: 9390 +Train: [53] [2400/6250] eta: 0:08:36 lr: 0.000061 grad: 0.0895 (0.0936) loss: 0.8201 (0.8197) time: 0.1426 data: 0.0636 max mem: 9390 +Train: [53] [2500/6250] eta: 0:08:25 lr: 0.000061 grad: 0.0907 (0.0937) loss: 0.8133 (0.8195) time: 0.1695 data: 0.0872 max mem: 9390 +Train: [53] [2600/6250] eta: 0:08:12 lr: 0.000061 grad: 0.0999 (0.0939) loss: 0.8185 (0.8193) time: 0.1323 data: 0.0534 max mem: 9390 +Train: [53] [2700/6250] eta: 0:07:59 lr: 0.000061 grad: 0.0881 (0.0940) loss: 0.8192 (0.8191) time: 0.1523 data: 0.0759 max mem: 9390 +Train: [53] [2800/6250] eta: 0:07:46 lr: 0.000061 grad: 0.0937 (0.0940) loss: 0.8207 (0.8190) time: 0.1490 data: 0.0745 max mem: 9390 +Train: [53] [2900/6250] eta: 0:07:33 lr: 0.000061 grad: 0.0964 (0.0941) loss: 0.8215 (0.8190) time: 0.1174 data: 0.0365 max mem: 9390 +Train: [53] [3000/6250] eta: 0:07:21 lr: 0.000060 grad: 0.0973 (0.0942) loss: 0.8094 (0.8189) time: 0.1535 data: 0.0687 max mem: 9390 +Train: [53] [3100/6250] eta: 0:07:09 lr: 0.000060 grad: 0.0927 (0.0942) loss: 0.8175 (0.8189) time: 0.1676 data: 0.0908 max mem: 9390 +Train: [53] [3200/6250] eta: 0:06:56 lr: 0.000060 grad: 0.0902 (0.0942) loss: 0.8152 (0.8188) time: 0.1673 data: 0.0911 max mem: 9390 +Train: [53] [3300/6250] eta: 0:06:42 lr: 0.000060 grad: 0.0900 (0.0942) loss: 0.8187 (0.8188) time: 0.1441 data: 0.0581 max mem: 9390 +Train: [53] [3400/6250] eta: 0:06:29 lr: 0.000060 grad: 0.0896 (0.0942) loss: 0.8174 (0.8187) time: 0.1147 data: 0.0282 max mem: 9390 +Train: [53] [3500/6250] eta: 0:06:15 lr: 0.000060 grad: 0.0941 (0.0943) loss: 0.8120 (0.8187) time: 0.1348 data: 0.0500 max mem: 9390 +Train: [53] [3600/6250] eta: 0:06:02 lr: 0.000060 grad: 0.0934 (0.0943) loss: 0.8153 (0.8186) time: 0.1348 data: 0.0532 max mem: 9390 +Train: [53] [3700/6250] eta: 0:05:48 lr: 0.000060 grad: 0.0908 (0.0943) loss: 0.8169 (0.8186) time: 0.1333 data: 0.0526 max mem: 9390 +Train: [53] [3800/6250] eta: 0:05:34 lr: 0.000060 grad: 0.0933 (0.0944) loss: 0.8160 (0.8186) time: 0.1502 data: 0.0572 max mem: 9390 +Train: [53] [3900/6250] eta: 0:05:21 lr: 0.000060 grad: 0.0845 (0.0944) loss: 0.8170 (0.8185) time: 0.1498 data: 0.0717 max mem: 9390 +Train: [53] [4000/6250] eta: 0:05:06 lr: 0.000060 grad: 0.0960 (0.0945) loss: 0.8096 (0.8184) time: 0.1245 data: 0.0444 max mem: 9390 +Train: [53] [4100/6250] eta: 0:04:53 lr: 0.000060 grad: 0.0871 (0.0945) loss: 0.8217 (0.8183) time: 0.1803 data: 0.0981 max mem: 9390 +Train: [53] [4200/6250] eta: 0:04:39 lr: 0.000060 grad: 0.0926 (0.0945) loss: 0.8140 (0.8182) time: 0.1343 data: 0.0552 max mem: 9390 +Train: [53] [4300/6250] eta: 0:04:26 lr: 0.000060 grad: 0.0930 (0.0945) loss: 0.8181 (0.8181) time: 0.1444 data: 0.0501 max mem: 9390 +Train: [53] [4400/6250] eta: 0:04:12 lr: 0.000060 grad: 0.0921 (0.0946) loss: 0.8193 (0.8181) time: 0.1276 data: 0.0474 max mem: 9390 +Train: [53] [4500/6250] eta: 0:03:58 lr: 0.000060 grad: 0.0903 (0.0946) loss: 0.8163 (0.8181) time: 0.1300 data: 0.0441 max mem: 9390 +Train: [53] [4600/6250] eta: 0:03:45 lr: 0.000060 grad: 0.0974 (0.0947) loss: 0.8203 (0.8181) time: 0.1103 data: 0.0272 max mem: 9390 +Train: [53] [4700/6250] eta: 0:03:31 lr: 0.000060 grad: 0.0906 (0.0947) loss: 0.8203 (0.8182) time: 0.1399 data: 0.0536 max mem: 9390 +Train: [53] [4800/6250] eta: 0:03:18 lr: 0.000060 grad: 0.0907 (0.0947) loss: 0.8208 (0.8182) time: 0.1255 data: 0.0347 max mem: 9390 +Train: [53] [4900/6250] eta: 0:03:04 lr: 0.000060 grad: 0.0890 (0.0947) loss: 0.8182 (0.8182) time: 0.1312 data: 0.0416 max mem: 9390 +Train: [53] [5000/6250] eta: 0:02:51 lr: 0.000060 grad: 0.0884 (0.0947) loss: 0.8229 (0.8183) time: 0.0871 data: 0.0002 max mem: 9390 +Train: [53] [5100/6250] eta: 0:02:37 lr: 0.000060 grad: 0.0909 (0.0946) loss: 0.8263 (0.8184) time: 0.1544 data: 0.0772 max mem: 9390 +Train: [53] [5200/6250] eta: 0:02:24 lr: 0.000060 grad: 0.0823 (0.0945) loss: 0.8281 (0.8185) time: 0.1791 data: 0.1006 max mem: 9390 +Train: [53] [5300/6250] eta: 0:02:10 lr: 0.000060 grad: 0.0865 (0.0944) loss: 0.8257 (0.8187) time: 0.1755 data: 0.0956 max mem: 9390 +Train: [53] [5400/6250] eta: 0:01:56 lr: 0.000060 grad: 0.0863 (0.0943) loss: 0.8224 (0.8187) time: 0.1088 data: 0.0329 max mem: 9390 +Train: [53] [5500/6250] eta: 0:01:43 lr: 0.000060 grad: 0.0899 (0.0943) loss: 0.8223 (0.8188) time: 0.1299 data: 0.0416 max mem: 9390 +Train: [53] [5600/6250] eta: 0:01:29 lr: 0.000060 grad: 0.0858 (0.0942) loss: 0.8236 (0.8189) time: 0.1119 data: 0.0323 max mem: 9390 +Train: [53] [5700/6250] eta: 0:01:15 lr: 0.000060 grad: 0.0868 (0.0941) loss: 0.8295 (0.8190) time: 0.1366 data: 0.0556 max mem: 9390 +Train: [53] [5800/6250] eta: 0:01:01 lr: 0.000060 grad: 0.0866 (0.0941) loss: 0.8233 (0.8190) time: 0.1203 data: 0.0401 max mem: 9390 +Train: [53] [5900/6250] eta: 0:00:48 lr: 0.000060 grad: 0.0900 (0.0940) loss: 0.8165 (0.8191) time: 0.1367 data: 0.0577 max mem: 9390 +Train: [53] [6000/6250] eta: 0:00:34 lr: 0.000059 grad: 0.0932 (0.0940) loss: 0.8165 (0.8191) time: 0.1241 data: 0.0353 max mem: 9390 +Train: [53] [6100/6250] eta: 0:00:20 lr: 0.000059 grad: 0.0883 (0.0940) loss: 0.8241 (0.8192) time: 0.1487 data: 0.0705 max mem: 9390 +Train: [53] [6200/6250] eta: 0:00:06 lr: 0.000059 grad: 0.0872 (0.0939) loss: 0.8238 (0.8192) time: 0.1292 data: 0.0492 max mem: 9390 +Train: [53] [6249/6250] eta: 0:00:00 lr: 0.000059 grad: 0.0892 (0.0939) loss: 0.8209 (0.8193) time: 0.1432 data: 0.0653 max mem: 9390 +Train: [53] Total time: 0:14:23 (0.1381 s / it) +Averaged stats: lr: 0.000059 grad: 0.0892 (0.0939) loss: 0.8209 (0.8193) +Eval (hcp-train-subset): [53] [ 0/62] eta: 0:03:39 loss: 0.8437 (0.8437) time: 3.5469 data: 3.4573 max mem: 9390 +Eval (hcp-train-subset): [53] [61/62] eta: 0:00:00 loss: 0.8315 (0.8340) time: 0.1367 data: 0.1117 max mem: 9390 +Eval (hcp-train-subset): [53] Total time: 0:00:12 (0.1988 s / it) +Averaged stats (hcp-train-subset): loss: 0.8315 (0.8340) +Eval (hcp-val): [53] [ 0/62] eta: 0:04:23 loss: 0.8322 (0.8322) time: 4.2483 data: 4.2170 max mem: 9390 +Eval (hcp-val): [53] [61/62] eta: 0:00:00 loss: 0.8333 (0.8349) time: 0.1359 data: 0.1104 max mem: 9390 +Eval (hcp-val): [53] Total time: 0:00:12 (0.2071 s / it) +Averaged stats (hcp-val): loss: 0.8333 (0.8349) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +Train: [54] [ 0/6250] eta: 8:31:43 lr: 0.000059 grad: 0.0627 (0.0627) loss: 0.8646 (0.8646) time: 4.9125 data: 4.8017 max mem: 9390 +Train: [54] [ 100/6250] eta: 0:19:48 lr: 0.000059 grad: 0.0929 (0.1058) loss: 0.8204 (0.8300) time: 0.1602 data: 0.0710 max mem: 9390 +Train: [54] [ 200/6250] eta: 0:16:55 lr: 0.000059 grad: 0.0949 (0.1053) loss: 0.8227 (0.8255) time: 0.1488 data: 0.0649 max mem: 9390 +Train: [54] [ 300/6250] eta: 0:15:29 lr: 0.000059 grad: 0.0904 (0.1021) loss: 0.8188 (0.8236) time: 0.1387 data: 0.0493 max mem: 9390 +Train: [54] [ 400/6250] eta: 0:14:47 lr: 0.000059 grad: 0.0893 (0.1011) loss: 0.8262 (0.8227) time: 0.1509 data: 0.0668 max mem: 9390 +Train: [54] [ 500/6250] eta: 0:14:00 lr: 0.000059 grad: 0.0923 (0.1002) loss: 0.8155 (0.8217) time: 0.1420 data: 0.0602 max mem: 9390 +Train: [54] [ 600/6250] eta: 0:13:23 lr: 0.000059 grad: 0.0936 (0.0991) loss: 0.8159 (0.8218) time: 0.1255 data: 0.0328 max mem: 9390 +Train: [54] [ 700/6250] eta: 0:12:53 lr: 0.000059 grad: 0.0914 (0.0980) loss: 0.8154 (0.8214) time: 0.1293 data: 0.0482 max mem: 9390 +Train: [54] [ 800/6250] eta: 0:12:28 lr: 0.000059 grad: 0.0899 (0.0971) loss: 0.8191 (0.8214) time: 0.1346 data: 0.0464 max mem: 9390 +Train: [54] [ 900/6250] eta: 0:12:14 lr: 0.000059 grad: 0.0912 (0.0966) loss: 0.8224 (0.8212) time: 0.1986 data: 0.1241 max mem: 9390 +Train: [54] [1000/6250] eta: 0:12:04 lr: 0.000059 grad: 0.0892 (0.0961) loss: 0.8139 (0.8208) time: 0.1257 data: 0.0452 max mem: 9390 +Train: [54] [1100/6250] eta: 0:11:51 lr: 0.000059 grad: 0.0907 (0.0957) loss: 0.8187 (0.8204) time: 0.1388 data: 0.0629 max mem: 9390 +Train: [54] [1200/6250] eta: 0:11:38 lr: 0.000059 grad: 0.0888 (0.0954) loss: 0.8192 (0.8202) time: 0.1173 data: 0.0341 max mem: 9390 +Train: [54] [1300/6250] eta: 0:11:22 lr: 0.000059 grad: 0.0888 (0.0952) loss: 0.8194 (0.8201) time: 0.1252 data: 0.0420 max mem: 9390 +Train: [54] [1400/6250] eta: 0:11:06 lr: 0.000059 grad: 0.0886 (0.0953) loss: 0.8194 (0.8198) time: 0.1255 data: 0.0417 max mem: 9390 +Train: [54] [1500/6250] eta: 0:10:47 lr: 0.000059 grad: 0.0893 (0.0953) loss: 0.8185 (0.8194) time: 0.1099 data: 0.0275 max mem: 9390 +Train: [54] [1600/6250] eta: 0:10:28 lr: 0.000059 grad: 0.0893 (0.0952) loss: 0.8216 (0.8193) time: 0.1152 data: 0.0333 max mem: 9390 +Train: [54] [1700/6250] eta: 0:10:10 lr: 0.000059 grad: 0.0889 (0.0951) loss: 0.8213 (0.8194) time: 0.1021 data: 0.0192 max mem: 9390 +Train: [54] [1800/6250] eta: 0:09:52 lr: 0.000059 grad: 0.0845 (0.0949) loss: 0.8179 (0.8194) time: 0.1155 data: 0.0355 max mem: 9390 +Train: [54] [1900/6250] eta: 0:09:34 lr: 0.000059 grad: 0.0862 (0.0947) loss: 0.8223 (0.8194) time: 0.1230 data: 0.0345 max mem: 9390 +Train: [54] [2000/6250] eta: 0:09:19 lr: 0.000059 grad: 0.0878 (0.0946) loss: 0.8206 (0.8195) time: 0.1318 data: 0.0439 max mem: 9390 +Train: [54] [2100/6250] eta: 0:09:07 lr: 0.000059 grad: 0.0904 (0.0945) loss: 0.8197 (0.8195) time: 0.1343 data: 0.0588 max mem: 9390 +Train: [54] [2200/6250] eta: 0:08:56 lr: 0.000059 grad: 0.0895 (0.0945) loss: 0.8236 (0.8196) time: 0.1486 data: 0.0649 max mem: 9390 +Train: [54] [2300/6250] eta: 0:08:48 lr: 0.000059 grad: 0.0908 (0.0946) loss: 0.8165 (0.8196) time: 0.0804 data: 0.0002 max mem: 9390 +Train: [54] [2400/6250] eta: 0:08:33 lr: 0.000059 grad: 0.0890 (0.0945) loss: 0.8143 (0.8195) time: 0.1345 data: 0.0580 max mem: 9390 +Train: [54] [2500/6250] eta: 0:08:20 lr: 0.000059 grad: 0.0940 (0.0945) loss: 0.8229 (0.8195) time: 0.1543 data: 0.0679 max mem: 9390 +Train: [54] [2600/6250] eta: 0:08:09 lr: 0.000059 grad: 0.0995 (0.0945) loss: 0.8147 (0.8194) time: 0.1413 data: 0.0653 max mem: 9390 +Train: [54] [2700/6250] eta: 0:07:56 lr: 0.000059 grad: 0.0934 (0.0945) loss: 0.8169 (0.8194) time: 0.1451 data: 0.0678 max mem: 9390 +Train: [54] [2800/6250] eta: 0:07:44 lr: 0.000058 grad: 0.0940 (0.0945) loss: 0.8157 (0.8194) time: 0.1461 data: 0.0615 max mem: 9390 +Train: [54] [2900/6250] eta: 0:07:32 lr: 0.000058 grad: 0.0943 (0.0945) loss: 0.8167 (0.8194) time: 0.1497 data: 0.0720 max mem: 9390 +Train: [54] [3000/6250] eta: 0:07:18 lr: 0.000058 grad: 0.0972 (0.0945) loss: 0.8143 (0.8192) time: 0.1510 data: 0.0688 max mem: 9390 +Train: [54] [3100/6250] eta: 0:07:04 lr: 0.000058 grad: 0.0908 (0.0944) loss: 0.8157 (0.8192) time: 0.1448 data: 0.0603 max mem: 9390 +Train: [54] [3200/6250] eta: 0:06:50 lr: 0.000058 grad: 0.0956 (0.0945) loss: 0.8172 (0.8190) time: 0.1083 data: 0.0268 max mem: 9390 +Train: [54] [3300/6250] eta: 0:06:37 lr: 0.000058 grad: 0.0934 (0.0945) loss: 0.8133 (0.8189) time: 0.1188 data: 0.0370 max mem: 9390 +Train: [54] [3400/6250] eta: 0:06:23 lr: 0.000058 grad: 0.0989 (0.0946) loss: 0.8137 (0.8188) time: 0.1487 data: 0.0596 max mem: 9390 +Train: [54] [3500/6250] eta: 0:06:10 lr: 0.000058 grad: 0.0911 (0.0946) loss: 0.8165 (0.8187) time: 0.1400 data: 0.0617 max mem: 9390 +Train: [54] [3600/6250] eta: 0:05:56 lr: 0.000058 grad: 0.0942 (0.0946) loss: 0.8113 (0.8186) time: 0.1288 data: 0.0484 max mem: 9390 +Train: [54] [3700/6250] eta: 0:05:42 lr: 0.000058 grad: 0.0958 (0.0947) loss: 0.8087 (0.8184) time: 0.1316 data: 0.0531 max mem: 9390 +Train: [54] [3800/6250] eta: 0:05:29 lr: 0.000058 grad: 0.0902 (0.0947) loss: 0.8150 (0.8183) time: 0.1215 data: 0.0383 max mem: 9390 +Train: [54] [3900/6250] eta: 0:05:16 lr: 0.000058 grad: 0.0937 (0.0947) loss: 0.8153 (0.8182) time: 0.1412 data: 0.0615 max mem: 9390 +Train: [54] [4000/6250] eta: 0:05:03 lr: 0.000058 grad: 0.0928 (0.0947) loss: 0.8202 (0.8181) time: 0.1530 data: 0.0691 max mem: 9390 +Train: [54] [4100/6250] eta: 0:04:50 lr: 0.000058 grad: 0.0950 (0.0947) loss: 0.8120 (0.8181) time: 0.1274 data: 0.0464 max mem: 9390 +Train: [54] [4200/6250] eta: 0:04:37 lr: 0.000058 grad: 0.0897 (0.0948) loss: 0.8133 (0.8180) time: 0.1460 data: 0.0288 max mem: 9390 +Train: [54] [4300/6250] eta: 0:04:23 lr: 0.000058 grad: 0.0947 (0.0948) loss: 0.8144 (0.8179) time: 0.1404 data: 0.0589 max mem: 9390 +Train: [54] [4400/6250] eta: 0:04:10 lr: 0.000058 grad: 0.0988 (0.0948) loss: 0.8128 (0.8178) time: 0.1492 data: 0.0613 max mem: 9390 +Train: [54] [4500/6250] eta: 0:03:57 lr: 0.000058 grad: 0.0930 (0.0949) loss: 0.8167 (0.8178) time: 0.1472 data: 0.0694 max mem: 9390 +Train: [54] [4600/6250] eta: 0:03:43 lr: 0.000058 grad: 0.1000 (0.0949) loss: 0.8129 (0.8177) time: 0.1292 data: 0.0484 max mem: 9390 +Train: [54] [4700/6250] eta: 0:03:29 lr: 0.000058 grad: 0.0954 (0.0949) loss: 0.8144 (0.8176) time: 0.1367 data: 0.0585 max mem: 9390 +Train: [54] [4800/6250] eta: 0:03:16 lr: 0.000058 grad: 0.0920 (0.0950) loss: 0.8166 (0.8176) time: 0.1340 data: 0.0575 max mem: 9390 +Train: [54] [4900/6250] eta: 0:03:03 lr: 0.000058 grad: 0.0915 (0.0950) loss: 0.8154 (0.8175) time: 0.1503 data: 0.0729 max mem: 9390 +Train: [54] [5000/6250] eta: 0:02:49 lr: 0.000058 grad: 0.0945 (0.0950) loss: 0.8144 (0.8175) time: 0.1488 data: 0.0662 max mem: 9390 +Train: [54] [5100/6250] eta: 0:02:36 lr: 0.000058 grad: 0.0965 (0.0951) loss: 0.8149 (0.8174) time: 0.1626 data: 0.0834 max mem: 9390 +Train: [54] [5200/6250] eta: 0:02:22 lr: 0.000058 grad: 0.0967 (0.0951) loss: 0.8111 (0.8174) time: 0.1444 data: 0.0603 max mem: 9390 +Train: [54] [5300/6250] eta: 0:02:08 lr: 0.000058 grad: 0.0935 (0.0951) loss: 0.8173 (0.8173) time: 0.1339 data: 0.0548 max mem: 9390 +Train: [54] [5400/6250] eta: 0:01:55 lr: 0.000058 grad: 0.0920 (0.0951) loss: 0.8146 (0.8173) time: 0.1418 data: 0.0505 max mem: 9390 +Train: [54] [5500/6250] eta: 0:01:41 lr: 0.000058 grad: 0.0929 (0.0952) loss: 0.8175 (0.8173) time: 0.1354 data: 0.0555 max mem: 9390 +Train: [54] [5600/6250] eta: 0:01:28 lr: 0.000058 grad: 0.0904 (0.0953) loss: 0.8133 (0.8172) time: 0.1353 data: 0.0529 max mem: 9390 +Train: [54] [5700/6250] eta: 0:01:14 lr: 0.000058 grad: 0.0939 (0.0952) loss: 0.8182 (0.8172) time: 0.1041 data: 0.0192 max mem: 9390 +Train: [54] [5800/6250] eta: 0:01:01 lr: 0.000057 grad: 0.0937 (0.0953) loss: 0.8140 (0.8171) time: 0.1295 data: 0.0531 max mem: 9390 +Train: [54] [5900/6250] eta: 0:00:47 lr: 0.000057 grad: 0.0954 (0.0953) loss: 0.8086 (0.8171) time: 0.1387 data: 0.0547 max mem: 9390 +Train: [54] [6000/6250] eta: 0:00:33 lr: 0.000057 grad: 0.0946 (0.0953) loss: 0.8113 (0.8170) time: 0.1232 data: 0.0432 max mem: 9390 +Train: [54] [6100/6250] eta: 0:00:20 lr: 0.000057 grad: 0.0928 (0.0953) loss: 0.8211 (0.8170) time: 0.1250 data: 0.0392 max mem: 9390 +Train: [54] [6200/6250] eta: 0:00:06 lr: 0.000057 grad: 0.0959 (0.0953) loss: 0.8141 (0.8170) time: 0.1317 data: 0.0490 max mem: 9390 +Train: [54] [6249/6250] eta: 0:00:00 lr: 0.000057 grad: 0.0951 (0.0953) loss: 0.8178 (0.8170) time: 0.1477 data: 0.0672 max mem: 9390 +Train: [54] Total time: 0:14:14 (0.1366 s / it) +Averaged stats: lr: 0.000057 grad: 0.0951 (0.0953) loss: 0.8178 (0.8170) +Eval (hcp-train-subset): [54] [ 0/62] eta: 0:03:37 loss: 0.8500 (0.8500) time: 3.5132 data: 3.4130 max mem: 9390 +Eval (hcp-train-subset): [54] [61/62] eta: 0:00:00 loss: 0.8318 (0.8352) time: 0.1108 data: 0.0856 max mem: 9390 +Eval (hcp-train-subset): [54] Total time: 0:00:11 (0.1895 s / it) +Averaged stats (hcp-train-subset): loss: 0.8318 (0.8352) +Making plots (hcp-train-subset): example=16 +Eval (hcp-val): [54] [ 0/62] eta: 0:04:23 loss: 0.8314 (0.8314) time: 4.2556 data: 4.2253 max mem: 9390 +Eval (hcp-val): [54] [61/62] eta: 0:00:00 loss: 0.8335 (0.8347) time: 0.1204 data: 0.0957 max mem: 9390 +Eval (hcp-val): [54] Total time: 0:00:11 (0.1897 s / it) +Averaged stats (hcp-val): loss: 0.8335 (0.8347) +Making plots (hcp-val): example=19 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +Train: [55] [ 0/6250] eta: 10:57:40 lr: 0.000057 grad: 0.0809 (0.0809) loss: 0.8620 (0.8620) time: 6.3136 data: 6.2111 max mem: 9390 +Train: [55] [ 100/6250] eta: 0:20:37 lr: 0.000057 grad: 0.1039 (0.1089) loss: 0.8051 (0.8308) time: 0.1542 data: 0.0614 max mem: 9390 +Train: [55] [ 200/6250] eta: 0:17:23 lr: 0.000057 grad: 0.1019 (0.1079) loss: 0.8168 (0.8227) time: 0.1505 data: 0.0683 max mem: 9390 +Train: [55] [ 300/6250] eta: 0:16:05 lr: 0.000057 grad: 0.0883 (0.1043) loss: 0.8168 (0.8209) time: 0.1357 data: 0.0475 max mem: 9390 +Train: [55] [ 400/6250] eta: 0:15:09 lr: 0.000057 grad: 0.0819 (0.1005) loss: 0.8214 (0.8211) time: 0.1303 data: 0.0481 max mem: 9390 +Train: [55] [ 500/6250] eta: 0:14:17 lr: 0.000057 grad: 0.0853 (0.0982) loss: 0.8284 (0.8219) time: 0.1287 data: 0.0390 max mem: 9390 +Train: [55] [ 600/6250] eta: 0:13:43 lr: 0.000057 grad: 0.0872 (0.0964) loss: 0.8231 (0.8224) time: 0.1206 data: 0.0378 max mem: 9390 +Train: [55] [ 700/6250] eta: 0:13:12 lr: 0.000057 grad: 0.0874 (0.0957) loss: 0.8263 (0.8228) time: 0.1387 data: 0.0587 max mem: 9390 +Train: [55] [ 800/6250] eta: 0:12:46 lr: 0.000057 grad: 0.0856 (0.0948) loss: 0.8325 (0.8232) time: 0.1303 data: 0.0474 max mem: 9390 +Train: [55] [ 900/6250] eta: 0:12:23 lr: 0.000057 grad: 0.0860 (0.0943) loss: 0.8227 (0.8232) time: 0.1171 data: 0.0355 max mem: 9390 +Train: [55] [1000/6250] eta: 0:12:20 lr: 0.000057 grad: 0.0936 (0.0942) loss: 0.8236 (0.8230) time: 0.1387 data: 0.0608 max mem: 9390 +Train: [55] [1100/6250] eta: 0:12:08 lr: 0.000057 grad: 0.0880 (0.0945) loss: 0.8157 (0.8226) time: 0.1391 data: 0.0690 max mem: 9390 +Train: [55] [1200/6250] eta: 0:11:52 lr: 0.000057 grad: 0.0851 (0.0944) loss: 0.8200 (0.8223) time: 0.1477 data: 0.0673 max mem: 9390 +Train: [55] [1300/6250] eta: 0:11:36 lr: 0.000057 grad: 0.0899 (0.0944) loss: 0.8259 (0.8219) time: 0.1393 data: 0.0621 max mem: 9390 +Train: [55] [1400/6250] eta: 0:11:18 lr: 0.000057 grad: 0.0944 (0.0945) loss: 0.8185 (0.8217) time: 0.1359 data: 0.0601 max mem: 9390 +Train: [55] [1500/6250] eta: 0:10:59 lr: 0.000057 grad: 0.0911 (0.0943) loss: 0.8174 (0.8214) time: 0.1186 data: 0.0342 max mem: 9390 +Train: [55] [1600/6250] eta: 0:10:41 lr: 0.000057 grad: 0.0919 (0.0942) loss: 0.8219 (0.8211) time: 0.1294 data: 0.0487 max mem: 9390 +Train: [55] [1700/6250] eta: 0:10:23 lr: 0.000057 grad: 0.0916 (0.0942) loss: 0.8186 (0.8209) time: 0.1229 data: 0.0446 max mem: 9390 +Train: [55] [1800/6250] eta: 0:10:05 lr: 0.000057 grad: 0.0860 (0.0941) loss: 0.8171 (0.8207) time: 0.1196 data: 0.0399 max mem: 9390 +Train: [55] [1900/6250] eta: 0:09:48 lr: 0.000057 grad: 0.0888 (0.0941) loss: 0.8215 (0.8207) time: 0.1301 data: 0.0463 max mem: 9390 +Train: [55] [2000/6250] eta: 0:09:31 lr: 0.000057 grad: 0.0961 (0.0943) loss: 0.8232 (0.8205) time: 0.1044 data: 0.0247 max mem: 9390 +Train: [55] [2100/6250] eta: 0:09:15 lr: 0.000057 grad: 0.0929 (0.0942) loss: 0.8183 (0.8204) time: 0.1268 data: 0.0416 max mem: 9390 +Train: [55] [2200/6250] eta: 0:09:04 lr: 0.000057 grad: 0.0932 (0.0942) loss: 0.8075 (0.8201) time: 0.1270 data: 0.0520 max mem: 9390 +Train: [55] [2300/6250] eta: 0:08:50 lr: 0.000057 grad: 0.0906 (0.0943) loss: 0.8228 (0.8200) time: 0.1248 data: 0.0431 max mem: 9390 +Train: [55] [2400/6250] eta: 0:08:37 lr: 0.000057 grad: 0.0906 (0.0943) loss: 0.8138 (0.8199) time: 0.1380 data: 0.0524 max mem: 9390 +Train: [55] [2500/6250] eta: 0:08:25 lr: 0.000057 grad: 0.0902 (0.0942) loss: 0.8240 (0.8199) time: 0.1256 data: 0.0508 max mem: 9390 +Train: [55] [2600/6250] eta: 0:08:13 lr: 0.000056 grad: 0.0938 (0.0942) loss: 0.8225 (0.8198) time: 0.1277 data: 0.0499 max mem: 9390 +Train: [55] [2700/6250] eta: 0:07:59 lr: 0.000056 grad: 0.0990 (0.0943) loss: 0.8189 (0.8198) time: 0.1351 data: 0.0570 max mem: 9390 +Train: [55] [2800/6250] eta: 0:07:47 lr: 0.000056 grad: 0.0932 (0.0943) loss: 0.8209 (0.8197) time: 0.1503 data: 0.0673 max mem: 9390 +Train: [55] [2900/6250] eta: 0:07:34 lr: 0.000056 grad: 0.0925 (0.0944) loss: 0.8191 (0.8195) time: 0.1547 data: 0.0768 max mem: 9390 +Train: [55] [3000/6250] eta: 0:07:20 lr: 0.000056 grad: 0.0957 (0.0945) loss: 0.8100 (0.8194) time: 0.1358 data: 0.0600 max mem: 9390 +Train: [55] [3100/6250] eta: 0:07:07 lr: 0.000056 grad: 0.0933 (0.0945) loss: 0.8168 (0.8193) time: 0.1404 data: 0.0675 max mem: 9390 +Train: [55] [3200/6250] eta: 0:06:52 lr: 0.000056 grad: 0.0961 (0.0947) loss: 0.8245 (0.8191) time: 0.1418 data: 0.0597 max mem: 9390 +Train: [55] [3300/6250] eta: 0:06:38 lr: 0.000056 grad: 0.0940 (0.0947) loss: 0.8162 (0.8191) time: 0.1317 data: 0.0533 max mem: 9390 +Train: [55] [3400/6250] eta: 0:06:25 lr: 0.000056 grad: 0.0973 (0.0948) loss: 0.8140 (0.8190) time: 0.1268 data: 0.0474 max mem: 9390 +Train: [55] [3500/6250] eta: 0:06:11 lr: 0.000056 grad: 0.0916 (0.0948) loss: 0.8111 (0.8189) time: 0.1213 data: 0.0375 max mem: 9390 +Train: [55] [3600/6250] eta: 0:05:57 lr: 0.000056 grad: 0.0961 (0.0949) loss: 0.8124 (0.8187) time: 0.1082 data: 0.0273 max mem: 9390 +Train: [55] [3700/6250] eta: 0:05:45 lr: 0.000056 grad: 0.0953 (0.0950) loss: 0.8069 (0.8186) time: 0.1560 data: 0.0638 max mem: 9390 +Train: [55] [3800/6250] eta: 0:05:31 lr: 0.000056 grad: 0.0988 (0.0951) loss: 0.8128 (0.8184) time: 0.1161 data: 0.0332 max mem: 9390 +Train: [55] [3900/6250] eta: 0:05:18 lr: 0.000056 grad: 0.1005 (0.0953) loss: 0.8133 (0.8183) time: 0.1456 data: 0.0606 max mem: 9390 +Train: [55] [4000/6250] eta: 0:05:05 lr: 0.000056 grad: 0.0936 (0.0953) loss: 0.8082 (0.8182) time: 0.1524 data: 0.0768 max mem: 9390 +Train: [55] [4100/6250] eta: 0:04:51 lr: 0.000056 grad: 0.0919 (0.0954) loss: 0.8149 (0.8181) time: 0.1425 data: 0.0605 max mem: 9390 +Train: [55] [4200/6250] eta: 0:04:38 lr: 0.000056 grad: 0.0951 (0.0953) loss: 0.8233 (0.8181) time: 0.1357 data: 0.0523 max mem: 9390 +Train: [55] [4300/6250] eta: 0:04:24 lr: 0.000056 grad: 0.0933 (0.0954) loss: 0.8136 (0.8180) time: 0.1297 data: 0.0475 max mem: 9390 +Train: [55] [4400/6250] eta: 0:04:11 lr: 0.000056 grad: 0.0946 (0.0954) loss: 0.8115 (0.8179) time: 0.1497 data: 0.0715 max mem: 9390 +Train: [55] [4500/6250] eta: 0:03:57 lr: 0.000056 grad: 0.0956 (0.0955) loss: 0.8138 (0.8178) time: 0.1365 data: 0.0608 max mem: 9390 +Train: [55] [4600/6250] eta: 0:03:44 lr: 0.000056 grad: 0.0922 (0.0956) loss: 0.8116 (0.8178) time: 0.1744 data: 0.1002 max mem: 9390 +Train: [55] [4700/6250] eta: 0:03:30 lr: 0.000056 grad: 0.0998 (0.0957) loss: 0.8089 (0.8176) time: 0.1310 data: 0.0520 max mem: 9390 +Train: [55] [4800/6250] eta: 0:03:16 lr: 0.000056 grad: 0.0909 (0.0959) loss: 0.8106 (0.8175) time: 0.1328 data: 0.0549 max mem: 9390 +Train: [55] [4900/6250] eta: 0:03:03 lr: 0.000056 grad: 0.0965 (0.0960) loss: 0.8153 (0.8174) time: 0.1403 data: 0.0528 max mem: 9390 +Train: [55] [5000/6250] eta: 0:02:50 lr: 0.000056 grad: 0.0946 (0.0960) loss: 0.8153 (0.8172) time: 0.1130 data: 0.0319 max mem: 9390 +Train: [55] [5100/6250] eta: 0:02:36 lr: 0.000056 grad: 0.0935 (0.0961) loss: 0.8145 (0.8171) time: 0.1427 data: 0.0635 max mem: 9390 +Train: [55] [5200/6250] eta: 0:02:23 lr: 0.000056 grad: 0.0929 (0.0961) loss: 0.8196 (0.8170) time: 0.1691 data: 0.0934 max mem: 9390 +Train: [55] [5300/6250] eta: 0:02:09 lr: 0.000056 grad: 0.0966 (0.0961) loss: 0.8139 (0.8169) time: 0.1467 data: 0.0604 max mem: 9390 +Train: [55] [5400/6250] eta: 0:01:56 lr: 0.000056 grad: 0.0944 (0.0962) loss: 0.8103 (0.8169) time: 0.1427 data: 0.0604 max mem: 9390 +Train: [55] [5500/6250] eta: 0:01:42 lr: 0.000056 grad: 0.0927 (0.0962) loss: 0.8230 (0.8169) time: 0.1363 data: 0.0543 max mem: 9390 +Train: [55] [5600/6250] eta: 0:01:28 lr: 0.000055 grad: 0.0914 (0.0962) loss: 0.8175 (0.8168) time: 0.1270 data: 0.0482 max mem: 9390 +Train: [55] [5700/6250] eta: 0:01:15 lr: 0.000055 grad: 0.0965 (0.0962) loss: 0.8149 (0.8168) time: 0.1478 data: 0.0709 max mem: 9390 +Train: [55] [5800/6250] eta: 0:01:01 lr: 0.000055 grad: 0.0896 (0.0963) loss: 0.8173 (0.8168) time: 0.1463 data: 0.0675 max mem: 9390 +Train: [55] [5900/6250] eta: 0:00:47 lr: 0.000055 grad: 0.1012 (0.0963) loss: 0.8150 (0.8167) time: 0.1452 data: 0.0653 max mem: 9390 +Train: [55] [6000/6250] eta: 0:00:34 lr: 0.000055 grad: 0.0954 (0.0963) loss: 0.8194 (0.8167) time: 0.1366 data: 0.0592 max mem: 9390 +Train: [55] [6100/6250] eta: 0:00:20 lr: 0.000055 grad: 0.0892 (0.0963) loss: 0.8187 (0.8167) time: 0.1197 data: 0.0442 max mem: 9390 +Train: [55] [6200/6250] eta: 0:00:06 lr: 0.000055 grad: 0.0917 (0.0963) loss: 0.8201 (0.8167) time: 0.1366 data: 0.0608 max mem: 9390 +Train: [55] [6249/6250] eta: 0:00:00 lr: 0.000055 grad: 0.0969 (0.0963) loss: 0.8138 (0.8167) time: 0.1727 data: 0.0914 max mem: 9390 +Train: [55] Total time: 0:14:19 (0.1375 s / it) +Averaged stats: lr: 0.000055 grad: 0.0969 (0.0963) loss: 0.8138 (0.8167) +Eval (hcp-train-subset): [55] [ 0/62] eta: 0:05:00 loss: 0.8483 (0.8483) time: 4.8535 data: 4.8045 max mem: 9390 +Eval (hcp-train-subset): [55] [61/62] eta: 0:00:00 loss: 0.8336 (0.8356) time: 0.1276 data: 0.1018 max mem: 9390 +Eval (hcp-train-subset): [55] Total time: 0:00:13 (0.2117 s / it) +Averaged stats (hcp-train-subset): loss: 0.8336 (0.8356) +Eval (hcp-val): [55] [ 0/62] eta: 0:03:44 loss: 0.8360 (0.8360) time: 3.6167 data: 3.5454 max mem: 9390 +Eval (hcp-val): [55] [61/62] eta: 0:00:00 loss: 0.8344 (0.8355) time: 0.1099 data: 0.0847 max mem: 9390 +Eval (hcp-val): [55] Total time: 0:00:12 (0.2035 s / it) +Averaged stats (hcp-val): loss: 0.8344 (0.8355) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +Train: [56] [ 0/6250] eta: 6:53:54 lr: 0.000055 grad: 0.1012 (0.1012) loss: 0.8667 (0.8667) time: 3.9736 data: 3.7136 max mem: 9390 +Train: [56] [ 100/6250] eta: 0:19:31 lr: 0.000055 grad: 0.0956 (0.1026) loss: 0.8189 (0.8389) time: 0.1303 data: 0.0394 max mem: 9390 +Train: [56] [ 200/6250] eta: 0:17:04 lr: 0.000055 grad: 0.0905 (0.1017) loss: 0.8267 (0.8321) time: 0.1520 data: 0.0589 max mem: 9390 +Train: [56] [ 300/6250] eta: 0:15:42 lr: 0.000055 grad: 0.0895 (0.0990) loss: 0.8264 (0.8290) time: 0.1169 data: 0.0322 max mem: 9390 +Train: [56] [ 400/6250] eta: 0:14:52 lr: 0.000055 grad: 0.0937 (0.0979) loss: 0.8228 (0.8273) time: 0.1307 data: 0.0487 max mem: 9390 +Train: [56] [ 500/6250] eta: 0:14:12 lr: 0.000055 grad: 0.0857 (0.0970) loss: 0.8188 (0.8261) time: 0.1041 data: 0.0159 max mem: 9390 +Train: [56] [ 600/6250] eta: 0:13:38 lr: 0.000055 grad: 0.0890 (0.0961) loss: 0.8227 (0.8257) time: 0.1264 data: 0.0436 max mem: 9390 +Train: [56] [ 700/6250] eta: 0:13:09 lr: 0.000055 grad: 0.0900 (0.0956) loss: 0.8259 (0.8255) time: 0.1361 data: 0.0535 max mem: 9390 +Train: [56] [ 800/6250] eta: 0:12:44 lr: 0.000055 grad: 0.0862 (0.0948) loss: 0.8244 (0.8254) time: 0.1214 data: 0.0337 max mem: 9390 +Train: [56] [ 900/6250] eta: 0:12:31 lr: 0.000055 grad: 0.0840 (0.0942) loss: 0.8208 (0.8252) time: 0.1764 data: 0.0988 max mem: 9390 +Train: [56] [1000/6250] eta: 0:12:23 lr: 0.000055 grad: 0.0818 (0.0937) loss: 0.8231 (0.8251) time: 0.1387 data: 0.0548 max mem: 9390 +Train: [56] [1100/6250] eta: 0:12:08 lr: 0.000055 grad: 0.0810 (0.0931) loss: 0.8242 (0.8248) time: 0.1207 data: 0.0420 max mem: 9390 +Train: [56] [1200/6250] eta: 0:11:53 lr: 0.000055 grad: 0.0860 (0.0928) loss: 0.8217 (0.8247) time: 0.1395 data: 0.0461 max mem: 9390 +Train: [56] [1300/6250] eta: 0:11:36 lr: 0.000055 grad: 0.0830 (0.0927) loss: 0.8281 (0.8245) time: 0.1380 data: 0.0589 max mem: 9390 +Train: [56] [1400/6250] eta: 0:11:17 lr: 0.000055 grad: 0.0864 (0.0925) loss: 0.8197 (0.8243) time: 0.1413 data: 0.0625 max mem: 9390 +Train: [56] [1500/6250] eta: 0:10:57 lr: 0.000055 grad: 0.0891 (0.0924) loss: 0.8228 (0.8241) time: 0.1153 data: 0.0338 max mem: 9390 +Train: [56] [1600/6250] eta: 0:10:39 lr: 0.000055 grad: 0.0857 (0.0923) loss: 0.8219 (0.8241) time: 0.1197 data: 0.0388 max mem: 9390 +Train: [56] [1700/6250] eta: 0:10:21 lr: 0.000055 grad: 0.0892 (0.0921) loss: 0.8211 (0.8240) time: 0.1103 data: 0.0298 max mem: 9390 +Train: [56] [1800/6250] eta: 0:10:02 lr: 0.000055 grad: 0.0882 (0.0922) loss: 0.8211 (0.8238) time: 0.1142 data: 0.0342 max mem: 9390 +Train: [56] [1900/6250] eta: 0:09:45 lr: 0.000055 grad: 0.0888 (0.0922) loss: 0.8230 (0.8236) time: 0.1185 data: 0.0330 max mem: 9390 +Train: [56] [2000/6250] eta: 0:09:30 lr: 0.000055 grad: 0.0878 (0.0921) loss: 0.8190 (0.8235) time: 0.1448 data: 0.0639 max mem: 9390 +Train: [56] [2100/6250] eta: 0:09:19 lr: 0.000055 grad: 0.0926 (0.0921) loss: 0.8194 (0.8234) time: 0.1563 data: 0.0823 max mem: 9390 +Train: [56] [2200/6250] eta: 0:09:07 lr: 0.000055 grad: 0.0810 (0.0920) loss: 0.8257 (0.8234) time: 0.1314 data: 0.0514 max mem: 9390 +Train: [56] [2300/6250] eta: 0:08:57 lr: 0.000055 grad: 0.0901 (0.0919) loss: 0.8179 (0.8233) time: 0.1443 data: 0.0653 max mem: 9390 +Train: [56] [2400/6250] eta: 0:08:45 lr: 0.000054 grad: 0.0914 (0.0918) loss: 0.8239 (0.8232) time: 0.1493 data: 0.0672 max mem: 9390 +Train: [56] [2500/6250] eta: 0:08:32 lr: 0.000054 grad: 0.0866 (0.0919) loss: 0.8206 (0.8230) time: 0.1293 data: 0.0505 max mem: 9390 +Train: [56] [2600/6250] eta: 0:08:21 lr: 0.000054 grad: 0.0878 (0.0918) loss: 0.8189 (0.8230) time: 0.1652 data: 0.0825 max mem: 9390 +Train: [56] [2700/6250] eta: 0:08:07 lr: 0.000054 grad: 0.0903 (0.0919) loss: 0.8172 (0.8229) time: 0.1219 data: 0.0389 max mem: 9390 +Train: [56] [2800/6250] eta: 0:07:55 lr: 0.000054 grad: 0.0965 (0.0921) loss: 0.8179 (0.8228) time: 0.1349 data: 0.0589 max mem: 9390 +Train: [56] [2900/6250] eta: 0:07:41 lr: 0.000054 grad: 0.0932 (0.0922) loss: 0.8139 (0.8227) time: 0.1533 data: 0.0719 max mem: 9390 +Train: [56] [3000/6250] eta: 0:07:26 lr: 0.000054 grad: 0.0924 (0.0923) loss: 0.8217 (0.8225) time: 0.1412 data: 0.0619 max mem: 9390 +Train: [56] [3100/6250] eta: 0:07:12 lr: 0.000054 grad: 0.1007 (0.0925) loss: 0.8154 (0.8224) time: 0.1569 data: 0.0768 max mem: 9390 +Train: [56] [3200/6250] eta: 0:06:57 lr: 0.000054 grad: 0.0943 (0.0926) loss: 0.8139 (0.8222) time: 0.1293 data: 0.0514 max mem: 9390 +Train: [56] [3300/6250] eta: 0:06:43 lr: 0.000054 grad: 0.0961 (0.0927) loss: 0.8165 (0.8221) time: 0.1162 data: 0.0392 max mem: 9390 +Train: [56] [3400/6250] eta: 0:06:28 lr: 0.000054 grad: 0.0897 (0.0927) loss: 0.8206 (0.8220) time: 0.1453 data: 0.0595 max mem: 9390 +Train: [56] [3500/6250] eta: 0:06:15 lr: 0.000054 grad: 0.0918 (0.0927) loss: 0.8160 (0.8219) time: 0.1708 data: 0.0954 max mem: 9390 +Train: [56] [3600/6250] eta: 0:06:01 lr: 0.000054 grad: 0.0951 (0.0928) loss: 0.8241 (0.8218) time: 0.1324 data: 0.0489 max mem: 9390 +Train: [56] [3700/6250] eta: 0:05:47 lr: 0.000054 grad: 0.0888 (0.0927) loss: 0.8227 (0.8218) time: 0.1340 data: 0.0483 max mem: 9390 +Train: [56] [3800/6250] eta: 0:05:33 lr: 0.000054 grad: 0.0876 (0.0927) loss: 0.8184 (0.8217) time: 0.1199 data: 0.0376 max mem: 9390 +Train: [56] [3900/6250] eta: 0:05:20 lr: 0.000054 grad: 0.0874 (0.0928) loss: 0.8219 (0.8216) time: 0.0946 data: 0.0151 max mem: 9390 +Train: [56] [4000/6250] eta: 0:05:06 lr: 0.000054 grad: 0.0932 (0.0928) loss: 0.8231 (0.8216) time: 0.1594 data: 0.0713 max mem: 9390 +Train: [56] [4100/6250] eta: 0:04:52 lr: 0.000054 grad: 0.0920 (0.0929) loss: 0.8261 (0.8216) time: 0.1271 data: 0.0434 max mem: 9390 +Train: [56] [4200/6250] eta: 0:04:38 lr: 0.000054 grad: 0.0865 (0.0929) loss: 0.8134 (0.8215) time: 0.1449 data: 0.0680 max mem: 9390 +Train: [56] [4300/6250] eta: 0:04:25 lr: 0.000054 grad: 0.0857 (0.0930) loss: 0.8191 (0.8215) time: 0.1416 data: 0.0621 max mem: 9390 +Train: [56] [4400/6250] eta: 0:04:11 lr: 0.000054 grad: 0.0875 (0.0930) loss: 0.8274 (0.8214) time: 0.1222 data: 0.0465 max mem: 9390 +Train: [56] [4500/6250] eta: 0:03:58 lr: 0.000054 grad: 0.0908 (0.0930) loss: 0.8181 (0.8214) time: 0.1122 data: 0.0329 max mem: 9390 +Train: [56] [4600/6250] eta: 0:03:44 lr: 0.000054 grad: 0.0933 (0.0930) loss: 0.8112 (0.8213) time: 0.1209 data: 0.0424 max mem: 9390 +Train: [56] [4700/6250] eta: 0:03:30 lr: 0.000054 grad: 0.0901 (0.0930) loss: 0.8191 (0.8213) time: 0.1249 data: 0.0390 max mem: 9390 +Train: [56] [4800/6250] eta: 0:03:16 lr: 0.000054 grad: 0.0878 (0.0930) loss: 0.8266 (0.8213) time: 0.1506 data: 0.0774 max mem: 9390 +Train: [56] [4900/6250] eta: 0:03:03 lr: 0.000054 grad: 0.0898 (0.0929) loss: 0.8187 (0.8213) time: 0.1504 data: 0.0678 max mem: 9390 +Train: [56] [5000/6250] eta: 0:02:50 lr: 0.000054 grad: 0.0951 (0.0929) loss: 0.8230 (0.8213) time: 0.1495 data: 0.0719 max mem: 9390 +Train: [56] [5100/6250] eta: 0:02:36 lr: 0.000054 grad: 0.0848 (0.0929) loss: 0.8283 (0.8214) time: 0.1227 data: 0.0399 max mem: 9390 +Train: [56] [5200/6250] eta: 0:02:22 lr: 0.000054 grad: 0.0975 (0.0929) loss: 0.8228 (0.8214) time: 0.1365 data: 0.0572 max mem: 9390 +Train: [56] [5300/6250] eta: 0:02:09 lr: 0.000054 grad: 0.0904 (0.0929) loss: 0.8183 (0.8214) time: 0.1415 data: 0.0617 max mem: 9390 +Train: [56] [5400/6250] eta: 0:01:55 lr: 0.000054 grad: 0.0860 (0.0928) loss: 0.8263 (0.8214) time: 0.1412 data: 0.0596 max mem: 9390 +Train: [56] [5500/6250] eta: 0:01:42 lr: 0.000053 grad: 0.0929 (0.0928) loss: 0.8220 (0.8214) time: 0.1396 data: 0.0610 max mem: 9390 +Train: [56] [5600/6250] eta: 0:01:28 lr: 0.000053 grad: 0.0933 (0.0929) loss: 0.8194 (0.8214) time: 0.1593 data: 0.0687 max mem: 9390 +Train: [56] [5700/6250] eta: 0:01:14 lr: 0.000053 grad: 0.0946 (0.0929) loss: 0.8234 (0.8214) time: 0.1283 data: 0.0522 max mem: 9390 +Train: [56] [5800/6250] eta: 0:01:01 lr: 0.000053 grad: 0.0919 (0.0929) loss: 0.8205 (0.8214) time: 0.1492 data: 0.0649 max mem: 9390 +Train: [56] [5900/6250] eta: 0:00:47 lr: 0.000053 grad: 0.0866 (0.0929) loss: 0.8236 (0.8215) time: 0.1423 data: 0.0618 max mem: 9390 +Train: [56] [6000/6250] eta: 0:00:34 lr: 0.000053 grad: 0.0998 (0.0929) loss: 0.8222 (0.8214) time: 0.1249 data: 0.0473 max mem: 9390 +Train: [56] [6100/6250] eta: 0:00:20 lr: 0.000053 grad: 0.0898 (0.0929) loss: 0.8201 (0.8214) time: 0.1383 data: 0.0592 max mem: 9390 +Train: [56] [6200/6250] eta: 0:00:06 lr: 0.000053 grad: 0.0934 (0.0929) loss: 0.8200 (0.8214) time: 0.1359 data: 0.0551 max mem: 9390 +Train: [56] [6249/6250] eta: 0:00:00 lr: 0.000053 grad: 0.0910 (0.0929) loss: 0.8205 (0.8214) time: 0.1321 data: 0.0456 max mem: 9390 +Train: [56] Total time: 0:14:14 (0.1368 s / it) +Averaged stats: lr: 0.000053 grad: 0.0910 (0.0929) loss: 0.8205 (0.8214) +Eval (hcp-train-subset): [56] [ 0/62] eta: 0:03:18 loss: 0.8429 (0.8429) time: 3.2079 data: 3.1181 max mem: 9390 +Eval (hcp-train-subset): [56] [61/62] eta: 0:00:00 loss: 0.8333 (0.8346) time: 0.1329 data: 0.1059 max mem: 9390 +Eval (hcp-train-subset): [56] Total time: 0:00:13 (0.2140 s / it) +Averaged stats (hcp-train-subset): loss: 0.8333 (0.8346) +Eval (hcp-val): [56] [ 0/62] eta: 0:04:57 loss: 0.8308 (0.8308) time: 4.8038 data: 4.7728 max mem: 9390 +Eval (hcp-val): [56] [61/62] eta: 0:00:00 loss: 0.8323 (0.8348) time: 0.1172 data: 0.0925 max mem: 9390 +Eval (hcp-val): [56] Total time: 0:00:12 (0.2056 s / it) +Averaged stats (hcp-val): loss: 0.8323 (0.8348) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +Train: [57] [ 0/6250] eta: 7:03:14 lr: 0.000053 grad: 0.4325 (0.4325) loss: 0.8195 (0.8195) time: 4.0631 data: 3.7717 max mem: 9390 +Train: [57] [ 100/6250] eta: 0:19:27 lr: 0.000053 grad: 0.0888 (0.1080) loss: 0.8228 (0.8148) time: 0.1491 data: 0.0530 max mem: 9390 +Train: [57] [ 200/6250] eta: 0:16:47 lr: 0.000053 grad: 0.0910 (0.1025) loss: 0.8209 (0.8168) time: 0.1248 data: 0.0461 max mem: 9390 +Train: [57] [ 300/6250] eta: 0:15:23 lr: 0.000053 grad: 0.0841 (0.1011) loss: 0.8188 (0.8180) time: 0.1403 data: 0.0613 max mem: 9390 +Train: [57] [ 400/6250] eta: 0:14:28 lr: 0.000053 grad: 0.0888 (0.0991) loss: 0.8244 (0.8194) time: 0.1218 data: 0.0354 max mem: 9390 +Train: [57] [ 500/6250] eta: 0:13:45 lr: 0.000053 grad: 0.0850 (0.0976) loss: 0.8267 (0.8203) time: 0.1015 data: 0.0080 max mem: 9390 +Train: [57] [ 600/6250] eta: 0:13:13 lr: 0.000053 grad: 0.0917 (0.0967) loss: 0.8242 (0.8213) time: 0.1293 data: 0.0430 max mem: 9390 +Train: [57] [ 700/6250] eta: 0:12:41 lr: 0.000053 grad: 0.0940 (0.0958) loss: 0.8273 (0.8219) time: 0.1102 data: 0.0160 max mem: 9390 +Train: [57] [ 800/6250] eta: 0:12:19 lr: 0.000053 grad: 0.0892 (0.0955) loss: 0.8191 (0.8221) time: 0.1199 data: 0.0343 max mem: 9390 +Train: [57] [ 900/6250] eta: 0:12:04 lr: 0.000053 grad: 0.0894 (0.0952) loss: 0.8202 (0.8221) time: 0.1241 data: 0.0479 max mem: 9390 +Train: [57] [1000/6250] eta: 0:12:04 lr: 0.000053 grad: 0.0915 (0.0950) loss: 0.8170 (0.8220) time: 0.1474 data: 0.0613 max mem: 9390 +Train: [57] [1100/6250] eta: 0:11:53 lr: 0.000053 grad: 0.0906 (0.0951) loss: 0.8132 (0.8218) time: 0.1360 data: 0.0583 max mem: 9390 +Train: [57] [1200/6250] eta: 0:11:37 lr: 0.000053 grad: 0.0965 (0.0950) loss: 0.8164 (0.8216) time: 0.1242 data: 0.0459 max mem: 9390 +Train: [57] [1300/6250] eta: 0:11:23 lr: 0.000053 grad: 0.0883 (0.0950) loss: 0.8184 (0.8213) time: 0.1447 data: 0.0643 max mem: 9390 +Train: [57] [1400/6250] eta: 0:11:07 lr: 0.000053 grad: 0.0925 (0.0948) loss: 0.8162 (0.8211) time: 0.1500 data: 0.0740 max mem: 9390 +Train: [57] [1500/6250] eta: 0:10:49 lr: 0.000053 grad: 0.1016 (0.0950) loss: 0.8231 (0.8208) time: 0.1244 data: 0.0405 max mem: 9390 +Train: [57] [1600/6250] eta: 0:10:30 lr: 0.000053 grad: 0.0867 (0.0952) loss: 0.8255 (0.8207) time: 0.1208 data: 0.0444 max mem: 9390 +Train: [57] [1700/6250] eta: 0:10:11 lr: 0.000053 grad: 0.0947 (0.0953) loss: 0.8156 (0.8204) time: 0.1160 data: 0.0340 max mem: 9390 +Train: [57] [1800/6250] eta: 0:09:53 lr: 0.000053 grad: 0.0912 (0.0953) loss: 0.8174 (0.8202) time: 0.1182 data: 0.0431 max mem: 9390 +Train: [57] [1900/6250] eta: 0:09:36 lr: 0.000053 grad: 0.0906 (0.0954) loss: 0.8202 (0.8201) time: 0.1194 data: 0.0393 max mem: 9390 +Train: [57] [2000/6250] eta: 0:09:20 lr: 0.000053 grad: 0.1010 (0.0954) loss: 0.8218 (0.8200) time: 0.1195 data: 0.0372 max mem: 9390 +Train: [57] [2100/6250] eta: 0:09:07 lr: 0.000053 grad: 0.0884 (0.0954) loss: 0.8262 (0.8201) time: 0.1409 data: 0.0668 max mem: 9390 +Train: [57] [2200/6250] eta: 0:08:57 lr: 0.000053 grad: 0.0912 (0.0953) loss: 0.8159 (0.8201) time: 0.1507 data: 0.0717 max mem: 9390 +Train: [57] [2300/6250] eta: 0:08:47 lr: 0.000052 grad: 0.0884 (0.0953) loss: 0.8149 (0.8200) time: 0.1661 data: 0.0883 max mem: 9390 +Train: [57] [2400/6250] eta: 0:08:36 lr: 0.000052 grad: 0.0903 (0.0951) loss: 0.8249 (0.8201) time: 0.1451 data: 0.0689 max mem: 9390 +Train: [57] [2500/6250] eta: 0:08:25 lr: 0.000052 grad: 0.0897 (0.0951) loss: 0.8182 (0.8201) time: 0.1654 data: 0.0842 max mem: 9390 +Train: [57] [2600/6250] eta: 0:08:13 lr: 0.000052 grad: 0.0889 (0.0950) loss: 0.8250 (0.8201) time: 0.1317 data: 0.0520 max mem: 9390 +Train: [57] [2700/6250] eta: 0:08:00 lr: 0.000052 grad: 0.0961 (0.0950) loss: 0.8157 (0.8201) time: 0.1369 data: 0.0548 max mem: 9390 +Train: [57] [2800/6250] eta: 0:07:48 lr: 0.000052 grad: 0.0919 (0.0950) loss: 0.8244 (0.8201) time: 0.1511 data: 0.0665 max mem: 9390 +Train: [57] [2900/6250] eta: 0:07:33 lr: 0.000052 grad: 0.0928 (0.0951) loss: 0.8202 (0.8201) time: 0.1251 data: 0.0365 max mem: 9390 +Train: [57] [3000/6250] eta: 0:07:19 lr: 0.000052 grad: 0.0925 (0.0952) loss: 0.8218 (0.8202) time: 0.1144 data: 0.0329 max mem: 9390 +Train: [57] [3100/6250] eta: 0:07:06 lr: 0.000052 grad: 0.0931 (0.0953) loss: 0.8204 (0.8201) time: 0.1500 data: 0.0673 max mem: 9390 +Train: [57] [3200/6250] eta: 0:06:52 lr: 0.000052 grad: 0.1003 (0.0954) loss: 0.8185 (0.8201) time: 0.1297 data: 0.0424 max mem: 9390 +Train: [57] [3300/6250] eta: 0:06:39 lr: 0.000052 grad: 0.0992 (0.0955) loss: 0.8144 (0.8201) time: 0.1317 data: 0.0538 max mem: 9390 +Train: [57] [3400/6250] eta: 0:06:25 lr: 0.000052 grad: 0.0915 (0.0955) loss: 0.8162 (0.8200) time: 0.1104 data: 0.0292 max mem: 9390 +Train: [57] [3500/6250] eta: 0:06:11 lr: 0.000052 grad: 0.0972 (0.0956) loss: 0.8192 (0.8200) time: 0.0997 data: 0.0206 max mem: 9390 +Train: [57] [3600/6250] eta: 0:05:57 lr: 0.000052 grad: 0.0893 (0.0957) loss: 0.8190 (0.8199) time: 0.1430 data: 0.0601 max mem: 9390 +Train: [57] [3700/6250] eta: 0:05:44 lr: 0.000052 grad: 0.1016 (0.0958) loss: 0.8116 (0.8198) time: 0.1173 data: 0.0317 max mem: 9390 +Train: [57] [3800/6250] eta: 0:05:30 lr: 0.000052 grad: 0.0949 (0.0959) loss: 0.8179 (0.8197) time: 0.1353 data: 0.0581 max mem: 9390 +Train: [57] [3900/6250] eta: 0:05:17 lr: 0.000052 grad: 0.0954 (0.0959) loss: 0.8171 (0.8197) time: 0.1347 data: 0.0574 max mem: 9390 +Train: [57] [4000/6250] eta: 0:05:04 lr: 0.000052 grad: 0.0901 (0.0960) loss: 0.8161 (0.8197) time: 0.1357 data: 0.0573 max mem: 9390 +Train: [57] [4100/6250] eta: 0:04:50 lr: 0.000052 grad: 0.0945 (0.0961) loss: 0.8154 (0.8196) time: 0.1333 data: 0.0482 max mem: 9390 +Train: [57] [4200/6250] eta: 0:04:37 lr: 0.000052 grad: 0.0933 (0.0962) loss: 0.8226 (0.8196) time: 0.1293 data: 0.0518 max mem: 9390 +Train: [57] [4300/6250] eta: 0:04:23 lr: 0.000052 grad: 0.1016 (0.0962) loss: 0.8181 (0.8195) time: 0.1498 data: 0.0762 max mem: 9390 +Train: [57] [4400/6250] eta: 0:04:10 lr: 0.000052 grad: 0.0939 (0.0963) loss: 0.8141 (0.8195) time: 0.1409 data: 0.0647 max mem: 9390 +Train: [57] [4500/6250] eta: 0:03:56 lr: 0.000052 grad: 0.0930 (0.0963) loss: 0.8198 (0.8194) time: 0.1476 data: 0.0705 max mem: 9390 +Train: [57] [4600/6250] eta: 0:03:43 lr: 0.000052 grad: 0.0921 (0.0963) loss: 0.8179 (0.8194) time: 0.1530 data: 0.0682 max mem: 9390 +Train: [57] [4700/6250] eta: 0:03:30 lr: 0.000052 grad: 0.0934 (0.0963) loss: 0.8264 (0.8195) time: 0.1715 data: 0.0890 max mem: 9390 +Train: [57] [4800/6250] eta: 0:03:16 lr: 0.000052 grad: 0.0931 (0.0963) loss: 0.8210 (0.8195) time: 0.1413 data: 0.0636 max mem: 9390 +Train: [57] [4900/6250] eta: 0:03:04 lr: 0.000052 grad: 0.0957 (0.0963) loss: 0.8182 (0.8195) time: 0.3825 data: 0.3041 max mem: 9390 +Train: [57] [5000/6250] eta: 0:02:50 lr: 0.000052 grad: 0.0912 (0.0963) loss: 0.8193 (0.8194) time: 0.1314 data: 0.0475 max mem: 9390 +Train: [57] [5100/6250] eta: 0:02:36 lr: 0.000052 grad: 0.0951 (0.0963) loss: 0.8141 (0.8193) time: 0.1145 data: 0.0321 max mem: 9390 +Train: [57] [5200/6250] eta: 0:02:23 lr: 0.000052 grad: 0.0953 (0.0964) loss: 0.8112 (0.8192) time: 0.1483 data: 0.0696 max mem: 9390 +Train: [57] [5300/6250] eta: 0:02:09 lr: 0.000052 grad: 0.0929 (0.0964) loss: 0.8220 (0.8192) time: 0.1707 data: 0.0827 max mem: 9390 +Train: [57] [5400/6250] eta: 0:01:56 lr: 0.000051 grad: 0.0966 (0.0964) loss: 0.8121 (0.8191) time: 0.1007 data: 0.0244 max mem: 9390 +Train: [57] [5500/6250] eta: 0:01:42 lr: 0.000051 grad: 0.0951 (0.0965) loss: 0.8193 (0.8191) time: 0.1267 data: 0.0497 max mem: 9390 +Train: [57] [5600/6250] eta: 0:01:28 lr: 0.000051 grad: 0.0978 (0.0965) loss: 0.8148 (0.8190) time: 0.1730 data: 0.0924 max mem: 9390 +Train: [57] [5700/6250] eta: 0:01:15 lr: 0.000051 grad: 0.0975 (0.0966) loss: 0.8153 (0.8190) time: 0.1331 data: 0.0564 max mem: 9390 +Train: [57] [5800/6250] eta: 0:01:01 lr: 0.000051 grad: 0.0949 (0.0966) loss: 0.8163 (0.8189) time: 0.1355 data: 0.0553 max mem: 9390 +Train: [57] [5900/6250] eta: 0:00:47 lr: 0.000051 grad: 0.0945 (0.0967) loss: 0.8161 (0.8189) time: 0.1149 data: 0.0324 max mem: 9390 +Train: [57] [6000/6250] eta: 0:00:34 lr: 0.000051 grad: 0.0898 (0.0967) loss: 0.8217 (0.8189) time: 0.1378 data: 0.0559 max mem: 9390 +Train: [57] [6100/6250] eta: 0:00:20 lr: 0.000051 grad: 0.0976 (0.0968) loss: 0.8143 (0.8188) time: 0.1584 data: 0.0727 max mem: 9390 +Train: [57] [6200/6250] eta: 0:00:06 lr: 0.000051 grad: 0.0955 (0.0968) loss: 0.8154 (0.8187) time: 0.1173 data: 0.0338 max mem: 9390 +Train: [57] [6249/6250] eta: 0:00:00 lr: 0.000051 grad: 0.0931 (0.0968) loss: 0.8175 (0.8187) time: 0.1513 data: 0.0769 max mem: 9390 +Train: [57] Total time: 0:14:18 (0.1374 s / it) +Averaged stats: lr: 0.000051 grad: 0.0931 (0.0968) loss: 0.8175 (0.8187) +Eval (hcp-train-subset): [57] [ 0/62] eta: 0:04:13 loss: 0.8417 (0.8417) time: 4.0825 data: 4.0453 max mem: 9390 +Eval (hcp-train-subset): [57] [61/62] eta: 0:00:00 loss: 0.8297 (0.8318) time: 0.1211 data: 0.0957 max mem: 9390 +Eval (hcp-train-subset): [57] Total time: 0:00:12 (0.2012 s / it) +Averaged stats (hcp-train-subset): loss: 0.8297 (0.8318) +Eval (hcp-val): [57] [ 0/62] eta: 0:04:26 loss: 0.8333 (0.8333) time: 4.2917 data: 4.2501 max mem: 9390 +Eval (hcp-val): [57] [61/62] eta: 0:00:00 loss: 0.8316 (0.8339) time: 0.1311 data: 0.1062 max mem: 9390 +Eval (hcp-val): [57] Total time: 0:00:12 (0.2074 s / it) +Averaged stats (hcp-val): loss: 0.8316 (0.8339) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +Train: [58] [ 0/6250] eta: 8:49:26 lr: 0.000051 grad: 0.0842 (0.0842) loss: 0.8590 (0.8590) time: 5.0826 data: 4.9315 max mem: 9390 +Train: [58] [ 100/6250] eta: 0:19:57 lr: 0.000051 grad: 0.1002 (0.1085) loss: 0.8208 (0.8323) time: 0.1509 data: 0.0567 max mem: 9390 +Train: [58] [ 200/6250] eta: 0:16:44 lr: 0.000051 grad: 0.0868 (0.1025) loss: 0.8322 (0.8280) time: 0.1396 data: 0.0453 max mem: 9390 +Train: [58] [ 300/6250] eta: 0:15:31 lr: 0.000051 grad: 0.0899 (0.0982) loss: 0.8291 (0.8275) time: 0.1395 data: 0.0481 max mem: 9390 +Train: [58] [ 400/6250] eta: 0:14:42 lr: 0.000051 grad: 0.0903 (0.0975) loss: 0.8283 (0.8270) time: 0.1406 data: 0.0603 max mem: 9390 +Train: [58] [ 500/6250] eta: 0:13:52 lr: 0.000051 grad: 0.0932 (0.0974) loss: 0.8274 (0.8260) time: 0.1368 data: 0.0508 max mem: 9390 +Train: [58] [ 600/6250] eta: 0:13:15 lr: 0.000051 grad: 0.0943 (0.0972) loss: 0.8255 (0.8251) time: 0.1273 data: 0.0348 max mem: 9390 +Train: [58] [ 700/6250] eta: 0:12:45 lr: 0.000051 grad: 0.0920 (0.0968) loss: 0.8244 (0.8248) time: 0.1122 data: 0.0297 max mem: 9390 +Train: [58] [ 800/6250] eta: 0:12:23 lr: 0.000051 grad: 0.0914 (0.0966) loss: 0.8218 (0.8244) time: 0.1292 data: 0.0444 max mem: 9390 +Train: [58] [ 900/6250] eta: 0:12:04 lr: 0.000051 grad: 0.0883 (0.0963) loss: 0.8271 (0.8243) time: 0.1297 data: 0.0469 max mem: 9390 +Train: [58] [1000/6250] eta: 0:11:52 lr: 0.000051 grad: 0.0928 (0.0960) loss: 0.8250 (0.8243) time: 0.1790 data: 0.1002 max mem: 9390 +Train: [58] [1100/6250] eta: 0:11:44 lr: 0.000051 grad: 0.0895 (0.0959) loss: 0.8227 (0.8241) time: 0.1376 data: 0.0517 max mem: 9390 +Train: [58] [1200/6250] eta: 0:11:33 lr: 0.000051 grad: 0.0971 (0.0957) loss: 0.8194 (0.8242) time: 0.1374 data: 0.0644 max mem: 9390 +Train: [58] [1300/6250] eta: 0:11:20 lr: 0.000051 grad: 0.0949 (0.0956) loss: 0.8226 (0.8242) time: 0.1549 data: 0.0781 max mem: 9390 +Train: [58] [1400/6250] eta: 0:11:04 lr: 0.000051 grad: 0.0850 (0.0956) loss: 0.8241 (0.8241) time: 0.1367 data: 0.0588 max mem: 9390 +Train: [58] [1500/6250] eta: 0:10:49 lr: 0.000051 grad: 0.0945 (0.0955) loss: 0.8186 (0.8240) time: 0.1319 data: 0.0509 max mem: 9390 +Train: [58] [1600/6250] eta: 0:10:33 lr: 0.000051 grad: 0.0921 (0.0955) loss: 0.8195 (0.8240) time: 0.1367 data: 0.0591 max mem: 9390 +Train: [58] [1700/6250] eta: 0:10:16 lr: 0.000051 grad: 0.0925 (0.0954) loss: 0.8239 (0.8240) time: 0.1209 data: 0.0390 max mem: 9390 +Train: [58] [1800/6250] eta: 0:09:58 lr: 0.000051 grad: 0.0905 (0.0953) loss: 0.8161 (0.8240) time: 0.1120 data: 0.0207 max mem: 9390 +Train: [58] [1900/6250] eta: 0:09:39 lr: 0.000051 grad: 0.0970 (0.0954) loss: 0.8181 (0.8239) time: 0.1090 data: 0.0197 max mem: 9390 +Train: [58] [2000/6250] eta: 0:09:22 lr: 0.000051 grad: 0.0943 (0.0954) loss: 0.8180 (0.8238) time: 0.1231 data: 0.0419 max mem: 9390 +Train: [58] [2100/6250] eta: 0:09:09 lr: 0.000051 grad: 0.0972 (0.0953) loss: 0.8237 (0.8236) time: 0.1308 data: 0.0487 max mem: 9390 +Train: [58] [2200/6250] eta: 0:09:00 lr: 0.000050 grad: 0.0921 (0.0953) loss: 0.8212 (0.8235) time: 0.1713 data: 0.0965 max mem: 9390 +Train: [58] [2300/6250] eta: 0:08:49 lr: 0.000050 grad: 0.0954 (0.0954) loss: 0.8167 (0.8233) time: 0.1713 data: 0.0892 max mem: 9390 +Train: [58] [2400/6250] eta: 0:08:38 lr: 0.000050 grad: 0.0928 (0.0954) loss: 0.8242 (0.8231) time: 0.1404 data: 0.0582 max mem: 9390 +Train: [58] [2500/6250] eta: 0:08:27 lr: 0.000050 grad: 0.1010 (0.0956) loss: 0.8049 (0.8228) time: 0.1469 data: 0.0610 max mem: 9390 +Train: [58] [2600/6250] eta: 0:08:16 lr: 0.000050 grad: 0.0910 (0.0957) loss: 0.8199 (0.8226) time: 0.1254 data: 0.0425 max mem: 9390 +Train: [58] [2700/6250] eta: 0:08:04 lr: 0.000050 grad: 0.0963 (0.0958) loss: 0.8165 (0.8224) time: 0.1600 data: 0.0838 max mem: 9390 +Train: [58] [2800/6250] eta: 0:07:50 lr: 0.000050 grad: 0.0942 (0.0959) loss: 0.8119 (0.8223) time: 0.1176 data: 0.0332 max mem: 9390 +Train: [58] [2900/6250] eta: 0:07:35 lr: 0.000050 grad: 0.0910 (0.0960) loss: 0.8241 (0.8222) time: 0.1342 data: 0.0564 max mem: 9390 +Train: [58] [3000/6250] eta: 0:07:21 lr: 0.000050 grad: 0.0979 (0.0961) loss: 0.8180 (0.8220) time: 0.1214 data: 0.0427 max mem: 9390 +Train: [58] [3100/6250] eta: 0:07:08 lr: 0.000050 grad: 0.0977 (0.0961) loss: 0.8211 (0.8219) time: 0.1397 data: 0.0630 max mem: 9390 +Train: [58] [3200/6250] eta: 0:06:54 lr: 0.000050 grad: 0.0912 (0.0962) loss: 0.8216 (0.8218) time: 0.1130 data: 0.0318 max mem: 9390 +Train: [58] [3300/6250] eta: 0:06:41 lr: 0.000050 grad: 0.0957 (0.0963) loss: 0.8227 (0.8217) time: 0.1331 data: 0.0481 max mem: 9390 +Train: [58] [3400/6250] eta: 0:06:27 lr: 0.000050 grad: 0.0904 (0.0963) loss: 0.8199 (0.8216) time: 0.1175 data: 0.0337 max mem: 9390 +Train: [58] [3500/6250] eta: 0:06:14 lr: 0.000050 grad: 0.0900 (0.0963) loss: 0.8211 (0.8216) time: 0.1456 data: 0.0667 max mem: 9390 +Train: [58] [3600/6250] eta: 0:06:00 lr: 0.000050 grad: 0.0960 (0.0963) loss: 0.8244 (0.8215) time: 0.1306 data: 0.0449 max mem: 9390 +Train: [58] [3700/6250] eta: 0:05:46 lr: 0.000050 grad: 0.1002 (0.0964) loss: 0.8208 (0.8214) time: 0.1348 data: 0.0549 max mem: 9390 +Train: [58] [3800/6250] eta: 0:05:33 lr: 0.000050 grad: 0.0987 (0.0966) loss: 0.8177 (0.8212) time: 0.1678 data: 0.0660 max mem: 9390 +Train: [58] [3900/6250] eta: 0:05:21 lr: 0.000050 grad: 0.0977 (0.0967) loss: 0.8134 (0.8210) time: 0.1403 data: 0.0609 max mem: 9390 +Train: [58] [4000/6250] eta: 0:05:07 lr: 0.000050 grad: 0.0982 (0.0969) loss: 0.8176 (0.8209) time: 0.1440 data: 0.0559 max mem: 9390 +Train: [58] [4100/6250] eta: 0:04:53 lr: 0.000050 grad: 0.0948 (0.0970) loss: 0.8151 (0.8207) time: 0.1202 data: 0.0443 max mem: 9390 +Train: [58] [4200/6250] eta: 0:04:39 lr: 0.000050 grad: 0.0985 (0.0970) loss: 0.8117 (0.8206) time: 0.1285 data: 0.0483 max mem: 9390 +Train: [58] [4300/6250] eta: 0:04:26 lr: 0.000050 grad: 0.0957 (0.0971) loss: 0.8237 (0.8205) time: 0.1340 data: 0.0501 max mem: 9390 +Train: [58] [4400/6250] eta: 0:04:12 lr: 0.000050 grad: 0.0972 (0.0973) loss: 0.8142 (0.8204) time: 0.1445 data: 0.0527 max mem: 9390 +Train: [58] [4500/6250] eta: 0:03:59 lr: 0.000050 grad: 0.1057 (0.0975) loss: 0.8106 (0.8202) time: 0.1361 data: 0.0546 max mem: 9390 +Train: [58] [4600/6250] eta: 0:03:45 lr: 0.000050 grad: 0.1009 (0.0976) loss: 0.8155 (0.8200) time: 0.1191 data: 0.0392 max mem: 9390 +Train: [58] [4700/6250] eta: 0:03:31 lr: 0.000050 grad: 0.1027 (0.0977) loss: 0.8192 (0.8198) time: 0.1895 data: 0.0952 max mem: 9390 +Train: [58] [4800/6250] eta: 0:03:18 lr: 0.000050 grad: 0.0986 (0.0978) loss: 0.8219 (0.8197) time: 0.1387 data: 0.0573 max mem: 9390 +Train: [58] [4900/6250] eta: 0:03:04 lr: 0.000050 grad: 0.0959 (0.0978) loss: 0.8095 (0.8195) time: 0.1189 data: 0.0417 max mem: 9390 +Train: [58] [5000/6250] eta: 0:02:50 lr: 0.000050 grad: 0.0979 (0.0978) loss: 0.8130 (0.8194) time: 0.1234 data: 0.0358 max mem: 9390 +Train: [58] [5100/6250] eta: 0:02:37 lr: 0.000050 grad: 0.1024 (0.0979) loss: 0.8063 (0.8193) time: 0.1156 data: 0.0380 max mem: 9390 +Train: [58] [5200/6250] eta: 0:02:23 lr: 0.000050 grad: 0.0957 (0.0980) loss: 0.8186 (0.8191) time: 0.1819 data: 0.1035 max mem: 9390 +Train: [58] [5300/6250] eta: 0:02:10 lr: 0.000049 grad: 0.1012 (0.0980) loss: 0.8114 (0.8191) time: 0.1221 data: 0.0426 max mem: 9390 +Train: [58] [5400/6250] eta: 0:01:56 lr: 0.000049 grad: 0.0964 (0.0981) loss: 0.8193 (0.8190) time: 0.1575 data: 0.0767 max mem: 9390 +Train: [58] [5500/6250] eta: 0:01:42 lr: 0.000049 grad: 0.0957 (0.0981) loss: 0.8151 (0.8190) time: 0.1369 data: 0.0523 max mem: 9390 +Train: [58] [5600/6250] eta: 0:01:29 lr: 0.000049 grad: 0.0940 (0.0980) loss: 0.8184 (0.8190) time: 0.1373 data: 0.0499 max mem: 9390 +Train: [58] [5700/6250] eta: 0:01:15 lr: 0.000049 grad: 0.0966 (0.0981) loss: 0.8203 (0.8190) time: 0.1011 data: 0.0201 max mem: 9390 +Train: [58] [5800/6250] eta: 0:01:01 lr: 0.000049 grad: 0.0986 (0.0981) loss: 0.8155 (0.8190) time: 0.1522 data: 0.0587 max mem: 9390 +Train: [58] [5900/6250] eta: 0:00:47 lr: 0.000049 grad: 0.1033 (0.0982) loss: 0.8191 (0.8189) time: 0.1285 data: 0.0468 max mem: 9390 +Train: [58] [6000/6250] eta: 0:00:34 lr: 0.000049 grad: 0.0958 (0.0982) loss: 0.8162 (0.8188) time: 0.1274 data: 0.0387 max mem: 9390 +Train: [58] [6100/6250] eta: 0:00:20 lr: 0.000049 grad: 0.0928 (0.0982) loss: 0.8200 (0.8188) time: 0.1444 data: 0.0652 max mem: 9390 +Train: [58] [6200/6250] eta: 0:00:06 lr: 0.000049 grad: 0.0970 (0.0982) loss: 0.8195 (0.8188) time: 0.1294 data: 0.0509 max mem: 9390 +Train: [58] [6249/6250] eta: 0:00:00 lr: 0.000049 grad: 0.0953 (0.0982) loss: 0.8162 (0.8188) time: 0.1554 data: 0.0760 max mem: 9390 +Train: [58] Total time: 0:14:20 (0.1376 s / it) +Averaged stats: lr: 0.000049 grad: 0.0953 (0.0982) loss: 0.8162 (0.8188) +Eval (hcp-train-subset): [58] [ 0/62] eta: 0:04:02 loss: 0.8443 (0.8443) time: 3.9098 data: 3.8356 max mem: 9390 +Eval (hcp-train-subset): [58] [61/62] eta: 0:00:00 loss: 0.8334 (0.8346) time: 0.1312 data: 0.1058 max mem: 9390 +Eval (hcp-train-subset): [58] Total time: 0:00:12 (0.2042 s / it) +Averaged stats (hcp-train-subset): loss: 0.8334 (0.8346) +Eval (hcp-val): [58] [ 0/62] eta: 0:03:23 loss: 0.8402 (0.8402) time: 3.2859 data: 3.2040 max mem: 9390 +Eval (hcp-val): [58] [61/62] eta: 0:00:00 loss: 0.8333 (0.8350) time: 0.1359 data: 0.1107 max mem: 9390 +Eval (hcp-val): [58] Total time: 0:00:13 (0.2106 s / it) +Averaged stats (hcp-val): loss: 0.8333 (0.8350) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +Train: [59] [ 0/6250] eta: 9:14:54 lr: 0.000049 grad: 0.1209 (0.1209) loss: 0.8414 (0.8414) time: 5.3272 data: 5.1876 max mem: 9390 +Train: [59] [ 100/6250] eta: 0:19:08 lr: 0.000049 grad: 0.0877 (0.1137) loss: 0.8285 (0.8251) time: 0.1337 data: 0.0309 max mem: 9390 +Train: [59] [ 200/6250] eta: 0:16:46 lr: 0.000049 grad: 0.0953 (0.1117) loss: 0.8095 (0.8227) time: 0.1565 data: 0.0662 max mem: 9390 +Train: [59] [ 300/6250] eta: 0:15:35 lr: 0.000049 grad: 0.0893 (0.1090) loss: 0.8139 (0.8205) time: 0.1351 data: 0.0504 max mem: 9390 +Train: [59] [ 400/6250] eta: 0:14:44 lr: 0.000049 grad: 0.0947 (0.1068) loss: 0.8243 (0.8194) time: 0.1341 data: 0.0521 max mem: 9390 +Train: [59] [ 500/6250] eta: 0:14:01 lr: 0.000049 grad: 0.0882 (0.1048) loss: 0.8204 (0.8193) time: 0.1297 data: 0.0454 max mem: 9390 +Train: [59] [ 600/6250] eta: 0:13:25 lr: 0.000049 grad: 0.0957 (0.1032) loss: 0.8105 (0.8194) time: 0.1344 data: 0.0428 max mem: 9390 +Train: [59] [ 700/6250] eta: 0:12:59 lr: 0.000049 grad: 0.0952 (0.1025) loss: 0.8147 (0.8188) time: 0.1357 data: 0.0487 max mem: 9390 +Train: [59] [ 800/6250] eta: 0:12:35 lr: 0.000049 grad: 0.0905 (0.1016) loss: 0.8145 (0.8186) time: 0.1274 data: 0.0437 max mem: 9390 +Train: [59] [ 900/6250] eta: 0:12:15 lr: 0.000049 grad: 0.0863 (0.1011) loss: 0.8286 (0.8185) time: 0.1158 data: 0.0355 max mem: 9390 +Train: [59] [1000/6250] eta: 0:12:01 lr: 0.000049 grad: 0.0896 (0.1003) loss: 0.8122 (0.8185) time: 0.1078 data: 0.0250 max mem: 9390 +Train: [59] [1100/6250] eta: 0:11:51 lr: 0.000049 grad: 0.0924 (0.1002) loss: 0.8190 (0.8183) time: 0.1590 data: 0.0825 max mem: 9390 +Train: [59] [1200/6250] eta: 0:11:44 lr: 0.000049 grad: 0.0889 (0.0998) loss: 0.8210 (0.8184) time: 0.1441 data: 0.0637 max mem: 9390 +Train: [59] [1300/6250] eta: 0:11:32 lr: 0.000049 grad: 0.0943 (0.0995) loss: 0.8164 (0.8182) time: 0.1377 data: 0.0612 max mem: 9390 +Train: [59] [1400/6250] eta: 0:11:18 lr: 0.000049 grad: 0.0892 (0.0993) loss: 0.8283 (0.8183) time: 0.1342 data: 0.0497 max mem: 9390 +Train: [59] [1500/6250] eta: 0:11:02 lr: 0.000049 grad: 0.0965 (0.0991) loss: 0.8166 (0.8183) time: 0.1309 data: 0.0492 max mem: 9390 +Train: [59] [1600/6250] eta: 0:10:47 lr: 0.000049 grad: 0.0948 (0.0988) loss: 0.8117 (0.8181) time: 0.1254 data: 0.0451 max mem: 9390 +Train: [59] [1700/6250] eta: 0:10:30 lr: 0.000049 grad: 0.0932 (0.0988) loss: 0.8146 (0.8180) time: 0.1210 data: 0.0437 max mem: 9390 +Train: [59] [1800/6250] eta: 0:10:11 lr: 0.000049 grad: 0.0893 (0.0987) loss: 0.8178 (0.8179) time: 0.1243 data: 0.0442 max mem: 9390 +Train: [59] [1900/6250] eta: 0:09:53 lr: 0.000049 grad: 0.0886 (0.0984) loss: 0.8180 (0.8178) time: 0.1200 data: 0.0426 max mem: 9390 +Train: [59] [2000/6250] eta: 0:09:35 lr: 0.000049 grad: 0.0962 (0.0983) loss: 0.8165 (0.8178) time: 0.1287 data: 0.0431 max mem: 9390 +Train: [59] [2100/6250] eta: 0:09:17 lr: 0.000048 grad: 0.0916 (0.0983) loss: 0.8190 (0.8179) time: 0.1183 data: 0.0345 max mem: 9390 +Train: [59] [2200/6250] eta: 0:09:04 lr: 0.000048 grad: 0.0919 (0.0981) loss: 0.8168 (0.8180) time: 0.1490 data: 0.0658 max mem: 9390 +Train: [59] [2300/6250] eta: 0:08:55 lr: 0.000048 grad: 0.0897 (0.0979) loss: 0.8250 (0.8181) time: 0.1614 data: 0.0858 max mem: 9390 +Train: [59] [2400/6250] eta: 0:08:47 lr: 0.000048 grad: 0.0923 (0.0977) loss: 0.8200 (0.8182) time: 0.1589 data: 0.0631 max mem: 9390 +Train: [59] [2500/6250] eta: 0:08:35 lr: 0.000048 grad: 0.0903 (0.0976) loss: 0.8186 (0.8182) time: 0.1371 data: 0.0536 max mem: 9390 +Train: [59] [2600/6250] eta: 0:08:24 lr: 0.000048 grad: 0.0922 (0.0978) loss: 0.8196 (0.8182) time: 0.1429 data: 0.0646 max mem: 9390 +Train: [59] [2700/6250] eta: 0:08:09 lr: 0.000048 grad: 0.0936 (0.0978) loss: 0.8159 (0.8182) time: 0.1369 data: 0.0543 max mem: 9390 +Train: [59] [2800/6250] eta: 0:07:55 lr: 0.000048 grad: 0.0925 (0.0979) loss: 0.8196 (0.8182) time: 0.1397 data: 0.0552 max mem: 9390 +Train: [59] [2900/6250] eta: 0:07:41 lr: 0.000048 grad: 0.0937 (0.0979) loss: 0.8176 (0.8181) time: 0.1233 data: 0.0371 max mem: 9390 +Train: [59] [3000/6250] eta: 0:07:26 lr: 0.000048 grad: 0.0906 (0.0979) loss: 0.8231 (0.8182) time: 0.1603 data: 0.0762 max mem: 9390 +Train: [59] [3100/6250] eta: 0:07:12 lr: 0.000048 grad: 0.0958 (0.0980) loss: 0.8152 (0.8181) time: 0.1455 data: 0.0661 max mem: 9390 +Train: [59] [3200/6250] eta: 0:06:58 lr: 0.000048 grad: 0.0914 (0.0981) loss: 0.8224 (0.8181) time: 0.1438 data: 0.0628 max mem: 9390 +Train: [59] [3300/6250] eta: 0:06:44 lr: 0.000048 grad: 0.0960 (0.0981) loss: 0.8168 (0.8180) time: 0.1435 data: 0.0643 max mem: 9390 +Train: [59] [3400/6250] eta: 0:06:31 lr: 0.000048 grad: 0.0913 (0.0981) loss: 0.8203 (0.8180) time: 0.1631 data: 0.0797 max mem: 9390 +Train: [59] [3500/6250] eta: 0:06:17 lr: 0.000048 grad: 0.0969 (0.0981) loss: 0.8168 (0.8181) time: 0.1364 data: 0.0570 max mem: 9390 +Train: [59] [3600/6250] eta: 0:06:03 lr: 0.000048 grad: 0.0969 (0.0981) loss: 0.8188 (0.8181) time: 0.1326 data: 0.0510 max mem: 9390 +Train: [59] [3700/6250] eta: 0:05:49 lr: 0.000048 grad: 0.0919 (0.0980) loss: 0.8208 (0.8181) time: 0.1501 data: 0.0696 max mem: 9390 +Train: [59] [3800/6250] eta: 0:05:35 lr: 0.000048 grad: 0.0958 (0.0980) loss: 0.8214 (0.8181) time: 0.1318 data: 0.0568 max mem: 9390 +Train: [59] [3900/6250] eta: 0:05:21 lr: 0.000048 grad: 0.0945 (0.0980) loss: 0.8152 (0.8181) time: 0.1140 data: 0.0316 max mem: 9390 +Train: [59] [4000/6250] eta: 0:05:07 lr: 0.000048 grad: 0.0938 (0.0979) loss: 0.8201 (0.8180) time: 0.1171 data: 0.0395 max mem: 9390 +Train: [59] [4100/6250] eta: 0:04:53 lr: 0.000048 grad: 0.0996 (0.0979) loss: 0.8184 (0.8180) time: 0.1300 data: 0.0495 max mem: 9390 +Train: [59] [4200/6250] eta: 0:04:40 lr: 0.000048 grad: 0.0891 (0.0979) loss: 0.8182 (0.8180) time: 0.1334 data: 0.0540 max mem: 9390 +Train: [59] [4300/6250] eta: 0:04:26 lr: 0.000048 grad: 0.0959 (0.0980) loss: 0.8171 (0.8180) time: 0.1413 data: 0.0499 max mem: 9390 +Train: [59] [4400/6250] eta: 0:04:12 lr: 0.000048 grad: 0.1022 (0.0980) loss: 0.8154 (0.8179) time: 0.1424 data: 0.0593 max mem: 9390 +Train: [59] [4500/6250] eta: 0:03:59 lr: 0.000048 grad: 0.0994 (0.0980) loss: 0.8192 (0.8179) time: 0.1180 data: 0.0382 max mem: 9390 +Train: [59] [4600/6250] eta: 0:03:45 lr: 0.000048 grad: 0.0927 (0.0981) loss: 0.8127 (0.8178) time: 0.1317 data: 0.0491 max mem: 9390 +Train: [59] [4700/6250] eta: 0:03:31 lr: 0.000048 grad: 0.0962 (0.0981) loss: 0.8111 (0.8178) time: 0.1326 data: 0.0478 max mem: 9390 +Train: [59] [4800/6250] eta: 0:03:17 lr: 0.000048 grad: 0.0912 (0.0981) loss: 0.8230 (0.8178) time: 0.1315 data: 0.0468 max mem: 9390 +Train: [59] [4900/6250] eta: 0:03:04 lr: 0.000048 grad: 0.0917 (0.0982) loss: 0.8150 (0.8177) time: 0.1185 data: 0.0320 max mem: 9390 +Train: [59] [5000/6250] eta: 0:02:50 lr: 0.000048 grad: 0.0978 (0.0983) loss: 0.8126 (0.8176) time: 0.1405 data: 0.0625 max mem: 9390 +Train: [59] [5100/6250] eta: 0:02:37 lr: 0.000048 grad: 0.1031 (0.0983) loss: 0.8121 (0.8176) time: 0.1587 data: 0.0837 max mem: 9390 +Train: [59] [5200/6250] eta: 0:02:23 lr: 0.000047 grad: 0.0989 (0.0983) loss: 0.8155 (0.8176) time: 0.1486 data: 0.0626 max mem: 9390 +Train: [59] [5300/6250] eta: 0:02:09 lr: 0.000047 grad: 0.0985 (0.0984) loss: 0.8114 (0.8175) time: 0.1164 data: 0.0365 max mem: 9390 +Train: [59] [5400/6250] eta: 0:01:56 lr: 0.000047 grad: 0.0967 (0.0984) loss: 0.8162 (0.8174) time: 0.1242 data: 0.0415 max mem: 9390 +Train: [59] [5500/6250] eta: 0:01:42 lr: 0.000047 grad: 0.0962 (0.0985) loss: 0.8190 (0.8174) time: 0.1370 data: 0.0582 max mem: 9390 +Train: [59] [5600/6250] eta: 0:01:28 lr: 0.000047 grad: 0.1056 (0.0986) loss: 0.8232 (0.8174) time: 0.1455 data: 0.0660 max mem: 9390 +Train: [59] [5700/6250] eta: 0:01:15 lr: 0.000047 grad: 0.0964 (0.0986) loss: 0.8143 (0.8174) time: 0.1418 data: 0.0597 max mem: 9390 +Train: [59] [5800/6250] eta: 0:01:01 lr: 0.000047 grad: 0.1020 (0.0987) loss: 0.8177 (0.8174) time: 0.1214 data: 0.0379 max mem: 9390 +Train: [59] [5900/6250] eta: 0:00:47 lr: 0.000047 grad: 0.1010 (0.0987) loss: 0.8171 (0.8174) time: 0.1294 data: 0.0466 max mem: 9390 +Train: [59] [6000/6250] eta: 0:00:34 lr: 0.000047 grad: 0.1031 (0.0988) loss: 0.8185 (0.8174) time: 0.1202 data: 0.0391 max mem: 9390 +Train: [59] [6100/6250] eta: 0:00:20 lr: 0.000047 grad: 0.1044 (0.0988) loss: 0.8141 (0.8174) time: 0.1388 data: 0.0558 max mem: 9390 +Train: [59] [6200/6250] eta: 0:00:06 lr: 0.000047 grad: 0.1008 (0.0989) loss: 0.8157 (0.8174) time: 0.1306 data: 0.0479 max mem: 9390 +Train: [59] [6249/6250] eta: 0:00:00 lr: 0.000047 grad: 0.0950 (0.0988) loss: 0.8203 (0.8174) time: 0.1335 data: 0.0418 max mem: 9390 +Train: [59] Total time: 0:14:18 (0.1373 s / it) +Averaged stats: lr: 0.000047 grad: 0.0950 (0.0988) loss: 0.8203 (0.8174) +Eval (hcp-train-subset): [59] [ 0/62] eta: 0:03:15 loss: 0.8434 (0.8434) time: 3.1496 data: 3.0738 max mem: 9390 +Eval (hcp-train-subset): [59] [61/62] eta: 0:00:00 loss: 0.8336 (0.8337) time: 0.1142 data: 0.0893 max mem: 9390 +Eval (hcp-train-subset): [59] Total time: 0:00:12 (0.2060 s / it) +Averaged stats (hcp-train-subset): loss: 0.8336 (0.8337) +Making plots (hcp-train-subset): example=21 +Eval (hcp-val): [59] [ 0/62] eta: 0:03:17 loss: 0.8318 (0.8318) time: 3.1887 data: 3.1111 max mem: 9390 +Eval (hcp-val): [59] [61/62] eta: 0:00:00 loss: 0.8336 (0.8342) time: 0.1220 data: 0.0972 max mem: 9390 +Eval (hcp-val): [59] Total time: 0:00:12 (0.2066 s / it) +Averaged stats (hcp-val): loss: 0.8336 (0.8342) +Making plots (hcp-val): example=2 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +Train: [60] [ 0/6250] eta: 8:51:12 lr: 0.000047 grad: 0.1103 (0.1103) loss: 0.8590 (0.8590) time: 5.0995 data: 4.9819 max mem: 9390 +Train: [60] [ 100/6250] eta: 0:19:14 lr: 0.000047 grad: 0.0894 (0.1018) loss: 0.8302 (0.8287) time: 0.1429 data: 0.0500 max mem: 9390 +Train: [60] [ 200/6250] eta: 0:16:36 lr: 0.000047 grad: 0.0850 (0.0994) loss: 0.8289 (0.8265) time: 0.1300 data: 0.0387 max mem: 9390 +Train: [60] [ 300/6250] eta: 0:15:21 lr: 0.000047 grad: 0.0968 (0.0998) loss: 0.8250 (0.8244) time: 0.1077 data: 0.0230 max mem: 9390 +Train: [60] [ 400/6250] eta: 0:14:26 lr: 0.000047 grad: 0.0927 (0.0994) loss: 0.8206 (0.8230) time: 0.1425 data: 0.0542 max mem: 9390 +Train: [60] [ 500/6250] eta: 0:13:47 lr: 0.000047 grad: 0.1025 (0.0990) loss: 0.8162 (0.8220) time: 0.1332 data: 0.0481 max mem: 9390 +Train: [60] [ 600/6250] eta: 0:13:14 lr: 0.000047 grad: 0.0962 (0.0987) loss: 0.8166 (0.8211) time: 0.1360 data: 0.0521 max mem: 9390 +Train: [60] [ 700/6250] eta: 0:12:46 lr: 0.000047 grad: 0.0902 (0.0983) loss: 0.8209 (0.8203) time: 0.1287 data: 0.0511 max mem: 9390 +Train: [60] [ 800/6250] eta: 0:12:24 lr: 0.000047 grad: 0.0925 (0.0977) loss: 0.8156 (0.8201) time: 0.1200 data: 0.0367 max mem: 9390 +Train: [60] [ 900/6250] eta: 0:12:07 lr: 0.000047 grad: 0.0914 (0.0973) loss: 0.8140 (0.8199) time: 0.1506 data: 0.0662 max mem: 9390 +Train: [60] [1000/6250] eta: 0:11:55 lr: 0.000047 grad: 0.0918 (0.0967) loss: 0.8199 (0.8202) time: 0.1296 data: 0.0506 max mem: 9390 +Train: [60] [1100/6250] eta: 0:11:41 lr: 0.000047 grad: 0.0907 (0.0964) loss: 0.8196 (0.8202) time: 0.0987 data: 0.0233 max mem: 9390 +Train: [60] [1200/6250] eta: 0:11:35 lr: 0.000047 grad: 0.0906 (0.0960) loss: 0.8238 (0.8204) time: 0.1206 data: 0.0300 max mem: 9390 +Train: [60] [1300/6250] eta: 0:11:24 lr: 0.000047 grad: 0.0905 (0.0957) loss: 0.8242 (0.8204) time: 0.1118 data: 0.0292 max mem: 9390 +Train: [60] [1400/6250] eta: 0:11:11 lr: 0.000047 grad: 0.0942 (0.0957) loss: 0.8220 (0.8204) time: 0.1517 data: 0.0710 max mem: 9390 +Train: [60] [1500/6250] eta: 0:10:57 lr: 0.000047 grad: 0.0930 (0.0959) loss: 0.8204 (0.8204) time: 0.1220 data: 0.0412 max mem: 9390 +Train: [60] [1600/6250] eta: 0:10:40 lr: 0.000047 grad: 0.0957 (0.0960) loss: 0.8128 (0.8203) time: 0.1328 data: 0.0518 max mem: 9390 +Train: [60] [1700/6250] eta: 0:10:24 lr: 0.000047 grad: 0.0989 (0.0962) loss: 0.8151 (0.8202) time: 0.1190 data: 0.0417 max mem: 9390 +Train: [60] [1800/6250] eta: 0:10:06 lr: 0.000047 grad: 0.0942 (0.0965) loss: 0.8150 (0.8200) time: 0.1320 data: 0.0512 max mem: 9390 +Train: [60] [1900/6250] eta: 0:09:48 lr: 0.000047 grad: 0.0956 (0.0967) loss: 0.8199 (0.8198) time: 0.1108 data: 0.0301 max mem: 9390 +Train: [60] [2000/6250] eta: 0:09:30 lr: 0.000047 grad: 0.1002 (0.0968) loss: 0.8198 (0.8199) time: 0.1016 data: 0.0166 max mem: 9390 +Train: [60] [2100/6250] eta: 0:09:14 lr: 0.000046 grad: 0.1011 (0.0969) loss: 0.8220 (0.8199) time: 0.1182 data: 0.0360 max mem: 9390 +Train: [60] [2200/6250] eta: 0:08:59 lr: 0.000046 grad: 0.0981 (0.0971) loss: 0.8209 (0.8198) time: 0.1317 data: 0.0496 max mem: 9390 +Train: [60] [2300/6250] eta: 0:08:45 lr: 0.000046 grad: 0.0982 (0.0972) loss: 0.8150 (0.8199) time: 0.1057 data: 0.0254 max mem: 9390 +Train: [60] [2400/6250] eta: 0:08:34 lr: 0.000046 grad: 0.0972 (0.0974) loss: 0.8189 (0.8198) time: 0.1400 data: 0.0579 max mem: 9390 +Train: [60] [2500/6250] eta: 0:08:24 lr: 0.000046 grad: 0.1047 (0.0978) loss: 0.8128 (0.8197) time: 0.1866 data: 0.1042 max mem: 9390 +Train: [60] [2600/6250] eta: 0:08:12 lr: 0.000046 grad: 0.0989 (0.0981) loss: 0.8229 (0.8197) time: 0.1457 data: 0.0575 max mem: 9390 +Train: [60] [2700/6250] eta: 0:07:58 lr: 0.000046 grad: 0.1047 (0.0984) loss: 0.8152 (0.8196) time: 0.1402 data: 0.0555 max mem: 9390 +Train: [60] [2800/6250] eta: 0:07:45 lr: 0.000046 grad: 0.1079 (0.0987) loss: 0.8154 (0.8194) time: 0.1365 data: 0.0574 max mem: 9390 +Train: [60] [2900/6250] eta: 0:07:31 lr: 0.000046 grad: 0.0979 (0.0990) loss: 0.8154 (0.8193) time: 0.1404 data: 0.0633 max mem: 9390 +Train: [60] [3000/6250] eta: 0:07:18 lr: 0.000046 grad: 0.1016 (0.0992) loss: 0.8138 (0.8192) time: 0.1405 data: 0.0584 max mem: 9390 +Train: [60] [3100/6250] eta: 0:07:04 lr: 0.000046 grad: 0.1043 (0.0994) loss: 0.8138 (0.8191) time: 0.1067 data: 0.0277 max mem: 9390 +Train: [60] [3200/6250] eta: 0:06:50 lr: 0.000046 grad: 0.1041 (0.0996) loss: 0.8195 (0.8190) time: 0.1456 data: 0.0689 max mem: 9390 +Train: [60] [3300/6250] eta: 0:06:37 lr: 0.000046 grad: 0.1034 (0.0997) loss: 0.8235 (0.8189) time: 0.1371 data: 0.0539 max mem: 9390 +Train: [60] [3400/6250] eta: 0:06:23 lr: 0.000046 grad: 0.0967 (0.0999) loss: 0.8201 (0.8188) time: 0.1364 data: 0.0571 max mem: 9390 +Train: [60] [3500/6250] eta: 0:06:09 lr: 0.000046 grad: 0.1070 (0.1001) loss: 0.8131 (0.8187) time: 0.1247 data: 0.0429 max mem: 9390 +Train: [60] [3600/6250] eta: 0:05:56 lr: 0.000046 grad: 0.1044 (0.1002) loss: 0.8124 (0.8186) time: 0.1375 data: 0.0590 max mem: 9390 +Train: [60] [3700/6250] eta: 0:05:42 lr: 0.000046 grad: 0.1037 (0.1003) loss: 0.8120 (0.8185) time: 0.1487 data: 0.0708 max mem: 9390 +Train: [60] [3800/6250] eta: 0:05:29 lr: 0.000046 grad: 0.1047 (0.1005) loss: 0.8123 (0.8184) time: 0.1312 data: 0.0524 max mem: 9390 +Train: [60] [3900/6250] eta: 0:05:15 lr: 0.000046 grad: 0.0967 (0.1006) loss: 0.8172 (0.8182) time: 0.1284 data: 0.0465 max mem: 9390 +Train: [60] [4000/6250] eta: 0:05:02 lr: 0.000046 grad: 0.1003 (0.1006) loss: 0.8100 (0.8181) time: 0.1248 data: 0.0464 max mem: 9390 +Train: [60] [4100/6250] eta: 0:04:49 lr: 0.000046 grad: 0.1086 (0.1007) loss: 0.8170 (0.8180) time: 0.1413 data: 0.0622 max mem: 9390 +Train: [60] [4200/6250] eta: 0:04:35 lr: 0.000046 grad: 0.1059 (0.1009) loss: 0.8037 (0.8179) time: 0.1313 data: 0.0524 max mem: 9390 +Train: [60] [4300/6250] eta: 0:04:22 lr: 0.000046 grad: 0.1044 (0.1010) loss: 0.8091 (0.8177) time: 0.1270 data: 0.0485 max mem: 9390 +Train: [60] [4400/6250] eta: 0:04:08 lr: 0.000046 grad: 0.0941 (0.1010) loss: 0.8177 (0.8176) time: 0.1345 data: 0.0537 max mem: 9390 +Train: [60] [4500/6250] eta: 0:03:55 lr: 0.000046 grad: 0.1031 (0.1010) loss: 0.8147 (0.8175) time: 0.1484 data: 0.0654 max mem: 9390 +Train: [60] [4600/6250] eta: 0:03:41 lr: 0.000046 grad: 0.1114 (0.1011) loss: 0.8092 (0.8174) time: 0.1358 data: 0.0569 max mem: 9390 +Train: [60] [4700/6250] eta: 0:03:28 lr: 0.000046 grad: 0.0978 (0.1011) loss: 0.8148 (0.8173) time: 0.1433 data: 0.0611 max mem: 9390 +Train: [60] [4800/6250] eta: 0:03:15 lr: 0.000046 grad: 0.0965 (0.1011) loss: 0.8193 (0.8173) time: 0.1680 data: 0.0926 max mem: 9390 +Train: [60] [4900/6250] eta: 0:03:02 lr: 0.000046 grad: 0.1004 (0.1011) loss: 0.8146 (0.8173) time: 0.1315 data: 0.0558 max mem: 9390 +Train: [60] [5000/6250] eta: 0:02:48 lr: 0.000046 grad: 0.0997 (0.1012) loss: 0.8105 (0.8172) time: 0.1510 data: 0.0706 max mem: 9390 +Train: [60] [5100/6250] eta: 0:02:35 lr: 0.000046 grad: 0.0935 (0.1012) loss: 0.8180 (0.8172) time: 0.1406 data: 0.0546 max mem: 9390 +Train: [60] [5200/6250] eta: 0:02:22 lr: 0.000045 grad: 0.1037 (0.1012) loss: 0.8073 (0.8171) time: 0.1161 data: 0.0264 max mem: 9390 +Train: [60] [5300/6250] eta: 0:02:08 lr: 0.000045 grad: 0.1017 (0.1013) loss: 0.8168 (0.8171) time: 0.1484 data: 0.0683 max mem: 9390 +Train: [60] [5400/6250] eta: 0:01:55 lr: 0.000045 grad: 0.0977 (0.1013) loss: 0.8120 (0.8171) time: 0.1425 data: 0.0626 max mem: 9390 +Train: [60] [5500/6250] eta: 0:01:42 lr: 0.000045 grad: 0.1000 (0.1013) loss: 0.8200 (0.8170) time: 0.1521 data: 0.0776 max mem: 9390 +Train: [60] [5600/6250] eta: 0:01:28 lr: 0.000045 grad: 0.1004 (0.1014) loss: 0.8166 (0.8170) time: 0.1203 data: 0.0467 max mem: 9390 +Train: [60] [5700/6250] eta: 0:01:14 lr: 0.000045 grad: 0.1049 (0.1015) loss: 0.8139 (0.8169) time: 0.1417 data: 0.0529 max mem: 9390 +Train: [60] [5800/6250] eta: 0:01:01 lr: 0.000045 grad: 0.0918 (0.1015) loss: 0.8160 (0.8169) time: 0.1252 data: 0.0420 max mem: 9390 +Train: [60] [5900/6250] eta: 0:00:47 lr: 0.000045 grad: 0.1024 (0.1016) loss: 0.8137 (0.8168) time: 0.1298 data: 0.0426 max mem: 9390 +Train: [60] [6000/6250] eta: 0:00:34 lr: 0.000045 grad: 0.1030 (0.1016) loss: 0.8108 (0.8168) time: 0.1291 data: 0.0518 max mem: 9390 +Train: [60] [6100/6250] eta: 0:00:20 lr: 0.000045 grad: 0.1042 (0.1017) loss: 0.8098 (0.8167) time: 0.1310 data: 0.0408 max mem: 9390 +Train: [60] [6200/6250] eta: 0:00:06 lr: 0.000045 grad: 0.1046 (0.1017) loss: 0.8139 (0.8166) time: 0.1250 data: 0.0437 max mem: 9390 +Train: [60] [6249/6250] eta: 0:00:00 lr: 0.000045 grad: 0.1021 (0.1017) loss: 0.8129 (0.8166) time: 0.1281 data: 0.0465 max mem: 9390 +Train: [60] Total time: 0:14:17 (0.1372 s / it) +Averaged stats: lr: 0.000045 grad: 0.1021 (0.1017) loss: 0.8129 (0.8166) +Eval (hcp-train-subset): [60] [ 0/62] eta: 0:03:36 loss: 0.8405 (0.8405) time: 3.4925 data: 3.4041 max mem: 9390 +Eval (hcp-train-subset): [60] [61/62] eta: 0:00:00 loss: 0.8312 (0.8335) time: 0.1173 data: 0.0926 max mem: 9390 +Eval (hcp-train-subset): [60] Total time: 0:00:11 (0.1905 s / it) +Averaged stats (hcp-train-subset): loss: 0.8312 (0.8335) +Eval (hcp-val): [60] [ 0/62] eta: 0:04:55 loss: 0.8310 (0.8310) time: 4.7650 data: 4.7340 max mem: 9390 +Eval (hcp-val): [60] [61/62] eta: 0:00:00 loss: 0.8321 (0.8339) time: 0.1239 data: 0.0969 max mem: 9390 +Eval (hcp-val): [60] Total time: 0:00:13 (0.2128 s / it) +Averaged stats (hcp-val): loss: 0.8321 (0.8339) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +Train: [61] [ 0/6250] eta: 7:55:21 lr: 0.000045 grad: 0.1182 (0.1182) loss: 0.8703 (0.8703) time: 4.5634 data: 4.2891 max mem: 9390 +Train: [61] [ 100/6250] eta: 0:19:43 lr: 0.000045 grad: 0.1011 (0.1129) loss: 0.8178 (0.8260) time: 0.1370 data: 0.0431 max mem: 9390 +Train: [61] [ 200/6250] eta: 0:16:44 lr: 0.000045 grad: 0.0964 (0.1090) loss: 0.8199 (0.8220) time: 0.1477 data: 0.0549 max mem: 9390 +Train: [61] [ 300/6250] eta: 0:15:27 lr: 0.000045 grad: 0.0920 (0.1069) loss: 0.8227 (0.8220) time: 0.1237 data: 0.0379 max mem: 9390 +Train: [61] [ 400/6250] eta: 0:14:39 lr: 0.000045 grad: 0.0994 (0.1056) loss: 0.8183 (0.8211) time: 0.1325 data: 0.0495 max mem: 9390 +Train: [61] [ 500/6250] eta: 0:13:52 lr: 0.000045 grad: 0.0996 (0.1044) loss: 0.8201 (0.8205) time: 0.1248 data: 0.0327 max mem: 9390 +Train: [61] [ 600/6250] eta: 0:13:16 lr: 0.000045 grad: 0.0954 (0.1029) loss: 0.8210 (0.8206) time: 0.1264 data: 0.0399 max mem: 9390 +Train: [61] [ 700/6250] eta: 0:12:46 lr: 0.000045 grad: 0.0926 (0.1027) loss: 0.8248 (0.8208) time: 0.1202 data: 0.0311 max mem: 9390 +Train: [61] [ 800/6250] eta: 0:12:24 lr: 0.000045 grad: 0.1027 (0.1024) loss: 0.8116 (0.8204) time: 0.1253 data: 0.0444 max mem: 9390 +Train: [61] [ 900/6250] eta: 0:12:14 lr: 0.000045 grad: 0.0993 (0.1024) loss: 0.8101 (0.8202) time: 0.1355 data: 0.0530 max mem: 9390 +Train: [61] [1000/6250] eta: 0:12:01 lr: 0.000045 grad: 0.0975 (0.1022) loss: 0.8135 (0.8197) time: 0.1405 data: 0.0608 max mem: 9390 +Train: [61] [1100/6250] eta: 0:11:46 lr: 0.000045 grad: 0.1052 (0.1021) loss: 0.8152 (0.8194) time: 0.1398 data: 0.0605 max mem: 9390 +Train: [61] [1200/6250] eta: 0:11:35 lr: 0.000045 grad: 0.1046 (0.1020) loss: 0.8142 (0.8192) time: 0.1953 data: 0.1205 max mem: 9390 +Train: [61] [1300/6250] eta: 0:11:26 lr: 0.000045 grad: 0.0995 (0.1023) loss: 0.8113 (0.8188) time: 0.1329 data: 0.0553 max mem: 9390 +Train: [61] [1400/6250] eta: 0:11:14 lr: 0.000045 grad: 0.1008 (0.1026) loss: 0.8140 (0.8186) time: 0.1391 data: 0.0641 max mem: 9390 +Train: [61] [1500/6250] eta: 0:11:00 lr: 0.000045 grad: 0.0999 (0.1025) loss: 0.8180 (0.8184) time: 0.1553 data: 0.0724 max mem: 9390 +Train: [61] [1600/6250] eta: 0:10:45 lr: 0.000045 grad: 0.1048 (0.1029) loss: 0.8145 (0.8180) time: 0.1403 data: 0.0590 max mem: 9390 +Train: [61] [1700/6250] eta: 0:10:30 lr: 0.000045 grad: 0.0964 (0.1032) loss: 0.8167 (0.8178) time: 0.1463 data: 0.0670 max mem: 9390 +Train: [61] [1800/6250] eta: 0:10:13 lr: 0.000045 grad: 0.0985 (0.1031) loss: 0.8126 (0.8176) time: 0.1369 data: 0.0546 max mem: 9390 +Train: [61] [1900/6250] eta: 0:09:55 lr: 0.000045 grad: 0.1020 (0.1033) loss: 0.8042 (0.8173) time: 0.1135 data: 0.0339 max mem: 9390 +Train: [61] [2000/6250] eta: 0:09:37 lr: 0.000045 grad: 0.1040 (0.1034) loss: 0.8084 (0.8169) time: 0.1304 data: 0.0416 max mem: 9390 +Train: [61] [2100/6250] eta: 0:09:19 lr: 0.000044 grad: 0.1060 (0.1035) loss: 0.8121 (0.8166) time: 0.1107 data: 0.0288 max mem: 9390 +Train: [61] [2200/6250] eta: 0:09:02 lr: 0.000044 grad: 0.1035 (0.1034) loss: 0.8080 (0.8165) time: 0.1155 data: 0.0378 max mem: 9390 +Train: [61] [2300/6250] eta: 0:08:46 lr: 0.000044 grad: 0.1000 (0.1033) loss: 0.8124 (0.8163) time: 0.1153 data: 0.0332 max mem: 9390 +Train: [61] [2400/6250] eta: 0:08:33 lr: 0.000044 grad: 0.0988 (0.1033) loss: 0.8132 (0.8161) time: 0.1400 data: 0.0611 max mem: 9390 +Train: [61] [2500/6250] eta: 0:08:20 lr: 0.000044 grad: 0.0961 (0.1033) loss: 0.8173 (0.8160) time: 0.1334 data: 0.0566 max mem: 9390 +Train: [61] [2600/6250] eta: 0:08:08 lr: 0.000044 grad: 0.1048 (0.1034) loss: 0.8113 (0.8159) time: 0.1362 data: 0.0579 max mem: 9390 +Train: [61] [2700/6250] eta: 0:07:54 lr: 0.000044 grad: 0.0963 (0.1033) loss: 0.8158 (0.8158) time: 0.1567 data: 0.0784 max mem: 9390 +Train: [61] [2800/6250] eta: 0:07:40 lr: 0.000044 grad: 0.1039 (0.1034) loss: 0.8144 (0.8158) time: 0.1237 data: 0.0405 max mem: 9390 +Train: [61] [2900/6250] eta: 0:07:26 lr: 0.000044 grad: 0.0989 (0.1034) loss: 0.8200 (0.8157) time: 0.1369 data: 0.0566 max mem: 9390 +Train: [61] [3000/6250] eta: 0:07:12 lr: 0.000044 grad: 0.1014 (0.1035) loss: 0.8163 (0.8157) time: 0.1277 data: 0.0473 max mem: 9390 +Train: [61] [3100/6250] eta: 0:06:58 lr: 0.000044 grad: 0.1038 (0.1035) loss: 0.8177 (0.8157) time: 0.1298 data: 0.0502 max mem: 9390 +Train: [61] [3200/6250] eta: 0:06:45 lr: 0.000044 grad: 0.0955 (0.1034) loss: 0.8214 (0.8157) time: 0.1481 data: 0.0639 max mem: 9390 +Train: [61] [3300/6250] eta: 0:06:31 lr: 0.000044 grad: 0.0995 (0.1034) loss: 0.8178 (0.8158) time: 0.1433 data: 0.0644 max mem: 9390 +Train: [61] [3400/6250] eta: 0:06:17 lr: 0.000044 grad: 0.1023 (0.1034) loss: 0.8149 (0.8158) time: 0.1230 data: 0.0439 max mem: 9390 +Train: [61] [3500/6250] eta: 0:06:03 lr: 0.000044 grad: 0.1040 (0.1033) loss: 0.8066 (0.8157) time: 0.1284 data: 0.0536 max mem: 9390 +Train: [61] [3600/6250] eta: 0:05:50 lr: 0.000044 grad: 0.1001 (0.1034) loss: 0.8183 (0.8157) time: 0.1430 data: 0.0635 max mem: 9390 +Train: [61] [3700/6250] eta: 0:05:36 lr: 0.000044 grad: 0.1035 (0.1035) loss: 0.8197 (0.8157) time: 0.1051 data: 0.0289 max mem: 9390 +Train: [61] [3800/6250] eta: 0:05:24 lr: 0.000044 grad: 0.0988 (0.1035) loss: 0.8187 (0.8158) time: 0.1128 data: 0.0296 max mem: 9390 +Train: [61] [3900/6250] eta: 0:05:10 lr: 0.000044 grad: 0.1016 (0.1035) loss: 0.8194 (0.8159) time: 0.1435 data: 0.0648 max mem: 9390 +Train: [61] [4000/6250] eta: 0:04:57 lr: 0.000044 grad: 0.1026 (0.1035) loss: 0.8126 (0.8159) time: 0.1219 data: 0.0458 max mem: 9390 +Train: [61] [4100/6250] eta: 0:04:44 lr: 0.000044 grad: 0.0991 (0.1036) loss: 0.8107 (0.8159) time: 0.1394 data: 0.0560 max mem: 9390 +Train: [61] [4200/6250] eta: 0:04:31 lr: 0.000044 grad: 0.0978 (0.1036) loss: 0.8267 (0.8159) time: 0.1343 data: 0.0561 max mem: 9390 +Train: [61] [4300/6250] eta: 0:04:18 lr: 0.000044 grad: 0.0989 (0.1035) loss: 0.8227 (0.8159) time: 0.1416 data: 0.0593 max mem: 9390 +Train: [61] [4400/6250] eta: 0:04:05 lr: 0.000044 grad: 0.1107 (0.1036) loss: 0.8096 (0.8159) time: 0.1461 data: 0.0690 max mem: 9390 +Train: [61] [4500/6250] eta: 0:03:52 lr: 0.000044 grad: 0.1016 (0.1037) loss: 0.8109 (0.8159) time: 0.1499 data: 0.0736 max mem: 9390 +Train: [61] [4600/6250] eta: 0:03:39 lr: 0.000044 grad: 0.1053 (0.1038) loss: 0.8192 (0.8159) time: 0.1377 data: 0.0582 max mem: 9390 +Train: [61] [4700/6250] eta: 0:03:25 lr: 0.000044 grad: 0.0998 (0.1038) loss: 0.8115 (0.8158) time: 0.1261 data: 0.0457 max mem: 9390 +Train: [61] [4800/6250] eta: 0:03:12 lr: 0.000044 grad: 0.1026 (0.1039) loss: 0.8136 (0.8158) time: 0.1359 data: 0.0574 max mem: 9390 +Train: [61] [4900/6250] eta: 0:02:59 lr: 0.000044 grad: 0.0970 (0.1039) loss: 0.8107 (0.8158) time: 0.1470 data: 0.0649 max mem: 9390 +Train: [61] [5000/6250] eta: 0:02:46 lr: 0.000044 grad: 0.1031 (0.1040) loss: 0.8179 (0.8159) time: 0.1433 data: 0.0663 max mem: 9390 +Train: [61] [5100/6250] eta: 0:02:33 lr: 0.000044 grad: 0.0966 (0.1040) loss: 0.8178 (0.8159) time: 0.1326 data: 0.0548 max mem: 9390 +Train: [61] [5200/6250] eta: 0:02:20 lr: 0.000044 grad: 0.0990 (0.1041) loss: 0.8157 (0.8159) time: 0.1414 data: 0.0651 max mem: 9390 +Train: [61] [5300/6250] eta: 0:02:07 lr: 0.000043 grad: 0.1048 (0.1041) loss: 0.8142 (0.8158) time: 0.1282 data: 0.0476 max mem: 9390 +Train: [61] [5400/6250] eta: 0:01:53 lr: 0.000043 grad: 0.1029 (0.1042) loss: 0.8115 (0.8158) time: 0.1840 data: 0.1053 max mem: 9390 +Train: [61] [5500/6250] eta: 0:01:40 lr: 0.000043 grad: 0.1080 (0.1042) loss: 0.8154 (0.8158) time: 0.1302 data: 0.0552 max mem: 9390 +Train: [61] [5600/6250] eta: 0:01:27 lr: 0.000043 grad: 0.1032 (0.1042) loss: 0.8165 (0.8158) time: 0.1432 data: 0.0639 max mem: 9390 +Train: [61] [5700/6250] eta: 0:01:13 lr: 0.000043 grad: 0.1063 (0.1042) loss: 0.8187 (0.8159) time: 0.1260 data: 0.0477 max mem: 9390 +Train: [61] [5800/6250] eta: 0:01:00 lr: 0.000043 grad: 0.1008 (0.1042) loss: 0.8188 (0.8159) time: 0.1339 data: 0.0484 max mem: 9390 +Train: [61] [5900/6250] eta: 0:00:47 lr: 0.000043 grad: 0.1029 (0.1042) loss: 0.8150 (0.8159) time: 0.1435 data: 0.0668 max mem: 9390 +Train: [61] [6000/6250] eta: 0:00:33 lr: 0.000043 grad: 0.0956 (0.1042) loss: 0.8154 (0.8160) time: 0.1292 data: 0.0455 max mem: 9390 +Train: [61] [6100/6250] eta: 0:00:20 lr: 0.000043 grad: 0.1065 (0.1042) loss: 0.8211 (0.8160) time: 0.1456 data: 0.0620 max mem: 9390 +Train: [61] [6200/6250] eta: 0:00:06 lr: 0.000043 grad: 0.1059 (0.1042) loss: 0.8129 (0.8160) time: 0.1357 data: 0.0574 max mem: 9390 +Train: [61] [6249/6250] eta: 0:00:00 lr: 0.000043 grad: 0.0998 (0.1042) loss: 0.8199 (0.8160) time: 0.1147 data: 0.0332 max mem: 9390 +Train: [61] Total time: 0:14:06 (0.1355 s / it) +Averaged stats: lr: 0.000043 grad: 0.0998 (0.1042) loss: 0.8199 (0.8160) +Eval (hcp-train-subset): [61] [ 0/62] eta: 0:03:39 loss: 0.8428 (0.8428) time: 3.5414 data: 3.4587 max mem: 9390 +Eval (hcp-train-subset): [61] [61/62] eta: 0:00:00 loss: 0.8283 (0.8308) time: 0.1138 data: 0.0860 max mem: 9390 +Eval (hcp-train-subset): [61] Total time: 0:00:11 (0.1920 s / it) +Averaged stats (hcp-train-subset): loss: 0.8283 (0.8308) +Eval (hcp-val): [61] [ 0/62] eta: 0:03:48 loss: 0.8318 (0.8318) time: 3.6821 data: 3.5960 max mem: 9390 +Eval (hcp-val): [61] [61/62] eta: 0:00:00 loss: 0.8336 (0.8338) time: 0.1040 data: 0.0788 max mem: 9390 +Eval (hcp-val): [61] Total time: 0:00:12 (0.2074 s / it) +Averaged stats (hcp-val): loss: 0.8336 (0.8338) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +Train: [62] [ 0/6250] eta: 10:23:01 lr: 0.000043 grad: 0.1378 (0.1378) loss: 0.8156 (0.8156) time: 5.9811 data: 5.8578 max mem: 9390 +Train: [62] [ 100/6250] eta: 0:20:15 lr: 0.000043 grad: 0.1046 (0.1238) loss: 0.8255 (0.8297) time: 0.1492 data: 0.0541 max mem: 9390 +Train: [62] [ 200/6250] eta: 0:17:01 lr: 0.000043 grad: 0.1205 (0.1211) loss: 0.8222 (0.8267) time: 0.1505 data: 0.0546 max mem: 9390 +Train: [62] [ 300/6250] eta: 0:15:47 lr: 0.000043 grad: 0.1135 (0.1215) loss: 0.8207 (0.8225) time: 0.1473 data: 0.0613 max mem: 9390 +Train: [62] [ 400/6250] eta: 0:14:55 lr: 0.000043 grad: 0.1034 (0.1185) loss: 0.8155 (0.8202) time: 0.1497 data: 0.0628 max mem: 9390 +Train: [62] [ 500/6250] eta: 0:14:07 lr: 0.000043 grad: 0.1004 (0.1157) loss: 0.8162 (0.8190) time: 0.1289 data: 0.0460 max mem: 9390 +Train: [62] [ 600/6250] eta: 0:13:26 lr: 0.000043 grad: 0.0988 (0.1135) loss: 0.8222 (0.8190) time: 0.1118 data: 0.0246 max mem: 9390 +Train: [62] [ 700/6250] eta: 0:12:58 lr: 0.000043 grad: 0.0991 (0.1118) loss: 0.8239 (0.8189) time: 0.1340 data: 0.0450 max mem: 9390 +Train: [62] [ 800/6250] eta: 0:12:33 lr: 0.000043 grad: 0.0962 (0.1106) loss: 0.8167 (0.8187) time: 0.1024 data: 0.0125 max mem: 9390 +Train: [62] [ 900/6250] eta: 0:12:16 lr: 0.000043 grad: 0.0996 (0.1099) loss: 0.8233 (0.8185) time: 0.1580 data: 0.0760 max mem: 9390 +Train: [62] [1000/6250] eta: 0:11:58 lr: 0.000043 grad: 0.1004 (0.1090) loss: 0.8128 (0.8183) time: 0.1221 data: 0.0366 max mem: 9390 +Train: [62] [1100/6250] eta: 0:11:53 lr: 0.000043 grad: 0.1086 (0.1086) loss: 0.8042 (0.8178) time: 0.2373 data: 0.1589 max mem: 9390 +Train: [62] [1200/6250] eta: 0:11:36 lr: 0.000043 grad: 0.1015 (0.1083) loss: 0.8161 (0.8174) time: 0.1591 data: 0.0742 max mem: 9390 +Train: [62] [1300/6250] eta: 0:11:25 lr: 0.000043 grad: 0.0940 (0.1081) loss: 0.8160 (0.8172) time: 0.1438 data: 0.0662 max mem: 9390 +Train: [62] [1400/6250] eta: 0:11:13 lr: 0.000043 grad: 0.1028 (0.1080) loss: 0.8216 (0.8169) time: 0.1517 data: 0.0627 max mem: 9390 +Train: [62] [1500/6250] eta: 0:11:01 lr: 0.000043 grad: 0.1046 (0.1078) loss: 0.8081 (0.8165) time: 0.1423 data: 0.0610 max mem: 9390 +Train: [62] [1600/6250] eta: 0:10:48 lr: 0.000043 grad: 0.1024 (0.1076) loss: 0.8206 (0.8165) time: 0.1447 data: 0.0568 max mem: 9390 +Train: [62] [1700/6250] eta: 0:10:33 lr: 0.000043 grad: 0.1009 (0.1074) loss: 0.8251 (0.8166) time: 0.1359 data: 0.0541 max mem: 9390 +Train: [62] [1800/6250] eta: 0:10:16 lr: 0.000043 grad: 0.1075 (0.1073) loss: 0.8191 (0.8165) time: 0.1115 data: 0.0252 max mem: 9390 +Train: [62] [1900/6250] eta: 0:09:59 lr: 0.000043 grad: 0.1053 (0.1073) loss: 0.8169 (0.8165) time: 0.1321 data: 0.0481 max mem: 9390 +Train: [62] [2000/6250] eta: 0:09:40 lr: 0.000043 grad: 0.1055 (0.1074) loss: 0.8042 (0.8161) time: 0.0960 data: 0.0134 max mem: 9390 +Train: [62] [2100/6250] eta: 0:09:22 lr: 0.000043 grad: 0.1091 (0.1075) loss: 0.8125 (0.8160) time: 0.1015 data: 0.0187 max mem: 9390 +Train: [62] [2200/6250] eta: 0:09:09 lr: 0.000042 grad: 0.1107 (0.1075) loss: 0.8099 (0.8159) time: 0.1483 data: 0.0689 max mem: 9390 +Train: [62] [2300/6250] eta: 0:08:58 lr: 0.000042 grad: 0.0960 (0.1074) loss: 0.8232 (0.8159) time: 0.1484 data: 0.0733 max mem: 9390 +Train: [62] [2400/6250] eta: 0:08:48 lr: 0.000042 grad: 0.1070 (0.1074) loss: 0.8172 (0.8159) time: 0.1538 data: 0.0760 max mem: 9390 +Train: [62] [2500/6250] eta: 0:08:36 lr: 0.000042 grad: 0.1050 (0.1076) loss: 0.8100 (0.8159) time: 0.1618 data: 0.0808 max mem: 9390 +Train: [62] [2600/6250] eta: 0:08:24 lr: 0.000042 grad: 0.0976 (0.1076) loss: 0.8159 (0.8159) time: 0.1318 data: 0.0522 max mem: 9390 +Train: [62] [2700/6250] eta: 0:08:10 lr: 0.000042 grad: 0.1027 (0.1075) loss: 0.8132 (0.8159) time: 0.1475 data: 0.0697 max mem: 9390 +Train: [62] [2800/6250] eta: 0:07:55 lr: 0.000042 grad: 0.1023 (0.1074) loss: 0.8153 (0.8160) time: 0.1178 data: 0.0361 max mem: 9390 +Train: [62] [2900/6250] eta: 0:07:41 lr: 0.000042 grad: 0.1090 (0.1074) loss: 0.8153 (0.8159) time: 0.0946 data: 0.0099 max mem: 9390 +Train: [62] [3000/6250] eta: 0:07:26 lr: 0.000042 grad: 0.1082 (0.1075) loss: 0.8100 (0.8159) time: 0.1234 data: 0.0362 max mem: 9390 +Train: [62] [3100/6250] eta: 0:07:12 lr: 0.000042 grad: 0.0982 (0.1073) loss: 0.8241 (0.8160) time: 0.1185 data: 0.0398 max mem: 9390 +Train: [62] [3200/6250] eta: 0:06:58 lr: 0.000042 grad: 0.1080 (0.1074) loss: 0.8142 (0.8160) time: 0.1288 data: 0.0488 max mem: 9390 +Train: [62] [3300/6250] eta: 0:06:45 lr: 0.000042 grad: 0.1013 (0.1072) loss: 0.8168 (0.8160) time: 0.0957 data: 0.0002 max mem: 9390 +Train: [62] [3400/6250] eta: 0:06:31 lr: 0.000042 grad: 0.0972 (0.1071) loss: 0.8182 (0.8161) time: 0.1207 data: 0.0389 max mem: 9390 +Train: [62] [3500/6250] eta: 0:06:20 lr: 0.000042 grad: 0.1034 (0.1071) loss: 0.8178 (0.8160) time: 0.2462 data: 0.0984 max mem: 9390 +Train: [62] [3600/6250] eta: 0:06:05 lr: 0.000042 grad: 0.1082 (0.1071) loss: 0.8163 (0.8160) time: 0.1217 data: 0.0427 max mem: 9390 +Train: [62] [3700/6250] eta: 0:05:51 lr: 0.000042 grad: 0.1034 (0.1071) loss: 0.8223 (0.8160) time: 0.1243 data: 0.0419 max mem: 9390 +Train: [62] [3800/6250] eta: 0:05:37 lr: 0.000042 grad: 0.1058 (0.1071) loss: 0.8150 (0.8161) time: 0.1188 data: 0.0326 max mem: 9390 +Train: [62] [3900/6250] eta: 0:05:24 lr: 0.000042 grad: 0.1108 (0.1071) loss: 0.8102 (0.8160) time: 0.1025 data: 0.0146 max mem: 9390 +Train: [62] [4000/6250] eta: 0:05:11 lr: 0.000042 grad: 0.1057 (0.1071) loss: 0.8103 (0.8160) time: 0.0856 data: 0.0002 max mem: 9390 +Train: [62] [4100/6250] eta: 0:04:57 lr: 0.000042 grad: 0.1089 (0.1071) loss: 0.8105 (0.8159) time: 0.1826 data: 0.1058 max mem: 9390 +Train: [62] [4200/6250] eta: 0:04:42 lr: 0.000042 grad: 0.1041 (0.1070) loss: 0.8092 (0.8159) time: 0.1255 data: 0.0453 max mem: 9390 +Train: [62] [4300/6250] eta: 0:04:29 lr: 0.000042 grad: 0.1064 (0.1070) loss: 0.8123 (0.8158) time: 0.1629 data: 0.0858 max mem: 9390 +Train: [62] [4400/6250] eta: 0:04:15 lr: 0.000042 grad: 0.1008 (0.1070) loss: 0.8103 (0.8157) time: 0.1598 data: 0.0600 max mem: 9390 +Train: [62] [4500/6250] eta: 0:04:01 lr: 0.000042 grad: 0.1039 (0.1069) loss: 0.8159 (0.8157) time: 0.1349 data: 0.0553 max mem: 9390 +Train: [62] [4600/6250] eta: 0:03:48 lr: 0.000042 grad: 0.1010 (0.1070) loss: 0.8162 (0.8157) time: 0.1573 data: 0.0757 max mem: 9390 +Train: [62] [4700/6250] eta: 0:03:34 lr: 0.000042 grad: 0.1099 (0.1070) loss: 0.8161 (0.8156) time: 0.1516 data: 0.0697 max mem: 9390 +Train: [62] [4800/6250] eta: 0:03:21 lr: 0.000042 grad: 0.1028 (0.1070) loss: 0.8157 (0.8156) time: 0.1277 data: 0.0427 max mem: 9390 +Train: [62] [4900/6250] eta: 0:03:07 lr: 0.000042 grad: 0.1071 (0.1071) loss: 0.8136 (0.8156) time: 0.1561 data: 0.0783 max mem: 9390 +Train: [62] [5000/6250] eta: 0:02:53 lr: 0.000042 grad: 0.1063 (0.1071) loss: 0.8066 (0.8155) time: 0.1362 data: 0.0528 max mem: 9390 +Train: [62] [5100/6250] eta: 0:02:39 lr: 0.000042 grad: 0.1035 (0.1071) loss: 0.8184 (0.8155) time: 0.1169 data: 0.0369 max mem: 9390 +Train: [62] [5200/6250] eta: 0:02:25 lr: 0.000042 grad: 0.1068 (0.1070) loss: 0.8169 (0.8155) time: 0.1406 data: 0.0566 max mem: 9390 +Train: [62] [5300/6250] eta: 0:02:11 lr: 0.000042 grad: 0.1029 (0.1071) loss: 0.8130 (0.8154) time: 0.1482 data: 0.0603 max mem: 9390 +Train: [62] [5400/6250] eta: 0:01:58 lr: 0.000041 grad: 0.1067 (0.1071) loss: 0.8094 (0.8154) time: 0.1428 data: 0.0661 max mem: 9390 +Train: [62] [5500/6250] eta: 0:01:44 lr: 0.000041 grad: 0.1013 (0.1071) loss: 0.8131 (0.8154) time: 0.1376 data: 0.0646 max mem: 9390 +Train: [62] [5600/6250] eta: 0:01:30 lr: 0.000041 grad: 0.1088 (0.1071) loss: 0.8124 (0.8153) time: 0.1379 data: 0.0547 max mem: 9390 +Train: [62] [5700/6250] eta: 0:01:16 lr: 0.000041 grad: 0.1097 (0.1071) loss: 0.8134 (0.8152) time: 0.1444 data: 0.0686 max mem: 9390 +Train: [62] [5800/6250] eta: 0:01:02 lr: 0.000041 grad: 0.1100 (0.1071) loss: 0.8095 (0.8152) time: 0.1408 data: 0.0603 max mem: 9390 +Train: [62] [5900/6250] eta: 0:00:48 lr: 0.000041 grad: 0.1065 (0.1071) loss: 0.8126 (0.8152) time: 0.1361 data: 0.0589 max mem: 9390 +Train: [62] [6000/6250] eta: 0:00:34 lr: 0.000041 grad: 0.1023 (0.1071) loss: 0.8134 (0.8151) time: 0.1042 data: 0.0222 max mem: 9390 +Train: [62] [6100/6250] eta: 0:00:20 lr: 0.000041 grad: 0.1096 (0.1071) loss: 0.8106 (0.8151) time: 0.1481 data: 0.0711 max mem: 9390 +Train: [62] [6200/6250] eta: 0:00:06 lr: 0.000041 grad: 0.1060 (0.1072) loss: 0.8158 (0.8151) time: 0.1327 data: 0.0516 max mem: 9390 +Train: [62] [6249/6250] eta: 0:00:00 lr: 0.000041 grad: 0.1032 (0.1072) loss: 0.8157 (0.8150) time: 0.1445 data: 0.0580 max mem: 9390 +Train: [62] Total time: 0:14:33 (0.1397 s / it) +Averaged stats: lr: 0.000041 grad: 0.1032 (0.1072) loss: 0.8157 (0.8150) +Eval (hcp-train-subset): [62] [ 0/62] eta: 0:04:00 loss: 0.8452 (0.8452) time: 3.8758 data: 3.7823 max mem: 9390 +Eval (hcp-train-subset): [62] [61/62] eta: 0:00:00 loss: 0.8321 (0.8307) time: 0.0968 data: 0.0700 max mem: 9390 +Eval (hcp-train-subset): [62] Total time: 0:00:13 (0.2154 s / it) +Averaged stats (hcp-train-subset): loss: 0.8321 (0.8307) +Eval (hcp-val): [62] [ 0/62] eta: 0:03:35 loss: 0.8314 (0.8314) time: 3.4687 data: 3.3946 max mem: 9390 +Eval (hcp-val): [62] [61/62] eta: 0:00:00 loss: 0.8316 (0.8335) time: 0.1282 data: 0.1029 max mem: 9390 +Eval (hcp-val): [62] Total time: 0:00:12 (0.2023 s / it) +Averaged stats (hcp-val): loss: 0.8316 (0.8335) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +Train: [63] [ 0/6250] eta: 10:48:38 lr: 0.000041 grad: 0.7525 (0.7525) loss: 0.8791 (0.8791) time: 6.2270 data: 6.1338 max mem: 9390 +Train: [63] [ 100/6250] eta: 0:20:02 lr: 0.000041 grad: 0.1133 (0.1435) loss: 0.8254 (0.8293) time: 0.1431 data: 0.0436 max mem: 9390 +Train: [63] [ 200/6250] eta: 0:16:54 lr: 0.000041 grad: 0.1034 (0.1309) loss: 0.8142 (0.8227) time: 0.1353 data: 0.0428 max mem: 9390 +Train: [63] [ 300/6250] eta: 0:15:37 lr: 0.000041 grad: 0.1020 (0.1243) loss: 0.8155 (0.8214) time: 0.1425 data: 0.0593 max mem: 9390 +Train: [63] [ 400/6250] eta: 0:14:38 lr: 0.000041 grad: 0.0936 (0.1185) loss: 0.8201 (0.8207) time: 0.1276 data: 0.0421 max mem: 9390 +Train: [63] [ 500/6250] eta: 0:14:03 lr: 0.000041 grad: 0.0947 (0.1148) loss: 0.8190 (0.8204) time: 0.1537 data: 0.0714 max mem: 9390 +Train: [63] [ 600/6250] eta: 0:13:23 lr: 0.000041 grad: 0.0996 (0.1127) loss: 0.8165 (0.8200) time: 0.1298 data: 0.0451 max mem: 9390 +Train: [63] [ 700/6250] eta: 0:12:54 lr: 0.000041 grad: 0.0981 (0.1106) loss: 0.8178 (0.8197) time: 0.1102 data: 0.0243 max mem: 9390 +Train: [63] [ 800/6250] eta: 0:12:38 lr: 0.000041 grad: 0.1004 (0.1095) loss: 0.8234 (0.8193) time: 0.1585 data: 0.0734 max mem: 9390 +Train: [63] [ 900/6250] eta: 0:12:25 lr: 0.000041 grad: 0.0977 (0.1084) loss: 0.8236 (0.8192) time: 0.1199 data: 0.0343 max mem: 9390 +Train: [63] [1000/6250] eta: 0:12:17 lr: 0.000041 grad: 0.0980 (0.1075) loss: 0.8202 (0.8190) time: 0.1884 data: 0.1083 max mem: 9390 +Train: [63] [1100/6250] eta: 0:11:56 lr: 0.000041 grad: 0.0953 (0.1069) loss: 0.8163 (0.8186) time: 0.1191 data: 0.0400 max mem: 9390 +Train: [63] [1200/6250] eta: 0:11:44 lr: 0.000041 grad: 0.0987 (0.1065) loss: 0.8147 (0.8185) time: 0.1556 data: 0.0780 max mem: 9390 +Train: [63] [1300/6250] eta: 0:11:29 lr: 0.000041 grad: 0.0977 (0.1061) loss: 0.8150 (0.8181) time: 0.1486 data: 0.0680 max mem: 9390 +Train: [63] [1400/6250] eta: 0:11:19 lr: 0.000041 grad: 0.1023 (0.1059) loss: 0.8131 (0.8178) time: 0.1500 data: 0.0690 max mem: 9390 +Train: [63] [1500/6250] eta: 0:11:08 lr: 0.000041 grad: 0.0970 (0.1061) loss: 0.8132 (0.8176) time: 0.1344 data: 0.0556 max mem: 9390 +Train: [63] [1600/6250] eta: 0:10:54 lr: 0.000041 grad: 0.0945 (0.1058) loss: 0.8206 (0.8174) time: 0.1338 data: 0.0485 max mem: 9390 +Train: [63] [1700/6250] eta: 0:10:38 lr: 0.000041 grad: 0.1010 (0.1057) loss: 0.8143 (0.8171) time: 0.1454 data: 0.0614 max mem: 9390 +Train: [63] [1800/6250] eta: 0:10:22 lr: 0.000041 grad: 0.0995 (0.1056) loss: 0.8182 (0.8168) time: 0.1338 data: 0.0488 max mem: 9390 +Train: [63] [1900/6250] eta: 0:10:05 lr: 0.000041 grad: 0.0986 (0.1056) loss: 0.8161 (0.8167) time: 0.1232 data: 0.0408 max mem: 9390 +Train: [63] [2000/6250] eta: 0:09:48 lr: 0.000041 grad: 0.0982 (0.1054) loss: 0.8132 (0.8166) time: 0.1128 data: 0.0294 max mem: 9390 +Train: [63] [2100/6250] eta: 0:09:31 lr: 0.000041 grad: 0.1036 (0.1053) loss: 0.8092 (0.8164) time: 0.1327 data: 0.0496 max mem: 9390 +Train: [63] [2200/6250] eta: 0:09:13 lr: 0.000041 grad: 0.1118 (0.1055) loss: 0.8146 (0.8163) time: 0.1159 data: 0.0328 max mem: 9390 +Train: [63] [2300/6250] eta: 0:08:56 lr: 0.000041 grad: 0.1050 (0.1055) loss: 0.8100 (0.8162) time: 0.1181 data: 0.0362 max mem: 9390 +Train: [63] [2400/6250] eta: 0:08:41 lr: 0.000040 grad: 0.1051 (0.1054) loss: 0.8144 (0.8160) time: 0.1421 data: 0.0589 max mem: 9390 +Train: [63] [2500/6250] eta: 0:08:29 lr: 0.000040 grad: 0.1050 (0.1054) loss: 0.8111 (0.8159) time: 0.1565 data: 0.0690 max mem: 9390 +Train: [63] [2600/6250] eta: 0:08:16 lr: 0.000040 grad: 0.1048 (0.1054) loss: 0.8183 (0.8159) time: 0.1417 data: 0.0572 max mem: 9390 +Train: [63] [2700/6250] eta: 0:08:03 lr: 0.000040 grad: 0.1030 (0.1053) loss: 0.8127 (0.8158) time: 0.1400 data: 0.0581 max mem: 9390 +Train: [63] [2800/6250] eta: 0:07:49 lr: 0.000040 grad: 0.0978 (0.1053) loss: 0.8144 (0.8158) time: 0.1489 data: 0.0652 max mem: 9390 +Train: [63] [2900/6250] eta: 0:07:35 lr: 0.000040 grad: 0.1116 (0.1054) loss: 0.8099 (0.8157) time: 0.1163 data: 0.0373 max mem: 9390 +Train: [63] [3000/6250] eta: 0:07:21 lr: 0.000040 grad: 0.1042 (0.1054) loss: 0.8131 (0.8156) time: 0.1252 data: 0.0446 max mem: 9390 +Train: [63] [3100/6250] eta: 0:07:06 lr: 0.000040 grad: 0.1004 (0.1054) loss: 0.8129 (0.8157) time: 0.1243 data: 0.0445 max mem: 9390 +Train: [63] [3200/6250] eta: 0:06:52 lr: 0.000040 grad: 0.1090 (0.1053) loss: 0.8195 (0.8157) time: 0.1362 data: 0.0571 max mem: 9390 +Train: [63] [3300/6250] eta: 0:06:38 lr: 0.000040 grad: 0.1017 (0.1053) loss: 0.8109 (0.8156) time: 0.1451 data: 0.0649 max mem: 9390 +Train: [63] [3400/6250] eta: 0:06:25 lr: 0.000040 grad: 0.1014 (0.1053) loss: 0.8154 (0.8157) time: 0.0927 data: 0.0179 max mem: 9390 +Train: [63] [3500/6250] eta: 0:06:11 lr: 0.000040 grad: 0.1011 (0.1053) loss: 0.8208 (0.8157) time: 0.1275 data: 0.0438 max mem: 9390 +Train: [63] [3600/6250] eta: 0:05:57 lr: 0.000040 grad: 0.1030 (0.1053) loss: 0.8173 (0.8158) time: 0.1222 data: 0.0429 max mem: 9390 +Train: [63] [3700/6250] eta: 0:05:43 lr: 0.000040 grad: 0.0969 (0.1052) loss: 0.8142 (0.8159) time: 0.1209 data: 0.0371 max mem: 9390 +Train: [63] [3800/6250] eta: 0:05:29 lr: 0.000040 grad: 0.1034 (0.1052) loss: 0.8157 (0.8159) time: 0.1329 data: 0.0492 max mem: 9390 +Train: [63] [3900/6250] eta: 0:05:16 lr: 0.000040 grad: 0.0979 (0.1052) loss: 0.8179 (0.8159) time: 0.1241 data: 0.0444 max mem: 9390 +Train: [63] [4000/6250] eta: 0:05:02 lr: 0.000040 grad: 0.1010 (0.1052) loss: 0.8216 (0.8159) time: 0.1285 data: 0.0491 max mem: 9390 +Train: [63] [4100/6250] eta: 0:04:49 lr: 0.000040 grad: 0.1047 (0.1052) loss: 0.8162 (0.8160) time: 0.1554 data: 0.0706 max mem: 9390 +Train: [63] [4200/6250] eta: 0:04:36 lr: 0.000040 grad: 0.1009 (0.1052) loss: 0.8175 (0.8160) time: 0.1257 data: 0.0383 max mem: 9390 +Train: [63] [4300/6250] eta: 0:04:22 lr: 0.000040 grad: 0.1023 (0.1052) loss: 0.8181 (0.8161) time: 0.1430 data: 0.0643 max mem: 9390 +Train: [63] [4400/6250] eta: 0:04:09 lr: 0.000040 grad: 0.1041 (0.1053) loss: 0.8116 (0.8161) time: 0.1230 data: 0.0400 max mem: 9390 +Train: [63] [4500/6250] eta: 0:03:55 lr: 0.000040 grad: 0.1017 (0.1053) loss: 0.8136 (0.8161) time: 0.1304 data: 0.0483 max mem: 9390 +Train: [63] [4600/6250] eta: 0:03:42 lr: 0.000040 grad: 0.1092 (0.1054) loss: 0.8149 (0.8161) time: 0.1254 data: 0.0368 max mem: 9390 +Train: [63] [4700/6250] eta: 0:03:28 lr: 0.000040 grad: 0.1004 (0.1054) loss: 0.8202 (0.8161) time: 0.1272 data: 0.0481 max mem: 9390 +Train: [63] [4800/6250] eta: 0:03:15 lr: 0.000040 grad: 0.1027 (0.1055) loss: 0.8200 (0.8161) time: 0.1438 data: 0.0616 max mem: 9390 +Train: [63] [4900/6250] eta: 0:03:01 lr: 0.000040 grad: 0.1046 (0.1055) loss: 0.8181 (0.8161) time: 0.1265 data: 0.0461 max mem: 9390 +Train: [63] [5000/6250] eta: 0:02:48 lr: 0.000040 grad: 0.1050 (0.1056) loss: 0.8146 (0.8161) time: 0.1427 data: 0.0598 max mem: 9390 +Train: [63] [5100/6250] eta: 0:02:35 lr: 0.000040 grad: 0.1025 (0.1056) loss: 0.8134 (0.8161) time: 0.1399 data: 0.0624 max mem: 9390 +Train: [63] [5200/6250] eta: 0:02:21 lr: 0.000040 grad: 0.1101 (0.1056) loss: 0.8139 (0.8161) time: 0.1218 data: 0.0422 max mem: 9390 +Train: [63] [5300/6250] eta: 0:02:08 lr: 0.000040 grad: 0.1095 (0.1056) loss: 0.8108 (0.8160) time: 0.1577 data: 0.0812 max mem: 9390 +Train: [63] [5400/6250] eta: 0:01:55 lr: 0.000040 grad: 0.1079 (0.1056) loss: 0.8165 (0.8161) time: 0.1589 data: 0.0806 max mem: 9390 +Train: [63] [5500/6250] eta: 0:01:41 lr: 0.000040 grad: 0.1098 (0.1056) loss: 0.8222 (0.8161) time: 0.1486 data: 0.0673 max mem: 9390 +Train: [63] [5600/6250] eta: 0:01:28 lr: 0.000039 grad: 0.1063 (0.1057) loss: 0.8127 (0.8161) time: 0.1440 data: 0.0594 max mem: 9390 +Train: [63] [5700/6250] eta: 0:01:14 lr: 0.000039 grad: 0.1041 (0.1058) loss: 0.8169 (0.8160) time: 0.1181 data: 0.0340 max mem: 9390 +Train: [63] [5800/6250] eta: 0:01:01 lr: 0.000039 grad: 0.1062 (0.1059) loss: 0.8150 (0.8160) time: 0.1443 data: 0.0597 max mem: 9390 +Train: [63] [5900/6250] eta: 0:00:47 lr: 0.000039 grad: 0.1049 (0.1059) loss: 0.8148 (0.8159) time: 0.1441 data: 0.0655 max mem: 9390 +Train: [63] [6000/6250] eta: 0:00:34 lr: 0.000039 grad: 0.1077 (0.1059) loss: 0.8188 (0.8159) time: 0.1518 data: 0.0695 max mem: 9390 +Train: [63] [6100/6250] eta: 0:00:20 lr: 0.000039 grad: 0.1061 (0.1059) loss: 0.8204 (0.8159) time: 0.1056 data: 0.0181 max mem: 9390 +Train: [63] [6200/6250] eta: 0:00:06 lr: 0.000039 grad: 0.1072 (0.1060) loss: 0.8160 (0.8159) time: 0.1346 data: 0.0529 max mem: 9390 +Train: [63] [6249/6250] eta: 0:00:00 lr: 0.000039 grad: 0.1035 (0.1059) loss: 0.8130 (0.8159) time: 0.1434 data: 0.0581 max mem: 9390 +Train: [63] Total time: 0:14:17 (0.1372 s / it) +Averaged stats: lr: 0.000039 grad: 0.1035 (0.1059) loss: 0.8130 (0.8159) +Eval (hcp-train-subset): [63] [ 0/62] eta: 0:04:33 loss: 0.8417 (0.8417) time: 4.4152 data: 4.3846 max mem: 9390 +Eval (hcp-train-subset): [63] [61/62] eta: 0:00:00 loss: 0.8272 (0.8303) time: 0.1085 data: 0.0837 max mem: 9390 +Eval (hcp-train-subset): [63] Total time: 0:00:12 (0.1973 s / it) +Averaged stats (hcp-train-subset): loss: 0.8272 (0.8303) +Eval (hcp-val): [63] [ 0/62] eta: 0:03:22 loss: 0.8336 (0.8336) time: 3.2621 data: 3.1910 max mem: 9390 +Eval (hcp-val): [63] [61/62] eta: 0:00:00 loss: 0.8320 (0.8336) time: 0.1078 data: 0.0829 max mem: 9390 +Eval (hcp-val): [63] Total time: 0:00:12 (0.1937 s / it) +Averaged stats (hcp-val): loss: 0.8320 (0.8336) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +Train: [64] [ 0/6250] eta: 11:00:54 lr: 0.000039 grad: 0.5495 (0.5495) loss: 0.8747 (0.8747) time: 6.3447 data: 6.2382 max mem: 9390 +Train: [64] [ 100/6250] eta: 0:20:22 lr: 0.000039 grad: 0.1019 (0.1328) loss: 0.8304 (0.8205) time: 0.1421 data: 0.0385 max mem: 9390 +Train: [64] [ 200/6250] eta: 0:17:09 lr: 0.000039 grad: 0.1014 (0.1230) loss: 0.8159 (0.8178) time: 0.1398 data: 0.0442 max mem: 9390 +Train: [64] [ 300/6250] eta: 0:15:56 lr: 0.000039 grad: 0.0962 (0.1164) loss: 0.8136 (0.8169) time: 0.1479 data: 0.0586 max mem: 9390 +Train: [64] [ 400/6250] eta: 0:14:55 lr: 0.000039 grad: 0.1010 (0.1123) loss: 0.8133 (0.8174) time: 0.1339 data: 0.0440 max mem: 9390 +Train: [64] [ 500/6250] eta: 0:14:08 lr: 0.000039 grad: 0.0995 (0.1105) loss: 0.8268 (0.8179) time: 0.1320 data: 0.0430 max mem: 9390 +Train: [64] [ 600/6250] eta: 0:13:28 lr: 0.000039 grad: 0.0982 (0.1096) loss: 0.8144 (0.8179) time: 0.1181 data: 0.0283 max mem: 9390 +Train: [64] [ 700/6250] eta: 0:13:06 lr: 0.000039 grad: 0.1021 (0.1088) loss: 0.8144 (0.8176) time: 0.1521 data: 0.0722 max mem: 9390 +Train: [64] [ 800/6250] eta: 0:12:35 lr: 0.000039 grad: 0.1032 (0.1082) loss: 0.8104 (0.8174) time: 0.1331 data: 0.0511 max mem: 9390 +Train: [64] [ 900/6250] eta: 0:12:20 lr: 0.000039 grad: 0.0994 (0.1077) loss: 0.8167 (0.8175) time: 0.1493 data: 0.0693 max mem: 9390 +Train: [64] [1000/6250] eta: 0:12:03 lr: 0.000039 grad: 0.1049 (0.1073) loss: 0.8133 (0.8173) time: 0.1330 data: 0.0480 max mem: 9390 +Train: [64] [1100/6250] eta: 0:11:44 lr: 0.000039 grad: 0.1068 (0.1068) loss: 0.8176 (0.8173) time: 0.1275 data: 0.0501 max mem: 9390 +Train: [64] [1200/6250] eta: 0:11:28 lr: 0.000039 grad: 0.0994 (0.1064) loss: 0.8120 (0.8170) time: 0.1477 data: 0.0707 max mem: 9390 +Train: [64] [1300/6250] eta: 0:11:14 lr: 0.000039 grad: 0.1055 (0.1062) loss: 0.8094 (0.8167) time: 0.1288 data: 0.0459 max mem: 9390 +Train: [64] [1400/6250] eta: 0:11:05 lr: 0.000039 grad: 0.1050 (0.1061) loss: 0.8196 (0.8166) time: 0.1812 data: 0.1007 max mem: 9390 +Train: [64] [1500/6250] eta: 0:10:55 lr: 0.000039 grad: 0.1019 (0.1060) loss: 0.8138 (0.8166) time: 0.1698 data: 0.0931 max mem: 9390 +Train: [64] [1600/6250] eta: 0:10:43 lr: 0.000039 grad: 0.0982 (0.1057) loss: 0.8132 (0.8166) time: 0.1409 data: 0.0647 max mem: 9390 +Train: [64] [1700/6250] eta: 0:10:30 lr: 0.000039 grad: 0.1029 (0.1055) loss: 0.8168 (0.8166) time: 0.1380 data: 0.0530 max mem: 9390 +Train: [64] [1800/6250] eta: 0:10:16 lr: 0.000039 grad: 0.1027 (0.1055) loss: 0.8187 (0.8166) time: 0.1396 data: 0.0607 max mem: 9390 +Train: [64] [1900/6250] eta: 0:10:00 lr: 0.000039 grad: 0.1006 (0.1055) loss: 0.8163 (0.8165) time: 0.1383 data: 0.0571 max mem: 9390 +Train: [64] [2000/6250] eta: 0:09:43 lr: 0.000039 grad: 0.1044 (0.1056) loss: 0.8120 (0.8164) time: 0.1316 data: 0.0528 max mem: 9390 +Train: [64] [2100/6250] eta: 0:09:27 lr: 0.000039 grad: 0.1127 (0.1057) loss: 0.8082 (0.8162) time: 0.0978 data: 0.0176 max mem: 9390 +Train: [64] [2200/6250] eta: 0:09:11 lr: 0.000039 grad: 0.1013 (0.1057) loss: 0.8158 (0.8162) time: 0.1263 data: 0.0462 max mem: 9390 +Train: [64] [2300/6250] eta: 0:08:54 lr: 0.000039 grad: 0.1006 (0.1058) loss: 0.8074 (0.8161) time: 0.1285 data: 0.0492 max mem: 9390 +Train: [64] [2400/6250] eta: 0:08:38 lr: 0.000039 grad: 0.1067 (0.1060) loss: 0.8152 (0.8159) time: 0.1279 data: 0.0452 max mem: 9390 +Train: [64] [2500/6250] eta: 0:08:25 lr: 0.000039 grad: 0.1068 (0.1061) loss: 0.8159 (0.8157) time: 0.1550 data: 0.0782 max mem: 9390 +Train: [64] [2600/6250] eta: 0:08:12 lr: 0.000039 grad: 0.1072 (0.1063) loss: 0.8148 (0.8157) time: 0.1177 data: 0.0338 max mem: 9390 +Train: [64] [2700/6250] eta: 0:07:58 lr: 0.000038 grad: 0.1075 (0.1065) loss: 0.8115 (0.8156) time: 0.1473 data: 0.0651 max mem: 9390 +Train: [64] [2800/6250] eta: 0:07:44 lr: 0.000038 grad: 0.1032 (0.1067) loss: 0.8155 (0.8154) time: 0.1326 data: 0.0536 max mem: 9390 +Train: [64] [2900/6250] eta: 0:07:30 lr: 0.000038 grad: 0.1129 (0.1069) loss: 0.8110 (0.8153) time: 0.1279 data: 0.0455 max mem: 9390 +Train: [64] [3000/6250] eta: 0:07:16 lr: 0.000038 grad: 0.1048 (0.1070) loss: 0.8167 (0.8152) time: 0.1362 data: 0.0445 max mem: 9390 +Train: [64] [3100/6250] eta: 0:07:04 lr: 0.000038 grad: 0.1107 (0.1072) loss: 0.8143 (0.8152) time: 0.1170 data: 0.0223 max mem: 9390 +Train: [64] [3200/6250] eta: 0:06:50 lr: 0.000038 grad: 0.1048 (0.1074) loss: 0.8132 (0.8151) time: 0.1256 data: 0.0470 max mem: 9390 +Train: [64] [3300/6250] eta: 0:06:36 lr: 0.000038 grad: 0.1109 (0.1076) loss: 0.8115 (0.8151) time: 0.1442 data: 0.0679 max mem: 9390 +Train: [64] [3400/6250] eta: 0:06:22 lr: 0.000038 grad: 0.1044 (0.1076) loss: 0.8180 (0.8151) time: 0.1360 data: 0.0588 max mem: 9390 +Train: [64] [3500/6250] eta: 0:06:11 lr: 0.000038 grad: 0.1062 (0.1077) loss: 0.8055 (0.8150) time: 0.2076 data: 0.1113 max mem: 9390 +Train: [64] [3600/6250] eta: 0:05:57 lr: 0.000038 grad: 0.1104 (0.1079) loss: 0.8180 (0.8149) time: 0.1436 data: 0.0601 max mem: 9390 +Train: [64] [3700/6250] eta: 0:05:43 lr: 0.000038 grad: 0.1085 (0.1080) loss: 0.8127 (0.8149) time: 0.1534 data: 0.0730 max mem: 9390 +Train: [64] [3800/6250] eta: 0:05:31 lr: 0.000038 grad: 0.1003 (0.1080) loss: 0.8141 (0.8149) time: 0.1587 data: 0.0779 max mem: 9390 +Train: [64] [3900/6250] eta: 0:05:17 lr: 0.000038 grad: 0.1076 (0.1082) loss: 0.8123 (0.8149) time: 0.1252 data: 0.0479 max mem: 9390 +Train: [64] [4000/6250] eta: 0:05:03 lr: 0.000038 grad: 0.1087 (0.1083) loss: 0.8155 (0.8148) time: 0.1370 data: 0.0548 max mem: 9390 +Train: [64] [4100/6250] eta: 0:04:53 lr: 0.000038 grad: 0.1104 (0.1085) loss: 0.8135 (0.8149) time: 0.3457 data: 0.2433 max mem: 9390 +Train: [64] [4200/6250] eta: 0:04:38 lr: 0.000038 grad: 0.1123 (0.1087) loss: 0.8140 (0.8148) time: 0.1495 data: 0.0674 max mem: 9390 +Train: [64] [4300/6250] eta: 0:04:24 lr: 0.000038 grad: 0.1128 (0.1088) loss: 0.8123 (0.8148) time: 0.1334 data: 0.0533 max mem: 9390 +Train: [64] [4400/6250] eta: 0:04:11 lr: 0.000038 grad: 0.1069 (0.1089) loss: 0.8222 (0.8147) time: 0.1393 data: 0.0583 max mem: 9390 +Train: [64] [4500/6250] eta: 0:03:57 lr: 0.000038 grad: 0.1075 (0.1090) loss: 0.8155 (0.8147) time: 0.1265 data: 0.0474 max mem: 9390 +Train: [64] [4600/6250] eta: 0:03:44 lr: 0.000038 grad: 0.1091 (0.1091) loss: 0.8156 (0.8147) time: 0.1481 data: 0.0719 max mem: 9390 +Train: [64] [4700/6250] eta: 0:03:31 lr: 0.000038 grad: 0.1103 (0.1092) loss: 0.8116 (0.8146) time: 0.1022 data: 0.0088 max mem: 9390 +Train: [64] [4800/6250] eta: 0:03:17 lr: 0.000038 grad: 0.1189 (0.1093) loss: 0.8066 (0.8146) time: 0.1413 data: 0.0633 max mem: 9390 +Train: [64] [4900/6250] eta: 0:03:04 lr: 0.000038 grad: 0.1088 (0.1094) loss: 0.8091 (0.8146) time: 0.1573 data: 0.0806 max mem: 9390 +Train: [64] [5000/6250] eta: 0:02:51 lr: 0.000038 grad: 0.1039 (0.1095) loss: 0.8139 (0.8145) time: 0.1624 data: 0.0688 max mem: 9390 +Train: [64] [5100/6250] eta: 0:02:37 lr: 0.000038 grad: 0.1091 (0.1095) loss: 0.8120 (0.8144) time: 0.1051 data: 0.0201 max mem: 9390 +Train: [64] [5200/6250] eta: 0:02:24 lr: 0.000038 grad: 0.1065 (0.1096) loss: 0.8084 (0.8144) time: 0.1447 data: 0.0692 max mem: 9390 +Train: [64] [5300/6250] eta: 0:02:10 lr: 0.000038 grad: 0.1025 (0.1095) loss: 0.8139 (0.8144) time: 0.1690 data: 0.0914 max mem: 9390 +Train: [64] [5400/6250] eta: 0:01:56 lr: 0.000038 grad: 0.1072 (0.1096) loss: 0.8145 (0.8144) time: 0.1365 data: 0.0586 max mem: 9390 +Train: [64] [5500/6250] eta: 0:01:42 lr: 0.000038 grad: 0.1062 (0.1096) loss: 0.8110 (0.8144) time: 0.1417 data: 0.0629 max mem: 9390 +Train: [64] [5600/6250] eta: 0:01:29 lr: 0.000038 grad: 0.1076 (0.1095) loss: 0.8102 (0.8143) time: 0.1557 data: 0.0779 max mem: 9390 +Train: [64] [5700/6250] eta: 0:01:15 lr: 0.000038 grad: 0.1052 (0.1096) loss: 0.8172 (0.8143) time: 0.1587 data: 0.0797 max mem: 9390 +Train: [64] [5800/6250] eta: 0:01:02 lr: 0.000038 grad: 0.1172 (0.1096) loss: 0.8115 (0.8142) time: 0.1736 data: 0.0970 max mem: 9390 +Train: [64] [5900/6250] eta: 0:00:48 lr: 0.000037 grad: 0.1083 (0.1096) loss: 0.8107 (0.8142) time: 0.1437 data: 0.0592 max mem: 9390 +Train: [64] [6000/6250] eta: 0:00:34 lr: 0.000037 grad: 0.1061 (0.1096) loss: 0.8072 (0.8141) time: 0.1237 data: 0.0460 max mem: 9390 +Train: [64] [6100/6250] eta: 0:00:20 lr: 0.000037 grad: 0.1037 (0.1096) loss: 0.8162 (0.8141) time: 0.1464 data: 0.0651 max mem: 9390 +Train: [64] [6200/6250] eta: 0:00:06 lr: 0.000037 grad: 0.1147 (0.1096) loss: 0.8079 (0.8141) time: 0.1780 data: 0.0962 max mem: 9390 +Train: [64] [6249/6250] eta: 0:00:00 lr: 0.000037 grad: 0.1048 (0.1096) loss: 0.8126 (0.8141) time: 0.1201 data: 0.0371 max mem: 9390 +Train: [64] Total time: 0:14:25 (0.1385 s / it) +Averaged stats: lr: 0.000037 grad: 0.1048 (0.1096) loss: 0.8126 (0.8141) +Eval (hcp-train-subset): [64] [ 0/62] eta: 0:03:27 loss: 0.8397 (0.8397) time: 3.3393 data: 3.2707 max mem: 9390 +Eval (hcp-train-subset): [64] [61/62] eta: 0:00:00 loss: 0.8272 (0.8298) time: 0.1111 data: 0.0848 max mem: 9390 +Eval (hcp-train-subset): [64] Total time: 0:00:12 (0.1953 s / it) +Averaged stats (hcp-train-subset): loss: 0.8272 (0.8298) +Making plots (hcp-train-subset): example=52 +Eval (hcp-val): [64] [ 0/62] eta: 0:04:44 loss: 0.8303 (0.8303) time: 4.5900 data: 4.5227 max mem: 9390 +Eval (hcp-val): [64] [61/62] eta: 0:00:00 loss: 0.8306 (0.8329) time: 0.1248 data: 0.0993 max mem: 9390 +Eval (hcp-val): [64] Total time: 0:00:12 (0.2076 s / it) +Averaged stats (hcp-val): loss: 0.8306 (0.8329) +Making plots (hcp-val): example=1 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +Train: [65] [ 0/6250] eta: 10:46:31 lr: 0.000037 grad: 0.1123 (0.1123) loss: 0.8565 (0.8565) time: 6.2067 data: 6.1027 max mem: 9390 +Train: [65] [ 100/6250] eta: 0:19:39 lr: 0.000037 grad: 0.0998 (0.1169) loss: 0.8304 (0.8306) time: 0.1100 data: 0.0120 max mem: 9390 +Train: [65] [ 200/6250] eta: 0:16:49 lr: 0.000037 grad: 0.1003 (0.1148) loss: 0.8262 (0.8265) time: 0.1193 data: 0.0228 max mem: 9390 +Train: [65] [ 300/6250] eta: 0:15:39 lr: 0.000037 grad: 0.1091 (0.1139) loss: 0.8149 (0.8248) time: 0.1167 data: 0.0309 max mem: 9390 +Train: [65] [ 400/6250] eta: 0:14:46 lr: 0.000037 grad: 0.0999 (0.1130) loss: 0.8263 (0.8234) time: 0.1325 data: 0.0563 max mem: 9390 +Train: [65] [ 500/6250] eta: 0:14:04 lr: 0.000037 grad: 0.1020 (0.1119) loss: 0.8256 (0.8228) time: 0.1345 data: 0.0450 max mem: 9390 +Train: [65] [ 600/6250] eta: 0:13:29 lr: 0.000037 grad: 0.0981 (0.1098) loss: 0.8256 (0.8228) time: 0.1160 data: 0.0302 max mem: 9390 +Train: [65] [ 700/6250] eta: 0:13:01 lr: 0.000037 grad: 0.0994 (0.1086) loss: 0.8223 (0.8228) time: 0.1403 data: 0.0622 max mem: 9390 +Train: [65] [ 800/6250] eta: 0:12:46 lr: 0.000037 grad: 0.1054 (0.1078) loss: 0.8237 (0.8230) time: 0.1178 data: 0.0107 max mem: 9390 +Train: [65] [ 900/6250] eta: 0:12:37 lr: 0.000037 grad: 0.1017 (0.1074) loss: 0.8229 (0.8228) time: 0.1480 data: 0.0672 max mem: 9390 +Train: [65] [1000/6250] eta: 0:12:23 lr: 0.000037 grad: 0.1009 (0.1070) loss: 0.8150 (0.8224) time: 0.1372 data: 0.0574 max mem: 9390 +Train: [65] [1100/6250] eta: 0:12:25 lr: 0.000037 grad: 0.0981 (0.1067) loss: 0.8186 (0.8218) time: 0.2406 data: 0.1568 max mem: 9390 +Train: [65] [1200/6250] eta: 0:12:04 lr: 0.000037 grad: 0.1028 (0.1068) loss: 0.8114 (0.8212) time: 0.1225 data: 0.0383 max mem: 9390 +Train: [65] [1300/6250] eta: 0:11:48 lr: 0.000037 grad: 0.1132 (0.1071) loss: 0.8167 (0.8205) time: 0.1573 data: 0.0811 max mem: 9390 +Train: [65] [1400/6250] eta: 0:11:32 lr: 0.000037 grad: 0.1021 (0.1070) loss: 0.8190 (0.8201) time: 0.1639 data: 0.0869 max mem: 9390 +Train: [65] [1500/6250] eta: 0:11:17 lr: 0.000037 grad: 0.1082 (0.1072) loss: 0.8134 (0.8196) time: 0.1359 data: 0.0613 max mem: 9390 +Train: [65] [1600/6250] eta: 0:11:04 lr: 0.000037 grad: 0.1059 (0.1072) loss: 0.8041 (0.8191) time: 0.1486 data: 0.0694 max mem: 9390 +Train: [65] [1700/6250] eta: 0:10:50 lr: 0.000037 grad: 0.1059 (0.1074) loss: 0.8113 (0.8187) time: 0.1495 data: 0.0643 max mem: 9390 +Train: [65] [1800/6250] eta: 0:10:34 lr: 0.000037 grad: 0.1041 (0.1075) loss: 0.8140 (0.8183) time: 0.1403 data: 0.0549 max mem: 9390 +Train: [65] [1900/6250] eta: 0:10:18 lr: 0.000037 grad: 0.1144 (0.1077) loss: 0.8045 (0.8179) time: 0.1397 data: 0.0558 max mem: 9390 +Train: [65] [2000/6250] eta: 0:10:01 lr: 0.000037 grad: 0.1052 (0.1079) loss: 0.8083 (0.8175) time: 0.1162 data: 0.0398 max mem: 9390 +Train: [65] [2100/6250] eta: 0:09:43 lr: 0.000037 grad: 0.1059 (0.1078) loss: 0.8077 (0.8173) time: 0.1149 data: 0.0354 max mem: 9390 +Train: [65] [2200/6250] eta: 0:09:26 lr: 0.000037 grad: 0.1074 (0.1078) loss: 0.8085 (0.8171) time: 0.1384 data: 0.0619 max mem: 9390 +Train: [65] [2300/6250] eta: 0:09:08 lr: 0.000037 grad: 0.1017 (0.1078) loss: 0.8129 (0.8170) time: 0.1096 data: 0.0275 max mem: 9390 +Train: [65] [2400/6250] eta: 0:08:51 lr: 0.000037 grad: 0.1015 (0.1077) loss: 0.8164 (0.8168) time: 0.1194 data: 0.0419 max mem: 9390 +Train: [65] [2500/6250] eta: 0:08:34 lr: 0.000037 grad: 0.1057 (0.1077) loss: 0.8168 (0.8167) time: 0.1179 data: 0.0341 max mem: 9390 +Train: [65] [2600/6250] eta: 0:08:18 lr: 0.000037 grad: 0.1078 (0.1076) loss: 0.8091 (0.8166) time: 0.1194 data: 0.0403 max mem: 9390 +Train: [65] [2700/6250] eta: 0:08:03 lr: 0.000037 grad: 0.1037 (0.1075) loss: 0.8130 (0.8165) time: 0.1085 data: 0.0279 max mem: 9390 +Train: [65] [2800/6250] eta: 0:07:48 lr: 0.000037 grad: 0.0985 (0.1075) loss: 0.8195 (0.8164) time: 0.1336 data: 0.0494 max mem: 9390 +Train: [65] [2900/6250] eta: 0:07:35 lr: 0.000037 grad: 0.1019 (0.1074) loss: 0.8113 (0.8164) time: 0.1808 data: 0.1046 max mem: 9390 +Train: [65] [3000/6250] eta: 0:07:20 lr: 0.000036 grad: 0.0991 (0.1073) loss: 0.8167 (0.8164) time: 0.1340 data: 0.0545 max mem: 9390 +Train: [65] [3100/6250] eta: 0:07:07 lr: 0.000036 grad: 0.1080 (0.1073) loss: 0.8103 (0.8163) time: 0.1250 data: 0.0515 max mem: 9390 +Train: [65] [3200/6250] eta: 0:06:54 lr: 0.000036 grad: 0.1012 (0.1072) loss: 0.8117 (0.8163) time: 0.1082 data: 0.0303 max mem: 9390 +Train: [65] [3300/6250] eta: 0:06:39 lr: 0.000036 grad: 0.1103 (0.1073) loss: 0.8072 (0.8163) time: 0.1282 data: 0.0469 max mem: 9390 +Train: [65] [3400/6250] eta: 0:06:26 lr: 0.000036 grad: 0.1039 (0.1073) loss: 0.8195 (0.8163) time: 0.1273 data: 0.0502 max mem: 9390 +Train: [65] [3500/6250] eta: 0:06:13 lr: 0.000036 grad: 0.0979 (0.1073) loss: 0.8186 (0.8163) time: 0.1481 data: 0.0636 max mem: 9390 +Train: [65] [3600/6250] eta: 0:06:00 lr: 0.000036 grad: 0.1059 (0.1073) loss: 0.8163 (0.8163) time: 0.1178 data: 0.0399 max mem: 9390 +Train: [65] [3700/6250] eta: 0:05:47 lr: 0.000036 grad: 0.1085 (0.1074) loss: 0.8118 (0.8163) time: 0.1358 data: 0.0572 max mem: 9390 +Train: [65] [3800/6250] eta: 0:05:33 lr: 0.000036 grad: 0.1001 (0.1074) loss: 0.8182 (0.8162) time: 0.1285 data: 0.0424 max mem: 9390 +Train: [65] [3900/6250] eta: 0:05:19 lr: 0.000036 grad: 0.1095 (0.1075) loss: 0.8112 (0.8162) time: 0.1523 data: 0.0767 max mem: 9390 +Train: [65] [4000/6250] eta: 0:05:06 lr: 0.000036 grad: 0.1019 (0.1075) loss: 0.8171 (0.8162) time: 0.1724 data: 0.0667 max mem: 9390 +Train: [65] [4100/6250] eta: 0:04:53 lr: 0.000036 grad: 0.1099 (0.1076) loss: 0.8165 (0.8161) time: 0.1482 data: 0.0709 max mem: 9390 +Train: [65] [4200/6250] eta: 0:04:39 lr: 0.000036 grad: 0.1020 (0.1076) loss: 0.8213 (0.8162) time: 0.1419 data: 0.0548 max mem: 9390 +Train: [65] [4300/6250] eta: 0:04:25 lr: 0.000036 grad: 0.1077 (0.1077) loss: 0.8176 (0.8162) time: 0.1348 data: 0.0615 max mem: 9390 +Train: [65] [4400/6250] eta: 0:04:12 lr: 0.000036 grad: 0.1039 (0.1077) loss: 0.8213 (0.8162) time: 0.1378 data: 0.0536 max mem: 9390 +Train: [65] [4500/6250] eta: 0:03:58 lr: 0.000036 grad: 0.1076 (0.1078) loss: 0.8126 (0.8161) time: 0.1189 data: 0.0377 max mem: 9390 +Train: [65] [4600/6250] eta: 0:03:45 lr: 0.000036 grad: 0.1098 (0.1078) loss: 0.8119 (0.8161) time: 0.1288 data: 0.0450 max mem: 9390 +Train: [65] [4700/6250] eta: 0:03:31 lr: 0.000036 grad: 0.1049 (0.1079) loss: 0.8137 (0.8160) time: 0.1503 data: 0.0726 max mem: 9390 +Train: [65] [4800/6250] eta: 0:03:17 lr: 0.000036 grad: 0.1082 (0.1079) loss: 0.8197 (0.8160) time: 0.1289 data: 0.0466 max mem: 9390 +Train: [65] [4900/6250] eta: 0:03:04 lr: 0.000036 grad: 0.1047 (0.1079) loss: 0.8126 (0.8160) time: 0.1391 data: 0.0622 max mem: 9390 +Train: [65] [5000/6250] eta: 0:02:50 lr: 0.000036 grad: 0.1047 (0.1080) loss: 0.8151 (0.8159) time: 0.1546 data: 0.0732 max mem: 9390 +Train: [65] [5100/6250] eta: 0:02:38 lr: 0.000036 grad: 0.1006 (0.1080) loss: 0.8146 (0.8159) time: 0.2882 data: 0.2041 max mem: 9390 +Train: [65] [5200/6250] eta: 0:02:24 lr: 0.000036 grad: 0.1024 (0.1080) loss: 0.8198 (0.8159) time: 0.1534 data: 0.0745 max mem: 9390 +Train: [65] [5300/6250] eta: 0:02:10 lr: 0.000036 grad: 0.1105 (0.1081) loss: 0.8120 (0.8159) time: 0.1255 data: 0.0474 max mem: 9390 +Train: [65] [5400/6250] eta: 0:01:57 lr: 0.000036 grad: 0.1105 (0.1081) loss: 0.8149 (0.8159) time: 0.1533 data: 0.0704 max mem: 9390 +Train: [65] [5500/6250] eta: 0:01:43 lr: 0.000036 grad: 0.1077 (0.1081) loss: 0.8112 (0.8158) time: 0.1718 data: 0.0940 max mem: 9390 +Train: [65] [5600/6250] eta: 0:01:29 lr: 0.000036 grad: 0.1042 (0.1081) loss: 0.8180 (0.8158) time: 0.1466 data: 0.0705 max mem: 9390 +Train: [65] [5700/6250] eta: 0:01:16 lr: 0.000036 grad: 0.1107 (0.1082) loss: 0.8136 (0.8157) time: 0.1388 data: 0.0586 max mem: 9390 +Train: [65] [5800/6250] eta: 0:01:02 lr: 0.000036 grad: 0.1103 (0.1082) loss: 0.8108 (0.8157) time: 0.1393 data: 0.0606 max mem: 9390 +Train: [65] [5900/6250] eta: 0:00:48 lr: 0.000036 grad: 0.1054 (0.1083) loss: 0.8026 (0.8156) time: 0.1155 data: 0.0322 max mem: 9390 +Train: [65] [6000/6250] eta: 0:00:34 lr: 0.000036 grad: 0.1048 (0.1083) loss: 0.8139 (0.8155) time: 0.1334 data: 0.0531 max mem: 9390 +Train: [65] [6100/6250] eta: 0:00:20 lr: 0.000036 grad: 0.1044 (0.1083) loss: 0.8069 (0.8154) time: 0.1324 data: 0.0444 max mem: 9390 +Train: [65] [6200/6250] eta: 0:00:06 lr: 0.000036 grad: 0.1123 (0.1084) loss: 0.8077 (0.8153) time: 0.1444 data: 0.0643 max mem: 9390 +Train: [65] [6249/6250] eta: 0:00:00 lr: 0.000036 grad: 0.1113 (0.1085) loss: 0.8085 (0.8153) time: 0.1290 data: 0.0408 max mem: 9390 +Train: [65] Total time: 0:14:29 (0.1391 s / it) +Averaged stats: lr: 0.000036 grad: 0.1113 (0.1085) loss: 0.8085 (0.8153) +Eval (hcp-train-subset): [65] [ 0/62] eta: 0:03:57 loss: 0.8403 (0.8403) time: 3.8366 data: 3.7569 max mem: 9390 +Eval (hcp-train-subset): [65] [61/62] eta: 0:00:00 loss: 0.8269 (0.8295) time: 0.1322 data: 0.1055 max mem: 9390 +Eval (hcp-train-subset): [65] Total time: 0:00:12 (0.2019 s / it) +Averaged stats (hcp-train-subset): loss: 0.8269 (0.8295) +Eval (hcp-val): [65] [ 0/62] eta: 0:05:22 loss: 0.8307 (0.8307) time: 5.1953 data: 5.1647 max mem: 9390 +Eval (hcp-val): [65] [61/62] eta: 0:00:00 loss: 0.8323 (0.8328) time: 0.1357 data: 0.1102 max mem: 9390 +Eval (hcp-val): [65] Total time: 0:00:13 (0.2202 s / it) +Averaged stats (hcp-val): loss: 0.8323 (0.8328) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +Train: [66] [ 0/6250] eta: 7:31:49 lr: 0.000036 grad: 0.1579 (0.1579) loss: 0.8553 (0.8553) time: 4.3375 data: 4.1763 max mem: 9390 +Train: [66] [ 100/6250] eta: 0:20:06 lr: 0.000035 grad: 0.1238 (0.1283) loss: 0.8202 (0.8286) time: 0.1439 data: 0.0504 max mem: 9390 +Train: [66] [ 200/6250] eta: 0:16:59 lr: 0.000035 grad: 0.1134 (0.1270) loss: 0.8126 (0.8207) time: 0.1374 data: 0.0435 max mem: 9390 +Train: [66] [ 300/6250] eta: 0:15:57 lr: 0.000035 grad: 0.1100 (0.1232) loss: 0.8143 (0.8188) time: 0.1302 data: 0.0476 max mem: 9390 +Train: [66] [ 400/6250] eta: 0:15:02 lr: 0.000035 grad: 0.1053 (0.1215) loss: 0.8011 (0.8169) time: 0.1260 data: 0.0408 max mem: 9390 +Train: [66] [ 500/6250] eta: 0:14:17 lr: 0.000035 grad: 0.1040 (0.1191) loss: 0.8095 (0.8160) time: 0.0926 data: 0.0046 max mem: 9390 +Train: [66] [ 600/6250] eta: 0:13:45 lr: 0.000035 grad: 0.1100 (0.1175) loss: 0.8110 (0.8155) time: 0.1284 data: 0.0433 max mem: 9390 +Train: [66] [ 700/6250] eta: 0:13:13 lr: 0.000035 grad: 0.1128 (0.1169) loss: 0.8106 (0.8147) time: 0.1282 data: 0.0427 max mem: 9390 +Train: [66] [ 800/6250] eta: 0:12:50 lr: 0.000035 grad: 0.1015 (0.1160) loss: 0.8150 (0.8144) time: 0.1291 data: 0.0447 max mem: 9390 +Train: [66] [ 900/6250] eta: 0:12:33 lr: 0.000035 grad: 0.1079 (0.1154) loss: 0.8153 (0.8143) time: 0.1454 data: 0.0659 max mem: 9390 +Train: [66] [1000/6250] eta: 0:12:18 lr: 0.000035 grad: 0.0999 (0.1146) loss: 0.8161 (0.8145) time: 0.1527 data: 0.0755 max mem: 9390 +Train: [66] [1100/6250] eta: 0:11:58 lr: 0.000035 grad: 0.0998 (0.1140) loss: 0.8202 (0.8145) time: 0.1219 data: 0.0401 max mem: 9390 +Train: [66] [1200/6250] eta: 0:11:39 lr: 0.000035 grad: 0.1060 (0.1136) loss: 0.8124 (0.8144) time: 0.1196 data: 0.0400 max mem: 9390 +Train: [66] [1300/6250] eta: 0:11:28 lr: 0.000035 grad: 0.1039 (0.1132) loss: 0.8135 (0.8142) time: 0.1132 data: 0.0340 max mem: 9390 +Train: [66] [1400/6250] eta: 0:11:12 lr: 0.000035 grad: 0.1077 (0.1129) loss: 0.8053 (0.8141) time: 0.1166 data: 0.0343 max mem: 9390 +Train: [66] [1500/6250] eta: 0:11:02 lr: 0.000035 grad: 0.1049 (0.1128) loss: 0.8155 (0.8140) time: 0.1629 data: 0.0789 max mem: 9390 +Train: [66] [1600/6250] eta: 0:10:50 lr: 0.000035 grad: 0.1047 (0.1124) loss: 0.8121 (0.8141) time: 0.1475 data: 0.0609 max mem: 9390 +Train: [66] [1700/6250] eta: 0:10:38 lr: 0.000035 grad: 0.1101 (0.1122) loss: 0.8203 (0.8141) time: 0.1598 data: 0.0789 max mem: 9390 +Train: [66] [1800/6250] eta: 0:10:24 lr: 0.000035 grad: 0.1062 (0.1119) loss: 0.8132 (0.8141) time: 0.1335 data: 0.0474 max mem: 9390 +Train: [66] [1900/6250] eta: 0:10:08 lr: 0.000035 grad: 0.1051 (0.1117) loss: 0.8152 (0.8141) time: 0.1285 data: 0.0488 max mem: 9390 +Train: [66] [2000/6250] eta: 0:09:52 lr: 0.000035 grad: 0.1088 (0.1115) loss: 0.8184 (0.8142) time: 0.1224 data: 0.0377 max mem: 9390 +Train: [66] [2100/6250] eta: 0:09:34 lr: 0.000035 grad: 0.1101 (0.1114) loss: 0.8114 (0.8140) time: 0.1069 data: 0.0223 max mem: 9390 +Train: [66] [2200/6250] eta: 0:09:17 lr: 0.000035 grad: 0.1136 (0.1115) loss: 0.8078 (0.8138) time: 0.1283 data: 0.0524 max mem: 9390 +Train: [66] [2300/6250] eta: 0:08:59 lr: 0.000035 grad: 0.1081 (0.1115) loss: 0.8101 (0.8137) time: 0.1083 data: 0.0303 max mem: 9390 +Train: [66] [2400/6250] eta: 0:08:43 lr: 0.000035 grad: 0.1126 (0.1115) loss: 0.8129 (0.8136) time: 0.1208 data: 0.0406 max mem: 9390 +Train: [66] [2500/6250] eta: 0:08:27 lr: 0.000035 grad: 0.1102 (0.1115) loss: 0.8146 (0.8136) time: 0.1310 data: 0.0551 max mem: 9390 +Train: [66] [2600/6250] eta: 0:08:14 lr: 0.000035 grad: 0.1055 (0.1114) loss: 0.8148 (0.8135) time: 0.1346 data: 0.0503 max mem: 9390 +Train: [66] [2700/6250] eta: 0:08:00 lr: 0.000035 grad: 0.1077 (0.1115) loss: 0.8136 (0.8135) time: 0.1231 data: 0.0424 max mem: 9390 +Train: [66] [2800/6250] eta: 0:07:46 lr: 0.000035 grad: 0.1127 (0.1115) loss: 0.8197 (0.8136) time: 0.1288 data: 0.0510 max mem: 9390 +Train: [66] [2900/6250] eta: 0:07:32 lr: 0.000035 grad: 0.1007 (0.1114) loss: 0.8205 (0.8136) time: 0.1385 data: 0.0584 max mem: 9390 +Train: [66] [3000/6250] eta: 0:07:19 lr: 0.000035 grad: 0.1036 (0.1114) loss: 0.8170 (0.8137) time: 0.1311 data: 0.0490 max mem: 9390 +Train: [66] [3100/6250] eta: 0:07:05 lr: 0.000035 grad: 0.1073 (0.1114) loss: 0.8130 (0.8137) time: 0.1395 data: 0.0596 max mem: 9390 +Train: [66] [3200/6250] eta: 0:06:52 lr: 0.000035 grad: 0.1089 (0.1114) loss: 0.8055 (0.8136) time: 0.1401 data: 0.0598 max mem: 9390 +Train: [66] [3300/6250] eta: 0:06:41 lr: 0.000035 grad: 0.1075 (0.1115) loss: 0.8169 (0.8136) time: 0.1043 data: 0.0269 max mem: 9390 +Train: [66] [3400/6250] eta: 0:06:26 lr: 0.000035 grad: 0.1039 (0.1115) loss: 0.8174 (0.8136) time: 0.1232 data: 0.0455 max mem: 9390 +Train: [66] [3500/6250] eta: 0:06:12 lr: 0.000034 grad: 0.1146 (0.1116) loss: 0.8135 (0.8136) time: 0.1246 data: 0.0416 max mem: 9390 +Train: [66] [3600/6250] eta: 0:06:00 lr: 0.000034 grad: 0.1080 (0.1116) loss: 0.8070 (0.8135) time: 0.2112 data: 0.0964 max mem: 9390 +Train: [66] [3700/6250] eta: 0:05:46 lr: 0.000034 grad: 0.1083 (0.1116) loss: 0.8112 (0.8134) time: 0.1331 data: 0.0499 max mem: 9390 +Train: [66] [3800/6250] eta: 0:05:33 lr: 0.000034 grad: 0.1128 (0.1116) loss: 0.8116 (0.8133) time: 0.1365 data: 0.0562 max mem: 9390 +Train: [66] [3900/6250] eta: 0:05:19 lr: 0.000034 grad: 0.1154 (0.1118) loss: 0.8053 (0.8132) time: 0.1337 data: 0.0582 max mem: 9390 +Train: [66] [4000/6250] eta: 0:05:05 lr: 0.000034 grad: 0.1138 (0.1120) loss: 0.8070 (0.8131) time: 0.1241 data: 0.0465 max mem: 9390 +Train: [66] [4100/6250] eta: 0:04:52 lr: 0.000034 grad: 0.1139 (0.1121) loss: 0.8063 (0.8130) time: 0.1367 data: 0.0588 max mem: 9390 +Train: [66] [4200/6250] eta: 0:04:38 lr: 0.000034 grad: 0.1231 (0.1123) loss: 0.7979 (0.8129) time: 0.1427 data: 0.0623 max mem: 9390 +Train: [66] [4300/6250] eta: 0:04:24 lr: 0.000034 grad: 0.1132 (0.1123) loss: 0.8141 (0.8128) time: 0.1327 data: 0.0500 max mem: 9390 +Train: [66] [4400/6250] eta: 0:04:10 lr: 0.000034 grad: 0.1124 (0.1124) loss: 0.8083 (0.8127) time: 0.1568 data: 0.0810 max mem: 9390 +Train: [66] [4500/6250] eta: 0:03:57 lr: 0.000034 grad: 0.1124 (0.1124) loss: 0.8140 (0.8127) time: 0.1137 data: 0.0349 max mem: 9390 +Train: [66] [4600/6250] eta: 0:03:43 lr: 0.000034 grad: 0.1107 (0.1125) loss: 0.8113 (0.8127) time: 0.1518 data: 0.0737 max mem: 9390 +Train: [66] [4700/6250] eta: 0:03:30 lr: 0.000034 grad: 0.1103 (0.1125) loss: 0.8107 (0.8127) time: 0.1527 data: 0.0725 max mem: 9390 +Train: [66] [4800/6250] eta: 0:03:16 lr: 0.000034 grad: 0.1159 (0.1125) loss: 0.8125 (0.8127) time: 0.1257 data: 0.0437 max mem: 9390 +Train: [66] [4900/6250] eta: 0:03:03 lr: 0.000034 grad: 0.1080 (0.1125) loss: 0.8110 (0.8127) time: 0.1454 data: 0.0665 max mem: 9390 +Train: [66] [5000/6250] eta: 0:02:49 lr: 0.000034 grad: 0.1001 (0.1124) loss: 0.8131 (0.8127) time: 0.1552 data: 0.0792 max mem: 9390 +Train: [66] [5100/6250] eta: 0:02:36 lr: 0.000034 grad: 0.1045 (0.1124) loss: 0.8141 (0.8127) time: 0.1637 data: 0.0868 max mem: 9390 +Train: [66] [5200/6250] eta: 0:02:22 lr: 0.000034 grad: 0.1043 (0.1124) loss: 0.8136 (0.8127) time: 0.1566 data: 0.0760 max mem: 9390 +Train: [66] [5300/6250] eta: 0:02:09 lr: 0.000034 grad: 0.0961 (0.1122) loss: 0.8198 (0.8128) time: 0.1402 data: 0.0628 max mem: 9390 +Train: [66] [5400/6250] eta: 0:01:55 lr: 0.000034 grad: 0.1097 (0.1122) loss: 0.8131 (0.8128) time: 0.1155 data: 0.0338 max mem: 9390 +Train: [66] [5500/6250] eta: 0:01:42 lr: 0.000034 grad: 0.1092 (0.1121) loss: 0.8115 (0.8128) time: 0.1333 data: 0.0583 max mem: 9390 +Train: [66] [5600/6250] eta: 0:01:28 lr: 0.000034 grad: 0.1099 (0.1121) loss: 0.8113 (0.8128) time: 0.1463 data: 0.0692 max mem: 9390 +Train: [66] [5700/6250] eta: 0:01:15 lr: 0.000034 grad: 0.1057 (0.1120) loss: 0.8118 (0.8129) time: 0.1221 data: 0.0418 max mem: 9390 +Train: [66] [5800/6250] eta: 0:01:01 lr: 0.000034 grad: 0.1051 (0.1120) loss: 0.8105 (0.8129) time: 0.1574 data: 0.0814 max mem: 9390 +Train: [66] [5900/6250] eta: 0:00:47 lr: 0.000034 grad: 0.1051 (0.1119) loss: 0.8130 (0.8129) time: 0.1535 data: 0.0629 max mem: 9390 +Train: [66] [6000/6250] eta: 0:00:34 lr: 0.000034 grad: 0.1060 (0.1119) loss: 0.8132 (0.8129) time: 0.1289 data: 0.0514 max mem: 9390 +Train: [66] [6100/6250] eta: 0:00:20 lr: 0.000034 grad: 0.1050 (0.1118) loss: 0.8123 (0.8129) time: 0.1166 data: 0.0373 max mem: 9390 +Train: [66] [6200/6250] eta: 0:00:06 lr: 0.000034 grad: 0.1080 (0.1119) loss: 0.8151 (0.8129) time: 0.1485 data: 0.0698 max mem: 9390 +Train: [66] [6249/6250] eta: 0:00:00 lr: 0.000034 grad: 0.1089 (0.1118) loss: 0.8163 (0.8129) time: 0.1441 data: 0.0636 max mem: 9390 +Train: [66] Total time: 0:14:20 (0.1377 s / it) +Averaged stats: lr: 0.000034 grad: 0.1089 (0.1118) loss: 0.8163 (0.8129) +Eval (hcp-train-subset): [66] [ 0/62] eta: 0:03:27 loss: 0.8405 (0.8405) time: 3.3432 data: 3.2921 max mem: 9390 +Eval (hcp-train-subset): [66] [61/62] eta: 0:00:00 loss: 0.8272 (0.8286) time: 0.1289 data: 0.1023 max mem: 9390 +Eval (hcp-train-subset): [66] Total time: 0:00:12 (0.2082 s / it) +Averaged stats (hcp-train-subset): loss: 0.8272 (0.8286) +Eval (hcp-val): [66] [ 0/62] eta: 0:03:32 loss: 0.8306 (0.8306) time: 3.4211 data: 3.3477 max mem: 9390 +Eval (hcp-val): [66] [61/62] eta: 0:00:00 loss: 0.8324 (0.8327) time: 0.1157 data: 0.0900 max mem: 9390 +Eval (hcp-val): [66] Total time: 0:00:12 (0.2031 s / it) +Averaged stats (hcp-val): loss: 0.8324 (0.8327) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +Train: [67] [ 0/6250] eta: 6:18:18 lr: 0.000034 grad: 0.0770 (0.0770) loss: 0.8370 (0.8370) time: 3.6318 data: 3.3797 max mem: 9390 +Train: [67] [ 100/6250] eta: 0:19:10 lr: 0.000034 grad: 0.1212 (0.1693) loss: 0.8167 (0.8240) time: 0.1346 data: 0.0409 max mem: 9390 +Train: [67] [ 200/6250] eta: 0:16:34 lr: 0.000034 grad: 0.1207 (0.1483) loss: 0.8175 (0.8209) time: 0.1368 data: 0.0501 max mem: 9390 +Train: [67] [ 300/6250] eta: 0:15:26 lr: 0.000034 grad: 0.1013 (0.1360) loss: 0.8197 (0.8203) time: 0.1411 data: 0.0480 max mem: 9390 +Train: [67] [ 400/6250] eta: 0:14:24 lr: 0.000034 grad: 0.0967 (0.1311) loss: 0.8240 (0.8201) time: 0.1315 data: 0.0470 max mem: 9390 +Train: [67] [ 500/6250] eta: 0:13:42 lr: 0.000034 grad: 0.0996 (0.1285) loss: 0.8191 (0.8196) time: 0.1069 data: 0.0189 max mem: 9390 +Train: [67] [ 600/6250] eta: 0:13:11 lr: 0.000033 grad: 0.1168 (0.1265) loss: 0.8188 (0.8189) time: 0.1126 data: 0.0263 max mem: 9390 +Train: [67] [ 700/6250] eta: 0:12:43 lr: 0.000033 grad: 0.1043 (0.1242) loss: 0.8208 (0.8185) time: 0.1182 data: 0.0358 max mem: 9390 +Train: [67] [ 800/6250] eta: 0:12:22 lr: 0.000033 grad: 0.1043 (0.1224) loss: 0.8228 (0.8185) time: 0.1226 data: 0.0311 max mem: 9390 +Train: [67] [ 900/6250] eta: 0:12:04 lr: 0.000033 grad: 0.1146 (0.1217) loss: 0.8187 (0.8180) time: 0.1196 data: 0.0357 max mem: 9390 +Train: [67] [1000/6250] eta: 0:11:50 lr: 0.000033 grad: 0.1087 (0.1212) loss: 0.8180 (0.8177) time: 0.1349 data: 0.0606 max mem: 9390 +Train: [67] [1100/6250] eta: 0:11:37 lr: 0.000033 grad: 0.1037 (0.1203) loss: 0.8172 (0.8175) time: 0.1332 data: 0.0466 max mem: 9390 +Train: [67] [1200/6250] eta: 0:11:22 lr: 0.000033 grad: 0.1124 (0.1203) loss: 0.8097 (0.8171) time: 0.1206 data: 0.0420 max mem: 9390 +Train: [67] [1300/6250] eta: 0:11:09 lr: 0.000033 grad: 0.1158 (0.1203) loss: 0.8130 (0.8168) time: 0.1043 data: 0.0258 max mem: 9390 +Train: [67] [1400/6250] eta: 0:11:01 lr: 0.000033 grad: 0.1035 (0.1197) loss: 0.8206 (0.8166) time: 0.1720 data: 0.0787 max mem: 9390 +Train: [67] [1500/6250] eta: 0:10:51 lr: 0.000033 grad: 0.1153 (0.1194) loss: 0.8048 (0.8164) time: 0.1637 data: 0.0771 max mem: 9390 +Train: [67] [1600/6250] eta: 0:10:43 lr: 0.000033 grad: 0.1109 (0.1191) loss: 0.8140 (0.8161) time: 0.1839 data: 0.1053 max mem: 9390 +Train: [67] [1700/6250] eta: 0:10:27 lr: 0.000033 grad: 0.1068 (0.1189) loss: 0.8144 (0.8159) time: 0.1365 data: 0.0564 max mem: 9390 +Train: [67] [1800/6250] eta: 0:10:15 lr: 0.000033 grad: 0.1098 (0.1186) loss: 0.8115 (0.8157) time: 0.1378 data: 0.0564 max mem: 9390 +Train: [67] [1900/6250] eta: 0:10:01 lr: 0.000033 grad: 0.1085 (0.1185) loss: 0.8123 (0.8155) time: 0.1417 data: 0.0636 max mem: 9390 +Train: [67] [2000/6250] eta: 0:09:46 lr: 0.000033 grad: 0.1219 (0.1183) loss: 0.8058 (0.8154) time: 0.1182 data: 0.0378 max mem: 9390 +Train: [67] [2100/6250] eta: 0:09:29 lr: 0.000033 grad: 0.1142 (0.1182) loss: 0.8102 (0.8153) time: 0.1198 data: 0.0318 max mem: 9390 +Train: [67] [2200/6250] eta: 0:09:12 lr: 0.000033 grad: 0.1152 (0.1181) loss: 0.8104 (0.8151) time: 0.1091 data: 0.0206 max mem: 9390 +Train: [67] [2300/6250] eta: 0:08:56 lr: 0.000033 grad: 0.1121 (0.1181) loss: 0.8077 (0.8150) time: 0.1294 data: 0.0366 max mem: 9390 +Train: [67] [2400/6250] eta: 0:08:39 lr: 0.000033 grad: 0.1164 (0.1180) loss: 0.8046 (0.8148) time: 0.1184 data: 0.0334 max mem: 9390 +Train: [67] [2500/6250] eta: 0:08:23 lr: 0.000033 grad: 0.1094 (0.1180) loss: 0.8072 (0.8147) time: 0.1348 data: 0.0556 max mem: 9390 +Train: [67] [2600/6250] eta: 0:08:08 lr: 0.000033 grad: 0.1106 (0.1179) loss: 0.8130 (0.8145) time: 0.1420 data: 0.0639 max mem: 9390 +Train: [67] [2700/6250] eta: 0:07:53 lr: 0.000033 grad: 0.1105 (0.1178) loss: 0.8110 (0.8143) time: 0.1207 data: 0.0401 max mem: 9390 +Train: [67] [2800/6250] eta: 0:07:39 lr: 0.000033 grad: 0.1092 (0.1178) loss: 0.8119 (0.8141) time: 0.1248 data: 0.0398 max mem: 9390 +Train: [67] [2900/6250] eta: 0:07:25 lr: 0.000033 grad: 0.1140 (0.1177) loss: 0.8044 (0.8140) time: 0.1353 data: 0.0566 max mem: 9390 +Train: [67] [3000/6250] eta: 0:07:12 lr: 0.000033 grad: 0.1057 (0.1175) loss: 0.8166 (0.8140) time: 0.1329 data: 0.0519 max mem: 9390 +Train: [67] [3100/6250] eta: 0:06:58 lr: 0.000033 grad: 0.1036 (0.1172) loss: 0.8178 (0.8139) time: 0.1352 data: 0.0562 max mem: 9390 +Train: [67] [3200/6250] eta: 0:06:44 lr: 0.000033 grad: 0.1072 (0.1170) loss: 0.8123 (0.8139) time: 0.1222 data: 0.0437 max mem: 9390 +Train: [67] [3300/6250] eta: 0:06:31 lr: 0.000033 grad: 0.1063 (0.1168) loss: 0.8105 (0.8138) time: 0.1313 data: 0.0518 max mem: 9390 +Train: [67] [3400/6250] eta: 0:06:18 lr: 0.000033 grad: 0.1113 (0.1168) loss: 0.8198 (0.8138) time: 0.1291 data: 0.0313 max mem: 9390 +Train: [67] [3500/6250] eta: 0:06:06 lr: 0.000033 grad: 0.1097 (0.1166) loss: 0.8098 (0.8138) time: 0.1461 data: 0.0636 max mem: 9390 +Train: [67] [3600/6250] eta: 0:05:52 lr: 0.000033 grad: 0.1024 (0.1164) loss: 0.8145 (0.8138) time: 0.1188 data: 0.0416 max mem: 9390 +Train: [67] [3700/6250] eta: 0:05:39 lr: 0.000033 grad: 0.1047 (0.1163) loss: 0.8190 (0.8139) time: 0.1415 data: 0.0542 max mem: 9390 +Train: [67] [3800/6250] eta: 0:05:27 lr: 0.000033 grad: 0.1083 (0.1161) loss: 0.8050 (0.8139) time: 0.1350 data: 0.0580 max mem: 9390 +Train: [67] [3900/6250] eta: 0:05:13 lr: 0.000033 grad: 0.1026 (0.1159) loss: 0.8191 (0.8140) time: 0.1195 data: 0.0405 max mem: 9390 +Train: [67] [4000/6250] eta: 0:05:00 lr: 0.000032 grad: 0.1043 (0.1157) loss: 0.8178 (0.8140) time: 0.1434 data: 0.0585 max mem: 9390 +Train: [67] [4100/6250] eta: 0:04:47 lr: 0.000032 grad: 0.1114 (0.1156) loss: 0.8090 (0.8141) time: 0.1366 data: 0.0536 max mem: 9390 +Train: [67] [4200/6250] eta: 0:04:35 lr: 0.000032 grad: 0.1079 (0.1156) loss: 0.8114 (0.8141) time: 0.0854 data: 0.0002 max mem: 9390 +Train: [67] [4300/6250] eta: 0:04:21 lr: 0.000032 grad: 0.1084 (0.1156) loss: 0.8161 (0.8140) time: 0.1074 data: 0.0278 max mem: 9390 +Train: [67] [4400/6250] eta: 0:04:08 lr: 0.000032 grad: 0.1105 (0.1155) loss: 0.8126 (0.8140) time: 0.1172 data: 0.0325 max mem: 9390 +Train: [67] [4500/6250] eta: 0:03:54 lr: 0.000032 grad: 0.1134 (0.1154) loss: 0.8091 (0.8140) time: 0.1597 data: 0.0823 max mem: 9390 +Train: [67] [4600/6250] eta: 0:03:41 lr: 0.000032 grad: 0.1097 (0.1154) loss: 0.8173 (0.8139) time: 0.1041 data: 0.0217 max mem: 9390 +Train: [67] [4700/6250] eta: 0:03:28 lr: 0.000032 grad: 0.1083 (0.1154) loss: 0.8156 (0.8139) time: 0.1344 data: 0.0507 max mem: 9390 +Train: [67] [4800/6250] eta: 0:03:15 lr: 0.000032 grad: 0.1108 (0.1154) loss: 0.8090 (0.8138) time: 0.1114 data: 0.0269 max mem: 9390 +Train: [67] [4900/6250] eta: 0:03:02 lr: 0.000032 grad: 0.1152 (0.1154) loss: 0.8087 (0.8138) time: 0.1261 data: 0.0439 max mem: 9390 +Train: [67] [5000/6250] eta: 0:02:48 lr: 0.000032 grad: 0.1129 (0.1154) loss: 0.8154 (0.8137) time: 0.1672 data: 0.0875 max mem: 9390 +Train: [67] [5100/6250] eta: 0:02:35 lr: 0.000032 grad: 0.1098 (0.1154) loss: 0.8022 (0.8136) time: 0.1362 data: 0.0587 max mem: 9390 +Train: [67] [5200/6250] eta: 0:02:21 lr: 0.000032 grad: 0.1078 (0.1154) loss: 0.8167 (0.8136) time: 0.1304 data: 0.0449 max mem: 9390 +Train: [67] [5300/6250] eta: 0:02:08 lr: 0.000032 grad: 0.1203 (0.1154) loss: 0.8057 (0.8136) time: 0.1019 data: 0.0003 max mem: 9390 +Train: [67] [5400/6250] eta: 0:01:55 lr: 0.000032 grad: 0.1163 (0.1154) loss: 0.8087 (0.8135) time: 0.1400 data: 0.0618 max mem: 9390 +Train: [67] [5500/6250] eta: 0:01:41 lr: 0.000032 grad: 0.1125 (0.1155) loss: 0.8110 (0.8135) time: 0.1436 data: 0.0617 max mem: 9390 +Train: [67] [5600/6250] eta: 0:01:28 lr: 0.000032 grad: 0.1085 (0.1155) loss: 0.8150 (0.8134) time: 0.1375 data: 0.0545 max mem: 9390 +Train: [67] [5700/6250] eta: 0:01:14 lr: 0.000032 grad: 0.1159 (0.1155) loss: 0.8128 (0.8134) time: 0.1286 data: 0.0493 max mem: 9390 +Train: [67] [5800/6250] eta: 0:01:01 lr: 0.000032 grad: 0.1093 (0.1155) loss: 0.8074 (0.8133) time: 0.1572 data: 0.0789 max mem: 9390 +Train: [67] [5900/6250] eta: 0:00:47 lr: 0.000032 grad: 0.1090 (0.1155) loss: 0.8124 (0.8132) time: 0.1506 data: 0.0680 max mem: 9390 +Train: [67] [6000/6250] eta: 0:00:34 lr: 0.000032 grad: 0.1167 (0.1155) loss: 0.8113 (0.8132) time: 0.1537 data: 0.0720 max mem: 9390 +Train: [67] [6100/6250] eta: 0:00:20 lr: 0.000032 grad: 0.1086 (0.1155) loss: 0.8126 (0.8132) time: 0.1589 data: 0.0795 max mem: 9390 +Train: [67] [6200/6250] eta: 0:00:06 lr: 0.000032 grad: 0.1053 (0.1155) loss: 0.8171 (0.8132) time: 0.1288 data: 0.0478 max mem: 9390 +Train: [67] [6249/6250] eta: 0:00:00 lr: 0.000032 grad: 0.1107 (0.1155) loss: 0.8136 (0.8132) time: 0.1229 data: 0.0400 max mem: 9390 +Train: [67] Total time: 0:14:18 (0.1373 s / it) +Averaged stats: lr: 0.000032 grad: 0.1107 (0.1155) loss: 0.8136 (0.8132) +Eval (hcp-train-subset): [67] [ 0/62] eta: 0:03:45 loss: 0.8381 (0.8381) time: 3.6345 data: 3.5809 max mem: 9390 +Eval (hcp-train-subset): [67] [61/62] eta: 0:00:00 loss: 0.8255 (0.8274) time: 0.0974 data: 0.0706 max mem: 9390 +Eval (hcp-train-subset): [67] Total time: 0:00:12 (0.2066 s / it) +Averaged stats (hcp-train-subset): loss: 0.8255 (0.8274) +Eval (hcp-val): [67] [ 0/62] eta: 0:04:07 loss: 0.8336 (0.8336) time: 3.9849 data: 3.8738 max mem: 9390 +Eval (hcp-val): [67] [61/62] eta: 0:00:00 loss: 0.8316 (0.8324) time: 0.1253 data: 0.0995 max mem: 9390 +Eval (hcp-val): [67] Total time: 0:00:12 (0.2093 s / it) +Averaged stats (hcp-val): loss: 0.8316 (0.8324) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +Train: [68] [ 0/6250] eta: 8:52:34 lr: 0.000032 grad: 0.1415 (0.1415) loss: 0.8450 (0.8450) time: 5.1128 data: 4.9702 max mem: 9390 +Train: [68] [ 100/6250] eta: 0:19:50 lr: 0.000032 grad: 0.1105 (0.1321) loss: 0.8233 (0.8260) time: 0.1514 data: 0.0601 max mem: 9390 +Train: [68] [ 200/6250] eta: 0:17:03 lr: 0.000032 grad: 0.1168 (0.1249) loss: 0.8096 (0.8208) time: 0.1481 data: 0.0590 max mem: 9390 +Train: [68] [ 300/6250] eta: 0:15:35 lr: 0.000032 grad: 0.1140 (0.1238) loss: 0.8142 (0.8168) time: 0.1289 data: 0.0465 max mem: 9390 +Train: [68] [ 400/6250] eta: 0:14:48 lr: 0.000032 grad: 0.1061 (0.1213) loss: 0.8092 (0.8155) time: 0.1459 data: 0.0633 max mem: 9390 +Train: [68] [ 500/6250] eta: 0:14:08 lr: 0.000032 grad: 0.1115 (0.1192) loss: 0.8149 (0.8151) time: 0.1298 data: 0.0340 max mem: 9390 +Train: [68] [ 600/6250] eta: 0:13:37 lr: 0.000032 grad: 0.1102 (0.1181) loss: 0.8132 (0.8150) time: 0.1411 data: 0.0517 max mem: 9390 +Train: [68] [ 700/6250] eta: 0:13:09 lr: 0.000032 grad: 0.1061 (0.1177) loss: 0.8194 (0.8146) time: 0.1329 data: 0.0413 max mem: 9390 +Train: [68] [ 800/6250] eta: 0:12:49 lr: 0.000032 grad: 0.1090 (0.1173) loss: 0.8099 (0.8141) time: 0.1587 data: 0.0769 max mem: 9390 +Train: [68] [ 900/6250] eta: 0:12:33 lr: 0.000032 grad: 0.1041 (0.1166) loss: 0.8212 (0.8141) time: 0.1566 data: 0.0726 max mem: 9390 +Train: [68] [1000/6250] eta: 0:12:23 lr: 0.000032 grad: 0.1145 (0.1168) loss: 0.8097 (0.8138) time: 0.1024 data: 0.0153 max mem: 9390 +Train: [68] [1100/6250] eta: 0:12:05 lr: 0.000032 grad: 0.1035 (0.1166) loss: 0.8146 (0.8135) time: 0.1535 data: 0.0664 max mem: 9390 +Train: [68] [1200/6250] eta: 0:11:56 lr: 0.000032 grad: 0.1141 (0.1166) loss: 0.8054 (0.8133) time: 0.1459 data: 0.0681 max mem: 9390 +Train: [68] [1300/6250] eta: 0:11:42 lr: 0.000031 grad: 0.1095 (0.1165) loss: 0.8094 (0.8131) time: 0.1463 data: 0.0696 max mem: 9390 +Train: [68] [1400/6250] eta: 0:11:24 lr: 0.000031 grad: 0.1157 (0.1164) loss: 0.8010 (0.8128) time: 0.1370 data: 0.0551 max mem: 9390 +Train: [68] [1500/6250] eta: 0:11:10 lr: 0.000031 grad: 0.1102 (0.1163) loss: 0.8082 (0.8126) time: 0.1620 data: 0.0813 max mem: 9390 +Train: [68] [1600/6250] eta: 0:10:58 lr: 0.000031 grad: 0.1112 (0.1160) loss: 0.8127 (0.8124) time: 0.1315 data: 0.0528 max mem: 9390 +Train: [68] [1700/6250] eta: 0:10:44 lr: 0.000031 grad: 0.1139 (0.1159) loss: 0.8107 (0.8122) time: 0.1246 data: 0.0418 max mem: 9390 +Train: [68] [1800/6250] eta: 0:10:31 lr: 0.000031 grad: 0.1129 (0.1159) loss: 0.8100 (0.8120) time: 0.1339 data: 0.0520 max mem: 9390 +Train: [68] [1900/6250] eta: 0:10:15 lr: 0.000031 grad: 0.1145 (0.1158) loss: 0.8104 (0.8118) time: 0.1340 data: 0.0461 max mem: 9390 +Train: [68] [2000/6250] eta: 0:09:58 lr: 0.000031 grad: 0.1172 (0.1157) loss: 0.8088 (0.8117) time: 0.1034 data: 0.0206 max mem: 9390 +Train: [68] [2100/6250] eta: 0:09:42 lr: 0.000031 grad: 0.1169 (0.1157) loss: 0.8108 (0.8116) time: 0.1380 data: 0.0547 max mem: 9390 +Train: [68] [2200/6250] eta: 0:09:24 lr: 0.000031 grad: 0.1119 (0.1156) loss: 0.8071 (0.8116) time: 0.0935 data: 0.0053 max mem: 9390 +Train: [68] [2300/6250] eta: 0:09:07 lr: 0.000031 grad: 0.1075 (0.1156) loss: 0.8145 (0.8116) time: 0.1100 data: 0.0251 max mem: 9390 +Train: [68] [2400/6250] eta: 0:08:49 lr: 0.000031 grad: 0.1137 (0.1156) loss: 0.8082 (0.8116) time: 0.1048 data: 0.0190 max mem: 9390 +Train: [68] [2500/6250] eta: 0:08:33 lr: 0.000031 grad: 0.1104 (0.1155) loss: 0.8101 (0.8116) time: 0.1482 data: 0.0653 max mem: 9390 +Train: [68] [2600/6250] eta: 0:08:16 lr: 0.000031 grad: 0.1115 (0.1154) loss: 0.8134 (0.8116) time: 0.1313 data: 0.0515 max mem: 9390 +Train: [68] [2700/6250] eta: 0:08:00 lr: 0.000031 grad: 0.1047 (0.1155) loss: 0.8159 (0.8116) time: 0.1193 data: 0.0436 max mem: 9390 +Train: [68] [2800/6250] eta: 0:07:46 lr: 0.000031 grad: 0.1126 (0.1155) loss: 0.8162 (0.8115) time: 0.1320 data: 0.0537 max mem: 9390 +Train: [68] [2900/6250] eta: 0:07:32 lr: 0.000031 grad: 0.1066 (0.1156) loss: 0.8117 (0.8115) time: 0.1224 data: 0.0409 max mem: 9390 +Train: [68] [3000/6250] eta: 0:07:18 lr: 0.000031 grad: 0.1061 (0.1155) loss: 0.8164 (0.8115) time: 0.1400 data: 0.0618 max mem: 9390 +Train: [68] [3100/6250] eta: 0:07:04 lr: 0.000031 grad: 0.1111 (0.1154) loss: 0.8176 (0.8116) time: 0.1256 data: 0.0509 max mem: 9390 +Train: [68] [3200/6250] eta: 0:06:51 lr: 0.000031 grad: 0.1124 (0.1155) loss: 0.8066 (0.8115) time: 0.1344 data: 0.0544 max mem: 9390 +Train: [68] [3300/6250] eta: 0:06:36 lr: 0.000031 grad: 0.1094 (0.1155) loss: 0.8123 (0.8114) time: 0.1151 data: 0.0272 max mem: 9390 +Train: [68] [3400/6250] eta: 0:06:23 lr: 0.000031 grad: 0.1120 (0.1155) loss: 0.8072 (0.8114) time: 0.1272 data: 0.0494 max mem: 9390 +Train: [68] [3500/6250] eta: 0:06:09 lr: 0.000031 grad: 0.1127 (0.1155) loss: 0.8099 (0.8114) time: 0.0972 data: 0.0175 max mem: 9390 +Train: [68] [3600/6250] eta: 0:05:55 lr: 0.000031 grad: 0.1062 (0.1154) loss: 0.8153 (0.8114) time: 0.1281 data: 0.0511 max mem: 9390 +Train: [68] [3700/6250] eta: 0:05:42 lr: 0.000031 grad: 0.1139 (0.1154) loss: 0.8094 (0.8114) time: 0.1381 data: 0.0634 max mem: 9390 +Train: [68] [3800/6250] eta: 0:05:28 lr: 0.000031 grad: 0.1101 (0.1153) loss: 0.8134 (0.8113) time: 0.1355 data: 0.0598 max mem: 9390 +Train: [68] [3900/6250] eta: 0:05:14 lr: 0.000031 grad: 0.1147 (0.1153) loss: 0.8086 (0.8113) time: 0.1228 data: 0.0438 max mem: 9390 +Train: [68] [4000/6250] eta: 0:05:01 lr: 0.000031 grad: 0.1225 (0.1153) loss: 0.8018 (0.8112) time: 0.1370 data: 0.0560 max mem: 9390 +Train: [68] [4100/6250] eta: 0:04:48 lr: 0.000031 grad: 0.1089 (0.1152) loss: 0.8084 (0.8111) time: 0.1434 data: 0.0589 max mem: 9390 +Train: [68] [4200/6250] eta: 0:04:35 lr: 0.000031 grad: 0.1040 (0.1151) loss: 0.8096 (0.8111) time: 0.1453 data: 0.0657 max mem: 9390 +Train: [68] [4300/6250] eta: 0:04:21 lr: 0.000031 grad: 0.1044 (0.1150) loss: 0.8129 (0.8111) time: 0.1228 data: 0.0411 max mem: 9390 +Train: [68] [4400/6250] eta: 0:04:08 lr: 0.000031 grad: 0.1073 (0.1151) loss: 0.8143 (0.8111) time: 0.1088 data: 0.0323 max mem: 9390 +Train: [68] [4500/6250] eta: 0:03:55 lr: 0.000031 grad: 0.1061 (0.1150) loss: 0.8135 (0.8111) time: 0.1552 data: 0.0680 max mem: 9390 +Train: [68] [4600/6250] eta: 0:03:41 lr: 0.000031 grad: 0.1052 (0.1148) loss: 0.8227 (0.8112) time: 0.1382 data: 0.0553 max mem: 9390 +Train: [68] [4700/6250] eta: 0:03:28 lr: 0.000031 grad: 0.1132 (0.1147) loss: 0.8076 (0.8112) time: 0.1152 data: 0.0375 max mem: 9390 +Train: [68] [4800/6250] eta: 0:03:15 lr: 0.000030 grad: 0.1005 (0.1146) loss: 0.8270 (0.8114) time: 0.1290 data: 0.0447 max mem: 9390 +Train: [68] [4900/6250] eta: 0:03:01 lr: 0.000030 grad: 0.1090 (0.1145) loss: 0.8136 (0.8115) time: 0.1391 data: 0.0596 max mem: 9390 +Train: [68] [5000/6250] eta: 0:02:48 lr: 0.000030 grad: 0.0996 (0.1143) loss: 0.8242 (0.8117) time: 0.1477 data: 0.0576 max mem: 9390 +Train: [68] [5100/6250] eta: 0:02:35 lr: 0.000030 grad: 0.1060 (0.1142) loss: 0.8187 (0.8118) time: 0.1376 data: 0.0601 max mem: 9390 +Train: [68] [5200/6250] eta: 0:02:21 lr: 0.000030 grad: 0.1140 (0.1142) loss: 0.8123 (0.8120) time: 0.0863 data: 0.0040 max mem: 9390 +Train: [68] [5300/6250] eta: 0:02:08 lr: 0.000030 grad: 0.1071 (0.1141) loss: 0.8205 (0.8121) time: 0.1359 data: 0.0552 max mem: 9390 +Train: [68] [5400/6250] eta: 0:01:54 lr: 0.000030 grad: 0.1068 (0.1140) loss: 0.8180 (0.8123) time: 0.1507 data: 0.0707 max mem: 9390 +Train: [68] [5500/6250] eta: 0:01:41 lr: 0.000030 grad: 0.1125 (0.1139) loss: 0.8171 (0.8124) time: 0.1846 data: 0.1071 max mem: 9390 +Train: [68] [5600/6250] eta: 0:01:27 lr: 0.000030 grad: 0.1034 (0.1139) loss: 0.8163 (0.8125) time: 0.1463 data: 0.0636 max mem: 9390 +Train: [68] [5700/6250] eta: 0:01:14 lr: 0.000030 grad: 0.1096 (0.1139) loss: 0.8169 (0.8126) time: 0.1681 data: 0.0876 max mem: 9390 +Train: [68] [5800/6250] eta: 0:01:00 lr: 0.000030 grad: 0.1126 (0.1140) loss: 0.8105 (0.8126) time: 0.1229 data: 0.0421 max mem: 9390 +Train: [68] [5900/6250] eta: 0:00:47 lr: 0.000030 grad: 0.1170 (0.1140) loss: 0.8187 (0.8127) time: 0.1433 data: 0.0606 max mem: 9390 +Train: [68] [6000/6250] eta: 0:00:33 lr: 0.000030 grad: 0.1139 (0.1140) loss: 0.8032 (0.8127) time: 0.1347 data: 0.0456 max mem: 9390 +Train: [68] [6100/6250] eta: 0:00:20 lr: 0.000030 grad: 0.1127 (0.1140) loss: 0.8187 (0.8127) time: 0.1332 data: 0.0490 max mem: 9390 +Train: [68] [6200/6250] eta: 0:00:06 lr: 0.000030 grad: 0.1155 (0.1140) loss: 0.8088 (0.8127) time: 0.1307 data: 0.0415 max mem: 9390 +Train: [68] [6249/6250] eta: 0:00:00 lr: 0.000030 grad: 0.1041 (0.1139) loss: 0.8188 (0.8127) time: 0.1236 data: 0.0461 max mem: 9390 +Train: [68] Total time: 0:14:12 (0.1364 s / it) +Averaged stats: lr: 0.000030 grad: 0.1041 (0.1139) loss: 0.8188 (0.8127) +Eval (hcp-train-subset): [68] [ 0/62] eta: 0:04:38 loss: 0.8370 (0.8370) time: 4.4937 data: 4.4615 max mem: 9390 +Eval (hcp-train-subset): [68] [61/62] eta: 0:00:00 loss: 0.8229 (0.8274) time: 0.1138 data: 0.0870 max mem: 9390 +Eval (hcp-train-subset): [68] Total time: 0:00:13 (0.2127 s / it) +Averaged stats (hcp-train-subset): loss: 0.8229 (0.8274) +Eval (hcp-val): [68] [ 0/62] eta: 0:04:09 loss: 0.8327 (0.8327) time: 4.0276 data: 3.9391 max mem: 9390 +Eval (hcp-val): [68] [61/62] eta: 0:00:00 loss: 0.8303 (0.8330) time: 0.1045 data: 0.0795 max mem: 9390 +Eval (hcp-val): [68] Total time: 0:00:12 (0.2072 s / it) +Averaged stats (hcp-val): loss: 0.8303 (0.8330) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +Train: [69] [ 0/6250] eta: 8:44:33 lr: 0.000030 grad: 0.1063 (0.1063) loss: 0.8405 (0.8405) time: 5.0358 data: 4.7643 max mem: 9390 +Train: [69] [ 100/6250] eta: 0:19:25 lr: 0.000030 grad: 0.1195 (0.1332) loss: 0.8244 (0.8287) time: 0.1335 data: 0.0376 max mem: 9390 +Train: [69] [ 200/6250] eta: 0:16:38 lr: 0.000030 grad: 0.1085 (0.1249) loss: 0.8187 (0.8247) time: 0.1294 data: 0.0352 max mem: 9390 +Train: [69] [ 300/6250] eta: 0:15:25 lr: 0.000030 grad: 0.1136 (0.1201) loss: 0.8202 (0.8250) time: 0.1427 data: 0.0559 max mem: 9390 +Train: [69] [ 400/6250] eta: 0:14:35 lr: 0.000030 grad: 0.1004 (0.1180) loss: 0.8180 (0.8247) time: 0.1282 data: 0.0435 max mem: 9390 +Train: [69] [ 500/6250] eta: 0:13:51 lr: 0.000030 grad: 0.1036 (0.1153) loss: 0.8229 (0.8245) time: 0.1181 data: 0.0341 max mem: 9390 +Train: [69] [ 600/6250] eta: 0:13:17 lr: 0.000030 grad: 0.1082 (0.1140) loss: 0.8208 (0.8243) time: 0.1185 data: 0.0311 max mem: 9390 +Train: [69] [ 700/6250] eta: 0:12:49 lr: 0.000030 grad: 0.1115 (0.1135) loss: 0.8197 (0.8236) time: 0.1174 data: 0.0247 max mem: 9390 +Train: [69] [ 800/6250] eta: 0:12:26 lr: 0.000030 grad: 0.1167 (0.1134) loss: 0.8183 (0.8227) time: 0.1227 data: 0.0418 max mem: 9390 +Train: [69] [ 900/6250] eta: 0:12:06 lr: 0.000030 grad: 0.1026 (0.1129) loss: 0.8109 (0.8221) time: 0.1253 data: 0.0372 max mem: 9390 +Train: [69] [1000/6250] eta: 0:11:52 lr: 0.000030 grad: 0.1039 (0.1129) loss: 0.8191 (0.8215) time: 0.1436 data: 0.0646 max mem: 9390 +Train: [69] [1100/6250] eta: 0:11:37 lr: 0.000030 grad: 0.1077 (0.1126) loss: 0.8168 (0.8212) time: 0.1268 data: 0.0452 max mem: 9390 +Train: [69] [1200/6250] eta: 0:11:19 lr: 0.000030 grad: 0.1074 (0.1125) loss: 0.8161 (0.8207) time: 0.1288 data: 0.0520 max mem: 9390 +Train: [69] [1300/6250] eta: 0:11:04 lr: 0.000030 grad: 0.1088 (0.1124) loss: 0.8155 (0.8203) time: 0.1169 data: 0.0366 max mem: 9390 +Train: [69] [1400/6250] eta: 0:10:54 lr: 0.000030 grad: 0.1089 (0.1123) loss: 0.8084 (0.8199) time: 0.1621 data: 0.0807 max mem: 9390 +Train: [69] [1500/6250] eta: 0:10:39 lr: 0.000030 grad: 0.1036 (0.1121) loss: 0.8166 (0.8197) time: 0.1356 data: 0.0615 max mem: 9390 +Train: [69] [1600/6250] eta: 0:10:32 lr: 0.000030 grad: 0.1061 (0.1122) loss: 0.8176 (0.8195) time: 0.1527 data: 0.0717 max mem: 9390 +Train: [69] [1700/6250] eta: 0:10:22 lr: 0.000030 grad: 0.1117 (0.1122) loss: 0.8215 (0.8192) time: 0.1603 data: 0.0771 max mem: 9390 +Train: [69] [1800/6250] eta: 0:10:09 lr: 0.000030 grad: 0.1086 (0.1123) loss: 0.8125 (0.8190) time: 0.1501 data: 0.0671 max mem: 9390 +Train: [69] [1900/6250] eta: 0:09:55 lr: 0.000030 grad: 0.1135 (0.1126) loss: 0.8131 (0.8187) time: 0.1327 data: 0.0514 max mem: 9390 +Train: [69] [2000/6250] eta: 0:09:42 lr: 0.000030 grad: 0.1145 (0.1127) loss: 0.8092 (0.8182) time: 0.1450 data: 0.0653 max mem: 9390 +Train: [69] [2100/6250] eta: 0:09:25 lr: 0.000029 grad: 0.1168 (0.1129) loss: 0.8058 (0.8179) time: 0.1265 data: 0.0443 max mem: 9390 +Train: [69] [2200/6250] eta: 0:09:10 lr: 0.000029 grad: 0.1132 (0.1130) loss: 0.8035 (0.8176) time: 0.1315 data: 0.0529 max mem: 9390 +Train: [69] [2300/6250] eta: 0:08:53 lr: 0.000029 grad: 0.1149 (0.1132) loss: 0.8046 (0.8173) time: 0.1077 data: 0.0276 max mem: 9390 +Train: [69] [2400/6250] eta: 0:08:37 lr: 0.000029 grad: 0.1163 (0.1133) loss: 0.8094 (0.8171) time: 0.1118 data: 0.0305 max mem: 9390 +Train: [69] [2500/6250] eta: 0:08:21 lr: 0.000029 grad: 0.1131 (0.1134) loss: 0.8136 (0.8169) time: 0.1257 data: 0.0447 max mem: 9390 +Train: [69] [2600/6250] eta: 0:08:05 lr: 0.000029 grad: 0.1123 (0.1135) loss: 0.8084 (0.8167) time: 0.1073 data: 0.0229 max mem: 9390 +Train: [69] [2700/6250] eta: 0:07:50 lr: 0.000029 grad: 0.1116 (0.1135) loss: 0.8106 (0.8166) time: 0.1277 data: 0.0454 max mem: 9390 +Train: [69] [2800/6250] eta: 0:07:36 lr: 0.000029 grad: 0.1153 (0.1136) loss: 0.8080 (0.8165) time: 0.1205 data: 0.0397 max mem: 9390 +Train: [69] [2900/6250] eta: 0:07:23 lr: 0.000029 grad: 0.1142 (0.1136) loss: 0.8090 (0.8163) time: 0.1410 data: 0.0639 max mem: 9390 +Train: [69] [3000/6250] eta: 0:07:10 lr: 0.000029 grad: 0.1208 (0.1136) loss: 0.8176 (0.8162) time: 0.1414 data: 0.0544 max mem: 9390 +Train: [69] [3100/6250] eta: 0:06:56 lr: 0.000029 grad: 0.1141 (0.1137) loss: 0.8118 (0.8161) time: 0.1322 data: 0.0544 max mem: 9390 +Train: [69] [3200/6250] eta: 0:06:43 lr: 0.000029 grad: 0.1102 (0.1137) loss: 0.8158 (0.8161) time: 0.1290 data: 0.0474 max mem: 9390 +Train: [69] [3300/6250] eta: 0:06:30 lr: 0.000029 grad: 0.1020 (0.1136) loss: 0.8149 (0.8160) time: 0.1375 data: 0.0571 max mem: 9390 +Train: [69] [3400/6250] eta: 0:06:17 lr: 0.000029 grad: 0.1122 (0.1136) loss: 0.8178 (0.8159) time: 0.1142 data: 0.0318 max mem: 9390 +Train: [69] [3500/6250] eta: 0:06:04 lr: 0.000029 grad: 0.1147 (0.1138) loss: 0.8136 (0.8158) time: 0.1346 data: 0.0553 max mem: 9390 +Train: [69] [3600/6250] eta: 0:05:50 lr: 0.000029 grad: 0.1085 (0.1138) loss: 0.8169 (0.8157) time: 0.1275 data: 0.0489 max mem: 9390 +Train: [69] [3700/6250] eta: 0:05:37 lr: 0.000029 grad: 0.1164 (0.1138) loss: 0.8144 (0.8156) time: 0.1379 data: 0.0434 max mem: 9390 +Train: [69] [3800/6250] eta: 0:05:24 lr: 0.000029 grad: 0.1128 (0.1138) loss: 0.8079 (0.8155) time: 0.1341 data: 0.0535 max mem: 9390 +Train: [69] [3900/6250] eta: 0:05:11 lr: 0.000029 grad: 0.1109 (0.1138) loss: 0.8055 (0.8154) time: 0.1618 data: 0.0841 max mem: 9390 +Train: [69] [4000/6250] eta: 0:04:57 lr: 0.000029 grad: 0.1146 (0.1138) loss: 0.8084 (0.8154) time: 0.1374 data: 0.0566 max mem: 9390 +Train: [69] [4100/6250] eta: 0:04:44 lr: 0.000029 grad: 0.1117 (0.1138) loss: 0.8161 (0.8154) time: 0.1358 data: 0.0480 max mem: 9390 +Train: [69] [4200/6250] eta: 0:04:31 lr: 0.000029 grad: 0.1099 (0.1137) loss: 0.8158 (0.8154) time: 0.1028 data: 0.0244 max mem: 9390 +Train: [69] [4300/6250] eta: 0:04:18 lr: 0.000029 grad: 0.1059 (0.1137) loss: 0.8220 (0.8154) time: 0.1173 data: 0.0407 max mem: 9390 +Train: [69] [4400/6250] eta: 0:04:06 lr: 0.000029 grad: 0.1137 (0.1137) loss: 0.8194 (0.8154) time: 0.1474 data: 0.0407 max mem: 9390 +Train: [69] [4500/6250] eta: 0:03:52 lr: 0.000029 grad: 0.1105 (0.1137) loss: 0.8163 (0.8154) time: 0.1269 data: 0.0486 max mem: 9390 +Train: [69] [4600/6250] eta: 0:03:39 lr: 0.000029 grad: 0.1094 (0.1137) loss: 0.8170 (0.8154) time: 0.1237 data: 0.0429 max mem: 9390 +Train: [69] [4700/6250] eta: 0:03:26 lr: 0.000029 grad: 0.1105 (0.1136) loss: 0.8140 (0.8154) time: 0.1264 data: 0.0497 max mem: 9390 +Train: [69] [4800/6250] eta: 0:03:12 lr: 0.000029 grad: 0.1095 (0.1136) loss: 0.8144 (0.8154) time: 0.1431 data: 0.0590 max mem: 9390 +Train: [69] [4900/6250] eta: 0:02:59 lr: 0.000029 grad: 0.1183 (0.1136) loss: 0.8137 (0.8154) time: 0.1594 data: 0.0719 max mem: 9390 +Train: [69] [5000/6250] eta: 0:02:46 lr: 0.000029 grad: 0.1079 (0.1136) loss: 0.8196 (0.8154) time: 0.1287 data: 0.0421 max mem: 9390 +Train: [69] [5100/6250] eta: 0:02:33 lr: 0.000029 grad: 0.1166 (0.1137) loss: 0.8139 (0.8154) time: 0.1286 data: 0.0511 max mem: 9390 +Train: [69] [5200/6250] eta: 0:02:20 lr: 0.000029 grad: 0.1121 (0.1137) loss: 0.8146 (0.8154) time: 0.1466 data: 0.0677 max mem: 9390 +Train: [69] [5300/6250] eta: 0:02:07 lr: 0.000029 grad: 0.1113 (0.1136) loss: 0.8177 (0.8154) time: 0.1375 data: 0.0600 max mem: 9390 +Train: [69] [5400/6250] eta: 0:01:53 lr: 0.000029 grad: 0.1089 (0.1137) loss: 0.8168 (0.8155) time: 0.1178 data: 0.0322 max mem: 9390 +Train: [69] [5500/6250] eta: 0:01:41 lr: 0.000029 grad: 0.1072 (0.1136) loss: 0.8191 (0.8155) time: 0.3396 data: 0.2658 max mem: 9390 +Train: [69] [5600/6250] eta: 0:01:27 lr: 0.000028 grad: 0.1134 (0.1137) loss: 0.8181 (0.8155) time: 0.1396 data: 0.0549 max mem: 9390 +Train: [69] [5700/6250] eta: 0:01:14 lr: 0.000028 grad: 0.1127 (0.1137) loss: 0.8176 (0.8155) time: 0.1515 data: 0.0761 max mem: 9390 +Train: [69] [5800/6250] eta: 0:01:00 lr: 0.000028 grad: 0.1125 (0.1137) loss: 0.8133 (0.8155) time: 0.1299 data: 0.0523 max mem: 9390 +Train: [69] [5900/6250] eta: 0:00:47 lr: 0.000028 grad: 0.1097 (0.1137) loss: 0.8158 (0.8156) time: 0.1543 data: 0.0720 max mem: 9390 +Train: [69] [6000/6250] eta: 0:00:33 lr: 0.000028 grad: 0.1173 (0.1138) loss: 0.8073 (0.8156) time: 0.1479 data: 0.0703 max mem: 9390 +Train: [69] [6100/6250] eta: 0:00:20 lr: 0.000028 grad: 0.1112 (0.1138) loss: 0.8122 (0.8156) time: 0.1413 data: 0.0661 max mem: 9390 +Train: [69] [6200/6250] eta: 0:00:06 lr: 0.000028 grad: 0.1133 (0.1139) loss: 0.8079 (0.8155) time: 0.1340 data: 0.0575 max mem: 9390 +Train: [69] [6249/6250] eta: 0:00:00 lr: 0.000028 grad: 0.1056 (0.1139) loss: 0.8216 (0.8155) time: 0.1557 data: 0.0822 max mem: 9390 +Train: [69] Total time: 0:14:07 (0.1356 s / it) +Averaged stats: lr: 0.000028 grad: 0.1056 (0.1139) loss: 0.8216 (0.8155) +Eval (hcp-train-subset): [69] [ 0/62] eta: 0:04:08 loss: 0.8415 (0.8415) time: 4.0161 data: 3.9334 max mem: 9390 +Eval (hcp-train-subset): [69] [61/62] eta: 0:00:00 loss: 0.8251 (0.8289) time: 0.1182 data: 0.0915 max mem: 9390 +Eval (hcp-train-subset): [69] Total time: 0:00:12 (0.2080 s / it) +Averaged stats (hcp-train-subset): loss: 0.8251 (0.8289) +Making plots (hcp-train-subset): example=60 +Eval (hcp-val): [69] [ 0/62] eta: 0:04:43 loss: 0.8298 (0.8298) time: 4.5752 data: 4.5440 max mem: 9390 +Eval (hcp-val): [69] [61/62] eta: 0:00:00 loss: 0.8304 (0.8322) time: 0.1193 data: 0.0942 max mem: 9390 +Eval (hcp-val): [69] Total time: 0:00:12 (0.2012 s / it) +Averaged stats (hcp-val): loss: 0.8304 (0.8322) +Making plots (hcp-val): example=27 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +Train: [70] [ 0/6250] eta: 9:49:26 lr: 0.000028 grad: 0.1335 (0.1335) loss: 0.8595 (0.8595) time: 5.6586 data: 5.5480 max mem: 9390 +Train: [70] [ 100/6250] eta: 0:20:38 lr: 0.000028 grad: 0.1120 (0.1263) loss: 0.8121 (0.8333) time: 0.1748 data: 0.0839 max mem: 9390 +Train: [70] [ 200/6250] eta: 0:17:27 lr: 0.000028 grad: 0.1066 (0.1249) loss: 0.8232 (0.8262) time: 0.1261 data: 0.0285 max mem: 9390 +Train: [70] [ 300/6250] eta: 0:16:00 lr: 0.000028 grad: 0.1108 (0.1223) loss: 0.8091 (0.8230) time: 0.1166 data: 0.0337 max mem: 9390 +Train: [70] [ 400/6250] eta: 0:15:18 lr: 0.000028 grad: 0.1163 (0.1212) loss: 0.8172 (0.8214) time: 0.1632 data: 0.0742 max mem: 9390 +Train: [70] [ 500/6250] eta: 0:14:30 lr: 0.000028 grad: 0.1087 (0.1200) loss: 0.8171 (0.8205) time: 0.1184 data: 0.0285 max mem: 9390 +Train: [70] [ 600/6250] eta: 0:13:59 lr: 0.000028 grad: 0.1164 (0.1197) loss: 0.8216 (0.8198) time: 0.1381 data: 0.0557 max mem: 9390 +Train: [70] [ 700/6250] eta: 0:13:40 lr: 0.000028 grad: 0.1063 (0.1186) loss: 0.8186 (0.8196) time: 0.1445 data: 0.0541 max mem: 9390 +Train: [70] [ 800/6250] eta: 0:13:17 lr: 0.000028 grad: 0.1045 (0.1178) loss: 0.8153 (0.8192) time: 0.1485 data: 0.0639 max mem: 9390 +Train: [70] [ 900/6250] eta: 0:13:04 lr: 0.000028 grad: 0.1065 (0.1171) loss: 0.8057 (0.8188) time: 0.1471 data: 0.0530 max mem: 9390 +Train: [70] [1000/6250] eta: 0:12:48 lr: 0.000028 grad: 0.1092 (0.1166) loss: 0.8098 (0.8183) time: 0.1338 data: 0.0512 max mem: 9390 +Train: [70] [1100/6250] eta: 0:12:25 lr: 0.000028 grad: 0.1152 (0.1161) loss: 0.8138 (0.8178) time: 0.1194 data: 0.0376 max mem: 9390 +Train: [70] [1200/6250] eta: 0:12:07 lr: 0.000028 grad: 0.1124 (0.1160) loss: 0.8093 (0.8173) time: 0.1530 data: 0.0771 max mem: 9390 +Train: [70] [1300/6250] eta: 0:11:51 lr: 0.000028 grad: 0.1132 (0.1156) loss: 0.8055 (0.8170) time: 0.1367 data: 0.0507 max mem: 9390 +Train: [70] [1400/6250] eta: 0:11:32 lr: 0.000028 grad: 0.1015 (0.1153) loss: 0.8179 (0.8168) time: 0.1239 data: 0.0425 max mem: 9390 +Train: [70] [1500/6250] eta: 0:11:17 lr: 0.000028 grad: 0.1100 (0.1151) loss: 0.8167 (0.8166) time: 0.1677 data: 0.0899 max mem: 9390 +Train: [70] [1600/6250] eta: 0:11:06 lr: 0.000028 grad: 0.1030 (0.1149) loss: 0.8127 (0.8166) time: 0.1430 data: 0.0587 max mem: 9390 +Train: [70] [1700/6250] eta: 0:10:52 lr: 0.000028 grad: 0.1086 (0.1148) loss: 0.8140 (0.8165) time: 0.1336 data: 0.0564 max mem: 9390 +Train: [70] [1800/6250] eta: 0:10:36 lr: 0.000028 grad: 0.1093 (0.1148) loss: 0.8158 (0.8163) time: 0.1456 data: 0.0641 max mem: 9390 +Train: [70] [1900/6250] eta: 0:10:23 lr: 0.000028 grad: 0.1122 (0.1147) loss: 0.8102 (0.8161) time: 0.1854 data: 0.1049 max mem: 9390 +Train: [70] [2000/6250] eta: 0:10:04 lr: 0.000028 grad: 0.1099 (0.1147) loss: 0.8111 (0.8159) time: 0.1210 data: 0.0441 max mem: 9390 +Train: [70] [2100/6250] eta: 0:09:47 lr: 0.000028 grad: 0.1162 (0.1147) loss: 0.8080 (0.8158) time: 0.1217 data: 0.0359 max mem: 9390 +Train: [70] [2200/6250] eta: 0:09:30 lr: 0.000028 grad: 0.1161 (0.1147) loss: 0.8201 (0.8157) time: 0.1181 data: 0.0310 max mem: 9390 +Train: [70] [2300/6250] eta: 0:09:12 lr: 0.000028 grad: 0.1097 (0.1148) loss: 0.8148 (0.8156) time: 0.1265 data: 0.0483 max mem: 9390 +Train: [70] [2400/6250] eta: 0:08:55 lr: 0.000028 grad: 0.1097 (0.1148) loss: 0.8123 (0.8155) time: 0.1318 data: 0.0465 max mem: 9390 +Train: [70] [2500/6250] eta: 0:08:38 lr: 0.000028 grad: 0.1196 (0.1147) loss: 0.8120 (0.8154) time: 0.1211 data: 0.0398 max mem: 9390 +Train: [70] [2600/6250] eta: 0:08:21 lr: 0.000028 grad: 0.1060 (0.1146) loss: 0.8167 (0.8154) time: 0.1246 data: 0.0398 max mem: 9390 +Train: [70] [2700/6250] eta: 0:08:05 lr: 0.000028 grad: 0.1134 (0.1144) loss: 0.8108 (0.8153) time: 0.1217 data: 0.0420 max mem: 9390 +Train: [70] [2800/6250] eta: 0:07:51 lr: 0.000028 grad: 0.1113 (0.1143) loss: 0.8130 (0.8154) time: 0.1234 data: 0.0453 max mem: 9390 +Train: [70] [2900/6250] eta: 0:07:37 lr: 0.000028 grad: 0.1147 (0.1144) loss: 0.8141 (0.8154) time: 0.1317 data: 0.0535 max mem: 9390 +Train: [70] [3000/6250] eta: 0:07:22 lr: 0.000027 grad: 0.1148 (0.1144) loss: 0.8072 (0.8154) time: 0.1126 data: 0.0277 max mem: 9390 +Train: [70] [3100/6250] eta: 0:07:08 lr: 0.000027 grad: 0.1163 (0.1145) loss: 0.8127 (0.8153) time: 0.1406 data: 0.0652 max mem: 9390 +Train: [70] [3200/6250] eta: 0:06:55 lr: 0.000027 grad: 0.1160 (0.1145) loss: 0.8118 (0.8153) time: 0.1520 data: 0.0749 max mem: 9390 +Train: [70] [3300/6250] eta: 0:06:40 lr: 0.000027 grad: 0.1185 (0.1146) loss: 0.8110 (0.8152) time: 0.1364 data: 0.0541 max mem: 9390 +Train: [70] [3400/6250] eta: 0:06:27 lr: 0.000027 grad: 0.1126 (0.1146) loss: 0.8175 (0.8152) time: 0.1386 data: 0.0551 max mem: 9390 +Train: [70] [3500/6250] eta: 0:06:13 lr: 0.000027 grad: 0.1130 (0.1146) loss: 0.8175 (0.8151) time: 0.1376 data: 0.0583 max mem: 9390 +Train: [70] [3600/6250] eta: 0:05:59 lr: 0.000027 grad: 0.1210 (0.1148) loss: 0.8131 (0.8150) time: 0.1333 data: 0.0550 max mem: 9390 +Train: [70] [3700/6250] eta: 0:05:45 lr: 0.000027 grad: 0.1166 (0.1149) loss: 0.8083 (0.8149) time: 0.1333 data: 0.0512 max mem: 9390 +Train: [70] [3800/6250] eta: 0:05:31 lr: 0.000027 grad: 0.1138 (0.1150) loss: 0.8121 (0.8148) time: 0.1134 data: 0.0280 max mem: 9390 +Train: [70] [3900/6250] eta: 0:05:17 lr: 0.000027 grad: 0.1122 (0.1150) loss: 0.8176 (0.8148) time: 0.1159 data: 0.0388 max mem: 9390 +Train: [70] [4000/6250] eta: 0:05:04 lr: 0.000027 grad: 0.1098 (0.1150) loss: 0.8166 (0.8148) time: 0.1258 data: 0.0458 max mem: 9390 +Train: [70] [4100/6250] eta: 0:04:51 lr: 0.000027 grad: 0.1162 (0.1151) loss: 0.8154 (0.8147) time: 0.1422 data: 0.0621 max mem: 9390 +Train: [70] [4200/6250] eta: 0:04:38 lr: 0.000027 grad: 0.1240 (0.1152) loss: 0.8114 (0.8147) time: 0.1432 data: 0.0665 max mem: 9390 +Train: [70] [4300/6250] eta: 0:04:24 lr: 0.000027 grad: 0.1123 (0.1152) loss: 0.8182 (0.8147) time: 0.1282 data: 0.0438 max mem: 9390 +Train: [70] [4400/6250] eta: 0:04:10 lr: 0.000027 grad: 0.1119 (0.1153) loss: 0.8106 (0.8146) time: 0.1360 data: 0.0578 max mem: 9390 +Train: [70] [4500/6250] eta: 0:03:57 lr: 0.000027 grad: 0.1177 (0.1153) loss: 0.8128 (0.8145) time: 0.1232 data: 0.0407 max mem: 9390 +Train: [70] [4600/6250] eta: 0:03:43 lr: 0.000027 grad: 0.1106 (0.1154) loss: 0.8155 (0.8145) time: 0.1251 data: 0.0449 max mem: 9390 +Train: [70] [4700/6250] eta: 0:03:29 lr: 0.000027 grad: 0.1183 (0.1154) loss: 0.8091 (0.8144) time: 0.1534 data: 0.0758 max mem: 9390 +Train: [70] [4800/6250] eta: 0:03:16 lr: 0.000027 grad: 0.1119 (0.1155) loss: 0.8145 (0.8143) time: 0.1240 data: 0.0380 max mem: 9390 +Train: [70] [4900/6250] eta: 0:03:02 lr: 0.000027 grad: 0.1064 (0.1156) loss: 0.8100 (0.8142) time: 0.1287 data: 0.0501 max mem: 9390 +Train: [70] [5000/6250] eta: 0:02:49 lr: 0.000027 grad: 0.1165 (0.1156) loss: 0.8131 (0.8141) time: 0.1289 data: 0.0491 max mem: 9390 +Train: [70] [5100/6250] eta: 0:02:35 lr: 0.000027 grad: 0.1206 (0.1157) loss: 0.8047 (0.8140) time: 0.1320 data: 0.0540 max mem: 9390 +Train: [70] [5200/6250] eta: 0:02:21 lr: 0.000027 grad: 0.1134 (0.1158) loss: 0.8065 (0.8138) time: 0.1167 data: 0.0351 max mem: 9390 +Train: [70] [5300/6250] eta: 0:02:08 lr: 0.000027 grad: 0.1090 (0.1159) loss: 0.8132 (0.8138) time: 0.1325 data: 0.0555 max mem: 9390 +Train: [70] [5400/6250] eta: 0:01:54 lr: 0.000027 grad: 0.1133 (0.1159) loss: 0.8166 (0.8138) time: 0.1342 data: 0.0448 max mem: 9390 +Train: [70] [5500/6250] eta: 0:01:41 lr: 0.000027 grad: 0.1108 (0.1158) loss: 0.8176 (0.8138) time: 0.1357 data: 0.0555 max mem: 9390 +Train: [70] [5600/6250] eta: 0:01:27 lr: 0.000027 grad: 0.1127 (0.1159) loss: 0.8118 (0.8137) time: 0.1722 data: 0.0836 max mem: 9390 +Train: [70] [5700/6250] eta: 0:01:14 lr: 0.000027 grad: 0.1209 (0.1159) loss: 0.8102 (0.8137) time: 0.1203 data: 0.0441 max mem: 9390 +Train: [70] [5800/6250] eta: 0:01:00 lr: 0.000027 grad: 0.1170 (0.1160) loss: 0.8124 (0.8137) time: 0.1588 data: 0.0727 max mem: 9390 +Train: [70] [5900/6250] eta: 0:00:47 lr: 0.000027 grad: 0.1194 (0.1160) loss: 0.8103 (0.8136) time: 0.1140 data: 0.0333 max mem: 9390 +Train: [70] [6000/6250] eta: 0:00:33 lr: 0.000027 grad: 0.1156 (0.1161) loss: 0.8106 (0.8136) time: 0.1102 data: 0.0313 max mem: 9390 +Train: [70] [6100/6250] eta: 0:00:20 lr: 0.000027 grad: 0.1153 (0.1161) loss: 0.8140 (0.8136) time: 0.0940 data: 0.0054 max mem: 9390 +Train: [70] [6200/6250] eta: 0:00:06 lr: 0.000027 grad: 0.1190 (0.1162) loss: 0.8101 (0.8135) time: 0.1339 data: 0.0524 max mem: 9390 +Train: [70] [6249/6250] eta: 0:00:00 lr: 0.000027 grad: 0.1138 (0.1162) loss: 0.8156 (0.8135) time: 0.1280 data: 0.0470 max mem: 9390 +Train: [70] Total time: 0:14:08 (0.1357 s / it) +Averaged stats: lr: 0.000027 grad: 0.1138 (0.1162) loss: 0.8156 (0.8135) +Eval (hcp-train-subset): [70] [ 0/62] eta: 0:04:20 loss: 0.8351 (0.8351) time: 4.2080 data: 4.1393 max mem: 9390 +Eval (hcp-train-subset): [70] [61/62] eta: 0:00:00 loss: 0.8221 (0.8270) time: 0.0977 data: 0.0723 max mem: 9390 +Eval (hcp-train-subset): [70] Total time: 0:00:13 (0.2108 s / it) +Averaged stats (hcp-train-subset): loss: 0.8221 (0.8270) +Eval (hcp-val): [70] [ 0/62] eta: 0:04:32 loss: 0.8283 (0.8283) time: 4.3948 data: 4.3570 max mem: 9390 +Eval (hcp-val): [70] [61/62] eta: 0:00:00 loss: 0.8302 (0.8322) time: 0.1077 data: 0.0822 max mem: 9390 +Eval (hcp-val): [70] Total time: 0:00:12 (0.1954 s / it) +Averaged stats (hcp-val): loss: 0.8302 (0.8322) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +Train: [71] [ 0/6250] eta: 10:00:51 lr: 0.000027 grad: 0.1774 (0.1774) loss: 0.8633 (0.8633) time: 5.7682 data: 5.6767 max mem: 9390 +Train: [71] [ 100/6250] eta: 0:19:08 lr: 0.000027 grad: 0.1169 (0.1391) loss: 0.8256 (0.8247) time: 0.1411 data: 0.0432 max mem: 9390 +Train: [71] [ 200/6250] eta: 0:16:34 lr: 0.000027 grad: 0.1260 (0.1342) loss: 0.8231 (0.8217) time: 0.1402 data: 0.0397 max mem: 9390 +Train: [71] [ 300/6250] eta: 0:15:23 lr: 0.000027 grad: 0.1106 (0.1315) loss: 0.8251 (0.8200) time: 0.1316 data: 0.0482 max mem: 9390 +Train: [71] [ 400/6250] eta: 0:14:41 lr: 0.000026 grad: 0.1132 (0.1284) loss: 0.8117 (0.8194) time: 0.1542 data: 0.0674 max mem: 9390 +Train: [71] [ 500/6250] eta: 0:14:01 lr: 0.000026 grad: 0.1136 (0.1265) loss: 0.8155 (0.8188) time: 0.1336 data: 0.0413 max mem: 9390 +Train: [71] [ 600/6250] eta: 0:13:31 lr: 0.000026 grad: 0.1137 (0.1241) loss: 0.8179 (0.8180) time: 0.1223 data: 0.0379 max mem: 9390 +Train: [71] [ 700/6250] eta: 0:13:05 lr: 0.000026 grad: 0.1101 (0.1226) loss: 0.8165 (0.8174) time: 0.1200 data: 0.0339 max mem: 9390 +Train: [71] [ 800/6250] eta: 0:12:41 lr: 0.000026 grad: 0.1127 (0.1215) loss: 0.8189 (0.8168) time: 0.1147 data: 0.0246 max mem: 9390 +Train: [71] [ 900/6250] eta: 0:12:21 lr: 0.000026 grad: 0.1055 (0.1202) loss: 0.8159 (0.8165) time: 0.1141 data: 0.0324 max mem: 9390 +Train: [71] [1000/6250] eta: 0:12:02 lr: 0.000026 grad: 0.1101 (0.1193) loss: 0.8152 (0.8164) time: 0.1162 data: 0.0358 max mem: 9390 +Train: [71] [1100/6250] eta: 0:11:43 lr: 0.000026 grad: 0.1066 (0.1186) loss: 0.8192 (0.8164) time: 0.1342 data: 0.0535 max mem: 9390 +Train: [71] [1200/6250] eta: 0:11:26 lr: 0.000026 grad: 0.1121 (0.1179) loss: 0.8220 (0.8165) time: 0.1278 data: 0.0459 max mem: 9390 +Train: [71] [1300/6250] eta: 0:11:11 lr: 0.000026 grad: 0.1062 (0.1172) loss: 0.8163 (0.8166) time: 0.1155 data: 0.0361 max mem: 9390 +Train: [71] [1400/6250] eta: 0:10:56 lr: 0.000026 grad: 0.1091 (0.1165) loss: 0.8130 (0.8168) time: 0.1442 data: 0.0618 max mem: 9390 +Train: [71] [1500/6250] eta: 0:10:46 lr: 0.000026 grad: 0.1059 (0.1162) loss: 0.8160 (0.8169) time: 0.1581 data: 0.0667 max mem: 9390 +Train: [71] [1600/6250] eta: 0:10:40 lr: 0.000026 grad: 0.1144 (0.1160) loss: 0.8097 (0.8167) time: 0.1320 data: 0.0501 max mem: 9390 +Train: [71] [1700/6250] eta: 0:10:28 lr: 0.000026 grad: 0.1113 (0.1159) loss: 0.8160 (0.8167) time: 0.1505 data: 0.0767 max mem: 9390 +Train: [71] [1800/6250] eta: 0:10:14 lr: 0.000026 grad: 0.1138 (0.1159) loss: 0.8072 (0.8163) time: 0.1517 data: 0.0686 max mem: 9390 +Train: [71] [1900/6250] eta: 0:10:01 lr: 0.000026 grad: 0.1158 (0.1158) loss: 0.8071 (0.8160) time: 0.1423 data: 0.0553 max mem: 9390 +Train: [71] [2000/6250] eta: 0:09:46 lr: 0.000026 grad: 0.1147 (0.1161) loss: 0.8104 (0.8157) time: 0.1216 data: 0.0412 max mem: 9390 +Train: [71] [2100/6250] eta: 0:09:30 lr: 0.000026 grad: 0.1177 (0.1160) loss: 0.8123 (0.8155) time: 0.1215 data: 0.0445 max mem: 9390 +Train: [71] [2200/6250] eta: 0:09:15 lr: 0.000026 grad: 0.1187 (0.1160) loss: 0.8123 (0.8153) time: 0.1257 data: 0.0459 max mem: 9390 +Train: [71] [2300/6250] eta: 0:08:59 lr: 0.000026 grad: 0.1129 (0.1162) loss: 0.8167 (0.8151) time: 0.1318 data: 0.0522 max mem: 9390 +Train: [71] [2400/6250] eta: 0:08:41 lr: 0.000026 grad: 0.1115 (0.1162) loss: 0.8190 (0.8151) time: 0.1143 data: 0.0290 max mem: 9390 +Train: [71] [2500/6250] eta: 0:08:25 lr: 0.000026 grad: 0.1201 (0.1163) loss: 0.8055 (0.8149) time: 0.1207 data: 0.0379 max mem: 9390 +Train: [71] [2600/6250] eta: 0:08:09 lr: 0.000026 grad: 0.1151 (0.1164) loss: 0.8100 (0.8147) time: 0.1278 data: 0.0504 max mem: 9390 +Train: [71] [2700/6250] eta: 0:07:53 lr: 0.000026 grad: 0.1214 (0.1166) loss: 0.8121 (0.8146) time: 0.0969 data: 0.0141 max mem: 9390 +Train: [71] [2800/6250] eta: 0:07:37 lr: 0.000026 grad: 0.1166 (0.1167) loss: 0.8155 (0.8145) time: 0.1126 data: 0.0348 max mem: 9390 +Train: [71] [2900/6250] eta: 0:07:22 lr: 0.000026 grad: 0.1186 (0.1168) loss: 0.8124 (0.8144) time: 0.1175 data: 0.0407 max mem: 9390 +Train: [71] [3000/6250] eta: 0:07:08 lr: 0.000026 grad: 0.1122 (0.1167) loss: 0.8137 (0.8143) time: 0.1182 data: 0.0406 max mem: 9390 +Train: [71] [3100/6250] eta: 0:06:54 lr: 0.000026 grad: 0.1157 (0.1167) loss: 0.8114 (0.8143) time: 0.1257 data: 0.0467 max mem: 9390 +Train: [71] [3200/6250] eta: 0:06:41 lr: 0.000026 grad: 0.1134 (0.1167) loss: 0.8219 (0.8143) time: 0.1391 data: 0.0614 max mem: 9390 +Train: [71] [3300/6250] eta: 0:06:27 lr: 0.000026 grad: 0.1145 (0.1167) loss: 0.8138 (0.8144) time: 0.1236 data: 0.0483 max mem: 9390 +Train: [71] [3400/6250] eta: 0:06:14 lr: 0.000026 grad: 0.1182 (0.1167) loss: 0.8167 (0.8144) time: 0.1344 data: 0.0549 max mem: 9390 +Train: [71] [3500/6250] eta: 0:06:00 lr: 0.000026 grad: 0.1118 (0.1166) loss: 0.8224 (0.8145) time: 0.1342 data: 0.0544 max mem: 9390 +Train: [71] [3600/6250] eta: 0:05:47 lr: 0.000026 grad: 0.1100 (0.1166) loss: 0.8146 (0.8145) time: 0.1562 data: 0.0800 max mem: 9390 +Train: [71] [3700/6250] eta: 0:05:34 lr: 0.000026 grad: 0.1078 (0.1165) loss: 0.8192 (0.8145) time: 0.1458 data: 0.0708 max mem: 9390 +Train: [71] [3800/6250] eta: 0:05:22 lr: 0.000026 grad: 0.1063 (0.1164) loss: 0.8131 (0.8146) time: 0.1411 data: 0.0634 max mem: 9390 +Train: [71] [3900/6250] eta: 0:05:09 lr: 0.000026 grad: 0.1173 (0.1164) loss: 0.8200 (0.8147) time: 0.1377 data: 0.0576 max mem: 9390 +Train: [71] [4000/6250] eta: 0:04:57 lr: 0.000026 grad: 0.1150 (0.1163) loss: 0.8145 (0.8148) time: 0.1339 data: 0.0458 max mem: 9390 +Train: [71] [4100/6250] eta: 0:04:44 lr: 0.000026 grad: 0.1079 (0.1163) loss: 0.8194 (0.8148) time: 0.1423 data: 0.0113 max mem: 9390 +Train: [71] [4200/6250] eta: 0:04:31 lr: 0.000025 grad: 0.1116 (0.1163) loss: 0.8158 (0.8148) time: 0.1361 data: 0.0615 max mem: 9390 +Train: [71] [4300/6250] eta: 0:04:18 lr: 0.000025 grad: 0.1151 (0.1164) loss: 0.8149 (0.8147) time: 0.1364 data: 0.0548 max mem: 9390 +Train: [71] [4400/6250] eta: 0:04:05 lr: 0.000025 grad: 0.1168 (0.1164) loss: 0.8145 (0.8147) time: 0.1482 data: 0.0721 max mem: 9390 +Train: [71] [4500/6250] eta: 0:03:52 lr: 0.000025 grad: 0.1108 (0.1164) loss: 0.8099 (0.8146) time: 0.1038 data: 0.0261 max mem: 9390 +Train: [71] [4600/6250] eta: 0:03:39 lr: 0.000025 grad: 0.1170 (0.1165) loss: 0.8105 (0.8145) time: 0.1537 data: 0.0694 max mem: 9390 +Train: [71] [4700/6250] eta: 0:03:26 lr: 0.000025 grad: 0.1144 (0.1165) loss: 0.8183 (0.8145) time: 0.1544 data: 0.0706 max mem: 9390 +Train: [71] [4800/6250] eta: 0:03:13 lr: 0.000025 grad: 0.1126 (0.1166) loss: 0.8143 (0.8144) time: 0.1391 data: 0.0624 max mem: 9390 +Train: [71] [4900/6250] eta: 0:03:00 lr: 0.000025 grad: 0.1183 (0.1167) loss: 0.8153 (0.8143) time: 0.1610 data: 0.0802 max mem: 9390 +Train: [71] [5000/6250] eta: 0:02:47 lr: 0.000025 grad: 0.1176 (0.1169) loss: 0.8116 (0.8142) time: 0.1547 data: 0.0761 max mem: 9390 +Train: [71] [5100/6250] eta: 0:02:33 lr: 0.000025 grad: 0.1211 (0.1169) loss: 0.8097 (0.8141) time: 0.1383 data: 0.0513 max mem: 9390 +Train: [71] [5200/6250] eta: 0:02:20 lr: 0.000025 grad: 0.1152 (0.1169) loss: 0.8107 (0.8140) time: 0.1142 data: 0.0414 max mem: 9390 +Train: [71] [5300/6250] eta: 0:02:07 lr: 0.000025 grad: 0.1149 (0.1169) loss: 0.8087 (0.8140) time: 0.1530 data: 0.0763 max mem: 9390 +Train: [71] [5400/6250] eta: 0:01:54 lr: 0.000025 grad: 0.1149 (0.1170) loss: 0.8136 (0.8139) time: 0.1261 data: 0.0518 max mem: 9390 +Train: [71] [5500/6250] eta: 0:01:40 lr: 0.000025 grad: 0.1177 (0.1171) loss: 0.8038 (0.8137) time: 0.1301 data: 0.0499 max mem: 9390 +Train: [71] [5600/6250] eta: 0:01:27 lr: 0.000025 grad: 0.1243 (0.1172) loss: 0.8049 (0.8137) time: 0.1763 data: 0.1026 max mem: 9390 +Train: [71] [5700/6250] eta: 0:01:14 lr: 0.000025 grad: 0.1236 (0.1173) loss: 0.8047 (0.8135) time: 0.1275 data: 0.0378 max mem: 9390 +Train: [71] [5800/6250] eta: 0:01:00 lr: 0.000025 grad: 0.1121 (0.1173) loss: 0.8095 (0.8134) time: 0.1445 data: 0.0692 max mem: 9390 +Train: [71] [5900/6250] eta: 0:00:47 lr: 0.000025 grad: 0.1139 (0.1173) loss: 0.8132 (0.8134) time: 0.1609 data: 0.0836 max mem: 9390 +Train: [71] [6000/6250] eta: 0:00:33 lr: 0.000025 grad: 0.1166 (0.1174) loss: 0.8111 (0.8133) time: 0.1051 data: 0.0257 max mem: 9390 +Train: [71] [6100/6250] eta: 0:00:20 lr: 0.000025 grad: 0.1164 (0.1174) loss: 0.8113 (0.8132) time: 0.1376 data: 0.0572 max mem: 9390 +Train: [71] [6200/6250] eta: 0:00:06 lr: 0.000025 grad: 0.1163 (0.1174) loss: 0.8051 (0.8131) time: 0.1357 data: 0.0582 max mem: 9390 +Train: [71] [6249/6250] eta: 0:00:00 lr: 0.000025 grad: 0.1217 (0.1174) loss: 0.8037 (0.8131) time: 0.1486 data: 0.0714 max mem: 9390 +Train: [71] Total time: 0:14:12 (0.1365 s / it) +Averaged stats: lr: 0.000025 grad: 0.1217 (0.1174) loss: 0.8037 (0.8131) +Eval (hcp-train-subset): [71] [ 0/62] eta: 0:05:41 loss: 0.8314 (0.8314) time: 5.5160 data: 5.4842 max mem: 9390 +Eval (hcp-train-subset): [71] [61/62] eta: 0:00:00 loss: 0.8219 (0.8269) time: 0.1354 data: 0.1086 max mem: 9390 +Eval (hcp-train-subset): [71] Total time: 0:00:13 (0.2138 s / it) +Averaged stats (hcp-train-subset): loss: 0.8219 (0.8269) +Eval (hcp-val): [71] [ 0/62] eta: 0:04:30 loss: 0.8308 (0.8308) time: 4.3691 data: 4.3376 max mem: 9390 +Eval (hcp-val): [71] [61/62] eta: 0:00:00 loss: 0.8308 (0.8325) time: 0.1228 data: 0.0979 max mem: 9390 +Eval (hcp-val): [71] Total time: 0:00:12 (0.2056 s / it) +Averaged stats (hcp-val): loss: 0.8308 (0.8325) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +Train: [72] [ 0/6250] eta: 7:12:44 lr: 0.000025 grad: 0.0713 (0.0713) loss: 0.8698 (0.8698) time: 4.1543 data: 3.9447 max mem: 9390 +Train: [72] [ 100/6250] eta: 0:18:54 lr: 0.000025 grad: 0.1185 (0.1401) loss: 0.8318 (0.8279) time: 0.1310 data: 0.0265 max mem: 9390 +Train: [72] [ 200/6250] eta: 0:16:11 lr: 0.000025 grad: 0.1021 (0.1267) loss: 0.8293 (0.8257) time: 0.1448 data: 0.0445 max mem: 9390 +Train: [72] [ 300/6250] eta: 0:14:48 lr: 0.000025 grad: 0.1090 (0.1219) loss: 0.8163 (0.8245) time: 0.1308 data: 0.0428 max mem: 9390 +Train: [72] [ 400/6250] eta: 0:13:58 lr: 0.000025 grad: 0.1157 (0.1207) loss: 0.8198 (0.8233) time: 0.1099 data: 0.0257 max mem: 9390 +Train: [72] [ 500/6250] eta: 0:13:22 lr: 0.000025 grad: 0.1073 (0.1203) loss: 0.8190 (0.8217) time: 0.1064 data: 0.0240 max mem: 9390 +Train: [72] [ 600/6250] eta: 0:12:53 lr: 0.000025 grad: 0.1167 (0.1195) loss: 0.8140 (0.8211) time: 0.1182 data: 0.0321 max mem: 9390 +Train: [72] [ 700/6250] eta: 0:12:24 lr: 0.000025 grad: 0.1026 (0.1181) loss: 0.8249 (0.8207) time: 0.1196 data: 0.0325 max mem: 9390 +Train: [72] [ 800/6250] eta: 0:12:01 lr: 0.000025 grad: 0.1108 (0.1179) loss: 0.8200 (0.8203) time: 0.1187 data: 0.0319 max mem: 9390 +Train: [72] [ 900/6250] eta: 0:11:45 lr: 0.000025 grad: 0.1169 (0.1180) loss: 0.8121 (0.8195) time: 0.1240 data: 0.0351 max mem: 9390 +Train: [72] [1000/6250] eta: 0:11:30 lr: 0.000025 grad: 0.1154 (0.1180) loss: 0.8150 (0.8190) time: 0.1402 data: 0.0654 max mem: 9390 +Train: [72] [1100/6250] eta: 0:11:13 lr: 0.000025 grad: 0.1144 (0.1177) loss: 0.8112 (0.8183) time: 0.1372 data: 0.0590 max mem: 9390 +Train: [72] [1200/6250] eta: 0:11:02 lr: 0.000025 grad: 0.1112 (0.1174) loss: 0.8145 (0.8178) time: 0.1142 data: 0.0316 max mem: 9390 +Train: [72] [1300/6250] eta: 0:10:50 lr: 0.000025 grad: 0.1169 (0.1173) loss: 0.8136 (0.8173) time: 0.1508 data: 0.0691 max mem: 9390 +Train: [72] [1400/6250] eta: 0:10:38 lr: 0.000025 grad: 0.1133 (0.1175) loss: 0.8101 (0.8167) time: 0.1304 data: 0.0496 max mem: 9390 +Train: [72] [1500/6250] eta: 0:10:25 lr: 0.000025 grad: 0.1155 (0.1176) loss: 0.8077 (0.8162) time: 0.1444 data: 0.0655 max mem: 9390 +Train: [72] [1600/6250] eta: 0:10:15 lr: 0.000025 grad: 0.1162 (0.1179) loss: 0.8074 (0.8159) time: 0.1194 data: 0.0397 max mem: 9390 +Train: [72] [1700/6250] eta: 0:10:05 lr: 0.000024 grad: 0.1138 (0.1181) loss: 0.8111 (0.8154) time: 0.1726 data: 0.0930 max mem: 9390 +Train: [72] [1800/6250] eta: 0:09:53 lr: 0.000024 grad: 0.1240 (0.1184) loss: 0.8045 (0.8150) time: 0.1523 data: 0.0734 max mem: 9390 +Train: [72] [1900/6250] eta: 0:09:45 lr: 0.000024 grad: 0.1129 (0.1184) loss: 0.8158 (0.8147) time: 0.1450 data: 0.0666 max mem: 9390 +Train: [72] [2000/6250] eta: 0:09:32 lr: 0.000024 grad: 0.1158 (0.1184) loss: 0.8126 (0.8146) time: 0.1313 data: 0.0481 max mem: 9390 +Train: [72] [2100/6250] eta: 0:09:18 lr: 0.000024 grad: 0.1130 (0.1185) loss: 0.8099 (0.8144) time: 0.1340 data: 0.0486 max mem: 9390 +Train: [72] [2200/6250] eta: 0:09:03 lr: 0.000024 grad: 0.1208 (0.1185) loss: 0.8173 (0.8143) time: 0.1096 data: 0.0253 max mem: 9390 +Train: [72] [2300/6250] eta: 0:08:48 lr: 0.000024 grad: 0.1163 (0.1185) loss: 0.8087 (0.8143) time: 0.1189 data: 0.0392 max mem: 9390 +Train: [72] [2400/6250] eta: 0:08:34 lr: 0.000024 grad: 0.1175 (0.1186) loss: 0.8156 (0.8142) time: 0.1413 data: 0.0609 max mem: 9390 +Train: [72] [2500/6250] eta: 0:08:17 lr: 0.000024 grad: 0.1155 (0.1186) loss: 0.8112 (0.8141) time: 0.1074 data: 0.0188 max mem: 9390 +Train: [72] [2600/6250] eta: 0:08:03 lr: 0.000024 grad: 0.1154 (0.1187) loss: 0.8160 (0.8141) time: 0.1307 data: 0.0523 max mem: 9390 +Train: [72] [2700/6250] eta: 0:07:47 lr: 0.000024 grad: 0.1115 (0.1188) loss: 0.8126 (0.8140) time: 0.1200 data: 0.0300 max mem: 9390 +Train: [72] [2800/6250] eta: 0:07:32 lr: 0.000024 grad: 0.1209 (0.1188) loss: 0.8189 (0.8140) time: 0.1285 data: 0.0454 max mem: 9390 +Train: [72] [2900/6250] eta: 0:07:18 lr: 0.000024 grad: 0.1176 (0.1189) loss: 0.8146 (0.8139) time: 0.1194 data: 0.0359 max mem: 9390 +Train: [72] [3000/6250] eta: 0:07:05 lr: 0.000024 grad: 0.1239 (0.1190) loss: 0.8124 (0.8138) time: 0.1286 data: 0.0513 max mem: 9390 +Train: [72] [3100/6250] eta: 0:06:51 lr: 0.000024 grad: 0.1191 (0.1190) loss: 0.8028 (0.8137) time: 0.1228 data: 0.0448 max mem: 9390 +Train: [72] [3200/6250] eta: 0:06:38 lr: 0.000024 grad: 0.1148 (0.1190) loss: 0.8114 (0.8137) time: 0.1558 data: 0.0661 max mem: 9390 +Train: [72] [3300/6250] eta: 0:06:25 lr: 0.000024 grad: 0.1161 (0.1189) loss: 0.8151 (0.8137) time: 0.1104 data: 0.0279 max mem: 9390 +Train: [72] [3400/6250] eta: 0:06:12 lr: 0.000024 grad: 0.1142 (0.1188) loss: 0.8120 (0.8138) time: 0.1341 data: 0.0437 max mem: 9390 +Train: [72] [3500/6250] eta: 0:05:59 lr: 0.000024 grad: 0.1132 (0.1188) loss: 0.8061 (0.8137) time: 0.1284 data: 0.0437 max mem: 9390 +Train: [72] [3600/6250] eta: 0:05:46 lr: 0.000024 grad: 0.1147 (0.1188) loss: 0.8088 (0.8137) time: 0.1239 data: 0.0420 max mem: 9390 +Train: [72] [3700/6250] eta: 0:05:33 lr: 0.000024 grad: 0.1194 (0.1188) loss: 0.8103 (0.8136) time: 0.1413 data: 0.0616 max mem: 9390 +Train: [72] [3800/6250] eta: 0:05:20 lr: 0.000024 grad: 0.1163 (0.1189) loss: 0.8129 (0.8136) time: 0.1122 data: 0.0246 max mem: 9390 +Train: [72] [3900/6250] eta: 0:05:07 lr: 0.000024 grad: 0.1182 (0.1189) loss: 0.8175 (0.8136) time: 0.1598 data: 0.0840 max mem: 9390 +Train: [72] [4000/6250] eta: 0:04:54 lr: 0.000024 grad: 0.1148 (0.1188) loss: 0.8135 (0.8136) time: 0.1464 data: 0.0654 max mem: 9390 +Train: [72] [4100/6250] eta: 0:04:41 lr: 0.000024 grad: 0.1128 (0.1187) loss: 0.8138 (0.8136) time: 0.1279 data: 0.0511 max mem: 9390 +Train: [72] [4200/6250] eta: 0:04:28 lr: 0.000024 grad: 0.1202 (0.1187) loss: 0.8099 (0.8136) time: 0.1477 data: 0.0672 max mem: 9390 +Train: [72] [4300/6250] eta: 0:04:16 lr: 0.000024 grad: 0.1136 (0.1187) loss: 0.8153 (0.8137) time: 0.1669 data: 0.0799 max mem: 9390 +Train: [72] [4400/6250] eta: 0:04:03 lr: 0.000024 grad: 0.1111 (0.1187) loss: 0.8148 (0.8137) time: 0.1470 data: 0.0664 max mem: 9390 +Train: [72] [4500/6250] eta: 0:03:50 lr: 0.000024 grad: 0.1125 (0.1186) loss: 0.8153 (0.8138) time: 0.1499 data: 0.0644 max mem: 9390 +Train: [72] [4600/6250] eta: 0:03:37 lr: 0.000024 grad: 0.1170 (0.1187) loss: 0.8171 (0.8138) time: 0.1423 data: 0.0642 max mem: 9390 +Train: [72] [4700/6250] eta: 0:03:25 lr: 0.000024 grad: 0.1095 (0.1186) loss: 0.8164 (0.8139) time: 0.1621 data: 0.0761 max mem: 9390 +Train: [72] [4800/6250] eta: 0:03:11 lr: 0.000024 grad: 0.1085 (0.1186) loss: 0.8111 (0.8139) time: 0.1395 data: 0.0575 max mem: 9390 +Train: [72] [4900/6250] eta: 0:02:58 lr: 0.000024 grad: 0.1171 (0.1186) loss: 0.8181 (0.8140) time: 0.1275 data: 0.0513 max mem: 9390 +Train: [72] [5000/6250] eta: 0:02:45 lr: 0.000024 grad: 0.1147 (0.1187) loss: 0.8187 (0.8140) time: 0.1191 data: 0.0395 max mem: 9390 +Train: [72] [5100/6250] eta: 0:02:32 lr: 0.000024 grad: 0.1152 (0.1187) loss: 0.8157 (0.8140) time: 0.1256 data: 0.0432 max mem: 9390 +Train: [72] [5200/6250] eta: 0:02:18 lr: 0.000024 grad: 0.1159 (0.1188) loss: 0.8165 (0.8140) time: 0.1308 data: 0.0531 max mem: 9390 +Train: [72] [5300/6250] eta: 0:02:05 lr: 0.000024 grad: 0.1136 (0.1188) loss: 0.8210 (0.8141) time: 0.1315 data: 0.0567 max mem: 9390 +Train: [72] [5400/6250] eta: 0:01:52 lr: 0.000024 grad: 0.1205 (0.1188) loss: 0.8231 (0.8141) time: 0.1382 data: 0.0604 max mem: 9390 +Train: [72] [5500/6250] eta: 0:01:39 lr: 0.000023 grad: 0.1159 (0.1188) loss: 0.8159 (0.8141) time: 0.1178 data: 0.0364 max mem: 9390 +Train: [72] [5600/6250] eta: 0:01:25 lr: 0.000023 grad: 0.1155 (0.1188) loss: 0.8123 (0.8142) time: 0.1289 data: 0.0513 max mem: 9390 +Train: [72] [5700/6250] eta: 0:01:12 lr: 0.000023 grad: 0.1133 (0.1188) loss: 0.8176 (0.8142) time: 0.1608 data: 0.0762 max mem: 9390 +Train: [72] [5800/6250] eta: 0:00:59 lr: 0.000023 grad: 0.1230 (0.1188) loss: 0.8154 (0.8142) time: 0.1236 data: 0.0458 max mem: 9390 +Train: [72] [5900/6250] eta: 0:00:46 lr: 0.000023 grad: 0.1114 (0.1187) loss: 0.8147 (0.8142) time: 0.1637 data: 0.0879 max mem: 9390 +Train: [72] [6000/6250] eta: 0:00:33 lr: 0.000023 grad: 0.1118 (0.1187) loss: 0.8175 (0.8142) time: 0.1334 data: 0.0450 max mem: 9390 +Train: [72] [6100/6250] eta: 0:00:19 lr: 0.000023 grad: 0.1156 (0.1187) loss: 0.8160 (0.8143) time: 0.1476 data: 0.0628 max mem: 9390 +Train: [72] [6200/6250] eta: 0:00:06 lr: 0.000023 grad: 0.1187 (0.1186) loss: 0.8121 (0.8143) time: 0.1376 data: 0.0603 max mem: 9390 +Train: [72] [6249/6250] eta: 0:00:00 lr: 0.000023 grad: 0.1127 (0.1186) loss: 0.8087 (0.8143) time: 0.1113 data: 0.0309 max mem: 9390 +Train: [72] Total time: 0:13:57 (0.1339 s / it) +Averaged stats: lr: 0.000023 grad: 0.1127 (0.1186) loss: 0.8087 (0.8143) +Eval (hcp-train-subset): [72] [ 0/62] eta: 0:05:27 loss: 0.8382 (0.8382) time: 5.2756 data: 5.2372 max mem: 9390 +Eval (hcp-train-subset): [72] [61/62] eta: 0:00:00 loss: 0.8248 (0.8271) time: 0.1366 data: 0.1116 max mem: 9390 +Eval (hcp-train-subset): [72] Total time: 0:00:13 (0.2155 s / it) +Averaged stats (hcp-train-subset): loss: 0.8248 (0.8271) +Eval (hcp-val): [72] [ 0/62] eta: 0:05:23 loss: 0.8316 (0.8316) time: 5.2186 data: 5.1885 max mem: 9390 +Eval (hcp-val): [72] [61/62] eta: 0:00:00 loss: 0.8295 (0.8317) time: 0.1185 data: 0.0933 max mem: 9390 +Eval (hcp-val): [72] Total time: 0:00:12 (0.2064 s / it) +Averaged stats (hcp-val): loss: 0.8295 (0.8317) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +Train: [73] [ 0/6250] eta: 8:50:38 lr: 0.000023 grad: 0.1268 (0.1268) loss: 0.8701 (0.8701) time: 5.0941 data: 4.9706 max mem: 9390 +Train: [73] [ 100/6250] eta: 0:18:43 lr: 0.000023 grad: 0.1344 (0.1555) loss: 0.8214 (0.8214) time: 0.1385 data: 0.0443 max mem: 9390 +Train: [73] [ 200/6250] eta: 0:16:17 lr: 0.000023 grad: 0.1200 (0.1452) loss: 0.8080 (0.8170) time: 0.1387 data: 0.0539 max mem: 9390 +Train: [73] [ 300/6250] eta: 0:15:03 lr: 0.000023 grad: 0.1124 (0.1381) loss: 0.8193 (0.8170) time: 0.1339 data: 0.0425 max mem: 9390 +Train: [73] [ 400/6250] eta: 0:14:15 lr: 0.000023 grad: 0.1118 (0.1326) loss: 0.8225 (0.8176) time: 0.1367 data: 0.0536 max mem: 9390 +Train: [73] [ 500/6250] eta: 0:13:39 lr: 0.000023 grad: 0.1121 (0.1291) loss: 0.8206 (0.8180) time: 0.1329 data: 0.0337 max mem: 9390 +Train: [73] [ 600/6250] eta: 0:13:10 lr: 0.000023 grad: 0.1099 (0.1270) loss: 0.8187 (0.8181) time: 0.1301 data: 0.0395 max mem: 9390 +Train: [73] [ 700/6250] eta: 0:12:48 lr: 0.000023 grad: 0.1145 (0.1257) loss: 0.8200 (0.8182) time: 0.1324 data: 0.0463 max mem: 9390 +Train: [73] [ 800/6250] eta: 0:12:22 lr: 0.000023 grad: 0.1179 (0.1246) loss: 0.8175 (0.8180) time: 0.1198 data: 0.0399 max mem: 9390 +Train: [73] [ 900/6250] eta: 0:12:10 lr: 0.000023 grad: 0.1117 (0.1234) loss: 0.8183 (0.8178) time: 0.1546 data: 0.0730 max mem: 9390 +Train: [73] [1000/6250] eta: 0:11:56 lr: 0.000023 grad: 0.1162 (0.1227) loss: 0.8166 (0.8176) time: 0.1069 data: 0.0279 max mem: 9390 +Train: [73] [1100/6250] eta: 0:11:40 lr: 0.000023 grad: 0.1164 (0.1220) loss: 0.8140 (0.8172) time: 0.1111 data: 0.0330 max mem: 9390 +Train: [73] [1200/6250] eta: 0:11:25 lr: 0.000023 grad: 0.1169 (0.1220) loss: 0.8113 (0.8163) time: 0.1391 data: 0.0573 max mem: 9390 +Train: [73] [1300/6250] eta: 0:11:11 lr: 0.000023 grad: 0.1118 (0.1217) loss: 0.8102 (0.8157) time: 0.1106 data: 0.0269 max mem: 9390 +Train: [73] [1400/6250] eta: 0:10:57 lr: 0.000023 grad: 0.1215 (0.1215) loss: 0.8086 (0.8153) time: 0.1545 data: 0.0714 max mem: 9390 +Train: [73] [1500/6250] eta: 0:10:45 lr: 0.000023 grad: 0.1147 (0.1215) loss: 0.8085 (0.8149) time: 0.1417 data: 0.0624 max mem: 9390 +Train: [73] [1600/6250] eta: 0:10:35 lr: 0.000023 grad: 0.1131 (0.1214) loss: 0.8169 (0.8147) time: 0.1913 data: 0.1185 max mem: 9390 +Train: [73] [1700/6250] eta: 0:10:26 lr: 0.000023 grad: 0.1177 (0.1214) loss: 0.8071 (0.8144) time: 0.1347 data: 0.0415 max mem: 9390 +Train: [73] [1800/6250] eta: 0:10:15 lr: 0.000023 grad: 0.1208 (0.1212) loss: 0.8050 (0.8142) time: 0.1613 data: 0.0812 max mem: 9390 +Train: [73] [1900/6250] eta: 0:10:02 lr: 0.000023 grad: 0.1143 (0.1210) loss: 0.8096 (0.8141) time: 0.1416 data: 0.0597 max mem: 9390 +Train: [73] [2000/6250] eta: 0:09:49 lr: 0.000023 grad: 0.1162 (0.1209) loss: 0.8078 (0.8140) time: 0.1438 data: 0.0671 max mem: 9390 +Train: [73] [2100/6250] eta: 0:09:34 lr: 0.000023 grad: 0.1217 (0.1209) loss: 0.8100 (0.8138) time: 0.1326 data: 0.0565 max mem: 9390 +Train: [73] [2200/6250] eta: 0:09:18 lr: 0.000023 grad: 0.1136 (0.1208) loss: 0.8158 (0.8138) time: 0.1248 data: 0.0487 max mem: 9390 +Train: [73] [2300/6250] eta: 0:09:02 lr: 0.000023 grad: 0.1134 (0.1207) loss: 0.8121 (0.8137) time: 0.1250 data: 0.0458 max mem: 9390 +Train: [73] [2400/6250] eta: 0:08:45 lr: 0.000023 grad: 0.1220 (0.1207) loss: 0.8146 (0.8137) time: 0.1170 data: 0.0262 max mem: 9390 +Train: [73] [2500/6250] eta: 0:08:28 lr: 0.000023 grad: 0.1178 (0.1206) loss: 0.8081 (0.8135) time: 0.1152 data: 0.0297 max mem: 9390 +Train: [73] [2600/6250] eta: 0:08:12 lr: 0.000023 grad: 0.1159 (0.1207) loss: 0.8102 (0.8134) time: 0.1128 data: 0.0357 max mem: 9390 +Train: [73] [2700/6250] eta: 0:07:56 lr: 0.000023 grad: 0.1094 (0.1206) loss: 0.8098 (0.8133) time: 0.1196 data: 0.0410 max mem: 9390 +Train: [73] [2800/6250] eta: 0:07:41 lr: 0.000023 grad: 0.1128 (0.1207) loss: 0.8112 (0.8131) time: 0.1263 data: 0.0446 max mem: 9390 +Train: [73] [2900/6250] eta: 0:07:28 lr: 0.000023 grad: 0.1211 (0.1206) loss: 0.8084 (0.8130) time: 0.1435 data: 0.0652 max mem: 9390 +Train: [73] [3000/6250] eta: 0:07:13 lr: 0.000023 grad: 0.1151 (0.1206) loss: 0.8085 (0.8130) time: 0.1220 data: 0.0405 max mem: 9390 +Train: [73] [3100/6250] eta: 0:07:00 lr: 0.000023 grad: 0.1116 (0.1207) loss: 0.8160 (0.8129) time: 0.1396 data: 0.0539 max mem: 9390 +Train: [73] [3200/6250] eta: 0:06:47 lr: 0.000022 grad: 0.1161 (0.1208) loss: 0.8101 (0.8128) time: 0.1341 data: 0.0529 max mem: 9390 +Train: [73] [3300/6250] eta: 0:06:35 lr: 0.000022 grad: 0.1196 (0.1209) loss: 0.8058 (0.8127) time: 0.0966 data: 0.0214 max mem: 9390 +Train: [73] [3400/6250] eta: 0:06:21 lr: 0.000022 grad: 0.1249 (0.1210) loss: 0.8094 (0.8126) time: 0.1301 data: 0.0489 max mem: 9390 +Train: [73] [3500/6250] eta: 0:06:07 lr: 0.000022 grad: 0.1170 (0.1211) loss: 0.8083 (0.8126) time: 0.1375 data: 0.0579 max mem: 9390 +Train: [73] [3600/6250] eta: 0:05:54 lr: 0.000022 grad: 0.1176 (0.1211) loss: 0.8068 (0.8125) time: 0.1059 data: 0.0225 max mem: 9390 +Train: [73] [3700/6250] eta: 0:05:41 lr: 0.000022 grad: 0.1228 (0.1211) loss: 0.8151 (0.8125) time: 0.1304 data: 0.0508 max mem: 9390 +Train: [73] [3800/6250] eta: 0:05:27 lr: 0.000022 grad: 0.1201 (0.1211) loss: 0.8126 (0.8125) time: 0.1209 data: 0.0442 max mem: 9390 +Train: [73] [3900/6250] eta: 0:05:15 lr: 0.000022 grad: 0.1158 (0.1211) loss: 0.8176 (0.8124) time: 0.1492 data: 0.0690 max mem: 9390 +Train: [73] [4000/6250] eta: 0:05:01 lr: 0.000022 grad: 0.1143 (0.1212) loss: 0.8115 (0.8123) time: 0.1341 data: 0.0539 max mem: 9390 +Train: [73] [4100/6250] eta: 0:04:48 lr: 0.000022 grad: 0.1220 (0.1212) loss: 0.8118 (0.8123) time: 0.1384 data: 0.0566 max mem: 9390 +Train: [73] [4200/6250] eta: 0:04:35 lr: 0.000022 grad: 0.1157 (0.1211) loss: 0.8129 (0.8123) time: 0.1516 data: 0.0620 max mem: 9390 +Train: [73] [4300/6250] eta: 0:04:22 lr: 0.000022 grad: 0.1128 (0.1211) loss: 0.8160 (0.8123) time: 0.1399 data: 0.0609 max mem: 9390 +Train: [73] [4400/6250] eta: 0:04:08 lr: 0.000022 grad: 0.1219 (0.1211) loss: 0.8133 (0.8123) time: 0.1327 data: 0.0507 max mem: 9390 +Train: [73] [4500/6250] eta: 0:03:55 lr: 0.000022 grad: 0.1205 (0.1211) loss: 0.8108 (0.8122) time: 0.1421 data: 0.0619 max mem: 9390 +Train: [73] [4600/6250] eta: 0:03:42 lr: 0.000022 grad: 0.1233 (0.1212) loss: 0.8124 (0.8122) time: 0.0989 data: 0.0138 max mem: 9390 +Train: [73] [4700/6250] eta: 0:03:28 lr: 0.000022 grad: 0.1202 (0.1212) loss: 0.8095 (0.8122) time: 0.1544 data: 0.0692 max mem: 9390 +Train: [73] [4800/6250] eta: 0:03:15 lr: 0.000022 grad: 0.1154 (0.1211) loss: 0.8119 (0.8122) time: 0.1430 data: 0.0665 max mem: 9390 +Train: [73] [4900/6250] eta: 0:03:02 lr: 0.000022 grad: 0.1134 (0.1211) loss: 0.8169 (0.8122) time: 0.1262 data: 0.0467 max mem: 9390 +Train: [73] [5000/6250] eta: 0:02:48 lr: 0.000022 grad: 0.1139 (0.1210) loss: 0.8149 (0.8123) time: 0.1141 data: 0.0350 max mem: 9390 +Train: [73] [5100/6250] eta: 0:02:35 lr: 0.000022 grad: 0.1184 (0.1210) loss: 0.8099 (0.8123) time: 0.1197 data: 0.0453 max mem: 9390 +Train: [73] [5200/6250] eta: 0:02:21 lr: 0.000022 grad: 0.1128 (0.1209) loss: 0.8181 (0.8123) time: 0.1269 data: 0.0475 max mem: 9390 +Train: [73] [5300/6250] eta: 0:02:08 lr: 0.000022 grad: 0.1145 (0.1209) loss: 0.8142 (0.8123) time: 0.1235 data: 0.0434 max mem: 9390 +Train: [73] [5400/6250] eta: 0:01:54 lr: 0.000022 grad: 0.1173 (0.1209) loss: 0.8114 (0.8124) time: 0.1573 data: 0.0710 max mem: 9390 +Train: [73] [5500/6250] eta: 0:01:41 lr: 0.000022 grad: 0.1195 (0.1209) loss: 0.8084 (0.8124) time: 0.1290 data: 0.0446 max mem: 9390 +Train: [73] [5600/6250] eta: 0:01:27 lr: 0.000022 grad: 0.1157 (0.1209) loss: 0.8175 (0.8124) time: 0.1216 data: 0.0420 max mem: 9390 +Train: [73] [5700/6250] eta: 0:01:14 lr: 0.000022 grad: 0.1134 (0.1208) loss: 0.8182 (0.8124) time: 0.1510 data: 0.0683 max mem: 9390 +Train: [73] [5800/6250] eta: 0:01:00 lr: 0.000022 grad: 0.1221 (0.1208) loss: 0.8169 (0.8125) time: 0.1368 data: 0.0545 max mem: 9390 +Train: [73] [5900/6250] eta: 0:00:47 lr: 0.000022 grad: 0.1181 (0.1208) loss: 0.8091 (0.8126) time: 0.1245 data: 0.0455 max mem: 9390 +Train: [73] [6000/6250] eta: 0:00:33 lr: 0.000022 grad: 0.1229 (0.1207) loss: 0.8163 (0.8126) time: 0.1814 data: 0.0962 max mem: 9390 +Train: [73] [6100/6250] eta: 0:00:20 lr: 0.000022 grad: 0.1197 (0.1207) loss: 0.8159 (0.8127) time: 0.1534 data: 0.0823 max mem: 9390 +Train: [73] [6200/6250] eta: 0:00:06 lr: 0.000022 grad: 0.1109 (0.1207) loss: 0.8248 (0.8127) time: 0.1389 data: 0.0550 max mem: 9390 +Train: [73] [6249/6250] eta: 0:00:00 lr: 0.000022 grad: 0.1054 (0.1206) loss: 0.8170 (0.8128) time: 0.1280 data: 0.0465 max mem: 9390 +Train: [73] Total time: 0:14:11 (0.1363 s / it) +Averaged stats: lr: 0.000022 grad: 0.1054 (0.1206) loss: 0.8170 (0.8128) +Eval (hcp-train-subset): [73] [ 0/62] eta: 0:03:39 loss: 0.8367 (0.8367) time: 3.5348 data: 3.4577 max mem: 9390 +Eval (hcp-train-subset): [73] [61/62] eta: 0:00:00 loss: 0.8219 (0.8263) time: 0.1108 data: 0.0840 max mem: 9390 +Eval (hcp-train-subset): [73] Total time: 0:00:13 (0.2116 s / it) +Averaged stats (hcp-train-subset): loss: 0.8219 (0.8263) +Eval (hcp-val): [73] [ 0/62] eta: 0:03:40 loss: 0.8293 (0.8293) time: 3.5492 data: 3.4321 max mem: 9390 +Eval (hcp-val): [73] [61/62] eta: 0:00:00 loss: 0.8304 (0.8315) time: 0.1146 data: 0.0896 max mem: 9390 +Eval (hcp-val): [73] Total time: 0:00:12 (0.2051 s / it) +Averaged stats (hcp-val): loss: 0.8304 (0.8315) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +Train: [74] [ 0/6250] eta: 9:08:52 lr: 0.000022 grad: 0.1291 (0.1291) loss: 0.8833 (0.8833) time: 5.2692 data: 5.1516 max mem: 9390 +Train: [74] [ 100/6250] eta: 0:19:09 lr: 0.000022 grad: 0.1262 (0.1435) loss: 0.8329 (0.8275) time: 0.1314 data: 0.0321 max mem: 9390 +Train: [74] [ 200/6250] eta: 0:16:25 lr: 0.000022 grad: 0.1242 (0.1372) loss: 0.8212 (0.8227) time: 0.1433 data: 0.0502 max mem: 9390 +Train: [74] [ 300/6250] eta: 0:15:08 lr: 0.000022 grad: 0.1310 (0.1346) loss: 0.8083 (0.8199) time: 0.1058 data: 0.0168 max mem: 9390 +Train: [74] [ 400/6250] eta: 0:14:16 lr: 0.000022 grad: 0.1123 (0.1323) loss: 0.8180 (0.8183) time: 0.1383 data: 0.0547 max mem: 9390 +Train: [74] [ 500/6250] eta: 0:13:30 lr: 0.000022 grad: 0.1179 (0.1291) loss: 0.8093 (0.8178) time: 0.1313 data: 0.0434 max mem: 9390 +Train: [74] [ 600/6250] eta: 0:12:58 lr: 0.000022 grad: 0.1117 (0.1277) loss: 0.8115 (0.8177) time: 0.1285 data: 0.0439 max mem: 9390 +Train: [74] [ 700/6250] eta: 0:12:30 lr: 0.000022 grad: 0.1194 (0.1264) loss: 0.8143 (0.8177) time: 0.1131 data: 0.0301 max mem: 9390 +Train: [74] [ 800/6250] eta: 0:12:07 lr: 0.000022 grad: 0.1065 (0.1248) loss: 0.8213 (0.8180) time: 0.1211 data: 0.0353 max mem: 9390 +Train: [74] [ 900/6250] eta: 0:11:53 lr: 0.000021 grad: 0.1097 (0.1239) loss: 0.8178 (0.8182) time: 0.1380 data: 0.0504 max mem: 9390 +Train: [74] [1000/6250] eta: 0:11:39 lr: 0.000021 grad: 0.1122 (0.1232) loss: 0.8175 (0.8184) time: 0.1119 data: 0.0246 max mem: 9390 +Train: [74] [1100/6250] eta: 0:11:24 lr: 0.000021 grad: 0.1174 (0.1227) loss: 0.8094 (0.8183) time: 0.1304 data: 0.0466 max mem: 9390 +Train: [74] [1200/6250] eta: 0:11:12 lr: 0.000021 grad: 0.1146 (0.1219) loss: 0.8198 (0.8184) time: 0.1331 data: 0.0510 max mem: 9390 +Train: [74] [1300/6250] eta: 0:10:56 lr: 0.000021 grad: 0.1116 (0.1217) loss: 0.8183 (0.8182) time: 0.1354 data: 0.0539 max mem: 9390 +Train: [74] [1400/6250] eta: 0:10:41 lr: 0.000021 grad: 0.1138 (0.1215) loss: 0.8191 (0.8179) time: 0.1244 data: 0.0388 max mem: 9390 +Train: [74] [1500/6250] eta: 0:10:28 lr: 0.000021 grad: 0.1202 (0.1214) loss: 0.8108 (0.8176) time: 0.1374 data: 0.0558 max mem: 9390 +Train: [74] [1600/6250] eta: 0:10:21 lr: 0.000021 grad: 0.1171 (0.1213) loss: 0.8143 (0.8172) time: 0.0892 data: 0.0002 max mem: 9390 +Train: [74] [1700/6250] eta: 0:10:13 lr: 0.000021 grad: 0.1172 (0.1213) loss: 0.8077 (0.8168) time: 0.1734 data: 0.0857 max mem: 9390 +Train: [74] [1800/6250] eta: 0:10:03 lr: 0.000021 grad: 0.1228 (0.1214) loss: 0.8062 (0.8165) time: 0.1645 data: 0.0789 max mem: 9390 +Train: [74] [1900/6250] eta: 0:09:51 lr: 0.000021 grad: 0.1303 (0.1215) loss: 0.8065 (0.8161) time: 0.1568 data: 0.0791 max mem: 9390 +Train: [74] [2000/6250] eta: 0:09:39 lr: 0.000021 grad: 0.1216 (0.1215) loss: 0.8085 (0.8158) time: 0.1406 data: 0.0574 max mem: 9390 +Train: [74] [2100/6250] eta: 0:09:25 lr: 0.000021 grad: 0.1204 (0.1215) loss: 0.8116 (0.8155) time: 0.1430 data: 0.0609 max mem: 9390 +Train: [74] [2200/6250] eta: 0:09:09 lr: 0.000021 grad: 0.1204 (0.1214) loss: 0.8076 (0.8153) time: 0.1183 data: 0.0362 max mem: 9390 +Train: [74] [2300/6250] eta: 0:08:54 lr: 0.000021 grad: 0.1148 (0.1213) loss: 0.8128 (0.8152) time: 0.1227 data: 0.0378 max mem: 9390 +Train: [74] [2400/6250] eta: 0:08:38 lr: 0.000021 grad: 0.1119 (0.1213) loss: 0.8167 (0.8150) time: 0.1213 data: 0.0264 max mem: 9390 +Train: [74] [2500/6250] eta: 0:08:22 lr: 0.000021 grad: 0.1226 (0.1213) loss: 0.8101 (0.8148) time: 0.1287 data: 0.0454 max mem: 9390 +Train: [74] [2600/6250] eta: 0:08:07 lr: 0.000021 grad: 0.1165 (0.1213) loss: 0.8041 (0.8146) time: 0.1321 data: 0.0506 max mem: 9390 +Train: [74] [2700/6250] eta: 0:07:51 lr: 0.000021 grad: 0.1155 (0.1212) loss: 0.8087 (0.8143) time: 0.1035 data: 0.0217 max mem: 9390 +Train: [74] [2800/6250] eta: 0:07:37 lr: 0.000021 grad: 0.1203 (0.1213) loss: 0.8043 (0.8140) time: 0.1029 data: 0.0251 max mem: 9390 +Train: [74] [2900/6250] eta: 0:07:23 lr: 0.000021 grad: 0.1233 (0.1212) loss: 0.8078 (0.8138) time: 0.1389 data: 0.0589 max mem: 9390 +Train: [74] [3000/6250] eta: 0:07:09 lr: 0.000021 grad: 0.1152 (0.1213) loss: 0.8100 (0.8137) time: 0.1247 data: 0.0464 max mem: 9390 +Train: [74] [3100/6250] eta: 0:06:57 lr: 0.000021 grad: 0.1202 (0.1213) loss: 0.8087 (0.8135) time: 0.1606 data: 0.0819 max mem: 9390 +Train: [74] [3200/6250] eta: 0:06:44 lr: 0.000021 grad: 0.1152 (0.1213) loss: 0.8127 (0.8135) time: 0.1433 data: 0.0622 max mem: 9390 +Train: [74] [3300/6250] eta: 0:06:30 lr: 0.000021 grad: 0.1154 (0.1213) loss: 0.8138 (0.8134) time: 0.1508 data: 0.0599 max mem: 9390 +Train: [74] [3400/6250] eta: 0:06:17 lr: 0.000021 grad: 0.1256 (0.1213) loss: 0.8080 (0.8134) time: 0.1226 data: 0.0441 max mem: 9390 +Train: [74] [3500/6250] eta: 0:06:04 lr: 0.000021 grad: 0.1300 (0.1214) loss: 0.8137 (0.8133) time: 0.1320 data: 0.0490 max mem: 9390 +Train: [74] [3600/6250] eta: 0:05:51 lr: 0.000021 grad: 0.1244 (0.1215) loss: 0.8117 (0.8132) time: 0.1322 data: 0.0569 max mem: 9390 +Train: [74] [3700/6250] eta: 0:05:38 lr: 0.000021 grad: 0.1210 (0.1216) loss: 0.8126 (0.8131) time: 0.1324 data: 0.0510 max mem: 9390 +Train: [74] [3800/6250] eta: 0:05:25 lr: 0.000021 grad: 0.1261 (0.1217) loss: 0.8059 (0.8130) time: 0.1512 data: 0.0700 max mem: 9390 +Train: [74] [3900/6250] eta: 0:05:12 lr: 0.000021 grad: 0.1269 (0.1218) loss: 0.8040 (0.8128) time: 0.1343 data: 0.0547 max mem: 9390 +Train: [74] [4000/6250] eta: 0:04:59 lr: 0.000021 grad: 0.1221 (0.1218) loss: 0.8108 (0.8127) time: 0.1345 data: 0.0519 max mem: 9390 +Train: [74] [4100/6250] eta: 0:04:46 lr: 0.000021 grad: 0.1181 (0.1220) loss: 0.8126 (0.8125) time: 0.1388 data: 0.0633 max mem: 9390 +Train: [74] [4200/6250] eta: 0:04:33 lr: 0.000021 grad: 0.1278 (0.1221) loss: 0.8004 (0.8123) time: 0.1336 data: 0.0520 max mem: 9390 +Train: [74] [4300/6250] eta: 0:04:19 lr: 0.000021 grad: 0.1298 (0.1223) loss: 0.8077 (0.8121) time: 0.1529 data: 0.0771 max mem: 9390 +Train: [74] [4400/6250] eta: 0:04:06 lr: 0.000021 grad: 0.1206 (0.1224) loss: 0.8039 (0.8120) time: 0.1333 data: 0.0518 max mem: 9390 +Train: [74] [4500/6250] eta: 0:03:53 lr: 0.000021 grad: 0.1201 (0.1225) loss: 0.8094 (0.8119) time: 0.1260 data: 0.0455 max mem: 9390 +Train: [74] [4600/6250] eta: 0:03:40 lr: 0.000021 grad: 0.1241 (0.1225) loss: 0.8086 (0.8118) time: 0.1331 data: 0.0538 max mem: 9390 +Train: [74] [4700/6250] eta: 0:03:27 lr: 0.000021 grad: 0.1268 (0.1226) loss: 0.8131 (0.8118) time: 0.1542 data: 0.0728 max mem: 9390 +Train: [74] [4800/6250] eta: 0:03:14 lr: 0.000021 grad: 0.1196 (0.1227) loss: 0.8112 (0.8117) time: 0.1438 data: 0.0620 max mem: 9390 +Train: [74] [4900/6250] eta: 0:03:00 lr: 0.000020 grad: 0.1226 (0.1227) loss: 0.8108 (0.8117) time: 0.1419 data: 0.0651 max mem: 9390 +Train: [74] [5000/6250] eta: 0:02:47 lr: 0.000020 grad: 0.1258 (0.1228) loss: 0.8099 (0.8116) time: 0.1285 data: 0.0420 max mem: 9390 +Train: [74] [5100/6250] eta: 0:02:34 lr: 0.000020 grad: 0.1188 (0.1228) loss: 0.8112 (0.8117) time: 0.1371 data: 0.0540 max mem: 9390 +Train: [74] [5200/6250] eta: 0:02:21 lr: 0.000020 grad: 0.1153 (0.1228) loss: 0.8165 (0.8116) time: 0.1402 data: 0.0601 max mem: 9390 +Train: [74] [5300/6250] eta: 0:02:07 lr: 0.000020 grad: 0.1220 (0.1228) loss: 0.8063 (0.8116) time: 0.1392 data: 0.0581 max mem: 9390 +Train: [74] [5400/6250] eta: 0:01:54 lr: 0.000020 grad: 0.1188 (0.1229) loss: 0.8139 (0.8117) time: 0.1453 data: 0.0660 max mem: 9390 +Train: [74] [5500/6250] eta: 0:01:41 lr: 0.000020 grad: 0.1158 (0.1229) loss: 0.8180 (0.8117) time: 0.1421 data: 0.0660 max mem: 9390 +Train: [74] [5600/6250] eta: 0:01:27 lr: 0.000020 grad: 0.1181 (0.1229) loss: 0.8131 (0.8117) time: 0.1641 data: 0.0847 max mem: 9390 +Train: [74] [5700/6250] eta: 0:01:14 lr: 0.000020 grad: 0.1241 (0.1230) loss: 0.8077 (0.8117) time: 0.1460 data: 0.0696 max mem: 9390 +Train: [74] [5800/6250] eta: 0:01:00 lr: 0.000020 grad: 0.1203 (0.1230) loss: 0.8082 (0.8117) time: 0.1304 data: 0.0564 max mem: 9390 +Train: [74] [5900/6250] eta: 0:00:47 lr: 0.000020 grad: 0.1248 (0.1230) loss: 0.8133 (0.8118) time: 0.1529 data: 0.0687 max mem: 9390 +Train: [74] [6000/6250] eta: 0:00:33 lr: 0.000020 grad: 0.1167 (0.1230) loss: 0.8127 (0.8118) time: 0.1314 data: 0.0501 max mem: 9390 +Train: [74] [6100/6250] eta: 0:00:20 lr: 0.000020 grad: 0.1242 (0.1231) loss: 0.8155 (0.8118) time: 0.1639 data: 0.0792 max mem: 9390 +Train: [74] [6200/6250] eta: 0:00:06 lr: 0.000020 grad: 0.1242 (0.1231) loss: 0.8123 (0.8118) time: 0.1765 data: 0.0974 max mem: 9390 +Train: [74] [6249/6250] eta: 0:00:00 lr: 0.000020 grad: 0.1259 (0.1231) loss: 0.8053 (0.8118) time: 0.1434 data: 0.0634 max mem: 9390 +Train: [74] Total time: 0:14:16 (0.1371 s / it) +Averaged stats: lr: 0.000020 grad: 0.1259 (0.1231) loss: 0.8053 (0.8118) +Eval (hcp-train-subset): [74] [ 0/62] eta: 0:03:43 loss: 0.8344 (0.8344) time: 3.6010 data: 3.5300 max mem: 9390 +Eval (hcp-train-subset): [74] [61/62] eta: 0:00:00 loss: 0.8219 (0.8261) time: 0.1193 data: 0.0938 max mem: 9390 +Eval (hcp-train-subset): [74] Total time: 0:00:13 (0.2153 s / it) +Averaged stats (hcp-train-subset): loss: 0.8219 (0.8261) +Making plots (hcp-train-subset): example=20 +Eval (hcp-val): [74] [ 0/62] eta: 0:04:45 loss: 0.8255 (0.8255) time: 4.5972 data: 4.5635 max mem: 9390 +Eval (hcp-val): [74] [61/62] eta: 0:00:00 loss: 0.8293 (0.8313) time: 0.1246 data: 0.0990 max mem: 9390 +Eval (hcp-val): [74] Total time: 0:00:12 (0.2018 s / it) +Averaged stats (hcp-val): loss: 0.8293 (0.8313) +Making plots (hcp-val): example=15 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +Train: [75] [ 0/6250] eta: 8:26:44 lr: 0.000020 grad: 0.0809 (0.0809) loss: 0.8373 (0.8373) time: 4.8647 data: 4.5627 max mem: 9390 +Train: [75] [ 100/6250] eta: 0:19:09 lr: 0.000020 grad: 0.1334 (0.1397) loss: 0.8299 (0.8326) time: 0.1344 data: 0.0300 max mem: 9390 +Train: [75] [ 200/6250] eta: 0:16:23 lr: 0.000020 grad: 0.1178 (0.1358) loss: 0.8273 (0.8263) time: 0.1400 data: 0.0559 max mem: 9390 +Train: [75] [ 300/6250] eta: 0:15:04 lr: 0.000020 grad: 0.1176 (0.1325) loss: 0.8187 (0.8231) time: 0.1350 data: 0.0471 max mem: 9390 +Train: [75] [ 400/6250] eta: 0:14:10 lr: 0.000020 grad: 0.1348 (0.1305) loss: 0.8058 (0.8209) time: 0.1126 data: 0.0228 max mem: 9390 +Train: [75] [ 500/6250] eta: 0:13:28 lr: 0.000020 grad: 0.1111 (0.1282) loss: 0.8165 (0.8202) time: 0.1208 data: 0.0269 max mem: 9390 +Train: [75] [ 600/6250] eta: 0:12:55 lr: 0.000020 grad: 0.1159 (0.1266) loss: 0.8126 (0.8197) time: 0.1186 data: 0.0310 max mem: 9390 +Train: [75] [ 700/6250] eta: 0:12:27 lr: 0.000020 grad: 0.1207 (0.1251) loss: 0.8143 (0.8196) time: 0.1160 data: 0.0269 max mem: 9390 +Train: [75] [ 800/6250] eta: 0:12:08 lr: 0.000020 grad: 0.1188 (0.1246) loss: 0.8139 (0.8191) time: 0.1480 data: 0.0651 max mem: 9390 +Train: [75] [ 900/6250] eta: 0:11:53 lr: 0.000020 grad: 0.1147 (0.1243) loss: 0.8197 (0.8186) time: 0.1305 data: 0.0445 max mem: 9390 +Train: [75] [1000/6250] eta: 0:11:43 lr: 0.000020 grad: 0.1163 (0.1240) loss: 0.8139 (0.8183) time: 0.1349 data: 0.0548 max mem: 9390 +Train: [75] [1100/6250] eta: 0:11:26 lr: 0.000020 grad: 0.1206 (0.1236) loss: 0.8149 (0.8178) time: 0.1237 data: 0.0437 max mem: 9390 +Train: [75] [1200/6250] eta: 0:11:11 lr: 0.000020 grad: 0.1190 (0.1234) loss: 0.8037 (0.8172) time: 0.1225 data: 0.0420 max mem: 9390 +Train: [75] [1300/6250] eta: 0:10:58 lr: 0.000020 grad: 0.1185 (0.1230) loss: 0.8100 (0.8168) time: 0.1469 data: 0.0704 max mem: 9390 +Train: [75] [1400/6250] eta: 0:10:48 lr: 0.000020 grad: 0.1168 (0.1229) loss: 0.8128 (0.8164) time: 0.1441 data: 0.0650 max mem: 9390 +Train: [75] [1500/6250] eta: 0:10:37 lr: 0.000020 grad: 0.1136 (0.1228) loss: 0.8050 (0.8160) time: 0.1567 data: 0.0744 max mem: 9390 +Train: [75] [1600/6250] eta: 0:10:27 lr: 0.000020 grad: 0.1270 (0.1227) loss: 0.8063 (0.8156) time: 0.1644 data: 0.0812 max mem: 9390 +Train: [75] [1700/6250] eta: 0:10:18 lr: 0.000020 grad: 0.1212 (0.1226) loss: 0.8091 (0.8154) time: 0.1497 data: 0.0578 max mem: 9390 +Train: [75] [1800/6250] eta: 0:10:09 lr: 0.000020 grad: 0.1168 (0.1224) loss: 0.8126 (0.8150) time: 0.1701 data: 0.0853 max mem: 9390 +Train: [75] [1900/6250] eta: 0:09:54 lr: 0.000020 grad: 0.1178 (0.1224) loss: 0.8047 (0.8147) time: 0.1323 data: 0.0590 max mem: 9390 +Train: [75] [2000/6250] eta: 0:09:42 lr: 0.000020 grad: 0.1197 (0.1226) loss: 0.8147 (0.8143) time: 0.1399 data: 0.0554 max mem: 9390 +Train: [75] [2100/6250] eta: 0:09:28 lr: 0.000020 grad: 0.1220 (0.1227) loss: 0.8129 (0.8140) time: 0.1488 data: 0.0640 max mem: 9390 +Train: [75] [2200/6250] eta: 0:09:13 lr: 0.000020 grad: 0.1186 (0.1227) loss: 0.8126 (0.8138) time: 0.1379 data: 0.0591 max mem: 9390 +Train: [75] [2300/6250] eta: 0:08:58 lr: 0.000020 grad: 0.1268 (0.1226) loss: 0.8022 (0.8136) time: 0.1338 data: 0.0477 max mem: 9390 +Train: [75] [2400/6250] eta: 0:08:42 lr: 0.000020 grad: 0.1227 (0.1225) loss: 0.8008 (0.8135) time: 0.1205 data: 0.0398 max mem: 9390 +Train: [75] [2500/6250] eta: 0:08:26 lr: 0.000020 grad: 0.1213 (0.1226) loss: 0.8156 (0.8133) time: 0.1208 data: 0.0361 max mem: 9390 +Train: [75] [2600/6250] eta: 0:08:10 lr: 0.000020 grad: 0.1230 (0.1226) loss: 0.8092 (0.8131) time: 0.1138 data: 0.0272 max mem: 9390 +Train: [75] [2700/6250] eta: 0:07:55 lr: 0.000020 grad: 0.1158 (0.1227) loss: 0.8090 (0.8130) time: 0.1256 data: 0.0382 max mem: 9390 +Train: [75] [2800/6250] eta: 0:07:41 lr: 0.000019 grad: 0.1205 (0.1226) loss: 0.8110 (0.8129) time: 0.1248 data: 0.0418 max mem: 9390 +Train: [75] [2900/6250] eta: 0:07:26 lr: 0.000019 grad: 0.1226 (0.1226) loss: 0.8115 (0.8127) time: 0.1113 data: 0.0303 max mem: 9390 +Train: [75] [3000/6250] eta: 0:07:13 lr: 0.000019 grad: 0.1204 (0.1227) loss: 0.8161 (0.8126) time: 0.1373 data: 0.0606 max mem: 9390 +Train: [75] [3100/6250] eta: 0:07:01 lr: 0.000019 grad: 0.1165 (0.1227) loss: 0.8098 (0.8126) time: 0.1650 data: 0.0820 max mem: 9390 +Train: [75] [3200/6250] eta: 0:06:47 lr: 0.000019 grad: 0.1214 (0.1226) loss: 0.8124 (0.8126) time: 0.1352 data: 0.0560 max mem: 9390 +Train: [75] [3300/6250] eta: 0:06:34 lr: 0.000019 grad: 0.1254 (0.1227) loss: 0.8112 (0.8125) time: 0.1288 data: 0.0356 max mem: 9390 +Train: [75] [3400/6250] eta: 0:06:20 lr: 0.000019 grad: 0.1215 (0.1228) loss: 0.8139 (0.8125) time: 0.1332 data: 0.0516 max mem: 9390 +Train: [75] [3500/6250] eta: 0:06:08 lr: 0.000019 grad: 0.1280 (0.1229) loss: 0.8067 (0.8124) time: 0.1655 data: 0.0868 max mem: 9390 +Train: [75] [3600/6250] eta: 0:05:56 lr: 0.000019 grad: 0.1257 (0.1230) loss: 0.8073 (0.8122) time: 0.1477 data: 0.0084 max mem: 9390 +Train: [75] [3700/6250] eta: 0:05:42 lr: 0.000019 grad: 0.1248 (0.1231) loss: 0.8155 (0.8122) time: 0.1360 data: 0.0562 max mem: 9390 +Train: [75] [3800/6250] eta: 0:05:30 lr: 0.000019 grad: 0.1239 (0.1232) loss: 0.8095 (0.8121) time: 0.1546 data: 0.0764 max mem: 9390 +Train: [75] [3900/6250] eta: 0:05:16 lr: 0.000019 grad: 0.1192 (0.1232) loss: 0.8096 (0.8120) time: 0.1382 data: 0.0612 max mem: 9390 +Train: [75] [4000/6250] eta: 0:05:03 lr: 0.000019 grad: 0.1206 (0.1232) loss: 0.8097 (0.8120) time: 0.1403 data: 0.0497 max mem: 9390 +Train: [75] [4100/6250] eta: 0:04:50 lr: 0.000019 grad: 0.1237 (0.1232) loss: 0.8119 (0.8120) time: 0.1343 data: 0.0491 max mem: 9390 +Train: [75] [4200/6250] eta: 0:04:38 lr: 0.000019 grad: 0.1127 (0.1232) loss: 0.8149 (0.8120) time: 0.1349 data: 0.0415 max mem: 9390 +Train: [75] [4300/6250] eta: 0:04:24 lr: 0.000019 grad: 0.1211 (0.1232) loss: 0.8093 (0.8120) time: 0.1383 data: 0.0634 max mem: 9390 +Train: [75] [4400/6250] eta: 0:04:11 lr: 0.000019 grad: 0.1251 (0.1231) loss: 0.8177 (0.8120) time: 0.1165 data: 0.0357 max mem: 9390 +Train: [75] [4500/6250] eta: 0:03:57 lr: 0.000019 grad: 0.1190 (0.1231) loss: 0.8058 (0.8120) time: 0.1183 data: 0.0414 max mem: 9390 +Train: [75] [4600/6250] eta: 0:03:43 lr: 0.000019 grad: 0.1170 (0.1231) loss: 0.8154 (0.8120) time: 0.1100 data: 0.0310 max mem: 9390 +Train: [75] [4700/6250] eta: 0:03:30 lr: 0.000019 grad: 0.1246 (0.1232) loss: 0.8046 (0.8119) time: 0.0997 data: 0.0186 max mem: 9390 +Train: [75] [4800/6250] eta: 0:03:16 lr: 0.000019 grad: 0.1245 (0.1232) loss: 0.8142 (0.8120) time: 0.1108 data: 0.0295 max mem: 9390 +Train: [75] [4900/6250] eta: 0:03:03 lr: 0.000019 grad: 0.1145 (0.1231) loss: 0.8045 (0.8120) time: 0.1313 data: 0.0473 max mem: 9390 +Train: [75] [5000/6250] eta: 0:02:49 lr: 0.000019 grad: 0.1243 (0.1232) loss: 0.8118 (0.8120) time: 0.1403 data: 0.0606 max mem: 9390 +Train: [75] [5100/6250] eta: 0:02:35 lr: 0.000019 grad: 0.1170 (0.1232) loss: 0.8134 (0.8121) time: 0.1235 data: 0.0416 max mem: 9390 +Train: [75] [5200/6250] eta: 0:02:22 lr: 0.000019 grad: 0.1228 (0.1233) loss: 0.8078 (0.8121) time: 0.1400 data: 0.0602 max mem: 9390 +Train: [75] [5300/6250] eta: 0:02:09 lr: 0.000019 grad: 0.1221 (0.1233) loss: 0.8159 (0.8121) time: 0.1747 data: 0.0584 max mem: 9390 +Train: [75] [5400/6250] eta: 0:01:55 lr: 0.000019 grad: 0.1197 (0.1233) loss: 0.8080 (0.8121) time: 0.1385 data: 0.0585 max mem: 9390 +Train: [75] [5500/6250] eta: 0:01:42 lr: 0.000019 grad: 0.1271 (0.1234) loss: 0.8116 (0.8122) time: 0.1334 data: 0.0544 max mem: 9390 +Train: [75] [5600/6250] eta: 0:01:28 lr: 0.000019 grad: 0.1259 (0.1234) loss: 0.8114 (0.8121) time: 0.0898 data: 0.0002 max mem: 9390 +Train: [75] [5700/6250] eta: 0:01:15 lr: 0.000019 grad: 0.1224 (0.1234) loss: 0.8117 (0.8121) time: 0.1116 data: 0.0325 max mem: 9390 +Train: [75] [5800/6250] eta: 0:01:01 lr: 0.000019 grad: 0.1259 (0.1235) loss: 0.8134 (0.8121) time: 0.1359 data: 0.0515 max mem: 9390 +Train: [75] [5900/6250] eta: 0:00:47 lr: 0.000019 grad: 0.1191 (0.1235) loss: 0.8130 (0.8121) time: 0.1422 data: 0.0558 max mem: 9390 +Train: [75] [6000/6250] eta: 0:00:34 lr: 0.000019 grad: 0.1286 (0.1235) loss: 0.8087 (0.8121) time: 0.1307 data: 0.0493 max mem: 9390 +Train: [75] [6100/6250] eta: 0:00:20 lr: 0.000019 grad: 0.1243 (0.1235) loss: 0.8075 (0.8121) time: 0.1565 data: 0.0732 max mem: 9390 +Train: [75] [6200/6250] eta: 0:00:06 lr: 0.000019 grad: 0.1216 (0.1235) loss: 0.8126 (0.8122) time: 0.1522 data: 0.0784 max mem: 9390 +Train: [75] [6249/6250] eta: 0:00:00 lr: 0.000019 grad: 0.1135 (0.1234) loss: 0.8134 (0.8122) time: 0.1468 data: 0.0708 max mem: 9390 +Train: [75] Total time: 0:14:19 (0.1375 s / it) +Averaged stats: lr: 0.000019 grad: 0.1135 (0.1234) loss: 0.8134 (0.8122) +Eval (hcp-train-subset): [75] [ 0/62] eta: 0:05:10 loss: 0.8368 (0.8368) time: 5.0095 data: 4.9796 max mem: 9390 +Eval (hcp-train-subset): [75] [61/62] eta: 0:00:00 loss: 0.8218 (0.8259) time: 0.1119 data: 0.0857 max mem: 9390 +Eval (hcp-train-subset): [75] Total time: 0:00:12 (0.1983 s / it) +Averaged stats (hcp-train-subset): loss: 0.8218 (0.8259) +Eval (hcp-val): [75] [ 0/62] eta: 0:03:40 loss: 0.8298 (0.8298) time: 3.5550 data: 3.4678 max mem: 9390 +Eval (hcp-val): [75] [61/62] eta: 0:00:00 loss: 0.8297 (0.8313) time: 0.1052 data: 0.0801 max mem: 9390 +Eval (hcp-val): [75] Total time: 0:00:11 (0.1931 s / it) +Averaged stats (hcp-val): loss: 0.8297 (0.8313) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +Train: [76] [ 0/6250] eta: 9:11:47 lr: 0.000019 grad: 0.1308 (0.1308) loss: 0.8599 (0.8599) time: 5.2972 data: 5.1232 max mem: 9390 +Train: [76] [ 100/6250] eta: 0:20:21 lr: 0.000019 grad: 0.1579 (0.1636) loss: 0.8166 (0.8255) time: 0.1499 data: 0.0603 max mem: 9390 +Train: [76] [ 200/6250] eta: 0:16:57 lr: 0.000019 grad: 0.1251 (0.1521) loss: 0.8234 (0.8202) time: 0.1385 data: 0.0496 max mem: 9390 +Train: [76] [ 300/6250] eta: 0:15:54 lr: 0.000019 grad: 0.1216 (0.1423) loss: 0.8179 (0.8199) time: 0.1347 data: 0.0541 max mem: 9390 +Train: [76] [ 400/6250] eta: 0:15:03 lr: 0.000019 grad: 0.1115 (0.1365) loss: 0.8079 (0.8181) time: 0.1494 data: 0.0656 max mem: 9390 +Train: [76] [ 500/6250] eta: 0:14:18 lr: 0.000019 grad: 0.1129 (0.1331) loss: 0.8089 (0.8171) time: 0.1306 data: 0.0450 max mem: 9390 +Train: [76] [ 600/6250] eta: 0:13:39 lr: 0.000019 grad: 0.1161 (0.1308) loss: 0.8153 (0.8168) time: 0.1185 data: 0.0362 max mem: 9390 +Train: [76] [ 700/6250] eta: 0:13:09 lr: 0.000019 grad: 0.1149 (0.1294) loss: 0.8173 (0.8163) time: 0.1366 data: 0.0550 max mem: 9390 +Train: [76] [ 800/6250] eta: 0:12:44 lr: 0.000018 grad: 0.1240 (0.1282) loss: 0.8156 (0.8159) time: 0.1271 data: 0.0437 max mem: 9390 +Train: [76] [ 900/6250] eta: 0:12:31 lr: 0.000018 grad: 0.1256 (0.1274) loss: 0.8059 (0.8156) time: 0.1583 data: 0.0768 max mem: 9390 +Train: [76] [1000/6250] eta: 0:12:16 lr: 0.000018 grad: 0.1180 (0.1268) loss: 0.8127 (0.8153) time: 0.1415 data: 0.0604 max mem: 9390 +Train: [76] [1100/6250] eta: 0:11:57 lr: 0.000018 grad: 0.1215 (0.1265) loss: 0.8102 (0.8149) time: 0.1336 data: 0.0552 max mem: 9390 +Train: [76] [1200/6250] eta: 0:11:46 lr: 0.000018 grad: 0.1180 (0.1261) loss: 0.8072 (0.8146) time: 0.1494 data: 0.0689 max mem: 9390 +Train: [76] [1300/6250] eta: 0:11:31 lr: 0.000018 grad: 0.1107 (0.1259) loss: 0.8151 (0.8142) time: 0.1252 data: 0.0434 max mem: 9390 +Train: [76] [1400/6250] eta: 0:11:20 lr: 0.000018 grad: 0.1216 (0.1257) loss: 0.8145 (0.8140) time: 0.1436 data: 0.0612 max mem: 9390 +Train: [76] [1500/6250] eta: 0:11:10 lr: 0.000018 grad: 0.1144 (0.1254) loss: 0.8146 (0.8139) time: 0.1697 data: 0.0908 max mem: 9390 +Train: [76] [1600/6250] eta: 0:10:53 lr: 0.000018 grad: 0.1242 (0.1250) loss: 0.8095 (0.8138) time: 0.1383 data: 0.0420 max mem: 9390 +Train: [76] [1700/6250] eta: 0:10:41 lr: 0.000018 grad: 0.1158 (0.1250) loss: 0.8211 (0.8137) time: 0.1772 data: 0.1036 max mem: 9390 +Train: [76] [1800/6250] eta: 0:10:27 lr: 0.000018 grad: 0.1207 (0.1249) loss: 0.8069 (0.8138) time: 0.1401 data: 0.0663 max mem: 9390 +Train: [76] [1900/6250] eta: 0:10:17 lr: 0.000018 grad: 0.1174 (0.1246) loss: 0.8145 (0.8139) time: 0.1401 data: 0.0562 max mem: 9390 +Train: [76] [2000/6250] eta: 0:10:10 lr: 0.000018 grad: 0.1196 (0.1244) loss: 0.8091 (0.8138) time: 0.2068 data: 0.1120 max mem: 9390 +Train: [76] [2100/6250] eta: 0:10:11 lr: 0.000018 grad: 0.1170 (0.1243) loss: 0.8155 (0.8137) time: 0.1875 data: 0.0448 max mem: 9390 +Train: [76] [2200/6250] eta: 0:10:16 lr: 0.000018 grad: 0.1162 (0.1243) loss: 0.8115 (0.8136) time: 0.3331 data: 0.2452 max mem: 9390 +Train: [76] [2300/6250] eta: 0:10:07 lr: 0.000018 grad: 0.1161 (0.1243) loss: 0.8172 (0.8135) time: 0.2079 data: 0.1041 max mem: 9390 +Train: [76] [2400/6250] eta: 0:10:02 lr: 0.000018 grad: 0.1255 (0.1244) loss: 0.8055 (0.8134) time: 0.2139 data: 0.0668 max mem: 9390 +Train: [76] [2500/6250] eta: 0:10:05 lr: 0.000018 grad: 0.1113 (0.1242) loss: 0.8113 (0.8133) time: 0.2239 data: 0.1425 max mem: 9390 +Train: [76] [2600/6250] eta: 0:10:04 lr: 0.000018 grad: 0.1179 (0.1241) loss: 0.8134 (0.8133) time: 0.4333 data: 0.3185 max mem: 9390 +Train: [76] [2700/6250] eta: 0:09:51 lr: 0.000018 grad: 0.1243 (0.1239) loss: 0.8120 (0.8133) time: 0.2812 data: 0.1958 max mem: 9390 +Train: [76] [2800/6250] eta: 0:09:44 lr: 0.000018 grad: 0.1177 (0.1238) loss: 0.8082 (0.8134) time: 0.2297 data: 0.1310 max mem: 9390 +Train: [76] [2900/6250] eta: 0:09:32 lr: 0.000018 grad: 0.1239 (0.1239) loss: 0.8093 (0.8134) time: 0.2301 data: 0.1424 max mem: 9390 +Train: [76] [3000/6250] eta: 0:09:19 lr: 0.000018 grad: 0.1213 (0.1239) loss: 0.8130 (0.8134) time: 0.2296 data: 0.1172 max mem: 9390 +Train: [76] [3100/6250] eta: 0:09:08 lr: 0.000018 grad: 0.1202 (0.1240) loss: 0.8190 (0.8133) time: 0.3983 data: 0.2719 max mem: 9390 +Train: [76] [3200/6250] eta: 0:08:51 lr: 0.000018 grad: 0.1192 (0.1241) loss: 0.8098 (0.8132) time: 0.1974 data: 0.0522 max mem: 9390 +Train: [76] [3300/6250] eta: 0:08:37 lr: 0.000018 grad: 0.1234 (0.1243) loss: 0.8065 (0.8131) time: 0.1678 data: 0.0792 max mem: 9390 +Train: [76] [3400/6250] eta: 0:08:20 lr: 0.000018 grad: 0.1190 (0.1242) loss: 0.8124 (0.8131) time: 0.1867 data: 0.0896 max mem: 9390 +Train: [76] [3500/6250] eta: 0:08:05 lr: 0.000018 grad: 0.1221 (0.1242) loss: 0.8122 (0.8131) time: 0.1870 data: 0.0830 max mem: 9390 +Train: [76] [3600/6250] eta: 0:07:49 lr: 0.000018 grad: 0.1172 (0.1242) loss: 0.8131 (0.8130) time: 0.1709 data: 0.0676 max mem: 9390 +Train: [76] [3700/6250] eta: 0:07:33 lr: 0.000018 grad: 0.1214 (0.1242) loss: 0.8030 (0.8129) time: 0.2576 data: 0.1588 max mem: 9390 +Train: [76] [3800/6250] eta: 0:07:17 lr: 0.000018 grad: 0.1224 (0.1242) loss: 0.8049 (0.8128) time: 0.3229 data: 0.2204 max mem: 9390 +Train: [76] [3900/6250] eta: 0:07:00 lr: 0.000018 grad: 0.1284 (0.1243) loss: 0.8070 (0.8127) time: 0.2786 data: 0.1782 max mem: 9390 +Train: [76] [4000/6250] eta: 0:06:43 lr: 0.000018 grad: 0.1241 (0.1244) loss: 0.8044 (0.8126) time: 0.3024 data: 0.2134 max mem: 9390 +Train: [76] [4100/6250] eta: 0:06:24 lr: 0.000018 grad: 0.1237 (0.1245) loss: 0.8059 (0.8125) time: 0.1724 data: 0.0786 max mem: 9390 +Train: [76] [4200/6250] eta: 0:06:08 lr: 0.000018 grad: 0.1289 (0.1246) loss: 0.8094 (0.8124) time: 0.1794 data: 0.0709 max mem: 9390 +Train: [76] [4300/6250] eta: 0:05:51 lr: 0.000018 grad: 0.1227 (0.1246) loss: 0.8141 (0.8124) time: 0.2269 data: 0.1263 max mem: 9390 +Train: [76] [4400/6250] eta: 0:05:32 lr: 0.000018 grad: 0.1162 (0.1246) loss: 0.8139 (0.8124) time: 0.1951 data: 0.0990 max mem: 9390 +Train: [76] [4500/6250] eta: 0:05:14 lr: 0.000018 grad: 0.1238 (0.1247) loss: 0.8132 (0.8123) time: 0.1577 data: 0.0503 max mem: 9390 +Train: [76] [4600/6250] eta: 0:04:58 lr: 0.000018 grad: 0.1239 (0.1247) loss: 0.8074 (0.8123) time: 0.3200 data: 0.2150 max mem: 9390 +Train: [76] [4700/6250] eta: 0:04:39 lr: 0.000018 grad: 0.1216 (0.1246) loss: 0.8114 (0.8123) time: 0.1357 data: 0.0223 max mem: 9390 +Train: [76] [4800/6250] eta: 0:04:21 lr: 0.000018 grad: 0.1178 (0.1246) loss: 0.8146 (0.8124) time: 0.1995 data: 0.1195 max mem: 9390 +Train: [76] [4900/6250] eta: 0:04:03 lr: 0.000018 grad: 0.1250 (0.1247) loss: 0.8102 (0.8123) time: 0.1682 data: 0.0737 max mem: 9390 +Train: [76] [5000/6250] eta: 0:03:45 lr: 0.000018 grad: 0.1270 (0.1248) loss: 0.8102 (0.8123) time: 0.1926 data: 0.0798 max mem: 9390 +Train: [76] [5100/6250] eta: 0:03:28 lr: 0.000017 grad: 0.1231 (0.1248) loss: 0.8077 (0.8123) time: 0.2822 data: 0.1733 max mem: 9390 +Train: [76] [5200/6250] eta: 0:03:10 lr: 0.000017 grad: 0.1254 (0.1248) loss: 0.8147 (0.8122) time: 0.1727 data: 0.0823 max mem: 9390 +Train: [76] [5300/6250] eta: 0:02:52 lr: 0.000017 grad: 0.1200 (0.1248) loss: 0.8051 (0.8122) time: 0.1828 data: 0.0744 max mem: 9390 +Train: [76] [5400/6250] eta: 0:02:34 lr: 0.000017 grad: 0.1283 (0.1248) loss: 0.8148 (0.8122) time: 0.1748 data: 0.0857 max mem: 9390 +Train: [76] [5500/6250] eta: 0:02:16 lr: 0.000017 grad: 0.1258 (0.1248) loss: 0.8104 (0.8122) time: 0.1752 data: 0.0809 max mem: 9390 +Train: [76] [5600/6250] eta: 0:01:57 lr: 0.000017 grad: 0.1226 (0.1248) loss: 0.8132 (0.8122) time: 0.1450 data: 0.0516 max mem: 9390 +Train: [76] [5700/6250] eta: 0:01:39 lr: 0.000017 grad: 0.1279 (0.1249) loss: 0.8139 (0.8122) time: 0.1846 data: 0.0833 max mem: 9390 +Train: [76] [5800/6250] eta: 0:01:21 lr: 0.000017 grad: 0.1201 (0.1249) loss: 0.8133 (0.8121) time: 0.1744 data: 0.0891 max mem: 9390 +Train: [76] [5900/6250] eta: 0:01:03 lr: 0.000017 grad: 0.1161 (0.1249) loss: 0.8171 (0.8121) time: 0.1734 data: 0.0862 max mem: 9390 +Train: [76] [6000/6250] eta: 0:00:45 lr: 0.000017 grad: 0.1223 (0.1249) loss: 0.8120 (0.8121) time: 0.1757 data: 0.0774 max mem: 9390 +Train: [76] [6100/6250] eta: 0:00:27 lr: 0.000017 grad: 0.1200 (0.1249) loss: 0.8130 (0.8121) time: 0.1466 data: 0.0589 max mem: 9390 +Train: [76] [6200/6250] eta: 0:00:09 lr: 0.000017 grad: 0.1272 (0.1249) loss: 0.8128 (0.8121) time: 0.1790 data: 0.0962 max mem: 9390 +Train: [76] [6249/6250] eta: 0:00:00 lr: 0.000017 grad: 0.1150 (0.1249) loss: 0.8165 (0.8121) time: 0.2089 data: 0.1170 max mem: 9390 +Train: [76] Total time: 0:18:53 (0.1813 s / it) +Averaged stats: lr: 0.000017 grad: 0.1150 (0.1249) loss: 0.8165 (0.8121) +Eval (hcp-train-subset): [76] [ 0/62] eta: 0:04:44 loss: 0.8362 (0.8362) time: 4.5846 data: 4.5157 max mem: 9390 +Eval (hcp-train-subset): [76] [61/62] eta: 0:00:00 loss: 0.8217 (0.8254) time: 0.1482 data: 0.1232 max mem: 9390 +Eval (hcp-train-subset): [76] Total time: 0:00:15 (0.2543 s / it) +Averaged stats (hcp-train-subset): loss: 0.8217 (0.8254) +Eval (hcp-val): [76] [ 0/62] eta: 0:05:04 loss: 0.8238 (0.8238) time: 4.9169 data: 4.8620 max mem: 9390 +Eval (hcp-val): [76] [61/62] eta: 0:00:00 loss: 0.8300 (0.8305) time: 0.1223 data: 0.0949 max mem: 9390 +Eval (hcp-val): [76] Total time: 0:00:16 (0.2726 s / it) +Averaged stats (hcp-val): loss: 0.8300 (0.8305) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +Train: [77] [ 0/6250] eta: 10:45:36 lr: 0.000017 grad: 0.1527 (0.1527) loss: 0.8327 (0.8327) time: 6.1978 data: 5.9480 max mem: 9390 +Train: [77] [ 100/6250] eta: 0:24:46 lr: 0.000017 grad: 0.1327 (0.1423) loss: 0.8134 (0.8258) time: 0.1835 data: 0.0696 max mem: 9390 +Train: [77] [ 200/6250] eta: 0:21:13 lr: 0.000017 grad: 0.1459 (0.1445) loss: 0.8077 (0.8160) time: 0.1763 data: 0.0621 max mem: 9390 +Train: [77] [ 300/6250] eta: 0:20:09 lr: 0.000017 grad: 0.1221 (0.1417) loss: 0.8130 (0.8127) time: 0.1939 data: 0.0889 max mem: 9390 +Train: [77] [ 400/6250] eta: 0:19:08 lr: 0.000017 grad: 0.1348 (0.1395) loss: 0.8076 (0.8120) time: 0.1304 data: 0.0181 max mem: 9390 +Train: [77] [ 500/6250] eta: 0:18:31 lr: 0.000017 grad: 0.1181 (0.1381) loss: 0.8185 (0.8120) time: 0.1671 data: 0.0714 max mem: 9390 +Train: [77] [ 600/6250] eta: 0:17:47 lr: 0.000017 grad: 0.1200 (0.1372) loss: 0.8177 (0.8118) time: 0.1780 data: 0.0794 max mem: 9390 +Train: [77] [ 700/6250] eta: 0:17:31 lr: 0.000017 grad: 0.1232 (0.1359) loss: 0.8161 (0.8119) time: 0.2493 data: 0.1367 max mem: 9390 +Train: [77] [ 800/6250] eta: 0:17:44 lr: 0.000017 grad: 0.1281 (0.1350) loss: 0.8152 (0.8123) time: 0.2506 data: 0.1241 max mem: 9390 +Train: [77] [ 900/6250] eta: 0:17:29 lr: 0.000017 grad: 0.1284 (0.1343) loss: 0.8124 (0.8124) time: 0.1878 data: 0.0935 max mem: 9390 +Train: [77] [1000/6250] eta: 0:17:01 lr: 0.000017 grad: 0.1208 (0.1340) loss: 0.8096 (0.8123) time: 0.1721 data: 0.0861 max mem: 9390 +Train: [77] [1100/6250] eta: 0:16:40 lr: 0.000017 grad: 0.1203 (0.1333) loss: 0.8100 (0.8123) time: 0.1491 data: 0.0588 max mem: 9390 +Train: [77] [1200/6250] eta: 0:16:18 lr: 0.000017 grad: 0.1315 (0.1330) loss: 0.8058 (0.8119) time: 0.2724 data: 0.1216 max mem: 9390 +Train: [77] [1300/6250] eta: 0:15:50 lr: 0.000017 grad: 0.1283 (0.1328) loss: 0.8069 (0.8114) time: 0.1254 data: 0.0318 max mem: 9390 +Train: [77] [1400/6250] eta: 0:15:30 lr: 0.000017 grad: 0.1268 (0.1325) loss: 0.8127 (0.8111) time: 0.1631 data: 0.0800 max mem: 9390 +Train: [77] [1500/6250] eta: 0:15:06 lr: 0.000017 grad: 0.1226 (0.1323) loss: 0.8088 (0.8109) time: 0.1604 data: 0.0771 max mem: 9390 +Train: [77] [1600/6250] eta: 0:14:45 lr: 0.000017 grad: 0.1225 (0.1320) loss: 0.8066 (0.8106) time: 0.1670 data: 0.0802 max mem: 9390 +Train: [77] [1700/6250] eta: 0:14:32 lr: 0.000017 grad: 0.1311 (0.1320) loss: 0.7979 (0.8105) time: 0.1869 data: 0.0985 max mem: 9390 +Train: [77] [1800/6250] eta: 0:14:12 lr: 0.000017 grad: 0.1299 (0.1319) loss: 0.7988 (0.8102) time: 0.1658 data: 0.0770 max mem: 9390 +Train: [77] [1900/6250] eta: 0:13:49 lr: 0.000017 grad: 0.1304 (0.1320) loss: 0.8020 (0.8100) time: 0.1744 data: 0.0885 max mem: 9390 +Train: [77] [2000/6250] eta: 0:13:26 lr: 0.000017 grad: 0.1224 (0.1320) loss: 0.8054 (0.8099) time: 0.1807 data: 0.0882 max mem: 9390 +Train: [77] [2100/6250] eta: 0:13:04 lr: 0.000017 grad: 0.1233 (0.1319) loss: 0.8058 (0.8098) time: 0.1894 data: 0.0949 max mem: 9390 +Train: [77] [2200/6250] eta: 0:12:41 lr: 0.000017 grad: 0.1358 (0.1321) loss: 0.8112 (0.8097) time: 0.1732 data: 0.0723 max mem: 9390 +Train: [77] [2300/6250] eta: 0:12:19 lr: 0.000017 grad: 0.1346 (0.1322) loss: 0.8054 (0.8095) time: 0.1736 data: 0.0752 max mem: 9390 +Train: [77] [2400/6250] eta: 0:12:01 lr: 0.000017 grad: 0.1245 (0.1323) loss: 0.8133 (0.8095) time: 0.2111 data: 0.1097 max mem: 9390 +Train: [77] [2500/6250] eta: 0:11:43 lr: 0.000017 grad: 0.1389 (0.1323) loss: 0.8030 (0.8094) time: 0.1917 data: 0.0958 max mem: 9390 +Train: [77] [2600/6250] eta: 0:11:26 lr: 0.000017 grad: 0.1222 (0.1323) loss: 0.8110 (0.8094) time: 0.1673 data: 0.0502 max mem: 9390 +Train: [77] [2700/6250] eta: 0:11:11 lr: 0.000017 grad: 0.1293 (0.1324) loss: 0.8035 (0.8094) time: 0.2490 data: 0.1504 max mem: 9390 +Train: [77] [2800/6250] eta: 0:10:58 lr: 0.000017 grad: 0.1274 (0.1324) loss: 0.8124 (0.8094) time: 0.2687 data: 0.1030 max mem: 9390 +Train: [77] [2900/6250] eta: 0:10:54 lr: 0.000017 grad: 0.1290 (0.1324) loss: 0.8120 (0.8094) time: 0.4630 data: 0.3312 max mem: 9390 +Train: [77] [3000/6250] eta: 0:10:34 lr: 0.000017 grad: 0.1281 (0.1324) loss: 0.8116 (0.8094) time: 0.3311 data: 0.2041 max mem: 9390 +Train: [77] [3100/6250] eta: 0:10:14 lr: 0.000017 grad: 0.1241 (0.1324) loss: 0.8082 (0.8093) time: 0.2509 data: 0.1667 max mem: 9390 +Train: [77] [3200/6250] eta: 0:09:58 lr: 0.000017 grad: 0.1289 (0.1324) loss: 0.8061 (0.8093) time: 0.4196 data: 0.2734 max mem: 9390 +Train: [77] [3300/6250] eta: 0:09:38 lr: 0.000016 grad: 0.1244 (0.1323) loss: 0.8005 (0.8092) time: 0.1734 data: 0.0560 max mem: 9390 +Train: [77] [3400/6250] eta: 0:09:17 lr: 0.000016 grad: 0.1205 (0.1321) loss: 0.8116 (0.8092) time: 0.1695 data: 0.0605 max mem: 9390 +Train: [77] [3500/6250] eta: 0:08:59 lr: 0.000016 grad: 0.1275 (0.1319) loss: 0.8061 (0.8092) time: 0.3251 data: 0.1948 max mem: 9390 +Train: [77] [3600/6250] eta: 0:08:37 lr: 0.000016 grad: 0.1250 (0.1317) loss: 0.8049 (0.8093) time: 0.1618 data: 0.0666 max mem: 9390 +Train: [77] [3700/6250] eta: 0:08:16 lr: 0.000016 grad: 0.1237 (0.1316) loss: 0.8123 (0.8093) time: 0.1760 data: 0.0899 max mem: 9390 +Train: [77] [3800/6250] eta: 0:07:58 lr: 0.000016 grad: 0.1227 (0.1314) loss: 0.8097 (0.8094) time: 0.2738 data: 0.1500 max mem: 9390 +Train: [77] [3900/6250] eta: 0:07:37 lr: 0.000016 grad: 0.1184 (0.1312) loss: 0.8142 (0.8094) time: 0.1323 data: 0.0229 max mem: 9390 +Train: [77] [4000/6250] eta: 0:07:18 lr: 0.000016 grad: 0.1246 (0.1311) loss: 0.8097 (0.8094) time: 0.1675 data: 0.0542 max mem: 9390 +Train: [77] [4100/6250] eta: 0:07:01 lr: 0.000016 grad: 0.1235 (0.1310) loss: 0.8049 (0.8095) time: 0.4059 data: 0.2709 max mem: 9390 +Train: [77] [4200/6250] eta: 0:06:41 lr: 0.000016 grad: 0.1234 (0.1308) loss: 0.8138 (0.8096) time: 0.1660 data: 0.0801 max mem: 9390 +Train: [77] [4300/6250] eta: 0:06:20 lr: 0.000016 grad: 0.1167 (0.1306) loss: 0.8203 (0.8097) time: 0.1864 data: 0.0949 max mem: 9390 +Train: [77] [4400/6250] eta: 0:06:01 lr: 0.000016 grad: 0.1225 (0.1305) loss: 0.8191 (0.8098) time: 0.1507 data: 0.0387 max mem: 9390 +Train: [77] [4500/6250] eta: 0:05:42 lr: 0.000016 grad: 0.1265 (0.1304) loss: 0.8106 (0.8099) time: 0.3166 data: 0.0896 max mem: 9390 +Train: [77] [4600/6250] eta: 0:05:22 lr: 0.000016 grad: 0.1247 (0.1304) loss: 0.8189 (0.8100) time: 0.1841 data: 0.0939 max mem: 9390 +Train: [77] [4700/6250] eta: 0:05:03 lr: 0.000016 grad: 0.1357 (0.1303) loss: 0.8146 (0.8100) time: 0.1756 data: 0.0509 max mem: 9390 +Train: [77] [4800/6250] eta: 0:04:43 lr: 0.000016 grad: 0.1222 (0.1303) loss: 0.8123 (0.8100) time: 0.1319 data: 0.0340 max mem: 9390 +Train: [77] [4900/6250] eta: 0:04:23 lr: 0.000016 grad: 0.1196 (0.1303) loss: 0.8194 (0.8101) time: 0.1888 data: 0.0953 max mem: 9390 +Train: [77] [5000/6250] eta: 0:04:03 lr: 0.000016 grad: 0.1211 (0.1301) loss: 0.8175 (0.8101) time: 0.1923 data: 0.0836 max mem: 9390 +Train: [77] [5100/6250] eta: 0:03:43 lr: 0.000016 grad: 0.1207 (0.1301) loss: 0.8093 (0.8102) time: 0.1870 data: 0.0870 max mem: 9390 +Train: [77] [5200/6250] eta: 0:03:24 lr: 0.000016 grad: 0.1246 (0.1301) loss: 0.8089 (0.8102) time: 0.2081 data: 0.0784 max mem: 9390 +Train: [77] [5300/6250] eta: 0:03:05 lr: 0.000016 grad: 0.1195 (0.1300) loss: 0.8094 (0.8102) time: 0.1244 data: 0.0286 max mem: 9390 +Train: [77] [5400/6250] eta: 0:02:45 lr: 0.000016 grad: 0.1278 (0.1300) loss: 0.8140 (0.8102) time: 0.1592 data: 0.0618 max mem: 9390 +Train: [77] [5500/6250] eta: 0:02:25 lr: 0.000016 grad: 0.1223 (0.1299) loss: 0.8134 (0.8102) time: 0.1709 data: 0.0828 max mem: 9390 +Train: [77] [5600/6250] eta: 0:02:06 lr: 0.000016 grad: 0.1239 (0.1299) loss: 0.8137 (0.8102) time: 0.1104 data: 0.0002 max mem: 9390 +Train: [77] [5700/6250] eta: 0:01:46 lr: 0.000016 grad: 0.1332 (0.1300) loss: 0.8113 (0.8102) time: 0.1660 data: 0.0797 max mem: 9390 +Train: [77] [5800/6250] eta: 0:01:27 lr: 0.000016 grad: 0.1241 (0.1299) loss: 0.8061 (0.8103) time: 0.2194 data: 0.1319 max mem: 9390 +Train: [77] [5900/6250] eta: 0:01:07 lr: 0.000016 grad: 0.1306 (0.1299) loss: 0.8127 (0.8103) time: 0.2156 data: 0.1311 max mem: 9390 +Train: [77] [6000/6250] eta: 0:00:48 lr: 0.000016 grad: 0.1218 (0.1300) loss: 0.8050 (0.8102) time: 0.3105 data: 0.2016 max mem: 9390 +Train: [77] [6100/6250] eta: 0:00:28 lr: 0.000016 grad: 0.1247 (0.1300) loss: 0.8143 (0.8102) time: 0.1767 data: 0.0920 max mem: 9390 +Train: [77] [6200/6250] eta: 0:00:09 lr: 0.000016 grad: 0.1193 (0.1299) loss: 0.8103 (0.8102) time: 0.1881 data: 0.0962 max mem: 9390 +Train: [77] [6249/6250] eta: 0:00:00 lr: 0.000016 grad: 0.1218 (0.1299) loss: 0.8104 (0.8102) time: 0.1811 data: 0.0965 max mem: 9390 +Train: [77] Total time: 0:20:12 (0.1941 s / it) +Averaged stats: lr: 0.000016 grad: 0.1218 (0.1299) loss: 0.8104 (0.8102) +Eval (hcp-train-subset): [77] [ 0/62] eta: 0:03:50 loss: 0.8341 (0.8341) time: 3.7157 data: 3.6479 max mem: 9390 +Eval (hcp-train-subset): [77] [61/62] eta: 0:00:00 loss: 0.8222 (0.8240) time: 0.1369 data: 0.1100 max mem: 9390 +Eval (hcp-train-subset): [77] Total time: 0:00:14 (0.2357 s / it) +Averaged stats (hcp-train-subset): loss: 0.8222 (0.8240) +Eval (hcp-val): [77] [ 0/62] eta: 0:05:49 loss: 0.8280 (0.8280) time: 5.6417 data: 5.6057 max mem: 9390 +Eval (hcp-val): [77] [61/62] eta: 0:00:00 loss: 0.8299 (0.8306) time: 0.1688 data: 0.1426 max mem: 9390 +Eval (hcp-val): [77] Total time: 0:00:16 (0.2731 s / it) +Averaged stats (hcp-val): loss: 0.8299 (0.8306) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +Train: [78] [ 0/6250] eta: 10:09:24 lr: 0.000016 grad: 0.0771 (0.0771) loss: 0.8483 (0.8483) time: 5.8504 data: 5.3462 max mem: 9390 +Train: [78] [ 100/6250] eta: 0:35:07 lr: 0.000016 grad: 0.1385 (0.1723) loss: 0.8203 (0.8150) time: 0.2855 data: 0.1238 max mem: 9390 +Train: [78] [ 200/6250] eta: 0:30:23 lr: 0.000016 grad: 0.1264 (0.1568) loss: 0.8178 (0.8139) time: 0.3408 data: 0.2117 max mem: 9390 +Train: [78] [ 300/6250] eta: 0:26:03 lr: 0.000016 grad: 0.1317 (0.1526) loss: 0.8177 (0.8114) time: 0.1817 data: 0.0797 max mem: 9390 +Train: [78] [ 400/6250] eta: 0:24:23 lr: 0.000016 grad: 0.1199 (0.1475) loss: 0.8180 (0.8121) time: 0.2341 data: 0.1187 max mem: 9390 +Train: [78] [ 500/6250] eta: 0:23:22 lr: 0.000016 grad: 0.1339 (0.1441) loss: 0.8050 (0.8119) time: 0.3446 data: 0.2488 max mem: 9390 +Train: [78] [ 600/6250] eta: 0:21:51 lr: 0.000016 grad: 0.1189 (0.1411) loss: 0.8134 (0.8119) time: 0.1872 data: 0.0969 max mem: 9390 +Train: [78] [ 700/6250] eta: 0:21:45 lr: 0.000016 grad: 0.1338 (0.1400) loss: 0.8030 (0.8118) time: 0.1062 data: 0.0002 max mem: 9390 +Train: [78] [ 800/6250] eta: 0:21:03 lr: 0.000016 grad: 0.1313 (0.1390) loss: 0.8114 (0.8114) time: 0.1963 data: 0.0977 max mem: 9390 +Train: [78] [ 900/6250] eta: 0:21:22 lr: 0.000016 grad: 0.1243 (0.1377) loss: 0.8159 (0.8114) time: 0.1361 data: 0.0209 max mem: 9390 +Train: [78] [1000/6250] eta: 0:20:33 lr: 0.000016 grad: 0.1276 (0.1368) loss: 0.8120 (0.8115) time: 0.1977 data: 0.0883 max mem: 9390 +Train: [78] [1100/6250] eta: 0:19:43 lr: 0.000016 grad: 0.1143 (0.1355) loss: 0.8148 (0.8119) time: 0.1698 data: 0.0627 max mem: 9390 +Train: [78] [1200/6250] eta: 0:18:57 lr: 0.000016 grad: 0.1228 (0.1345) loss: 0.8188 (0.8123) time: 0.1728 data: 0.0962 max mem: 9390 +Train: [78] [1300/6250] eta: 0:18:16 lr: 0.000016 grad: 0.1215 (0.1335) loss: 0.8218 (0.8126) time: 0.1811 data: 0.0957 max mem: 9390 +Train: [78] [1400/6250] eta: 0:17:38 lr: 0.000016 grad: 0.1203 (0.1328) loss: 0.8171 (0.8128) time: 0.1515 data: 0.0678 max mem: 9390 +Train: [78] [1500/6250] eta: 0:17:12 lr: 0.000015 grad: 0.1147 (0.1320) loss: 0.8199 (0.8130) time: 0.1886 data: 0.0940 max mem: 9390 +Train: [78] [1600/6250] eta: 0:16:42 lr: 0.000015 grad: 0.1180 (0.1313) loss: 0.8184 (0.8133) time: 0.2069 data: 0.1237 max mem: 9390 +Train: [78] [1700/6250] eta: 0:16:14 lr: 0.000015 grad: 0.1154 (0.1307) loss: 0.8140 (0.8135) time: 0.2225 data: 0.1382 max mem: 9390 +Train: [78] [1800/6250] eta: 0:15:50 lr: 0.000015 grad: 0.1181 (0.1303) loss: 0.8151 (0.8136) time: 0.1943 data: 0.1010 max mem: 9390 +Train: [78] [1900/6250] eta: 0:15:18 lr: 0.000015 grad: 0.1195 (0.1298) loss: 0.8173 (0.8138) time: 0.1534 data: 0.0692 max mem: 9390 +Train: [78] [2000/6250] eta: 0:14:47 lr: 0.000015 grad: 0.1209 (0.1293) loss: 0.8132 (0.8140) time: 0.1884 data: 0.0861 max mem: 9390 +Train: [78] [2100/6250] eta: 0:14:22 lr: 0.000015 grad: 0.1264 (0.1290) loss: 0.8163 (0.8142) time: 0.1668 data: 0.0688 max mem: 9390 +Train: [78] [2200/6250] eta: 0:13:56 lr: 0.000015 grad: 0.1172 (0.1287) loss: 0.8186 (0.8143) time: 0.1569 data: 0.0526 max mem: 9390 +Train: [78] [2300/6250] eta: 0:13:37 lr: 0.000015 grad: 0.1177 (0.1285) loss: 0.8175 (0.8143) time: 0.2238 data: 0.1112 max mem: 9390 +Train: [78] [2400/6250] eta: 0:13:14 lr: 0.000015 grad: 0.1113 (0.1283) loss: 0.8188 (0.8144) time: 0.1899 data: 0.1007 max mem: 9390 +Train: [78] [2500/6250] eta: 0:12:53 lr: 0.000015 grad: 0.1188 (0.1281) loss: 0.8158 (0.8145) time: 0.2502 data: 0.1214 max mem: 9390 +Train: [78] [2600/6250] eta: 0:12:38 lr: 0.000015 grad: 0.1191 (0.1280) loss: 0.8171 (0.8145) time: 0.2868 data: 0.1698 max mem: 9390 +Train: [78] [2700/6250] eta: 0:12:21 lr: 0.000015 grad: 0.1167 (0.1278) loss: 0.8166 (0.8147) time: 0.2515 data: 0.1477 max mem: 9390 +Train: [78] [2800/6250] eta: 0:12:00 lr: 0.000015 grad: 0.1268 (0.1276) loss: 0.8085 (0.8147) time: 0.1565 data: 0.0408 max mem: 9390 +Train: [78] [2900/6250] eta: 0:11:38 lr: 0.000015 grad: 0.1199 (0.1275) loss: 0.8183 (0.8147) time: 0.1896 data: 0.0310 max mem: 9390 +Train: [78] [3000/6250] eta: 0:11:21 lr: 0.000015 grad: 0.1231 (0.1275) loss: 0.8095 (0.8146) time: 0.1282 data: 0.0003 max mem: 9390 +Train: [78] [3100/6250] eta: 0:10:57 lr: 0.000015 grad: 0.1220 (0.1275) loss: 0.8118 (0.8145) time: 0.1707 data: 0.0608 max mem: 9390 +Train: [78] [3200/6250] eta: 0:10:36 lr: 0.000015 grad: 0.1216 (0.1274) loss: 0.8125 (0.8145) time: 0.1555 data: 0.0004 max mem: 9390 +Train: [78] [3300/6250] eta: 0:10:17 lr: 0.000015 grad: 0.1202 (0.1274) loss: 0.8201 (0.8145) time: 0.2033 data: 0.1050 max mem: 9390 +Train: [78] [3400/6250] eta: 0:09:53 lr: 0.000015 grad: 0.1184 (0.1274) loss: 0.8113 (0.8144) time: 0.1481 data: 0.0284 max mem: 9390 +Train: [78] [3500/6250] eta: 0:09:33 lr: 0.000015 grad: 0.1220 (0.1275) loss: 0.8120 (0.8143) time: 0.1217 data: 0.0113 max mem: 9390 +Train: [78] [3600/6250] eta: 0:09:10 lr: 0.000015 grad: 0.1263 (0.1275) loss: 0.8146 (0.8143) time: 0.1924 data: 0.0934 max mem: 9390 +Train: [78] [3700/6250] eta: 0:08:50 lr: 0.000015 grad: 0.1277 (0.1275) loss: 0.8157 (0.8143) time: 0.2876 data: 0.1814 max mem: 9390 +Train: [78] [3800/6250] eta: 0:08:29 lr: 0.000015 grad: 0.1196 (0.1275) loss: 0.8074 (0.8142) time: 0.1165 data: 0.0107 max mem: 9390 +Train: [78] [3900/6250] eta: 0:08:08 lr: 0.000015 grad: 0.1321 (0.1276) loss: 0.8078 (0.8142) time: 0.3104 data: 0.1883 max mem: 9390 +Train: [78] [4000/6250] eta: 0:07:47 lr: 0.000015 grad: 0.1299 (0.1277) loss: 0.8114 (0.8141) time: 0.1894 data: 0.0376 max mem: 9390 +Train: [78] [4100/6250] eta: 0:07:25 lr: 0.000015 grad: 0.1261 (0.1277) loss: 0.8080 (0.8140) time: 0.1588 data: 0.0579 max mem: 9390 +Train: [78] [4200/6250] eta: 0:07:02 lr: 0.000015 grad: 0.1292 (0.1279) loss: 0.8098 (0.8138) time: 0.1680 data: 0.0799 max mem: 9390 +Train: [78] [4300/6250] eta: 0:06:42 lr: 0.000015 grad: 0.1194 (0.1279) loss: 0.8055 (0.8138) time: 0.2598 data: 0.1268 max mem: 9390 +Train: [78] [4400/6250] eta: 0:06:21 lr: 0.000015 grad: 0.1293 (0.1278) loss: 0.8139 (0.8137) time: 0.2043 data: 0.1133 max mem: 9390 +Train: [78] [4500/6250] eta: 0:05:59 lr: 0.000015 grad: 0.1157 (0.1278) loss: 0.8112 (0.8137) time: 0.1795 data: 0.0732 max mem: 9390 +Train: [78] [4600/6250] eta: 0:05:38 lr: 0.000015 grad: 0.1281 (0.1278) loss: 0.8048 (0.8136) time: 0.1666 data: 0.0708 max mem: 9390 +Train: [78] [4700/6250] eta: 0:05:18 lr: 0.000015 grad: 0.1300 (0.1278) loss: 0.8103 (0.8136) time: 0.2575 data: 0.1692 max mem: 9390 +Train: [78] [4800/6250] eta: 0:04:56 lr: 0.000015 grad: 0.1265 (0.1279) loss: 0.8018 (0.8135) time: 0.1797 data: 0.0910 max mem: 9390 +Train: [78] [4900/6250] eta: 0:04:35 lr: 0.000015 grad: 0.1238 (0.1280) loss: 0.8077 (0.8133) time: 0.1987 data: 0.0761 max mem: 9390 +Train: [78] [5000/6250] eta: 0:04:14 lr: 0.000015 grad: 0.1302 (0.1280) loss: 0.8051 (0.8133) time: 0.1830 data: 0.0900 max mem: 9390 +Train: [78] [5100/6250] eta: 0:03:54 lr: 0.000015 grad: 0.1238 (0.1281) loss: 0.8091 (0.8132) time: 0.3005 data: 0.1616 max mem: 9390 +Train: [78] [5200/6250] eta: 0:03:33 lr: 0.000015 grad: 0.1278 (0.1281) loss: 0.8105 (0.8131) time: 0.1613 data: 0.0604 max mem: 9390 +Train: [78] [5300/6250] eta: 0:03:12 lr: 0.000015 grad: 0.1231 (0.1281) loss: 0.8169 (0.8131) time: 0.2222 data: 0.1266 max mem: 9390 +Train: [78] [5400/6250] eta: 0:02:51 lr: 0.000015 grad: 0.1248 (0.1281) loss: 0.8168 (0.8130) time: 0.2219 data: 0.1202 max mem: 9390 +Train: [78] [5500/6250] eta: 0:02:31 lr: 0.000015 grad: 0.1200 (0.1281) loss: 0.8124 (0.8130) time: 0.1460 data: 0.0409 max mem: 9390 +Train: [78] [5600/6250] eta: 0:02:11 lr: 0.000015 grad: 0.1189 (0.1280) loss: 0.8175 (0.8130) time: 0.2066 data: 0.1077 max mem: 9390 +Train: [78] [5700/6250] eta: 0:01:51 lr: 0.000015 grad: 0.1197 (0.1280) loss: 0.8091 (0.8131) time: 0.1615 data: 0.0589 max mem: 9390 +Train: [78] [5800/6250] eta: 0:01:30 lr: 0.000015 grad: 0.1227 (0.1280) loss: 0.8109 (0.8131) time: 0.1964 data: 0.1115 max mem: 9390 +Train: [78] [5900/6250] eta: 0:01:10 lr: 0.000015 grad: 0.1262 (0.1280) loss: 0.8145 (0.8131) time: 0.1531 data: 0.0700 max mem: 9390 +Train: [78] [6000/6250] eta: 0:00:50 lr: 0.000015 grad: 0.1241 (0.1280) loss: 0.8131 (0.8131) time: 0.1754 data: 0.0817 max mem: 9390 +Train: [78] [6100/6250] eta: 0:00:30 lr: 0.000015 grad: 0.1204 (0.1279) loss: 0.8077 (0.8131) time: 0.2009 data: 0.1152 max mem: 9390 +Train: [78] [6200/6250] eta: 0:00:10 lr: 0.000014 grad: 0.1243 (0.1279) loss: 0.8175 (0.8131) time: 0.2161 data: 0.0998 max mem: 9390 +Train: [78] [6249/6250] eta: 0:00:00 lr: 0.000014 grad: 0.1263 (0.1279) loss: 0.8054 (0.8131) time: 0.2046 data: 0.0943 max mem: 9390 +Train: [78] Total time: 0:20:57 (0.2012 s / it) +Averaged stats: lr: 0.000014 grad: 0.1263 (0.1279) loss: 0.8054 (0.8131) +Eval (hcp-train-subset): [78] [ 0/62] eta: 0:06:05 loss: 0.8313 (0.8313) time: 5.8997 data: 5.8674 max mem: 9390 +Eval (hcp-train-subset): [78] [61/62] eta: 0:00:00 loss: 0.8228 (0.8244) time: 0.1057 data: 0.0800 max mem: 9390 +Eval (hcp-train-subset): [78] Total time: 0:00:15 (0.2575 s / it) +Averaged stats (hcp-train-subset): loss: 0.8228 (0.8244) +Eval (hcp-val): [78] [ 0/62] eta: 0:06:33 loss: 0.8235 (0.8235) time: 6.3524 data: 6.3214 max mem: 9390 +Eval (hcp-val): [78] [61/62] eta: 0:00:00 loss: 0.8298 (0.8310) time: 0.1415 data: 0.1154 max mem: 9390 +Eval (hcp-val): [78] Total time: 0:00:15 (0.2447 s / it) +Averaged stats (hcp-val): loss: 0.8298 (0.8310) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +Train: [79] [ 0/6250] eta: 11:32:56 lr: 0.000014 grad: 0.2374 (0.2374) loss: 0.8602 (0.8602) time: 6.6522 data: 6.4301 max mem: 9390 +Train: [79] [ 100/6250] eta: 0:27:51 lr: 0.000014 grad: 0.1475 (0.1533) loss: 0.8295 (0.8288) time: 0.2235 data: 0.1101 max mem: 9390 +Train: [79] [ 200/6250] eta: 0:24:12 lr: 0.000014 grad: 0.1245 (0.1416) loss: 0.8292 (0.8258) time: 0.1851 data: 0.0322 max mem: 9390 +Train: [79] [ 300/6250] eta: 0:22:16 lr: 0.000014 grad: 0.1188 (0.1401) loss: 0.8098 (0.8226) time: 0.2209 data: 0.0833 max mem: 9390 +Train: [79] [ 400/6250] eta: 0:22:42 lr: 0.000014 grad: 0.1342 (0.1379) loss: 0.8176 (0.8209) time: 0.2139 data: 0.0802 max mem: 9390 +Train: [79] [ 500/6250] eta: 0:22:40 lr: 0.000014 grad: 0.1239 (0.1374) loss: 0.8137 (0.8193) time: 0.1153 data: 0.0003 max mem: 9390 +Train: [79] [ 600/6250] eta: 0:22:31 lr: 0.000014 grad: 0.1177 (0.1363) loss: 0.8202 (0.8182) time: 0.2525 data: 0.1254 max mem: 9390 +Train: [79] [ 700/6250] eta: 0:22:23 lr: 0.000014 grad: 0.1161 (0.1352) loss: 0.8108 (0.8175) time: 0.1573 data: 0.0404 max mem: 9390 +Train: [79] [ 800/6250] eta: 0:22:12 lr: 0.000014 grad: 0.1208 (0.1338) loss: 0.8177 (0.8174) time: 0.2934 data: 0.1813 max mem: 9390 +Train: [79] [ 900/6250] eta: 0:22:04 lr: 0.000014 grad: 0.1213 (0.1326) loss: 0.8183 (0.8172) time: 0.5004 data: 0.3969 max mem: 9390 +Train: [79] [1000/6250] eta: 0:21:00 lr: 0.000014 grad: 0.1255 (0.1316) loss: 0.8158 (0.8171) time: 0.1637 data: 0.0412 max mem: 9390 +Train: [79] [1100/6250] eta: 0:20:20 lr: 0.000014 grad: 0.1294 (0.1312) loss: 0.8090 (0.8169) time: 0.2052 data: 0.1047 max mem: 9390 +Train: [79] [1200/6250] eta: 0:20:05 lr: 0.000014 grad: 0.1321 (0.1312) loss: 0.8088 (0.8162) time: 0.2251 data: 0.1483 max mem: 9390 +Train: [79] [1300/6250] eta: 0:19:18 lr: 0.000014 grad: 0.1144 (0.1311) loss: 0.8089 (0.8158) time: 0.2069 data: 0.1193 max mem: 9390 +Train: [79] [1400/6250] eta: 0:18:31 lr: 0.000014 grad: 0.1317 (0.1310) loss: 0.8110 (0.8154) time: 0.1622 data: 0.0696 max mem: 9390 +Train: [79] [1500/6250] eta: 0:17:55 lr: 0.000014 grad: 0.1246 (0.1308) loss: 0.8110 (0.8150) time: 0.1660 data: 0.0776 max mem: 9390 +Train: [79] [1600/6250] eta: 0:17:20 lr: 0.000014 grad: 0.1262 (0.1305) loss: 0.8136 (0.8148) time: 0.1859 data: 0.0951 max mem: 9390 +Train: [79] [1700/6250] eta: 0:16:44 lr: 0.000014 grad: 0.1231 (0.1304) loss: 0.8090 (0.8147) time: 0.1826 data: 0.0884 max mem: 9390 +Train: [79] [1800/6250] eta: 0:16:13 lr: 0.000014 grad: 0.1245 (0.1303) loss: 0.8066 (0.8144) time: 0.1741 data: 0.0706 max mem: 9390 +Train: [79] [1900/6250] eta: 0:15:40 lr: 0.000014 grad: 0.1240 (0.1302) loss: 0.8182 (0.8143) time: 0.1802 data: 0.0908 max mem: 9390 +Train: [79] [2000/6250] eta: 0:15:08 lr: 0.000014 grad: 0.1205 (0.1300) loss: 0.8201 (0.8142) time: 0.1706 data: 0.0729 max mem: 9390 +Train: [79] [2100/6250] eta: 0:14:38 lr: 0.000014 grad: 0.1289 (0.1298) loss: 0.8106 (0.8142) time: 0.1379 data: 0.0324 max mem: 9390 +Train: [79] [2200/6250] eta: 0:14:08 lr: 0.000014 grad: 0.1268 (0.1299) loss: 0.8142 (0.8142) time: 0.1684 data: 0.0654 max mem: 9390 +Train: [79] [2300/6250] eta: 0:13:41 lr: 0.000014 grad: 0.1234 (0.1298) loss: 0.8151 (0.8141) time: 0.2006 data: 0.0914 max mem: 9390 +Train: [79] [2400/6250] eta: 0:13:16 lr: 0.000014 grad: 0.1240 (0.1298) loss: 0.8148 (0.8141) time: 0.2080 data: 0.1129 max mem: 9390 +Train: [79] [2500/6250] eta: 0:12:53 lr: 0.000014 grad: 0.1343 (0.1300) loss: 0.8111 (0.8140) time: 0.1913 data: 0.0999 max mem: 9390 +Train: [79] [2600/6250] eta: 0:12:29 lr: 0.000014 grad: 0.1257 (0.1300) loss: 0.8080 (0.8139) time: 0.1930 data: 0.0954 max mem: 9390 +Train: [79] [2700/6250] eta: 0:12:11 lr: 0.000014 grad: 0.1277 (0.1302) loss: 0.8110 (0.8138) time: 0.2839 data: 0.1679 max mem: 9390 +pretraining fmri mae +start: 2026-04-01 13:10:47 +cwd: /data/connor/fmri-fm +sha: 7f4cedc35609f6857314e0d1ea6657523f17ddeb, status: has uncommitted changes, branch: dev/clane9 +config: +name: input_space_v3/flat_lr1e-3_4/pretrain +notes: input_space ablation v3 flat_lr1e-3_4; use tube masking and on-disk data (input_space=flat + base_lr=1e-3 seed=5404) +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain +input_space: flat +patch_size: 16 +num_frames: 16 +t_patch_size: 4 +mask_ratio: 0.9 +pred_mask_ratio: null +masking: tube +masking_kwargs: {} +mask_patch_size: null +model: mae_vit_base +model_kwargs: + decoding: attn + pos_embed: sep + target_norm: null + pca_norm_nc: 2 + t_pred_stride: 2 + no_decode_pos: true + mask_drop_scale: false + pred_edge_pad: 0 + gauss_sigma: null + class_token: true + reg_tokens: 0 + no_embed_class: true + head_init_scale: 0.0 + decoder_depth: 4 + drop_path_rate: 0.0 +datasets: + hcp-train: + type: wds + url: /data/fmri-datasets/pretrain/hcpya-all.${input_space}.wds/hcpya-all-${input_space}-{00000..01799}.tar + clipping: random + clipping_kwargs: + oversample: 4.0 + shuffle: true + buffer_size: 2000 + samples_per_epoch: 200000 + hcp-train-subset: + type: arrow + root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/validation + split_range: + - 0 + - 2000 + shuffle: false + hcp-val: + type: arrow + root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/test + split_range: + - 0 + - 2000 + shuffle: false +train_dataset: hcp-train +eval_datasets: +- hcp-train-subset +- hcp-val +val_dataset: null +clip_vmax: 3.0 +normalize: frame +tr_scale: null +crop_scale: null +crop_aspect: null +gray_jitter: null +num_workers: 16 +epochs: 100 +batch_size: 32 +accum_iter: 1 +base_lr: 0.001 +min_lr: 0.0 +warmup_epochs: 5 +weight_decay: 0.05 +betas: +- 0.9 +- 0.95 +clip_grad: 1.0 +amp: true +amp_dtype: float16 +ckpt: null +resume: true +auto_resume: true +start_epoch: 0 +max_checkpoints: 0 +checkpoint_period: null +plot_period: 5 +device: cuda +presend_cuda: false +seed: 5404 +debug: false +wandb: true +wandb_entity: null +wandb_project: fMRI-foundation-model +rank: 0 +world_size: 1 +gpu: 0 +distributed: true +dist_backend: nccl +in_chans: 1 +img_size: +- 224 +- 560 + +train transform: +Compose( + ToTensor() + TemporalCenterCrop(num_frames=16) + Normalize(mode='frame') + Clip(vmax=3.0) + FlatUnmask((224, 560)) +) +val transform: +Compose( + ToTensor() + TemporalCenterCrop(num_frames=16) + Normalize(mode='frame') + Clip(vmax=3.0) + FlatUnmask((224, 560)) +) +mask generator: +TubeMasking( + mask_ratio=0.9 + (patchify): Patchify2D((224, 560), (16, 16), in_chans=1) +) +loading dataset: hcp-train + +type: wds +url: /data/fmri-datasets/pretrain/hcpya-all.${input_space}.wds/hcpya-all-${input_space}-{00000..01799}.tar +clipping: random +clipping_kwargs: + oversample: 4.0 +shuffle: true +buffer_size: 2000 +samples_per_epoch: 200000 + +loading dataset: hcp-train-subset + +type: arrow +root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/validation +split_range: +- 0 +- 2000 +shuffle: false + +split indices: [899, 472, 767, 116, 1265, 1852, 300, 1335, 361, 1560] +loading dataset: hcp-val + +type: arrow +root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/test +split_range: +- 0 +- 2000 +shuffle: false + +split indices: [1075, 1189, 738, 1350, 965, 1964, 1367, 1183, 1619, 1407] +model: +MaskedAutoencoderViT( + decoding=attn, t_pred_stride=2, pred_edge_pad=0, no_decode_pos=True + (encoder): MaskedEncoder( + class_token=True, reg_tokens=0, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) + (pred_patchify): StridedPatchify3D((16, 224, 560), (2, 16, 16), in_chans=1, t_stride=2) + (decoder): MaskedDecoder( + cross_decode=False, class_token=True, no_embed_class=True + (pos_embed): SeparablePosEmbed(512, (4, 14, 35)) + (proj): Linear(in_features=768, out_features=512, bias=True) + (blocks): ModuleList( + (0-3): 4 x Block( + (norm1): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=16 + (q): Linear(in_features=512, out_features=512, bias=True) + (k): Linear(in_features=512, out_features=512, bias=True) + (v): Linear(in_features=512, out_features=512, bias=True) + (proj): Linear(in_features=512, out_features=512, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=512, out_features=2048, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=2048, out_features=512, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (head): Linear(in_features=512, out_features=512, bias=True) + ) +) +num params: 99.7M +total batch size: 32 = 32 bs per gpu x 1 accum x 1 gpus +lr: 1.25e-04 = 1.00e-03 x 32 / 256 +full schedule: epochs = 100 (steps = 625000) +warmup: epochs = 5 (steps = 31250) +loaded model state from checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +loaded optimizer state, resuming training from 79 +start training for 100 epochs +Train: [79] [ 0/6250] eta: 10:01:49 lr: 0.000014 grad: 0.1028 (0.1028) loss: 0.8314 (0.8314) time: 5.7776 data: 4.4896 max mem: 9353 +Train: [79] [ 100/6250] eta: 0:17:34 lr: 0.000014 grad: 0.1435 (0.1794) loss: 0.8076 (0.8108) time: 0.1200 data: 0.0382 max mem: 9390 +Train: [79] [ 200/6250] eta: 0:14:19 lr: 0.000014 grad: 0.1404 (0.1745) loss: 0.8021 (0.8064) time: 0.1258 data: 0.0502 max mem: 9390 +Train: [79] [ 300/6250] eta: 0:13:10 lr: 0.000014 grad: 0.1213 (0.1652) loss: 0.8167 (0.8064) time: 0.1180 data: 0.0194 max mem: 9390 +Train: [79] [ 400/6250] eta: 0:13:13 lr: 0.000014 grad: 0.1441 (0.1590) loss: 0.8109 (0.8069) time: 0.1421 data: 0.0579 max mem: 9390 +Train: [79] [ 500/6250] eta: 0:13:29 lr: 0.000014 grad: 0.1273 (0.1542) loss: 0.8150 (0.8081) time: 0.1936 data: 0.1103 max mem: 9390 +Train: [79] [ 600/6250] eta: 0:13:31 lr: 0.000014 grad: 0.1288 (0.1506) loss: 0.8061 (0.8089) time: 0.1907 data: 0.1073 max mem: 9390 +Train: [79] [ 700/6250] eta: 0:13:29 lr: 0.000014 grad: 0.1308 (0.1484) loss: 0.8059 (0.8093) time: 0.1741 data: 0.0930 max mem: 9390 +Train: [79] [ 800/6250] eta: 0:13:28 lr: 0.000014 grad: 0.1251 (0.1467) loss: 0.8193 (0.8097) time: 0.1507 data: 0.0685 max mem: 9390 +Train: [79] [ 900/6250] eta: 0:13:26 lr: 0.000014 grad: 0.1283 (0.1451) loss: 0.8135 (0.8098) time: 0.2190 data: 0.1338 max mem: 9390 +Train: [79] [1000/6250] eta: 0:13:15 lr: 0.000014 grad: 0.1251 (0.1435) loss: 0.8096 (0.8097) time: 0.1705 data: 0.0879 max mem: 9390 +Train: [79] [1100/6250] eta: 0:12:59 lr: 0.000014 grad: 0.1298 (0.1420) loss: 0.8086 (0.8098) time: 0.1282 data: 0.0441 max mem: 9390 +Train: [79] [1200/6250] eta: 0:12:48 lr: 0.000014 grad: 0.1259 (0.1409) loss: 0.8158 (0.8098) time: 0.1557 data: 0.0735 max mem: 9390 +Train: [79] [1300/6250] eta: 0:12:31 lr: 0.000014 grad: 0.1244 (0.1402) loss: 0.8082 (0.8097) time: 0.1448 data: 0.0566 max mem: 9390 +Train: [79] [1400/6250] eta: 0:12:16 lr: 0.000014 grad: 0.1293 (0.1394) loss: 0.8126 (0.8097) time: 0.1456 data: 0.0643 max mem: 9390 +Train: [79] [1500/6250] eta: 0:12:00 lr: 0.000014 grad: 0.1246 (0.1386) loss: 0.8144 (0.8098) time: 0.1287 data: 0.0407 max mem: 9390 +Train: [79] [1600/6250] eta: 0:11:45 lr: 0.000014 grad: 0.1166 (0.1380) loss: 0.8158 (0.8099) time: 0.1579 data: 0.0808 max mem: 9390 +Train: [79] [1700/6250] eta: 0:11:29 lr: 0.000014 grad: 0.1213 (0.1374) loss: 0.8152 (0.8100) time: 0.1385 data: 0.0523 max mem: 9390 +Train: [79] [1800/6250] eta: 0:11:14 lr: 0.000014 grad: 0.1203 (0.1367) loss: 0.8142 (0.8101) time: 0.1816 data: 0.0965 max mem: 9390 +Train: [79] [1900/6250] eta: 0:10:57 lr: 0.000014 grad: 0.1197 (0.1361) loss: 0.8126 (0.8102) time: 0.1264 data: 0.0404 max mem: 9390 +Train: [79] [2000/6250] eta: 0:10:42 lr: 0.000014 grad: 0.1202 (0.1358) loss: 0.8169 (0.8103) time: 0.1458 data: 0.0619 max mem: 9390 +Train: [79] [2100/6250] eta: 0:10:26 lr: 0.000014 grad: 0.1274 (0.1355) loss: 0.8042 (0.8102) time: 0.1389 data: 0.0562 max mem: 9390 +Train: [79] [2200/6250] eta: 0:10:10 lr: 0.000014 grad: 0.1365 (0.1353) loss: 0.8109 (0.8101) time: 0.1438 data: 0.0571 max mem: 9390 +Train: [79] [2300/6250] eta: 0:09:56 lr: 0.000014 grad: 0.1244 (0.1350) loss: 0.8077 (0.8101) time: 0.1600 data: 0.0752 max mem: 9390 +Train: [79] [2400/6250] eta: 0:09:40 lr: 0.000014 grad: 0.1227 (0.1348) loss: 0.8132 (0.8101) time: 0.1283 data: 0.0417 max mem: 9390 +Train: [79] [2500/6250] eta: 0:09:25 lr: 0.000014 grad: 0.1287 (0.1346) loss: 0.8026 (0.8100) time: 0.1315 data: 0.0516 max mem: 9390 +Train: [79] [2600/6250] eta: 0:09:09 lr: 0.000014 grad: 0.1265 (0.1345) loss: 0.8074 (0.8100) time: 0.1615 data: 0.0759 max mem: 9390 +Train: [79] [2700/6250] eta: 0:08:54 lr: 0.000014 grad: 0.1259 (0.1344) loss: 0.8055 (0.8100) time: 0.1512 data: 0.0574 max mem: 9390 +Train: [79] [2800/6250] eta: 0:08:39 lr: 0.000014 grad: 0.1300 (0.1342) loss: 0.8100 (0.8100) time: 0.1452 data: 0.0620 max mem: 9390 +Train: [79] [2900/6250] eta: 0:08:24 lr: 0.000014 grad: 0.1269 (0.1342) loss: 0.8083 (0.8099) time: 0.1466 data: 0.0652 max mem: 9390 +Train: [79] [3000/6250] eta: 0:08:09 lr: 0.000014 grad: 0.1265 (0.1340) loss: 0.8072 (0.8099) time: 0.1585 data: 0.0736 max mem: 9390 +Train: [79] [3100/6250] eta: 0:07:53 lr: 0.000014 grad: 0.1190 (0.1338) loss: 0.8148 (0.8099) time: 0.1427 data: 0.0617 max mem: 9390 +Train: [79] [3200/6250] eta: 0:07:38 lr: 0.000014 grad: 0.1333 (0.1337) loss: 0.8092 (0.8099) time: 0.1657 data: 0.0794 max mem: 9390 +Train: [79] [3300/6250] eta: 0:07:24 lr: 0.000014 grad: 0.1245 (0.1336) loss: 0.8067 (0.8099) time: 0.1416 data: 0.0585 max mem: 9390 +Train: [79] [3400/6250] eta: 0:07:08 lr: 0.000014 grad: 0.1192 (0.1335) loss: 0.8096 (0.8099) time: 0.1242 data: 0.0401 max mem: 9390 +Train: [79] [3500/6250] eta: 0:06:53 lr: 0.000014 grad: 0.1200 (0.1334) loss: 0.8180 (0.8100) time: 0.1520 data: 0.0764 max mem: 9390 +Train: [79] [3600/6250] eta: 0:06:38 lr: 0.000014 grad: 0.1209 (0.1333) loss: 0.8070 (0.8100) time: 0.1457 data: 0.0585 max mem: 9390 +Train: [79] [3700/6250] eta: 0:06:23 lr: 0.000014 grad: 0.1293 (0.1334) loss: 0.8086 (0.8100) time: 0.1579 data: 0.0777 max mem: 9390 +Train: [79] [3800/6250] eta: 0:06:08 lr: 0.000014 grad: 0.1260 (0.1334) loss: 0.8091 (0.8100) time: 0.1602 data: 0.0797 max mem: 9390 +Train: [79] [3900/6250] eta: 0:05:53 lr: 0.000014 grad: 0.1311 (0.1333) loss: 0.8099 (0.8100) time: 0.1537 data: 0.0693 max mem: 9390 +Train: [79] [4000/6250] eta: 0:05:38 lr: 0.000014 grad: 0.1166 (0.1332) loss: 0.8225 (0.8101) time: 0.1484 data: 0.0654 max mem: 9390 +Train: [79] [4100/6250] eta: 0:05:23 lr: 0.000014 grad: 0.1271 (0.1332) loss: 0.8131 (0.8101) time: 0.1425 data: 0.0553 max mem: 9390 +pretraining fmri mae +start: 2026-04-01 13:28:40 +cwd: /data/connor/fmri-fm +sha: 7f4cedc35609f6857314e0d1ea6657523f17ddeb, status: has uncommitted changes, branch: dev/clane9 +config: +name: input_space_v3/flat_lr1e-3_4/pretrain +notes: input_space ablation v3 flat_lr1e-3_4; use tube masking and on-disk data (input_space=flat + base_lr=1e-3 seed=5404) +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain +input_space: flat +patch_size: 16 +num_frames: 16 +t_patch_size: 4 +mask_ratio: 0.9 +pred_mask_ratio: null +masking: tube +masking_kwargs: {} +mask_patch_size: null +model: mae_vit_base +model_kwargs: + decoding: attn + pos_embed: sep + target_norm: null + pca_norm_nc: 2 + t_pred_stride: 2 + no_decode_pos: true + mask_drop_scale: false + pred_edge_pad: 0 + gauss_sigma: null + class_token: true + reg_tokens: 0 + no_embed_class: true + head_init_scale: 0.0 + decoder_depth: 4 + drop_path_rate: 0.0 +datasets: + hcp-train: + type: wds + url: /data/fmri-datasets/pretrain/hcpya-all.${input_space}.wds/hcpya-all-${input_space}-{00000..01799}.tar + clipping: random + clipping_kwargs: + oversample: 4.0 + shuffle: true + buffer_size: 2000 + samples_per_epoch: 200000 + hcp-train-subset: + type: arrow + root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/validation + split_range: + - 0 + - 2000 + shuffle: false + hcp-val: + type: arrow + root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/test + split_range: + - 0 + - 2000 + shuffle: false +train_dataset: hcp-train +eval_datasets: +- hcp-train-subset +- hcp-val +val_dataset: null +clip_vmax: 3.0 +normalize: frame +tr_scale: null +crop_scale: null +crop_aspect: null +gray_jitter: null +num_workers: 16 +epochs: 100 +batch_size: 32 +accum_iter: 1 +base_lr: 0.001 +min_lr: 0.0 +warmup_epochs: 5 +weight_decay: 0.05 +betas: +- 0.9 +- 0.95 +clip_grad: 1.0 +amp: true +amp_dtype: float16 +ckpt: null +resume: true +auto_resume: true +start_epoch: 0 +max_checkpoints: 0 +checkpoint_period: null +plot_period: 5 +device: cuda +presend_cuda: false +seed: 5404 +debug: false +wandb: true +wandb_entity: null +wandb_project: fMRI-foundation-model +rank: 0 +world_size: 1 +gpu: 0 +distributed: true +dist_backend: nccl +in_chans: 1 +img_size: +- 224 +- 560 + +train transform: +Compose( + ToTensor() + TemporalCenterCrop(num_frames=16) + Normalize(mode='frame') + Clip(vmax=3.0) + FlatUnmask((224, 560)) +) +val transform: +Compose( + ToTensor() + TemporalCenterCrop(num_frames=16) + Normalize(mode='frame') + Clip(vmax=3.0) + FlatUnmask((224, 560)) +) +mask generator: +TubeMasking( + mask_ratio=0.9 + (patchify): Patchify2D((224, 560), (16, 16), in_chans=1) +) +loading dataset: hcp-train + +type: wds +url: /data/fmri-datasets/pretrain/hcpya-all.${input_space}.wds/hcpya-all-${input_space}-{00000..01799}.tar +clipping: random +clipping_kwargs: + oversample: 4.0 +shuffle: true +buffer_size: 2000 +samples_per_epoch: 200000 + +loading dataset: hcp-train-subset + +type: arrow +root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/validation +split_range: +- 0 +- 2000 +shuffle: false + +split indices: [899, 472, 767, 116, 1265, 1852, 300, 1335, 361, 1560] +loading dataset: hcp-val + +type: arrow +root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/test +split_range: +- 0 +- 2000 +shuffle: false + +split indices: [1075, 1189, 738, 1350, 965, 1964, 1367, 1183, 1619, 1407] +model: +MaskedAutoencoderViT( + decoding=attn, t_pred_stride=2, pred_edge_pad=0, no_decode_pos=True + (encoder): MaskedEncoder( + class_token=True, reg_tokens=0, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) + (pred_patchify): StridedPatchify3D((16, 224, 560), (2, 16, 16), in_chans=1, t_stride=2) + (decoder): MaskedDecoder( + cross_decode=False, class_token=True, no_embed_class=True + (pos_embed): SeparablePosEmbed(512, (4, 14, 35)) + (proj): Linear(in_features=768, out_features=512, bias=True) + (blocks): ModuleList( + (0-3): 4 x Block( + (norm1): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=16 + (q): Linear(in_features=512, out_features=512, bias=True) + (k): Linear(in_features=512, out_features=512, bias=True) + (v): Linear(in_features=512, out_features=512, bias=True) + (proj): Linear(in_features=512, out_features=512, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=512, out_features=2048, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=2048, out_features=512, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (head): Linear(in_features=512, out_features=512, bias=True) + ) +) +num params: 99.7M +total batch size: 32 = 32 bs per gpu x 1 accum x 1 gpus +lr: 1.25e-04 = 1.00e-03 x 32 / 256 +full schedule: epochs = 100 (steps = 625000) +warmup: epochs = 5 (steps = 31250) +loaded model state from checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +loaded optimizer state, resuming training from 79 +start training for 100 epochs +Train: [79] [ 0/6250] eta: 15:09:04 lr: 0.000014 grad: 0.0988 (0.0988) loss: 0.8475 (0.8475) time: 8.7271 data: 7.6401 max mem: 9353 +Train: [79] [ 100/6250] eta: 0:23:47 lr: 0.000014 grad: 0.1020 (0.1633) loss: 0.8330 (0.8204) time: 0.1760 data: 0.0865 max mem: 9390 +Train: [79] [ 200/6250] eta: 0:19:13 lr: 0.000014 grad: 0.1466 (0.1531) loss: 0.8202 (0.8207) time: 0.1376 data: 0.0389 max mem: 9390 +Train: [79] [ 300/6250] eta: 0:17:52 lr: 0.000014 grad: 0.1395 (0.1492) loss: 0.8086 (0.8175) time: 0.1686 data: 0.0776 max mem: 9390 +Train: [79] [ 400/6250] eta: 0:16:54 lr: 0.000014 grad: 0.1336 (0.1477) loss: 0.8092 (0.8151) time: 0.1467 data: 0.0501 max mem: 9390 +Train: [79] [ 500/6250] eta: 0:16:37 lr: 0.000014 grad: 0.1173 (0.1450) loss: 0.8142 (0.8136) time: 0.1734 data: 0.0884 max mem: 9390 +Train: [79] [ 600/6250] eta: 0:16:18 lr: 0.000014 grad: 0.1199 (0.1423) loss: 0.8171 (0.8139) time: 0.1787 data: 0.0901 max mem: 9390 +Train: [79] [ 700/6250] eta: 0:15:49 lr: 0.000014 grad: 0.1290 (0.1404) loss: 0.8119 (0.8139) time: 0.1531 data: 0.0701 max mem: 9390 +Train: [79] [ 800/6250] eta: 0:15:27 lr: 0.000014 grad: 0.1251 (0.1396) loss: 0.8141 (0.8137) time: 0.1709 data: 0.0894 max mem: 9390 +Train: [79] [ 900/6250] eta: 0:15:01 lr: 0.000014 grad: 0.1178 (0.1384) loss: 0.8196 (0.8135) time: 0.1244 data: 0.0396 max mem: 9390 +Train: [79] [1000/6250] eta: 0:14:40 lr: 0.000014 grad: 0.1245 (0.1376) loss: 0.8053 (0.8134) time: 0.1775 data: 0.0928 max mem: 9390 +Train: [79] [1100/6250] eta: 0:14:14 lr: 0.000014 grad: 0.1198 (0.1369) loss: 0.8152 (0.8129) time: 0.1466 data: 0.0597 max mem: 9390 +Train: [79] [1200/6250] eta: 0:13:52 lr: 0.000014 grad: 0.1191 (0.1362) loss: 0.8142 (0.8127) time: 0.1416 data: 0.0584 max mem: 9390 +Train: [79] [1300/6250] eta: 0:13:31 lr: 0.000014 grad: 0.1215 (0.1357) loss: 0.8133 (0.8124) time: 0.1541 data: 0.0780 max mem: 9390 +Train: [79] [1400/6250] eta: 0:13:11 lr: 0.000014 grad: 0.1274 (0.1350) loss: 0.8035 (0.8121) time: 0.1680 data: 0.0829 max mem: 9390 +Train: [79] [1500/6250] eta: 0:12:49 lr: 0.000014 grad: 0.1329 (0.1346) loss: 0.8038 (0.8118) time: 0.1409 data: 0.0593 max mem: 9390 +Train: [79] [1600/6250] eta: 0:12:29 lr: 0.000014 grad: 0.1338 (0.1343) loss: 0.7959 (0.8116) time: 0.1706 data: 0.0862 max mem: 9390 +Train: [79] [1700/6250] eta: 0:12:08 lr: 0.000014 grad: 0.1284 (0.1339) loss: 0.8108 (0.8115) time: 0.1484 data: 0.0680 max mem: 9390 +Train: [79] [1800/6250] eta: 0:11:49 lr: 0.000014 grad: 0.1203 (0.1336) loss: 0.8168 (0.8115) time: 0.1480 data: 0.0675 max mem: 9390 +Train: [79] [1900/6250] eta: 0:11:33 lr: 0.000014 grad: 0.1338 (0.1333) loss: 0.8046 (0.8115) time: 0.1439 data: 0.0599 max mem: 9390 +Train: [79] [2000/6250] eta: 0:11:40 lr: 0.000014 grad: 0.1354 (0.1331) loss: 0.8104 (0.8114) time: 0.7497 data: 0.6728 max mem: 9390 +Train: [79] [2100/6250] eta: 0:11:22 lr: 0.000014 grad: 0.1227 (0.1328) loss: 0.8145 (0.8115) time: 0.1679 data: 0.0836 max mem: 9390 +Train: [79] [2200/6250] eta: 0:11:03 lr: 0.000014 grad: 0.1237 (0.1326) loss: 0.8115 (0.8115) time: 0.1493 data: 0.0613 max mem: 9390 +Train: [79] [2300/6250] eta: 0:10:45 lr: 0.000014 grad: 0.1323 (0.1325) loss: 0.8035 (0.8114) time: 0.1423 data: 0.0588 max mem: 9390 +pretraining fmri mae +start: 2026-04-01 13:39:46 +cwd: /data/connor/fmri-fm +sha: 7f4cedc35609f6857314e0d1ea6657523f17ddeb, status: has uncommitted changes, branch: dev/clane9 +config: +name: input_space_v3/flat_lr1e-3_4/pretrain +notes: input_space ablation v3 flat_lr1e-3_4; use tube masking and on-disk data (input_space=flat + base_lr=1e-3 seed=5404) +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain +input_space: flat +patch_size: 16 +num_frames: 16 +t_patch_size: 4 +mask_ratio: 0.9 +pred_mask_ratio: null +masking: tube +masking_kwargs: {} +mask_patch_size: null +model: mae_vit_base +model_kwargs: + decoding: attn + pos_embed: sep + target_norm: null + pca_norm_nc: 2 + t_pred_stride: 2 + no_decode_pos: true + mask_drop_scale: false + pred_edge_pad: 0 + gauss_sigma: null + class_token: true + reg_tokens: 0 + no_embed_class: true + head_init_scale: 0.0 + decoder_depth: 4 + drop_path_rate: 0.0 +datasets: + hcp-train: + type: wds + url: /data/fmri-datasets/pretrain/hcpya-all.${input_space}.wds/hcpya-all-${input_space}-{00000..01799}.tar + clipping: random + clipping_kwargs: + oversample: 4.0 + shuffle: true + buffer_size: 2000 + samples_per_epoch: 200000 + hcp-train-subset: + type: arrow + root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/validation + split_range: + - 0 + - 2000 + shuffle: false + hcp-val: + type: arrow + root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/test + split_range: + - 0 + - 2000 + shuffle: false +train_dataset: hcp-train +eval_datasets: +- hcp-train-subset +- hcp-val +val_dataset: null +clip_vmax: 3.0 +normalize: frame +tr_scale: null +crop_scale: null +crop_aspect: null +gray_jitter: null +num_workers: 16 +epochs: 100 +batch_size: 32 +accum_iter: 1 +base_lr: 0.001 +min_lr: 0.0 +warmup_epochs: 5 +weight_decay: 0.05 +betas: +- 0.9 +- 0.95 +clip_grad: 1.0 +amp: true +amp_dtype: float16 +ckpt: null +resume: true +auto_resume: true +start_epoch: 0 +max_checkpoints: 0 +checkpoint_period: null +plot_period: 5 +device: cuda +presend_cuda: false +seed: 5404 +debug: false +wandb: true +wandb_entity: null +wandb_project: fMRI-foundation-model +rank: 0 +world_size: 1 +gpu: 0 +distributed: true +dist_backend: nccl +in_chans: 1 +img_size: +- 224 +- 560 + +train transform: +Compose( + ToTensor() + TemporalCenterCrop(num_frames=16) + Normalize(mode='frame') + Clip(vmax=3.0) + FlatUnmask((224, 560)) +) +val transform: +Compose( + ToTensor() + TemporalCenterCrop(num_frames=16) + Normalize(mode='frame') + Clip(vmax=3.0) + FlatUnmask((224, 560)) +) +mask generator: +TubeMasking( + mask_ratio=0.9 + (patchify): Patchify2D((224, 560), (16, 16), in_chans=1) +) +loading dataset: hcp-train + +type: wds +url: /data/fmri-datasets/pretrain/hcpya-all.${input_space}.wds/hcpya-all-${input_space}-{00000..01799}.tar +clipping: random +clipping_kwargs: + oversample: 4.0 +shuffle: true +buffer_size: 2000 +samples_per_epoch: 200000 + +loading dataset: hcp-train-subset + +type: arrow +root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/validation +split_range: +- 0 +- 2000 +shuffle: false + +split indices: [899, 472, 767, 116, 1265, 1852, 300, 1335, 361, 1560] +loading dataset: hcp-val + +type: arrow +root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/test +split_range: +- 0 +- 2000 +shuffle: false + +split indices: [1075, 1189, 738, 1350, 965, 1964, 1367, 1183, 1619, 1407] +model: +MaskedAutoencoderViT( + decoding=attn, t_pred_stride=2, pred_edge_pad=0, no_decode_pos=True + (encoder): MaskedEncoder( + class_token=True, reg_tokens=0, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) + (pred_patchify): StridedPatchify3D((16, 224, 560), (2, 16, 16), in_chans=1, t_stride=2) + (decoder): MaskedDecoder( + cross_decode=False, class_token=True, no_embed_class=True + (pos_embed): SeparablePosEmbed(512, (4, 14, 35)) + (proj): Linear(in_features=768, out_features=512, bias=True) + (blocks): ModuleList( + (0-3): 4 x Block( + (norm1): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=16 + (q): Linear(in_features=512, out_features=512, bias=True) + (k): Linear(in_features=512, out_features=512, bias=True) + (v): Linear(in_features=512, out_features=512, bias=True) + (proj): Linear(in_features=512, out_features=512, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=512, out_features=2048, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=2048, out_features=512, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (head): Linear(in_features=512, out_features=512, bias=True) + ) +) +num params: 99.7M +total batch size: 32 = 32 bs per gpu x 1 accum x 1 gpus +lr: 1.25e-04 = 1.00e-03 x 32 / 256 +full schedule: epochs = 100 (steps = 625000) +warmup: epochs = 5 (steps = 31250) +loaded model state from checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +loaded optimizer state, resuming training from 79 +start training for 100 epochs +Train: [79] [ 0/6250] eta: 1 day, 7:02:52 lr: 0.000014 grad: 0.4012 (0.4012) loss: 0.7677 (0.7677) time: 17.8836 data: 12.2596 max mem: 9353 +Train: [79] [ 100/6250] eta: 0:57:30 lr: 0.000014 grad: 0.1185 (0.1473) loss: 0.8313 (0.8276) time: 0.4956 data: 0.3876 max mem: 9390 +Train: [79] [ 200/6250] eta: 0:49:34 lr: 0.000014 grad: 0.1323 (0.1364) loss: 0.8220 (0.8259) time: 0.1050 data: 0.0007 max mem: 9390 +Train: [79] [ 300/6250] eta: 0:42:11 lr: 0.000014 grad: 0.1367 (0.1359) loss: 0.8086 (0.8230) time: 0.1855 data: 0.1035 max mem: 9390 +Train: [79] [ 400/6250] eta: 0:37:41 lr: 0.000014 grad: 0.1197 (0.1347) loss: 0.8176 (0.8211) time: 0.4266 data: 0.3309 max mem: 9390 +Train: [79] [ 500/6250] eta: 0:37:12 lr: 0.000014 grad: 0.1290 (0.1349) loss: 0.8129 (0.8199) time: 0.2543 data: 0.1618 max mem: 9390 +Train: [79] [ 600/6250] eta: 0:36:44 lr: 0.000014 grad: 0.1241 (0.1345) loss: 0.8183 (0.8193) time: 1.0338 data: 0.8955 max mem: 9390 +Train: [79] [ 700/6250] eta: 0:33:55 lr: 0.000014 grad: 0.1271 (0.1344) loss: 0.8172 (0.8183) time: 0.2346 data: 0.0771 max mem: 9390 +Train: [79] [ 800/6250] eta: 0:31:54 lr: 0.000014 grad: 0.1314 (0.1342) loss: 0.8081 (0.8171) time: 0.1178 data: 0.0356 max mem: 9390 +Train: [79] [ 900/6250] eta: 0:29:20 lr: 0.000014 grad: 0.1257 (0.1340) loss: 0.8148 (0.8162) time: 0.1651 data: 0.0769 max mem: 9390 +Train: [79] [1000/6250] eta: 0:27:10 lr: 0.000014 grad: 0.1347 (0.1335) loss: 0.8132 (0.8156) time: 0.1512 data: 0.0735 max mem: 9390 +Train: [79] [1100/6250] eta: 0:25:21 lr: 0.000014 grad: 0.1184 (0.1331) loss: 0.8123 (0.8152) time: 0.1583 data: 0.0805 max mem: 9390 +Train: [79] [1200/6250] eta: 0:23:40 lr: 0.000014 grad: 0.1201 (0.1327) loss: 0.8165 (0.8151) time: 0.1293 data: 0.0531 max mem: 9390 +Train: [79] [1300/6250] eta: 0:22:14 lr: 0.000014 grad: 0.1235 (0.1321) loss: 0.8077 (0.8149) time: 0.1319 data: 0.0559 max mem: 9390 +Train: [79] [1400/6250] eta: 0:21:01 lr: 0.000014 grad: 0.1208 (0.1319) loss: 0.8124 (0.8148) time: 0.1311 data: 0.0546 max mem: 9390 +Train: [79] [1500/6250] eta: 0:19:55 lr: 0.000014 grad: 0.1250 (0.1318) loss: 0.8061 (0.8144) time: 0.1324 data: 0.0587 max mem: 9390 +Train: [79] [1600/6250] eta: 0:18:54 lr: 0.000014 grad: 0.1262 (0.1315) loss: 0.8127 (0.8141) time: 0.1316 data: 0.0521 max mem: 9390 +Train: [79] [1700/6250] eta: 0:17:59 lr: 0.000014 grad: 0.1190 (0.1310) loss: 0.8218 (0.8140) time: 0.1286 data: 0.0560 max mem: 9390 +Train: [79] [1800/6250] eta: 0:17:09 lr: 0.000014 grad: 0.1290 (0.1309) loss: 0.8116 (0.8138) time: 0.1265 data: 0.0508 max mem: 9390 +Train: [79] [1900/6250] eta: 0:16:20 lr: 0.000014 grad: 0.1252 (0.1307) loss: 0.8155 (0.8137) time: 0.1212 data: 0.0457 max mem: 9390 +Train: [79] [2000/6250] eta: 0:15:38 lr: 0.000014 grad: 0.1237 (0.1304) loss: 0.8087 (0.8137) time: 0.1336 data: 0.0605 max mem: 9390 +Train: [79] [2100/6250] eta: 0:14:58 lr: 0.000014 grad: 0.1281 (0.1303) loss: 0.8078 (0.8136) time: 0.1105 data: 0.0336 max mem: 9390 +Train: [79] [2200/6250] eta: 0:14:21 lr: 0.000014 grad: 0.1263 (0.1304) loss: 0.8109 (0.8135) time: 0.1282 data: 0.0546 max mem: 9390 +Train: [79] [2300/6250] eta: 0:13:45 lr: 0.000014 grad: 0.1255 (0.1302) loss: 0.8105 (0.8135) time: 0.1269 data: 0.0482 max mem: 9390 +Train: [79] [2400/6250] eta: 0:13:11 lr: 0.000014 grad: 0.1218 (0.1301) loss: 0.8143 (0.8135) time: 0.1384 data: 0.0623 max mem: 9390 +Train: [79] [2500/6250] eta: 0:12:40 lr: 0.000014 grad: 0.1217 (0.1300) loss: 0.8196 (0.8135) time: 0.1232 data: 0.0468 max mem: 9390 +Train: [79] [2600/6250] eta: 0:12:10 lr: 0.000014 grad: 0.1317 (0.1299) loss: 0.8141 (0.8135) time: 0.1274 data: 0.0482 max mem: 9390 +Train: [79] [2700/6250] eta: 0:11:41 lr: 0.000014 grad: 0.1178 (0.1298) loss: 0.8110 (0.8135) time: 0.1303 data: 0.0483 max mem: 9390 +Train: [79] [2800/6250] eta: 0:11:13 lr: 0.000014 grad: 0.1333 (0.1297) loss: 0.8064 (0.8135) time: 0.1235 data: 0.0468 max mem: 9390 +Train: [79] [2900/6250] eta: 0:10:46 lr: 0.000014 grad: 0.1247 (0.1297) loss: 0.8162 (0.8136) time: 0.1397 data: 0.0640 max mem: 9390 +Train: [79] [3000/6250] eta: 0:10:21 lr: 0.000014 grad: 0.1233 (0.1297) loss: 0.8099 (0.8136) time: 0.1533 data: 0.0768 max mem: 9390 +Train: [79] [3100/6250] eta: 0:09:56 lr: 0.000014 grad: 0.1280 (0.1298) loss: 0.8122 (0.8136) time: 0.1389 data: 0.0589 max mem: 9390 +Train: [79] [3200/6250] eta: 0:09:32 lr: 0.000014 grad: 0.1248 (0.1299) loss: 0.8116 (0.8135) time: 0.1314 data: 0.0566 max mem: 9390 +Train: [79] [3300/6250] eta: 0:09:08 lr: 0.000014 grad: 0.1204 (0.1297) loss: 0.8186 (0.8135) time: 0.1283 data: 0.0437 max mem: 9390 +Train: [79] [3400/6250] eta: 0:08:44 lr: 0.000014 grad: 0.1287 (0.1297) loss: 0.8155 (0.8136) time: 0.1228 data: 0.0417 max mem: 9390 +Train: [79] [3500/6250] eta: 0:08:21 lr: 0.000014 grad: 0.1242 (0.1297) loss: 0.8150 (0.8136) time: 0.1324 data: 0.0564 max mem: 9390 +Train: [79] [3600/6250] eta: 0:07:58 lr: 0.000014 grad: 0.1218 (0.1296) loss: 0.8085 (0.8136) time: 0.1170 data: 0.0383 max mem: 9390 +Train: [79] [3700/6250] eta: 0:07:36 lr: 0.000014 grad: 0.1278 (0.1296) loss: 0.8156 (0.8136) time: 0.1161 data: 0.0393 max mem: 9390 +Train: [79] [3800/6250] eta: 0:07:15 lr: 0.000014 grad: 0.1298 (0.1296) loss: 0.8097 (0.8136) time: 0.1281 data: 0.0484 max mem: 9390 +Train: [79] [3900/6250] eta: 0:06:54 lr: 0.000014 grad: 0.1329 (0.1297) loss: 0.8031 (0.8135) time: 0.1199 data: 0.0461 max mem: 9390 +Train: [79] [4000/6250] eta: 0:06:33 lr: 0.000014 grad: 0.1345 (0.1297) loss: 0.8039 (0.8134) time: 0.1432 data: 0.0668 max mem: 9390 +Train: [79] [4100/6250] eta: 0:06:13 lr: 0.000014 grad: 0.1254 (0.1297) loss: 0.8113 (0.8134) time: 0.1168 data: 0.0380 max mem: 9390 +Train: [79] [4200/6250] eta: 0:05:53 lr: 0.000014 grad: 0.1258 (0.1296) loss: 0.8117 (0.8133) time: 0.1153 data: 0.0355 max mem: 9390 +Train: [79] [4300/6250] eta: 0:05:34 lr: 0.000014 grad: 0.1235 (0.1295) loss: 0.8107 (0.8133) time: 0.1375 data: 0.0586 max mem: 9390 +Train: [79] [4400/6250] eta: 0:05:14 lr: 0.000014 grad: 0.1240 (0.1295) loss: 0.8071 (0.8132) time: 0.1065 data: 0.0328 max mem: 9390 +Train: [79] [4500/6250] eta: 0:04:56 lr: 0.000014 grad: 0.1199 (0.1295) loss: 0.8178 (0.8132) time: 0.1403 data: 0.0606 max mem: 9390 +Train: [79] [4600/6250] eta: 0:04:37 lr: 0.000014 grad: 0.1268 (0.1295) loss: 0.8076 (0.8132) time: 0.1230 data: 0.0389 max mem: 9390 +Train: [79] [4700/6250] eta: 0:04:19 lr: 0.000013 grad: 0.1233 (0.1294) loss: 0.8098 (0.8131) time: 0.1231 data: 0.0451 max mem: 9390 +Train: [79] [4800/6250] eta: 0:04:01 lr: 0.000013 grad: 0.1260 (0.1294) loss: 0.8083 (0.8130) time: 0.1194 data: 0.0374 max mem: 9390 +Train: [79] [4900/6250] eta: 0:03:43 lr: 0.000013 grad: 0.1245 (0.1294) loss: 0.8147 (0.8130) time: 0.1110 data: 0.0319 max mem: 9390 +Train: [79] [5000/6250] eta: 0:03:25 lr: 0.000013 grad: 0.1222 (0.1294) loss: 0.8140 (0.8130) time: 0.1182 data: 0.0410 max mem: 9390 +Train: [79] [5100/6250] eta: 0:03:09 lr: 0.000013 grad: 0.1238 (0.1294) loss: 0.8117 (0.8130) time: 0.1314 data: 0.0426 max mem: 9390 +Train: [79] [5200/6250] eta: 0:02:52 lr: 0.000013 grad: 0.1287 (0.1294) loss: 0.8084 (0.8130) time: 0.1169 data: 0.0373 max mem: 9390 +Train: [79] [5300/6250] eta: 0:02:35 lr: 0.000013 grad: 0.1259 (0.1294) loss: 0.8105 (0.8130) time: 0.1425 data: 0.0573 max mem: 9390 +Train: [79] [5400/6250] eta: 0:02:18 lr: 0.000013 grad: 0.1205 (0.1294) loss: 0.8103 (0.8130) time: 0.1525 data: 0.0711 max mem: 9390 +Train: [79] [5500/6250] eta: 0:02:01 lr: 0.000013 grad: 0.1236 (0.1294) loss: 0.8168 (0.8130) time: 0.1452 data: 0.0675 max mem: 9390 +Train: [79] [5600/6250] eta: 0:01:45 lr: 0.000013 grad: 0.1305 (0.1294) loss: 0.8147 (0.8129) time: 0.1520 data: 0.0781 max mem: 9390 +Train: [79] [5700/6250] eta: 0:01:28 lr: 0.000013 grad: 0.1297 (0.1295) loss: 0.8132 (0.8130) time: 0.1170 data: 0.0406 max mem: 9390 +Train: [79] [5800/6250] eta: 0:01:12 lr: 0.000013 grad: 0.1251 (0.1295) loss: 0.8105 (0.8129) time: 0.1460 data: 0.0640 max mem: 9390 +Train: [79] [5900/6250] eta: 0:00:56 lr: 0.000013 grad: 0.1306 (0.1296) loss: 0.8083 (0.8129) time: 0.1396 data: 0.0453 max mem: 9390 +Train: [79] [6000/6250] eta: 0:00:40 lr: 0.000013 grad: 0.1281 (0.1296) loss: 0.8081 (0.8128) time: 0.1439 data: 0.0571 max mem: 9390 +Train: [79] [6100/6250] eta: 0:00:24 lr: 0.000013 grad: 0.1303 (0.1296) loss: 0.8094 (0.8128) time: 0.2709 data: 0.1795 max mem: 9390 +Train: [79] [6200/6250] eta: 0:00:08 lr: 0.000013 grad: 0.1353 (0.1297) loss: 0.8107 (0.8127) time: 0.1477 data: 0.0700 max mem: 9390 +Train: [79] [6249/6250] eta: 0:00:00 lr: 0.000013 grad: 0.1316 (0.1297) loss: 0.8111 (0.8127) time: 0.1717 data: 0.0899 max mem: 9390 +Train: [79] Total time: 0:17:02 (0.1636 s / it) +Averaged stats: lr: 0.000013 grad: 0.1316 (0.1297) loss: 0.8111 (0.8127) +Eval (hcp-train-subset): [79] [ 0/62] eta: 0:05:09 loss: 0.8315 (0.8315) time: 4.9860 data: 4.9529 max mem: 9390 +Eval (hcp-train-subset): [79] [61/62] eta: 0:00:00 loss: 0.8210 (0.8228) time: 0.1243 data: 0.0990 max mem: 9390 +Eval (hcp-train-subset): [79] Total time: 0:00:14 (0.2350 s / it) +Averaged stats (hcp-train-subset): loss: 0.8210 (0.8228) +Making plots (hcp-train-subset): example=24 +Eval (hcp-val): [79] [ 0/62] eta: 0:03:33 loss: 0.8295 (0.8295) time: 3.4365 data: 3.3216 max mem: 9390 +Eval (hcp-val): [79] [61/62] eta: 0:00:00 loss: 0.8288 (0.8302) time: 0.1298 data: 0.1048 max mem: 9390 +Eval (hcp-val): [79] Total time: 0:00:13 (0.2159 s / it) +Averaged stats (hcp-val): loss: 0.8288 (0.8302) +Making plots (hcp-val): example=24 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +Train: [80] [ 0/6250] eta: 9:33:42 lr: 0.000013 grad: 0.0789 (0.0789) loss: 0.8511 (0.8511) time: 5.5076 data: 5.3414 max mem: 9390 +Train: [80] [ 100/6250] eta: 0:22:15 lr: 0.000013 grad: 0.1480 (0.1632) loss: 0.8188 (0.8307) time: 0.1722 data: 0.0829 max mem: 9390 +Train: [80] [ 200/6250] eta: 0:20:00 lr: 0.000013 grad: 0.1283 (0.1520) loss: 0.8099 (0.8224) time: 0.1219 data: 0.0301 max mem: 9390 +Train: [80] [ 300/6250] eta: 0:19:24 lr: 0.000013 grad: 0.1303 (0.1465) loss: 0.8115 (0.8193) time: 0.1748 data: 0.0919 max mem: 9390 +Train: [80] [ 400/6250] eta: 0:18:51 lr: 0.000013 grad: 0.1346 (0.1437) loss: 0.8184 (0.8174) time: 0.1815 data: 0.0760 max mem: 9390 +Train: [80] [ 500/6250] eta: 0:19:17 lr: 0.000013 grad: 0.1466 (0.1426) loss: 0.8103 (0.8155) time: 0.2490 data: 0.1568 max mem: 9390 +Train: [80] [ 600/6250] eta: 0:18:27 lr: 0.000013 grad: 0.1371 (0.1415) loss: 0.8030 (0.8146) time: 0.1863 data: 0.1008 max mem: 9390 +Train: [80] [ 700/6250] eta: 0:18:12 lr: 0.000013 grad: 0.1241 (0.1400) loss: 0.8157 (0.8141) time: 0.2032 data: 0.1132 max mem: 9390 +Train: [80] [ 800/6250] eta: 0:18:02 lr: 0.000013 grad: 0.1310 (0.1385) loss: 0.8107 (0.8137) time: 0.1798 data: 0.0900 max mem: 9390 +Train: [80] [ 900/6250] eta: 0:17:23 lr: 0.000013 grad: 0.1350 (0.1376) loss: 0.8063 (0.8136) time: 0.1953 data: 0.0890 max mem: 9390 +Train: [80] [1000/6250] eta: 0:17:05 lr: 0.000013 grad: 0.1328 (0.1367) loss: 0.8084 (0.8135) time: 0.1449 data: 0.0406 max mem: 9390 +Train: [80] [1100/6250] eta: 0:16:25 lr: 0.000013 grad: 0.1252 (0.1358) loss: 0.8091 (0.8135) time: 0.1748 data: 0.0946 max mem: 9390 +Train: [80] [1200/6250] eta: 0:16:04 lr: 0.000013 grad: 0.1209 (0.1350) loss: 0.8179 (0.8134) time: 0.2243 data: 0.1404 max mem: 9390 +Train: [80] [1300/6250] eta: 0:15:30 lr: 0.000013 grad: 0.1183 (0.1342) loss: 0.8100 (0.8135) time: 0.1409 data: 0.0561 max mem: 9390 +Train: [80] [1400/6250] eta: 0:15:01 lr: 0.000013 grad: 0.1238 (0.1337) loss: 0.8136 (0.8135) time: 0.1515 data: 0.0646 max mem: 9390 +Train: [80] [1500/6250] eta: 0:14:36 lr: 0.000013 grad: 0.1284 (0.1335) loss: 0.8110 (0.8135) time: 0.1217 data: 0.0037 max mem: 9390 +Train: [80] [1600/6250] eta: 0:14:13 lr: 0.000013 grad: 0.1240 (0.1333) loss: 0.8083 (0.8134) time: 0.1665 data: 0.0796 max mem: 9390 +Train: [80] [1700/6250] eta: 0:13:48 lr: 0.000013 grad: 0.1241 (0.1329) loss: 0.8075 (0.8132) time: 0.1701 data: 0.0775 max mem: 9390 +Train: [80] [1800/6250] eta: 0:13:25 lr: 0.000013 grad: 0.1252 (0.1328) loss: 0.8097 (0.8132) time: 0.2070 data: 0.1169 max mem: 9390 +Train: [80] [1900/6250] eta: 0:12:59 lr: 0.000013 grad: 0.1274 (0.1326) loss: 0.8079 (0.8131) time: 0.1464 data: 0.0592 max mem: 9390 +Train: [80] [2000/6250] eta: 0:12:35 lr: 0.000013 grad: 0.1225 (0.1323) loss: 0.8116 (0.8131) time: 0.1240 data: 0.0344 max mem: 9390 +Train: [80] [2100/6250] eta: 0:12:14 lr: 0.000013 grad: 0.1292 (0.1323) loss: 0.8109 (0.8129) time: 0.1507 data: 0.0715 max mem: 9390 +Train: [80] [2200/6250] eta: 0:11:52 lr: 0.000013 grad: 0.1297 (0.1323) loss: 0.8040 (0.8127) time: 0.1378 data: 0.0539 max mem: 9390 +Train: [80] [2300/6250] eta: 0:11:31 lr: 0.000013 grad: 0.1232 (0.1321) loss: 0.8111 (0.8126) time: 0.1684 data: 0.0902 max mem: 9390 +Train: [80] [2400/6250] eta: 0:11:13 lr: 0.000013 grad: 0.1296 (0.1319) loss: 0.8102 (0.8124) time: 0.2177 data: 0.1352 max mem: 9390 +Train: [80] [2500/6250] eta: 0:10:51 lr: 0.000013 grad: 0.1302 (0.1318) loss: 0.8109 (0.8122) time: 0.1109 data: 0.0177 max mem: 9390 +Train: [80] [2600/6250] eta: 0:10:30 lr: 0.000013 grad: 0.1295 (0.1318) loss: 0.8077 (0.8120) time: 0.1519 data: 0.0700 max mem: 9390 +Train: [80] [2700/6250] eta: 0:10:12 lr: 0.000013 grad: 0.1209 (0.1317) loss: 0.8080 (0.8118) time: 0.1331 data: 0.0454 max mem: 9390 +Train: [80] [2800/6250] eta: 0:09:54 lr: 0.000013 grad: 0.1256 (0.1315) loss: 0.8094 (0.8117) time: 0.1670 data: 0.0864 max mem: 9390 +Train: [80] [2900/6250] eta: 0:09:34 lr: 0.000013 grad: 0.1238 (0.1314) loss: 0.8137 (0.8117) time: 0.1478 data: 0.0646 max mem: 9390 +Train: [80] [3000/6250] eta: 0:09:15 lr: 0.000013 grad: 0.1201 (0.1312) loss: 0.8080 (0.8115) time: 0.1520 data: 0.0747 max mem: 9390 +Train: [80] [3100/6250] eta: 0:08:57 lr: 0.000013 grad: 0.1233 (0.1311) loss: 0.8050 (0.8115) time: 0.1681 data: 0.0815 max mem: 9390 +Train: [80] [3200/6250] eta: 0:08:38 lr: 0.000013 grad: 0.1272 (0.1310) loss: 0.8072 (0.8114) time: 0.1692 data: 0.0817 max mem: 9390 +Train: [80] [3300/6250] eta: 0:08:20 lr: 0.000013 grad: 0.1286 (0.1309) loss: 0.8115 (0.8113) time: 0.1589 data: 0.0796 max mem: 9390 +Train: [80] [3400/6250] eta: 0:08:02 lr: 0.000012 grad: 0.1227 (0.1309) loss: 0.8081 (0.8112) time: 0.1606 data: 0.0799 max mem: 9390 +Train: [80] [3500/6250] eta: 0:07:44 lr: 0.000012 grad: 0.1310 (0.1310) loss: 0.8030 (0.8111) time: 0.1674 data: 0.0904 max mem: 9390 +Train: [80] [3600/6250] eta: 0:07:26 lr: 0.000012 grad: 0.1266 (0.1311) loss: 0.8124 (0.8110) time: 0.1456 data: 0.0571 max mem: 9390 +Train: [80] [3700/6250] eta: 0:07:08 lr: 0.000012 grad: 0.1244 (0.1311) loss: 0.8153 (0.8110) time: 0.1534 data: 0.0725 max mem: 9390 +Train: [80] [3800/6250] eta: 0:06:50 lr: 0.000012 grad: 0.1209 (0.1311) loss: 0.8133 (0.8109) time: 0.1671 data: 0.0727 max mem: 9390 +Train: [80] [3900/6250] eta: 0:06:32 lr: 0.000012 grad: 0.1321 (0.1310) loss: 0.8103 (0.8109) time: 0.1508 data: 0.0709 max mem: 9390 +Train: [80] [4000/6250] eta: 0:06:14 lr: 0.000012 grad: 0.1379 (0.1310) loss: 0.8007 (0.8108) time: 0.1709 data: 0.0776 max mem: 9390 +Train: [80] [4100/6250] eta: 0:05:57 lr: 0.000012 grad: 0.1275 (0.1311) loss: 0.8142 (0.8108) time: 0.1376 data: 0.0445 max mem: 9390 +Train: [80] [4200/6250] eta: 0:05:39 lr: 0.000012 grad: 0.1302 (0.1311) loss: 0.8099 (0.8107) time: 0.1675 data: 0.0767 max mem: 9390 +Train: [80] [4300/6250] eta: 0:05:22 lr: 0.000012 grad: 0.1302 (0.1312) loss: 0.8102 (0.8106) time: 0.1394 data: 0.0572 max mem: 9390 +Train: [80] [4400/6250] eta: 0:05:05 lr: 0.000012 grad: 0.1335 (0.1314) loss: 0.8096 (0.8105) time: 0.1407 data: 0.0563 max mem: 9390 +Train: [80] [4500/6250] eta: 0:04:48 lr: 0.000012 grad: 0.1243 (0.1314) loss: 0.8095 (0.8104) time: 0.1417 data: 0.0524 max mem: 9390 +Train: [80] [4600/6250] eta: 0:04:31 lr: 0.000012 grad: 0.1303 (0.1315) loss: 0.8066 (0.8103) time: 0.1091 data: 0.0230 max mem: 9390 +Train: [80] [4700/6250] eta: 0:04:13 lr: 0.000012 grad: 0.1193 (0.1315) loss: 0.8043 (0.8103) time: 0.1400 data: 0.0483 max mem: 9390 +Train: [80] [4800/6250] eta: 0:03:57 lr: 0.000012 grad: 0.1284 (0.1315) loss: 0.8102 (0.8103) time: 0.1771 data: 0.0892 max mem: 9390 +Train: [80] [4900/6250] eta: 0:03:40 lr: 0.000012 grad: 0.1175 (0.1314) loss: 0.8098 (0.8103) time: 0.1447 data: 0.0629 max mem: 9390 +Train: [80] [5000/6250] eta: 0:03:24 lr: 0.000012 grad: 0.1289 (0.1313) loss: 0.8092 (0.8103) time: 0.1661 data: 0.0923 max mem: 9390 +Train: [80] [5100/6250] eta: 0:03:08 lr: 0.000012 grad: 0.1217 (0.1313) loss: 0.8111 (0.8103) time: 0.2879 data: 0.1908 max mem: 9390 +Train: [80] [5200/6250] eta: 0:02:51 lr: 0.000012 grad: 0.1281 (0.1312) loss: 0.8109 (0.8104) time: 0.1411 data: 0.0620 max mem: 9390 +Train: [80] [5300/6250] eta: 0:02:34 lr: 0.000012 grad: 0.1223 (0.1312) loss: 0.8159 (0.8104) time: 0.1645 data: 0.0819 max mem: 9390 +Train: [80] [5400/6250] eta: 0:02:18 lr: 0.000012 grad: 0.1257 (0.1311) loss: 0.8161 (0.8104) time: 0.0997 data: 0.0002 max mem: 9390 +Train: [80] [5500/6250] eta: 0:02:02 lr: 0.000012 grad: 0.1295 (0.1311) loss: 0.8176 (0.8105) time: 0.2445 data: 0.1511 max mem: 9390 +Train: [80] [5600/6250] eta: 0:01:45 lr: 0.000012 grad: 0.1276 (0.1310) loss: 0.8123 (0.8105) time: 0.1759 data: 0.0905 max mem: 9390 +Train: [80] [5700/6250] eta: 0:01:29 lr: 0.000012 grad: 0.1221 (0.1310) loss: 0.8083 (0.8105) time: 0.1560 data: 0.0699 max mem: 9390 +Train: [80] [5800/6250] eta: 0:01:13 lr: 0.000012 grad: 0.1217 (0.1310) loss: 0.8159 (0.8106) time: 0.1826 data: 0.0736 max mem: 9390 +Train: [80] [5900/6250] eta: 0:00:56 lr: 0.000012 grad: 0.1222 (0.1310) loss: 0.8141 (0.8106) time: 0.1328 data: 0.0547 max mem: 9390 +Train: [80] [6000/6250] eta: 0:00:40 lr: 0.000012 grad: 0.1339 (0.1310) loss: 0.8071 (0.8106) time: 0.1433 data: 0.0598 max mem: 9390 +Train: [80] [6100/6250] eta: 0:00:24 lr: 0.000012 grad: 0.1291 (0.1310) loss: 0.8152 (0.8107) time: 0.1651 data: 0.0859 max mem: 9390 +Train: [80] [6200/6250] eta: 0:00:08 lr: 0.000012 grad: 0.1225 (0.1310) loss: 0.8154 (0.8108) time: 0.1303 data: 0.0501 max mem: 9390 +Train: [80] [6249/6250] eta: 0:00:00 lr: 0.000012 grad: 0.1246 (0.1310) loss: 0.8162 (0.8108) time: 0.1330 data: 0.0506 max mem: 9390 +Train: [80] Total time: 0:16:56 (0.1627 s / it) +Averaged stats: lr: 0.000012 grad: 0.1246 (0.1310) loss: 0.8162 (0.8108) +Eval (hcp-train-subset): [80] [ 0/62] eta: 0:04:26 loss: 0.8345 (0.8345) time: 4.2959 data: 4.2669 max mem: 9390 +Eval (hcp-train-subset): [80] [61/62] eta: 0:00:00 loss: 0.8188 (0.8228) time: 0.1312 data: 0.1063 max mem: 9390 +Eval (hcp-train-subset): [80] Total time: 0:00:13 (0.2108 s / it) +Averaged stats (hcp-train-subset): loss: 0.8188 (0.8228) +Eval (hcp-val): [80] [ 0/62] eta: 0:03:17 loss: 0.8275 (0.8275) time: 3.1870 data: 3.1195 max mem: 9390 +Eval (hcp-val): [80] [61/62] eta: 0:00:00 loss: 0.8280 (0.8301) time: 0.1450 data: 0.1196 max mem: 9390 +Eval (hcp-val): [80] Total time: 0:00:12 (0.2091 s / it) +Averaged stats (hcp-val): loss: 0.8280 (0.8301) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +Train: [81] [ 0/6250] eta: 10:33:08 lr: 0.000012 grad: 0.1758 (0.1758) loss: 0.7791 (0.7791) time: 6.0782 data: 5.9724 max mem: 9390 +Train: [81] [ 100/6250] eta: 0:20:10 lr: 0.000012 grad: 0.1221 (0.1511) loss: 0.8287 (0.8226) time: 0.1384 data: 0.0551 max mem: 9390 +Train: [81] [ 200/6250] eta: 0:17:37 lr: 0.000012 grad: 0.1169 (0.1436) loss: 0.8256 (0.8239) time: 0.1413 data: 0.0537 max mem: 9390 +Train: [81] [ 300/6250] eta: 0:16:30 lr: 0.000012 grad: 0.1217 (0.1378) loss: 0.8217 (0.8238) time: 0.1516 data: 0.0659 max mem: 9390 +Train: [81] [ 400/6250] eta: 0:15:46 lr: 0.000012 grad: 0.1311 (0.1358) loss: 0.8194 (0.8227) time: 0.1406 data: 0.0611 max mem: 9390 +Train: [81] [ 500/6250] eta: 0:14:58 lr: 0.000012 grad: 0.1304 (0.1366) loss: 0.8153 (0.8209) time: 0.1287 data: 0.0387 max mem: 9390 +Train: [81] [ 600/6250] eta: 0:14:19 lr: 0.000012 grad: 0.1438 (0.1368) loss: 0.8102 (0.8194) time: 0.1379 data: 0.0539 max mem: 9390 +Train: [81] [ 700/6250] eta: 0:13:50 lr: 0.000012 grad: 0.1273 (0.1363) loss: 0.8168 (0.8181) time: 0.1304 data: 0.0362 max mem: 9390 +Train: [81] [ 800/6250] eta: 0:13:31 lr: 0.000012 grad: 0.1150 (0.1356) loss: 0.8136 (0.8174) time: 0.1593 data: 0.0662 max mem: 9390 +Train: [81] [ 900/6250] eta: 0:13:26 lr: 0.000012 grad: 0.1233 (0.1354) loss: 0.8104 (0.8167) time: 0.1580 data: 0.0753 max mem: 9390 +Train: [81] [1000/6250] eta: 0:13:13 lr: 0.000012 grad: 0.1301 (0.1350) loss: 0.8054 (0.8161) time: 0.1598 data: 0.0760 max mem: 9390 +Train: [81] [1100/6250] eta: 0:12:57 lr: 0.000012 grad: 0.1287 (0.1346) loss: 0.8124 (0.8157) time: 0.1325 data: 0.0508 max mem: 9390 +Train: [81] [1200/6250] eta: 0:12:39 lr: 0.000012 grad: 0.1267 (0.1346) loss: 0.8119 (0.8152) time: 0.1409 data: 0.0585 max mem: 9390 +Train: [81] [1300/6250] eta: 0:12:22 lr: 0.000012 grad: 0.1220 (0.1342) loss: 0.8175 (0.8149) time: 0.1540 data: 0.0771 max mem: 9390 +Train: [81] [1400/6250] eta: 0:12:04 lr: 0.000012 grad: 0.1255 (0.1338) loss: 0.8101 (0.8146) time: 0.1000 data: 0.0095 max mem: 9390 +Train: [81] [1500/6250] eta: 0:11:47 lr: 0.000012 grad: 0.1303 (0.1338) loss: 0.8056 (0.8141) time: 0.1466 data: 0.0636 max mem: 9390 +Train: [81] [1600/6250] eta: 0:11:30 lr: 0.000012 grad: 0.1287 (0.1337) loss: 0.8073 (0.8137) time: 0.1352 data: 0.0512 max mem: 9390 +Train: [81] [1700/6250] eta: 0:11:16 lr: 0.000012 grad: 0.1297 (0.1336) loss: 0.8064 (0.8133) time: 0.1265 data: 0.0524 max mem: 9390 +Train: [81] [1800/6250] eta: 0:11:01 lr: 0.000012 grad: 0.1343 (0.1337) loss: 0.8115 (0.8131) time: 0.1560 data: 0.0778 max mem: 9390 +Train: [81] [1900/6250] eta: 0:10:45 lr: 0.000012 grad: 0.1211 (0.1336) loss: 0.8094 (0.8129) time: 0.1711 data: 0.0890 max mem: 9390 +Train: [81] [2000/6250] eta: 0:10:32 lr: 0.000012 grad: 0.1336 (0.1337) loss: 0.8050 (0.8127) time: 0.0881 data: 0.0003 max mem: 9390 +Train: [81] [2100/6250] eta: 0:10:15 lr: 0.000012 grad: 0.1280 (0.1336) loss: 0.8134 (0.8125) time: 0.1125 data: 0.0299 max mem: 9390 +Train: [81] [2200/6250] eta: 0:10:00 lr: 0.000012 grad: 0.1323 (0.1336) loss: 0.8042 (0.8124) time: 0.1124 data: 0.0343 max mem: 9390 +Train: [81] [2300/6250] eta: 0:09:45 lr: 0.000011 grad: 0.1288 (0.1336) loss: 0.8104 (0.8122) time: 0.1758 data: 0.0930 max mem: 9390 +Train: [81] [2400/6250] eta: 0:09:28 lr: 0.000011 grad: 0.1330 (0.1336) loss: 0.8053 (0.8120) time: 0.1431 data: 0.0619 max mem: 9390 +Train: [81] [2500/6250] eta: 0:09:13 lr: 0.000011 grad: 0.1368 (0.1338) loss: 0.8025 (0.8118) time: 0.1612 data: 0.0761 max mem: 9390 +Train: [81] [2600/6250] eta: 0:08:57 lr: 0.000011 grad: 0.1303 (0.1339) loss: 0.8058 (0.8117) time: 0.1173 data: 0.0344 max mem: 9390 +Train: [81] [2700/6250] eta: 0:08:41 lr: 0.000011 grad: 0.1301 (0.1338) loss: 0.8052 (0.8115) time: 0.1461 data: 0.0657 max mem: 9390 +Train: [81] [2800/6250] eta: 0:08:25 lr: 0.000011 grad: 0.1341 (0.1338) loss: 0.8043 (0.8114) time: 0.1119 data: 0.0291 max mem: 9390 +Train: [81] [2900/6250] eta: 0:08:10 lr: 0.000011 grad: 0.1298 (0.1340) loss: 0.8053 (0.8112) time: 0.1441 data: 0.0683 max mem: 9390 +Train: [81] [3000/6250] eta: 0:07:55 lr: 0.000011 grad: 0.1317 (0.1340) loss: 0.8075 (0.8111) time: 0.1305 data: 0.0434 max mem: 9390 +Train: [81] [3100/6250] eta: 0:07:40 lr: 0.000011 grad: 0.1347 (0.1341) loss: 0.8030 (0.8110) time: 0.1526 data: 0.0665 max mem: 9390 +Train: [81] [3200/6250] eta: 0:07:25 lr: 0.000011 grad: 0.1335 (0.1341) loss: 0.8121 (0.8109) time: 0.1397 data: 0.0565 max mem: 9390 +Train: [81] [3300/6250] eta: 0:07:10 lr: 0.000011 grad: 0.1294 (0.1341) loss: 0.8065 (0.8108) time: 0.1518 data: 0.0680 max mem: 9390 +Train: [81] [3400/6250] eta: 0:06:54 lr: 0.000011 grad: 0.1375 (0.1341) loss: 0.8050 (0.8106) time: 0.1406 data: 0.0495 max mem: 9390 +Train: [81] [3500/6250] eta: 0:06:40 lr: 0.000011 grad: 0.1304 (0.1342) loss: 0.8039 (0.8105) time: 0.1463 data: 0.0689 max mem: 9390 +Train: [81] [3600/6250] eta: 0:06:25 lr: 0.000011 grad: 0.1245 (0.1342) loss: 0.8107 (0.8105) time: 0.1480 data: 0.0657 max mem: 9390 +Train: [81] [3700/6250] eta: 0:06:10 lr: 0.000011 grad: 0.1377 (0.1343) loss: 0.8084 (0.8104) time: 0.1531 data: 0.0722 max mem: 9390 +Train: [81] [3800/6250] eta: 0:06:00 lr: 0.000011 grad: 0.1222 (0.1343) loss: 0.8045 (0.8104) time: 0.1846 data: 0.1055 max mem: 9390 +Train: [81] [3900/6250] eta: 0:05:49 lr: 0.000011 grad: 0.1226 (0.1342) loss: 0.8130 (0.8104) time: 0.1252 data: 0.0097 max mem: 9390 +Train: [81] [4000/6250] eta: 0:05:41 lr: 0.000011 grad: 0.1285 (0.1341) loss: 0.8144 (0.8104) time: 0.2959 data: 0.1942 max mem: 9390 +Train: [81] [4100/6250] eta: 0:05:28 lr: 0.000011 grad: 0.1336 (0.1341) loss: 0.8091 (0.8104) time: 0.1228 data: 0.0003 max mem: 9390 +Train: [81] [4200/6250] eta: 0:05:13 lr: 0.000011 grad: 0.1348 (0.1341) loss: 0.8009 (0.8104) time: 0.1281 data: 0.0412 max mem: 9390 +Train: [81] [4300/6250] eta: 0:05:01 lr: 0.000011 grad: 0.1283 (0.1342) loss: 0.8114 (0.8103) time: 0.1058 data: 0.0002 max mem: 9390 +Train: [81] [4400/6250] eta: 0:04:46 lr: 0.000011 grad: 0.1274 (0.1342) loss: 0.8073 (0.8103) time: 0.1763 data: 0.1017 max mem: 9390 +Train: [81] [4500/6250] eta: 0:04:31 lr: 0.000011 grad: 0.1330 (0.1342) loss: 0.8116 (0.8103) time: 0.1624 data: 0.0714 max mem: 9390 +Train: [81] [4600/6250] eta: 0:04:16 lr: 0.000011 grad: 0.1306 (0.1342) loss: 0.8035 (0.8103) time: 0.1508 data: 0.0394 max mem: 9390 +Train: [81] [4700/6250] eta: 0:04:02 lr: 0.000011 grad: 0.1370 (0.1343) loss: 0.8049 (0.8102) time: 0.2224 data: 0.1255 max mem: 9390 +Train: [81] [4800/6250] eta: 0:03:47 lr: 0.000011 grad: 0.1318 (0.1344) loss: 0.8115 (0.8102) time: 0.1551 data: 0.0628 max mem: 9390 +Train: [81] [4900/6250] eta: 0:03:32 lr: 0.000011 grad: 0.1281 (0.1344) loss: 0.8107 (0.8101) time: 0.1799 data: 0.0810 max mem: 9390 +Train: [81] [5000/6250] eta: 0:03:16 lr: 0.000011 grad: 0.1274 (0.1344) loss: 0.8122 (0.8102) time: 0.1773 data: 0.0607 max mem: 9390 +Train: [81] [5100/6250] eta: 0:03:01 lr: 0.000011 grad: 0.1307 (0.1345) loss: 0.8115 (0.8101) time: 0.1819 data: 0.1032 max mem: 9390 +Train: [81] [5200/6250] eta: 0:02:45 lr: 0.000011 grad: 0.1281 (0.1345) loss: 0.8140 (0.8101) time: 0.1689 data: 0.0804 max mem: 9390 +Train: [81] [5300/6250] eta: 0:02:30 lr: 0.000011 grad: 0.1321 (0.1345) loss: 0.8124 (0.8101) time: 0.1478 data: 0.0609 max mem: 9390 +Train: [81] [5400/6250] eta: 0:02:14 lr: 0.000011 grad: 0.1394 (0.1346) loss: 0.8083 (0.8101) time: 0.1548 data: 0.0650 max mem: 9390 +Train: [81] [5500/6250] eta: 0:01:59 lr: 0.000011 grad: 0.1364 (0.1346) loss: 0.8060 (0.8101) time: 0.1145 data: 0.0003 max mem: 9390 +Train: [81] [5600/6250] eta: 0:01:43 lr: 0.000011 grad: 0.1327 (0.1346) loss: 0.8089 (0.8102) time: 0.1309 data: 0.0407 max mem: 9390 +Train: [81] [5700/6250] eta: 0:01:27 lr: 0.000011 grad: 0.1257 (0.1347) loss: 0.8146 (0.8102) time: 0.1742 data: 0.0850 max mem: 9390 +Train: [81] [5800/6250] eta: 0:01:11 lr: 0.000011 grad: 0.1344 (0.1347) loss: 0.8057 (0.8102) time: 0.1457 data: 0.0561 max mem: 9390 +Train: [81] [5900/6250] eta: 0:00:55 lr: 0.000011 grad: 0.1333 (0.1347) loss: 0.8104 (0.8102) time: 0.2084 data: 0.0868 max mem: 9390 +Train: [81] [6000/6250] eta: 0:00:40 lr: 0.000011 grad: 0.1332 (0.1347) loss: 0.8091 (0.8102) time: 0.1786 data: 0.0922 max mem: 9390 +Train: [81] [6100/6250] eta: 0:00:24 lr: 0.000011 grad: 0.1290 (0.1347) loss: 0.8093 (0.8102) time: 0.2488 data: 0.1251 max mem: 9390 +Train: [81] [6200/6250] eta: 0:00:08 lr: 0.000011 grad: 0.1345 (0.1346) loss: 0.8056 (0.8102) time: 0.1197 data: 0.0328 max mem: 9390 +Train: [81] [6249/6250] eta: 0:00:00 lr: 0.000011 grad: 0.1374 (0.1347) loss: 0.8081 (0.8103) time: 0.3015 data: 0.2227 max mem: 9390 +Train: [81] Total time: 0:16:55 (0.1625 s / it) +Averaged stats: lr: 0.000011 grad: 0.1374 (0.1347) loss: 0.8081 (0.8103) +Eval (hcp-train-subset): [81] [ 0/62] eta: 0:03:27 loss: 0.8345 (0.8345) time: 3.3495 data: 3.2596 max mem: 9390 +Eval (hcp-train-subset): [81] [61/62] eta: 0:00:00 loss: 0.8206 (0.8231) time: 0.1244 data: 0.0976 max mem: 9390 +Eval (hcp-train-subset): [81] Total time: 0:00:13 (0.2159 s / it) +Averaged stats (hcp-train-subset): loss: 0.8206 (0.8231) +Eval (hcp-val): [81] [ 0/62] eta: 0:03:53 loss: 0.8247 (0.8247) time: 3.7654 data: 3.6972 max mem: 9390 +Eval (hcp-val): [81] [61/62] eta: 0:00:00 loss: 0.8272 (0.8297) time: 0.1194 data: 0.0923 max mem: 9390 +Eval (hcp-val): [81] Total time: 0:00:13 (0.2178 s / it) +Averaged stats (hcp-val): loss: 0.8272 (0.8297) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +Train: [82] [ 0/6250] eta: 9:09:09 lr: 0.000011 grad: 0.1038 (0.1038) loss: 0.8362 (0.8362) time: 5.2719 data: 5.1617 max mem: 9390 +Train: [82] [ 100/6250] eta: 0:21:13 lr: 0.000011 grad: 0.1733 (0.2026) loss: 0.8168 (0.8158) time: 0.1714 data: 0.0712 max mem: 9390 +Train: [82] [ 200/6250] eta: 0:18:54 lr: 0.000011 grad: 0.1305 (0.1806) loss: 0.8170 (0.8133) time: 0.1480 data: 0.0624 max mem: 9390 +Train: [82] [ 300/6250] eta: 0:17:55 lr: 0.000011 grad: 0.1428 (0.1713) loss: 0.8054 (0.8109) time: 0.1956 data: 0.1050 max mem: 9390 +Train: [82] [ 400/6250] eta: 0:17:08 lr: 0.000011 grad: 0.1375 (0.1653) loss: 0.8073 (0.8087) time: 0.1538 data: 0.0683 max mem: 9390 +Train: [82] [ 500/6250] eta: 0:16:46 lr: 0.000011 grad: 0.1339 (0.1624) loss: 0.8069 (0.8077) time: 0.1200 data: 0.0352 max mem: 9390 +Train: [82] [ 600/6250] eta: 0:16:11 lr: 0.000011 grad: 0.1308 (0.1583) loss: 0.8175 (0.8080) time: 0.1693 data: 0.0838 max mem: 9390 +Train: [82] [ 700/6250] eta: 0:15:49 lr: 0.000011 grad: 0.1327 (0.1556) loss: 0.8139 (0.8086) time: 0.1136 data: 0.0046 max mem: 9390 +Train: [82] [ 800/6250] eta: 0:15:50 lr: 0.000011 grad: 0.1280 (0.1532) loss: 0.8131 (0.8091) time: 0.2177 data: 0.1172 max mem: 9390 +Train: [82] [ 900/6250] eta: 0:16:29 lr: 0.000011 grad: 0.1296 (0.1508) loss: 0.8142 (0.8095) time: 0.2537 data: 0.1475 max mem: 9390 +Train: [82] [1000/6250] eta: 0:15:50 lr: 0.000011 grad: 0.1287 (0.1492) loss: 0.8144 (0.8099) time: 0.1643 data: 0.0816 max mem: 9390 +Train: [82] [1100/6250] eta: 0:15:29 lr: 0.000011 grad: 0.1326 (0.1480) loss: 0.8118 (0.8102) time: 0.2020 data: 0.1175 max mem: 9390 +Train: [82] [1200/6250] eta: 0:15:25 lr: 0.000011 grad: 0.1260 (0.1468) loss: 0.8154 (0.8105) time: 0.1845 data: 0.0979 max mem: 9390 +Train: [82] [1300/6250] eta: 0:14:51 lr: 0.000011 grad: 0.1301 (0.1456) loss: 0.8158 (0.8107) time: 0.1149 data: 0.0295 max mem: 9390 +Train: [82] [1400/6250] eta: 0:14:39 lr: 0.000010 grad: 0.1337 (0.1450) loss: 0.8150 (0.8108) time: 0.0951 data: 0.0004 max mem: 9390 +Train: [82] [1500/6250] eta: 0:14:16 lr: 0.000010 grad: 0.1346 (0.1442) loss: 0.8019 (0.8107) time: 0.1501 data: 0.0561 max mem: 9390 +Train: [82] [1600/6250] eta: 0:13:57 lr: 0.000010 grad: 0.1295 (0.1434) loss: 0.8102 (0.8108) time: 0.1339 data: 0.0479 max mem: 9390 +Train: [82] [1700/6250] eta: 0:13:49 lr: 0.000010 grad: 0.1334 (0.1429) loss: 0.8110 (0.8108) time: 0.2236 data: 0.1151 max mem: 9390 +Train: [82] [1800/6250] eta: 0:13:23 lr: 0.000010 grad: 0.1233 (0.1424) loss: 0.8180 (0.8109) time: 0.1908 data: 0.1049 max mem: 9390 +Train: [82] [1900/6250] eta: 0:13:02 lr: 0.000010 grad: 0.1291 (0.1419) loss: 0.8078 (0.8108) time: 0.1894 data: 0.0883 max mem: 9390 +Train: [82] [2000/6250] eta: 0:12:43 lr: 0.000010 grad: 0.1242 (0.1416) loss: 0.8102 (0.8108) time: 0.1192 data: 0.0109 max mem: 9390 +Train: [82] [2100/6250] eta: 0:12:25 lr: 0.000010 grad: 0.1201 (0.1413) loss: 0.8140 (0.8107) time: 0.1039 data: 0.0158 max mem: 9390 +Train: [82] [2200/6250] eta: 0:12:19 lr: 0.000010 grad: 0.1318 (0.1409) loss: 0.8119 (0.8108) time: 0.0821 data: 0.0002 max mem: 9390 +Train: [82] [2300/6250] eta: 0:11:55 lr: 0.000010 grad: 0.1315 (0.1404) loss: 0.8114 (0.8108) time: 0.1648 data: 0.0750 max mem: 9390 +Train: [82] [2400/6250] eta: 0:11:35 lr: 0.000010 grad: 0.1266 (0.1400) loss: 0.8169 (0.8109) time: 0.1695 data: 0.0867 max mem: 9390 +Train: [82] [2500/6250] eta: 0:11:15 lr: 0.000010 grad: 0.1322 (0.1398) loss: 0.8130 (0.8110) time: 0.1512 data: 0.0645 max mem: 9390 +Train: [82] [2600/6250] eta: 0:10:55 lr: 0.000010 grad: 0.1302 (0.1396) loss: 0.8133 (0.8110) time: 0.1676 data: 0.0857 max mem: 9390 +Train: [82] [2700/6250] eta: 0:10:41 lr: 0.000010 grad: 0.1367 (0.1396) loss: 0.8121 (0.8110) time: 0.2757 data: 0.1823 max mem: 9390 +Train: [82] [2800/6250] eta: 0:10:19 lr: 0.000010 grad: 0.1256 (0.1395) loss: 0.8119 (0.8110) time: 0.1569 data: 0.0779 max mem: 9390 +Train: [82] [2900/6250] eta: 0:10:04 lr: 0.000010 grad: 0.1321 (0.1394) loss: 0.8066 (0.8110) time: 0.2345 data: 0.1537 max mem: 9390 +Train: [82] [3000/6250] eta: 0:09:54 lr: 0.000010 grad: 0.1350 (0.1393) loss: 0.8145 (0.8111) time: 0.4912 data: 0.3995 max mem: 9390 +Train: [82] [3100/6250] eta: 0:09:37 lr: 0.000010 grad: 0.1267 (0.1390) loss: 0.8131 (0.8113) time: 0.2662 data: 0.1660 max mem: 9390 +Train: [82] [3200/6250] eta: 0:09:15 lr: 0.000010 grad: 0.1302 (0.1388) loss: 0.8121 (0.8114) time: 0.1518 data: 0.0607 max mem: 9390 +Train: [82] [3300/6250] eta: 0:08:55 lr: 0.000010 grad: 0.1164 (0.1387) loss: 0.8198 (0.8114) time: 0.2044 data: 0.1213 max mem: 9390 +Train: [82] [3400/6250] eta: 0:08:34 lr: 0.000010 grad: 0.1288 (0.1385) loss: 0.8141 (0.8115) time: 0.1462 data: 0.0619 max mem: 9390 +Train: [82] [3500/6250] eta: 0:08:14 lr: 0.000010 grad: 0.1318 (0.1384) loss: 0.8101 (0.8116) time: 0.1594 data: 0.0780 max mem: 9390 +Train: [82] [3600/6250] eta: 0:07:55 lr: 0.000010 grad: 0.1260 (0.1383) loss: 0.8115 (0.8116) time: 0.1867 data: 0.0888 max mem: 9390 +Train: [82] [3700/6250] eta: 0:07:40 lr: 0.000010 grad: 0.1319 (0.1383) loss: 0.8168 (0.8116) time: 0.2534 data: 0.1594 max mem: 9390 +Train: [82] [3800/6250] eta: 0:07:24 lr: 0.000010 grad: 0.1403 (0.1382) loss: 0.8045 (0.8116) time: 0.1142 data: 0.0177 max mem: 9390 +Train: [82] [3900/6250] eta: 0:07:09 lr: 0.000010 grad: 0.1313 (0.1381) loss: 0.8160 (0.8116) time: 0.3723 data: 0.2764 max mem: 9390 +Train: [82] [4000/6250] eta: 0:06:50 lr: 0.000010 grad: 0.1286 (0.1380) loss: 0.8169 (0.8116) time: 0.2126 data: 0.1070 max mem: 9390 +Train: [82] [4100/6250] eta: 0:06:33 lr: 0.000010 grad: 0.1256 (0.1378) loss: 0.8114 (0.8116) time: 0.2254 data: 0.1142 max mem: 9390 +Train: [82] [4200/6250] eta: 0:06:20 lr: 0.000010 grad: 0.1332 (0.1377) loss: 0.8111 (0.8116) time: 0.1825 data: 0.0937 max mem: 9390 +Train: [82] [4300/6250] eta: 0:06:01 lr: 0.000010 grad: 0.1268 (0.1375) loss: 0.8164 (0.8116) time: 0.1670 data: 0.0846 max mem: 9390 +Train: [82] [4400/6250] eta: 0:05:42 lr: 0.000010 grad: 0.1245 (0.1374) loss: 0.8165 (0.8116) time: 0.1940 data: 0.0896 max mem: 9390 +Train: [82] [4500/6250] eta: 0:05:25 lr: 0.000010 grad: 0.1347 (0.1374) loss: 0.8053 (0.8116) time: 0.2268 data: 0.1538 max mem: 9390 +Train: [82] [4600/6250] eta: 0:05:04 lr: 0.000010 grad: 0.1339 (0.1373) loss: 0.8074 (0.8116) time: 0.1523 data: 0.0655 max mem: 9390 +Train: [82] [4700/6250] eta: 0:04:45 lr: 0.000010 grad: 0.1312 (0.1372) loss: 0.8150 (0.8116) time: 0.1374 data: 0.0568 max mem: 9390 +Train: [82] [4800/6250] eta: 0:04:25 lr: 0.000010 grad: 0.1359 (0.1372) loss: 0.8123 (0.8116) time: 0.1430 data: 0.0666 max mem: 9390 +Train: [82] [4900/6250] eta: 0:04:06 lr: 0.000010 grad: 0.1340 (0.1372) loss: 0.8097 (0.8115) time: 0.1263 data: 0.0503 max mem: 9390 +Train: [82] [5000/6250] eta: 0:03:47 lr: 0.000010 grad: 0.1383 (0.1371) loss: 0.8082 (0.8115) time: 0.1331 data: 0.0573 max mem: 9390 +Train: [82] [5100/6250] eta: 0:03:28 lr: 0.000010 grad: 0.1303 (0.1371) loss: 0.8142 (0.8114) time: 0.1103 data: 0.0345 max mem: 9390 +Train: [82] [5200/6250] eta: 0:03:09 lr: 0.000010 grad: 0.1282 (0.1370) loss: 0.8144 (0.8114) time: 0.1456 data: 0.0691 max mem: 9390 +Train: [82] [5300/6250] eta: 0:02:50 lr: 0.000010 grad: 0.1325 (0.1370) loss: 0.8065 (0.8113) time: 0.1337 data: 0.0575 max mem: 9390 +Train: [82] [5400/6250] eta: 0:02:32 lr: 0.000010 grad: 0.1299 (0.1370) loss: 0.8035 (0.8113) time: 0.1520 data: 0.0737 max mem: 9390 +Train: [82] [5500/6250] eta: 0:02:13 lr: 0.000010 grad: 0.1419 (0.1370) loss: 0.8075 (0.8112) time: 0.1400 data: 0.0659 max mem: 9390 +Train: [82] [5600/6250] eta: 0:01:55 lr: 0.000010 grad: 0.1292 (0.1370) loss: 0.8074 (0.8112) time: 0.1664 data: 0.0913 max mem: 9390 +Train: [82] [5700/6250] eta: 0:01:37 lr: 0.000010 grad: 0.1328 (0.1369) loss: 0.8143 (0.8111) time: 0.1489 data: 0.0715 max mem: 9390 +Train: [82] [5800/6250] eta: 0:01:19 lr: 0.000010 grad: 0.1194 (0.1369) loss: 0.8103 (0.8111) time: 0.1671 data: 0.0914 max mem: 9390 +Train: [82] [5900/6250] eta: 0:01:01 lr: 0.000010 grad: 0.1321 (0.1369) loss: 0.8122 (0.8111) time: 0.1394 data: 0.0631 max mem: 9390 +Train: [82] [6000/6250] eta: 0:00:43 lr: 0.000010 grad: 0.1251 (0.1368) loss: 0.8091 (0.8111) time: 0.1400 data: 0.0588 max mem: 9390 +Train: [82] [6100/6250] eta: 0:00:26 lr: 0.000010 grad: 0.1381 (0.1368) loss: 0.8143 (0.8111) time: 0.1335 data: 0.0609 max mem: 9390 +Train: [82] [6200/6250] eta: 0:00:08 lr: 0.000010 grad: 0.1406 (0.1369) loss: 0.8028 (0.8110) time: 0.1272 data: 0.0436 max mem: 9390 +Train: [82] [6249/6250] eta: 0:00:00 lr: 0.000010 grad: 0.1349 (0.1368) loss: 0.8105 (0.8110) time: 0.1160 data: 0.0365 max mem: 9390 +Train: [82] Total time: 0:18:12 (0.1748 s / it) +Averaged stats: lr: 0.000010 grad: 0.1349 (0.1368) loss: 0.8105 (0.8110) +Eval (hcp-train-subset): [82] [ 0/62] eta: 0:03:19 loss: 0.8302 (0.8302) time: 3.2147 data: 3.1802 max mem: 9390 +Eval (hcp-train-subset): [82] [61/62] eta: 0:00:00 loss: 0.8183 (0.8219) time: 0.1155 data: 0.0893 max mem: 9390 +Eval (hcp-train-subset): [82] Total time: 0:00:10 (0.1714 s / it) +Averaged stats (hcp-train-subset): loss: 0.8183 (0.8219) +Eval (hcp-val): [82] [ 0/62] eta: 0:02:41 loss: 0.8271 (0.8271) time: 2.6125 data: 2.5541 max mem: 9390 +Eval (hcp-val): [82] [61/62] eta: 0:00:00 loss: 0.8283 (0.8299) time: 0.1074 data: 0.0812 max mem: 9390 +Eval (hcp-val): [82] Total time: 0:00:10 (0.1727 s / it) +Averaged stats (hcp-val): loss: 0.8283 (0.8299) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +Train: [83] [ 0/6250] eta: 5:16:21 lr: 0.000010 grad: 0.0803 (0.0803) loss: 0.8663 (0.8663) time: 3.0370 data: 2.8502 max mem: 9390 +Train: [83] [ 100/6250] eta: 0:18:10 lr: 0.000010 grad: 0.1617 (0.1702) loss: 0.7920 (0.8022) time: 0.1414 data: 0.0623 max mem: 9390 +Train: [83] [ 200/6250] eta: 0:15:55 lr: 0.000010 grad: 0.1363 (0.1624) loss: 0.8044 (0.8024) time: 0.1295 data: 0.0510 max mem: 9390 +Train: [83] [ 300/6250] eta: 0:14:43 lr: 0.000010 grad: 0.1282 (0.1551) loss: 0.8069 (0.8048) time: 0.1146 data: 0.0318 max mem: 9390 +Train: [83] [ 400/6250] eta: 0:14:13 lr: 0.000010 grad: 0.1349 (0.1503) loss: 0.8073 (0.8067) time: 0.1583 data: 0.0802 max mem: 9390 +Train: [83] [ 500/6250] eta: 0:13:36 lr: 0.000010 grad: 0.1313 (0.1469) loss: 0.8182 (0.8082) time: 0.1306 data: 0.0536 max mem: 9390 +Train: [83] [ 600/6250] eta: 0:13:13 lr: 0.000010 grad: 0.1269 (0.1449) loss: 0.8103 (0.8091) time: 0.1331 data: 0.0512 max mem: 9390 +Train: [83] [ 700/6250] eta: 0:12:48 lr: 0.000009 grad: 0.1350 (0.1433) loss: 0.8065 (0.8094) time: 0.1321 data: 0.0526 max mem: 9390 +Train: [83] [ 800/6250] eta: 0:12:24 lr: 0.000009 grad: 0.1361 (0.1423) loss: 0.8099 (0.8092) time: 0.1330 data: 0.0573 max mem: 9390 +Train: [83] [ 900/6250] eta: 0:12:06 lr: 0.000009 grad: 0.1300 (0.1411) loss: 0.8140 (0.8097) time: 0.1329 data: 0.0548 max mem: 9390 +Train: [83] [1000/6250] eta: 0:11:43 lr: 0.000009 grad: 0.1274 (0.1404) loss: 0.8139 (0.8097) time: 0.1222 data: 0.0413 max mem: 9390 +Train: [83] [1100/6250] eta: 0:11:24 lr: 0.000009 grad: 0.1341 (0.1400) loss: 0.8021 (0.8097) time: 0.1225 data: 0.0457 max mem: 9390 +Train: [83] [1200/6250] eta: 0:11:06 lr: 0.000009 grad: 0.1302 (0.1395) loss: 0.8017 (0.8096) time: 0.1094 data: 0.0312 max mem: 9390 +Train: [83] [1300/6250] eta: 0:10:50 lr: 0.000009 grad: 0.1373 (0.1391) loss: 0.8104 (0.8097) time: 0.1334 data: 0.0545 max mem: 9390 +Train: [83] [1400/6250] eta: 0:10:34 lr: 0.000009 grad: 0.1348 (0.1387) loss: 0.8064 (0.8097) time: 0.1209 data: 0.0447 max mem: 9390 +Train: [83] [1500/6250] eta: 0:10:19 lr: 0.000009 grad: 0.1207 (0.1382) loss: 0.8118 (0.8097) time: 0.1264 data: 0.0452 max mem: 9390 +Train: [83] [1600/6250] eta: 0:10:06 lr: 0.000009 grad: 0.1214 (0.1376) loss: 0.8123 (0.8098) time: 0.1311 data: 0.0516 max mem: 9390 +Train: [83] [1700/6250] eta: 0:09:51 lr: 0.000009 grad: 0.1258 (0.1371) loss: 0.8114 (0.8099) time: 0.1035 data: 0.0165 max mem: 9390 +Train: [83] [1800/6250] eta: 0:09:36 lr: 0.000009 grad: 0.1248 (0.1369) loss: 0.8134 (0.8101) time: 0.1379 data: 0.0598 max mem: 9390 +Train: [83] [1900/6250] eta: 0:09:21 lr: 0.000009 grad: 0.1382 (0.1370) loss: 0.8107 (0.8101) time: 0.1324 data: 0.0515 max mem: 9390 +Train: [83] [2000/6250] eta: 0:09:05 lr: 0.000009 grad: 0.1317 (0.1369) loss: 0.8166 (0.8101) time: 0.1120 data: 0.0307 max mem: 9390 +Train: [83] [2100/6250] eta: 0:08:51 lr: 0.000009 grad: 0.1385 (0.1371) loss: 0.8117 (0.8101) time: 0.1235 data: 0.0412 max mem: 9390 +Train: [83] [2200/6250] eta: 0:08:37 lr: 0.000009 grad: 0.1369 (0.1371) loss: 0.8063 (0.8101) time: 0.1132 data: 0.0351 max mem: 9390 +Train: [83] [2300/6250] eta: 0:08:23 lr: 0.000009 grad: 0.1304 (0.1370) loss: 0.8096 (0.8101) time: 0.1194 data: 0.0409 max mem: 9390 +Train: [83] [2400/6250] eta: 0:08:10 lr: 0.000009 grad: 0.1338 (0.1370) loss: 0.8080 (0.8102) time: 0.1294 data: 0.0567 max mem: 9390 +Train: [83] [2500/6250] eta: 0:07:56 lr: 0.000009 grad: 0.1268 (0.1369) loss: 0.8173 (0.8103) time: 0.1182 data: 0.0359 max mem: 9390 +Train: [83] [2600/6250] eta: 0:07:43 lr: 0.000009 grad: 0.1361 (0.1370) loss: 0.8118 (0.8102) time: 0.1289 data: 0.0513 max mem: 9390 +Train: [83] [2700/6250] eta: 0:07:30 lr: 0.000009 grad: 0.1288 (0.1370) loss: 0.8165 (0.8103) time: 0.1315 data: 0.0518 max mem: 9390 +Train: [83] [2800/6250] eta: 0:07:16 lr: 0.000009 grad: 0.1342 (0.1371) loss: 0.8147 (0.8104) time: 0.1140 data: 0.0382 max mem: 9390 +Train: [83] [2900/6250] eta: 0:07:03 lr: 0.000009 grad: 0.1436 (0.1371) loss: 0.8113 (0.8104) time: 0.1236 data: 0.0387 max mem: 9390 +Train: [83] [3000/6250] eta: 0:06:50 lr: 0.000009 grad: 0.1415 (0.1371) loss: 0.8108 (0.8104) time: 0.1218 data: 0.0471 max mem: 9390 +Train: [83] [3100/6250] eta: 0:06:37 lr: 0.000009 grad: 0.1372 (0.1371) loss: 0.8085 (0.8105) time: 0.1299 data: 0.0543 max mem: 9390 +Train: [83] [3200/6250] eta: 0:06:23 lr: 0.000009 grad: 0.1350 (0.1371) loss: 0.8159 (0.8105) time: 0.1195 data: 0.0419 max mem: 9390 +Train: [83] [3300/6250] eta: 0:06:09 lr: 0.000009 grad: 0.1328 (0.1371) loss: 0.8111 (0.8106) time: 0.1141 data: 0.0346 max mem: 9390 +Train: [83] [3400/6250] eta: 0:05:57 lr: 0.000009 grad: 0.1322 (0.1371) loss: 0.8070 (0.8106) time: 0.1374 data: 0.0622 max mem: 9390 +Train: [83] [3500/6250] eta: 0:05:44 lr: 0.000009 grad: 0.1496 (0.1372) loss: 0.8051 (0.8106) time: 0.1380 data: 0.0581 max mem: 9390 +Train: [83] [3600/6250] eta: 0:05:31 lr: 0.000009 grad: 0.1400 (0.1373) loss: 0.8113 (0.8106) time: 0.1308 data: 0.0541 max mem: 9390 +Train: [83] [3700/6250] eta: 0:05:19 lr: 0.000009 grad: 0.1292 (0.1372) loss: 0.8167 (0.8107) time: 0.1196 data: 0.0429 max mem: 9390 +Train: [83] [3800/6250] eta: 0:05:06 lr: 0.000009 grad: 0.1345 (0.1371) loss: 0.8112 (0.8107) time: 0.1267 data: 0.0532 max mem: 9390 +Train: [83] [3900/6250] eta: 0:04:53 lr: 0.000009 grad: 0.1230 (0.1370) loss: 0.8140 (0.8107) time: 0.1109 data: 0.0400 max mem: 9390 +Train: [83] [4000/6250] eta: 0:04:41 lr: 0.000009 grad: 0.1373 (0.1370) loss: 0.8100 (0.8107) time: 0.1323 data: 0.0520 max mem: 9390 +Train: [83] [4100/6250] eta: 0:04:28 lr: 0.000009 grad: 0.1394 (0.1370) loss: 0.8038 (0.8107) time: 0.1207 data: 0.0460 max mem: 9390 +Train: [83] [4200/6250] eta: 0:04:15 lr: 0.000009 grad: 0.1305 (0.1371) loss: 0.8083 (0.8107) time: 0.1290 data: 0.0553 max mem: 9390 +Train: [83] [4300/6250] eta: 0:04:03 lr: 0.000009 grad: 0.1345 (0.1372) loss: 0.8119 (0.8107) time: 0.1332 data: 0.0518 max mem: 9390 +Train: [83] [4400/6250] eta: 0:03:50 lr: 0.000009 grad: 0.1389 (0.1372) loss: 0.8153 (0.8107) time: 0.1218 data: 0.0326 max mem: 9390 +Train: [83] [4500/6250] eta: 0:03:38 lr: 0.000009 grad: 0.1351 (0.1372) loss: 0.8087 (0.8107) time: 0.1402 data: 0.0555 max mem: 9390 +Train: [83] [4600/6250] eta: 0:03:26 lr: 0.000009 grad: 0.1374 (0.1373) loss: 0.8030 (0.8107) time: 0.1319 data: 0.0524 max mem: 9390 +Train: [83] [4700/6250] eta: 0:03:13 lr: 0.000009 grad: 0.1348 (0.1373) loss: 0.8133 (0.8107) time: 0.1271 data: 0.0477 max mem: 9390 +Train: [83] [4800/6250] eta: 0:03:01 lr: 0.000009 grad: 0.1373 (0.1372) loss: 0.8106 (0.8108) time: 0.1444 data: 0.0605 max mem: 9390 +Train: [83] [4900/6250] eta: 0:02:49 lr: 0.000009 grad: 0.1320 (0.1372) loss: 0.8137 (0.8109) time: 0.1258 data: 0.0470 max mem: 9390 +Train: [83] [5000/6250] eta: 0:02:36 lr: 0.000009 grad: 0.1312 (0.1372) loss: 0.8205 (0.8109) time: 0.1202 data: 0.0362 max mem: 9390 +Train: [83] [5100/6250] eta: 0:02:24 lr: 0.000009 grad: 0.1471 (0.1372) loss: 0.8100 (0.8110) time: 0.1329 data: 0.0482 max mem: 9390 +Train: [83] [5200/6250] eta: 0:02:11 lr: 0.000009 grad: 0.1330 (0.1373) loss: 0.8155 (0.8110) time: 0.1315 data: 0.0538 max mem: 9390 +Train: [83] [5300/6250] eta: 0:01:59 lr: 0.000009 grad: 0.1271 (0.1372) loss: 0.8162 (0.8111) time: 0.1225 data: 0.0307 max mem: 9390 +Train: [83] [5400/6250] eta: 0:01:46 lr: 0.000009 grad: 0.1337 (0.1372) loss: 0.8188 (0.8111) time: 0.1358 data: 0.0510 max mem: 9390 +Train: [83] [5500/6250] eta: 0:01:34 lr: 0.000009 grad: 0.1410 (0.1373) loss: 0.8046 (0.8111) time: 0.1293 data: 0.0393 max mem: 9390 +Train: [83] [5600/6250] eta: 0:01:21 lr: 0.000009 grad: 0.1341 (0.1373) loss: 0.8149 (0.8112) time: 0.1213 data: 0.0325 max mem: 9390 +Train: [83] [5700/6250] eta: 0:01:09 lr: 0.000009 grad: 0.1374 (0.1374) loss: 0.8056 (0.8112) time: 0.1399 data: 0.0624 max mem: 9390 +Train: [83] [5800/6250] eta: 0:00:56 lr: 0.000009 grad: 0.1407 (0.1375) loss: 0.8061 (0.8111) time: 0.1290 data: 0.0452 max mem: 9390 +Train: [83] [5900/6250] eta: 0:00:44 lr: 0.000009 grad: 0.1380 (0.1375) loss: 0.8107 (0.8111) time: 0.1029 data: 0.0181 max mem: 9390 +Train: [83] [6000/6250] eta: 0:00:31 lr: 0.000009 grad: 0.1337 (0.1375) loss: 0.8096 (0.8112) time: 0.1899 data: 0.0811 max mem: 9390 +Train: [83] [6100/6250] eta: 0:00:19 lr: 0.000009 grad: 0.1356 (0.1375) loss: 0.8084 (0.8112) time: 0.1988 data: 0.1053 max mem: 9390 +pretraining fmri mae +start: 2026-04-01 15:19:02 +cwd: /data/connor/fmri-fm +sha: 7f4cedc35609f6857314e0d1ea6657523f17ddeb, status: has uncommitted changes, branch: dev/clane9 +config: +name: input_space_v3/flat_lr1e-3_4/pretrain +notes: input_space ablation v3 flat_lr1e-3_4; use tube masking and on-disk data (input_space=flat + base_lr=1e-3 seed=5404) +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain +input_space: flat +patch_size: 16 +num_frames: 16 +t_patch_size: 4 +mask_ratio: 0.9 +pred_mask_ratio: null +masking: tube +masking_kwargs: {} +mask_patch_size: null +model: mae_vit_base +model_kwargs: + decoding: attn + pos_embed: sep + target_norm: null + pca_norm_nc: 2 + t_pred_stride: 2 + no_decode_pos: true + mask_drop_scale: false + pred_edge_pad: 0 + gauss_sigma: null + class_token: true + reg_tokens: 0 + no_embed_class: true + head_init_scale: 0.0 + decoder_depth: 4 + drop_path_rate: 0.0 +datasets: + hcp-train: + type: wds + url: /data/fmri-datasets/pretrain/hcpya-all.${input_space}.wds/hcpya-all-${input_space}-{00000..01799}.tar + clipping: random + clipping_kwargs: + oversample: 4.0 + shuffle: true + buffer_size: 2000 + samples_per_epoch: 200000 + hcp-train-subset: + type: arrow + root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/validation + split_range: + - 0 + - 2000 + shuffle: false + hcp-val: + type: arrow + root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/test + split_range: + - 0 + - 2000 + shuffle: false +train_dataset: hcp-train +eval_datasets: +- hcp-train-subset +- hcp-val +val_dataset: null +clip_vmax: 3.0 +normalize: frame +tr_scale: null +crop_scale: null +crop_aspect: null +gray_jitter: null +num_workers: 16 +epochs: 100 +batch_size: 32 +accum_iter: 1 +base_lr: 0.001 +min_lr: 0.0 +warmup_epochs: 5 +weight_decay: 0.05 +betas: +- 0.9 +- 0.95 +clip_grad: 1.0 +amp: true +amp_dtype: float16 +ckpt: null +resume: true +auto_resume: true +start_epoch: 0 +max_checkpoints: 0 +checkpoint_period: null +plot_period: 5 +device: cuda +presend_cuda: false +seed: 5404 +debug: false +wandb: true +wandb_entity: null +wandb_project: fMRI-foundation-model +rank: 0 +world_size: 1 +gpu: 0 +distributed: true +dist_backend: nccl +in_chans: 1 +img_size: +- 224 +- 560 + +train transform: +Compose( + ToTensor() + TemporalCenterCrop(num_frames=16) + Normalize(mode='frame') + Clip(vmax=3.0) + FlatUnmask((224, 560)) +) +val transform: +Compose( + ToTensor() + TemporalCenterCrop(num_frames=16) + Normalize(mode='frame') + Clip(vmax=3.0) + FlatUnmask((224, 560)) +) +mask generator: +TubeMasking( + mask_ratio=0.9 + (patchify): Patchify2D((224, 560), (16, 16), in_chans=1) +) +loading dataset: hcp-train + +type: wds +url: /data/fmri-datasets/pretrain/hcpya-all.${input_space}.wds/hcpya-all-${input_space}-{00000..01799}.tar +clipping: random +clipping_kwargs: + oversample: 4.0 +shuffle: true +buffer_size: 2000 +samples_per_epoch: 200000 + +loading dataset: hcp-train-subset + +type: arrow +root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/validation +split_range: +- 0 +- 2000 +shuffle: false + +split indices: [899, 472, 767, 116, 1265, 1852, 300, 1335, 361, 1560] +loading dataset: hcp-val + +type: arrow +root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/test +split_range: +- 0 +- 2000 +shuffle: false + +split indices: [1075, 1189, 738, 1350, 965, 1964, 1367, 1183, 1619, 1407] +model: +MaskedAutoencoderViT( + decoding=attn, t_pred_stride=2, pred_edge_pad=0, no_decode_pos=True + (encoder): MaskedEncoder( + class_token=True, reg_tokens=0, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) + (pred_patchify): StridedPatchify3D((16, 224, 560), (2, 16, 16), in_chans=1, t_stride=2) + (decoder): MaskedDecoder( + cross_decode=False, class_token=True, no_embed_class=True + (pos_embed): SeparablePosEmbed(512, (4, 14, 35)) + (proj): Linear(in_features=768, out_features=512, bias=True) + (blocks): ModuleList( + (0-3): 4 x Block( + (norm1): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=16 + (q): Linear(in_features=512, out_features=512, bias=True) + (k): Linear(in_features=512, out_features=512, bias=True) + (v): Linear(in_features=512, out_features=512, bias=True) + (proj): Linear(in_features=512, out_features=512, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=512, out_features=2048, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=2048, out_features=512, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (head): Linear(in_features=512, out_features=512, bias=True) + ) +) +num params: 99.7M +total batch size: 32 = 32 bs per gpu x 1 accum x 1 gpus +lr: 1.25e-04 = 1.00e-03 x 32 / 256 +full schedule: epochs = 100 (steps = 625000) +warmup: epochs = 5 (steps = 31250) +loaded model state from checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +loaded optimizer state, resuming training from 83 +start training for 100 epochs +Train: [83] [ 0/6250] eta: 15:14:51 lr: 0.000010 grad: 0.0795 (0.0795) loss: 0.8713 (0.8713) time: 8.7827 data: 7.1275 max mem: 9353 +Train: [83] [ 100/6250] eta: 0:39:19 lr: 0.000010 grad: 0.1025 (0.1302) loss: 0.8387 (0.8381) time: 0.3911 data: 0.1707 max mem: 9390 +Train: [83] [ 200/6250] eta: 0:33:00 lr: 0.000010 grad: 0.1214 (0.1283) loss: 0.8242 (0.8339) time: 0.2068 data: 0.1203 max mem: 9390 +Train: [83] [ 300/6250] eta: 0:29:05 lr: 0.000010 grad: 0.1354 (0.1318) loss: 0.8111 (0.8300) time: 0.2644 data: 0.1024 max mem: 9390 +Train: [83] [ 400/6250] eta: 0:29:54 lr: 0.000010 grad: 0.1383 (0.1322) loss: 0.8220 (0.8278) time: 0.5617 data: 0.3817 max mem: 9390 +Train: [83] [ 500/6250] eta: 0:31:01 lr: 0.000010 grad: 0.1279 (0.1321) loss: 0.8169 (0.8257) time: 0.2154 data: 0.0005 max mem: 9390 +Train: [83] [ 600/6250] eta: 0:29:35 lr: 0.000010 grad: 0.1314 (0.1319) loss: 0.8172 (0.8243) time: 0.1748 data: 0.0692 max mem: 9390 +Train: [83] [ 700/6250] eta: 0:27:43 lr: 0.000009 grad: 0.1299 (0.1318) loss: 0.8152 (0.8231) time: 0.2072 data: 0.0979 max mem: 9390 +Train: [83] [ 800/6250] eta: 0:26:17 lr: 0.000009 grad: 0.1288 (0.1319) loss: 0.8154 (0.8222) time: 0.1177 data: 0.0207 max mem: 9390 +Train: [83] [ 900/6250] eta: 0:24:57 lr: 0.000009 grad: 0.1293 (0.1322) loss: 0.8145 (0.8213) time: 0.2115 data: 0.1222 max mem: 9390 +Train: [83] [1000/6250] eta: 0:24:37 lr: 0.000009 grad: 0.1284 (0.1322) loss: 0.8144 (0.8206) time: 0.1117 data: 0.0156 max mem: 9390 +Train: [83] [1100/6250] eta: 0:23:51 lr: 0.000009 grad: 0.1263 (0.1321) loss: 0.8124 (0.8200) time: 0.2026 data: 0.1072 max mem: 9390 +Train: [83] [1200/6250] eta: 0:23:19 lr: 0.000009 grad: 0.1238 (0.1321) loss: 0.8125 (0.8194) time: 0.2934 data: 0.1773 max mem: 9390 +Train: [83] [1300/6250] eta: 0:23:10 lr: 0.000009 grad: 0.1256 (0.1321) loss: 0.8161 (0.8189) time: 0.3382 data: 0.2223 max mem: 9390 +Train: [83] [1400/6250] eta: 0:23:02 lr: 0.000009 grad: 0.1294 (0.1320) loss: 0.8192 (0.8188) time: 0.4206 data: 0.1658 max mem: 9390 +Train: [83] [1500/6250] eta: 0:22:43 lr: 0.000009 grad: 0.1247 (0.1319) loss: 0.8191 (0.8185) time: 0.4439 data: 0.3304 max mem: 9390 +Train: [83] [1600/6250] eta: 0:22:12 lr: 0.000009 grad: 0.1267 (0.1318) loss: 0.8107 (0.8183) time: 0.1804 data: 0.0003 max mem: 9390 +Train: [83] [1700/6250] eta: 0:22:41 lr: 0.000009 grad: 0.1242 (0.1317) loss: 0.8139 (0.8180) time: 1.1464 data: 0.9563 max mem: 9390 +Train: [83] [1800/6250] eta: 0:22:05 lr: 0.000009 grad: 0.1283 (0.1316) loss: 0.8104 (0.8178) time: 0.2596 data: 0.1420 max mem: 9390 +Train: [83] [1900/6250] eta: 0:22:16 lr: 0.000009 grad: 0.1304 (0.1317) loss: 0.8118 (0.8175) time: 0.1082 data: 0.0003 max mem: 9390 +Train: [83] [2000/6250] eta: 0:22:26 lr: 0.000009 grad: 0.1289 (0.1316) loss: 0.8097 (0.8174) time: 1.0306 data: 0.9203 max mem: 9390 +Train: [83] [2100/6250] eta: 0:21:45 lr: 0.000009 grad: 0.1294 (0.1315) loss: 0.8137 (0.8173) time: 0.4415 data: 0.2990 max mem: 9390 +Train: [83] [2200/6250] eta: 0:21:31 lr: 0.000009 grad: 0.1290 (0.1315) loss: 0.8139 (0.8172) time: 0.0908 data: 0.0002 max mem: 9390 +Train: [83] [2300/6250] eta: 0:20:31 lr: 0.000009 grad: 0.1348 (0.1318) loss: 0.8127 (0.8169) time: 0.1535 data: 0.0664 max mem: 9390 +Train: [83] [2400/6250] eta: 0:19:36 lr: 0.000009 grad: 0.1286 (0.1320) loss: 0.8134 (0.8167) time: 0.2317 data: 0.1459 max mem: 9390 +Train: [83] [2500/6250] eta: 0:18:40 lr: 0.000009 grad: 0.1314 (0.1321) loss: 0.8092 (0.8165) time: 0.1319 data: 0.0502 max mem: 9390 +Train: [83] [2600/6250] eta: 0:17:52 lr: 0.000009 grad: 0.1281 (0.1321) loss: 0.8160 (0.8163) time: 0.1651 data: 0.0827 max mem: 9390 +Train: [83] [2700/6250] eta: 0:17:07 lr: 0.000009 grad: 0.1247 (0.1321) loss: 0.8031 (0.8161) time: 0.1804 data: 0.0851 max mem: 9390 +Train: [83] [2800/6250] eta: 0:16:24 lr: 0.000009 grad: 0.1313 (0.1321) loss: 0.8213 (0.8161) time: 0.2400 data: 0.1646 max mem: 9390 +Train: [83] [2900/6250] eta: 0:15:41 lr: 0.000009 grad: 0.1311 (0.1321) loss: 0.8203 (0.8161) time: 0.1548 data: 0.0728 max mem: 9390 +Train: [83] [3000/6250] eta: 0:15:00 lr: 0.000009 grad: 0.1318 (0.1322) loss: 0.8147 (0.8159) time: 0.1647 data: 0.0859 max mem: 9390 +Train: [83] [3100/6250] eta: 0:14:22 lr: 0.000009 grad: 0.1274 (0.1323) loss: 0.8080 (0.8158) time: 0.1407 data: 0.0569 max mem: 9390 +Train: [83] [3200/6250] eta: 0:13:46 lr: 0.000009 grad: 0.1333 (0.1323) loss: 0.8147 (0.8157) time: 0.1566 data: 0.0671 max mem: 9390 +Train: [83] [3300/6250] eta: 0:13:10 lr: 0.000009 grad: 0.1279 (0.1324) loss: 0.8117 (0.8156) time: 0.1718 data: 0.0817 max mem: 9390 +Train: [83] [3400/6250] eta: 0:12:37 lr: 0.000009 grad: 0.1300 (0.1324) loss: 0.8181 (0.8157) time: 0.1249 data: 0.0092 max mem: 9390 +Train: [83] [3500/6250] eta: 0:12:06 lr: 0.000009 grad: 0.1234 (0.1324) loss: 0.8167 (0.8156) time: 0.1339 data: 0.0311 max mem: 9390 +Train: [83] [3600/6250] eta: 0:11:46 lr: 0.000009 grad: 0.1324 (0.1323) loss: 0.8125 (0.8156) time: 0.3189 data: 0.0833 max mem: 9390 +Train: [83] [3700/6250] eta: 0:11:23 lr: 0.000009 grad: 0.1195 (0.1322) loss: 0.8190 (0.8157) time: 0.3598 data: 0.2443 max mem: 9390 +Train: [83] [3800/6250] eta: 0:10:55 lr: 0.000009 grad: 0.1321 (0.1321) loss: 0.8104 (0.8157) time: 0.4930 data: 0.3716 max mem: 9390 +Train: [83] [3900/6250] eta: 0:10:27 lr: 0.000009 grad: 0.1252 (0.1322) loss: 0.8158 (0.8157) time: 0.3733 data: 0.2399 max mem: 9390 +Train: [83] [4000/6250] eta: 0:10:03 lr: 0.000009 grad: 0.1325 (0.1323) loss: 0.8189 (0.8157) time: 0.4670 data: 0.3569 max mem: 9390 +Train: [83] [4100/6250] eta: 0:09:36 lr: 0.000009 grad: 0.1294 (0.1324) loss: 0.8197 (0.8157) time: 0.4024 data: 0.2433 max mem: 9390 +Train: [83] [4200/6250] eta: 0:09:11 lr: 0.000009 grad: 0.1250 (0.1324) loss: 0.8176 (0.8157) time: 0.3069 data: 0.1703 max mem: 9390 +Train: [83] [4300/6250] eta: 0:08:44 lr: 0.000009 grad: 0.1327 (0.1325) loss: 0.8160 (0.8157) time: 0.2000 data: 0.0709 max mem: 9390 +Train: [83] [4400/6250] eta: 0:08:19 lr: 0.000009 grad: 0.1345 (0.1327) loss: 0.8122 (0.8156) time: 0.3875 data: 0.2000 max mem: 9390 +Train: [83] [4500/6250] eta: 0:07:55 lr: 0.000009 grad: 0.1396 (0.1328) loss: 0.8167 (0.8156) time: 0.3299 data: 0.1850 max mem: 9390 +Train: [83] [4600/6250] eta: 0:07:30 lr: 0.000009 grad: 0.1314 (0.1329) loss: 0.8141 (0.8155) time: 0.1457 data: 0.0318 max mem: 9390 +Train: [83] [4700/6250] eta: 0:07:06 lr: 0.000009 grad: 0.1356 (0.1330) loss: 0.8142 (0.8155) time: 0.3283 data: 0.2014 max mem: 9390 +Train: [83] [4800/6250] eta: 0:06:38 lr: 0.000009 grad: 0.1330 (0.1331) loss: 0.8152 (0.8155) time: 0.1382 data: 0.0003 max mem: 9390 +Train: [83] [4900/6250] eta: 0:06:11 lr: 0.000009 grad: 0.1340 (0.1333) loss: 0.8052 (0.8155) time: 0.1750 data: 0.0003 max mem: 9390 +Train: [83] [5000/6250] eta: 0:05:47 lr: 0.000009 grad: 0.1360 (0.1334) loss: 0.8171 (0.8155) time: 0.2125 data: 0.0759 max mem: 9390 +Train: [83] [5100/6250] eta: 0:05:22 lr: 0.000009 grad: 0.1323 (0.1336) loss: 0.8158 (0.8155) time: 0.5586 data: 0.4262 max mem: 9390 +Train: [83] [5200/6250] eta: 0:04:55 lr: 0.000009 grad: 0.1382 (0.1337) loss: 0.8150 (0.8154) time: 0.3195 data: 0.1693 max mem: 9390 +pretraining fmri mae +start: 2026-04-01 15:51:29 +cwd: /data/connor/fmri-fm +sha: 7f4cedc35609f6857314e0d1ea6657523f17ddeb, status: has uncommitted changes, branch: dev/clane9 +config: +name: input_space_v3/flat_lr1e-3_4/pretrain +notes: input_space ablation v3 flat_lr1e-3_4; use tube masking and on-disk data (input_space=flat + base_lr=1e-3 seed=5404) +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain +input_space: flat +patch_size: 16 +num_frames: 16 +t_patch_size: 4 +mask_ratio: 0.9 +pred_mask_ratio: null +masking: tube +masking_kwargs: {} +mask_patch_size: null +model: mae_vit_base +model_kwargs: + decoding: attn + pos_embed: sep + target_norm: null + pca_norm_nc: 2 + t_pred_stride: 2 + no_decode_pos: true + mask_drop_scale: false + pred_edge_pad: 0 + gauss_sigma: null + class_token: true + reg_tokens: 0 + no_embed_class: true + head_init_scale: 0.0 + decoder_depth: 4 + drop_path_rate: 0.0 +datasets: + hcp-train: + type: wds + url: /data/fmri-datasets/pretrain/hcpya-all.${input_space}.wds/hcpya-all-${input_space}-{00000..01799}.tar + clipping: random + clipping_kwargs: + oversample: 4.0 + shuffle: true + buffer_size: 2000 + samples_per_epoch: 200000 + hcp-train-subset: + type: arrow + root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/validation + split_range: + - 0 + - 2000 + shuffle: false + hcp-val: + type: arrow + root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/test + split_range: + - 0 + - 2000 + shuffle: false +train_dataset: hcp-train +eval_datasets: +- hcp-train-subset +- hcp-val +val_dataset: null +clip_vmax: 3.0 +normalize: frame +tr_scale: null +crop_scale: null +crop_aspect: null +gray_jitter: null +num_workers: 16 +epochs: 100 +batch_size: 32 +accum_iter: 1 +base_lr: 0.001 +min_lr: 0.0 +warmup_epochs: 5 +weight_decay: 0.05 +betas: +- 0.9 +- 0.95 +clip_grad: 1.0 +amp: true +amp_dtype: float16 +ckpt: null +resume: true +auto_resume: true +start_epoch: 0 +max_checkpoints: 0 +checkpoint_period: null +plot_period: 5 +device: cuda +presend_cuda: false +seed: 5404 +debug: false +wandb: true +wandb_entity: null +wandb_project: fMRI-foundation-model +rank: 0 +world_size: 1 +gpu: 0 +distributed: true +dist_backend: nccl +in_chans: 1 +img_size: +- 224 +- 560 + +train transform: +Compose( + ToTensor() + TemporalCenterCrop(num_frames=16) + Normalize(mode='frame') + Clip(vmax=3.0) + FlatUnmask((224, 560)) +) +val transform: +Compose( + ToTensor() + TemporalCenterCrop(num_frames=16) + Normalize(mode='frame') + Clip(vmax=3.0) + FlatUnmask((224, 560)) +) +mask generator: +TubeMasking( + mask_ratio=0.9 + (patchify): Patchify2D((224, 560), (16, 16), in_chans=1) +) +loading dataset: hcp-train + +type: wds +url: /data/fmri-datasets/pretrain/hcpya-all.${input_space}.wds/hcpya-all-${input_space}-{00000..01799}.tar +clipping: random +clipping_kwargs: + oversample: 4.0 +shuffle: true +buffer_size: 2000 +samples_per_epoch: 200000 + +loading dataset: hcp-train-subset + +type: arrow +root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/validation +split_range: +- 0 +- 2000 +shuffle: false + +split indices: [899, 472, 767, 116, 1265, 1852, 300, 1335, 361, 1560] +loading dataset: hcp-val + +type: arrow +root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/test +split_range: +- 0 +- 2000 +shuffle: false + +split indices: [1075, 1189, 738, 1350, 965, 1964, 1367, 1183, 1619, 1407] +model: +MaskedAutoencoderViT( + decoding=attn, t_pred_stride=2, pred_edge_pad=0, no_decode_pos=True + (encoder): MaskedEncoder( + class_token=True, reg_tokens=0, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) + (pred_patchify): StridedPatchify3D((16, 224, 560), (2, 16, 16), in_chans=1, t_stride=2) + (decoder): MaskedDecoder( + cross_decode=False, class_token=True, no_embed_class=True + (pos_embed): SeparablePosEmbed(512, (4, 14, 35)) + (proj): Linear(in_features=768, out_features=512, bias=True) + (blocks): ModuleList( + (0-3): 4 x Block( + (norm1): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=16 + (q): Linear(in_features=512, out_features=512, bias=True) + (k): Linear(in_features=512, out_features=512, bias=True) + (v): Linear(in_features=512, out_features=512, bias=True) + (proj): Linear(in_features=512, out_features=512, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=512, out_features=2048, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=2048, out_features=512, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (head): Linear(in_features=512, out_features=512, bias=True) + ) +) +num params: 99.7M +total batch size: 32 = 32 bs per gpu x 1 accum x 1 gpus +lr: 1.25e-04 = 1.00e-03 x 32 / 256 +full schedule: epochs = 100 (steps = 625000) +warmup: epochs = 5 (steps = 31250) +loaded model state from checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +loaded optimizer state, resuming training from 83 +start training for 100 epochs +Train: [83] [ 0/6250] eta: 11:39:35 lr: 0.000010 grad: 0.1767 (0.1767) loss: 0.8413 (0.8413) time: 6.7161 data: 5.7743 max mem: 9353 +Train: [83] [ 100/6250] eta: 0:20:43 lr: 0.000010 grad: 0.1214 (0.1649) loss: 0.8316 (0.8240) time: 0.1640 data: 0.0804 max mem: 9390 +Train: [83] [ 200/6250] eta: 0:16:54 lr: 0.000010 grad: 0.1700 (0.1647) loss: 0.8060 (0.8175) time: 0.1350 data: 0.0517 max mem: 9390 +Train: [83] [ 300/6250] eta: 0:15:27 lr: 0.000010 grad: 0.1442 (0.1623) loss: 0.8121 (0.8154) time: 0.1410 data: 0.0567 max mem: 9390 +Train: [83] [ 400/6250] eta: 0:14:22 lr: 0.000010 grad: 0.1425 (0.1588) loss: 0.8126 (0.8142) time: 0.1288 data: 0.0415 max mem: 9390 +Train: [83] [ 500/6250] eta: 0:13:40 lr: 0.000010 grad: 0.1337 (0.1551) loss: 0.8145 (0.8141) time: 0.1225 data: 0.0296 max mem: 9390 +Train: [83] [ 600/6250] eta: 0:13:08 lr: 0.000010 grad: 0.1341 (0.1513) loss: 0.8210 (0.8150) time: 0.1366 data: 0.0511 max mem: 9390 +Train: [83] [ 700/6250] eta: 0:12:56 lr: 0.000009 grad: 0.1263 (0.1481) loss: 0.8141 (0.8157) time: 0.1556 data: 0.0546 max mem: 9390 +Train: [83] [ 800/6250] eta: 0:12:54 lr: 0.000009 grad: 0.1270 (0.1462) loss: 0.8209 (0.8158) time: 0.1817 data: 0.0932 max mem: 9390 +Train: [83] [ 900/6250] eta: 0:12:51 lr: 0.000009 grad: 0.1256 (0.1449) loss: 0.8175 (0.8155) time: 0.1464 data: 0.0559 max mem: 9390 +Train: [83] [1000/6250] eta: 0:12:44 lr: 0.000009 grad: 0.1321 (0.1439) loss: 0.8156 (0.8152) time: 0.1573 data: 0.0784 max mem: 9390 +Train: [83] [1100/6250] eta: 0:12:31 lr: 0.000009 grad: 0.1301 (0.1430) loss: 0.8051 (0.8147) time: 0.1518 data: 0.0626 max mem: 9390 +Train: [83] [1200/6250] eta: 0:12:20 lr: 0.000009 grad: 0.1347 (0.1421) loss: 0.8102 (0.8146) time: 0.1710 data: 0.0893 max mem: 9390 +Train: [83] [1300/6250] eta: 0:12:07 lr: 0.000009 grad: 0.1381 (0.1418) loss: 0.8101 (0.8143) time: 0.1460 data: 0.0610 max mem: 9390 +Train: [83] [1400/6250] eta: 0:11:54 lr: 0.000009 grad: 0.1305 (0.1415) loss: 0.8096 (0.8139) time: 0.1557 data: 0.0726 max mem: 9390 +Train: [83] [1500/6250] eta: 0:11:43 lr: 0.000009 grad: 0.1293 (0.1411) loss: 0.8164 (0.8136) time: 0.1447 data: 0.0641 max mem: 9390 +Train: [83] [1600/6250] eta: 0:11:29 lr: 0.000009 grad: 0.1261 (0.1406) loss: 0.8160 (0.8136) time: 0.1499 data: 0.0693 max mem: 9390 +Train: [83] [1700/6250] eta: 0:11:14 lr: 0.000009 grad: 0.1285 (0.1402) loss: 0.8089 (0.8136) time: 0.1603 data: 0.0787 max mem: 9390 +Train: [83] [1800/6250] eta: 0:11:01 lr: 0.000009 grad: 0.1289 (0.1397) loss: 0.8171 (0.8136) time: 0.1231 data: 0.0364 max mem: 9390 +Train: [83] [1900/6250] eta: 0:10:47 lr: 0.000009 grad: 0.1299 (0.1392) loss: 0.8155 (0.8136) time: 0.1666 data: 0.0813 max mem: 9390 +Train: [83] [2000/6250] eta: 0:10:33 lr: 0.000009 grad: 0.1320 (0.1388) loss: 0.8106 (0.8137) time: 0.1351 data: 0.0450 max mem: 9390 +Train: [83] [2100/6250] eta: 0:10:19 lr: 0.000009 grad: 0.1298 (0.1384) loss: 0.8111 (0.8136) time: 0.1563 data: 0.0746 max mem: 9390 +Train: [83] [2200/6250] eta: 0:10:19 lr: 0.000009 grad: 0.1314 (0.1383) loss: 0.8090 (0.8135) time: 0.4754 data: 0.4008 max mem: 9390 +Train: [83] [2300/6250] eta: 0:10:28 lr: 0.000009 grad: 0.1267 (0.1383) loss: 0.8109 (0.8134) time: 0.3824 data: 0.2945 max mem: 9390 +Train: [83] [2400/6250] eta: 0:10:14 lr: 0.000009 grad: 0.1283 (0.1381) loss: 0.8143 (0.8133) time: 0.1701 data: 0.0797 max mem: 9390 +Train: [83] [2500/6250] eta: 0:10:00 lr: 0.000009 grad: 0.1292 (0.1379) loss: 0.8119 (0.8133) time: 0.1706 data: 0.0788 max mem: 9390 +Train: [83] [2600/6250] eta: 0:09:46 lr: 0.000009 grad: 0.1318 (0.1377) loss: 0.8098 (0.8133) time: 0.1573 data: 0.0702 max mem: 9390 +Train: [83] [2700/6250] eta: 0:09:32 lr: 0.000009 grad: 0.1265 (0.1375) loss: 0.8147 (0.8133) time: 0.1694 data: 0.0796 max mem: 9390 +Train: [83] [2800/6250] eta: 0:09:19 lr: 0.000009 grad: 0.1305 (0.1373) loss: 0.8104 (0.8134) time: 0.1745 data: 0.0834 max mem: 9390 +Train: [83] [2900/6250] eta: 0:09:04 lr: 0.000009 grad: 0.1238 (0.1372) loss: 0.8158 (0.8134) time: 0.1668 data: 0.0730 max mem: 9390 +Train: [83] [3000/6250] eta: 0:08:50 lr: 0.000009 grad: 0.1263 (0.1370) loss: 0.8122 (0.8135) time: 0.1860 data: 0.1000 max mem: 9390 +Train: [83] [3100/6250] eta: 0:08:36 lr: 0.000009 grad: 0.1249 (0.1369) loss: 0.8225 (0.8135) time: 0.1982 data: 0.1053 max mem: 9390 +Train: [83] [3200/6250] eta: 0:08:21 lr: 0.000009 grad: 0.1385 (0.1370) loss: 0.8120 (0.8135) time: 0.1880 data: 0.0961 max mem: 9390 +Train: [83] [3300/6250] eta: 0:08:05 lr: 0.000009 grad: 0.1268 (0.1369) loss: 0.8160 (0.8134) time: 0.1675 data: 0.0789 max mem: 9390 +Train: [83] [3400/6250] eta: 0:07:49 lr: 0.000009 grad: 0.1254 (0.1368) loss: 0.8163 (0.8135) time: 0.1727 data: 0.0740 max mem: 9390 +Train: [83] [3500/6250] eta: 0:07:33 lr: 0.000009 grad: 0.1257 (0.1367) loss: 0.8079 (0.8134) time: 0.1830 data: 0.0864 max mem: 9390 +Train: [83] [3600/6250] eta: 0:07:17 lr: 0.000009 grad: 0.1272 (0.1366) loss: 0.8188 (0.8135) time: 0.1629 data: 0.0787 max mem: 9390 +Train: [83] [3700/6250] eta: 0:07:01 lr: 0.000009 grad: 0.1254 (0.1365) loss: 0.8153 (0.8135) time: 0.1513 data: 0.0599 max mem: 9390 +Train: [83] [3800/6250] eta: 0:06:45 lr: 0.000009 grad: 0.1225 (0.1363) loss: 0.8199 (0.8135) time: 0.1760 data: 0.0857 max mem: 9390 +Train: [83] [3900/6250] eta: 0:06:28 lr: 0.000009 grad: 0.1317 (0.1362) loss: 0.8145 (0.8135) time: 0.1581 data: 0.0660 max mem: 9390 +Train: [83] [4000/6250] eta: 0:06:12 lr: 0.000009 grad: 0.1310 (0.1361) loss: 0.8081 (0.8135) time: 0.1567 data: 0.0720 max mem: 9390 +Train: [83] [4100/6250] eta: 0:05:56 lr: 0.000009 grad: 0.1331 (0.1361) loss: 0.8112 (0.8134) time: 0.1582 data: 0.0733 max mem: 9390 +Train: [83] [4200/6250] eta: 0:05:40 lr: 0.000009 grad: 0.1260 (0.1360) loss: 0.8128 (0.8134) time: 0.1870 data: 0.1019 max mem: 9390 +Train: [83] [4300/6250] eta: 0:05:24 lr: 0.000009 grad: 0.1286 (0.1359) loss: 0.8152 (0.8134) time: 0.1662 data: 0.0788 max mem: 9390 +Train: [83] [4400/6250] eta: 0:05:07 lr: 0.000009 grad: 0.1288 (0.1357) loss: 0.8153 (0.8134) time: 0.1586 data: 0.0658 max mem: 9390 +Train: [83] [4500/6250] eta: 0:04:51 lr: 0.000009 grad: 0.1289 (0.1357) loss: 0.8096 (0.8134) time: 0.1865 data: 0.1019 max mem: 9390 +Train: [83] [4600/6250] eta: 0:04:35 lr: 0.000009 grad: 0.1232 (0.1356) loss: 0.8161 (0.8134) time: 0.1351 data: 0.0442 max mem: 9390 +Train: [83] [4700/6250] eta: 0:04:18 lr: 0.000009 grad: 0.1251 (0.1356) loss: 0.8161 (0.8134) time: 0.1877 data: 0.1003 max mem: 9390 +Train: [83] [4800/6250] eta: 0:04:02 lr: 0.000009 grad: 0.1428 (0.1355) loss: 0.8122 (0.8134) time: 0.1746 data: 0.0898 max mem: 9390 +Train: [83] [4900/6250] eta: 0:03:45 lr: 0.000009 grad: 0.1295 (0.1354) loss: 0.8174 (0.8134) time: 0.1622 data: 0.0716 max mem: 9390 +Train: [83] [5000/6250] eta: 0:03:29 lr: 0.000009 grad: 0.1345 (0.1354) loss: 0.8137 (0.8135) time: 0.2010 data: 0.1083 max mem: 9390 +Train: [83] [5100/6250] eta: 0:03:12 lr: 0.000009 grad: 0.1298 (0.1353) loss: 0.8142 (0.8134) time: 0.1690 data: 0.0805 max mem: 9390 +Train: [83] [5200/6250] eta: 0:02:56 lr: 0.000009 grad: 0.1316 (0.1353) loss: 0.8142 (0.8134) time: 0.1555 data: 0.0655 max mem: 9390 +Train: [83] [5300/6250] eta: 0:02:39 lr: 0.000009 grad: 0.1293 (0.1353) loss: 0.8184 (0.8135) time: 0.1817 data: 0.0918 max mem: 9390 +Train: [83] [5400/6250] eta: 0:02:22 lr: 0.000009 grad: 0.1309 (0.1353) loss: 0.8158 (0.8135) time: 0.1920 data: 0.1023 max mem: 9390 +Train: [83] [5500/6250] eta: 0:02:05 lr: 0.000009 grad: 0.1344 (0.1353) loss: 0.8149 (0.8135) time: 0.1647 data: 0.0718 max mem: 9390 +Train: [83] [5600/6250] eta: 0:01:49 lr: 0.000009 grad: 0.1286 (0.1352) loss: 0.8129 (0.8135) time: 0.1835 data: 0.0987 max mem: 9390 +Train: [83] [5700/6250] eta: 0:01:32 lr: 0.000009 grad: 0.1299 (0.1352) loss: 0.8167 (0.8135) time: 0.1524 data: 0.0630 max mem: 9390 +Train: [83] [5800/6250] eta: 0:01:15 lr: 0.000009 grad: 0.1262 (0.1351) loss: 0.8176 (0.8136) time: 0.1647 data: 0.0712 max mem: 9390 +Train: [83] [5900/6250] eta: 0:00:58 lr: 0.000009 grad: 0.1326 (0.1351) loss: 0.8131 (0.8136) time: 0.1577 data: 0.0571 max mem: 9390 +Train: [83] [6000/6250] eta: 0:00:42 lr: 0.000009 grad: 0.1284 (0.1351) loss: 0.8176 (0.8136) time: 0.1625 data: 0.0747 max mem: 9390 +Train: [83] [6100/6250] eta: 0:00:25 lr: 0.000009 grad: 0.1295 (0.1351) loss: 0.8160 (0.8137) time: 0.1682 data: 0.0739 max mem: 9390 +Train: [83] [6200/6250] eta: 0:00:08 lr: 0.000009 grad: 0.1344 (0.1351) loss: 0.8171 (0.8137) time: 0.1574 data: 0.0700 max mem: 9390 +Train: [83] [6249/6250] eta: 0:00:00 lr: 0.000009 grad: 0.1400 (0.1351) loss: 0.8112 (0.8137) time: 0.1926 data: 0.1109 max mem: 9390 +Train: [83] Total time: 0:17:40 (0.1696 s / it) +Averaged stats: lr: 0.000009 grad: 0.1400 (0.1351) loss: 0.8112 (0.8137) +Eval (hcp-train-subset): [83] [ 0/62] eta: 0:06:41 loss: 0.8264 (0.8264) time: 6.4814 data: 6.4366 max mem: 9390 +Eval (hcp-train-subset): [83] [61/62] eta: 0:00:00 loss: 0.8171 (0.8206) time: 0.1337 data: 0.1081 max mem: 9390 +Eval (hcp-train-subset): [83] Total time: 0:00:15 (0.2579 s / it) +Averaged stats (hcp-train-subset): loss: 0.8171 (0.8206) +Eval (hcp-val): [83] [ 0/62] eta: 0:05:20 loss: 0.8249 (0.8249) time: 5.1706 data: 5.0912 max mem: 9390 +Eval (hcp-val): [83] [61/62] eta: 0:00:00 loss: 0.8276 (0.8291) time: 0.1404 data: 0.1143 max mem: 9390 +Eval (hcp-val): [83] Total time: 0:00:14 (0.2361 s / it) +Averaged stats (hcp-val): loss: 0.8276 (0.8291) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +Train: [84] [ 0/6250] eta: 12:05:14 lr: 0.000009 grad: 0.3826 (0.3826) loss: 0.7706 (0.7706) time: 6.9623 data: 6.8510 max mem: 9390 +Train: [84] [ 100/6250] eta: 0:23:12 lr: 0.000009 grad: 0.1378 (0.1402) loss: 0.8115 (0.8291) time: 0.1561 data: 0.0567 max mem: 9390 +Train: [84] [ 200/6250] eta: 0:20:11 lr: 0.000009 grad: 0.1338 (0.1411) loss: 0.8173 (0.8243) time: 0.1600 data: 0.0576 max mem: 9390 +Train: [84] [ 300/6250] eta: 0:18:49 lr: 0.000008 grad: 0.1364 (0.1393) loss: 0.8187 (0.8230) time: 0.1768 data: 0.0785 max mem: 9390 +Train: [84] [ 400/6250] eta: 0:18:31 lr: 0.000008 grad: 0.1344 (0.1390) loss: 0.8144 (0.8209) time: 0.1976 data: 0.1062 max mem: 9390 +Train: [84] [ 500/6250] eta: 0:17:52 lr: 0.000008 grad: 0.1383 (0.1388) loss: 0.8140 (0.8196) time: 0.1854 data: 0.0901 max mem: 9390 +Train: [84] [ 600/6250] eta: 0:17:16 lr: 0.000008 grad: 0.1313 (0.1388) loss: 0.8195 (0.8186) time: 0.1867 data: 0.0875 max mem: 9390 +Train: [84] [ 700/6250] eta: 0:17:03 lr: 0.000008 grad: 0.1302 (0.1386) loss: 0.8136 (0.8180) time: 0.1822 data: 0.0735 max mem: 9390 +Train: [84] [ 800/6250] eta: 0:16:48 lr: 0.000008 grad: 0.1381 (0.1393) loss: 0.8114 (0.8168) time: 0.1764 data: 0.0765 max mem: 9390 +Train: [84] [ 900/6250] eta: 0:16:34 lr: 0.000008 grad: 0.1335 (0.1396) loss: 0.8054 (0.8158) time: 0.1654 data: 0.0713 max mem: 9390 +Train: [84] [1000/6250] eta: 0:16:11 lr: 0.000008 grad: 0.1371 (0.1406) loss: 0.8100 (0.8151) time: 0.1697 data: 0.0774 max mem: 9390 +Train: [84] [1100/6250] eta: 0:15:45 lr: 0.000008 grad: 0.1355 (0.1407) loss: 0.8075 (0.8144) time: 0.1774 data: 0.0823 max mem: 9390 +Train: [84] [1200/6250] eta: 0:15:23 lr: 0.000008 grad: 0.1321 (0.1405) loss: 0.8131 (0.8142) time: 0.1875 data: 0.0938 max mem: 9390 +Train: [84] [1300/6250] eta: 0:15:00 lr: 0.000008 grad: 0.1398 (0.1406) loss: 0.8017 (0.8137) time: 0.1558 data: 0.0522 max mem: 9390 +Train: [84] [1400/6250] eta: 0:14:38 lr: 0.000008 grad: 0.1307 (0.1404) loss: 0.8105 (0.8132) time: 0.1465 data: 0.0454 max mem: 9390 +Train: [84] [1500/6250] eta: 0:14:17 lr: 0.000008 grad: 0.1324 (0.1403) loss: 0.8112 (0.8127) time: 0.1754 data: 0.0854 max mem: 9390 +Train: [84] [1600/6250] eta: 0:13:58 lr: 0.000008 grad: 0.1399 (0.1402) loss: 0.8099 (0.8124) time: 0.1882 data: 0.0998 max mem: 9390 +Train: [84] [1700/6250] eta: 0:13:36 lr: 0.000008 grad: 0.1339 (0.1400) loss: 0.8105 (0.8122) time: 0.1602 data: 0.0697 max mem: 9390 +Train: [84] [1800/6250] eta: 0:13:16 lr: 0.000008 grad: 0.1359 (0.1398) loss: 0.8083 (0.8121) time: 0.1586 data: 0.0662 max mem: 9390 +Train: [84] [1900/6250] eta: 0:12:56 lr: 0.000008 grad: 0.1288 (0.1395) loss: 0.8148 (0.8121) time: 0.1639 data: 0.0690 max mem: 9390 +Train: [84] [2000/6250] eta: 0:12:36 lr: 0.000008 grad: 0.1247 (0.1393) loss: 0.8133 (0.8121) time: 0.1734 data: 0.0819 max mem: 9390 +Train: [84] [2100/6250] eta: 0:12:16 lr: 0.000008 grad: 0.1359 (0.1390) loss: 0.8104 (0.8121) time: 0.1946 data: 0.1079 max mem: 9390 +Train: [84] [2200/6250] eta: 0:11:57 lr: 0.000008 grad: 0.1286 (0.1389) loss: 0.8169 (0.8120) time: 0.1763 data: 0.0874 max mem: 9390 +Train: [84] [2300/6250] eta: 0:11:37 lr: 0.000008 grad: 0.1348 (0.1389) loss: 0.8086 (0.8120) time: 0.1620 data: 0.0688 max mem: 9390 +Train: [84] [2400/6250] eta: 0:11:20 lr: 0.000008 grad: 0.1353 (0.1388) loss: 0.8149 (0.8120) time: 0.1814 data: 0.0996 max mem: 9390 +Train: [84] [2500/6250] eta: 0:11:01 lr: 0.000008 grad: 0.1339 (0.1388) loss: 0.8092 (0.8119) time: 0.1779 data: 0.0912 max mem: 9390 +Train: [84] [2600/6250] eta: 0:10:43 lr: 0.000008 grad: 0.1338 (0.1386) loss: 0.8102 (0.8120) time: 0.1651 data: 0.0727 max mem: 9390 +Train: [84] [2700/6250] eta: 0:10:24 lr: 0.000008 grad: 0.1309 (0.1383) loss: 0.8103 (0.8121) time: 0.1682 data: 0.0745 max mem: 9390 +Train: [84] [2800/6250] eta: 0:10:06 lr: 0.000008 grad: 0.1313 (0.1381) loss: 0.8117 (0.8120) time: 0.1780 data: 0.0861 max mem: 9390 +Train: [84] [2900/6250] eta: 0:09:48 lr: 0.000008 grad: 0.1285 (0.1380) loss: 0.8107 (0.8120) time: 0.1976 data: 0.1151 max mem: 9390 +Train: [84] [3000/6250] eta: 0:09:29 lr: 0.000008 grad: 0.1286 (0.1378) loss: 0.8151 (0.8121) time: 0.1850 data: 0.0956 max mem: 9390 +Train: [84] [3100/6250] eta: 0:09:11 lr: 0.000008 grad: 0.1323 (0.1378) loss: 0.8141 (0.8121) time: 0.1874 data: 0.0952 max mem: 9390 +Train: [84] [3200/6250] eta: 0:08:53 lr: 0.000008 grad: 0.1284 (0.1376) loss: 0.8177 (0.8122) time: 0.1688 data: 0.0817 max mem: 9390 +Train: [84] [3300/6250] eta: 0:08:36 lr: 0.000008 grad: 0.1244 (0.1375) loss: 0.8121 (0.8121) time: 0.1662 data: 0.0711 max mem: 9390 +Train: [84] [3400/6250] eta: 0:08:18 lr: 0.000008 grad: 0.1266 (0.1375) loss: 0.8130 (0.8120) time: 0.1530 data: 0.0657 max mem: 9390 +Train: [84] [3500/6250] eta: 0:08:01 lr: 0.000008 grad: 0.1305 (0.1374) loss: 0.8097 (0.8120) time: 0.1581 data: 0.0652 max mem: 9390 +Train: [84] [3600/6250] eta: 0:07:43 lr: 0.000008 grad: 0.1276 (0.1373) loss: 0.8153 (0.8120) time: 0.1660 data: 0.0740 max mem: 9390 +Train: [84] [3700/6250] eta: 0:07:25 lr: 0.000008 grad: 0.1238 (0.1371) loss: 0.8156 (0.8121) time: 0.1876 data: 0.0981 max mem: 9390 +Train: [84] [3800/6250] eta: 0:07:07 lr: 0.000008 grad: 0.1214 (0.1369) loss: 0.8191 (0.8121) time: 0.1878 data: 0.0968 max mem: 9390 +Train: [84] [3900/6250] eta: 0:06:49 lr: 0.000008 grad: 0.1372 (0.1368) loss: 0.8141 (0.8121) time: 0.1670 data: 0.0746 max mem: 9390 +Train: [84] [4000/6250] eta: 0:06:32 lr: 0.000008 grad: 0.1303 (0.1368) loss: 0.8185 (0.8122) time: 0.1813 data: 0.0980 max mem: 9390 +Train: [84] [4100/6250] eta: 0:06:15 lr: 0.000008 grad: 0.1305 (0.1367) loss: 0.8163 (0.8122) time: 0.1574 data: 0.0686 max mem: 9390 +Train: [84] [4200/6250] eta: 0:05:57 lr: 0.000008 grad: 0.1330 (0.1367) loss: 0.8171 (0.8122) time: 0.1796 data: 0.0820 max mem: 9390 +Train: [84] [4300/6250] eta: 0:05:40 lr: 0.000008 grad: 0.1379 (0.1366) loss: 0.8137 (0.8122) time: 0.1437 data: 0.0526 max mem: 9390 +Train: [84] [4400/6250] eta: 0:05:22 lr: 0.000008 grad: 0.1316 (0.1366) loss: 0.8145 (0.8122) time: 0.1747 data: 0.0857 max mem: 9390 +Train: [84] [4500/6250] eta: 0:05:05 lr: 0.000008 grad: 0.1311 (0.1365) loss: 0.8076 (0.8122) time: 0.1705 data: 0.0811 max mem: 9390 +Train: [84] [4600/6250] eta: 0:04:48 lr: 0.000008 grad: 0.1352 (0.1366) loss: 0.8145 (0.8122) time: 0.1935 data: 0.1176 max mem: 9390 +pretraining fmri mae +start: 2026-04-02 10:08:38 +cwd: /data/connor/fmri-fm +sha: 7f4cedc35609f6857314e0d1ea6657523f17ddeb, status: has uncommitted changes, branch: dev/clane9 +config: +name: input_space_v3/flat_lr1e-3_4/pretrain +notes: input_space ablation v3 flat_lr1e-3_4; use tube masking and on-disk data (input_space=flat + base_lr=1e-3 seed=5404) +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain +input_space: flat +patch_size: 16 +num_frames: 16 +t_patch_size: 4 +mask_ratio: 0.9 +pred_mask_ratio: null +masking: tube +masking_kwargs: {} +mask_patch_size: null +model: mae_vit_base +model_kwargs: + decoding: attn + pos_embed: sep + target_norm: null + pca_norm_nc: 2 + t_pred_stride: 2 + no_decode_pos: true + mask_drop_scale: false + pred_edge_pad: 0 + gauss_sigma: null + class_token: true + reg_tokens: 0 + no_embed_class: true + head_init_scale: 0.0 + decoder_depth: 4 + drop_path_rate: 0.0 +datasets: + hcp-train: + type: wds + url: /data/fmri-datasets/pretrain/hcpya-all.${input_space}.wds/hcpya-all-${input_space}-{00000..01799}.tar + clipping: random + clipping_kwargs: + oversample: 4.0 + shuffle: true + buffer_size: 2000 + samples_per_epoch: 200000 + hcp-train-subset: + type: arrow + root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/validation + split_range: + - 0 + - 2000 + shuffle: false + hcp-val: + type: arrow + root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/test + split_range: + - 0 + - 2000 + shuffle: false +train_dataset: hcp-train +eval_datasets: +- hcp-train-subset +- hcp-val +val_dataset: null +clip_vmax: 3.0 +normalize: frame +tr_scale: null +crop_scale: null +crop_aspect: null +gray_jitter: null +num_workers: 16 +epochs: 100 +batch_size: 32 +accum_iter: 1 +base_lr: 0.001 +min_lr: 0.0 +warmup_epochs: 5 +weight_decay: 0.05 +betas: +- 0.9 +- 0.95 +clip_grad: 1.0 +amp: true +amp_dtype: float16 +ckpt: null +resume: true +auto_resume: true +start_epoch: 0 +max_checkpoints: 0 +checkpoint_period: null +plot_period: 5 +device: cuda +presend_cuda: false +seed: 5404 +debug: false +wandb: true +wandb_entity: null +wandb_project: fMRI-foundation-model +rank: 0 +world_size: 1 +gpu: 0 +distributed: true +dist_backend: nccl +in_chans: 1 +img_size: +- 224 +- 560 + +train transform: +Compose( + ToTensor() + TemporalCenterCrop(num_frames=16) + Normalize(mode='frame') + Clip(vmax=3.0) + FlatUnmask((224, 560)) +) +val transform: +Compose( + ToTensor() + TemporalCenterCrop(num_frames=16) + Normalize(mode='frame') + Clip(vmax=3.0) + FlatUnmask((224, 560)) +) +mask generator: +TubeMasking( + mask_ratio=0.9 + (patchify): Patchify2D((224, 560), (16, 16), in_chans=1) +) +loading dataset: hcp-train + +type: wds +url: /data/fmri-datasets/pretrain/hcpya-all.${input_space}.wds/hcpya-all-${input_space}-{00000..01799}.tar +clipping: random +clipping_kwargs: + oversample: 4.0 +shuffle: true +buffer_size: 2000 +samples_per_epoch: 200000 + +loading dataset: hcp-train-subset + +type: arrow +root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/validation +split_range: +- 0 +- 2000 +shuffle: false + +split indices: [899, 472, 767, 116, 1265, 1852, 300, 1335, 361, 1560] +loading dataset: hcp-val + +type: arrow +root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/test +split_range: +- 0 +- 2000 +shuffle: false + +split indices: [1075, 1189, 738, 1350, 965, 1964, 1367, 1183, 1619, 1407] +model: +MaskedAutoencoderViT( + decoding=attn, t_pred_stride=2, pred_edge_pad=0, no_decode_pos=True + (encoder): MaskedEncoder( + class_token=True, reg_tokens=0, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) + (pred_patchify): StridedPatchify3D((16, 224, 560), (2, 16, 16), in_chans=1, t_stride=2) + (decoder): MaskedDecoder( + cross_decode=False, class_token=True, no_embed_class=True + (pos_embed): SeparablePosEmbed(512, (4, 14, 35)) + (proj): Linear(in_features=768, out_features=512, bias=True) + (blocks): ModuleList( + (0-3): 4 x Block( + (norm1): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=16 + (q): Linear(in_features=512, out_features=512, bias=True) + (k): Linear(in_features=512, out_features=512, bias=True) + (v): Linear(in_features=512, out_features=512, bias=True) + (proj): Linear(in_features=512, out_features=512, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=512, out_features=2048, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=2048, out_features=512, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (head): Linear(in_features=512, out_features=512, bias=True) + ) +) +num params: 99.7M +total batch size: 32 = 32 bs per gpu x 1 accum x 1 gpus +lr: 1.25e-04 = 1.00e-03 x 32 / 256 +full schedule: epochs = 100 (steps = 625000) +warmup: epochs = 5 (steps = 31250) +loaded model state from checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +loaded optimizer state, resuming training from 84 +start training for 100 epochs +Train: [84] [ 0/6250] eta: 16:07:02 lr: 0.000009 grad: 0.1284 (0.1284) loss: 0.8159 (0.8159) time: 9.2836 data: 8.1296 max mem: 9353 +Train: [84] [ 100/6250] eta: 0:25:28 lr: 0.000009 grad: 0.1428 (0.1596) loss: 0.8326 (0.8262) time: 0.1616 data: 0.0376 max mem: 9390 +Train: [84] [ 200/6250] eta: 0:20:59 lr: 0.000009 grad: 0.1352 (0.1598) loss: 0.8186 (0.8218) time: 0.1725 data: 0.0709 max mem: 9390 +Train: [84] [ 300/6250] eta: 0:19:23 lr: 0.000008 grad: 0.1262 (0.1533) loss: 0.8175 (0.8194) time: 0.1732 data: 0.0773 max mem: 9390 +Train: [84] [ 400/6250] eta: 0:18:33 lr: 0.000008 grad: 0.1221 (0.1481) loss: 0.8134 (0.8185) time: 0.1793 data: 0.0846 max mem: 9390 +Train: [84] [ 500/6250] eta: 0:17:45 lr: 0.000008 grad: 0.1359 (0.1474) loss: 0.8155 (0.8174) time: 0.1800 data: 0.0825 max mem: 9390 +Train: [84] [ 600/6250] eta: 0:17:19 lr: 0.000008 grad: 0.1381 (0.1458) loss: 0.8112 (0.8165) time: 0.1997 data: 0.1116 max mem: 9390 +Train: [84] [ 700/6250] eta: 0:16:44 lr: 0.000008 grad: 0.1307 (0.1444) loss: 0.8152 (0.8163) time: 0.1465 data: 0.0420 max mem: 9390 +Train: [84] [ 800/6250] eta: 0:16:17 lr: 0.000008 grad: 0.1400 (0.1437) loss: 0.8091 (0.8158) time: 0.1559 data: 0.0553 max mem: 9390 +Train: [84] [ 900/6250] eta: 0:15:56 lr: 0.000008 grad: 0.1268 (0.1431) loss: 0.8175 (0.8156) time: 0.2005 data: 0.0900 max mem: 9390 +Train: [84] [1000/6250] eta: 0:15:33 lr: 0.000008 grad: 0.1391 (0.1430) loss: 0.8126 (0.8151) time: 0.1412 data: 0.0452 max mem: 9390 +Train: [84] [1100/6250] eta: 0:15:09 lr: 0.000008 grad: 0.1368 (0.1429) loss: 0.8129 (0.8147) time: 0.1571 data: 0.0595 max mem: 9390 +Train: [84] [1200/6250] eta: 0:14:46 lr: 0.000008 grad: 0.1413 (0.1427) loss: 0.8067 (0.8143) time: 0.1722 data: 0.0806 max mem: 9390 +Train: [84] [1300/6250] eta: 0:14:23 lr: 0.000008 grad: 0.1328 (0.1423) loss: 0.8058 (0.8138) time: 0.1630 data: 0.0740 max mem: 9390 +Train: [84] [1400/6250] eta: 0:14:00 lr: 0.000008 grad: 0.1442 (0.1421) loss: 0.8071 (0.8134) time: 0.1441 data: 0.0454 max mem: 9390 +Train: [84] [1500/6250] eta: 0:13:39 lr: 0.000008 grad: 0.1326 (0.1418) loss: 0.8101 (0.8129) time: 0.1492 data: 0.0577 max mem: 9390 +Train: [84] [1600/6250] eta: 0:13:17 lr: 0.000008 grad: 0.1410 (0.1414) loss: 0.7953 (0.8125) time: 0.1608 data: 0.0698 max mem: 9390 +Train: [84] [1700/6250] eta: 0:12:54 lr: 0.000008 grad: 0.1306 (0.1413) loss: 0.8062 (0.8123) time: 0.1528 data: 0.0584 max mem: 9390 +Train: [84] [1800/6250] eta: 0:12:36 lr: 0.000008 grad: 0.1307 (0.1410) loss: 0.8090 (0.8120) time: 0.1703 data: 0.0799 max mem: 9390 +Train: [84] [1900/6250] eta: 0:12:16 lr: 0.000008 grad: 0.1354 (0.1406) loss: 0.8078 (0.8119) time: 0.1705 data: 0.0813 max mem: 9390 +Train: [84] [2000/6250] eta: 0:11:58 lr: 0.000008 grad: 0.1327 (0.1403) loss: 0.8042 (0.8117) time: 0.1875 data: 0.0976 max mem: 9390 +Train: [84] [2100/6250] eta: 0:11:38 lr: 0.000008 grad: 0.1345 (0.1402) loss: 0.8096 (0.8116) time: 0.1277 data: 0.0221 max mem: 9390 +Train: [84] [2200/6250] eta: 0:11:19 lr: 0.000008 grad: 0.1281 (0.1401) loss: 0.8054 (0.8114) time: 0.1641 data: 0.0773 max mem: 9390 +Train: [84] [2300/6250] eta: 0:11:01 lr: 0.000008 grad: 0.1370 (0.1399) loss: 0.8111 (0.8112) time: 0.1491 data: 0.0608 max mem: 9390 +Train: [84] [2400/6250] eta: 0:10:43 lr: 0.000008 grad: 0.1378 (0.1400) loss: 0.8010 (0.8110) time: 0.1637 data: 0.0802 max mem: 9390 +Train: [84] [2500/6250] eta: 0:10:25 lr: 0.000008 grad: 0.1367 (0.1399) loss: 0.8041 (0.8108) time: 0.1659 data: 0.0753 max mem: 9390 +Train: [84] [2600/6250] eta: 0:10:07 lr: 0.000008 grad: 0.1363 (0.1398) loss: 0.8026 (0.8107) time: 0.1504 data: 0.0694 max mem: 9390 +Train: [84] [2700/6250] eta: 0:09:50 lr: 0.000008 grad: 0.1287 (0.1396) loss: 0.8103 (0.8106) time: 0.1591 data: 0.0672 max mem: 9390 +Train: [84] [2800/6250] eta: 0:09:33 lr: 0.000008 grad: 0.1440 (0.1395) loss: 0.8017 (0.8105) time: 0.1803 data: 0.0978 max mem: 9390 +Train: [84] [2900/6250] eta: 0:09:15 lr: 0.000008 grad: 0.1394 (0.1396) loss: 0.8056 (0.8103) time: 0.1709 data: 0.0784 max mem: 9390 +Train: [84] [3000/6250] eta: 0:08:58 lr: 0.000008 grad: 0.1385 (0.1396) loss: 0.8002 (0.8102) time: 0.1619 data: 0.0745 max mem: 9390 +Train: [84] [3100/6250] eta: 0:08:40 lr: 0.000008 grad: 0.1426 (0.1397) loss: 0.8047 (0.8100) time: 0.1651 data: 0.0755 max mem: 9390 +Train: [84] [3200/6250] eta: 0:08:23 lr: 0.000008 grad: 0.1371 (0.1398) loss: 0.8065 (0.8098) time: 0.1550 data: 0.0744 max mem: 9390 +Train: [84] [3300/6250] eta: 0:08:06 lr: 0.000008 grad: 0.1375 (0.1397) loss: 0.8040 (0.8098) time: 0.1599 data: 0.0753 max mem: 9390 +Train: [84] [3400/6250] eta: 0:07:49 lr: 0.000008 grad: 0.1334 (0.1397) loss: 0.8142 (0.8097) time: 0.1770 data: 0.0890 max mem: 9390 +Train: [84] [3500/6250] eta: 0:07:32 lr: 0.000008 grad: 0.1474 (0.1397) loss: 0.8011 (0.8096) time: 0.1275 data: 0.0493 max mem: 9390 +Train: [84] [3600/6250] eta: 0:07:15 lr: 0.000008 grad: 0.1333 (0.1397) loss: 0.8058 (0.8095) time: 0.1605 data: 0.0680 max mem: 9390 +Train: [84] [3700/6250] eta: 0:06:58 lr: 0.000008 grad: 0.1340 (0.1396) loss: 0.8084 (0.8095) time: 0.1680 data: 0.0768 max mem: 9390 +Train: [84] [3800/6250] eta: 0:06:42 lr: 0.000008 grad: 0.1229 (0.1394) loss: 0.8104 (0.8095) time: 0.1600 data: 0.0679 max mem: 9390 +Train: [84] [3900/6250] eta: 0:06:25 lr: 0.000008 grad: 0.1323 (0.1393) loss: 0.8032 (0.8095) time: 0.1536 data: 0.0635 max mem: 9390 +Train: [84] [4000/6250] eta: 0:06:08 lr: 0.000008 grad: 0.1299 (0.1391) loss: 0.8058 (0.8094) time: 0.1695 data: 0.0767 max mem: 9390 +Train: [84] [4100/6250] eta: 0:05:52 lr: 0.000008 grad: 0.1262 (0.1390) loss: 0.8113 (0.8094) time: 0.1565 data: 0.0727 max mem: 9390 +Train: [84] [4200/6250] eta: 0:05:35 lr: 0.000008 grad: 0.1353 (0.1388) loss: 0.8150 (0.8094) time: 0.1608 data: 0.0711 max mem: 9390 +Train: [84] [4300/6250] eta: 0:05:18 lr: 0.000008 grad: 0.1310 (0.1388) loss: 0.8082 (0.8094) time: 0.1442 data: 0.0547 max mem: 9390 +Train: [84] [4400/6250] eta: 0:05:02 lr: 0.000008 grad: 0.1326 (0.1386) loss: 0.8140 (0.8094) time: 0.1567 data: 0.0746 max mem: 9390 +Train: [84] [4500/6250] eta: 0:04:46 lr: 0.000008 grad: 0.1334 (0.1385) loss: 0.8124 (0.8095) time: 0.1634 data: 0.0750 max mem: 9390 +Train: [84] [4600/6250] eta: 0:04:29 lr: 0.000008 grad: 0.1210 (0.1384) loss: 0.8158 (0.8095) time: 0.1614 data: 0.0740 max mem: 9390 +Train: [84] [4700/6250] eta: 0:04:13 lr: 0.000008 grad: 0.1360 (0.1384) loss: 0.8067 (0.8096) time: 0.1671 data: 0.0765 max mem: 9390 +Train: [84] [4800/6250] eta: 0:03:56 lr: 0.000008 grad: 0.1325 (0.1383) loss: 0.8101 (0.8096) time: 0.1596 data: 0.0625 max mem: 9390 +Train: [84] [4900/6250] eta: 0:03:40 lr: 0.000008 grad: 0.1357 (0.1383) loss: 0.8149 (0.8097) time: 0.1524 data: 0.0610 max mem: 9390 +Train: [84] [5000/6250] eta: 0:03:23 lr: 0.000008 grad: 0.1361 (0.1382) loss: 0.8089 (0.8097) time: 0.1512 data: 0.0596 max mem: 9390 +Train: [84] [5100/6250] eta: 0:03:07 lr: 0.000008 grad: 0.1355 (0.1381) loss: 0.8145 (0.8098) time: 0.1449 data: 0.0549 max mem: 9390 +Train: [84] [5200/6250] eta: 0:02:50 lr: 0.000008 grad: 0.1330 (0.1381) loss: 0.8121 (0.8098) time: 0.1525 data: 0.0595 max mem: 9390 +Train: [84] [5300/6250] eta: 0:02:34 lr: 0.000008 grad: 0.1322 (0.1381) loss: 0.8173 (0.8099) time: 0.1551 data: 0.0692 max mem: 9390 +Train: [84] [5400/6250] eta: 0:02:18 lr: 0.000008 grad: 0.1291 (0.1380) loss: 0.8118 (0.8100) time: 0.1659 data: 0.0823 max mem: 9390 +Train: [84] [5500/6250] eta: 0:02:01 lr: 0.000008 grad: 0.1273 (0.1380) loss: 0.8164 (0.8101) time: 0.1583 data: 0.0749 max mem: 9390 +Train: [84] [5600/6250] eta: 0:01:45 lr: 0.000008 grad: 0.1297 (0.1379) loss: 0.8085 (0.8101) time: 0.1612 data: 0.0676 max mem: 9390 +Train: [84] [5700/6250] eta: 0:01:29 lr: 0.000008 grad: 0.1314 (0.1379) loss: 0.8137 (0.8101) time: 0.1592 data: 0.0798 max mem: 9390 +Train: [84] [5800/6250] eta: 0:01:13 lr: 0.000008 grad: 0.1380 (0.1379) loss: 0.8064 (0.8101) time: 0.1786 data: 0.0860 max mem: 9390 +Train: [84] [5900/6250] eta: 0:00:56 lr: 0.000008 grad: 0.1341 (0.1379) loss: 0.8124 (0.8102) time: 0.1493 data: 0.0697 max mem: 9390 +Train: [84] [6000/6250] eta: 0:00:40 lr: 0.000008 grad: 0.1373 (0.1379) loss: 0.8098 (0.8102) time: 0.1543 data: 0.0541 max mem: 9390 +Train: [84] [6100/6250] eta: 0:00:24 lr: 0.000008 grad: 0.1371 (0.1380) loss: 0.8097 (0.8102) time: 0.1795 data: 0.0888 max mem: 9390 +Train: [84] [6200/6250] eta: 0:00:08 lr: 0.000008 grad: 0.1395 (0.1381) loss: 0.8151 (0.8102) time: 0.1491 data: 0.0660 max mem: 9390 +Train: [84] [6249/6250] eta: 0:00:00 lr: 0.000008 grad: 0.1342 (0.1381) loss: 0.8135 (0.8102) time: 0.1651 data: 0.0769 max mem: 9390 +Train: [84] Total time: 0:16:58 (0.1630 s / it) +Averaged stats: lr: 0.000008 grad: 0.1342 (0.1381) loss: 0.8135 (0.8102) +Eval (hcp-train-subset): [84] [ 0/62] eta: 0:03:29 loss: 0.8283 (0.8283) time: 3.3753 data: 3.3034 max mem: 9390 +Eval (hcp-train-subset): [84] [61/62] eta: 0:00:00 loss: 0.8182 (0.8204) time: 0.1115 data: 0.0865 max mem: 9390 +Eval (hcp-train-subset): [84] Total time: 0:00:11 (0.1883 s / it) +Averaged stats (hcp-train-subset): loss: 0.8182 (0.8204) +Making plots (hcp-train-subset): example=24 +Eval (hcp-val): [84] [ 0/62] eta: 0:02:47 loss: 0.8253 (0.8253) time: 2.7003 data: 2.6334 max mem: 9390 +Eval (hcp-val): [84] [61/62] eta: 0:00:00 loss: 0.8282 (0.8294) time: 0.1036 data: 0.0780 max mem: 9390 +Eval (hcp-val): [84] Total time: 0:00:12 (0.2026 s / it) +Averaged stats (hcp-val): loss: 0.8282 (0.8294) +Making plots (hcp-val): example=24 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +Train: [85] [ 0/6250] eta: 10:38:49 lr: 0.000008 grad: 0.1840 (0.1840) loss: 0.8267 (0.8267) time: 6.1328 data: 6.0424 max mem: 9390 +Train: [85] [ 100/6250] eta: 0:21:56 lr: 0.000008 grad: 0.1494 (0.1707) loss: 0.8242 (0.8191) time: 0.1983 data: 0.1034 max mem: 9390 +Train: [85] [ 200/6250] eta: 0:19:10 lr: 0.000008 grad: 0.1333 (0.1618) loss: 0.8113 (0.8178) time: 0.1690 data: 0.0686 max mem: 9390 +Train: [85] [ 300/6250] eta: 0:18:04 lr: 0.000007 grad: 0.1315 (0.1550) loss: 0.8052 (0.8167) time: 0.1983 data: 0.1028 max mem: 9390 +Train: [85] [ 400/6250] eta: 0:17:40 lr: 0.000007 grad: 0.1291 (0.1489) loss: 0.8151 (0.8166) time: 0.1506 data: 0.0477 max mem: 9390 +Train: [85] [ 500/6250] eta: 0:17:15 lr: 0.000007 grad: 0.1336 (0.1465) loss: 0.8226 (0.8167) time: 0.1827 data: 0.0872 max mem: 9390 +Train: [85] [ 600/6250] eta: 0:16:49 lr: 0.000007 grad: 0.1345 (0.1447) loss: 0.8222 (0.8172) time: 0.1757 data: 0.0852 max mem: 9390 +Train: [85] [ 700/6250] eta: 0:16:24 lr: 0.000007 grad: 0.1268 (0.1439) loss: 0.8216 (0.8170) time: 0.1629 data: 0.0695 max mem: 9390 +Train: [85] [ 800/6250] eta: 0:16:01 lr: 0.000007 grad: 0.1329 (0.1428) loss: 0.8179 (0.8172) time: 0.1919 data: 0.1001 max mem: 9390 +Train: [85] [ 900/6250] eta: 0:15:34 lr: 0.000007 grad: 0.1269 (0.1419) loss: 0.8189 (0.8173) time: 0.1477 data: 0.0562 max mem: 9390 +Train: [85] [1000/6250] eta: 0:15:12 lr: 0.000007 grad: 0.1342 (0.1411) loss: 0.8174 (0.8172) time: 0.1687 data: 0.0799 max mem: 9390 +Train: [85] [1100/6250] eta: 0:14:51 lr: 0.000007 grad: 0.1238 (0.1402) loss: 0.8188 (0.8173) time: 0.1656 data: 0.0848 max mem: 9390 +Train: [85] [1200/6250] eta: 0:14:25 lr: 0.000007 grad: 0.1229 (0.1397) loss: 0.8168 (0.8172) time: 0.1516 data: 0.0670 max mem: 9390 +Train: [85] [1300/6250] eta: 0:14:03 lr: 0.000007 grad: 0.1299 (0.1392) loss: 0.8141 (0.8171) time: 0.1633 data: 0.0803 max mem: 9390 +Train: [85] [1400/6250] eta: 0:13:43 lr: 0.000007 grad: 0.1347 (0.1389) loss: 0.8109 (0.8169) time: 0.1711 data: 0.0808 max mem: 9390 +Train: [85] [1500/6250] eta: 0:13:23 lr: 0.000007 grad: 0.1331 (0.1387) loss: 0.8177 (0.8170) time: 0.1701 data: 0.0904 max mem: 9390 +Train: [85] [1600/6250] eta: 0:13:03 lr: 0.000007 grad: 0.1193 (0.1382) loss: 0.8190 (0.8170) time: 0.1648 data: 0.0788 max mem: 9390 +Train: [85] [1700/6250] eta: 0:12:44 lr: 0.000007 grad: 0.1297 (0.1382) loss: 0.8148 (0.8170) time: 0.1583 data: 0.0713 max mem: 9390 +Train: [85] [1800/6250] eta: 0:12:27 lr: 0.000007 grad: 0.1295 (0.1380) loss: 0.8091 (0.8170) time: 0.1778 data: 0.0961 max mem: 9390 +Train: [85] [1900/6250] eta: 0:12:08 lr: 0.000007 grad: 0.1312 (0.1379) loss: 0.8153 (0.8170) time: 0.1724 data: 0.0903 max mem: 9390 +Train: [85] [2000/6250] eta: 0:11:49 lr: 0.000007 grad: 0.1382 (0.1379) loss: 0.8073 (0.8169) time: 0.1411 data: 0.0522 max mem: 9390 +Train: [85] [2100/6250] eta: 0:11:32 lr: 0.000007 grad: 0.1336 (0.1380) loss: 0.8112 (0.8167) time: 0.1559 data: 0.0697 max mem: 9390 +Train: [85] [2200/6250] eta: 0:11:15 lr: 0.000007 grad: 0.1326 (0.1381) loss: 0.8146 (0.8165) time: 0.1492 data: 0.0665 max mem: 9390 +Train: [85] [2300/6250] eta: 0:10:57 lr: 0.000007 grad: 0.1362 (0.1382) loss: 0.8207 (0.8164) time: 0.1784 data: 0.0975 max mem: 9390 +Train: [85] [2400/6250] eta: 0:10:40 lr: 0.000007 grad: 0.1359 (0.1384) loss: 0.8181 (0.8163) time: 0.1587 data: 0.0653 max mem: 9390 +Train: [85] [2500/6250] eta: 0:10:23 lr: 0.000007 grad: 0.1357 (0.1386) loss: 0.8141 (0.8161) time: 0.1789 data: 0.0951 max mem: 9390 +Train: [85] [2600/6250] eta: 0:10:06 lr: 0.000007 grad: 0.1499 (0.1389) loss: 0.8071 (0.8158) time: 0.1698 data: 0.0834 max mem: 9390 +Train: [85] [2700/6250] eta: 0:09:49 lr: 0.000007 grad: 0.1345 (0.1390) loss: 0.8126 (0.8156) time: 0.1484 data: 0.0557 max mem: 9390 +Train: [85] [2800/6250] eta: 0:09:32 lr: 0.000007 grad: 0.1388 (0.1392) loss: 0.8059 (0.8154) time: 0.1607 data: 0.0777 max mem: 9390 +Train: [85] [2900/6250] eta: 0:09:15 lr: 0.000007 grad: 0.1368 (0.1394) loss: 0.8031 (0.8152) time: 0.1754 data: 0.0887 max mem: 9390 +Train: [85] [3000/6250] eta: 0:08:58 lr: 0.000007 grad: 0.1398 (0.1394) loss: 0.8113 (0.8150) time: 0.1478 data: 0.0639 max mem: 9390 +Train: [85] [3100/6250] eta: 0:08:41 lr: 0.000007 grad: 0.1298 (0.1393) loss: 0.8139 (0.8148) time: 0.1571 data: 0.0742 max mem: 9390 +Train: [85] [3200/6250] eta: 0:08:24 lr: 0.000007 grad: 0.1358 (0.1394) loss: 0.8105 (0.8147) time: 0.1641 data: 0.0809 max mem: 9390 +Train: [85] [3300/6250] eta: 0:08:08 lr: 0.000007 grad: 0.1374 (0.1393) loss: 0.8126 (0.8147) time: 0.1618 data: 0.0692 max mem: 9390 +Train: [85] [3400/6250] eta: 0:07:51 lr: 0.000007 grad: 0.1393 (0.1395) loss: 0.8143 (0.8146) time: 0.1581 data: 0.0726 max mem: 9390 +Train: [85] [3500/6250] eta: 0:07:34 lr: 0.000007 grad: 0.1348 (0.1395) loss: 0.8185 (0.8146) time: 0.1766 data: 0.0909 max mem: 9390 +Train: [85] [3600/6250] eta: 0:07:17 lr: 0.000007 grad: 0.1377 (0.1396) loss: 0.8080 (0.8146) time: 0.1597 data: 0.0732 max mem: 9390 +Train: [85] [3700/6250] eta: 0:07:00 lr: 0.000007 grad: 0.1348 (0.1396) loss: 0.8137 (0.8145) time: 0.1507 data: 0.0701 max mem: 9390 +Train: [85] [3800/6250] eta: 0:06:43 lr: 0.000007 grad: 0.1310 (0.1395) loss: 0.8191 (0.8145) time: 0.1427 data: 0.0564 max mem: 9390 +Train: [85] [3900/6250] eta: 0:06:27 lr: 0.000007 grad: 0.1298 (0.1394) loss: 0.8137 (0.8145) time: 0.1439 data: 0.0609 max mem: 9390 +Train: [85] [4000/6250] eta: 0:06:10 lr: 0.000007 grad: 0.1318 (0.1394) loss: 0.8136 (0.8144) time: 0.1592 data: 0.0743 max mem: 9390 +Train: [85] [4100/6250] eta: 0:05:53 lr: 0.000007 grad: 0.1225 (0.1393) loss: 0.8185 (0.8144) time: 0.1866 data: 0.0965 max mem: 9390 +Train: [85] [4200/6250] eta: 0:05:37 lr: 0.000007 grad: 0.1377 (0.1393) loss: 0.8154 (0.8144) time: 0.1695 data: 0.0798 max mem: 9390 +Train: [85] [4300/6250] eta: 0:05:20 lr: 0.000007 grad: 0.1394 (0.1392) loss: 0.8150 (0.8143) time: 0.1771 data: 0.0910 max mem: 9390 +Train: [85] [4400/6250] eta: 0:05:04 lr: 0.000007 grad: 0.1289 (0.1392) loss: 0.8162 (0.8143) time: 0.1569 data: 0.0601 max mem: 9390 +Train: [85] [4500/6250] eta: 0:04:47 lr: 0.000007 grad: 0.1219 (0.1391) loss: 0.8205 (0.8143) time: 0.1552 data: 0.0686 max mem: 9390 +Train: [85] [4600/6250] eta: 0:04:31 lr: 0.000007 grad: 0.1306 (0.1391) loss: 0.8162 (0.8142) time: 0.1678 data: 0.0843 max mem: 9390 +Train: [85] [4700/6250] eta: 0:04:14 lr: 0.000007 grad: 0.1303 (0.1391) loss: 0.8247 (0.8142) time: 0.1740 data: 0.0923 max mem: 9390 +Train: [85] [4800/6250] eta: 0:03:57 lr: 0.000007 grad: 0.1277 (0.1391) loss: 0.8134 (0.8141) time: 0.1586 data: 0.0802 max mem: 9390 +Train: [85] [4900/6250] eta: 0:03:41 lr: 0.000007 grad: 0.1337 (0.1391) loss: 0.8150 (0.8140) time: 0.1501 data: 0.0660 max mem: 9390 +Train: [85] [5000/6250] eta: 0:03:24 lr: 0.000007 grad: 0.1336 (0.1391) loss: 0.8134 (0.8140) time: 0.1662 data: 0.0769 max mem: 9390 +Train: [85] [5100/6250] eta: 0:03:07 lr: 0.000007 grad: 0.1351 (0.1390) loss: 0.8164 (0.8140) time: 0.1678 data: 0.0746 max mem: 9390 +Train: [85] [5200/6250] eta: 0:02:51 lr: 0.000007 grad: 0.1404 (0.1390) loss: 0.8115 (0.8139) time: 0.1651 data: 0.0716 max mem: 9390 +Train: [85] [5300/6250] eta: 0:02:35 lr: 0.000007 grad: 0.1339 (0.1389) loss: 0.8074 (0.8139) time: 0.1803 data: 0.0887 max mem: 9390 +Train: [85] [5400/6250] eta: 0:02:19 lr: 0.000007 grad: 0.1421 (0.1389) loss: 0.8115 (0.8138) time: 0.1671 data: 0.0749 max mem: 9390 +Train: [85] [5500/6250] eta: 0:02:02 lr: 0.000007 grad: 0.1252 (0.1389) loss: 0.8211 (0.8138) time: 0.1532 data: 0.0567 max mem: 9390 +Train: [85] [5600/6250] eta: 0:01:46 lr: 0.000007 grad: 0.1365 (0.1389) loss: 0.8067 (0.8137) time: 0.1378 data: 0.0371 max mem: 9390 +Train: [85] [5700/6250] eta: 0:01:29 lr: 0.000007 grad: 0.1322 (0.1389) loss: 0.8138 (0.8137) time: 0.1790 data: 0.0889 max mem: 9390 +Train: [85] [5800/6250] eta: 0:01:13 lr: 0.000007 grad: 0.1450 (0.1389) loss: 0.8089 (0.8136) time: 0.1694 data: 0.0776 max mem: 9390 +Train: [85] [5900/6250] eta: 0:00:57 lr: 0.000007 grad: 0.1278 (0.1388) loss: 0.8139 (0.8136) time: 0.1819 data: 0.0869 max mem: 9390 +Train: [85] [6000/6250] eta: 0:00:40 lr: 0.000007 grad: 0.1350 (0.1389) loss: 0.8134 (0.8136) time: 0.1561 data: 0.0586 max mem: 9390 +Train: [85] [6100/6250] eta: 0:00:24 lr: 0.000007 grad: 0.1343 (0.1388) loss: 0.8184 (0.8136) time: 0.1599 data: 0.0702 max mem: 9390 +Train: [85] [6200/6250] eta: 0:00:08 lr: 0.000007 grad: 0.1484 (0.1388) loss: 0.8038 (0.8135) time: 0.1658 data: 0.0735 max mem: 9390 +Train: [85] [6249/6250] eta: 0:00:00 lr: 0.000007 grad: 0.1392 (0.1389) loss: 0.8072 (0.8135) time: 0.1663 data: 0.0742 max mem: 9390 +Train: [85] Total time: 0:17:04 (0.1639 s / it) +Averaged stats: lr: 0.000007 grad: 0.1392 (0.1389) loss: 0.8072 (0.8135) +Eval (hcp-train-subset): [85] [ 0/62] eta: 0:03:12 loss: 0.8289 (0.8289) time: 3.1117 data: 3.0504 max mem: 9390 +Eval (hcp-train-subset): [85] [61/62] eta: 0:00:00 loss: 0.8164 (0.8192) time: 0.1419 data: 0.1166 max mem: 9390 +Eval (hcp-train-subset): [85] Total time: 0:00:12 (0.2061 s / it) +Averaged stats (hcp-train-subset): loss: 0.8164 (0.8192) +Eval (hcp-val): [85] [ 0/62] eta: 0:03:16 loss: 0.8277 (0.8277) time: 3.1629 data: 3.1066 max mem: 9390 +Eval (hcp-val): [85] [61/62] eta: 0:00:00 loss: 0.8277 (0.8296) time: 0.1260 data: 0.0999 max mem: 9390 +Eval (hcp-val): [85] Total time: 0:00:13 (0.2185 s / it) +Averaged stats (hcp-val): loss: 0.8277 (0.8296) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +Train: [86] [ 0/6250] eta: 11:03:00 lr: 0.000007 grad: 0.3797 (0.3797) loss: 0.7968 (0.7968) time: 6.3649 data: 6.2469 max mem: 9390 +Train: [86] [ 100/6250] eta: 0:22:28 lr: 0.000007 grad: 0.1607 (0.1853) loss: 0.8214 (0.8139) time: 0.1567 data: 0.0607 max mem: 9390 +Train: [86] [ 200/6250] eta: 0:21:29 lr: 0.000007 grad: 0.1385 (0.1680) loss: 0.8261 (0.8145) time: 0.2160 data: 0.1056 max mem: 9390 +Train: [86] [ 300/6250] eta: 0:19:54 lr: 0.000007 grad: 0.1331 (0.1569) loss: 0.8265 (0.8174) time: 0.1673 data: 0.0733 max mem: 9390 +Train: [86] [ 400/6250] eta: 0:18:54 lr: 0.000007 grad: 0.1278 (0.1527) loss: 0.8171 (0.8169) time: 0.1494 data: 0.0546 max mem: 9390 +Train: [86] [ 500/6250] eta: 0:18:10 lr: 0.000007 grad: 0.1436 (0.1504) loss: 0.8104 (0.8158) time: 0.1704 data: 0.0847 max mem: 9390 +Train: [86] [ 600/6250] eta: 0:17:35 lr: 0.000006 grad: 0.1432 (0.1488) loss: 0.8159 (0.8154) time: 0.1625 data: 0.0671 max mem: 9390 +Train: [86] [ 700/6250] eta: 0:17:09 lr: 0.000006 grad: 0.1365 (0.1482) loss: 0.8096 (0.8149) time: 0.1644 data: 0.0713 max mem: 9390 +Train: [86] [ 800/6250] eta: 0:16:42 lr: 0.000006 grad: 0.1395 (0.1475) loss: 0.8093 (0.8145) time: 0.1521 data: 0.0579 max mem: 9390 +Train: [86] [ 900/6250] eta: 0:16:13 lr: 0.000006 grad: 0.1346 (0.1467) loss: 0.8082 (0.8142) time: 0.1527 data: 0.0667 max mem: 9390 +Train: [86] [1000/6250] eta: 0:15:41 lr: 0.000006 grad: 0.1383 (0.1462) loss: 0.8091 (0.8139) time: 0.1301 data: 0.0336 max mem: 9390 +Train: [86] [1100/6250] eta: 0:15:15 lr: 0.000006 grad: 0.1321 (0.1452) loss: 0.8120 (0.8137) time: 0.1579 data: 0.0722 max mem: 9390 +Train: [86] [1200/6250] eta: 0:14:48 lr: 0.000006 grad: 0.1303 (0.1446) loss: 0.8123 (0.8134) time: 0.1589 data: 0.0700 max mem: 9390 +Train: [86] [1300/6250] eta: 0:14:26 lr: 0.000006 grad: 0.1399 (0.1441) loss: 0.8097 (0.8130) time: 0.1739 data: 0.0799 max mem: 9390 +Train: [86] [1400/6250] eta: 0:14:03 lr: 0.000006 grad: 0.1245 (0.1433) loss: 0.8148 (0.8130) time: 0.1681 data: 0.0786 max mem: 9390 +Train: [86] [1500/6250] eta: 0:13:42 lr: 0.000006 grad: 0.1275 (0.1429) loss: 0.8084 (0.8130) time: 0.1657 data: 0.0790 max mem: 9390 +Train: [86] [1600/6250] eta: 0:13:22 lr: 0.000006 grad: 0.1319 (0.1426) loss: 0.8109 (0.8129) time: 0.1610 data: 0.0660 max mem: 9390 +Train: [86] [1700/6250] eta: 0:13:02 lr: 0.000006 grad: 0.1407 (0.1420) loss: 0.8056 (0.8129) time: 0.1793 data: 0.0866 max mem: 9390 +Train: [86] [1800/6250] eta: 0:12:43 lr: 0.000006 grad: 0.1399 (0.1418) loss: 0.8059 (0.8128) time: 0.1775 data: 0.0900 max mem: 9390 +Train: [86] [1900/6250] eta: 0:12:22 lr: 0.000006 grad: 0.1237 (0.1414) loss: 0.8181 (0.8129) time: 0.1435 data: 0.0433 max mem: 9390 +Train: [86] [2000/6250] eta: 0:12:04 lr: 0.000006 grad: 0.1170 (0.1408) loss: 0.8183 (0.8129) time: 0.1552 data: 0.0650 max mem: 9390 +Train: [86] [2100/6250] eta: 0:11:45 lr: 0.000006 grad: 0.1341 (0.1404) loss: 0.8144 (0.8130) time: 0.1580 data: 0.0729 max mem: 9390 +Train: [86] [2200/6250] eta: 0:11:27 lr: 0.000006 grad: 0.1299 (0.1400) loss: 0.8152 (0.8130) time: 0.1647 data: 0.0697 max mem: 9390 +Train: [86] [2300/6250] eta: 0:11:10 lr: 0.000006 grad: 0.1397 (0.1398) loss: 0.8080 (0.8130) time: 0.1641 data: 0.0719 max mem: 9390 +Train: [86] [2400/6250] eta: 0:10:51 lr: 0.000006 grad: 0.1278 (0.1396) loss: 0.8193 (0.8130) time: 0.1570 data: 0.0644 max mem: 9390 +Train: [86] [2500/6250] eta: 0:10:33 lr: 0.000006 grad: 0.1403 (0.1396) loss: 0.8101 (0.8131) time: 0.1542 data: 0.0674 max mem: 9390 +Train: [86] [2600/6250] eta: 0:10:14 lr: 0.000006 grad: 0.1304 (0.1395) loss: 0.8091 (0.8131) time: 0.1519 data: 0.0565 max mem: 9390 +Train: [86] [2700/6250] eta: 0:09:56 lr: 0.000006 grad: 0.1351 (0.1394) loss: 0.8125 (0.8130) time: 0.1467 data: 0.0562 max mem: 9390 +Train: [86] [2800/6250] eta: 0:09:39 lr: 0.000006 grad: 0.1359 (0.1393) loss: 0.8138 (0.8130) time: 0.1650 data: 0.0715 max mem: 9390 +Train: [86] [2900/6250] eta: 0:09:21 lr: 0.000006 grad: 0.1335 (0.1393) loss: 0.8123 (0.8129) time: 0.1463 data: 0.0528 max mem: 9390 +Train: [86] [3000/6250] eta: 0:09:04 lr: 0.000006 grad: 0.1296 (0.1392) loss: 0.8123 (0.8129) time: 0.1560 data: 0.0663 max mem: 9390 +Train: [86] [3100/6250] eta: 0:08:47 lr: 0.000006 grad: 0.1369 (0.1391) loss: 0.8171 (0.8129) time: 0.1684 data: 0.0833 max mem: 9390 +Train: [86] [3200/6250] eta: 0:08:30 lr: 0.000006 grad: 0.1306 (0.1390) loss: 0.8169 (0.8129) time: 0.1490 data: 0.0633 max mem: 9390 +Train: [86] [3300/6250] eta: 0:08:13 lr: 0.000006 grad: 0.1296 (0.1389) loss: 0.8125 (0.8128) time: 0.1657 data: 0.0748 max mem: 9390 +Train: [86] [3400/6250] eta: 0:07:56 lr: 0.000006 grad: 0.1388 (0.1388) loss: 0.8117 (0.8128) time: 0.1548 data: 0.0696 max mem: 9390 +Train: [86] [3500/6250] eta: 0:07:39 lr: 0.000006 grad: 0.1268 (0.1388) loss: 0.8123 (0.8127) time: 0.1343 data: 0.0445 max mem: 9390 +Train: [86] [3600/6250] eta: 0:07:22 lr: 0.000006 grad: 0.1284 (0.1387) loss: 0.8104 (0.8127) time: 0.1648 data: 0.0745 max mem: 9390 +Train: [86] [3700/6250] eta: 0:07:05 lr: 0.000006 grad: 0.1262 (0.1386) loss: 0.8083 (0.8127) time: 0.1657 data: 0.0764 max mem: 9390 +Train: [86] [3800/6250] eta: 0:06:49 lr: 0.000006 grad: 0.1311 (0.1385) loss: 0.8138 (0.8126) time: 0.1869 data: 0.0999 max mem: 9390 +Train: [86] [3900/6250] eta: 0:06:32 lr: 0.000006 grad: 0.1280 (0.1385) loss: 0.8133 (0.8125) time: 0.1572 data: 0.0697 max mem: 9390 +Train: [86] [4000/6250] eta: 0:06:14 lr: 0.000006 grad: 0.1310 (0.1384) loss: 0.8122 (0.8125) time: 0.1490 data: 0.0582 max mem: 9390 +Train: [86] [4100/6250] eta: 0:05:58 lr: 0.000006 grad: 0.1260 (0.1383) loss: 0.8156 (0.8125) time: 0.1696 data: 0.0846 max mem: 9390 +Train: [86] [4200/6250] eta: 0:05:42 lr: 0.000006 grad: 0.1310 (0.1383) loss: 0.8097 (0.8124) time: 0.2018 data: 0.1159 max mem: 9390 +Train: [86] [4300/6250] eta: 0:05:25 lr: 0.000006 grad: 0.1331 (0.1383) loss: 0.8121 (0.8124) time: 0.1755 data: 0.0905 max mem: 9390 +Train: [86] [4400/6250] eta: 0:05:08 lr: 0.000006 grad: 0.1356 (0.1382) loss: 0.8115 (0.8124) time: 0.1551 data: 0.0639 max mem: 9390 +Train: [86] [4500/6250] eta: 0:04:51 lr: 0.000006 grad: 0.1384 (0.1382) loss: 0.8100 (0.8123) time: 0.1677 data: 0.0706 max mem: 9390 +Train: [86] [4600/6250] eta: 0:04:34 lr: 0.000006 grad: 0.1396 (0.1383) loss: 0.8065 (0.8122) time: 0.1671 data: 0.0792 max mem: 9390 +Train: [86] [4700/6250] eta: 0:04:18 lr: 0.000006 grad: 0.1431 (0.1383) loss: 0.8060 (0.8121) time: 0.1753 data: 0.0861 max mem: 9390 +Train: [86] [4800/6250] eta: 0:04:01 lr: 0.000006 grad: 0.1411 (0.1385) loss: 0.8112 (0.8120) time: 0.1644 data: 0.0718 max mem: 9390 +Train: [86] [4900/6250] eta: 0:03:44 lr: 0.000006 grad: 0.1334 (0.1385) loss: 0.8115 (0.8120) time: 0.1578 data: 0.0658 max mem: 9390 +Train: [86] [5000/6250] eta: 0:03:28 lr: 0.000006 grad: 0.1343 (0.1385) loss: 0.8154 (0.8120) time: 0.1730 data: 0.0797 max mem: 9390 +Train: [86] [5100/6250] eta: 0:03:11 lr: 0.000006 grad: 0.1373 (0.1386) loss: 0.8075 (0.8119) time: 0.1679 data: 0.0683 max mem: 9390 +Train: [86] [5200/6250] eta: 0:02:54 lr: 0.000006 grad: 0.1393 (0.1386) loss: 0.8127 (0.8119) time: 0.1439 data: 0.0462 max mem: 9390 +Train: [86] [5300/6250] eta: 0:02:37 lr: 0.000006 grad: 0.1416 (0.1387) loss: 0.8031 (0.8119) time: 0.1778 data: 0.0860 max mem: 9390 +Train: [86] [5400/6250] eta: 0:02:21 lr: 0.000006 grad: 0.1383 (0.1387) loss: 0.8104 (0.8118) time: 0.1647 data: 0.0733 max mem: 9390 +Train: [86] [5500/6250] eta: 0:02:04 lr: 0.000006 grad: 0.1309 (0.1388) loss: 0.8069 (0.8118) time: 0.1701 data: 0.0792 max mem: 9390 +Train: [86] [5600/6250] eta: 0:01:47 lr: 0.000006 grad: 0.1363 (0.1388) loss: 0.8138 (0.8117) time: 0.1679 data: 0.0757 max mem: 9390 +Train: [86] [5700/6250] eta: 0:01:31 lr: 0.000006 grad: 0.1352 (0.1388) loss: 0.8122 (0.8117) time: 0.1556 data: 0.0712 max mem: 9390 +Train: [86] [5800/6250] eta: 0:01:14 lr: 0.000006 grad: 0.1351 (0.1388) loss: 0.8092 (0.8117) time: 0.1622 data: 0.0745 max mem: 9390 +Train: [86] [5900/6250] eta: 0:00:58 lr: 0.000006 grad: 0.1376 (0.1388) loss: 0.8111 (0.8117) time: 0.1924 data: 0.1013 max mem: 9390 +Train: [86] [6000/6250] eta: 0:00:41 lr: 0.000006 grad: 0.1407 (0.1388) loss: 0.8127 (0.8117) time: 0.1601 data: 0.0717 max mem: 9390 +Train: [86] [6100/6250] eta: 0:00:24 lr: 0.000006 grad: 0.1366 (0.1388) loss: 0.8094 (0.8117) time: 0.1868 data: 0.1101 max mem: 9390 +Train: [86] [6200/6250] eta: 0:00:08 lr: 0.000006 grad: 0.1357 (0.1388) loss: 0.8040 (0.8117) time: 0.1897 data: 0.1002 max mem: 9390 +Train: [86] [6249/6250] eta: 0:00:00 lr: 0.000006 grad: 0.1431 (0.1389) loss: 0.8030 (0.8116) time: 0.1743 data: 0.0916 max mem: 9390 +Train: [86] Total time: 0:17:23 (0.1669 s / it) +Averaged stats: lr: 0.000006 grad: 0.1431 (0.1389) loss: 0.8030 (0.8116) +Eval (hcp-train-subset): [86] [ 0/62] eta: 0:02:42 loss: 0.8281 (0.8281) time: 2.6145 data: 2.5493 max mem: 9390 +Eval (hcp-train-subset): [86] [61/62] eta: 0:00:00 loss: 0.8161 (0.8191) time: 0.1270 data: 0.1001 max mem: 9390 +Eval (hcp-train-subset): [86] Total time: 0:00:13 (0.2130 s / it) +Averaged stats (hcp-train-subset): loss: 0.8161 (0.8191) +Eval (hcp-val): [86] [ 0/62] eta: 0:02:54 loss: 0.8237 (0.8237) time: 2.8151 data: 2.7506 max mem: 9390 +Eval (hcp-val): [86] [61/62] eta: 0:00:00 loss: 0.8268 (0.8289) time: 0.1302 data: 0.1028 max mem: 9390 +Eval (hcp-val): [86] Total time: 0:00:13 (0.2136 s / it) +Averaged stats (hcp-val): loss: 0.8268 (0.8289) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +Train: [87] [ 0/6250] eta: 6:45:58 lr: 0.000006 grad: 0.0826 (0.0826) loss: 0.8702 (0.8702) time: 3.8973 data: 3.6074 max mem: 9390 +Train: [87] [ 100/6250] eta: 0:21:48 lr: 0.000006 grad: 0.1355 (0.1753) loss: 0.8207 (0.8191) time: 0.1625 data: 0.0603 max mem: 9390 +Train: [87] [ 200/6250] eta: 0:19:26 lr: 0.000006 grad: 0.1334 (0.1656) loss: 0.8198 (0.8164) time: 0.1454 data: 0.0483 max mem: 9390 +Train: [87] [ 300/6250] eta: 0:18:45 lr: 0.000006 grad: 0.1547 (0.1615) loss: 0.8030 (0.8137) time: 0.1795 data: 0.0652 max mem: 9390 +Train: [87] [ 400/6250] eta: 0:18:56 lr: 0.000006 grad: 0.1463 (0.1610) loss: 0.8051 (0.8118) time: 0.1951 data: 0.0932 max mem: 9390 +Train: [87] [ 500/6250] eta: 0:18:19 lr: 0.000006 grad: 0.1404 (0.1587) loss: 0.7991 (0.8107) time: 0.1834 data: 0.0861 max mem: 9390 +Train: [87] [ 600/6250] eta: 0:17:48 lr: 0.000006 grad: 0.1470 (0.1573) loss: 0.8093 (0.8105) time: 0.2059 data: 0.1139 max mem: 9390 +Train: [87] [ 700/6250] eta: 0:17:16 lr: 0.000006 grad: 0.1362 (0.1555) loss: 0.8040 (0.8104) time: 0.1646 data: 0.0677 max mem: 9390 +Train: [87] [ 800/6250] eta: 0:16:46 lr: 0.000006 grad: 0.1389 (0.1547) loss: 0.8149 (0.8104) time: 0.1808 data: 0.0991 max mem: 9390 +Train: [87] [ 900/6250] eta: 0:16:19 lr: 0.000006 grad: 0.1502 (0.1540) loss: 0.8079 (0.8106) time: 0.1683 data: 0.0574 max mem: 9390 +Train: [87] [1000/6250] eta: 0:15:54 lr: 0.000006 grad: 0.1403 (0.1533) loss: 0.8138 (0.8106) time: 0.1800 data: 0.0886 max mem: 9390 +Train: [87] [1100/6250] eta: 0:15:27 lr: 0.000006 grad: 0.1385 (0.1525) loss: 0.8096 (0.8106) time: 0.1588 data: 0.0741 max mem: 9390 +Train: [87] [1200/6250] eta: 0:15:03 lr: 0.000006 grad: 0.1412 (0.1517) loss: 0.8132 (0.8106) time: 0.1740 data: 0.0907 max mem: 9390 +Train: [87] [1300/6250] eta: 0:14:37 lr: 0.000006 grad: 0.1447 (0.1511) loss: 0.8024 (0.8105) time: 0.1214 data: 0.0293 max mem: 9390 +Train: [87] [1400/6250] eta: 0:14:17 lr: 0.000005 grad: 0.1438 (0.1507) loss: 0.8076 (0.8102) time: 0.1791 data: 0.0952 max mem: 9390 +Train: [87] [1500/6250] eta: 0:13:53 lr: 0.000005 grad: 0.1362 (0.1501) loss: 0.8114 (0.8101) time: 0.1592 data: 0.0714 max mem: 9390 +Train: [87] [1600/6250] eta: 0:13:30 lr: 0.000005 grad: 0.1401 (0.1498) loss: 0.8057 (0.8099) time: 0.1305 data: 0.0322 max mem: 9390 +Train: [87] [1700/6250] eta: 0:13:11 lr: 0.000005 grad: 0.1331 (0.1495) loss: 0.8073 (0.8097) time: 0.1330 data: 0.0500 max mem: 9390 +Train: [87] [1800/6250] eta: 0:12:51 lr: 0.000005 grad: 0.1407 (0.1491) loss: 0.8080 (0.8095) time: 0.1773 data: 0.0896 max mem: 9390 +Train: [87] [1900/6250] eta: 0:12:30 lr: 0.000005 grad: 0.1450 (0.1488) loss: 0.8067 (0.8093) time: 0.1448 data: 0.0655 max mem: 9390 +Train: [87] [2000/6250] eta: 0:12:10 lr: 0.000005 grad: 0.1346 (0.1485) loss: 0.8180 (0.8092) time: 0.1628 data: 0.0659 max mem: 9390 +Train: [87] [2100/6250] eta: 0:11:50 lr: 0.000005 grad: 0.1412 (0.1483) loss: 0.8108 (0.8091) time: 0.1608 data: 0.0720 max mem: 9390 +Train: [87] [2200/6250] eta: 0:11:31 lr: 0.000005 grad: 0.1415 (0.1480) loss: 0.8048 (0.8091) time: 0.1785 data: 0.0926 max mem: 9390 +Train: [87] [2300/6250] eta: 0:11:12 lr: 0.000005 grad: 0.1327 (0.1475) loss: 0.8099 (0.8092) time: 0.1577 data: 0.0608 max mem: 9390 +Train: [87] [2400/6250] eta: 0:10:53 lr: 0.000005 grad: 0.1363 (0.1473) loss: 0.8080 (0.8092) time: 0.1640 data: 0.0724 max mem: 9390 +Train: [87] [2500/6250] eta: 0:10:35 lr: 0.000005 grad: 0.1323 (0.1471) loss: 0.8136 (0.8093) time: 0.1687 data: 0.0789 max mem: 9390 +Train: [87] [2600/6250] eta: 0:10:17 lr: 0.000005 grad: 0.1447 (0.1471) loss: 0.8190 (0.8094) time: 0.1355 data: 0.0466 max mem: 9390 +Train: [87] [2700/6250] eta: 0:09:58 lr: 0.000005 grad: 0.1327 (0.1469) loss: 0.8052 (0.8095) time: 0.1419 data: 0.0552 max mem: 9390 +Train: [87] [2800/6250] eta: 0:09:40 lr: 0.000005 grad: 0.1373 (0.1466) loss: 0.8148 (0.8094) time: 0.1465 data: 0.0620 max mem: 9390 +Train: [87] [2900/6250] eta: 0:09:23 lr: 0.000005 grad: 0.1295 (0.1464) loss: 0.8159 (0.8094) time: 0.1577 data: 0.0726 max mem: 9390 +Train: [87] [3000/6250] eta: 0:09:06 lr: 0.000005 grad: 0.1329 (0.1461) loss: 0.8126 (0.8094) time: 0.1715 data: 0.0886 max mem: 9390 +Train: [87] [3100/6250] eta: 0:08:49 lr: 0.000005 grad: 0.1332 (0.1459) loss: 0.8152 (0.8095) time: 0.1552 data: 0.0631 max mem: 9390 +Train: [87] [3200/6250] eta: 0:08:32 lr: 0.000005 grad: 0.1433 (0.1457) loss: 0.8047 (0.8095) time: 0.1734 data: 0.0774 max mem: 9390 +Train: [87] [3300/6250] eta: 0:08:14 lr: 0.000005 grad: 0.1402 (0.1456) loss: 0.8106 (0.8095) time: 0.1666 data: 0.0812 max mem: 9390 +Train: [87] [3400/6250] eta: 0:07:58 lr: 0.000005 grad: 0.1349 (0.1455) loss: 0.8125 (0.8095) time: 0.1671 data: 0.0811 max mem: 9390 +Train: [87] [3500/6250] eta: 0:07:41 lr: 0.000005 grad: 0.1406 (0.1454) loss: 0.8074 (0.8095) time: 0.1854 data: 0.1025 max mem: 9390 +Train: [87] [3600/6250] eta: 0:07:25 lr: 0.000005 grad: 0.1375 (0.1453) loss: 0.8090 (0.8095) time: 0.1648 data: 0.0882 max mem: 9390 +Train: [87] [3700/6250] eta: 0:07:08 lr: 0.000005 grad: 0.1296 (0.1452) loss: 0.8164 (0.8095) time: 0.1395 data: 0.0561 max mem: 9390 +Train: [87] [3800/6250] eta: 0:06:51 lr: 0.000005 grad: 0.1381 (0.1451) loss: 0.8140 (0.8096) time: 0.1531 data: 0.0724 max mem: 9390 +Train: [87] [3900/6250] eta: 0:06:34 lr: 0.000005 grad: 0.1306 (0.1450) loss: 0.8090 (0.8096) time: 0.1622 data: 0.0833 max mem: 9390 +Train: [87] [4000/6250] eta: 0:06:17 lr: 0.000005 grad: 0.1443 (0.1448) loss: 0.8126 (0.8097) time: 0.1711 data: 0.0716 max mem: 9390 +Train: [87] [4100/6250] eta: 0:06:00 lr: 0.000005 grad: 0.1372 (0.1446) loss: 0.8123 (0.8098) time: 0.1470 data: 0.0519 max mem: 9390 +Train: [87] [4200/6250] eta: 0:05:43 lr: 0.000005 grad: 0.1320 (0.1444) loss: 0.8149 (0.8100) time: 0.1842 data: 0.0936 max mem: 9390 +Train: [87] [4300/6250] eta: 0:05:26 lr: 0.000005 grad: 0.1307 (0.1441) loss: 0.8177 (0.8101) time: 0.1774 data: 0.0746 max mem: 9390 +Train: [87] [4400/6250] eta: 0:05:09 lr: 0.000005 grad: 0.1275 (0.1439) loss: 0.8172 (0.8103) time: 0.1333 data: 0.0481 max mem: 9390 +Train: [87] [4500/6250] eta: 0:04:52 lr: 0.000005 grad: 0.1383 (0.1437) loss: 0.8150 (0.8104) time: 0.1674 data: 0.0697 max mem: 9390 +Train: [87] [4600/6250] eta: 0:04:35 lr: 0.000005 grad: 0.1322 (0.1435) loss: 0.8159 (0.8105) time: 0.1768 data: 0.0855 max mem: 9390 +Train: [87] [4700/6250] eta: 0:04:19 lr: 0.000005 grad: 0.1317 (0.1434) loss: 0.8165 (0.8106) time: 0.1638 data: 0.0685 max mem: 9390 +Train: [87] [4800/6250] eta: 0:04:02 lr: 0.000005 grad: 0.1330 (0.1433) loss: 0.8169 (0.8107) time: 0.1769 data: 0.0867 max mem: 9390 +Train: [87] [4900/6250] eta: 0:03:45 lr: 0.000005 grad: 0.1270 (0.1431) loss: 0.8188 (0.8107) time: 0.1672 data: 0.0822 max mem: 9390 +Train: [87] [5000/6250] eta: 0:03:29 lr: 0.000005 grad: 0.1358 (0.1430) loss: 0.8128 (0.8108) time: 0.1769 data: 0.0803 max mem: 9390 +Train: [87] [5100/6250] eta: 0:03:12 lr: 0.000005 grad: 0.1391 (0.1429) loss: 0.8142 (0.8109) time: 0.1432 data: 0.0461 max mem: 9390 +Train: [87] [5200/6250] eta: 0:02:55 lr: 0.000005 grad: 0.1357 (0.1428) loss: 0.8129 (0.8109) time: 0.1745 data: 0.0799 max mem: 9390 +Train: [87] [5300/6250] eta: 0:02:38 lr: 0.000005 grad: 0.1345 (0.1428) loss: 0.8147 (0.8110) time: 0.1669 data: 0.0727 max mem: 9390 +Train: [87] [5400/6250] eta: 0:02:22 lr: 0.000005 grad: 0.1419 (0.1429) loss: 0.8118 (0.8110) time: 0.1478 data: 0.0540 max mem: 9390 +Train: [87] [5500/6250] eta: 0:02:05 lr: 0.000005 grad: 0.1475 (0.1429) loss: 0.8097 (0.8110) time: 0.1401 data: 0.0481 max mem: 9390 +Train: [87] [5600/6250] eta: 0:01:48 lr: 0.000005 grad: 0.1390 (0.1429) loss: 0.8117 (0.8110) time: 0.1603 data: 0.0763 max mem: 9390 +Train: [87] [5700/6250] eta: 0:01:31 lr: 0.000005 grad: 0.1362 (0.1428) loss: 0.8164 (0.8110) time: 0.1402 data: 0.0519 max mem: 9390 +Train: [87] [5800/6250] eta: 0:01:15 lr: 0.000005 grad: 0.1373 (0.1428) loss: 0.8079 (0.8110) time: 0.1540 data: 0.0598 max mem: 9390 +Train: [87] [5900/6250] eta: 0:00:58 lr: 0.000005 grad: 0.1354 (0.1428) loss: 0.8089 (0.8110) time: 0.1692 data: 0.0861 max mem: 9390 +Train: [87] [6000/6250] eta: 0:00:41 lr: 0.000005 grad: 0.1290 (0.1427) loss: 0.8143 (0.8110) time: 0.1393 data: 0.0536 max mem: 9390 +Train: [87] [6100/6250] eta: 0:00:25 lr: 0.000005 grad: 0.1399 (0.1426) loss: 0.8153 (0.8110) time: 0.1948 data: 0.1201 max mem: 9390 +Train: [87] [6200/6250] eta: 0:00:08 lr: 0.000005 grad: 0.1312 (0.1426) loss: 0.8168 (0.8110) time: 0.1534 data: 0.0724 max mem: 9390 +Train: [87] [6249/6250] eta: 0:00:00 lr: 0.000005 grad: 0.1374 (0.1426) loss: 0.8107 (0.8109) time: 0.1739 data: 0.0859 max mem: 9390 +Train: [87] Total time: 0:17:28 (0.1678 s / it) +Averaged stats: lr: 0.000005 grad: 0.1374 (0.1426) loss: 0.8107 (0.8109) +Eval (hcp-train-subset): [87] [ 0/62] eta: 0:03:07 loss: 0.8288 (0.8288) time: 3.0277 data: 2.9624 max mem: 9390 +Eval (hcp-train-subset): [87] [61/62] eta: 0:00:00 loss: 0.8162 (0.8183) time: 0.1279 data: 0.0982 max mem: 9390 +Eval (hcp-train-subset): [87] Total time: 0:00:12 (0.2016 s / it) +Averaged stats (hcp-train-subset): loss: 0.8162 (0.8183) +Eval (hcp-val): [87] [ 0/62] eta: 0:03:07 loss: 0.8282 (0.8282) time: 3.0217 data: 2.9627 max mem: 9390 +Eval (hcp-val): [87] [61/62] eta: 0:00:00 loss: 0.8274 (0.8293) time: 0.1407 data: 0.1132 max mem: 9390 +Eval (hcp-val): [87] Total time: 0:00:13 (0.2246 s / it) +Averaged stats (hcp-val): loss: 0.8274 (0.8293) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +Train: [88] [ 0/6250] eta: 10:13:38 lr: 0.000005 grad: 0.3173 (0.3173) loss: 0.8107 (0.8107) time: 5.8910 data: 5.7577 max mem: 9390 +Train: [88] [ 100/6250] eta: 0:23:13 lr: 0.000005 grad: 0.1543 (0.1902) loss: 0.8033 (0.8116) time: 0.1762 data: 0.0866 max mem: 9390 +Train: [88] [ 200/6250] eta: 0:19:59 lr: 0.000005 grad: 0.1471 (0.1749) loss: 0.8185 (0.8101) time: 0.1818 data: 0.0837 max mem: 9390 +Train: [88] [ 300/6250] eta: 0:20:03 lr: 0.000005 grad: 0.1517 (0.1715) loss: 0.8133 (0.8100) time: 0.2415 data: 0.1258 max mem: 9390 +Train: [88] [ 400/6250] eta: 0:19:51 lr: 0.000005 grad: 0.1425 (0.1664) loss: 0.8109 (0.8099) time: 0.2062 data: 0.1077 max mem: 9390 +Train: [88] [ 500/6250] eta: 0:18:55 lr: 0.000005 grad: 0.1304 (0.1612) loss: 0.8180 (0.8108) time: 0.1607 data: 0.0608 max mem: 9390 +Train: [88] [ 600/6250] eta: 0:18:24 lr: 0.000005 grad: 0.1413 (0.1582) loss: 0.8093 (0.8111) time: 0.2102 data: 0.1156 max mem: 9390 +Train: [88] [ 700/6250] eta: 0:17:49 lr: 0.000005 grad: 0.1375 (0.1555) loss: 0.8134 (0.8116) time: 0.2082 data: 0.1120 max mem: 9390 +Train: [88] [ 800/6250] eta: 0:17:10 lr: 0.000005 grad: 0.1342 (0.1539) loss: 0.8121 (0.8115) time: 0.1763 data: 0.0897 max mem: 9390 +Train: [88] [ 900/6250] eta: 0:16:43 lr: 0.000005 grad: 0.1445 (0.1534) loss: 0.8169 (0.8115) time: 0.1790 data: 0.0905 max mem: 9390 +Train: [88] [1000/6250] eta: 0:16:11 lr: 0.000005 grad: 0.1366 (0.1526) loss: 0.8164 (0.8116) time: 0.1517 data: 0.0501 max mem: 9390 +Train: [88] [1100/6250] eta: 0:15:43 lr: 0.000005 grad: 0.1422 (0.1523) loss: 0.8106 (0.8111) time: 0.1640 data: 0.0793 max mem: 9390 +Train: [88] [1200/6250] eta: 0:15:15 lr: 0.000005 grad: 0.1411 (0.1516) loss: 0.8119 (0.8110) time: 0.1820 data: 0.0953 max mem: 9390 +Train: [88] [1300/6250] eta: 0:14:50 lr: 0.000005 grad: 0.1441 (0.1513) loss: 0.8020 (0.8107) time: 0.1523 data: 0.0568 max mem: 9390 +Train: [88] [1400/6250] eta: 0:14:25 lr: 0.000005 grad: 0.1357 (0.1510) loss: 0.8016 (0.8104) time: 0.1479 data: 0.0595 max mem: 9390 +Train: [88] [1500/6250] eta: 0:14:03 lr: 0.000005 grad: 0.1460 (0.1506) loss: 0.8091 (0.8104) time: 0.1651 data: 0.0766 max mem: 9390 +Train: [88] [1600/6250] eta: 0:13:41 lr: 0.000005 grad: 0.1387 (0.1502) loss: 0.8128 (0.8102) time: 0.1631 data: 0.0709 max mem: 9390 +Train: [88] [1700/6250] eta: 0:13:20 lr: 0.000005 grad: 0.1387 (0.1497) loss: 0.8146 (0.8102) time: 0.1624 data: 0.0738 max mem: 9390 +Train: [88] [1800/6250] eta: 0:13:00 lr: 0.000005 grad: 0.1312 (0.1492) loss: 0.8129 (0.8101) time: 0.1636 data: 0.0716 max mem: 9390 +Train: [88] [1900/6250] eta: 0:12:39 lr: 0.000005 grad: 0.1391 (0.1488) loss: 0.8089 (0.8101) time: 0.1651 data: 0.0744 max mem: 9390 +Train: [88] [2000/6250] eta: 0:12:18 lr: 0.000005 grad: 0.1449 (0.1484) loss: 0.7978 (0.8101) time: 0.1551 data: 0.0616 max mem: 9390 +Train: [88] [2100/6250] eta: 0:12:00 lr: 0.000005 grad: 0.1358 (0.1481) loss: 0.8144 (0.8099) time: 0.1678 data: 0.0761 max mem: 9390 +Train: [88] [2200/6250] eta: 0:11:41 lr: 0.000005 grad: 0.1386 (0.1478) loss: 0.8040 (0.8098) time: 0.1584 data: 0.0696 max mem: 9390 +Train: [88] [2300/6250] eta: 0:11:22 lr: 0.000005 grad: 0.1482 (0.1478) loss: 0.8028 (0.8096) time: 0.1703 data: 0.0839 max mem: 9390 +Train: [88] [2400/6250] eta: 0:11:04 lr: 0.000005 grad: 0.1396 (0.1476) loss: 0.8018 (0.8094) time: 0.1652 data: 0.0755 max mem: 9390 +Train: [88] [2500/6250] eta: 0:10:44 lr: 0.000005 grad: 0.1433 (0.1477) loss: 0.8023 (0.8091) time: 0.1412 data: 0.0516 max mem: 9390 +Train: [88] [2600/6250] eta: 0:10:26 lr: 0.000005 grad: 0.1346 (0.1474) loss: 0.8136 (0.8091) time: 0.1602 data: 0.0680 max mem: 9390 +Train: [88] [2700/6250] eta: 0:10:08 lr: 0.000005 grad: 0.1421 (0.1472) loss: 0.8006 (0.8090) time: 0.1600 data: 0.0729 max mem: 9390 +Train: [88] [2800/6250] eta: 0:09:52 lr: 0.000005 grad: 0.1375 (0.1472) loss: 0.8012 (0.8089) time: 0.2475 data: 0.1609 max mem: 9390 +Train: [88] [2900/6250] eta: 0:09:32 lr: 0.000004 grad: 0.1423 (0.1469) loss: 0.8062 (0.8089) time: 0.1524 data: 0.0671 max mem: 9390 +Train: [88] [3000/6250] eta: 0:09:14 lr: 0.000004 grad: 0.1408 (0.1470) loss: 0.8078 (0.8088) time: 0.1261 data: 0.0291 max mem: 9390 +Train: [88] [3100/6250] eta: 0:08:57 lr: 0.000004 grad: 0.1429 (0.1469) loss: 0.8085 (0.8088) time: 0.1766 data: 0.0866 max mem: 9390 +Train: [88] [3200/6250] eta: 0:08:38 lr: 0.000004 grad: 0.1405 (0.1468) loss: 0.8040 (0.8088) time: 0.1630 data: 0.0766 max mem: 9390 +Train: [88] [3300/6250] eta: 0:08:21 lr: 0.000004 grad: 0.1483 (0.1468) loss: 0.8170 (0.8088) time: 0.1539 data: 0.0627 max mem: 9390 +Train: [88] [3400/6250] eta: 0:08:04 lr: 0.000004 grad: 0.1402 (0.1467) loss: 0.8129 (0.8089) time: 0.1623 data: 0.0774 max mem: 9390 +Train: [88] [3500/6250] eta: 0:07:47 lr: 0.000004 grad: 0.1376 (0.1465) loss: 0.8143 (0.8090) time: 0.1759 data: 0.0852 max mem: 9390 +Train: [88] [3600/6250] eta: 0:07:29 lr: 0.000004 grad: 0.1400 (0.1465) loss: 0.8063 (0.8090) time: 0.1210 data: 0.0357 max mem: 9390 +Train: [88] [3700/6250] eta: 0:07:11 lr: 0.000004 grad: 0.1312 (0.1463) loss: 0.8175 (0.8091) time: 0.1583 data: 0.0686 max mem: 9390 +Train: [88] [3800/6250] eta: 0:06:54 lr: 0.000004 grad: 0.1341 (0.1462) loss: 0.8178 (0.8092) time: 0.1716 data: 0.0910 max mem: 9390 +Train: [88] [3900/6250] eta: 0:06:37 lr: 0.000004 grad: 0.1368 (0.1462) loss: 0.8144 (0.8093) time: 0.1323 data: 0.0476 max mem: 9390 +Train: [88] [4000/6250] eta: 0:06:20 lr: 0.000004 grad: 0.1422 (0.1463) loss: 0.8139 (0.8093) time: 0.1701 data: 0.0855 max mem: 9390 +Train: [88] [4100/6250] eta: 0:06:02 lr: 0.000004 grad: 0.1421 (0.1463) loss: 0.8125 (0.8093) time: 0.1611 data: 0.0711 max mem: 9390 +Train: [88] [4200/6250] eta: 0:05:45 lr: 0.000004 grad: 0.1388 (0.1463) loss: 0.8081 (0.8093) time: 0.1517 data: 0.0676 max mem: 9390 +Train: [88] [4300/6250] eta: 0:05:28 lr: 0.000004 grad: 0.1408 (0.1462) loss: 0.8159 (0.8093) time: 0.1638 data: 0.0759 max mem: 9390 +Train: [88] [4400/6250] eta: 0:05:10 lr: 0.000004 grad: 0.1257 (0.1461) loss: 0.8154 (0.8094) time: 0.1557 data: 0.0646 max mem: 9390 +Train: [88] [4500/6250] eta: 0:04:54 lr: 0.000004 grad: 0.1337 (0.1459) loss: 0.8137 (0.8094) time: 0.1790 data: 0.0950 max mem: 9390 +Train: [88] [4600/6250] eta: 0:04:37 lr: 0.000004 grad: 0.1421 (0.1459) loss: 0.8098 (0.8095) time: 0.1851 data: 0.1013 max mem: 9390 +Train: [88] [4700/6250] eta: 0:04:20 lr: 0.000004 grad: 0.1351 (0.1457) loss: 0.8158 (0.8096) time: 0.1509 data: 0.0632 max mem: 9390 +Train: [88] [4800/6250] eta: 0:04:03 lr: 0.000004 grad: 0.1382 (0.1456) loss: 0.8115 (0.8097) time: 0.1853 data: 0.1020 max mem: 9390 +Train: [88] [4900/6250] eta: 0:03:46 lr: 0.000004 grad: 0.1366 (0.1456) loss: 0.8132 (0.8098) time: 0.1696 data: 0.0827 max mem: 9390 +Train: [88] [5000/6250] eta: 0:03:30 lr: 0.000004 grad: 0.1359 (0.1455) loss: 0.8173 (0.8098) time: 0.1694 data: 0.0776 max mem: 9390 +Train: [88] [5100/6250] eta: 0:03:13 lr: 0.000004 grad: 0.1342 (0.1454) loss: 0.8135 (0.8099) time: 0.1628 data: 0.0786 max mem: 9390 +Train: [88] [5200/6250] eta: 0:02:56 lr: 0.000004 grad: 0.1433 (0.1454) loss: 0.8147 (0.8100) time: 0.1462 data: 0.0539 max mem: 9390 +Train: [88] [5300/6250] eta: 0:02:39 lr: 0.000004 grad: 0.1411 (0.1453) loss: 0.8156 (0.8101) time: 0.1558 data: 0.0699 max mem: 9390 +Train: [88] [5400/6250] eta: 0:02:22 lr: 0.000004 grad: 0.1333 (0.1452) loss: 0.8152 (0.8102) time: 0.1740 data: 0.0856 max mem: 9390 +Train: [88] [5500/6250] eta: 0:02:05 lr: 0.000004 grad: 0.1422 (0.1451) loss: 0.8117 (0.8103) time: 0.1613 data: 0.0770 max mem: 9390 +Train: [88] [5600/6250] eta: 0:01:48 lr: 0.000004 grad: 0.1370 (0.1452) loss: 0.8113 (0.8104) time: 0.1674 data: 0.0833 max mem: 9390 +Train: [88] [5700/6250] eta: 0:01:32 lr: 0.000004 grad: 0.1392 (0.1452) loss: 0.8139 (0.8104) time: 0.1555 data: 0.0701 max mem: 9390 +Train: [88] [5800/6250] eta: 0:01:15 lr: 0.000004 grad: 0.1402 (0.1452) loss: 0.8168 (0.8105) time: 0.1703 data: 0.0830 max mem: 9390 +Train: [88] [5900/6250] eta: 0:00:58 lr: 0.000004 grad: 0.1369 (0.1451) loss: 0.8189 (0.8105) time: 0.1789 data: 0.0939 max mem: 9390 +Train: [88] [6000/6250] eta: 0:00:41 lr: 0.000004 grad: 0.1379 (0.1450) loss: 0.8117 (0.8106) time: 0.1827 data: 0.0936 max mem: 9390 +Train: [88] [6100/6250] eta: 0:00:25 lr: 0.000004 grad: 0.1427 (0.1450) loss: 0.8126 (0.8106) time: 0.1799 data: 0.0927 max mem: 9390 +Train: [88] [6200/6250] eta: 0:00:08 lr: 0.000004 grad: 0.1364 (0.1449) loss: 0.8111 (0.8107) time: 0.1793 data: 0.0944 max mem: 9390 +Train: [88] [6249/6250] eta: 0:00:00 lr: 0.000004 grad: 0.1436 (0.1449) loss: 0.8141 (0.8107) time: 0.1515 data: 0.0724 max mem: 9390 +Train: [88] Total time: 0:17:33 (0.1685 s / it) +Averaged stats: lr: 0.000004 grad: 0.1436 (0.1449) loss: 0.8141 (0.8107) +Eval (hcp-train-subset): [88] [ 0/62] eta: 0:04:45 loss: 0.8277 (0.8277) time: 4.6006 data: 4.5683 max mem: 9390 +Eval (hcp-train-subset): [88] [61/62] eta: 0:00:00 loss: 0.8158 (0.8182) time: 0.1320 data: 0.1049 max mem: 9390 +Eval (hcp-train-subset): [88] Total time: 0:00:13 (0.2123 s / it) +Averaged stats (hcp-train-subset): loss: 0.8158 (0.8182) +Eval (hcp-val): [88] [ 0/62] eta: 0:02:54 loss: 0.8253 (0.8253) time: 2.8108 data: 2.7481 max mem: 9390 +Eval (hcp-val): [88] [61/62] eta: 0:00:00 loss: 0.8264 (0.8291) time: 0.1224 data: 0.0953 max mem: 9390 +Eval (hcp-val): [88] Total time: 0:00:13 (0.2119 s / it) +Averaged stats (hcp-val): loss: 0.8264 (0.8291) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +Train: [89] [ 0/6250] eta: 9:10:23 lr: 0.000004 grad: 0.0918 (0.0918) loss: 0.8493 (0.8493) time: 5.2838 data: 5.0644 max mem: 9390 +Train: [89] [ 100/6250] eta: 0:22:03 lr: 0.000004 grad: 0.1603 (0.1946) loss: 0.8088 (0.8113) time: 0.1627 data: 0.0719 max mem: 9390 +Train: [89] [ 200/6250] eta: 0:20:33 lr: 0.000004 grad: 0.1738 (0.1802) loss: 0.8009 (0.8118) time: 0.2087 data: 0.1083 max mem: 9390 +Train: [89] [ 300/6250] eta: 0:20:42 lr: 0.000004 grad: 0.1391 (0.1723) loss: 0.8147 (0.8121) time: 0.2007 data: 0.0916 max mem: 9390 +Train: [89] [ 400/6250] eta: 0:19:43 lr: 0.000004 grad: 0.1423 (0.1662) loss: 0.8167 (0.8123) time: 0.1290 data: 0.0266 max mem: 9390 +Train: [89] [ 500/6250] eta: 0:18:57 lr: 0.000004 grad: 0.1463 (0.1625) loss: 0.8123 (0.8122) time: 0.1725 data: 0.0711 max mem: 9390 +Train: [89] [ 600/6250] eta: 0:18:18 lr: 0.000004 grad: 0.1466 (0.1606) loss: 0.8144 (0.8122) time: 0.1908 data: 0.0904 max mem: 9390 +Train: [89] [ 700/6250] eta: 0:17:39 lr: 0.000004 grad: 0.1336 (0.1580) loss: 0.8197 (0.8126) time: 0.1588 data: 0.0711 max mem: 9390 +Train: [89] [ 800/6250] eta: 0:17:06 lr: 0.000004 grad: 0.1294 (0.1561) loss: 0.8185 (0.8128) time: 0.1835 data: 0.0973 max mem: 9390 +Train: [89] [ 900/6250] eta: 0:16:33 lr: 0.000004 grad: 0.1439 (0.1550) loss: 0.8158 (0.8131) time: 0.1736 data: 0.0858 max mem: 9390 +Train: [89] [1000/6250] eta: 0:16:03 lr: 0.000004 grad: 0.1395 (0.1538) loss: 0.8077 (0.8132) time: 0.1839 data: 0.0959 max mem: 9390 +Train: [89] [1100/6250] eta: 0:15:38 lr: 0.000004 grad: 0.1407 (0.1527) loss: 0.8090 (0.8132) time: 0.1654 data: 0.0816 max mem: 9390 +Train: [89] [1200/6250] eta: 0:15:13 lr: 0.000004 grad: 0.1400 (0.1521) loss: 0.8039 (0.8131) time: 0.1712 data: 0.0815 max mem: 9390 +Train: [89] [1300/6250] eta: 0:14:49 lr: 0.000004 grad: 0.1389 (0.1512) loss: 0.8037 (0.8129) time: 0.1557 data: 0.0687 max mem: 9390 +Train: [89] [1400/6250] eta: 0:14:25 lr: 0.000004 grad: 0.1463 (0.1509) loss: 0.8098 (0.8126) time: 0.1487 data: 0.0629 max mem: 9390 +Train: [89] [1500/6250] eta: 0:14:04 lr: 0.000004 grad: 0.1455 (0.1505) loss: 0.8076 (0.8126) time: 0.1786 data: 0.0953 max mem: 9390 +Train: [89] [1600/6250] eta: 0:13:40 lr: 0.000004 grad: 0.1355 (0.1500) loss: 0.8166 (0.8126) time: 0.1612 data: 0.0736 max mem: 9390 +Train: [89] [1700/6250] eta: 0:13:18 lr: 0.000004 grad: 0.1403 (0.1496) loss: 0.8145 (0.8126) time: 0.1646 data: 0.0726 max mem: 9390 +Train: [89] [1800/6250] eta: 0:12:57 lr: 0.000004 grad: 0.1375 (0.1490) loss: 0.8114 (0.8127) time: 0.1361 data: 0.0459 max mem: 9390 +Train: [89] [1900/6250] eta: 0:12:38 lr: 0.000004 grad: 0.1305 (0.1486) loss: 0.8221 (0.8127) time: 0.1641 data: 0.0797 max mem: 9390 +Train: [89] [2000/6250] eta: 0:12:20 lr: 0.000004 grad: 0.1344 (0.1482) loss: 0.8139 (0.8127) time: 0.1936 data: 0.1108 max mem: 9390 +Train: [89] [2100/6250] eta: 0:12:03 lr: 0.000004 grad: 0.1404 (0.1479) loss: 0.8099 (0.8127) time: 0.1993 data: 0.1119 max mem: 9390 +Train: [89] [2200/6250] eta: 0:11:45 lr: 0.000004 grad: 0.1419 (0.1479) loss: 0.8100 (0.8126) time: 0.1460 data: 0.0567 max mem: 9390 +Train: [89] [2300/6250] eta: 0:11:28 lr: 0.000004 grad: 0.1393 (0.1477) loss: 0.8091 (0.8126) time: 0.1563 data: 0.0742 max mem: 9390 +Train: [89] [2400/6250] eta: 0:11:08 lr: 0.000004 grad: 0.1493 (0.1477) loss: 0.8072 (0.8124) time: 0.1696 data: 0.0821 max mem: 9390 +Train: [89] [2500/6250] eta: 0:10:52 lr: 0.000004 grad: 0.1357 (0.1474) loss: 0.8156 (0.8125) time: 0.1632 data: 0.0764 max mem: 9390 +Train: [89] [2600/6250] eta: 0:10:32 lr: 0.000004 grad: 0.1413 (0.1472) loss: 0.8162 (0.8125) time: 0.1736 data: 0.0750 max mem: 9390 +Train: [89] [2700/6250] eta: 0:10:15 lr: 0.000004 grad: 0.1415 (0.1471) loss: 0.8108 (0.8124) time: 0.2087 data: 0.1149 max mem: 9390 +Train: [89] [2800/6250] eta: 0:09:56 lr: 0.000004 grad: 0.1380 (0.1470) loss: 0.8169 (0.8125) time: 0.1675 data: 0.0796 max mem: 9390 +Train: [89] [2900/6250] eta: 0:09:37 lr: 0.000004 grad: 0.1351 (0.1469) loss: 0.8131 (0.8126) time: 0.1449 data: 0.0457 max mem: 9390 +Train: [89] [3000/6250] eta: 0:09:19 lr: 0.000004 grad: 0.1389 (0.1469) loss: 0.8131 (0.8125) time: 0.1576 data: 0.0561 max mem: 9390 +Train: [89] [3100/6250] eta: 0:09:01 lr: 0.000004 grad: 0.1342 (0.1469) loss: 0.8141 (0.8125) time: 0.1822 data: 0.0867 max mem: 9390 +Train: [89] [3200/6250] eta: 0:08:42 lr: 0.000004 grad: 0.1422 (0.1469) loss: 0.8132 (0.8125) time: 0.1599 data: 0.0694 max mem: 9390 +Train: [89] [3300/6250] eta: 0:08:24 lr: 0.000004 grad: 0.1429 (0.1469) loss: 0.8078 (0.8125) time: 0.1675 data: 0.0687 max mem: 9390 +Train: [89] [3400/6250] eta: 0:08:06 lr: 0.000004 grad: 0.1416 (0.1469) loss: 0.8067 (0.8124) time: 0.1785 data: 0.0740 max mem: 9390 +Train: [89] [3500/6250] eta: 0:07:49 lr: 0.000004 grad: 0.1468 (0.1469) loss: 0.8082 (0.8124) time: 0.1664 data: 0.0643 max mem: 9390 +Train: [89] [3600/6250] eta: 0:07:31 lr: 0.000004 grad: 0.1587 (0.1469) loss: 0.8069 (0.8123) time: 0.1618 data: 0.0717 max mem: 9390 +Train: [89] [3700/6250] eta: 0:07:14 lr: 0.000004 grad: 0.1446 (0.1468) loss: 0.8113 (0.8123) time: 0.1295 data: 0.0339 max mem: 9390 +Train: [89] [3800/6250] eta: 0:06:57 lr: 0.000004 grad: 0.1340 (0.1468) loss: 0.8140 (0.8123) time: 0.1373 data: 0.0354 max mem: 9390 +Train: [89] [3900/6250] eta: 0:06:39 lr: 0.000004 grad: 0.1501 (0.1468) loss: 0.8025 (0.8122) time: 0.1725 data: 0.0826 max mem: 9390 +Train: [89] [4000/6250] eta: 0:06:22 lr: 0.000004 grad: 0.1441 (0.1468) loss: 0.8051 (0.8121) time: 0.1575 data: 0.0565 max mem: 9390 +Train: [89] [4100/6250] eta: 0:06:05 lr: 0.000004 grad: 0.1426 (0.1467) loss: 0.8141 (0.8121) time: 0.1577 data: 0.0682 max mem: 9390 +Train: [89] [4200/6250] eta: 0:05:48 lr: 0.000004 grad: 0.1406 (0.1467) loss: 0.8090 (0.8120) time: 0.1715 data: 0.0761 max mem: 9390 +Train: [89] [4300/6250] eta: 0:05:30 lr: 0.000004 grad: 0.1372 (0.1467) loss: 0.8160 (0.8120) time: 0.1392 data: 0.0503 max mem: 9390 +Train: [89] [4400/6250] eta: 0:05:13 lr: 0.000004 grad: 0.1516 (0.1467) loss: 0.8041 (0.8120) time: 0.1681 data: 0.0816 max mem: 9390 +Train: [89] [4500/6250] eta: 0:04:56 lr: 0.000004 grad: 0.1460 (0.1467) loss: 0.8154 (0.8120) time: 0.1838 data: 0.0969 max mem: 9390 +Train: [89] [4600/6250] eta: 0:04:39 lr: 0.000004 grad: 0.1484 (0.1467) loss: 0.8103 (0.8119) time: 0.1504 data: 0.0620 max mem: 9390 +Train: [89] [4700/6250] eta: 0:04:21 lr: 0.000004 grad: 0.1418 (0.1466) loss: 0.8070 (0.8119) time: 0.1490 data: 0.0635 max mem: 9390 +Train: [89] [4800/6250] eta: 0:04:04 lr: 0.000004 grad: 0.1453 (0.1467) loss: 0.8062 (0.8118) time: 0.1447 data: 0.0603 max mem: 9390 +Train: [89] [4900/6250] eta: 0:03:47 lr: 0.000004 grad: 0.1419 (0.1466) loss: 0.8128 (0.8117) time: 0.1874 data: 0.0995 max mem: 9390 +Train: [89] [5000/6250] eta: 0:03:30 lr: 0.000004 grad: 0.1515 (0.1466) loss: 0.8008 (0.8117) time: 0.1649 data: 0.0804 max mem: 9390 +Train: [89] [5100/6250] eta: 0:03:13 lr: 0.000004 grad: 0.1420 (0.1466) loss: 0.8136 (0.8116) time: 0.1431 data: 0.0537 max mem: 9390 +Train: [89] [5200/6250] eta: 0:02:56 lr: 0.000003 grad: 0.1360 (0.1465) loss: 0.8102 (0.8116) time: 0.1480 data: 0.0602 max mem: 9390 +Train: [89] [5300/6250] eta: 0:02:39 lr: 0.000003 grad: 0.1285 (0.1465) loss: 0.8125 (0.8115) time: 0.1567 data: 0.0710 max mem: 9390 +Train: [89] [5400/6250] eta: 0:02:22 lr: 0.000003 grad: 0.1440 (0.1464) loss: 0.8028 (0.8115) time: 0.1576 data: 0.0626 max mem: 9390 +Train: [89] [5500/6250] eta: 0:02:05 lr: 0.000003 grad: 0.1396 (0.1463) loss: 0.8117 (0.8115) time: 0.1520 data: 0.0615 max mem: 9390 +Train: [89] [5600/6250] eta: 0:01:49 lr: 0.000003 grad: 0.1432 (0.1463) loss: 0.8028 (0.8115) time: 0.1479 data: 0.0569 max mem: 9390 +Train: [89] [5700/6250] eta: 0:01:32 lr: 0.000003 grad: 0.1400 (0.1462) loss: 0.8101 (0.8115) time: 0.1754 data: 0.0962 max mem: 9390 +Train: [89] [5800/6250] eta: 0:01:15 lr: 0.000003 grad: 0.1419 (0.1462) loss: 0.8152 (0.8115) time: 0.1732 data: 0.0814 max mem: 9390 +Train: [89] [5900/6250] eta: 0:00:58 lr: 0.000003 grad: 0.1391 (0.1462) loss: 0.8077 (0.8114) time: 0.1943 data: 0.0989 max mem: 9390 +Train: [89] [6000/6250] eta: 0:00:41 lr: 0.000003 grad: 0.1392 (0.1462) loss: 0.8093 (0.8114) time: 0.1568 data: 0.0705 max mem: 9390 +Train: [89] [6100/6250] eta: 0:00:25 lr: 0.000003 grad: 0.1421 (0.1462) loss: 0.8055 (0.8114) time: 0.1685 data: 0.0899 max mem: 9390 +Train: [89] [6200/6250] eta: 0:00:08 lr: 0.000003 grad: 0.1493 (0.1462) loss: 0.8039 (0.8114) time: 0.1812 data: 0.0779 max mem: 9390 +Train: [89] [6249/6250] eta: 0:00:00 lr: 0.000003 grad: 0.1414 (0.1462) loss: 0.8169 (0.8114) time: 0.1627 data: 0.0808 max mem: 9390 +Train: [89] Total time: 0:17:35 (0.1688 s / it) +Averaged stats: lr: 0.000003 grad: 0.1414 (0.1462) loss: 0.8169 (0.8114) +Eval (hcp-train-subset): [89] [ 0/62] eta: 0:04:19 loss: 0.8237 (0.8237) time: 4.1884 data: 4.1559 max mem: 9390 +Eval (hcp-train-subset): [89] [61/62] eta: 0:00:00 loss: 0.8161 (0.8178) time: 0.1368 data: 0.1091 max mem: 9390 +Eval (hcp-train-subset): [89] Total time: 0:00:13 (0.2184 s / it) +Averaged stats (hcp-train-subset): loss: 0.8161 (0.8178) +Making plots (hcp-train-subset): example=46 +Eval (hcp-val): [89] [ 0/62] eta: 0:05:12 loss: 0.8271 (0.8271) time: 5.0334 data: 5.0029 max mem: 9390 +Eval (hcp-val): [89] [61/62] eta: 0:00:00 loss: 0.8288 (0.8287) time: 0.1069 data: 0.0810 max mem: 9390 +Eval (hcp-val): [89] Total time: 0:00:13 (0.2158 s / it) +Averaged stats (hcp-val): loss: 0.8288 (0.8287) +Making plots (hcp-val): example=42 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +Train: [90] [ 0/6250] eta: 9:53:29 lr: 0.000003 grad: 0.0782 (0.0782) loss: 0.8665 (0.8665) time: 5.6976 data: 5.5531 max mem: 9390 +Train: [90] [ 100/6250] eta: 0:22:32 lr: 0.000003 grad: 0.1570 (0.1819) loss: 0.8145 (0.8252) time: 0.1813 data: 0.0850 max mem: 9390 +Train: [90] [ 200/6250] eta: 0:20:55 lr: 0.000003 grad: 0.1584 (0.1705) loss: 0.8095 (0.8182) time: 0.2376 data: 0.1333 max mem: 9390 +Train: [90] [ 300/6250] eta: 0:21:01 lr: 0.000003 grad: 0.1388 (0.1647) loss: 0.8031 (0.8153) time: 0.2155 data: 0.1013 max mem: 9390 +Train: [90] [ 400/6250] eta: 0:20:01 lr: 0.000003 grad: 0.1403 (0.1619) loss: 0.8169 (0.8150) time: 0.1835 data: 0.0894 max mem: 9390 +Train: [90] [ 500/6250] eta: 0:18:59 lr: 0.000003 grad: 0.1420 (0.1586) loss: 0.8144 (0.8148) time: 0.1622 data: 0.0653 max mem: 9390 +Train: [90] [ 600/6250] eta: 0:18:14 lr: 0.000003 grad: 0.1339 (0.1563) loss: 0.8170 (0.8150) time: 0.1597 data: 0.0606 max mem: 9390 +Train: [90] [ 700/6250] eta: 0:17:36 lr: 0.000003 grad: 0.1412 (0.1542) loss: 0.8077 (0.8151) time: 0.1704 data: 0.0750 max mem: 9390 +Train: [90] [ 800/6250] eta: 0:17:01 lr: 0.000003 grad: 0.1431 (0.1541) loss: 0.8120 (0.8148) time: 0.1598 data: 0.0692 max mem: 9390 +Train: [90] [ 900/6250] eta: 0:16:31 lr: 0.000003 grad: 0.1379 (0.1530) loss: 0.8120 (0.8146) time: 0.1618 data: 0.0730 max mem: 9390 +Train: [90] [1000/6250] eta: 0:16:01 lr: 0.000003 grad: 0.1453 (0.1530) loss: 0.8124 (0.8145) time: 0.1695 data: 0.0726 max mem: 9390 +Train: [90] [1100/6250] eta: 0:15:38 lr: 0.000003 grad: 0.1556 (0.1526) loss: 0.8027 (0.8141) time: 0.1855 data: 0.1040 max mem: 9390 +Train: [90] [1200/6250] eta: 0:15:11 lr: 0.000003 grad: 0.1388 (0.1522) loss: 0.8125 (0.8139) time: 0.1654 data: 0.0832 max mem: 9390 +Train: [90] [1300/6250] eta: 0:14:49 lr: 0.000003 grad: 0.1420 (0.1515) loss: 0.8108 (0.8138) time: 0.1937 data: 0.1002 max mem: 9390 +Train: [90] [1400/6250] eta: 0:14:23 lr: 0.000003 grad: 0.1482 (0.1514) loss: 0.7973 (0.8133) time: 0.1575 data: 0.0668 max mem: 9390 +Train: [90] [1500/6250] eta: 0:14:01 lr: 0.000003 grad: 0.1390 (0.1513) loss: 0.8005 (0.8128) time: 0.1810 data: 0.0958 max mem: 9390 +Train: [90] [1600/6250] eta: 0:13:38 lr: 0.000003 grad: 0.1444 (0.1513) loss: 0.8033 (0.8124) time: 0.1599 data: 0.0784 max mem: 9390 +Train: [90] [1700/6250] eta: 0:13:17 lr: 0.000003 grad: 0.1354 (0.1510) loss: 0.8081 (0.8122) time: 0.1590 data: 0.0674 max mem: 9390 +Train: [90] [1800/6250] eta: 0:12:58 lr: 0.000003 grad: 0.1432 (0.1506) loss: 0.8040 (0.8120) time: 0.1950 data: 0.1069 max mem: 9390 +Train: [90] [1900/6250] eta: 0:12:38 lr: 0.000003 grad: 0.1443 (0.1505) loss: 0.8069 (0.8117) time: 0.1482 data: 0.0675 max mem: 9390 +Train: [90] [2000/6250] eta: 0:12:19 lr: 0.000003 grad: 0.1362 (0.1502) loss: 0.8146 (0.8116) time: 0.1604 data: 0.0696 max mem: 9390 +Train: [90] [2100/6250] eta: 0:11:58 lr: 0.000003 grad: 0.1556 (0.1501) loss: 0.7999 (0.8115) time: 0.1604 data: 0.0733 max mem: 9390 +Train: [90] [2200/6250] eta: 0:11:39 lr: 0.000003 grad: 0.1387 (0.1499) loss: 0.8149 (0.8113) time: 0.1778 data: 0.0889 max mem: 9390 +Train: [90] [2300/6250] eta: 0:11:20 lr: 0.000003 grad: 0.1430 (0.1498) loss: 0.8042 (0.8112) time: 0.1604 data: 0.0768 max mem: 9390 +Train: [90] [2400/6250] eta: 0:11:01 lr: 0.000003 grad: 0.1455 (0.1497) loss: 0.8104 (0.8111) time: 0.1507 data: 0.0489 max mem: 9390 +Train: [90] [2500/6250] eta: 0:10:42 lr: 0.000003 grad: 0.1424 (0.1494) loss: 0.8087 (0.8111) time: 0.1651 data: 0.0702 max mem: 9390 +Train: [90] [2600/6250] eta: 0:10:24 lr: 0.000003 grad: 0.1409 (0.1492) loss: 0.8089 (0.8111) time: 0.1687 data: 0.0733 max mem: 9390 +Train: [90] [2700/6250] eta: 0:10:06 lr: 0.000003 grad: 0.1391 (0.1490) loss: 0.8114 (0.8110) time: 0.1530 data: 0.0613 max mem: 9390 +Train: [90] [2800/6250] eta: 0:09:49 lr: 0.000003 grad: 0.1315 (0.1489) loss: 0.8147 (0.8110) time: 0.1611 data: 0.0720 max mem: 9390 +Train: [90] [2900/6250] eta: 0:09:31 lr: 0.000003 grad: 0.1411 (0.1488) loss: 0.8141 (0.8109) time: 0.1747 data: 0.0913 max mem: 9390 +Train: [90] [3000/6250] eta: 0:09:14 lr: 0.000003 grad: 0.1391 (0.1486) loss: 0.8127 (0.8109) time: 0.1714 data: 0.0843 max mem: 9390 +Train: [90] [3100/6250] eta: 0:08:56 lr: 0.000003 grad: 0.1407 (0.1484) loss: 0.8075 (0.8109) time: 0.1734 data: 0.0784 max mem: 9390 +Train: [90] [3200/6250] eta: 0:08:38 lr: 0.000003 grad: 0.1419 (0.1482) loss: 0.8070 (0.8109) time: 0.1509 data: 0.0636 max mem: 9390 +Train: [90] [3300/6250] eta: 0:08:21 lr: 0.000003 grad: 0.1366 (0.1481) loss: 0.8202 (0.8110) time: 0.1795 data: 0.0945 max mem: 9390 +Train: [90] [3400/6250] eta: 0:08:03 lr: 0.000003 grad: 0.1338 (0.1479) loss: 0.8029 (0.8109) time: 0.1652 data: 0.0742 max mem: 9390 +Train: [90] [3500/6250] eta: 0:07:46 lr: 0.000003 grad: 0.1380 (0.1477) loss: 0.8133 (0.8109) time: 0.1718 data: 0.0860 max mem: 9390 +Train: [90] [3600/6250] eta: 0:07:28 lr: 0.000003 grad: 0.1345 (0.1476) loss: 0.8174 (0.8110) time: 0.1500 data: 0.0669 max mem: 9390 +Train: [90] [3700/6250] eta: 0:07:11 lr: 0.000003 grad: 0.1429 (0.1474) loss: 0.8110 (0.8110) time: 0.1918 data: 0.1127 max mem: 9390 +Train: [90] [3800/6250] eta: 0:06:54 lr: 0.000003 grad: 0.1404 (0.1473) loss: 0.8080 (0.8109) time: 0.1640 data: 0.0720 max mem: 9390 +Train: [90] [3900/6250] eta: 0:06:37 lr: 0.000003 grad: 0.1411 (0.1473) loss: 0.8110 (0.8110) time: 0.1569 data: 0.0740 max mem: 9390 +Train: [90] [4000/6250] eta: 0:06:20 lr: 0.000003 grad: 0.1559 (0.1472) loss: 0.8063 (0.8110) time: 0.1583 data: 0.0667 max mem: 9390 +Train: [90] [4100/6250] eta: 0:06:03 lr: 0.000003 grad: 0.1388 (0.1471) loss: 0.8109 (0.8109) time: 0.1662 data: 0.0737 max mem: 9390 +Train: [90] [4200/6250] eta: 0:05:45 lr: 0.000003 grad: 0.1450 (0.1470) loss: 0.8094 (0.8109) time: 0.1538 data: 0.0617 max mem: 9390 +Train: [90] [4300/6250] eta: 0:05:28 lr: 0.000003 grad: 0.1394 (0.1470) loss: 0.8094 (0.8110) time: 0.1606 data: 0.0739 max mem: 9390 +Train: [90] [4400/6250] eta: 0:05:12 lr: 0.000003 grad: 0.1400 (0.1469) loss: 0.8137 (0.8110) time: 0.1847 data: 0.0966 max mem: 9390 +Train: [90] [4500/6250] eta: 0:04:55 lr: 0.000003 grad: 0.1327 (0.1467) loss: 0.8195 (0.8111) time: 0.1509 data: 0.0652 max mem: 9390 +Train: [90] [4600/6250] eta: 0:04:38 lr: 0.000003 grad: 0.1391 (0.1466) loss: 0.8050 (0.8110) time: 0.1646 data: 0.0796 max mem: 9390 +Train: [90] [4700/6250] eta: 0:04:20 lr: 0.000003 grad: 0.1402 (0.1465) loss: 0.8141 (0.8111) time: 0.1594 data: 0.0731 max mem: 9390 +Train: [90] [4800/6250] eta: 0:04:04 lr: 0.000003 grad: 0.1399 (0.1464) loss: 0.8124 (0.8111) time: 0.1530 data: 0.0633 max mem: 9390 +Train: [90] [4900/6250] eta: 0:03:47 lr: 0.000003 grad: 0.1330 (0.1462) loss: 0.8132 (0.8111) time: 0.1671 data: 0.0813 max mem: 9390 +Train: [90] [5000/6250] eta: 0:03:30 lr: 0.000003 grad: 0.1448 (0.1461) loss: 0.8104 (0.8111) time: 0.1609 data: 0.0765 max mem: 9390 +Train: [90] [5100/6250] eta: 0:03:13 lr: 0.000003 grad: 0.1368 (0.1461) loss: 0.8118 (0.8111) time: 0.1680 data: 0.0852 max mem: 9390 +Train: [90] [5200/6250] eta: 0:02:56 lr: 0.000003 grad: 0.1293 (0.1460) loss: 0.8143 (0.8110) time: 0.1572 data: 0.0630 max mem: 9390 +Train: [90] [5300/6250] eta: 0:02:39 lr: 0.000003 grad: 0.1347 (0.1459) loss: 0.8134 (0.8110) time: 0.1692 data: 0.0863 max mem: 9390 +Train: [90] [5400/6250] eta: 0:02:22 lr: 0.000003 grad: 0.1367 (0.1458) loss: 0.8113 (0.8110) time: 0.1736 data: 0.0821 max mem: 9390 +Train: [90] [5500/6250] eta: 0:02:05 lr: 0.000003 grad: 0.1381 (0.1457) loss: 0.8146 (0.8110) time: 0.1645 data: 0.0781 max mem: 9390 +Train: [90] [5600/6250] eta: 0:01:49 lr: 0.000003 grad: 0.1347 (0.1456) loss: 0.8123 (0.8109) time: 0.1465 data: 0.0546 max mem: 9390 +Train: [90] [5700/6250] eta: 0:01:32 lr: 0.000003 grad: 0.1370 (0.1456) loss: 0.8143 (0.8109) time: 0.1595 data: 0.0727 max mem: 9390 +Train: [90] [5800/6250] eta: 0:01:15 lr: 0.000003 grad: 0.1327 (0.1454) loss: 0.8185 (0.8110) time: 0.1060 data: 0.0003 max mem: 9390 +Train: [90] [5900/6250] eta: 0:00:58 lr: 0.000003 grad: 0.1404 (0.1454) loss: 0.8140 (0.8110) time: 0.1766 data: 0.0882 max mem: 9390 +Train: [90] [6000/6250] eta: 0:00:41 lr: 0.000003 grad: 0.1287 (0.1453) loss: 0.8191 (0.8111) time: 0.1776 data: 0.0895 max mem: 9390 +Train: [90] [6100/6250] eta: 0:00:25 lr: 0.000003 grad: 0.1403 (0.1452) loss: 0.8133 (0.8111) time: 0.1718 data: 0.0855 max mem: 9390 +Train: [90] [6200/6250] eta: 0:00:08 lr: 0.000003 grad: 0.1340 (0.1451) loss: 0.8167 (0.8111) time: 0.1665 data: 0.0892 max mem: 9390 +Train: [90] [6249/6250] eta: 0:00:00 lr: 0.000003 grad: 0.1441 (0.1451) loss: 0.8102 (0.8111) time: 0.1758 data: 0.0791 max mem: 9390 +Train: [90] Total time: 0:17:36 (0.1691 s / it) +Averaged stats: lr: 0.000003 grad: 0.1441 (0.1451) loss: 0.8102 (0.8111) +Eval (hcp-train-subset): [90] [ 0/62] eta: 0:02:48 loss: 0.8236 (0.8236) time: 2.7133 data: 2.6485 max mem: 9390 +Eval (hcp-train-subset): [90] [61/62] eta: 0:00:00 loss: 0.8139 (0.8161) time: 0.1017 data: 0.0749 max mem: 9390 +Eval (hcp-train-subset): [90] Total time: 0:00:13 (0.2156 s / it) +Averaged stats (hcp-train-subset): loss: 0.8139 (0.8161) +Eval (hcp-val): [90] [ 0/62] eta: 0:03:24 loss: 0.8239 (0.8239) time: 3.3026 data: 3.1983 max mem: 9390 +Eval (hcp-val): [90] [61/62] eta: 0:00:00 loss: 0.8272 (0.8288) time: 0.1288 data: 0.1031 max mem: 9390 +Eval (hcp-val): [90] Total time: 0:00:13 (0.2114 s / it) +Averaged stats (hcp-val): loss: 0.8272 (0.8288) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +Train: [91] [ 0/6250] eta: 10:36:16 lr: 0.000003 grad: 0.2200 (0.2200) loss: 0.8069 (0.8069) time: 6.1082 data: 6.0140 max mem: 9390 +Train: [91] [ 100/6250] eta: 0:22:08 lr: 0.000003 grad: 0.1848 (0.2117) loss: 0.8165 (0.8200) time: 0.1809 data: 0.0838 max mem: 9390 +Train: [91] [ 200/6250] eta: 0:20:18 lr: 0.000003 grad: 0.1463 (0.1872) loss: 0.8197 (0.8182) time: 0.1966 data: 0.1043 max mem: 9390 +Train: [91] [ 300/6250] eta: 0:19:57 lr: 0.000003 grad: 0.1304 (0.1747) loss: 0.8213 (0.8196) time: 0.1963 data: 0.0956 max mem: 9390 +Train: [91] [ 400/6250] eta: 0:19:02 lr: 0.000003 grad: 0.1336 (0.1670) loss: 0.8243 (0.8197) time: 0.1633 data: 0.0716 max mem: 9390 +Train: [91] [ 500/6250] eta: 0:18:32 lr: 0.000003 grad: 0.1323 (0.1616) loss: 0.8218 (0.8201) time: 0.2058 data: 0.1215 max mem: 9390 +Train: [91] [ 600/6250] eta: 0:17:51 lr: 0.000003 grad: 0.1410 (0.1582) loss: 0.8203 (0.8204) time: 0.1835 data: 0.0979 max mem: 9390 +Train: [91] [ 700/6250] eta: 0:17:25 lr: 0.000003 grad: 0.1340 (0.1560) loss: 0.8219 (0.8205) time: 0.1510 data: 0.0684 max mem: 9390 +Train: [91] [ 800/6250] eta: 0:17:00 lr: 0.000003 grad: 0.1523 (0.1545) loss: 0.8186 (0.8205) time: 0.1503 data: 0.0481 max mem: 9390 +Train: [91] [ 900/6250] eta: 0:16:48 lr: 0.000003 grad: 0.1439 (0.1535) loss: 0.8230 (0.8207) time: 0.2113 data: 0.1233 max mem: 9390 +Train: [91] [1000/6250] eta: 0:16:19 lr: 0.000003 grad: 0.1351 (0.1523) loss: 0.8207 (0.8208) time: 0.1799 data: 0.0884 max mem: 9390 +Train: [91] [1100/6250] eta: 0:15:53 lr: 0.000003 grad: 0.1398 (0.1510) loss: 0.8209 (0.8208) time: 0.1781 data: 0.0907 max mem: 9390 +Train: [91] [1200/6250] eta: 0:15:24 lr: 0.000003 grad: 0.1387 (0.1502) loss: 0.8169 (0.8206) time: 0.1868 data: 0.1002 max mem: 9390 +Train: [91] [1300/6250] eta: 0:14:59 lr: 0.000003 grad: 0.1369 (0.1495) loss: 0.8207 (0.8205) time: 0.1483 data: 0.0698 max mem: 9390 +Train: [91] [1400/6250] eta: 0:14:35 lr: 0.000003 grad: 0.1345 (0.1487) loss: 0.8149 (0.8203) time: 0.1609 data: 0.0665 max mem: 9390 +Train: [91] [1500/6250] eta: 0:14:10 lr: 0.000003 grad: 0.1416 (0.1481) loss: 0.8151 (0.8202) time: 0.1455 data: 0.0553 max mem: 9390 +Train: [91] [1600/6250] eta: 0:13:49 lr: 0.000003 grad: 0.1437 (0.1478) loss: 0.8118 (0.8198) time: 0.1509 data: 0.0705 max mem: 9390 +Train: [91] [1700/6250] eta: 0:13:26 lr: 0.000003 grad: 0.1411 (0.1474) loss: 0.8194 (0.8197) time: 0.1655 data: 0.0819 max mem: 9390 +Train: [91] [1800/6250] eta: 0:13:03 lr: 0.000003 grad: 0.1423 (0.1473) loss: 0.8161 (0.8192) time: 0.1488 data: 0.0551 max mem: 9390 +Train: [91] [1900/6250] eta: 0:12:43 lr: 0.000003 grad: 0.1347 (0.1472) loss: 0.8155 (0.8188) time: 0.1717 data: 0.0714 max mem: 9390 +Train: [91] [2000/6250] eta: 0:12:24 lr: 0.000003 grad: 0.1424 (0.1470) loss: 0.8109 (0.8185) time: 0.1629 data: 0.0580 max mem: 9390 +Train: [91] [2100/6250] eta: 0:12:05 lr: 0.000003 grad: 0.1403 (0.1467) loss: 0.8158 (0.8184) time: 0.1680 data: 0.0708 max mem: 9390 +Train: [91] [2200/6250] eta: 0:11:46 lr: 0.000003 grad: 0.1339 (0.1465) loss: 0.8200 (0.8182) time: 0.1597 data: 0.0618 max mem: 9390 +Train: [91] [2300/6250] eta: 0:11:29 lr: 0.000003 grad: 0.1414 (0.1464) loss: 0.8141 (0.8180) time: 0.1733 data: 0.0824 max mem: 9390 +Train: [91] [2400/6250] eta: 0:11:13 lr: 0.000003 grad: 0.1404 (0.1464) loss: 0.8134 (0.8177) time: 0.1852 data: 0.0903 max mem: 9390 +Train: [91] [2500/6250] eta: 0:10:55 lr: 0.000003 grad: 0.1389 (0.1464) loss: 0.8166 (0.8175) time: 0.1540 data: 0.0768 max mem: 9390 +Train: [91] [2600/6250] eta: 0:10:37 lr: 0.000003 grad: 0.1419 (0.1465) loss: 0.8135 (0.8173) time: 0.1798 data: 0.1012 max mem: 9390 +Train: [91] [2700/6250] eta: 0:10:20 lr: 0.000002 grad: 0.1499 (0.1465) loss: 0.8085 (0.8171) time: 0.1951 data: 0.1092 max mem: 9390 +Train: [91] [2800/6250] eta: 0:10:02 lr: 0.000002 grad: 0.1430 (0.1464) loss: 0.8107 (0.8170) time: 0.1761 data: 0.0841 max mem: 9390 +Train: [91] [2900/6250] eta: 0:09:43 lr: 0.000002 grad: 0.1403 (0.1463) loss: 0.8141 (0.8168) time: 0.1480 data: 0.0573 max mem: 9390 +Train: [91] [3000/6250] eta: 0:09:25 lr: 0.000002 grad: 0.1455 (0.1464) loss: 0.8111 (0.8165) time: 0.1546 data: 0.0658 max mem: 9390 +Train: [91] [3100/6250] eta: 0:09:07 lr: 0.000002 grad: 0.1410 (0.1464) loss: 0.8134 (0.8164) time: 0.1871 data: 0.1017 max mem: 9390 +Train: [91] [3200/6250] eta: 0:08:48 lr: 0.000002 grad: 0.1385 (0.1464) loss: 0.8181 (0.8162) time: 0.1721 data: 0.0834 max mem: 9390 +Train: [91] [3300/6250] eta: 0:08:29 lr: 0.000002 grad: 0.1517 (0.1465) loss: 0.8179 (0.8161) time: 0.1606 data: 0.0711 max mem: 9390 +Train: [91] [3400/6250] eta: 0:08:11 lr: 0.000002 grad: 0.1395 (0.1465) loss: 0.8121 (0.8159) time: 0.1675 data: 0.0839 max mem: 9390 +Train: [91] [3500/6250] eta: 0:07:53 lr: 0.000002 grad: 0.1444 (0.1465) loss: 0.8039 (0.8157) time: 0.1536 data: 0.0616 max mem: 9390 +Train: [91] [3600/6250] eta: 0:07:35 lr: 0.000002 grad: 0.1385 (0.1465) loss: 0.8101 (0.8155) time: 0.1691 data: 0.0863 max mem: 9390 +Train: [91] [3700/6250] eta: 0:07:17 lr: 0.000002 grad: 0.1456 (0.1466) loss: 0.8093 (0.8154) time: 0.1374 data: 0.0482 max mem: 9390 +Train: [91] [3800/6250] eta: 0:06:59 lr: 0.000002 grad: 0.1456 (0.1465) loss: 0.8194 (0.8153) time: 0.1557 data: 0.0642 max mem: 9390 +Train: [91] [3900/6250] eta: 0:06:42 lr: 0.000002 grad: 0.1398 (0.1464) loss: 0.8120 (0.8152) time: 0.1749 data: 0.0868 max mem: 9390 +Train: [91] [4000/6250] eta: 0:06:24 lr: 0.000002 grad: 0.1426 (0.1464) loss: 0.8173 (0.8151) time: 0.1316 data: 0.0397 max mem: 9390 +Train: [91] [4100/6250] eta: 0:06:06 lr: 0.000002 grad: 0.1371 (0.1463) loss: 0.8106 (0.8150) time: 0.1690 data: 0.0906 max mem: 9390 +Train: [91] [4200/6250] eta: 0:05:49 lr: 0.000002 grad: 0.1424 (0.1463) loss: 0.8156 (0.8150) time: 0.1628 data: 0.0773 max mem: 9390 +Train: [91] [4300/6250] eta: 0:05:32 lr: 0.000002 grad: 0.1431 (0.1463) loss: 0.8123 (0.8148) time: 0.1432 data: 0.0550 max mem: 9390 +Train: [91] [4400/6250] eta: 0:05:14 lr: 0.000002 grad: 0.1391 (0.1462) loss: 0.8157 (0.8147) time: 0.1585 data: 0.0752 max mem: 9390 +Train: [91] [4500/6250] eta: 0:04:57 lr: 0.000002 grad: 0.1478 (0.1463) loss: 0.8038 (0.8146) time: 0.1544 data: 0.0638 max mem: 9390 +Train: [91] [4600/6250] eta: 0:04:40 lr: 0.000002 grad: 0.1377 (0.1462) loss: 0.8046 (0.8145) time: 0.1508 data: 0.0604 max mem: 9390 +Train: [91] [4700/6250] eta: 0:04:23 lr: 0.000002 grad: 0.1357 (0.1463) loss: 0.8167 (0.8144) time: 0.1726 data: 0.0825 max mem: 9390 +Train: [91] [4800/6250] eta: 0:04:05 lr: 0.000002 grad: 0.1493 (0.1462) loss: 0.8114 (0.8143) time: 0.1610 data: 0.0750 max mem: 9390 +Train: [91] [4900/6250] eta: 0:03:49 lr: 0.000002 grad: 0.1445 (0.1462) loss: 0.8139 (0.8143) time: 0.1519 data: 0.0659 max mem: 9390 +Train: [91] [5000/6250] eta: 0:03:32 lr: 0.000002 grad: 0.1353 (0.1462) loss: 0.8122 (0.8142) time: 0.1520 data: 0.0677 max mem: 9390 +Train: [91] [5100/6250] eta: 0:03:15 lr: 0.000002 grad: 0.1386 (0.1461) loss: 0.8204 (0.8142) time: 0.1725 data: 0.0946 max mem: 9390 +Train: [91] [5200/6250] eta: 0:02:58 lr: 0.000002 grad: 0.1478 (0.1461) loss: 0.8093 (0.8142) time: 0.1825 data: 0.0926 max mem: 9390 +Train: [91] [5300/6250] eta: 0:02:41 lr: 0.000002 grad: 0.1354 (0.1460) loss: 0.8103 (0.8141) time: 0.1763 data: 0.0829 max mem: 9390 +Train: [91] [5400/6250] eta: 0:02:24 lr: 0.000002 grad: 0.1359 (0.1461) loss: 0.8080 (0.8140) time: 0.1801 data: 0.0975 max mem: 9390 +Train: [91] [5500/6250] eta: 0:02:07 lr: 0.000002 grad: 0.1408 (0.1460) loss: 0.8126 (0.8140) time: 0.1644 data: 0.0740 max mem: 9390 +Train: [91] [5600/6250] eta: 0:01:50 lr: 0.000002 grad: 0.1499 (0.1460) loss: 0.8053 (0.8140) time: 0.1776 data: 0.0980 max mem: 9390 +Train: [91] [5700/6250] eta: 0:01:33 lr: 0.000002 grad: 0.1473 (0.1460) loss: 0.8017 (0.8139) time: 0.1885 data: 0.0985 max mem: 9390 +Train: [91] [5800/6250] eta: 0:01:16 lr: 0.000002 grad: 0.1398 (0.1460) loss: 0.8121 (0.8138) time: 0.1893 data: 0.1097 max mem: 9390 +Train: [91] [5900/6250] eta: 0:00:59 lr: 0.000002 grad: 0.1448 (0.1460) loss: 0.8152 (0.8138) time: 0.1683 data: 0.0838 max mem: 9390 +Train: [91] [6000/6250] eta: 0:00:42 lr: 0.000002 grad: 0.1327 (0.1460) loss: 0.8131 (0.8137) time: 0.1782 data: 0.0889 max mem: 9390 +Train: [91] [6100/6250] eta: 0:00:25 lr: 0.000002 grad: 0.1465 (0.1460) loss: 0.8067 (0.8136) time: 0.1635 data: 0.0858 max mem: 9390 +Train: [91] [6200/6250] eta: 0:00:08 lr: 0.000002 grad: 0.1421 (0.1460) loss: 0.8108 (0.8136) time: 0.1735 data: 0.0922 max mem: 9390 +Train: [91] [6249/6250] eta: 0:00:00 lr: 0.000002 grad: 0.1427 (0.1461) loss: 0.8105 (0.8136) time: 0.1573 data: 0.0748 max mem: 9390 +Train: [91] Total time: 0:17:46 (0.1707 s / it) +Averaged stats: lr: 0.000002 grad: 0.1427 (0.1461) loss: 0.8105 (0.8136) +Eval (hcp-train-subset): [91] [ 0/62] eta: 0:03:02 loss: 0.8274 (0.8274) time: 2.9501 data: 2.8540 max mem: 9390 +Eval (hcp-train-subset): [91] [61/62] eta: 0:00:00 loss: 0.8128 (0.8165) time: 0.1333 data: 0.1080 max mem: 9390 +Eval (hcp-train-subset): [91] Total time: 0:00:13 (0.2103 s / it) +Averaged stats (hcp-train-subset): loss: 0.8128 (0.8165) +Eval (hcp-val): [91] [ 0/62] eta: 0:04:50 loss: 0.8246 (0.8246) time: 4.6919 data: 4.6615 max mem: 9390 +Eval (hcp-val): [91] [61/62] eta: 0:00:00 loss: 0.8279 (0.8281) time: 0.1338 data: 0.1083 max mem: 9390 +Eval (hcp-val): [91] Total time: 0:00:13 (0.2174 s / it) +Averaged stats (hcp-val): loss: 0.8279 (0.8281) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +Train: [92] [ 0/6250] eta: 11:30:00 lr: 0.000002 grad: 0.2334 (0.2334) loss: 0.7845 (0.7845) time: 6.6241 data: 6.5145 max mem: 9390 +Train: [92] [ 100/6250] eta: 0:22:24 lr: 0.000002 grad: 0.1627 (0.1957) loss: 0.8071 (0.8144) time: 0.1698 data: 0.0664 max mem: 9390 +Train: [92] [ 200/6250] eta: 0:20:59 lr: 0.000002 grad: 0.1584 (0.1859) loss: 0.8047 (0.8110) time: 0.2246 data: 0.1237 max mem: 9390 +Train: [92] [ 300/6250] eta: 0:20:40 lr: 0.000002 grad: 0.1627 (0.1793) loss: 0.8023 (0.8097) time: 0.1849 data: 0.0890 max mem: 9390 +Train: [92] [ 400/6250] eta: 0:19:39 lr: 0.000002 grad: 0.1426 (0.1744) loss: 0.8085 (0.8081) time: 0.1738 data: 0.0794 max mem: 9390 +Train: [92] [ 500/6250] eta: 0:18:53 lr: 0.000002 grad: 0.1450 (0.1707) loss: 0.8047 (0.8080) time: 0.1780 data: 0.0885 max mem: 9390 +Train: [92] [ 600/6250] eta: 0:18:18 lr: 0.000002 grad: 0.1496 (0.1686) loss: 0.8167 (0.8081) time: 0.1943 data: 0.1069 max mem: 9390 +Train: [92] [ 700/6250] eta: 0:17:44 lr: 0.000002 grad: 0.1495 (0.1674) loss: 0.8086 (0.8080) time: 0.2172 data: 0.1262 max mem: 9390 +Train: [92] [ 800/6250] eta: 0:17:06 lr: 0.000002 grad: 0.1429 (0.1655) loss: 0.8150 (0.8080) time: 0.1749 data: 0.0892 max mem: 9390 +Train: [92] [ 900/6250] eta: 0:16:37 lr: 0.000002 grad: 0.1571 (0.1643) loss: 0.8063 (0.8080) time: 0.1536 data: 0.0548 max mem: 9390 +Train: [92] [1000/6250] eta: 0:16:13 lr: 0.000002 grad: 0.1577 (0.1633) loss: 0.8052 (0.8078) time: 0.1802 data: 0.0915 max mem: 9390 +Train: [92] [1100/6250] eta: 0:15:47 lr: 0.000002 grad: 0.1486 (0.1627) loss: 0.8045 (0.8074) time: 0.1874 data: 0.0940 max mem: 9390 +Train: [92] [1200/6250] eta: 0:15:22 lr: 0.000002 grad: 0.1461 (0.1622) loss: 0.8122 (0.8073) time: 0.1771 data: 0.0844 max mem: 9390 +Train: [92] [1300/6250] eta: 0:14:55 lr: 0.000002 grad: 0.1499 (0.1617) loss: 0.8117 (0.8073) time: 0.1350 data: 0.0542 max mem: 9390 +Train: [92] [1400/6250] eta: 0:14:31 lr: 0.000002 grad: 0.1416 (0.1613) loss: 0.8124 (0.8074) time: 0.1707 data: 0.0872 max mem: 9390 +Train: [92] [1500/6250] eta: 0:14:08 lr: 0.000002 grad: 0.1402 (0.1607) loss: 0.8095 (0.8073) time: 0.1102 data: 0.0108 max mem: 9390 +Train: [92] [1600/6250] eta: 0:13:50 lr: 0.000002 grad: 0.1502 (0.1601) loss: 0.8067 (0.8074) time: 0.2016 data: 0.1119 max mem: 9390 +Train: [92] [1700/6250] eta: 0:13:28 lr: 0.000002 grad: 0.1458 (0.1595) loss: 0.8111 (0.8075) time: 0.1659 data: 0.0804 max mem: 9390 +Train: [92] [1800/6250] eta: 0:13:07 lr: 0.000002 grad: 0.1393 (0.1590) loss: 0.8092 (0.8076) time: 0.1535 data: 0.0717 max mem: 9390 +Train: [92] [1900/6250] eta: 0:12:48 lr: 0.000002 grad: 0.1401 (0.1585) loss: 0.8124 (0.8078) time: 0.1892 data: 0.1028 max mem: 9390 +Train: [92] [2000/6250] eta: 0:12:27 lr: 0.000002 grad: 0.1404 (0.1578) loss: 0.8169 (0.8080) time: 0.1801 data: 0.0951 max mem: 9390 +Train: [92] [2100/6250] eta: 0:12:07 lr: 0.000002 grad: 0.1395 (0.1573) loss: 0.8120 (0.8081) time: 0.1656 data: 0.0792 max mem: 9390 +Train: [92] [2200/6250] eta: 0:11:48 lr: 0.000002 grad: 0.1453 (0.1567) loss: 0.8107 (0.8082) time: 0.1524 data: 0.0646 max mem: 9390 +Train: [92] [2300/6250] eta: 0:11:29 lr: 0.000002 grad: 0.1406 (0.1562) loss: 0.8062 (0.8084) time: 0.1700 data: 0.0756 max mem: 9390 +Train: [92] [2400/6250] eta: 0:11:09 lr: 0.000002 grad: 0.1461 (0.1558) loss: 0.8064 (0.8085) time: 0.1638 data: 0.0758 max mem: 9390 +Train: [92] [2500/6250] eta: 0:10:51 lr: 0.000002 grad: 0.1438 (0.1554) loss: 0.8047 (0.8086) time: 0.1849 data: 0.0974 max mem: 9390 +Train: [92] [2600/6250] eta: 0:10:33 lr: 0.000002 grad: 0.1401 (0.1550) loss: 0.8146 (0.8088) time: 0.1791 data: 0.0885 max mem: 9390 +Train: [92] [2700/6250] eta: 0:10:16 lr: 0.000002 grad: 0.1448 (0.1546) loss: 0.8142 (0.8089) time: 0.1352 data: 0.0405 max mem: 9390 +Train: [92] [2800/6250] eta: 0:09:58 lr: 0.000002 grad: 0.1451 (0.1542) loss: 0.8125 (0.8090) time: 0.1568 data: 0.0787 max mem: 9390 +Train: [92] [2900/6250] eta: 0:09:40 lr: 0.000002 grad: 0.1359 (0.1539) loss: 0.8168 (0.8091) time: 0.1958 data: 0.1123 max mem: 9390 +Train: [92] [3000/6250] eta: 0:09:22 lr: 0.000002 grad: 0.1449 (0.1536) loss: 0.8151 (0.8092) time: 0.1515 data: 0.0614 max mem: 9390 +Train: [92] [3100/6250] eta: 0:09:04 lr: 0.000002 grad: 0.1464 (0.1534) loss: 0.8149 (0.8093) time: 0.1748 data: 0.0789 max mem: 9390 +Train: [92] [3200/6250] eta: 0:08:46 lr: 0.000002 grad: 0.1345 (0.1531) loss: 0.8143 (0.8094) time: 0.1577 data: 0.0691 max mem: 9390 +Train: [92] [3300/6250] eta: 0:08:29 lr: 0.000002 grad: 0.1455 (0.1530) loss: 0.8089 (0.8095) time: 0.1685 data: 0.0843 max mem: 9390 +Train: [92] [3400/6250] eta: 0:08:12 lr: 0.000002 grad: 0.1485 (0.1528) loss: 0.8119 (0.8096) time: 0.1994 data: 0.0667 max mem: 9390 +Train: [92] [3500/6250] eta: 0:07:54 lr: 0.000002 grad: 0.1449 (0.1527) loss: 0.8184 (0.8097) time: 0.1938 data: 0.0892 max mem: 9390 +Train: [92] [3600/6250] eta: 0:07:36 lr: 0.000002 grad: 0.1362 (0.1525) loss: 0.8136 (0.8098) time: 0.1763 data: 0.0807 max mem: 9390 +Train: [92] [3700/6250] eta: 0:07:19 lr: 0.000002 grad: 0.1438 (0.1524) loss: 0.8131 (0.8099) time: 0.1905 data: 0.0393 max mem: 9390 +Train: [92] [3800/6250] eta: 0:07:01 lr: 0.000002 grad: 0.1426 (0.1522) loss: 0.8148 (0.8100) time: 0.1678 data: 0.0803 max mem: 9390 +Train: [92] [3900/6250] eta: 0:06:44 lr: 0.000002 grad: 0.1456 (0.1520) loss: 0.8153 (0.8102) time: 0.1415 data: 0.0474 max mem: 9390 +Train: [92] [4000/6250] eta: 0:06:26 lr: 0.000002 grad: 0.1511 (0.1518) loss: 0.8225 (0.8104) time: 0.1828 data: 0.0834 max mem: 9390 +Train: [92] [4100/6250] eta: 0:06:10 lr: 0.000002 grad: 0.1466 (0.1516) loss: 0.8119 (0.8106) time: 0.1346 data: 0.0421 max mem: 9390 +Train: [92] [4200/6250] eta: 0:05:52 lr: 0.000002 grad: 0.1413 (0.1515) loss: 0.8156 (0.8107) time: 0.1732 data: 0.0843 max mem: 9390 +Train: [92] [4300/6250] eta: 0:05:35 lr: 0.000002 grad: 0.1392 (0.1514) loss: 0.8163 (0.8108) time: 0.1714 data: 0.0841 max mem: 9390 +Train: [92] [4400/6250] eta: 0:05:17 lr: 0.000002 grad: 0.1310 (0.1512) loss: 0.8216 (0.8110) time: 0.1797 data: 0.0910 max mem: 9390 +Train: [92] [4500/6250] eta: 0:05:00 lr: 0.000002 grad: 0.1525 (0.1511) loss: 0.8151 (0.8111) time: 0.1866 data: 0.0911 max mem: 9390 +Train: [92] [4600/6250] eta: 0:04:43 lr: 0.000002 grad: 0.1469 (0.1509) loss: 0.8146 (0.8112) time: 0.1840 data: 0.0823 max mem: 9390 +Train: [92] [4700/6250] eta: 0:04:26 lr: 0.000002 grad: 0.1398 (0.1507) loss: 0.8187 (0.8113) time: 0.1742 data: 0.0876 max mem: 9390 +Train: [92] [4800/6250] eta: 0:04:09 lr: 0.000002 grad: 0.1389 (0.1506) loss: 0.8207 (0.8115) time: 0.1628 data: 0.0770 max mem: 9390 +Train: [92] [4900/6250] eta: 0:03:52 lr: 0.000002 grad: 0.1320 (0.1506) loss: 0.8166 (0.8116) time: 0.1913 data: 0.0941 max mem: 9390 +Train: [92] [5000/6250] eta: 0:03:34 lr: 0.000002 grad: 0.1571 (0.1506) loss: 0.8166 (0.8116) time: 0.1810 data: 0.0988 max mem: 9390 +Train: [92] [5100/6250] eta: 0:03:17 lr: 0.000002 grad: 0.1389 (0.1505) loss: 0.8134 (0.8117) time: 0.2195 data: 0.1308 max mem: 9390 +Train: [92] [5200/6250] eta: 0:03:00 lr: 0.000002 grad: 0.1395 (0.1504) loss: 0.8184 (0.8118) time: 0.1907 data: 0.0907 max mem: 9390 +Train: [92] [5300/6250] eta: 0:02:43 lr: 0.000002 grad: 0.1450 (0.1503) loss: 0.8181 (0.8119) time: 0.1797 data: 0.0862 max mem: 9390 +Train: [92] [5400/6250] eta: 0:02:26 lr: 0.000002 grad: 0.1406 (0.1501) loss: 0.8203 (0.8120) time: 0.1608 data: 0.0704 max mem: 9390 +Train: [92] [5500/6250] eta: 0:02:09 lr: 0.000002 grad: 0.1399 (0.1500) loss: 0.8122 (0.8121) time: 0.1654 data: 0.0766 max mem: 9390 +Train: [92] [5600/6250] eta: 0:01:51 lr: 0.000002 grad: 0.1397 (0.1499) loss: 0.8213 (0.8122) time: 0.1601 data: 0.0649 max mem: 9390 +Train: [92] [5700/6250] eta: 0:01:34 lr: 0.000002 grad: 0.1309 (0.1497) loss: 0.8171 (0.8123) time: 0.1667 data: 0.0825 max mem: 9390 +Train: [92] [5800/6250] eta: 0:01:17 lr: 0.000002 grad: 0.1421 (0.1496) loss: 0.8125 (0.8123) time: 0.1756 data: 0.0873 max mem: 9390 +Train: [92] [5900/6250] eta: 0:01:00 lr: 0.000002 grad: 0.1434 (0.1494) loss: 0.8126 (0.8124) time: 0.2044 data: 0.1259 max mem: 9390 +Train: [92] [6000/6250] eta: 0:00:43 lr: 0.000002 grad: 0.1375 (0.1494) loss: 0.8133 (0.8124) time: 0.2152 data: 0.1165 max mem: 9390 +Train: [92] [6100/6250] eta: 0:00:25 lr: 0.000002 grad: 0.1398 (0.1493) loss: 0.8162 (0.8124) time: 0.2109 data: 0.1251 max mem: 9390 +Train: [92] [6200/6250] eta: 0:00:08 lr: 0.000002 grad: 0.1392 (0.1492) loss: 0.8075 (0.8125) time: 0.1797 data: 0.0923 max mem: 9390 +Train: [92] [6249/6250] eta: 0:00:00 lr: 0.000002 grad: 0.1448 (0.1491) loss: 0.8097 (0.8125) time: 0.1498 data: 0.0598 max mem: 9390 +Train: [92] Total time: 0:18:06 (0.1738 s / it) +Averaged stats: lr: 0.000002 grad: 0.1448 (0.1491) loss: 0.8097 (0.8125) +Eval (hcp-train-subset): [92] [ 0/62] eta: 0:04:00 loss: 0.8216 (0.8216) time: 3.8728 data: 3.8093 max mem: 9390 +Eval (hcp-train-subset): [92] [61/62] eta: 0:00:00 loss: 0.8130 (0.8159) time: 0.1255 data: 0.0985 max mem: 9390 +Eval (hcp-train-subset): [92] Total time: 0:00:15 (0.2483 s / it) +Averaged stats (hcp-train-subset): loss: 0.8130 (0.8159) +Eval (hcp-val): [92] [ 0/62] eta: 0:04:48 loss: 0.8252 (0.8252) time: 4.6500 data: 4.6207 max mem: 9390 +Eval (hcp-val): [92] [61/62] eta: 0:00:00 loss: 0.8277 (0.8283) time: 0.1078 data: 0.0829 max mem: 9390 +Eval (hcp-val): [92] Total time: 0:00:12 (0.2067 s / it) +Averaged stats (hcp-val): loss: 0.8277 (0.8283) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +Train: [93] [ 0/6250] eta: 7:56:55 lr: 0.000002 grad: 0.2126 (0.2126) loss: 0.8635 (0.8635) time: 4.5785 data: 4.3240 max mem: 9390 +Train: [93] [ 100/6250] eta: 0:23:20 lr: 0.000002 grad: 0.1818 (0.2036) loss: 0.8239 (0.8184) time: 0.1788 data: 0.0731 max mem: 9390 +Train: [93] [ 200/6250] eta: 0:19:53 lr: 0.000002 grad: 0.1664 (0.1853) loss: 0.8123 (0.8158) time: 0.1880 data: 0.1013 max mem: 9390 +Train: [93] [ 300/6250] eta: 0:19:04 lr: 0.000002 grad: 0.1557 (0.1802) loss: 0.8127 (0.8135) time: 0.1942 data: 0.0922 max mem: 9390 +Train: [93] [ 400/6250] eta: 0:18:21 lr: 0.000002 grad: 0.1574 (0.1745) loss: 0.8117 (0.8129) time: 0.1848 data: 0.0763 max mem: 9390 +Train: [93] [ 500/6250] eta: 0:17:45 lr: 0.000002 grad: 0.1561 (0.1703) loss: 0.8122 (0.8124) time: 0.1753 data: 0.0651 max mem: 9390 +Train: [93] [ 600/6250] eta: 0:17:09 lr: 0.000002 grad: 0.1463 (0.1670) loss: 0.8087 (0.8122) time: 0.1531 data: 0.0505 max mem: 9390 +Train: [93] [ 700/6250] eta: 0:16:43 lr: 0.000002 grad: 0.1485 (0.1662) loss: 0.8150 (0.8120) time: 0.1660 data: 0.0699 max mem: 9390 +Train: [93] [ 800/6250] eta: 0:16:15 lr: 0.000002 grad: 0.1498 (0.1647) loss: 0.8114 (0.8121) time: 0.1758 data: 0.0775 max mem: 9390 +Train: [93] [ 900/6250] eta: 0:15:48 lr: 0.000002 grad: 0.1398 (0.1633) loss: 0.8165 (0.8121) time: 0.1756 data: 0.0689 max mem: 9390 +Train: [93] [1000/6250] eta: 0:15:29 lr: 0.000002 grad: 0.1462 (0.1625) loss: 0.8150 (0.8120) time: 0.1490 data: 0.0504 max mem: 9390 +Train: [93] [1100/6250] eta: 0:15:07 lr: 0.000002 grad: 0.1462 (0.1619) loss: 0.8061 (0.8115) time: 0.1575 data: 0.0662 max mem: 9390 +Train: [93] [1200/6250] eta: 0:14:46 lr: 0.000002 grad: 0.1452 (0.1608) loss: 0.8144 (0.8116) time: 0.1729 data: 0.0826 max mem: 9390 +Train: [93] [1300/6250] eta: 0:14:22 lr: 0.000002 grad: 0.1517 (0.1599) loss: 0.8145 (0.8116) time: 0.1521 data: 0.0573 max mem: 9390 +Train: [93] [1400/6250] eta: 0:14:01 lr: 0.000002 grad: 0.1437 (0.1590) loss: 0.8161 (0.8117) time: 0.1698 data: 0.0803 max mem: 9390 +Train: [93] [1500/6250] eta: 0:13:43 lr: 0.000002 grad: 0.1476 (0.1583) loss: 0.8128 (0.8117) time: 0.1694 data: 0.0736 max mem: 9390 +Train: [93] [1600/6250] eta: 0:13:24 lr: 0.000002 grad: 0.1492 (0.1576) loss: 0.8092 (0.8117) time: 0.1552 data: 0.0639 max mem: 9390 +Train: [93] [1700/6250] eta: 0:13:04 lr: 0.000002 grad: 0.1411 (0.1569) loss: 0.8125 (0.8116) time: 0.1672 data: 0.0728 max mem: 9390 +Train: [93] [1800/6250] eta: 0:12:45 lr: 0.000002 grad: 0.1415 (0.1563) loss: 0.8134 (0.8117) time: 0.1750 data: 0.0872 max mem: 9390 +Train: [93] [1900/6250] eta: 0:12:26 lr: 0.000002 grad: 0.1402 (0.1559) loss: 0.8164 (0.8116) time: 0.1601 data: 0.0693 max mem: 9390 +Train: [93] [2000/6250] eta: 0:12:07 lr: 0.000002 grad: 0.1417 (0.1556) loss: 0.8065 (0.8116) time: 0.1892 data: 0.1115 max mem: 9390 +Train: [93] [2100/6250] eta: 0:11:47 lr: 0.000002 grad: 0.1463 (0.1552) loss: 0.8097 (0.8114) time: 0.1691 data: 0.0704 max mem: 9390 +Train: [93] [2200/6250] eta: 0:11:30 lr: 0.000002 grad: 0.1365 (0.1547) loss: 0.8115 (0.8114) time: 0.1876 data: 0.0957 max mem: 9390 +Train: [93] [2300/6250] eta: 0:11:12 lr: 0.000001 grad: 0.1373 (0.1543) loss: 0.8130 (0.8114) time: 0.1686 data: 0.0768 max mem: 9390 +Train: [93] [2400/6250] eta: 0:10:53 lr: 0.000001 grad: 0.1387 (0.1538) loss: 0.8143 (0.8115) time: 0.1701 data: 0.0786 max mem: 9390 +Train: [93] [2500/6250] eta: 0:10:35 lr: 0.000001 grad: 0.1416 (0.1533) loss: 0.8096 (0.8115) time: 0.1708 data: 0.0832 max mem: 9390 +Train: [93] [2600/6250] eta: 0:10:17 lr: 0.000001 grad: 0.1301 (0.1530) loss: 0.8176 (0.8115) time: 0.1542 data: 0.0675 max mem: 9390 +Train: [93] [2700/6250] eta: 0:10:01 lr: 0.000001 grad: 0.1441 (0.1526) loss: 0.8082 (0.8115) time: 0.1727 data: 0.0936 max mem: 9390 +Train: [93] [2800/6250] eta: 0:09:43 lr: 0.000001 grad: 0.1505 (0.1523) loss: 0.8068 (0.8115) time: 0.1605 data: 0.0653 max mem: 9390 +Train: [93] [2900/6250] eta: 0:09:25 lr: 0.000001 grad: 0.1304 (0.1519) loss: 0.8142 (0.8115) time: 0.1622 data: 0.0690 max mem: 9390 +Train: [93] [3000/6250] eta: 0:09:08 lr: 0.000001 grad: 0.1342 (0.1515) loss: 0.8143 (0.8116) time: 0.1628 data: 0.0803 max mem: 9390 +Train: [93] [3100/6250] eta: 0:08:50 lr: 0.000001 grad: 0.1347 (0.1511) loss: 0.8102 (0.8116) time: 0.1687 data: 0.0867 max mem: 9390 +Train: [93] [3200/6250] eta: 0:08:34 lr: 0.000001 grad: 0.1379 (0.1507) loss: 0.8113 (0.8116) time: 0.1630 data: 0.0794 max mem: 9390 +Train: [93] [3300/6250] eta: 0:08:17 lr: 0.000001 grad: 0.1328 (0.1504) loss: 0.8122 (0.8117) time: 0.1805 data: 0.0876 max mem: 9390 +Train: [93] [3400/6250] eta: 0:08:00 lr: 0.000001 grad: 0.1429 (0.1502) loss: 0.8143 (0.8117) time: 0.1754 data: 0.0927 max mem: 9390 +Train: [93] [3500/6250] eta: 0:07:43 lr: 0.000001 grad: 0.1467 (0.1500) loss: 0.8125 (0.8117) time: 0.1790 data: 0.0959 max mem: 9390 +Train: [93] [3600/6250] eta: 0:07:26 lr: 0.000001 grad: 0.1360 (0.1499) loss: 0.8159 (0.8117) time: 0.1577 data: 0.0667 max mem: 9390 +Train: [93] [3700/6250] eta: 0:07:09 lr: 0.000001 grad: 0.1287 (0.1496) loss: 0.8156 (0.8118) time: 0.1819 data: 0.0923 max mem: 9390 +Train: [93] [3800/6250] eta: 0:06:52 lr: 0.000001 grad: 0.1442 (0.1493) loss: 0.8164 (0.8119) time: 0.1579 data: 0.0668 max mem: 9390 +Train: [93] [3900/6250] eta: 0:06:35 lr: 0.000001 grad: 0.1385 (0.1491) loss: 0.8144 (0.8121) time: 0.1599 data: 0.0735 max mem: 9390 +Train: [93] [4000/6250] eta: 0:06:18 lr: 0.000001 grad: 0.1347 (0.1489) loss: 0.8197 (0.8122) time: 0.1631 data: 0.0776 max mem: 9390 +Train: [93] [4100/6250] eta: 0:06:01 lr: 0.000001 grad: 0.1398 (0.1488) loss: 0.8125 (0.8123) time: 0.1684 data: 0.0826 max mem: 9390 +Train: [93] [4200/6250] eta: 0:05:44 lr: 0.000001 grad: 0.1348 (0.1486) loss: 0.8181 (0.8124) time: 0.1578 data: 0.0718 max mem: 9390 +Train: [93] [4300/6250] eta: 0:05:27 lr: 0.000001 grad: 0.1405 (0.1485) loss: 0.8141 (0.8125) time: 0.1692 data: 0.0816 max mem: 9390 +Train: [93] [4400/6250] eta: 0:05:10 lr: 0.000001 grad: 0.1261 (0.1483) loss: 0.8150 (0.8125) time: 0.1797 data: 0.0934 max mem: 9390 +Train: [93] [4500/6250] eta: 0:04:53 lr: 0.000001 grad: 0.1407 (0.1481) loss: 0.8151 (0.8126) time: 0.1620 data: 0.0770 max mem: 9390 +Train: [93] [4600/6250] eta: 0:04:37 lr: 0.000001 grad: 0.1405 (0.1480) loss: 0.8179 (0.8127) time: 0.1765 data: 0.0845 max mem: 9390 +Train: [93] [4700/6250] eta: 0:04:20 lr: 0.000001 grad: 0.1375 (0.1478) loss: 0.8148 (0.8128) time: 0.1709 data: 0.0942 max mem: 9390 +Train: [93] [4800/6250] eta: 0:04:03 lr: 0.000001 grad: 0.1463 (0.1477) loss: 0.8139 (0.8128) time: 0.1687 data: 0.0822 max mem: 9390 +Train: [93] [4900/6250] eta: 0:03:46 lr: 0.000001 grad: 0.1441 (0.1475) loss: 0.8125 (0.8129) time: 0.1638 data: 0.0790 max mem: 9390 +Train: [93] [5000/6250] eta: 0:03:30 lr: 0.000001 grad: 0.1345 (0.1474) loss: 0.8222 (0.8130) time: 0.1944 data: 0.1149 max mem: 9390 +Train: [93] [5100/6250] eta: 0:03:13 lr: 0.000001 grad: 0.1393 (0.1472) loss: 0.8142 (0.8130) time: 0.1833 data: 0.0968 max mem: 9390 +Train: [93] [5200/6250] eta: 0:02:56 lr: 0.000001 grad: 0.1371 (0.1471) loss: 0.8087 (0.8131) time: 0.1610 data: 0.0737 max mem: 9390 +Train: [93] [5300/6250] eta: 0:02:39 lr: 0.000001 grad: 0.1440 (0.1470) loss: 0.8069 (0.8131) time: 0.1411 data: 0.0598 max mem: 9390 +Train: [93] [5400/6250] eta: 0:02:22 lr: 0.000001 grad: 0.1392 (0.1470) loss: 0.8144 (0.8131) time: 0.1699 data: 0.0851 max mem: 9390 +Train: [93] [5500/6250] eta: 0:02:06 lr: 0.000001 grad: 0.1359 (0.1469) loss: 0.8162 (0.8132) time: 0.1644 data: 0.0793 max mem: 9390 +Train: [93] [5600/6250] eta: 0:01:49 lr: 0.000001 grad: 0.1405 (0.1469) loss: 0.8109 (0.8132) time: 0.1710 data: 0.0814 max mem: 9390 +Train: [93] [5700/6250] eta: 0:01:32 lr: 0.000001 grad: 0.1381 (0.1468) loss: 0.8166 (0.8133) time: 0.1449 data: 0.0606 max mem: 9390 +Train: [93] [5800/6250] eta: 0:01:15 lr: 0.000001 grad: 0.1501 (0.1467) loss: 0.8150 (0.8133) time: 0.1522 data: 0.0589 max mem: 9390 +Train: [93] [5900/6250] eta: 0:00:58 lr: 0.000001 grad: 0.1258 (0.1466) loss: 0.8197 (0.8134) time: 0.1310 data: 0.0325 max mem: 9390 +Train: [93] [6000/6250] eta: 0:00:42 lr: 0.000001 grad: 0.1463 (0.1466) loss: 0.8134 (0.8134) time: 0.1859 data: 0.0905 max mem: 9390 +Train: [93] [6100/6250] eta: 0:00:25 lr: 0.000001 grad: 0.1402 (0.1466) loss: 0.8139 (0.8134) time: 0.2057 data: 0.1204 max mem: 9390 +Train: [93] [6200/6250] eta: 0:00:08 lr: 0.000001 grad: 0.1444 (0.1465) loss: 0.8159 (0.8135) time: 0.1638 data: 0.0787 max mem: 9390 +Train: [93] [6249/6250] eta: 0:00:00 lr: 0.000001 grad: 0.1409 (0.1465) loss: 0.8183 (0.8135) time: 0.1498 data: 0.0543 max mem: 9390 +Train: [93] Total time: 0:17:39 (0.1695 s / it) +Averaged stats: lr: 0.000001 grad: 0.1409 (0.1465) loss: 0.8183 (0.8135) +Eval (hcp-train-subset): [93] [ 0/62] eta: 0:04:56 loss: 0.8202 (0.8202) time: 4.7851 data: 4.7497 max mem: 9390 +Eval (hcp-train-subset): [93] [61/62] eta: 0:00:00 loss: 0.8110 (0.8152) time: 0.1211 data: 0.0943 max mem: 9390 +Eval (hcp-train-subset): [93] Total time: 0:00:13 (0.2154 s / it) +Averaged stats (hcp-train-subset): loss: 0.8110 (0.8152) +Eval (hcp-val): [93] [ 0/62] eta: 0:05:07 loss: 0.8269 (0.8269) time: 4.9538 data: 4.8872 max mem: 9390 +Eval (hcp-val): [93] [61/62] eta: 0:00:00 loss: 0.8281 (0.8281) time: 0.1086 data: 0.0836 max mem: 9390 +Eval (hcp-val): [93] Total time: 0:00:13 (0.2164 s / it) +Averaged stats (hcp-val): loss: 0.8281 (0.8281) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +Train: [94] [ 0/6250] eta: 8:10:19 lr: 0.000001 grad: 0.2643 (0.2643) loss: 0.8478 (0.8478) time: 4.7071 data: 4.4455 max mem: 9390 +Train: [94] [ 100/6250] eta: 0:21:51 lr: 0.000001 grad: 0.1649 (0.1855) loss: 0.8153 (0.8250) time: 0.1441 data: 0.0459 max mem: 9390 +Train: [94] [ 200/6250] eta: 0:19:33 lr: 0.000001 grad: 0.1490 (0.1775) loss: 0.8240 (0.8212) time: 0.1721 data: 0.0880 max mem: 9390 +Train: [94] [ 300/6250] eta: 0:18:11 lr: 0.000001 grad: 0.1360 (0.1695) loss: 0.8251 (0.8205) time: 0.1750 data: 0.0771 max mem: 9390 +Train: [94] [ 400/6250] eta: 0:17:30 lr: 0.000001 grad: 0.1459 (0.1644) loss: 0.8203 (0.8203) time: 0.1472 data: 0.0552 max mem: 9390 +Train: [94] [ 500/6250] eta: 0:17:11 lr: 0.000001 grad: 0.1600 (0.1623) loss: 0.8219 (0.8203) time: 0.1842 data: 0.0919 max mem: 9390 +Train: [94] [ 600/6250] eta: 0:16:59 lr: 0.000001 grad: 0.1400 (0.1602) loss: 0.8208 (0.8205) time: 0.2051 data: 0.1276 max mem: 9390 +Train: [94] [ 700/6250] eta: 0:16:28 lr: 0.000001 grad: 0.1371 (0.1584) loss: 0.8157 (0.8202) time: 0.1663 data: 0.0764 max mem: 9390 +Train: [94] [ 800/6250] eta: 0:16:06 lr: 0.000001 grad: 0.1481 (0.1579) loss: 0.8163 (0.8198) time: 0.1493 data: 0.0568 max mem: 9390 +Train: [94] [ 900/6250] eta: 0:15:45 lr: 0.000001 grad: 0.1421 (0.1569) loss: 0.8166 (0.8197) time: 0.1679 data: 0.0802 max mem: 9390 +Train: [94] [1000/6250] eta: 0:15:21 lr: 0.000001 grad: 0.1541 (0.1565) loss: 0.8194 (0.8195) time: 0.1456 data: 0.0599 max mem: 9390 +Train: [94] [1100/6250] eta: 0:14:56 lr: 0.000001 grad: 0.1409 (0.1558) loss: 0.8111 (0.8193) time: 0.1739 data: 0.0881 max mem: 9390 +Train: [94] [1200/6250] eta: 0:14:35 lr: 0.000001 grad: 0.1458 (0.1554) loss: 0.8139 (0.8187) time: 0.1808 data: 0.0926 max mem: 9390 +Train: [94] [1300/6250] eta: 0:14:14 lr: 0.000001 grad: 0.1357 (0.1551) loss: 0.8176 (0.8182) time: 0.1770 data: 0.0952 max mem: 9390 +Train: [94] [1400/6250] eta: 0:13:54 lr: 0.000001 grad: 0.1301 (0.1544) loss: 0.8185 (0.8179) time: 0.1734 data: 0.0907 max mem: 9390 +Train: [94] [1500/6250] eta: 0:13:36 lr: 0.000001 grad: 0.1432 (0.1538) loss: 0.8162 (0.8177) time: 0.1699 data: 0.0754 max mem: 9390 +Train: [94] [1600/6250] eta: 0:13:18 lr: 0.000001 grad: 0.1417 (0.1532) loss: 0.8122 (0.8174) time: 0.1767 data: 0.0799 max mem: 9390 +Train: [94] [1700/6250] eta: 0:12:59 lr: 0.000001 grad: 0.1418 (0.1527) loss: 0.8240 (0.8172) time: 0.1728 data: 0.0849 max mem: 9390 +Train: [94] [1800/6250] eta: 0:12:40 lr: 0.000001 grad: 0.1407 (0.1524) loss: 0.8119 (0.8169) time: 0.1447 data: 0.0583 max mem: 9390 +Train: [94] [1900/6250] eta: 0:12:22 lr: 0.000001 grad: 0.1478 (0.1522) loss: 0.8095 (0.8166) time: 0.1503 data: 0.0674 max mem: 9390 +Train: [94] [2000/6250] eta: 0:12:06 lr: 0.000001 grad: 0.1396 (0.1520) loss: 0.8110 (0.8164) time: 0.1730 data: 0.0852 max mem: 9390 +Train: [94] [2100/6250] eta: 0:11:47 lr: 0.000001 grad: 0.1341 (0.1516) loss: 0.8221 (0.8162) time: 0.1769 data: 0.0931 max mem: 9390 +Train: [94] [2200/6250] eta: 0:11:28 lr: 0.000001 grad: 0.1406 (0.1513) loss: 0.8160 (0.8161) time: 0.1675 data: 0.0828 max mem: 9390 +Train: [94] [2300/6250] eta: 0:11:11 lr: 0.000001 grad: 0.1424 (0.1513) loss: 0.8090 (0.8159) time: 0.1844 data: 0.0981 max mem: 9390 +Train: [94] [2400/6250] eta: 0:10:53 lr: 0.000001 grad: 0.1421 (0.1512) loss: 0.8152 (0.8157) time: 0.1760 data: 0.0895 max mem: 9390 +Train: [94] [2500/6250] eta: 0:10:35 lr: 0.000001 grad: 0.1462 (0.1511) loss: 0.8156 (0.8155) time: 0.1725 data: 0.0866 max mem: 9390 +Train: [94] [2600/6250] eta: 0:10:19 lr: 0.000001 grad: 0.1375 (0.1510) loss: 0.8203 (0.8155) time: 0.1446 data: 0.0509 max mem: 9390 +Train: [94] [2700/6250] eta: 0:10:02 lr: 0.000001 grad: 0.1429 (0.1509) loss: 0.8239 (0.8155) time: 0.1564 data: 0.0727 max mem: 9390 +Train: [94] [2800/6250] eta: 0:09:45 lr: 0.000001 grad: 0.1515 (0.1508) loss: 0.8122 (0.8156) time: 0.1981 data: 0.1104 max mem: 9390 +Train: [94] [2900/6250] eta: 0:09:27 lr: 0.000001 grad: 0.1328 (0.1505) loss: 0.8249 (0.8157) time: 0.1771 data: 0.0890 max mem: 9390 +Train: [94] [3000/6250] eta: 0:09:10 lr: 0.000001 grad: 0.1358 (0.1503) loss: 0.8184 (0.8158) time: 0.1507 data: 0.0661 max mem: 9390 +Train: [94] [3100/6250] eta: 0:08:53 lr: 0.000001 grad: 0.1436 (0.1501) loss: 0.8213 (0.8158) time: 0.1485 data: 0.0610 max mem: 9390 +Train: [94] [3200/6250] eta: 0:08:36 lr: 0.000001 grad: 0.1480 (0.1501) loss: 0.8159 (0.8158) time: 0.1658 data: 0.0850 max mem: 9390 +Train: [94] [3300/6250] eta: 0:08:19 lr: 0.000001 grad: 0.1420 (0.1500) loss: 0.8172 (0.8158) time: 0.1956 data: 0.1094 max mem: 9390 +Train: [94] [3400/6250] eta: 0:08:02 lr: 0.000001 grad: 0.1396 (0.1498) loss: 0.8118 (0.8158) time: 0.1291 data: 0.0385 max mem: 9390 +Train: [94] [3500/6250] eta: 0:07:45 lr: 0.000001 grad: 0.1439 (0.1497) loss: 0.8172 (0.8159) time: 0.1815 data: 0.0985 max mem: 9390 +Train: [94] [3600/6250] eta: 0:07:28 lr: 0.000001 grad: 0.1465 (0.1496) loss: 0.8206 (0.8159) time: 0.1399 data: 0.0498 max mem: 9390 +Train: [94] [3700/6250] eta: 0:07:11 lr: 0.000001 grad: 0.1496 (0.1495) loss: 0.8145 (0.8159) time: 0.1526 data: 0.0613 max mem: 9390 +Train: [94] [3800/6250] eta: 0:06:53 lr: 0.000001 grad: 0.1408 (0.1496) loss: 0.8124 (0.8159) time: 0.1544 data: 0.0648 max mem: 9390 +Train: [94] [3900/6250] eta: 0:06:37 lr: 0.000001 grad: 0.1423 (0.1495) loss: 0.8191 (0.8159) time: 0.1403 data: 0.0442 max mem: 9390 +Train: [94] [4000/6250] eta: 0:06:20 lr: 0.000001 grad: 0.1451 (0.1496) loss: 0.8127 (0.8159) time: 0.1929 data: 0.1067 max mem: 9390 +Train: [94] [4100/6250] eta: 0:06:03 lr: 0.000001 grad: 0.1491 (0.1496) loss: 0.8075 (0.8158) time: 0.1656 data: 0.0737 max mem: 9390 +Train: [94] [4200/6250] eta: 0:05:46 lr: 0.000001 grad: 0.1498 (0.1497) loss: 0.8169 (0.8157) time: 0.1808 data: 0.0900 max mem: 9390 +Train: [94] [4300/6250] eta: 0:05:29 lr: 0.000001 grad: 0.1533 (0.1498) loss: 0.8142 (0.8156) time: 0.1600 data: 0.0807 max mem: 9390 +Train: [94] [4400/6250] eta: 0:05:12 lr: 0.000001 grad: 0.1418 (0.1498) loss: 0.8158 (0.8155) time: 0.1690 data: 0.0759 max mem: 9390 +Train: [94] [4500/6250] eta: 0:04:55 lr: 0.000001 grad: 0.1497 (0.1498) loss: 0.8114 (0.8154) time: 0.1641 data: 0.0823 max mem: 9390 +Train: [94] [4600/6250] eta: 0:04:38 lr: 0.000001 grad: 0.1505 (0.1498) loss: 0.8130 (0.8154) time: 0.1553 data: 0.0703 max mem: 9390 +Train: [94] [4700/6250] eta: 0:04:21 lr: 0.000001 grad: 0.1433 (0.1498) loss: 0.8059 (0.8153) time: 0.1391 data: 0.0568 max mem: 9390 +Train: [94] [4800/6250] eta: 0:04:04 lr: 0.000001 grad: 0.1496 (0.1498) loss: 0.8042 (0.8152) time: 0.1586 data: 0.0721 max mem: 9390 +Train: [94] [4900/6250] eta: 0:03:48 lr: 0.000001 grad: 0.1404 (0.1498) loss: 0.8073 (0.8151) time: 0.2122 data: 0.1072 max mem: 9390 +Train: [94] [5000/6250] eta: 0:03:31 lr: 0.000001 grad: 0.1459 (0.1499) loss: 0.8084 (0.8150) time: 0.1696 data: 0.0749 max mem: 9390 +Train: [94] [5100/6250] eta: 0:03:15 lr: 0.000001 grad: 0.1446 (0.1499) loss: 0.8089 (0.8149) time: 0.1872 data: 0.0942 max mem: 9390 +Train: [94] [5200/6250] eta: 0:02:57 lr: 0.000001 grad: 0.1420 (0.1499) loss: 0.8078 (0.8148) time: 0.1364 data: 0.0554 max mem: 9390 +Train: [94] [5300/6250] eta: 0:02:40 lr: 0.000001 grad: 0.1571 (0.1499) loss: 0.8090 (0.8147) time: 0.1619 data: 0.0768 max mem: 9390 +Train: [94] [5400/6250] eta: 0:02:23 lr: 0.000001 grad: 0.1415 (0.1499) loss: 0.8067 (0.8146) time: 0.1848 data: 0.1047 max mem: 9390 +Train: [94] [5500/6250] eta: 0:02:06 lr: 0.000001 grad: 0.1541 (0.1499) loss: 0.8060 (0.8145) time: 0.1775 data: 0.0789 max mem: 9390 +Train: [94] [5600/6250] eta: 0:01:49 lr: 0.000001 grad: 0.1422 (0.1500) loss: 0.8071 (0.8145) time: 0.1764 data: 0.0876 max mem: 9390 +Train: [94] [5700/6250] eta: 0:01:33 lr: 0.000001 grad: 0.1593 (0.1500) loss: 0.8124 (0.8144) time: 0.1579 data: 0.0575 max mem: 9390 +Train: [94] [5800/6250] eta: 0:01:16 lr: 0.000001 grad: 0.1576 (0.1501) loss: 0.8068 (0.8143) time: 0.1709 data: 0.0743 max mem: 9390 +Train: [94] [5900/6250] eta: 0:00:59 lr: 0.000001 grad: 0.1472 (0.1502) loss: 0.8091 (0.8142) time: 0.1318 data: 0.0350 max mem: 9390 +Train: [94] [6000/6250] eta: 0:00:42 lr: 0.000001 grad: 0.1577 (0.1503) loss: 0.8085 (0.8141) time: 0.2031 data: 0.1132 max mem: 9390 +Train: [94] [6100/6250] eta: 0:00:25 lr: 0.000001 grad: 0.1526 (0.1504) loss: 0.8058 (0.8139) time: 0.1544 data: 0.0611 max mem: 9390 +Train: [94] [6200/6250] eta: 0:00:08 lr: 0.000001 grad: 0.1451 (0.1505) loss: 0.8100 (0.8138) time: 0.1723 data: 0.0780 max mem: 9390 +Train: [94] [6249/6250] eta: 0:00:00 lr: 0.000001 grad: 0.1536 (0.1505) loss: 0.8085 (0.8138) time: 0.1754 data: 0.0706 max mem: 9390 +Train: [94] Total time: 0:17:43 (0.1702 s / it) +Averaged stats: lr: 0.000001 grad: 0.1536 (0.1505) loss: 0.8085 (0.8138) +Eval (hcp-train-subset): [94] [ 0/62] eta: 0:05:09 loss: 0.8226 (0.8226) time: 4.9941 data: 4.9640 max mem: 9390 +Eval (hcp-train-subset): [94] [61/62] eta: 0:00:00 loss: 0.8115 (0.8149) time: 0.1039 data: 0.0767 max mem: 9390 +Eval (hcp-train-subset): [94] Total time: 0:00:13 (0.2241 s / it) +Averaged stats (hcp-train-subset): loss: 0.8115 (0.8149) +Making plots (hcp-train-subset): example=55 +Eval (hcp-val): [94] [ 0/62] eta: 0:05:51 loss: 0.8263 (0.8263) time: 5.6654 data: 5.6191 max mem: 9390 +Eval (hcp-val): [94] [61/62] eta: 0:00:00 loss: 0.8277 (0.8280) time: 0.1281 data: 0.1011 max mem: 9390 +Eval (hcp-val): [94] Total time: 0:00:13 (0.2230 s / it) +Averaged stats (hcp-val): loss: 0.8277 (0.8280) +Making plots (hcp-val): example=62 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +Train: [95] [ 0/6250] eta: 11:34:27 lr: 0.000001 grad: 0.3297 (0.3297) loss: 0.7545 (0.7545) time: 6.6668 data: 6.5599 max mem: 9390 +Train: [95] [ 100/6250] eta: 0:23:09 lr: 0.000001 grad: 0.1421 (0.1813) loss: 0.8190 (0.8180) time: 0.1907 data: 0.0871 max mem: 9390 +Train: [95] [ 200/6250] eta: 0:19:42 lr: 0.000001 grad: 0.1458 (0.1742) loss: 0.8249 (0.8197) time: 0.1614 data: 0.0639 max mem: 9390 +Train: [95] [ 300/6250] eta: 0:18:44 lr: 0.000001 grad: 0.1477 (0.1689) loss: 0.8133 (0.8195) time: 0.1927 data: 0.0945 max mem: 9390 +Train: [95] [ 400/6250] eta: 0:18:23 lr: 0.000001 grad: 0.1601 (0.1666) loss: 0.8188 (0.8190) time: 0.1781 data: 0.0925 max mem: 9390 +Train: [95] [ 500/6250] eta: 0:18:08 lr: 0.000001 grad: 0.1635 (0.1654) loss: 0.8115 (0.8183) time: 0.2085 data: 0.1133 max mem: 9390 +Train: [95] [ 600/6250] eta: 0:17:40 lr: 0.000001 grad: 0.1594 (0.1648) loss: 0.8190 (0.8174) time: 0.1597 data: 0.0697 max mem: 9390 +Train: [95] [ 700/6250] eta: 0:17:14 lr: 0.000001 grad: 0.1529 (0.1638) loss: 0.8086 (0.8168) time: 0.1795 data: 0.0852 max mem: 9390 +Train: [95] [ 800/6250] eta: 0:16:40 lr: 0.000001 grad: 0.1491 (0.1637) loss: 0.8140 (0.8161) time: 0.1602 data: 0.0695 max mem: 9390 +Train: [95] [ 900/6250] eta: 0:16:15 lr: 0.000001 grad: 0.1472 (0.1630) loss: 0.8108 (0.8159) time: 0.1738 data: 0.0845 max mem: 9390 +Train: [95] [1000/6250] eta: 0:15:49 lr: 0.000001 grad: 0.1550 (0.1620) loss: 0.8121 (0.8156) time: 0.1789 data: 0.0889 max mem: 9390 +Train: [95] [1100/6250] eta: 0:15:23 lr: 0.000001 grad: 0.1400 (0.1613) loss: 0.8222 (0.8155) time: 0.1481 data: 0.0599 max mem: 9390 +Train: [95] [1200/6250] eta: 0:15:00 lr: 0.000001 grad: 0.1328 (0.1604) loss: 0.8235 (0.8154) time: 0.1586 data: 0.0732 max mem: 9390 +Train: [95] [1300/6250] eta: 0:14:39 lr: 0.000001 grad: 0.1642 (0.1600) loss: 0.8084 (0.8152) time: 0.1692 data: 0.0782 max mem: 9390 +Train: [95] [1400/6250] eta: 0:14:18 lr: 0.000001 grad: 0.1471 (0.1593) loss: 0.8063 (0.8151) time: 0.1753 data: 0.0921 max mem: 9390 +Train: [95] [1500/6250] eta: 0:14:00 lr: 0.000001 grad: 0.1493 (0.1590) loss: 0.8113 (0.8148) time: 0.1781 data: 0.0918 max mem: 9390 +Train: [95] [1600/6250] eta: 0:13:42 lr: 0.000001 grad: 0.1559 (0.1588) loss: 0.8107 (0.8146) time: 0.1855 data: 0.0887 max mem: 9390 +Train: [95] [1700/6250] eta: 0:13:23 lr: 0.000001 grad: 0.1571 (0.1590) loss: 0.8096 (0.8142) time: 0.1889 data: 0.0914 max mem: 9390 +Train: [95] [1800/6250] eta: 0:13:03 lr: 0.000001 grad: 0.1481 (0.1587) loss: 0.8082 (0.8140) time: 0.1874 data: 0.0970 max mem: 9390 +Train: [95] [1900/6250] eta: 0:12:45 lr: 0.000001 grad: 0.1446 (0.1585) loss: 0.8077 (0.8138) time: 0.1719 data: 0.0843 max mem: 9390 +Train: [95] [2000/6250] eta: 0:12:27 lr: 0.000001 grad: 0.1530 (0.1583) loss: 0.8012 (0.8135) time: 0.1852 data: 0.0984 max mem: 9390 +Train: [95] [2100/6250] eta: 0:12:10 lr: 0.000001 grad: 0.1473 (0.1581) loss: 0.8074 (0.8133) time: 0.2064 data: 0.1249 max mem: 9390 +Train: [95] [2200/6250] eta: 0:11:52 lr: 0.000001 grad: 0.1513 (0.1579) loss: 0.8100 (0.8131) time: 0.1644 data: 0.0841 max mem: 9390 +Train: [95] [2300/6250] eta: 0:11:32 lr: 0.000001 grad: 0.1588 (0.1577) loss: 0.8108 (0.8129) time: 0.1548 data: 0.0663 max mem: 9390 +Train: [95] [2400/6250] eta: 0:11:15 lr: 0.000001 grad: 0.1382 (0.1575) loss: 0.8180 (0.8129) time: 0.1616 data: 0.0699 max mem: 9390 +Train: [95] [2500/6250] eta: 0:10:57 lr: 0.000001 grad: 0.1484 (0.1576) loss: 0.8055 (0.8127) time: 0.1733 data: 0.0814 max mem: 9390 +Train: [95] [2600/6250] eta: 0:10:40 lr: 0.000001 grad: 0.1550 (0.1575) loss: 0.8085 (0.8126) time: 0.1867 data: 0.1000 max mem: 9390 +Train: [95] [2700/6250] eta: 0:10:23 lr: 0.000001 grad: 0.1615 (0.1575) loss: 0.8139 (0.8125) time: 0.1788 data: 0.0859 max mem: 9390 +Train: [95] [2800/6250] eta: 0:10:05 lr: 0.000001 grad: 0.1471 (0.1573) loss: 0.8112 (0.8125) time: 0.1581 data: 0.0666 max mem: 9390 +Train: [95] [2900/6250] eta: 0:09:49 lr: 0.000001 grad: 0.1578 (0.1571) loss: 0.8030 (0.8125) time: 0.1838 data: 0.1024 max mem: 9390 +Train: [95] [3000/6250] eta: 0:09:32 lr: 0.000001 grad: 0.1514 (0.1571) loss: 0.8117 (0.8124) time: 0.1670 data: 0.0768 max mem: 9390 +Train: [95] [3100/6250] eta: 0:09:15 lr: 0.000001 grad: 0.1551 (0.1570) loss: 0.8083 (0.8124) time: 0.1795 data: 0.0873 max mem: 9390 +Train: [95] [3200/6250] eta: 0:08:58 lr: 0.000001 grad: 0.1511 (0.1569) loss: 0.8083 (0.8123) time: 0.1932 data: 0.1085 max mem: 9390 +Train: [95] [3300/6250] eta: 0:08:39 lr: 0.000001 grad: 0.1444 (0.1568) loss: 0.8145 (0.8123) time: 0.1581 data: 0.0706 max mem: 9390 +Train: [95] [3400/6250] eta: 0:08:23 lr: 0.000001 grad: 0.1437 (0.1567) loss: 0.8157 (0.8123) time: 0.1964 data: 0.1048 max mem: 9390 +Train: [95] [3500/6250] eta: 0:08:05 lr: 0.000001 grad: 0.1397 (0.1566) loss: 0.8141 (0.8123) time: 0.1573 data: 0.0723 max mem: 9390 +Train: [95] [3600/6250] eta: 0:07:48 lr: 0.000001 grad: 0.1524 (0.1565) loss: 0.8140 (0.8124) time: 0.1805 data: 0.0967 max mem: 9390 +Train: [95] [3700/6250] eta: 0:07:31 lr: 0.000001 grad: 0.1432 (0.1564) loss: 0.8090 (0.8123) time: 0.1902 data: 0.1039 max mem: 9390 +Train: [95] [3800/6250] eta: 0:07:13 lr: 0.000001 grad: 0.1429 (0.1562) loss: 0.8168 (0.8124) time: 0.1606 data: 0.0746 max mem: 9390 +Train: [95] [3900/6250] eta: 0:06:55 lr: 0.000001 grad: 0.1514 (0.1560) loss: 0.8087 (0.8124) time: 0.1609 data: 0.0724 max mem: 9390 +Train: [95] [4000/6250] eta: 0:06:38 lr: 0.000001 grad: 0.1473 (0.1560) loss: 0.8162 (0.8124) time: 0.1732 data: 0.0769 max mem: 9390 +Train: [95] [4100/6250] eta: 0:06:21 lr: 0.000001 grad: 0.1430 (0.1558) loss: 0.8143 (0.8124) time: 0.2008 data: 0.1056 max mem: 9390 +Train: [95] [4200/6250] eta: 0:06:03 lr: 0.000001 grad: 0.1512 (0.1557) loss: 0.8063 (0.8124) time: 0.1629 data: 0.0779 max mem: 9390 +Train: [95] [4300/6250] eta: 0:05:46 lr: 0.000001 grad: 0.1474 (0.1556) loss: 0.8090 (0.8123) time: 0.1212 data: 0.0141 max mem: 9390 +Train: [95] [4400/6250] eta: 0:05:28 lr: 0.000001 grad: 0.1417 (0.1554) loss: 0.8174 (0.8124) time: 0.1773 data: 0.0938 max mem: 9390 +Train: [95] [4500/6250] eta: 0:05:11 lr: 0.000001 grad: 0.1463 (0.1553) loss: 0.8111 (0.8124) time: 0.1851 data: 0.0956 max mem: 9390 +Train: [95] [4600/6250] eta: 0:04:53 lr: 0.000001 grad: 0.1431 (0.1551) loss: 0.8083 (0.8124) time: 0.1730 data: 0.0832 max mem: 9390 +Train: [95] [4700/6250] eta: 0:04:35 lr: 0.000001 grad: 0.1511 (0.1550) loss: 0.8125 (0.8124) time: 0.1878 data: 0.0900 max mem: 9390 +Train: [95] [4800/6250] eta: 0:04:17 lr: 0.000001 grad: 0.1454 (0.1550) loss: 0.8171 (0.8123) time: 0.1699 data: 0.0876 max mem: 9390 +Train: [95] [4900/6250] eta: 0:04:00 lr: 0.000001 grad: 0.1426 (0.1548) loss: 0.8163 (0.8123) time: 0.1643 data: 0.0077 max mem: 9390 +Train: [95] [5000/6250] eta: 0:03:42 lr: 0.000001 grad: 0.1572 (0.1548) loss: 0.8071 (0.8123) time: 0.1270 data: 0.0359 max mem: 9390 +Train: [95] [5100/6250] eta: 0:03:25 lr: 0.000001 grad: 0.1442 (0.1548) loss: 0.8123 (0.8123) time: 0.1337 data: 0.0029 max mem: 9390 +Train: [95] [5200/6250] eta: 0:03:08 lr: 0.000001 grad: 0.1502 (0.1548) loss: 0.8056 (0.8122) time: 0.1587 data: 0.0707 max mem: 9390 +Train: [95] [5300/6250] eta: 0:02:50 lr: 0.000001 grad: 0.1453 (0.1547) loss: 0.8051 (0.8122) time: 0.1958 data: 0.1037 max mem: 9390 +Train: [95] [5400/6250] eta: 0:02:32 lr: 0.000001 grad: 0.1514 (0.1548) loss: 0.8055 (0.8122) time: 0.2055 data: 0.1223 max mem: 9390 +Train: [95] [5500/6250] eta: 0:02:15 lr: 0.000001 grad: 0.1540 (0.1547) loss: 0.8079 (0.8121) time: 0.1967 data: 0.1088 max mem: 9390 +Train: [95] [5600/6250] eta: 0:01:57 lr: 0.000001 grad: 0.1514 (0.1547) loss: 0.8104 (0.8121) time: 0.1691 data: 0.0687 max mem: 9390 +Train: [95] [5700/6250] eta: 0:01:39 lr: 0.000001 grad: 0.1456 (0.1547) loss: 0.8158 (0.8121) time: 0.1412 data: 0.0452 max mem: 9390 +Train: [95] [5800/6250] eta: 0:01:21 lr: 0.000001 grad: 0.1488 (0.1547) loss: 0.8081 (0.8121) time: 0.2093 data: 0.1252 max mem: 9390 +Train: [95] [5900/6250] eta: 0:01:03 lr: 0.000001 grad: 0.1465 (0.1547) loss: 0.8174 (0.8121) time: 0.2214 data: 0.1450 max mem: 9390 +Train: [95] [6000/6250] eta: 0:00:45 lr: 0.000001 grad: 0.1473 (0.1546) loss: 0.8148 (0.8121) time: 0.1376 data: 0.0487 max mem: 9390 +Train: [95] [6100/6250] eta: 0:00:26 lr: 0.000001 grad: 0.1452 (0.1546) loss: 0.8144 (0.8121) time: 0.1562 data: 0.0717 max mem: 9390 +Train: [95] [6200/6250] eta: 0:00:08 lr: 0.000001 grad: 0.1542 (0.1545) loss: 0.8133 (0.8122) time: 0.1734 data: 0.0840 max mem: 9390 +Train: [95] [6249/6250] eta: 0:00:00 lr: 0.000001 grad: 0.1482 (0.1544) loss: 0.8143 (0.8122) time: 0.1320 data: 0.0414 max mem: 9390 +Train: [95] Total time: 0:18:51 (0.1810 s / it) +Averaged stats: lr: 0.000001 grad: 0.1482 (0.1544) loss: 0.8143 (0.8122) +Eval (hcp-train-subset): [95] [ 0/62] eta: 0:05:01 loss: 0.8234 (0.8234) time: 4.8653 data: 4.8344 max mem: 9390 +Eval (hcp-train-subset): [95] [61/62] eta: 0:00:00 loss: 0.8104 (0.8146) time: 0.1161 data: 0.0910 max mem: 9390 +Eval (hcp-train-subset): [95] Total time: 0:00:13 (0.2225 s / it) +Averaged stats (hcp-train-subset): loss: 0.8104 (0.8146) +Eval (hcp-val): [95] [ 0/62] eta: 0:04:53 loss: 0.8224 (0.8224) time: 4.7315 data: 4.7000 max mem: 9390 +Eval (hcp-val): [95] [61/62] eta: 0:00:00 loss: 0.8265 (0.8274) time: 0.1163 data: 0.0911 max mem: 9390 +Eval (hcp-val): [95] Total time: 0:00:13 (0.2191 s / it) +Averaged stats (hcp-val): loss: 0.8265 (0.8274) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +Train: [96] [ 0/6250] eta: 10:20:00 lr: 0.000001 grad: 0.1279 (0.1279) loss: 0.8612 (0.8612) time: 5.9520 data: 5.8365 max mem: 9390 +Train: [96] [ 100/6250] eta: 0:21:58 lr: 0.000001 grad: 0.1567 (0.1985) loss: 0.8247 (0.8235) time: 0.1388 data: 0.0393 max mem: 9390 +Train: [96] [ 200/6250] eta: 0:19:29 lr: 0.000001 grad: 0.1460 (0.1821) loss: 0.8265 (0.8227) time: 0.1985 data: 0.1092 max mem: 9390 +Train: [96] [ 300/6250] eta: 0:17:59 lr: 0.000001 grad: 0.1573 (0.1724) loss: 0.8233 (0.8238) time: 0.1433 data: 0.0471 max mem: 9390 +Train: [96] [ 400/6250] eta: 0:17:07 lr: 0.000001 grad: 0.1349 (0.1659) loss: 0.8285 (0.8246) time: 0.1381 data: 0.0466 max mem: 9390 +Train: [96] [ 500/6250] eta: 0:16:38 lr: 0.000001 grad: 0.1499 (0.1631) loss: 0.8156 (0.8236) time: 0.1668 data: 0.0656 max mem: 9390 +Train: [96] [ 600/6250] eta: 0:16:18 lr: 0.000001 grad: 0.1484 (0.1617) loss: 0.8162 (0.8225) time: 0.1780 data: 0.0769 max mem: 9390 +Train: [96] [ 700/6250] eta: 0:15:56 lr: 0.000001 grad: 0.1423 (0.1607) loss: 0.8193 (0.8218) time: 0.1707 data: 0.0812 max mem: 9390 +Train: [96] [ 800/6250] eta: 0:15:36 lr: 0.000001 grad: 0.1410 (0.1592) loss: 0.8133 (0.8210) time: 0.1800 data: 0.0943 max mem: 9390 +Train: [96] [ 900/6250] eta: 0:15:19 lr: 0.000001 grad: 0.1323 (0.1578) loss: 0.8192 (0.8203) time: 0.1842 data: 0.1001 max mem: 9390 +Train: [96] [1000/6250] eta: 0:14:58 lr: 0.000001 grad: 0.1476 (0.1567) loss: 0.8099 (0.8198) time: 0.1778 data: 0.0966 max mem: 9390 +Train: [96] [1100/6250] eta: 0:14:38 lr: 0.000000 grad: 0.1360 (0.1552) loss: 0.8224 (0.8197) time: 0.1689 data: 0.0828 max mem: 9390 +Train: [96] [1200/6250] eta: 0:14:17 lr: 0.000000 grad: 0.1361 (0.1540) loss: 0.8222 (0.8195) time: 0.1631 data: 0.0791 max mem: 9390 +Train: [96] [1300/6250] eta: 0:13:56 lr: 0.000000 grad: 0.1391 (0.1533) loss: 0.8157 (0.8192) time: 0.1589 data: 0.0736 max mem: 9390 +Train: [96] [1400/6250] eta: 0:13:39 lr: 0.000000 grad: 0.1447 (0.1527) loss: 0.8075 (0.8188) time: 0.1960 data: 0.1097 max mem: 9390 +Train: [96] [1500/6250] eta: 0:13:17 lr: 0.000000 grad: 0.1398 (0.1522) loss: 0.8138 (0.8186) time: 0.1563 data: 0.0581 max mem: 9390 +Train: [96] [1600/6250] eta: 0:13:01 lr: 0.000000 grad: 0.1376 (0.1520) loss: 0.8128 (0.8182) time: 0.1965 data: 0.1092 max mem: 9390 +Train: [96] [1700/6250] eta: 0:12:40 lr: 0.000000 grad: 0.1354 (0.1516) loss: 0.8136 (0.8179) time: 0.1491 data: 0.0612 max mem: 9390 +Train: [96] [1800/6250] eta: 0:12:22 lr: 0.000000 grad: 0.1378 (0.1514) loss: 0.8152 (0.8176) time: 0.1685 data: 0.0815 max mem: 9390 +Train: [96] [1900/6250] eta: 0:12:04 lr: 0.000000 grad: 0.1441 (0.1512) loss: 0.8101 (0.8171) time: 0.1670 data: 0.0753 max mem: 9390 +Train: [96] [2000/6250] eta: 0:11:46 lr: 0.000000 grad: 0.1396 (0.1508) loss: 0.8142 (0.8169) time: 0.1699 data: 0.0895 max mem: 9390 +Train: [96] [2100/6250] eta: 0:11:30 lr: 0.000000 grad: 0.1351 (0.1505) loss: 0.8177 (0.8168) time: 0.1587 data: 0.0765 max mem: 9390 +Train: [96] [2200/6250] eta: 0:11:11 lr: 0.000000 grad: 0.1391 (0.1503) loss: 0.8105 (0.8166) time: 0.1546 data: 0.0705 max mem: 9390 +Train: [96] [2300/6250] eta: 0:10:55 lr: 0.000000 grad: 0.1359 (0.1497) loss: 0.8143 (0.8166) time: 0.1648 data: 0.0784 max mem: 9390 +Train: [96] [2400/6250] eta: 0:10:37 lr: 0.000000 grad: 0.1322 (0.1493) loss: 0.8186 (0.8166) time: 0.1619 data: 0.0779 max mem: 9390 +Train: [96] [2500/6250] eta: 0:10:20 lr: 0.000000 grad: 0.1410 (0.1489) loss: 0.8169 (0.8166) time: 0.1484 data: 0.0570 max mem: 9390 +Train: [96] [2600/6250] eta: 0:10:03 lr: 0.000000 grad: 0.1361 (0.1487) loss: 0.8195 (0.8167) time: 0.1738 data: 0.0865 max mem: 9390 +Train: [96] [2700/6250] eta: 0:09:47 lr: 0.000000 grad: 0.1418 (0.1484) loss: 0.8129 (0.8167) time: 0.1224 data: 0.0298 max mem: 9390 +Train: [96] [2800/6250] eta: 0:09:30 lr: 0.000000 grad: 0.1403 (0.1483) loss: 0.8143 (0.8166) time: 0.1865 data: 0.0983 max mem: 9390 +Train: [96] [2900/6250] eta: 0:09:14 lr: 0.000000 grad: 0.1328 (0.1482) loss: 0.8132 (0.8165) time: 0.1627 data: 0.0797 max mem: 9390 +Train: [96] [3000/6250] eta: 0:08:56 lr: 0.000000 grad: 0.1381 (0.1481) loss: 0.8111 (0.8164) time: 0.1512 data: 0.0592 max mem: 9390 +Train: [96] [3100/6250] eta: 0:08:40 lr: 0.000000 grad: 0.1366 (0.1479) loss: 0.8183 (0.8165) time: 0.1957 data: 0.1090 max mem: 9390 +Train: [96] [3200/6250] eta: 0:08:24 lr: 0.000000 grad: 0.1406 (0.1478) loss: 0.8158 (0.8164) time: 0.1704 data: 0.0866 max mem: 9390 +Train: [96] [3300/6250] eta: 0:08:08 lr: 0.000000 grad: 0.1435 (0.1477) loss: 0.8128 (0.8164) time: 0.1775 data: 0.0916 max mem: 9390 +Train: [96] [3400/6250] eta: 0:07:51 lr: 0.000000 grad: 0.1526 (0.1478) loss: 0.8070 (0.8162) time: 0.1839 data: 0.1019 max mem: 9390 +Train: [96] [3500/6250] eta: 0:07:34 lr: 0.000000 grad: 0.1466 (0.1479) loss: 0.8142 (0.8161) time: 0.1658 data: 0.0811 max mem: 9390 +Train: [96] [3600/6250] eta: 0:07:18 lr: 0.000000 grad: 0.1352 (0.1478) loss: 0.8145 (0.8161) time: 0.1754 data: 0.0929 max mem: 9390 +Train: [96] [3700/6250] eta: 0:07:03 lr: 0.000000 grad: 0.1386 (0.1477) loss: 0.8178 (0.8161) time: 0.1812 data: 0.0986 max mem: 9390 +Train: [96] [3800/6250] eta: 0:06:47 lr: 0.000000 grad: 0.1416 (0.1476) loss: 0.8187 (0.8161) time: 0.1943 data: 0.1130 max mem: 9390 +Train: [96] [3900/6250] eta: 0:06:31 lr: 0.000000 grad: 0.1348 (0.1475) loss: 0.8147 (0.8161) time: 0.1829 data: 0.0988 max mem: 9390 +Train: [96] [4000/6250] eta: 0:06:15 lr: 0.000000 grad: 0.1413 (0.1474) loss: 0.8117 (0.8161) time: 0.1515 data: 0.0638 max mem: 9390 +Train: [96] [4100/6250] eta: 0:05:59 lr: 0.000000 grad: 0.1431 (0.1473) loss: 0.8136 (0.8161) time: 0.1602 data: 0.0703 max mem: 9390 +Train: [96] [4200/6250] eta: 0:05:41 lr: 0.000000 grad: 0.1386 (0.1473) loss: 0.8121 (0.8161) time: 0.1563 data: 0.0773 max mem: 9390 +Train: [96] [4300/6250] eta: 0:05:24 lr: 0.000000 grad: 0.1382 (0.1473) loss: 0.8172 (0.8161) time: 0.1566 data: 0.0575 max mem: 9390 +Train: [96] [4400/6250] eta: 0:05:07 lr: 0.000000 grad: 0.1473 (0.1473) loss: 0.8078 (0.8161) time: 0.1653 data: 0.0810 max mem: 9390 +Train: [96] [4500/6250] eta: 0:04:51 lr: 0.000000 grad: 0.1422 (0.1474) loss: 0.8119 (0.8160) time: 0.1420 data: 0.0392 max mem: 9390 +Train: [96] [4600/6250] eta: 0:04:34 lr: 0.000000 grad: 0.1461 (0.1474) loss: 0.8132 (0.8159) time: 0.1915 data: 0.0883 max mem: 9390 +Train: [96] [4700/6250] eta: 0:04:18 lr: 0.000000 grad: 0.1429 (0.1474) loss: 0.8189 (0.8159) time: 0.1953 data: 0.0932 max mem: 9390 +Train: [96] [4800/6250] eta: 0:04:02 lr: 0.000000 grad: 0.1413 (0.1474) loss: 0.8144 (0.8159) time: 0.1864 data: 0.0970 max mem: 9390 +Train: [96] [4900/6250] eta: 0:03:46 lr: 0.000000 grad: 0.1373 (0.1474) loss: 0.8087 (0.8159) time: 0.1805 data: 0.0843 max mem: 9390 +Train: [96] [5000/6250] eta: 0:03:29 lr: 0.000000 grad: 0.1452 (0.1474) loss: 0.8127 (0.8159) time: 0.1667 data: 0.0783 max mem: 9390 +Train: [96] [5100/6250] eta: 0:03:12 lr: 0.000000 grad: 0.1342 (0.1473) loss: 0.8147 (0.8159) time: 0.1584 data: 0.0777 max mem: 9390 +Train: [96] [5200/6250] eta: 0:02:55 lr: 0.000000 grad: 0.1508 (0.1473) loss: 0.8100 (0.8158) time: 0.1622 data: 0.0722 max mem: 9390 +Train: [96] [5300/6250] eta: 0:02:38 lr: 0.000000 grad: 0.1314 (0.1472) loss: 0.8146 (0.8159) time: 0.1674 data: 0.0862 max mem: 9390 +Train: [96] [5400/6250] eta: 0:02:22 lr: 0.000000 grad: 0.1370 (0.1471) loss: 0.8148 (0.8159) time: 0.1491 data: 0.0660 max mem: 9390 +Train: [96] [5500/6250] eta: 0:02:05 lr: 0.000000 grad: 0.1385 (0.1471) loss: 0.8145 (0.8159) time: 0.1714 data: 0.0804 max mem: 9390 +Train: [96] [5600/6250] eta: 0:01:48 lr: 0.000000 grad: 0.1337 (0.1470) loss: 0.8142 (0.8159) time: 0.1635 data: 0.0786 max mem: 9390 +Train: [96] [5700/6250] eta: 0:01:31 lr: 0.000000 grad: 0.1338 (0.1470) loss: 0.8136 (0.8159) time: 0.1547 data: 0.0676 max mem: 9390 +Train: [96] [5800/6250] eta: 0:01:14 lr: 0.000000 grad: 0.1364 (0.1469) loss: 0.8178 (0.8159) time: 0.1583 data: 0.0680 max mem: 9390 +Train: [96] [5900/6250] eta: 0:00:58 lr: 0.000000 grad: 0.1421 (0.1468) loss: 0.8149 (0.8159) time: 0.1871 data: 0.0951 max mem: 9390 +Train: [96] [6000/6250] eta: 0:00:41 lr: 0.000000 grad: 0.1469 (0.1468) loss: 0.8123 (0.8159) time: 0.1723 data: 0.0851 max mem: 9390 +Train: [96] [6100/6250] eta: 0:00:25 lr: 0.000000 grad: 0.1383 (0.1468) loss: 0.8192 (0.8160) time: 0.1504 data: 0.0660 max mem: 9390 +Train: [96] [6200/6250] eta: 0:00:08 lr: 0.000000 grad: 0.1341 (0.1467) loss: 0.8164 (0.8160) time: 0.1701 data: 0.0749 max mem: 9390 +Train: [96] [6249/6250] eta: 0:00:00 lr: 0.000000 grad: 0.1365 (0.1467) loss: 0.8183 (0.8160) time: 0.1837 data: 0.0979 max mem: 9390 +Train: [96] Total time: 0:17:29 (0.1680 s / it) +Averaged stats: lr: 0.000000 grad: 0.1365 (0.1467) loss: 0.8183 (0.8160) +Eval (hcp-train-subset): [96] [ 0/62] eta: 0:05:20 loss: 0.8221 (0.8221) time: 5.1628 data: 5.1282 max mem: 9390 +Eval (hcp-train-subset): [96] [61/62] eta: 0:00:00 loss: 0.8100 (0.8145) time: 0.1344 data: 0.1091 max mem: 9390 +Eval (hcp-train-subset): [96] Total time: 0:00:13 (0.2179 s / it) +Averaged stats (hcp-train-subset): loss: 0.8100 (0.8145) +Eval (hcp-val): [96] [ 0/62] eta: 0:05:27 loss: 0.8257 (0.8257) time: 5.2879 data: 5.2576 max mem: 9390 +Eval (hcp-val): [96] [61/62] eta: 0:00:00 loss: 0.8256 (0.8274) time: 0.0997 data: 0.0748 max mem: 9390 +Eval (hcp-val): [96] Total time: 0:00:13 (0.2108 s / it) +Averaged stats (hcp-val): loss: 0.8256 (0.8274) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +Train: [97] [ 0/6250] eta: 11:10:40 lr: 0.000000 grad: 0.1787 (0.1787) loss: 0.8285 (0.8285) time: 6.4386 data: 6.3404 max mem: 9390 +Train: [97] [ 100/6250] eta: 0:22:01 lr: 0.000000 grad: 0.1768 (0.1744) loss: 0.8075 (0.8173) time: 0.1682 data: 0.0705 max mem: 9390 +Train: [97] [ 200/6250] eta: 0:19:37 lr: 0.000000 grad: 0.1545 (0.1668) loss: 0.8207 (0.8168) time: 0.1789 data: 0.0826 max mem: 9390 +Train: [97] [ 300/6250] eta: 0:18:04 lr: 0.000000 grad: 0.1583 (0.1639) loss: 0.8199 (0.8178) time: 0.1693 data: 0.0748 max mem: 9390 +Train: [97] [ 400/6250] eta: 0:17:27 lr: 0.000000 grad: 0.1600 (0.1637) loss: 0.8124 (0.8183) time: 0.1694 data: 0.0799 max mem: 9390 +Train: [97] [ 500/6250] eta: 0:16:46 lr: 0.000000 grad: 0.1371 (0.1622) loss: 0.8158 (0.8180) time: 0.1591 data: 0.0734 max mem: 9390 +Train: [97] [ 600/6250] eta: 0:16:23 lr: 0.000000 grad: 0.1526 (0.1609) loss: 0.8183 (0.8180) time: 0.1647 data: 0.0764 max mem: 9390 +Train: [97] [ 700/6250] eta: 0:15:53 lr: 0.000000 grad: 0.1640 (0.1598) loss: 0.8228 (0.8182) time: 0.1452 data: 0.0501 max mem: 9390 +Train: [97] [ 800/6250] eta: 0:15:32 lr: 0.000000 grad: 0.1511 (0.1590) loss: 0.8148 (0.8185) time: 0.1615 data: 0.0745 max mem: 9390 +Train: [97] [ 900/6250] eta: 0:15:12 lr: 0.000000 grad: 0.1510 (0.1578) loss: 0.8177 (0.8185) time: 0.1733 data: 0.0774 max mem: 9390 +Train: [97] [1000/6250] eta: 0:14:47 lr: 0.000000 grad: 0.1454 (0.1570) loss: 0.8191 (0.8185) time: 0.1457 data: 0.0560 max mem: 9390 +Train: [97] [1100/6250] eta: 0:14:22 lr: 0.000000 grad: 0.1462 (0.1563) loss: 0.8172 (0.8185) time: 0.1811 data: 0.1001 max mem: 9390 +Train: [97] [1200/6250] eta: 0:14:00 lr: 0.000000 grad: 0.1492 (0.1557) loss: 0.8168 (0.8185) time: 0.1662 data: 0.0777 max mem: 9390 +Train: [97] [1300/6250] eta: 0:13:41 lr: 0.000000 grad: 0.1444 (0.1549) loss: 0.8188 (0.8185) time: 0.1620 data: 0.0751 max mem: 9390 +Train: [97] [1400/6250] eta: 0:13:22 lr: 0.000000 grad: 0.1523 (0.1542) loss: 0.8151 (0.8186) time: 0.1607 data: 0.0731 max mem: 9390 +Train: [97] [1500/6250] eta: 0:13:04 lr: 0.000000 grad: 0.1364 (0.1537) loss: 0.8187 (0.8186) time: 0.1691 data: 0.0787 max mem: 9390 +Train: [97] [1600/6250] eta: 0:12:47 lr: 0.000000 grad: 0.1508 (0.1534) loss: 0.8141 (0.8184) time: 0.1581 data: 0.0725 max mem: 9390 +Train: [97] [1700/6250] eta: 0:12:31 lr: 0.000000 grad: 0.1405 (0.1529) loss: 0.8192 (0.8183) time: 0.1761 data: 0.0951 max mem: 9390 +Train: [97] [1800/6250] eta: 0:12:12 lr: 0.000000 grad: 0.1459 (0.1528) loss: 0.8181 (0.8182) time: 0.1517 data: 0.0707 max mem: 9390 +Train: [97] [1900/6250] eta: 0:11:55 lr: 0.000000 grad: 0.1489 (0.1524) loss: 0.8173 (0.8183) time: 0.1487 data: 0.0640 max mem: 9390 +Train: [97] [2000/6250] eta: 0:11:38 lr: 0.000000 grad: 0.1450 (0.1521) loss: 0.8214 (0.8183) time: 0.1541 data: 0.0620 max mem: 9390 +Train: [97] [2100/6250] eta: 0:11:22 lr: 0.000000 grad: 0.1470 (0.1521) loss: 0.8128 (0.8181) time: 0.1578 data: 0.0667 max mem: 9390 +Train: [97] [2200/6250] eta: 0:11:05 lr: 0.000000 grad: 0.1466 (0.1518) loss: 0.8122 (0.8181) time: 0.1797 data: 0.0919 max mem: 9390 +Train: [97] [2300/6250] eta: 0:10:48 lr: 0.000000 grad: 0.1506 (0.1517) loss: 0.8136 (0.8180) time: 0.1511 data: 0.0755 max mem: 9390 +Train: [97] [2400/6250] eta: 0:10:30 lr: 0.000000 grad: 0.1470 (0.1515) loss: 0.8198 (0.8179) time: 0.1588 data: 0.0667 max mem: 9390 +Train: [97] [2500/6250] eta: 0:10:13 lr: 0.000000 grad: 0.1393 (0.1515) loss: 0.8128 (0.8177) time: 0.1469 data: 0.0563 max mem: 9390 +Train: [97] [2600/6250] eta: 0:09:55 lr: 0.000000 grad: 0.1512 (0.1515) loss: 0.8147 (0.8177) time: 0.1484 data: 0.0639 max mem: 9390 +Train: [97] [2700/6250] eta: 0:09:39 lr: 0.000000 grad: 0.1462 (0.1515) loss: 0.8159 (0.8176) time: 0.1652 data: 0.0884 max mem: 9390 +Train: [97] [2800/6250] eta: 0:09:22 lr: 0.000000 grad: 0.1472 (0.1514) loss: 0.8137 (0.8176) time: 0.1565 data: 0.0668 max mem: 9390 +Train: [97] [2900/6250] eta: 0:09:05 lr: 0.000000 grad: 0.1546 (0.1514) loss: 0.8135 (0.8175) time: 0.1568 data: 0.0674 max mem: 9390 +Train: [97] [3000/6250] eta: 0:08:48 lr: 0.000000 grad: 0.1435 (0.1513) loss: 0.8163 (0.8175) time: 0.1574 data: 0.0672 max mem: 9390 +Train: [97] [3100/6250] eta: 0:08:31 lr: 0.000000 grad: 0.1434 (0.1512) loss: 0.8166 (0.8175) time: 0.1614 data: 0.0714 max mem: 9390 +Train: [97] [3200/6250] eta: 0:08:15 lr: 0.000000 grad: 0.1416 (0.1512) loss: 0.8211 (0.8175) time: 0.1489 data: 0.0587 max mem: 9390 +Train: [97] [3300/6250] eta: 0:07:59 lr: 0.000000 grad: 0.1387 (0.1510) loss: 0.8239 (0.8176) time: 0.1497 data: 0.0702 max mem: 9390 +Train: [97] [3400/6250] eta: 0:07:42 lr: 0.000000 grad: 0.1391 (0.1509) loss: 0.8247 (0.8176) time: 0.1581 data: 0.0699 max mem: 9390 +Train: [97] [3500/6250] eta: 0:07:26 lr: 0.000000 grad: 0.1359 (0.1506) loss: 0.8215 (0.8177) time: 0.1540 data: 0.0712 max mem: 9390 +Train: [97] [3600/6250] eta: 0:07:11 lr: 0.000000 grad: 0.1355 (0.1503) loss: 0.8174 (0.8177) time: 0.2009 data: 0.1187 max mem: 9390 +Train: [97] [3700/6250] eta: 0:06:54 lr: 0.000000 grad: 0.1374 (0.1500) loss: 0.8204 (0.8177) time: 0.1391 data: 0.0477 max mem: 9390 +Train: [97] [3800/6250] eta: 0:06:37 lr: 0.000000 grad: 0.1414 (0.1499) loss: 0.8146 (0.8177) time: 0.1623 data: 0.0740 max mem: 9390 +Train: [97] [3900/6250] eta: 0:06:21 lr: 0.000000 grad: 0.1486 (0.1498) loss: 0.8138 (0.8177) time: 0.1591 data: 0.0744 max mem: 9390 +Train: [97] [4000/6250] eta: 0:06:04 lr: 0.000000 grad: 0.1338 (0.1498) loss: 0.8235 (0.8176) time: 0.1703 data: 0.0881 max mem: 9390 +Train: [97] [4100/6250] eta: 0:05:48 lr: 0.000000 grad: 0.1430 (0.1497) loss: 0.8140 (0.8176) time: 0.1499 data: 0.0643 max mem: 9390 +Train: [97] [4200/6250] eta: 0:05:32 lr: 0.000000 grad: 0.1468 (0.1497) loss: 0.8129 (0.8175) time: 0.1860 data: 0.1019 max mem: 9390 +Train: [97] [4300/6250] eta: 0:05:16 lr: 0.000000 grad: 0.1513 (0.1496) loss: 0.8066 (0.8174) time: 0.1762 data: 0.0933 max mem: 9390 +Train: [97] [4400/6250] eta: 0:04:59 lr: 0.000000 grad: 0.1461 (0.1495) loss: 0.8126 (0.8174) time: 0.1565 data: 0.0705 max mem: 9390 +Train: [97] [4500/6250] eta: 0:04:43 lr: 0.000000 grad: 0.1436 (0.1494) loss: 0.8168 (0.8174) time: 0.1610 data: 0.0809 max mem: 9390 +Train: [97] [4600/6250] eta: 0:04:27 lr: 0.000000 grad: 0.1432 (0.1494) loss: 0.8142 (0.8173) time: 0.1564 data: 0.0666 max mem: 9390 +Train: [97] [4700/6250] eta: 0:04:11 lr: 0.000000 grad: 0.1555 (0.1493) loss: 0.8111 (0.8173) time: 0.1658 data: 0.0764 max mem: 9390 +Train: [97] [4800/6250] eta: 0:03:54 lr: 0.000000 grad: 0.1359 (0.1492) loss: 0.8185 (0.8173) time: 0.1807 data: 0.1050 max mem: 9390 +Train: [97] [4900/6250] eta: 0:03:38 lr: 0.000000 grad: 0.1355 (0.1492) loss: 0.8145 (0.8173) time: 0.1563 data: 0.0680 max mem: 9390 +Train: [97] [5000/6250] eta: 0:03:22 lr: 0.000000 grad: 0.1396 (0.1492) loss: 0.8131 (0.8173) time: 0.1558 data: 0.0737 max mem: 9390 +Train: [97] [5100/6250] eta: 0:03:05 lr: 0.000000 grad: 0.1511 (0.1493) loss: 0.8109 (0.8173) time: 0.1640 data: 0.0823 max mem: 9390 +Train: [97] [5200/6250] eta: 0:02:49 lr: 0.000000 grad: 0.1421 (0.1492) loss: 0.8142 (0.8173) time: 0.1745 data: 0.0865 max mem: 9390 +Train: [97] [5300/6250] eta: 0:02:33 lr: 0.000000 grad: 0.1441 (0.1492) loss: 0.8128 (0.8173) time: 0.1613 data: 0.0758 max mem: 9390 +Train: [97] [5400/6250] eta: 0:02:17 lr: 0.000000 grad: 0.1423 (0.1491) loss: 0.8194 (0.8173) time: 0.1545 data: 0.0727 max mem: 9390 +Train: [97] [5500/6250] eta: 0:02:01 lr: 0.000000 grad: 0.1404 (0.1490) loss: 0.8148 (0.8173) time: 0.1608 data: 0.0687 max mem: 9390 +Train: [97] [5600/6250] eta: 0:01:45 lr: 0.000000 grad: 0.1411 (0.1489) loss: 0.8218 (0.8173) time: 0.1699 data: 0.0805 max mem: 9390 +Train: [97] [5700/6250] eta: 0:01:28 lr: 0.000000 grad: 0.1362 (0.1489) loss: 0.8196 (0.8173) time: 0.1597 data: 0.0653 max mem: 9390 +Train: [97] [5800/6250] eta: 0:01:12 lr: 0.000000 grad: 0.1443 (0.1488) loss: 0.8140 (0.8173) time: 0.1477 data: 0.0616 max mem: 9390 +Train: [97] [5900/6250] eta: 0:00:56 lr: 0.000000 grad: 0.1458 (0.1488) loss: 0.8166 (0.8173) time: 0.1772 data: 0.0902 max mem: 9390 +Train: [97] [6000/6250] eta: 0:00:40 lr: 0.000000 grad: 0.1428 (0.1488) loss: 0.8178 (0.8173) time: 0.1665 data: 0.0883 max mem: 9390 +Train: [97] [6100/6250] eta: 0:00:24 lr: 0.000000 grad: 0.1452 (0.1487) loss: 0.8204 (0.8174) time: 0.1527 data: 0.0740 max mem: 9390 +Train: [97] [6200/6250] eta: 0:00:08 lr: 0.000000 grad: 0.1499 (0.1487) loss: 0.8139 (0.8174) time: 0.1485 data: 0.0700 max mem: 9390 +Train: [97] [6249/6250] eta: 0:00:00 lr: 0.000000 grad: 0.1503 (0.1487) loss: 0.8149 (0.8174) time: 0.1576 data: 0.0781 max mem: 9390 +Train: [97] Total time: 0:16:54 (0.1623 s / it) +Averaged stats: lr: 0.000000 grad: 0.1503 (0.1487) loss: 0.8149 (0.8174) +Eval (hcp-train-subset): [97] [ 0/62] eta: 0:03:21 loss: 0.8213 (0.8213) time: 3.2440 data: 3.1803 max mem: 9390 +Eval (hcp-train-subset): [97] [61/62] eta: 0:00:00 loss: 0.8109 (0.8141) time: 0.1188 data: 0.0940 max mem: 9390 +Eval (hcp-train-subset): [97] Total time: 0:00:12 (0.1936 s / it) +Averaged stats (hcp-train-subset): loss: 0.8109 (0.8141) +Eval (hcp-val): [97] [ 0/62] eta: 0:04:56 loss: 0.8264 (0.8264) time: 4.7881 data: 4.7588 max mem: 9390 +Eval (hcp-val): [97] [61/62] eta: 0:00:00 loss: 0.8260 (0.8273) time: 0.1216 data: 0.0952 max mem: 9390 +Eval (hcp-val): [97] Total time: 0:00:12 (0.1942 s / it) +Averaged stats (hcp-val): loss: 0.8260 (0.8273) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +Train: [98] [ 0/6250] eta: 7:58:48 lr: 0.000000 grad: 0.1339 (0.1339) loss: 0.8345 (0.8345) time: 4.5965 data: 4.2848 max mem: 9390 +Train: [98] [ 100/6250] eta: 0:20:33 lr: 0.000000 grad: 0.1740 (0.1998) loss: 0.8091 (0.8237) time: 0.1542 data: 0.0728 max mem: 9390 +Train: [98] [ 200/6250] eta: 0:17:38 lr: 0.000000 grad: 0.1698 (0.1970) loss: 0.8140 (0.8191) time: 0.1409 data: 0.0598 max mem: 9390 +Train: [98] [ 300/6250] eta: 0:16:53 lr: 0.000000 grad: 0.1615 (0.1859) loss: 0.8148 (0.8182) time: 0.1538 data: 0.0715 max mem: 9390 +Train: [98] [ 400/6250] eta: 0:16:06 lr: 0.000000 grad: 0.1589 (0.1805) loss: 0.8130 (0.8170) time: 0.1555 data: 0.0707 max mem: 9390 +Train: [98] [ 500/6250] eta: 0:15:22 lr: 0.000000 grad: 0.1551 (0.1773) loss: 0.8109 (0.8164) time: 0.1469 data: 0.0596 max mem: 9390 +Train: [98] [ 600/6250] eta: 0:14:54 lr: 0.000000 grad: 0.1419 (0.1746) loss: 0.8098 (0.8158) time: 0.1627 data: 0.0650 max mem: 9390 +Train: [98] [ 700/6250] eta: 0:14:23 lr: 0.000000 grad: 0.1451 (0.1714) loss: 0.8106 (0.8154) time: 0.1367 data: 0.0509 max mem: 9390 +Train: [98] [ 800/6250] eta: 0:14:00 lr: 0.000000 grad: 0.1435 (0.1690) loss: 0.8181 (0.8152) time: 0.1210 data: 0.0344 max mem: 9390 +Train: [98] [ 900/6250] eta: 0:13:42 lr: 0.000000 grad: 0.1399 (0.1671) loss: 0.8110 (0.8150) time: 0.1657 data: 0.0827 max mem: 9390 +Train: [98] [1000/6250] eta: 0:13:15 lr: 0.000000 grad: 0.1392 (0.1650) loss: 0.8107 (0.8148) time: 0.1349 data: 0.0425 max mem: 9390 +Train: [98] [1100/6250] eta: 0:12:51 lr: 0.000000 grad: 0.1380 (0.1637) loss: 0.8158 (0.8147) time: 0.1195 data: 0.0386 max mem: 9390 +Train: [98] [1200/6250] eta: 0:12:31 lr: 0.000000 grad: 0.1436 (0.1622) loss: 0.8151 (0.8146) time: 0.1536 data: 0.0652 max mem: 9390 +Train: [98] [1300/6250] eta: 0:12:11 lr: 0.000000 grad: 0.1455 (0.1616) loss: 0.8152 (0.8144) time: 0.1502 data: 0.0640 max mem: 9390 +Train: [98] [1400/6250] eta: 0:11:52 lr: 0.000000 grad: 0.1401 (0.1607) loss: 0.8150 (0.8143) time: 0.1296 data: 0.0383 max mem: 9390 +Train: [98] [1500/6250] eta: 0:11:34 lr: 0.000000 grad: 0.1514 (0.1600) loss: 0.8060 (0.8141) time: 0.1415 data: 0.0581 max mem: 9390 +Train: [98] [1600/6250] eta: 0:11:16 lr: 0.000000 grad: 0.1413 (0.1596) loss: 0.8088 (0.8139) time: 0.1365 data: 0.0550 max mem: 9390 +Train: [98] [1700/6250] eta: 0:11:01 lr: 0.000000 grad: 0.1484 (0.1596) loss: 0.8136 (0.8137) time: 0.1527 data: 0.0746 max mem: 9390 +Train: [98] [1800/6250] eta: 0:10:44 lr: 0.000000 grad: 0.1363 (0.1590) loss: 0.8126 (0.8136) time: 0.1412 data: 0.0540 max mem: 9390 +Train: [98] [1900/6250] eta: 0:10:28 lr: 0.000000 grad: 0.1425 (0.1586) loss: 0.8122 (0.8134) time: 0.1316 data: 0.0416 max mem: 9390 +Train: [98] [2000/6250] eta: 0:10:14 lr: 0.000000 grad: 0.1384 (0.1582) loss: 0.8176 (0.8134) time: 0.1573 data: 0.0713 max mem: 9390 +Train: [98] [2100/6250] eta: 0:09:59 lr: 0.000000 grad: 0.1361 (0.1579) loss: 0.8145 (0.8133) time: 0.1589 data: 0.0794 max mem: 9390 +Train: [98] [2200/6250] eta: 0:09:45 lr: 0.000000 grad: 0.1377 (0.1573) loss: 0.8177 (0.8133) time: 0.1540 data: 0.0707 max mem: 9390 +Train: [98] [2300/6250] eta: 0:09:31 lr: 0.000000 grad: 0.1444 (0.1567) loss: 0.8099 (0.8133) time: 0.1496 data: 0.0655 max mem: 9390 +Train: [98] [2400/6250] eta: 0:09:17 lr: 0.000000 grad: 0.1446 (0.1563) loss: 0.8119 (0.8132) time: 0.1558 data: 0.0675 max mem: 9390 +Train: [98] [2500/6250] eta: 0:09:07 lr: 0.000000 grad: 0.1422 (0.1560) loss: 0.8101 (0.8131) time: 0.1944 data: 0.1170 max mem: 9390 +Train: [98] [2600/6250] eta: 0:08:55 lr: 0.000000 grad: 0.1381 (0.1557) loss: 0.8117 (0.8131) time: 0.1529 data: 0.0694 max mem: 9390 +Train: [98] [2700/6250] eta: 0:08:44 lr: 0.000000 grad: 0.1505 (0.1556) loss: 0.8158 (0.8130) time: 0.1776 data: 0.1017 max mem: 9390 +Train: [98] [2800/6250] eta: 0:08:31 lr: 0.000000 grad: 0.1615 (0.1555) loss: 0.8122 (0.8129) time: 0.1633 data: 0.0892 max mem: 9390 +Train: [98] [2900/6250] eta: 0:08:19 lr: 0.000000 grad: 0.1422 (0.1552) loss: 0.8195 (0.8130) time: 0.1837 data: 0.1033 max mem: 9390 +Train: [98] [3000/6250] eta: 0:08:05 lr: 0.000000 grad: 0.1497 (0.1549) loss: 0.8099 (0.8131) time: 0.1273 data: 0.0495 max mem: 9390 +Train: [98] [3100/6250] eta: 0:07:50 lr: 0.000000 grad: 0.1463 (0.1547) loss: 0.8133 (0.8132) time: 0.1802 data: 0.0934 max mem: 9390 +Train: [98] [3200/6250] eta: 0:07:36 lr: 0.000000 grad: 0.1474 (0.1546) loss: 0.8198 (0.8133) time: 0.1511 data: 0.0651 max mem: 9390 +Train: [98] [3300/6250] eta: 0:07:22 lr: 0.000000 grad: 0.1471 (0.1545) loss: 0.8170 (0.8134) time: 0.1599 data: 0.0688 max mem: 9390 +Train: [98] [3400/6250] eta: 0:07:07 lr: 0.000000 grad: 0.1458 (0.1543) loss: 0.8195 (0.8135) time: 0.1565 data: 0.0639 max mem: 9390 +Train: [98] [3500/6250] eta: 0:06:52 lr: 0.000000 grad: 0.1455 (0.1541) loss: 0.8170 (0.8137) time: 0.1675 data: 0.0794 max mem: 9390 +Train: [98] [3600/6250] eta: 0:06:37 lr: 0.000000 grad: 0.1476 (0.1538) loss: 0.8209 (0.8138) time: 0.1563 data: 0.0658 max mem: 9390 +Train: [98] [3700/6250] eta: 0:06:23 lr: 0.000000 grad: 0.1398 (0.1535) loss: 0.8237 (0.8140) time: 0.1389 data: 0.0427 max mem: 9390 +Train: [98] [3800/6250] eta: 0:06:08 lr: 0.000000 grad: 0.1434 (0.1533) loss: 0.8195 (0.8141) time: 0.1639 data: 0.0727 max mem: 9390 +Train: [98] [3900/6250] eta: 0:05:53 lr: 0.000000 grad: 0.1412 (0.1531) loss: 0.8188 (0.8142) time: 0.1433 data: 0.0516 max mem: 9390 +Train: [98] [4000/6250] eta: 0:05:38 lr: 0.000000 grad: 0.1430 (0.1530) loss: 0.8181 (0.8142) time: 0.1392 data: 0.0510 max mem: 9390 +Train: [98] [4100/6250] eta: 0:05:23 lr: 0.000000 grad: 0.1459 (0.1529) loss: 0.8109 (0.8143) time: 0.1471 data: 0.0622 max mem: 9390 +Train: [98] [4200/6250] eta: 0:05:07 lr: 0.000000 grad: 0.1454 (0.1528) loss: 0.8182 (0.8143) time: 0.1588 data: 0.0741 max mem: 9390 +Train: [98] [4300/6250] eta: 0:04:52 lr: 0.000000 grad: 0.1455 (0.1527) loss: 0.8162 (0.8144) time: 0.1595 data: 0.0717 max mem: 9390 +Train: [98] [4400/6250] eta: 0:04:38 lr: 0.000000 grad: 0.1399 (0.1525) loss: 0.8206 (0.8144) time: 0.1915 data: 0.1099 max mem: 9390 +Train: [98] [4500/6250] eta: 0:04:22 lr: 0.000000 grad: 0.1425 (0.1524) loss: 0.8215 (0.8144) time: 0.1431 data: 0.0617 max mem: 9390 +Train: [98] [4600/6250] eta: 0:04:07 lr: 0.000000 grad: 0.1388 (0.1524) loss: 0.8143 (0.8144) time: 0.1523 data: 0.0687 max mem: 9390 +Train: [98] [4700/6250] eta: 0:03:52 lr: 0.000000 grad: 0.1361 (0.1522) loss: 0.8139 (0.8144) time: 0.1181 data: 0.0337 max mem: 9390 +Train: [98] [4800/6250] eta: 0:03:37 lr: 0.000000 grad: 0.1368 (0.1521) loss: 0.8137 (0.8144) time: 0.1460 data: 0.0655 max mem: 9390 +Train: [98] [4900/6250] eta: 0:03:21 lr: 0.000000 grad: 0.1365 (0.1520) loss: 0.8145 (0.8144) time: 0.1252 data: 0.0368 max mem: 9390 +Train: [98] [5000/6250] eta: 0:03:06 lr: 0.000000 grad: 0.1488 (0.1519) loss: 0.8123 (0.8143) time: 0.1316 data: 0.0543 max mem: 9390 +Train: [98] [5100/6250] eta: 0:02:51 lr: 0.000000 grad: 0.1370 (0.1518) loss: 0.8161 (0.8144) time: 0.1666 data: 0.0855 max mem: 9390 +Train: [98] [5200/6250] eta: 0:02:36 lr: 0.000000 grad: 0.1475 (0.1517) loss: 0.8127 (0.8144) time: 0.1422 data: 0.0585 max mem: 9390 +Train: [98] [5300/6250] eta: 0:02:21 lr: 0.000000 grad: 0.1413 (0.1516) loss: 0.8166 (0.8144) time: 0.1306 data: 0.0448 max mem: 9390 +Train: [98] [5400/6250] eta: 0:02:06 lr: 0.000000 grad: 0.1342 (0.1514) loss: 0.8184 (0.8144) time: 0.1075 data: 0.0229 max mem: 9390 +Train: [98] [5500/6250] eta: 0:01:51 lr: 0.000000 grad: 0.1426 (0.1514) loss: 0.8160 (0.8144) time: 0.1449 data: 0.0588 max mem: 9390 +Train: [98] [5600/6250] eta: 0:01:36 lr: 0.000000 grad: 0.1379 (0.1514) loss: 0.8139 (0.8144) time: 0.1258 data: 0.0386 max mem: 9390 +Train: [98] [5700/6250] eta: 0:01:21 lr: 0.000000 grad: 0.1461 (0.1514) loss: 0.8078 (0.8143) time: 0.1337 data: 0.0487 max mem: 9390 +Train: [98] [5800/6250] eta: 0:01:06 lr: 0.000000 grad: 0.1506 (0.1513) loss: 0.8080 (0.8143) time: 0.1352 data: 0.0564 max mem: 9390 +Train: [98] [5900/6250] eta: 0:00:51 lr: 0.000000 grad: 0.1475 (0.1513) loss: 0.8113 (0.8143) time: 0.1507 data: 0.0616 max mem: 9390 +Train: [98] [6000/6250] eta: 0:00:36 lr: 0.000000 grad: 0.1398 (0.1513) loss: 0.8155 (0.8143) time: 0.1431 data: 0.0594 max mem: 9390 +Train: [98] [6100/6250] eta: 0:00:22 lr: 0.000000 grad: 0.1413 (0.1512) loss: 0.8166 (0.8143) time: 0.1460 data: 0.0646 max mem: 9390 +Train: [98] [6200/6250] eta: 0:00:07 lr: 0.000000 grad: 0.1472 (0.1511) loss: 0.8096 (0.8144) time: 0.1110 data: 0.0286 max mem: 9390 +Train: [98] [6249/6250] eta: 0:00:00 lr: 0.000000 grad: 0.1398 (0.1511) loss: 0.8184 (0.8144) time: 0.1393 data: 0.0597 max mem: 9390 +Train: [98] Total time: 0:15:27 (0.1484 s / it) +Averaged stats: lr: 0.000000 grad: 0.1398 (0.1511) loss: 0.8184 (0.8144) +Eval (hcp-train-subset): [98] [ 0/62] eta: 0:04:09 loss: 0.8219 (0.8219) time: 4.0215 data: 3.9914 max mem: 9390 +Eval (hcp-train-subset): [98] [61/62] eta: 0:00:00 loss: 0.8110 (0.8140) time: 0.1046 data: 0.0781 max mem: 9390 +Eval (hcp-train-subset): [98] Total time: 0:00:11 (0.1915 s / it) +Averaged stats (hcp-train-subset): loss: 0.8110 (0.8140) +Eval (hcp-val): [98] [ 0/62] eta: 0:03:05 loss: 0.8230 (0.8230) time: 2.9936 data: 2.9121 max mem: 9390 +Eval (hcp-val): [98] [61/62] eta: 0:00:00 loss: 0.8271 (0.8277) time: 0.1150 data: 0.0904 max mem: 9390 +Eval (hcp-val): [98] Total time: 0:00:12 (0.1952 s / it) +Averaged stats (hcp-val): loss: 0.8271 (0.8277) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +Train: [99] [ 0/6250] eta: 6:07:51 lr: 0.000000 grad: 0.0931 (0.0931) loss: 0.8370 (0.8370) time: 3.5314 data: 3.3545 max mem: 9390 +Train: [99] [ 100/6250] eta: 0:19:20 lr: 0.000000 grad: 0.1817 (0.2291) loss: 0.8092 (0.8124) time: 0.1431 data: 0.0545 max mem: 9390 +Train: [99] [ 200/6250] eta: 0:17:02 lr: 0.000000 grad: 0.1864 (0.2233) loss: 0.8086 (0.8100) time: 0.1358 data: 0.0512 max mem: 9390 +Train: [99] [ 300/6250] eta: 0:16:16 lr: 0.000000 grad: 0.1467 (0.2073) loss: 0.8229 (0.8120) time: 0.1308 data: 0.0399 max mem: 9390 +Train: [99] [ 400/6250] eta: 0:15:22 lr: 0.000000 grad: 0.1426 (0.2005) loss: 0.8122 (0.8121) time: 0.1267 data: 0.0335 max mem: 9390 +Train: [99] [ 500/6250] eta: 0:14:54 lr: 0.000000 grad: 0.1789 (0.1964) loss: 0.8048 (0.8114) time: 0.1382 data: 0.0485 max mem: 9390 +Train: [99] [ 600/6250] eta: 0:14:26 lr: 0.000000 grad: 0.1627 (0.1917) loss: 0.8078 (0.8119) time: 0.1385 data: 0.0405 max mem: 9390 +Train: [99] [ 700/6250] eta: 0:14:08 lr: 0.000000 grad: 0.1572 (0.1878) loss: 0.8174 (0.8122) time: 0.1364 data: 0.0534 max mem: 9390 +Train: [99] [ 800/6250] eta: 0:13:47 lr: 0.000000 grad: 0.1471 (0.1843) loss: 0.8159 (0.8130) time: 0.1569 data: 0.0733 max mem: 9390 +Train: [99] [ 900/6250] eta: 0:13:30 lr: 0.000000 grad: 0.1583 (0.1813) loss: 0.8176 (0.8137) time: 0.1606 data: 0.0777 max mem: 9390 +Train: [99] [1000/6250] eta: 0:13:15 lr: 0.000000 grad: 0.1440 (0.1786) loss: 0.8257 (0.8144) time: 0.1619 data: 0.0791 max mem: 9390 +Train: [99] [1100/6250] eta: 0:12:56 lr: 0.000000 grad: 0.1394 (0.1759) loss: 0.8220 (0.8150) time: 0.1732 data: 0.0955 max mem: 9390 +Train: [99] [1200/6250] eta: 0:12:39 lr: 0.000000 grad: 0.1362 (0.1741) loss: 0.8219 (0.8155) time: 0.1646 data: 0.0855 max mem: 9390 +Train: [99] [1300/6250] eta: 0:12:20 lr: 0.000000 grad: 0.1485 (0.1724) loss: 0.8212 (0.8159) time: 0.1465 data: 0.0605 max mem: 9390 +Train: [99] [1400/6250] eta: 0:12:05 lr: 0.000000 grad: 0.1396 (0.1708) loss: 0.8195 (0.8161) time: 0.1466 data: 0.0655 max mem: 9390 +Train: [99] [1500/6250] eta: 0:11:48 lr: 0.000000 grad: 0.1407 (0.1694) loss: 0.8169 (0.8163) time: 0.1426 data: 0.0606 max mem: 9390 +Train: [99] [1600/6250] eta: 0:11:31 lr: 0.000000 grad: 0.1379 (0.1679) loss: 0.8230 (0.8167) time: 0.1425 data: 0.0568 max mem: 9390 +Train: [99] [1700/6250] eta: 0:11:13 lr: 0.000000 grad: 0.1425 (0.1664) loss: 0.8205 (0.8170) time: 0.1281 data: 0.0480 max mem: 9390 +Train: [99] [1800/6250] eta: 0:10:58 lr: 0.000000 grad: 0.1397 (0.1654) loss: 0.8203 (0.8172) time: 0.1581 data: 0.0763 max mem: 9390 +Train: [99] [1900/6250] eta: 0:10:41 lr: 0.000000 grad: 0.1455 (0.1648) loss: 0.8210 (0.8174) time: 0.1198 data: 0.0370 max mem: 9390 +Train: [99] [2000/6250] eta: 0:10:26 lr: 0.000000 grad: 0.1469 (0.1640) loss: 0.8158 (0.8174) time: 0.1490 data: 0.0720 max mem: 9390 +Train: [99] [2100/6250] eta: 0:10:10 lr: 0.000000 grad: 0.1522 (0.1635) loss: 0.8188 (0.8175) time: 0.1540 data: 0.0734 max mem: 9390 +Train: [99] [2200/6250] eta: 0:09:54 lr: 0.000000 grad: 0.1449 (0.1631) loss: 0.8218 (0.8175) time: 0.1464 data: 0.0632 max mem: 9390 +Train: [99] [2300/6250] eta: 0:09:39 lr: 0.000000 grad: 0.1419 (0.1627) loss: 0.8195 (0.8176) time: 0.1704 data: 0.0910 max mem: 9390 +Train: [99] [2400/6250] eta: 0:09:24 lr: 0.000000 grad: 0.1401 (0.1621) loss: 0.8158 (0.8177) time: 0.1308 data: 0.0496 max mem: 9390 +Train: [99] [2500/6250] eta: 0:09:09 lr: 0.000000 grad: 0.1443 (0.1616) loss: 0.8177 (0.8177) time: 0.1396 data: 0.0599 max mem: 9390 +Train: [99] [2600/6250] eta: 0:08:53 lr: 0.000000 grad: 0.1522 (0.1611) loss: 0.8165 (0.8177) time: 0.1397 data: 0.0539 max mem: 9390 +Train: [99] [2700/6250] eta: 0:08:38 lr: 0.000000 grad: 0.1354 (0.1606) loss: 0.8200 (0.8176) time: 0.1611 data: 0.0832 max mem: 9390 +Train: [99] [2800/6250] eta: 0:08:23 lr: 0.000000 grad: 0.1502 (0.1602) loss: 0.8103 (0.8175) time: 0.1709 data: 0.0854 max mem: 9390 +Train: [99] [2900/6250] eta: 0:08:07 lr: 0.000000 grad: 0.1507 (0.1597) loss: 0.8158 (0.8175) time: 0.1386 data: 0.0560 max mem: 9390 +Train: [99] [3000/6250] eta: 0:07:52 lr: 0.000000 grad: 0.1438 (0.1594) loss: 0.8183 (0.8174) time: 0.1375 data: 0.0567 max mem: 9390 +Train: [99] [3100/6250] eta: 0:07:37 lr: 0.000000 grad: 0.1525 (0.1589) loss: 0.8189 (0.8175) time: 0.1349 data: 0.0533 max mem: 9390 +Train: [99] [3200/6250] eta: 0:07:23 lr: 0.000000 grad: 0.1422 (0.1585) loss: 0.8195 (0.8175) time: 0.1431 data: 0.0583 max mem: 9390 +Train: [99] [3300/6250] eta: 0:07:08 lr: 0.000000 grad: 0.1424 (0.1580) loss: 0.8182 (0.8175) time: 0.1386 data: 0.0564 max mem: 9390 +Train: [99] [3400/6250] eta: 0:06:53 lr: 0.000000 grad: 0.1381 (0.1576) loss: 0.8202 (0.8175) time: 0.1499 data: 0.0717 max mem: 9390 +Train: [99] [3500/6250] eta: 0:06:38 lr: 0.000000 grad: 0.1430 (0.1572) loss: 0.8186 (0.8175) time: 0.1592 data: 0.0739 max mem: 9390 +Train: [99] [3600/6250] eta: 0:06:23 lr: 0.000000 grad: 0.1407 (0.1568) loss: 0.8192 (0.8176) time: 0.1363 data: 0.0510 max mem: 9390 +Train: [99] [3700/6250] eta: 0:06:08 lr: 0.000000 grad: 0.1335 (0.1564) loss: 0.8163 (0.8175) time: 0.1362 data: 0.0512 max mem: 9390 +Train: [99] [3800/6250] eta: 0:05:54 lr: 0.000000 grad: 0.1483 (0.1561) loss: 0.8159 (0.8175) time: 0.1491 data: 0.0703 max mem: 9390 +Train: [99] [3900/6250] eta: 0:05:39 lr: 0.000000 grad: 0.1321 (0.1558) loss: 0.8154 (0.8174) time: 0.1591 data: 0.0779 max mem: 9390 +Train: [99] [4000/6250] eta: 0:05:25 lr: 0.000000 grad: 0.1415 (0.1554) loss: 0.8198 (0.8175) time: 0.1411 data: 0.0614 max mem: 9390 +Train: [99] [4100/6250] eta: 0:05:10 lr: 0.000000 grad: 0.1371 (0.1550) loss: 0.8228 (0.8175) time: 0.1383 data: 0.0582 max mem: 9390 +Train: [99] [4200/6250] eta: 0:04:56 lr: 0.000000 grad: 0.1275 (0.1547) loss: 0.8203 (0.8176) time: 0.1521 data: 0.0728 max mem: 9390 +Train: [99] [4300/6250] eta: 0:04:41 lr: 0.000000 grad: 0.1319 (0.1544) loss: 0.8179 (0.8175) time: 0.1349 data: 0.0574 max mem: 9390 +Train: [99] [4400/6250] eta: 0:04:27 lr: 0.000000 grad: 0.1387 (0.1541) loss: 0.8236 (0.8176) time: 0.1549 data: 0.0729 max mem: 9390 +Train: [99] [4500/6250] eta: 0:04:12 lr: 0.000000 grad: 0.1428 (0.1537) loss: 0.8178 (0.8176) time: 0.1214 data: 0.0415 max mem: 9390 +Train: [99] [4600/6250] eta: 0:03:58 lr: 0.000000 grad: 0.1383 (0.1535) loss: 0.8179 (0.8177) time: 0.1542 data: 0.0770 max mem: 9390 +Train: [99] [4700/6250] eta: 0:03:43 lr: 0.000000 grad: 0.1336 (0.1532) loss: 0.8230 (0.8177) time: 0.1320 data: 0.0437 max mem: 9390 +Train: [99] [4800/6250] eta: 0:03:29 lr: 0.000000 grad: 0.1304 (0.1531) loss: 0.8277 (0.8177) time: 0.1666 data: 0.0854 max mem: 9390 +Train: [99] [4900/6250] eta: 0:03:15 lr: 0.000000 grad: 0.1368 (0.1530) loss: 0.8216 (0.8177) time: 0.1593 data: 0.0789 max mem: 9390 +Train: [99] [5000/6250] eta: 0:03:00 lr: 0.000000 grad: 0.1373 (0.1528) loss: 0.8168 (0.8177) time: 0.1299 data: 0.0461 max mem: 9390 +Train: [99] [5100/6250] eta: 0:02:46 lr: 0.000000 grad: 0.1425 (0.1527) loss: 0.8197 (0.8176) time: 0.1917 data: 0.1160 max mem: 9390 +Train: [99] [5200/6250] eta: 0:02:31 lr: 0.000000 grad: 0.1389 (0.1526) loss: 0.8143 (0.8176) time: 0.1466 data: 0.0671 max mem: 9390 +Train: [99] [5300/6250] eta: 0:02:17 lr: 0.000000 grad: 0.1375 (0.1526) loss: 0.8179 (0.8176) time: 0.1449 data: 0.0654 max mem: 9390 +Train: [99] [5400/6250] eta: 0:02:03 lr: 0.000000 grad: 0.1362 (0.1524) loss: 0.8189 (0.8177) time: 0.1656 data: 0.0842 max mem: 9390 +Train: [99] [5500/6250] eta: 0:01:48 lr: 0.000000 grad: 0.1377 (0.1522) loss: 0.8186 (0.8177) time: 0.1476 data: 0.0656 max mem: 9390 +Train: [99] [5600/6250] eta: 0:01:34 lr: 0.000000 grad: 0.1418 (0.1521) loss: 0.8189 (0.8177) time: 0.1413 data: 0.0599 max mem: 9390 +Train: [99] [5700/6250] eta: 0:01:19 lr: 0.000000 grad: 0.1404 (0.1520) loss: 0.8249 (0.8178) time: 0.1413 data: 0.0605 max mem: 9390 +Train: [99] [5800/6250] eta: 0:01:05 lr: 0.000000 grad: 0.1410 (0.1519) loss: 0.8198 (0.8178) time: 0.1399 data: 0.0583 max mem: 9390 +Train: [99] [5900/6250] eta: 0:00:50 lr: 0.000000 grad: 0.1510 (0.1519) loss: 0.8195 (0.8178) time: 0.1427 data: 0.0591 max mem: 9390 +Train: [99] [6000/6250] eta: 0:00:36 lr: 0.000000 grad: 0.1589 (0.1518) loss: 0.8099 (0.8178) time: 0.1382 data: 0.0566 max mem: 9390 +Train: [99] [6100/6250] eta: 0:00:21 lr: 0.000000 grad: 0.1448 (0.1519) loss: 0.8185 (0.8178) time: 0.1469 data: 0.0632 max mem: 9390 +Train: [99] [6200/6250] eta: 0:00:07 lr: 0.000000 grad: 0.1386 (0.1518) loss: 0.8208 (0.8178) time: 0.1422 data: 0.0574 max mem: 9390 +Train: [99] [6249/6250] eta: 0:00:00 lr: 0.000000 grad: 0.1414 (0.1518) loss: 0.8169 (0.8178) time: 0.1492 data: 0.0673 max mem: 9390 +Train: [99] Total time: 0:15:10 (0.1456 s / it) +Averaged stats: lr: 0.000000 grad: 0.1414 (0.1518) loss: 0.8169 (0.8178) +Eval (hcp-train-subset): [99] [ 0/62] eta: 0:04:31 loss: 0.8215 (0.8215) time: 4.3727 data: 4.3419 max mem: 9390 +Eval (hcp-train-subset): [99] [61/62] eta: 0:00:00 loss: 0.8125 (0.8144) time: 0.1128 data: 0.0878 max mem: 9390 +Eval (hcp-train-subset): [99] Total time: 0:00:12 (0.2037 s / it) +Averaged stats (hcp-train-subset): loss: 0.8125 (0.8144) +Making plots (hcp-train-subset): example=41 +Eval (hcp-val): [99] [ 0/62] eta: 0:04:45 loss: 0.8229 (0.8229) time: 4.6011 data: 4.5695 max mem: 9390 +Eval (hcp-val): [99] [61/62] eta: 0:00:00 loss: 0.8265 (0.8277) time: 0.1138 data: 0.0890 max mem: 9390 +Eval (hcp-val): [99] Total time: 0:00:13 (0.2102 s / it) +Averaged stats (hcp-val): loss: 0.8265 (0.8277) +Making plots (hcp-val): example=10 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_4/pretrain/checkpoint-last.pth +done! training time: 4:45:31 diff --git a/input_space_v3/flat_lr1e-3_5/eval_v2/aabc_age__patch__logistic/config.yaml b/input_space_v3/flat_lr1e-3_5/eval_v2/aabc_age__patch__logistic/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..47fe081f34d5df156f582194b0054bcdabf90ec0 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_5/eval_v2/aabc_age__patch__logistic/config.yaml @@ -0,0 +1,30 @@ +output_root: experiments/input_space_v3/output +name_prefix: eval_logistic +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_5; eval v2 (aabc_age patch logistic) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: input_space_v3/flat_lr1e-3_5/eval_v2/aabc_age__patch__logistic +model: flat_mae +representation: patch +dataset: aabc_age +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/eval_v2/aabc_age__patch__logistic +remote_dir: null diff --git a/input_space_v3/flat_lr1e-3_5/eval_v2/aabc_age__patch__logistic/eval_table.csv b/input_space_v3/flat_lr1e-3_5/eval_v2/aabc_age__patch__logistic/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..6fce7a71faae4458eaaee9b8ead292b999be8085 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_5/eval_v2/aabc_age__patch__logistic/eval_table.csv @@ -0,0 +1,203 @@ +model,repr,clf,dataset,trial,C,split,acc,acc_std,f1,f1_std,bacc,bacc_std +flat_mae,patch,logistic,aabc_age,,0.046415888336127774,train,0.8385826771653543,0.015930308787009642,0.8371986395229913,0.01618617338054115,0.8381462813942608,0.015891388002597408 +flat_mae,patch,logistic,aabc_age,,0.046415888336127774,test,0.4423076923076923,0.05658030895061236,0.4147930922124471,0.059913011814365556,0.4336080586080586,0.056968683438119325 +flat_mae,patch,logistic,aabc_age,1,0.005994842503189409,train,0.687007874015748,0.020354260649599946,0.6853001338215468,0.020542498354297008,0.6872970565163439,0.02031925779442575 +flat_mae,patch,logistic,aabc_age,1,0.005994842503189409,test,0.4807692307692308,0.06108596861907142,0.4624668435013263,0.060999558786876705,0.47573260073260076,0.06043942970036643 +flat_mae,patch,logistic,aabc_age,2,0.000774263682681127,train,0.5610236220472441,0.022003717931913355,0.5563123645456456,0.02260531761122971,0.560746151146265,0.022013890045276534 +flat_mae,patch,logistic,aabc_age,2,0.000774263682681127,test,0.5384615384615384,0.06848422268958339,0.5348193473193474,0.06850206841790545,0.5338827838827839,0.06834725888185308 +flat_mae,patch,logistic,aabc_age,3,0.046415888336127774,train,0.8405511811023622,0.015692952400281807,0.8402745535714287,0.01584114986766503,0.840683131980153,0.015728467100077134 +flat_mae,patch,logistic,aabc_age,3,0.046415888336127774,test,0.6153846153846154,0.06739317648461444,0.6097204968944099,0.06911569507471783,0.6153846153846154,0.06771919362274331 +flat_mae,patch,logistic,aabc_age,4,0.3593813663804626,train,0.9901574803149606,0.004239417170474714,0.990070282496035,0.0042782040087089275,0.9900869360496674,0.004255486919310401 +flat_mae,patch,logistic,aabc_age,4,0.3593813663804626,test,0.5192307692307693,0.06359862815311805,0.49911083540115797,0.06641471687302049,0.5231227106227107,0.06411502368446155 +flat_mae,patch,logistic,aabc_age,5,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,5,2.782559402207126,test,0.4230769230769231,0.0661985537660005,0.41917060395321265,0.06611319931423,0.423992673992674,0.06649557939837873 +flat_mae,patch,logistic,aabc_age,6,0.005994842503189409,train,0.6771653543307087,0.019145315904582037,0.6744432453760898,0.019444274409027556,0.6773839925660112,0.01907170924312021 +flat_mae,patch,logistic,aabc_age,6,0.005994842503189409,test,0.5769230769230769,0.06526245375269371,0.5721548566376153,0.06737457817979146,0.5753205128205129,0.0653205978737284 +flat_mae,patch,logistic,aabc_age,7,0.046415888336127774,train,0.8385826771653543,0.01587727428356888,0.837546950035049,0.016115028260690823,0.8388345841588526,0.01585138664186225 +flat_mae,patch,logistic,aabc_age,7,0.046415888336127774,test,0.5576923076923077,0.06228559674700224,0.5589173789173789,0.0610961065162261,0.5531135531135531,0.06245921544284178 +flat_mae,patch,logistic,aabc_age,8,0.3593813663804626,train,0.9940944881889764,0.0032688523782501565,0.9941242546401277,0.0032601412993777334,0.9939516129032258,0.0033479375164336372 +flat_mae,patch,logistic,aabc_age,8,0.3593813663804626,test,0.5,0.06004066669187421,0.4973789173789174,0.059319469221224864,0.502518315018315,0.060470497027108716 +flat_mae,patch,logistic,aabc_age,9,0.005994842503189409,train,0.6751968503937008,0.01993033156864764,0.6741595015081058,0.020232829533298448,0.6754678368741956,0.019893755567813146 +flat_mae,patch,logistic,aabc_age,9,0.005994842503189409,test,0.4423076923076923,0.06634519508783288,0.4349924585218703,0.0655235648666099,0.4358974358974359,0.06599008401231207 +flat_mae,patch,logistic,aabc_age,10,0.000774263682681127,train,0.5807086614173228,0.020042169490280135,0.5726310032339661,0.02074353401970813,0.5799371966036875,0.020002546728153006 +flat_mae,patch,logistic,aabc_age,10,0.000774263682681127,test,0.4807692307692308,0.06606595234439293,0.4790247252747253,0.06545348765682724,0.47733516483516486,0.06589522136650743 +flat_mae,patch,logistic,aabc_age,11,0.046415888336127774,train,0.8346456692913385,0.016570769797472407,0.8335966908078462,0.016802026901010306,0.8349699073052941,0.01657017006976552 +flat_mae,patch,logistic,aabc_age,11,0.046415888336127774,test,0.6153846153846154,0.06638308893868543,0.6219405594405594,0.06624105679372524,0.614010989010989,0.06662837471994132 +flat_mae,patch,logistic,aabc_age,12,0.046415888336127774,train,0.8287401574803149,0.016685176393740123,0.8281449002089438,0.016797225849995316,0.8288539123380049,0.01661284135155663 +flat_mae,patch,logistic,aabc_age,12,0.046415888336127774,test,0.4423076923076923,0.0628732170333151,0.4472723955482576,0.0627343293601991,0.44482600732600736,0.06318377623660765 +flat_mae,patch,logistic,aabc_age,13,0.046415888336127774,train,0.8287401574803149,0.016742829006611944,0.8279093627234699,0.01704114147530115,0.8294066426410991,0.016777587391590385 +flat_mae,patch,logistic,aabc_age,13,0.046415888336127774,test,0.4807692307692308,0.0653877261703434,0.48484330484330485,0.06334683782838717,0.4832875457875458,0.06597123306805289 +flat_mae,patch,logistic,aabc_age,14,0.046415888336127774,train,0.844488188976378,0.01549919347740383,0.8438847077371945,0.015706320055491902,0.8447653767148904,0.015552370526473397 +flat_mae,patch,logistic,aabc_age,14,0.046415888336127774,test,0.5384615384615384,0.06682061121271068,0.5341414141414141,0.06898052146755347,0.5398351648351648,0.06675100394866842 +flat_mae,patch,logistic,aabc_age,15,0.046415888336127774,train,0.8464566929133859,0.016329994897043513,0.8464939625591801,0.0163295183502895,0.8472490069794337,0.016307195957314623 +flat_mae,patch,logistic,aabc_age,15,0.046415888336127774,test,0.46153846153846156,0.06706981040271115,0.47472514713894026,0.06488882117740079,0.46565934065934067,0.06731322626044223 +flat_mae,patch,logistic,aabc_age,16,0.046415888336127774,train,0.8326771653543307,0.016663346177590257,0.832172436945731,0.016867221689779704,0.831965912207584,0.016749085820003944 +flat_mae,patch,logistic,aabc_age,16,0.046415888336127774,test,0.5,0.06506637484979991,0.49522546419098146,0.06637158094597087,0.5059523809523809,0.0651028661581655 +flat_mae,patch,logistic,aabc_age,17,9.999999999999999e-05,train,0.4940944881889764,0.0203398839210492,0.4686898695114658,0.021228706605033777,0.4908981106237377,0.02016173308043746 +flat_mae,patch,logistic,aabc_age,17,9.999999999999999e-05,test,0.4423076923076923,0.05577453555672201,0.4031010536398468,0.055272018404423785,0.4356684981684982,0.054694384590792684 +flat_mae,patch,logistic,aabc_age,18,0.046415888336127774,train,0.8464566929133859,0.015459600269686196,0.8455446867927945,0.015592660052048367,0.8462463966443481,0.015440371268237121 +flat_mae,patch,logistic,aabc_age,18,0.046415888336127774,test,0.4807692307692308,0.06968376369770021,0.4903846153846153,0.0689060910831291,0.4835164835164835,0.07005196015062341 +flat_mae,patch,logistic,aabc_age,19,0.005994842503189409,train,0.6673228346456693,0.02048030247300022,0.6635637480798771,0.020972297714120763,0.6678060910375938,0.020432380653857732 +flat_mae,patch,logistic,aabc_age,19,0.005994842503189409,test,0.4423076923076923,0.06744284233518424,0.43100168665667166,0.06925262705466918,0.4375,0.06745522642845192 +flat_mae,patch,logistic,aabc_age,20,0.046415888336127774,train,0.8464566929133859,0.015850356540709275,0.8461003529682458,0.01595183152928992,0.8464463433252332,0.015945043899182075 +flat_mae,patch,logistic,aabc_age,20,0.046415888336127774,test,0.46153846153846156,0.05526069202281344,0.43981481481481477,0.050789745059337435,0.4576465201465202,0.05461054752737594 +flat_mae,patch,logistic,aabc_age,21,0.046415888336127774,train,0.8484251968503937,0.016164076622397782,0.8482110197450862,0.016344699521692464,0.8482449044763123,0.016226538540412953 +flat_mae,patch,logistic,aabc_age,21,0.046415888336127774,test,0.3269230769230769,0.06457182597742742,0.3296182266009852,0.06390856635783718,0.3289835164835165,0.06511282149492238 +flat_mae,patch,logistic,aabc_age,22,0.046415888336127774,train,0.84251968503937,0.015676864786307868,0.8414782396655105,0.015944850231924556,0.8423817197907896,0.015748625021140487 +flat_mae,patch,logistic,aabc_age,22,0.046415888336127774,test,0.36538461538461536,0.06307611397229662,0.3932843137254902,0.06142410940253011,0.3708791208791209,0.063529559035273 +flat_mae,patch,logistic,aabc_age,23,0.046415888336127774,train,0.8267716535433071,0.017353074446863456,0.8266118600233099,0.017413387718709948,0.8272229323978834,0.017307939306037908 +flat_mae,patch,logistic,aabc_age,23,0.046415888336127774,test,0.5576923076923077,0.05811257184049902,0.5379889886989279,0.06367476817829491,0.5542582417582418,0.05823759397477178 +flat_mae,patch,logistic,aabc_age,24,0.046415888336127774,train,0.844488188976378,0.016981980781856486,0.844387837906974,0.01703176588217253,0.8449153367255543,0.016937144584620464 +flat_mae,patch,logistic,aabc_age,24,0.046415888336127774,test,0.40384615384615385,0.06316217269198075,0.3958333333333333,0.06268832562009978,0.40315934065934067,0.06301428727425992 +flat_mae,patch,logistic,aabc_age,25,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,25,2.782559402207126,test,0.5,0.06591875715135032,0.49755852842809367,0.066128229702766,0.4981684981684981,0.06600399079456545 +flat_mae,patch,logistic,aabc_age,26,0.046415888336127774,train,0.8366141732283464,0.01641784964882961,0.8358147882686822,0.01664276043100921,0.8366508739156369,0.016508329047208913 +flat_mae,patch,logistic,aabc_age,26,0.046415888336127774,test,0.4807692307692308,0.06620100063599568,0.4881543187994801,0.0656381025921867,0.48511904761904767,0.06634358561597829 +flat_mae,patch,logistic,aabc_age,27,0.046415888336127774,train,0.8582677165354331,0.01492296128084325,0.8580599363750299,0.015040150406655954,0.8587606853999604,0.014875828201174222 +flat_mae,patch,logistic,aabc_age,27,0.046415888336127774,test,0.4230769230769231,0.06081024662566791,0.3958855472013367,0.061836487427333574,0.41689560439560436,0.06026962887307377 +flat_mae,patch,logistic,aabc_age,28,0.005994842503189409,train,0.6732283464566929,0.02105976537208891,0.6726161414148163,0.021305591503401774,0.6738368569340741,0.02097575140908867 +flat_mae,patch,logistic,aabc_age,28,0.005994842503189409,test,0.5769230769230769,0.06451040006058195,0.5679759552042161,0.06830412257905911,0.5766941391941391,0.06472567254060557 +flat_mae,patch,logistic,aabc_age,29,9.999999999999999e-05,train,0.5039370078740157,0.018763223993150783,0.46623769432134654,0.018791977058511287,0.4995410096875845,0.018579749683306994 +flat_mae,patch,logistic,aabc_age,29,9.999999999999999e-05,test,0.3076923076923077,0.06053278000902736,0.2954032258064516,0.05621134351834604,0.30654761904761907,0.06013266721036993 +flat_mae,patch,logistic,aabc_age,30,0.046415888336127774,train,0.8405511811023622,0.016406060734303594,0.8408556789851753,0.016499512019857176,0.8414857956343537,0.01638907367325991 +flat_mae,patch,logistic,aabc_age,30,0.046415888336127774,test,0.5961538461538461,0.06828200313891444,0.5960989010989011,0.06825507303452724,0.5975274725274725,0.0682867252341207 +flat_mae,patch,logistic,aabc_age,31,0.3593813663804626,train,0.9921259842519685,0.003842912962319082,0.9921036091635906,0.003866496072059992,0.9921530517521466,0.003839804839540504 +flat_mae,patch,logistic,aabc_age,31,0.3593813663804626,test,0.5769230769230769,0.06411800326893582,0.5719372456628828,0.0656868775861503,0.5755494505494505,0.06415723109036968 +flat_mae,patch,logistic,aabc_age,32,0.005994842503189409,train,0.6791338582677166,0.020360436724067753,0.6767181530146305,0.02053449578610501,0.6796676761496694,0.02022199167588267 +flat_mae,patch,logistic,aabc_age,32,0.005994842503189409,test,0.5,0.06279226340239111,0.48344827586206895,0.061943808010026816,0.49496336996337,0.062212320917483944 +flat_mae,patch,logistic,aabc_age,33,9.999999999999999e-05,train,0.49606299212598426,0.01943706010688373,0.4621578814586611,0.020139938172272824,0.4913588990178159,0.019300869053262868 +flat_mae,patch,logistic,aabc_age,33,9.999999999999999e-05,test,0.4807692307692308,0.05377273841315601,0.4180778371954843,0.047136054925837466,0.47115384615384615,0.052351754674950395 +flat_mae,patch,logistic,aabc_age,34,0.005994842503189409,train,0.6771653543307087,0.020905313106103714,0.6754492913397911,0.021053995865292142,0.6767312889224744,0.020834545204039594 +flat_mae,patch,logistic,aabc_age,34,0.005994842503189409,test,0.5192307692307693,0.06512503904074969,0.5174485125858124,0.06883933053379125,0.5135073260073261,0.06559486519703017 +flat_mae,patch,logistic,aabc_age,35,0.000774263682681127,train,0.5570866141732284,0.021055073940318445,0.5503488349757006,0.02167021606226913,0.5567315142820428,0.02102447837446689 +flat_mae,patch,logistic,aabc_age,35,0.000774263682681127,test,0.40384615384615385,0.06485445699191364,0.3915057566336766,0.06494547042953264,0.4001831501831502,0.06428858449417393 +flat_mae,patch,logistic,aabc_age,36,0.046415888336127774,train,0.8346456692913385,0.01658329172725154,0.8341830081721227,0.01668636452130588,0.8343172036617573,0.016542352364707427 +flat_mae,patch,logistic,aabc_age,36,0.046415888336127774,test,0.4807692307692308,0.06469613772619189,0.46615804744836997,0.06656764661501756,0.48168498168498164,0.06490070438190533 +flat_mae,patch,logistic,aabc_age,37,0.046415888336127774,train,0.8523622047244095,0.016422786058272944,0.85266682875771,0.016433818296047252,0.8535149619573869,0.016295426611679816 +flat_mae,patch,logistic,aabc_age,37,0.046415888336127774,test,0.46153846153846156,0.058554720778463173,0.4444305694305694,0.05388930479162662,0.453525641025641,0.057671494159695705 +flat_mae,patch,logistic,aabc_age,38,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,38,2.782559402207126,test,0.4423076923076923,0.06506578373475379,0.4439039855072464,0.06444285310614131,0.4391025641025641,0.06521060883965044 +flat_mae,patch,logistic,aabc_age,39,0.005994842503189409,train,0.6751968503937008,0.02040796137466393,0.6713650471507409,0.020622464112494066,0.675167916852868,0.020377289060232347 +flat_mae,patch,logistic,aabc_age,39,0.005994842503189409,test,0.5,0.06427956460676677,0.48856460146782726,0.06510501843973844,0.4951923076923077,0.06382130187094258 +flat_mae,patch,logistic,aabc_age,40,0.046415888336127774,train,0.8326771653543307,0.01609615757479336,0.832595662183182,0.01617454272975199,0.8331537249539211,0.016079484305811798 +flat_mae,patch,logistic,aabc_age,40,0.046415888336127774,test,0.5192307692307693,0.06235822974209617,0.5033866995073891,0.06407948853725826,0.5231227106227107,0.06311348122334488 +flat_mae,patch,logistic,aabc_age,41,0.046415888336127774,train,0.8405511811023622,0.01566058595672287,0.8394643089945043,0.015862467635746315,0.840900699861332,0.015701605406623687 +flat_mae,patch,logistic,aabc_age,41,0.046415888336127774,test,0.4230769230769231,0.05908987988924537,0.39633390541571323,0.05763361659348744,0.41781135531135527,0.05812425124102991 +flat_mae,patch,logistic,aabc_age,42,0.005994842503189409,train,0.6791338582677166,0.019660971113034317,0.6763587348558814,0.020124437165623288,0.6791825537170904,0.019630040693076105 +flat_mae,patch,logistic,aabc_age,42,0.005994842503189409,test,0.5576923076923077,0.05925647544072128,0.5419047619047619,0.06311986211516418,0.5618131868131868,0.05962784701154919 +flat_mae,patch,logistic,aabc_age,43,0.005994842503189409,train,0.6771653543307087,0.020346959477954434,0.6740675875939452,0.020605804500604914,0.67733400589579,0.02038760364717364 +flat_mae,patch,logistic,aabc_age,43,0.005994842503189409,test,0.46153846153846156,0.06828520939768148,0.4561915470836011,0.06903322379463118,0.4597069597069597,0.06824285603419211 +flat_mae,patch,logistic,aabc_age,44,0.005994842503189409,train,0.6850393700787402,0.0194977750224599,0.6817661016604679,0.019728478377261553,0.6849633862624643,0.019510337626618735 +flat_mae,patch,logistic,aabc_age,44,0.005994842503189409,test,0.4807692307692308,0.07059904285520452,0.4794973544973545,0.07214194679024354,0.4791666666666667,0.07070574419497137 +flat_mae,patch,logistic,aabc_age,45,0.005994842503189409,train,0.6614173228346457,0.019032036844143962,0.6590329587895973,0.01937832490298424,0.6608374457458827,0.019100862897588385 +flat_mae,patch,logistic,aabc_age,45,0.005994842503189409,test,0.5,0.06680799123089762,0.5101148851148851,0.06459900655987698,0.5011446886446886,0.0671159141016875 +flat_mae,patch,logistic,aabc_age,46,0.046415888336127774,train,0.8405511811023622,0.016358094316713666,0.8397057618860678,0.016586513418086663,0.8406831319801531,0.016426050735582242 +flat_mae,patch,logistic,aabc_age,46,0.046415888336127774,test,0.46153846153846156,0.06484921062235989,0.46279304792048426,0.06459626157920341,0.46108058608058605,0.0647272730263692 +flat_mae,patch,logistic,aabc_age,47,0.046415888336127774,train,0.8503937007874016,0.015484937651362645,0.850276270845891,0.015600583980946495,0.8514488462549076,0.01540076785637805 +flat_mae,patch,logistic,aabc_age,47,0.046415888336127774,test,0.46153846153846156,0.0662864837579584,0.45673090350509704,0.06887898306394184,0.4597069597069597,0.06638675698306708 +flat_mae,patch,logistic,aabc_age,48,0.046415888336127774,train,0.8523622047244095,0.015128060209967827,0.8512917590754117,0.015375253334656452,0.8523447704113436,0.015135103256950399 +flat_mae,patch,logistic,aabc_age,48,0.046415888336127774,test,0.4423076923076923,0.06753227367833606,0.43952254641909816,0.06868398696895076,0.4432234432234432,0.06763098103652383 +flat_mae,patch,logistic,aabc_age,49,9.999999999999999e-05,train,0.5,0.018189801256136343,0.4727330085886978,0.019090252532837592,0.4964613752879328,0.018105547024653227 +flat_mae,patch,logistic,aabc_age,49,9.999999999999999e-05,test,0.36538461538461536,0.05698295966609397,0.3647683397683398,0.060789155585289065,0.3630952380952381,0.0569382353611538 +flat_mae,patch,logistic,aabc_age,50,0.005994842503189409,train,0.6830708661417323,0.019303854207840834,0.6803820320758609,0.01967482497727111,0.6831648251113852,0.019209576934638217 +flat_mae,patch,logistic,aabc_age,50,0.005994842503189409,test,0.4423076923076923,0.06571494610826242,0.43999333999334,0.06725957070723902,0.4391025641025641,0.06562424443485564 +flat_mae,patch,logistic,aabc_age,51,0.005994842503189409,train,0.6673228346456693,0.020815843031178016,0.663835125120792,0.02120907009543154,0.6685587680215731,0.020666142554800034 +flat_mae,patch,logistic,aabc_age,51,0.005994842503189409,test,0.4807692307692308,0.07079268006154207,0.4816632902186899,0.07135231700497639,0.47916666666666663,0.0708093119076851 +flat_mae,patch,logistic,aabc_age,52,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,52,21.54434690031882,test,0.38461538461538464,0.06523494181139503,0.390625,0.0640326532274451,0.3825549450549451,0.06504597522578551 +flat_mae,patch,logistic,aabc_age,53,9.999999999999999e-05,train,0.48031496062992124,0.020078043835386167,0.45964145272580137,0.02038723972368776,0.47770546559286825,0.01995525093047129 +flat_mae,patch,logistic,aabc_age,53,9.999999999999999e-05,test,0.5576923076923077,0.05627621019862235,0.5101851851851851,0.055961476940857346,0.5483058608058609,0.05531616138484628 +flat_mae,patch,logistic,aabc_age,54,0.3593813663804626,train,0.9940944881889764,0.003271108665315746,0.9942222870058268,0.0032033585919524466,0.9943367619953625,0.0031524001976342537 +flat_mae,patch,logistic,aabc_age,54,0.3593813663804626,test,0.46153846153846156,0.0637646722876599,0.4496579091406678,0.06499604214308828,0.46703296703296704,0.06407377658640724 +flat_mae,patch,logistic,aabc_age,55,0.005994842503189409,train,0.6673228346456693,0.019964667081518374,0.6629119071858949,0.02044340737770811,0.6670534140536145,0.019922710438159855 +flat_mae,patch,logistic,aabc_age,55,0.005994842503189409,test,0.6153846153846154,0.0611417501341551,0.6017349748065035,0.06414419053821253,0.6211080586080586,0.0614796734625691 +flat_mae,patch,logistic,aabc_age,56,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,56,21.54434690031882,test,0.46153846153846156,0.06933772720677527,0.46784511784511784,0.0684273188974537,0.4626831501831502,0.06941555762223556 +flat_mae,patch,logistic,aabc_age,57,0.005994842503189409,train,0.6830708661417323,0.020442984562710882,0.6795736431184218,0.020922029221609274,0.6820269990352692,0.020421148243025725 +flat_mae,patch,logistic,aabc_age,57,0.005994842503189409,test,0.46153846153846156,0.059974402823895136,0.4484126984126984,0.05949439135136193,0.46222527472527475,0.059979212883864146 +flat_mae,patch,logistic,aabc_age,58,0.005994842503189409,train,0.6830708661417323,0.019291449059622587,0.682090939933354,0.01953117574820854,0.6837322996841131,0.019287826915271252 +flat_mae,patch,logistic,aabc_age,58,0.005994842503189409,test,0.5,0.06211265771580467,0.4796329057938965,0.06608391691061037,0.4951923076923077,0.06161610914507229 +flat_mae,patch,logistic,aabc_age,59,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,59,166.81005372000556,test,0.46153846153846156,0.06865541907269475,0.46673330001665836,0.06798725072068017,0.46130952380952384,0.06878683606961011 +flat_mae,patch,logistic,aabc_age,60,0.046415888336127774,train,0.8543307086614174,0.015297544902034454,0.8532429941976318,0.01570764942906422,0.8540433582219801,0.015393094412160017 +flat_mae,patch,logistic,aabc_age,60,0.046415888336127774,test,0.4230769230769231,0.06387876831483304,0.4173534798534799,0.06526738570520524,0.4269688644688645,0.06440841799967018 +flat_mae,patch,logistic,aabc_age,61,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,61,2.782559402207126,test,0.40384615384615385,0.06467116411087419,0.4034136777764964,0.06349756046936854,0.40315934065934067,0.0647135491298074 +flat_mae,patch,logistic,aabc_age,62,0.005994842503189409,train,0.6692913385826772,0.020643769394915013,0.6675233179326541,0.02087730096003037,0.669319476436979,0.02067228072258206 +flat_mae,patch,logistic,aabc_age,62,0.005994842503189409,test,0.5576923076923077,0.06551272517429964,0.5497286079182631,0.06700529538790218,0.5531135531135531,0.06559256999435395 +flat_mae,patch,logistic,aabc_age,63,0.005994842503189409,train,0.6850393700787402,0.01931694066844937,0.6837392075851475,0.019542953074612037,0.6858660232571074,0.01933836317619989 +flat_mae,patch,logistic,aabc_age,63,0.005994842503189409,test,0.4230769230769231,0.057609376291419705,0.4080128205128205,0.0542102889683337,0.4191849816849817,0.05707597680929449 +flat_mae,patch,logistic,aabc_age,64,0.046415888336127774,train,0.8582677165354331,0.01567339399461899,0.8581693425652885,0.01582909944031641,0.857940400545466,0.01577993876860998 +flat_mae,patch,logistic,aabc_age,64,0.046415888336127774,test,0.34615384615384615,0.06434203858282767,0.35672392124005026,0.06435991612450276,0.3456959706959707,0.06462592714727507 +flat_mae,patch,logistic,aabc_age,65,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,65,21.54434690031882,test,0.4423076923076923,0.06564094551277161,0.4391025641025641,0.06563418299951708,0.44184981684981683,0.0658941730324761 +flat_mae,patch,logistic,aabc_age,66,0.046415888336127774,train,0.8405511811023622,0.01569691457854871,0.8404583464958861,0.01579643874210284,0.8405155507691954,0.015744941220547735 +flat_mae,patch,logistic,aabc_age,66,0.046415888336127774,test,0.4423076923076923,0.06465479567325455,0.43496133496133493,0.06517649831991498,0.43887362637362637,0.06454443673928736 +flat_mae,patch,logistic,aabc_age,67,0.005994842503189409,train,0.6811023622047244,0.0200347406592066,0.6792230777106136,0.020320195604305726,0.6810311015383907,0.020041987922347522 +flat_mae,patch,logistic,aabc_age,67,0.005994842503189409,test,0.5192307692307693,0.05145659399036004,0.4673423423423423,0.06081158263425813,0.5183150183150182,0.051204718761735046 +flat_mae,patch,logistic,aabc_age,68,0.3593813663804626,train,0.9960629921259843,0.002701863264513986,0.9960426157427643,0.002731080400209666,0.9959677419354839,0.0027672309241393413 +flat_mae,patch,logistic,aabc_age,68,0.3593813663804626,test,0.46153846153846156,0.0668442838545202,0.4529651383099659,0.06769088712565953,0.459478021978022,0.06680006744817896 +flat_mae,patch,logistic,aabc_age,69,0.005994842503189409,train,0.6830708661417323,0.018950812654516962,0.6801994109565972,0.019330815838322513,0.6840850833063221,0.01893480026898858 +flat_mae,patch,logistic,aabc_age,69,0.005994842503189409,test,0.4423076923076923,0.06724088992649123,0.44334609990290214,0.06828401660273148,0.44047619047619047,0.06738926447336738 +flat_mae,patch,logistic,aabc_age,70,0.046415888336127774,train,0.8484251968503937,0.01559078779745683,0.8480937339837316,0.015725655930878636,0.8485800668982275,0.015560613661499917 +flat_mae,patch,logistic,aabc_age,70,0.046415888336127774,test,0.5576923076923077,0.0690564471965383,0.5577777777777778,0.07017927580840069,0.5608974358974359,0.06905965009658767 +flat_mae,patch,logistic,aabc_age,71,0.005994842503189409,train,0.6791338582677166,0.020292263995226257,0.6768741954567594,0.020610553505238494,0.679835257360627,0.02029903803181455 +flat_mae,patch,logistic,aabc_age,71,0.005994842503189409,test,0.5,0.06915504405568111,0.5033380084151473,0.06988477476381036,0.5,0.06946991444190484 +flat_mae,patch,logistic,aabc_age,72,0.046415888336127774,train,0.8366141732283464,0.015451617892796575,0.8364698826617526,0.015629554402216184,0.837135996348216,0.015435967271782864 +flat_mae,patch,logistic,aabc_age,72,0.046415888336127774,test,0.5576923076923077,0.06352489844063894,0.5554112554112554,0.06526173093794888,0.55746336996337,0.06357928466031043 +flat_mae,patch,logistic,aabc_age,73,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,73,21.54434690031882,test,0.40384615384615385,0.06322415977059896,0.40346880131362894,0.06336699806506582,0.4036172161172161,0.06330462368224175 +flat_mae,patch,logistic,aabc_age,74,0.046415888336127774,train,0.8405511811023622,0.015474732354218066,0.8401227226505434,0.01565454596379071,0.8405155507691954,0.01550268995402488 +flat_mae,patch,logistic,aabc_age,74,0.046415888336127774,test,0.4230769230769231,0.0677676481959632,0.43683418031244114,0.06737536840090773,0.4212454212454212,0.06765627252395247 +flat_mae,patch,logistic,aabc_age,75,0.005994842503189409,train,0.6811023622047244,0.02009121273874871,0.6790547076840081,0.020335060551214194,0.6816838051819274,0.020075392569178476 +flat_mae,patch,logistic,aabc_age,75,0.005994842503189409,test,0.5384615384615384,0.06705839546519782,0.5375107886503399,0.06676019581178463,0.5341117216117217,0.06704428098139308 +flat_mae,patch,logistic,aabc_age,76,0.046415888336127774,train,0.8503937007874016,0.016168167330259484,0.8499066732399495,0.016327980897253618,0.8512988862442438,0.01616089364999327 +flat_mae,patch,logistic,aabc_age,76,0.046415888336127774,test,0.5192307692307693,0.06457566315717825,0.5155960729312763,0.06639598498945963,0.5233516483516484,0.06518953330290685 +flat_mae,patch,logistic,aabc_age,77,0.3593813663804626,train,0.9881889763779528,0.004850297831141714,0.9880041667935557,0.004939579794695792,0.9880208203471881,0.004939651337028071 +flat_mae,patch,logistic,aabc_age,77,0.3593813663804626,test,0.46153846153846156,0.06745345754600904,0.45999589490968806,0.06877927800846542,0.46130952380952384,0.06766802171925676 +flat_mae,patch,logistic,aabc_age,78,0.046415888336127774,train,0.8385826771653543,0.016330944044955494,0.8375320241923976,0.016554541654053602,0.8387845974886313,0.01628073488864235 +flat_mae,patch,logistic,aabc_age,78,0.046415888336127774,test,0.5769230769230769,0.06489330113767043,0.583896993810787,0.06362861143040752,0.5798992673992673,0.06512085823986961 +flat_mae,patch,logistic,aabc_age,79,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,79,21.54434690031882,test,0.36538461538461536,0.05963740288179229,0.35507468487978233,0.05727276956121866,0.3644688644688645,0.05937785961980687 +flat_mae,patch,logistic,aabc_age,80,0.046415888336127774,train,0.8503937007874016,0.016059809395972173,0.8502961339353106,0.01609443846617245,0.8510137104925498,0.015993938467961558 +flat_mae,patch,logistic,aabc_age,80,0.046415888336127774,test,0.5,0.06003907751125401,0.482736013986014,0.06204844884553497,0.5022893772893773,0.060253199439252 +flat_mae,patch,logistic,aabc_age,81,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,81,166.81005372000556,test,0.40384615384615385,0.06642630609940488,0.40758921614461585,0.0654087705118412,0.40613553113553114,0.06687725861034624 +flat_mae,patch,logistic,aabc_age,82,0.005994842503189409,train,0.6712598425196851,0.0202137881579496,0.6699308567746445,0.020438128975081377,0.6718207279018161,0.02020509657017279 +flat_mae,patch,logistic,aabc_age,82,0.005994842503189409,test,0.4807692307692308,0.06939804577505371,0.48068965517241385,0.0691324646657347,0.4789377289377289,0.06972541523137961 +flat_mae,patch,logistic,aabc_age,83,0.005994842503189409,train,0.6732283464566929,0.0207122897333417,0.668262584669362,0.021085224081704965,0.672013961744494,0.020721257387658527 +flat_mae,patch,logistic,aabc_age,83,0.005994842503189409,test,0.5192307692307693,0.06490105122187267,0.5047619047619047,0.06682249250408638,0.5157967032967034,0.06465802278192988 +flat_mae,patch,logistic,aabc_age,84,0.046415888336127774,train,0.8562992125984252,0.015955258604627955,0.8559859505478172,0.016166117550726958,0.8565269884865235,0.015922582722593778 +flat_mae,patch,logistic,aabc_age,84,0.046415888336127774,test,0.5961538461538461,0.05929879959270756,0.586726222142385,0.061188177018927384,0.5902014652014652,0.05926553270749994 +flat_mae,patch,logistic,aabc_age,85,0.046415888336127774,train,0.8464566929133859,0.016633960303465655,0.8466919302074192,0.016682277015636855,0.8466639112064122,0.01669176913977957 +flat_mae,patch,logistic,aabc_age,85,0.046415888336127774,test,0.46153846153846156,0.06708445397032789,0.45486943164362514,0.06630108184063135,0.4581043956043956,0.06668322991893998 +flat_mae,patch,logistic,aabc_age,86,0.3593813663804626,train,0.9960629921259843,0.0027416278071696817,0.995942918634392,0.002824831689693298,0.995967741935484,0.0028079575121818636 +flat_mae,patch,logistic,aabc_age,86,0.3593813663804626,test,0.5961538461538461,0.05923081918079812,0.5654029710291053,0.059502187048100334,0.586996336996337,0.05889641946402417 +flat_mae,patch,logistic,aabc_age,87,0.005994842503189409,train,0.6732283464566929,0.01868305168094442,0.6690377753808097,0.019242653713894328,0.6723991108366306,0.018674053013009315 +flat_mae,patch,logistic,aabc_age,87,0.005994842503189409,test,0.5576923076923077,0.06529400962039084,0.5442409442409442,0.06732034269132693,0.5572344322344323,0.06554359318397608 +flat_mae,patch,logistic,aabc_age,88,0.046415888336127774,train,0.8346456692913385,0.016037274359701467,0.8333495597387073,0.016249420819638455,0.834484784872715,0.016013746871511123 +flat_mae,patch,logistic,aabc_age,88,0.046415888336127774,test,0.5192307692307693,0.06649797567769089,0.5233333333333333,0.06628526408024485,0.5176282051282051,0.06667213726617272 +flat_mae,patch,logistic,aabc_age,89,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,89,2.782559402207126,test,0.4230769230769231,0.06363415916799524,0.4152573875399962,0.06484763475545981,0.41689560439560436,0.06346888233748671 +flat_mae,patch,logistic,aabc_age,90,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,90,21.54434690031882,test,0.5961538461538461,0.06339040302180034,0.5899962106858658,0.06459962036946569,0.5989010989010989,0.06356744227848057 +flat_mae,patch,logistic,aabc_age,91,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,91,2.782559402207126,test,0.5576923076923077,0.06361291968064237,0.5519574628270281,0.06487953073422123,0.5531135531135531,0.06350219426065606 +flat_mae,patch,logistic,aabc_age,92,0.3593813663804626,train,0.9921259842519685,0.003870403139214424,0.992094869835221,0.0038948946964655375,0.9921030650819254,0.0038836230798507945 +flat_mae,patch,logistic,aabc_age,92,0.3593813663804626,test,0.5961538461538461,0.06096942438681189,0.5754105090311987,0.06258348876059311,0.5885989010989011,0.060793983735665934 +flat_mae,patch,logistic,aabc_age,93,0.046415888336127774,train,0.8484251968503937,0.015308339661456656,0.8483965110548473,0.015386992514470859,0.849115176001028,0.01526887663133486 +flat_mae,patch,logistic,aabc_age,93,0.046415888336127774,test,0.5,0.066650406054419,0.5046620046620047,0.06620664901065994,0.5011446886446886,0.06698663875223354 +flat_mae,patch,logistic,aabc_age,94,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,94,166.81005372000556,test,0.4807692307692308,0.06406564449635802,0.4741666666666666,0.06465224372171517,0.4807692307692308,0.06437524172795656 +flat_mae,patch,logistic,aabc_age,95,0.005994842503189409,train,0.6811023622047244,0.01967510615523088,0.678844212687474,0.02007931965088453,0.6819013730631065,0.019619429303264976 +flat_mae,patch,logistic,aabc_age,95,0.005994842503189409,test,0.5,0.06083096912538651,0.4739389920424404,0.05590383224524485,0.49198717948717946,0.059801337554711335 +flat_mae,patch,logistic,aabc_age,96,0.046415888336127774,train,0.8307086614173228,0.0168005093528211,0.8301709493664604,0.01696146963206685,0.830434905607905,0.016858376271999428 +flat_mae,patch,logistic,aabc_age,96,0.046415888336127774,test,0.4423076923076923,0.06700441564536125,0.4462068965517242,0.06682540442155173,0.44345238095238093,0.06724054310827016 +flat_mae,patch,logistic,aabc_age,97,0.3593813663804626,train,0.9960629921259843,0.0026941189685227352,0.9960426157427643,0.002717847444637552,0.9959677419354839,0.002759299266148303 +flat_mae,patch,logistic,aabc_age,97,0.3593813663804626,test,0.5,0.0639886731840721,0.49880341880341883,0.06342271522642204,0.4981684981684982,0.06410965130235767 +flat_mae,patch,logistic,aabc_age,98,0.046415888336127774,train,0.8405511811023622,0.015210315930559166,0.8395405592402317,0.015449565495721922,0.8410182944020683,0.015172613800195385 +flat_mae,patch,logistic,aabc_age,98,0.046415888336127774,test,0.5,0.06847315156473448,0.4906400966183575,0.0707904419481997,0.5011446886446886,0.06888138941663191 +flat_mae,patch,logistic,aabc_age,99,0.3593813663804626,train,0.9960629921259843,0.0027888108675441013,0.9959265281741554,0.002879991632985227,0.995967741935484,0.0028562820982105026 +flat_mae,patch,logistic,aabc_age,99,0.3593813663804626,test,0.4423076923076923,0.06304342450074445,0.41947997775305895,0.06394576552446031,0.4429945054945055,0.06340970117498167 +flat_mae,patch,logistic,aabc_age,100,0.3593813663804626,train,0.9921259842519685,0.003845332244834,0.992087017966999,0.003874103385841371,0.9921530517521466,0.00382348271509725 +flat_mae,patch,logistic,aabc_age,100,0.3593813663804626,test,0.4230769230769231,0.06849544320350787,0.42124223602484473,0.06893922153896247,0.4244505494505495,0.06828296825955621 diff --git a/input_space_v3/flat_lr1e-3_5/eval_v2/aabc_age__patch__logistic/log.txt b/input_space_v3/flat_lr1e-3_5/eval_v2/aabc_age__patch__logistic/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..be821be3d53bbeda6890aeb91cdec002a6e83060 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_5/eval_v2/aabc_age__patch__logistic/log.txt @@ -0,0 +1,245 @@ +fMRI foundation model logistic probe eval +version: 0.1.dev86+gf97f52698 +sha: bcce2b486277d3a5b520775efd9cdf1a2affce36, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-04-08 22:30:56 +config: +output_root: experiments/input_space_v3/output +name_prefix: eval_logistic +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_5; eval v2 (aabc_age patch logistic) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: input_space_v3/flat_lr1e-3_5/eval_v2/aabc_age__patch__logistic +model: flat_mae +representation: patch +dataset: aabc_age +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/eval_v2/aabc_age__patch__logistic +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=True, reg_tokens=0, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: aabc_age (flat) +train (n=455): +HFDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'segment', 'bold', 'mean', 'std'], + num_rows: 471 +}), + labels=[0 1 2 3], + counts=[110 127 109 109] +) + +validation (n=53): +HFDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'segment', 'bold', 'mean', 'std'], + num_rows: 58 +}), + labels=[0 1 2 3], + counts=[14 13 12 14] +) + +test (n=52): +HFDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'segment', 'bold', 'mean', 'std'], + num_rows: 55 +}), + labels=[0 1 2 3], + counts=[13 13 12 14] +) + +extracting features for all splits +extract (train) [ 0/228] eta: 0:23:40 time: 6.2323 data: 5.0395 max mem: 3205 +extract (train) [ 20/228] eta: 0:01:57 time: 0.2835 data: 0.1083 max mem: 3393 +extract (train) [ 40/228] eta: 0:01:14 time: 0.2151 data: 0.0711 max mem: 3393 +extract (train) [ 60/228] eta: 0:00:57 time: 0.2401 data: 0.0861 max mem: 3393 +extract (train) [ 80/228] eta: 0:00:46 time: 0.2318 data: 0.0801 max mem: 3393 +extract (train) [100/228] eta: 0:00:38 time: 0.2226 data: 0.0770 max mem: 3393 +extract (train) [120/228] eta: 0:00:31 time: 0.2448 data: 0.0898 max mem: 3393 +extract (train) [140/228] eta: 0:00:24 time: 0.2385 data: 0.0853 max mem: 3393 +extract (train) [160/228] eta: 0:00:18 time: 0.2397 data: 0.0905 max mem: 3393 +extract (train) [180/228] eta: 0:00:13 time: 0.2685 data: 0.1032 max mem: 3393 +extract (train) [200/228] eta: 0:00:07 time: 0.2385 data: 0.0849 max mem: 3393 +extract (train) [220/228] eta: 0:00:02 time: 0.2116 data: 0.0729 max mem: 3393 +extract (train) [227/228] eta: 0:00:00 time: 0.2070 data: 0.0723 max mem: 3393 +extract (train) Total time: 0:01:00 (0.2673 s / it) +extract (validation) [ 0/27] eta: 0:02:47 time: 6.2199 data: 6.0216 max mem: 3393 +extract (validation) [20/27] eta: 0:00:03 time: 0.2464 data: 0.0881 max mem: 3393 +extract (validation) [26/27] eta: 0:00:00 time: 0.2075 data: 0.0711 max mem: 3393 +extract (validation) Total time: 0:00:12 (0.4771 s / it) +extract (test) [ 0/26] eta: 0:02:25 time: 5.5996 data: 5.4448 max mem: 3393 +extract (test) [20/26] eta: 0:00:02 time: 0.1955 data: 0.0583 max mem: 3393 +extract (test) [25/26] eta: 0:00:00 time: 0.1919 data: 0.0570 max mem: 3393 +extract (test) Total time: 0:00:10 (0.4181 s / it) +feature extraction time: 0:01:24 +train features: (455, 768) +validation features: (53, 768) +test features: (52, 768) +evaluating fixed splits +eval results (fixed splits): + +| model | repr | clf | dataset | trial | C | split | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|---------:|:--------|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | aabc_age | | 0.046416 | train | 0.83858 | 0.01593 | 0.8372 | 0.016186 | 0.83815 | 0.015891 | +| flat_mae | patch | logistic | aabc_age | | 0.046416 | test | 0.44231 | 0.05658 | 0.41479 | 0.059913 | 0.43361 | 0.056969 | + + +evaluating random splits (n=100) +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 1, "C": 0.005994842503189409, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.06108596861907142, "f1": 0.4624668435013263, "f1_std": 0.060999558786876705, "bacc": 0.47573260073260076, "bacc_std": 0.06043942970036643} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 2, "C": 0.000774263682681127, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.06848422268958339, "f1": 0.5348193473193474, "f1_std": 0.06850206841790545, "bacc": 0.5338827838827839, "bacc_std": 0.06834725888185308} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 3, "C": 0.046415888336127774, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.06739317648461444, "f1": 0.6097204968944099, "f1_std": 0.06911569507471783, "bacc": 0.6153846153846154, "bacc_std": 0.06771919362274331} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 4, "C": 0.3593813663804626, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.06359862815311805, "f1": 0.49911083540115797, "f1_std": 0.06641471687302049, "bacc": 0.5231227106227107, "bacc_std": 0.06411502368446155} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 5, "C": 2.782559402207126, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.0661985537660005, "f1": 0.41917060395321265, "f1_std": 0.06611319931423, "bacc": 0.423992673992674, "bacc_std": 0.06649557939837873} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 6, "C": 0.005994842503189409, "split": "test", "acc": 0.5769230769230769, "acc_std": 0.06526245375269371, "f1": 0.5721548566376153, "f1_std": 0.06737457817979146, "bacc": 0.5753205128205129, "bacc_std": 0.0653205978737284} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 7, "C": 0.046415888336127774, "split": "test", "acc": 0.5576923076923077, "acc_std": 0.06228559674700224, "f1": 0.5589173789173789, "f1_std": 0.0610961065162261, "bacc": 0.5531135531135531, "bacc_std": 0.06245921544284178} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 8, "C": 0.3593813663804626, "split": "test", "acc": 0.5, "acc_std": 0.06004066669187421, "f1": 0.4973789173789174, "f1_std": 0.059319469221224864, "bacc": 0.502518315018315, "bacc_std": 0.060470497027108716} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 9, "C": 0.005994842503189409, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.06634519508783288, "f1": 0.4349924585218703, "f1_std": 0.0655235648666099, "bacc": 0.4358974358974359, "bacc_std": 0.06599008401231207} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 10, "C": 0.000774263682681127, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.06606595234439293, "f1": 0.4790247252747253, "f1_std": 0.06545348765682724, "bacc": 0.47733516483516486, "bacc_std": 0.06589522136650743} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 11, "C": 0.046415888336127774, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.06638308893868543, "f1": 0.6219405594405594, "f1_std": 0.06624105679372524, "bacc": 0.614010989010989, "bacc_std": 0.06662837471994132} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 12, "C": 0.046415888336127774, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.0628732170333151, "f1": 0.4472723955482576, "f1_std": 0.0627343293601991, "bacc": 0.44482600732600736, "bacc_std": 0.06318377623660765} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 13, "C": 0.046415888336127774, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.0653877261703434, "f1": 0.48484330484330485, "f1_std": 0.06334683782838717, "bacc": 0.4832875457875458, "bacc_std": 0.06597123306805289} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 14, "C": 0.046415888336127774, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.06682061121271068, "f1": 0.5341414141414141, "f1_std": 0.06898052146755347, "bacc": 0.5398351648351648, "bacc_std": 0.06675100394866842} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 15, "C": 0.046415888336127774, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.06706981040271115, "f1": 0.47472514713894026, "f1_std": 0.06488882117740079, "bacc": 0.46565934065934067, "bacc_std": 0.06731322626044223} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 16, "C": 0.046415888336127774, "split": "test", "acc": 0.5, "acc_std": 0.06506637484979991, "f1": 0.49522546419098146, "f1_std": 0.06637158094597087, "bacc": 0.5059523809523809, "bacc_std": 0.0651028661581655} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 17, "C": 9.999999999999999e-05, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.05577453555672201, "f1": 0.4031010536398468, "f1_std": 0.055272018404423785, "bacc": 0.4356684981684982, "bacc_std": 0.054694384590792684} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 18, "C": 0.046415888336127774, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.06968376369770021, "f1": 0.4903846153846153, "f1_std": 0.0689060910831291, "bacc": 0.4835164835164835, "bacc_std": 0.07005196015062341} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 19, "C": 0.005994842503189409, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.06744284233518424, "f1": 0.43100168665667166, "f1_std": 0.06925262705466918, "bacc": 0.4375, "bacc_std": 0.06745522642845192} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 20, "C": 0.046415888336127774, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.05526069202281344, "f1": 0.43981481481481477, "f1_std": 0.050789745059337435, "bacc": 0.4576465201465202, "bacc_std": 0.05461054752737594} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 21, "C": 0.046415888336127774, "split": "test", "acc": 0.3269230769230769, "acc_std": 0.06457182597742742, "f1": 0.3296182266009852, "f1_std": 0.06390856635783718, "bacc": 0.3289835164835165, "bacc_std": 0.06511282149492238} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 22, "C": 0.046415888336127774, "split": "test", "acc": 0.36538461538461536, "acc_std": 0.06307611397229662, "f1": 0.3932843137254902, "f1_std": 0.06142410940253011, "bacc": 0.3708791208791209, "bacc_std": 0.063529559035273} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 23, "C": 0.046415888336127774, "split": "test", "acc": 0.5576923076923077, "acc_std": 0.05811257184049902, "f1": 0.5379889886989279, "f1_std": 0.06367476817829491, "bacc": 0.5542582417582418, "bacc_std": 0.05823759397477178} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 24, "C": 0.046415888336127774, "split": "test", "acc": 0.40384615384615385, "acc_std": 0.06316217269198075, "f1": 0.3958333333333333, "f1_std": 0.06268832562009978, "bacc": 0.40315934065934067, "bacc_std": 0.06301428727425992} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 25, "C": 2.782559402207126, "split": "test", "acc": 0.5, "acc_std": 0.06591875715135032, "f1": 0.49755852842809367, "f1_std": 0.066128229702766, "bacc": 0.4981684981684981, "bacc_std": 0.06600399079456545} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 26, "C": 0.046415888336127774, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.06620100063599568, "f1": 0.4881543187994801, "f1_std": 0.0656381025921867, "bacc": 0.48511904761904767, "bacc_std": 0.06634358561597829} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 27, "C": 0.046415888336127774, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.06081024662566791, "f1": 0.3958855472013367, "f1_std": 0.061836487427333574, "bacc": 0.41689560439560436, "bacc_std": 0.06026962887307377} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 28, "C": 0.005994842503189409, "split": "test", "acc": 0.5769230769230769, "acc_std": 0.06451040006058195, "f1": 0.5679759552042161, "f1_std": 0.06830412257905911, "bacc": 0.5766941391941391, "bacc_std": 0.06472567254060557} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 29, "C": 9.999999999999999e-05, "split": "test", "acc": 0.3076923076923077, "acc_std": 0.06053278000902736, "f1": 0.2954032258064516, "f1_std": 0.05621134351834604, "bacc": 0.30654761904761907, "bacc_std": 0.06013266721036993} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 30, "C": 0.046415888336127774, "split": "test", "acc": 0.5961538461538461, "acc_std": 0.06828200313891444, "f1": 0.5960989010989011, "f1_std": 0.06825507303452724, "bacc": 0.5975274725274725, "bacc_std": 0.0682867252341207} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 31, "C": 0.3593813663804626, "split": "test", "acc": 0.5769230769230769, "acc_std": 0.06411800326893582, "f1": 0.5719372456628828, "f1_std": 0.0656868775861503, "bacc": 0.5755494505494505, "bacc_std": 0.06415723109036968} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 32, "C": 0.005994842503189409, "split": "test", "acc": 0.5, "acc_std": 0.06279226340239111, "f1": 0.48344827586206895, "f1_std": 0.061943808010026816, "bacc": 0.49496336996337, "bacc_std": 0.062212320917483944} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 33, "C": 9.999999999999999e-05, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.05377273841315601, "f1": 0.4180778371954843, "f1_std": 0.047136054925837466, "bacc": 0.47115384615384615, "bacc_std": 0.052351754674950395} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 34, "C": 0.005994842503189409, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.06512503904074969, "f1": 0.5174485125858124, "f1_std": 0.06883933053379125, "bacc": 0.5135073260073261, "bacc_std": 0.06559486519703017} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 35, "C": 0.000774263682681127, "split": "test", "acc": 0.40384615384615385, "acc_std": 0.06485445699191364, "f1": 0.3915057566336766, "f1_std": 0.06494547042953264, "bacc": 0.4001831501831502, "bacc_std": 0.06428858449417393} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 36, "C": 0.046415888336127774, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.06469613772619189, "f1": 0.46615804744836997, "f1_std": 0.06656764661501756, "bacc": 0.48168498168498164, "bacc_std": 0.06490070438190533} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 37, "C": 0.046415888336127774, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.058554720778463173, "f1": 0.4444305694305694, "f1_std": 0.05388930479162662, "bacc": 0.453525641025641, "bacc_std": 0.057671494159695705} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 38, "C": 2.782559402207126, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.06506578373475379, "f1": 0.4439039855072464, "f1_std": 0.06444285310614131, "bacc": 0.4391025641025641, "bacc_std": 0.06521060883965044} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 39, "C": 0.005994842503189409, "split": "test", "acc": 0.5, "acc_std": 0.06427956460676677, "f1": 0.48856460146782726, "f1_std": 0.06510501843973844, "bacc": 0.4951923076923077, "bacc_std": 0.06382130187094258} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 40, "C": 0.046415888336127774, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.06235822974209617, "f1": 0.5033866995073891, "f1_std": 0.06407948853725826, "bacc": 0.5231227106227107, "bacc_std": 0.06311348122334488} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 41, "C": 0.046415888336127774, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.05908987988924537, "f1": 0.39633390541571323, "f1_std": 0.05763361659348744, "bacc": 0.41781135531135527, "bacc_std": 0.05812425124102991} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 42, "C": 0.005994842503189409, "split": "test", "acc": 0.5576923076923077, "acc_std": 0.05925647544072128, "f1": 0.5419047619047619, "f1_std": 0.06311986211516418, "bacc": 0.5618131868131868, "bacc_std": 0.05962784701154919} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 43, "C": 0.005994842503189409, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.06828520939768148, "f1": 0.4561915470836011, "f1_std": 0.06903322379463118, "bacc": 0.4597069597069597, "bacc_std": 0.06824285603419211} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 44, "C": 0.005994842503189409, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.07059904285520452, "f1": 0.4794973544973545, "f1_std": 0.07214194679024354, "bacc": 0.4791666666666667, "bacc_std": 0.07070574419497137} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 45, "C": 0.005994842503189409, "split": "test", "acc": 0.5, "acc_std": 0.06680799123089762, "f1": 0.5101148851148851, "f1_std": 0.06459900655987698, "bacc": 0.5011446886446886, "bacc_std": 0.0671159141016875} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 46, "C": 0.046415888336127774, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.06484921062235989, "f1": 0.46279304792048426, "f1_std": 0.06459626157920341, "bacc": 0.46108058608058605, "bacc_std": 0.0647272730263692} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 47, "C": 0.046415888336127774, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.0662864837579584, "f1": 0.45673090350509704, "f1_std": 0.06887898306394184, "bacc": 0.4597069597069597, "bacc_std": 0.06638675698306708} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 48, "C": 0.046415888336127774, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.06753227367833606, "f1": 0.43952254641909816, "f1_std": 0.06868398696895076, "bacc": 0.4432234432234432, "bacc_std": 0.06763098103652383} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 49, "C": 9.999999999999999e-05, "split": "test", "acc": 0.36538461538461536, "acc_std": 0.05698295966609397, "f1": 0.3647683397683398, "f1_std": 0.060789155585289065, "bacc": 0.3630952380952381, "bacc_std": 0.0569382353611538} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 50, "C": 0.005994842503189409, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.06571494610826242, "f1": 0.43999333999334, "f1_std": 0.06725957070723902, "bacc": 0.4391025641025641, "bacc_std": 0.06562424443485564} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 51, "C": 0.005994842503189409, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.07079268006154207, "f1": 0.4816632902186899, "f1_std": 0.07135231700497639, "bacc": 0.47916666666666663, "bacc_std": 0.0708093119076851} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 52, "C": 21.54434690031882, "split": "test", "acc": 0.38461538461538464, "acc_std": 0.06523494181139503, "f1": 0.390625, "f1_std": 0.0640326532274451, "bacc": 0.3825549450549451, "bacc_std": 0.06504597522578551} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 53, "C": 9.999999999999999e-05, "split": "test", "acc": 0.5576923076923077, "acc_std": 0.05627621019862235, "f1": 0.5101851851851851, "f1_std": 0.055961476940857346, "bacc": 0.5483058608058609, "bacc_std": 0.05531616138484628} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 54, "C": 0.3593813663804626, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.0637646722876599, "f1": 0.4496579091406678, "f1_std": 0.06499604214308828, "bacc": 0.46703296703296704, "bacc_std": 0.06407377658640724} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 55, "C": 0.005994842503189409, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.0611417501341551, "f1": 0.6017349748065035, "f1_std": 0.06414419053821253, "bacc": 0.6211080586080586, "bacc_std": 0.0614796734625691} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 56, "C": 21.54434690031882, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.06933772720677527, "f1": 0.46784511784511784, "f1_std": 0.0684273188974537, "bacc": 0.4626831501831502, "bacc_std": 0.06941555762223556} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 57, "C": 0.005994842503189409, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.059974402823895136, "f1": 0.4484126984126984, "f1_std": 0.05949439135136193, "bacc": 0.46222527472527475, "bacc_std": 0.059979212883864146} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 58, "C": 0.005994842503189409, "split": "test", "acc": 0.5, "acc_std": 0.06211265771580467, "f1": 0.4796329057938965, "f1_std": 0.06608391691061037, "bacc": 0.4951923076923077, "bacc_std": 0.06161610914507229} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 59, "C": 166.81005372000556, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.06865541907269475, "f1": 0.46673330001665836, "f1_std": 0.06798725072068017, "bacc": 0.46130952380952384, "bacc_std": 0.06878683606961011} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 60, "C": 0.046415888336127774, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.06387876831483304, "f1": 0.4173534798534799, "f1_std": 0.06526738570520524, "bacc": 0.4269688644688645, "bacc_std": 0.06440841799967018} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 61, "C": 2.782559402207126, "split": "test", "acc": 0.40384615384615385, "acc_std": 0.06467116411087419, "f1": 0.4034136777764964, "f1_std": 0.06349756046936854, "bacc": 0.40315934065934067, "bacc_std": 0.0647135491298074} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 62, "C": 0.005994842503189409, "split": "test", "acc": 0.5576923076923077, "acc_std": 0.06551272517429964, "f1": 0.5497286079182631, "f1_std": 0.06700529538790218, "bacc": 0.5531135531135531, "bacc_std": 0.06559256999435395} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 63, "C": 0.005994842503189409, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.057609376291419705, "f1": 0.4080128205128205, "f1_std": 0.0542102889683337, "bacc": 0.4191849816849817, "bacc_std": 0.05707597680929449} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 64, "C": 0.046415888336127774, "split": "test", "acc": 0.34615384615384615, "acc_std": 0.06434203858282767, "f1": 0.35672392124005026, "f1_std": 0.06435991612450276, "bacc": 0.3456959706959707, "bacc_std": 0.06462592714727507} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 65, "C": 21.54434690031882, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.06564094551277161, "f1": 0.4391025641025641, "f1_std": 0.06563418299951708, "bacc": 0.44184981684981683, "bacc_std": 0.0658941730324761} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 66, "C": 0.046415888336127774, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.06465479567325455, "f1": 0.43496133496133493, "f1_std": 0.06517649831991498, "bacc": 0.43887362637362637, "bacc_std": 0.06454443673928736} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 67, "C": 0.005994842503189409, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.05145659399036004, "f1": 0.4673423423423423, "f1_std": 0.06081158263425813, "bacc": 0.5183150183150182, "bacc_std": 0.051204718761735046} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 68, "C": 0.3593813663804626, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.0668442838545202, "f1": 0.4529651383099659, "f1_std": 0.06769088712565953, "bacc": 0.459478021978022, "bacc_std": 0.06680006744817896} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 69, "C": 0.005994842503189409, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.06724088992649123, "f1": 0.44334609990290214, "f1_std": 0.06828401660273148, "bacc": 0.44047619047619047, "bacc_std": 0.06738926447336738} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 70, "C": 0.046415888336127774, "split": "test", "acc": 0.5576923076923077, "acc_std": 0.0690564471965383, "f1": 0.5577777777777778, "f1_std": 0.07017927580840069, "bacc": 0.5608974358974359, "bacc_std": 0.06905965009658767} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 71, "C": 0.005994842503189409, "split": "test", "acc": 0.5, "acc_std": 0.06915504405568111, "f1": 0.5033380084151473, "f1_std": 0.06988477476381036, "bacc": 0.5, "bacc_std": 0.06946991444190484} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 72, "C": 0.046415888336127774, "split": "test", "acc": 0.5576923076923077, "acc_std": 0.06352489844063894, "f1": 0.5554112554112554, "f1_std": 0.06526173093794888, "bacc": 0.55746336996337, "bacc_std": 0.06357928466031043} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 73, "C": 21.54434690031882, "split": "test", "acc": 0.40384615384615385, "acc_std": 0.06322415977059896, "f1": 0.40346880131362894, "f1_std": 0.06336699806506582, "bacc": 0.4036172161172161, "bacc_std": 0.06330462368224175} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 74, "C": 0.046415888336127774, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.0677676481959632, "f1": 0.43683418031244114, "f1_std": 0.06737536840090773, "bacc": 0.4212454212454212, "bacc_std": 0.06765627252395247} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 75, "C": 0.005994842503189409, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.06705839546519782, "f1": 0.5375107886503399, "f1_std": 0.06676019581178463, "bacc": 0.5341117216117217, "bacc_std": 0.06704428098139308} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 76, "C": 0.046415888336127774, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.06457566315717825, "f1": 0.5155960729312763, "f1_std": 0.06639598498945963, "bacc": 0.5233516483516484, "bacc_std": 0.06518953330290685} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 77, "C": 0.3593813663804626, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.06745345754600904, "f1": 0.45999589490968806, "f1_std": 0.06877927800846542, "bacc": 0.46130952380952384, "bacc_std": 0.06766802171925676} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 78, "C": 0.046415888336127774, "split": "test", "acc": 0.5769230769230769, "acc_std": 0.06489330113767043, "f1": 0.583896993810787, "f1_std": 0.06362861143040752, "bacc": 0.5798992673992673, "bacc_std": 0.06512085823986961} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 79, "C": 21.54434690031882, "split": "test", "acc": 0.36538461538461536, "acc_std": 0.05963740288179229, "f1": 0.35507468487978233, "f1_std": 0.05727276956121866, "bacc": 0.3644688644688645, "bacc_std": 0.05937785961980687} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 80, "C": 0.046415888336127774, "split": "test", "acc": 0.5, "acc_std": 0.06003907751125401, "f1": 0.482736013986014, "f1_std": 0.06204844884553497, "bacc": 0.5022893772893773, "bacc_std": 0.060253199439252} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 81, "C": 166.81005372000556, "split": "test", "acc": 0.40384615384615385, "acc_std": 0.06642630609940488, "f1": 0.40758921614461585, "f1_std": 0.0654087705118412, "bacc": 0.40613553113553114, "bacc_std": 0.06687725861034624} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 82, "C": 0.005994842503189409, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.06939804577505371, "f1": 0.48068965517241385, "f1_std": 0.0691324646657347, "bacc": 0.4789377289377289, "bacc_std": 0.06972541523137961} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 83, "C": 0.005994842503189409, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.06490105122187267, "f1": 0.5047619047619047, "f1_std": 0.06682249250408638, "bacc": 0.5157967032967034, "bacc_std": 0.06465802278192988} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 84, "C": 0.046415888336127774, "split": "test", "acc": 0.5961538461538461, "acc_std": 0.05929879959270756, "f1": 0.586726222142385, "f1_std": 0.061188177018927384, "bacc": 0.5902014652014652, "bacc_std": 0.05926553270749994} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 85, "C": 0.046415888336127774, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.06708445397032789, "f1": 0.45486943164362514, "f1_std": 0.06630108184063135, "bacc": 0.4581043956043956, "bacc_std": 0.06668322991893998} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 86, "C": 0.3593813663804626, "split": "test", "acc": 0.5961538461538461, "acc_std": 0.05923081918079812, "f1": 0.5654029710291053, "f1_std": 0.059502187048100334, "bacc": 0.586996336996337, "bacc_std": 0.05889641946402417} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 87, "C": 0.005994842503189409, "split": "test", "acc": 0.5576923076923077, "acc_std": 0.06529400962039084, "f1": 0.5442409442409442, "f1_std": 0.06732034269132693, "bacc": 0.5572344322344323, "bacc_std": 0.06554359318397608} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 88, "C": 0.046415888336127774, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.06649797567769089, "f1": 0.5233333333333333, "f1_std": 0.06628526408024485, "bacc": 0.5176282051282051, "bacc_std": 0.06667213726617272} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 89, "C": 2.782559402207126, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.06363415916799524, "f1": 0.4152573875399962, "f1_std": 0.06484763475545981, "bacc": 0.41689560439560436, "bacc_std": 0.06346888233748671} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 90, "C": 21.54434690031882, "split": "test", "acc": 0.5961538461538461, "acc_std": 0.06339040302180034, "f1": 0.5899962106858658, "f1_std": 0.06459962036946569, "bacc": 0.5989010989010989, "bacc_std": 0.06356744227848057} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 91, "C": 2.782559402207126, "split": "test", "acc": 0.5576923076923077, "acc_std": 0.06361291968064237, "f1": 0.5519574628270281, "f1_std": 0.06487953073422123, "bacc": 0.5531135531135531, "bacc_std": 0.06350219426065606} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 92, "C": 0.3593813663804626, "split": "test", "acc": 0.5961538461538461, "acc_std": 0.06096942438681189, "f1": 0.5754105090311987, "f1_std": 0.06258348876059311, "bacc": 0.5885989010989011, "bacc_std": 0.060793983735665934} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 93, "C": 0.046415888336127774, "split": "test", "acc": 0.5, "acc_std": 0.066650406054419, "f1": 0.5046620046620047, "f1_std": 0.06620664901065994, "bacc": 0.5011446886446886, "bacc_std": 0.06698663875223354} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 94, "C": 166.81005372000556, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.06406564449635802, "f1": 0.4741666666666666, "f1_std": 0.06465224372171517, "bacc": 0.4807692307692308, "bacc_std": 0.06437524172795656} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 95, "C": 0.005994842503189409, "split": "test", "acc": 0.5, "acc_std": 0.06083096912538651, "f1": 0.4739389920424404, "f1_std": 0.05590383224524485, "bacc": 0.49198717948717946, "bacc_std": 0.059801337554711335} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 96, "C": 0.046415888336127774, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.06700441564536125, "f1": 0.4462068965517242, "f1_std": 0.06682540442155173, "bacc": 0.44345238095238093, "bacc_std": 0.06724054310827016} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 97, "C": 0.3593813663804626, "split": "test", "acc": 0.5, "acc_std": 0.0639886731840721, "f1": 0.49880341880341883, "f1_std": 0.06342271522642204, "bacc": 0.4981684981684982, "bacc_std": 0.06410965130235767} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 98, "C": 0.046415888336127774, "split": "test", "acc": 0.5, "acc_std": 0.06847315156473448, "f1": 0.4906400966183575, "f1_std": 0.0707904419481997, "bacc": 0.5011446886446886, "bacc_std": 0.06888138941663191} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 99, "C": 0.3593813663804626, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.06304342450074445, "f1": 0.41947997775305895, "f1_std": 0.06394576552446031, "bacc": 0.4429945054945055, "bacc_std": 0.06340970117498167} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 100, "C": 0.3593813663804626, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.06849544320350787, "f1": 0.42124223602484473, "f1_std": 0.06893922153896247, "bacc": 0.4244505494505495, "bacc_std": 0.06828296825955621} +eval results (random splits): + +| model | repr | clf | dataset | split | n_trials | C | C_std | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|-----------:|-------:|--------:|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | aabc_age | train | 100 | 6.5232 | 28.789 | 0.8124 | 0.146 | 0.80987 | 0.15019 | 0.81234 | 0.1464 | +| flat_mae | patch | logistic | aabc_age | test | 100 | 6.5232 | 28.789 | 0.48365 | 0.066301 | 0.47655 | 0.065281 | 0.48244 | 0.066221 | + + +done! total time: 0:06:07 diff --git a/input_space_v3/flat_lr1e-3_5/eval_v2/aabc_sex__patch__logistic/config.yaml b/input_space_v3/flat_lr1e-3_5/eval_v2/aabc_sex__patch__logistic/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..a9404367c017bbedb590faa06516635cf6aa5669 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_5/eval_v2/aabc_sex__patch__logistic/config.yaml @@ -0,0 +1,30 @@ +output_root: experiments/input_space_v3/output +name_prefix: eval_logistic +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_5; eval v2 (aabc_sex patch logistic) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: input_space_v3/flat_lr1e-3_5/eval_v2/aabc_sex__patch__logistic +model: flat_mae +representation: patch +dataset: aabc_sex +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/eval_v2/aabc_sex__patch__logistic +remote_dir: null diff --git a/input_space_v3/flat_lr1e-3_5/eval_v2/aabc_sex__patch__logistic/eval_table.csv b/input_space_v3/flat_lr1e-3_5/eval_v2/aabc_sex__patch__logistic/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..1c8bad325f5d8c75676b7e83ca2a9c6a1b1a1ca1 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_5/eval_v2/aabc_sex__patch__logistic/eval_table.csv @@ -0,0 +1,203 @@ +model,repr,clf,dataset,trial,C,split,acc,acc_std,f1,f1_std,bacc,bacc_std +flat_mae,patch,logistic,aabc_sex,,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,,2.782559402207126,test,0.9636363636363636,0.025035406332790652,0.9626358695652174,0.025353011679456864,0.9696969696969697,0.020862838610658855 +flat_mae,patch,logistic,aabc_sex,1,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,1,2.782559402207126,test,0.8,0.05431528406116115,0.7989365237620472,0.054238799022593126,0.8097826086956521,0.05249849674559848 +flat_mae,patch,logistic,aabc_sex,2,0.3593813663804626,train,0.9924385633270322,0.003602602045693809,0.9922570257611241,0.003683815331767842,0.9928558867493186,0.0034498735837747386 +flat_mae,patch,logistic,aabc_sex,2,0.3593813663804626,test,0.9090909090909091,0.040611442429423106,0.9071259709557582,0.04134577365904692,0.9096467391304348,0.04072304096085218 +flat_mae,patch,logistic,aabc_sex,3,0.046415888336127774,train,0.943289224952741,0.009918146567094091,0.9417862487895061,0.010200037071665993,0.9412497435446525,0.010401007051062774 +flat_mae,patch,logistic,aabc_sex,3,0.046415888336127774,test,0.8727272727272727,0.040376017757046745,0.8609606356085229,0.04807408277020655,0.8478260869565217,0.048275673405164594 +flat_mae,patch,logistic,aabc_sex,4,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,4,21.54434690031882,test,0.9090909090909091,0.03912558293072989,0.9071259709557582,0.03971062433844468,0.9096467391304348,0.038865751107732924 +flat_mae,patch,logistic,aabc_sex,5,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,5,21.54434690031882,test,0.8545454545454545,0.046858549234516794,0.84593837535014,0.05143810533392128,0.8383152173913043,0.05152595039530369 +flat_mae,patch,logistic,aabc_sex,6,0.046415888336127774,train,0.945179584120983,0.009861444121415737,0.943691387252473,0.010166018999155372,0.9428837304727571,0.010532476284127337 +flat_mae,patch,logistic,aabc_sex,6,0.046415888336127774,test,0.9454545454545454,0.030464720145665536,0.9435897435897436,0.031856996515590215,0.9408967391304348,0.03345344386828878 +flat_mae,patch,logistic,aabc_sex,7,0.3593813663804626,train,0.994328922495274,0.0035676361503724947,0.9941893034853195,0.0036518247698620956,0.9944898736774231,0.003490361157270077 +flat_mae,patch,logistic,aabc_sex,7,0.3593813663804626,test,0.8909090909090909,0.04259749730746518,0.8891129032258065,0.043031687875229256,0.8940217391304348,0.04194112295121189 +flat_mae,patch,logistic,aabc_sex,8,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,8,2.782559402207126,test,0.8545454545454545,0.04606031259874614,0.8521505376344086,0.046677756374624485,0.8566576086956521,0.04620429528719357 +flat_mae,patch,logistic,aabc_sex,9,0.046415888336127774,train,0.9489603024574669,0.009931871512856244,0.9477656971705049,0.010153769057001792,0.9485843664820188,0.010177724528107394 +flat_mae,patch,logistic,aabc_sex,9,0.046415888336127774,test,0.8909090909090909,0.042437719071599496,0.8879076086956521,0.04366517877489821,0.8879076086956521,0.043834059975295124 +flat_mae,patch,logistic,aabc_sex,10,0.005994842503189409,train,0.9054820415879017,0.01291115256554674,0.9021935273932079,0.013511419508100848,0.8988393563703508,0.013983907712084525 +flat_mae,patch,logistic,aabc_sex,10,0.005994842503189409,test,0.8909090909090909,0.0425179553709444,0.8879076086956521,0.04375262580989762,0.8879076086956521,0.043804534182767904 +flat_mae,patch,logistic,aabc_sex,11,0.3593813663804626,train,0.996219281663516,0.0028238093888112666,0.9961238606055277,0.002895508239655895,0.9961238606055277,0.002931833938081291 +flat_mae,patch,logistic,aabc_sex,11,0.3593813663804626,test,0.9272727272727272,0.03491232939523878,0.9242424242424243,0.03704483705534569,0.9191576086956521,0.038790809387581025 +flat_mae,patch,logistic,aabc_sex,12,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,12,2.782559402207126,test,0.7818181818181819,0.05496926263568343,0.7727272727272727,0.05848863216587098,0.7697010869565217,0.05812569801855407 +flat_mae,patch,logistic,aabc_sex,13,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,13,166.81005372000556,test,0.9090909090909091,0.03805831106765399,0.905982905982906,0.03970379011553819,0.9035326086956521,0.040372554561821275 +flat_mae,patch,logistic,aabc_sex,14,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,14,166.81005372000556,test,0.9454545454545454,0.030748481115480994,0.9447975911676145,0.030773387886052203,0.953125,0.026424475958616474 +flat_mae,patch,logistic,aabc_sex,15,0.046415888336127774,train,0.9508506616257089,0.009437796816409253,0.9494843391902215,0.009738101646208175,0.9483938567953341,0.010087448074250672 +flat_mae,patch,logistic,aabc_sex,15,0.046415888336127774,test,0.8909090909090909,0.0409522358343804,0.8879076086956521,0.04216199251420086,0.8879076086956521,0.04225007969701995 +flat_mae,patch,logistic,aabc_sex,16,0.046415888336127774,train,0.941398865784499,0.010040281077421172,0.9398830580860384,0.010306871133682047,0.939615756616548,0.010443630143496295 +flat_mae,patch,logistic,aabc_sex,16,0.046415888336127774,test,0.8909090909090909,0.04297837241994825,0.8863636363636364,0.04584762719157093,0.8817934782608696,0.04705627227209899 +flat_mae,patch,logistic,aabc_sex,17,0.3593813663804626,train,0.994328922495274,0.0032417559880630145,0.9941893034853195,0.0033179742314291398,0.9944898736774231,0.003145395474973747 +flat_mae,patch,logistic,aabc_sex,17,0.3593813663804626,test,0.8545454545454545,0.04662374098182699,0.84593837535014,0.051043421274761774,0.8383152173913043,0.05101300411741281 +flat_mae,patch,logistic,aabc_sex,18,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,18,21.54434690031882,test,0.8363636363636363,0.047668982586441304,0.8354935194416749,0.04761718489244628,0.8471467391304348,0.04576962430696513 +flat_mae,patch,logistic,aabc_sex,19,0.046415888336127774,train,0.9508506616257089,0.008876289317497085,0.9495480822842386,0.009117035070972876,0.9490020223335971,0.009267736245962681 +flat_mae,patch,logistic,aabc_sex,19,0.046415888336127774,test,0.8363636363636363,0.047515460728740286,0.8343927735028438,0.04768811211271068,0.8410326086956521,0.04666220403780517 +flat_mae,patch,logistic,aabc_sex,20,0.046415888336127774,train,0.9508506616257089,0.009792871341719033,0.9496706674473068,0.01002562803178824,0.9502183534101234,0.010090032576315792 +flat_mae,patch,logistic,aabc_sex,20,0.046415888336127774,test,0.9090909090909091,0.03883255003407271,0.905982905982906,0.040793920544294704,0.9035326086956521,0.04186463901654034 +flat_mae,patch,logistic,aabc_sex,21,0.005994842503189409,train,0.9111531190926276,0.012383652735700386,0.9081274826789838,0.012926449575070291,0.9049576482311907,0.013348377809267939 +flat_mae,patch,logistic,aabc_sex,21,0.005994842503189409,test,0.8363636363636363,0.046935806346065576,0.8281846581048247,0.050638454383670685,0.8226902173913043,0.05077208431169486 +flat_mae,patch,logistic,aabc_sex,22,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,22,2.782559402207126,test,0.9454545454545454,0.030422610121611376,0.9442755825734549,0.03097666215677749,0.9470108695652174,0.0301274298604226 +flat_mae,patch,logistic,aabc_sex,23,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,23,21.54434690031882,test,0.8545454545454545,0.04765788549219085,0.8533333333333333,0.04768302921406751,0.8627717391304348,0.04609096616180971 +flat_mae,patch,logistic,aabc_sex,24,0.005994842503189409,train,0.9054820415879017,0.012884250993233865,0.9025997937840624,0.013342713592439446,0.9006638529851403,0.013608781972419949 +flat_mae,patch,logistic,aabc_sex,24,0.005994842503189409,test,0.8727272727272727,0.04437941597163565,0.8663658451926415,0.04788913918531563,0.8600543478260869,0.04862966265227339 +flat_mae,patch,logistic,aabc_sex,25,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,25,21.54434690031882,test,0.8727272727272727,0.04455048580121171,0.8699763593380614,0.0455050131729565,0.8722826086956521,0.04503708586800879 +flat_mae,patch,logistic,aabc_sex,26,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,26,2.782559402207126,test,0.8727272727272727,0.042690893603837966,0.8663658451926415,0.04624391738603346,0.8600543478260869,0.04708772248723998 +flat_mae,patch,logistic,aabc_sex,27,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,27,2.782559402207126,test,0.9272727272727272,0.03228540084059693,0.9229691876750701,0.03595015495886943,0.9130434782608696,0.03860210970071372 +flat_mae,patch,logistic,aabc_sex,28,0.3593813663804626,train,0.998109640831758,0.0018894931853874158,0.998060743809227,0.0019409750652304258,0.9977578475336323,0.002241125325268921 +flat_mae,patch,logistic,aabc_sex,28,0.3593813663804626,test,0.8727272727272727,0.04326232113227473,0.8663658451926415,0.046962802229400386,0.8600543478260869,0.0478476408940967 +flat_mae,patch,logistic,aabc_sex,29,0.046415888336127774,train,0.941398865784499,0.010485187566646258,0.939956136014968,0.010749725607276415,0.9402239221548111,0.010858580990886461 +flat_mae,patch,logistic,aabc_sex,29,0.046415888336127774,test,0.8727272727272727,0.04356029733750942,0.8663658451926415,0.04697216860093558,0.8600543478260869,0.04784784528138381 +flat_mae,patch,logistic,aabc_sex,30,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,30,21.54434690031882,test,0.8545454545454545,0.04815506632975536,0.8505434782608696,0.04962348587159336,0.8505434782608696,0.0495346242619035 +flat_mae,patch,logistic,aabc_sex,31,0.005994842503189409,train,0.9187145557655955,0.01199218349323615,0.9161793372319689,0.012446200760534265,0.9139262580966616,0.012782839355112392 +flat_mae,patch,logistic,aabc_sex,31,0.005994842503189409,test,0.8,0.05228529493189936,0.795677136102668,0.05313668322962192,0.7975543478260869,0.05280358014557665 +flat_mae,patch,logistic,aabc_sex,32,0.3593813663804626,train,0.996219281663516,0.0026356678012660834,0.9961238606055277,0.002703639700940017,0.9961238606055277,0.0027858769180179517 +flat_mae,patch,logistic,aabc_sex,32,0.3593813663804626,test,0.8545454545454545,0.04770077532852214,0.8505434782608696,0.04934319020414946,0.8505434782608696,0.049690144779125846 +flat_mae,patch,logistic,aabc_sex,33,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,33,21.54434690031882,test,0.9090909090909091,0.03938307729037314,0.905982905982906,0.041356483341926376,0.9035326086956521,0.04226660595639463 +flat_mae,patch,logistic,aabc_sex,34,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,34,21.54434690031882,test,0.9272727272727272,0.03475389745668466,0.9242424242424243,0.036997559311752186,0.9191576086956521,0.03883174467772284 +flat_mae,patch,logistic,aabc_sex,35,0.005994842503189409,train,0.9035916824196597,0.013127213211022924,0.900308545034642,0.01370294907398373,0.8972053694422463,0.014112775947011193 +flat_mae,patch,logistic,aabc_sex,35,0.005994842503189409,test,0.8727272727272727,0.04445134400072818,0.8663658451926415,0.0480646463499244,0.8600543478260869,0.04886964520615045 +flat_mae,patch,logistic,aabc_sex,36,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,36,2.782559402207126,test,0.8909090909090909,0.04218025075457717,0.8879076086956521,0.04362670281609824,0.8879076086956521,0.04398373416084546 +flat_mae,patch,logistic,aabc_sex,37,0.005994842503189409,train,0.9111531190926276,0.012435519993585808,0.9079955742551908,0.012981711858499799,0.9043494826929277,0.01331080196278501 +flat_mae,patch,logistic,aabc_sex,37,0.005994842503189409,test,0.7636363636363637,0.05754887538302759,0.7555555555555555,0.06023291517247965,0.7540760869565217,0.059927490633963965 +flat_mae,patch,logistic,aabc_sex,38,0.3593813663804626,train,0.996219281663516,0.0027125725335332995,0.9961238606055277,0.002781899550988551,0.9961238606055277,0.002857384069077892 +flat_mae,patch,logistic,aabc_sex,38,0.3593813663804626,test,0.8727272727272727,0.04194445756784984,0.8663658451926415,0.044949293435373266,0.8600543478260869,0.04544465003951602 +flat_mae,patch,logistic,aabc_sex,39,0.3593813663804626,train,0.994328922495274,0.0030781734781022705,0.9941893034853195,0.0031518135915798518,0.9944898736774231,0.0030285911527636097 +flat_mae,patch,logistic,aabc_sex,39,0.3593813663804626,test,0.8363636363636363,0.04756130102690525,0.8307692307692308,0.04956340095051584,0.8288043478260869,0.04962009089068066 +flat_mae,patch,logistic,aabc_sex,40,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,40,166.81005372000556,test,0.8545454545454545,0.044957809422826324,0.8484848484848485,0.047609691706065875,0.8444293478260869,0.04807609932086562 +flat_mae,patch,logistic,aabc_sex,41,0.000774263682681127,train,0.8695652173913043,0.01412657450858742,0.8647314529667471,0.014761084176620044,0.8611037838154694,0.014918172759979238 +flat_mae,patch,logistic,aabc_sex,41,0.000774263682681127,test,0.8909090909090909,0.04128467588355172,0.8863636363636364,0.04390523496029357,0.8817934782608696,0.04470380426523564 +flat_mae,patch,logistic,aabc_sex,42,0.3593813663804626,train,0.998109640831758,0.0018746264024367785,0.998060743809227,0.0019256169531600528,0.9977578475336323,0.002223491854011329 +flat_mae,patch,logistic,aabc_sex,42,0.3593813663804626,test,0.8,0.05214976525861764,0.795677136102668,0.05334947399930197,0.7975543478260869,0.053526720650447966 +flat_mae,patch,logistic,aabc_sex,43,0.046415888336127774,train,0.9395085066162571,0.01012276373628129,0.9379817696884434,0.010370885656834989,0.9379817696884434,0.010470582059035912 +flat_mae,patch,logistic,aabc_sex,43,0.046415888336127774,test,0.8909090909090909,0.039173797955789166,0.8863636363636364,0.041622378125460595,0.8817934782608696,0.04268155848240831 +flat_mae,patch,logistic,aabc_sex,44,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,44,2.782559402207126,test,0.8545454545454545,0.04583116699112726,0.8484848484848485,0.048684723610377525,0.8444293478260869,0.04897455371543174 +flat_mae,patch,logistic,aabc_sex,45,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,45,166.81005372000556,test,0.9454545454545454,0.030032489294481417,0.9447975911676145,0.030043243348843153,0.953125,0.02580917048744496 +flat_mae,patch,logistic,aabc_sex,46,0.3593813663804626,train,0.998109640831758,0.0018401653721947869,0.9980631011617731,0.0018832588607614249,0.9983660130718954,0.0015906004606062634 +flat_mae,patch,logistic,aabc_sex,46,0.3593813663804626,test,0.8909090909090909,0.04341573009675998,0.8891129032258065,0.0438868123385168,0.8940217391304348,0.04288974479786065 +flat_mae,patch,logistic,aabc_sex,47,0.005994842503189409,train,0.9073724007561437,0.011988540404883279,0.904218013856813,0.012493970753831475,0.9010815088367186,0.012813592370351127 +flat_mae,patch,logistic,aabc_sex,47,0.005994842503189409,test,0.8545454545454545,0.04413203330503096,0.84593837535014,0.048531456708173104,0.8383152173913043,0.04889090189903741 +flat_mae,patch,logistic,aabc_sex,48,0.005994842503189409,train,0.9017013232514177,0.013287664709813306,0.8982812684889363,0.013886353642368536,0.8949632169758786,0.014297573565749856 +flat_mae,patch,logistic,aabc_sex,48,0.005994842503189409,test,0.9090909090909091,0.037959456405203075,0.905982905982906,0.03961412854866127,0.9035326086956521,0.04038021936568441 +flat_mae,patch,logistic,aabc_sex,49,0.3593813663804626,train,0.996219281663516,0.002668887241702534,0.9961238606055277,0.002735896277913794,0.9961238606055277,0.0027530573563953097 +flat_mae,patch,logistic,aabc_sex,49,0.3593813663804626,test,0.8545454545454545,0.0490476711943266,0.8484848484848485,0.051977417450803004,0.8444293478260869,0.052182587081128516 +flat_mae,patch,logistic,aabc_sex,50,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,50,2.782559402207126,test,0.8545454545454545,0.04709780223329545,0.8505434782608696,0.04844664451656783,0.8505434782608696,0.04847370725454584 +flat_mae,patch,logistic,aabc_sex,51,0.046415888336127774,train,0.945179584120983,0.00980906917024092,0.9437615704675844,0.010074825407962158,0.9434918960110203,0.010230937769850866 +flat_mae,patch,logistic,aabc_sex,51,0.046415888336127774,test,0.8727272727272727,0.041388703693017836,0.8639095086603039,0.04705166592959979,0.8539402173913043,0.04737846308997824 +flat_mae,patch,logistic,aabc_sex,52,0.046415888336127774,train,0.943289224952741,0.009860846923208261,0.9417862487895061,0.010146601086846611,0.9412497435446525,0.010416572137361706 +flat_mae,patch,logistic,aabc_sex,52,0.046415888336127774,test,0.8909090909090909,0.0423328955965308,0.8891129032258065,0.042703807712126285,0.8940217391304348,0.04135438330943399 +flat_mae,patch,logistic,aabc_sex,53,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,53,2.782559402207126,test,0.9636363636363636,0.02537608687571761,0.9626358695652174,0.026101532625034007,0.9626358695652174,0.02623879227132286 +flat_mae,patch,logistic,aabc_sex,54,0.3593813663804626,train,0.996219281663516,0.0026098350981288523,0.9961238606055277,0.0026765173612181914,0.9961238606055277,0.002736642881598633 +flat_mae,patch,logistic,aabc_sex,54,0.3593813663804626,test,0.8909090909090909,0.04222605830526927,0.8891129032258065,0.04249491506336823,0.8940217391304348,0.040916340366257 +flat_mae,patch,logistic,aabc_sex,55,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,55,166.81005372000556,test,0.8545454545454545,0.04787558255477081,0.8505434782608696,0.04963339726106,0.8505434782608696,0.04997861034906628 +flat_mae,patch,logistic,aabc_sex,56,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,56,166.81005372000556,test,0.7636363636363637,0.056354615113831615,0.7607895617263298,0.05677721801852059,0.7663043478260869,0.056431791982622 +flat_mae,patch,logistic,aabc_sex,57,0.046415888336127774,train,0.9508506616257089,0.009121734985699724,0.9496101878718604,0.009362063187969172,0.9496101878718604,0.009501394779638413 +flat_mae,patch,logistic,aabc_sex,57,0.046415888336127774,test,0.8909090909090909,0.04124506882621653,0.8879076086956521,0.04268247505691516,0.8879076086956521,0.04315086987064224 +flat_mae,patch,logistic,aabc_sex,58,0.046415888336127774,train,0.9527410207939508,0.008725662032043693,0.9515185952306762,0.008948721860598285,0.9512441747999649,0.009018568617028662 +flat_mae,patch,logistic,aabc_sex,58,0.046415888336127774,test,0.7818181818181819,0.054780330668034234,0.7782258064516129,0.05542516571248587,0.7819293478260869,0.05514285631035653 +flat_mae,patch,logistic,aabc_sex,59,0.046415888336127774,train,0.9395085066162571,0.010446682346624306,0.9379053320421398,0.010738137886043985,0.9373736041501802,0.010878633974166198 +flat_mae,patch,logistic,aabc_sex,59,0.046415888336127774,test,0.9272727272727272,0.033619435543759395,0.9252717391304348,0.034638595839659024,0.9252717391304348,0.03489629992152492 +flat_mae,patch,logistic,aabc_sex,60,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,60,21.54434690031882,test,0.8727272727272727,0.044053326062739935,0.8639095086603039,0.049660810837759306,0.8539402173913043,0.049996867443813264 +flat_mae,patch,logistic,aabc_sex,61,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,61,21.54434690031882,test,0.9090909090909091,0.03846585262517677,0.905982905982906,0.040074767712279684,0.9035326086956521,0.040625529183517216 +flat_mae,patch,logistic,aabc_sex,62,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,62,21.54434690031882,test,0.8909090909090909,0.04169022320333392,0.8891129032258065,0.04219508350419092,0.8940217391304348,0.04135390378527929 +flat_mae,patch,logistic,aabc_sex,63,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,63,2.782559402207126,test,0.9272727272727272,0.034736619399025115,0.9260752688172043,0.03507527277779534,0.9313858695652174,0.033532405110896335 +flat_mae,patch,logistic,aabc_sex,64,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,64,2.782559402207126,test,0.8545454545454545,0.045488801637108035,0.8521505376344086,0.04602301669518236,0.8566576086956521,0.04568442060764806 +flat_mae,patch,logistic,aabc_sex,65,0.005994842503189409,train,0.9092627599243857,0.012289021259836597,0.9061057862974795,0.012853164946703358,0.9027154957648231,0.013283520069979222 +flat_mae,patch,logistic,aabc_sex,65,0.005994842503189409,test,0.8909090909090909,0.04128104041228444,0.884453781512605,0.045399466625611846,0.8756793478260869,0.046531901631378686 +flat_mae,patch,logistic,aabc_sex,66,0.005994842503189409,train,0.9054820415879017,0.012473450995984021,0.9024676244136995,0.01291656728629241,0.900055687446877,0.013132323778550278 +flat_mae,patch,logistic,aabc_sex,66,0.005994842503189409,test,0.8909090909090909,0.040596804010510086,0.8863636363636364,0.04310093338095725,0.8817934782608696,0.044082655534378436 +flat_mae,patch,logistic,aabc_sex,67,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,67,166.81005372000556,test,0.8727272727272727,0.046448763205340395,0.8699763593380614,0.047383114918081656,0.8722826086956521,0.04723272731169107 +flat_mae,patch,logistic,aabc_sex,68,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,68,21.54434690031882,test,0.9454545454545454,0.030573558499769758,0.9435897435897436,0.0319108676947168,0.9408967391304348,0.03324967450996044 +flat_mae,patch,logistic,aabc_sex,69,0.3593813663804626,train,0.994328922495274,0.0032850308962725696,0.9941893034853195,0.0033647116004598865,0.9944898736774231,0.003282395261896013 +flat_mae,patch,logistic,aabc_sex,69,0.3593813663804626,test,0.9454545454545454,0.02989648255934949,0.9427282193682749,0.032548341587280594,0.9347826086956521,0.0357457943644396 +flat_mae,patch,logistic,aabc_sex,70,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,70,21.54434690031882,test,0.9090909090909091,0.03886658680985423,0.9079959852793577,0.03899311766480679,0.9157608695652174,0.036588729397995116 +flat_mae,patch,logistic,aabc_sex,71,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,71,21.54434690031882,test,0.9090909090909091,0.03686022739534259,0.9045470322804582,0.03982235757275534,0.8974184782608696,0.04153402361652718 +flat_mae,patch,logistic,aabc_sex,72,0.046415888336127774,train,0.9395085066162571,0.010230973102874992,0.938056206088993,0.010473756329111227,0.9385899352267065,0.010548569406691912 +flat_mae,patch,logistic,aabc_sex,72,0.046415888336127774,test,0.9454545454545454,0.02962072091354323,0.9435897435897436,0.030902111914584772,0.9408967391304348,0.032219871006114204 +flat_mae,patch,logistic,aabc_sex,73,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,73,2.782559402207126,test,0.9090909090909091,0.036331185520463195,0.9027925061859314,0.04121927995550777,0.8913043478260869,0.0434394609483799 +flat_mae,patch,logistic,aabc_sex,74,0.005994842503189409,train,0.9092627599243857,0.012095276087452705,0.9062389223679547,0.012570497283606511,0.9033236613030862,0.012820857346249647 +flat_mae,patch,logistic,aabc_sex,74,0.005994842503189409,test,0.9090909090909091,0.03945050670572994,0.905982905982906,0.04122527157904843,0.9035326086956521,0.04222734334658748 +flat_mae,patch,logistic,aabc_sex,75,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,75,166.81005372000556,test,0.8909090909090909,0.041597838468954804,0.8891129032258065,0.04215949422052935,0.8940217391304348,0.04142841501567792 +flat_mae,patch,logistic,aabc_sex,76,0.3593813663804626,train,0.996219281663516,0.002645149532467605,0.9961285128805621,0.0027038850469191696,0.9967320261437909,0.002286411932476078 +flat_mae,patch,logistic,aabc_sex,76,0.3593813663804626,test,0.8545454545454545,0.046553919684775485,0.8484848484848485,0.04941138648926772,0.8444293478260869,0.04991745749056916 +flat_mae,patch,logistic,aabc_sex,77,0.005994842503189409,train,0.9017013232514177,0.013055912541219608,0.8985663293902475,0.013539751720416908,0.8961795480524049,0.013799448370062547 +flat_mae,patch,logistic,aabc_sex,77,0.005994842503189409,test,0.8727272727272727,0.044139882829458736,0.8663658451926415,0.0476039804206764,0.8600543478260869,0.04839657074266412 +flat_mae,patch,logistic,aabc_sex,78,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,78,21.54434690031882,test,0.9818181818181818,0.01883903105016527,0.9814251941911516,0.019066884938430423,0.984375,0.01618979230873577 +flat_mae,patch,logistic,aabc_sex,79,0.046415888336127774,train,0.941398865784499,0.009494896813065468,0.9398830580860384,0.009766633278470164,0.939615756616548,0.010013328808118699 +flat_mae,patch,logistic,aabc_sex,79,0.046415888336127774,test,0.8545454545454545,0.045105569464249234,0.84593837535014,0.050093208500207674,0.8383152173913043,0.050276206672083 +flat_mae,patch,logistic,aabc_sex,80,0.3593813663804626,train,0.996219281663516,0.002719490436046035,0.9961238606055277,0.0027878705162727667,0.9961238606055277,0.0028044210672482184 +flat_mae,patch,logistic,aabc_sex,80,0.3593813663804626,test,0.8727272727272727,0.04464121802894089,0.8683760683760684,0.04696701906892495,0.8661684782608696,0.04780974577238351 +flat_mae,patch,logistic,aabc_sex,81,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,81,21.54434690031882,test,0.9272727272727272,0.034875059169356494,0.9252717391304348,0.03589818645711236,0.9252717391304348,0.03620616381018178 +flat_mae,patch,logistic,aabc_sex,82,0.046415888336127774,train,0.943289224952741,0.010303324567662319,0.9419276932084308,0.010538171982951016,0.9424660746211788,0.01055283316024914 +flat_mae,patch,logistic,aabc_sex,82,0.046415888336127774,test,0.8545454545454545,0.04653492778690249,0.8484848484848485,0.04903107653919976,0.8444293478260869,0.04936787794327687 +flat_mae,patch,logistic,aabc_sex,83,0.3593813663804626,train,0.994328922495274,0.0030956927143253868,0.9941893034853195,0.00316964011713893,0.9944898736774231,0.003054638354545473 +flat_mae,patch,logistic,aabc_sex,83,0.3593813663804626,test,0.8909090909090909,0.04014603095765374,0.884453781512605,0.044364390932058476,0.8756793478260869,0.045471895333560185 +flat_mae,patch,logistic,aabc_sex,84,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,84,2.782559402207126,test,0.8545454545454545,0.05020816172827113,0.8505434782608696,0.05183679018770084,0.8505434782608696,0.0521805451089413 +flat_mae,patch,logistic,aabc_sex,85,0.3593813663804626,train,0.994328922495274,0.0034453339988888497,0.9941893034853195,0.003527194453484027,0.9944898736774231,0.003376267519703628 +flat_mae,patch,logistic,aabc_sex,85,0.3593813663804626,test,0.8545454545454545,0.04765001886170307,0.8505434782608696,0.04920292601685931,0.8505434782608696,0.04980726447357592 +flat_mae,patch,logistic,aabc_sex,86,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,86,21.54434690031882,test,0.9272727272727272,0.0365757269463355,0.9260752688172043,0.036935229229283315,0.9313858695652174,0.03528066854546726 +flat_mae,patch,logistic,aabc_sex,87,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,87,1291.5496650148827,test,0.8909090909090909,0.04153898895382247,0.8863636363636364,0.0440347025282356,0.8817934782608696,0.04506279700630213 +flat_mae,patch,logistic,aabc_sex,88,0.3593813663804626,train,0.996219281663516,0.0027938971322256775,0.9961238606055277,0.0028638207065355163,0.9961238606055277,0.002859170737099553 +flat_mae,patch,logistic,aabc_sex,88,0.3593813663804626,test,0.8727272727272727,0.044798229008679,0.8663658451926415,0.047953512287876456,0.8600543478260869,0.0488395057672689 +flat_mae,patch,logistic,aabc_sex,89,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,89,21.54434690031882,test,0.8909090909090909,0.03940266383577856,0.884453781512605,0.04362209950132576,0.8756793478260869,0.04497025005347213 +flat_mae,patch,logistic,aabc_sex,90,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,90,166.81005372000556,test,0.8363636363636363,0.049123813888063375,0.8328267477203647,0.05033269190867406,0.8349184782608696,0.050497531199011896 +flat_mae,patch,logistic,aabc_sex,91,0.046415888336127774,train,0.9489603024574669,0.009463598679809088,0.9475747398557507,0.009752270395370055,0.9467598698672295,0.010058019859898236 +flat_mae,patch,logistic,aabc_sex,91,0.046415888336127774,test,0.8545454545454545,0.04737436625974425,0.8505434782608696,0.04873123781760968,0.8505434782608696,0.04864910134557515 +flat_mae,patch,logistic,aabc_sex,92,0.005994842503189409,train,0.9092627599243857,0.012781344479903336,0.9059694860020737,0.013414461386578716,0.90210733022656,0.013894600291464183 +flat_mae,patch,logistic,aabc_sex,92,0.005994842503189409,test,0.8909090909090909,0.04182448964284319,0.8863636363636364,0.04433174394875053,0.8817934782608696,0.04525097274774546 +flat_mae,patch,logistic,aabc_sex,93,0.046415888336127774,train,0.9546313799621928,0.009198961649939177,0.9534289990316049,0.009466622226841722,0.9528781617280695,0.009704090374217971 +flat_mae,patch,logistic,aabc_sex,93,0.046415888336127774,test,0.9090909090909091,0.03702132510319822,0.9027925061859314,0.042028994844589294,0.8913043478260869,0.04426462784078048 +flat_mae,patch,logistic,aabc_sex,94,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,94,21.54434690031882,test,0.9090909090909091,0.03843035989921863,0.9071259709557582,0.03908424166822591,0.9096467391304348,0.03823445610859572 +flat_mae,patch,logistic,aabc_sex,95,0.046415888336127774,train,0.943289224952741,0.00956071458680227,0.9417862487895061,0.009832524310283747,0.9412497435446525,0.01006070337533703 +flat_mae,patch,logistic,aabc_sex,95,0.046415888336127774,test,0.9090909090909091,0.03883042174497416,0.905982905982906,0.04056979512695986,0.9035326086956521,0.04125093735956661 +flat_mae,patch,logistic,aabc_sex,96,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,96,21.54434690031882,test,0.9090909090909091,0.03713466225100032,0.905982905982906,0.03855940962600297,0.9035326086956521,0.039049423874718374 +flat_mae,patch,logistic,aabc_sex,97,0.3593813663804626,train,0.994328922495274,0.003425445567835324,0.9941893034853195,0.00350679329061981,0.9944898736774231,0.003373712098334047 +flat_mae,patch,logistic,aabc_sex,97,0.3593813663804626,test,0.8181818181818182,0.04996171757596503,0.8131793478260869,0.05163064405612378,0.8131793478260869,0.051966617245606084 +flat_mae,patch,logistic,aabc_sex,98,0.005994842503189409,train,0.9168241965973535,0.011429953188404394,0.9139303041060229,0.011949476225541628,0.9104677745537677,0.012372022384161414 +flat_mae,patch,logistic,aabc_sex,98,0.005994842503189409,test,0.8181818181818182,0.047015510013379405,0.8035714285714286,0.053323606163455065,0.7948369565217391,0.05206232646621422 +flat_mae,patch,logistic,aabc_sex,99,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,99,166.81005372000556,test,0.9454545454545454,0.03090889839512241,0.9447975911676145,0.030909590464159684,0.953125,0.026562334558308313 +flat_mae,patch,logistic,aabc_sex,100,0.3593813663804626,train,0.994328922495274,0.0030424800814715476,0.9941893034853195,0.0031154852396830684,0.9944898736774231,0.0030203084291233317 +flat_mae,patch,logistic,aabc_sex,100,0.3593813663804626,test,0.9272727272727272,0.036138557966538,0.9260752688172043,0.036452112110364754,0.9313858695652174,0.034424556669653335 diff --git a/input_space_v3/flat_lr1e-3_5/eval_v2/aabc_sex__patch__logistic/log.txt b/input_space_v3/flat_lr1e-3_5/eval_v2/aabc_sex__patch__logistic/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..b94ea8323ca1f853eeb8c189d1e26ca958dc19af --- /dev/null +++ b/input_space_v3/flat_lr1e-3_5/eval_v2/aabc_sex__patch__logistic/log.txt @@ -0,0 +1,245 @@ +fMRI foundation model logistic probe eval +version: 0.1.dev86+gf97f52698 +sha: bcce2b486277d3a5b520775efd9cdf1a2affce36, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-04-08 22:31:06 +config: +output_root: experiments/input_space_v3/output +name_prefix: eval_logistic +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_5; eval v2 (aabc_sex patch logistic) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: input_space_v3/flat_lr1e-3_5/eval_v2/aabc_sex__patch__logistic +model: flat_mae +representation: patch +dataset: aabc_sex +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/eval_v2/aabc_sex__patch__logistic +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=True, reg_tokens=0, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: aabc_sex (flat) +train (n=471): +HFDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'segment', 'bold', 'mean', 'std'], + num_rows: 471 +}), + labels=[0 1], + counts=[269 202] +) + +validation (n=58): +HFDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'segment', 'bold', 'mean', 'std'], + num_rows: 58 +}), + labels=[0 1], + counts=[36 22] +) + +test (n=55): +HFDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'segment', 'bold', 'mean', 'std'], + num_rows: 55 +}), + labels=[0 1], + counts=[33 22] +) + +extracting features for all splits +extract (train) [ 0/236] eta: 0:27:25 time: 6.9715 data: 5.9633 max mem: 3205 +extract (train) [ 20/236] eta: 0:02:15 time: 0.3100 data: 0.1164 max mem: 3393 +extract (train) [ 40/236] eta: 0:01:26 time: 0.2428 data: 0.0804 max mem: 3393 +extract (train) [ 60/236] eta: 0:01:07 time: 0.2654 data: 0.0914 max mem: 3393 +extract (train) [ 80/236] eta: 0:00:54 time: 0.2597 data: 0.0896 max mem: 3393 +extract (train) [100/236] eta: 0:00:45 time: 0.2658 data: 0.0932 max mem: 3393 +extract (train) [120/236] eta: 0:00:37 time: 0.2433 data: 0.0811 max mem: 3393 +extract (train) [140/236] eta: 0:00:30 time: 0.2746 data: 0.0981 max mem: 3393 +extract (train) [160/236] eta: 0:00:23 time: 0.2485 data: 0.0836 max mem: 3393 +extract (train) [180/236] eta: 0:00:16 time: 0.2623 data: 0.0916 max mem: 3393 +extract (train) [200/236] eta: 0:00:10 time: 0.2506 data: 0.0871 max mem: 3393 +extract (train) [220/236] eta: 0:00:04 time: 0.2167 data: 0.0694 max mem: 3393 +extract (train) [235/236] eta: 0:00:00 time: 0.2091 data: 0.0662 max mem: 3393 +extract (train) Total time: 0:01:07 (0.2867 s / it) +extract (validation) [ 0/29] eta: 0:02:54 time: 6.0218 data: 5.8441 max mem: 3393 +extract (validation) [20/29] eta: 0:00:04 time: 0.2189 data: 0.0675 max mem: 3393 +extract (validation) [28/29] eta: 0:00:00 time: 0.2090 data: 0.0629 max mem: 3393 +extract (validation) Total time: 0:00:12 (0.4305 s / it) +extract (test) [ 0/28] eta: 0:02:47 time: 5.9754 data: 5.7577 max mem: 3393 +extract (test) [20/28] eta: 0:00:04 time: 0.2376 data: 0.0776 max mem: 3393 +extract (test) [27/28] eta: 0:00:00 time: 0.1998 data: 0.0612 max mem: 3393 +extract (test) Total time: 0:00:12 (0.4481 s / it) +feature extraction time: 0:01:32 +train features: (471, 768) +validation features: (58, 768) +test features: (55, 768) +evaluating fixed splits +eval results (fixed splits): + +| model | repr | clf | dataset | trial | C | split | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|-------:|:--------|--------:|----------:|--------:|---------:|-------:|-----------:| +| flat_mae | patch | logistic | aabc_sex | | 2.7826 | train | 1 | 0 | 1 | 0 | 1 | 0 | +| flat_mae | patch | logistic | aabc_sex | | 2.7826 | test | 0.96364 | 0.025035 | 0.96264 | 0.025353 | 0.9697 | 0.020863 | + + +evaluating random splits (n=100) +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 1, "C": 2.782559402207126, "split": "test", "acc": 0.8, "acc_std": 0.05431528406116115, "f1": 0.7989365237620472, "f1_std": 0.054238799022593126, "bacc": 0.8097826086956521, "bacc_std": 0.05249849674559848} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 2, "C": 0.3593813663804626, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.040611442429423106, "f1": 0.9071259709557582, "f1_std": 0.04134577365904692, "bacc": 0.9096467391304348, "bacc_std": 0.04072304096085218} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 3, "C": 0.046415888336127774, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.040376017757046745, "f1": 0.8609606356085229, "f1_std": 0.04807408277020655, "bacc": 0.8478260869565217, "bacc_std": 0.048275673405164594} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 4, "C": 21.54434690031882, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.03912558293072989, "f1": 0.9071259709557582, "f1_std": 0.03971062433844468, "bacc": 0.9096467391304348, "bacc_std": 0.038865751107732924} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 5, "C": 21.54434690031882, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.046858549234516794, "f1": 0.84593837535014, "f1_std": 0.05143810533392128, "bacc": 0.8383152173913043, "bacc_std": 0.05152595039530369} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 6, "C": 0.046415888336127774, "split": "test", "acc": 0.9454545454545454, "acc_std": 0.030464720145665536, "f1": 0.9435897435897436, "f1_std": 0.031856996515590215, "bacc": 0.9408967391304348, "bacc_std": 0.03345344386828878} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 7, "C": 0.3593813663804626, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.04259749730746518, "f1": 0.8891129032258065, "f1_std": 0.043031687875229256, "bacc": 0.8940217391304348, "bacc_std": 0.04194112295121189} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 8, "C": 2.782559402207126, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.04606031259874614, "f1": 0.8521505376344086, "f1_std": 0.046677756374624485, "bacc": 0.8566576086956521, "bacc_std": 0.04620429528719357} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 9, "C": 0.046415888336127774, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.042437719071599496, "f1": 0.8879076086956521, "f1_std": 0.04366517877489821, "bacc": 0.8879076086956521, "bacc_std": 0.043834059975295124} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 10, "C": 0.005994842503189409, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.0425179553709444, "f1": 0.8879076086956521, "f1_std": 0.04375262580989762, "bacc": 0.8879076086956521, "bacc_std": 0.043804534182767904} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 11, "C": 0.3593813663804626, "split": "test", "acc": 0.9272727272727272, "acc_std": 0.03491232939523878, "f1": 0.9242424242424243, "f1_std": 0.03704483705534569, "bacc": 0.9191576086956521, "bacc_std": 0.038790809387581025} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 12, "C": 2.782559402207126, "split": "test", "acc": 0.7818181818181819, "acc_std": 0.05496926263568343, "f1": 0.7727272727272727, "f1_std": 0.05848863216587098, "bacc": 0.7697010869565217, "bacc_std": 0.05812569801855407} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 13, "C": 166.81005372000556, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.03805831106765399, "f1": 0.905982905982906, "f1_std": 0.03970379011553819, "bacc": 0.9035326086956521, "bacc_std": 0.040372554561821275} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 14, "C": 166.81005372000556, "split": "test", "acc": 0.9454545454545454, "acc_std": 0.030748481115480994, "f1": 0.9447975911676145, "f1_std": 0.030773387886052203, "bacc": 0.953125, "bacc_std": 0.026424475958616474} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 15, "C": 0.046415888336127774, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.0409522358343804, "f1": 0.8879076086956521, "f1_std": 0.04216199251420086, "bacc": 0.8879076086956521, "bacc_std": 0.04225007969701995} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 16, "C": 0.046415888336127774, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.04297837241994825, "f1": 0.8863636363636364, "f1_std": 0.04584762719157093, "bacc": 0.8817934782608696, "bacc_std": 0.04705627227209899} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 17, "C": 0.3593813663804626, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.04662374098182699, "f1": 0.84593837535014, "f1_std": 0.051043421274761774, "bacc": 0.8383152173913043, "bacc_std": 0.05101300411741281} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 18, "C": 21.54434690031882, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.047668982586441304, "f1": 0.8354935194416749, "f1_std": 0.04761718489244628, "bacc": 0.8471467391304348, "bacc_std": 0.04576962430696513} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 19, "C": 0.046415888336127774, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.047515460728740286, "f1": 0.8343927735028438, "f1_std": 0.04768811211271068, "bacc": 0.8410326086956521, "bacc_std": 0.04666220403780517} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 20, "C": 0.046415888336127774, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.03883255003407271, "f1": 0.905982905982906, "f1_std": 0.040793920544294704, "bacc": 0.9035326086956521, "bacc_std": 0.04186463901654034} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 21, "C": 0.005994842503189409, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.046935806346065576, "f1": 0.8281846581048247, "f1_std": 0.050638454383670685, "bacc": 0.8226902173913043, "bacc_std": 0.05077208431169486} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 22, "C": 2.782559402207126, "split": "test", "acc": 0.9454545454545454, "acc_std": 0.030422610121611376, "f1": 0.9442755825734549, "f1_std": 0.03097666215677749, "bacc": 0.9470108695652174, "bacc_std": 0.0301274298604226} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 23, "C": 21.54434690031882, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.04765788549219085, "f1": 0.8533333333333333, "f1_std": 0.04768302921406751, "bacc": 0.8627717391304348, "bacc_std": 0.04609096616180971} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 24, "C": 0.005994842503189409, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.04437941597163565, "f1": 0.8663658451926415, "f1_std": 0.04788913918531563, "bacc": 0.8600543478260869, "bacc_std": 0.04862966265227339} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 25, "C": 21.54434690031882, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.04455048580121171, "f1": 0.8699763593380614, "f1_std": 0.0455050131729565, "bacc": 0.8722826086956521, "bacc_std": 0.04503708586800879} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 26, "C": 2.782559402207126, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.042690893603837966, "f1": 0.8663658451926415, "f1_std": 0.04624391738603346, "bacc": 0.8600543478260869, "bacc_std": 0.04708772248723998} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 27, "C": 2.782559402207126, "split": "test", "acc": 0.9272727272727272, "acc_std": 0.03228540084059693, "f1": 0.9229691876750701, "f1_std": 0.03595015495886943, "bacc": 0.9130434782608696, "bacc_std": 0.03860210970071372} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 28, "C": 0.3593813663804626, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.04326232113227473, "f1": 0.8663658451926415, "f1_std": 0.046962802229400386, "bacc": 0.8600543478260869, "bacc_std": 0.0478476408940967} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 29, "C": 0.046415888336127774, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.04356029733750942, "f1": 0.8663658451926415, "f1_std": 0.04697216860093558, "bacc": 0.8600543478260869, "bacc_std": 0.04784784528138381} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 30, "C": 21.54434690031882, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.04815506632975536, "f1": 0.8505434782608696, "f1_std": 0.04962348587159336, "bacc": 0.8505434782608696, "bacc_std": 0.0495346242619035} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 31, "C": 0.005994842503189409, "split": "test", "acc": 0.8, "acc_std": 0.05228529493189936, "f1": 0.795677136102668, "f1_std": 0.05313668322962192, "bacc": 0.7975543478260869, "bacc_std": 0.05280358014557665} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 32, "C": 0.3593813663804626, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.04770077532852214, "f1": 0.8505434782608696, "f1_std": 0.04934319020414946, "bacc": 0.8505434782608696, "bacc_std": 0.049690144779125846} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 33, "C": 21.54434690031882, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.03938307729037314, "f1": 0.905982905982906, "f1_std": 0.041356483341926376, "bacc": 0.9035326086956521, "bacc_std": 0.04226660595639463} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 34, "C": 21.54434690031882, "split": "test", "acc": 0.9272727272727272, "acc_std": 0.03475389745668466, "f1": 0.9242424242424243, "f1_std": 0.036997559311752186, "bacc": 0.9191576086956521, "bacc_std": 0.03883174467772284} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 35, "C": 0.005994842503189409, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.04445134400072818, "f1": 0.8663658451926415, "f1_std": 0.0480646463499244, "bacc": 0.8600543478260869, "bacc_std": 0.04886964520615045} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 36, "C": 2.782559402207126, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.04218025075457717, "f1": 0.8879076086956521, "f1_std": 0.04362670281609824, "bacc": 0.8879076086956521, "bacc_std": 0.04398373416084546} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 37, "C": 0.005994842503189409, "split": "test", "acc": 0.7636363636363637, "acc_std": 0.05754887538302759, "f1": 0.7555555555555555, "f1_std": 0.06023291517247965, "bacc": 0.7540760869565217, "bacc_std": 0.059927490633963965} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 38, "C": 0.3593813663804626, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.04194445756784984, "f1": 0.8663658451926415, "f1_std": 0.044949293435373266, "bacc": 0.8600543478260869, "bacc_std": 0.04544465003951602} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 39, "C": 0.3593813663804626, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.04756130102690525, "f1": 0.8307692307692308, "f1_std": 0.04956340095051584, "bacc": 0.8288043478260869, "bacc_std": 0.04962009089068066} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 40, "C": 166.81005372000556, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.044957809422826324, "f1": 0.8484848484848485, "f1_std": 0.047609691706065875, "bacc": 0.8444293478260869, "bacc_std": 0.04807609932086562} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 41, "C": 0.000774263682681127, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.04128467588355172, "f1": 0.8863636363636364, "f1_std": 0.04390523496029357, "bacc": 0.8817934782608696, "bacc_std": 0.04470380426523564} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 42, "C": 0.3593813663804626, "split": "test", "acc": 0.8, "acc_std": 0.05214976525861764, "f1": 0.795677136102668, "f1_std": 0.05334947399930197, "bacc": 0.7975543478260869, "bacc_std": 0.053526720650447966} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 43, "C": 0.046415888336127774, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.039173797955789166, "f1": 0.8863636363636364, "f1_std": 0.041622378125460595, "bacc": 0.8817934782608696, "bacc_std": 0.04268155848240831} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 44, "C": 2.782559402207126, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.04583116699112726, "f1": 0.8484848484848485, "f1_std": 0.048684723610377525, "bacc": 0.8444293478260869, "bacc_std": 0.04897455371543174} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 45, "C": 166.81005372000556, "split": "test", "acc": 0.9454545454545454, "acc_std": 0.030032489294481417, "f1": 0.9447975911676145, "f1_std": 0.030043243348843153, "bacc": 0.953125, "bacc_std": 0.02580917048744496} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 46, "C": 0.3593813663804626, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.04341573009675998, "f1": 0.8891129032258065, "f1_std": 0.0438868123385168, "bacc": 0.8940217391304348, "bacc_std": 0.04288974479786065} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 47, "C": 0.005994842503189409, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.04413203330503096, "f1": 0.84593837535014, "f1_std": 0.048531456708173104, "bacc": 0.8383152173913043, "bacc_std": 0.04889090189903741} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 48, "C": 0.005994842503189409, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.037959456405203075, "f1": 0.905982905982906, "f1_std": 0.03961412854866127, "bacc": 0.9035326086956521, "bacc_std": 0.04038021936568441} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 49, "C": 0.3593813663804626, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.0490476711943266, "f1": 0.8484848484848485, "f1_std": 0.051977417450803004, "bacc": 0.8444293478260869, "bacc_std": 0.052182587081128516} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 50, "C": 2.782559402207126, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.04709780223329545, "f1": 0.8505434782608696, "f1_std": 0.04844664451656783, "bacc": 0.8505434782608696, "bacc_std": 0.04847370725454584} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 51, "C": 0.046415888336127774, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.041388703693017836, "f1": 0.8639095086603039, "f1_std": 0.04705166592959979, "bacc": 0.8539402173913043, "bacc_std": 0.04737846308997824} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 52, "C": 0.046415888336127774, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.0423328955965308, "f1": 0.8891129032258065, "f1_std": 0.042703807712126285, "bacc": 0.8940217391304348, "bacc_std": 0.04135438330943399} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 53, "C": 2.782559402207126, "split": "test", "acc": 0.9636363636363636, "acc_std": 0.02537608687571761, "f1": 0.9626358695652174, "f1_std": 0.026101532625034007, "bacc": 0.9626358695652174, "bacc_std": 0.02623879227132286} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 54, "C": 0.3593813663804626, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.04222605830526927, "f1": 0.8891129032258065, "f1_std": 0.04249491506336823, "bacc": 0.8940217391304348, "bacc_std": 0.040916340366257} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 55, "C": 166.81005372000556, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.04787558255477081, "f1": 0.8505434782608696, "f1_std": 0.04963339726106, "bacc": 0.8505434782608696, "bacc_std": 0.04997861034906628} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 56, "C": 166.81005372000556, "split": "test", "acc": 0.7636363636363637, "acc_std": 0.056354615113831615, "f1": 0.7607895617263298, "f1_std": 0.05677721801852059, "bacc": 0.7663043478260869, "bacc_std": 0.056431791982622} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 57, "C": 0.046415888336127774, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.04124506882621653, "f1": 0.8879076086956521, "f1_std": 0.04268247505691516, "bacc": 0.8879076086956521, "bacc_std": 0.04315086987064224} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 58, "C": 0.046415888336127774, "split": "test", "acc": 0.7818181818181819, "acc_std": 0.054780330668034234, "f1": 0.7782258064516129, "f1_std": 0.05542516571248587, "bacc": 0.7819293478260869, "bacc_std": 0.05514285631035653} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 59, "C": 0.046415888336127774, "split": "test", "acc": 0.9272727272727272, "acc_std": 0.033619435543759395, "f1": 0.9252717391304348, "f1_std": 0.034638595839659024, "bacc": 0.9252717391304348, "bacc_std": 0.03489629992152492} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 60, "C": 21.54434690031882, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.044053326062739935, "f1": 0.8639095086603039, "f1_std": 0.049660810837759306, "bacc": 0.8539402173913043, "bacc_std": 0.049996867443813264} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 61, "C": 21.54434690031882, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.03846585262517677, "f1": 0.905982905982906, "f1_std": 0.040074767712279684, "bacc": 0.9035326086956521, "bacc_std": 0.040625529183517216} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 62, "C": 21.54434690031882, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.04169022320333392, "f1": 0.8891129032258065, "f1_std": 0.04219508350419092, "bacc": 0.8940217391304348, "bacc_std": 0.04135390378527929} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 63, "C": 2.782559402207126, "split": "test", "acc": 0.9272727272727272, "acc_std": 0.034736619399025115, "f1": 0.9260752688172043, "f1_std": 0.03507527277779534, "bacc": 0.9313858695652174, "bacc_std": 0.033532405110896335} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 64, "C": 2.782559402207126, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.045488801637108035, "f1": 0.8521505376344086, "f1_std": 0.04602301669518236, "bacc": 0.8566576086956521, "bacc_std": 0.04568442060764806} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 65, "C": 0.005994842503189409, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.04128104041228444, "f1": 0.884453781512605, "f1_std": 0.045399466625611846, "bacc": 0.8756793478260869, "bacc_std": 0.046531901631378686} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 66, "C": 0.005994842503189409, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.040596804010510086, "f1": 0.8863636363636364, "f1_std": 0.04310093338095725, "bacc": 0.8817934782608696, "bacc_std": 0.044082655534378436} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 67, "C": 166.81005372000556, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.046448763205340395, "f1": 0.8699763593380614, "f1_std": 0.047383114918081656, "bacc": 0.8722826086956521, "bacc_std": 0.04723272731169107} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 68, "C": 21.54434690031882, "split": "test", "acc": 0.9454545454545454, "acc_std": 0.030573558499769758, "f1": 0.9435897435897436, "f1_std": 0.0319108676947168, "bacc": 0.9408967391304348, "bacc_std": 0.03324967450996044} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 69, "C": 0.3593813663804626, "split": "test", "acc": 0.9454545454545454, "acc_std": 0.02989648255934949, "f1": 0.9427282193682749, "f1_std": 0.032548341587280594, "bacc": 0.9347826086956521, "bacc_std": 0.0357457943644396} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 70, "C": 21.54434690031882, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.03886658680985423, "f1": 0.9079959852793577, "f1_std": 0.03899311766480679, "bacc": 0.9157608695652174, "bacc_std": 0.036588729397995116} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 71, "C": 21.54434690031882, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.03686022739534259, "f1": 0.9045470322804582, "f1_std": 0.03982235757275534, "bacc": 0.8974184782608696, "bacc_std": 0.04153402361652718} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 72, "C": 0.046415888336127774, "split": "test", "acc": 0.9454545454545454, "acc_std": 0.02962072091354323, "f1": 0.9435897435897436, "f1_std": 0.030902111914584772, "bacc": 0.9408967391304348, "bacc_std": 0.032219871006114204} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 73, "C": 2.782559402207126, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.036331185520463195, "f1": 0.9027925061859314, "f1_std": 0.04121927995550777, "bacc": 0.8913043478260869, "bacc_std": 0.0434394609483799} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 74, "C": 0.005994842503189409, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.03945050670572994, "f1": 0.905982905982906, "f1_std": 0.04122527157904843, "bacc": 0.9035326086956521, "bacc_std": 0.04222734334658748} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 75, "C": 166.81005372000556, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.041597838468954804, "f1": 0.8891129032258065, "f1_std": 0.04215949422052935, "bacc": 0.8940217391304348, "bacc_std": 0.04142841501567792} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 76, "C": 0.3593813663804626, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.046553919684775485, "f1": 0.8484848484848485, "f1_std": 0.04941138648926772, "bacc": 0.8444293478260869, "bacc_std": 0.04991745749056916} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 77, "C": 0.005994842503189409, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.044139882829458736, "f1": 0.8663658451926415, "f1_std": 0.0476039804206764, "bacc": 0.8600543478260869, "bacc_std": 0.04839657074266412} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 78, "C": 21.54434690031882, "split": "test", "acc": 0.9818181818181818, "acc_std": 0.01883903105016527, "f1": 0.9814251941911516, "f1_std": 0.019066884938430423, "bacc": 0.984375, "bacc_std": 0.01618979230873577} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 79, "C": 0.046415888336127774, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.045105569464249234, "f1": 0.84593837535014, "f1_std": 0.050093208500207674, "bacc": 0.8383152173913043, "bacc_std": 0.050276206672083} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 80, "C": 0.3593813663804626, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.04464121802894089, "f1": 0.8683760683760684, "f1_std": 0.04696701906892495, "bacc": 0.8661684782608696, "bacc_std": 0.04780974577238351} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 81, "C": 21.54434690031882, "split": "test", "acc": 0.9272727272727272, "acc_std": 0.034875059169356494, "f1": 0.9252717391304348, "f1_std": 0.03589818645711236, "bacc": 0.9252717391304348, "bacc_std": 0.03620616381018178} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 82, "C": 0.046415888336127774, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.04653492778690249, "f1": 0.8484848484848485, "f1_std": 0.04903107653919976, "bacc": 0.8444293478260869, "bacc_std": 0.04936787794327687} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 83, "C": 0.3593813663804626, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.04014603095765374, "f1": 0.884453781512605, "f1_std": 0.044364390932058476, "bacc": 0.8756793478260869, "bacc_std": 0.045471895333560185} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 84, "C": 2.782559402207126, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.05020816172827113, "f1": 0.8505434782608696, "f1_std": 0.05183679018770084, "bacc": 0.8505434782608696, "bacc_std": 0.0521805451089413} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 85, "C": 0.3593813663804626, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.04765001886170307, "f1": 0.8505434782608696, "f1_std": 0.04920292601685931, "bacc": 0.8505434782608696, "bacc_std": 0.04980726447357592} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 86, "C": 21.54434690031882, "split": "test", "acc": 0.9272727272727272, "acc_std": 0.0365757269463355, "f1": 0.9260752688172043, "f1_std": 0.036935229229283315, "bacc": 0.9313858695652174, "bacc_std": 0.03528066854546726} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 87, "C": 1291.5496650148827, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.04153898895382247, "f1": 0.8863636363636364, "f1_std": 0.0440347025282356, "bacc": 0.8817934782608696, "bacc_std": 0.04506279700630213} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 88, "C": 0.3593813663804626, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.044798229008679, "f1": 0.8663658451926415, "f1_std": 0.047953512287876456, "bacc": 0.8600543478260869, "bacc_std": 0.0488395057672689} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 89, "C": 21.54434690031882, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.03940266383577856, "f1": 0.884453781512605, "f1_std": 0.04362209950132576, "bacc": 0.8756793478260869, "bacc_std": 0.04497025005347213} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 90, "C": 166.81005372000556, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.049123813888063375, "f1": 0.8328267477203647, "f1_std": 0.05033269190867406, "bacc": 0.8349184782608696, "bacc_std": 0.050497531199011896} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 91, "C": 0.046415888336127774, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.04737436625974425, "f1": 0.8505434782608696, "f1_std": 0.04873123781760968, "bacc": 0.8505434782608696, "bacc_std": 0.04864910134557515} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 92, "C": 0.005994842503189409, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.04182448964284319, "f1": 0.8863636363636364, "f1_std": 0.04433174394875053, "bacc": 0.8817934782608696, "bacc_std": 0.04525097274774546} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 93, "C": 0.046415888336127774, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.03702132510319822, "f1": 0.9027925061859314, "f1_std": 0.042028994844589294, "bacc": 0.8913043478260869, "bacc_std": 0.04426462784078048} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 94, "C": 21.54434690031882, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.03843035989921863, "f1": 0.9071259709557582, "f1_std": 0.03908424166822591, "bacc": 0.9096467391304348, "bacc_std": 0.03823445610859572} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 95, "C": 0.046415888336127774, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.03883042174497416, "f1": 0.905982905982906, "f1_std": 0.04056979512695986, "bacc": 0.9035326086956521, "bacc_std": 0.04125093735956661} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 96, "C": 21.54434690031882, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.03713466225100032, "f1": 0.905982905982906, "f1_std": 0.03855940962600297, "bacc": 0.9035326086956521, "bacc_std": 0.039049423874718374} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 97, "C": 0.3593813663804626, "split": "test", "acc": 0.8181818181818182, "acc_std": 0.04996171757596503, "f1": 0.8131793478260869, "f1_std": 0.05163064405612378, "bacc": 0.8131793478260869, "bacc_std": 0.051966617245606084} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 98, "C": 0.005994842503189409, "split": "test", "acc": 0.8181818181818182, "acc_std": 0.047015510013379405, "f1": 0.8035714285714286, "f1_std": 0.053323606163455065, "bacc": 0.7948369565217391, "bacc_std": 0.05206232646621422} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 99, "C": 166.81005372000556, "split": "test", "acc": 0.9454545454545454, "acc_std": 0.03090889839512241, "f1": 0.9447975911676145, "f1_std": 0.030909590464159684, "bacc": 0.953125, "bacc_std": 0.026562334558308313} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 100, "C": 0.3593813663804626, "split": "test", "acc": 0.9272727272727272, "acc_std": 0.036138557966538, "f1": 0.9260752688172043, "f1_std": 0.036452112110364754, "bacc": 0.9313858695652174, "bacc_std": 0.034424556669653335} +eval results (random splits): + +| model | repr | clf | dataset | split | n_trials | C | C_std | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|-----------:|-------:|--------:|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | aabc_sex | train | 100 | 34.377 | 136.24 | 0.97412 | 0.035931 | 0.97334 | 0.03709 | 0.97287 | 0.038038 | +| flat_mae | patch | logistic | aabc_sex | test | 100 | 34.377 | 136.24 | 0.88145 | 0.042658 | 0.87731 | 0.043954 | 0.87593 | 0.044421 | + + +done! total time: 0:05:55 diff --git a/input_space_v3/flat_lr1e-3_5/eval_v2/abide_dx__patch__logistic/config.yaml b/input_space_v3/flat_lr1e-3_5/eval_v2/abide_dx__patch__logistic/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..f565d52c2af9da3ef3e641b481b141ae05bd109f --- /dev/null +++ b/input_space_v3/flat_lr1e-3_5/eval_v2/abide_dx__patch__logistic/config.yaml @@ -0,0 +1,30 @@ +output_root: experiments/input_space_v3/output +name_prefix: eval_logistic +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_5; eval v2 (abide_dx patch logistic) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: input_space_v3/flat_lr1e-3_5/eval_v2/abide_dx__patch__logistic +model: flat_mae +representation: patch +dataset: abide_dx +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/eval_v2/abide_dx__patch__logistic +remote_dir: null diff --git a/input_space_v3/flat_lr1e-3_5/eval_v2/abide_dx__patch__logistic/eval_table.csv b/input_space_v3/flat_lr1e-3_5/eval_v2/abide_dx__patch__logistic/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..9e08413c2b2aef312700295344850c335e0d727b --- /dev/null +++ b/input_space_v3/flat_lr1e-3_5/eval_v2/abide_dx__patch__logistic/eval_table.csv @@ -0,0 +1,203 @@ +model,repr,clf,dataset,trial,C,split,acc,acc_std,f1,f1_std,bacc,bacc_std +flat_mae,patch,logistic,abide_dx,,0.3593813663804626,train,0.8846153846153846,0.01201680087287453,0.8829795334574977,0.012220170913085408,0.8819521964672664,0.012322745882785497 +flat_mae,patch,logistic,abide_dx,,0.3593813663804626,test,0.6209677419354839,0.04303731169242239,0.6153389215233318,0.04410794058012374,0.6152134066509558,0.04354022269921347 +flat_mae,patch,logistic,abide_dx,1,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,1,21.54434690031882,test,0.5483870967741935,0.043268106409433564,0.5482695810564664,0.04346503766267118,0.5551470588235294,0.04363571369856811 +flat_mae,patch,logistic,abide_dx,2,0.3593813663804626,train,0.9002849002849003,0.011532339834339394,0.898905529953917,0.011724651524185045,0.8977482465854558,0.011822247213574959 +flat_mae,patch,logistic,abide_dx,2,0.3593813663804626,test,0.6612903225806451,0.043215802886753384,0.6569169960474308,0.04397150772894741,0.6565126050420168,0.043746451869701636 +flat_mae,patch,logistic,abide_dx,3,0.3593813663804626,train,0.8817663817663818,0.01239398628430153,0.8802498340399907,0.012587698409493505,0.8794758213362864,0.0126957383106655 +flat_mae,patch,logistic,abide_dx,3,0.3593813663804626,test,0.6612903225806451,0.041477884858827155,0.6569169960474308,0.04196653889925515,0.6565126050420168,0.04181739616875048 +flat_mae,patch,logistic,abide_dx,4,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,4,166.81005372000556,test,0.6290322580645161,0.04164370890248665,0.6266038229903116,0.04179672223315922,0.6271008403361344,0.04195846289310614 +flat_mae,patch,logistic,abide_dx,5,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,5,1291.5496650148827,test,0.6209677419354839,0.041056153014038886,0.6197559861681998,0.041074846569783954,0.6213235294117647,0.04102801724503678 +flat_mae,patch,logistic,abide_dx,6,2.782559402207126,train,0.9843304843304843,0.004883908067823471,0.9841396662387677,0.004951702621757582,0.9834256183093393,0.005167489727710115 +flat_mae,patch,logistic,abide_dx,6,2.782559402207126,test,0.6370967741935484,0.042499543977476316,0.6365057650967364,0.04255336896340709,0.6391806722689075,0.042542106857462535 +flat_mae,patch,logistic,abide_dx,7,0.046415888336127774,train,0.8076923076923077,0.014705799870568057,0.8044055700142201,0.015067720119444511,0.8028423772609818,0.015137020626537547 +flat_mae,patch,logistic,abide_dx,7,0.046415888336127774,test,0.6451612903225806,0.03837185926909079,0.6288435374149659,0.041277816415308526,0.6307773109243697,0.03911836760826682 +flat_mae,patch,logistic,abide_dx,8,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,8,21.54434690031882,test,0.6532258064516129,0.04282001085783053,0.6526610644257702,0.042842699232630094,0.6554621848739496,0.04285125361167494 +flat_mae,patch,logistic,abide_dx,9,0.3593813663804626,train,0.8903133903133903,0.011881877646402852,0.8886813474223556,0.012105742418306639,0.8872277593207826,0.012221569650182357 +flat_mae,patch,logistic,abide_dx,9,0.3593813663804626,test,0.6935483870967742,0.039435401411616416,0.6835885038947085,0.04179682753117038,0.6827731092436975,0.040515396315985094 +flat_mae,patch,logistic,abide_dx,10,0.3593813663804626,train,0.8974358974358975,0.011304462761263488,0.8959460460979767,0.011529211869383894,0.8945736434108527,0.011700611908803648 +flat_mae,patch,logistic,abide_dx,10,0.3593813663804626,test,0.5725806451612904,0.04648648724476782,0.5678306043269548,0.047121159628630296,0.5677521008403361,0.046968948575400134 +flat_mae,patch,logistic,abide_dx,11,0.3593813663804626,train,0.8988603988603988,0.011204081783366798,0.8977547566541875,0.011325060141238595,0.8976375046142488,0.011356166370378533 +flat_mae,patch,logistic,abide_dx,11,0.3593813663804626,test,0.5725806451612904,0.045961445522369325,0.5718845677806006,0.04592478013512361,0.5740546218487395,0.045843954633754715 +flat_mae,patch,logistic,abide_dx,12,0.046415888336127774,train,0.8105413105413105,0.01478302830371789,0.8066968528145788,0.015215678405741763,0.8045404208194906,0.015188060727460043 +flat_mae,patch,logistic,abide_dx,12,0.046415888336127774,test,0.5725806451612904,0.04581711597804107,0.5691904293674206,0.04628331217384462,0.569327731092437,0.04616799352152163 +flat_mae,patch,logistic,abide_dx,13,0.3593813663804626,train,0.896011396011396,0.011042473366514325,0.8946082514298406,0.011226640160415875,0.893576965669989,0.011333457629711458 +flat_mae,patch,logistic,abide_dx,13,0.3593813663804626,test,0.6612903225806451,0.04269343261375774,0.6590730557737627,0.04289569654292875,0.6596638655462186,0.04281592075187539 +flat_mae,patch,logistic,abide_dx,14,0.3593813663804626,train,0.9017094017094017,0.011054622643047587,0.9003158988712018,0.011249187742432413,0.8990402362495387,0.011372911817429061 +flat_mae,patch,logistic,abide_dx,14,0.3593813663804626,test,0.6209677419354839,0.03939607833977373,0.5990368077055384,0.04286855218335484,0.6039915966386554,0.04012957296782566 +flat_mae,patch,logistic,abide_dx,15,0.046415888336127774,train,0.8034188034188035,0.014163762291105525,0.8001336898395722,0.01453597355427858,0.7986710963455149,0.014586567416749213 +flat_mae,patch,logistic,abide_dx,15,0.046415888336127774,test,0.5967741935483871,0.04203276557513032,0.5836690840719849,0.04472495788020216,0.5850840336134454,0.04301764280305291 +flat_mae,patch,logistic,abide_dx,16,0.046415888336127774,train,0.8105413105413105,0.014655614038060875,0.8073032652732688,0.014999317372680362,0.8057216685123662,0.01504366286187115 +flat_mae,patch,logistic,abide_dx,16,0.046415888336127774,test,0.5806451612903226,0.04293292690090994,0.5716183895827798,0.04383281041564535,0.571953781512605,0.043146630467546215 +flat_mae,patch,logistic,abide_dx,17,0.046415888336127774,train,0.8005698005698005,0.013861364793893844,0.7964391347213362,0.01428630114422549,0.7943152454780362,0.01427042707101354 +flat_mae,patch,logistic,abide_dx,17,0.046415888336127774,test,0.6209677419354839,0.042860307784133744,0.6167554415729598,0.043377580273204,0.6165966386554622,0.04329173745583712 +flat_mae,patch,logistic,abide_dx,18,0.3593813663804626,train,0.8888888888888888,0.012002884843562406,0.8871149960829589,0.012280016290980942,0.8853451458102621,0.0124456390923273 +flat_mae,patch,logistic,abide_dx,18,0.3593813663804626,test,0.6774193548387096,0.042749737571533275,0.6732542819499341,0.043412531003126836,0.6727941176470589,0.043122574332385526 +flat_mae,patch,logistic,abide_dx,19,0.046415888336127774,train,0.8162393162393162,0.013945792991653575,0.8123550827491748,0.014352331611286101,0.8100036913990403,0.014333418908623118 +flat_mae,patch,logistic,abide_dx,19,0.046415888336127774,test,0.5806451612903226,0.04128510551718424,0.5643243243243243,0.0440425365500571,0.5672268907563025,0.042171630338420585 +flat_mae,patch,logistic,abide_dx,20,0.046415888336127774,train,0.7934472934472935,0.014998105685804036,0.7897574123989218,0.015419682348381668,0.7881506090808417,0.015457578682287981 +flat_mae,patch,logistic,abide_dx,20,0.046415888336127774,test,0.6370967741935484,0.040820550923909994,0.6241664982824813,0.042799088699076115,0.625,0.0414634687526891 +flat_mae,patch,logistic,abide_dx,21,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,21,1291.5496650148827,test,0.532258064516129,0.04537706517288745,0.5317708333333333,0.04547020356594052,0.5341386554621849,0.0456669935392154 +flat_mae,patch,logistic,abide_dx,22,0.046415888336127774,train,0.8091168091168092,0.01423912442340669,0.8059269162210339,0.014535631256795268,0.8044296788482834,0.014539730837624446 +flat_mae,patch,logistic,abide_dx,22,0.046415888336127774,test,0.6532258064516129,0.04167064011577802,0.6408702094699266,0.044298232607423264,0.641281512605042,0.042725902973927934 +flat_mae,patch,logistic,abide_dx,23,0.046415888336127774,train,0.8062678062678063,0.015462731668394729,0.8028822727835818,0.015775939441501234,0.8012550756736803,0.015749812334855066 +flat_mae,patch,logistic,abide_dx,23,0.046415888336127774,test,0.6451612903225806,0.04173401979091432,0.6336287939833467,0.04429600954967696,0.6339285714285714,0.042854801694993394 +flat_mae,patch,logistic,abide_dx,24,0.046415888336127774,train,0.8247863247863247,0.014003921033179833,0.8216562877590854,0.014319019210936201,0.8198228128460687,0.014330202223111602 +flat_mae,patch,logistic,abide_dx,24,0.046415888336127774,test,0.6209677419354839,0.04276627122177429,0.6137071651090342,0.04374161739563067,0.6134453781512605,0.04315938514078809 +flat_mae,patch,logistic,abide_dx,25,0.3593813663804626,train,0.9031339031339032,0.011592499819334301,0.9015151515151515,0.011842732224461914,0.8994462901439646,0.011973094657538564 +flat_mae,patch,logistic,abide_dx,25,0.3593813663804626,test,0.6048387096774194,0.043722861361296404,0.6035753898349319,0.04400170756696923,0.6050420168067226,0.04401404997277175 +flat_mae,patch,logistic,abide_dx,26,0.046415888336127774,train,0.7991452991452992,0.014027182342350451,0.7958641569203293,0.014298781265952534,0.794499815430048,0.01430289047748225 +flat_mae,patch,logistic,abide_dx,26,0.046415888336127774,test,0.6129032258064516,0.04215210490557812,0.5951020408163266,0.04529904697569786,0.5982142857142857,0.042923882630261825 +flat_mae,patch,logistic,abide_dx,27,0.3593813663804626,train,0.8917378917378918,0.011902404241457092,0.8903134020279438,0.012087453835609713,0.889405684754522,0.012169703896712047 +flat_mae,patch,logistic,abide_dx,27,0.3593813663804626,test,0.6209677419354839,0.04517076801470727,0.6179613241560145,0.045492634381514414,0.618172268907563,0.04543967166900425 +flat_mae,patch,logistic,abide_dx,28,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,28,1291.5496650148827,test,0.6370967741935484,0.043395490254191905,0.6330637206549615,0.04389294232132652,0.6328781512605042,0.04375373116535861 +flat_mae,patch,logistic,abide_dx,29,0.046415888336127774,train,0.7948717948717948,0.015243952021373105,0.7911266860618884,0.01554590080720081,0.7894425987449243,0.015464616026537696 +flat_mae,patch,logistic,abide_dx,29,0.046415888336127774,test,0.717741935483871,0.04104582348291016,0.7135502607088642,0.04183136815066794,0.7127100840336134,0.04161633651839809 +flat_mae,patch,logistic,abide_dx,30,0.3593813663804626,train,0.8931623931623932,0.011621507973125483,0.891417104744856,0.011877106003791235,0.8895164267257291,0.012010844281954303 +flat_mae,patch,logistic,abide_dx,30,0.3593813663804626,test,0.7258064516129032,0.03852914893139649,0.7211640211640211,0.03956873674738482,0.720063025210084,0.03919180203008043 +flat_mae,patch,logistic,abide_dx,31,0.046415888336127774,train,0.8062678062678063,0.015361811473361032,0.802089552238806,0.015846437583174364,0.7997785160575859,0.01582646015816783 +flat_mae,patch,logistic,abide_dx,31,0.046415888336127774,test,0.5967741935483871,0.04577769144833791,0.5915678524374176,0.046424042404320943,0.5913865546218487,0.04614485999488417 +flat_mae,patch,logistic,abide_dx,32,0.3593813663804626,train,0.896011396011396,0.011303362702876919,0.8944641345692461,0.011520318151356762,0.8929863418235511,0.011658185597537033 +flat_mae,patch,logistic,abide_dx,32,0.3593813663804626,test,0.6290322580645161,0.04309229501544598,0.6227513227513227,0.04339083340792182,0.6223739495798319,0.0429626310305366 +flat_mae,patch,logistic,abide_dx,33,0.005994842503189409,train,0.7293447293447294,0.016132935912967175,0.7211979832944541,0.016875704627503693,0.7193798449612403,0.016580589888668527 +flat_mae,patch,logistic,abide_dx,33,0.005994842503189409,test,0.5645161290322581,0.043717128278178786,0.555142173797502,0.04535167182300192,0.555672268907563,0.04453188603857468 +flat_mae,patch,logistic,abide_dx,34,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,34,21.54434690031882,test,0.6612903225806451,0.03922738483666518,0.6604954367666231,0.039337178615939085,0.6628151260504203,0.0393826274385554 +flat_mae,patch,logistic,abide_dx,35,0.046415888336127774,train,0.8076923076923077,0.014780910964281547,0.8042569011989962,0.015186544662199387,0.802547065337763,0.015246217165232528 +flat_mae,patch,logistic,abide_dx,35,0.046415888336127774,test,0.6693548387096774,0.04377026808652519,0.667603792088918,0.043957674196486274,0.66859243697479,0.043879437372669326 +flat_mae,patch,logistic,abide_dx,36,0.3593813663804626,train,0.886039886039886,0.011369579032470354,0.8842205088030347,0.011585604326377657,0.8824658545588778,0.011668789502999152 +flat_mae,patch,logistic,abide_dx,36,0.3593813663804626,test,0.5806451612903226,0.043399563504520816,0.5670158474348643,0.045842206156709045,0.5688025210084033,0.04429278725180169 +flat_mae,patch,logistic,abide_dx,37,0.046415888336127774,train,0.811965811965812,0.014114921346520818,0.808532795556731,0.014478105126857021,0.8067183462532299,0.014510913620021864 +flat_mae,patch,logistic,abide_dx,37,0.046415888336127774,test,0.6209677419354839,0.042511245987148054,0.6137071651090342,0.043970851432391836,0.6134453781512605,0.04346932878651812 +flat_mae,patch,logistic,abide_dx,38,0.3593813663804626,train,0.8988603988603988,0.010808746973084178,0.897628754813864,0.01094602283805296,0.8970468807678109,0.010976477942027345 +flat_mae,patch,logistic,abide_dx,38,0.3593813663804626,test,0.6048387096774194,0.044287738100944087,0.6035753898349319,0.04450256421413519,0.6050420168067226,0.04479420379847532 +flat_mae,patch,logistic,abide_dx,39,0.046415888336127774,train,0.8062678062678063,0.014451707294815886,0.8033159733667348,0.014707484198990506,0.8021410114433369,0.014706225060173241 +flat_mae,patch,logistic,abide_dx,39,0.046415888336127774,test,0.5887096774193549,0.04393876402894441,0.5788211788211788,0.044986039881547576,0.5793067226890757,0.04422173215994966 +flat_mae,patch,logistic,abide_dx,40,0.046415888336127774,train,0.7977207977207977,0.01483610649479407,0.7940277043110289,0.015200568597040963,0.7923218899963086,0.0151772705194359 +flat_mae,patch,logistic,abide_dx,40,0.046415888336127774,test,0.6129032258064516,0.04134024200147955,0.588836695219674,0.04605552260645633,0.595063025210084,0.0425075871675899 +flat_mae,patch,logistic,abide_dx,41,0.3593813663804626,train,0.8931623931623932,0.011565774012731156,0.8917208062635349,0.011762506631160363,0.8906976744186046,0.011896193434825337 +flat_mae,patch,logistic,abide_dx,41,0.3593813663804626,test,0.5967741935483871,0.043732418795375,0.5915678524374176,0.04426551133662506,0.5913865546218487,0.04381954623234574 +flat_mae,patch,logistic,abide_dx,42,0.046415888336127774,train,0.8005698005698005,0.015131149347852207,0.7962686567164179,0.015550994495368755,0.7940199335548173,0.015496851613396024 +flat_mae,patch,logistic,abide_dx,42,0.046415888336127774,test,0.6129032258064516,0.04155062544060826,0.610369206598586,0.04185262308751665,0.6108193277310925,0.041893286650882815 +flat_mae,patch,logistic,abide_dx,43,0.3593813663804626,train,0.8831908831908832,0.011744976148825827,0.8817307692307692,0.011928126766762526,0.8810631229235881,0.012052832517880207 +flat_mae,patch,logistic,abide_dx,43,0.3593813663804626,test,0.6129032258064516,0.04179523383449262,0.607905138339921,0.04238464617398716,0.6076680672268908,0.042129831949010946 +flat_mae,patch,logistic,abide_dx,44,0.046415888336127774,train,0.8091168091168092,0.014439462325720687,0.8054790441450159,0.014811503587496689,0.8035437430786267,0.014811020511323322 +flat_mae,patch,logistic,abide_dx,44,0.046415888336127774,test,0.5403225806451613,0.04251331431281925,0.5292707292707293,0.04381722872432997,0.5304621848739496,0.04292924370455228 +flat_mae,patch,logistic,abide_dx,45,0.3593813663804626,train,0.8760683760683761,0.011921848418773548,0.874135212835018,0.012168443654413288,0.8725359911406423,0.01229363274198852 +flat_mae,patch,logistic,abide_dx,45,0.3593813663804626,test,0.6451612903225806,0.04365702995289547,0.6356837606837606,0.04511426767393476,0.6355042016806722,0.04417298793694698 +flat_mae,patch,logistic,abide_dx,46,0.046415888336127774,train,0.8034188034188035,0.015389514889348407,0.8008322299981085,0.01562209203444437,0.8001476559616094,0.015656269189825288 +flat_mae,patch,logistic,abide_dx,46,0.046415888336127774,test,0.532258064516129,0.04387171192442827,0.5311603650586701,0.04398909192283896,0.532563025210084,0.044241959762613914 +flat_mae,patch,logistic,abide_dx,47,0.3593813663804626,train,0.8888888888888888,0.011681375850689985,0.8874269126076266,0.011865796373868876,0.8865263935031378,0.011960682553484083 +flat_mae,patch,logistic,abide_dx,47,0.3593813663804626,test,0.6370967741935484,0.041284888125233024,0.6317074780542539,0.04182356013800314,0.6313025210084033,0.04151463644697558 +flat_mae,patch,logistic,abide_dx,48,0.046415888336127774,train,0.8048433048433048,0.014403787530312403,0.8015078747551716,0.014705469705783942,0.7999630860095976,0.014681170599222212 +flat_mae,patch,logistic,abide_dx,48,0.046415888336127774,test,0.6209677419354839,0.04369503087543244,0.6137071651090342,0.044667082243354396,0.6134453781512605,0.04410496129889271 +flat_mae,patch,logistic,abide_dx,49,0.3593813663804626,train,0.9045584045584045,0.011086062788156732,0.9029272088218723,0.011365304870620216,0.9007382798080472,0.011597902722105388 +flat_mae,patch,logistic,abide_dx,49,0.3593813663804626,test,0.6290322580645161,0.04284294516080831,0.6227513227513227,0.04378155650448326,0.6223739495798319,0.043413455796548324 +flat_mae,patch,logistic,abide_dx,50,0.3593813663804626,train,0.9002849002849003,0.010991234034024633,0.8988364337063663,0.011197199349895992,0.8974529346622371,0.011339410441259636 +flat_mae,patch,logistic,abide_dx,50,0.3593813663804626,test,0.5806451612903226,0.04542199806733209,0.5670158474348643,0.047662535394215076,0.5688025210084033,0.04609428470056079 +flat_mae,patch,logistic,abide_dx,51,0.3593813663804626,train,0.9116809116809117,0.010532397479241912,0.9105769230769231,0.010678387865847886,0.9098560354374308,0.010762446309210999 +flat_mae,patch,logistic,abide_dx,51,0.3593813663804626,test,0.5725806451612904,0.04432618135817845,0.5623043623043623,0.045990305966460664,0.5630252100840336,0.044935348929596025 +flat_mae,patch,logistic,abide_dx,52,0.046415888336127774,train,0.7977207977207977,0.015672680074160096,0.7937003311258278,0.016095039345814716,0.7917312661498708,0.016050726720785086 +flat_mae,patch,logistic,abide_dx,52,0.046415888336127774,test,0.6370967741935484,0.042930066791882146,0.6301451580831179,0.04395065649639746,0.6297268907563025,0.04340828288903001 +flat_mae,patch,logistic,abide_dx,53,0.046415888336127774,train,0.792022792022792,0.015369412135557385,0.7883883222529628,0.0157329647116344,0.786858619416759,0.01571416871982658 +flat_mae,patch,logistic,abide_dx,53,0.046415888336127774,test,0.6451612903225806,0.04236471091001416,0.6375232527238905,0.0433435079928184,0.6370798319327731,0.04275246054966052 +flat_mae,patch,logistic,abide_dx,54,0.3593813663804626,train,0.896011396011396,0.011188905468705015,0.8947450577663671,0.011336465563921051,0.8941675895164267,0.011385742413060942 +flat_mae,patch,logistic,abide_dx,54,0.3593813663804626,test,0.6693548387096774,0.04147035788037435,0.665680278818965,0.04203753434147787,0.6654411764705883,0.041902222645376415 +flat_mae,patch,logistic,abide_dx,55,0.046415888336127774,train,0.8176638176638177,0.01536100752777124,0.8140397350993378,0.015794658350321723,0.8118863049095607,0.015787818296857475 +flat_mae,patch,logistic,abide_dx,55,0.046415888336127774,test,0.5564516129032258,0.04528270258018686,0.5498646953996436,0.04601491852654321,0.5498949579831933,0.04564247272207431 +flat_mae,patch,logistic,abide_dx,56,0.3593813663804626,train,0.8831908831908832,0.011833956396974217,0.8813260215231106,0.012070087165151766,0.8795865633074935,0.012146198610850234 +flat_mae,patch,logistic,abide_dx,56,0.3593813663804626,test,0.7096774193548387,0.03912615671693408,0.7084639498432602,0.03919520903835374,0.7100840336134454,0.039172092959254654 +flat_mae,patch,logistic,abide_dx,57,0.3593813663804626,train,0.8931623931623932,0.011257103557316966,0.891792018710835,0.011413485558602915,0.8909929863418236,0.011458432833661238 +flat_mae,patch,logistic,abide_dx,57,0.3593813663804626,test,0.6854838709677419,0.04193621587450457,0.6819885579009667,0.04268715568545375,0.6817226890756303,0.04251873596567905 +flat_mae,patch,logistic,abide_dx,58,0.046415888336127774,train,0.7877492877492878,0.01455221209618088,0.78378970563005,0.014911053247182244,0.7820967146548542,0.014892755935964294 +flat_mae,patch,logistic,abide_dx,58,0.046415888336127774,test,0.6370967741935484,0.042201402544121046,0.6351748937561295,0.04259971583678637,0.6360294117647058,0.04272102214159372 +flat_mae,patch,logistic,abide_dx,59,0.046415888336127774,train,0.7877492877492878,0.0151833075601893,0.78378970563005,0.015552454532947249,0.7820967146548542,0.015540327340243531 +flat_mae,patch,logistic,abide_dx,59,0.046415888336127774,test,0.6693548387096774,0.044155575869112916,0.667603792088918,0.044247041175048324,0.66859243697479,0.04417321694080843 +flat_mae,patch,logistic,abide_dx,60,2.782559402207126,train,0.9857549857549858,0.0042092182797563915,0.9855860443342066,0.0042640034802242975,0.9850129198966409,0.00443219432944857 +flat_mae,patch,logistic,abide_dx,60,2.782559402207126,test,0.6129032258064516,0.043462831130821965,0.6063492063492064,0.04473027666839228,0.60609243697479,0.04425985657162603 +flat_mae,patch,logistic,abide_dx,61,0.3593813663804626,train,0.8974358974358975,0.01142876028070777,0.8961538461538461,0.011586126650524024,0.8954595791805093,0.011658239123943953 +flat_mae,patch,logistic,abide_dx,61,0.3593813663804626,test,0.6612903225806451,0.043661320113911925,0.6590730557737627,0.04389108393088674,0.6596638655462186,0.043879168312034804 +flat_mae,patch,logistic,abide_dx,62,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,62,21.54434690031882,test,0.532258064516129,0.04459336450828279,0.5303030303030303,0.044587377354163286,0.5309873949579832,0.0444801030277084 +flat_mae,patch,logistic,abide_dx,63,0.3593813663804626,train,0.8803418803418803,0.011955880765445839,0.8787674443466749,0.012125726252836639,0.8778885197489849,0.01216002798057137 +flat_mae,patch,logistic,abide_dx,63,0.3593813663804626,test,0.6370967741935484,0.042516750081126584,0.635936582501468,0.04288360875442909,0.6376050420168067,0.04319772420132801 +flat_mae,patch,logistic,abide_dx,64,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,64,21.54434690031882,test,0.5564516129032258,0.04336161861349872,0.5550336008351275,0.04339687421469905,0.5561974789915967,0.043467300699941265 +flat_mae,patch,logistic,abide_dx,65,0.3593813663804626,train,0.9045584045584045,0.011246279875968393,0.9032052931068191,0.011455991444436285,0.9019195275009229,0.011631568717094998 +flat_mae,patch,logistic,abide_dx,65,0.3593813663804626,test,0.6935483870967742,0.03950531781008419,0.6816216216216215,0.04229831395371728,0.6811974789915967,0.04068664974250473 +flat_mae,patch,logistic,abide_dx,66,0.046415888336127774,train,0.8034188034188035,0.014026199472323414,0.799983482677458,0.014372581321069949,0.7983757844222961,0.014396633423865608 +flat_mae,patch,logistic,abide_dx,66,0.046415888336127774,test,0.5967741935483871,0.045687746577226705,0.5950888192267503,0.045840383696708634,0.5961134453781513,0.045930838013793295 +flat_mae,patch,logistic,abide_dx,67,0.3593813663804626,train,0.896011396011396,0.011673259949518962,0.8945371103999671,0.011872456671443156,0.89328165374677,0.011983905502913509 +flat_mae,patch,logistic,abide_dx,67,0.3593813663804626,test,0.6612903225806451,0.042185640350965635,0.6590730557737627,0.0424930549130221,0.6596638655462186,0.042480774195510045 +flat_mae,patch,logistic,abide_dx,68,0.3593813663804626,train,0.8789173789173789,0.011690531442916237,0.8773642878722796,0.011879067911324932,0.8765965300849021,0.011985253008393919 +flat_mae,patch,logistic,abide_dx,68,0.3593813663804626,test,0.6854838709677419,0.041297391028044445,0.6819885579009667,0.041561564952387914,0.6817226890756303,0.041386512111802595 +flat_mae,patch,logistic,abide_dx,69,0.046415888336127774,train,0.801994301994302,0.015068087879474579,0.7974631521921877,0.01555721976367961,0.7950166112956811,0.015494731865645959 +flat_mae,patch,logistic,abide_dx,69,0.046415888336127774,test,0.6774193548387096,0.04318842871198004,0.671957671957672,0.04419107756478538,0.671218487394958,0.043732529916074146 +flat_mae,patch,logistic,abide_dx,70,0.046415888336127774,train,0.8034188034188035,0.014815597995954381,0.7996724484478523,0.015185295406603475,0.7977851605758582,0.015153638776605048 +flat_mae,patch,logistic,abide_dx,70,0.046415888336127774,test,0.6451612903225806,0.04393419009510947,0.6356837606837606,0.045537200066747344,0.6355042016806722,0.04455029846261225 +flat_mae,patch,logistic,abide_dx,71,0.046415888336127774,train,0.7891737891737892,0.014995276892141883,0.7849834437086092,0.015424442666938383,0.783093392395718,0.015404889200249733 +flat_mae,patch,logistic,abide_dx,71,0.046415888336127774,test,0.6935483870967742,0.04035627946681591,0.6869519000797236,0.04158723153026497,0.6859243697478992,0.041061380328572455 +flat_mae,patch,logistic,abide_dx,72,0.3593813663804626,train,0.896011396011396,0.01136112752086271,0.8944641345692461,0.011560963176161601,0.8929863418235511,0.011621576174143515 +flat_mae,patch,logistic,abide_dx,72,0.3593813663804626,test,0.5806451612903226,0.0450959319686917,0.5766806722689075,0.04521167785836012,0.5766806722689075,0.04506909838412064 +flat_mae,patch,logistic,abide_dx,73,0.3593813663804626,train,0.9017094017094017,0.011098502598499345,0.9003831417624522,0.011279212704816773,0.8993355481727574,0.011425241262341474 +flat_mae,patch,logistic,abide_dx,73,0.3593813663804626,test,0.6048387096774194,0.04217487502348546,0.5989703649924097,0.04287987199763131,0.5987394957983193,0.04253998521967229 +flat_mae,patch,logistic,abide_dx,74,0.3593813663804626,train,0.8931623931623932,0.011218089720092458,0.8917208062635349,0.01139155776266509,0.8906976744186046,0.011471475045026904 +flat_mae,patch,logistic,abide_dx,74,0.3593813663804626,test,0.6774193548387096,0.043164168258359906,0.6753076721654884,0.04339986758551995,0.6759453781512605,0.043291638871471284 +flat_mae,patch,logistic,abide_dx,75,0.046415888336127774,train,0.7948717948717948,0.015487128125379973,0.7917463247412486,0.01582957297818299,0.7906238464377999,0.015894688561734944 +flat_mae,patch,logistic,abide_dx,75,0.046415888336127774,test,0.7096774193548387,0.03954500261790291,0.7002417405318292,0.04161704343084888,0.6990546218487395,0.04057893023416495 +flat_mae,patch,logistic,abide_dx,76,0.046415888336127774,train,0.8105413105413105,0.014425431554834611,0.8071567989590112,0.014859731907295618,0.8054263565891473,0.014945442324776534 +flat_mae,patch,logistic,abide_dx,76,0.046415888336127774,test,0.6048387096774194,0.04288161898317396,0.5880957223239103,0.04533730738000938,0.5908613445378151,0.04346326507255579 +flat_mae,patch,logistic,abide_dx,77,0.3593813663804626,train,0.8817663817663818,0.011609698495091187,0.8797456467494835,0.011906450019723054,0.8777039497969731,0.012086769575993422 +flat_mae,patch,logistic,abide_dx,77,0.3593813663804626,test,0.5725806451612904,0.044130388113485096,0.5718845677806006,0.04417746123537055,0.5740546218487395,0.04415612192857203 +flat_mae,patch,logistic,abide_dx,78,0.046415888336127774,train,0.8076923076923077,0.014826089014962181,0.8046925716405453,0.01507906590508579,0.8034330011074197,0.015065317678104937 +flat_mae,patch,logistic,abide_dx,78,0.046415888336127774,test,0.5967741935483871,0.044515544643195515,0.58994708994709,0.045620791038690586,0.5898109243697479,0.045144571510113946 +flat_mae,patch,logistic,abide_dx,79,2.782559402207126,train,0.9857549857549858,0.004300461038817442,0.9855675528984137,0.004371238768347059,0.984422296050203,0.0047185046491914325 +flat_mae,patch,logistic,abide_dx,79,2.782559402207126,test,0.6129032258064516,0.04338177206803275,0.607905138339921,0.04435917172320687,0.6076680672268908,0.044054920831767784 +flat_mae,patch,logistic,abide_dx,80,0.3593813663804626,train,0.8760683760683761,0.01234393603007716,0.8744787417045685,0.012514701592852276,0.8737172388335179,0.01254309607041651 +flat_mae,patch,logistic,abide_dx,80,0.3593813663804626,test,0.7016129032258065,0.0395732437804769,0.6928021426180114,0.04123121574272059,0.6917016806722689,0.04030183047333079 +flat_mae,patch,logistic,abide_dx,81,0.3593813663804626,train,0.8888888888888888,0.012114829792454991,0.8872748832728081,0.01233895440464862,0.8859357696566998,0.012444889721342224 +flat_mae,patch,logistic,abide_dx,81,0.3593813663804626,test,0.6370967741935484,0.040825059508480414,0.6241664982824813,0.04317487222049394,0.625,0.041613094357198975 +flat_mae,patch,logistic,abide_dx,82,2.782559402207126,train,0.9871794871794872,0.004242144195080567,0.9870233632862644,0.004300790155657794,0.9863049095607235,0.004540255318750655 +flat_mae,patch,logistic,abide_dx,82,2.782559402207126,test,0.6048387096774194,0.04097399939511398,0.5953379953379954,0.04213878601167693,0.5955882352941176,0.04139830351673394 +flat_mae,patch,logistic,abide_dx,83,2.782559402207126,train,0.99002849002849,0.0037081761293674595,0.9899070603337612,0.003760940786778305,0.9891842008121078,0.004042407679818537 +flat_mae,patch,logistic,abide_dx,83,2.782559402207126,test,0.5483870967741935,0.045097639476677345,0.5483870967741935,0.04526958280609117,0.5535714285714286,0.04512684383985137 +flat_mae,patch,logistic,abide_dx,84,2.782559402207126,train,0.9843304843304843,0.004405719229465316,0.9841495630969315,0.004461073769578475,0.9837209302325581,0.004599828236867355 +flat_mae,patch,logistic,abide_dx,84,2.782559402207126,test,0.5806451612903226,0.044026302326746425,0.5778999738151349,0.044256210410751985,0.5782563025210083,0.0442241922113251 +flat_mae,patch,logistic,abide_dx,85,0.046415888336127774,train,0.801994301994302,0.014040045601638906,0.7979764100844094,0.014486132913036834,0.7959025470653378,0.0144848826475406 +flat_mae,patch,logistic,abide_dx,85,0.046415888336127774,test,0.6774193548387096,0.04140126225284723,0.6743697478991597,0.04183847093603445,0.6743697478991597,0.041774192019826406 +flat_mae,patch,logistic,abide_dx,86,0.3593813663804626,train,0.8974358974358975,0.011168046107240918,0.8960171165240289,0.011371818468774686,0.8948689553340716,0.011532490698583042 +flat_mae,patch,logistic,abide_dx,86,0.3593813663804626,test,0.6048387096774194,0.04235238181705396,0.5989703649924097,0.0429170030628922,0.5987394957983193,0.04261871935572771 +flat_mae,patch,logistic,abide_dx,87,0.046415888336127774,train,0.7977207977207977,0.0149511747199438,0.7940277043110289,0.01539106152754254,0.7923218899963086,0.015431457983622119 +flat_mae,patch,logistic,abide_dx,87,0.046415888336127774,test,0.6693548387096774,0.042301553588540486,0.6630211440312852,0.043582009002831726,0.6622899159663866,0.04310266111215358 +flat_mae,patch,logistic,abide_dx,88,0.046415888336127774,train,0.7934472934472935,0.01586629587043481,0.7899170937189772,0.01623666110378684,0.7884459210040606,0.016258481685721412 +flat_mae,patch,logistic,abide_dx,88,0.046415888336127774,test,0.6129032258064516,0.042911044036613395,0.607905138339921,0.04348853379417213,0.6076680672268908,0.043257082090020015 +flat_mae,patch,logistic,abide_dx,89,0.3593813663804626,train,0.8846153846153846,0.012059775889094067,0.8831353802077018,0.012251168071265982,0.8823551125876707,0.012373503509956436 +flat_mae,patch,logistic,abide_dx,89,0.3593813663804626,test,0.5967741935483871,0.04189718784877806,0.5958279009126467,0.04210599014265548,0.5976890756302521,0.04244277108836576 +flat_mae,patch,logistic,abide_dx,90,2.782559402207126,train,0.9814814814814815,0.005100062061443573,0.9812316064190127,0.00518367494962816,0.9799557032115171,0.005515595801946594 +flat_mae,patch,logistic,abide_dx,90,2.782559402207126,test,0.6209677419354839,0.04424179142191919,0.6137071651090342,0.04527210498386818,0.6134453781512605,0.04455121205033533 +flat_mae,patch,logistic,abide_dx,91,0.046415888336127774,train,0.8076923076923077,0.015448587845020177,0.8042569011989962,0.015795937377849054,0.802547065337763,0.01579114045211676 +flat_mae,patch,logistic,abide_dx,91,0.046415888336127774,test,0.5967741935483871,0.043304367103073,0.58994708994709,0.043923122767066065,0.5898109243697479,0.04351190145970663 +flat_mae,patch,logistic,abide_dx,92,0.046415888336127774,train,0.811965811965812,0.014329344684028954,0.808228476821192,0.014782183111532923,0.8061277224067922,0.014838468001864762 +flat_mae,patch,logistic,abide_dx,92,0.046415888336127774,test,0.6129032258064516,0.044473740922410764,0.6045708211533352,0.04571554664296464,0.6045168067226891,0.04492837833621383 +flat_mae,patch,logistic,abide_dx,93,0.046415888336127774,train,0.8048433048433048,0.014198544145618107,0.8008832243277992,0.014604980672422935,0.798781838316722,0.014599096705525472 +flat_mae,patch,logistic,abide_dx,93,0.046415888336127774,test,0.6048387096774194,0.04283905885497024,0.5989703649924097,0.04353366638182324,0.5987394957983193,0.043344788849647445 +flat_mae,patch,logistic,abide_dx,94,0.3593813663804626,train,0.9017094017094017,0.01149356959469372,0.9003158988712018,0.011726340776413532,0.8990402362495387,0.011922016452606378 +flat_mae,patch,logistic,abide_dx,94,0.3593813663804626,test,0.6612903225806451,0.03939651415777237,0.6580882352941176,0.040138218243220884,0.6580882352941176,0.04010188672543152 +flat_mae,patch,logistic,abide_dx,95,0.046415888336127774,train,0.7977207977207977,0.014850947335584758,0.7940277043110289,0.015160160366353842,0.7923218899963086,0.015101840780303686 +flat_mae,patch,logistic,abide_dx,95,0.046415888336127774,test,0.5806451612903226,0.041963080249884814,0.5581140350877193,0.0454844381259524,0.5640756302521008,0.04268796735021691 +flat_mae,patch,logistic,abide_dx,96,0.3593813663804626,train,0.9002849002849003,0.010763429827919098,0.8991644231400617,0.01089181383032844,0.8989294942783315,0.01095961021279814 +flat_mae,patch,logistic,abide_dx,96,0.3593813663804626,test,0.6048387096774194,0.04421966205170162,0.6004471624909581,0.04461186884832921,0.6003151260504203,0.04443249518160093 +flat_mae,patch,logistic,abide_dx,97,2.782559402207126,train,0.9829059829059829,0.005006076615264404,0.982703253201048,0.005073119413735086,0.9821336286452566,0.005278247378621139 +flat_mae,patch,logistic,abide_dx,97,2.782559402207126,test,0.6693548387096774,0.04217757355180597,0.6644445911160979,0.04312265694438706,0.6638655462184874,0.042947525531612865 +flat_mae,patch,logistic,abide_dx,98,0.046415888336127774,train,0.8176638176638177,0.014530980353065824,0.8141889376907616,0.014906519287473219,0.8121816168327796,0.014879346634355344 +flat_mae,patch,logistic,abide_dx,98,0.046415888336127774,test,0.6129032258064516,0.043739279941277916,0.5852842809364549,0.048677073542870423,0.5934873949579832,0.0447374348019143 +flat_mae,patch,logistic,abide_dx,99,0.046415888336127774,train,0.8005698005698005,0.014446584128737608,0.7967691505992704,0.01484666778075485,0.7949058693244739,0.014851646057378749 +flat_mae,patch,logistic,abide_dx,99,0.046415888336127774,test,0.5967741935483871,0.04240681465567031,0.5860042735042735,0.04438799076202749,0.5866596638655462,0.04324445696529544 +flat_mae,patch,logistic,abide_dx,100,0.046415888336127774,train,0.8005698005698005,0.015110102055578547,0.7966059602649007,0.015556606112886643,0.7946105574012551,0.015546699517803849 +flat_mae,patch,logistic,abide_dx,100,0.046415888336127774,test,0.7096774193548387,0.04099333719116655,0.7034281158650013,0.04219132831075011,0.7022058823529411,0.04171527697834944 diff --git a/input_space_v3/flat_lr1e-3_5/eval_v2/abide_dx__patch__logistic/log.txt b/input_space_v3/flat_lr1e-3_5/eval_v2/abide_dx__patch__logistic/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..b3b0b7f693f710e1f41472a4f39dca061e46dee9 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_5/eval_v2/abide_dx__patch__logistic/log.txt @@ -0,0 +1,252 @@ +fMRI foundation model logistic probe eval +version: 0.1.dev86+gf97f52698 +sha: bcce2b486277d3a5b520775efd9cdf1a2affce36, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-04-08 22:26:49 +config: +output_root: experiments/input_space_v3/output +name_prefix: eval_logistic +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_5; eval v2 (abide_dx patch logistic) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: input_space_v3/flat_lr1e-3_5/eval_v2/abide_dx__patch__logistic +model: flat_mae +representation: patch +dataset: abide_dx +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/eval_v2/abide_dx__patch__logistic +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=True, reg_tokens=0, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: abide_dx (flat) +train (n=578): +HFDataset( + dataset=Dataset({ + features: ['sub', 'site', 'dataset', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 578 +}), + labels=['Autism' 'Control'], + counts=[260 318] +) + +validation (n=124): +HFDataset( + dataset=Dataset({ + features: ['sub', 'site', 'dataset', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 124 +}), + labels=['Autism' 'Control'], + counts=[54 70] +) + +test (n=124): +HFDataset( + dataset=Dataset({ + features: ['sub', 'site', 'dataset', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 124 +}), + labels=['Autism' 'Control'], + counts=[57 67] +) + +extracting features for all splits +extract (train) [ 0/289] eta: 0:26:00 time: 5.4007 data: 4.2828 max mem: 2698 +extract (train) [ 20/289] eta: 0:02:11 time: 0.2415 data: 0.0875 max mem: 2851 +extract (train) [ 40/289] eta: 0:01:28 time: 0.2140 data: 0.0735 max mem: 2851 +extract (train) [ 60/289] eta: 0:01:09 time: 0.1972 data: 0.0656 max mem: 2851 +extract (train) [ 80/289] eta: 0:00:57 time: 0.1982 data: 0.0667 max mem: 2851 +extract (train) [100/289] eta: 0:00:48 time: 0.1796 data: 0.0572 max mem: 2851 +extract (train) [120/289] eta: 0:00:42 time: 0.2052 data: 0.0701 max mem: 2851 +extract (train) [140/289] eta: 0:00:36 time: 0.2089 data: 0.0736 max mem: 2851 +extract (train) [160/289] eta: 0:00:30 time: 0.2089 data: 0.0730 max mem: 2851 +extract (train) [180/289] eta: 0:00:25 time: 0.1890 data: 0.0636 max mem: 2851 +extract (train) [200/289] eta: 0:00:20 time: 0.2052 data: 0.0716 max mem: 2851 +extract (train) [220/289] eta: 0:00:15 time: 0.1838 data: 0.0604 max mem: 2851 +extract (train) [240/289] eta: 0:00:10 time: 0.1904 data: 0.0660 max mem: 2851 +extract (train) [260/289] eta: 0:00:06 time: 0.2215 data: 0.0788 max mem: 2851 +extract (train) [280/289] eta: 0:00:01 time: 0.1695 data: 0.0533 max mem: 2851 +extract (train) [288/289] eta: 0:00:00 time: 0.1702 data: 0.0540 max mem: 2851 +extract (train) Total time: 0:01:03 (0.2194 s / it) +extract (validation) [ 0/62] eta: 0:04:09 time: 4.0179 data: 3.8569 max mem: 2851 +extract (validation) [20/62] eta: 0:00:18 time: 0.2492 data: 0.0930 max mem: 2851 +extract (validation) [40/62] eta: 0:00:06 time: 0.1684 data: 0.0525 max mem: 2851 +extract (validation) [60/62] eta: 0:00:00 time: 0.1647 data: 0.0520 max mem: 2851 +extract (validation) [61/62] eta: 0:00:00 time: 0.1641 data: 0.0516 max mem: 2851 +extract (validation) Total time: 0:00:16 (0.2601 s / it) +extract (test) [ 0/62] eta: 0:04:01 time: 3.8934 data: 3.7231 max mem: 2851 +extract (test) [20/62] eta: 0:00:17 time: 0.2393 data: 0.0849 max mem: 2851 +extract (test) [40/62] eta: 0:00:06 time: 0.1818 data: 0.0593 max mem: 2851 +extract (test) [60/62] eta: 0:00:00 time: 0.1573 data: 0.0482 max mem: 2851 +extract (test) [61/62] eta: 0:00:00 time: 0.1579 data: 0.0481 max mem: 2851 +extract (test) Total time: 0:00:15 (0.2576 s / it) +feature extraction time: 0:01:35 +train features: (578, 768) +validation features: (124, 768) +test features: (124, 768) +evaluating fixed splits +eval results (fixed splits): + +| model | repr | clf | dataset | trial | C | split | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|--------:|:--------|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | abide_dx | | 0.35938 | train | 0.88462 | 0.012017 | 0.88298 | 0.01222 | 0.88195 | 0.012323 | +| flat_mae | patch | logistic | abide_dx | | 0.35938 | test | 0.62097 | 0.043037 | 0.61534 | 0.044108 | 0.61521 | 0.04354 | + + +evaluating random splits (n=100) +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 1, "C": 21.54434690031882, "split": "test", "acc": 0.5483870967741935, "acc_std": 0.043268106409433564, "f1": 0.5482695810564664, "f1_std": 0.04346503766267118, "bacc": 0.5551470588235294, "bacc_std": 0.04363571369856811} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 2, "C": 0.3593813663804626, "split": "test", "acc": 0.6612903225806451, "acc_std": 0.043215802886753384, "f1": 0.6569169960474308, "f1_std": 0.04397150772894741, "bacc": 0.6565126050420168, "bacc_std": 0.043746451869701636} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 3, "C": 0.3593813663804626, "split": "test", "acc": 0.6612903225806451, "acc_std": 0.041477884858827155, "f1": 0.6569169960474308, "f1_std": 0.04196653889925515, "bacc": 0.6565126050420168, "bacc_std": 0.04181739616875048} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 4, "C": 166.81005372000556, "split": "test", "acc": 0.6290322580645161, "acc_std": 0.04164370890248665, "f1": 0.6266038229903116, "f1_std": 0.04179672223315922, "bacc": 0.6271008403361344, "bacc_std": 0.04195846289310614} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 5, "C": 1291.5496650148827, "split": "test", "acc": 0.6209677419354839, "acc_std": 0.041056153014038886, "f1": 0.6197559861681998, "f1_std": 0.041074846569783954, "bacc": 0.6213235294117647, "bacc_std": 0.04102801724503678} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 6, "C": 2.782559402207126, "split": "test", "acc": 0.6370967741935484, "acc_std": 0.042499543977476316, "f1": 0.6365057650967364, "f1_std": 0.04255336896340709, "bacc": 0.6391806722689075, "bacc_std": 0.042542106857462535} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 7, "C": 0.046415888336127774, "split": "test", "acc": 0.6451612903225806, "acc_std": 0.03837185926909079, "f1": 0.6288435374149659, "f1_std": 0.041277816415308526, "bacc": 0.6307773109243697, "bacc_std": 0.03911836760826682} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 8, "C": 21.54434690031882, "split": "test", "acc": 0.6532258064516129, "acc_std": 0.04282001085783053, "f1": 0.6526610644257702, "f1_std": 0.042842699232630094, "bacc": 0.6554621848739496, "bacc_std": 0.04285125361167494} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 9, "C": 0.3593813663804626, "split": "test", "acc": 0.6935483870967742, "acc_std": 0.039435401411616416, "f1": 0.6835885038947085, "f1_std": 0.04179682753117038, "bacc": 0.6827731092436975, "bacc_std": 0.040515396315985094} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 10, "C": 0.3593813663804626, "split": "test", "acc": 0.5725806451612904, "acc_std": 0.04648648724476782, "f1": 0.5678306043269548, "f1_std": 0.047121159628630296, "bacc": 0.5677521008403361, "bacc_std": 0.046968948575400134} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 11, "C": 0.3593813663804626, "split": "test", "acc": 0.5725806451612904, "acc_std": 0.045961445522369325, "f1": 0.5718845677806006, "f1_std": 0.04592478013512361, "bacc": 0.5740546218487395, "bacc_std": 0.045843954633754715} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 12, "C": 0.046415888336127774, "split": "test", "acc": 0.5725806451612904, "acc_std": 0.04581711597804107, "f1": 0.5691904293674206, "f1_std": 0.04628331217384462, "bacc": 0.569327731092437, "bacc_std": 0.04616799352152163} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 13, "C": 0.3593813663804626, "split": "test", "acc": 0.6612903225806451, "acc_std": 0.04269343261375774, "f1": 0.6590730557737627, "f1_std": 0.04289569654292875, "bacc": 0.6596638655462186, "bacc_std": 0.04281592075187539} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 14, "C": 0.3593813663804626, "split": "test", "acc": 0.6209677419354839, "acc_std": 0.03939607833977373, "f1": 0.5990368077055384, "f1_std": 0.04286855218335484, "bacc": 0.6039915966386554, "bacc_std": 0.04012957296782566} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 15, "C": 0.046415888336127774, "split": "test", "acc": 0.5967741935483871, "acc_std": 0.04203276557513032, "f1": 0.5836690840719849, "f1_std": 0.04472495788020216, "bacc": 0.5850840336134454, "bacc_std": 0.04301764280305291} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 16, "C": 0.046415888336127774, "split": "test", "acc": 0.5806451612903226, "acc_std": 0.04293292690090994, "f1": 0.5716183895827798, "f1_std": 0.04383281041564535, "bacc": 0.571953781512605, "bacc_std": 0.043146630467546215} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 17, "C": 0.046415888336127774, "split": "test", "acc": 0.6209677419354839, "acc_std": 0.042860307784133744, "f1": 0.6167554415729598, "f1_std": 0.043377580273204, "bacc": 0.6165966386554622, "bacc_std": 0.04329173745583712} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 18, "C": 0.3593813663804626, "split": "test", "acc": 0.6774193548387096, "acc_std": 0.042749737571533275, "f1": 0.6732542819499341, "f1_std": 0.043412531003126836, "bacc": 0.6727941176470589, "bacc_std": 0.043122574332385526} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 19, "C": 0.046415888336127774, "split": "test", "acc": 0.5806451612903226, "acc_std": 0.04128510551718424, "f1": 0.5643243243243243, "f1_std": 0.0440425365500571, "bacc": 0.5672268907563025, "bacc_std": 0.042171630338420585} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 20, "C": 0.046415888336127774, "split": "test", "acc": 0.6370967741935484, "acc_std": 0.040820550923909994, "f1": 0.6241664982824813, "f1_std": 0.042799088699076115, "bacc": 0.625, "bacc_std": 0.0414634687526891} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 21, "C": 1291.5496650148827, "split": "test", "acc": 0.532258064516129, "acc_std": 0.04537706517288745, "f1": 0.5317708333333333, "f1_std": 0.04547020356594052, "bacc": 0.5341386554621849, "bacc_std": 0.0456669935392154} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 22, "C": 0.046415888336127774, "split": "test", "acc": 0.6532258064516129, "acc_std": 0.04167064011577802, "f1": 0.6408702094699266, "f1_std": 0.044298232607423264, "bacc": 0.641281512605042, "bacc_std": 0.042725902973927934} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 23, "C": 0.046415888336127774, "split": "test", "acc": 0.6451612903225806, "acc_std": 0.04173401979091432, "f1": 0.6336287939833467, "f1_std": 0.04429600954967696, "bacc": 0.6339285714285714, "bacc_std": 0.042854801694993394} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 24, "C": 0.046415888336127774, "split": "test", "acc": 0.6209677419354839, "acc_std": 0.04276627122177429, "f1": 0.6137071651090342, "f1_std": 0.04374161739563067, "bacc": 0.6134453781512605, "bacc_std": 0.04315938514078809} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 25, "C": 0.3593813663804626, "split": "test", "acc": 0.6048387096774194, "acc_std": 0.043722861361296404, "f1": 0.6035753898349319, "f1_std": 0.04400170756696923, "bacc": 0.6050420168067226, "bacc_std": 0.04401404997277175} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 26, "C": 0.046415888336127774, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.04215210490557812, "f1": 0.5951020408163266, "f1_std": 0.04529904697569786, "bacc": 0.5982142857142857, "bacc_std": 0.042923882630261825} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 27, "C": 0.3593813663804626, "split": "test", "acc": 0.6209677419354839, "acc_std": 0.04517076801470727, "f1": 0.6179613241560145, "f1_std": 0.045492634381514414, "bacc": 0.618172268907563, "bacc_std": 0.04543967166900425} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 28, "C": 1291.5496650148827, "split": "test", "acc": 0.6370967741935484, "acc_std": 0.043395490254191905, "f1": 0.6330637206549615, "f1_std": 0.04389294232132652, "bacc": 0.6328781512605042, "bacc_std": 0.04375373116535861} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 29, "C": 0.046415888336127774, "split": "test", "acc": 0.717741935483871, "acc_std": 0.04104582348291016, "f1": 0.7135502607088642, "f1_std": 0.04183136815066794, "bacc": 0.7127100840336134, "bacc_std": 0.04161633651839809} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 30, "C": 0.3593813663804626, "split": "test", "acc": 0.7258064516129032, "acc_std": 0.03852914893139649, "f1": 0.7211640211640211, "f1_std": 0.03956873674738482, "bacc": 0.720063025210084, "bacc_std": 0.03919180203008043} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 31, "C": 0.046415888336127774, "split": "test", "acc": 0.5967741935483871, "acc_std": 0.04577769144833791, "f1": 0.5915678524374176, "f1_std": 0.046424042404320943, "bacc": 0.5913865546218487, "bacc_std": 0.04614485999488417} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 32, "C": 0.3593813663804626, "split": "test", "acc": 0.6290322580645161, "acc_std": 0.04309229501544598, "f1": 0.6227513227513227, "f1_std": 0.04339083340792182, "bacc": 0.6223739495798319, "bacc_std": 0.0429626310305366} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 33, "C": 0.005994842503189409, "split": "test", "acc": 0.5645161290322581, "acc_std": 0.043717128278178786, "f1": 0.555142173797502, "f1_std": 0.04535167182300192, "bacc": 0.555672268907563, "bacc_std": 0.04453188603857468} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 34, "C": 21.54434690031882, "split": "test", "acc": 0.6612903225806451, "acc_std": 0.03922738483666518, "f1": 0.6604954367666231, "f1_std": 0.039337178615939085, "bacc": 0.6628151260504203, "bacc_std": 0.0393826274385554} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 35, "C": 0.046415888336127774, "split": "test", "acc": 0.6693548387096774, "acc_std": 0.04377026808652519, "f1": 0.667603792088918, "f1_std": 0.043957674196486274, "bacc": 0.66859243697479, "bacc_std": 0.043879437372669326} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 36, "C": 0.3593813663804626, "split": "test", "acc": 0.5806451612903226, "acc_std": 0.043399563504520816, "f1": 0.5670158474348643, "f1_std": 0.045842206156709045, "bacc": 0.5688025210084033, "bacc_std": 0.04429278725180169} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 37, "C": 0.046415888336127774, "split": "test", "acc": 0.6209677419354839, "acc_std": 0.042511245987148054, "f1": 0.6137071651090342, "f1_std": 0.043970851432391836, "bacc": 0.6134453781512605, "bacc_std": 0.04346932878651812} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 38, "C": 0.3593813663804626, "split": "test", "acc": 0.6048387096774194, "acc_std": 0.044287738100944087, "f1": 0.6035753898349319, "f1_std": 0.04450256421413519, "bacc": 0.6050420168067226, "bacc_std": 0.04479420379847532} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 39, "C": 0.046415888336127774, "split": "test", "acc": 0.5887096774193549, "acc_std": 0.04393876402894441, "f1": 0.5788211788211788, "f1_std": 0.044986039881547576, "bacc": 0.5793067226890757, "bacc_std": 0.04422173215994966} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 40, "C": 0.046415888336127774, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.04134024200147955, "f1": 0.588836695219674, "f1_std": 0.04605552260645633, "bacc": 0.595063025210084, "bacc_std": 0.0425075871675899} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 41, "C": 0.3593813663804626, "split": "test", "acc": 0.5967741935483871, "acc_std": 0.043732418795375, "f1": 0.5915678524374176, "f1_std": 0.04426551133662506, "bacc": 0.5913865546218487, "bacc_std": 0.04381954623234574} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 42, "C": 0.046415888336127774, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.04155062544060826, "f1": 0.610369206598586, "f1_std": 0.04185262308751665, "bacc": 0.6108193277310925, "bacc_std": 0.041893286650882815} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 43, "C": 0.3593813663804626, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.04179523383449262, "f1": 0.607905138339921, "f1_std": 0.04238464617398716, "bacc": 0.6076680672268908, "bacc_std": 0.042129831949010946} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 44, "C": 0.046415888336127774, "split": "test", "acc": 0.5403225806451613, "acc_std": 0.04251331431281925, "f1": 0.5292707292707293, "f1_std": 0.04381722872432997, "bacc": 0.5304621848739496, "bacc_std": 0.04292924370455228} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 45, "C": 0.3593813663804626, "split": "test", "acc": 0.6451612903225806, "acc_std": 0.04365702995289547, "f1": 0.6356837606837606, "f1_std": 0.04511426767393476, "bacc": 0.6355042016806722, "bacc_std": 0.04417298793694698} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 46, "C": 0.046415888336127774, "split": "test", "acc": 0.532258064516129, "acc_std": 0.04387171192442827, "f1": 0.5311603650586701, "f1_std": 0.04398909192283896, "bacc": 0.532563025210084, "bacc_std": 0.044241959762613914} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 47, "C": 0.3593813663804626, "split": "test", "acc": 0.6370967741935484, "acc_std": 0.041284888125233024, "f1": 0.6317074780542539, "f1_std": 0.04182356013800314, "bacc": 0.6313025210084033, "bacc_std": 0.04151463644697558} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 48, "C": 0.046415888336127774, "split": "test", "acc": 0.6209677419354839, "acc_std": 0.04369503087543244, "f1": 0.6137071651090342, "f1_std": 0.044667082243354396, "bacc": 0.6134453781512605, "bacc_std": 0.04410496129889271} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 49, "C": 0.3593813663804626, "split": "test", "acc": 0.6290322580645161, "acc_std": 0.04284294516080831, "f1": 0.6227513227513227, "f1_std": 0.04378155650448326, "bacc": 0.6223739495798319, "bacc_std": 0.043413455796548324} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 50, "C": 0.3593813663804626, "split": "test", "acc": 0.5806451612903226, "acc_std": 0.04542199806733209, "f1": 0.5670158474348643, "f1_std": 0.047662535394215076, "bacc": 0.5688025210084033, "bacc_std": 0.04609428470056079} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 51, "C": 0.3593813663804626, "split": "test", "acc": 0.5725806451612904, "acc_std": 0.04432618135817845, "f1": 0.5623043623043623, "f1_std": 0.045990305966460664, "bacc": 0.5630252100840336, "bacc_std": 0.044935348929596025} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 52, "C": 0.046415888336127774, "split": "test", "acc": 0.6370967741935484, "acc_std": 0.042930066791882146, "f1": 0.6301451580831179, "f1_std": 0.04395065649639746, "bacc": 0.6297268907563025, "bacc_std": 0.04340828288903001} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 53, "C": 0.046415888336127774, "split": "test", "acc": 0.6451612903225806, "acc_std": 0.04236471091001416, "f1": 0.6375232527238905, "f1_std": 0.0433435079928184, "bacc": 0.6370798319327731, "bacc_std": 0.04275246054966052} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 54, "C": 0.3593813663804626, "split": "test", "acc": 0.6693548387096774, "acc_std": 0.04147035788037435, "f1": 0.665680278818965, "f1_std": 0.04203753434147787, "bacc": 0.6654411764705883, "bacc_std": 0.041902222645376415} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 55, "C": 0.046415888336127774, "split": "test", "acc": 0.5564516129032258, "acc_std": 0.04528270258018686, "f1": 0.5498646953996436, "f1_std": 0.04601491852654321, "bacc": 0.5498949579831933, "bacc_std": 0.04564247272207431} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 56, "C": 0.3593813663804626, "split": "test", "acc": 0.7096774193548387, "acc_std": 0.03912615671693408, "f1": 0.7084639498432602, "f1_std": 0.03919520903835374, "bacc": 0.7100840336134454, "bacc_std": 0.039172092959254654} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 57, "C": 0.3593813663804626, "split": "test", "acc": 0.6854838709677419, "acc_std": 0.04193621587450457, "f1": 0.6819885579009667, "f1_std": 0.04268715568545375, "bacc": 0.6817226890756303, "bacc_std": 0.04251873596567905} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 58, "C": 0.046415888336127774, "split": "test", "acc": 0.6370967741935484, "acc_std": 0.042201402544121046, "f1": 0.6351748937561295, "f1_std": 0.04259971583678637, "bacc": 0.6360294117647058, "bacc_std": 0.04272102214159372} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 59, "C": 0.046415888336127774, "split": "test", "acc": 0.6693548387096774, "acc_std": 0.044155575869112916, "f1": 0.667603792088918, "f1_std": 0.044247041175048324, "bacc": 0.66859243697479, "bacc_std": 0.04417321694080843} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 60, "C": 2.782559402207126, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.043462831130821965, "f1": 0.6063492063492064, "f1_std": 0.04473027666839228, "bacc": 0.60609243697479, "bacc_std": 0.04425985657162603} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 61, "C": 0.3593813663804626, "split": "test", "acc": 0.6612903225806451, "acc_std": 0.043661320113911925, "f1": 0.6590730557737627, "f1_std": 0.04389108393088674, "bacc": 0.6596638655462186, "bacc_std": 0.043879168312034804} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 62, "C": 21.54434690031882, "split": "test", "acc": 0.532258064516129, "acc_std": 0.04459336450828279, "f1": 0.5303030303030303, "f1_std": 0.044587377354163286, "bacc": 0.5309873949579832, "bacc_std": 0.0444801030277084} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 63, "C": 0.3593813663804626, "split": "test", "acc": 0.6370967741935484, "acc_std": 0.042516750081126584, "f1": 0.635936582501468, "f1_std": 0.04288360875442909, "bacc": 0.6376050420168067, "bacc_std": 0.04319772420132801} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 64, "C": 21.54434690031882, "split": "test", "acc": 0.5564516129032258, "acc_std": 0.04336161861349872, "f1": 0.5550336008351275, "f1_std": 0.04339687421469905, "bacc": 0.5561974789915967, "bacc_std": 0.043467300699941265} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 65, "C": 0.3593813663804626, "split": "test", "acc": 0.6935483870967742, "acc_std": 0.03950531781008419, "f1": 0.6816216216216215, "f1_std": 0.04229831395371728, "bacc": 0.6811974789915967, "bacc_std": 0.04068664974250473} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 66, "C": 0.046415888336127774, "split": "test", "acc": 0.5967741935483871, "acc_std": 0.045687746577226705, "f1": 0.5950888192267503, "f1_std": 0.045840383696708634, "bacc": 0.5961134453781513, "bacc_std": 0.045930838013793295} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 67, "C": 0.3593813663804626, "split": "test", "acc": 0.6612903225806451, "acc_std": 0.042185640350965635, "f1": 0.6590730557737627, "f1_std": 0.0424930549130221, "bacc": 0.6596638655462186, "bacc_std": 0.042480774195510045} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 68, "C": 0.3593813663804626, "split": "test", "acc": 0.6854838709677419, "acc_std": 0.041297391028044445, "f1": 0.6819885579009667, "f1_std": 0.041561564952387914, "bacc": 0.6817226890756303, "bacc_std": 0.041386512111802595} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 69, "C": 0.046415888336127774, "split": "test", "acc": 0.6774193548387096, "acc_std": 0.04318842871198004, "f1": 0.671957671957672, "f1_std": 0.04419107756478538, "bacc": 0.671218487394958, "bacc_std": 0.043732529916074146} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 70, "C": 0.046415888336127774, "split": "test", "acc": 0.6451612903225806, "acc_std": 0.04393419009510947, "f1": 0.6356837606837606, "f1_std": 0.045537200066747344, "bacc": 0.6355042016806722, "bacc_std": 0.04455029846261225} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 71, "C": 0.046415888336127774, "split": "test", "acc": 0.6935483870967742, "acc_std": 0.04035627946681591, "f1": 0.6869519000797236, "f1_std": 0.04158723153026497, "bacc": 0.6859243697478992, "bacc_std": 0.041061380328572455} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 72, "C": 0.3593813663804626, "split": "test", "acc": 0.5806451612903226, "acc_std": 0.0450959319686917, "f1": 0.5766806722689075, "f1_std": 0.04521167785836012, "bacc": 0.5766806722689075, "bacc_std": 0.04506909838412064} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 73, "C": 0.3593813663804626, "split": "test", "acc": 0.6048387096774194, "acc_std": 0.04217487502348546, "f1": 0.5989703649924097, "f1_std": 0.04287987199763131, "bacc": 0.5987394957983193, "bacc_std": 0.04253998521967229} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 74, "C": 0.3593813663804626, "split": "test", "acc": 0.6774193548387096, "acc_std": 0.043164168258359906, "f1": 0.6753076721654884, "f1_std": 0.04339986758551995, "bacc": 0.6759453781512605, "bacc_std": 0.043291638871471284} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 75, "C": 0.046415888336127774, "split": "test", "acc": 0.7096774193548387, "acc_std": 0.03954500261790291, "f1": 0.7002417405318292, "f1_std": 0.04161704343084888, "bacc": 0.6990546218487395, "bacc_std": 0.04057893023416495} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 76, "C": 0.046415888336127774, "split": "test", "acc": 0.6048387096774194, "acc_std": 0.04288161898317396, "f1": 0.5880957223239103, "f1_std": 0.04533730738000938, "bacc": 0.5908613445378151, "bacc_std": 0.04346326507255579} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 77, "C": 0.3593813663804626, "split": "test", "acc": 0.5725806451612904, "acc_std": 0.044130388113485096, "f1": 0.5718845677806006, "f1_std": 0.04417746123537055, "bacc": 0.5740546218487395, "bacc_std": 0.04415612192857203} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 78, "C": 0.046415888336127774, "split": "test", "acc": 0.5967741935483871, "acc_std": 0.044515544643195515, "f1": 0.58994708994709, "f1_std": 0.045620791038690586, "bacc": 0.5898109243697479, "bacc_std": 0.045144571510113946} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 79, "C": 2.782559402207126, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.04338177206803275, "f1": 0.607905138339921, "f1_std": 0.04435917172320687, "bacc": 0.6076680672268908, "bacc_std": 0.044054920831767784} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 80, "C": 0.3593813663804626, "split": "test", "acc": 0.7016129032258065, "acc_std": 0.0395732437804769, "f1": 0.6928021426180114, "f1_std": 0.04123121574272059, "bacc": 0.6917016806722689, "bacc_std": 0.04030183047333079} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 81, "C": 0.3593813663804626, "split": "test", "acc": 0.6370967741935484, "acc_std": 0.040825059508480414, "f1": 0.6241664982824813, "f1_std": 0.04317487222049394, "bacc": 0.625, "bacc_std": 0.041613094357198975} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 82, "C": 2.782559402207126, "split": "test", "acc": 0.6048387096774194, "acc_std": 0.04097399939511398, "f1": 0.5953379953379954, "f1_std": 0.04213878601167693, "bacc": 0.5955882352941176, "bacc_std": 0.04139830351673394} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 83, "C": 2.782559402207126, "split": "test", "acc": 0.5483870967741935, "acc_std": 0.045097639476677345, "f1": 0.5483870967741935, "f1_std": 0.04526958280609117, "bacc": 0.5535714285714286, "bacc_std": 0.04512684383985137} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 84, "C": 2.782559402207126, "split": "test", "acc": 0.5806451612903226, "acc_std": 0.044026302326746425, "f1": 0.5778999738151349, "f1_std": 0.044256210410751985, "bacc": 0.5782563025210083, "bacc_std": 0.0442241922113251} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 85, "C": 0.046415888336127774, "split": "test", "acc": 0.6774193548387096, "acc_std": 0.04140126225284723, "f1": 0.6743697478991597, "f1_std": 0.04183847093603445, "bacc": 0.6743697478991597, "bacc_std": 0.041774192019826406} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 86, "C": 0.3593813663804626, "split": "test", "acc": 0.6048387096774194, "acc_std": 0.04235238181705396, "f1": 0.5989703649924097, "f1_std": 0.0429170030628922, "bacc": 0.5987394957983193, "bacc_std": 0.04261871935572771} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 87, "C": 0.046415888336127774, "split": "test", "acc": 0.6693548387096774, "acc_std": 0.042301553588540486, "f1": 0.6630211440312852, "f1_std": 0.043582009002831726, "bacc": 0.6622899159663866, "bacc_std": 0.04310266111215358} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 88, "C": 0.046415888336127774, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.042911044036613395, "f1": 0.607905138339921, "f1_std": 0.04348853379417213, "bacc": 0.6076680672268908, "bacc_std": 0.043257082090020015} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 89, "C": 0.3593813663804626, "split": "test", "acc": 0.5967741935483871, "acc_std": 0.04189718784877806, "f1": 0.5958279009126467, "f1_std": 0.04210599014265548, "bacc": 0.5976890756302521, "bacc_std": 0.04244277108836576} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 90, "C": 2.782559402207126, "split": "test", "acc": 0.6209677419354839, "acc_std": 0.04424179142191919, "f1": 0.6137071651090342, "f1_std": 0.04527210498386818, "bacc": 0.6134453781512605, "bacc_std": 0.04455121205033533} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 91, "C": 0.046415888336127774, "split": "test", "acc": 0.5967741935483871, "acc_std": 0.043304367103073, "f1": 0.58994708994709, "f1_std": 0.043923122767066065, "bacc": 0.5898109243697479, "bacc_std": 0.04351190145970663} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 92, "C": 0.046415888336127774, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.044473740922410764, "f1": 0.6045708211533352, "f1_std": 0.04571554664296464, "bacc": 0.6045168067226891, "bacc_std": 0.04492837833621383} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 93, "C": 0.046415888336127774, "split": "test", "acc": 0.6048387096774194, "acc_std": 0.04283905885497024, "f1": 0.5989703649924097, "f1_std": 0.04353366638182324, "bacc": 0.5987394957983193, "bacc_std": 0.043344788849647445} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 94, "C": 0.3593813663804626, "split": "test", "acc": 0.6612903225806451, "acc_std": 0.03939651415777237, "f1": 0.6580882352941176, "f1_std": 0.040138218243220884, "bacc": 0.6580882352941176, "bacc_std": 0.04010188672543152} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 95, "C": 0.046415888336127774, "split": "test", "acc": 0.5806451612903226, "acc_std": 0.041963080249884814, "f1": 0.5581140350877193, "f1_std": 0.0454844381259524, "bacc": 0.5640756302521008, "bacc_std": 0.04268796735021691} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 96, "C": 0.3593813663804626, "split": "test", "acc": 0.6048387096774194, "acc_std": 0.04421966205170162, "f1": 0.6004471624909581, "f1_std": 0.04461186884832921, "bacc": 0.6003151260504203, "bacc_std": 0.04443249518160093} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 97, "C": 2.782559402207126, "split": "test", "acc": 0.6693548387096774, "acc_std": 0.04217757355180597, "f1": 0.6644445911160979, "f1_std": 0.04312265694438706, "bacc": 0.6638655462184874, "bacc_std": 0.042947525531612865} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 98, "C": 0.046415888336127774, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.043739279941277916, "f1": 0.5852842809364549, "f1_std": 0.048677073542870423, "bacc": 0.5934873949579832, "bacc_std": 0.0447374348019143} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 99, "C": 0.046415888336127774, "split": "test", "acc": 0.5967741935483871, "acc_std": 0.04240681465567031, "f1": 0.5860042735042735, "f1_std": 0.04438799076202749, "bacc": 0.5866596638655462, "bacc_std": 0.04324445696529544} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 100, "C": 0.046415888336127774, "split": "test", "acc": 0.7096774193548387, "acc_std": 0.04099333719116655, "f1": 0.7034281158650013, "f1_std": 0.04219132831075011, "bacc": 0.7022058823529411, "bacc_std": 0.04171527697834944} +eval results (random splits): + +| model | repr | clf | dataset | split | n_trials | C | C_std | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|-----------:|-------:|--------:|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | abide_dx | train | 100 | 41.875 | 221.55 | 0.86997 | 0.070682 | 0.86774 | 0.07212 | 0.86645 | 0.072622 | +| flat_mae | patch | logistic | abide_dx | test | 100 | 41.875 | 221.55 | 0.62452 | 0.044957 | 0.61794 | 0.045585 | 0.61871 | 0.044853 | + + +done! total time: 0:06:06 diff --git a/input_space_v3/flat_lr1e-3_5/eval_v2/adhd200_dx__patch__logistic/config.yaml b/input_space_v3/flat_lr1e-3_5/eval_v2/adhd200_dx__patch__logistic/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..e694fc640bafcf8b16c9a06f6926cf5b7f22b60c --- /dev/null +++ b/input_space_v3/flat_lr1e-3_5/eval_v2/adhd200_dx__patch__logistic/config.yaml @@ -0,0 +1,30 @@ +output_root: experiments/input_space_v3/output +name_prefix: eval_logistic +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_5; eval v2 (adhd200_dx patch logistic) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: input_space_v3/flat_lr1e-3_5/eval_v2/adhd200_dx__patch__logistic +model: flat_mae +representation: patch +dataset: adhd200_dx +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/eval_v2/adhd200_dx__patch__logistic +remote_dir: null diff --git a/input_space_v3/flat_lr1e-3_5/eval_v2/adhd200_dx__patch__logistic/eval_table.csv b/input_space_v3/flat_lr1e-3_5/eval_v2/adhd200_dx__patch__logistic/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..5924469e0fc95ea3993be3ae9cb72b8d40491ed5 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_5/eval_v2/adhd200_dx__patch__logistic/eval_table.csv @@ -0,0 +1,203 @@ +model,repr,clf,dataset,trial,C,split,acc,acc_std,f1,f1_std,bacc,bacc_std +flat_mae,patch,logistic,adhd200_dx,,0.000774263682681127,train,0.684931506849315,0.02349065828066548,0.6706525747553924,0.024920368551699514,0.6692159736215424,0.02412762679205033 +flat_mae,patch,logistic,adhd200_dx,,0.000774263682681127,test,0.6153846153846154,0.05763854725942974,0.5905769715293525,0.06353936150710236,0.5926640926640927,0.05994538862065275 +flat_mae,patch,logistic,adhd200_dx,1,0.005994842503189409,train,0.7534246575342466,0.0213383089837763,0.7413059913059913,0.0230580842842923,0.7377877511143677,0.022418360972234447 +flat_mae,patch,logistic,adhd200_dx,1,0.005994842503189409,test,0.5846153846153846,0.058767619792660264,0.5644080416976918,0.06181326567968907,0.5656370656370656,0.05985113975574871 +flat_mae,patch,logistic,adhd200_dx,2,0.005994842503189409,train,0.7287671232876712,0.022714778194671013,0.7184102863822326,0.023921573735413544,0.7159430909201929,0.023508900895318617 +flat_mae,patch,logistic,adhd200_dx,2,0.005994842503189409,test,0.7076923076923077,0.05602517608209354,0.6973780936045086,0.05896899298516095,0.6954633204633205,0.058240692414928324 +flat_mae,patch,logistic,adhd200_dx,3,0.005994842503189409,train,0.7534246575342466,0.023387617916235805,0.7431506849315068,0.0249921474315908,0.7399401599804604,0.02459549122654065 +flat_mae,patch,logistic,adhd200_dx,3,0.005994842503189409,test,0.5384615384615384,0.061486893778340074,0.5125,0.06535431069970007,0.5164092664092664,0.06243658922314471 +flat_mae,patch,logistic,adhd200_dx,4,0.046415888336127774,train,0.8273972602739726,0.018966982204909236,0.8235348287531943,0.019533495839814122,0.8219759418696952,0.019700901092356397 +flat_mae,patch,logistic,adhd200_dx,4,0.046415888336127774,test,0.676923076923077,0.054551642109149506,0.6655231560891939,0.05804094522874361,0.6640926640926641,0.056973664747773343 +flat_mae,patch,logistic,adhd200_dx,5,0.005994842503189409,train,0.7561643835616438,0.021988742065698664,0.7462922032786373,0.023622723563486832,0.7430848140685107,0.023249602541683158 +flat_mae,patch,logistic,adhd200_dx,5,0.005994842503189409,test,0.49230769230769234,0.0637532224501716,0.4879446168536643,0.06438433948045456,0.4888996138996139,0.06503356065462686 +flat_mae,patch,logistic,adhd200_dx,6,0.046415888336127774,train,0.8273972602739726,0.019042492113981634,0.8222691121571173,0.01985745097512819,0.8191060633815718,0.01990504470549447 +flat_mae,patch,logistic,adhd200_dx,6,0.046415888336127774,test,0.6923076923076923,0.058292581764384024,0.6886973180076628,0.058778103955758824,0.6906370656370657,0.05864509935348486 +flat_mae,patch,logistic,adhd200_dx,7,0.005994842503189409,train,0.7506849315068493,0.02184592046460319,0.7399979647590196,0.02346502869606923,0.73679550589241,0.023058145424007814 +flat_mae,patch,logistic,adhd200_dx,7,0.005994842503189409,test,0.6307692307692307,0.05790013847568034,0.6198830409356726,0.05985347967221368,0.6192084942084942,0.059135040506936916 +flat_mae,patch,logistic,adhd200_dx,8,0.005994842503189409,train,0.7561643835616438,0.022210545761613125,0.7473969875817451,0.02360579370014866,0.7445197533125725,0.02333756847081866 +flat_mae,patch,logistic,adhd200_dx,8,0.005994842503189409,test,0.6153846153846154,0.06123323535814546,0.5966741126830479,0.06549652528062001,0.597007722007722,0.06287288979462803 +flat_mae,patch,logistic,adhd200_dx,9,0.005994842503189409,train,0.7424657534246575,0.022554118897152066,0.732337889284154,0.02386079138927986,0.7295139524943518,0.023486764972606204 +flat_mae,patch,logistic,adhd200_dx,9,0.005994842503189409,test,0.6153846153846154,0.06185404465543613,0.6018132810585641,0.06463507273961049,0.6013513513513513,0.06329600710588597 +flat_mae,patch,logistic,adhd200_dx,10,0.3593813663804626,train,0.9534246575342465,0.011544635935266138,0.9524597574336697,0.011827167067878439,0.95084569823533,0.012183627474241503 +flat_mae,patch,logistic,adhd200_dx,10,0.3593813663804626,test,0.46153846153846156,0.06119547494583365,0.44253859348198965,0.062481272337692836,0.44449806949806947,0.06154613142512716 +flat_mae,patch,logistic,adhd200_dx,11,0.005994842503189409,train,0.7479452054794521,0.021189377625378064,0.7362053795877326,0.022742956027752975,0.7329333821823288,0.022191261130438705 +flat_mae,patch,logistic,adhd200_dx,11,0.005994842503189409,test,0.5846153846153846,0.054824898243914885,0.5578231292517006,0.0593273516058535,0.5612934362934363,0.05595768176541273 +flat_mae,patch,logistic,adhd200_dx,12,0.005994842503189409,train,0.7506849315068493,0.02182911094029279,0.7437608486017357,0.02262233969602528,0.7418177932466263,0.022471894282356783 +flat_mae,patch,logistic,adhd200_dx,12,0.005994842503189409,test,0.5692307692307692,0.05586034996511257,0.545,0.06082057942421427,0.5477799227799228,0.05739957577879453 +flat_mae,patch,logistic,adhd200_dx,13,0.000774263682681127,train,0.6958904109589041,0.024104231036013012,0.681338042016344,0.025888155442176684,0.679642181107651,0.025029381544376544 +flat_mae,patch,logistic,adhd200_dx,13,0.000774263682681127,test,0.5538461538461539,0.057471544798608484,0.5321419707123356,0.060046491740810094,0.5342664092664092,0.05800877452905307 +flat_mae,patch,logistic,adhd200_dx,14,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adhd200_dx,14,1291.5496650148827,test,0.6,0.06248359595376702,0.5953065134099617,0.06303480728005004,0.5965250965250966,0.06356924377787453 +flat_mae,patch,logistic,adhd200_dx,15,0.005994842503189409,train,0.726027397260274,0.022279856339276073,0.7146118721461188,0.023905507106992442,0.7120809672101117,0.023411668803518772 +flat_mae,patch,logistic,adhd200_dx,15,0.005994842503189409,test,0.5846153846153846,0.05952907101457227,0.578226387887527,0.06007513475763612,0.5786679536679536,0.060236271874179764 +flat_mae,patch,logistic,adhd200_dx,16,0.000774263682681127,train,0.6904109589041096,0.022387852911028495,0.6792793213116539,0.02344793422343181,0.6776576906637357,0.02301903854930101 +flat_mae,patch,logistic,adhd200_dx,16,0.000774263682681127,test,0.6153846153846154,0.059479995145302486,0.606060606060606,0.0612540277456109,0.6056949806949807,0.06072205273317732 +flat_mae,patch,logistic,adhd200_dx,17,0.005994842503189409,train,0.726027397260274,0.021249212628773825,0.7152530737065468,0.022464105857464636,0.7127984368321426,0.022024286919071188 +flat_mae,patch,logistic,adhd200_dx,17,0.005994842503189409,test,0.6307692307692307,0.05998434509773974,0.61,0.0648400717422398,0.6105212355212355,0.061849304102088914 +flat_mae,patch,logistic,adhd200_dx,18,0.005994842503189409,train,0.7178082191780822,0.022849629773464327,0.7043046696187697,0.024485917034172872,0.7019295353239299,0.023727705713295272 +flat_mae,patch,logistic,adhd200_dx,18,0.005994842503189409,test,0.676923076923077,0.05618649419724918,0.6655231560891939,0.05901599202178849,0.6640926640926641,0.057782295674758705 +flat_mae,patch,logistic,adhd200_dx,19,0.005994842503189409,train,0.7452054794520548,0.023175493880546395,0.734283634314163,0.024729131828828854,0.7312236673383403,0.024221652256471275 +flat_mae,patch,logistic,adhd200_dx,19,0.005994842503189409,test,0.676923076923077,0.054772852084256,0.656084656084656,0.06080862211802793,0.6554054054054055,0.05752040712643485 +flat_mae,patch,logistic,adhd200_dx,20,0.046415888336127774,train,0.8328767123287671,0.018679363650401397,0.8275755252499439,0.0195886518856899,0.8239604323136106,0.019670102718224624 +flat_mae,patch,logistic,adhd200_dx,20,0.046415888336127774,test,0.5692307692307692,0.05531855034104129,0.5512820512820513,0.05833766989591626,0.5521235521235521,0.05650388847503729 +flat_mae,patch,logistic,adhd200_dx,21,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adhd200_dx,21,21.54434690031882,test,0.5846153846153846,0.060275627268437035,0.5830363506771205,0.06045947095696174,0.5873552123552124,0.06025461066409738 +flat_mae,patch,logistic,adhd200_dx,22,0.000774263682681127,train,0.6876712328767123,0.02249412908956117,0.6723209223209223,0.02405597090902385,0.6709256884655309,0.02325155427215287 +flat_mae,patch,logistic,adhd200_dx,22,0.000774263682681127,test,0.6153846153846154,0.06103622748080648,0.606060606060606,0.063224891492281,0.6056949806949807,0.06271347359798328 +flat_mae,patch,logistic,adhd200_dx,23,0.005994842503189409,train,0.7424657534246575,0.021599730334770605,0.7329212853406402,0.022761566778625963,0.7302314221163827,0.02241230951981728 +flat_mae,patch,logistic,adhd200_dx,23,0.005994842503189409,test,0.6307692307692307,0.0529757430255813,0.587737843551797,0.06212023903986025,0.5974903474903475,0.05494855306554449 +flat_mae,patch,logistic,adhd200_dx,24,0.005994842503189409,train,0.7424657534246575,0.021991445478533603,0.732337889284154,0.023375889411499855,0.7295139524943518,0.02295570865616318 +flat_mae,patch,logistic,adhd200_dx,24,0.005994842503189409,test,0.6307692307692307,0.056307482134958745,0.61,0.060791226870776434,0.6105212355212355,0.05779447617699375 +flat_mae,patch,logistic,adhd200_dx,25,0.046415888336127774,train,0.8301369863013699,0.019084638102983813,0.8245736434108527,0.020001770268066817,0.8208157782255603,0.020051314222779806 +flat_mae,patch,logistic,adhd200_dx,25,0.046415888336127774,test,0.6,0.06400742560472478,0.5976190476190476,0.06428730110439299,0.6008687258687259,0.06471513971906379 +flat_mae,patch,logistic,adhd200_dx,26,0.005994842503189409,train,0.726027397260274,0.021462875208075233,0.7125622125622125,0.023192478188468393,0.709928558344019,0.022461269789664635 +flat_mae,patch,logistic,adhd200_dx,26,0.005994842503189409,test,0.6923076923076923,0.05554284235865236,0.6832358674463938,0.057825879580425836,0.6819498069498069,0.05690540585566157 +flat_mae,patch,logistic,adhd200_dx,27,0.005994842503189409,train,0.7452054794520548,0.021525513932236628,0.734283634314163,0.023176693268256065,0.7312236673383403,0.022693097850546958 +flat_mae,patch,logistic,adhd200_dx,27,0.005994842503189409,test,0.6307692307692307,0.05563508322279298,0.61,0.05989056334128341,0.6105212355212355,0.057126852442759744 +flat_mae,patch,logistic,adhd200_dx,28,0.000774263682681127,train,0.6821917808219178,0.022577113908421785,0.6673893916540976,0.024136680697042553,0.6660713195334921,0.023347983773721655 +flat_mae,patch,logistic,adhd200_dx,28,0.000774263682681127,test,0.5692307692307692,0.054464285024181366,0.5376016260162602,0.05933113816565911,0.5434362934362934,0.05568131390001869 +flat_mae,patch,logistic,adhd200_dx,29,0.005994842503189409,train,0.7342465753424657,0.02333814031568568,0.7228549734244495,0.024807056747379753,0.7200799902302009,0.02425406189037214 +flat_mae,patch,logistic,adhd200_dx,29,0.005994842503189409,test,0.6,0.060568384746245554,0.5833333333333333,0.06384893967124061,0.5834942084942085,0.06207801503236489 +flat_mae,patch,logistic,adhd200_dx,30,0.000774263682681127,train,0.6904109589041096,0.023785792675370763,0.6778766176459103,0.02540876101153792,0.6762227514196739,0.024762982143296745 +flat_mae,patch,logistic,adhd200_dx,30,0.000774263682681127,test,0.5538461538461539,0.058557419350127995,0.5321419707123356,0.062133966855182146,0.5342664092664092,0.059787416767317754 +flat_mae,patch,logistic,adhd200_dx,31,0.005994842503189409,train,0.7506849315068493,0.021868162953198537,0.74059090447591,0.023035140710394343,0.737512975514441,0.022594639890804027 +flat_mae,patch,logistic,adhd200_dx,31,0.005994842503189409,test,0.6307692307692307,0.05748624533196497,0.6036585365853658,0.06345837279287103,0.6061776061776062,0.05960312502656322 +flat_mae,patch,logistic,adhd200_dx,32,0.3593813663804626,train,0.947945205479452,0.011955017962942446,0.9467803451795348,0.01230177295671059,0.9445563900592294,0.012811370993339314 +flat_mae,patch,logistic,adhd200_dx,32,0.3593813663804626,test,0.5384615384615384,0.05791598894215594,0.5248538011695907,0.05942724136060567,0.525096525096525,0.0585086553623215 +flat_mae,patch,logistic,adhd200_dx,33,0.005994842503189409,train,0.7397260273972602,0.022604590044645972,0.7303675710142223,0.023863196689968454,0.7278042376503633,0.023558090305238914 +flat_mae,patch,logistic,adhd200_dx,33,0.005994842503189409,test,0.6153846153846154,0.05877490105549171,0.61207925519217,0.059746208296140024,0.6143822393822393,0.060078307362730586 +flat_mae,patch,logistic,adhd200_dx,34,0.005994842503189409,train,0.7315068493150685,0.021354531908399074,0.7227131782945737,0.02235601672507913,0.720522684252305,0.022137723061520894 +flat_mae,patch,logistic,adhd200_dx,34,0.005994842503189409,test,0.6461538461538462,0.0604680677625382,0.6431129147767964,0.061127846253699866,0.6457528957528957,0.06131338808218241 +flat_mae,patch,logistic,adhd200_dx,35,0.005994842503189409,train,0.7397260273972602,0.02291258871693442,0.7265917602996255,0.024738951455583254,0.7234994199181779,0.023950289368823693 +flat_mae,patch,logistic,adhd200_dx,35,0.005994842503189409,test,0.6615384615384615,0.05735919420427133,0.6474358974358974,0.06095479758688411,0.6462355212355213,0.059349782664367516 +flat_mae,patch,logistic,adhd200_dx,36,0.000774263682681127,train,0.6931506849315069,0.023219869064757877,0.682450907283122,0.024373387934456883,0.680802344751786,0.023992358604895663 +flat_mae,patch,logistic,adhd200_dx,36,0.000774263682681127,test,0.5384615384615384,0.05674236595943595,0.5125,0.06019548377689636,0.5164092664092664,0.05731486466784236 +flat_mae,patch,logistic,adhd200_dx,37,0.005994842503189409,train,0.7178082191780822,0.022762793383493782,0.7050192626070035,0.024270406573842235,0.7026470049459608,0.023647320193975252 +flat_mae,patch,logistic,adhd200_dx,37,0.005994842503189409,test,0.6923076923076923,0.0528093231862009,0.675,0.0574788077722897,0.6732625482625483,0.054813521347461425 +flat_mae,patch,logistic,adhd200_dx,38,0.005994842503189409,train,0.7534246575342466,0.02228554519164041,0.7448266219239373,0.023414929665819262,0.7420925688465531,0.023139079914871682 +flat_mae,patch,logistic,adhd200_dx,38,0.005994842503189409,test,0.6,0.05493384940681735,0.570630081300813,0.060788064594913274,0.5748069498069498,0.05626250251544979 +flat_mae,patch,logistic,adhd200_dx,39,0.005994842503189409,train,0.7479452054794521,0.022315517709514333,0.7374429223744292,0.02369544919574207,0.7343683214263906,0.023239502068670207 +flat_mae,patch,logistic,adhd200_dx,39,0.005994842503189409,test,0.6461538461538462,0.05806455497443082,0.6233308138070043,0.06336720869636565,0.6240347490347491,0.06004871573816458 +flat_mae,patch,logistic,adhd200_dx,40,0.005994842503189409,train,0.726027397260274,0.021829060737072227,0.7125622125622125,0.023713029611172713,0.709928558344019,0.022964102187789943 +flat_mae,patch,logistic,adhd200_dx,40,0.005994842503189409,test,0.7230769230769231,0.05242390709879376,0.7027439024390244,0.059131835578175466,0.7002895752895753,0.05563408415584436 +flat_mae,patch,logistic,adhd200_dx,41,0.000774263682681127,train,0.6958904109589041,0.0234063977537733,0.678883085385475,0.025857265609542077,0.6774897722415583,0.024657438029554907 +flat_mae,patch,logistic,adhd200_dx,41,0.000774263682681127,test,0.6,0.0596661243129847,0.588206627680312,0.06173370058551594,0.5878378378378378,0.06084829587913847 +flat_mae,patch,logistic,adhd200_dx,42,0.005994842503189409,train,0.7452054794520548,0.02321689486491086,0.7348896056731828,0.024336284969804525,0.7319411369603712,0.02389118662785432 +flat_mae,patch,logistic,adhd200_dx,42,0.005994842503189409,test,0.6,0.060577254699946986,0.5921814671814671,0.061610676921627784,0.5921814671814671,0.06145525244972158 +flat_mae,patch,logistic,adhd200_dx,43,0.005994842503189409,train,0.7397260273972602,0.020772182128623067,0.7285693038693062,0.02229529636560711,0.7256518287842706,0.02178296586047445 +flat_mae,patch,logistic,adhd200_dx,43,0.005994842503189409,test,0.6,0.05800856904665238,0.5833333333333333,0.05975374009547867,0.5834942084942085,0.05830002954588878 +flat_mae,patch,logistic,adhd200_dx,44,0.046415888336127774,train,0.8356164383561644,0.019606223712298823,0.8312060673325934,0.020339449202500987,0.8285400256457227,0.020471021791269486 +flat_mae,patch,logistic,adhd200_dx,44,0.046415888336127774,test,0.6153846153846154,0.05882800122229763,0.5966741126830479,0.06257516244105404,0.597007722007722,0.06024687038021029 +flat_mae,patch,logistic,adhd200_dx,45,0.005994842503189409,train,0.7726027397260274,0.021244185410923412,0.7622970756930223,0.022922530946079076,0.7583653904866581,0.022525841173140264 +flat_mae,patch,logistic,adhd200_dx,45,0.005994842503189409,test,0.5384615384615384,0.05827054631670563,0.5045731707317074,0.06342532074738591,0.5120656370656371,0.05913066537873777 +flat_mae,patch,logistic,adhd200_dx,46,0.005994842503189409,train,0.726027397260274,0.02226881336734496,0.7146118721461188,0.02375937610956038,0.7120809672101117,0.023238301171104748 +flat_mae,patch,logistic,adhd200_dx,46,0.005994842503189409,test,0.6923076923076923,0.055416905117311135,0.675,0.060313722596862095,0.6732625482625483,0.05753067917243245 +flat_mae,patch,logistic,adhd200_dx,47,0.005994842503189409,train,0.7561643835616438,0.020741354598479006,0.7462922032786373,0.02200453206808954,0.7430848140685107,0.021601700901433044 +flat_mae,patch,logistic,adhd200_dx,47,0.005994842503189409,test,0.5076923076923077,0.06165293967374305,0.49317738791423005,0.06253700601065859,0.49372586872586877,0.06169901580468184 +flat_mae,patch,logistic,adhd200_dx,48,0.000774263682681127,train,0.673972602739726,0.022606266889591265,0.6528671328671329,0.0247971696138542,0.6530500091591867,0.023416197159937972 +flat_mae,patch,logistic,adhd200_dx,48,0.000774263682681127,test,0.7076923076923077,0.05681256632390138,0.6973780936045086,0.05987764876559988,0.6954633204633205,0.05910914752180083 +flat_mae,patch,logistic,adhd200_dx,49,0.005994842503189409,train,0.7561643835616438,0.021674875609540643,0.7451137317672167,0.023217783225692547,0.7416498748244489,0.022713017927977624 +flat_mae,patch,logistic,adhd200_dx,49,0.005994842503189409,test,0.5692307692307692,0.058205715573677014,0.5512820512820513,0.06089864814234744,0.5521235521235521,0.05928107306519364 +flat_mae,patch,logistic,adhd200_dx,50,0.005994842503189409,train,0.7397260273972602,0.022023178905016854,0.7291883068704555,0.023470995219833517,0.7263692984063015,0.0230291861204741 +flat_mae,patch,logistic,adhd200_dx,50,0.005994842503189409,test,0.6307692307692307,0.05810120531599665,0.6153846153846154,0.06150978701207276,0.6148648648648649,0.05966779570736597 +flat_mae,patch,logistic,adhd200_dx,51,0.005994842503189409,train,0.736986301369863,0.022368416599632266,0.7278150633855331,0.023374737787612093,0.7253770531843439,0.023045115877765296 +flat_mae,patch,logistic,adhd200_dx,51,0.005994842503189409,test,0.6461538461538462,0.05833004645572149,0.6289401836684041,0.06249868212756579,0.6283783783783784,0.06015914463961707 +flat_mae,patch,logistic,adhd200_dx,52,0.046415888336127774,train,0.8246575342465754,0.0201143035047066,0.8189147286821705,0.021136591472456504,0.8152439396714906,0.021183221318288446 +flat_mae,patch,logistic,adhd200_dx,52,0.046415888336127774,test,0.6615384615384615,0.05822507644157472,0.6474358974358974,0.06163140134299893,0.6462355212355213,0.06014396595980233 +flat_mae,patch,logistic,adhd200_dx,53,0.005994842503189409,train,0.7534246575342466,0.021960431842531065,0.7453488372093022,0.023020835531534087,0.742810038468584,0.022824461611047942 +flat_mae,patch,logistic,adhd200_dx,53,0.005994842503189409,test,0.6461538461538462,0.05445276765533084,0.6091503267973856,0.06323873171064828,0.6153474903474904,0.05681767286071785 +flat_mae,patch,logistic,adhd200_dx,54,0.005994842503189409,train,0.7452054794520548,0.021071025374662024,0.7365929742606834,0.022217343280271532,0.7340935458264639,0.022009817256623248 +flat_mae,patch,logistic,adhd200_dx,54,0.005994842503189409,test,0.6,0.0596992462263972,0.5775,0.0639360236099825,0.5791505791505791,0.06090105025419816 +flat_mae,patch,logistic,adhd200_dx,55,0.005994842503189409,train,0.7561643835616438,0.021777220344946144,0.7484298647089345,0.02278692510181753,0.7459546925566343,0.022642718389953697 +flat_mae,patch,logistic,adhd200_dx,55,0.005994842503189409,test,0.5076923076923077,0.06007908791529484,0.5019157088122606,0.060994355514617106,0.5024131274131274,0.061063010299507045 +flat_mae,patch,logistic,adhd200_dx,56,0.000774263682681127,train,0.6712328767123288,0.022477427638344316,0.6523809523809523,0.024435137593978147,0.652057763937229,0.023300215120201074 +flat_mae,patch,logistic,adhd200_dx,56,0.000774263682681127,test,0.676923076923077,0.05735770868472808,0.6655231560891939,0.06019946594551272,0.6640926640926641,0.059036032531544984 +flat_mae,patch,logistic,adhd200_dx,57,0.046415888336127774,train,0.8547945205479452,0.018531901359183006,0.8510330276218419,0.019189396484431548,0.8484001953959822,0.019384552096070845 +flat_mae,patch,logistic,adhd200_dx,57,0.046415888336127774,test,0.5230769230769231,0.06137961036083022,0.5115151515151515,0.06264185917943703,0.5115830115830116,0.06193553059962164 +flat_mae,patch,logistic,adhd200_dx,58,0.005994842503189409,train,0.7205479452054795,0.022415510808118804,0.7119669493098967,0.023515412095332932,0.7100964767661965,0.02330587155938198 +flat_mae,patch,logistic,adhd200_dx,58,0.005994842503189409,test,0.6,0.05795938998621331,0.5921814671814671,0.059640145656202175,0.5921814671814671,0.059197732043297736 +flat_mae,patch,logistic,adhd200_dx,59,0.005994842503189409,train,0.7424657534246575,0.022033853752869748,0.732337889284154,0.0233495181436311,0.7295139524943518,0.02292739989000903 +flat_mae,patch,logistic,adhd200_dx,59,0.005994842503189409,test,0.6307692307692307,0.05717789948353395,0.6153846153846154,0.060156752194153104,0.6148648648648649,0.05856493872847476 +flat_mae,patch,logistic,adhd200_dx,60,0.005994842503189409,train,0.7479452054794521,0.022120172646383173,0.7391561024111359,0.02320620070801842,0.7365207302924833,0.02292473994913093 +flat_mae,patch,logistic,adhd200_dx,60,0.005994842503189409,test,0.6461538461538462,0.057347267697999665,0.6289401836684041,0.06108088066371084,0.6283783783783784,0.05897590584360272 +flat_mae,patch,logistic,adhd200_dx,61,0.005994842503189409,train,0.7315068493150685,0.023483227905660802,0.7232623630624497,0.024464734159223366,0.7212401538743359,0.024280430285051082 +flat_mae,patch,logistic,adhd200_dx,61,0.005994842503189409,test,0.5846153846153846,0.06233158895976037,0.5699583435432491,0.06536864955769466,0.5699806949806949,0.06401675229409352 +flat_mae,patch,logistic,adhd200_dx,62,0.005994842503189409,train,0.7315068493150685,0.023393990339657958,0.7232623630624497,0.02435356755619777,0.7212401538743359,0.024147990329672502 +flat_mae,patch,logistic,adhd200_dx,62,0.005994842503189409,test,0.5692307692307692,0.057277367299254665,0.5608108108108107,0.05885821991363949,0.5608108108108107,0.05845363856162681 +flat_mae,patch,logistic,adhd200_dx,63,0.005994842503189409,train,0.7424657534246575,0.02324365929676784,0.7350660983444527,0.024194549261381027,0.7331013006045063,0.024100738061962328 +flat_mae,patch,logistic,adhd200_dx,63,0.005994842503189409,test,0.6307692307692307,0.057871115727130745,0.6153846153846154,0.06087284249077606,0.6148648648648649,0.05924656267876491 +flat_mae,patch,logistic,adhd200_dx,64,0.005994842503189409,train,0.7178082191780822,0.02152930962264983,0.7082696381596816,0.022538412629080424,0.7062343530561153,0.022226661610875487 +flat_mae,patch,logistic,adhd200_dx,64,0.005994842503189409,test,0.6307692307692307,0.05759535648606923,0.6198830409356726,0.05973060010525334,0.6192084942084942,0.05881793812709332 +flat_mae,patch,logistic,adhd200_dx,65,0.005994842503189409,train,0.7342465753424657,0.02245429644379642,0.7228549734244495,0.02384621981880634,0.7200799902302009,0.023363833734416885 +flat_mae,patch,logistic,adhd200_dx,65,0.005994842503189409,test,0.6923076923076923,0.051043325372557354,0.6697154471544715,0.057985797162748626,0.6689189189189189,0.0540220902805426 +flat_mae,patch,logistic,adhd200_dx,66,0.000774263682681127,train,0.6904109589041096,0.024489212395216734,0.6747880938300808,0.02615451244759823,0.6733528729315503,0.025224054866816087 +flat_mae,patch,logistic,adhd200_dx,66,0.000774263682681127,test,0.6153846153846154,0.06035869115241927,0.5966741126830479,0.06392069295021832,0.597007722007722,0.061603147927041454 +flat_mae,patch,logistic,adhd200_dx,67,0.005994842503189409,train,0.7534246575342466,0.02242259469512171,0.7437277663358921,0.023784374006545435,0.7406576296024913,0.023421303147492585 +flat_mae,patch,logistic,adhd200_dx,67,0.005994842503189409,test,0.7076923076923077,0.05091818707640649,0.6834145091002307,0.058893582272055885,0.6824324324324325,0.054201730661821414 +flat_mae,patch,logistic,adhd200_dx,68,0.000774263682681127,train,0.6794520547945205,0.022651378799782677,0.6545489843958551,0.025690738160869777,0.6557519692251328,0.0237640671607502 +flat_mae,patch,logistic,adhd200_dx,68,0.000774263682681127,test,0.6615384615384615,0.055723612111434076,0.6425000000000001,0.060220122037863366,0.6418918918918919,0.0576464201678257 +flat_mae,patch,logistic,adhd200_dx,69,0.000774263682681127,train,0.684931506849315,0.023582962639436714,0.672175318843183,0.024924393623283105,0.6706509128656042,0.0243344584099989 +flat_mae,patch,logistic,adhd200_dx,69,0.000774263682681127,test,0.6,0.06001921585783464,0.588206627680312,0.06206177688483114,0.5878378378378378,0.06077687950663774 +flat_mae,patch,logistic,adhd200_dx,70,0.005994842503189409,train,0.7424657534246575,0.02199505497231431,0.732337889284154,0.02333492901203634,0.7295139524943518,0.02294244803745171 +flat_mae,patch,logistic,adhd200_dx,70,0.005994842503189409,test,0.5538461538461539,0.06411525125730212,0.5469838981014179,0.06512638175390686,0.5472972972972974,0.06518901553639884 +flat_mae,patch,logistic,adhd200_dx,71,0.046415888336127774,train,0.8383561643835616,0.018528606498405455,0.8344594854292062,0.01908160103094958,0.8324021493558039,0.019173938583143986 +flat_mae,patch,logistic,adhd200_dx,71,0.046415888336127774,test,0.5846153846153846,0.06248395959844888,0.5810455956075435,0.06280915458431627,0.583011583011583,0.06307454313582861 +flat_mae,patch,logistic,adhd200_dx,72,0.005994842503189409,train,0.7178082191780822,0.022903454142813993,0.7070329242158582,0.023987305796632722,0.7047994138120535,0.023521101716121758 +flat_mae,patch,logistic,adhd200_dx,72,0.005994842503189409,test,0.6615384615384615,0.05432500051056947,0.6474358974358974,0.057321260081157406,0.6462355212355213,0.055616921762780325 +flat_mae,patch,logistic,adhd200_dx,73,0.000774263682681127,train,0.6794520547945205,0.02404418276244443,0.6632761679479597,0.025591795517232268,0.6622091958234109,0.0247069796467458 +flat_mae,patch,logistic,adhd200_dx,73,0.000774263682681127,test,0.5692307692307692,0.06181969583311946,0.5512820512820513,0.06467651806891489,0.5521235521235521,0.06299703143727894 +flat_mae,patch,logistic,adhd200_dx,74,0.005994842503189409,train,0.7178082191780822,0.02126432598019523,0.7063831116595465,0.022637475824904447,0.7040819441900226,0.02213482474442921 +flat_mae,patch,logistic,adhd200_dx,74,0.005994842503189409,test,0.6923076923076923,0.05380280452864821,0.6794871794871795,0.05750331268789716,0.6776061776061776,0.055714825663560584 +flat_mae,patch,logistic,adhd200_dx,75,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adhd200_dx,75,1291.5496650148827,test,0.5384615384615384,0.060778414106504745,0.5294401544401545,0.061237400555991285,0.5294401544401545,0.06089355572747354 +flat_mae,patch,logistic,adhd200_dx,76,0.005994842503189409,train,0.7479452054794521,0.021859975756249175,0.7386038111844564,0.023055830279661158,0.7358032606704524,0.022697403319461 +flat_mae,patch,logistic,adhd200_dx,76,0.005994842503189409,test,0.5692307692307692,0.05179901075110314,0.5075757575757576,0.06287803392626735,0.5304054054054055,0.053225202068004 +flat_mae,patch,logistic,adhd200_dx,77,0.046415888336127774,train,0.8356164383561644,0.018959805980607848,0.8305687937117039,0.019897251323891675,0.8271050864016609,0.02004467341918679 +flat_mae,patch,logistic,adhd200_dx,77,0.046415888336127774,test,0.6923076923076923,0.058849433794966675,0.6794871794871795,0.06282439554861471,0.6776061776061776,0.06089616283686193 +flat_mae,patch,logistic,adhd200_dx,78,0.005994842503189409,train,0.7506849315068493,0.02280786951066863,0.7422576414808837,0.023770843088260715,0.7396653843805336,0.023507341471443465 +flat_mae,patch,logistic,adhd200_dx,78,0.005994842503189409,test,0.5692307692307692,0.05858166605375043,0.545,0.06235302750701073,0.5477799227799228,0.059385757070235 +flat_mae,patch,logistic,adhd200_dx,79,0.000774263682681127,train,0.684931506849315,0.022922781273109115,0.672175318843183,0.02429211004565347,0.6706509128656042,0.023699621466325652 +flat_mae,patch,logistic,adhd200_dx,79,0.000774263682681127,test,0.6307692307692307,0.05888529819229301,0.6153846153846154,0.061935513292029815,0.6148648648648649,0.0601274479304864 +flat_mae,patch,logistic,adhd200_dx,80,0.005994842503189409,train,0.7397260273972602,0.02203822810123347,0.7272712972211954,0.023815987813135934,0.7242168895402088,0.023196803664004995 +flat_mae,patch,logistic,adhd200_dx,80,0.005994842503189409,test,0.6153846153846154,0.06308676095888918,0.6018132810585641,0.06587239449155134,0.6013513513513513,0.06461960731296817 +flat_mae,patch,logistic,adhd200_dx,81,0.005994842503189409,train,0.7506849315068493,0.02245269516918387,0.7432776064491695,0.02325824318420641,0.7411003236245954,0.023059618413148575 +flat_mae,patch,logistic,adhd200_dx,81,0.005994842503189409,test,0.5692307692307692,0.05511574909965905,0.5376016260162602,0.06039522925078285,0.5434362934362934,0.056310999201381384 +flat_mae,patch,logistic,adhd200_dx,82,0.005994842503189409,train,0.7232876712328767,0.02279176155589541,0.7120844104622738,0.024124939229739666,0.7096537827440923,0.023643918150573807 +flat_mae,patch,logistic,adhd200_dx,82,0.005994842503189409,test,0.7846153846153846,0.050016603160510376,0.7804054054054055,0.05140204487493186,0.7804054054054055,0.051498286196021065 +flat_mae,patch,logistic,adhd200_dx,83,0.005994842503189409,train,0.7205479452054795,0.022573599480526466,0.7089041095890412,0.023836310281127267,0.706509128656042,0.023300533864154815 +flat_mae,patch,logistic,adhd200_dx,83,0.005994842503189409,test,0.676923076923077,0.056431943616670074,0.6612062546537603,0.06041870055633723,0.6597490347490347,0.05835470331147598 +flat_mae,patch,logistic,adhd200_dx,84,0.005994842503189409,train,0.7506849315068493,0.020737721623704002,0.74059090447591,0.021999739982055944,0.737512975514441,0.021599977252706144 +flat_mae,patch,logistic,adhd200_dx,84,0.005994842503189409,test,0.5692307692307692,0.060329666326387504,0.564176245210728,0.06156845829391082,0.5651544401544402,0.06179451567396361 +flat_mae,patch,logistic,adhd200_dx,85,0.000774263682681127,train,0.6794520547945205,0.023298080510018505,0.6556298333185495,0.026354911358614886,0.6564694388471637,0.02446285829842334 +flat_mae,patch,logistic,adhd200_dx,85,0.000774263682681127,test,0.6153846153846154,0.05566441290362565,0.5834401435529352,0.06273048262671767,0.5883204633204633,0.05767657798248015 +flat_mae,patch,logistic,adhd200_dx,86,0.000774263682681127,train,0.6931506849315069,0.02356457197478958,0.6788587229763701,0.02544350282981262,0.6772149966416315,0.024634018197802834 +flat_mae,patch,logistic,adhd200_dx,86,0.000774263682681127,test,0.5692307692307692,0.058432381393079234,0.5289855072463768,0.0649026798988492,0.5390926640926641,0.05958981332277602 +flat_mae,patch,logistic,adhd200_dx,87,0.046415888336127774,train,0.8301369863013699,0.01904196785231235,0.8245736434108527,0.01995853980208208,0.8208157782255603,0.020009995229985793 +flat_mae,patch,logistic,adhd200_dx,87,0.046415888336127774,test,0.5538461538461539,0.05879911443200625,0.5381034060279344,0.06168572129610213,0.5386100386100386,0.06012729464030759 +flat_mae,patch,logistic,adhd200_dx,88,0.000774263682681127,train,0.6958904109589041,0.023975023595965383,0.6842781998831093,0.02519433908865228,0.6825120595957745,0.024713594874282964 +flat_mae,patch,logistic,adhd200_dx,88,0.000774263682681127,test,0.6,0.05912673380872289,0.5921814671814671,0.06084917014382201,0.5921814671814671,0.06065967007675859 +flat_mae,patch,logistic,adhd200_dx,89,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adhd200_dx,89,166.81005372000556,test,0.47692307692307695,0.06281925608371403,0.47078544061302685,0.06317157185228982,0.471042471042471,0.06358919400559768 +flat_mae,patch,logistic,adhd200_dx,90,0.000774263682681127,train,0.673972602739726,0.02443981259865517,0.6575202050068993,0.0259625644274929,0.6566373572693411,0.0250634531195294 +flat_mae,patch,logistic,adhd200_dx,90,0.000774263682681127,test,0.5538461538461539,0.0591106554336764,0.5250692869740489,0.06317831756431101,0.5299227799227799,0.05971743371251455 +flat_mae,patch,logistic,adhd200_dx,91,0.046415888336127774,train,0.8191780821917808,0.020019385613394194,0.8146580907244414,0.02064476652072594,0.8125419796055444,0.020708185479343902 +flat_mae,patch,logistic,adhd200_dx,91,0.046415888336127774,test,0.6,0.058567159648980016,0.570630081300813,0.0646465465372136,0.5748069498069498,0.060181872575289286 +flat_mae,patch,logistic,adhd200_dx,92,0.005994842503189409,train,0.7342465753424657,0.021793066946523044,0.7228549734244495,0.023269847424473963,0.7200799902302009,0.02274203380823707 +flat_mae,patch,logistic,adhd200_dx,92,0.005994842503189409,test,0.676923076923077,0.05708894752046217,0.6612062546537603,0.06110553466928374,0.6597490347490347,0.0589560118125476 +flat_mae,patch,logistic,adhd200_dx,93,0.046415888336127774,train,0.810958904109589,0.019010943703144868,0.8041617094734878,0.02000953766788042,0.8002381388532698,0.019952491219442453 +flat_mae,patch,logistic,adhd200_dx,93,0.046415888336127774,test,0.6923076923076923,0.05280181994353142,0.6697154471544715,0.059289230778099195,0.6689189189189189,0.05548903374586729 +flat_mae,patch,logistic,adhd200_dx,94,0.005994842503189409,train,0.7506849315068493,0.021489354021776038,0.7417205153925708,0.02273731023324428,0.7389479147585027,0.022429911195537267 +flat_mae,patch,logistic,adhd200_dx,94,0.005994842503189409,test,0.6461538461538462,0.052336381272817555,0.6091503267973856,0.062270823833273446,0.6153474903474904,0.055175948049973986 +flat_mae,patch,logistic,adhd200_dx,95,0.005994842503189409,train,0.7506849315068493,0.02302859987243729,0.7427766032417196,0.02407791101180649,0.7403828540025645,0.02387482824838363 +flat_mae,patch,logistic,adhd200_dx,95,0.005994842503189409,test,0.5384615384615384,0.06088927578256653,0.5248538011695907,0.0632338117728356,0.525096525096525,0.06217760333052334 +flat_mae,patch,logistic,adhd200_dx,96,0.046415888336127774,train,0.8191780821917808,0.020771789695120158,0.8149769585253457,0.021414596648098368,0.8132594492275753,0.021562735638098057 +flat_mae,patch,logistic,adhd200_dx,96,0.046415888336127774,test,0.6153846153846154,0.06245601339716982,0.61207925519217,0.0629339416847213,0.6143822393822393,0.06314975089035861 +flat_mae,patch,logistic,adhd200_dx,97,0.005994842503189409,train,0.7424657534246575,0.02245084102463546,0.7311128526645768,0.024068196409349332,0.72807901325029,0.023492146117618528 +flat_mae,patch,logistic,adhd200_dx,97,0.005994842503189409,test,0.6,0.050847082500538494,0.5427489177489178,0.06391907202699812,0.5617760617760618,0.05343417684276163 +flat_mae,patch,logistic,adhd200_dx,98,0.005994842503189409,train,0.7232876712328767,0.022774276442509154,0.7100463265193762,0.024230423014134896,0.7075013738779996,0.02348809186937375 +flat_mae,patch,logistic,adhd200_dx,98,0.005994842503189409,test,0.6615384615384615,0.056567705675975466,0.6366869918699187,0.06278374626024745,0.6375482625482626,0.05860472475160718 +flat_mae,patch,logistic,adhd200_dx,99,0.005994842503189409,train,0.7342465753424657,0.02432699240719367,0.7252636398202826,0.02550766026510494,0.7229498687183245,0.025207142239024632 +flat_mae,patch,logistic,adhd200_dx,99,0.005994842503189409,test,0.6153846153846154,0.05631440901511703,0.6018132810585641,0.059012126217700835,0.6013513513513513,0.05775012979383391 +flat_mae,patch,logistic,adhd200_dx,100,0.005994842503189409,train,0.7342465753424657,0.02234084621596364,0.7252636398202826,0.023466758468510557,0.7229498687183245,0.023162020019101195 +flat_mae,patch,logistic,adhd200_dx,100,0.005994842503189409,test,0.6307692307692307,0.054595888177747964,0.6036585365853658,0.061360097348893486,0.6061776061776062,0.0569516116460339 diff --git a/input_space_v3/flat_lr1e-3_5/eval_v2/adhd200_dx__patch__logistic/log.txt b/input_space_v3/flat_lr1e-3_5/eval_v2/adhd200_dx__patch__logistic/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..690222132e0bdd8d41094201b8e86189275aa096 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_5/eval_v2/adhd200_dx__patch__logistic/log.txt @@ -0,0 +1,241 @@ +fMRI foundation model logistic probe eval +version: 0.1.dev86+gf97f52698 +sha: bcce2b486277d3a5b520775efd9cdf1a2affce36, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-04-08 22:28:21 +config: +output_root: experiments/input_space_v3/output +name_prefix: eval_logistic +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_5; eval v2 (adhd200_dx patch logistic) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: input_space_v3/flat_lr1e-3_5/eval_v2/adhd200_dx__patch__logistic +model: flat_mae +representation: patch +dataset: adhd200_dx +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/eval_v2/adhd200_dx__patch__logistic +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=True, reg_tokens=0, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: adhd200_dx (flat) +train (n=301): +HFDataset( + dataset=Dataset({ + features: ['sub', 'site', 'gender', 'dx', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 301 +}), + labels=['ADHD' 'Control'], + counts=[131 170] +) + +validation (n=64): +HFDataset( + dataset=Dataset({ + features: ['sub', 'site', 'gender', 'dx', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 64 +}), + labels=['ADHD' 'Control'], + counts=[28 36] +) + +test (n=65): +HFDataset( + dataset=Dataset({ + features: ['sub', 'site', 'gender', 'dx', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 65 +}), + labels=['ADHD' 'Control'], + counts=[28 37] +) + +extracting features for all splits +extract (train) [ 0/151] eta: 0:12:45 time: 5.0719 data: 4.0064 max mem: 2698 +extract (train) [ 20/151] eta: 0:00:57 time: 0.2068 data: 0.0713 max mem: 2851 +extract (train) [ 40/151] eta: 0:00:34 time: 0.1809 data: 0.0604 max mem: 2851 +extract (train) [ 60/151] eta: 0:00:25 time: 0.2112 data: 0.0747 max mem: 2851 +extract (train) [ 80/151] eta: 0:00:18 time: 0.1999 data: 0.0715 max mem: 2851 +extract (train) [100/151] eta: 0:00:12 time: 0.2000 data: 0.0655 max mem: 2851 +extract (train) [120/151] eta: 0:00:07 time: 0.1901 data: 0.0647 max mem: 2851 +extract (train) [140/151] eta: 0:00:02 time: 0.1634 data: 0.0513 max mem: 2851 +extract (train) [150/151] eta: 0:00:00 time: 0.1657 data: 0.0551 max mem: 2851 +extract (train) Total time: 0:00:34 (0.2266 s / it) +extract (validation) [ 0/32] eta: 0:02:06 time: 3.9496 data: 3.7276 max mem: 2851 +extract (validation) [20/32] eta: 0:00:04 time: 0.1903 data: 0.0637 max mem: 2851 +extract (validation) [31/32] eta: 0:00:00 time: 0.1522 data: 0.0458 max mem: 2851 +extract (validation) Total time: 0:00:09 (0.3091 s / it) +extract (test) [ 0/33] eta: 0:02:18 time: 4.1944 data: 4.0421 max mem: 2851 +extract (test) [20/33] eta: 0:00:05 time: 0.2144 data: 0.0769 max mem: 2851 +extract (test) [32/33] eta: 0:00:00 time: 0.1594 data: 0.0531 max mem: 2851 +extract (test) Total time: 0:00:10 (0.3243 s / it) +feature extraction time: 0:00:54 +train features: (301, 768) +validation features: (64, 768) +test features: (65, 768) +evaluating fixed splits +eval results (fixed splits): + +| model | repr | clf | dataset | trial | C | split | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:-----------|:--------|-----------:|:--------|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | adhd200_dx | | 0.00077426 | train | 0.68493 | 0.023491 | 0.67065 | 0.02492 | 0.66922 | 0.024128 | +| flat_mae | patch | logistic | adhd200_dx | | 0.00077426 | test | 0.61538 | 0.057639 | 0.59058 | 0.063539 | 0.59266 | 0.059945 | + + +evaluating random splits (n=100) +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 1, "C": 0.005994842503189409, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.058767619792660264, "f1": 0.5644080416976918, "f1_std": 0.06181326567968907, "bacc": 0.5656370656370656, "bacc_std": 0.05985113975574871} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 2, "C": 0.005994842503189409, "split": "test", "acc": 0.7076923076923077, "acc_std": 0.05602517608209354, "f1": 0.6973780936045086, "f1_std": 0.05896899298516095, "bacc": 0.6954633204633205, "bacc_std": 0.058240692414928324} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 3, "C": 0.005994842503189409, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.061486893778340074, "f1": 0.5125, "f1_std": 0.06535431069970007, "bacc": 0.5164092664092664, "bacc_std": 0.06243658922314471} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 4, "C": 0.046415888336127774, "split": "test", "acc": 0.676923076923077, "acc_std": 0.054551642109149506, "f1": 0.6655231560891939, "f1_std": 0.05804094522874361, "bacc": 0.6640926640926641, "bacc_std": 0.056973664747773343} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 5, "C": 0.005994842503189409, "split": "test", "acc": 0.49230769230769234, "acc_std": 0.0637532224501716, "f1": 0.4879446168536643, "f1_std": 0.06438433948045456, "bacc": 0.4888996138996139, "bacc_std": 0.06503356065462686} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 6, "C": 0.046415888336127774, "split": "test", "acc": 0.6923076923076923, "acc_std": 0.058292581764384024, "f1": 0.6886973180076628, "f1_std": 0.058778103955758824, "bacc": 0.6906370656370657, "bacc_std": 0.05864509935348486} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 7, "C": 0.005994842503189409, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.05790013847568034, "f1": 0.6198830409356726, "f1_std": 0.05985347967221368, "bacc": 0.6192084942084942, "bacc_std": 0.059135040506936916} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 8, "C": 0.005994842503189409, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.06123323535814546, "f1": 0.5966741126830479, "f1_std": 0.06549652528062001, "bacc": 0.597007722007722, "bacc_std": 0.06287288979462803} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 9, "C": 0.005994842503189409, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.06185404465543613, "f1": 0.6018132810585641, "f1_std": 0.06463507273961049, "bacc": 0.6013513513513513, "bacc_std": 0.06329600710588597} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 10, "C": 0.3593813663804626, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.06119547494583365, "f1": 0.44253859348198965, "f1_std": 0.062481272337692836, "bacc": 0.44449806949806947, "bacc_std": 0.06154613142512716} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 11, "C": 0.005994842503189409, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.054824898243914885, "f1": 0.5578231292517006, "f1_std": 0.0593273516058535, "bacc": 0.5612934362934363, "bacc_std": 0.05595768176541273} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 12, "C": 0.005994842503189409, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.05586034996511257, "f1": 0.545, "f1_std": 0.06082057942421427, "bacc": 0.5477799227799228, "bacc_std": 0.05739957577879453} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 13, "C": 0.000774263682681127, "split": "test", "acc": 0.5538461538461539, "acc_std": 0.057471544798608484, "f1": 0.5321419707123356, "f1_std": 0.060046491740810094, "bacc": 0.5342664092664092, "bacc_std": 0.05800877452905307} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 14, "C": 1291.5496650148827, "split": "test", "acc": 0.6, "acc_std": 0.06248359595376702, "f1": 0.5953065134099617, "f1_std": 0.06303480728005004, "bacc": 0.5965250965250966, "bacc_std": 0.06356924377787453} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 15, "C": 0.005994842503189409, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.05952907101457227, "f1": 0.578226387887527, "f1_std": 0.06007513475763612, "bacc": 0.5786679536679536, "bacc_std": 0.060236271874179764} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 16, "C": 0.000774263682681127, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.059479995145302486, "f1": 0.606060606060606, "f1_std": 0.0612540277456109, "bacc": 0.6056949806949807, "bacc_std": 0.06072205273317732} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 17, "C": 0.005994842503189409, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.05998434509773974, "f1": 0.61, "f1_std": 0.0648400717422398, "bacc": 0.6105212355212355, "bacc_std": 0.061849304102088914} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 18, "C": 0.005994842503189409, "split": "test", "acc": 0.676923076923077, "acc_std": 0.05618649419724918, "f1": 0.6655231560891939, "f1_std": 0.05901599202178849, "bacc": 0.6640926640926641, "bacc_std": 0.057782295674758705} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 19, "C": 0.005994842503189409, "split": "test", "acc": 0.676923076923077, "acc_std": 0.054772852084256, "f1": 0.656084656084656, "f1_std": 0.06080862211802793, "bacc": 0.6554054054054055, "bacc_std": 0.05752040712643485} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 20, "C": 0.046415888336127774, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.05531855034104129, "f1": 0.5512820512820513, "f1_std": 0.05833766989591626, "bacc": 0.5521235521235521, "bacc_std": 0.05650388847503729} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 21, "C": 21.54434690031882, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.060275627268437035, "f1": 0.5830363506771205, "f1_std": 0.06045947095696174, "bacc": 0.5873552123552124, "bacc_std": 0.06025461066409738} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 22, "C": 0.000774263682681127, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.06103622748080648, "f1": 0.606060606060606, "f1_std": 0.063224891492281, "bacc": 0.6056949806949807, "bacc_std": 0.06271347359798328} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 23, "C": 0.005994842503189409, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.0529757430255813, "f1": 0.587737843551797, "f1_std": 0.06212023903986025, "bacc": 0.5974903474903475, "bacc_std": 0.05494855306554449} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 24, "C": 0.005994842503189409, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.056307482134958745, "f1": 0.61, "f1_std": 0.060791226870776434, "bacc": 0.6105212355212355, "bacc_std": 0.05779447617699375} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 25, "C": 0.046415888336127774, "split": "test", "acc": 0.6, "acc_std": 0.06400742560472478, "f1": 0.5976190476190476, "f1_std": 0.06428730110439299, "bacc": 0.6008687258687259, "bacc_std": 0.06471513971906379} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 26, "C": 0.005994842503189409, "split": "test", "acc": 0.6923076923076923, "acc_std": 0.05554284235865236, "f1": 0.6832358674463938, "f1_std": 0.057825879580425836, "bacc": 0.6819498069498069, "bacc_std": 0.05690540585566157} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 27, "C": 0.005994842503189409, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.05563508322279298, "f1": 0.61, "f1_std": 0.05989056334128341, "bacc": 0.6105212355212355, "bacc_std": 0.057126852442759744} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 28, "C": 0.000774263682681127, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.054464285024181366, "f1": 0.5376016260162602, "f1_std": 0.05933113816565911, "bacc": 0.5434362934362934, "bacc_std": 0.05568131390001869} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 29, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.060568384746245554, "f1": 0.5833333333333333, "f1_std": 0.06384893967124061, "bacc": 0.5834942084942085, "bacc_std": 0.06207801503236489} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 30, "C": 0.000774263682681127, "split": "test", "acc": 0.5538461538461539, "acc_std": 0.058557419350127995, "f1": 0.5321419707123356, "f1_std": 0.062133966855182146, "bacc": 0.5342664092664092, "bacc_std": 0.059787416767317754} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 31, "C": 0.005994842503189409, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.05748624533196497, "f1": 0.6036585365853658, "f1_std": 0.06345837279287103, "bacc": 0.6061776061776062, "bacc_std": 0.05960312502656322} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 32, "C": 0.3593813663804626, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.05791598894215594, "f1": 0.5248538011695907, "f1_std": 0.05942724136060567, "bacc": 0.525096525096525, "bacc_std": 0.0585086553623215} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 33, "C": 0.005994842503189409, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.05877490105549171, "f1": 0.61207925519217, "f1_std": 0.059746208296140024, "bacc": 0.6143822393822393, "bacc_std": 0.060078307362730586} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 34, "C": 0.005994842503189409, "split": "test", "acc": 0.6461538461538462, "acc_std": 0.0604680677625382, "f1": 0.6431129147767964, "f1_std": 0.061127846253699866, "bacc": 0.6457528957528957, "bacc_std": 0.06131338808218241} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 35, "C": 0.005994842503189409, "split": "test", "acc": 0.6615384615384615, "acc_std": 0.05735919420427133, "f1": 0.6474358974358974, "f1_std": 0.06095479758688411, "bacc": 0.6462355212355213, "bacc_std": 0.059349782664367516} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 36, "C": 0.000774263682681127, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.05674236595943595, "f1": 0.5125, "f1_std": 0.06019548377689636, "bacc": 0.5164092664092664, "bacc_std": 0.05731486466784236} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 37, "C": 0.005994842503189409, "split": "test", "acc": 0.6923076923076923, "acc_std": 0.0528093231862009, "f1": 0.675, "f1_std": 0.0574788077722897, "bacc": 0.6732625482625483, "bacc_std": 0.054813521347461425} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 38, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.05493384940681735, "f1": 0.570630081300813, "f1_std": 0.060788064594913274, "bacc": 0.5748069498069498, "bacc_std": 0.05626250251544979} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 39, "C": 0.005994842503189409, "split": "test", "acc": 0.6461538461538462, "acc_std": 0.05806455497443082, "f1": 0.6233308138070043, "f1_std": 0.06336720869636565, "bacc": 0.6240347490347491, "bacc_std": 0.06004871573816458} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 40, "C": 0.005994842503189409, "split": "test", "acc": 0.7230769230769231, "acc_std": 0.05242390709879376, "f1": 0.7027439024390244, "f1_std": 0.059131835578175466, "bacc": 0.7002895752895753, "bacc_std": 0.05563408415584436} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 41, "C": 0.000774263682681127, "split": "test", "acc": 0.6, "acc_std": 0.0596661243129847, "f1": 0.588206627680312, "f1_std": 0.06173370058551594, "bacc": 0.5878378378378378, "bacc_std": 0.06084829587913847} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 42, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.060577254699946986, "f1": 0.5921814671814671, "f1_std": 0.061610676921627784, "bacc": 0.5921814671814671, "bacc_std": 0.06145525244972158} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 43, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.05800856904665238, "f1": 0.5833333333333333, "f1_std": 0.05975374009547867, "bacc": 0.5834942084942085, "bacc_std": 0.05830002954588878} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 44, "C": 0.046415888336127774, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.05882800122229763, "f1": 0.5966741126830479, "f1_std": 0.06257516244105404, "bacc": 0.597007722007722, "bacc_std": 0.06024687038021029} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 45, "C": 0.005994842503189409, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.05827054631670563, "f1": 0.5045731707317074, "f1_std": 0.06342532074738591, "bacc": 0.5120656370656371, "bacc_std": 0.05913066537873777} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 46, "C": 0.005994842503189409, "split": "test", "acc": 0.6923076923076923, "acc_std": 0.055416905117311135, "f1": 0.675, "f1_std": 0.060313722596862095, "bacc": 0.6732625482625483, "bacc_std": 0.05753067917243245} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 47, "C": 0.005994842503189409, "split": "test", "acc": 0.5076923076923077, "acc_std": 0.06165293967374305, "f1": 0.49317738791423005, "f1_std": 0.06253700601065859, "bacc": 0.49372586872586877, "bacc_std": 0.06169901580468184} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 48, "C": 0.000774263682681127, "split": "test", "acc": 0.7076923076923077, "acc_std": 0.05681256632390138, "f1": 0.6973780936045086, "f1_std": 0.05987764876559988, "bacc": 0.6954633204633205, "bacc_std": 0.05910914752180083} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 49, "C": 0.005994842503189409, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.058205715573677014, "f1": 0.5512820512820513, "f1_std": 0.06089864814234744, "bacc": 0.5521235521235521, "bacc_std": 0.05928107306519364} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 50, "C": 0.005994842503189409, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.05810120531599665, "f1": 0.6153846153846154, "f1_std": 0.06150978701207276, "bacc": 0.6148648648648649, "bacc_std": 0.05966779570736597} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 51, "C": 0.005994842503189409, "split": "test", "acc": 0.6461538461538462, "acc_std": 0.05833004645572149, "f1": 0.6289401836684041, "f1_std": 0.06249868212756579, "bacc": 0.6283783783783784, "bacc_std": 0.06015914463961707} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 52, "C": 0.046415888336127774, "split": "test", "acc": 0.6615384615384615, "acc_std": 0.05822507644157472, "f1": 0.6474358974358974, "f1_std": 0.06163140134299893, "bacc": 0.6462355212355213, "bacc_std": 0.06014396595980233} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 53, "C": 0.005994842503189409, "split": "test", "acc": 0.6461538461538462, "acc_std": 0.05445276765533084, "f1": 0.6091503267973856, "f1_std": 0.06323873171064828, "bacc": 0.6153474903474904, "bacc_std": 0.05681767286071785} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 54, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.0596992462263972, "f1": 0.5775, "f1_std": 0.0639360236099825, "bacc": 0.5791505791505791, "bacc_std": 0.06090105025419816} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 55, "C": 0.005994842503189409, "split": "test", "acc": 0.5076923076923077, "acc_std": 0.06007908791529484, "f1": 0.5019157088122606, "f1_std": 0.060994355514617106, "bacc": 0.5024131274131274, "bacc_std": 0.061063010299507045} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 56, "C": 0.000774263682681127, "split": "test", "acc": 0.676923076923077, "acc_std": 0.05735770868472808, "f1": 0.6655231560891939, "f1_std": 0.06019946594551272, "bacc": 0.6640926640926641, "bacc_std": 0.059036032531544984} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 57, "C": 0.046415888336127774, "split": "test", "acc": 0.5230769230769231, "acc_std": 0.06137961036083022, "f1": 0.5115151515151515, "f1_std": 0.06264185917943703, "bacc": 0.5115830115830116, "bacc_std": 0.06193553059962164} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 58, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.05795938998621331, "f1": 0.5921814671814671, "f1_std": 0.059640145656202175, "bacc": 0.5921814671814671, "bacc_std": 0.059197732043297736} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 59, "C": 0.005994842503189409, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.05717789948353395, "f1": 0.6153846153846154, "f1_std": 0.060156752194153104, "bacc": 0.6148648648648649, "bacc_std": 0.05856493872847476} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 60, "C": 0.005994842503189409, "split": "test", "acc": 0.6461538461538462, "acc_std": 0.057347267697999665, "f1": 0.6289401836684041, "f1_std": 0.06108088066371084, "bacc": 0.6283783783783784, "bacc_std": 0.05897590584360272} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 61, "C": 0.005994842503189409, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.06233158895976037, "f1": 0.5699583435432491, "f1_std": 0.06536864955769466, "bacc": 0.5699806949806949, "bacc_std": 0.06401675229409352} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 62, "C": 0.005994842503189409, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.057277367299254665, "f1": 0.5608108108108107, "f1_std": 0.05885821991363949, "bacc": 0.5608108108108107, "bacc_std": 0.05845363856162681} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 63, "C": 0.005994842503189409, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.057871115727130745, "f1": 0.6153846153846154, "f1_std": 0.06087284249077606, "bacc": 0.6148648648648649, "bacc_std": 0.05924656267876491} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 64, "C": 0.005994842503189409, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.05759535648606923, "f1": 0.6198830409356726, "f1_std": 0.05973060010525334, "bacc": 0.6192084942084942, "bacc_std": 0.05881793812709332} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 65, "C": 0.005994842503189409, "split": "test", "acc": 0.6923076923076923, "acc_std": 0.051043325372557354, "f1": 0.6697154471544715, "f1_std": 0.057985797162748626, "bacc": 0.6689189189189189, "bacc_std": 0.0540220902805426} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 66, "C": 0.000774263682681127, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.06035869115241927, "f1": 0.5966741126830479, "f1_std": 0.06392069295021832, "bacc": 0.597007722007722, "bacc_std": 0.061603147927041454} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 67, "C": 0.005994842503189409, "split": "test", "acc": 0.7076923076923077, "acc_std": 0.05091818707640649, "f1": 0.6834145091002307, "f1_std": 0.058893582272055885, "bacc": 0.6824324324324325, "bacc_std": 0.054201730661821414} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 68, "C": 0.000774263682681127, "split": "test", "acc": 0.6615384615384615, "acc_std": 0.055723612111434076, "f1": 0.6425000000000001, "f1_std": 0.060220122037863366, "bacc": 0.6418918918918919, "bacc_std": 0.0576464201678257} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 69, "C": 0.000774263682681127, "split": "test", "acc": 0.6, "acc_std": 0.06001921585783464, "f1": 0.588206627680312, "f1_std": 0.06206177688483114, "bacc": 0.5878378378378378, "bacc_std": 0.06077687950663774} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 70, "C": 0.005994842503189409, "split": "test", "acc": 0.5538461538461539, "acc_std": 0.06411525125730212, "f1": 0.5469838981014179, "f1_std": 0.06512638175390686, "bacc": 0.5472972972972974, "bacc_std": 0.06518901553639884} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 71, "C": 0.046415888336127774, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.06248395959844888, "f1": 0.5810455956075435, "f1_std": 0.06280915458431627, "bacc": 0.583011583011583, "bacc_std": 0.06307454313582861} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 72, "C": 0.005994842503189409, "split": "test", "acc": 0.6615384615384615, "acc_std": 0.05432500051056947, "f1": 0.6474358974358974, "f1_std": 0.057321260081157406, "bacc": 0.6462355212355213, "bacc_std": 0.055616921762780325} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 73, "C": 0.000774263682681127, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.06181969583311946, "f1": 0.5512820512820513, "f1_std": 0.06467651806891489, "bacc": 0.5521235521235521, "bacc_std": 0.06299703143727894} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 74, "C": 0.005994842503189409, "split": "test", "acc": 0.6923076923076923, "acc_std": 0.05380280452864821, "f1": 0.6794871794871795, "f1_std": 0.05750331268789716, "bacc": 0.6776061776061776, "bacc_std": 0.055714825663560584} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 75, "C": 1291.5496650148827, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.060778414106504745, "f1": 0.5294401544401545, "f1_std": 0.061237400555991285, "bacc": 0.5294401544401545, "bacc_std": 0.06089355572747354} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 76, "C": 0.005994842503189409, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.05179901075110314, "f1": 0.5075757575757576, "f1_std": 0.06287803392626735, "bacc": 0.5304054054054055, "bacc_std": 0.053225202068004} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 77, "C": 0.046415888336127774, "split": "test", "acc": 0.6923076923076923, "acc_std": 0.058849433794966675, "f1": 0.6794871794871795, "f1_std": 0.06282439554861471, "bacc": 0.6776061776061776, "bacc_std": 0.06089616283686193} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 78, "C": 0.005994842503189409, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.05858166605375043, "f1": 0.545, "f1_std": 0.06235302750701073, "bacc": 0.5477799227799228, "bacc_std": 0.059385757070235} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 79, "C": 0.000774263682681127, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.05888529819229301, "f1": 0.6153846153846154, "f1_std": 0.061935513292029815, "bacc": 0.6148648648648649, "bacc_std": 0.0601274479304864} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 80, "C": 0.005994842503189409, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.06308676095888918, "f1": 0.6018132810585641, "f1_std": 0.06587239449155134, "bacc": 0.6013513513513513, "bacc_std": 0.06461960731296817} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 81, "C": 0.005994842503189409, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.05511574909965905, "f1": 0.5376016260162602, "f1_std": 0.06039522925078285, "bacc": 0.5434362934362934, "bacc_std": 0.056310999201381384} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 82, "C": 0.005994842503189409, "split": "test", "acc": 0.7846153846153846, "acc_std": 0.050016603160510376, "f1": 0.7804054054054055, "f1_std": 0.05140204487493186, "bacc": 0.7804054054054055, "bacc_std": 0.051498286196021065} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 83, "C": 0.005994842503189409, "split": "test", "acc": 0.676923076923077, "acc_std": 0.056431943616670074, "f1": 0.6612062546537603, "f1_std": 0.06041870055633723, "bacc": 0.6597490347490347, "bacc_std": 0.05835470331147598} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 84, "C": 0.005994842503189409, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.060329666326387504, "f1": 0.564176245210728, "f1_std": 0.06156845829391082, "bacc": 0.5651544401544402, "bacc_std": 0.06179451567396361} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 85, "C": 0.000774263682681127, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.05566441290362565, "f1": 0.5834401435529352, "f1_std": 0.06273048262671767, "bacc": 0.5883204633204633, "bacc_std": 0.05767657798248015} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 86, "C": 0.000774263682681127, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.058432381393079234, "f1": 0.5289855072463768, "f1_std": 0.0649026798988492, "bacc": 0.5390926640926641, "bacc_std": 0.05958981332277602} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 87, "C": 0.046415888336127774, "split": "test", "acc": 0.5538461538461539, "acc_std": 0.05879911443200625, "f1": 0.5381034060279344, "f1_std": 0.06168572129610213, "bacc": 0.5386100386100386, "bacc_std": 0.06012729464030759} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 88, "C": 0.000774263682681127, "split": "test", "acc": 0.6, "acc_std": 0.05912673380872289, "f1": 0.5921814671814671, "f1_std": 0.06084917014382201, "bacc": 0.5921814671814671, "bacc_std": 0.06065967007675859} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 89, "C": 166.81005372000556, "split": "test", "acc": 0.47692307692307695, "acc_std": 0.06281925608371403, "f1": 0.47078544061302685, "f1_std": 0.06317157185228982, "bacc": 0.471042471042471, "bacc_std": 0.06358919400559768} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 90, "C": 0.000774263682681127, "split": "test", "acc": 0.5538461538461539, "acc_std": 0.0591106554336764, "f1": 0.5250692869740489, "f1_std": 0.06317831756431101, "bacc": 0.5299227799227799, "bacc_std": 0.05971743371251455} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 91, "C": 0.046415888336127774, "split": "test", "acc": 0.6, "acc_std": 0.058567159648980016, "f1": 0.570630081300813, "f1_std": 0.0646465465372136, "bacc": 0.5748069498069498, "bacc_std": 0.060181872575289286} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 92, "C": 0.005994842503189409, "split": "test", "acc": 0.676923076923077, "acc_std": 0.05708894752046217, "f1": 0.6612062546537603, "f1_std": 0.06110553466928374, "bacc": 0.6597490347490347, "bacc_std": 0.0589560118125476} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 93, "C": 0.046415888336127774, "split": "test", "acc": 0.6923076923076923, "acc_std": 0.05280181994353142, "f1": 0.6697154471544715, "f1_std": 0.059289230778099195, "bacc": 0.6689189189189189, "bacc_std": 0.05548903374586729} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 94, "C": 0.005994842503189409, "split": "test", "acc": 0.6461538461538462, "acc_std": 0.052336381272817555, "f1": 0.6091503267973856, "f1_std": 0.062270823833273446, "bacc": 0.6153474903474904, "bacc_std": 0.055175948049973986} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 95, "C": 0.005994842503189409, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.06088927578256653, "f1": 0.5248538011695907, "f1_std": 0.0632338117728356, "bacc": 0.525096525096525, "bacc_std": 0.06217760333052334} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 96, "C": 0.046415888336127774, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.06245601339716982, "f1": 0.61207925519217, "f1_std": 0.0629339416847213, "bacc": 0.6143822393822393, "bacc_std": 0.06314975089035861} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 97, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.050847082500538494, "f1": 0.5427489177489178, "f1_std": 0.06391907202699812, "bacc": 0.5617760617760618, "bacc_std": 0.05343417684276163} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 98, "C": 0.005994842503189409, "split": "test", "acc": 0.6615384615384615, "acc_std": 0.056567705675975466, "f1": 0.6366869918699187, "f1_std": 0.06278374626024745, "bacc": 0.6375482625482626, "bacc_std": 0.05860472475160718} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 99, "C": 0.005994842503189409, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.05631440901511703, "f1": 0.6018132810585641, "f1_std": 0.059012126217700835, "bacc": 0.6013513513513513, "bacc_std": 0.05775012979383391} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 100, "C": 0.005994842503189409, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.054595888177747964, "f1": 0.6036585365853658, "f1_std": 0.061360097348893486, "bacc": 0.6061776061776062, "bacc_std": 0.0569516116460339} +eval results (random splits): + +| model | repr | clf | dataset | split | n_trials | C | C_std | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:-----------|:--------|-----------:|-------:|--------:|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | adhd200_dx | train | 100 | 27.732 | 182.23 | 0.75663 | 0.071182 | 0.74669 | 0.074996 | 0.74439 | 0.075028 | +| flat_mae | patch | logistic | adhd200_dx | test | 100 | 27.732 | 182.23 | 0.61292 | 0.057801 | 0.59543 | 0.059455 | 0.5968 | 0.057899 | + + +done! total time: 0:04:58 diff --git a/input_space_v3/flat_lr1e-3_5/eval_v2/adni_ad_vs_cn__patch__logistic/config.yaml b/input_space_v3/flat_lr1e-3_5/eval_v2/adni_ad_vs_cn__patch__logistic/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..e90c939e7f3e05e783668edd1d9cfc94ea59f248 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_5/eval_v2/adni_ad_vs_cn__patch__logistic/config.yaml @@ -0,0 +1,30 @@ +output_root: experiments/input_space_v3/output +name_prefix: eval_logistic +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_5; eval v2 (adni_ad_vs_cn patch logistic) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: input_space_v3/flat_lr1e-3_5/eval_v2/adni_ad_vs_cn__patch__logistic +model: flat_mae +representation: patch +dataset: adni_ad_vs_cn +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/eval_v2/adni_ad_vs_cn__patch__logistic +remote_dir: null diff --git a/input_space_v3/flat_lr1e-3_5/eval_v2/adni_ad_vs_cn__patch__logistic/eval_table.csv b/input_space_v3/flat_lr1e-3_5/eval_v2/adni_ad_vs_cn__patch__logistic/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..0f918bffea66a709dd049d4de01ba0f87ebf2b03 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_5/eval_v2/adni_ad_vs_cn__patch__logistic/eval_table.csv @@ -0,0 +1,203 @@ +model,repr,clf,dataset,trial,C,split,acc,acc_std,f1,f1_std,bacc,bacc_std +flat_mae,patch,logistic,adni_ad_vs_cn,,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,,2.782559402207126,test,0.7317073170731707,0.06421074389206156,0.6232247284878863,0.0833772214857729,0.6284722222222222,0.08771620417529954 +flat_mae,patch,logistic,adni_ad_vs_cn,1,0.005994842503189409,train,0.8265582655826558,0.014079477320277521,0.6937441643323996,0.03088903351921361,0.6643314980688635,0.026328047357988653 +flat_mae,patch,logistic,adni_ad_vs_cn,1,0.005994842503189409,test,0.7804878048780488,0.02458149408150368,0.5275288092189501,0.0853385069223417,0.55,0.05039206286708255 +flat_mae,patch,logistic,adni_ad_vs_cn,2,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,2,2.782559402207126,test,0.7073170731707317,0.0654904346113233,0.603225806451613,0.08456097177344545,0.603225806451613,0.08511817548636101 +flat_mae,patch,logistic,adni_ad_vs_cn,3,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,3,1291.5496650148827,test,0.6341463414634146,0.06359634379023703,0.48621553884711777,0.07121864111235741,0.48709677419354835,0.06925912104607539 +flat_mae,patch,logistic,adni_ad_vs_cn,4,0.3593813663804626,train,0.981029810298103,0.007257569960859325,0.9729123189697663,0.010626432051906968,0.9633494946174705,0.014383697594550871 +flat_mae,patch,logistic,adni_ad_vs_cn,4,0.3593813663804626,test,0.8536585365853658,0.05776884747206786,0.8016129032258064,0.07713014469925067,0.8016129032258064,0.07939894892585604 +flat_mae,patch,logistic,adni_ad_vs_cn,5,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,5,21.54434690031882,test,0.6585365853658537,0.055302424179836523,0.4564393939393939,0.0681875110605505,0.4693548387096774,0.060284501608914146 +flat_mae,patch,logistic,adni_ad_vs_cn,6,0.046415888336127774,train,0.8915989159891599,0.014303600053602962,0.8326530612244898,0.024362325319004115,0.8038663817897937,0.026354720509220733 +flat_mae,patch,logistic,adni_ad_vs_cn,6,0.046415888336127774,test,0.7560975609756098,0.05113805369189952,0.6117424242424243,0.08754684704957878,0.6016129032258064,0.07427900436242992 +flat_mae,patch,logistic,adni_ad_vs_cn,7,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,7,1291.5496650148827,test,0.8292682926829268,0.0567436600037804,0.7602339181286549,0.08435914526217973,0.7516129032258064,0.08697169339879202 +flat_mae,patch,logistic,adni_ad_vs_cn,8,10000.0,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,8,10000.0,test,0.7317073170731707,0.06765716494995952,0.6676492262343405,0.08019646065184916,0.6870967741935483,0.08633188025513573 +flat_mae,patch,logistic,adni_ad_vs_cn,9,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,9,166.81005372000556,test,0.6341463414634146,0.07333354244377376,0.5467943994104643,0.08428791488963022,0.5548387096774194,0.09193662313951718 +flat_mae,patch,logistic,adni_ad_vs_cn,10,0.3593813663804626,train,0.986449864498645,0.005794582962291279,0.9808134274809954,0.008335007908006196,0.9749774015942148,0.01149157868197632 +flat_mae,patch,logistic,adni_ad_vs_cn,10,0.3593813663804626,test,0.7560975609756098,0.06010997258594587,0.6440972222222222,0.0893730804803424,0.635483870967742,0.08475611703971793 +flat_mae,patch,logistic,adni_ad_vs_cn,11,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,11,21.54434690031882,test,0.7804878048780488,0.048524106742501134,0.6328358208955224,0.09384905479396635,0.6177419354838709,0.07659031245881572 +flat_mae,patch,logistic,adni_ad_vs_cn,12,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,12,21.54434690031882,test,0.6341463414634146,0.07331212355296585,0.5684210526315789,0.07929486656280713,0.5887096774193548,0.09018606336332674 +flat_mae,patch,logistic,adni_ad_vs_cn,13,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,13,2.782559402207126,test,0.7560975609756098,0.051663372951246456,0.6117424242424243,0.08821984261711012,0.6016129032258064,0.07587998321189358 +flat_mae,patch,logistic,adni_ad_vs_cn,14,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,14,166.81005372000556,test,0.7073170731707317,0.06919824696125192,0.603225806451613,0.08970592389053395,0.603225806451613,0.08945092213825398 +flat_mae,patch,logistic,adni_ad_vs_cn,15,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,15,2.782559402207126,test,0.6829268292682927,0.06910726731822596,0.6259649122807017,0.07529631281904256,0.6548387096774193,0.08338519190436752 +flat_mae,patch,logistic,adni_ad_vs_cn,16,0.3593813663804626,train,0.9728997289972899,0.008072489784800598,0.9608013937282229,0.012089631482822284,0.9459076341523543,0.016309052814795846 +flat_mae,patch,logistic,adni_ad_vs_cn,16,0.3593813663804626,test,0.8048780487804879,0.057748578119607465,0.7152777777777778,0.08601160714642149,0.7016129032258065,0.08319196511270312 +flat_mae,patch,logistic,adni_ad_vs_cn,17,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,17,166.81005372000556,test,0.6585365853658537,0.07410968285053593,0.5876436781609196,0.08155959742787672,0.6048387096774194,0.09011673871870023 +flat_mae,patch,logistic,adni_ad_vs_cn,18,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,18,2.782559402207126,test,0.8536585365853658,0.03961296995251998,0.7415966386554622,0.09682956906426606,0.7,0.08120658840266597 +flat_mae,patch,logistic,adni_ad_vs_cn,19,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,19,2.782559402207126,test,0.7317073170731707,0.06015676526294157,0.5918552036199095,0.0895098015201144,0.5854838709677419,0.07911657615360052 +flat_mae,patch,logistic,adni_ad_vs_cn,20,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,20,166.81005372000556,test,0.7073170731707317,0.06989350273926463,0.6272727272727273,0.08242168137735993,0.6370967741935484,0.0871728494520036 +flat_mae,patch,logistic,adni_ad_vs_cn,21,0.046415888336127774,train,0.9132791327913279,0.012405957075035693,0.8661224489795918,0.021145768888510965,0.8341893335524694,0.02408508673875873 +flat_mae,patch,logistic,adni_ad_vs_cn,21,0.046415888336127774,test,0.7804878048780488,0.05417162670437117,0.6660633484162897,0.0924774456255057,0.6516129032258065,0.08347855164536272 +flat_mae,patch,logistic,adni_ad_vs_cn,22,0.3593813663804626,train,0.981029810298103,0.006904527887041932,0.9729123189697663,0.010109502604347741,0.9633494946174705,0.013824771834218071 +flat_mae,patch,logistic,adni_ad_vs_cn,22,0.3593813663804626,test,0.6829268292682927,0.0537112601286211,0.4696517412935323,0.07005712708025878,0.4854838709677419,0.058310187360803685 +flat_mae,patch,logistic,adni_ad_vs_cn,23,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,23,21.54434690031882,test,0.6829268292682927,0.06816118001062052,0.6259649122807017,0.07464889749089174,0.6548387096774193,0.08500468861403097 +flat_mae,patch,logistic,adni_ad_vs_cn,24,0.005994842503189409,train,0.8319783197831978,0.014276616189301098,0.6995114006514658,0.03149710950079992,0.6678650669734572,0.026490621374003473 +flat_mae,patch,logistic,adni_ad_vs_cn,24,0.005994842503189409,test,0.7560975609756098,0.03161558964539202,0.5119047619047619,0.07564517768144166,0.5338709677419355,0.04854056040222786 +flat_mae,patch,logistic,adni_ad_vs_cn,25,0.046415888336127774,train,0.9214092140921409,0.012699518945609759,0.8815802578431915,0.02060622808285841,0.8556783630536609,0.0238695577241356 +flat_mae,patch,logistic,adni_ad_vs_cn,25,0.046415888336127774,test,0.7560975609756098,0.052505482561240185,0.6117424242424243,0.09145306538218784,0.6016129032258064,0.07886789036809229 +flat_mae,patch,logistic,adni_ad_vs_cn,26,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,26,166.81005372000556,test,0.7560975609756098,0.059669743478031535,0.6440972222222222,0.0893611659129043,0.635483870967742,0.0844951732207625 +flat_mae,patch,logistic,adni_ad_vs_cn,27,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,27,21.54434690031882,test,0.6585365853658537,0.06801579758408634,0.5370967741935484,0.08165852162537643,0.5370967741935484,0.08121682263469909 +flat_mae,patch,logistic,adni_ad_vs_cn,28,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,28,2.782559402207126,test,0.7073170731707317,0.06430045476546652,0.603225806451613,0.08387859361730543,0.603225806451613,0.08356826883878687 +flat_mae,patch,logistic,adni_ad_vs_cn,29,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,29,21.54434690031882,test,0.7560975609756098,0.06457983912688059,0.6893939393939394,0.07983072287503302,0.7032258064516128,0.0850330277389416 +flat_mae,patch,logistic,adni_ad_vs_cn,30,0.046415888336127774,train,0.9024390243902439,0.013871044389656051,0.8478699038021071,0.023881309808832567,0.8149806886350563,0.025963630625818388 +flat_mae,patch,logistic,adni_ad_vs_cn,30,0.046415888336127774,test,0.7317073170731707,0.05701477103871648,0.5918552036199095,0.09062024307000272,0.5854838709677419,0.07993216791268484 +flat_mae,patch,logistic,adni_ad_vs_cn,31,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,31,166.81005372000556,test,0.7073170731707317,0.06403865578586267,0.603225806451613,0.08405787476642411,0.603225806451613,0.08511585200317769 +flat_mae,patch,logistic,adni_ad_vs_cn,32,0.005994842503189409,train,0.8184281842818428,0.01436772029145488,0.6688455201789517,0.03226529989191604,0.6428424685676719,0.02577562662412816 +flat_mae,patch,logistic,adni_ad_vs_cn,32,0.005994842503189409,test,0.8048780487804879,0.05139028441777837,0.6893939393939394,0.09442504810367564,0.667741935483871,0.08377173807374383 +flat_mae,patch,logistic,adni_ad_vs_cn,33,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,33,166.81005372000556,test,0.6341463414634146,0.0738333573927838,0.5998698763825634,0.07409928527338958,0.6564516129032258,0.08589502650051059 +flat_mae,patch,logistic,adni_ad_vs_cn,34,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,34,2.782559402207126,test,0.6829268292682927,0.06850161420087934,0.6259649122807017,0.07608315958332734,0.6548387096774193,0.08534073689375549 +flat_mae,patch,logistic,adni_ad_vs_cn,35,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,35,166.81005372000556,test,0.8048780487804879,0.045823134625044594,0.6554621848739496,0.10101798607269728,0.6338709677419355,0.0801794841428863 +flat_mae,patch,logistic,adni_ad_vs_cn,36,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,36,21.54434690031882,test,0.7073170731707317,0.06126058286118868,0.5729166666666666,0.08285999167163964,0.5693548387096774,0.0765030078370553 +flat_mae,patch,logistic,adni_ad_vs_cn,37,0.005994842503189409,train,0.8373983739837398,0.013401262394652084,0.709204581275612,0.030404669864772048,0.6754458049141261,0.02590712121298276 +flat_mae,patch,logistic,adni_ad_vs_cn,37,0.005994842503189409,test,0.7073170731707317,0.05609756097560976,0.5340909090909092,0.08629011153158576,0.535483870967742,0.0734918503696813 +flat_mae,patch,logistic,adni_ad_vs_cn,38,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,38,166.81005372000556,test,0.7073170731707317,0.07432063916776933,0.6620879120879121,0.07873424465210177,0.7048387096774194,0.08692848712044234 +flat_mae,patch,logistic,adni_ad_vs_cn,39,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,39,166.81005372000556,test,0.6097560975609756,0.05329535629840953,0.3787878787878788,0.020998122390869116,0.4032258064516129,0.03524370335862565 +flat_mae,patch,logistic,adni_ad_vs_cn,40,0.005994842503189409,train,0.8211382113821138,0.014836789285984796,0.6880891393442623,0.030938041486731894,0.6607979291642698,0.026386191987166015 +flat_mae,patch,logistic,adni_ad_vs_cn,40,0.005994842503189409,test,0.7073170731707317,0.046145928941589344,0.4831932773109243,0.0711687295867353,0.5016129032258064,0.05502811541341511 +flat_mae,patch,logistic,adni_ad_vs_cn,41,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,41,21.54434690031882,test,0.7317073170731707,0.06512193294966401,0.6479313036690086,0.08516434580247821,0.6532258064516129,0.08960370165722159 +flat_mae,patch,logistic,adni_ad_vs_cn,42,0.3593813663804626,train,0.983739837398374,0.006373771727388597,0.9768796992481203,0.00923554259330747,0.9691634481058427,0.01258922292372538 +flat_mae,patch,logistic,adni_ad_vs_cn,42,0.3593813663804626,test,0.7073170731707317,0.0657261819479595,0.603225806451613,0.08231324843620222,0.603225806451613,0.08263619830020573 +flat_mae,patch,logistic,adni_ad_vs_cn,43,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,43,166.81005372000556,test,0.6829268292682927,0.06625309753345958,0.5839188134270101,0.08191373700869571,0.5870967741935484,0.08442950861563772 +flat_mae,patch,logistic,adni_ad_vs_cn,44,0.3593813663804626,train,0.978319783197832,0.007284044697723761,0.9689106074648244,0.010744554887966055,0.9575355411290984,0.014653479871941153 +flat_mae,patch,logistic,adni_ad_vs_cn,44,0.3593813663804626,test,0.8292682926829268,0.043859057157051747,0.7144278606965174,0.0911837580016484,0.6838709677419355,0.07880376944717991 +flat_mae,patch,logistic,adni_ad_vs_cn,45,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,45,166.81005372000556,test,0.8292682926829268,0.05852949144006972,0.7759562841530054,0.0759599348206402,0.7854838709677419,0.08160171133256794 +flat_mae,patch,logistic,adni_ad_vs_cn,46,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,46,21.54434690031882,test,0.8048780487804879,0.0604091542164508,0.7515151515151515,0.07337638097497876,0.7693548387096774,0.07857985982710487 +flat_mae,patch,logistic,adni_ad_vs_cn,47,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,47,2.782559402207126,test,0.7804878048780488,0.049412756085949285,0.6328358208955224,0.09532531708977952,0.6177419354838709,0.07855749327887279 +flat_mae,patch,logistic,adni_ad_vs_cn,48,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,48,166.81005372000556,test,0.7073170731707317,0.0670527685156676,0.6620879120879121,0.0717316941186946,0.7048387096774194,0.0806042066330976 +flat_mae,patch,logistic,adni_ad_vs_cn,49,0.046415888336127774,train,0.9051490514905149,0.01379593216718082,0.8528389603582457,0.023530505423252506,0.8207946421234283,0.025992394621807656 +flat_mae,patch,logistic,adni_ad_vs_cn,49,0.046415888336127774,test,0.7317073170731707,0.05188361569544244,0.5512437810945273,0.09134526780870197,0.5516129032258065,0.07327246452981251 +flat_mae,patch,logistic,adni_ad_vs_cn,50,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,50,166.81005372000556,test,0.8048780487804879,0.059493699644937184,0.7354838709677419,0.08285162366280704,0.7354838709677419,0.08489359539459881 +flat_mae,patch,logistic,adni_ad_vs_cn,51,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,51,2.782559402207126,test,0.6829268292682927,0.0717483041978326,0.6259649122807017,0.07942650498827593,0.6548387096774193,0.09044261862234766 +flat_mae,patch,logistic,adni_ad_vs_cn,52,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,52,2.782559402207126,test,0.7804878048780488,0.06236693628217969,0.7119437939110069,0.08108861015550645,0.7193548387096774,0.086544640066532 +flat_mae,patch,logistic,adni_ad_vs_cn,53,0.3593813663804626,train,0.983739837398374,0.006601481390898046,0.9768796992481203,0.009590990657739308,0.9691634481058427,0.013015528144595745 +flat_mae,patch,logistic,adni_ad_vs_cn,53,0.3593813663804626,test,0.7560975609756098,0.05400235745179076,0.6117424242424243,0.09402662527585066,0.6016129032258064,0.08110981565525564 +flat_mae,patch,logistic,adni_ad_vs_cn,54,0.3593813663804626,train,0.983739837398374,0.006434588272328259,0.9766829555986183,0.00952337902227613,0.9651162790697674,0.013804436467960026 +flat_mae,patch,logistic,adni_ad_vs_cn,54,0.3593813663804626,test,0.6585365853658537,0.06726493208676952,0.5651515151515152,0.0808901384784537,0.5709677419354839,0.08725459268031988 +flat_mae,patch,logistic,adni_ad_vs_cn,55,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,55,21.54434690031882,test,0.7560975609756098,0.06615718667837159,0.7054597701149425,0.07574050412596191,0.7370967741935484,0.08356553635180491 +flat_mae,patch,logistic,adni_ad_vs_cn,56,10000.0,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,56,10000.0,test,0.8048780487804879,0.06172117842966046,0.764367816091954,0.07055384173910768,0.8032258064516129,0.07589095194348704 +flat_mae,patch,logistic,adni_ad_vs_cn,57,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,57,1291.5496650148827,test,0.6585365853658537,0.07246112826925578,0.5651515151515152,0.08519182695531463,0.5709677419354839,0.08946783259763835 +flat_mae,patch,logistic,adni_ad_vs_cn,58,0.3593813663804626,train,0.983739837398374,0.006618014909445814,0.9768796992481203,0.009592126851478262,0.9691634481058427,0.013079575759294903 +flat_mae,patch,logistic,adni_ad_vs_cn,58,0.3593813663804626,test,0.7804878048780488,0.05026471271615739,0.6328358208955224,0.09244237296131863,0.6177419354838709,0.07539572714136962 +flat_mae,patch,logistic,adni_ad_vs_cn,59,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,59,166.81005372000556,test,0.6829268292682927,0.07168016741715809,0.6072218128224024,0.08430410883164094,0.6209677419354839,0.09156920220753284 +flat_mae,patch,logistic,adni_ad_vs_cn,60,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,60,2.782559402207126,test,0.7073170731707317,0.07044814480512766,0.646551724137931,0.08004063898994011,0.6709677419354838,0.08768584402545129 +flat_mae,patch,logistic,adni_ad_vs_cn,61,0.046415888336127774,train,0.9214092140921409,0.01285810505737063,0.8815802578431915,0.020917023688648968,0.8556783630536609,0.02424661690259764 +flat_mae,patch,logistic,adni_ad_vs_cn,61,0.046415888336127774,test,0.6341463414634146,0.06649786084324921,0.48621553884711777,0.07929981538515514,0.48709677419354835,0.07588156498298114 +flat_mae,patch,logistic,adni_ad_vs_cn,62,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,62,166.81005372000556,test,0.7317073170731707,0.059566628444719515,0.5918552036199095,0.0892895272858601,0.5854838709677419,0.07995720109060532 +flat_mae,patch,logistic,adni_ad_vs_cn,63,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,63,166.81005372000556,test,0.7804878048780488,0.05896703522568821,0.6917293233082706,0.0857692043982056,0.685483870967742,0.0858308257886822 +flat_mae,patch,logistic,adni_ad_vs_cn,64,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,64,166.81005372000556,test,0.7317073170731707,0.06049732419193674,0.6232247284878863,0.08514239584531934,0.6193548387096774,0.0833746867286275 +flat_mae,patch,logistic,adni_ad_vs_cn,65,0.3593813663804626,train,0.986449864498645,0.005838875239998889,0.9808134274809954,0.008362421309272745,0.9749774015942148,0.011100944594234502 +flat_mae,patch,logistic,adni_ad_vs_cn,65,0.3593813663804626,test,0.8048780487804879,0.06183480515930997,0.7354838709677419,0.08296285627334479,0.7354838709677419,0.0863680747083327 +flat_mae,patch,logistic,adni_ad_vs_cn,66,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,66,21.54434690031882,test,0.6585365853658537,0.07425055256906457,0.6057692307692308,0.07836818044881141,0.6387096774193548,0.08920684471855844 +flat_mae,patch,logistic,adni_ad_vs_cn,67,0.046415888336127774,train,0.8943089430894309,0.013801309970524192,0.8343520149176422,0.02430027008920064,0.8015859972060153,0.026050084576577703 +flat_mae,patch,logistic,adni_ad_vs_cn,67,0.046415888336127774,test,0.7560975609756098,0.04489063980318528,0.569327731092437,0.0899265670244746,0.567741935483871,0.06751174129971363 +flat_mae,patch,logistic,adni_ad_vs_cn,68,0.046415888336127774,train,0.8970189701897019,0.014297740338232931,0.8425767918088738,0.023632590102177827,0.815494288766538,0.02555641265057358 +flat_mae,patch,logistic,adni_ad_vs_cn,68,0.046415888336127774,test,0.6341463414634146,0.05709816004936762,0.44343891402714936,0.06510463128023876,0.45322580645161287,0.05991620049874688 +flat_mae,patch,logistic,adni_ad_vs_cn,69,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,69,2.782559402207126,test,0.7317073170731707,0.06751154306748414,0.6479313036690086,0.08614474888818278,0.6532258064516129,0.09061978545046577 +flat_mae,patch,logistic,adni_ad_vs_cn,70,0.046415888336127774,train,0.9051490514905149,0.013420391307918203,0.8557063851181499,0.022551713420895802,0.828888980195579,0.025675182907177727 +flat_mae,patch,logistic,adni_ad_vs_cn,70,0.046415888336127774,test,0.8536585365853658,0.04691808143198926,0.7670454545454546,0.08962379159599836,0.7338709677419355,0.08323888838170446 +flat_mae,patch,logistic,adni_ad_vs_cn,71,0.046415888336127774,train,0.9024390243902439,0.013693570374823391,0.8478699038021071,0.023977814916276097,0.8149806886350563,0.026547432381186616 +flat_mae,patch,logistic,adni_ad_vs_cn,71,0.046415888336127774,test,0.7073170731707317,0.033078926040715675,0.4142857142857143,0.011514250991618458,0.46774193548387094,0.021874773672086185 +flat_mae,patch,logistic,adni_ad_vs_cn,72,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,72,21.54434690031882,test,0.7073170731707317,0.04641778054777671,0.4831932773109243,0.07405650033628015,0.5016129032258064,0.0568676630697771 +flat_mae,patch,logistic,adni_ad_vs_cn,73,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,73,2.782559402207126,test,0.7804878048780488,0.06292907918080261,0.7119437939110069,0.0806906356779623,0.7193548387096774,0.08463799389402979 +flat_mae,patch,logistic,adni_ad_vs_cn,74,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,74,166.81005372000556,test,0.7560975609756098,0.06009906554974386,0.6440972222222222,0.09135443821241848,0.635483870967742,0.08662366101269592 +flat_mae,patch,logistic,adni_ad_vs_cn,75,0.005994842503189409,train,0.8373983739837398,0.01356942150539908,0.709204581275612,0.03022902606211144,0.6754458049141261,0.025810774033689438 +flat_mae,patch,logistic,adni_ad_vs_cn,75,0.005994842503189409,test,0.7317073170731707,0.04154594369177018,0.4972129319955407,0.07667784004953351,0.5177419354838709,0.054612496997517426 +flat_mae,patch,logistic,adni_ad_vs_cn,76,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,76,1291.5496650148827,test,0.5853658536585366,0.07274019678579,0.5108771929824562,0.07766951041551493,0.5225806451612903,0.08743738291669953 +flat_mae,patch,logistic,adni_ad_vs_cn,77,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,77,21.54434690031882,test,0.8292682926829268,0.05569294163329124,0.7602339181286549,0.08102426070973019,0.7516129032258064,0.08412642800986044 +flat_mae,patch,logistic,adni_ad_vs_cn,78,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,78,166.81005372000556,test,0.7317073170731707,0.06859880866073997,0.6479313036690086,0.08768752208919921,0.6532258064516129,0.0909148539919565 +flat_mae,patch,logistic,adni_ad_vs_cn,79,0.3593813663804626,train,0.975609756097561,0.008328581278872527,0.9651729815325566,0.012162232047786594,0.9557687566768016,0.015595209450854337 +flat_mae,patch,logistic,adni_ad_vs_cn,79,0.3593813663804626,test,0.8536585365853658,0.056608300650681974,0.8232758620689655,0.06292246245888129,0.8693548387096774,0.0598686473236378 +flat_mae,patch,logistic,adni_ad_vs_cn,80,0.3593813663804626,train,0.981029810298103,0.006825350534524947,0.9731387984733936,0.00977247828487376,0.9673966636535458,0.012399664998721274 +flat_mae,patch,logistic,adni_ad_vs_cn,80,0.3593813663804626,test,0.7073170731707317,0.06789800588276096,0.6272727272727273,0.08223496256648546,0.6370967741935484,0.08681880439793194 +flat_mae,patch,logistic,adni_ad_vs_cn,81,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,81,21.54434690031882,test,0.7073170731707317,0.057372386387613654,0.5340909090909092,0.08734654207578378,0.535483870967742,0.07433279352713974 +flat_mae,patch,logistic,adni_ad_vs_cn,82,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,82,2.782559402207126,test,0.5853658536585366,0.06142081373044429,0.4177109440267335,0.060365278939756246,0.42096774193548386,0.06073978856295284 +flat_mae,patch,logistic,adni_ad_vs_cn,83,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,83,1291.5496650148827,test,0.7560975609756098,0.06598142979604037,0.7054597701149425,0.07588313602813544,0.7370967741935484,0.0832546759130944 +flat_mae,patch,logistic,adni_ad_vs_cn,84,0.046415888336127774,train,0.8970189701897019,0.013690051610243115,0.8394182317911132,0.023659129528268912,0.8073999506943874,0.025567399963967015 +flat_mae,patch,logistic,adni_ad_vs_cn,84,0.046415888336127774,test,0.7317073170731707,0.05850183928122379,0.5918552036199095,0.0884847013642466,0.5854838709677419,0.07905898455268422 +flat_mae,patch,logistic,adni_ad_vs_cn,85,0.005994842503189409,train,0.8130081300813008,0.012838747023616414,0.6495726495726495,0.030390764495462717,0.6271673925548525,0.02337697106080916 +flat_mae,patch,logistic,adni_ad_vs_cn,85,0.005994842503189409,test,0.9024390243902439,0.038378062343538105,0.8446969696969697,0.07673636095637511,0.8,0.07867502780425312 +flat_mae,patch,logistic,adni_ad_vs_cn,86,0.3593813663804626,train,0.989159891598916,0.005469197266673004,0.9847141673570836,0.0077856265877751666,0.9807913550825869,0.010235584292924774 +flat_mae,patch,logistic,adni_ad_vs_cn,86,0.3593813663804626,test,0.7073170731707317,0.06781365095027132,0.6272727272727273,0.08232099750304414,0.6370967741935484,0.087594068655838 +flat_mae,patch,logistic,adni_ad_vs_cn,87,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,87,2.782559402207126,test,0.8048780487804879,0.056010536953784676,0.7354838709677419,0.07782528425870976,0.7354838709677419,0.08066183692108597 +flat_mae,patch,logistic,adni_ad_vs_cn,88,0.3593813663804626,train,0.986449864498645,0.006011336152406807,0.9808134274809954,0.008651564214049664,0.9749774015942148,0.01188986947775532 +flat_mae,patch,logistic,adni_ad_vs_cn,88,0.3593813663804626,test,0.7073170731707317,0.06636676346845467,0.6272727272727273,0.08226082798141872,0.6370967741935484,0.0891092044189309 +flat_mae,patch,logistic,adni_ad_vs_cn,89,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,89,21.54434690031882,test,0.7073170731707317,0.06792897925397241,0.6272727272727273,0.08461009100956969,0.6370967741935484,0.09080778953921825 +flat_mae,patch,logistic,adni_ad_vs_cn,90,0.046415888336127774,train,0.9105691056910569,0.013360423709710105,0.8639517345399699,0.02197135590912456,0.8364697181362479,0.024426221154574344 +flat_mae,patch,logistic,adni_ad_vs_cn,90,0.046415888336127774,test,0.8048780487804879,0.059093207212064326,0.7354838709677419,0.07916802921588748,0.7354838709677419,0.08104690764176906 +flat_mae,patch,logistic,adni_ad_vs_cn,91,0.005994842503189409,train,0.8238482384823849,0.01405215925109896,0.6869820554649266,0.029980886574759953,0.6585175445804914,0.02511499893522947 +flat_mae,patch,logistic,adni_ad_vs_cn,91,0.005994842503189409,test,0.7073170731707317,0.05748690976879015,0.5340909090909092,0.08715468553239285,0.535483870967742,0.0750012650604373 +flat_mae,patch,logistic,adni_ad_vs_cn,92,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,92,2.782559402207126,test,0.6585365853658537,0.07000746114736502,0.5370967741935484,0.08754994646452054,0.5370967741935484,0.08770865420751146 +flat_mae,patch,logistic,adni_ad_vs_cn,93,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,93,166.81005372000556,test,0.5121951219512195,0.07682384804728533,0.47435897435897434,0.07407432242648171,0.5080645161290323,0.09024025482017661 +flat_mae,patch,logistic,adni_ad_vs_cn,94,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,94,2.782559402207126,test,0.7073170731707317,0.06625826921330927,0.603225806451613,0.08426162463629196,0.603225806451613,0.08459443528240625 +flat_mae,patch,logistic,adni_ad_vs_cn,95,0.046415888336127774,train,0.8915989159891599,0.014701317286535459,0.830966559780119,0.025286330222726815,0.7998192127537185,0.027181857167108282 +flat_mae,patch,logistic,adni_ad_vs_cn,95,0.046415888336127774,test,0.7804878048780488,0.054755331625910314,0.6660633484162897,0.08803284014248669,0.6516129032258065,0.08152696457082892 +flat_mae,patch,logistic,adni_ad_vs_cn,96,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,96,166.81005372000556,test,0.7804878048780488,0.061222505028389836,0.7119437939110069,0.07902824693077351,0.7193548387096774,0.08281788321006799 +flat_mae,patch,logistic,adni_ad_vs_cn,97,0.046415888336127774,train,0.8915989159891599,0.014097321332575973,0.830966559780119,0.024173721407555884,0.7998192127537185,0.02557710434378935 +flat_mae,patch,logistic,adni_ad_vs_cn,97,0.046415888336127774,test,0.7804878048780488,0.04827728259002588,0.6328358208955224,0.09187963790303717,0.6177419354838709,0.07661659916382194 +flat_mae,patch,logistic,adni_ad_vs_cn,98,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,98,2.782559402207126,test,0.6097560975609756,0.0774539989362687,0.5287356321839081,0.08447534213816575,0.5387096774193548,0.0933335826950239 +flat_mae,patch,logistic,adni_ad_vs_cn,99,0.3593813663804626,train,0.986449864498645,0.005976095820554896,0.9808134274809954,0.008575538936977288,0.9749774015942148,0.011494565620604167 +flat_mae,patch,logistic,adni_ad_vs_cn,99,0.3593813663804626,test,0.7804878048780488,0.052560834134833076,0.6660633484162897,0.09042270880797809,0.6516129032258065,0.08218295185403264 +flat_mae,patch,logistic,adni_ad_vs_cn,100,0.046415888336127774,train,0.9024390243902439,0.014310150232402018,0.8478699038021071,0.02475165434252555,0.8149806886350563,0.027040494551223145 +flat_mae,patch,logistic,adni_ad_vs_cn,100,0.046415888336127774,test,0.7073170731707317,0.059838449973085364,0.5729166666666666,0.08760559707489342,0.5693548387096774,0.08180437179354745 diff --git a/input_space_v3/flat_lr1e-3_5/eval_v2/adni_ad_vs_cn__patch__logistic/log.txt b/input_space_v3/flat_lr1e-3_5/eval_v2/adni_ad_vs_cn__patch__logistic/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..1e18bd773b5d5a02acc73bf1bdfdbde7dbd0b1d3 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_5/eval_v2/adni_ad_vs_cn__patch__logistic/log.txt @@ -0,0 +1,240 @@ +fMRI foundation model logistic probe eval +version: 0.1.dev86+gf97f52698 +sha: bcce2b486277d3a5b520775efd9cdf1a2affce36, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-04-08 22:29:58 +config: +output_root: experiments/input_space_v3/output +name_prefix: eval_logistic +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_5; eval v2 (adni_ad_vs_cn patch logistic) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: input_space_v3/flat_lr1e-3_5/eval_v2/adni_ad_vs_cn__patch__logistic +model: flat_mae +representation: patch +dataset: adni_ad_vs_cn +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/eval_v2/adni_ad_vs_cn__patch__logistic +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=True, reg_tokens=0, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: adni_ad_vs_cn (flat) +train (n=328): +ADNIDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'bold', 'mean', 'std'], + num_rows: 525 +}), + labels=[0 1], + counts=[251 77] +) + +validation (n=41): +ADNIDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'bold', 'mean', 'std'], + num_rows: 66 +}), + labels=[0 1], + counts=[31 10] +) + +test (n=41): +ADNIDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'bold', 'mean', 'std'], + num_rows: 66 +}), + labels=[0 1], + counts=[32 9] +) + +extracting features for all splits +extract (train) [ 0/164] eta: 0:13:14 time: 4.8418 data: 3.7794 max mem: 2698 +extract (train) [ 20/164] eta: 0:01:01 time: 0.2064 data: 0.0726 max mem: 2851 +extract (train) [ 40/164] eta: 0:00:38 time: 0.1860 data: 0.0639 max mem: 2851 +extract (train) [ 60/164] eta: 0:00:27 time: 0.1639 data: 0.0514 max mem: 2851 +extract (train) [ 80/164] eta: 0:00:20 time: 0.1783 data: 0.0600 max mem: 2851 +extract (train) [100/164] eta: 0:00:14 time: 0.1889 data: 0.0621 max mem: 2851 +extract (train) [120/164] eta: 0:00:09 time: 0.1854 data: 0.0633 max mem: 2851 +extract (train) [140/164] eta: 0:00:05 time: 0.1870 data: 0.0655 max mem: 2851 +extract (train) [160/164] eta: 0:00:00 time: 0.1608 data: 0.0511 max mem: 2851 +extract (train) [163/164] eta: 0:00:00 time: 0.1599 data: 0.0502 max mem: 2851 +extract (train) Total time: 0:00:34 (0.2131 s / it) +extract (validation) [ 0/21] eta: 0:01:24 time: 4.0242 data: 3.8841 max mem: 2851 +extract (validation) [20/21] eta: 0:00:00 time: 0.1516 data: 0.0435 max mem: 2851 +extract (validation) Total time: 0:00:07 (0.3586 s / it) +extract (test) [ 0/21] eta: 0:01:23 time: 3.9952 data: 3.8591 max mem: 2851 +extract (test) [20/21] eta: 0:00:00 time: 0.1494 data: 0.0450 max mem: 2851 +extract (test) Total time: 0:00:07 (0.3536 s / it) +feature extraction time: 0:00:50 +train features: (328, 768) +validation features: (41, 768) +test features: (41, 768) +evaluating fixed splits +eval results (fixed splits): + +| model | repr | clf | dataset | trial | C | split | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:--------------|:--------|-------:|:--------|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | adni_ad_vs_cn | | 2.7826 | train | 1 | 0 | 1 | 0 | 1 | 0 | +| flat_mae | patch | logistic | adni_ad_vs_cn | | 2.7826 | test | 0.73171 | 0.064211 | 0.62322 | 0.083377 | 0.62847 | 0.087716 | + + +evaluating random splits (n=100) +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 1, "C": 0.005994842503189409, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.02458149408150368, "f1": 0.5275288092189501, "f1_std": 0.0853385069223417, "bacc": 0.55, "bacc_std": 0.05039206286708255} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 2, "C": 2.782559402207126, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.0654904346113233, "f1": 0.603225806451613, "f1_std": 0.08456097177344545, "bacc": 0.603225806451613, "bacc_std": 0.08511817548636101} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 3, "C": 1291.5496650148827, "split": "test", "acc": 0.6341463414634146, "acc_std": 0.06359634379023703, "f1": 0.48621553884711777, "f1_std": 0.07121864111235741, "bacc": 0.48709677419354835, "bacc_std": 0.06925912104607539} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 4, "C": 0.3593813663804626, "split": "test", "acc": 0.8536585365853658, "acc_std": 0.05776884747206786, "f1": 0.8016129032258064, "f1_std": 0.07713014469925067, "bacc": 0.8016129032258064, "bacc_std": 0.07939894892585604} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 5, "C": 21.54434690031882, "split": "test", "acc": 0.6585365853658537, "acc_std": 0.055302424179836523, "f1": 0.4564393939393939, "f1_std": 0.0681875110605505, "bacc": 0.4693548387096774, "bacc_std": 0.060284501608914146} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 6, "C": 0.046415888336127774, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.05113805369189952, "f1": 0.6117424242424243, "f1_std": 0.08754684704957878, "bacc": 0.6016129032258064, "bacc_std": 0.07427900436242992} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 7, "C": 1291.5496650148827, "split": "test", "acc": 0.8292682926829268, "acc_std": 0.0567436600037804, "f1": 0.7602339181286549, "f1_std": 0.08435914526217973, "bacc": 0.7516129032258064, "bacc_std": 0.08697169339879202} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 8, "C": 10000.0, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.06765716494995952, "f1": 0.6676492262343405, "f1_std": 0.08019646065184916, "bacc": 0.6870967741935483, "bacc_std": 0.08633188025513573} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 9, "C": 166.81005372000556, "split": "test", "acc": 0.6341463414634146, "acc_std": 0.07333354244377376, "f1": 0.5467943994104643, "f1_std": 0.08428791488963022, "bacc": 0.5548387096774194, "bacc_std": 0.09193662313951718} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 10, "C": 0.3593813663804626, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.06010997258594587, "f1": 0.6440972222222222, "f1_std": 0.0893730804803424, "bacc": 0.635483870967742, "bacc_std": 0.08475611703971793} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 11, "C": 21.54434690031882, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.048524106742501134, "f1": 0.6328358208955224, "f1_std": 0.09384905479396635, "bacc": 0.6177419354838709, "bacc_std": 0.07659031245881572} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 12, "C": 21.54434690031882, "split": "test", "acc": 0.6341463414634146, "acc_std": 0.07331212355296585, "f1": 0.5684210526315789, "f1_std": 0.07929486656280713, "bacc": 0.5887096774193548, "bacc_std": 0.09018606336332674} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 13, "C": 2.782559402207126, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.051663372951246456, "f1": 0.6117424242424243, "f1_std": 0.08821984261711012, "bacc": 0.6016129032258064, "bacc_std": 0.07587998321189358} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 14, "C": 166.81005372000556, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.06919824696125192, "f1": 0.603225806451613, "f1_std": 0.08970592389053395, "bacc": 0.603225806451613, "bacc_std": 0.08945092213825398} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 15, "C": 2.782559402207126, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.06910726731822596, "f1": 0.6259649122807017, "f1_std": 0.07529631281904256, "bacc": 0.6548387096774193, "bacc_std": 0.08338519190436752} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 16, "C": 0.3593813663804626, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.057748578119607465, "f1": 0.7152777777777778, "f1_std": 0.08601160714642149, "bacc": 0.7016129032258065, "bacc_std": 0.08319196511270312} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 17, "C": 166.81005372000556, "split": "test", "acc": 0.6585365853658537, "acc_std": 0.07410968285053593, "f1": 0.5876436781609196, "f1_std": 0.08155959742787672, "bacc": 0.6048387096774194, "bacc_std": 0.09011673871870023} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 18, "C": 2.782559402207126, "split": "test", "acc": 0.8536585365853658, "acc_std": 0.03961296995251998, "f1": 0.7415966386554622, "f1_std": 0.09682956906426606, "bacc": 0.7, "bacc_std": 0.08120658840266597} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 19, "C": 2.782559402207126, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.06015676526294157, "f1": 0.5918552036199095, "f1_std": 0.0895098015201144, "bacc": 0.5854838709677419, "bacc_std": 0.07911657615360052} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 20, "C": 166.81005372000556, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.06989350273926463, "f1": 0.6272727272727273, "f1_std": 0.08242168137735993, "bacc": 0.6370967741935484, "bacc_std": 0.0871728494520036} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 21, "C": 0.046415888336127774, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.05417162670437117, "f1": 0.6660633484162897, "f1_std": 0.0924774456255057, "bacc": 0.6516129032258065, "bacc_std": 0.08347855164536272} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 22, "C": 0.3593813663804626, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.0537112601286211, "f1": 0.4696517412935323, "f1_std": 0.07005712708025878, "bacc": 0.4854838709677419, "bacc_std": 0.058310187360803685} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 23, "C": 21.54434690031882, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.06816118001062052, "f1": 0.6259649122807017, "f1_std": 0.07464889749089174, "bacc": 0.6548387096774193, "bacc_std": 0.08500468861403097} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 24, "C": 0.005994842503189409, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.03161558964539202, "f1": 0.5119047619047619, "f1_std": 0.07564517768144166, "bacc": 0.5338709677419355, "bacc_std": 0.04854056040222786} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 25, "C": 0.046415888336127774, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.052505482561240185, "f1": 0.6117424242424243, "f1_std": 0.09145306538218784, "bacc": 0.6016129032258064, "bacc_std": 0.07886789036809229} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 26, "C": 166.81005372000556, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.059669743478031535, "f1": 0.6440972222222222, "f1_std": 0.0893611659129043, "bacc": 0.635483870967742, "bacc_std": 0.0844951732207625} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 27, "C": 21.54434690031882, "split": "test", "acc": 0.6585365853658537, "acc_std": 0.06801579758408634, "f1": 0.5370967741935484, "f1_std": 0.08165852162537643, "bacc": 0.5370967741935484, "bacc_std": 0.08121682263469909} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 28, "C": 2.782559402207126, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.06430045476546652, "f1": 0.603225806451613, "f1_std": 0.08387859361730543, "bacc": 0.603225806451613, "bacc_std": 0.08356826883878687} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 29, "C": 21.54434690031882, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.06457983912688059, "f1": 0.6893939393939394, "f1_std": 0.07983072287503302, "bacc": 0.7032258064516128, "bacc_std": 0.0850330277389416} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 30, "C": 0.046415888336127774, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.05701477103871648, "f1": 0.5918552036199095, "f1_std": 0.09062024307000272, "bacc": 0.5854838709677419, "bacc_std": 0.07993216791268484} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 31, "C": 166.81005372000556, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.06403865578586267, "f1": 0.603225806451613, "f1_std": 0.08405787476642411, "bacc": 0.603225806451613, "bacc_std": 0.08511585200317769} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 32, "C": 0.005994842503189409, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.05139028441777837, "f1": 0.6893939393939394, "f1_std": 0.09442504810367564, "bacc": 0.667741935483871, "bacc_std": 0.08377173807374383} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 33, "C": 166.81005372000556, "split": "test", "acc": 0.6341463414634146, "acc_std": 0.0738333573927838, "f1": 0.5998698763825634, "f1_std": 0.07409928527338958, "bacc": 0.6564516129032258, "bacc_std": 0.08589502650051059} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 34, "C": 2.782559402207126, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.06850161420087934, "f1": 0.6259649122807017, "f1_std": 0.07608315958332734, "bacc": 0.6548387096774193, "bacc_std": 0.08534073689375549} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 35, "C": 166.81005372000556, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.045823134625044594, "f1": 0.6554621848739496, "f1_std": 0.10101798607269728, "bacc": 0.6338709677419355, "bacc_std": 0.0801794841428863} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 36, "C": 21.54434690031882, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.06126058286118868, "f1": 0.5729166666666666, "f1_std": 0.08285999167163964, "bacc": 0.5693548387096774, "bacc_std": 0.0765030078370553} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 37, "C": 0.005994842503189409, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.05609756097560976, "f1": 0.5340909090909092, "f1_std": 0.08629011153158576, "bacc": 0.535483870967742, "bacc_std": 0.0734918503696813} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 38, "C": 166.81005372000556, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.07432063916776933, "f1": 0.6620879120879121, "f1_std": 0.07873424465210177, "bacc": 0.7048387096774194, "bacc_std": 0.08692848712044234} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 39, "C": 166.81005372000556, "split": "test", "acc": 0.6097560975609756, "acc_std": 0.05329535629840953, "f1": 0.3787878787878788, "f1_std": 0.020998122390869116, "bacc": 0.4032258064516129, "bacc_std": 0.03524370335862565} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 40, "C": 0.005994842503189409, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.046145928941589344, "f1": 0.4831932773109243, "f1_std": 0.0711687295867353, "bacc": 0.5016129032258064, "bacc_std": 0.05502811541341511} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 41, "C": 21.54434690031882, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.06512193294966401, "f1": 0.6479313036690086, "f1_std": 0.08516434580247821, "bacc": 0.6532258064516129, "bacc_std": 0.08960370165722159} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 42, "C": 0.3593813663804626, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.0657261819479595, "f1": 0.603225806451613, "f1_std": 0.08231324843620222, "bacc": 0.603225806451613, "bacc_std": 0.08263619830020573} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 43, "C": 166.81005372000556, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.06625309753345958, "f1": 0.5839188134270101, "f1_std": 0.08191373700869571, "bacc": 0.5870967741935484, "bacc_std": 0.08442950861563772} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 44, "C": 0.3593813663804626, "split": "test", "acc": 0.8292682926829268, "acc_std": 0.043859057157051747, "f1": 0.7144278606965174, "f1_std": 0.0911837580016484, "bacc": 0.6838709677419355, "bacc_std": 0.07880376944717991} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 45, "C": 166.81005372000556, "split": "test", "acc": 0.8292682926829268, "acc_std": 0.05852949144006972, "f1": 0.7759562841530054, "f1_std": 0.0759599348206402, "bacc": 0.7854838709677419, "bacc_std": 0.08160171133256794} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 46, "C": 21.54434690031882, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.0604091542164508, "f1": 0.7515151515151515, "f1_std": 0.07337638097497876, "bacc": 0.7693548387096774, "bacc_std": 0.07857985982710487} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 47, "C": 2.782559402207126, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.049412756085949285, "f1": 0.6328358208955224, "f1_std": 0.09532531708977952, "bacc": 0.6177419354838709, "bacc_std": 0.07855749327887279} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 48, "C": 166.81005372000556, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.0670527685156676, "f1": 0.6620879120879121, "f1_std": 0.0717316941186946, "bacc": 0.7048387096774194, "bacc_std": 0.0806042066330976} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 49, "C": 0.046415888336127774, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.05188361569544244, "f1": 0.5512437810945273, "f1_std": 0.09134526780870197, "bacc": 0.5516129032258065, "bacc_std": 0.07327246452981251} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 50, "C": 166.81005372000556, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.059493699644937184, "f1": 0.7354838709677419, "f1_std": 0.08285162366280704, "bacc": 0.7354838709677419, "bacc_std": 0.08489359539459881} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 51, "C": 2.782559402207126, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.0717483041978326, "f1": 0.6259649122807017, "f1_std": 0.07942650498827593, "bacc": 0.6548387096774193, "bacc_std": 0.09044261862234766} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 52, "C": 2.782559402207126, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.06236693628217969, "f1": 0.7119437939110069, "f1_std": 0.08108861015550645, "bacc": 0.7193548387096774, "bacc_std": 0.086544640066532} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 53, "C": 0.3593813663804626, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.05400235745179076, "f1": 0.6117424242424243, "f1_std": 0.09402662527585066, "bacc": 0.6016129032258064, "bacc_std": 0.08110981565525564} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 54, "C": 0.3593813663804626, "split": "test", "acc": 0.6585365853658537, "acc_std": 0.06726493208676952, "f1": 0.5651515151515152, "f1_std": 0.0808901384784537, "bacc": 0.5709677419354839, "bacc_std": 0.08725459268031988} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 55, "C": 21.54434690031882, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.06615718667837159, "f1": 0.7054597701149425, "f1_std": 0.07574050412596191, "bacc": 0.7370967741935484, "bacc_std": 0.08356553635180491} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 56, "C": 10000.0, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.06172117842966046, "f1": 0.764367816091954, "f1_std": 0.07055384173910768, "bacc": 0.8032258064516129, "bacc_std": 0.07589095194348704} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 57, "C": 1291.5496650148827, "split": "test", "acc": 0.6585365853658537, "acc_std": 0.07246112826925578, "f1": 0.5651515151515152, "f1_std": 0.08519182695531463, "bacc": 0.5709677419354839, "bacc_std": 0.08946783259763835} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 58, "C": 0.3593813663804626, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.05026471271615739, "f1": 0.6328358208955224, "f1_std": 0.09244237296131863, "bacc": 0.6177419354838709, "bacc_std": 0.07539572714136962} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 59, "C": 166.81005372000556, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.07168016741715809, "f1": 0.6072218128224024, "f1_std": 0.08430410883164094, "bacc": 0.6209677419354839, "bacc_std": 0.09156920220753284} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 60, "C": 2.782559402207126, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.07044814480512766, "f1": 0.646551724137931, "f1_std": 0.08004063898994011, "bacc": 0.6709677419354838, "bacc_std": 0.08768584402545129} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 61, "C": 0.046415888336127774, "split": "test", "acc": 0.6341463414634146, "acc_std": 0.06649786084324921, "f1": 0.48621553884711777, "f1_std": 0.07929981538515514, "bacc": 0.48709677419354835, "bacc_std": 0.07588156498298114} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 62, "C": 166.81005372000556, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.059566628444719515, "f1": 0.5918552036199095, "f1_std": 0.0892895272858601, "bacc": 0.5854838709677419, "bacc_std": 0.07995720109060532} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 63, "C": 166.81005372000556, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.05896703522568821, "f1": 0.6917293233082706, "f1_std": 0.0857692043982056, "bacc": 0.685483870967742, "bacc_std": 0.0858308257886822} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 64, "C": 166.81005372000556, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.06049732419193674, "f1": 0.6232247284878863, "f1_std": 0.08514239584531934, "bacc": 0.6193548387096774, "bacc_std": 0.0833746867286275} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 65, "C": 0.3593813663804626, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.06183480515930997, "f1": 0.7354838709677419, "f1_std": 0.08296285627334479, "bacc": 0.7354838709677419, "bacc_std": 0.0863680747083327} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 66, "C": 21.54434690031882, "split": "test", "acc": 0.6585365853658537, "acc_std": 0.07425055256906457, "f1": 0.6057692307692308, "f1_std": 0.07836818044881141, "bacc": 0.6387096774193548, "bacc_std": 0.08920684471855844} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 67, "C": 0.046415888336127774, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.04489063980318528, "f1": 0.569327731092437, "f1_std": 0.0899265670244746, "bacc": 0.567741935483871, "bacc_std": 0.06751174129971363} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 68, "C": 0.046415888336127774, "split": "test", "acc": 0.6341463414634146, "acc_std": 0.05709816004936762, "f1": 0.44343891402714936, "f1_std": 0.06510463128023876, "bacc": 0.45322580645161287, "bacc_std": 0.05991620049874688} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 69, "C": 2.782559402207126, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.06751154306748414, "f1": 0.6479313036690086, "f1_std": 0.08614474888818278, "bacc": 0.6532258064516129, "bacc_std": 0.09061978545046577} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 70, "C": 0.046415888336127774, "split": "test", "acc": 0.8536585365853658, "acc_std": 0.04691808143198926, "f1": 0.7670454545454546, "f1_std": 0.08962379159599836, "bacc": 0.7338709677419355, "bacc_std": 0.08323888838170446} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 71, "C": 0.046415888336127774, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.033078926040715675, "f1": 0.4142857142857143, "f1_std": 0.011514250991618458, "bacc": 0.46774193548387094, "bacc_std": 0.021874773672086185} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 72, "C": 21.54434690031882, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.04641778054777671, "f1": 0.4831932773109243, "f1_std": 0.07405650033628015, "bacc": 0.5016129032258064, "bacc_std": 0.0568676630697771} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 73, "C": 2.782559402207126, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.06292907918080261, "f1": 0.7119437939110069, "f1_std": 0.0806906356779623, "bacc": 0.7193548387096774, "bacc_std": 0.08463799389402979} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 74, "C": 166.81005372000556, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.06009906554974386, "f1": 0.6440972222222222, "f1_std": 0.09135443821241848, "bacc": 0.635483870967742, "bacc_std": 0.08662366101269592} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 75, "C": 0.005994842503189409, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.04154594369177018, "f1": 0.4972129319955407, "f1_std": 0.07667784004953351, "bacc": 0.5177419354838709, "bacc_std": 0.054612496997517426} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 76, "C": 1291.5496650148827, "split": "test", "acc": 0.5853658536585366, "acc_std": 0.07274019678579, "f1": 0.5108771929824562, "f1_std": 0.07766951041551493, "bacc": 0.5225806451612903, "bacc_std": 0.08743738291669953} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 77, "C": 21.54434690031882, "split": "test", "acc": 0.8292682926829268, "acc_std": 0.05569294163329124, "f1": 0.7602339181286549, "f1_std": 0.08102426070973019, "bacc": 0.7516129032258064, "bacc_std": 0.08412642800986044} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 78, "C": 166.81005372000556, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.06859880866073997, "f1": 0.6479313036690086, "f1_std": 0.08768752208919921, "bacc": 0.6532258064516129, "bacc_std": 0.0909148539919565} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 79, "C": 0.3593813663804626, "split": "test", "acc": 0.8536585365853658, "acc_std": 0.056608300650681974, "f1": 0.8232758620689655, "f1_std": 0.06292246245888129, "bacc": 0.8693548387096774, "bacc_std": 0.0598686473236378} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 80, "C": 0.3593813663804626, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.06789800588276096, "f1": 0.6272727272727273, "f1_std": 0.08223496256648546, "bacc": 0.6370967741935484, "bacc_std": 0.08681880439793194} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 81, "C": 21.54434690031882, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.057372386387613654, "f1": 0.5340909090909092, "f1_std": 0.08734654207578378, "bacc": 0.535483870967742, "bacc_std": 0.07433279352713974} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 82, "C": 2.782559402207126, "split": "test", "acc": 0.5853658536585366, "acc_std": 0.06142081373044429, "f1": 0.4177109440267335, "f1_std": 0.060365278939756246, "bacc": 0.42096774193548386, "bacc_std": 0.06073978856295284} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 83, "C": 1291.5496650148827, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.06598142979604037, "f1": 0.7054597701149425, "f1_std": 0.07588313602813544, "bacc": 0.7370967741935484, "bacc_std": 0.0832546759130944} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 84, "C": 0.046415888336127774, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.05850183928122379, "f1": 0.5918552036199095, "f1_std": 0.0884847013642466, "bacc": 0.5854838709677419, "bacc_std": 0.07905898455268422} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 85, "C": 0.005994842503189409, "split": "test", "acc": 0.9024390243902439, "acc_std": 0.038378062343538105, "f1": 0.8446969696969697, "f1_std": 0.07673636095637511, "bacc": 0.8, "bacc_std": 0.07867502780425312} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 86, "C": 0.3593813663804626, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.06781365095027132, "f1": 0.6272727272727273, "f1_std": 0.08232099750304414, "bacc": 0.6370967741935484, "bacc_std": 0.087594068655838} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 87, "C": 2.782559402207126, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.056010536953784676, "f1": 0.7354838709677419, "f1_std": 0.07782528425870976, "bacc": 0.7354838709677419, "bacc_std": 0.08066183692108597} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 88, "C": 0.3593813663804626, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.06636676346845467, "f1": 0.6272727272727273, "f1_std": 0.08226082798141872, "bacc": 0.6370967741935484, "bacc_std": 0.0891092044189309} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 89, "C": 21.54434690031882, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.06792897925397241, "f1": 0.6272727272727273, "f1_std": 0.08461009100956969, "bacc": 0.6370967741935484, "bacc_std": 0.09080778953921825} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 90, "C": 0.046415888336127774, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.059093207212064326, "f1": 0.7354838709677419, "f1_std": 0.07916802921588748, "bacc": 0.7354838709677419, "bacc_std": 0.08104690764176906} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 91, "C": 0.005994842503189409, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.05748690976879015, "f1": 0.5340909090909092, "f1_std": 0.08715468553239285, "bacc": 0.535483870967742, "bacc_std": 0.0750012650604373} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 92, "C": 2.782559402207126, "split": "test", "acc": 0.6585365853658537, "acc_std": 0.07000746114736502, "f1": 0.5370967741935484, "f1_std": 0.08754994646452054, "bacc": 0.5370967741935484, "bacc_std": 0.08770865420751146} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 93, "C": 166.81005372000556, "split": "test", "acc": 0.5121951219512195, "acc_std": 0.07682384804728533, "f1": 0.47435897435897434, "f1_std": 0.07407432242648171, "bacc": 0.5080645161290323, "bacc_std": 0.09024025482017661} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 94, "C": 2.782559402207126, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.06625826921330927, "f1": 0.603225806451613, "f1_std": 0.08426162463629196, "bacc": 0.603225806451613, "bacc_std": 0.08459443528240625} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 95, "C": 0.046415888336127774, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.054755331625910314, "f1": 0.6660633484162897, "f1_std": 0.08803284014248669, "bacc": 0.6516129032258065, "bacc_std": 0.08152696457082892} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 96, "C": 166.81005372000556, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.061222505028389836, "f1": 0.7119437939110069, "f1_std": 0.07902824693077351, "bacc": 0.7193548387096774, "bacc_std": 0.08281788321006799} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 97, "C": 0.046415888336127774, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.04827728259002588, "f1": 0.6328358208955224, "f1_std": 0.09187963790303717, "bacc": 0.6177419354838709, "bacc_std": 0.07661659916382194} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 98, "C": 2.782559402207126, "split": "test", "acc": 0.6097560975609756, "acc_std": 0.0774539989362687, "f1": 0.5287356321839081, "f1_std": 0.08447534213816575, "bacc": 0.5387096774193548, "bacc_std": 0.0933335826950239} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 99, "C": 0.3593813663804626, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.052560834134833076, "f1": 0.6660633484162897, "f1_std": 0.09042270880797809, "bacc": 0.6516129032258065, "bacc_std": 0.08218295185403264} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 100, "C": 0.046415888336127774, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.059838449973085364, "f1": 0.5729166666666666, "f1_std": 0.08760559707489342, "bacc": 0.5693548387096774, "bacc_std": 0.08180437179354745} +eval results (random splits): + +| model | repr | clf | dataset | split | n_trials | C | C_std | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:--------------|:--------|-----------:|-------:|--------:|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | adni_ad_vs_cn | train | 100 | 305.07 | 1420.1 | 0.96897 | 0.054375 | 0.94891 | 0.0937 | 0.94084 | 0.10485 | +| flat_mae | patch | logistic | adni_ad_vs_cn | test | 100 | 305.07 | 1420.1 | 0.73024 | 0.067828 | 0.61919 | 0.092668 | 0.62448 | 0.089566 | + + +done! total time: 0:04:51 diff --git a/input_space_v3/flat_lr1e-3_5/eval_v2/hcpya_task21__patch__attn/config.yaml b/input_space_v3/flat_lr1e-3_5/eval_v2/hcpya_task21__patch__attn/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..5594a5dc16b3ca4abac3ff26822e362662817b46 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_5/eval_v2/hcpya_task21__patch__attn/config.yaml @@ -0,0 +1,96 @@ +output_root: experiments/input_space_v3/output +name_prefix: eval_probe +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_5; eval v2 (hcpya_task21 patch attn) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +dataset_kwargs: {} +classifier_kwargs: + embed_dim: null + dropout: 0.0 + xavier_init: true + norm: true +lr_scale_grid: +- 0.02 +- 0.023 +- 0.028 +- 0.033 +- 0.038 +- 0.045 +- 0.053 +- 0.062 +- 0.074 +- 0.087 +- 0.1 +- 0.12 +- 0.14 +- 0.17 +- 0.2 +- 0.23 +- 0.27 +- 0.32 +- 0.38 +- 0.44 +- 0.52 +- 0.61 +- 0.72 +- 0.85 +- 1 +- 1.2 +- 1.4 +- 1.6 +- 1.9 +- 2.3 +- 2.7 +- 3.1 +- 3.7 +- 4.3 +- 5.1 +- 6 +- 7.1 +- 8.3 +- 9.8 +- 12 +- 14 +- 16 +- 19 +- 22 +- 26 +- 31 +- 36 +- 43 +- 50 +wd_scale_grid: +- 1.0 +num_workers: 8 +prefetch_factor: null +balanced_sampling: false +epochs: 20 +steps_per_epoch: 200 +batch_size: 64 +accum_iter: 2 +lr: 0.0003 +warmup_epochs: 5 +no_decay: false +weight_decay: 0.05 +clip_grad: 1.0 +metrics: +- acc +- f1 +cv_metric: acc +early_stopping: true +amp: true +device: cuda +seed: 4466 +debug: false +wandb: false +wandb_entity: null +wandb_project: fMRI-fm-eval +name: input_space_v3/flat_lr1e-3_5/eval_v2/hcpya_task21__patch__attn +model: flat_mae +representation: patch +classifier: attn +dataset: hcpya_task21 +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/eval_v2/hcpya_task21__patch__attn +remote_dir: null diff --git a/input_space_v3/flat_lr1e-3_5/eval_v2/hcpya_task21__patch__attn/eval_log.json b/input_space_v3/flat_lr1e-3_5/eval_v2/hcpya_task21__patch__attn/eval_log.json new file mode 100644 index 0000000000000000000000000000000000000000..7187b5dff35b0ce39eda4dba4d1fa110ef5774ac --- /dev/null +++ b/input_space_v3/flat_lr1e-3_5/eval_v2/hcpya_task21__patch__attn/eval_log.json @@ -0,0 +1 @@ +{"eval/epoch": 11, "eval/id_best": 30, "eval/lr_best": 0.00081, "eval/wd_best": 0.05, "eval/train/loss": 0.0004559845256153494, "eval/train/acc": 1.0, "eval/train/acc_std": 0.0, "eval/train/f1": 1.0, "eval/train/f1_std": 0.0, "eval/validation/loss": 0.025608496740460396, "eval/validation/acc": 0.9933035714285714, "eval/validation/acc_std": 0.0013353553255026586, "eval/validation/f1": 0.9918192710343651, "eval/validation/f1_std": 0.0017535212594815808, "eval/test/loss": 0.037847477942705154, "eval/test/acc": 0.9898809523809524, "eval/test/acc_std": 0.0013789290847468856, "eval/test/f1": 0.9872462315199817, "eval/test/f1_std": 0.0019133122477410793} diff --git a/input_space_v3/flat_lr1e-3_5/eval_v2/hcpya_task21__patch__attn/eval_log_best.json b/input_space_v3/flat_lr1e-3_5/eval_v2/hcpya_task21__patch__attn/eval_log_best.json new file mode 100644 index 0000000000000000000000000000000000000000..2d0240a025a4cb26f16dd3147df7261580a36dba --- /dev/null +++ b/input_space_v3/flat_lr1e-3_5/eval_v2/hcpya_task21__patch__attn/eval_log_best.json @@ -0,0 +1 @@ +{"eval/best/epoch": 11, "eval/best/id_best": 30, "eval/best/lr_best": 0.00081, "eval/best/wd_best": 0.05, "eval/best/train/loss": 0.0004559845256153494, "eval/best/train/acc": 1.0, "eval/best/train/acc_std": 0.0, "eval/best/train/f1": 1.0, "eval/best/train/f1_std": 0.0, "eval/best/validation/loss": 0.025608496740460396, "eval/best/validation/acc": 0.9933035714285714, "eval/best/validation/acc_std": 0.0013353553255026586, "eval/best/validation/f1": 0.9918192710343651, "eval/best/validation/f1_std": 0.0017535212594815808, "eval/best/test/loss": 0.037847477942705154, "eval/best/test/acc": 0.9898809523809524, "eval/best/test/acc_std": 0.0013789290847468856, "eval/best/test/f1": 0.9872462315199817, "eval/best/test/f1_std": 0.0019133122477410793} diff --git a/input_space_v3/flat_lr1e-3_5/eval_v2/hcpya_task21__patch__attn/eval_log_last.json b/input_space_v3/flat_lr1e-3_5/eval_v2/hcpya_task21__patch__attn/eval_log_last.json new file mode 100644 index 0000000000000000000000000000000000000000..8f628a7670798d116629e2544fbd00069ae41533 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_5/eval_v2/hcpya_task21__patch__attn/eval_log_last.json @@ -0,0 +1 @@ +{"eval/last/epoch": 19, "eval/last/id_best": 35, "eval/last/lr_best": 0.0018, "eval/last/wd_best": 0.05, "eval/last/train/loss": 3.240009391447529e-05, "eval/last/train/acc": 1.0, "eval/last/train/acc_std": 0.0, "eval/last/train/f1": 1.0, "eval/last/train/f1_std": 0.0, "eval/last/validation/loss": 0.03544091433286667, "eval/last/validation/acc": 0.9928075396825397, "eval/last/validation/acc_std": 0.0013364788156808862, "eval/last/validation/f1": 0.9916223286574622, "eval/last/validation/f1_std": 0.0017053470369513795, "eval/last/test/loss": 0.054097723215818405, "eval/last/test/acc": 0.9904761904761905, "eval/last/test/acc_std": 0.001374809590792387, "eval/last/test/f1": 0.9881383099761788, "eval/last/test/f1_std": 0.0018283610291883535} diff --git a/input_space_v3/flat_lr1e-3_5/eval_v2/hcpya_task21__patch__attn/eval_table.csv b/input_space_v3/flat_lr1e-3_5/eval_v2/hcpya_task21__patch__attn/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..fea07c7ecd952b66ed805d9ed9124bebe6db4484 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_5/eval_v2/hcpya_task21__patch__attn/eval_table.csv @@ -0,0 +1,4 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,patch,attn,hcpya_task21,best,11,0.00081,0.05,30,"[2.7, 1.0]",train,0.0004559845256153494,1.0,0.0,1.0,0.0 +flat_mae,patch,attn,hcpya_task21,best,11,0.00081,0.05,30,"[2.7, 1.0]",validation,0.025608496740460396,0.9933035714285714,0.0013353553255026586,0.9918192710343651,0.0017535212594815808 +flat_mae,patch,attn,hcpya_task21,best,11,0.00081,0.05,30,"[2.7, 1.0]",test,0.037847477942705154,0.9898809523809524,0.0013789290847468856,0.9872462315199817,0.0019133122477410793 diff --git a/input_space_v3/flat_lr1e-3_5/eval_v2/hcpya_task21__patch__attn/eval_table_best.csv b/input_space_v3/flat_lr1e-3_5/eval_v2/hcpya_task21__patch__attn/eval_table_best.csv new file mode 100644 index 0000000000000000000000000000000000000000..fea07c7ecd952b66ed805d9ed9124bebe6db4484 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_5/eval_v2/hcpya_task21__patch__attn/eval_table_best.csv @@ -0,0 +1,4 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,patch,attn,hcpya_task21,best,11,0.00081,0.05,30,"[2.7, 1.0]",train,0.0004559845256153494,1.0,0.0,1.0,0.0 +flat_mae,patch,attn,hcpya_task21,best,11,0.00081,0.05,30,"[2.7, 1.0]",validation,0.025608496740460396,0.9933035714285714,0.0013353553255026586,0.9918192710343651,0.0017535212594815808 +flat_mae,patch,attn,hcpya_task21,best,11,0.00081,0.05,30,"[2.7, 1.0]",test,0.037847477942705154,0.9898809523809524,0.0013789290847468856,0.9872462315199817,0.0019133122477410793 diff --git a/input_space_v3/flat_lr1e-3_5/eval_v2/hcpya_task21__patch__attn/eval_table_last.csv b/input_space_v3/flat_lr1e-3_5/eval_v2/hcpya_task21__patch__attn/eval_table_last.csv new file mode 100644 index 0000000000000000000000000000000000000000..46d20210563d8c23ba8b6d4b26f09718ddfc9648 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_5/eval_v2/hcpya_task21__patch__attn/eval_table_last.csv @@ -0,0 +1,4 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,patch,attn,hcpya_task21,last,19,0.0018,0.05,35,"[6, 1.0]",train,3.240009391447529e-05,1.0,0.0,1.0,0.0 +flat_mae,patch,attn,hcpya_task21,last,19,0.0018,0.05,35,"[6, 1.0]",validation,0.03544091433286667,0.9928075396825397,0.0013364788156808862,0.9916223286574622,0.0017053470369513795 +flat_mae,patch,attn,hcpya_task21,last,19,0.0018,0.05,35,"[6, 1.0]",test,0.054097723215818405,0.9904761904761905,0.001374809590792387,0.9881383099761788,0.0018283610291883535 diff --git a/input_space_v3/flat_lr1e-3_5/eval_v2/hcpya_task21__patch__attn/log.txt b/input_space_v3/flat_lr1e-3_5/eval_v2/hcpya_task21__patch__attn/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..7a43abe2e68fa847fa0c5d231b5a42f652a536f8 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_5/eval_v2/hcpya_task21__patch__attn/log.txt @@ -0,0 +1,886 @@ +fMRI foundation model probe eval +version: 0.1.dev86+gf97f52698 +sha: bcce2b486277d3a5b520775efd9cdf1a2affce36, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-04-08 20:31:09 +config: +output_root: experiments/input_space_v3/output +name_prefix: eval_probe +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_5; eval v2 (hcpya_task21 patch attn) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +dataset_kwargs: {} +classifier_kwargs: + embed_dim: null + dropout: 0.0 + xavier_init: true + norm: true +lr_scale_grid: +- 0.02 +- 0.023 +- 0.028 +- 0.033 +- 0.038 +- 0.045 +- 0.053 +- 0.062 +- 0.074 +- 0.087 +- 0.1 +- 0.12 +- 0.14 +- 0.17 +- 0.2 +- 0.23 +- 0.27 +- 0.32 +- 0.38 +- 0.44 +- 0.52 +- 0.61 +- 0.72 +- 0.85 +- 1 +- 1.2 +- 1.4 +- 1.6 +- 1.9 +- 2.3 +- 2.7 +- 3.1 +- 3.7 +- 4.3 +- 5.1 +- 6 +- 7.1 +- 8.3 +- 9.8 +- 12 +- 14 +- 16 +- 19 +- 22 +- 26 +- 31 +- 36 +- 43 +- 50 +wd_scale_grid: +- 1.0 +num_workers: 8 +prefetch_factor: null +balanced_sampling: false +epochs: 20 +steps_per_epoch: 200 +batch_size: 64 +accum_iter: 2 +lr: 0.0003 +warmup_epochs: 5 +no_decay: false +weight_decay: 0.05 +clip_grad: 1.0 +metrics: +- acc +- f1 +cv_metric: acc +early_stopping: true +amp: true +device: cuda +seed: 4466 +debug: false +wandb: false +wandb_entity: null +wandb_project: fMRI-fm-eval +name: input_space_v3/flat_lr1e-3_5/eval_v2/hcpya_task21__patch__attn +model: flat_mae +representation: patch +classifier: attn +dataset: hcpya_task21 +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/eval_v2/hcpya_task21__patch__attn +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=True, reg_tokens=0, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: hcpya_task21 (flat) +train (n=18999): +HFDataset( + dataset=Dataset({ + features: ['sub', 'task', 'cond', 'cond_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 18999 +}), + labels=[ 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20], + counts=[ 832 1248 3201 1660 832 832 832 832 832 1248 1247 1243 832 416 + 416 416 416 416 416 416 416] +) + +validation (n=4032): +HFDataset( + dataset=Dataset({ + features: ['sub', 'task', 'cond', 'cond_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 4032 +}), + labels=[ 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20], + counts=[176 264 688 352 176 176 176 176 176 264 264 264 176 88 88 88 88 88 + 88 88 88] +) + +test (n=5040): +HFDataset( + dataset=Dataset({ + features: ['sub', 'task', 'cond', 'cond_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 5040 +}), + labels=[ 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20], + counts=[220 330 860 440 220 220 220 220 220 330 330 330 220 110 110 110 110 110 + 110 110 110] +) + +running backbone on example batch to get embedding dim +embedding feature dim (patch): 768 +initializing sweep of classifier heads +classifiers: +ModuleList( + (0-48): 49 x AttnPoolClassifier( + (kv): Linear(in_features=768, out_features=1536, bias=True) + (linear): Linear(in_features=768, out_features=21, bias=True) + ) +) +classifier params (train): 58.7M (58.7M) +setting up optimizer +total batch size: 128 = 64 bs per gpu x 2 accum +lr: 3.00e-04 +full schedule: epochs = 20 (steps = 4000) (decay = True) +warmup: epochs = 5 (steps = 1000) +start training for 20 epochs +train: [0] [ 0/400] eta: 0:23:52 lr: nan time: 3.5812 data: 2.9731 max mem: 21740 +train: [0] [ 20/400] eta: 0:03:57 lr: 0.000003 loss: 3.0412 (3.0442) grad: 0.2648 (0.2736) time: 0.4779 data: 0.0050 max mem: 22446 +train: [0] [ 40/400] eta: 0:03:17 lr: 0.000006 loss: 3.0093 (3.0016) grad: 0.2648 (0.2729) time: 0.4694 data: 0.0037 max mem: 22446 +train: [0] [ 60/400] eta: 0:02:57 lr: 0.000009 loss: 2.8952 (2.9422) grad: 0.2641 (0.2684) time: 0.4686 data: 0.0036 max mem: 22446 +train: [0] [ 80/400] eta: 0:02:42 lr: 0.000012 loss: 2.7597 (2.8810) grad: 0.2500 (0.2613) time: 0.4650 data: 0.0035 max mem: 22446 +train: [0] [100/400] eta: 0:02:29 lr: 0.000015 loss: 2.5996 (2.8130) grad: 0.2340 (0.2573) time: 0.4598 data: 0.0035 max mem: 22446 +train: [0] [120/400] eta: 0:02:17 lr: 0.000018 loss: 2.4979 (2.7441) grad: 0.2372 (0.2530) time: 0.4573 data: 0.0036 max mem: 22446 +train: [0] [140/400] eta: 0:02:06 lr: 0.000021 loss: 2.3292 (2.6762) grad: 0.2331 (0.2512) time: 0.4606 data: 0.0035 max mem: 22446 +train: [0] [160/400] eta: 0:01:56 lr: 0.000024 loss: 2.2194 (2.6159) grad: 0.2247 (0.2464) time: 0.4654 data: 0.0035 max mem: 22446 +train: [0] [180/400] eta: 0:01:45 lr: 0.000027 loss: 2.1308 (2.5561) grad: 0.2083 (0.2420) time: 0.4538 data: 0.0035 max mem: 22446 +train: [0] [200/400] eta: 0:01:35 lr: 0.000030 loss: 2.0480 (2.5000) grad: 0.2087 (0.2390) time: 0.4580 data: 0.0034 max mem: 22446 +train: [0] [220/400] eta: 0:01:25 lr: 0.000033 loss: 1.9402 (2.4471) grad: 0.1986 (0.2352) time: 0.4572 data: 0.0038 max mem: 22446 +train: [0] [240/400] eta: 0:01:16 lr: 0.000036 loss: 1.8553 (2.3935) grad: 0.2036 (0.2330) time: 0.4735 data: 0.0035 max mem: 22446 +train: [0] [260/400] eta: 0:01:06 lr: 0.000039 loss: 1.7837 (2.3448) grad: 0.2036 (0.2306) time: 0.4657 data: 0.0036 max mem: 22446 +train: [0] [280/400] eta: 0:00:57 lr: 0.000042 loss: 1.7420 (2.3014) grad: 0.1891 (0.2274) time: 0.4716 data: 0.0035 max mem: 22446 +train: [0] [300/400] eta: 0:00:48 lr: 0.000045 loss: 1.6972 (2.2596) grad: 0.1751 (0.2240) time: 0.6437 data: 0.1741 max mem: 22446 +train: [0] [320/400] eta: 0:00:38 lr: 0.000048 loss: 1.6474 (2.2189) grad: 0.1747 (0.2212) time: 0.4730 data: 0.0164 max mem: 22446 +train: [0] [340/400] eta: 0:00:29 lr: 0.000051 loss: 1.5705 (2.1800) grad: 0.1833 (0.2192) time: 0.4794 data: 0.0034 max mem: 22446 +train: [0] [360/400] eta: 0:00:19 lr: 0.000054 loss: 1.5407 (2.1445) grad: 0.1796 (0.2169) time: 0.5038 data: 0.0038 max mem: 22446 +train: [0] [380/400] eta: 0:00:09 lr: 0.000057 loss: 1.5059 (2.1099) grad: 0.1735 (0.2145) time: 0.4740 data: 0.0038 max mem: 22446 +train: [0] [399/400] eta: 0:00:00 lr: 0.000060 loss: 1.4476 (2.0753) grad: 0.1716 (0.2126) time: 0.4587 data: 0.0035 max mem: 22446 +train: [0] Total time: 0:03:13 (0.4849 s / it) +train: [0] Summary: lr: 0.000060 loss: 1.4476 (2.0753) grad: 0.1716 (0.2126) +eval (validation): [0] [ 0/63] eta: 0:03:22 time: 3.2078 data: 2.9059 max mem: 22446 +eval (validation): [0] [20/63] eta: 0:00:23 time: 0.4063 data: 0.0048 max mem: 22446 +eval (validation): [0] [40/63] eta: 0:00:10 time: 0.3596 data: 0.0030 max mem: 22446 +eval (validation): [0] [60/63] eta: 0:00:01 time: 0.3303 data: 0.0034 max mem: 22446 +eval (validation): [0] [62/63] eta: 0:00:00 time: 0.3313 data: 0.0034 max mem: 22446 +eval (validation): [0] Total time: 0:00:26 (0.4161 s / it) +cv: [0] best hparam: (26, 1.0) (044) ('044_lr2.6e+01_wd1.0e+00') loss: 0.041 acc: 0.986 f1: 0.985 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/eval_v2/hcpya_task21__patch__attn/checkpoint-best.pth +train: [1] [ 0/400] eta: 0:21:41 lr: nan time: 3.2550 data: 2.8770 max mem: 22446 +train: [1] [ 20/400] eta: 0:03:43 lr: 0.000063 loss: 1.4022 (1.4085) grad: 0.1676 (0.1724) time: 0.4536 data: 0.0034 max mem: 22446 +train: [1] [ 40/400] eta: 0:03:08 lr: 0.000066 loss: 1.3846 (1.3874) grad: 0.1690 (0.1713) time: 0.4578 data: 0.0035 max mem: 22446 +train: [1] [ 60/400] eta: 0:02:50 lr: 0.000069 loss: 1.3501 (1.3670) grad: 0.1653 (0.1680) time: 0.4521 data: 0.0035 max mem: 22446 +train: [1] [ 80/400] eta: 0:02:36 lr: 0.000072 loss: 1.3084 (1.3507) grad: 0.1554 (0.1657) time: 0.4576 data: 0.0035 max mem: 22446 +train: [1] [100/400] eta: 0:02:24 lr: 0.000075 loss: 1.2810 (1.3377) grad: 0.1590 (0.1652) time: 0.4486 data: 0.0034 max mem: 22446 +train: [1] [120/400] eta: 0:02:13 lr: 0.000078 loss: 1.2598 (1.3193) grad: 0.1544 (0.1643) time: 0.4491 data: 0.0035 max mem: 22446 +train: [1] [140/400] eta: 0:02:03 lr: 0.000081 loss: 1.2199 (1.3052) grad: 0.1541 (0.1626) time: 0.4546 data: 0.0035 max mem: 22446 +train: [1] [160/400] eta: 0:01:53 lr: 0.000084 loss: 1.2005 (1.2893) grad: 0.1499 (0.1613) time: 0.4552 data: 0.0036 max mem: 22446 +train: [1] [180/400] eta: 0:01:43 lr: 0.000087 loss: 1.1663 (1.2746) grad: 0.1513 (0.1604) time: 0.4534 data: 0.0035 max mem: 22446 +train: [1] [200/400] eta: 0:01:33 lr: 0.000090 loss: 1.1332 (1.2601) grad: 0.1482 (0.1593) time: 0.4502 data: 0.0035 max mem: 22446 +train: [1] [220/400] eta: 0:01:23 lr: 0.000093 loss: 1.1038 (1.2449) grad: 0.1495 (0.1592) time: 0.4505 data: 0.0035 max mem: 22446 +train: [1] [240/400] eta: 0:01:14 lr: 0.000096 loss: 1.0917 (1.2316) grad: 0.1523 (0.1583) time: 0.4475 data: 0.0034 max mem: 22446 +train: [1] [260/400] eta: 0:01:05 lr: 0.000099 loss: 1.0849 (1.2200) grad: 0.1483 (0.1573) time: 0.4718 data: 0.0035 max mem: 22446 +train: [1] [280/400] eta: 0:00:55 lr: 0.000102 loss: 1.0528 (1.2068) grad: 0.1405 (0.1567) time: 0.4567 data: 0.0035 max mem: 22446 +train: [1] [300/400] eta: 0:00:47 lr: 0.000105 loss: 1.0284 (1.1945) grad: 0.1347 (0.1552) time: 0.6118 data: 0.1736 max mem: 22446 +train: [1] [320/400] eta: 0:00:37 lr: 0.000108 loss: 1.0059 (1.1828) grad: 0.1346 (0.1542) time: 0.4606 data: 0.0027 max mem: 22446 +train: [1] [340/400] eta: 0:00:28 lr: 0.000111 loss: 0.9841 (1.1702) grad: 0.1322 (0.1528) time: 0.4592 data: 0.0035 max mem: 22446 +train: [1] [360/400] eta: 0:00:18 lr: 0.000114 loss: 0.9790 (1.1596) grad: 0.1309 (0.1515) time: 0.4980 data: 0.0038 max mem: 22446 +train: [1] [380/400] eta: 0:00:09 lr: 0.000117 loss: 0.9631 (1.1488) grad: 0.1335 (0.1509) time: 0.4963 data: 0.0041 max mem: 22446 +train: [1] [399/400] eta: 0:00:00 lr: 0.000120 loss: 0.9377 (1.1393) grad: 0.1372 (0.1504) time: 0.4501 data: 0.0034 max mem: 22446 +train: [1] Total time: 0:03:09 (0.4741 s / it) +train: [1] Summary: lr: 0.000120 loss: 0.9377 (1.1393) grad: 0.1372 (0.1504) +eval (validation): [1] [ 0/63] eta: 0:03:36 time: 3.4313 data: 3.1432 max mem: 22446 +eval (validation): [1] [20/63] eta: 0:00:21 time: 0.3609 data: 0.0029 max mem: 22446 +eval (validation): [1] [40/63] eta: 0:00:10 time: 0.3712 data: 0.0032 max mem: 22446 +eval (validation): [1] [60/63] eta: 0:00:01 time: 0.3347 data: 0.0035 max mem: 22446 +eval (validation): [1] [62/63] eta: 0:00:00 time: 0.3328 data: 0.0034 max mem: 22446 +eval (validation): [1] Total time: 0:00:25 (0.4087 s / it) +cv: [1] best hparam: (12, 1.0) (039) ('039_lr1.2e+01_wd1.0e+00') loss: 0.033 acc: 0.990 f1: 0.988 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/eval_v2/hcpya_task21__patch__attn/checkpoint-best.pth +train: [2] [ 0/400] eta: 0:21:59 lr: nan time: 3.2996 data: 2.9498 max mem: 22446 +train: [2] [ 20/400] eta: 0:03:43 lr: 0.000123 loss: 0.8774 (0.8997) grad: 0.1384 (0.1434) time: 0.4530 data: 0.0024 max mem: 22446 +train: [2] [ 40/400] eta: 0:03:08 lr: 0.000126 loss: 0.9004 (0.9079) grad: 0.1453 (0.1474) time: 0.4565 data: 0.0035 max mem: 22446 +train: [2] [ 60/400] eta: 0:02:50 lr: 0.000129 loss: 0.9004 (0.8969) grad: 0.1503 (0.1520) time: 0.4574 data: 0.0035 max mem: 22446 +train: [2] [ 80/400] eta: 0:02:36 lr: 0.000132 loss: 0.8802 (0.8931) grad: 0.1503 (0.1514) time: 0.4516 data: 0.0035 max mem: 22446 +train: [2] [100/400] eta: 0:02:24 lr: 0.000135 loss: 0.8634 (0.8866) grad: 0.1412 (0.1501) time: 0.4564 data: 0.0034 max mem: 22446 +train: [2] [120/400] eta: 0:02:13 lr: 0.000138 loss: 0.8501 (0.8859) grad: 0.1440 (0.1575) time: 0.4491 data: 0.0035 max mem: 22446 +train: [2] [140/400] eta: 0:02:03 lr: 0.000141 loss: 0.8435 (0.8783) grad: 0.1624 (0.1603) time: 0.4521 data: 0.0035 max mem: 22446 +train: [2] [160/400] eta: 0:01:52 lr: 0.000144 loss: 0.8335 (0.8795) grad: 0.1744 (0.1650) time: 0.4483 data: 0.0035 max mem: 22446 +train: [2] [180/400] eta: 0:01:43 lr: 0.000147 loss: 0.8664 (0.8757) grad: 0.1736 (0.1670) time: 0.4500 data: 0.0035 max mem: 22446 +train: [2] [200/400] eta: 0:01:33 lr: 0.000150 loss: 0.8061 (0.8666) grad: 0.1443 (0.1656) time: 0.4484 data: 0.0035 max mem: 22446 +train: [2] [220/400] eta: 0:01:23 lr: 0.000153 loss: 0.8061 (0.8664) grad: 0.1574 (0.1724) time: 0.4428 data: 0.0034 max mem: 22446 +train: [2] [240/400] eta: 0:01:14 lr: 0.000156 loss: 0.8461 (0.8630) grad: 0.1774 (0.1727) time: 0.4440 data: 0.0034 max mem: 22446 +train: [2] [260/400] eta: 0:01:04 lr: 0.000159 loss: 0.8147 (0.8614) grad: 0.1774 (0.1759) time: 0.4740 data: 0.0034 max mem: 22446 +train: [2] [280/400] eta: 0:00:55 lr: 0.000162 loss: 0.8102 (0.8585) grad: 0.2050 (0.1785) time: 0.4575 data: 0.0035 max mem: 22446 +train: [2] [300/400] eta: 0:00:47 lr: 0.000165 loss: 0.7879 (0.8522) grad: 0.1774 (0.1788) time: 0.6123 data: 0.1718 max mem: 22446 +train: [2] [320/400] eta: 0:00:37 lr: 0.000168 loss: 0.7801 (0.8535) grad: 0.1946 (0.1852) time: 0.4679 data: 0.0029 max mem: 22446 +train: [2] [340/400] eta: 0:00:28 lr: 0.000171 loss: 0.8150 (0.8495) grad: 0.2087 (0.1861) time: 0.4581 data: 0.0036 max mem: 22446 +train: [2] [360/400] eta: 0:00:18 lr: 0.000174 loss: 0.8195 (0.8481) grad: 0.1842 (0.1874) time: 0.4748 data: 0.0037 max mem: 22446 +train: [2] [380/400] eta: 0:00:09 lr: 0.000177 loss: 0.7677 (0.8424) grad: 0.1781 (0.1875) time: 0.4660 data: 0.0038 max mem: 22446 +train: [2] [399/400] eta: 0:00:00 lr: 0.000180 loss: 0.6715 (0.8340) grad: 0.1932 (0.1897) time: 0.4573 data: 0.0035 max mem: 22446 +train: [2] Total time: 0:03:08 (0.4712 s / it) +train: [2] Summary: lr: 0.000180 loss: 0.6715 (0.8340) grad: 0.1932 (0.1897) +eval (validation): [2] [ 0/63] eta: 0:03:28 time: 3.3164 data: 3.0306 max mem: 22446 +eval (validation): [2] [20/63] eta: 0:00:23 time: 0.4005 data: 0.0254 max mem: 22446 +eval (validation): [2] [40/63] eta: 0:00:10 time: 0.3568 data: 0.0033 max mem: 22446 +eval (validation): [2] [60/63] eta: 0:00:01 time: 0.3318 data: 0.0034 max mem: 22446 +eval (validation): [2] [62/63] eta: 0:00:00 time: 0.3297 data: 0.0034 max mem: 22446 +eval (validation): [2] Total time: 0:00:26 (0.4134 s / it) +cv: [2] best hparam: (7.1, 1.0) (036) ('036_lr7.1e+00_wd1.0e+00') loss: 0.034 acc: 0.990 f1: 0.988 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/eval_v2/hcpya_task21__patch__attn/checkpoint-best.pth +train: [3] [ 0/400] eta: 0:21:54 lr: nan time: 3.2867 data: 2.9469 max mem: 22446 +train: [3] [ 20/400] eta: 0:03:48 lr: 0.000183 loss: 0.6137 (0.6534) grad: 0.1772 (0.1917) time: 0.4657 data: 0.0035 max mem: 22446 +train: [3] [ 40/400] eta: 0:03:08 lr: 0.000186 loss: 0.6636 (0.6757) grad: 0.1798 (0.1891) time: 0.4453 data: 0.0031 max mem: 22446 +train: [3] [ 60/400] eta: 0:02:49 lr: 0.000189 loss: 0.7165 (0.7085) grad: 0.2020 (0.2148) time: 0.4409 data: 0.0037 max mem: 22446 +train: [3] [ 80/400] eta: 0:02:35 lr: 0.000192 loss: 0.7165 (0.7190) grad: 0.2173 (0.2134) time: 0.4519 data: 0.0036 max mem: 22446 +train: [3] [100/400] eta: 0:02:23 lr: 0.000195 loss: 0.6476 (0.7105) grad: 0.1972 (0.2100) time: 0.4468 data: 0.0035 max mem: 22446 +train: [3] [120/400] eta: 0:02:12 lr: 0.000198 loss: 0.6442 (0.7138) grad: 0.1881 (0.2097) time: 0.4502 data: 0.0038 max mem: 22446 +train: [3] [140/400] eta: 0:02:01 lr: 0.000201 loss: 0.6860 (0.7217) grad: 0.2079 (0.2131) time: 0.4402 data: 0.0035 max mem: 22446 +train: [3] [160/400] eta: 0:01:51 lr: 0.000204 loss: 0.7211 (0.7210) grad: 0.2266 (0.2181) time: 0.4454 data: 0.0034 max mem: 22446 +train: [3] [180/400] eta: 0:01:41 lr: 0.000207 loss: 0.7266 (0.7265) grad: 0.2545 (0.2218) time: 0.4432 data: 0.0035 max mem: 22446 +train: [3] [200/400] eta: 0:01:32 lr: 0.000210 loss: 0.7021 (0.7267) grad: 0.2413 (0.2226) time: 0.4472 data: 0.0035 max mem: 22446 +train: [3] [220/400] eta: 0:01:23 lr: 0.000213 loss: 0.6363 (0.7182) grad: 0.2366 (0.2220) time: 0.4548 data: 0.0035 max mem: 22446 +train: [3] [240/400] eta: 0:01:13 lr: 0.000216 loss: 0.6676 (0.7273) grad: 0.2399 (0.2243) time: 0.4512 data: 0.0034 max mem: 22446 +train: [3] [260/400] eta: 0:01:04 lr: 0.000219 loss: 0.7148 (0.7287) grad: 0.2639 (0.2320) time: 0.4696 data: 0.0034 max mem: 22446 +train: [3] [280/400] eta: 0:00:55 lr: 0.000222 loss: 0.7113 (0.7283) grad: 0.2970 (0.2355) time: 0.4542 data: 0.0036 max mem: 22446 +train: [3] [300/400] eta: 0:00:47 lr: 0.000225 loss: 0.7203 (0.7285) grad: 0.2918 (0.2411) time: 0.6322 data: 0.1759 max mem: 22446 +train: [3] [320/400] eta: 0:00:37 lr: 0.000228 loss: 0.7292 (0.7328) grad: 0.2959 (0.2470) time: 0.4648 data: 0.0029 max mem: 22446 +train: [3] [340/400] eta: 0:00:28 lr: 0.000231 loss: 0.7166 (0.7315) grad: 0.3315 (0.2537) time: 0.4498 data: 0.0035 max mem: 22446 +train: [3] [360/400] eta: 0:00:18 lr: 0.000234 loss: 0.6847 (0.7271) grad: 0.3424 (0.2607) time: 0.4686 data: 0.0036 max mem: 22446 +train: [3] [380/400] eta: 0:00:09 lr: 0.000237 loss: 0.7052 (0.7329) grad: 0.3355 (0.2633) time: 0.4789 data: 0.0035 max mem: 22446 +train: [3] [399/400] eta: 0:00:00 lr: 0.000240 loss: 0.7368 (0.7396) grad: 0.3560 (0.2732) time: 0.4523 data: 0.0033 max mem: 22446 +train: [3] Total time: 0:03:07 (0.4699 s / it) +train: [3] Summary: lr: 0.000240 loss: 0.7368 (0.7396) grad: 0.3560 (0.2732) +eval (validation): [3] [ 0/63] eta: 0:03:30 time: 3.3362 data: 3.0504 max mem: 22446 +eval (validation): [3] [20/63] eta: 0:00:24 time: 0.4208 data: 0.0046 max mem: 22446 +eval (validation): [3] [40/63] eta: 0:00:10 time: 0.3528 data: 0.0035 max mem: 22446 +eval (validation): [3] [60/63] eta: 0:00:01 time: 0.3413 data: 0.0034 max mem: 22446 +eval (validation): [3] [62/63] eta: 0:00:00 time: 0.3327 data: 0.0034 max mem: 22446 +eval (validation): [3] Total time: 0:00:26 (0.4218 s / it) +cv: [3] best hparam: (1.2, 1.0) (025) ('025_lr1.2e+00_wd1.0e+00') loss: 0.039 acc: 0.989 f1: 0.987 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [4] [ 0/400] eta: 0:21:50 lr: nan time: 3.2759 data: 2.9331 max mem: 22446 +train: [4] [ 20/400] eta: 0:03:45 lr: 0.000243 loss: 0.7780 (0.7556) grad: 0.3950 (0.3724) time: 0.4591 data: 0.0033 max mem: 22446 +train: [4] [ 40/400] eta: 0:03:08 lr: 0.000246 loss: 0.7938 (0.7783) grad: 0.3975 (0.4012) time: 0.4515 data: 0.0033 max mem: 22446 +train: [4] [ 60/400] eta: 0:02:49 lr: 0.000249 loss: 0.6781 (0.7385) grad: 0.3832 (0.3889) time: 0.4450 data: 0.0036 max mem: 22446 +train: [4] [ 80/400] eta: 0:02:35 lr: 0.000252 loss: 0.5702 (0.7146) grad: 0.3371 (0.3852) time: 0.4449 data: 0.0035 max mem: 22446 +train: [4] [100/400] eta: 0:02:23 lr: 0.000255 loss: 0.5636 (0.7073) grad: 0.3020 (0.3702) time: 0.4462 data: 0.0035 max mem: 22446 +train: [4] [120/400] eta: 0:02:12 lr: 0.000258 loss: 0.6503 (0.7140) grad: 0.3124 (0.3667) time: 0.4504 data: 0.0035 max mem: 22446 +train: [4] [140/400] eta: 0:02:02 lr: 0.000261 loss: 0.6424 (0.7116) grad: 0.3341 (0.3652) time: 0.4513 data: 0.0035 max mem: 22446 +train: [4] [160/400] eta: 0:01:52 lr: 0.000264 loss: 0.7351 (0.7301) grad: 0.3857 (0.3806) time: 0.4487 data: 0.0035 max mem: 22446 +train: [4] [180/400] eta: 0:01:42 lr: 0.000267 loss: 0.7468 (0.7518) grad: 0.4522 (0.3903) time: 0.4528 data: 0.0035 max mem: 22446 +train: [4] [200/400] eta: 0:01:32 lr: 0.000270 loss: 0.7352 (0.7580) grad: 0.4703 (0.3965) time: 0.4491 data: 0.0034 max mem: 22446 +train: [4] [220/400] eta: 0:01:23 lr: 0.000273 loss: 0.7409 (0.7691) grad: 0.3859 (0.3948) time: 0.4412 data: 0.0033 max mem: 22446 +train: [4] [240/400] eta: 0:01:13 lr: 0.000276 loss: 0.7029 (0.7612) grad: 0.3859 (0.3955) time: 0.4441 data: 0.0033 max mem: 22446 +train: [4] [260/400] eta: 0:01:04 lr: 0.000279 loss: 0.7095 (0.7782) grad: 0.3911 (0.3955) time: 0.4711 data: 0.0035 max mem: 22446 +train: [4] [280/400] eta: 0:00:55 lr: 0.000282 loss: 0.8164 (0.7894) grad: 0.4100 (0.4067) time: 0.4524 data: 0.0038 max mem: 22446 +train: [4] [300/400] eta: 0:00:47 lr: 0.000285 loss: 0.7188 (0.7939) grad: 0.4465 (0.4198) time: 0.6061 data: 0.1692 max mem: 22446 +train: [4] [320/400] eta: 0:00:37 lr: 0.000288 loss: 0.4858 (0.7773) grad: 0.3753 (0.4252) time: 0.4621 data: 0.0033 max mem: 22446 +train: [4] [340/400] eta: 0:00:28 lr: 0.000291 loss: 0.5038 (0.7654) grad: 0.3746 (0.4245) time: 0.4471 data: 0.0036 max mem: 22446 +train: [4] [360/400] eta: 0:00:18 lr: 0.000294 loss: 0.5905 (0.7720) grad: 0.4524 (0.4264) time: 0.4742 data: 0.0035 max mem: 22446 +train: [4] [380/400] eta: 0:00:09 lr: 0.000297 loss: 0.7818 (0.7797) grad: 0.4677 (0.4296) time: 0.4753 data: 0.0036 max mem: 22446 +train: [4] [399/400] eta: 0:00:00 lr: 0.000300 loss: 0.8107 (0.7835) grad: 0.4504 (0.4336) time: 0.4414 data: 0.0035 max mem: 22446 +train: [4] Total time: 0:03:07 (0.4680 s / it) +train: [4] Summary: lr: 0.000300 loss: 0.8107 (0.7835) grad: 0.4504 (0.4336) +eval (validation): [4] [ 0/63] eta: 0:03:29 time: 3.3324 data: 3.0470 max mem: 22446 +eval (validation): [4] [20/63] eta: 0:00:21 time: 0.3559 data: 0.0042 max mem: 22446 +eval (validation): [4] [40/63] eta: 0:00:09 time: 0.3453 data: 0.0029 max mem: 22446 +eval (validation): [4] [60/63] eta: 0:00:01 time: 0.3294 data: 0.0034 max mem: 22446 +eval (validation): [4] [62/63] eta: 0:00:00 time: 0.3286 data: 0.0034 max mem: 22446 +eval (validation): [4] Total time: 0:00:24 (0.3949 s / it) +cv: [4] best hparam: (0.52, 1.0) (020) ('020_lr5.2e-01_wd1.0e+00') loss: 0.044 acc: 0.989 f1: 0.987 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [5] [ 0/400] eta: 0:21:39 lr: nan time: 3.2489 data: 2.9150 max mem: 22446 +train: [5] [ 20/400] eta: 0:03:43 lr: 0.000300 loss: 0.6988 (0.8209) grad: 0.3687 (0.4114) time: 0.4542 data: 0.0039 max mem: 22446 +train: [5] [ 40/400] eta: 0:03:06 lr: 0.000300 loss: 0.6988 (0.7845) grad: 0.3687 (0.4132) time: 0.4474 data: 0.0032 max mem: 22446 +train: [5] [ 60/400] eta: 0:02:48 lr: 0.000300 loss: 0.7320 (0.7935) grad: 0.4194 (0.4241) time: 0.4491 data: 0.0036 max mem: 22446 +train: [5] [ 80/400] eta: 0:02:34 lr: 0.000300 loss: 0.7798 (0.8130) grad: 0.4534 (0.4341) time: 0.4459 data: 0.0036 max mem: 22446 +train: [5] [100/400] eta: 0:02:23 lr: 0.000300 loss: 0.8724 (0.8708) grad: 0.5217 (0.4601) time: 0.4481 data: 0.0033 max mem: 22446 +train: [5] [120/400] eta: 0:02:12 lr: 0.000300 loss: 0.9911 (0.8992) grad: 0.5403 (0.4839) time: 0.4538 data: 0.0034 max mem: 22446 +train: [5] [140/400] eta: 0:02:02 lr: 0.000300 loss: 0.9114 (0.8846) grad: 0.4727 (0.4811) time: 0.4482 data: 0.0035 max mem: 22446 +train: [5] [160/400] eta: 0:01:52 lr: 0.000299 loss: 0.6832 (0.8839) grad: 0.4621 (0.4841) time: 0.4572 data: 0.0034 max mem: 22446 +train: [5] [180/400] eta: 0:01:42 lr: 0.000299 loss: 0.6664 (0.8554) grad: 0.4899 (0.4820) time: 0.4520 data: 0.0033 max mem: 22446 +train: [5] [200/400] eta: 0:01:33 lr: 0.000299 loss: 0.6980 (0.8492) grad: 0.5103 (0.4865) time: 0.4586 data: 0.0034 max mem: 22446 +train: [5] [220/400] eta: 0:01:23 lr: 0.000299 loss: 0.7260 (0.8593) grad: 0.4570 (0.4825) time: 0.4487 data: 0.0035 max mem: 22446 +train: [5] [240/400] eta: 0:01:13 lr: 0.000299 loss: 0.7762 (0.8592) grad: 0.4570 (0.4846) time: 0.4406 data: 0.0034 max mem: 22446 +train: [5] [260/400] eta: 0:01:04 lr: 0.000299 loss: 1.0362 (0.8857) grad: 0.5132 (0.4912) time: 0.4667 data: 0.0035 max mem: 22446 +train: [5] [280/400] eta: 0:00:55 lr: 0.000298 loss: 1.0420 (0.9098) grad: 0.5094 (0.4940) time: 0.4634 data: 0.0036 max mem: 22446 +train: [5] [300/400] eta: 0:00:47 lr: 0.000298 loss: 0.6896 (0.9023) grad: 0.5063 (0.4936) time: 0.6092 data: 0.1737 max mem: 22446 +train: [5] [320/400] eta: 0:00:37 lr: 0.000298 loss: 0.6737 (0.9013) grad: 0.4757 (0.4921) time: 0.4756 data: 0.0033 max mem: 22446 +train: [5] [340/400] eta: 0:00:28 lr: 0.000298 loss: 0.7400 (0.9010) grad: 0.4564 (0.4909) time: 0.4540 data: 0.0036 max mem: 22446 +train: [5] [360/400] eta: 0:00:18 lr: 0.000297 loss: 0.8326 (0.8948) grad: 0.4270 (0.4892) time: 0.4671 data: 0.0036 max mem: 22446 +train: [5] [380/400] eta: 0:00:09 lr: 0.000297 loss: 0.6765 (0.8838) grad: 0.4105 (0.4839) time: 0.4693 data: 0.0036 max mem: 22446 +train: [5] [399/400] eta: 0:00:00 lr: 0.000297 loss: 0.5257 (0.8641) grad: 0.3427 (0.4759) time: 0.4586 data: 0.0034 max mem: 22446 +train: [5] Total time: 0:03:08 (0.4706 s / it) +train: [5] Summary: lr: 0.000297 loss: 0.5257 (0.8641) grad: 0.3427 (0.4759) +eval (validation): [5] [ 0/63] eta: 0:03:23 time: 3.2352 data: 2.9804 max mem: 22446 +eval (validation): [5] [20/63] eta: 0:00:22 time: 0.3838 data: 0.0038 max mem: 22446 +eval (validation): [5] [40/63] eta: 0:00:10 time: 0.3651 data: 0.0030 max mem: 22446 +eval (validation): [5] [60/63] eta: 0:00:01 time: 0.3295 data: 0.0035 max mem: 22446 +eval (validation): [5] [62/63] eta: 0:00:00 time: 0.3283 data: 0.0034 max mem: 22446 +eval (validation): [5] Total time: 0:00:25 (0.4081 s / it) +cv: [5] best hparam: (3.1, 1.0) (031) ('031_lr3.1e+00_wd1.0e+00') loss: 0.032 acc: 0.990 f1: 0.988 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [6] [ 0/400] eta: 0:21:56 lr: nan time: 3.2913 data: 2.9525 max mem: 22446 +train: [6] [ 20/400] eta: 0:03:42 lr: 0.000296 loss: 0.4752 (0.4857) grad: 0.3633 (0.3883) time: 0.4496 data: 0.0030 max mem: 22446 +train: [6] [ 40/400] eta: 0:03:09 lr: 0.000296 loss: 0.4247 (0.5188) grad: 0.3171 (0.3567) time: 0.4650 data: 0.0034 max mem: 22446 +train: [6] [ 60/400] eta: 0:02:50 lr: 0.000296 loss: 0.4012 (0.5081) grad: 0.3208 (0.3591) time: 0.4485 data: 0.0035 max mem: 22446 +train: [6] [ 80/400] eta: 0:02:36 lr: 0.000295 loss: 0.5849 (0.5464) grad: 0.3566 (0.3622) time: 0.4478 data: 0.0035 max mem: 22446 +train: [6] [100/400] eta: 0:02:24 lr: 0.000295 loss: 0.6106 (0.5541) grad: 0.3734 (0.3646) time: 0.4497 data: 0.0036 max mem: 22446 +train: [6] [120/400] eta: 0:02:12 lr: 0.000295 loss: 0.4863 (0.5606) grad: 0.3734 (0.3704) time: 0.4439 data: 0.0036 max mem: 22446 +train: [6] [140/400] eta: 0:02:02 lr: 0.000294 loss: 0.4933 (0.5738) grad: 0.3932 (0.3768) time: 0.4516 data: 0.0036 max mem: 22446 +train: [6] [160/400] eta: 0:01:52 lr: 0.000294 loss: 0.4933 (0.5649) grad: 0.3885 (0.3805) time: 0.4507 data: 0.0035 max mem: 22446 +train: [6] [180/400] eta: 0:01:42 lr: 0.000293 loss: 0.5994 (0.5881) grad: 0.3938 (0.3861) time: 0.4550 data: 0.0035 max mem: 22446 +train: [6] [200/400] eta: 0:01:33 lr: 0.000293 loss: 0.5058 (0.6094) grad: 0.4403 (0.3865) time: 0.4539 data: 0.0035 max mem: 22446 +train: [6] [220/400] eta: 0:01:23 lr: 0.000292 loss: 0.4226 (0.6088) grad: 0.3992 (0.3863) time: 0.4531 data: 0.0035 max mem: 22446 +train: [6] [240/400] eta: 0:01:14 lr: 0.000292 loss: 0.4250 (0.6044) grad: 0.3600 (0.3830) time: 0.4445 data: 0.0035 max mem: 22446 +train: [6] [260/400] eta: 0:01:04 lr: 0.000291 loss: 0.4400 (0.6002) grad: 0.3911 (0.3888) time: 0.4662 data: 0.0035 max mem: 22446 +train: [6] [280/400] eta: 0:00:55 lr: 0.000291 loss: 0.5174 (0.6066) grad: 0.4164 (0.3898) time: 0.4597 data: 0.0037 max mem: 22446 +train: [6] [300/400] eta: 0:00:47 lr: 0.000290 loss: 0.5922 (0.6042) grad: 0.3492 (0.3858) time: 0.5997 data: 0.1726 max mem: 22446 +train: [6] [320/400] eta: 0:00:37 lr: 0.000290 loss: 0.3883 (0.5942) grad: 0.3150 (0.3820) time: 0.4619 data: 0.0033 max mem: 22446 +train: [6] [340/400] eta: 0:00:28 lr: 0.000289 loss: 0.4837 (0.5908) grad: 0.3484 (0.3836) time: 0.4614 data: 0.0035 max mem: 22446 +train: [6] [360/400] eta: 0:00:18 lr: 0.000288 loss: 0.4379 (0.5861) grad: 0.3484 (0.3816) time: 0.4701 data: 0.0035 max mem: 22446 +train: [6] [380/400] eta: 0:00:09 lr: 0.000288 loss: 0.3972 (0.5761) grad: 0.3342 (0.3789) time: 0.4768 data: 0.0035 max mem: 22446 +train: [6] [399/400] eta: 0:00:00 lr: 0.000287 loss: 0.2825 (0.5621) grad: 0.3026 (0.3750) time: 0.4603 data: 0.0035 max mem: 22446 +train: [6] Total time: 0:03:08 (0.4708 s / it) +train: [6] Summary: lr: 0.000287 loss: 0.2825 (0.5621) grad: 0.3026 (0.3750) +eval (validation): [6] [ 0/63] eta: 0:03:19 time: 3.1626 data: 2.8751 max mem: 22446 +eval (validation): [6] [20/63] eta: 0:00:22 time: 0.3794 data: 0.0032 max mem: 22446 +eval (validation): [6] [40/63] eta: 0:00:10 time: 0.3732 data: 0.0034 max mem: 22446 +eval (validation): [6] [60/63] eta: 0:00:01 time: 0.3320 data: 0.0035 max mem: 22446 +eval (validation): [6] [62/63] eta: 0:00:00 time: 0.3293 data: 0.0034 max mem: 22446 +eval (validation): [6] Total time: 0:00:25 (0.4093 s / it) +cv: [6] best hparam: (3.1, 1.0) (031) ('031_lr3.1e+00_wd1.0e+00') loss: 0.028 acc: 0.991 f1: 0.989 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/eval_v2/hcpya_task21__patch__attn/checkpoint-best.pth +train: [7] [ 0/400] eta: 0:22:40 lr: nan time: 3.4012 data: 3.0091 max mem: 22446 +train: [7] [ 20/400] eta: 0:03:51 lr: 0.000286 loss: 0.2996 (0.3850) grad: 0.2748 (0.2973) time: 0.4707 data: 0.0024 max mem: 22446 +train: [7] [ 40/400] eta: 0:03:12 lr: 0.000286 loss: 0.3158 (0.4141) grad: 0.2748 (0.2867) time: 0.4550 data: 0.0037 max mem: 22446 +train: [7] [ 60/400] eta: 0:02:52 lr: 0.000285 loss: 0.3407 (0.4365) grad: 0.2878 (0.2957) time: 0.4553 data: 0.0035 max mem: 22446 +train: [7] [ 80/400] eta: 0:02:38 lr: 0.000284 loss: 0.3889 (0.4213) grad: 0.3066 (0.3033) time: 0.4492 data: 0.0035 max mem: 22446 +train: [7] [100/400] eta: 0:02:25 lr: 0.000284 loss: 0.3246 (0.4186) grad: 0.3066 (0.3110) time: 0.4519 data: 0.0035 max mem: 22446 +train: [7] [120/400] eta: 0:02:14 lr: 0.000283 loss: 0.3587 (0.4144) grad: 0.3156 (0.3105) time: 0.4530 data: 0.0034 max mem: 22446 +train: [7] [140/400] eta: 0:02:03 lr: 0.000282 loss: 0.3254 (0.4144) grad: 0.3285 (0.3101) time: 0.4459 data: 0.0035 max mem: 22446 +train: [7] [160/400] eta: 0:01:53 lr: 0.000282 loss: 0.3254 (0.4170) grad: 0.3327 (0.3112) time: 0.4526 data: 0.0035 max mem: 22446 +train: [7] [180/400] eta: 0:01:43 lr: 0.000281 loss: 0.3716 (0.4186) grad: 0.2968 (0.3127) time: 0.4485 data: 0.0034 max mem: 22446 +train: [7] [200/400] eta: 0:01:33 lr: 0.000280 loss: 0.3061 (0.4164) grad: 0.3048 (0.3129) time: 0.4415 data: 0.0035 max mem: 22446 +train: [7] [220/400] eta: 0:01:23 lr: 0.000279 loss: 0.2187 (0.4125) grad: 0.3225 (0.3122) time: 0.4517 data: 0.0035 max mem: 22446 +train: [7] [240/400] eta: 0:01:14 lr: 0.000278 loss: 0.2148 (0.4164) grad: 0.3165 (0.3136) time: 0.4438 data: 0.0033 max mem: 22446 +train: [7] [260/400] eta: 0:01:05 lr: 0.000278 loss: 0.2322 (0.4086) grad: 0.3165 (0.3128) time: 0.4736 data: 0.0035 max mem: 22446 +train: [7] [280/400] eta: 0:00:55 lr: 0.000277 loss: 0.3543 (0.4170) grad: 0.3134 (0.3132) time: 0.4532 data: 0.0037 max mem: 22446 +train: [7] [300/400] eta: 0:00:47 lr: 0.000276 loss: 0.4047 (0.4153) grad: 0.3175 (0.3124) time: 0.5968 data: 0.1689 max mem: 22446 +train: [7] [320/400] eta: 0:00:37 lr: 0.000275 loss: 0.2938 (0.4142) grad: 0.2737 (0.3109) time: 0.4587 data: 0.0036 max mem: 22446 +train: [7] [340/400] eta: 0:00:28 lr: 0.000274 loss: 0.2418 (0.4083) grad: 0.2549 (0.3134) time: 0.4552 data: 0.0034 max mem: 22446 +train: [7] [360/400] eta: 0:00:18 lr: 0.000273 loss: 0.2440 (0.4005) grad: 0.2233 (0.3117) time: 0.4627 data: 0.0035 max mem: 22446 +train: [7] [380/400] eta: 0:00:09 lr: 0.000272 loss: 0.2513 (0.3926) grad: 0.2412 (0.3111) time: 0.4725 data: 0.0035 max mem: 22446 +train: [7] [399/400] eta: 0:00:00 lr: 0.000271 loss: 0.2303 (0.3846) grad: 0.2268 (0.3093) time: 0.4557 data: 0.0036 max mem: 22446 +train: [7] Total time: 0:03:08 (0.4700 s / it) +train: [7] Summary: lr: 0.000271 loss: 0.2303 (0.3846) grad: 0.2268 (0.3093) +eval (validation): [7] [ 0/63] eta: 0:03:24 time: 3.2530 data: 3.0040 max mem: 22446 +eval (validation): [7] [20/63] eta: 0:00:21 time: 0.3740 data: 0.0034 max mem: 22446 +eval (validation): [7] [40/63] eta: 0:00:10 time: 0.3749 data: 0.0034 max mem: 22446 +eval (validation): [7] [60/63] eta: 0:00:01 time: 0.3320 data: 0.0035 max mem: 22446 +eval (validation): [7] [62/63] eta: 0:00:00 time: 0.3323 data: 0.0035 max mem: 22446 +eval (validation): [7] Total time: 0:00:25 (0.4098 s / it) +cv: [7] best hparam: (3.1, 1.0) (031) ('031_lr3.1e+00_wd1.0e+00') loss: 0.025 acc: 0.993 f1: 0.991 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/eval_v2/hcpya_task21__patch__attn/checkpoint-best.pth +train: [8] [ 0/400] eta: 0:22:31 lr: nan time: 3.3776 data: 3.0290 max mem: 22446 +train: [8] [ 20/400] eta: 0:03:46 lr: 0.000270 loss: 0.2166 (0.2466) grad: 0.2288 (0.2532) time: 0.4566 data: 0.0030 max mem: 22446 +train: [8] [ 40/400] eta: 0:03:09 lr: 0.000270 loss: 0.2194 (0.2628) grad: 0.2033 (0.2394) time: 0.4515 data: 0.0035 max mem: 22446 +train: [8] [ 60/400] eta: 0:02:50 lr: 0.000269 loss: 0.2194 (0.2508) grad: 0.1997 (0.2268) time: 0.4502 data: 0.0035 max mem: 22446 +train: [8] [ 80/400] eta: 0:02:37 lr: 0.000268 loss: 0.2146 (0.2458) grad: 0.2017 (0.2239) time: 0.4604 data: 0.0035 max mem: 22446 +train: [8] [100/400] eta: 0:02:25 lr: 0.000267 loss: 0.2079 (0.2393) grad: 0.1989 (0.2179) time: 0.4545 data: 0.0035 max mem: 22446 +train: [8] [120/400] eta: 0:02:13 lr: 0.000266 loss: 0.2041 (0.2523) grad: 0.1989 (0.2180) time: 0.4443 data: 0.0036 max mem: 22446 +train: [8] [140/400] eta: 0:02:03 lr: 0.000265 loss: 0.2168 (0.2574) grad: 0.2168 (0.2205) time: 0.4511 data: 0.0035 max mem: 22446 +train: [8] [160/400] eta: 0:01:52 lr: 0.000264 loss: 0.2323 (0.2573) grad: 0.2065 (0.2223) time: 0.4528 data: 0.0037 max mem: 22446 +train: [8] [180/400] eta: 0:01:42 lr: 0.000263 loss: 0.2323 (0.2616) grad: 0.1779 (0.2189) time: 0.4455 data: 0.0035 max mem: 22446 +train: [8] [200/400] eta: 0:01:33 lr: 0.000262 loss: 0.1976 (0.2579) grad: 0.2029 (0.2201) time: 0.4596 data: 0.0034 max mem: 22446 +train: [8] [220/400] eta: 0:01:23 lr: 0.000260 loss: 0.2003 (0.2540) grad: 0.2065 (0.2218) time: 0.4574 data: 0.0035 max mem: 22446 +train: [8] [240/400] eta: 0:01:14 lr: 0.000259 loss: 0.1942 (0.2510) grad: 0.2028 (0.2189) time: 0.4530 data: 0.0034 max mem: 22446 +train: [8] [260/400] eta: 0:01:05 lr: 0.000258 loss: 0.1942 (0.2504) grad: 0.2028 (0.2204) time: 0.4596 data: 0.0035 max mem: 22446 +train: [8] [280/400] eta: 0:00:55 lr: 0.000257 loss: 0.2080 (0.2492) grad: 0.2164 (0.2202) time: 0.4555 data: 0.0036 max mem: 22446 +train: [8] [300/400] eta: 0:00:47 lr: 0.000256 loss: 0.2308 (0.2596) grad: 0.2217 (0.2223) time: 0.6132 data: 0.1769 max mem: 22446 +train: [8] [320/400] eta: 0:00:37 lr: 0.000255 loss: 0.2709 (0.2603) grad: 0.2360 (0.2233) time: 0.4535 data: 0.0038 max mem: 22446 +train: [8] [340/400] eta: 0:00:28 lr: 0.000254 loss: 0.2132 (0.2576) grad: 0.2148 (0.2224) time: 0.4447 data: 0.0034 max mem: 22446 +train: [8] [360/400] eta: 0:00:18 lr: 0.000253 loss: 0.1834 (0.2523) grad: 0.1965 (0.2199) time: 0.4562 data: 0.0035 max mem: 22446 +train: [8] [380/400] eta: 0:00:09 lr: 0.000252 loss: 0.1310 (0.2471) grad: 0.1700 (0.2171) time: 0.4701 data: 0.0036 max mem: 22446 +train: [8] [399/400] eta: 0:00:00 lr: 0.000250 loss: 0.1715 (0.2449) grad: 0.1742 (0.2154) time: 0.4543 data: 0.0034 max mem: 22446 +train: [8] Total time: 0:03:07 (0.4698 s / it) +train: [8] Summary: lr: 0.000250 loss: 0.1715 (0.2449) grad: 0.1742 (0.2154) +eval (validation): [8] [ 0/63] eta: 0:03:25 time: 3.2570 data: 3.0018 max mem: 22446 +eval (validation): [8] [20/63] eta: 0:00:22 time: 0.3926 data: 0.0032 max mem: 22446 +eval (validation): [8] [40/63] eta: 0:00:10 time: 0.3408 data: 0.0028 max mem: 22446 +eval (validation): [8] [60/63] eta: 0:00:01 time: 0.3239 data: 0.0029 max mem: 22446 +eval (validation): [8] [62/63] eta: 0:00:00 time: 0.3153 data: 0.0029 max mem: 22446 +eval (validation): [8] Total time: 0:00:25 (0.4019 s / it) +cv: [8] best hparam: (1.4, 1.0) (026) ('026_lr1.4e+00_wd1.0e+00') loss: 0.025 acc: 0.993 f1: 0.991 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [9] [ 0/400] eta: 0:22:42 lr: nan time: 3.4057 data: 3.0568 max mem: 22446 +train: [9] [ 20/400] eta: 0:03:41 lr: 0.000249 loss: 0.2345 (0.2558) grad: 0.2013 (0.1951) time: 0.4425 data: 0.0032 max mem: 22446 +train: [9] [ 40/400] eta: 0:03:05 lr: 0.000248 loss: 0.2215 (0.2189) grad: 0.1863 (0.1865) time: 0.4417 data: 0.0031 max mem: 22446 +train: [9] [ 60/400] eta: 0:02:47 lr: 0.000247 loss: 0.1554 (0.2119) grad: 0.1641 (0.1807) time: 0.4482 data: 0.0035 max mem: 22446 +train: [9] [ 80/400] eta: 0:02:33 lr: 0.000246 loss: 0.1533 (0.2097) grad: 0.1518 (0.1734) time: 0.4407 data: 0.0035 max mem: 22446 +train: [9] [100/400] eta: 0:02:22 lr: 0.000244 loss: 0.1563 (0.2042) grad: 0.1518 (0.1794) time: 0.4578 data: 0.0035 max mem: 22446 +train: [9] [120/400] eta: 0:02:11 lr: 0.000243 loss: 0.1623 (0.2060) grad: 0.2072 (0.1841) time: 0.4431 data: 0.0035 max mem: 22446 +train: [9] [140/400] eta: 0:02:01 lr: 0.000242 loss: 0.1488 (0.1985) grad: 0.1622 (0.1806) time: 0.4461 data: 0.0036 max mem: 22446 +train: [9] [160/400] eta: 0:01:51 lr: 0.000241 loss: 0.1566 (0.1951) grad: 0.1656 (0.1811) time: 0.4397 data: 0.0036 max mem: 22446 +train: [9] [180/400] eta: 0:01:41 lr: 0.000240 loss: 0.1566 (0.1895) grad: 0.1509 (0.1776) time: 0.4413 data: 0.0035 max mem: 22446 +train: [9] [200/400] eta: 0:01:31 lr: 0.000238 loss: 0.1398 (0.1886) grad: 0.1776 (0.1803) time: 0.4401 data: 0.0035 max mem: 22446 +train: [9] [220/400] eta: 0:01:22 lr: 0.000237 loss: 0.1395 (0.1864) grad: 0.1744 (0.1780) time: 0.4631 data: 0.0037 max mem: 22446 +train: [9] [240/400] eta: 0:01:13 lr: 0.000236 loss: 0.1280 (0.1817) grad: 0.1546 (0.1767) time: 0.4385 data: 0.0034 max mem: 22446 +train: [9] [260/400] eta: 0:01:04 lr: 0.000234 loss: 0.1254 (0.1824) grad: 0.1799 (0.1781) time: 0.4875 data: 0.0036 max mem: 22446 +train: [9] [280/400] eta: 0:00:55 lr: 0.000233 loss: 0.2077 (0.1864) grad: 0.1731 (0.1807) time: 0.4540 data: 0.0035 max mem: 22446 +train: [9] [300/400] eta: 0:00:46 lr: 0.000232 loss: 0.1880 (0.1878) grad: 0.1705 (0.1814) time: 0.6132 data: 0.1800 max mem: 22446 +train: [9] [320/400] eta: 0:00:37 lr: 0.000230 loss: 0.1770 (0.1880) grad: 0.1508 (0.1807) time: 0.4442 data: 0.0031 max mem: 22446 +train: [9] [340/400] eta: 0:00:27 lr: 0.000229 loss: 0.1500 (0.1869) grad: 0.1610 (0.1800) time: 0.4393 data: 0.0034 max mem: 22446 +train: [9] [360/400] eta: 0:00:18 lr: 0.000228 loss: 0.1445 (0.1853) grad: 0.1588 (0.1784) time: 0.4554 data: 0.0036 max mem: 22446 +train: [9] [380/400] eta: 0:00:09 lr: 0.000226 loss: 0.1423 (0.1828) grad: 0.1386 (0.1762) time: 0.4717 data: 0.0035 max mem: 22446 +train: [9] [399/400] eta: 0:00:00 lr: 0.000225 loss: 0.1371 (0.1812) grad: 0.1241 (0.1748) time: 0.4538 data: 0.0034 max mem: 22446 +train: [9] Total time: 0:03:06 (0.4657 s / it) +train: [9] Summary: lr: 0.000225 loss: 0.1371 (0.1812) grad: 0.1241 (0.1748) +eval (validation): [9] [ 0/63] eta: 0:03:31 time: 3.3593 data: 3.0458 max mem: 22446 +eval (validation): [9] [20/63] eta: 0:00:22 time: 0.3906 data: 0.0037 max mem: 22446 +eval (validation): [9] [40/63] eta: 0:00:10 time: 0.3408 data: 0.0038 max mem: 22446 +eval (validation): [9] [60/63] eta: 0:00:01 time: 0.3177 data: 0.0033 max mem: 22446 +eval (validation): [9] [62/63] eta: 0:00:00 time: 0.3146 data: 0.0033 max mem: 22446 +eval (validation): [9] Total time: 0:00:25 (0.4007 s / it) +cv: [9] best hparam: (2.3, 1.0) (029) ('029_lr2.3e+00_wd1.0e+00') loss: 0.025 acc: 0.993 f1: 0.991 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/eval_v2/hcpya_task21__patch__attn/checkpoint-best.pth +train: [10] [ 0/400] eta: 0:22:37 lr: nan time: 3.3928 data: 3.0520 max mem: 22446 +train: [10] [ 20/400] eta: 0:03:41 lr: 0.000224 loss: 0.1454 (0.2122) grad: 0.0997 (0.1472) time: 0.4430 data: 0.0080 max mem: 22446 +train: [10] [ 40/400] eta: 0:03:03 lr: 0.000222 loss: 0.1263 (0.1775) grad: 0.1345 (0.1506) time: 0.4349 data: 0.0032 max mem: 22446 +train: [10] [ 60/400] eta: 0:02:46 lr: 0.000221 loss: 0.1192 (0.1641) grad: 0.1243 (0.1349) time: 0.4465 data: 0.0037 max mem: 22446 +train: [10] [ 80/400] eta: 0:02:32 lr: 0.000220 loss: 0.1236 (0.1561) grad: 0.1418 (0.1479) time: 0.4396 data: 0.0035 max mem: 22446 +train: [10] [100/400] eta: 0:02:21 lr: 0.000218 loss: 0.1236 (0.1536) grad: 0.1584 (0.1483) time: 0.4438 data: 0.0036 max mem: 22446 +train: [10] [120/400] eta: 0:02:10 lr: 0.000217 loss: 0.1095 (0.1479) grad: 0.1431 (0.1479) time: 0.4482 data: 0.0034 max mem: 22446 +train: [10] [140/400] eta: 0:02:00 lr: 0.000215 loss: 0.1170 (0.1476) grad: 0.1273 (0.1446) time: 0.4483 data: 0.0035 max mem: 22446 +train: [10] [160/400] eta: 0:01:50 lr: 0.000214 loss: 0.1087 (0.1459) grad: 0.1234 (0.1461) time: 0.4474 data: 0.0036 max mem: 22446 +train: [10] [180/400] eta: 0:01:41 lr: 0.000213 loss: 0.1079 (0.1441) grad: 0.1242 (0.1422) time: 0.4373 data: 0.0036 max mem: 22446 +train: [10] [200/400] eta: 0:01:31 lr: 0.000211 loss: 0.1221 (0.1437) grad: 0.1225 (0.1428) time: 0.4476 data: 0.0035 max mem: 22446 +train: [10] [220/400] eta: 0:01:22 lr: 0.000210 loss: 0.1152 (0.1414) grad: 0.1097 (0.1398) time: 0.4440 data: 0.0035 max mem: 22446 +train: [10] [240/400] eta: 0:01:12 lr: 0.000208 loss: 0.1110 (0.1410) grad: 0.1041 (0.1388) time: 0.4315 data: 0.0034 max mem: 22446 +train: [10] [260/400] eta: 0:01:03 lr: 0.000207 loss: 0.1042 (0.1398) grad: 0.1261 (0.1398) time: 0.4682 data: 0.0036 max mem: 22446 +train: [10] [280/400] eta: 0:00:54 lr: 0.000205 loss: 0.1099 (0.1390) grad: 0.1359 (0.1382) time: 0.4369 data: 0.0036 max mem: 22446 +train: [10] [300/400] eta: 0:00:46 lr: 0.000204 loss: 0.1006 (0.1388) grad: 0.1120 (0.1373) time: 0.6223 data: 0.1927 max mem: 22446 +train: [10] [320/400] eta: 0:00:37 lr: 0.000202 loss: 0.1004 (0.1367) grad: 0.1043 (0.1365) time: 0.4342 data: 0.0031 max mem: 22446 +train: [10] [340/400] eta: 0:00:27 lr: 0.000201 loss: 0.1004 (0.1348) grad: 0.1043 (0.1353) time: 0.4446 data: 0.0031 max mem: 22446 +train: [10] [360/400] eta: 0:00:18 lr: 0.000199 loss: 0.0983 (0.1353) grad: 0.1187 (0.1341) time: 0.4698 data: 0.0038 max mem: 22446 +train: [10] [380/400] eta: 0:00:09 lr: 0.000198 loss: 0.1107 (0.1354) grad: 0.1187 (0.1336) time: 0.4533 data: 0.0035 max mem: 22446 +train: [10] [399/400] eta: 0:00:00 lr: 0.000196 loss: 0.1146 (0.1341) grad: 0.0960 (0.1312) time: 0.4512 data: 0.0034 max mem: 22446 +train: [10] Total time: 0:03:04 (0.4623 s / it) +train: [10] Summary: lr: 0.000196 loss: 0.1146 (0.1341) grad: 0.0960 (0.1312) +eval (validation): [10] [ 0/63] eta: 0:03:18 time: 3.1547 data: 2.9222 max mem: 22446 +eval (validation): [10] [20/63] eta: 0:00:21 time: 0.3619 data: 0.0039 max mem: 22446 +eval (validation): [10] [40/63] eta: 0:00:09 time: 0.3548 data: 0.0034 max mem: 22446 +eval (validation): [10] [60/63] eta: 0:00:01 time: 0.3157 data: 0.0031 max mem: 22446 +eval (validation): [10] [62/63] eta: 0:00:00 time: 0.3144 data: 0.0029 max mem: 22446 +eval (validation): [10] Total time: 0:00:24 (0.3922 s / it) +cv: [10] best hparam: (3.7, 1.0) (032) ('032_lr3.7e+00_wd1.0e+00') loss: 0.027 acc: 0.993 f1: 0.991 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [11] [ 0/400] eta: 0:23:09 lr: nan time: 3.4730 data: 3.0907 max mem: 22446 +train: [11] [ 20/400] eta: 0:03:40 lr: 0.000195 loss: 0.1174 (0.1360) grad: 0.1062 (0.1123) time: 0.4354 data: 0.0029 max mem: 22446 +train: [11] [ 40/400] eta: 0:03:03 lr: 0.000193 loss: 0.1165 (0.1285) grad: 0.1025 (0.1096) time: 0.4359 data: 0.0036 max mem: 22446 +train: [11] [ 60/400] eta: 0:02:46 lr: 0.000192 loss: 0.1115 (0.1329) grad: 0.1049 (0.1105) time: 0.4445 data: 0.0036 max mem: 22446 +train: [11] [ 80/400] eta: 0:02:33 lr: 0.000190 loss: 0.1084 (0.1275) grad: 0.1179 (0.1110) time: 0.4481 data: 0.0035 max mem: 22446 +train: [11] [100/400] eta: 0:02:21 lr: 0.000189 loss: 0.0968 (0.1241) grad: 0.1094 (0.1087) time: 0.4414 data: 0.0035 max mem: 22446 +train: [11] [120/400] eta: 0:02:10 lr: 0.000187 loss: 0.0937 (0.1195) grad: 0.1093 (0.1094) time: 0.4361 data: 0.0035 max mem: 22446 +train: [11] [140/400] eta: 0:02:00 lr: 0.000186 loss: 0.0944 (0.1181) grad: 0.1068 (0.1080) time: 0.4440 data: 0.0036 max mem: 22446 +train: [11] [160/400] eta: 0:01:50 lr: 0.000184 loss: 0.0975 (0.1183) grad: 0.0897 (0.1061) time: 0.4474 data: 0.0034 max mem: 22446 +train: [11] [180/400] eta: 0:01:40 lr: 0.000183 loss: 0.0911 (0.1185) grad: 0.0906 (0.1072) time: 0.4461 data: 0.0034 max mem: 22446 +train: [11] [200/400] eta: 0:01:31 lr: 0.000181 loss: 0.0898 (0.1162) grad: 0.1130 (0.1068) time: 0.4424 data: 0.0035 max mem: 22446 +train: [11] [220/400] eta: 0:01:22 lr: 0.000180 loss: 0.0944 (0.1149) grad: 0.1088 (0.1054) time: 0.4403 data: 0.0036 max mem: 22446 +train: [11] [240/400] eta: 0:01:12 lr: 0.000178 loss: 0.0949 (0.1133) grad: 0.0955 (0.1045) time: 0.4290 data: 0.0034 max mem: 22446 +train: [11] [260/400] eta: 0:01:03 lr: 0.000177 loss: 0.0949 (0.1120) grad: 0.0798 (0.1021) time: 0.4614 data: 0.0035 max mem: 22446 +train: [11] [280/400] eta: 0:00:54 lr: 0.000175 loss: 0.0978 (0.1120) grad: 0.0855 (0.1016) time: 0.4416 data: 0.0035 max mem: 22446 +train: [11] [300/400] eta: 0:00:46 lr: 0.000174 loss: 0.0937 (0.1109) grad: 0.0977 (0.1006) time: 0.6298 data: 0.1813 max mem: 22446 +train: [11] [320/400] eta: 0:00:37 lr: 0.000172 loss: 0.0933 (0.1098) grad: 0.0768 (0.0996) time: 0.4508 data: 0.0036 max mem: 22446 +train: [11] [340/400] eta: 0:00:27 lr: 0.000170 loss: 0.0975 (0.1089) grad: 0.0915 (0.0991) time: 0.4600 data: 0.0038 max mem: 22446 +train: [11] [360/400] eta: 0:00:18 lr: 0.000169 loss: 0.0926 (0.1079) grad: 0.0769 (0.0970) time: 0.4602 data: 0.0038 max mem: 22446 +train: [11] [380/400] eta: 0:00:09 lr: 0.000167 loss: 0.0816 (0.1066) grad: 0.0431 (0.0947) time: 0.4706 data: 0.0036 max mem: 22446 +train: [11] [399/400] eta: 0:00:00 lr: 0.000166 loss: 0.0812 (0.1057) grad: 0.0443 (0.0935) time: 0.4444 data: 0.0034 max mem: 22446 +train: [11] Total time: 0:03:05 (0.4633 s / it) +train: [11] Summary: lr: 0.000166 loss: 0.0812 (0.1057) grad: 0.0443 (0.0935) +eval (validation): [11] [ 0/63] eta: 0:03:18 time: 3.1563 data: 2.9214 max mem: 22446 +eval (validation): [11] [20/63] eta: 0:00:20 time: 0.3532 data: 0.0037 max mem: 22446 +eval (validation): [11] [40/63] eta: 0:00:09 time: 0.3715 data: 0.0038 max mem: 22446 +eval (validation): [11] [60/63] eta: 0:00:01 time: 0.3094 data: 0.0033 max mem: 22446 +eval (validation): [11] [62/63] eta: 0:00:00 time: 0.3090 data: 0.0033 max mem: 22446 +eval (validation): [11] Total time: 0:00:24 (0.3926 s / it) +cv: [11] best hparam: (2.7, 1.0) (030) ('030_lr2.7e+00_wd1.0e+00') loss: 0.026 acc: 0.993 f1: 0.992 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/eval_v2/hcpya_task21__patch__attn/checkpoint-best.pth +train: [12] [ 0/400] eta: 0:22:53 lr: nan time: 3.4327 data: 3.0524 max mem: 22446 +train: [12] [ 20/400] eta: 0:03:43 lr: 0.000164 loss: 0.0871 (0.0862) grad: 0.0622 (0.0654) time: 0.4455 data: 0.0037 max mem: 22446 +train: [12] [ 40/400] eta: 0:03:06 lr: 0.000163 loss: 0.0843 (0.0845) grad: 0.0587 (0.0637) time: 0.4444 data: 0.0039 max mem: 22446 +train: [12] [ 60/400] eta: 0:02:48 lr: 0.000161 loss: 0.0829 (0.0850) grad: 0.0711 (0.0662) time: 0.4527 data: 0.0035 max mem: 22446 +train: [12] [ 80/400] eta: 0:02:34 lr: 0.000160 loss: 0.0907 (0.0864) grad: 0.0729 (0.0704) time: 0.4466 data: 0.0036 max mem: 22446 +train: [12] [100/400] eta: 0:02:23 lr: 0.000158 loss: 0.0915 (0.0876) grad: 0.0767 (0.0697) time: 0.4475 data: 0.0035 max mem: 22446 +train: [12] [120/400] eta: 0:02:12 lr: 0.000156 loss: 0.0964 (0.0916) grad: 0.0771 (0.0715) time: 0.4465 data: 0.0035 max mem: 22446 +train: [12] [140/400] eta: 0:02:01 lr: 0.000155 loss: 0.0900 (0.0912) grad: 0.0699 (0.0698) time: 0.4435 data: 0.0035 max mem: 22446 +train: [12] [160/400] eta: 0:01:51 lr: 0.000153 loss: 0.0793 (0.0903) grad: 0.0506 (0.0679) time: 0.4414 data: 0.0035 max mem: 22446 +train: [12] [180/400] eta: 0:01:41 lr: 0.000152 loss: 0.0793 (0.0897) grad: 0.0474 (0.0659) time: 0.4449 data: 0.0035 max mem: 22446 +train: [12] [200/400] eta: 0:01:32 lr: 0.000150 loss: 0.0752 (0.0887) grad: 0.0469 (0.0657) time: 0.4425 data: 0.0035 max mem: 22446 +train: [12] [220/400] eta: 0:01:22 lr: 0.000149 loss: 0.0772 (0.0892) grad: 0.0669 (0.0654) time: 0.4461 data: 0.0036 max mem: 22446 +train: [12] [240/400] eta: 0:01:13 lr: 0.000147 loss: 0.0875 (0.0896) grad: 0.0588 (0.0653) time: 0.4352 data: 0.0034 max mem: 22446 +train: [12] [260/400] eta: 0:01:04 lr: 0.000145 loss: 0.0819 (0.0888) grad: 0.0648 (0.0647) time: 0.4775 data: 0.0036 max mem: 22446 +train: [12] [280/400] eta: 0:00:54 lr: 0.000144 loss: 0.0764 (0.0884) grad: 0.0648 (0.0647) time: 0.4420 data: 0.0036 max mem: 22446 +train: [12] [300/400] eta: 0:00:46 lr: 0.000142 loss: 0.0870 (0.0887) grad: 0.0657 (0.0648) time: 0.6185 data: 0.1978 max mem: 22446 +train: [12] [320/400] eta: 0:00:37 lr: 0.000141 loss: 0.0834 (0.0882) grad: 0.0553 (0.0642) time: 0.4339 data: 0.0044 max mem: 22446 +train: [12] [340/400] eta: 0:00:27 lr: 0.000139 loss: 0.0766 (0.0879) grad: 0.0455 (0.0636) time: 0.4380 data: 0.0036 max mem: 22446 +train: [12] [360/400] eta: 0:00:18 lr: 0.000138 loss: 0.0780 (0.0875) grad: 0.0461 (0.0638) time: 0.4617 data: 0.0036 max mem: 22446 +train: [12] [380/400] eta: 0:00:09 lr: 0.000136 loss: 0.0731 (0.0874) grad: 0.0472 (0.0634) time: 0.4650 data: 0.0036 max mem: 22446 +train: [12] [399/400] eta: 0:00:00 lr: 0.000134 loss: 0.0766 (0.0871) grad: 0.0542 (0.0632) time: 0.4474 data: 0.0034 max mem: 22446 +train: [12] Total time: 0:03:05 (0.4638 s / it) +train: [12] Summary: lr: 0.000134 loss: 0.0766 (0.0871) grad: 0.0542 (0.0632) +eval (validation): [12] [ 0/63] eta: 0:04:17 time: 4.0925 data: 3.8432 max mem: 22446 +eval (validation): [12] [20/63] eta: 0:00:22 time: 0.3519 data: 0.0033 max mem: 22446 +eval (validation): [12] [40/63] eta: 0:00:10 time: 0.3467 data: 0.0028 max mem: 22446 +eval (validation): [12] [60/63] eta: 0:00:01 time: 0.3121 data: 0.0033 max mem: 22446 +eval (validation): [12] [62/63] eta: 0:00:00 time: 0.3117 data: 0.0032 max mem: 22446 +eval (validation): [12] Total time: 0:00:25 (0.4012 s / it) +cv: [12] best hparam: (4.3, 1.0) (033) ('033_lr4.3e+00_wd1.0e+00') loss: 0.026 acc: 0.993 f1: 0.992 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [13] [ 0/400] eta: 0:22:43 lr: nan time: 3.4084 data: 3.0684 max mem: 22446 +train: [13] [ 20/400] eta: 0:03:36 lr: 0.000133 loss: 0.0841 (0.0805) grad: 0.0390 (0.0471) time: 0.4279 data: 0.0028 max mem: 22446 +train: [13] [ 40/400] eta: 0:03:03 lr: 0.000131 loss: 0.0734 (0.0765) grad: 0.0382 (0.0497) time: 0.4468 data: 0.0036 max mem: 22446 +train: [13] [ 60/400] eta: 0:02:45 lr: 0.000130 loss: 0.0681 (0.0754) grad: 0.0421 (0.0527) time: 0.4414 data: 0.0036 max mem: 22446 +train: [13] [ 80/400] eta: 0:02:33 lr: 0.000128 loss: 0.0743 (0.0761) grad: 0.0421 (0.0527) time: 0.4584 data: 0.0035 max mem: 22446 +train: [13] [100/400] eta: 0:02:21 lr: 0.000127 loss: 0.0737 (0.0771) grad: 0.0418 (0.0537) time: 0.4449 data: 0.0035 max mem: 22446 +train: [13] [120/400] eta: 0:02:11 lr: 0.000125 loss: 0.0691 (0.0769) grad: 0.0418 (0.0526) time: 0.4491 data: 0.0035 max mem: 22446 +train: [13] [140/400] eta: 0:02:01 lr: 0.000124 loss: 0.0682 (0.0766) grad: 0.0415 (0.0521) time: 0.4487 data: 0.0035 max mem: 22446 +train: [13] [160/400] eta: 0:01:51 lr: 0.000122 loss: 0.0709 (0.0764) grad: 0.0462 (0.0519) time: 0.4464 data: 0.0034 max mem: 22446 +train: [13] [180/400] eta: 0:01:41 lr: 0.000120 loss: 0.0788 (0.0773) grad: 0.0404 (0.0521) time: 0.4473 data: 0.0034 max mem: 22446 +train: [13] [200/400] eta: 0:01:32 lr: 0.000119 loss: 0.0788 (0.0780) grad: 0.0404 (0.0516) time: 0.4448 data: 0.0035 max mem: 22446 +train: [13] [220/400] eta: 0:01:22 lr: 0.000117 loss: 0.0733 (0.0783) grad: 0.0450 (0.0527) time: 0.4535 data: 0.0036 max mem: 22446 +train: [13] [240/400] eta: 0:01:13 lr: 0.000116 loss: 0.0775 (0.0780) grad: 0.0472 (0.0526) time: 0.4390 data: 0.0033 max mem: 22446 +train: [13] [260/400] eta: 0:01:04 lr: 0.000114 loss: 0.0767 (0.0783) grad: 0.0412 (0.0530) time: 0.4718 data: 0.0033 max mem: 22446 +train: [13] [280/400] eta: 0:00:54 lr: 0.000113 loss: 0.0683 (0.0776) grad: 0.0428 (0.0527) time: 0.4461 data: 0.0035 max mem: 22446 +train: [13] [300/400] eta: 0:00:46 lr: 0.000111 loss: 0.0683 (0.0776) grad: 0.0507 (0.0533) time: 0.6109 data: 0.1834 max mem: 22446 +train: [13] [320/400] eta: 0:00:37 lr: 0.000110 loss: 0.0786 (0.0777) grad: 0.0452 (0.0526) time: 0.4360 data: 0.0029 max mem: 22446 +train: [13] [340/400] eta: 0:00:27 lr: 0.000108 loss: 0.0711 (0.0773) grad: 0.0396 (0.0525) time: 0.4472 data: 0.0035 max mem: 22446 +train: [13] [360/400] eta: 0:00:18 lr: 0.000107 loss: 0.0594 (0.0769) grad: 0.0402 (0.0520) time: 0.4587 data: 0.0036 max mem: 22446 +train: [13] [380/400] eta: 0:00:09 lr: 0.000105 loss: 0.0677 (0.0768) grad: 0.0413 (0.0519) time: 0.4609 data: 0.0035 max mem: 22446 +train: [13] [399/400] eta: 0:00:00 lr: 0.000104 loss: 0.0788 (0.0769) grad: 0.0413 (0.0516) time: 0.4432 data: 0.0034 max mem: 22446 +train: [13] Total time: 0:03:05 (0.4638 s / it) +train: [13] Summary: lr: 0.000104 loss: 0.0788 (0.0769) grad: 0.0413 (0.0516) +eval (validation): [13] [ 0/63] eta: 0:03:36 time: 3.4374 data: 3.1466 max mem: 22446 +eval (validation): [13] [20/63] eta: 0:00:21 time: 0.3452 data: 0.0035 max mem: 22446 +eval (validation): [13] [40/63] eta: 0:00:09 time: 0.3288 data: 0.0030 max mem: 22446 +eval (validation): [13] [60/63] eta: 0:00:01 time: 0.3141 data: 0.0031 max mem: 22446 +eval (validation): [13] [62/63] eta: 0:00:00 time: 0.3109 data: 0.0031 max mem: 22446 +eval (validation): [13] Total time: 0:00:24 (0.3834 s / it) +cv: [13] best hparam: (3.1, 1.0) (031) ('031_lr3.1e+00_wd1.0e+00') loss: 0.026 acc: 0.993 f1: 0.991 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [14] [ 0/400] eta: 0:23:05 lr: nan time: 3.4645 data: 3.0831 max mem: 22446 +train: [14] [ 20/400] eta: 0:03:38 lr: 0.000102 loss: 0.0717 (0.0748) grad: 0.0379 (0.0374) time: 0.4306 data: 0.0031 max mem: 22446 +train: [14] [ 40/400] eta: 0:03:02 lr: 0.000101 loss: 0.0723 (0.0736) grad: 0.0398 (0.0430) time: 0.4381 data: 0.0036 max mem: 22446 +train: [14] [ 60/400] eta: 0:02:45 lr: 0.000099 loss: 0.0698 (0.0724) grad: 0.0410 (0.0419) time: 0.4448 data: 0.0035 max mem: 22446 +train: [14] [ 80/400] eta: 0:02:32 lr: 0.000098 loss: 0.0661 (0.0721) grad: 0.0396 (0.0426) time: 0.4379 data: 0.0036 max mem: 22446 +train: [14] [100/400] eta: 0:02:20 lr: 0.000096 loss: 0.0669 (0.0723) grad: 0.0398 (0.0418) time: 0.4405 data: 0.0035 max mem: 22446 +train: [14] [120/400] eta: 0:02:09 lr: 0.000095 loss: 0.0708 (0.0738) grad: 0.0387 (0.0415) time: 0.4413 data: 0.0035 max mem: 22446 +train: [14] [140/400] eta: 0:01:59 lr: 0.000093 loss: 0.0768 (0.0750) grad: 0.0386 (0.0422) time: 0.4435 data: 0.0034 max mem: 22446 +train: [14] [160/400] eta: 0:01:50 lr: 0.000092 loss: 0.0657 (0.0738) grad: 0.0386 (0.0422) time: 0.4402 data: 0.0035 max mem: 22446 +train: [14] [180/400] eta: 0:01:40 lr: 0.000090 loss: 0.0662 (0.0729) grad: 0.0369 (0.0418) time: 0.4375 data: 0.0035 max mem: 22446 +train: [14] [200/400] eta: 0:01:31 lr: 0.000089 loss: 0.0668 (0.0733) grad: 0.0384 (0.0422) time: 0.4464 data: 0.0035 max mem: 22446 +train: [14] [220/400] eta: 0:01:21 lr: 0.000088 loss: 0.0681 (0.0729) grad: 0.0416 (0.0424) time: 0.4443 data: 0.0034 max mem: 22446 +train: [14] [240/400] eta: 0:01:12 lr: 0.000086 loss: 0.0668 (0.0724) grad: 0.0372 (0.0423) time: 0.4327 data: 0.0034 max mem: 22446 +train: [14] [260/400] eta: 0:01:03 lr: 0.000085 loss: 0.0635 (0.0718) grad: 0.0395 (0.0423) time: 0.4864 data: 0.0035 max mem: 22446 +train: [14] [280/400] eta: 0:00:54 lr: 0.000083 loss: 0.0755 (0.0728) grad: 0.0429 (0.0428) time: 0.4526 data: 0.0036 max mem: 22446 +train: [14] [300/400] eta: 0:00:46 lr: 0.000082 loss: 0.0761 (0.0727) grad: 0.0425 (0.0427) time: 0.6321 data: 0.2068 max mem: 22446 +train: [14] [320/400] eta: 0:00:37 lr: 0.000081 loss: 0.0669 (0.0725) grad: 0.0371 (0.0425) time: 0.4454 data: 0.0030 max mem: 22446 +train: [14] [340/400] eta: 0:00:27 lr: 0.000079 loss: 0.0726 (0.0730) grad: 0.0366 (0.0422) time: 0.4461 data: 0.0032 max mem: 22446 +train: [14] [360/400] eta: 0:00:18 lr: 0.000078 loss: 0.0776 (0.0732) grad: 0.0394 (0.0423) time: 0.4577 data: 0.0034 max mem: 22446 +train: [14] [380/400] eta: 0:00:09 lr: 0.000076 loss: 0.0746 (0.0732) grad: 0.0431 (0.0424) time: 0.4587 data: 0.0036 max mem: 22446 +train: [14] [399/400] eta: 0:00:00 lr: 0.000075 loss: 0.0667 (0.0730) grad: 0.0393 (0.0422) time: 0.4403 data: 0.0034 max mem: 22446 +train: [14] Total time: 0:03:05 (0.4627 s / it) +train: [14] Summary: lr: 0.000075 loss: 0.0667 (0.0730) grad: 0.0393 (0.0422) +eval (validation): [14] [ 0/63] eta: 0:03:29 time: 3.3247 data: 3.0416 max mem: 22446 +eval (validation): [14] [20/63] eta: 0:00:21 time: 0.3695 data: 0.0044 max mem: 22446 +eval (validation): [14] [40/63] eta: 0:00:09 time: 0.3353 data: 0.0032 max mem: 22446 +eval (validation): [14] [60/63] eta: 0:00:01 time: 0.3145 data: 0.0032 max mem: 22446 +eval (validation): [14] [62/63] eta: 0:00:00 time: 0.3115 data: 0.0033 max mem: 22446 +eval (validation): [14] Total time: 0:00:24 (0.3910 s / it) +cv: [14] best hparam: (3.1, 1.0) (031) ('031_lr3.1e+00_wd1.0e+00') loss: 0.026 acc: 0.993 f1: 0.991 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [15] [ 0/400] eta: 0:23:05 lr: nan time: 3.4630 data: 3.1264 max mem: 22446 +train: [15] [ 20/400] eta: 0:03:42 lr: 0.000074 loss: 0.0668 (0.0744) grad: 0.0356 (0.0402) time: 0.4413 data: 0.0030 max mem: 22446 +train: [15] [ 40/400] eta: 0:03:04 lr: 0.000072 loss: 0.0697 (0.0741) grad: 0.0402 (0.0413) time: 0.4387 data: 0.0035 max mem: 22446 +train: [15] [ 60/400] eta: 0:02:46 lr: 0.000071 loss: 0.0643 (0.0693) grad: 0.0390 (0.0397) time: 0.4407 data: 0.0035 max mem: 22446 +train: [15] [ 80/400] eta: 0:02:33 lr: 0.000070 loss: 0.0614 (0.0685) grad: 0.0357 (0.0392) time: 0.4430 data: 0.0035 max mem: 22446 +train: [15] [100/400] eta: 0:02:21 lr: 0.000068 loss: 0.0614 (0.0679) grad: 0.0343 (0.0396) time: 0.4465 data: 0.0036 max mem: 22446 +train: [15] [120/400] eta: 0:02:10 lr: 0.000067 loss: 0.0587 (0.0675) grad: 0.0365 (0.0392) time: 0.4436 data: 0.0036 max mem: 22446 +train: [15] [140/400] eta: 0:02:00 lr: 0.000066 loss: 0.0615 (0.0674) grad: 0.0370 (0.0389) time: 0.4467 data: 0.0036 max mem: 22446 +train: [15] [160/400] eta: 0:01:50 lr: 0.000064 loss: 0.0615 (0.0669) grad: 0.0378 (0.0391) time: 0.4361 data: 0.0036 max mem: 22446 +train: [15] [180/400] eta: 0:01:40 lr: 0.000063 loss: 0.0602 (0.0675) grad: 0.0394 (0.0395) time: 0.4415 data: 0.0036 max mem: 22446 +train: [15] [200/400] eta: 0:01:31 lr: 0.000062 loss: 0.0751 (0.0682) grad: 0.0369 (0.0395) time: 0.4481 data: 0.0035 max mem: 22446 +train: [15] [220/400] eta: 0:01:22 lr: 0.000061 loss: 0.0683 (0.0676) grad: 0.0372 (0.0395) time: 0.4413 data: 0.0035 max mem: 22446 +train: [15] [240/400] eta: 0:01:12 lr: 0.000059 loss: 0.0638 (0.0674) grad: 0.0385 (0.0396) time: 0.4304 data: 0.0035 max mem: 22446 +train: [15] [260/400] eta: 0:01:03 lr: 0.000058 loss: 0.0626 (0.0676) grad: 0.0369 (0.0393) time: 0.4622 data: 0.0035 max mem: 22446 +train: [15] [280/400] eta: 0:00:54 lr: 0.000057 loss: 0.0622 (0.0676) grad: 0.0354 (0.0392) time: 0.4403 data: 0.0036 max mem: 22446 +train: [15] [300/400] eta: 0:00:46 lr: 0.000056 loss: 0.0622 (0.0677) grad: 0.0351 (0.0392) time: 0.6020 data: 0.1792 max mem: 22446 +train: [15] [320/400] eta: 0:00:37 lr: 0.000054 loss: 0.0625 (0.0674) grad: 0.0379 (0.0393) time: 0.4548 data: 0.0035 max mem: 22446 +train: [15] [340/400] eta: 0:00:27 lr: 0.000053 loss: 0.0625 (0.0678) grad: 0.0413 (0.0395) time: 0.4419 data: 0.0035 max mem: 22446 +train: [15] [360/400] eta: 0:00:18 lr: 0.000052 loss: 0.0615 (0.0678) grad: 0.0394 (0.0395) time: 0.4551 data: 0.0035 max mem: 22446 +train: [15] [380/400] eta: 0:00:09 lr: 0.000051 loss: 0.0570 (0.0674) grad: 0.0369 (0.0393) time: 0.4683 data: 0.0035 max mem: 22446 +train: [15] [399/400] eta: 0:00:00 lr: 0.000050 loss: 0.0645 (0.0677) grad: 0.0345 (0.0391) time: 0.4460 data: 0.0035 max mem: 22446 +train: [15] Total time: 0:03:04 (0.4613 s / it) +train: [15] Summary: lr: 0.000050 loss: 0.0645 (0.0677) grad: 0.0345 (0.0391) +eval (validation): [15] [ 0/63] eta: 0:03:31 time: 3.3498 data: 3.0527 max mem: 22446 +eval (validation): [15] [20/63] eta: 0:00:24 time: 0.4195 data: 0.0051 max mem: 22446 +eval (validation): [15] [40/63] eta: 0:00:10 time: 0.3440 data: 0.0035 max mem: 22446 +eval (validation): [15] [60/63] eta: 0:00:01 time: 0.3187 data: 0.0033 max mem: 22446 +eval (validation): [15] [62/63] eta: 0:00:00 time: 0.3164 data: 0.0033 max mem: 22446 +eval (validation): [15] Total time: 0:00:25 (0.4109 s / it) +cv: [15] best hparam: (1.2, 1.0) (025) ('025_lr1.2e+00_wd1.0e+00') loss: 0.024 acc: 0.993 f1: 0.992 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [16] [ 0/400] eta: 0:24:32 lr: nan time: 3.6805 data: 3.3439 max mem: 22446 +train: [16] [ 20/400] eta: 0:03:49 lr: 0.000048 loss: 0.0675 (0.0687) grad: 0.0360 (0.0383) time: 0.4499 data: 0.0025 max mem: 22446 +train: [16] [ 40/400] eta: 0:03:08 lr: 0.000047 loss: 0.0657 (0.0677) grad: 0.0365 (0.0382) time: 0.4415 data: 0.0034 max mem: 22446 +train: [16] [ 60/400] eta: 0:02:50 lr: 0.000046 loss: 0.0626 (0.0664) grad: 0.0330 (0.0368) time: 0.4506 data: 0.0034 max mem: 22446 +train: [16] [ 80/400] eta: 0:02:35 lr: 0.000045 loss: 0.0648 (0.0670) grad: 0.0330 (0.0366) time: 0.4429 data: 0.0034 max mem: 22446 +train: [16] [100/400] eta: 0:02:23 lr: 0.000044 loss: 0.0664 (0.0674) grad: 0.0357 (0.0368) time: 0.4419 data: 0.0035 max mem: 22446 +train: [16] [120/400] eta: 0:02:11 lr: 0.000043 loss: 0.0628 (0.0672) grad: 0.0375 (0.0378) time: 0.4390 data: 0.0036 max mem: 22446 +train: [16] [140/400] eta: 0:02:01 lr: 0.000042 loss: 0.0612 (0.0672) grad: 0.0397 (0.0380) time: 0.4434 data: 0.0035 max mem: 22446 +train: [16] [160/400] eta: 0:01:51 lr: 0.000041 loss: 0.0612 (0.0673) grad: 0.0382 (0.0381) time: 0.4505 data: 0.0034 max mem: 22446 +train: [16] [180/400] eta: 0:01:42 lr: 0.000040 loss: 0.0673 (0.0675) grad: 0.0375 (0.0379) time: 0.4529 data: 0.0038 max mem: 22446 +train: [16] [200/400] eta: 0:01:32 lr: 0.000039 loss: 0.0678 (0.0681) grad: 0.0394 (0.0384) time: 0.4490 data: 0.0038 max mem: 22446 +train: [16] [220/400] eta: 0:01:22 lr: 0.000038 loss: 0.0642 (0.0678) grad: 0.0364 (0.0381) time: 0.4414 data: 0.0034 max mem: 22446 +train: [16] [240/400] eta: 0:01:13 lr: 0.000036 loss: 0.0607 (0.0674) grad: 0.0336 (0.0377) time: 0.4401 data: 0.0034 max mem: 22446 +train: [16] [260/400] eta: 0:01:04 lr: 0.000035 loss: 0.0631 (0.0678) grad: 0.0346 (0.0378) time: 0.4825 data: 0.0035 max mem: 22446 +train: [16] [280/400] eta: 0:00:55 lr: 0.000034 loss: 0.0658 (0.0676) grad: 0.0386 (0.0383) time: 0.4381 data: 0.0035 max mem: 22446 +train: [16] [300/400] eta: 0:00:46 lr: 0.000033 loss: 0.0625 (0.0676) grad: 0.0406 (0.0385) time: 0.6254 data: 0.1898 max mem: 22446 +train: [16] [320/400] eta: 0:00:37 lr: 0.000032 loss: 0.0663 (0.0676) grad: 0.0379 (0.0385) time: 0.4397 data: 0.0030 max mem: 22446 +train: [16] [340/400] eta: 0:00:28 lr: 0.000031 loss: 0.0693 (0.0681) grad: 0.0357 (0.0387) time: 0.4466 data: 0.0036 max mem: 22446 +train: [16] [360/400] eta: 0:00:18 lr: 0.000031 loss: 0.0701 (0.0680) grad: 0.0348 (0.0385) time: 0.4576 data: 0.0036 max mem: 22446 +train: [16] [380/400] eta: 0:00:09 lr: 0.000030 loss: 0.0592 (0.0675) grad: 0.0345 (0.0384) time: 0.4638 data: 0.0037 max mem: 22446 +train: [16] [399/400] eta: 0:00:00 lr: 0.000029 loss: 0.0576 (0.0675) grad: 0.0389 (0.0386) time: 0.4491 data: 0.0034 max mem: 22446 +train: [16] Total time: 0:03:06 (0.4657 s / it) +train: [16] Summary: lr: 0.000029 loss: 0.0576 (0.0675) grad: 0.0389 (0.0386) +eval (validation): [16] [ 0/63] eta: 0:03:30 time: 3.3401 data: 3.0824 max mem: 22446 +eval (validation): [16] [20/63] eta: 0:00:21 time: 0.3563 data: 0.0041 max mem: 22446 +eval (validation): [16] [40/63] eta: 0:00:09 time: 0.3271 data: 0.0029 max mem: 22446 +eval (validation): [16] [60/63] eta: 0:00:01 time: 0.3228 data: 0.0033 max mem: 22446 +eval (validation): [16] [62/63] eta: 0:00:00 time: 0.3271 data: 0.0033 max mem: 22446 +eval (validation): [16] Total time: 0:00:24 (0.3884 s / it) +cv: [16] best hparam: (1.6, 1.0) (027) ('027_lr1.6e+00_wd1.0e+00') loss: 0.025 acc: 0.993 f1: 0.992 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [17] [ 0/400] eta: 0:23:04 lr: nan time: 3.4611 data: 3.0761 max mem: 22446 +train: [17] [ 20/400] eta: 0:03:43 lr: 0.000028 loss: 0.0581 (0.0634) grad: 0.0362 (0.0377) time: 0.4458 data: 0.0032 max mem: 22446 +train: [17] [ 40/400] eta: 0:03:06 lr: 0.000027 loss: 0.0650 (0.0670) grad: 0.0367 (0.0389) time: 0.4449 data: 0.0038 max mem: 22446 +train: [17] [ 60/400] eta: 0:02:48 lr: 0.000026 loss: 0.0696 (0.0700) grad: 0.0387 (0.0385) time: 0.4501 data: 0.0037 max mem: 22446 +train: [17] [ 80/400] eta: 0:02:34 lr: 0.000025 loss: 0.0738 (0.0709) grad: 0.0375 (0.0382) time: 0.4408 data: 0.0035 max mem: 22446 +train: [17] [100/400] eta: 0:02:22 lr: 0.000024 loss: 0.0676 (0.0696) grad: 0.0349 (0.0378) time: 0.4407 data: 0.0036 max mem: 22446 +train: [17] [120/400] eta: 0:02:11 lr: 0.000023 loss: 0.0629 (0.0691) grad: 0.0349 (0.0375) time: 0.4446 data: 0.0036 max mem: 22446 +train: [17] [140/400] eta: 0:02:01 lr: 0.000023 loss: 0.0617 (0.0688) grad: 0.0351 (0.0378) time: 0.4445 data: 0.0035 max mem: 22446 +train: [17] [160/400] eta: 0:01:51 lr: 0.000022 loss: 0.0669 (0.0684) grad: 0.0360 (0.0379) time: 0.4489 data: 0.0035 max mem: 22446 +train: [17] [180/400] eta: 0:01:41 lr: 0.000021 loss: 0.0612 (0.0677) grad: 0.0364 (0.0378) time: 0.4426 data: 0.0034 max mem: 22446 +train: [17] [200/400] eta: 0:01:32 lr: 0.000020 loss: 0.0574 (0.0674) grad: 0.0347 (0.0377) time: 0.4521 data: 0.0034 max mem: 22446 +train: [17] [220/400] eta: 0:01:22 lr: 0.000019 loss: 0.0588 (0.0674) grad: 0.0347 (0.0376) time: 0.4517 data: 0.0035 max mem: 22446 +train: [17] [240/400] eta: 0:01:13 lr: 0.000019 loss: 0.0620 (0.0672) grad: 0.0338 (0.0376) time: 0.4437 data: 0.0033 max mem: 22446 +train: [17] [260/400] eta: 0:01:04 lr: 0.000018 loss: 0.0620 (0.0674) grad: 0.0379 (0.0376) time: 0.4649 data: 0.0035 max mem: 22446 +train: [17] [280/400] eta: 0:00:54 lr: 0.000017 loss: 0.0641 (0.0672) grad: 0.0334 (0.0372) time: 0.4365 data: 0.0036 max mem: 22446 +train: [17] [300/400] eta: 0:00:47 lr: 0.000016 loss: 0.0617 (0.0672) grad: 0.0334 (0.0374) time: 0.6590 data: 0.2131 max mem: 22446 +train: [17] [320/400] eta: 0:00:37 lr: 0.000016 loss: 0.0621 (0.0671) grad: 0.0400 (0.0376) time: 0.4347 data: 0.0030 max mem: 22446 +train: [17] [340/400] eta: 0:00:28 lr: 0.000015 loss: 0.0587 (0.0669) grad: 0.0341 (0.0373) time: 0.4437 data: 0.0036 max mem: 22446 +train: [17] [360/400] eta: 0:00:18 lr: 0.000014 loss: 0.0587 (0.0666) grad: 0.0321 (0.0372) time: 0.4708 data: 0.0036 max mem: 22446 +train: [17] [380/400] eta: 0:00:09 lr: 0.000014 loss: 0.0606 (0.0668) grad: 0.0354 (0.0371) time: 0.4702 data: 0.0037 max mem: 22446 +train: [17] [399/400] eta: 0:00:00 lr: 0.000013 loss: 0.0577 (0.0666) grad: 0.0359 (0.0371) time: 0.4454 data: 0.0035 max mem: 22446 +train: [17] Total time: 0:03:06 (0.4665 s / it) +train: [17] Summary: lr: 0.000013 loss: 0.0577 (0.0666) grad: 0.0359 (0.0371) +eval (validation): [17] [ 0/63] eta: 0:03:30 time: 3.3359 data: 3.0520 max mem: 22446 +eval (validation): [17] [20/63] eta: 0:00:21 time: 0.3528 data: 0.0039 max mem: 22446 +eval (validation): [17] [40/63] eta: 0:00:09 time: 0.3412 data: 0.0038 max mem: 22446 +eval (validation): [17] [60/63] eta: 0:00:01 time: 0.3246 data: 0.0022 max mem: 22446 +eval (validation): [17] [62/63] eta: 0:00:00 time: 0.3286 data: 0.0025 max mem: 22446 +eval (validation): [17] Total time: 0:00:24 (0.3915 s / it) +cv: [17] best hparam: (6, 1.0) (035) ('035_lr6.0e+00_wd1.0e+00') loss: 0.035 acc: 0.993 f1: 0.992 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [18] [ 0/400] eta: 0:25:13 lr: nan time: 3.7840 data: 3.3909 max mem: 22446 +train: [18] [ 20/400] eta: 0:03:47 lr: 0.000012 loss: 0.0606 (0.0642) grad: 0.0323 (0.0358) time: 0.4403 data: 0.0024 max mem: 22446 +train: [18] [ 40/400] eta: 0:03:08 lr: 0.000012 loss: 0.0629 (0.0670) grad: 0.0355 (0.0367) time: 0.4418 data: 0.0034 max mem: 22446 +train: [18] [ 60/400] eta: 0:02:48 lr: 0.000011 loss: 0.0588 (0.0669) grad: 0.0373 (0.0372) time: 0.4402 data: 0.0035 max mem: 22446 +train: [18] [ 80/400] eta: 0:02:34 lr: 0.000011 loss: 0.0669 (0.0681) grad: 0.0363 (0.0371) time: 0.4420 data: 0.0036 max mem: 22446 +train: [18] [100/400] eta: 0:02:22 lr: 0.000010 loss: 0.0619 (0.0678) grad: 0.0378 (0.0373) time: 0.4454 data: 0.0035 max mem: 22446 +train: [18] [120/400] eta: 0:02:11 lr: 0.000009 loss: 0.0589 (0.0658) grad: 0.0372 (0.0372) time: 0.4443 data: 0.0036 max mem: 22446 +train: [18] [140/400] eta: 0:02:01 lr: 0.000009 loss: 0.0633 (0.0668) grad: 0.0349 (0.0373) time: 0.4449 data: 0.0036 max mem: 22446 +train: [18] [160/400] eta: 0:01:51 lr: 0.000008 loss: 0.0721 (0.0664) grad: 0.0367 (0.0374) time: 0.4392 data: 0.0035 max mem: 22446 +train: [18] [180/400] eta: 0:01:41 lr: 0.000008 loss: 0.0589 (0.0656) grad: 0.0372 (0.0377) time: 0.4384 data: 0.0036 max mem: 22446 +train: [18] [200/400] eta: 0:01:31 lr: 0.000007 loss: 0.0608 (0.0655) grad: 0.0367 (0.0377) time: 0.4451 data: 0.0036 max mem: 22446 +train: [18] [220/400] eta: 0:01:22 lr: 0.000007 loss: 0.0617 (0.0652) grad: 0.0349 (0.0375) time: 0.4364 data: 0.0035 max mem: 22446 +train: [18] [240/400] eta: 0:01:12 lr: 0.000006 loss: 0.0598 (0.0648) grad: 0.0357 (0.0375) time: 0.4407 data: 0.0035 max mem: 22446 +train: [18] [260/400] eta: 0:01:03 lr: 0.000006 loss: 0.0598 (0.0650) grad: 0.0345 (0.0372) time: 0.4776 data: 0.0036 max mem: 22446 +train: [18] [280/400] eta: 0:00:54 lr: 0.000006 loss: 0.0616 (0.0649) grad: 0.0374 (0.0374) time: 0.4522 data: 0.0035 max mem: 22446 +train: [18] [300/400] eta: 0:00:46 lr: 0.000005 loss: 0.0580 (0.0645) grad: 0.0382 (0.0375) time: 0.6182 data: 0.1791 max mem: 22446 +train: [18] [320/400] eta: 0:00:37 lr: 0.000005 loss: 0.0578 (0.0646) grad: 0.0385 (0.0375) time: 0.4556 data: 0.0039 max mem: 22446 +train: [18] [340/400] eta: 0:00:27 lr: 0.000004 loss: 0.0636 (0.0649) grad: 0.0369 (0.0375) time: 0.4538 data: 0.0032 max mem: 22446 +train: [18] [360/400] eta: 0:00:18 lr: 0.000004 loss: 0.0626 (0.0646) grad: 0.0348 (0.0376) time: 0.4662 data: 0.0037 max mem: 22446 +train: [18] [380/400] eta: 0:00:09 lr: 0.000004 loss: 0.0598 (0.0641) grad: 0.0343 (0.0374) time: 0.4651 data: 0.0036 max mem: 22446 +train: [18] [399/400] eta: 0:00:00 lr: 0.000003 loss: 0.0545 (0.0639) grad: 0.0346 (0.0373) time: 0.4433 data: 0.0034 max mem: 22446 +train: [18] Total time: 0:03:06 (0.4652 s / it) +train: [18] Summary: lr: 0.000003 loss: 0.0545 (0.0639) grad: 0.0346 (0.0373) +eval (validation): [18] [ 0/63] eta: 0:03:29 time: 3.3308 data: 3.0793 max mem: 22446 +eval (validation): [18] [20/63] eta: 0:00:22 time: 0.3719 data: 0.0035 max mem: 22446 +eval (validation): [18] [40/63] eta: 0:00:09 time: 0.3312 data: 0.0036 max mem: 22446 +eval (validation): [18] [60/63] eta: 0:00:01 time: 0.3250 data: 0.0032 max mem: 22446 +eval (validation): [18] [62/63] eta: 0:00:00 time: 0.3259 data: 0.0032 max mem: 22446 +eval (validation): [18] Total time: 0:00:24 (0.3944 s / it) +cv: [18] best hparam: (1.6, 1.0) (027) ('027_lr1.6e+00_wd1.0e+00') loss: 0.025 acc: 0.993 f1: 0.991 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [19] [ 0/400] eta: 0:23:14 lr: nan time: 3.4852 data: 3.1043 max mem: 22446 +train: [19] [ 20/400] eta: 0:03:44 lr: 0.000003 loss: 0.0653 (0.0630) grad: 0.0347 (0.0347) time: 0.4463 data: 0.0026 max mem: 22446 +train: [19] [ 40/400] eta: 0:03:07 lr: 0.000003 loss: 0.0615 (0.0621) grad: 0.0351 (0.0357) time: 0.4463 data: 0.0034 max mem: 22446 +train: [19] [ 60/400] eta: 0:02:49 lr: 0.000002 loss: 0.0611 (0.0616) grad: 0.0348 (0.0353) time: 0.4533 data: 0.0036 max mem: 22446 +train: [19] [ 80/400] eta: 0:02:35 lr: 0.000002 loss: 0.0611 (0.0632) grad: 0.0349 (0.0364) time: 0.4490 data: 0.0035 max mem: 22446 +train: [19] [100/400] eta: 0:02:23 lr: 0.000002 loss: 0.0645 (0.0652) grad: 0.0372 (0.0366) time: 0.4438 data: 0.0035 max mem: 22446 +train: [19] [120/400] eta: 0:02:12 lr: 0.000002 loss: 0.0645 (0.0647) grad: 0.0369 (0.0364) time: 0.4403 data: 0.0036 max mem: 22446 +train: [19] [140/400] eta: 0:02:01 lr: 0.000001 loss: 0.0598 (0.0638) grad: 0.0330 (0.0363) time: 0.4457 data: 0.0036 max mem: 22446 +train: [19] [160/400] eta: 0:01:51 lr: 0.000001 loss: 0.0598 (0.0639) grad: 0.0322 (0.0361) time: 0.4425 data: 0.0035 max mem: 22446 +train: [19] [180/400] eta: 0:01:41 lr: 0.000001 loss: 0.0648 (0.0642) grad: 0.0336 (0.0362) time: 0.4419 data: 0.0035 max mem: 22446 +train: [19] [200/400] eta: 0:01:32 lr: 0.000001 loss: 0.0629 (0.0645) grad: 0.0355 (0.0362) time: 0.4426 data: 0.0033 max mem: 22446 +train: [19] [220/400] eta: 0:01:22 lr: 0.000001 loss: 0.0676 (0.0653) grad: 0.0355 (0.0364) time: 0.4397 data: 0.0035 max mem: 22446 +train: [19] [240/400] eta: 0:01:13 lr: 0.000001 loss: 0.0672 (0.0650) grad: 0.0355 (0.0363) time: 0.4350 data: 0.0035 max mem: 22446 +train: [19] [260/400] eta: 0:01:04 lr: 0.000000 loss: 0.0599 (0.0648) grad: 0.0337 (0.0362) time: 0.4770 data: 0.0036 max mem: 22446 +train: [19] [280/400] eta: 0:00:54 lr: 0.000000 loss: 0.0635 (0.0653) grad: 0.0345 (0.0364) time: 0.4398 data: 0.0035 max mem: 22446 +train: [19] [300/400] eta: 0:00:46 lr: 0.000000 loss: 0.0634 (0.0651) grad: 0.0389 (0.0365) time: 0.6354 data: 0.1820 max mem: 22446 +train: [19] [320/400] eta: 0:00:37 lr: 0.000000 loss: 0.0612 (0.0649) grad: 0.0387 (0.0367) time: 0.4348 data: 0.0034 max mem: 22446 +train: [19] [340/400] eta: 0:00:27 lr: 0.000000 loss: 0.0565 (0.0645) grad: 0.0374 (0.0367) time: 0.4422 data: 0.0035 max mem: 22446 +train: [19] [360/400] eta: 0:00:18 lr: 0.000000 loss: 0.0598 (0.0646) grad: 0.0369 (0.0368) time: 0.4622 data: 0.0035 max mem: 22446 +train: [19] [380/400] eta: 0:00:09 lr: 0.000000 loss: 0.0584 (0.0644) grad: 0.0369 (0.0368) time: 0.4709 data: 0.0036 max mem: 22446 +train: [19] [399/400] eta: 0:00:00 lr: 0.000000 loss: 0.0581 (0.0642) grad: 0.0345 (0.0369) time: 0.4519 data: 0.0033 max mem: 22446 +train: [19] Total time: 0:03:05 (0.4648 s / it) +train: [19] Summary: lr: 0.000000 loss: 0.0581 (0.0642) grad: 0.0345 (0.0369) +eval (validation): [19] [ 0/63] eta: 0:03:31 time: 3.3630 data: 3.0760 max mem: 22446 +eval (validation): [19] [20/63] eta: 0:00:23 time: 0.3987 data: 0.0049 max mem: 22446 +eval (validation): [19] [40/63] eta: 0:00:10 time: 0.3304 data: 0.0034 max mem: 22446 +eval (validation): [19] [60/63] eta: 0:00:01 time: 0.3290 data: 0.0031 max mem: 22446 +eval (validation): [19] [62/63] eta: 0:00:00 time: 0.3321 data: 0.0031 max mem: 22446 +eval (validation): [19] Total time: 0:00:25 (0.4054 s / it) +cv: [19] best hparam: (6, 1.0) (035) ('035_lr6.0e+00_wd1.0e+00') loss: 0.035 acc: 0.993 f1: 0.992 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +evaluating last checkpoint: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +eval model info: +{"score": 0.9928075396825397, "hparam": [6, 1.0], "hparam_id": 35, "epoch": 19, "is_best": false, "best_score": 0.9933035714285714} +eval (train): [20] [ 0/297] eta: 0:15:23 time: 3.1079 data: 2.8691 max mem: 22446 +eval (train): [20] [ 20/297] eta: 0:02:12 time: 0.3467 data: 0.0031 max mem: 22446 +eval (train): [20] [ 40/297] eta: 0:01:46 time: 0.3485 data: 0.0033 max mem: 22446 +eval (train): [20] [ 60/297] eta: 0:01:34 time: 0.3665 data: 0.0039 max mem: 22446 +eval (train): [20] [ 80/297] eta: 0:01:23 time: 0.3493 data: 0.0034 max mem: 22446 +eval (train): [20] [100/297] eta: 0:01:15 time: 0.3694 data: 0.0036 max mem: 22446 +eval (train): [20] [120/297] eta: 0:01:07 time: 0.3766 data: 0.0039 max mem: 22446 +eval (train): [20] [140/297] eta: 0:00:59 time: 0.3634 data: 0.0036 max mem: 22446 +eval (train): [20] [160/297] eta: 0:00:51 time: 0.3580 data: 0.0036 max mem: 22446 +eval (train): [20] [180/297] eta: 0:00:44 time: 0.4118 data: 0.0037 max mem: 22446 +eval (train): [20] [200/297] eta: 0:00:36 time: 0.3588 data: 0.0039 max mem: 22446 +eval (train): [20] [220/297] eta: 0:00:28 time: 0.3476 data: 0.0034 max mem: 22446 +eval (train): [20] [240/297] eta: 0:00:21 time: 0.3769 data: 0.0036 max mem: 22446 +eval (train): [20] [260/297] eta: 0:00:13 time: 0.3691 data: 0.0033 max mem: 22446 +eval (train): [20] [280/297] eta: 0:00:06 time: 0.3519 data: 0.0035 max mem: 22446 +eval (train): [20] [296/297] eta: 0:00:00 time: 0.3222 data: 0.0030 max mem: 22446 +eval (train): [20] Total time: 0:01:50 (0.3727 s / it) +eval (validation): [20] [ 0/63] eta: 0:03:26 time: 3.2835 data: 2.9918 max mem: 22446 +eval (validation): [20] [20/63] eta: 0:00:21 time: 0.3538 data: 0.0036 max mem: 22446 +eval (validation): [20] [40/63] eta: 0:00:10 time: 0.3806 data: 0.0044 max mem: 22446 +eval (validation): [20] [60/63] eta: 0:00:01 time: 0.3427 data: 0.0021 max mem: 22446 +eval (validation): [20] [62/63] eta: 0:00:00 time: 0.3423 data: 0.0022 max mem: 22446 +eval (validation): [20] Total time: 0:00:25 (0.4089 s / it) +eval (test): [20] [ 0/79] eta: 0:03:52 time: 2.9441 data: 2.7174 max mem: 22446 +eval (test): [20] [20/79] eta: 0:00:27 time: 0.3406 data: 0.0033 max mem: 22446 +eval (test): [20] [40/79] eta: 0:00:16 time: 0.3805 data: 0.0029 max mem: 22446 +eval (test): [20] [60/79] eta: 0:00:07 time: 0.3747 data: 0.0037 max mem: 22446 +eval (test): [20] [78/79] eta: 0:00:00 time: 0.3329 data: 0.0032 max mem: 22446 +eval (test): [20] Total time: 0:00:31 (0.3945 s / it) +evaluating best checkpoint: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/eval_v2/hcpya_task21__patch__attn/checkpoint-best.pth +eval model info: +{"score": 0.9933035714285714, "hparam": [2.7, 1.0], "hparam_id": 30, "epoch": 11, "is_best": true, "best_score": 0.9933035714285714} +eval (train): [20] [ 0/297] eta: 0:16:07 time: 3.2567 data: 3.0019 max mem: 22446 +eval (train): [20] [ 20/297] eta: 0:02:15 time: 0.3503 data: 0.0033 max mem: 22446 +eval (train): [20] [ 40/297] eta: 0:01:49 time: 0.3593 data: 0.0041 max mem: 22446 +eval (train): [20] [ 60/297] eta: 0:01:36 time: 0.3740 data: 0.0031 max mem: 22446 +eval (train): [20] [ 80/297] eta: 0:01:26 time: 0.3599 data: 0.0035 max mem: 22446 +eval (train): [20] [100/297] eta: 0:01:17 time: 0.3729 data: 0.0040 max mem: 22446 +eval (train): [20] [120/297] eta: 0:01:08 time: 0.3659 data: 0.0036 max mem: 22446 +eval (train): [20] [140/297] eta: 0:01:00 time: 0.3901 data: 0.0039 max mem: 22446 +eval (train): [20] [160/297] eta: 0:00:53 time: 0.3962 data: 0.0035 max mem: 22446 +eval (train): [20] [180/297] eta: 0:00:45 time: 0.3496 data: 0.0037 max mem: 22446 +eval (train): [20] [200/297] eta: 0:00:37 time: 0.3532 data: 0.0034 max mem: 22446 +eval (train): [20] [220/297] eta: 0:00:29 time: 0.3479 data: 0.0035 max mem: 22446 +eval (train): [20] [240/297] eta: 0:00:21 time: 0.3366 data: 0.0033 max mem: 22446 +eval (train): [20] [260/297] eta: 0:00:13 time: 0.3990 data: 0.0036 max mem: 22446 +eval (train): [20] [280/297] eta: 0:00:06 time: 0.3729 data: 0.0036 max mem: 22446 +eval (train): [20] [296/297] eta: 0:00:00 time: 0.3316 data: 0.0031 max mem: 22446 +eval (train): [20] Total time: 0:01:51 (0.3756 s / it) +eval (validation): [20] [ 0/63] eta: 0:03:09 time: 3.0116 data: 2.7599 max mem: 22446 +eval (validation): [20] [20/63] eta: 0:00:22 time: 0.4028 data: 0.0178 max mem: 22446 +eval (validation): [20] [40/63] eta: 0:00:10 time: 0.3848 data: 0.0036 max mem: 22446 +eval (validation): [20] [60/63] eta: 0:00:01 time: 0.3477 data: 0.0036 max mem: 22446 +eval (validation): [20] [62/63] eta: 0:00:00 time: 0.3469 data: 0.0035 max mem: 22446 +eval (validation): [20] Total time: 0:00:26 (0.4231 s / it) +eval (test): [20] [ 0/79] eta: 0:03:54 time: 2.9713 data: 2.7422 max mem: 22446 +eval (test): [20] [20/79] eta: 0:00:27 time: 0.3479 data: 0.0034 max mem: 22446 +eval (test): [20] [40/79] eta: 0:00:16 time: 0.3460 data: 0.0029 max mem: 22446 +eval (test): [20] [60/79] eta: 0:00:07 time: 0.3495 data: 0.0032 max mem: 22446 +eval (test): [20] [78/79] eta: 0:00:00 time: 0.3330 data: 0.0031 max mem: 22446 +eval (test): [20] Total time: 0:00:30 (0.3798 s / it) +eval results: + +| model | repr | clf | dataset | ckpt | epoch | lr | wd | hparam_id | hparam | split | loss | acc | acc_std | f1 | f1_std | +|:---------|:-------|:------|:-------------|:-------|--------:|--------:|-----:|------------:|:-----------|:-----------|-----------:|--------:|----------:|--------:|----------:| +| flat_mae | patch | attn | hcpya_task21 | best | 11 | 0.00081 | 0.05 | 30 | [2.7, 1.0] | train | 0.00045598 | 1 | 0 | 1 | 0 | +| flat_mae | patch | attn | hcpya_task21 | best | 11 | 0.00081 | 0.05 | 30 | [2.7, 1.0] | validation | 0.025608 | 0.9933 | 0.0013354 | 0.99182 | 0.0017535 | +| flat_mae | patch | attn | hcpya_task21 | best | 11 | 0.00081 | 0.05 | 30 | [2.7, 1.0] | test | 0.037847 | 0.98988 | 0.0013789 | 0.98725 | 0.0019133 | + + +done! total time: 1:18:40 diff --git a/input_space_v3/flat_lr1e-3_5/eval_v2/hcpya_task21__patch__attn/train_log.json b/input_space_v3/flat_lr1e-3_5/eval_v2/hcpya_task21__patch__attn/train_log.json new file mode 100644 index 0000000000000000000000000000000000000000..9826ef20aeb63cd36c012f465e86cd1ece848070 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_5/eval_v2/hcpya_task21__patch__attn/train_log.json @@ -0,0 +1,20 @@ +{"epoch": 0, "train/lr": 2.987987987987988e-05, "train/loss": 2.0753355234861375, "train/grad": 0.2126280763745308, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.03500244140625, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.031949462890625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.027034912109375, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.0220849609375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.017144775390625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.010177001953125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.002354736328125, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.99370361328125, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.982276611328125, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.970123291015625, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.95803466796875, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.9398712158203124, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.9222369384765625, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.896302490234375, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.87143310546875, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.8472650146484373, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.816325988769531, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.7793902587890624, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.73725830078125, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.6972393798828125, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.6466455078125, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.5927197265625, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.530550842285156, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.461515197753906, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.3871543502807615, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.2956775665283202, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.2118649673461914, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.1351036262512206, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.031255254745483, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.9106254529953004, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.8063781929016114, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.7153899025917054, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.5991173341870308, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.5023804641515017, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.3961358995735644, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.2995908778347074, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.2057632731366903, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.1252093306090682, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.0456744098197668, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.9562044243142008, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.8933546500094235, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.8429187418986112, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.7829166556056589, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.7361387785989791, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.6869102897215634, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.6391095333360135, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.6023568907473237, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.5631029468588531, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.5324685746990144, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.04000151486136019, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.03994100718759, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.03983996082097292, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.03973895763978362, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.03963822807185352, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.03950096762739122, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.039344011368229986, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.03916863633319736, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.0389373317360878, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.03868951506912708, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.03844245368614793, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.03806922098621726, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.03770485196262598, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.037171146748587486, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.036656083539128304, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.03616293038241565, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.035544891310855746, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.034845176450908184, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.03411168868653476, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.03347841708920896, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.0327594995778054, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.032079163808375596, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.03137033847160638, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.03065233724191785, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.029927585599943997, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.029079310549423098, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.02832525294274092, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.027647161362692713, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.026745101055130362, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.025717815696261824, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.024843831094913185, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.02407114270143211, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.023044849657453598, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.022181784545537084, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.021200811073649673, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.020251468997448684, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.01938528640428558, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.01872922609327361, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.018047653218964115, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.017054206136381252, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.016134493092540652, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.015484605162637308, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.014909719192655758, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.014633855668944307, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.014510154160670936, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.014268839470751117, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.014210417016001883, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.014245966670277993, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.014278154045750852, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.9939565658569336, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.984980583190918, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.9700822830200195, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.9553184509277344, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.940812110900879, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.9207324981689453, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.897998809814453, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.8728840351104736, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.840151786804199, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.8055388927459717, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.7718851566314697, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.721616744995117, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.673349142074585, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.604616641998291, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.539740562438965, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.4783778190612793, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.401362419128418, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.3113365173339844, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.2102482318878174, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.1150388717651367, "validation/loss_020_lr5.2e-01_wd1.0e+00": 1.9952930212020874, "validation/loss_021_lr6.1e-01_wd1.0e+00": 1.869032382965088, "validation/loss_022_lr7.2e-01_wd1.0e+00": 1.7255710363388062, "validation/loss_023_lr8.5e-01_wd1.0e+00": 1.5702928304672241, "validation/loss_024_lr1.0e+00_wd1.0e+00": 1.409458041191101, "validation/loss_025_lr1.2e+00_wd1.0e+00": 1.2231756448745728, "validation/loss_026_lr1.4e+00_wd1.0e+00": 1.0650720596313477, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.9308732151985168, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.7644475698471069, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.5901286602020264, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.45446768403053284, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.34928637742996216, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.24087943136692047, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.17245429754257202, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.11069194227457047, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.07501441985368729, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.06199081987142563, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.05729232355952263, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.056616298854351044, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.05752722918987274, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.05057905986905098, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.04386607185006142, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.040492795407772064, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.03944065421819687, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.040603477507829666, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.055079616606235504, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.06899107992649078, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.08055047690868378, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.07000747323036194, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.16245039682539683, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.19419642857142858, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.24603174603174602, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.2683531746031746, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.27331349206349204, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.27455357142857145, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.2725694444444444, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.263640873015873, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.25049603174603174, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.24131944444444445, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.23586309523809523, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.22842261904761904, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.2286706349206349, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.2286706349206349, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.234375, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.25049603174603174, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.2854662698412698, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.3410218253968254, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.41393849206349204, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.482390873015873, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.5545634920634921, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.5840773809523809, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.6041666666666666, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.6351686507936508, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.6770833333333334, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.7564484126984127, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.84375, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.878968253968254, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.8975694444444444, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9067460317460317, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9077380952380952, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9164186507936508, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9404761904761905, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9697420634920635, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9796626984126984, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9813988095238095, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9826388888888888, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9828869047619048, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9831349206349206, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.982390873015873, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9841269841269841, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.984375, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.984375, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9853670634920635, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.986359126984127, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9816468253968254, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9786706349206349, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9751984126984127, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9754464285714286, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.0691023781013056, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.07779300688004441, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.0898820314344577, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.09355483997961167, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.09578171182888762, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.09899277574031079, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.1030970181938287, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.103057089576215, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.08756173665321436, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.07440454018442402, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.06985788749329369, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.06085009145869721, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.06333198466897146, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.06460509963844638, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.06953249083159782, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.08275453424368447, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.11157065621166265, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.15100918806104557, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.19982691047525988, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.2495729937211833, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.29276168621945925, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.31425616656894495, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.34039347894839345, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.3924576908764924, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.4638784630631954, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.6333885253826966, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.7936431772135217, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.8519586136742399, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.8787615121254527, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.8894537378832881, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.8886000357034263, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9003360188069385, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.93181005840871, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9662349705994715, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9780775262023704, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9799505549708268, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9817162800658762, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9819701846120288, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.982521994439273, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9820078496048618, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9832673581327247, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9832859711345834, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9828476476486466, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9844625097783093, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9852902030590099, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9745691171822796, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9696648287491806, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9662418634013018, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9718229596243881, "id_best": 44, "lr_best": 0.0078, "wd_best": 0.05, "train/loss_best": 0.6869102897215634, "validation/loss_best": 0.040603477507829666, "validation/acc_best": 0.986359126984127, "validation/f1_best": 0.9852902030590099} +{"epoch": 1, "train/lr": 8.993993993993998e-05, "train/loss": 1.1393139719963075, "train/grad": 0.15042410083115101, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.919793701171875, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.90055419921875, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.8689935302734373, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.8382733154296873, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.8082440185546873, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.7675311279296877, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.722901611328125, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.6745751953125, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.6131271362304687, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.550043640136719, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.490065002441406, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.402792510986328, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.320784912109375, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.205454864501953, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.0981099700927732, "train/loss_015_lr2.3e-01_wd1.0e+00": 1.9973760986328124, "train/loss_016_lr2.7e-01_wd1.0e+00": 1.8723941802978517, "train/loss_017_lr3.2e-01_wd1.0e+00": 1.729492416381836, "train/loss_018_lr3.8e-01_wd1.0e+00": 1.5754401397705078, "train/loss_019_lr4.4e-01_wd1.0e+00": 1.438042106628418, "train/loss_020_lr5.2e-01_wd1.0e+00": 1.2771686553955077, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.1215492630004882, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.9613386678695679, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.8068415713310242, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.6660115739703178, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.5235932378470898, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.4179977669194341, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.33946710409596564, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.25634775425307454, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.18558710505254566, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.1418993593379855, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.11437925942242146, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.08987430978566407, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.07665632478892803, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.06789568793028593, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.06358026004396379, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.060860799616202714, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.059268251061439514, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.057953328052535655, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.05683943540789187, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.05659283431246877, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.05779770825058222, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.058334254221990706, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.05819192931987345, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.06259914268739522, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.06909998533315957, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.07428619778715075, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.1043785637896508, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.146005926374346, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.03727527902461589, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.036892264522612093, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.03626721297390759, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.03565622499212623, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.03506506479345262, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.034266834994778034, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.033403260465711355, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.032499480322003366, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.03141261229291558, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.03039092255756259, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.02951114515773952, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.028390915282070637, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.027487628972157837, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.02640961144119501, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.025549232410266996, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.024823975702747702, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.023985480330884455, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.023053942248225212, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.022037641797214746, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.021103808651678265, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.019969221204519272, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.01882448449265212, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0175695061031729, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.016236393693834544, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.014912174462806434, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.01341261291410774, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.012120675886981189, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.01112594141275622, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.010067686719121411, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.00910379788489081, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.008445300611201674, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.008013883916428313, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.007615610829088837, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.007490697787725367, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.007402201578370296, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.007366256001987494, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0072632930014515295, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.007192840900970623, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.00715122114343103, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.007150019780383445, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.007281301848997827, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.007461157524958253, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.007560179849970154, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.007583887307700934, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.008499077145097544, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.009083690730913077, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0093149416349479, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.013109575659618712, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0158449537791239, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.8250014781951904, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.7935917377471924, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.74277663230896, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.6940181255340576, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.6470143795013428, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.5842461585998535, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.5163559913635254, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.444186210632324, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.354069232940674, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.262626886367798, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.176260471343994, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.0510125160217285, "validation/loss_012_lr1.4e-01_wd1.0e+00": 1.9336879253387451, "validation/loss_013_lr1.7e-01_wd1.0e+00": 1.7699881792068481, "validation/loss_014_lr2.0e-01_wd1.0e+00": 1.6198811531066895, "validation/loss_015_lr2.3e-01_wd1.0e+00": 1.482757329940796, "validation/loss_016_lr2.7e-01_wd1.0e+00": 1.3186832666397095, "validation/loss_017_lr3.2e-01_wd1.0e+00": 1.1411224603652954, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.9623714685440063, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.8134021162986755, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.6498361229896545, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.5020717978477478, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.3650963008403778, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.25683385133743286, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.17686785757541656, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.10765890032052994, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.07762036472558975, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.06581153720617294, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.057559676468372345, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.052486952394247055, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.049334537237882614, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.04682198911905289, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.043684374541044235, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.0419427827000618, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.0409933477640152, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.03933748975396156, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.03576739504933357, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.03498348221182823, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.03403899818658829, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.03263762593269348, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.03878575935959816, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.043147843331098557, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.0510060116648674, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.06328782439231873, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.07662219554185867, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.0806417390704155, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.12029679864645004, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.21562209725379944, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.22070305049419403, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.251984126984127, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.24677579365079366, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.23983134920634921, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.2361111111111111, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.23660714285714285, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.23958333333333334, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.25223214285714285, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.2760416666666667, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.32762896825396826, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.3970734126984127, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.470734126984127, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.550843253968254, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.580109126984127, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.6026785714285714, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.6227678571428571, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.654265873015873, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.7313988095238095, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.8182043650793651, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.8663194444444444, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.8936011904761905, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9107142857142857, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9288194444444444, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9419642857142857, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9605654761904762, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9739583333333334, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9811507936507936, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.984375, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9846230158730159, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9858630952380952, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9856150793650794, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9853670634920635, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.986359126984127, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9871031746031746, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9871031746031746, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9871031746031746, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9866071428571429, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9880952380952381, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9880952380952381, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.988343253968254, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9895833333333334, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9858630952380952, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9856150793650794, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.984375, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.982390873015873, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9789186507936508, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9751984126984127, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9712301587301587, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9702380952380952, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9714781746031746, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.08735604250412027, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.07738916611330297, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.06828211616095295, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.06499779020584244, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.06620457910338776, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.06887296468310164, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.07717600871603404, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.09743745115850176, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.14031033219756098, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.19093168255553983, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.2478611226857523, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.29366230922653663, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.31511937248892224, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.3386025383811034, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.3746758432773098, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.4428087390462889, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.5979702189472477, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.747013739773343, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.8255810241192505, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.8695127468626606, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.8933936858771645, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9203421954678584, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9352778645102979, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9557699918542726, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9707030768890781, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9782504097104339, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9812829870065556, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9812679971278261, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9832044619154924, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9835978469357145, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9837789545834336, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9844888359822553, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9852297570123392, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9857306807425158, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9861910706144054, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9846092652816187, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9865730292065833, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9865897862551934, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9871334877451771, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9882688447093495, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9844453882557032, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9837998384067483, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.982640403897473, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9798673908660339, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9756745572200023, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9695972387691304, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9548448533442032, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.959482185164952, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9680172488393415, "id_best": 39, "lr_best": 0.0036, "wd_best": 0.05, "train/loss_best": 0.05683943540789187, "validation/loss_best": 0.03263762593269348, "validation/acc_best": 0.9895833333333334, "validation/f1_best": 0.9882688447093495} +{"epoch": 2, "train/lr": 0.00014999999999999988, "train/loss": 0.8340402150154114, "train/grad": 0.18969817228615285, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.71093017578125, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.6661566162109374, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.5950933837890626, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.52828125, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.4647952270507814, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.3809744262695314, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.290965270996094, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.1957366943359373, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.076709442138672, "train/loss_009_lr8.7e-02_wd1.0e+00": 1.9562088775634765, "train/loss_010_lr1.0e-01_wd1.0e+00": 1.8435099029541016, "train/loss_011_lr1.2e-01_wd1.0e+00": 1.6836516952514649, "train/loss_012_lr1.4e-01_wd1.0e+00": 1.5389578819274903, "train/loss_013_lr1.7e-01_wd1.0e+00": 1.3474979019165039, "train/loss_014_lr2.0e-01_wd1.0e+00": 1.1827702236175537, "train/loss_015_lr2.3e-01_wd1.0e+00": 1.0405981969833373, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.8793793845176697, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.7145543754100799, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.560063447356224, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.4426465633511543, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.3275473929941654, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.23862257584929467, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.17054215071722864, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.12450253615155817, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.09544397183693945, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.07740148809738458, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.0700471010338515, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.06616628472693264, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.062453448567539455, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.05941416149027646, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.05783783746883273, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.05692505842074752, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.05603356442414224, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.05471850899979472, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.05406566177494824, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.05423752713017166, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.0521966612432152, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.050326502369716766, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.050880438089370726, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.05305862437002361, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.06259389386512339, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.0739768377225846, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.08920478804968297, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.1218066784646362, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.13896444785408676, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.29200440294109287, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.5352124438900501, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.867098566358909, "train/loss_048_lr5.0e+01_wd1.0e+00": 1.755207142625004, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.0336573245562613, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.03278883925639093, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.031455082595348356, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.030282631628215314, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.029272800739854575, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.028107194006443025, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.027069050036370754, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.026169699244201185, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.025250646667554975, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.024453370589762925, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.023757345816120504, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.022771379789337517, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.021834928775206208, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.020508585264906287, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.019291902519762517, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.018203480509109794, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.016936937160789967, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.015582233211025595, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.01418447429779917, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.013000966818071901, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.0116642439016141, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.010368719603866339, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.009121440061135218, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.00812013921677135, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.007422190768411383, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.006950373575091362, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.006853896694374271, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.006854462508345023, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.006855000421637669, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.006875641212100163, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.006982836682000198, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.007079845540574752, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.007177595621615182, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.007107864019926638, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.007074180856870953, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.007097995355725289, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.006994256140606012, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.006877364736283198, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.006968944364780327, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.007412522953818552, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.00851413174328627, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.009863501573454414, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.011984728291572537, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.014383036661311053, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.016222941439482382, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.02798446621020048, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.044909780656041606, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.06106289882290341, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.10065685105277225, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.582015037536621, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.5243966579437256, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.434112071990967, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.3498878479003906, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.2706480026245117, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.1659672260284424, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.0534956455230713, "validation/loss_007_lr6.2e-02_wd1.0e+00": 1.934456467628479, "validation/loss_008_lr7.4e-02_wd1.0e+00": 1.7863962650299072, "validation/loss_009_lr8.7e-02_wd1.0e+00": 1.6385602951049805, "validation/loss_010_lr1.0e-01_wd1.0e+00": 1.503110647201538, "validation/loss_011_lr1.2e-01_wd1.0e+00": 1.3172558546066284, "validation/loss_012_lr1.4e-01_wd1.0e+00": 1.1561932563781738, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.9537700414657593, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.7883621454238892, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.6509604454040527, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.5011575222015381, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.3606613278388977, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.25044164061546326, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.17836463451385498, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.11354925483465195, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.08059944212436676, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.06561548262834549, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.057326070964336395, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.05187172070145607, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.04750905930995941, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.04471562057733536, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.04305613413453102, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.041087307035923004, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.039072152227163315, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.03784099966287613, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.037227530032396317, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.03672713786363602, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.03621852025389671, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.03642405569553375, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.03836092725396156, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.03420967981219292, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.035929251462221146, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.040105149149894714, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.04738115891814232, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.04838266968727112, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.08466608077287674, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.10724814981222153, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.12756916880607605, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.19974298775196075, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.38064825534820557, "validation/loss_046_lr3.6e+01_wd1.0e+00": 1.0231488943099976, "validation/loss_047_lr4.3e+01_wd1.0e+00": 1.236343502998352, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1752126216888428, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.23239087301587302, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.24305555555555555, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.2700892857142857, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.3196924603174603, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.37450396825396826, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.45783730158730157, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.5369543650793651, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.5773809523809523, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.6059027777777778, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.6339285714285714, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.6659226190476191, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.7348710317460317, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.8157242063492064, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.8705357142857143, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.8963293650793651, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9084821428571429, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9270833333333334, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9444444444444444, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9627976190476191, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9761904761904762, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9821428571428571, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9841269841269841, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9851190476190477, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9848710317460317, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9848710317460317, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9856150793650794, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9866071428571429, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9873511904761905, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9873511904761905, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.988343253968254, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9875992063492064, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9878472222222222, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9875992063492064, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9873511904761905, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9875992063492064, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.988343253968254, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9898313492063492, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9888392857142857, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.986359126984127, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9871031746031746, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9851190476190477, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9779265873015873, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9779265873015873, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9786706349206349, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9744543650793651, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9744543650793651, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9682539682539683, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9719742063492064, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9600694444444444, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.06757180961508172, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.075323503338481, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.09573974303580031, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.13552984506849236, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.1748365541370059, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.2386922591743451, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.289997625182488, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.31522121757367955, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.3453367286085515, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.3886897843476193, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.43907594101724207, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.5750277688196723, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.7264486122579237, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.8272658345983647, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.8712917926777619, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.8900756533170561, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9171922961377694, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9384787950053156, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9585433208602092, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.974091684121396, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9807796533503245, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9828232680444406, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9835143356886205, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9831001436224068, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9829813129834652, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9846920053806282, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9854128846812881, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9859917513335126, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9858010332303022, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9865703640214912, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9858639588468505, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9860494703731577, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9858932985581783, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9852972084484575, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9858933142953767, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9871046332911455, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9881709041188762, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9872094790266104, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9848479957710746, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9861921274355671, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9837516259408465, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9739586836097858, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9776361801747336, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9781692792709265, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.970719572335625, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9729574577908157, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9551332787272658, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9682079651485535, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9577228843280492, "id_best": 36, "lr_best": 0.0021299999999999995, "wd_best": 0.05, "train/loss_best": 0.0521966612432152, "validation/loss_best": 0.03420967981219292, "validation/acc_best": 0.9898313492063492, "validation/f1_best": 0.9881709041188762} +{"epoch": 3, "train/lr": 0.0002100600600600602, "train/loss": 0.7395920065045357, "train/grad": 0.2731562130153179, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.457461242675781, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.3879156494140625, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.2792555236816407, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.177373809814453, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.08091796875, "train/loss_005_lr4.5e-02_wd1.0e+00": 1.9537716674804688, "train/loss_006_lr5.3e-02_wd1.0e+00": 1.818305130004883, "train/loss_007_lr6.2e-02_wd1.0e+00": 1.6773217010498047, "train/loss_008_lr7.4e-02_wd1.0e+00": 1.5069984436035155, "train/loss_009_lr8.7e-02_wd1.0e+00": 1.3435773658752441, "train/loss_010_lr1.0e-01_wd1.0e+00": 1.1996329498291016, "train/loss_011_lr1.2e-01_wd1.0e+00": 1.0105646133422852, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.8534427642822265, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.6635303258895874, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.5170539999008179, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.4058896142244339, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.29826254799962043, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.20832521714270114, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.1443663405813277, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.10871654206886888, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.0850519454292953, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.07378390858881176, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.06714169715531171, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.06257293189875782, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.058990980396047235, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.05559553644619882, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.05288134717382491, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.050682953288778664, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.04785280796699226, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.045042394809424874, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.04297194582410157, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.041381930280476806, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.039453157363459467, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.03837314725853503, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.0383429704234004, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.03941275608725846, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.038071726681664586, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.03935561660677195, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.04576139372773468, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.05828917605802417, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.06281660201959312, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.09200870236381889, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.18821456444449722, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.3008311223704368, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.5912005412578583, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.9311523891892284, "train/loss_046_lr3.6e+01_wd1.0e+00": 1.0114149508159607, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.9859777506254614, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.9626988248340784, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.028652793969959022, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.027710739877074956, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.026517842281609773, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.025652137445285918, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.02498098771087825, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.024206580715253948, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.023426688415929674, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.022591193579137324, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.021501005226746202, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.02036302149295807, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.019291773387230933, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.01781974360346794, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.016563685736618938, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.014993921369314194, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.013640628601424397, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.012433369592763484, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.011001175786368549, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.00941392526961863, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.008042267300188541, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.007190146769862622, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.006612844832707196, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.006408075561048463, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0063531518424861134, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.006326969008659944, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0062717393541242925, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.006186696104123257, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.006123545487644151, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.006059968765475788, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.005955148096545599, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0058154260035371405, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.005661152050888632, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.005543534086609725, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.005395974756102078, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.005348149195779115, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.005432669762376463, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.005595224233693443, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.005676521798304748, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.006126528146851342, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.006820321706400136, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.008850768299598712, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.009526007845197455, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.012503401941503399, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.021199599919909815, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.029934920164814683, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.04556945980273693, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.06195748311009673, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.06739699416426906, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.14098113421918926, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.155454504947801, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.3088173866271973, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.226205348968506, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.097147226333618, "validation/loss_003_lr3.3e-02_wd1.0e+00": 1.9763706922531128, "validation/loss_004_lr3.8e-02_wd1.0e+00": 1.8628343343734741, "validation/loss_005_lr4.5e-02_wd1.0e+00": 1.7143783569335938, "validation/loss_006_lr5.3e-02_wd1.0e+00": 1.5593650341033936, "validation/loss_007_lr6.2e-02_wd1.0e+00": 1.4022105932235718, "validation/loss_008_lr7.4e-02_wd1.0e+00": 1.2188266515731812, "validation/loss_009_lr8.7e-02_wd1.0e+00": 1.0496430397033691, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.9057760834693909, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.7224625945091248, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.5739881992340088, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.4038599729537964, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.28918248414993286, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.21360661089420319, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.14264167845249176, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.09327038377523422, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.07207174599170685, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.06269727647304535, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.055759113281965256, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.05091772601008415, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.047081660479307175, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.043874237686395645, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.04132603481411934, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.038997359573841095, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.037532370537519455, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.03737147897481918, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.037869054824113846, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.03827035054564476, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.0386873260140419, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.03976025432348251, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.04211709648370743, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.04404393211007118, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.0433073453605175, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.04371272027492523, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.07984382659196854, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.0795150026679039, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.07164418697357178, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.06346560269594193, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.11598173528909683, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.10924726724624634, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.2282658964395523, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.7880682945251465, "validation/loss_044_lr2.6e+01_wd1.0e+00": 1.4835995435714722, "validation/loss_045_lr3.1e+01_wd1.0e+00": 1.1759521961212158, "validation/loss_046_lr3.6e+01_wd1.0e+00": 2.128589391708374, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.9215757846832275, "validation/loss_048_lr5.0e+01_wd1.0e+00": 4.994147300720215, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.36334325396825395, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.43179563492063494, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.5205853174603174, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.5682043650793651, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.5890376984126984, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.6076388888888888, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.636656746031746, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.6899801587301587, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.7834821428571429, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.8482142857142857, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.8740079365079365, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.8998015873015873, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9164186507936508, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9347718253968254, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9516369047619048, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.964781746031746, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9771825396825397, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.982390873015873, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9846230158730159, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9853670634920635, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9858630952380952, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.986359126984127, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9873511904761905, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9885912698412699, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9885912698412699, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9888392857142857, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.988343253968254, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9871031746031746, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9880952380952381, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9873511904761905, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.986359126984127, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9856150793650794, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9846230158730159, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9838789682539683, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9856150793650794, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9871031746031746, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9764384920634921, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9781746031746031, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9816468253968254, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9841269841269841, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9769345238095238, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9838789682539683, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.982390873015873, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9692460317460317, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.957093253968254, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.970734126984127, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9610615079365079, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9722222222222222, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.964781746031746, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.16848986673768826, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.21833741103238363, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.2783995114936908, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.3036881730542161, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.3218679333243118, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.3486065296654764, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.4033119254256418, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.5109221866485297, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.6873802269463258, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.804392685907878, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.8423441080533813, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.8817516575150399, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9039827576081201, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9286527353449027, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9466057553942386, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9623925824771506, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9749195752226941, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9806225700160768, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9823005081876035, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9831391338561092, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9836779089583261, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9838610652270632, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9849462657852063, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.986529220336726, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9865314392279603, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9874367971295396, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9868864989566617, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9856425657320613, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9863525482945316, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9862761852688661, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9851717297472447, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.984356847841189, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9831555754395382, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9830577952559455, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9847281334555766, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9863152512721711, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9768189669669978, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9790956242785349, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9808166728977192, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9832193962492871, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9755415878841379, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9794503317353942, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9787810458021944, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9570343528439658, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9526394422129788, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9689057134130663, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9597101638683779, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9665406117124868, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9528097023704503, "id_best": 25, "lr_best": 0.00035999999999999997, "wd_best": 0.05, "train/loss_best": 0.05559553644619882, "validation/loss_best": 0.038997359573841095, "validation/acc_best": 0.9888392857142857, "validation/f1_best": 0.9874367971295396} +{"epoch": 4, "train/lr": 0.0002701201201201201, "train/loss": 0.7835398845374584, "train/grad": 0.43359429351985457, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.171289520263672, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.0757859802246093, "train/loss_002_lr2.8e-02_wd1.0e+00": 1.9265621948242186, "train/loss_003_lr3.3e-02_wd1.0e+00": 1.7884854888916015, "train/loss_004_lr3.8e-02_wd1.0e+00": 1.6604382705688476, "train/loss_005_lr4.5e-02_wd1.0e+00": 1.4970545196533203, "train/loss_006_lr5.3e-02_wd1.0e+00": 1.3312454986572266, "train/loss_007_lr6.2e-02_wd1.0e+00": 1.168656120300293, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.9851417064666748, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.8204349088668823, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.6833494186401368, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.51561842918396, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.39143445730209353, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.2660945375263691, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.18682093277573586, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.1372143980488181, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.10059032106772064, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.08074144339188934, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.07066613940522075, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.06508120706304908, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.06033255341462791, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.0566087696608156, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.05330224916338921, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.05041220678016543, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.04786100714467466, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.0453917024563998, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.04360632092691958, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.04215981129556894, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.04012420768849552, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.03752192931249738, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.03577888824045658, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.03441519645042718, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.033927742019295694, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.035224000746384265, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.032130230758339165, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.03298412033356726, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.0379737785551697, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.04649552258662879, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.05767691644839942, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.11449933125637472, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.19491329698823393, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.3299337268434465, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.6311993753165006, "train/loss_043_lr2.2e+01_wd1.0e+00": 1.1573772943299263, "train/loss_044_lr2.6e+01_wd1.0e+00": 1.5886341781262308, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.2917396903876215, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.922819900130853, "train/loss_047_lr4.3e+01_wd1.0e+00": 4.454788285139948, "train/loss_048_lr5.0e+01_wd1.0e+00": 5.960917364116758, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.025658412892371415, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.025002812780439854, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.024118517776951193, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.02334133175201714, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.022592884050682188, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.02156607729382813, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.020425817705690862, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.019224094646051525, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.01780059318523854, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.016488887229934336, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.015375354350544513, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.013872683783993124, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.012506539816968143, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.01070767715573311, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.009137430218979717, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.00789253213093616, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.006866685574641452, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.006373264334397391, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.0061992757953703405, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.0061307107424363495, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.006081816900987178, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.0060529576521366835, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.006041748524294235, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.006038676762836985, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.006071333793806843, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.006185982286988292, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.006303779331792611, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.006392175963846967, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.006385145102976822, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0061936629505362365, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.006086030890874099, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0059695148846367375, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.006055519257497508, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.006355225498264189, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.005911161692783935, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0059378081405884586, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.007187017109245062, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.008247643765134854, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.010738573715789243, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.016842756911784135, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.022583263063214502, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.032054963221598884, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.04974218350861335, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.07587252127399552, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.09980286126255741, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.1280568944897681, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.14027940477020137, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.18053027086049356, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.24453381273895503, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.017019748687744, "validation/loss_001_lr2.3e-02_wd1.0e+00": 1.9079843759536743, "validation/loss_002_lr2.8e-02_wd1.0e+00": 1.7390819787979126, "validation/loss_003_lr3.3e-02_wd1.0e+00": 1.5851997137069702, "validation/loss_004_lr3.8e-02_wd1.0e+00": 1.4453648328781128, "validation/loss_005_lr4.5e-02_wd1.0e+00": 1.2715145349502563, "validation/loss_006_lr5.3e-02_wd1.0e+00": 1.1008355617523193, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.9383929371833801, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.7600259780883789, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.6033104658126831, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.4761826694011688, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.3325669467449188, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.2399550974369049, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.15011879801750183, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.09822512418031693, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.0767708420753479, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.0640333965420723, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.05592753738164902, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.050340667366981506, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.04692172259092331, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.043877553194761276, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.04175253584980965, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.03995084762573242, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.03840699791908264, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.03816433995962143, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.043810050934553146, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.050382714718580246, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.04988884553313255, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.04412117600440979, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.04127170518040657, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.04364119470119476, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.0443137027323246, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.04291786625981331, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.04181983321905136, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.04291287064552307, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.05647218972444534, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.11863787472248077, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.05231303721666336, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.11138784140348434, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.21301564574241638, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.5073310136795044, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.5216379165649414, "validation/loss_042_lr1.9e+01_wd1.0e+00": 1.5800085067749023, "validation/loss_043_lr2.2e+01_wd1.0e+00": 1.5945358276367188, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.5832931995391846, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.96122670173645, "validation/loss_046_lr3.6e+01_wd1.0e+00": 4.499084949493408, "validation/loss_047_lr4.3e+01_wd1.0e+00": 5.875968933105469, "validation/loss_048_lr5.0e+01_wd1.0e+00": 11.698193550109863, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.5592757936507936, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.5823412698412699, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.6086309523809523, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.6346726190476191, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.6785714285714286, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.7611607142857143, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.839781746031746, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.8767361111111112, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.8975694444444444, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9112103174603174, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9265873015873016, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9494047619047619, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9670138888888888, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9779265873015873, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9809027777777778, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9841269841269841, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9861111111111112, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.986359126984127, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9878472222222222, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9880952380952381, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9885912698412699, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9880952380952381, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9873511904761905, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9875992063492064, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9868551587301587, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9841269841269841, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9818948412698413, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9828869047619048, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9858630952380952, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.986359126984127, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9858630952380952, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.986359126984127, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9871031746031746, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9880952380952381, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9878472222222222, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9846230158730159, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9749503968253969, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9875992063492064, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9799107142857143, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9771825396825397, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.970734126984127, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9759424603174603, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9610615079365079, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9682539682539683, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.955109126984127, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9704861111111112, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9766865079365079, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9635416666666666, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9593253968253969, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.2969109467730901, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.31452135484679433, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.34672684558976197, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.39178216203886473, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.4826278342993594, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.6373823061613183, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.7773708923243335, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.8391099545074644, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.874022623914723, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.8942783210087439, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9159150442010089, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9447691566217444, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9642285140005675, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9762820854633679, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.979472954549655, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9824659032262747, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9845182233009796, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9846987461321406, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9856933278096343, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9863814575951475, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9868357018737076, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9861131917386174, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9855781903261137, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9858743426507213, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9856091434679132, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9829295531150574, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9812951730469112, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9820038355162246, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9847122660990725, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9848026174561045, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9842288117735204, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9844227541143136, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9853403296651922, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9859632339196296, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9860957513329994, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9833982691484109, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9715690776717687, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9853196568300421, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9767362762708183, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9632590467653046, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9621533858130464, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.976090260650415, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9415818515434221, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9557631087468775, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9547035475563597, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9680390185500248, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9706282629117522, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9559616195376828, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9583907085670637, "id_best": 20, "lr_best": 0.000156, "wd_best": 0.05, "train/loss_best": 0.06033255341462791, "validation/loss_best": 0.043877553194761276, "validation/acc_best": 0.9885912698412699, "validation/f1_best": 0.9868357018737076} +{"epoch": 5, "train/lr": 0.00029891323817685334, "train/loss": 0.8641306645423174, "train/grad": 0.47589423924684526, "train/loss_000_lr2.0e-02_wd1.0e+00": 1.8859627532958985, "train/loss_001_lr2.3e-02_wd1.0e+00": 1.7653549194335938, "train/loss_002_lr2.8e-02_wd1.0e+00": 1.5816618347167968, "train/loss_003_lr3.3e-02_wd1.0e+00": 1.4180622863769532, "train/loss_004_lr3.8e-02_wd1.0e+00": 1.2729827499389648, "train/loss_005_lr4.5e-02_wd1.0e+00": 1.0973456859588624, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.9290121364593505, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.7718982982635498, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.6024179649353028, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.46008602261543274, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.3544709795713425, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.24521894499659538, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.17432415802031756, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.1140641175955534, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.08909602253697813, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.07832993348129094, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.07080153968185186, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.06534241411834955, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.06109519184567034, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.058146040802821514, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.055097598498687145, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.05236740699969232, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.04969977292232215, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.04704647211357951, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.04450781620107591, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.04177629360929132, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.03927468251436949, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.036782518615946176, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.03349330703727901, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0305357844568789, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.02831501048989594, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.026696032183244824, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.02755679693073034, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.026229370115324856, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.028809456350281835, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.031256573302671314, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.04277725114487112, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.056761181270703676, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.09909321865066886, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.21121824298985303, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.3501457301992923, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.5893451794795692, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.9422048966865987, "train/loss_043_lr2.2e+01_wd1.0e+00": 1.3061026783939451, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.024767332505435, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.7592995966318994, "train/loss_046_lr3.6e+01_wd1.0e+00": 6.1300710272882135, "train/loss_047_lr4.3e+01_wd1.0e+00": 4.677743430975824, "train/loss_048_lr5.0e+01_wd1.0e+00": 8.457754901051521, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.023763176603242755, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.023087773025035858, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.02199299675412476, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.02090809930115938, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.019859818229451775, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.018502931990660727, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.017152812336571514, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.01588513145688921, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.014488169983960688, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.013135107653215527, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.011877062350977212, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.010205560449976473, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.008786696516908705, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.007233454782981426, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.006548187372973188, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.006321700211847201, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.006220817714929581, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.006186517125461251, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.006170113995904103, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.006154526516329497, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.006113504462409765, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.0060635976877529175, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.006023193884175271, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.00600508700532373, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.005996742135030217, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.005942323617055081, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.005792631147487555, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.005588306866702624, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.005349566546210553, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.005184660947998054, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.005070061090227682, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0050690810175728985, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.005255566923660808, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.005201313163270243, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.005818393921726965, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.006007204745947093, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.007655188086282579, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.009366069348743622, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.013925211172689416, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.02209594914036643, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.032774877596015134, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.041385197977292766, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.06696575419709914, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.07923083268920149, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.10792954408937415, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.1521022925014989, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.22377023853361608, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.18104929602418163, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.24189781486988068, "validation/loss_000_lr2.0e-02_wd1.0e+00": 1.7401877641677856, "validation/loss_001_lr2.3e-02_wd1.0e+00": 1.6101365089416504, "validation/loss_002_lr2.8e-02_wd1.0e+00": 1.4156274795532227, "validation/loss_003_lr3.3e-02_wd1.0e+00": 1.2463797330856323, "validation/loss_004_lr3.8e-02_wd1.0e+00": 1.0997204780578613, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.9257649183273315, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.7619398832321167, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.6106032729148865, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.4512849748134613, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.3273799419403076, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.24385736882686615, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.1577300876379013, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.10441417992115021, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.07386709749698639, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.062268272042274475, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.055817458778619766, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.050607483834028244, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.046376317739486694, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.04301359876990318, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.040545910596847534, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.038126081228256226, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.03604443743824959, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.034280482679605484, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.032882917672395706, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.03224290534853935, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.03155747801065445, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.031437840312719345, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.03171178326010704, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.031812701374292374, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.03011493757367134, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.03008461184799671, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.03153096139431, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.03384610638022423, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.05235821381211281, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.0410473607480526, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.04884345084428787, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.12312248349189758, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.10378186404705048, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.2550962269306183, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.2693040668964386, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.506812572479248, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.26692894101142883, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.8021383285522461, "validation/loss_043_lr2.2e+01_wd1.0e+00": 1.3302278518676758, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.2770137786865234, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.290518045425415, "validation/loss_046_lr3.6e+01_wd1.0e+00": 5.5071210861206055, "validation/loss_047_lr4.3e+01_wd1.0e+00": 5.795583248138428, "validation/loss_048_lr5.0e+01_wd1.0e+00": 8.64951229095459, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.6116071428571429, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.6267361111111112, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.6907242063492064, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.7782738095238095, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.8439980158730159, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.8764880952380952, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.8965773809523809, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.9134424603174603, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9285714285714286, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9456845238095238, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9637896825396826, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9774305555555556, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9811507936507936, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9851190476190477, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9858630952380952, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.986359126984127, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9868551587301587, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9878472222222222, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9880952380952381, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9885912698412699, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9888392857142857, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9885912698412699, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9885912698412699, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9890873015873016, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9893353174603174, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9893353174603174, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9888392857142857, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.988343253968254, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9878472222222222, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9875992063492064, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9890873015873016, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9898313492063492, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9888392857142857, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9836309523809523, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9868551587301587, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9841269841269841, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9754464285714286, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.984375, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9749503968253969, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9781746031746031, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9761904761904762, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9851190476190477, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9761904761904762, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9769345238095238, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9784226190476191, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9769345238095238, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9756944444444444, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9685019841269841, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9722222222222222, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.3504900462434651, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.3778567358639508, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.5090685074244478, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.6781678270665034, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.795259224872105, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.8488555370149562, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.8776405364201113, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9016792311328266, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9205378771608166, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9398974186205877, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9590790393456994, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9754412385594028, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.979722231394758, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9832036513313327, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9838320176808977, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9843623052687588, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9848594946546074, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9859880874394865, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9863531115141987, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9870568979468567, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9875564783791588, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9872025662299523, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9871304325564225, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.987129911956332, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.987558695954531, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9879027777648187, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9871871815874439, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9856710840824583, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9845483437281048, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9840167758958229, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.986319686746813, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9876206133047621, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9863373814602681, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.975616962719019, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9831761888412134, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9802019132545258, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9658697109074258, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9807176392221151, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.966538770837124, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9722122272708942, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9689074991596611, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9831043584308387, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9756165684069037, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9747491018414196, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9772222876984884, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9710432579317909, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9673328188975132, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9527911536920305, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9668899357095183, "id_best": 31, "lr_best": 0.0009299999999999999, "wd_best": 0.05, "train/loss_best": 0.026696032183244824, "validation/loss_best": 0.03153096139431, "validation/acc_best": 0.9898313492063492, "validation/f1_best": 0.9876206133047621} +{"epoch": 6, "train/lr": 0.0002924170901991409, "train/loss": 0.562126327753067, "train/grad": 0.37501865908503534, "train/loss_000_lr2.0e-02_wd1.0e+00": 1.6266651153564453, "train/loss_001_lr2.3e-02_wd1.0e+00": 1.489934310913086, "train/loss_002_lr2.8e-02_wd1.0e+00": 1.289140224456787, "train/loss_003_lr3.3e-02_wd1.0e+00": 1.118375644683838, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.9727450561523437, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.8022113943099975, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.6435813426971435, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.5008185243606568, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.36064541459083554, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.2604046094417572, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.19260721728205682, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.12506243940442802, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.0931362770870328, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.07512940282002091, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.06704110055230558, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.06218986978754401, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.05771521258167923, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.05377277570776642, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.05010407800786197, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.0472411391697824, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.04410570253618062, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.04111246788874268, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.03809704277664423, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.03511863636784256, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.03222072321921587, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.029183729784563184, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.02672106836922467, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.024669331097975374, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.02179296176880598, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.018079150952398777, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.015226086368784308, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.013713363138958812, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.014442417249083518, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.016024338277056814, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.015334061533212661, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.016131600039079784, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.03332342785783112, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.07616666969843208, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.11943450615741312, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.17278386755846442, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.17086651205085218, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.26149243989028037, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.442084580892697, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.47898221119306983, "train/loss_044_lr2.6e+01_wd1.0e+00": 1.0309342939034105, "train/loss_045_lr3.1e+01_wd1.0e+00": 1.873321750247851, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.6672655055485666, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.5367725033313038, "train/loss_048_lr5.0e+01_wd1.0e+00": 6.390268564708531, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.02226472079753876, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.021384632345288992, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.019965634606778623, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.018662629895843566, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.01751002763863653, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.016147417686879634, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.014872886925004422, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.01360962348524481, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.012018186380155385, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.010509644232224674, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.009235604398418218, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.007588096173712984, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.006727939052507281, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.006366358894156292, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.006257605018327013, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.006213445686153136, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.0061599147832021115, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.006094613514724187, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.006000571012264117, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.005932051507406868, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.005847879705252126, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.005736753639066592, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.005609023337019608, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.005477509726188145, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.005316959185001906, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.005126672963378951, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.004920413105865009, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.004754811071034055, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.00451906703892746, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.00414750707866915, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0037862531132850565, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0035354212946549523, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.003868688134243712, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0041186929964624145, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.004115166221290565, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.004552281825508544, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.007156437554272088, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.011879984964020878, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.016912216761766886, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.021244861543546253, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.022699205407992213, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.029102762067207934, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0424132307749506, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.045397000668524576, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.07394683405164479, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.10978016897167105, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.14038042433905698, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.15806508088717885, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.2164883987580177, "validation/loss_000_lr2.0e-02_wd1.0e+00": 1.50692617893219, "validation/loss_001_lr2.3e-02_wd1.0e+00": 1.3662962913513184, "validation/loss_002_lr2.8e-02_wd1.0e+00": 1.163446068763733, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.9940747618675232, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.8518150448799133, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.6864471435546875, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.5339014530181885, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.40069377422332764, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.27897465229034424, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.19452153146266937, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.13484732806682587, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.08694358170032501, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.06953241676092148, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.058143045753240585, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.052141107618808746, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.04838677868247032, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.04485810548067093, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.041783902794122696, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.03914520516991615, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.03718774393200874, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.035284318029880524, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.03361661359667778, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.03201249614357948, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.03056337684392929, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.029431279748678207, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.02854294888675213, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.027964645996689796, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.027497844770550728, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.027316590771079063, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.027522360906004906, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.02780078537762165, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.02827407792210579, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.033006247133016586, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.0379517637193203, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.04177296906709671, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.04793396219611168, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.06459236890077591, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.16028492152690887, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.19723248481750488, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.28054672479629517, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.3443538248538971, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.4247799515724182, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.5287370681762695, "validation/loss_043_lr2.2e+01_wd1.0e+00": 1.137976050376892, "validation/loss_044_lr2.6e+01_wd1.0e+00": 1.0631152391433716, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.7201132774353027, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.2126336097717285, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.329667329788208, "validation/loss_048_lr5.0e+01_wd1.0e+00": 4.574137210845947, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.6547619047619048, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.71875, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.8169642857142857, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.875, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.8950892857142857, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.9129464285714286, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9278273809523809, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.9404761904761905, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9605654761904762, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9729662698412699, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9791666666666666, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9818948412698413, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9851190476190477, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9861111111111112, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9868551587301587, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9868551587301587, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9873511904761905, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9885912698412699, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9888392857142857, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9878472222222222, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9875992063492064, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9880952380952381, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.988343253968254, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.988343253968254, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9890873015873016, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9898313492063492, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9900793650793651, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9900793650793651, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9900793650793651, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9905753968253969, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9903273809523809, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9908234126984127, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9900793650793651, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9888392857142857, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9903273809523809, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9888392857142857, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9861111111111112, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9801587301587301, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9828869047619048, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9801587301587301, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9846230158730159, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9838789682539683, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9848710317460317, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9794146825396826, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9866071428571429, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9799107142857143, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9776785714285714, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9761904761904762, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9806547619047619, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.43759203521696577, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.5701056050105668, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.7528087003499674, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.8487888559534701, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.8765230110455471, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.9011275013818382, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.9198422755789826, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9348553412246835, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.956563828732428, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9703441179179713, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9778969434909648, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9805281691572107, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9833233337891164, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9845490625891163, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9848339136181326, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9848717676080994, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9857907432055115, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9868366645020227, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9870641106415486, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9858314232537118, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9856532510725258, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9865522216250908, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9867336630993561, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9864977272479207, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9870924303454529, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9879619640506734, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9881425381099401, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9877706050709931, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.987947897821226, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9883557587036026, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9883630874055965, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9888014442463654, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9885277982253045, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9877599412835009, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9872879789973219, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9861236902704027, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9826039820562468, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9793086754507565, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9812743031823811, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9779829251696429, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9826480765139152, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9798876423496174, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.982076880701216, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9776658949653265, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9843708906228402, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9767587448619363, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9733756901471173, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9762897870867316, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9769608756401722, "id_best": 31, "lr_best": 0.0009299999999999999, "wd_best": 0.05, "train/loss_best": 0.013713363138958812, "validation/loss_best": 0.02827407792210579, "validation/acc_best": 0.9908234126984127, "validation/f1_best": 0.9888014442463654} +{"epoch": 7, "train/lr": 0.00027969249556793234, "train/loss": 0.3846473012119532, "train/grad": 0.3092936043813825, "train/loss_000_lr2.0e-02_wd1.0e+00": 1.4090640258789062, "train/loss_001_lr2.3e-02_wd1.0e+00": 1.2664546394348144, "train/loss_002_lr2.8e-02_wd1.0e+00": 1.064222354888916, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.8981367778778077, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.75983651638031, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.6008968067169189, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.45809226512908935, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.340479251742363, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.23778388708829878, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.1649629236012697, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.11884588655084372, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.0880869990028441, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.0759982013888657, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.0670735889300704, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.06186684825457633, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.05818205420859158, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.05454433508217335, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.05095202865079045, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.04750733154825866, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.04464108683168888, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.04132865596562624, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.038142609214410185, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.034739530701190235, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.031250824499875304, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.027823753515258433, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.02390316592529416, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.02051083231344819, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0175871295761317, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.013964117970317602, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.010520977061241865, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.00919240246526897, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.008129252074286341, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.007572455480694771, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.008944598846137524, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.008204517662525177, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.011480311369523407, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.031109379306435585, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.05988623266108334, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.11005148414522409, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.12354666062630713, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.11989804503507911, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.1232179850526154, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.29343377316370606, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.2596600894536823, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.6059958781208843, "train/loss_045_lr3.1e+01_wd1.0e+00": 1.040124427974224, "train/loss_046_lr3.6e+01_wd1.0e+00": 1.5248516336549074, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.488802769826725, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.886216866625473, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.021070782523602248, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.02002769535407424, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.01844246739987284, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.017089598109014333, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.015958455447107552, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.014630029224790633, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.013265053196810185, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.011810910319909454, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.010167678208090366, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.008632431842852385, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.0073874232778325674, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.0065843120974022895, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.006353256704751402, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.006227274645352736, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.006143737400416285, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.00605351441714447, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.005951199433766306, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.005826585505274124, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.005689139071619138, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.0055725960098789076, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.005436443836952094, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.005286950876179617, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.005116573671984952, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.004905899152799975, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.004671349648560863, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.004384995381115004, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.004112033738492755, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.003850073646462988, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.003490349566563964, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0030297430896825974, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.002782683785462723, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.002656751709982927, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0024873356430725833, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.002591045211374876, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0027926281039117383, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0037823605072844655, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0069834884775173125, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.011866278531431079, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.01600188189139556, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.017116803166075882, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.017723901595739108, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.017896799202112797, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.03482020422650883, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.028675000384888752, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.05384589456487267, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.07863610408161853, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.10488532614756213, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.1355625319136611, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.16844439476698703, "validation/loss_000_lr2.0e-02_wd1.0e+00": 1.31614351272583, "validation/loss_001_lr2.3e-02_wd1.0e+00": 1.1724773645401, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.9716323614120483, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.8082602620124817, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.6727874875068665, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.5177946090698242, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.38262367248535156, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.2771315276622772, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.18587608635425568, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.12028095126152039, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.08688224107027054, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.06716830283403397, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.05819958820939064, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.051037244498729706, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.046923696994781494, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.04429437220096588, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.04175989702343941, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.039491795003414154, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.037423186004161835, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.03572777658700943, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.03432999178767204, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.03313802182674408, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.03206198289990425, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.030688568949699402, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.029026012867689133, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.027050063014030457, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.025360843166708946, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.024103479459881783, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.023316890001296997, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.024570338428020477, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.025286905467510223, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.025474218651652336, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.028402602300047874, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.029104746878147125, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.03133473917841911, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.051261935383081436, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.062365252524614334, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.1052384153008461, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.14696386456489563, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.3650278151035309, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.3754693865776062, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.2964205741882324, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.5877037048339844, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.7338130474090576, "validation/loss_044_lr2.6e+01_wd1.0e+00": 1.2488117218017578, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1277549266815186, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.0980703830718994, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.358635425567627, "validation/loss_048_lr5.0e+01_wd1.0e+00": 4.507900714874268, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.7435515873015873, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.8125, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.8782242063492064, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.9007936507936508, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9164186507936508, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.9295634920634921, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9441964285714286, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.9613095238095238, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9737103174603174, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9801587301587301, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9818948412698413, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9851190476190477, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.986359126984127, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9871031746031746, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9880952380952381, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.988343253968254, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.988343253968254, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9885912698412699, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9888392857142857, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9888392857142857, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9893353174603174, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9898313492063492, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9890873015873016, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9890873015873016, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9893353174603174, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9900793650793651, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9900793650793651, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9910714285714286, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9910714285714286, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9928075396825397, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9928075396825397, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9925595238095238, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9923115079365079, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9898313492063492, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9878472222222222, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9875992063492064, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.984375, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9818948412698413, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9828869047619048, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.984375, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9846230158730159, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9853670634920635, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9846230158730159, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9759424603174603, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.982390873015873, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9821428571428571, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9799107142857143, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.6166521868310467, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.7390305562678651, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.8524639048012672, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.8845288733313071, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.9055703972060387, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.9225469938097294, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.9382831192320052, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9572915424290023, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9716341991034584, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9788089098684045, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9805402593295095, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9833756987260424, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9844424295402628, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9850239339375007, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9860284170782821, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.986613954146192, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9866981064693396, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9868769098453358, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9872750015746293, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.986918063101492, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9880069504207453, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9885318090508787, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9878861342279873, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9879327915672087, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9881128423954699, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.988757913386634, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9883084558562842, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9892930074133882, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9896564392153725, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.990468244240064, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9901872515387573, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9910870200355253, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9913613911570022, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9909724011014004, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9905299851150842, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.987428884883882, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.985897811631106, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9853263578359889, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.981267030583537, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9755015072578503, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9798761291580851, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9827649116620146, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9831444815528434, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9830427449134019, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9806058907973073, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9663004384101774, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9810359608893668, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9792290689359715, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9764769641118821, "id_best": 31, "lr_best": 0.0009299999999999999, "wd_best": 0.05, "train/loss_best": 0.008129252074286341, "validation/loss_best": 0.025474218651652336, "validation/acc_best": 0.9928075396825397, "validation/f1_best": 0.9910870200355253} +{"epoch": 8, "train/lr": 0.0002612959497061927, "train/loss": 0.24485855907201767, "train/grad": 0.21543868862092494, "train/loss_000_lr2.0e-02_wd1.0e+00": 1.2273726081848144, "train/loss_001_lr2.3e-02_wd1.0e+00": 1.0845253944396973, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.8871794700622558, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.7282123327255249, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.5976462054252625, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.45184292435646056, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.3309337991476059, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.2401350647211075, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.15971802294254303, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.10787957496941089, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.08545307029038668, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.07119168887846172, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.06410760347731412, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.057764772353693844, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.053691974971443415, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.050609421459957955, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.047281664609909055, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.0438244538847357, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.040424817018210886, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.03748882535845041, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.03427937661297619, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.031178511679172516, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.027890288271009922, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.024639019519090654, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.02147229451686144, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.0178167765121907, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.014677190678194165, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.012009619614109396, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.008780995160341263, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.005558417364954949, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.004646049300208688, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.003808524701744318, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.004306099908426404, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.003159827208146453, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.0043729415070265535, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.009407131196931005, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.014266000790521503, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.03581311021000147, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.044953378681093455, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.12127950707450509, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.0768694509100169, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.09887282647192479, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.1490700173471123, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.12176694591529667, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.20447864316403866, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.42035778364166615, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.5427099524624646, "train/loss_047_lr4.3e+01_wd1.0e+00": 1.401343140611425, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.1710021760687233, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.01953735943417996, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.018378748553805054, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.01670216821599752, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.015339549886994064, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.014214289942756295, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.012827948788180948, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.011347603038884699, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.009934943697880954, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.008323081673588605, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.006900376653065905, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.006260876863962039, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.005942486728308723, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.005824594006408006, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.005724097022903152, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.005658336328924634, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.005592970429279376, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.005511629321845248, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.005382332710141781, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.00522720916866092, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.005073998221632792, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.004892117306881118, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.004705590302328346, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.004482897630950901, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.004255620343319606, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.004021836839965545, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0036758792235923464, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.00332485767059552, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0029801863724787836, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.002474553015017591, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.001757948679914989, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0014439718757057562, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0011893403160684103, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.001130869590401744, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0008875885132215444, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.001629722798476223, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0032159248007776853, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0035763333351055593, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.006217342273385939, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.009637025300577994, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.015547788627257928, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.014462284705008101, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.01568015396641629, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.021267850599739586, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.01846640041425328, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.029191846044176385, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.047242136331377915, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.05696412081531208, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0819048415656443, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.12523364959338026, "validation/loss_000_lr2.0e-02_wd1.0e+00": 1.163718819618225, "validation/loss_001_lr2.3e-02_wd1.0e+00": 1.0213942527770996, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.8264052867889404, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.6699748039245605, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.5411466956138611, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.3996344208717346, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.2865336835384369, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.2025744765996933, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.12686771154403687, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.08615186810493469, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.06995155662298203, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.058570247143507004, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.05261579528450966, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.04728834703564644, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.04381357505917549, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.041348252445459366, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.03887082263827324, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.0365842767059803, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.03457482159137726, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.0329345241189003, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.03138578683137894, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.030003687366843224, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.028749775141477585, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.027649259194731712, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.02666388265788555, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.025465350598096848, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.024788077920675278, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.02453078143298626, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.02487180195748806, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.025296367704868317, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.026902712881565094, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.026767410337924957, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.031215066090226173, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.027914123609662056, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.049533579498529434, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.054804299026727676, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.08508942276239395, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.09734611213207245, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.23125481605529785, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.1851533204317093, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.33956441283226013, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.28525009751319885, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.659451425075531, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.5444989204406738, "validation/loss_044_lr2.6e+01_wd1.0e+00": 1.041355848312378, "validation/loss_045_lr3.1e+01_wd1.0e+00": 1.7572712898254395, "validation/loss_046_lr3.6e+01_wd1.0e+00": 2.0386152267456055, "validation/loss_047_lr4.3e+01_wd1.0e+00": 2.9965243339538574, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.6411051750183105, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.8112599206349206, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.8586309523809523, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.8869047619047619, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.9055059523809523, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9221230158730159, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.9382440476190477, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9558531746031746, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.972718253968254, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9789186507936508, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9828869047619048, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9853670634920635, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.986359126984127, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9871031746031746, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9871031746031746, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9875992063492064, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.988343253968254, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9880952380952381, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9888392857142857, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.988343253968254, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9888392857142857, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9903273809523809, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9903273809523809, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9910714285714286, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9913194444444444, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9915674603174603, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9915674603174603, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9925595238095238, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9918154761904762, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9913194444444444, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9923115079365079, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9925595238095238, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9918154761904762, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9918154761904762, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9903273809523809, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9875992063492064, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9866071428571429, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9885912698412699, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9846230158730159, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9861111111111112, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9861111111111112, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9841269841269841, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9841269841269841, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9861111111111112, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9866071428571429, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9831349206349206, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9836309523809523, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9799107142857143, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9754464285714286, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.7362689603705376, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.818686596870661, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.8621005421112232, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.8900027195107097, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.9129576074059965, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.9324683637137444, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.9510355583505614, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9702919532799894, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9774008127890568, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.981346412078897, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9836104320020033, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9841124795090321, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9846937930680004, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.985058493966188, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9858760183643402, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9865901520950112, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9860597225316001, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9871808711052383, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9868253110094491, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9871848509240044, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9890027501339215, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9885929903750097, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9900306288803546, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9901959628417661, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9903267158874763, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9901575700216018, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9914150882578158, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.99037928998916, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9900759264497995, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9909760541929754, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9912153241917003, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9907801327712672, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9905678235437889, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9907965952219804, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9889762033804838, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9858320035430933, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9852324094629484, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9860936977495962, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9803572288801231, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9841141398210821, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.983426058310297, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9826126256842544, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9839404463389348, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9843261544876382, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9846175873220909, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9805747500376748, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9803500024630034, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9743693448349359, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9726253095422088, "id_best": 26, "lr_best": 0.00041999999999999996, "wd_best": 0.05, "train/loss_best": 0.014677190678194165, "validation/loss_best": 0.024788077920675278, "validation/acc_best": 0.9925595238095238, "validation/f1_best": 0.9914150882578158} +{"epoch": 9, "train/lr": 0.00023803200426111704, "train/loss": 0.18122161578387022, "train/grad": 0.17482992207631468, "train/loss_000_lr2.0e-02_wd1.0e+00": 1.1038532257080078, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.9628186416625977, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.7706924962997437, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.6175730443000793, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.49354307651519774, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.36111181139945986, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.25943666100502016, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.18305625528097152, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.11743252743035555, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.08733078403398395, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.07504246779717505, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.06585027186200022, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.06056877288967371, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.05532328178174794, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.05159783056937158, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.04858996659517288, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.0452381366956979, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.04170612257905305, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.03811356987804174, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.035032191090285776, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.03152335811406374, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.02808637390844524, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.024548914544284345, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.021079051680862902, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.017700569182634355, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.013930690083652735, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.010868183439597487, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.008481040187180043, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.005617585396394133, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0029368769191205502, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0020024419482797384, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.0011663693748414517, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.001069086939096451, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.00038214008323848246, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.005382142765447497, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.0030826716870069504, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.014807823486626149, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.009940792424604297, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.02205429458990693, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.028946110568940638, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.0263771911803633, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.05474882839247584, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.08018108972348273, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.05308561056852341, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.132893284894526, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.21357854476198554, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.27316653755493464, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.8070803725812584, "train/loss_048_lr5.0e+01_wd1.0e+00": 1.5112302551791073, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.018645075708627702, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.017489914456382392, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.01589302809443325, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.014606465599499643, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.013468312034383416, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.011944144209846854, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.010390469254925847, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.008917647446505726, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.007224201321369037, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.006405280294129625, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.00614772689237725, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.00600698827940505, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.0059415361849823965, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.0058729534241138024, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.00582745858002454, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.0057712785096373405, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.005694356731837615, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.005576380714192055, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.005432332212803885, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.005273088498797734, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.005060639919829555, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.004825541870959568, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.004550946552044479, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.004241458145261276, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0038804285832156893, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.003382014336602879, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.002904055094186333, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0024922676096684883, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0019323383585287957, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0012250566687362152, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0009472882223872148, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0005693555908192139, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.00042150831086701146, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.00023334423184451225, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0014009473567807617, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.001555267214017988, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.003922535038150059, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.004062839414987475, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0056489321631020915, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.007465544139281534, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0072673970195465945, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.011484199707817045, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.014012347740115484, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.011715259398705359, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.019014652664401298, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0371013682911802, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.04487694058730454, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.06788739081372733, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.09673054184761018, "validation/loss_000_lr2.0e-02_wd1.0e+00": 1.0436569452285767, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.9045547246932983, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.7157540917396545, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.5655114054679871, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.4447473883628845, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.31919237971305847, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.22447821497917175, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.15189078450202942, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.09481478482484818, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.07178868353366852, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.06163876876235008, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.05346821993589401, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.04877951741218567, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.0444999597966671, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.04149535298347473, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.03914628550410271, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.0367639996111393, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.03436918929219246, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.03220533952116966, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.030648700892925262, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.029093096032738686, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.02786725014448166, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.026646088808774948, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.02588847652077675, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.02508004941046238, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.024475790560245514, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.024582892656326294, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.025081194937229156, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.026191556826233864, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.024737577885389328, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.025904294103384018, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.02640565298497677, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.026753190904855728, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.02639213390648365, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.03964294493198395, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.04234451428055763, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.05932564288377762, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.07404939830303192, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.1813972145318985, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.1976141482591629, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.2596084475517273, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.2968032658100128, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.5020878911018372, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.46832236647605896, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.948758065700531, "validation/loss_045_lr3.1e+01_wd1.0e+00": 1.3939533233642578, "validation/loss_046_lr3.6e+01_wd1.0e+00": 1.8598966598510742, "validation/loss_047_lr4.3e+01_wd1.0e+00": 1.8875149488449097, "validation/loss_048_lr5.0e+01_wd1.0e+00": 2.7570960521698, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.8596230158730159, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.8849206349206349, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.9097222222222222, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.923859126984127, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9347718253968254, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.9506448412698413, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9694940476190477, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.9776785714285714, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9828869047619048, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9848710317460317, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9866071428571429, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9871031746031746, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9866071428571429, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9875992063492064, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9880952380952381, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9890873015873016, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9890873015873016, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9893353174603174, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9900793650793651, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9900793650793651, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9903273809523809, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9903273809523809, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9900793650793651, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9905753968253969, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9923115079365079, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9923115079365079, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9918154761904762, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9913194444444444, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9915674603174603, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9930555555555556, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9925595238095238, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9925595238095238, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9918154761904762, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9918154761904762, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9908234126984127, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9888392857142857, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9903273809523809, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9868551587301587, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9885912698412699, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.986359126984127, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9851190476190477, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9861111111111112, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9885912698412699, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9853670634920635, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9848710317460317, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9841269841269841, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9821428571428571, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9836309523809523, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.8212991146654164, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.8612570985234395, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.8966281071668301, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.91526776982523, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.9292884685178603, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.9460514583861181, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.9663267035035109, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9766781165657367, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9809530389825734, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9827331285068952, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9845423112113613, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.984943894043852, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9847575027271956, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9859299317764748, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9866959665127717, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9876528333805968, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9876525188535293, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9878318711122767, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9883728323405969, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9888101033108095, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9890714449735034, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9884447560627763, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9879968543392494, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9885315038776848, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9901142612338893, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9900230654790715, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9895744646226938, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9892767932814015, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9902482898403707, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9914632526185395, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9911057302867637, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9906079692906515, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9909102490787428, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9904348494840965, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9902170532115206, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9884978965168972, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9879104970403412, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9883488152663619, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.98509684906027, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9861546825210423, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9839367935138272, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9821671195415824, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9841969165546199, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9871545728620881, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9838720165489792, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9821120491302248, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9810662362367495, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9776791627421412, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9800664254407162, "id_best": 29, "lr_best": 0.0006899999999999999, "wd_best": 0.05, "train/loss_best": 0.0029368769191205502, "validation/loss_best": 0.024737577885389328, "validation/acc_best": 0.9930555555555556, "validation/f1_best": 0.9914632526185395} +{"epoch": 10, "train/lr": 0.00021091808096876188, "train/loss": 0.13409193977713585, "train/grad": 0.1311626504175365, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.9988339805603027, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.8618959140777588, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.6766103315353393, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.5300556707382202, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.41432532072067263, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.2977846205234528, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.21093840271234512, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.14382174782454968, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.09715621592476964, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.0789619138278067, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.0704260582756251, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.06315639946609736, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.058618886340409515, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.0539642487000674, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.05047747320495546, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.047603671066462995, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.04429746366105974, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.040925611220300195, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.03735851984471083, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.03428284524008632, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.030599181028082966, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.026962919384241103, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.023034599237143995, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.019008523719385266, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.014995635617524386, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.010658266814425587, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.007474309364333749, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.005342288725078106, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.00312220212072134, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0016618502885103225, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0008824420534074306, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.0005215548351407051, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.00032598129473626614, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.0002060004696249962, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.0014030612632632256, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.0017365530133247376, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.00552321532741189, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.011372604249045253, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.010305947763845325, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.011491675116121768, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.033069915967062116, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.021255200877785683, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.038457299629226324, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.015236427057534457, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.10454770304262638, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.1369109620433301, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.09903081616386772, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.41625636311247943, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.7076164017245173, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.01769431752152741, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.01658699276857078, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.015107229417189956, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.013896369449794293, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.012762235524132848, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.011244005511980504, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.009752035555429757, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.008142197075067088, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.006709116342826746, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.00622906913398765, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.006046681083971634, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.0059088547702413055, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.005823388017597608, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.005719268387765624, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.005620612695347518, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.005530092424014583, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.005403420754009858, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.005249687707691919, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.0050601801573066044, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.004890790321223903, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.004665040399559075, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.004410866654943675, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.004107964084105333, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0037504728593921754, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.003349740500852931, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0028397491513896967, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.002319262357596017, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0018519373048911803, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0012289515676093287, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0007335242969202227, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0004188461630292295, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0002218684400395432, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.00013302114295356659, "train/grad_033_lr4.3e+00_wd1.0e+00": 9.444887271797597e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0005032742616828045, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0009765583486359475, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0026782060406488916, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0033761808061832464, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0038352611907920874, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0050767876133050085, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0061737813996362145, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.006444287479123767, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.007031057054436829, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.006483882566870946, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.01739555333642639, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.021909833937620173, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.023629779346203864, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.03987418584211121, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.06828851222139598, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.9501323103904724, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.8142716288566589, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.6312516331672668, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.4872603118419647, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.3750167489051819, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.2644135355949402, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.18161354959011078, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.11815395206212997, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.07950891554355621, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.06437626481056213, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.05681697651743889, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.050151195377111435, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.04618306830525398, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.042316023260354996, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.039525121450424194, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.03745447099208832, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.035251449793577194, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.03318597376346588, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.03141194209456444, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.03004336729645729, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.028586754575371742, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.027542835101485252, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.026685846969485283, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.026005852967500687, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.02518252469599247, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.024326350539922714, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.023541025817394257, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.02327987365424633, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.023983832448720932, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.024605456739664078, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.025098389014601707, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.02618948556482792, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.026673760265111923, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.026158781722187996, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.03528188541531563, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.042831648141145706, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.07420720160007477, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.10449610650539398, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.1461406946182251, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.14144057035446167, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.26152303814888, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.2498309165239334, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.4619511365890503, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.36857858300209045, "validation/loss_044_lr2.6e+01_wd1.0e+00": 1.111637830734253, "validation/loss_045_lr3.1e+01_wd1.0e+00": 1.8218363523483276, "validation/loss_046_lr3.6e+01_wd1.0e+00": 1.8535449504852295, "validation/loss_047_lr4.3e+01_wd1.0e+00": 1.5723198652267456, "validation/loss_048_lr5.0e+01_wd1.0e+00": 2.2220160961151123, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.8754960317460317, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.8948412698412699, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.9159226190476191, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.9308035714285714, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9417162698412699, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.9625496031746031, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9739583333333334, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.980406746031746, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9846230158730159, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9858630952380952, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9866071428571429, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9873511904761905, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9880952380952381, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9885912698412699, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9888392857142857, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9885912698412699, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9885912698412699, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9890873015873016, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9888392857142857, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9890873015873016, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9900793650793651, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9900793650793651, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9905753968253969, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9903273809523809, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9908234126984127, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9913194444444444, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9910714285714286, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9918154761904762, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9918154761904762, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9928075396825397, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9928075396825397, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9923115079365079, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9903273809523809, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9895833333333334, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9893353174603174, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9898313492063492, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9873511904761905, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9888392857142857, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.986359126984127, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9893353174603174, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9853670634920635, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9821428571428571, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9841269841269841, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9831349206349206, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9841269841269841, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.847459940753578, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.8748163804876466, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.905155787290104, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.9244536482023362, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.9358710084594423, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.9586215043898187, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.9720821822925737, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9782452982243262, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.982376942985712, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.983807198977085, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9845423112113613, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9851228775732472, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9861607690737001, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.986715497218759, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9868906839715477, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9866671238910284, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9865450317817357, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9871808129948453, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9872921411951643, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9875520123403457, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9882775179342141, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9882931778955608, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9891826074925415, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9886374499385854, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9889200663331608, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9893220038645499, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9891974658032916, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9894552337132927, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9901710674559112, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.989855228003482, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9899753320836695, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9898757404872983, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9911934709546484, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9915968040457939, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9910933351112208, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9897005090838594, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.987245879482024, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.987448301457425, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9882702656887965, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9894490699281704, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9862523925129147, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9861575498376829, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9862087369740588, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9871450935928922, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9832274694651675, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9790741797287306, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9797980060641303, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9786664615912369, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9816493546612962, "id_best": 32, "lr_best": 0.0011099999999999999, "wd_best": 0.05, "train/loss_best": 0.00032598129473626614, "validation/loss_best": 0.026673760265111923, "validation/acc_best": 0.9928075396825397, "validation/f1_best": 0.9911934709546484} +{"epoch": 11, "train/lr": 0.00018113997589164516, "train/loss": 0.10571247614920139, "train/grad": 0.09354434641078115, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.9113676261901855, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.7783757400512695, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.5996071219444274, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.4604569244384766, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.3543368375301361, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.2517870873212814, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.1739272490143776, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.11641886707395316, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.08460836004465819, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.07181133189238607, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.06523259640671313, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.059114730600267645, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.05504247454926372, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.05055566870607436, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.04702434278093279, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.044063254185020925, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.040639225672930476, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.03701648190617561, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.03323289853520692, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.029966499609872698, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.026071725487709044, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.02225132253021002, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.018314141435548662, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.014382634898647667, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.010613883761689067, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.006763177942484617, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.004278947114944458, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.002784414887428284, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.001497176606208086, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0008460185863077641, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0005301749240607023, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.0003956097271293402, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.00026074660941958425, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.00017997142858803273, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.0002286900207400322, "train/loss_035_lr6.0e+00_wd1.0e+00": 8.98138526827097e-05, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.0027955888956785204, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.003307067034766078, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.004141163863241672, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.006433227658271789, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.013858252726495266, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.017698586452752352, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.009626809544861316, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.014128075037151576, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.06836937388405204, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.02711643185466528, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.11735587070696056, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.18408847379498183, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.3369187664333731, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.01692251218482852, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.01577666456345469, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.0142116161249578, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.012851838488131762, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.01153365707024932, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.009900800460018217, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.008399704995099455, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.006987021758686751, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.006175569688202813, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.005945770114194602, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.005871090292930603, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.005809557230677455, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.005760536265443079, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.005687956744804978, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.0056032224994851275, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.005519040394574404, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.005402542037190869, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.005240926084807143, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.005034032436669804, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.004828353310003876, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.004542618327541277, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.004226982687541749, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0038637447985820474, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0034498053065908606, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0029721669800346715, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.002292187471903162, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.001689114849032194, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.001219207673184428, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0007004173145105597, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0003762481099329307, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.00023291232043447962, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.00016852957945957315, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.00011490004515962937, "train/grad_033_lr4.3e+00_wd1.0e+00": 8.519442969600278e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.000173850691094799, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.00011806173977603862, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.002201857847368056, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0012970169969107315, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.001661294700630889, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.00249189509612574, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.003915701166812336, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.003708208627189941, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.003378359082344877, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.003843595798228953, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.011590087585126103, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.01142200496960147, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.016800694017889202, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.025216670979482565, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.03997170212190947, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.8781159520149231, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.7454518675804138, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.5672429800033569, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.42919546365737915, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.3254593014717102, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.22636300325393677, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.15038995444774628, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.09770836681127548, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.07093603163957596, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.05953584983944893, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.05345407873392105, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.04793289303779602, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.044390685856342316, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.040850669145584106, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.038404881954193115, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.03640665486454964, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.03441280499100685, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.03259086608886719, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.030971450731158257, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.029881324619054794, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.028637712821364403, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.02784877084195614, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.027091937139630318, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.026503542438149452, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.025806566700339317, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.024813147261738777, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.024248212575912476, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.024271760135889053, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.024560531601309776, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.02518319897353649, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.025608496740460396, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.0263983067125082, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.026879841461777687, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.02628212235867977, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.036224115639925, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.03808198124170303, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.06476067751646042, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.09162348508834839, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.1887667030096054, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.14656485617160797, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.2131929099559784, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.21129110455513, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.3379538655281067, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.3465513288974762, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.6885005831718445, "validation/loss_045_lr3.1e+01_wd1.0e+00": 1.0754952430725098, "validation/loss_046_lr3.6e+01_wd1.0e+00": 1.4478260278701782, "validation/loss_047_lr4.3e+01_wd1.0e+00": 1.5217410326004028, "validation/loss_048_lr5.0e+01_wd1.0e+00": 2.0030157566070557, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.8856646825396826, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.9007936507936508, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.9203869047619048, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.9340277777777778, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9486607142857143, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.9682539682539683, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9784226190476191, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.982390873015873, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9853670634920635, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9868551587301587, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9871031746031746, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9875992063492064, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9880952380952381, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9890873015873016, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9895833333333334, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9893353174603174, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9895833333333334, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9895833333333334, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9893353174603174, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9903273809523809, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9903273809523809, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9910714285714286, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9918154761904762, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9920634920634921, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9925595238095238, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9918154761904762, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9925595238095238, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9925595238095238, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9933035714285714, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9928075396825397, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9928075396825397, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9923115079365079, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9923115079365079, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9925595238095238, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9893353174603174, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9908234126984127, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9866071428571429, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9900793650793651, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.988343253968254, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9878472222222222, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.988343253968254, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9895833333333334, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9888392857142857, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9888392857142857, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9856150793650794, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.982390873015873, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9821428571428571, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.8623798664976299, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.8841764497007227, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.9116476111370065, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.9282604295307941, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.9442738029158039, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.9645709196905105, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.976872591253093, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9805067340983608, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9838106369796551, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9847658458158032, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.984946948000769, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9854767788921408, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9863319107189555, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9874668928962012, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9880042382447566, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9876518975046916, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9878353530961169, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9878986433733536, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.987718218134427, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9888090747519881, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9892235728565384, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9901239374720282, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.990839900006141, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9910176704652246, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9913755925564325, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9917919329009212, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9903402541616521, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9905207732239977, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9911862200479017, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9912361683464294, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9918192710343651, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9909984999236785, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9912373942167805, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9912472099272455, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9912526218916901, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.991413196665428, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9872705305673906, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9883296314047906, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9849609121314382, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9892189271358922, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9865670907572911, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9853630606771795, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9875153313870333, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9865012636777625, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9873063306573717, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9874473464933557, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9820171754817503, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9803778328239268, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9803266494754749, "id_best": 30, "lr_best": 0.00081, "wd_best": 0.05, "train/loss_best": 0.0005301749240607023, "validation/loss_best": 0.025608496740460396, "validation/acc_best": 0.9933035714285714, "validation/f1_best": 0.9918192710343651} +{"epoch": 12, "train/lr": 0.0001499999999999999, "train/loss": 0.08713228212669492, "train/grad": 0.06319542119279503, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.8582456159591675, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.7273020315170288, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.5520384454727173, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.41784107863903047, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.3187676852941513, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.22466490179300308, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.1512932872772217, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.10366578515619039, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.0803882315941155, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.07020785399712622, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.06448499794118107, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.05886282795108855, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.05497712046839297, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.050532152270898224, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.04694045288488269, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.04388511311262846, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.04042684089392424, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.036718818731606005, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.03295723511837423, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.029622998712584378, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.025730077559128404, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.021773569379001857, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.01756866170093417, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.01321090042591095, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.009253389583900571, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.00556430303491652, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.0034528972022235395, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.002249717153608799, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.001285816188901663, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0007248194795101881, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0004900899901986122, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.0003769066836684942, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.0002534417249262333, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.00017731474712491036, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.00010950753465294839, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.95679846405983e-05, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.0002981957141309977, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.00027666983194649217, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.000835268534719944, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.0015573321189731358, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.002100872304290533, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.006147943278774619, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.0007171435095369816, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.005584010789170861, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.015172126032412052, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.0044599795527756215, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.0221880086325109, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.06535785682499409, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.07870204949751497, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.016483668833971024, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.015413158442825078, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.013933059079572558, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.01257970045786351, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.011277610855177044, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.009720045072026551, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.008117454601451754, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.006770098540000618, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.006193585126893595, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.006014872522791847, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.005928750260500238, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.005835711106192321, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.00575682504742872, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.005629043994122185, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.0054997540765907614, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.005367256324971095, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.005203564320108853, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.005007104054675438, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.004788933498202823, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.004579776628524997, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.004301500302972272, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.003984628719335887, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0036039172604796477, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0031341414373309818, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0025858865382906515, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.001864607838797383, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0012874985353118972, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0008665772286985885, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.000492280456746812, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0002775554260369972, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.00018761435574560892, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.00014094509097049013, "train/grad_032_lr3.7e+00_wd1.0e+00": 9.735685748637479e-05, "train/grad_033_lr4.3e+00_wd1.0e+00": 7.390611899154464e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 5.837538692503586e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 2.837697009965723e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.00018515479329007657, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0002177605672213761, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0005592408543186418, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0007745457893071647, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0020880504833430654, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0016030419693149748, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0011633570101952514, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0027766955450844754, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0034458016070364377, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.004345154791927212, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.007077750804841826, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.013068470110858023, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.014328064622124865, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.8230906128883362, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.692971408367157, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.519209086894989, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.38697171211242676, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.2906252443790436, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.19946864247322083, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.12869925796985626, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.0862407386302948, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.06580003350973129, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.056453198194503784, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.05120640993118286, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.04621042311191559, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.04299010708928108, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.03966977819800377, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.03725278005003929, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.03543538600206375, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.03355465084314346, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.031721606850624084, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.030178166925907135, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.02901332639157772, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.027986884117126465, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.027178237214684486, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.026388855651021004, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.02597394399344921, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.025417180731892586, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.024698717519640923, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.02411048486828804, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.024108687415719032, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.024536045268177986, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.02494226209819317, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.02550172433257103, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.02642262727022171, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.026954252272844315, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.026308048516511917, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.034303076565265656, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.03713518753647804, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.05418361350893974, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.08256905525922775, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.1640430986881256, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.14723588526248932, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.17432723939418793, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.18311463296413422, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.2520764172077179, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.3104550242424011, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.6220282912254333, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.9696143865585327, "validation/loss_046_lr3.6e+01_wd1.0e+00": 1.2574646472930908, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.9475606083869934, "validation/loss_048_lr5.0e+01_wd1.0e+00": 1.4597352743148804, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.8955853174603174, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.9107142857142857, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.9283234126984127, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.9407242063492064, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9543650793650794, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.9714781746031746, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9799107142857143, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.9828869047619048, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9858630952380952, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9868551587301587, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9871031746031746, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9873511904761905, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9880952380952381, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9888392857142857, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9888392857142857, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9888392857142857, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9888392857142857, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9898313492063492, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9903273809523809, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9903273809523809, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9900793650793651, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9905753968253969, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9910714285714286, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9908234126984127, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9915674603174603, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9925595238095238, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9928075396825397, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9925595238095238, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9915674603174603, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9923115079365079, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9925595238095238, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9928075396825397, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9933035714285714, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9925595238095238, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9928075396825397, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9900793650793651, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9913194444444444, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9873511904761905, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9898313492063492, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9895833333333334, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9915674603174603, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9873511904761905, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9893353174603174, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9878472222222222, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9880952380952381, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9853670634920635, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.988343253968254, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9831349206349206, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.8756937763607946, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.8995081824671864, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.9214336786511458, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.9351275993072182, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.9494027696785501, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.9688309407650357, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.9783335762287616, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9809408636334871, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9838860709826714, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9848449625626374, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9850239339375007, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9856520822631009, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9864581763300538, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9873649074580696, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9875442937729522, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9875442937729522, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9871933437424083, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9881145473578676, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.988670624592602, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.988710497550259, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9884674063376427, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9892781623728206, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9896809052522589, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9893245046744344, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9902195451598879, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9912847894770377, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9911505148359231, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9910695942162091, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9899350648207582, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9906071955173403, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9904603041949843, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9907316334323193, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9912373942167805, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9923158767372874, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9914778016222257, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9915769594453115, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9881177438540324, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9889999604958252, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.985685423432228, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9893793249957192, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9869230734273637, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9904956508727144, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9874256088662333, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9861027610047753, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9857564215183675, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9853701292550784, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9835245511424879, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9862027415284502, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9817397964923473, "id_best": 33, "lr_best": 0.00129, "wd_best": 0.05, "train/loss_best": 0.00017731474712491036, "validation/loss_best": 0.026308048516511917, "validation/acc_best": 0.9933035714285714, "validation/f1_best": 0.9923158767372874} +{"epoch": 13, "train/lr": 0.00011886002410835478, "train/loss": 0.07691698534414172, "train/grad": 0.051643322724848985, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.8013864660263061, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.6721670722961426, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.5008109855651856, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.3725096136331558, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.28083090752363205, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.19460293918848037, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.12798539601266384, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.09052510144189001, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.0727490248158574, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.06428954106755555, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.059377133827656504, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.054283701526001094, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.05060506917536259, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.046287265131250026, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.042731112567707896, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.039709123419597744, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.036160090491175655, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.03241793121211231, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.028534053545445203, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.025250871097669006, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.021514510037377477, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.01790695630013943, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.014104992570355534, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.010298435706645251, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.006868657032027841, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.003941866466775536, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.0023871287889778614, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.001569388573989272, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0009326840937137604, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0005456426460295915, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0003766847588121891, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.00029913147911429403, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.0002044986840337515, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.00014987070113420487, "train/loss_034_lr5.1e+00_wd1.0e+00": 8.34872666746378e-05, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.7202630192041394e-05, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.3253586366772652e-05, "train/loss_037_lr8.3e+00_wd1.0e+00": 6.393089890480041e-05, "train/loss_038_lr9.8e+00_wd1.0e+00": 4.6849995851516726e-05, "train/loss_039_lr1.2e+01_wd1.0e+00": 4.83661238104105e-05, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.0008331142086535692, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.0017761116195470095, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.0014949793741106986, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.0002873175032436848, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.002055531730875373, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.006162332808598876, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.00447563249617815, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.03448974178172648, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.04275066524744034, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.015940719568170607, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.014873976823873819, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.01338499845471233, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.01201709819259122, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.01075336312642321, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.00927368029486388, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.007668587935622782, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.006552615351974964, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.006119338218122721, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.005965151956770569, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.0058799283800181, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.0057906219724100086, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.005714682411635295, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.005582770344917662, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.0054508810507832095, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.005302340577472932, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.005110535379208159, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.0048747592867584896, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.004596836252312641, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.004334639997687191, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.004012585228338139, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.003663736515591154, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0032582904815353685, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.00277296821877826, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0021791526158631315, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0014426978436677018, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0009387280475493754, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0006247554274887079, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0003724695718938165, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.00021913951658461884, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0001532530146459976, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.00011907833390750966, "train/grad_032_lr3.7e+00_wd1.0e+00": 8.714665244951902e-05, "train/grad_033_lr4.3e+00_wd1.0e+00": 6.630865415104381e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 4.7323217870598455e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 2.4908934824701135e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 1.3859708365335787e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 4.3405644542729785e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 8.599713431649698e-05, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.00029020942959138844, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.00044163825594087207, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0003415325177665687, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0005187451632175166, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0002991316904165957, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0009631136764754969, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.001958386134588641, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0030575527310396293, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.007280315181481929, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.011570667333797026, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.782444179058075, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.6544905304908752, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.4842849671840668, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.35684049129486084, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.2661217451095581, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.18004149198532104, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.11418618261814117, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.07932157069444656, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.06250409036874771, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.05434880405664444, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.049563150852918625, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.04496175795793533, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.041947778314352036, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.038800813257694244, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.03657318279147148, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.034908272325992584, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.033154960721731186, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.03154074028134346, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.0300596896559, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.028970040380954742, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.027809705585241318, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.026789601892232895, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.025599276646971703, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.024552837014198303, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.024052467197179794, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.023805825039744377, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.023927314206957817, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.02436291053891182, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.02480425126850605, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.025156455114483833, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.0256198700517416, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.026218106970191002, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.026884904131293297, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.026133393868803978, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.03366844356060028, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.036643121391534805, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.05283275991678238, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.07885955274105072, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.1657623052597046, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.13786624372005463, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.13766223192214966, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.14863614737987518, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.24185994267463684, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.2807532548904419, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.5658935308456421, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.8918709754943848, "validation/loss_046_lr3.6e+01_wd1.0e+00": 1.0659608840942383, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.7274268269538879, "validation/loss_048_lr5.0e+01_wd1.0e+00": 1.3425856828689575, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.9020337301587301, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.9146825396825397, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.9308035714285714, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.9444444444444444, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9603174603174603, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.9742063492063492, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9811507936507936, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.9833829365079365, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9868551587301587, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9871031746031746, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9873511904761905, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9868551587301587, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9875992063492064, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9880952380952381, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.988343253968254, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.988343253968254, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9895833333333334, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9898313492063492, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9905753968253969, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9905753968253969, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9903273809523809, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9910714285714286, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9913194444444444, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9915674603174603, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9928075396825397, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9923115079365079, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9923115079365079, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9930555555555556, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9925595238095238, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9925595238095238, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9923115079365079, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9925595238095238, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9905753968253969, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9915674603174603, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9873511904761905, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9908234126984127, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9900793650793651, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9923115079365079, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9888392857142857, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9890873015873016, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9880952380952381, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9888392857142857, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9871031746031746, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9893353174603174, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9853670634920635, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.884961414316261, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.9037135454632916, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.924827535566578, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.9397420572484311, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.9560006238424291, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.9718525231402673, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.9792915102940124, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9815131860060944, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9848878020765012, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9850653510589763, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9856033702339314, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9851625341423484, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9860644793343609, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9864737755690077, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9866577689980225, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9866581365058129, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9877364692674115, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9883538503506806, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.988940127127845, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.988940127127845, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9886037746083881, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9892334108192534, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9894129673919112, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9895917240347023, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9904914428596566, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9905029217962819, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9910736388194233, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.990348815824805, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9901688025692763, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9908326414212931, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9903831061788815, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.991091739502332, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9910104207305127, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9917883529381222, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9911320504982816, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9913979175763897, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9885228469503483, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9892214982202967, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9854525572478714, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9897644014016991, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9885182441386856, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9910744802612497, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9881533112470128, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9859220173203193, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9859374209630991, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9868050953115806, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9843278760756723, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9884426210240846, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9829933924256478, "id_best": 31, "lr_best": 0.0009299999999999999, "wd_best": 0.05, "train/loss_best": 0.00029913147911429403, "validation/loss_best": 0.026218106970191002, "validation/acc_best": 0.9930555555555556, "validation/f1_best": 0.991091739502332} +{"epoch": 14, "train/lr": 8.9081919031238e-05, "train/loss": 0.07301871841773391, "train/grad": 0.042244804594665765, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.7718936252593994, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.6455990409851075, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.47859206557273865, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.3551721960306168, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.26815649747848513, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.18520523220300675, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.12224744684994221, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.09009360257536173, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.07433718726970255, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.06633857913315296, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.06138012637384236, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.056169274542480704, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.05237929669208825, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.04786451860330999, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.04416729759424925, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.040980113493278625, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.03726375635713339, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.0332697176001966, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.029139643376693128, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.02549782975576818, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.021342139998450874, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.017343473620712757, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.013164399499073625, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.009247871693223714, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.0060214497894048695, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.00341956558637321, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.0020414176117628815, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0013427511788904668, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0008174983132630587, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0005141422804445028, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0003686567768454552, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.00029406022280454636, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.0002038709819316864, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.0001524363365024328, "train/loss_034_lr5.1e+00_wd1.0e+00": 8.738654665648937e-05, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.881294280290604e-05, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.1962838470935822e-05, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.2455862015485763e-05, "train/loss_038_lr9.8e+00_wd1.0e+00": 7.120519876480102e-07, "train/loss_039_lr1.2e+01_wd1.0e+00": 6.158817559480667e-06, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.803979441523552e-06, "train/loss_041_lr1.6e+01_wd1.0e+00": 4.287436604499817e-07, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.6325945034623145e-05, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.000454459311440587, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.0028937841765582562, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.438538871705532e-05, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.0020828828401863574, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.005566412936896086, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.004687509695068002, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.01588802275247872, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.014815266486257314, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.013287113038823009, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.01186047799885273, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.010576554720755667, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.009037968486081809, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.0073620230914093554, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.006448646559147164, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.0061483144492376594, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.00603434735618066, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.005968059233273379, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.005882570430403575, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.0057982598466333, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.005663664295279886, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.00552172422001604, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.005372879674832802, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.0051724043244030325, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.004928011807496659, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.004633613515470643, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.004345438506279606, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.003987916667247191, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.003616984484979184, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0031647566809260754, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0026079771432705456, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0019521607782371575, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0012583739118053926, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0008010880711299251, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0005278981205265154, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.00031473959783397733, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.00020150767579707463, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.000144454097153357, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.00011309210570743744, "train/grad_032_lr3.7e+00_wd1.0e+00": 8.245109577842413e-05, "train/grad_033_lr4.3e+00_wd1.0e+00": 6.462326961582222e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 4.4445557211361116e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 2.3544500479815157e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 1.2280314420119177e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 1.3255536523006711e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 1.6353229130949133e-06, "train/grad_039_lr1.2e+01_wd1.0e+00": 1.2277676337852134e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 3.25249962233041e-05, "train/grad_041_lr1.6e+01_wd1.0e+00": 1.8295499485068727e-06, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.00015051097456548134, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0003137629475659907, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0012951559612725874, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0003647183250475515, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0016359387641581447, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0026127361402426587, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.00040293925819437956, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.7531792521476746, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.6268767714500427, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.4594784677028656, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.33613425493240356, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.24940866231918335, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.16655893623828888, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.10505641996860504, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.07518180459737778, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.060391832143068314, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.05283952131867409, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.04844387620687485, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.0440903939306736, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.04111175611615181, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.0380144938826561, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.03592058643698692, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.03417600691318512, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.03247428312897682, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.03080912120640278, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.029439548030495644, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.028331713750958443, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.027280716225504875, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.026423344388604164, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.025638693943619728, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.024860486388206482, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.024472340941429138, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.024192074313759804, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.024276787415146828, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.024404773488640785, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.024809183552861214, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.02522258460521698, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.025705667212605476, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.02645195834338665, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.027043547481298447, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.026364337652921677, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.03329826518893242, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.03620061278343201, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.051722414791584015, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.07681156694889069, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.16081872582435608, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.130504310131073, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.13276304304599762, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.14224398136138916, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.2577718496322632, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.25638246536254883, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.5468993186950684, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.7937759757041931, "validation/loss_046_lr3.6e+01_wd1.0e+00": 1.0072274208068848, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.644316554069519, "validation/loss_048_lr5.0e+01_wd1.0e+00": 1.103520154953003, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.9047619047619048, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.9169146825396826, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.9325396825396826, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.9476686507936508, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9642857142857143, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.9756944444444444, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9826388888888888, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.9838789682539683, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9866071428571429, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9871031746031746, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9875992063492064, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9878472222222222, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9885912698412699, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9888392857142857, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9885912698412699, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9885912698412699, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9888392857142857, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9890873015873016, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9895833333333334, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9893353174603174, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9893353174603174, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9903273809523809, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9908234126984127, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9918154761904762, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9913194444444444, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9913194444444444, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9915674603174603, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9918154761904762, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9918154761904762, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9923115079365079, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9928075396825397, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9925595238095238, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9925595238095238, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9928075396825397, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9905753968253969, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9915674603174603, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9873511904761905, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9905753968253969, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9900793650793651, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9923115079365079, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9890873015873016, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9895833333333334, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.988343253968254, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9888392857142857, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9868551587301587, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9888392857142857, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9861111111111112, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.8891356732833833, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.9073946387894248, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.9268211190394685, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.9425936965126102, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.9603484386097966, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.9734866039958047, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.9805913811229109, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9819175317227437, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9848378564128213, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9850239339375007, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9858313802890726, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9864718397404117, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9870081845609727, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9871874877484801, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9871848528060164, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9870126417417898, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9874703093654909, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9877234830198124, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9879924143762915, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9878286967674581, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9874637284733064, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9885109252070678, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9889602625492453, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9902141499931413, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9894572714741893, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9894572714741893, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9896776738203541, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9899440421240724, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9901576924019172, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9903366779787304, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9904603041949843, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9909116944495844, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9910587206633584, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9913712120714164, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9909068707677458, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9916223286574622, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9885228469503483, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9892214982202967, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9854525572478714, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9895854682399674, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9885182441386856, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9910744802612497, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9881611307678094, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9862838413176188, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9865617227034336, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9867249444270844, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9846960217184786, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9872302558936781, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9841666838875889, "id_best": 31, "lr_best": 0.0009299999999999999, "wd_best": 0.05, "train/loss_best": 0.00029406022280454636, "validation/loss_best": 0.02645195834338665, "validation/acc_best": 0.9928075396825397, "validation/f1_best": 0.9909116944495844} +{"epoch": 15, "train/lr": 6.196799573888289e-05, "train/loss": 0.0676993983052671, "train/grad": 0.03914949960075319, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.7413810396194458, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.6157099676132202, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.45056950449943545, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.3304953867197037, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.24720275074243545, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.16742528550326824, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.10886081799864769, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.08123464414849878, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.06739898951724171, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.06016583312302828, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.05563748516142368, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.050813289526849985, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.047193797044456004, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.0428670219797641, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.03942391795106232, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.03640130713582039, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.03293269953690469, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.029240204505622387, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.02540706536732614, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.022112167244777083, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.018337236912921072, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.014678803654387593, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.011046968251466751, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.0076720855291932824, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.004935157196596265, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.002776069613173604, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.0016635755728930234, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.001113460063934326, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0006954629719257355, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0004430752899497747, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.00031644019298255444, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.000249804025515914, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.00017508413642644883, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.00013189546763896941, "train/loss_034_lr5.1e+00_wd1.0e+00": 8.201810531318188e-05, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.7189051508903506e-05, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.227816566824913e-05, "train/loss_037_lr8.3e+00_wd1.0e+00": 9.994106367230415e-06, "train/loss_038_lr9.8e+00_wd1.0e+00": 8.531752973794937e-07, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.3014843463897703e-06, "train/loss_040_lr1.4e+01_wd1.0e+00": 4.5765470713377e-06, "train/loss_041_lr1.6e+01_wd1.0e+00": 9.652040898799897e-07, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.084655523300171e-06, "train/loss_043_lr2.2e+01_wd1.0e+00": 1.1383555829524994e-07, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.8126686811447143e-06, "train/loss_045_lr3.1e+01_wd1.0e+00": 1.0477378964424133e-08, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.0, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.0004080450814217329, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.646127879619598e-08, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.015545822763815522, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.014498559199273587, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.012972888853400946, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.011527038458734751, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.010218814120162279, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008647094578482211, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.007092837822856381, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.0063457254029344766, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.006065548156620935, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.005952892938512378, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.0058876877737930045, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.005794319453998469, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.005704467969480902, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.005560374977067113, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.005423271986946929, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.00526304795028409, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.005061108838126529, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.004821688008814817, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.0045497142433305274, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.004285473936470226, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.0039512147223285865, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.0035734797790064475, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.00308521277642285, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0024675275753543247, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0017887951230659382, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0011195375803072238, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0006966495904271141, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.00046600757883425104, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.00028811005569878034, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.00018449796130425966, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.00013311107449226256, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.00010541217979607608, "train/grad_032_lr3.7e+00_wd1.0e+00": 7.623310465646682e-05, "train/grad_033_lr4.3e+00_wd1.0e+00": 5.9002316273222274e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 4.127991804011799e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 2.4148223157034464e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 1.2184976617809345e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 1.2535751026060833e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 1.6799769586978023e-06, "train/grad_039_lr1.2e+01_wd1.0e+00": 5.093308395383865e-06, "train/grad_040_lr1.4e+01_wd1.0e+00": 9.24088391685317e-06, "train/grad_041_lr1.6e+01_wd1.0e+00": 1.7343773158112192e-06, "train/grad_042_lr1.9e+01_wd1.0e+00": 2.613565054857837e-05, "train/grad_043_lr2.2e+01_wd1.0e+00": 5.483466670947545e-07, "train/grad_044_lr2.6e+01_wd1.0e+00": 1.325640916394054e-05, "train/grad_045_lr3.1e+01_wd1.0e+00": 1.488382591579079e-07, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0004926667157391397, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0006831062928574024, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0003013164597248399, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.7332833409309387, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.6082575917243958, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.4428231418132782, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.3222753703594208, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.2381819486618042, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.15723706781864166, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.09910565614700317, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.072443388402462, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.05886834114789963, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.05197411775588989, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.04774409160017967, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.043564390391111374, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.04075050726532936, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.0377051904797554, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.03551097586750984, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.033790796995162964, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.03205632418394089, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.03029461018741131, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.028841687366366386, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.02768087200820446, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.02652856335043907, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.025569643825292587, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.024712707847356796, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.023974604904651642, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.02359868213534355, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.023617161437869072, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.023857994005084038, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.02431408129632473, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.02486921288073063, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.025266652926802635, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.025738373398780823, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.02644791267812252, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.026996087282896042, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.026292169466614723, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.033194102346897125, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.035672325640916824, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.05079521983861923, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.07537015527486801, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.1574401557445526, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.12758569419384003, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.1298236846923828, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.1369018703699112, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.24138367176055908, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.24480843544006348, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.5246456265449524, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.7513110041618347, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.8762533068656921, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.5861005187034607, "validation/loss_048_lr5.0e+01_wd1.0e+00": 1.0530575513839722, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.9055059523809523, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.9188988095238095, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.9340277777777778, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.9486607142857143, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9650297619047619, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.9766865079365079, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9821428571428571, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.984375, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9868551587301587, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9868551587301587, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9873511904761905, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9875992063492064, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9885912698412699, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.988343253968254, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9885912698412699, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9885912698412699, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9885912698412699, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9898313492063492, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9900793650793651, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9900793650793651, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9905753968253969, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9908234126984127, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9913194444444444, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9920634920634921, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9930555555555556, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9928075396825397, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9925595238095238, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9923115079365079, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9923115079365079, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9925595238095238, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9928075396825397, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9925595238095238, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9918154761904762, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9925595238095238, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9905753968253969, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9915674603174603, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9873511904761905, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9905753968253969, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9900793650793651, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9923115079365079, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9893353174603174, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9895833333333334, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.988343253968254, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9888392857142857, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9873511904761905, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9890873015873016, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9866071428571429, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.8903688477763344, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.9086662230518947, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.9286589782384254, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.9435978541311358, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.9608035050786082, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.9750066601005639, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.9803919499858131, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9822836570126734, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9848449625626374, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9848419086057204, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9856520822631009, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9859258014128548, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9870081845609727, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.986828858763683, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9870125495180323, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9870126417417898, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9869227700160812, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9883071230939061, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9884865306389414, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9883340772154054, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9887832624917724, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9893211892612263, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9900387491075425, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9907550685097777, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9907551028604118, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9916880910767525, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9915648006875992, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9914317070548319, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9906957607365957, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9908777516994706, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9904603041949843, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9906411316790215, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9912373942167805, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9913712120714164, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9903657982382787, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9913979175763897, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9885228469503483, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9890984888564424, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9854510329749686, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9895854682399674, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9884700789121216, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9910744802612497, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9883340658725521, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9862838413176188, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9865617227034336, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9867249444270844, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9846682975510729, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9871833386848536, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9846655800315935, "id_best": 25, "lr_best": 0.00035999999999999997, "wd_best": 0.05, "train/loss_best": 0.002776069613173604, "validation/loss_best": 0.023617161437869072, "validation/acc_best": 0.9930555555555556, "validation/f1_best": 0.9916880910767525} +{"epoch": 16, "train/lr": 3.870405029380728e-05, "train/loss": 0.06748578712344169, "train/grad": 0.03861984224058688, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.7312719058990479, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.6068867182731629, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.44320140838623046, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.32485789895057676, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.2430240261554718, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.1643336985260248, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.108345942273736, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.08306727832183242, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.07012508303858339, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.06319168491289019, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.058633627723902466, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.05368446353822946, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.04995069492608309, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.04542744849808514, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.041725939884781835, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.03846070173196495, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.03480027507059276, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.0308175057079643, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.026665537459775804, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.02310076423920691, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.01900494928471744, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.01510922479443252, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.011147663500159978, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.007539966432377696, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.004682828551158309, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.0025857362151145936, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.0015948948916047812, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0010784519743174314, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0006837986875325441, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.00043737124651670455, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0003180304355919361, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.0002560000214725733, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.00018423382192850113, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.00013695142231881619, "train/loss_034_lr5.1e+00_wd1.0e+00": 8.64340178668499e-05, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.5840030759572985e-05, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.2183710932731628e-05, "train/loss_037_lr8.3e+00_wd1.0e+00": 9.748470038175583e-06, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.3050436973571777e-06, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.068363294005394e-06, "train/loss_040_lr1.4e+01_wd1.0e+00": 4.206588491797447e-06, "train/loss_041_lr1.6e+01_wd1.0e+00": 7.845833897590638e-07, "train/loss_042_lr1.9e+01_wd1.0e+00": 8.70702788233757e-07, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.4623779356479643e-07, "train/loss_044_lr2.6e+01_wd1.0e+00": 1.037316396832466e-06, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.6170164346694947e-09, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.7939677238464354e-11, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.00031511100009083747, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.2351741790771484e-10, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.015557563374750316, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.014514424628578127, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.01298882553819567, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.011530756400898099, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.010255270234774799, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008703093775548041, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.007146320353494957, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.0064222831616643815, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.006150307835196145, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.006033940576598979, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.005947555515449494, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.005848167413496412, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.005739850327954627, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.005574172169144731, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.00540060115599772, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.0052200342630385425, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.004984640864277026, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.004696080537687521, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.004364493008615682, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.0040528621098928855, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.0036630596932809567, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.00324795593318413, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0027408001158255504, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.002138286542867718, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0015055532116093674, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.000926063588285615, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0006004724950798845, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.00041156535702612017, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0002637754990610119, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.00017320033068244812, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.00012693384161138965, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.00010168581559810263, "train/grad_032_lr3.7e+00_wd1.0e+00": 7.546747531705477e-05, "train/grad_033_lr4.3e+00_wd1.0e+00": 5.862190059758632e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 4.105386108676612e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 2.1879907879309713e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 1.1746724126514563e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 1.3409331168888761e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 1.7367780441854094e-06, "train/grad_039_lr1.2e+01_wd1.0e+00": 6.859792130279636e-06, "train/grad_040_lr1.4e+01_wd1.0e+00": 6.90159364538851e-06, "train/grad_041_lr1.6e+01_wd1.0e+00": 2.000406453322699e-06, "train/grad_042_lr1.9e+01_wd1.0e+00": 4.2216820535916955e-06, "train/grad_043_lr2.2e+01_wd1.0e+00": 6.575118619589446e-07, "train/grad_044_lr2.6e+01_wd1.0e+00": 3.656511968545483e-06, "train/grad_045_lr3.1e+01_wd1.0e+00": 8.100408379137213e-07, "train/grad_046_lr3.6e+01_wd1.0e+00": 3.514881858310032e-10, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0005131550617170881, "train/grad_048_lr5.0e+01_wd1.0e+00": 8.389658121185473e-08, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.7212244272232056, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.5966310501098633, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.43264976143836975, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.3136654794216156, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.23128901422023773, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.1516818106174469, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.09590087831020355, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.07090699672698975, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.05810609832406044, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.051395613700151443, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.04733092337846756, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.04323349893093109, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.04045668989419937, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.03758905827999115, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.035489730536937714, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.03383312001824379, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.032090723514556885, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.030581846833229065, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.029079651460051537, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.028098387643694878, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.026976915076375008, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.02598113939166069, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.0251242034137249, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.02442854829132557, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.024084754288196564, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.02402595616877079, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.024230878800153732, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.024556107819080353, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.02507109008729458, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.02538393996655941, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.025794319808483124, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.026545995846390724, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.027057763189077377, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.02635117992758751, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.03302620351314545, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.035548970103263855, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.05066360533237457, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.07438276708126068, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.1552530974149704, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.12569351494312286, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.1275908201932907, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.13476870954036713, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.23608320951461792, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.23710514605045319, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.5098965167999268, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.7252221703529358, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.8448910117149353, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.5778427124023438, "validation/loss_048_lr5.0e+01_wd1.0e+00": 1.0059759616851807, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.9067460317460317, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.9203869047619048, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.9350198412698413, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.9506448412698413, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9670138888888888, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.9781746031746031, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9818948412698413, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.9846230158730159, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9866071428571429, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9871031746031746, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9873511904761905, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9878472222222222, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9885912698412699, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9880952380952381, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9885912698412699, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9888392857142857, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9895833333333334, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9900793650793651, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9903273809523809, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9898313492063492, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9903273809523809, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9908234126984127, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9913194444444444, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9915674603174603, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9910714285714286, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9928075396825397, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9923115079365079, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9925595238095238, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9925595238095238, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9925595238095238, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9925595238095238, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9905753968253969, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9915674603174603, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9873511904761905, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9905753968253969, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9898313492063492, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9923115079365079, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9893353174603174, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9898313492063492, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9885912698412699, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9890873015873016, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9875992063492064, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9878472222222222, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9866071428571429, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.8928125852743385, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.9111507621128319, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.9297652052728835, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.9458800853709901, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.9628548621174629, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.9763590267587468, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.9802131616776212, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9824605536556891, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9846638603776716, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9850208921351157, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9856520822631009, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9866015339018984, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9871409429933994, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9866524520775131, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9870125495180323, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9871946021840815, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9878204913928909, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9887082190542151, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9888585505915655, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9883651791440842, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9888573945470247, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9895005858022912, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9898538298242666, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9900341934014721, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9903923501361828, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9893327778587528, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9906721934981165, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9915684885694352, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.990697112905769, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9906071955173403, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9904603041949843, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9906411316790215, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9910587206633584, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9913712120714164, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9905458515353807, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9914423820062855, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9885228469503483, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9890984888564424, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9854510329749686, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9895854682399674, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9882450255798907, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9910744802612497, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9883340658725521, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9865544389172756, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9868315016853157, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9872631845346727, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9848473491456294, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9860243662450847, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9846655800315935, "id_best": 27, "lr_best": 0.00047999999999999996, "wd_best": 0.05, "train/loss_best": 0.0010784519743174314, "validation/loss_best": 0.024556107819080353, "validation/acc_best": 0.9928075396825397, "validation/f1_best": 0.9915684885694352} +{"epoch": 17, "train/lr": 2.030750443206766e-05, "train/loss": 0.06659290205687285, "train/grad": 0.037145194597542286, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.7230736494064331, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.5991469502449036, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.43648998260498045, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.31927506268024447, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.23837708055973053, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.16010974831879138, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.10533665258437395, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.0810037337616086, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.06855182398110628, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.06170616012997925, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.05739939434453845, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.05277550455182791, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.04930881282314658, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.04515161570161581, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.04174632123671472, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.03882172462530434, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.035399423809722066, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.03162397325970232, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.02759657216258347, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.024011717420071365, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.01979524677619338, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.015645185317844153, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.011430321503430605, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.007549912966787815, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.004560014801099897, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.0024896463099867107, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.001523522837087512, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.001037743641063571, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.00066184027120471, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0004258637968450785, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.00031120765954256057, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.00024813253432512286, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.0001797455921769142, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.00013544505462050437, "train/loss_034_lr5.1e+00_wd1.0e+00": 8.31135269254446e-05, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.6529814824461934e-05, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.2506945058703422e-05, "train/loss_037_lr8.3e+00_wd1.0e+00": 8.885487914085388e-06, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.014508306980133e-06, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.922937273979187e-06, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.2508203983306886e-06, "train/loss_041_lr1.6e+01_wd1.0e+00": 8.281785994768143e-07, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.112641766667366e-06, "train/loss_043_lr2.2e+01_wd1.0e+00": 1.4443323016166686e-06, "train/loss_044_lr2.6e+01_wd1.0e+00": 1.2167636305093765e-06, "train/loss_045_lr3.1e+01_wd1.0e+00": 5.504116415977478e-09, "train/loss_046_lr3.6e+01_wd1.0e+00": 1.9557774066925048e-10, "train/loss_047_lr4.3e+01_wd1.0e+00": 4.954170435667038e-07, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.021249383687973e-07, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.015019295918755234, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.014004258457571268, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.012547490349970759, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.011175649336073547, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.009949895876925439, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.00836575981695205, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.006838446396868676, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.006189877273282036, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.005954211937496439, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.0058467754145385695, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.005770176236401312, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.005669057744671591, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.0055685398861533035, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.005404431217466481, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.005242008425993845, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.005081230502692051, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.004865824854059611, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.004612377848243341, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.004310212503187358, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.004030966085992987, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.0036599222183576786, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.0032415744224272205, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0026973335226648486, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0020404408375179627, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0014008348113566172, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0008535855769878254, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0005488183123088674, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0003796484550912282, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.00024675275511981454, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0001620289014226728, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0001195707875649532, "train/grad_031_lr3.1e+00_wd1.0e+00": 9.60800815391849e-05, "train/grad_032_lr3.7e+00_wd1.0e+00": 7.016584843995588e-05, "train/grad_033_lr4.3e+00_wd1.0e+00": 5.4965692796713484e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 3.882982087873188e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 2.1368163273862705e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 1.1829895318599127e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 1.37177770796975e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 1.3585059059219567e-06, "train/grad_039_lr1.2e+01_wd1.0e+00": 5.265830500449708e-06, "train/grad_040_lr1.4e+01_wd1.0e+00": 6.144871773281927e-06, "train/grad_041_lr1.6e+01_wd1.0e+00": 1.989151762236699e-06, "train/grad_042_lr1.9e+01_wd1.0e+00": 4.68365102327643e-06, "train/grad_043_lr2.2e+01_wd1.0e+00": 2.302776819845031e-06, "train/grad_044_lr2.6e+01_wd1.0e+00": 3.3699194645200782e-06, "train/grad_045_lr3.1e+01_wd1.0e+00": 6.3986880351595464e-06, "train/grad_046_lr3.6e+01_wd1.0e+00": 6.959000336186547e-10, "train/grad_047_lr4.3e+01_wd1.0e+00": 1.8222320232759956e-06, "train/grad_048_lr5.0e+01_wd1.0e+00": 5.590503252428855e-07, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.7148544192314148, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.5907482504844666, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.4275250732898712, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.309428870677948, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.22772760689258575, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.14886604249477386, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.09425733983516693, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.07016952335834503, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.05774985998868942, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.05117765814065933, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.04714600369334221, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.043072137981653214, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.04024559259414673, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.0373343788087368, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.03512120246887207, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.033469878137111664, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.031647711992263794, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.030195554718375206, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.028691288083791733, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.027714485302567482, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.02659056894481182, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.02563326805830002, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.02481798455119133, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.02419748529791832, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.023871194571256638, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.02396245114505291, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.024159308522939682, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.024464165791869164, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.02503523789346218, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.025393815711140633, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.025801576673984528, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.02637500874698162, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.027003208175301552, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.02635723538696766, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.03298446163535118, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.03542549908161163, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.050284359604120255, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.07408701628446579, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.1539659947156906, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.12488306313753128, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.12686766684055328, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.1333528608083725, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.2339329868555069, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.2335558980703354, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.5014761090278625, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.7108690142631531, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.8311368227005005, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.566002607345581, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.9836417436599731, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.9072420634920635, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.9208829365079365, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.9350198412698413, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.9508928571428571, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9675099206349206, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.9779265873015873, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9826388888888888, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.9848710317460317, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9866071428571429, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9873511904761905, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9878472222222222, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9875992063492064, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9888392857142857, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9888392857142857, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9888392857142857, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9885912698412699, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9885912698412699, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9893353174603174, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9898313492063492, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9895833333333334, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9903273809523809, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9908234126984127, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9910714285714286, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9915674603174603, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9923115079365079, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9925595238095238, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9923115079365079, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9923115079365079, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9925595238095238, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9925595238095238, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9925595238095238, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9918154761904762, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9928075396825397, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9908234126984127, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9918154761904762, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9873511904761905, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9908234126984127, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9900793650793651, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9923115079365079, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9895833333333334, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9900793650793651, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9888392857142857, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9890873015873016, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9873511904761905, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9878472222222222, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9866071428571429, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.8941336527261893, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.9122734855943836, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.9298396987426143, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.9464489929938367, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.9636691477738916, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.9761771221690021, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.9807494450266002, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9830822492116856, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9846638603776716, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9852907036505458, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9860587836355685, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9860693849116577, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9871874877484801, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9871874877484801, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9871874877484801, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9870126417417898, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9872896073648724, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9879470431003319, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9883245890900431, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.988010738415151, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9886055728475305, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.989322985154633, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9894963123833529, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9900341934014721, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9903923501361828, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9906826161065095, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9908508965665825, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9910302635823273, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9908758083409774, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9906071955173403, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9904603041949843, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9906411316790215, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9910587206633584, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9913712120714164, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9903657982382787, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9916223286574622, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9890639899612251, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9893691149588186, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9854525572478714, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9897635723625834, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9884700789121216, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9910744802612497, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9885149313433782, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9870940203919509, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9871020797419635, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9872631845346727, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9846682975510729, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9860243662450847, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9846655800315935, "id_best": 35, "lr_best": 0.0018, "wd_best": 0.05, "train/loss_best": 3.6529814824461934e-05, "validation/loss_best": 0.03542549908161163, "validation/acc_best": 0.9928075396825397, "validation/f1_best": 0.9916223286574622} +{"epoch": 18, "train/lr": 7.5829098008590064e-06, "train/loss": 0.0639276290871203, "train/grad": 0.037326512783765795, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.7084330654144287, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.586181640625, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.42597315073013303, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.31061380088329316, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.23087923020124435, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.15350948378443718, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.09989472674205899, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.07619516772218049, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.06386542079970241, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.05719453174620867, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.052918501384556296, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.04833063473924994, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.04488201569765806, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.04077475808560848, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.03746666688472033, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.034619426745921375, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.03132986154407263, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.027798991668969392, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.024109368193894625, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.02094126828946173, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.01715627282857895, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.013462257916107773, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.009690990084782242, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.006311424160376191, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.003819814696907997, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.002112214155495167, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.001303840270265937, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0008930347859859467, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0005650156177580357, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.00036170619539916516, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.00026123606599867346, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.0002107978519052267, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.00014979150146245956, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.00011348220519721508, "train/loss_034_lr5.1e+00_wd1.0e+00": 7.083915174007416e-05, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.8891563415527345e-05, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.0253051295876502e-05, "train/loss_037_lr8.3e+00_wd1.0e+00": 9.131841361522674e-06, "train/loss_038_lr9.8e+00_wd1.0e+00": 7.771607488393784e-07, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.4618860334157942e-06, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.65537591278553e-06, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.8494203686714174e-07, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.8741190433502197e-06, "train/loss_043_lr2.2e+01_wd1.0e+00": 7.30091705918312e-07, "train/loss_044_lr2.6e+01_wd1.0e+00": 8.379667997360229e-07, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.194289118051529e-07, "train/loss_046_lr3.6e+01_wd1.0e+00": 7.450580596923828e-11, "train/loss_047_lr4.3e+01_wd1.0e+00": 4.402920603752136e-07, "train/loss_048_lr5.0e+01_wd1.0e+00": 4.097819328308106e-09, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.015202155783772469, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.014165127258747816, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.0126726418081671, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.011277258801274002, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.01005174730438739, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008468558597378432, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.00690388515824452, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.006240887579042465, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.005990286651067436, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.00587130357103888, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.005791969184065238, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.005677929993253201, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.005563621051551309, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.005385362824308686, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.005208810480835382, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.005031085147929843, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.0048017155451816505, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.004520022041397169, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.004210606609121897, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.00392039646874764, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.003541348182989168, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.0031177729716728208, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.002582132649840787, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0019457025299561793, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0013386002699371602, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0008158642060334387, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0005222077383132273, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0003610843282422138, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.00023356814901489997, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.00015477797809580805, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.00011437949179708084, "train/grad_031_lr3.1e+00_wd1.0e+00": 9.136816634963907e-05, "train/grad_032_lr3.7e+00_wd1.0e+00": 6.710198626365127e-05, "train/grad_033_lr4.3e+00_wd1.0e+00": 5.3244158707457245e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 3.755957657972431e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 2.0209994268896025e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 1.1010028322937514e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 1.1486926851639254e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 1.5938824614532068e-06, "train/grad_039_lr1.2e+01_wd1.0e+00": 5.474879251807706e-06, "train/grad_040_lr1.4e+01_wd1.0e+00": 6.819200620343153e-06, "train/grad_041_lr1.6e+01_wd1.0e+00": 1.6613700865780845e-06, "train/grad_042_lr1.9e+01_wd1.0e+00": 5.180633282531268e-06, "train/grad_043_lr2.2e+01_wd1.0e+00": 1.6059420640137919e-06, "train/grad_044_lr2.6e+01_wd1.0e+00": 2.3242410193177644e-06, "train/grad_045_lr3.1e+01_wd1.0e+00": 7.992064430361156e-07, "train/grad_046_lr3.6e+01_wd1.0e+00": 7.375402973785984e-10, "train/grad_047_lr4.3e+01_wd1.0e+00": 1.9553015635678335e-06, "train/grad_048_lr5.0e+01_wd1.0e+00": 4.0427101478756015e-07, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.7123851180076599, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.5884056091308594, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.42536571621894836, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.30764299631118774, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.22645583748817444, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.1477515548467636, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.0936630368232727, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.06980383396148682, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.05758340656757355, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.050995271652936935, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.04702026769518852, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.04299333319067955, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.04022476077079773, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.03721065819263458, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.035065729171037674, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.0334257148206234, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.03168777748942375, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.030155165120959282, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.028786303475499153, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.027655022218823433, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.026584245264530182, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.0256329458206892, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.024810824543237686, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.024216454476118088, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.023900920525193214, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.023948566988110542, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.024138571694493294, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.024582231417298317, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.0250814501196146, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.025465069338679314, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.025821303948760033, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.02647070400416851, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.02705502323806286, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.02636956050992012, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.03297848254442215, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.03540773689746857, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.050396669656038284, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.07389654219150543, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.15381821990013123, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.1246890127658844, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.12629376351833344, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.1323530524969101, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.23319470882415771, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.23155666887760162, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.49924883246421814, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.706369936466217, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.8248035311698914, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.5623641014099121, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.975218653678894, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.910218253968254, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.9206349206349206, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.9362599206349206, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.9518849206349206, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.96875, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.9779265873015873, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9826388888888888, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.9853670634920635, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9868551587301587, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9871031746031746, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9873511904761905, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9878472222222222, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9885912698412699, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9888392857142857, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.988343253968254, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9885912698412699, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9888392857142857, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9895833333333334, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9898313492063492, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9900793650793651, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9903273809523809, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9905753968253969, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9913194444444444, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9920634920634921, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9913194444444444, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9928075396825397, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9923115079365079, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9923115079365079, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9925595238095238, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9925595238095238, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9925595238095238, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9918154761904762, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9928075396825397, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9908234126984127, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9915674603174603, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9873511904761905, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9908234126984127, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9898313492063492, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9923115079365079, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9895833333333334, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9900793650793651, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9888392857142857, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9890873015873016, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9873511904761905, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9878472222222222, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9868551587301587, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.8974321698034311, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.9114772684753409, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.9311150823331945, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.947185583102596, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.9653021711667131, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.9761771221690021, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.9807494450266002, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9834441049157758, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9848449625626374, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9850208921351157, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9856520822631009, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9862996897182503, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9870081845609727, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9871874877484801, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.986828858763683, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9870126417417898, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9874703093654909, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9881710075650021, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9883245890900431, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9883357808740605, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9886055728475305, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9887785897371283, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9896757825204471, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9903923501361828, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9903923501361828, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9895984565571493, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9906246125126317, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9912542433326595, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9906957607365957, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9908777516994706, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9904603041949843, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9906411316790215, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9910587206633584, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9913712120714164, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9903657982382787, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9916223286574622, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9890639899612251, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9890984888564424, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9854510329749686, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9897635723625834, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9882450255798907, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9910744802612497, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9885149313433782, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9870940203919509, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9871020797419635, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9872631845346727, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9846682975510729, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9860243662450847, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9852068278745142, "id_best": 27, "lr_best": 0.00047999999999999996, "wd_best": 0.05, "train/loss_best": 0.0008930347859859467, "validation/loss_best": 0.024582231417298317, "validation/acc_best": 0.9928075396825397, "validation/f1_best": 0.9912542433326595} +{"epoch": 19, "train/lr": 1.0867618231465446e-06, "train/loss": 0.06424415593966842, "train/grad": 0.03685081993229687, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.7098186445236206, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.5870042037963867, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.4260683763027191, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.31030205607414246, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.23062170416116715, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.15372046411037446, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.10079850483685732, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.07763142194598913, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.06552427029237151, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.05888223921880126, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.054578100526705385, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.04987152483314276, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.04634419813752175, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.04194029251113534, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.038386539248749615, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.03532386960461736, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.03177636888809502, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.027965286867693066, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.02414315761998296, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.020855408823117615, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.017079325756058097, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.013372082933783532, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.00955860142596066, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.006191636826843023, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.003821802493184805, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.002164881955832243, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.001359730428084731, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.000939644780009985, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0006042884755879641, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.00039171033538877966, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0002856410015374422, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.00022632393054664135, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.00016284643672406673, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.00012167073786258698, "train/loss_034_lr5.1e+00_wd1.0e+00": 7.04581942409277e-05, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.7135107666254042e-05, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.1587487533688545e-05, "train/loss_037_lr8.3e+00_wd1.0e+00": 6.213830783963204e-06, "train/loss_038_lr9.8e+00_wd1.0e+00": 6.574392318725586e-07, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.8035230934619906e-06, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.636591136455536e-06, "train/loss_041_lr1.6e+01_wd1.0e+00": 9.191036224365234e-07, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.4495756477117539e-06, "train/loss_043_lr2.2e+01_wd1.0e+00": 1.2089498341083526e-06, "train/loss_044_lr2.6e+01_wd1.0e+00": 6.246566772460938e-07, "train/loss_045_lr3.1e+01_wd1.0e+00": 1.9798986613750458e-07, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.421438694000244e-10, "train/loss_047_lr4.3e+01_wd1.0e+00": 6.7148357629776e-09, "train/loss_048_lr5.0e+01_wd1.0e+00": 1.9557774066925048e-10, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.014913203902542591, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.01388556970283389, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.012406664113514125, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.011019545895978809, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.009784410337451845, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008247576532885431, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.0068063793051987885, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.006240035271039232, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.006035490029025823, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.0059391856472939255, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.005858783638686873, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.005746454739128239, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.005623008374532219, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.00543032176909037, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.005247839905787259, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.00506844743504189, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.004838160760409664, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.004568884638283635, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.004266855492751347, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.003970010856573935, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.0035795077416696584, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.003146899928251514, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.002614611427707132, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.001969279854747583, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0013550558152928716, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.000823015209298319, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0005309108726123668, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.00036879023377878184, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.00023793738256244979, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.00015588761622666424, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.00011514079052631132, "train/grad_031_lr3.1e+00_wd1.0e+00": 9.182821779518235e-05, "train/grad_032_lr3.7e+00_wd1.0e+00": 6.787890573491496e-05, "train/grad_033_lr4.3e+00_wd1.0e+00": 5.431230514318486e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 3.7042321191051995e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 2.0388347862070335e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 1.1299746160735592e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 1.2485319849413478e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 1.595940469007136e-06, "train/grad_039_lr1.2e+01_wd1.0e+00": 6.090764172362226e-06, "train/grad_040_lr1.4e+01_wd1.0e+00": 8.085431485446194e-06, "train/grad_041_lr1.6e+01_wd1.0e+00": 1.948949004842427e-06, "train/grad_042_lr1.9e+01_wd1.0e+00": 5.565307825326968e-06, "train/grad_043_lr2.2e+01_wd1.0e+00": 3.1343482716036834e-06, "train/grad_044_lr2.6e+01_wd1.0e+00": 3.0976658424026375e-06, "train/grad_045_lr3.1e+01_wd1.0e+00": 5.734994123131902e-06, "train/grad_046_lr3.6e+01_wd1.0e+00": 7.103068204175076e-10, "train/grad_047_lr4.3e+01_wd1.0e+00": 1.3857125658364722e-06, "train/grad_048_lr5.0e+01_wd1.0e+00": 5.367382240788702e-07, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.7120277881622314, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.5881382822990417, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.4251425266265869, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.30745482444763184, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.22627100348472595, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.14759410917758942, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.09356851875782013, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.06978132575750351, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.05757196992635727, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.05098383501172066, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.047064781188964844, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.04294455796480179, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.04021006077528, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.03724529221653938, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.03507613763213158, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.03341025114059448, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.03169345483183861, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.030141113325953484, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.028724782168865204, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.02764362283051014, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.02658195048570633, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.025645535439252853, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.02480757050216198, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.024169165641069412, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.023939695209264755, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.023953866213560104, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.0240944791585207, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.02457532472908497, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.025082383304834366, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.025483161211013794, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.02582501992583275, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.02649759314954281, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.02700880356132984, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.0263542328029871, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.03298892080783844, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.03544091433286667, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.05047561973333359, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.07382453233003616, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.15370704233646393, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.12464354187250137, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.12621696293354034, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.1322946697473526, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.23244769871234894, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.23189304769039154, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.4981585741043091, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.7049674391746521, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.8246630430221558, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.5618327260017395, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.9747623205184937, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.9104662698412699, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.9211309523809523, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.9360119047619048, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.9516369047619048, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9689980158730159, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.9779265873015873, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9826388888888888, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.9853670634920635, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9868551587301587, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9871031746031746, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9873511904761905, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9880952380952381, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9885912698412699, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9888392857142857, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.988343253968254, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9885912698412699, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9888392857142857, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9895833333333334, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9900793650793651, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9903273809523809, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9903273809523809, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9905753968253969, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9913194444444444, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9920634920634921, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9915674603174603, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9925595238095238, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9918154761904762, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9923115079365079, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9923115079365079, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9925595238095238, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9925595238095238, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9925595238095238, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9918154761904762, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9928075396825397, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9908234126984127, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9915674603174603, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9873511904761905, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9908234126984127, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9898313492063492, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9923115079365079, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9895833333333334, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9900793650793651, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9888392857142857, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9890873015873016, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9873511904761905, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9878472222222222, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9868551587301587, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.897716615728506, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.9120184842608697, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.9308406302837194, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.947007417539324, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.9655737341387118, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.9760888160797487, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.9807494450266002, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9834441049157758, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9848449625626374, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9850208921351157, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9856520822631009, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9866511629569892, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9870081845609727, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9871874877484801, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.986828858763683, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9870126417417898, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9874703093654909, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9881710075650021, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9885041098626324, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9885589941576207, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9886055728475305, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9887785897371283, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9896757825204471, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9903923501361828, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9903923501361828, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9899642013435235, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9906246125126317, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9910752094896937, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9905170736176462, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9908777516994706, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9904603041949843, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9906411316790215, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9910587206633584, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9913712120714164, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9903657982382787, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9916223286574622, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9890639899612251, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9890984888564424, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9854510329749686, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9897635723625834, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9882450255798907, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9910744802612497, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9885149313433782, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9870940203919509, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9871020797419635, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9872631845346727, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.984668286669754, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9860243662450847, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9852068278745142, "id_best": 35, "lr_best": 0.0018, "wd_best": 0.05, "train/loss_best": 2.7135107666254042e-05, "validation/loss_best": 0.03544091433286667, "validation/acc_best": 0.9928075396825397, "validation/f1_best": 0.9916223286574622} diff --git a/input_space_v3/flat_lr1e-3_5/eval_v2/nsd_cococlip__patch__attn/config.yaml b/input_space_v3/flat_lr1e-3_5/eval_v2/nsd_cococlip__patch__attn/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..354b6eba7bea0d08ce8634932f7cec2fc2e8fbbb --- /dev/null +++ b/input_space_v3/flat_lr1e-3_5/eval_v2/nsd_cococlip__patch__attn/config.yaml @@ -0,0 +1,96 @@ +output_root: experiments/input_space_v3/output +name_prefix: eval_probe +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_5; eval v2 (nsd_cococlip patch attn) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +dataset_kwargs: {} +classifier_kwargs: + embed_dim: null + dropout: 0.0 + xavier_init: true + norm: true +lr_scale_grid: +- 0.02 +- 0.023 +- 0.028 +- 0.033 +- 0.038 +- 0.045 +- 0.053 +- 0.062 +- 0.074 +- 0.087 +- 0.1 +- 0.12 +- 0.14 +- 0.17 +- 0.2 +- 0.23 +- 0.27 +- 0.32 +- 0.38 +- 0.44 +- 0.52 +- 0.61 +- 0.72 +- 0.85 +- 1 +- 1.2 +- 1.4 +- 1.6 +- 1.9 +- 2.3 +- 2.7 +- 3.1 +- 3.7 +- 4.3 +- 5.1 +- 6 +- 7.1 +- 8.3 +- 9.8 +- 12 +- 14 +- 16 +- 19 +- 22 +- 26 +- 31 +- 36 +- 43 +- 50 +wd_scale_grid: +- 1.0 +num_workers: 8 +prefetch_factor: null +balanced_sampling: false +epochs: 20 +steps_per_epoch: 200 +batch_size: 64 +accum_iter: 2 +lr: 0.0003 +warmup_epochs: 5 +no_decay: false +weight_decay: 0.05 +clip_grad: 1.0 +metrics: +- acc +- f1 +cv_metric: acc +early_stopping: true +amp: true +device: cuda +seed: 4466 +debug: false +wandb: false +wandb_entity: null +wandb_project: fMRI-fm-eval +name: input_space_v3/flat_lr1e-3_5/eval_v2/nsd_cococlip__patch__attn +model: flat_mae +representation: patch +classifier: attn +dataset: nsd_cococlip +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/eval_v2/nsd_cococlip__patch__attn +remote_dir: null diff --git a/input_space_v3/flat_lr1e-3_5/eval_v2/nsd_cococlip__patch__attn/eval_log.json b/input_space_v3/flat_lr1e-3_5/eval_v2/nsd_cococlip__patch__attn/eval_log.json new file mode 100644 index 0000000000000000000000000000000000000000..e6ad7dbdfbc71dfd4deda12171b76554fa4ccbe1 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_5/eval_v2/nsd_cococlip__patch__attn/eval_log.json @@ -0,0 +1 @@ +{"eval/epoch": 5, "eval/id_best": 25, "eval/lr_best": 0.00035999999999999997, "eval/wd_best": 0.05, "eval/train/loss": 2.035885810852051, "eval/train/acc": 0.38369341405697777, "eval/train/acc_std": 0.002323840240242684, "eval/train/f1": 0.32585344814976397, "eval/train/f1_std": 0.0024966679441346825, "eval/validation/loss": 2.3722212314605713, "eval/validation/acc": 0.2886674049464747, "eval/validation/acc_std": 0.005735408727237691, "eval/validation/f1": 0.22127566685655334, "eval/validation/f1_std": 0.005239730280838057, "eval/test/loss": 2.2694780826568604, "eval/test/acc": 0.30612244897959184, "eval/test/acc_std": 0.005497617114951402, "eval/test/f1": 0.2384996092204615, "eval/test/f1_std": 0.0053290126329661285, "eval/testid/loss": 2.2547659873962402, "eval/testid/acc": 0.3132832080200501, "eval/testid/acc_std": 0.0057233525271597925, "eval/testid/f1": 0.2496706562070913, "eval/testid/f1_std": 0.005458624008422905} diff --git a/input_space_v3/flat_lr1e-3_5/eval_v2/nsd_cococlip__patch__attn/eval_log_best.json b/input_space_v3/flat_lr1e-3_5/eval_v2/nsd_cococlip__patch__attn/eval_log_best.json new file mode 100644 index 0000000000000000000000000000000000000000..8568460f30a521f7eb6fa9d11e8c34b672c6f300 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_5/eval_v2/nsd_cococlip__patch__attn/eval_log_best.json @@ -0,0 +1 @@ +{"eval/best/epoch": 5, "eval/best/id_best": 25, "eval/best/lr_best": 0.00035999999999999997, "eval/best/wd_best": 0.05, "eval/best/train/loss": 2.035885810852051, "eval/best/train/acc": 0.38369341405697777, "eval/best/train/acc_std": 0.002323840240242684, "eval/best/train/f1": 0.32585344814976397, "eval/best/train/f1_std": 0.0024966679441346825, "eval/best/validation/loss": 2.3722212314605713, "eval/best/validation/acc": 0.2886674049464747, "eval/best/validation/acc_std": 0.005735408727237691, "eval/best/validation/f1": 0.22127566685655334, "eval/best/validation/f1_std": 0.005239730280838057, "eval/best/test/loss": 2.2694780826568604, "eval/best/test/acc": 0.30612244897959184, "eval/best/test/acc_std": 0.005497617114951402, "eval/best/test/f1": 0.2384996092204615, "eval/best/test/f1_std": 0.0053290126329661285, "eval/best/testid/loss": 2.2547659873962402, "eval/best/testid/acc": 0.3132832080200501, "eval/best/testid/acc_std": 0.0057233525271597925, "eval/best/testid/f1": 0.2496706562070913, "eval/best/testid/f1_std": 0.005458624008422905} diff --git a/input_space_v3/flat_lr1e-3_5/eval_v2/nsd_cococlip__patch__attn/eval_log_last.json b/input_space_v3/flat_lr1e-3_5/eval_v2/nsd_cococlip__patch__attn/eval_log_last.json new file mode 100644 index 0000000000000000000000000000000000000000..97699dabe06a36475c8d7f8a900ec77f1cf8bc23 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_5/eval_v2/nsd_cococlip__patch__attn/eval_log_last.json @@ -0,0 +1 @@ +{"eval/last/epoch": 19, "eval/last/id_best": 18, "eval/last/lr_best": 0.00011399999999999999, "eval/last/wd_best": 0.05, "eval/last/train/loss": 1.9935252666473389, "eval/last/train/acc": 0.40059620762776976, "eval/last/train/acc_std": 0.002503472253957788, "eval/last/train/f1": 0.34588870139823974, "eval/last/train/f1_std": 0.0026742730075012496, "eval/last/validation/loss": 2.4069631099700928, "eval/last/validation/acc": 0.28183831672203763, "eval/last/validation/acc_std": 0.005268241942360167, "eval/last/validation/f1": 0.2221281844274662, "eval/last/validation/f1_std": 0.005125457680941457, "eval/last/test/loss": 2.269773244857788, "eval/last/test/acc": 0.3111317254174397, "eval/last/test/acc_std": 0.005559893199527688, "eval/last/test/f1": 0.24160390893989905, "eval/last/test/f1_std": 0.005637711505287774, "eval/last/testid/loss": 2.2119102478027344, "eval/last/testid/acc": 0.32542895700790436, "eval/last/testid/acc_std": 0.005607381490322983, "eval/last/testid/f1": 0.2651684579608029, "eval/last/testid/f1_std": 0.005644312783821556} diff --git a/input_space_v3/flat_lr1e-3_5/eval_v2/nsd_cococlip__patch__attn/eval_table.csv b/input_space_v3/flat_lr1e-3_5/eval_v2/nsd_cococlip__patch__attn/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..c61fff3ac379f67973a959c1e1552bc2da472776 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_5/eval_v2/nsd_cococlip__patch__attn/eval_table.csv @@ -0,0 +1,5 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,patch,attn,nsd_cococlip,best,5,0.00035999999999999997,0.05,25,"[1.2, 1.0]",train,2.035885810852051,0.38369341405697777,0.002323840240242684,0.32585344814976397,0.0024966679441346825 +flat_mae,patch,attn,nsd_cococlip,best,5,0.00035999999999999997,0.05,25,"[1.2, 1.0]",validation,2.3722212314605713,0.2886674049464747,0.005735408727237691,0.22127566685655334,0.005239730280838057 +flat_mae,patch,attn,nsd_cococlip,best,5,0.00035999999999999997,0.05,25,"[1.2, 1.0]",test,2.2694780826568604,0.30612244897959184,0.005497617114951402,0.2384996092204615,0.0053290126329661285 +flat_mae,patch,attn,nsd_cococlip,best,5,0.00035999999999999997,0.05,25,"[1.2, 1.0]",testid,2.2547659873962402,0.3132832080200501,0.0057233525271597925,0.2496706562070913,0.005458624008422905 diff --git a/input_space_v3/flat_lr1e-3_5/eval_v2/nsd_cococlip__patch__attn/eval_table_best.csv b/input_space_v3/flat_lr1e-3_5/eval_v2/nsd_cococlip__patch__attn/eval_table_best.csv new file mode 100644 index 0000000000000000000000000000000000000000..c61fff3ac379f67973a959c1e1552bc2da472776 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_5/eval_v2/nsd_cococlip__patch__attn/eval_table_best.csv @@ -0,0 +1,5 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,patch,attn,nsd_cococlip,best,5,0.00035999999999999997,0.05,25,"[1.2, 1.0]",train,2.035885810852051,0.38369341405697777,0.002323840240242684,0.32585344814976397,0.0024966679441346825 +flat_mae,patch,attn,nsd_cococlip,best,5,0.00035999999999999997,0.05,25,"[1.2, 1.0]",validation,2.3722212314605713,0.2886674049464747,0.005735408727237691,0.22127566685655334,0.005239730280838057 +flat_mae,patch,attn,nsd_cococlip,best,5,0.00035999999999999997,0.05,25,"[1.2, 1.0]",test,2.2694780826568604,0.30612244897959184,0.005497617114951402,0.2384996092204615,0.0053290126329661285 +flat_mae,patch,attn,nsd_cococlip,best,5,0.00035999999999999997,0.05,25,"[1.2, 1.0]",testid,2.2547659873962402,0.3132832080200501,0.0057233525271597925,0.2496706562070913,0.005458624008422905 diff --git a/input_space_v3/flat_lr1e-3_5/eval_v2/nsd_cococlip__patch__attn/eval_table_last.csv b/input_space_v3/flat_lr1e-3_5/eval_v2/nsd_cococlip__patch__attn/eval_table_last.csv new file mode 100644 index 0000000000000000000000000000000000000000..1f25c98d3b4e226429663822007aa18daeea52e0 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_5/eval_v2/nsd_cococlip__patch__attn/eval_table_last.csv @@ -0,0 +1,5 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,patch,attn,nsd_cococlip,last,19,0.00011399999999999999,0.05,18,"[0.38, 1.0]",train,1.9935252666473389,0.40059620762776976,0.002503472253957788,0.34588870139823974,0.0026742730075012496 +flat_mae,patch,attn,nsd_cococlip,last,19,0.00011399999999999999,0.05,18,"[0.38, 1.0]",validation,2.4069631099700928,0.28183831672203763,0.005268241942360167,0.2221281844274662,0.005125457680941457 +flat_mae,patch,attn,nsd_cococlip,last,19,0.00011399999999999999,0.05,18,"[0.38, 1.0]",test,2.269773244857788,0.3111317254174397,0.005559893199527688,0.24160390893989905,0.005637711505287774 +flat_mae,patch,attn,nsd_cococlip,last,19,0.00011399999999999999,0.05,18,"[0.38, 1.0]",testid,2.2119102478027344,0.32542895700790436,0.005607381490322983,0.2651684579608029,0.005644312783821556 diff --git a/input_space_v3/flat_lr1e-3_5/eval_v2/nsd_cococlip__patch__attn/log.txt b/input_space_v3/flat_lr1e-3_5/eval_v2/nsd_cococlip__patch__attn/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..3c85cc6c8ff19d2220a6c6e549cd6a80e790e04e --- /dev/null +++ b/input_space_v3/flat_lr1e-3_5/eval_v2/nsd_cococlip__patch__attn/log.txt @@ -0,0 +1,961 @@ +fMRI foundation model probe eval +version: 0.1.dev86+gf97f52698 +sha: bcce2b486277d3a5b520775efd9cdf1a2affce36, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-04-08 20:31:09 +config: +output_root: experiments/input_space_v3/output +name_prefix: eval_probe +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_5; eval v2 (nsd_cococlip patch attn) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +dataset_kwargs: {} +classifier_kwargs: + embed_dim: null + dropout: 0.0 + xavier_init: true + norm: true +lr_scale_grid: +- 0.02 +- 0.023 +- 0.028 +- 0.033 +- 0.038 +- 0.045 +- 0.053 +- 0.062 +- 0.074 +- 0.087 +- 0.1 +- 0.12 +- 0.14 +- 0.17 +- 0.2 +- 0.23 +- 0.27 +- 0.32 +- 0.38 +- 0.44 +- 0.52 +- 0.61 +- 0.72 +- 0.85 +- 1 +- 1.2 +- 1.4 +- 1.6 +- 1.9 +- 2.3 +- 2.7 +- 3.1 +- 3.7 +- 4.3 +- 5.1 +- 6 +- 7.1 +- 8.3 +- 9.8 +- 12 +- 14 +- 16 +- 19 +- 22 +- 26 +- 31 +- 36 +- 43 +- 50 +wd_scale_grid: +- 1.0 +num_workers: 8 +prefetch_factor: null +balanced_sampling: false +epochs: 20 +steps_per_epoch: 200 +batch_size: 64 +accum_iter: 2 +lr: 0.0003 +warmup_epochs: 5 +no_decay: false +weight_decay: 0.05 +clip_grad: 1.0 +metrics: +- acc +- f1 +cv_metric: acc +early_stopping: true +amp: true +device: cuda +seed: 4466 +debug: false +wandb: false +wandb_entity: null +wandb_project: fMRI-fm-eval +name: input_space_v3/flat_lr1e-3_5/eval_v2/nsd_cococlip__patch__attn +model: flat_mae +representation: patch +classifier: attn +dataset: nsd_cococlip +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/eval_v2/nsd_cococlip__patch__attn +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=True, reg_tokens=0, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: nsd_cococlip (flat) +train (n=32539): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'run', 'trial_id', 'nsd_id', 'category_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 32539 +}), + labels=[ 3 4 5 6 10 11 17 18 19 20 22 23 25 30 31 33 36 37 38 53 55 59 61 74], + counts=[1286 1180 1639 1868 834 824 1026 1042 913 1853 1503 2092 1001 1410 + 794 1241 1904 1872 2267 1428 889 904 1447 1322] +) + +validation (n=5418): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'run', 'trial_id', 'nsd_id', 'category_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 5418 +}), + labels=[ 3 4 5 6 10 11 17 18 19 20 22 23 25 30 31 33 36 37 38 53 55 59 61 74], + counts=[197 161 276 345 126 142 143 185 112 295 285 387 169 250 159 193 316 334 + 343 215 172 141 226 246] +) + +test (n=5390): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'run', 'trial_id', 'nsd_id', 'category_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 5390 +}), + labels=[ 3 4 5 6 10 11 17 18 19 20 22 23 25 30 31 33 36 37 38 53 55 59 61 74], + counts=[202 172 274 298 144 180 134 182 186 293 218 343 165 185 140 177 346 333 + 345 271 165 140 251 246] +) + +testid (n=5187): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'run', 'trial_id', 'nsd_id', 'category_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 5187 +}), + labels=[ 3 4 5 6 10 11 17 18 19 20 22 23 25 30 31 33 36 37 38 53 55 59 61 74], + counts=[197 159 267 273 123 153 175 184 139 310 215 386 153 230 118 192 330 306 + 349 223 143 127 249 186] +) + +running backbone on example batch to get embedding dim +embedding feature dim (patch): 768 +initializing sweep of classifier heads +classifiers: +ModuleList( + (0-48): 49 x AttnPoolClassifier( + (kv): Linear(in_features=768, out_features=1536, bias=True) + (linear): Linear(in_features=768, out_features=24, bias=True) + ) +) +classifier params (train): 58.8M (58.8M) +setting up optimizer +total batch size: 128 = 64 bs per gpu x 2 accum +lr: 3.00e-04 +full schedule: epochs = 20 (steps = 4000) (decay = True) +warmup: epochs = 5 (steps = 1000) +start training for 20 epochs +train: [0] [ 0/400] eta: 0:33:07 lr: nan time: 4.9692 data: 4.4139 max mem: 21740 +train: [0] [ 20/400] eta: 0:04:21 lr: 0.000003 loss: 3.1979 (3.2010) grad: 0.1782 (0.1809) time: 0.4749 data: 0.0050 max mem: 22448 +train: [0] [ 40/400] eta: 0:03:27 lr: 0.000006 loss: 3.1898 (3.1912) grad: 0.1776 (0.1786) time: 0.4561 data: 0.0038 max mem: 22448 +train: [0] [ 60/400] eta: 0:03:00 lr: 0.000009 loss: 3.1805 (3.1883) grad: 0.1677 (0.1773) time: 0.4408 data: 0.0041 max mem: 22448 +train: [0] [ 80/400] eta: 0:02:43 lr: 0.000012 loss: 3.1718 (3.1836) grad: 0.1669 (0.1750) time: 0.4436 data: 0.0041 max mem: 22448 +train: [0] [100/400] eta: 0:02:29 lr: 0.000015 loss: 3.1683 (3.1815) grad: 0.1626 (0.1725) time: 0.4566 data: 0.0042 max mem: 22448 +train: [0] [120/400] eta: 0:02:18 lr: 0.000018 loss: 3.1694 (3.1787) grad: 0.1525 (0.1697) time: 0.4630 data: 0.0042 max mem: 22448 +train: [0] [140/400] eta: 0:02:06 lr: 0.000021 loss: 3.1588 (3.1758) grad: 0.1569 (0.1691) time: 0.4500 data: 0.0041 max mem: 22448 +train: [0] [160/400] eta: 0:01:55 lr: 0.000024 loss: 3.1517 (3.1721) grad: 0.1741 (0.1702) time: 0.4480 data: 0.0042 max mem: 22448 +train: [0] [180/400] eta: 0:01:45 lr: 0.000027 loss: 3.1377 (3.1688) grad: 0.1687 (0.1696) time: 0.4491 data: 0.0041 max mem: 22448 +train: [0] [200/400] eta: 0:01:35 lr: 0.000030 loss: 3.1460 (3.1670) grad: 0.1557 (0.1682) time: 0.4541 data: 0.0042 max mem: 22448 +train: [0] [220/400] eta: 0:01:25 lr: 0.000033 loss: 3.1567 (3.1652) grad: 0.1587 (0.1676) time: 0.4456 data: 0.0041 max mem: 22448 +train: [0] [240/400] eta: 0:01:15 lr: 0.000036 loss: 3.1367 (3.1624) grad: 0.1617 (0.1672) time: 0.4577 data: 0.0043 max mem: 22448 +train: [0] [260/400] eta: 0:01:05 lr: 0.000039 loss: 3.1213 (3.1590) grad: 0.1590 (0.1663) time: 0.4505 data: 0.0041 max mem: 22448 +train: [0] [280/400] eta: 0:00:56 lr: 0.000042 loss: 3.1016 (3.1544) grad: 0.1570 (0.1658) time: 0.4535 data: 0.0042 max mem: 22448 +train: [0] [300/400] eta: 0:00:46 lr: 0.000045 loss: 3.0758 (3.1483) grad: 0.1586 (0.1656) time: 0.4553 data: 0.0041 max mem: 22448 +train: [0] [320/400] eta: 0:00:37 lr: 0.000048 loss: 3.0639 (3.1442) grad: 0.1667 (0.1662) time: 0.4530 data: 0.0042 max mem: 22448 +train: [0] [340/400] eta: 0:00:27 lr: 0.000051 loss: 3.0809 (3.1401) grad: 0.1699 (0.1662) time: 0.4551 data: 0.0041 max mem: 22448 +train: [0] [360/400] eta: 0:00:18 lr: 0.000054 loss: 3.0562 (3.1353) grad: 0.1709 (0.1669) time: 0.4524 data: 0.0041 max mem: 22448 +train: [0] [380/400] eta: 0:00:09 lr: 0.000057 loss: 3.0497 (3.1309) grad: 0.1833 (0.1676) time: 0.4592 data: 0.0041 max mem: 22448 +train: [0] [399/400] eta: 0:00:00 lr: 0.000060 loss: 3.0497 (3.1275) grad: 0.1845 (0.1683) time: 0.4497 data: 0.0041 max mem: 22448 +train: [0] Total time: 0:03:05 (0.4649 s / it) +train: [0] Summary: lr: 0.000060 loss: 3.0497 (3.1275) grad: 0.1845 (0.1683) +eval (validation): [0] [ 0/85] eta: 0:04:26 time: 3.1389 data: 2.8499 max mem: 22448 +eval (validation): [0] [20/85] eta: 0:00:33 time: 0.3855 data: 0.0051 max mem: 22448 +eval (validation): [0] [40/85] eta: 0:00:19 time: 0.3550 data: 0.0035 max mem: 22448 +eval (validation): [0] [60/85] eta: 0:00:10 time: 0.3421 data: 0.0041 max mem: 22448 +eval (validation): [0] [80/85] eta: 0:00:01 time: 0.3271 data: 0.0039 max mem: 22448 +eval (validation): [0] [84/85] eta: 0:00:00 time: 0.3170 data: 0.0038 max mem: 22448 +eval (validation): [0] Total time: 0:00:32 (0.3855 s / it) +cv: [0] best hparam: (36, 1.0) (046) ('046_lr3.6e+01_wd1.0e+00') loss: 2.532 acc: 0.243 f1: 0.160 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/eval_v2/nsd_cococlip__patch__attn/checkpoint-best.pth +train: [1] [ 0/400] eta: 0:21:27 lr: nan time: 3.2181 data: 2.8502 max mem: 22448 +train: [1] [ 20/400] eta: 0:03:48 lr: 0.000063 loss: 2.9987 (3.0060) grad: 0.1809 (0.1773) time: 0.4699 data: 0.0042 max mem: 22448 +train: [1] [ 40/400] eta: 0:03:10 lr: 0.000066 loss: 3.0092 (3.0049) grad: 0.1712 (0.1730) time: 0.4558 data: 0.0041 max mem: 22448 +train: [1] [ 60/400] eta: 0:02:52 lr: 0.000069 loss: 2.9851 (2.9929) grad: 0.1703 (0.1737) time: 0.4616 data: 0.0043 max mem: 22448 +train: [1] [ 80/400] eta: 0:02:39 lr: 0.000072 loss: 2.9727 (2.9926) grad: 0.1755 (0.1758) time: 0.4697 data: 0.0044 max mem: 22448 +train: [1] [100/400] eta: 0:02:28 lr: 0.000075 loss: 2.9770 (2.9863) grad: 0.1776 (0.1776) time: 0.4775 data: 0.0044 max mem: 22448 +train: [1] [120/400] eta: 0:02:16 lr: 0.000078 loss: 2.9690 (2.9831) grad: 0.1818 (0.1787) time: 0.4569 data: 0.0042 max mem: 22448 +train: [1] [140/400] eta: 0:02:05 lr: 0.000081 loss: 2.9653 (2.9797) grad: 0.1822 (0.1797) time: 0.4429 data: 0.0039 max mem: 22448 +train: [1] [160/400] eta: 0:01:54 lr: 0.000084 loss: 2.9706 (2.9804) grad: 0.1822 (0.1800) time: 0.4536 data: 0.0042 max mem: 22448 +train: [1] [180/400] eta: 0:01:44 lr: 0.000087 loss: 2.9800 (2.9801) grad: 0.1840 (0.1808) time: 0.4671 data: 0.0044 max mem: 22448 +train: [1] [200/400] eta: 0:01:34 lr: 0.000090 loss: 2.9665 (2.9773) grad: 0.1845 (0.1818) time: 0.4544 data: 0.0046 max mem: 22448 +train: [1] [220/400] eta: 0:01:25 lr: 0.000093 loss: 2.9139 (2.9696) grad: 0.1961 (0.1836) time: 0.4757 data: 0.0046 max mem: 22448 +train: [1] [240/400] eta: 0:01:15 lr: 0.000096 loss: 2.9128 (2.9662) grad: 0.1959 (0.1836) time: 0.4270 data: 0.0041 max mem: 22448 +train: [1] [260/400] eta: 0:01:05 lr: 0.000099 loss: 2.9368 (2.9643) grad: 0.1868 (0.1844) time: 0.4573 data: 0.0043 max mem: 22448 +train: [1] [280/400] eta: 0:00:56 lr: 0.000102 loss: 2.9368 (2.9610) grad: 0.1868 (0.1850) time: 0.4642 data: 0.0043 max mem: 22448 +train: [1] [300/400] eta: 0:00:46 lr: 0.000105 loss: 2.9215 (2.9595) grad: 0.1902 (0.1858) time: 0.4471 data: 0.0042 max mem: 22448 +train: [1] [320/400] eta: 0:00:37 lr: 0.000108 loss: 2.8847 (2.9552) grad: 0.1970 (0.1867) time: 0.4517 data: 0.0041 max mem: 22448 +train: [1] [340/400] eta: 0:00:27 lr: 0.000111 loss: 2.8694 (2.9501) grad: 0.1970 (0.1874) time: 0.4474 data: 0.0043 max mem: 22448 +train: [1] [360/400] eta: 0:00:18 lr: 0.000114 loss: 2.8694 (2.9479) grad: 0.1969 (0.1880) time: 0.4307 data: 0.0040 max mem: 22448 +train: [1] [380/400] eta: 0:00:09 lr: 0.000117 loss: 2.8747 (2.9440) grad: 0.2003 (0.1889) time: 0.4405 data: 0.0040 max mem: 22448 +train: [1] [399/400] eta: 0:00:00 lr: 0.000120 loss: 2.8747 (2.9426) grad: 0.2104 (0.1905) time: 0.4492 data: 0.0042 max mem: 22448 +train: [1] Total time: 0:03:04 (0.4623 s / it) +train: [1] Summary: lr: 0.000120 loss: 2.8747 (2.9426) grad: 0.2104 (0.1905) +eval (validation): [1] [ 0/85] eta: 0:04:25 time: 3.1274 data: 2.9026 max mem: 22448 +eval (validation): [1] [20/85] eta: 0:00:29 time: 0.3226 data: 0.0042 max mem: 22448 +eval (validation): [1] [40/85] eta: 0:00:18 time: 0.3447 data: 0.0039 max mem: 22448 +eval (validation): [1] [60/85] eta: 0:00:09 time: 0.3554 data: 0.0046 max mem: 22448 +eval (validation): [1] [80/85] eta: 0:00:01 time: 0.3205 data: 0.0039 max mem: 22448 +eval (validation): [1] [84/85] eta: 0:00:00 time: 0.3094 data: 0.0041 max mem: 22448 +eval (validation): [1] Total time: 0:00:31 (0.3696 s / it) +cv: [1] best hparam: (8.3, 1.0) (037) ('037_lr8.3e+00_wd1.0e+00') loss: 2.478 acc: 0.248 f1: 0.189 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/eval_v2/nsd_cococlip__patch__attn/checkpoint-best.pth +train: [2] [ 0/400] eta: 0:21:39 lr: nan time: 3.2486 data: 2.8278 max mem: 22448 +train: [2] [ 20/400] eta: 0:03:40 lr: 0.000123 loss: 2.9145 (2.8939) grad: 0.2413 (0.2453) time: 0.4462 data: 0.0033 max mem: 22448 +train: [2] [ 40/400] eta: 0:03:04 lr: 0.000126 loss: 2.8876 (2.8859) grad: 0.2318 (0.2352) time: 0.4413 data: 0.0041 max mem: 22448 +train: [2] [ 60/400] eta: 0:02:46 lr: 0.000129 loss: 2.8820 (2.8822) grad: 0.2232 (0.2304) time: 0.4471 data: 0.0043 max mem: 22448 +train: [2] [ 80/400] eta: 0:02:32 lr: 0.000132 loss: 2.8682 (2.8825) grad: 0.2271 (0.2432) time: 0.4391 data: 0.0041 max mem: 22448 +train: [2] [100/400] eta: 0:02:21 lr: 0.000135 loss: 2.9102 (2.9074) grad: 0.3225 (0.3124) time: 0.4438 data: 0.0041 max mem: 22448 +WARNING: classifier 48 (50, 1.0) diverged (loss=75.10 > 63.56) at step 457. Freezing. +train: [2] [120/400] eta: 0:02:10 lr: 0.000138 loss: 3.0234 (2.9849) grad: 0.7087 (0.4308) time: 0.4443 data: 0.0038 max mem: 22448 +train: [2] [140/400] eta: 0:02:00 lr: 0.000141 loss: 2.9192 (2.9697) grad: 0.2264 (0.4008) time: 0.4511 data: 0.0042 max mem: 22448 +train: [2] [160/400] eta: 0:01:50 lr: 0.000144 loss: 2.8365 (2.9517) grad: 0.2190 (0.3785) time: 0.4411 data: 0.0042 max mem: 22448 +train: [2] [180/400] eta: 0:01:41 lr: 0.000147 loss: 2.8095 (2.9346) grad: 0.2174 (0.3604) time: 0.4470 data: 0.0041 max mem: 22448 +train: [2] [200/400] eta: 0:01:31 lr: 0.000150 loss: 2.8095 (2.9225) grad: 0.2166 (0.3462) time: 0.4480 data: 0.0041 max mem: 22448 +train: [2] [220/400] eta: 0:01:22 lr: 0.000153 loss: 2.8241 (2.9159) grad: 0.2221 (0.3357) time: 0.4588 data: 0.0042 max mem: 22448 +train: [2] [240/400] eta: 0:01:13 lr: 0.000156 loss: 2.8493 (2.9113) grad: 0.2273 (0.3270) time: 0.4467 data: 0.0041 max mem: 22448 +train: [2] [260/400] eta: 0:01:03 lr: 0.000159 loss: 2.8455 (2.9033) grad: 0.2221 (0.3187) time: 0.4425 data: 0.0041 max mem: 22448 +train: [2] [280/400] eta: 0:00:54 lr: 0.000162 loss: 2.7900 (2.8953) grad: 0.2283 (0.3139) time: 0.4405 data: 0.0041 max mem: 22448 +train: [2] [300/400] eta: 0:00:45 lr: 0.000165 loss: 2.7787 (2.8885) grad: 0.2461 (0.3096) time: 0.4366 data: 0.0041 max mem: 22448 +train: [2] [320/400] eta: 0:00:36 lr: 0.000168 loss: 2.7787 (2.8832) grad: 0.2465 (0.3059) time: 0.4570 data: 0.0041 max mem: 22448 +train: [2] [340/400] eta: 0:00:27 lr: 0.000171 loss: 2.8388 (2.8843) grad: 0.2625 (0.3122) time: 0.4850 data: 0.0047 max mem: 22448 +WARNING: classifier 47 (43, 1.0) diverged (loss=84.93 > 63.56) at step 580. Freezing. +train: [2] [360/400] eta: 0:00:18 lr: 0.000174 loss: 3.1012 (2.9247) grad: 0.6562 (0.3752) time: 0.4544 data: 0.0043 max mem: 22448 +train: [2] [380/400] eta: 0:00:09 lr: 0.000177 loss: 3.0038 (2.9209) grad: 0.4133 (0.3716) time: 0.4503 data: 0.0042 max mem: 22448 +train: [2] [399/400] eta: 0:00:00 lr: 0.000180 loss: 2.9019 (2.9244) grad: 0.3967 (0.3846) time: 0.4458 data: 0.0041 max mem: 22448 +train: [2] Total time: 0:03:02 (0.4556 s / it) +train: [2] Summary: lr: 0.000180 loss: 2.9019 (2.9244) grad: 0.3967 (0.3846) +eval (validation): [2] [ 0/85] eta: 0:04:14 time: 2.9956 data: 2.7549 max mem: 22448 +eval (validation): [2] [20/85] eta: 0:00:30 time: 0.3448 data: 0.0049 max mem: 22448 +eval (validation): [2] [40/85] eta: 0:00:18 time: 0.3550 data: 0.0044 max mem: 22448 +eval (validation): [2] [60/85] eta: 0:00:09 time: 0.3469 data: 0.0039 max mem: 22448 +eval (validation): [2] [80/85] eta: 0:00:01 time: 0.3253 data: 0.0039 max mem: 22448 +eval (validation): [2] [84/85] eta: 0:00:00 time: 0.3175 data: 0.0036 max mem: 22448 +eval (validation): [2] Total time: 0:00:31 (0.3754 s / it) +cv: [2] best hparam: (2.7, 1.0) (030) ('030_lr2.7e+00_wd1.0e+00') loss: 2.424 acc: 0.274 f1: 0.196 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/eval_v2/nsd_cococlip__patch__attn/checkpoint-best.pth +train: [3] [ 0/400] eta: 0:21:39 lr: nan time: 3.2486 data: 2.8836 max mem: 22448 +WARNING: classifier 46 (36, 1.0) diverged (loss=91.69 > 63.56) at step 609. Freezing. +train: [3] [ 20/400] eta: 0:03:44 lr: 0.000183 loss: 3.5273 (3.5578) grad: 1.5153 (1.5460) time: 0.4574 data: 0.0038 max mem: 22448 +train: [3] [ 40/400] eta: 0:03:06 lr: 0.000186 loss: 2.8917 (3.1913) grad: 0.2539 (0.8904) time: 0.4432 data: 0.0040 max mem: 22448 +train: [3] [ 60/400] eta: 0:02:48 lr: 0.000189 loss: 2.7910 (3.0559) grad: 0.2338 (0.6734) time: 0.4526 data: 0.0044 max mem: 22448 +train: [3] [ 80/400] eta: 0:02:34 lr: 0.000192 loss: 2.7862 (2.9889) grad: 0.2355 (0.5657) time: 0.4437 data: 0.0043 max mem: 22448 +train: [3] [100/400] eta: 0:02:22 lr: 0.000195 loss: 2.7898 (2.9511) grad: 0.2624 (0.5177) time: 0.4439 data: 0.0043 max mem: 22448 +train: [3] [120/400] eta: 0:02:11 lr: 0.000198 loss: 2.8231 (2.9594) grad: 0.4740 (0.5547) time: 0.4469 data: 0.0043 max mem: 22448 +WARNING: classifier 45 (31, 1.0) diverged (loss=66.08 > 63.56) at step 667. Freezing. +train: [3] [140/400] eta: 0:02:01 lr: 0.000201 loss: 3.0921 (3.0233) grad: 0.7392 (0.6413) time: 0.4394 data: 0.0042 max mem: 22448 +train: [3] [160/400] eta: 0:01:50 lr: 0.000204 loss: 2.8448 (2.9978) grad: 0.2382 (0.5895) time: 0.4325 data: 0.0041 max mem: 22448 +train: [3] [180/400] eta: 0:01:41 lr: 0.000207 loss: 2.7875 (2.9719) grad: 0.2229 (0.5486) time: 0.4582 data: 0.0043 max mem: 22448 +train: [3] [200/400] eta: 0:01:32 lr: 0.000210 loss: 2.7861 (2.9538) grad: 0.2209 (0.5160) time: 0.4449 data: 0.0042 max mem: 22448 +train: [3] [220/400] eta: 0:01:22 lr: 0.000213 loss: 2.7731 (2.9375) grad: 0.2306 (0.4901) time: 0.4421 data: 0.0041 max mem: 22448 +train: [3] [240/400] eta: 0:01:13 lr: 0.000216 loss: 2.7593 (2.9227) grad: 0.2297 (0.4682) time: 0.4375 data: 0.0043 max mem: 22448 +train: [3] [260/400] eta: 0:01:03 lr: 0.000219 loss: 2.7760 (2.9096) grad: 0.2229 (0.4495) time: 0.4458 data: 0.0043 max mem: 22448 +train: [3] [280/400] eta: 0:00:54 lr: 0.000222 loss: 2.7543 (2.8981) grad: 0.2229 (0.4333) time: 0.4458 data: 0.0043 max mem: 22448 +train: [3] [300/400] eta: 0:00:45 lr: 0.000225 loss: 2.7701 (2.8886) grad: 0.2211 (0.4190) time: 0.4470 data: 0.0044 max mem: 22448 +train: [3] [320/400] eta: 0:00:36 lr: 0.000228 loss: 2.7386 (2.8789) grad: 0.2237 (0.4075) time: 0.4429 data: 0.0043 max mem: 22448 +train: [3] [340/400] eta: 0:00:27 lr: 0.000231 loss: 2.7439 (2.8730) grad: 0.2323 (0.3980) time: 0.4381 data: 0.0042 max mem: 22448 +train: [3] [360/400] eta: 0:00:18 lr: 0.000234 loss: 2.7931 (2.8691) grad: 0.2463 (0.3894) time: 0.4441 data: 0.0043 max mem: 22448 +train: [3] [380/400] eta: 0:00:09 lr: 0.000237 loss: 2.7748 (2.8634) grad: 0.2516 (0.3825) time: 0.4404 data: 0.0043 max mem: 22448 +train: [3] [399/400] eta: 0:00:00 lr: 0.000240 loss: 2.7344 (2.8572) grad: 0.2522 (0.3758) time: 0.4422 data: 0.0044 max mem: 22448 +train: [3] Total time: 0:03:00 (0.4518 s / it) +train: [3] Summary: lr: 0.000240 loss: 2.7344 (2.8572) grad: 0.2522 (0.3758) +eval (validation): [3] [ 0/85] eta: 0:04:15 time: 3.0111 data: 2.7396 max mem: 22448 +eval (validation): [3] [20/85] eta: 0:00:30 time: 0.3365 data: 0.0108 max mem: 22448 +eval (validation): [3] [40/85] eta: 0:00:17 time: 0.3299 data: 0.0042 max mem: 22448 +eval (validation): [3] [60/85] eta: 0:00:09 time: 0.3405 data: 0.0035 max mem: 22448 +eval (validation): [3] [80/85] eta: 0:00:01 time: 0.3277 data: 0.0041 max mem: 22448 +eval (validation): [3] [84/85] eta: 0:00:00 time: 0.3216 data: 0.0039 max mem: 22448 +eval (validation): [3] Total time: 0:00:31 (0.3663 s / it) +cv: [3] best hparam: (3.7, 1.0) (032) ('032_lr3.7e+00_wd1.0e+00') loss: 2.461 acc: 0.265 f1: 0.191 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [4] [ 0/400] eta: 0:20:52 lr: nan time: 3.1301 data: 2.7893 max mem: 22448 +train: [4] [ 20/400] eta: 0:03:36 lr: 0.000243 loss: 2.7180 (2.7163) grad: 0.2595 (0.2771) time: 0.4427 data: 0.0046 max mem: 22448 +train: [4] [ 40/400] eta: 0:03:02 lr: 0.000246 loss: 2.7847 (2.8125) grad: 0.3615 (0.4595) time: 0.4409 data: 0.0041 max mem: 22448 +WARNING: classifier 44 (26, 1.0) diverged (loss=65.00 > 63.56) at step 828. Freezing. +train: [4] [ 60/400] eta: 0:02:46 lr: 0.000249 loss: 3.0156 (2.9980) grad: 0.7649 (0.7189) time: 0.4526 data: 0.0042 max mem: 22448 +train: [4] [ 80/400] eta: 0:02:33 lr: 0.000252 loss: 3.0032 (2.9923) grad: 0.7421 (0.7098) time: 0.4447 data: 0.0042 max mem: 22448 +train: [4] [100/400] eta: 0:02:21 lr: 0.000255 loss: 3.1060 (3.0876) grad: 0.9177 (0.8284) time: 0.4522 data: 0.0041 max mem: 22448 +WARNING: classifier 43 (22, 1.0) diverged (loss=91.87 > 63.56) at step 854. Freezing. +train: [4] [120/400] eta: 0:02:12 lr: 0.000258 loss: 3.3686 (3.0939) grad: 1.0434 (0.8041) time: 0.4641 data: 0.0042 max mem: 22448 +train: [4] [140/400] eta: 0:02:01 lr: 0.000261 loss: 2.7413 (3.0406) grad: 0.2364 (0.7226) time: 0.4510 data: 0.0042 max mem: 22448 +train: [4] [160/400] eta: 0:01:52 lr: 0.000264 loss: 2.7259 (3.0019) grad: 0.2364 (0.6624) time: 0.4531 data: 0.0046 max mem: 22448 +train: [4] [180/400] eta: 0:01:42 lr: 0.000267 loss: 2.7293 (2.9737) grad: 0.2395 (0.6160) time: 0.4424 data: 0.0042 max mem: 22448 +train: [4] [200/400] eta: 0:01:32 lr: 0.000270 loss: 2.7121 (2.9473) grad: 0.2377 (0.5779) time: 0.4381 data: 0.0043 max mem: 22448 +train: [4] [220/400] eta: 0:01:22 lr: 0.000273 loss: 2.7121 (2.9294) grad: 0.2413 (0.5477) time: 0.4493 data: 0.0043 max mem: 22448 +train: [4] [240/400] eta: 0:01:13 lr: 0.000276 loss: 2.7363 (2.9119) grad: 0.2408 (0.5220) time: 0.4575 data: 0.0041 max mem: 22448 +train: [4] [260/400] eta: 0:01:04 lr: 0.000279 loss: 2.7586 (2.8994) grad: 0.2351 (0.5002) time: 0.4606 data: 0.0044 max mem: 22448 +train: [4] [280/400] eta: 0:00:55 lr: 0.000282 loss: 2.7766 (2.8893) grad: 0.2351 (0.4821) time: 0.4451 data: 0.0043 max mem: 22448 +train: [4] [300/400] eta: 0:00:45 lr: 0.000285 loss: 2.7363 (2.8791) grad: 0.2323 (0.4654) time: 0.4496 data: 0.0042 max mem: 22448 +train: [4] [320/400] eta: 0:00:36 lr: 0.000288 loss: 2.7265 (2.8687) grad: 0.2224 (0.4496) time: 0.4238 data: 0.0042 max mem: 22448 +train: [4] [340/400] eta: 0:00:27 lr: 0.000291 loss: 2.7193 (2.8605) grad: 0.2160 (0.4362) time: 0.4607 data: 0.0043 max mem: 22448 +train: [4] [360/400] eta: 0:00:18 lr: 0.000294 loss: 2.7163 (2.8538) grad: 0.2250 (0.4248) time: 0.4532 data: 0.0042 max mem: 22448 +train: [4] [380/400] eta: 0:00:09 lr: 0.000297 loss: 2.7046 (2.8459) grad: 0.2292 (0.4147) time: 0.4453 data: 0.0044 max mem: 22448 +train: [4] [399/400] eta: 0:00:00 lr: 0.000300 loss: 2.6980 (2.8382) grad: 0.2267 (0.4053) time: 0.4431 data: 0.0042 max mem: 22448 +train: [4] Total time: 0:03:02 (0.4556 s / it) +train: [4] Summary: lr: 0.000300 loss: 2.6980 (2.8382) grad: 0.2267 (0.4053) +eval (validation): [4] [ 0/85] eta: 0:04:23 time: 3.0983 data: 2.8176 max mem: 22448 +eval (validation): [4] [20/85] eta: 0:00:32 time: 0.3684 data: 0.0056 max mem: 22448 +eval (validation): [4] [40/85] eta: 0:00:18 time: 0.3165 data: 0.0036 max mem: 22448 +eval (validation): [4] [60/85] eta: 0:00:09 time: 0.3388 data: 0.0040 max mem: 22448 +eval (validation): [4] [80/85] eta: 0:00:01 time: 0.3346 data: 0.0038 max mem: 22448 +eval (validation): [4] [84/85] eta: 0:00:00 time: 0.3311 data: 0.0038 max mem: 22448 +eval (validation): [4] Total time: 0:00:31 (0.3744 s / it) +cv: [4] best hparam: (1.6, 1.0) (027) ('027_lr1.6e+00_wd1.0e+00') loss: 2.402 acc: 0.274 f1: 0.219 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [5] [ 0/400] eta: 0:21:15 lr: nan time: 3.1884 data: 2.8501 max mem: 22448 +train: [5] [ 20/400] eta: 0:03:38 lr: 0.000300 loss: 2.5952 (2.5921) grad: 0.2290 (0.2312) time: 0.4437 data: 0.0035 max mem: 22448 +train: [5] [ 40/400] eta: 0:03:01 lr: 0.000300 loss: 2.6222 (2.6442) grad: 0.2340 (0.2357) time: 0.4328 data: 0.0038 max mem: 22448 +train: [5] [ 60/400] eta: 0:02:43 lr: 0.000300 loss: 2.6747 (2.6533) grad: 0.2469 (0.2412) time: 0.4320 data: 0.0041 max mem: 22448 +train: [5] [ 80/400] eta: 0:02:31 lr: 0.000300 loss: 2.6824 (2.6536) grad: 0.2469 (0.2421) time: 0.4438 data: 0.0043 max mem: 22448 +train: [5] [100/400] eta: 0:02:20 lr: 0.000300 loss: 2.6831 (2.6619) grad: 0.2477 (0.2462) time: 0.4451 data: 0.0044 max mem: 22448 +train: [5] [120/400] eta: 0:02:09 lr: 0.000300 loss: 2.6282 (2.6546) grad: 0.2455 (0.2446) time: 0.4459 data: 0.0043 max mem: 22448 +train: [5] [140/400] eta: 0:01:59 lr: 0.000300 loss: 2.6043 (2.6494) grad: 0.2292 (0.2420) time: 0.4409 data: 0.0044 max mem: 22448 +train: [5] [160/400] eta: 0:01:49 lr: 0.000299 loss: 2.6011 (2.6461) grad: 0.2275 (0.2412) time: 0.4394 data: 0.0041 max mem: 22448 +train: [5] [180/400] eta: 0:01:40 lr: 0.000299 loss: 2.6347 (2.6503) grad: 0.2363 (0.2410) time: 0.4424 data: 0.0042 max mem: 22448 +train: [5] [200/400] eta: 0:01:31 lr: 0.000299 loss: 2.6571 (2.6484) grad: 0.2380 (0.2408) time: 0.4494 data: 0.0041 max mem: 22448 +train: [5] [220/400] eta: 0:01:21 lr: 0.000299 loss: 2.6478 (2.6484) grad: 0.2374 (0.2403) time: 0.4474 data: 0.0041 max mem: 22448 +train: [5] [240/400] eta: 0:01:12 lr: 0.000299 loss: 2.6082 (2.6478) grad: 0.2379 (0.2405) time: 0.4437 data: 0.0043 max mem: 22448 +train: [5] [260/400] eta: 0:01:03 lr: 0.000299 loss: 2.6090 (2.6460) grad: 0.2385 (0.2400) time: 0.4457 data: 0.0042 max mem: 22448 +train: [5] [280/400] eta: 0:00:54 lr: 0.000298 loss: 2.6162 (2.6479) grad: 0.2385 (0.2406) time: 0.4428 data: 0.0043 max mem: 22448 +train: [5] [300/400] eta: 0:00:45 lr: 0.000298 loss: 2.6125 (2.6437) grad: 0.2382 (0.2406) time: 0.4441 data: 0.0043 max mem: 22448 +train: [5] [320/400] eta: 0:00:36 lr: 0.000298 loss: 2.6237 (2.6442) grad: 0.2423 (0.2411) time: 0.4492 data: 0.0042 max mem: 22448 +train: [5] [340/400] eta: 0:00:27 lr: 0.000298 loss: 2.6336 (2.6428) grad: 0.2451 (0.2410) time: 0.4533 data: 0.0042 max mem: 22448 +train: [5] [360/400] eta: 0:00:18 lr: 0.000297 loss: 2.6303 (2.6425) grad: 0.2398 (0.2411) time: 0.4387 data: 0.0041 max mem: 22448 +train: [5] [380/400] eta: 0:00:09 lr: 0.000297 loss: 2.5758 (2.6420) grad: 0.2424 (0.2413) time: 0.4389 data: 0.0042 max mem: 22448 +train: [5] [399/400] eta: 0:00:00 lr: 0.000297 loss: 2.5679 (2.6385) grad: 0.2371 (0.2409) time: 0.4430 data: 0.0042 max mem: 22448 +train: [5] Total time: 0:03:00 (0.4503 s / it) +train: [5] Summary: lr: 0.000297 loss: 2.5679 (2.6385) grad: 0.2371 (0.2409) +eval (validation): [5] [ 0/85] eta: 0:04:23 time: 3.1027 data: 2.8522 max mem: 22448 +eval (validation): [5] [20/85] eta: 0:00:31 time: 0.3497 data: 0.0039 max mem: 22448 +eval (validation): [5] [40/85] eta: 0:00:18 time: 0.3437 data: 0.0039 max mem: 22448 +eval (validation): [5] [60/85] eta: 0:00:09 time: 0.3481 data: 0.0041 max mem: 22448 +eval (validation): [5] [80/85] eta: 0:00:01 time: 0.3319 data: 0.0041 max mem: 22448 +eval (validation): [5] [84/85] eta: 0:00:00 time: 0.3251 data: 0.0040 max mem: 22448 +eval (validation): [5] Total time: 0:00:32 (0.3772 s / it) +cv: [5] best hparam: (1.2, 1.0) (025) ('025_lr1.2e+00_wd1.0e+00') loss: 2.372 acc: 0.289 f1: 0.221 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/eval_v2/nsd_cococlip__patch__attn/checkpoint-best.pth +train: [6] [ 0/400] eta: 0:21:27 lr: nan time: 3.2191 data: 2.8321 max mem: 22448 +train: [6] [ 20/400] eta: 0:03:40 lr: 0.000296 loss: 2.5684 (2.5547) grad: 0.2395 (0.2403) time: 0.4478 data: 0.0043 max mem: 22448 +train: [6] [ 40/400] eta: 0:03:05 lr: 0.000296 loss: 2.5713 (2.5759) grad: 0.2395 (0.2416) time: 0.4502 data: 0.0036 max mem: 22448 +train: [6] [ 60/400] eta: 0:02:48 lr: 0.000296 loss: 2.5713 (2.5738) grad: 0.2389 (0.2438) time: 0.4505 data: 0.0045 max mem: 22448 +train: [6] [ 80/400] eta: 0:02:34 lr: 0.000295 loss: 2.5467 (2.5610) grad: 0.2421 (0.2439) time: 0.4432 data: 0.0043 max mem: 22448 +train: [6] [100/400] eta: 0:02:22 lr: 0.000295 loss: 2.5613 (2.5625) grad: 0.2449 (0.2441) time: 0.4443 data: 0.0041 max mem: 22448 +train: [6] [120/400] eta: 0:02:10 lr: 0.000295 loss: 2.5823 (2.5625) grad: 0.2453 (0.2450) time: 0.4261 data: 0.0040 max mem: 22448 +train: [6] [140/400] eta: 0:02:00 lr: 0.000294 loss: 2.5917 (2.5701) grad: 0.2480 (0.2450) time: 0.4536 data: 0.0041 max mem: 22448 +train: [6] [160/400] eta: 0:01:51 lr: 0.000294 loss: 2.6100 (2.5746) grad: 0.2469 (0.2444) time: 0.4572 data: 0.0044 max mem: 22448 +train: [6] [180/400] eta: 0:01:41 lr: 0.000293 loss: 2.5822 (2.5736) grad: 0.2454 (0.2452) time: 0.4548 data: 0.0044 max mem: 22448 +train: [6] [200/400] eta: 0:01:32 lr: 0.000293 loss: 2.5674 (2.5739) grad: 0.2475 (0.2455) time: 0.4407 data: 0.0042 max mem: 22448 +train: [6] [220/400] eta: 0:01:22 lr: 0.000292 loss: 2.5985 (2.5712) grad: 0.2501 (0.2462) time: 0.4362 data: 0.0041 max mem: 22448 +train: [6] [240/400] eta: 0:01:13 lr: 0.000292 loss: 2.5731 (2.5736) grad: 0.2514 (0.2468) time: 0.4443 data: 0.0040 max mem: 22448 +train: [6] [260/400] eta: 0:01:03 lr: 0.000291 loss: 2.5703 (2.5709) grad: 0.2508 (0.2470) time: 0.4328 data: 0.0041 max mem: 22448 +train: [6] [280/400] eta: 0:00:54 lr: 0.000291 loss: 2.5589 (2.5731) grad: 0.2448 (0.2474) time: 0.4470 data: 0.0041 max mem: 22448 +train: [6] [300/400] eta: 0:00:45 lr: 0.000290 loss: 2.6294 (2.5761) grad: 0.2508 (0.2479) time: 0.4566 data: 0.0041 max mem: 22448 +train: [6] [320/400] eta: 0:00:36 lr: 0.000290 loss: 2.5988 (2.5768) grad: 0.2517 (0.2482) time: 0.4423 data: 0.0044 max mem: 22448 +train: [6] [340/400] eta: 0:00:27 lr: 0.000289 loss: 2.5993 (2.5782) grad: 0.2503 (0.2484) time: 0.4397 data: 0.0043 max mem: 22448 +train: [6] [360/400] eta: 0:00:18 lr: 0.000288 loss: 2.5737 (2.5758) grad: 0.2504 (0.2487) time: 0.4468 data: 0.0040 max mem: 22448 +train: [6] [380/400] eta: 0:00:09 lr: 0.000288 loss: 2.5239 (2.5778) grad: 0.2542 (0.2491) time: 0.4412 data: 0.0042 max mem: 22448 +train: [6] [399/400] eta: 0:00:00 lr: 0.000287 loss: 2.5726 (2.5775) grad: 0.2427 (0.2485) time: 0.4427 data: 0.0041 max mem: 22448 +train: [6] Total time: 0:03:00 (0.4521 s / it) +train: [6] Summary: lr: 0.000287 loss: 2.5726 (2.5775) grad: 0.2427 (0.2485) +eval (validation): [6] [ 0/85] eta: 0:04:25 time: 3.1200 data: 2.8315 max mem: 22448 +eval (validation): [6] [20/85] eta: 0:00:31 time: 0.3539 data: 0.0048 max mem: 22448 +eval (validation): [6] [40/85] eta: 0:00:18 time: 0.3393 data: 0.0039 max mem: 22448 +eval (validation): [6] [60/85] eta: 0:00:09 time: 0.3376 data: 0.0043 max mem: 22448 +eval (validation): [6] [80/85] eta: 0:00:01 time: 0.3313 data: 0.0043 max mem: 22448 +eval (validation): [6] [84/85] eta: 0:00:00 time: 0.3213 data: 0.0040 max mem: 22448 +eval (validation): [6] Total time: 0:00:31 (0.3741 s / it) +cv: [6] best hparam: (0.85, 1.0) (023) ('023_lr8.5e-01_wd1.0e+00') loss: 2.398 acc: 0.284 f1: 0.225 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [7] [ 0/400] eta: 0:21:31 lr: nan time: 3.2299 data: 2.8364 max mem: 22448 +train: [7] [ 20/400] eta: 0:03:49 lr: 0.000286 loss: 2.4626 (2.4774) grad: 0.2335 (0.2413) time: 0.4737 data: 0.0029 max mem: 22448 +train: [7] [ 40/400] eta: 0:03:09 lr: 0.000286 loss: 2.4626 (2.4784) grad: 0.2409 (0.2439) time: 0.4422 data: 0.0042 max mem: 22448 +train: [7] [ 60/400] eta: 0:02:49 lr: 0.000285 loss: 2.4682 (2.4798) grad: 0.2504 (0.2494) time: 0.4413 data: 0.0042 max mem: 22448 +train: [7] [ 80/400] eta: 0:02:34 lr: 0.000284 loss: 2.4922 (2.4939) grad: 0.2505 (0.2471) time: 0.4364 data: 0.0043 max mem: 22448 +train: [7] [100/400] eta: 0:02:22 lr: 0.000284 loss: 2.4757 (2.4847) grad: 0.2375 (0.2451) time: 0.4463 data: 0.0045 max mem: 22448 +train: [7] [120/400] eta: 0:02:11 lr: 0.000283 loss: 2.4611 (2.4842) grad: 0.2382 (0.2452) time: 0.4464 data: 0.0043 max mem: 22448 +train: [7] [140/400] eta: 0:02:01 lr: 0.000282 loss: 2.4766 (2.4872) grad: 0.2444 (0.2455) time: 0.4487 data: 0.0042 max mem: 22448 +train: [7] [160/400] eta: 0:01:51 lr: 0.000282 loss: 2.5061 (2.4889) grad: 0.2475 (0.2463) time: 0.4440 data: 0.0043 max mem: 22448 +train: [7] [180/400] eta: 0:01:41 lr: 0.000281 loss: 2.5299 (2.4973) grad: 0.2572 (0.2484) time: 0.4421 data: 0.0042 max mem: 22448 +train: [7] [200/400] eta: 0:01:32 lr: 0.000280 loss: 2.5186 (2.4956) grad: 0.2550 (0.2484) time: 0.4434 data: 0.0043 max mem: 22448 +train: [7] [220/400] eta: 0:01:22 lr: 0.000279 loss: 2.4740 (2.4936) grad: 0.2541 (0.2489) time: 0.4622 data: 0.0044 max mem: 22448 +train: [7] [240/400] eta: 0:01:13 lr: 0.000278 loss: 2.5092 (2.4976) grad: 0.2545 (0.2497) time: 0.4447 data: 0.0044 max mem: 22448 +train: [7] [260/400] eta: 0:01:04 lr: 0.000278 loss: 2.4999 (2.4960) grad: 0.2526 (0.2497) time: 0.4451 data: 0.0047 max mem: 22448 +train: [7] [280/400] eta: 0:00:54 lr: 0.000277 loss: 2.4313 (2.4933) grad: 0.2494 (0.2499) time: 0.4486 data: 0.0044 max mem: 22448 +train: [7] [300/400] eta: 0:00:45 lr: 0.000276 loss: 2.4199 (2.4913) grad: 0.2530 (0.2502) time: 0.4446 data: 0.0042 max mem: 22448 +train: [7] [320/400] eta: 0:00:36 lr: 0.000275 loss: 2.4444 (2.4919) grad: 0.2534 (0.2503) time: 0.4444 data: 0.0042 max mem: 22448 +train: [7] [340/400] eta: 0:00:27 lr: 0.000274 loss: 2.4607 (2.4900) grad: 0.2542 (0.2501) time: 0.4650 data: 0.0043 max mem: 22448 +train: [7] [360/400] eta: 0:00:18 lr: 0.000273 loss: 2.4712 (2.4913) grad: 0.2542 (0.2504) time: 0.4600 data: 0.0042 max mem: 22448 +train: [7] [380/400] eta: 0:00:09 lr: 0.000272 loss: 2.5201 (2.4921) grad: 0.2534 (0.2509) time: 0.4562 data: 0.0042 max mem: 22448 +train: [7] [399/400] eta: 0:00:00 lr: 0.000271 loss: 2.5284 (2.4936) grad: 0.2541 (0.2513) time: 0.4599 data: 0.0043 max mem: 22448 +train: [7] Total time: 0:03:02 (0.4569 s / it) +train: [7] Summary: lr: 0.000271 loss: 2.5284 (2.4936) grad: 0.2541 (0.2513) +eval (validation): [7] [ 0/85] eta: 0:04:13 time: 2.9845 data: 2.7537 max mem: 22448 +eval (validation): [7] [20/85] eta: 0:00:31 time: 0.3671 data: 0.0041 max mem: 22448 +eval (validation): [7] [40/85] eta: 0:00:19 time: 0.3549 data: 0.0036 max mem: 22448 +eval (validation): [7] [60/85] eta: 0:00:10 time: 0.3555 data: 0.0046 max mem: 22448 +eval (validation): [7] [80/85] eta: 0:00:01 time: 0.3392 data: 0.0043 max mem: 22448 +eval (validation): [7] [84/85] eta: 0:00:00 time: 0.3293 data: 0.0040 max mem: 22448 +eval (validation): [7] Total time: 0:00:32 (0.3857 s / it) +cv: [7] best hparam: (0.72, 1.0) (022) ('022_lr7.2e-01_wd1.0e+00') loss: 2.416 acc: 0.278 f1: 0.222 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [8] [ 0/400] eta: 0:21:17 lr: nan time: 3.1936 data: 2.8108 max mem: 22448 +train: [8] [ 20/400] eta: 0:03:46 lr: 0.000270 loss: 2.3756 (2.3851) grad: 0.2356 (0.2396) time: 0.4651 data: 0.0038 max mem: 22448 +train: [8] [ 40/400] eta: 0:03:07 lr: 0.000270 loss: 2.3945 (2.3984) grad: 0.2455 (0.2447) time: 0.4435 data: 0.0040 max mem: 22448 +train: [8] [ 60/400] eta: 0:02:47 lr: 0.000269 loss: 2.4298 (2.4112) grad: 0.2455 (0.2455) time: 0.4368 data: 0.0041 max mem: 22448 +train: [8] [ 80/400] eta: 0:02:34 lr: 0.000268 loss: 2.4366 (2.4194) grad: 0.2496 (0.2491) time: 0.4484 data: 0.0041 max mem: 22448 +train: [8] [100/400] eta: 0:02:22 lr: 0.000267 loss: 2.4519 (2.4215) grad: 0.2638 (0.2541) time: 0.4450 data: 0.0042 max mem: 22448 +train: [8] [120/400] eta: 0:02:11 lr: 0.000266 loss: 2.4564 (2.4244) grad: 0.2768 (0.2582) time: 0.4384 data: 0.0042 max mem: 22448 +train: [8] [140/400] eta: 0:02:01 lr: 0.000265 loss: 2.4229 (2.4281) grad: 0.2721 (0.2596) time: 0.4454 data: 0.0042 max mem: 22448 +train: [8] [160/400] eta: 0:01:51 lr: 0.000264 loss: 2.4384 (2.4287) grad: 0.2721 (0.2631) time: 0.4502 data: 0.0041 max mem: 22448 +train: [8] [180/400] eta: 0:01:41 lr: 0.000263 loss: 2.4252 (2.4259) grad: 0.2762 (0.2638) time: 0.4454 data: 0.0042 max mem: 22448 +train: [8] [200/400] eta: 0:01:32 lr: 0.000262 loss: 2.4356 (2.4291) grad: 0.2630 (0.2637) time: 0.4471 data: 0.0041 max mem: 22448 +train: [8] [220/400] eta: 0:01:22 lr: 0.000260 loss: 2.4387 (2.4299) grad: 0.2593 (0.2630) time: 0.4370 data: 0.0042 max mem: 22448 +train: [8] [240/400] eta: 0:01:13 lr: 0.000259 loss: 2.4138 (2.4278) grad: 0.2498 (0.2623) time: 0.4411 data: 0.0041 max mem: 22448 +train: [8] [260/400] eta: 0:01:03 lr: 0.000258 loss: 2.4138 (2.4294) grad: 0.2501 (0.2622) time: 0.4401 data: 0.0042 max mem: 22448 +train: [8] [280/400] eta: 0:00:54 lr: 0.000257 loss: 2.4455 (2.4288) grad: 0.2518 (0.2623) time: 0.4337 data: 0.0044 max mem: 22448 +train: [8] [300/400] eta: 0:00:45 lr: 0.000256 loss: 2.3874 (2.4291) grad: 0.2557 (0.2622) time: 0.4401 data: 0.0043 max mem: 22448 +train: [8] [320/400] eta: 0:00:36 lr: 0.000255 loss: 2.3889 (2.4284) grad: 0.2537 (0.2615) time: 0.4434 data: 0.0043 max mem: 22448 +train: [8] [340/400] eta: 0:00:27 lr: 0.000254 loss: 2.4053 (2.4292) grad: 0.2586 (0.2623) time: 0.4403 data: 0.0043 max mem: 22448 +train: [8] [360/400] eta: 0:00:18 lr: 0.000253 loss: 2.4196 (2.4286) grad: 0.2650 (0.2622) time: 0.4442 data: 0.0044 max mem: 22448 +train: [8] [380/400] eta: 0:00:09 lr: 0.000252 loss: 2.4330 (2.4308) grad: 0.2575 (0.2620) time: 0.4376 data: 0.0043 max mem: 22448 +train: [8] [399/400] eta: 0:00:00 lr: 0.000250 loss: 2.4756 (2.4321) grad: 0.2647 (0.2629) time: 0.4440 data: 0.0041 max mem: 22448 +train: [8] Total time: 0:03:00 (0.4506 s / it) +train: [8] Summary: lr: 0.000250 loss: 2.4756 (2.4321) grad: 0.2647 (0.2629) +eval (validation): [8] [ 0/85] eta: 0:04:12 time: 2.9656 data: 2.7215 max mem: 22448 +eval (validation): [8] [20/85] eta: 0:00:30 time: 0.3517 data: 0.0050 max mem: 22448 +eval (validation): [8] [40/85] eta: 0:00:18 time: 0.3511 data: 0.0041 max mem: 22448 +eval (validation): [8] [60/85] eta: 0:00:09 time: 0.3412 data: 0.0042 max mem: 22448 +eval (validation): [8] [80/85] eta: 0:00:01 time: 0.3265 data: 0.0038 max mem: 22448 +eval (validation): [8] [84/85] eta: 0:00:00 time: 0.3185 data: 0.0037 max mem: 22448 +eval (validation): [8] Total time: 0:00:31 (0.3745 s / it) +cv: [8] best hparam: (0.44, 1.0) (019) ('019_lr4.4e-01_wd1.0e+00') loss: 2.431 acc: 0.270 f1: 0.211 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [9] [ 0/400] eta: 0:20:38 lr: nan time: 3.0956 data: 2.7665 max mem: 22448 +train: [9] [ 20/400] eta: 0:03:41 lr: 0.000249 loss: 2.3621 (2.3804) grad: 0.2703 (0.2769) time: 0.4573 data: 0.0051 max mem: 22448 +train: [9] [ 40/400] eta: 0:03:06 lr: 0.000248 loss: 2.3847 (2.3887) grad: 0.2635 (0.2674) time: 0.4517 data: 0.0041 max mem: 22448 +train: [9] [ 60/400] eta: 0:02:48 lr: 0.000247 loss: 2.3738 (2.3793) grad: 0.2555 (0.2625) time: 0.4517 data: 0.0043 max mem: 22448 +train: [9] [ 80/400] eta: 0:02:35 lr: 0.000246 loss: 2.3738 (2.3865) grad: 0.2555 (0.2629) time: 0.4511 data: 0.0043 max mem: 22448 +train: [9] [100/400] eta: 0:02:23 lr: 0.000244 loss: 2.3824 (2.3866) grad: 0.2612 (0.2633) time: 0.4449 data: 0.0043 max mem: 22448 +train: [9] [120/400] eta: 0:02:11 lr: 0.000243 loss: 2.3819 (2.3829) grad: 0.2595 (0.2631) time: 0.4363 data: 0.0040 max mem: 22448 +train: [9] [140/400] eta: 0:02:01 lr: 0.000242 loss: 2.3611 (2.3844) grad: 0.2589 (0.2638) time: 0.4468 data: 0.0041 max mem: 22448 +train: [9] [160/400] eta: 0:01:51 lr: 0.000241 loss: 2.3792 (2.3826) grad: 0.2610 (0.2644) time: 0.4520 data: 0.0043 max mem: 22448 +train: [9] [180/400] eta: 0:01:41 lr: 0.000240 loss: 2.3573 (2.3843) grad: 0.2611 (0.2649) time: 0.4451 data: 0.0045 max mem: 22448 +train: [9] [200/400] eta: 0:01:32 lr: 0.000238 loss: 2.3560 (2.3797) grad: 0.2674 (0.2658) time: 0.4548 data: 0.0040 max mem: 22448 +train: [9] [220/400] eta: 0:01:22 lr: 0.000237 loss: 2.3458 (2.3774) grad: 0.2702 (0.2665) time: 0.4483 data: 0.0041 max mem: 22448 +train: [9] [240/400] eta: 0:01:13 lr: 0.000236 loss: 2.4069 (2.3826) grad: 0.2692 (0.2661) time: 0.4420 data: 0.0041 max mem: 22448 +train: [9] [260/400] eta: 0:01:04 lr: 0.000234 loss: 2.3988 (2.3814) grad: 0.2618 (0.2651) time: 0.4655 data: 0.0044 max mem: 22448 +train: [9] [280/400] eta: 0:00:55 lr: 0.000233 loss: 2.3661 (2.3811) grad: 0.2607 (0.2654) time: 0.4446 data: 0.0042 max mem: 22448 +train: [9] [300/400] eta: 0:00:45 lr: 0.000232 loss: 2.3555 (2.3806) grad: 0.2693 (0.2660) time: 0.4423 data: 0.0042 max mem: 22448 +train: [9] [320/400] eta: 0:00:36 lr: 0.000230 loss: 2.3447 (2.3816) grad: 0.2690 (0.2660) time: 0.4481 data: 0.0042 max mem: 22448 +train: [9] [340/400] eta: 0:00:27 lr: 0.000229 loss: 2.3337 (2.3792) grad: 0.2686 (0.2662) time: 0.4414 data: 0.0041 max mem: 22448 +train: [9] [360/400] eta: 0:00:18 lr: 0.000228 loss: 2.3704 (2.3807) grad: 0.2696 (0.2669) time: 0.4263 data: 0.0041 max mem: 22448 +train: [9] [380/400] eta: 0:00:09 lr: 0.000226 loss: 2.3704 (2.3806) grad: 0.2686 (0.2669) time: 0.4518 data: 0.0043 max mem: 22448 +train: [9] [399/400] eta: 0:00:00 lr: 0.000225 loss: 2.3885 (2.3819) grad: 0.2688 (0.2672) time: 0.4422 data: 0.0042 max mem: 22448 +train: [9] Total time: 0:03:01 (0.4541 s / it) +train: [9] Summary: lr: 0.000225 loss: 2.3885 (2.3819) grad: 0.2688 (0.2672) +eval (validation): [9] [ 0/85] eta: 0:04:59 time: 3.5213 data: 3.2334 max mem: 22448 +eval (validation): [9] [20/85] eta: 0:00:31 time: 0.3352 data: 0.0043 max mem: 22448 +eval (validation): [9] [40/85] eta: 0:00:19 time: 0.3729 data: 0.0035 max mem: 22448 +eval (validation): [9] [60/85] eta: 0:00:10 time: 0.3635 data: 0.0045 max mem: 22448 +eval (validation): [9] [80/85] eta: 0:00:01 time: 0.3351 data: 0.0040 max mem: 22448 +eval (validation): [9] [84/85] eta: 0:00:00 time: 0.3280 data: 0.0039 max mem: 22448 +eval (validation): [9] Total time: 0:00:33 (0.3901 s / it) +cv: [9] best hparam: (0.38, 1.0) (018) ('018_lr3.8e-01_wd1.0e+00') loss: 2.395 acc: 0.280 f1: 0.210 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [10] [ 0/400] eta: 0:21:09 lr: nan time: 3.1745 data: 2.8371 max mem: 22448 +train: [10] [ 20/400] eta: 0:03:38 lr: 0.000224 loss: 2.3210 (2.3206) grad: 0.2741 (0.2695) time: 0.4442 data: 0.0037 max mem: 22448 +train: [10] [ 40/400] eta: 0:03:02 lr: 0.000222 loss: 2.3210 (2.3224) grad: 0.2654 (0.2660) time: 0.4378 data: 0.0036 max mem: 22448 +train: [10] [ 60/400] eta: 0:02:45 lr: 0.000221 loss: 2.3250 (2.3325) grad: 0.2565 (0.2633) time: 0.4396 data: 0.0044 max mem: 22448 +train: [10] [ 80/400] eta: 0:02:31 lr: 0.000220 loss: 2.2962 (2.3175) grad: 0.2542 (0.2619) time: 0.4390 data: 0.0042 max mem: 22448 +train: [10] [100/400] eta: 0:02:20 lr: 0.000218 loss: 2.2962 (2.3152) grad: 0.2594 (0.2622) time: 0.4502 data: 0.0042 max mem: 22448 +train: [10] [120/400] eta: 0:02:10 lr: 0.000217 loss: 2.3107 (2.3137) grad: 0.2612 (0.2630) time: 0.4417 data: 0.0040 max mem: 22448 +train: [10] [140/400] eta: 0:02:00 lr: 0.000215 loss: 2.2921 (2.3180) grad: 0.2600 (0.2626) time: 0.4452 data: 0.0040 max mem: 22448 +train: [10] [160/400] eta: 0:01:50 lr: 0.000214 loss: 2.2943 (2.3203) grad: 0.2600 (0.2626) time: 0.4472 data: 0.0043 max mem: 22448 +train: [10] [180/400] eta: 0:01:40 lr: 0.000213 loss: 2.3370 (2.3217) grad: 0.2606 (0.2628) time: 0.4461 data: 0.0042 max mem: 22448 +train: [10] [200/400] eta: 0:01:31 lr: 0.000211 loss: 2.3370 (2.3225) grad: 0.2590 (0.2630) time: 0.4468 data: 0.0041 max mem: 22448 +train: [10] [220/400] eta: 0:01:22 lr: 0.000210 loss: 2.3339 (2.3237) grad: 0.2590 (0.2631) time: 0.4525 data: 0.0043 max mem: 22448 +train: [10] [240/400] eta: 0:01:13 lr: 0.000208 loss: 2.2982 (2.3232) grad: 0.2605 (0.2631) time: 0.4538 data: 0.0044 max mem: 22448 +train: [10] [260/400] eta: 0:01:03 lr: 0.000207 loss: 2.3455 (2.3241) grad: 0.2640 (0.2633) time: 0.4472 data: 0.0042 max mem: 22448 +train: [10] [280/400] eta: 0:00:54 lr: 0.000205 loss: 2.3512 (2.3241) grad: 0.2647 (0.2636) time: 0.4452 data: 0.0040 max mem: 22448 +train: [10] [300/400] eta: 0:00:45 lr: 0.000204 loss: 2.2696 (2.3211) grad: 0.2611 (0.2632) time: 0.4693 data: 0.0043 max mem: 22448 +train: [10] [320/400] eta: 0:00:36 lr: 0.000202 loss: 2.2677 (2.3186) grad: 0.2611 (0.2634) time: 0.4531 data: 0.0043 max mem: 22448 +train: [10] [340/400] eta: 0:00:27 lr: 0.000201 loss: 2.3053 (2.3182) grad: 0.2652 (0.2634) time: 0.4582 data: 0.0043 max mem: 22448 +train: [10] [360/400] eta: 0:00:18 lr: 0.000199 loss: 2.2997 (2.3165) grad: 0.2622 (0.2632) time: 0.4616 data: 0.0044 max mem: 22448 +train: [10] [380/400] eta: 0:00:09 lr: 0.000198 loss: 2.2831 (2.3154) grad: 0.2622 (0.2632) time: 0.4577 data: 0.0044 max mem: 22448 +train: [10] [399/400] eta: 0:00:00 lr: 0.000196 loss: 2.2930 (2.3164) grad: 0.2674 (0.2636) time: 0.4512 data: 0.0041 max mem: 22448 +train: [10] Total time: 0:03:02 (0.4565 s / it) +train: [10] Summary: lr: 0.000196 loss: 2.2930 (2.3164) grad: 0.2674 (0.2636) +eval (validation): [10] [ 0/85] eta: 0:04:25 time: 3.1179 data: 2.8260 max mem: 22448 +eval (validation): [10] [20/85] eta: 0:00:33 time: 0.3790 data: 0.0082 max mem: 22448 +eval (validation): [10] [40/85] eta: 0:00:19 time: 0.3653 data: 0.0046 max mem: 22448 +eval (validation): [10] [60/85] eta: 0:00:10 time: 0.3559 data: 0.0041 max mem: 22448 +eval (validation): [10] [80/85] eta: 0:00:01 time: 0.3433 data: 0.0041 max mem: 22448 +eval (validation): [10] [84/85] eta: 0:00:00 time: 0.3338 data: 0.0041 max mem: 22448 +eval (validation): [10] Total time: 0:00:33 (0.3941 s / it) +cv: [10] best hparam: (0.44, 1.0) (019) ('019_lr4.4e-01_wd1.0e+00') loss: 2.394 acc: 0.284 f1: 0.220 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [11] [ 0/400] eta: 0:21:16 lr: nan time: 3.1910 data: 2.8058 max mem: 22448 +train: [11] [ 20/400] eta: 0:03:35 lr: 0.000195 loss: 2.2447 (2.2556) grad: 0.2526 (0.2601) time: 0.4347 data: 0.0039 max mem: 22448 +train: [11] [ 40/400] eta: 0:03:04 lr: 0.000193 loss: 2.2484 (2.2674) grad: 0.2533 (0.2606) time: 0.4555 data: 0.0037 max mem: 22448 +train: [11] [ 60/400] eta: 0:02:49 lr: 0.000192 loss: 2.2216 (2.2493) grad: 0.2640 (0.2638) time: 0.4676 data: 0.0044 max mem: 22448 +train: [11] [ 80/400] eta: 0:02:35 lr: 0.000190 loss: 2.2265 (2.2637) grad: 0.2696 (0.2659) time: 0.4568 data: 0.0043 max mem: 22448 +train: [11] [100/400] eta: 0:02:23 lr: 0.000189 loss: 2.2279 (2.2554) grad: 0.2591 (0.2645) time: 0.4468 data: 0.0042 max mem: 22448 +train: [11] [120/400] eta: 0:02:12 lr: 0.000187 loss: 2.1825 (2.2431) grad: 0.2552 (0.2635) time: 0.4433 data: 0.0043 max mem: 22448 +train: [11] [140/400] eta: 0:02:01 lr: 0.000186 loss: 2.2327 (2.2489) grad: 0.2587 (0.2641) time: 0.4358 data: 0.0042 max mem: 22448 +train: [11] [160/400] eta: 0:01:51 lr: 0.000184 loss: 2.2733 (2.2551) grad: 0.2679 (0.2649) time: 0.4313 data: 0.0040 max mem: 22448 +train: [11] [180/400] eta: 0:01:41 lr: 0.000183 loss: 2.2778 (2.2583) grad: 0.2745 (0.2668) time: 0.4492 data: 0.0042 max mem: 22448 +train: [11] [200/400] eta: 0:01:31 lr: 0.000181 loss: 2.2487 (2.2588) grad: 0.2742 (0.2668) time: 0.4402 data: 0.0043 max mem: 22448 +train: [11] [220/400] eta: 0:01:22 lr: 0.000180 loss: 2.2940 (2.2657) grad: 0.2638 (0.2662) time: 0.4459 data: 0.0042 max mem: 22448 +train: [11] [240/400] eta: 0:01:13 lr: 0.000178 loss: 2.3008 (2.2646) grad: 0.2551 (0.2663) time: 0.4412 data: 0.0042 max mem: 22448 +train: [11] [260/400] eta: 0:01:03 lr: 0.000177 loss: 2.2530 (2.2633) grad: 0.2691 (0.2666) time: 0.4524 data: 0.0042 max mem: 22448 +train: [11] [280/400] eta: 0:00:54 lr: 0.000175 loss: 2.2501 (2.2631) grad: 0.2712 (0.2667) time: 0.4394 data: 0.0042 max mem: 22448 +train: [11] [300/400] eta: 0:00:45 lr: 0.000174 loss: 2.2700 (2.2669) grad: 0.2703 (0.2671) time: 0.4460 data: 0.0042 max mem: 22448 +train: [11] [320/400] eta: 0:00:36 lr: 0.000172 loss: 2.2983 (2.2676) grad: 0.2729 (0.2678) time: 0.4545 data: 0.0043 max mem: 22448 +train: [11] [340/400] eta: 0:00:27 lr: 0.000170 loss: 2.2820 (2.2685) grad: 0.2729 (0.2687) time: 0.4423 data: 0.0044 max mem: 22448 +train: [11] [360/400] eta: 0:00:18 lr: 0.000169 loss: 2.2820 (2.2686) grad: 0.2742 (0.2691) time: 0.4479 data: 0.0042 max mem: 22448 +train: [11] [380/400] eta: 0:00:09 lr: 0.000167 loss: 2.2231 (2.2657) grad: 0.2725 (0.2689) time: 0.4388 data: 0.0041 max mem: 22448 +train: [11] [399/400] eta: 0:00:00 lr: 0.000166 loss: 2.2624 (2.2696) grad: 0.2679 (0.2688) time: 0.4523 data: 0.0041 max mem: 22448 +train: [11] Total time: 0:03:01 (0.4533 s / it) +train: [11] Summary: lr: 0.000166 loss: 2.2624 (2.2696) grad: 0.2679 (0.2688) +eval (validation): [11] [ 0/85] eta: 0:04:25 time: 3.1181 data: 2.8273 max mem: 22448 +eval (validation): [11] [20/85] eta: 0:00:32 time: 0.3708 data: 0.0049 max mem: 22448 +eval (validation): [11] [40/85] eta: 0:00:19 time: 0.3483 data: 0.0038 max mem: 22448 +eval (validation): [11] [60/85] eta: 0:00:09 time: 0.3369 data: 0.0042 max mem: 22448 +eval (validation): [11] [80/85] eta: 0:00:01 time: 0.3350 data: 0.0039 max mem: 22448 +eval (validation): [11] [84/85] eta: 0:00:00 time: 0.3280 data: 0.0039 max mem: 22448 +eval (validation): [11] Total time: 0:00:32 (0.3815 s / it) +cv: [11] best hparam: (0.44, 1.0) (019) ('019_lr4.4e-01_wd1.0e+00') loss: 2.408 acc: 0.282 f1: 0.221 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [12] [ 0/400] eta: 0:20:48 lr: nan time: 3.1217 data: 2.7853 max mem: 22448 +train: [12] [ 20/400] eta: 0:03:34 lr: 0.000164 loss: 2.1255 (2.1578) grad: 0.2473 (0.2510) time: 0.4371 data: 0.0034 max mem: 22448 +train: [12] [ 40/400] eta: 0:03:01 lr: 0.000163 loss: 2.1721 (2.1713) grad: 0.2542 (0.2538) time: 0.4387 data: 0.0043 max mem: 22448 +train: [12] [ 60/400] eta: 0:02:44 lr: 0.000161 loss: 2.1721 (2.1677) grad: 0.2533 (0.2539) time: 0.4453 data: 0.0043 max mem: 22448 +train: [12] [ 80/400] eta: 0:02:31 lr: 0.000160 loss: 2.1661 (2.1795) grad: 0.2574 (0.2553) time: 0.4375 data: 0.0043 max mem: 22448 +train: [12] [100/400] eta: 0:02:19 lr: 0.000158 loss: 2.2268 (2.1843) grad: 0.2621 (0.2569) time: 0.4373 data: 0.0042 max mem: 22448 +train: [12] [120/400] eta: 0:02:10 lr: 0.000156 loss: 2.2018 (2.1907) grad: 0.2574 (0.2564) time: 0.4683 data: 0.0042 max mem: 22448 +train: [12] [140/400] eta: 0:02:01 lr: 0.000155 loss: 2.1919 (2.1894) grad: 0.2578 (0.2588) time: 0.4630 data: 0.0044 max mem: 22448 +train: [12] [160/400] eta: 0:01:51 lr: 0.000153 loss: 2.1753 (2.1914) grad: 0.2729 (0.2609) time: 0.4513 data: 0.0044 max mem: 22448 +train: [12] [180/400] eta: 0:01:41 lr: 0.000152 loss: 2.2001 (2.1952) grad: 0.2756 (0.2621) time: 0.4461 data: 0.0041 max mem: 22448 +train: [12] [200/400] eta: 0:01:32 lr: 0.000150 loss: 2.2343 (2.2024) grad: 0.2703 (0.2631) time: 0.4509 data: 0.0044 max mem: 22448 +train: [12] [220/400] eta: 0:01:22 lr: 0.000149 loss: 2.2448 (2.2060) grad: 0.2650 (0.2633) time: 0.4505 data: 0.0041 max mem: 22448 +train: [12] [240/400] eta: 0:01:13 lr: 0.000147 loss: 2.2340 (2.2052) grad: 0.2669 (0.2646) time: 0.4661 data: 0.0043 max mem: 22448 +train: [12] [260/400] eta: 0:01:04 lr: 0.000145 loss: 2.1722 (2.2043) grad: 0.2687 (0.2647) time: 0.4583 data: 0.0043 max mem: 22448 +train: [12] [280/400] eta: 0:00:55 lr: 0.000144 loss: 2.1670 (2.2013) grad: 0.2640 (0.2647) time: 0.4556 data: 0.0043 max mem: 22448 +train: [12] [300/400] eta: 0:00:45 lr: 0.000142 loss: 2.1670 (2.2029) grad: 0.2668 (0.2654) time: 0.4472 data: 0.0041 max mem: 22448 +train: [12] [320/400] eta: 0:00:36 lr: 0.000141 loss: 2.1748 (2.2036) grad: 0.2668 (0.2656) time: 0.4329 data: 0.0043 max mem: 22448 +train: [12] [340/400] eta: 0:00:27 lr: 0.000139 loss: 2.1796 (2.2026) grad: 0.2673 (0.2654) time: 0.4696 data: 0.0043 max mem: 22448 +train: [12] [360/400] eta: 0:00:18 lr: 0.000138 loss: 2.1796 (2.2018) grad: 0.2611 (0.2654) time: 0.4628 data: 0.0042 max mem: 22448 +train: [12] [380/400] eta: 0:00:09 lr: 0.000136 loss: 2.2050 (2.2032) grad: 0.2612 (0.2655) time: 0.4460 data: 0.0044 max mem: 22448 +train: [12] [399/400] eta: 0:00:00 lr: 0.000134 loss: 2.1993 (2.2025) grad: 0.2679 (0.2660) time: 0.4573 data: 0.0042 max mem: 22448 +train: [12] Total time: 0:03:03 (0.4580 s / it) +train: [12] Summary: lr: 0.000134 loss: 2.1993 (2.2025) grad: 0.2679 (0.2660) +eval (validation): [12] [ 0/85] eta: 0:04:37 time: 3.2686 data: 2.9766 max mem: 22448 +eval (validation): [12] [20/85] eta: 0:00:33 time: 0.3702 data: 0.0035 max mem: 22448 +eval (validation): [12] [40/85] eta: 0:00:19 time: 0.3333 data: 0.0039 max mem: 22448 +eval (validation): [12] [60/85] eta: 0:00:09 time: 0.3521 data: 0.0041 max mem: 22448 +eval (validation): [12] [80/85] eta: 0:00:01 time: 0.3347 data: 0.0041 max mem: 22448 +eval (validation): [12] [84/85] eta: 0:00:00 time: 0.3281 data: 0.0040 max mem: 22448 +eval (validation): [12] Total time: 0:00:32 (0.3837 s / it) +cv: [12] best hparam: (0.38, 1.0) (018) ('018_lr3.8e-01_wd1.0e+00') loss: 2.428 acc: 0.276 f1: 0.215 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [13] [ 0/400] eta: 0:21:27 lr: nan time: 3.2177 data: 2.8398 max mem: 22448 +train: [13] [ 20/400] eta: 0:03:43 lr: 0.000133 loss: 2.1280 (2.1406) grad: 0.2625 (0.2619) time: 0.4563 data: 0.0027 max mem: 22448 +train: [13] [ 40/400] eta: 0:03:07 lr: 0.000131 loss: 2.1296 (2.1407) grad: 0.2577 (0.2601) time: 0.4496 data: 0.0041 max mem: 22448 +train: [13] [ 60/400] eta: 0:02:47 lr: 0.000130 loss: 2.1854 (2.1460) grad: 0.2556 (0.2605) time: 0.4400 data: 0.0040 max mem: 22448 +train: [13] [ 80/400] eta: 0:02:33 lr: 0.000128 loss: 2.1448 (2.1436) grad: 0.2595 (0.2623) time: 0.4388 data: 0.0041 max mem: 22448 +train: [13] [100/400] eta: 0:02:21 lr: 0.000127 loss: 2.1019 (2.1413) grad: 0.2595 (0.2616) time: 0.4422 data: 0.0040 max mem: 22448 +train: [13] [120/400] eta: 0:02:10 lr: 0.000125 loss: 2.1013 (2.1394) grad: 0.2654 (0.2626) time: 0.4395 data: 0.0041 max mem: 22448 +train: [13] [140/400] eta: 0:02:00 lr: 0.000124 loss: 2.1885 (2.1522) grad: 0.2790 (0.2640) time: 0.4456 data: 0.0045 max mem: 22448 +train: [13] [160/400] eta: 0:01:50 lr: 0.000122 loss: 2.1893 (2.1521) grad: 0.2765 (0.2649) time: 0.4493 data: 0.0045 max mem: 22448 +train: [13] [180/400] eta: 0:01:41 lr: 0.000120 loss: 2.1704 (2.1583) grad: 0.2673 (0.2654) time: 0.4498 data: 0.0044 max mem: 22448 +train: [13] [200/400] eta: 0:01:31 lr: 0.000119 loss: 2.1360 (2.1525) grad: 0.2612 (0.2652) time: 0.4386 data: 0.0044 max mem: 22448 +train: [13] [220/400] eta: 0:01:22 lr: 0.000117 loss: 2.0980 (2.1526) grad: 0.2606 (0.2657) time: 0.4461 data: 0.0043 max mem: 22448 +train: [13] [240/400] eta: 0:01:12 lr: 0.000116 loss: 2.1887 (2.1543) grad: 0.2684 (0.2657) time: 0.4385 data: 0.0044 max mem: 22448 +train: [13] [260/400] eta: 0:01:03 lr: 0.000114 loss: 2.1483 (2.1567) grad: 0.2602 (0.2649) time: 0.4432 data: 0.0043 max mem: 22448 +train: [13] [280/400] eta: 0:00:54 lr: 0.000113 loss: 2.1330 (2.1545) grad: 0.2524 (0.2643) time: 0.4472 data: 0.0042 max mem: 22448 +train: [13] [300/400] eta: 0:00:45 lr: 0.000111 loss: 2.0848 (2.1527) grad: 0.2536 (0.2636) time: 0.4481 data: 0.0042 max mem: 22448 +train: [13] [320/400] eta: 0:00:36 lr: 0.000110 loss: 2.1622 (2.1551) grad: 0.2685 (0.2644) time: 0.4445 data: 0.0042 max mem: 22448 +train: [13] [340/400] eta: 0:00:27 lr: 0.000108 loss: 2.1438 (2.1546) grad: 0.2682 (0.2641) time: 0.4484 data: 0.0041 max mem: 22448 +train: [13] [360/400] eta: 0:00:18 lr: 0.000107 loss: 2.1438 (2.1555) grad: 0.2685 (0.2647) time: 0.4362 data: 0.0042 max mem: 22448 +train: [13] [380/400] eta: 0:00:09 lr: 0.000105 loss: 2.1605 (2.1553) grad: 0.2718 (0.2650) time: 0.4474 data: 0.0041 max mem: 22448 +train: [13] [399/400] eta: 0:00:00 lr: 0.000104 loss: 2.1461 (2.1565) grad: 0.2689 (0.2652) time: 0.4410 data: 0.0042 max mem: 22448 +train: [13] Total time: 0:03:00 (0.4518 s / it) +train: [13] Summary: lr: 0.000104 loss: 2.1461 (2.1565) grad: 0.2689 (0.2652) +eval (validation): [13] [ 0/85] eta: 0:04:28 time: 3.1608 data: 2.8808 max mem: 22448 +eval (validation): [13] [20/85] eta: 0:00:33 time: 0.3768 data: 0.0043 max mem: 22448 +eval (validation): [13] [40/85] eta: 0:00:19 time: 0.3424 data: 0.0039 max mem: 22448 +eval (validation): [13] [60/85] eta: 0:00:10 time: 0.3460 data: 0.0044 max mem: 22448 +eval (validation): [13] [80/85] eta: 0:00:01 time: 0.3401 data: 0.0039 max mem: 22448 +eval (validation): [13] [84/85] eta: 0:00:00 time: 0.3310 data: 0.0040 max mem: 22448 +eval (validation): [13] Total time: 0:00:32 (0.3854 s / it) +cv: [13] best hparam: (0.38, 1.0) (018) ('018_lr3.8e-01_wd1.0e+00') loss: 2.412 acc: 0.280 f1: 0.219 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [14] [ 0/400] eta: 0:25:43 lr: nan time: 3.8581 data: 3.4604 max mem: 22448 +train: [14] [ 20/400] eta: 0:04:01 lr: 0.000102 loss: 2.0463 (2.0552) grad: 0.2518 (0.2512) time: 0.4754 data: 0.0026 max mem: 22448 +train: [14] [ 40/400] eta: 0:03:17 lr: 0.000101 loss: 2.0751 (2.0688) grad: 0.2460 (0.2520) time: 0.4554 data: 0.0043 max mem: 22448 +train: [14] [ 60/400] eta: 0:02:56 lr: 0.000099 loss: 2.0855 (2.0782) grad: 0.2618 (0.2558) time: 0.4633 data: 0.0042 max mem: 22448 +train: [14] [ 80/400] eta: 0:02:41 lr: 0.000098 loss: 2.0796 (2.0904) grad: 0.2550 (0.2548) time: 0.4555 data: 0.0042 max mem: 22448 +train: [14] [100/400] eta: 0:02:28 lr: 0.000096 loss: 2.1240 (2.0957) grad: 0.2552 (0.2559) time: 0.4544 data: 0.0043 max mem: 22448 +train: [14] [120/400] eta: 0:02:15 lr: 0.000095 loss: 2.0704 (2.0920) grad: 0.2579 (0.2571) time: 0.4405 data: 0.0042 max mem: 22448 +train: [14] [140/400] eta: 0:02:05 lr: 0.000093 loss: 2.0596 (2.0933) grad: 0.2653 (0.2587) time: 0.4743 data: 0.0043 max mem: 22448 +train: [14] [160/400] eta: 0:01:55 lr: 0.000092 loss: 2.0671 (2.0937) grad: 0.2673 (0.2596) time: 0.4566 data: 0.0044 max mem: 22448 +train: [14] [180/400] eta: 0:01:44 lr: 0.000090 loss: 2.0671 (2.0921) grad: 0.2636 (0.2606) time: 0.4476 data: 0.0047 max mem: 22448 +train: [14] [200/400] eta: 0:01:34 lr: 0.000089 loss: 2.0710 (2.0921) grad: 0.2651 (0.2616) time: 0.4513 data: 0.0043 max mem: 22448 +train: [14] [220/400] eta: 0:01:25 lr: 0.000088 loss: 2.1005 (2.0929) grad: 0.2662 (0.2626) time: 0.4566 data: 0.0042 max mem: 22448 +train: [14] [240/400] eta: 0:01:15 lr: 0.000086 loss: 2.1067 (2.0960) grad: 0.2609 (0.2625) time: 0.4356 data: 0.0040 max mem: 22448 +train: [14] [260/400] eta: 0:01:05 lr: 0.000085 loss: 2.1026 (2.0972) grad: 0.2613 (0.2627) time: 0.4502 data: 0.0042 max mem: 22448 +train: [14] [280/400] eta: 0:00:56 lr: 0.000083 loss: 2.0974 (2.0976) grad: 0.2605 (0.2622) time: 0.4535 data: 0.0042 max mem: 22448 +train: [14] [300/400] eta: 0:00:46 lr: 0.000082 loss: 2.1200 (2.1023) grad: 0.2605 (0.2623) time: 0.4485 data: 0.0043 max mem: 22448 +train: [14] [320/400] eta: 0:00:37 lr: 0.000081 loss: 2.1373 (2.1041) grad: 0.2647 (0.2628) time: 0.4454 data: 0.0043 max mem: 22448 +train: [14] [340/400] eta: 0:00:27 lr: 0.000079 loss: 2.1162 (2.1037) grad: 0.2725 (0.2633) time: 0.4455 data: 0.0043 max mem: 22448 +train: [14] [360/400] eta: 0:00:18 lr: 0.000078 loss: 2.1058 (2.1046) grad: 0.2632 (0.2630) time: 0.4526 data: 0.0042 max mem: 22448 +train: [14] [380/400] eta: 0:00:09 lr: 0.000076 loss: 2.0888 (2.1023) grad: 0.2572 (0.2628) time: 0.4497 data: 0.0044 max mem: 22448 +train: [14] [399/400] eta: 0:00:00 lr: 0.000075 loss: 2.0747 (2.1035) grad: 0.2636 (0.2634) time: 0.4403 data: 0.0045 max mem: 22448 +train: [14] Total time: 0:03:04 (0.4614 s / it) +train: [14] Summary: lr: 0.000075 loss: 2.0747 (2.1035) grad: 0.2636 (0.2634) +eval (validation): [14] [ 0/85] eta: 0:04:23 time: 3.0953 data: 2.8487 max mem: 22448 +eval (validation): [14] [20/85] eta: 0:00:29 time: 0.3252 data: 0.0040 max mem: 22448 +eval (validation): [14] [40/85] eta: 0:00:18 time: 0.3626 data: 0.0039 max mem: 22448 +eval (validation): [14] [60/85] eta: 0:00:09 time: 0.3424 data: 0.0044 max mem: 22448 +eval (validation): [14] [80/85] eta: 0:00:01 time: 0.3328 data: 0.0038 max mem: 22448 +eval (validation): [14] [84/85] eta: 0:00:00 time: 0.3228 data: 0.0036 max mem: 22448 +eval (validation): [14] Total time: 0:00:31 (0.3743 s / it) +cv: [14] best hparam: (0.38, 1.0) (018) ('018_lr3.8e-01_wd1.0e+00') loss: 2.413 acc: 0.282 f1: 0.219 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [15] [ 0/400] eta: 0:20:44 lr: nan time: 3.1121 data: 2.7880 max mem: 22448 +train: [15] [ 20/400] eta: 0:03:32 lr: 0.000074 loss: 2.0405 (2.0420) grad: 0.2496 (0.2519) time: 0.4314 data: 0.0042 max mem: 22448 +train: [15] [ 40/400] eta: 0:03:01 lr: 0.000072 loss: 2.0405 (2.0424) grad: 0.2496 (0.2514) time: 0.4481 data: 0.0041 max mem: 22448 +train: [15] [ 60/400] eta: 0:02:45 lr: 0.000071 loss: 2.0214 (2.0421) grad: 0.2471 (0.2511) time: 0.4452 data: 0.0042 max mem: 22448 +train: [15] [ 80/400] eta: 0:02:32 lr: 0.000070 loss: 2.0174 (2.0353) grad: 0.2471 (0.2499) time: 0.4487 data: 0.0043 max mem: 22448 +train: [15] [100/400] eta: 0:02:20 lr: 0.000068 loss: 1.9951 (2.0326) grad: 0.2474 (0.2510) time: 0.4390 data: 0.0041 max mem: 22448 +train: [15] [120/400] eta: 0:02:10 lr: 0.000067 loss: 2.0464 (2.0386) grad: 0.2584 (0.2527) time: 0.4429 data: 0.0041 max mem: 22448 +train: [15] [140/400] eta: 0:02:00 lr: 0.000066 loss: 2.0566 (2.0443) grad: 0.2613 (0.2555) time: 0.4462 data: 0.0044 max mem: 22448 +train: [15] [160/400] eta: 0:01:50 lr: 0.000064 loss: 2.0442 (2.0446) grad: 0.2613 (0.2564) time: 0.4482 data: 0.0043 max mem: 22448 +train: [15] [180/400] eta: 0:01:41 lr: 0.000063 loss: 2.0513 (2.0540) grad: 0.2660 (0.2582) time: 0.4505 data: 0.0041 max mem: 22448 +train: [15] [200/400] eta: 0:01:31 lr: 0.000062 loss: 2.0969 (2.0535) grad: 0.2619 (0.2582) time: 0.4506 data: 0.0045 max mem: 22448 +train: [15] [220/400] eta: 0:01:22 lr: 0.000061 loss: 2.0603 (2.0515) grad: 0.2574 (0.2583) time: 0.4662 data: 0.0042 max mem: 22448 +train: [15] [240/400] eta: 0:01:13 lr: 0.000059 loss: 2.0386 (2.0523) grad: 0.2617 (0.2587) time: 0.4578 data: 0.0043 max mem: 22448 +train: [15] [260/400] eta: 0:01:04 lr: 0.000058 loss: 2.0717 (2.0547) grad: 0.2611 (0.2587) time: 0.4577 data: 0.0041 max mem: 22448 +train: [15] [280/400] eta: 0:00:55 lr: 0.000057 loss: 2.0603 (2.0538) grad: 0.2503 (0.2580) time: 0.4534 data: 0.0041 max mem: 22448 +train: [15] [300/400] eta: 0:00:45 lr: 0.000056 loss: 2.0083 (2.0533) grad: 0.2467 (0.2580) time: 0.4614 data: 0.0045 max mem: 22448 +train: [15] [320/400] eta: 0:00:36 lr: 0.000054 loss: 2.0541 (2.0546) grad: 0.2538 (0.2580) time: 0.4705 data: 0.0044 max mem: 22448 +train: [15] [340/400] eta: 0:00:27 lr: 0.000053 loss: 2.0774 (2.0564) grad: 0.2554 (0.2579) time: 0.4685 data: 0.0044 max mem: 22448 +train: [15] [360/400] eta: 0:00:18 lr: 0.000052 loss: 2.0745 (2.0571) grad: 0.2554 (0.2580) time: 0.4662 data: 0.0044 max mem: 22448 +train: [15] [380/400] eta: 0:00:09 lr: 0.000051 loss: 2.0271 (2.0549) grad: 0.2496 (0.2574) time: 0.4488 data: 0.0042 max mem: 22448 +train: [15] [399/400] eta: 0:00:00 lr: 0.000050 loss: 2.0269 (2.0559) grad: 0.2474 (0.2571) time: 0.4494 data: 0.0042 max mem: 22448 +train: [15] Total time: 0:03:03 (0.4595 s / it) +train: [15] Summary: lr: 0.000050 loss: 2.0269 (2.0559) grad: 0.2474 (0.2571) +eval (validation): [15] [ 0/85] eta: 0:05:14 time: 3.6968 data: 3.4506 max mem: 22448 +eval (validation): [15] [20/85] eta: 0:00:33 time: 0.3572 data: 0.0041 max mem: 22448 +eval (validation): [15] [40/85] eta: 0:00:19 time: 0.3688 data: 0.0043 max mem: 22448 +eval (validation): [15] [60/85] eta: 0:00:10 time: 0.3485 data: 0.0036 max mem: 22448 +eval (validation): [15] [80/85] eta: 0:00:01 time: 0.3312 data: 0.0041 max mem: 22448 +eval (validation): [15] [84/85] eta: 0:00:00 time: 0.3286 data: 0.0040 max mem: 22448 +eval (validation): [15] Total time: 0:00:33 (0.3921 s / it) +cv: [15] best hparam: (0.38, 1.0) (018) ('018_lr3.8e-01_wd1.0e+00') loss: 2.409 acc: 0.280 f1: 0.220 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [16] [ 0/400] eta: 0:21:50 lr: nan time: 3.2773 data: 2.9371 max mem: 22448 +train: [16] [ 20/400] eta: 0:03:38 lr: 0.000048 loss: 1.9947 (2.0272) grad: 0.2376 (0.2389) time: 0.4412 data: 0.0043 max mem: 22448 +train: [16] [ 40/400] eta: 0:03:03 lr: 0.000047 loss: 1.9790 (2.0047) grad: 0.2389 (0.2396) time: 0.4415 data: 0.0034 max mem: 22448 +train: [16] [ 60/400] eta: 0:02:46 lr: 0.000046 loss: 1.9656 (2.0025) grad: 0.2442 (0.2430) time: 0.4507 data: 0.0042 max mem: 22448 +train: [16] [ 80/400] eta: 0:02:34 lr: 0.000045 loss: 2.0228 (2.0111) grad: 0.2546 (0.2466) time: 0.4541 data: 0.0043 max mem: 22448 +train: [16] [100/400] eta: 0:02:21 lr: 0.000044 loss: 2.0361 (2.0128) grad: 0.2557 (0.2479) time: 0.4380 data: 0.0041 max mem: 22448 +train: [16] [120/400] eta: 0:02:11 lr: 0.000043 loss: 2.0037 (2.0119) grad: 0.2493 (0.2486) time: 0.4511 data: 0.0042 max mem: 22448 +train: [16] [140/400] eta: 0:02:00 lr: 0.000042 loss: 2.0029 (2.0135) grad: 0.2487 (0.2487) time: 0.4365 data: 0.0041 max mem: 22448 +train: [16] [160/400] eta: 0:01:50 lr: 0.000041 loss: 2.0029 (2.0210) grad: 0.2533 (0.2501) time: 0.4405 data: 0.0044 max mem: 22448 +train: [16] [180/400] eta: 0:01:41 lr: 0.000040 loss: 2.0128 (2.0212) grad: 0.2533 (0.2498) time: 0.4574 data: 0.0041 max mem: 22448 +train: [16] [200/400] eta: 0:01:31 lr: 0.000039 loss: 1.9967 (2.0172) grad: 0.2426 (0.2491) time: 0.4441 data: 0.0041 max mem: 22448 +train: [16] [220/400] eta: 0:01:22 lr: 0.000038 loss: 1.9932 (2.0170) grad: 0.2427 (0.2487) time: 0.4425 data: 0.0041 max mem: 22448 +train: [16] [240/400] eta: 0:01:13 lr: 0.000036 loss: 2.0031 (2.0160) grad: 0.2427 (0.2488) time: 0.4516 data: 0.0041 max mem: 22448 +train: [16] [260/400] eta: 0:01:03 lr: 0.000035 loss: 2.0089 (2.0184) grad: 0.2570 (0.2496) time: 0.4490 data: 0.0044 max mem: 22448 +train: [16] [280/400] eta: 0:00:54 lr: 0.000034 loss: 2.0221 (2.0193) grad: 0.2558 (0.2499) time: 0.4513 data: 0.0041 max mem: 22448 +train: [16] [300/400] eta: 0:00:45 lr: 0.000033 loss: 2.0262 (2.0215) grad: 0.2479 (0.2503) time: 0.4461 data: 0.0041 max mem: 22448 +train: [16] [320/400] eta: 0:00:36 lr: 0.000032 loss: 2.0801 (2.0259) grad: 0.2578 (0.2508) time: 0.4473 data: 0.0042 max mem: 22448 +train: [16] [340/400] eta: 0:00:27 lr: 0.000031 loss: 2.0316 (2.0261) grad: 0.2520 (0.2510) time: 0.4452 data: 0.0042 max mem: 22448 +train: [16] [360/400] eta: 0:00:18 lr: 0.000031 loss: 2.0038 (2.0267) grad: 0.2527 (0.2512) time: 0.4457 data: 0.0042 max mem: 22448 +train: [16] [380/400] eta: 0:00:09 lr: 0.000030 loss: 2.0183 (2.0267) grad: 0.2548 (0.2516) time: 0.4439 data: 0.0043 max mem: 22448 +train: [16] [399/400] eta: 0:00:00 lr: 0.000029 loss: 2.0009 (2.0265) grad: 0.2615 (0.2522) time: 0.4457 data: 0.0043 max mem: 22448 +train: [16] Total time: 0:03:01 (0.4536 s / it) +train: [16] Summary: lr: 0.000029 loss: 2.0009 (2.0265) grad: 0.2615 (0.2522) +eval (validation): [16] [ 0/85] eta: 0:04:35 time: 3.2448 data: 2.9435 max mem: 22448 +eval (validation): [16] [20/85] eta: 0:00:32 time: 0.3676 data: 0.0036 max mem: 22448 +eval (validation): [16] [40/85] eta: 0:00:18 time: 0.3357 data: 0.0043 max mem: 22448 +eval (validation): [16] [60/85] eta: 0:00:09 time: 0.3479 data: 0.0042 max mem: 22448 +eval (validation): [16] [80/85] eta: 0:00:01 time: 0.3302 data: 0.0040 max mem: 22448 +eval (validation): [16] [84/85] eta: 0:00:00 time: 0.3251 data: 0.0038 max mem: 22448 +eval (validation): [16] Total time: 0:00:32 (0.3812 s / it) +cv: [16] best hparam: (0.38, 1.0) (018) ('018_lr3.8e-01_wd1.0e+00') loss: 2.409 acc: 0.281 f1: 0.221 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [17] [ 0/400] eta: 0:20:21 lr: nan time: 3.0539 data: 2.7243 max mem: 22448 +train: [17] [ 20/400] eta: 0:03:44 lr: 0.000028 loss: 1.9501 (1.9731) grad: 0.2337 (0.2401) time: 0.4690 data: 0.0039 max mem: 22448 +train: [17] [ 40/400] eta: 0:03:05 lr: 0.000027 loss: 1.9865 (1.9943) grad: 0.2460 (0.2433) time: 0.4375 data: 0.0037 max mem: 22448 +train: [17] [ 60/400] eta: 0:02:48 lr: 0.000026 loss: 1.9957 (2.0028) grad: 0.2369 (0.2410) time: 0.4551 data: 0.0041 max mem: 22448 +train: [17] [ 80/400] eta: 0:02:35 lr: 0.000025 loss: 1.9773 (1.9875) grad: 0.2369 (0.2411) time: 0.4515 data: 0.0042 max mem: 22448 +train: [17] [100/400] eta: 0:02:23 lr: 0.000024 loss: 1.9643 (1.9948) grad: 0.2408 (0.2410) time: 0.4512 data: 0.0041 max mem: 22448 +train: [17] [120/400] eta: 0:02:13 lr: 0.000023 loss: 1.9887 (1.9923) grad: 0.2386 (0.2413) time: 0.4693 data: 0.0043 max mem: 22448 +train: [17] [140/400] eta: 0:02:02 lr: 0.000023 loss: 1.9956 (1.9922) grad: 0.2383 (0.2415) time: 0.4429 data: 0.0041 max mem: 22448 +train: [17] [160/400] eta: 0:01:53 lr: 0.000022 loss: 2.0130 (1.9910) grad: 0.2444 (0.2420) time: 0.4619 data: 0.0044 max mem: 22448 +train: [17] [180/400] eta: 0:01:43 lr: 0.000021 loss: 1.9965 (1.9904) grad: 0.2419 (0.2414) time: 0.4523 data: 0.0042 max mem: 22448 +train: [17] [200/400] eta: 0:01:33 lr: 0.000020 loss: 1.9965 (1.9893) grad: 0.2410 (0.2412) time: 0.4452 data: 0.0042 max mem: 22448 +train: [17] [220/400] eta: 0:01:23 lr: 0.000019 loss: 2.0057 (1.9909) grad: 0.2450 (0.2419) time: 0.4464 data: 0.0041 max mem: 22448 +train: [17] [240/400] eta: 0:01:14 lr: 0.000019 loss: 2.0157 (1.9908) grad: 0.2414 (0.2424) time: 0.4710 data: 0.0044 max mem: 22448 +train: [17] [260/400] eta: 0:01:04 lr: 0.000018 loss: 1.9817 (1.9905) grad: 0.2394 (0.2427) time: 0.4433 data: 0.0042 max mem: 22448 +train: [17] [280/400] eta: 0:00:55 lr: 0.000017 loss: 1.9711 (1.9909) grad: 0.2440 (0.2427) time: 0.4478 data: 0.0043 max mem: 22448 +train: [17] [300/400] eta: 0:00:46 lr: 0.000016 loss: 2.0013 (1.9918) grad: 0.2426 (0.2426) time: 0.4498 data: 0.0043 max mem: 22448 +train: [17] [320/400] eta: 0:00:36 lr: 0.000016 loss: 1.9940 (1.9914) grad: 0.2313 (0.2419) time: 0.4422 data: 0.0040 max mem: 22448 +train: [17] [340/400] eta: 0:00:27 lr: 0.000015 loss: 1.9802 (1.9921) grad: 0.2304 (0.2423) time: 0.4380 data: 0.0042 max mem: 22448 +train: [17] [360/400] eta: 0:00:18 lr: 0.000014 loss: 1.9894 (1.9929) grad: 0.2419 (0.2424) time: 0.4576 data: 0.0042 max mem: 22448 +train: [17] [380/400] eta: 0:00:09 lr: 0.000014 loss: 1.9772 (1.9921) grad: 0.2446 (0.2431) time: 0.4563 data: 0.0042 max mem: 22448 +train: [17] [399/400] eta: 0:00:00 lr: 0.000013 loss: 1.9757 (1.9911) grad: 0.2456 (0.2429) time: 0.4434 data: 0.0042 max mem: 22448 +train: [17] Total time: 0:03:03 (0.4584 s / it) +train: [17] Summary: lr: 0.000013 loss: 1.9757 (1.9911) grad: 0.2456 (0.2429) +eval (validation): [17] [ 0/85] eta: 0:04:19 time: 3.0566 data: 2.8039 max mem: 22448 +eval (validation): [17] [20/85] eta: 0:00:30 time: 0.3463 data: 0.0054 max mem: 22448 +eval (validation): [17] [40/85] eta: 0:00:18 time: 0.3445 data: 0.0033 max mem: 22448 +eval (validation): [17] [60/85] eta: 0:00:09 time: 0.3468 data: 0.0043 max mem: 22448 +eval (validation): [17] [80/85] eta: 0:00:01 time: 0.3429 data: 0.0044 max mem: 22448 +eval (validation): [17] [84/85] eta: 0:00:00 time: 0.3363 data: 0.0041 max mem: 22448 +eval (validation): [17] Total time: 0:00:32 (0.3791 s / it) +cv: [17] best hparam: (0.38, 1.0) (018) ('018_lr3.8e-01_wd1.0e+00') loss: 2.403 acc: 0.282 f1: 0.222 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [18] [ 0/400] eta: 0:21:07 lr: nan time: 3.1688 data: 2.8420 max mem: 22448 +train: [18] [ 20/400] eta: 0:03:45 lr: 0.000012 loss: 1.9943 (2.0038) grad: 0.2386 (0.2404) time: 0.4647 data: 0.0041 max mem: 22448 +train: [18] [ 40/400] eta: 0:03:07 lr: 0.000012 loss: 1.9688 (1.9731) grad: 0.2371 (0.2380) time: 0.4468 data: 0.0039 max mem: 22448 +train: [18] [ 60/400] eta: 0:02:49 lr: 0.000011 loss: 1.9207 (1.9666) grad: 0.2425 (0.2402) time: 0.4463 data: 0.0044 max mem: 22448 +train: [18] [ 80/400] eta: 0:02:35 lr: 0.000011 loss: 1.9519 (1.9679) grad: 0.2389 (0.2390) time: 0.4480 data: 0.0043 max mem: 22448 +train: [18] [100/400] eta: 0:02:22 lr: 0.000010 loss: 1.9836 (1.9702) grad: 0.2358 (0.2389) time: 0.4416 data: 0.0041 max mem: 22448 +train: [18] [120/400] eta: 0:02:11 lr: 0.000009 loss: 1.9534 (1.9644) grad: 0.2358 (0.2386) time: 0.4426 data: 0.0043 max mem: 22448 +train: [18] [140/400] eta: 0:02:01 lr: 0.000009 loss: 1.9611 (1.9695) grad: 0.2388 (0.2391) time: 0.4486 data: 0.0041 max mem: 22448 +train: [18] [160/400] eta: 0:01:51 lr: 0.000008 loss: 1.9801 (1.9715) grad: 0.2388 (0.2382) time: 0.4499 data: 0.0041 max mem: 22448 +train: [18] [180/400] eta: 0:01:41 lr: 0.000008 loss: 1.9704 (1.9695) grad: 0.2381 (0.2390) time: 0.4465 data: 0.0042 max mem: 22448 +train: [18] [200/400] eta: 0:01:32 lr: 0.000007 loss: 1.9696 (1.9711) grad: 0.2385 (0.2392) time: 0.4514 data: 0.0042 max mem: 22448 +train: [18] [220/400] eta: 0:01:23 lr: 0.000007 loss: 1.9714 (1.9721) grad: 0.2384 (0.2392) time: 0.4572 data: 0.0042 max mem: 22448 +train: [18] [240/400] eta: 0:01:13 lr: 0.000006 loss: 1.9999 (1.9771) grad: 0.2380 (0.2392) time: 0.4515 data: 0.0041 max mem: 22448 +train: [18] [260/400] eta: 0:01:04 lr: 0.000006 loss: 1.9999 (1.9779) grad: 0.2371 (0.2391) time: 0.4477 data: 0.0043 max mem: 22448 +train: [18] [280/400] eta: 0:00:55 lr: 0.000006 loss: 1.9783 (1.9769) grad: 0.2385 (0.2392) time: 0.4497 data: 0.0043 max mem: 22448 +train: [18] [300/400] eta: 0:00:45 lr: 0.000005 loss: 1.9559 (1.9755) grad: 0.2401 (0.2390) time: 0.4563 data: 0.0043 max mem: 22448 +train: [18] [320/400] eta: 0:00:36 lr: 0.000005 loss: 1.9647 (1.9781) grad: 0.2382 (0.2389) time: 0.4467 data: 0.0040 max mem: 22448 +train: [18] [340/400] eta: 0:00:27 lr: 0.000004 loss: 1.9767 (1.9760) grad: 0.2355 (0.2386) time: 0.4445 data: 0.0041 max mem: 22448 +train: [18] [360/400] eta: 0:00:18 lr: 0.000004 loss: 1.9549 (1.9760) grad: 0.2336 (0.2384) time: 0.4618 data: 0.0042 max mem: 22448 +train: [18] [380/400] eta: 0:00:09 lr: 0.000004 loss: 1.9587 (1.9755) grad: 0.2346 (0.2383) time: 0.4550 data: 0.0042 max mem: 22448 +train: [18] [399/400] eta: 0:00:00 lr: 0.000003 loss: 1.9489 (1.9741) grad: 0.2352 (0.2386) time: 0.4818 data: 0.0046 max mem: 22448 +train: [18] Total time: 0:03:03 (0.4590 s / it) +train: [18] Summary: lr: 0.000003 loss: 1.9489 (1.9741) grad: 0.2352 (0.2386) +eval (validation): [18] [ 0/85] eta: 0:04:32 time: 3.2061 data: 2.9397 max mem: 22448 +eval (validation): [18] [20/85] eta: 0:00:33 time: 0.3774 data: 0.0043 max mem: 22448 +eval (validation): [18] [40/85] eta: 0:00:19 time: 0.3541 data: 0.0035 max mem: 22448 +eval (validation): [18] [60/85] eta: 0:00:10 time: 0.3317 data: 0.0040 max mem: 22448 +eval (validation): [18] [80/85] eta: 0:00:01 time: 0.3392 data: 0.0038 max mem: 22448 +eval (validation): [18] [84/85] eta: 0:00:00 time: 0.3370 data: 0.0039 max mem: 22448 +eval (validation): [18] Total time: 0:00:32 (0.3866 s / it) +cv: [18] best hparam: (0.38, 1.0) (018) ('018_lr3.8e-01_wd1.0e+00') loss: 2.408 acc: 0.281 f1: 0.221 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [19] [ 0/400] eta: 0:20:58 lr: nan time: 3.1455 data: 2.7995 max mem: 22448 +train: [19] [ 20/400] eta: 0:03:47 lr: 0.000003 loss: 1.9649 (1.9785) grad: 0.2293 (0.2335) time: 0.4710 data: 0.0047 max mem: 22448 +train: [19] [ 40/400] eta: 0:03:13 lr: 0.000003 loss: 1.9398 (1.9500) grad: 0.2303 (0.2346) time: 0.4760 data: 0.0043 max mem: 22448 +train: [19] [ 60/400] eta: 0:02:53 lr: 0.000002 loss: 1.9580 (1.9750) grad: 0.2330 (0.2363) time: 0.4522 data: 0.0042 max mem: 22448 +train: [19] [ 80/400] eta: 0:02:38 lr: 0.000002 loss: 2.0093 (1.9773) grad: 0.2325 (0.2350) time: 0.4470 data: 0.0041 max mem: 22448 +train: [19] [100/400] eta: 0:02:25 lr: 0.000002 loss: 1.9682 (1.9761) grad: 0.2325 (0.2352) time: 0.4466 data: 0.0045 max mem: 22448 +train: [19] [120/400] eta: 0:02:14 lr: 0.000002 loss: 1.9691 (1.9779) grad: 0.2361 (0.2362) time: 0.4499 data: 0.0042 max mem: 22448 +train: [19] [140/400] eta: 0:02:03 lr: 0.000001 loss: 1.9726 (1.9755) grad: 0.2330 (0.2353) time: 0.4441 data: 0.0042 max mem: 22448 +train: [19] [160/400] eta: 0:01:53 lr: 0.000001 loss: 1.9402 (1.9698) grad: 0.2271 (0.2346) time: 0.4656 data: 0.0042 max mem: 22448 +train: [19] [180/400] eta: 0:01:43 lr: 0.000001 loss: 1.9402 (1.9679) grad: 0.2354 (0.2358) time: 0.4574 data: 0.0043 max mem: 22448 +train: [19] [200/400] eta: 0:01:33 lr: 0.000001 loss: 1.9520 (1.9672) grad: 0.2378 (0.2356) time: 0.4507 data: 0.0040 max mem: 22448 +train: [19] [220/400] eta: 0:01:24 lr: 0.000001 loss: 1.9466 (1.9650) grad: 0.2351 (0.2351) time: 0.4427 data: 0.0041 max mem: 22448 +train: [19] [240/400] eta: 0:01:14 lr: 0.000001 loss: 1.9520 (1.9637) grad: 0.2286 (0.2353) time: 0.4544 data: 0.0043 max mem: 22448 +train: [19] [260/400] eta: 0:01:05 lr: 0.000000 loss: 1.9520 (1.9629) grad: 0.2345 (0.2353) time: 0.4477 data: 0.0043 max mem: 22448 +train: [19] [280/400] eta: 0:00:55 lr: 0.000000 loss: 1.9761 (1.9659) grad: 0.2335 (0.2352) time: 0.4536 data: 0.0044 max mem: 22448 +train: [19] [300/400] eta: 0:00:46 lr: 0.000000 loss: 2.0045 (1.9659) grad: 0.2330 (0.2350) time: 0.4430 data: 0.0042 max mem: 22448 +train: [19] [320/400] eta: 0:00:36 lr: 0.000000 loss: 1.9706 (1.9682) grad: 0.2330 (0.2353) time: 0.4454 data: 0.0043 max mem: 22448 +train: [19] [340/400] eta: 0:00:27 lr: 0.000000 loss: 1.9970 (1.9713) grad: 0.2336 (0.2352) time: 0.4461 data: 0.0042 max mem: 22448 +train: [19] [360/400] eta: 0:00:18 lr: 0.000000 loss: 2.0025 (1.9717) grad: 0.2280 (0.2348) time: 0.4468 data: 0.0042 max mem: 22448 +train: [19] [380/400] eta: 0:00:09 lr: 0.000000 loss: 1.9576 (1.9713) grad: 0.2261 (0.2346) time: 0.4439 data: 0.0041 max mem: 22448 +train: [19] [399/400] eta: 0:00:00 lr: 0.000000 loss: 1.9802 (1.9731) grad: 0.2292 (0.2347) time: 0.4523 data: 0.0042 max mem: 22448 +train: [19] Total time: 0:03:03 (0.4588 s / it) +train: [19] Summary: lr: 0.000000 loss: 1.9802 (1.9731) grad: 0.2292 (0.2347) +eval (validation): [19] [ 0/85] eta: 0:04:19 time: 3.0503 data: 2.8072 max mem: 22448 +eval (validation): [19] [20/85] eta: 0:00:29 time: 0.3288 data: 0.0037 max mem: 22448 +eval (validation): [19] [40/85] eta: 0:00:18 time: 0.3615 data: 0.0045 max mem: 22448 +eval (validation): [19] [60/85] eta: 0:00:09 time: 0.3383 data: 0.0042 max mem: 22448 +eval (validation): [19] [80/85] eta: 0:00:01 time: 0.3352 data: 0.0039 max mem: 22448 +eval (validation): [19] [84/85] eta: 0:00:00 time: 0.3278 data: 0.0039 max mem: 22448 +eval (validation): [19] Total time: 0:00:31 (0.3746 s / it) +cv: [19] best hparam: (0.38, 1.0) (018) ('018_lr3.8e-01_wd1.0e+00') loss: 2.407 acc: 0.282 f1: 0.222 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +evaluating last checkpoint: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +eval model info: +{"score": 0.28183831672203763, "hparam": [0.38, 1.0], "hparam_id": 18, "epoch": 19, "is_best": false, "best_score": 0.2886674049464747} +eval (train): [20] [ 0/509] eta: 0:24:16 time: 2.8614 data: 2.5753 max mem: 22448 +eval (train): [20] [ 20/509] eta: 0:04:04 time: 0.3828 data: 0.0046 max mem: 22448 +eval (train): [20] [ 40/509] eta: 0:03:20 time: 0.3495 data: 0.0038 max mem: 22448 +eval (train): [20] [ 60/509] eta: 0:03:00 time: 0.3528 data: 0.0042 max mem: 22448 +eval (train): [20] [ 80/509] eta: 0:02:48 time: 0.3580 data: 0.0044 max mem: 22448 +eval (train): [20] [100/509] eta: 0:02:36 time: 0.3455 data: 0.0042 max mem: 22448 +eval (train): [20] [120/509] eta: 0:02:27 time: 0.3620 data: 0.0045 max mem: 22448 +eval (train): [20] [140/509] eta: 0:02:18 time: 0.3539 data: 0.0043 max mem: 22448 +eval (train): [20] [160/509] eta: 0:02:10 time: 0.3530 data: 0.0044 max mem: 22448 +eval (train): [20] [180/509] eta: 0:02:01 time: 0.3499 data: 0.0041 max mem: 22448 +eval (train): [20] [200/509] eta: 0:01:54 time: 0.3625 data: 0.0043 max mem: 22448 +eval (train): [20] [220/509] eta: 0:01:47 time: 0.3830 data: 0.0044 max mem: 22448 +eval (train): [20] [240/509] eta: 0:01:39 time: 0.3589 data: 0.0042 max mem: 22448 +eval (train): [20] [260/509] eta: 0:01:32 time: 0.3738 data: 0.0042 max mem: 22448 +eval (train): [20] [280/509] eta: 0:01:25 time: 0.3873 data: 0.0048 max mem: 22448 +eval (train): [20] [300/509] eta: 0:01:17 time: 0.3691 data: 0.0040 max mem: 22448 +eval (train): [20] [320/509] eta: 0:01:10 time: 0.3606 data: 0.0042 max mem: 22448 +eval (train): [20] [340/509] eta: 0:01:02 time: 0.3500 data: 0.0040 max mem: 22448 +eval (train): [20] [360/509] eta: 0:00:54 time: 0.3480 data: 0.0041 max mem: 22448 +eval (train): [20] [380/509] eta: 0:00:47 time: 0.3579 data: 0.0041 max mem: 22448 +eval (train): [20] [400/509] eta: 0:00:40 time: 0.3671 data: 0.0043 max mem: 22448 +eval (train): [20] [420/509] eta: 0:00:32 time: 0.3974 data: 0.0045 max mem: 22448 +eval (train): [20] [440/509] eta: 0:00:25 time: 0.3670 data: 0.0039 max mem: 22448 +eval (train): [20] [460/509] eta: 0:00:18 time: 0.3660 data: 0.0042 max mem: 22448 +eval (train): [20] [480/509] eta: 0:00:10 time: 0.3761 data: 0.0043 max mem: 22448 +eval (train): [20] [500/509] eta: 0:00:03 time: 0.3676 data: 0.0039 max mem: 22448 +eval (train): [20] [508/509] eta: 0:00:00 time: 0.3465 data: 0.0040 max mem: 22448 +eval (train): [20] Total time: 0:03:07 (0.3693 s / it) +eval (validation): [20] [ 0/85] eta: 0:03:55 time: 2.7702 data: 2.4958 max mem: 22448 +eval (validation): [20] [20/85] eta: 0:00:29 time: 0.3458 data: 0.0045 max mem: 22448 +eval (validation): [20] [40/85] eta: 0:00:18 time: 0.3787 data: 0.0043 max mem: 22448 +eval (validation): [20] [60/85] eta: 0:00:10 time: 0.3789 data: 0.0045 max mem: 22448 +eval (validation): [20] [80/85] eta: 0:00:01 time: 0.3460 data: 0.0042 max mem: 22448 +eval (validation): [20] [84/85] eta: 0:00:00 time: 0.3319 data: 0.0040 max mem: 22448 +eval (validation): [20] Total time: 0:00:33 (0.3900 s / it) +eval (test): [20] [ 0/85] eta: 0:04:09 time: 2.9320 data: 2.6399 max mem: 22448 +eval (test): [20] [20/85] eta: 0:00:30 time: 0.3427 data: 0.0054 max mem: 22448 +eval (test): [20] [40/85] eta: 0:00:18 time: 0.3674 data: 0.0041 max mem: 22448 +eval (test): [20] [60/85] eta: 0:00:10 time: 0.3749 data: 0.0040 max mem: 22448 +eval (test): [20] [80/85] eta: 0:00:01 time: 0.3447 data: 0.0042 max mem: 22448 +eval (test): [20] [84/85] eta: 0:00:00 time: 0.3279 data: 0.0039 max mem: 22448 +eval (test): [20] Total time: 0:00:32 (0.3875 s / it) +eval (testid): [20] [ 0/82] eta: 0:04:16 time: 3.1266 data: 2.8023 max mem: 22448 +eval (testid): [20] [20/82] eta: 0:00:33 time: 0.4143 data: 0.0045 max mem: 22448 +eval (testid): [20] [40/82] eta: 0:00:19 time: 0.3592 data: 0.0039 max mem: 22448 +eval (testid): [20] [60/82] eta: 0:00:09 time: 0.3934 data: 0.0047 max mem: 22448 +eval (testid): [20] [80/82] eta: 0:00:00 time: 0.3330 data: 0.0039 max mem: 22448 +eval (testid): [20] [81/82] eta: 0:00:00 time: 0.3215 data: 0.0038 max mem: 22448 +eval (testid): [20] Total time: 0:00:33 (0.4080 s / it) +evaluating best checkpoint: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/eval_v2/nsd_cococlip__patch__attn/checkpoint-best.pth +eval model info: +{"score": 0.2886674049464747, "hparam": [1.2, 1.0], "hparam_id": 25, "epoch": 5, "is_best": true, "best_score": 0.2886674049464747} +eval (train): [20] [ 0/509] eta: 0:25:52 time: 3.0496 data: 2.7855 max mem: 22448 +eval (train): [20] [ 20/509] eta: 0:04:03 time: 0.3696 data: 0.0076 max mem: 22448 +eval (train): [20] [ 40/509] eta: 0:03:26 time: 0.3823 data: 0.0044 max mem: 22448 +eval (train): [20] [ 60/509] eta: 0:03:06 time: 0.3598 data: 0.0039 max mem: 22448 +eval (train): [20] [ 80/509] eta: 0:02:51 time: 0.3558 data: 0.0043 max mem: 22448 +eval (train): [20] [100/509] eta: 0:02:38 time: 0.3410 data: 0.0041 max mem: 22448 +eval (train): [20] [120/509] eta: 0:02:29 time: 0.3578 data: 0.0043 max mem: 22448 +eval (train): [20] [140/509] eta: 0:02:20 time: 0.3581 data: 0.0042 max mem: 22448 +eval (train): [20] [160/509] eta: 0:02:10 time: 0.3408 data: 0.0037 max mem: 22448 +eval (train): [20] [180/509] eta: 0:02:01 time: 0.3361 data: 0.0042 max mem: 22448 +eval (train): [20] [200/509] eta: 0:01:54 time: 0.3771 data: 0.0046 max mem: 22448 +eval (train): [20] [220/509] eta: 0:01:47 time: 0.3706 data: 0.0045 max mem: 22448 +eval (train): [20] [240/509] eta: 0:01:40 time: 0.3815 data: 0.0045 max mem: 22448 +eval (train): [20] [260/509] eta: 0:01:32 time: 0.3546 data: 0.0041 max mem: 22448 +eval (train): [20] [280/509] eta: 0:01:24 time: 0.3590 data: 0.0040 max mem: 22448 +eval (train): [20] [300/509] eta: 0:01:17 time: 0.3576 data: 0.0042 max mem: 22448 +eval (train): [20] [320/509] eta: 0:01:09 time: 0.3512 data: 0.0041 max mem: 22448 +eval (train): [20] [340/509] eta: 0:01:01 time: 0.3385 data: 0.0040 max mem: 22448 +eval (train): [20] [360/509] eta: 0:00:54 time: 0.3470 data: 0.0041 max mem: 22448 +eval (train): [20] [380/509] eta: 0:00:47 time: 0.4089 data: 0.0048 max mem: 22448 +eval (train): [20] [400/509] eta: 0:00:39 time: 0.3573 data: 0.0041 max mem: 22448 +eval (train): [20] [420/509] eta: 0:00:32 time: 0.4019 data: 0.0047 max mem: 22448 +eval (train): [20] [440/509] eta: 0:00:25 time: 0.4353 data: 0.0055 max mem: 22448 +eval (train): [20] [460/509] eta: 0:00:18 time: 0.3462 data: 0.0043 max mem: 22448 +eval (train): [20] [480/509] eta: 0:00:10 time: 0.3527 data: 0.0042 max mem: 22448 +eval (train): [20] [500/509] eta: 0:00:03 time: 0.3334 data: 0.0039 max mem: 22448 +eval (train): [20] [508/509] eta: 0:00:00 time: 0.3195 data: 0.0037 max mem: 22448 +eval (train): [20] Total time: 0:03:07 (0.3687 s / it) +eval (validation): [20] [ 0/85] eta: 0:03:52 time: 2.7373 data: 2.4401 max mem: 22448 +eval (validation): [20] [20/85] eta: 0:00:30 time: 0.3540 data: 0.0053 max mem: 22448 +eval (validation): [20] [40/85] eta: 0:00:18 time: 0.3689 data: 0.0038 max mem: 22448 +eval (validation): [20] [60/85] eta: 0:00:09 time: 0.3495 data: 0.0039 max mem: 22448 +eval (validation): [20] [80/85] eta: 0:00:01 time: 0.3318 data: 0.0039 max mem: 22448 +eval (validation): [20] [84/85] eta: 0:00:00 time: 0.3239 data: 0.0037 max mem: 22448 +eval (validation): [20] Total time: 0:00:32 (0.3793 s / it) +eval (test): [20] [ 0/85] eta: 0:04:17 time: 3.0326 data: 2.7753 max mem: 22448 +eval (test): [20] [20/85] eta: 0:00:33 time: 0.3840 data: 0.0048 max mem: 22448 +eval (test): [20] [40/85] eta: 0:00:19 time: 0.3640 data: 0.0040 max mem: 22448 +eval (test): [20] [60/85] eta: 0:00:10 time: 0.3476 data: 0.0040 max mem: 22448 +eval (test): [20] [80/85] eta: 0:00:01 time: 0.3352 data: 0.0041 max mem: 22448 +eval (test): [20] [84/85] eta: 0:00:00 time: 0.3273 data: 0.0039 max mem: 22448 +eval (test): [20] Total time: 0:00:33 (0.3899 s / it) +eval (testid): [20] [ 0/82] eta: 0:04:13 time: 3.0912 data: 2.7747 max mem: 22448 +eval (testid): [20] [20/82] eta: 0:00:33 time: 0.4098 data: 0.0040 max mem: 22448 +eval (testid): [20] [40/82] eta: 0:00:18 time: 0.3461 data: 0.0039 max mem: 22448 +eval (testid): [20] [60/82] eta: 0:00:09 time: 0.3440 data: 0.0042 max mem: 22448 +eval (testid): [20] [80/82] eta: 0:00:00 time: 0.3356 data: 0.0043 max mem: 22448 +eval (testid): [20] [81/82] eta: 0:00:00 time: 0.3219 data: 0.0041 max mem: 22448 +eval (testid): [20] Total time: 0:00:32 (0.3924 s / it) +eval results: + +| model | repr | clf | dataset | ckpt | epoch | lr | wd | hparam_id | hparam | split | loss | acc | acc_std | f1 | f1_std | +|:---------|:-------|:------|:-------------|:-------|--------:|--------:|-----:|------------:|:-----------|:-----------|-------:|--------:|----------:|--------:|----------:| +| flat_mae | patch | attn | nsd_cococlip | best | 5 | 0.00036 | 0.05 | 25 | [1.2, 1.0] | train | 2.0359 | 0.38369 | 0.0023238 | 0.32585 | 0.0024967 | +| flat_mae | patch | attn | nsd_cococlip | best | 5 | 0.00036 | 0.05 | 25 | [1.2, 1.0] | validation | 2.3722 | 0.28867 | 0.0057354 | 0.22128 | 0.0052397 | +| flat_mae | patch | attn | nsd_cococlip | best | 5 | 0.00036 | 0.05 | 25 | [1.2, 1.0] | test | 2.2695 | 0.30612 | 0.0054976 | 0.2385 | 0.005329 | +| flat_mae | patch | attn | nsd_cococlip | best | 5 | 0.00036 | 0.05 | 25 | [1.2, 1.0] | testid | 2.2548 | 0.31328 | 0.0057234 | 0.24967 | 0.0054586 | + + +done! total time: 1:23:36 diff --git a/input_space_v3/flat_lr1e-3_5/eval_v2/nsd_cococlip__patch__attn/train_log.json b/input_space_v3/flat_lr1e-3_5/eval_v2/nsd_cococlip__patch__attn/train_log.json new file mode 100644 index 0000000000000000000000000000000000000000..99129bd431f3c861c6203e88d07699fe0c56728e --- /dev/null +++ b/input_space_v3/flat_lr1e-3_5/eval_v2/nsd_cococlip__patch__attn/train_log.json @@ -0,0 +1,20 @@ +{"epoch": 0, "train/lr": 2.987987987987988e-05, "train/loss": 3.1274906897544863, "train/grad": 0.16833202876150608, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.19104736328125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.19019775390625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.18866455078125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.187265625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.185968017578125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.1841748046875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.182200927734375, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.180220947265625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.177841796875, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.175556640625, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.17338623046875, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.170687255859375, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.168291015625, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.165384521484375, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.162938232421875, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.161070556640625, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.15906005859375, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.1570458984375, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.155125732421875, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.153609619140625, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.151854248046875, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.150487060546875, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.1492236328125, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.148043212890625, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.14704345703125, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.14600830078125, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.145380859375, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.144981689453125, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.14447265625, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.1440625, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.143836669921875, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.143719482421875, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.1435247802734376, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.14322509765625, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.1428387451171873, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.1420306396484374, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.1399371337890627, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.134430236816406, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.120868988037109, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.0968733978271485, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.076757049560547, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.0580459594726563, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.0306047058105468, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.008167724609375, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.987596893310547, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.9696943664550783, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.955632095336914, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.9405430793762206, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.927424659729004, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.025795207927003502, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.02571741282939911, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.025592251536436378, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.025471407072618604, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.02535581397358328, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.025202983552590014, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.025038215266540646, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.024865029216744005, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.024654275681823493, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.024449777514673768, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.024266560445539653, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.0240229964023456, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.02381889841053635, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.023571170484647155, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.02337738968897611, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.023222364583052695, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.023059095493517815, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.022905697110109032, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.022769402782432734, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.02266581391915679, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.02256242692004889, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.022477423911914228, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.02240033104084432, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.022336947591975333, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.022287279069423675, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.022244412689469754, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.022219085791148244, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.02220168165396899, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.022187633193098008, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.02217491030227393, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.022164530735462904, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.022147960714064538, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.022108823861926793, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.02205486102961004, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.02196150604635477, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.021840501567348836, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.02170395040884614, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.021655941344797612, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.02184734670445323, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.022536134235560893, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.023266662694513798, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.023845381597056986, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.024475359795615076, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.02501519988756627, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.025835250755771994, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.02689513495191932, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.027754592522978783, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.029028681488707662, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.03019823390059173, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.177307605743408, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.174578905105591, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1702842712402344, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1663100719451904, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1626205444335938, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.157897472381592, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.153154134750366, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.148514747619629, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.143394708633423, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.138920545578003, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.135387420654297, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.131431818008423, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.128678321838379, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1261377334594727, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1247005462646484, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1239001750946045, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.123342514038086, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1230597496032715, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1228833198547363, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.122878074645996, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.123015880584717, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.1233742237091064, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.1240947246551514, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.125185966491699, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.1265597343444824, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.128229856491089, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.1295478343963623, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.1305320262908936, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.130950689315796, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.129655361175537, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.12692928314209, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.1238722801208496, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.119503974914551, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.1154870986938477, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.109628677368164, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.09869122505188, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.062539577484131, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.9676973819732666, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.8461859226226807, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.7365078926086426, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.6807146072387695, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.631216526031494, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.6176493167877197, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.6262612342834473, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.5873770713806152, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.5791540145874023, "validation/loss_046_lr3.6e+01_wd1.0e+00": 2.5318470001220703, "validation/loss_047_lr4.3e+01_wd1.0e+00": 2.551210880279541, "validation/loss_048_lr5.0e+01_wd1.0e+00": 2.6562886238098145, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06275378368401624, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.0651531930601698, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06589147286821706, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06496862310815799, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06423034330011074, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06404577334809892, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06423034330011074, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06423034330011074, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06570690291620525, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06589147286821706, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06533776301218161, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.067921742340347, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.0651531930601698, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06699889258028793, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.07087486157253599, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.07179771133259505, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.07179771133259505, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.07069029162052418, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.0695828719084533, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.07032115171650055, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.0695828719084533, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.062384643779992616, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.057770394979697305, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.05518641565153193, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.053156146179401995, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.052233296419342934, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.051310446659283866, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.053156146179401995, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.056847545219638244, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.06662975267626431, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.0784422296050203, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.07604282022886674, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.0812107788851975, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.08545588778146918, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.09191583610188261, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.11609449981543005, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.1568844592100406, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.18604651162790697, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.20376522702104097, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.21410114433370248, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.21188630490956073, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.21557770394979697, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.2355112587670727, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.2395717977113326, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.24289405684754523, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.23015873015873015, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.21225544481358435, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.008367568690295276, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.008511015413884026, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.008532038642462167, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.008582149965232728, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.008036710052552852, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.007094363407167297, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.006840229829538577, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.006717029470967371, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.0060244909182951166, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.006482332532040345, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.00791617234964625, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.009422960262161469, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.0095212376976104, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.010972421150124931, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.0115527492470162, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.011972858876995077, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.012713925568136645, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.012845271565065819, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.012504119794894646, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.012239524179197778, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.01275060924598187, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.014102325085508115, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.014936968854574934, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.012851958588942614, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.010344540610486909, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.008158674368579874, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.0067522884689011865, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.005716426031428701, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.0047342719842493166, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.007079824196616292, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.009954459189521559, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.014359539368250317, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.01749847977657978, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.017114180364342733, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.024797307824740003, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.028414282142561084, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.030820395804331532, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.05480297511990053, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.08876052543705754, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.10784708557522478, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.12108412084268344, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.12852749967479038, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.13576015819909448, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.15190271667324595, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.16943512395753554, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.1612338837316256, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.16043766573165777, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.1510938090134176, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.14295932681380794, "id_best": 46, "lr_best": 0.010799999999999999, "wd_best": 0.05, "train/loss_best": 2.955632095336914, "validation/loss_best": 2.5318470001220703, "validation/acc_best": 0.24289405684754523, "validation/f1_best": 0.16043766573165777} +{"epoch": 1, "train/lr": 8.993993993993998e-05, "train/loss": 2.942597131729126, "train/grad": 0.19047478795051576, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.159874267578125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.156522216796875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.15183837890625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.148218994140625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.14517578125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.14179931640625, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.138759765625, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.1364892578125, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.134228515625, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.132598876953125, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.1314453125, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.1304833984375, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.12970703125, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.1292529296875, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.12886962890625, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.12856201171875, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.1283154296875, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.127860107421875, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.127479248046875, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.126964111328125, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.12625732421875, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.125572509765625, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.124833984375, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.1237841796875, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.122757568359375, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.1210211181640624, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.1186962890625, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.114522705078125, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.0986563110351564, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.0538331604003908, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.0012511444091796, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.950609588623047, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.885625305175781, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.8252375411987303, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.7590886116027833, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.6971562194824217, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.63685733795166, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.588420286178589, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.552017250061035, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.5273771190643313, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.51032808303833, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.4994725799560547, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.4919748210906985, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.4942929124832154, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.5035766983032226, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.5316281843185426, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.5626910877227784, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.6172446525096893, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.6880329561233522, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.022937469612807036, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.0226387226767838, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.02222000831272453, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.02188175147399306, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.021608952772803603, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.021315506496466696, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.021073880433104934, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.02088419093284756, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.020723277409560977, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.020622242870740593, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.02056615225970745, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.02053035296034068, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.02052393478807062, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.020536539014428853, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.02056064481846988, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.020584905329160394, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.02061699640471488, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.02065344100818038, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.02069133419543505, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.020723733659833668, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.020758698121644558, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.020789282261393965, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.020813438720069827, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.020816536596976222, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.020789878140203655, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.020705556105822323, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.020581694738939404, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.02045501282438636, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.020451691481284798, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.021034368663094938, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.021883513797074556, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.022757526491768657, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.02396495443303138, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.02490859050769359, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.026178158605471253, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.02747494268696755, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.029114548871293663, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.030522556491196156, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.031706171222031114, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.032896063262596725, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.03426405203528702, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.03570282367989421, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.03715700085274875, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.038119446961209176, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.03912268015556038, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.04077043370343745, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.04317346497438848, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.046057821968570355, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.05098072504624725, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1409847736358643, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.13736629486084, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1328299045562744, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1297309398651123, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1276466846466064, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.125847578048706, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1247050762176514, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.124063014984131, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1236965656280518, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.123541831970215, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.123443841934204, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1232454776763916, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.122981309890747, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1224799156188965, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1219191551208496, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.121297836303711, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1205482482910156, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1197476387023926, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1191349029541016, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.1187984943389893, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.118654251098633, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.1187288761138916, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.119088649749756, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.119788408279419, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.1207664012908936, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.120248317718506, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.112210273742676, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.0832269191741943, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.9540531635284424, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.7755284309387207, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.691960573196411, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.642157554626465, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.579037666320801, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.5398080348968506, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.537950038909912, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.5415427684783936, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.4842448234558105, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.478276252746582, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.4967377185821533, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.506363868713379, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.4833219051361084, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.509817361831665, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.529416799545288, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.6040284633636475, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.6635289192199707, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.8755624294281006, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.062490224838257, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.212907552719116, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.242652416229248, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06404577334809892, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06441491325212255, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06533776301218161, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06626061277224068, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06607604282022887, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06570690291620525, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06533776301218161, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.0651531930601698, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06496862310815799, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06423034330011074, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.0636766334440753, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06386120339608711, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06404577334809892, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06478405315614617, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06570690291620525, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.0664451827242525, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.067921742340347, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06902916205241787, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.07327427094868956, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.07567368032484312, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.07641196013289037, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.07475083056478406, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.07585825027685493, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.07659653008490218, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.07788851974898486, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.08213362864525656, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.08877814691768181, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.13178294573643412, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.16777408637873753, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.19361387966039129, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.20376522702104097, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.21650055370985605, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.23089700996677742, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.22886674049464747, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.2307124400147656, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.24492432631967515, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.2482465854558878, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.24326319675156885, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.23901808785529716, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.24067921742340348, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.23791066814322628, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.22831303063861202, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.22812846068660023, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.2222222222222222, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.20136581764488742, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.18401624215577703, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.17755629383536362, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.1699889258028793, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.005788486433647724, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.0059640949655635385, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.0064097412411395745, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.00733585589394236, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.008276237836745158, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.008552064529093368, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.008749974858162075, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.008867301465479102, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.009422626854732446, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.009707491189015297, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.009600599016287481, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.00983633800144027, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.01022040534874876, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.01066166754424669, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.012157635545919874, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.013254946908509112, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.013541202872312008, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.014434602547568237, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.014706538743306975, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.016737892424305265, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.017986381376245777, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.018535958284239592, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.01753929811232863, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.01734555406317179, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.015776283540322483, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.015926346417039983, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.01705803090071521, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.023353827463307813, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.05760396583462953, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.0847017913192349, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.10958523358602519, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.12589662493423195, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.14776243546069118, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.16821415408674956, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.16810721217391025, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.1687142622617924, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.1817729975285807, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.18879359811158544, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.18522080814157293, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.18118095151998545, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.1806287024974981, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.17692344051593092, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.16631332077777541, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.16568556191557546, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.15684044330472974, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.13485864285152419, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.12588373420006452, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.11663971152394627, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.11673889521773144, "id_best": 37, "lr_best": 0.00249, "wd_best": 0.05, "train/loss_best": 2.588420286178589, "validation/loss_best": 2.478276252746582, "validation/acc_best": 0.2482465854558878, "validation/f1_best": 0.18879359811158544} +{"epoch": 2, "train/lr": 0.00014999999999999988, "train/loss": 2.924426941871643, "train/grad": 0.3845723896473646, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.1394384765625, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.13760009765625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.135791015625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.13485107421875, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.134027099609375, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.133740234375, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.133399658203125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.133232421875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.132901611328125, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.132457275390625, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.132220458984375, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.1316259765625, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.131024169921875, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.130234375, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.129229736328125, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.12842041015625, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.12736328125, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.1260205078125, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.124505615234375, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.122957763671875, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.120428466796875, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.11634033203125, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.105537109375, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.07090087890625, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.0045230102539064, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.9067306518554688, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.8159869003295896, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.7367769622802736, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.6419467163085937, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.5602416229248046, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.5056512260437014, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.463642158508301, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.4160187911987303, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.377977743148804, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.3466030502319337, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.32684739112854, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.312818305492401, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.3076302790641785, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.3119973707199097, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.3298997688293457, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.341770361661911, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.360338132381439, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.403795050382614, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.4459132874011993, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.5019564306735993, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.5853348422050475, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.2810966873168947, "train/loss_047_lr4.3e+01_wd1.0e+00": 5.043101596832275, "train/loss_048_lr5.0e+01_wd1.0e+00": 4.924077234268188, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.021009604996070266, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.020858165994286536, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.020713315354660155, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.020649609686806798, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.020625495803542435, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.02062217523343861, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.020634908252395688, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.020654135369695723, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.020680106137879194, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.020703620514832436, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.020724621661938728, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.020751391341909765, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.020773556856438516, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.0208025770355016, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.020825182190164923, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.020842755967751144, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.020858339508995415, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.020864873332902788, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.020854885107837617, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.020824329569004475, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.020751440282911062, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.020635796459391714, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.020531747164204715, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.02086671968456358, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.022011101385578512, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.023743344116955997, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.02524070743471384, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.026622436968609692, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.028381856717169286, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.03000823316164315, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.031002315739169718, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.031901371832937, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.032979586776345965, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.03402753483504057, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.034982825089246036, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.03595779507420957, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.03704837962053716, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.03794172052294016, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0391600823123008, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.041013378323987125, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.04193998688831926, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.043238679524511096, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.045997281465679406, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.04788003521040082, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.05054800296202302, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.05569265399128199, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.09697033235803247, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.14776313483715056, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.09557354498654604, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1262567043304443, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1252405643463135, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1243889331817627, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1240549087524414, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.123889684677124, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1237740516662598, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.123703718185425, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1236510276794434, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1235594749450684, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1234726905822754, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.123418092727661, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.123372793197632, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1233279705047607, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.123307228088379, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1231329441070557, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.122749090194702, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.121903657913208, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1202728748321533, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.117396593093872, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.1136488914489746, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.106198310852051, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.0897226333618164, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.027174234390259, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.8546175956726074, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.7150964736938477, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.6279172897338867, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.5788841247558594, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.5342936515808105, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.4763669967651367, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.436173439025879, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.4235126972198486, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.4269251823425293, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.424160957336426, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.4548516273498535, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.5152456760406494, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.5449607372283936, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.5344278812408447, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.533838987350464, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.5287528038024902, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.5282435417175293, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.5905258655548096, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.5830442905426025, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.625239849090576, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.6620118618011475, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.7774369716644287, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.8499276638031006, "validation/loss_046_lr3.6e+01_wd1.0e+00": 33.73202896118164, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06607604282022887, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06589147286821706, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06866002214839424, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.0710594315245478, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.07124400147655961, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06939830195644149, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.0695828719084533, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.07087486157253599, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.07216685123661867, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.07216685123661867, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.07419712070874862, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.0725359911406423, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.07235142118863049, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.07032115171650055, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.07087486157253599, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06995201181247693, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06939830195644149, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06921373200442968, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06866002214839424, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.07087486157253599, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.07438169066076043, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.08342561830933924, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.10815799187892211, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.16002214839424142, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.19748984865263935, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.21853082318198597, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.2349575489110373, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.2454780361757106, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.26208933185677374, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.2691029900332226, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.27445551864156514, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.2718715393133998, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.2691029900332226, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.2681801402731635, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.2561830933923957, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.24787744555186417, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.2499077150239941, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.2497231450719823, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.25101513473606496, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.23809523809523808, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.23255813953488372, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.24215577703949798, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.23606496862310816, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.23883351790328536, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.2279438907345884, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.21779254337393872, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.023255813953488372, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.008945560296250921, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.009006013665286668, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.009939690010145922, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.010854193565957598, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.010923854031075037, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.011066201400943271, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.011385524449991689, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.012592542020525259, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.01351533529207237, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.01380335455408605, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.014571443786345515, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.01425921375135275, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.014062584035204646, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.013170967063629946, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.012998288344083236, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.01224559848671701, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.01210974326989185, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.012187154005939027, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.012146704757415304, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.013869878840280651, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.01566362632602349, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.018460178901304736, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.0358883587375727, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.07542993607906709, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.1059442677783442, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.13272233815886253, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.15735733882773328, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.16874819095312313, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.1869917479589304, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.1937820213438061, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.19562206523224943, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.19114331920246794, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.194773677725709, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.2038005191736161, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.18931713728583113, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.17876385981434048, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.1805741929149105, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.18258727998059845, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.19019564290496768, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.19152544035535826, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.17502644546199408, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.18842368442323562, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.16571918019290469, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.1624863338933372, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.1563981417178266, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.1590838881303727, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0018953068592057762, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 30, "lr_best": 0.00081, "wd_best": 0.05, "train/loss_best": 2.5056512260437014, "validation/loss_best": 2.4235126972198486, "validation/acc_best": 0.27445551864156514, "validation/f1_best": 0.19562206523224943} +{"epoch": 3, "train/lr": 0.0002100600600600602, "train/loss": 2.8571944212913514, "train/grad": 0.3757509465515614, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.13151123046875, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.13096923828125, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.130382080078125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.12990478515625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.12954345703125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.129141845703125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.128525390625, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.1278369140625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.127010498046875, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.126080322265625, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.125228271484375, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.1240087890625, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.122757568359375, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.120858154296875, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.119066162109375, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.117247314453125, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.114412841796875, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.1098681640625, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.099385986328125, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.0707415771484374, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.990800323486328, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.880587615966797, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.7599308776855467, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.6581576538085936, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.581707649230957, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.5097844886779783, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.4559690666198732, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.4131657600402834, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.36696231842041, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.317430877685547, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.282588453292847, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.2587031650543214, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.235510859489441, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.220425453186035, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.209542503356934, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.205882315635681, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.2126194643974304, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.2294928002357484, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.251933870315552, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.2962761974334716, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.3354995787143706, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.3835353004932402, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.4767661821842193, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.5615293622016906, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.691825153827667, "train/loss_045_lr3.1e+01_wd1.0e+00": 5.337648314237595, "train/loss_046_lr3.6e+01_wd1.0e+00": 5.120023727416992, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.02053045043721795, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.020534731107763948, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.02055376853328198, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.020573144848458468, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.020588705469854175, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.02060681491624564, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.020624410868622364, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.020640157610177994, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.02065951366443187, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.02067712914664298, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.020691747525706888, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.02070760927628726, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.020714572994038463, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.02071675082668662, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.02070626531727612, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.020682638776488602, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.02063048324547708, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.02053951005451381, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.02043599863536656, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.020636892574839295, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.02183506548870355, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.02381531717721373, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.026097524613142013, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.027951785428449512, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.02924531019292772, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.03061204982921481, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.031969619914889336, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.03304294185712933, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.03396884012967348, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.03513767172582447, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.03610781447961926, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.03703166303224861, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.03828056685626507, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.03929335611872375, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.040160830244421956, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.040744090359658, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.041776261888444424, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.042792288195341824, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.04415926842018962, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.046357642952352764, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.048458424042910335, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.05093873091042042, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.056027591563761234, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.06068054972216487, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.06805236477404833, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.12005298690870404, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0756797432899475, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1235923767089844, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1233510971069336, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1229727268218994, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1226720809936523, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1223223209381104, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1218395233154297, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1212570667266846, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1205697059631348, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1196625232696533, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1187117099761963, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.117790699005127, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.116429328918457, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.11517596244812, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1133952140808105, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1116514205932617, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1098053455352783, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1063525676727295, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.0969269275665283, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.057051181793213, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.9310386180877686, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.7614665031433105, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.6665456295013428, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.606534957885742, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.557372570037842, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.511265277862549, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.465270519256592, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.4562788009643555, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.4627456665039062, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.4694976806640625, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.465568780899048, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.4714887142181396, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.4636497497558594, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.4610941410064697, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.470686912536621, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.558990716934204, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.669858694076538, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.724879503250122, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.7419159412384033, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.7478790283203125, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.775416851043701, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.6933023929595947, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.799382448196411, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.8406951427459717, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.4999895095825195, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.2923154830932617, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06902916205241787, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06847545219638243, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06829088224437062, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.07050572166851236, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.0710594315245478, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.07124400147655961, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.07216685123661867, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.0725359911406423, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.073827980804725, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.07456626061277224, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.073827980804725, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.0769656699889258, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.07567368032484312, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.07585825027685493, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.0753045404208195, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.07401255075673681, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.07511997046880768, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.07936507936507936, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.09653008490217793, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.14174972314507198, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.17109634551495018, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.19582871908453303, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.2129937246216316, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.2220376522702104, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.2368032484311554, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.2499077150239941, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.25507567368032485, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.2543373938722776, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.2547065337763012, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.2547065337763012, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.25692137320044295, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.26301218161683276, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.26504245108896274, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.2622739018087855, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.2561830933923957, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.23938722775932078, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.2349575489110373, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.22093023255813954, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.22277593207825766, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.22572905131044665, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.2248062015503876, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.21816168327796234, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.22129937246216316, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.1777408637873754, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.17792543373938724, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.010222539336436577, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.010165263509833473, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.010217729103059988, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.010527662754239353, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.010585332958143826, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.010833407343600806, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.011590969667295533, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.012020436469356154, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.012349523378507267, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.013253520324961944, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.014898528511229003, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.018145683055156764, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.01805357693826427, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.020418644960270033, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.02027220140745103, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.020001631069992344, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.019995221239489266, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.02482764595183805, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.04458222236959417, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.07787265793433716, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.09871579944748066, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.12114436496257645, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.1372194363655743, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.1490286691466642, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.16527363764400999, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.18589385537132438, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.19500523978572296, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.19885026176510542, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.19854511456141255, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.1956758288322964, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.19133291636131952, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.1942305815143782, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.1909833695502038, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.18379333539524945, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.17663483110861555, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.17632981235847747, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.17748360311682376, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.17055940337497896, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.16828690724709086, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.1638462070843238, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.17618573217021405, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.16519383888819675, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.15982105880525743, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.1300845858099288, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.11845696188916942, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 32, "lr_best": 0.0011099999999999999, "wd_best": 0.05, "train/loss_best": 2.235510859489441, "validation/loss_best": 2.4610941410064697, "validation/acc_best": 0.26504245108896274, "validation/f1_best": 0.1909833695502038} +{"epoch": 4, "train/lr": 0.0002701201201201201, "train/loss": 2.838165191411972, "train/grad": 0.4053061628341675, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.133118896484375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.132752685546875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.132056884765625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.131348876953125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.13072509765625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.12996826171875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.1289501953125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.12798828125, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.126544189453125, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.12515380859375, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.123765869140625, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.12153076171875, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.119305419921875, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.11565185546875, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.110906982421875, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.10303955078125, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.075576171875, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.9882846069335938, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.851392364501953, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.7326171875, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.634177551269531, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.564579544067383, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.4970289611816407, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.4332443618774415, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.373742389678955, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.31790735244751, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.2772003507614134, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.2459836053848266, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.2142787837982176, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.1786909651756288, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.1559869384765626, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.1405534863471987, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.1309324848651885, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.1306180012226106, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.135639624595642, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.1565657901763915, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.174577773809433, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.206647287607193, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.253080314397812, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.3188169503211977, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.4069628179073335, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.494457544088364, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.59488223195076, "train/loss_043_lr2.2e+01_wd1.0e+00": 6.610167704820633, "train/loss_044_lr2.6e+01_wd1.0e+00": 5.095197238922119, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.020357260932214558, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.020370014109648765, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.020384220452979208, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.020395793044008313, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.020404981384053826, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.02041532870847732, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.02042676370125264, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.02043632511049509, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.02044625223148614, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.020455338982865213, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.020459490180946886, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.02045498261693865, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.020437952210195363, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.02038281600922346, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.020296770590357484, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.02020144081208855, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.020288966093212367, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.021442313217557966, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.023845968176610766, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.02610693003050983, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.02797289845533669, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.02927158458158374, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.030616832226514817, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.03190496860072017, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.03331343560479581, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.03457341603003442, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.03541203967295587, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.03600385170429945, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.036724756192415955, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.03776218382641673, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.03849697086028755, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.03919593105092645, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.04035607935860753, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.041536075919866564, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.04291132958605885, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.044367487747222184, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.04527311934158206, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.046977818030864, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.04955861452966928, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.05322533965110779, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.057537708114832636, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.06341162607073784, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.06735762163996696, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.14806110225617886, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.09066497534513474, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1238648891448975, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.123777151107788, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.123569965362549, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1233367919921875, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.123054027557373, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.122612953186035, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.121997594833374, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1212565898895264, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1201205253601074, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1187548637390137, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1172845363616943, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1149532794952393, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1123952865600586, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1076598167419434, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.0991897583007812, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.0773210525512695, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.9783527851104736, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.7945475578308105, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.671478748321533, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.6083455085754395, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.558342933654785, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.521268367767334, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.486879825592041, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.4499566555023193, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.425309181213379, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.412161350250244, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.408778190612793, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.4017767906188965, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.403949499130249, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.425952911376953, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.4225003719329834, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.4452528953552246, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.4881198406219482, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.5181632041931152, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.5390870571136475, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.564786672592163, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.6010019779205322, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.6249642372131348, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.7130043506622314, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.9037716388702393, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.8594882488250732, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.0535709857940674, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.0909366607666016, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06533776301218161, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06496862310815799, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06478405315614617, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06441491325212255, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06404577334809892, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06441491325212255, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06589147286821706, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.067921742340347, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06884459210040605, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06995201181247693, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.07235142118863049, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.07659653008490218, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.08785529715762273, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.13215208564045774, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.17275747508305647, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.20081210778885197, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.21650055370985605, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.23034330011074197, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.24086378737541528, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.25212255444813586, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.2622739018087855, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.2676264304171281, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.2698412698412698, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.2707641196013289, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.2739018087855297, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.27205610926541157, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.2691029900332226, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.268733850129199, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.2672572905131045, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.26005906238464377, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.2517534145441122, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.2558139534883721, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.25489110372831303, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.2382798080472499, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.24621631598375784, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.22997416020671835, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.20321151716500555, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.21336286452565523, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.18955334071613142, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.2009966777408638, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.008192600654135842, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.008318518278339513, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.008328005650764784, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.008381669604768091, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.008385476327332832, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.008324674898102473, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.0091824606720645, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.009340064458823212, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.011082929175946941, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.012799667560676421, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.014003257649644255, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.0147490561637068, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.01571785146773991, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.017782992093209403, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.02337053153399099, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.033954237798020474, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.06489206438418536, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.10035313251360652, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.12492033723740047, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.14064001027501216, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.15646755043747532, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.16938286849924197, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.18255666901710485, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.19664550272279793, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.20238712191330574, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.20657910160413004, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.21179233532755828, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.2194945865247014, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.22150143839438197, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.21975969968052134, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.22150828619960014, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.21828104357139666, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.2136675752010131, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.20748662929229011, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.20090846942812635, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.19298878899842167, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.1795826185800532, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.1903520607714877, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.173030615895401, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.15183904604060108, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.15416487741326018, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.13893126367835254, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.1424305931103591, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 27, "lr_best": 0.00047999999999999996, "wd_best": 0.05, "train/loss_best": 2.2459836053848266, "validation/loss_best": 2.4017767906188965, "validation/acc_best": 0.2739018087855297, "validation/f1_best": 0.2194945865247014} +{"epoch": 5, "train/lr": 0.00029891323817685334, "train/loss": 2.6385216510295866, "train/grad": 0.24085602045059204, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.125120849609375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.124544677734375, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.1236572265625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.122896728515625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.122081298828125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.12087890625, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.11957275390625, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.118211669921875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.116419677734375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.114322509765625, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.112239990234375, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.108499755859375, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.1036163330078126, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.0886309814453123, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.0398513793945314, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.9360646057128905, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.781385803222656, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.6526528930664064, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.5673861694335938, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.5071041107177736, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.439160842895508, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.373782043457031, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.3130714988708494, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.261828775405884, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.2123892498016358, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.163065347671509, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.125168342590332, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.0940451717376707, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.066514263153076, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.039490647315979, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.0268855237960817, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.0209496462345125, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.0163777089118957, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.018547261953354, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.0328025782108305, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.0602613723278047, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.091404466629028, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.1350003373622894, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.187790596485138, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.2619536221027374, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.3185167473554613, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.376016428470612, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.5161526024341585, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.171875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.02064057149924338, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.020651392773725092, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.020666399798355998, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.020680813356302678, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.02069246963597834, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.020707365470007063, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.020720485737547277, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.020732710929587485, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.020741061973385513, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.02074359361547977, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.020735845281742514, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.020703593655489384, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.02064976090565324, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.020579247837886214, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.021034411801956594, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.022524983794428407, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.025131793683394788, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.027497522477060558, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.028971017114818098, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.03000546262599528, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.031661585224792364, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.03357129285112023, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.03489790175110102, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.035748154111206534, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.03658996848389506, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.03728729436174035, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.03812127429060638, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.03863619018346071, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.03903418062254786, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.040208304012194274, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.04140392815694213, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.042588678114116194, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.043941069208085534, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.04505615657195449, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.04643960600718856, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.047905177231878045, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.049425503239035606, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.05114099618047476, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.05247109496966004, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.055486583691090344, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.05689835235476494, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.05863912919536233, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.06609091199934483, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.121501922607422, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.12093448638916, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.120014190673828, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1191582679748535, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1182870864868164, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1171517372131348, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.115901231765747, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1144979000091553, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1126341819763184, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1104917526245117, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1080949306488037, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.103288173675537, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.095202684402466, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.059037208557129, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.9284660816192627, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.7739760875701904, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.659844160079956, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.5867221355438232, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.5276520252227783, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.481560230255127, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.4433162212371826, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.4262588024139404, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.4147162437438965, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.400949716567993, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.379210948944092, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.3722212314605713, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.3912813663482666, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.4463675022125244, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.4774115085601807, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.4881818294525146, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.485513687133789, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.494734764099121, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.536182403564453, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.622189998626709, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.736654043197632, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.746706485748291, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.8673834800720215, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.8756537437438965, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.8657217025756836, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.89432430267334, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.9491193294525146, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.8331387042999268, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.9042701721191406, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06496862310815799, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06496862310815799, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.0651531930601698, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.0651531930601698, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06478405315614617, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06496862310815799, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06626061277224068, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06681432262827612, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.0681063122923588, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06847545219638243, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.07032115171650055, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.07327427094868956, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.07918050941306755, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.09689922480620156, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.1478405315614618, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.1731266149870801, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.1967515688445921, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.2157622739018088, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.2349575489110373, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.2499077150239941, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.26098191214470284, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.26578073089701, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.2707641196013289, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.2807308970099668, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.28497600590623845, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.2886674049464747, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.28552971576227393, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.28017718715393136, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.2796234772978959, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.27593207825765964, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.27703949796973054, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.2748246585455888, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.2702104097452935, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.2561830933923957, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.23440383905500184, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.22554448135843486, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.2085640457733481, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.2081949058693245, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.21483942414174972, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.1967515688445921, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.19638242894056848, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.2131782945736434, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.19158361018826134, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.007377516229975247, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.007408944413524988, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.007495203875838646, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.007418292353344728, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.00728483641157177, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.0076833666415555375, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.008921126190736548, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.009760743096726747, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.010839702174659275, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.011490542397924066, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.012265096533412172, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.014932132958067022, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.018876397112828208, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.03635371212248376, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.07149168217602835, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.09069971596031419, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.11171349880476299, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.13236297350952733, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.1538702762782959, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.17083085571990184, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.18759607685675592, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.19414495713462973, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.20031949910700544, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.20932589042348115, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.21331888089506745, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.22127566685655334, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.2187123976341736, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.21555994404587508, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.21431894293138196, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.2104891362956319, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.21134277323072617, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.21171984713241368, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.20832632769967205, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.1958341928022754, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.18032710453320822, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.18831426613559857, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.1703161043862943, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.16841832028236584, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.16950021485038536, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.1662591290524044, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.158774875385819, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.17160295778117882, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.16471593547811195, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 25, "lr_best": 0.00035999999999999997, "wd_best": 0.05, "train/loss_best": 2.163065347671509, "validation/loss_best": 2.3722212314605713, "validation/acc_best": 0.2886674049464747, "validation/f1_best": 0.22127566685655334} +{"epoch": 6, "train/lr": 0.0002924170901991409, "train/loss": 2.5774658834934234, "train/grad": 0.2484837603569031, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.129293212890625, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.12861572265625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.1272705078125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.126007080078125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.124759521484375, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.123062744140625, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.12120849609375, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.119229736328125, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.11632568359375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.113082275390625, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.109215087890625, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.1003485107421875, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.0794482421875, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.971646423339844, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.803827209472656, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.6871041107177733, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.598214340209961, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.522313346862793, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.449934387207031, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.3888632583618166, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.32436918258667, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.2661320209503173, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.20951455116272, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.158558406829834, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.1099971103668214, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.0648072504997255, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.0307203197479247, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.0015272176265717, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.9781963336467743, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.9509192323684692, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.9372346663475037, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.9344575476646424, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.9336781030893326, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.9481145399808883, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.9634272223711013, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.9943911159038543, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.03340114235878, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.07135194838047, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.1306273514032363, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.228244570493698, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.2912348651885988, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.328430367708206, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.435475687980652, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.171875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.020620491802692414, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.02062525146175176, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.020628817025572063, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.02063347607385367, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.0206352621037513, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.020635937694460153, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.020634410623461007, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.020625816164538263, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.02060373889748007, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.020565910250879824, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.02051075219642371, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.0204010516917333, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.02038266756106168, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.02174543500877917, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.024511584341526033, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.026667170953005553, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.028342666309326886, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.02975173053331673, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.031359326737001536, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.03297938433475792, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.03445461671799421, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.03545680289156735, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.03612064427696168, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.03660361355170608, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.03739465582184494, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.038443158566951754, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.03968840045854449, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.040580871608108283, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.04101191809400916, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0419270571321249, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.04310575183480978, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.04430288469418883, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.04548970287665725, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.04607521116733551, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0474682816490531, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.04855022914707661, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.050684730038046834, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.05181461444124579, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0540945472382009, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.05783730344846845, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.05994498608633876, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.06082856608554721, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.06374852515757085, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1208274364471436, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.120234966278076, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1193344593048096, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.118452548980713, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1176037788391113, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1164791584014893, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1151225566864014, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.113555908203125, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1112000942230225, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1079702377319336, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.103239059448242, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.0877277851104736, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.036837577819824, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.832125663757324, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.6815640926361084, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.6025307178497314, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.539820671081543, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.4850072860717773, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.4423253536224365, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.4166533946990967, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.3999969959259033, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.3943605422973633, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.3955771923065186, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.398184061050415, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.4076383113861084, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.4335196018218994, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.462860107421875, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.5052125453948975, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.519193410873413, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.51102876663208, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.5126023292541504, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.531747817993164, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.5819737911224365, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.613481044769287, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.641160488128662, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.6508069038391113, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.7017388343811035, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.7127788066864014, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.758302927017212, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.8130152225494385, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.85320782661438, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.7234396934509277, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.8486645221710205, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06847545219638243, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.0681063122923588, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.0681063122923588, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.0681063122923588, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06921373200442968, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06976744186046512, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.07069029162052418, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.0725359911406423, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.07401255075673681, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.07511997046880768, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.07604282022886674, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.08471760797342193, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.11055740125507567, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.16205241786637137, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.1952750092284976, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.21963824289405684, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.23661867847914358, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.25359911406423036, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.26301218161683276, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.27445551864156514, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.2794389073458841, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.28054632705795496, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.2794389073458841, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.2838685861941676, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.28165374677002586, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.27353266888150607, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.2722406792174234, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.26707272056109266, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.2678110003691399, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.2703949796973053, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.2698412698412698, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.2705795496493171, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.2643041712809155, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.26301218161683276, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.2497231450719823, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.24953857511997046, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.23440383905500184, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.2412329272794389, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.22572905131044665, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.2279438907345884, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.22406792174234036, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.22831303063861202, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.2277593207825766, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.009190258307093871, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.00922032065937291, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.009452429946414303, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.009447976837894702, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.010001360748934145, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.011380367444356438, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.01229848155284506, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.014474707294858573, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.016175199102990995, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.018366098162841044, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.021234772610386754, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.030220181639953287, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.051236828081021646, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.0830689450443115, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.11402844520124777, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.13939754089680248, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.15994805389820058, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.18222488591884653, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.19609003804449535, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.20983626277322823, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.2153663602236169, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.21850509190560455, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.21939638646632406, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.22510231728351301, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.22497747520283728, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.21915804919096712, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.21691504005255813, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.21110175789424734, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.21336406268237407, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.21826964949529784, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.2216074512181935, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.22426410445121414, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.21552157460610913, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.21368453352164377, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.21195354149172085, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.20593462209761873, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.20068845728021767, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.19394771969140523, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.1829978257313409, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.18631713471521927, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.1768253222100895, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.18046111573498402, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.18578517822952048, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 23, "lr_best": 0.00025499999999999996, "wd_best": 0.05, "train/loss_best": 2.158558406829834, "validation/loss_best": 2.398184061050415, "validation/acc_best": 0.2838685861941676, "validation/f1_best": 0.22510231728351301} +{"epoch": 7, "train/lr": 0.00027969249556793234, "train/loss": 2.4935777938365935, "train/grad": 0.25133944049477575, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.126800537109375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.12576904296875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.124151611328125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.122542724609375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.12096435546875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.118787841796875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.116175537109375, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.113349609375, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.108961181640625, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.103045654296875, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.0939862060546877, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.0581005859375, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.9497421264648436, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.7421859741210937, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.6256977844238283, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.5556668853759765, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.48229549407959, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.4033404922485353, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.3294976234436033, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.2723551559448243, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.2111445903778075, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.1533962535858153, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.0957947063446043, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.0421908044815065, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.9897464895248413, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.940750298500061, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.9016802418231964, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.87063461124897, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.849153391122818, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.8241136652231216, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.8109992402791977, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.8078116863965987, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.8104286396503448, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.8244724881649017, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.839344429373741, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.8713031756877898, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.904988626241684, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.9517648702859878, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.013153398633003, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.0918146604299546, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.1415202909708024, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.2194712561368943, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.294969490170479, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.171875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.02012276729568839, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.02012564013246447, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.020128674674779176, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.020129817058332264, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.020128302313387393, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.020121867167763412, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.020110240560024976, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.02008866532240063, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.020047948751598595, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.019980147420428692, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.019905850095674395, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.020013592899776996, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.02139491556212306, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.024772147005423902, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.027011269861832263, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.028276457777246834, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.029758834913372993, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.0318434349168092, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.033800189178436996, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.03491575540974736, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.035872220108285544, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.03668695417232812, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.037475850945338604, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0382260100543499, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.03918068289756775, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.040113828331232074, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.041070631612092255, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.041941054109483955, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.04313681358471513, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.044509201422333715, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.04555751347914338, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.04639883665367961, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.047666000835597515, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.04829563904553652, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.04895667392760515, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.04987948782742024, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.050619824510067704, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.05200294373556971, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.05323692297562957, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.05530589869245887, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.05576576817780733, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.05840888103470206, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.060581408701837064, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.119985342025757, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1193363666534424, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1182782649993896, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.117281198501587, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1162636280059814, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.114849090576172, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.113192319869995, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1111690998077393, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1077075004577637, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.101684331893921, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.0889804363250732, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.021085023880005, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.8572590351104736, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.6809253692626953, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.5947105884552, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.5405852794647217, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.4868342876434326, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.4395852088928223, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.411207437515259, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.3978281021118164, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.3907928466796875, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.396000623703003, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.416274070739746, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.4385149478912354, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.456890821456909, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.474030017852783, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.4971888065338135, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.541804790496826, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.556720018386841, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.616643190383911, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.672018527984619, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.689448833465576, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.6775014400482178, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.720332145690918, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.7748019695281982, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.864814519882202, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.8710083961486816, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.9031007289886475, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.9225800037384033, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.8641555309295654, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.8632071018218994, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.9738190174102783, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.0401663780212402, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06976744186046512, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06921373200442968, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.07142857142857142, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.0725359911406423, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.07198228128460686, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.07198228128460686, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.07290513104466592, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.07364341085271318, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.07678110003691399, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.08084163898117387, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.08545588778146918, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.11166482096714656, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.16020671834625322, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.20302694721299372, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.2201919527500923, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.2355112587670727, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.24806201550387597, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.2617201919527501, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.26891842008121075, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.2737172388335179, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.2763012181616833, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.2766703580657069, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.2779623477297896, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.27611664820967147, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.27556293835363604, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.27260981912144705, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.26301218161683276, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.2631967515688446, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.26707272056109266, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.2606127722406792, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.2528608342561831, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.24898486526393504, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.2467700258397933, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.24307862679955702, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.2355112587670727, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.22702104097452935, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.22978959025470652, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.2364341085271318, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.2220376522702104, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.22905131044665927, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.2294204503506829, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.21797711332595054, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.21096345514950166, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.011174613676144007, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.011356209221865301, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.01312685920731327, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.014048875567006841, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.01413565864588282, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.014606903415330705, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.015432693359754472, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.016281475977122924, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.0179368071379284, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.020249179103187465, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.02292731571609651, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.04185511637213855, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.07875717338628287, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.1215806107327337, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.1394250411444395, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.15712655139283815, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.17618044199361482, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.19584320838854175, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.20436469750784347, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.21245945282274006, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.2179243780628922, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.2212616617455853, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.22178210959341094, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.22347868595387918, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.22681915441513759, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.22729214653384822, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.2167837725216587, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.21638655898306278, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.21618995412908862, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.21003648057694968, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.2057859404399546, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.20493578270521573, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.20361930500908368, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.19749252366880699, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.18843957984672824, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.18181717503557301, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.18079265571756153, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.18753352862680225, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.17606230057592476, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.18051681664639596, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.18104872031995586, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.16826549426632198, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.14728977422724163, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 22, "lr_best": 0.00021599999999999996, "wd_best": 0.05, "train/loss_best": 2.0957947063446043, "validation/loss_best": 2.416274070739746, "validation/acc_best": 0.2779623477297896, "validation/f1_best": 0.22178210959341094} +{"epoch": 8, "train/lr": 0.0002612959497061927, "train/loss": 2.4320630824565885, "train/grad": 0.2628987566381693, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.1223046875, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.12109375, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.119306640625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.117559814453125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.1157177734375, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.1132861328125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.1102734375, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.10651123046875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.100364990234375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.0891680908203125, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.0637005615234374, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.9426873779296874, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.771482391357422, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.6197589111328123, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.5391565704345704, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.477657661437988, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.404006156921387, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.327432098388672, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.260350589752197, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.203448944091797, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.1396509552001954, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.0775371551513673, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.0156865167617797, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.9589296340942384, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.9048181235790254, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.8531316578388215, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.810874263048172, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.7784922832250596, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.7593856924772262, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.732683093547821, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.7105161762237548, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.701178439259529, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.7045325249433518, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.7270032477378845, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.744423251748085, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.7769728314876556, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.8098691350221634, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.8655011355876923, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.923747643828392, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.0112725561857223, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.077763685584068, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.1279437214136125, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.2026614320278166, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.171875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.020795598840340972, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.020799001920968296, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.02080335990525782, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.02080540640745312, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.02080308607313782, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.02079539429396391, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.02077715754043311, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.020746429758146404, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.020680954330600798, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.02059538963716477, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.020637527317740025, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.022067376389168204, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.02477593533694744, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.027804494919255376, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.029412782602012157, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.030697230407968165, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.032747944379225374, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.03502249416895211, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.036404512617737056, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.03726176422089338, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.03795127163641155, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.038546902034431695, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.03921511812135577, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.040157215725630524, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.041344655118882655, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.042600461132824424, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.04382029931992292, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.04485074317082763, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.04581720368936658, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.046856787353754044, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.04769186047837138, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.04866969296708703, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.04985509594902396, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.05072851510718465, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.05163467800244689, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.05188583556562662, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.05248451430350542, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.054081479161977766, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.055035404823720456, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.05672530628740788, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.057245444506406784, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.058029555529356, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.060514889247715475, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1192123889923096, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1183478832244873, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1169495582580566, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.115544319152832, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.114121198654175, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1120376586914062, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.109461545944214, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.105987787246704, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.0990664958953857, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.083514928817749, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.0402615070343018, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.867147445678711, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.716175079345703, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.6016268730163574, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.539851665496826, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.494971990585327, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.45530366897583, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.4336416721343994, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.429608106613159, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.430832862854004, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.441283941268921, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.4571657180786133, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.4741199016571045, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.496137857437134, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.5208632946014404, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.561589479446411, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.594770908355713, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.614452362060547, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.6282100677490234, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.691307544708252, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.718456983566284, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.7679824829101562, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.84660005569458, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.8797361850738525, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.929264545440674, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.955009698867798, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.97784161567688, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.100281238555908, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.1849238872528076, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.019045829772949, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.071439504623413, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.127390146255493, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.9940989017486572, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.0664451827242525, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06662975267626431, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.0695828719084533, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.07179771133259505, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.073827980804725, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.07604282022886674, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.07733480989294943, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.08176448874123293, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.08324104835732743, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.09099298634182355, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.1138796603912883, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.15799187892211147, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.18752307124400147, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.21982281284606867, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.23403469915097821, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.24363233665559247, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.25599852344038393, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.26393503137689184, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.266703580657069, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.2698412698412698, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.26541159099298633, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.26651901070505724, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.262827611664821, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.26356589147286824, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.26393503137689184, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.25839793281653745, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.2515688445921004, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.24898486526393504, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.25359911406423036, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.2497231450719823, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.24953857511997046, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.24584717607973422, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.23920265780730898, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.2355112587670727, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.23385012919896642, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.23274270948689554, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.22314507198228128, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.21631598375784422, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.2056109265411591, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.22111480251015134, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.2081949058693245, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.20376522702104097, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.2203765227021041, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.009520565164143008, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.010034019269458105, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.013213073642940706, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.015427098405700487, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.01745782894578353, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.01991276076059791, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.021296232190633414, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.02421379409731021, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.02604625255668003, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.03480722292025818, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.05345342550221525, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.07855055571673457, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.10830341303204487, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.14351839946130854, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.160308544271153, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.17480564980596067, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.19111671100187308, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.20188177468145843, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.2065059903964027, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.21141238165496254, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.209074147792931, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.2099731153528176, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.2064632897207828, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.20685368154328132, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.2073197038170579, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.20563561870899216, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.2021567650826742, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.19944123283825024, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.20132164009440265, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.19759553389529802, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.19682922258087268, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.1932416909977789, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.1871109840951218, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.18491843939596878, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.18027130973688044, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.17415106789792123, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.17913755093951375, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.17318337610514764, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.16041977169115113, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.17413780663796996, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.16067063213628072, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.1595184316498737, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.16835680383413923, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 19, "lr_best": 0.00013199999999999998, "wd_best": 0.05, "train/loss_best": 2.203448944091797, "validation/loss_best": 2.430832862854004, "validation/acc_best": 0.2698412698412698, "validation/f1_best": 0.21141238165496254} +{"epoch": 9, "train/lr": 0.00023803200426111704, "train/loss": 2.3819390869140626, "train/grad": 0.2671831854432821, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.1207080078125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.1194091796875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.117078857421875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.114925537109375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.11273681640625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.109630126953125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.105782470703125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.1007305908203127, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.0907177734375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.0667877197265625, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.9991705322265627, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.8083201599121095, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.6705856323242188, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.562131042480469, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.4885477447509765, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.424281806945801, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.3476125144958497, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.274792251586914, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.2076375389099123, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.149389820098877, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.084540615081787, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.0209380531311036, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.9571920394897462, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.898166879415512, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.840864624977112, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.7834098517894745, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.7315966749191285, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.693507603406906, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.6696744459867476, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.633592295050621, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.6108648461103439, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.5977104431390763, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.6004910469055176, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.6153236293792725, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.6401634776592255, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.684862272143364, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.7324962574243545, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.7925477510690688, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.879214117527008, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.9536000347137452, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.017201524972916, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.0863937312364578, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.168440264463425, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.171875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.020677036731503905, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.020677263787947594, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.020675456034950912, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.02067230850458145, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.02066550843883306, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.02064749099779874, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.020620412863790988, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.020571594242937863, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.020487764049321414, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.02048903241287917, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.021173278680071236, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.0240431513171643, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.02663586486130953, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.02887664978392422, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.030320199439302087, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.031849660677835345, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.034045519083738325, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.03570050078444183, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.036701106345281, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.037435195008292795, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.03814155499450862, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.03885945918038487, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.03975606914609671, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.040720162931829694, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.04198635477572679, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.043324137087911364, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.04445288250222802, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.04539619391784072, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.046281226798892024, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.04758560061454773, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.04868262326344848, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.04947115099057555, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.05096874291077256, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.05103896582499146, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.052164993546903134, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.05282631404697895, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.05405267283320427, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.055342384316027164, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.05713721973821521, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.057862527761608364, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.05790110170841217, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.05966389156877994, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.060196944959461686, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.118401288986206, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.117478847503662, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1159675121307373, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1144449710845947, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1128854751586914, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.110551595687866, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.107421398162842, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.10258412361145, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.090690851211548, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.054826021194458, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.95176100730896, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.7559709548950195, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.642184019088745, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.5560083389282227, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.5010995864868164, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.4597678184509277, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.423922538757324, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.4031171798706055, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.395432472229004, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.394827365875244, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.404910087585449, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.4179904460906982, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.440412759780884, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.4594979286193848, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.4931976795196533, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.5409111976623535, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.596219062805176, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.656934976577759, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.6582133769989014, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.7194454669952393, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.7989423274993896, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.854726791381836, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.9115946292877197, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.9508697986602783, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.013409376144409, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.0362610816955566, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.02081036567688, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.9717953205108643, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.9931886196136475, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.917830228805542, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.8673665523529053, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.8456177711486816, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.8488993644714355, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06866002214839424, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.07032115171650055, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.07235142118863049, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.07511997046880768, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.07733480989294943, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.07807308970099668, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.07936507936507936, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.08324104835732743, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.08951642672572906, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.10760428202288667, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.14082687338501293, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.18014027316352899, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.20801033591731266, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.22757475083056478, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.2425249169435216, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.2547065337763012, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.26799557032115173, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.2742709486895533, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.28036175710594313, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.27999261720191954, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.28017718715393136, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.27851605758582504, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.27113325950535255, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.26596530084902176, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.2567368032484312, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.25489110372831303, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.24806201550387597, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.2410483573274271, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.24492432631967515, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.23255813953488372, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.22609819121447028, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.22517534145441123, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.23311184939091917, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.2216685123661868, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.20985603543743078, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.2131782945736434, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.2172388335179033, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.2146548541897379, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.20911775562938353, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.22296050203026946, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.20967146548541898, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.2187153931339978, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.21391657438169065, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.009842396702126803, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.011007047729946824, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.012622864373014084, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.014948629354323674, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.017327515599531388, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.0186749279597366, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.021810925992729508, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.026296238094629897, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.031258730975177985, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.046310152630338504, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.06892440488264963, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.09646621990559091, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.12247973237401288, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.1450542421247931, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.16481489385702283, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.1785753933838866, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.19435462964043118, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.20247945388788444, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.2101022533240574, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.2135659863609292, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.21686334699294108, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.21876292597670757, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.214855130939686, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.2123803413042112, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.20812211933799127, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.21218825429755928, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.20975315535452269, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.20762923962516752, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.2127398765381651, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.20422478949989206, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.19832581075106306, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.19447648729390263, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.19079922964352325, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.1779032848981407, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.1691315736045337, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.17428792268629392, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.17612593941593546, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.18034443717849954, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.17254307162972515, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.18073147810523152, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.17363586237157227, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.17837469701016292, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.17552197817651827, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 18, "lr_best": 0.00011399999999999999, "wd_best": 0.05, "train/loss_best": 2.2076375389099123, "validation/loss_best": 2.395432472229004, "validation/acc_best": 0.28036175710594313, "validation/f1_best": 0.2101022533240574} +{"epoch": 10, "train/lr": 0.00021091808096876188, "train/loss": 2.3164026713371277, "train/grad": 0.26358733475208285, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.1195068359375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.117991943359375, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.115618896484375, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.113145751953125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.1106396484375, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.107008056640625, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.102325439453125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.095433349609375, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.0786102294921873, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.0270562744140626, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.9030035400390624, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.71375732421875, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.6067852783203125, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.512007827758789, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.437450981140137, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.3704763793945314, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.2951113891601564, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.2245364570617676, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.1559506320953368, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.0949559116363528, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.0265477752685546, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.9586117792129516, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.888640387058258, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.8222822833061219, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.7567792534828186, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.6919635784626008, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.6402609145641327, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.5998918491601943, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.5661575293540955, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.5289306688308715, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.4995723205804825, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.4838393771648406, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.4757821184396744, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.494050670862198, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.5183592766523362, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.5687956553697586, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.6180325168371201, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.657686843276024, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.7247299093008042, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.8066473388671875, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.8644741809368133, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.9650716233253478, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.014003301858902, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.171875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.020358920088037847, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.020358286164700985, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.0203551213350147, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.020348529289476572, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.020338885807432233, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.020317986034788193, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.02028030417393893, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.020221136985346676, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.020155007359571753, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.020487760133109986, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.022076346995308995, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.025207438319921494, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.027442009607329964, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.02940897670574486, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.031083729919046163, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.03290326113812626, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.03499093745835125, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.03636458448134363, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.03728372633457184, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.037985762022435664, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.03863134197890759, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.03927205301821232, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.04000526364892721, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.04075582902878523, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.04185389026999473, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.04321926269680262, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.04464651433750987, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.045646554958075285, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0462051972001791, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.04739379985257983, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.04867784440517425, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.04952096972614527, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.050765822771936656, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.05127562316134572, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.051504090297967195, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.05283471653237939, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.05343424215912819, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.05372637577354908, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.05451628038659692, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.055020685102790595, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.05420685175806284, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.05692731799557805, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.05509300110861659, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1181373596191406, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.117173194885254, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1156005859375, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1140072345733643, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1122632026672363, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.109527111053467, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.10551381111145, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.0984995365142822, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.077677011489868, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.0044524669647217, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.8594205379486084, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.6900980472564697, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.6012542247772217, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.5274887084960938, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.4758713245391846, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.441847324371338, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.418971538543701, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.404526948928833, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.396754741668701, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.394127368927002, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.4025208950042725, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.419433116912842, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.4522674083709717, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.488170862197876, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.543595790863037, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.6172616481781006, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.6696648597717285, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.7273898124694824, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.7504560947418213, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.860365629196167, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.9040637016296387, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.964444875717163, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.0248007774353027, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.077889919281006, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.1220858097076416, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.095937728881836, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.1929636001586914, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.076385974884033, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.0569229125976562, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.043532609939575, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.0188369750976562, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.141261577606201, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.0396010875701904, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06829088224437062, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06921373200442968, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06921373200442968, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.07050572166851236, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.07069029162052418, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.07290513104466592, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.07585825027685493, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.08047249907715023, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.08840900701365817, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.12292358803986711, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.1596530084902178, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.1984126984126984, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.2188999630860096, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.24197120708748615, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.2561830933923957, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.26393503137689184, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.2698412698412698, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.2748246585455888, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.27999261720191954, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.2836840162421558, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.2796234772978959, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.27851605758582504, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.2702104097452935, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.2648578811369509, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.2556293835363603, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.24584717607973422, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.23864894795127353, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.2368032484311554, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.23791066814322628, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.23108157991878922, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.22554448135843486, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.22388335179032853, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.2248062015503876, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.21853082318198597, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.21686969361387967, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.2146548541897379, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.20358065706902917, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.2207456626061277, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.20930232558139536, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.20837947582133629, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.21207087486157253, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.20062753783684018, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.21114802510151348, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.011808664457044713, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.01319827900893608, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.014388190281920529, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.015817151637030628, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.01612041790468648, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.017363763687293098, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.01955676283924106, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.023456765097391485, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.03228474388453828, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.05572366196865092, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.07926984390553839, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.11757504408413655, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.13881984570226394, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.16344989365662077, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.18140997625421554, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.1927092778773358, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.2005881039876917, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.20657838119330132, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.216223302419401, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.2199987357483111, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.21763559262243812, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.21862167738410557, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.2129833994283852, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.21141186013866187, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.20444181866182842, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.19950303092551602, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.1960751103180992, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.19652089646235452, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.197199841355748, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.19096405481426895, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.19155593040378385, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.18777374765771646, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.1823664468849769, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.17379793323253911, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.17787357012732696, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.18062079706032697, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.1652538128177704, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.18779576881858082, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.1773678751844657, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.17119579788395367, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.17405696054744157, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.16511986456048378, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.17463760535358178, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 19, "lr_best": 0.00013199999999999998, "wd_best": 0.05, "train/loss_best": 2.0949559116363528, "validation/loss_best": 2.394127368927002, "validation/acc_best": 0.2836840162421558, "validation/f1_best": 0.2199987357483111} +{"epoch": 11, "train/lr": 0.00018113997589164516, "train/loss": 2.269645071029663, "train/grad": 0.2688236546516418, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.12400390625, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.122445068359375, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.119866943359375, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.1171533203125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.11453857421875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.110394287109375, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.10477294921875, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.0953765869140626, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.0680877685546877, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.97698974609375, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.8268083190917968, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.665345458984375, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.5767412567138672, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.4852545166015627, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.405834846496582, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.3357670593261717, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.261450099945068, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.191178789138794, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.12291552066803, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.061800465583801, "train/loss_020_lr5.2e-01_wd1.0e+00": 1.9915003430843354, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.9209835159778594, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.8496806335449218, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.7808470666408538, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.7128478652238845, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.6417287075519562, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.5832934403419494, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.5358274781703949, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.4978505820035934, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.451588113307953, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.4147145068645477, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.3957056611776353, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.3853249436616897, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.4005383896827697, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.413573170900345, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.4486425513029098, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.4991226118803025, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.543816587328911, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.608556841611862, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.6886099606752396, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.777590297460556, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.8360873228311538, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.9162049555778504, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.171875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.020463128774426877, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.020461868518032132, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.02045620761346072, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.02044912490993738, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.0204378780676052, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.020411675195209682, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.02036745483055711, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.020303050223737955, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.020321128200739624, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.02126709868200123, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.02344711823388934, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.02648644826374948, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.028392407977953553, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.030327650839462875, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.03228635500185192, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.03428283086977899, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.0361857270821929, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.03745091140270233, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.038312734169885516, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.03900571285746992, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.03977716866880655, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.04056740647181869, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.041409088131040335, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.04235470274463296, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0435983046144247, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.04495862815529108, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.04640769332647324, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.047392083294689656, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.04795327508822084, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.04912931628525257, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.05035286709666252, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.05144212450832129, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.05261066410690546, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.05270198354497552, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.053040635883808133, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.05320518909022212, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.053148472011089326, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.05436941534280777, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.05492097364738584, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.054158255346119406, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.054214264750480655, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.05438582256436348, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.05471877174451947, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1176185607910156, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1165149211883545, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1146738529205322, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1127326488494873, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.110645294189453, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.107264995574951, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.102001905441284, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.0919101238250732, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.0569286346435547, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.9398672580718994, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.789149045944214, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.6470861434936523, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.5752933025360107, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.5100507736206055, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.465383768081665, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.4393703937530518, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.423511505126953, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.4135403633117676, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.4086804389953613, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.407521963119507, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.4187235832214355, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.4364266395568848, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.464162588119507, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.489514112472534, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.5278573036193848, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.5771636962890625, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.6180713176727295, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.6754562854766846, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.712131977081299, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.775485038757324, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.8601057529449463, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.9485931396484375, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.029334306716919, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.021876811981201, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.038008451461792, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.06339693069458, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.0809314250946045, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.070415496826172, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.0047686100006104, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.9404242038726807, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.860187292098999, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.885835886001587, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.8223536014556885, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06884459210040605, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06995201181247693, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.07179771133259505, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.07198228128460686, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.07345884090070137, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.07678110003691399, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.0799187892211148, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.08693244739756367, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.1079734219269103, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.14581026208933184, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.17423403469915097, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.20524178663713546, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.22462163159837578, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.24529346622369877, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.2556293835363603, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.26375046142488, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.271686969361388, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.2794389073458841, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.2798080472499077, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.28183831672203763, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.27999261720191954, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.2763012181616833, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.2702104097452935, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.26356589147286824, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.26264304171280917, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.2552602436323367, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.2497231450719823, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.24880029531192321, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.25212255444813586, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.24621631598375784, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.2441860465116279, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.24086378737541528, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.23754152823920266, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.24141749723145073, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.2351421188630491, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.23403469915097821, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.23255813953488372, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.23624953857511996, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.22997416020671835, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.24234034699150978, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.2334809892949428, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.23624953857511996, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.23034330011074197, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.011982004280106817, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.013499167905712761, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.014274149816470816, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.01503880569720567, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.0169288842628946, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.01934959723352828, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.02108325475397403, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.029496267723762695, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.049511292390364635, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.06971955326055647, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.09058293909555722, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.12246394266763494, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.1421030272956758, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.16403425796852014, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.17820154784955156, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.1896126562211599, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.20016600269302987, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.2127616931517374, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.21730100904590546, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.22142418239973768, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.22310574289161736, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.2199457242763642, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.21708957570606982, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.21394234206691523, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.21703630715668812, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.21550154408389796, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.20920800532121733, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.21174305321737039, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.21353681663345728, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.2086319755470378, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.20445132340245667, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.20098137460933427, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.19214617836045292, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.1999670630859288, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.19882811749292165, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.19859414225228655, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.19708463453492656, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.19139036158171452, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.1909340800442699, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.19936280430078032, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.20159930148342267, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.20417344384803252, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.2029192759468459, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 19, "lr_best": 0.00013199999999999998, "wd_best": 0.05, "train/loss_best": 2.061800465583801, "validation/loss_best": 2.407521963119507, "validation/acc_best": 0.28183831672203763, "validation/f1_best": 0.22142418239973768} +{"epoch": 12, "train/lr": 0.0001499999999999999, "train/loss": 2.202489414215088, "train/grad": 0.2660027337819338, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.11618896484375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.114415283203125, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.111383056640625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.108369140625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.10518310546875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.100196533203125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.0929876708984376, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.079984130859375, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.0361639404296876, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.9043338012695314, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.75269287109375, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.612898712158203, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.533724136352539, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.4437866592407227, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.3638942718505858, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.296836566925049, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.224959468841553, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.15238543510437, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.0802894020080567, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.015340557098389, "train/loss_020_lr5.2e-01_wd1.0e+00": 1.9398520040512084, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.8669982051849365, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.7919560503959655, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.7165766954421997, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.6411344492435456, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.5614124059677124, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.4927709221839904, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.4390696448087692, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.3890395319461823, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.3324327260255813, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.2892043530941009, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.261805168390274, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.2356708654761315, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.2482577547430993, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.2559161311388016, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.2943311232328414, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.347299994826317, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.398304464817047, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.4555265229940415, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.562457379102707, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.6439485031366348, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.6912042862176895, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.7895500254631043, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.171875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.020464604115113617, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.020464010210707782, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.020458160401321947, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.02044998690020293, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.020435992241837085, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.020405058288015424, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.020351859866641463, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.020291916895657777, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.020475612743757664, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.02205673628952354, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.02448587404564023, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.027416686518117784, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.029150903057307005, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.031224349308758975, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.03338640092872083, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.03524571635760367, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.03688389968127012, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.03801103919744492, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.03876394957304001, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.03940444834530354, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.040150687992572785, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.04088233906775713, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.04173485727980733, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.04262325648218393, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.043650266751646995, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.04474202994257212, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.04584679715335369, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.046799810100346804, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.047395870368927714, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.048449030220508574, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0493570695631206, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.050200492087751625, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.050760064646601676, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.05120070720091462, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.05163025068119168, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.052518903017044066, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.05230693399906158, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.05284358486533165, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.052891374342143534, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.05317731378600001, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0528859088011086, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.05234601642936468, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.05333573078736663, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1174161434173584, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.116274356842041, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.114342451095581, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.112297773361206, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1100587844848633, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1061885356903076, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.0997607707977295, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.0862510204315186, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.034097909927368, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.8882999420166016, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.7476704120635986, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.6235642433166504, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.5596823692321777, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.498321056365967, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.4595909118652344, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.441368341445923, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.4318907260894775, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.426691770553589, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.428101062774658, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.4374537467956543, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.4619617462158203, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.4910192489624023, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.534456491470337, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.570939540863037, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.599135398864746, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.6471920013427734, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.7093863487243652, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.7922940254211426, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.831624746322632, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.942277431488037, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.002950668334961, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.0625646114349365, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.171771287918091, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.1774747371673584, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.217174768447876, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.2226293087005615, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.235698699951172, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.1944832801818848, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.183584690093994, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.0782530307769775, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.068803548812866, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.032562255859375, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.918365240097046, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06736803248431156, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.0681063122923588, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06939830195644149, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.07198228128460686, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.07308970099667775, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.07493540051679587, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.0784422296050203, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.08600959763750461, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.11720191952750092, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.1566998892580288, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.18032484311554078, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.21040974529346623, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.2249907715023994, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.24713916574381692, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.26098191214470284, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.2672572905131045, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.26836471022517533, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.2698412698412698, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.27556293835363604, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.271686969361388, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.2672572905131045, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.2648578811369509, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.2582133628645257, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.25378368401624213, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.25858250276854927, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.25655223329641935, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.24880029531192321, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.23791066814322628, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.24787744555186417, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.2395717977113326, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.2395717977113326, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.23440383905500184, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.23458840900701367, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.23329641934293097, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.2307124400147656, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.22720561092654115, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.22517534145441123, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.2279438907345884, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.21834625322997417, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.24289405684754523, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.2292358803986711, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.2279438907345884, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.23255813953488372, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.009918847062063557, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.010617551045365353, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.012110252521515631, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.013690830561969021, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.01519196074666824, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.016693261999377488, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.02050729712544903, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.030445182902360476, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.055616273009688764, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.07625326738594106, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.09657836501375912, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.1270324210555581, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.14202220465359003, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.16758295509736074, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.18588563118814938, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.19619475039084056, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.19890757374144794, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.2046593916162646, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.2149804564390102, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.21180168818757047, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.20706754909182487, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.2064345401060849, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.20174578923636655, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.19866561096227361, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.2016319706337014, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.20014771398214928, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.19603563995287976, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.18592044613459371, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.19419761156588625, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.18562904933402627, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.19036718212698103, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.18668508549459387, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.18396356489393648, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.18913186759350076, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.1860484828955081, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.18645659550008883, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.18629592217803967, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.18441501769573612, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.17858927672336647, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.189960695050822, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.18060432673639917, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.18308736760488972, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.1872171566525858, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 18, "lr_best": 0.00011399999999999999, "wd_best": 0.05, "train/loss_best": 2.0802894020080567, "validation/loss_best": 2.428101062774658, "validation/acc_best": 0.27556293835363604, "validation/f1_best": 0.2149804564390102} +{"epoch": 13, "train/lr": 0.00011886002410835478, "train/loss": 2.1564790779352188, "train/grad": 0.2652108895033598, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.119486083984375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.117635498046875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.11450927734375, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.11130126953125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.107867431640625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.10250244140625, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.0942669677734376, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.078133544921875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.0188787841796874, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.866926574707031, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.72487548828125, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.599303436279297, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.5235304260253906, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.4316972351074218, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.3500321960449218, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.2836652183532715, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.2113308715820312, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.137379026412964, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.062969512939453, "train/loss_019_lr4.4e-01_wd1.0e+00": 1.9960588121414184, "train/loss_020_lr5.2e-01_wd1.0e+00": 1.9185031020641328, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.842547186613083, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.7639512968063356, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.6859494739770888, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.6040053522586823, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.517508710026741, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.4427075040340425, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.3834246665239334, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.3258980774879456, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.2611426323652268, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.2027485352754592, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.1632050496339799, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.1243683129549027, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.132297067940235, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.1372302407026291, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.1543281903862954, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.2131628301739692, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.2534716314077377, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.3116934019327164, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.4033119958639144, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.5160440599918366, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.5643175399303437, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.662060758471489, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.171875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.020826591914519667, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.020823084181174636, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.020814049439504743, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.020802166881039738, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.020781460138969123, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.020740814264863728, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.020677413092926145, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.020622449060902, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.020998440845869482, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.022955647185444832, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.025394863970577716, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.028113567875698207, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.029722981238737702, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.031862326823174955, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.03411016831174493, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.03584889576770365, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.03738088754937053, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.038428217628970744, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.03912452734075487, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.039789049047976734, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.04056492010131478, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.04130529897287488, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.04214003004133701, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0430684987269342, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.044139970261603594, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.04540213810279965, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.04668250491842627, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0477196404337883, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.04830641977488995, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.04880024842917919, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.04944467378780246, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0496609377861023, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.049740988332778215, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.05011576836928725, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.050198446623981, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.05034805016592145, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.05093850305303931, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.05130023537203669, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.05163016585633159, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.05229219550266862, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.05221883872523904, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0519173781760037, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.05160165153443813, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.116981267929077, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.115723133087158, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.113548755645752, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.111217737197876, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.108607769012451, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1041276454925537, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.096343755722046, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.0790157318115234, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.0092966556549072, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.8476016521453857, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.7144789695739746, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.6023237705230713, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.5432417392730713, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.4838485717773438, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.4461278915405273, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.4284462928771973, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.416904926300049, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.4104440212249756, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.411987781524658, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.419877529144287, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.4429421424865723, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.472052812576294, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.5143587589263916, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.5525670051574707, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.5970239639282227, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.661619186401367, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.747014284133911, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.8219153881073, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.8207497596740723, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.925157308578491, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.0502889156341553, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.1648895740509033, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.2794511318206787, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.3072164058685303, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.3786020278930664, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.4250524044036865, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.3834919929504395, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.331448793411255, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.3104848861694336, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.2313122749328613, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.1674933433532715, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.237464427947998, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.047057867050171, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.07013658176448874, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.07087486157253599, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.07364341085271318, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.073827980804725, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.07511997046880768, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.0769656699889258, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.08102620893318568, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.09283868586194167, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.1258767072720561, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.1626061277224068, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.18955334071613142, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.21705426356589147, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.23588039867109634, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.25193798449612403, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.26393503137689184, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.26836471022517533, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.2724252491694352, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.27759320782576596, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.2798080472499077, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.2777777777777778, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.2766703580657069, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.27464008859357697, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.26578073089701, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.26356589147286824, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.26116648209671467, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.2530454042081949, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.2410483573274271, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.2353266888150609, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.24197120708748615, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.23791066814322628, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.23015873015873015, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.21982281284606867, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.21963824289405684, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.21631598375784422, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.2081949058693245, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.20911775562938353, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.21354743447766703, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.2201919527500923, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.21797711332595054, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.22369878183831673, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.23126614987080105, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.21816168327796234, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.22462163159837578, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.012843384544412993, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.013965545912449093, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.015689027676651528, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.016653835279416995, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.018654080822899505, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.02045731788519366, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.023870688689182684, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.03609851721685113, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.058526969859916185, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.08009691872339855, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.10671291989341765, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.13351381873756393, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.15441860087351034, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.17392816268299746, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.18925770110543808, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.19676064844160032, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.20248700464012823, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.2122598387384859, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.21874860819577183, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.220052298911276, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.21881341582288236, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.21509070310901715, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.20914299952223495, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.20950286833130907, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.20860945446967064, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.2041101506707986, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.1928412405196125, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.19223338064455542, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.20158747000500019, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.1999001001241801, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.1938528366280314, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.18769243119881887, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.18775296381114245, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.18629607356485411, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.17723374197955652, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.1757017126937613, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.18309549361978827, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.1856291835784163, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.1803101613294182, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.18580326297303085, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.1833859909504664, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.18120825809932284, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.18114581078342806, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 18, "lr_best": 0.00011399999999999999, "wd_best": 0.05, "train/loss_best": 2.062969512939453, "validation/loss_best": 2.411987781524658, "validation/acc_best": 0.2798080472499077, "validation/f1_best": 0.21874860819577183} +{"epoch": 14, "train/lr": 8.9081919031238e-05, "train/loss": 2.1034862923622133, "train/grad": 0.26339964747428896, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.116712646484375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.11469970703125, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.111495361328125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.10811767578125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.10461181640625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.0987890625, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.0893853759765624, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.0699322509765623, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.99522216796875, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.830549468994141, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.693936309814453, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.574171905517578, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.4990997314453125, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.4052075576782226, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.3227630996704103, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.2572022247314454, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.1848309516906737, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.110029411315918, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.0343088817596438, "train/loss_019_lr4.4e-01_wd1.0e+00": 1.9659560298919678, "train/loss_020_lr5.2e-01_wd1.0e+00": 1.8864563536643981, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.8074414867162705, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.7248602712154388, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.6426859086751937, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.557968099117279, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.4660210770368576, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.383030697107315, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.3171555590629578, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.2494010883569717, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.1777180081605911, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.1157671573758126, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.0738370221853257, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.0218027997016907, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.0162381026148797, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.0078940111398698, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.0176735591888428, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.060876953303814, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.104007099866867, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.1551714539527893, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.2569934329390526, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.3725620192289352, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.4264921301603317, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.5105046945810319, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.171875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.02039836852811277, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.02039530907291919, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.020385786513797938, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.02037197371944785, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.02035444008652121, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.020317159416154026, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.02026324742939323, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.0202475000731647, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.020862337397411466, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.023118763864040374, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.02556261685676873, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.028122784113511445, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.02969494109041989, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.03194484426639974, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.03424263692460954, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.035880955467000604, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.03734061466529966, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.038345520179718734, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.03904073502868414, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.03969215424731374, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.04045837311074138, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.04115471940487623, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.04193329878151417, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.04287707520648837, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.043997165467590096, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.04529167367145419, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.04653654018417001, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.047434220295399426, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.048050140757113696, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.048663263656198975, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.04902436695992947, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.04948376260697842, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.04938395131379366, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.049545307289808986, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.049884455241262914, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.04992246188223362, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.05056341838091612, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.05070639019832015, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.05100127650424838, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.05228171458467841, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.05159033883363009, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.051299239937216044, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0505689406208694, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1163060665130615, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1149823665618896, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.112658739089966, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.110185384750366, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1074092388153076, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1024906635284424, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.0937085151672363, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.073040723800659, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.9886693954467773, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.82088565826416, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.6948556900024414, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.590503454208374, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.5337870121002197, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.476231813430786, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.4413743019104004, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.426184892654419, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.416628122329712, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.4118261337280273, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.4126172065734863, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.419196844100952, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.4387595653533936, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.460219144821167, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.4938321113586426, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.526575803756714, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.583266019821167, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.6566996574401855, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.73944091796875, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.8236005306243896, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.853584051132202, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.9428019523620605, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.0651051998138428, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.1813504695892334, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.2933833599090576, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.344553232192993, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.4967169761657715, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.546139717102051, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.59498929977417, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.489732503890991, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.4427425861358643, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.369018793106079, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.3243420124053955, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.2858102321624756, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.16387677192688, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.07069029162052418, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.07235142118863049, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.07308970099667775, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.07419712070874862, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.07438169066076043, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.07881136950904392, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.0843484680693983, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.09653008490217793, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.1314138058324105, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.16961978589885568, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.19472129937246216, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.21908453303802142, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.2349575489110373, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.25230712440014763, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.26559616094499816, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.2692875599852344, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.2757475083056478, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.2792543373938723, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.28202288667404946, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.2811000369139904, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.27759320782576596, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.2742709486895533, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.2698412698412698, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.25987449243263194, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.26135105204872644, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.2530454042081949, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.24326319675156885, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.23735695828719083, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.23791066814322628, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.2336655592469546, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.22720561092654115, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.21502399409376152, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.22240679217423404, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.21779254337393872, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.20376522702104097, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.19656699889258028, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.1997046880767811, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.2069029162052418, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.1997046880767811, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.2144702842377261, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.20948689553340716, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.20579549649317092, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.2087486157253599, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.011634339854628901, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.013007714583966665, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.01412613036621558, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.0156033608837199, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.016370640166540603, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.019987976582877844, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.02474689846912564, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.0378513274982949, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.06189444299344208, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.08525597133819553, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.11236453019811166, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.13557369482408987, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.15280028487930783, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.17489135782094442, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.1917371086871037, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.20014344826121322, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.2055947103071446, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.21440608306801823, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.21948050569536115, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.2218292508872796, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.2188561484462677, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.2179778550387673, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.21600706979240938, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.21069324311862392, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.2166170332757793, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.20894701086180642, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.20044091455879876, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.19689222373480608, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.20457154619479076, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.20329477691430564, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.19933637114523386, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.18835578123705202, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.19146882061796391, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.1854938986200149, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.17068264275254916, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.16801779980472853, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.17007752536847373, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.17925422860853982, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.1716254732072969, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.18420121915879414, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.17905883057984298, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.17572007157464523, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.17552388876555738, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 18, "lr_best": 0.00011399999999999999, "wd_best": 0.05, "train/loss_best": 2.0343088817596438, "validation/loss_best": 2.4126172065734863, "validation/acc_best": 0.28202288667404946, "validation/f1_best": 0.21948050569536115} +{"epoch": 15, "train/lr": 6.196799573888289e-05, "train/loss": 2.055947421789169, "train/grad": 0.25713264547288417, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.111923828125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.109879150390625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.10654052734375, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.10315185546875, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.099403076171875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.093333740234375, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.0831622314453124, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.0610296630859377, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.975242919921875, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.806582183837891, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.6764990234375, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.5639412689208982, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.489766311645508, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.3939964294433596, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.309864196777344, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.2434890937805174, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.1691332244873047, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.0919083404541015, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.013560247421265, "train/loss_019_lr4.4e-01_wd1.0e+00": 1.9433974266052245, "train/loss_020_lr5.2e-01_wd1.0e+00": 1.861624505519867, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.781785844564438, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.697250030040741, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.611785352230072, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.523344834446907, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.4263790225982667, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.3392202562093736, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.2674807196855544, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.189194157421589, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.0992176520824433, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.0283426123857498, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.9747408345341683, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.916943676173687, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.9132373693585396, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.8946820724010468, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.9004100278019905, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.9343529400229454, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.9668293231725693, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.0045324888825418, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.1035088112950324, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.2193438997864723, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.256261367201805, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.3539031255245209, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.171875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.020820931741036476, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.020816565696150063, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.020802349797450007, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.020783515167422592, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.020759567390196024, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.020709392786957322, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.02064012022688985, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.020624952889047563, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.02134948058053851, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.023666011989116668, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.026092328988015653, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.028568907612934707, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.030146622713655234, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.03253238486126065, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.03489678489044309, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.03648799025453627, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.03789387707598507, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.03883822049945593, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.03946608709171415, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.0400382961332798, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.04073622595518828, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.04137147484347224, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.04206986317411065, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.04285612933337688, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.04382539900019765, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.04480606907978654, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.04562486555427313, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.04615725077688694, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.04621121685951948, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.046397033650428056, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.04652469577267766, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.04662990693002939, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.04616650206968188, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.046255509555339816, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.046834546476602554, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.04731885487213731, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.047704476788640024, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.048384722899645564, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.04870148522779345, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.04974536675959826, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.04935525106266141, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.04960359634831548, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.049780426695942875, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1162378787994385, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1148681640625, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1125717163085938, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.110045909881592, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1072065830230713, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1020278930664062, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.092460870742798, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.069185495376587, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.974586248397827, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.8046605587005615, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.6828877925872803, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.5827932357788086, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.526834487915039, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.4693472385406494, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.4359207153320312, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.422001361846924, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.4128644466400146, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.4079437255859375, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.409078359603882, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.416564702987671, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.4366567134857178, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.4590933322906494, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.498054027557373, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.5294244289398193, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.5733859539031982, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.63889217376709, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.7235283851623535, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.809194326400757, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.85026478767395, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.961730480194092, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.088108777999878, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.193662166595459, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.3023033142089844, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.351257801055908, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.441589117050171, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.506784677505493, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.5257060527801514, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.525674343109131, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.491194248199463, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.376880407333374, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.2430520057678223, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.2288527488708496, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.157851219177246, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.07124400147655961, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.0725359911406423, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.07327427094868956, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.07419712070874862, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.07511997046880768, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.07659653008490218, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.08508674787744555, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.09745293466223699, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.1345514950166113, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.17423403469915097, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.1998892580287929, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.22129937246216316, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.24086378737541528, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.25507567368032485, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.26596530084902176, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.2713178294573643, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.2763012181616833, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.2763012181616833, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.2796234772978959, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.2779623477297896, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.2783314876338132, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.2781469176818014, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.2707641196013289, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.2678110003691399, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.2663344407530454, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.2563676633444075, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.24473975636766335, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.2397563676633444, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.24289405684754523, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.23569582871908454, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.22812846068660023, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.2207456626061277, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.21853082318198597, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.2188999630860096, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.2087486157253599, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.2024732373569583, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.20431893687707642, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.1997046880767811, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.2039497969730528, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.2201919527500923, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.21631598375784422, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.21650055370985605, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.21354743447766703, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.012543002986833448, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.013649496909318909, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.015078241655444394, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.01689103790575792, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.01814597292621865, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.019623705759441477, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.02840449300741502, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.041683027768490755, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.06302031779092133, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.09107938671954345, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.11825935747549599, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.14076125634701303, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.1600798518677228, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.17879607498589192, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.19520752291751006, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.20163010892826158, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.20657268220892355, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.21171850887228283, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.2200186671790166, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.22065746693168484, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.2211413853628871, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.22104257518846313, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.21732458175673197, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.21937058255597508, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.22192581075858273, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.2159723170879422, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.20486587710584328, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.20592237776888986, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.21042563196015251, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.20500743791692844, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.20230452004309538, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.19685266589553904, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.19341536789859315, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.19639526899075657, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.19219530469314292, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.18251783106520472, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.18443758916204578, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.18427738567660024, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.18173673288485234, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.19386701733467357, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.1899577422801529, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.19614675329909245, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.19162197317088794, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 18, "lr_best": 0.00011399999999999999, "wd_best": 0.05, "train/loss_best": 2.013560247421265, "validation/loss_best": 2.409078359603882, "validation/acc_best": 0.2796234772978959, "validation/f1_best": 0.2200186671790166} +{"epoch": 16, "train/lr": 3.870405029380728e-05, "train/loss": 2.0265408223867416, "train/grad": 0.2521612244099379, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.11984130859375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.117713623046875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.11418701171875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.11052734375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.10664794921875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.10012451171875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.0891510009765626, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.0647906494140624, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.9707992553710936, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.7994834899902346, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.6742288208007814, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.5664689636230467, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.4933003997802734, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.3979277420043945, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.3151165008544923, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.249969825744629, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.176512641906738, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.0994799518585205, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.019623346328735, "train/loss_019_lr4.4e-01_wd1.0e+00": 1.9463581085205077, "train/loss_020_lr5.2e-01_wd1.0e+00": 1.8619699716567992, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.7799557781219482, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.6922894287109376, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.6038904011249542, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.5123855412006377, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.408887917995453, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.316937468647957, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.2429732173681258, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.1609213095903397, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.0691215270757675, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.9911446264386177, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.9297205227613449, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.861830302476883, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.8411493393778801, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.8107930615544319, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.8008476513624191, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.832476752102375, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.8480450427532196, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.8821907639503479, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.9451459980010987, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.062732209265232, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.097880882024765, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.1837095138430596, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.171875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.020743917557410896, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.020739288832992316, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.02072447048034519, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.020705585782416165, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.020678795026615262, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.020630652089603244, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.020566065316088497, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.0205739117320627, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.021447077286429705, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.023895285669714213, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.026303137205541133, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.028750861333683132, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.03034280770458281, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.03277053069323301, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.035093651451170445, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.03662859590724111, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.037970426650717856, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.038848240692168474, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.03943070695735514, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.04000334549695253, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.04065708231180906, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.041264065336436034, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.04197266113013029, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.04276754891499877, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.04365056350827217, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.04456728581339121, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.04548669157549739, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.04577958915382624, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.046014752574265, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.04631780438125133, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.04607063565403223, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.04580719355493784, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.04504842052236199, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.04511037738993764, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.044824715480208395, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.04467052342370152, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.045444935224950314, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.04558823298662901, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.04620348190888762, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.04687576968222856, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.04706129088997841, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.047167088873684405, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.04738903947174549, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1161398887634277, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1147899627685547, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1124496459960938, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.109938144683838, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1070396900177, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1017298698425293, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.091744899749756, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.066836357116699, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.9662411212921143, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.795638084411621, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.6762824058532715, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.5788071155548096, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.5236032009124756, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.4664273262023926, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.433224678039551, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.4194493293762207, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.4104528427124023, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.406362533569336, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.409396171569824, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.419588327407837, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.4446892738342285, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.471303701400757, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.515194892883301, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.5541317462921143, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.6089987754821777, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.683410167694092, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.77189564704895, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.85978627204895, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.9019839763641357, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.0270538330078125, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.1526479721069336, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.2590036392211914, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.3822224140167236, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.4396986961364746, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.577293634414673, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.619687795639038, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.647077798843384, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.662886142730713, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.624312162399292, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.527904748916626, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.4155242443084717, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.4206106662750244, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.2586092948913574, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.07032115171650055, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.07179771133259505, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.0725359911406423, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.07345884090070137, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.07475083056478406, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.07622739018087855, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.08379475821336287, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.09837578442229605, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.13805832410483573, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.17478774455518642, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.1997046880767811, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.22572905131044665, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.24197120708748615, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.2561830933923957, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.26578073089701, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.2724252491694352, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.27408637873754155, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.27740863787375414, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.2809154669619786, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.2779623477297896, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.27611664820967147, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.27759320782576596, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.26651901070505724, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.26245847176079734, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.26301218161683276, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.25489110372831303, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.24178663713547435, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.23329641934293097, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.2364341085271318, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.23015873015873015, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.21982281284606867, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.21982281284606867, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.22277593207825766, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.21908453303802142, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.20302694721299372, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.20358065706902917, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.2070874861572536, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.2024732373569583, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.20450350682908822, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.21354743447766703, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.2102251753414544, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.20376522702104097, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.20893318567737174, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.012391335987216437, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.013467786429560527, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.014685897845337229, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.016267552284137395, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.018254191041668436, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.020037722624629484, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.026846183469003016, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.04118426750225968, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.06603277577731038, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.09079270675213841, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.11798005343879943, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.14351946157611822, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.1622914533737502, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.18069818332422707, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.19478665489847527, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.20398117548579578, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.20601078518970914, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.21388927417556478, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.22067311412879007, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.21933828660931362, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.2172003848648184, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.220144188424837, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.21369583568288433, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.21469335333089967, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.21920180337091233, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.21234492388189483, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.2008494410508388, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.1959948655734398, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.20329184037292158, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.19767929679560456, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.19295831194626353, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.19431171064013564, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.1922319878734673, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.19154289167868108, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.17756786762401733, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.1801525292052625, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.18244576256689396, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.17845638937409194, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.17935559246073093, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.18496713523118577, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.183079485308736, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.18099279727677786, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.18508133473687927, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 18, "lr_best": 0.00011399999999999999, "wd_best": 0.05, "train/loss_best": 2.019623346328735, "validation/loss_best": 2.409396171569824, "validation/acc_best": 0.2809154669619786, "validation/f1_best": 0.22067311412879007} +{"epoch": 17, "train/lr": 2.030750443206766e-05, "train/loss": 1.991125888824463, "train/grad": 0.2428506986051798, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.115692138671875, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.113681640625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.1102197265625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.106644287109375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.102696533203125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.096168212890625, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.08504150390625, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.059656982421875, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.961412048339844, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.7864794921875, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.6604623413085937, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.5522934722900392, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.478826599121094, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.382102470397949, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.298696823120117, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.2333566093444825, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.1596173286437987, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.0826976108551025, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.0037154245376585, "train/loss_019_lr4.4e-01_wd1.0e+00": 1.9316458129882812, "train/loss_020_lr5.2e-01_wd1.0e+00": 1.847608528137207, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.7644305849075317, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.674313371181488, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.5829944038391113, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.488185750246048, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.381899038553238, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.2865811067819595, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.2075858479738235, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.1196303206682205, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.0234666791558267, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.9339909705519677, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.8722765102982522, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.7977654936909676, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.772686296403408, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.7420596486330032, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.726119901239872, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.7376702019572258, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.7436238190531731, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.7655701038241386, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.819811858534813, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.9300224560499192, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.9607569795846939, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.0337642601132393, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.171875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.020548532023094594, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.02054240146651864, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.02052469105925411, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.02050437720026821, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.020477990824729203, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.020427230605855586, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.02036510189063847, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.02038512014783919, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.021310603735037147, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.023773986957967282, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.026180029986426233, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.028582387752830982, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.030166017087176443, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.03261445381678641, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.03490872144699097, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.0363945597410202, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.03769753518514335, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.03854351048357785, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.039129862021654846, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.03969393031671643, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.040309709515422586, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.04085862662643194, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.04151361269876361, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.04220403093844652, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.04304471999406814, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.04390786621719599, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.04460033971816301, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.044860906936228274, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.04481762023642659, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.04450037945061922, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.044041458368301395, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.04370373081415892, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.042831377163529395, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.042381055876612665, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.041916822567582133, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.04168059485033154, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.04154649861156941, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.04174640506505966, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.04211814919486642, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.042662194017320874, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.04353662855923176, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.043867407776415346, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.044315573573112485, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.116086483001709, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.11474347114563, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1123764514923096, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.109804391860962, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1068356037139893, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1013996601104736, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.091043472290039, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.065145254135132, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.9612457752227783, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.7903988361358643, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.672236680984497, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.5758583545684814, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.5208852291107178, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.463881492614746, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.430875062942505, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.4166009426116943, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.4065887928009033, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.4013023376464844, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.403261423110962, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.4121744632720947, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.4350714683532715, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.461332321166992, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.5039026737213135, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.5413854122161865, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.5948939323425293, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.6674506664276123, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.7540202140808105, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.838624954223633, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.8784568309783936, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.9955010414123535, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.127040386199951, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.249695301055908, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.3618218898773193, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.4130380153656006, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.55006742477417, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.622241258621216, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.6798481941223145, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.6909213066101074, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.649249315261841, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.5861690044403076, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.461179733276367, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.4825351238250732, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.367896556854248, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.07069029162052418, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.0710594315245478, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.0725359911406423, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.07475083056478406, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.07511997046880768, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.07788851974898486, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.08600959763750461, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.10077519379844961, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.13971945367294206, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.1758951642672573, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.20228866740494647, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.22572905131044665, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.24215577703949798, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.2574750830564784, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.2652270210409745, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.2727943890734588, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.27703949796973054, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.28017718715393136, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.28183831672203763, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.2807308970099668, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.2794389073458841, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.27851605758582504, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.26799557032115173, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.26098191214470284, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.2631967515688446, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.25452196382428943, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.24197120708748615, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.23588039867109634, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.24160206718346253, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.23477297895902546, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.22609819121447028, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.21853082318198597, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.2203765227021041, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.22056109265411591, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.20339608711701734, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.2039497969730528, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.19878183831672203, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.2011812476928756, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.20358065706902917, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.21686969361387967, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.21207087486157253, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.2115171650055371, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.21077888519748986, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.012873796517181317, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.01359896305692316, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.015289035575165241, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.017683933744841954, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.0186904144727363, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.020968015775145496, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.02921439958443131, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.04388079695785793, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.06661694823862636, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.09359511474529429, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.1205871808581041, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.1442647611827959, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.16278800548902567, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.18254411632005843, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.1953638657065815, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.20420663684119292, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.20862991481692292, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.2157516760061565, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.22197273127362416, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.22242762225000787, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.2217488939163641, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.2220264672447386, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.21649989714071102, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.21233677573067053, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.21923962463079097, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.21348490349685278, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.20096827902130074, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.19746925554265235, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.20820720670786286, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.20132071121094328, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.19990338883123723, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.19244189321211924, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.1928506039745427, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.19391775753069473, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.17941050614056933, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.17874395400835194, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.17432115229805825, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.17703511635406644, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.17791491226811326, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.18523360894139584, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.1839254606190551, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.18612916639830582, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.18248112129871683, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 18, "lr_best": 0.00011399999999999999, "wd_best": 0.05, "train/loss_best": 2.0037154245376585, "validation/loss_best": 2.403261423110962, "validation/acc_best": 0.28183831672203763, "validation/f1_best": 0.22197273127362416} +{"epoch": 18, "train/lr": 7.5829098008590064e-06, "train/loss": 1.974122217297554, "train/grad": 0.23859416618943213, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.11802978515625, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.115972900390625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.11244140625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.1087890625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.104910888671875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.098353271484375, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.08706787109375, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.06126953125, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.961236572265625, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.788468017578125, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.6646556091308593, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.5567186737060545, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.4820363616943357, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.3832075500488283, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.2980054092407225, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.2310912132263185, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.1561104583740236, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.0788641452789305, "train/loss_018_lr3.8e-01_wd1.0e+00": 1.9993307304382324, "train/loss_019_lr4.4e-01_wd1.0e+00": 1.9263663744926454, "train/loss_020_lr5.2e-01_wd1.0e+00": 1.8394538426399232, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.754891233444214, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.6666561567783356, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.5763243728876113, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.4792330980300903, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.3714168697595597, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.2732919216156007, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.1898477739095688, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.1049199253320694, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.0062212133407593, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.9165136358141899, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.849273187816143, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.7740966954827309, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.743932709991932, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.70886678352952, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.6873620228469371, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.6914628185331821, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.6927774587273597, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.7067767305672169, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.7430461655557156, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.8347207528352737, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.8481856095790863, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.9085436710715293, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.171875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.020666886800900102, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.020658644922077654, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.02064028025139123, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.02062004622537643, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.02059337115380913, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.020544085060246287, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.02048263975419104, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.020508902361616493, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.021462406162172556, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.023919034246355296, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.02630302691832185, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.028695542672649024, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.030268287174403666, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.032702394034713506, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.03499312029220164, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.036471990784630176, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.03777547053992748, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.03862476248294115, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.039188593830913304, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.03972524739801884, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.04032023498788476, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.040846955645829436, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.041471559461206196, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.042164820358157155, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.042972275987267494, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.043652643114328385, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0441465469263494, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0442769162915647, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.04421279339119792, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.043821662329137326, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.04321560854092241, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.042689753584563735, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.04159466626122594, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.04123478272929788, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.04057088827714324, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.04016129788011313, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.040071398038417104, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.03990174317732453, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.040056307073682546, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.040547004211694, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.04118078500032425, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.04103505428880453, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.04163977313786745, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1160659790039062, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1147072315216064, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1123123168945312, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.109722852706909, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.106750011444092, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1012659072875977, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.090806722640991, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.064537525177002, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.9594247341156006, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.788469076156616, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.670851230621338, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.5753531455993652, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.5207531452178955, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.4644784927368164, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.432389736175537, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.41898250579834, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.409912586212158, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.4056315422058105, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.4083213806152344, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.4181220531463623, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.4415996074676514, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.4675800800323486, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.5096333026885986, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.5463778972625732, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.597200870513916, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.667689561843872, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.7590110301971436, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.84846830368042, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.887984275817871, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.007129430770874, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.137322187423706, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.258808135986328, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.3855807781219482, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.450343132019043, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.5919229984283447, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.6549768447875977, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.7060132026672363, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.7162787914276123, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.6868515014648438, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.6207261085510254, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.482255697250366, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.5065908432006836, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.3895082473754883, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.07050572166851236, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.07069029162052418, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.07216685123661867, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.07419712070874862, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.07475083056478406, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.07715023994093761, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.08637873754152824, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.10077519379844961, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.1406423034330011, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.17571059431524547, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.20191952750092285, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.2249907715023994, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.2412329272794389, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.2556293835363603, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.2646733111849391, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.27297895902547065, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.27648578811369506, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.2781469176818014, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.28146917681801403, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.2783314876338132, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.2777777777777778, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.2783314876338132, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.26707272056109266, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.2622739018087855, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.2631967515688446, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.25378368401624213, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.24289405684754523, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.23920265780730898, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.2425249169435216, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.23624953857511996, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.22591362126245848, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.2159468438538206, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.2157622739018088, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.22277593207825766, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.20616463639719454, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.20321151716500555, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.20007382798080472, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.19582871908453303, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.20025839793281655, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.21391657438169065, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.21280915466961978, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.2129937246216316, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.20653377630121816, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.012665137095883601, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.013522959990051514, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.014772733271140634, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.017228567681222075, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.018262658673260483, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.020454798789122344, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.02971652380779224, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.04403510833543928, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.06720393121600793, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.09339640136574047, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.11972638293710687, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.1438087901682132, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.16152497371585975, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.18107168081996447, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.19417641720311518, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.2049308427245091, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.20823118943874022, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.21345276018196171, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.22138179038255792, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.21899908440434035, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.21887301276630433, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.22072431548137525, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.21424380724613531, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.21298530520203404, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.2204540241467344, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.21344010297462476, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.2025323010410199, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.20176790577107653, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.2098562436316007, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.20321361872097218, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.19927335614088407, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.19106233429654287, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.18930571949768524, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.1957241979269162, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.18168498629658694, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.17811674419987347, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.17837900089085168, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.1736716901127249, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.17361159658197559, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.18376578598511106, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.18467687491988072, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.1892794527728067, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.18314597827410115, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 18, "lr_best": 0.00011399999999999999, "wd_best": 0.05, "train/loss_best": 1.9993307304382324, "validation/loss_best": 2.4083213806152344, "validation/acc_best": 0.28146917681801403, "validation/f1_best": 0.22138179038255792} +{"epoch": 19, "train/lr": 1.0867618231465446e-06, "train/loss": 1.9731260490417482, "train/grad": 0.2346757236868143, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.1187841796875, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.1167041015625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.113408203125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.10978271484375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.105849609375, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.099228515625, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.087803955078125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.0617144775390623, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.961508483886719, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.7889747619628906, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.6655860900878907, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.5587667083740233, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.485412902832031, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.389884910583496, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.307153358459473, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.2413621711730958, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.1662253379821776, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.088071069717407, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.008381805419922, "train/loss_019_lr4.4e-01_wd1.0e+00": 1.9351686573028564, "train/loss_020_lr5.2e-01_wd1.0e+00": 1.8496906137466431, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.765473325252533, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.6744038248062134, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.5822194957733153, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.4874433493614196, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.3793081206083297, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.2808963298797607, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.1978805607557297, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.110400761961937, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.0080310127139092, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.921702162027359, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.8503730285167694, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.7730272349715233, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.740362032353878, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.6926690490543842, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.6660174044966698, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.6673796424269676, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.6773449742794037, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.6844908681511879, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.7160757257044316, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.811018368601799, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.822412206530571, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.8835359278321266, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.171875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.020271833045408128, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.020263560954481362, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.020246079969219864, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.02022525486536324, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.020198153429664672, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.020147210187278688, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.02008637262508273, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.020116966045461596, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.021075774212367834, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.023520410526543856, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.025871794503182173, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.028222296116873623, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.02980045247823, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.03225515379570425, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.03453801036812365, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.03600452500395477, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.03730188791640103, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.03815371798351407, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.03873740084469318, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.0393134540412575, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.039952554553747174, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.04051366541534662, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.041129118222743274, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.04174856010824442, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.04252154162153601, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.04325322106480598, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.04376429013907909, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0438927011564374, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.04373481506481767, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.043444601353257895, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.04281272729858756, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.04213418988510966, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.04112562466412783, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.04056715438142419, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.039762913901358846, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.039062408879399296, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.038857589717954395, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.03892433177679777, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.038889841567724945, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.039176139235496524, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.039922812823206186, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.039800790809094905, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.04023901043459773, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1160569190979004, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1146907806396484, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.112307548522949, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.109712839126587, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1067440509796143, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.101226568222046, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.0907561779022217, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.0644285678863525, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.9591264724731445, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.7881813049316406, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.670644998550415, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.5751428604125977, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.5206058025360107, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.4642231464385986, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.432037115097046, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.418482542037964, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.409154176712036, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.4047200679779053, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.4069631099700928, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.416836738586426, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.4404799938201904, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.4663949012756348, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.508694887161255, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.5457229614257812, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.5969622135162354, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.6683108806610107, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.7589192390441895, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.8465757369995117, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.88820743560791, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.0084588527679443, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.1375510692596436, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.2597711086273193, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.383638620376587, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.443429946899414, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.586909294128418, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.659351348876953, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.70233416557312, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.715036153793335, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.69400691986084, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.6249091625213623, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.4879581928253174, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.5179226398468018, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.407024383544922, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.07050572166851236, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.07087486157253599, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.07235142118863049, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.07401255075673681, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.07585825027685493, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.07733480989294943, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.08656330749354005, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.10040605389442599, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.14101144333702473, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.17681801402731634, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.20228866740494647, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.22591362126245848, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.24160206718346253, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.2547065337763012, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.26448874123292726, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.2737172388335179, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.2763012181616833, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.27722406792174237, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.28183831672203763, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.27870062753783686, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.27888519748984864, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.2781469176818014, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.26799557032115173, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.26264304171280917, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.26264304171280917, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.25599852344038393, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.24326319675156885, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.23864894795127353, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.24344776670358065, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.23717238833517904, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.22665190107050573, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.2174234034699151, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.21834625322997417, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.22240679217423404, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.2056109265411591, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.20228866740494647, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.20081210778885197, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.19712070874861573, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.20191952750092285, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.2131782945736434, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.21244001476559615, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.21354743447766703, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.20893318567737174, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.012657554748715197, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.013587175715035834, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.014797473363718908, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.01700807287579524, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.01901081582911843, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.020558450740999837, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.029608123780874948, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.04384605683421771, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.06756401630689264, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.09531587390640016, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.12022220781875063, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.14416062940900687, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.1618092167600396, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.1805454869548254, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.19400545951155965, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.20589025823590804, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.207792066385733, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.21287114714597236, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.2221281844274662, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.21923029693143423, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.21978474779473736, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.22062520447686942, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.2157601264293398, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.2136608824219386, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.21936996358382976, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.21510748164140128, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.20295811964312838, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.20144176247442444, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.21087225514894328, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.20433186035868456, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.19917192316056068, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.19155767844585989, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.19208357010785146, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.1969623254080101, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.18164213581873132, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.1770967680458324, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.17744188823122298, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.17443375152323415, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.17400320361187163, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.18317381608676364, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.1841733150177983, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.189716914380205, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.1845684928985991, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 18, "lr_best": 0.00011399999999999999, "wd_best": 0.05, "train/loss_best": 2.008381805419922, "validation/loss_best": 2.4069631099700928, "validation/acc_best": 0.28183831672203763, "validation/f1_best": 0.2221281844274662} diff --git a/input_space_v3/flat_lr1e-3_5/eval_v2/ppmi_dx__patch__logistic/config.yaml b/input_space_v3/flat_lr1e-3_5/eval_v2/ppmi_dx__patch__logistic/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..f03b2eaa758dcf8263a63fed9676ec0978410c51 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_5/eval_v2/ppmi_dx__patch__logistic/config.yaml @@ -0,0 +1,30 @@ +output_root: experiments/input_space_v3/output +name_prefix: eval_logistic +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_5; eval v2 (ppmi_dx patch logistic) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: input_space_v3/flat_lr1e-3_5/eval_v2/ppmi_dx__patch__logistic +model: flat_mae +representation: patch +dataset: ppmi_dx +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/eval_v2/ppmi_dx__patch__logistic +remote_dir: null diff --git a/input_space_v3/flat_lr1e-3_5/eval_v2/ppmi_dx__patch__logistic/eval_table.csv b/input_space_v3/flat_lr1e-3_5/eval_v2/ppmi_dx__patch__logistic/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..ff61ca92dba967503e5b9aa9ceba2a866b307d0d --- /dev/null +++ b/input_space_v3/flat_lr1e-3_5/eval_v2/ppmi_dx__patch__logistic/eval_table.csv @@ -0,0 +1,203 @@ +model,repr,clf,dataset,trial,C,split,acc,acc_std,f1,f1_std,bacc,bacc_std +flat_mae,patch,logistic,ppmi_dx,,0.046415888336127774,train,0.8078291814946619,0.01562622064988,0.7858624631320472,0.01830896052264764,0.7750884926200494,0.0179961687672111 +flat_mae,patch,logistic,ppmi_dx,,0.046415888336127774,test,0.64,0.04385824437890783,0.5863970588235294,0.052176487642161824,0.586014586014586,0.04814876910198504 +flat_mae,patch,logistic,ppmi_dx,1,0.005994842503189409,train,0.7170818505338078,0.016885785746046728,0.669625658563638,0.021361052698671043,0.6649941126097195,0.019157048801848358 +flat_mae,patch,logistic,ppmi_dx,1,0.005994842503189409,test,0.72,0.034719786865705274,0.6448503297818367,0.05351509447065291,0.6468590831918506,0.04235552286254733 +flat_mae,patch,logistic,ppmi_dx,2,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,2,1291.5496650148827,test,0.66,0.044803017755503924,0.6392190152801358,0.04728595480378686,0.6392190152801358,0.047429114745199515 +flat_mae,patch,logistic,ppmi_dx,3,0.046415888336127774,train,0.806049822064057,0.015342807108477864,0.7836041019771587,0.01810258460907286,0.7729073003639477,0.017925548507109586 +flat_mae,patch,logistic,ppmi_dx,3,0.046415888336127774,test,0.63,0.047458862186108085,0.6009060511271707,0.051157931337640794,0.5997453310696095,0.049983730962565025 +flat_mae,patch,logistic,ppmi_dx,4,0.005994842503189409,train,0.7402135231316725,0.017395192525230363,0.695187006850231,0.02220165835479158,0.6881288803254121,0.019938136573792422 +flat_mae,patch,logistic,ppmi_dx,4,0.005994842503189409,test,0.65,0.041896462857859494,0.6072270227808326,0.048184640076157685,0.6056876061120543,0.04514075637065264 +flat_mae,patch,logistic,ppmi_dx,5,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,5,21.54434690031882,test,0.58,0.04593133570886002,0.5543293718166383,0.04728693957483686,0.5543293718166383,0.046933673586288645 +flat_mae,patch,logistic,ppmi_dx,6,0.005994842503189409,train,0.7348754448398577,0.01573737546455345,0.6913715387195336,0.020241272576428902,0.6846633483194177,0.01835028649770613 +flat_mae,patch,logistic,ppmi_dx,6,0.005994842503189409,test,0.64,0.04118727473383011,0.5714285714285714,0.05333048867527479,0.5772495755517827,0.04577921051082555 +flat_mae,patch,logistic,ppmi_dx,7,0.046415888336127774,train,0.8202846975088968,0.015631048644976418,0.8037784115461066,0.017500832247233183,0.7957744594305287,0.01753146964292081 +flat_mae,patch,logistic,ppmi_dx,7,0.046415888336127774,test,0.55,0.049480598217887375,0.52,0.05153865847417581,0.5199490662139219,0.05100687596780509 +flat_mae,patch,logistic,ppmi_dx,8,0.046415888336127774,train,0.7953736654804271,0.016514532327367517,0.7734021927010473,0.01898207644939178,0.7642367801327339,0.018635700707122248 +flat_mae,patch,logistic,ppmi_dx,8,0.046415888336127774,test,0.6,0.042596168841810174,0.5404411764705883,0.04873137694448012,0.5449915110356536,0.044320814043012184 +flat_mae,patch,logistic,ppmi_dx,9,0.3593813663804626,train,0.9074733096085409,0.01126617045292266,0.900776836158192,0.012239010937967088,0.8952847356026546,0.012825258046379238 +flat_mae,patch,logistic,ppmi_dx,9,0.3593813663804626,test,0.64,0.04461302052091967,0.6138996138996139,0.0482742456728774,0.6129032258064516,0.047734393807892725 +flat_mae,patch,logistic,ppmi_dx,10,0.046415888336127774,train,0.8202846975088968,0.01584564920493803,0.8009880127200502,0.018215707451066532,0.7905560907728538,0.01804937036257479 +flat_mae,patch,logistic,ppmi_dx,10,0.046415888336127774,test,0.67,0.041411471840541954,0.6239316239316239,0.04977766476095066,0.6218166383701189,0.04579143043996181 +flat_mae,patch,logistic,ppmi_dx,11,0.046415888336127774,train,0.800711743772242,0.016464796543190184,0.78064012490242,0.01884892082823763,0.7720509526867909,0.01872214919241188 +flat_mae,patch,logistic,ppmi_dx,11,0.046415888336127774,test,0.68,0.0442348098221299,0.6527777777777778,0.048669910541670997,0.6502546689303905,0.04754725007846055 +flat_mae,patch,logistic,ppmi_dx,12,0.046415888336127774,train,0.8220640569395018,0.015162123740667095,0.8041429686628749,0.017387989195226508,0.7946103618068936,0.01746612216532775 +flat_mae,patch,logistic,ppmi_dx,12,0.046415888336127774,test,0.57,0.04142976707634258,0.49286472461375164,0.04865685494696078,0.5055178268251274,0.042941973549405564 +flat_mae,patch,logistic,ppmi_dx,13,2.782559402207126,train,0.9928825622775801,0.0033553567191932795,0.9924669928288989,0.0035589634786624713,0.9916104688503533,0.004037674067202389 +flat_mae,patch,logistic,ppmi_dx,13,2.782559402207126,test,0.61,0.045786718598300975,0.5793334052421529,0.04989904629279219,0.5785229202037352,0.04906496167352984 +flat_mae,patch,logistic,ppmi_dx,14,0.005994842503189409,train,0.7437722419928826,0.01583340970885048,0.704002808988764,0.01967274361133503,0.6962374223934917,0.018052743851346517 +flat_mae,patch,logistic,ppmi_dx,14,0.005994842503189409,test,0.6,0.04223209679852517,0.5324918186068257,0.04978312395067441,0.5398981324278438,0.0443802229456521 +flat_mae,patch,logistic,ppmi_dx,15,0.005994842503189409,train,0.7295373665480427,0.01529297063768646,0.683671051072402,0.019548809619789338,0.6777189038749732,0.01759609017724949 +flat_mae,patch,logistic,ppmi_dx,15,0.005994842503189409,test,0.68,0.04317654919050386,0.6323529411764706,0.051525254314443464,0.6298811544991512,0.047305126121923134 +flat_mae,patch,logistic,ppmi_dx,16,10000.0,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,16,10000.0,test,0.62,0.04796386556565266,0.5967741935483871,0.05010868673825183,0.5967741935483871,0.05029864325398614 +flat_mae,patch,logistic,ppmi_dx,17,0.046415888336127774,train,0.800711743772242,0.015315551821007654,0.7773627617430674,0.01804329845474387,0.7668325840291158,0.01770055119157162 +flat_mae,patch,logistic,ppmi_dx,17,0.046415888336127774,test,0.64,0.04597434066955176,0.6043956043956044,0.050946786021574965,0.6027164685908319,0.04902879207541099 +flat_mae,patch,logistic,ppmi_dx,18,0.046415888336127774,train,0.8167259786476868,0.015048626660671895,0.7970471812887641,0.017407726181279764,0.7867961892528367,0.017295687522279127 +flat_mae,patch,logistic,ppmi_dx,18,0.046415888336127774,test,0.57,0.045335478380623705,0.5305164319248826,0.0486468334526727,0.5309847198641766,0.04700173759445523 +flat_mae,patch,logistic,ppmi_dx,19,0.3593813663804626,train,0.9181494661921709,0.010849776867953125,0.9116895538703287,0.011959078673430873,0.9039552558338686,0.012809073961884887 +flat_mae,patch,logistic,ppmi_dx,19,0.3593813663804626,test,0.66,0.04710503582420886,0.6458333333333333,0.04864894080161696,0.6494057724957556,0.04938652659142659 +flat_mae,patch,logistic,ppmi_dx,20,0.046415888336127774,train,0.797153024911032,0.01596693052941052,0.774535472972973,0.018567677103430234,0.7648121387283238,0.018255814288852253 +flat_mae,patch,logistic,ppmi_dx,20,0.046415888336127774,test,0.65,0.04082638362627775,0.5944849959448499,0.04963030888115686,0.5955008488964346,0.044646064218265134 +flat_mae,patch,logistic,ppmi_dx,21,0.046415888336127774,train,0.791814946619217,0.01621522741535593,0.7652674003919706,0.019305617288541348,0.7543887818454292,0.018615834218012606 +flat_mae,patch,logistic,ppmi_dx,21,0.046415888336127774,test,0.69,0.04131819937993425,0.6408295678368672,0.051842155906366184,0.6379456706281834,0.04661605292557239 +flat_mae,patch,logistic,ppmi_dx,22,0.046415888336127774,train,0.8202846975088968,0.015156899056611058,0.7999950670007012,0.017715221498624627,0.7888166345536287,0.01760721308986293 +flat_mae,patch,logistic,ppmi_dx,22,0.046415888336127774,test,0.62,0.04433402305227893,0.5634191176470589,0.05164375941486428,0.566213921901528,0.04714080591889674 +flat_mae,patch,logistic,ppmi_dx,23,0.3593813663804626,train,0.9092526690391459,0.011922226047072906,0.9025880673611228,0.012992511982843786,0.896729822307857,0.013657600869104843 +flat_mae,patch,logistic,ppmi_dx,23,0.3593813663804626,test,0.57,0.048091491971033705,0.5413333333333333,0.05161201650917838,0.5411714770797962,0.051031395569356125 +flat_mae,patch,logistic,ppmi_dx,24,0.005994842503189409,train,0.7384341637010676,0.016286042860585815,0.6964539632499642,0.02048065313763315,0.6892929779490473,0.01871120108569682 +flat_mae,patch,logistic,ppmi_dx,24,0.005994842503189409,test,0.65,0.04416362303978241,0.5872154735228211,0.05429119887745847,0.5904074702886248,0.04778781917005062 +flat_mae,patch,logistic,ppmi_dx,25,0.046415888336127774,train,0.7900355871886121,0.016379922788086827,0.764826872065478,0.019148376605894357,0.754683151359452,0.01855218951371829 +flat_mae,patch,logistic,ppmi_dx,25,0.046415888336127774,test,0.65,0.03894272204148036,0.5872154735228211,0.04981719462708731,0.5904074702886248,0.043384030531979666 +flat_mae,patch,logistic,ppmi_dx,26,0.005994842503189409,train,0.7455516014234875,0.015630549545756274,0.7056136559277643,0.019864344221631525,0.6976825090986941,0.018223132183725513 +flat_mae,patch,logistic,ppmi_dx,26,0.005994842503189409,test,0.65,0.045227297067147405,0.6011396011396011,0.05185317984155702,0.6005942275042444,0.04788330419638174 +flat_mae,patch,logistic,ppmi_dx,27,0.3593813663804626,train,0.9145907473309609,0.011315729381574945,0.9076569175156095,0.0125732382188901,0.899325626204239,0.01357594644141265 +flat_mae,patch,logistic,ppmi_dx,27,0.3593813663804626,test,0.57,0.04647171612927588,0.5501621508525996,0.04827555992788557,0.551358234295416,0.04898095808197892 +flat_mae,patch,logistic,ppmi_dx,28,2.782559402207126,train,0.998220640569395,0.0017829145978470273,0.9981184064710746,0.0018886459897671326,0.9976851851851851,0.0023194398240509928 +flat_mae,patch,logistic,ppmi_dx,28,2.782559402207126,test,0.6,0.04797792825873164,0.5796553173602353,0.049275592435860056,0.5806451612903225,0.049335124839865505 +flat_mae,patch,logistic,ppmi_dx,29,0.3593813663804626,train,0.9110320284697508,0.012209551071665731,0.9047806226872874,0.01324628140320285,0.8999143652322843,0.013920242571700043 +flat_mae,patch,logistic,ppmi_dx,29,0.3593813663804626,test,0.62,0.04689338972605841,0.6006725514922235,0.04848545877356072,0.6018675721561969,0.04890309933681076 +flat_mae,patch,logistic,ppmi_dx,30,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,30,166.81005372000556,test,0.63,0.047968973305669155,0.6093337556752191,0.050200531258142174,0.6099320882852293,0.050521470315288974 +flat_mae,patch,logistic,ppmi_dx,31,0.005994842503189409,train,0.7473309608540926,0.016532744238980077,0.7081138810861423,0.02079491093049992,0.6999973239135089,0.01915228763388185 +flat_mae,patch,logistic,ppmi_dx,31,0.005994842503189409,test,0.6,0.04857734451367222,0.5604395604395604,0.05241267879434175,0.5602716468590832,0.05042830740435462 +flat_mae,patch,logistic,ppmi_dx,32,2.782559402207126,train,0.994661921708185,0.002847917993323507,0.9943552194132241,0.003014794630427517,0.993925283665168,0.0033260905534293044 +flat_mae,patch,logistic,ppmi_dx,32,2.782559402207126,test,0.64,0.05063309589586637,0.6179966044142615,0.05294438398050823,0.6179966044142615,0.052791938164719346 +flat_mae,patch,logistic,ppmi_dx,33,0.3593813663804626,train,0.9128113879003559,0.012033312003079319,0.9065935370515469,0.01307134175595203,0.9013594519374866,0.013684171987360393 +flat_mae,patch,logistic,ppmi_dx,33,0.3593813663804626,test,0.58,0.04731231974866588,0.5495495495495495,0.04986850787640493,0.5492359932088284,0.04894780522681723 +flat_mae,patch,logistic,ppmi_dx,34,0.046415888336127774,train,0.8131672597864769,0.01594102522596166,0.793106349857478,0.018272241683167656,0.7830362877328195,0.018074119721662722 +flat_mae,patch,logistic,ppmi_dx,34,0.046415888336127774,test,0.67,0.04528351134795092,0.6296711929076422,0.0528274568735957,0.6269100169779287,0.049796521716383255 +flat_mae,patch,logistic,ppmi_dx,35,0.005994842503189409,train,0.7473309608540926,0.015016004008668336,0.7035380477584439,0.01937107643554489,0.6956486833654464,0.017464871232800563 +flat_mae,patch,logistic,ppmi_dx,35,0.005994842503189409,test,0.62,0.04643176068167134,0.5876736111111112,0.04989967109038557,0.5865874363327674,0.048742323952458935 +flat_mae,patch,logistic,ppmi_dx,36,0.046415888336127774,train,0.8042704626334519,0.01655657530754973,0.7855616605616605,0.018663746849859403,0.7775503104260331,0.01861122977440523 +flat_mae,patch,logistic,ppmi_dx,36,0.046415888336127774,test,0.66,0.04334517735573359,0.609375,0.05217523901672738,0.6086587436332768,0.047714063582913434 +flat_mae,patch,logistic,ppmi_dx,37,0.046415888336127774,train,0.798932384341637,0.015283858556222357,0.7744967491539989,0.018029861266914665,0.7636480411046885,0.017500585877740463 +flat_mae,patch,logistic,ppmi_dx,37,0.046415888336127774,test,0.63,0.04672729395118018,0.6053333333333333,0.0500051360176617,0.6048387096774194,0.04982858438409728 +flat_mae,patch,logistic,ppmi_dx,38,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,38,21.54434690031882,test,0.57,0.050692705589660526,0.5538956323270048,0.05169921519042101,0.5564516129032258,0.0528071253381006 +flat_mae,patch,logistic,ppmi_dx,39,0.3593813663804626,train,0.9217081850533808,0.01135719336418266,0.9153521743893088,0.012613896139427415,0.9068454292442731,0.013705185806000388 +flat_mae,patch,logistic,ppmi_dx,39,0.3593813663804626,test,0.72,0.04546251202914331,0.7028862478777589,0.04792152492653265,0.7028862478777589,0.048137394455146844 +flat_mae,patch,logistic,ppmi_dx,40,0.3593813663804626,train,0.9217081850533808,0.011625307815982321,0.916041938287701,0.012676889702538224,0.9103243416827231,0.013529473110106268 +flat_mae,patch,logistic,ppmi_dx,40,0.3593813663804626,test,0.67,0.0464950535003456,0.6515679442508711,0.04916463058772718,0.652376910016978,0.04964336138445553 +flat_mae,patch,logistic,ppmi_dx,41,0.005994842503189409,train,0.7402135231316725,0.015864693645058655,0.6971133259505353,0.02031095441904164,0.6898683365446372,0.018463413946474307 +flat_mae,patch,logistic,ppmi_dx,41,0.005994842503189409,test,0.67,0.04329942262894506,0.6349153667441089,0.048783767757865006,0.6320033955857385,0.04648370719701013 +flat_mae,patch,logistic,ppmi_dx,42,0.3593813663804626,train,0.9145907473309609,0.011107853301129353,0.9080397076469946,0.012177978300177951,0.9010650824234638,0.01293331996410568 +flat_mae,patch,logistic,ppmi_dx,42,0.3593813663804626,test,0.67,0.04027902680055713,0.6176572818908586,0.04920311590087093,0.616723259762309,0.044278828495158816 +flat_mae,patch,logistic,ppmi_dx,43,0.005994842503189409,train,0.7188612099644128,0.016781627724696744,0.6701338841255925,0.02148973821811441,0.6655694712053094,0.019185211993736503 +flat_mae,patch,logistic,ppmi_dx,43,0.005994842503189409,test,0.69,0.03685263084231571,0.6196785670469881,0.05088326083280931,0.6226655348047538,0.04233314281455529 +flat_mae,patch,logistic,ppmi_dx,44,2.782559402207126,train,0.998220640569395,0.0017734099825687509,0.9981184064710746,0.0018791307132620852,0.9976851851851851,0.0023070750236195313 +flat_mae,patch,logistic,ppmi_dx,44,2.782559402207126,test,0.56,0.050408138231837124,0.5452666391070691,0.05101776941279667,0.5483870967741935,0.05186183170782402 +flat_mae,patch,logistic,ppmi_dx,45,2.782559402207126,train,0.99644128113879,0.0026028227441586625,0.9962334964144495,0.0027622565129254524,0.9953703703703703,0.003386079588465663 +flat_mae,patch,logistic,ppmi_dx,45,2.782559402207126,test,0.57,0.050226252099873026,0.5601023017902813,0.05036476531007583,0.5666383701188455,0.05185512216540719 +flat_mae,patch,logistic,ppmi_dx,46,0.046415888336127774,train,0.8256227758007118,0.015182538633681453,0.8085112300952646,0.01707361563656171,0.7992399914365232,0.01696066143769383 +flat_mae,patch,logistic,ppmi_dx,46,0.046415888336127774,test,0.58,0.04609164783341988,0.5320855614973261,0.0516305244543477,0.533955857385399,0.048521138943948446 +flat_mae,patch,logistic,ppmi_dx,47,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,47,21.54434690031882,test,0.59,0.04718348863744605,0.5777983729790959,0.048192466026256875,0.58276740237691,0.049618034975389684 +flat_mae,patch,logistic,ppmi_dx,48,2.782559402207126,train,0.99644128113879,0.002660570193756366,0.9962334964144495,0.002823780361481074,0.9953703703703703,0.0034612047428034167 +flat_mae,patch,logistic,ppmi_dx,48,2.782559402207126,test,0.69,0.04396494512677116,0.6615351020853806,0.049070413947449425,0.6583191850594228,0.047949487045824794 +flat_mae,patch,logistic,ppmi_dx,49,0.005994842503189409,train,0.7206405693950177,0.016579387525730082,0.6684365781710915,0.021640262789626108,0.6644053735816742,0.01896859685815167 +flat_mae,patch,logistic,ppmi_dx,49,0.005994842503189409,test,0.69,0.03557155605255411,0.6196785670469881,0.05043589448028314,0.6226655348047538,0.04131229201013078 +flat_mae,patch,logistic,ppmi_dx,50,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,50,1291.5496650148827,test,0.55,0.04854480816730044,0.5021573182874212,0.05199044012765227,0.5046689303904923,0.04968783207010084 +flat_mae,patch,logistic,ppmi_dx,51,2.782559402207126,train,0.994661921708185,0.003018018104184834,0.994365029762402,0.0031836219184398873,0.9947950117747806,0.003072334976237416 +flat_mae,patch,logistic,ppmi_dx,51,2.782559402207126,test,0.61,0.047457007912425325,0.5983935742971888,0.04858350984175536,0.6039898132427843,0.04973643044167271 +flat_mae,patch,logistic,ppmi_dx,52,2.782559402207126,train,0.998220640569395,0.0018598553891677049,0.9981184064710746,0.0019703661876776923,0.9976851851851851,0.00241953409424132 +flat_mae,patch,logistic,ppmi_dx,52,2.782559402207126,test,0.61,0.050107707989889144,0.5920075321686369,0.051567866614193235,0.5938030560271647,0.052069659053562506 +flat_mae,patch,logistic,ppmi_dx,53,0.046415888336127774,train,0.8078291814946619,0.015406635185711249,0.788474406155905,0.017579321469997435,0.7795707557268251,0.01751480726737899 +flat_mae,patch,logistic,ppmi_dx,53,0.046415888336127774,test,0.66,0.04427380263767728,0.6263736263736264,0.04961920077019107,0.6239388794567062,0.047936146230507744 +flat_mae,patch,logistic,ppmi_dx,54,0.046415888336127774,train,0.8113879003558719,0.015923626230124634,0.7918954796338993,0.01824639034973197,0.7824609291372298,0.018116442669084992 +flat_mae,patch,logistic,ppmi_dx,54,0.046415888336127774,test,0.55,0.047603209975798894,0.5146154675870995,0.04876940939841477,0.514855687606112,0.04800616320136609 +flat_mae,patch,logistic,ppmi_dx,55,2.782559402207126,train,0.99644128113879,0.002438309407989171,0.9962334964144495,0.0025874610774967036,0.9953703703703703,0.0031720599242822047 +flat_mae,patch,logistic,ppmi_dx,55,2.782559402207126,test,0.68,0.046577230488727,0.6637242538881883,0.04896999442530735,0.6655348047538201,0.04953297038081854 +flat_mae,patch,logistic,ppmi_dx,56,0.005994842503189409,train,0.7295373665480427,0.01591582097244705,0.683671051072402,0.020316860800010564,0.6777189038749732,0.018291121296236248 +flat_mae,patch,logistic,ppmi_dx,56,0.005994842503189409,test,0.64,0.04029453560968286,0.5628946090335114,0.051904947765090165,0.5721561969439728,0.043691134735568134 +flat_mae,patch,logistic,ppmi_dx,57,2.782559402207126,train,0.99644128113879,0.0025050423434318857,0.9962334964144495,0.0026580743346949517,0.9953703703703703,0.0032588745301127737 +flat_mae,patch,logistic,ppmi_dx,57,2.782559402207126,test,0.56,0.04593638644908847,0.5225694444444444,0.049408255528955156,0.5229202037351443,0.04800851117218283 +flat_mae,patch,logistic,ppmi_dx,58,0.005994842503189409,train,0.7366548042704626,0.016071790206609936,0.6910114863961246,0.021026035342100464,0.6843689788053949,0.018797250063796667 +flat_mae,patch,logistic,ppmi_dx,58,0.005994842503189409,test,0.68,0.03999467964617293,0.6190476190476191,0.051850743347748106,0.6196943972835314,0.04503093720530703 +flat_mae,patch,logistic,ppmi_dx,59,0.3593813663804626,train,0.9074733096085409,0.012347748838622158,0.9009718475947789,0.0133594138475024,0.8961544637122671,0.013925053085849041 +flat_mae,patch,logistic,ppmi_dx,59,0.3593813663804626,test,0.6,0.04802006247392854,0.554367201426025,0.05335591702391213,0.5551782682512734,0.05041725363546822 +flat_mae,patch,logistic,ppmi_dx,60,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,60,21.54434690031882,test,0.62,0.04970673998563977,0.6124031007751938,0.0499255277938015,0.6222410865874364,0.051307436046064775 +flat_mae,patch,logistic,ppmi_dx,61,0.3593813663804626,train,0.9074733096085409,0.012075933959770866,0.9009718475947789,0.01301942463946331,0.8961544637122671,0.013491998116965777 +flat_mae,patch,logistic,ppmi_dx,61,0.3593813663804626,test,0.61,0.04679970512727618,0.584,0.04929258656518385,0.583616298811545,0.0489213464279063 +flat_mae,patch,logistic,ppmi_dx,62,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,62,166.81005372000556,test,0.64,0.04803706901966439,0.6216897856242118,0.049869420280316955,0.6230899830220713,0.05023357863446226 +flat_mae,patch,logistic,ppmi_dx,63,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,63,1291.5496650148827,test,0.54,0.048965861577225406,0.5166036149642708,0.05103065725092895,0.5169779286926994,0.05148901024529485 +flat_mae,patch,logistic,ppmi_dx,64,0.005994842503189409,train,0.7366548042704626,0.015608299131734104,0.6889965749839219,0.0206139607356201,0.68262952258617,0.018326918820363528 +flat_mae,patch,logistic,ppmi_dx,64,0.005994842503189409,test,0.64,0.04228839557136213,0.5792426367461431,0.050427213746009523,0.5823429541595926,0.04523567959492689 +flat_mae,patch,logistic,ppmi_dx,65,0.3593813663804626,train,0.9217081850533808,0.011111991229465799,0.916041938287701,0.012101456412226954,0.9103243416827231,0.01290769995042923 +flat_mae,patch,logistic,ppmi_dx,65,0.3593813663804626,test,0.53,0.05084818187506806,0.49304282170208175,0.05234521458180613,0.4936332767402377,0.05152919673739481 +flat_mae,patch,logistic,ppmi_dx,66,0.005994842503189409,train,0.7295373665480427,0.016447323303181088,0.6856453132359868,0.020533891155288423,0.6794583600941982,0.01860445313376608 +flat_mae,patch,logistic,ppmi_dx,66,0.005994842503189409,test,0.63,0.042930506635724675,0.5713127099988413,0.050827440024669476,0.5742784380305602,0.0457253162118849 +flat_mae,patch,logistic,ppmi_dx,67,0.046415888336127774,train,0.798932384341637,0.01559521844226386,0.7744967491539989,0.018586296699048575,0.7636480411046885,0.01820672287124072 +flat_mae,patch,logistic,ppmi_dx,67,0.046415888336127774,test,0.61,0.047220550610936336,0.5793334052421529,0.05106944702854767,0.5785229202037352,0.050452293899769934 +flat_mae,patch,logistic,ppmi_dx,68,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,68,1291.5496650148827,test,0.58,0.04485159528935398,0.5495495495495495,0.047398874778283896,0.5492359932088284,0.04685897477288705 +flat_mae,patch,logistic,ppmi_dx,69,0.005994842503189409,train,0.708185053380783,0.0163871870509868,0.6597711332595053,0.020403763630733585,0.6560292228644831,0.01831214049661309 +flat_mae,patch,logistic,ppmi_dx,69,0.005994842503189409,test,0.71,0.041246653197562586,0.6640018537828757,0.050511176433841155,0.6591680814940577,0.04632776831784595 +flat_mae,patch,logistic,ppmi_dx,70,0.3593813663804626,train,0.9128113879003559,0.01093898254601899,0.9060274430714946,0.012010546888662868,0.8987502676086491,0.012754009893519892 +flat_mae,patch,logistic,ppmi_dx,70,0.3593813663804626,test,0.56,0.04797906210004526,0.5280995280995281,0.05007985997718756,0.5280135823429541,0.049350640596634056 +flat_mae,patch,logistic,ppmi_dx,71,0.005994842503189409,train,0.7348754448398577,0.016177021187108735,0.6894209977783465,0.020961346691385867,0.6829238921001927,0.01880924782227376 +flat_mae,patch,logistic,ppmi_dx,71,0.005994842503189409,test,0.65,0.041182185468962185,0.5792763553311696,0.05197680341106155,0.5853140916808149,0.04460873933775471 +flat_mae,patch,logistic,ppmi_dx,72,0.005994842503189409,train,0.7366548042704626,0.01587621184849441,0.6869175060601954,0.020964248261299178,0.6808900663669449,0.018445625529984945 +flat_mae,patch,logistic,ppmi_dx,72,0.005994842503189409,test,0.64,0.04260269944498822,0.5863970588235294,0.05095613702593209,0.5874363327674024,0.04612419841130511 +flat_mae,patch,logistic,ppmi_dx,73,0.046415888336127774,train,0.800711743772242,0.015570310090038203,0.779041520985158,0.01787032516912426,0.7694417683579533,0.017553063785616194 +flat_mae,patch,logistic,ppmi_dx,73,0.046415888336127774,test,0.65,0.04671503398264846,0.6338529134846741,0.04802575814643857,0.6362478777589134,0.048526827880828294 +flat_mae,patch,logistic,ppmi_dx,74,0.005994842503189409,train,0.7348754448398577,0.017551553439884994,0.6941848447331997,0.021702225117467423,0.6872725326482552,0.01999415848867939 +flat_mae,patch,logistic,ppmi_dx,74,0.005994842503189409,test,0.58,0.04429271271891122,0.5174632352941176,0.051077487757178026,0.5237691001697793,0.046536848011569154 +flat_mae,patch,logistic,ppmi_dx,75,0.046415888336127774,train,0.8113879003558719,0.015616528959663695,0.7887427833808531,0.01844469168765132,0.7772425604795548,0.01815633254191997 +flat_mae,patch,logistic,ppmi_dx,75,0.046415888336127774,test,0.6,0.04603209315249525,0.554367201426025,0.050904754357527685,0.5551782682512734,0.04819827411550661 +flat_mae,patch,logistic,ppmi_dx,76,0.3593813663804626,train,0.9234875444839857,0.010613850814172382,0.9177027887605017,0.011643691325538323,0.910899700278313,0.012558448195862134 +flat_mae,patch,logistic,ppmi_dx,76,0.3593813663804626,test,0.59,0.04798947801341456,0.5523528769516323,0.05205722467112479,0.5522071307300509,0.05025096647990061 +flat_mae,patch,logistic,ppmi_dx,77,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,77,1291.5496650148827,test,0.58,0.044708388474647566,0.5442708333333334,0.04912022675526458,0.5441426146010186,0.04771257429131255 +flat_mae,patch,logistic,ppmi_dx,78,10000.0,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,78,10000.0,test,0.6,0.04911612362554684,0.5796553173602353,0.05126725261465157,0.5806451612903225,0.05184237996181347 +flat_mae,patch,logistic,ppmi_dx,79,0.005994842503189409,train,0.7224199288256228,0.015743172139174665,0.6688723712835387,0.020837637166036184,0.664980732177264,0.018156477571765695 +flat_mae,patch,logistic,ppmi_dx,79,0.005994842503189409,test,0.7,0.03955308331849743,0.6428571428571428,0.05089337165862021,0.6409168081494058,0.04472446908983935 +flat_mae,patch,logistic,ppmi_dx,80,2.782559402207126,train,0.998220640569395,0.0017904954023378542,0.9981184064710746,0.0018965794626401612,0.9976851851851851,0.002329301889152484 +flat_mae,patch,logistic,ppmi_dx,80,2.782559402207126,test,0.5,0.04928092531598814,0.48686371100164205,0.04965592073428879,0.4898132427843803,0.05113804614322587 +flat_mae,patch,logistic,ppmi_dx,81,0.046415888336127774,train,0.7900355871886121,0.015509033984423428,0.7660349134220517,0.018263649788795588,0.756422607578677,0.017977090700861044 +flat_mae,patch,logistic,ppmi_dx,81,0.046415888336127774,test,0.65,0.04707595564616825,0.6338529134846741,0.04857725368594455,0.6362478777589134,0.0491651987671376 +flat_mae,patch,logistic,ppmi_dx,82,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,82,166.81005372000556,test,0.62,0.04834149770125043,0.6041666666666667,0.049342292597446644,0.6069609507640068,0.0500780105992134 +flat_mae,patch,logistic,ppmi_dx,83,0.005994842503189409,train,0.7508896797153025,0.01616936292068036,0.7139325189063409,0.019716150046395788,0.705496681652751,0.01829970650207136 +flat_mae,patch,logistic,ppmi_dx,83,0.005994842503189409,test,0.55,0.049910876570142496,0.5146154675870995,0.05368843475629555,0.514855687606112,0.05262443729272983 +flat_mae,patch,logistic,ppmi_dx,84,0.3593813663804626,train,0.9217081850533808,0.011440977287686104,0.916041938287701,0.012440049586962473,0.9103243416827231,0.013116007107304635 +flat_mae,patch,logistic,ppmi_dx,84,0.3593813663804626,test,0.52,0.05042608848602081,0.4851994851994852,0.052809693178770385,0.48556876061120546,0.05234115456734051 +flat_mae,patch,logistic,ppmi_dx,85,0.046415888336127774,train,0.8113879003558719,0.01548276008107793,0.7903575450450451,0.01812276216419673,0.7798517448083921,0.017908438101493125 +flat_mae,patch,logistic,ppmi_dx,85,0.046415888336127774,test,0.65,0.04189191330077918,0.6178622120318812,0.046441777587299386,0.615874363327674,0.04495573241031964 +flat_mae,patch,logistic,ppmi_dx,86,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,86,166.81005372000556,test,0.54,0.04926728732130479,0.5118845500848896,0.05118141222843086,0.5118845500848896,0.05097888125382487 +flat_mae,patch,logistic,ppmi_dx,87,0.005994842503189409,train,0.7295373665480427,0.016653669700078113,0.6866094357619781,0.021143685379149027,0.6803280882038107,0.019262977699374767 +flat_mae,patch,logistic,ppmi_dx,87,0.005994842503189409,test,0.61,0.04644237720013911,0.5481404240528328,0.05583305024802776,0.5530560271646858,0.04994133480056656 +flat_mae,patch,logistic,ppmi_dx,88,0.046415888336127774,train,0.8149466192170819,0.015646055904328764,0.79630868740939,0.017800370113009306,0.7870905587668593,0.017726828536203148 +flat_mae,patch,logistic,ppmi_dx,88,0.046415888336127774,test,0.58,0.04554531369965519,0.5384615384615385,0.04993953444066339,0.5390492359932089,0.0478650410792981 +flat_mae,patch,logistic,ppmi_dx,89,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,89,21.54434690031882,test,0.63,0.04942751865105106,0.6189887756152817,0.050362804315718754,0.6252122241086587,0.05175122657129086 +flat_mae,patch,logistic,ppmi_dx,90,0.005994842503189409,train,0.7366548042704626,0.015442353474201332,0.6939178049929345,0.01928417257555008,0.6869781631342324,0.01750416147525534 +flat_mae,patch,logistic,ppmi_dx,90,0.005994842503189409,test,0.63,0.043506247827179954,0.5713127099988413,0.050822560147855605,0.5742784380305602,0.04593640881238346 +flat_mae,patch,logistic,ppmi_dx,91,0.046415888336127774,train,0.7935943060498221,0.016091509881450354,0.7682045738991923,0.01910298535743078,0.7575733247698566,0.018584355445986415 +flat_mae,patch,logistic,ppmi_dx,91,0.046415888336127774,test,0.66,0.04144453643123542,0.6212121212121212,0.046771206078196535,0.6188455008488964,0.04455995981880292 +flat_mae,patch,logistic,ppmi_dx,92,10000.0,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,92,10000.0,test,0.63,0.04779477377287186,0.6129302228266555,0.04881367405874333,0.615025466893039,0.04931276652269948 +flat_mae,patch,logistic,ppmi_dx,93,0.005994842503189409,train,0.7330960854092526,0.015738027692004497,0.6897815591144607,0.019865256603522626,0.6832182616142154,0.018057097044557525 +flat_mae,patch,logistic,ppmi_dx,93,0.005994842503189409,test,0.62,0.04570732982793898,0.5824175824175825,0.05089476178057351,0.5814940577249575,0.048972301929353736 +flat_mae,patch,logistic,ppmi_dx,94,0.005994842503189409,train,0.7241992882562278,0.016742089613322134,0.6769144607761323,0.02128584360853223,0.6716441875401413,0.01901201093308951 +flat_mae,patch,logistic,ppmi_dx,94,0.005994842503189409,test,0.71,0.03905124325805774,0.6579785352046232,0.05028025771072811,0.6540747028862479,0.04454179523835655 +flat_mae,patch,logistic,ppmi_dx,95,0.005994842503189409,train,0.7419928825622776,0.01625394964436497,0.702394647559154,0.020245189820166796,0.6947923356882895,0.01868820150220373 +flat_mae,patch,logistic,ppmi_dx,95,0.005994842503189409,test,0.62,0.03616130528617573,0.5180111618467782,0.049020689471753205,0.5407470288624787,0.03898450126219541 +flat_mae,patch,logistic,ppmi_dx,96,0.005994842503189409,train,0.7491103202846975,0.016263450711012126,0.7114643071713365,0.02042774527857385,0.7031818668379362,0.018969117802102333 +flat_mae,patch,logistic,ppmi_dx,96,0.005994842503189409,test,0.57,0.041595672851872455,0.5017958521608157,0.04762235817213195,0.5106112054329371,0.042989739419809214 +flat_mae,patch,logistic,ppmi_dx,97,0.3593813663804626,train,0.9145907473309609,0.010683776047344148,0.9078499692559951,0.011739488170810459,0.9001953543138514,0.012427871101454524 +flat_mae,patch,logistic,ppmi_dx,97,0.3593813663804626,test,0.59,0.04385402604094634,0.5464100011063171,0.04896524143031426,0.5471137521222411,0.04662809288192921 +flat_mae,patch,logistic,ppmi_dx,98,0.3593813663804626,train,0.9163701067615658,0.011805301448308382,0.9102282189406427,0.012873758630711517,0.9042496253478913,0.013586103343081727 +flat_mae,patch,logistic,ppmi_dx,98,0.3593813663804626,test,0.61,0.045086454728665466,0.5623386825272135,0.05119695809825289,0.5632427843803056,0.04784055462908207 +flat_mae,patch,logistic,ppmi_dx,99,0.3593813663804626,train,0.9039145907473309,0.011831054384497525,0.8961140322050608,0.013102375696081841,0.8880459216441876,0.013915829124417271 +flat_mae,patch,logistic,ppmi_dx,99,0.3593813663804626,test,0.61,0.04722065226148407,0.5882166613873931,0.04936053660985505,0.5887096774193548,0.049665690165646 +flat_mae,patch,logistic,ppmi_dx,100,0.046415888336127774,train,0.8078291814946619,0.015203641251726647,0.7869328952356881,0.01756552124153722,0.7769615713979876,0.017382605680340613 +flat_mae,patch,logistic,ppmi_dx,100,0.046415888336127774,test,0.65,0.04663819893606527,0.6224786970121885,0.05074796008072561,0.6209677419354839,0.050121791562250585 diff --git a/input_space_v3/flat_lr1e-3_5/eval_v2/ppmi_dx__patch__logistic/log.txt b/input_space_v3/flat_lr1e-3_5/eval_v2/ppmi_dx__patch__logistic/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..d49cd91860e2c3e02779f25d94f5c9a33b5bbbc3 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_5/eval_v2/ppmi_dx__patch__logistic/log.txt @@ -0,0 +1,247 @@ +fMRI foundation model logistic probe eval +version: 0.1.dev86+gf97f52698 +sha: bcce2b486277d3a5b520775efd9cdf1a2affce36, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-04-08 22:30:56 +config: +output_root: experiments/input_space_v3/output +name_prefix: eval_logistic +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_5; eval v2 (ppmi_dx patch logistic) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: input_space_v3/flat_lr1e-3_5/eval_v2/ppmi_dx__patch__logistic +model: flat_mae +representation: patch +dataset: ppmi_dx +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/eval_v2/ppmi_dx__patch__logistic +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=True, reg_tokens=0, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: ppmi_dx (flat) +train (n=463): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'dir', 'sex', 'age', 'age_bin', 'dx', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 463 +}), + labels=['PD' 'Prodromal'], + counts=[178 285] +) + +validation (n=99): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'dir', 'sex', 'age', 'age_bin', 'dx', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 99 +}), + labels=['PD' 'Prodromal'], + counts=[39 60] +) + +test (n=100): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'dir', 'sex', 'age', 'age_bin', 'dx', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 100 +}), + labels=['PD' 'Prodromal'], + counts=[37 63] +) + +extracting features for all splits +extract (train) [ 0/232] eta: 0:16:33 time: 4.2821 data: 3.3985 max mem: 2698 +extract (train) [ 20/232] eta: 0:01:23 time: 0.2010 data: 0.0744 max mem: 2851 +extract (train) [ 40/232] eta: 0:00:56 time: 0.1830 data: 0.0618 max mem: 2851 +extract (train) [ 60/232] eta: 0:00:43 time: 0.1806 data: 0.0587 max mem: 2851 +extract (train) [ 80/232] eta: 0:00:36 time: 0.1975 data: 0.0708 max mem: 2851 +extract (train) [100/232] eta: 0:00:30 time: 0.1830 data: 0.0607 max mem: 2851 +extract (train) [120/232] eta: 0:00:24 time: 0.1912 data: 0.0664 max mem: 2851 +extract (train) [140/232] eta: 0:00:19 time: 0.1691 data: 0.0538 max mem: 2851 +extract (train) [160/232] eta: 0:00:15 time: 0.1703 data: 0.0544 max mem: 2851 +extract (train) [180/232] eta: 0:00:10 time: 0.2096 data: 0.0771 max mem: 2851 +extract (train) [200/232] eta: 0:00:06 time: 0.2028 data: 0.0755 max mem: 2851 +extract (train) [220/232] eta: 0:00:02 time: 0.1796 data: 0.0622 max mem: 2851 +extract (train) [231/232] eta: 0:00:00 time: 0.1819 data: 0.0629 max mem: 2851 +extract (train) Total time: 0:00:48 (0.2081 s / it) +extract (validation) [ 0/50] eta: 0:03:49 time: 4.5959 data: 4.4261 max mem: 2851 +extract (validation) [20/50] eta: 0:00:14 time: 0.2838 data: 0.1144 max mem: 2851 +extract (validation) [40/50] eta: 0:00:03 time: 0.1792 data: 0.0575 max mem: 2851 +extract (validation) [49/50] eta: 0:00:00 time: 0.1706 data: 0.0564 max mem: 2851 +extract (validation) Total time: 0:00:15 (0.3134 s / it) +extract (test) [ 0/50] eta: 0:03:28 time: 4.1687 data: 4.0006 max mem: 2851 +extract (test) [20/50] eta: 0:00:13 time: 0.2656 data: 0.0972 max mem: 2851 +extract (test) [40/50] eta: 0:00:03 time: 0.1833 data: 0.0637 max mem: 2851 +extract (test) [49/50] eta: 0:00:00 time: 0.1782 data: 0.0600 max mem: 2851 +extract (test) Total time: 0:00:15 (0.3075 s / it) +feature extraction time: 0:01:19 +train features: (463, 768) +validation features: (99, 768) +test features: (100, 768) +evaluating fixed splits +eval results (fixed splits): + +| model | repr | clf | dataset | trial | C | split | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|---------:|:--------|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | ppmi_dx | | 0.046416 | train | 0.80783 | 0.015626 | 0.78586 | 0.018309 | 0.77509 | 0.017996 | +| flat_mae | patch | logistic | ppmi_dx | | 0.046416 | test | 0.64 | 0.043858 | 0.5864 | 0.052176 | 0.58601 | 0.048149 | + + +evaluating random splits (n=100) +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 1, "C": 0.005994842503189409, "split": "test", "acc": 0.72, "acc_std": 0.034719786865705274, "f1": 0.6448503297818367, "f1_std": 0.05351509447065291, "bacc": 0.6468590831918506, "bacc_std": 0.04235552286254733} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 2, "C": 1291.5496650148827, "split": "test", "acc": 0.66, "acc_std": 0.044803017755503924, "f1": 0.6392190152801358, "f1_std": 0.04728595480378686, "bacc": 0.6392190152801358, "bacc_std": 0.047429114745199515} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 3, "C": 0.046415888336127774, "split": "test", "acc": 0.63, "acc_std": 0.047458862186108085, "f1": 0.6009060511271707, "f1_std": 0.051157931337640794, "bacc": 0.5997453310696095, "bacc_std": 0.049983730962565025} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 4, "C": 0.005994842503189409, "split": "test", "acc": 0.65, "acc_std": 0.041896462857859494, "f1": 0.6072270227808326, "f1_std": 0.048184640076157685, "bacc": 0.6056876061120543, "bacc_std": 0.04514075637065264} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 5, "C": 21.54434690031882, "split": "test", "acc": 0.58, "acc_std": 0.04593133570886002, "f1": 0.5543293718166383, "f1_std": 0.04728693957483686, "bacc": 0.5543293718166383, "bacc_std": 0.046933673586288645} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 6, "C": 0.005994842503189409, "split": "test", "acc": 0.64, "acc_std": 0.04118727473383011, "f1": 0.5714285714285714, "f1_std": 0.05333048867527479, "bacc": 0.5772495755517827, "bacc_std": 0.04577921051082555} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 7, "C": 0.046415888336127774, "split": "test", "acc": 0.55, "acc_std": 0.049480598217887375, "f1": 0.52, "f1_std": 0.05153865847417581, "bacc": 0.5199490662139219, "bacc_std": 0.05100687596780509} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 8, "C": 0.046415888336127774, "split": "test", "acc": 0.6, "acc_std": 0.042596168841810174, "f1": 0.5404411764705883, "f1_std": 0.04873137694448012, "bacc": 0.5449915110356536, "bacc_std": 0.044320814043012184} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 9, "C": 0.3593813663804626, "split": "test", "acc": 0.64, "acc_std": 0.04461302052091967, "f1": 0.6138996138996139, "f1_std": 0.0482742456728774, "bacc": 0.6129032258064516, "bacc_std": 0.047734393807892725} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 10, "C": 0.046415888336127774, "split": "test", "acc": 0.67, "acc_std": 0.041411471840541954, "f1": 0.6239316239316239, "f1_std": 0.04977766476095066, "bacc": 0.6218166383701189, "bacc_std": 0.04579143043996181} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 11, "C": 0.046415888336127774, "split": "test", "acc": 0.68, "acc_std": 0.0442348098221299, "f1": 0.6527777777777778, "f1_std": 0.048669910541670997, "bacc": 0.6502546689303905, "bacc_std": 0.04754725007846055} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 12, "C": 0.046415888336127774, "split": "test", "acc": 0.57, "acc_std": 0.04142976707634258, "f1": 0.49286472461375164, "f1_std": 0.04865685494696078, "bacc": 0.5055178268251274, "bacc_std": 0.042941973549405564} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 13, "C": 2.782559402207126, "split": "test", "acc": 0.61, "acc_std": 0.045786718598300975, "f1": 0.5793334052421529, "f1_std": 0.04989904629279219, "bacc": 0.5785229202037352, "bacc_std": 0.04906496167352984} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 14, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.04223209679852517, "f1": 0.5324918186068257, "f1_std": 0.04978312395067441, "bacc": 0.5398981324278438, "bacc_std": 0.0443802229456521} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 15, "C": 0.005994842503189409, "split": "test", "acc": 0.68, "acc_std": 0.04317654919050386, "f1": 0.6323529411764706, "f1_std": 0.051525254314443464, "bacc": 0.6298811544991512, "bacc_std": 0.047305126121923134} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 16, "C": 10000.0, "split": "test", "acc": 0.62, "acc_std": 0.04796386556565266, "f1": 0.5967741935483871, "f1_std": 0.05010868673825183, "bacc": 0.5967741935483871, "bacc_std": 0.05029864325398614} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 17, "C": 0.046415888336127774, "split": "test", "acc": 0.64, "acc_std": 0.04597434066955176, "f1": 0.6043956043956044, "f1_std": 0.050946786021574965, "bacc": 0.6027164685908319, "bacc_std": 0.04902879207541099} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 18, "C": 0.046415888336127774, "split": "test", "acc": 0.57, "acc_std": 0.045335478380623705, "f1": 0.5305164319248826, "f1_std": 0.0486468334526727, "bacc": 0.5309847198641766, "bacc_std": 0.04700173759445523} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 19, "C": 0.3593813663804626, "split": "test", "acc": 0.66, "acc_std": 0.04710503582420886, "f1": 0.6458333333333333, "f1_std": 0.04864894080161696, "bacc": 0.6494057724957556, "bacc_std": 0.04938652659142659} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 20, "C": 0.046415888336127774, "split": "test", "acc": 0.65, "acc_std": 0.04082638362627775, "f1": 0.5944849959448499, "f1_std": 0.04963030888115686, "bacc": 0.5955008488964346, "bacc_std": 0.044646064218265134} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 21, "C": 0.046415888336127774, "split": "test", "acc": 0.69, "acc_std": 0.04131819937993425, "f1": 0.6408295678368672, "f1_std": 0.051842155906366184, "bacc": 0.6379456706281834, "bacc_std": 0.04661605292557239} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 22, "C": 0.046415888336127774, "split": "test", "acc": 0.62, "acc_std": 0.04433402305227893, "f1": 0.5634191176470589, "f1_std": 0.05164375941486428, "bacc": 0.566213921901528, "bacc_std": 0.04714080591889674} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 23, "C": 0.3593813663804626, "split": "test", "acc": 0.57, "acc_std": 0.048091491971033705, "f1": 0.5413333333333333, "f1_std": 0.05161201650917838, "bacc": 0.5411714770797962, "bacc_std": 0.051031395569356125} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 24, "C": 0.005994842503189409, "split": "test", "acc": 0.65, "acc_std": 0.04416362303978241, "f1": 0.5872154735228211, "f1_std": 0.05429119887745847, "bacc": 0.5904074702886248, "bacc_std": 0.04778781917005062} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 25, "C": 0.046415888336127774, "split": "test", "acc": 0.65, "acc_std": 0.03894272204148036, "f1": 0.5872154735228211, "f1_std": 0.04981719462708731, "bacc": 0.5904074702886248, "bacc_std": 0.043384030531979666} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 26, "C": 0.005994842503189409, "split": "test", "acc": 0.65, "acc_std": 0.045227297067147405, "f1": 0.6011396011396011, "f1_std": 0.05185317984155702, "bacc": 0.6005942275042444, "bacc_std": 0.04788330419638174} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 27, "C": 0.3593813663804626, "split": "test", "acc": 0.57, "acc_std": 0.04647171612927588, "f1": 0.5501621508525996, "f1_std": 0.04827555992788557, "bacc": 0.551358234295416, "bacc_std": 0.04898095808197892} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 28, "C": 2.782559402207126, "split": "test", "acc": 0.6, "acc_std": 0.04797792825873164, "f1": 0.5796553173602353, "f1_std": 0.049275592435860056, "bacc": 0.5806451612903225, "bacc_std": 0.049335124839865505} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 29, "C": 0.3593813663804626, "split": "test", "acc": 0.62, "acc_std": 0.04689338972605841, "f1": 0.6006725514922235, "f1_std": 0.04848545877356072, "bacc": 0.6018675721561969, "bacc_std": 0.04890309933681076} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 30, "C": 166.81005372000556, "split": "test", "acc": 0.63, "acc_std": 0.047968973305669155, "f1": 0.6093337556752191, "f1_std": 0.050200531258142174, "bacc": 0.6099320882852293, "bacc_std": 0.050521470315288974} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 31, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.04857734451367222, "f1": 0.5604395604395604, "f1_std": 0.05241267879434175, "bacc": 0.5602716468590832, "bacc_std": 0.05042830740435462} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 32, "C": 2.782559402207126, "split": "test", "acc": 0.64, "acc_std": 0.05063309589586637, "f1": 0.6179966044142615, "f1_std": 0.05294438398050823, "bacc": 0.6179966044142615, "bacc_std": 0.052791938164719346} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 33, "C": 0.3593813663804626, "split": "test", "acc": 0.58, "acc_std": 0.04731231974866588, "f1": 0.5495495495495495, "f1_std": 0.04986850787640493, "bacc": 0.5492359932088284, "bacc_std": 0.04894780522681723} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 34, "C": 0.046415888336127774, "split": "test", "acc": 0.67, "acc_std": 0.04528351134795092, "f1": 0.6296711929076422, "f1_std": 0.0528274568735957, "bacc": 0.6269100169779287, "bacc_std": 0.049796521716383255} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 35, "C": 0.005994842503189409, "split": "test", "acc": 0.62, "acc_std": 0.04643176068167134, "f1": 0.5876736111111112, "f1_std": 0.04989967109038557, "bacc": 0.5865874363327674, "bacc_std": 0.048742323952458935} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 36, "C": 0.046415888336127774, "split": "test", "acc": 0.66, "acc_std": 0.04334517735573359, "f1": 0.609375, "f1_std": 0.05217523901672738, "bacc": 0.6086587436332768, "bacc_std": 0.047714063582913434} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 37, "C": 0.046415888336127774, "split": "test", "acc": 0.63, "acc_std": 0.04672729395118018, "f1": 0.6053333333333333, "f1_std": 0.0500051360176617, "bacc": 0.6048387096774194, "bacc_std": 0.04982858438409728} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 38, "C": 21.54434690031882, "split": "test", "acc": 0.57, "acc_std": 0.050692705589660526, "f1": 0.5538956323270048, "f1_std": 0.05169921519042101, "bacc": 0.5564516129032258, "bacc_std": 0.0528071253381006} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 39, "C": 0.3593813663804626, "split": "test", "acc": 0.72, "acc_std": 0.04546251202914331, "f1": 0.7028862478777589, "f1_std": 0.04792152492653265, "bacc": 0.7028862478777589, "bacc_std": 0.048137394455146844} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 40, "C": 0.3593813663804626, "split": "test", "acc": 0.67, "acc_std": 0.0464950535003456, "f1": 0.6515679442508711, "f1_std": 0.04916463058772718, "bacc": 0.652376910016978, "bacc_std": 0.04964336138445553} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 41, "C": 0.005994842503189409, "split": "test", "acc": 0.67, "acc_std": 0.04329942262894506, "f1": 0.6349153667441089, "f1_std": 0.048783767757865006, "bacc": 0.6320033955857385, "bacc_std": 0.04648370719701013} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 42, "C": 0.3593813663804626, "split": "test", "acc": 0.67, "acc_std": 0.04027902680055713, "f1": 0.6176572818908586, "f1_std": 0.04920311590087093, "bacc": 0.616723259762309, "bacc_std": 0.044278828495158816} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 43, "C": 0.005994842503189409, "split": "test", "acc": 0.69, "acc_std": 0.03685263084231571, "f1": 0.6196785670469881, "f1_std": 0.05088326083280931, "bacc": 0.6226655348047538, "bacc_std": 0.04233314281455529} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 44, "C": 2.782559402207126, "split": "test", "acc": 0.56, "acc_std": 0.050408138231837124, "f1": 0.5452666391070691, "f1_std": 0.05101776941279667, "bacc": 0.5483870967741935, "bacc_std": 0.05186183170782402} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 45, "C": 2.782559402207126, "split": "test", "acc": 0.57, "acc_std": 0.050226252099873026, "f1": 0.5601023017902813, "f1_std": 0.05036476531007583, "bacc": 0.5666383701188455, "bacc_std": 0.05185512216540719} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 46, "C": 0.046415888336127774, "split": "test", "acc": 0.58, "acc_std": 0.04609164783341988, "f1": 0.5320855614973261, "f1_std": 0.0516305244543477, "bacc": 0.533955857385399, "bacc_std": 0.048521138943948446} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 47, "C": 21.54434690031882, "split": "test", "acc": 0.59, "acc_std": 0.04718348863744605, "f1": 0.5777983729790959, "f1_std": 0.048192466026256875, "bacc": 0.58276740237691, "bacc_std": 0.049618034975389684} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 48, "C": 2.782559402207126, "split": "test", "acc": 0.69, "acc_std": 0.04396494512677116, "f1": 0.6615351020853806, "f1_std": 0.049070413947449425, "bacc": 0.6583191850594228, "bacc_std": 0.047949487045824794} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 49, "C": 0.005994842503189409, "split": "test", "acc": 0.69, "acc_std": 0.03557155605255411, "f1": 0.6196785670469881, "f1_std": 0.05043589448028314, "bacc": 0.6226655348047538, "bacc_std": 0.04131229201013078} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 50, "C": 1291.5496650148827, "split": "test", "acc": 0.55, "acc_std": 0.04854480816730044, "f1": 0.5021573182874212, "f1_std": 0.05199044012765227, "bacc": 0.5046689303904923, "bacc_std": 0.04968783207010084} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 51, "C": 2.782559402207126, "split": "test", "acc": 0.61, "acc_std": 0.047457007912425325, "f1": 0.5983935742971888, "f1_std": 0.04858350984175536, "bacc": 0.6039898132427843, "bacc_std": 0.04973643044167271} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 52, "C": 2.782559402207126, "split": "test", "acc": 0.61, "acc_std": 0.050107707989889144, "f1": 0.5920075321686369, "f1_std": 0.051567866614193235, "bacc": 0.5938030560271647, "bacc_std": 0.052069659053562506} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 53, "C": 0.046415888336127774, "split": "test", "acc": 0.66, "acc_std": 0.04427380263767728, "f1": 0.6263736263736264, "f1_std": 0.04961920077019107, "bacc": 0.6239388794567062, "bacc_std": 0.047936146230507744} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 54, "C": 0.046415888336127774, "split": "test", "acc": 0.55, "acc_std": 0.047603209975798894, "f1": 0.5146154675870995, "f1_std": 0.04876940939841477, "bacc": 0.514855687606112, "bacc_std": 0.04800616320136609} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 55, "C": 2.782559402207126, "split": "test", "acc": 0.68, "acc_std": 0.046577230488727, "f1": 0.6637242538881883, "f1_std": 0.04896999442530735, "bacc": 0.6655348047538201, "bacc_std": 0.04953297038081854} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 56, "C": 0.005994842503189409, "split": "test", "acc": 0.64, "acc_std": 0.04029453560968286, "f1": 0.5628946090335114, "f1_std": 0.051904947765090165, "bacc": 0.5721561969439728, "bacc_std": 0.043691134735568134} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 57, "C": 2.782559402207126, "split": "test", "acc": 0.56, "acc_std": 0.04593638644908847, "f1": 0.5225694444444444, "f1_std": 0.049408255528955156, "bacc": 0.5229202037351443, "bacc_std": 0.04800851117218283} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 58, "C": 0.005994842503189409, "split": "test", "acc": 0.68, "acc_std": 0.03999467964617293, "f1": 0.6190476190476191, "f1_std": 0.051850743347748106, "bacc": 0.6196943972835314, "bacc_std": 0.04503093720530703} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 59, "C": 0.3593813663804626, "split": "test", "acc": 0.6, "acc_std": 0.04802006247392854, "f1": 0.554367201426025, "f1_std": 0.05335591702391213, "bacc": 0.5551782682512734, "bacc_std": 0.05041725363546822} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 60, "C": 21.54434690031882, "split": "test", "acc": 0.62, "acc_std": 0.04970673998563977, "f1": 0.6124031007751938, "f1_std": 0.0499255277938015, "bacc": 0.6222410865874364, "bacc_std": 0.051307436046064775} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 61, "C": 0.3593813663804626, "split": "test", "acc": 0.61, "acc_std": 0.04679970512727618, "f1": 0.584, "f1_std": 0.04929258656518385, "bacc": 0.583616298811545, "bacc_std": 0.0489213464279063} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 62, "C": 166.81005372000556, "split": "test", "acc": 0.64, "acc_std": 0.04803706901966439, "f1": 0.6216897856242118, "f1_std": 0.049869420280316955, "bacc": 0.6230899830220713, "bacc_std": 0.05023357863446226} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 63, "C": 1291.5496650148827, "split": "test", "acc": 0.54, "acc_std": 0.048965861577225406, "f1": 0.5166036149642708, "f1_std": 0.05103065725092895, "bacc": 0.5169779286926994, "bacc_std": 0.05148901024529485} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 64, "C": 0.005994842503189409, "split": "test", "acc": 0.64, "acc_std": 0.04228839557136213, "f1": 0.5792426367461431, "f1_std": 0.050427213746009523, "bacc": 0.5823429541595926, "bacc_std": 0.04523567959492689} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 65, "C": 0.3593813663804626, "split": "test", "acc": 0.53, "acc_std": 0.05084818187506806, "f1": 0.49304282170208175, "f1_std": 0.05234521458180613, "bacc": 0.4936332767402377, "bacc_std": 0.05152919673739481} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 66, "C": 0.005994842503189409, "split": "test", "acc": 0.63, "acc_std": 0.042930506635724675, "f1": 0.5713127099988413, "f1_std": 0.050827440024669476, "bacc": 0.5742784380305602, "bacc_std": 0.0457253162118849} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 67, "C": 0.046415888336127774, "split": "test", "acc": 0.61, "acc_std": 0.047220550610936336, "f1": 0.5793334052421529, "f1_std": 0.05106944702854767, "bacc": 0.5785229202037352, "bacc_std": 0.050452293899769934} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 68, "C": 1291.5496650148827, "split": "test", "acc": 0.58, "acc_std": 0.04485159528935398, "f1": 0.5495495495495495, "f1_std": 0.047398874778283896, "bacc": 0.5492359932088284, "bacc_std": 0.04685897477288705} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 69, "C": 0.005994842503189409, "split": "test", "acc": 0.71, "acc_std": 0.041246653197562586, "f1": 0.6640018537828757, "f1_std": 0.050511176433841155, "bacc": 0.6591680814940577, "bacc_std": 0.04632776831784595} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 70, "C": 0.3593813663804626, "split": "test", "acc": 0.56, "acc_std": 0.04797906210004526, "f1": 0.5280995280995281, "f1_std": 0.05007985997718756, "bacc": 0.5280135823429541, "bacc_std": 0.049350640596634056} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 71, "C": 0.005994842503189409, "split": "test", "acc": 0.65, "acc_std": 0.041182185468962185, "f1": 0.5792763553311696, "f1_std": 0.05197680341106155, "bacc": 0.5853140916808149, "bacc_std": 0.04460873933775471} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 72, "C": 0.005994842503189409, "split": "test", "acc": 0.64, "acc_std": 0.04260269944498822, "f1": 0.5863970588235294, "f1_std": 0.05095613702593209, "bacc": 0.5874363327674024, "bacc_std": 0.04612419841130511} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 73, "C": 0.046415888336127774, "split": "test", "acc": 0.65, "acc_std": 0.04671503398264846, "f1": 0.6338529134846741, "f1_std": 0.04802575814643857, "bacc": 0.6362478777589134, "bacc_std": 0.048526827880828294} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 74, "C": 0.005994842503189409, "split": "test", "acc": 0.58, "acc_std": 0.04429271271891122, "f1": 0.5174632352941176, "f1_std": 0.051077487757178026, "bacc": 0.5237691001697793, "bacc_std": 0.046536848011569154} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 75, "C": 0.046415888336127774, "split": "test", "acc": 0.6, "acc_std": 0.04603209315249525, "f1": 0.554367201426025, "f1_std": 0.050904754357527685, "bacc": 0.5551782682512734, "bacc_std": 0.04819827411550661} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 76, "C": 0.3593813663804626, "split": "test", "acc": 0.59, "acc_std": 0.04798947801341456, "f1": 0.5523528769516323, "f1_std": 0.05205722467112479, "bacc": 0.5522071307300509, "bacc_std": 0.05025096647990061} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 77, "C": 1291.5496650148827, "split": "test", "acc": 0.58, "acc_std": 0.044708388474647566, "f1": 0.5442708333333334, "f1_std": 0.04912022675526458, "bacc": 0.5441426146010186, "bacc_std": 0.04771257429131255} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 78, "C": 10000.0, "split": "test", "acc": 0.6, "acc_std": 0.04911612362554684, "f1": 0.5796553173602353, "f1_std": 0.05126725261465157, "bacc": 0.5806451612903225, "bacc_std": 0.05184237996181347} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 79, "C": 0.005994842503189409, "split": "test", "acc": 0.7, "acc_std": 0.03955308331849743, "f1": 0.6428571428571428, "f1_std": 0.05089337165862021, "bacc": 0.6409168081494058, "bacc_std": 0.04472446908983935} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 80, "C": 2.782559402207126, "split": "test", "acc": 0.5, "acc_std": 0.04928092531598814, "f1": 0.48686371100164205, "f1_std": 0.04965592073428879, "bacc": 0.4898132427843803, "bacc_std": 0.05113804614322587} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 81, "C": 0.046415888336127774, "split": "test", "acc": 0.65, "acc_std": 0.04707595564616825, "f1": 0.6338529134846741, "f1_std": 0.04857725368594455, "bacc": 0.6362478777589134, "bacc_std": 0.0491651987671376} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 82, "C": 166.81005372000556, "split": "test", "acc": 0.62, "acc_std": 0.04834149770125043, "f1": 0.6041666666666667, "f1_std": 0.049342292597446644, "bacc": 0.6069609507640068, "bacc_std": 0.0500780105992134} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 83, "C": 0.005994842503189409, "split": "test", "acc": 0.55, "acc_std": 0.049910876570142496, "f1": 0.5146154675870995, "f1_std": 0.05368843475629555, "bacc": 0.514855687606112, "bacc_std": 0.05262443729272983} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 84, "C": 0.3593813663804626, "split": "test", "acc": 0.52, "acc_std": 0.05042608848602081, "f1": 0.4851994851994852, "f1_std": 0.052809693178770385, "bacc": 0.48556876061120546, "bacc_std": 0.05234115456734051} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 85, "C": 0.046415888336127774, "split": "test", "acc": 0.65, "acc_std": 0.04189191330077918, "f1": 0.6178622120318812, "f1_std": 0.046441777587299386, "bacc": 0.615874363327674, "bacc_std": 0.04495573241031964} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 86, "C": 166.81005372000556, "split": "test", "acc": 0.54, "acc_std": 0.04926728732130479, "f1": 0.5118845500848896, "f1_std": 0.05118141222843086, "bacc": 0.5118845500848896, "bacc_std": 0.05097888125382487} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 87, "C": 0.005994842503189409, "split": "test", "acc": 0.61, "acc_std": 0.04644237720013911, "f1": 0.5481404240528328, "f1_std": 0.05583305024802776, "bacc": 0.5530560271646858, "bacc_std": 0.04994133480056656} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 88, "C": 0.046415888336127774, "split": "test", "acc": 0.58, "acc_std": 0.04554531369965519, "f1": 0.5384615384615385, "f1_std": 0.04993953444066339, "bacc": 0.5390492359932089, "bacc_std": 0.0478650410792981} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 89, "C": 21.54434690031882, "split": "test", "acc": 0.63, "acc_std": 0.04942751865105106, "f1": 0.6189887756152817, "f1_std": 0.050362804315718754, "bacc": 0.6252122241086587, "bacc_std": 0.05175122657129086} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 90, "C": 0.005994842503189409, "split": "test", "acc": 0.63, "acc_std": 0.043506247827179954, "f1": 0.5713127099988413, "f1_std": 0.050822560147855605, "bacc": 0.5742784380305602, "bacc_std": 0.04593640881238346} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 91, "C": 0.046415888336127774, "split": "test", "acc": 0.66, "acc_std": 0.04144453643123542, "f1": 0.6212121212121212, "f1_std": 0.046771206078196535, "bacc": 0.6188455008488964, "bacc_std": 0.04455995981880292} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 92, "C": 10000.0, "split": "test", "acc": 0.63, "acc_std": 0.04779477377287186, "f1": 0.6129302228266555, "f1_std": 0.04881367405874333, "bacc": 0.615025466893039, "bacc_std": 0.04931276652269948} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 93, "C": 0.005994842503189409, "split": "test", "acc": 0.62, "acc_std": 0.04570732982793898, "f1": 0.5824175824175825, "f1_std": 0.05089476178057351, "bacc": 0.5814940577249575, "bacc_std": 0.048972301929353736} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 94, "C": 0.005994842503189409, "split": "test", "acc": 0.71, "acc_std": 0.03905124325805774, "f1": 0.6579785352046232, "f1_std": 0.05028025771072811, "bacc": 0.6540747028862479, "bacc_std": 0.04454179523835655} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 95, "C": 0.005994842503189409, "split": "test", "acc": 0.62, "acc_std": 0.03616130528617573, "f1": 0.5180111618467782, "f1_std": 0.049020689471753205, "bacc": 0.5407470288624787, "bacc_std": 0.03898450126219541} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 96, "C": 0.005994842503189409, "split": "test", "acc": 0.57, "acc_std": 0.041595672851872455, "f1": 0.5017958521608157, "f1_std": 0.04762235817213195, "bacc": 0.5106112054329371, "bacc_std": 0.042989739419809214} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 97, "C": 0.3593813663804626, "split": "test", "acc": 0.59, "acc_std": 0.04385402604094634, "f1": 0.5464100011063171, "f1_std": 0.04896524143031426, "bacc": 0.5471137521222411, "bacc_std": 0.04662809288192921} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 98, "C": 0.3593813663804626, "split": "test", "acc": 0.61, "acc_std": 0.045086454728665466, "f1": 0.5623386825272135, "f1_std": 0.05119695809825289, "bacc": 0.5632427843803056, "bacc_std": 0.04784055462908207} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 99, "C": 0.3593813663804626, "split": "test", "acc": 0.61, "acc_std": 0.04722065226148407, "f1": 0.5882166613873931, "f1_std": 0.04936053660985505, "bacc": 0.5887096774193548, "bacc_std": 0.049665690165646} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 100, "C": 0.046415888336127774, "split": "test", "acc": 0.65, "acc_std": 0.04663819893606527, "f1": 0.6224786970121885, "f1_std": 0.05074796008072561, "bacc": 0.6209677419354839, "bacc_std": 0.050121791562250585} +eval results (random splits): + +| model | repr | clf | dataset | split | n_trials | C | C_std | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|-----------:|-------:|--------:|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | ppmi_dx | train | 100 | 372.71 | 1724.9 | 0.85952 | 0.10612 | 0.84039 | 0.12334 | 0.83479 | 0.126 | +| flat_mae | patch | logistic | ppmi_dx | test | 100 | 372.71 | 1724.9 | 0.6209 | 0.047207 | 0.58267 | 0.047065 | 0.5841 | 0.045777 | + + +done! total time: 0:05:45 diff --git a/input_space_v3/flat_lr1e-3_5/pretrain/config.yaml b/input_space_v3/flat_lr1e-3_5/pretrain/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..1d400c2e2c9fd3a30edb67f526af46eb20402038 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_5/pretrain/config.yaml @@ -0,0 +1,102 @@ +name: input_space_v3/flat_lr1e-3_5/pretrain +notes: input_space ablation v3 flat_lr1e-3_5; use tube masking and on-disk data (input_space=flat + base_lr=1e-3 seed=5405) +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain +input_space: flat +patch_size: 16 +num_frames: 16 +t_patch_size: 4 +mask_ratio: 0.9 +pred_mask_ratio: null +masking: tube +masking_kwargs: {} +mask_patch_size: null +model: mae_vit_base +model_kwargs: + decoding: attn + pos_embed: sep + target_norm: null + pca_norm_nc: 2 + t_pred_stride: 2 + no_decode_pos: true + mask_drop_scale: false + pred_edge_pad: 0 + gauss_sigma: null + class_token: true + reg_tokens: 0 + no_embed_class: true + head_init_scale: 0.0 + decoder_depth: 4 + drop_path_rate: 0.0 +datasets: + hcp-train: + type: wds + url: /data/fmri-datasets/pretrain/hcpya-all.${input_space}.wds/hcpya-all-${input_space}-{00000..01799}.tar + clipping: random + clipping_kwargs: + oversample: 4.0 + shuffle: true + buffer_size: 2000 + samples_per_epoch: 200000 + hcp-train-subset: + type: arrow + root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/validation + split_range: + - 0 + - 2000 + shuffle: false + hcp-val: + type: arrow + root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/test + split_range: + - 0 + - 2000 + shuffle: false +train_dataset: hcp-train +eval_datasets: +- hcp-train-subset +- hcp-val +val_dataset: null +clip_vmax: 3.0 +normalize: frame +tr_scale: null +crop_scale: null +crop_aspect: null +gray_jitter: null +num_workers: 16 +epochs: 100 +batch_size: 32 +accum_iter: 1 +base_lr: 0.001 +min_lr: 0.0 +warmup_epochs: 5 +weight_decay: 0.05 +betas: +- 0.9 +- 0.95 +clip_grad: 1.0 +amp: true +amp_dtype: float16 +ckpt: null +resume: true +auto_resume: true +start_epoch: 0 +max_checkpoints: 0 +checkpoint_period: null +plot_period: 5 +device: cuda +presend_cuda: false +seed: 5405 +debug: false +wandb: true +wandb_entity: null +wandb_project: fMRI-foundation-model +rank: 0 +world_size: 1 +gpu: 0 +distributed: true +dist_backend: nccl +in_chans: 1 +img_size: +- 224 +- 560 diff --git a/input_space_v3/flat_lr1e-3_5/pretrain/log.json b/input_space_v3/flat_lr1e-3_5/pretrain/log.json new file mode 100644 index 0000000000000000000000000000000000000000..cc28a518595913d87a4de557f1115e677cd92edb --- /dev/null +++ b/input_space_v3/flat_lr1e-3_5/pretrain/log.json @@ -0,0 +1,100 @@ +{"epoch": 0, "train/lr": 1.2502400076802458e-05, "train/grad": 0.05190150394797325, "train/loss": 0.9933083045005798, "eval/hcp-train-subset/loss": 0.9928643261232684, "eval/hcp-val/loss": 0.9914478303924683} +{"epoch": 1, "train/lr": 3.750320010240327e-05, "train/grad": 0.08426367010235787, "train/loss": 0.9876970536136627, "eval/hcp-train-subset/loss": 0.9891270283729799, "eval/hcp-val/loss": 0.9873784155614914} +{"epoch": 2, "train/lr": 6.250400012800409e-05, "train/grad": 0.108169542038849, "train/loss": 0.9849529489135742, "eval/hcp-train-subset/loss": 0.9834680143863924, "eval/hcp-val/loss": 0.9814837334617492} +{"epoch": 3, "train/lr": 8.75048001536049e-05, "train/grad": 0.19319188657244155, "train/loss": 0.9766521514129639, "eval/hcp-train-subset/loss": 0.97490214628558, "eval/hcp-val/loss": 0.9719547783174822} +{"epoch": 4, "train/lr": 0.00011250559953918529, "train/grad": 0.22621659530679214, "train/loss": 0.948030247220993, "eval/hcp-train-subset/loss": 0.9301184204316908, "eval/hcp-val/loss": 0.9250891737399562} +{"epoch": 5, "train/lr": 0.00012498860637884563, "train/grad": 0.17449986517176547, "train/loss": 0.908826066493988, "eval/hcp-train-subset/loss": 0.8915544854056451, "eval/hcp-val/loss": 0.8854582242427333} +{"epoch": 6, "train/lr": 0.0001249202705377922, "train/grad": 0.12262926932672341, "train/loss": 0.8773734486961364, "eval/hcp-train-subset/loss": 0.8723088166406078, "eval/hcp-val/loss": 0.8660534110761458} +{"epoch": 7, "train/lr": 0.0001247836790473516, "train/grad": 0.09381858995731437, "train/loss": 0.863777961215973, "eval/hcp-train-subset/loss": 0.8638700189128998, "eval/hcp-val/loss": 0.8582405938256171} +{"epoch": 8, "train/lr": 0.000124578981268311, "train/grad": 0.07828290407604296, "train/loss": 0.8580851108646392, "eval/hcp-train-subset/loss": 0.8596092885540377, "eval/hcp-val/loss": 0.8537325791774257} +{"epoch": 9, "train/lr": 0.00012430640103468907, "train/grad": 0.07494351844170179, "train/loss": 0.8523781890296936, "eval/hcp-train-subset/loss": 0.8569057458831418, "eval/hcp-val/loss": 0.8518832797004331} +{"epoch": 10, "train/lr": 0.00012396623640896796, "train/grad": 0.06970731179896508, "train/loss": 0.8508103270435333, "eval/hcp-train-subset/loss": 0.8543266231013883, "eval/hcp-val/loss": 0.8486407303041027} +{"epoch": 11, "train/lr": 0.0001235588593561712, "train/grad": 0.06752975893551127, "train/loss": 0.8488845871639251, "eval/hcp-train-subset/loss": 0.8528802837094953, "eval/hcp-val/loss": 0.8471741455216562} +{"epoch": 12, "train/lr": 0.00012308471533712604, "train/grad": 0.06652800859132169, "train/loss": 0.8475524717140198, "eval/hcp-train-subset/loss": 0.8511563866369186, "eval/hcp-val/loss": 0.8458350512289232} +{"epoch": 13, "train/lr": 0.00012254432282135565, "train/grad": 0.06504525525630798, "train/loss": 0.8456306867980957, "eval/hcp-train-subset/loss": 0.8502467092006437, "eval/hcp-val/loss": 0.8452141996352903} +{"epoch": 14, "train/lr": 0.00012193827272014171, "train/grad": 0.0649330881179791, "train/loss": 0.8438644865894318, "eval/hcp-train-subset/loss": 0.849805784802283, "eval/hcp-val/loss": 0.8437207562308158} +{"epoch": 15, "train/lr": 0.00012126722774037197, "train/grad": 0.06481406446272046, "train/loss": 0.8418144307422638, "eval/hcp-train-subset/loss": 0.8494838572317555, "eval/hcp-val/loss": 0.8443003277624807} +{"epoch": 16, "train/lr": 0.00012053192165988122, "train/grad": 0.06445062832260716, "train/loss": 0.8409463905906677, "eval/hcp-train-subset/loss": 0.8476741640798507, "eval/hcp-val/loss": 0.8429383529770759} +{"epoch": 17, "train/lr": 0.00011973315852507104, "train/grad": 0.06521173707030833, "train/loss": 0.8404405590057373, "eval/hcp-train-subset/loss": 0.8468773422702667, "eval/hcp-val/loss": 0.8424066151342084} +{"epoch": 18, "train/lr": 0.00011887181177170142, "train/grad": 0.0644595150382825, "train/loss": 0.8404059634399415, "eval/hcp-train-subset/loss": 0.8477106200110528, "eval/hcp-val/loss": 0.8428242975665677} +{"epoch": 19, "train/lr": 0.00011794882326980209, "train/grad": 0.06650032944367831, "train/loss": 0.8375672415161133, "eval/hcp-train-subset/loss": 0.8462256894957635, "eval/hcp-val/loss": 0.8417871267564835} +{"epoch": 20, "train/lr": 0.00011696520229374954, "train/grad": 0.06654471767501054, "train/loss": 0.8374385042667389, "eval/hcp-train-subset/loss": 0.8460128413092706, "eval/hcp-val/loss": 0.840875897676714} +{"epoch": 21, "train/lr": 0.00011592202441863837, "train/grad": 0.06650045098469767, "train/loss": 0.8365870004272461, "eval/hcp-train-subset/loss": 0.8449499434040438, "eval/hcp-val/loss": 0.8414429781898376} +{"epoch": 22, "train/lr": 0.00011482043034415979, "train/grad": 0.06802651463414891, "train/loss": 0.8358025500774383, "eval/hcp-train-subset/loss": 0.844341036773497, "eval/hcp-val/loss": 0.8403929462355952} +{"epoch": 23, "train/lr": 0.00011366162464726024, "train/grad": 0.06918541498343855, "train/loss": 0.8340182905864716, "eval/hcp-train-subset/loss": 0.8442633623077024, "eval/hcp-val/loss": 0.8402435760344228} +{"epoch": 24, "train/lr": 0.0001124468744649569, "train/grad": 0.06966296170055866, "train/loss": 0.8350737998580933, "eval/hcp-train-subset/loss": 0.8460729006798037, "eval/hcp-val/loss": 0.8408468317600989} +{"epoch": 25, "train/lr": 0.0001111775081087387, "train/grad": 0.06946272232391003, "train/loss": 0.8334357727622986, "eval/hcp-train-subset/loss": 0.8443779849237011, "eval/hcp-val/loss": 0.8399711030144845} +{"epoch": 26, "train/lr": 0.0001098549136120796, "train/grad": 0.06812945052645045, "train/loss": 0.8344582202339172, "eval/hcp-train-subset/loss": 0.8429928864202192, "eval/hcp-val/loss": 0.8388730873984676} +{"epoch": 27, "train/lr": 0.00010848053721264312, "train/grad": 0.06947359299375443, "train/loss": 0.8331948050022125, "eval/hcp-train-subset/loss": 0.8440266491905335, "eval/hcp-val/loss": 0.8393577548765367} +{"epoch": 28, "train/lr": 0.00010705588177084458, "train/grad": 0.07186732157079859, "train/loss": 0.831569600610733, "eval/hcp-train-subset/loss": 0.8439117948855123, "eval/hcp-val/loss": 0.8400714935794953} +{"epoch": 29, "train/lr": 0.00010558250512649171, "train/grad": 0.07114916361960216, "train/loss": 0.8313686544036866, "eval/hcp-train-subset/loss": 0.8416775532307164, "eval/hcp-val/loss": 0.8391392250214854} +{"epoch": 30, "train/lr": 0.00010406201839531515, "train/grad": 0.07215322960804904, "train/loss": 0.830041254234314, "eval/hcp-train-subset/loss": 0.8421879670312328, "eval/hcp-val/loss": 0.8385801671012756} +{"epoch": 31, "train/lr": 0.00010249608420723018, "train/grad": 0.07110813771910776, "train/loss": 0.832885725402832, "eval/hcp-train-subset/loss": 0.8405515378521334, "eval/hcp-val/loss": 0.8384491320579283} +{"epoch": 32, "train/lr": 0.00010088641488828097, "train/grad": 0.07258270405085039, "train/loss": 0.8323377115917205, "eval/hcp-train-subset/loss": 0.8415297779344744, "eval/hcp-val/loss": 0.839254460027141} +{"epoch": 33, "train/lr": 9.923477058823526e-05, "train/grad": 0.0739786816844086, "train/loss": 0.829475677318573, "eval/hcp-train-subset/loss": 0.8402350131542452, "eval/hcp-val/loss": 0.8386966961045419} +{"epoch": 34, "train/lr": 9.754295735588547e-05, "train/grad": 0.07661666538269973, "train/loss": 0.8290076809310913, "eval/hcp-train-subset/loss": 0.8394847973700492, "eval/hcp-val/loss": 0.8385512415439852} +{"epoch": 35, "train/lr": 9.581282516416285e-05, "train/grad": 0.07511238564519629, "train/loss": 0.8295481632900238, "eval/hcp-train-subset/loss": 0.8423168515005419, "eval/hcp-val/loss": 0.8394539375458995} +{"epoch": 36, "train/lr": 9.404626588721676e-05, "train/grad": 0.07623812691553015, "train/loss": 0.8265246430015564, "eval/hcp-train-subset/loss": 0.8406150552534288, "eval/hcp-val/loss": 0.8378722542716611} +{"epoch": 37, "train/lr": 9.224521123168153e-05, "train/grad": 0.07784975880414978, "train/loss": 0.8260462900066375, "eval/hcp-train-subset/loss": 0.8410384405043817, "eval/hcp-val/loss": 0.8379111982160999} +{"epoch": 38, "train/lr": 9.041163062437843e-05, "train/grad": 0.0778486668108396, "train/loss": 0.826598436832428, "eval/hcp-train-subset/loss": 0.8417733475085227, "eval/hcp-val/loss": 0.8383735985525193} +{"epoch": 39, "train/lr": 8.85475290587822e-05, "train/grad": 0.07730017374929568, "train/loss": 0.827218225364685, "eval/hcp-train-subset/loss": 0.8414719008630321, "eval/hcp-val/loss": 0.8388459470964247} +{"epoch": 40, "train/lr": 8.665494490258622e-05, "train/grad": 0.0798201887486963, "train/loss": 0.8254073515415191, "eval/hcp-train-subset/loss": 0.8405316164416652, "eval/hcp-val/loss": 0.8375941639946353} +{"epoch": 41, "train/lr": 8.473594766877838e-05, "train/grad": 0.07984961500134644, "train/loss": 0.8273792673110962, "eval/hcp-train-subset/loss": 0.8391068404720675, "eval/hcp-val/loss": 0.8375318877158626} +{"epoch": 42, "train/lr": 8.279263575265999e-05, "train/grad": 0.08207263725555757, "train/loss": 0.8253643847465515, "eval/hcp-train-subset/loss": 0.8384247508741194, "eval/hcp-val/loss": 0.8367192812504307} +{"epoch": 43, "train/lr": 8.082713413727944e-05, "train/grad": 0.08402318870301378, "train/loss": 0.82191746427536, "eval/hcp-train-subset/loss": 0.838308350693795, "eval/hcp-val/loss": 0.8372443366435266} +{"epoch": 44, "train/lr": 7.884159206979602e-05, "train/grad": 0.08313060573286707, "train/loss": 0.8255124870586396, "eval/hcp-train-subset/loss": 0.8383665132907129, "eval/hcp-val/loss": 0.8370202577883198} +{"epoch": 45, "train/lr": 7.683818071130916e-05, "train/grad": 0.0842109571912215, "train/loss": 0.8245022483730317, "eval/hcp-train-subset/loss": 0.838678632051714, "eval/hcp-val/loss": 0.8360604403480407} +{"epoch": 46, "train/lr": 7.481909076272522e-05, "train/grad": 0.08666292630978957, "train/loss": 0.8195172914886475, "eval/hcp-train-subset/loss": 0.8397912921444062, "eval/hcp-val/loss": 0.8368009261546596} +{"epoch": 47, "train/lr": 7.278653006925963e-05, "train/grad": 0.08455245475619841, "train/loss": 0.8260713587570191, "eval/hcp-train-subset/loss": 0.8383042485483231, "eval/hcp-val/loss": 0.8358542438476316} +{"epoch": 48, "train/lr": 7.074272120618864e-05, "train/grad": 0.08491540372512409, "train/loss": 0.8252328568935394, "eval/hcp-train-subset/loss": 0.8374591123673224, "eval/hcp-val/loss": 0.8366111363134077} +{"epoch": 49, "train/lr": 6.868989904849677e-05, "train/grad": 0.08832216614597356, "train/loss": 0.8221004347038269, "eval/hcp-train-subset/loss": 0.8379096148475524, "eval/hcp-val/loss": 0.835692040381893} +{"epoch": 50, "train/lr": 6.6630308327075e-05, "train/grad": 0.08910032644944228, "train/loss": 0.8233734031581879, "eval/hcp-train-subset/loss": 0.8384191739943719, "eval/hcp-val/loss": 0.8362608513524455} +{"epoch": 51, "train/lr": 6.456620117413798e-05, "train/grad": 0.0899894437269712, "train/loss": 0.8219389038467407, "eval/hcp-train-subset/loss": 0.8386052702703783, "eval/hcp-val/loss": 0.836193666342766} +{"epoch": 52, "train/lr": 6.249983466055255e-05, "train/grad": 0.09128973613550839, "train/loss": 0.8206843563556672, "eval/hcp-train-subset/loss": 0.8382875275227332, "eval/hcp-val/loss": 0.8367786176743046} +{"epoch": 53, "train/lr": 6.0433468327763305e-05, "train/grad": 0.09471053572636332, "train/loss": 0.8187176603507995, "eval/hcp-train-subset/loss": 0.836287175455401, "eval/hcp-val/loss": 0.8345623218244121} +{"epoch": 54, "train/lr": 5.83693617170174e-05, "train/grad": 0.09428825821410317, "train/loss": 0.8216660606384277, "eval/hcp-train-subset/loss": 0.8369483986208516, "eval/hcp-val/loss": 0.8351589633572486} +{"epoch": 55, "train/lr": 5.6309771898588165e-05, "train/grad": 0.09330243464754318, "train/loss": 0.8221987435722351, "eval/hcp-train-subset/loss": 0.8359322499844336, "eval/hcp-val/loss": 0.8343621857704655} +{"epoch": 56, "train/lr": 5.4256951003704155e-05, "train/grad": 0.09700704945782976, "train/loss": 0.8211495281028748, "eval/hcp-train-subset/loss": 0.83706158784128, "eval/hcp-val/loss": 0.834117240482761} +{"epoch": 57, "train/lr": 5.221314376187425e-05, "train/grad": 0.09972300574989448, "train/loss": 0.8185236590290069, "eval/hcp-train-subset/loss": 0.835242009931995, "eval/hcp-val/loss": 0.8342852073331033} +{"epoch": 58, "train/lr": 5.018058504631059e-05, "train/grad": 0.09971359983938012, "train/loss": 0.817264119234085, "eval/hcp-train-subset/loss": 0.8350418584962045, "eval/hcp-val/loss": 0.8336062162153183} +{"epoch": 59, "train/lr": 4.816149743012713e-05, "train/grad": 0.09936296246783681, "train/loss": 0.820180139760971, "eval/hcp-train-subset/loss": 0.834335042584327, "eval/hcp-val/loss": 0.8336176026252008} +{"epoch": 60, "train/lr": 4.615808875598772e-05, "train/grad": 0.09976787512556756, "train/loss": 0.8183381102371216, "eval/hcp-train-subset/loss": 0.8349751974305799, "eval/hcp-val/loss": 0.8339069975960639} +{"epoch": 61, "train/lr": 4.417254972186445e-05, "train/grad": 0.10442736927747727, "train/loss": 0.8169599151611329, "eval/hcp-train-subset/loss": 0.8334762213691589, "eval/hcp-val/loss": 0.8334436791558419} +{"epoch": 62, "train/lr": 4.220705148553925e-05, "train/grad": 0.10483007455809894, "train/loss": 0.8172924546337128, "eval/hcp-train-subset/loss": 0.834077101561331, "eval/hcp-val/loss": 0.8342440301372159} +{"epoch": 63, "train/lr": 4.026374329047657e-05, "train/grad": 0.10527037577329397, "train/loss": 0.819215121421814, "eval/hcp-train-subset/loss": 0.8331824156545824, "eval/hcp-val/loss": 0.8329504901363004} +{"epoch": 64, "train/lr": 3.834475011565652e-05, "train/grad": 0.10885144531412023, "train/loss": 0.8154851113033295, "eval/hcp-train-subset/loss": 0.8325067681650962, "eval/hcp-val/loss": 0.8340658939653828} +{"epoch": 65, "train/lr": 3.6452170351940815e-05, "train/grad": 0.11060739980733902, "train/loss": 0.8144065601730347, "eval/hcp-train-subset/loss": 0.8310420964994738, "eval/hcp-val/loss": 0.8331078079438978} +{"epoch": 66, "train/lr": 3.458807350751516e-05, "train/grad": 0.1113462867807136, "train/loss": 0.8137488618850708, "eval/hcp-train-subset/loss": 0.8297409069153571, "eval/hcp-val/loss": 0.8330242970297413} +{"epoch": 67, "train/lr": 3.2754497944910164e-05, "train/grad": 0.1119518103531148, "train/loss": 0.8153142554569245, "eval/hcp-train-subset/loss": 0.8288548665661966, "eval/hcp-val/loss": 0.8328403436368511} +{"epoch": 68, "train/lr": 3.0953448652083367e-05, "train/grad": 0.11333527591459995, "train/loss": 0.8148955133628846, "eval/hcp-train-subset/loss": 0.830704866878448, "eval/hcp-val/loss": 0.8326840592968848} +{"epoch": 69, "train/lr": 2.9186895049993948e-05, "train/grad": 0.11316557533909062, "train/loss": 0.8165231104660035, "eval/hcp-train-subset/loss": 0.8307270330767478, "eval/hcp-val/loss": 0.8325208569726636} +{"epoch": 70, "train/lr": 2.7456768839068717e-05, "train/grad": 0.11418936239045316, "train/loss": 0.8158973337173462, "eval/hcp-train-subset/loss": 0.8311303719397514, "eval/hcp-val/loss": 0.8326035795673248} +{"epoch": 71, "train/lr": 2.5764961886919063e-05, "train/grad": 0.12154169636532507, "train/loss": 0.8124763909339905, "eval/hcp-train-subset/loss": 0.8286006008425066, "eval/hcp-val/loss": 0.8323644611143297} +{"epoch": 72, "train/lr": 2.411332415960724e-05, "train/grad": 0.12051014783649869, "train/loss": 0.8122299294185639, "eval/hcp-train-subset/loss": 0.8290624608916621, "eval/hcp-val/loss": 0.8319394434652021} +{"epoch": 73, "train/lr": 2.2503661698739544e-05, "train/grad": 0.12226581564182049, "train/loss": 0.8122861870861053, "eval/hcp-train-subset/loss": 0.8270260710870067, "eval/hcp-val/loss": 0.831727550875756} +{"epoch": 74, "train/lr": 2.0937734646583902e-05, "train/grad": 0.12006066593408585, "train/loss": 0.814562677307129, "eval/hcp-train-subset/loss": 0.8266378650742192, "eval/hcp-val/loss": 0.8306513707483968} +{"epoch": 75, "train/lr": 1.9417255321381202e-05, "train/grad": 0.1265434565910229, "train/loss": 0.8123068084239959, "eval/hcp-train-subset/loss": 0.8272953283402228, "eval/hcp-val/loss": 0.8313470944281547} +{"epoch": 76, "train/lr": 1.7943886344950134e-05, "train/grad": 0.1280370644635777, "train/loss": 0.8103292639350891, "eval/hcp-train-subset/loss": 0.8267417271291057, "eval/hcp-val/loss": 0.8305954904325547} +{"epoch": 77, "train/lr": 1.651923882463461e-05, "train/grad": 0.1245711419287778, "train/loss": 0.8151434906101227, "eval/hcp-train-subset/loss": 0.8262601802426, "eval/hcp-val/loss": 0.8311254497497312} +{"epoch": 78, "train/lr": 1.5144870591581508e-05, "train/grad": 0.12798368287492948, "train/loss": 0.8138485295963287, "eval/hcp-train-subset/loss": 0.8247633066869551, "eval/hcp-val/loss": 0.830225182156409} +{"epoch": 79, "train/lr": 1.3822284497275662e-05, "train/grad": 0.1282058145991609, "train/loss": 0.8143136977005004, "eval/hcp-train-subset/loss": 0.823850417329419, "eval/hcp-val/loss": 0.8307239490170633} +{"epoch": 80, "train/lr": 1.2552926770192975e-05, "train/grad": 0.13156330983829972, "train/loss": 0.81359164560318, "eval/hcp-train-subset/loss": 0.8235173869517541, "eval/hcp-val/loss": 0.8309908441958889} +{"epoch": 81, "train/lr": 1.1338185434371453e-05, "train/grad": 0.13215525429421576, "train/loss": 0.8141100001525879, "eval/hcp-train-subset/loss": 0.8248640856435222, "eval/hcp-val/loss": 0.8302475194777211} +{"epoch": 82, "train/lr": 1.0179388791627326e-05, "train/grad": 0.13253694148717812, "train/loss": 0.8132099184703827, "eval/hcp-train-subset/loss": 0.8243265142363887, "eval/hcp-val/loss": 0.8299254303978335} +{"epoch": 83, "train/lr": 9.07780396907607e-06, "train/grad": 0.1321795500393904, "train/loss": 0.8141171507358551, "eval/hcp-train-subset/loss": 0.8238657761004663, "eval/hcp-val/loss": 0.829607016617252} +{"epoch": 84, "train/lr": 8.034635533547902e-06, "train/grad": 0.13574172383610747, "train/loss": 0.8135992841720581, "eval/hcp-train-subset/loss": 0.8230688014338093, "eval/hcp-val/loss": 0.8296980309870935} +{"epoch": 85, "train/lr": 7.051024174411275e-06, "train/grad": 0.13678116074875463, "train/loss": 0.8135245353889465, "eval/hcp-train-subset/loss": 0.8221701441272613, "eval/hcp-val/loss": 0.8293095346420042} +{"epoch": 86, "train/lr": 6.1280454562463606e-06, "train/grad": 0.14146084891973246, "train/loss": 0.8140101198387146, "eval/hcp-train-subset/loss": 0.8200483620166779, "eval/hcp-val/loss": 0.8292026144842948} +{"epoch": 87, "train/lr": 5.266708642730326e-06, "train/grad": 0.1366045283917257, "train/loss": 0.8161539752864838, "eval/hcp-train-subset/loss": 0.8203532647702002, "eval/hcp-val/loss": 0.8290616446925748} +{"epoch": 88, "train/lr": 4.467955593022733e-06, "train/grad": 0.13513098687663427, "train/loss": 0.8164604730701447, "eval/hcp-train-subset/loss": 0.819496403778753, "eval/hcp-val/loss": 0.8286778042393346} +{"epoch": 89, "train/lr": 3.732659731856291e-06, "train/grad": 0.14014696457903836, "train/loss": 0.813173850517273, "eval/hcp-train-subset/loss": 0.8190694682059749, "eval/hcp-val/loss": 0.828546259672411} +{"epoch": 90, "train/lr": 3.0616250944596583e-06, "train/grad": 0.1408195419644844, "train/loss": 0.8131461294364929, "eval/hcp-train-subset/loss": 0.8180731525344234, "eval/hcp-val/loss": 0.8283755894630186} +{"epoch": 91, "train/lr": 2.4555854473568305e-06, "train/grad": 0.14305208610886286, "train/loss": 0.8152698047828675, "eval/hcp-train-subset/loss": 0.8175976824375891, "eval/hcp-val/loss": 0.8282034550943682} +{"epoch": 92, "train/lr": 1.915203486004091e-06, "train/grad": 0.14489186121016975, "train/loss": 0.8137645604610443, "eval/hcp-train-subset/loss": 0.8173183356561968, "eval/hcp-val/loss": 0.8280147765913317} +{"epoch": 93, "train/lr": 1.4410701101423926e-06, "train/grad": 0.14769838935672933, "train/loss": 0.8143771920776367, "eval/hcp-train-subset/loss": 0.81681007819791, "eval/hcp-val/loss": 0.8279066056974472} +{"epoch": 94, "train/lr": 1.0337037776570775e-06, "train/grad": 0.14731661620685077, "train/loss": 0.8140349470710755, "eval/hcp-train-subset/loss": 0.8163719292609922, "eval/hcp-val/loss": 0.827634024043237} +{"epoch": 95, "train/lr": 6.935499376518293e-07, "train/grad": 0.14341514034938455, "train/loss": 0.8166788635540009, "eval/hcp-train-subset/loss": 0.8164511342202464, "eval/hcp-val/loss": 0.8272709038949781} +{"epoch": 96, "train/lr": 4.209805433566085e-07, "train/grad": 0.1486437248791092, "train/loss": 0.8162448957061768, "eval/hcp-train-subset/loss": 0.8157972020487632, "eval/hcp-val/loss": 0.8276174693338333} +{"epoch": 97, "train/lr": 2.1629364540224422e-07, "train/grad": 0.1522263638592919, "train/loss": 0.8167360429668427, "eval/hcp-train-subset/loss": 0.8155050623801446, "eval/hcp-val/loss": 0.8272189305674645} +{"epoch": 98, "train/lr": 7.971306590647406e-08, "train/grad": 0.15054466361300706, "train/loss": 0.8172342530155182, "eval/hcp-train-subset/loss": 0.8156726158434345, "eval/hcp-val/loss": 0.8273537851149037} +{"epoch": 99, "train/lr": 1.1388153727718725e-08, "train/grad": 0.15326722565389173, "train/loss": 0.8144631449127198, "eval/hcp-train-subset/loss": 0.81582308776917, "eval/hcp-val/loss": 0.8271719909483387} diff --git a/input_space_v3/flat_lr1e-3_5/pretrain/log.txt b/input_space_v3/flat_lr1e-3_5/pretrain/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..c39189053d28b855f4904d153841c2b4207cec3f --- /dev/null +++ b/input_space_v3/flat_lr1e-3_5/pretrain/log.txt @@ -0,0 +1,9153 @@ +pretraining fmri mae +start: 2026-04-01 11:59:15 +cwd: /data/connor/fmri-fm +sha: 7f4cedc35609f6857314e0d1ea6657523f17ddeb, status: has uncommitted changes, branch: dev/clane9 +config: +name: input_space_v3/flat_lr1e-3_5/pretrain +notes: input_space ablation v3 flat_lr1e-3_5; use tube masking and on-disk data (input_space=flat + base_lr=1e-3 seed=5405) +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain +input_space: flat +patch_size: 16 +num_frames: 16 +t_patch_size: 4 +mask_ratio: 0.9 +pred_mask_ratio: null +masking: tube +masking_kwargs: {} +mask_patch_size: null +model: mae_vit_base +model_kwargs: + decoding: attn + pos_embed: sep + target_norm: null + pca_norm_nc: 2 + t_pred_stride: 2 + no_decode_pos: true + mask_drop_scale: false + pred_edge_pad: 0 + gauss_sigma: null + class_token: true + reg_tokens: 0 + no_embed_class: true + head_init_scale: 0.0 + decoder_depth: 4 + drop_path_rate: 0.0 +datasets: + hcp-train: + type: wds + url: /data/fmri-datasets/pretrain/hcpya-all.${input_space}.wds/hcpya-all-${input_space}-{00000..01799}.tar + clipping: random + clipping_kwargs: + oversample: 4.0 + shuffle: true + buffer_size: 2000 + samples_per_epoch: 200000 + hcp-train-subset: + type: arrow + root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/validation + split_range: + - 0 + - 2000 + shuffle: false + hcp-val: + type: arrow + root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/test + split_range: + - 0 + - 2000 + shuffle: false +train_dataset: hcp-train +eval_datasets: +- hcp-train-subset +- hcp-val +val_dataset: null +clip_vmax: 3.0 +normalize: frame +tr_scale: null +crop_scale: null +crop_aspect: null +gray_jitter: null +num_workers: 16 +epochs: 100 +batch_size: 32 +accum_iter: 1 +base_lr: 0.001 +min_lr: 0.0 +warmup_epochs: 5 +weight_decay: 0.05 +betas: +- 0.9 +- 0.95 +clip_grad: 1.0 +amp: true +amp_dtype: float16 +ckpt: null +resume: true +auto_resume: true +start_epoch: 0 +max_checkpoints: 0 +checkpoint_period: null +plot_period: 5 +device: cuda +presend_cuda: false +seed: 5405 +debug: false +wandb: true +wandb_entity: null +wandb_project: fMRI-foundation-model +rank: 0 +world_size: 1 +gpu: 0 +distributed: true +dist_backend: nccl +in_chans: 1 +img_size: +- 224 +- 560 + +train transform: +Compose( + ToTensor() + TemporalCenterCrop(num_frames=16) + Normalize(mode='frame') + Clip(vmax=3.0) + FlatUnmask((224, 560)) +) +val transform: +Compose( + ToTensor() + TemporalCenterCrop(num_frames=16) + Normalize(mode='frame') + Clip(vmax=3.0) + FlatUnmask((224, 560)) +) +mask generator: +TubeMasking( + mask_ratio=0.9 + (patchify): Patchify2D((224, 560), (16, 16), in_chans=1) +) +loading dataset: hcp-train + +type: wds +url: /data/fmri-datasets/pretrain/hcpya-all.${input_space}.wds/hcpya-all-${input_space}-{00000..01799}.tar +clipping: random +clipping_kwargs: + oversample: 4.0 +shuffle: true +buffer_size: 2000 +samples_per_epoch: 200000 + +loading dataset: hcp-train-subset + +type: arrow +root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/validation +split_range: +- 0 +- 2000 +shuffle: false + +split indices: [899, 472, 767, 116, 1265, 1852, 300, 1335, 361, 1560] +loading dataset: hcp-val + +type: arrow +root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/test +split_range: +- 0 +- 2000 +shuffle: false + +split indices: [1075, 1189, 738, 1350, 965, 1964, 1367, 1183, 1619, 1407] +model: +MaskedAutoencoderViT( + decoding=attn, t_pred_stride=2, pred_edge_pad=0, no_decode_pos=True + (encoder): MaskedEncoder( + class_token=True, reg_tokens=0, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) + (pred_patchify): StridedPatchify3D((16, 224, 560), (2, 16, 16), in_chans=1, t_stride=2) + (decoder): MaskedDecoder( + cross_decode=False, class_token=True, no_embed_class=True + (pos_embed): SeparablePosEmbed(512, (4, 14, 35)) + (proj): Linear(in_features=768, out_features=512, bias=True) + (blocks): ModuleList( + (0-3): 4 x Block( + (norm1): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=16 + (q): Linear(in_features=512, out_features=512, bias=True) + (k): Linear(in_features=512, out_features=512, bias=True) + (v): Linear(in_features=512, out_features=512, bias=True) + (proj): Linear(in_features=512, out_features=512, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=512, out_features=2048, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=2048, out_features=512, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (head): Linear(in_features=512, out_features=512, bias=True) + ) +) +num params: 99.7M +total batch size: 32 = 32 bs per gpu x 1 accum x 1 gpus +lr: 1.25e-04 = 1.00e-03 x 32 / 256 +full schedule: epochs = 100 (steps = 625000) +warmup: epochs = 5 (steps = 31250) +start training for 100 epochs +Train: [0] [ 0/6250] eta: 21:26:07 lr: 0.000000 grad: 0.0196 (0.0196) loss: 0.9933 (0.9933) time: 12.3468 data: 10.5657 max mem: 8589 +Train: [0] [ 100/6250] eta: 0:31:18 lr: 0.000000 grad: 0.0137 (0.0163) loss: 0.9960 (0.9958) time: 0.2226 data: 0.1394 max mem: 9394 +Train: [0] [ 200/6250] eta: 0:27:31 lr: 0.000001 grad: 0.0128 (0.0149) loss: 0.9955 (0.9958) time: 0.4175 data: 0.3223 max mem: 9394 +Train: [0] [ 300/6250] eta: 0:25:15 lr: 0.000001 grad: 0.0120 (0.0142) loss: 0.9953 (0.9958) time: 0.2383 data: 0.1456 max mem: 9394 +Train: [0] [ 400/6250] eta: 0:24:11 lr: 0.000002 grad: 0.0130 (0.0139) loss: 0.9965 (0.9958) time: 0.1209 data: 0.0002 max mem: 9394 +Train: [0] [ 500/6250] eta: 0:24:31 lr: 0.000002 grad: 0.0129 (0.0137) loss: 0.9961 (0.9959) time: 0.3011 data: 0.1927 max mem: 9394 +Train: [0] [ 600/6250] eta: 0:23:54 lr: 0.000002 grad: 0.0128 (0.0136) loss: 0.9958 (0.9959) time: 0.2322 data: 0.1191 max mem: 9394 +Train: [0] [ 700/6250] eta: 0:22:59 lr: 0.000003 grad: 0.0126 (0.0135) loss: 0.9960 (0.9958) time: 0.2477 data: 0.1555 max mem: 9394 +Train: [0] [ 800/6250] eta: 0:22:59 lr: 0.000003 grad: 0.0131 (0.0134) loss: 0.9956 (0.9959) time: 0.3653 data: 0.2598 max mem: 9394 +Train: [0] [ 900/6250] eta: 0:21:59 lr: 0.000004 grad: 0.0130 (0.0134) loss: 0.9963 (0.9959) time: 0.2164 data: 0.1218 max mem: 9394 +Train: [0] [1000/6250] eta: 0:21:03 lr: 0.000004 grad: 0.0139 (0.0134) loss: 0.9961 (0.9959) time: 0.1784 data: 0.0672 max mem: 9394 +Train: [0] [1100/6250] eta: 0:20:26 lr: 0.000004 grad: 0.0132 (0.0134) loss: 0.9961 (0.9959) time: 0.2252 data: 0.1309 max mem: 9394 +Train: [0] [1200/6250] eta: 0:19:48 lr: 0.000005 grad: 0.0145 (0.0135) loss: 0.9958 (0.9959) time: 0.2812 data: 0.1736 max mem: 9394 +Train: [0] [1300/6250] eta: 0:18:58 lr: 0.000005 grad: 0.0185 (0.0138) loss: 0.9962 (0.9959) time: 0.1868 data: 0.0906 max mem: 9394 +Train: [0] [1400/6250] eta: 0:18:16 lr: 0.000006 grad: 0.0144 (0.0142) loss: 0.9955 (0.9959) time: 0.1754 data: 0.0962 max mem: 9394 +Train: [0] [1500/6250] eta: 0:17:44 lr: 0.000006 grad: 0.0243 (0.0146) loss: 0.9954 (0.9959) time: 0.1437 data: 0.0527 max mem: 9394 +Train: [0] [1600/6250] eta: 0:17:12 lr: 0.000006 grad: 0.0238 (0.0154) loss: 0.9951 (0.9958) time: 0.1206 data: 0.0167 max mem: 9394 +Train: [0] [1700/6250] eta: 0:16:45 lr: 0.000007 grad: 0.0290 (0.0164) loss: 0.9953 (0.9958) time: 0.1363 data: 0.0290 max mem: 9394 +Train: [0] [1800/6250] eta: 0:16:21 lr: 0.000007 grad: 0.0325 (0.0175) loss: 0.9956 (0.9958) time: 0.3287 data: 0.2137 max mem: 9394 +Train: [0] [1900/6250] eta: 0:15:43 lr: 0.000008 grad: 0.0480 (0.0192) loss: 0.9952 (0.9958) time: 0.1231 data: 0.0193 max mem: 9394 +Train: [0] [2000/6250] eta: 0:15:22 lr: 0.000008 grad: 0.0441 (0.0205) loss: 0.9948 (0.9957) time: 0.3634 data: 0.2292 max mem: 9394 +Train: [0] [2100/6250] eta: 0:14:47 lr: 0.000008 grad: 0.0405 (0.0218) loss: 0.9956 (0.9957) time: 0.1570 data: 0.0729 max mem: 9394 +Train: [0] [2200/6250] eta: 0:14:20 lr: 0.000009 grad: 0.0438 (0.0229) loss: 0.9945 (0.9957) time: 0.2337 data: 0.1493 max mem: 9394 +Train: [0] [2300/6250] eta: 0:13:58 lr: 0.000009 grad: 0.0568 (0.0241) loss: 0.9943 (0.9956) time: 0.3391 data: 0.2588 max mem: 9394 +Train: [0] [2400/6250] eta: 0:13:29 lr: 0.000010 grad: 0.0462 (0.0250) loss: 0.9943 (0.9956) time: 0.1616 data: 0.0685 max mem: 9394 +Train: [0] [2500/6250] eta: 0:13:07 lr: 0.000010 grad: 0.0430 (0.0260) loss: 0.9946 (0.9955) time: 0.2944 data: 0.1979 max mem: 9394 +Train: [0] [2600/6250] eta: 0:12:40 lr: 0.000010 grad: 0.0526 (0.0270) loss: 0.9935 (0.9955) time: 0.1433 data: 0.0338 max mem: 9394 +Train: [0] [2700/6250] eta: 0:12:19 lr: 0.000011 grad: 0.0427 (0.0279) loss: 0.9944 (0.9954) time: 0.1407 data: 0.0665 max mem: 9394 +Train: [0] [2800/6250] eta: 0:11:53 lr: 0.000011 grad: 0.0508 (0.0287) loss: 0.9944 (0.9954) time: 0.1850 data: 0.0913 max mem: 9394 +Train: [0] [2900/6250] eta: 0:11:30 lr: 0.000012 grad: 0.0560 (0.0296) loss: 0.9938 (0.9954) time: 0.1950 data: 0.1125 max mem: 9394 +Train: [0] [3000/6250] eta: 0:11:08 lr: 0.000012 grad: 0.0627 (0.0304) loss: 0.9936 (0.9953) time: 0.1134 data: 0.0003 max mem: 9394 +Train: [0] [3100/6250] eta: 0:10:45 lr: 0.000012 grad: 0.0516 (0.0312) loss: 0.9945 (0.9952) time: 0.1314 data: 0.0014 max mem: 9394 +Train: [0] [3200/6250] eta: 0:10:25 lr: 0.000013 grad: 0.0489 (0.0320) loss: 0.9937 (0.9952) time: 0.2530 data: 0.1681 max mem: 9394 +Train: [0] [3300/6250] eta: 0:10:01 lr: 0.000013 grad: 0.0639 (0.0330) loss: 0.9930 (0.9951) time: 0.1657 data: 0.0497 max mem: 9394 +Train: [0] [3400/6250] eta: 0:09:39 lr: 0.000014 grad: 0.0718 (0.0338) loss: 0.9927 (0.9951) time: 0.1877 data: 0.1090 max mem: 9394 +Train: [0] [3500/6250] eta: 0:09:19 lr: 0.000014 grad: 0.0543 (0.0345) loss: 0.9924 (0.9950) time: 0.2507 data: 0.1616 max mem: 9394 +Train: [0] [3600/6250] eta: 0:08:56 lr: 0.000014 grad: 0.0664 (0.0354) loss: 0.9914 (0.9949) time: 0.1716 data: 0.0811 max mem: 9394 +Train: [0] [3700/6250] eta: 0:08:35 lr: 0.000015 grad: 0.0568 (0.0365) loss: 0.9936 (0.9949) time: 0.1109 data: 0.0193 max mem: 9394 +Train: [0] [3800/6250] eta: 0:08:11 lr: 0.000015 grad: 0.0761 (0.0374) loss: 0.9916 (0.9948) time: 0.1781 data: 0.0807 max mem: 9394 +Train: [0] [3900/6250] eta: 0:07:49 lr: 0.000016 grad: 0.0783 (0.0385) loss: 0.9914 (0.9947) time: 0.1580 data: 0.0727 max mem: 9394 +Train: [0] [4000/6250] eta: 0:07:27 lr: 0.000016 grad: 0.0547 (0.0393) loss: 0.9920 (0.9946) time: 0.1492 data: 0.0588 max mem: 9394 +Train: [0] [4100/6250] eta: 0:07:05 lr: 0.000016 grad: 0.0712 (0.0400) loss: 0.9917 (0.9946) time: 0.1725 data: 0.0894 max mem: 9394 +Train: [0] [4200/6250] eta: 0:06:43 lr: 0.000017 grad: 0.0632 (0.0407) loss: 0.9911 (0.9945) time: 0.1750 data: 0.0925 max mem: 9394 +Train: [0] [4300/6250] eta: 0:06:23 lr: 0.000017 grad: 0.0642 (0.0414) loss: 0.9930 (0.9945) time: 0.2261 data: 0.1461 max mem: 9394 +Train: [0] [4400/6250] eta: 0:06:02 lr: 0.000018 grad: 0.0670 (0.0422) loss: 0.9922 (0.9944) time: 0.1734 data: 0.0917 max mem: 9394 +Train: [0] [4500/6250] eta: 0:05:42 lr: 0.000018 grad: 0.0681 (0.0429) loss: 0.9911 (0.9943) time: 0.1575 data: 0.0746 max mem: 9394 +Train: [0] [4600/6250] eta: 0:05:21 lr: 0.000018 grad: 0.0529 (0.0434) loss: 0.9935 (0.9943) time: 0.1457 data: 0.0586 max mem: 9394 +Train: [0] [4700/6250] eta: 0:05:01 lr: 0.000019 grad: 0.0729 (0.0440) loss: 0.9917 (0.9942) time: 0.1737 data: 0.0796 max mem: 9394 +Train: [0] [4800/6250] eta: 0:04:41 lr: 0.000019 grad: 0.0673 (0.0446) loss: 0.9917 (0.9942) time: 0.1647 data: 0.0778 max mem: 9394 +Train: [0] [4900/6250] eta: 0:04:21 lr: 0.000020 grad: 0.0607 (0.0452) loss: 0.9907 (0.9941) time: 0.1303 data: 0.0430 max mem: 9394 +Train: [0] [5000/6250] eta: 0:04:01 lr: 0.000020 grad: 0.0701 (0.0458) loss: 0.9916 (0.9940) time: 0.1759 data: 0.0868 max mem: 9394 +Train: [0] [5100/6250] eta: 0:03:42 lr: 0.000020 grad: 0.0657 (0.0463) loss: 0.9900 (0.9940) time: 0.1721 data: 0.0786 max mem: 9394 +Train: [0] [5200/6250] eta: 0:03:22 lr: 0.000021 grad: 0.0796 (0.0469) loss: 0.9898 (0.9939) time: 0.1556 data: 0.0619 max mem: 9394 +Train: [0] [5300/6250] eta: 0:03:02 lr: 0.000021 grad: 0.0600 (0.0474) loss: 0.9909 (0.9939) time: 0.1908 data: 0.1002 max mem: 9394 +Train: [0] [5400/6250] eta: 0:02:43 lr: 0.000022 grad: 0.0763 (0.0479) loss: 0.9898 (0.9938) time: 0.3041 data: 0.1917 max mem: 9394 +Train: [0] [5500/6250] eta: 0:02:24 lr: 0.000022 grad: 0.0620 (0.0484) loss: 0.9914 (0.9937) time: 0.1325 data: 0.0005 max mem: 9394 +Train: [0] [5600/6250] eta: 0:02:05 lr: 0.000022 grad: 0.0787 (0.0489) loss: 0.9882 (0.9937) time: 0.1546 data: 0.0673 max mem: 9394 +Train: [0] [5700/6250] eta: 0:01:45 lr: 0.000023 grad: 0.0789 (0.0494) loss: 0.9903 (0.9936) time: 0.2347 data: 0.1521 max mem: 9394 +Train: [0] [5800/6250] eta: 0:01:26 lr: 0.000023 grad: 0.0803 (0.0499) loss: 0.9912 (0.9936) time: 0.1714 data: 0.0783 max mem: 9394 +Train: [0] [5900/6250] eta: 0:01:07 lr: 0.000024 grad: 0.0683 (0.0503) loss: 0.9912 (0.9935) time: 0.1700 data: 0.0605 max mem: 9394 +Train: [0] [6000/6250] eta: 0:00:47 lr: 0.000024 grad: 0.0778 (0.0508) loss: 0.9911 (0.9934) time: 0.1784 data: 0.0854 max mem: 9394 +Train: [0] [6100/6250] eta: 0:00:28 lr: 0.000024 grad: 0.0726 (0.0512) loss: 0.9896 (0.9934) time: 0.1786 data: 0.1000 max mem: 9394 +Train: [0] [6200/6250] eta: 0:00:09 lr: 0.000025 grad: 0.0715 (0.0516) loss: 0.9904 (0.9933) time: 0.1702 data: 0.0907 max mem: 9394 +Train: [0] [6249/6250] eta: 0:00:00 lr: 0.000025 grad: 0.0863 (0.0519) loss: 0.9896 (0.9933) time: 0.1796 data: 0.0990 max mem: 9394 +Train: [0] Total time: 0:20:03 (0.1925 s / it) +Averaged stats: lr: 0.000025 grad: 0.0863 (0.0519) loss: 0.9896 (0.9933) +Eval (hcp-train-subset): [0] [ 0/62] eta: 0:04:03 loss: 0.9909 (0.9909) time: 3.9244 data: 3.8100 max mem: 9394 +Eval (hcp-train-subset): [0] [61/62] eta: 0:00:00 loss: 0.9920 (0.9929) time: 0.1160 data: 0.0861 max mem: 9394 +Eval (hcp-train-subset): [0] Total time: 0:00:14 (0.2278 s / it) +Averaged stats (hcp-train-subset): loss: 0.9920 (0.9929) +Eval (hcp-val): [0] [ 0/62] eta: 0:04:23 loss: 0.9888 (0.9888) time: 4.2548 data: 4.1797 max mem: 9394 +Eval (hcp-val): [0] [61/62] eta: 0:00:00 loss: 0.9923 (0.9914) time: 0.1258 data: 0.1003 max mem: 9394 +Eval (hcp-val): [0] Total time: 0:00:20 (0.3268 s / it) +Averaged stats (hcp-val): loss: 0.9923 (0.9914) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +Train: [1] [ 0/6250] eta: 7:16:39 lr: 0.000025 grad: 0.0880 (0.0880) loss: 0.9936 (0.9936) time: 4.1919 data: 3.9037 max mem: 9394 +Train: [1] [ 100/6250] eta: 0:22:56 lr: 0.000025 grad: 0.0658 (0.0814) loss: 0.9914 (0.9907) time: 0.1703 data: 0.0820 max mem: 9394 +Train: [1] [ 200/6250] eta: 0:20:46 lr: 0.000026 grad: 0.0799 (0.0835) loss: 0.9897 (0.9901) time: 0.1973 data: 0.1043 max mem: 9394 +Train: [1] [ 300/6250] eta: 0:19:38 lr: 0.000026 grad: 0.0884 (0.0874) loss: 0.9898 (0.9897) time: 0.1876 data: 0.0888 max mem: 9394 +Train: [1] [ 400/6250] eta: 0:18:43 lr: 0.000027 grad: 0.0879 (0.0883) loss: 0.9893 (0.9894) time: 0.1519 data: 0.0659 max mem: 9394 +Train: [1] [ 500/6250] eta: 0:18:22 lr: 0.000027 grad: 0.0786 (0.0880) loss: 0.9903 (0.9893) time: 0.1934 data: 0.0838 max mem: 9394 +Train: [1] [ 600/6250] eta: 0:18:14 lr: 0.000027 grad: 0.0792 (0.0876) loss: 0.9880 (0.9892) time: 0.1844 data: 0.0872 max mem: 9394 +Train: [1] [ 700/6250] eta: 0:18:00 lr: 0.000028 grad: 0.0873 (0.0878) loss: 0.9885 (0.9892) time: 0.1484 data: 0.0443 max mem: 9394 +Train: [1] [ 800/6250] eta: 0:18:03 lr: 0.000028 grad: 0.0707 (0.0871) loss: 0.9888 (0.9892) time: 0.1917 data: 0.0724 max mem: 9394 +Train: [1] [ 900/6250] eta: 0:18:18 lr: 0.000029 grad: 0.0809 (0.0872) loss: 0.9902 (0.9892) time: 0.2692 data: 0.1167 max mem: 9394 +Train: [1] [1000/6250] eta: 0:18:37 lr: 0.000029 grad: 0.0719 (0.0869) loss: 0.9892 (0.9891) time: 0.3163 data: 0.2059 max mem: 9394 +Train: [1] [1100/6250] eta: 0:18:06 lr: 0.000029 grad: 0.0766 (0.0864) loss: 0.9887 (0.9891) time: 0.2860 data: 0.1893 max mem: 9394 +Train: [1] [1200/6250] eta: 0:17:35 lr: 0.000030 grad: 0.0725 (0.0861) loss: 0.9878 (0.9891) time: 0.2711 data: 0.1814 max mem: 9394 +Train: [1] [1300/6250] eta: 0:17:09 lr: 0.000030 grad: 0.0817 (0.0860) loss: 0.9897 (0.9891) time: 0.3217 data: 0.2011 max mem: 9394 +Train: [1] [1400/6250] eta: 0:16:46 lr: 0.000031 grad: 0.0829 (0.0856) loss: 0.9898 (0.9891) time: 0.1301 data: 0.0003 max mem: 9394 +Train: [1] [1500/6250] eta: 0:16:23 lr: 0.000031 grad: 0.0663 (0.0851) loss: 0.9893 (0.9891) time: 0.3223 data: 0.2350 max mem: 9394 +Train: [1] [1600/6250] eta: 0:15:46 lr: 0.000031 grad: 0.0786 (0.0847) loss: 0.9884 (0.9890) time: 0.1825 data: 0.0956 max mem: 9394 +Train: [1] [1700/6250] eta: 0:15:25 lr: 0.000032 grad: 0.0795 (0.0845) loss: 0.9869 (0.9890) time: 0.1744 data: 0.0844 max mem: 9394 +Train: [1] [1800/6250] eta: 0:14:57 lr: 0.000032 grad: 0.0784 (0.0842) loss: 0.9888 (0.9890) time: 0.2052 data: 0.1051 max mem: 9394 +Train: [1] [1900/6250] eta: 0:14:40 lr: 0.000033 grad: 0.0921 (0.0840) loss: 0.9879 (0.9890) time: 0.2163 data: 0.1155 max mem: 9394 +Train: [1] [2000/6250] eta: 0:14:14 lr: 0.000033 grad: 0.0852 (0.0840) loss: 0.9856 (0.9889) time: 0.1902 data: 0.0954 max mem: 9394 +Train: [1] [2100/6250] eta: 0:13:46 lr: 0.000033 grad: 0.0748 (0.0840) loss: 0.9889 (0.9889) time: 0.1005 data: 0.0003 max mem: 9394 +Train: [1] [2200/6250] eta: 0:13:23 lr: 0.000034 grad: 0.0700 (0.0841) loss: 0.9885 (0.9888) time: 0.2062 data: 0.0881 max mem: 9394 +Train: [1] [2300/6250] eta: 0:13:14 lr: 0.000034 grad: 0.0775 (0.0841) loss: 0.9874 (0.9888) time: 0.1508 data: 0.0352 max mem: 9394 +Train: [1] [2400/6250] eta: 0:12:48 lr: 0.000035 grad: 0.0799 (0.0841) loss: 0.9878 (0.9887) time: 0.1752 data: 0.0856 max mem: 9394 +Train: [1] [2500/6250] eta: 0:12:23 lr: 0.000035 grad: 0.0819 (0.0841) loss: 0.9867 (0.9887) time: 0.1751 data: 0.0709 max mem: 9394 +Train: [1] [2600/6250] eta: 0:12:02 lr: 0.000035 grad: 0.0756 (0.0840) loss: 0.9885 (0.9887) time: 0.1619 data: 0.0712 max mem: 9394 +Train: [1] [2700/6250] eta: 0:11:46 lr: 0.000036 grad: 0.0723 (0.0841) loss: 0.9881 (0.9886) time: 0.1595 data: 0.0628 max mem: 9394 +Train: [1] [2800/6250] eta: 0:11:27 lr: 0.000036 grad: 0.0903 (0.0843) loss: 0.9871 (0.9885) time: 0.3359 data: 0.2169 max mem: 9394 +Train: [1] [2900/6250] eta: 0:11:04 lr: 0.000037 grad: 0.0819 (0.0843) loss: 0.9869 (0.9885) time: 0.1481 data: 0.0522 max mem: 9394 +Train: [1] [3000/6250] eta: 0:10:42 lr: 0.000037 grad: 0.0829 (0.0845) loss: 0.9893 (0.9884) time: 0.2100 data: 0.1104 max mem: 9394 +Train: [1] [3100/6250] eta: 0:10:20 lr: 0.000037 grad: 0.0730 (0.0845) loss: 0.9877 (0.9884) time: 0.1797 data: 0.0877 max mem: 9394 +Train: [1] [3200/6250] eta: 0:09:58 lr: 0.000038 grad: 0.0819 (0.0846) loss: 0.9865 (0.9884) time: 0.1521 data: 0.0397 max mem: 9394 +Train: [1] [3300/6250] eta: 0:09:37 lr: 0.000038 grad: 0.0899 (0.0847) loss: 0.9896 (0.9883) time: 0.1673 data: 0.0801 max mem: 9394 +Train: [1] [3400/6250] eta: 0:09:20 lr: 0.000039 grad: 0.0728 (0.0846) loss: 0.9889 (0.9883) time: 0.2900 data: 0.1668 max mem: 9394 +Train: [1] [3500/6250] eta: 0:08:57 lr: 0.000039 grad: 0.0852 (0.0845) loss: 0.9868 (0.9883) time: 0.1516 data: 0.0641 max mem: 9394 +Train: [1] [3600/6250] eta: 0:08:35 lr: 0.000039 grad: 0.0764 (0.0845) loss: 0.9872 (0.9883) time: 0.1672 data: 0.0767 max mem: 9394 +Train: [1] [3700/6250] eta: 0:08:14 lr: 0.000040 grad: 0.0720 (0.0844) loss: 0.9881 (0.9883) time: 0.1715 data: 0.0711 max mem: 9394 +Train: [1] [3800/6250] eta: 0:07:54 lr: 0.000040 grad: 0.0694 (0.0843) loss: 0.9900 (0.9883) time: 0.1459 data: 0.0325 max mem: 9394 +Train: [1] [3900/6250] eta: 0:07:34 lr: 0.000041 grad: 0.0712 (0.0843) loss: 0.9868 (0.9882) time: 0.1783 data: 0.0927 max mem: 9394 +Train: [1] [4000/6250] eta: 0:07:14 lr: 0.000041 grad: 0.0753 (0.0843) loss: 0.9863 (0.9882) time: 0.1475 data: 0.0563 max mem: 9394 +Train: [1] [4100/6250] eta: 0:06:54 lr: 0.000041 grad: 0.0730 (0.0842) loss: 0.9891 (0.9882) time: 0.1581 data: 0.0764 max mem: 9394 +Train: [1] [4200/6250] eta: 0:06:35 lr: 0.000042 grad: 0.0735 (0.0842) loss: 0.9876 (0.9882) time: 0.1057 data: 0.0153 max mem: 9394 +Train: [1] [4300/6250] eta: 0:06:15 lr: 0.000042 grad: 0.0713 (0.0842) loss: 0.9871 (0.9881) time: 0.1603 data: 0.0689 max mem: 9394 +Train: [1] [4400/6250] eta: 0:05:55 lr: 0.000043 grad: 0.0793 (0.0842) loss: 0.9881 (0.9881) time: 0.1874 data: 0.1083 max mem: 9394 +Train: [1] [4500/6250] eta: 0:05:36 lr: 0.000043 grad: 0.0806 (0.0843) loss: 0.9866 (0.9881) time: 0.1773 data: 0.0848 max mem: 9394 +Train: [1] [4600/6250] eta: 0:05:16 lr: 0.000043 grad: 0.0768 (0.0845) loss: 0.9874 (0.9881) time: 0.1916 data: 0.0949 max mem: 9394 +Train: [1] [4700/6250] eta: 0:04:57 lr: 0.000044 grad: 0.0786 (0.0845) loss: 0.9875 (0.9880) time: 0.2019 data: 0.1143 max mem: 9394 +Train: [1] [4800/6250] eta: 0:04:39 lr: 0.000044 grad: 0.0732 (0.0846) loss: 0.9859 (0.9880) time: 0.2072 data: 0.1017 max mem: 9394 +Train: [1] [4900/6250] eta: 0:04:21 lr: 0.000045 grad: 0.0813 (0.0846) loss: 0.9864 (0.9880) time: 0.3173 data: 0.2044 max mem: 9394 +Train: [1] [5000/6250] eta: 0:04:02 lr: 0.000045 grad: 0.0726 (0.0846) loss: 0.9877 (0.9880) time: 0.2116 data: 0.1138 max mem: 9394 +Train: [1] [5100/6250] eta: 0:03:42 lr: 0.000045 grad: 0.0758 (0.0845) loss: 0.9876 (0.9879) time: 0.1671 data: 0.0619 max mem: 9394 +Train: [1] [5200/6250] eta: 0:03:23 lr: 0.000046 grad: 0.0777 (0.0845) loss: 0.9870 (0.9879) time: 0.1345 data: 0.0540 max mem: 9394 +Train: [1] [5300/6250] eta: 0:03:03 lr: 0.000046 grad: 0.0812 (0.0845) loss: 0.9854 (0.9879) time: 0.1754 data: 0.0922 max mem: 9394 +Train: [1] [5400/6250] eta: 0:02:44 lr: 0.000047 grad: 0.0731 (0.0844) loss: 0.9868 (0.9879) time: 0.2259 data: 0.1504 max mem: 9394 +Train: [1] [5500/6250] eta: 0:02:25 lr: 0.000047 grad: 0.0806 (0.0844) loss: 0.9876 (0.9879) time: 0.1702 data: 0.0926 max mem: 9394 +Train: [1] [5600/6250] eta: 0:02:06 lr: 0.000047 grad: 0.0781 (0.0844) loss: 0.9865 (0.9878) time: 0.2153 data: 0.1286 max mem: 9394 +Train: [1] [5700/6250] eta: 0:01:47 lr: 0.000048 grad: 0.0811 (0.0843) loss: 0.9879 (0.9878) time: 0.2615 data: 0.1772 max mem: 9394 +Train: [1] [5800/6250] eta: 0:01:27 lr: 0.000048 grad: 0.0751 (0.0844) loss: 0.9865 (0.9878) time: 0.1245 data: 0.0354 max mem: 9394 +Train: [1] [5900/6250] eta: 0:01:08 lr: 0.000049 grad: 0.0689 (0.0843) loss: 0.9870 (0.9878) time: 0.1789 data: 0.0769 max mem: 9394 +Train: [1] [6000/6250] eta: 0:00:48 lr: 0.000049 grad: 0.0766 (0.0843) loss: 0.9863 (0.9877) time: 0.1547 data: 0.0599 max mem: 9394 +Train: [1] [6100/6250] eta: 0:00:29 lr: 0.000049 grad: 0.0796 (0.0843) loss: 0.9854 (0.9877) time: 0.2651 data: 0.1817 max mem: 9394 +Train: [1] [6200/6250] eta: 0:00:09 lr: 0.000050 grad: 0.0740 (0.0843) loss: 0.9872 (0.9877) time: 0.2391 data: 0.1520 max mem: 9394 +Train: [1] [6249/6250] eta: 0:00:00 lr: 0.000050 grad: 0.0762 (0.0843) loss: 0.9868 (0.9877) time: 0.3177 data: 0.2341 max mem: 9394 +Train: [1] Total time: 0:20:21 (0.1954 s / it) +Averaged stats: lr: 0.000050 grad: 0.0762 (0.0843) loss: 0.9868 (0.9877) +Eval (hcp-train-subset): [1] [ 0/62] eta: 0:04:34 loss: 0.9856 (0.9856) time: 4.4308 data: 4.3898 max mem: 9394 +Eval (hcp-train-subset): [1] [61/62] eta: 0:00:00 loss: 0.9895 (0.9891) time: 0.1560 data: 0.1307 max mem: 9394 +Eval (hcp-train-subset): [1] Total time: 0:00:14 (0.2261 s / it) +Averaged stats (hcp-train-subset): loss: 0.9895 (0.9891) +Eval (hcp-val): [1] [ 0/62] eta: 0:03:03 loss: 0.9832 (0.9832) time: 2.9655 data: 2.8872 max mem: 9394 +Eval (hcp-val): [1] [61/62] eta: 0:00:00 loss: 0.9878 (0.9874) time: 0.1346 data: 0.1097 max mem: 9394 +Eval (hcp-val): [1] Total time: 0:00:15 (0.2497 s / it) +Averaged stats (hcp-val): loss: 0.9878 (0.9874) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +Train: [2] [ 0/6250] eta: 11:20:31 lr: 0.000050 grad: 0.0724 (0.0724) loss: 0.9914 (0.9914) time: 6.5331 data: 6.4358 max mem: 9394 +Train: [2] [ 100/6250] eta: 0:25:45 lr: 0.000050 grad: 0.0856 (0.0904) loss: 0.9849 (0.9866) time: 0.1693 data: 0.0404 max mem: 9394 +Train: [2] [ 200/6250] eta: 0:21:25 lr: 0.000051 grad: 0.0778 (0.0882) loss: 0.9879 (0.9866) time: 0.1596 data: 0.0753 max mem: 9394 +Train: [2] [ 300/6250] eta: 0:19:30 lr: 0.000051 grad: 0.0826 (0.0886) loss: 0.9873 (0.9865) time: 0.1717 data: 0.0788 max mem: 9394 +Train: [2] [ 400/6250] eta: 0:18:31 lr: 0.000052 grad: 0.0782 (0.0887) loss: 0.9865 (0.9861) time: 0.1622 data: 0.0602 max mem: 9394 +Train: [2] [ 500/6250] eta: 0:17:59 lr: 0.000052 grad: 0.0748 (0.0883) loss: 0.9858 (0.9860) time: 0.1881 data: 0.0920 max mem: 9394 +Train: [2] [ 600/6250] eta: 0:18:06 lr: 0.000052 grad: 0.0726 (0.0875) loss: 0.9854 (0.9860) time: 0.2466 data: 0.1355 max mem: 9394 +Train: [2] [ 700/6250] eta: 0:18:02 lr: 0.000053 grad: 0.0712 (0.0867) loss: 0.9868 (0.9860) time: 0.2026 data: 0.1103 max mem: 9394 +Train: [2] [ 800/6250] eta: 0:18:08 lr: 0.000053 grad: 0.0714 (0.0852) loss: 0.9866 (0.9862) time: 0.3567 data: 0.2204 max mem: 9394 +Train: [2] [ 900/6250] eta: 0:18:03 lr: 0.000054 grad: 0.0819 (0.0847) loss: 0.9858 (0.9863) time: 0.2126 data: 0.1049 max mem: 9394 +Train: [2] [1000/6250] eta: 0:18:01 lr: 0.000054 grad: 0.0734 (0.0845) loss: 0.9874 (0.9863) time: 0.1209 data: 0.0057 max mem: 9394 +Train: [2] [1100/6250] eta: 0:17:37 lr: 0.000054 grad: 0.0844 (0.0838) loss: 0.9862 (0.9864) time: 0.2044 data: 0.0978 max mem: 9394 +Train: [2] [1200/6250] eta: 0:17:09 lr: 0.000055 grad: 0.0779 (0.0837) loss: 0.9837 (0.9863) time: 0.2468 data: 0.1195 max mem: 9394 +Train: [2] [1300/6250] eta: 0:16:50 lr: 0.000055 grad: 0.0803 (0.0831) loss: 0.9841 (0.9864) time: 0.1068 data: 0.0003 max mem: 9394 +Train: [2] [1400/6250] eta: 0:16:20 lr: 0.000056 grad: 0.0731 (0.0827) loss: 0.9854 (0.9864) time: 0.1481 data: 0.0592 max mem: 9394 +Train: [2] [1500/6250] eta: 0:15:57 lr: 0.000056 grad: 0.0761 (0.0824) loss: 0.9855 (0.9864) time: 0.1851 data: 0.0615 max mem: 9394 +Train: [2] [1600/6250] eta: 0:15:41 lr: 0.000056 grad: 0.0705 (0.0823) loss: 0.9873 (0.9864) time: 0.3991 data: 0.3114 max mem: 9394 +Train: [2] [1700/6250] eta: 0:15:09 lr: 0.000057 grad: 0.0774 (0.0824) loss: 0.9861 (0.9863) time: 0.1514 data: 0.0539 max mem: 9394 +Train: [2] [1800/6250] eta: 0:14:53 lr: 0.000057 grad: 0.0753 (0.0823) loss: 0.9884 (0.9863) time: 0.1523 data: 0.0390 max mem: 9394 +Train: [2] [1900/6250] eta: 0:14:26 lr: 0.000058 grad: 0.0774 (0.0823) loss: 0.9853 (0.9863) time: 0.1850 data: 0.0883 max mem: 9394 +Train: [2] [2000/6250] eta: 0:13:59 lr: 0.000058 grad: 0.0884 (0.0825) loss: 0.9851 (0.9863) time: 0.1835 data: 0.0965 max mem: 9394 +Train: [2] [2100/6250] eta: 0:13:44 lr: 0.000058 grad: 0.0799 (0.0828) loss: 0.9874 (0.9863) time: 0.3033 data: 0.2113 max mem: 9394 +Train: [2] [2200/6250] eta: 0:13:19 lr: 0.000059 grad: 0.0747 (0.0828) loss: 0.9871 (0.9862) time: 0.1641 data: 0.0647 max mem: 9394 +Train: [2] [2300/6250] eta: 0:13:01 lr: 0.000059 grad: 0.0752 (0.0828) loss: 0.9869 (0.9862) time: 0.2858 data: 0.1791 max mem: 9394 +Train: [2] [2400/6250] eta: 0:12:46 lr: 0.000060 grad: 0.0818 (0.0830) loss: 0.9870 (0.9863) time: 0.3650 data: 0.2479 max mem: 9394 +Train: [2] [2500/6250] eta: 0:12:19 lr: 0.000060 grad: 0.0717 (0.0830) loss: 0.9844 (0.9862) time: 0.1741 data: 0.0814 max mem: 9394 +Train: [2] [2600/6250] eta: 0:11:56 lr: 0.000060 grad: 0.0763 (0.0829) loss: 0.9858 (0.9863) time: 0.1814 data: 0.0909 max mem: 9394 +Train: [2] [2700/6250] eta: 0:11:41 lr: 0.000061 grad: 0.0780 (0.0829) loss: 0.9864 (0.9863) time: 0.4014 data: 0.2936 max mem: 9394 +Train: [2] [2800/6250] eta: 0:11:19 lr: 0.000061 grad: 0.0799 (0.0828) loss: 0.9853 (0.9862) time: 0.1500 data: 0.0524 max mem: 9394 +Train: [2] [2900/6250] eta: 0:10:58 lr: 0.000062 grad: 0.0790 (0.0827) loss: 0.9872 (0.9862) time: 0.2677 data: 0.1741 max mem: 9394 +Train: [2] [3000/6250] eta: 0:10:34 lr: 0.000062 grad: 0.0799 (0.0829) loss: 0.9852 (0.9862) time: 0.1593 data: 0.0518 max mem: 9394 +Train: [2] [3100/6250] eta: 0:10:15 lr: 0.000062 grad: 0.0752 (0.0830) loss: 0.9855 (0.9862) time: 0.2241 data: 0.1386 max mem: 9394 +Train: [2] [3200/6250] eta: 0:09:54 lr: 0.000063 grad: 0.0769 (0.0830) loss: 0.9850 (0.9862) time: 0.1945 data: 0.1083 max mem: 9394 +Train: [2] [3300/6250] eta: 0:09:33 lr: 0.000063 grad: 0.0840 (0.0830) loss: 0.9858 (0.9862) time: 0.2047 data: 0.0991 max mem: 9394 +Train: [2] [3400/6250] eta: 0:09:12 lr: 0.000064 grad: 0.0877 (0.0831) loss: 0.9862 (0.9861) time: 0.1952 data: 0.1032 max mem: 9394 +Train: [2] [3500/6250] eta: 0:08:53 lr: 0.000064 grad: 0.0920 (0.0834) loss: 0.9864 (0.9861) time: 0.2996 data: 0.1992 max mem: 9394 +Train: [2] [3600/6250] eta: 0:08:31 lr: 0.000064 grad: 0.0854 (0.0835) loss: 0.9869 (0.9861) time: 0.1422 data: 0.0475 max mem: 9394 +Train: [2] [3700/6250] eta: 0:08:12 lr: 0.000065 grad: 0.0761 (0.0836) loss: 0.9856 (0.9860) time: 0.2514 data: 0.1692 max mem: 9394 +Train: [2] [3800/6250] eta: 0:07:51 lr: 0.000065 grad: 0.0869 (0.0838) loss: 0.9855 (0.9860) time: 0.1898 data: 0.0966 max mem: 9394 +Train: [2] [3900/6250] eta: 0:07:32 lr: 0.000066 grad: 0.0856 (0.0840) loss: 0.9826 (0.9859) time: 0.1125 data: 0.0267 max mem: 9394 +Train: [2] [4000/6250] eta: 0:07:12 lr: 0.000066 grad: 0.0909 (0.0841) loss: 0.9850 (0.9859) time: 0.1804 data: 0.0720 max mem: 9394 +Train: [2] [4100/6250] eta: 0:06:53 lr: 0.000066 grad: 0.1031 (0.0846) loss: 0.9843 (0.9858) time: 0.1437 data: 0.0301 max mem: 9394 +Train: [2] [4200/6250] eta: 0:06:33 lr: 0.000067 grad: 0.0788 (0.0848) loss: 0.9861 (0.9858) time: 0.1659 data: 0.0654 max mem: 9394 +Train: [2] [4300/6250] eta: 0:06:13 lr: 0.000067 grad: 0.0873 (0.0853) loss: 0.9850 (0.9858) time: 0.1767 data: 0.0908 max mem: 9394 +Train: [2] [4400/6250] eta: 0:05:54 lr: 0.000068 grad: 0.0916 (0.0856) loss: 0.9849 (0.9858) time: 0.2227 data: 0.1423 max mem: 9394 +Train: [2] [4500/6250] eta: 0:05:33 lr: 0.000068 grad: 0.0891 (0.0859) loss: 0.9862 (0.9858) time: 0.1283 data: 0.0329 max mem: 9394 +Train: [2] [4600/6250] eta: 0:05:14 lr: 0.000068 grad: 0.0860 (0.0863) loss: 0.9848 (0.9857) time: 0.1872 data: 0.1002 max mem: 9394 +Train: [2] [4700/6250] eta: 0:04:55 lr: 0.000069 grad: 0.0906 (0.0866) loss: 0.9841 (0.9857) time: 0.1824 data: 0.1009 max mem: 9394 +Train: [2] [4800/6250] eta: 0:04:36 lr: 0.000069 grad: 0.0972 (0.0872) loss: 0.9836 (0.9856) time: 0.1676 data: 0.0800 max mem: 9394 +Train: [2] [4900/6250] eta: 0:04:16 lr: 0.000070 grad: 0.1054 (0.0878) loss: 0.9843 (0.9856) time: 0.1779 data: 0.0934 max mem: 9394 +Train: [2] [5000/6250] eta: 0:03:58 lr: 0.000070 grad: 0.0927 (0.0884) loss: 0.9847 (0.9855) time: 0.1856 data: 0.0978 max mem: 9394 +Train: [2] [5100/6250] eta: 0:03:39 lr: 0.000070 grad: 0.1059 (0.0892) loss: 0.9836 (0.9855) time: 0.2256 data: 0.1383 max mem: 9394 +Train: [2] [5200/6250] eta: 0:03:20 lr: 0.000071 grad: 0.1240 (0.0900) loss: 0.9833 (0.9855) time: 0.1388 data: 0.0380 max mem: 9394 +Train: [2] [5300/6250] eta: 0:03:02 lr: 0.000071 grad: 0.1920 (0.0916) loss: 0.9826 (0.9854) time: 0.5363 data: 0.4238 max mem: 9394 +Train: [2] [5400/6250] eta: 0:02:42 lr: 0.000072 grad: 0.2256 (0.0937) loss: 0.9829 (0.9853) time: 0.2001 data: 0.1053 max mem: 9394 +Train: [2] [5500/6250] eta: 0:02:24 lr: 0.000072 grad: 0.1212 (0.0952) loss: 0.9801 (0.9853) time: 0.1651 data: 0.0678 max mem: 9394 +Train: [2] [5600/6250] eta: 0:02:05 lr: 0.000072 grad: 0.1909 (0.0974) loss: 0.9839 (0.9852) time: 0.3747 data: 0.2103 max mem: 9394 +Train: [2] [5700/6250] eta: 0:01:46 lr: 0.000073 grad: 0.1494 (0.0994) loss: 0.9845 (0.9852) time: 0.2334 data: 0.1200 max mem: 9394 +Train: [2] [5800/6250] eta: 0:01:27 lr: 0.000073 grad: 0.1218 (0.1007) loss: 0.9820 (0.9851) time: 0.1721 data: 0.0702 max mem: 9394 +Train: [2] [5900/6250] eta: 0:01:08 lr: 0.000074 grad: 0.1961 (0.1027) loss: 0.9813 (0.9851) time: 0.4078 data: 0.2773 max mem: 9394 +Train: [2] [6000/6250] eta: 0:00:48 lr: 0.000074 grad: 0.1165 (0.1043) loss: 0.9822 (0.9851) time: 0.1916 data: 0.0912 max mem: 9394 +Train: [2] [6100/6250] eta: 0:00:29 lr: 0.000074 grad: 0.1993 (0.1060) loss: 0.9832 (0.9850) time: 0.2352 data: 0.1254 max mem: 9394 +Train: [2] [6200/6250] eta: 0:00:09 lr: 0.000075 grad: 0.1550 (0.1072) loss: 0.9820 (0.9850) time: 0.3995 data: 0.3055 max mem: 9394 +Train: [2] [6249/6250] eta: 0:00:00 lr: 0.000075 grad: 0.1800 (0.1082) loss: 0.9802 (0.9850) time: 0.3176 data: 0.2269 max mem: 9394 +Train: [2] Total time: 0:20:26 (0.1963 s / it) +Averaged stats: lr: 0.000075 grad: 0.1800 (0.1082) loss: 0.9802 (0.9850) +Eval (hcp-train-subset): [2] [ 0/62] eta: 0:03:45 loss: 0.9802 (0.9802) time: 3.6383 data: 3.5554 max mem: 9394 +Eval (hcp-train-subset): [2] [61/62] eta: 0:00:00 loss: 0.9832 (0.9835) time: 0.1417 data: 0.1169 max mem: 9394 +Eval (hcp-train-subset): [2] Total time: 0:00:13 (0.2225 s / it) +Averaged stats (hcp-train-subset): loss: 0.9832 (0.9835) +Eval (hcp-val): [2] [ 0/62] eta: 0:03:04 loss: 0.9772 (0.9772) time: 2.9747 data: 2.9152 max mem: 9394 +Eval (hcp-val): [2] [61/62] eta: 0:00:00 loss: 0.9810 (0.9815) time: 0.1484 data: 0.1215 max mem: 9394 +Eval (hcp-val): [2] Total time: 0:00:13 (0.2211 s / it) +Averaged stats (hcp-val): loss: 0.9810 (0.9815) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +Train: [3] [ 0/6250] eta: 9:32:30 lr: 0.000075 grad: 0.0508 (0.0508) loss: 0.9834 (0.9834) time: 5.4961 data: 5.3325 max mem: 9394 +Train: [3] [ 100/6250] eta: 0:22:56 lr: 0.000075 grad: 0.1715 (0.1822) loss: 0.9820 (0.9830) time: 0.1758 data: 0.0817 max mem: 9394 +Train: [3] [ 200/6250] eta: 0:20:13 lr: 0.000076 grad: 0.1677 (0.2081) loss: 0.9826 (0.9823) time: 0.1776 data: 0.0808 max mem: 9394 +Train: [3] [ 300/6250] eta: 0:19:19 lr: 0.000076 grad: 0.1301 (0.2053) loss: 0.9834 (0.9821) time: 0.1808 data: 0.0931 max mem: 9394 +Train: [3] [ 400/6250] eta: 0:18:46 lr: 0.000077 grad: 0.1814 (0.2059) loss: 0.9809 (0.9817) time: 0.1701 data: 0.0835 max mem: 9394 +Train: [3] [ 500/6250] eta: 0:18:08 lr: 0.000077 grad: 0.1066 (0.2002) loss: 0.9821 (0.9815) time: 0.1960 data: 0.1079 max mem: 9394 +Train: [3] [ 600/6250] eta: 0:17:33 lr: 0.000077 grad: 0.1452 (0.1975) loss: 0.9803 (0.9813) time: 0.1704 data: 0.0757 max mem: 9394 +Train: [3] [ 700/6250] eta: 0:17:08 lr: 0.000078 grad: 0.2140 (0.2007) loss: 0.9811 (0.9811) time: 0.1862 data: 0.0887 max mem: 9394 +Train: [3] [ 800/6250] eta: 0:16:39 lr: 0.000078 grad: 0.1548 (0.2011) loss: 0.9810 (0.9813) time: 0.1766 data: 0.0756 max mem: 9394 +Train: [3] [ 900/6250] eta: 0:16:19 lr: 0.000079 grad: 0.2247 (0.2011) loss: 0.9792 (0.9811) time: 0.1796 data: 0.0888 max mem: 9394 +Train: [3] [1000/6250] eta: 0:15:58 lr: 0.000079 grad: 0.2367 (0.2027) loss: 0.9786 (0.9810) time: 0.1757 data: 0.0847 max mem: 9394 +Train: [3] [1100/6250] eta: 0:15:42 lr: 0.000079 grad: 0.1942 (0.2037) loss: 0.9794 (0.9808) time: 0.2081 data: 0.1248 max mem: 9394 +Train: [3] [1200/6250] eta: 0:15:25 lr: 0.000080 grad: 0.1726 (0.2041) loss: 0.9792 (0.9807) time: 0.2147 data: 0.0937 max mem: 9394 +pretraining fmri mae +start: 2026-04-01 13:11:27 +cwd: /data/connor/fmri-fm +sha: 7f4cedc35609f6857314e0d1ea6657523f17ddeb, status: has uncommitted changes, branch: dev/clane9 +config: +name: input_space_v3/flat_lr1e-3_5/pretrain +notes: input_space ablation v3 flat_lr1e-3_5; use tube masking and on-disk data (input_space=flat + base_lr=1e-3 seed=5405) +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain +input_space: flat +patch_size: 16 +num_frames: 16 +t_patch_size: 4 +mask_ratio: 0.9 +pred_mask_ratio: null +masking: tube +masking_kwargs: {} +mask_patch_size: null +model: mae_vit_base +model_kwargs: + decoding: attn + pos_embed: sep + target_norm: null + pca_norm_nc: 2 + t_pred_stride: 2 + no_decode_pos: true + mask_drop_scale: false + pred_edge_pad: 0 + gauss_sigma: null + class_token: true + reg_tokens: 0 + no_embed_class: true + head_init_scale: 0.0 + decoder_depth: 4 + drop_path_rate: 0.0 +datasets: + hcp-train: + type: wds + url: /data/fmri-datasets/pretrain/hcpya-all.${input_space}.wds/hcpya-all-${input_space}-{00000..01799}.tar + clipping: random + clipping_kwargs: + oversample: 4.0 + shuffle: true + buffer_size: 2000 + samples_per_epoch: 200000 + hcp-train-subset: + type: arrow + root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/validation + split_range: + - 0 + - 2000 + shuffle: false + hcp-val: + type: arrow + root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/test + split_range: + - 0 + - 2000 + shuffle: false +train_dataset: hcp-train +eval_datasets: +- hcp-train-subset +- hcp-val +val_dataset: null +clip_vmax: 3.0 +normalize: frame +tr_scale: null +crop_scale: null +crop_aspect: null +gray_jitter: null +num_workers: 16 +epochs: 100 +batch_size: 32 +accum_iter: 1 +base_lr: 0.001 +min_lr: 0.0 +warmup_epochs: 5 +weight_decay: 0.05 +betas: +- 0.9 +- 0.95 +clip_grad: 1.0 +amp: true +amp_dtype: float16 +ckpt: null +resume: true +auto_resume: true +start_epoch: 0 +max_checkpoints: 0 +checkpoint_period: null +plot_period: 5 +device: cuda +presend_cuda: false +seed: 5405 +debug: false +wandb: true +wandb_entity: null +wandb_project: fMRI-foundation-model +rank: 0 +world_size: 1 +gpu: 0 +distributed: true +dist_backend: nccl +in_chans: 1 +img_size: +- 224 +- 560 + +train transform: +Compose( + ToTensor() + TemporalCenterCrop(num_frames=16) + Normalize(mode='frame') + Clip(vmax=3.0) + FlatUnmask((224, 560)) +) +val transform: +Compose( + ToTensor() + TemporalCenterCrop(num_frames=16) + Normalize(mode='frame') + Clip(vmax=3.0) + FlatUnmask((224, 560)) +) +mask generator: +TubeMasking( + mask_ratio=0.9 + (patchify): Patchify2D((224, 560), (16, 16), in_chans=1) +) +loading dataset: hcp-train + +type: wds +url: /data/fmri-datasets/pretrain/hcpya-all.${input_space}.wds/hcpya-all-${input_space}-{00000..01799}.tar +clipping: random +clipping_kwargs: + oversample: 4.0 +shuffle: true +buffer_size: 2000 +samples_per_epoch: 200000 + +loading dataset: hcp-train-subset + +type: arrow +root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/validation +split_range: +- 0 +- 2000 +shuffle: false + +split indices: [899, 472, 767, 116, 1265, 1852, 300, 1335, 361, 1560] +loading dataset: hcp-val + +type: arrow +root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/test +split_range: +- 0 +- 2000 +shuffle: false + +split indices: [1075, 1189, 738, 1350, 965, 1964, 1367, 1183, 1619, 1407] +model: +MaskedAutoencoderViT( + decoding=attn, t_pred_stride=2, pred_edge_pad=0, no_decode_pos=True + (encoder): MaskedEncoder( + class_token=True, reg_tokens=0, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) + (pred_patchify): StridedPatchify3D((16, 224, 560), (2, 16, 16), in_chans=1, t_stride=2) + (decoder): MaskedDecoder( + cross_decode=False, class_token=True, no_embed_class=True + (pos_embed): SeparablePosEmbed(512, (4, 14, 35)) + (proj): Linear(in_features=768, out_features=512, bias=True) + (blocks): ModuleList( + (0-3): 4 x Block( + (norm1): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=16 + (q): Linear(in_features=512, out_features=512, bias=True) + (k): Linear(in_features=512, out_features=512, bias=True) + (v): Linear(in_features=512, out_features=512, bias=True) + (proj): Linear(in_features=512, out_features=512, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=512, out_features=2048, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=2048, out_features=512, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (head): Linear(in_features=512, out_features=512, bias=True) + ) +) +num params: 99.7M +total batch size: 32 = 32 bs per gpu x 1 accum x 1 gpus +lr: 1.25e-04 = 1.00e-03 x 32 / 256 +full schedule: epochs = 100 (steps = 625000) +warmup: epochs = 5 (steps = 31250) +loaded model state from checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +loaded optimizer state, resuming training from 3 +start training for 100 epochs +Train: [3] [ 0/6250] eta: 17:21:15 lr: 0.000075 grad: 0.2764 (0.2764) loss: 0.9742 (0.9742) time: 9.9961 data: 9.0536 max mem: 9353 +Train: [3] [ 100/6250] eta: 0:25:21 lr: 0.000075 grad: 0.1809 (0.2207) loss: 0.9826 (0.9809) time: 0.1545 data: 0.0638 max mem: 9390 +Train: [3] [ 200/6250] eta: 0:20:30 lr: 0.000076 grad: 0.1377 (0.2183) loss: 0.9788 (0.9807) time: 0.1638 data: 0.0750 max mem: 9390 +Train: [3] [ 300/6250] eta: 0:19:18 lr: 0.000076 grad: 0.1649 (0.2082) loss: 0.9815 (0.9808) time: 0.2092 data: 0.1290 max mem: 9390 +Train: [3] [ 400/6250] eta: 0:18:07 lr: 0.000077 grad: 0.1569 (0.2032) loss: 0.9826 (0.9811) time: 0.1503 data: 0.0559 max mem: 9390 +Train: [3] [ 500/6250] eta: 0:17:35 lr: 0.000077 grad: 0.2537 (0.2056) loss: 0.9815 (0.9813) time: 0.1579 data: 0.0781 max mem: 9390 +Train: [3] [ 600/6250] eta: 0:17:10 lr: 0.000077 grad: 0.1306 (0.2009) loss: 0.9821 (0.9812) time: 0.1922 data: 0.1073 max mem: 9390 +Train: [3] [ 700/6250] eta: 0:16:37 lr: 0.000078 grad: 0.2279 (0.2020) loss: 0.9825 (0.9812) time: 0.1560 data: 0.0663 max mem: 9390 +Train: [3] [ 800/6250] eta: 0:16:13 lr: 0.000078 grad: 0.2485 (0.2041) loss: 0.9827 (0.9812) time: 0.1770 data: 0.0951 max mem: 9390 +Train: [3] [ 900/6250] eta: 0:15:45 lr: 0.000079 grad: 0.1905 (0.2029) loss: 0.9823 (0.9812) time: 0.1388 data: 0.0538 max mem: 9390 +Train: [3] [1000/6250] eta: 0:15:22 lr: 0.000079 grad: 0.1752 (0.2035) loss: 0.9811 (0.9810) time: 0.1695 data: 0.0915 max mem: 9390 +Train: [3] [1100/6250] eta: 0:14:57 lr: 0.000079 grad: 0.1718 (0.2044) loss: 0.9792 (0.9810) time: 0.1649 data: 0.0864 max mem: 9390 +Train: [3] [1200/6250] eta: 0:14:35 lr: 0.000080 grad: 0.2065 (0.2052) loss: 0.9795 (0.9809) time: 0.1647 data: 0.0722 max mem: 9390 +Train: [3] [1300/6250] eta: 0:14:14 lr: 0.000080 grad: 0.1312 (0.2056) loss: 0.9807 (0.9809) time: 0.1633 data: 0.0858 max mem: 9390 +Train: [3] [1400/6250] eta: 0:13:48 lr: 0.000081 grad: 0.2003 (0.2060) loss: 0.9792 (0.9808) time: 0.1373 data: 0.0575 max mem: 9390 +Train: [3] [1500/6250] eta: 0:13:27 lr: 0.000081 grad: 0.1872 (0.2058) loss: 0.9792 (0.9806) time: 0.1391 data: 0.0503 max mem: 9390 +Train: [3] [1600/6250] eta: 0:13:08 lr: 0.000081 grad: 0.1428 (0.2066) loss: 0.9795 (0.9805) time: 0.1561 data: 0.0710 max mem: 9390 +Train: [3] [1700/6250] eta: 0:12:47 lr: 0.000082 grad: 0.2333 (0.2064) loss: 0.9780 (0.9804) time: 0.1594 data: 0.0751 max mem: 9390 +Train: [3] [1800/6250] eta: 0:12:28 lr: 0.000082 grad: 0.2054 (0.2085) loss: 0.9786 (0.9803) time: 0.1491 data: 0.0568 max mem: 9390 +Train: [3] [1900/6250] eta: 0:12:09 lr: 0.000083 grad: 0.1596 (0.2073) loss: 0.9775 (0.9802) time: 0.1463 data: 0.0658 max mem: 9390 +Train: [3] [2000/6250] eta: 0:11:50 lr: 0.000083 grad: 0.1993 (0.2074) loss: 0.9777 (0.9801) time: 0.1330 data: 0.0389 max mem: 9390 +Train: [3] [2100/6250] eta: 0:11:30 lr: 0.000083 grad: 0.2220 (0.2075) loss: 0.9778 (0.9800) time: 0.1468 data: 0.0558 max mem: 9390 +Train: [3] [2200/6250] eta: 0:11:12 lr: 0.000084 grad: 0.1683 (0.2079) loss: 0.9760 (0.9799) time: 0.1419 data: 0.0535 max mem: 9390 +Train: [3] [2300/6250] eta: 0:10:54 lr: 0.000084 grad: 0.2378 (0.2087) loss: 0.9804 (0.9798) time: 0.1464 data: 0.0630 max mem: 9390 +Train: [3] [2400/6250] eta: 0:10:37 lr: 0.000085 grad: 0.1886 (0.2085) loss: 0.9794 (0.9797) time: 0.1623 data: 0.0720 max mem: 9390 +Train: [3] [2500/6250] eta: 0:10:19 lr: 0.000085 grad: 0.1641 (0.2078) loss: 0.9788 (0.9795) time: 0.1590 data: 0.0764 max mem: 9390 +Train: [3] [2600/6250] eta: 0:10:01 lr: 0.000085 grad: 0.1309 (0.2071) loss: 0.9800 (0.9795) time: 0.1572 data: 0.0635 max mem: 9390 +Train: [3] [2700/6250] eta: 0:09:43 lr: 0.000086 grad: 0.2813 (0.2068) loss: 0.9800 (0.9794) time: 0.1508 data: 0.0712 max mem: 9390 +Train: [3] [2800/6250] eta: 0:09:25 lr: 0.000086 grad: 0.1807 (0.2064) loss: 0.9760 (0.9793) time: 0.1657 data: 0.0807 max mem: 9390 +Train: [3] [2900/6250] eta: 0:09:08 lr: 0.000087 grad: 0.1923 (0.2057) loss: 0.9768 (0.9792) time: 0.1760 data: 0.0926 max mem: 9390 +Train: [3] [3000/6250] eta: 0:08:51 lr: 0.000087 grad: 0.1868 (0.2058) loss: 0.9786 (0.9792) time: 0.1644 data: 0.0894 max mem: 9390 +Train: [3] [3100/6250] eta: 0:08:34 lr: 0.000087 grad: 0.1417 (0.2052) loss: 0.9782 (0.9791) time: 0.1513 data: 0.0679 max mem: 9390 +Train: [3] [3200/6250] eta: 0:08:18 lr: 0.000088 grad: 0.1523 (0.2045) loss: 0.9777 (0.9790) time: 0.1595 data: 0.0817 max mem: 9390 +Train: [3] [3300/6250] eta: 0:08:01 lr: 0.000088 grad: 0.1651 (0.2037) loss: 0.9767 (0.9789) time: 0.1552 data: 0.0755 max mem: 9390 +Train: [3] [3400/6250] eta: 0:07:44 lr: 0.000089 grad: 0.2008 (0.2033) loss: 0.9774 (0.9788) time: 0.1792 data: 0.0910 max mem: 9390 +Train: [3] [3500/6250] eta: 0:07:27 lr: 0.000089 grad: 0.1446 (0.2028) loss: 0.9757 (0.9787) time: 0.1456 data: 0.0651 max mem: 9390 +Train: [3] [3600/6250] eta: 0:07:10 lr: 0.000089 grad: 0.1710 (0.2025) loss: 0.9747 (0.9787) time: 0.1587 data: 0.0691 max mem: 9390 +Train: [3] [3700/6250] eta: 0:06:54 lr: 0.000090 grad: 0.1441 (0.2022) loss: 0.9762 (0.9786) time: 0.1454 data: 0.0645 max mem: 9390 +Train: [3] [3800/6250] eta: 0:06:37 lr: 0.000090 grad: 0.1466 (0.2015) loss: 0.9753 (0.9785) time: 0.1189 data: 0.0397 max mem: 9390 +Train: [3] [3900/6250] eta: 0:06:19 lr: 0.000091 grad: 0.1955 (0.2006) loss: 0.9745 (0.9785) time: 0.1504 data: 0.0777 max mem: 9390 +Train: [3] [4000/6250] eta: 0:06:02 lr: 0.000091 grad: 0.1408 (0.1998) loss: 0.9770 (0.9784) time: 0.1435 data: 0.0693 max mem: 9390 +Train: [3] [4100/6250] eta: 0:05:45 lr: 0.000091 grad: 0.1580 (0.1999) loss: 0.9758 (0.9784) time: 0.1259 data: 0.0439 max mem: 9390 +Train: [3] [4200/6250] eta: 0:05:28 lr: 0.000092 grad: 0.1509 (0.1995) loss: 0.9726 (0.9783) time: 0.1486 data: 0.0696 max mem: 9390 +Train: [3] [4300/6250] eta: 0:05:11 lr: 0.000092 grad: 0.2238 (0.1997) loss: 0.9751 (0.9782) time: 0.1368 data: 0.0590 max mem: 9390 +Train: [3] [4400/6250] eta: 0:04:54 lr: 0.000093 grad: 0.1334 (0.1994) loss: 0.9740 (0.9782) time: 0.1129 data: 0.0263 max mem: 9390 +Train: [3] [4500/6250] eta: 0:04:37 lr: 0.000093 grad: 0.1318 (0.1987) loss: 0.9738 (0.9781) time: 0.1530 data: 0.0717 max mem: 9390 +Train: [3] [4600/6250] eta: 0:04:20 lr: 0.000093 grad: 0.1678 (0.1984) loss: 0.9777 (0.9780) time: 0.1005 data: 0.0233 max mem: 9390 +Train: [3] [4700/6250] eta: 0:04:04 lr: 0.000094 grad: 0.2072 (0.1985) loss: 0.9756 (0.9780) time: 0.1349 data: 0.0460 max mem: 9390 +Train: [3] [4800/6250] eta: 0:03:47 lr: 0.000094 grad: 0.1426 (0.1978) loss: 0.9739 (0.9779) time: 0.1472 data: 0.0694 max mem: 9390 +Train: [3] [4900/6250] eta: 0:03:31 lr: 0.000095 grad: 0.1727 (0.1973) loss: 0.9726 (0.9778) time: 0.1240 data: 0.0418 max mem: 9390 +Train: [3] [5000/6250] eta: 0:03:14 lr: 0.000095 grad: 0.1577 (0.1970) loss: 0.9713 (0.9777) time: 0.1376 data: 0.0580 max mem: 9390 +Train: [3] [5100/6250] eta: 0:02:58 lr: 0.000095 grad: 0.1665 (0.1966) loss: 0.9750 (0.9776) time: 0.1408 data: 0.0666 max mem: 9390 +Train: [3] [5200/6250] eta: 0:02:42 lr: 0.000096 grad: 0.1832 (0.1967) loss: 0.9716 (0.9775) time: 0.1317 data: 0.0542 max mem: 9390 +Train: [3] [5300/6250] eta: 0:02:26 lr: 0.000096 grad: 0.1358 (0.1961) loss: 0.9743 (0.9774) time: 0.1415 data: 0.0597 max mem: 9390 +Train: [3] [5400/6250] eta: 0:02:11 lr: 0.000097 grad: 0.1502 (0.1959) loss: 0.9720 (0.9773) time: 0.1365 data: 0.0488 max mem: 9390 +Train: [3] [5500/6250] eta: 0:01:55 lr: 0.000097 grad: 0.1717 (0.1959) loss: 0.9721 (0.9772) time: 0.1549 data: 0.0686 max mem: 9390 +Train: [3] [5600/6250] eta: 0:01:39 lr: 0.000097 grad: 0.1367 (0.1955) loss: 0.9719 (0.9771) time: 0.1322 data: 0.0457 max mem: 9390 +Train: [3] [5700/6250] eta: 0:01:24 lr: 0.000098 grad: 0.1594 (0.1951) loss: 0.9739 (0.9771) time: 0.1499 data: 0.0728 max mem: 9390 +Train: [3] [5800/6250] eta: 0:01:09 lr: 0.000098 grad: 0.1385 (0.1950) loss: 0.9733 (0.9770) time: 0.1301 data: 0.0490 max mem: 9390 +Train: [3] [5900/6250] eta: 0:00:53 lr: 0.000099 grad: 0.1304 (0.1945) loss: 0.9715 (0.9769) time: 0.1294 data: 0.0447 max mem: 9390 +Train: [3] [6000/6250] eta: 0:00:38 lr: 0.000099 grad: 0.1587 (0.1943) loss: 0.9731 (0.9768) time: 0.1394 data: 0.0617 max mem: 9390 +Train: [3] [6100/6250] eta: 0:00:22 lr: 0.000099 grad: 0.1353 (0.1939) loss: 0.9726 (0.9768) time: 0.1367 data: 0.0587 max mem: 9390 +Train: [3] [6200/6250] eta: 0:00:07 lr: 0.000100 grad: 0.1624 (0.1935) loss: 0.9759 (0.9767) time: 0.1520 data: 0.0713 max mem: 9390 +Train: [3] [6249/6250] eta: 0:00:00 lr: 0.000100 grad: 0.1644 (0.1932) loss: 0.9701 (0.9767) time: 0.1503 data: 0.0654 max mem: 9390 +Train: [3] Total time: 0:15:57 (0.1532 s / it) +Averaged stats: lr: 0.000100 grad: 0.1644 (0.1932) loss: 0.9701 (0.9767) +Eval (hcp-train-subset): [3] [ 0/62] eta: 0:04:27 loss: 0.9767 (0.9767) time: 4.3185 data: 4.2602 max mem: 9390 +Eval (hcp-train-subset): [3] [61/62] eta: 0:00:00 loss: 0.9775 (0.9749) time: 0.1012 data: 0.0707 max mem: 9390 +Eval (hcp-train-subset): [3] Total time: 0:00:13 (0.2123 s / it) +Averaged stats (hcp-train-subset): loss: 0.9775 (0.9749) +Eval (hcp-val): [3] [ 0/62] eta: 0:03:23 loss: 0.9640 (0.9640) time: 3.2875 data: 3.2144 max mem: 9390 +Eval (hcp-val): [3] [61/62] eta: 0:00:00 loss: 0.9716 (0.9720) time: 0.1364 data: 0.1108 max mem: 9390 +Eval (hcp-val): [3] Total time: 0:00:12 (0.2057 s / it) +Averaged stats (hcp-val): loss: 0.9716 (0.9720) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +Train: [4] [ 0/6250] eta: 9:36:39 lr: 0.000100 grad: 0.2057 (0.2057) loss: 0.9806 (0.9806) time: 5.5360 data: 5.4478 max mem: 9390 +Train: [4] [ 100/6250] eta: 0:20:24 lr: 0.000100 grad: 0.2012 (0.2166) loss: 0.9719 (0.9738) time: 0.1577 data: 0.0728 max mem: 9390 +Train: [4] [ 200/6250] eta: 0:17:42 lr: 0.000101 grad: 0.1379 (0.1904) loss: 0.9728 (0.9726) time: 0.1608 data: 0.0800 max mem: 9390 +Train: [4] [ 300/6250] eta: 0:16:39 lr: 0.000101 grad: 0.2037 (0.1901) loss: 0.9694 (0.9720) time: 0.1682 data: 0.0738 max mem: 9390 +Train: [4] [ 400/6250] eta: 0:16:00 lr: 0.000102 grad: 0.1343 (0.1851) loss: 0.9711 (0.9714) time: 0.1275 data: 0.0343 max mem: 9390 +Train: [4] [ 500/6250] eta: 0:15:49 lr: 0.000102 grad: 0.1733 (0.1834) loss: 0.9695 (0.9707) time: 0.1744 data: 0.0915 max mem: 9390 +Train: [4] [ 600/6250] eta: 0:15:39 lr: 0.000102 grad: 0.2022 (0.1828) loss: 0.9695 (0.9701) time: 0.1854 data: 0.1045 max mem: 9390 +Train: [4] [ 700/6250] eta: 0:15:16 lr: 0.000103 grad: 0.1743 (0.1848) loss: 0.9664 (0.9697) time: 0.1688 data: 0.0827 max mem: 9390 +Train: [4] [ 800/6250] eta: 0:15:03 lr: 0.000103 grad: 0.1699 (0.1879) loss: 0.9668 (0.9692) time: 0.1874 data: 0.1031 max mem: 9390 +Train: [4] [ 900/6250] eta: 0:14:48 lr: 0.000104 grad: 0.1915 (0.1912) loss: 0.9658 (0.9689) time: 0.1654 data: 0.0697 max mem: 9390 +Train: [4] [1000/6250] eta: 0:14:35 lr: 0.000104 grad: 0.1540 (0.1891) loss: 0.9632 (0.9684) time: 0.1364 data: 0.0449 max mem: 9390 +Train: [4] [1100/6250] eta: 0:14:15 lr: 0.000104 grad: 0.1766 (0.1930) loss: 0.9650 (0.9681) time: 0.1630 data: 0.0708 max mem: 9390 +Train: [4] [1200/6250] eta: 0:13:53 lr: 0.000105 grad: 0.1829 (0.1934) loss: 0.9634 (0.9677) time: 0.1490 data: 0.0664 max mem: 9390 +Train: [4] [1300/6250] eta: 0:13:36 lr: 0.000105 grad: 0.1389 (0.1938) loss: 0.9623 (0.9674) time: 0.1240 data: 0.0348 max mem: 9390 +Train: [4] [1400/6250] eta: 0:13:18 lr: 0.000106 grad: 0.2633 (0.1948) loss: 0.9626 (0.9671) time: 0.1515 data: 0.0643 max mem: 9390 +Train: [4] [1500/6250] eta: 0:12:59 lr: 0.000106 grad: 0.1608 (0.1973) loss: 0.9667 (0.9668) time: 0.1764 data: 0.0925 max mem: 9390 +Train: [4] [1600/6250] eta: 0:12:39 lr: 0.000106 grad: 0.1872 (0.1977) loss: 0.9604 (0.9664) time: 0.1336 data: 0.0539 max mem: 9390 +Train: [4] [1700/6250] eta: 0:12:20 lr: 0.000107 grad: 0.2005 (0.1985) loss: 0.9608 (0.9660) time: 0.1509 data: 0.0650 max mem: 9390 +Train: [4] [1800/6250] eta: 0:12:01 lr: 0.000107 grad: 0.1545 (0.1993) loss: 0.9596 (0.9656) time: 0.1631 data: 0.0819 max mem: 9390 +Train: [4] [1900/6250] eta: 0:11:43 lr: 0.000108 grad: 0.1590 (0.2002) loss: 0.9594 (0.9652) time: 0.1614 data: 0.0810 max mem: 9390 +Train: [4] [2000/6250] eta: 0:11:25 lr: 0.000108 grad: 0.1652 (0.2007) loss: 0.9597 (0.9649) time: 0.1487 data: 0.0653 max mem: 9390 +Train: [4] [2100/6250] eta: 0:11:07 lr: 0.000108 grad: 0.1594 (0.2001) loss: 0.9588 (0.9646) time: 0.1472 data: 0.0574 max mem: 9390 +Train: [4] [2200/6250] eta: 0:10:50 lr: 0.000109 grad: 0.1469 (0.1996) loss: 0.9588 (0.9642) time: 0.1540 data: 0.0716 max mem: 9390 +Train: [4] [2300/6250] eta: 0:10:50 lr: 0.000109 grad: 0.1654 (0.2006) loss: 0.9568 (0.9639) time: 0.0995 data: 0.0002 max mem: 9390 +Train: [4] [2400/6250] eta: 0:10:35 lr: 0.000110 grad: 0.1605 (0.2013) loss: 0.9534 (0.9635) time: 0.1687 data: 0.0814 max mem: 9390 +Train: [4] [2500/6250] eta: 0:10:19 lr: 0.000110 grad: 0.1566 (0.2017) loss: 0.9560 (0.9632) time: 0.1622 data: 0.0752 max mem: 9390 +Train: [4] [2600/6250] eta: 0:10:02 lr: 0.000110 grad: 0.2155 (0.2025) loss: 0.9536 (0.9629) time: 0.1947 data: 0.1147 max mem: 9390 +Train: [4] [2700/6250] eta: 0:09:44 lr: 0.000111 grad: 0.1823 (0.2032) loss: 0.9551 (0.9625) time: 0.1563 data: 0.0748 max mem: 9390 +Train: [4] [2800/6250] eta: 0:09:25 lr: 0.000111 grad: 0.1832 (0.2049) loss: 0.9498 (0.9621) time: 0.1556 data: 0.0763 max mem: 9390 +Train: [4] [2900/6250] eta: 0:09:08 lr: 0.000112 grad: 0.2021 (0.2049) loss: 0.9492 (0.9617) time: 0.1603 data: 0.0750 max mem: 9390 +Train: [4] [3000/6250] eta: 0:08:50 lr: 0.000112 grad: 0.2347 (0.2059) loss: 0.9483 (0.9613) time: 0.1588 data: 0.0737 max mem: 9390 +Train: [4] [3100/6250] eta: 0:08:33 lr: 0.000112 grad: 0.2118 (0.2071) loss: 0.9511 (0.9609) time: 0.1719 data: 0.0820 max mem: 9390 +Train: [4] [3200/6250] eta: 0:08:15 lr: 0.000113 grad: 0.2254 (0.2083) loss: 0.9471 (0.9605) time: 0.1508 data: 0.0695 max mem: 9390 +Train: [4] [3300/6250] eta: 0:07:57 lr: 0.000113 grad: 0.2648 (0.2103) loss: 0.9482 (0.9601) time: 0.1502 data: 0.0689 max mem: 9390 +Train: [4] [3400/6250] eta: 0:07:39 lr: 0.000114 grad: 0.1971 (0.2112) loss: 0.9452 (0.9596) time: 0.1457 data: 0.0657 max mem: 9390 +Train: [4] [3500/6250] eta: 0:07:20 lr: 0.000114 grad: 0.2042 (0.2127) loss: 0.9440 (0.9592) time: 0.1395 data: 0.0547 max mem: 9390 +Train: [4] [3600/6250] eta: 0:07:03 lr: 0.000114 grad: 0.2012 (0.2134) loss: 0.9438 (0.9588) time: 0.1393 data: 0.0658 max mem: 9390 +Train: [4] [3700/6250] eta: 0:06:45 lr: 0.000115 grad: 0.1841 (0.2147) loss: 0.9421 (0.9583) time: 0.1432 data: 0.0586 max mem: 9390 +Train: [4] [3800/6250] eta: 0:06:28 lr: 0.000115 grad: 0.2363 (0.2163) loss: 0.9428 (0.9579) time: 0.1571 data: 0.0721 max mem: 9390 +Train: [4] [3900/6250] eta: 0:06:10 lr: 0.000116 grad: 0.3585 (0.2180) loss: 0.9405 (0.9574) time: 0.1616 data: 0.0825 max mem: 9390 +Train: [4] [4000/6250] eta: 0:05:53 lr: 0.000116 grad: 0.2352 (0.2192) loss: 0.9324 (0.9570) time: 0.1193 data: 0.0253 max mem: 9390 +Train: [4] [4100/6250] eta: 0:05:36 lr: 0.000116 grad: 0.2127 (0.2201) loss: 0.9360 (0.9565) time: 0.1428 data: 0.0569 max mem: 9390 +Train: [4] [4200/6250] eta: 0:05:19 lr: 0.000117 grad: 0.2496 (0.2208) loss: 0.9359 (0.9560) time: 0.1431 data: 0.0626 max mem: 9390 +Train: [4] [4300/6250] eta: 0:05:03 lr: 0.000117 grad: 0.2293 (0.2229) loss: 0.9388 (0.9555) time: 0.1319 data: 0.0495 max mem: 9390 +Train: [4] [4400/6250] eta: 0:04:47 lr: 0.000118 grad: 0.2712 (0.2237) loss: 0.9319 (0.9550) time: 0.1347 data: 0.0517 max mem: 9390 +Train: [4] [4500/6250] eta: 0:04:31 lr: 0.000118 grad: 0.2335 (0.2249) loss: 0.9356 (0.9546) time: 0.1631 data: 0.0811 max mem: 9390 +Train: [4] [4600/6250] eta: 0:04:15 lr: 0.000118 grad: 0.2052 (0.2257) loss: 0.9347 (0.9542) time: 0.1423 data: 0.0600 max mem: 9390 +Train: [4] [4700/6250] eta: 0:04:05 lr: 0.000119 grad: 0.3039 (0.2267) loss: 0.9353 (0.9537) time: 0.3204 data: 0.2404 max mem: 9390 +Train: [4] [4800/6250] eta: 0:03:53 lr: 0.000119 grad: 0.2513 (0.2276) loss: 0.9355 (0.9533) time: 0.5359 data: 0.4502 max mem: 9390 +Train: [4] [4900/6250] eta: 0:03:44 lr: 0.000120 grad: 0.2034 (0.2272) loss: 0.9329 (0.9529) time: 0.3814 data: 0.2607 max mem: 9390 +Train: [4] [5000/6250] eta: 0:03:30 lr: 0.000120 grad: 0.1723 (0.2275) loss: 0.9326 (0.9524) time: 0.2901 data: 0.2080 max mem: 9390 +Train: [4] [5100/6250] eta: 0:03:16 lr: 0.000120 grad: 0.2069 (0.2277) loss: 0.9313 (0.9521) time: 0.5825 data: 0.4827 max mem: 9390 +Train: [4] [5200/6250] eta: 0:03:02 lr: 0.000121 grad: 0.2146 (0.2273) loss: 0.9321 (0.9517) time: 0.4101 data: 0.3049 max mem: 9390 +Train: [4] [5300/6250] eta: 0:02:45 lr: 0.000121 grad: 0.2044 (0.2280) loss: 0.9322 (0.9513) time: 0.2243 data: 0.1152 max mem: 9390 +Train: [4] [5400/6250] eta: 0:02:30 lr: 0.000122 grad: 0.2567 (0.2282) loss: 0.9325 (0.9510) time: 0.2298 data: 0.1424 max mem: 9390 +Train: [4] [5500/6250] eta: 0:02:14 lr: 0.000122 grad: 0.2175 (0.2281) loss: 0.9297 (0.9506) time: 0.3793 data: 0.2817 max mem: 9390 +Train: [4] [5600/6250] eta: 0:01:56 lr: 0.000122 grad: 0.1785 (0.2282) loss: 0.9328 (0.9503) time: 0.1780 data: 0.0925 max mem: 9390 +Train: [4] [5700/6250] eta: 0:01:38 lr: 0.000123 grad: 0.2043 (0.2282) loss: 0.9318 (0.9499) time: 0.1762 data: 0.0954 max mem: 9390 +Train: [4] [5800/6250] eta: 0:01:20 lr: 0.000123 grad: 0.2158 (0.2280) loss: 0.9255 (0.9496) time: 0.1549 data: 0.0651 max mem: 9390 +Train: [4] [5900/6250] eta: 0:01:02 lr: 0.000124 grad: 0.1736 (0.2276) loss: 0.9268 (0.9492) time: 0.1543 data: 0.0718 max mem: 9390 +Train: [4] [6000/6250] eta: 0:00:44 lr: 0.000124 grad: 0.1874 (0.2273) loss: 0.9291 (0.9489) time: 0.1559 data: 0.0627 max mem: 9390 +Train: [4] [6100/6250] eta: 0:00:26 lr: 0.000124 grad: 0.1733 (0.2271) loss: 0.9291 (0.9485) time: 0.1619 data: 0.0784 max mem: 9390 +Train: [4] [6200/6250] eta: 0:00:08 lr: 0.000125 grad: 0.1771 (0.2263) loss: 0.9269 (0.9482) time: 0.1393 data: 0.0542 max mem: 9390 +Train: [4] [6249/6250] eta: 0:00:00 lr: 0.000125 grad: 0.2209 (0.2262) loss: 0.9302 (0.9480) time: 0.1421 data: 0.0557 max mem: 9390 +Train: [4] Total time: 0:18:27 (0.1773 s / it) +Averaged stats: lr: 0.000125 grad: 0.2209 (0.2262) loss: 0.9302 (0.9480) +Eval (hcp-train-subset): [4] [ 0/62] eta: 0:04:59 loss: 0.9338 (0.9338) time: 4.8378 data: 4.8072 max mem: 9390 +Eval (hcp-train-subset): [4] [61/62] eta: 0:00:00 loss: 0.9322 (0.9301) time: 0.1349 data: 0.1099 max mem: 9390 +Eval (hcp-train-subset): [4] Total time: 0:00:12 (0.2069 s / it) +Averaged stats (hcp-train-subset): loss: 0.9322 (0.9301) +Making plots (hcp-train-subset): example=24 +Eval (hcp-val): [4] [ 0/62] eta: 0:03:49 loss: 0.9236 (0.9236) time: 3.7077 data: 3.6531 max mem: 9390 +Eval (hcp-val): [4] [61/62] eta: 0:00:00 loss: 0.9256 (0.9251) time: 0.1336 data: 0.1086 max mem: 9390 +Eval (hcp-val): [4] Total time: 0:00:13 (0.2255 s / it) +Averaged stats (hcp-val): loss: 0.9256 (0.9251) +Making plots (hcp-val): example=12 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +Train: [5] [ 0/6250] eta: 5:53:18 lr: 0.000125 grad: 0.1936 (0.1936) loss: 0.9462 (0.9462) time: 3.3917 data: 3.1503 max mem: 9390 +Train: [5] [ 100/6250] eta: 0:19:34 lr: 0.000125 grad: 0.1963 (0.2063) loss: 0.9363 (0.9345) time: 0.1303 data: 0.0478 max mem: 9390 +Train: [5] [ 200/6250] eta: 0:17:33 lr: 0.000125 grad: 0.1645 (0.1993) loss: 0.9314 (0.9324) time: 0.1488 data: 0.0635 max mem: 9390 +Train: [5] [ 300/6250] eta: 0:16:27 lr: 0.000125 grad: 0.1618 (0.2034) loss: 0.9292 (0.9310) time: 0.1412 data: 0.0469 max mem: 9390 +Train: [5] [ 400/6250] eta: 0:15:48 lr: 0.000125 grad: 0.1764 (0.1998) loss: 0.9327 (0.9307) time: 0.1379 data: 0.0458 max mem: 9390 +Train: [5] [ 500/6250] eta: 0:15:07 lr: 0.000125 grad: 0.1291 (0.1955) loss: 0.9292 (0.9305) time: 0.1348 data: 0.0469 max mem: 9390 +Train: [5] [ 600/6250] eta: 0:14:34 lr: 0.000125 grad: 0.1548 (0.1936) loss: 0.9295 (0.9299) time: 0.1345 data: 0.0440 max mem: 9390 +Train: [5] [ 700/6250] eta: 0:14:08 lr: 0.000125 grad: 0.1499 (0.1935) loss: 0.9262 (0.9291) time: 0.1555 data: 0.0703 max mem: 9390 +Train: [5] [ 800/6250] eta: 0:13:51 lr: 0.000125 grad: 0.1652 (0.1916) loss: 0.9200 (0.9284) time: 0.1600 data: 0.0792 max mem: 9390 +Train: [5] [ 900/6250] eta: 0:13:39 lr: 0.000125 grad: 0.1759 (0.1916) loss: 0.9197 (0.9278) time: 0.1252 data: 0.0408 max mem: 9390 +Train: [5] [1000/6250] eta: 0:13:28 lr: 0.000125 grad: 0.1654 (0.1916) loss: 0.9200 (0.9271) time: 0.1716 data: 0.0943 max mem: 9390 +Train: [5] [1100/6250] eta: 0:13:08 lr: 0.000125 grad: 0.1551 (0.1904) loss: 0.9204 (0.9265) time: 0.1387 data: 0.0579 max mem: 9390 +Train: [5] [1200/6250] eta: 0:12:48 lr: 0.000125 grad: 0.1744 (0.1906) loss: 0.9196 (0.9260) time: 0.1269 data: 0.0466 max mem: 9390 +Train: [5] [1300/6250] eta: 0:12:33 lr: 0.000125 grad: 0.1790 (0.1899) loss: 0.9196 (0.9255) time: 0.1814 data: 0.1018 max mem: 9390 +Train: [5] [1400/6250] eta: 0:12:12 lr: 0.000125 grad: 0.1545 (0.1894) loss: 0.9176 (0.9251) time: 0.1364 data: 0.0553 max mem: 9390 +Train: [5] [1500/6250] eta: 0:11:54 lr: 0.000125 grad: 0.1864 (0.1887) loss: 0.9166 (0.9247) time: 0.1235 data: 0.0406 max mem: 9390 +Train: [5] [1600/6250] eta: 0:11:38 lr: 0.000125 grad: 0.1762 (0.1880) loss: 0.9149 (0.9242) time: 0.1645 data: 0.0847 max mem: 9390 +Train: [5] [1700/6250] eta: 0:11:20 lr: 0.000125 grad: 0.1671 (0.1871) loss: 0.9132 (0.9237) time: 0.1494 data: 0.0662 max mem: 9390 +Train: [5] [1800/6250] eta: 0:11:05 lr: 0.000125 grad: 0.1549 (0.1872) loss: 0.9160 (0.9232) time: 0.1633 data: 0.0880 max mem: 9390 +Train: [5] [1900/6250] eta: 0:10:49 lr: 0.000125 grad: 0.1884 (0.1871) loss: 0.9193 (0.9228) time: 0.1459 data: 0.0681 max mem: 9390 +Train: [5] [2000/6250] eta: 0:10:33 lr: 0.000125 grad: 0.1591 (0.1865) loss: 0.9115 (0.9223) time: 0.1362 data: 0.0570 max mem: 9390 +Train: [5] [2100/6250] eta: 0:10:19 lr: 0.000125 grad: 0.1775 (0.1865) loss: 0.9107 (0.9219) time: 0.1437 data: 0.0620 max mem: 9390 +Train: [5] [2200/6250] eta: 0:10:03 lr: 0.000125 grad: 0.1686 (0.1859) loss: 0.9130 (0.9216) time: 0.1611 data: 0.0843 max mem: 9390 +Train: [5] [2300/6250] eta: 0:09:47 lr: 0.000125 grad: 0.2056 (0.1854) loss: 0.9123 (0.9212) time: 0.1297 data: 0.0521 max mem: 9390 +Train: [5] [2400/6250] eta: 0:09:32 lr: 0.000125 grad: 0.1766 (0.1848) loss: 0.9132 (0.9209) time: 0.1390 data: 0.0577 max mem: 9390 +Train: [5] [2500/6250] eta: 0:09:16 lr: 0.000125 grad: 0.1958 (0.1844) loss: 0.9140 (0.9206) time: 0.1498 data: 0.0759 max mem: 9390 +Train: [5] [2600/6250] eta: 0:09:03 lr: 0.000125 grad: 0.1790 (0.1840) loss: 0.9123 (0.9203) time: 0.1754 data: 0.1018 max mem: 9390 +Train: [5] [2700/6250] eta: 0:08:48 lr: 0.000125 grad: 0.1467 (0.1831) loss: 0.9144 (0.9200) time: 0.1634 data: 0.0825 max mem: 9390 +Train: [5] [2800/6250] eta: 0:08:34 lr: 0.000125 grad: 0.1640 (0.1828) loss: 0.9114 (0.9198) time: 0.1422 data: 0.0586 max mem: 9390 +Train: [5] [2900/6250] eta: 0:08:21 lr: 0.000125 grad: 0.1595 (0.1819) loss: 0.9097 (0.9195) time: 0.1471 data: 0.0555 max mem: 9390 +Train: [5] [3000/6250] eta: 0:08:07 lr: 0.000125 grad: 0.1406 (0.1814) loss: 0.9100 (0.9192) time: 0.1685 data: 0.0882 max mem: 9390 +Train: [5] [3100/6250] eta: 0:07:52 lr: 0.000125 grad: 0.1331 (0.1812) loss: 0.9107 (0.9190) time: 0.1967 data: 0.1245 max mem: 9390 +Train: [5] [3200/6250] eta: 0:07:37 lr: 0.000125 grad: 0.1636 (0.1808) loss: 0.9030 (0.9187) time: 0.1061 data: 0.0241 max mem: 9390 +Train: [5] [3300/6250] eta: 0:07:23 lr: 0.000125 grad: 0.1754 (0.1807) loss: 0.9038 (0.9183) time: 0.1575 data: 0.0785 max mem: 9390 +Train: [5] [3400/6250] eta: 0:07:12 lr: 0.000125 grad: 0.1988 (0.1808) loss: 0.9076 (0.9180) time: 0.2747 data: 0.1959 max mem: 9390 +Train: [5] [3500/6250] eta: 0:07:00 lr: 0.000125 grad: 0.1679 (0.1808) loss: 0.9058 (0.9177) time: 0.2762 data: 0.1844 max mem: 9390 +Train: [5] [3600/6250] eta: 0:06:46 lr: 0.000125 grad: 0.1477 (0.1804) loss: 0.9063 (0.9173) time: 0.1216 data: 0.0411 max mem: 9390 +Train: [5] [3700/6250] eta: 0:06:32 lr: 0.000125 grad: 0.1694 (0.1800) loss: 0.9052 (0.9170) time: 0.1738 data: 0.0946 max mem: 9390 +Train: [5] [3800/6250] eta: 0:06:18 lr: 0.000125 grad: 0.1477 (0.1794) loss: 0.9090 (0.9167) time: 0.1219 data: 0.0343 max mem: 9390 +Train: [5] [3900/6250] eta: 0:06:03 lr: 0.000125 grad: 0.1536 (0.1792) loss: 0.9057 (0.9164) time: 0.1833 data: 0.1045 max mem: 9390 +Train: [5] [4000/6250] eta: 0:05:48 lr: 0.000125 grad: 0.1592 (0.1792) loss: 0.9028 (0.9161) time: 0.2068 data: 0.1281 max mem: 9390 +Train: [5] [4100/6250] eta: 0:05:32 lr: 0.000125 grad: 0.1380 (0.1792) loss: 0.9044 (0.9158) time: 0.1152 data: 0.0298 max mem: 9390 +Train: [5] [4200/6250] eta: 0:05:17 lr: 0.000125 grad: 0.1516 (0.1789) loss: 0.9030 (0.9155) time: 0.0958 data: 0.0116 max mem: 9390 +Train: [5] [4300/6250] eta: 0:05:02 lr: 0.000125 grad: 0.1480 (0.1790) loss: 0.9050 (0.9153) time: 0.1373 data: 0.0569 max mem: 9390 +Train: [5] [4400/6250] eta: 0:04:48 lr: 0.000125 grad: 0.1873 (0.1786) loss: 0.9048 (0.9150) time: 0.1746 data: 0.0870 max mem: 9390 +Train: [5] [4500/6250] eta: 0:04:34 lr: 0.000125 grad: 0.1522 (0.1786) loss: 0.9004 (0.9147) time: 0.1880 data: 0.0943 max mem: 9390 +Train: [5] [4600/6250] eta: 0:04:20 lr: 0.000125 grad: 0.1842 (0.1784) loss: 0.9015 (0.9144) time: 0.0843 data: 0.0002 max mem: 9390 +Train: [5] [4700/6250] eta: 0:04:05 lr: 0.000125 grad: 0.1765 (0.1780) loss: 0.9005 (0.9141) time: 0.1212 data: 0.0339 max mem: 9390 +Train: [5] [4800/6250] eta: 0:03:50 lr: 0.000125 grad: 0.1507 (0.1777) loss: 0.8921 (0.9137) time: 0.3007 data: 0.2219 max mem: 9390 +Train: [5] [4900/6250] eta: 0:03:35 lr: 0.000125 grad: 0.1448 (0.1775) loss: 0.9007 (0.9134) time: 0.1024 data: 0.0020 max mem: 9390 +Train: [5] [5000/6250] eta: 0:03:19 lr: 0.000125 grad: 0.1469 (0.1775) loss: 0.8968 (0.9131) time: 0.1474 data: 0.0624 max mem: 9390 +Train: [5] [5100/6250] eta: 0:03:04 lr: 0.000125 grad: 0.1641 (0.1774) loss: 0.8964 (0.9128) time: 0.1217 data: 0.0380 max mem: 9390 +Train: [5] [5200/6250] eta: 0:02:48 lr: 0.000125 grad: 0.1503 (0.1772) loss: 0.8957 (0.9124) time: 0.2111 data: 0.1235 max mem: 9390 +Train: [5] [5300/6250] eta: 0:02:33 lr: 0.000125 grad: 0.1819 (0.1771) loss: 0.8939 (0.9121) time: 0.2948 data: 0.2110 max mem: 9390 +Train: [5] [5400/6250] eta: 0:02:16 lr: 0.000125 grad: 0.1452 (0.1769) loss: 0.8934 (0.9118) time: 0.1193 data: 0.0385 max mem: 9390 +Train: [5] [5500/6250] eta: 0:02:00 lr: 0.000125 grad: 0.1433 (0.1767) loss: 0.8944 (0.9114) time: 0.1433 data: 0.0612 max mem: 9390 +Train: [5] [5600/6250] eta: 0:01:45 lr: 0.000125 grad: 0.1626 (0.1767) loss: 0.8897 (0.9111) time: 0.2291 data: 0.1402 max mem: 9390 +Train: [5] [5700/6250] eta: 0:01:28 lr: 0.000125 grad: 0.1419 (0.1763) loss: 0.8915 (0.9107) time: 0.1703 data: 0.0919 max mem: 9390 +Train: [5] [5800/6250] eta: 0:01:12 lr: 0.000125 grad: 0.1423 (0.1761) loss: 0.8887 (0.9104) time: 0.1385 data: 0.0528 max mem: 9390 +Train: [5] [5900/6250] eta: 0:00:56 lr: 0.000125 grad: 0.1932 (0.1757) loss: 0.8877 (0.9100) time: 0.1090 data: 0.0220 max mem: 9390 +Train: [5] [6000/6250] eta: 0:00:40 lr: 0.000125 grad: 0.1613 (0.1755) loss: 0.8867 (0.9097) time: 0.1687 data: 0.0891 max mem: 9390 +Train: [5] [6100/6250] eta: 0:00:24 lr: 0.000125 grad: 0.1316 (0.1751) loss: 0.8902 (0.9093) time: 0.1618 data: 0.0840 max mem: 9390 +Train: [5] [6200/6250] eta: 0:00:08 lr: 0.000125 grad: 0.1652 (0.1748) loss: 0.8926 (0.9090) time: 0.1382 data: 0.0577 max mem: 9390 +Train: [5] [6249/6250] eta: 0:00:00 lr: 0.000125 grad: 0.1385 (0.1745) loss: 0.8885 (0.9088) time: 0.1833 data: 0.1072 max mem: 9390 +Train: [5] Total time: 0:16:54 (0.1624 s / it) +Averaged stats: lr: 0.000125 grad: 0.1385 (0.1745) loss: 0.8885 (0.9088) +Eval (hcp-train-subset): [5] [ 0/62] eta: 0:02:56 loss: 0.8959 (0.8959) time: 2.8454 data: 2.7485 max mem: 9390 +Eval (hcp-train-subset): [5] [61/62] eta: 0:00:00 loss: 0.8936 (0.8916) time: 0.1266 data: 0.1018 max mem: 9390 +Eval (hcp-train-subset): [5] Total time: 0:00:13 (0.2183 s / it) +Averaged stats (hcp-train-subset): loss: 0.8936 (0.8916) +Eval (hcp-val): [5] [ 0/62] eta: 0:05:09 loss: 0.8807 (0.8807) time: 4.9926 data: 4.9622 max mem: 9390 +Eval (hcp-val): [5] [61/62] eta: 0:00:00 loss: 0.8856 (0.8855) time: 0.1724 data: 0.1456 max mem: 9390 +Eval (hcp-val): [5] Total time: 0:00:14 (0.2362 s / it) +Averaged stats (hcp-val): loss: 0.8856 (0.8855) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +Train: [6] [ 0/6250] eta: 11:26:30 lr: 0.000125 grad: 0.1399 (0.1399) loss: 0.9053 (0.9053) time: 6.5904 data: 6.4930 max mem: 9390 +Train: [6] [ 100/6250] eta: 0:21:43 lr: 0.000125 grad: 0.1424 (0.1344) loss: 0.8899 (0.8979) time: 0.1502 data: 0.0673 max mem: 9390 +Train: [6] [ 200/6250] eta: 0:18:45 lr: 0.000125 grad: 0.1797 (0.1448) loss: 0.8916 (0.8958) time: 0.1480 data: 0.0629 max mem: 9390 +Train: [6] [ 300/6250] eta: 0:17:47 lr: 0.000125 grad: 0.1367 (0.1526) loss: 0.8868 (0.8937) time: 0.1712 data: 0.0911 max mem: 9390 +Train: [6] [ 400/6250] eta: 0:17:00 lr: 0.000125 grad: 0.1519 (0.1540) loss: 0.8798 (0.8913) time: 0.1200 data: 0.0297 max mem: 9390 +Train: [6] [ 500/6250] eta: 0:16:15 lr: 0.000125 grad: 0.1244 (0.1527) loss: 0.8833 (0.8897) time: 0.1520 data: 0.0685 max mem: 9390 +Train: [6] [ 600/6250] eta: 0:15:32 lr: 0.000125 grad: 0.1234 (0.1516) loss: 0.8832 (0.8891) time: 0.1444 data: 0.0546 max mem: 9390 +Train: [6] [ 700/6250] eta: 0:15:07 lr: 0.000125 grad: 0.1487 (0.1513) loss: 0.8827 (0.8882) time: 0.1735 data: 0.0865 max mem: 9390 +Train: [6] [ 800/6250] eta: 0:14:44 lr: 0.000125 grad: 0.1339 (0.1501) loss: 0.8861 (0.8876) time: 0.1501 data: 0.0623 max mem: 9390 +Train: [6] [ 900/6250] eta: 0:14:35 lr: 0.000125 grad: 0.1294 (0.1487) loss: 0.8888 (0.8872) time: 0.1819 data: 0.1008 max mem: 9390 +Train: [6] [1000/6250] eta: 0:14:28 lr: 0.000125 grad: 0.1212 (0.1476) loss: 0.8827 (0.8867) time: 0.1726 data: 0.0850 max mem: 9390 +Train: [6] [1100/6250] eta: 0:14:19 lr: 0.000125 grad: 0.1286 (0.1464) loss: 0.8858 (0.8865) time: 0.2073 data: 0.1258 max mem: 9390 +Train: [6] [1200/6250] eta: 0:13:59 lr: 0.000125 grad: 0.1487 (0.1455) loss: 0.8832 (0.8861) time: 0.1537 data: 0.0756 max mem: 9390 +Train: [6] [1300/6250] eta: 0:13:44 lr: 0.000125 grad: 0.1236 (0.1440) loss: 0.8840 (0.8858) time: 0.1791 data: 0.1026 max mem: 9390 +Train: [6] [1400/6250] eta: 0:13:25 lr: 0.000125 grad: 0.1144 (0.1432) loss: 0.8832 (0.8856) time: 0.1653 data: 0.0842 max mem: 9390 +Train: [6] [1500/6250] eta: 0:13:06 lr: 0.000125 grad: 0.1218 (0.1423) loss: 0.8807 (0.8854) time: 0.1387 data: 0.0570 max mem: 9390 +Train: [6] [1600/6250] eta: 0:12:50 lr: 0.000125 grad: 0.1261 (0.1422) loss: 0.8822 (0.8851) time: 0.1680 data: 0.0883 max mem: 9390 +Train: [6] [1700/6250] eta: 0:12:31 lr: 0.000125 grad: 0.1103 (0.1415) loss: 0.8846 (0.8848) time: 0.1152 data: 0.0314 max mem: 9390 +Train: [6] [1800/6250] eta: 0:12:14 lr: 0.000125 grad: 0.1066 (0.1406) loss: 0.8772 (0.8845) time: 0.1227 data: 0.0444 max mem: 9390 +Train: [6] [1900/6250] eta: 0:11:55 lr: 0.000125 grad: 0.1273 (0.1407) loss: 0.8795 (0.8841) time: 0.1803 data: 0.0989 max mem: 9390 +Train: [6] [2000/6250] eta: 0:11:39 lr: 0.000125 grad: 0.1152 (0.1405) loss: 0.8834 (0.8839) time: 0.1712 data: 0.0954 max mem: 9390 +Train: [6] [2100/6250] eta: 0:11:19 lr: 0.000125 grad: 0.1248 (0.1398) loss: 0.8740 (0.8836) time: 0.1495 data: 0.0702 max mem: 9390 +Train: [6] [2200/6250] eta: 0:10:59 lr: 0.000125 grad: 0.1157 (0.1390) loss: 0.8748 (0.8834) time: 0.1400 data: 0.0593 max mem: 9390 +Train: [6] [2300/6250] eta: 0:10:44 lr: 0.000125 grad: 0.1175 (0.1386) loss: 0.8787 (0.8832) time: 0.1837 data: 0.0965 max mem: 9390 +Train: [6] [2400/6250] eta: 0:10:29 lr: 0.000125 grad: 0.1048 (0.1380) loss: 0.8774 (0.8830) time: 0.1049 data: 0.0002 max mem: 9390 +Train: [6] [2500/6250] eta: 0:10:15 lr: 0.000125 grad: 0.1231 (0.1374) loss: 0.8766 (0.8827) time: 0.2797 data: 0.1863 max mem: 9390 +Train: [6] [2600/6250] eta: 0:09:58 lr: 0.000125 grad: 0.1102 (0.1368) loss: 0.8785 (0.8825) time: 0.1679 data: 0.0910 max mem: 9390 +Train: [6] [2700/6250] eta: 0:09:40 lr: 0.000125 grad: 0.1233 (0.1364) loss: 0.8764 (0.8823) time: 0.1518 data: 0.0752 max mem: 9390 +Train: [6] [2800/6250] eta: 0:09:25 lr: 0.000125 grad: 0.1246 (0.1359) loss: 0.8764 (0.8821) time: 0.0929 data: 0.0002 max mem: 9390 +Train: [6] [2900/6250] eta: 0:09:12 lr: 0.000125 grad: 0.1167 (0.1355) loss: 0.8746 (0.8819) time: 0.0964 data: 0.0209 max mem: 9390 +Train: [6] [3000/6250] eta: 0:08:55 lr: 0.000125 grad: 0.1129 (0.1350) loss: 0.8748 (0.8818) time: 0.1613 data: 0.0869 max mem: 9390 +Train: [6] [3100/6250] eta: 0:08:37 lr: 0.000125 grad: 0.1170 (0.1351) loss: 0.8752 (0.8816) time: 0.1787 data: 0.0961 max mem: 9390 +Train: [6] [3200/6250] eta: 0:08:23 lr: 0.000125 grad: 0.1103 (0.1345) loss: 0.8775 (0.8814) time: 0.0970 data: 0.0137 max mem: 9390 +Train: [6] [3300/6250] eta: 0:08:06 lr: 0.000125 grad: 0.1175 (0.1339) loss: 0.8755 (0.8813) time: 0.2119 data: 0.1304 max mem: 9390 +Train: [6] [3400/6250] eta: 0:07:48 lr: 0.000125 grad: 0.1209 (0.1335) loss: 0.8780 (0.8811) time: 0.1352 data: 0.0583 max mem: 9390 +Train: [6] [3500/6250] eta: 0:07:31 lr: 0.000125 grad: 0.1062 (0.1328) loss: 0.8730 (0.8809) time: 0.1498 data: 0.0701 max mem: 9390 +Train: [6] [3600/6250] eta: 0:07:16 lr: 0.000125 grad: 0.1070 (0.1324) loss: 0.8704 (0.8808) time: 0.2644 data: 0.1770 max mem: 9390 +Train: [6] [3700/6250] eta: 0:06:58 lr: 0.000125 grad: 0.1276 (0.1322) loss: 0.8735 (0.8806) time: 0.1292 data: 0.0491 max mem: 9390 +Train: [6] [3800/6250] eta: 0:06:40 lr: 0.000125 grad: 0.1074 (0.1318) loss: 0.8723 (0.8805) time: 0.1532 data: 0.0739 max mem: 9390 +Train: [6] [3900/6250] eta: 0:06:24 lr: 0.000125 grad: 0.1202 (0.1313) loss: 0.8740 (0.8803) time: 0.1336 data: 0.0503 max mem: 9390 +Train: [6] [4000/6250] eta: 0:06:07 lr: 0.000125 grad: 0.1035 (0.1310) loss: 0.8729 (0.8802) time: 0.1391 data: 0.0664 max mem: 9390 +Train: [6] [4100/6250] eta: 0:05:51 lr: 0.000125 grad: 0.1244 (0.1306) loss: 0.8777 (0.8801) time: 0.1437 data: 0.0646 max mem: 9390 +Train: [6] [4200/6250] eta: 0:05:35 lr: 0.000125 grad: 0.1228 (0.1304) loss: 0.8779 (0.8800) time: 0.1717 data: 0.0917 max mem: 9390 +Train: [6] [4300/6250] eta: 0:05:19 lr: 0.000125 grad: 0.1122 (0.1298) loss: 0.8712 (0.8798) time: 0.1443 data: 0.0681 max mem: 9390 +Train: [6] [4400/6250] eta: 0:05:02 lr: 0.000125 grad: 0.1009 (0.1294) loss: 0.8678 (0.8797) time: 0.1612 data: 0.0822 max mem: 9390 +Train: [6] [4500/6250] eta: 0:04:46 lr: 0.000125 grad: 0.1063 (0.1289) loss: 0.8779 (0.8796) time: 0.1668 data: 0.0908 max mem: 9390 +Train: [6] [4600/6250] eta: 0:04:30 lr: 0.000125 grad: 0.1246 (0.1286) loss: 0.8719 (0.8794) time: 0.1723 data: 0.0913 max mem: 9390 +Train: [6] [4700/6250] eta: 0:04:14 lr: 0.000125 grad: 0.1002 (0.1282) loss: 0.8722 (0.8793) time: 0.1541 data: 0.0655 max mem: 9390 +Train: [6] [4800/6250] eta: 0:03:57 lr: 0.000125 grad: 0.1005 (0.1278) loss: 0.8733 (0.8791) time: 0.1609 data: 0.0778 max mem: 9390 +Train: [6] [4900/6250] eta: 0:03:40 lr: 0.000125 grad: 0.1018 (0.1274) loss: 0.8693 (0.8790) time: 0.1569 data: 0.0668 max mem: 9390 +Train: [6] [5000/6250] eta: 0:03:24 lr: 0.000125 grad: 0.1024 (0.1269) loss: 0.8713 (0.8789) time: 0.1791 data: 0.0911 max mem: 9390 +Train: [6] [5100/6250] eta: 0:03:07 lr: 0.000125 grad: 0.1039 (0.1266) loss: 0.8690 (0.8788) time: 0.1392 data: 0.0489 max mem: 9390 +Train: [6] [5200/6250] eta: 0:02:50 lr: 0.000125 grad: 0.0983 (0.1263) loss: 0.8751 (0.8786) time: 0.1302 data: 0.0460 max mem: 9390 +Train: [6] [5300/6250] eta: 0:02:34 lr: 0.000125 grad: 0.1014 (0.1258) loss: 0.8752 (0.8785) time: 0.1784 data: 0.1021 max mem: 9390 +Train: [6] [5400/6250] eta: 0:02:17 lr: 0.000125 grad: 0.1079 (0.1255) loss: 0.8694 (0.8784) time: 0.1589 data: 0.0730 max mem: 9390 +Train: [6] [5500/6250] eta: 0:02:01 lr: 0.000125 grad: 0.0994 (0.1250) loss: 0.8692 (0.8782) time: 0.1652 data: 0.0849 max mem: 9390 +Train: [6] [5600/6250] eta: 0:01:45 lr: 0.000125 grad: 0.1054 (0.1248) loss: 0.8642 (0.8781) time: 0.1543 data: 0.0719 max mem: 9390 +Train: [6] [5700/6250] eta: 0:01:29 lr: 0.000125 grad: 0.1015 (0.1244) loss: 0.8733 (0.8780) time: 0.1630 data: 0.0749 max mem: 9390 +Train: [6] [5800/6250] eta: 0:01:12 lr: 0.000125 grad: 0.0912 (0.1240) loss: 0.8731 (0.8779) time: 0.1777 data: 0.0906 max mem: 9390 +Train: [6] [5900/6250] eta: 0:00:56 lr: 0.000125 grad: 0.0970 (0.1236) loss: 0.8656 (0.8778) time: 0.1705 data: 0.0932 max mem: 9390 +Train: [6] [6000/6250] eta: 0:00:40 lr: 0.000125 grad: 0.0927 (0.1233) loss: 0.8698 (0.8777) time: 0.1618 data: 0.0785 max mem: 9390 +Train: [6] [6100/6250] eta: 0:00:24 lr: 0.000125 grad: 0.0989 (0.1231) loss: 0.8701 (0.8775) time: 0.1823 data: 0.1040 max mem: 9390 +Train: [6] [6200/6250] eta: 0:00:08 lr: 0.000125 grad: 0.1019 (0.1228) loss: 0.8714 (0.8774) time: 0.1562 data: 0.0765 max mem: 9390 +Train: [6] [6249/6250] eta: 0:00:00 lr: 0.000125 grad: 0.0996 (0.1226) loss: 0.8670 (0.8774) time: 0.1272 data: 0.0513 max mem: 9390 +Train: [6] Total time: 0:16:54 (0.1623 s / it) +Averaged stats: lr: 0.000125 grad: 0.0996 (0.1226) loss: 0.8670 (0.8774) +Eval (hcp-train-subset): [6] [ 0/62] eta: 0:04:19 loss: 0.8794 (0.8794) time: 4.1855 data: 4.1552 max mem: 9390 +Eval (hcp-train-subset): [6] [61/62] eta: 0:00:00 loss: 0.8721 (0.8723) time: 0.1187 data: 0.0917 max mem: 9390 +Eval (hcp-train-subset): [6] Total time: 0:00:13 (0.2118 s / it) +Averaged stats (hcp-train-subset): loss: 0.8721 (0.8723) +Eval (hcp-val): [6] [ 0/62] eta: 0:02:51 loss: 0.8636 (0.8636) time: 2.7732 data: 2.7027 max mem: 9390 +Eval (hcp-val): [6] [61/62] eta: 0:00:00 loss: 0.8655 (0.8661) time: 0.1284 data: 0.1035 max mem: 9390 +Eval (hcp-val): [6] Total time: 0:00:13 (0.2139 s / it) +Averaged stats (hcp-val): loss: 0.8655 (0.8661) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +Train: [7] [ 0/6250] eta: 6:36:31 lr: 0.000125 grad: 0.0615 (0.0615) loss: 0.8825 (0.8825) time: 3.8067 data: 3.5719 max mem: 9390 +Train: [7] [ 100/6250] eta: 0:21:42 lr: 0.000125 grad: 0.1136 (0.1194) loss: 0.8720 (0.8728) time: 0.1637 data: 0.0860 max mem: 9390 +Train: [7] [ 200/6250] eta: 0:18:19 lr: 0.000125 grad: 0.0953 (0.1096) loss: 0.8693 (0.8709) time: 0.1520 data: 0.0693 max mem: 9390 +Train: [7] [ 300/6250] eta: 0:17:23 lr: 0.000125 grad: 0.0903 (0.1073) loss: 0.8693 (0.8700) time: 0.1793 data: 0.0936 max mem: 9390 +Train: [7] [ 400/6250] eta: 0:16:24 lr: 0.000125 grad: 0.0922 (0.1059) loss: 0.8693 (0.8696) time: 0.1385 data: 0.0474 max mem: 9390 +Train: [7] [ 500/6250] eta: 0:15:41 lr: 0.000125 grad: 0.0918 (0.1052) loss: 0.8638 (0.8687) time: 0.1315 data: 0.0300 max mem: 9390 +Train: [7] [ 600/6250] eta: 0:15:03 lr: 0.000125 grad: 0.1094 (0.1050) loss: 0.8636 (0.8680) time: 0.1342 data: 0.0468 max mem: 9390 +Train: [7] [ 700/6250] eta: 0:14:31 lr: 0.000125 grad: 0.0960 (0.1036) loss: 0.8695 (0.8679) time: 0.1322 data: 0.0475 max mem: 9390 +Train: [7] [ 800/6250] eta: 0:14:24 lr: 0.000125 grad: 0.0900 (0.1030) loss: 0.8651 (0.8678) time: 0.1667 data: 0.0915 max mem: 9390 +Train: [7] [ 900/6250] eta: 0:14:51 lr: 0.000125 grad: 0.0973 (0.1019) loss: 0.8692 (0.8677) time: 0.2221 data: 0.0979 max mem: 9390 +Train: [7] [1000/6250] eta: 0:15:00 lr: 0.000125 grad: 0.0985 (0.1018) loss: 0.8675 (0.8677) time: 0.1920 data: 0.0817 max mem: 9390 +Train: [7] [1100/6250] eta: 0:14:45 lr: 0.000125 grad: 0.1089 (0.1014) loss: 0.8655 (0.8676) time: 0.1130 data: 0.0319 max mem: 9390 +Train: [7] [1200/6250] eta: 0:14:40 lr: 0.000125 grad: 0.1031 (0.1014) loss: 0.8675 (0.8675) time: 0.0996 data: 0.0002 max mem: 9390 +Train: [7] [1300/6250] eta: 0:14:18 lr: 0.000125 grad: 0.0869 (0.1016) loss: 0.8702 (0.8675) time: 0.1954 data: 0.1060 max mem: 9390 +Train: [7] [1400/6250] eta: 0:13:58 lr: 0.000125 grad: 0.0930 (0.1013) loss: 0.8676 (0.8674) time: 0.1747 data: 0.0976 max mem: 9390 +Train: [7] [1500/6250] eta: 0:13:38 lr: 0.000125 grad: 0.0862 (0.1011) loss: 0.8651 (0.8674) time: 0.1791 data: 0.0985 max mem: 9390 +Train: [7] [1600/6250] eta: 0:13:16 lr: 0.000125 grad: 0.0888 (0.1007) loss: 0.8674 (0.8673) time: 0.1301 data: 0.0494 max mem: 9390 +Train: [7] [1700/6250] eta: 0:12:57 lr: 0.000125 grad: 0.0914 (0.1004) loss: 0.8657 (0.8672) time: 0.1589 data: 0.0791 max mem: 9390 +Train: [7] [1800/6250] eta: 0:12:47 lr: 0.000125 grad: 0.1004 (0.1003) loss: 0.8642 (0.8672) time: 0.1929 data: 0.0990 max mem: 9390 +Train: [7] [1900/6250] eta: 0:12:33 lr: 0.000125 grad: 0.0934 (0.1004) loss: 0.8644 (0.8671) time: 0.1967 data: 0.1239 max mem: 9390 +Train: [7] [2000/6250] eta: 0:12:16 lr: 0.000125 grad: 0.0894 (0.1000) loss: 0.8632 (0.8671) time: 0.1584 data: 0.0754 max mem: 9390 +Train: [7] [2100/6250] eta: 0:11:55 lr: 0.000125 grad: 0.0902 (0.0999) loss: 0.8671 (0.8671) time: 0.1585 data: 0.0796 max mem: 9390 +Train: [7] [2200/6250] eta: 0:11:40 lr: 0.000125 grad: 0.0927 (0.0998) loss: 0.8647 (0.8670) time: 0.1537 data: 0.0759 max mem: 9390 +Train: [7] [2300/6250] eta: 0:11:23 lr: 0.000125 grad: 0.0888 (0.0994) loss: 0.8634 (0.8668) time: 0.1954 data: 0.1158 max mem: 9390 +Train: [7] [2400/6250] eta: 0:11:04 lr: 0.000125 grad: 0.0880 (0.0997) loss: 0.8658 (0.8668) time: 0.1938 data: 0.1020 max mem: 9390 +Train: [7] [2500/6250] eta: 0:10:46 lr: 0.000125 grad: 0.0846 (0.0994) loss: 0.8646 (0.8667) time: 0.1428 data: 0.0544 max mem: 9390 +Train: [7] [2600/6250] eta: 0:10:34 lr: 0.000125 grad: 0.0895 (0.0989) loss: 0.8698 (0.8666) time: 0.2312 data: 0.1500 max mem: 9390 +Train: [7] [2700/6250] eta: 0:10:16 lr: 0.000125 grad: 0.0887 (0.0988) loss: 0.8600 (0.8665) time: 0.1454 data: 0.0575 max mem: 9390 +Train: [7] [2800/6250] eta: 0:09:58 lr: 0.000125 grad: 0.0825 (0.0989) loss: 0.8625 (0.8664) time: 0.1467 data: 0.0618 max mem: 9390 +Train: [7] [2900/6250] eta: 0:09:40 lr: 0.000125 grad: 0.0864 (0.0987) loss: 0.8635 (0.8662) time: 0.2031 data: 0.1251 max mem: 9390 +Train: [7] [3000/6250] eta: 0:09:24 lr: 0.000125 grad: 0.1054 (0.0987) loss: 0.8603 (0.8661) time: 0.1505 data: 0.0022 max mem: 9390 +Train: [7] [3100/6250] eta: 0:09:07 lr: 0.000125 grad: 0.0836 (0.0986) loss: 0.8599 (0.8659) time: 0.1418 data: 0.0617 max mem: 9390 +Train: [7] [3200/6250] eta: 0:08:54 lr: 0.000125 grad: 0.0969 (0.0984) loss: 0.8609 (0.8658) time: 0.3173 data: 0.2155 max mem: 9390 +Train: [7] [3300/6250] eta: 0:08:35 lr: 0.000125 grad: 0.0876 (0.0982) loss: 0.8622 (0.8657) time: 0.1405 data: 0.0518 max mem: 9390 +Train: [7] [3400/6250] eta: 0:08:19 lr: 0.000125 grad: 0.0896 (0.0982) loss: 0.8624 (0.8656) time: 0.3029 data: 0.2207 max mem: 9390 +Train: [7] [3500/6250] eta: 0:07:58 lr: 0.000125 grad: 0.0946 (0.0981) loss: 0.8610 (0.8655) time: 0.1315 data: 0.0420 max mem: 9390 +Train: [7] [3600/6250] eta: 0:07:39 lr: 0.000125 grad: 0.0845 (0.0979) loss: 0.8610 (0.8654) time: 0.1486 data: 0.0699 max mem: 9390 +Train: [7] [3700/6250] eta: 0:07:21 lr: 0.000125 grad: 0.0863 (0.0977) loss: 0.8659 (0.8654) time: 0.1544 data: 0.0724 max mem: 9390 +Train: [7] [3800/6250] eta: 0:07:03 lr: 0.000125 grad: 0.0820 (0.0975) loss: 0.8636 (0.8653) time: 0.1369 data: 0.0579 max mem: 9390 +Train: [7] [3900/6250] eta: 0:06:45 lr: 0.000125 grad: 0.0814 (0.0973) loss: 0.8649 (0.8653) time: 0.1378 data: 0.0552 max mem: 9390 +Train: [7] [4000/6250] eta: 0:06:27 lr: 0.000125 grad: 0.0942 (0.0972) loss: 0.8625 (0.8652) time: 0.1554 data: 0.0742 max mem: 9390 +Train: [7] [4100/6250] eta: 0:06:09 lr: 0.000125 grad: 0.0828 (0.0973) loss: 0.8617 (0.8651) time: 0.1623 data: 0.0817 max mem: 9390 +Train: [7] [4200/6250] eta: 0:05:52 lr: 0.000125 grad: 0.0841 (0.0970) loss: 0.8588 (0.8650) time: 0.1655 data: 0.0838 max mem: 9390 +Train: [7] [4300/6250] eta: 0:05:35 lr: 0.000125 grad: 0.0838 (0.0969) loss: 0.8629 (0.8649) time: 0.2549 data: 0.1772 max mem: 9390 +Train: [7] [4400/6250] eta: 0:05:18 lr: 0.000125 grad: 0.0871 (0.0967) loss: 0.8597 (0.8648) time: 0.2075 data: 0.1257 max mem: 9390 +Train: [7] [4500/6250] eta: 0:05:02 lr: 0.000125 grad: 0.0847 (0.0966) loss: 0.8632 (0.8647) time: 0.3211 data: 0.2071 max mem: 9390 +Train: [7] [4600/6250] eta: 0:04:45 lr: 0.000125 grad: 0.0846 (0.0963) loss: 0.8610 (0.8647) time: 0.1080 data: 0.0208 max mem: 9390 +Train: [7] [4700/6250] eta: 0:04:27 lr: 0.000125 grad: 0.0788 (0.0961) loss: 0.8608 (0.8646) time: 0.1409 data: 0.0632 max mem: 9390 +Train: [7] [4800/6250] eta: 0:04:09 lr: 0.000125 grad: 0.0902 (0.0963) loss: 0.8605 (0.8645) time: 0.1543 data: 0.0676 max mem: 9390 +Train: [7] [4900/6250] eta: 0:03:53 lr: 0.000125 grad: 0.0859 (0.0961) loss: 0.8558 (0.8644) time: 0.1602 data: 0.0710 max mem: 9390 +Train: [7] [5000/6250] eta: 0:03:36 lr: 0.000125 grad: 0.0817 (0.0959) loss: 0.8585 (0.8644) time: 0.1932 data: 0.1026 max mem: 9390 +Train: [7] [5100/6250] eta: 0:03:19 lr: 0.000125 grad: 0.0780 (0.0957) loss: 0.8638 (0.8643) time: 0.1983 data: 0.1143 max mem: 9390 +Train: [7] [5200/6250] eta: 0:03:01 lr: 0.000125 grad: 0.0867 (0.0956) loss: 0.8610 (0.8642) time: 0.1707 data: 0.0927 max mem: 9390 +Train: [7] [5300/6250] eta: 0:02:44 lr: 0.000125 grad: 0.0803 (0.0953) loss: 0.8669 (0.8642) time: 0.1649 data: 0.0870 max mem: 9390 +Train: [7] [5400/6250] eta: 0:02:27 lr: 0.000125 grad: 0.0890 (0.0952) loss: 0.8600 (0.8641) time: 0.2480 data: 0.1672 max mem: 9390 +Train: [7] [5500/6250] eta: 0:02:09 lr: 0.000125 grad: 0.0850 (0.0951) loss: 0.8581 (0.8641) time: 0.1744 data: 0.0902 max mem: 9390 +Train: [7] [5600/6250] eta: 0:01:52 lr: 0.000125 grad: 0.0789 (0.0948) loss: 0.8595 (0.8640) time: 0.1550 data: 0.0730 max mem: 9390 +Train: [7] [5700/6250] eta: 0:01:35 lr: 0.000125 grad: 0.0794 (0.0947) loss: 0.8611 (0.8640) time: 0.1392 data: 0.0513 max mem: 9390 +Train: [7] [5800/6250] eta: 0:01:17 lr: 0.000125 grad: 0.0833 (0.0945) loss: 0.8631 (0.8640) time: 0.0944 data: 0.0089 max mem: 9390 +Train: [7] [5900/6250] eta: 0:01:00 lr: 0.000125 grad: 0.0843 (0.0943) loss: 0.8659 (0.8639) time: 0.2198 data: 0.0905 max mem: 9390 +Train: [7] [6000/6250] eta: 0:00:43 lr: 0.000125 grad: 0.0739 (0.0942) loss: 0.8598 (0.8639) time: 0.1926 data: 0.1147 max mem: 9390 +Train: [7] [6100/6250] eta: 0:00:25 lr: 0.000125 grad: 0.0804 (0.0940) loss: 0.8638 (0.8639) time: 0.1571 data: 0.0790 max mem: 9390 +Train: [7] [6200/6250] eta: 0:00:08 lr: 0.000125 grad: 0.0780 (0.0939) loss: 0.8606 (0.8638) time: 0.1768 data: 0.0977 max mem: 9390 +Train: [7] [6249/6250] eta: 0:00:00 lr: 0.000125 grad: 0.0780 (0.0938) loss: 0.8611 (0.8638) time: 0.2858 data: 0.1958 max mem: 9390 +Train: [7] Total time: 0:18:07 (0.1739 s / it) +Averaged stats: lr: 0.000125 grad: 0.0780 (0.0938) loss: 0.8611 (0.8638) +Eval (hcp-train-subset): [7] [ 0/62] eta: 0:03:37 loss: 0.8718 (0.8718) time: 3.5154 data: 3.4205 max mem: 9390 +Eval (hcp-train-subset): [7] [61/62] eta: 0:00:00 loss: 0.8645 (0.8639) time: 0.1427 data: 0.1172 max mem: 9390 +Eval (hcp-train-subset): [7] Total time: 0:00:14 (0.2281 s / it) +Averaged stats (hcp-train-subset): loss: 0.8645 (0.8639) +Eval (hcp-val): [7] [ 0/62] eta: 0:04:19 loss: 0.8516 (0.8516) time: 4.1817 data: 4.1478 max mem: 9390 +Eval (hcp-val): [7] [61/62] eta: 0:00:00 loss: 0.8576 (0.8582) time: 0.1390 data: 0.1119 max mem: 9390 +Eval (hcp-val): [7] Total time: 0:00:14 (0.2299 s / it) +Averaged stats (hcp-val): loss: 0.8576 (0.8582) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +Train: [8] [ 0/6250] eta: 9:45:27 lr: 0.000125 grad: 0.0711 (0.0711) loss: 0.8833 (0.8833) time: 5.6203 data: 5.5088 max mem: 9390 +Train: [8] [ 100/6250] eta: 0:25:46 lr: 0.000125 grad: 0.0875 (0.0916) loss: 0.8668 (0.8651) time: 0.3062 data: 0.2245 max mem: 9390 +Train: [8] [ 200/6250] eta: 0:23:41 lr: 0.000125 grad: 0.0791 (0.0882) loss: 0.8588 (0.8629) time: 0.2007 data: 0.0357 max mem: 9390 +Train: [8] [ 300/6250] eta: 0:21:30 lr: 0.000125 grad: 0.0852 (0.0875) loss: 0.8594 (0.8621) time: 0.1614 data: 0.0674 max mem: 9390 +Train: [8] [ 400/6250] eta: 0:19:43 lr: 0.000125 grad: 0.0734 (0.0864) loss: 0.8578 (0.8619) time: 0.1714 data: 0.0877 max mem: 9390 +Train: [8] [ 500/6250] eta: 0:18:38 lr: 0.000125 grad: 0.0817 (0.0853) loss: 0.8657 (0.8623) time: 0.1717 data: 0.0840 max mem: 9390 +Train: [8] [ 600/6250] eta: 0:17:40 lr: 0.000125 grad: 0.0796 (0.0850) loss: 0.8626 (0.8625) time: 0.1584 data: 0.0667 max mem: 9390 +Train: [8] [ 700/6250] eta: 0:16:49 lr: 0.000125 grad: 0.0764 (0.0838) loss: 0.8605 (0.8626) time: 0.1504 data: 0.0626 max mem: 9390 +Train: [8] [ 800/6250] eta: 0:16:17 lr: 0.000125 grad: 0.0761 (0.0829) loss: 0.8623 (0.8628) time: 0.1752 data: 0.0851 max mem: 9390 +Train: [8] [ 900/6250] eta: 0:16:05 lr: 0.000125 grad: 0.0747 (0.0823) loss: 0.8579 (0.8628) time: 0.1275 data: 0.0211 max mem: 9390 +Train: [8] [1000/6250] eta: 0:15:58 lr: 0.000125 grad: 0.0825 (0.0817) loss: 0.8607 (0.8627) time: 0.1710 data: 0.0855 max mem: 9390 +Train: [8] [1100/6250] eta: 0:15:42 lr: 0.000125 grad: 0.0774 (0.0813) loss: 0.8643 (0.8627) time: 0.2761 data: 0.1884 max mem: 9390 +Train: [8] [1200/6250] eta: 0:15:30 lr: 0.000125 grad: 0.0757 (0.0811) loss: 0.8612 (0.8627) time: 0.1947 data: 0.1097 max mem: 9390 +Train: [8] [1300/6250] eta: 0:15:26 lr: 0.000125 grad: 0.0765 (0.0808) loss: 0.8644 (0.8626) time: 0.1625 data: 0.0766 max mem: 9390 +Train: [8] [1400/6250] eta: 0:15:04 lr: 0.000125 grad: 0.0706 (0.0807) loss: 0.8643 (0.8624) time: 0.1223 data: 0.0004 max mem: 9390 +Train: [8] [1500/6250] eta: 0:14:53 lr: 0.000125 grad: 0.0820 (0.0807) loss: 0.8607 (0.8622) time: 0.1493 data: 0.0640 max mem: 9390 +Train: [8] [1600/6250] eta: 0:14:27 lr: 0.000125 grad: 0.0749 (0.0805) loss: 0.8584 (0.8620) time: 0.1731 data: 0.0833 max mem: 9390 +Train: [8] [1700/6250] eta: 0:14:05 lr: 0.000125 grad: 0.0746 (0.0804) loss: 0.8604 (0.8620) time: 0.2053 data: 0.1252 max mem: 9390 +Train: [8] [1800/6250] eta: 0:13:44 lr: 0.000125 grad: 0.0802 (0.0803) loss: 0.8601 (0.8618) time: 0.1284 data: 0.0507 max mem: 9390 +Train: [8] [1900/6250] eta: 0:13:17 lr: 0.000125 grad: 0.0782 (0.0801) loss: 0.8609 (0.8618) time: 0.1584 data: 0.0727 max mem: 9390 +Train: [8] [2000/6250] eta: 0:12:54 lr: 0.000125 grad: 0.0791 (0.0800) loss: 0.8556 (0.8616) time: 0.1410 data: 0.0498 max mem: 9390 +Train: [8] [2100/6250] eta: 0:12:31 lr: 0.000125 grad: 0.0744 (0.0798) loss: 0.8607 (0.8615) time: 0.1606 data: 0.0842 max mem: 9390 +Train: [8] [2200/6250] eta: 0:12:09 lr: 0.000125 grad: 0.0777 (0.0797) loss: 0.8595 (0.8613) time: 0.1723 data: 0.0873 max mem: 9390 +Train: [8] [2300/6250] eta: 0:11:46 lr: 0.000125 grad: 0.0824 (0.0796) loss: 0.8582 (0.8612) time: 0.1491 data: 0.0670 max mem: 9390 +Train: [8] [2400/6250] eta: 0:11:25 lr: 0.000125 grad: 0.0815 (0.0797) loss: 0.8568 (0.8611) time: 0.1668 data: 0.0930 max mem: 9390 +Train: [8] [2500/6250] eta: 0:11:05 lr: 0.000125 grad: 0.0736 (0.0796) loss: 0.8610 (0.8609) time: 0.1642 data: 0.0782 max mem: 9390 +Train: [8] [2600/6250] eta: 0:10:45 lr: 0.000125 grad: 0.0745 (0.0794) loss: 0.8588 (0.8608) time: 0.1226 data: 0.0484 max mem: 9390 +Train: [8] [2700/6250] eta: 0:10:25 lr: 0.000125 grad: 0.0747 (0.0795) loss: 0.8567 (0.8607) time: 0.1810 data: 0.1081 max mem: 9390 +Train: [8] [2800/6250] eta: 0:10:06 lr: 0.000125 grad: 0.0706 (0.0795) loss: 0.8569 (0.8606) time: 0.1586 data: 0.0802 max mem: 9390 +Train: [8] [2900/6250] eta: 0:09:47 lr: 0.000125 grad: 0.0762 (0.0794) loss: 0.8604 (0.8606) time: 0.1685 data: 0.0882 max mem: 9390 +Train: [8] [3000/6250] eta: 0:09:28 lr: 0.000125 grad: 0.0719 (0.0794) loss: 0.8571 (0.8605) time: 0.1776 data: 0.0983 max mem: 9390 +Train: [8] [3100/6250] eta: 0:09:09 lr: 0.000125 grad: 0.0758 (0.0793) loss: 0.8555 (0.8604) time: 0.1696 data: 0.0918 max mem: 9390 +Train: [8] [3200/6250] eta: 0:08:51 lr: 0.000125 grad: 0.0741 (0.0793) loss: 0.8572 (0.8603) time: 0.1419 data: 0.0653 max mem: 9390 +Train: [8] [3300/6250] eta: 0:08:32 lr: 0.000125 grad: 0.0774 (0.0793) loss: 0.8615 (0.8603) time: 0.1568 data: 0.0691 max mem: 9390 +Train: [8] [3400/6250] eta: 0:08:14 lr: 0.000125 grad: 0.0718 (0.0792) loss: 0.8570 (0.8602) time: 0.1565 data: 0.0734 max mem: 9390 +Train: [8] [3500/6250] eta: 0:07:55 lr: 0.000125 grad: 0.0699 (0.0790) loss: 0.8608 (0.8602) time: 0.1413 data: 0.0584 max mem: 9390 +Train: [8] [3600/6250] eta: 0:07:37 lr: 0.000125 grad: 0.0712 (0.0789) loss: 0.8612 (0.8602) time: 0.1501 data: 0.0714 max mem: 9390 +Train: [8] [3700/6250] eta: 0:07:18 lr: 0.000125 grad: 0.0728 (0.0788) loss: 0.8544 (0.8601) time: 0.1537 data: 0.0747 max mem: 9390 +Train: [8] [3800/6250] eta: 0:07:00 lr: 0.000125 grad: 0.0808 (0.0789) loss: 0.8613 (0.8601) time: 0.1440 data: 0.0690 max mem: 9390 +Train: [8] [3900/6250] eta: 0:06:41 lr: 0.000125 grad: 0.0723 (0.0788) loss: 0.8587 (0.8601) time: 0.1447 data: 0.0558 max mem: 9390 +Train: [8] [4000/6250] eta: 0:06:23 lr: 0.000125 grad: 0.0704 (0.0787) loss: 0.8575 (0.8601) time: 0.1394 data: 0.0542 max mem: 9390 +Train: [8] [4100/6250] eta: 0:06:05 lr: 0.000125 grad: 0.0710 (0.0786) loss: 0.8617 (0.8601) time: 0.1363 data: 0.0498 max mem: 9390 +Train: [8] [4200/6250] eta: 0:05:46 lr: 0.000125 grad: 0.0719 (0.0786) loss: 0.8641 (0.8601) time: 0.1301 data: 0.0521 max mem: 9390 +Train: [8] [4300/6250] eta: 0:05:28 lr: 0.000125 grad: 0.0738 (0.0786) loss: 0.8613 (0.8600) time: 0.1426 data: 0.0529 max mem: 9390 +Train: [8] [4400/6250] eta: 0:05:10 lr: 0.000125 grad: 0.0714 (0.0786) loss: 0.8581 (0.8599) time: 0.1391 data: 0.0547 max mem: 9390 +Train: [8] [4500/6250] eta: 0:04:52 lr: 0.000125 grad: 0.0795 (0.0786) loss: 0.8611 (0.8599) time: 0.1161 data: 0.0293 max mem: 9390 +Train: [8] [4600/6250] eta: 0:04:34 lr: 0.000125 grad: 0.0713 (0.0786) loss: 0.8575 (0.8598) time: 0.1492 data: 0.0641 max mem: 9390 +Train: [8] [4700/6250] eta: 0:04:17 lr: 0.000125 grad: 0.0774 (0.0785) loss: 0.8525 (0.8597) time: 0.1365 data: 0.0586 max mem: 9390 +Train: [8] [4800/6250] eta: 0:04:00 lr: 0.000125 grad: 0.0759 (0.0785) loss: 0.8555 (0.8596) time: 0.1344 data: 0.0494 max mem: 9390 +Train: [8] [4900/6250] eta: 0:03:42 lr: 0.000125 grad: 0.0744 (0.0785) loss: 0.8534 (0.8595) time: 0.1435 data: 0.0635 max mem: 9390 +Train: [8] [5000/6250] eta: 0:03:25 lr: 0.000125 grad: 0.0730 (0.0785) loss: 0.8543 (0.8593) time: 0.1531 data: 0.0773 max mem: 9390 +Train: [8] [5100/6250] eta: 0:03:08 lr: 0.000125 grad: 0.0792 (0.0785) loss: 0.8550 (0.8592) time: 0.1213 data: 0.0404 max mem: 9390 +Train: [8] [5200/6250] eta: 0:02:51 lr: 0.000124 grad: 0.0766 (0.0785) loss: 0.8552 (0.8591) time: 0.1281 data: 0.0432 max mem: 9390 +Train: [8] [5300/6250] eta: 0:02:35 lr: 0.000124 grad: 0.0720 (0.0785) loss: 0.8483 (0.8590) time: 0.1419 data: 0.0611 max mem: 9390 +Train: [8] [5400/6250] eta: 0:02:18 lr: 0.000124 grad: 0.0753 (0.0784) loss: 0.8561 (0.8589) time: 0.1363 data: 0.0552 max mem: 9390 +Train: [8] [5500/6250] eta: 0:02:01 lr: 0.000124 grad: 0.0788 (0.0785) loss: 0.8562 (0.8588) time: 0.1434 data: 0.0649 max mem: 9390 +Train: [8] [5600/6250] eta: 0:01:45 lr: 0.000124 grad: 0.0714 (0.0784) loss: 0.8552 (0.8587) time: 0.1332 data: 0.0354 max mem: 9390 +Train: [8] [5700/6250] eta: 0:01:28 lr: 0.000124 grad: 0.0794 (0.0784) loss: 0.8505 (0.8586) time: 0.1041 data: 0.0157 max mem: 9390 +Train: [8] [5800/6250] eta: 0:01:12 lr: 0.000124 grad: 0.0721 (0.0783) loss: 0.8516 (0.8585) time: 0.1439 data: 0.0673 max mem: 9390 +Train: [8] [5900/6250] eta: 0:00:56 lr: 0.000124 grad: 0.0790 (0.0784) loss: 0.8550 (0.8584) time: 0.1276 data: 0.0513 max mem: 9390 +Train: [8] [6000/6250] eta: 0:00:40 lr: 0.000124 grad: 0.0775 (0.0784) loss: 0.8549 (0.8583) time: 0.1375 data: 0.0604 max mem: 9390 +Train: [8] [6100/6250] eta: 0:00:23 lr: 0.000124 grad: 0.0712 (0.0783) loss: 0.8541 (0.8582) time: 0.1536 data: 0.0722 max mem: 9390 +Train: [8] [6200/6250] eta: 0:00:07 lr: 0.000124 grad: 0.0786 (0.0783) loss: 0.8553 (0.8581) time: 0.1215 data: 0.0452 max mem: 9390 +Train: [8] [6249/6250] eta: 0:00:00 lr: 0.000124 grad: 0.0743 (0.0783) loss: 0.8531 (0.8581) time: 0.1347 data: 0.0557 max mem: 9390 +Train: [8] Total time: 0:16:43 (0.1605 s / it) +Averaged stats: lr: 0.000124 grad: 0.0743 (0.0783) loss: 0.8531 (0.8581) +Eval (hcp-train-subset): [8] [ 0/62] eta: 0:03:54 loss: 0.8677 (0.8677) time: 3.7792 data: 3.7170 max mem: 9390 +Eval (hcp-train-subset): [8] [61/62] eta: 0:00:00 loss: 0.8603 (0.8596) time: 0.1299 data: 0.1047 max mem: 9390 +Eval (hcp-train-subset): [8] Total time: 0:00:13 (0.2116 s / it) +Averaged stats (hcp-train-subset): loss: 0.8603 (0.8596) +Eval (hcp-val): [8] [ 0/62] eta: 0:03:27 loss: 0.8516 (0.8516) time: 3.3461 data: 3.2630 max mem: 9390 +Eval (hcp-val): [8] [61/62] eta: 0:00:00 loss: 0.8529 (0.8537) time: 0.1283 data: 0.1032 max mem: 9390 +Eval (hcp-val): [8] Total time: 0:00:12 (0.2004 s / it) +Averaged stats (hcp-val): loss: 0.8529 (0.8537) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +Train: [9] [ 0/6250] eta: 8:32:57 lr: 0.000124 grad: 0.0695 (0.0695) loss: 0.8703 (0.8703) time: 4.9244 data: 4.8229 max mem: 9390 +Train: [9] [ 100/6250] eta: 0:20:50 lr: 0.000124 grad: 0.0810 (0.0782) loss: 0.8554 (0.8579) time: 0.1600 data: 0.0738 max mem: 9390 +Train: [9] [ 200/6250] eta: 0:18:17 lr: 0.000124 grad: 0.0821 (0.0783) loss: 0.8559 (0.8565) time: 0.1625 data: 0.0810 max mem: 9390 +Train: [9] [ 300/6250] eta: 0:16:54 lr: 0.000124 grad: 0.0779 (0.0777) loss: 0.8487 (0.8547) time: 0.1553 data: 0.0721 max mem: 9390 +Train: [9] [ 400/6250] eta: 0:16:09 lr: 0.000124 grad: 0.0732 (0.0779) loss: 0.8499 (0.8537) time: 0.1264 data: 0.0386 max mem: 9390 +Train: [9] [ 500/6250] eta: 0:15:25 lr: 0.000124 grad: 0.0758 (0.0791) loss: 0.8526 (0.8538) time: 0.1409 data: 0.0541 max mem: 9390 +Train: [9] [ 600/6250] eta: 0:14:45 lr: 0.000124 grad: 0.0762 (0.0789) loss: 0.8573 (0.8537) time: 0.1440 data: 0.0513 max mem: 9390 +Train: [9] [ 700/6250] eta: 0:14:18 lr: 0.000124 grad: 0.0765 (0.0787) loss: 0.8562 (0.8536) time: 0.1617 data: 0.0867 max mem: 9390 +Train: [9] [ 800/6250] eta: 0:13:52 lr: 0.000124 grad: 0.0769 (0.0788) loss: 0.8519 (0.8534) time: 0.1379 data: 0.0500 max mem: 9390 +Train: [9] [ 900/6250] eta: 0:13:40 lr: 0.000124 grad: 0.0733 (0.0784) loss: 0.8539 (0.8532) time: 0.1756 data: 0.0897 max mem: 9390 +Train: [9] [1000/6250] eta: 0:13:24 lr: 0.000124 grad: 0.0779 (0.0782) loss: 0.8505 (0.8531) time: 0.1361 data: 0.0509 max mem: 9390 +Train: [9] [1100/6250] eta: 0:13:09 lr: 0.000124 grad: 0.0703 (0.0778) loss: 0.8555 (0.8531) time: 0.1411 data: 0.0597 max mem: 9390 +Train: [9] [1200/6250] eta: 0:12:52 lr: 0.000124 grad: 0.0886 (0.0780) loss: 0.8490 (0.8528) time: 0.1484 data: 0.0638 max mem: 9390 +Train: [9] [1300/6250] eta: 0:12:36 lr: 0.000124 grad: 0.0733 (0.0777) loss: 0.8511 (0.8527) time: 0.1870 data: 0.1057 max mem: 9390 +Train: [9] [1400/6250] eta: 0:12:19 lr: 0.000124 grad: 0.0702 (0.0778) loss: 0.8565 (0.8527) time: 0.1609 data: 0.0797 max mem: 9390 +Train: [9] [1500/6250] eta: 0:12:03 lr: 0.000124 grad: 0.0693 (0.0775) loss: 0.8570 (0.8528) time: 0.1463 data: 0.0673 max mem: 9390 +Train: [9] [1600/6250] eta: 0:11:48 lr: 0.000124 grad: 0.0711 (0.0775) loss: 0.8518 (0.8529) time: 0.1632 data: 0.0778 max mem: 9390 +Train: [9] [1700/6250] eta: 0:11:31 lr: 0.000124 grad: 0.0722 (0.0776) loss: 0.8508 (0.8529) time: 0.1511 data: 0.0725 max mem: 9390 +Train: [9] [1800/6250] eta: 0:11:16 lr: 0.000124 grad: 0.0717 (0.0773) loss: 0.8504 (0.8528) time: 0.1711 data: 0.0836 max mem: 9390 +Train: [9] [1900/6250] eta: 0:11:01 lr: 0.000124 grad: 0.0792 (0.0771) loss: 0.8476 (0.8527) time: 0.1556 data: 0.0672 max mem: 9390 +Train: [9] [2000/6250] eta: 0:10:45 lr: 0.000124 grad: 0.0737 (0.0773) loss: 0.8503 (0.8527) time: 0.1532 data: 0.0736 max mem: 9390 +Train: [9] [2100/6250] eta: 0:10:30 lr: 0.000124 grad: 0.0786 (0.0772) loss: 0.8517 (0.8526) time: 0.1645 data: 0.0886 max mem: 9390 +Train: [9] [2200/6250] eta: 0:10:16 lr: 0.000124 grad: 0.0708 (0.0771) loss: 0.8537 (0.8526) time: 0.1508 data: 0.0693 max mem: 9390 +Train: [9] [2300/6250] eta: 0:10:03 lr: 0.000124 grad: 0.0735 (0.0770) loss: 0.8526 (0.8526) time: 0.1853 data: 0.1041 max mem: 9390 +Train: [9] [2400/6250] eta: 0:09:49 lr: 0.000124 grad: 0.0760 (0.0770) loss: 0.8545 (0.8526) time: 0.1975 data: 0.1167 max mem: 9390 +Train: [9] [2500/6250] eta: 0:09:35 lr: 0.000124 grad: 0.0733 (0.0768) loss: 0.8532 (0.8525) time: 0.1683 data: 0.0877 max mem: 9390 +Train: [9] [2600/6250] eta: 0:09:18 lr: 0.000124 grad: 0.0694 (0.0767) loss: 0.8508 (0.8525) time: 0.1502 data: 0.0725 max mem: 9390 +Train: [9] [2700/6250] eta: 0:09:04 lr: 0.000124 grad: 0.0724 (0.0767) loss: 0.8567 (0.8525) time: 0.1553 data: 0.0787 max mem: 9390 +Train: [9] [2800/6250] eta: 0:08:50 lr: 0.000124 grad: 0.0722 (0.0766) loss: 0.8513 (0.8524) time: 0.1577 data: 0.0751 max mem: 9390 +Train: [9] [2900/6250] eta: 0:08:37 lr: 0.000124 grad: 0.0710 (0.0765) loss: 0.8501 (0.8524) time: 0.1736 data: 0.0976 max mem: 9390 +Train: [9] [3000/6250] eta: 0:08:23 lr: 0.000124 grad: 0.0710 (0.0766) loss: 0.8480 (0.8523) time: 0.1570 data: 0.0778 max mem: 9390 +Train: [9] [3100/6250] eta: 0:08:08 lr: 0.000124 grad: 0.0718 (0.0766) loss: 0.8482 (0.8522) time: 0.1615 data: 0.0790 max mem: 9390 +Train: [9] [3200/6250] eta: 0:07:53 lr: 0.000124 grad: 0.0727 (0.0765) loss: 0.8486 (0.8521) time: 0.1552 data: 0.0785 max mem: 9390 +Train: [9] [3300/6250] eta: 0:07:37 lr: 0.000124 grad: 0.0669 (0.0765) loss: 0.8520 (0.8520) time: 0.1492 data: 0.0735 max mem: 9390 +Train: [9] [3400/6250] eta: 0:07:21 lr: 0.000124 grad: 0.0700 (0.0765) loss: 0.8486 (0.8520) time: 0.1433 data: 0.0597 max mem: 9390 +Train: [9] [3500/6250] eta: 0:07:06 lr: 0.000124 grad: 0.0725 (0.0764) loss: 0.8477 (0.8519) time: 0.1561 data: 0.0769 max mem: 9390 +Train: [9] [3600/6250] eta: 0:06:50 lr: 0.000124 grad: 0.0700 (0.0763) loss: 0.8503 (0.8519) time: 0.1455 data: 0.0644 max mem: 9390 +Train: [9] [3700/6250] eta: 0:06:35 lr: 0.000124 grad: 0.0722 (0.0762) loss: 0.8535 (0.8520) time: 0.1773 data: 0.0950 max mem: 9390 +Train: [9] [3800/6250] eta: 0:06:18 lr: 0.000124 grad: 0.0691 (0.0761) loss: 0.8503 (0.8520) time: 0.1447 data: 0.0623 max mem: 9390 +Train: [9] [3900/6250] eta: 0:06:03 lr: 0.000124 grad: 0.0658 (0.0760) loss: 0.8511 (0.8520) time: 0.1526 data: 0.0741 max mem: 9390 +Train: [9] [4000/6250] eta: 0:05:47 lr: 0.000124 grad: 0.0708 (0.0760) loss: 0.8463 (0.8519) time: 0.1134 data: 0.0318 max mem: 9390 +Train: [9] [4100/6250] eta: 0:05:31 lr: 0.000124 grad: 0.0722 (0.0759) loss: 0.8506 (0.8519) time: 0.1543 data: 0.0727 max mem: 9390 +Train: [9] [4200/6250] eta: 0:05:16 lr: 0.000124 grad: 0.0707 (0.0759) loss: 0.8495 (0.8519) time: 0.1683 data: 0.0903 max mem: 9390 +Train: [9] [4300/6250] eta: 0:05:00 lr: 0.000124 grad: 0.0712 (0.0757) loss: 0.8534 (0.8519) time: 0.1586 data: 0.0803 max mem: 9390 +Train: [9] [4400/6250] eta: 0:04:45 lr: 0.000124 grad: 0.0687 (0.0756) loss: 0.8510 (0.8519) time: 0.1607 data: 0.0812 max mem: 9390 +Train: [9] [4500/6250] eta: 0:04:29 lr: 0.000124 grad: 0.0651 (0.0755) loss: 0.8535 (0.8519) time: 0.1319 data: 0.0485 max mem: 9390 +Train: [9] [4600/6250] eta: 0:04:14 lr: 0.000124 grad: 0.0687 (0.0755) loss: 0.8519 (0.8519) time: 0.1613 data: 0.0841 max mem: 9390 +Train: [9] [4700/6250] eta: 0:03:59 lr: 0.000124 grad: 0.0655 (0.0756) loss: 0.8510 (0.8520) time: 0.1580 data: 0.0652 max mem: 9390 +Train: [9] [4800/6250] eta: 0:03:44 lr: 0.000124 grad: 0.0710 (0.0756) loss: 0.8522 (0.8520) time: 0.1595 data: 0.0768 max mem: 9390 +Train: [9] [4900/6250] eta: 0:03:29 lr: 0.000124 grad: 0.0722 (0.0756) loss: 0.8491 (0.8520) time: 0.1500 data: 0.0662 max mem: 9390 +Train: [9] [5000/6250] eta: 0:03:13 lr: 0.000124 grad: 0.0669 (0.0755) loss: 0.8577 (0.8521) time: 0.1736 data: 0.0913 max mem: 9390 +Train: [9] [5100/6250] eta: 0:02:58 lr: 0.000124 grad: 0.0667 (0.0754) loss: 0.8536 (0.8521) time: 0.1313 data: 0.0510 max mem: 9390 +Train: [9] [5200/6250] eta: 0:02:42 lr: 0.000124 grad: 0.0713 (0.0754) loss: 0.8525 (0.8522) time: 0.1579 data: 0.0815 max mem: 9390 +Train: [9] [5300/6250] eta: 0:02:27 lr: 0.000124 grad: 0.0774 (0.0756) loss: 0.8520 (0.8522) time: 0.1347 data: 0.0445 max mem: 9390 +Train: [9] [5400/6250] eta: 0:02:11 lr: 0.000124 grad: 0.0690 (0.0755) loss: 0.8493 (0.8522) time: 0.1283 data: 0.0434 max mem: 9390 +Train: [9] [5500/6250] eta: 0:01:55 lr: 0.000124 grad: 0.0701 (0.0754) loss: 0.8492 (0.8522) time: 0.1694 data: 0.0900 max mem: 9390 +Train: [9] [5600/6250] eta: 0:01:40 lr: 0.000124 grad: 0.0679 (0.0754) loss: 0.8561 (0.8522) time: 0.1570 data: 0.0749 max mem: 9390 +Train: [9] [5700/6250] eta: 0:01:24 lr: 0.000124 grad: 0.0669 (0.0753) loss: 0.8490 (0.8522) time: 0.1573 data: 0.0767 max mem: 9390 +Train: [9] [5800/6250] eta: 0:01:09 lr: 0.000124 grad: 0.0690 (0.0752) loss: 0.8554 (0.8523) time: 0.2477 data: 0.1684 max mem: 9390 +Train: [9] [5900/6250] eta: 0:00:54 lr: 0.000124 grad: 0.0657 (0.0752) loss: 0.8539 (0.8523) time: 0.1710 data: 0.0901 max mem: 9390 +Train: [9] [6000/6250] eta: 0:00:38 lr: 0.000124 grad: 0.0674 (0.0751) loss: 0.8553 (0.8523) time: 0.1488 data: 0.0688 max mem: 9390 +Train: [9] [6100/6250] eta: 0:00:23 lr: 0.000124 grad: 0.0639 (0.0750) loss: 0.8551 (0.8523) time: 0.1497 data: 0.0672 max mem: 9390 +Train: [9] [6200/6250] eta: 0:00:07 lr: 0.000124 grad: 0.0678 (0.0750) loss: 0.8506 (0.8524) time: 0.1521 data: 0.0714 max mem: 9390 +Train: [9] [6249/6250] eta: 0:00:00 lr: 0.000124 grad: 0.0644 (0.0749) loss: 0.8512 (0.8524) time: 0.1415 data: 0.0605 max mem: 9390 +Train: [9] Total time: 0:16:08 (0.1549 s / it) +Averaged stats: lr: 0.000124 grad: 0.0644 (0.0749) loss: 0.8512 (0.8524) +Eval (hcp-train-subset): [9] [ 0/62] eta: 0:03:00 loss: 0.8677 (0.8677) time: 2.9079 data: 2.8343 max mem: 9390 +Eval (hcp-train-subset): [9] [61/62] eta: 0:00:00 loss: 0.8582 (0.8569) time: 0.1214 data: 0.0938 max mem: 9390 +Eval (hcp-train-subset): [9] Total time: 0:00:12 (0.1999 s / it) +Averaged stats (hcp-train-subset): loss: 0.8582 (0.8569) +Making plots (hcp-train-subset): example=61 +Eval (hcp-val): [9] [ 0/62] eta: 0:02:52 loss: 0.8531 (0.8531) time: 2.7755 data: 2.7136 max mem: 9390 +Eval (hcp-val): [9] [61/62] eta: 0:00:00 loss: 0.8517 (0.8519) time: 0.1303 data: 0.1055 max mem: 9390 +Eval (hcp-val): [9] Total time: 0:00:12 (0.2024 s / it) +Averaged stats (hcp-val): loss: 0.8517 (0.8519) +Making plots (hcp-val): example=20 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +Train: [10] [ 0/6250] eta: 8:38:43 lr: 0.000124 grad: 0.0719 (0.0719) loss: 0.8811 (0.8811) time: 4.9798 data: 4.7612 max mem: 9390 +Train: [10] [ 100/6250] eta: 0:20:49 lr: 0.000124 grad: 0.0749 (0.0843) loss: 0.8479 (0.8499) time: 0.1541 data: 0.0749 max mem: 9390 +Train: [10] [ 200/6250] eta: 0:18:02 lr: 0.000124 grad: 0.0733 (0.0804) loss: 0.8426 (0.8469) time: 0.1282 data: 0.0477 max mem: 9390 +Train: [10] [ 300/6250] eta: 0:16:46 lr: 0.000124 grad: 0.0677 (0.0777) loss: 0.8551 (0.8484) time: 0.1469 data: 0.0639 max mem: 9390 +Train: [10] [ 400/6250] eta: 0:16:00 lr: 0.000124 grad: 0.0683 (0.0763) loss: 0.8548 (0.8495) time: 0.1488 data: 0.0640 max mem: 9390 +Train: [10] [ 500/6250] eta: 0:15:20 lr: 0.000124 grad: 0.0698 (0.0755) loss: 0.8508 (0.8501) time: 0.1616 data: 0.0779 max mem: 9390 +Train: [10] [ 600/6250] eta: 0:14:44 lr: 0.000124 grad: 0.0713 (0.0756) loss: 0.8505 (0.8504) time: 0.1423 data: 0.0501 max mem: 9390 +Train: [10] [ 700/6250] eta: 0:14:15 lr: 0.000124 grad: 0.0687 (0.0753) loss: 0.8524 (0.8505) time: 0.1307 data: 0.0328 max mem: 9390 +Train: [10] [ 800/6250] eta: 0:13:59 lr: 0.000124 grad: 0.0668 (0.0748) loss: 0.8547 (0.8509) time: 0.1561 data: 0.0789 max mem: 9390 +Train: [10] [ 900/6250] eta: 0:13:43 lr: 0.000124 grad: 0.0671 (0.0743) loss: 0.8556 (0.8513) time: 0.1422 data: 0.0659 max mem: 9390 +Train: [10] [1000/6250] eta: 0:13:36 lr: 0.000124 grad: 0.0660 (0.0739) loss: 0.8511 (0.8514) time: 0.1382 data: 0.0552 max mem: 9390 +Train: [10] [1100/6250] eta: 0:13:38 lr: 0.000124 grad: 0.0669 (0.0735) loss: 0.8545 (0.8516) time: 0.2145 data: 0.1109 max mem: 9390 +Train: [10] [1200/6250] eta: 0:13:23 lr: 0.000124 grad: 0.0661 (0.0731) loss: 0.8535 (0.8518) time: 0.0875 data: 0.0003 max mem: 9390 +Train: [10] [1300/6250] eta: 0:13:01 lr: 0.000124 grad: 0.0670 (0.0726) loss: 0.8548 (0.8519) time: 0.1661 data: 0.0862 max mem: 9390 +Train: [10] [1400/6250] eta: 0:12:53 lr: 0.000124 grad: 0.0674 (0.0723) loss: 0.8533 (0.8521) time: 0.3333 data: 0.2502 max mem: 9390 +Train: [10] [1500/6250] eta: 0:12:30 lr: 0.000124 grad: 0.0645 (0.0720) loss: 0.8523 (0.8522) time: 0.1314 data: 0.0493 max mem: 9390 +Train: [10] [1600/6250] eta: 0:12:12 lr: 0.000124 grad: 0.0683 (0.0718) loss: 0.8567 (0.8523) time: 0.1290 data: 0.0490 max mem: 9390 +Train: [10] [1700/6250] eta: 0:11:56 lr: 0.000124 grad: 0.0714 (0.0716) loss: 0.8483 (0.8524) time: 0.1775 data: 0.0973 max mem: 9390 +Train: [10] [1800/6250] eta: 0:11:36 lr: 0.000124 grad: 0.0670 (0.0715) loss: 0.8543 (0.8525) time: 0.1276 data: 0.0349 max mem: 9390 +Train: [10] [1900/6250] eta: 0:11:19 lr: 0.000124 grad: 0.0672 (0.0714) loss: 0.8503 (0.8525) time: 0.1347 data: 0.0403 max mem: 9390 +Train: [10] [2000/6250] eta: 0:11:06 lr: 0.000124 grad: 0.0668 (0.0714) loss: 0.8484 (0.8524) time: 0.2717 data: 0.1848 max mem: 9390 +Train: [10] [2100/6250] eta: 0:10:44 lr: 0.000124 grad: 0.0667 (0.0713) loss: 0.8526 (0.8524) time: 0.1380 data: 0.0567 max mem: 9390 +Train: [10] [2200/6250] eta: 0:10:27 lr: 0.000124 grad: 0.0634 (0.0711) loss: 0.8525 (0.8524) time: 0.1718 data: 0.0945 max mem: 9390 +Train: [10] [2300/6250] eta: 0:10:13 lr: 0.000124 grad: 0.0754 (0.0711) loss: 0.8529 (0.8524) time: 0.1401 data: 0.0629 max mem: 9390 +Train: [10] [2400/6250] eta: 0:09:56 lr: 0.000124 grad: 0.0651 (0.0710) loss: 0.8511 (0.8523) time: 0.1441 data: 0.0665 max mem: 9390 +Train: [10] [2500/6250] eta: 0:09:40 lr: 0.000124 grad: 0.0708 (0.0709) loss: 0.8541 (0.8523) time: 0.1489 data: 0.0692 max mem: 9390 +Train: [10] [2600/6250] eta: 0:09:23 lr: 0.000124 grad: 0.0673 (0.0709) loss: 0.8464 (0.8523) time: 0.1235 data: 0.0427 max mem: 9390 +Train: [10] [2700/6250] eta: 0:09:08 lr: 0.000124 grad: 0.0648 (0.0708) loss: 0.8470 (0.8522) time: 0.1707 data: 0.0888 max mem: 9390 +Train: [10] [2800/6250] eta: 0:08:52 lr: 0.000124 grad: 0.0695 (0.0708) loss: 0.8495 (0.8522) time: 0.1591 data: 0.0773 max mem: 9390 +Train: [10] [2900/6250] eta: 0:08:37 lr: 0.000124 grad: 0.0660 (0.0707) loss: 0.8527 (0.8521) time: 0.1536 data: 0.0700 max mem: 9390 +Train: [10] [3000/6250] eta: 0:08:21 lr: 0.000124 grad: 0.0701 (0.0707) loss: 0.8506 (0.8521) time: 0.1389 data: 0.0580 max mem: 9390 +Train: [10] [3100/6250] eta: 0:08:03 lr: 0.000124 grad: 0.0662 (0.0706) loss: 0.8547 (0.8521) time: 0.1245 data: 0.0461 max mem: 9390 +Train: [10] [3200/6250] eta: 0:07:46 lr: 0.000124 grad: 0.0655 (0.0706) loss: 0.8492 (0.8521) time: 0.1273 data: 0.0421 max mem: 9390 +Train: [10] [3300/6250] eta: 0:07:30 lr: 0.000124 grad: 0.0674 (0.0704) loss: 0.8567 (0.8522) time: 0.1272 data: 0.0408 max mem: 9390 +Train: [10] [3400/6250] eta: 0:07:13 lr: 0.000124 grad: 0.0635 (0.0704) loss: 0.8544 (0.8522) time: 0.1169 data: 0.0302 max mem: 9390 +Train: [10] [3500/6250] eta: 0:06:57 lr: 0.000124 grad: 0.0669 (0.0703) loss: 0.8555 (0.8522) time: 0.1433 data: 0.0584 max mem: 9390 +Train: [10] [3600/6250] eta: 0:06:41 lr: 0.000124 grad: 0.0655 (0.0702) loss: 0.8541 (0.8522) time: 0.1462 data: 0.0686 max mem: 9390 +Train: [10] [3700/6250] eta: 0:06:25 lr: 0.000124 grad: 0.0661 (0.0702) loss: 0.8512 (0.8522) time: 0.1322 data: 0.0575 max mem: 9390 +Train: [10] [3800/6250] eta: 0:06:09 lr: 0.000124 grad: 0.0678 (0.0701) loss: 0.8510 (0.8521) time: 0.1141 data: 0.0320 max mem: 9390 +Train: [10] [3900/6250] eta: 0:05:58 lr: 0.000124 grad: 0.0684 (0.0701) loss: 0.8488 (0.8521) time: 0.1454 data: 0.0551 max mem: 9390 +Train: [10] [4000/6250] eta: 0:05:43 lr: 0.000124 grad: 0.0634 (0.0700) loss: 0.8485 (0.8520) time: 0.1635 data: 0.0848 max mem: 9390 +Train: [10] [4100/6250] eta: 0:05:29 lr: 0.000124 grad: 0.0669 (0.0701) loss: 0.8469 (0.8520) time: 0.1644 data: 0.0742 max mem: 9390 +Train: [10] [4200/6250] eta: 0:05:15 lr: 0.000124 grad: 0.0661 (0.0701) loss: 0.8507 (0.8519) time: 0.1316 data: 0.0401 max mem: 9390 +Train: [10] [4300/6250] eta: 0:05:01 lr: 0.000124 grad: 0.0666 (0.0700) loss: 0.8475 (0.8518) time: 0.2954 data: 0.2057 max mem: 9390 +Train: [10] [4400/6250] eta: 0:04:50 lr: 0.000124 grad: 0.0669 (0.0700) loss: 0.8470 (0.8517) time: 0.4700 data: 0.3713 max mem: 9390 +Train: [10] [4500/6250] eta: 0:04:34 lr: 0.000124 grad: 0.0666 (0.0700) loss: 0.8505 (0.8517) time: 0.1914 data: 0.1057 max mem: 9390 +Train: [10] [4600/6250] eta: 0:04:18 lr: 0.000124 grad: 0.0648 (0.0700) loss: 0.8525 (0.8516) time: 0.1916 data: 0.1172 max mem: 9390 +Train: [10] [4700/6250] eta: 0:04:03 lr: 0.000124 grad: 0.0676 (0.0700) loss: 0.8491 (0.8516) time: 0.1819 data: 0.1015 max mem: 9390 +Train: [10] [4800/6250] eta: 0:03:47 lr: 0.000124 grad: 0.0673 (0.0700) loss: 0.8560 (0.8515) time: 0.1971 data: 0.1087 max mem: 9390 +Train: [10] [4900/6250] eta: 0:03:32 lr: 0.000124 grad: 0.0679 (0.0700) loss: 0.8520 (0.8515) time: 0.2236 data: 0.1344 max mem: 9390 +Train: [10] [5000/6250] eta: 0:03:16 lr: 0.000124 grad: 0.0676 (0.0700) loss: 0.8486 (0.8514) time: 0.1614 data: 0.0781 max mem: 9390 +Train: [10] [5100/6250] eta: 0:03:01 lr: 0.000124 grad: 0.0664 (0.0700) loss: 0.8486 (0.8514) time: 0.1809 data: 0.0902 max mem: 9390 +Train: [10] [5200/6250] eta: 0:02:46 lr: 0.000124 grad: 0.0662 (0.0699) loss: 0.8469 (0.8513) time: 0.1778 data: 0.0956 max mem: 9390 +Train: [10] [5300/6250] eta: 0:02:31 lr: 0.000124 grad: 0.0667 (0.0700) loss: 0.8493 (0.8512) time: 0.1703 data: 0.0640 max mem: 9390 +Train: [10] [5400/6250] eta: 0:02:15 lr: 0.000124 grad: 0.0690 (0.0700) loss: 0.8457 (0.8512) time: 0.0960 data: 0.0002 max mem: 9390 +Train: [10] [5500/6250] eta: 0:01:59 lr: 0.000124 grad: 0.0666 (0.0700) loss: 0.8443 (0.8511) time: 0.1458 data: 0.0577 max mem: 9390 +Train: [10] [5600/6250] eta: 0:01:43 lr: 0.000124 grad: 0.0652 (0.0700) loss: 0.8429 (0.8510) time: 0.1462 data: 0.0607 max mem: 9390 +Train: [10] [5700/6250] eta: 0:01:27 lr: 0.000124 grad: 0.0684 (0.0699) loss: 0.8474 (0.8510) time: 0.1442 data: 0.0625 max mem: 9390 +Train: [10] [5800/6250] eta: 0:01:11 lr: 0.000124 grad: 0.0633 (0.0699) loss: 0.8513 (0.8510) time: 0.1616 data: 0.0767 max mem: 9390 +Train: [10] [5900/6250] eta: 0:00:55 lr: 0.000124 grad: 0.0685 (0.0699) loss: 0.8477 (0.8509) time: 0.1629 data: 0.0824 max mem: 9390 +Train: [10] [6000/6250] eta: 0:00:39 lr: 0.000124 grad: 0.0611 (0.0698) loss: 0.8542 (0.8509) time: 0.1447 data: 0.0584 max mem: 9390 +Train: [10] [6100/6250] eta: 0:00:23 lr: 0.000124 grad: 0.0634 (0.0698) loss: 0.8507 (0.8509) time: 0.1977 data: 0.1203 max mem: 9390 +Train: [10] [6200/6250] eta: 0:00:07 lr: 0.000124 grad: 0.0674 (0.0697) loss: 0.8475 (0.8508) time: 0.1416 data: 0.0553 max mem: 9390 +Train: [10] [6249/6250] eta: 0:00:00 lr: 0.000124 grad: 0.0619 (0.0697) loss: 0.8512 (0.8508) time: 0.1446 data: 0.0598 max mem: 9390 +Train: [10] Total time: 0:16:44 (0.1606 s / it) +Averaged stats: lr: 0.000124 grad: 0.0619 (0.0697) loss: 0.8512 (0.8508) +Eval (hcp-train-subset): [10] [ 0/62] eta: 0:05:02 loss: 0.8649 (0.8649) time: 4.8816 data: 4.8503 max mem: 9390 +Eval (hcp-train-subset): [10] [61/62] eta: 0:00:00 loss: 0.8526 (0.8543) time: 0.1081 data: 0.0830 max mem: 9390 +Eval (hcp-train-subset): [10] Total time: 0:00:13 (0.2185 s / it) +Averaged stats (hcp-train-subset): loss: 0.8526 (0.8543) +Eval (hcp-val): [10] [ 0/62] eta: 0:03:44 loss: 0.8457 (0.8457) time: 3.6259 data: 3.5605 max mem: 9390 +Eval (hcp-val): [10] [61/62] eta: 0:00:00 loss: 0.8476 (0.8486) time: 0.1242 data: 0.0992 max mem: 9390 +Eval (hcp-val): [10] Total time: 0:00:13 (0.2217 s / it) +Averaged stats (hcp-val): loss: 0.8476 (0.8486) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +Train: [11] [ 0/6250] eta: 7:41:37 lr: 0.000124 grad: 0.1996 (0.1996) loss: 0.8094 (0.8094) time: 4.4317 data: 4.2512 max mem: 9390 +Train: [11] [ 100/6250] eta: 0:23:25 lr: 0.000124 grad: 0.0711 (0.0872) loss: 0.8428 (0.8496) time: 0.1827 data: 0.0973 max mem: 9390 +Train: [11] [ 200/6250] eta: 0:21:24 lr: 0.000124 grad: 0.0693 (0.0814) loss: 0.8532 (0.8490) time: 0.1762 data: 0.0966 max mem: 9390 +Train: [11] [ 300/6250] eta: 0:19:49 lr: 0.000124 grad: 0.0683 (0.0775) loss: 0.8480 (0.8492) time: 0.1834 data: 0.1077 max mem: 9390 +Train: [11] [ 400/6250] eta: 0:18:40 lr: 0.000124 grad: 0.0698 (0.0755) loss: 0.8539 (0.8502) time: 0.1572 data: 0.0684 max mem: 9390 +Train: [11] [ 500/6250] eta: 0:18:02 lr: 0.000124 grad: 0.0810 (0.0755) loss: 0.8466 (0.8504) time: 0.1896 data: 0.0966 max mem: 9390 +Train: [11] [ 600/6250] eta: 0:17:13 lr: 0.000124 grad: 0.0625 (0.0749) loss: 0.8509 (0.8505) time: 0.1332 data: 0.0481 max mem: 9390 +Train: [11] [ 700/6250] eta: 0:16:37 lr: 0.000124 grad: 0.0678 (0.0740) loss: 0.8489 (0.8502) time: 0.1594 data: 0.0708 max mem: 9390 +Train: [11] [ 800/6250] eta: 0:16:03 lr: 0.000124 grad: 0.0623 (0.0731) loss: 0.8480 (0.8503) time: 0.1564 data: 0.0731 max mem: 9390 +Train: [11] [ 900/6250] eta: 0:15:37 lr: 0.000124 grad: 0.0636 (0.0726) loss: 0.8548 (0.8502) time: 0.1304 data: 0.0462 max mem: 9390 +Train: [11] [1000/6250] eta: 0:15:08 lr: 0.000124 grad: 0.0671 (0.0720) loss: 0.8508 (0.8503) time: 0.1772 data: 0.0898 max mem: 9390 +Train: [11] [1100/6250] eta: 0:14:44 lr: 0.000124 grad: 0.0638 (0.0715) loss: 0.8512 (0.8502) time: 0.1432 data: 0.0570 max mem: 9390 +Train: [11] [1200/6250] eta: 0:14:38 lr: 0.000124 grad: 0.0669 (0.0711) loss: 0.8456 (0.8500) time: 0.1563 data: 0.0729 max mem: 9390 +Train: [11] [1300/6250] eta: 0:14:24 lr: 0.000124 grad: 0.0637 (0.0709) loss: 0.8500 (0.8499) time: 0.1958 data: 0.1145 max mem: 9390 +Train: [11] [1400/6250] eta: 0:13:59 lr: 0.000124 grad: 0.0637 (0.0707) loss: 0.8525 (0.8498) time: 0.1528 data: 0.0731 max mem: 9390 +Train: [11] [1500/6250] eta: 0:13:39 lr: 0.000124 grad: 0.0626 (0.0705) loss: 0.8487 (0.8496) time: 0.1626 data: 0.0803 max mem: 9390 +Train: [11] [1600/6250] eta: 0:13:22 lr: 0.000124 grad: 0.0672 (0.0702) loss: 0.8528 (0.8496) time: 0.1975 data: 0.1082 max mem: 9390 +Train: [11] [1700/6250] eta: 0:13:02 lr: 0.000124 grad: 0.0650 (0.0700) loss: 0.8491 (0.8495) time: 0.1695 data: 0.0882 max mem: 9390 +Train: [11] [1800/6250] eta: 0:12:45 lr: 0.000124 grad: 0.0636 (0.0697) loss: 0.8480 (0.8495) time: 0.1719 data: 0.0926 max mem: 9390 +Train: [11] [1900/6250] eta: 0:12:31 lr: 0.000124 grad: 0.0652 (0.0695) loss: 0.8484 (0.8494) time: 0.1722 data: 0.0877 max mem: 9390 +Train: [11] [2000/6250] eta: 0:12:10 lr: 0.000124 grad: 0.0642 (0.0692) loss: 0.8502 (0.8494) time: 0.1471 data: 0.0632 max mem: 9390 +pretraining fmri mae +start: 2026-04-01 16:16:58 +cwd: /data/connor/fmri-fm +sha: 7f4cedc35609f6857314e0d1ea6657523f17ddeb, status: has uncommitted changes, branch: dev/clane9 +config: +name: input_space_v3/flat_lr1e-3_5/pretrain +notes: input_space ablation v3 flat_lr1e-3_5; use tube masking and on-disk data (input_space=flat + base_lr=1e-3 seed=5405) +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain +input_space: flat +patch_size: 16 +num_frames: 16 +t_patch_size: 4 +mask_ratio: 0.9 +pred_mask_ratio: null +masking: tube +masking_kwargs: {} +mask_patch_size: null +model: mae_vit_base +model_kwargs: + decoding: attn + pos_embed: sep + target_norm: null + pca_norm_nc: 2 + t_pred_stride: 2 + no_decode_pos: true + mask_drop_scale: false + pred_edge_pad: 0 + gauss_sigma: null + class_token: true + reg_tokens: 0 + no_embed_class: true + head_init_scale: 0.0 + decoder_depth: 4 + drop_path_rate: 0.0 +datasets: + hcp-train: + type: wds + url: /data/fmri-datasets/pretrain/hcpya-all.${input_space}.wds/hcpya-all-${input_space}-{00000..01799}.tar + clipping: random + clipping_kwargs: + oversample: 4.0 + shuffle: true + buffer_size: 2000 + samples_per_epoch: 200000 + hcp-train-subset: + type: arrow + root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/validation + split_range: + - 0 + - 2000 + shuffle: false + hcp-val: + type: arrow + root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/test + split_range: + - 0 + - 2000 + shuffle: false +train_dataset: hcp-train +eval_datasets: +- hcp-train-subset +- hcp-val +val_dataset: null +clip_vmax: 3.0 +normalize: frame +tr_scale: null +crop_scale: null +crop_aspect: null +gray_jitter: null +num_workers: 16 +epochs: 100 +batch_size: 32 +accum_iter: 1 +base_lr: 0.001 +min_lr: 0.0 +warmup_epochs: 5 +weight_decay: 0.05 +betas: +- 0.9 +- 0.95 +clip_grad: 1.0 +amp: true +amp_dtype: float16 +ckpt: null +resume: true +auto_resume: true +start_epoch: 0 +max_checkpoints: 0 +checkpoint_period: null +plot_period: 5 +device: cuda +presend_cuda: false +seed: 5405 +debug: false +wandb: true +wandb_entity: null +wandb_project: fMRI-foundation-model +rank: 0 +world_size: 1 +gpu: 0 +distributed: true +dist_backend: nccl +in_chans: 1 +img_size: +- 224 +- 560 + +train transform: +Compose( + ToTensor() + TemporalCenterCrop(num_frames=16) + Normalize(mode='frame') + Clip(vmax=3.0) + FlatUnmask((224, 560)) +) +val transform: +Compose( + ToTensor() + TemporalCenterCrop(num_frames=16) + Normalize(mode='frame') + Clip(vmax=3.0) + FlatUnmask((224, 560)) +) +mask generator: +TubeMasking( + mask_ratio=0.9 + (patchify): Patchify2D((224, 560), (16, 16), in_chans=1) +) +loading dataset: hcp-train + +type: wds +url: /data/fmri-datasets/pretrain/hcpya-all.${input_space}.wds/hcpya-all-${input_space}-{00000..01799}.tar +clipping: random +clipping_kwargs: + oversample: 4.0 +shuffle: true +buffer_size: 2000 +samples_per_epoch: 200000 + +loading dataset: hcp-train-subset + +type: arrow +root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/validation +split_range: +- 0 +- 2000 +shuffle: false + +split indices: [899, 472, 767, 116, 1265, 1852, 300, 1335, 361, 1560] +loading dataset: hcp-val + +type: arrow +root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/test +split_range: +- 0 +- 2000 +shuffle: false + +split indices: [1075, 1189, 738, 1350, 965, 1964, 1367, 1183, 1619, 1407] +model: +MaskedAutoencoderViT( + decoding=attn, t_pred_stride=2, pred_edge_pad=0, no_decode_pos=True + (encoder): MaskedEncoder( + class_token=True, reg_tokens=0, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) + (pred_patchify): StridedPatchify3D((16, 224, 560), (2, 16, 16), in_chans=1, t_stride=2) + (decoder): MaskedDecoder( + cross_decode=False, class_token=True, no_embed_class=True + (pos_embed): SeparablePosEmbed(512, (4, 14, 35)) + (proj): Linear(in_features=768, out_features=512, bias=True) + (blocks): ModuleList( + (0-3): 4 x Block( + (norm1): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=16 + (q): Linear(in_features=512, out_features=512, bias=True) + (k): Linear(in_features=512, out_features=512, bias=True) + (v): Linear(in_features=512, out_features=512, bias=True) + (proj): Linear(in_features=512, out_features=512, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=512, out_features=2048, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=2048, out_features=512, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (head): Linear(in_features=512, out_features=512, bias=True) + ) +) +num params: 99.7M +total batch size: 32 = 32 bs per gpu x 1 accum x 1 gpus +lr: 1.25e-04 = 1.00e-03 x 32 / 256 +full schedule: epochs = 100 (steps = 625000) +warmup: epochs = 5 (steps = 31250) +loaded model state from checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +loaded optimizer state, resuming training from 11 +start training for 100 epochs +Train: [11] [ 0/6250] eta: 12:42:38 lr: 0.000124 grad: 0.0692 (0.0692) loss: 0.8563 (0.8563) time: 7.3214 data: 6.4487 max mem: 9353 +Train: [11] [ 100/6250] eta: 0:19:01 lr: 0.000124 grad: 0.0666 (0.0690) loss: 0.8569 (0.8573) time: 0.1275 data: 0.0448 max mem: 9390 +Train: [11] [ 200/6250] eta: 0:15:45 lr: 0.000124 grad: 0.0663 (0.0684) loss: 0.8535 (0.8568) time: 0.1462 data: 0.0676 max mem: 9390 +Train: [11] [ 300/6250] eta: 0:14:15 lr: 0.000124 grad: 0.0679 (0.0693) loss: 0.8561 (0.8564) time: 0.1259 data: 0.0469 max mem: 9390 +Train: [11] [ 400/6250] eta: 0:13:30 lr: 0.000124 grad: 0.0720 (0.0704) loss: 0.8545 (0.8555) time: 0.1263 data: 0.0505 max mem: 9390 +Train: [11] [ 500/6250] eta: 0:13:01 lr: 0.000124 grad: 0.0596 (0.0697) loss: 0.8525 (0.8553) time: 0.1360 data: 0.0602 max mem: 9390 +Train: [11] [ 600/6250] eta: 0:12:31 lr: 0.000124 grad: 0.0635 (0.0688) loss: 0.8540 (0.8551) time: 0.1265 data: 0.0481 max mem: 9390 +Train: [11] [ 700/6250] eta: 0:12:11 lr: 0.000124 grad: 0.0663 (0.0682) loss: 0.8531 (0.8551) time: 0.1185 data: 0.0356 max mem: 9390 +Train: [11] [ 800/6250] eta: 0:11:57 lr: 0.000124 grad: 0.0613 (0.0677) loss: 0.8529 (0.8548) time: 0.1478 data: 0.0660 max mem: 9390 +Train: [11] [ 900/6250] eta: 0:11:35 lr: 0.000124 grad: 0.0619 (0.0676) loss: 0.8520 (0.8546) time: 0.1244 data: 0.0462 max mem: 9390 +Train: [11] [1000/6250] eta: 0:11:17 lr: 0.000124 grad: 0.0616 (0.0672) loss: 0.8522 (0.8545) time: 0.1181 data: 0.0318 max mem: 9390 +Train: [11] [1100/6250] eta: 0:10:59 lr: 0.000124 grad: 0.0672 (0.0670) loss: 0.8513 (0.8542) time: 0.1261 data: 0.0469 max mem: 9390 +Train: [11] [1200/6250] eta: 0:10:41 lr: 0.000124 grad: 0.0629 (0.0667) loss: 0.8472 (0.8540) time: 0.0940 data: 0.0182 max mem: 9390 +Train: [11] [1300/6250] eta: 0:10:24 lr: 0.000124 grad: 0.0634 (0.0666) loss: 0.8511 (0.8537) time: 0.1196 data: 0.0415 max mem: 9390 +Train: [11] [1400/6250] eta: 0:10:08 lr: 0.000124 grad: 0.0615 (0.0667) loss: 0.8545 (0.8536) time: 0.1170 data: 0.0424 max mem: 9390 +Train: [11] [1500/6250] eta: 0:09:56 lr: 0.000124 grad: 0.0634 (0.0666) loss: 0.8571 (0.8534) time: 0.1433 data: 0.0623 max mem: 9390 +Train: [11] [1600/6250] eta: 0:09:39 lr: 0.000124 grad: 0.0702 (0.0667) loss: 0.8456 (0.8531) time: 0.1114 data: 0.0357 max mem: 9390 +Train: [11] [1700/6250] eta: 0:09:23 lr: 0.000124 grad: 0.0659 (0.0673) loss: 0.8470 (0.8529) time: 0.1134 data: 0.0367 max mem: 9390 +Train: [11] [1800/6250] eta: 0:09:09 lr: 0.000124 grad: 0.0656 (0.0672) loss: 0.8507 (0.8528) time: 0.1286 data: 0.0516 max mem: 9390 +Train: [11] [1900/6250] eta: 0:08:54 lr: 0.000124 grad: 0.0652 (0.0671) loss: 0.8519 (0.8526) time: 0.1242 data: 0.0455 max mem: 9390 +Train: [11] [2000/6250] eta: 0:08:41 lr: 0.000124 grad: 0.0658 (0.0671) loss: 0.8431 (0.8524) time: 0.1273 data: 0.0482 max mem: 9390 +Train: [11] [2100/6250] eta: 0:08:27 lr: 0.000124 grad: 0.0638 (0.0672) loss: 0.8511 (0.8522) time: 0.1026 data: 0.0259 max mem: 9390 +Train: [11] [2200/6250] eta: 0:08:14 lr: 0.000124 grad: 0.0639 (0.0672) loss: 0.8488 (0.8521) time: 0.1028 data: 0.0261 max mem: 9390 +Train: [11] [2300/6250] eta: 0:08:02 lr: 0.000124 grad: 0.0647 (0.0671) loss: 0.8490 (0.8520) time: 0.1330 data: 0.0564 max mem: 9390 +Train: [11] [2400/6250] eta: 0:07:49 lr: 0.000124 grad: 0.0632 (0.0672) loss: 0.8511 (0.8519) time: 0.1223 data: 0.0445 max mem: 9390 +Train: [11] [2500/6250] eta: 0:07:35 lr: 0.000124 grad: 0.0663 (0.0672) loss: 0.8509 (0.8518) time: 0.1192 data: 0.0414 max mem: 9390 +Train: [11] [2600/6250] eta: 0:07:23 lr: 0.000124 grad: 0.0606 (0.0671) loss: 0.8550 (0.8517) time: 0.1237 data: 0.0476 max mem: 9390 +Train: [11] [2700/6250] eta: 0:07:10 lr: 0.000124 grad: 0.0651 (0.0670) loss: 0.8514 (0.8517) time: 0.1049 data: 0.0233 max mem: 9390 +Train: [11] [2800/6250] eta: 0:06:58 lr: 0.000124 grad: 0.0631 (0.0671) loss: 0.8494 (0.8517) time: 0.1238 data: 0.0492 max mem: 9390 +Train: [11] [2900/6250] eta: 0:06:45 lr: 0.000124 grad: 0.0701 (0.0671) loss: 0.8493 (0.8516) time: 0.1260 data: 0.0509 max mem: 9390 +Train: [11] [3000/6250] eta: 0:06:32 lr: 0.000124 grad: 0.0613 (0.0670) loss: 0.8470 (0.8516) time: 0.1245 data: 0.0505 max mem: 9390 +pretraining fmri mae +start: 2026-04-02 10:17:10 +cwd: /data/connor/fmri-fm +sha: 7f4cedc35609f6857314e0d1ea6657523f17ddeb, status: has uncommitted changes, branch: dev/clane9 +config: +name: input_space_v3/flat_lr1e-3_5/pretrain +notes: input_space ablation v3 flat_lr1e-3_5; use tube masking and on-disk data (input_space=flat + base_lr=1e-3 seed=5405) +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain +input_space: flat +patch_size: 16 +num_frames: 16 +t_patch_size: 4 +mask_ratio: 0.9 +pred_mask_ratio: null +masking: tube +masking_kwargs: {} +mask_patch_size: null +model: mae_vit_base +model_kwargs: + decoding: attn + pos_embed: sep + target_norm: null + pca_norm_nc: 2 + t_pred_stride: 2 + no_decode_pos: true + mask_drop_scale: false + pred_edge_pad: 0 + gauss_sigma: null + class_token: true + reg_tokens: 0 + no_embed_class: true + head_init_scale: 0.0 + decoder_depth: 4 + drop_path_rate: 0.0 +datasets: + hcp-train: + type: wds + url: /data/fmri-datasets/pretrain/hcpya-all.${input_space}.wds/hcpya-all-${input_space}-{00000..01799}.tar + clipping: random + clipping_kwargs: + oversample: 4.0 + shuffle: true + buffer_size: 2000 + samples_per_epoch: 200000 + hcp-train-subset: + type: arrow + root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/validation + split_range: + - 0 + - 2000 + shuffle: false + hcp-val: + type: arrow + root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/test + split_range: + - 0 + - 2000 + shuffle: false +train_dataset: hcp-train +eval_datasets: +- hcp-train-subset +- hcp-val +val_dataset: null +clip_vmax: 3.0 +normalize: frame +tr_scale: null +crop_scale: null +crop_aspect: null +gray_jitter: null +num_workers: 16 +epochs: 100 +batch_size: 32 +accum_iter: 1 +base_lr: 0.001 +min_lr: 0.0 +warmup_epochs: 5 +weight_decay: 0.05 +betas: +- 0.9 +- 0.95 +clip_grad: 1.0 +amp: true +amp_dtype: float16 +ckpt: null +resume: true +auto_resume: true +start_epoch: 0 +max_checkpoints: 0 +checkpoint_period: null +plot_period: 5 +device: cuda +presend_cuda: false +seed: 5405 +debug: false +wandb: true +wandb_entity: null +wandb_project: fMRI-foundation-model +rank: 0 +world_size: 1 +gpu: 0 +distributed: true +dist_backend: nccl +in_chans: 1 +img_size: +- 224 +- 560 + +train transform: +Compose( + ToTensor() + TemporalCenterCrop(num_frames=16) + Normalize(mode='frame') + Clip(vmax=3.0) + FlatUnmask((224, 560)) +) +val transform: +Compose( + ToTensor() + TemporalCenterCrop(num_frames=16) + Normalize(mode='frame') + Clip(vmax=3.0) + FlatUnmask((224, 560)) +) +mask generator: +TubeMasking( + mask_ratio=0.9 + (patchify): Patchify2D((224, 560), (16, 16), in_chans=1) +) +loading dataset: hcp-train + +type: wds +url: /data/fmri-datasets/pretrain/hcpya-all.${input_space}.wds/hcpya-all-${input_space}-{00000..01799}.tar +clipping: random +clipping_kwargs: + oversample: 4.0 +shuffle: true +buffer_size: 2000 +samples_per_epoch: 200000 + +loading dataset: hcp-train-subset + +type: arrow +root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/validation +split_range: +- 0 +- 2000 +shuffle: false + +split indices: [899, 472, 767, 116, 1265, 1852, 300, 1335, 361, 1560] +loading dataset: hcp-val + +type: arrow +root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/test +split_range: +- 0 +- 2000 +shuffle: false + +split indices: [1075, 1189, 738, 1350, 965, 1964, 1367, 1183, 1619, 1407] +model: +MaskedAutoencoderViT( + decoding=attn, t_pred_stride=2, pred_edge_pad=0, no_decode_pos=True + (encoder): MaskedEncoder( + class_token=True, reg_tokens=0, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) + (pred_patchify): StridedPatchify3D((16, 224, 560), (2, 16, 16), in_chans=1, t_stride=2) + (decoder): MaskedDecoder( + cross_decode=False, class_token=True, no_embed_class=True + (pos_embed): SeparablePosEmbed(512, (4, 14, 35)) + (proj): Linear(in_features=768, out_features=512, bias=True) + (blocks): ModuleList( + (0-3): 4 x Block( + (norm1): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=16 + (q): Linear(in_features=512, out_features=512, bias=True) + (k): Linear(in_features=512, out_features=512, bias=True) + (v): Linear(in_features=512, out_features=512, bias=True) + (proj): Linear(in_features=512, out_features=512, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=512, out_features=2048, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=2048, out_features=512, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (head): Linear(in_features=512, out_features=512, bias=True) + ) +) +num params: 99.7M +total batch size: 32 = 32 bs per gpu x 1 accum x 1 gpus +lr: 1.25e-04 = 1.00e-03 x 32 / 256 +full schedule: epochs = 100 (steps = 625000) +warmup: epochs = 5 (steps = 31250) +loaded model state from checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +loaded optimizer state, resuming training from 11 +start training for 100 epochs +Train: [11] [ 0/6250] eta: 9:34:44 lr: 0.000124 grad: 0.0754 (0.0754) loss: 0.8683 (0.8683) time: 5.5176 data: 4.1580 max mem: 9353 +Train: [11] [ 100/6250] eta: 0:21:47 lr: 0.000124 grad: 0.0632 (0.0708) loss: 0.8537 (0.8548) time: 0.1733 data: 0.0700 max mem: 9390 +Train: [11] [ 200/6250] eta: 0:19:17 lr: 0.000124 grad: 0.0664 (0.0692) loss: 0.8512 (0.8529) time: 0.1767 data: 0.0793 max mem: 9390 +Train: [11] [ 300/6250] eta: 0:18:11 lr: 0.000124 grad: 0.0652 (0.0678) loss: 0.8534 (0.8541) time: 0.1640 data: 0.0571 max mem: 9390 +Train: [11] [ 400/6250] eta: 0:17:27 lr: 0.000124 grad: 0.0672 (0.0673) loss: 0.8483 (0.8532) time: 0.1543 data: 0.0568 max mem: 9390 +Train: [11] [ 500/6250] eta: 0:16:56 lr: 0.000124 grad: 0.0652 (0.0674) loss: 0.8528 (0.8527) time: 0.1699 data: 0.0679 max mem: 9390 +Train: [11] [ 600/6250] eta: 0:16:30 lr: 0.000124 grad: 0.0672 (0.0674) loss: 0.8482 (0.8522) time: 0.1859 data: 0.0946 max mem: 9390 +Train: [11] [ 700/6250] eta: 0:16:03 lr: 0.000124 grad: 0.0642 (0.0672) loss: 0.8504 (0.8519) time: 0.1692 data: 0.0660 max mem: 9390 +Train: [11] [ 800/6250] eta: 0:15:38 lr: 0.000124 grad: 0.0646 (0.0672) loss: 0.8528 (0.8519) time: 0.1698 data: 0.0653 max mem: 9390 +Train: [11] [ 900/6250] eta: 0:15:16 lr: 0.000124 grad: 0.0652 (0.0673) loss: 0.8543 (0.8517) time: 0.1675 data: 0.0721 max mem: 9390 +Train: [11] [1000/6250] eta: 0:14:57 lr: 0.000124 grad: 0.0611 (0.0674) loss: 0.8473 (0.8514) time: 0.1722 data: 0.0602 max mem: 9390 +Train: [11] [1100/6250] eta: 0:14:38 lr: 0.000124 grad: 0.0648 (0.0674) loss: 0.8527 (0.8512) time: 0.1674 data: 0.0708 max mem: 9390 +Train: [11] [1200/6250] eta: 0:14:18 lr: 0.000124 grad: 0.0640 (0.0676) loss: 0.8459 (0.8510) time: 0.2016 data: 0.1138 max mem: 9390 +Train: [11] [1300/6250] eta: 0:13:56 lr: 0.000124 grad: 0.0660 (0.0676) loss: 0.8498 (0.8509) time: 0.1639 data: 0.0720 max mem: 9390 +Train: [11] [1400/6250] eta: 0:13:36 lr: 0.000124 grad: 0.0615 (0.0677) loss: 0.8471 (0.8506) time: 0.1507 data: 0.0581 max mem: 9390 +Train: [11] [1500/6250] eta: 0:13:17 lr: 0.000124 grad: 0.0679 (0.0677) loss: 0.8443 (0.8505) time: 0.1439 data: 0.0488 max mem: 9390 +Train: [11] [1600/6250] eta: 0:12:59 lr: 0.000124 grad: 0.0636 (0.0676) loss: 0.8506 (0.8504) time: 0.1660 data: 0.0735 max mem: 9390 +Train: [11] [1700/6250] eta: 0:12:41 lr: 0.000124 grad: 0.0684 (0.0675) loss: 0.8463 (0.8502) time: 0.1511 data: 0.0632 max mem: 9390 +Train: [11] [1800/6250] eta: 0:12:21 lr: 0.000124 grad: 0.0607 (0.0676) loss: 0.8475 (0.8500) time: 0.1401 data: 0.0540 max mem: 9390 +Train: [11] [1900/6250] eta: 0:12:01 lr: 0.000124 grad: 0.0667 (0.0677) loss: 0.8494 (0.8498) time: 0.1553 data: 0.0604 max mem: 9390 +Train: [11] [2000/6250] eta: 0:11:43 lr: 0.000124 grad: 0.0665 (0.0678) loss: 0.8467 (0.8497) time: 0.1527 data: 0.0648 max mem: 9390 +Train: [11] [2100/6250] eta: 0:11:25 lr: 0.000124 grad: 0.0674 (0.0680) loss: 0.8457 (0.8496) time: 0.1559 data: 0.0673 max mem: 9390 +Train: [11] [2200/6250] eta: 0:11:07 lr: 0.000124 grad: 0.0644 (0.0679) loss: 0.8458 (0.8495) time: 0.1485 data: 0.0544 max mem: 9390 +Train: [11] [2300/6250] eta: 0:10:50 lr: 0.000124 grad: 0.0668 (0.0682) loss: 0.8463 (0.8494) time: 0.1489 data: 0.0607 max mem: 9390 +Train: [11] [2400/6250] eta: 0:10:33 lr: 0.000124 grad: 0.0696 (0.0681) loss: 0.8477 (0.8494) time: 0.1757 data: 0.0893 max mem: 9390 +Train: [11] [2500/6250] eta: 0:10:13 lr: 0.000124 grad: 0.0631 (0.0680) loss: 0.8472 (0.8493) time: 0.1430 data: 0.0365 max mem: 9390 +Train: [11] [2600/6250] eta: 0:09:56 lr: 0.000124 grad: 0.0640 (0.0681) loss: 0.8496 (0.8492) time: 0.1405 data: 0.0505 max mem: 9390 +Train: [11] [2700/6250] eta: 0:09:39 lr: 0.000124 grad: 0.0681 (0.0680) loss: 0.8477 (0.8492) time: 0.1550 data: 0.0568 max mem: 9390 +Train: [11] [2800/6250] eta: 0:09:22 lr: 0.000124 grad: 0.0713 (0.0682) loss: 0.8474 (0.8492) time: 0.1401 data: 0.0549 max mem: 9390 +Train: [11] [2900/6250] eta: 0:09:06 lr: 0.000124 grad: 0.0662 (0.0681) loss: 0.8461 (0.8491) time: 0.1589 data: 0.0670 max mem: 9390 +Train: [11] [3000/6250] eta: 0:08:49 lr: 0.000124 grad: 0.0652 (0.0681) loss: 0.8438 (0.8491) time: 0.1359 data: 0.0422 max mem: 9390 +Train: [11] [3100/6250] eta: 0:08:33 lr: 0.000124 grad: 0.0661 (0.0680) loss: 0.8508 (0.8491) time: 0.1500 data: 0.0616 max mem: 9390 +Train: [11] [3200/6250] eta: 0:08:16 lr: 0.000124 grad: 0.0633 (0.0680) loss: 0.8517 (0.8491) time: 0.1631 data: 0.0743 max mem: 9390 +Train: [11] [3300/6250] eta: 0:08:00 lr: 0.000124 grad: 0.0586 (0.0680) loss: 0.8484 (0.8491) time: 0.1490 data: 0.0525 max mem: 9390 +Train: [11] [3400/6250] eta: 0:07:43 lr: 0.000124 grad: 0.0676 (0.0681) loss: 0.8457 (0.8491) time: 0.1540 data: 0.0660 max mem: 9390 +Train: [11] [3500/6250] eta: 0:07:26 lr: 0.000124 grad: 0.0662 (0.0680) loss: 0.8496 (0.8491) time: 0.1616 data: 0.0637 max mem: 9390 +Train: [11] [3600/6250] eta: 0:07:10 lr: 0.000124 grad: 0.0633 (0.0679) loss: 0.8514 (0.8492) time: 0.1567 data: 0.0673 max mem: 9390 +Train: [11] [3700/6250] eta: 0:06:54 lr: 0.000124 grad: 0.0620 (0.0679) loss: 0.8533 (0.8491) time: 0.1677 data: 0.0810 max mem: 9390 +Train: [11] [3800/6250] eta: 0:06:37 lr: 0.000124 grad: 0.0665 (0.0679) loss: 0.8502 (0.8492) time: 0.1629 data: 0.0736 max mem: 9390 +Train: [11] [3900/6250] eta: 0:06:21 lr: 0.000124 grad: 0.0661 (0.0680) loss: 0.8442 (0.8492) time: 0.1426 data: 0.0535 max mem: 9390 +Train: [11] [4000/6250] eta: 0:06:04 lr: 0.000123 grad: 0.0623 (0.0679) loss: 0.8446 (0.8491) time: 0.1714 data: 0.0896 max mem: 9390 +Train: [11] [4100/6250] eta: 0:05:48 lr: 0.000123 grad: 0.0628 (0.0679) loss: 0.8486 (0.8491) time: 0.1624 data: 0.0773 max mem: 9390 +Train: [11] [4200/6250] eta: 0:05:32 lr: 0.000123 grad: 0.0675 (0.0679) loss: 0.8474 (0.8491) time: 0.1806 data: 0.0933 max mem: 9390 +Train: [11] [4300/6250] eta: 0:05:15 lr: 0.000123 grad: 0.0670 (0.0679) loss: 0.8479 (0.8491) time: 0.1682 data: 0.0649 max mem: 9390 +Train: [11] [4400/6250] eta: 0:04:59 lr: 0.000123 grad: 0.0663 (0.0679) loss: 0.8519 (0.8492) time: 0.1746 data: 0.0915 max mem: 9390 +Train: [11] [4500/6250] eta: 0:04:43 lr: 0.000123 grad: 0.0631 (0.0679) loss: 0.8508 (0.8492) time: 0.1890 data: 0.0985 max mem: 9390 +Train: [11] [4600/6250] eta: 0:04:27 lr: 0.000123 grad: 0.0680 (0.0679) loss: 0.8424 (0.8492) time: 0.1689 data: 0.0850 max mem: 9390 +Train: [11] [4700/6250] eta: 0:04:11 lr: 0.000123 grad: 0.0661 (0.0679) loss: 0.8498 (0.8492) time: 0.1731 data: 0.0894 max mem: 9390 +Train: [11] [4800/6250] eta: 0:03:54 lr: 0.000123 grad: 0.0618 (0.0679) loss: 0.8463 (0.8492) time: 0.1667 data: 0.0804 max mem: 9390 +Train: [11] [4900/6250] eta: 0:03:38 lr: 0.000123 grad: 0.0675 (0.0679) loss: 0.8504 (0.8491) time: 0.1525 data: 0.0621 max mem: 9390 +Train: [11] [5000/6250] eta: 0:03:22 lr: 0.000123 grad: 0.0698 (0.0678) loss: 0.8470 (0.8491) time: 0.1803 data: 0.1006 max mem: 9390 +Train: [11] [5100/6250] eta: 0:03:06 lr: 0.000123 grad: 0.0622 (0.0678) loss: 0.8524 (0.8491) time: 0.1413 data: 0.0505 max mem: 9390 +Train: [11] [5200/6250] eta: 0:02:50 lr: 0.000123 grad: 0.0625 (0.0677) loss: 0.8501 (0.8491) time: 0.1784 data: 0.0937 max mem: 9390 +Train: [11] [5300/6250] eta: 0:02:33 lr: 0.000123 grad: 0.0656 (0.0678) loss: 0.8495 (0.8491) time: 0.1725 data: 0.0898 max mem: 9390 +Train: [11] [5400/6250] eta: 0:02:17 lr: 0.000123 grad: 0.0629 (0.0678) loss: 0.8488 (0.8490) time: 0.1528 data: 0.0590 max mem: 9390 +Train: [11] [5500/6250] eta: 0:02:01 lr: 0.000123 grad: 0.0644 (0.0677) loss: 0.8469 (0.8490) time: 0.1564 data: 0.0706 max mem: 9390 +Train: [11] [5600/6250] eta: 0:01:45 lr: 0.000123 grad: 0.0659 (0.0677) loss: 0.8505 (0.8490) time: 0.1736 data: 0.0805 max mem: 9390 +Train: [11] [5700/6250] eta: 0:01:29 lr: 0.000123 grad: 0.0664 (0.0677) loss: 0.8493 (0.8490) time: 0.1372 data: 0.0507 max mem: 9390 +Train: [11] [5800/6250] eta: 0:01:12 lr: 0.000123 grad: 0.0607 (0.0676) loss: 0.8478 (0.8490) time: 0.1600 data: 0.0772 max mem: 9390 +Train: [11] [5900/6250] eta: 0:00:56 lr: 0.000123 grad: 0.0655 (0.0676) loss: 0.8543 (0.8490) time: 0.1647 data: 0.0791 max mem: 9390 +Train: [11] [6000/6250] eta: 0:00:40 lr: 0.000123 grad: 0.0632 (0.0676) loss: 0.8455 (0.8490) time: 0.1680 data: 0.0824 max mem: 9390 +Train: [11] [6100/6250] eta: 0:00:24 lr: 0.000123 grad: 0.0630 (0.0676) loss: 0.8512 (0.8489) time: 0.1513 data: 0.0684 max mem: 9390 +Train: [11] [6200/6250] eta: 0:00:08 lr: 0.000123 grad: 0.0647 (0.0675) loss: 0.8421 (0.8489) time: 0.1728 data: 0.0859 max mem: 9390 +Train: [11] [6249/6250] eta: 0:00:00 lr: 0.000123 grad: 0.0632 (0.0675) loss: 0.8447 (0.8489) time: 0.1891 data: 0.1041 max mem: 9390 +Train: [11] Total time: 0:16:55 (0.1624 s / it) +Averaged stats: lr: 0.000123 grad: 0.0632 (0.0675) loss: 0.8447 (0.8489) +Eval (hcp-train-subset): [11] [ 0/62] eta: 0:04:15 loss: 0.8625 (0.8625) time: 4.1239 data: 4.0537 max mem: 9390 +Eval (hcp-train-subset): [11] [61/62] eta: 0:00:00 loss: 0.8509 (0.8529) time: 0.1129 data: 0.0819 max mem: 9390 +Eval (hcp-train-subset): [11] Total time: 0:00:12 (0.2039 s / it) +Averaged stats (hcp-train-subset): loss: 0.8509 (0.8529) +Eval (hcp-val): [11] [ 0/62] eta: 0:03:20 loss: 0.8438 (0.8438) time: 3.2356 data: 3.1650 max mem: 9390 +Eval (hcp-val): [11] [61/62] eta: 0:00:00 loss: 0.8464 (0.8472) time: 0.1196 data: 0.0937 max mem: 9390 +Eval (hcp-val): [11] Total time: 0:00:13 (0.2138 s / it) +Averaged stats (hcp-val): loss: 0.8464 (0.8472) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +Train: [12] [ 0/6250] eta: 5:30:54 lr: 0.000123 grad: 0.0624 (0.0624) loss: 0.8794 (0.8794) time: 3.1767 data: 2.9843 max mem: 9390 +Train: [12] [ 100/6250] eta: 0:20:22 lr: 0.000123 grad: 0.0687 (0.0746) loss: 0.8501 (0.8528) time: 0.1306 data: 0.0468 max mem: 9390 +Train: [12] [ 200/6250] eta: 0:18:29 lr: 0.000123 grad: 0.0643 (0.0734) loss: 0.8463 (0.8496) time: 0.1635 data: 0.0657 max mem: 9390 +Train: [12] [ 300/6250] eta: 0:17:33 lr: 0.000123 grad: 0.0710 (0.0741) loss: 0.8432 (0.8482) time: 0.1693 data: 0.0741 max mem: 9390 +Train: [12] [ 400/6250] eta: 0:16:55 lr: 0.000123 grad: 0.0662 (0.0728) loss: 0.8403 (0.8478) time: 0.1880 data: 0.0913 max mem: 9390 +Train: [12] [ 500/6250] eta: 0:16:22 lr: 0.000123 grad: 0.0660 (0.0720) loss: 0.8430 (0.8479) time: 0.1778 data: 0.0866 max mem: 9390 +Train: [12] [ 600/6250] eta: 0:15:53 lr: 0.000123 grad: 0.0635 (0.0717) loss: 0.8481 (0.8480) time: 0.1548 data: 0.0475 max mem: 9390 +Train: [12] [ 700/6250] eta: 0:15:34 lr: 0.000123 grad: 0.0627 (0.0710) loss: 0.8509 (0.8481) time: 0.1669 data: 0.0748 max mem: 9390 +Train: [12] [ 800/6250] eta: 0:15:22 lr: 0.000123 grad: 0.0614 (0.0710) loss: 0.8480 (0.8483) time: 0.1716 data: 0.0792 max mem: 9390 +Train: [12] [ 900/6250] eta: 0:15:04 lr: 0.000123 grad: 0.0610 (0.0704) loss: 0.8495 (0.8487) time: 0.1552 data: 0.0666 max mem: 9390 +Train: [12] [1000/6250] eta: 0:14:47 lr: 0.000123 grad: 0.0614 (0.0697) loss: 0.8534 (0.8490) time: 0.1821 data: 0.0923 max mem: 9390 +Train: [12] [1100/6250] eta: 0:14:24 lr: 0.000123 grad: 0.0611 (0.0697) loss: 0.8512 (0.8492) time: 0.1501 data: 0.0644 max mem: 9390 +Train: [12] [1200/6250] eta: 0:14:03 lr: 0.000123 grad: 0.0650 (0.0692) loss: 0.8461 (0.8493) time: 0.1678 data: 0.0775 max mem: 9390 +Train: [12] [1300/6250] eta: 0:13:45 lr: 0.000123 grad: 0.0610 (0.0691) loss: 0.8492 (0.8494) time: 0.1582 data: 0.0723 max mem: 9390 +Train: [12] [1400/6250] eta: 0:13:28 lr: 0.000123 grad: 0.0618 (0.0687) loss: 0.8498 (0.8493) time: 0.1784 data: 0.0842 max mem: 9390 +Train: [12] [1500/6250] eta: 0:13:09 lr: 0.000123 grad: 0.0627 (0.0685) loss: 0.8455 (0.8493) time: 0.1651 data: 0.0873 max mem: 9390 +Train: [12] [1600/6250] eta: 0:12:51 lr: 0.000123 grad: 0.0660 (0.0684) loss: 0.8426 (0.8491) time: 0.1649 data: 0.0810 max mem: 9390 +Train: [12] [1700/6250] eta: 0:12:33 lr: 0.000123 grad: 0.0617 (0.0685) loss: 0.8454 (0.8491) time: 0.1492 data: 0.0450 max mem: 9390 +Train: [12] [1800/6250] eta: 0:12:17 lr: 0.000123 grad: 0.0615 (0.0683) loss: 0.8453 (0.8490) time: 0.1809 data: 0.0951 max mem: 9390 +Train: [12] [1900/6250] eta: 0:11:59 lr: 0.000123 grad: 0.0629 (0.0682) loss: 0.8475 (0.8489) time: 0.1685 data: 0.0855 max mem: 9390 +Train: [12] [2000/6250] eta: 0:11:41 lr: 0.000123 grad: 0.0631 (0.0681) loss: 0.8501 (0.8489) time: 0.1253 data: 0.0317 max mem: 9390 +Train: [12] [2100/6250] eta: 0:11:24 lr: 0.000123 grad: 0.0715 (0.0683) loss: 0.8476 (0.8488) time: 0.1533 data: 0.0687 max mem: 9390 +Train: [12] [2200/6250] eta: 0:11:08 lr: 0.000123 grad: 0.0628 (0.0682) loss: 0.8474 (0.8487) time: 0.1765 data: 0.0945 max mem: 9390 +Train: [12] [2300/6250] eta: 0:10:52 lr: 0.000123 grad: 0.0659 (0.0683) loss: 0.8458 (0.8486) time: 0.1772 data: 0.0962 max mem: 9390 +Train: [12] [2400/6250] eta: 0:10:34 lr: 0.000123 grad: 0.0625 (0.0683) loss: 0.8462 (0.8486) time: 0.1545 data: 0.0691 max mem: 9390 +Train: [12] [2500/6250] eta: 0:10:17 lr: 0.000123 grad: 0.0701 (0.0683) loss: 0.8478 (0.8485) time: 0.1723 data: 0.0839 max mem: 9390 +Train: [12] [2600/6250] eta: 0:10:00 lr: 0.000123 grad: 0.0654 (0.0682) loss: 0.8469 (0.8484) time: 0.1678 data: 0.0826 max mem: 9390 +Train: [12] [2700/6250] eta: 0:09:42 lr: 0.000123 grad: 0.0645 (0.0684) loss: 0.8474 (0.8483) time: 0.1778 data: 0.0935 max mem: 9390 +Train: [12] [2800/6250] eta: 0:09:26 lr: 0.000123 grad: 0.0664 (0.0683) loss: 0.8488 (0.8482) time: 0.1782 data: 0.0910 max mem: 9390 +Train: [12] [2900/6250] eta: 0:09:08 lr: 0.000123 grad: 0.0626 (0.0682) loss: 0.8463 (0.8482) time: 0.1487 data: 0.0611 max mem: 9390 +Train: [12] [3000/6250] eta: 0:08:52 lr: 0.000123 grad: 0.0649 (0.0682) loss: 0.8468 (0.8482) time: 0.1563 data: 0.0613 max mem: 9390 +Train: [12] [3100/6250] eta: 0:08:35 lr: 0.000123 grad: 0.0641 (0.0682) loss: 0.8472 (0.8481) time: 0.1509 data: 0.0622 max mem: 9390 +Train: [12] [3200/6250] eta: 0:08:19 lr: 0.000123 grad: 0.0636 (0.0681) loss: 0.8389 (0.8480) time: 0.1665 data: 0.0736 max mem: 9390 +Train: [12] [3300/6250] eta: 0:08:02 lr: 0.000123 grad: 0.0624 (0.0681) loss: 0.8446 (0.8479) time: 0.1441 data: 0.0556 max mem: 9390 +Train: [12] [3400/6250] eta: 0:07:45 lr: 0.000123 grad: 0.0641 (0.0680) loss: 0.8407 (0.8478) time: 0.1506 data: 0.0616 max mem: 9390 +Train: [12] [3500/6250] eta: 0:07:28 lr: 0.000123 grad: 0.0616 (0.0680) loss: 0.8491 (0.8477) time: 0.1631 data: 0.0823 max mem: 9390 +Train: [12] [3600/6250] eta: 0:07:12 lr: 0.000123 grad: 0.0645 (0.0679) loss: 0.8461 (0.8477) time: 0.1540 data: 0.0700 max mem: 9390 +Train: [12] [3700/6250] eta: 0:06:55 lr: 0.000123 grad: 0.0656 (0.0679) loss: 0.8496 (0.8477) time: 0.1698 data: 0.0865 max mem: 9390 +Train: [12] [3800/6250] eta: 0:06:39 lr: 0.000123 grad: 0.0642 (0.0679) loss: 0.8452 (0.8476) time: 0.1716 data: 0.0839 max mem: 9390 +Train: [12] [3900/6250] eta: 0:06:23 lr: 0.000123 grad: 0.0630 (0.0679) loss: 0.8498 (0.8476) time: 0.1791 data: 0.0940 max mem: 9390 +Train: [12] [4000/6250] eta: 0:06:06 lr: 0.000123 grad: 0.0612 (0.0679) loss: 0.8502 (0.8476) time: 0.1701 data: 0.0872 max mem: 9390 +Train: [12] [4100/6250] eta: 0:05:50 lr: 0.000123 grad: 0.0685 (0.0678) loss: 0.8451 (0.8476) time: 0.1645 data: 0.0758 max mem: 9390 +Train: [12] [4200/6250] eta: 0:05:34 lr: 0.000123 grad: 0.0653 (0.0677) loss: 0.8439 (0.8476) time: 0.1769 data: 0.0982 max mem: 9390 +Train: [12] [4300/6250] eta: 0:05:17 lr: 0.000123 grad: 0.0646 (0.0676) loss: 0.8477 (0.8475) time: 0.1484 data: 0.0597 max mem: 9390 +Train: [12] [4400/6250] eta: 0:05:01 lr: 0.000123 grad: 0.0626 (0.0676) loss: 0.8421 (0.8475) time: 0.1574 data: 0.0737 max mem: 9390 +Train: [12] [4500/6250] eta: 0:04:45 lr: 0.000123 grad: 0.0696 (0.0675) loss: 0.8380 (0.8474) time: 0.1275 data: 0.0449 max mem: 9390 +Train: [12] [4600/6250] eta: 0:04:28 lr: 0.000123 grad: 0.0633 (0.0675) loss: 0.8473 (0.8474) time: 0.1668 data: 0.0764 max mem: 9390 +Train: [12] [4700/6250] eta: 0:04:12 lr: 0.000123 grad: 0.0632 (0.0674) loss: 0.8462 (0.8474) time: 0.1597 data: 0.0750 max mem: 9390 +Train: [12] [4800/6250] eta: 0:03:56 lr: 0.000123 grad: 0.0631 (0.0673) loss: 0.8460 (0.8474) time: 0.1667 data: 0.0747 max mem: 9390 +Train: [12] [4900/6250] eta: 0:03:39 lr: 0.000123 grad: 0.0641 (0.0672) loss: 0.8491 (0.8474) time: 0.1553 data: 0.0630 max mem: 9390 +Train: [12] [5000/6250] eta: 0:03:23 lr: 0.000123 grad: 0.0619 (0.0671) loss: 0.8441 (0.8474) time: 0.1571 data: 0.0763 max mem: 9390 +Train: [12] [5100/6250] eta: 0:03:07 lr: 0.000123 grad: 0.0620 (0.0670) loss: 0.8475 (0.8473) time: 0.1900 data: 0.0936 max mem: 9390 +Train: [12] [5200/6250] eta: 0:02:50 lr: 0.000123 grad: 0.0651 (0.0670) loss: 0.8512 (0.8474) time: 0.1486 data: 0.0693 max mem: 9390 +Train: [12] [5300/6250] eta: 0:02:34 lr: 0.000123 grad: 0.0606 (0.0670) loss: 0.8460 (0.8474) time: 0.1656 data: 0.0761 max mem: 9390 +Train: [12] [5400/6250] eta: 0:02:18 lr: 0.000123 grad: 0.0689 (0.0670) loss: 0.8413 (0.8474) time: 0.1476 data: 0.0447 max mem: 9390 +Train: [12] [5500/6250] eta: 0:02:01 lr: 0.000123 grad: 0.0643 (0.0669) loss: 0.8455 (0.8474) time: 0.1582 data: 0.0670 max mem: 9390 +Train: [12] [5600/6250] eta: 0:01:45 lr: 0.000123 grad: 0.0654 (0.0669) loss: 0.8453 (0.8474) time: 0.1460 data: 0.0489 max mem: 9390 +Train: [12] [5700/6250] eta: 0:01:29 lr: 0.000123 grad: 0.0644 (0.0669) loss: 0.8496 (0.8474) time: 0.1707 data: 0.0782 max mem: 9390 +Train: [12] [5800/6250] eta: 0:01:13 lr: 0.000123 grad: 0.0633 (0.0668) loss: 0.8465 (0.8475) time: 0.1849 data: 0.0824 max mem: 9390 +Train: [12] [5900/6250] eta: 0:00:56 lr: 0.000123 grad: 0.0574 (0.0667) loss: 0.8509 (0.8475) time: 0.1653 data: 0.0737 max mem: 9390 +Train: [12] [6000/6250] eta: 0:00:40 lr: 0.000123 grad: 0.0618 (0.0667) loss: 0.8434 (0.8475) time: 0.1507 data: 0.0469 max mem: 9390 +Train: [12] [6100/6250] eta: 0:00:24 lr: 0.000123 grad: 0.0606 (0.0666) loss: 0.8483 (0.8475) time: 0.1583 data: 0.0639 max mem: 9390 +Train: [12] [6200/6250] eta: 0:00:08 lr: 0.000123 grad: 0.0642 (0.0665) loss: 0.8512 (0.8475) time: 0.1725 data: 0.0906 max mem: 9390 +Train: [12] [6249/6250] eta: 0:00:00 lr: 0.000123 grad: 0.0605 (0.0665) loss: 0.8474 (0.8476) time: 0.1745 data: 0.0776 max mem: 9390 +Train: [12] Total time: 0:16:57 (0.1628 s / it) +Averaged stats: lr: 0.000123 grad: 0.0605 (0.0665) loss: 0.8474 (0.8476) +Eval (hcp-train-subset): [12] [ 0/62] eta: 0:05:44 loss: 0.8579 (0.8579) time: 5.5499 data: 5.5191 max mem: 9390 +Eval (hcp-train-subset): [12] [61/62] eta: 0:00:00 loss: 0.8517 (0.8512) time: 0.1129 data: 0.0871 max mem: 9390 +Eval (hcp-train-subset): [12] Total time: 0:00:14 (0.2288 s / it) +Averaged stats (hcp-train-subset): loss: 0.8517 (0.8512) +Eval (hcp-val): [12] [ 0/62] eta: 0:03:48 loss: 0.8422 (0.8422) time: 3.6921 data: 3.6285 max mem: 9390 +Eval (hcp-val): [12] [61/62] eta: 0:00:00 loss: 0.8448 (0.8458) time: 0.1163 data: 0.0905 max mem: 9390 +Eval (hcp-val): [12] Total time: 0:00:12 (0.2096 s / it) +Averaged stats (hcp-val): loss: 0.8448 (0.8458) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +Train: [13] [ 0/6250] eta: 8:32:50 lr: 0.000123 grad: 0.0682 (0.0682) loss: 0.8619 (0.8619) time: 4.9232 data: 4.6770 max mem: 9390 +Train: [13] [ 100/6250] eta: 0:21:43 lr: 0.000123 grad: 0.0601 (0.0710) loss: 0.8533 (0.8547) time: 0.1740 data: 0.0878 max mem: 9390 +Train: [13] [ 200/6250] eta: 0:18:40 lr: 0.000123 grad: 0.0653 (0.0698) loss: 0.8452 (0.8514) time: 0.1633 data: 0.0694 max mem: 9390 +Train: [13] [ 300/6250] eta: 0:17:45 lr: 0.000123 grad: 0.0621 (0.0691) loss: 0.8459 (0.8493) time: 0.1717 data: 0.0731 max mem: 9390 +Train: [13] [ 400/6250] eta: 0:17:24 lr: 0.000123 grad: 0.0722 (0.0691) loss: 0.8421 (0.8479) time: 0.2081 data: 0.0940 max mem: 9390 +Train: [13] [ 500/6250] eta: 0:16:57 lr: 0.000123 grad: 0.0681 (0.0689) loss: 0.8426 (0.8475) time: 0.1869 data: 0.0857 max mem: 9390 +Train: [13] [ 600/6250] eta: 0:16:32 lr: 0.000123 grad: 0.0624 (0.0689) loss: 0.8459 (0.8472) time: 0.1612 data: 0.0606 max mem: 9390 +Train: [13] [ 700/6250] eta: 0:16:09 lr: 0.000123 grad: 0.0633 (0.0682) loss: 0.8484 (0.8467) time: 0.1897 data: 0.0940 max mem: 9390 +Train: [13] [ 800/6250] eta: 0:15:51 lr: 0.000123 grad: 0.0632 (0.0677) loss: 0.8451 (0.8466) time: 0.2039 data: 0.1139 max mem: 9390 +Train: [13] [ 900/6250] eta: 0:15:30 lr: 0.000123 grad: 0.0598 (0.0673) loss: 0.8443 (0.8466) time: 0.1634 data: 0.0599 max mem: 9390 +Train: [13] [1000/6250] eta: 0:15:09 lr: 0.000123 grad: 0.0626 (0.0671) loss: 0.8466 (0.8465) time: 0.1590 data: 0.0603 max mem: 9390 +Train: [13] [1100/6250] eta: 0:14:49 lr: 0.000123 grad: 0.0620 (0.0671) loss: 0.8568 (0.8466) time: 0.1795 data: 0.0943 max mem: 9390 +Train: [13] [1200/6250] eta: 0:14:25 lr: 0.000123 grad: 0.0633 (0.0672) loss: 0.8524 (0.8465) time: 0.1515 data: 0.0550 max mem: 9390 +Train: [13] [1300/6250] eta: 0:14:02 lr: 0.000123 grad: 0.0589 (0.0670) loss: 0.8536 (0.8466) time: 0.1503 data: 0.0606 max mem: 9390 +Train: [13] [1400/6250] eta: 0:13:42 lr: 0.000123 grad: 0.0653 (0.0669) loss: 0.8430 (0.8465) time: 0.1422 data: 0.0514 max mem: 9390 +Train: [13] [1500/6250] eta: 0:13:24 lr: 0.000123 grad: 0.0656 (0.0667) loss: 0.8448 (0.8464) time: 0.1472 data: 0.0518 max mem: 9390 +Train: [13] [1600/6250] eta: 0:13:06 lr: 0.000123 grad: 0.0607 (0.0666) loss: 0.8452 (0.8464) time: 0.1836 data: 0.0920 max mem: 9390 +Train: [13] [1700/6250] eta: 0:12:47 lr: 0.000123 grad: 0.0616 (0.0666) loss: 0.8488 (0.8464) time: 0.1485 data: 0.0560 max mem: 9390 +Train: [13] [1800/6250] eta: 0:12:28 lr: 0.000123 grad: 0.0593 (0.0664) loss: 0.8437 (0.8464) time: 0.1551 data: 0.0662 max mem: 9390 +Train: [13] [1900/6250] eta: 0:12:11 lr: 0.000123 grad: 0.0633 (0.0663) loss: 0.8467 (0.8463) time: 0.1892 data: 0.0984 max mem: 9390 +Train: [13] [2000/6250] eta: 0:11:54 lr: 0.000123 grad: 0.0672 (0.0664) loss: 0.8388 (0.8462) time: 0.1724 data: 0.0890 max mem: 9390 +Train: [13] [2100/6250] eta: 0:11:36 lr: 0.000123 grad: 0.0618 (0.0664) loss: 0.8444 (0.8461) time: 0.1758 data: 0.0778 max mem: 9390 +Train: [13] [2200/6250] eta: 0:11:17 lr: 0.000123 grad: 0.0645 (0.0664) loss: 0.8463 (0.8461) time: 0.1493 data: 0.0612 max mem: 9390 +Train: [13] [2300/6250] eta: 0:11:01 lr: 0.000123 grad: 0.0650 (0.0664) loss: 0.8444 (0.8460) time: 0.1662 data: 0.0826 max mem: 9390 +Train: [13] [2400/6250] eta: 0:10:43 lr: 0.000123 grad: 0.0616 (0.0663) loss: 0.8465 (0.8460) time: 0.1527 data: 0.0637 max mem: 9390 +Train: [13] [2500/6250] eta: 0:10:26 lr: 0.000123 grad: 0.0642 (0.0663) loss: 0.8420 (0.8460) time: 0.1989 data: 0.1196 max mem: 9390 +Train: [13] [2600/6250] eta: 0:10:08 lr: 0.000123 grad: 0.0660 (0.0662) loss: 0.8418 (0.8459) time: 0.1607 data: 0.0717 max mem: 9390 +Train: [13] [2700/6250] eta: 0:09:51 lr: 0.000123 grad: 0.0666 (0.0662) loss: 0.8479 (0.8459) time: 0.1638 data: 0.0751 max mem: 9390 +Train: [13] [2800/6250] eta: 0:09:33 lr: 0.000123 grad: 0.0674 (0.0662) loss: 0.8438 (0.8459) time: 0.1617 data: 0.0758 max mem: 9390 +Train: [13] [2900/6250] eta: 0:09:16 lr: 0.000123 grad: 0.0638 (0.0662) loss: 0.8442 (0.8459) time: 0.1578 data: 0.0746 max mem: 9390 +Train: [13] [3000/6250] eta: 0:09:00 lr: 0.000123 grad: 0.0656 (0.0661) loss: 0.8418 (0.8459) time: 0.1800 data: 0.0900 max mem: 9390 +Train: [13] [3100/6250] eta: 0:08:42 lr: 0.000123 grad: 0.0651 (0.0660) loss: 0.8481 (0.8459) time: 0.1469 data: 0.0606 max mem: 9390 +Train: [13] [3200/6250] eta: 0:08:26 lr: 0.000123 grad: 0.0660 (0.0660) loss: 0.8450 (0.8459) time: 0.2024 data: 0.1052 max mem: 9390 +Train: [13] [3300/6250] eta: 0:08:09 lr: 0.000123 grad: 0.0675 (0.0660) loss: 0.8439 (0.8458) time: 0.1689 data: 0.0764 max mem: 9390 +Train: [13] [3400/6250] eta: 0:07:52 lr: 0.000123 grad: 0.0619 (0.0660) loss: 0.8410 (0.8457) time: 0.1726 data: 0.0923 max mem: 9390 +Train: [13] [3500/6250] eta: 0:07:35 lr: 0.000123 grad: 0.0619 (0.0659) loss: 0.8407 (0.8457) time: 0.1645 data: 0.0799 max mem: 9390 +Train: [13] [3600/6250] eta: 0:07:18 lr: 0.000123 grad: 0.0608 (0.0659) loss: 0.8487 (0.8456) time: 0.1396 data: 0.0560 max mem: 9390 +Train: [13] [3700/6250] eta: 0:07:02 lr: 0.000122 grad: 0.0617 (0.0659) loss: 0.8462 (0.8456) time: 0.1762 data: 0.0823 max mem: 9390 +Train: [13] [3800/6250] eta: 0:06:45 lr: 0.000122 grad: 0.0571 (0.0658) loss: 0.8472 (0.8456) time: 0.1531 data: 0.0715 max mem: 9390 +Train: [13] [3900/6250] eta: 0:06:28 lr: 0.000122 grad: 0.0630 (0.0658) loss: 0.8440 (0.8455) time: 0.1656 data: 0.0849 max mem: 9390 +Train: [13] [4000/6250] eta: 0:06:12 lr: 0.000122 grad: 0.0637 (0.0658) loss: 0.8470 (0.8455) time: 0.1582 data: 0.0735 max mem: 9390 +Train: [13] [4100/6250] eta: 0:05:55 lr: 0.000122 grad: 0.0616 (0.0657) loss: 0.8480 (0.8455) time: 0.1493 data: 0.0694 max mem: 9390 +Train: [13] [4200/6250] eta: 0:05:38 lr: 0.000122 grad: 0.0633 (0.0657) loss: 0.8497 (0.8455) time: 0.1746 data: 0.0855 max mem: 9390 +Train: [13] [4300/6250] eta: 0:05:21 lr: 0.000122 grad: 0.0626 (0.0657) loss: 0.8462 (0.8455) time: 0.1507 data: 0.0574 max mem: 9390 +Train: [13] [4400/6250] eta: 0:05:05 lr: 0.000122 grad: 0.0621 (0.0656) loss: 0.8442 (0.8456) time: 0.1523 data: 0.0661 max mem: 9390 +Train: [13] [4500/6250] eta: 0:04:48 lr: 0.000122 grad: 0.0617 (0.0656) loss: 0.8430 (0.8456) time: 0.1681 data: 0.0803 max mem: 9390 +Train: [13] [4600/6250] eta: 0:04:32 lr: 0.000122 grad: 0.0591 (0.0656) loss: 0.8478 (0.8456) time: 0.1813 data: 0.0957 max mem: 9390 +Train: [13] [4700/6250] eta: 0:04:15 lr: 0.000122 grad: 0.0620 (0.0655) loss: 0.8493 (0.8457) time: 0.1506 data: 0.0651 max mem: 9390 +Train: [13] [4800/6250] eta: 0:03:59 lr: 0.000122 grad: 0.0605 (0.0655) loss: 0.8478 (0.8457) time: 0.1447 data: 0.0548 max mem: 9390 +Train: [13] [4900/6250] eta: 0:03:42 lr: 0.000122 grad: 0.0643 (0.0655) loss: 0.8435 (0.8457) time: 0.1375 data: 0.0562 max mem: 9390 +Train: [13] [5000/6250] eta: 0:03:26 lr: 0.000122 grad: 0.0595 (0.0654) loss: 0.8460 (0.8457) time: 0.1941 data: 0.1092 max mem: 9390 +Train: [13] [5100/6250] eta: 0:03:09 lr: 0.000122 grad: 0.0589 (0.0654) loss: 0.8473 (0.8457) time: 0.1634 data: 0.0782 max mem: 9390 +Train: [13] [5200/6250] eta: 0:02:52 lr: 0.000122 grad: 0.0597 (0.0653) loss: 0.8437 (0.8457) time: 0.1550 data: 0.0658 max mem: 9390 +Train: [13] [5300/6250] eta: 0:02:36 lr: 0.000122 grad: 0.0596 (0.0653) loss: 0.8464 (0.8458) time: 0.1534 data: 0.0662 max mem: 9390 +Train: [13] [5400/6250] eta: 0:02:19 lr: 0.000122 grad: 0.0625 (0.0652) loss: 0.8465 (0.8458) time: 0.1551 data: 0.0633 max mem: 9390 +Train: [13] [5500/6250] eta: 0:02:03 lr: 0.000122 grad: 0.0630 (0.0652) loss: 0.8457 (0.8457) time: 0.1591 data: 0.0789 max mem: 9390 +Train: [13] [5600/6250] eta: 0:01:47 lr: 0.000122 grad: 0.0617 (0.0652) loss: 0.8433 (0.8457) time: 0.1732 data: 0.0795 max mem: 9390 +Train: [13] [5700/6250] eta: 0:01:30 lr: 0.000122 grad: 0.0635 (0.0651) loss: 0.8459 (0.8457) time: 0.1717 data: 0.0814 max mem: 9390 +Train: [13] [5800/6250] eta: 0:01:14 lr: 0.000122 grad: 0.0610 (0.0651) loss: 0.8434 (0.8457) time: 0.1448 data: 0.0537 max mem: 9390 +Train: [13] [5900/6250] eta: 0:00:57 lr: 0.000122 grad: 0.0618 (0.0651) loss: 0.8452 (0.8457) time: 0.1531 data: 0.0643 max mem: 9390 +Train: [13] [6000/6250] eta: 0:00:41 lr: 0.000122 grad: 0.0609 (0.0651) loss: 0.8410 (0.8457) time: 0.1707 data: 0.0830 max mem: 9390 +Train: [13] [6100/6250] eta: 0:00:24 lr: 0.000122 grad: 0.0602 (0.0650) loss: 0.8470 (0.8457) time: 0.1627 data: 0.0761 max mem: 9390 +Train: [13] [6200/6250] eta: 0:00:08 lr: 0.000122 grad: 0.0611 (0.0650) loss: 0.8413 (0.8456) time: 0.1579 data: 0.0722 max mem: 9390 +Train: [13] [6249/6250] eta: 0:00:00 lr: 0.000122 grad: 0.0633 (0.0650) loss: 0.8429 (0.8456) time: 0.1646 data: 0.0762 max mem: 9390 +Train: [13] Total time: 0:17:14 (0.1655 s / it) +Averaged stats: lr: 0.000122 grad: 0.0633 (0.0650) loss: 0.8429 (0.8456) +Eval (hcp-train-subset): [13] [ 0/62] eta: 0:05:46 loss: 0.8576 (0.8576) time: 5.5890 data: 5.5598 max mem: 9390 +Eval (hcp-train-subset): [13] [61/62] eta: 0:00:00 loss: 0.8495 (0.8502) time: 0.1121 data: 0.0867 max mem: 9390 +Eval (hcp-train-subset): [13] Total time: 0:00:13 (0.2222 s / it) +Averaged stats (hcp-train-subset): loss: 0.8495 (0.8502) +Eval (hcp-val): [13] [ 0/62] eta: 0:03:59 loss: 0.8406 (0.8406) time: 3.8609 data: 3.7927 max mem: 9390 +Eval (hcp-val): [13] [61/62] eta: 0:00:00 loss: 0.8458 (0.8452) time: 0.1312 data: 0.1042 max mem: 9390 +Eval (hcp-val): [13] Total time: 0:00:13 (0.2183 s / it) +Averaged stats (hcp-val): loss: 0.8458 (0.8452) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +Train: [14] [ 0/6250] eta: 7:03:49 lr: 0.000122 grad: 0.0622 (0.0622) loss: 0.8481 (0.8481) time: 4.0688 data: 3.8392 max mem: 9390 +Train: [14] [ 100/6250] eta: 0:21:53 lr: 0.000122 grad: 0.0688 (0.0771) loss: 0.8470 (0.8394) time: 0.1403 data: 0.0488 max mem: 9390 +Train: [14] [ 200/6250] eta: 0:19:07 lr: 0.000122 grad: 0.0630 (0.0738) loss: 0.8488 (0.8413) time: 0.1322 data: 0.0461 max mem: 9390 +Train: [14] [ 300/6250] eta: 0:18:06 lr: 0.000122 grad: 0.0665 (0.0723) loss: 0.8415 (0.8417) time: 0.1702 data: 0.0750 max mem: 9390 +Train: [14] [ 400/6250] eta: 0:17:29 lr: 0.000122 grad: 0.0627 (0.0706) loss: 0.8441 (0.8425) time: 0.1762 data: 0.0862 max mem: 9390 +Train: [14] [ 500/6250] eta: 0:16:51 lr: 0.000122 grad: 0.0640 (0.0697) loss: 0.8486 (0.8434) time: 0.1660 data: 0.0645 max mem: 9390 +Train: [14] [ 600/6250] eta: 0:16:20 lr: 0.000122 grad: 0.0604 (0.0688) loss: 0.8476 (0.8442) time: 0.1649 data: 0.0622 max mem: 9390 +Train: [14] [ 700/6250] eta: 0:15:56 lr: 0.000122 grad: 0.0605 (0.0679) loss: 0.8485 (0.8449) time: 0.2024 data: 0.1044 max mem: 9390 +Train: [14] [ 800/6250] eta: 0:15:38 lr: 0.000122 grad: 0.0598 (0.0673) loss: 0.8479 (0.8453) time: 0.1906 data: 0.1009 max mem: 9390 +Train: [14] [ 900/6250] eta: 0:15:19 lr: 0.000122 grad: 0.0601 (0.0668) loss: 0.8493 (0.8456) time: 0.1725 data: 0.0798 max mem: 9390 +Train: [14] [1000/6250] eta: 0:14:59 lr: 0.000122 grad: 0.0617 (0.0663) loss: 0.8472 (0.8460) time: 0.1644 data: 0.0692 max mem: 9390 +Train: [14] [1100/6250] eta: 0:14:41 lr: 0.000122 grad: 0.0653 (0.0662) loss: 0.8458 (0.8460) time: 0.1650 data: 0.0748 max mem: 9390 +Train: [14] [1200/6250] eta: 0:14:19 lr: 0.000122 grad: 0.0616 (0.0660) loss: 0.8511 (0.8462) time: 0.1757 data: 0.0925 max mem: 9390 +Train: [14] [1300/6250] eta: 0:13:57 lr: 0.000122 grad: 0.0591 (0.0656) loss: 0.8480 (0.8463) time: 0.1237 data: 0.0380 max mem: 9390 +Train: [14] [1400/6250] eta: 0:13:37 lr: 0.000122 grad: 0.0603 (0.0654) loss: 0.8492 (0.8463) time: 0.1709 data: 0.0832 max mem: 9390 +Train: [14] [1500/6250] eta: 0:13:17 lr: 0.000122 grad: 0.0595 (0.0653) loss: 0.8477 (0.8463) time: 0.1509 data: 0.0666 max mem: 9390 +Train: [14] [1600/6250] eta: 0:12:59 lr: 0.000122 grad: 0.0631 (0.0651) loss: 0.8439 (0.8462) time: 0.1567 data: 0.0622 max mem: 9390 +Train: [14] [1700/6250] eta: 0:12:39 lr: 0.000122 grad: 0.0620 (0.0650) loss: 0.8450 (0.8462) time: 0.1540 data: 0.0632 max mem: 9390 +Train: [14] [1800/6250] eta: 0:12:22 lr: 0.000122 grad: 0.0589 (0.0648) loss: 0.8441 (0.8461) time: 0.1699 data: 0.0758 max mem: 9390 +Train: [14] [1900/6250] eta: 0:12:03 lr: 0.000122 grad: 0.0577 (0.0647) loss: 0.8425 (0.8460) time: 0.1432 data: 0.0496 max mem: 9390 +Train: [14] [2000/6250] eta: 0:11:45 lr: 0.000122 grad: 0.0625 (0.0647) loss: 0.8432 (0.8460) time: 0.1530 data: 0.0603 max mem: 9390 +Train: [14] [2100/6250] eta: 0:11:29 lr: 0.000122 grad: 0.0636 (0.0646) loss: 0.8452 (0.8460) time: 0.1649 data: 0.0755 max mem: 9390 +Train: [14] [2200/6250] eta: 0:11:14 lr: 0.000122 grad: 0.0639 (0.0645) loss: 0.8471 (0.8459) time: 0.1869 data: 0.1036 max mem: 9390 +Train: [14] [2300/6250] eta: 0:10:56 lr: 0.000122 grad: 0.0651 (0.0644) loss: 0.8479 (0.8459) time: 0.1453 data: 0.0597 max mem: 9390 +Train: [14] [2400/6250] eta: 0:10:39 lr: 0.000122 grad: 0.0620 (0.0644) loss: 0.8431 (0.8458) time: 0.1385 data: 0.0485 max mem: 9390 +Train: [14] [2500/6250] eta: 0:10:23 lr: 0.000122 grad: 0.0639 (0.0644) loss: 0.8444 (0.8456) time: 0.1649 data: 0.0808 max mem: 9390 +Train: [14] [2600/6250] eta: 0:10:06 lr: 0.000122 grad: 0.0628 (0.0647) loss: 0.8420 (0.8454) time: 0.1516 data: 0.0556 max mem: 9390 +Train: [14] [2700/6250] eta: 0:09:48 lr: 0.000122 grad: 0.0624 (0.0647) loss: 0.8406 (0.8452) time: 0.1623 data: 0.0745 max mem: 9390 +Train: [14] [2800/6250] eta: 0:09:31 lr: 0.000122 grad: 0.0654 (0.0647) loss: 0.8422 (0.8451) time: 0.1576 data: 0.0726 max mem: 9390 +Train: [14] [2900/6250] eta: 0:09:14 lr: 0.000122 grad: 0.0620 (0.0647) loss: 0.8415 (0.8450) time: 0.1720 data: 0.0787 max mem: 9390 +Train: [14] [3000/6250] eta: 0:08:57 lr: 0.000122 grad: 0.0647 (0.0647) loss: 0.8345 (0.8448) time: 0.1634 data: 0.0765 max mem: 9390 +Train: [14] [3100/6250] eta: 0:08:41 lr: 0.000122 grad: 0.0656 (0.0648) loss: 0.8385 (0.8446) time: 0.1556 data: 0.0712 max mem: 9390 +Train: [14] [3200/6250] eta: 0:08:24 lr: 0.000122 grad: 0.0656 (0.0649) loss: 0.8400 (0.8445) time: 0.1773 data: 0.0827 max mem: 9390 +Train: [14] [3300/6250] eta: 0:08:07 lr: 0.000122 grad: 0.0645 (0.0650) loss: 0.8409 (0.8444) time: 0.1660 data: 0.0815 max mem: 9390 +Train: [14] [3400/6250] eta: 0:07:51 lr: 0.000122 grad: 0.0643 (0.0650) loss: 0.8393 (0.8443) time: 0.1543 data: 0.0667 max mem: 9390 +Train: [14] [3500/6250] eta: 0:07:34 lr: 0.000122 grad: 0.0611 (0.0650) loss: 0.8404 (0.8442) time: 0.1474 data: 0.0586 max mem: 9390 +Train: [14] [3600/6250] eta: 0:07:18 lr: 0.000122 grad: 0.0645 (0.0650) loss: 0.8403 (0.8441) time: 0.1825 data: 0.0954 max mem: 9390 +Train: [14] [3700/6250] eta: 0:07:02 lr: 0.000122 grad: 0.0651 (0.0650) loss: 0.8435 (0.8441) time: 0.2004 data: 0.1172 max mem: 9390 +Train: [14] [3800/6250] eta: 0:06:46 lr: 0.000122 grad: 0.0643 (0.0651) loss: 0.8435 (0.8441) time: 0.1518 data: 0.0715 max mem: 9390 +Train: [14] [3900/6250] eta: 0:06:30 lr: 0.000122 grad: 0.0665 (0.0651) loss: 0.8421 (0.8440) time: 0.1763 data: 0.0957 max mem: 9390 +Train: [14] [4000/6250] eta: 0:06:12 lr: 0.000122 grad: 0.0634 (0.0651) loss: 0.8396 (0.8440) time: 0.1743 data: 0.0878 max mem: 9390 +Train: [14] [4100/6250] eta: 0:05:56 lr: 0.000122 grad: 0.0661 (0.0651) loss: 0.8397 (0.8440) time: 0.2013 data: 0.1095 max mem: 9390 +Train: [14] [4200/6250] eta: 0:05:39 lr: 0.000122 grad: 0.0581 (0.0650) loss: 0.8464 (0.8440) time: 0.1593 data: 0.0656 max mem: 9390 +Train: [14] [4300/6250] eta: 0:05:22 lr: 0.000122 grad: 0.0625 (0.0650) loss: 0.8446 (0.8439) time: 0.1610 data: 0.0712 max mem: 9390 +Train: [14] [4400/6250] eta: 0:05:05 lr: 0.000122 grad: 0.0627 (0.0650) loss: 0.8421 (0.8439) time: 0.1429 data: 0.0539 max mem: 9390 +Train: [14] [4500/6250] eta: 0:04:48 lr: 0.000122 grad: 0.0634 (0.0650) loss: 0.8405 (0.8438) time: 0.1560 data: 0.0632 max mem: 9390 +Train: [14] [4600/6250] eta: 0:04:32 lr: 0.000122 grad: 0.0609 (0.0650) loss: 0.8423 (0.8438) time: 0.1478 data: 0.0564 max mem: 9390 +Train: [14] [4700/6250] eta: 0:04:15 lr: 0.000122 grad: 0.0613 (0.0650) loss: 0.8430 (0.8438) time: 0.1683 data: 0.0815 max mem: 9390 +Train: [14] [4800/6250] eta: 0:03:58 lr: 0.000122 grad: 0.0646 (0.0651) loss: 0.8402 (0.8437) time: 0.1580 data: 0.0683 max mem: 9390 +Train: [14] [4900/6250] eta: 0:03:42 lr: 0.000122 grad: 0.0612 (0.0650) loss: 0.8451 (0.8437) time: 0.1394 data: 0.0449 max mem: 9390 +Train: [14] [5000/6250] eta: 0:03:25 lr: 0.000122 grad: 0.0615 (0.0650) loss: 0.8450 (0.8438) time: 0.1981 data: 0.1085 max mem: 9390 +Train: [14] [5100/6250] eta: 0:03:09 lr: 0.000122 grad: 0.0613 (0.0650) loss: 0.8437 (0.8438) time: 0.1607 data: 0.0680 max mem: 9390 +Train: [14] [5200/6250] eta: 0:02:52 lr: 0.000122 grad: 0.0612 (0.0650) loss: 0.8438 (0.8438) time: 0.1594 data: 0.0722 max mem: 9390 +Train: [14] [5300/6250] eta: 0:02:36 lr: 0.000122 grad: 0.0651 (0.0649) loss: 0.8433 (0.8438) time: 0.1576 data: 0.0599 max mem: 9390 +Train: [14] [5400/6250] eta: 0:02:19 lr: 0.000122 grad: 0.0618 (0.0649) loss: 0.8458 (0.8438) time: 0.1476 data: 0.0532 max mem: 9390 +Train: [14] [5500/6250] eta: 0:02:03 lr: 0.000122 grad: 0.0640 (0.0649) loss: 0.8465 (0.8438) time: 0.1719 data: 0.0834 max mem: 9390 +Train: [14] [5600/6250] eta: 0:01:46 lr: 0.000122 grad: 0.0620 (0.0649) loss: 0.8479 (0.8438) time: 0.1698 data: 0.0764 max mem: 9390 +Train: [14] [5700/6250] eta: 0:01:30 lr: 0.000122 grad: 0.0618 (0.0649) loss: 0.8469 (0.8438) time: 0.1643 data: 0.0737 max mem: 9390 +Train: [14] [5800/6250] eta: 0:01:13 lr: 0.000122 grad: 0.0631 (0.0649) loss: 0.8450 (0.8438) time: 0.1583 data: 0.0668 max mem: 9390 +Train: [14] [5900/6250] eta: 0:00:57 lr: 0.000122 grad: 0.0685 (0.0649) loss: 0.8428 (0.8438) time: 0.1559 data: 0.0699 max mem: 9390 +Train: [14] [6000/6250] eta: 0:00:41 lr: 0.000122 grad: 0.0616 (0.0649) loss: 0.8458 (0.8439) time: 0.1591 data: 0.0692 max mem: 9390 +Train: [14] [6100/6250] eta: 0:00:24 lr: 0.000122 grad: 0.0595 (0.0649) loss: 0.8361 (0.8438) time: 0.1537 data: 0.0553 max mem: 9390 +Train: [14] [6200/6250] eta: 0:00:08 lr: 0.000122 grad: 0.0594 (0.0649) loss: 0.8445 (0.8439) time: 0.1659 data: 0.0742 max mem: 9390 +Train: [14] [6249/6250] eta: 0:00:00 lr: 0.000122 grad: 0.0609 (0.0649) loss: 0.8464 (0.8439) time: 0.1643 data: 0.0790 max mem: 9390 +Train: [14] Total time: 0:17:11 (0.1651 s / it) +Averaged stats: lr: 0.000122 grad: 0.0609 (0.0649) loss: 0.8464 (0.8439) +Eval (hcp-train-subset): [14] [ 0/62] eta: 0:04:03 loss: 0.8564 (0.8564) time: 3.9260 data: 3.8811 max mem: 9390 +Eval (hcp-train-subset): [14] [61/62] eta: 0:00:00 loss: 0.8491 (0.8498) time: 0.1319 data: 0.1049 max mem: 9390 +Eval (hcp-train-subset): [14] Total time: 0:00:13 (0.2209 s / it) +Averaged stats (hcp-train-subset): loss: 0.8491 (0.8498) +Making plots (hcp-train-subset): example=60 +Eval (hcp-val): [14] [ 0/62] eta: 0:05:08 loss: 0.8406 (0.8406) time: 4.9817 data: 4.9519 max mem: 9390 +Eval (hcp-val): [14] [61/62] eta: 0:00:00 loss: 0.8427 (0.8437) time: 0.1276 data: 0.1026 max mem: 9390 +Eval (hcp-val): [14] Total time: 0:00:13 (0.2151 s / it) +Averaged stats (hcp-val): loss: 0.8427 (0.8437) +Making plots (hcp-val): example=35 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +Train: [15] [ 0/6250] eta: 7:01:41 lr: 0.000122 grad: 0.1043 (0.1043) loss: 0.8494 (0.8494) time: 4.0483 data: 3.8313 max mem: 9390 +Train: [15] [ 100/6250] eta: 0:22:07 lr: 0.000122 grad: 0.0629 (0.0666) loss: 0.8484 (0.8568) time: 0.1497 data: 0.0608 max mem: 9390 +Train: [15] [ 200/6250] eta: 0:19:29 lr: 0.000122 grad: 0.0621 (0.0664) loss: 0.8413 (0.8496) time: 0.1516 data: 0.0727 max mem: 9390 +Train: [15] [ 300/6250] eta: 0:18:31 lr: 0.000122 grad: 0.0606 (0.0664) loss: 0.8500 (0.8466) time: 0.1709 data: 0.0784 max mem: 9390 +Train: [15] [ 400/6250] eta: 0:17:43 lr: 0.000122 grad: 0.0634 (0.0663) loss: 0.8492 (0.8456) time: 0.1586 data: 0.0730 max mem: 9390 +Train: [15] [ 500/6250] eta: 0:17:02 lr: 0.000122 grad: 0.0642 (0.0661) loss: 0.8416 (0.8451) time: 0.1459 data: 0.0604 max mem: 9390 +Train: [15] [ 600/6250] eta: 0:16:36 lr: 0.000122 grad: 0.0620 (0.0661) loss: 0.8388 (0.8442) time: 0.1480 data: 0.0497 max mem: 9390 +Train: [15] [ 700/6250] eta: 0:16:10 lr: 0.000122 grad: 0.0610 (0.0660) loss: 0.8373 (0.8434) time: 0.1721 data: 0.0784 max mem: 9390 +Train: [15] [ 800/6250] eta: 0:15:51 lr: 0.000122 grad: 0.0618 (0.0658) loss: 0.8375 (0.8429) time: 0.1675 data: 0.0720 max mem: 9390 +Train: [15] [ 900/6250] eta: 0:15:35 lr: 0.000122 grad: 0.0601 (0.0654) loss: 0.8389 (0.8427) time: 0.1741 data: 0.0848 max mem: 9390 +Train: [15] [1000/6250] eta: 0:15:14 lr: 0.000122 grad: 0.0625 (0.0652) loss: 0.8380 (0.8425) time: 0.1550 data: 0.0800 max mem: 9390 +Train: [15] [1100/6250] eta: 0:14:53 lr: 0.000121 grad: 0.0605 (0.0650) loss: 0.8432 (0.8424) time: 0.1735 data: 0.0820 max mem: 9390 +Train: [15] [1200/6250] eta: 0:14:34 lr: 0.000121 grad: 0.0666 (0.0651) loss: 0.8413 (0.8421) time: 0.1733 data: 0.0761 max mem: 9390 +Train: [15] [1300/6250] eta: 0:14:09 lr: 0.000121 grad: 0.0619 (0.0650) loss: 0.8399 (0.8421) time: 0.1513 data: 0.0697 max mem: 9390 +Train: [15] [1400/6250] eta: 0:13:48 lr: 0.000121 grad: 0.0640 (0.0650) loss: 0.8402 (0.8419) time: 0.1640 data: 0.0763 max mem: 9390 +Train: [15] [1500/6250] eta: 0:13:28 lr: 0.000121 grad: 0.0643 (0.0650) loss: 0.8394 (0.8419) time: 0.1537 data: 0.0717 max mem: 9390 +Train: [15] [1600/6250] eta: 0:13:09 lr: 0.000121 grad: 0.0594 (0.0649) loss: 0.8425 (0.8420) time: 0.1400 data: 0.0571 max mem: 9390 +Train: [15] [1700/6250] eta: 0:12:50 lr: 0.000121 grad: 0.0636 (0.0648) loss: 0.8414 (0.8420) time: 0.1715 data: 0.0853 max mem: 9390 +Train: [15] [1800/6250] eta: 0:12:32 lr: 0.000121 grad: 0.0643 (0.0648) loss: 0.8442 (0.8420) time: 0.1441 data: 0.0571 max mem: 9390 +Train: [15] [1900/6250] eta: 0:12:14 lr: 0.000121 grad: 0.0563 (0.0648) loss: 0.8454 (0.8421) time: 0.1661 data: 0.0828 max mem: 9390 +Train: [15] [2000/6250] eta: 0:11:56 lr: 0.000121 grad: 0.0649 (0.0649) loss: 0.8385 (0.8420) time: 0.1798 data: 0.0942 max mem: 9390 +Train: [15] [2100/6250] eta: 0:11:38 lr: 0.000121 grad: 0.0597 (0.0651) loss: 0.8422 (0.8420) time: 0.1341 data: 0.0478 max mem: 9390 +Train: [15] [2200/6250] eta: 0:11:21 lr: 0.000121 grad: 0.0601 (0.0652) loss: 0.8426 (0.8419) time: 0.1548 data: 0.0649 max mem: 9390 +Train: [15] [2300/6250] eta: 0:11:03 lr: 0.000121 grad: 0.0627 (0.0653) loss: 0.8398 (0.8419) time: 0.1752 data: 0.0861 max mem: 9390 +Train: [15] [2400/6250] eta: 0:10:47 lr: 0.000121 grad: 0.0619 (0.0653) loss: 0.8449 (0.8419) time: 0.1712 data: 0.0827 max mem: 9390 +Train: [15] [2500/6250] eta: 0:10:29 lr: 0.000121 grad: 0.0594 (0.0652) loss: 0.8463 (0.8418) time: 0.1678 data: 0.0844 max mem: 9390 +Train: [15] [2600/6250] eta: 0:10:13 lr: 0.000121 grad: 0.0624 (0.0652) loss: 0.8402 (0.8419) time: 0.1652 data: 0.0782 max mem: 9390 +Train: [15] [2700/6250] eta: 0:09:56 lr: 0.000121 grad: 0.0636 (0.0651) loss: 0.8397 (0.8419) time: 0.1675 data: 0.0780 max mem: 9390 +Train: [15] [2800/6250] eta: 0:09:38 lr: 0.000121 grad: 0.0612 (0.0650) loss: 0.8418 (0.8419) time: 0.1739 data: 0.0897 max mem: 9390 +Train: [15] [2900/6250] eta: 0:09:21 lr: 0.000121 grad: 0.0613 (0.0650) loss: 0.8395 (0.8419) time: 0.1503 data: 0.0703 max mem: 9390 +Train: [15] [3000/6250] eta: 0:09:04 lr: 0.000121 grad: 0.0606 (0.0650) loss: 0.8422 (0.8420) time: 0.1634 data: 0.0700 max mem: 9390 +Train: [15] [3100/6250] eta: 0:08:47 lr: 0.000121 grad: 0.0602 (0.0649) loss: 0.8479 (0.8420) time: 0.1575 data: 0.0759 max mem: 9390 +Train: [15] [3200/6250] eta: 0:08:30 lr: 0.000121 grad: 0.0587 (0.0649) loss: 0.8467 (0.8421) time: 0.1620 data: 0.0726 max mem: 9390 +Train: [15] [3300/6250] eta: 0:08:13 lr: 0.000121 grad: 0.0597 (0.0648) loss: 0.8441 (0.8421) time: 0.1791 data: 0.0928 max mem: 9390 +Train: [15] [3400/6250] eta: 0:07:56 lr: 0.000121 grad: 0.0688 (0.0648) loss: 0.8380 (0.8422) time: 0.1645 data: 0.0721 max mem: 9390 +Train: [15] [3500/6250] eta: 0:07:39 lr: 0.000121 grad: 0.0629 (0.0648) loss: 0.8434 (0.8422) time: 0.1754 data: 0.0900 max mem: 9390 +Train: [15] [3600/6250] eta: 0:07:22 lr: 0.000121 grad: 0.0598 (0.0647) loss: 0.8448 (0.8422) time: 0.1511 data: 0.0544 max mem: 9390 +Train: [15] [3700/6250] eta: 0:07:05 lr: 0.000121 grad: 0.0637 (0.0646) loss: 0.8437 (0.8422) time: 0.1533 data: 0.0631 max mem: 9390 +Train: [15] [3800/6250] eta: 0:06:48 lr: 0.000121 grad: 0.0655 (0.0646) loss: 0.8471 (0.8422) time: 0.1451 data: 0.0576 max mem: 9390 +Train: [15] [3900/6250] eta: 0:06:31 lr: 0.000121 grad: 0.0621 (0.0646) loss: 0.8391 (0.8422) time: 0.1419 data: 0.0542 max mem: 9390 +Train: [15] [4000/6250] eta: 0:06:14 lr: 0.000121 grad: 0.0625 (0.0646) loss: 0.8416 (0.8422) time: 0.1582 data: 0.0663 max mem: 9390 +Train: [15] [4100/6250] eta: 0:05:58 lr: 0.000121 grad: 0.0670 (0.0645) loss: 0.8425 (0.8422) time: 0.1470 data: 0.0552 max mem: 9390 +Train: [15] [4200/6250] eta: 0:05:41 lr: 0.000121 grad: 0.0609 (0.0645) loss: 0.8389 (0.8421) time: 0.1594 data: 0.0775 max mem: 9390 +Train: [15] [4300/6250] eta: 0:05:25 lr: 0.000121 grad: 0.0608 (0.0645) loss: 0.8438 (0.8421) time: 0.1834 data: 0.0989 max mem: 9390 +Train: [15] [4400/6250] eta: 0:05:08 lr: 0.000121 grad: 0.0621 (0.0645) loss: 0.8409 (0.8421) time: 0.1482 data: 0.0656 max mem: 9390 +Train: [15] [4500/6250] eta: 0:04:51 lr: 0.000121 grad: 0.0600 (0.0645) loss: 0.8423 (0.8421) time: 0.1893 data: 0.0995 max mem: 9390 +Train: [15] [4600/6250] eta: 0:04:34 lr: 0.000121 grad: 0.0624 (0.0645) loss: 0.8444 (0.8421) time: 0.1659 data: 0.0778 max mem: 9390 +Train: [15] [4700/6250] eta: 0:04:18 lr: 0.000121 grad: 0.0661 (0.0645) loss: 0.8373 (0.8421) time: 0.1467 data: 0.0534 max mem: 9390 +Train: [15] [4800/6250] eta: 0:04:01 lr: 0.000121 grad: 0.0647 (0.0645) loss: 0.8346 (0.8420) time: 0.1423 data: 0.0567 max mem: 9390 +Train: [15] [4900/6250] eta: 0:03:44 lr: 0.000121 grad: 0.0674 (0.0645) loss: 0.8427 (0.8420) time: 0.1636 data: 0.0789 max mem: 9390 +Train: [15] [5000/6250] eta: 0:03:28 lr: 0.000121 grad: 0.0631 (0.0646) loss: 0.8381 (0.8419) time: 0.1704 data: 0.0881 max mem: 9390 +Train: [15] [5100/6250] eta: 0:03:11 lr: 0.000121 grad: 0.0681 (0.0646) loss: 0.8390 (0.8419) time: 0.1700 data: 0.0879 max mem: 9390 +Train: [15] [5200/6250] eta: 0:02:54 lr: 0.000121 grad: 0.0594 (0.0647) loss: 0.8421 (0.8419) time: 0.1669 data: 0.0748 max mem: 9390 +Train: [15] [5300/6250] eta: 0:02:38 lr: 0.000121 grad: 0.0618 (0.0647) loss: 0.8367 (0.8418) time: 0.1753 data: 0.0889 max mem: 9390 +Train: [15] [5400/6250] eta: 0:02:21 lr: 0.000121 grad: 0.0603 (0.0647) loss: 0.8384 (0.8418) time: 0.2027 data: 0.1204 max mem: 9390 +Train: [15] [5500/6250] eta: 0:02:04 lr: 0.000121 grad: 0.0629 (0.0647) loss: 0.8385 (0.8418) time: 0.1450 data: 0.0532 max mem: 9390 +Train: [15] [5600/6250] eta: 0:01:48 lr: 0.000121 grad: 0.0657 (0.0647) loss: 0.8434 (0.8418) time: 0.1773 data: 0.0905 max mem: 9390 +Train: [15] [5700/6250] eta: 0:01:31 lr: 0.000121 grad: 0.0668 (0.0648) loss: 0.8405 (0.8418) time: 0.1708 data: 0.0818 max mem: 9390 +Train: [15] [5800/6250] eta: 0:01:14 lr: 0.000121 grad: 0.0647 (0.0648) loss: 0.8423 (0.8418) time: 0.1712 data: 0.0870 max mem: 9390 +Train: [15] [5900/6250] eta: 0:00:58 lr: 0.000121 grad: 0.0594 (0.0648) loss: 0.8413 (0.8418) time: 0.1728 data: 0.0880 max mem: 9390 +Train: [15] [6000/6250] eta: 0:00:41 lr: 0.000121 grad: 0.0718 (0.0648) loss: 0.8425 (0.8418) time: 0.1668 data: 0.0749 max mem: 9390 +Train: [15] [6100/6250] eta: 0:00:24 lr: 0.000121 grad: 0.0647 (0.0648) loss: 0.8386 (0.8418) time: 0.1692 data: 0.0861 max mem: 9390 +Train: [15] [6200/6250] eta: 0:00:08 lr: 0.000121 grad: 0.0654 (0.0648) loss: 0.8400 (0.8418) time: 0.1801 data: 0.1001 max mem: 9390 +Train: [15] [6249/6250] eta: 0:00:00 lr: 0.000121 grad: 0.0597 (0.0648) loss: 0.8431 (0.8418) time: 0.1605 data: 0.0750 max mem: 9390 +Train: [15] Total time: 0:17:26 (0.1675 s / it) +Averaged stats: lr: 0.000121 grad: 0.0597 (0.0648) loss: 0.8431 (0.8418) +Eval (hcp-train-subset): [15] [ 0/62] eta: 0:04:25 loss: 0.8600 (0.8600) time: 4.2800 data: 4.2043 max mem: 9390 +Eval (hcp-train-subset): [15] [61/62] eta: 0:00:00 loss: 0.8497 (0.8495) time: 0.1429 data: 0.1174 max mem: 9390 +Eval (hcp-train-subset): [15] Total time: 0:00:14 (0.2265 s / it) +Averaged stats (hcp-train-subset): loss: 0.8497 (0.8495) +Eval (hcp-val): [15] [ 0/62] eta: 0:05:39 loss: 0.8376 (0.8376) time: 5.4770 data: 5.4469 max mem: 9390 +Eval (hcp-val): [15] [61/62] eta: 0:00:00 loss: 0.8432 (0.8443) time: 0.1271 data: 0.0999 max mem: 9390 +Eval (hcp-val): [15] Total time: 0:00:13 (0.2170 s / it) +Averaged stats (hcp-val): loss: 0.8432 (0.8443) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +Train: [16] [ 0/6250] eta: 9:11:30 lr: 0.000121 grad: 0.1358 (0.1358) loss: 0.8775 (0.8775) time: 5.2945 data: 5.1220 max mem: 9390 +Train: [16] [ 100/6250] eta: 0:22:21 lr: 0.000121 grad: 0.0700 (0.0766) loss: 0.8357 (0.8422) time: 0.1446 data: 0.0551 max mem: 9390 +Train: [16] [ 200/6250] eta: 0:19:32 lr: 0.000121 grad: 0.0686 (0.0747) loss: 0.8350 (0.8400) time: 0.1446 data: 0.0587 max mem: 9390 +Train: [16] [ 300/6250] eta: 0:18:39 lr: 0.000121 grad: 0.0611 (0.0729) loss: 0.8403 (0.8394) time: 0.1610 data: 0.0718 max mem: 9390 +Train: [16] [ 400/6250] eta: 0:17:44 lr: 0.000121 grad: 0.0627 (0.0706) loss: 0.8430 (0.8401) time: 0.1604 data: 0.0679 max mem: 9390 +Train: [16] [ 500/6250] eta: 0:17:02 lr: 0.000121 grad: 0.0640 (0.0694) loss: 0.8415 (0.8408) time: 0.1547 data: 0.0522 max mem: 9390 +Train: [16] [ 600/6250] eta: 0:16:28 lr: 0.000121 grad: 0.0603 (0.0680) loss: 0.8483 (0.8417) time: 0.1361 data: 0.0367 max mem: 9390 +Train: [16] [ 700/6250] eta: 0:16:09 lr: 0.000121 grad: 0.0611 (0.0673) loss: 0.8479 (0.8423) time: 0.1851 data: 0.0913 max mem: 9390 +Train: [16] [ 800/6250] eta: 0:15:47 lr: 0.000121 grad: 0.0630 (0.0668) loss: 0.8396 (0.8425) time: 0.1765 data: 0.0845 max mem: 9390 +Train: [16] [ 900/6250] eta: 0:15:34 lr: 0.000121 grad: 0.0616 (0.0662) loss: 0.8427 (0.8426) time: 0.1964 data: 0.1107 max mem: 9390 +Train: [16] [1000/6250] eta: 0:15:15 lr: 0.000121 grad: 0.0607 (0.0658) loss: 0.8382 (0.8425) time: 0.1761 data: 0.0851 max mem: 9390 +Train: [16] [1100/6250] eta: 0:14:52 lr: 0.000121 grad: 0.0614 (0.0655) loss: 0.8432 (0.8421) time: 0.1688 data: 0.0937 max mem: 9390 +Train: [16] [1200/6250] eta: 0:14:30 lr: 0.000121 grad: 0.0631 (0.0652) loss: 0.8413 (0.8419) time: 0.1585 data: 0.0706 max mem: 9390 +Train: [16] [1300/6250] eta: 0:14:08 lr: 0.000121 grad: 0.0592 (0.0650) loss: 0.8384 (0.8418) time: 0.1763 data: 0.0830 max mem: 9390 +Train: [16] [1400/6250] eta: 0:13:48 lr: 0.000121 grad: 0.0586 (0.0650) loss: 0.8387 (0.8417) time: 0.1867 data: 0.1008 max mem: 9390 +Train: [16] [1500/6250] eta: 0:13:27 lr: 0.000121 grad: 0.0591 (0.0648) loss: 0.8384 (0.8416) time: 0.1493 data: 0.0652 max mem: 9390 +Train: [16] [1600/6250] eta: 0:13:08 lr: 0.000121 grad: 0.0627 (0.0647) loss: 0.8457 (0.8416) time: 0.1756 data: 0.0856 max mem: 9390 +Train: [16] [1700/6250] eta: 0:12:49 lr: 0.000121 grad: 0.0633 (0.0646) loss: 0.8427 (0.8416) time: 0.1397 data: 0.0513 max mem: 9390 +Train: [16] [1800/6250] eta: 0:12:29 lr: 0.000121 grad: 0.0617 (0.0645) loss: 0.8400 (0.8416) time: 0.1781 data: 0.0904 max mem: 9390 +Train: [16] [1900/6250] eta: 0:12:10 lr: 0.000121 grad: 0.0644 (0.0645) loss: 0.8342 (0.8415) time: 0.1490 data: 0.0648 max mem: 9390 +Train: [16] [2000/6250] eta: 0:11:52 lr: 0.000121 grad: 0.0604 (0.0648) loss: 0.8418 (0.8414) time: 0.1593 data: 0.0717 max mem: 9390 +Train: [16] [2100/6250] eta: 0:11:34 lr: 0.000121 grad: 0.0607 (0.0648) loss: 0.8384 (0.8413) time: 0.1675 data: 0.0810 max mem: 9390 +Train: [16] [2200/6250] eta: 0:11:17 lr: 0.000121 grad: 0.0648 (0.0648) loss: 0.8389 (0.8412) time: 0.1759 data: 0.0948 max mem: 9390 +Train: [16] [2300/6250] eta: 0:11:01 lr: 0.000121 grad: 0.0616 (0.0648) loss: 0.8398 (0.8412) time: 0.1607 data: 0.0755 max mem: 9390 +Train: [16] [2400/6250] eta: 0:10:44 lr: 0.000121 grad: 0.0577 (0.0647) loss: 0.8490 (0.8412) time: 0.1842 data: 0.1000 max mem: 9390 +Train: [16] [2500/6250] eta: 0:10:29 lr: 0.000121 grad: 0.0640 (0.0647) loss: 0.8394 (0.8411) time: 0.1594 data: 0.0755 max mem: 9390 +Train: [16] [2600/6250] eta: 0:10:14 lr: 0.000121 grad: 0.0624 (0.0647) loss: 0.8349 (0.8410) time: 0.1982 data: 0.1165 max mem: 9390 +Train: [16] [2700/6250] eta: 0:09:55 lr: 0.000121 grad: 0.0645 (0.0647) loss: 0.8410 (0.8410) time: 0.1388 data: 0.0600 max mem: 9390 +Train: [16] [2800/6250] eta: 0:09:39 lr: 0.000121 grad: 0.0589 (0.0648) loss: 0.8408 (0.8409) time: 0.1573 data: 0.0733 max mem: 9390 +Train: [16] [2900/6250] eta: 0:09:22 lr: 0.000121 grad: 0.0664 (0.0648) loss: 0.8406 (0.8409) time: 0.1733 data: 0.0781 max mem: 9390 +Train: [16] [3000/6250] eta: 0:09:04 lr: 0.000121 grad: 0.0585 (0.0647) loss: 0.8389 (0.8408) time: 0.1500 data: 0.0572 max mem: 9390 +Train: [16] [3100/6250] eta: 0:08:47 lr: 0.000121 grad: 0.0610 (0.0646) loss: 0.8424 (0.8408) time: 0.1389 data: 0.0414 max mem: 9390 +Train: [16] [3200/6250] eta: 0:08:30 lr: 0.000121 grad: 0.0669 (0.0647) loss: 0.8420 (0.8409) time: 0.1743 data: 0.0825 max mem: 9390 +Train: [16] [3300/6250] eta: 0:08:12 lr: 0.000121 grad: 0.0638 (0.0647) loss: 0.8399 (0.8408) time: 0.1644 data: 0.0739 max mem: 9390 +Train: [16] [3400/6250] eta: 0:07:55 lr: 0.000121 grad: 0.0617 (0.0647) loss: 0.8408 (0.8408) time: 0.1667 data: 0.0794 max mem: 9390 +Train: [16] [3500/6250] eta: 0:07:37 lr: 0.000120 grad: 0.0688 (0.0647) loss: 0.8394 (0.8408) time: 0.1534 data: 0.0561 max mem: 9390 +Train: [16] [3600/6250] eta: 0:07:20 lr: 0.000120 grad: 0.0597 (0.0646) loss: 0.8431 (0.8409) time: 0.1511 data: 0.0424 max mem: 9390 +Train: [16] [3700/6250] eta: 0:07:03 lr: 0.000120 grad: 0.0609 (0.0645) loss: 0.8420 (0.8409) time: 0.1619 data: 0.0659 max mem: 9390 +Train: [16] [3800/6250] eta: 0:06:46 lr: 0.000120 grad: 0.0634 (0.0645) loss: 0.8447 (0.8409) time: 0.1694 data: 0.0709 max mem: 9390 +Train: [16] [3900/6250] eta: 0:06:29 lr: 0.000120 grad: 0.0614 (0.0645) loss: 0.8405 (0.8409) time: 0.1764 data: 0.0875 max mem: 9390 +Train: [16] [4000/6250] eta: 0:06:13 lr: 0.000120 grad: 0.0652 (0.0644) loss: 0.8419 (0.8410) time: 0.1927 data: 0.1053 max mem: 9390 +Train: [16] [4100/6250] eta: 0:05:57 lr: 0.000120 grad: 0.0639 (0.0644) loss: 0.8394 (0.8409) time: 0.1732 data: 0.0845 max mem: 9390 +Train: [16] [4200/6250] eta: 0:05:40 lr: 0.000120 grad: 0.0586 (0.0643) loss: 0.8441 (0.8410) time: 0.1626 data: 0.0765 max mem: 9390 +Train: [16] [4300/6250] eta: 0:05:23 lr: 0.000120 grad: 0.0568 (0.0643) loss: 0.8426 (0.8410) time: 0.1505 data: 0.0513 max mem: 9390 +Train: [16] [4400/6250] eta: 0:05:07 lr: 0.000120 grad: 0.0612 (0.0642) loss: 0.8442 (0.8410) time: 0.1522 data: 0.0552 max mem: 9390 +Train: [16] [4500/6250] eta: 0:04:50 lr: 0.000120 grad: 0.0615 (0.0642) loss: 0.8436 (0.8411) time: 0.1575 data: 0.0624 max mem: 9390 +Train: [16] [4600/6250] eta: 0:04:33 lr: 0.000120 grad: 0.0624 (0.0642) loss: 0.8432 (0.8411) time: 0.1748 data: 0.0819 max mem: 9390 +Train: [16] [4700/6250] eta: 0:04:17 lr: 0.000120 grad: 0.0577 (0.0641) loss: 0.8453 (0.8412) time: 0.1654 data: 0.0751 max mem: 9390 +Train: [16] [4800/6250] eta: 0:04:00 lr: 0.000120 grad: 0.0611 (0.0641) loss: 0.8424 (0.8412) time: 0.1603 data: 0.0734 max mem: 9390 +Train: [16] [4900/6250] eta: 0:03:43 lr: 0.000120 grad: 0.0619 (0.0641) loss: 0.8418 (0.8413) time: 0.1595 data: 0.0753 max mem: 9390 +Train: [16] [5000/6250] eta: 0:03:27 lr: 0.000120 grad: 0.0611 (0.0641) loss: 0.8437 (0.8413) time: 0.1520 data: 0.0683 max mem: 9390 +Train: [16] [5100/6250] eta: 0:03:10 lr: 0.000120 grad: 0.0638 (0.0641) loss: 0.8426 (0.8413) time: 0.1282 data: 0.0449 max mem: 9390 +Train: [16] [5200/6250] eta: 0:02:53 lr: 0.000120 grad: 0.0615 (0.0640) loss: 0.8428 (0.8413) time: 0.1752 data: 0.0837 max mem: 9390 +Train: [16] [5300/6250] eta: 0:02:37 lr: 0.000120 grad: 0.0618 (0.0640) loss: 0.8428 (0.8413) time: 0.1781 data: 0.0966 max mem: 9390 +Train: [16] [5400/6250] eta: 0:02:20 lr: 0.000120 grad: 0.0614 (0.0641) loss: 0.8444 (0.8413) time: 0.1578 data: 0.0676 max mem: 9390 +Train: [16] [5500/6250] eta: 0:02:04 lr: 0.000120 grad: 0.0643 (0.0641) loss: 0.8400 (0.8412) time: 0.1684 data: 0.0828 max mem: 9390 +Train: [16] [5600/6250] eta: 0:01:47 lr: 0.000120 grad: 0.0655 (0.0641) loss: 0.8403 (0.8413) time: 0.1591 data: 0.0697 max mem: 9390 +Train: [16] [5700/6250] eta: 0:01:30 lr: 0.000120 grad: 0.0619 (0.0641) loss: 0.8387 (0.8412) time: 0.1629 data: 0.0760 max mem: 9390 +Train: [16] [5800/6250] eta: 0:01:14 lr: 0.000120 grad: 0.0731 (0.0643) loss: 0.8394 (0.8412) time: 0.1685 data: 0.0678 max mem: 9390 +Train: [16] [5900/6250] eta: 0:00:57 lr: 0.000120 grad: 0.0662 (0.0643) loss: 0.8399 (0.8412) time: 0.1699 data: 0.0843 max mem: 9390 +Train: [16] [6000/6250] eta: 0:00:41 lr: 0.000120 grad: 0.0647 (0.0644) loss: 0.8379 (0.8411) time: 0.1631 data: 0.0864 max mem: 9390 +Train: [16] [6100/6250] eta: 0:00:24 lr: 0.000120 grad: 0.0675 (0.0644) loss: 0.8362 (0.8410) time: 0.2182 data: 0.1366 max mem: 9390 +Train: [16] [6200/6250] eta: 0:00:08 lr: 0.000120 grad: 0.0608 (0.0644) loss: 0.8361 (0.8410) time: 0.1566 data: 0.0657 max mem: 9390 +Train: [16] [6249/6250] eta: 0:00:00 lr: 0.000120 grad: 0.0658 (0.0645) loss: 0.8379 (0.8409) time: 0.1874 data: 0.1009 max mem: 9390 +Train: [16] Total time: 0:17:21 (0.1666 s / it) +Averaged stats: lr: 0.000120 grad: 0.0658 (0.0645) loss: 0.8379 (0.8409) +Eval (hcp-train-subset): [16] [ 0/62] eta: 0:04:30 loss: 0.8568 (0.8568) time: 4.3624 data: 4.3239 max mem: 9390 +Eval (hcp-train-subset): [16] [61/62] eta: 0:00:00 loss: 0.8494 (0.8477) time: 0.1206 data: 0.0902 max mem: 9390 +Eval (hcp-train-subset): [16] Total time: 0:00:13 (0.2228 s / it) +Averaged stats (hcp-train-subset): loss: 0.8494 (0.8477) +Eval (hcp-val): [16] [ 0/62] eta: 0:03:50 loss: 0.8378 (0.8378) time: 3.7187 data: 3.6581 max mem: 9390 +Eval (hcp-val): [16] [61/62] eta: 0:00:00 loss: 0.8427 (0.8429) time: 0.1208 data: 0.0939 max mem: 9390 +Eval (hcp-val): [16] Total time: 0:00:13 (0.2160 s / it) +Averaged stats (hcp-val): loss: 0.8427 (0.8429) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +Train: [17] [ 0/6250] eta: 9:39:25 lr: 0.000120 grad: 0.1154 (0.1154) loss: 0.7930 (0.7930) time: 5.5624 data: 5.3919 max mem: 9390 +Train: [17] [ 100/6250] eta: 0:22:51 lr: 0.000120 grad: 0.0653 (0.0706) loss: 0.8453 (0.8440) time: 0.1821 data: 0.1031 max mem: 9390 +Train: [17] [ 200/6250] eta: 0:19:37 lr: 0.000120 grad: 0.0603 (0.0689) loss: 0.8414 (0.8412) time: 0.1480 data: 0.0613 max mem: 9390 +Train: [17] [ 300/6250] eta: 0:18:32 lr: 0.000120 grad: 0.0641 (0.0674) loss: 0.8432 (0.8420) time: 0.1659 data: 0.0734 max mem: 9390 +Train: [17] [ 400/6250] eta: 0:17:55 lr: 0.000120 grad: 0.0604 (0.0663) loss: 0.8425 (0.8419) time: 0.1851 data: 0.0943 max mem: 9390 +Train: [17] [ 500/6250] eta: 0:17:28 lr: 0.000120 grad: 0.0610 (0.0653) loss: 0.8422 (0.8423) time: 0.1790 data: 0.0849 max mem: 9390 +Train: [17] [ 600/6250] eta: 0:16:54 lr: 0.000120 grad: 0.0617 (0.0649) loss: 0.8491 (0.8428) time: 0.1799 data: 0.0651 max mem: 9390 +Train: [17] [ 700/6250] eta: 0:16:38 lr: 0.000120 grad: 0.0619 (0.0646) loss: 0.8402 (0.8428) time: 0.1728 data: 0.0800 max mem: 9390 +Train: [17] [ 800/6250] eta: 0:16:20 lr: 0.000120 grad: 0.0598 (0.0643) loss: 0.8455 (0.8429) time: 0.1757 data: 0.0752 max mem: 9390 +Train: [17] [ 900/6250] eta: 0:15:59 lr: 0.000120 grad: 0.0595 (0.0644) loss: 0.8430 (0.8432) time: 0.1907 data: 0.0988 max mem: 9390 +Train: [17] [1000/6250] eta: 0:15:36 lr: 0.000120 grad: 0.0609 (0.0642) loss: 0.8451 (0.8431) time: 0.1612 data: 0.0742 max mem: 9390 +Train: [17] [1100/6250] eta: 0:15:16 lr: 0.000120 grad: 0.0614 (0.0642) loss: 0.8395 (0.8429) time: 0.1725 data: 0.0829 max mem: 9390 +Train: [17] [1200/6250] eta: 0:14:52 lr: 0.000120 grad: 0.0627 (0.0641) loss: 0.8456 (0.8429) time: 0.1837 data: 0.1018 max mem: 9390 +Train: [17] [1300/6250] eta: 0:14:29 lr: 0.000120 grad: 0.0617 (0.0641) loss: 0.8450 (0.8429) time: 0.1502 data: 0.0555 max mem: 9390 +Train: [17] [1400/6250] eta: 0:14:08 lr: 0.000120 grad: 0.0603 (0.0640) loss: 0.8463 (0.8429) time: 0.1532 data: 0.0626 max mem: 9390 +Train: [17] [1500/6250] eta: 0:13:46 lr: 0.000120 grad: 0.0636 (0.0639) loss: 0.8387 (0.8429) time: 0.1636 data: 0.0761 max mem: 9390 +Train: [17] [1600/6250] eta: 0:13:26 lr: 0.000120 grad: 0.0577 (0.0638) loss: 0.8442 (0.8429) time: 0.1580 data: 0.0721 max mem: 9390 +Train: [17] [1700/6250] eta: 0:13:08 lr: 0.000120 grad: 0.0652 (0.0638) loss: 0.8379 (0.8428) time: 0.1697 data: 0.0759 max mem: 9390 +Train: [17] [1800/6250] eta: 0:12:48 lr: 0.000120 grad: 0.0606 (0.0638) loss: 0.8432 (0.8429) time: 0.1529 data: 0.0615 max mem: 9390 +Train: [17] [1900/6250] eta: 0:12:30 lr: 0.000120 grad: 0.0613 (0.0639) loss: 0.8430 (0.8429) time: 0.1901 data: 0.1044 max mem: 9390 +Train: [17] [2000/6250] eta: 0:12:12 lr: 0.000120 grad: 0.0621 (0.0640) loss: 0.8426 (0.8429) time: 0.1642 data: 0.0734 max mem: 9390 +Train: [17] [2100/6250] eta: 0:11:53 lr: 0.000120 grad: 0.0616 (0.0639) loss: 0.8481 (0.8428) time: 0.1713 data: 0.0875 max mem: 9390 +Train: [17] [2200/6250] eta: 0:11:34 lr: 0.000120 grad: 0.0634 (0.0639) loss: 0.8438 (0.8427) time: 0.1399 data: 0.0471 max mem: 9390 +Train: [17] [2300/6250] eta: 0:11:15 lr: 0.000120 grad: 0.0629 (0.0639) loss: 0.8430 (0.8427) time: 0.1614 data: 0.0768 max mem: 9390 +Train: [17] [2400/6250] eta: 0:10:58 lr: 0.000120 grad: 0.0629 (0.0638) loss: 0.8428 (0.8427) time: 0.1913 data: 0.1046 max mem: 9390 +Train: [17] [2500/6250] eta: 0:10:38 lr: 0.000120 grad: 0.0561 (0.0641) loss: 0.8477 (0.8428) time: 0.1586 data: 0.0731 max mem: 9390 +Train: [17] [2600/6250] eta: 0:10:20 lr: 0.000120 grad: 0.0645 (0.0641) loss: 0.8437 (0.8429) time: 0.1234 data: 0.0398 max mem: 9390 +Train: [17] [2700/6250] eta: 0:10:02 lr: 0.000120 grad: 0.0668 (0.0642) loss: 0.8361 (0.8429) time: 0.1768 data: 0.0913 max mem: 9390 +Train: [17] [2800/6250] eta: 0:09:45 lr: 0.000120 grad: 0.0607 (0.0642) loss: 0.8456 (0.8430) time: 0.2017 data: 0.1172 max mem: 9390 +Train: [17] [2900/6250] eta: 0:09:28 lr: 0.000120 grad: 0.0632 (0.0643) loss: 0.8395 (0.8430) time: 0.1761 data: 0.0894 max mem: 9390 +Train: [17] [3000/6250] eta: 0:09:11 lr: 0.000120 grad: 0.0630 (0.0643) loss: 0.8421 (0.8430) time: 0.1437 data: 0.0478 max mem: 9390 +Train: [17] [3100/6250] eta: 0:08:53 lr: 0.000120 grad: 0.0658 (0.0644) loss: 0.8362 (0.8430) time: 0.1668 data: 0.0774 max mem: 9390 +Train: [17] [3200/6250] eta: 0:08:36 lr: 0.000120 grad: 0.0660 (0.0645) loss: 0.8408 (0.8429) time: 0.1475 data: 0.0611 max mem: 9390 +Train: [17] [3300/6250] eta: 0:08:19 lr: 0.000120 grad: 0.0660 (0.0646) loss: 0.8346 (0.8427) time: 0.1848 data: 0.0957 max mem: 9390 +Train: [17] [3400/6250] eta: 0:08:02 lr: 0.000120 grad: 0.0642 (0.0647) loss: 0.8364 (0.8426) time: 0.1788 data: 0.1008 max mem: 9390 +Train: [17] [3500/6250] eta: 0:07:45 lr: 0.000120 grad: 0.0648 (0.0647) loss: 0.8367 (0.8424) time: 0.1685 data: 0.0787 max mem: 9390 +Train: [17] [3600/6250] eta: 0:07:28 lr: 0.000120 grad: 0.0653 (0.0648) loss: 0.8342 (0.8423) time: 0.1653 data: 0.0785 max mem: 9390 +Train: [17] [3700/6250] eta: 0:07:10 lr: 0.000120 grad: 0.0627 (0.0649) loss: 0.8395 (0.8422) time: 0.1488 data: 0.0583 max mem: 9390 +Train: [17] [3800/6250] eta: 0:06:53 lr: 0.000120 grad: 0.0614 (0.0649) loss: 0.8415 (0.8421) time: 0.1589 data: 0.0694 max mem: 9390 +Train: [17] [3900/6250] eta: 0:06:36 lr: 0.000120 grad: 0.0665 (0.0649) loss: 0.8384 (0.8420) time: 0.1655 data: 0.0761 max mem: 9390 +Train: [17] [4000/6250] eta: 0:06:19 lr: 0.000120 grad: 0.0627 (0.0649) loss: 0.8435 (0.8419) time: 0.1648 data: 0.0700 max mem: 9390 +Train: [17] [4100/6250] eta: 0:06:02 lr: 0.000120 grad: 0.0630 (0.0649) loss: 0.8398 (0.8419) time: 0.1844 data: 0.1011 max mem: 9390 +Train: [17] [4200/6250] eta: 0:05:45 lr: 0.000120 grad: 0.0625 (0.0649) loss: 0.8403 (0.8418) time: 0.1702 data: 0.0830 max mem: 9390 +Train: [17] [4300/6250] eta: 0:05:28 lr: 0.000120 grad: 0.0661 (0.0649) loss: 0.8341 (0.8418) time: 0.1652 data: 0.0685 max mem: 9390 +Train: [17] [4400/6250] eta: 0:05:11 lr: 0.000120 grad: 0.0614 (0.0649) loss: 0.8373 (0.8417) time: 0.1391 data: 0.0490 max mem: 9390 +Train: [17] [4500/6250] eta: 0:04:54 lr: 0.000120 grad: 0.0615 (0.0650) loss: 0.8426 (0.8417) time: 0.1602 data: 0.0728 max mem: 9390 +Train: [17] [4600/6250] eta: 0:04:37 lr: 0.000120 grad: 0.0618 (0.0650) loss: 0.8384 (0.8416) time: 0.1721 data: 0.0802 max mem: 9390 +Train: [17] [4700/6250] eta: 0:04:20 lr: 0.000120 grad: 0.0611 (0.0650) loss: 0.8383 (0.8415) time: 0.1621 data: 0.0807 max mem: 9390 +Train: [17] [4800/6250] eta: 0:04:03 lr: 0.000120 grad: 0.0700 (0.0651) loss: 0.8259 (0.8414) time: 0.1701 data: 0.0831 max mem: 9390 +Train: [17] [4900/6250] eta: 0:03:47 lr: 0.000119 grad: 0.0644 (0.0651) loss: 0.8393 (0.8414) time: 0.1650 data: 0.0836 max mem: 9390 +Train: [17] [5000/6250] eta: 0:03:30 lr: 0.000119 grad: 0.0611 (0.0650) loss: 0.8372 (0.8413) time: 0.1741 data: 0.0862 max mem: 9390 +Train: [17] [5100/6250] eta: 0:03:13 lr: 0.000119 grad: 0.0694 (0.0651) loss: 0.8397 (0.8412) time: 0.1390 data: 0.0477 max mem: 9390 +Train: [17] [5200/6250] eta: 0:02:56 lr: 0.000119 grad: 0.0612 (0.0651) loss: 0.8342 (0.8411) time: 0.1717 data: 0.0850 max mem: 9390 +Train: [17] [5300/6250] eta: 0:02:39 lr: 0.000119 grad: 0.0651 (0.0651) loss: 0.8352 (0.8411) time: 0.1802 data: 0.0975 max mem: 9390 +Train: [17] [5400/6250] eta: 0:02:22 lr: 0.000119 grad: 0.0657 (0.0651) loss: 0.8341 (0.8410) time: 0.1626 data: 0.0687 max mem: 9390 +Train: [17] [5500/6250] eta: 0:02:06 lr: 0.000119 grad: 0.0653 (0.0651) loss: 0.8406 (0.8410) time: 0.1730 data: 0.0859 max mem: 9390 +Train: [17] [5600/6250] eta: 0:01:49 lr: 0.000119 grad: 0.0640 (0.0651) loss: 0.8390 (0.8409) time: 0.1598 data: 0.0662 max mem: 9390 +Train: [17] [5700/6250] eta: 0:01:32 lr: 0.000119 grad: 0.0625 (0.0651) loss: 0.8375 (0.8408) time: 0.1511 data: 0.0570 max mem: 9390 +Train: [17] [5800/6250] eta: 0:01:15 lr: 0.000119 grad: 0.0618 (0.0651) loss: 0.8402 (0.8408) time: 0.1613 data: 0.0782 max mem: 9390 +Train: [17] [5900/6250] eta: 0:00:58 lr: 0.000119 grad: 0.0655 (0.0651) loss: 0.8371 (0.8407) time: 0.1587 data: 0.0634 max mem: 9390 +Train: [17] [6000/6250] eta: 0:00:41 lr: 0.000119 grad: 0.0684 (0.0652) loss: 0.8333 (0.8406) time: 0.1586 data: 0.0712 max mem: 9390 +Train: [17] [6100/6250] eta: 0:00:25 lr: 0.000119 grad: 0.0623 (0.0652) loss: 0.8386 (0.8406) time: 0.1460 data: 0.0657 max mem: 9390 +Train: [17] [6200/6250] eta: 0:00:08 lr: 0.000119 grad: 0.0635 (0.0652) loss: 0.8365 (0.8405) time: 0.1742 data: 0.0926 max mem: 9390 +Train: [17] [6249/6250] eta: 0:00:00 lr: 0.000119 grad: 0.0644 (0.0652) loss: 0.8402 (0.8404) time: 0.1743 data: 0.0908 max mem: 9390 +Train: [17] Total time: 0:17:34 (0.1688 s / it) +Averaged stats: lr: 0.000119 grad: 0.0644 (0.0652) loss: 0.8402 (0.8404) +Eval (hcp-train-subset): [17] [ 0/62] eta: 0:03:42 loss: 0.8578 (0.8578) time: 3.5910 data: 3.5089 max mem: 9390 +Eval (hcp-train-subset): [17] [61/62] eta: 0:00:00 loss: 0.8481 (0.8469) time: 0.1438 data: 0.1170 max mem: 9390 +Eval (hcp-train-subset): [17] Total time: 0:00:13 (0.2229 s / it) +Averaged stats (hcp-train-subset): loss: 0.8481 (0.8469) +Eval (hcp-val): [17] [ 0/62] eta: 0:03:19 loss: 0.8433 (0.8433) time: 3.2203 data: 3.1521 max mem: 9390 +Eval (hcp-val): [17] [61/62] eta: 0:00:00 loss: 0.8415 (0.8424) time: 0.1273 data: 0.1023 max mem: 9390 +Eval (hcp-val): [17] Total time: 0:00:13 (0.2158 s / it) +Averaged stats (hcp-val): loss: 0.8415 (0.8424) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +Train: [18] [ 0/6250] eta: 9:17:10 lr: 0.000119 grad: 0.0521 (0.0521) loss: 0.8702 (0.8702) time: 5.3488 data: 5.1876 max mem: 9390 +Train: [18] [ 100/6250] eta: 0:22:27 lr: 0.000119 grad: 0.0700 (0.0677) loss: 0.8469 (0.8527) time: 0.1597 data: 0.0678 max mem: 9390 +Train: [18] [ 200/6250] eta: 0:19:32 lr: 0.000119 grad: 0.0644 (0.0669) loss: 0.8446 (0.8484) time: 0.1738 data: 0.0882 max mem: 9390 +Train: [18] [ 300/6250] eta: 0:18:10 lr: 0.000119 grad: 0.0652 (0.0663) loss: 0.8436 (0.8465) time: 0.1479 data: 0.0661 max mem: 9390 +Train: [18] [ 400/6250] eta: 0:17:34 lr: 0.000119 grad: 0.0645 (0.0662) loss: 0.8338 (0.8448) time: 0.1653 data: 0.0701 max mem: 9390 +Train: [18] [ 500/6250] eta: 0:17:04 lr: 0.000119 grad: 0.0612 (0.0659) loss: 0.8412 (0.8441) time: 0.1871 data: 0.0928 max mem: 9390 +Train: [18] [ 600/6250] eta: 0:16:29 lr: 0.000119 grad: 0.0642 (0.0660) loss: 0.8320 (0.8432) time: 0.1345 data: 0.0411 max mem: 9390 +Train: [18] [ 700/6250] eta: 0:16:20 lr: 0.000119 grad: 0.0664 (0.0658) loss: 0.8438 (0.8427) time: 0.1800 data: 0.0749 max mem: 9390 +Train: [18] [ 800/6250] eta: 0:16:02 lr: 0.000119 grad: 0.0643 (0.0656) loss: 0.8414 (0.8422) time: 0.1754 data: 0.0804 max mem: 9390 +Train: [18] [ 900/6250] eta: 0:15:40 lr: 0.000119 grad: 0.0585 (0.0653) loss: 0.8405 (0.8418) time: 0.1696 data: 0.0688 max mem: 9390 +Train: [18] [1000/6250] eta: 0:15:18 lr: 0.000119 grad: 0.0620 (0.0652) loss: 0.8351 (0.8414) time: 0.1725 data: 0.0897 max mem: 9390 +Train: [18] [1100/6250] eta: 0:14:57 lr: 0.000119 grad: 0.0611 (0.0652) loss: 0.8414 (0.8411) time: 0.1719 data: 0.0784 max mem: 9390 +Train: [18] [1200/6250] eta: 0:14:40 lr: 0.000119 grad: 0.0695 (0.0654) loss: 0.8330 (0.8408) time: 0.1776 data: 0.0969 max mem: 9390 +Train: [18] [1300/6250] eta: 0:14:24 lr: 0.000119 grad: 0.0612 (0.0653) loss: 0.8357 (0.8405) time: 0.1517 data: 0.0682 max mem: 9390 +Train: [18] [1400/6250] eta: 0:14:03 lr: 0.000119 grad: 0.0633 (0.0653) loss: 0.8354 (0.8402) time: 0.2086 data: 0.1286 max mem: 9390 +Train: [18] [1500/6250] eta: 0:13:46 lr: 0.000119 grad: 0.0580 (0.0652) loss: 0.8372 (0.8401) time: 0.1476 data: 0.0579 max mem: 9390 +Train: [18] [1600/6250] eta: 0:13:24 lr: 0.000119 grad: 0.0602 (0.0652) loss: 0.8404 (0.8401) time: 0.1754 data: 0.0850 max mem: 9390 +Train: [18] [1700/6250] eta: 0:13:05 lr: 0.000119 grad: 0.0603 (0.0651) loss: 0.8356 (0.8400) time: 0.1476 data: 0.0627 max mem: 9390 +Train: [18] [1800/6250] eta: 0:12:46 lr: 0.000119 grad: 0.0617 (0.0652) loss: 0.8416 (0.8400) time: 0.1858 data: 0.1020 max mem: 9390 +Train: [18] [1900/6250] eta: 0:12:29 lr: 0.000119 grad: 0.0613 (0.0652) loss: 0.8400 (0.8399) time: 0.1847 data: 0.0979 max mem: 9390 +Train: [18] [2000/6250] eta: 0:12:11 lr: 0.000119 grad: 0.0643 (0.0651) loss: 0.8374 (0.8399) time: 0.2045 data: 0.1112 max mem: 9390 +Train: [18] [2100/6250] eta: 0:11:51 lr: 0.000119 grad: 0.0615 (0.0651) loss: 0.8427 (0.8400) time: 0.1503 data: 0.0451 max mem: 9390 +Train: [18] [2200/6250] eta: 0:11:32 lr: 0.000119 grad: 0.0594 (0.0650) loss: 0.8454 (0.8401) time: 0.1588 data: 0.0597 max mem: 9390 +Train: [18] [2300/6250] eta: 0:11:13 lr: 0.000119 grad: 0.0631 (0.0649) loss: 0.8409 (0.8401) time: 0.1461 data: 0.0473 max mem: 9390 +Train: [18] [2400/6250] eta: 0:10:54 lr: 0.000119 grad: 0.0669 (0.0649) loss: 0.8421 (0.8402) time: 0.1510 data: 0.0580 max mem: 9390 +Train: [18] [2500/6250] eta: 0:10:35 lr: 0.000119 grad: 0.0650 (0.0650) loss: 0.8398 (0.8401) time: 0.1696 data: 0.0730 max mem: 9390 +Train: [18] [2600/6250] eta: 0:10:17 lr: 0.000119 grad: 0.0734 (0.0650) loss: 0.8352 (0.8401) time: 0.1685 data: 0.0681 max mem: 9390 +Train: [18] [2700/6250] eta: 0:09:59 lr: 0.000119 grad: 0.0643 (0.0651) loss: 0.8421 (0.8401) time: 0.1627 data: 0.0768 max mem: 9390 +Train: [18] [2800/6250] eta: 0:09:43 lr: 0.000119 grad: 0.0650 (0.0650) loss: 0.8395 (0.8401) time: 0.1823 data: 0.0967 max mem: 9390 +Train: [18] [2900/6250] eta: 0:09:27 lr: 0.000119 grad: 0.0615 (0.0651) loss: 0.8483 (0.8402) time: 0.1780 data: 0.0821 max mem: 9390 +Train: [18] [3000/6250] eta: 0:09:10 lr: 0.000119 grad: 0.0634 (0.0650) loss: 0.8386 (0.8403) time: 0.1771 data: 0.0884 max mem: 9390 +Train: [18] [3100/6250] eta: 0:08:52 lr: 0.000119 grad: 0.0649 (0.0650) loss: 0.8416 (0.8403) time: 0.1730 data: 0.0770 max mem: 9390 +Train: [18] [3200/6250] eta: 0:08:34 lr: 0.000119 grad: 0.0683 (0.0650) loss: 0.8393 (0.8403) time: 0.1689 data: 0.0752 max mem: 9390 +Train: [18] [3300/6250] eta: 0:08:18 lr: 0.000119 grad: 0.0613 (0.0649) loss: 0.8379 (0.8403) time: 0.1580 data: 0.0700 max mem: 9390 +Train: [18] [3400/6250] eta: 0:08:01 lr: 0.000119 grad: 0.0592 (0.0648) loss: 0.8357 (0.8403) time: 0.1917 data: 0.0985 max mem: 9390 +Train: [18] [3500/6250] eta: 0:07:44 lr: 0.000119 grad: 0.0626 (0.0648) loss: 0.8400 (0.8402) time: 0.1590 data: 0.0654 max mem: 9390 +Train: [18] [3600/6250] eta: 0:07:27 lr: 0.000119 grad: 0.0612 (0.0648) loss: 0.8387 (0.8402) time: 0.1518 data: 0.0597 max mem: 9390 +Train: [18] [3700/6250] eta: 0:07:09 lr: 0.000119 grad: 0.0607 (0.0647) loss: 0.8370 (0.8402) time: 0.1377 data: 0.0527 max mem: 9390 +Train: [18] [3800/6250] eta: 0:06:52 lr: 0.000119 grad: 0.0599 (0.0646) loss: 0.8382 (0.8402) time: 0.1399 data: 0.0492 max mem: 9390 +Train: [18] [3900/6250] eta: 0:06:35 lr: 0.000119 grad: 0.0625 (0.0646) loss: 0.8416 (0.8402) time: 0.2017 data: 0.1166 max mem: 9390 +Train: [18] [4000/6250] eta: 0:06:18 lr: 0.000119 grad: 0.0634 (0.0645) loss: 0.8323 (0.8402) time: 0.1509 data: 0.0604 max mem: 9390 +Train: [18] [4100/6250] eta: 0:06:01 lr: 0.000119 grad: 0.0595 (0.0645) loss: 0.8429 (0.8402) time: 0.1693 data: 0.0749 max mem: 9390 +Train: [18] [4200/6250] eta: 0:05:44 lr: 0.000119 grad: 0.0591 (0.0644) loss: 0.8435 (0.8403) time: 0.1361 data: 0.0451 max mem: 9390 +Train: [18] [4300/6250] eta: 0:05:27 lr: 0.000119 grad: 0.0589 (0.0644) loss: 0.8435 (0.8403) time: 0.1393 data: 0.0534 max mem: 9390 +Train: [18] [4400/6250] eta: 0:05:10 lr: 0.000119 grad: 0.0638 (0.0644) loss: 0.8433 (0.8403) time: 0.1724 data: 0.0874 max mem: 9390 +Train: [18] [4500/6250] eta: 0:04:53 lr: 0.000119 grad: 0.0637 (0.0644) loss: 0.8401 (0.8404) time: 0.1621 data: 0.0773 max mem: 9390 +Train: [18] [4600/6250] eta: 0:04:36 lr: 0.000119 grad: 0.0620 (0.0644) loss: 0.8439 (0.8404) time: 0.1793 data: 0.0919 max mem: 9390 +Train: [18] [4700/6250] eta: 0:04:20 lr: 0.000119 grad: 0.0624 (0.0643) loss: 0.8407 (0.8404) time: 0.2200 data: 0.1354 max mem: 9390 +Train: [18] [4800/6250] eta: 0:04:03 lr: 0.000119 grad: 0.0665 (0.0644) loss: 0.8431 (0.8405) time: 0.1774 data: 0.0905 max mem: 9390 +Train: [18] [4900/6250] eta: 0:03:46 lr: 0.000119 grad: 0.0659 (0.0644) loss: 0.8424 (0.8405) time: 0.1686 data: 0.0783 max mem: 9390 +Train: [18] [5000/6250] eta: 0:03:29 lr: 0.000119 grad: 0.0654 (0.0644) loss: 0.8368 (0.8405) time: 0.1558 data: 0.0640 max mem: 9390 +Train: [18] [5100/6250] eta: 0:03:12 lr: 0.000119 grad: 0.0639 (0.0644) loss: 0.8390 (0.8404) time: 0.1559 data: 0.0640 max mem: 9390 +Train: [18] [5200/6250] eta: 0:02:55 lr: 0.000119 grad: 0.0645 (0.0644) loss: 0.8392 (0.8404) time: 0.1717 data: 0.0801 max mem: 9390 +Train: [18] [5300/6250] eta: 0:02:38 lr: 0.000119 grad: 0.0615 (0.0644) loss: 0.8425 (0.8404) time: 0.1408 data: 0.0475 max mem: 9390 +Train: [18] [5400/6250] eta: 0:02:22 lr: 0.000119 grad: 0.0623 (0.0644) loss: 0.8434 (0.8404) time: 0.1488 data: 0.0625 max mem: 9390 +Train: [18] [5500/6250] eta: 0:02:05 lr: 0.000119 grad: 0.0666 (0.0644) loss: 0.8441 (0.8404) time: 0.1591 data: 0.0732 max mem: 9390 +Train: [18] [5600/6250] eta: 0:01:48 lr: 0.000119 grad: 0.0628 (0.0644) loss: 0.8406 (0.8405) time: 0.1658 data: 0.0812 max mem: 9390 +Train: [18] [5700/6250] eta: 0:01:31 lr: 0.000119 grad: 0.0603 (0.0644) loss: 0.8386 (0.8405) time: 0.1908 data: 0.1069 max mem: 9390 +Train: [18] [5800/6250] eta: 0:01:15 lr: 0.000118 grad: 0.0627 (0.0644) loss: 0.8424 (0.8405) time: 0.1504 data: 0.0682 max mem: 9390 +Train: [18] [5900/6250] eta: 0:00:58 lr: 0.000118 grad: 0.0633 (0.0644) loss: 0.8355 (0.8404) time: 0.1690 data: 0.0850 max mem: 9390 +Train: [18] [6000/6250] eta: 0:00:41 lr: 0.000118 grad: 0.0619 (0.0644) loss: 0.8430 (0.8404) time: 0.1557 data: 0.0637 max mem: 9390 +Train: [18] [6100/6250] eta: 0:00:24 lr: 0.000118 grad: 0.0628 (0.0645) loss: 0.8383 (0.8404) time: 0.1478 data: 0.0681 max mem: 9390 +Train: [18] [6200/6250] eta: 0:00:08 lr: 0.000118 grad: 0.0604 (0.0644) loss: 0.8432 (0.8404) time: 0.1667 data: 0.0803 max mem: 9390 +Train: [18] [6249/6250] eta: 0:00:00 lr: 0.000118 grad: 0.0607 (0.0645) loss: 0.8393 (0.8404) time: 0.1799 data: 0.0897 max mem: 9390 +Train: [18] Total time: 0:17:28 (0.1678 s / it) +Averaged stats: lr: 0.000118 grad: 0.0607 (0.0645) loss: 0.8393 (0.8404) +Eval (hcp-train-subset): [18] [ 0/62] eta: 0:05:12 loss: 0.8593 (0.8593) time: 5.0424 data: 5.0134 max mem: 9390 +Eval (hcp-train-subset): [18] [61/62] eta: 0:00:00 loss: 0.8467 (0.8477) time: 0.1505 data: 0.1253 max mem: 9390 +Eval (hcp-train-subset): [18] Total time: 0:00:13 (0.2214 s / it) +Averaged stats (hcp-train-subset): loss: 0.8467 (0.8477) +Eval (hcp-val): [18] [ 0/62] eta: 0:03:42 loss: 0.8392 (0.8392) time: 3.5887 data: 3.5221 max mem: 9390 +Eval (hcp-val): [18] [61/62] eta: 0:00:00 loss: 0.8432 (0.8428) time: 0.1369 data: 0.1116 max mem: 9390 +Eval (hcp-val): [18] Total time: 0:00:13 (0.2200 s / it) +Averaged stats (hcp-val): loss: 0.8432 (0.8428) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +Train: [19] [ 0/6250] eta: 7:24:54 lr: 0.000118 grad: 0.0867 (0.0867) loss: 0.8610 (0.8610) time: 4.2712 data: 3.9344 max mem: 9390 +Train: [19] [ 100/6250] eta: 0:22:45 lr: 0.000118 grad: 0.0580 (0.0683) loss: 0.8498 (0.8520) time: 0.1610 data: 0.0705 max mem: 9390 +Train: [19] [ 200/6250] eta: 0:20:05 lr: 0.000118 grad: 0.0625 (0.0654) loss: 0.8434 (0.8495) time: 0.1494 data: 0.0686 max mem: 9390 +Train: [19] [ 300/6250] eta: 0:19:02 lr: 0.000118 grad: 0.0588 (0.0655) loss: 0.8452 (0.8466) time: 0.1978 data: 0.1083 max mem: 9390 +Train: [19] [ 400/6250] eta: 0:17:58 lr: 0.000118 grad: 0.0619 (0.0649) loss: 0.8409 (0.8447) time: 0.1609 data: 0.0713 max mem: 9390 +Train: [19] [ 500/6250] eta: 0:17:24 lr: 0.000118 grad: 0.0623 (0.0648) loss: 0.8366 (0.8433) time: 0.1639 data: 0.0692 max mem: 9390 +Train: [19] [ 600/6250] eta: 0:16:50 lr: 0.000118 grad: 0.0616 (0.0646) loss: 0.8400 (0.8423) time: 0.1749 data: 0.0788 max mem: 9390 +Train: [19] [ 700/6250] eta: 0:16:38 lr: 0.000118 grad: 0.0604 (0.0644) loss: 0.8395 (0.8420) time: 0.2076 data: 0.1110 max mem: 9390 +Train: [19] [ 800/6250] eta: 0:16:21 lr: 0.000118 grad: 0.0623 (0.0644) loss: 0.8372 (0.8418) time: 0.1586 data: 0.0386 max mem: 9390 +Train: [19] [ 900/6250] eta: 0:16:03 lr: 0.000118 grad: 0.0642 (0.0647) loss: 0.8390 (0.8413) time: 0.1792 data: 0.0892 max mem: 9390 +Train: [19] [1000/6250] eta: 0:15:45 lr: 0.000118 grad: 0.0621 (0.0647) loss: 0.8401 (0.8411) time: 0.1858 data: 0.0974 max mem: 9390 +Train: [19] [1100/6250] eta: 0:15:20 lr: 0.000118 grad: 0.0626 (0.0647) loss: 0.8349 (0.8407) time: 0.1492 data: 0.0548 max mem: 9390 +Train: [19] [1200/6250] eta: 0:14:56 lr: 0.000118 grad: 0.0606 (0.0648) loss: 0.8403 (0.8404) time: 0.1877 data: 0.1006 max mem: 9390 +Train: [19] [1300/6250] eta: 0:14:36 lr: 0.000118 grad: 0.0621 (0.0648) loss: 0.8353 (0.8401) time: 0.1697 data: 0.0811 max mem: 9390 +Train: [19] [1400/6250] eta: 0:14:12 lr: 0.000118 grad: 0.0616 (0.0648) loss: 0.8346 (0.8399) time: 0.1593 data: 0.0608 max mem: 9390 +Train: [19] [1500/6250] eta: 0:13:52 lr: 0.000118 grad: 0.0637 (0.0648) loss: 0.8358 (0.8395) time: 0.2024 data: 0.1157 max mem: 9390 +Train: [19] [1600/6250] eta: 0:13:30 lr: 0.000118 grad: 0.0714 (0.0651) loss: 0.8324 (0.8391) time: 0.1620 data: 0.0678 max mem: 9390 +Train: [19] [1700/6250] eta: 0:13:09 lr: 0.000118 grad: 0.0677 (0.0652) loss: 0.8347 (0.8387) time: 0.1513 data: 0.0576 max mem: 9390 +Train: [19] [1800/6250] eta: 0:12:49 lr: 0.000118 grad: 0.0707 (0.0655) loss: 0.8296 (0.8384) time: 0.1759 data: 0.0902 max mem: 9390 +Train: [19] [1900/6250] eta: 0:12:30 lr: 0.000118 grad: 0.0709 (0.0657) loss: 0.8336 (0.8382) time: 0.1780 data: 0.0800 max mem: 9390 +Train: [19] [2000/6250] eta: 0:12:10 lr: 0.000118 grad: 0.0679 (0.0660) loss: 0.8287 (0.8379) time: 0.1649 data: 0.0769 max mem: 9390 +Train: [19] [2100/6250] eta: 0:11:53 lr: 0.000118 grad: 0.0683 (0.0663) loss: 0.8342 (0.8377) time: 0.1712 data: 0.0742 max mem: 9390 +Train: [19] [2200/6250] eta: 0:11:34 lr: 0.000118 grad: 0.0651 (0.0665) loss: 0.8333 (0.8374) time: 0.1685 data: 0.0867 max mem: 9390 +Train: [19] [2300/6250] eta: 0:11:16 lr: 0.000118 grad: 0.0657 (0.0666) loss: 0.8374 (0.8374) time: 0.1388 data: 0.0491 max mem: 9390 +Train: [19] [2400/6250] eta: 0:10:58 lr: 0.000118 grad: 0.0627 (0.0667) loss: 0.8339 (0.8373) time: 0.1698 data: 0.0830 max mem: 9390 +Train: [19] [2500/6250] eta: 0:10:41 lr: 0.000118 grad: 0.0683 (0.0667) loss: 0.8366 (0.8372) time: 0.1777 data: 0.0983 max mem: 9390 +Train: [19] [2600/6250] eta: 0:10:24 lr: 0.000118 grad: 0.0651 (0.0668) loss: 0.8373 (0.8372) time: 0.1591 data: 0.0749 max mem: 9390 +Train: [19] [2700/6250] eta: 0:10:05 lr: 0.000118 grad: 0.0691 (0.0668) loss: 0.8305 (0.8371) time: 0.1663 data: 0.0777 max mem: 9390 +Train: [19] [2800/6250] eta: 0:09:47 lr: 0.000118 grad: 0.0652 (0.0669) loss: 0.8271 (0.8370) time: 0.1477 data: 0.0611 max mem: 9390 +Train: [19] [2900/6250] eta: 0:09:31 lr: 0.000118 grad: 0.0646 (0.0669) loss: 0.8373 (0.8369) time: 0.1751 data: 0.0873 max mem: 9390 +Train: [19] [3000/6250] eta: 0:09:13 lr: 0.000118 grad: 0.0637 (0.0669) loss: 0.8313 (0.8368) time: 0.1341 data: 0.0443 max mem: 9390 +Train: [19] [3100/6250] eta: 0:08:56 lr: 0.000118 grad: 0.0765 (0.0670) loss: 0.8372 (0.8368) time: 0.1753 data: 0.0887 max mem: 9390 +Train: [19] [3200/6250] eta: 0:08:39 lr: 0.000118 grad: 0.0637 (0.0671) loss: 0.8374 (0.8368) time: 0.1343 data: 0.0444 max mem: 9390 +Train: [19] [3300/6250] eta: 0:08:22 lr: 0.000118 grad: 0.0620 (0.0670) loss: 0.8371 (0.8368) time: 0.1500 data: 0.0611 max mem: 9390 +Train: [19] [3400/6250] eta: 0:08:05 lr: 0.000118 grad: 0.0668 (0.0670) loss: 0.8383 (0.8368) time: 0.2005 data: 0.1116 max mem: 9390 +Train: [19] [3500/6250] eta: 0:07:48 lr: 0.000118 grad: 0.0618 (0.0670) loss: 0.8363 (0.8368) time: 0.1838 data: 0.0922 max mem: 9390 +Train: [19] [3600/6250] eta: 0:07:30 lr: 0.000118 grad: 0.0616 (0.0669) loss: 0.8361 (0.8369) time: 0.1736 data: 0.0863 max mem: 9390 +Train: [19] [3700/6250] eta: 0:07:14 lr: 0.000118 grad: 0.0616 (0.0669) loss: 0.8408 (0.8369) time: 0.1807 data: 0.0953 max mem: 9390 +Train: [19] [3800/6250] eta: 0:06:56 lr: 0.000118 grad: 0.0682 (0.0668) loss: 0.8344 (0.8370) time: 0.1946 data: 0.1090 max mem: 9390 +Train: [19] [3900/6250] eta: 0:06:39 lr: 0.000118 grad: 0.0652 (0.0668) loss: 0.8376 (0.8370) time: 0.1542 data: 0.0664 max mem: 9390 +Train: [19] [4000/6250] eta: 0:06:22 lr: 0.000118 grad: 0.0669 (0.0668) loss: 0.8412 (0.8370) time: 0.1517 data: 0.0562 max mem: 9390 +Train: [19] [4100/6250] eta: 0:06:05 lr: 0.000118 grad: 0.0656 (0.0668) loss: 0.8381 (0.8371) time: 0.1514 data: 0.0640 max mem: 9390 +Train: [19] [4200/6250] eta: 0:05:48 lr: 0.000118 grad: 0.0630 (0.0668) loss: 0.8415 (0.8371) time: 0.1546 data: 0.0693 max mem: 9390 +Train: [19] [4300/6250] eta: 0:05:30 lr: 0.000118 grad: 0.0611 (0.0668) loss: 0.8401 (0.8372) time: 0.1669 data: 0.0848 max mem: 9390 +Train: [19] [4400/6250] eta: 0:05:13 lr: 0.000118 grad: 0.0619 (0.0667) loss: 0.8397 (0.8373) time: 0.1679 data: 0.0816 max mem: 9390 +Train: [19] [4500/6250] eta: 0:04:56 lr: 0.000118 grad: 0.0631 (0.0666) loss: 0.8418 (0.8373) time: 0.1654 data: 0.0797 max mem: 9390 +Train: [19] [4600/6250] eta: 0:04:39 lr: 0.000118 grad: 0.0639 (0.0666) loss: 0.8403 (0.8374) time: 0.1515 data: 0.0638 max mem: 9390 +Train: [19] [4700/6250] eta: 0:04:22 lr: 0.000118 grad: 0.0614 (0.0665) loss: 0.8371 (0.8374) time: 0.1776 data: 0.0966 max mem: 9390 +Train: [19] [4800/6250] eta: 0:04:05 lr: 0.000118 grad: 0.0647 (0.0665) loss: 0.8407 (0.8375) time: 0.1711 data: 0.0760 max mem: 9390 +Train: [19] [4900/6250] eta: 0:03:48 lr: 0.000118 grad: 0.0631 (0.0664) loss: 0.8382 (0.8375) time: 0.1748 data: 0.0958 max mem: 9390 +Train: [19] [5000/6250] eta: 0:03:31 lr: 0.000118 grad: 0.0630 (0.0664) loss: 0.8405 (0.8375) time: 0.1577 data: 0.0678 max mem: 9390 +Train: [19] [5100/6250] eta: 0:03:14 lr: 0.000118 grad: 0.0631 (0.0664) loss: 0.8369 (0.8374) time: 0.1327 data: 0.0461 max mem: 9390 +Train: [19] [5200/6250] eta: 0:02:57 lr: 0.000118 grad: 0.0671 (0.0665) loss: 0.8359 (0.8374) time: 0.1847 data: 0.0978 max mem: 9390 +Train: [19] [5300/6250] eta: 0:02:40 lr: 0.000118 grad: 0.0643 (0.0665) loss: 0.8344 (0.8374) time: 0.1634 data: 0.0711 max mem: 9390 +Train: [19] [5400/6250] eta: 0:02:23 lr: 0.000118 grad: 0.0601 (0.0665) loss: 0.8413 (0.8374) time: 0.1541 data: 0.0719 max mem: 9390 +Train: [19] [5500/6250] eta: 0:02:06 lr: 0.000118 grad: 0.0598 (0.0665) loss: 0.8403 (0.8374) time: 0.1637 data: 0.0795 max mem: 9390 +Train: [19] [5600/6250] eta: 0:01:49 lr: 0.000118 grad: 0.0639 (0.0665) loss: 0.8351 (0.8374) time: 0.1506 data: 0.0615 max mem: 9390 +Train: [19] [5700/6250] eta: 0:01:32 lr: 0.000118 grad: 0.0695 (0.0665) loss: 0.8350 (0.8374) time: 0.1760 data: 0.0918 max mem: 9390 +Train: [19] [5800/6250] eta: 0:01:15 lr: 0.000118 grad: 0.0667 (0.0665) loss: 0.8396 (0.8374) time: 0.1670 data: 0.0770 max mem: 9390 +Train: [19] [5900/6250] eta: 0:00:58 lr: 0.000118 grad: 0.0632 (0.0665) loss: 0.8417 (0.8375) time: 0.1437 data: 0.0458 max mem: 9390 +Train: [19] [6000/6250] eta: 0:00:42 lr: 0.000118 grad: 0.0663 (0.0665) loss: 0.8347 (0.8375) time: 0.1730 data: 0.0861 max mem: 9390 +Train: [19] [6100/6250] eta: 0:00:25 lr: 0.000117 grad: 0.0626 (0.0665) loss: 0.8430 (0.8375) time: 0.1685 data: 0.0698 max mem: 9390 +Train: [19] [6200/6250] eta: 0:00:08 lr: 0.000117 grad: 0.0635 (0.0665) loss: 0.8387 (0.8375) time: 0.1704 data: 0.0806 max mem: 9390 +Train: [19] [6249/6250] eta: 0:00:00 lr: 0.000117 grad: 0.0621 (0.0665) loss: 0.8425 (0.8376) time: 0.1974 data: 0.1067 max mem: 9390 +Train: [19] Total time: 0:17:39 (0.1694 s / it) +Averaged stats: lr: 0.000117 grad: 0.0621 (0.0665) loss: 0.8425 (0.8376) +Eval (hcp-train-subset): [19] [ 0/62] eta: 0:05:46 loss: 0.8568 (0.8568) time: 5.5878 data: 5.5423 max mem: 9390 +Eval (hcp-train-subset): [19] [61/62] eta: 0:00:00 loss: 0.8458 (0.8462) time: 0.1235 data: 0.0984 max mem: 9390 +Eval (hcp-train-subset): [19] Total time: 0:00:14 (0.2334 s / it) +Averaged stats (hcp-train-subset): loss: 0.8458 (0.8462) +Making plots (hcp-train-subset): example=32 +Eval (hcp-val): [19] [ 0/62] eta: 0:05:52 loss: 0.8366 (0.8366) time: 5.6894 data: 5.6589 max mem: 9390 +Eval (hcp-val): [19] [61/62] eta: 0:00:00 loss: 0.8420 (0.8418) time: 0.1437 data: 0.1185 max mem: 9390 +Eval (hcp-val): [19] Total time: 0:00:13 (0.2252 s / it) +Averaged stats (hcp-val): loss: 0.8420 (0.8418) +Making plots (hcp-val): example=37 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +Train: [20] [ 0/6250] eta: 8:51:39 lr: 0.000117 grad: 0.0635 (0.0635) loss: 0.8828 (0.8828) time: 5.1039 data: 4.9242 max mem: 9390 +Train: [20] [ 100/6250] eta: 0:23:00 lr: 0.000117 grad: 0.0670 (0.0677) loss: 0.8355 (0.8454) time: 0.1847 data: 0.0928 max mem: 9390 +Train: [20] [ 200/6250] eta: 0:20:40 lr: 0.000117 grad: 0.0663 (0.0691) loss: 0.8418 (0.8432) time: 0.2105 data: 0.0966 max mem: 9390 +Train: [20] [ 300/6250] eta: 0:19:40 lr: 0.000117 grad: 0.0638 (0.0698) loss: 0.8374 (0.8421) time: 0.2112 data: 0.1337 max mem: 9390 +Train: [20] [ 400/6250] eta: 0:18:38 lr: 0.000117 grad: 0.0661 (0.0701) loss: 0.8368 (0.8413) time: 0.1730 data: 0.0864 max mem: 9390 +Train: [20] [ 500/6250] eta: 0:17:55 lr: 0.000117 grad: 0.0668 (0.0696) loss: 0.8402 (0.8404) time: 0.1771 data: 0.0880 max mem: 9390 +Train: [20] [ 600/6250] eta: 0:17:29 lr: 0.000117 grad: 0.0637 (0.0694) loss: 0.8341 (0.8401) time: 0.1803 data: 0.0864 max mem: 9390 +Train: [20] [ 700/6250] eta: 0:17:03 lr: 0.000117 grad: 0.0641 (0.0691) loss: 0.8389 (0.8400) time: 0.2089 data: 0.1012 max mem: 9390 +Train: [20] [ 800/6250] eta: 0:16:37 lr: 0.000117 grad: 0.0621 (0.0687) loss: 0.8372 (0.8398) time: 0.1842 data: 0.0834 max mem: 9390 +Train: [20] [ 900/6250] eta: 0:16:12 lr: 0.000117 grad: 0.0624 (0.0682) loss: 0.8433 (0.8401) time: 0.2011 data: 0.0957 max mem: 9390 +Train: [20] [1000/6250] eta: 0:15:41 lr: 0.000117 grad: 0.0636 (0.0679) loss: 0.8346 (0.8399) time: 0.1617 data: 0.0621 max mem: 9390 +Train: [20] [1100/6250] eta: 0:15:14 lr: 0.000117 grad: 0.0640 (0.0678) loss: 0.8371 (0.8397) time: 0.1609 data: 0.0524 max mem: 9390 +Train: [20] [1200/6250] eta: 0:14:48 lr: 0.000117 grad: 0.0641 (0.0677) loss: 0.8311 (0.8393) time: 0.1484 data: 0.0512 max mem: 9390 +Train: [20] [1300/6250] eta: 0:14:24 lr: 0.000117 grad: 0.0623 (0.0675) loss: 0.8338 (0.8390) time: 0.1506 data: 0.0594 max mem: 9390 +Train: [20] [1400/6250] eta: 0:14:00 lr: 0.000117 grad: 0.0622 (0.0674) loss: 0.8409 (0.8388) time: 0.1570 data: 0.0698 max mem: 9390 +Train: [20] [1500/6250] eta: 0:13:41 lr: 0.000117 grad: 0.0607 (0.0672) loss: 0.8358 (0.8387) time: 0.1482 data: 0.0538 max mem: 9390 +Train: [20] [1600/6250] eta: 0:13:21 lr: 0.000117 grad: 0.0630 (0.0670) loss: 0.8360 (0.8387) time: 0.1320 data: 0.0417 max mem: 9390 +Train: [20] [1700/6250] eta: 0:13:04 lr: 0.000117 grad: 0.0615 (0.0668) loss: 0.8380 (0.8387) time: 0.1883 data: 0.1037 max mem: 9390 +Train: [20] [1800/6250] eta: 0:12:45 lr: 0.000117 grad: 0.0615 (0.0667) loss: 0.8362 (0.8387) time: 0.1459 data: 0.0524 max mem: 9390 +Train: [20] [1900/6250] eta: 0:12:27 lr: 0.000117 grad: 0.0594 (0.0664) loss: 0.8383 (0.8388) time: 0.1910 data: 0.1068 max mem: 9390 +Train: [20] [2000/6250] eta: 0:12:09 lr: 0.000117 grad: 0.0596 (0.0664) loss: 0.8383 (0.8388) time: 0.1499 data: 0.0544 max mem: 9390 +Train: [20] [2100/6250] eta: 0:11:50 lr: 0.000117 grad: 0.0637 (0.0663) loss: 0.8396 (0.8388) time: 0.1628 data: 0.0744 max mem: 9390 +Train: [20] [2200/6250] eta: 0:11:32 lr: 0.000117 grad: 0.0643 (0.0662) loss: 0.8326 (0.8387) time: 0.1770 data: 0.0798 max mem: 9390 +Train: [20] [2300/6250] eta: 0:11:15 lr: 0.000117 grad: 0.0623 (0.0661) loss: 0.8363 (0.8386) time: 0.1729 data: 0.0852 max mem: 9390 +Train: [20] [2400/6250] eta: 0:10:57 lr: 0.000117 grad: 0.0611 (0.0660) loss: 0.8380 (0.8386) time: 0.1476 data: 0.0565 max mem: 9390 +Train: [20] [2500/6250] eta: 0:10:39 lr: 0.000117 grad: 0.0638 (0.0659) loss: 0.8349 (0.8384) time: 0.1505 data: 0.0558 max mem: 9390 +Train: [20] [2600/6250] eta: 0:10:22 lr: 0.000117 grad: 0.0651 (0.0659) loss: 0.8344 (0.8383) time: 0.1770 data: 0.0945 max mem: 9390 +Train: [20] [2700/6250] eta: 0:10:04 lr: 0.000117 grad: 0.0655 (0.0660) loss: 0.8355 (0.8383) time: 0.1782 data: 0.0968 max mem: 9390 +Train: [20] [2800/6250] eta: 0:09:46 lr: 0.000117 grad: 0.0636 (0.0659) loss: 0.8357 (0.8383) time: 0.1586 data: 0.0742 max mem: 9390 +Train: [20] [2900/6250] eta: 0:09:28 lr: 0.000117 grad: 0.0640 (0.0659) loss: 0.8359 (0.8383) time: 0.1631 data: 0.0647 max mem: 9390 +Train: [20] [3000/6250] eta: 0:09:11 lr: 0.000117 grad: 0.0659 (0.0658) loss: 0.8348 (0.8383) time: 0.1523 data: 0.0662 max mem: 9390 +Train: [20] [3100/6250] eta: 0:08:53 lr: 0.000117 grad: 0.0624 (0.0658) loss: 0.8388 (0.8383) time: 0.1518 data: 0.0610 max mem: 9390 +Train: [20] [3200/6250] eta: 0:08:36 lr: 0.000117 grad: 0.0617 (0.0657) loss: 0.8411 (0.8383) time: 0.1933 data: 0.1151 max mem: 9390 +Train: [20] [3300/6250] eta: 0:08:19 lr: 0.000117 grad: 0.0624 (0.0656) loss: 0.8400 (0.8383) time: 0.1790 data: 0.0918 max mem: 9390 +Train: [20] [3400/6250] eta: 0:08:02 lr: 0.000117 grad: 0.0620 (0.0657) loss: 0.8370 (0.8383) time: 0.1497 data: 0.0602 max mem: 9390 +Train: [20] [3500/6250] eta: 0:07:45 lr: 0.000117 grad: 0.0623 (0.0656) loss: 0.8365 (0.8383) time: 0.1655 data: 0.0817 max mem: 9390 +Train: [20] [3600/6250] eta: 0:07:28 lr: 0.000117 grad: 0.0649 (0.0656) loss: 0.8306 (0.8382) time: 0.1761 data: 0.0927 max mem: 9390 +Train: [20] [3700/6250] eta: 0:07:10 lr: 0.000117 grad: 0.0639 (0.0657) loss: 0.8406 (0.8381) time: 0.1623 data: 0.0785 max mem: 9390 +Train: [20] [3800/6250] eta: 0:06:53 lr: 0.000117 grad: 0.0689 (0.0657) loss: 0.8339 (0.8381) time: 0.1561 data: 0.0642 max mem: 9390 +Train: [20] [3900/6250] eta: 0:06:36 lr: 0.000117 grad: 0.0782 (0.0658) loss: 0.8333 (0.8381) time: 0.1726 data: 0.0822 max mem: 9390 +Train: [20] [4000/6250] eta: 0:06:19 lr: 0.000117 grad: 0.0614 (0.0658) loss: 0.8388 (0.8381) time: 0.1713 data: 0.0806 max mem: 9390 +Train: [20] [4100/6250] eta: 0:06:02 lr: 0.000117 grad: 0.0656 (0.0658) loss: 0.8316 (0.8381) time: 0.1649 data: 0.0780 max mem: 9390 +Train: [20] [4200/6250] eta: 0:05:45 lr: 0.000117 grad: 0.0670 (0.0658) loss: 0.8346 (0.8380) time: 0.1761 data: 0.0928 max mem: 9390 +Train: [20] [4300/6250] eta: 0:05:28 lr: 0.000117 grad: 0.0655 (0.0659) loss: 0.8395 (0.8380) time: 0.1499 data: 0.0641 max mem: 9390 +Train: [20] [4400/6250] eta: 0:05:11 lr: 0.000117 grad: 0.0660 (0.0659) loss: 0.8375 (0.8379) time: 0.1605 data: 0.0692 max mem: 9390 +Train: [20] [4500/6250] eta: 0:04:54 lr: 0.000117 grad: 0.0625 (0.0660) loss: 0.8401 (0.8379) time: 0.1641 data: 0.0774 max mem: 9390 +Train: [20] [4600/6250] eta: 0:04:38 lr: 0.000117 grad: 0.0636 (0.0660) loss: 0.8364 (0.8379) time: 0.1788 data: 0.0900 max mem: 9390 +Train: [20] [4700/6250] eta: 0:04:21 lr: 0.000117 grad: 0.0635 (0.0661) loss: 0.8411 (0.8379) time: 0.1671 data: 0.0826 max mem: 9390 +Train: [20] [4800/6250] eta: 0:04:04 lr: 0.000117 grad: 0.0659 (0.0661) loss: 0.8377 (0.8378) time: 0.1767 data: 0.0926 max mem: 9390 +Train: [20] [4900/6250] eta: 0:03:47 lr: 0.000117 grad: 0.0650 (0.0661) loss: 0.8356 (0.8378) time: 0.1611 data: 0.0733 max mem: 9390 +Train: [20] [5000/6250] eta: 0:03:30 lr: 0.000117 grad: 0.0635 (0.0662) loss: 0.8341 (0.8377) time: 0.1615 data: 0.0841 max mem: 9390 +Train: [20] [5100/6250] eta: 0:03:13 lr: 0.000117 grad: 0.0631 (0.0662) loss: 0.8442 (0.8377) time: 0.1706 data: 0.0836 max mem: 9390 +Train: [20] [5200/6250] eta: 0:02:56 lr: 0.000117 grad: 0.0661 (0.0662) loss: 0.8338 (0.8377) time: 0.1551 data: 0.0610 max mem: 9390 +Train: [20] [5300/6250] eta: 0:02:40 lr: 0.000117 grad: 0.0637 (0.0662) loss: 0.8379 (0.8377) time: 0.1715 data: 0.0821 max mem: 9390 +Train: [20] [5400/6250] eta: 0:02:23 lr: 0.000117 grad: 0.0626 (0.0663) loss: 0.8412 (0.8377) time: 0.1723 data: 0.0880 max mem: 9390 +Train: [20] [5500/6250] eta: 0:02:06 lr: 0.000117 grad: 0.0670 (0.0663) loss: 0.8373 (0.8377) time: 0.1649 data: 0.0774 max mem: 9390 +Train: [20] [5600/6250] eta: 0:01:49 lr: 0.000117 grad: 0.0669 (0.0663) loss: 0.8409 (0.8377) time: 0.1616 data: 0.0787 max mem: 9390 +Train: [20] [5700/6250] eta: 0:01:32 lr: 0.000117 grad: 0.0672 (0.0663) loss: 0.8345 (0.8377) time: 0.1750 data: 0.0802 max mem: 9390 +Train: [20] [5800/6250] eta: 0:01:15 lr: 0.000117 grad: 0.0643 (0.0664) loss: 0.8364 (0.8376) time: 0.1746 data: 0.0821 max mem: 9390 +Train: [20] [5900/6250] eta: 0:00:58 lr: 0.000117 grad: 0.0639 (0.0664) loss: 0.8345 (0.8376) time: 0.1586 data: 0.0764 max mem: 9390 +Train: [20] [6000/6250] eta: 0:00:42 lr: 0.000116 grad: 0.0628 (0.0665) loss: 0.8361 (0.8376) time: 0.1641 data: 0.0781 max mem: 9390 +Train: [20] [6100/6250] eta: 0:00:25 lr: 0.000116 grad: 0.0682 (0.0665) loss: 0.8334 (0.8375) time: 0.1801 data: 0.0894 max mem: 9390 +Train: [20] [6200/6250] eta: 0:00:08 lr: 0.000116 grad: 0.0634 (0.0665) loss: 0.8394 (0.8375) time: 0.1694 data: 0.0869 max mem: 9390 +Train: [20] [6249/6250] eta: 0:00:00 lr: 0.000116 grad: 0.0633 (0.0665) loss: 0.8333 (0.8374) time: 0.1477 data: 0.0604 max mem: 9390 +Train: [20] Total time: 0:17:39 (0.1695 s / it) +Averaged stats: lr: 0.000116 grad: 0.0633 (0.0665) loss: 0.8333 (0.8374) +Eval (hcp-train-subset): [20] [ 0/62] eta: 0:06:24 loss: 0.8575 (0.8575) time: 6.2069 data: 6.1767 max mem: 9390 +Eval (hcp-train-subset): [20] [61/62] eta: 0:00:00 loss: 0.8467 (0.8460) time: 0.1145 data: 0.0886 max mem: 9390 +Eval (hcp-train-subset): [20] Total time: 0:00:14 (0.2353 s / it) +Averaged stats (hcp-train-subset): loss: 0.8467 (0.8460) +Eval (hcp-val): [20] [ 0/62] eta: 0:06:02 loss: 0.8372 (0.8372) time: 5.8544 data: 5.8247 max mem: 9390 +Eval (hcp-val): [20] [61/62] eta: 0:00:00 loss: 0.8405 (0.8409) time: 0.1207 data: 0.0954 max mem: 9390 +Eval (hcp-val): [20] Total time: 0:00:13 (0.2228 s / it) +Averaged stats (hcp-val): loss: 0.8405 (0.8409) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +Train: [21] [ 0/6250] eta: 11:14:31 lr: 0.000116 grad: 0.1174 (0.1174) loss: 0.8808 (0.8808) time: 6.4755 data: 6.3636 max mem: 9390 +Train: [21] [ 100/6250] eta: 0:23:02 lr: 0.000116 grad: 0.0681 (0.0741) loss: 0.8453 (0.8492) time: 0.1677 data: 0.0755 max mem: 9390 +Train: [21] [ 200/6250] eta: 0:20:21 lr: 0.000116 grad: 0.0731 (0.0741) loss: 0.8335 (0.8437) time: 0.1751 data: 0.0943 max mem: 9390 +Train: [21] [ 300/6250] eta: 0:19:01 lr: 0.000116 grad: 0.0657 (0.0718) loss: 0.8430 (0.8424) time: 0.1838 data: 0.0911 max mem: 9390 +Train: [21] [ 400/6250] eta: 0:18:04 lr: 0.000116 grad: 0.0632 (0.0702) loss: 0.8349 (0.8415) time: 0.1584 data: 0.0779 max mem: 9390 +Train: [21] [ 500/6250] eta: 0:17:25 lr: 0.000116 grad: 0.0655 (0.0693) loss: 0.8385 (0.8412) time: 0.1526 data: 0.0574 max mem: 9390 +Train: [21] [ 600/6250] eta: 0:16:55 lr: 0.000116 grad: 0.0622 (0.0687) loss: 0.8396 (0.8409) time: 0.1465 data: 0.0459 max mem: 9390 +Train: [21] [ 700/6250] eta: 0:16:20 lr: 0.000116 grad: 0.0611 (0.0682) loss: 0.8415 (0.8402) time: 0.1521 data: 0.0547 max mem: 9390 +Train: [21] [ 800/6250] eta: 0:15:59 lr: 0.000116 grad: 0.0623 (0.0677) loss: 0.8378 (0.8402) time: 0.1794 data: 0.0956 max mem: 9390 +Train: [21] [ 900/6250] eta: 0:15:44 lr: 0.000116 grad: 0.0649 (0.0674) loss: 0.8439 (0.8401) time: 0.2039 data: 0.1147 max mem: 9390 +Train: [21] [1000/6250] eta: 0:15:23 lr: 0.000116 grad: 0.0619 (0.0672) loss: 0.8408 (0.8399) time: 0.1638 data: 0.0716 max mem: 9390 +Train: [21] [1100/6250] eta: 0:15:03 lr: 0.000116 grad: 0.0629 (0.0670) loss: 0.8419 (0.8400) time: 0.1824 data: 0.1008 max mem: 9390 +Train: [21] [1200/6250] eta: 0:14:42 lr: 0.000116 grad: 0.0634 (0.0668) loss: 0.8383 (0.8399) time: 0.1784 data: 0.0904 max mem: 9390 +Train: [21] [1300/6250] eta: 0:14:21 lr: 0.000116 grad: 0.0631 (0.0667) loss: 0.8422 (0.8400) time: 0.1669 data: 0.0758 max mem: 9390 +Train: [21] [1400/6250] eta: 0:13:59 lr: 0.000116 grad: 0.0654 (0.0667) loss: 0.8343 (0.8398) time: 0.1623 data: 0.0756 max mem: 9390 +Train: [21] [1500/6250] eta: 0:13:39 lr: 0.000116 grad: 0.0643 (0.0666) loss: 0.8379 (0.8397) time: 0.1784 data: 0.0972 max mem: 9390 +Train: [21] [1600/6250] eta: 0:13:20 lr: 0.000116 grad: 0.0615 (0.0664) loss: 0.8312 (0.8395) time: 0.1609 data: 0.0696 max mem: 9390 +Train: [21] [1700/6250] eta: 0:13:01 lr: 0.000116 grad: 0.0627 (0.0664) loss: 0.8352 (0.8392) time: 0.1599 data: 0.0750 max mem: 9390 +Train: [21] [1800/6250] eta: 0:12:42 lr: 0.000116 grad: 0.0625 (0.0664) loss: 0.8385 (0.8390) time: 0.1572 data: 0.0724 max mem: 9390 +Train: [21] [1900/6250] eta: 0:12:24 lr: 0.000116 grad: 0.0648 (0.0664) loss: 0.8361 (0.8388) time: 0.1764 data: 0.0915 max mem: 9390 +Train: [21] [2000/6250] eta: 0:12:03 lr: 0.000116 grad: 0.0644 (0.0664) loss: 0.8343 (0.8386) time: 0.1516 data: 0.0689 max mem: 9390 +Train: [21] [2100/6250] eta: 0:11:45 lr: 0.000116 grad: 0.0686 (0.0664) loss: 0.8382 (0.8384) time: 0.1538 data: 0.0657 max mem: 9390 +Train: [21] [2200/6250] eta: 0:11:28 lr: 0.000116 grad: 0.0653 (0.0664) loss: 0.8348 (0.8382) time: 0.1810 data: 0.0986 max mem: 9390 +Train: [21] [2300/6250] eta: 0:11:11 lr: 0.000116 grad: 0.0682 (0.0665) loss: 0.8365 (0.8380) time: 0.1800 data: 0.0948 max mem: 9390 +Train: [21] [2400/6250] eta: 0:10:54 lr: 0.000116 grad: 0.0646 (0.0665) loss: 0.8391 (0.8380) time: 0.1630 data: 0.0811 max mem: 9390 +Train: [21] [2500/6250] eta: 0:10:36 lr: 0.000116 grad: 0.0653 (0.0668) loss: 0.8316 (0.8379) time: 0.1385 data: 0.0454 max mem: 9390 +Train: [21] [2600/6250] eta: 0:10:19 lr: 0.000116 grad: 0.0662 (0.0669) loss: 0.8356 (0.8378) time: 0.1479 data: 0.0616 max mem: 9390 +Train: [21] [2700/6250] eta: 0:10:01 lr: 0.000116 grad: 0.0656 (0.0669) loss: 0.8338 (0.8376) time: 0.1693 data: 0.0878 max mem: 9390 +Train: [21] [2800/6250] eta: 0:09:44 lr: 0.000116 grad: 0.0632 (0.0669) loss: 0.8343 (0.8375) time: 0.1827 data: 0.0940 max mem: 9390 +Train: [21] [2900/6250] eta: 0:09:27 lr: 0.000116 grad: 0.0667 (0.0669) loss: 0.8362 (0.8374) time: 0.1887 data: 0.1089 max mem: 9390 +Train: [21] [3000/6250] eta: 0:09:09 lr: 0.000116 grad: 0.0622 (0.0669) loss: 0.8386 (0.8372) time: 0.1709 data: 0.0793 max mem: 9390 +Train: [21] [3100/6250] eta: 0:08:53 lr: 0.000116 grad: 0.0642 (0.0669) loss: 0.8371 (0.8372) time: 0.1872 data: 0.1004 max mem: 9390 +Train: [21] [3200/6250] eta: 0:08:35 lr: 0.000116 grad: 0.0663 (0.0669) loss: 0.8345 (0.8371) time: 0.1610 data: 0.0667 max mem: 9390 +Train: [21] [3300/6250] eta: 0:08:18 lr: 0.000116 grad: 0.0632 (0.0669) loss: 0.8347 (0.8370) time: 0.1698 data: 0.0807 max mem: 9390 +Train: [21] [3400/6250] eta: 0:08:01 lr: 0.000116 grad: 0.0631 (0.0669) loss: 0.8374 (0.8370) time: 0.1517 data: 0.0658 max mem: 9390 +Train: [21] [3500/6250] eta: 0:07:44 lr: 0.000116 grad: 0.0631 (0.0669) loss: 0.8362 (0.8369) time: 0.1456 data: 0.0615 max mem: 9390 +Train: [21] [3600/6250] eta: 0:07:27 lr: 0.000116 grad: 0.0676 (0.0669) loss: 0.8317 (0.8369) time: 0.1523 data: 0.0614 max mem: 9390 +Train: [21] [3700/6250] eta: 0:07:10 lr: 0.000116 grad: 0.0648 (0.0669) loss: 0.8350 (0.8369) time: 0.1755 data: 0.0957 max mem: 9390 +Train: [21] [3800/6250] eta: 0:06:54 lr: 0.000116 grad: 0.0671 (0.0669) loss: 0.8386 (0.8369) time: 0.1591 data: 0.0696 max mem: 9390 +Train: [21] [3900/6250] eta: 0:06:37 lr: 0.000116 grad: 0.0660 (0.0669) loss: 0.8373 (0.8370) time: 0.1761 data: 0.0932 max mem: 9390 +Train: [21] [4000/6250] eta: 0:06:20 lr: 0.000116 grad: 0.0638 (0.0668) loss: 0.8339 (0.8369) time: 0.1612 data: 0.0750 max mem: 9390 +Train: [21] [4100/6250] eta: 0:06:03 lr: 0.000116 grad: 0.0650 (0.0668) loss: 0.8330 (0.8369) time: 0.1594 data: 0.0750 max mem: 9390 +Train: [21] [4200/6250] eta: 0:05:46 lr: 0.000116 grad: 0.0665 (0.0667) loss: 0.8389 (0.8369) time: 0.1852 data: 0.1028 max mem: 9390 +Train: [21] [4300/6250] eta: 0:05:29 lr: 0.000116 grad: 0.0677 (0.0667) loss: 0.8357 (0.8369) time: 0.1585 data: 0.0766 max mem: 9390 +Train: [21] [4400/6250] eta: 0:05:12 lr: 0.000116 grad: 0.0596 (0.0666) loss: 0.8390 (0.8369) time: 0.1590 data: 0.0669 max mem: 9390 +Train: [21] [4500/6250] eta: 0:04:55 lr: 0.000116 grad: 0.0639 (0.0666) loss: 0.8343 (0.8369) time: 0.1616 data: 0.0710 max mem: 9390 +Train: [21] [4600/6250] eta: 0:04:38 lr: 0.000116 grad: 0.0632 (0.0666) loss: 0.8356 (0.8369) time: 0.1489 data: 0.0681 max mem: 9390 +Train: [21] [4700/6250] eta: 0:04:21 lr: 0.000116 grad: 0.0636 (0.0665) loss: 0.8345 (0.8369) time: 0.1666 data: 0.0826 max mem: 9390 +Train: [21] [4800/6250] eta: 0:04:04 lr: 0.000116 grad: 0.0638 (0.0664) loss: 0.8332 (0.8369) time: 0.1735 data: 0.0869 max mem: 9390 +Train: [21] [4900/6250] eta: 0:03:47 lr: 0.000116 grad: 0.0633 (0.0664) loss: 0.8328 (0.8369) time: 0.1616 data: 0.0733 max mem: 9390 +Train: [21] [5000/6250] eta: 0:03:30 lr: 0.000116 grad: 0.0589 (0.0663) loss: 0.8417 (0.8369) time: 0.1795 data: 0.0887 max mem: 9390 +Train: [21] [5100/6250] eta: 0:03:13 lr: 0.000116 grad: 0.0626 (0.0663) loss: 0.8354 (0.8369) time: 0.1695 data: 0.0869 max mem: 9390 +Train: [21] [5200/6250] eta: 0:02:56 lr: 0.000116 grad: 0.0615 (0.0663) loss: 0.8322 (0.8369) time: 0.1470 data: 0.0686 max mem: 9390 +Train: [21] [5300/6250] eta: 0:02:40 lr: 0.000116 grad: 0.0667 (0.0663) loss: 0.8372 (0.8369) time: 0.1613 data: 0.0784 max mem: 9390 +Train: [21] [5400/6250] eta: 0:02:23 lr: 0.000116 grad: 0.0636 (0.0663) loss: 0.8374 (0.8369) time: 0.1985 data: 0.1159 max mem: 9390 +Train: [21] [5500/6250] eta: 0:02:06 lr: 0.000116 grad: 0.0653 (0.0663) loss: 0.8324 (0.8368) time: 0.1838 data: 0.1012 max mem: 9390 +Train: [21] [5600/6250] eta: 0:01:49 lr: 0.000115 grad: 0.0654 (0.0663) loss: 0.8334 (0.8368) time: 0.2300 data: 0.1520 max mem: 9390 +Train: [21] [5700/6250] eta: 0:01:33 lr: 0.000115 grad: 0.0652 (0.0663) loss: 0.8335 (0.8368) time: 0.1738 data: 0.0949 max mem: 9390 +Train: [21] [5800/6250] eta: 0:01:16 lr: 0.000115 grad: 0.0682 (0.0664) loss: 0.8371 (0.8367) time: 0.1926 data: 0.1026 max mem: 9390 +Train: [21] [5900/6250] eta: 0:00:59 lr: 0.000115 grad: 0.0688 (0.0664) loss: 0.8330 (0.8367) time: 0.1597 data: 0.0682 max mem: 9390 +Train: [21] [6000/6250] eta: 0:00:42 lr: 0.000115 grad: 0.0675 (0.0664) loss: 0.8312 (0.8367) time: 0.1670 data: 0.0772 max mem: 9390 +Train: [21] [6100/6250] eta: 0:00:25 lr: 0.000115 grad: 0.0691 (0.0665) loss: 0.8357 (0.8366) time: 0.1851 data: 0.0943 max mem: 9390 +Train: [21] [6200/6250] eta: 0:00:08 lr: 0.000115 grad: 0.0660 (0.0665) loss: 0.8293 (0.8366) time: 0.1665 data: 0.0700 max mem: 9390 +Train: [21] [6249/6250] eta: 0:00:00 lr: 0.000115 grad: 0.0675 (0.0665) loss: 0.8289 (0.8366) time: 0.1612 data: 0.0752 max mem: 9390 +Train: [21] Total time: 0:17:42 (0.1700 s / it) +Averaged stats: lr: 0.000115 grad: 0.0675 (0.0665) loss: 0.8289 (0.8366) +Eval (hcp-train-subset): [21] [ 0/62] eta: 0:06:13 loss: 0.8535 (0.8535) time: 6.0267 data: 5.9965 max mem: 9390 +Eval (hcp-train-subset): [21] [61/62] eta: 0:00:00 loss: 0.8462 (0.8449) time: 0.1130 data: 0.0854 max mem: 9390 +Eval (hcp-train-subset): [21] Total time: 0:00:14 (0.2299 s / it) +Averaged stats (hcp-train-subset): loss: 0.8462 (0.8449) +Eval (hcp-val): [21] [ 0/62] eta: 0:05:37 loss: 0.8387 (0.8387) time: 5.4379 data: 5.4081 max mem: 9390 +Eval (hcp-val): [21] [61/62] eta: 0:00:00 loss: 0.8405 (0.8414) time: 0.1257 data: 0.1003 max mem: 9390 +Eval (hcp-val): [21] Total time: 0:00:13 (0.2217 s / it) +Averaged stats (hcp-val): loss: 0.8405 (0.8414) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +Train: [22] [ 0/6250] eta: 10:25:32 lr: 0.000115 grad: 0.0998 (0.0998) loss: 0.8499 (0.8499) time: 6.0053 data: 5.8789 max mem: 9390 +Train: [22] [ 100/6250] eta: 0:22:20 lr: 0.000115 grad: 0.0703 (0.0785) loss: 0.8342 (0.8436) time: 0.1538 data: 0.0588 max mem: 9390 +Train: [22] [ 200/6250] eta: 0:19:43 lr: 0.000115 grad: 0.0699 (0.0771) loss: 0.8376 (0.8410) time: 0.1757 data: 0.0747 max mem: 9390 +Train: [22] [ 300/6250] eta: 0:18:52 lr: 0.000115 grad: 0.0616 (0.0735) loss: 0.8427 (0.8400) time: 0.2050 data: 0.1098 max mem: 9390 +Train: [22] [ 400/6250] eta: 0:18:14 lr: 0.000115 grad: 0.0597 (0.0714) loss: 0.8440 (0.8404) time: 0.2027 data: 0.1159 max mem: 9390 +Train: [22] [ 500/6250] eta: 0:17:27 lr: 0.000115 grad: 0.0645 (0.0701) loss: 0.8414 (0.8401) time: 0.1793 data: 0.0844 max mem: 9390 +Train: [22] [ 600/6250] eta: 0:16:57 lr: 0.000115 grad: 0.0616 (0.0693) loss: 0.8338 (0.8393) time: 0.1827 data: 0.0800 max mem: 9390 +Train: [22] [ 700/6250] eta: 0:16:34 lr: 0.000115 grad: 0.0619 (0.0687) loss: 0.8404 (0.8391) time: 0.1998 data: 0.1076 max mem: 9390 +Train: [22] [ 800/6250] eta: 0:16:23 lr: 0.000115 grad: 0.0620 (0.0684) loss: 0.8356 (0.8388) time: 0.2181 data: 0.1132 max mem: 9390 +Train: [22] [ 900/6250] eta: 0:16:04 lr: 0.000115 grad: 0.0620 (0.0683) loss: 0.8415 (0.8385) time: 0.1927 data: 0.0998 max mem: 9390 +Train: [22] [1000/6250] eta: 0:15:48 lr: 0.000115 grad: 0.0639 (0.0681) loss: 0.8388 (0.8385) time: 0.1852 data: 0.0882 max mem: 9390 +Train: [22] [1100/6250] eta: 0:15:24 lr: 0.000115 grad: 0.0679 (0.0681) loss: 0.8348 (0.8382) time: 0.1885 data: 0.0956 max mem: 9390 +Train: [22] [1200/6250] eta: 0:15:01 lr: 0.000115 grad: 0.0640 (0.0679) loss: 0.8352 (0.8380) time: 0.1430 data: 0.0361 max mem: 9390 +Train: [22] [1300/6250] eta: 0:14:38 lr: 0.000115 grad: 0.0681 (0.0681) loss: 0.8321 (0.8379) time: 0.1585 data: 0.0714 max mem: 9390 +Train: [22] [1400/6250] eta: 0:14:20 lr: 0.000115 grad: 0.0681 (0.0680) loss: 0.8363 (0.8375) time: 0.1916 data: 0.1061 max mem: 9390 +Train: [22] [1500/6250] eta: 0:13:59 lr: 0.000115 grad: 0.0646 (0.0679) loss: 0.8346 (0.8374) time: 0.1635 data: 0.0813 max mem: 9390 +Train: [22] [1600/6250] eta: 0:13:37 lr: 0.000115 grad: 0.0678 (0.0679) loss: 0.8344 (0.8372) time: 0.1472 data: 0.0545 max mem: 9390 +Train: [22] [1700/6250] eta: 0:13:17 lr: 0.000115 grad: 0.0632 (0.0677) loss: 0.8330 (0.8372) time: 0.1682 data: 0.0809 max mem: 9390 +Train: [22] [1800/6250] eta: 0:12:57 lr: 0.000115 grad: 0.0693 (0.0677) loss: 0.8299 (0.8370) time: 0.1763 data: 0.0959 max mem: 9390 +Train: [22] [1900/6250] eta: 0:12:37 lr: 0.000115 grad: 0.0655 (0.0677) loss: 0.8326 (0.8368) time: 0.1433 data: 0.0582 max mem: 9390 +Train: [22] [2000/6250] eta: 0:12:18 lr: 0.000115 grad: 0.0630 (0.0677) loss: 0.8365 (0.8366) time: 0.1493 data: 0.0689 max mem: 9390 +Train: [22] [2100/6250] eta: 0:12:00 lr: 0.000115 grad: 0.0640 (0.0675) loss: 0.8342 (0.8365) time: 0.1276 data: 0.0320 max mem: 9390 +Train: [22] [2200/6250] eta: 0:11:41 lr: 0.000115 grad: 0.0656 (0.0675) loss: 0.8394 (0.8365) time: 0.1629 data: 0.0722 max mem: 9390 +Train: [22] [2300/6250] eta: 0:11:21 lr: 0.000115 grad: 0.0620 (0.0674) loss: 0.8346 (0.8364) time: 0.1566 data: 0.0611 max mem: 9390 +Train: [22] [2400/6250] eta: 0:11:03 lr: 0.000115 grad: 0.0680 (0.0675) loss: 0.8280 (0.8363) time: 0.1472 data: 0.0628 max mem: 9390 +Train: [22] [2500/6250] eta: 0:10:46 lr: 0.000115 grad: 0.0662 (0.0675) loss: 0.8371 (0.8363) time: 0.1854 data: 0.1017 max mem: 9390 +Train: [22] [2600/6250] eta: 0:10:27 lr: 0.000115 grad: 0.0657 (0.0676) loss: 0.8345 (0.8364) time: 0.1667 data: 0.0756 max mem: 9390 +Train: [22] [2700/6250] eta: 0:10:10 lr: 0.000115 grad: 0.0624 (0.0676) loss: 0.8383 (0.8364) time: 0.1437 data: 0.0488 max mem: 9390 +Train: [22] [2800/6250] eta: 0:09:52 lr: 0.000115 grad: 0.0644 (0.0676) loss: 0.8385 (0.8364) time: 0.1458 data: 0.0487 max mem: 9390 +Train: [22] [2900/6250] eta: 0:09:34 lr: 0.000115 grad: 0.0641 (0.0676) loss: 0.8299 (0.8363) time: 0.1783 data: 0.0907 max mem: 9390 +Train: [22] [3000/6250] eta: 0:09:16 lr: 0.000115 grad: 0.0661 (0.0676) loss: 0.8332 (0.8362) time: 0.1786 data: 0.0948 max mem: 9390 +Train: [22] [3100/6250] eta: 0:08:59 lr: 0.000115 grad: 0.0623 (0.0677) loss: 0.8416 (0.8361) time: 0.1858 data: 0.1062 max mem: 9390 +Train: [22] [3200/6250] eta: 0:08:42 lr: 0.000115 grad: 0.0629 (0.0678) loss: 0.8386 (0.8360) time: 0.1610 data: 0.0702 max mem: 9390 +Train: [22] [3300/6250] eta: 0:08:24 lr: 0.000115 grad: 0.0655 (0.0679) loss: 0.8348 (0.8359) time: 0.1673 data: 0.0780 max mem: 9390 +Train: [22] [3400/6250] eta: 0:08:07 lr: 0.000115 grad: 0.0680 (0.0679) loss: 0.8286 (0.8358) time: 0.1555 data: 0.0628 max mem: 9390 +Train: [22] [3500/6250] eta: 0:07:50 lr: 0.000115 grad: 0.0685 (0.0679) loss: 0.8347 (0.8357) time: 0.1529 data: 0.0623 max mem: 9390 +Train: [22] [3600/6250] eta: 0:07:32 lr: 0.000115 grad: 0.0692 (0.0680) loss: 0.8335 (0.8357) time: 0.1828 data: 0.0939 max mem: 9390 +Train: [22] [3700/6250] eta: 0:07:15 lr: 0.000115 grad: 0.0695 (0.0680) loss: 0.8325 (0.8356) time: 0.1807 data: 0.0986 max mem: 9390 +Train: [22] [3800/6250] eta: 0:06:58 lr: 0.000115 grad: 0.0695 (0.0681) loss: 0.8279 (0.8355) time: 0.1597 data: 0.0733 max mem: 9390 +Train: [22] [3900/6250] eta: 0:06:41 lr: 0.000115 grad: 0.0620 (0.0681) loss: 0.8372 (0.8355) time: 0.1872 data: 0.1002 max mem: 9390 +Train: [22] [4000/6250] eta: 0:06:23 lr: 0.000115 grad: 0.0671 (0.0682) loss: 0.8322 (0.8355) time: 0.1778 data: 0.0908 max mem: 9390 +Train: [22] [4100/6250] eta: 0:06:06 lr: 0.000115 grad: 0.0674 (0.0682) loss: 0.8325 (0.8354) time: 0.1561 data: 0.0583 max mem: 9390 +Train: [22] [4200/6250] eta: 0:05:49 lr: 0.000115 grad: 0.0712 (0.0682) loss: 0.8331 (0.8354) time: 0.1482 data: 0.0601 max mem: 9390 +Train: [22] [4300/6250] eta: 0:05:32 lr: 0.000115 grad: 0.0643 (0.0682) loss: 0.8373 (0.8354) time: 0.1362 data: 0.0494 max mem: 9390 +Train: [22] [4400/6250] eta: 0:05:14 lr: 0.000115 grad: 0.0623 (0.0682) loss: 0.8392 (0.8354) time: 0.1528 data: 0.0717 max mem: 9390 +Train: [22] [4500/6250] eta: 0:04:57 lr: 0.000115 grad: 0.0618 (0.0682) loss: 0.8375 (0.8353) time: 0.1698 data: 0.0853 max mem: 9390 +Train: [22] [4600/6250] eta: 0:04:40 lr: 0.000115 grad: 0.0698 (0.0683) loss: 0.8375 (0.8353) time: 0.1716 data: 0.0869 max mem: 9390 +Train: [22] [4700/6250] eta: 0:04:23 lr: 0.000115 grad: 0.0658 (0.0683) loss: 0.8387 (0.8353) time: 0.1628 data: 0.0729 max mem: 9390 +Train: [22] [4800/6250] eta: 0:04:06 lr: 0.000115 grad: 0.0664 (0.0683) loss: 0.8357 (0.8353) time: 0.1606 data: 0.0724 max mem: 9390 +Train: [22] [4900/6250] eta: 0:03:49 lr: 0.000114 grad: 0.0681 (0.0683) loss: 0.8355 (0.8353) time: 0.1768 data: 0.0824 max mem: 9390 +Train: [22] [5000/6250] eta: 0:03:32 lr: 0.000114 grad: 0.0671 (0.0683) loss: 0.8305 (0.8353) time: 0.1840 data: 0.0918 max mem: 9390 +Train: [22] [5100/6250] eta: 0:03:15 lr: 0.000114 grad: 0.0671 (0.0683) loss: 0.8370 (0.8353) time: 0.1532 data: 0.0691 max mem: 9390 +Train: [22] [5200/6250] eta: 0:02:58 lr: 0.000114 grad: 0.0701 (0.0683) loss: 0.8411 (0.8354) time: 0.1655 data: 0.0816 max mem: 9390 +Train: [22] [5300/6250] eta: 0:02:41 lr: 0.000114 grad: 0.0647 (0.0683) loss: 0.8384 (0.8354) time: 0.1570 data: 0.0701 max mem: 9390 +Train: [22] [5400/6250] eta: 0:02:24 lr: 0.000114 grad: 0.0644 (0.0682) loss: 0.8396 (0.8355) time: 0.1839 data: 0.0994 max mem: 9390 +Train: [22] [5500/6250] eta: 0:02:07 lr: 0.000114 grad: 0.0653 (0.0682) loss: 0.8384 (0.8355) time: 0.1733 data: 0.0874 max mem: 9390 +Train: [22] [5600/6250] eta: 0:01:50 lr: 0.000114 grad: 0.0631 (0.0682) loss: 0.8349 (0.8356) time: 0.1518 data: 0.0526 max mem: 9390 +Train: [22] [5700/6250] eta: 0:01:33 lr: 0.000114 grad: 0.0699 (0.0682) loss: 0.8373 (0.8356) time: 0.1643 data: 0.0754 max mem: 9390 +Train: [22] [5800/6250] eta: 0:01:16 lr: 0.000114 grad: 0.0650 (0.0682) loss: 0.8431 (0.8356) time: 0.1524 data: 0.0684 max mem: 9390 +Train: [22] [5900/6250] eta: 0:00:59 lr: 0.000114 grad: 0.0630 (0.0681) loss: 0.8415 (0.8357) time: 0.1842 data: 0.1071 max mem: 9390 +Train: [22] [6000/6250] eta: 0:00:42 lr: 0.000114 grad: 0.0671 (0.0681) loss: 0.8353 (0.8357) time: 0.1570 data: 0.0740 max mem: 9390 +Train: [22] [6100/6250] eta: 0:00:25 lr: 0.000114 grad: 0.0662 (0.0681) loss: 0.8393 (0.8357) time: 0.1789 data: 0.0937 max mem: 9390 +Train: [22] [6200/6250] eta: 0:00:08 lr: 0.000114 grad: 0.0591 (0.0681) loss: 0.8444 (0.8358) time: 0.1839 data: 0.1022 max mem: 9390 +Train: [22] [6249/6250] eta: 0:00:00 lr: 0.000114 grad: 0.0633 (0.0680) loss: 0.8415 (0.8358) time: 0.1540 data: 0.0672 max mem: 9390 +Train: [22] Total time: 0:17:46 (0.1706 s / it) +Averaged stats: lr: 0.000114 grad: 0.0633 (0.0680) loss: 0.8415 (0.8358) +Eval (hcp-train-subset): [22] [ 0/62] eta: 0:06:23 loss: 0.8574 (0.8574) time: 6.1789 data: 6.1339 max mem: 9390 +Eval (hcp-train-subset): [22] [61/62] eta: 0:00:00 loss: 0.8452 (0.8443) time: 0.1238 data: 0.0968 max mem: 9390 +Eval (hcp-train-subset): [22] Total time: 0:00:14 (0.2318 s / it) +Averaged stats (hcp-train-subset): loss: 0.8452 (0.8443) +Eval (hcp-val): [22] [ 0/62] eta: 0:05:51 loss: 0.8418 (0.8418) time: 5.6659 data: 5.6363 max mem: 9390 +Eval (hcp-val): [22] [61/62] eta: 0:00:00 loss: 0.8383 (0.8404) time: 0.1214 data: 0.0935 max mem: 9390 +Eval (hcp-val): [22] Total time: 0:00:13 (0.2184 s / it) +Averaged stats (hcp-val): loss: 0.8383 (0.8404) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +Train: [23] [ 0/6250] eta: 8:08:26 lr: 0.000114 grad: 0.0853 (0.0853) loss: 0.8513 (0.8513) time: 4.6890 data: 4.4674 max mem: 9390 +Train: [23] [ 100/6250] eta: 0:22:00 lr: 0.000114 grad: 0.0697 (0.0766) loss: 0.8278 (0.8347) time: 0.1659 data: 0.0678 max mem: 9390 +Train: [23] [ 200/6250] eta: 0:19:03 lr: 0.000114 grad: 0.0671 (0.0737) loss: 0.8401 (0.8340) time: 0.1864 data: 0.0963 max mem: 9390 +Train: [23] [ 300/6250] eta: 0:18:01 lr: 0.000114 grad: 0.0692 (0.0737) loss: 0.8339 (0.8323) time: 0.1506 data: 0.0549 max mem: 9390 +Train: [23] [ 400/6250] eta: 0:17:38 lr: 0.000114 grad: 0.0659 (0.0729) loss: 0.8341 (0.8324) time: 0.1505 data: 0.0614 max mem: 9390 +Train: [23] [ 500/6250] eta: 0:17:08 lr: 0.000114 grad: 0.0652 (0.0715) loss: 0.8390 (0.8330) time: 0.1593 data: 0.0706 max mem: 9390 +Train: [23] [ 600/6250] eta: 0:16:38 lr: 0.000114 grad: 0.0623 (0.0708) loss: 0.8320 (0.8332) time: 0.1695 data: 0.0779 max mem: 9390 +Train: [23] [ 700/6250] eta: 0:16:15 lr: 0.000114 grad: 0.0621 (0.0700) loss: 0.8342 (0.8335) time: 0.1873 data: 0.0957 max mem: 9390 +Train: [23] [ 800/6250] eta: 0:15:59 lr: 0.000114 grad: 0.0644 (0.0694) loss: 0.8378 (0.8339) time: 0.2245 data: 0.1226 max mem: 9390 +Train: [23] [ 900/6250] eta: 0:15:44 lr: 0.000114 grad: 0.0609 (0.0689) loss: 0.8358 (0.8342) time: 0.1546 data: 0.0596 max mem: 9390 +Train: [23] [1000/6250] eta: 0:15:24 lr: 0.000114 grad: 0.0667 (0.0686) loss: 0.8308 (0.8344) time: 0.1740 data: 0.0876 max mem: 9390 +Train: [23] [1100/6250] eta: 0:15:00 lr: 0.000114 grad: 0.0622 (0.0683) loss: 0.8367 (0.8346) time: 0.1593 data: 0.0698 max mem: 9390 +Train: [23] [1200/6250] eta: 0:14:39 lr: 0.000114 grad: 0.0687 (0.0681) loss: 0.8393 (0.8348) time: 0.1803 data: 0.0924 max mem: 9390 +Train: [23] [1300/6250] eta: 0:14:18 lr: 0.000114 grad: 0.0612 (0.0679) loss: 0.8371 (0.8350) time: 0.1738 data: 0.0889 max mem: 9390 +Train: [23] [1400/6250] eta: 0:13:59 lr: 0.000114 grad: 0.0677 (0.0679) loss: 0.8352 (0.8351) time: 0.1950 data: 0.1134 max mem: 9390 +Train: [23] [1500/6250] eta: 0:13:37 lr: 0.000114 grad: 0.0635 (0.0679) loss: 0.8304 (0.8350) time: 0.1638 data: 0.0714 max mem: 9390 +Train: [23] [1600/6250] eta: 0:13:17 lr: 0.000114 grad: 0.0635 (0.0681) loss: 0.8382 (0.8350) time: 0.1615 data: 0.0770 max mem: 9390 +Train: [23] [1700/6250] eta: 0:12:57 lr: 0.000114 grad: 0.0630 (0.0681) loss: 0.8414 (0.8351) time: 0.1624 data: 0.0737 max mem: 9390 +Train: [23] [1800/6250] eta: 0:12:39 lr: 0.000114 grad: 0.0729 (0.0681) loss: 0.8314 (0.8351) time: 0.1543 data: 0.0630 max mem: 9390 +Train: [23] [1900/6250] eta: 0:12:21 lr: 0.000114 grad: 0.0682 (0.0682) loss: 0.8356 (0.8352) time: 0.1717 data: 0.0860 max mem: 9390 +Train: [23] [2000/6250] eta: 0:12:03 lr: 0.000114 grad: 0.0666 (0.0682) loss: 0.8326 (0.8352) time: 0.1704 data: 0.0841 max mem: 9390 +Train: [23] [2100/6250] eta: 0:11:46 lr: 0.000114 grad: 0.0675 (0.0682) loss: 0.8308 (0.8351) time: 0.1673 data: 0.0796 max mem: 9390 +Train: [23] [2200/6250] eta: 0:11:29 lr: 0.000114 grad: 0.0693 (0.0683) loss: 0.8284 (0.8351) time: 0.1392 data: 0.0541 max mem: 9390 +Train: [23] [2300/6250] eta: 0:11:10 lr: 0.000114 grad: 0.0693 (0.0684) loss: 0.8327 (0.8350) time: 0.1531 data: 0.0646 max mem: 9390 +Train: [23] [2400/6250] eta: 0:10:51 lr: 0.000114 grad: 0.0693 (0.0685) loss: 0.8335 (0.8351) time: 0.1637 data: 0.0731 max mem: 9390 +Train: [23] [2500/6250] eta: 0:10:34 lr: 0.000114 grad: 0.0643 (0.0686) loss: 0.8356 (0.8350) time: 0.1511 data: 0.0536 max mem: 9390 +Train: [23] [2600/6250] eta: 0:10:17 lr: 0.000114 grad: 0.0661 (0.0686) loss: 0.8341 (0.8350) time: 0.1701 data: 0.0863 max mem: 9390 +Train: [23] [2700/6250] eta: 0:10:00 lr: 0.000114 grad: 0.0669 (0.0687) loss: 0.8334 (0.8349) time: 0.1755 data: 0.0866 max mem: 9390 +Train: [23] [2800/6250] eta: 0:09:42 lr: 0.000114 grad: 0.0625 (0.0686) loss: 0.8355 (0.8350) time: 0.1726 data: 0.0831 max mem: 9390 +Train: [23] [2900/6250] eta: 0:09:25 lr: 0.000114 grad: 0.0680 (0.0686) loss: 0.8346 (0.8350) time: 0.1628 data: 0.0732 max mem: 9390 +Train: [23] [3000/6250] eta: 0:09:07 lr: 0.000114 grad: 0.0658 (0.0686) loss: 0.8394 (0.8350) time: 0.1540 data: 0.0700 max mem: 9390 +Train: [23] [3100/6250] eta: 0:08:50 lr: 0.000114 grad: 0.0656 (0.0686) loss: 0.8355 (0.8349) time: 0.1528 data: 0.0692 max mem: 9390 +Train: [23] [3200/6250] eta: 0:08:34 lr: 0.000114 grad: 0.0665 (0.0687) loss: 0.8346 (0.8349) time: 0.1577 data: 0.0678 max mem: 9390 +Train: [23] [3300/6250] eta: 0:08:16 lr: 0.000114 grad: 0.0648 (0.0687) loss: 0.8354 (0.8349) time: 0.1616 data: 0.0690 max mem: 9390 +Train: [23] [3400/6250] eta: 0:07:59 lr: 0.000114 grad: 0.0692 (0.0687) loss: 0.8366 (0.8349) time: 0.1516 data: 0.0610 max mem: 9390 +Train: [23] [3500/6250] eta: 0:07:42 lr: 0.000114 grad: 0.0650 (0.0687) loss: 0.8336 (0.8349) time: 0.1365 data: 0.0532 max mem: 9390 +Train: [23] [3600/6250] eta: 0:07:25 lr: 0.000114 grad: 0.0673 (0.0688) loss: 0.8330 (0.8349) time: 0.1850 data: 0.1014 max mem: 9390 +Train: [23] [3700/6250] eta: 0:07:08 lr: 0.000114 grad: 0.0643 (0.0689) loss: 0.8382 (0.8349) time: 0.1724 data: 0.0823 max mem: 9390 +Train: [23] [3800/6250] eta: 0:06:51 lr: 0.000114 grad: 0.0671 (0.0689) loss: 0.8365 (0.8350) time: 0.1778 data: 0.0939 max mem: 9390 +Train: [23] [3900/6250] eta: 0:06:34 lr: 0.000114 grad: 0.0679 (0.0689) loss: 0.8313 (0.8349) time: 0.1652 data: 0.0855 max mem: 9390 +Train: [23] [4000/6250] eta: 0:06:18 lr: 0.000113 grad: 0.0640 (0.0689) loss: 0.8321 (0.8349) time: 0.1925 data: 0.1115 max mem: 9390 +Train: [23] [4100/6250] eta: 0:06:00 lr: 0.000113 grad: 0.0655 (0.0689) loss: 0.8299 (0.8348) time: 0.1699 data: 0.0798 max mem: 9390 +Train: [23] [4200/6250] eta: 0:05:44 lr: 0.000113 grad: 0.0684 (0.0689) loss: 0.8354 (0.8348) time: 0.1728 data: 0.0737 max mem: 9390 +Train: [23] [4300/6250] eta: 0:05:28 lr: 0.000113 grad: 0.0670 (0.0689) loss: 0.8315 (0.8348) time: 0.1764 data: 0.0760 max mem: 9390 +Train: [23] [4400/6250] eta: 0:05:11 lr: 0.000113 grad: 0.0704 (0.0690) loss: 0.8288 (0.8347) time: 0.1630 data: 0.0837 max mem: 9390 +Train: [23] [4500/6250] eta: 0:04:55 lr: 0.000113 grad: 0.0669 (0.0691) loss: 0.8285 (0.8346) time: 0.1597 data: 0.0862 max mem: 9390 +Train: [23] [4600/6250] eta: 0:04:38 lr: 0.000113 grad: 0.0684 (0.0691) loss: 0.8354 (0.8345) time: 0.1771 data: 0.0960 max mem: 9390 +Train: [23] [4700/6250] eta: 0:04:21 lr: 0.000113 grad: 0.0680 (0.0692) loss: 0.8279 (0.8344) time: 0.1895 data: 0.0969 max mem: 9390 +Train: [23] [4800/6250] eta: 0:04:04 lr: 0.000113 grad: 0.0671 (0.0692) loss: 0.8318 (0.8344) time: 0.1590 data: 0.0748 max mem: 9390 +Train: [23] [4900/6250] eta: 0:03:47 lr: 0.000113 grad: 0.0671 (0.0692) loss: 0.8388 (0.8343) time: 0.1757 data: 0.0877 max mem: 9390 +Train: [23] [5000/6250] eta: 0:03:30 lr: 0.000113 grad: 0.0669 (0.0692) loss: 0.8372 (0.8343) time: 0.1573 data: 0.0622 max mem: 9390 +Train: [23] [5100/6250] eta: 0:03:13 lr: 0.000113 grad: 0.0649 (0.0692) loss: 0.8349 (0.8342) time: 0.1825 data: 0.0905 max mem: 9390 +Train: [23] [5200/6250] eta: 0:02:56 lr: 0.000113 grad: 0.0682 (0.0692) loss: 0.8261 (0.8342) time: 0.1682 data: 0.0640 max mem: 9390 +Train: [23] [5300/6250] eta: 0:02:39 lr: 0.000113 grad: 0.0695 (0.0692) loss: 0.8379 (0.8341) time: 0.1411 data: 0.0528 max mem: 9390 +Train: [23] [5400/6250] eta: 0:02:22 lr: 0.000113 grad: 0.0653 (0.0692) loss: 0.8345 (0.8341) time: 0.1619 data: 0.0677 max mem: 9390 +Train: [23] [5500/6250] eta: 0:02:06 lr: 0.000113 grad: 0.0698 (0.0692) loss: 0.8265 (0.8340) time: 0.1672 data: 0.0723 max mem: 9390 +Train: [23] [5600/6250] eta: 0:01:49 lr: 0.000113 grad: 0.0618 (0.0692) loss: 0.8305 (0.8340) time: 0.1301 data: 0.0356 max mem: 9390 +Train: [23] [5700/6250] eta: 0:01:32 lr: 0.000113 grad: 0.0654 (0.0692) loss: 0.8333 (0.8340) time: 0.1972 data: 0.1060 max mem: 9390 +Train: [23] [5800/6250] eta: 0:01:15 lr: 0.000113 grad: 0.0631 (0.0691) loss: 0.8331 (0.8340) time: 0.1468 data: 0.0587 max mem: 9390 +Train: [23] [5900/6250] eta: 0:00:58 lr: 0.000113 grad: 0.0687 (0.0692) loss: 0.8357 (0.8340) time: 0.1841 data: 0.0927 max mem: 9390 +Train: [23] [6000/6250] eta: 0:00:41 lr: 0.000113 grad: 0.0598 (0.0691) loss: 0.8334 (0.8340) time: 0.1675 data: 0.0835 max mem: 9390 +Train: [23] [6100/6250] eta: 0:00:25 lr: 0.000113 grad: 0.0661 (0.0692) loss: 0.8344 (0.8340) time: 0.1766 data: 0.0759 max mem: 9390 +Train: [23] [6200/6250] eta: 0:00:08 lr: 0.000113 grad: 0.0674 (0.0692) loss: 0.8347 (0.8340) time: 0.1630 data: 0.0675 max mem: 9390 +Train: [23] [6249/6250] eta: 0:00:00 lr: 0.000113 grad: 0.0651 (0.0692) loss: 0.8372 (0.8340) time: 0.1518 data: 0.0570 max mem: 9390 +Train: [23] Total time: 0:17:36 (0.1690 s / it) +Averaged stats: lr: 0.000113 grad: 0.0651 (0.0692) loss: 0.8372 (0.8340) +Eval (hcp-train-subset): [23] [ 0/62] eta: 0:05:19 loss: 0.8556 (0.8556) time: 5.1526 data: 5.1223 max mem: 9390 +Eval (hcp-train-subset): [23] [61/62] eta: 0:00:00 loss: 0.8434 (0.8443) time: 0.1331 data: 0.1078 max mem: 9390 +Eval (hcp-train-subset): [23] Total time: 0:00:13 (0.2229 s / it) +Averaged stats (hcp-train-subset): loss: 0.8434 (0.8443) +Eval (hcp-val): [23] [ 0/62] eta: 0:05:47 loss: 0.8357 (0.8357) time: 5.6087 data: 5.5792 max mem: 9390 +Eval (hcp-val): [23] [61/62] eta: 0:00:00 loss: 0.8388 (0.8402) time: 0.1054 data: 0.0786 max mem: 9390 +Eval (hcp-val): [23] Total time: 0:00:13 (0.2244 s / it) +Averaged stats (hcp-val): loss: 0.8388 (0.8402) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +Train: [24] [ 0/6250] eta: 10:06:31 lr: 0.000113 grad: 0.0827 (0.0827) loss: 0.8572 (0.8572) time: 5.8226 data: 5.6701 max mem: 9390 +Train: [24] [ 100/6250] eta: 0:22:32 lr: 0.000113 grad: 0.0665 (0.0687) loss: 0.8506 (0.8467) time: 0.1785 data: 0.0843 max mem: 9390 +Train: [24] [ 200/6250] eta: 0:19:33 lr: 0.000113 grad: 0.0774 (0.0702) loss: 0.8338 (0.8421) time: 0.1667 data: 0.0619 max mem: 9390 +Train: [24] [ 300/6250] eta: 0:18:26 lr: 0.000113 grad: 0.0681 (0.0702) loss: 0.8319 (0.8396) time: 0.1714 data: 0.0818 max mem: 9390 +Train: [24] [ 400/6250] eta: 0:18:01 lr: 0.000113 grad: 0.0635 (0.0694) loss: 0.8404 (0.8396) time: 0.1612 data: 0.0710 max mem: 9390 +Train: [24] [ 500/6250] eta: 0:17:33 lr: 0.000113 grad: 0.0642 (0.0690) loss: 0.8389 (0.8393) time: 0.1761 data: 0.0783 max mem: 9390 +Train: [24] [ 600/6250] eta: 0:17:40 lr: 0.000113 grad: 0.0673 (0.0691) loss: 0.8345 (0.8391) time: 0.1736 data: 0.0535 max mem: 9390 +Train: [24] [ 700/6250] eta: 0:17:19 lr: 0.000113 grad: 0.0618 (0.0689) loss: 0.8360 (0.8388) time: 0.1863 data: 0.0902 max mem: 9390 +Train: [24] [ 800/6250] eta: 0:16:57 lr: 0.000113 grad: 0.0680 (0.0688) loss: 0.8385 (0.8386) time: 0.1879 data: 0.0923 max mem: 9390 +Train: [24] [ 900/6250] eta: 0:16:30 lr: 0.000113 grad: 0.0668 (0.0688) loss: 0.8313 (0.8383) time: 0.1689 data: 0.0740 max mem: 9390 +Train: [24] [1000/6250] eta: 0:16:03 lr: 0.000113 grad: 0.0658 (0.0687) loss: 0.8314 (0.8379) time: 0.1504 data: 0.0558 max mem: 9390 +Train: [24] [1100/6250] eta: 0:15:39 lr: 0.000113 grad: 0.0644 (0.0687) loss: 0.8369 (0.8376) time: 0.1757 data: 0.0921 max mem: 9390 +Train: [24] [1200/6250] eta: 0:15:14 lr: 0.000113 grad: 0.0660 (0.0687) loss: 0.8352 (0.8373) time: 0.1530 data: 0.0530 max mem: 9390 +Train: [24] [1300/6250] eta: 0:14:51 lr: 0.000113 grad: 0.0670 (0.0690) loss: 0.8347 (0.8370) time: 0.1790 data: 0.0890 max mem: 9390 +Train: [24] [1400/6250] eta: 0:14:28 lr: 0.000113 grad: 0.0675 (0.0691) loss: 0.8348 (0.8367) time: 0.1709 data: 0.0791 max mem: 9390 +Train: [24] [1500/6250] eta: 0:14:08 lr: 0.000113 grad: 0.0691 (0.0692) loss: 0.8296 (0.8365) time: 0.2097 data: 0.1228 max mem: 9390 +Train: [24] [1600/6250] eta: 0:13:44 lr: 0.000113 grad: 0.0669 (0.0692) loss: 0.8324 (0.8362) time: 0.1450 data: 0.0608 max mem: 9390 +Train: [24] [1700/6250] eta: 0:13:24 lr: 0.000113 grad: 0.0643 (0.0692) loss: 0.8346 (0.8359) time: 0.1603 data: 0.0675 max mem: 9390 +Train: [24] [1800/6250] eta: 0:13:05 lr: 0.000113 grad: 0.0638 (0.0691) loss: 0.8350 (0.8358) time: 0.1802 data: 0.0885 max mem: 9390 +Train: [24] [1900/6250] eta: 0:12:47 lr: 0.000113 grad: 0.0657 (0.0690) loss: 0.8312 (0.8356) time: 0.2044 data: 0.1129 max mem: 9390 +Train: [24] [2000/6250] eta: 0:12:28 lr: 0.000113 grad: 0.0672 (0.0690) loss: 0.8333 (0.8354) time: 0.1787 data: 0.0952 max mem: 9390 +Train: [24] [2100/6250] eta: 0:12:09 lr: 0.000113 grad: 0.0637 (0.0690) loss: 0.8336 (0.8354) time: 0.1631 data: 0.0721 max mem: 9390 +Train: [24] [2200/6250] eta: 0:11:49 lr: 0.000113 grad: 0.0656 (0.0689) loss: 0.8326 (0.8353) time: 0.1694 data: 0.0770 max mem: 9390 +Train: [24] [2300/6250] eta: 0:11:29 lr: 0.000113 grad: 0.0661 (0.0688) loss: 0.8357 (0.8353) time: 0.1575 data: 0.0722 max mem: 9390 +Train: [24] [2400/6250] eta: 0:11:10 lr: 0.000113 grad: 0.0682 (0.0691) loss: 0.8347 (0.8352) time: 0.1533 data: 0.0672 max mem: 9390 +Train: [24] [2500/6250] eta: 0:10:52 lr: 0.000113 grad: 0.0661 (0.0693) loss: 0.8302 (0.8351) time: 0.1613 data: 0.0710 max mem: 9390 +Train: [24] [2600/6250] eta: 0:10:34 lr: 0.000113 grad: 0.0676 (0.0694) loss: 0.8339 (0.8350) time: 0.1730 data: 0.0815 max mem: 9390 +Train: [24] [2700/6250] eta: 0:10:16 lr: 0.000113 grad: 0.0655 (0.0695) loss: 0.8315 (0.8349) time: 0.1780 data: 0.0882 max mem: 9390 +Train: [24] [2800/6250] eta: 0:09:59 lr: 0.000113 grad: 0.0671 (0.0695) loss: 0.8311 (0.8348) time: 0.1716 data: 0.0821 max mem: 9390 +Train: [24] [2900/6250] eta: 0:09:41 lr: 0.000112 grad: 0.0681 (0.0697) loss: 0.8321 (0.8347) time: 0.1817 data: 0.0965 max mem: 9390 +Train: [24] [3000/6250] eta: 0:09:23 lr: 0.000112 grad: 0.0646 (0.0697) loss: 0.8304 (0.8346) time: 0.1631 data: 0.0703 max mem: 9390 +Train: [24] [3100/6250] eta: 0:09:05 lr: 0.000112 grad: 0.0715 (0.0698) loss: 0.8276 (0.8346) time: 0.1800 data: 0.0963 max mem: 9390 +Train: [24] [3200/6250] eta: 0:08:47 lr: 0.000112 grad: 0.0695 (0.0698) loss: 0.8270 (0.8345) time: 0.1910 data: 0.1055 max mem: 9390 +Train: [24] [3300/6250] eta: 0:08:28 lr: 0.000112 grad: 0.0718 (0.0699) loss: 0.8346 (0.8344) time: 0.1594 data: 0.0754 max mem: 9390 +Train: [24] [3400/6250] eta: 0:08:10 lr: 0.000112 grad: 0.0701 (0.0698) loss: 0.8387 (0.8345) time: 0.1582 data: 0.0686 max mem: 9390 +Train: [24] [3500/6250] eta: 0:07:52 lr: 0.000112 grad: 0.0700 (0.0699) loss: 0.8348 (0.8345) time: 0.1314 data: 0.0355 max mem: 9390 +Train: [24] [3600/6250] eta: 0:07:35 lr: 0.000112 grad: 0.0703 (0.0699) loss: 0.8337 (0.8344) time: 0.1665 data: 0.0823 max mem: 9390 +Train: [24] [3700/6250] eta: 0:07:17 lr: 0.000112 grad: 0.0679 (0.0699) loss: 0.8349 (0.8344) time: 0.1657 data: 0.0809 max mem: 9390 +Train: [24] [3800/6250] eta: 0:07:00 lr: 0.000112 grad: 0.0700 (0.0700) loss: 0.8299 (0.8344) time: 0.1492 data: 0.0588 max mem: 9390 +Train: [24] [3900/6250] eta: 0:06:42 lr: 0.000112 grad: 0.0639 (0.0699) loss: 0.8354 (0.8345) time: 0.1559 data: 0.0680 max mem: 9390 +Train: [24] [4000/6250] eta: 0:06:24 lr: 0.000112 grad: 0.0669 (0.0699) loss: 0.8371 (0.8346) time: 0.1686 data: 0.0842 max mem: 9390 +Train: [24] [4100/6250] eta: 0:06:07 lr: 0.000112 grad: 0.0703 (0.0699) loss: 0.8356 (0.8346) time: 0.1494 data: 0.0656 max mem: 9390 +Train: [24] [4200/6250] eta: 0:05:50 lr: 0.000112 grad: 0.0692 (0.0699) loss: 0.8352 (0.8346) time: 0.1421 data: 0.0547 max mem: 9390 +Train: [24] [4300/6250] eta: 0:05:33 lr: 0.000112 grad: 0.0631 (0.0698) loss: 0.8375 (0.8346) time: 0.1605 data: 0.0757 max mem: 9390 +Train: [24] [4400/6250] eta: 0:05:16 lr: 0.000112 grad: 0.0665 (0.0698) loss: 0.8321 (0.8347) time: 0.1517 data: 0.0559 max mem: 9390 +Train: [24] [4500/6250] eta: 0:04:58 lr: 0.000112 grad: 0.0703 (0.0698) loss: 0.8367 (0.8347) time: 0.1736 data: 0.0906 max mem: 9390 +Train: [24] [4600/6250] eta: 0:04:41 lr: 0.000112 grad: 0.0687 (0.0697) loss: 0.8350 (0.8348) time: 0.1516 data: 0.0630 max mem: 9390 +Train: [24] [4700/6250] eta: 0:04:24 lr: 0.000112 grad: 0.0691 (0.0698) loss: 0.8343 (0.8348) time: 0.1601 data: 0.0823 max mem: 9390 +Train: [24] [4800/6250] eta: 0:04:07 lr: 0.000112 grad: 0.0621 (0.0697) loss: 0.8430 (0.8348) time: 0.1880 data: 0.1044 max mem: 9390 +Train: [24] [4900/6250] eta: 0:03:50 lr: 0.000112 grad: 0.0676 (0.0697) loss: 0.8392 (0.8348) time: 0.1540 data: 0.0737 max mem: 9390 +Train: [24] [5000/6250] eta: 0:03:33 lr: 0.000112 grad: 0.0647 (0.0697) loss: 0.8386 (0.8348) time: 0.1673 data: 0.0791 max mem: 9390 +Train: [24] [5100/6250] eta: 0:03:16 lr: 0.000112 grad: 0.0690 (0.0697) loss: 0.8387 (0.8348) time: 0.1505 data: 0.0662 max mem: 9390 +Train: [24] [5200/6250] eta: 0:02:58 lr: 0.000112 grad: 0.0652 (0.0696) loss: 0.8343 (0.8349) time: 0.1470 data: 0.0592 max mem: 9390 +Train: [24] [5300/6250] eta: 0:02:41 lr: 0.000112 grad: 0.0715 (0.0696) loss: 0.8309 (0.8348) time: 0.1666 data: 0.0803 max mem: 9390 +Train: [24] [5400/6250] eta: 0:02:24 lr: 0.000112 grad: 0.0632 (0.0697) loss: 0.8389 (0.8349) time: 0.1693 data: 0.0840 max mem: 9390 +Train: [24] [5500/6250] eta: 0:02:07 lr: 0.000112 grad: 0.0696 (0.0697) loss: 0.8386 (0.8349) time: 0.1424 data: 0.0573 max mem: 9390 +Train: [24] [5600/6250] eta: 0:01:50 lr: 0.000112 grad: 0.0648 (0.0697) loss: 0.8378 (0.8349) time: 0.1749 data: 0.0815 max mem: 9390 +Train: [24] [5700/6250] eta: 0:01:33 lr: 0.000112 grad: 0.0650 (0.0697) loss: 0.8382 (0.8349) time: 0.1613 data: 0.0764 max mem: 9390 +Train: [24] [5800/6250] eta: 0:01:16 lr: 0.000112 grad: 0.0668 (0.0697) loss: 0.8367 (0.8350) time: 0.1894 data: 0.1045 max mem: 9390 +Train: [24] [5900/6250] eta: 0:00:59 lr: 0.000112 grad: 0.0680 (0.0697) loss: 0.8365 (0.8350) time: 0.1637 data: 0.0751 max mem: 9390 +Train: [24] [6000/6250] eta: 0:00:42 lr: 0.000112 grad: 0.0703 (0.0697) loss: 0.8339 (0.8350) time: 0.1663 data: 0.0789 max mem: 9390 +Train: [24] [6100/6250] eta: 0:00:25 lr: 0.000112 grad: 0.0634 (0.0697) loss: 0.8373 (0.8350) time: 0.1716 data: 0.0808 max mem: 9390 +Train: [24] [6200/6250] eta: 0:00:08 lr: 0.000112 grad: 0.0664 (0.0697) loss: 0.8374 (0.8350) time: 0.1555 data: 0.0726 max mem: 9390 +Train: [24] [6249/6250] eta: 0:00:00 lr: 0.000112 grad: 0.0671 (0.0697) loss: 0.8399 (0.8351) time: 0.1855 data: 0.1011 max mem: 9390 +Train: [24] Total time: 0:17:48 (0.1710 s / it) +Averaged stats: lr: 0.000112 grad: 0.0671 (0.0697) loss: 0.8399 (0.8351) +Eval (hcp-train-subset): [24] [ 0/62] eta: 0:05:45 loss: 0.8564 (0.8564) time: 5.5698 data: 5.5288 max mem: 9390 +Eval (hcp-train-subset): [24] [61/62] eta: 0:00:00 loss: 0.8465 (0.8461) time: 0.1140 data: 0.0891 max mem: 9390 +Eval (hcp-train-subset): [24] Total time: 0:00:13 (0.2168 s / it) +Averaged stats (hcp-train-subset): loss: 0.8465 (0.8461) +Making plots (hcp-train-subset): example=38 +Eval (hcp-val): [24] [ 0/62] eta: 0:05:35 loss: 0.8381 (0.8381) time: 5.4134 data: 5.3836 max mem: 9390 +Eval (hcp-val): [24] [61/62] eta: 0:00:00 loss: 0.8398 (0.8408) time: 0.1359 data: 0.1101 max mem: 9390 +Eval (hcp-val): [24] Total time: 0:00:13 (0.2157 s / it) +Averaged stats (hcp-val): loss: 0.8398 (0.8408) +Making plots (hcp-val): example=30 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +Train: [25] [ 0/6250] eta: 9:31:57 lr: 0.000112 grad: 0.0612 (0.0612) loss: 0.8636 (0.8636) time: 5.4908 data: 5.2538 max mem: 9390 +Train: [25] [ 100/6250] eta: 0:22:58 lr: 0.000112 grad: 0.0676 (0.0711) loss: 0.8417 (0.8467) time: 0.1771 data: 0.0842 max mem: 9390 +Train: [25] [ 200/6250] eta: 0:19:50 lr: 0.000112 grad: 0.0683 (0.0714) loss: 0.8382 (0.8427) time: 0.1591 data: 0.0722 max mem: 9390 +Train: [25] [ 300/6250] eta: 0:18:30 lr: 0.000112 grad: 0.0656 (0.0709) loss: 0.8361 (0.8403) time: 0.1728 data: 0.0821 max mem: 9390 +Train: [25] [ 400/6250] eta: 0:18:00 lr: 0.000112 grad: 0.0627 (0.0706) loss: 0.8376 (0.8383) time: 0.1880 data: 0.1048 max mem: 9390 +Train: [25] [ 500/6250] eta: 0:17:24 lr: 0.000112 grad: 0.0651 (0.0708) loss: 0.8324 (0.8374) time: 0.1769 data: 0.0988 max mem: 9390 +Train: [25] [ 600/6250] eta: 0:16:57 lr: 0.000112 grad: 0.0635 (0.0704) loss: 0.8324 (0.8366) time: 0.1883 data: 0.0938 max mem: 9390 +Train: [25] [ 700/6250] eta: 0:17:15 lr: 0.000112 grad: 0.0663 (0.0702) loss: 0.8320 (0.8361) time: 0.2260 data: 0.1188 max mem: 9390 +Train: [25] [ 800/6250] eta: 0:16:54 lr: 0.000112 grad: 0.0628 (0.0700) loss: 0.8335 (0.8360) time: 0.2059 data: 0.1024 max mem: 9390 +Train: [25] [ 900/6250] eta: 0:16:32 lr: 0.000112 grad: 0.0688 (0.0700) loss: 0.8311 (0.8357) time: 0.1757 data: 0.0867 max mem: 9390 +Train: [25] [1000/6250] eta: 0:16:08 lr: 0.000112 grad: 0.0650 (0.0696) loss: 0.8318 (0.8356) time: 0.1779 data: 0.0872 max mem: 9390 +Train: [25] [1100/6250] eta: 0:15:43 lr: 0.000112 grad: 0.0661 (0.0694) loss: 0.8402 (0.8353) time: 0.1770 data: 0.0950 max mem: 9390 +Train: [25] [1200/6250] eta: 0:15:13 lr: 0.000112 grad: 0.0660 (0.0692) loss: 0.8382 (0.8354) time: 0.1433 data: 0.0480 max mem: 9390 +Train: [25] [1300/6250] eta: 0:14:48 lr: 0.000112 grad: 0.0635 (0.0691) loss: 0.8296 (0.8351) time: 0.1687 data: 0.0741 max mem: 9390 +Train: [25] [1400/6250] eta: 0:14:27 lr: 0.000112 grad: 0.0653 (0.0690) loss: 0.8372 (0.8352) time: 0.1692 data: 0.0868 max mem: 9390 +Train: [25] [1500/6250] eta: 0:14:04 lr: 0.000112 grad: 0.0615 (0.0688) loss: 0.8333 (0.8352) time: 0.1678 data: 0.0755 max mem: 9390 +Train: [25] [1600/6250] eta: 0:13:43 lr: 0.000111 grad: 0.0659 (0.0688) loss: 0.8384 (0.8352) time: 0.1576 data: 0.0624 max mem: 9390 +Train: [25] [1700/6250] eta: 0:13:25 lr: 0.000111 grad: 0.0669 (0.0687) loss: 0.8316 (0.8352) time: 0.1825 data: 0.0930 max mem: 9390 +Train: [25] [1800/6250] eta: 0:13:02 lr: 0.000111 grad: 0.0662 (0.0687) loss: 0.8328 (0.8352) time: 0.1655 data: 0.0731 max mem: 9390 +Train: [25] [1900/6250] eta: 0:12:42 lr: 0.000111 grad: 0.0661 (0.0687) loss: 0.8319 (0.8351) time: 0.1805 data: 0.0914 max mem: 9390 +Train: [25] [2000/6250] eta: 0:12:25 lr: 0.000111 grad: 0.0682 (0.0686) loss: 0.8390 (0.8352) time: 0.1841 data: 0.0895 max mem: 9390 +Train: [25] [2100/6250] eta: 0:12:04 lr: 0.000111 grad: 0.0639 (0.0685) loss: 0.8338 (0.8352) time: 0.1525 data: 0.0693 max mem: 9390 +Train: [25] [2200/6250] eta: 0:11:45 lr: 0.000111 grad: 0.0650 (0.0685) loss: 0.8350 (0.8352) time: 0.1724 data: 0.0892 max mem: 9390 +Train: [25] [2300/6250] eta: 0:11:26 lr: 0.000111 grad: 0.0641 (0.0685) loss: 0.8321 (0.8352) time: 0.1454 data: 0.0596 max mem: 9390 +Train: [25] [2400/6250] eta: 0:11:07 lr: 0.000111 grad: 0.0642 (0.0685) loss: 0.8365 (0.8352) time: 0.1718 data: 0.0800 max mem: 9390 +Train: [25] [2500/6250] eta: 0:10:48 lr: 0.000111 grad: 0.0661 (0.0686) loss: 0.8388 (0.8351) time: 0.1684 data: 0.0807 max mem: 9390 +Train: [25] [2600/6250] eta: 0:10:30 lr: 0.000111 grad: 0.0632 (0.0686) loss: 0.8339 (0.8351) time: 0.1615 data: 0.0659 max mem: 9390 +Train: [25] [2700/6250] eta: 0:10:12 lr: 0.000111 grad: 0.0659 (0.0687) loss: 0.8341 (0.8350) time: 0.1742 data: 0.0840 max mem: 9390 +Train: [25] [2800/6250] eta: 0:09:53 lr: 0.000111 grad: 0.0681 (0.0688) loss: 0.8325 (0.8350) time: 0.1528 data: 0.0715 max mem: 9390 +Train: [25] [2900/6250] eta: 0:09:35 lr: 0.000111 grad: 0.0703 (0.0689) loss: 0.8350 (0.8350) time: 0.1709 data: 0.0866 max mem: 9390 +Train: [25] [3000/6250] eta: 0:09:17 lr: 0.000111 grad: 0.0687 (0.0689) loss: 0.8382 (0.8350) time: 0.1738 data: 0.0886 max mem: 9390 +Train: [25] [3100/6250] eta: 0:09:01 lr: 0.000111 grad: 0.0669 (0.0689) loss: 0.8341 (0.8350) time: 0.1809 data: 0.0933 max mem: 9390 +Train: [25] [3200/6250] eta: 0:08:44 lr: 0.000111 grad: 0.0695 (0.0688) loss: 0.8345 (0.8349) time: 0.2022 data: 0.1154 max mem: 9390 +Train: [25] [3300/6250] eta: 0:08:28 lr: 0.000111 grad: 0.0654 (0.0688) loss: 0.8369 (0.8349) time: 0.1653 data: 0.0817 max mem: 9390 +Train: [25] [3400/6250] eta: 0:08:10 lr: 0.000111 grad: 0.0622 (0.0688) loss: 0.8417 (0.8350) time: 0.1669 data: 0.0894 max mem: 9390 +Train: [25] [3500/6250] eta: 0:07:52 lr: 0.000111 grad: 0.0679 (0.0688) loss: 0.8339 (0.8350) time: 0.1487 data: 0.0615 max mem: 9390 +Train: [25] [3600/6250] eta: 0:07:35 lr: 0.000111 grad: 0.0663 (0.0688) loss: 0.8285 (0.8350) time: 0.1575 data: 0.0725 max mem: 9390 +Train: [25] [3700/6250] eta: 0:07:17 lr: 0.000111 grad: 0.0664 (0.0688) loss: 0.8305 (0.8350) time: 0.1533 data: 0.0665 max mem: 9390 +Train: [25] [3800/6250] eta: 0:07:00 lr: 0.000111 grad: 0.0649 (0.0688) loss: 0.8389 (0.8349) time: 0.1764 data: 0.0841 max mem: 9390 +Train: [25] [3900/6250] eta: 0:06:42 lr: 0.000111 grad: 0.0671 (0.0687) loss: 0.8322 (0.8349) time: 0.1629 data: 0.0702 max mem: 9390 +Train: [25] [4000/6250] eta: 0:06:24 lr: 0.000111 grad: 0.0687 (0.0687) loss: 0.8345 (0.8349) time: 0.1500 data: 0.0586 max mem: 9390 +Train: [25] [4100/6250] eta: 0:06:07 lr: 0.000111 grad: 0.0683 (0.0687) loss: 0.8352 (0.8349) time: 0.1295 data: 0.0280 max mem: 9390 +Train: [25] [4200/6250] eta: 0:05:49 lr: 0.000111 grad: 0.0681 (0.0687) loss: 0.8306 (0.8349) time: 0.1549 data: 0.0562 max mem: 9390 +Train: [25] [4300/6250] eta: 0:05:32 lr: 0.000111 grad: 0.0647 (0.0687) loss: 0.8352 (0.8348) time: 0.1671 data: 0.0667 max mem: 9390 +Train: [25] [4400/6250] eta: 0:05:14 lr: 0.000111 grad: 0.0668 (0.0687) loss: 0.8339 (0.8348) time: 0.1642 data: 0.0549 max mem: 9390 +Train: [25] [4500/6250] eta: 0:04:57 lr: 0.000111 grad: 0.0661 (0.0687) loss: 0.8356 (0.8347) time: 0.1724 data: 0.0803 max mem: 9390 +Train: [25] [4600/6250] eta: 0:04:40 lr: 0.000111 grad: 0.0688 (0.0687) loss: 0.8294 (0.8347) time: 0.1605 data: 0.0767 max mem: 9390 +Train: [25] [4700/6250] eta: 0:04:23 lr: 0.000111 grad: 0.0701 (0.0688) loss: 0.8330 (0.8346) time: 0.1676 data: 0.0762 max mem: 9390 +Train: [25] [4800/6250] eta: 0:04:06 lr: 0.000111 grad: 0.0678 (0.0688) loss: 0.8337 (0.8346) time: 0.1956 data: 0.1051 max mem: 9390 +Train: [25] [4900/6250] eta: 0:03:49 lr: 0.000111 grad: 0.0680 (0.0688) loss: 0.8294 (0.8345) time: 0.1330 data: 0.0323 max mem: 9390 +Train: [25] [5000/6250] eta: 0:03:32 lr: 0.000111 grad: 0.0686 (0.0688) loss: 0.8266 (0.8344) time: 0.1696 data: 0.0762 max mem: 9390 +Train: [25] [5100/6250] eta: 0:03:15 lr: 0.000111 grad: 0.0684 (0.0689) loss: 0.8317 (0.8343) time: 0.1728 data: 0.0825 max mem: 9390 +Train: [25] [5200/6250] eta: 0:02:58 lr: 0.000111 grad: 0.0727 (0.0689) loss: 0.8337 (0.8342) time: 0.1873 data: 0.1044 max mem: 9390 +Train: [25] [5300/6250] eta: 0:02:41 lr: 0.000111 grad: 0.0720 (0.0689) loss: 0.8311 (0.8342) time: 0.1695 data: 0.0770 max mem: 9390 +Train: [25] [5400/6250] eta: 0:02:24 lr: 0.000111 grad: 0.0714 (0.0690) loss: 0.8351 (0.8341) time: 0.1576 data: 0.0727 max mem: 9390 +Train: [25] [5500/6250] eta: 0:02:07 lr: 0.000111 grad: 0.0680 (0.0691) loss: 0.8287 (0.8341) time: 0.1676 data: 0.0739 max mem: 9390 +Train: [25] [5600/6250] eta: 0:01:50 lr: 0.000111 grad: 0.0666 (0.0691) loss: 0.8291 (0.8340) time: 0.1529 data: 0.0683 max mem: 9390 +Train: [25] [5700/6250] eta: 0:01:33 lr: 0.000111 grad: 0.0683 (0.0692) loss: 0.8288 (0.8339) time: 0.1553 data: 0.0633 max mem: 9390 +Train: [25] [5800/6250] eta: 0:01:16 lr: 0.000111 grad: 0.0693 (0.0692) loss: 0.8257 (0.8338) time: 0.1689 data: 0.0793 max mem: 9390 +Train: [25] [5900/6250] eta: 0:00:59 lr: 0.000111 grad: 0.0709 (0.0693) loss: 0.8315 (0.8337) time: 0.1655 data: 0.0761 max mem: 9390 +Train: [25] [6000/6250] eta: 0:00:42 lr: 0.000111 grad: 0.0690 (0.0693) loss: 0.8291 (0.8337) time: 0.1735 data: 0.0875 max mem: 9390 +Train: [25] [6100/6250] eta: 0:00:25 lr: 0.000111 grad: 0.0668 (0.0694) loss: 0.8261 (0.8336) time: 0.1705 data: 0.0813 max mem: 9390 +Train: [25] [6200/6250] eta: 0:00:08 lr: 0.000111 grad: 0.0711 (0.0694) loss: 0.8273 (0.8335) time: 0.1810 data: 0.0955 max mem: 9390 +Train: [25] [6249/6250] eta: 0:00:00 lr: 0.000111 grad: 0.0729 (0.0695) loss: 0.8247 (0.8334) time: 0.1587 data: 0.0675 max mem: 9390 +Train: [25] Total time: 0:17:45 (0.1704 s / it) +Averaged stats: lr: 0.000111 grad: 0.0729 (0.0695) loss: 0.8247 (0.8334) +Eval (hcp-train-subset): [25] [ 0/62] eta: 0:05:34 loss: 0.8573 (0.8573) time: 5.4002 data: 5.3642 max mem: 9390 +Eval (hcp-train-subset): [25] [61/62] eta: 0:00:00 loss: 0.8434 (0.8444) time: 0.1417 data: 0.1160 max mem: 9390 +Eval (hcp-train-subset): [25] Total time: 0:00:14 (0.2274 s / it) +Averaged stats (hcp-train-subset): loss: 0.8434 (0.8444) +Eval (hcp-val): [25] [ 0/62] eta: 0:05:19 loss: 0.8371 (0.8371) time: 5.1557 data: 5.1247 max mem: 9390 +Eval (hcp-val): [25] [61/62] eta: 0:00:00 loss: 0.8378 (0.8400) time: 0.1413 data: 0.1161 max mem: 9390 +Eval (hcp-val): [25] Total time: 0:00:13 (0.2205 s / it) +Averaged stats (hcp-val): loss: 0.8378 (0.8400) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +Train: [26] [ 0/6250] eta: 8:57:36 lr: 0.000111 grad: 0.1156 (0.1156) loss: 0.8499 (0.8499) time: 5.1610 data: 4.9258 max mem: 9390 +Train: [26] [ 100/6250] eta: 0:23:22 lr: 0.000111 grad: 0.0605 (0.0720) loss: 0.8457 (0.8468) time: 0.1991 data: 0.1078 max mem: 9390 +Train: [26] [ 200/6250] eta: 0:20:04 lr: 0.000110 grad: 0.0650 (0.0686) loss: 0.8385 (0.8452) time: 0.1780 data: 0.0856 max mem: 9390 +Train: [26] [ 300/6250] eta: 0:18:37 lr: 0.000110 grad: 0.0669 (0.0684) loss: 0.8342 (0.8419) time: 0.1718 data: 0.0754 max mem: 9390 +Train: [26] [ 400/6250] eta: 0:18:11 lr: 0.000110 grad: 0.0638 (0.0682) loss: 0.8323 (0.8398) time: 0.1887 data: 0.0939 max mem: 9390 +Train: [26] [ 500/6250] eta: 0:17:42 lr: 0.000110 grad: 0.0674 (0.0680) loss: 0.8334 (0.8385) time: 0.2098 data: 0.1202 max mem: 9390 +Train: [26] [ 600/6250] eta: 0:17:06 lr: 0.000110 grad: 0.0692 (0.0679) loss: 0.8359 (0.8379) time: 0.1863 data: 0.0937 max mem: 9390 +Train: [26] [ 700/6250] eta: 0:17:07 lr: 0.000110 grad: 0.0651 (0.0678) loss: 0.8364 (0.8376) time: 0.2154 data: 0.1146 max mem: 9390 +Train: [26] [ 800/6250] eta: 0:16:52 lr: 0.000110 grad: 0.0641 (0.0677) loss: 0.8238 (0.8373) time: 0.1622 data: 0.0664 max mem: 9390 +Train: [26] [ 900/6250] eta: 0:16:31 lr: 0.000110 grad: 0.0649 (0.0676) loss: 0.8300 (0.8369) time: 0.1838 data: 0.0914 max mem: 9390 +Train: [26] [1000/6250] eta: 0:16:01 lr: 0.000110 grad: 0.0675 (0.0676) loss: 0.8334 (0.8364) time: 0.1468 data: 0.0368 max mem: 9390 +Train: [26] [1100/6250] eta: 0:15:38 lr: 0.000110 grad: 0.0659 (0.0676) loss: 0.8319 (0.8363) time: 0.1890 data: 0.0971 max mem: 9390 +Train: [26] [1200/6250] eta: 0:15:13 lr: 0.000110 grad: 0.0639 (0.0675) loss: 0.8319 (0.8360) time: 0.1896 data: 0.0982 max mem: 9390 +Train: [26] [1300/6250] eta: 0:14:49 lr: 0.000110 grad: 0.0666 (0.0675) loss: 0.8338 (0.8358) time: 0.1666 data: 0.0766 max mem: 9390 +Train: [26] [1400/6250] eta: 0:14:25 lr: 0.000110 grad: 0.0610 (0.0675) loss: 0.8350 (0.8357) time: 0.1581 data: 0.0736 max mem: 9390 +Train: [26] [1500/6250] eta: 0:14:05 lr: 0.000110 grad: 0.0640 (0.0673) loss: 0.8330 (0.8355) time: 0.1820 data: 0.0941 max mem: 9390 +Train: [26] [1600/6250] eta: 0:13:44 lr: 0.000110 grad: 0.0720 (0.0676) loss: 0.8305 (0.8354) time: 0.1648 data: 0.0774 max mem: 9390 +Train: [26] [1700/6250] eta: 0:13:22 lr: 0.000110 grad: 0.0619 (0.0675) loss: 0.8378 (0.8355) time: 0.1638 data: 0.0812 max mem: 9390 +Train: [26] [1800/6250] eta: 0:13:01 lr: 0.000110 grad: 0.0649 (0.0676) loss: 0.8325 (0.8353) time: 0.1683 data: 0.0736 max mem: 9390 +Train: [26] [1900/6250] eta: 0:12:41 lr: 0.000110 grad: 0.0673 (0.0676) loss: 0.8307 (0.8353) time: 0.1598 data: 0.0646 max mem: 9390 +Train: [26] [2000/6250] eta: 0:12:22 lr: 0.000110 grad: 0.0716 (0.0676) loss: 0.8338 (0.8352) time: 0.1743 data: 0.0865 max mem: 9390 +Train: [26] [2100/6250] eta: 0:12:02 lr: 0.000110 grad: 0.0629 (0.0676) loss: 0.8366 (0.8350) time: 0.1543 data: 0.0675 max mem: 9390 +Train: [26] [2200/6250] eta: 0:11:44 lr: 0.000110 grad: 0.0664 (0.0678) loss: 0.8316 (0.8349) time: 0.2247 data: 0.1350 max mem: 9390 +Train: [26] [2300/6250] eta: 0:11:24 lr: 0.000110 grad: 0.0636 (0.0678) loss: 0.8329 (0.8348) time: 0.1841 data: 0.0965 max mem: 9390 +Train: [26] [2400/6250] eta: 0:11:07 lr: 0.000110 grad: 0.0638 (0.0677) loss: 0.8334 (0.8348) time: 0.2406 data: 0.1539 max mem: 9390 +Train: [26] [2500/6250] eta: 0:10:47 lr: 0.000110 grad: 0.0637 (0.0677) loss: 0.8373 (0.8348) time: 0.1758 data: 0.0917 max mem: 9390 +Train: [26] [2600/6250] eta: 0:10:29 lr: 0.000110 grad: 0.0686 (0.0676) loss: 0.8340 (0.8348) time: 0.1839 data: 0.0976 max mem: 9390 +Train: [26] [2700/6250] eta: 0:10:11 lr: 0.000110 grad: 0.0626 (0.0676) loss: 0.8351 (0.8348) time: 0.1582 data: 0.0688 max mem: 9390 +Train: [26] [2800/6250] eta: 0:09:53 lr: 0.000110 grad: 0.0665 (0.0676) loss: 0.8358 (0.8348) time: 0.1670 data: 0.0774 max mem: 9390 +Train: [26] [2900/6250] eta: 0:09:35 lr: 0.000110 grad: 0.0648 (0.0675) loss: 0.8350 (0.8347) time: 0.1479 data: 0.0560 max mem: 9390 +Train: [26] [3000/6250] eta: 0:09:17 lr: 0.000110 grad: 0.0657 (0.0675) loss: 0.8352 (0.8347) time: 0.1805 data: 0.0901 max mem: 9390 +Train: [26] [3100/6250] eta: 0:09:00 lr: 0.000110 grad: 0.0661 (0.0675) loss: 0.8341 (0.8348) time: 0.1616 data: 0.0714 max mem: 9390 +Train: [26] [3200/6250] eta: 0:08:42 lr: 0.000110 grad: 0.0662 (0.0675) loss: 0.8341 (0.8348) time: 0.1673 data: 0.0811 max mem: 9390 +Train: [26] [3300/6250] eta: 0:08:25 lr: 0.000110 grad: 0.0632 (0.0675) loss: 0.8404 (0.8347) time: 0.1606 data: 0.0777 max mem: 9390 +Train: [26] [3400/6250] eta: 0:08:07 lr: 0.000110 grad: 0.0624 (0.0675) loss: 0.8379 (0.8347) time: 0.1758 data: 0.0915 max mem: 9390 +Train: [26] [3500/6250] eta: 0:07:50 lr: 0.000110 grad: 0.0642 (0.0675) loss: 0.8380 (0.8348) time: 0.1657 data: 0.0692 max mem: 9390 +Train: [26] [3600/6250] eta: 0:07:32 lr: 0.000110 grad: 0.0631 (0.0674) loss: 0.8377 (0.8349) time: 0.1476 data: 0.0591 max mem: 9390 +Train: [26] [3700/6250] eta: 0:07:15 lr: 0.000110 grad: 0.0664 (0.0674) loss: 0.8381 (0.8349) time: 0.1714 data: 0.0825 max mem: 9390 +Train: [26] [3800/6250] eta: 0:06:57 lr: 0.000110 grad: 0.0651 (0.0674) loss: 0.8348 (0.8350) time: 0.1440 data: 0.0470 max mem: 9390 +Train: [26] [3900/6250] eta: 0:06:40 lr: 0.000110 grad: 0.0582 (0.0673) loss: 0.8376 (0.8351) time: 0.1732 data: 0.0898 max mem: 9390 +Train: [26] [4000/6250] eta: 0:06:23 lr: 0.000110 grad: 0.0646 (0.0674) loss: 0.8412 (0.8351) time: 0.1801 data: 0.0907 max mem: 9390 +Train: [26] [4100/6250] eta: 0:06:06 lr: 0.000110 grad: 0.0668 (0.0673) loss: 0.8363 (0.8352) time: 0.1653 data: 0.0823 max mem: 9390 +Train: [26] [4200/6250] eta: 0:05:48 lr: 0.000110 grad: 0.0650 (0.0674) loss: 0.8364 (0.8353) time: 0.1633 data: 0.0777 max mem: 9390 +Train: [26] [4300/6250] eta: 0:05:31 lr: 0.000110 grad: 0.0668 (0.0675) loss: 0.8353 (0.8353) time: 0.1618 data: 0.0734 max mem: 9390 +Train: [26] [4400/6250] eta: 0:05:14 lr: 0.000110 grad: 0.0663 (0.0675) loss: 0.8360 (0.8354) time: 0.1857 data: 0.1007 max mem: 9390 +Train: [26] [4500/6250] eta: 0:04:57 lr: 0.000110 grad: 0.0655 (0.0675) loss: 0.8362 (0.8354) time: 0.1576 data: 0.0700 max mem: 9390 +Train: [26] [4600/6250] eta: 0:04:40 lr: 0.000110 grad: 0.0671 (0.0676) loss: 0.8313 (0.8354) time: 0.1614 data: 0.0719 max mem: 9390 +Train: [26] [4700/6250] eta: 0:04:22 lr: 0.000110 grad: 0.0677 (0.0676) loss: 0.8372 (0.8354) time: 0.1675 data: 0.0820 max mem: 9390 +Train: [26] [4800/6250] eta: 0:04:05 lr: 0.000109 grad: 0.0720 (0.0676) loss: 0.8345 (0.8354) time: 0.1650 data: 0.0797 max mem: 9390 +Train: [26] [4900/6250] eta: 0:03:48 lr: 0.000109 grad: 0.0651 (0.0677) loss: 0.8323 (0.8353) time: 0.1629 data: 0.0737 max mem: 9390 +Train: [26] [5000/6250] eta: 0:03:32 lr: 0.000109 grad: 0.0646 (0.0677) loss: 0.8314 (0.8352) time: 0.1989 data: 0.1089 max mem: 9390 +Train: [26] [5100/6250] eta: 0:03:15 lr: 0.000109 grad: 0.0689 (0.0677) loss: 0.8339 (0.8352) time: 0.1884 data: 0.1011 max mem: 9390 +Train: [26] [5200/6250] eta: 0:02:58 lr: 0.000109 grad: 0.0667 (0.0678) loss: 0.8300 (0.8351) time: 0.1844 data: 0.1002 max mem: 9390 +Train: [26] [5300/6250] eta: 0:02:40 lr: 0.000109 grad: 0.0691 (0.0678) loss: 0.8329 (0.8350) time: 0.1597 data: 0.0796 max mem: 9390 +Train: [26] [5400/6250] eta: 0:02:23 lr: 0.000109 grad: 0.0701 (0.0679) loss: 0.8283 (0.8349) time: 0.1688 data: 0.0810 max mem: 9390 +Train: [26] [5500/6250] eta: 0:02:06 lr: 0.000109 grad: 0.0668 (0.0680) loss: 0.8271 (0.8348) time: 0.1414 data: 0.0580 max mem: 9390 +Train: [26] [5600/6250] eta: 0:01:50 lr: 0.000109 grad: 0.0661 (0.0680) loss: 0.8340 (0.8347) time: 0.1513 data: 0.0610 max mem: 9390 +Train: [26] [5700/6250] eta: 0:01:33 lr: 0.000109 grad: 0.0702 (0.0680) loss: 0.8286 (0.8347) time: 0.1756 data: 0.0827 max mem: 9390 +Train: [26] [5800/6250] eta: 0:01:16 lr: 0.000109 grad: 0.0646 (0.0680) loss: 0.8282 (0.8347) time: 0.1488 data: 0.0586 max mem: 9390 +Train: [26] [5900/6250] eta: 0:00:59 lr: 0.000109 grad: 0.0641 (0.0680) loss: 0.8304 (0.8346) time: 0.1483 data: 0.0639 max mem: 9390 +Train: [26] [6000/6250] eta: 0:00:42 lr: 0.000109 grad: 0.0680 (0.0680) loss: 0.8328 (0.8346) time: 0.1730 data: 0.0865 max mem: 9390 +Train: [26] [6100/6250] eta: 0:00:25 lr: 0.000109 grad: 0.0680 (0.0681) loss: 0.8275 (0.8345) time: 0.1645 data: 0.0772 max mem: 9390 +Train: [26] [6200/6250] eta: 0:00:08 lr: 0.000109 grad: 0.0698 (0.0681) loss: 0.8310 (0.8345) time: 0.1707 data: 0.0775 max mem: 9390 +Train: [26] [6249/6250] eta: 0:00:00 lr: 0.000109 grad: 0.0679 (0.0681) loss: 0.8277 (0.8345) time: 0.1664 data: 0.0718 max mem: 9390 +Train: [26] Total time: 0:17:42 (0.1699 s / it) +Averaged stats: lr: 0.000109 grad: 0.0679 (0.0681) loss: 0.8277 (0.8345) +Eval (hcp-train-subset): [26] [ 0/62] eta: 0:04:54 loss: 0.8539 (0.8539) time: 4.7450 data: 4.7138 max mem: 9390 +Eval (hcp-train-subset): [26] [61/62] eta: 0:00:00 loss: 0.8419 (0.8430) time: 0.1326 data: 0.1072 max mem: 9390 +Eval (hcp-train-subset): [26] Total time: 0:00:13 (0.2171 s / it) +Averaged stats (hcp-train-subset): loss: 0.8419 (0.8430) +Eval (hcp-val): [26] [ 0/62] eta: 0:04:35 loss: 0.8355 (0.8355) time: 4.4394 data: 4.4098 max mem: 9390 +Eval (hcp-val): [26] [61/62] eta: 0:00:00 loss: 0.8370 (0.8389) time: 0.1434 data: 0.1147 max mem: 9390 +Eval (hcp-val): [26] Total time: 0:00:13 (0.2218 s / it) +Averaged stats (hcp-val): loss: 0.8370 (0.8389) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +Train: [27] [ 0/6250] eta: 10:18:00 lr: 0.000109 grad: 0.0692 (0.0692) loss: 0.8544 (0.8544) time: 5.9328 data: 5.8098 max mem: 9390 +Train: [27] [ 100/6250] eta: 0:22:06 lr: 0.000109 grad: 0.0665 (0.0738) loss: 0.8412 (0.8417) time: 0.1670 data: 0.0760 max mem: 9390 +Train: [27] [ 200/6250] eta: 0:19:19 lr: 0.000109 grad: 0.0690 (0.0713) loss: 0.8307 (0.8398) time: 0.1846 data: 0.0975 max mem: 9390 +Train: [27] [ 300/6250] eta: 0:18:30 lr: 0.000109 grad: 0.0637 (0.0701) loss: 0.8340 (0.8384) time: 0.1787 data: 0.0841 max mem: 9390 +Train: [27] [ 400/6250] eta: 0:18:02 lr: 0.000109 grad: 0.0640 (0.0699) loss: 0.8386 (0.8374) time: 0.1774 data: 0.0908 max mem: 9390 +Train: [27] [ 500/6250] eta: 0:17:27 lr: 0.000109 grad: 0.0624 (0.0693) loss: 0.8334 (0.8366) time: 0.1619 data: 0.0730 max mem: 9390 +Train: [27] [ 600/6250] eta: 0:17:28 lr: 0.000109 grad: 0.0666 (0.0689) loss: 0.8352 (0.8360) time: 0.2394 data: 0.1385 max mem: 9390 +Train: [27] [ 700/6250] eta: 0:17:34 lr: 0.000109 grad: 0.0627 (0.0684) loss: 0.8381 (0.8361) time: 0.2043 data: 0.1060 max mem: 9390 +Train: [27] [ 800/6250] eta: 0:17:05 lr: 0.000109 grad: 0.0611 (0.0682) loss: 0.8365 (0.8361) time: 0.1510 data: 0.0690 max mem: 9390 +Train: [27] [ 900/6250] eta: 0:16:41 lr: 0.000109 grad: 0.0649 (0.0679) loss: 0.8351 (0.8360) time: 0.1735 data: 0.0844 max mem: 9390 +Train: [27] [1000/6250] eta: 0:16:12 lr: 0.000109 grad: 0.0652 (0.0675) loss: 0.8352 (0.8363) time: 0.1803 data: 0.0919 max mem: 9390 +Train: [27] [1100/6250] eta: 0:15:45 lr: 0.000109 grad: 0.0614 (0.0673) loss: 0.8375 (0.8365) time: 0.1548 data: 0.0742 max mem: 9390 +Train: [27] [1200/6250] eta: 0:15:20 lr: 0.000109 grad: 0.0637 (0.0673) loss: 0.8328 (0.8364) time: 0.1677 data: 0.0804 max mem: 9390 +Train: [27] [1300/6250] eta: 0:15:00 lr: 0.000109 grad: 0.0655 (0.0671) loss: 0.8366 (0.8365) time: 0.2267 data: 0.1454 max mem: 9390 +Train: [27] [1400/6250] eta: 0:14:35 lr: 0.000109 grad: 0.0668 (0.0671) loss: 0.8360 (0.8365) time: 0.1763 data: 0.0919 max mem: 9390 +Train: [27] [1500/6250] eta: 0:14:14 lr: 0.000109 grad: 0.0637 (0.0670) loss: 0.8347 (0.8365) time: 0.1810 data: 0.1014 max mem: 9390 +Train: [27] [1600/6250] eta: 0:13:52 lr: 0.000109 grad: 0.0655 (0.0670) loss: 0.8374 (0.8364) time: 0.1577 data: 0.0710 max mem: 9390 +Train: [27] [1700/6250] eta: 0:13:32 lr: 0.000109 grad: 0.0672 (0.0671) loss: 0.8374 (0.8364) time: 0.1514 data: 0.0601 max mem: 9390 +Train: [27] [1800/6250] eta: 0:13:13 lr: 0.000109 grad: 0.0683 (0.0674) loss: 0.8306 (0.8363) time: 0.1476 data: 0.0607 max mem: 9390 +Train: [27] [1900/6250] eta: 0:13:00 lr: 0.000109 grad: 0.0708 (0.0675) loss: 0.8371 (0.8362) time: 0.2455 data: 0.1415 max mem: 9390 +Train: [27] [2000/6250] eta: 0:12:38 lr: 0.000109 grad: 0.0640 (0.0675) loss: 0.8301 (0.8361) time: 0.1583 data: 0.0749 max mem: 9390 +Train: [27] [2100/6250] eta: 0:12:22 lr: 0.000109 grad: 0.0668 (0.0675) loss: 0.8353 (0.8361) time: 0.1678 data: 0.0921 max mem: 9390 +Train: [27] [2200/6250] eta: 0:12:00 lr: 0.000109 grad: 0.0678 (0.0675) loss: 0.8386 (0.8360) time: 0.1744 data: 0.0876 max mem: 9390 +Train: [27] [2300/6250] eta: 0:11:41 lr: 0.000109 grad: 0.0643 (0.0676) loss: 0.8389 (0.8359) time: 0.1840 data: 0.0960 max mem: 9390 +Train: [27] [2400/6250] eta: 0:11:19 lr: 0.000109 grad: 0.0661 (0.0676) loss: 0.8374 (0.8358) time: 0.1407 data: 0.0605 max mem: 9390 +Train: [27] [2500/6250] eta: 0:11:01 lr: 0.000109 grad: 0.0680 (0.0677) loss: 0.8326 (0.8356) time: 0.1719 data: 0.0844 max mem: 9390 +Train: [27] [2600/6250] eta: 0:10:42 lr: 0.000109 grad: 0.0670 (0.0678) loss: 0.8330 (0.8355) time: 0.1744 data: 0.0826 max mem: 9390 +Train: [27] [2700/6250] eta: 0:10:23 lr: 0.000109 grad: 0.0713 (0.0679) loss: 0.8305 (0.8353) time: 0.1672 data: 0.0784 max mem: 9390 +Train: [27] [2800/6250] eta: 0:10:03 lr: 0.000109 grad: 0.0685 (0.0680) loss: 0.8280 (0.8351) time: 0.1572 data: 0.0673 max mem: 9390 +Train: [27] [2900/6250] eta: 0:09:45 lr: 0.000109 grad: 0.0634 (0.0680) loss: 0.8345 (0.8350) time: 0.1951 data: 0.1022 max mem: 9390 +Train: [27] [3000/6250] eta: 0:09:26 lr: 0.000109 grad: 0.0651 (0.0680) loss: 0.8343 (0.8348) time: 0.1717 data: 0.0771 max mem: 9390 +Train: [27] [3100/6250] eta: 0:09:08 lr: 0.000108 grad: 0.0738 (0.0681) loss: 0.8325 (0.8347) time: 0.1889 data: 0.0886 max mem: 9390 +Train: [27] [3200/6250] eta: 0:08:52 lr: 0.000108 grad: 0.0637 (0.0681) loss: 0.8354 (0.8346) time: 0.1832 data: 0.0810 max mem: 9390 +Train: [27] [3300/6250] eta: 0:08:33 lr: 0.000108 grad: 0.0610 (0.0681) loss: 0.8369 (0.8345) time: 0.1654 data: 0.0699 max mem: 9390 +Train: [27] [3400/6250] eta: 0:08:15 lr: 0.000108 grad: 0.0668 (0.0682) loss: 0.8277 (0.8345) time: 0.1605 data: 0.0655 max mem: 9390 +Train: [27] [3500/6250] eta: 0:07:57 lr: 0.000108 grad: 0.0672 (0.0683) loss: 0.8324 (0.8343) time: 0.1748 data: 0.0804 max mem: 9390 +Train: [27] [3600/6250] eta: 0:07:40 lr: 0.000108 grad: 0.0678 (0.0683) loss: 0.8283 (0.8342) time: 0.1834 data: 0.0963 max mem: 9390 +Train: [27] [3700/6250] eta: 0:07:22 lr: 0.000108 grad: 0.0669 (0.0683) loss: 0.8264 (0.8342) time: 0.1639 data: 0.0754 max mem: 9390 +Train: [27] [3800/6250] eta: 0:07:05 lr: 0.000108 grad: 0.0670 (0.0683) loss: 0.8330 (0.8341) time: 0.1624 data: 0.0740 max mem: 9390 +Train: [27] [3900/6250] eta: 0:06:48 lr: 0.000108 grad: 0.0701 (0.0684) loss: 0.8368 (0.8341) time: 0.1708 data: 0.0805 max mem: 9390 +Train: [27] [4000/6250] eta: 0:06:30 lr: 0.000108 grad: 0.0678 (0.0684) loss: 0.8297 (0.8340) time: 0.1580 data: 0.0751 max mem: 9390 +Train: [27] [4100/6250] eta: 0:06:12 lr: 0.000108 grad: 0.0659 (0.0684) loss: 0.8322 (0.8340) time: 0.1693 data: 0.0869 max mem: 9390 +Train: [27] [4200/6250] eta: 0:05:55 lr: 0.000108 grad: 0.0664 (0.0684) loss: 0.8314 (0.8339) time: 0.1666 data: 0.0722 max mem: 9390 +Train: [27] [4300/6250] eta: 0:05:37 lr: 0.000108 grad: 0.0694 (0.0685) loss: 0.8293 (0.8339) time: 0.1642 data: 0.0745 max mem: 9390 +Train: [27] [4400/6250] eta: 0:05:20 lr: 0.000108 grad: 0.0693 (0.0686) loss: 0.8297 (0.8338) time: 0.1590 data: 0.0689 max mem: 9390 +Train: [27] [4500/6250] eta: 0:05:02 lr: 0.000108 grad: 0.0706 (0.0686) loss: 0.8314 (0.8338) time: 0.1438 data: 0.0560 max mem: 9390 +Train: [27] [4600/6250] eta: 0:04:44 lr: 0.000108 grad: 0.0667 (0.0686) loss: 0.8316 (0.8337) time: 0.1807 data: 0.0958 max mem: 9390 +Train: [27] [4700/6250] eta: 0:04:27 lr: 0.000108 grad: 0.0682 (0.0687) loss: 0.8329 (0.8337) time: 0.1557 data: 0.0608 max mem: 9390 +Train: [27] [4800/6250] eta: 0:04:09 lr: 0.000108 grad: 0.0666 (0.0687) loss: 0.8369 (0.8337) time: 0.1821 data: 0.0984 max mem: 9390 +Train: [27] [4900/6250] eta: 0:03:52 lr: 0.000108 grad: 0.0674 (0.0688) loss: 0.8350 (0.8337) time: 0.1619 data: 0.0748 max mem: 9390 +Train: [27] [5000/6250] eta: 0:03:35 lr: 0.000108 grad: 0.0690 (0.0689) loss: 0.8333 (0.8337) time: 0.1583 data: 0.0734 max mem: 9390 +Train: [27] [5100/6250] eta: 0:03:17 lr: 0.000108 grad: 0.0667 (0.0690) loss: 0.8310 (0.8336) time: 0.1731 data: 0.0875 max mem: 9390 +Train: [27] [5200/6250] eta: 0:03:00 lr: 0.000108 grad: 0.0701 (0.0691) loss: 0.8317 (0.8336) time: 0.1824 data: 0.1023 max mem: 9390 +Train: [27] [5300/6250] eta: 0:02:43 lr: 0.000108 grad: 0.0730 (0.0691) loss: 0.8331 (0.8335) time: 0.1481 data: 0.0633 max mem: 9390 +Train: [27] [5400/6250] eta: 0:02:25 lr: 0.000108 grad: 0.0663 (0.0691) loss: 0.8302 (0.8335) time: 0.1606 data: 0.0736 max mem: 9390 +Train: [27] [5500/6250] eta: 0:02:08 lr: 0.000108 grad: 0.0664 (0.0692) loss: 0.8325 (0.8335) time: 0.1608 data: 0.0747 max mem: 9390 +Train: [27] [5600/6250] eta: 0:01:51 lr: 0.000108 grad: 0.0683 (0.0692) loss: 0.8319 (0.8335) time: 0.1840 data: 0.0894 max mem: 9390 +Train: [27] [5700/6250] eta: 0:01:34 lr: 0.000108 grad: 0.0699 (0.0692) loss: 0.8335 (0.8334) time: 0.1611 data: 0.0649 max mem: 9390 +Train: [27] [5800/6250] eta: 0:01:17 lr: 0.000108 grad: 0.0709 (0.0693) loss: 0.8286 (0.8334) time: 0.1584 data: 0.0668 max mem: 9390 +Train: [27] [5900/6250] eta: 0:00:59 lr: 0.000108 grad: 0.0680 (0.0693) loss: 0.8332 (0.8333) time: 0.1510 data: 0.0661 max mem: 9390 +Train: [27] [6000/6250] eta: 0:00:42 lr: 0.000108 grad: 0.0681 (0.0694) loss: 0.8261 (0.8333) time: 0.1487 data: 0.0583 max mem: 9390 +Train: [27] [6100/6250] eta: 0:00:25 lr: 0.000108 grad: 0.0706 (0.0694) loss: 0.8318 (0.8333) time: 0.1569 data: 0.0684 max mem: 9390 +Train: [27] [6200/6250] eta: 0:00:08 lr: 0.000108 grad: 0.0699 (0.0695) loss: 0.8298 (0.8332) time: 0.1806 data: 0.1016 max mem: 9390 +Train: [27] [6249/6250] eta: 0:00:00 lr: 0.000108 grad: 0.0670 (0.0695) loss: 0.8331 (0.8332) time: 0.1583 data: 0.0629 max mem: 9390 +Train: [27] Total time: 0:17:55 (0.1721 s / it) +Averaged stats: lr: 0.000108 grad: 0.0670 (0.0695) loss: 0.8331 (0.8332) +Eval (hcp-train-subset): [27] [ 0/62] eta: 0:05:18 loss: 0.8542 (0.8542) time: 5.1428 data: 5.1128 max mem: 9390 +Eval (hcp-train-subset): [27] [61/62] eta: 0:00:00 loss: 0.8424 (0.8440) time: 0.1284 data: 0.1033 max mem: 9390 +Eval (hcp-train-subset): [27] Total time: 0:00:14 (0.2317 s / it) +Averaged stats (hcp-train-subset): loss: 0.8424 (0.8440) +Eval (hcp-val): [27] [ 0/62] eta: 0:04:29 loss: 0.8329 (0.8329) time: 4.3401 data: 4.3103 max mem: 9390 +Eval (hcp-val): [27] [61/62] eta: 0:00:00 loss: 0.8388 (0.8394) time: 0.1311 data: 0.1057 max mem: 9390 +Eval (hcp-val): [27] Total time: 0:00:13 (0.2217 s / it) +Averaged stats (hcp-val): loss: 0.8388 (0.8394) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +Train: [28] [ 0/6250] eta: 9:42:28 lr: 0.000108 grad: 0.0493 (0.0493) loss: 0.8620 (0.8620) time: 5.5918 data: 5.4541 max mem: 9390 +Train: [28] [ 100/6250] eta: 0:22:49 lr: 0.000108 grad: 0.0750 (0.0866) loss: 0.8282 (0.8397) time: 0.1621 data: 0.0732 max mem: 9390 +Train: [28] [ 200/6250] eta: 0:19:47 lr: 0.000108 grad: 0.0706 (0.0777) loss: 0.8358 (0.8382) time: 0.1511 data: 0.0604 max mem: 9390 +Train: [28] [ 300/6250] eta: 0:18:30 lr: 0.000108 grad: 0.0629 (0.0769) loss: 0.8354 (0.8362) time: 0.1587 data: 0.0609 max mem: 9390 +Train: [28] [ 400/6250] eta: 0:17:48 lr: 0.000108 grad: 0.0653 (0.0753) loss: 0.8257 (0.8352) time: 0.1766 data: 0.0787 max mem: 9390 +Train: [28] [ 500/6250] eta: 0:17:32 lr: 0.000108 grad: 0.0627 (0.0741) loss: 0.8310 (0.8344) time: 0.1841 data: 0.1009 max mem: 9390 +Train: [28] [ 600/6250] eta: 0:17:28 lr: 0.000108 grad: 0.0676 (0.0733) loss: 0.8303 (0.8340) time: 0.1950 data: 0.0990 max mem: 9390 +Train: [28] [ 700/6250] eta: 0:17:33 lr: 0.000108 grad: 0.0695 (0.0728) loss: 0.8284 (0.8337) time: 0.2314 data: 0.1148 max mem: 9390 +Train: [28] [ 800/6250] eta: 0:17:20 lr: 0.000108 grad: 0.0669 (0.0724) loss: 0.8292 (0.8333) time: 0.1680 data: 0.0712 max mem: 9390 +Train: [28] [ 900/6250] eta: 0:16:59 lr: 0.000108 grad: 0.0694 (0.0722) loss: 0.8289 (0.8332) time: 0.1611 data: 0.0628 max mem: 9390 +Train: [28] [1000/6250] eta: 0:16:28 lr: 0.000108 grad: 0.0700 (0.0722) loss: 0.8304 (0.8331) time: 0.1901 data: 0.0941 max mem: 9390 +Train: [28] [1100/6250] eta: 0:15:59 lr: 0.000108 grad: 0.0623 (0.0719) loss: 0.8349 (0.8332) time: 0.1734 data: 0.0850 max mem: 9390 +Train: [28] [1200/6250] eta: 0:15:31 lr: 0.000108 grad: 0.0648 (0.0717) loss: 0.8385 (0.8333) time: 0.1727 data: 0.0797 max mem: 9390 +Train: [28] [1300/6250] eta: 0:15:05 lr: 0.000107 grad: 0.0665 (0.0714) loss: 0.8261 (0.8333) time: 0.1513 data: 0.0658 max mem: 9390 +Train: [28] [1400/6250] eta: 0:14:44 lr: 0.000107 grad: 0.0635 (0.0712) loss: 0.8332 (0.8334) time: 0.1802 data: 0.0896 max mem: 9390 +Train: [28] [1500/6250] eta: 0:14:19 lr: 0.000107 grad: 0.0655 (0.0709) loss: 0.8323 (0.8334) time: 0.1474 data: 0.0590 max mem: 9390 +Train: [28] [1600/6250] eta: 0:13:56 lr: 0.000107 grad: 0.0689 (0.0709) loss: 0.8232 (0.8333) time: 0.1453 data: 0.0542 max mem: 9390 +Train: [28] [1700/6250] eta: 0:13:37 lr: 0.000107 grad: 0.0624 (0.0706) loss: 0.8295 (0.8333) time: 0.1787 data: 0.0876 max mem: 9390 +Train: [28] [1800/6250] eta: 0:13:13 lr: 0.000107 grad: 0.0691 (0.0706) loss: 0.8315 (0.8332) time: 0.1289 data: 0.0344 max mem: 9390 +Train: [28] [1900/6250] eta: 0:12:53 lr: 0.000107 grad: 0.0660 (0.0707) loss: 0.8319 (0.8333) time: 0.1581 data: 0.0711 max mem: 9390 +Train: [28] [2000/6250] eta: 0:12:32 lr: 0.000107 grad: 0.0669 (0.0706) loss: 0.8294 (0.8332) time: 0.1517 data: 0.0663 max mem: 9390 +Train: [28] [2100/6250] eta: 0:12:12 lr: 0.000107 grad: 0.0713 (0.0705) loss: 0.8270 (0.8332) time: 0.1720 data: 0.0875 max mem: 9390 +Train: [28] [2200/6250] eta: 0:11:53 lr: 0.000107 grad: 0.0649 (0.0705) loss: 0.8309 (0.8331) time: 0.1709 data: 0.0778 max mem: 9390 +Train: [28] [2300/6250] eta: 0:11:33 lr: 0.000107 grad: 0.0636 (0.0704) loss: 0.8283 (0.8331) time: 0.1671 data: 0.0757 max mem: 9390 +Train: [28] [2400/6250] eta: 0:11:15 lr: 0.000107 grad: 0.0705 (0.0704) loss: 0.8202 (0.8329) time: 0.1833 data: 0.0955 max mem: 9390 +Train: [28] [2500/6250] eta: 0:10:55 lr: 0.000107 grad: 0.0736 (0.0705) loss: 0.8291 (0.8328) time: 0.1672 data: 0.0843 max mem: 9390 +Train: [28] [2600/6250] eta: 0:10:35 lr: 0.000107 grad: 0.0717 (0.0706) loss: 0.8320 (0.8327) time: 0.1601 data: 0.0792 max mem: 9390 +Train: [28] [2700/6250] eta: 0:10:18 lr: 0.000107 grad: 0.0681 (0.0706) loss: 0.8305 (0.8327) time: 0.1834 data: 0.0935 max mem: 9390 +Train: [28] [2800/6250] eta: 0:09:58 lr: 0.000107 grad: 0.0727 (0.0708) loss: 0.8400 (0.8326) time: 0.1543 data: 0.0712 max mem: 9390 +Train: [28] [2900/6250] eta: 0:09:41 lr: 0.000107 grad: 0.0701 (0.0709) loss: 0.8329 (0.8326) time: 0.1980 data: 0.1073 max mem: 9390 +Train: [28] [3000/6250] eta: 0:09:22 lr: 0.000107 grad: 0.0624 (0.0710) loss: 0.8354 (0.8325) time: 0.1661 data: 0.0782 max mem: 9390 +Train: [28] [3100/6250] eta: 0:09:05 lr: 0.000107 grad: 0.0688 (0.0710) loss: 0.8336 (0.8325) time: 0.1886 data: 0.1087 max mem: 9390 +Train: [28] [3200/6250] eta: 0:08:46 lr: 0.000107 grad: 0.0670 (0.0710) loss: 0.8353 (0.8324) time: 0.1922 data: 0.1075 max mem: 9390 +Train: [28] [3300/6250] eta: 0:08:29 lr: 0.000107 grad: 0.0685 (0.0710) loss: 0.8351 (0.8323) time: 0.1450 data: 0.0576 max mem: 9390 +Train: [28] [3400/6250] eta: 0:08:11 lr: 0.000107 grad: 0.0652 (0.0710) loss: 0.8319 (0.8323) time: 0.1515 data: 0.0696 max mem: 9390 +Train: [28] [3500/6250] eta: 0:07:53 lr: 0.000107 grad: 0.0688 (0.0710) loss: 0.8247 (0.8322) time: 0.1787 data: 0.0912 max mem: 9390 +Train: [28] [3600/6250] eta: 0:07:35 lr: 0.000107 grad: 0.0691 (0.0711) loss: 0.8295 (0.8321) time: 0.1341 data: 0.0574 max mem: 9390 +Train: [28] [3700/6250] eta: 0:07:17 lr: 0.000107 grad: 0.0698 (0.0711) loss: 0.8299 (0.8320) time: 0.1635 data: 0.0719 max mem: 9390 +Train: [28] [3800/6250] eta: 0:07:00 lr: 0.000107 grad: 0.0685 (0.0711) loss: 0.8331 (0.8320) time: 0.1850 data: 0.0954 max mem: 9390 +Train: [28] [3900/6250] eta: 0:06:43 lr: 0.000107 grad: 0.0689 (0.0712) loss: 0.8286 (0.8320) time: 0.1752 data: 0.0962 max mem: 9390 +Train: [28] [4000/6250] eta: 0:06:25 lr: 0.000107 grad: 0.0735 (0.0712) loss: 0.8328 (0.8320) time: 0.1529 data: 0.0640 max mem: 9390 +Train: [28] [4100/6250] eta: 0:06:08 lr: 0.000107 grad: 0.0710 (0.0712) loss: 0.8263 (0.8320) time: 0.1573 data: 0.0683 max mem: 9390 +Train: [28] [4200/6250] eta: 0:05:50 lr: 0.000107 grad: 0.0704 (0.0712) loss: 0.8277 (0.8319) time: 0.1751 data: 0.0889 max mem: 9390 +Train: [28] [4300/6250] eta: 0:05:33 lr: 0.000107 grad: 0.0682 (0.0712) loss: 0.8308 (0.8319) time: 0.1658 data: 0.0777 max mem: 9390 +Train: [28] [4400/6250] eta: 0:05:16 lr: 0.000107 grad: 0.0752 (0.0714) loss: 0.8240 (0.8318) time: 0.1587 data: 0.0699 max mem: 9390 +Train: [28] [4500/6250] eta: 0:04:58 lr: 0.000107 grad: 0.0724 (0.0714) loss: 0.8315 (0.8318) time: 0.1633 data: 0.0794 max mem: 9390 +Train: [28] [4600/6250] eta: 0:04:41 lr: 0.000107 grad: 0.0669 (0.0715) loss: 0.8376 (0.8318) time: 0.1408 data: 0.0547 max mem: 9390 +Train: [28] [4700/6250] eta: 0:04:24 lr: 0.000107 grad: 0.0711 (0.0715) loss: 0.8300 (0.8317) time: 0.1522 data: 0.0685 max mem: 9390 +Train: [28] [4800/6250] eta: 0:04:07 lr: 0.000107 grad: 0.0707 (0.0716) loss: 0.8315 (0.8317) time: 0.1555 data: 0.0731 max mem: 9390 +Train: [28] [4900/6250] eta: 0:03:50 lr: 0.000107 grad: 0.0693 (0.0716) loss: 0.8278 (0.8316) time: 0.1561 data: 0.0677 max mem: 9390 +Train: [28] [5000/6250] eta: 0:03:32 lr: 0.000107 grad: 0.0678 (0.0716) loss: 0.8321 (0.8316) time: 0.1937 data: 0.1132 max mem: 9390 +Train: [28] [5100/6250] eta: 0:03:15 lr: 0.000107 grad: 0.0684 (0.0716) loss: 0.8360 (0.8316) time: 0.1995 data: 0.1164 max mem: 9390 +Train: [28] [5200/6250] eta: 0:02:58 lr: 0.000107 grad: 0.0714 (0.0717) loss: 0.8270 (0.8316) time: 0.1698 data: 0.0895 max mem: 9390 +Train: [28] [5300/6250] eta: 0:02:41 lr: 0.000107 grad: 0.0724 (0.0717) loss: 0.8267 (0.8316) time: 0.1521 data: 0.0701 max mem: 9390 +Train: [28] [5400/6250] eta: 0:02:24 lr: 0.000107 grad: 0.0698 (0.0717) loss: 0.8342 (0.8316) time: 0.1552 data: 0.0615 max mem: 9390 +Train: [28] [5500/6250] eta: 0:02:07 lr: 0.000107 grad: 0.0715 (0.0718) loss: 0.8387 (0.8316) time: 0.1671 data: 0.0818 max mem: 9390 +Train: [28] [5600/6250] eta: 0:01:50 lr: 0.000106 grad: 0.0692 (0.0718) loss: 0.8319 (0.8316) time: 0.1591 data: 0.0713 max mem: 9390 +Train: [28] [5700/6250] eta: 0:01:33 lr: 0.000106 grad: 0.0692 (0.0718) loss: 0.8291 (0.8316) time: 0.1680 data: 0.0834 max mem: 9390 +Train: [28] [5800/6250] eta: 0:01:16 lr: 0.000106 grad: 0.0698 (0.0718) loss: 0.8328 (0.8316) time: 0.1837 data: 0.1068 max mem: 9390 +Train: [28] [5900/6250] eta: 0:00:59 lr: 0.000106 grad: 0.0704 (0.0718) loss: 0.8296 (0.8316) time: 0.1801 data: 0.0895 max mem: 9390 +Train: [28] [6000/6250] eta: 0:00:42 lr: 0.000106 grad: 0.0693 (0.0718) loss: 0.8365 (0.8316) time: 0.2252 data: 0.1441 max mem: 9390 +Train: [28] [6100/6250] eta: 0:00:25 lr: 0.000106 grad: 0.0687 (0.0719) loss: 0.8306 (0.8316) time: 0.1498 data: 0.0643 max mem: 9390 +Train: [28] [6200/6250] eta: 0:00:08 lr: 0.000106 grad: 0.0704 (0.0719) loss: 0.8298 (0.8316) time: 0.1630 data: 0.0778 max mem: 9390 +Train: [28] [6249/6250] eta: 0:00:00 lr: 0.000106 grad: 0.0740 (0.0719) loss: 0.8306 (0.8316) time: 0.1598 data: 0.0794 max mem: 9390 +Train: [28] Total time: 0:17:46 (0.1706 s / it) +Averaged stats: lr: 0.000106 grad: 0.0740 (0.0719) loss: 0.8306 (0.8316) +Eval (hcp-train-subset): [28] [ 0/62] eta: 0:05:19 loss: 0.8585 (0.8585) time: 5.1612 data: 5.0904 max mem: 9390 +Eval (hcp-train-subset): [28] [61/62] eta: 0:00:00 loss: 0.8433 (0.8439) time: 0.1325 data: 0.1058 max mem: 9390 +Eval (hcp-train-subset): [28] Total time: 0:00:14 (0.2314 s / it) +Averaged stats (hcp-train-subset): loss: 0.8433 (0.8439) +Eval (hcp-val): [28] [ 0/62] eta: 0:05:47 loss: 0.8377 (0.8377) time: 5.6002 data: 5.5659 max mem: 9390 +Eval (hcp-val): [28] [61/62] eta: 0:00:00 loss: 0.8396 (0.8401) time: 0.1348 data: 0.1099 max mem: 9390 +Eval (hcp-val): [28] Total time: 0:00:13 (0.2234 s / it) +Averaged stats (hcp-val): loss: 0.8396 (0.8401) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +Train: [29] [ 0/6250] eta: 8:35:15 lr: 0.000106 grad: nan (nan) loss: 0.8204 (0.8204) time: 4.9465 data: 4.6764 max mem: 9390 +Train: [29] [ 100/6250] eta: 0:23:45 lr: 0.000106 grad: 0.0673 (0.0772) loss: 0.8318 (0.8341) time: 0.1711 data: 0.0849 max mem: 9390 +Train: [29] [ 200/6250] eta: 0:20:38 lr: 0.000106 grad: 0.0696 (0.0730) loss: 0.8218 (0.8307) time: 0.2112 data: 0.1217 max mem: 9390 +Train: [29] [ 300/6250] eta: 0:19:03 lr: 0.000106 grad: 0.0684 (0.0732) loss: 0.8285 (0.8298) time: 0.1530 data: 0.0590 max mem: 9390 +Train: [29] [ 400/6250] eta: 0:18:05 lr: 0.000106 grad: 0.0667 (0.0730) loss: 0.8310 (0.8300) time: 0.1569 data: 0.0707 max mem: 9390 +Train: [29] [ 500/6250] eta: 0:17:25 lr: 0.000106 grad: 0.0710 (0.0729) loss: 0.8308 (0.8302) time: 0.1855 data: 0.1070 max mem: 9390 +Train: [29] [ 600/6250] eta: 0:17:11 lr: 0.000106 grad: 0.0691 (0.0730) loss: 0.8271 (0.8305) time: 0.2063 data: 0.1199 max mem: 9390 +Train: [29] [ 700/6250] eta: 0:16:44 lr: 0.000106 grad: 0.0636 (0.0725) loss: 0.8388 (0.8310) time: 0.1974 data: 0.1254 max mem: 9390 +Train: [29] [ 800/6250] eta: 0:16:25 lr: 0.000106 grad: 0.0661 (0.0720) loss: 0.8377 (0.8314) time: 0.1678 data: 0.0742 max mem: 9390 +Train: [29] [ 900/6250] eta: 0:16:01 lr: 0.000106 grad: 0.0672 (0.0720) loss: 0.8363 (0.8318) time: 0.1714 data: 0.0781 max mem: 9390 +Train: [29] [1000/6250] eta: 0:15:40 lr: 0.000106 grad: 0.0651 (0.0714) loss: 0.8348 (0.8322) time: 0.1545 data: 0.0677 max mem: 9390 +Train: [29] [1100/6250] eta: 0:15:16 lr: 0.000106 grad: 0.0678 (0.0716) loss: 0.8337 (0.8322) time: 0.1702 data: 0.0829 max mem: 9390 +Train: [29] [1200/6250] eta: 0:14:51 lr: 0.000106 grad: 0.0693 (0.0714) loss: 0.8338 (0.8322) time: 0.1607 data: 0.0783 max mem: 9390 +Train: [29] [1300/6250] eta: 0:14:27 lr: 0.000106 grad: 0.0658 (0.0712) loss: 0.8276 (0.8323) time: 0.1706 data: 0.0780 max mem: 9390 +Train: [29] [1400/6250] eta: 0:14:04 lr: 0.000106 grad: 0.0721 (0.0711) loss: 0.8317 (0.8323) time: 0.1448 data: 0.0401 max mem: 9390 +Train: [29] [1500/6250] eta: 0:13:46 lr: 0.000106 grad: 0.0636 (0.0711) loss: 0.8369 (0.8322) time: 0.1699 data: 0.0730 max mem: 9390 +Train: [29] [1600/6250] eta: 0:13:24 lr: 0.000106 grad: 0.0675 (0.0711) loss: 0.8330 (0.8321) time: 0.1427 data: 0.0428 max mem: 9390 +Train: [29] [1700/6250] eta: 0:13:05 lr: 0.000106 grad: 0.0728 (0.0712) loss: 0.8262 (0.8318) time: 0.1625 data: 0.0667 max mem: 9390 +Train: [29] [1800/6250] eta: 0:12:46 lr: 0.000106 grad: 0.0676 (0.0711) loss: 0.8288 (0.8317) time: 0.1319 data: 0.0393 max mem: 9390 +Train: [29] [1900/6250] eta: 0:12:27 lr: 0.000106 grad: 0.0701 (0.0712) loss: 0.8338 (0.8316) time: 0.1564 data: 0.0658 max mem: 9390 +Train: [29] [2000/6250] eta: 0:12:11 lr: 0.000106 grad: 0.0674 (0.0712) loss: 0.8347 (0.8315) time: 0.1792 data: 0.0887 max mem: 9390 +Train: [29] [2100/6250] eta: 0:11:53 lr: 0.000106 grad: 0.0695 (0.0712) loss: 0.8290 (0.8314) time: 0.1683 data: 0.0836 max mem: 9390 +Train: [29] [2200/6250] eta: 0:11:35 lr: 0.000106 grad: 0.0669 (0.0711) loss: 0.8288 (0.8315) time: 0.1639 data: 0.0678 max mem: 9390 +Train: [29] [2300/6250] eta: 0:11:19 lr: 0.000106 grad: 0.0688 (0.0710) loss: 0.8304 (0.8315) time: 0.1925 data: 0.1075 max mem: 9390 +Train: [29] [2400/6250] eta: 0:11:02 lr: 0.000106 grad: 0.0651 (0.0709) loss: 0.8337 (0.8316) time: 0.1673 data: 0.0729 max mem: 9390 +Train: [29] [2500/6250] eta: 0:10:45 lr: 0.000106 grad: 0.0713 (0.0709) loss: 0.8292 (0.8316) time: 0.1893 data: 0.1041 max mem: 9390 +Train: [29] [2600/6250] eta: 0:10:28 lr: 0.000106 grad: 0.0635 (0.0709) loss: 0.8318 (0.8317) time: 0.1920 data: 0.1034 max mem: 9390 +Train: [29] [2700/6250] eta: 0:10:11 lr: 0.000106 grad: 0.0682 (0.0709) loss: 0.8339 (0.8317) time: 0.1959 data: 0.1039 max mem: 9390 +Train: [29] [2800/6250] eta: 0:09:54 lr: 0.000106 grad: 0.0722 (0.0710) loss: 0.8273 (0.8317) time: 0.1728 data: 0.0755 max mem: 9390 +Train: [29] [2900/6250] eta: 0:09:36 lr: 0.000106 grad: 0.0733 (0.0710) loss: 0.8257 (0.8317) time: 0.1782 data: 0.0896 max mem: 9390 +Train: [29] [3000/6250] eta: 0:09:19 lr: 0.000106 grad: 0.0698 (0.0710) loss: 0.8326 (0.8317) time: 0.1710 data: 0.0862 max mem: 9390 +Train: [29] [3100/6250] eta: 0:09:01 lr: 0.000106 grad: 0.0679 (0.0710) loss: 0.8325 (0.8316) time: 0.1639 data: 0.0843 max mem: 9390 +Train: [29] [3200/6250] eta: 0:08:45 lr: 0.000106 grad: 0.0671 (0.0709) loss: 0.8317 (0.8316) time: 0.1788 data: 0.0862 max mem: 9390 +Train: [29] [3300/6250] eta: 0:08:27 lr: 0.000106 grad: 0.0681 (0.0709) loss: 0.8319 (0.8316) time: 0.1856 data: 0.1049 max mem: 9390 +Train: [29] [3400/6250] eta: 0:08:09 lr: 0.000106 grad: 0.0647 (0.0708) loss: 0.8322 (0.8316) time: 0.1491 data: 0.0640 max mem: 9390 +Train: [29] [3500/6250] eta: 0:07:52 lr: 0.000105 grad: 0.0695 (0.0708) loss: 0.8322 (0.8316) time: 0.1784 data: 0.0957 max mem: 9390 +Train: [29] [3600/6250] eta: 0:07:34 lr: 0.000105 grad: 0.0722 (0.0708) loss: 0.8315 (0.8317) time: 0.1512 data: 0.0630 max mem: 9390 +Train: [29] [3700/6250] eta: 0:07:17 lr: 0.000105 grad: 0.0673 (0.0708) loss: 0.8277 (0.8317) time: 0.1783 data: 0.0885 max mem: 9390 +Train: [29] [3800/6250] eta: 0:06:59 lr: 0.000105 grad: 0.0662 (0.0708) loss: 0.8341 (0.8317) time: 0.1813 data: 0.0998 max mem: 9390 +Train: [29] [3900/6250] eta: 0:06:42 lr: 0.000105 grad: 0.0766 (0.0708) loss: 0.8241 (0.8316) time: 0.1601 data: 0.0682 max mem: 9390 +Train: [29] [4000/6250] eta: 0:06:24 lr: 0.000105 grad: 0.0675 (0.0709) loss: 0.8257 (0.8316) time: 0.1692 data: 0.0830 max mem: 9390 +Train: [29] [4100/6250] eta: 0:06:07 lr: 0.000105 grad: 0.0697 (0.0709) loss: 0.8308 (0.8316) time: 0.1563 data: 0.0770 max mem: 9390 +Train: [29] [4200/6250] eta: 0:05:50 lr: 0.000105 grad: 0.0671 (0.0708) loss: 0.8358 (0.8316) time: 0.1923 data: 0.1092 max mem: 9390 +Train: [29] [4300/6250] eta: 0:05:32 lr: 0.000105 grad: 0.0717 (0.0708) loss: 0.8272 (0.8315) time: 0.1785 data: 0.0930 max mem: 9390 +Train: [29] [4400/6250] eta: 0:05:15 lr: 0.000105 grad: 0.0677 (0.0708) loss: 0.8287 (0.8315) time: 0.1833 data: 0.0934 max mem: 9390 +Train: [29] [4500/6250] eta: 0:04:58 lr: 0.000105 grad: 0.0697 (0.0708) loss: 0.8312 (0.8316) time: 0.1986 data: 0.1077 max mem: 9390 +Train: [29] [4600/6250] eta: 0:04:41 lr: 0.000105 grad: 0.0681 (0.0708) loss: 0.8327 (0.8316) time: 0.1414 data: 0.0548 max mem: 9390 +Train: [29] [4700/6250] eta: 0:04:24 lr: 0.000105 grad: 0.0694 (0.0708) loss: 0.8310 (0.8316) time: 0.2063 data: 0.1214 max mem: 9390 +Train: [29] [4800/6250] eta: 0:04:07 lr: 0.000105 grad: 0.0697 (0.0709) loss: 0.8293 (0.8315) time: 0.1554 data: 0.0688 max mem: 9390 +Train: [29] [4900/6250] eta: 0:03:50 lr: 0.000105 grad: 0.0687 (0.0709) loss: 0.8335 (0.8315) time: 0.1670 data: 0.0740 max mem: 9390 +Train: [29] [5000/6250] eta: 0:03:32 lr: 0.000105 grad: 0.0696 (0.0710) loss: 0.8335 (0.8315) time: 0.1744 data: 0.0849 max mem: 9390 +Train: [29] [5100/6250] eta: 0:03:15 lr: 0.000105 grad: 0.0654 (0.0709) loss: 0.8269 (0.8315) time: 0.1778 data: 0.0889 max mem: 9390 +Train: [29] [5200/6250] eta: 0:02:58 lr: 0.000105 grad: 0.0678 (0.0709) loss: 0.8313 (0.8315) time: 0.1658 data: 0.0785 max mem: 9390 +Train: [29] [5300/6250] eta: 0:02:41 lr: 0.000105 grad: 0.0684 (0.0709) loss: 0.8355 (0.8315) time: 0.1772 data: 0.0922 max mem: 9390 +Train: [29] [5400/6250] eta: 0:02:24 lr: 0.000105 grad: 0.0689 (0.0710) loss: 0.8363 (0.8315) time: 0.1936 data: 0.1105 max mem: 9390 +Train: [29] [5500/6250] eta: 0:02:07 lr: 0.000105 grad: 0.0682 (0.0710) loss: 0.8300 (0.8315) time: 0.1662 data: 0.0723 max mem: 9390 +Train: [29] [5600/6250] eta: 0:01:50 lr: 0.000105 grad: 0.0740 (0.0710) loss: 0.8368 (0.8315) time: 0.1657 data: 0.0758 max mem: 9390 +Train: [29] [5700/6250] eta: 0:01:33 lr: 0.000105 grad: 0.0669 (0.0710) loss: 0.8278 (0.8315) time: 0.1641 data: 0.0856 max mem: 9390 +Train: [29] [5800/6250] eta: 0:01:16 lr: 0.000105 grad: 0.0681 (0.0711) loss: 0.8349 (0.8315) time: 0.1735 data: 0.0844 max mem: 9390 +Train: [29] [5900/6250] eta: 0:00:59 lr: 0.000105 grad: 0.0648 (0.0711) loss: 0.8289 (0.8314) time: 0.1824 data: 0.0981 max mem: 9390 +Train: [29] [6000/6250] eta: 0:00:42 lr: 0.000105 grad: 0.0675 (0.0711) loss: 0.8304 (0.8314) time: 0.1718 data: 0.0821 max mem: 9390 +Train: [29] [6100/6250] eta: 0:00:25 lr: 0.000105 grad: 0.0664 (0.0711) loss: 0.8318 (0.8314) time: 0.1528 data: 0.0690 max mem: 9390 +Train: [29] [6200/6250] eta: 0:00:08 lr: 0.000105 grad: 0.0662 (0.0711) loss: 0.8288 (0.8314) time: 0.1399 data: 0.0593 max mem: 9390 +Train: [29] [6249/6250] eta: 0:00:00 lr: 0.000105 grad: 0.0697 (0.0711) loss: 0.8319 (0.8314) time: 0.1749 data: 0.0938 max mem: 9390 +Train: [29] Total time: 0:17:47 (0.1708 s / it) +Averaged stats: lr: 0.000105 grad: 0.0697 (0.0711) loss: 0.8319 (0.8314) +Eval (hcp-train-subset): [29] [ 0/62] eta: 0:04:55 loss: 0.8523 (0.8523) time: 4.7737 data: 4.7073 max mem: 9390 +Eval (hcp-train-subset): [29] [61/62] eta: 0:00:00 loss: 0.8394 (0.8417) time: 0.1238 data: 0.0984 max mem: 9390 +Eval (hcp-train-subset): [29] Total time: 0:00:13 (0.2243 s / it) +Averaged stats (hcp-train-subset): loss: 0.8394 (0.8417) +Making plots (hcp-train-subset): example=23 +Eval (hcp-val): [29] [ 0/62] eta: 0:04:59 loss: 0.8405 (0.8405) time: 4.8380 data: 4.8076 max mem: 9390 +Eval (hcp-val): [29] [61/62] eta: 0:00:00 loss: 0.8384 (0.8391) time: 0.1109 data: 0.0857 max mem: 9390 +Eval (hcp-val): [29] Total time: 0:00:13 (0.2196 s / it) +Averaged stats (hcp-val): loss: 0.8384 (0.8391) +Making plots (hcp-val): example=17 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +Train: [30] [ 0/6250] eta: 11:26:42 lr: 0.000105 grad: 0.0434 (0.0434) loss: 0.8872 (0.8872) time: 6.5924 data: 6.5003 max mem: 9390 +Train: [30] [ 100/6250] eta: 0:23:23 lr: 0.000105 grad: 0.0714 (0.0724) loss: 0.8385 (0.8440) time: 0.1954 data: 0.1037 max mem: 9390 +Train: [30] [ 200/6250] eta: 0:20:09 lr: 0.000105 grad: 0.0628 (0.0722) loss: 0.8431 (0.8401) time: 0.1681 data: 0.0785 max mem: 9390 +Train: [30] [ 300/6250] eta: 0:18:36 lr: 0.000105 grad: 0.0684 (0.0718) loss: 0.8380 (0.8377) time: 0.1642 data: 0.0736 max mem: 9390 +Train: [30] [ 400/6250] eta: 0:17:45 lr: 0.000105 grad: 0.0699 (0.0713) loss: 0.8329 (0.8363) time: 0.1605 data: 0.0698 max mem: 9390 +Train: [30] [ 500/6250] eta: 0:17:09 lr: 0.000105 grad: 0.0655 (0.0703) loss: 0.8381 (0.8361) time: 0.1795 data: 0.0857 max mem: 9390 +Train: [30] [ 600/6250] eta: 0:16:53 lr: 0.000105 grad: 0.0632 (0.0699) loss: 0.8334 (0.8360) time: 0.1686 data: 0.0759 max mem: 9390 +Train: [30] [ 700/6250] eta: 0:16:43 lr: 0.000105 grad: 0.0639 (0.0696) loss: 0.8307 (0.8359) time: 0.2061 data: 0.1197 max mem: 9390 +Train: [30] [ 800/6250] eta: 0:16:46 lr: 0.000105 grad: 0.0660 (0.0693) loss: 0.8346 (0.8356) time: 0.2144 data: 0.1131 max mem: 9390 +Train: [30] [ 900/6250] eta: 0:16:32 lr: 0.000105 grad: 0.0699 (0.0691) loss: 0.8330 (0.8352) time: 0.1826 data: 0.0871 max mem: 9390 +Train: [30] [1000/6250] eta: 0:16:05 lr: 0.000105 grad: 0.0656 (0.0690) loss: 0.8335 (0.8350) time: 0.1667 data: 0.0812 max mem: 9390 +Train: [30] [1100/6250] eta: 0:15:41 lr: 0.000105 grad: 0.0658 (0.0689) loss: 0.8339 (0.8347) time: 0.1448 data: 0.0501 max mem: 9390 +Train: [30] [1200/6250] eta: 0:15:18 lr: 0.000105 grad: 0.0646 (0.0688) loss: 0.8349 (0.8344) time: 0.1756 data: 0.0874 max mem: 9390 +Train: [30] [1300/6250] eta: 0:14:55 lr: 0.000105 grad: 0.0666 (0.0687) loss: 0.8342 (0.8341) time: 0.1739 data: 0.0819 max mem: 9390 +Train: [30] [1400/6250] eta: 0:14:33 lr: 0.000104 grad: 0.0681 (0.0687) loss: 0.8283 (0.8338) time: 0.1792 data: 0.0883 max mem: 9390 +Train: [30] [1500/6250] eta: 0:14:10 lr: 0.000104 grad: 0.0678 (0.0687) loss: 0.8317 (0.8336) time: 0.1857 data: 0.1032 max mem: 9390 +Train: [30] [1600/6250] eta: 0:13:48 lr: 0.000104 grad: 0.0662 (0.0687) loss: 0.8312 (0.8334) time: 0.1645 data: 0.0768 max mem: 9390 +Train: [30] [1700/6250] eta: 0:13:29 lr: 0.000104 grad: 0.0695 (0.0689) loss: 0.8311 (0.8332) time: 0.1811 data: 0.0889 max mem: 9390 +Train: [30] [1800/6250] eta: 0:13:07 lr: 0.000104 grad: 0.0727 (0.0691) loss: 0.8259 (0.8329) time: 0.1744 data: 0.0877 max mem: 9390 +Train: [30] [1900/6250] eta: 0:12:48 lr: 0.000104 grad: 0.0708 (0.0692) loss: 0.8282 (0.8326) time: 0.1823 data: 0.1006 max mem: 9390 +Train: [30] [2000/6250] eta: 0:12:28 lr: 0.000104 grad: 0.0695 (0.0694) loss: 0.8298 (0.8325) time: 0.1729 data: 0.0875 max mem: 9390 +Train: [30] [2100/6250] eta: 0:12:10 lr: 0.000104 grad: 0.0658 (0.0693) loss: 0.8286 (0.8324) time: 0.1510 data: 0.0671 max mem: 9390 +Train: [30] [2200/6250] eta: 0:11:52 lr: 0.000104 grad: 0.0683 (0.0694) loss: 0.8242 (0.8322) time: 0.1817 data: 0.0977 max mem: 9390 +Train: [30] [2300/6250] eta: 0:11:34 lr: 0.000104 grad: 0.0617 (0.0694) loss: 0.8285 (0.8321) time: 0.1886 data: 0.1041 max mem: 9390 +Train: [30] [2400/6250] eta: 0:11:16 lr: 0.000104 grad: 0.0679 (0.0694) loss: 0.8299 (0.8319) time: 0.1808 data: 0.0943 max mem: 9390 +Train: [30] [2500/6250] eta: 0:10:56 lr: 0.000104 grad: 0.0674 (0.0694) loss: 0.8281 (0.8319) time: 0.1562 data: 0.0690 max mem: 9390 +Train: [30] [2600/6250] eta: 0:10:38 lr: 0.000104 grad: 0.0672 (0.0694) loss: 0.8294 (0.8319) time: 0.1718 data: 0.0833 max mem: 9390 +Train: [30] [2700/6250] eta: 0:10:20 lr: 0.000104 grad: 0.0681 (0.0694) loss: 0.8314 (0.8319) time: 0.1676 data: 0.0839 max mem: 9390 +Train: [30] [2800/6250] eta: 0:10:02 lr: 0.000104 grad: 0.0695 (0.0694) loss: 0.8303 (0.8318) time: 0.1552 data: 0.0708 max mem: 9390 +Train: [30] [2900/6250] eta: 0:09:43 lr: 0.000104 grad: 0.0682 (0.0694) loss: 0.8303 (0.8319) time: 0.1591 data: 0.0704 max mem: 9390 +Train: [30] [3000/6250] eta: 0:09:26 lr: 0.000104 grad: 0.0706 (0.0695) loss: 0.8308 (0.8318) time: 0.1777 data: 0.0906 max mem: 9390 +Train: [30] [3100/6250] eta: 0:09:07 lr: 0.000104 grad: 0.0709 (0.0697) loss: 0.8327 (0.8318) time: 0.1723 data: 0.0880 max mem: 9390 +Train: [30] [3200/6250] eta: 0:08:49 lr: 0.000104 grad: 0.0735 (0.0698) loss: 0.8296 (0.8318) time: 0.1772 data: 0.0964 max mem: 9390 +Train: [30] [3300/6250] eta: 0:08:31 lr: 0.000104 grad: 0.0708 (0.0699) loss: 0.8298 (0.8317) time: 0.1693 data: 0.0809 max mem: 9390 +Train: [30] [3400/6250] eta: 0:08:13 lr: 0.000104 grad: 0.0710 (0.0699) loss: 0.8291 (0.8316) time: 0.1705 data: 0.0829 max mem: 9390 +Train: [30] [3500/6250] eta: 0:07:56 lr: 0.000104 grad: 0.0693 (0.0701) loss: 0.8327 (0.8315) time: 0.1754 data: 0.0836 max mem: 9390 +Train: [30] [3600/6250] eta: 0:07:38 lr: 0.000104 grad: 0.0706 (0.0701) loss: 0.8263 (0.8315) time: 0.1765 data: 0.0967 max mem: 9390 +Train: [30] [3700/6250] eta: 0:07:21 lr: 0.000104 grad: 0.0699 (0.0703) loss: 0.8300 (0.8314) time: 0.1751 data: 0.0869 max mem: 9390 +Train: [30] [3800/6250] eta: 0:07:03 lr: 0.000104 grad: 0.0735 (0.0703) loss: 0.8306 (0.8314) time: 0.1568 data: 0.0611 max mem: 9390 +Train: [30] [3900/6250] eta: 0:06:45 lr: 0.000104 grad: 0.0689 (0.0704) loss: 0.8292 (0.8313) time: 0.1541 data: 0.0652 max mem: 9390 +Train: [30] [4000/6250] eta: 0:06:27 lr: 0.000104 grad: 0.0709 (0.0705) loss: 0.8274 (0.8313) time: 0.1554 data: 0.0682 max mem: 9390 +Train: [30] [4100/6250] eta: 0:06:10 lr: 0.000104 grad: 0.0708 (0.0705) loss: 0.8264 (0.8312) time: 0.1540 data: 0.0724 max mem: 9390 +Train: [30] [4200/6250] eta: 0:05:52 lr: 0.000104 grad: 0.0743 (0.0707) loss: 0.8234 (0.8310) time: 0.1679 data: 0.0798 max mem: 9390 +Train: [30] [4300/6250] eta: 0:05:35 lr: 0.000104 grad: 0.0742 (0.0707) loss: 0.8246 (0.8309) time: 0.1444 data: 0.0578 max mem: 9390 +Train: [30] [4400/6250] eta: 0:05:18 lr: 0.000104 grad: 0.0679 (0.0710) loss: 0.8258 (0.8308) time: 0.1785 data: 0.0925 max mem: 9390 +Train: [30] [4500/6250] eta: 0:05:00 lr: 0.000104 grad: 0.0741 (0.0711) loss: 0.8262 (0.8307) time: 0.1677 data: 0.0791 max mem: 9390 +Train: [30] [4600/6250] eta: 0:04:43 lr: 0.000104 grad: 0.0700 (0.0711) loss: 0.8307 (0.8307) time: 0.1274 data: 0.0411 max mem: 9390 +Train: [30] [4700/6250] eta: 0:04:26 lr: 0.000104 grad: 0.0728 (0.0711) loss: 0.8297 (0.8307) time: 0.1658 data: 0.0842 max mem: 9390 +Train: [30] [4800/6250] eta: 0:04:08 lr: 0.000104 grad: 0.0708 (0.0712) loss: 0.8313 (0.8306) time: 0.1628 data: 0.0825 max mem: 9390 +Train: [30] [4900/6250] eta: 0:03:51 lr: 0.000104 grad: 0.0787 (0.0713) loss: 0.8220 (0.8306) time: 0.1443 data: 0.0543 max mem: 9390 +Train: [30] [5000/6250] eta: 0:03:34 lr: 0.000104 grad: 0.0697 (0.0713) loss: 0.8338 (0.8305) time: 0.1756 data: 0.0868 max mem: 9390 +Train: [30] [5100/6250] eta: 0:03:17 lr: 0.000104 grad: 0.0713 (0.0714) loss: 0.8291 (0.8305) time: 0.1444 data: 0.0525 max mem: 9390 +Train: [30] [5200/6250] eta: 0:03:00 lr: 0.000104 grad: 0.0773 (0.0715) loss: 0.8216 (0.8305) time: 0.1820 data: 0.1006 max mem: 9390 +Train: [30] [5300/6250] eta: 0:02:42 lr: 0.000104 grad: 0.0767 (0.0715) loss: 0.8226 (0.8304) time: 0.2011 data: 0.1165 max mem: 9390 +Train: [30] [5400/6250] eta: 0:02:25 lr: 0.000103 grad: 0.0745 (0.0716) loss: 0.8268 (0.8303) time: 0.1614 data: 0.0749 max mem: 9390 +Train: [30] [5500/6250] eta: 0:02:08 lr: 0.000103 grad: 0.0753 (0.0717) loss: 0.8277 (0.8302) time: 0.1676 data: 0.0825 max mem: 9390 +Train: [30] [5600/6250] eta: 0:01:51 lr: 0.000103 grad: 0.0739 (0.0718) loss: 0.8307 (0.8302) time: 0.1650 data: 0.0775 max mem: 9390 +Train: [30] [5700/6250] eta: 0:01:34 lr: 0.000103 grad: 0.0726 (0.0720) loss: 0.8251 (0.8301) time: 0.1662 data: 0.0827 max mem: 9390 +Train: [30] [5800/6250] eta: 0:01:17 lr: 0.000103 grad: 0.0755 (0.0721) loss: 0.8333 (0.8301) time: 0.1518 data: 0.0664 max mem: 9390 +Train: [30] [5900/6250] eta: 0:00:59 lr: 0.000103 grad: 0.0769 (0.0721) loss: 0.8272 (0.8301) time: 0.1328 data: 0.0460 max mem: 9390 +Train: [30] [6000/6250] eta: 0:00:42 lr: 0.000103 grad: 0.0725 (0.0721) loss: 0.8340 (0.8301) time: 0.1940 data: 0.1165 max mem: 9390 +Train: [30] [6100/6250] eta: 0:00:25 lr: 0.000103 grad: 0.0726 (0.0722) loss: 0.8224 (0.8301) time: 0.1500 data: 0.0601 max mem: 9390 +Train: [30] [6200/6250] eta: 0:00:08 lr: 0.000103 grad: 0.0719 (0.0722) loss: 0.8320 (0.8300) time: 0.1615 data: 0.0808 max mem: 9390 +Train: [30] [6249/6250] eta: 0:00:00 lr: 0.000103 grad: 0.0692 (0.0722) loss: 0.8289 (0.8300) time: 0.1730 data: 0.0867 max mem: 9390 +Train: [30] Total time: 0:17:55 (0.1721 s / it) +Averaged stats: lr: 0.000103 grad: 0.0692 (0.0722) loss: 0.8289 (0.8300) +Eval (hcp-train-subset): [30] [ 0/62] eta: 0:04:27 loss: 0.8545 (0.8545) time: 4.3139 data: 4.2795 max mem: 9390 +Eval (hcp-train-subset): [30] [61/62] eta: 0:00:00 loss: 0.8407 (0.8422) time: 0.1302 data: 0.1051 max mem: 9390 +Eval (hcp-train-subset): [30] Total time: 0:00:13 (0.2103 s / it) +Averaged stats (hcp-train-subset): loss: 0.8407 (0.8422) +Eval (hcp-val): [30] [ 0/62] eta: 0:03:17 loss: 0.8389 (0.8389) time: 3.1807 data: 3.0949 max mem: 9390 +Eval (hcp-val): [30] [61/62] eta: 0:00:00 loss: 0.8382 (0.8386) time: 0.1396 data: 0.1124 max mem: 9390 +Eval (hcp-val): [30] Total time: 0:00:13 (0.2236 s / it) +Averaged stats (hcp-val): loss: 0.8382 (0.8386) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +Train: [31] [ 0/6250] eta: 7:11:05 lr: 0.000103 grad: 0.0473 (0.0473) loss: 0.8733 (0.8733) time: 4.1384 data: 3.8351 max mem: 9390 +Train: [31] [ 100/6250] eta: 0:23:10 lr: 0.000103 grad: 0.0693 (0.0800) loss: 0.8376 (0.8387) time: 0.1829 data: 0.0851 max mem: 9390 +Train: [31] [ 200/6250] eta: 0:20:16 lr: 0.000103 grad: 0.0657 (0.0770) loss: 0.8306 (0.8360) time: 0.2051 data: 0.0928 max mem: 9390 +Train: [31] [ 300/6250] eta: 0:19:03 lr: 0.000103 grad: 0.0696 (0.0751) loss: 0.8281 (0.8344) time: 0.1718 data: 0.0697 max mem: 9390 +Train: [31] [ 400/6250] eta: 0:18:11 lr: 0.000103 grad: 0.0622 (0.0733) loss: 0.8281 (0.8339) time: 0.1559 data: 0.0631 max mem: 9390 +Train: [31] [ 500/6250] eta: 0:17:32 lr: 0.000103 grad: 0.0630 (0.0717) loss: 0.8366 (0.8342) time: 0.1853 data: 0.0881 max mem: 9390 +Train: [31] [ 600/6250] eta: 0:17:22 lr: 0.000103 grad: 0.0637 (0.0708) loss: 0.8374 (0.8344) time: 0.1980 data: 0.1149 max mem: 9390 +Train: [31] [ 700/6250] eta: 0:16:59 lr: 0.000103 grad: 0.0628 (0.0704) loss: 0.8385 (0.8346) time: 0.2060 data: 0.1151 max mem: 9390 +Train: [31] [ 800/6250] eta: 0:16:31 lr: 0.000103 grad: 0.0641 (0.0699) loss: 0.8366 (0.8349) time: 0.2113 data: 0.1093 max mem: 9390 +Train: [31] [ 900/6250] eta: 0:16:47 lr: 0.000103 grad: 0.0668 (0.0698) loss: 0.8335 (0.8351) time: 0.2451 data: 0.1343 max mem: 9390 +Train: [31] [1000/6250] eta: 0:16:47 lr: 0.000103 grad: 0.0656 (0.0696) loss: 0.8332 (0.8349) time: 0.1867 data: 0.0731 max mem: 9390 +Train: [31] [1100/6250] eta: 0:16:24 lr: 0.000103 grad: 0.0676 (0.0695) loss: 0.8337 (0.8347) time: 0.1727 data: 0.0730 max mem: 9390 +Train: [31] [1200/6250] eta: 0:16:00 lr: 0.000103 grad: 0.0672 (0.0696) loss: 0.8284 (0.8345) time: 0.1710 data: 0.0741 max mem: 9390 +Train: [31] [1300/6250] eta: 0:15:38 lr: 0.000103 grad: 0.0701 (0.0696) loss: 0.8279 (0.8342) time: 0.1641 data: 0.0735 max mem: 9390 +Train: [31] [1400/6250] eta: 0:15:16 lr: 0.000103 grad: 0.0623 (0.0696) loss: 0.8366 (0.8341) time: 0.1571 data: 0.0586 max mem: 9390 +Train: [31] [1500/6250] eta: 0:14:56 lr: 0.000103 grad: 0.0706 (0.0697) loss: 0.8342 (0.8340) time: 0.1863 data: 0.0905 max mem: 9390 +Train: [31] [1600/6250] eta: 0:14:35 lr: 0.000103 grad: 0.0728 (0.0698) loss: 0.8277 (0.8339) time: 0.2102 data: 0.1256 max mem: 9390 +Train: [31] [1700/6250] eta: 0:14:15 lr: 0.000103 grad: 0.0712 (0.0699) loss: 0.8299 (0.8338) time: 0.1866 data: 0.0899 max mem: 9390 +Train: [31] [1800/6250] eta: 0:13:51 lr: 0.000103 grad: 0.0653 (0.0699) loss: 0.8340 (0.8338) time: 0.1754 data: 0.0836 max mem: 9390 +Train: [31] [1900/6250] eta: 0:13:29 lr: 0.000103 grad: 0.0699 (0.0700) loss: 0.8312 (0.8336) time: 0.1726 data: 0.0708 max mem: 9390 +Train: [31] [2000/6250] eta: 0:13:07 lr: 0.000103 grad: 0.0647 (0.0701) loss: 0.8267 (0.8336) time: 0.1593 data: 0.0777 max mem: 9390 +Train: [31] [2100/6250] eta: 0:12:45 lr: 0.000103 grad: 0.0698 (0.0703) loss: 0.8300 (0.8334) time: 0.2042 data: 0.1047 max mem: 9390 +Train: [31] [2200/6250] eta: 0:12:22 lr: 0.000103 grad: 0.0671 (0.0705) loss: 0.8389 (0.8333) time: 0.1556 data: 0.0577 max mem: 9390 +Train: [31] [2300/6250] eta: 0:12:02 lr: 0.000103 grad: 0.0738 (0.0705) loss: 0.8281 (0.8332) time: 0.1886 data: 0.1034 max mem: 9390 +Train: [31] [2400/6250] eta: 0:11:41 lr: 0.000103 grad: 0.0735 (0.0706) loss: 0.8300 (0.8332) time: 0.1624 data: 0.0673 max mem: 9390 +Train: [31] [2500/6250] eta: 0:11:21 lr: 0.000103 grad: 0.0680 (0.0707) loss: 0.8306 (0.8332) time: 0.1893 data: 0.1039 max mem: 9390 +Train: [31] [2600/6250] eta: 0:11:01 lr: 0.000103 grad: 0.0660 (0.0707) loss: 0.8351 (0.8332) time: 0.1500 data: 0.0699 max mem: 9390 +Train: [31] [2700/6250] eta: 0:10:40 lr: 0.000103 grad: 0.0725 (0.0707) loss: 0.8291 (0.8331) time: 0.1592 data: 0.0784 max mem: 9390 +Train: [31] [2800/6250] eta: 0:10:21 lr: 0.000103 grad: 0.0689 (0.0708) loss: 0.8353 (0.8331) time: 0.2024 data: 0.1082 max mem: 9390 +Train: [31] [2900/6250] eta: 0:10:01 lr: 0.000103 grad: 0.0680 (0.0709) loss: 0.8286 (0.8331) time: 0.1729 data: 0.0849 max mem: 9390 +Train: [31] [3000/6250] eta: 0:09:41 lr: 0.000103 grad: 0.0721 (0.0709) loss: 0.8346 (0.8331) time: 0.1699 data: 0.0809 max mem: 9390 +Train: [31] [3100/6250] eta: 0:09:22 lr: 0.000103 grad: 0.0718 (0.0709) loss: 0.8334 (0.8331) time: 0.1688 data: 0.0777 max mem: 9390 +Train: [31] [3200/6250] eta: 0:09:03 lr: 0.000102 grad: 0.0770 (0.0710) loss: 0.8255 (0.8331) time: 0.1856 data: 0.0986 max mem: 9390 +Train: [31] [3300/6250] eta: 0:08:45 lr: 0.000102 grad: 0.0673 (0.0710) loss: 0.8368 (0.8331) time: 0.1982 data: 0.1121 max mem: 9390 +Train: [31] [3400/6250] eta: 0:08:25 lr: 0.000102 grad: 0.0696 (0.0711) loss: 0.8373 (0.8331) time: 0.1417 data: 0.0534 max mem: 9390 +Train: [31] [3500/6250] eta: 0:08:06 lr: 0.000102 grad: 0.0704 (0.0712) loss: 0.8286 (0.8331) time: 0.1481 data: 0.0645 max mem: 9390 +Train: [31] [3600/6250] eta: 0:07:48 lr: 0.000102 grad: 0.0707 (0.0712) loss: 0.8343 (0.8331) time: 0.1448 data: 0.0588 max mem: 9390 +Train: [31] [3700/6250] eta: 0:07:29 lr: 0.000102 grad: 0.0749 (0.0712) loss: 0.8319 (0.8332) time: 0.1763 data: 0.0925 max mem: 9390 +Train: [31] [3800/6250] eta: 0:07:11 lr: 0.000102 grad: 0.0680 (0.0712) loss: 0.8276 (0.8332) time: 0.1781 data: 0.0892 max mem: 9390 +Train: [31] [3900/6250] eta: 0:06:53 lr: 0.000102 grad: 0.0699 (0.0711) loss: 0.8382 (0.8332) time: 0.1643 data: 0.0750 max mem: 9390 +Train: [31] [4000/6250] eta: 0:06:34 lr: 0.000102 grad: 0.0681 (0.0711) loss: 0.8308 (0.8332) time: 0.1593 data: 0.0722 max mem: 9390 +Train: [31] [4100/6250] eta: 0:06:16 lr: 0.000102 grad: 0.0687 (0.0711) loss: 0.8321 (0.8333) time: 0.1718 data: 0.0809 max mem: 9390 +Train: [31] [4200/6250] eta: 0:05:58 lr: 0.000102 grad: 0.0685 (0.0712) loss: 0.8311 (0.8333) time: 0.1808 data: 0.1003 max mem: 9390 +Train: [31] [4300/6250] eta: 0:05:40 lr: 0.000102 grad: 0.0723 (0.0712) loss: 0.8331 (0.8332) time: 0.1642 data: 0.0788 max mem: 9390 +Train: [31] [4400/6250] eta: 0:05:23 lr: 0.000102 grad: 0.0717 (0.0712) loss: 0.8305 (0.8332) time: 0.1943 data: 0.1082 max mem: 9390 +Train: [31] [4500/6250] eta: 0:05:05 lr: 0.000102 grad: 0.0711 (0.0712) loss: 0.8347 (0.8331) time: 0.1527 data: 0.0624 max mem: 9390 +Train: [31] [4600/6250] eta: 0:04:47 lr: 0.000102 grad: 0.0738 (0.0712) loss: 0.8303 (0.8331) time: 0.1716 data: 0.0888 max mem: 9390 +Train: [31] [4700/6250] eta: 0:04:29 lr: 0.000102 grad: 0.0648 (0.0712) loss: 0.8393 (0.8331) time: 0.1586 data: 0.0747 max mem: 9390 +Train: [31] [4800/6250] eta: 0:04:12 lr: 0.000102 grad: 0.0733 (0.0712) loss: 0.8255 (0.8331) time: 0.1633 data: 0.0800 max mem: 9390 +Train: [31] [4900/6250] eta: 0:03:54 lr: 0.000102 grad: 0.0768 (0.0712) loss: 0.8319 (0.8331) time: 0.1569 data: 0.0667 max mem: 9390 +Train: [31] [5000/6250] eta: 0:03:36 lr: 0.000102 grad: 0.0653 (0.0712) loss: 0.8354 (0.8331) time: 0.1728 data: 0.0865 max mem: 9390 +Train: [31] [5100/6250] eta: 0:03:19 lr: 0.000102 grad: 0.0647 (0.0712) loss: 0.8328 (0.8331) time: 0.1268 data: 0.0342 max mem: 9390 +Train: [31] [5200/6250] eta: 0:03:01 lr: 0.000102 grad: 0.0658 (0.0712) loss: 0.8288 (0.8330) time: 0.1628 data: 0.0773 max mem: 9390 +Train: [31] [5300/6250] eta: 0:02:44 lr: 0.000102 grad: 0.0685 (0.0712) loss: 0.8325 (0.8330) time: 0.1618 data: 0.0786 max mem: 9390 +Train: [31] [5400/6250] eta: 0:02:26 lr: 0.000102 grad: 0.0699 (0.0712) loss: 0.8264 (0.8330) time: 0.1665 data: 0.0764 max mem: 9390 +Train: [31] [5500/6250] eta: 0:02:09 lr: 0.000102 grad: 0.0677 (0.0711) loss: 0.8329 (0.8330) time: 0.1506 data: 0.0661 max mem: 9390 +Train: [31] [5600/6250] eta: 0:01:52 lr: 0.000102 grad: 0.0691 (0.0711) loss: 0.8309 (0.8330) time: 0.1743 data: 0.0924 max mem: 9390 +Train: [31] [5700/6250] eta: 0:01:34 lr: 0.000102 grad: 0.0671 (0.0711) loss: 0.8364 (0.8330) time: 0.1728 data: 0.0801 max mem: 9390 +Train: [31] [5800/6250] eta: 0:01:17 lr: 0.000102 grad: 0.0703 (0.0711) loss: 0.8234 (0.8330) time: 0.1399 data: 0.0505 max mem: 9390 +Train: [31] [5900/6250] eta: 0:01:00 lr: 0.000102 grad: 0.0669 (0.0711) loss: 0.8287 (0.8330) time: 0.1442 data: 0.0581 max mem: 9390 +Train: [31] [6000/6250] eta: 0:00:43 lr: 0.000102 grad: 0.0706 (0.0711) loss: 0.8289 (0.8329) time: 0.1590 data: 0.0739 max mem: 9390 +Train: [31] [6100/6250] eta: 0:00:25 lr: 0.000102 grad: 0.0693 (0.0711) loss: 0.8335 (0.8329) time: 0.1704 data: 0.0847 max mem: 9390 +Train: [31] [6200/6250] eta: 0:00:08 lr: 0.000102 grad: 0.0699 (0.0711) loss: 0.8333 (0.8329) time: 0.1470 data: 0.0610 max mem: 9390 +Train: [31] [6249/6250] eta: 0:00:00 lr: 0.000102 grad: 0.0736 (0.0711) loss: 0.8341 (0.8329) time: 0.1682 data: 0.0804 max mem: 9390 +Train: [31] Total time: 0:18:02 (0.1732 s / it) +Averaged stats: lr: 0.000102 grad: 0.0736 (0.0711) loss: 0.8341 (0.8329) +Eval (hcp-train-subset): [31] [ 0/62] eta: 0:03:46 loss: 0.8514 (0.8514) time: 3.6514 data: 3.5542 max mem: 9390 +Eval (hcp-train-subset): [31] [61/62] eta: 0:00:00 loss: 0.8399 (0.8406) time: 0.1380 data: 0.1106 max mem: 9390 +Eval (hcp-train-subset): [31] Total time: 0:00:14 (0.2267 s / it) +Averaged stats (hcp-train-subset): loss: 0.8399 (0.8406) +Eval (hcp-val): [31] [ 0/62] eta: 0:04:55 loss: 0.8353 (0.8353) time: 4.7692 data: 4.7377 max mem: 9390 +Eval (hcp-val): [31] [61/62] eta: 0:00:00 loss: 0.8368 (0.8384) time: 0.1264 data: 0.0991 max mem: 9390 +Eval (hcp-val): [31] Total time: 0:00:13 (0.2225 s / it) +Averaged stats (hcp-val): loss: 0.8368 (0.8384) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +Train: [32] [ 0/6250] eta: 8:19:51 lr: 0.000102 grad: 0.1425 (0.1425) loss: 0.8742 (0.8742) time: 4.7987 data: 4.4333 max mem: 9390 +Train: [32] [ 100/6250] eta: 0:23:19 lr: 0.000102 grad: 0.0762 (0.0790) loss: 0.8449 (0.8432) time: 0.1805 data: 0.0807 max mem: 9390 +Train: [32] [ 200/6250] eta: 0:19:58 lr: 0.000102 grad: 0.0656 (0.0764) loss: 0.8425 (0.8397) time: 0.1713 data: 0.0737 max mem: 9390 +Train: [32] [ 300/6250] eta: 0:18:28 lr: 0.000102 grad: 0.0676 (0.0742) loss: 0.8393 (0.8389) time: 0.1487 data: 0.0462 max mem: 9390 +Train: [32] [ 400/6250] eta: 0:17:34 lr: 0.000102 grad: 0.0653 (0.0726) loss: 0.8345 (0.8382) time: 0.1580 data: 0.0597 max mem: 9390 +Train: [32] [ 500/6250] eta: 0:17:07 lr: 0.000102 grad: 0.0641 (0.0720) loss: 0.8407 (0.8383) time: 0.1607 data: 0.0707 max mem: 9390 +Train: [32] [ 600/6250] eta: 0:16:48 lr: 0.000102 grad: 0.0681 (0.0718) loss: 0.8392 (0.8380) time: 0.1995 data: 0.1207 max mem: 9390 +Train: [32] [ 700/6250] eta: 0:16:49 lr: 0.000102 grad: 0.0681 (0.0720) loss: 0.8299 (0.8374) time: 0.2224 data: 0.1175 max mem: 9390 +Train: [32] [ 800/6250] eta: 0:16:45 lr: 0.000101 grad: 0.0677 (0.0718) loss: 0.8377 (0.8372) time: 0.2285 data: 0.1168 max mem: 9390 +Train: [32] [ 900/6250] eta: 0:16:44 lr: 0.000101 grad: 0.0680 (0.0720) loss: 0.8360 (0.8369) time: 0.1967 data: 0.0912 max mem: 9390 +Train: [32] [1000/6250] eta: 0:16:24 lr: 0.000101 grad: 0.0644 (0.0716) loss: 0.8326 (0.8368) time: 0.1734 data: 0.0762 max mem: 9390 +Train: [32] [1100/6250] eta: 0:16:01 lr: 0.000101 grad: 0.0651 (0.0717) loss: 0.8298 (0.8367) time: 0.1635 data: 0.0741 max mem: 9390 +Train: [32] [1200/6250] eta: 0:15:39 lr: 0.000101 grad: 0.0691 (0.0718) loss: 0.8280 (0.8363) time: 0.1937 data: 0.1018 max mem: 9390 +Train: [32] [1300/6250] eta: 0:15:16 lr: 0.000101 grad: 0.0655 (0.0717) loss: 0.8323 (0.8361) time: 0.1654 data: 0.0747 max mem: 9390 +Train: [32] [1400/6250] eta: 0:14:54 lr: 0.000101 grad: 0.0681 (0.0716) loss: 0.8310 (0.8359) time: 0.1778 data: 0.0936 max mem: 9390 +Train: [32] [1500/6250] eta: 0:14:30 lr: 0.000101 grad: 0.0672 (0.0715) loss: 0.8335 (0.8357) time: 0.1566 data: 0.0692 max mem: 9390 +Train: [32] [1600/6250] eta: 0:14:09 lr: 0.000101 grad: 0.0672 (0.0714) loss: 0.8317 (0.8355) time: 0.1764 data: 0.0875 max mem: 9390 +Train: [32] [1700/6250] eta: 0:13:48 lr: 0.000101 grad: 0.0694 (0.0714) loss: 0.8301 (0.8352) time: 0.1734 data: 0.0843 max mem: 9390 +Train: [32] [1800/6250] eta: 0:13:29 lr: 0.000101 grad: 0.0665 (0.0713) loss: 0.8356 (0.8350) time: 0.2048 data: 0.1161 max mem: 9390 +Train: [32] [1900/6250] eta: 0:13:09 lr: 0.000101 grad: 0.0688 (0.0712) loss: 0.8319 (0.8349) time: 0.1507 data: 0.0620 max mem: 9390 +Train: [32] [2000/6250] eta: 0:12:48 lr: 0.000101 grad: 0.0705 (0.0713) loss: 0.8275 (0.8347) time: 0.1820 data: 0.0979 max mem: 9390 +Train: [32] [2100/6250] eta: 0:12:29 lr: 0.000101 grad: 0.0684 (0.0715) loss: 0.8304 (0.8345) time: 0.1622 data: 0.0780 max mem: 9390 +Train: [32] [2200/6250] eta: 0:12:08 lr: 0.000101 grad: 0.0680 (0.0715) loss: 0.8250 (0.8342) time: 0.1609 data: 0.0614 max mem: 9390 +Train: [32] [2300/6250] eta: 0:11:48 lr: 0.000101 grad: 0.0720 (0.0715) loss: 0.8250 (0.8341) time: 0.1438 data: 0.0561 max mem: 9390 +Train: [32] [2400/6250] eta: 0:11:28 lr: 0.000101 grad: 0.0725 (0.0715) loss: 0.8305 (0.8340) time: 0.1629 data: 0.0755 max mem: 9390 +Train: [32] [2500/6250] eta: 0:11:08 lr: 0.000101 grad: 0.0725 (0.0716) loss: 0.8320 (0.8337) time: 0.1423 data: 0.0530 max mem: 9390 +Train: [32] [2600/6250] eta: 0:10:49 lr: 0.000101 grad: 0.0737 (0.0717) loss: 0.8248 (0.8335) time: 0.1808 data: 0.0889 max mem: 9390 +Train: [32] [2700/6250] eta: 0:10:29 lr: 0.000101 grad: 0.0696 (0.0719) loss: 0.8341 (0.8333) time: 0.1437 data: 0.0522 max mem: 9390 +Train: [32] [2800/6250] eta: 0:10:11 lr: 0.000101 grad: 0.0721 (0.0719) loss: 0.8219 (0.8331) time: 0.1804 data: 0.0941 max mem: 9390 +Train: [32] [2900/6250] eta: 0:09:51 lr: 0.000101 grad: 0.0830 (0.0722) loss: 0.8249 (0.8330) time: 0.1606 data: 0.0710 max mem: 9390 +Train: [32] [3000/6250] eta: 0:09:32 lr: 0.000101 grad: 0.0728 (0.0723) loss: 0.8340 (0.8329) time: 0.1616 data: 0.0755 max mem: 9390 +Train: [32] [3100/6250] eta: 0:09:14 lr: 0.000101 grad: 0.0693 (0.0723) loss: 0.8294 (0.8327) time: 0.1827 data: 0.0994 max mem: 9390 +Train: [32] [3200/6250] eta: 0:08:56 lr: 0.000101 grad: 0.0689 (0.0723) loss: 0.8315 (0.8326) time: 0.1732 data: 0.0772 max mem: 9390 +Train: [32] [3300/6250] eta: 0:08:37 lr: 0.000101 grad: 0.0676 (0.0723) loss: 0.8323 (0.8325) time: 0.1562 data: 0.0761 max mem: 9390 +Train: [32] [3400/6250] eta: 0:08:19 lr: 0.000101 grad: 0.0658 (0.0723) loss: 0.8311 (0.8325) time: 0.1565 data: 0.0693 max mem: 9390 +Train: [32] [3500/6250] eta: 0:08:01 lr: 0.000101 grad: 0.0689 (0.0722) loss: 0.8234 (0.8324) time: 0.1910 data: 0.1051 max mem: 9390 +Train: [32] [3600/6250] eta: 0:07:42 lr: 0.000101 grad: 0.0716 (0.0722) loss: 0.8309 (0.8323) time: 0.1532 data: 0.0678 max mem: 9390 +Train: [32] [3700/6250] eta: 0:07:25 lr: 0.000101 grad: 0.0668 (0.0721) loss: 0.8293 (0.8323) time: 0.1856 data: 0.0984 max mem: 9390 +Train: [32] [3800/6250] eta: 0:07:07 lr: 0.000101 grad: 0.0696 (0.0720) loss: 0.8343 (0.8323) time: 0.1730 data: 0.0816 max mem: 9390 +Train: [32] [3900/6250] eta: 0:06:49 lr: 0.000101 grad: 0.0658 (0.0719) loss: 0.8367 (0.8323) time: 0.1448 data: 0.0610 max mem: 9390 +Train: [32] [4000/6250] eta: 0:06:31 lr: 0.000101 grad: 0.0698 (0.0719) loss: 0.8321 (0.8323) time: 0.1644 data: 0.0746 max mem: 9390 +Train: [32] [4100/6250] eta: 0:06:13 lr: 0.000101 grad: 0.0665 (0.0719) loss: 0.8306 (0.8323) time: 0.2021 data: 0.1162 max mem: 9390 +Train: [32] [4200/6250] eta: 0:05:55 lr: 0.000101 grad: 0.0690 (0.0718) loss: 0.8341 (0.8324) time: 0.1593 data: 0.0744 max mem: 9390 +Train: [32] [4300/6250] eta: 0:05:38 lr: 0.000101 grad: 0.0709 (0.0718) loss: 0.8278 (0.8324) time: 0.1889 data: 0.1086 max mem: 9390 +Train: [32] [4400/6250] eta: 0:05:20 lr: 0.000101 grad: 0.0706 (0.0719) loss: 0.8364 (0.8324) time: 0.1535 data: 0.0654 max mem: 9390 +Train: [32] [4500/6250] eta: 0:05:02 lr: 0.000101 grad: 0.0760 (0.0719) loss: 0.8302 (0.8324) time: 0.1813 data: 0.0955 max mem: 9390 +Train: [32] [4600/6250] eta: 0:04:44 lr: 0.000101 grad: 0.0708 (0.0719) loss: 0.8275 (0.8324) time: 0.1398 data: 0.0478 max mem: 9390 +Train: [32] [4700/6250] eta: 0:04:27 lr: 0.000100 grad: 0.0716 (0.0720) loss: 0.8317 (0.8324) time: 0.1808 data: 0.0901 max mem: 9390 +Train: [32] [4800/6250] eta: 0:04:10 lr: 0.000100 grad: 0.0681 (0.0720) loss: 0.8367 (0.8324) time: 0.1893 data: 0.1117 max mem: 9390 +Train: [32] [4900/6250] eta: 0:03:53 lr: 0.000100 grad: 0.0731 (0.0721) loss: 0.8297 (0.8324) time: 0.1749 data: 0.0883 max mem: 9390 +Train: [32] [5000/6250] eta: 0:03:35 lr: 0.000100 grad: 0.0708 (0.0722) loss: 0.8307 (0.8324) time: 0.1583 data: 0.0646 max mem: 9390 +Train: [32] [5100/6250] eta: 0:03:18 lr: 0.000100 grad: 0.0652 (0.0722) loss: 0.8406 (0.8324) time: 0.1428 data: 0.0611 max mem: 9390 +Train: [32] [5200/6250] eta: 0:03:01 lr: 0.000100 grad: 0.0650 (0.0723) loss: 0.8346 (0.8324) time: 0.1951 data: 0.1118 max mem: 9390 +Train: [32] [5300/6250] eta: 0:02:44 lr: 0.000100 grad: 0.0710 (0.0724) loss: 0.8326 (0.8324) time: 0.1692 data: 0.0861 max mem: 9390 +Train: [32] [5400/6250] eta: 0:02:27 lr: 0.000100 grad: 0.0674 (0.0724) loss: 0.8308 (0.8324) time: 0.1639 data: 0.0687 max mem: 9390 +Train: [32] [5500/6250] eta: 0:02:09 lr: 0.000100 grad: 0.0727 (0.0724) loss: 0.8371 (0.8324) time: 0.1624 data: 0.0844 max mem: 9390 +Train: [32] [5600/6250] eta: 0:01:52 lr: 0.000100 grad: 0.0688 (0.0725) loss: 0.8322 (0.8324) time: 0.1888 data: 0.0920 max mem: 9390 +Train: [32] [5700/6250] eta: 0:01:34 lr: 0.000100 grad: 0.0739 (0.0725) loss: 0.8319 (0.8324) time: 0.1753 data: 0.0767 max mem: 9390 +Train: [32] [5800/6250] eta: 0:01:17 lr: 0.000100 grad: 0.0687 (0.0725) loss: 0.8328 (0.8324) time: 0.1602 data: 0.0734 max mem: 9390 +Train: [32] [5900/6250] eta: 0:01:00 lr: 0.000100 grad: 0.0755 (0.0725) loss: 0.8314 (0.8324) time: 0.1705 data: 0.0754 max mem: 9390 +Train: [32] [6000/6250] eta: 0:00:43 lr: 0.000100 grad: 0.0702 (0.0725) loss: 0.8366 (0.8324) time: 0.1546 data: 0.0536 max mem: 9390 +Train: [32] [6100/6250] eta: 0:00:25 lr: 0.000100 grad: 0.0675 (0.0726) loss: 0.8299 (0.8324) time: 0.1418 data: 0.0481 max mem: 9390 +Train: [32] [6200/6250] eta: 0:00:08 lr: 0.000100 grad: 0.0749 (0.0726) loss: 0.8282 (0.8324) time: 0.1519 data: 0.0481 max mem: 9390 +Train: [32] [6249/6250] eta: 0:00:00 lr: 0.000100 grad: 0.0694 (0.0726) loss: 0.8304 (0.8323) time: 0.1580 data: 0.0661 max mem: 9390 +Train: [32] Total time: 0:18:01 (0.1730 s / it) +Averaged stats: lr: 0.000100 grad: 0.0694 (0.0726) loss: 0.8304 (0.8323) +Eval (hcp-train-subset): [32] [ 0/62] eta: 0:03:42 loss: 0.8517 (0.8517) time: 3.5930 data: 3.5119 max mem: 9390 +Eval (hcp-train-subset): [32] [61/62] eta: 0:00:00 loss: 0.8376 (0.8415) time: 0.1365 data: 0.1074 max mem: 9390 +Eval (hcp-train-subset): [32] Total time: 0:00:13 (0.2236 s / it) +Averaged stats (hcp-train-subset): loss: 0.8376 (0.8415) +Eval (hcp-val): [32] [ 0/62] eta: 0:04:40 loss: 0.8397 (0.8397) time: 4.5241 data: 4.4941 max mem: 9390 +Eval (hcp-val): [32] [61/62] eta: 0:00:00 loss: 0.8379 (0.8393) time: 0.1170 data: 0.0913 max mem: 9390 +Eval (hcp-val): [32] Total time: 0:00:13 (0.2155 s / it) +Averaged stats (hcp-val): loss: 0.8379 (0.8393) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +Train: [33] [ 0/6250] eta: 10:44:32 lr: 0.000100 grad: 0.0522 (0.0522) loss: 0.8711 (0.8711) time: 6.1876 data: 6.0820 max mem: 9390 +Train: [33] [ 100/6250] eta: 0:22:31 lr: 0.000100 grad: 0.0647 (0.0673) loss: 0.8472 (0.8547) time: 0.1563 data: 0.0482 max mem: 9390 +Train: [33] [ 200/6250] eta: 0:20:45 lr: 0.000100 grad: 0.0687 (0.0694) loss: 0.8411 (0.8474) time: 0.2068 data: 0.0963 max mem: 9390 +Train: [33] [ 300/6250] eta: 0:19:54 lr: 0.000100 grad: 0.0693 (0.0707) loss: 0.8331 (0.8438) time: 0.1989 data: 0.1160 max mem: 9390 +Train: [33] [ 400/6250] eta: 0:19:18 lr: 0.000100 grad: 0.0731 (0.0716) loss: 0.8254 (0.8405) time: 0.2021 data: 0.1211 max mem: 9390 +Train: [33] [ 500/6250] eta: 0:18:41 lr: 0.000100 grad: 0.0692 (0.0720) loss: 0.8328 (0.8383) time: 0.1604 data: 0.0636 max mem: 9390 +Train: [33] [ 600/6250] eta: 0:18:30 lr: 0.000100 grad: 0.0684 (0.0717) loss: 0.8248 (0.8367) time: 0.2461 data: 0.1673 max mem: 9390 +Train: [33] [ 700/6250] eta: 0:18:20 lr: 0.000100 grad: 0.0696 (0.0721) loss: 0.8191 (0.8351) time: 0.2190 data: 0.1261 max mem: 9390 +Train: [33] [ 800/6250] eta: 0:18:04 lr: 0.000100 grad: 0.0641 (0.0721) loss: 0.8299 (0.8344) time: 0.1829 data: 0.0875 max mem: 9390 +Train: [33] [ 900/6250] eta: 0:17:46 lr: 0.000100 grad: 0.0661 (0.0718) loss: 0.8279 (0.8336) time: 0.1919 data: 0.0961 max mem: 9390 +Train: [33] [1000/6250] eta: 0:17:21 lr: 0.000100 grad: 0.0693 (0.0718) loss: 0.8276 (0.8332) time: 0.1561 data: 0.0684 max mem: 9390 +Train: [33] [1100/6250] eta: 0:16:53 lr: 0.000100 grad: 0.0683 (0.0719) loss: 0.8277 (0.8328) time: 0.1746 data: 0.0871 max mem: 9390 +Train: [33] [1200/6250] eta: 0:16:21 lr: 0.000100 grad: 0.0729 (0.0721) loss: 0.8271 (0.8323) time: 0.1518 data: 0.0563 max mem: 9390 +Train: [33] [1300/6250] eta: 0:15:54 lr: 0.000100 grad: 0.0695 (0.0719) loss: 0.8238 (0.8319) time: 0.1683 data: 0.0732 max mem: 9390 +Train: [33] [1400/6250] eta: 0:15:29 lr: 0.000100 grad: 0.0741 (0.0722) loss: 0.8194 (0.8313) time: 0.1796 data: 0.0924 max mem: 9390 +Train: [33] [1500/6250] eta: 0:15:04 lr: 0.000100 grad: 0.0747 (0.0725) loss: 0.8228 (0.8308) time: 0.1908 data: 0.1061 max mem: 9390 +Train: [33] [1600/6250] eta: 0:14:40 lr: 0.000100 grad: 0.0719 (0.0725) loss: 0.8279 (0.8304) time: 0.1603 data: 0.0695 max mem: 9390 +Train: [33] [1700/6250] eta: 0:14:18 lr: 0.000100 grad: 0.0772 (0.0728) loss: 0.8263 (0.8301) time: 0.1887 data: 0.0971 max mem: 9390 +Train: [33] [1800/6250] eta: 0:13:54 lr: 0.000100 grad: 0.0704 (0.0728) loss: 0.8260 (0.8299) time: 0.1696 data: 0.0857 max mem: 9390 +Train: [33] [1900/6250] eta: 0:13:31 lr: 0.000100 grad: 0.0698 (0.0728) loss: 0.8295 (0.8298) time: 0.1381 data: 0.0553 max mem: 9390 +Train: [33] [2000/6250] eta: 0:13:09 lr: 0.000100 grad: 0.0732 (0.0729) loss: 0.8330 (0.8296) time: 0.1748 data: 0.0804 max mem: 9390 +Train: [33] [2100/6250] eta: 0:12:45 lr: 0.000100 grad: 0.0707 (0.0730) loss: 0.8285 (0.8295) time: 0.1559 data: 0.0606 max mem: 9390 +Train: [33] [2200/6250] eta: 0:12:24 lr: 0.000099 grad: 0.0702 (0.0731) loss: 0.8314 (0.8295) time: 0.1674 data: 0.0848 max mem: 9390 +Train: [33] [2300/6250] eta: 0:12:03 lr: 0.000099 grad: 0.0688 (0.0731) loss: 0.8295 (0.8294) time: 0.1619 data: 0.0711 max mem: 9390 +Train: [33] [2400/6250] eta: 0:11:42 lr: 0.000099 grad: 0.0717 (0.0731) loss: 0.8328 (0.8294) time: 0.1747 data: 0.0840 max mem: 9390 +Train: [33] [2500/6250] eta: 0:11:22 lr: 0.000099 grad: 0.0719 (0.0733) loss: 0.8350 (0.8293) time: 0.1629 data: 0.0792 max mem: 9390 +Train: [33] [2600/6250] eta: 0:11:03 lr: 0.000099 grad: 0.0700 (0.0733) loss: 0.8282 (0.8293) time: 0.1724 data: 0.0898 max mem: 9390 +Train: [33] [2700/6250] eta: 0:10:43 lr: 0.000099 grad: 0.0768 (0.0734) loss: 0.8249 (0.8292) time: 0.1852 data: 0.0983 max mem: 9390 +Train: [33] [2800/6250] eta: 0:10:24 lr: 0.000099 grad: 0.0732 (0.0736) loss: 0.8270 (0.8292) time: 0.1771 data: 0.0918 max mem: 9390 +Train: [33] [2900/6250] eta: 0:10:04 lr: 0.000099 grad: 0.0757 (0.0737) loss: 0.8215 (0.8292) time: 0.1693 data: 0.0775 max mem: 9390 +Train: [33] [3000/6250] eta: 0:09:45 lr: 0.000099 grad: 0.0700 (0.0738) loss: 0.8285 (0.8291) time: 0.1770 data: 0.0868 max mem: 9390 +Train: [33] [3100/6250] eta: 0:09:26 lr: 0.000099 grad: 0.0724 (0.0739) loss: 0.8282 (0.8290) time: 0.1765 data: 0.0869 max mem: 9390 +Train: [33] [3200/6250] eta: 0:09:07 lr: 0.000099 grad: 0.0761 (0.0739) loss: 0.8306 (0.8290) time: 0.1867 data: 0.1064 max mem: 9390 +Train: [33] [3300/6250] eta: 0:08:48 lr: 0.000099 grad: 0.0784 (0.0740) loss: 0.8295 (0.8290) time: 0.1654 data: 0.0758 max mem: 9390 +Train: [33] [3400/6250] eta: 0:08:29 lr: 0.000099 grad: 0.0759 (0.0740) loss: 0.8292 (0.8290) time: 0.1633 data: 0.0811 max mem: 9390 +Train: [33] [3500/6250] eta: 0:08:11 lr: 0.000099 grad: 0.0697 (0.0740) loss: 0.8260 (0.8290) time: 0.1681 data: 0.0793 max mem: 9390 +Train: [33] [3600/6250] eta: 0:07:53 lr: 0.000099 grad: 0.0778 (0.0741) loss: 0.8281 (0.8290) time: 0.1557 data: 0.0724 max mem: 9390 +Train: [33] [3700/6250] eta: 0:07:35 lr: 0.000099 grad: 0.0711 (0.0741) loss: 0.8249 (0.8290) time: 0.1834 data: 0.0950 max mem: 9390 +Train: [33] [3800/6250] eta: 0:07:16 lr: 0.000099 grad: 0.0735 (0.0742) loss: 0.8274 (0.8290) time: 0.1794 data: 0.0951 max mem: 9390 +Train: [33] [3900/6250] eta: 0:06:58 lr: 0.000099 grad: 0.0737 (0.0742) loss: 0.8260 (0.8290) time: 0.1630 data: 0.0694 max mem: 9390 +Train: [33] [4000/6250] eta: 0:06:39 lr: 0.000099 grad: 0.0734 (0.0742) loss: 0.8321 (0.8290) time: 0.1460 data: 0.0576 max mem: 9390 +Train: [33] [4100/6250] eta: 0:06:21 lr: 0.000099 grad: 0.0740 (0.0743) loss: 0.8301 (0.8290) time: 0.1684 data: 0.0767 max mem: 9390 +Train: [33] [4200/6250] eta: 0:06:03 lr: 0.000099 grad: 0.0706 (0.0743) loss: 0.8315 (0.8290) time: 0.1963 data: 0.1052 max mem: 9390 +Train: [33] [4300/6250] eta: 0:05:45 lr: 0.000099 grad: 0.0711 (0.0743) loss: 0.8320 (0.8291) time: 0.1883 data: 0.1030 max mem: 9390 +Train: [33] [4400/6250] eta: 0:05:26 lr: 0.000099 grad: 0.0667 (0.0742) loss: 0.8346 (0.8292) time: 0.1523 data: 0.0718 max mem: 9390 +Train: [33] [4500/6250] eta: 0:05:08 lr: 0.000099 grad: 0.0730 (0.0742) loss: 0.8307 (0.8292) time: 0.1817 data: 0.0990 max mem: 9390 +Train: [33] [4600/6250] eta: 0:04:50 lr: 0.000099 grad: 0.0698 (0.0742) loss: 0.8317 (0.8293) time: 0.1707 data: 0.0796 max mem: 9390 +Train: [33] [4700/6250] eta: 0:04:32 lr: 0.000099 grad: 0.0674 (0.0741) loss: 0.8343 (0.8294) time: 0.1613 data: 0.0699 max mem: 9390 +Train: [33] [4800/6250] eta: 0:04:15 lr: 0.000099 grad: 0.0716 (0.0740) loss: 0.8328 (0.8294) time: 0.1884 data: 0.1050 max mem: 9390 +Train: [33] [4900/6250] eta: 0:03:57 lr: 0.000099 grad: 0.0730 (0.0740) loss: 0.8293 (0.8295) time: 0.1556 data: 0.0674 max mem: 9390 +Train: [33] [5000/6250] eta: 0:03:39 lr: 0.000099 grad: 0.0725 (0.0740) loss: 0.8275 (0.8295) time: 0.1725 data: 0.0822 max mem: 9390 +Train: [33] [5100/6250] eta: 0:03:21 lr: 0.000099 grad: 0.0662 (0.0740) loss: 0.8358 (0.8294) time: 0.1583 data: 0.0700 max mem: 9390 +Train: [33] [5200/6250] eta: 0:03:03 lr: 0.000099 grad: 0.0703 (0.0740) loss: 0.8270 (0.8295) time: 0.1870 data: 0.0930 max mem: 9390 +Train: [33] [5300/6250] eta: 0:02:46 lr: 0.000099 grad: 0.0720 (0.0739) loss: 0.8291 (0.8294) time: 0.1533 data: 0.0583 max mem: 9390 +Train: [33] [5400/6250] eta: 0:02:28 lr: 0.000099 grad: 0.0736 (0.0739) loss: 0.8329 (0.8295) time: 0.1635 data: 0.0735 max mem: 9390 +Train: [33] [5500/6250] eta: 0:02:11 lr: 0.000099 grad: 0.0701 (0.0739) loss: 0.8352 (0.8295) time: 0.1536 data: 0.0685 max mem: 9390 +Train: [33] [5600/6250] eta: 0:01:53 lr: 0.000099 grad: 0.0729 (0.0739) loss: 0.8309 (0.8295) time: 0.1600 data: 0.0723 max mem: 9390 +Train: [33] [5700/6250] eta: 0:01:35 lr: 0.000099 grad: 0.0758 (0.0740) loss: 0.8268 (0.8294) time: 0.1666 data: 0.0767 max mem: 9390 +Train: [33] [5800/6250] eta: 0:01:18 lr: 0.000099 grad: 0.0747 (0.0740) loss: 0.8294 (0.8294) time: 0.1588 data: 0.0632 max mem: 9390 +Train: [33] [5900/6250] eta: 0:01:00 lr: 0.000098 grad: 0.0725 (0.0740) loss: 0.8339 (0.8294) time: 0.1417 data: 0.0457 max mem: 9390 +Train: [33] [6000/6250] eta: 0:00:43 lr: 0.000098 grad: 0.0762 (0.0740) loss: 0.8299 (0.8295) time: 0.1308 data: 0.0374 max mem: 9390 +Train: [33] [6100/6250] eta: 0:00:26 lr: 0.000098 grad: 0.0725 (0.0740) loss: 0.8301 (0.8295) time: 0.1993 data: 0.1193 max mem: 9390 +Train: [33] [6200/6250] eta: 0:00:08 lr: 0.000098 grad: 0.0771 (0.0740) loss: 0.8286 (0.8295) time: 0.1351 data: 0.0457 max mem: 9390 +Train: [33] [6249/6250] eta: 0:00:00 lr: 0.000098 grad: 0.0714 (0.0740) loss: 0.8204 (0.8295) time: 0.1621 data: 0.0740 max mem: 9390 +Train: [33] Total time: 0:18:11 (0.1746 s / it) +Averaged stats: lr: 0.000098 grad: 0.0714 (0.0740) loss: 0.8204 (0.8295) +Eval (hcp-train-subset): [33] [ 0/62] eta: 0:05:48 loss: 0.8492 (0.8492) time: 5.6224 data: 5.5876 max mem: 9390 +Eval (hcp-train-subset): [33] [61/62] eta: 0:00:00 loss: 0.8387 (0.8402) time: 0.1348 data: 0.1066 max mem: 9390 +Eval (hcp-train-subset): [33] Total time: 0:00:13 (0.2225 s / it) +Averaged stats (hcp-train-subset): loss: 0.8387 (0.8402) +Eval (hcp-val): [33] [ 0/62] eta: 0:03:49 loss: 0.8372 (0.8372) time: 3.6971 data: 3.6212 max mem: 9390 +Eval (hcp-val): [33] [61/62] eta: 0:00:00 loss: 0.8380 (0.8387) time: 0.1304 data: 0.1044 max mem: 9390 +Eval (hcp-val): [33] Total time: 0:00:13 (0.2199 s / it) +Averaged stats (hcp-val): loss: 0.8380 (0.8387) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +Train: [34] [ 0/6250] eta: 9:38:21 lr: 0.000098 grad: 0.0784 (0.0784) loss: 0.8277 (0.8277) time: 5.5522 data: 5.3968 max mem: 9390 +Train: [34] [ 100/6250] eta: 0:23:22 lr: 0.000098 grad: 0.0703 (0.0820) loss: 0.8357 (0.8361) time: 0.1724 data: 0.0796 max mem: 9390 +Train: [34] [ 200/6250] eta: 0:20:05 lr: 0.000098 grad: 0.0691 (0.0808) loss: 0.8275 (0.8293) time: 0.1606 data: 0.0489 max mem: 9390 +Train: [34] [ 300/6250] eta: 0:19:43 lr: 0.000098 grad: 0.0714 (0.0787) loss: 0.8307 (0.8288) time: 0.2184 data: 0.1260 max mem: 9390 +Train: [34] [ 400/6250] eta: 0:18:44 lr: 0.000098 grad: 0.0711 (0.0785) loss: 0.8284 (0.8290) time: 0.1946 data: 0.1047 max mem: 9390 +Train: [34] [ 500/6250] eta: 0:17:58 lr: 0.000098 grad: 0.0752 (0.0781) loss: 0.8334 (0.8290) time: 0.1632 data: 0.0655 max mem: 9390 +Train: [34] [ 600/6250] eta: 0:17:33 lr: 0.000098 grad: 0.0784 (0.0778) loss: 0.8310 (0.8295) time: 0.1887 data: 0.0973 max mem: 9390 +Train: [34] [ 700/6250] eta: 0:17:18 lr: 0.000098 grad: 0.0764 (0.0778) loss: 0.8308 (0.8297) time: 0.2061 data: 0.1126 max mem: 9390 +Train: [34] [ 800/6250] eta: 0:17:03 lr: 0.000098 grad: 0.0734 (0.0777) loss: 0.8348 (0.8297) time: 0.2161 data: 0.1142 max mem: 9390 +Train: [34] [ 900/6250] eta: 0:16:46 lr: 0.000098 grad: 0.0730 (0.0779) loss: 0.8374 (0.8300) time: 0.2003 data: 0.1143 max mem: 9390 +Train: [34] [1000/6250] eta: 0:16:28 lr: 0.000098 grad: 0.0730 (0.0777) loss: 0.8323 (0.8301) time: 0.1850 data: 0.0954 max mem: 9390 +Train: [34] [1100/6250] eta: 0:16:08 lr: 0.000098 grad: 0.0722 (0.0775) loss: 0.8300 (0.8300) time: 0.1666 data: 0.0707 max mem: 9390 +Train: [34] [1200/6250] eta: 0:15:46 lr: 0.000098 grad: 0.0748 (0.0774) loss: 0.8197 (0.8298) time: 0.1655 data: 0.0761 max mem: 9390 +Train: [34] [1300/6250] eta: 0:15:21 lr: 0.000098 grad: 0.0740 (0.0772) loss: 0.8319 (0.8298) time: 0.1553 data: 0.0612 max mem: 9390 +Train: [34] [1400/6250] eta: 0:14:57 lr: 0.000098 grad: 0.0747 (0.0772) loss: 0.8284 (0.8296) time: 0.1702 data: 0.0769 max mem: 9390 +Train: [34] [1500/6250] eta: 0:14:33 lr: 0.000098 grad: 0.0782 (0.0771) loss: 0.8259 (0.8295) time: 0.1596 data: 0.0642 max mem: 9390 +Train: [34] [1600/6250] eta: 0:14:11 lr: 0.000098 grad: 0.0757 (0.0770) loss: 0.8235 (0.8293) time: 0.1719 data: 0.0785 max mem: 9390 +Train: [34] [1700/6250] eta: 0:13:49 lr: 0.000098 grad: 0.0770 (0.0771) loss: 0.8267 (0.8290) time: 0.1701 data: 0.0852 max mem: 9390 +Train: [34] [1800/6250] eta: 0:13:29 lr: 0.000098 grad: 0.0750 (0.0772) loss: 0.8324 (0.8289) time: 0.1269 data: 0.0401 max mem: 9390 +Train: [34] [1900/6250] eta: 0:13:07 lr: 0.000098 grad: 0.0725 (0.0772) loss: 0.8315 (0.8289) time: 0.1902 data: 0.1026 max mem: 9390 +Train: [34] [2000/6250] eta: 0:12:44 lr: 0.000098 grad: 0.0773 (0.0773) loss: 0.8271 (0.8289) time: 0.1539 data: 0.0672 max mem: 9390 +Train: [34] [2100/6250] eta: 0:12:24 lr: 0.000098 grad: 0.0731 (0.0773) loss: 0.8269 (0.8288) time: 0.1717 data: 0.0816 max mem: 9390 +Train: [34] [2200/6250] eta: 0:12:04 lr: 0.000098 grad: 0.0751 (0.0774) loss: 0.8226 (0.8288) time: 0.1736 data: 0.0876 max mem: 9390 +Train: [34] [2300/6250] eta: 0:11:45 lr: 0.000098 grad: 0.0782 (0.0774) loss: 0.8287 (0.8287) time: 0.1578 data: 0.0743 max mem: 9390 +Train: [34] [2400/6250] eta: 0:11:25 lr: 0.000098 grad: 0.0694 (0.0774) loss: 0.8293 (0.8286) time: 0.1594 data: 0.0730 max mem: 9390 +Train: [34] [2500/6250] eta: 0:11:04 lr: 0.000098 grad: 0.0730 (0.0774) loss: 0.8271 (0.8287) time: 0.1628 data: 0.0761 max mem: 9390 +Train: [34] [2600/6250] eta: 0:10:44 lr: 0.000098 grad: 0.0736 (0.0774) loss: 0.8298 (0.8287) time: 0.1634 data: 0.0754 max mem: 9390 +Train: [34] [2700/6250] eta: 0:10:26 lr: 0.000098 grad: 0.0709 (0.0773) loss: 0.8322 (0.8288) time: 0.2113 data: 0.1203 max mem: 9390 +Train: [34] [2800/6250] eta: 0:10:07 lr: 0.000098 grad: 0.0765 (0.0774) loss: 0.8322 (0.8289) time: 0.1802 data: 0.0913 max mem: 9390 +Train: [34] [2900/6250] eta: 0:09:47 lr: 0.000098 grad: 0.0761 (0.0774) loss: 0.8281 (0.8289) time: 0.1450 data: 0.0614 max mem: 9390 +Train: [34] [3000/6250] eta: 0:09:29 lr: 0.000098 grad: 0.0730 (0.0773) loss: 0.8278 (0.8289) time: 0.1918 data: 0.0987 max mem: 9390 +Train: [34] [3100/6250] eta: 0:09:11 lr: 0.000098 grad: 0.0699 (0.0773) loss: 0.8317 (0.8290) time: 0.1714 data: 0.0810 max mem: 9390 +Train: [34] [3200/6250] eta: 0:08:53 lr: 0.000098 grad: 0.0756 (0.0773) loss: 0.8257 (0.8290) time: 0.1552 data: 0.0678 max mem: 9390 +Train: [34] [3300/6250] eta: 0:08:35 lr: 0.000097 grad: 0.0751 (0.0773) loss: 0.8277 (0.8291) time: 0.1591 data: 0.0763 max mem: 9390 +Train: [34] [3400/6250] eta: 0:08:17 lr: 0.000097 grad: 0.0689 (0.0773) loss: 0.8306 (0.8291) time: 0.1418 data: 0.0525 max mem: 9390 +Train: [34] [3500/6250] eta: 0:07:59 lr: 0.000097 grad: 0.0751 (0.0773) loss: 0.8339 (0.8292) time: 0.1546 data: 0.0660 max mem: 9390 +Train: [34] [3600/6250] eta: 0:07:42 lr: 0.000097 grad: 0.0774 (0.0772) loss: 0.8289 (0.8292) time: 0.2212 data: 0.1438 max mem: 9390 +Train: [34] [3700/6250] eta: 0:07:25 lr: 0.000097 grad: 0.0757 (0.0772) loss: 0.8236 (0.8292) time: 0.1807 data: 0.0941 max mem: 9390 +Train: [34] [3800/6250] eta: 0:07:07 lr: 0.000097 grad: 0.0727 (0.0772) loss: 0.8312 (0.8292) time: 0.1588 data: 0.0731 max mem: 9390 +Train: [34] [3900/6250] eta: 0:06:49 lr: 0.000097 grad: 0.0729 (0.0772) loss: 0.8292 (0.8291) time: 0.1656 data: 0.0830 max mem: 9390 +Train: [34] [4000/6250] eta: 0:06:32 lr: 0.000097 grad: 0.0715 (0.0771) loss: 0.8317 (0.8292) time: 0.1751 data: 0.0850 max mem: 9390 +Train: [34] [4100/6250] eta: 0:06:15 lr: 0.000097 grad: 0.0789 (0.0772) loss: 0.8304 (0.8291) time: 0.1896 data: 0.0962 max mem: 9390 +Train: [34] [4200/6250] eta: 0:05:57 lr: 0.000097 grad: 0.0735 (0.0771) loss: 0.8303 (0.8291) time: 0.1527 data: 0.0703 max mem: 9390 +Train: [34] [4300/6250] eta: 0:05:39 lr: 0.000097 grad: 0.0732 (0.0770) loss: 0.8260 (0.8291) time: 0.1661 data: 0.0799 max mem: 9390 +Train: [34] [4400/6250] eta: 0:05:21 lr: 0.000097 grad: 0.0738 (0.0770) loss: 0.8301 (0.8291) time: 0.1629 data: 0.0535 max mem: 9390 +Train: [34] [4500/6250] eta: 0:05:04 lr: 0.000097 grad: 0.0713 (0.0770) loss: 0.8304 (0.8291) time: 0.1715 data: 0.0835 max mem: 9390 +Train: [34] [4600/6250] eta: 0:04:46 lr: 0.000097 grad: 0.0735 (0.0769) loss: 0.8303 (0.8292) time: 0.1671 data: 0.0732 max mem: 9390 +Train: [34] [4700/6250] eta: 0:04:29 lr: 0.000097 grad: 0.0722 (0.0768) loss: 0.8372 (0.8292) time: 0.2062 data: 0.1112 max mem: 9390 +Train: [34] [4800/6250] eta: 0:04:13 lr: 0.000097 grad: 0.0694 (0.0768) loss: 0.8313 (0.8293) time: 0.1782 data: 0.0613 max mem: 9390 +Train: [34] [4900/6250] eta: 0:03:55 lr: 0.000097 grad: 0.0750 (0.0768) loss: 0.8255 (0.8293) time: 0.1416 data: 0.0394 max mem: 9390 +Train: [34] [5000/6250] eta: 0:03:37 lr: 0.000097 grad: 0.0744 (0.0767) loss: 0.8278 (0.8293) time: 0.1708 data: 0.0821 max mem: 9390 +Train: [34] [5100/6250] eta: 0:03:20 lr: 0.000097 grad: 0.0699 (0.0767) loss: 0.8237 (0.8293) time: 0.1611 data: 0.0676 max mem: 9390 +Train: [34] [5200/6250] eta: 0:03:02 lr: 0.000097 grad: 0.0693 (0.0766) loss: 0.8299 (0.8293) time: 0.1677 data: 0.0780 max mem: 9390 +Train: [34] [5300/6250] eta: 0:02:45 lr: 0.000097 grad: 0.0728 (0.0765) loss: 0.8337 (0.8294) time: 0.1725 data: 0.0832 max mem: 9390 +Train: [34] [5400/6250] eta: 0:02:28 lr: 0.000097 grad: 0.0710 (0.0765) loss: 0.8239 (0.8294) time: 0.1640 data: 0.0597 max mem: 9390 +Train: [34] [5500/6250] eta: 0:02:10 lr: 0.000097 grad: 0.0682 (0.0764) loss: 0.8307 (0.8294) time: 0.1618 data: 0.0675 max mem: 9390 +Train: [34] [5600/6250] eta: 0:01:53 lr: 0.000097 grad: 0.0741 (0.0765) loss: 0.8251 (0.8293) time: 0.1873 data: 0.0992 max mem: 9390 +Train: [34] [5700/6250] eta: 0:01:35 lr: 0.000097 grad: 0.0680 (0.0764) loss: 0.8345 (0.8293) time: 0.1523 data: 0.0604 max mem: 9390 +Train: [34] [5800/6250] eta: 0:01:18 lr: 0.000097 grad: 0.0796 (0.0765) loss: 0.8260 (0.8293) time: 0.1809 data: 0.0939 max mem: 9390 +Train: [34] [5900/6250] eta: 0:01:00 lr: 0.000097 grad: 0.0786 (0.0766) loss: 0.8223 (0.8292) time: 0.1693 data: 0.0797 max mem: 9390 +Train: [34] [6000/6250] eta: 0:00:43 lr: 0.000097 grad: 0.0699 (0.0766) loss: 0.8319 (0.8291) time: 0.1600 data: 0.0698 max mem: 9390 +Train: [34] [6100/6250] eta: 0:00:26 lr: 0.000097 grad: 0.0715 (0.0766) loss: 0.8320 (0.8291) time: 0.1922 data: 0.1113 max mem: 9390 +Train: [34] [6200/6250] eta: 0:00:08 lr: 0.000097 grad: 0.0710 (0.0766) loss: 0.8261 (0.8290) time: 0.1841 data: 0.0990 max mem: 9390 +Train: [34] [6249/6250] eta: 0:00:00 lr: 0.000097 grad: 0.0747 (0.0766) loss: 0.8213 (0.8290) time: 0.1938 data: 0.1098 max mem: 9390 +Train: [34] Total time: 0:18:14 (0.1751 s / it) +Averaged stats: lr: 0.000097 grad: 0.0747 (0.0766) loss: 0.8213 (0.8290) +Eval (hcp-train-subset): [34] [ 0/62] eta: 0:04:06 loss: 0.8520 (0.8520) time: 3.9730 data: 3.8827 max mem: 9390 +Eval (hcp-train-subset): [34] [61/62] eta: 0:00:00 loss: 0.8393 (0.8395) time: 0.1173 data: 0.0902 max mem: 9390 +Eval (hcp-train-subset): [34] Total time: 0:00:13 (0.2170 s / it) +Averaged stats (hcp-train-subset): loss: 0.8393 (0.8395) +Making plots (hcp-train-subset): example=61 +Eval (hcp-val): [34] [ 0/62] eta: 0:03:09 loss: 0.8350 (0.8350) time: 3.0521 data: 2.9721 max mem: 9390 +Eval (hcp-val): [34] [61/62] eta: 0:00:00 loss: 0.8380 (0.8386) time: 0.1321 data: 0.1048 max mem: 9390 +Eval (hcp-val): [34] Total time: 0:00:13 (0.2218 s / it) +Averaged stats (hcp-val): loss: 0.8380 (0.8386) +Making plots (hcp-val): example=48 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +Train: [35] [ 0/6250] eta: 7:13:15 lr: 0.000097 grad: 0.1570 (0.1570) loss: 0.8238 (0.8238) time: 4.1592 data: 3.9308 max mem: 9390 +Train: [35] [ 100/6250] eta: 0:22:07 lr: 0.000097 grad: 0.0741 (0.0790) loss: 0.8344 (0.8412) time: 0.1681 data: 0.0693 max mem: 9390 +Train: [35] [ 200/6250] eta: 0:20:04 lr: 0.000097 grad: 0.0700 (0.0765) loss: 0.8281 (0.8377) time: 0.1709 data: 0.0840 max mem: 9390 +Train: [35] [ 300/6250] eta: 0:19:11 lr: 0.000097 grad: 0.0689 (0.0747) loss: 0.8400 (0.8372) time: 0.1734 data: 0.0675 max mem: 9390 +Train: [35] [ 400/6250] eta: 0:18:29 lr: 0.000097 grad: 0.0648 (0.0733) loss: 0.8401 (0.8371) time: 0.1481 data: 0.0540 max mem: 9390 +Train: [35] [ 500/6250] eta: 0:18:06 lr: 0.000097 grad: 0.0772 (0.0730) loss: 0.8379 (0.8364) time: 0.2014 data: 0.1159 max mem: 9390 +Train: [35] [ 600/6250] eta: 0:17:31 lr: 0.000097 grad: 0.0734 (0.0728) loss: 0.8320 (0.8353) time: 0.1666 data: 0.0806 max mem: 9390 +Train: [35] [ 700/6250] eta: 0:17:22 lr: 0.000096 grad: 0.0726 (0.0732) loss: 0.8308 (0.8345) time: 0.1636 data: 0.0758 max mem: 9390 +Train: [35] [ 800/6250] eta: 0:17:05 lr: 0.000096 grad: 0.0662 (0.0730) loss: 0.8382 (0.8341) time: 0.1783 data: 0.0982 max mem: 9390 +Train: [35] [ 900/6250] eta: 0:16:47 lr: 0.000096 grad: 0.0699 (0.0729) loss: 0.8309 (0.8337) time: 0.2134 data: 0.1231 max mem: 9390 +Train: [35] [1000/6250] eta: 0:16:25 lr: 0.000096 grad: 0.0675 (0.0727) loss: 0.8281 (0.8335) time: 0.1681 data: 0.0741 max mem: 9390 +Train: [35] [1100/6250] eta: 0:16:00 lr: 0.000096 grad: 0.0695 (0.0724) loss: 0.8308 (0.8334) time: 0.1449 data: 0.0507 max mem: 9390 +Train: [35] [1200/6250] eta: 0:15:37 lr: 0.000096 grad: 0.0704 (0.0724) loss: 0.8258 (0.8330) time: 0.1640 data: 0.0735 max mem: 9390 +Train: [35] [1300/6250] eta: 0:15:14 lr: 0.000096 grad: 0.0729 (0.0725) loss: 0.8291 (0.8326) time: 0.1810 data: 0.0937 max mem: 9390 +Train: [35] [1400/6250] eta: 0:14:51 lr: 0.000096 grad: 0.0671 (0.0726) loss: 0.8316 (0.8323) time: 0.1827 data: 0.0892 max mem: 9390 +Train: [35] [1500/6250] eta: 0:14:28 lr: 0.000096 grad: 0.0693 (0.0726) loss: 0.8264 (0.8321) time: 0.1668 data: 0.0819 max mem: 9390 +Train: [35] [1600/6250] eta: 0:14:07 lr: 0.000096 grad: 0.0718 (0.0728) loss: 0.8336 (0.8319) time: 0.1825 data: 0.0846 max mem: 9390 +Train: [35] [1700/6250] eta: 0:13:46 lr: 0.000096 grad: 0.0744 (0.0729) loss: 0.8326 (0.8319) time: 0.1831 data: 0.0997 max mem: 9390 +Train: [35] [1800/6250] eta: 0:13:26 lr: 0.000096 grad: 0.0702 (0.0729) loss: 0.8338 (0.8318) time: 0.1761 data: 0.0885 max mem: 9390 +Train: [35] [1900/6250] eta: 0:13:05 lr: 0.000096 grad: 0.0708 (0.0729) loss: 0.8262 (0.8317) time: 0.1657 data: 0.0794 max mem: 9390 +Train: [35] [2000/6250] eta: 0:12:45 lr: 0.000096 grad: 0.0744 (0.0733) loss: 0.8333 (0.8317) time: 0.1800 data: 0.0931 max mem: 9390 +Train: [35] [2100/6250] eta: 0:12:23 lr: 0.000096 grad: 0.0712 (0.0733) loss: 0.8265 (0.8316) time: 0.1682 data: 0.0807 max mem: 9390 +Train: [35] [2200/6250] eta: 0:12:03 lr: 0.000096 grad: 0.0677 (0.0732) loss: 0.8279 (0.8316) time: 0.1416 data: 0.0551 max mem: 9390 +Train: [35] [2300/6250] eta: 0:11:44 lr: 0.000096 grad: 0.0722 (0.0731) loss: 0.8307 (0.8316) time: 0.1701 data: 0.0809 max mem: 9390 +Train: [35] [2400/6250] eta: 0:11:24 lr: 0.000096 grad: 0.0716 (0.0730) loss: 0.8336 (0.8316) time: 0.1360 data: 0.0537 max mem: 9390 +Train: [35] [2500/6250] eta: 0:11:03 lr: 0.000096 grad: 0.0727 (0.0731) loss: 0.8324 (0.8316) time: 0.1639 data: 0.0631 max mem: 9390 +Train: [35] [2600/6250] eta: 0:10:45 lr: 0.000096 grad: 0.0741 (0.0730) loss: 0.8284 (0.8317) time: 0.1671 data: 0.0824 max mem: 9390 +Train: [35] [2700/6250] eta: 0:10:26 lr: 0.000096 grad: 0.0694 (0.0729) loss: 0.8326 (0.8317) time: 0.1846 data: 0.1062 max mem: 9390 +Train: [35] [2800/6250] eta: 0:10:07 lr: 0.000096 grad: 0.0691 (0.0729) loss: 0.8324 (0.8317) time: 0.1612 data: 0.0715 max mem: 9390 +Train: [35] [2900/6250] eta: 0:09:48 lr: 0.000096 grad: 0.0705 (0.0729) loss: 0.8340 (0.8317) time: 0.1570 data: 0.0699 max mem: 9390 +Train: [35] [3000/6250] eta: 0:09:29 lr: 0.000096 grad: 0.0700 (0.0729) loss: 0.8354 (0.8317) time: 0.1687 data: 0.0775 max mem: 9390 +Train: [35] [3100/6250] eta: 0:09:10 lr: 0.000096 grad: 0.0685 (0.0728) loss: 0.8328 (0.8317) time: 0.1416 data: 0.0482 max mem: 9390 +Train: [35] [3200/6250] eta: 0:08:53 lr: 0.000096 grad: 0.0717 (0.0728) loss: 0.8301 (0.8317) time: 0.1769 data: 0.0923 max mem: 9390 +Train: [35] [3300/6250] eta: 0:08:35 lr: 0.000096 grad: 0.0704 (0.0727) loss: 0.8322 (0.8317) time: 0.1491 data: 0.0609 max mem: 9390 +Train: [35] [3400/6250] eta: 0:08:16 lr: 0.000096 grad: 0.0737 (0.0727) loss: 0.8333 (0.8317) time: 0.1714 data: 0.0889 max mem: 9390 +Train: [35] [3500/6250] eta: 0:07:58 lr: 0.000096 grad: 0.0686 (0.0727) loss: 0.8341 (0.8317) time: 0.1760 data: 0.0900 max mem: 9390 +Train: [35] [3600/6250] eta: 0:07:40 lr: 0.000096 grad: 0.0751 (0.0727) loss: 0.8315 (0.8317) time: 0.1626 data: 0.0764 max mem: 9390 +Train: [35] [3700/6250] eta: 0:07:22 lr: 0.000096 grad: 0.0686 (0.0727) loss: 0.8334 (0.8316) time: 0.1695 data: 0.0841 max mem: 9390 +Train: [35] [3800/6250] eta: 0:07:04 lr: 0.000096 grad: 0.0741 (0.0728) loss: 0.8318 (0.8316) time: 0.1728 data: 0.0902 max mem: 9390 +Train: [35] [3900/6250] eta: 0:06:46 lr: 0.000096 grad: 0.0718 (0.0728) loss: 0.8307 (0.8316) time: 0.1593 data: 0.0656 max mem: 9390 +Train: [35] [4000/6250] eta: 0:06:30 lr: 0.000096 grad: 0.0792 (0.0729) loss: 0.8255 (0.8315) time: 0.2068 data: 0.1182 max mem: 9390 +Train: [35] [4100/6250] eta: 0:06:12 lr: 0.000096 grad: 0.0744 (0.0730) loss: 0.8277 (0.8315) time: 0.1753 data: 0.0927 max mem: 9390 +Train: [35] [4200/6250] eta: 0:05:54 lr: 0.000096 grad: 0.0778 (0.0731) loss: 0.8301 (0.8314) time: 0.2029 data: 0.1136 max mem: 9390 +Train: [35] [4300/6250] eta: 0:05:37 lr: 0.000095 grad: 0.0712 (0.0731) loss: 0.8339 (0.8314) time: 0.1894 data: 0.1047 max mem: 9390 +Train: [35] [4400/6250] eta: 0:05:20 lr: 0.000095 grad: 0.0754 (0.0732) loss: 0.8272 (0.8314) time: 0.2037 data: 0.1158 max mem: 9390 +Train: [35] [4500/6250] eta: 0:05:02 lr: 0.000095 grad: 0.0784 (0.0733) loss: 0.8262 (0.8313) time: 0.1607 data: 0.0723 max mem: 9390 +Train: [35] [4600/6250] eta: 0:04:44 lr: 0.000095 grad: 0.0785 (0.0734) loss: 0.8287 (0.8312) time: 0.1779 data: 0.0893 max mem: 9390 +Train: [35] [4700/6250] eta: 0:04:27 lr: 0.000095 grad: 0.0747 (0.0735) loss: 0.8246 (0.8311) time: 0.1794 data: 0.0872 max mem: 9390 +Train: [35] [4800/6250] eta: 0:04:09 lr: 0.000095 grad: 0.0803 (0.0736) loss: 0.8200 (0.8310) time: 0.1612 data: 0.0803 max mem: 9390 +Train: [35] [4900/6250] eta: 0:03:52 lr: 0.000095 grad: 0.0776 (0.0738) loss: 0.8208 (0.8308) time: 0.1904 data: 0.1046 max mem: 9390 +Train: [35] [5000/6250] eta: 0:03:35 lr: 0.000095 grad: 0.0722 (0.0738) loss: 0.8275 (0.8307) time: 0.1799 data: 0.0946 max mem: 9390 +Train: [35] [5100/6250] eta: 0:03:17 lr: 0.000095 grad: 0.0774 (0.0739) loss: 0.8242 (0.8306) time: 0.1984 data: 0.1080 max mem: 9390 +Train: [35] [5200/6250] eta: 0:03:00 lr: 0.000095 grad: 0.0720 (0.0740) loss: 0.8277 (0.8305) time: 0.1702 data: 0.0827 max mem: 9390 +Train: [35] [5300/6250] eta: 0:02:43 lr: 0.000095 grad: 0.0745 (0.0742) loss: 0.8292 (0.8304) time: 0.1683 data: 0.0838 max mem: 9390 +Train: [35] [5400/6250] eta: 0:02:26 lr: 0.000095 grad: 0.0741 (0.0743) loss: 0.8330 (0.8303) time: 0.1584 data: 0.0684 max mem: 9390 +Train: [35] [5500/6250] eta: 0:02:08 lr: 0.000095 grad: 0.0757 (0.0744) loss: 0.8266 (0.8302) time: 0.1687 data: 0.0803 max mem: 9390 +Train: [35] [5600/6250] eta: 0:01:51 lr: 0.000095 grad: 0.0822 (0.0744) loss: 0.8216 (0.8301) time: 0.1606 data: 0.0724 max mem: 9390 +Train: [35] [5700/6250] eta: 0:01:34 lr: 0.000095 grad: 0.0741 (0.0745) loss: 0.8269 (0.8301) time: 0.1642 data: 0.0849 max mem: 9390 +Train: [35] [5800/6250] eta: 0:01:17 lr: 0.000095 grad: 0.0771 (0.0746) loss: 0.8202 (0.8299) time: 0.1752 data: 0.0854 max mem: 9390 +Train: [35] [5900/6250] eta: 0:01:00 lr: 0.000095 grad: 0.0767 (0.0747) loss: 0.8229 (0.8298) time: 0.1406 data: 0.0466 max mem: 9390 +Train: [35] [6000/6250] eta: 0:00:42 lr: 0.000095 grad: 0.0752 (0.0748) loss: 0.8263 (0.8297) time: 0.1667 data: 0.0799 max mem: 9390 +Train: [35] [6100/6250] eta: 0:00:25 lr: 0.000095 grad: 0.0822 (0.0750) loss: 0.8297 (0.8296) time: 0.1803 data: 0.0936 max mem: 9390 +Train: [35] [6200/6250] eta: 0:00:08 lr: 0.000095 grad: 0.0714 (0.0750) loss: 0.8234 (0.8296) time: 0.1599 data: 0.0740 max mem: 9390 +Train: [35] [6249/6250] eta: 0:00:00 lr: 0.000095 grad: 0.0779 (0.0751) loss: 0.8270 (0.8295) time: 0.1656 data: 0.0832 max mem: 9390 +Train: [35] Total time: 0:17:55 (0.1720 s / it) +Averaged stats: lr: 0.000095 grad: 0.0779 (0.0751) loss: 0.8270 (0.8295) +Eval (hcp-train-subset): [35] [ 0/62] eta: 0:05:38 loss: 0.8505 (0.8505) time: 5.4516 data: 5.4216 max mem: 9390 +Eval (hcp-train-subset): [35] [61/62] eta: 0:00:00 loss: 0.8418 (0.8423) time: 0.1324 data: 0.1050 max mem: 9390 +Eval (hcp-train-subset): [35] Total time: 0:00:14 (0.2324 s / it) +Averaged stats (hcp-train-subset): loss: 0.8418 (0.8423) +Eval (hcp-val): [35] [ 0/62] eta: 0:04:07 loss: 0.8390 (0.8390) time: 4.0000 data: 3.9241 max mem: 9390 +Eval (hcp-val): [35] [61/62] eta: 0:00:00 loss: 0.8376 (0.8395) time: 0.1213 data: 0.0943 max mem: 9390 +Eval (hcp-val): [35] Total time: 0:00:13 (0.2253 s / it) +Averaged stats (hcp-val): loss: 0.8376 (0.8395) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +Train: [36] [ 0/6250] eta: 8:30:17 lr: 0.000095 grad: 0.0467 (0.0467) loss: 0.8581 (0.8581) time: 4.8988 data: 4.6786 max mem: 9390 +Train: [36] [ 100/6250] eta: 0:22:51 lr: 0.000095 grad: 0.0724 (0.0839) loss: 0.8264 (0.8296) time: 0.1681 data: 0.0780 max mem: 9390 +Train: [36] [ 200/6250] eta: 0:20:29 lr: 0.000095 grad: 0.0687 (0.0800) loss: 0.8362 (0.8270) time: 0.1760 data: 0.0783 max mem: 9390 +Train: [36] [ 300/6250] eta: 0:19:58 lr: 0.000095 grad: 0.0691 (0.0791) loss: 0.8273 (0.8255) time: 0.1986 data: 0.1030 max mem: 9390 +Train: [36] [ 400/6250] eta: 0:18:57 lr: 0.000095 grad: 0.0700 (0.0775) loss: 0.8250 (0.8252) time: 0.1685 data: 0.0750 max mem: 9390 +Train: [36] [ 500/6250] eta: 0:18:30 lr: 0.000095 grad: 0.0697 (0.0767) loss: 0.8252 (0.8256) time: 0.2215 data: 0.1320 max mem: 9390 +Train: [36] [ 600/6250] eta: 0:17:59 lr: 0.000095 grad: 0.0681 (0.0761) loss: 0.8316 (0.8260) time: 0.1681 data: 0.0752 max mem: 9390 +Train: [36] [ 700/6250] eta: 0:17:48 lr: 0.000095 grad: 0.0696 (0.0755) loss: 0.8258 (0.8265) time: 0.1994 data: 0.1127 max mem: 9390 +Train: [36] [ 800/6250] eta: 0:17:26 lr: 0.000095 grad: 0.0683 (0.0750) loss: 0.8254 (0.8270) time: 0.1857 data: 0.0965 max mem: 9390 +Train: [36] [ 900/6250] eta: 0:17:03 lr: 0.000095 grad: 0.0650 (0.0746) loss: 0.8251 (0.8272) time: 0.1956 data: 0.0917 max mem: 9390 +Train: [36] [1000/6250] eta: 0:16:41 lr: 0.000095 grad: 0.0714 (0.0744) loss: 0.8316 (0.8274) time: 0.1542 data: 0.0676 max mem: 9390 +Train: [36] [1100/6250] eta: 0:16:14 lr: 0.000095 grad: 0.0689 (0.0742) loss: 0.8307 (0.8275) time: 0.1622 data: 0.0639 max mem: 9390 +Train: [36] [1200/6250] eta: 0:15:47 lr: 0.000095 grad: 0.0724 (0.0740) loss: 0.8257 (0.8274) time: 0.1655 data: 0.0839 max mem: 9390 +Train: [36] [1300/6250] eta: 0:15:24 lr: 0.000095 grad: 0.0705 (0.0741) loss: 0.8230 (0.8273) time: 0.1884 data: 0.0981 max mem: 9390 +Train: [36] [1400/6250] eta: 0:15:00 lr: 0.000095 grad: 0.0723 (0.0739) loss: 0.8229 (0.8274) time: 0.1840 data: 0.1004 max mem: 9390 +Train: [36] [1500/6250] eta: 0:14:35 lr: 0.000095 grad: 0.0728 (0.0738) loss: 0.8258 (0.8275) time: 0.1690 data: 0.0801 max mem: 9390 +Train: [36] [1600/6250] eta: 0:14:10 lr: 0.000094 grad: 0.0705 (0.0738) loss: 0.8292 (0.8276) time: 0.1544 data: 0.0653 max mem: 9390 +Train: [36] [1700/6250] eta: 0:13:49 lr: 0.000094 grad: 0.0704 (0.0737) loss: 0.8303 (0.8276) time: 0.1743 data: 0.0817 max mem: 9390 +Train: [36] [1800/6250] eta: 0:13:26 lr: 0.000094 grad: 0.0711 (0.0738) loss: 0.8234 (0.8276) time: 0.1823 data: 0.0942 max mem: 9390 +Train: [36] [1900/6250] eta: 0:13:07 lr: 0.000094 grad: 0.0770 (0.0739) loss: 0.8266 (0.8276) time: 0.1573 data: 0.0631 max mem: 9390 +Train: [36] [2000/6250] eta: 0:12:56 lr: 0.000094 grad: 0.0757 (0.0741) loss: 0.8287 (0.8275) time: 0.2451 data: 0.1349 max mem: 9390 +Train: [36] [2100/6250] eta: 0:12:29 lr: 0.000094 grad: 0.0716 (0.0744) loss: 0.8294 (0.8275) time: 0.1378 data: 0.0480 max mem: 9390 +Train: [36] [2200/6250] eta: 0:12:08 lr: 0.000094 grad: 0.0735 (0.0747) loss: 0.8308 (0.8275) time: 0.1560 data: 0.0680 max mem: 9390 +Train: [36] [2300/6250] eta: 0:11:48 lr: 0.000094 grad: 0.0706 (0.0746) loss: 0.8353 (0.8276) time: 0.1916 data: 0.1118 max mem: 9390 +Train: [36] [2400/6250] eta: 0:11:31 lr: 0.000094 grad: 0.0757 (0.0746) loss: 0.8308 (0.8276) time: 0.1376 data: 0.0590 max mem: 9390 +Train: [36] [2500/6250] eta: 0:11:10 lr: 0.000094 grad: 0.0715 (0.0746) loss: 0.8254 (0.8276) time: 0.1472 data: 0.0658 max mem: 9390 +Train: [36] [2600/6250] eta: 0:10:51 lr: 0.000094 grad: 0.0705 (0.0746) loss: 0.8324 (0.8277) time: 0.1778 data: 0.0919 max mem: 9390 +Train: [36] [2700/6250] eta: 0:10:30 lr: 0.000094 grad: 0.0690 (0.0746) loss: 0.8321 (0.8277) time: 0.1663 data: 0.0823 max mem: 9390 +Train: [36] [2800/6250] eta: 0:10:12 lr: 0.000094 grad: 0.0754 (0.0746) loss: 0.8289 (0.8278) time: 0.1756 data: 0.0880 max mem: 9390 +Train: [36] [2900/6250] eta: 0:09:56 lr: 0.000094 grad: 0.0744 (0.0746) loss: 0.8259 (0.8278) time: 0.1925 data: 0.1160 max mem: 9390 +Train: [36] [3000/6250] eta: 0:09:38 lr: 0.000094 grad: 0.0705 (0.0746) loss: 0.8304 (0.8278) time: 0.1596 data: 0.0778 max mem: 9390 +Train: [36] [3100/6250] eta: 0:09:18 lr: 0.000094 grad: 0.0721 (0.0747) loss: 0.8283 (0.8278) time: 0.1438 data: 0.0481 max mem: 9390 +Train: [36] [3200/6250] eta: 0:09:00 lr: 0.000094 grad: 0.0784 (0.0748) loss: 0.8271 (0.8278) time: 0.1507 data: 0.0679 max mem: 9390 +Train: [36] [3300/6250] eta: 0:08:42 lr: 0.000094 grad: 0.0705 (0.0749) loss: 0.8285 (0.8278) time: 0.1630 data: 0.0708 max mem: 9390 +Train: [36] [3400/6250] eta: 0:08:25 lr: 0.000094 grad: 0.0748 (0.0749) loss: 0.8272 (0.8278) time: 0.1994 data: 0.1106 max mem: 9390 +Train: [36] [3500/6250] eta: 0:08:10 lr: 0.000094 grad: 0.0745 (0.0749) loss: 0.8276 (0.8278) time: 0.2211 data: 0.1134 max mem: 9390 +Train: [36] [3600/6250] eta: 0:07:52 lr: 0.000094 grad: 0.0728 (0.0750) loss: 0.8296 (0.8278) time: 0.1781 data: 0.0830 max mem: 9390 +Train: [36] [3700/6250] eta: 0:07:34 lr: 0.000094 grad: 0.0787 (0.0751) loss: 0.8230 (0.8278) time: 0.1680 data: 0.0840 max mem: 9390 +Train: [36] [3800/6250] eta: 0:07:16 lr: 0.000094 grad: 0.0747 (0.0751) loss: 0.8269 (0.8277) time: 0.1323 data: 0.0353 max mem: 9390 +Train: [36] [3900/6250] eta: 0:06:57 lr: 0.000094 grad: 0.0737 (0.0752) loss: 0.8290 (0.8277) time: 0.1745 data: 0.0838 max mem: 9390 +Train: [36] [4000/6250] eta: 0:06:39 lr: 0.000094 grad: 0.0747 (0.0753) loss: 0.8304 (0.8278) time: 0.1650 data: 0.0781 max mem: 9390 +Train: [36] [4100/6250] eta: 0:06:21 lr: 0.000094 grad: 0.0785 (0.0754) loss: 0.8306 (0.8278) time: 0.1662 data: 0.0755 max mem: 9390 +Train: [36] [4200/6250] eta: 0:06:04 lr: 0.000094 grad: 0.0742 (0.0754) loss: 0.8297 (0.8278) time: 0.1667 data: 0.0783 max mem: 9390 +Train: [36] [4300/6250] eta: 0:05:46 lr: 0.000094 grad: 0.0736 (0.0755) loss: 0.8257 (0.8278) time: 0.1714 data: 0.0802 max mem: 9390 +Train: [36] [4400/6250] eta: 0:05:28 lr: 0.000094 grad: 0.0712 (0.0755) loss: 0.8248 (0.8278) time: 0.1568 data: 0.0721 max mem: 9390 +Train: [36] [4500/6250] eta: 0:05:10 lr: 0.000094 grad: 0.0705 (0.0756) loss: 0.8296 (0.8278) time: 0.1857 data: 0.0971 max mem: 9390 +Train: [36] [4600/6250] eta: 0:04:52 lr: 0.000094 grad: 0.0722 (0.0756) loss: 0.8256 (0.8277) time: 0.1689 data: 0.0878 max mem: 9390 +Train: [36] [4700/6250] eta: 0:04:34 lr: 0.000094 grad: 0.0753 (0.0756) loss: 0.8256 (0.8277) time: 0.1890 data: 0.1028 max mem: 9390 +Train: [36] [4800/6250] eta: 0:04:16 lr: 0.000094 grad: 0.0708 (0.0757) loss: 0.8203 (0.8276) time: 0.1835 data: 0.0953 max mem: 9390 +Train: [36] [4900/6250] eta: 0:03:58 lr: 0.000094 grad: 0.0736 (0.0757) loss: 0.8226 (0.8275) time: 0.1736 data: 0.0867 max mem: 9390 +Train: [36] [5000/6250] eta: 0:03:40 lr: 0.000094 grad: 0.0735 (0.0758) loss: 0.8232 (0.8274) time: 0.1807 data: 0.0939 max mem: 9390 +Train: [36] [5100/6250] eta: 0:03:22 lr: 0.000093 grad: 0.0757 (0.0758) loss: 0.8212 (0.8273) time: 0.1548 data: 0.0696 max mem: 9390 +Train: [36] [5200/6250] eta: 0:03:04 lr: 0.000093 grad: 0.0742 (0.0759) loss: 0.8258 (0.8272) time: 0.1592 data: 0.0765 max mem: 9390 +Train: [36] [5300/6250] eta: 0:02:46 lr: 0.000093 grad: 0.0718 (0.0759) loss: 0.8209 (0.8271) time: 0.1859 data: 0.1011 max mem: 9390 +Train: [36] [5400/6250] eta: 0:02:29 lr: 0.000093 grad: 0.0776 (0.0760) loss: 0.8200 (0.8270) time: 0.1545 data: 0.0618 max mem: 9390 +Train: [36] [5500/6250] eta: 0:02:11 lr: 0.000093 grad: 0.0797 (0.0760) loss: 0.8211 (0.8269) time: 0.1683 data: 0.0781 max mem: 9390 +Train: [36] [5600/6250] eta: 0:01:53 lr: 0.000093 grad: 0.0745 (0.0760) loss: 0.8252 (0.8269) time: 0.1617 data: 0.0740 max mem: 9390 +Train: [36] [5700/6250] eta: 0:01:36 lr: 0.000093 grad: 0.0777 (0.0761) loss: 0.8287 (0.8268) time: 0.1536 data: 0.0660 max mem: 9390 +Train: [36] [5800/6250] eta: 0:01:18 lr: 0.000093 grad: 0.0781 (0.0761) loss: 0.8158 (0.8267) time: 0.1675 data: 0.0803 max mem: 9390 +Train: [36] [5900/6250] eta: 0:01:01 lr: 0.000093 grad: 0.0744 (0.0761) loss: 0.8221 (0.8266) time: 0.1638 data: 0.0739 max mem: 9390 +Train: [36] [6000/6250] eta: 0:00:43 lr: 0.000093 grad: 0.0771 (0.0762) loss: 0.8269 (0.8266) time: 0.1804 data: 0.0986 max mem: 9390 +Train: [36] [6100/6250] eta: 0:00:26 lr: 0.000093 grad: 0.0735 (0.0762) loss: 0.8254 (0.8265) time: 0.1309 data: 0.0439 max mem: 9390 +Train: [36] [6200/6250] eta: 0:00:08 lr: 0.000093 grad: 0.0707 (0.0762) loss: 0.8287 (0.8265) time: 0.1806 data: 0.0957 max mem: 9390 +Train: [36] [6249/6250] eta: 0:00:00 lr: 0.000093 grad: 0.0753 (0.0762) loss: 0.8159 (0.8265) time: 0.2070 data: 0.1273 max mem: 9390 +Train: [36] Total time: 0:18:15 (0.1753 s / it) +Averaged stats: lr: 0.000093 grad: 0.0753 (0.0762) loss: 0.8159 (0.8265) +Eval (hcp-train-subset): [36] [ 0/62] eta: 0:05:29 loss: 0.8522 (0.8522) time: 5.3171 data: 5.2839 max mem: 9390 +Eval (hcp-train-subset): [36] [61/62] eta: 0:00:00 loss: 0.8407 (0.8406) time: 0.1204 data: 0.0947 max mem: 9390 +Eval (hcp-train-subset): [36] Total time: 0:00:14 (0.2261 s / it) +Averaged stats (hcp-train-subset): loss: 0.8407 (0.8406) +Eval (hcp-val): [36] [ 0/62] eta: 0:04:28 loss: 0.8326 (0.8326) time: 4.3329 data: 4.2809 max mem: 9390 +Eval (hcp-val): [36] [61/62] eta: 0:00:00 loss: 0.8366 (0.8379) time: 0.1002 data: 0.0750 max mem: 9390 +Eval (hcp-val): [36] Total time: 0:00:13 (0.2195 s / it) +Averaged stats (hcp-val): loss: 0.8366 (0.8379) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +Train: [37] [ 0/6250] eta: 10:24:22 lr: 0.000093 grad: 0.2125 (0.2125) loss: 0.8308 (0.8308) time: 5.9940 data: 5.8613 max mem: 9390 +Train: [37] [ 100/6250] eta: 0:23:15 lr: 0.000093 grad: 0.0755 (0.0869) loss: 0.8286 (0.8356) time: 0.1763 data: 0.0705 max mem: 9390 +Train: [37] [ 200/6250] eta: 0:21:51 lr: 0.000093 grad: 0.0775 (0.0834) loss: 0.8214 (0.8301) time: 0.2711 data: 0.1811 max mem: 9390 +Train: [37] [ 300/6250] eta: 0:20:07 lr: 0.000093 grad: 0.0736 (0.0816) loss: 0.8226 (0.8283) time: 0.1971 data: 0.0974 max mem: 9390 +Train: [37] [ 400/6250] eta: 0:18:59 lr: 0.000093 grad: 0.0684 (0.0809) loss: 0.8351 (0.8276) time: 0.1522 data: 0.0488 max mem: 9390 +Train: [37] [ 500/6250] eta: 0:18:22 lr: 0.000093 grad: 0.0738 (0.0800) loss: 0.8253 (0.8275) time: 0.2013 data: 0.1150 max mem: 9390 +Train: [37] [ 600/6250] eta: 0:17:45 lr: 0.000093 grad: 0.0763 (0.0792) loss: 0.8230 (0.8274) time: 0.1835 data: 0.0967 max mem: 9390 +Train: [37] [ 700/6250] eta: 0:17:41 lr: 0.000093 grad: 0.0731 (0.0788) loss: 0.8243 (0.8272) time: 0.2161 data: 0.1244 max mem: 9390 +Train: [37] [ 800/6250] eta: 0:17:12 lr: 0.000093 grad: 0.0715 (0.0784) loss: 0.8253 (0.8270) time: 0.1717 data: 0.0931 max mem: 9390 +Train: [37] [ 900/6250] eta: 0:16:52 lr: 0.000093 grad: 0.0702 (0.0784) loss: 0.8288 (0.8269) time: 0.1853 data: 0.0998 max mem: 9390 +Train: [37] [1000/6250] eta: 0:16:34 lr: 0.000093 grad: 0.0720 (0.0781) loss: 0.8234 (0.8269) time: 0.1930 data: 0.1029 max mem: 9390 +Train: [37] [1100/6250] eta: 0:16:06 lr: 0.000093 grad: 0.0711 (0.0779) loss: 0.8197 (0.8268) time: 0.1803 data: 0.0917 max mem: 9390 +Train: [37] [1200/6250] eta: 0:15:45 lr: 0.000093 grad: 0.0728 (0.0777) loss: 0.8296 (0.8267) time: 0.1976 data: 0.1154 max mem: 9390 +Train: [37] [1300/6250] eta: 0:15:20 lr: 0.000093 grad: 0.0733 (0.0776) loss: 0.8239 (0.8265) time: 0.1896 data: 0.0983 max mem: 9390 +Train: [37] [1400/6250] eta: 0:14:55 lr: 0.000093 grad: 0.0782 (0.0775) loss: 0.8309 (0.8265) time: 0.1647 data: 0.0670 max mem: 9390 +Train: [37] [1500/6250] eta: 0:14:31 lr: 0.000093 grad: 0.0759 (0.0776) loss: 0.8266 (0.8266) time: 0.1637 data: 0.0735 max mem: 9390 +Train: [37] [1600/6250] eta: 0:14:11 lr: 0.000093 grad: 0.0807 (0.0775) loss: 0.8214 (0.8265) time: 0.2095 data: 0.1278 max mem: 9390 +Train: [37] [1700/6250] eta: 0:13:47 lr: 0.000093 grad: 0.0772 (0.0775) loss: 0.8273 (0.8264) time: 0.1627 data: 0.0769 max mem: 9390 +Train: [37] [1800/6250] eta: 0:13:27 lr: 0.000093 grad: 0.0758 (0.0774) loss: 0.8271 (0.8264) time: 0.1637 data: 0.0722 max mem: 9390 +Train: [37] [1900/6250] eta: 0:13:06 lr: 0.000093 grad: 0.0713 (0.0773) loss: 0.8287 (0.8265) time: 0.1116 data: 0.0292 max mem: 9390 +Train: [37] [2000/6250] eta: 0:12:46 lr: 0.000093 grad: 0.0741 (0.0774) loss: 0.8269 (0.8265) time: 0.1769 data: 0.0876 max mem: 9390 +Train: [37] [2100/6250] eta: 0:12:24 lr: 0.000093 grad: 0.0774 (0.0774) loss: 0.8285 (0.8265) time: 0.1380 data: 0.0523 max mem: 9390 +Train: [37] [2200/6250] eta: 0:12:06 lr: 0.000093 grad: 0.0780 (0.0774) loss: 0.8265 (0.8264) time: 0.1826 data: 0.0917 max mem: 9390 +Train: [37] [2300/6250] eta: 0:11:46 lr: 0.000092 grad: 0.0774 (0.0773) loss: 0.8225 (0.8263) time: 0.1841 data: 0.0960 max mem: 9390 +Train: [37] [2400/6250] eta: 0:11:25 lr: 0.000092 grad: 0.0750 (0.0773) loss: 0.8260 (0.8261) time: 0.1577 data: 0.0718 max mem: 9390 +Train: [37] [2500/6250] eta: 0:11:05 lr: 0.000092 grad: 0.0790 (0.0774) loss: 0.8167 (0.8260) time: 0.1393 data: 0.0485 max mem: 9390 +Train: [37] [2600/6250] eta: 0:10:47 lr: 0.000092 grad: 0.0753 (0.0775) loss: 0.8256 (0.8259) time: 0.1988 data: 0.1131 max mem: 9390 +Train: [37] [2700/6250] eta: 0:10:28 lr: 0.000092 grad: 0.0775 (0.0775) loss: 0.8212 (0.8259) time: 0.1841 data: 0.1025 max mem: 9390 +Train: [37] [2800/6250] eta: 0:10:11 lr: 0.000092 grad: 0.0767 (0.0775) loss: 0.8260 (0.8259) time: 0.1360 data: 0.0476 max mem: 9390 +Train: [37] [2900/6250] eta: 0:09:52 lr: 0.000092 grad: 0.0763 (0.0775) loss: 0.8275 (0.8259) time: 0.1297 data: 0.0395 max mem: 9390 +Train: [37] [3000/6250] eta: 0:09:37 lr: 0.000092 grad: 0.0702 (0.0775) loss: 0.8323 (0.8260) time: 0.3201 data: 0.2353 max mem: 9390 +Train: [37] [3100/6250] eta: 0:09:17 lr: 0.000092 grad: 0.0736 (0.0775) loss: 0.8282 (0.8261) time: 0.1877 data: 0.0907 max mem: 9390 +Train: [37] [3200/6250] eta: 0:08:58 lr: 0.000092 grad: 0.0732 (0.0774) loss: 0.8310 (0.8261) time: 0.1945 data: 0.1070 max mem: 9390 +Train: [37] [3300/6250] eta: 0:08:41 lr: 0.000092 grad: 0.0737 (0.0774) loss: 0.8279 (0.8261) time: 0.2037 data: 0.1175 max mem: 9390 +Train: [37] [3400/6250] eta: 0:08:23 lr: 0.000092 grad: 0.0739 (0.0774) loss: 0.8276 (0.8260) time: 0.1823 data: 0.0958 max mem: 9390 +Train: [37] [3500/6250] eta: 0:08:05 lr: 0.000092 grad: 0.0757 (0.0774) loss: 0.8234 (0.8260) time: 0.1643 data: 0.0738 max mem: 9390 +Train: [37] [3600/6250] eta: 0:07:47 lr: 0.000092 grad: 0.0766 (0.0774) loss: 0.8255 (0.8260) time: 0.1729 data: 0.0888 max mem: 9390 +Train: [37] [3700/6250] eta: 0:07:29 lr: 0.000092 grad: 0.0774 (0.0774) loss: 0.8202 (0.8260) time: 0.1626 data: 0.0696 max mem: 9390 +Train: [37] [3800/6250] eta: 0:07:12 lr: 0.000092 grad: 0.0760 (0.0774) loss: 0.8230 (0.8259) time: 0.1238 data: 0.0234 max mem: 9390 +Train: [37] [3900/6250] eta: 0:06:54 lr: 0.000092 grad: 0.0745 (0.0774) loss: 0.8262 (0.8260) time: 0.1719 data: 0.0800 max mem: 9390 +Train: [37] [4000/6250] eta: 0:06:36 lr: 0.000092 grad: 0.0740 (0.0774) loss: 0.8285 (0.8260) time: 0.1780 data: 0.0937 max mem: 9390 +Train: [37] [4100/6250] eta: 0:06:18 lr: 0.000092 grad: 0.0735 (0.0773) loss: 0.8283 (0.8261) time: 0.1716 data: 0.0744 max mem: 9390 +Train: [37] [4200/6250] eta: 0:06:02 lr: 0.000092 grad: 0.0711 (0.0773) loss: 0.8323 (0.8261) time: 0.1941 data: 0.1064 max mem: 9390 +Train: [37] [4300/6250] eta: 0:05:44 lr: 0.000092 grad: 0.0772 (0.0773) loss: 0.8269 (0.8262) time: 0.1638 data: 0.0657 max mem: 9390 +Train: [37] [4400/6250] eta: 0:05:26 lr: 0.000092 grad: 0.0748 (0.0773) loss: 0.8225 (0.8262) time: 0.1720 data: 0.0838 max mem: 9390 +Train: [37] [4500/6250] eta: 0:05:08 lr: 0.000092 grad: 0.0762 (0.0773) loss: 0.8262 (0.8262) time: 0.1520 data: 0.0432 max mem: 9390 +Train: [37] [4600/6250] eta: 0:04:51 lr: 0.000092 grad: 0.0773 (0.0773) loss: 0.8285 (0.8262) time: 0.1746 data: 0.0884 max mem: 9390 +Train: [37] [4700/6250] eta: 0:04:33 lr: 0.000092 grad: 0.0753 (0.0774) loss: 0.8286 (0.8263) time: 0.1752 data: 0.0744 max mem: 9390 +Train: [37] [4800/6250] eta: 0:04:15 lr: 0.000092 grad: 0.0763 (0.0774) loss: 0.8207 (0.8263) time: 0.1834 data: 0.1058 max mem: 9390 +Train: [37] [4900/6250] eta: 0:03:58 lr: 0.000092 grad: 0.0743 (0.0774) loss: 0.8276 (0.8263) time: 0.1523 data: 0.0530 max mem: 9390 +Train: [37] [5000/6250] eta: 0:03:40 lr: 0.000092 grad: 0.0775 (0.0774) loss: 0.8245 (0.8262) time: 0.1390 data: 0.0397 max mem: 9390 +Train: [37] [5100/6250] eta: 0:03:23 lr: 0.000092 grad: 0.0693 (0.0775) loss: 0.8311 (0.8262) time: 0.1813 data: 0.0902 max mem: 9390 +Train: [37] [5200/6250] eta: 0:03:05 lr: 0.000092 grad: 0.0772 (0.0775) loss: 0.8199 (0.8262) time: 0.1732 data: 0.0869 max mem: 9390 +Train: [37] [5300/6250] eta: 0:02:47 lr: 0.000092 grad: 0.0805 (0.0776) loss: 0.8220 (0.8262) time: 0.1121 data: 0.0115 max mem: 9390 +Train: [37] [5400/6250] eta: 0:02:30 lr: 0.000092 grad: 0.0743 (0.0776) loss: 0.8215 (0.8262) time: 0.1639 data: 0.0766 max mem: 9390 +Train: [37] [5500/6250] eta: 0:02:12 lr: 0.000092 grad: 0.0763 (0.0776) loss: 0.8230 (0.8262) time: 0.1522 data: 0.0591 max mem: 9390 +Train: [37] [5600/6250] eta: 0:01:54 lr: 0.000092 grad: 0.0793 (0.0776) loss: 0.8255 (0.8262) time: 0.1471 data: 0.0605 max mem: 9390 +Train: [37] [5700/6250] eta: 0:01:37 lr: 0.000091 grad: 0.0767 (0.0777) loss: 0.8273 (0.8262) time: 0.2202 data: 0.1282 max mem: 9390 +Train: [37] [5800/6250] eta: 0:01:19 lr: 0.000091 grad: 0.0735 (0.0777) loss: 0.8215 (0.8261) time: 0.1584 data: 0.0715 max mem: 9390 +Train: [37] [5900/6250] eta: 0:01:01 lr: 0.000091 grad: 0.0704 (0.0777) loss: 0.8309 (0.8261) time: 0.1963 data: 0.1109 max mem: 9390 +Train: [37] [6000/6250] eta: 0:00:44 lr: 0.000091 grad: 0.0791 (0.0778) loss: 0.8200 (0.8261) time: 0.2477 data: 0.1685 max mem: 9390 +Train: [37] [6100/6250] eta: 0:00:26 lr: 0.000091 grad: 0.0760 (0.0778) loss: 0.8233 (0.8261) time: 0.1535 data: 0.0636 max mem: 9390 +Train: [37] [6200/6250] eta: 0:00:08 lr: 0.000091 grad: 0.0800 (0.0778) loss: 0.8224 (0.8260) time: 0.1843 data: 0.1026 max mem: 9390 +Train: [37] [6249/6250] eta: 0:00:00 lr: 0.000091 grad: 0.0770 (0.0778) loss: 0.8236 (0.8260) time: 0.1809 data: 0.0976 max mem: 9390 +Train: [37] Total time: 0:18:32 (0.1780 s / it) +Averaged stats: lr: 0.000091 grad: 0.0770 (0.0778) loss: 0.8236 (0.8260) +Eval (hcp-train-subset): [37] [ 0/62] eta: 0:04:39 loss: 0.8534 (0.8534) time: 4.5044 data: 4.4730 max mem: 9390 +Eval (hcp-train-subset): [37] [61/62] eta: 0:00:00 loss: 0.8381 (0.8410) time: 0.1471 data: 0.1215 max mem: 9390 +Eval (hcp-train-subset): [37] Total time: 0:00:14 (0.2295 s / it) +Averaged stats (hcp-train-subset): loss: 0.8381 (0.8410) +Eval (hcp-val): [37] [ 0/62] eta: 0:05:14 loss: 0.8318 (0.8318) time: 5.0783 data: 5.0482 max mem: 9390 +Eval (hcp-val): [37] [61/62] eta: 0:00:00 loss: 0.8382 (0.8379) time: 0.1225 data: 0.0971 max mem: 9390 +Eval (hcp-val): [37] Total time: 0:00:13 (0.2222 s / it) +Averaged stats (hcp-val): loss: 0.8382 (0.8379) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +Train: [38] [ 0/6250] eta: 9:54:10 lr: 0.000091 grad: 0.0666 (0.0666) loss: 0.8309 (0.8309) time: 5.7041 data: 5.5847 max mem: 9390 +Train: [38] [ 100/6250] eta: 0:27:30 lr: 0.000091 grad: 0.0742 (0.1023) loss: 0.8237 (0.8293) time: 0.2738 data: 0.1671 max mem: 9390 +Train: [38] [ 200/6250] eta: 0:24:17 lr: 0.000091 grad: 0.0763 (0.0923) loss: 0.8224 (0.8278) time: 0.1792 data: 0.0676 max mem: 9390 +Train: [38] [ 300/6250] eta: 0:22:06 lr: 0.000091 grad: 0.0766 (0.0890) loss: 0.8190 (0.8260) time: 0.1939 data: 0.0915 max mem: 9390 +Train: [38] [ 400/6250] eta: 0:20:54 lr: 0.000091 grad: 0.0710 (0.0858) loss: 0.8276 (0.8262) time: 0.1894 data: 0.0895 max mem: 9390 +Train: [38] [ 500/6250] eta: 0:20:03 lr: 0.000091 grad: 0.0732 (0.0834) loss: 0.8290 (0.8264) time: 0.2113 data: 0.1113 max mem: 9390 +Train: [38] [ 600/6250] eta: 0:19:18 lr: 0.000091 grad: 0.0756 (0.0824) loss: 0.8255 (0.8263) time: 0.1811 data: 0.0874 max mem: 9390 +Train: [38] [ 700/6250] eta: 0:18:50 lr: 0.000091 grad: 0.0732 (0.0815) loss: 0.8253 (0.8267) time: 0.1730 data: 0.0732 max mem: 9390 +Train: [38] [ 800/6250] eta: 0:18:12 lr: 0.000091 grad: 0.0688 (0.0808) loss: 0.8295 (0.8268) time: 0.1850 data: 0.0996 max mem: 9390 +Train: [38] [ 900/6250] eta: 0:17:34 lr: 0.000091 grad: 0.0710 (0.0801) loss: 0.8229 (0.8269) time: 0.1560 data: 0.0551 max mem: 9390 +Train: [38] [1000/6250] eta: 0:17:08 lr: 0.000091 grad: 0.0719 (0.0794) loss: 0.8295 (0.8268) time: 0.1876 data: 0.1021 max mem: 9390 +Train: [38] [1100/6250] eta: 0:16:36 lr: 0.000091 grad: 0.0737 (0.0790) loss: 0.8265 (0.8269) time: 0.1338 data: 0.0312 max mem: 9390 +Train: [38] [1200/6250] eta: 0:16:05 lr: 0.000091 grad: 0.0720 (0.0785) loss: 0.8327 (0.8272) time: 0.1690 data: 0.0746 max mem: 9390 +Train: [38] [1300/6250] eta: 0:15:49 lr: 0.000091 grad: 0.0712 (0.0782) loss: 0.8268 (0.8270) time: 0.2493 data: 0.1622 max mem: 9390 +Train: [38] [1400/6250] eta: 0:15:17 lr: 0.000091 grad: 0.0715 (0.0779) loss: 0.8253 (0.8269) time: 0.1559 data: 0.0633 max mem: 9390 +Train: [38] [1500/6250] eta: 0:14:55 lr: 0.000091 grad: 0.0806 (0.0778) loss: 0.8257 (0.8268) time: 0.1786 data: 0.0922 max mem: 9390 +Train: [38] [1600/6250] eta: 0:14:30 lr: 0.000091 grad: 0.0736 (0.0776) loss: 0.8216 (0.8268) time: 0.1882 data: 0.0939 max mem: 9390 +Train: [38] [1700/6250] eta: 0:14:05 lr: 0.000091 grad: 0.0730 (0.0775) loss: 0.8315 (0.8267) time: 0.1623 data: 0.0737 max mem: 9390 +Train: [38] [1800/6250] eta: 0:13:41 lr: 0.000091 grad: 0.0725 (0.0774) loss: 0.8259 (0.8266) time: 0.1517 data: 0.0594 max mem: 9390 +Train: [38] [1900/6250] eta: 0:13:17 lr: 0.000091 grad: 0.0749 (0.0773) loss: 0.8298 (0.8266) time: 0.1758 data: 0.0798 max mem: 9390 +Train: [38] [2000/6250] eta: 0:12:59 lr: 0.000091 grad: 0.0694 (0.0771) loss: 0.8284 (0.8267) time: 0.1838 data: 0.0956 max mem: 9390 +Train: [38] [2100/6250] eta: 0:12:39 lr: 0.000091 grad: 0.0781 (0.0771) loss: 0.8254 (0.8267) time: 0.2051 data: 0.1075 max mem: 9390 +Train: [38] [2200/6250] eta: 0:12:22 lr: 0.000091 grad: 0.0742 (0.0770) loss: 0.8332 (0.8268) time: 0.1754 data: 0.0836 max mem: 9390 +Train: [38] [2300/6250] eta: 0:12:07 lr: 0.000091 grad: 0.0743 (0.0768) loss: 0.8257 (0.8269) time: 0.2185 data: 0.1227 max mem: 9390 +Train: [38] [2400/6250] eta: 0:11:51 lr: 0.000091 grad: 0.0712 (0.0767) loss: 0.8275 (0.8270) time: 0.1779 data: 0.0769 max mem: 9390 +Train: [38] [2500/6250] eta: 0:11:32 lr: 0.000091 grad: 0.0789 (0.0768) loss: 0.8262 (0.8271) time: 0.1789 data: 0.0903 max mem: 9390 +Train: [38] [2600/6250] eta: 0:11:11 lr: 0.000091 grad: 0.0754 (0.0768) loss: 0.8218 (0.8270) time: 0.1687 data: 0.0763 max mem: 9390 +Train: [38] [2700/6250] eta: 0:10:52 lr: 0.000091 grad: 0.0710 (0.0768) loss: 0.8280 (0.8270) time: 0.1730 data: 0.0779 max mem: 9390 +Train: [38] [2800/6250] eta: 0:10:35 lr: 0.000091 grad: 0.0756 (0.0769) loss: 0.8280 (0.8270) time: 0.2356 data: 0.1483 max mem: 9390 +Train: [38] [2900/6250] eta: 0:10:16 lr: 0.000090 grad: 0.0771 (0.0769) loss: 0.8257 (0.8269) time: 0.1954 data: 0.1081 max mem: 9390 +Train: [38] [3000/6250] eta: 0:09:56 lr: 0.000090 grad: 0.0777 (0.0770) loss: 0.8263 (0.8270) time: 0.1913 data: 0.0954 max mem: 9390 +Train: [38] [3100/6250] eta: 0:09:37 lr: 0.000090 grad: 0.0782 (0.0771) loss: 0.8239 (0.8269) time: 0.2141 data: 0.1211 max mem: 9390 +Train: [38] [3200/6250] eta: 0:09:18 lr: 0.000090 grad: 0.0773 (0.0771) loss: 0.8238 (0.8268) time: 0.1750 data: 0.0736 max mem: 9390 +Train: [38] [3300/6250] eta: 0:09:00 lr: 0.000090 grad: 0.0716 (0.0772) loss: 0.8275 (0.8267) time: 0.1706 data: 0.0698 max mem: 9390 +Train: [38] [3400/6250] eta: 0:08:42 lr: 0.000090 grad: 0.0759 (0.0772) loss: 0.8266 (0.8267) time: 0.1651 data: 0.0667 max mem: 9390 +Train: [38] [3500/6250] eta: 0:08:23 lr: 0.000090 grad: 0.0744 (0.0773) loss: 0.8247 (0.8266) time: 0.1779 data: 0.0852 max mem: 9390 +Train: [38] [3600/6250] eta: 0:08:03 lr: 0.000090 grad: 0.0814 (0.0773) loss: 0.8189 (0.8266) time: 0.1592 data: 0.0643 max mem: 9390 +Train: [38] [3700/6250] eta: 0:07:45 lr: 0.000090 grad: 0.0813 (0.0774) loss: 0.8205 (0.8265) time: 0.1036 data: 0.0003 max mem: 9390 +Train: [38] [3800/6250] eta: 0:07:27 lr: 0.000090 grad: 0.0749 (0.0774) loss: 0.8295 (0.8265) time: 0.1755 data: 0.0911 max mem: 9390 +Train: [38] [3900/6250] eta: 0:07:10 lr: 0.000090 grad: 0.0789 (0.0775) loss: 0.8314 (0.8264) time: 0.2421 data: 0.1575 max mem: 9390 +Train: [38] [4000/6250] eta: 0:06:50 lr: 0.000090 grad: 0.0779 (0.0775) loss: 0.8269 (0.8264) time: 0.1431 data: 0.0511 max mem: 9390 +Train: [38] [4100/6250] eta: 0:06:32 lr: 0.000090 grad: 0.0734 (0.0775) loss: 0.8247 (0.8264) time: 0.1669 data: 0.0864 max mem: 9390 +Train: [38] [4200/6250] eta: 0:06:15 lr: 0.000090 grad: 0.0746 (0.0775) loss: 0.8237 (0.8263) time: 0.1675 data: 0.0752 max mem: 9390 +Train: [38] [4300/6250] eta: 0:05:56 lr: 0.000090 grad: 0.0769 (0.0776) loss: 0.8344 (0.8263) time: 0.1152 data: 0.0068 max mem: 9390 +Train: [38] [4400/6250] eta: 0:05:38 lr: 0.000090 grad: 0.0763 (0.0776) loss: 0.8234 (0.8263) time: 0.1525 data: 0.0381 max mem: 9390 +Train: [38] [4500/6250] eta: 0:05:21 lr: 0.000090 grad: 0.0786 (0.0776) loss: 0.8284 (0.8263) time: 0.2315 data: 0.1356 max mem: 9390 +Train: [38] [4600/6250] eta: 0:05:02 lr: 0.000090 grad: 0.0766 (0.0776) loss: 0.8262 (0.8263) time: 0.1824 data: 0.0988 max mem: 9390 +Train: [38] [4700/6250] eta: 0:04:43 lr: 0.000090 grad: 0.0781 (0.0776) loss: 0.8282 (0.8263) time: 0.1481 data: 0.0641 max mem: 9390 +Train: [38] [4800/6250] eta: 0:04:25 lr: 0.000090 grad: 0.0782 (0.0777) loss: 0.8236 (0.8264) time: 0.1937 data: 0.1137 max mem: 9390 +Train: [38] [4900/6250] eta: 0:04:07 lr: 0.000090 grad: 0.0772 (0.0777) loss: 0.8222 (0.8263) time: 0.2374 data: 0.1545 max mem: 9390 +Train: [38] [5000/6250] eta: 0:03:48 lr: 0.000090 grad: 0.0747 (0.0776) loss: 0.8306 (0.8264) time: 0.1597 data: 0.0726 max mem: 9390 +Train: [38] [5100/6250] eta: 0:03:30 lr: 0.000090 grad: 0.0758 (0.0777) loss: 0.8294 (0.8263) time: 0.2160 data: 0.1276 max mem: 9390 +Train: [38] [5200/6250] eta: 0:03:12 lr: 0.000090 grad: 0.0823 (0.0777) loss: 0.8215 (0.8263) time: 0.1893 data: 0.1085 max mem: 9390 +Train: [38] [5300/6250] eta: 0:02:53 lr: 0.000090 grad: 0.0785 (0.0778) loss: 0.8177 (0.8263) time: 0.1770 data: 0.0938 max mem: 9390 +Train: [38] [5400/6250] eta: 0:02:35 lr: 0.000090 grad: 0.0828 (0.0778) loss: 0.8205 (0.8264) time: 0.2176 data: 0.1163 max mem: 9390 +Train: [38] [5500/6250] eta: 0:02:17 lr: 0.000090 grad: 0.0783 (0.0778) loss: 0.8292 (0.8264) time: 0.1625 data: 0.0774 max mem: 9390 +Train: [38] [5600/6250] eta: 0:01:59 lr: 0.000090 grad: 0.0782 (0.0778) loss: 0.8277 (0.8264) time: 0.2023 data: 0.1195 max mem: 9390 +Train: [38] [5700/6250] eta: 0:01:40 lr: 0.000090 grad: 0.0778 (0.0778) loss: 0.8326 (0.8264) time: 0.1497 data: 0.0650 max mem: 9390 +Train: [38] [5800/6250] eta: 0:01:22 lr: 0.000090 grad: 0.0754 (0.0778) loss: 0.8298 (0.8265) time: 0.1629 data: 0.0804 max mem: 9390 +Train: [38] [5900/6250] eta: 0:01:03 lr: 0.000090 grad: 0.0762 (0.0778) loss: 0.8268 (0.8265) time: 0.1510 data: 0.0679 max mem: 9390 +Train: [38] [6000/6250] eta: 0:00:45 lr: 0.000090 grad: 0.0785 (0.0778) loss: 0.8301 (0.8265) time: 0.2374 data: 0.1497 max mem: 9390 +Train: [38] [6100/6250] eta: 0:00:27 lr: 0.000090 grad: 0.0781 (0.0778) loss: 0.8299 (0.8266) time: 0.2071 data: 0.1243 max mem: 9390 +Train: [38] [6200/6250] eta: 0:00:09 lr: 0.000089 grad: 0.0795 (0.0778) loss: 0.8256 (0.8266) time: 0.1814 data: 0.1025 max mem: 9390 +Train: [38] [6249/6250] eta: 0:00:00 lr: 0.000089 grad: 0.0840 (0.0778) loss: 0.8282 (0.8266) time: 0.1447 data: 0.0571 max mem: 9390 +Train: [38] Total time: 0:19:08 (0.1838 s / it) +Averaged stats: lr: 0.000089 grad: 0.0840 (0.0778) loss: 0.8282 (0.8266) +Eval (hcp-train-subset): [38] [ 0/62] eta: 0:05:05 loss: 0.8526 (0.8526) time: 4.9276 data: 4.8963 max mem: 9390 +Eval (hcp-train-subset): [38] [61/62] eta: 0:00:00 loss: 0.8417 (0.8418) time: 0.1158 data: 0.0886 max mem: 9390 +Eval (hcp-train-subset): [38] Total time: 0:00:14 (0.2311 s / it) +Averaged stats (hcp-train-subset): loss: 0.8417 (0.8418) +Eval (hcp-val): [38] [ 0/62] eta: 0:04:57 loss: 0.8387 (0.8387) time: 4.7928 data: 4.7638 max mem: 9390 +Eval (hcp-val): [38] [61/62] eta: 0:00:00 loss: 0.8369 (0.8384) time: 0.1435 data: 0.1178 max mem: 9390 +Eval (hcp-val): [38] Total time: 0:00:13 (0.2249 s / it) +Averaged stats (hcp-val): loss: 0.8369 (0.8384) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +Train: [39] [ 0/6250] eta: 9:18:30 lr: 0.000089 grad: 0.0789 (0.0789) loss: 0.8643 (0.8643) time: 5.3617 data: 4.9856 max mem: 9390 +Train: [39] [ 100/6250] eta: 0:27:16 lr: 0.000089 grad: 0.0735 (0.0899) loss: 0.8353 (0.8446) time: 0.2212 data: 0.1095 max mem: 9390 +Train: [39] [ 200/6250] eta: 0:24:43 lr: 0.000089 grad: 0.0764 (0.0848) loss: 0.8332 (0.8373) time: 0.2100 data: 0.0976 max mem: 9390 +Train: [39] [ 300/6250] eta: 0:22:57 lr: 0.000089 grad: 0.0728 (0.0822) loss: 0.8266 (0.8343) time: 0.1426 data: 0.0277 max mem: 9390 +Train: [39] [ 400/6250] eta: 0:21:47 lr: 0.000089 grad: 0.0718 (0.0802) loss: 0.8246 (0.8318) time: 0.2179 data: 0.1218 max mem: 9390 +Train: [39] [ 500/6250] eta: 0:20:43 lr: 0.000089 grad: 0.0752 (0.0795) loss: 0.8273 (0.8301) time: 0.1727 data: 0.0776 max mem: 9390 +Train: [39] [ 600/6250] eta: 0:20:23 lr: 0.000089 grad: 0.0716 (0.0792) loss: 0.8255 (0.8287) time: 0.2699 data: 0.1726 max mem: 9390 +Train: [39] [ 700/6250] eta: 0:19:20 lr: 0.000089 grad: 0.0715 (0.0792) loss: 0.8286 (0.8279) time: 0.1792 data: 0.0874 max mem: 9390 +Train: [39] [ 800/6250] eta: 0:18:51 lr: 0.000089 grad: 0.0741 (0.0789) loss: 0.8217 (0.8274) time: 0.1818 data: 0.0912 max mem: 9390 +Train: [39] [ 900/6250] eta: 0:18:16 lr: 0.000089 grad: 0.0747 (0.0787) loss: 0.8292 (0.8273) time: 0.1864 data: 0.0990 max mem: 9390 +Train: [39] [1000/6250] eta: 0:17:52 lr: 0.000089 grad: 0.0696 (0.0783) loss: 0.8256 (0.8274) time: 0.2360 data: 0.1510 max mem: 9390 +Train: [39] [1100/6250] eta: 0:17:26 lr: 0.000089 grad: 0.0762 (0.0779) loss: 0.8239 (0.8276) time: 0.1986 data: 0.1069 max mem: 9390 +Train: [39] [1200/6250] eta: 0:16:59 lr: 0.000089 grad: 0.0752 (0.0778) loss: 0.8215 (0.8274) time: 0.2148 data: 0.1286 max mem: 9390 +Train: [39] [1300/6250] eta: 0:16:33 lr: 0.000089 grad: 0.0739 (0.0777) loss: 0.8290 (0.8273) time: 0.1878 data: 0.0984 max mem: 9390 +Train: [39] [1400/6250] eta: 0:16:08 lr: 0.000089 grad: 0.0731 (0.0776) loss: 0.8236 (0.8271) time: 0.1716 data: 0.0796 max mem: 9390 +Train: [39] [1500/6250] eta: 0:15:41 lr: 0.000089 grad: 0.0719 (0.0775) loss: 0.8246 (0.8269) time: 0.1418 data: 0.0500 max mem: 9390 +Train: [39] [1600/6250] eta: 0:15:28 lr: 0.000089 grad: 0.0712 (0.0774) loss: 0.8282 (0.8269) time: 0.3690 data: 0.2666 max mem: 9390 +Train: [39] [1700/6250] eta: 0:15:05 lr: 0.000089 grad: 0.0753 (0.0773) loss: 0.8274 (0.8269) time: 0.1295 data: 0.0349 max mem: 9390 +Train: [39] [1800/6250] eta: 0:14:40 lr: 0.000089 grad: 0.0750 (0.0771) loss: 0.8238 (0.8269) time: 0.1625 data: 0.0567 max mem: 9390 +Train: [39] [1900/6250] eta: 0:14:18 lr: 0.000089 grad: 0.0739 (0.0771) loss: 0.8256 (0.8269) time: 0.1451 data: 0.0407 max mem: 9390 +Train: [39] [2000/6250] eta: 0:14:01 lr: 0.000089 grad: 0.0747 (0.0771) loss: 0.8279 (0.8268) time: 0.1638 data: 0.0687 max mem: 9390 +Train: [39] [2100/6250] eta: 0:13:34 lr: 0.000089 grad: 0.0705 (0.0770) loss: 0.8260 (0.8268) time: 0.1908 data: 0.1067 max mem: 9390 +Train: [39] [2200/6250] eta: 0:13:15 lr: 0.000089 grad: 0.0741 (0.0770) loss: 0.8290 (0.8268) time: 0.2238 data: 0.1318 max mem: 9390 +Train: [39] [2300/6250] eta: 0:12:56 lr: 0.000089 grad: 0.0740 (0.0770) loss: 0.8302 (0.8268) time: 0.1300 data: 0.0003 max mem: 9390 +Train: [39] [2400/6250] eta: 0:12:41 lr: 0.000089 grad: 0.0729 (0.0770) loss: 0.8247 (0.8269) time: 0.3423 data: 0.2302 max mem: 9390 +Train: [39] [2500/6250] eta: 0:12:17 lr: 0.000089 grad: 0.0745 (0.0770) loss: 0.8259 (0.8269) time: 0.1705 data: 0.0717 max mem: 9390 +Train: [39] [2600/6250] eta: 0:11:58 lr: 0.000089 grad: 0.0754 (0.0770) loss: 0.8256 (0.8269) time: 0.1177 data: 0.0003 max mem: 9390 +Train: [39] [2700/6250] eta: 0:11:35 lr: 0.000089 grad: 0.0750 (0.0770) loss: 0.8212 (0.8268) time: 0.1730 data: 0.0810 max mem: 9390 +Train: [39] [2800/6250] eta: 0:11:13 lr: 0.000089 grad: 0.0732 (0.0770) loss: 0.8334 (0.8268) time: 0.1613 data: 0.0636 max mem: 9390 +Train: [39] [2900/6250] eta: 0:10:53 lr: 0.000089 grad: 0.0714 (0.0770) loss: 0.8254 (0.8268) time: 0.1828 data: 0.0915 max mem: 9390 +Train: [39] [3000/6250] eta: 0:10:31 lr: 0.000089 grad: 0.0703 (0.0769) loss: 0.8254 (0.8268) time: 0.1621 data: 0.0727 max mem: 9390 +Train: [39] [3100/6250] eta: 0:10:10 lr: 0.000089 grad: 0.0699 (0.0768) loss: 0.8306 (0.8269) time: 0.1317 data: 0.0326 max mem: 9390 +Train: [39] [3200/6250] eta: 0:09:50 lr: 0.000089 grad: 0.0754 (0.0767) loss: 0.8265 (0.8270) time: 0.2054 data: 0.1117 max mem: 9390 +Train: [39] [3300/6250] eta: 0:09:29 lr: 0.000088 grad: 0.0767 (0.0766) loss: 0.8250 (0.8270) time: 0.2124 data: 0.1227 max mem: 9390 +Train: [39] [3400/6250] eta: 0:09:14 lr: 0.000088 grad: 0.0721 (0.0766) loss: 0.8259 (0.8270) time: 0.2390 data: 0.1254 max mem: 9390 +Train: [39] [3500/6250] eta: 0:08:52 lr: 0.000088 grad: 0.0741 (0.0765) loss: 0.8304 (0.8271) time: 0.1269 data: 0.0349 max mem: 9390 +Train: [39] [3600/6250] eta: 0:08:35 lr: 0.000088 grad: 0.0678 (0.0764) loss: 0.8291 (0.8272) time: 0.3552 data: 0.2579 max mem: 9390 +Train: [39] [3700/6250] eta: 0:08:12 lr: 0.000088 grad: 0.0764 (0.0763) loss: 0.8293 (0.8273) time: 0.1143 data: 0.0003 max mem: 9390 +Train: [39] [3800/6250] eta: 0:07:52 lr: 0.000088 grad: 0.0714 (0.0763) loss: 0.8308 (0.8273) time: 0.2003 data: 0.1080 max mem: 9390 +Train: [39] [3900/6250] eta: 0:07:32 lr: 0.000088 grad: 0.0702 (0.0763) loss: 0.8295 (0.8274) time: 0.1479 data: 0.0532 max mem: 9390 +Train: [39] [4000/6250] eta: 0:07:14 lr: 0.000088 grad: 0.0709 (0.0762) loss: 0.8283 (0.8275) time: 0.2202 data: 0.1254 max mem: 9390 +Train: [39] [4100/6250] eta: 0:06:56 lr: 0.000088 grad: 0.0747 (0.0762) loss: 0.8363 (0.8276) time: 0.3538 data: 0.2455 max mem: 9390 +Train: [39] [4200/6250] eta: 0:06:34 lr: 0.000088 grad: 0.0695 (0.0761) loss: 0.8297 (0.8276) time: 0.1817 data: 0.0931 max mem: 9390 +Train: [39] [4300/6250] eta: 0:06:16 lr: 0.000088 grad: 0.0784 (0.0761) loss: 0.8314 (0.8277) time: 0.3042 data: 0.2175 max mem: 9390 +Train: [39] [4400/6250] eta: 0:05:56 lr: 0.000088 grad: 0.0734 (0.0761) loss: 0.8318 (0.8278) time: 0.1629 data: 0.0393 max mem: 9390 +Train: [39] [4500/6250] eta: 0:05:37 lr: 0.000088 grad: 0.0774 (0.0762) loss: 0.8248 (0.8278) time: 0.2162 data: 0.1050 max mem: 9390 +Train: [39] [4600/6250] eta: 0:05:17 lr: 0.000088 grad: 0.0775 (0.0762) loss: 0.8301 (0.8278) time: 0.1996 data: 0.1091 max mem: 9390 +Train: [39] [4700/6250] eta: 0:04:58 lr: 0.000088 grad: 0.0746 (0.0763) loss: 0.8353 (0.8278) time: 0.1250 data: 0.0375 max mem: 9390 +Train: [39] [4800/6250] eta: 0:04:39 lr: 0.000088 grad: 0.0809 (0.0763) loss: 0.8195 (0.8278) time: 0.1255 data: 0.0176 max mem: 9390 +Train: [39] [4900/6250] eta: 0:04:20 lr: 0.000088 grad: 0.0759 (0.0764) loss: 0.8261 (0.8277) time: 0.1231 data: 0.0244 max mem: 9390 +Train: [39] [5000/6250] eta: 0:04:01 lr: 0.000088 grad: 0.0693 (0.0764) loss: 0.8268 (0.8278) time: 0.2717 data: 0.1799 max mem: 9390 +Train: [39] [5100/6250] eta: 0:03:41 lr: 0.000088 grad: 0.0706 (0.0764) loss: 0.8273 (0.8278) time: 0.1400 data: 0.0499 max mem: 9390 +Train: [39] [5200/6250] eta: 0:03:21 lr: 0.000088 grad: 0.0745 (0.0765) loss: 0.8257 (0.8277) time: 0.1555 data: 0.0634 max mem: 9390 +Train: [39] [5300/6250] eta: 0:03:02 lr: 0.000088 grad: 0.0761 (0.0765) loss: 0.8265 (0.8277) time: 0.2781 data: 0.1905 max mem: 9390 +Train: [39] [5400/6250] eta: 0:02:43 lr: 0.000088 grad: 0.0774 (0.0767) loss: 0.8281 (0.8276) time: 0.3418 data: 0.2648 max mem: 9390 +Train: [39] [5500/6250] eta: 0:02:24 lr: 0.000088 grad: 0.0728 (0.0768) loss: 0.8289 (0.8277) time: 0.1236 data: 0.0312 max mem: 9390 +Train: [39] [5600/6250] eta: 0:02:04 lr: 0.000088 grad: 0.0784 (0.0769) loss: 0.8247 (0.8276) time: 0.1794 data: 0.0942 max mem: 9390 +Train: [39] [5700/6250] eta: 0:01:45 lr: 0.000088 grad: 0.0791 (0.0769) loss: 0.8204 (0.8276) time: 0.2068 data: 0.1170 max mem: 9390 +Train: [39] [5800/6250] eta: 0:01:26 lr: 0.000088 grad: 0.0758 (0.0770) loss: 0.8250 (0.8276) time: 0.1676 data: 0.0686 max mem: 9390 +Train: [39] [5900/6250] eta: 0:01:06 lr: 0.000088 grad: 0.0742 (0.0770) loss: 0.8261 (0.8275) time: 0.0969 data: 0.0002 max mem: 9390 +Train: [39] [6000/6250] eta: 0:00:47 lr: 0.000088 grad: 0.0808 (0.0771) loss: 0.8205 (0.8275) time: 0.1730 data: 0.0831 max mem: 9390 +Train: [39] [6100/6250] eta: 0:00:28 lr: 0.000088 grad: 0.0762 (0.0772) loss: 0.8230 (0.8274) time: 0.1800 data: 0.0986 max mem: 9390 +Train: [39] [6200/6250] eta: 0:00:09 lr: 0.000088 grad: 0.0822 (0.0773) loss: 0.8147 (0.8273) time: 0.1994 data: 0.1053 max mem: 9390 +Train: [39] [6249/6250] eta: 0:00:00 lr: 0.000088 grad: 0.0751 (0.0773) loss: 0.8237 (0.8272) time: 0.1539 data: 0.0718 max mem: 9390 +Train: [39] Total time: 0:19:57 (0.1916 s / it) +Averaged stats: lr: 0.000088 grad: 0.0751 (0.0773) loss: 0.8237 (0.8272) +Eval (hcp-train-subset): [39] [ 0/62] eta: 0:05:33 loss: 0.8502 (0.8502) time: 5.3754 data: 5.3444 max mem: 9390 +Eval (hcp-train-subset): [39] [61/62] eta: 0:00:00 loss: 0.8410 (0.8415) time: 0.1269 data: 0.1017 max mem: 9390 +Eval (hcp-train-subset): [39] Total time: 0:00:14 (0.2311 s / it) +Averaged stats (hcp-train-subset): loss: 0.8410 (0.8415) +Making plots (hcp-train-subset): example=24 +Eval (hcp-val): [39] [ 0/62] eta: 0:05:18 loss: 0.8385 (0.8385) time: 5.1364 data: 5.1070 max mem: 9390 +Eval (hcp-val): [39] [61/62] eta: 0:00:00 loss: 0.8375 (0.8388) time: 0.1511 data: 0.1241 max mem: 9390 +Eval (hcp-val): [39] Total time: 0:00:14 (0.2312 s / it) +Averaged stats (hcp-val): loss: 0.8375 (0.8388) +Making plots (hcp-val): example=62 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +Train: [40] [ 0/6250] eta: 7:54:05 lr: 0.000088 grad: 0.3472 (0.3472) loss: 0.8521 (0.8521) time: 4.5513 data: 4.3650 max mem: 9390 +Train: [40] [ 100/6250] eta: 0:24:05 lr: 0.000088 grad: 0.0735 (0.0909) loss: 0.8408 (0.8284) time: 0.1069 data: 0.0002 max mem: 9390 +Train: [40] [ 200/6250] eta: 0:20:49 lr: 0.000088 grad: 0.0718 (0.0856) loss: 0.8371 (0.8318) time: 0.1634 data: 0.0732 max mem: 9390 +Train: [40] [ 300/6250] eta: 0:19:34 lr: 0.000088 grad: 0.0742 (0.0834) loss: 0.8257 (0.8317) time: 0.1614 data: 0.0665 max mem: 9390 +Train: [40] [ 400/6250] eta: 0:18:40 lr: 0.000087 grad: 0.0724 (0.0812) loss: 0.8397 (0.8321) time: 0.1761 data: 0.0737 max mem: 9390 +Train: [40] [ 500/6250] eta: 0:18:04 lr: 0.000087 grad: 0.0664 (0.0794) loss: 0.8387 (0.8329) time: 0.1475 data: 0.0532 max mem: 9390 +Train: [40] [ 600/6250] eta: 0:17:30 lr: 0.000087 grad: 0.0696 (0.0782) loss: 0.8367 (0.8328) time: 0.1734 data: 0.0784 max mem: 9390 +Train: [40] [ 700/6250] eta: 0:17:15 lr: 0.000087 grad: 0.0677 (0.0773) loss: 0.8314 (0.8326) time: 0.1904 data: 0.0983 max mem: 9390 +Train: [40] [ 800/6250] eta: 0:17:28 lr: 0.000087 grad: 0.0702 (0.0773) loss: 0.8274 (0.8320) time: 0.2428 data: 0.1707 max mem: 9390 +Train: [40] [ 900/6250] eta: 0:17:22 lr: 0.000087 grad: 0.0727 (0.0771) loss: 0.8328 (0.8317) time: 0.2270 data: 0.1414 max mem: 9390 +Train: [40] [1000/6250] eta: 0:17:00 lr: 0.000087 grad: 0.0737 (0.0770) loss: 0.8268 (0.8313) time: 0.1904 data: 0.1020 max mem: 9390 +Train: [40] [1100/6250] eta: 0:16:54 lr: 0.000087 grad: 0.0698 (0.0770) loss: 0.8267 (0.8308) time: 0.2592 data: 0.1689 max mem: 9390 +Train: [40] [1200/6250] eta: 0:16:40 lr: 0.000087 grad: 0.0716 (0.0769) loss: 0.8212 (0.8302) time: 0.1392 data: 0.0375 max mem: 9390 +Train: [40] [1300/6250] eta: 0:16:44 lr: 0.000087 grad: 0.0754 (0.0769) loss: 0.8209 (0.8295) time: 0.2068 data: 0.1232 max mem: 9390 +Train: [40] [1400/6250] eta: 0:16:34 lr: 0.000087 grad: 0.0751 (0.0769) loss: 0.8284 (0.8291) time: 0.1306 data: 0.0100 max mem: 9390 +Train: [40] [1500/6250] eta: 0:16:21 lr: 0.000087 grad: 0.0728 (0.0769) loss: 0.8316 (0.8288) time: 0.2068 data: 0.1150 max mem: 9390 +Train: [40] [1600/6250] eta: 0:16:17 lr: 0.000087 grad: 0.0735 (0.0768) loss: 0.8260 (0.8286) time: 0.4039 data: 0.2917 max mem: 9390 +Train: [40] [1700/6250] eta: 0:15:55 lr: 0.000087 grad: 0.0736 (0.0768) loss: 0.8246 (0.8282) time: 0.1613 data: 0.0464 max mem: 9390 +Train: [40] [1800/6250] eta: 0:15:31 lr: 0.000087 grad: 0.0761 (0.0769) loss: 0.8265 (0.8280) time: 0.2071 data: 0.1142 max mem: 9390 +Train: [40] [1900/6250] eta: 0:15:04 lr: 0.000087 grad: 0.0836 (0.0771) loss: 0.8230 (0.8278) time: 0.1784 data: 0.0707 max mem: 9390 +Train: [40] [2000/6250] eta: 0:14:40 lr: 0.000087 grad: 0.0801 (0.0772) loss: 0.8187 (0.8276) time: 0.1836 data: 0.0970 max mem: 9390 +Train: [40] [2100/6250] eta: 0:14:17 lr: 0.000087 grad: 0.0799 (0.0773) loss: 0.8225 (0.8274) time: 0.1147 data: 0.0236 max mem: 9390 +Train: [40] [2200/6250] eta: 0:13:52 lr: 0.000087 grad: 0.0720 (0.0774) loss: 0.8316 (0.8273) time: 0.1664 data: 0.0781 max mem: 9390 +Train: [40] [2300/6250] eta: 0:13:29 lr: 0.000087 grad: 0.0790 (0.0775) loss: 0.8325 (0.8273) time: 0.1874 data: 0.0944 max mem: 9390 +Train: [40] [2400/6250] eta: 0:13:06 lr: 0.000087 grad: 0.0741 (0.0775) loss: 0.8300 (0.8272) time: 0.1790 data: 0.0918 max mem: 9390 +Train: [40] [2500/6250] eta: 0:12:45 lr: 0.000087 grad: 0.0746 (0.0777) loss: 0.8310 (0.8272) time: 0.2567 data: 0.1650 max mem: 9390 +Train: [40] [2600/6250] eta: 0:12:21 lr: 0.000087 grad: 0.0799 (0.0778) loss: 0.8270 (0.8272) time: 0.2298 data: 0.1402 max mem: 9390 +Train: [40] [2700/6250] eta: 0:12:00 lr: 0.000087 grad: 0.0756 (0.0779) loss: 0.8281 (0.8273) time: 0.2653 data: 0.1681 max mem: 9390 +Train: [40] [2800/6250] eta: 0:11:38 lr: 0.000087 grad: 0.0779 (0.0779) loss: 0.8272 (0.8273) time: 0.1614 data: 0.0730 max mem: 9390 +Train: [40] [2900/6250] eta: 0:11:14 lr: 0.000087 grad: 0.0746 (0.0778) loss: 0.8263 (0.8273) time: 0.1586 data: 0.0688 max mem: 9390 +Train: [40] [3000/6250] eta: 0:10:52 lr: 0.000087 grad: 0.0759 (0.0778) loss: 0.8215 (0.8272) time: 0.1803 data: 0.1006 max mem: 9390 +Train: [40] [3100/6250] eta: 0:10:32 lr: 0.000087 grad: 0.0764 (0.0779) loss: 0.8178 (0.8271) time: 0.2656 data: 0.1563 max mem: 9390 +Train: [40] [3200/6250] eta: 0:10:09 lr: 0.000087 grad: 0.0753 (0.0778) loss: 0.8198 (0.8271) time: 0.1844 data: 0.0977 max mem: 9390 +Train: [40] [3300/6250] eta: 0:09:47 lr: 0.000087 grad: 0.0711 (0.0778) loss: 0.8324 (0.8271) time: 0.2037 data: 0.1141 max mem: 9390 +Train: [40] [3400/6250] eta: 0:09:25 lr: 0.000087 grad: 0.0784 (0.0778) loss: 0.8274 (0.8271) time: 0.1294 data: 0.0409 max mem: 9390 +Train: [40] [3500/6250] eta: 0:09:04 lr: 0.000087 grad: 0.0787 (0.0778) loss: 0.8271 (0.8271) time: 0.1718 data: 0.0905 max mem: 9390 +Train: [40] [3600/6250] eta: 0:08:44 lr: 0.000087 grad: 0.0727 (0.0778) loss: 0.8273 (0.8272) time: 0.1862 data: 0.1014 max mem: 9390 +Train: [40] [3700/6250] eta: 0:08:24 lr: 0.000086 grad: 0.0751 (0.0778) loss: 0.8245 (0.8272) time: 0.2547 data: 0.1702 max mem: 9390 +Train: [40] [3800/6250] eta: 0:08:02 lr: 0.000086 grad: 0.0840 (0.0779) loss: 0.8275 (0.8272) time: 0.1442 data: 0.0538 max mem: 9390 +Train: [40] [3900/6250] eta: 0:07:42 lr: 0.000086 grad: 0.0805 (0.0779) loss: 0.8289 (0.8272) time: 0.2484 data: 0.1655 max mem: 9390 +Train: [40] [4000/6250] eta: 0:07:21 lr: 0.000086 grad: 0.0774 (0.0780) loss: 0.8200 (0.8271) time: 0.1475 data: 0.0681 max mem: 9390 +Train: [40] [4100/6250] eta: 0:07:00 lr: 0.000086 grad: 0.0794 (0.0780) loss: 0.8210 (0.8270) time: 0.1743 data: 0.0817 max mem: 9390 +Train: [40] [4200/6250] eta: 0:06:40 lr: 0.000086 grad: 0.0759 (0.0781) loss: 0.8309 (0.8270) time: 0.1893 data: 0.1054 max mem: 9390 +Train: [40] [4300/6250] eta: 0:06:19 lr: 0.000086 grad: 0.0802 (0.0781) loss: 0.8277 (0.8270) time: 0.1715 data: 0.0704 max mem: 9390 +Train: [40] [4400/6250] eta: 0:06:00 lr: 0.000086 grad: 0.0841 (0.0782) loss: 0.8179 (0.8270) time: 0.1693 data: 0.0780 max mem: 9390 +Train: [40] [4500/6250] eta: 0:05:40 lr: 0.000086 grad: 0.0814 (0.0784) loss: 0.8218 (0.8269) time: 0.1630 data: 0.0798 max mem: 9390 +Train: [40] [4600/6250] eta: 0:05:20 lr: 0.000086 grad: 0.0798 (0.0785) loss: 0.8269 (0.8268) time: 0.1702 data: 0.0765 max mem: 9390 +Train: [40] [4700/6250] eta: 0:05:00 lr: 0.000086 grad: 0.0789 (0.0786) loss: 0.8208 (0.8267) time: 0.2414 data: 0.1552 max mem: 9390 +Train: [40] [4800/6250] eta: 0:04:40 lr: 0.000086 grad: 0.0768 (0.0786) loss: 0.8201 (0.8266) time: 0.1803 data: 0.0880 max mem: 9390 +Train: [40] [4900/6250] eta: 0:04:20 lr: 0.000086 grad: 0.0826 (0.0787) loss: 0.8200 (0.8265) time: 0.1829 data: 0.0899 max mem: 9390 +Train: [40] [5000/6250] eta: 0:04:00 lr: 0.000086 grad: 0.0835 (0.0788) loss: 0.8210 (0.8263) time: 0.2075 data: 0.1252 max mem: 9390 +Train: [40] [5100/6250] eta: 0:03:41 lr: 0.000086 grad: 0.0783 (0.0789) loss: 0.8209 (0.8262) time: 0.1112 data: 0.0003 max mem: 9390 +Train: [40] [5200/6250] eta: 0:03:22 lr: 0.000086 grad: 0.0858 (0.0789) loss: 0.8222 (0.8261) time: 0.1150 data: 0.0209 max mem: 9390 +Train: [40] [5300/6250] eta: 0:03:03 lr: 0.000086 grad: 0.0790 (0.0790) loss: 0.8124 (0.8260) time: 0.2020 data: 0.1185 max mem: 9390 +Train: [40] [5400/6250] eta: 0:02:43 lr: 0.000086 grad: 0.0810 (0.0791) loss: 0.8243 (0.8260) time: 0.1013 data: 0.0125 max mem: 9390 +Train: [40] [5500/6250] eta: 0:02:24 lr: 0.000086 grad: 0.0834 (0.0792) loss: 0.8161 (0.8259) time: 0.3720 data: 0.2936 max mem: 9390 +Train: [40] [5600/6250] eta: 0:02:04 lr: 0.000086 grad: 0.0833 (0.0793) loss: 0.8222 (0.8258) time: 0.1677 data: 0.0850 max mem: 9390 +Train: [40] [5700/6250] eta: 0:01:45 lr: 0.000086 grad: 0.0782 (0.0794) loss: 0.8250 (0.8258) time: 0.1272 data: 0.0409 max mem: 9390 +Train: [40] [5800/6250] eta: 0:01:26 lr: 0.000086 grad: 0.0781 (0.0795) loss: 0.8203 (0.8257) time: 0.1821 data: 0.1062 max mem: 9390 +Train: [40] [5900/6250] eta: 0:01:06 lr: 0.000086 grad: 0.0823 (0.0796) loss: 0.8189 (0.8256) time: 0.1655 data: 0.0797 max mem: 9390 +Train: [40] [6000/6250] eta: 0:00:47 lr: 0.000086 grad: 0.0815 (0.0797) loss: 0.8242 (0.8256) time: 0.1746 data: 0.0911 max mem: 9390 +Train: [40] [6100/6250] eta: 0:00:28 lr: 0.000086 grad: 0.0776 (0.0797) loss: 0.8248 (0.8255) time: 0.1785 data: 0.0955 max mem: 9390 +Train: [40] [6200/6250] eta: 0:00:09 lr: 0.000086 grad: 0.0806 (0.0798) loss: 0.8245 (0.8254) time: 0.1601 data: 0.0699 max mem: 9390 +Train: [40] [6249/6250] eta: 0:00:00 lr: 0.000086 grad: 0.0810 (0.0798) loss: 0.8209 (0.8254) time: 0.2000 data: 0.1196 max mem: 9390 +Train: [40] Total time: 0:19:59 (0.1919 s / it) +Averaged stats: lr: 0.000086 grad: 0.0810 (0.0798) loss: 0.8209 (0.8254) +Eval (hcp-train-subset): [40] [ 0/62] eta: 0:03:29 loss: 0.8556 (0.8556) time: 3.3715 data: 3.3031 max mem: 9390 +Eval (hcp-train-subset): [40] [61/62] eta: 0:00:00 loss: 0.8395 (0.8405) time: 0.1762 data: 0.1454 max mem: 9390 +Eval (hcp-train-subset): [40] Total time: 0:00:16 (0.2685 s / it) +Averaged stats (hcp-train-subset): loss: 0.8395 (0.8405) +Eval (hcp-val): [40] [ 0/62] eta: 0:05:54 loss: 0.8336 (0.8336) time: 5.7119 data: 5.6825 max mem: 9390 +Eval (hcp-val): [40] [61/62] eta: 0:00:00 loss: 0.8366 (0.8376) time: 0.2063 data: 0.1800 max mem: 9390 +Eval (hcp-val): [40] Total time: 0:00:17 (0.2903 s / it) +Averaged stats (hcp-val): loss: 0.8366 (0.8376) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +Train: [41] [ 0/6250] eta: 13:39:59 lr: 0.000086 grad: 0.1093 (0.1093) loss: 0.8792 (0.8792) time: 7.8719 data: 7.5661 max mem: 9390 +Train: [41] [ 100/6250] eta: 0:45:08 lr: 0.000086 grad: 0.0763 (0.0930) loss: 0.8287 (0.8365) time: 0.5798 data: 0.4724 max mem: 9390 +Train: [41] [ 200/6250] eta: 0:33:15 lr: 0.000086 grad: 0.0768 (0.0886) loss: 0.8289 (0.8330) time: 0.1486 data: 0.0291 max mem: 9390 +Train: [41] [ 300/6250] eta: 0:28:47 lr: 0.000086 grad: 0.0771 (0.0857) loss: 0.8324 (0.8317) time: 0.2549 data: 0.1602 max mem: 9390 +Train: [41] [ 400/6250] eta: 0:26:16 lr: 0.000086 grad: 0.0748 (0.0840) loss: 0.8235 (0.8305) time: 0.2296 data: 0.1202 max mem: 9390 +Train: [41] [ 500/6250] eta: 0:24:39 lr: 0.000086 grad: 0.0759 (0.0830) loss: 0.8236 (0.8299) time: 0.2877 data: 0.1860 max mem: 9390 +Train: [41] [ 600/6250] eta: 0:23:05 lr: 0.000086 grad: 0.0707 (0.0818) loss: 0.8320 (0.8294) time: 0.1772 data: 0.0808 max mem: 9390 +Train: [41] [ 700/6250] eta: 0:22:16 lr: 0.000085 grad: 0.0741 (0.0812) loss: 0.8296 (0.8292) time: 0.2526 data: 0.1576 max mem: 9390 +Train: [41] [ 800/6250] eta: 0:21:19 lr: 0.000085 grad: 0.0736 (0.0806) loss: 0.8292 (0.8292) time: 0.1792 data: 0.0958 max mem: 9390 +Train: [41] [ 900/6250] eta: 0:20:29 lr: 0.000085 grad: 0.0715 (0.0801) loss: 0.8293 (0.8289) time: 0.1658 data: 0.0763 max mem: 9390 +Train: [41] [1000/6250] eta: 0:19:37 lr: 0.000085 grad: 0.0728 (0.0798) loss: 0.8310 (0.8289) time: 0.1948 data: 0.1048 max mem: 9390 +Train: [41] [1100/6250] eta: 0:19:03 lr: 0.000085 grad: 0.0713 (0.0795) loss: 0.8310 (0.8288) time: 0.2186 data: 0.1355 max mem: 9390 +Train: [41] [1200/6250] eta: 0:18:33 lr: 0.000085 grad: 0.0734 (0.0793) loss: 0.8263 (0.8287) time: 0.2658 data: 0.1679 max mem: 9390 +Train: [41] [1300/6250] eta: 0:17:56 lr: 0.000085 grad: 0.0740 (0.0789) loss: 0.8265 (0.8285) time: 0.2123 data: 0.1252 max mem: 9390 +Train: [41] [1400/6250] eta: 0:17:23 lr: 0.000085 grad: 0.0739 (0.0790) loss: 0.8256 (0.8282) time: 0.1165 data: 0.0082 max mem: 9390 +Train: [41] [1500/6250] eta: 0:16:53 lr: 0.000085 grad: 0.0759 (0.0788) loss: 0.8270 (0.8283) time: 0.1475 data: 0.0614 max mem: 9390 +Train: [41] [1600/6250] eta: 0:16:22 lr: 0.000085 grad: 0.0798 (0.0788) loss: 0.8218 (0.8280) time: 0.1845 data: 0.0864 max mem: 9390 +Train: [41] [1700/6250] eta: 0:15:53 lr: 0.000085 grad: 0.0780 (0.0790) loss: 0.8288 (0.8279) time: 0.0981 data: 0.0003 max mem: 9390 +Train: [41] [1800/6250] eta: 0:15:27 lr: 0.000085 grad: 0.0736 (0.0789) loss: 0.8304 (0.8279) time: 0.1547 data: 0.0619 max mem: 9390 +Train: [41] [1900/6250] eta: 0:15:05 lr: 0.000085 grad: 0.0790 (0.0791) loss: 0.8316 (0.8279) time: 0.2829 data: 0.1993 max mem: 9390 +Train: [41] [2000/6250] eta: 0:14:38 lr: 0.000085 grad: 0.0783 (0.0790) loss: 0.8265 (0.8279) time: 0.1938 data: 0.1008 max mem: 9390 +Train: [41] [2100/6250] eta: 0:14:14 lr: 0.000085 grad: 0.0809 (0.0791) loss: 0.8254 (0.8279) time: 0.1112 data: 0.0032 max mem: 9390 +Train: [41] [2200/6250] eta: 0:13:52 lr: 0.000085 grad: 0.0793 (0.0792) loss: 0.8320 (0.8279) time: 0.1603 data: 0.0674 max mem: 9390 +Train: [41] [2300/6250] eta: 0:13:30 lr: 0.000085 grad: 0.0769 (0.0792) loss: 0.8301 (0.8279) time: 0.1234 data: 0.0466 max mem: 9390 +Train: [41] [2400/6250] eta: 0:13:03 lr: 0.000085 grad: 0.0737 (0.0792) loss: 0.8302 (0.8280) time: 0.2025 data: 0.1217 max mem: 9390 +Train: [41] [2500/6250] eta: 0:12:41 lr: 0.000085 grad: 0.0712 (0.0791) loss: 0.8326 (0.8281) time: 0.1999 data: 0.1215 max mem: 9390 +Train: [41] [2600/6250] eta: 0:12:17 lr: 0.000085 grad: 0.0753 (0.0791) loss: 0.8274 (0.8282) time: 0.2365 data: 0.1396 max mem: 9390 +Train: [41] [2700/6250] eta: 0:11:53 lr: 0.000085 grad: 0.0742 (0.0791) loss: 0.8242 (0.8281) time: 0.1538 data: 0.0701 max mem: 9390 +Train: [41] [2800/6250] eta: 0:11:33 lr: 0.000085 grad: 0.0800 (0.0791) loss: 0.8247 (0.8281) time: 0.2667 data: 0.1743 max mem: 9390 +Train: [41] [2900/6250] eta: 0:11:10 lr: 0.000085 grad: 0.0766 (0.0792) loss: 0.8282 (0.8281) time: 0.2376 data: 0.1541 max mem: 9390 +Train: [41] [3000/6250] eta: 0:10:48 lr: 0.000085 grad: 0.0789 (0.0792) loss: 0.8258 (0.8281) time: 0.1505 data: 0.0635 max mem: 9390 +Train: [41] [3100/6250] eta: 0:10:25 lr: 0.000085 grad: 0.0760 (0.0792) loss: 0.8311 (0.8281) time: 0.1843 data: 0.0897 max mem: 9390 +Train: [41] [3200/6250] eta: 0:10:04 lr: 0.000085 grad: 0.0787 (0.0792) loss: 0.8258 (0.8281) time: 0.1989 data: 0.1083 max mem: 9390 +Train: [41] [3300/6250] eta: 0:09:42 lr: 0.000085 grad: 0.0759 (0.0792) loss: 0.8304 (0.8281) time: 0.1690 data: 0.0840 max mem: 9390 +Train: [41] [3400/6250] eta: 0:09:23 lr: 0.000085 grad: 0.0764 (0.0793) loss: 0.8301 (0.8280) time: 0.2650 data: 0.1917 max mem: 9390 +Train: [41] [3500/6250] eta: 0:09:06 lr: 0.000085 grad: 0.0772 (0.0792) loss: 0.8313 (0.8281) time: 0.1079 data: 0.0003 max mem: 9390 +Train: [41] [3600/6250] eta: 0:08:46 lr: 0.000085 grad: 0.0764 (0.0793) loss: 0.8261 (0.8281) time: 0.1093 data: 0.0003 max mem: 9390 +Train: [41] [3700/6250] eta: 0:08:25 lr: 0.000085 grad: 0.0786 (0.0793) loss: 0.8253 (0.8281) time: 0.1324 data: 0.0307 max mem: 9390 +Train: [41] [3800/6250] eta: 0:08:05 lr: 0.000085 grad: 0.0801 (0.0793) loss: 0.8236 (0.8280) time: 0.1174 data: 0.0004 max mem: 9390 +Train: [41] [3900/6250] eta: 0:07:44 lr: 0.000084 grad: 0.0836 (0.0794) loss: 0.8254 (0.8280) time: 0.1343 data: 0.0380 max mem: 9390 +Train: [41] [4000/6250] eta: 0:07:24 lr: 0.000084 grad: 0.0778 (0.0795) loss: 0.8250 (0.8279) time: 0.1944 data: 0.0908 max mem: 9390 +Train: [41] [4100/6250] eta: 0:07:05 lr: 0.000084 grad: 0.0817 (0.0795) loss: 0.8147 (0.8278) time: 0.2476 data: 0.1543 max mem: 9390 +Train: [41] [4200/6250] eta: 0:06:45 lr: 0.000084 grad: 0.0783 (0.0795) loss: 0.8223 (0.8278) time: 0.1939 data: 0.1066 max mem: 9390 +Train: [41] [4300/6250] eta: 0:06:24 lr: 0.000084 grad: 0.0790 (0.0795) loss: 0.8230 (0.8277) time: 0.1692 data: 0.0752 max mem: 9390 +Train: [41] [4400/6250] eta: 0:06:04 lr: 0.000084 grad: 0.0780 (0.0795) loss: 0.8276 (0.8277) time: 0.2240 data: 0.1364 max mem: 9390 +Train: [41] [4500/6250] eta: 0:05:44 lr: 0.000084 grad: 0.0777 (0.0796) loss: 0.8272 (0.8276) time: 0.1098 data: 0.0146 max mem: 9390 +Train: [41] [4600/6250] eta: 0:05:25 lr: 0.000084 grad: 0.0812 (0.0796) loss: 0.8242 (0.8275) time: 0.2887 data: 0.1970 max mem: 9390 +Train: [41] [4700/6250] eta: 0:05:05 lr: 0.000084 grad: 0.0791 (0.0797) loss: 0.8317 (0.8275) time: 0.2661 data: 0.1837 max mem: 9390 +Train: [41] [4800/6250] eta: 0:04:44 lr: 0.000084 grad: 0.0770 (0.0797) loss: 0.8281 (0.8275) time: 0.1775 data: 0.0927 max mem: 9390 +Train: [41] [4900/6250] eta: 0:04:24 lr: 0.000084 grad: 0.0819 (0.0797) loss: 0.8244 (0.8274) time: 0.1530 data: 0.0674 max mem: 9390 +Train: [41] [5000/6250] eta: 0:04:04 lr: 0.000084 grad: 0.0870 (0.0798) loss: 0.8254 (0.8274) time: 0.1768 data: 0.0942 max mem: 9390 +Train: [41] [5100/6250] eta: 0:03:43 lr: 0.000084 grad: 0.0772 (0.0799) loss: 0.8251 (0.8273) time: 0.1564 data: 0.0693 max mem: 9390 +Train: [41] [5200/6250] eta: 0:03:24 lr: 0.000084 grad: 0.0780 (0.0799) loss: 0.8303 (0.8273) time: 0.1802 data: 0.0918 max mem: 9390 +Train: [41] [5300/6250] eta: 0:03:04 lr: 0.000084 grad: 0.0756 (0.0799) loss: 0.8234 (0.8273) time: 0.1584 data: 0.0699 max mem: 9390 +Train: [41] [5400/6250] eta: 0:02:44 lr: 0.000084 grad: 0.0760 (0.0799) loss: 0.8302 (0.8274) time: 0.1726 data: 0.0869 max mem: 9390 +Train: [41] [5500/6250] eta: 0:02:25 lr: 0.000084 grad: 0.0756 (0.0799) loss: 0.8286 (0.8273) time: 0.2424 data: 0.1581 max mem: 9390 +Train: [41] [5600/6250] eta: 0:02:05 lr: 0.000084 grad: 0.0724 (0.0799) loss: 0.8312 (0.8274) time: 0.1363 data: 0.0422 max mem: 9390 +Train: [41] [5700/6250] eta: 0:01:46 lr: 0.000084 grad: 0.0773 (0.0799) loss: 0.8283 (0.8274) time: 0.1590 data: 0.0778 max mem: 9390 +Train: [41] [5800/6250] eta: 0:01:26 lr: 0.000084 grad: 0.0753 (0.0799) loss: 0.8259 (0.8274) time: 0.1690 data: 0.0772 max mem: 9390 +Train: [41] [5900/6250] eta: 0:01:07 lr: 0.000084 grad: 0.0803 (0.0799) loss: 0.8257 (0.8274) time: 0.1347 data: 0.0495 max mem: 9390 +Train: [41] [6000/6250] eta: 0:00:48 lr: 0.000084 grad: 0.0777 (0.0799) loss: 0.8280 (0.8274) time: 0.1664 data: 0.0850 max mem: 9390 +Train: [41] [6100/6250] eta: 0:00:28 lr: 0.000084 grad: 0.0798 (0.0799) loss: 0.8276 (0.8274) time: 0.1575 data: 0.0742 max mem: 9390 +Train: [41] [6200/6250] eta: 0:00:09 lr: 0.000084 grad: 0.0758 (0.0799) loss: 0.8270 (0.8274) time: 0.2181 data: 0.0753 max mem: 9390 +Train: [41] [6249/6250] eta: 0:00:00 lr: 0.000084 grad: 0.0785 (0.0798) loss: 0.8297 (0.8274) time: 0.1563 data: 0.0648 max mem: 9390 +Train: [41] Total time: 0:20:04 (0.1928 s / it) +Averaged stats: lr: 0.000084 grad: 0.0785 (0.0798) loss: 0.8297 (0.8274) +Eval (hcp-train-subset): [41] [ 0/62] eta: 0:06:05 loss: 0.8509 (0.8509) time: 5.8917 data: 5.8615 max mem: 9390 +Eval (hcp-train-subset): [41] [61/62] eta: 0:00:00 loss: 0.8385 (0.8391) time: 0.2086 data: 0.1824 max mem: 9390 +Eval (hcp-train-subset): [41] Total time: 0:00:16 (0.2604 s / it) +Averaged stats (hcp-train-subset): loss: 0.8385 (0.8391) +Eval (hcp-val): [41] [ 0/62] eta: 0:05:48 loss: 0.8336 (0.8336) time: 5.6171 data: 5.5869 max mem: 9390 +Eval (hcp-val): [41] [61/62] eta: 0:00:00 loss: 0.8361 (0.8375) time: 0.2299 data: 0.2028 max mem: 9390 +Eval (hcp-val): [41] Total time: 0:00:20 (0.3247 s / it) +Averaged stats (hcp-val): loss: 0.8361 (0.8375) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +Train: [42] [ 0/6250] eta: 1 day, 0:28:31 lr: 0.000084 grad: 0.0654 (0.0654) loss: 0.8392 (0.8392) time: 14.0979 data: 13.9783 max mem: 9390 +Train: [42] [ 100/6250] eta: 0:50:44 lr: 0.000084 grad: 0.0853 (0.0958) loss: 0.8347 (0.8409) time: 0.2310 data: 0.1016 max mem: 9390 +Train: [42] [ 200/6250] eta: 0:35:55 lr: 0.000084 grad: 0.0820 (0.0960) loss: 0.8274 (0.8316) time: 0.2486 data: 0.1443 max mem: 9390 +Train: [42] [ 300/6250] eta: 0:31:45 lr: 0.000084 grad: 0.0769 (0.0923) loss: 0.8196 (0.8289) time: 0.2691 data: 0.1673 max mem: 9390 +Train: [42] [ 400/6250] eta: 0:29:57 lr: 0.000084 grad: 0.0780 (0.0896) loss: 0.8261 (0.8281) time: 0.2763 data: 0.1468 max mem: 9390 +Train: [42] [ 500/6250] eta: 0:27:33 lr: 0.000084 grad: 0.0717 (0.0877) loss: 0.8314 (0.8279) time: 0.2025 data: 0.1049 max mem: 9390 +Train: [42] [ 600/6250] eta: 0:25:49 lr: 0.000084 grad: 0.0736 (0.0867) loss: 0.8275 (0.8276) time: 0.2453 data: 0.1465 max mem: 9390 +Train: [42] [ 700/6250] eta: 0:24:35 lr: 0.000084 grad: 0.0780 (0.0856) loss: 0.8257 (0.8276) time: 0.1083 data: 0.0003 max mem: 9390 +Train: [42] [ 800/6250] eta: 0:23:35 lr: 0.000084 grad: 0.0735 (0.0846) loss: 0.8250 (0.8276) time: 0.2929 data: 0.2060 max mem: 9390 +Train: [42] [ 900/6250] eta: 0:23:01 lr: 0.000083 grad: 0.0752 (0.0839) loss: 0.8300 (0.8278) time: 0.1866 data: 0.1000 max mem: 9390 +Train: [42] [1000/6250] eta: 0:22:07 lr: 0.000083 grad: 0.0798 (0.0834) loss: 0.8239 (0.8277) time: 0.1730 data: 0.0858 max mem: 9390 +Train: [42] [1100/6250] eta: 0:21:25 lr: 0.000083 grad: 0.0721 (0.0827) loss: 0.8264 (0.8277) time: 0.2694 data: 0.1770 max mem: 9390 +Train: [42] [1200/6250] eta: 0:20:47 lr: 0.000083 grad: 0.0748 (0.0825) loss: 0.8264 (0.8275) time: 0.2160 data: 0.1182 max mem: 9390 +Train: [42] [1300/6250] eta: 0:20:11 lr: 0.000083 grad: 0.0752 (0.0822) loss: 0.8302 (0.8275) time: 0.1950 data: 0.0906 max mem: 9390 +Train: [42] [1400/6250] eta: 0:19:33 lr: 0.000083 grad: 0.0808 (0.0821) loss: 0.8231 (0.8275) time: 0.2202 data: 0.1251 max mem: 9390 +Train: [42] [1500/6250] eta: 0:18:52 lr: 0.000083 grad: 0.0772 (0.0821) loss: 0.8210 (0.8273) time: 0.2232 data: 0.1131 max mem: 9390 +Train: [42] [1600/6250] eta: 0:18:15 lr: 0.000083 grad: 0.0800 (0.0820) loss: 0.8233 (0.8272) time: 0.2041 data: 0.1137 max mem: 9390 +Train: [42] [1700/6250] eta: 0:17:39 lr: 0.000083 grad: 0.0734 (0.0818) loss: 0.8259 (0.8273) time: 0.1774 data: 0.0829 max mem: 9390 +Train: [42] [1800/6250] eta: 0:17:03 lr: 0.000083 grad: 0.0763 (0.0819) loss: 0.8286 (0.8272) time: 0.1644 data: 0.0743 max mem: 9390 +Train: [42] [1900/6250] eta: 0:16:35 lr: 0.000083 grad: 0.0795 (0.0818) loss: 0.8277 (0.8271) time: 0.1779 data: 0.0771 max mem: 9390 +Train: [42] [2000/6250] eta: 0:16:04 lr: 0.000083 grad: 0.0847 (0.0820) loss: 0.8235 (0.8270) time: 0.2039 data: 0.1072 max mem: 9390 +Train: [42] [2100/6250] eta: 0:15:36 lr: 0.000083 grad: 0.0766 (0.0820) loss: 0.8279 (0.8269) time: 0.2563 data: 0.1632 max mem: 9390 +Train: [42] [2200/6250] eta: 0:15:05 lr: 0.000083 grad: 0.0811 (0.0819) loss: 0.8207 (0.8270) time: 0.1398 data: 0.0454 max mem: 9390 +Train: [42] [2300/6250] eta: 0:14:34 lr: 0.000083 grad: 0.0770 (0.0818) loss: 0.8211 (0.8269) time: 0.1625 data: 0.0772 max mem: 9390 +Train: [42] [2400/6250] eta: 0:14:06 lr: 0.000083 grad: 0.0748 (0.0816) loss: 0.8283 (0.8268) time: 0.1581 data: 0.0552 max mem: 9390 +Train: [42] [2500/6250] eta: 0:13:41 lr: 0.000083 grad: 0.0732 (0.0816) loss: 0.8288 (0.8267) time: 0.2561 data: 0.1542 max mem: 9390 +Train: [42] [2600/6250] eta: 0:13:13 lr: 0.000083 grad: 0.0796 (0.0816) loss: 0.8251 (0.8267) time: 0.1902 data: 0.1095 max mem: 9390 +Train: [42] [2700/6250] eta: 0:12:48 lr: 0.000083 grad: 0.0750 (0.0815) loss: 0.8279 (0.8267) time: 0.2304 data: 0.1485 max mem: 9390 +Train: [42] [2800/6250] eta: 0:12:25 lr: 0.000083 grad: 0.0804 (0.0816) loss: 0.8232 (0.8266) time: 0.2503 data: 0.1546 max mem: 9390 +Train: [42] [2900/6250] eta: 0:12:00 lr: 0.000083 grad: 0.0749 (0.0816) loss: 0.8252 (0.8265) time: 0.3357 data: 0.2466 max mem: 9390 +Train: [42] [3000/6250] eta: 0:11:32 lr: 0.000083 grad: 0.0741 (0.0815) loss: 0.8210 (0.8263) time: 0.1430 data: 0.0451 max mem: 9390 +Train: [42] [3100/6250] eta: 0:11:10 lr: 0.000083 grad: 0.0841 (0.0816) loss: 0.8203 (0.8262) time: 0.1017 data: 0.0002 max mem: 9390 +Train: [42] [3200/6250] eta: 0:10:47 lr: 0.000083 grad: 0.0785 (0.0816) loss: 0.8224 (0.8261) time: 0.1461 data: 0.0587 max mem: 9390 +Train: [42] [3300/6250] eta: 0:10:23 lr: 0.000083 grad: 0.0762 (0.0816) loss: 0.8265 (0.8261) time: 0.1707 data: 0.0845 max mem: 9390 +Train: [42] [3400/6250] eta: 0:10:03 lr: 0.000083 grad: 0.0859 (0.0815) loss: 0.8168 (0.8259) time: 0.3172 data: 0.2277 max mem: 9390 +Train: [42] [3500/6250] eta: 0:09:38 lr: 0.000083 grad: 0.0819 (0.0816) loss: 0.8238 (0.8259) time: 0.1846 data: 0.1004 max mem: 9390 +Train: [42] [3600/6250] eta: 0:09:15 lr: 0.000083 grad: 0.0769 (0.0816) loss: 0.8231 (0.8257) time: 0.1763 data: 0.0831 max mem: 9390 +Train: [42] [3700/6250] eta: 0:08:54 lr: 0.000083 grad: 0.0783 (0.0816) loss: 0.8243 (0.8256) time: 0.3372 data: 0.2349 max mem: 9390 +Train: [42] [3800/6250] eta: 0:08:32 lr: 0.000083 grad: 0.0808 (0.0816) loss: 0.8212 (0.8256) time: 0.2783 data: 0.1930 max mem: 9390 +Train: [42] [3900/6250] eta: 0:08:09 lr: 0.000083 grad: 0.0816 (0.0817) loss: 0.8232 (0.8255) time: 0.1876 data: 0.0933 max mem: 9390 +Train: [42] [4000/6250] eta: 0:07:47 lr: 0.000083 grad: 0.0806 (0.0817) loss: 0.8284 (0.8255) time: 0.1496 data: 0.0585 max mem: 9390 +Train: [42] [4100/6250] eta: 0:07:25 lr: 0.000082 grad: 0.0756 (0.0816) loss: 0.8256 (0.8256) time: 0.1892 data: 0.1045 max mem: 9390 +Train: [42] [4200/6250] eta: 0:07:03 lr: 0.000082 grad: 0.0784 (0.0816) loss: 0.8289 (0.8256) time: 0.0975 data: 0.0002 max mem: 9390 +Train: [42] [4300/6250] eta: 0:06:45 lr: 0.000082 grad: 0.0792 (0.0817) loss: 0.8312 (0.8256) time: 0.1897 data: 0.1029 max mem: 9390 +Train: [42] [4400/6250] eta: 0:06:24 lr: 0.000082 grad: 0.0781 (0.0816) loss: 0.8213 (0.8256) time: 0.1938 data: 0.1026 max mem: 9390 +Train: [42] [4500/6250] eta: 0:06:03 lr: 0.000082 grad: 0.0760 (0.0816) loss: 0.8305 (0.8256) time: 0.2939 data: 0.1983 max mem: 9390 +Train: [42] [4600/6250] eta: 0:05:41 lr: 0.000082 grad: 0.0782 (0.0815) loss: 0.8242 (0.8256) time: 0.2627 data: 0.1756 max mem: 9390 +Train: [42] [4700/6250] eta: 0:05:19 lr: 0.000082 grad: 0.0753 (0.0815) loss: 0.8261 (0.8256) time: 0.1656 data: 0.0804 max mem: 9390 +Train: [42] [4800/6250] eta: 0:05:00 lr: 0.000082 grad: 0.0795 (0.0815) loss: 0.8240 (0.8256) time: 0.1083 data: 0.0015 max mem: 9390 +Train: [42] [4900/6250] eta: 0:04:38 lr: 0.000082 grad: 0.0794 (0.0815) loss: 0.8275 (0.8257) time: 0.1568 data: 0.0600 max mem: 9390 +Train: [42] [5000/6250] eta: 0:04:17 lr: 0.000082 grad: 0.0826 (0.0816) loss: 0.8251 (0.8256) time: 0.1819 data: 0.0991 max mem: 9390 +Train: [42] [5100/6250] eta: 0:03:56 lr: 0.000082 grad: 0.0791 (0.0816) loss: 0.8259 (0.8257) time: 0.1671 data: 0.0802 max mem: 9390 +Train: [42] [5200/6250] eta: 0:03:35 lr: 0.000082 grad: 0.0848 (0.0816) loss: 0.8209 (0.8257) time: 0.2419 data: 0.1508 max mem: 9390 +Train: [42] [5300/6250] eta: 0:03:14 lr: 0.000082 grad: 0.0797 (0.0816) loss: 0.8245 (0.8257) time: 0.1895 data: 0.1104 max mem: 9390 +Train: [42] [5400/6250] eta: 0:02:53 lr: 0.000082 grad: 0.0851 (0.0817) loss: 0.8196 (0.8256) time: 0.1879 data: 0.1050 max mem: 9390 +Train: [42] [5500/6250] eta: 0:02:32 lr: 0.000082 grad: 0.0870 (0.0817) loss: 0.8221 (0.8256) time: 0.2160 data: 0.1340 max mem: 9390 +Train: [42] [5600/6250] eta: 0:02:11 lr: 0.000082 grad: 0.0755 (0.0817) loss: 0.8296 (0.8256) time: 0.1697 data: 0.0764 max mem: 9390 +Train: [42] [5700/6250] eta: 0:01:51 lr: 0.000082 grad: 0.0819 (0.0818) loss: 0.8239 (0.8256) time: 0.1511 data: 0.0610 max mem: 9390 +Train: [42] [5800/6250] eta: 0:01:30 lr: 0.000082 grad: 0.0840 (0.0819) loss: 0.8241 (0.8255) time: 0.1300 data: 0.0423 max mem: 9390 +Train: [42] [5900/6250] eta: 0:01:10 lr: 0.000082 grad: 0.0799 (0.0820) loss: 0.8240 (0.8255) time: 0.1067 data: 0.0149 max mem: 9390 +Train: [42] [6000/6250] eta: 0:00:50 lr: 0.000082 grad: 0.0791 (0.0820) loss: 0.8216 (0.8254) time: 0.1419 data: 0.0494 max mem: 9390 +Train: [42] [6100/6250] eta: 0:00:30 lr: 0.000082 grad: 0.0812 (0.0821) loss: 0.8260 (0.8254) time: 0.1889 data: 0.0987 max mem: 9390 +Train: [42] [6200/6250] eta: 0:00:10 lr: 0.000082 grad: 0.0832 (0.0821) loss: 0.8231 (0.8254) time: 0.2109 data: 0.1188 max mem: 9390 +Train: [42] [6249/6250] eta: 0:00:00 lr: 0.000082 grad: 0.0829 (0.0821) loss: 0.8236 (0.8254) time: 0.1814 data: 0.0989 max mem: 9390 +Train: [42] Total time: 0:21:03 (0.2021 s / it) +Averaged stats: lr: 0.000082 grad: 0.0829 (0.0821) loss: 0.8236 (0.8254) +Eval (hcp-train-subset): [42] [ 0/62] eta: 0:05:43 loss: 0.8477 (0.8477) time: 5.5343 data: 5.5005 max mem: 9390 +Eval (hcp-train-subset): [42] [61/62] eta: 0:00:00 loss: 0.8355 (0.8384) time: 0.1904 data: 0.1647 max mem: 9390 +Eval (hcp-train-subset): [42] Total time: 0:00:16 (0.2712 s / it) +Averaged stats (hcp-train-subset): loss: 0.8355 (0.8384) +Eval (hcp-val): [42] [ 0/62] eta: 0:03:24 loss: 0.8356 (0.8356) time: 3.3042 data: 3.2420 max mem: 9390 +Eval (hcp-val): [42] [61/62] eta: 0:00:00 loss: 0.8347 (0.8367) time: 0.1880 data: 0.1622 max mem: 9390 +Eval (hcp-val): [42] Total time: 0:00:16 (0.2726 s / it) +Averaged stats (hcp-val): loss: 0.8347 (0.8367) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +Train: [43] [ 0/6250] eta: 23:17:07 lr: 0.000082 grad: 0.1177 (0.1177) loss: 0.8488 (0.8488) time: 13.4124 data: 13.3085 max mem: 9390 +Train: [43] [ 100/6250] eta: 0:37:33 lr: 0.000082 grad: 0.0929 (0.1013) loss: 0.8083 (0.8263) time: 0.2669 data: 0.1585 max mem: 9390 +Train: [43] [ 200/6250] eta: 0:29:15 lr: 0.000082 grad: 0.0841 (0.0970) loss: 0.8195 (0.8222) time: 0.2175 data: 0.1132 max mem: 9390 +Train: [43] [ 300/6250] eta: 0:25:52 lr: 0.000082 grad: 0.0876 (0.0941) loss: 0.8171 (0.8216) time: 0.1911 data: 0.1023 max mem: 9390 +Train: [43] [ 400/6250] eta: 0:23:39 lr: 0.000082 grad: 0.0777 (0.0908) loss: 0.8291 (0.8215) time: 0.1808 data: 0.0724 max mem: 9390 +Train: [43] [ 500/6250] eta: 0:22:10 lr: 0.000082 grad: 0.0787 (0.0889) loss: 0.8214 (0.8219) time: 0.1991 data: 0.0983 max mem: 9390 +Train: [43] [ 600/6250] eta: 0:21:19 lr: 0.000082 grad: 0.0791 (0.0872) loss: 0.8250 (0.8226) time: 0.2274 data: 0.1411 max mem: 9390 +Train: [43] [ 700/6250] eta: 0:20:32 lr: 0.000082 grad: 0.0797 (0.0862) loss: 0.8216 (0.8232) time: 0.1922 data: 0.1018 max mem: 9390 +Train: [43] [ 800/6250] eta: 0:20:07 lr: 0.000082 grad: 0.0741 (0.0853) loss: 0.8293 (0.8234) time: 0.2870 data: 0.2065 max mem: 9390 +Train: [43] [ 900/6250] eta: 0:19:20 lr: 0.000082 grad: 0.0796 (0.0846) loss: 0.8249 (0.8239) time: 0.1710 data: 0.0780 max mem: 9390 +Train: [43] [1000/6250] eta: 0:18:38 lr: 0.000081 grad: 0.0745 (0.0842) loss: 0.8257 (0.8239) time: 0.1728 data: 0.0871 max mem: 9390 +Train: [43] [1100/6250] eta: 0:17:59 lr: 0.000081 grad: 0.0759 (0.0836) loss: 0.8245 (0.8241) time: 0.2068 data: 0.1094 max mem: 9390 +Train: [43] [1200/6250] eta: 0:17:37 lr: 0.000081 grad: 0.0761 (0.0832) loss: 0.8209 (0.8243) time: 0.1911 data: 0.0789 max mem: 9390 +Train: [43] [1300/6250] eta: 0:17:13 lr: 0.000081 grad: 0.0763 (0.0829) loss: 0.8260 (0.8245) time: 0.2113 data: 0.1105 max mem: 9390 +Train: [43] [1400/6250] eta: 0:16:42 lr: 0.000081 grad: 0.0788 (0.0826) loss: 0.8268 (0.8246) time: 0.1606 data: 0.0597 max mem: 9390 +Train: [43] [1500/6250] eta: 0:16:13 lr: 0.000081 grad: 0.0788 (0.0824) loss: 0.8233 (0.8247) time: 0.1693 data: 0.0741 max mem: 9390 +Train: [43] [1600/6250] eta: 0:15:47 lr: 0.000081 grad: 0.0778 (0.0822) loss: 0.8292 (0.8246) time: 0.1905 data: 0.1130 max mem: 9390 +Train: [43] [1700/6250] eta: 0:15:22 lr: 0.000081 grad: 0.0781 (0.0820) loss: 0.8241 (0.8246) time: 0.1766 data: 0.0730 max mem: 9390 +Train: [43] [1800/6250] eta: 0:14:57 lr: 0.000081 grad: 0.0765 (0.0820) loss: 0.8293 (0.8245) time: 0.1907 data: 0.0969 max mem: 9390 +Train: [43] [1900/6250] eta: 0:14:33 lr: 0.000081 grad: 0.0780 (0.0819) loss: 0.8300 (0.8246) time: 0.1282 data: 0.0228 max mem: 9390 +Train: [43] [2000/6250] eta: 0:14:13 lr: 0.000081 grad: 0.0816 (0.0819) loss: 0.8234 (0.8245) time: 0.2060 data: 0.1251 max mem: 9390 +Train: [43] [2100/6250] eta: 0:14:10 lr: 0.000081 grad: 0.0779 (0.0819) loss: 0.8261 (0.8245) time: 0.2669 data: 0.1897 max mem: 9390 +Train: [43] [2200/6250] eta: 0:13:44 lr: 0.000081 grad: 0.0837 (0.0820) loss: 0.8169 (0.8243) time: 0.1809 data: 0.1036 max mem: 9390 +Train: [43] [2300/6250] eta: 0:13:19 lr: 0.000081 grad: 0.0829 (0.0821) loss: 0.8206 (0.8241) time: 0.1993 data: 0.1149 max mem: 9390 +Train: [43] [2400/6250] eta: 0:12:54 lr: 0.000081 grad: 0.0807 (0.0822) loss: 0.8170 (0.8239) time: 0.1776 data: 0.0985 max mem: 9390 +Train: [43] [2500/6250] eta: 0:12:30 lr: 0.000081 grad: 0.0815 (0.0823) loss: 0.8175 (0.8237) time: 0.1933 data: 0.1044 max mem: 9390 +Train: [43] [2600/6250] eta: 0:12:06 lr: 0.000081 grad: 0.0774 (0.0824) loss: 0.8152 (0.8234) time: 0.1811 data: 0.0930 max mem: 9390 +Train: [43] [2700/6250] eta: 0:11:43 lr: 0.000081 grad: 0.0754 (0.0824) loss: 0.8213 (0.8233) time: 0.1698 data: 0.0835 max mem: 9390 +Train: [43] [2800/6250] eta: 0:11:19 lr: 0.000081 grad: 0.0830 (0.0826) loss: 0.8221 (0.8231) time: 0.1674 data: 0.0790 max mem: 9390 +Train: [43] [2900/6250] eta: 0:10:56 lr: 0.000081 grad: 0.0847 (0.0826) loss: 0.8172 (0.8230) time: 0.1839 data: 0.0973 max mem: 9390 +Train: [43] [3000/6250] eta: 0:10:33 lr: 0.000081 grad: 0.0829 (0.0827) loss: 0.8183 (0.8228) time: 0.1816 data: 0.0938 max mem: 9390 +Train: [43] [3100/6250] eta: 0:10:12 lr: 0.000081 grad: 0.0840 (0.0827) loss: 0.8241 (0.8226) time: 0.1708 data: 0.0852 max mem: 9390 +Train: [43] [3200/6250] eta: 0:09:50 lr: 0.000081 grad: 0.0816 (0.0829) loss: 0.8229 (0.8225) time: 0.1843 data: 0.0961 max mem: 9390 +Train: [43] [3300/6250] eta: 0:09:28 lr: 0.000081 grad: 0.0828 (0.0830) loss: 0.8181 (0.8224) time: 0.1686 data: 0.0865 max mem: 9390 +Train: [43] [3400/6250] eta: 0:09:07 lr: 0.000081 grad: 0.0851 (0.0832) loss: 0.8170 (0.8224) time: 0.1686 data: 0.0796 max mem: 9390 +Train: [43] [3500/6250] eta: 0:08:46 lr: 0.000081 grad: 0.0831 (0.0832) loss: 0.8154 (0.8222) time: 0.2018 data: 0.1198 max mem: 9390 +Train: [43] [3600/6250] eta: 0:08:25 lr: 0.000081 grad: 0.0868 (0.0833) loss: 0.8131 (0.8221) time: 0.1720 data: 0.0898 max mem: 9390 +Train: [43] [3700/6250] eta: 0:08:04 lr: 0.000081 grad: 0.0771 (0.0833) loss: 0.8183 (0.8221) time: 0.1476 data: 0.0638 max mem: 9390 +Train: [43] [3800/6250] eta: 0:07:44 lr: 0.000081 grad: 0.0805 (0.0834) loss: 0.8192 (0.8220) time: 0.1409 data: 0.0589 max mem: 9390 +Train: [43] [3900/6250] eta: 0:07:24 lr: 0.000081 grad: 0.0781 (0.0833) loss: 0.8277 (0.8219) time: 0.1835 data: 0.1061 max mem: 9390 +Train: [43] [4000/6250] eta: 0:07:04 lr: 0.000081 grad: 0.0861 (0.0834) loss: 0.8236 (0.8219) time: 0.1528 data: 0.0610 max mem: 9390 +Train: [43] [4100/6250] eta: 0:06:45 lr: 0.000081 grad: 0.0854 (0.0835) loss: 0.8172 (0.8219) time: 0.1714 data: 0.0945 max mem: 9390 +Train: [43] [4200/6250] eta: 0:06:25 lr: 0.000080 grad: 0.0892 (0.0836) loss: 0.8188 (0.8219) time: 0.1675 data: 0.0800 max mem: 9390 +Train: [43] [4300/6250] eta: 0:06:05 lr: 0.000080 grad: 0.0825 (0.0836) loss: 0.8217 (0.8218) time: 0.1700 data: 0.0689 max mem: 9390 +Train: [43] [4400/6250] eta: 0:05:46 lr: 0.000080 grad: 0.0915 (0.0837) loss: 0.8170 (0.8218) time: 0.1637 data: 0.0765 max mem: 9390 +Train: [43] [4500/6250] eta: 0:05:26 lr: 0.000080 grad: 0.0844 (0.0838) loss: 0.8161 (0.8217) time: 0.1713 data: 0.0862 max mem: 9390 +Train: [43] [4600/6250] eta: 0:05:06 lr: 0.000080 grad: 0.0873 (0.0838) loss: 0.8145 (0.8217) time: 0.1387 data: 0.0475 max mem: 9390 +Train: [43] [4700/6250] eta: 0:04:47 lr: 0.000080 grad: 0.0859 (0.0838) loss: 0.8198 (0.8217) time: 0.1966 data: 0.1098 max mem: 9390 +Train: [43] [4800/6250] eta: 0:04:28 lr: 0.000080 grad: 0.0787 (0.0838) loss: 0.8202 (0.8217) time: 0.1595 data: 0.0635 max mem: 9390 +Train: [43] [4900/6250] eta: 0:04:09 lr: 0.000080 grad: 0.0808 (0.0838) loss: 0.8236 (0.8217) time: 0.1705 data: 0.0804 max mem: 9390 +Train: [43] [5000/6250] eta: 0:03:50 lr: 0.000080 grad: 0.0812 (0.0839) loss: 0.8174 (0.8217) time: 0.1645 data: 0.0825 max mem: 9390 +Train: [43] [5100/6250] eta: 0:03:31 lr: 0.000080 grad: 0.0798 (0.0839) loss: 0.8225 (0.8217) time: 0.2146 data: 0.1287 max mem: 9390 +Train: [43] [5200/6250] eta: 0:03:13 lr: 0.000080 grad: 0.0803 (0.0839) loss: 0.8197 (0.8217) time: 0.1425 data: 0.0586 max mem: 9390 +Train: [43] [5300/6250] eta: 0:02:54 lr: 0.000080 grad: 0.0787 (0.0838) loss: 0.8253 (0.8217) time: 0.1455 data: 0.0608 max mem: 9390 +Train: [43] [5400/6250] eta: 0:02:36 lr: 0.000080 grad: 0.0848 (0.0839) loss: 0.8180 (0.8217) time: 0.1044 data: 0.0002 max mem: 9390 +Train: [43] [5500/6250] eta: 0:02:17 lr: 0.000080 grad: 0.0824 (0.0839) loss: 0.8167 (0.8217) time: 0.1399 data: 0.0416 max mem: 9390 +Train: [43] [5600/6250] eta: 0:01:59 lr: 0.000080 grad: 0.0812 (0.0839) loss: 0.8249 (0.8217) time: 0.1637 data: 0.0853 max mem: 9390 +Train: [43] [5700/6250] eta: 0:01:40 lr: 0.000080 grad: 0.0792 (0.0839) loss: 0.8260 (0.8218) time: 0.1783 data: 0.0916 max mem: 9390 +Train: [43] [5800/6250] eta: 0:01:22 lr: 0.000080 grad: 0.0855 (0.0839) loss: 0.8243 (0.8218) time: 0.1906 data: 0.1035 max mem: 9390 +Train: [43] [5900/6250] eta: 0:01:04 lr: 0.000080 grad: 0.0778 (0.0839) loss: 0.8269 (0.8218) time: 0.1808 data: 0.0889 max mem: 9390 +Train: [43] [6000/6250] eta: 0:00:45 lr: 0.000080 grad: 0.0861 (0.0840) loss: 0.8230 (0.8218) time: 0.1700 data: 0.0671 max mem: 9390 +Train: [43] [6100/6250] eta: 0:00:27 lr: 0.000080 grad: 0.0788 (0.0840) loss: 0.8264 (0.8219) time: 0.2564 data: 0.1708 max mem: 9390 +Train: [43] [6200/6250] eta: 0:00:09 lr: 0.000080 grad: 0.0850 (0.0840) loss: 0.8277 (0.8219) time: 0.1709 data: 0.0897 max mem: 9390 +Train: [43] [6249/6250] eta: 0:00:00 lr: 0.000080 grad: 0.0789 (0.0840) loss: 0.8296 (0.8219) time: 0.1983 data: 0.1060 max mem: 9390 +Train: [43] Total time: 0:19:24 (0.1863 s / it) +Averaged stats: lr: 0.000080 grad: 0.0789 (0.0840) loss: 0.8296 (0.8219) +Eval (hcp-train-subset): [43] [ 0/62] eta: 0:03:22 loss: 0.8513 (0.8513) time: 3.2631 data: 3.1997 max mem: 9390 +Eval (hcp-train-subset): [43] [61/62] eta: 0:00:00 loss: 0.8357 (0.8383) time: 0.1694 data: 0.1443 max mem: 9390 +Eval (hcp-train-subset): [43] Total time: 0:00:14 (0.2381 s / it) +Averaged stats (hcp-train-subset): loss: 0.8357 (0.8383) +Eval (hcp-val): [43] [ 0/62] eta: 0:03:59 loss: 0.8313 (0.8313) time: 3.8557 data: 3.7885 max mem: 9390 +Eval (hcp-val): [43] [61/62] eta: 0:00:00 loss: 0.8356 (0.8372) time: 0.1638 data: 0.1373 max mem: 9390 +Eval (hcp-val): [43] Total time: 0:00:17 (0.2825 s / it) +Averaged stats (hcp-val): loss: 0.8356 (0.8372) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +Train: [44] [ 0/6250] eta: 13:17:31 lr: 0.000080 grad: 0.1834 (0.1834) loss: 0.8297 (0.8297) time: 7.6563 data: 7.4909 max mem: 9390 +Train: [44] [ 100/6250] eta: 0:27:38 lr: 0.000080 grad: 0.0842 (0.0870) loss: 0.8312 (0.8377) time: 0.2149 data: 0.0858 max mem: 9390 +Train: [44] [ 200/6250] eta: 0:24:23 lr: 0.000080 grad: 0.0876 (0.0877) loss: 0.8229 (0.8311) time: 0.2358 data: 0.1380 max mem: 9390 +Train: [44] [ 300/6250] eta: 0:23:27 lr: 0.000080 grad: 0.0800 (0.0877) loss: 0.8273 (0.8289) time: 0.2985 data: 0.2120 max mem: 9390 +Train: [44] [ 400/6250] eta: 0:22:23 lr: 0.000080 grad: 0.0798 (0.0866) loss: 0.8251 (0.8280) time: 0.2214 data: 0.1257 max mem: 9390 +Train: [44] [ 500/6250] eta: 0:21:22 lr: 0.000080 grad: 0.0792 (0.0864) loss: 0.8324 (0.8276) time: 0.2071 data: 0.0716 max mem: 9390 +Train: [44] [ 600/6250] eta: 0:20:41 lr: 0.000080 grad: 0.0796 (0.0856) loss: 0.8247 (0.8276) time: 0.1944 data: 0.0775 max mem: 9390 +Train: [44] [ 700/6250] eta: 0:20:00 lr: 0.000080 grad: 0.0778 (0.0852) loss: 0.8260 (0.8273) time: 0.1818 data: 0.0798 max mem: 9390 +Train: [44] [ 800/6250] eta: 0:19:20 lr: 0.000080 grad: 0.0753 (0.0844) loss: 0.8299 (0.8274) time: 0.2059 data: 0.1116 max mem: 9390 +Train: [44] [ 900/6250] eta: 0:18:56 lr: 0.000080 grad: 0.0824 (0.0839) loss: 0.8249 (0.8272) time: 0.2670 data: 0.1896 max mem: 9390 +Train: [44] [1000/6250] eta: 0:18:24 lr: 0.000080 grad: 0.0791 (0.0834) loss: 0.8261 (0.8273) time: 0.1785 data: 0.0913 max mem: 9390 +Train: [44] [1100/6250] eta: 0:17:48 lr: 0.000079 grad: 0.0791 (0.0831) loss: 0.8301 (0.8273) time: 0.1527 data: 0.0700 max mem: 9390 +pretraining fmri mae +start: 2026-04-02 20:43:05 +cwd: /data/connor/fmri-fm +sha: bcce2b486277d3a5b520775efd9cdf1a2affce36, status: has uncommitted changes, branch: dev/clane9 +config: +name: input_space_v3/flat_lr1e-3_5/pretrain +notes: input_space ablation v3 flat_lr1e-3_5; use tube masking and on-disk data (input_space=flat + base_lr=1e-3 seed=5405) +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain +input_space: flat +patch_size: 16 +num_frames: 16 +t_patch_size: 4 +mask_ratio: 0.9 +pred_mask_ratio: null +masking: tube +masking_kwargs: {} +mask_patch_size: null +model: mae_vit_base +model_kwargs: + decoding: attn + pos_embed: sep + target_norm: null + pca_norm_nc: 2 + t_pred_stride: 2 + no_decode_pos: true + mask_drop_scale: false + pred_edge_pad: 0 + gauss_sigma: null + class_token: true + reg_tokens: 0 + no_embed_class: true + head_init_scale: 0.0 + decoder_depth: 4 + drop_path_rate: 0.0 +datasets: + hcp-train: + type: wds + url: /data/fmri-datasets/pretrain/hcpya-all.${input_space}.wds/hcpya-all-${input_space}-{00000..01799}.tar + clipping: random + clipping_kwargs: + oversample: 4.0 + shuffle: true + buffer_size: 2000 + samples_per_epoch: 200000 + hcp-train-subset: + type: arrow + root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/validation + split_range: + - 0 + - 2000 + shuffle: false + hcp-val: + type: arrow + root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/test + split_range: + - 0 + - 2000 + shuffle: false +train_dataset: hcp-train +eval_datasets: +- hcp-train-subset +- hcp-val +val_dataset: null +clip_vmax: 3.0 +normalize: frame +tr_scale: null +crop_scale: null +crop_aspect: null +gray_jitter: null +num_workers: 16 +epochs: 100 +batch_size: 32 +accum_iter: 1 +base_lr: 0.001 +min_lr: 0.0 +warmup_epochs: 5 +weight_decay: 0.05 +betas: +- 0.9 +- 0.95 +clip_grad: 1.0 +amp: true +amp_dtype: float16 +ckpt: null +resume: true +auto_resume: true +start_epoch: 0 +max_checkpoints: 0 +checkpoint_period: null +plot_period: 5 +device: cuda +presend_cuda: false +seed: 5405 +debug: false +wandb: true +wandb_entity: null +wandb_project: fMRI-foundation-model +rank: 0 +world_size: 1 +gpu: 0 +distributed: true +dist_backend: nccl +in_chans: 1 +img_size: +- 224 +- 560 + +train transform: +Compose( + ToTensor() + TemporalCenterCrop(num_frames=16) + Normalize(mode='frame') + Clip(vmax=3.0) + FlatUnmask((224, 560)) +) +val transform: +Compose( + ToTensor() + TemporalCenterCrop(num_frames=16) + Normalize(mode='frame') + Clip(vmax=3.0) + FlatUnmask((224, 560)) +) +mask generator: +TubeMasking( + mask_ratio=0.9 + (patchify): Patchify2D((224, 560), (16, 16), in_chans=1) +) +loading dataset: hcp-train + +type: wds +url: /data/fmri-datasets/pretrain/hcpya-all.${input_space}.wds/hcpya-all-${input_space}-{00000..01799}.tar +clipping: random +clipping_kwargs: + oversample: 4.0 +shuffle: true +buffer_size: 2000 +samples_per_epoch: 200000 + +loading dataset: hcp-train-subset + +type: arrow +root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/validation +split_range: +- 0 +- 2000 +shuffle: false + +pretraining fmri mae +start: 2026-04-02 20:47:29 +cwd: /data/connor/fmri-fm +sha: bcce2b486277d3a5b520775efd9cdf1a2affce36, status: has uncommitted changes, branch: dev/clane9 +config: +name: input_space_v3/flat_lr1e-3_5/pretrain +notes: input_space ablation v3 flat_lr1e-3_5; use tube masking and on-disk data (input_space=flat + base_lr=1e-3 seed=5405) +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain +input_space: flat +patch_size: 16 +num_frames: 16 +t_patch_size: 4 +mask_ratio: 0.9 +pred_mask_ratio: null +masking: tube +masking_kwargs: {} +mask_patch_size: null +model: mae_vit_base +model_kwargs: + decoding: attn + pos_embed: sep + target_norm: null + pca_norm_nc: 2 + t_pred_stride: 2 + no_decode_pos: true + mask_drop_scale: false + pred_edge_pad: 0 + gauss_sigma: null + class_token: true + reg_tokens: 0 + no_embed_class: true + head_init_scale: 0.0 + decoder_depth: 4 + drop_path_rate: 0.0 +datasets: + hcp-train: + type: wds + url: /data/fmri-datasets/pretrain/hcpya-all.${input_space}.wds/hcpya-all-${input_space}-{00000..01799}.tar + clipping: random + clipping_kwargs: + oversample: 4.0 + shuffle: true + buffer_size: 2000 + samples_per_epoch: 200000 + hcp-train-subset: + type: arrow + root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/validation + split_range: + - 0 + - 2000 + shuffle: false + hcp-val: + type: arrow + root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/test + split_range: + - 0 + - 2000 + shuffle: false +train_dataset: hcp-train +eval_datasets: +- hcp-train-subset +- hcp-val +val_dataset: null +clip_vmax: 3.0 +normalize: frame +tr_scale: null +crop_scale: null +crop_aspect: null +gray_jitter: null +num_workers: 16 +epochs: 100 +batch_size: 32 +accum_iter: 1 +base_lr: 0.001 +min_lr: 0.0 +warmup_epochs: 5 +weight_decay: 0.05 +betas: +- 0.9 +- 0.95 +clip_grad: 1.0 +amp: true +amp_dtype: float16 +ckpt: null +resume: true +auto_resume: true +start_epoch: 0 +max_checkpoints: 0 +checkpoint_period: null +plot_period: 5 +device: cuda +presend_cuda: false +seed: 5405 +debug: false +wandb: true +wandb_entity: null +wandb_project: fMRI-foundation-model +rank: 0 +world_size: 1 +gpu: 0 +distributed: true +dist_backend: nccl +in_chans: 1 +img_size: +- 224 +- 560 + +train transform: +Compose( + ToTensor() + TemporalCenterCrop(num_frames=16) + Normalize(mode='frame') + Clip(vmax=3.0) + FlatUnmask((224, 560)) +) +val transform: +Compose( + ToTensor() + TemporalCenterCrop(num_frames=16) + Normalize(mode='frame') + Clip(vmax=3.0) + FlatUnmask((224, 560)) +) +mask generator: +TubeMasking( + mask_ratio=0.9 + (patchify): Patchify2D((224, 560), (16, 16), in_chans=1) +) +loading dataset: hcp-train + +type: wds +url: /data/fmri-datasets/pretrain/hcpya-all.${input_space}.wds/hcpya-all-${input_space}-{00000..01799}.tar +clipping: random +clipping_kwargs: + oversample: 4.0 +shuffle: true +buffer_size: 2000 +samples_per_epoch: 200000 + +loading dataset: hcp-train-subset + +type: arrow +root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/validation +split_range: +- 0 +- 2000 +shuffle: false + +split indices: [899, 472, 767, 116, 1265, 1852, 300, 1335, 361, 1560] +loading dataset: hcp-val + +type: arrow +root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/test +split_range: +- 0 +- 2000 +shuffle: false + +split indices: [1075, 1189, 738, 1350, 965, 1964, 1367, 1183, 1619, 1407] +model: +MaskedAutoencoderViT( + decoding=attn, t_pred_stride=2, pred_edge_pad=0, no_decode_pos=True + (encoder): MaskedEncoder( + class_token=True, reg_tokens=0, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) + (pred_patchify): StridedPatchify3D((16, 224, 560), (2, 16, 16), in_chans=1, t_stride=2) + (decoder): MaskedDecoder( + cross_decode=False, class_token=True, no_embed_class=True + (pos_embed): SeparablePosEmbed(512, (4, 14, 35)) + (proj): Linear(in_features=768, out_features=512, bias=True) + (blocks): ModuleList( + (0-3): 4 x Block( + (norm1): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=16 + (q): Linear(in_features=512, out_features=512, bias=True) + (k): Linear(in_features=512, out_features=512, bias=True) + (v): Linear(in_features=512, out_features=512, bias=True) + (proj): Linear(in_features=512, out_features=512, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=512, out_features=2048, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=2048, out_features=512, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (head): Linear(in_features=512, out_features=512, bias=True) + ) +) +num params: 99.7M +total batch size: 32 = 32 bs per gpu x 1 accum x 1 gpus +lr: 1.25e-04 = 1.00e-03 x 32 / 256 +full schedule: epochs = 100 (steps = 625000) +warmup: epochs = 5 (steps = 31250) +loaded model state from checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +loaded optimizer state, resuming training from 44 +start training for 100 epochs +Train: [44] [ 0/6250] eta: 10:34:47 lr: 0.000080 grad: 0.3452 (0.3452) loss: 0.8253 (0.8253) time: 6.0941 data: 5.1710 max mem: 9353 +Train: [44] [ 100/6250] eta: 0:20:57 lr: 0.000080 grad: 0.0759 (0.0900) loss: 0.8288 (0.8329) time: 0.1414 data: 0.0588 max mem: 9390 +Train: [44] [ 200/6250] eta: 0:17:49 lr: 0.000080 grad: 0.0726 (0.0867) loss: 0.8286 (0.8280) time: 0.1489 data: 0.0618 max mem: 9390 +Train: [44] [ 300/6250] eta: 0:16:23 lr: 0.000080 grad: 0.0799 (0.0851) loss: 0.8268 (0.8258) time: 0.1547 data: 0.0629 max mem: 9390 +Train: [44] [ 400/6250] eta: 0:15:34 lr: 0.000080 grad: 0.0770 (0.0840) loss: 0.8301 (0.8248) time: 0.1317 data: 0.0292 max mem: 9390 +Train: [44] [ 500/6250] eta: 0:15:05 lr: 0.000080 grad: 0.0738 (0.0834) loss: 0.8296 (0.8250) time: 0.1720 data: 0.0744 max mem: 9390 +Train: [44] [ 600/6250] eta: 0:14:33 lr: 0.000080 grad: 0.0707 (0.0828) loss: 0.8304 (0.8252) time: 0.1372 data: 0.0457 max mem: 9390 +Train: [44] [ 700/6250] eta: 0:14:10 lr: 0.000080 grad: 0.0782 (0.0830) loss: 0.8294 (0.8253) time: 0.1542 data: 0.0609 max mem: 9390 +Train: [44] [ 800/6250] eta: 0:13:47 lr: 0.000080 grad: 0.0826 (0.0828) loss: 0.8247 (0.8254) time: 0.1398 data: 0.0427 max mem: 9390 +Train: [44] [ 900/6250] eta: 0:13:38 lr: 0.000080 grad: 0.0738 (0.0826) loss: 0.8239 (0.8253) time: 0.1639 data: 0.0751 max mem: 9390 +Train: [44] [1000/6250] eta: 0:13:28 lr: 0.000080 grad: 0.0691 (0.0824) loss: 0.8301 (0.8255) time: 0.1609 data: 0.0793 max mem: 9390 +Train: [44] [1100/6250] eta: 0:13:13 lr: 0.000079 grad: 0.0789 (0.0821) loss: 0.8248 (0.8257) time: 0.1431 data: 0.0552 max mem: 9390 +Train: [44] [1200/6250] eta: 0:12:57 lr: 0.000079 grad: 0.0780 (0.0818) loss: 0.8204 (0.8259) time: 0.1565 data: 0.0748 max mem: 9390 +Train: [44] [1300/6250] eta: 0:12:42 lr: 0.000079 grad: 0.0779 (0.0816) loss: 0.8288 (0.8258) time: 0.1613 data: 0.0700 max mem: 9390 +Train: [44] [1400/6250] eta: 0:12:24 lr: 0.000079 grad: 0.0748 (0.0815) loss: 0.8278 (0.8258) time: 0.1516 data: 0.0641 max mem: 9390 +Train: [44] [1500/6250] eta: 0:12:09 lr: 0.000079 grad: 0.0789 (0.0815) loss: 0.8266 (0.8257) time: 0.1511 data: 0.0709 max mem: 9390 +Train: [44] [1600/6250] eta: 0:11:53 lr: 0.000079 grad: 0.0766 (0.0816) loss: 0.8227 (0.8257) time: 0.1498 data: 0.0643 max mem: 9390 +Train: [44] [1700/6250] eta: 0:11:36 lr: 0.000079 grad: 0.0797 (0.0817) loss: 0.8173 (0.8255) time: 0.1286 data: 0.0466 max mem: 9390 +Train: [44] [1800/6250] eta: 0:11:19 lr: 0.000079 grad: 0.0782 (0.0816) loss: 0.8213 (0.8254) time: 0.1432 data: 0.0604 max mem: 9390 +Train: [44] [1900/6250] eta: 0:11:03 lr: 0.000079 grad: 0.0844 (0.0818) loss: 0.8197 (0.8252) time: 0.1572 data: 0.0732 max mem: 9390 +Train: [44] [2000/6250] eta: 0:10:46 lr: 0.000079 grad: 0.0818 (0.0818) loss: 0.8260 (0.8252) time: 0.1453 data: 0.0618 max mem: 9390 +Train: [44] [2100/6250] eta: 0:10:29 lr: 0.000079 grad: 0.0821 (0.0818) loss: 0.8241 (0.8252) time: 0.1167 data: 0.0393 max mem: 9390 +Train: [44] [2200/6250] eta: 0:10:13 lr: 0.000079 grad: 0.0782 (0.0824) loss: 0.8256 (0.8251) time: 0.1338 data: 0.0476 max mem: 9390 +Train: [44] [2300/6250] eta: 0:09:57 lr: 0.000079 grad: 0.0755 (0.0823) loss: 0.8280 (0.8250) time: 0.1622 data: 0.0799 max mem: 9390 +Train: [44] [2400/6250] eta: 0:09:42 lr: 0.000079 grad: 0.0784 (0.0824) loss: 0.8169 (0.8249) time: 0.1650 data: 0.0857 max mem: 9390 +Train: [44] [2500/6250] eta: 0:09:26 lr: 0.000079 grad: 0.0808 (0.0824) loss: 0.8186 (0.8249) time: 0.1381 data: 0.0561 max mem: 9390 +pretraining fmri mae +start: 2026-04-02 21:02:06 +cwd: /data/connor/fmri-fm +sha: bcce2b486277d3a5b520775efd9cdf1a2affce36, status: has uncommitted changes, branch: dev/clane9 +config: +name: input_space_v3/flat_lr1e-3_5/pretrain +notes: input_space ablation v3 flat_lr1e-3_5; use tube masking and on-disk data (input_space=flat + base_lr=1e-3 seed=5405) +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain +input_space: flat +patch_size: 16 +num_frames: 16 +t_patch_size: 4 +mask_ratio: 0.9 +pred_mask_ratio: null +masking: tube +masking_kwargs: {} +mask_patch_size: null +model: mae_vit_base +model_kwargs: + decoding: attn + pos_embed: sep + target_norm: null + pca_norm_nc: 2 + t_pred_stride: 2 + no_decode_pos: true + mask_drop_scale: false + pred_edge_pad: 0 + gauss_sigma: null + class_token: true + reg_tokens: 0 + no_embed_class: true + head_init_scale: 0.0 + decoder_depth: 4 + drop_path_rate: 0.0 +datasets: + hcp-train: + type: wds + url: /data/fmri-datasets/pretrain/hcpya-all.${input_space}.wds/hcpya-all-${input_space}-{00000..01799}.tar + clipping: random + clipping_kwargs: + oversample: 4.0 + shuffle: true + buffer_size: 2000 + samples_per_epoch: 200000 + hcp-train-subset: + type: arrow + root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/validation + split_range: + - 0 + - 2000 + shuffle: false + hcp-val: + type: arrow + root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/test + split_range: + - 0 + - 2000 + shuffle: false +train_dataset: hcp-train +eval_datasets: +- hcp-train-subset +- hcp-val +val_dataset: null +clip_vmax: 3.0 +normalize: frame +tr_scale: null +crop_scale: null +crop_aspect: null +gray_jitter: null +num_workers: 16 +epochs: 100 +batch_size: 32 +accum_iter: 1 +base_lr: 0.001 +min_lr: 0.0 +warmup_epochs: 5 +weight_decay: 0.05 +betas: +- 0.9 +- 0.95 +clip_grad: 1.0 +amp: true +amp_dtype: float16 +ckpt: null +resume: true +auto_resume: true +start_epoch: 0 +max_checkpoints: 0 +checkpoint_period: null +plot_period: 5 +device: cuda +presend_cuda: false +seed: 5405 +debug: false +wandb: true +wandb_entity: null +wandb_project: fMRI-foundation-model +rank: 0 +world_size: 1 +gpu: 0 +distributed: true +dist_backend: nccl +in_chans: 1 +img_size: +- 224 +- 560 + +train transform: +Compose( + ToTensor() + TemporalCenterCrop(num_frames=16) + Normalize(mode='frame') + Clip(vmax=3.0) + FlatUnmask((224, 560)) +) +val transform: +Compose( + ToTensor() + TemporalCenterCrop(num_frames=16) + Normalize(mode='frame') + Clip(vmax=3.0) + FlatUnmask((224, 560)) +) +mask generator: +TubeMasking( + mask_ratio=0.9 + (patchify): Patchify2D((224, 560), (16, 16), in_chans=1) +) +loading dataset: hcp-train + +type: wds +url: /data/fmri-datasets/pretrain/hcpya-all.${input_space}.wds/hcpya-all-${input_space}-{00000..01799}.tar +clipping: random +clipping_kwargs: + oversample: 4.0 +shuffle: true +buffer_size: 2000 +samples_per_epoch: 200000 + +loading dataset: hcp-train-subset + +type: arrow +root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/validation +split_range: +- 0 +- 2000 +shuffle: false + +split indices: [899, 472, 767, 116, 1265, 1852, 300, 1335, 361, 1560] +loading dataset: hcp-val + +type: arrow +root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/test +split_range: +- 0 +- 2000 +shuffle: false + +split indices: [1075, 1189, 738, 1350, 965, 1964, 1367, 1183, 1619, 1407] +model: +MaskedAutoencoderViT( + decoding=attn, t_pred_stride=2, pred_edge_pad=0, no_decode_pos=True + (encoder): MaskedEncoder( + class_token=True, reg_tokens=0, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) + (pred_patchify): StridedPatchify3D((16, 224, 560), (2, 16, 16), in_chans=1, t_stride=2) + (decoder): MaskedDecoder( + cross_decode=False, class_token=True, no_embed_class=True + (pos_embed): SeparablePosEmbed(512, (4, 14, 35)) + (proj): Linear(in_features=768, out_features=512, bias=True) + (blocks): ModuleList( + (0-3): 4 x Block( + (norm1): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=16 + (q): Linear(in_features=512, out_features=512, bias=True) + (k): Linear(in_features=512, out_features=512, bias=True) + (v): Linear(in_features=512, out_features=512, bias=True) + (proj): Linear(in_features=512, out_features=512, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=512, out_features=2048, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=2048, out_features=512, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (head): Linear(in_features=512, out_features=512, bias=True) + ) +) +num params: 99.7M +total batch size: 32 = 32 bs per gpu x 1 accum x 1 gpus +lr: 1.25e-04 = 1.00e-03 x 32 / 256 +full schedule: epochs = 100 (steps = 625000) +warmup: epochs = 5 (steps = 31250) +loaded model state from checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +loaded optimizer state, resuming training from 44 +start training for 100 epochs +Train: [44] [ 0/6250] eta: 14:34:14 lr: 0.000080 grad: 0.1810 (0.1810) loss: 0.7710 (0.7710) time: 8.3927 data: 7.3709 max mem: 9353 +Train: [44] [ 100/6250] eta: 0:20:28 lr: 0.000080 grad: 0.0840 (0.0961) loss: 0.8290 (0.8333) time: 0.1248 data: 0.0381 max mem: 9390 +Train: [44] [ 200/6250] eta: 0:18:25 lr: 0.000080 grad: 0.0775 (0.0915) loss: 0.8286 (0.8302) time: 0.1475 data: 0.0458 max mem: 9390 +Train: [44] [ 300/6250] eta: 0:18:36 lr: 0.000080 grad: 0.0808 (0.0893) loss: 0.8332 (0.8287) time: 0.2343 data: 0.1308 max mem: 9390 +Train: [44] [ 400/6250] eta: 0:19:04 lr: 0.000080 grad: 0.0791 (0.0874) loss: 0.8220 (0.8284) time: 0.1718 data: 0.0524 max mem: 9390 +Train: [44] [ 500/6250] eta: 0:18:30 lr: 0.000080 grad: 0.0807 (0.0872) loss: 0.8220 (0.8276) time: 0.1793 data: 0.0841 max mem: 9390 +Train: [44] [ 600/6250] eta: 0:17:52 lr: 0.000080 grad: 0.0755 (0.0861) loss: 0.8270 (0.8271) time: 0.1792 data: 0.0605 max mem: 9390 +Train: [44] [ 700/6250] eta: 0:17:18 lr: 0.000080 grad: 0.0757 (0.0852) loss: 0.8282 (0.8272) time: 0.1525 data: 0.0581 max mem: 9390 +Train: [44] [ 800/6250] eta: 0:16:49 lr: 0.000080 grad: 0.0718 (0.0843) loss: 0.8278 (0.8272) time: 0.1630 data: 0.0561 max mem: 9390 +Train: [44] [ 900/6250] eta: 0:16:25 lr: 0.000080 grad: 0.0762 (0.0846) loss: 0.8316 (0.8275) time: 0.1688 data: 0.0779 max mem: 9390 +Train: [44] [1000/6250] eta: 0:16:01 lr: 0.000080 grad: 0.0777 (0.0841) loss: 0.8254 (0.8275) time: 0.1820 data: 0.0879 max mem: 9390 +Train: [44] [1100/6250] eta: 0:15:33 lr: 0.000079 grad: 0.0748 (0.0837) loss: 0.8285 (0.8275) time: 0.1695 data: 0.0806 max mem: 9390 +Train: [44] [1200/6250] eta: 0:15:06 lr: 0.000079 grad: 0.0722 (0.0836) loss: 0.8307 (0.8275) time: 0.1558 data: 0.0668 max mem: 9390 +Train: [44] [1300/6250] eta: 0:14:44 lr: 0.000079 grad: 0.0764 (0.0832) loss: 0.8286 (0.8276) time: 0.1690 data: 0.0853 max mem: 9390 +Train: [44] [1400/6250] eta: 0:14:24 lr: 0.000079 grad: 0.0749 (0.0830) loss: 0.8328 (0.8276) time: 0.1880 data: 0.0948 max mem: 9390 +Train: [44] [1500/6250] eta: 0:14:02 lr: 0.000079 grad: 0.0821 (0.0828) loss: 0.8238 (0.8276) time: 0.1604 data: 0.0787 max mem: 9390 +Train: [44] [1600/6250] eta: 0:13:39 lr: 0.000079 grad: 0.0803 (0.0827) loss: 0.8201 (0.8274) time: 0.1748 data: 0.0838 max mem: 9390 +Train: [44] [1700/6250] eta: 0:13:19 lr: 0.000079 grad: 0.0807 (0.0829) loss: 0.8291 (0.8273) time: 0.1632 data: 0.0813 max mem: 9390 +Train: [44] [1800/6250] eta: 0:12:58 lr: 0.000079 grad: 0.0795 (0.0829) loss: 0.8269 (0.8271) time: 0.1360 data: 0.0431 max mem: 9390 +Train: [44] [1900/6250] eta: 0:12:38 lr: 0.000079 grad: 0.0773 (0.0829) loss: 0.8285 (0.8269) time: 0.1781 data: 0.0966 max mem: 9390 +Train: [44] [2000/6250] eta: 0:12:18 lr: 0.000079 grad: 0.0788 (0.0829) loss: 0.8155 (0.8267) time: 0.1559 data: 0.0700 max mem: 9390 +Train: [44] [2100/6250] eta: 0:11:58 lr: 0.000079 grad: 0.0811 (0.0829) loss: 0.8251 (0.8266) time: 0.1714 data: 0.0856 max mem: 9390 +Train: [44] [2200/6250] eta: 0:11:39 lr: 0.000079 grad: 0.0789 (0.0829) loss: 0.8258 (0.8265) time: 0.1693 data: 0.0762 max mem: 9390 +Train: [44] [2300/6250] eta: 0:11:19 lr: 0.000079 grad: 0.0760 (0.0828) loss: 0.8256 (0.8265) time: 0.1462 data: 0.0559 max mem: 9390 +Train: [44] [2400/6250] eta: 0:11:00 lr: 0.000079 grad: 0.0790 (0.0829) loss: 0.8235 (0.8263) time: 0.1543 data: 0.0671 max mem: 9390 +Train: [44] [2500/6250] eta: 0:10:43 lr: 0.000079 grad: 0.0802 (0.0830) loss: 0.8231 (0.8261) time: 0.2012 data: 0.1177 max mem: 9390 +Train: [44] [2600/6250] eta: 0:10:23 lr: 0.000079 grad: 0.0851 (0.0831) loss: 0.8191 (0.8260) time: 0.1745 data: 0.0891 max mem: 9390 +Train: [44] [2700/6250] eta: 0:10:05 lr: 0.000079 grad: 0.0836 (0.0830) loss: 0.8248 (0.8259) time: 0.1580 data: 0.0749 max mem: 9390 +Train: [44] [2800/6250] eta: 0:09:46 lr: 0.000079 grad: 0.0800 (0.0830) loss: 0.8281 (0.8258) time: 0.1542 data: 0.0716 max mem: 9390 +Train: [44] [2900/6250] eta: 0:09:28 lr: 0.000079 grad: 0.0792 (0.0830) loss: 0.8281 (0.8258) time: 0.1458 data: 0.0449 max mem: 9390 +Train: [44] [3000/6250] eta: 0:09:10 lr: 0.000079 grad: 0.0778 (0.0829) loss: 0.8279 (0.8257) time: 0.1740 data: 0.0810 max mem: 9390 +Train: [44] [3100/6250] eta: 0:08:52 lr: 0.000079 grad: 0.0808 (0.0831) loss: 0.8276 (0.8257) time: 0.1667 data: 0.0758 max mem: 9390 +Train: [44] [3200/6250] eta: 0:08:34 lr: 0.000079 grad: 0.0791 (0.0831) loss: 0.8257 (0.8257) time: 0.1536 data: 0.0546 max mem: 9390 +Train: [44] [3300/6250] eta: 0:08:16 lr: 0.000079 grad: 0.0782 (0.0831) loss: 0.8279 (0.8257) time: 0.1489 data: 0.0531 max mem: 9390 +Train: [44] [3400/6250] eta: 0:07:59 lr: 0.000079 grad: 0.0825 (0.0832) loss: 0.8240 (0.8256) time: 0.1389 data: 0.0463 max mem: 9390 +Train: [44] [3500/6250] eta: 0:07:41 lr: 0.000079 grad: 0.0788 (0.0833) loss: 0.8237 (0.8256) time: 0.1384 data: 0.0558 max mem: 9390 +Train: [44] [3600/6250] eta: 0:07:23 lr: 0.000079 grad: 0.0797 (0.0833) loss: 0.8283 (0.8255) time: 0.1582 data: 0.0704 max mem: 9390 +Train: [44] [3700/6250] eta: 0:07:06 lr: 0.000079 grad: 0.0799 (0.0834) loss: 0.8208 (0.8254) time: 0.1686 data: 0.0785 max mem: 9390 +Train: [44] [3800/6250] eta: 0:06:49 lr: 0.000079 grad: 0.0823 (0.0834) loss: 0.8208 (0.8253) time: 0.1770 data: 0.0930 max mem: 9390 +Train: [44] [3900/6250] eta: 0:06:32 lr: 0.000079 grad: 0.0821 (0.0835) loss: 0.8239 (0.8252) time: 0.2097 data: 0.1217 max mem: 9390 +Train: [44] [4000/6250] eta: 0:06:15 lr: 0.000079 grad: 0.0799 (0.0835) loss: 0.8241 (0.8252) time: 0.1402 data: 0.0437 max mem: 9390 +Train: [44] [4100/6250] eta: 0:05:58 lr: 0.000079 grad: 0.0798 (0.0835) loss: 0.8209 (0.8251) time: 0.1755 data: 0.0916 max mem: 9390 +Train: [44] [4200/6250] eta: 0:05:41 lr: 0.000078 grad: 0.0847 (0.0835) loss: 0.8214 (0.8251) time: 0.1444 data: 0.0583 max mem: 9390 +Train: [44] [4300/6250] eta: 0:05:24 lr: 0.000078 grad: 0.0762 (0.0834) loss: 0.8292 (0.8251) time: 0.1611 data: 0.0741 max mem: 9390 +Train: [44] [4400/6250] eta: 0:05:07 lr: 0.000078 grad: 0.0813 (0.0834) loss: 0.8268 (0.8252) time: 0.1649 data: 0.0770 max mem: 9390 +Train: [44] [4500/6250] eta: 0:04:50 lr: 0.000078 grad: 0.0783 (0.0834) loss: 0.8218 (0.8252) time: 0.1670 data: 0.0856 max mem: 9390 +Train: [44] [4600/6250] eta: 0:04:33 lr: 0.000078 grad: 0.0788 (0.0834) loss: 0.8326 (0.8252) time: 0.1565 data: 0.0617 max mem: 9390 +Train: [44] [4700/6250] eta: 0:04:17 lr: 0.000078 grad: 0.0795 (0.0834) loss: 0.8246 (0.8252) time: 0.1705 data: 0.0866 max mem: 9390 +Train: [44] [4800/6250] eta: 0:04:00 lr: 0.000078 grad: 0.0770 (0.0834) loss: 0.8266 (0.8252) time: 0.1681 data: 0.0691 max mem: 9390 +Train: [44] [4900/6250] eta: 0:03:43 lr: 0.000078 grad: 0.0768 (0.0834) loss: 0.8245 (0.8252) time: 0.1602 data: 0.0723 max mem: 9390 +Train: [44] [5000/6250] eta: 0:03:26 lr: 0.000078 grad: 0.0809 (0.0834) loss: 0.8230 (0.8252) time: 0.1416 data: 0.0507 max mem: 9390 +Train: [44] [5100/6250] eta: 0:03:09 lr: 0.000078 grad: 0.0730 (0.0834) loss: 0.8277 (0.8253) time: 0.1663 data: 0.0806 max mem: 9390 +Train: [44] [5200/6250] eta: 0:02:53 lr: 0.000078 grad: 0.0813 (0.0834) loss: 0.8290 (0.8253) time: 0.1633 data: 0.0760 max mem: 9390 +Train: [44] [5300/6250] eta: 0:02:36 lr: 0.000078 grad: 0.0805 (0.0833) loss: 0.8297 (0.8253) time: 0.1708 data: 0.0702 max mem: 9390 +Train: [44] [5400/6250] eta: 0:02:20 lr: 0.000078 grad: 0.0772 (0.0832) loss: 0.8298 (0.8254) time: 0.1497 data: 0.0665 max mem: 9390 +Train: [44] [5500/6250] eta: 0:02:03 lr: 0.000078 grad: 0.0763 (0.0832) loss: 0.8279 (0.8254) time: 0.1727 data: 0.0766 max mem: 9390 +Train: [44] [5600/6250] eta: 0:01:47 lr: 0.000078 grad: 0.0796 (0.0831) loss: 0.8306 (0.8254) time: 0.1461 data: 0.0611 max mem: 9390 +Train: [44] [5700/6250] eta: 0:01:30 lr: 0.000078 grad: 0.0761 (0.0831) loss: 0.8298 (0.8255) time: 0.1521 data: 0.0599 max mem: 9390 +Train: [44] [5800/6250] eta: 0:01:13 lr: 0.000078 grad: 0.0787 (0.0831) loss: 0.8296 (0.8255) time: 0.1327 data: 0.0466 max mem: 9390 +Train: [44] [5900/6250] eta: 0:00:57 lr: 0.000078 grad: 0.0762 (0.0831) loss: 0.8246 (0.8256) time: 0.1797 data: 0.0889 max mem: 9390 +Train: [44] [6000/6250] eta: 0:00:41 lr: 0.000078 grad: 0.0821 (0.0831) loss: 0.8253 (0.8256) time: 0.1707 data: 0.0778 max mem: 9390 +Train: [44] [6100/6250] eta: 0:00:24 lr: 0.000078 grad: 0.0841 (0.0831) loss: 0.8217 (0.8255) time: 0.1546 data: 0.0593 max mem: 9390 +Train: [44] [6200/6250] eta: 0:00:08 lr: 0.000078 grad: 0.0839 (0.0831) loss: 0.8265 (0.8255) time: 0.1556 data: 0.0713 max mem: 9390 +Train: [44] [6249/6250] eta: 0:00:00 lr: 0.000078 grad: 0.0784 (0.0831) loss: 0.8254 (0.8255) time: 0.1485 data: 0.0660 max mem: 9390 +Train: [44] Total time: 0:17:09 (0.1648 s / it) +Averaged stats: lr: 0.000078 grad: 0.0784 (0.0831) loss: 0.8254 (0.8255) +Eval (hcp-train-subset): [44] [ 0/62] eta: 0:05:14 loss: 0.8483 (0.8483) time: 5.0745 data: 5.0427 max mem: 9390 +Eval (hcp-train-subset): [44] [61/62] eta: 0:00:00 loss: 0.8349 (0.8384) time: 0.1387 data: 0.1078 max mem: 9390 +Eval (hcp-train-subset): [44] Total time: 0:00:13 (0.2156 s / it) +Averaged stats (hcp-train-subset): loss: 0.8349 (0.8384) +Making plots (hcp-train-subset): example=45 +Eval (hcp-val): [44] [ 0/62] eta: 0:04:06 loss: 0.8351 (0.8351) time: 3.9745 data: 3.9032 max mem: 9390 +Eval (hcp-val): [44] [61/62] eta: 0:00:00 loss: 0.8346 (0.8370) time: 0.1604 data: 0.1348 max mem: 9390 +Eval (hcp-val): [44] Total time: 0:00:14 (0.2376 s / it) +Averaged stats (hcp-val): loss: 0.8346 (0.8370) +Making plots (hcp-val): example=17 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +Train: [45] [ 0/6250] eta: 11:30:15 lr: 0.000078 grad: 0.0627 (0.0627) loss: 0.8552 (0.8552) time: 6.6265 data: 6.5061 max mem: 9390 +Train: [45] [ 100/6250] eta: 0:23:37 lr: 0.000078 grad: 0.0879 (0.0975) loss: 0.8242 (0.8324) time: 0.1626 data: 0.0740 max mem: 9390 +Train: [45] [ 200/6250] eta: 0:22:23 lr: 0.000078 grad: 0.0867 (0.0959) loss: 0.8172 (0.8250) time: 0.2285 data: 0.1206 max mem: 9390 +Train: [45] [ 300/6250] eta: 0:21:09 lr: 0.000078 grad: 0.0787 (0.0926) loss: 0.8195 (0.8227) time: 0.2010 data: 0.0908 max mem: 9390 +Train: [45] [ 400/6250] eta: 0:20:47 lr: 0.000078 grad: 0.0797 (0.0917) loss: 0.8227 (0.8216) time: 0.2091 data: 0.1007 max mem: 9390 +Train: [45] [ 500/6250] eta: 0:20:05 lr: 0.000078 grad: 0.0875 (0.0904) loss: 0.8176 (0.8214) time: 0.1715 data: 0.0689 max mem: 9390 +Train: [45] [ 600/6250] eta: 0:19:13 lr: 0.000078 grad: 0.0823 (0.0898) loss: 0.8205 (0.8213) time: 0.1707 data: 0.0791 max mem: 9390 +Train: [45] [ 700/6250] eta: 0:18:30 lr: 0.000078 grad: 0.0785 (0.0889) loss: 0.8214 (0.8213) time: 0.1635 data: 0.0718 max mem: 9390 +Train: [45] [ 800/6250] eta: 0:17:55 lr: 0.000078 grad: 0.0807 (0.0882) loss: 0.8246 (0.8215) time: 0.1834 data: 0.0911 max mem: 9390 +Train: [45] [ 900/6250] eta: 0:17:19 lr: 0.000078 grad: 0.0821 (0.0877) loss: 0.8244 (0.8216) time: 0.1729 data: 0.0716 max mem: 9390 +Train: [45] [1000/6250] eta: 0:16:46 lr: 0.000078 grad: 0.0810 (0.0874) loss: 0.8274 (0.8218) time: 0.1594 data: 0.0722 max mem: 9390 +Train: [45] [1100/6250] eta: 0:16:12 lr: 0.000077 grad: 0.0761 (0.0869) loss: 0.8241 (0.8220) time: 0.1672 data: 0.0818 max mem: 9390 +Train: [45] [1200/6250] eta: 0:15:41 lr: 0.000077 grad: 0.0778 (0.0866) loss: 0.8303 (0.8221) time: 0.1683 data: 0.0844 max mem: 9390 +Train: [45] [1300/6250] eta: 0:15:11 lr: 0.000077 grad: 0.0828 (0.0863) loss: 0.8295 (0.8223) time: 0.1624 data: 0.0760 max mem: 9390 +Train: [45] [1400/6250] eta: 0:14:45 lr: 0.000077 grad: 0.0844 (0.0859) loss: 0.8220 (0.8224) time: 0.1952 data: 0.1094 max mem: 9390 +Train: [45] [1500/6250] eta: 0:14:18 lr: 0.000077 grad: 0.0830 (0.0857) loss: 0.8181 (0.8224) time: 0.1712 data: 0.0806 max mem: 9390 +Train: [45] [1600/6250] eta: 0:13:55 lr: 0.000077 grad: 0.0869 (0.0855) loss: 0.8195 (0.8224) time: 0.1627 data: 0.0844 max mem: 9390 +Train: [45] [1700/6250] eta: 0:13:33 lr: 0.000077 grad: 0.0825 (0.0853) loss: 0.8230 (0.8225) time: 0.1813 data: 0.0915 max mem: 9390 +Train: [45] [1800/6250] eta: 0:13:10 lr: 0.000077 grad: 0.0782 (0.0851) loss: 0.8264 (0.8226) time: 0.1705 data: 0.0839 max mem: 9390 +Train: [45] [1900/6250] eta: 0:12:47 lr: 0.000077 grad: 0.0793 (0.0850) loss: 0.8210 (0.8227) time: 0.1490 data: 0.0576 max mem: 9390 +Train: [45] [2000/6250] eta: 0:12:27 lr: 0.000077 grad: 0.0791 (0.0850) loss: 0.8256 (0.8228) time: 0.1670 data: 0.0775 max mem: 9390 +Train: [45] [2100/6250] eta: 0:12:05 lr: 0.000077 grad: 0.0771 (0.0849) loss: 0.8239 (0.8229) time: 0.1550 data: 0.0692 max mem: 9390 +Train: [45] [2200/6250] eta: 0:11:46 lr: 0.000077 grad: 0.0872 (0.0848) loss: 0.8225 (0.8229) time: 0.1695 data: 0.0784 max mem: 9390 +Train: [45] [2300/6250] eta: 0:11:26 lr: 0.000077 grad: 0.0844 (0.0848) loss: 0.8213 (0.8229) time: 0.1525 data: 0.0663 max mem: 9390 +Train: [45] [2400/6250] eta: 0:11:07 lr: 0.000077 grad: 0.0804 (0.0847) loss: 0.8240 (0.8229) time: 0.1502 data: 0.0553 max mem: 9390 +Train: [45] [2500/6250] eta: 0:10:47 lr: 0.000077 grad: 0.0807 (0.0848) loss: 0.8267 (0.8229) time: 0.1700 data: 0.0889 max mem: 9390 +Train: [45] [2600/6250] eta: 0:10:28 lr: 0.000077 grad: 0.0842 (0.0847) loss: 0.8224 (0.8229) time: 0.1605 data: 0.0712 max mem: 9390 +Train: [45] [2700/6250] eta: 0:10:09 lr: 0.000077 grad: 0.0804 (0.0846) loss: 0.8223 (0.8229) time: 0.1630 data: 0.0808 max mem: 9390 +Train: [45] [2800/6250] eta: 0:09:51 lr: 0.000077 grad: 0.0795 (0.0846) loss: 0.8251 (0.8229) time: 0.1674 data: 0.0857 max mem: 9390 +Train: [45] [2900/6250] eta: 0:09:32 lr: 0.000077 grad: 0.0805 (0.0845) loss: 0.8253 (0.8229) time: 0.1525 data: 0.0616 max mem: 9390 +Train: [45] [3000/6250] eta: 0:09:14 lr: 0.000077 grad: 0.0762 (0.0845) loss: 0.8294 (0.8229) time: 0.1584 data: 0.0657 max mem: 9390 +Train: [45] [3100/6250] eta: 0:08:56 lr: 0.000077 grad: 0.0785 (0.0845) loss: 0.8277 (0.8229) time: 0.1778 data: 0.0874 max mem: 9390 +Train: [45] [3200/6250] eta: 0:08:38 lr: 0.000077 grad: 0.0809 (0.0845) loss: 0.8262 (0.8231) time: 0.1598 data: 0.0658 max mem: 9390 +Train: [45] [3300/6250] eta: 0:08:19 lr: 0.000077 grad: 0.0748 (0.0844) loss: 0.8319 (0.8232) time: 0.1510 data: 0.0589 max mem: 9390 +Train: [45] [3400/6250] eta: 0:08:02 lr: 0.000077 grad: 0.0832 (0.0844) loss: 0.8268 (0.8232) time: 0.1333 data: 0.0424 max mem: 9390 +Train: [45] [3500/6250] eta: 0:07:44 lr: 0.000077 grad: 0.0827 (0.0844) loss: 0.8220 (0.8234) time: 0.1782 data: 0.0860 max mem: 9390 +Train: [45] [3600/6250] eta: 0:07:26 lr: 0.000077 grad: 0.0794 (0.0843) loss: 0.8265 (0.8234) time: 0.1640 data: 0.0707 max mem: 9390 +Train: [45] [3700/6250] eta: 0:07:09 lr: 0.000077 grad: 0.0824 (0.0843) loss: 0.8258 (0.8235) time: 0.1699 data: 0.0891 max mem: 9390 +Train: [45] [3800/6250] eta: 0:06:51 lr: 0.000077 grad: 0.0873 (0.0843) loss: 0.8173 (0.8235) time: 0.1587 data: 0.0600 max mem: 9390 +Train: [45] [3900/6250] eta: 0:06:34 lr: 0.000077 grad: 0.0788 (0.0843) loss: 0.8302 (0.8235) time: 0.1572 data: 0.0685 max mem: 9390 +Train: [45] [4000/6250] eta: 0:06:16 lr: 0.000077 grad: 0.0830 (0.0842) loss: 0.8294 (0.8236) time: 0.1572 data: 0.0716 max mem: 9390 +Train: [45] [4100/6250] eta: 0:05:59 lr: 0.000077 grad: 0.0781 (0.0842) loss: 0.8278 (0.8238) time: 0.1700 data: 0.0808 max mem: 9390 +Train: [45] [4200/6250] eta: 0:05:42 lr: 0.000076 grad: 0.0820 (0.0842) loss: 0.8227 (0.8239) time: 0.1640 data: 0.0704 max mem: 9390 +Train: [45] [4300/6250] eta: 0:05:25 lr: 0.000076 grad: 0.0754 (0.0842) loss: 0.8282 (0.8240) time: 0.1661 data: 0.0802 max mem: 9390 +Train: [45] [4400/6250] eta: 0:05:09 lr: 0.000076 grad: 0.0825 (0.0842) loss: 0.8244 (0.8240) time: 0.1743 data: 0.0955 max mem: 9390 +Train: [45] [4500/6250] eta: 0:04:52 lr: 0.000076 grad: 0.0838 (0.0843) loss: 0.8285 (0.8241) time: 0.1922 data: 0.1108 max mem: 9390 +Train: [45] [4600/6250] eta: 0:04:35 lr: 0.000076 grad: 0.0816 (0.0842) loss: 0.8303 (0.8242) time: 0.1637 data: 0.0719 max mem: 9390 +Train: [45] [4700/6250] eta: 0:04:19 lr: 0.000076 grad: 0.0861 (0.0842) loss: 0.8274 (0.8243) time: 0.1645 data: 0.0755 max mem: 9390 +Train: [45] [4800/6250] eta: 0:04:02 lr: 0.000076 grad: 0.0788 (0.0841) loss: 0.8291 (0.8244) time: 0.1746 data: 0.0818 max mem: 9390 +Train: [45] [4900/6250] eta: 0:03:45 lr: 0.000076 grad: 0.0774 (0.0841) loss: 0.8247 (0.8245) time: 0.1386 data: 0.0424 max mem: 9390 +Train: [45] [5000/6250] eta: 0:03:28 lr: 0.000076 grad: 0.0843 (0.0841) loss: 0.8267 (0.8245) time: 0.1348 data: 0.0503 max mem: 9390 +Train: [45] [5100/6250] eta: 0:03:12 lr: 0.000076 grad: 0.0797 (0.0841) loss: 0.8291 (0.8245) time: 0.1707 data: 0.0775 max mem: 9390 +Train: [45] [5200/6250] eta: 0:02:55 lr: 0.000076 grad: 0.0860 (0.0841) loss: 0.8226 (0.8245) time: 0.1814 data: 0.0870 max mem: 9390 +Train: [45] [5300/6250] eta: 0:02:38 lr: 0.000076 grad: 0.0844 (0.0841) loss: 0.8225 (0.8245) time: 0.1732 data: 0.0776 max mem: 9390 +Train: [45] [5400/6250] eta: 0:02:21 lr: 0.000076 grad: 0.0833 (0.0841) loss: 0.8245 (0.8245) time: 0.1979 data: 0.1067 max mem: 9390 +Train: [45] [5500/6250] eta: 0:02:05 lr: 0.000076 grad: 0.0812 (0.0841) loss: 0.8234 (0.8245) time: 0.1686 data: 0.0675 max mem: 9390 +Train: [45] [5600/6250] eta: 0:01:48 lr: 0.000076 grad: 0.0789 (0.0840) loss: 0.8262 (0.8245) time: 0.1544 data: 0.0489 max mem: 9390 +Train: [45] [5700/6250] eta: 0:01:31 lr: 0.000076 grad: 0.0809 (0.0841) loss: 0.8277 (0.8245) time: 0.1321 data: 0.0343 max mem: 9390 +Train: [45] [5800/6250] eta: 0:01:14 lr: 0.000076 grad: 0.0862 (0.0841) loss: 0.8271 (0.8245) time: 0.1535 data: 0.0501 max mem: 9390 +Train: [45] [5900/6250] eta: 0:00:58 lr: 0.000076 grad: 0.0827 (0.0842) loss: 0.8345 (0.8245) time: 0.1679 data: 0.0713 max mem: 9390 +Train: [45] [6000/6250] eta: 0:00:41 lr: 0.000076 grad: 0.0793 (0.0842) loss: 0.8250 (0.8245) time: 0.1735 data: 0.0843 max mem: 9390 +Train: [45] [6100/6250] eta: 0:00:24 lr: 0.000076 grad: 0.0838 (0.0842) loss: 0.8249 (0.8245) time: 0.1775 data: 0.0845 max mem: 9390 +Train: [45] [6200/6250] eta: 0:00:08 lr: 0.000076 grad: 0.0821 (0.0842) loss: 0.8246 (0.8245) time: 0.1697 data: 0.0735 max mem: 9390 +Train: [45] [6249/6250] eta: 0:00:00 lr: 0.000076 grad: 0.0810 (0.0842) loss: 0.8237 (0.8245) time: 0.1643 data: 0.0669 max mem: 9390 +Train: [45] Total time: 0:17:23 (0.1670 s / it) +Averaged stats: lr: 0.000076 grad: 0.0810 (0.0842) loss: 0.8237 (0.8245) +Eval (hcp-train-subset): [45] [ 0/62] eta: 0:04:57 loss: 0.8503 (0.8503) time: 4.7909 data: 4.7592 max mem: 9390 +Eval (hcp-train-subset): [45] [61/62] eta: 0:00:00 loss: 0.8368 (0.8387) time: 0.2736 data: 0.2489 max mem: 9390 +Eval (hcp-train-subset): [45] Total time: 0:00:18 (0.2928 s / it) +Averaged stats (hcp-train-subset): loss: 0.8368 (0.8387) +Eval (hcp-val): [45] [ 0/62] eta: 0:04:18 loss: 0.8346 (0.8346) time: 4.1687 data: 4.0593 max mem: 9390 +Eval (hcp-val): [45] [61/62] eta: 0:00:00 loss: 0.8343 (0.8361) time: 0.1186 data: 0.0938 max mem: 9390 +Eval (hcp-val): [45] Total time: 0:00:14 (0.2267 s / it) +Averaged stats (hcp-val): loss: 0.8343 (0.8361) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +Train: [46] [ 0/6250] eta: 6:56:45 lr: 0.000076 grad: 0.0746 (0.0746) loss: 0.8373 (0.8373) time: 4.0008 data: 3.8189 max mem: 9390 +Train: [46] [ 100/6250] eta: 0:22:56 lr: 0.000076 grad: 0.0748 (0.0914) loss: 0.8339 (0.8306) time: 0.1606 data: 0.0666 max mem: 9390 +Train: [46] [ 200/6250] eta: 0:21:00 lr: 0.000076 grad: 0.0828 (0.0870) loss: 0.8253 (0.8297) time: 0.1661 data: 0.0564 max mem: 9390 +Train: [46] [ 300/6250] eta: 0:19:50 lr: 0.000076 grad: 0.0805 (0.0851) loss: 0.8241 (0.8284) time: 0.1750 data: 0.0752 max mem: 9390 +Train: [46] [ 400/6250] eta: 0:19:16 lr: 0.000076 grad: 0.0815 (0.0843) loss: 0.8268 (0.8275) time: 0.2047 data: 0.0977 max mem: 9390 +Train: [46] [ 500/6250] eta: 0:18:50 lr: 0.000076 grad: 0.0797 (0.0845) loss: 0.8174 (0.8260) time: 0.1718 data: 0.0531 max mem: 9390 +Train: [46] [ 600/6250] eta: 0:18:12 lr: 0.000076 grad: 0.0834 (0.0847) loss: 0.8181 (0.8246) time: 0.1546 data: 0.0534 max mem: 9390 +Train: [46] [ 700/6250] eta: 0:17:38 lr: 0.000076 grad: 0.0853 (0.0850) loss: 0.8174 (0.8239) time: 0.1695 data: 0.0698 max mem: 9390 +Train: [46] [ 800/6250] eta: 0:17:02 lr: 0.000076 grad: 0.0800 (0.0847) loss: 0.8168 (0.8236) time: 0.1841 data: 0.0930 max mem: 9390 +Train: [46] [ 900/6250] eta: 0:16:32 lr: 0.000076 grad: 0.0804 (0.0843) loss: 0.8233 (0.8236) time: 0.1548 data: 0.0544 max mem: 9390 +Train: [46] [1000/6250] eta: 0:16:03 lr: 0.000076 grad: 0.0847 (0.0844) loss: 0.8191 (0.8231) time: 0.1637 data: 0.0684 max mem: 9390 +Train: [46] [1100/6250] eta: 0:15:30 lr: 0.000075 grad: 0.0845 (0.0846) loss: 0.8163 (0.8226) time: 0.1449 data: 0.0476 max mem: 9390 +Train: [46] [1200/6250] eta: 0:15:04 lr: 0.000075 grad: 0.0887 (0.0849) loss: 0.8199 (0.8222) time: 0.1664 data: 0.0765 max mem: 9390 +Train: [46] [1300/6250] eta: 0:14:39 lr: 0.000075 grad: 0.0771 (0.0848) loss: 0.8193 (0.8218) time: 0.1539 data: 0.0608 max mem: 9390 +Train: [46] [1400/6250] eta: 0:14:16 lr: 0.000075 grad: 0.0879 (0.0852) loss: 0.8147 (0.8214) time: 0.1645 data: 0.0750 max mem: 9390 +Train: [46] [1500/6250] eta: 0:13:52 lr: 0.000075 grad: 0.0863 (0.0853) loss: 0.8155 (0.8210) time: 0.1511 data: 0.0609 max mem: 9390 +Train: [46] [1600/6250] eta: 0:13:30 lr: 0.000075 grad: 0.0866 (0.0853) loss: 0.8214 (0.8208) time: 0.1356 data: 0.0479 max mem: 9390 +Train: [46] [1700/6250] eta: 0:13:08 lr: 0.000075 grad: 0.0796 (0.0853) loss: 0.8158 (0.8206) time: 0.1257 data: 0.0328 max mem: 9390 +Train: [46] [1800/6250] eta: 0:12:48 lr: 0.000075 grad: 0.0858 (0.0854) loss: 0.8181 (0.8205) time: 0.1666 data: 0.0826 max mem: 9390 +Train: [46] [1900/6250] eta: 0:12:28 lr: 0.000075 grad: 0.0790 (0.0856) loss: 0.8198 (0.8203) time: 0.1527 data: 0.0576 max mem: 9390 +Train: [46] [2000/6250] eta: 0:12:08 lr: 0.000075 grad: 0.0822 (0.0856) loss: 0.8204 (0.8201) time: 0.1437 data: 0.0500 max mem: 9390 +Train: [46] [2100/6250] eta: 0:11:49 lr: 0.000075 grad: 0.0832 (0.0858) loss: 0.8189 (0.8199) time: 0.1704 data: 0.0809 max mem: 9390 +Train: [46] [2200/6250] eta: 0:11:29 lr: 0.000075 grad: 0.0846 (0.0859) loss: 0.8174 (0.8197) time: 0.1716 data: 0.0806 max mem: 9390 +Train: [46] [2300/6250] eta: 0:11:10 lr: 0.000075 grad: 0.0870 (0.0859) loss: 0.8152 (0.8196) time: 0.1497 data: 0.0605 max mem: 9390 +Train: [46] [2400/6250] eta: 0:10:52 lr: 0.000075 grad: 0.0814 (0.0859) loss: 0.8197 (0.8195) time: 0.1572 data: 0.0723 max mem: 9390 +Train: [46] [2500/6250] eta: 0:10:34 lr: 0.000075 grad: 0.0838 (0.0860) loss: 0.8169 (0.8194) time: 0.1577 data: 0.0724 max mem: 9390 +Train: [46] [2600/6250] eta: 0:10:15 lr: 0.000075 grad: 0.0837 (0.0861) loss: 0.8167 (0.8193) time: 0.1472 data: 0.0600 max mem: 9390 +Train: [46] [2700/6250] eta: 0:09:58 lr: 0.000075 grad: 0.0860 (0.0862) loss: 0.8181 (0.8192) time: 0.1872 data: 0.0898 max mem: 9390 +Train: [46] [2800/6250] eta: 0:09:38 lr: 0.000075 grad: 0.0903 (0.0863) loss: 0.8221 (0.8193) time: 0.1442 data: 0.0541 max mem: 9390 +Train: [46] [2900/6250] eta: 0:09:21 lr: 0.000075 grad: 0.0835 (0.0864) loss: 0.8277 (0.8192) time: 0.1694 data: 0.0810 max mem: 9390 +Train: [46] [3000/6250] eta: 0:09:04 lr: 0.000075 grad: 0.0883 (0.0864) loss: 0.8124 (0.8191) time: 0.1529 data: 0.0650 max mem: 9390 +Train: [46] [3100/6250] eta: 0:08:47 lr: 0.000075 grad: 0.0873 (0.0864) loss: 0.8179 (0.8191) time: 0.1474 data: 0.0500 max mem: 9390 +Train: [46] [3200/6250] eta: 0:08:29 lr: 0.000075 grad: 0.0856 (0.0865) loss: 0.8156 (0.8190) time: 0.1495 data: 0.0555 max mem: 9390 +Train: [46] [3300/6250] eta: 0:08:12 lr: 0.000075 grad: 0.0861 (0.0865) loss: 0.8181 (0.8190) time: 0.1399 data: 0.0490 max mem: 9390 +Train: [46] [3400/6250] eta: 0:07:55 lr: 0.000075 grad: 0.0827 (0.0866) loss: 0.8170 (0.8189) time: 0.1677 data: 0.0728 max mem: 9390 +Train: [46] [3500/6250] eta: 0:07:38 lr: 0.000075 grad: 0.0804 (0.0866) loss: 0.8208 (0.8189) time: 0.1683 data: 0.0842 max mem: 9390 +Train: [46] [3600/6250] eta: 0:07:21 lr: 0.000075 grad: 0.0909 (0.0868) loss: 0.8240 (0.8189) time: 0.1456 data: 0.0539 max mem: 9390 +Train: [46] [3700/6250] eta: 0:07:03 lr: 0.000075 grad: 0.0836 (0.0868) loss: 0.8128 (0.8189) time: 0.1576 data: 0.0729 max mem: 9390 +Train: [46] [3800/6250] eta: 0:06:46 lr: 0.000075 grad: 0.0852 (0.0868) loss: 0.8181 (0.8189) time: 0.1679 data: 0.0787 max mem: 9390 +Train: [46] [3900/6250] eta: 0:06:29 lr: 0.000075 grad: 0.0848 (0.0868) loss: 0.8205 (0.8190) time: 0.1649 data: 0.0685 max mem: 9390 +Train: [46] [4000/6250] eta: 0:06:12 lr: 0.000075 grad: 0.0891 (0.0868) loss: 0.8155 (0.8190) time: 0.2009 data: 0.1112 max mem: 9390 +Train: [46] [4100/6250] eta: 0:05:55 lr: 0.000075 grad: 0.0853 (0.0868) loss: 0.8170 (0.8190) time: 0.1410 data: 0.0502 max mem: 9390 +Train: [46] [4200/6250] eta: 0:05:38 lr: 0.000074 grad: 0.0810 (0.0867) loss: 0.8218 (0.8191) time: 0.1544 data: 0.0696 max mem: 9390 +Train: [46] [4300/6250] eta: 0:05:22 lr: 0.000074 grad: 0.0811 (0.0866) loss: 0.8256 (0.8192) time: 0.1827 data: 0.0942 max mem: 9390 +Train: [46] [4400/6250] eta: 0:05:05 lr: 0.000074 grad: 0.0852 (0.0866) loss: 0.8216 (0.8193) time: 0.1802 data: 0.0887 max mem: 9390 +Train: [46] [4500/6250] eta: 0:04:49 lr: 0.000074 grad: 0.0888 (0.0866) loss: 0.8240 (0.8193) time: 0.1649 data: 0.0776 max mem: 9390 +Train: [46] [4600/6250] eta: 0:04:32 lr: 0.000074 grad: 0.0843 (0.0866) loss: 0.8227 (0.8194) time: 0.1808 data: 0.0967 max mem: 9390 +Train: [46] [4700/6250] eta: 0:04:15 lr: 0.000074 grad: 0.0779 (0.0865) loss: 0.8229 (0.8195) time: 0.1570 data: 0.0742 max mem: 9390 +Train: [46] [4800/6250] eta: 0:03:59 lr: 0.000074 grad: 0.0847 (0.0864) loss: 0.8240 (0.8196) time: 0.1831 data: 0.0894 max mem: 9390 +Train: [46] [4900/6250] eta: 0:03:42 lr: 0.000074 grad: 0.0763 (0.0864) loss: 0.8193 (0.8196) time: 0.1588 data: 0.0719 max mem: 9390 +Train: [46] [5000/6250] eta: 0:03:26 lr: 0.000074 grad: 0.0856 (0.0864) loss: 0.8203 (0.8196) time: 0.1574 data: 0.0666 max mem: 9390 +Train: [46] [5100/6250] eta: 0:03:09 lr: 0.000074 grad: 0.0886 (0.0863) loss: 0.8193 (0.8197) time: 0.1673 data: 0.0803 max mem: 9390 +Train: [46] [5200/6250] eta: 0:02:52 lr: 0.000074 grad: 0.0847 (0.0864) loss: 0.8218 (0.8197) time: 0.1604 data: 0.0757 max mem: 9390 +Train: [46] [5300/6250] eta: 0:02:36 lr: 0.000074 grad: 0.0820 (0.0864) loss: 0.8212 (0.8197) time: 0.1466 data: 0.0593 max mem: 9390 +Train: [46] [5400/6250] eta: 0:02:20 lr: 0.000074 grad: 0.0844 (0.0864) loss: 0.8164 (0.8197) time: 0.1695 data: 0.0805 max mem: 9390 +Train: [46] [5500/6250] eta: 0:02:03 lr: 0.000074 grad: 0.0916 (0.0865) loss: 0.8073 (0.8196) time: 0.1638 data: 0.0827 max mem: 9390 +Train: [46] [5600/6250] eta: 0:01:47 lr: 0.000074 grad: 0.0888 (0.0865) loss: 0.8150 (0.8196) time: 0.1687 data: 0.0798 max mem: 9390 +Train: [46] [5700/6250] eta: 0:01:30 lr: 0.000074 grad: 0.0853 (0.0866) loss: 0.8178 (0.8195) time: 0.1623 data: 0.0737 max mem: 9390 +Train: [46] [5800/6250] eta: 0:01:14 lr: 0.000074 grad: 0.0863 (0.0866) loss: 0.8225 (0.8195) time: 0.1604 data: 0.0566 max mem: 9390 +Train: [46] [5900/6250] eta: 0:00:57 lr: 0.000074 grad: 0.0854 (0.0866) loss: 0.8201 (0.8195) time: 0.1688 data: 0.0780 max mem: 9390 +Train: [46] [6000/6250] eta: 0:00:41 lr: 0.000074 grad: 0.0869 (0.0866) loss: 0.8141 (0.8195) time: 0.1614 data: 0.0761 max mem: 9390 +Train: [46] [6100/6250] eta: 0:00:24 lr: 0.000074 grad: 0.0843 (0.0867) loss: 0.8226 (0.8195) time: 0.1660 data: 0.0749 max mem: 9390 +Train: [46] [6200/6250] eta: 0:00:08 lr: 0.000074 grad: 0.0802 (0.0867) loss: 0.8220 (0.8195) time: 0.1699 data: 0.0870 max mem: 9390 +Train: [46] [6249/6250] eta: 0:00:00 lr: 0.000074 grad: 0.0871 (0.0867) loss: 0.8212 (0.8195) time: 0.1351 data: 0.0463 max mem: 9390 +Train: [46] Total time: 0:17:14 (0.1656 s / it) +Averaged stats: lr: 0.000074 grad: 0.0871 (0.0867) loss: 0.8212 (0.8195) +Eval (hcp-train-subset): [46] [ 0/62] eta: 0:05:20 loss: 0.8521 (0.8521) time: 5.1659 data: 5.1334 max mem: 9390 +Eval (hcp-train-subset): [46] [61/62] eta: 0:00:00 loss: 0.8400 (0.8398) time: 0.1601 data: 0.1343 max mem: 9390 +Eval (hcp-train-subset): [46] Total time: 0:00:14 (0.2286 s / it) +Averaged stats (hcp-train-subset): loss: 0.8400 (0.8398) +Eval (hcp-val): [46] [ 0/62] eta: 0:03:35 loss: 0.8362 (0.8362) time: 3.4794 data: 3.3987 max mem: 9390 +Eval (hcp-val): [46] [61/62] eta: 0:00:00 loss: 0.8358 (0.8368) time: 0.1275 data: 0.1002 max mem: 9390 +Eval (hcp-val): [46] Total time: 0:00:14 (0.2319 s / it) +Averaged stats (hcp-val): loss: 0.8358 (0.8368) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +Train: [47] [ 0/6250] eta: 11:00:13 lr: 0.000074 grad: 0.1739 (0.1739) loss: 0.7861 (0.7861) time: 6.3381 data: 6.2289 max mem: 9390 +Train: [47] [ 100/6250] eta: 0:21:25 lr: 0.000074 grad: 0.0884 (0.0923) loss: 0.8368 (0.8327) time: 0.1673 data: 0.0818 max mem: 9390 +Train: [47] [ 200/6250] eta: 0:19:59 lr: 0.000074 grad: 0.0845 (0.0911) loss: 0.8271 (0.8289) time: 0.1789 data: 0.0786 max mem: 9390 +Train: [47] [ 300/6250] eta: 0:19:15 lr: 0.000074 grad: 0.0831 (0.0888) loss: 0.8284 (0.8275) time: 0.1969 data: 0.0993 max mem: 9390 +Train: [47] [ 400/6250] eta: 0:18:24 lr: 0.000074 grad: 0.0795 (0.0875) loss: 0.8263 (0.8270) time: 0.1605 data: 0.0545 max mem: 9390 +Train: [47] [ 500/6250] eta: 0:18:02 lr: 0.000074 grad: 0.0764 (0.0858) loss: 0.8285 (0.8277) time: 0.1979 data: 0.0922 max mem: 9390 +Train: [47] [ 600/6250] eta: 0:17:33 lr: 0.000074 grad: 0.0693 (0.0840) loss: 0.8339 (0.8282) time: 0.1766 data: 0.0651 max mem: 9390 +Train: [47] [ 700/6250] eta: 0:17:02 lr: 0.000074 grad: 0.0762 (0.0826) loss: 0.8329 (0.8287) time: 0.1701 data: 0.0724 max mem: 9390 +Train: [47] [ 800/6250] eta: 0:16:34 lr: 0.000074 grad: 0.0765 (0.0817) loss: 0.8251 (0.8293) time: 0.1633 data: 0.0680 max mem: 9390 +Train: [47] [ 900/6250] eta: 0:16:09 lr: 0.000074 grad: 0.0762 (0.0812) loss: 0.8288 (0.8295) time: 0.1506 data: 0.0419 max mem: 9390 +Train: [47] [1000/6250] eta: 0:15:45 lr: 0.000073 grad: 0.0760 (0.0807) loss: 0.8293 (0.8297) time: 0.1762 data: 0.0797 max mem: 9390 +Train: [47] [1100/6250] eta: 0:15:16 lr: 0.000073 grad: 0.0755 (0.0804) loss: 0.8290 (0.8297) time: 0.1374 data: 0.0432 max mem: 9390 +Train: [47] [1200/6250] eta: 0:14:50 lr: 0.000073 grad: 0.0773 (0.0803) loss: 0.8282 (0.8296) time: 0.1753 data: 0.0915 max mem: 9390 +Train: [47] [1300/6250] eta: 0:14:24 lr: 0.000073 grad: 0.0733 (0.0801) loss: 0.8332 (0.8296) time: 0.1528 data: 0.0643 max mem: 9390 +Train: [47] [1400/6250] eta: 0:14:00 lr: 0.000073 grad: 0.0774 (0.0802) loss: 0.8308 (0.8296) time: 0.1464 data: 0.0624 max mem: 9390 +Train: [47] [1500/6250] eta: 0:13:39 lr: 0.000073 grad: 0.0756 (0.0801) loss: 0.8305 (0.8295) time: 0.1706 data: 0.0824 max mem: 9390 +Train: [47] [1600/6250] eta: 0:13:17 lr: 0.000073 grad: 0.0817 (0.0802) loss: 0.8276 (0.8294) time: 0.1554 data: 0.0658 max mem: 9390 +Train: [47] [1700/6250] eta: 0:12:57 lr: 0.000073 grad: 0.0819 (0.0801) loss: 0.8283 (0.8293) time: 0.1601 data: 0.0733 max mem: 9390 +Train: [47] [1800/6250] eta: 0:12:39 lr: 0.000073 grad: 0.0769 (0.0801) loss: 0.8305 (0.8292) time: 0.1625 data: 0.0570 max mem: 9390 +Train: [47] [1900/6250] eta: 0:12:21 lr: 0.000073 grad: 0.0798 (0.0802) loss: 0.8275 (0.8290) time: 0.1757 data: 0.0902 max mem: 9390 +Train: [47] [2000/6250] eta: 0:12:01 lr: 0.000073 grad: 0.0801 (0.0804) loss: 0.8267 (0.8289) time: 0.1791 data: 0.0992 max mem: 9390 +Train: [47] [2100/6250] eta: 0:11:45 lr: 0.000073 grad: 0.0791 (0.0805) loss: 0.8250 (0.8287) time: 0.1823 data: 0.0969 max mem: 9390 +Train: [47] [2200/6250] eta: 0:11:27 lr: 0.000073 grad: 0.0826 (0.0806) loss: 0.8292 (0.8286) time: 0.1789 data: 0.0997 max mem: 9390 +Train: [47] [2300/6250] eta: 0:11:10 lr: 0.000073 grad: 0.0835 (0.0808) loss: 0.8201 (0.8284) time: 0.1812 data: 0.0969 max mem: 9390 +Train: [47] [2400/6250] eta: 0:10:52 lr: 0.000073 grad: 0.0830 (0.0809) loss: 0.8194 (0.8282) time: 0.1685 data: 0.0901 max mem: 9390 +Train: [47] [2500/6250] eta: 0:10:34 lr: 0.000073 grad: 0.0822 (0.0810) loss: 0.8262 (0.8281) time: 0.1471 data: 0.0584 max mem: 9390 +Train: [47] [2600/6250] eta: 0:10:15 lr: 0.000073 grad: 0.0825 (0.0812) loss: 0.8286 (0.8279) time: 0.1358 data: 0.0429 max mem: 9390 +Train: [47] [2700/6250] eta: 0:09:56 lr: 0.000073 grad: 0.0892 (0.0815) loss: 0.8229 (0.8277) time: 0.1552 data: 0.0695 max mem: 9390 +Train: [47] [2800/6250] eta: 0:09:39 lr: 0.000073 grad: 0.0792 (0.0815) loss: 0.8269 (0.8276) time: 0.1502 data: 0.0613 max mem: 9390 +Train: [47] [2900/6250] eta: 0:09:22 lr: 0.000073 grad: 0.0793 (0.0816) loss: 0.8205 (0.8274) time: 0.1687 data: 0.0893 max mem: 9390 +Train: [47] [3000/6250] eta: 0:09:04 lr: 0.000073 grad: 0.0822 (0.0817) loss: 0.8190 (0.8273) time: 0.1554 data: 0.0641 max mem: 9390 +Train: [47] [3100/6250] eta: 0:08:46 lr: 0.000073 grad: 0.0839 (0.0819) loss: 0.8192 (0.8271) time: 0.1464 data: 0.0514 max mem: 9390 +Train: [47] [3200/6250] eta: 0:08:28 lr: 0.000073 grad: 0.0819 (0.0820) loss: 0.8268 (0.8271) time: 0.1648 data: 0.0771 max mem: 9390 +Train: [47] [3300/6250] eta: 0:08:11 lr: 0.000073 grad: 0.0878 (0.0822) loss: 0.8183 (0.8269) time: 0.1678 data: 0.0760 max mem: 9390 +Train: [47] [3400/6250] eta: 0:07:54 lr: 0.000073 grad: 0.0838 (0.0823) loss: 0.8236 (0.8268) time: 0.1463 data: 0.0486 max mem: 9390 +Train: [47] [3500/6250] eta: 0:07:37 lr: 0.000073 grad: 0.0819 (0.0824) loss: 0.8234 (0.8267) time: 0.1656 data: 0.0698 max mem: 9390 +Train: [47] [3600/6250] eta: 0:07:20 lr: 0.000073 grad: 0.0884 (0.0825) loss: 0.8231 (0.8265) time: 0.1651 data: 0.0815 max mem: 9390 +Train: [47] [3700/6250] eta: 0:07:02 lr: 0.000073 grad: 0.0826 (0.0827) loss: 0.8271 (0.8265) time: 0.1597 data: 0.0610 max mem: 9390 +Train: [47] [3800/6250] eta: 0:06:48 lr: 0.000073 grad: 0.0864 (0.0828) loss: 0.8174 (0.8264) time: 0.2059 data: 0.1098 max mem: 9390 +Train: [47] [3900/6250] eta: 0:06:32 lr: 0.000073 grad: 0.0855 (0.0829) loss: 0.8235 (0.8263) time: 0.1811 data: 0.0923 max mem: 9390 +Train: [47] [4000/6250] eta: 0:06:18 lr: 0.000073 grad: 0.0854 (0.0830) loss: 0.8154 (0.8262) time: 0.2216 data: 0.1345 max mem: 9390 +Train: [47] [4100/6250] eta: 0:06:02 lr: 0.000072 grad: 0.0807 (0.0832) loss: 0.8235 (0.8262) time: 0.1935 data: 0.0977 max mem: 9390 +Train: [47] [4200/6250] eta: 0:05:47 lr: 0.000072 grad: 0.0823 (0.0834) loss: 0.8276 (0.8261) time: 0.1929 data: 0.1020 max mem: 9390 +Train: [47] [4300/6250] eta: 0:05:31 lr: 0.000072 grad: 0.0843 (0.0836) loss: 0.8231 (0.8261) time: 0.1609 data: 0.0664 max mem: 9390 +Train: [47] [4400/6250] eta: 0:05:14 lr: 0.000072 grad: 0.0786 (0.0836) loss: 0.8287 (0.8261) time: 0.1766 data: 0.0828 max mem: 9390 +Train: [47] [4500/6250] eta: 0:04:57 lr: 0.000072 grad: 0.0857 (0.0837) loss: 0.8298 (0.8262) time: 0.1606 data: 0.0739 max mem: 9390 +Train: [47] [4600/6250] eta: 0:04:40 lr: 0.000072 grad: 0.0901 (0.0838) loss: 0.8217 (0.8262) time: 0.1782 data: 0.0889 max mem: 9390 +Train: [47] [4700/6250] eta: 0:04:23 lr: 0.000072 grad: 0.0791 (0.0838) loss: 0.8286 (0.8262) time: 0.1618 data: 0.0730 max mem: 9390 +Train: [47] [4800/6250] eta: 0:04:06 lr: 0.000072 grad: 0.0871 (0.0838) loss: 0.8227 (0.8262) time: 0.1647 data: 0.0773 max mem: 9390 +Train: [47] [4900/6250] eta: 0:03:49 lr: 0.000072 grad: 0.0790 (0.0838) loss: 0.8287 (0.8262) time: 0.1501 data: 0.0532 max mem: 9390 +Train: [47] [5000/6250] eta: 0:03:32 lr: 0.000072 grad: 0.0857 (0.0839) loss: 0.8264 (0.8262) time: 0.1729 data: 0.0867 max mem: 9390 +Train: [47] [5100/6250] eta: 0:03:15 lr: 0.000072 grad: 0.0870 (0.0839) loss: 0.8313 (0.8263) time: 0.1651 data: 0.0661 max mem: 9390 +Train: [47] [5200/6250] eta: 0:02:58 lr: 0.000072 grad: 0.0844 (0.0840) loss: 0.8252 (0.8262) time: 0.1572 data: 0.0515 max mem: 9390 +Train: [47] [5300/6250] eta: 0:02:41 lr: 0.000072 grad: 0.0856 (0.0841) loss: 0.8235 (0.8262) time: 0.1499 data: 0.0555 max mem: 9390 +Train: [47] [5400/6250] eta: 0:02:23 lr: 0.000072 grad: 0.0856 (0.0841) loss: 0.8277 (0.8262) time: 0.1657 data: 0.0713 max mem: 9390 +Train: [47] [5500/6250] eta: 0:02:07 lr: 0.000072 grad: 0.0881 (0.0842) loss: 0.8269 (0.8262) time: 0.1600 data: 0.0573 max mem: 9390 +Train: [47] [5600/6250] eta: 0:01:50 lr: 0.000072 grad: 0.0868 (0.0842) loss: 0.8257 (0.8262) time: 0.1787 data: 0.0926 max mem: 9390 +Train: [47] [5700/6250] eta: 0:01:33 lr: 0.000072 grad: 0.0800 (0.0843) loss: 0.8247 (0.8261) time: 0.1604 data: 0.0721 max mem: 9390 +Train: [47] [5800/6250] eta: 0:01:16 lr: 0.000072 grad: 0.0873 (0.0844) loss: 0.8259 (0.8261) time: 0.1678 data: 0.0814 max mem: 9390 +Train: [47] [5900/6250] eta: 0:00:59 lr: 0.000072 grad: 0.0842 (0.0844) loss: 0.8295 (0.8261) time: 0.1702 data: 0.0852 max mem: 9390 +Train: [47] [6000/6250] eta: 0:00:42 lr: 0.000072 grad: 0.0815 (0.0845) loss: 0.8299 (0.8261) time: 0.1595 data: 0.0750 max mem: 9390 +Train: [47] [6100/6250] eta: 0:00:25 lr: 0.000072 grad: 0.0799 (0.0845) loss: 0.8275 (0.8261) time: 0.1549 data: 0.0673 max mem: 9390 +Train: [47] [6200/6250] eta: 0:00:08 lr: 0.000072 grad: 0.0914 (0.0845) loss: 0.8194 (0.8261) time: 0.1673 data: 0.0814 max mem: 9390 +Train: [47] [6249/6250] eta: 0:00:00 lr: 0.000072 grad: 0.0830 (0.0846) loss: 0.8291 (0.8261) time: 0.1504 data: 0.0722 max mem: 9390 +Train: [47] Total time: 0:17:37 (0.1692 s / it) +Averaged stats: lr: 0.000072 grad: 0.0830 (0.0846) loss: 0.8291 (0.8261) +Eval (hcp-train-subset): [47] [ 0/62] eta: 0:05:35 loss: 0.8501 (0.8501) time: 5.4176 data: 5.3863 max mem: 9390 +Eval (hcp-train-subset): [47] [61/62] eta: 0:00:00 loss: 0.8382 (0.8383) time: 0.1347 data: 0.1068 max mem: 9390 +Eval (hcp-train-subset): [47] Total time: 0:00:13 (0.2234 s / it) +Averaged stats (hcp-train-subset): loss: 0.8382 (0.8383) +Eval (hcp-val): [47] [ 0/62] eta: 0:03:22 loss: 0.8349 (0.8349) time: 3.2625 data: 3.2026 max mem: 9390 +Eval (hcp-val): [47] [61/62] eta: 0:00:00 loss: 0.8342 (0.8359) time: 0.1475 data: 0.1220 max mem: 9390 +Eval (hcp-val): [47] Total time: 0:00:14 (0.2362 s / it) +Averaged stats (hcp-val): loss: 0.8342 (0.8359) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +Train: [48] [ 0/6250] eta: 11:07:04 lr: 0.000072 grad: 0.0972 (0.0972) loss: 0.8341 (0.8341) time: 6.4040 data: 6.2954 max mem: 9390 +Train: [48] [ 100/6250] eta: 0:22:11 lr: 0.000072 grad: 0.0841 (0.0949) loss: 0.8323 (0.8393) time: 0.1492 data: 0.0627 max mem: 9390 +Train: [48] [ 200/6250] eta: 0:20:13 lr: 0.000072 grad: 0.0878 (0.0930) loss: 0.8297 (0.8343) time: 0.2134 data: 0.1125 max mem: 9390 +Train: [48] [ 300/6250] eta: 0:19:12 lr: 0.000072 grad: 0.0835 (0.0909) loss: 0.8227 (0.8306) time: 0.1918 data: 0.0860 max mem: 9390 +Train: [48] [ 400/6250] eta: 0:18:30 lr: 0.000072 grad: 0.0799 (0.0887) loss: 0.8313 (0.8301) time: 0.1736 data: 0.0678 max mem: 9390 +Train: [48] [ 500/6250] eta: 0:18:06 lr: 0.000072 grad: 0.0775 (0.0873) loss: 0.8336 (0.8303) time: 0.1740 data: 0.0500 max mem: 9390 +Train: [48] [ 600/6250] eta: 0:17:36 lr: 0.000072 grad: 0.0782 (0.0863) loss: 0.8319 (0.8304) time: 0.1738 data: 0.0715 max mem: 9390 +Train: [48] [ 700/6250] eta: 0:17:15 lr: 0.000072 grad: 0.0845 (0.0856) loss: 0.8349 (0.8303) time: 0.1712 data: 0.0606 max mem: 9390 +Train: [48] [ 800/6250] eta: 0:16:50 lr: 0.000072 grad: 0.0761 (0.0850) loss: 0.8274 (0.8303) time: 0.1605 data: 0.0608 max mem: 9390 +Train: [48] [ 900/6250] eta: 0:16:20 lr: 0.000071 grad: 0.0826 (0.0848) loss: 0.8265 (0.8300) time: 0.1614 data: 0.0670 max mem: 9390 +Train: [48] [1000/6250] eta: 0:15:53 lr: 0.000071 grad: 0.0749 (0.0844) loss: 0.8284 (0.8299) time: 0.1460 data: 0.0529 max mem: 9390 +Train: [48] [1100/6250] eta: 0:15:28 lr: 0.000071 grad: 0.0802 (0.0842) loss: 0.8241 (0.8299) time: 0.1730 data: 0.0775 max mem: 9390 +Train: [48] [1200/6250] eta: 0:14:57 lr: 0.000071 grad: 0.0755 (0.0841) loss: 0.8334 (0.8298) time: 0.1385 data: 0.0384 max mem: 9390 +Train: [48] [1300/6250] eta: 0:14:30 lr: 0.000071 grad: 0.0829 (0.0840) loss: 0.8241 (0.8295) time: 0.1427 data: 0.0466 max mem: 9390 +Train: [48] [1400/6250] eta: 0:14:07 lr: 0.000071 grad: 0.0768 (0.0837) loss: 0.8277 (0.8295) time: 0.1663 data: 0.0826 max mem: 9390 +Train: [48] [1500/6250] eta: 0:13:44 lr: 0.000071 grad: 0.0798 (0.0836) loss: 0.8256 (0.8294) time: 0.1700 data: 0.0814 max mem: 9390 +Train: [48] [1600/6250] eta: 0:13:24 lr: 0.000071 grad: 0.0859 (0.0837) loss: 0.8231 (0.8290) time: 0.1550 data: 0.0620 max mem: 9390 +Train: [48] [1700/6250] eta: 0:13:01 lr: 0.000071 grad: 0.0788 (0.0837) loss: 0.8259 (0.8289) time: 0.1620 data: 0.0664 max mem: 9390 +Train: [48] [1800/6250] eta: 0:12:41 lr: 0.000071 grad: 0.0805 (0.0837) loss: 0.8251 (0.8287) time: 0.1866 data: 0.1002 max mem: 9390 +Train: [48] [1900/6250] eta: 0:12:19 lr: 0.000071 grad: 0.0797 (0.0838) loss: 0.8302 (0.8287) time: 0.1443 data: 0.0486 max mem: 9390 +Train: [48] [2000/6250] eta: 0:12:00 lr: 0.000071 grad: 0.0788 (0.0841) loss: 0.8235 (0.8287) time: 0.1570 data: 0.0719 max mem: 9390 +Train: [48] [2100/6250] eta: 0:11:41 lr: 0.000071 grad: 0.0763 (0.0841) loss: 0.8240 (0.8285) time: 0.1527 data: 0.0608 max mem: 9390 +Train: [48] [2200/6250] eta: 0:11:22 lr: 0.000071 grad: 0.0828 (0.0842) loss: 0.8213 (0.8283) time: 0.1504 data: 0.0526 max mem: 9390 +Train: [48] [2300/6250] eta: 0:11:03 lr: 0.000071 grad: 0.0791 (0.0842) loss: 0.8311 (0.8282) time: 0.1736 data: 0.0796 max mem: 9390 +Train: [48] [2400/6250] eta: 0:10:45 lr: 0.000071 grad: 0.0838 (0.0841) loss: 0.8253 (0.8282) time: 0.1559 data: 0.0641 max mem: 9390 +Train: [48] [2500/6250] eta: 0:10:26 lr: 0.000071 grad: 0.0785 (0.0840) loss: 0.8293 (0.8280) time: 0.1512 data: 0.0615 max mem: 9390 +Train: [48] [2600/6250] eta: 0:10:07 lr: 0.000071 grad: 0.0797 (0.0840) loss: 0.8205 (0.8280) time: 0.1396 data: 0.0509 max mem: 9390 +Train: [48] [2700/6250] eta: 0:09:49 lr: 0.000071 grad: 0.0806 (0.0840) loss: 0.8204 (0.8278) time: 0.1517 data: 0.0540 max mem: 9390 +Train: [48] [2800/6250] eta: 0:09:31 lr: 0.000071 grad: 0.0806 (0.0840) loss: 0.8269 (0.8276) time: 0.1551 data: 0.0628 max mem: 9390 +Train: [48] [2900/6250] eta: 0:09:14 lr: 0.000071 grad: 0.0818 (0.0839) loss: 0.8288 (0.8275) time: 0.1478 data: 0.0526 max mem: 9390 +Train: [48] [3000/6250] eta: 0:08:57 lr: 0.000071 grad: 0.0836 (0.0839) loss: 0.8234 (0.8274) time: 0.1526 data: 0.0628 max mem: 9390 +Train: [48] [3100/6250] eta: 0:08:39 lr: 0.000071 grad: 0.0828 (0.0839) loss: 0.8189 (0.8273) time: 0.1500 data: 0.0646 max mem: 9390 +Train: [48] [3200/6250] eta: 0:08:22 lr: 0.000071 grad: 0.0814 (0.0840) loss: 0.8222 (0.8272) time: 0.1706 data: 0.0892 max mem: 9390 +Train: [48] [3300/6250] eta: 0:08:05 lr: 0.000071 grad: 0.0879 (0.0842) loss: 0.8213 (0.8270) time: 0.1674 data: 0.0832 max mem: 9390 +Train: [48] [3400/6250] eta: 0:07:48 lr: 0.000071 grad: 0.0894 (0.0843) loss: 0.8208 (0.8269) time: 0.1690 data: 0.0890 max mem: 9390 +Train: [48] [3500/6250] eta: 0:07:31 lr: 0.000071 grad: 0.0824 (0.0843) loss: 0.8281 (0.8269) time: 0.1470 data: 0.0599 max mem: 9390 +Train: [48] [3600/6250] eta: 0:07:14 lr: 0.000071 grad: 0.0860 (0.0844) loss: 0.8226 (0.8268) time: 0.1472 data: 0.0500 max mem: 9390 +Train: [48] [3700/6250] eta: 0:06:58 lr: 0.000071 grad: 0.0830 (0.0845) loss: 0.8263 (0.8267) time: 0.1464 data: 0.0475 max mem: 9390 +Train: [48] [3800/6250] eta: 0:06:41 lr: 0.000071 grad: 0.0848 (0.0846) loss: 0.8250 (0.8266) time: 0.1614 data: 0.0676 max mem: 9390 +Train: [48] [3900/6250] eta: 0:06:25 lr: 0.000070 grad: 0.0887 (0.0847) loss: 0.8267 (0.8265) time: 0.1384 data: 0.0484 max mem: 9390 +Train: [48] [4000/6250] eta: 0:06:09 lr: 0.000070 grad: 0.0836 (0.0847) loss: 0.8238 (0.8264) time: 0.1753 data: 0.0828 max mem: 9390 +Train: [48] [4100/6250] eta: 0:05:52 lr: 0.000070 grad: 0.0843 (0.0848) loss: 0.8223 (0.8262) time: 0.1478 data: 0.0634 max mem: 9390 +Train: [48] [4200/6250] eta: 0:05:35 lr: 0.000070 grad: 0.0840 (0.0849) loss: 0.8229 (0.8261) time: 0.1545 data: 0.0676 max mem: 9390 +Train: [48] [4300/6250] eta: 0:05:19 lr: 0.000070 grad: 0.0850 (0.0849) loss: 0.8243 (0.8260) time: 0.1685 data: 0.0818 max mem: 9390 +Train: [48] [4400/6250] eta: 0:05:02 lr: 0.000070 grad: 0.0887 (0.0849) loss: 0.8249 (0.8259) time: 0.1392 data: 0.0463 max mem: 9390 +Train: [48] [4500/6250] eta: 0:04:46 lr: 0.000070 grad: 0.0750 (0.0849) loss: 0.8292 (0.8258) time: 0.1612 data: 0.0724 max mem: 9390 +Train: [48] [4600/6250] eta: 0:04:29 lr: 0.000070 grad: 0.0883 (0.0850) loss: 0.8164 (0.8257) time: 0.1686 data: 0.0773 max mem: 9390 +Train: [48] [4700/6250] eta: 0:04:13 lr: 0.000070 grad: 0.0771 (0.0850) loss: 0.8255 (0.8257) time: 0.1740 data: 0.0879 max mem: 9390 +Train: [48] [4800/6250] eta: 0:03:56 lr: 0.000070 grad: 0.0882 (0.0850) loss: 0.8204 (0.8257) time: 0.1631 data: 0.0749 max mem: 9390 +Train: [48] [4900/6250] eta: 0:03:40 lr: 0.000070 grad: 0.0802 (0.0850) loss: 0.8238 (0.8256) time: 0.1633 data: 0.0735 max mem: 9390 +Train: [48] [5000/6250] eta: 0:03:24 lr: 0.000070 grad: 0.0831 (0.0850) loss: 0.8244 (0.8256) time: 0.1569 data: 0.0647 max mem: 9390 +Train: [48] [5100/6250] eta: 0:03:07 lr: 0.000070 grad: 0.0801 (0.0850) loss: 0.8234 (0.8256) time: 0.1679 data: 0.0774 max mem: 9390 +Train: [48] [5200/6250] eta: 0:02:51 lr: 0.000070 grad: 0.0838 (0.0850) loss: 0.8224 (0.8255) time: 0.1483 data: 0.0627 max mem: 9390 +Train: [48] [5300/6250] eta: 0:02:35 lr: 0.000070 grad: 0.0837 (0.0850) loss: 0.8274 (0.8255) time: 0.1555 data: 0.0628 max mem: 9390 +Train: [48] [5400/6250] eta: 0:02:18 lr: 0.000070 grad: 0.0857 (0.0850) loss: 0.8221 (0.8255) time: 0.1548 data: 0.0723 max mem: 9390 +Train: [48] [5500/6250] eta: 0:02:02 lr: 0.000070 grad: 0.0782 (0.0850) loss: 0.8233 (0.8255) time: 0.1629 data: 0.0763 max mem: 9390 +Train: [48] [5600/6250] eta: 0:01:46 lr: 0.000070 grad: 0.0825 (0.0850) loss: 0.8227 (0.8254) time: 0.1883 data: 0.0993 max mem: 9390 +Train: [48] [5700/6250] eta: 0:01:29 lr: 0.000070 grad: 0.0766 (0.0849) loss: 0.8228 (0.8254) time: 0.1835 data: 0.1018 max mem: 9390 +Train: [48] [5800/6250] eta: 0:01:13 lr: 0.000070 grad: 0.0762 (0.0849) loss: 0.8250 (0.8253) time: 0.1539 data: 0.0659 max mem: 9390 +Train: [48] [5900/6250] eta: 0:00:57 lr: 0.000070 grad: 0.0839 (0.0849) loss: 0.8226 (0.8253) time: 0.1431 data: 0.0590 max mem: 9390 +Train: [48] [6000/6250] eta: 0:00:40 lr: 0.000070 grad: 0.0817 (0.0850) loss: 0.8233 (0.8252) time: 0.1630 data: 0.0748 max mem: 9390 +Train: [48] [6100/6250] eta: 0:00:24 lr: 0.000070 grad: 0.0812 (0.0850) loss: 0.8212 (0.8252) time: 0.1672 data: 0.0830 max mem: 9390 +Train: [48] [6200/6250] eta: 0:00:08 lr: 0.000070 grad: 0.0775 (0.0849) loss: 0.8352 (0.8252) time: 0.1669 data: 0.0808 max mem: 9390 +Train: [48] [6249/6250] eta: 0:00:00 lr: 0.000070 grad: 0.0818 (0.0849) loss: 0.8260 (0.8252) time: 0.1525 data: 0.0576 max mem: 9390 +Train: [48] Total time: 0:17:06 (0.1642 s / it) +Averaged stats: lr: 0.000070 grad: 0.0818 (0.0849) loss: 0.8260 (0.8252) +Eval (hcp-train-subset): [48] [ 0/62] eta: 0:03:07 loss: 0.8466 (0.8466) time: 3.0172 data: 2.8925 max mem: 9390 +Eval (hcp-train-subset): [48] [61/62] eta: 0:00:00 loss: 0.8385 (0.8375) time: 0.1443 data: 0.1192 max mem: 9390 +Eval (hcp-train-subset): [48] Total time: 0:00:13 (0.2162 s / it) +Averaged stats (hcp-train-subset): loss: 0.8385 (0.8375) +Eval (hcp-val): [48] [ 0/62] eta: 0:03:37 loss: 0.8322 (0.8322) time: 3.5050 data: 3.4431 max mem: 9390 +Eval (hcp-val): [48] [61/62] eta: 0:00:00 loss: 0.8347 (0.8366) time: 0.1438 data: 0.1166 max mem: 9390 +Eval (hcp-val): [48] Total time: 0:00:14 (0.2338 s / it) +Averaged stats (hcp-val): loss: 0.8347 (0.8366) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +Train: [49] [ 0/6250] eta: 6:02:05 lr: 0.000070 grad: 0.0606 (0.0606) loss: 0.8569 (0.8569) time: 3.4761 data: 3.1857 max mem: 9390 +Train: [49] [ 100/6250] eta: 0:22:14 lr: 0.000070 grad: 0.0778 (0.0910) loss: 0.8323 (0.8333) time: 0.1471 data: 0.0683 max mem: 9390 +Train: [49] [ 200/6250] eta: 0:19:27 lr: 0.000070 grad: 0.0736 (0.0858) loss: 0.8347 (0.8337) time: 0.1589 data: 0.0701 max mem: 9390 +Train: [49] [ 300/6250] eta: 0:18:37 lr: 0.000070 grad: 0.0774 (0.0844) loss: 0.8391 (0.8344) time: 0.1958 data: 0.1038 max mem: 9390 +Train: [49] [ 400/6250] eta: 0:17:47 lr: 0.000070 grad: 0.0796 (0.0847) loss: 0.8282 (0.8333) time: 0.1425 data: 0.0469 max mem: 9390 +Train: [49] [ 500/6250] eta: 0:17:17 lr: 0.000070 grad: 0.0814 (0.0849) loss: 0.8257 (0.8316) time: 0.1565 data: 0.0561 max mem: 9390 +Train: [49] [ 600/6250] eta: 0:16:48 lr: 0.000070 grad: 0.0823 (0.0857) loss: 0.8256 (0.8301) time: 0.1815 data: 0.0793 max mem: 9390 +Train: [49] [ 700/6250] eta: 0:16:11 lr: 0.000069 grad: 0.0808 (0.0859) loss: 0.8316 (0.8296) time: 0.1630 data: 0.0633 max mem: 9390 +Train: [49] [ 800/6250] eta: 0:15:46 lr: 0.000069 grad: 0.0779 (0.0857) loss: 0.8359 (0.8298) time: 0.1748 data: 0.0782 max mem: 9390 +Train: [49] [ 900/6250] eta: 0:15:26 lr: 0.000069 grad: 0.0796 (0.0857) loss: 0.8298 (0.8298) time: 0.2028 data: 0.1039 max mem: 9390 +Train: [49] [1000/6250] eta: 0:15:06 lr: 0.000069 grad: 0.0831 (0.0856) loss: 0.8209 (0.8297) time: 0.1741 data: 0.0829 max mem: 9390 +Train: [49] [1100/6250] eta: 0:14:46 lr: 0.000069 grad: 0.0873 (0.0854) loss: 0.8289 (0.8295) time: 0.1634 data: 0.0665 max mem: 9390 +Train: [49] [1200/6250] eta: 0:14:23 lr: 0.000069 grad: 0.0792 (0.0854) loss: 0.8239 (0.8292) time: 0.1441 data: 0.0479 max mem: 9390 +Train: [49] [1300/6250] eta: 0:14:02 lr: 0.000069 grad: 0.0832 (0.0852) loss: 0.8270 (0.8290) time: 0.1440 data: 0.0547 max mem: 9390 +Train: [49] [1400/6250] eta: 0:13:43 lr: 0.000069 grad: 0.0854 (0.0853) loss: 0.8200 (0.8284) time: 0.1643 data: 0.0697 max mem: 9390 +Train: [49] [1500/6250] eta: 0:13:23 lr: 0.000069 grad: 0.0810 (0.0851) loss: 0.8172 (0.8281) time: 0.1830 data: 0.0999 max mem: 9390 +Train: [49] [1600/6250] eta: 0:13:02 lr: 0.000069 grad: 0.0874 (0.0854) loss: 0.8211 (0.8276) time: 0.1623 data: 0.0716 max mem: 9390 +Train: [49] [1700/6250] eta: 0:12:43 lr: 0.000069 grad: 0.0829 (0.0857) loss: 0.8212 (0.8274) time: 0.1487 data: 0.0531 max mem: 9390 +Train: [49] [1800/6250] eta: 0:12:25 lr: 0.000069 grad: 0.0919 (0.0858) loss: 0.8223 (0.8270) time: 0.1861 data: 0.0962 max mem: 9390 +Train: [49] [1900/6250] eta: 0:12:08 lr: 0.000069 grad: 0.0895 (0.0861) loss: 0.8197 (0.8267) time: 0.1779 data: 0.0959 max mem: 9390 +Train: [49] [2000/6250] eta: 0:11:51 lr: 0.000069 grad: 0.0858 (0.0863) loss: 0.8176 (0.8263) time: 0.1383 data: 0.0474 max mem: 9390 +Train: [49] [2100/6250] eta: 0:11:33 lr: 0.000069 grad: 0.0839 (0.0865) loss: 0.8183 (0.8260) time: 0.1662 data: 0.0755 max mem: 9390 +Train: [49] [2200/6250] eta: 0:11:14 lr: 0.000069 grad: 0.0847 (0.0866) loss: 0.8185 (0.8258) time: 0.1480 data: 0.0573 max mem: 9390 +Train: [49] [2300/6250] eta: 0:10:57 lr: 0.000069 grad: 0.0870 (0.0869) loss: 0.8191 (0.8255) time: 0.1712 data: 0.0832 max mem: 9390 +Train: [49] [2400/6250] eta: 0:10:40 lr: 0.000069 grad: 0.0877 (0.0871) loss: 0.8214 (0.8253) time: 0.1488 data: 0.0483 max mem: 9390 +Train: [49] [2500/6250] eta: 0:10:24 lr: 0.000069 grad: 0.0844 (0.0872) loss: 0.8223 (0.8251) time: 0.1758 data: 0.0883 max mem: 9390 +Train: [49] [2600/6250] eta: 0:10:06 lr: 0.000069 grad: 0.0858 (0.0872) loss: 0.8229 (0.8248) time: 0.1505 data: 0.0473 max mem: 9390 +Train: [49] [2700/6250] eta: 0:09:50 lr: 0.000069 grad: 0.0842 (0.0873) loss: 0.8125 (0.8246) time: 0.1860 data: 0.1003 max mem: 9390 +Train: [49] [2800/6250] eta: 0:09:34 lr: 0.000069 grad: 0.0862 (0.0873) loss: 0.8174 (0.8244) time: 0.1688 data: 0.0795 max mem: 9390 +Train: [49] [2900/6250] eta: 0:09:19 lr: 0.000069 grad: 0.0843 (0.0875) loss: 0.8253 (0.8243) time: 0.1911 data: 0.1029 max mem: 9390 +Train: [49] [3000/6250] eta: 0:09:01 lr: 0.000069 grad: 0.0847 (0.0874) loss: 0.8246 (0.8242) time: 0.1589 data: 0.0709 max mem: 9390 +Train: [49] [3100/6250] eta: 0:08:46 lr: 0.000069 grad: 0.0843 (0.0875) loss: 0.8147 (0.8240) time: 0.1827 data: 0.0925 max mem: 9390 +Train: [49] [3200/6250] eta: 0:08:30 lr: 0.000069 grad: 0.0868 (0.0875) loss: 0.8146 (0.8239) time: 0.1983 data: 0.1092 max mem: 9390 +Train: [49] [3300/6250] eta: 0:08:13 lr: 0.000069 grad: 0.0878 (0.0875) loss: 0.8166 (0.8237) time: 0.1710 data: 0.0693 max mem: 9390 +Train: [49] [3400/6250] eta: 0:07:55 lr: 0.000069 grad: 0.0901 (0.0876) loss: 0.8236 (0.8236) time: 0.1529 data: 0.0562 max mem: 9390 +Train: [49] [3500/6250] eta: 0:07:38 lr: 0.000069 grad: 0.0881 (0.0877) loss: 0.8207 (0.8234) time: 0.1436 data: 0.0350 max mem: 9390 +Train: [49] [3600/6250] eta: 0:07:20 lr: 0.000069 grad: 0.0858 (0.0877) loss: 0.8171 (0.8234) time: 0.1548 data: 0.0561 max mem: 9390 +Train: [49] [3700/6250] eta: 0:07:03 lr: 0.000069 grad: 0.0935 (0.0880) loss: 0.8192 (0.8233) time: 0.1313 data: 0.0487 max mem: 9390 +Train: [49] [3800/6250] eta: 0:06:46 lr: 0.000068 grad: 0.0847 (0.0880) loss: 0.8269 (0.8232) time: 0.1459 data: 0.0536 max mem: 9390 +Train: [49] [3900/6250] eta: 0:06:29 lr: 0.000068 grad: 0.0867 (0.0880) loss: 0.8227 (0.8231) time: 0.1509 data: 0.0661 max mem: 9390 +Train: [49] [4000/6250] eta: 0:06:12 lr: 0.000068 grad: 0.0846 (0.0880) loss: 0.8286 (0.8231) time: 0.1841 data: 0.0925 max mem: 9390 +Train: [49] [4100/6250] eta: 0:05:55 lr: 0.000068 grad: 0.0826 (0.0880) loss: 0.8214 (0.8231) time: 0.1519 data: 0.0577 max mem: 9390 +Train: [49] [4200/6250] eta: 0:05:39 lr: 0.000068 grad: 0.0873 (0.0880) loss: 0.8200 (0.8230) time: 0.1765 data: 0.0867 max mem: 9390 +Train: [49] [4300/6250] eta: 0:05:22 lr: 0.000068 grad: 0.0803 (0.0880) loss: 0.8191 (0.8230) time: 0.1634 data: 0.0738 max mem: 9390 +Train: [49] [4400/6250] eta: 0:05:06 lr: 0.000068 grad: 0.0886 (0.0880) loss: 0.8180 (0.8229) time: 0.1535 data: 0.0706 max mem: 9390 +Train: [49] [4500/6250] eta: 0:04:50 lr: 0.000068 grad: 0.0827 (0.0880) loss: 0.8200 (0.8228) time: 0.2142 data: 0.1261 max mem: 9390 +Train: [49] [4600/6250] eta: 0:04:33 lr: 0.000068 grad: 0.0885 (0.0880) loss: 0.8203 (0.8228) time: 0.1797 data: 0.0847 max mem: 9390 +Train: [49] [4700/6250] eta: 0:04:16 lr: 0.000068 grad: 0.0841 (0.0880) loss: 0.8187 (0.8228) time: 0.1567 data: 0.0602 max mem: 9390 +Train: [49] [4800/6250] eta: 0:04:00 lr: 0.000068 grad: 0.0845 (0.0880) loss: 0.8225 (0.8227) time: 0.1771 data: 0.0953 max mem: 9390 +Train: [49] [4900/6250] eta: 0:03:43 lr: 0.000068 grad: 0.0877 (0.0880) loss: 0.8221 (0.8227) time: 0.1662 data: 0.0832 max mem: 9390 +Train: [49] [5000/6250] eta: 0:03:26 lr: 0.000068 grad: 0.0879 (0.0880) loss: 0.8216 (0.8227) time: 0.1505 data: 0.0509 max mem: 9390 +Train: [49] [5100/6250] eta: 0:03:09 lr: 0.000068 grad: 0.0821 (0.0881) loss: 0.8203 (0.8227) time: 0.1593 data: 0.0730 max mem: 9390 +Train: [49] [5200/6250] eta: 0:02:53 lr: 0.000068 grad: 0.0843 (0.0881) loss: 0.8197 (0.8227) time: 0.1697 data: 0.0910 max mem: 9390 +Train: [49] [5300/6250] eta: 0:02:36 lr: 0.000068 grad: 0.0838 (0.0881) loss: 0.8257 (0.8227) time: 0.1523 data: 0.0665 max mem: 9390 +Train: [49] [5400/6250] eta: 0:02:20 lr: 0.000068 grad: 0.0846 (0.0881) loss: 0.8124 (0.8226) time: 0.1645 data: 0.0755 max mem: 9390 +Train: [49] [5500/6250] eta: 0:02:03 lr: 0.000068 grad: 0.0834 (0.0881) loss: 0.8264 (0.8226) time: 0.1571 data: 0.0688 max mem: 9390 +Train: [49] [5600/6250] eta: 0:01:47 lr: 0.000068 grad: 0.0883 (0.0881) loss: 0.8225 (0.8226) time: 0.1456 data: 0.0473 max mem: 9390 +Train: [49] [5700/6250] eta: 0:01:30 lr: 0.000068 grad: 0.0842 (0.0882) loss: 0.8176 (0.8225) time: 0.1431 data: 0.0481 max mem: 9390 +Train: [49] [5800/6250] eta: 0:01:13 lr: 0.000068 grad: 0.0833 (0.0882) loss: 0.8166 (0.8225) time: 0.1687 data: 0.0746 max mem: 9390 +Train: [49] [5900/6250] eta: 0:00:57 lr: 0.000068 grad: 0.0824 (0.0882) loss: 0.8206 (0.8224) time: 0.1735 data: 0.0872 max mem: 9390 +Train: [49] [6000/6250] eta: 0:00:41 lr: 0.000068 grad: 0.0835 (0.0882) loss: 0.8173 (0.8223) time: 0.1394 data: 0.0475 max mem: 9390 +Train: [49] [6100/6250] eta: 0:00:24 lr: 0.000068 grad: 0.0859 (0.0883) loss: 0.8218 (0.8222) time: 0.1560 data: 0.0578 max mem: 9390 +Train: [49] [6200/6250] eta: 0:00:08 lr: 0.000068 grad: 0.0864 (0.0883) loss: 0.8165 (0.8221) time: 0.1727 data: 0.0856 max mem: 9390 +Train: [49] [6249/6250] eta: 0:00:00 lr: 0.000068 grad: 0.0771 (0.0883) loss: 0.8208 (0.8221) time: 0.1614 data: 0.0676 max mem: 9390 +Train: [49] Total time: 0:17:11 (0.1651 s / it) +Averaged stats: lr: 0.000068 grad: 0.0771 (0.0883) loss: 0.8208 (0.8221) +Eval (hcp-train-subset): [49] [ 0/62] eta: 0:03:55 loss: 0.8485 (0.8485) time: 3.7999 data: 3.7208 max mem: 9390 +Eval (hcp-train-subset): [49] [61/62] eta: 0:00:00 loss: 0.8394 (0.8379) time: 0.1222 data: 0.0966 max mem: 9390 +Eval (hcp-train-subset): [49] Total time: 0:00:13 (0.2217 s / it) +Averaged stats (hcp-train-subset): loss: 0.8394 (0.8379) +Making plots (hcp-train-subset): example=9 +Eval (hcp-val): [49] [ 0/62] eta: 0:04:03 loss: 0.8334 (0.8334) time: 3.9256 data: 3.8585 max mem: 9390 +Eval (hcp-val): [49] [61/62] eta: 0:00:00 loss: 0.8342 (0.8357) time: 0.1144 data: 0.0892 max mem: 9390 +Eval (hcp-val): [49] Total time: 0:00:14 (0.2404 s / it) +Averaged stats (hcp-val): loss: 0.8342 (0.8357) +Making plots (hcp-val): example=42 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +Train: [50] [ 0/6250] eta: 6:41:41 lr: 0.000068 grad: 0.0641 (0.0641) loss: 0.8415 (0.8415) time: 3.8562 data: 3.6162 max mem: 9390 +Train: [50] [ 100/6250] eta: 0:22:32 lr: 0.000068 grad: 0.0813 (0.0892) loss: 0.8321 (0.8358) time: 0.1838 data: 0.1008 max mem: 9390 +Train: [50] [ 200/6250] eta: 0:20:09 lr: 0.000068 grad: 0.0791 (0.0914) loss: 0.8332 (0.8312) time: 0.2005 data: 0.1029 max mem: 9390 +Train: [50] [ 300/6250] eta: 0:18:57 lr: 0.000068 grad: 0.0795 (0.0906) loss: 0.8304 (0.8305) time: 0.1599 data: 0.0600 max mem: 9390 +Train: [50] [ 400/6250] eta: 0:18:29 lr: 0.000068 grad: 0.0825 (0.0897) loss: 0.8296 (0.8303) time: 0.2012 data: 0.0921 max mem: 9390 +Train: [50] [ 500/6250] eta: 0:17:53 lr: 0.000067 grad: 0.0842 (0.0887) loss: 0.8220 (0.8298) time: 0.1995 data: 0.1036 max mem: 9390 +Train: [50] [ 600/6250] eta: 0:17:19 lr: 0.000067 grad: 0.0812 (0.0878) loss: 0.8263 (0.8297) time: 0.1696 data: 0.0676 max mem: 9390 +Train: [50] [ 700/6250] eta: 0:16:58 lr: 0.000067 grad: 0.0793 (0.0873) loss: 0.8259 (0.8295) time: 0.1615 data: 0.0605 max mem: 9390 +Train: [50] [ 800/6250] eta: 0:16:36 lr: 0.000067 grad: 0.0861 (0.0870) loss: 0.8219 (0.8292) time: 0.1741 data: 0.0742 max mem: 9390 +Train: [50] [ 900/6250] eta: 0:16:09 lr: 0.000067 grad: 0.0838 (0.0867) loss: 0.8219 (0.8289) time: 0.1581 data: 0.0663 max mem: 9390 +Train: [50] [1000/6250] eta: 0:15:45 lr: 0.000067 grad: 0.0810 (0.0862) loss: 0.8266 (0.8286) time: 0.1836 data: 0.0926 max mem: 9390 +Train: [50] [1100/6250] eta: 0:15:16 lr: 0.000067 grad: 0.0862 (0.0863) loss: 0.8256 (0.8284) time: 0.1665 data: 0.0797 max mem: 9390 +Train: [50] [1200/6250] eta: 0:14:51 lr: 0.000067 grad: 0.0790 (0.0862) loss: 0.8234 (0.8280) time: 0.1727 data: 0.0881 max mem: 9390 +Train: [50] [1300/6250] eta: 0:14:26 lr: 0.000067 grad: 0.0881 (0.0862) loss: 0.8151 (0.8277) time: 0.1831 data: 0.0936 max mem: 9390 +Train: [50] [1400/6250] eta: 0:14:03 lr: 0.000067 grad: 0.0807 (0.0863) loss: 0.8278 (0.8273) time: 0.1740 data: 0.0776 max mem: 9390 +Train: [50] [1500/6250] eta: 0:13:39 lr: 0.000067 grad: 0.0842 (0.0863) loss: 0.8229 (0.8269) time: 0.1647 data: 0.0796 max mem: 9390 +Train: [50] [1600/6250] eta: 0:13:18 lr: 0.000067 grad: 0.0781 (0.0864) loss: 0.8304 (0.8268) time: 0.1431 data: 0.0539 max mem: 9390 +Train: [50] [1700/6250] eta: 0:12:57 lr: 0.000067 grad: 0.0822 (0.0864) loss: 0.8221 (0.8265) time: 0.1286 data: 0.0382 max mem: 9390 +Train: [50] [1800/6250] eta: 0:12:36 lr: 0.000067 grad: 0.0850 (0.0866) loss: 0.8238 (0.8262) time: 0.1579 data: 0.0609 max mem: 9390 +Train: [50] [1900/6250] eta: 0:12:15 lr: 0.000067 grad: 0.0830 (0.0869) loss: 0.8236 (0.8260) time: 0.1569 data: 0.0668 max mem: 9390 +Train: [50] [2000/6250] eta: 0:11:55 lr: 0.000067 grad: 0.0836 (0.0869) loss: 0.8259 (0.8258) time: 0.1613 data: 0.0694 max mem: 9390 +Train: [50] [2100/6250] eta: 0:11:36 lr: 0.000067 grad: 0.0826 (0.0869) loss: 0.8223 (0.8255) time: 0.1574 data: 0.0674 max mem: 9390 +Train: [50] [2200/6250] eta: 0:11:18 lr: 0.000067 grad: 0.0853 (0.0871) loss: 0.8248 (0.8253) time: 0.1632 data: 0.0754 max mem: 9390 +Train: [50] [2300/6250] eta: 0:11:00 lr: 0.000067 grad: 0.0905 (0.0873) loss: 0.8176 (0.8252) time: 0.1673 data: 0.0772 max mem: 9390 +Train: [50] [2400/6250] eta: 0:10:41 lr: 0.000067 grad: 0.0851 (0.0874) loss: 0.8201 (0.8250) time: 0.1318 data: 0.0376 max mem: 9390 +Train: [50] [2500/6250] eta: 0:10:23 lr: 0.000067 grad: 0.0834 (0.0873) loss: 0.8263 (0.8249) time: 0.1590 data: 0.0694 max mem: 9390 +Train: [50] [2600/6250] eta: 0:10:06 lr: 0.000067 grad: 0.0814 (0.0873) loss: 0.8312 (0.8249) time: 0.1516 data: 0.0611 max mem: 9390 +Train: [50] [2700/6250] eta: 0:09:49 lr: 0.000067 grad: 0.0841 (0.0873) loss: 0.8193 (0.8248) time: 0.1527 data: 0.0607 max mem: 9390 +Train: [50] [2800/6250] eta: 0:09:32 lr: 0.000067 grad: 0.0867 (0.0873) loss: 0.8219 (0.8247) time: 0.1673 data: 0.0832 max mem: 9390 +Train: [50] [2900/6250] eta: 0:09:15 lr: 0.000067 grad: 0.0852 (0.0874) loss: 0.8256 (0.8247) time: 0.1862 data: 0.0946 max mem: 9390 +Train: [50] [3000/6250] eta: 0:08:57 lr: 0.000067 grad: 0.0872 (0.0874) loss: 0.8220 (0.8246) time: 0.1562 data: 0.0661 max mem: 9390 +Train: [50] [3100/6250] eta: 0:08:40 lr: 0.000067 grad: 0.0897 (0.0875) loss: 0.8216 (0.8246) time: 0.1460 data: 0.0547 max mem: 9390 +Train: [50] [3200/6250] eta: 0:08:24 lr: 0.000067 grad: 0.0837 (0.0875) loss: 0.8262 (0.8246) time: 0.1691 data: 0.0855 max mem: 9390 +Train: [50] [3300/6250] eta: 0:08:07 lr: 0.000067 grad: 0.0846 (0.0874) loss: 0.8273 (0.8247) time: 0.1622 data: 0.0779 max mem: 9390 +Train: [50] [3400/6250] eta: 0:07:50 lr: 0.000067 grad: 0.0846 (0.0874) loss: 0.8212 (0.8247) time: 0.1697 data: 0.0835 max mem: 9390 +Train: [50] [3500/6250] eta: 0:07:33 lr: 0.000067 grad: 0.0818 (0.0874) loss: 0.8286 (0.8248) time: 0.1647 data: 0.0705 max mem: 9390 +Train: [50] [3600/6250] eta: 0:07:16 lr: 0.000066 grad: 0.0825 (0.0874) loss: 0.8247 (0.8248) time: 0.1719 data: 0.0820 max mem: 9390 +Train: [50] [3700/6250] eta: 0:07:00 lr: 0.000066 grad: 0.0833 (0.0874) loss: 0.8172 (0.8247) time: 0.1552 data: 0.0557 max mem: 9390 +Train: [50] [3800/6250] eta: 0:06:43 lr: 0.000066 grad: 0.0856 (0.0874) loss: 0.8243 (0.8247) time: 0.1562 data: 0.0685 max mem: 9390 +Train: [50] [3900/6250] eta: 0:06:27 lr: 0.000066 grad: 0.0830 (0.0874) loss: 0.8216 (0.8247) time: 0.1694 data: 0.0809 max mem: 9390 +Train: [50] [4000/6250] eta: 0:06:10 lr: 0.000066 grad: 0.0813 (0.0874) loss: 0.8228 (0.8247) time: 0.1559 data: 0.0678 max mem: 9390 +Train: [50] [4100/6250] eta: 0:05:54 lr: 0.000066 grad: 0.0839 (0.0874) loss: 0.8243 (0.8247) time: 0.1747 data: 0.0777 max mem: 9390 +Train: [50] [4200/6250] eta: 0:05:37 lr: 0.000066 grad: 0.0963 (0.0874) loss: 0.8146 (0.8246) time: 0.1507 data: 0.0603 max mem: 9390 +Train: [50] [4300/6250] eta: 0:05:20 lr: 0.000066 grad: 0.0867 (0.0874) loss: 0.8209 (0.8246) time: 0.1569 data: 0.0699 max mem: 9390 +Train: [50] [4400/6250] eta: 0:05:04 lr: 0.000066 grad: 0.0912 (0.0875) loss: 0.8191 (0.8245) time: 0.1803 data: 0.0949 max mem: 9390 +Train: [50] [4500/6250] eta: 0:04:47 lr: 0.000066 grad: 0.0848 (0.0876) loss: 0.8260 (0.8244) time: 0.1702 data: 0.0767 max mem: 9390 +Train: [50] [4600/6250] eta: 0:04:31 lr: 0.000066 grad: 0.0927 (0.0877) loss: 0.8170 (0.8243) time: 0.1579 data: 0.0704 max mem: 9390 +Train: [50] [4700/6250] eta: 0:04:14 lr: 0.000066 grad: 0.0865 (0.0878) loss: 0.8277 (0.8243) time: 0.1611 data: 0.0771 max mem: 9390 +Train: [50] [4800/6250] eta: 0:03:58 lr: 0.000066 grad: 0.0955 (0.0880) loss: 0.8247 (0.8242) time: 0.1839 data: 0.1001 max mem: 9390 +Train: [50] [4900/6250] eta: 0:03:42 lr: 0.000066 grad: 0.0950 (0.0882) loss: 0.8213 (0.8241) time: 0.1756 data: 0.0915 max mem: 9390 +Train: [50] [5000/6250] eta: 0:03:25 lr: 0.000066 grad: 0.0898 (0.0883) loss: 0.8173 (0.8240) time: 0.1527 data: 0.0627 max mem: 9390 +Train: [50] [5100/6250] eta: 0:03:09 lr: 0.000066 grad: 0.0879 (0.0884) loss: 0.8207 (0.8240) time: 0.1579 data: 0.0619 max mem: 9390 +Train: [50] [5200/6250] eta: 0:02:52 lr: 0.000066 grad: 0.0832 (0.0885) loss: 0.8273 (0.8239) time: 0.1612 data: 0.0779 max mem: 9390 +Train: [50] [5300/6250] eta: 0:02:36 lr: 0.000066 grad: 0.0848 (0.0886) loss: 0.8276 (0.8239) time: 0.1560 data: 0.0782 max mem: 9390 +Train: [50] [5400/6250] eta: 0:02:19 lr: 0.000066 grad: 0.0835 (0.0887) loss: 0.8176 (0.8238) time: 0.1619 data: 0.0708 max mem: 9390 +Train: [50] [5500/6250] eta: 0:02:03 lr: 0.000066 grad: 0.0894 (0.0887) loss: 0.8218 (0.8238) time: 0.1734 data: 0.0846 max mem: 9390 +Train: [50] [5600/6250] eta: 0:01:46 lr: 0.000066 grad: 0.0875 (0.0887) loss: 0.8202 (0.8238) time: 0.1512 data: 0.0658 max mem: 9390 +Train: [50] [5700/6250] eta: 0:01:30 lr: 0.000066 grad: 0.0904 (0.0887) loss: 0.8207 (0.8237) time: 0.1744 data: 0.0882 max mem: 9390 +Train: [50] [5800/6250] eta: 0:01:13 lr: 0.000066 grad: 0.0889 (0.0888) loss: 0.8216 (0.8236) time: 0.1804 data: 0.0910 max mem: 9390 +Train: [50] [5900/6250] eta: 0:00:57 lr: 0.000066 grad: 0.0957 (0.0889) loss: 0.8105 (0.8236) time: 0.1613 data: 0.0666 max mem: 9390 +Train: [50] [6000/6250] eta: 0:00:41 lr: 0.000066 grad: 0.0875 (0.0890) loss: 0.8169 (0.8235) time: 0.1596 data: 0.0661 max mem: 9390 +Train: [50] [6100/6250] eta: 0:00:24 lr: 0.000066 grad: 0.0903 (0.0891) loss: 0.8168 (0.8235) time: 0.1876 data: 0.1034 max mem: 9390 +Train: [50] [6200/6250] eta: 0:00:08 lr: 0.000066 grad: 0.0872 (0.0891) loss: 0.8220 (0.8234) time: 0.1614 data: 0.0689 max mem: 9390 +Train: [50] [6249/6250] eta: 0:00:00 lr: 0.000066 grad: 0.0914 (0.0891) loss: 0.8164 (0.8234) time: 0.1635 data: 0.0763 max mem: 9390 +Train: [50] Total time: 0:17:12 (0.1652 s / it) +Averaged stats: lr: 0.000066 grad: 0.0914 (0.0891) loss: 0.8164 (0.8234) +Eval (hcp-train-subset): [50] [ 0/62] eta: 0:06:24 loss: 0.8468 (0.8468) time: 6.2065 data: 6.1763 max mem: 9390 +Eval (hcp-train-subset): [50] [61/62] eta: 0:00:00 loss: 0.8374 (0.8384) time: 0.1701 data: 0.1421 max mem: 9390 +Eval (hcp-train-subset): [50] Total time: 0:00:16 (0.2640 s / it) +Averaged stats (hcp-train-subset): loss: 0.8374 (0.8384) +Eval (hcp-val): [50] [ 0/62] eta: 0:06:01 loss: 0.8387 (0.8387) time: 5.8226 data: 5.7904 max mem: 9390 +Eval (hcp-val): [50] [61/62] eta: 0:00:00 loss: 0.8352 (0.8363) time: 0.1494 data: 0.1236 max mem: 9390 +Eval (hcp-val): [50] Total time: 0:00:15 (0.2452 s / it) +Averaged stats (hcp-val): loss: 0.8352 (0.8363) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +Train: [51] [ 0/6250] eta: 10:46:55 lr: 0.000066 grad: 0.0700 (0.0700) loss: 0.8592 (0.8592) time: 6.2104 data: 6.0145 max mem: 9390 +Train: [51] [ 100/6250] eta: 0:28:22 lr: 0.000066 grad: 0.0864 (0.0951) loss: 0.8186 (0.8280) time: 0.2113 data: 0.1126 max mem: 9390 +Train: [51] [ 200/6250] eta: 0:24:12 lr: 0.000066 grad: 0.0848 (0.0923) loss: 0.8377 (0.8289) time: 0.2102 data: 0.1002 max mem: 9390 +Train: [51] [ 300/6250] eta: 0:22:36 lr: 0.000065 grad: 0.0785 (0.0904) loss: 0.8229 (0.8294) time: 0.1892 data: 0.0832 max mem: 9390 +Train: [51] [ 400/6250] eta: 0:21:34 lr: 0.000065 grad: 0.0878 (0.0907) loss: 0.8217 (0.8278) time: 0.2000 data: 0.0976 max mem: 9390 +Train: [51] [ 500/6250] eta: 0:21:02 lr: 0.000065 grad: 0.0793 (0.0900) loss: 0.8314 (0.8274) time: 0.1639 data: 0.0591 max mem: 9390 +Train: [51] [ 600/6250] eta: 0:20:21 lr: 0.000065 grad: 0.0804 (0.0900) loss: 0.8301 (0.8273) time: 0.2075 data: 0.1017 max mem: 9390 +Train: [51] [ 700/6250] eta: 0:19:36 lr: 0.000065 grad: 0.0794 (0.0895) loss: 0.8219 (0.8270) time: 0.1996 data: 0.1028 max mem: 9390 +Train: [51] [ 800/6250] eta: 0:18:51 lr: 0.000065 grad: 0.0793 (0.0885) loss: 0.8275 (0.8270) time: 0.1647 data: 0.0727 max mem: 9390 +Train: [51] [ 900/6250] eta: 0:18:12 lr: 0.000065 grad: 0.0848 (0.0883) loss: 0.8219 (0.8265) time: 0.1715 data: 0.0715 max mem: 9390 +Train: [51] [1000/6250] eta: 0:17:29 lr: 0.000065 grad: 0.0828 (0.0881) loss: 0.8249 (0.8262) time: 0.1605 data: 0.0793 max mem: 9390 +Train: [51] [1100/6250] eta: 0:16:56 lr: 0.000065 grad: 0.0898 (0.0880) loss: 0.8201 (0.8258) time: 0.1663 data: 0.0758 max mem: 9390 +Train: [51] [1200/6250] eta: 0:16:21 lr: 0.000065 grad: 0.0853 (0.0882) loss: 0.8240 (0.8255) time: 0.1589 data: 0.0715 max mem: 9390 +Train: [51] [1300/6250] eta: 0:15:49 lr: 0.000065 grad: 0.0886 (0.0882) loss: 0.8212 (0.8251) time: 0.1560 data: 0.0633 max mem: 9390 +Train: [51] [1400/6250] eta: 0:15:18 lr: 0.000065 grad: 0.0843 (0.0881) loss: 0.8198 (0.8247) time: 0.1660 data: 0.0769 max mem: 9390 +Train: [51] [1500/6250] eta: 0:14:54 lr: 0.000065 grad: 0.0825 (0.0880) loss: 0.8267 (0.8244) time: 0.1599 data: 0.0756 max mem: 9390 +Train: [51] [1600/6250] eta: 0:14:32 lr: 0.000065 grad: 0.0881 (0.0879) loss: 0.8205 (0.8242) time: 0.1687 data: 0.0839 max mem: 9390 +Train: [51] [1700/6250] eta: 0:14:08 lr: 0.000065 grad: 0.0863 (0.0880) loss: 0.8171 (0.8239) time: 0.1507 data: 0.0616 max mem: 9390 +Train: [51] [1800/6250] eta: 0:13:43 lr: 0.000065 grad: 0.0849 (0.0881) loss: 0.8181 (0.8236) time: 0.1568 data: 0.0767 max mem: 9390 +Train: [51] [1900/6250] eta: 0:13:19 lr: 0.000065 grad: 0.0840 (0.0880) loss: 0.8177 (0.8234) time: 0.1691 data: 0.0822 max mem: 9390 +Train: [51] [2000/6250] eta: 0:12:57 lr: 0.000065 grad: 0.0868 (0.0881) loss: 0.8173 (0.8234) time: 0.1603 data: 0.0794 max mem: 9390 +Train: [51] [2100/6250] eta: 0:12:37 lr: 0.000065 grad: 0.0832 (0.0881) loss: 0.8247 (0.8232) time: 0.1481 data: 0.0538 max mem: 9390 +Train: [51] [2200/6250] eta: 0:12:16 lr: 0.000065 grad: 0.0862 (0.0882) loss: 0.8131 (0.8230) time: 0.1857 data: 0.1013 max mem: 9390 +Train: [51] [2300/6250] eta: 0:11:53 lr: 0.000065 grad: 0.0889 (0.0882) loss: 0.8179 (0.8229) time: 0.1522 data: 0.0572 max mem: 9390 +Train: [51] [2400/6250] eta: 0:11:31 lr: 0.000065 grad: 0.0870 (0.0882) loss: 0.8213 (0.8228) time: 0.1581 data: 0.0669 max mem: 9390 +Train: [51] [2500/6250] eta: 0:11:10 lr: 0.000065 grad: 0.0859 (0.0883) loss: 0.8193 (0.8227) time: 0.1530 data: 0.0582 max mem: 9390 +Train: [51] [2600/6250] eta: 0:10:49 lr: 0.000065 grad: 0.0851 (0.0883) loss: 0.8178 (0.8226) time: 0.1665 data: 0.0805 max mem: 9390 +Train: [51] [2700/6250] eta: 0:10:28 lr: 0.000065 grad: 0.0806 (0.0883) loss: 0.8209 (0.8226) time: 0.1497 data: 0.0579 max mem: 9390 +Train: [51] [2800/6250] eta: 0:10:08 lr: 0.000065 grad: 0.0883 (0.0883) loss: 0.8266 (0.8227) time: 0.1561 data: 0.0610 max mem: 9390 +Train: [51] [2900/6250] eta: 0:09:48 lr: 0.000065 grad: 0.0871 (0.0883) loss: 0.8233 (0.8228) time: 0.1508 data: 0.0585 max mem: 9390 +Train: [51] [3000/6250] eta: 0:09:29 lr: 0.000065 grad: 0.0850 (0.0883) loss: 0.8245 (0.8229) time: 0.1591 data: 0.0737 max mem: 9390 +Train: [51] [3100/6250] eta: 0:09:11 lr: 0.000065 grad: 0.0833 (0.0883) loss: 0.8268 (0.8229) time: 0.1879 data: 0.1082 max mem: 9390 +Train: [51] [3200/6250] eta: 0:08:53 lr: 0.000065 grad: 0.0835 (0.0886) loss: 0.8217 (0.8229) time: 0.1814 data: 0.0889 max mem: 9390 +Train: [51] [3300/6250] eta: 0:08:34 lr: 0.000065 grad: 0.0888 (0.0887) loss: 0.8187 (0.8228) time: 0.1772 data: 0.0919 max mem: 9390 +Train: [51] [3400/6250] eta: 0:08:16 lr: 0.000064 grad: 0.0873 (0.0888) loss: 0.8151 (0.8227) time: 0.1616 data: 0.0768 max mem: 9390 +Train: [51] [3500/6250] eta: 0:07:58 lr: 0.000064 grad: 0.0912 (0.0888) loss: 0.8187 (0.8227) time: 0.1704 data: 0.0794 max mem: 9390 +Train: [51] [3600/6250] eta: 0:07:40 lr: 0.000064 grad: 0.0888 (0.0889) loss: 0.8159 (0.8226) time: 0.1414 data: 0.0524 max mem: 9390 +Train: [51] [3700/6250] eta: 0:07:21 lr: 0.000064 grad: 0.0894 (0.0890) loss: 0.8262 (0.8226) time: 0.1644 data: 0.0700 max mem: 9390 +Train: [51] [3800/6250] eta: 0:07:03 lr: 0.000064 grad: 0.0908 (0.0891) loss: 0.8181 (0.8226) time: 0.1520 data: 0.0616 max mem: 9390 +Train: [51] [3900/6250] eta: 0:06:44 lr: 0.000064 grad: 0.0897 (0.0891) loss: 0.8179 (0.8226) time: 0.1442 data: 0.0535 max mem: 9390 +Train: [51] [4000/6250] eta: 0:06:26 lr: 0.000064 grad: 0.0903 (0.0893) loss: 0.8202 (0.8225) time: 0.1495 data: 0.0551 max mem: 9390 +Train: [51] [4100/6250] eta: 0:06:08 lr: 0.000064 grad: 0.0893 (0.0893) loss: 0.8253 (0.8225) time: 0.1563 data: 0.0740 max mem: 9390 +Train: [51] [4200/6250] eta: 0:05:51 lr: 0.000064 grad: 0.0942 (0.0894) loss: 0.8203 (0.8225) time: 0.1762 data: 0.0896 max mem: 9390 +Train: [51] [4300/6250] eta: 0:05:33 lr: 0.000064 grad: 0.0913 (0.0894) loss: 0.8230 (0.8225) time: 0.1597 data: 0.0779 max mem: 9390 +Train: [51] [4400/6250] eta: 0:05:16 lr: 0.000064 grad: 0.0944 (0.0895) loss: 0.8226 (0.8225) time: 0.1570 data: 0.0674 max mem: 9390 +Train: [51] [4500/6250] eta: 0:04:58 lr: 0.000064 grad: 0.0858 (0.0894) loss: 0.8263 (0.8225) time: 0.1378 data: 0.0524 max mem: 9390 +Train: [51] [4600/6250] eta: 0:04:40 lr: 0.000064 grad: 0.0841 (0.0895) loss: 0.8252 (0.8225) time: 0.1501 data: 0.0554 max mem: 9390 +Train: [51] [4700/6250] eta: 0:04:23 lr: 0.000064 grad: 0.0879 (0.0894) loss: 0.8215 (0.8226) time: 0.1588 data: 0.0704 max mem: 9390 +Train: [51] [4800/6250] eta: 0:04:06 lr: 0.000064 grad: 0.0895 (0.0895) loss: 0.8178 (0.8225) time: 0.1442 data: 0.0498 max mem: 9390 +Train: [51] [4900/6250] eta: 0:03:49 lr: 0.000064 grad: 0.0851 (0.0895) loss: 0.8266 (0.8225) time: 0.1928 data: 0.1086 max mem: 9390 +Train: [51] [5000/6250] eta: 0:03:32 lr: 0.000064 grad: 0.0862 (0.0896) loss: 0.8213 (0.8224) time: 0.1689 data: 0.0864 max mem: 9390 +Train: [51] [5100/6250] eta: 0:03:14 lr: 0.000064 grad: 0.0897 (0.0896) loss: 0.8195 (0.8224) time: 0.1594 data: 0.0707 max mem: 9390 +Train: [51] [5200/6250] eta: 0:02:57 lr: 0.000064 grad: 0.0862 (0.0896) loss: 0.8210 (0.8223) time: 0.1628 data: 0.0755 max mem: 9390 +Train: [51] [5300/6250] eta: 0:02:40 lr: 0.000064 grad: 0.0916 (0.0897) loss: 0.8194 (0.8222) time: 0.1646 data: 0.0751 max mem: 9390 +Train: [51] [5400/6250] eta: 0:02:23 lr: 0.000064 grad: 0.0901 (0.0897) loss: 0.8155 (0.8221) time: 0.1735 data: 0.0864 max mem: 9390 +Train: [51] [5500/6250] eta: 0:02:06 lr: 0.000064 grad: 0.0916 (0.0897) loss: 0.8206 (0.8221) time: 0.1549 data: 0.0679 max mem: 9390 +Train: [51] [5600/6250] eta: 0:01:49 lr: 0.000064 grad: 0.0886 (0.0898) loss: 0.8213 (0.8221) time: 0.1498 data: 0.0583 max mem: 9390 +Train: [51] [5700/6250] eta: 0:01:32 lr: 0.000064 grad: 0.0912 (0.0899) loss: 0.8216 (0.8220) time: 0.1722 data: 0.0855 max mem: 9390 +Train: [51] [5800/6250] eta: 0:01:15 lr: 0.000064 grad: 0.0839 (0.0899) loss: 0.8232 (0.8220) time: 0.1434 data: 0.0493 max mem: 9390 +Train: [51] [5900/6250] eta: 0:00:58 lr: 0.000064 grad: 0.0871 (0.0899) loss: 0.8253 (0.8220) time: 0.1804 data: 0.0992 max mem: 9390 +Train: [51] [6000/6250] eta: 0:00:42 lr: 0.000064 grad: 0.0885 (0.0899) loss: 0.8189 (0.8220) time: 0.1729 data: 0.0771 max mem: 9390 +Train: [51] [6100/6250] eta: 0:00:25 lr: 0.000064 grad: 0.0906 (0.0900) loss: 0.8194 (0.8219) time: 0.1657 data: 0.0781 max mem: 9390 +Train: [51] [6200/6250] eta: 0:00:08 lr: 0.000064 grad: 0.0885 (0.0900) loss: 0.8200 (0.8219) time: 0.1693 data: 0.0881 max mem: 9390 +Train: [51] [6249/6250] eta: 0:00:00 lr: 0.000064 grad: 0.0864 (0.0900) loss: 0.8214 (0.8219) time: 0.1677 data: 0.0790 max mem: 9390 +Train: [51] Total time: 0:17:35 (0.1688 s / it) +Averaged stats: lr: 0.000064 grad: 0.0864 (0.0900) loss: 0.8214 (0.8219) +Eval (hcp-train-subset): [51] [ 0/62] eta: 0:03:11 loss: 0.8495 (0.8495) time: 3.0822 data: 2.9883 max mem: 9390 +Eval (hcp-train-subset): [51] [61/62] eta: 0:00:00 loss: 0.8378 (0.8386) time: 0.0972 data: 0.0717 max mem: 9390 +Eval (hcp-train-subset): [51] Total time: 0:00:15 (0.2530 s / it) +Averaged stats (hcp-train-subset): loss: 0.8378 (0.8386) +Eval (hcp-val): [51] [ 0/62] eta: 0:03:41 loss: 0.8355 (0.8355) time: 3.5770 data: 3.5007 max mem: 9390 +Eval (hcp-val): [51] [61/62] eta: 0:00:00 loss: 0.8358 (0.8362) time: 0.1361 data: 0.1106 max mem: 9390 +Eval (hcp-val): [51] Total time: 0:00:13 (0.2189 s / it) +Averaged stats (hcp-val): loss: 0.8358 (0.8362) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +Train: [52] [ 0/6250] eta: 10:09:59 lr: 0.000064 grad: nan (nan) loss: 0.8616 (0.8616) time: 5.8559 data: 5.7632 max mem: 9390 +Train: [52] [ 100/6250] eta: 0:24:39 lr: 0.000063 grad: 0.0827 (0.0923) loss: 0.8360 (0.8381) time: 0.1915 data: 0.0987 max mem: 9390 +Train: [52] [ 200/6250] eta: 0:21:15 lr: 0.000063 grad: 0.0889 (0.0915) loss: 0.8300 (0.8334) time: 0.1903 data: 0.1069 max mem: 9390 +Train: [52] [ 300/6250] eta: 0:19:53 lr: 0.000063 grad: 0.0841 (0.0917) loss: 0.8253 (0.8308) time: 0.1844 data: 0.0782 max mem: 9390 +Train: [52] [ 400/6250] eta: 0:19:09 lr: 0.000063 grad: 0.0853 (0.0911) loss: 0.8268 (0.8287) time: 0.1793 data: 0.0830 max mem: 9390 +Train: [52] [ 500/6250] eta: 0:18:32 lr: 0.000063 grad: 0.0837 (0.0907) loss: 0.8255 (0.8273) time: 0.1723 data: 0.0716 max mem: 9390 +Train: [52] [ 600/6250] eta: 0:18:00 lr: 0.000063 grad: 0.0824 (0.0900) loss: 0.8257 (0.8262) time: 0.2057 data: 0.1014 max mem: 9390 +Train: [52] [ 700/6250] eta: 0:17:22 lr: 0.000063 grad: 0.0878 (0.0896) loss: 0.8141 (0.8251) time: 0.1594 data: 0.0594 max mem: 9390 +Train: [52] [ 800/6250] eta: 0:16:52 lr: 0.000063 grad: 0.0859 (0.0895) loss: 0.8201 (0.8243) time: 0.1752 data: 0.0722 max mem: 9390 +Train: [52] [ 900/6250] eta: 0:16:25 lr: 0.000063 grad: 0.0882 (0.0892) loss: 0.8138 (0.8236) time: 0.1612 data: 0.0728 max mem: 9390 +Train: [52] [1000/6250] eta: 0:16:02 lr: 0.000063 grad: 0.0882 (0.0891) loss: 0.8202 (0.8233) time: 0.1461 data: 0.0521 max mem: 9390 +Train: [52] [1100/6250] eta: 0:15:33 lr: 0.000063 grad: 0.0839 (0.0890) loss: 0.8211 (0.8229) time: 0.1579 data: 0.0734 max mem: 9390 +Train: [52] [1200/6250] eta: 0:15:03 lr: 0.000063 grad: 0.0868 (0.0893) loss: 0.8186 (0.8224) time: 0.1679 data: 0.0755 max mem: 9390 +Train: [52] [1300/6250] eta: 0:14:37 lr: 0.000063 grad: 0.0823 (0.0894) loss: 0.8204 (0.8220) time: 0.1604 data: 0.0673 max mem: 9390 +Train: [52] [1400/6250] eta: 0:14:11 lr: 0.000063 grad: 0.0891 (0.0894) loss: 0.8223 (0.8219) time: 0.1458 data: 0.0572 max mem: 9390 +Train: [52] [1500/6250] eta: 0:13:48 lr: 0.000063 grad: 0.0825 (0.0893) loss: 0.8251 (0.8220) time: 0.1610 data: 0.0663 max mem: 9390 +Train: [52] [1600/6250] eta: 0:13:26 lr: 0.000063 grad: 0.0889 (0.0892) loss: 0.8222 (0.8220) time: 0.1810 data: 0.0913 max mem: 9390 +Train: [52] [1700/6250] eta: 0:13:04 lr: 0.000063 grad: 0.0861 (0.0892) loss: 0.8205 (0.8219) time: 0.1396 data: 0.0458 max mem: 9390 +Train: [52] [1800/6250] eta: 0:12:44 lr: 0.000063 grad: 0.0874 (0.0891) loss: 0.8235 (0.8218) time: 0.1424 data: 0.0582 max mem: 9390 +Train: [52] [1900/6250] eta: 0:12:24 lr: 0.000063 grad: 0.0892 (0.0892) loss: 0.8232 (0.8219) time: 0.1535 data: 0.0601 max mem: 9390 +Train: [52] [2000/6250] eta: 0:12:05 lr: 0.000063 grad: 0.0931 (0.0893) loss: 0.8238 (0.8220) time: 0.1713 data: 0.0848 max mem: 9390 +Train: [52] [2100/6250] eta: 0:11:45 lr: 0.000063 grad: 0.0858 (0.0892) loss: 0.8227 (0.8220) time: 0.1058 data: 0.0131 max mem: 9390 +Train: [52] [2200/6250] eta: 0:11:26 lr: 0.000063 grad: 0.0830 (0.0892) loss: 0.8243 (0.8220) time: 0.1335 data: 0.0507 max mem: 9390 +Train: [52] [2300/6250] eta: 0:11:08 lr: 0.000063 grad: 0.0873 (0.0892) loss: 0.8209 (0.8220) time: 0.1615 data: 0.0775 max mem: 9390 +Train: [52] [2400/6250] eta: 0:10:49 lr: 0.000063 grad: 0.0848 (0.0892) loss: 0.8245 (0.8219) time: 0.1741 data: 0.0950 max mem: 9390 +Train: [52] [2500/6250] eta: 0:10:32 lr: 0.000063 grad: 0.0854 (0.0892) loss: 0.8225 (0.8218) time: 0.1710 data: 0.0870 max mem: 9390 +Train: [52] [2600/6250] eta: 0:10:15 lr: 0.000063 grad: 0.0898 (0.0891) loss: 0.8224 (0.8218) time: 0.1570 data: 0.0646 max mem: 9390 +Train: [52] [2700/6250] eta: 0:09:58 lr: 0.000063 grad: 0.0848 (0.0892) loss: 0.8208 (0.8217) time: 0.1711 data: 0.0884 max mem: 9390 +Train: [52] [2800/6250] eta: 0:09:41 lr: 0.000063 grad: 0.0894 (0.0892) loss: 0.8177 (0.8216) time: 0.1819 data: 0.0969 max mem: 9390 +Train: [52] [2900/6250] eta: 0:09:24 lr: 0.000063 grad: 0.0870 (0.0893) loss: 0.8232 (0.8216) time: 0.1701 data: 0.0928 max mem: 9390 +Train: [52] [3000/6250] eta: 0:09:06 lr: 0.000063 grad: 0.0899 (0.0893) loss: 0.8137 (0.8214) time: 0.1615 data: 0.0837 max mem: 9390 +Train: [52] [3100/6250] eta: 0:08:49 lr: 0.000063 grad: 0.0905 (0.0894) loss: 0.8291 (0.8214) time: 0.1984 data: 0.1136 max mem: 9390 +Train: [52] [3200/6250] eta: 0:08:30 lr: 0.000062 grad: 0.0931 (0.0896) loss: 0.8200 (0.8212) time: 0.1509 data: 0.0603 max mem: 9390 +Train: [52] [3300/6250] eta: 0:08:13 lr: 0.000062 grad: 0.0919 (0.0897) loss: 0.8161 (0.8211) time: 0.1588 data: 0.0660 max mem: 9390 +Train: [52] [3400/6250] eta: 0:07:56 lr: 0.000062 grad: 0.0930 (0.0899) loss: 0.8164 (0.8209) time: 0.1540 data: 0.0663 max mem: 9390 +Train: [52] [3500/6250] eta: 0:07:38 lr: 0.000062 grad: 0.0905 (0.0900) loss: 0.8129 (0.8208) time: 0.1507 data: 0.0664 max mem: 9390 +Train: [52] [3600/6250] eta: 0:07:21 lr: 0.000062 grad: 0.0957 (0.0901) loss: 0.8215 (0.8208) time: 0.1572 data: 0.0651 max mem: 9390 +Train: [52] [3700/6250] eta: 0:07:04 lr: 0.000062 grad: 0.0899 (0.0902) loss: 0.8228 (0.8207) time: 0.1846 data: 0.1017 max mem: 9390 +Train: [52] [3800/6250] eta: 0:06:47 lr: 0.000062 grad: 0.0872 (0.0903) loss: 0.8185 (0.8207) time: 0.1958 data: 0.1055 max mem: 9390 +Train: [52] [3900/6250] eta: 0:06:30 lr: 0.000062 grad: 0.0900 (0.0904) loss: 0.8194 (0.8206) time: 0.1771 data: 0.0791 max mem: 9390 +Train: [52] [4000/6250] eta: 0:06:14 lr: 0.000062 grad: 0.0876 (0.0904) loss: 0.8207 (0.8206) time: 0.1705 data: 0.0826 max mem: 9390 +Train: [52] [4100/6250] eta: 0:05:57 lr: 0.000062 grad: 0.0914 (0.0905) loss: 0.8222 (0.8206) time: 0.1682 data: 0.0837 max mem: 9390 +Train: [52] [4200/6250] eta: 0:05:40 lr: 0.000062 grad: 0.0872 (0.0905) loss: 0.8140 (0.8205) time: 0.1355 data: 0.0420 max mem: 9390 +Train: [52] [4300/6250] eta: 0:05:24 lr: 0.000062 grad: 0.0884 (0.0906) loss: 0.8256 (0.8205) time: 0.1760 data: 0.0941 max mem: 9390 +Train: [52] [4400/6250] eta: 0:05:07 lr: 0.000062 grad: 0.0884 (0.0906) loss: 0.8213 (0.8205) time: 0.1792 data: 0.0976 max mem: 9390 +Train: [52] [4500/6250] eta: 0:04:51 lr: 0.000062 grad: 0.0887 (0.0906) loss: 0.8256 (0.8205) time: 0.1784 data: 0.0905 max mem: 9390 +Train: [52] [4600/6250] eta: 0:04:34 lr: 0.000062 grad: 0.0874 (0.0906) loss: 0.8198 (0.8205) time: 0.1509 data: 0.0685 max mem: 9390 +Train: [52] [4700/6250] eta: 0:04:18 lr: 0.000062 grad: 0.0890 (0.0907) loss: 0.8228 (0.8206) time: 0.1854 data: 0.0974 max mem: 9390 +Train: [52] [4800/6250] eta: 0:04:01 lr: 0.000062 grad: 0.0909 (0.0906) loss: 0.8193 (0.8206) time: 0.1684 data: 0.0835 max mem: 9390 +Train: [52] [4900/6250] eta: 0:03:44 lr: 0.000062 grad: 0.0881 (0.0906) loss: 0.8251 (0.8206) time: 0.1548 data: 0.0651 max mem: 9390 +Train: [52] [5000/6250] eta: 0:03:28 lr: 0.000062 grad: 0.0896 (0.0907) loss: 0.8211 (0.8206) time: 0.1658 data: 0.0845 max mem: 9390 +Train: [52] [5100/6250] eta: 0:03:11 lr: 0.000062 grad: 0.0898 (0.0907) loss: 0.8243 (0.8206) time: 0.1562 data: 0.0701 max mem: 9390 +Train: [52] [5200/6250] eta: 0:02:55 lr: 0.000062 grad: 0.0911 (0.0907) loss: 0.8213 (0.8207) time: 0.2397 data: 0.1481 max mem: 9390 +Train: [52] [5300/6250] eta: 0:02:37 lr: 0.000062 grad: 0.0894 (0.0908) loss: 0.8269 (0.8207) time: 0.1634 data: 0.0775 max mem: 9390 +Train: [52] [5400/6250] eta: 0:02:21 lr: 0.000062 grad: 0.0929 (0.0908) loss: 0.8210 (0.8207) time: 0.1715 data: 0.0860 max mem: 9390 +Train: [52] [5500/6250] eta: 0:02:04 lr: 0.000062 grad: 0.0878 (0.0908) loss: 0.8235 (0.8207) time: 0.1937 data: 0.1090 max mem: 9390 +Train: [52] [5600/6250] eta: 0:01:47 lr: 0.000062 grad: 0.0891 (0.0909) loss: 0.8154 (0.8207) time: 0.1621 data: 0.0832 max mem: 9390 +Train: [52] [5700/6250] eta: 0:01:31 lr: 0.000062 grad: 0.0885 (0.0909) loss: 0.8267 (0.8207) time: 0.1481 data: 0.0620 max mem: 9390 +Train: [52] [5800/6250] eta: 0:01:14 lr: 0.000062 grad: 0.0898 (0.0910) loss: 0.8203 (0.8207) time: 0.1585 data: 0.0743 max mem: 9390 +Train: [52] [5900/6250] eta: 0:00:58 lr: 0.000062 grad: 0.0925 (0.0911) loss: 0.8235 (0.8207) time: 0.1820 data: 0.0902 max mem: 9390 +Train: [52] [6000/6250] eta: 0:00:41 lr: 0.000062 grad: 0.0886 (0.0911) loss: 0.8255 (0.8207) time: 0.1591 data: 0.0709 max mem: 9390 +Train: [52] [6100/6250] eta: 0:00:24 lr: 0.000062 grad: 0.0869 (0.0912) loss: 0.8258 (0.8207) time: 0.1182 data: 0.0179 max mem: 9390 +Train: [52] [6200/6250] eta: 0:00:08 lr: 0.000061 grad: 0.0911 (0.0913) loss: 0.8236 (0.8207) time: 0.1657 data: 0.0839 max mem: 9390 +Train: [52] [6249/6250] eta: 0:00:00 lr: 0.000061 grad: 0.0958 (0.0913) loss: 0.8170 (0.8207) time: 0.1496 data: 0.0675 max mem: 9390 +Train: [52] Total time: 0:17:23 (0.1670 s / it) +Averaged stats: lr: 0.000061 grad: 0.0958 (0.0913) loss: 0.8170 (0.8207) +Eval (hcp-train-subset): [52] [ 0/62] eta: 0:05:27 loss: 0.8490 (0.8490) time: 5.2761 data: 5.2446 max mem: 9390 +Eval (hcp-train-subset): [52] [61/62] eta: 0:00:00 loss: 0.8375 (0.8383) time: 0.1519 data: 0.1261 max mem: 9390 +Eval (hcp-train-subset): [52] Total time: 0:00:15 (0.2423 s / it) +Averaged stats (hcp-train-subset): loss: 0.8375 (0.8383) +Eval (hcp-val): [52] [ 0/62] eta: 0:05:46 loss: 0.8320 (0.8320) time: 5.5815 data: 5.5500 max mem: 9390 +Eval (hcp-val): [52] [61/62] eta: 0:00:00 loss: 0.8360 (0.8368) time: 0.1577 data: 0.1326 max mem: 9390 +Eval (hcp-val): [52] Total time: 0:00:14 (0.2285 s / it) +Averaged stats (hcp-val): loss: 0.8360 (0.8368) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +Train: [53] [ 0/6250] eta: 7:52:50 lr: 0.000061 grad: 0.0544 (0.0544) loss: 0.8571 (0.8571) time: 4.5393 data: 4.2622 max mem: 9390 +Train: [53] [ 100/6250] eta: 0:24:40 lr: 0.000061 grad: 0.0880 (0.0983) loss: 0.8128 (0.8382) time: 0.1771 data: 0.0809 max mem: 9390 +Train: [53] [ 200/6250] eta: 0:21:33 lr: 0.000061 grad: 0.0913 (0.0976) loss: 0.8185 (0.8282) time: 0.1940 data: 0.0967 max mem: 9390 +Train: [53] [ 300/6250] eta: 0:19:45 lr: 0.000061 grad: 0.0842 (0.0956) loss: 0.8203 (0.8259) time: 0.1582 data: 0.0677 max mem: 9390 +Train: [53] [ 400/6250] eta: 0:19:28 lr: 0.000061 grad: 0.0832 (0.0941) loss: 0.8267 (0.8261) time: 0.2007 data: 0.1106 max mem: 9390 +Train: [53] [ 500/6250] eta: 0:19:08 lr: 0.000061 grad: 0.0879 (0.0932) loss: 0.8230 (0.8260) time: 0.1873 data: 0.1003 max mem: 9390 +Train: [53] [ 600/6250] eta: 0:18:38 lr: 0.000061 grad: 0.0827 (0.0925) loss: 0.8269 (0.8257) time: 0.1908 data: 0.0961 max mem: 9390 +Train: [53] [ 700/6250] eta: 0:18:13 lr: 0.000061 grad: 0.0887 (0.0922) loss: 0.8148 (0.8249) time: 0.2021 data: 0.1077 max mem: 9390 +Train: [53] [ 800/6250] eta: 0:17:38 lr: 0.000061 grad: 0.0925 (0.0923) loss: 0.8144 (0.8241) time: 0.1815 data: 0.0843 max mem: 9390 +Train: [53] [ 900/6250] eta: 0:17:19 lr: 0.000061 grad: 0.0936 (0.0922) loss: 0.8103 (0.8234) time: 0.2334 data: 0.1091 max mem: 9390 +Train: [53] [1000/6250] eta: 0:16:50 lr: 0.000061 grad: 0.0902 (0.0926) loss: 0.8162 (0.8226) time: 0.1758 data: 0.0871 max mem: 9390 +Train: [53] [1100/6250] eta: 0:16:22 lr: 0.000061 grad: 0.0906 (0.0928) loss: 0.8204 (0.8219) time: 0.1313 data: 0.0383 max mem: 9390 +Train: [53] [1200/6250] eta: 0:15:51 lr: 0.000061 grad: 0.0915 (0.0930) loss: 0.8153 (0.8213) time: 0.1470 data: 0.0640 max mem: 9390 +Train: [53] [1300/6250] eta: 0:15:26 lr: 0.000061 grad: 0.0874 (0.0932) loss: 0.8190 (0.8206) time: 0.1771 data: 0.0918 max mem: 9390 +Train: [53] [1400/6250] eta: 0:15:05 lr: 0.000061 grad: 0.0923 (0.0933) loss: 0.8114 (0.8201) time: 0.1839 data: 0.1021 max mem: 9390 +Train: [53] [1500/6250] eta: 0:14:43 lr: 0.000061 grad: 0.0870 (0.0935) loss: 0.8103 (0.8198) time: 0.1684 data: 0.0914 max mem: 9390 +Train: [53] [1600/6250] eta: 0:14:20 lr: 0.000061 grad: 0.0912 (0.0936) loss: 0.8088 (0.8193) time: 0.2006 data: 0.1222 max mem: 9390 +Train: [53] [1700/6250] eta: 0:13:55 lr: 0.000061 grad: 0.0923 (0.0936) loss: 0.8129 (0.8190) time: 0.1489 data: 0.0576 max mem: 9390 +Train: [53] [1800/6250] eta: 0:13:32 lr: 0.000061 grad: 0.0911 (0.0940) loss: 0.8158 (0.8187) time: 0.1763 data: 0.0883 max mem: 9390 +Train: [53] [1900/6250] eta: 0:13:08 lr: 0.000061 grad: 0.0884 (0.0940) loss: 0.8175 (0.8185) time: 0.1379 data: 0.0487 max mem: 9390 +Train: [53] [2000/6250] eta: 0:12:46 lr: 0.000061 grad: 0.0880 (0.0941) loss: 0.8174 (0.8183) time: 0.1552 data: 0.0628 max mem: 9390 +Train: [53] [2100/6250] eta: 0:12:25 lr: 0.000061 grad: 0.0926 (0.0942) loss: 0.8167 (0.8182) time: 0.1693 data: 0.0752 max mem: 9390 +Train: [53] [2200/6250] eta: 0:12:04 lr: 0.000061 grad: 0.0889 (0.0942) loss: 0.8197 (0.8181) time: 0.1682 data: 0.0756 max mem: 9390 +Train: [53] [2300/6250] eta: 0:11:45 lr: 0.000061 grad: 0.0892 (0.0942) loss: 0.8157 (0.8181) time: 0.1486 data: 0.0598 max mem: 9390 +Train: [53] [2400/6250] eta: 0:11:26 lr: 0.000061 grad: 0.0845 (0.0941) loss: 0.8186 (0.8180) time: 0.1798 data: 0.0926 max mem: 9390 +Train: [53] [2500/6250] eta: 0:11:05 lr: 0.000061 grad: 0.0924 (0.0941) loss: 0.8182 (0.8181) time: 0.1532 data: 0.0621 max mem: 9390 +Train: [53] [2600/6250] eta: 0:10:45 lr: 0.000061 grad: 0.0883 (0.0939) loss: 0.8177 (0.8181) time: 0.1512 data: 0.0718 max mem: 9390 +Train: [53] [2700/6250] eta: 0:10:26 lr: 0.000061 grad: 0.0879 (0.0938) loss: 0.8199 (0.8181) time: 0.1586 data: 0.0619 max mem: 9390 +Train: [53] [2800/6250] eta: 0:10:07 lr: 0.000061 grad: 0.0843 (0.0938) loss: 0.8208 (0.8182) time: 0.1480 data: 0.0622 max mem: 9390 +Train: [53] [2900/6250] eta: 0:09:49 lr: 0.000061 grad: 0.0875 (0.0937) loss: 0.8220 (0.8182) time: 0.1570 data: 0.0700 max mem: 9390 +Train: [53] [3000/6250] eta: 0:09:29 lr: 0.000060 grad: 0.0937 (0.0937) loss: 0.8173 (0.8182) time: 0.1393 data: 0.0480 max mem: 9390 +Train: [53] [3100/6250] eta: 0:09:09 lr: 0.000060 grad: 0.0885 (0.0937) loss: 0.8218 (0.8181) time: 0.1469 data: 0.0541 max mem: 9390 +Train: [53] [3200/6250] eta: 0:08:50 lr: 0.000060 grad: 0.0946 (0.0936) loss: 0.8225 (0.8181) time: 0.1607 data: 0.0728 max mem: 9390 +Train: [53] [3300/6250] eta: 0:08:32 lr: 0.000060 grad: 0.0869 (0.0935) loss: 0.8244 (0.8182) time: 0.1413 data: 0.0544 max mem: 9390 +Train: [53] [3400/6250] eta: 0:08:13 lr: 0.000060 grad: 0.0901 (0.0936) loss: 0.8138 (0.8182) time: 0.1563 data: 0.0703 max mem: 9390 +Train: [53] [3500/6250] eta: 0:07:55 lr: 0.000060 grad: 0.0892 (0.0936) loss: 0.8158 (0.8182) time: 0.1678 data: 0.0772 max mem: 9390 +Train: [53] [3600/6250] eta: 0:07:37 lr: 0.000060 grad: 0.0947 (0.0937) loss: 0.8157 (0.8181) time: 0.1789 data: 0.0907 max mem: 9390 +Train: [53] [3700/6250] eta: 0:07:18 lr: 0.000060 grad: 0.0887 (0.0937) loss: 0.8193 (0.8181) time: 0.1556 data: 0.0639 max mem: 9390 +Train: [53] [3800/6250] eta: 0:07:00 lr: 0.000060 grad: 0.0966 (0.0937) loss: 0.8188 (0.8181) time: 0.1289 data: 0.0373 max mem: 9390 +Train: [53] [3900/6250] eta: 0:06:42 lr: 0.000060 grad: 0.0885 (0.0939) loss: 0.8166 (0.8181) time: 0.1373 data: 0.0458 max mem: 9390 +Train: [53] [4000/6250] eta: 0:06:25 lr: 0.000060 grad: 0.0955 (0.0940) loss: 0.8193 (0.8181) time: 0.1768 data: 0.0946 max mem: 9390 +Train: [53] [4100/6250] eta: 0:06:07 lr: 0.000060 grad: 0.0924 (0.0940) loss: 0.8252 (0.8181) time: 0.1689 data: 0.0756 max mem: 9390 +Train: [53] [4200/6250] eta: 0:05:50 lr: 0.000060 grad: 0.0928 (0.0940) loss: 0.8219 (0.8182) time: 0.1655 data: 0.0780 max mem: 9390 +Train: [53] [4300/6250] eta: 0:05:32 lr: 0.000060 grad: 0.0895 (0.0939) loss: 0.8222 (0.8182) time: 0.1628 data: 0.0768 max mem: 9390 +Train: [53] [4400/6250] eta: 0:05:15 lr: 0.000060 grad: 0.0965 (0.0941) loss: 0.8188 (0.8183) time: 0.1602 data: 0.0709 max mem: 9390 +Train: [53] [4500/6250] eta: 0:04:57 lr: 0.000060 grad: 0.0948 (0.0942) loss: 0.8234 (0.8183) time: 0.1867 data: 0.1013 max mem: 9390 +Train: [53] [4600/6250] eta: 0:04:40 lr: 0.000060 grad: 0.0956 (0.0943) loss: 0.8189 (0.8183) time: 0.1660 data: 0.0727 max mem: 9390 +Train: [53] [4700/6250] eta: 0:04:23 lr: 0.000060 grad: 0.0922 (0.0943) loss: 0.8201 (0.8183) time: 0.1736 data: 0.0890 max mem: 9390 +Train: [53] [4800/6250] eta: 0:04:05 lr: 0.000060 grad: 0.0887 (0.0946) loss: 0.8230 (0.8183) time: 0.1667 data: 0.0862 max mem: 9390 +Train: [53] [4900/6250] eta: 0:03:48 lr: 0.000060 grad: 0.0941 (0.0948) loss: 0.8182 (0.8182) time: 0.1461 data: 0.0540 max mem: 9390 +Train: [53] [5000/6250] eta: 0:03:31 lr: 0.000060 grad: 0.0997 (0.0948) loss: 0.8182 (0.8183) time: 0.1570 data: 0.0745 max mem: 9390 +Train: [53] [5100/6250] eta: 0:03:14 lr: 0.000060 grad: 0.0910 (0.0949) loss: 0.8212 (0.8183) time: 0.1701 data: 0.0845 max mem: 9390 +Train: [53] [5200/6250] eta: 0:02:57 lr: 0.000060 grad: 0.0890 (0.0948) loss: 0.8187 (0.8183) time: 0.1609 data: 0.0807 max mem: 9390 +Train: [53] [5300/6250] eta: 0:02:40 lr: 0.000060 grad: 0.0958 (0.0949) loss: 0.8222 (0.8183) time: 0.1581 data: 0.0710 max mem: 9390 +Train: [53] [5400/6250] eta: 0:02:23 lr: 0.000060 grad: 0.0925 (0.0949) loss: 0.8169 (0.8182) time: 0.1773 data: 0.0965 max mem: 9390 +Train: [53] [5500/6250] eta: 0:02:06 lr: 0.000060 grad: 0.0878 (0.0949) loss: 0.8257 (0.8183) time: 0.1440 data: 0.0551 max mem: 9390 +Train: [53] [5600/6250] eta: 0:01:49 lr: 0.000060 grad: 0.0873 (0.0949) loss: 0.8227 (0.8184) time: 0.1470 data: 0.0579 max mem: 9390 +Train: [53] [5700/6250] eta: 0:01:32 lr: 0.000060 grad: 0.0873 (0.0949) loss: 0.8205 (0.8185) time: 0.1787 data: 0.0928 max mem: 9390 +Train: [53] [5800/6250] eta: 0:01:15 lr: 0.000060 grad: 0.0917 (0.0949) loss: 0.8182 (0.8185) time: 0.1806 data: 0.0911 max mem: 9390 +Train: [53] [5900/6250] eta: 0:00:59 lr: 0.000060 grad: 0.0898 (0.0948) loss: 0.8280 (0.8186) time: 0.2079 data: 0.1219 max mem: 9390 +Train: [53] [6000/6250] eta: 0:00:42 lr: 0.000059 grad: 0.0925 (0.0948) loss: 0.8269 (0.8186) time: 0.1429 data: 0.0589 max mem: 9390 +Train: [53] [6100/6250] eta: 0:00:25 lr: 0.000059 grad: 0.0949 (0.0948) loss: 0.8172 (0.8186) time: 0.1749 data: 0.0892 max mem: 9390 +Train: [53] [6200/6250] eta: 0:00:08 lr: 0.000059 grad: 0.0896 (0.0948) loss: 0.8226 (0.8187) time: 0.1652 data: 0.0746 max mem: 9390 +Train: [53] [6249/6250] eta: 0:00:00 lr: 0.000059 grad: 0.0880 (0.0947) loss: 0.8231 (0.8187) time: 0.1717 data: 0.0860 max mem: 9390 +Train: [53] Total time: 0:17:39 (0.1695 s / it) +Averaged stats: lr: 0.000059 grad: 0.0880 (0.0947) loss: 0.8231 (0.8187) +Eval (hcp-train-subset): [53] [ 0/62] eta: 0:03:58 loss: 0.8505 (0.8505) time: 3.8526 data: 3.7803 max mem: 9390 +Eval (hcp-train-subset): [53] [61/62] eta: 0:00:00 loss: 0.8351 (0.8363) time: 0.1594 data: 0.1339 max mem: 9390 +Eval (hcp-train-subset): [53] Total time: 0:00:15 (0.2426 s / it) +Averaged stats (hcp-train-subset): loss: 0.8351 (0.8363) +Eval (hcp-val): [53] [ 0/62] eta: 0:04:29 loss: 0.8355 (0.8355) time: 4.3509 data: 4.3136 max mem: 9390 +Eval (hcp-val): [53] [61/62] eta: 0:00:00 loss: 0.8328 (0.8346) time: 0.1459 data: 0.1206 max mem: 9390 +Eval (hcp-val): [53] Total time: 0:00:13 (0.2166 s / it) +Averaged stats (hcp-val): loss: 0.8328 (0.8346) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +Train: [54] [ 0/6250] eta: 11:11:51 lr: 0.000059 grad: 0.1427 (0.1427) loss: 0.8294 (0.8294) time: 6.4499 data: 6.3251 max mem: 9390 +Train: [54] [ 100/6250] eta: 0:24:52 lr: 0.000059 grad: 0.0858 (0.0903) loss: 0.8269 (0.8363) time: 0.2377 data: 0.1456 max mem: 9390 +Train: [54] [ 200/6250] eta: 0:21:55 lr: 0.000059 grad: 0.0854 (0.0885) loss: 0.8420 (0.8346) time: 0.1717 data: 0.0840 max mem: 9390 +Train: [54] [ 300/6250] eta: 0:20:23 lr: 0.000059 grad: 0.0869 (0.0882) loss: 0.8366 (0.8352) time: 0.1588 data: 0.0719 max mem: 9390 +Train: [54] [ 400/6250] eta: 0:19:41 lr: 0.000059 grad: 0.0846 (0.0885) loss: 0.8298 (0.8351) time: 0.1917 data: 0.1026 max mem: 9390 +Train: [54] [ 500/6250] eta: 0:18:56 lr: 0.000059 grad: 0.0887 (0.0885) loss: 0.8317 (0.8341) time: 0.1742 data: 0.0731 max mem: 9390 +Train: [54] [ 600/6250] eta: 0:18:10 lr: 0.000059 grad: 0.0830 (0.0886) loss: 0.8201 (0.8328) time: 0.1812 data: 0.0863 max mem: 9390 +Train: [54] [ 700/6250] eta: 0:17:23 lr: 0.000059 grad: 0.0897 (0.0884) loss: 0.8231 (0.8320) time: 0.1619 data: 0.0601 max mem: 9390 +Train: [54] [ 800/6250] eta: 0:16:45 lr: 0.000059 grad: 0.0801 (0.0882) loss: 0.8301 (0.8316) time: 0.1547 data: 0.0483 max mem: 9390 +Train: [54] [ 900/6250] eta: 0:16:21 lr: 0.000059 grad: 0.0882 (0.0884) loss: 0.8209 (0.8307) time: 0.1935 data: 0.1029 max mem: 9390 +Train: [54] [1000/6250] eta: 0:16:04 lr: 0.000059 grad: 0.0904 (0.0886) loss: 0.8212 (0.8299) time: 0.1498 data: 0.0573 max mem: 9390 +Train: [54] [1100/6250] eta: 0:16:08 lr: 0.000059 grad: 0.0861 (0.0887) loss: 0.8278 (0.8293) time: 0.2049 data: 0.1238 max mem: 9390 +Train: [54] [1200/6250] eta: 0:15:59 lr: 0.000059 grad: 0.0852 (0.0888) loss: 0.8283 (0.8287) time: 0.1462 data: 0.0552 max mem: 9390 +Train: [54] [1300/6250] eta: 0:15:41 lr: 0.000059 grad: 0.0892 (0.0891) loss: 0.8199 (0.8282) time: 0.1931 data: 0.1126 max mem: 9390 +Train: [54] [1400/6250] eta: 0:15:23 lr: 0.000059 grad: 0.0897 (0.0893) loss: 0.8207 (0.8278) time: 0.1690 data: 0.0837 max mem: 9390 +Train: [54] [1500/6250] eta: 0:15:07 lr: 0.000059 grad: 0.0933 (0.0894) loss: 0.8195 (0.8275) time: 0.1681 data: 0.0711 max mem: 9390 +Train: [54] [1600/6250] eta: 0:14:45 lr: 0.000059 grad: 0.0879 (0.0894) loss: 0.8236 (0.8273) time: 0.1687 data: 0.0796 max mem: 9390 +Train: [54] [1700/6250] eta: 0:14:20 lr: 0.000059 grad: 0.0890 (0.0896) loss: 0.8240 (0.8271) time: 0.1401 data: 0.0451 max mem: 9390 +Train: [54] [1800/6250] eta: 0:13:54 lr: 0.000059 grad: 0.0900 (0.0900) loss: 0.8208 (0.8267) time: 0.1444 data: 0.0591 max mem: 9390 +Train: [54] [1900/6250] eta: 0:13:31 lr: 0.000059 grad: 0.0939 (0.0902) loss: 0.8233 (0.8265) time: 0.1892 data: 0.0976 max mem: 9390 +Train: [54] [2000/6250] eta: 0:13:07 lr: 0.000059 grad: 0.0937 (0.0903) loss: 0.8212 (0.8263) time: 0.1794 data: 0.0986 max mem: 9390 +Train: [54] [2100/6250] eta: 0:12:45 lr: 0.000059 grad: 0.0924 (0.0906) loss: 0.8252 (0.8260) time: 0.1536 data: 0.0612 max mem: 9390 +Train: [54] [2200/6250] eta: 0:12:23 lr: 0.000059 grad: 0.0896 (0.0908) loss: 0.8217 (0.8258) time: 0.1618 data: 0.0677 max mem: 9390 +Train: [54] [2300/6250] eta: 0:12:02 lr: 0.000059 grad: 0.0972 (0.0909) loss: 0.8180 (0.8256) time: 0.1799 data: 0.0931 max mem: 9390 +Train: [54] [2400/6250] eta: 0:11:40 lr: 0.000059 grad: 0.0883 (0.0911) loss: 0.8242 (0.8255) time: 0.1585 data: 0.0621 max mem: 9390 +Train: [54] [2500/6250] eta: 0:11:20 lr: 0.000059 grad: 0.0927 (0.0912) loss: 0.8210 (0.8253) time: 0.1770 data: 0.0876 max mem: 9390 +Train: [54] [2600/6250] eta: 0:10:58 lr: 0.000059 grad: 0.0942 (0.0913) loss: 0.8188 (0.8252) time: 0.1483 data: 0.0594 max mem: 9390 +Train: [54] [2700/6250] eta: 0:10:38 lr: 0.000059 grad: 0.0945 (0.0914) loss: 0.8189 (0.8250) time: 0.1545 data: 0.0657 max mem: 9390 +Train: [54] [2800/6250] eta: 0:10:18 lr: 0.000058 grad: 0.0899 (0.0915) loss: 0.8172 (0.8249) time: 0.1614 data: 0.0619 max mem: 9390 +Train: [54] [2900/6250] eta: 0:09:58 lr: 0.000058 grad: 0.0926 (0.0918) loss: 0.8182 (0.8247) time: 0.1454 data: 0.0492 max mem: 9390 +Train: [54] [3000/6250] eta: 0:09:38 lr: 0.000058 grad: 0.0901 (0.0919) loss: 0.8168 (0.8245) time: 0.1472 data: 0.0506 max mem: 9390 +Train: [54] [3100/6250] eta: 0:09:18 lr: 0.000058 grad: 0.0906 (0.0920) loss: 0.8181 (0.8243) time: 0.1419 data: 0.0422 max mem: 9390 +Train: [54] [3200/6250] eta: 0:08:59 lr: 0.000058 grad: 0.0941 (0.0921) loss: 0.8274 (0.8242) time: 0.1991 data: 0.1205 max mem: 9390 +Train: [54] [3300/6250] eta: 0:08:40 lr: 0.000058 grad: 0.0876 (0.0922) loss: 0.8220 (0.8241) time: 0.1651 data: 0.0703 max mem: 9390 +Train: [54] [3400/6250] eta: 0:08:22 lr: 0.000058 grad: 0.0945 (0.0923) loss: 0.8184 (0.8240) time: 0.1765 data: 0.0906 max mem: 9390 +Train: [54] [3500/6250] eta: 0:08:03 lr: 0.000058 grad: 0.0944 (0.0924) loss: 0.8194 (0.8239) time: 0.1676 data: 0.0788 max mem: 9390 +Train: [54] [3600/6250] eta: 0:07:44 lr: 0.000058 grad: 0.0867 (0.0924) loss: 0.8220 (0.8239) time: 0.1622 data: 0.0734 max mem: 9390 +Train: [54] [3700/6250] eta: 0:07:26 lr: 0.000058 grad: 0.0863 (0.0924) loss: 0.8222 (0.8239) time: 0.1776 data: 0.0875 max mem: 9390 +Train: [54] [3800/6250] eta: 0:07:08 lr: 0.000058 grad: 0.0879 (0.0923) loss: 0.8228 (0.8239) time: 0.1772 data: 0.0874 max mem: 9390 +Train: [54] [3900/6250] eta: 0:06:50 lr: 0.000058 grad: 0.0845 (0.0922) loss: 0.8216 (0.8239) time: 0.1625 data: 0.0717 max mem: 9390 +Train: [54] [4000/6250] eta: 0:06:31 lr: 0.000058 grad: 0.0923 (0.0922) loss: 0.8253 (0.8238) time: 0.1589 data: 0.0648 max mem: 9390 +Train: [54] [4100/6250] eta: 0:06:13 lr: 0.000058 grad: 0.0890 (0.0923) loss: 0.8261 (0.8238) time: 0.1594 data: 0.0708 max mem: 9390 +Train: [54] [4200/6250] eta: 0:05:55 lr: 0.000058 grad: 0.0929 (0.0924) loss: 0.8188 (0.8236) time: 0.1684 data: 0.0750 max mem: 9390 +Train: [54] [4300/6250] eta: 0:05:37 lr: 0.000058 grad: 0.0903 (0.0925) loss: 0.8231 (0.8235) time: 0.1665 data: 0.0854 max mem: 9390 +Train: [54] [4400/6250] eta: 0:05:20 lr: 0.000058 grad: 0.0951 (0.0926) loss: 0.8175 (0.8234) time: 0.1500 data: 0.0612 max mem: 9390 +Train: [54] [4500/6250] eta: 0:05:02 lr: 0.000058 grad: 0.0931 (0.0927) loss: 0.8118 (0.8232) time: 0.1561 data: 0.0617 max mem: 9390 +Train: [54] [4600/6250] eta: 0:04:44 lr: 0.000058 grad: 0.0962 (0.0928) loss: 0.8212 (0.8231) time: 0.1613 data: 0.0730 max mem: 9390 +Train: [54] [4700/6250] eta: 0:04:27 lr: 0.000058 grad: 0.0970 (0.0929) loss: 0.8111 (0.8230) time: 0.1483 data: 0.0605 max mem: 9390 +Train: [54] [4800/6250] eta: 0:04:09 lr: 0.000058 grad: 0.0987 (0.0930) loss: 0.8151 (0.8228) time: 0.1551 data: 0.0680 max mem: 9390 +Train: [54] [4900/6250] eta: 0:03:52 lr: 0.000058 grad: 0.0917 (0.0931) loss: 0.8210 (0.8227) time: 0.1639 data: 0.0757 max mem: 9390 +Train: [54] [5000/6250] eta: 0:03:34 lr: 0.000058 grad: 0.0965 (0.0932) loss: 0.8224 (0.8226) time: 0.1557 data: 0.0683 max mem: 9390 +Train: [54] [5100/6250] eta: 0:03:17 lr: 0.000058 grad: 0.0944 (0.0933) loss: 0.8159 (0.8226) time: 0.1729 data: 0.0814 max mem: 9390 +Train: [54] [5200/6250] eta: 0:02:59 lr: 0.000058 grad: 0.0967 (0.0934) loss: 0.8227 (0.8225) time: 0.1560 data: 0.0605 max mem: 9390 +Train: [54] [5300/6250] eta: 0:02:42 lr: 0.000058 grad: 0.0921 (0.0935) loss: 0.8217 (0.8224) time: 0.2008 data: 0.1187 max mem: 9390 +Train: [54] [5400/6250] eta: 0:02:25 lr: 0.000058 grad: 0.0994 (0.0936) loss: 0.8213 (0.8224) time: 0.1695 data: 0.0841 max mem: 9390 +Train: [54] [5500/6250] eta: 0:02:08 lr: 0.000058 grad: 0.0959 (0.0936) loss: 0.8154 (0.8224) time: 0.1605 data: 0.0761 max mem: 9390 +Train: [54] [5600/6250] eta: 0:01:51 lr: 0.000058 grad: 0.0973 (0.0937) loss: 0.8177 (0.8223) time: 0.1608 data: 0.0724 max mem: 9390 +Train: [54] [5700/6250] eta: 0:01:33 lr: 0.000058 grad: 0.0944 (0.0938) loss: 0.8187 (0.8222) time: 0.1667 data: 0.0739 max mem: 9390 +Train: [54] [5800/6250] eta: 0:01:16 lr: 0.000057 grad: 0.0967 (0.0938) loss: 0.8144 (0.8222) time: 0.1652 data: 0.0793 max mem: 9390 +Train: [54] [5900/6250] eta: 0:00:59 lr: 0.000057 grad: 0.0972 (0.0939) loss: 0.8162 (0.8221) time: 0.1777 data: 0.0934 max mem: 9390 +Train: [54] [6000/6250] eta: 0:00:42 lr: 0.000057 grad: 0.0954 (0.0940) loss: 0.8154 (0.8220) time: 0.1475 data: 0.0599 max mem: 9390 +Train: [54] [6100/6250] eta: 0:00:25 lr: 0.000057 grad: 0.0986 (0.0941) loss: 0.8157 (0.8218) time: 0.1696 data: 0.0766 max mem: 9390 +Train: [54] [6200/6250] eta: 0:00:08 lr: 0.000057 grad: 0.1000 (0.0942) loss: 0.8142 (0.8217) time: 0.2028 data: 0.1073 max mem: 9390 +Train: [54] [6249/6250] eta: 0:00:00 lr: 0.000057 grad: 0.0975 (0.0943) loss: 0.8151 (0.8217) time: 0.1818 data: 0.1013 max mem: 9390 +Train: [54] Total time: 0:17:54 (0.1720 s / it) +Averaged stats: lr: 0.000057 grad: 0.0975 (0.0943) loss: 0.8151 (0.8217) +Eval (hcp-train-subset): [54] [ 0/62] eta: 0:05:52 loss: 0.8494 (0.8494) time: 5.6866 data: 5.6556 max mem: 9390 +Eval (hcp-train-subset): [54] [61/62] eta: 0:00:00 loss: 0.8356 (0.8369) time: 0.1403 data: 0.1138 max mem: 9390 +Eval (hcp-train-subset): [54] Total time: 0:00:15 (0.2504 s / it) +Averaged stats (hcp-train-subset): loss: 0.8356 (0.8369) +Making plots (hcp-train-subset): example=49 +Eval (hcp-val): [54] [ 0/62] eta: 0:05:09 loss: 0.8334 (0.8334) time: 4.9894 data: 4.9583 max mem: 9390 +Eval (hcp-val): [54] [61/62] eta: 0:00:00 loss: 0.8333 (0.8352) time: 0.1530 data: 0.1275 max mem: 9390 +Eval (hcp-val): [54] Total time: 0:00:14 (0.2263 s / it) +Averaged stats (hcp-val): loss: 0.8333 (0.8352) +Making plots (hcp-val): example=31 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +Train: [55] [ 0/6250] eta: 8:42:52 lr: 0.000057 grad: 0.3649 (0.3649) loss: 0.8396 (0.8396) time: 5.0197 data: 4.8252 max mem: 9390 +Train: [55] [ 100/6250] eta: 0:25:55 lr: 0.000057 grad: 0.0935 (0.1054) loss: 0.8376 (0.8358) time: 0.1828 data: 0.0899 max mem: 9390 +Train: [55] [ 200/6250] eta: 0:21:23 lr: 0.000057 grad: 0.0869 (0.0988) loss: 0.8222 (0.8319) time: 0.1868 data: 0.0912 max mem: 9390 +Train: [55] [ 300/6250] eta: 0:19:30 lr: 0.000057 grad: 0.0942 (0.0979) loss: 0.8132 (0.8279) time: 0.1907 data: 0.0968 max mem: 9390 +Train: [55] [ 400/6250] eta: 0:18:45 lr: 0.000057 grad: 0.0832 (0.0966) loss: 0.8208 (0.8262) time: 0.1647 data: 0.0513 max mem: 9390 +Train: [55] [ 500/6250] eta: 0:18:14 lr: 0.000057 grad: 0.0898 (0.0957) loss: 0.8229 (0.8255) time: 0.1874 data: 0.0926 max mem: 9390 +Train: [55] [ 600/6250] eta: 0:17:42 lr: 0.000057 grad: 0.0821 (0.0944) loss: 0.8300 (0.8253) time: 0.1834 data: 0.0817 max mem: 9390 +Train: [55] [ 700/6250] eta: 0:17:16 lr: 0.000057 grad: 0.0898 (0.0935) loss: 0.8235 (0.8253) time: 0.1758 data: 0.0635 max mem: 9390 +Train: [55] [ 800/6250] eta: 0:16:45 lr: 0.000057 grad: 0.0887 (0.0930) loss: 0.8272 (0.8252) time: 0.1969 data: 0.1062 max mem: 9390 +Train: [55] [ 900/6250] eta: 0:16:33 lr: 0.000057 grad: 0.0876 (0.0925) loss: 0.8286 (0.8253) time: 0.1874 data: 0.1029 max mem: 9390 +Train: [55] [1000/6250] eta: 0:16:20 lr: 0.000057 grad: 0.0819 (0.0922) loss: 0.8257 (0.8253) time: 0.1573 data: 0.0701 max mem: 9390 +Train: [55] [1100/6250] eta: 0:15:51 lr: 0.000057 grad: 0.0900 (0.0917) loss: 0.8255 (0.8253) time: 0.1364 data: 0.0443 max mem: 9390 +Train: [55] [1200/6250] eta: 0:15:30 lr: 0.000057 grad: 0.0941 (0.0913) loss: 0.8221 (0.8251) time: 0.1957 data: 0.1053 max mem: 9390 +Train: [55] [1300/6250] eta: 0:15:08 lr: 0.000057 grad: 0.0851 (0.0911) loss: 0.8232 (0.8249) time: 0.1822 data: 0.0932 max mem: 9390 +Train: [55] [1400/6250] eta: 0:14:43 lr: 0.000057 grad: 0.0892 (0.0909) loss: 0.8224 (0.8248) time: 0.1371 data: 0.0528 max mem: 9390 +Train: [55] [1500/6250] eta: 0:14:20 lr: 0.000057 grad: 0.0920 (0.0907) loss: 0.8220 (0.8247) time: 0.1623 data: 0.0722 max mem: 9390 +Train: [55] [1600/6250] eta: 0:13:57 lr: 0.000057 grad: 0.0805 (0.0906) loss: 0.8208 (0.8244) time: 0.1759 data: 0.0900 max mem: 9390 +Train: [55] [1700/6250] eta: 0:13:33 lr: 0.000057 grad: 0.0831 (0.0906) loss: 0.8214 (0.8243) time: 0.1534 data: 0.0568 max mem: 9390 +Train: [55] [1800/6250] eta: 0:13:11 lr: 0.000057 grad: 0.0873 (0.0906) loss: 0.8218 (0.8240) time: 0.1716 data: 0.0766 max mem: 9390 +Train: [55] [1900/6250] eta: 0:12:48 lr: 0.000057 grad: 0.0897 (0.0907) loss: 0.8188 (0.8237) time: 0.1685 data: 0.0790 max mem: 9390 +Train: [55] [2000/6250] eta: 0:12:26 lr: 0.000057 grad: 0.0933 (0.0907) loss: 0.8167 (0.8234) time: 0.1505 data: 0.0682 max mem: 9390 +Train: [55] [2100/6250] eta: 0:12:04 lr: 0.000057 grad: 0.0889 (0.0908) loss: 0.8193 (0.8233) time: 0.1583 data: 0.0676 max mem: 9390 +Train: [55] [2200/6250] eta: 0:11:45 lr: 0.000057 grad: 0.0885 (0.0908) loss: 0.8268 (0.8233) time: 0.1624 data: 0.0734 max mem: 9390 +Train: [55] [2300/6250] eta: 0:11:25 lr: 0.000057 grad: 0.0852 (0.0908) loss: 0.8218 (0.8231) time: 0.1586 data: 0.0719 max mem: 9390 +Train: [55] [2400/6250] eta: 0:11:06 lr: 0.000057 grad: 0.0899 (0.0908) loss: 0.8259 (0.8231) time: 0.1402 data: 0.0556 max mem: 9390 +Train: [55] [2500/6250] eta: 0:10:46 lr: 0.000057 grad: 0.0920 (0.0909) loss: 0.8207 (0.8229) time: 0.1525 data: 0.0674 max mem: 9390 +Train: [55] [2600/6250] eta: 0:10:27 lr: 0.000056 grad: 0.0915 (0.0910) loss: 0.8234 (0.8228) time: 0.1559 data: 0.0627 max mem: 9390 +Train: [55] [2700/6250] eta: 0:10:09 lr: 0.000056 grad: 0.0856 (0.0910) loss: 0.8246 (0.8228) time: 0.1558 data: 0.0706 max mem: 9390 +Train: [55] [2800/6250] eta: 0:09:51 lr: 0.000056 grad: 0.0942 (0.0911) loss: 0.8215 (0.8228) time: 0.1667 data: 0.0834 max mem: 9390 +Train: [55] [2900/6250] eta: 0:09:33 lr: 0.000056 grad: 0.0903 (0.0912) loss: 0.8241 (0.8229) time: 0.1578 data: 0.0643 max mem: 9390 +Train: [55] [3000/6250] eta: 0:09:15 lr: 0.000056 grad: 0.0882 (0.0913) loss: 0.8248 (0.8228) time: 0.1627 data: 0.0713 max mem: 9390 +Train: [55] [3100/6250] eta: 0:08:57 lr: 0.000056 grad: 0.0906 (0.0915) loss: 0.8182 (0.8227) time: 0.1617 data: 0.0738 max mem: 9390 +Train: [55] [3200/6250] eta: 0:08:39 lr: 0.000056 grad: 0.0980 (0.0916) loss: 0.8209 (0.8227) time: 0.1641 data: 0.0749 max mem: 9390 +Train: [55] [3300/6250] eta: 0:08:21 lr: 0.000056 grad: 0.0917 (0.0917) loss: 0.8287 (0.8227) time: 0.1527 data: 0.0622 max mem: 9390 +Train: [55] [3400/6250] eta: 0:08:03 lr: 0.000056 grad: 0.0886 (0.0918) loss: 0.8249 (0.8227) time: 0.1590 data: 0.0694 max mem: 9390 +Train: [55] [3500/6250] eta: 0:07:46 lr: 0.000056 grad: 0.0933 (0.0919) loss: 0.8178 (0.8226) time: 0.1947 data: 0.1119 max mem: 9390 +Train: [55] [3600/6250] eta: 0:07:28 lr: 0.000056 grad: 0.0919 (0.0920) loss: 0.8201 (0.8226) time: 0.1722 data: 0.0915 max mem: 9390 +Train: [55] [3700/6250] eta: 0:07:10 lr: 0.000056 grad: 0.0907 (0.0921) loss: 0.8171 (0.8226) time: 0.1612 data: 0.0764 max mem: 9390 +Train: [55] [3800/6250] eta: 0:06:53 lr: 0.000056 grad: 0.0885 (0.0922) loss: 0.8270 (0.8225) time: 0.1269 data: 0.0389 max mem: 9390 +Train: [55] [3900/6250] eta: 0:06:35 lr: 0.000056 grad: 0.0885 (0.0922) loss: 0.8220 (0.8225) time: 0.1492 data: 0.0586 max mem: 9390 +Train: [55] [4000/6250] eta: 0:06:19 lr: 0.000056 grad: 0.0910 (0.0922) loss: 0.8226 (0.8225) time: 0.1780 data: 0.0958 max mem: 9390 +Train: [55] [4100/6250] eta: 0:06:01 lr: 0.000056 grad: 0.0914 (0.0923) loss: 0.8172 (0.8225) time: 0.1556 data: 0.0642 max mem: 9390 +Train: [55] [4200/6250] eta: 0:05:44 lr: 0.000056 grad: 0.0947 (0.0924) loss: 0.8229 (0.8225) time: 0.1664 data: 0.0823 max mem: 9390 +Train: [55] [4300/6250] eta: 0:05:27 lr: 0.000056 grad: 0.0943 (0.0924) loss: 0.8198 (0.8225) time: 0.1781 data: 0.0954 max mem: 9390 +Train: [55] [4400/6250] eta: 0:05:10 lr: 0.000056 grad: 0.0877 (0.0925) loss: 0.8217 (0.8224) time: 0.1542 data: 0.0711 max mem: 9390 +Train: [55] [4500/6250] eta: 0:04:53 lr: 0.000056 grad: 0.0942 (0.0925) loss: 0.8217 (0.8224) time: 0.1638 data: 0.0726 max mem: 9390 +Train: [55] [4600/6250] eta: 0:04:36 lr: 0.000056 grad: 0.0941 (0.0926) loss: 0.8219 (0.8224) time: 0.1471 data: 0.0595 max mem: 9390 +Train: [55] [4700/6250] eta: 0:04:20 lr: 0.000056 grad: 0.0968 (0.0927) loss: 0.8236 (0.8223) time: 0.1557 data: 0.0630 max mem: 9390 +Train: [55] [4800/6250] eta: 0:04:03 lr: 0.000056 grad: 0.0894 (0.0928) loss: 0.8196 (0.8223) time: 0.1718 data: 0.0840 max mem: 9390 +Train: [55] [4900/6250] eta: 0:03:46 lr: 0.000056 grad: 0.0926 (0.0929) loss: 0.8239 (0.8222) time: 0.1775 data: 0.0854 max mem: 9390 +Train: [55] [5000/6250] eta: 0:03:29 lr: 0.000056 grad: 0.0959 (0.0930) loss: 0.8184 (0.8221) time: 0.1577 data: 0.0731 max mem: 9390 +Train: [55] [5100/6250] eta: 0:03:12 lr: 0.000056 grad: 0.0985 (0.0930) loss: 0.8226 (0.8221) time: 0.1512 data: 0.0644 max mem: 9390 +Train: [55] [5200/6250] eta: 0:02:55 lr: 0.000056 grad: 0.0936 (0.0931) loss: 0.8232 (0.8222) time: 0.1735 data: 0.0941 max mem: 9390 +Train: [55] [5300/6250] eta: 0:02:38 lr: 0.000056 grad: 0.0883 (0.0931) loss: 0.8198 (0.8222) time: 0.1530 data: 0.0638 max mem: 9390 +Train: [55] [5400/6250] eta: 0:02:21 lr: 0.000056 grad: 0.0898 (0.0931) loss: 0.8281 (0.8221) time: 0.1534 data: 0.0662 max mem: 9390 +Train: [55] [5500/6250] eta: 0:02:05 lr: 0.000056 grad: 0.0914 (0.0931) loss: 0.8165 (0.8222) time: 0.1515 data: 0.0697 max mem: 9390 +Train: [55] [5600/6250] eta: 0:01:48 lr: 0.000055 grad: 0.0869 (0.0931) loss: 0.8245 (0.8222) time: 0.1709 data: 0.0837 max mem: 9390 +Train: [55] [5700/6250] eta: 0:01:31 lr: 0.000055 grad: 0.0867 (0.0931) loss: 0.8203 (0.8223) time: 0.1535 data: 0.0677 max mem: 9390 +Train: [55] [5800/6250] eta: 0:01:15 lr: 0.000055 grad: 0.0883 (0.0931) loss: 0.8193 (0.8223) time: 0.1563 data: 0.0753 max mem: 9390 +Train: [55] [5900/6250] eta: 0:00:58 lr: 0.000055 grad: 0.0899 (0.0931) loss: 0.8176 (0.8223) time: 0.1654 data: 0.0748 max mem: 9390 +Train: [55] [6000/6250] eta: 0:00:41 lr: 0.000055 grad: 0.0903 (0.0931) loss: 0.8222 (0.8223) time: 0.1747 data: 0.0907 max mem: 9390 +Train: [55] [6100/6250] eta: 0:00:25 lr: 0.000055 grad: 0.0883 (0.0931) loss: 0.8224 (0.8223) time: 0.1676 data: 0.0856 max mem: 9390 +Train: [55] [6200/6250] eta: 0:00:08 lr: 0.000055 grad: 0.0964 (0.0932) loss: 0.8225 (0.8223) time: 0.1547 data: 0.0700 max mem: 9390 +Train: [55] [6249/6250] eta: 0:00:00 lr: 0.000055 grad: 0.0965 (0.0933) loss: 0.8177 (0.8222) time: 0.1978 data: 0.1161 max mem: 9390 +Train: [55] Total time: 0:17:35 (0.1688 s / it) +Averaged stats: lr: 0.000055 grad: 0.0965 (0.0933) loss: 0.8177 (0.8222) +Eval (hcp-train-subset): [55] [ 0/62] eta: 0:05:14 loss: 0.8544 (0.8544) time: 5.0666 data: 5.0369 max mem: 9390 +Eval (hcp-train-subset): [55] [61/62] eta: 0:00:00 loss: 0.8349 (0.8359) time: 0.1339 data: 0.1070 max mem: 9390 +Eval (hcp-train-subset): [55] Total time: 0:00:13 (0.2165 s / it) +Averaged stats (hcp-train-subset): loss: 0.8349 (0.8359) +Eval (hcp-val): [55] [ 0/62] eta: 0:05:37 loss: 0.8340 (0.8340) time: 5.4476 data: 5.4166 max mem: 9390 +Eval (hcp-val): [55] [61/62] eta: 0:00:00 loss: 0.8323 (0.8344) time: 0.1309 data: 0.1052 max mem: 9390 +Eval (hcp-val): [55] Total time: 0:00:13 (0.2242 s / it) +Averaged stats (hcp-val): loss: 0.8323 (0.8344) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +Train: [56] [ 0/6250] eta: 6:05:53 lr: 0.000055 grad: 0.0702 (0.0702) loss: 0.8631 (0.8631) time: 3.5125 data: 3.2639 max mem: 9390 +Train: [56] [ 100/6250] eta: 0:22:13 lr: 0.000055 grad: 0.0973 (0.1103) loss: 0.8181 (0.8285) time: 0.1526 data: 0.0493 max mem: 9390 +Train: [56] [ 200/6250] eta: 0:19:49 lr: 0.000055 grad: 0.0970 (0.1090) loss: 0.8273 (0.8255) time: 0.1709 data: 0.0820 max mem: 9390 +Train: [56] [ 300/6250] eta: 0:18:27 lr: 0.000055 grad: 0.0912 (0.1061) loss: 0.8227 (0.8242) time: 0.1467 data: 0.0474 max mem: 9390 +Train: [56] [ 400/6250] eta: 0:17:35 lr: 0.000055 grad: 0.0955 (0.1046) loss: 0.8204 (0.8235) time: 0.1669 data: 0.0733 max mem: 9390 +Train: [56] [ 500/6250] eta: 0:16:55 lr: 0.000055 grad: 0.0893 (0.1027) loss: 0.8259 (0.8234) time: 0.1720 data: 0.0753 max mem: 9390 +Train: [56] [ 600/6250] eta: 0:16:33 lr: 0.000055 grad: 0.0903 (0.1012) loss: 0.8244 (0.8232) time: 0.1759 data: 0.0742 max mem: 9390 +Train: [56] [ 700/6250] eta: 0:16:07 lr: 0.000055 grad: 0.0946 (0.1003) loss: 0.8208 (0.8230) time: 0.1649 data: 0.0753 max mem: 9390 +Train: [56] [ 800/6250] eta: 0:15:47 lr: 0.000055 grad: 0.0889 (0.0993) loss: 0.8231 (0.8228) time: 0.1598 data: 0.0765 max mem: 9390 +Train: [56] [ 900/6250] eta: 0:15:40 lr: 0.000055 grad: 0.0899 (0.0985) loss: 0.8242 (0.8230) time: 0.1883 data: 0.0978 max mem: 9390 +Train: [56] [1000/6250] eta: 0:15:18 lr: 0.000055 grad: 0.0882 (0.0980) loss: 0.8246 (0.8229) time: 0.1802 data: 0.0976 max mem: 9390 +Train: [56] [1100/6250] eta: 0:15:04 lr: 0.000055 grad: 0.0948 (0.0977) loss: 0.8242 (0.8229) time: 0.2138 data: 0.1323 max mem: 9390 +Train: [56] [1200/6250] eta: 0:14:42 lr: 0.000055 grad: 0.0872 (0.0972) loss: 0.8224 (0.8227) time: 0.1512 data: 0.0570 max mem: 9390 +Train: [56] [1300/6250] eta: 0:14:21 lr: 0.000055 grad: 0.0959 (0.0971) loss: 0.8218 (0.8224) time: 0.1735 data: 0.0920 max mem: 9390 +Train: [56] [1400/6250] eta: 0:14:01 lr: 0.000055 grad: 0.0957 (0.0969) loss: 0.8201 (0.8222) time: 0.1790 data: 0.0932 max mem: 9390 +Train: [56] [1500/6250] eta: 0:13:40 lr: 0.000055 grad: 0.0909 (0.0968) loss: 0.8195 (0.8221) time: 0.1714 data: 0.0825 max mem: 9390 +Train: [56] [1600/6250] eta: 0:13:20 lr: 0.000055 grad: 0.0906 (0.0965) loss: 0.8198 (0.8220) time: 0.1531 data: 0.0617 max mem: 9390 +Train: [56] [1700/6250] eta: 0:12:59 lr: 0.000055 grad: 0.0967 (0.0966) loss: 0.8174 (0.8219) time: 0.1593 data: 0.0675 max mem: 9390 +Train: [56] [1800/6250] eta: 0:12:40 lr: 0.000055 grad: 0.0920 (0.0965) loss: 0.8172 (0.8218) time: 0.1657 data: 0.0740 max mem: 9390 +Train: [56] [1900/6250] eta: 0:12:23 lr: 0.000055 grad: 0.0969 (0.0966) loss: 0.8175 (0.8216) time: 0.1808 data: 0.0957 max mem: 9390 +Train: [56] [2000/6250] eta: 0:12:02 lr: 0.000055 grad: 0.1016 (0.0967) loss: 0.8109 (0.8214) time: 0.1507 data: 0.0629 max mem: 9390 +Train: [56] [2100/6250] eta: 0:11:42 lr: 0.000055 grad: 0.0995 (0.0969) loss: 0.8178 (0.8214) time: 0.1630 data: 0.0772 max mem: 9390 +Train: [56] [2200/6250] eta: 0:11:22 lr: 0.000055 grad: 0.0887 (0.0970) loss: 0.8205 (0.8212) time: 0.1633 data: 0.0783 max mem: 9390 +Train: [56] [2300/6250] eta: 0:11:04 lr: 0.000055 grad: 0.0974 (0.0970) loss: 0.8214 (0.8210) time: 0.1632 data: 0.0741 max mem: 9390 +Train: [56] [2400/6250] eta: 0:10:46 lr: 0.000054 grad: 0.0927 (0.0970) loss: 0.8250 (0.8209) time: 0.1717 data: 0.0803 max mem: 9390 +Train: [56] [2500/6250] eta: 0:10:28 lr: 0.000054 grad: 0.0892 (0.0969) loss: 0.8229 (0.8208) time: 0.1446 data: 0.0516 max mem: 9390 +Train: [56] [2600/6250] eta: 0:10:11 lr: 0.000054 grad: 0.0917 (0.0968) loss: 0.8216 (0.8208) time: 0.1772 data: 0.0946 max mem: 9390 +Train: [56] [2700/6250] eta: 0:09:53 lr: 0.000054 grad: 0.0938 (0.0968) loss: 0.8269 (0.8207) time: 0.1478 data: 0.0517 max mem: 9390 +Train: [56] [2800/6250] eta: 0:09:36 lr: 0.000054 grad: 0.0899 (0.0967) loss: 0.8209 (0.8208) time: 0.1506 data: 0.0521 max mem: 9390 +Train: [56] [2900/6250] eta: 0:09:18 lr: 0.000054 grad: 0.0920 (0.0968) loss: 0.8223 (0.8207) time: 0.1610 data: 0.0711 max mem: 9390 +Train: [56] [3000/6250] eta: 0:09:00 lr: 0.000054 grad: 0.0862 (0.0967) loss: 0.8218 (0.8207) time: 0.1518 data: 0.0599 max mem: 9390 +Train: [56] [3100/6250] eta: 0:08:44 lr: 0.000054 grad: 0.0912 (0.0966) loss: 0.8229 (0.8207) time: 0.1683 data: 0.0824 max mem: 9390 +Train: [56] [3200/6250] eta: 0:08:27 lr: 0.000054 grad: 0.0907 (0.0966) loss: 0.8233 (0.8207) time: 0.1438 data: 0.0526 max mem: 9390 +Train: [56] [3300/6250] eta: 0:08:10 lr: 0.000054 grad: 0.0903 (0.0965) loss: 0.8234 (0.8207) time: 0.1794 data: 0.0911 max mem: 9390 +Train: [56] [3400/6250] eta: 0:07:53 lr: 0.000054 grad: 0.0905 (0.0965) loss: 0.8243 (0.8207) time: 0.1786 data: 0.0951 max mem: 9390 +Train: [56] [3500/6250] eta: 0:07:37 lr: 0.000054 grad: 0.0903 (0.0966) loss: 0.8212 (0.8206) time: 0.1739 data: 0.0836 max mem: 9390 +Train: [56] [3600/6250] eta: 0:07:19 lr: 0.000054 grad: 0.0933 (0.0966) loss: 0.8241 (0.8206) time: 0.1493 data: 0.0615 max mem: 9390 +Train: [56] [3700/6250] eta: 0:07:02 lr: 0.000054 grad: 0.0937 (0.0967) loss: 0.8233 (0.8207) time: 0.1254 data: 0.0372 max mem: 9390 +Train: [56] [3800/6250] eta: 0:06:46 lr: 0.000054 grad: 0.0927 (0.0966) loss: 0.8251 (0.8207) time: 0.1967 data: 0.1120 max mem: 9390 +Train: [56] [3900/6250] eta: 0:06:29 lr: 0.000054 grad: 0.1040 (0.0967) loss: 0.8122 (0.8208) time: 0.1793 data: 0.0967 max mem: 9390 +Train: [56] [4000/6250] eta: 0:06:12 lr: 0.000054 grad: 0.0905 (0.0966) loss: 0.8265 (0.8208) time: 0.1721 data: 0.0922 max mem: 9390 +Train: [56] [4100/6250] eta: 0:05:56 lr: 0.000054 grad: 0.0931 (0.0966) loss: 0.8242 (0.8209) time: 0.1697 data: 0.0834 max mem: 9390 +Train: [56] [4200/6250] eta: 0:05:39 lr: 0.000054 grad: 0.0920 (0.0966) loss: 0.8218 (0.8209) time: 0.1471 data: 0.0590 max mem: 9390 +Train: [56] [4300/6250] eta: 0:05:22 lr: 0.000054 grad: 0.0909 (0.0966) loss: 0.8224 (0.8209) time: 0.1598 data: 0.0732 max mem: 9390 +Train: [56] [4400/6250] eta: 0:05:05 lr: 0.000054 grad: 0.0929 (0.0967) loss: 0.8227 (0.8209) time: 0.1676 data: 0.0824 max mem: 9390 +Train: [56] [4500/6250] eta: 0:04:49 lr: 0.000054 grad: 0.0885 (0.0967) loss: 0.8244 (0.8210) time: 0.1599 data: 0.0759 max mem: 9390 +Train: [56] [4600/6250] eta: 0:04:32 lr: 0.000054 grad: 0.0860 (0.0966) loss: 0.8227 (0.8210) time: 0.1677 data: 0.0824 max mem: 9390 +Train: [56] [4700/6250] eta: 0:04:16 lr: 0.000054 grad: 0.0967 (0.0966) loss: 0.8182 (0.8210) time: 0.1522 data: 0.0620 max mem: 9390 +Train: [56] [4800/6250] eta: 0:04:00 lr: 0.000054 grad: 0.0904 (0.0966) loss: 0.8231 (0.8211) time: 0.1587 data: 0.0723 max mem: 9390 +Train: [56] [4900/6250] eta: 0:03:44 lr: 0.000054 grad: 0.1001 (0.0966) loss: 0.8229 (0.8212) time: 0.2046 data: 0.1180 max mem: 9390 +Train: [56] [5000/6250] eta: 0:03:28 lr: 0.000054 grad: 0.0924 (0.0966) loss: 0.8270 (0.8212) time: 0.1575 data: 0.0755 max mem: 9390 +Train: [56] [5100/6250] eta: 0:03:12 lr: 0.000054 grad: 0.1023 (0.0966) loss: 0.8198 (0.8212) time: 0.1658 data: 0.0863 max mem: 9390 +Train: [56] [5200/6250] eta: 0:02:55 lr: 0.000054 grad: 0.0943 (0.0967) loss: 0.8179 (0.8212) time: 0.1920 data: 0.1053 max mem: 9390 +Train: [56] [5300/6250] eta: 0:02:39 lr: 0.000054 grad: 0.0920 (0.0967) loss: 0.8229 (0.8212) time: 0.1686 data: 0.0701 max mem: 9390 +Train: [56] [5400/6250] eta: 0:02:22 lr: 0.000054 grad: 0.0910 (0.0968) loss: 0.8208 (0.8211) time: 0.1805 data: 0.0817 max mem: 9390 +Train: [56] [5500/6250] eta: 0:02:05 lr: 0.000053 grad: 0.1003 (0.0968) loss: 0.8163 (0.8211) time: 0.1521 data: 0.0575 max mem: 9390 +Train: [56] [5600/6250] eta: 0:01:48 lr: 0.000053 grad: 0.0906 (0.0969) loss: 0.8264 (0.8211) time: 0.1535 data: 0.0637 max mem: 9390 +Train: [56] [5700/6250] eta: 0:01:32 lr: 0.000053 grad: 0.0923 (0.0969) loss: 0.8162 (0.8211) time: 0.1667 data: 0.0842 max mem: 9390 +Train: [56] [5800/6250] eta: 0:01:15 lr: 0.000053 grad: 0.0979 (0.0969) loss: 0.8184 (0.8211) time: 0.1686 data: 0.0795 max mem: 9390 +Train: [56] [5900/6250] eta: 0:00:58 lr: 0.000053 grad: 0.0950 (0.0969) loss: 0.8252 (0.8210) time: 0.1795 data: 0.0864 max mem: 9390 +Train: [56] [6000/6250] eta: 0:00:41 lr: 0.000053 grad: 0.0923 (0.0969) loss: 0.8294 (0.8211) time: 0.1884 data: 0.1006 max mem: 9390 +Train: [56] [6100/6250] eta: 0:00:25 lr: 0.000053 grad: 0.0899 (0.0969) loss: 0.8262 (0.8211) time: 0.1542 data: 0.0680 max mem: 9390 +Train: [56] [6200/6250] eta: 0:00:08 lr: 0.000053 grad: 0.0928 (0.0970) loss: 0.8205 (0.8211) time: 0.1586 data: 0.0732 max mem: 9390 +Train: [56] [6249/6250] eta: 0:00:00 lr: 0.000053 grad: 0.0964 (0.0970) loss: 0.8282 (0.8211) time: 0.1585 data: 0.0703 max mem: 9390 +Train: [56] Total time: 0:17:32 (0.1684 s / it) +Averaged stats: lr: 0.000053 grad: 0.0964 (0.0970) loss: 0.8282 (0.8211) +Eval (hcp-train-subset): [56] [ 0/62] eta: 0:06:00 loss: 0.8496 (0.8496) time: 5.8090 data: 5.7755 max mem: 9390 +Eval (hcp-train-subset): [56] [61/62] eta: 0:00:00 loss: 0.8360 (0.8371) time: 0.1577 data: 0.1325 max mem: 9390 +Eval (hcp-train-subset): [56] Total time: 0:00:15 (0.2502 s / it) +Averaged stats (hcp-train-subset): loss: 0.8360 (0.8371) +Eval (hcp-val): [56] [ 0/62] eta: 0:04:37 loss: 0.8331 (0.8331) time: 4.4833 data: 4.4341 max mem: 9390 +Eval (hcp-val): [56] [61/62] eta: 0:00:00 loss: 0.8322 (0.8341) time: 0.1501 data: 0.1232 max mem: 9390 +Eval (hcp-val): [56] Total time: 0:00:13 (0.2248 s / it) +Averaged stats (hcp-val): loss: 0.8322 (0.8341) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +Train: [57] [ 0/6250] eta: 6:47:33 lr: 0.000053 grad: 0.1577 (0.1577) loss: 0.8524 (0.8524) time: 3.9126 data: 3.6885 max mem: 9390 +Train: [57] [ 100/6250] eta: 0:24:05 lr: 0.000053 grad: 0.0998 (0.1087) loss: 0.8192 (0.8368) time: 0.1612 data: 0.0624 max mem: 9390 +Train: [57] [ 200/6250] eta: 0:20:58 lr: 0.000053 grad: 0.1039 (0.1070) loss: 0.8157 (0.8294) time: 0.1619 data: 0.0695 max mem: 9390 +Train: [57] [ 300/6250] eta: 0:19:21 lr: 0.000053 grad: 0.0957 (0.1061) loss: 0.8248 (0.8261) time: 0.1811 data: 0.0907 max mem: 9390 +Train: [57] [ 400/6250] eta: 0:18:23 lr: 0.000053 grad: 0.0968 (0.1038) loss: 0.8156 (0.8244) time: 0.1657 data: 0.0815 max mem: 9390 +Train: [57] [ 500/6250] eta: 0:17:38 lr: 0.000053 grad: 0.0879 (0.1019) loss: 0.8217 (0.8234) time: 0.1627 data: 0.0627 max mem: 9390 +Train: [57] [ 600/6250] eta: 0:16:59 lr: 0.000053 grad: 0.0878 (0.1003) loss: 0.8214 (0.8231) time: 0.1539 data: 0.0564 max mem: 9390 +Train: [57] [ 700/6250] eta: 0:16:27 lr: 0.000053 grad: 0.0854 (0.0996) loss: 0.8178 (0.8231) time: 0.1289 data: 0.0143 max mem: 9390 +Train: [57] [ 800/6250] eta: 0:16:13 lr: 0.000053 grad: 0.0924 (0.0994) loss: 0.8218 (0.8229) time: 0.1993 data: 0.1106 max mem: 9390 +Train: [57] [ 900/6250] eta: 0:15:50 lr: 0.000053 grad: 0.0901 (0.0990) loss: 0.8185 (0.8226) time: 0.1621 data: 0.0753 max mem: 9390 +Train: [57] [1000/6250] eta: 0:15:28 lr: 0.000053 grad: 0.0892 (0.0987) loss: 0.8174 (0.8224) time: 0.1597 data: 0.0662 max mem: 9390 +Train: [57] [1100/6250] eta: 0:15:05 lr: 0.000053 grad: 0.0954 (0.0983) loss: 0.8170 (0.8222) time: 0.1460 data: 0.0574 max mem: 9390 +Train: [57] [1200/6250] eta: 0:14:42 lr: 0.000053 grad: 0.0964 (0.0981) loss: 0.8172 (0.8219) time: 0.1522 data: 0.0602 max mem: 9390 +Train: [57] [1300/6250] eta: 0:14:19 lr: 0.000053 grad: 0.0943 (0.0983) loss: 0.8192 (0.8215) time: 0.1649 data: 0.0779 max mem: 9390 +Train: [57] [1400/6250] eta: 0:13:57 lr: 0.000053 grad: 0.0987 (0.0984) loss: 0.8067 (0.8210) time: 0.1384 data: 0.0512 max mem: 9390 +Train: [57] [1500/6250] eta: 0:13:37 lr: 0.000053 grad: 0.0969 (0.0987) loss: 0.8118 (0.8204) time: 0.1541 data: 0.0721 max mem: 9390 +Train: [57] [1600/6250] eta: 0:13:17 lr: 0.000053 grad: 0.1018 (0.0988) loss: 0.8055 (0.8200) time: 0.1650 data: 0.0753 max mem: 9390 +Train: [57] [1700/6250] eta: 0:12:56 lr: 0.000053 grad: 0.0960 (0.0990) loss: 0.8172 (0.8197) time: 0.1601 data: 0.0795 max mem: 9390 +Train: [57] [1800/6250] eta: 0:12:38 lr: 0.000053 grad: 0.1016 (0.0992) loss: 0.8123 (0.8194) time: 0.1639 data: 0.0682 max mem: 9390 +Train: [57] [1900/6250] eta: 0:12:20 lr: 0.000053 grad: 0.1015 (0.0991) loss: 0.8126 (0.8191) time: 0.1843 data: 0.1003 max mem: 9390 +Train: [57] [2000/6250] eta: 0:12:02 lr: 0.000053 grad: 0.0972 (0.0992) loss: 0.8168 (0.8190) time: 0.1579 data: 0.0727 max mem: 9390 +Train: [57] [2100/6250] eta: 0:11:41 lr: 0.000053 grad: 0.0971 (0.0993) loss: 0.8128 (0.8188) time: 0.1505 data: 0.0588 max mem: 9390 +Train: [57] [2200/6250] eta: 0:11:23 lr: 0.000053 grad: 0.0993 (0.0993) loss: 0.8181 (0.8188) time: 0.1759 data: 0.0958 max mem: 9390 +Train: [57] [2300/6250] eta: 0:11:03 lr: 0.000052 grad: 0.0978 (0.0993) loss: 0.8215 (0.8187) time: 0.1713 data: 0.0878 max mem: 9390 +Train: [57] [2400/6250] eta: 0:10:45 lr: 0.000052 grad: 0.0909 (0.0993) loss: 0.8184 (0.8187) time: 0.1691 data: 0.0799 max mem: 9390 +Train: [57] [2500/6250] eta: 0:10:28 lr: 0.000052 grad: 0.0991 (0.0994) loss: 0.8181 (0.8187) time: 0.1548 data: 0.0729 max mem: 9390 +Train: [57] [2600/6250] eta: 0:10:11 lr: 0.000052 grad: 0.1085 (0.0998) loss: 0.8135 (0.8187) time: 0.1535 data: 0.0642 max mem: 9390 +Train: [57] [2700/6250] eta: 0:09:54 lr: 0.000052 grad: 0.0937 (0.1000) loss: 0.8152 (0.8187) time: 0.1769 data: 0.0925 max mem: 9390 +Train: [57] [2800/6250] eta: 0:09:36 lr: 0.000052 grad: 0.0939 (0.1000) loss: 0.8150 (0.8186) time: 0.1652 data: 0.0865 max mem: 9390 +Train: [57] [2900/6250] eta: 0:09:19 lr: 0.000052 grad: 0.0955 (0.1000) loss: 0.8212 (0.8186) time: 0.1626 data: 0.0818 max mem: 9390 +Train: [57] [3000/6250] eta: 0:09:01 lr: 0.000052 grad: 0.1032 (0.1000) loss: 0.8198 (0.8185) time: 0.1612 data: 0.0682 max mem: 9390 +Train: [57] [3100/6250] eta: 0:08:44 lr: 0.000052 grad: 0.0958 (0.1000) loss: 0.8204 (0.8185) time: 0.1529 data: 0.0635 max mem: 9390 +Train: [57] [3200/6250] eta: 0:08:27 lr: 0.000052 grad: 0.0975 (0.0999) loss: 0.8119 (0.8184) time: 0.1938 data: 0.1059 max mem: 9390 +Train: [57] [3300/6250] eta: 0:08:10 lr: 0.000052 grad: 0.0978 (0.1000) loss: 0.8202 (0.8184) time: 0.1724 data: 0.0872 max mem: 9390 +Train: [57] [3400/6250] eta: 0:07:53 lr: 0.000052 grad: 0.0976 (0.0999) loss: 0.8154 (0.8184) time: 0.1540 data: 0.0606 max mem: 9390 +Train: [57] [3500/6250] eta: 0:07:37 lr: 0.000052 grad: 0.1009 (0.0999) loss: 0.8176 (0.8185) time: 0.1664 data: 0.0828 max mem: 9390 +Train: [57] [3600/6250] eta: 0:07:20 lr: 0.000052 grad: 0.1022 (0.0999) loss: 0.8154 (0.8185) time: 0.1504 data: 0.0546 max mem: 9390 +Train: [57] [3700/6250] eta: 0:07:03 lr: 0.000052 grad: 0.1056 (0.0999) loss: 0.8193 (0.8185) time: 0.1780 data: 0.0935 max mem: 9390 +Train: [57] [3800/6250] eta: 0:06:47 lr: 0.000052 grad: 0.1007 (0.0999) loss: 0.8202 (0.8185) time: 0.1623 data: 0.0761 max mem: 9390 +Train: [57] [3900/6250] eta: 0:06:30 lr: 0.000052 grad: 0.1055 (0.0999) loss: 0.8158 (0.8185) time: 0.1691 data: 0.0872 max mem: 9390 +Train: [57] [4000/6250] eta: 0:06:14 lr: 0.000052 grad: 0.0961 (0.1000) loss: 0.8146 (0.8184) time: 0.1890 data: 0.1095 max mem: 9390 +Train: [57] [4100/6250] eta: 0:05:57 lr: 0.000052 grad: 0.0966 (0.1000) loss: 0.8097 (0.8184) time: 0.1699 data: 0.0891 max mem: 9390 +Train: [57] [4200/6250] eta: 0:05:41 lr: 0.000052 grad: 0.0978 (0.1000) loss: 0.8150 (0.8183) time: 0.1701 data: 0.0852 max mem: 9390 +Train: [57] [4300/6250] eta: 0:05:26 lr: 0.000052 grad: 0.0998 (0.1000) loss: 0.8140 (0.8183) time: 0.1657 data: 0.0823 max mem: 9390 +Train: [57] [4400/6250] eta: 0:05:10 lr: 0.000052 grad: 0.0964 (0.1001) loss: 0.8214 (0.8183) time: 0.1738 data: 0.0928 max mem: 9390 +Train: [57] [4500/6250] eta: 0:04:54 lr: 0.000052 grad: 0.0930 (0.1003) loss: 0.8151 (0.8183) time: 0.1900 data: 0.1072 max mem: 9390 +Train: [57] [4600/6250] eta: 0:04:37 lr: 0.000052 grad: 0.0987 (0.1003) loss: 0.8143 (0.8182) time: 0.1707 data: 0.0883 max mem: 9390 +Train: [57] [4700/6250] eta: 0:04:21 lr: 0.000052 grad: 0.0993 (0.1003) loss: 0.8201 (0.8182) time: 0.1611 data: 0.0835 max mem: 9390 +Train: [57] [4800/6250] eta: 0:04:04 lr: 0.000052 grad: 0.0969 (0.1002) loss: 0.8182 (0.8181) time: 0.1650 data: 0.0737 max mem: 9390 +Train: [57] [4900/6250] eta: 0:03:47 lr: 0.000052 grad: 0.0992 (0.1002) loss: 0.8198 (0.8181) time: 0.1771 data: 0.0999 max mem: 9390 +Train: [57] [5000/6250] eta: 0:03:30 lr: 0.000052 grad: 0.0944 (0.1002) loss: 0.8116 (0.8181) time: 0.1676 data: 0.0749 max mem: 9390 +Train: [57] [5100/6250] eta: 0:03:13 lr: 0.000052 grad: 0.0960 (0.1002) loss: 0.8140 (0.8181) time: 0.1566 data: 0.0690 max mem: 9390 +Train: [57] [5200/6250] eta: 0:02:56 lr: 0.000052 grad: 0.0891 (0.1001) loss: 0.8247 (0.8181) time: 0.1814 data: 0.0923 max mem: 9390 +Train: [57] [5300/6250] eta: 0:02:39 lr: 0.000052 grad: 0.0955 (0.1000) loss: 0.8165 (0.8181) time: 0.1713 data: 0.0864 max mem: 9390 +Train: [57] [5400/6250] eta: 0:02:22 lr: 0.000051 grad: 0.0973 (0.1000) loss: 0.8178 (0.8182) time: 0.1523 data: 0.0579 max mem: 9390 +Train: [57] [5500/6250] eta: 0:02:06 lr: 0.000051 grad: 0.0921 (0.0999) loss: 0.8217 (0.8182) time: 0.1755 data: 0.0900 max mem: 9390 +Train: [57] [5600/6250] eta: 0:01:49 lr: 0.000051 grad: 0.0988 (0.0999) loss: 0.8226 (0.8183) time: 0.1718 data: 0.0890 max mem: 9390 +Train: [57] [5700/6250] eta: 0:01:32 lr: 0.000051 grad: 0.0931 (0.0999) loss: 0.8180 (0.8183) time: 0.1400 data: 0.0533 max mem: 9390 +Train: [57] [5800/6250] eta: 0:01:15 lr: 0.000051 grad: 0.0960 (0.0999) loss: 0.8183 (0.8184) time: 0.1503 data: 0.0675 max mem: 9390 +Train: [57] [5900/6250] eta: 0:00:58 lr: 0.000051 grad: 0.0965 (0.0998) loss: 0.8164 (0.8184) time: 0.1825 data: 0.0915 max mem: 9390 +Train: [57] [6000/6250] eta: 0:00:42 lr: 0.000051 grad: 0.0878 (0.0998) loss: 0.8249 (0.8184) time: 0.1731 data: 0.0865 max mem: 9390 +Train: [57] [6100/6250] eta: 0:00:25 lr: 0.000051 grad: 0.0926 (0.0998) loss: 0.8239 (0.8185) time: 0.1642 data: 0.0724 max mem: 9390 +Train: [57] [6200/6250] eta: 0:00:08 lr: 0.000051 grad: 0.0883 (0.0997) loss: 0.8225 (0.8185) time: 0.1600 data: 0.0738 max mem: 9390 +Train: [57] [6249/6250] eta: 0:00:00 lr: 0.000051 grad: 0.0918 (0.0997) loss: 0.8179 (0.8185) time: 0.1918 data: 0.1054 max mem: 9390 +Train: [57] Total time: 0:17:38 (0.1693 s / it) +Averaged stats: lr: 0.000051 grad: 0.0918 (0.0997) loss: 0.8179 (0.8185) +Eval (hcp-train-subset): [57] [ 0/62] eta: 0:06:20 loss: 0.8454 (0.8454) time: 6.1395 data: 6.1047 max mem: 9390 +Eval (hcp-train-subset): [57] [61/62] eta: 0:00:00 loss: 0.8344 (0.8352) time: 0.1213 data: 0.0963 max mem: 9390 +Eval (hcp-train-subset): [57] Total time: 0:00:14 (0.2418 s / it) +Averaged stats (hcp-train-subset): loss: 0.8344 (0.8352) +Eval (hcp-val): [57] [ 0/62] eta: 0:03:02 loss: 0.8340 (0.8340) time: 2.9402 data: 2.8433 max mem: 9390 +Eval (hcp-val): [57] [61/62] eta: 0:00:00 loss: 0.8328 (0.8343) time: 0.1350 data: 0.1091 max mem: 9390 +Eval (hcp-val): [57] Total time: 0:00:13 (0.2258 s / it) +Averaged stats (hcp-val): loss: 0.8328 (0.8343) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +Train: [58] [ 0/6250] eta: 11:05:09 lr: 0.000051 grad: 0.0609 (0.0609) loss: 0.8771 (0.8771) time: 6.3855 data: 6.2716 max mem: 9390 +Train: [58] [ 100/6250] eta: 0:23:49 lr: 0.000051 grad: 0.1082 (0.1193) loss: 0.8292 (0.8346) time: 0.1620 data: 0.0739 max mem: 9390 +Train: [58] [ 200/6250] eta: 0:20:22 lr: 0.000051 grad: 0.1013 (0.1119) loss: 0.8263 (0.8292) time: 0.1635 data: 0.0735 max mem: 9390 +Train: [58] [ 300/6250] eta: 0:18:48 lr: 0.000051 grad: 0.1013 (0.1063) loss: 0.8188 (0.8275) time: 0.1603 data: 0.0594 max mem: 9390 +Train: [58] [ 400/6250] eta: 0:18:06 lr: 0.000051 grad: 0.0877 (0.1027) loss: 0.8204 (0.8267) time: 0.1771 data: 0.0708 max mem: 9390 +Train: [58] [ 500/6250] eta: 0:17:24 lr: 0.000051 grad: 0.0943 (0.1017) loss: 0.8202 (0.8257) time: 0.1292 data: 0.0332 max mem: 9390 +Train: [58] [ 600/6250] eta: 0:16:50 lr: 0.000051 grad: 0.0907 (0.1010) loss: 0.8185 (0.8246) time: 0.1564 data: 0.0483 max mem: 9390 +Train: [58] [ 700/6250] eta: 0:16:24 lr: 0.000051 grad: 0.0919 (0.1005) loss: 0.8205 (0.8237) time: 0.1535 data: 0.0450 max mem: 9390 +Train: [58] [ 800/6250] eta: 0:16:04 lr: 0.000051 grad: 0.0932 (0.1001) loss: 0.8243 (0.8235) time: 0.1390 data: 0.0334 max mem: 9390 +Train: [58] [ 900/6250] eta: 0:15:48 lr: 0.000051 grad: 0.0860 (0.0995) loss: 0.8256 (0.8231) time: 0.1906 data: 0.1071 max mem: 9390 +Train: [58] [1000/6250] eta: 0:15:22 lr: 0.000051 grad: 0.0881 (0.0991) loss: 0.8135 (0.8225) time: 0.1639 data: 0.0797 max mem: 9390 +Train: [58] [1100/6250] eta: 0:15:01 lr: 0.000051 grad: 0.0921 (0.0986) loss: 0.8186 (0.8223) time: 0.1453 data: 0.0425 max mem: 9390 +Train: [58] [1200/6250] eta: 0:14:39 lr: 0.000051 grad: 0.0927 (0.0984) loss: 0.8165 (0.8221) time: 0.1492 data: 0.0572 max mem: 9390 +Train: [58] [1300/6250] eta: 0:14:19 lr: 0.000051 grad: 0.0902 (0.0981) loss: 0.8146 (0.8218) time: 0.1790 data: 0.0857 max mem: 9390 +Train: [58] [1400/6250] eta: 0:13:57 lr: 0.000051 grad: 0.0950 (0.0980) loss: 0.8189 (0.8213) time: 0.1747 data: 0.0761 max mem: 9390 +Train: [58] [1500/6250] eta: 0:13:35 lr: 0.000051 grad: 0.0965 (0.0978) loss: 0.8143 (0.8212) time: 0.1629 data: 0.0659 max mem: 9390 +Train: [58] [1600/6250] eta: 0:13:15 lr: 0.000051 grad: 0.0990 (0.0977) loss: 0.8097 (0.8209) time: 0.1527 data: 0.0637 max mem: 9390 +Train: [58] [1700/6250] eta: 0:12:55 lr: 0.000051 grad: 0.0943 (0.0976) loss: 0.8250 (0.8208) time: 0.1866 data: 0.0959 max mem: 9390 +Train: [58] [1800/6250] eta: 0:12:35 lr: 0.000051 grad: 0.0940 (0.0976) loss: 0.8057 (0.8205) time: 0.1564 data: 0.0670 max mem: 9390 +Train: [58] [1900/6250] eta: 0:12:15 lr: 0.000051 grad: 0.0971 (0.0976) loss: 0.8111 (0.8202) time: 0.1417 data: 0.0511 max mem: 9390 +Train: [58] [2000/6250] eta: 0:11:56 lr: 0.000051 grad: 0.0955 (0.0975) loss: 0.8119 (0.8201) time: 0.1630 data: 0.0684 max mem: 9390 +Train: [58] [2100/6250] eta: 0:11:37 lr: 0.000051 grad: 0.0920 (0.0975) loss: 0.8189 (0.8200) time: 0.1569 data: 0.0710 max mem: 9390 +Train: [58] [2200/6250] eta: 0:11:19 lr: 0.000050 grad: 0.0987 (0.0975) loss: 0.8177 (0.8199) time: 0.1639 data: 0.0673 max mem: 9390 +Train: [58] [2300/6250] eta: 0:11:01 lr: 0.000050 grad: 0.0946 (0.0975) loss: 0.8170 (0.8199) time: 0.1405 data: 0.0492 max mem: 9390 +Train: [58] [2400/6250] eta: 0:10:43 lr: 0.000050 grad: 0.0968 (0.0975) loss: 0.8226 (0.8199) time: 0.1406 data: 0.0566 max mem: 9390 +Train: [58] [2500/6250] eta: 0:10:26 lr: 0.000050 grad: 0.0942 (0.0976) loss: 0.8151 (0.8198) time: 0.1790 data: 0.0976 max mem: 9390 +Train: [58] [2600/6250] eta: 0:10:08 lr: 0.000050 grad: 0.0985 (0.0976) loss: 0.8187 (0.8198) time: 0.1533 data: 0.0699 max mem: 9390 +Train: [58] [2700/6250] eta: 0:09:50 lr: 0.000050 grad: 0.1003 (0.0975) loss: 0.8194 (0.8197) time: 0.1635 data: 0.0731 max mem: 9390 +Train: [58] [2800/6250] eta: 0:09:34 lr: 0.000050 grad: 0.0994 (0.0976) loss: 0.8151 (0.8196) time: 0.2124 data: 0.1132 max mem: 9390 +Train: [58] [2900/6250] eta: 0:09:17 lr: 0.000050 grad: 0.0909 (0.0977) loss: 0.8222 (0.8196) time: 0.1959 data: 0.0770 max mem: 9390 +Train: [58] [3000/6250] eta: 0:09:02 lr: 0.000050 grad: 0.0932 (0.0977) loss: 0.8215 (0.8195) time: 0.1676 data: 0.0682 max mem: 9390 +Train: [58] [3100/6250] eta: 0:08:45 lr: 0.000050 grad: 0.0962 (0.0979) loss: 0.8180 (0.8194) time: 0.1667 data: 0.0772 max mem: 9390 +Train: [58] [3200/6250] eta: 0:08:27 lr: 0.000050 grad: 0.1031 (0.0980) loss: 0.8174 (0.8193) time: 0.1538 data: 0.0630 max mem: 9390 +Train: [58] [3300/6250] eta: 0:08:10 lr: 0.000050 grad: 0.0999 (0.0981) loss: 0.8204 (0.8191) time: 0.1579 data: 0.0715 max mem: 9390 +Train: [58] [3400/6250] eta: 0:07:53 lr: 0.000050 grad: 0.0939 (0.0980) loss: 0.8220 (0.8191) time: 0.1660 data: 0.0733 max mem: 9390 +Train: [58] [3500/6250] eta: 0:07:37 lr: 0.000050 grad: 0.0999 (0.0980) loss: 0.8194 (0.8191) time: 0.1954 data: 0.1054 max mem: 9390 +Train: [58] [3600/6250] eta: 0:07:21 lr: 0.000050 grad: 0.0968 (0.0981) loss: 0.8166 (0.8190) time: 0.2368 data: 0.1640 max mem: 9390 +Train: [58] [3700/6250] eta: 0:07:06 lr: 0.000050 grad: 0.0991 (0.0982) loss: 0.8096 (0.8189) time: 0.2013 data: 0.1097 max mem: 9390 +Train: [58] [3800/6250] eta: 0:06:50 lr: 0.000050 grad: 0.1047 (0.0982) loss: 0.8138 (0.8188) time: 0.1988 data: 0.1175 max mem: 9390 +Train: [58] [3900/6250] eta: 0:06:34 lr: 0.000050 grad: 0.0998 (0.0983) loss: 0.8158 (0.8187) time: 0.1734 data: 0.0897 max mem: 9390 +Train: [58] [4000/6250] eta: 0:06:19 lr: 0.000050 grad: 0.1001 (0.0983) loss: 0.8121 (0.8187) time: 0.1825 data: 0.0999 max mem: 9390 +Train: [58] [4100/6250] eta: 0:06:03 lr: 0.000050 grad: 0.1023 (0.0984) loss: 0.8175 (0.8186) time: 0.1853 data: 0.0901 max mem: 9390 +Train: [58] [4200/6250] eta: 0:05:47 lr: 0.000050 grad: 0.1001 (0.0986) loss: 0.8126 (0.8185) time: 0.2100 data: 0.1310 max mem: 9390 +Train: [58] [4300/6250] eta: 0:05:30 lr: 0.000050 grad: 0.0993 (0.0986) loss: 0.8157 (0.8184) time: 0.1575 data: 0.0629 max mem: 9390 +Train: [58] [4400/6250] eta: 0:05:13 lr: 0.000050 grad: 0.0937 (0.0987) loss: 0.8152 (0.8184) time: 0.1654 data: 0.0754 max mem: 9390 +Train: [58] [4500/6250] eta: 0:04:56 lr: 0.000050 grad: 0.0955 (0.0988) loss: 0.8169 (0.8183) time: 0.1908 data: 0.1039 max mem: 9390 +Train: [58] [4600/6250] eta: 0:04:39 lr: 0.000050 grad: 0.0930 (0.0989) loss: 0.8192 (0.8182) time: 0.1342 data: 0.0476 max mem: 9390 +Train: [58] [4700/6250] eta: 0:04:22 lr: 0.000050 grad: 0.1002 (0.0989) loss: 0.8128 (0.8181) time: 0.1474 data: 0.0609 max mem: 9390 +Train: [58] [4800/6250] eta: 0:04:05 lr: 0.000050 grad: 0.0948 (0.0990) loss: 0.8175 (0.8180) time: 0.1754 data: 0.0853 max mem: 9390 +Train: [58] [4900/6250] eta: 0:03:49 lr: 0.000050 grad: 0.0985 (0.0991) loss: 0.8136 (0.8179) time: 0.1764 data: 0.0880 max mem: 9390 +Train: [58] [5000/6250] eta: 0:03:31 lr: 0.000050 grad: 0.0901 (0.0991) loss: 0.8189 (0.8179) time: 0.1381 data: 0.0511 max mem: 9390 +Train: [58] [5100/6250] eta: 0:03:14 lr: 0.000050 grad: 0.0974 (0.0991) loss: 0.8135 (0.8179) time: 0.1659 data: 0.0682 max mem: 9390 +Train: [58] [5200/6250] eta: 0:02:57 lr: 0.000050 grad: 0.0958 (0.0991) loss: 0.8115 (0.8178) time: 0.1608 data: 0.0694 max mem: 9390 +Train: [58] [5300/6250] eta: 0:02:40 lr: 0.000049 grad: 0.0988 (0.0992) loss: 0.8232 (0.8178) time: 0.1744 data: 0.0815 max mem: 9390 +Train: [58] [5400/6250] eta: 0:02:23 lr: 0.000049 grad: 0.0972 (0.0992) loss: 0.8181 (0.8177) time: 0.1469 data: 0.0523 max mem: 9390 +Train: [58] [5500/6250] eta: 0:02:06 lr: 0.000049 grad: 0.1008 (0.0993) loss: 0.8157 (0.8177) time: 0.2019 data: 0.1151 max mem: 9390 +Train: [58] [5600/6250] eta: 0:01:49 lr: 0.000049 grad: 0.0937 (0.0993) loss: 0.8116 (0.8177) time: 0.1705 data: 0.0767 max mem: 9390 +Train: [58] [5700/6250] eta: 0:01:32 lr: 0.000049 grad: 0.0999 (0.0994) loss: 0.8093 (0.8176) time: 0.1678 data: 0.0765 max mem: 9390 +Train: [58] [5800/6250] eta: 0:01:16 lr: 0.000049 grad: 0.0951 (0.0994) loss: 0.8141 (0.8175) time: 0.1705 data: 0.0787 max mem: 9390 +Train: [58] [5900/6250] eta: 0:00:59 lr: 0.000049 grad: 0.0984 (0.0996) loss: 0.8149 (0.8174) time: 0.1697 data: 0.0795 max mem: 9390 +Train: [58] [6000/6250] eta: 0:00:42 lr: 0.000049 grad: 0.0956 (0.0996) loss: 0.8196 (0.8174) time: 0.1531 data: 0.0637 max mem: 9390 +Train: [58] [6100/6250] eta: 0:00:25 lr: 0.000049 grad: 0.0956 (0.0997) loss: 0.8113 (0.8173) time: 0.1292 data: 0.0332 max mem: 9390 +Train: [58] [6200/6250] eta: 0:00:08 lr: 0.000049 grad: 0.1035 (0.0997) loss: 0.8169 (0.8173) time: 0.1727 data: 0.0922 max mem: 9390 +Train: [58] [6249/6250] eta: 0:00:00 lr: 0.000049 grad: 0.1007 (0.0997) loss: 0.8187 (0.8173) time: 0.1591 data: 0.0716 max mem: 9390 +Train: [58] Total time: 0:17:39 (0.1695 s / it) +Averaged stats: lr: 0.000049 grad: 0.1007 (0.0997) loss: 0.8187 (0.8173) +Eval (hcp-train-subset): [58] [ 0/62] eta: 0:04:06 loss: 0.8472 (0.8472) time: 3.9795 data: 3.9388 max mem: 9390 +Eval (hcp-train-subset): [58] [61/62] eta: 0:00:00 loss: 0.8331 (0.8350) time: 0.1309 data: 0.1051 max mem: 9390 +Eval (hcp-train-subset): [58] Total time: 0:00:14 (0.2270 s / it) +Averaged stats (hcp-train-subset): loss: 0.8331 (0.8350) +Eval (hcp-val): [58] [ 0/62] eta: 0:04:43 loss: 0.8312 (0.8312) time: 4.5791 data: 4.5491 max mem: 9390 +Eval (hcp-val): [58] [61/62] eta: 0:00:00 loss: 0.8324 (0.8336) time: 0.1273 data: 0.1020 max mem: 9390 +Eval (hcp-val): [58] Total time: 0:00:13 (0.2164 s / it) +Averaged stats (hcp-val): loss: 0.8324 (0.8336) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +Train: [59] [ 0/6250] eta: 10:39:03 lr: 0.000049 grad: 0.1724 (0.1724) loss: 0.8336 (0.8336) time: 6.1349 data: 6.0339 max mem: 9390 +Train: [59] [ 100/6250] eta: 0:22:54 lr: 0.000049 grad: 0.1044 (0.1150) loss: 0.8262 (0.8337) time: 0.1789 data: 0.0735 max mem: 9390 +Train: [59] [ 200/6250] eta: 0:20:00 lr: 0.000049 grad: 0.0953 (0.1111) loss: 0.8134 (0.8248) time: 0.1757 data: 0.0717 max mem: 9390 +Train: [59] [ 300/6250] eta: 0:18:47 lr: 0.000049 grad: 0.0957 (0.1084) loss: 0.8176 (0.8231) time: 0.2110 data: 0.1145 max mem: 9390 +Train: [59] [ 400/6250] eta: 0:17:56 lr: 0.000049 grad: 0.0880 (0.1060) loss: 0.8165 (0.8223) time: 0.1867 data: 0.0828 max mem: 9390 +Train: [59] [ 500/6250] eta: 0:17:39 lr: 0.000049 grad: 0.0964 (0.1043) loss: 0.8167 (0.8225) time: 0.1953 data: 0.0771 max mem: 9390 +Train: [59] [ 600/6250] eta: 0:17:26 lr: 0.000049 grad: 0.0859 (0.1027) loss: 0.8215 (0.8226) time: 0.2049 data: 0.0993 max mem: 9390 +Train: [59] [ 700/6250] eta: 0:17:11 lr: 0.000049 grad: 0.0928 (0.1020) loss: 0.8105 (0.8223) time: 0.2008 data: 0.0860 max mem: 9390 +Train: [59] [ 800/6250] eta: 0:16:49 lr: 0.000049 grad: 0.0898 (0.1010) loss: 0.8276 (0.8227) time: 0.1186 data: 0.0091 max mem: 9390 +Train: [59] [ 900/6250] eta: 0:16:32 lr: 0.000049 grad: 0.0950 (0.1004) loss: 0.8212 (0.8229) time: 0.1820 data: 0.0896 max mem: 9390 +Train: [59] [1000/6250] eta: 0:16:03 lr: 0.000049 grad: 0.0887 (0.0999) loss: 0.8205 (0.8228) time: 0.1351 data: 0.0400 max mem: 9390 +Train: [59] [1100/6250] eta: 0:15:33 lr: 0.000049 grad: 0.0938 (0.0995) loss: 0.8208 (0.8226) time: 0.1462 data: 0.0544 max mem: 9390 +Train: [59] [1200/6250] eta: 0:15:08 lr: 0.000049 grad: 0.0936 (0.0994) loss: 0.8237 (0.8224) time: 0.1693 data: 0.0789 max mem: 9390 +Train: [59] [1300/6250] eta: 0:14:43 lr: 0.000049 grad: 0.0950 (0.0993) loss: 0.8242 (0.8222) time: 0.1695 data: 0.0839 max mem: 9390 +Train: [59] [1400/6250] eta: 0:14:19 lr: 0.000049 grad: 0.0926 (0.0994) loss: 0.8206 (0.8220) time: 0.1456 data: 0.0523 max mem: 9390 +Train: [59] [1500/6250] eta: 0:13:58 lr: 0.000049 grad: 0.0950 (0.0993) loss: 0.8248 (0.8219) time: 0.1606 data: 0.0770 max mem: 9390 +Train: [59] [1600/6250] eta: 0:13:37 lr: 0.000049 grad: 0.0954 (0.0993) loss: 0.8151 (0.8216) time: 0.1230 data: 0.0260 max mem: 9390 +Train: [59] [1700/6250] eta: 0:13:16 lr: 0.000049 grad: 0.0925 (0.0992) loss: 0.8225 (0.8214) time: 0.1648 data: 0.0769 max mem: 9390 +Train: [59] [1800/6250] eta: 0:12:58 lr: 0.000049 grad: 0.0925 (0.0990) loss: 0.8206 (0.8213) time: 0.1784 data: 0.0890 max mem: 9390 +Train: [59] [1900/6250] eta: 0:12:37 lr: 0.000049 grad: 0.0931 (0.0990) loss: 0.8215 (0.8211) time: 0.1535 data: 0.0667 max mem: 9390 +Train: [59] [2000/6250] eta: 0:12:16 lr: 0.000049 grad: 0.0939 (0.0989) loss: 0.8142 (0.8210) time: 0.1774 data: 0.0880 max mem: 9390 +Train: [59] [2100/6250] eta: 0:11:58 lr: 0.000048 grad: 0.0957 (0.0987) loss: 0.8165 (0.8209) time: 0.1800 data: 0.0990 max mem: 9390 +Train: [59] [2200/6250] eta: 0:11:39 lr: 0.000048 grad: 0.0970 (0.0986) loss: 0.8179 (0.8208) time: 0.1523 data: 0.0687 max mem: 9390 +Train: [59] [2300/6250] eta: 0:11:24 lr: 0.000048 grad: 0.0911 (0.0985) loss: 0.8204 (0.8207) time: 0.1996 data: 0.1186 max mem: 9390 +Train: [59] [2400/6250] eta: 0:11:05 lr: 0.000048 grad: 0.0964 (0.0984) loss: 0.8206 (0.8207) time: 0.1878 data: 0.0994 max mem: 9390 +Train: [59] [2500/6250] eta: 0:10:47 lr: 0.000048 grad: 0.0905 (0.0983) loss: 0.8222 (0.8207) time: 0.1873 data: 0.1015 max mem: 9390 +Train: [59] [2600/6250] eta: 0:10:28 lr: 0.000048 grad: 0.0941 (0.0982) loss: 0.8191 (0.8206) time: 0.1595 data: 0.0706 max mem: 9390 +Train: [59] [2700/6250] eta: 0:10:15 lr: 0.000048 grad: 0.0938 (0.0981) loss: 0.8243 (0.8206) time: 0.1901 data: 0.1101 max mem: 9390 +Train: [59] [2800/6250] eta: 0:09:58 lr: 0.000048 grad: 0.0971 (0.0982) loss: 0.8200 (0.8205) time: 0.1828 data: 0.0982 max mem: 9390 +Train: [59] [2900/6250] eta: 0:09:41 lr: 0.000048 grad: 0.0944 (0.0981) loss: 0.8202 (0.8204) time: 0.1830 data: 0.0964 max mem: 9390 +Train: [59] [3000/6250] eta: 0:09:24 lr: 0.000048 grad: 0.0941 (0.0982) loss: 0.8228 (0.8204) time: 0.1604 data: 0.0711 max mem: 9390 +Train: [59] [3100/6250] eta: 0:09:10 lr: 0.000048 grad: 0.0990 (0.0981) loss: 0.8223 (0.8204) time: 0.2817 data: 0.1946 max mem: 9390 +Train: [59] [3200/6250] eta: 0:08:52 lr: 0.000048 grad: 0.0971 (0.0982) loss: 0.8170 (0.8204) time: 0.1480 data: 0.0524 max mem: 9390 +Train: [59] [3300/6250] eta: 0:08:33 lr: 0.000048 grad: 0.0989 (0.0982) loss: 0.8166 (0.8204) time: 0.1437 data: 0.0529 max mem: 9390 +Train: [59] [3400/6250] eta: 0:08:15 lr: 0.000048 grad: 0.0950 (0.0982) loss: 0.8205 (0.8204) time: 0.1611 data: 0.0797 max mem: 9390 +Train: [59] [3500/6250] eta: 0:07:56 lr: 0.000048 grad: 0.0956 (0.0981) loss: 0.8185 (0.8204) time: 0.1550 data: 0.0687 max mem: 9390 +Train: [59] [3600/6250] eta: 0:07:38 lr: 0.000048 grad: 0.0987 (0.0982) loss: 0.8194 (0.8204) time: 0.1787 data: 0.0961 max mem: 9390 +Train: [59] [3700/6250] eta: 0:07:20 lr: 0.000048 grad: 0.0941 (0.0982) loss: 0.8186 (0.8205) time: 0.1665 data: 0.0804 max mem: 9390 +Train: [59] [3800/6250] eta: 0:07:03 lr: 0.000048 grad: 0.1003 (0.0983) loss: 0.8200 (0.8204) time: 0.1695 data: 0.0783 max mem: 9390 +Train: [59] [3900/6250] eta: 0:06:45 lr: 0.000048 grad: 0.0915 (0.0982) loss: 0.8243 (0.8204) time: 0.1520 data: 0.0531 max mem: 9390 +Train: [59] [4000/6250] eta: 0:06:27 lr: 0.000048 grad: 0.0942 (0.0982) loss: 0.8263 (0.8204) time: 0.1650 data: 0.0754 max mem: 9390 +Train: [59] [4100/6250] eta: 0:06:09 lr: 0.000048 grad: 0.0925 (0.0982) loss: 0.8213 (0.8205) time: 0.1656 data: 0.0798 max mem: 9390 +Train: [59] [4200/6250] eta: 0:05:52 lr: 0.000048 grad: 0.0963 (0.0982) loss: 0.8243 (0.8205) time: 0.1576 data: 0.0593 max mem: 9390 +Train: [59] [4300/6250] eta: 0:05:35 lr: 0.000048 grad: 0.0992 (0.0982) loss: 0.8165 (0.8205) time: 0.1898 data: 0.1051 max mem: 9390 +Train: [59] [4400/6250] eta: 0:05:18 lr: 0.000048 grad: 0.0928 (0.0982) loss: 0.8207 (0.8205) time: 0.1666 data: 0.0795 max mem: 9390 +Train: [59] [4500/6250] eta: 0:05:00 lr: 0.000048 grad: 0.1002 (0.0983) loss: 0.8192 (0.8205) time: 0.1792 data: 0.0909 max mem: 9390 +Train: [59] [4600/6250] eta: 0:04:43 lr: 0.000048 grad: 0.1046 (0.0983) loss: 0.8214 (0.8204) time: 0.1718 data: 0.0867 max mem: 9390 +Train: [59] [4700/6250] eta: 0:04:26 lr: 0.000048 grad: 0.0952 (0.0984) loss: 0.8172 (0.8204) time: 0.1549 data: 0.0738 max mem: 9390 +Train: [59] [4800/6250] eta: 0:04:08 lr: 0.000048 grad: 0.0950 (0.0984) loss: 0.8159 (0.8203) time: 0.1669 data: 0.0805 max mem: 9390 +Train: [59] [4900/6250] eta: 0:03:51 lr: 0.000048 grad: 0.0977 (0.0985) loss: 0.8234 (0.8203) time: 0.1781 data: 0.0856 max mem: 9390 +Train: [59] [5000/6250] eta: 0:03:34 lr: 0.000048 grad: 0.1044 (0.0986) loss: 0.8158 (0.8203) time: 0.1544 data: 0.0593 max mem: 9390 +Train: [59] [5100/6250] eta: 0:03:17 lr: 0.000048 grad: 0.0949 (0.0987) loss: 0.8251 (0.8202) time: 0.1749 data: 0.0815 max mem: 9390 +Train: [59] [5200/6250] eta: 0:02:59 lr: 0.000047 grad: 0.0916 (0.0988) loss: 0.8178 (0.8202) time: 0.1562 data: 0.0606 max mem: 9390 +Train: [59] [5300/6250] eta: 0:02:42 lr: 0.000047 grad: 0.1042 (0.0989) loss: 0.8153 (0.8202) time: 0.1749 data: 0.0881 max mem: 9390 +Train: [59] [5400/6250] eta: 0:02:25 lr: 0.000047 grad: 0.0986 (0.0990) loss: 0.8231 (0.8202) time: 0.1525 data: 0.0550 max mem: 9390 +Train: [59] [5500/6250] eta: 0:02:08 lr: 0.000047 grad: 0.1003 (0.0991) loss: 0.8252 (0.8202) time: 0.1482 data: 0.0554 max mem: 9390 +Train: [59] [5600/6250] eta: 0:01:51 lr: 0.000047 grad: 0.1018 (0.0991) loss: 0.8206 (0.8202) time: 0.2493 data: 0.1594 max mem: 9390 +Train: [59] [5700/6250] eta: 0:01:34 lr: 0.000047 grad: 0.0963 (0.0991) loss: 0.8231 (0.8202) time: 0.1332 data: 0.0316 max mem: 9390 +Train: [59] [5800/6250] eta: 0:01:17 lr: 0.000047 grad: 0.0987 (0.0991) loss: 0.8218 (0.8203) time: 0.2213 data: 0.1181 max mem: 9390 +Train: [59] [5900/6250] eta: 0:00:59 lr: 0.000047 grad: 0.1008 (0.0992) loss: 0.8155 (0.8203) time: 0.1676 data: 0.0820 max mem: 9390 +Train: [59] [6000/6250] eta: 0:00:42 lr: 0.000047 grad: 0.0958 (0.0992) loss: 0.8195 (0.8202) time: 0.1552 data: 0.0583 max mem: 9390 +Train: [59] [6100/6250] eta: 0:00:25 lr: 0.000047 grad: 0.1005 (0.0993) loss: 0.8165 (0.8202) time: 0.1473 data: 0.0549 max mem: 9390 +Train: [59] [6200/6250] eta: 0:00:08 lr: 0.000047 grad: 0.0985 (0.0993) loss: 0.8239 (0.8202) time: 0.1571 data: 0.0631 max mem: 9390 +Train: [59] [6249/6250] eta: 0:00:00 lr: 0.000047 grad: 0.0987 (0.0994) loss: 0.8179 (0.8202) time: 0.1470 data: 0.0620 max mem: 9390 +Train: [59] Total time: 0:17:51 (0.1714 s / it) +Averaged stats: lr: 0.000047 grad: 0.0987 (0.0994) loss: 0.8179 (0.8202) +Eval (hcp-train-subset): [59] [ 0/62] eta: 0:03:57 loss: 0.8456 (0.8456) time: 3.8378 data: 3.7333 max mem: 9390 +Eval (hcp-train-subset): [59] [61/62] eta: 0:00:00 loss: 0.8333 (0.8343) time: 0.2048 data: 0.1799 max mem: 9390 +Eval (hcp-train-subset): [59] Total time: 0:00:14 (0.2409 s / it) +Averaged stats (hcp-train-subset): loss: 0.8333 (0.8343) +Making plots (hcp-train-subset): example=28 +Eval (hcp-val): [59] [ 0/62] eta: 0:04:06 loss: 0.8321 (0.8321) time: 3.9809 data: 3.9012 max mem: 9390 +Eval (hcp-val): [59] [61/62] eta: 0:00:00 loss: 0.8320 (0.8336) time: 0.1496 data: 0.1229 max mem: 9390 +Eval (hcp-val): [59] Total time: 0:00:13 (0.2227 s / it) +Averaged stats (hcp-val): loss: 0.8320 (0.8336) +Making plots (hcp-val): example=56 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +Train: [60] [ 0/6250] eta: 7:01:26 lr: 0.000047 grad: 0.0618 (0.0618) loss: 0.8436 (0.8436) time: 4.0458 data: 3.8146 max mem: 9390 +Train: [60] [ 100/6250] eta: 0:23:55 lr: 0.000047 grad: 0.0851 (0.0890) loss: 0.8385 (0.8398) time: 0.1831 data: 0.0942 max mem: 9390 +Train: [60] [ 200/6250] eta: 0:21:33 lr: 0.000047 grad: 0.0877 (0.0893) loss: 0.8293 (0.8357) time: 0.2235 data: 0.1262 max mem: 9390 +Train: [60] [ 300/6250] eta: 0:20:33 lr: 0.000047 grad: 0.1002 (0.0908) loss: 0.8227 (0.8328) time: 0.1782 data: 0.0843 max mem: 9390 +Train: [60] [ 400/6250] eta: 0:20:19 lr: 0.000047 grad: 0.0830 (0.0920) loss: 0.8202 (0.8301) time: 0.2179 data: 0.1300 max mem: 9390 +Train: [60] [ 500/6250] eta: 0:20:01 lr: 0.000047 grad: 0.0911 (0.0931) loss: 0.8308 (0.8286) time: 0.2056 data: 0.1036 max mem: 9390 +Train: [60] [ 600/6250] eta: 0:19:36 lr: 0.000047 grad: 0.0980 (0.0940) loss: 0.8216 (0.8268) time: 0.2334 data: 0.1318 max mem: 9390 +Train: [60] [ 700/6250] eta: 0:18:54 lr: 0.000047 grad: 0.0883 (0.0941) loss: 0.8200 (0.8255) time: 0.1753 data: 0.0830 max mem: 9390 +Train: [60] [ 800/6250] eta: 0:18:21 lr: 0.000047 grad: 0.0890 (0.0945) loss: 0.8219 (0.8248) time: 0.1986 data: 0.1071 max mem: 9390 +Train: [60] [ 900/6250] eta: 0:17:50 lr: 0.000047 grad: 0.0947 (0.0947) loss: 0.8199 (0.8244) time: 0.2014 data: 0.1129 max mem: 9390 +Train: [60] [1000/6250] eta: 0:17:16 lr: 0.000047 grad: 0.0919 (0.0946) loss: 0.8266 (0.8239) time: 0.1329 data: 0.0420 max mem: 9390 +Train: [60] [1100/6250] eta: 0:16:46 lr: 0.000047 grad: 0.0996 (0.0947) loss: 0.8240 (0.8237) time: 0.2042 data: 0.1154 max mem: 9390 +Train: [60] [1200/6250] eta: 0:16:12 lr: 0.000047 grad: 0.0962 (0.0949) loss: 0.8223 (0.8231) time: 0.1664 data: 0.0821 max mem: 9390 +Train: [60] [1300/6250] eta: 0:15:44 lr: 0.000047 grad: 0.0947 (0.0949) loss: 0.8165 (0.8228) time: 0.1484 data: 0.0629 max mem: 9390 +Train: [60] [1400/6250] eta: 0:15:15 lr: 0.000047 grad: 0.0963 (0.0951) loss: 0.8212 (0.8226) time: 0.1728 data: 0.0842 max mem: 9390 +Train: [60] [1500/6250] eta: 0:14:47 lr: 0.000047 grad: 0.0925 (0.0954) loss: 0.8192 (0.8222) time: 0.1656 data: 0.0710 max mem: 9390 +Train: [60] [1600/6250] eta: 0:14:19 lr: 0.000047 grad: 0.0953 (0.0955) loss: 0.8211 (0.8220) time: 0.1560 data: 0.0680 max mem: 9390 +Train: [60] [1700/6250] eta: 0:13:57 lr: 0.000047 grad: 0.0975 (0.0957) loss: 0.8231 (0.8217) time: 0.1706 data: 0.0851 max mem: 9390 +Train: [60] [1800/6250] eta: 0:13:34 lr: 0.000047 grad: 0.0987 (0.0959) loss: 0.8154 (0.8217) time: 0.1572 data: 0.0721 max mem: 9390 +Train: [60] [1900/6250] eta: 0:13:13 lr: 0.000047 grad: 0.0946 (0.0961) loss: 0.8244 (0.8216) time: 0.1571 data: 0.0649 max mem: 9390 +Train: [60] [2000/6250] eta: 0:12:51 lr: 0.000047 grad: 0.0997 (0.0962) loss: 0.8209 (0.8215) time: 0.1703 data: 0.0809 max mem: 9390 +Train: [60] [2100/6250] eta: 0:12:29 lr: 0.000046 grad: 0.1000 (0.0963) loss: 0.8244 (0.8213) time: 0.1400 data: 0.0495 max mem: 9390 +Train: [60] [2200/6250] eta: 0:12:08 lr: 0.000046 grad: 0.0937 (0.0963) loss: 0.8226 (0.8213) time: 0.1665 data: 0.0796 max mem: 9390 +Train: [60] [2300/6250] eta: 0:11:47 lr: 0.000046 grad: 0.0952 (0.0965) loss: 0.8186 (0.8213) time: 0.1800 data: 0.0912 max mem: 9390 +Train: [60] [2400/6250] eta: 0:11:27 lr: 0.000046 grad: 0.0972 (0.0966) loss: 0.8192 (0.8212) time: 0.1650 data: 0.0768 max mem: 9390 +Train: [60] [2500/6250] eta: 0:11:12 lr: 0.000046 grad: 0.0957 (0.0967) loss: 0.8167 (0.8210) time: 0.1756 data: 0.0885 max mem: 9390 +Train: [60] [2600/6250] eta: 0:10:53 lr: 0.000046 grad: 0.0945 (0.0968) loss: 0.8174 (0.8209) time: 0.1497 data: 0.0665 max mem: 9390 +Train: [60] [2700/6250] eta: 0:10:34 lr: 0.000046 grad: 0.0975 (0.0969) loss: 0.8158 (0.8207) time: 0.1700 data: 0.0838 max mem: 9390 +Train: [60] [2800/6250] eta: 0:10:15 lr: 0.000046 grad: 0.0938 (0.0968) loss: 0.8211 (0.8207) time: 0.1643 data: 0.0895 max mem: 9390 +Train: [60] [2900/6250] eta: 0:09:57 lr: 0.000046 grad: 0.0987 (0.0970) loss: 0.8164 (0.8206) time: 0.1935 data: 0.1084 max mem: 9390 +Train: [60] [3000/6250] eta: 0:09:40 lr: 0.000046 grad: 0.0926 (0.0970) loss: 0.8256 (0.8206) time: 0.1772 data: 0.0797 max mem: 9390 +Train: [60] [3100/6250] eta: 0:09:22 lr: 0.000046 grad: 0.0993 (0.0972) loss: 0.8204 (0.8206) time: 0.1541 data: 0.0591 max mem: 9390 +Train: [60] [3200/6250] eta: 0:09:05 lr: 0.000046 grad: 0.0965 (0.0973) loss: 0.8213 (0.8206) time: 0.1621 data: 0.0706 max mem: 9390 +Train: [60] [3300/6250] eta: 0:08:46 lr: 0.000046 grad: 0.0985 (0.0974) loss: 0.8184 (0.8205) time: 0.1418 data: 0.0499 max mem: 9390 +Train: [60] [3400/6250] eta: 0:08:28 lr: 0.000046 grad: 0.0951 (0.0975) loss: 0.8224 (0.8205) time: 0.1784 data: 0.0904 max mem: 9390 +Train: [60] [3500/6250] eta: 0:08:09 lr: 0.000046 grad: 0.1003 (0.0976) loss: 0.8150 (0.8204) time: 0.1685 data: 0.0644 max mem: 9390 +Train: [60] [3600/6250] eta: 0:07:51 lr: 0.000046 grad: 0.0957 (0.0977) loss: 0.8190 (0.8204) time: 0.1735 data: 0.0841 max mem: 9390 +Train: [60] [3700/6250] eta: 0:07:33 lr: 0.000046 grad: 0.1021 (0.0978) loss: 0.8159 (0.8203) time: 0.1791 data: 0.0819 max mem: 9390 +Train: [60] [3800/6250] eta: 0:07:15 lr: 0.000046 grad: 0.1012 (0.0979) loss: 0.8180 (0.8202) time: 0.2139 data: 0.1268 max mem: 9390 +Train: [60] [3900/6250] eta: 0:06:56 lr: 0.000046 grad: 0.1005 (0.0980) loss: 0.8193 (0.8202) time: 0.1773 data: 0.0928 max mem: 9390 +Train: [60] [4000/6250] eta: 0:06:38 lr: 0.000046 grad: 0.0960 (0.0981) loss: 0.8196 (0.8201) time: 0.1784 data: 0.0888 max mem: 9390 +Train: [60] [4100/6250] eta: 0:06:19 lr: 0.000046 grad: 0.1019 (0.0982) loss: 0.8132 (0.8200) time: 0.1719 data: 0.0849 max mem: 9390 +Train: [60] [4200/6250] eta: 0:06:01 lr: 0.000046 grad: 0.0958 (0.0983) loss: 0.8219 (0.8199) time: 0.1992 data: 0.1122 max mem: 9390 +Train: [60] [4300/6250] eta: 0:05:43 lr: 0.000046 grad: 0.0946 (0.0983) loss: 0.8132 (0.8198) time: 0.1562 data: 0.0677 max mem: 9390 +Train: [60] [4400/6250] eta: 0:05:25 lr: 0.000046 grad: 0.0994 (0.0984) loss: 0.8157 (0.8197) time: 0.1828 data: 0.0938 max mem: 9390 +Train: [60] [4500/6250] eta: 0:05:07 lr: 0.000046 grad: 0.0984 (0.0985) loss: 0.8129 (0.8196) time: 0.1798 data: 0.1027 max mem: 9390 +Train: [60] [4600/6250] eta: 0:04:49 lr: 0.000046 grad: 0.1028 (0.0985) loss: 0.8143 (0.8195) time: 0.1767 data: 0.0882 max mem: 9390 +Train: [60] [4700/6250] eta: 0:04:31 lr: 0.000046 grad: 0.0936 (0.0986) loss: 0.8128 (0.8194) time: 0.1629 data: 0.0818 max mem: 9390 +Train: [60] [4800/6250] eta: 0:04:14 lr: 0.000046 grad: 0.0989 (0.0986) loss: 0.8147 (0.8193) time: 0.1936 data: 0.1080 max mem: 9390 +Train: [60] [4900/6250] eta: 0:03:56 lr: 0.000046 grad: 0.0959 (0.0987) loss: 0.8135 (0.8192) time: 0.1688 data: 0.0763 max mem: 9390 +Train: [60] [5000/6250] eta: 0:03:38 lr: 0.000046 grad: 0.0920 (0.0989) loss: 0.8219 (0.8191) time: 0.1637 data: 0.0830 max mem: 9390 +Train: [60] [5100/6250] eta: 0:03:20 lr: 0.000046 grad: 0.0977 (0.0991) loss: 0.8050 (0.8191) time: 0.1516 data: 0.0669 max mem: 9390 +Train: [60] [5200/6250] eta: 0:03:03 lr: 0.000045 grad: 0.0991 (0.0991) loss: 0.8184 (0.8190) time: 0.1909 data: 0.1107 max mem: 9390 +Train: [60] [5300/6250] eta: 0:02:45 lr: 0.000045 grad: 0.1037 (0.0992) loss: 0.8043 (0.8189) time: 0.2398 data: 0.1104 max mem: 9390 +Train: [60] [5400/6250] eta: 0:02:28 lr: 0.000045 grad: 0.1017 (0.0993) loss: 0.8107 (0.8189) time: 0.1761 data: 0.0889 max mem: 9390 +Train: [60] [5500/6250] eta: 0:02:10 lr: 0.000045 grad: 0.0985 (0.0993) loss: 0.8171 (0.8188) time: 0.1211 data: 0.0314 max mem: 9390 +Train: [60] [5600/6250] eta: 0:01:53 lr: 0.000045 grad: 0.0995 (0.0994) loss: 0.8141 (0.8188) time: 0.1683 data: 0.0864 max mem: 9390 +Train: [60] [5700/6250] eta: 0:01:35 lr: 0.000045 grad: 0.1062 (0.0994) loss: 0.8141 (0.8187) time: 0.1567 data: 0.0762 max mem: 9390 +Train: [60] [5800/6250] eta: 0:01:18 lr: 0.000045 grad: 0.1079 (0.0995) loss: 0.8154 (0.8186) time: 0.1658 data: 0.0820 max mem: 9390 +Train: [60] [5900/6250] eta: 0:01:00 lr: 0.000045 grad: 0.1003 (0.0996) loss: 0.8194 (0.8185) time: 0.1662 data: 0.0769 max mem: 9390 +Train: [60] [6000/6250] eta: 0:00:43 lr: 0.000045 grad: 0.1007 (0.0997) loss: 0.8153 (0.8185) time: 0.1821 data: 0.0973 max mem: 9390 +Train: [60] [6100/6250] eta: 0:00:26 lr: 0.000045 grad: 0.1003 (0.0997) loss: 0.8142 (0.8184) time: 0.2023 data: 0.1145 max mem: 9390 +Train: [60] [6200/6250] eta: 0:00:08 lr: 0.000045 grad: 0.1000 (0.0997) loss: 0.8132 (0.8184) time: 0.1871 data: 0.0966 max mem: 9390 +Train: [60] [6249/6250] eta: 0:00:00 lr: 0.000045 grad: 0.1053 (0.0998) loss: 0.8181 (0.8183) time: 0.1738 data: 0.0858 max mem: 9390 +Train: [60] Total time: 0:18:09 (0.1744 s / it) +Averaged stats: lr: 0.000045 grad: 0.1053 (0.0998) loss: 0.8181 (0.8183) +Eval (hcp-train-subset): [60] [ 0/62] eta: 0:04:26 loss: 0.8448 (0.8448) time: 4.2959 data: 4.2356 max mem: 9390 +Eval (hcp-train-subset): [60] [61/62] eta: 0:00:00 loss: 0.8331 (0.8350) time: 0.1685 data: 0.1431 max mem: 9390 +Eval (hcp-train-subset): [60] Total time: 0:00:15 (0.2581 s / it) +Averaged stats (hcp-train-subset): loss: 0.8331 (0.8350) +Eval (hcp-val): [60] [ 0/62] eta: 0:04:20 loss: 0.8304 (0.8304) time: 4.2042 data: 4.1402 max mem: 9390 +Eval (hcp-val): [60] [61/62] eta: 0:00:00 loss: 0.8327 (0.8339) time: 0.1850 data: 0.1595 max mem: 9390 +Eval (hcp-val): [60] Total time: 0:00:15 (0.2544 s / it) +Averaged stats (hcp-val): loss: 0.8327 (0.8339) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +Train: [61] [ 0/6250] eta: 8:23:21 lr: 0.000045 grad: 0.2444 (0.2444) loss: 0.8292 (0.8292) time: 4.8323 data: 4.6460 max mem: 9390 +Train: [61] [ 100/6250] eta: 0:26:44 lr: 0.000045 grad: 0.0976 (0.1217) loss: 0.8281 (0.8342) time: 0.1997 data: 0.0962 max mem: 9390 +Train: [61] [ 200/6250] eta: 0:22:21 lr: 0.000045 grad: 0.1008 (0.1119) loss: 0.8247 (0.8286) time: 0.2062 data: 0.1150 max mem: 9390 +Train: [61] [ 300/6250] eta: 0:20:15 lr: 0.000045 grad: 0.0898 (0.1063) loss: 0.8290 (0.8273) time: 0.1881 data: 0.0879 max mem: 9390 +Train: [61] [ 400/6250] eta: 0:19:12 lr: 0.000045 grad: 0.0956 (0.1038) loss: 0.8244 (0.8261) time: 0.1816 data: 0.0921 max mem: 9390 +Train: [61] [ 500/6250] eta: 0:18:22 lr: 0.000045 grad: 0.1020 (0.1036) loss: 0.8161 (0.8251) time: 0.1719 data: 0.0721 max mem: 9390 +Train: [61] [ 600/6250] eta: 0:17:45 lr: 0.000045 grad: 0.0989 (0.1033) loss: 0.8165 (0.8238) time: 0.1664 data: 0.0575 max mem: 9390 +Train: [61] [ 700/6250] eta: 0:17:00 lr: 0.000045 grad: 0.1012 (0.1034) loss: 0.8165 (0.8229) time: 0.1585 data: 0.0439 max mem: 9390 +Train: [61] [ 800/6250] eta: 0:16:27 lr: 0.000045 grad: 0.0995 (0.1038) loss: 0.8176 (0.8220) time: 0.1470 data: 0.0432 max mem: 9390 +Train: [61] [ 900/6250] eta: 0:16:06 lr: 0.000045 grad: 0.1010 (0.1038) loss: 0.8118 (0.8212) time: 0.1912 data: 0.1025 max mem: 9390 +Train: [61] [1000/6250] eta: 0:15:40 lr: 0.000045 grad: 0.1024 (0.1035) loss: 0.8123 (0.8206) time: 0.1678 data: 0.0803 max mem: 9390 +Train: [61] [1100/6250] eta: 0:15:15 lr: 0.000045 grad: 0.0936 (0.1032) loss: 0.8153 (0.8200) time: 0.1695 data: 0.0731 max mem: 9390 +Train: [61] [1200/6250] eta: 0:14:53 lr: 0.000045 grad: 0.1024 (0.1032) loss: 0.8170 (0.8197) time: 0.1847 data: 0.1015 max mem: 9390 +Train: [61] [1300/6250] eta: 0:14:33 lr: 0.000045 grad: 0.0993 (0.1032) loss: 0.8109 (0.8191) time: 0.1812 data: 0.1005 max mem: 9390 +Train: [61] [1400/6250] eta: 0:14:09 lr: 0.000045 grad: 0.1006 (0.1032) loss: 0.8161 (0.8188) time: 0.1594 data: 0.0731 max mem: 9390 +Train: [61] [1500/6250] eta: 0:13:50 lr: 0.000045 grad: 0.1000 (0.1031) loss: 0.8152 (0.8185) time: 0.1584 data: 0.0748 max mem: 9390 +Train: [61] [1600/6250] eta: 0:13:32 lr: 0.000045 grad: 0.0998 (0.1030) loss: 0.8117 (0.8183) time: 0.1557 data: 0.0667 max mem: 9390 +Train: [61] [1700/6250] eta: 0:13:17 lr: 0.000045 grad: 0.0956 (0.1032) loss: 0.8149 (0.8181) time: 0.1142 data: 0.0238 max mem: 9390 +Train: [61] [1800/6250] eta: 0:12:57 lr: 0.000045 grad: 0.1105 (0.1032) loss: 0.8162 (0.8180) time: 0.1397 data: 0.0442 max mem: 9390 +Train: [61] [1900/6250] eta: 0:12:36 lr: 0.000045 grad: 0.0979 (0.1032) loss: 0.8145 (0.8179) time: 0.1605 data: 0.0739 max mem: 9390 +Train: [61] [2000/6250] eta: 0:12:18 lr: 0.000045 grad: 0.1021 (0.1034) loss: 0.8144 (0.8176) time: 0.1889 data: 0.0931 max mem: 9390 +Train: [61] [2100/6250] eta: 0:12:00 lr: 0.000044 grad: 0.1054 (0.1034) loss: 0.8126 (0.8174) time: 0.1604 data: 0.0690 max mem: 9390 +Train: [61] [2200/6250] eta: 0:11:41 lr: 0.000044 grad: 0.1088 (0.1035) loss: 0.8089 (0.8173) time: 0.1562 data: 0.0582 max mem: 9390 +Train: [61] [2300/6250] eta: 0:11:24 lr: 0.000044 grad: 0.0993 (0.1037) loss: 0.8165 (0.8172) time: 0.1486 data: 0.0600 max mem: 9390 +Train: [61] [2400/6250] eta: 0:11:06 lr: 0.000044 grad: 0.1052 (0.1038) loss: 0.8124 (0.8170) time: 0.1674 data: 0.0751 max mem: 9390 +Train: [61] [2500/6250] eta: 0:10:48 lr: 0.000044 grad: 0.1094 (0.1041) loss: 0.8182 (0.8169) time: 0.1649 data: 0.0767 max mem: 9390 +Train: [61] [2600/6250] eta: 0:10:30 lr: 0.000044 grad: 0.1115 (0.1043) loss: 0.8110 (0.8168) time: 0.1883 data: 0.1064 max mem: 9390 +Train: [61] [2700/6250] eta: 0:10:15 lr: 0.000044 grad: 0.1041 (0.1043) loss: 0.8156 (0.8168) time: 0.1929 data: 0.1006 max mem: 9390 +Train: [61] [2800/6250] eta: 0:09:57 lr: 0.000044 grad: 0.1060 (0.1044) loss: 0.8150 (0.8167) time: 0.1568 data: 0.0652 max mem: 9390 +Train: [61] [2900/6250] eta: 0:09:39 lr: 0.000044 grad: 0.1049 (0.1045) loss: 0.8124 (0.8167) time: 0.1841 data: 0.0954 max mem: 9390 +Train: [61] [3000/6250] eta: 0:09:24 lr: 0.000044 grad: 0.1026 (0.1045) loss: 0.8159 (0.8167) time: 0.1551 data: 0.0653 max mem: 9390 +Train: [61] [3100/6250] eta: 0:09:08 lr: 0.000044 grad: 0.1027 (0.1046) loss: 0.8177 (0.8168) time: 0.1783 data: 0.0847 max mem: 9390 +Train: [61] [3200/6250] eta: 0:08:52 lr: 0.000044 grad: 0.1009 (0.1046) loss: 0.8203 (0.8169) time: 0.2351 data: 0.1473 max mem: 9390 +Train: [61] [3300/6250] eta: 0:08:33 lr: 0.000044 grad: 0.1036 (0.1046) loss: 0.8182 (0.8169) time: 0.1710 data: 0.0875 max mem: 9390 +Train: [61] [3400/6250] eta: 0:08:15 lr: 0.000044 grad: 0.1026 (0.1046) loss: 0.8204 (0.8169) time: 0.1677 data: 0.0802 max mem: 9390 +Train: [61] [3500/6250] eta: 0:07:57 lr: 0.000044 grad: 0.0973 (0.1045) loss: 0.8195 (0.8170) time: 0.1649 data: 0.0703 max mem: 9390 +Train: [61] [3600/6250] eta: 0:07:40 lr: 0.000044 grad: 0.0997 (0.1045) loss: 0.8189 (0.8170) time: 0.1821 data: 0.0831 max mem: 9390 +Train: [61] [3700/6250] eta: 0:07:22 lr: 0.000044 grad: 0.0996 (0.1045) loss: 0.8111 (0.8170) time: 0.1613 data: 0.0754 max mem: 9390 +Train: [61] [3800/6250] eta: 0:07:05 lr: 0.000044 grad: 0.1018 (0.1045) loss: 0.8180 (0.8171) time: 0.1767 data: 0.0904 max mem: 9390 +Train: [61] [3900/6250] eta: 0:06:47 lr: 0.000044 grad: 0.0988 (0.1045) loss: 0.8218 (0.8171) time: 0.1708 data: 0.0815 max mem: 9390 +Train: [61] [4000/6250] eta: 0:06:29 lr: 0.000044 grad: 0.0980 (0.1044) loss: 0.8199 (0.8172) time: 0.1701 data: 0.0723 max mem: 9390 +Train: [61] [4100/6250] eta: 0:06:11 lr: 0.000044 grad: 0.0955 (0.1044) loss: 0.8183 (0.8172) time: 0.1555 data: 0.0701 max mem: 9390 +Train: [61] [4200/6250] eta: 0:05:53 lr: 0.000044 grad: 0.1041 (0.1044) loss: 0.8135 (0.8173) time: 0.1318 data: 0.0402 max mem: 9390 +Train: [61] [4300/6250] eta: 0:05:36 lr: 0.000044 grad: 0.0985 (0.1044) loss: 0.8087 (0.8173) time: 0.1754 data: 0.0883 max mem: 9390 +Train: [61] [4400/6250] eta: 0:05:19 lr: 0.000044 grad: 0.0986 (0.1044) loss: 0.8181 (0.8173) time: 0.1944 data: 0.1086 max mem: 9390 +Train: [61] [4500/6250] eta: 0:05:01 lr: 0.000044 grad: 0.0970 (0.1043) loss: 0.8189 (0.8173) time: 0.1524 data: 0.0637 max mem: 9390 +Train: [61] [4600/6250] eta: 0:04:43 lr: 0.000044 grad: 0.0927 (0.1042) loss: 0.8212 (0.8173) time: 0.1515 data: 0.0640 max mem: 9390 +Train: [61] [4700/6250] eta: 0:04:26 lr: 0.000044 grad: 0.0945 (0.1042) loss: 0.8207 (0.8173) time: 0.1872 data: 0.0937 max mem: 9390 +Train: [61] [4800/6250] eta: 0:04:09 lr: 0.000044 grad: 0.0926 (0.1042) loss: 0.8203 (0.8173) time: 0.1464 data: 0.0679 max mem: 9390 +Train: [61] [4900/6250] eta: 0:03:52 lr: 0.000044 grad: 0.1050 (0.1043) loss: 0.8207 (0.8173) time: 0.1734 data: 0.0873 max mem: 9390 +Train: [61] [5000/6250] eta: 0:03:34 lr: 0.000044 grad: 0.1052 (0.1043) loss: 0.8135 (0.8173) time: 0.1755 data: 0.0900 max mem: 9390 +Train: [61] [5100/6250] eta: 0:03:17 lr: 0.000044 grad: 0.0979 (0.1044) loss: 0.8177 (0.8172) time: 0.1207 data: 0.0250 max mem: 9390 +Train: [61] [5200/6250] eta: 0:03:00 lr: 0.000044 grad: 0.0982 (0.1044) loss: 0.8173 (0.8172) time: 0.1632 data: 0.0729 max mem: 9390 +Train: [61] [5300/6250] eta: 0:02:43 lr: 0.000043 grad: 0.1043 (0.1045) loss: 0.8128 (0.8171) time: 0.1460 data: 0.0624 max mem: 9390 +Train: [61] [5400/6250] eta: 0:02:25 lr: 0.000043 grad: 0.0991 (0.1045) loss: 0.8130 (0.8171) time: 0.1739 data: 0.0718 max mem: 9390 +Train: [61] [5500/6250] eta: 0:02:08 lr: 0.000043 grad: 0.1000 (0.1044) loss: 0.8148 (0.8170) time: 0.1671 data: 0.0768 max mem: 9390 +Train: [61] [5600/6250] eta: 0:01:51 lr: 0.000043 grad: 0.0997 (0.1044) loss: 0.8085 (0.8170) time: 0.1518 data: 0.0712 max mem: 9390 +Train: [61] [5700/6250] eta: 0:01:34 lr: 0.000043 grad: 0.1014 (0.1044) loss: 0.8149 (0.8169) time: 0.1743 data: 0.0866 max mem: 9390 +Train: [61] [5800/6250] eta: 0:01:16 lr: 0.000043 grad: 0.1025 (0.1044) loss: 0.8187 (0.8169) time: 0.1372 data: 0.0418 max mem: 9390 +Train: [61] [5900/6250] eta: 0:00:59 lr: 0.000043 grad: 0.0964 (0.1044) loss: 0.8164 (0.8169) time: 0.1298 data: 0.0401 max mem: 9390 +Train: [61] [6000/6250] eta: 0:00:42 lr: 0.000043 grad: 0.1078 (0.1044) loss: 0.8188 (0.8169) time: 0.1856 data: 0.0982 max mem: 9390 +Train: [61] [6100/6250] eta: 0:00:25 lr: 0.000043 grad: 0.1014 (0.1044) loss: 0.8228 (0.8170) time: 0.1262 data: 0.0358 max mem: 9390 +Train: [61] [6200/6250] eta: 0:00:08 lr: 0.000043 grad: 0.1018 (0.1044) loss: 0.8191 (0.8170) time: 0.2566 data: 0.1669 max mem: 9390 +Train: [61] [6249/6250] eta: 0:00:00 lr: 0.000043 grad: 0.1036 (0.1044) loss: 0.8202 (0.8170) time: 0.1602 data: 0.0706 max mem: 9390 +Train: [61] Total time: 0:17:57 (0.1724 s / it) +Averaged stats: lr: 0.000043 grad: 0.1036 (0.1044) loss: 0.8202 (0.8170) +Eval (hcp-train-subset): [61] [ 0/62] eta: 0:04:56 loss: 0.8432 (0.8432) time: 4.7832 data: 4.7496 max mem: 9390 +Eval (hcp-train-subset): [61] [61/62] eta: 0:00:00 loss: 0.8309 (0.8335) time: 0.1355 data: 0.1083 max mem: 9390 +Eval (hcp-train-subset): [61] Total time: 0:00:15 (0.2551 s / it) +Averaged stats (hcp-train-subset): loss: 0.8309 (0.8335) +Eval (hcp-val): [61] [ 0/62] eta: 0:03:46 loss: 0.8309 (0.8309) time: 3.6514 data: 3.5551 max mem: 9390 +Eval (hcp-val): [61] [61/62] eta: 0:00:00 loss: 0.8315 (0.8334) time: 0.1520 data: 0.1264 max mem: 9390 +Eval (hcp-val): [61] Total time: 0:00:14 (0.2269 s / it) +Averaged stats (hcp-val): loss: 0.8315 (0.8334) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +Train: [62] [ 0/6250] eta: 10:27:51 lr: 0.000043 grad: 0.3132 (0.3132) loss: 0.8381 (0.8381) time: 6.0274 data: 5.9064 max mem: 9390 +Train: [62] [ 100/6250] eta: 0:25:20 lr: 0.000043 grad: 0.1014 (0.1199) loss: 0.8227 (0.8291) time: 0.1685 data: 0.0696 max mem: 9390 +Train: [62] [ 200/6250] eta: 0:21:48 lr: 0.000043 grad: 0.1139 (0.1181) loss: 0.8155 (0.8223) time: 0.1901 data: 0.0916 max mem: 9390 +Train: [62] [ 300/6250] eta: 0:20:43 lr: 0.000043 grad: 0.0920 (0.1141) loss: 0.8185 (0.8208) time: 0.1910 data: 0.0921 max mem: 9390 +Train: [62] [ 400/6250] eta: 0:19:52 lr: 0.000043 grad: 0.1013 (0.1108) loss: 0.8163 (0.8212) time: 0.2018 data: 0.1109 max mem: 9390 +Train: [62] [ 500/6250] eta: 0:19:12 lr: 0.000043 grad: 0.0981 (0.1096) loss: 0.8207 (0.8211) time: 0.1791 data: 0.0707 max mem: 9390 +Train: [62] [ 600/6250] eta: 0:18:41 lr: 0.000043 grad: 0.0976 (0.1081) loss: 0.8206 (0.8213) time: 0.1965 data: 0.0988 max mem: 9390 +Train: [62] [ 700/6250] eta: 0:18:14 lr: 0.000043 grad: 0.0993 (0.1069) loss: 0.8234 (0.8214) time: 0.2240 data: 0.1211 max mem: 9390 +Train: [62] [ 800/6250] eta: 0:17:37 lr: 0.000043 grad: 0.1019 (0.1068) loss: 0.8237 (0.8214) time: 0.1894 data: 0.0961 max mem: 9390 +Train: [62] [ 900/6250] eta: 0:17:06 lr: 0.000043 grad: 0.0988 (0.1061) loss: 0.8206 (0.8213) time: 0.1534 data: 0.0526 max mem: 9390 +Train: [62] [1000/6250] eta: 0:16:39 lr: 0.000043 grad: 0.1008 (0.1055) loss: 0.8207 (0.8214) time: 0.1885 data: 0.0962 max mem: 9390 +Train: [62] [1100/6250] eta: 0:16:09 lr: 0.000043 grad: 0.1025 (0.1050) loss: 0.8233 (0.8215) time: 0.1787 data: 0.0879 max mem: 9390 +Train: [62] [1200/6250] eta: 0:15:37 lr: 0.000043 grad: 0.0988 (0.1044) loss: 0.8152 (0.8214) time: 0.1596 data: 0.0622 max mem: 9390 +Train: [62] [1300/6250] eta: 0:15:08 lr: 0.000043 grad: 0.0983 (0.1041) loss: 0.8210 (0.8213) time: 0.1669 data: 0.0788 max mem: 9390 +Train: [62] [1400/6250] eta: 0:14:46 lr: 0.000043 grad: 0.0992 (0.1038) loss: 0.8182 (0.8211) time: 0.1815 data: 0.0707 max mem: 9390 +Train: [62] [1500/6250] eta: 0:14:25 lr: 0.000043 grad: 0.0986 (0.1037) loss: 0.8219 (0.8210) time: 0.1187 data: 0.0181 max mem: 9390 +Train: [62] [1600/6250] eta: 0:14:06 lr: 0.000043 grad: 0.1001 (0.1034) loss: 0.8201 (0.8210) time: 0.1937 data: 0.1116 max mem: 9390 +Train: [62] [1700/6250] eta: 0:13:48 lr: 0.000043 grad: 0.0994 (0.1033) loss: 0.8183 (0.8209) time: 0.1880 data: 0.1105 max mem: 9390 +Train: [62] [1800/6250] eta: 0:13:28 lr: 0.000043 grad: 0.0999 (0.1032) loss: 0.8158 (0.8208) time: 0.1818 data: 0.0895 max mem: 9390 +Train: [62] [1900/6250] eta: 0:13:10 lr: 0.000043 grad: 0.1015 (0.1031) loss: 0.8187 (0.8208) time: 0.2068 data: 0.1277 max mem: 9390 +Train: [62] [2000/6250] eta: 0:12:51 lr: 0.000043 grad: 0.1008 (0.1030) loss: 0.8198 (0.8206) time: 0.1790 data: 0.0841 max mem: 9390 +Train: [62] [2100/6250] eta: 0:12:32 lr: 0.000043 grad: 0.1060 (0.1031) loss: 0.8190 (0.8205) time: 0.1780 data: 0.0792 max mem: 9390 +Train: [62] [2200/6250] eta: 0:12:13 lr: 0.000042 grad: 0.0923 (0.1031) loss: 0.8183 (0.8205) time: 0.1832 data: 0.0839 max mem: 9390 +Train: [62] [2300/6250] eta: 0:11:54 lr: 0.000042 grad: 0.0948 (0.1029) loss: 0.8186 (0.8204) time: 0.1626 data: 0.0730 max mem: 9390 +Train: [62] [2400/6250] eta: 0:11:34 lr: 0.000042 grad: 0.0991 (0.1029) loss: 0.8223 (0.8203) time: 0.1752 data: 0.0798 max mem: 9390 +Train: [62] [2500/6250] eta: 0:11:13 lr: 0.000042 grad: 0.0956 (0.1028) loss: 0.8223 (0.8204) time: 0.1504 data: 0.0632 max mem: 9390 +Train: [62] [2600/6250] eta: 0:10:54 lr: 0.000042 grad: 0.1012 (0.1028) loss: 0.8198 (0.8203) time: 0.1534 data: 0.0591 max mem: 9390 +Train: [62] [2700/6250] eta: 0:10:35 lr: 0.000042 grad: 0.1050 (0.1029) loss: 0.8124 (0.8203) time: 0.1722 data: 0.0898 max mem: 9390 +Train: [62] [2800/6250] eta: 0:10:15 lr: 0.000042 grad: 0.0929 (0.1029) loss: 0.8204 (0.8203) time: 0.1606 data: 0.0732 max mem: 9390 +Train: [62] [2900/6250] eta: 0:09:59 lr: 0.000042 grad: 0.0990 (0.1029) loss: 0.8180 (0.8203) time: 0.2632 data: 0.1798 max mem: 9390 +Train: [62] [3000/6250] eta: 0:09:38 lr: 0.000042 grad: 0.0939 (0.1029) loss: 0.8192 (0.8202) time: 0.1576 data: 0.0693 max mem: 9390 +Train: [62] [3100/6250] eta: 0:09:20 lr: 0.000042 grad: 0.1038 (0.1029) loss: 0.8180 (0.8201) time: 0.1740 data: 0.0891 max mem: 9390 +Train: [62] [3200/6250] eta: 0:09:02 lr: 0.000042 grad: 0.0993 (0.1029) loss: 0.8173 (0.8200) time: 0.1842 data: 0.1018 max mem: 9390 +Train: [62] [3300/6250] eta: 0:08:43 lr: 0.000042 grad: 0.0984 (0.1029) loss: 0.8167 (0.8199) time: 0.1690 data: 0.0857 max mem: 9390 +Train: [62] [3400/6250] eta: 0:08:25 lr: 0.000042 grad: 0.1016 (0.1030) loss: 0.8214 (0.8198) time: 0.1463 data: 0.0666 max mem: 9390 +Train: [62] [3500/6250] eta: 0:08:07 lr: 0.000042 grad: 0.1037 (0.1031) loss: 0.8081 (0.8197) time: 0.1922 data: 0.0963 max mem: 9390 +Train: [62] [3600/6250] eta: 0:07:49 lr: 0.000042 grad: 0.0980 (0.1031) loss: 0.8138 (0.8196) time: 0.1805 data: 0.1007 max mem: 9390 +Train: [62] [3700/6250] eta: 0:07:31 lr: 0.000042 grad: 0.1027 (0.1031) loss: 0.8143 (0.8195) time: 0.1883 data: 0.1034 max mem: 9390 +Train: [62] [3800/6250] eta: 0:07:12 lr: 0.000042 grad: 0.1062 (0.1033) loss: 0.8137 (0.8194) time: 0.1655 data: 0.0755 max mem: 9390 +Train: [62] [3900/6250] eta: 0:06:55 lr: 0.000042 grad: 0.1042 (0.1034) loss: 0.8200 (0.8193) time: 0.2514 data: 0.1572 max mem: 9390 +Train: [62] [4000/6250] eta: 0:06:36 lr: 0.000042 grad: 0.1052 (0.1034) loss: 0.8170 (0.8192) time: 0.1339 data: 0.0460 max mem: 9390 +Train: [62] [4100/6250] eta: 0:06:19 lr: 0.000042 grad: 0.0982 (0.1034) loss: 0.8176 (0.8191) time: 0.2156 data: 0.1097 max mem: 9390 +Train: [62] [4200/6250] eta: 0:06:01 lr: 0.000042 grad: 0.1062 (0.1037) loss: 0.8117 (0.8189) time: 0.1635 data: 0.0714 max mem: 9390 +Train: [62] [4300/6250] eta: 0:05:43 lr: 0.000042 grad: 0.1001 (0.1038) loss: 0.8167 (0.8188) time: 0.1548 data: 0.0649 max mem: 9390 +Train: [62] [4400/6250] eta: 0:05:25 lr: 0.000042 grad: 0.1037 (0.1038) loss: 0.8103 (0.8187) time: 0.1545 data: 0.0671 max mem: 9390 +Train: [62] [4500/6250] eta: 0:05:07 lr: 0.000042 grad: 0.0967 (0.1039) loss: 0.8185 (0.8186) time: 0.1375 data: 0.0385 max mem: 9390 +Train: [62] [4600/6250] eta: 0:04:50 lr: 0.000042 grad: 0.1062 (0.1039) loss: 0.8128 (0.8185) time: 0.1768 data: 0.0843 max mem: 9390 +Train: [62] [4700/6250] eta: 0:04:32 lr: 0.000042 grad: 0.1037 (0.1040) loss: 0.8129 (0.8184) time: 0.2579 data: 0.1664 max mem: 9390 +Train: [62] [4800/6250] eta: 0:04:14 lr: 0.000042 grad: 0.1013 (0.1041) loss: 0.8117 (0.8183) time: 0.1692 data: 0.0775 max mem: 9390 +Train: [62] [4900/6250] eta: 0:03:56 lr: 0.000042 grad: 0.1067 (0.1042) loss: 0.8149 (0.8182) time: 0.1512 data: 0.0620 max mem: 9390 +Train: [62] [5000/6250] eta: 0:03:39 lr: 0.000042 grad: 0.1049 (0.1043) loss: 0.8129 (0.8181) time: 0.1599 data: 0.0708 max mem: 9390 +Train: [62] [5100/6250] eta: 0:03:21 lr: 0.000042 grad: 0.1082 (0.1044) loss: 0.8125 (0.8180) time: 0.1855 data: 0.0982 max mem: 9390 +Train: [62] [5200/6250] eta: 0:03:03 lr: 0.000042 grad: 0.1081 (0.1044) loss: 0.8128 (0.8178) time: 0.1858 data: 0.1027 max mem: 9390 +Train: [62] [5300/6250] eta: 0:02:46 lr: 0.000042 grad: 0.1059 (0.1045) loss: 0.8166 (0.8177) time: 0.1594 data: 0.0789 max mem: 9390 +Train: [62] [5400/6250] eta: 0:02:28 lr: 0.000041 grad: 0.1026 (0.1045) loss: 0.8107 (0.8176) time: 0.1461 data: 0.0613 max mem: 9390 +Train: [62] [5500/6250] eta: 0:02:11 lr: 0.000041 grad: 0.1048 (0.1046) loss: 0.8116 (0.8175) time: 0.1789 data: 0.0899 max mem: 9390 +Train: [62] [5600/6250] eta: 0:01:53 lr: 0.000041 grad: 0.1028 (0.1046) loss: 0.8146 (0.8175) time: 0.1927 data: 0.1034 max mem: 9390 +Train: [62] [5700/6250] eta: 0:01:36 lr: 0.000041 grad: 0.1050 (0.1046) loss: 0.8200 (0.8175) time: 0.1538 data: 0.0716 max mem: 9390 +Train: [62] [5800/6250] eta: 0:01:18 lr: 0.000041 grad: 0.1057 (0.1047) loss: 0.8184 (0.8174) time: 0.1423 data: 0.0530 max mem: 9390 +Train: [62] [5900/6250] eta: 0:01:01 lr: 0.000041 grad: 0.1052 (0.1047) loss: 0.8118 (0.8174) time: 0.1878 data: 0.1055 max mem: 9390 +Train: [62] [6000/6250] eta: 0:00:43 lr: 0.000041 grad: 0.1044 (0.1047) loss: 0.8125 (0.8174) time: 0.1616 data: 0.0625 max mem: 9390 +Train: [62] [6100/6250] eta: 0:00:26 lr: 0.000041 grad: 0.1097 (0.1048) loss: 0.8063 (0.8173) time: 0.1478 data: 0.0610 max mem: 9390 +Train: [62] [6200/6250] eta: 0:00:08 lr: 0.000041 grad: 0.1046 (0.1048) loss: 0.8128 (0.8173) time: 0.1431 data: 0.0474 max mem: 9390 +Train: [62] [6249/6250] eta: 0:00:00 lr: 0.000041 grad: 0.1097 (0.1048) loss: 0.8210 (0.8173) time: 0.1525 data: 0.0608 max mem: 9390 +Train: [62] Total time: 0:18:19 (0.1759 s / it) +Averaged stats: lr: 0.000041 grad: 0.1097 (0.1048) loss: 0.8210 (0.8173) +Eval (hcp-train-subset): [62] [ 0/62] eta: 0:04:59 loss: 0.8414 (0.8414) time: 4.8251 data: 4.7949 max mem: 9390 +Eval (hcp-train-subset): [62] [61/62] eta: 0:00:00 loss: 0.8332 (0.8341) time: 0.1624 data: 0.1373 max mem: 9390 +Eval (hcp-train-subset): [62] Total time: 0:00:15 (0.2494 s / it) +Averaged stats (hcp-train-subset): loss: 0.8332 (0.8341) +Eval (hcp-val): [62] [ 0/62] eta: 0:04:08 loss: 0.8350 (0.8350) time: 4.0156 data: 3.9338 max mem: 9390 +Eval (hcp-val): [62] [61/62] eta: 0:00:00 loss: 0.8328 (0.8342) time: 0.1265 data: 0.1017 max mem: 9390 +Eval (hcp-val): [62] Total time: 0:00:13 (0.2207 s / it) +Averaged stats (hcp-val): loss: 0.8328 (0.8342) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +Train: [63] [ 0/6250] eta: 7:34:43 lr: 0.000041 grad: 0.2165 (0.2165) loss: 0.8398 (0.8398) time: 4.3654 data: 4.1511 max mem: 9390 +Train: [63] [ 100/6250] eta: 0:21:49 lr: 0.000041 grad: 0.1017 (0.1286) loss: 0.8297 (0.8266) time: 0.1960 data: 0.1121 max mem: 9390 +Train: [63] [ 200/6250] eta: 0:19:45 lr: 0.000041 grad: 0.1021 (0.1162) loss: 0.8166 (0.8250) time: 0.1663 data: 0.0723 max mem: 9390 +Train: [63] [ 300/6250] eta: 0:18:30 lr: 0.000041 grad: 0.1015 (0.1129) loss: 0.8157 (0.8237) time: 0.1834 data: 0.0847 max mem: 9390 +Train: [63] [ 400/6250] eta: 0:18:03 lr: 0.000041 grad: 0.1000 (0.1113) loss: 0.8166 (0.8226) time: 0.1710 data: 0.0688 max mem: 9390 +Train: [63] [ 500/6250] eta: 0:17:59 lr: 0.000041 grad: 0.0981 (0.1093) loss: 0.8187 (0.8221) time: 0.1894 data: 0.0895 max mem: 9390 +Train: [63] [ 600/6250] eta: 0:17:54 lr: 0.000041 grad: 0.0983 (0.1079) loss: 0.8147 (0.8218) time: 0.2107 data: 0.0781 max mem: 9390 +Train: [63] [ 700/6250] eta: 0:17:49 lr: 0.000041 grad: 0.1021 (0.1074) loss: 0.8203 (0.8214) time: 0.1814 data: 0.0612 max mem: 9390 +Train: [63] [ 800/6250] eta: 0:17:28 lr: 0.000041 grad: 0.1030 (0.1067) loss: 0.8227 (0.8213) time: 0.2109 data: 0.1127 max mem: 9390 +Train: [63] [ 900/6250] eta: 0:17:07 lr: 0.000041 grad: 0.0970 (0.1062) loss: 0.8218 (0.8213) time: 0.2095 data: 0.1113 max mem: 9390 +Train: [63] [1000/6250] eta: 0:16:37 lr: 0.000041 grad: 0.0956 (0.1058) loss: 0.8156 (0.8212) time: 0.1837 data: 0.0915 max mem: 9390 +Train: [63] [1100/6250] eta: 0:16:13 lr: 0.000041 grad: 0.0986 (0.1059) loss: 0.8172 (0.8210) time: 0.1796 data: 0.0932 max mem: 9390 +Train: [63] [1200/6250] eta: 0:15:42 lr: 0.000041 grad: 0.0982 (0.1057) loss: 0.8239 (0.8210) time: 0.1560 data: 0.0736 max mem: 9390 +Train: [63] [1300/6250] eta: 0:15:15 lr: 0.000041 grad: 0.1045 (0.1057) loss: 0.8162 (0.8208) time: 0.1545 data: 0.0644 max mem: 9390 +Train: [63] [1400/6250] eta: 0:14:49 lr: 0.000041 grad: 0.0962 (0.1057) loss: 0.8195 (0.8208) time: 0.1514 data: 0.0560 max mem: 9390 +Train: [63] [1500/6250] eta: 0:14:24 lr: 0.000041 grad: 0.1054 (0.1057) loss: 0.8156 (0.8208) time: 0.1710 data: 0.0785 max mem: 9390 +Train: [63] [1600/6250] eta: 0:14:00 lr: 0.000041 grad: 0.1015 (0.1057) loss: 0.8222 (0.8207) time: 0.1521 data: 0.0624 max mem: 9390 +Train: [63] [1700/6250] eta: 0:13:38 lr: 0.000041 grad: 0.1011 (0.1056) loss: 0.8220 (0.8207) time: 0.1567 data: 0.0678 max mem: 9390 +Train: [63] [1800/6250] eta: 0:13:16 lr: 0.000041 grad: 0.1073 (0.1056) loss: 0.8176 (0.8206) time: 0.1504 data: 0.0581 max mem: 9390 +Train: [63] [1900/6250] eta: 0:12:54 lr: 0.000041 grad: 0.1031 (0.1057) loss: 0.8259 (0.8206) time: 0.1601 data: 0.0685 max mem: 9390 +Train: [63] [2000/6250] eta: 0:12:34 lr: 0.000041 grad: 0.1092 (0.1058) loss: 0.8210 (0.8204) time: 0.1576 data: 0.0669 max mem: 9390 +Train: [63] [2100/6250] eta: 0:12:13 lr: 0.000041 grad: 0.1029 (0.1058) loss: 0.8193 (0.8204) time: 0.1612 data: 0.0747 max mem: 9390 +Train: [63] [2200/6250] eta: 0:11:56 lr: 0.000041 grad: 0.1013 (0.1058) loss: 0.8166 (0.8203) time: 0.1743 data: 0.0810 max mem: 9390 +Train: [63] [2300/6250] eta: 0:11:37 lr: 0.000041 grad: 0.1102 (0.1057) loss: 0.8187 (0.8203) time: 0.1789 data: 0.0899 max mem: 9390 +Train: [63] [2400/6250] eta: 0:11:16 lr: 0.000040 grad: 0.1001 (0.1057) loss: 0.8237 (0.8203) time: 0.1742 data: 0.0906 max mem: 9390 +Train: [63] [2500/6250] eta: 0:10:57 lr: 0.000040 grad: 0.1014 (0.1057) loss: 0.8235 (0.8202) time: 0.1733 data: 0.0804 max mem: 9390 +Train: [63] [2600/6250] eta: 0:10:38 lr: 0.000040 grad: 0.0999 (0.1057) loss: 0.8219 (0.8201) time: 0.1599 data: 0.0697 max mem: 9390 +Train: [63] [2700/6250] eta: 0:10:19 lr: 0.000040 grad: 0.1057 (0.1056) loss: 0.8195 (0.8201) time: 0.1485 data: 0.0629 max mem: 9390 +Train: [63] [2800/6250] eta: 0:09:59 lr: 0.000040 grad: 0.1064 (0.1055) loss: 0.8235 (0.8200) time: 0.1654 data: 0.0743 max mem: 9390 +Train: [63] [2900/6250] eta: 0:09:40 lr: 0.000040 grad: 0.1029 (0.1055) loss: 0.8200 (0.8200) time: 0.1527 data: 0.0554 max mem: 9390 +Train: [63] [3000/6250] eta: 0:09:23 lr: 0.000040 grad: 0.0994 (0.1054) loss: 0.8259 (0.8200) time: 0.2010 data: 0.1206 max mem: 9390 +Train: [63] [3100/6250] eta: 0:09:04 lr: 0.000040 grad: 0.0986 (0.1054) loss: 0.8216 (0.8199) time: 0.1741 data: 0.0834 max mem: 9390 +Train: [63] [3200/6250] eta: 0:08:46 lr: 0.000040 grad: 0.1076 (0.1055) loss: 0.8147 (0.8199) time: 0.1688 data: 0.0753 max mem: 9390 +Train: [63] [3300/6250] eta: 0:08:29 lr: 0.000040 grad: 0.1003 (0.1054) loss: 0.8140 (0.8199) time: 0.1743 data: 0.0893 max mem: 9390 +Train: [63] [3400/6250] eta: 0:08:11 lr: 0.000040 grad: 0.1011 (0.1055) loss: 0.8220 (0.8198) time: 0.1601 data: 0.0754 max mem: 9390 +Train: [63] [3500/6250] eta: 0:07:52 lr: 0.000040 grad: 0.1083 (0.1055) loss: 0.8162 (0.8197) time: 0.1507 data: 0.0549 max mem: 9390 +Train: [63] [3600/6250] eta: 0:07:35 lr: 0.000040 grad: 0.1028 (0.1054) loss: 0.8208 (0.8196) time: 0.1747 data: 0.0921 max mem: 9390 +Train: [63] [3700/6250] eta: 0:07:17 lr: 0.000040 grad: 0.1022 (0.1054) loss: 0.8158 (0.8195) time: 0.1649 data: 0.0789 max mem: 9390 +Train: [63] [3800/6250] eta: 0:07:02 lr: 0.000040 grad: 0.1004 (0.1054) loss: 0.8173 (0.8193) time: 0.0983 data: 0.0002 max mem: 9390 +Train: [63] [3900/6250] eta: 0:06:43 lr: 0.000040 grad: 0.1030 (0.1054) loss: 0.8190 (0.8193) time: 0.1728 data: 0.0799 max mem: 9390 +Train: [63] [4000/6250] eta: 0:06:26 lr: 0.000040 grad: 0.1082 (0.1054) loss: 0.8150 (0.8192) time: 0.1673 data: 0.0724 max mem: 9390 +Train: [63] [4100/6250] eta: 0:06:09 lr: 0.000040 grad: 0.1014 (0.1054) loss: 0.8204 (0.8192) time: 0.1982 data: 0.1114 max mem: 9390 +Train: [63] [4200/6250] eta: 0:05:51 lr: 0.000040 grad: 0.0980 (0.1053) loss: 0.8127 (0.8192) time: 0.1374 data: 0.0466 max mem: 9390 +Train: [63] [4300/6250] eta: 0:05:34 lr: 0.000040 grad: 0.1003 (0.1053) loss: 0.8280 (0.8191) time: 0.1480 data: 0.0552 max mem: 9390 +Train: [63] [4400/6250] eta: 0:05:16 lr: 0.000040 grad: 0.1019 (0.1053) loss: 0.8138 (0.8190) time: 0.1525 data: 0.0671 max mem: 9390 +Train: [63] [4500/6250] eta: 0:05:00 lr: 0.000040 grad: 0.1033 (0.1053) loss: 0.8156 (0.8190) time: 0.1312 data: 0.0360 max mem: 9390 +Train: [63] [4600/6250] eta: 0:04:43 lr: 0.000040 grad: 0.1055 (0.1052) loss: 0.8165 (0.8190) time: 0.1809 data: 0.0961 max mem: 9390 +Train: [63] [4700/6250] eta: 0:04:26 lr: 0.000040 grad: 0.1034 (0.1052) loss: 0.8191 (0.8190) time: 0.1930 data: 0.1106 max mem: 9390 +Train: [63] [4800/6250] eta: 0:04:08 lr: 0.000040 grad: 0.1007 (0.1052) loss: 0.8173 (0.8190) time: 0.1676 data: 0.0797 max mem: 9390 +Train: [63] [4900/6250] eta: 0:03:52 lr: 0.000040 grad: 0.1045 (0.1052) loss: 0.8203 (0.8191) time: 0.2486 data: 0.1623 max mem: 9390 +Train: [63] [5000/6250] eta: 0:03:34 lr: 0.000040 grad: 0.1066 (0.1051) loss: 0.8217 (0.8191) time: 0.1517 data: 0.0670 max mem: 9390 +Train: [63] [5100/6250] eta: 0:03:16 lr: 0.000040 grad: 0.1064 (0.1052) loss: 0.8214 (0.8191) time: 0.1293 data: 0.0402 max mem: 9390 +Train: [63] [5200/6250] eta: 0:02:59 lr: 0.000040 grad: 0.1023 (0.1052) loss: 0.8247 (0.8191) time: 0.1844 data: 0.0865 max mem: 9390 +Train: [63] [5300/6250] eta: 0:02:42 lr: 0.000040 grad: 0.1024 (0.1052) loss: 0.8187 (0.8191) time: 0.1860 data: 0.0915 max mem: 9390 +Train: [63] [5400/6250] eta: 0:02:25 lr: 0.000040 grad: 0.1014 (0.1051) loss: 0.8173 (0.8191) time: 0.1901 data: 0.1003 max mem: 9390 +Train: [63] [5500/6250] eta: 0:02:08 lr: 0.000040 grad: 0.1036 (0.1052) loss: 0.8231 (0.8191) time: 0.2031 data: 0.1169 max mem: 9390 +Train: [63] [5600/6250] eta: 0:01:51 lr: 0.000039 grad: 0.1015 (0.1052) loss: 0.8178 (0.8192) time: 0.1986 data: 0.0997 max mem: 9390 +Train: [63] [5700/6250] eta: 0:01:34 lr: 0.000039 grad: 0.1070 (0.1052) loss: 0.8113 (0.8191) time: 0.1576 data: 0.0599 max mem: 9390 +Train: [63] [5800/6250] eta: 0:01:17 lr: 0.000039 grad: 0.1043 (0.1053) loss: 0.8171 (0.8191) time: 0.1693 data: 0.0819 max mem: 9390 +Train: [63] [5900/6250] eta: 0:00:59 lr: 0.000039 grad: 0.0931 (0.1053) loss: 0.8218 (0.8191) time: 0.1762 data: 0.0851 max mem: 9390 +Train: [63] [6000/6250] eta: 0:00:42 lr: 0.000039 grad: 0.1110 (0.1053) loss: 0.8198 (0.8192) time: 0.1502 data: 0.0572 max mem: 9390 +Train: [63] [6100/6250] eta: 0:00:25 lr: 0.000039 grad: 0.1016 (0.1053) loss: 0.8224 (0.8192) time: 0.1849 data: 0.0953 max mem: 9390 +Train: [63] [6200/6250] eta: 0:00:08 lr: 0.000039 grad: 0.0972 (0.1053) loss: 0.8260 (0.8192) time: 0.1299 data: 0.0438 max mem: 9390 +Train: [63] [6249/6250] eta: 0:00:00 lr: 0.000039 grad: 0.1039 (0.1053) loss: 0.8191 (0.8192) time: 0.1469 data: 0.0616 max mem: 9390 +Train: [63] Total time: 0:17:59 (0.1726 s / it) +Averaged stats: lr: 0.000039 grad: 0.1039 (0.1053) loss: 0.8191 (0.8192) +Eval (hcp-train-subset): [63] [ 0/62] eta: 0:05:46 loss: 0.8394 (0.8394) time: 5.5964 data: 5.5538 max mem: 9390 +Eval (hcp-train-subset): [63] [61/62] eta: 0:00:00 loss: 0.8298 (0.8332) time: 0.1178 data: 0.0923 max mem: 9390 +Eval (hcp-train-subset): [63] Total time: 0:00:15 (0.2505 s / it) +Averaged stats (hcp-train-subset): loss: 0.8298 (0.8332) +Eval (hcp-val): [63] [ 0/62] eta: 0:04:36 loss: 0.8302 (0.8302) time: 4.4597 data: 4.4300 max mem: 9390 +Eval (hcp-val): [63] [61/62] eta: 0:00:00 loss: 0.8318 (0.8330) time: 0.1735 data: 0.1463 max mem: 9390 +Eval (hcp-val): [63] Total time: 0:00:14 (0.2361 s / it) +Averaged stats (hcp-val): loss: 0.8318 (0.8330) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +Train: [64] [ 0/6250] eta: 8:05:23 lr: 0.000039 grad: 0.1018 (0.1018) loss: 0.8653 (0.8653) time: 4.6597 data: 4.3909 max mem: 9390 +Train: [64] [ 100/6250] eta: 0:24:20 lr: 0.000039 grad: 0.1077 (0.1223) loss: 0.8249 (0.8239) time: 0.2107 data: 0.1040 max mem: 9390 +Train: [64] [ 200/6250] eta: 0:21:43 lr: 0.000039 grad: 0.1019 (0.1182) loss: 0.8212 (0.8209) time: 0.1903 data: 0.0969 max mem: 9390 +Train: [64] [ 300/6250] eta: 0:20:19 lr: 0.000039 grad: 0.1059 (0.1154) loss: 0.8139 (0.8186) time: 0.1909 data: 0.0822 max mem: 9390 +Train: [64] [ 400/6250] eta: 0:19:41 lr: 0.000039 grad: 0.1051 (0.1140) loss: 0.8103 (0.8172) time: 0.1954 data: 0.0895 max mem: 9390 +Train: [64] [ 500/6250] eta: 0:19:10 lr: 0.000039 grad: 0.0997 (0.1124) loss: 0.8187 (0.8167) time: 0.1988 data: 0.0867 max mem: 9390 +Train: [64] [ 600/6250] eta: 0:18:31 lr: 0.000039 grad: 0.1095 (0.1116) loss: 0.8124 (0.8167) time: 0.1801 data: 0.0751 max mem: 9390 +Train: [64] [ 700/6250] eta: 0:18:17 lr: 0.000039 grad: 0.0979 (0.1111) loss: 0.8169 (0.8163) time: 0.1864 data: 0.0968 max mem: 9390 +Train: [64] [ 800/6250] eta: 0:17:48 lr: 0.000039 grad: 0.1105 (0.1108) loss: 0.8093 (0.8160) time: 0.1647 data: 0.0736 max mem: 9390 +Train: [64] [ 900/6250] eta: 0:17:22 lr: 0.000039 grad: 0.1011 (0.1102) loss: 0.8186 (0.8161) time: 0.1772 data: 0.0702 max mem: 9390 +Train: [64] [1000/6250] eta: 0:16:45 lr: 0.000039 grad: 0.1042 (0.1098) loss: 0.8114 (0.8161) time: 0.1482 data: 0.0579 max mem: 9390 +Train: [64] [1100/6250] eta: 0:16:17 lr: 0.000039 grad: 0.1065 (0.1097) loss: 0.8124 (0.8160) time: 0.1689 data: 0.0741 max mem: 9390 +Train: [64] [1200/6250] eta: 0:15:52 lr: 0.000039 grad: 0.1053 (0.1095) loss: 0.8115 (0.8157) time: 0.1618 data: 0.0673 max mem: 9390 +Train: [64] [1300/6250] eta: 0:15:26 lr: 0.000039 grad: 0.1118 (0.1093) loss: 0.8092 (0.8157) time: 0.1753 data: 0.0933 max mem: 9390 +Train: [64] [1400/6250] eta: 0:15:05 lr: 0.000039 grad: 0.1065 (0.1091) loss: 0.8131 (0.8156) time: 0.2038 data: 0.1184 max mem: 9390 +Train: [64] [1500/6250] eta: 0:14:36 lr: 0.000039 grad: 0.1051 (0.1090) loss: 0.8159 (0.8156) time: 0.1641 data: 0.0659 max mem: 9390 +Train: [64] [1600/6250] eta: 0:14:11 lr: 0.000039 grad: 0.1072 (0.1088) loss: 0.8134 (0.8155) time: 0.1537 data: 0.0662 max mem: 9390 +Train: [64] [1700/6250] eta: 0:13:50 lr: 0.000039 grad: 0.1010 (0.1087) loss: 0.8146 (0.8154) time: 0.1993 data: 0.1058 max mem: 9390 +Train: [64] [1800/6250] eta: 0:13:25 lr: 0.000039 grad: 0.1101 (0.1087) loss: 0.8075 (0.8152) time: 0.1696 data: 0.0781 max mem: 9390 +Train: [64] [1900/6250] eta: 0:13:03 lr: 0.000039 grad: 0.1105 (0.1087) loss: 0.8118 (0.8151) time: 0.1717 data: 0.0916 max mem: 9390 +Train: [64] [2000/6250] eta: 0:12:44 lr: 0.000039 grad: 0.1040 (0.1089) loss: 0.8187 (0.8149) time: 0.1631 data: 0.0790 max mem: 9390 +Train: [64] [2100/6250] eta: 0:12:24 lr: 0.000039 grad: 0.1058 (0.1089) loss: 0.8112 (0.8149) time: 0.1774 data: 0.0861 max mem: 9390 +Train: [64] [2200/6250] eta: 0:12:04 lr: 0.000039 grad: 0.1097 (0.1090) loss: 0.8113 (0.8147) time: 0.1485 data: 0.0473 max mem: 9390 +Train: [64] [2300/6250] eta: 0:11:44 lr: 0.000039 grad: 0.1102 (0.1089) loss: 0.8191 (0.8148) time: 0.1681 data: 0.0792 max mem: 9390 +Train: [64] [2400/6250] eta: 0:11:25 lr: 0.000039 grad: 0.1107 (0.1089) loss: 0.8165 (0.8148) time: 0.1691 data: 0.0744 max mem: 9390 +Train: [64] [2500/6250] eta: 0:11:04 lr: 0.000039 grad: 0.1036 (0.1090) loss: 0.8241 (0.8149) time: 0.1577 data: 0.0718 max mem: 9390 +Train: [64] [2600/6250] eta: 0:10:45 lr: 0.000039 grad: 0.1028 (0.1091) loss: 0.8208 (0.8150) time: 0.1381 data: 0.0493 max mem: 9390 +Train: [64] [2700/6250] eta: 0:10:25 lr: 0.000038 grad: 0.1084 (0.1092) loss: 0.8145 (0.8150) time: 0.1686 data: 0.0776 max mem: 9390 +Train: [64] [2800/6250] eta: 0:10:06 lr: 0.000038 grad: 0.1032 (0.1091) loss: 0.8170 (0.8150) time: 0.1563 data: 0.0575 max mem: 9390 +Train: [64] [2900/6250] eta: 0:09:48 lr: 0.000038 grad: 0.1081 (0.1092) loss: 0.8115 (0.8151) time: 0.1257 data: 0.0286 max mem: 9390 +Train: [64] [3000/6250] eta: 0:09:29 lr: 0.000038 grad: 0.1117 (0.1092) loss: 0.8134 (0.8151) time: 0.1757 data: 0.0856 max mem: 9390 +Train: [64] [3100/6250] eta: 0:09:10 lr: 0.000038 grad: 0.1113 (0.1092) loss: 0.8123 (0.8151) time: 0.1786 data: 0.0937 max mem: 9390 +Train: [64] [3200/6250] eta: 0:08:52 lr: 0.000038 grad: 0.1041 (0.1093) loss: 0.8140 (0.8150) time: 0.1732 data: 0.0973 max mem: 9390 +Train: [64] [3300/6250] eta: 0:08:34 lr: 0.000038 grad: 0.1025 (0.1092) loss: 0.8227 (0.8150) time: 0.1322 data: 0.0210 max mem: 9390 +Train: [64] [3400/6250] eta: 0:08:17 lr: 0.000038 grad: 0.1083 (0.1092) loss: 0.8119 (0.8150) time: 0.2076 data: 0.1185 max mem: 9390 +Train: [64] [3500/6250] eta: 0:07:58 lr: 0.000038 grad: 0.1076 (0.1092) loss: 0.8134 (0.8150) time: 0.1783 data: 0.0897 max mem: 9390 +Train: [64] [3600/6250] eta: 0:07:39 lr: 0.000038 grad: 0.1023 (0.1091) loss: 0.8192 (0.8151) time: 0.1616 data: 0.0709 max mem: 9390 +Train: [64] [3700/6250] eta: 0:07:21 lr: 0.000038 grad: 0.1052 (0.1091) loss: 0.8226 (0.8151) time: 0.1459 data: 0.0607 max mem: 9390 +Train: [64] [3800/6250] eta: 0:07:04 lr: 0.000038 grad: 0.1040 (0.1090) loss: 0.8173 (0.8152) time: 0.2706 data: 0.1830 max mem: 9390 +Train: [64] [3900/6250] eta: 0:06:46 lr: 0.000038 grad: 0.1124 (0.1090) loss: 0.8130 (0.8152) time: 0.1836 data: 0.0966 max mem: 9390 +Train: [64] [4000/6250] eta: 0:06:28 lr: 0.000038 grad: 0.1113 (0.1090) loss: 0.8161 (0.8152) time: 0.1498 data: 0.0602 max mem: 9390 +Train: [64] [4100/6250] eta: 0:06:11 lr: 0.000038 grad: 0.1011 (0.1089) loss: 0.8178 (0.8153) time: 0.1552 data: 0.0734 max mem: 9390 +Train: [64] [4200/6250] eta: 0:05:54 lr: 0.000038 grad: 0.1064 (0.1089) loss: 0.8180 (0.8153) time: 0.2044 data: 0.1260 max mem: 9390 +Train: [64] [4300/6250] eta: 0:05:37 lr: 0.000038 grad: 0.1008 (0.1089) loss: 0.8198 (0.8153) time: 0.1902 data: 0.1064 max mem: 9390 +Train: [64] [4400/6250] eta: 0:05:20 lr: 0.000038 grad: 0.1040 (0.1088) loss: 0.8205 (0.8153) time: 0.1638 data: 0.0704 max mem: 9390 +Train: [64] [4500/6250] eta: 0:05:03 lr: 0.000038 grad: 0.1074 (0.1088) loss: 0.8171 (0.8154) time: 0.1733 data: 0.0845 max mem: 9390 +Train: [64] [4600/6250] eta: 0:04:46 lr: 0.000038 grad: 0.1092 (0.1088) loss: 0.8134 (0.8154) time: 0.1394 data: 0.0404 max mem: 9390 +Train: [64] [4700/6250] eta: 0:04:28 lr: 0.000038 grad: 0.1022 (0.1088) loss: 0.8175 (0.8154) time: 0.1755 data: 0.0919 max mem: 9390 +Train: [64] [4800/6250] eta: 0:04:11 lr: 0.000038 grad: 0.1046 (0.1089) loss: 0.8119 (0.8154) time: 0.2036 data: 0.1210 max mem: 9390 +Train: [64] [4900/6250] eta: 0:03:54 lr: 0.000038 grad: 0.1067 (0.1088) loss: 0.8114 (0.8154) time: 0.2250 data: 0.1403 max mem: 9390 +Train: [64] [5000/6250] eta: 0:03:36 lr: 0.000038 grad: 0.1041 (0.1088) loss: 0.8143 (0.8154) time: 0.1620 data: 0.0803 max mem: 9390 +Train: [64] [5100/6250] eta: 0:03:19 lr: 0.000038 grad: 0.1038 (0.1088) loss: 0.8194 (0.8154) time: 0.1299 data: 0.0401 max mem: 9390 +Train: [64] [5200/6250] eta: 0:03:01 lr: 0.000038 grad: 0.0976 (0.1088) loss: 0.8184 (0.8155) time: 0.1826 data: 0.0973 max mem: 9390 +Train: [64] [5300/6250] eta: 0:02:44 lr: 0.000038 grad: 0.1067 (0.1088) loss: 0.8158 (0.8154) time: 0.1451 data: 0.0511 max mem: 9390 +Train: [64] [5400/6250] eta: 0:02:26 lr: 0.000038 grad: 0.1148 (0.1088) loss: 0.8140 (0.8155) time: 0.1888 data: 0.0989 max mem: 9390 +Train: [64] [5500/6250] eta: 0:02:09 lr: 0.000038 grad: 0.1021 (0.1088) loss: 0.8164 (0.8155) time: 0.2053 data: 0.0932 max mem: 9390 +Train: [64] [5600/6250] eta: 0:01:52 lr: 0.000038 grad: 0.1106 (0.1088) loss: 0.8168 (0.8155) time: 0.2079 data: 0.1188 max mem: 9390 +Train: [64] [5700/6250] eta: 0:01:35 lr: 0.000038 grad: 0.1070 (0.1088) loss: 0.8212 (0.8155) time: 0.2120 data: 0.1110 max mem: 9390 +Train: [64] [5800/6250] eta: 0:01:18 lr: 0.000038 grad: 0.1020 (0.1088) loss: 0.8189 (0.8155) time: 0.1963 data: 0.1041 max mem: 9390 +Train: [64] [5900/6250] eta: 0:01:00 lr: 0.000037 grad: 0.1070 (0.1088) loss: 0.8171 (0.8155) time: 0.1883 data: 0.1007 max mem: 9390 +Train: [64] [6000/6250] eta: 0:00:43 lr: 0.000037 grad: 0.1108 (0.1088) loss: 0.8147 (0.8154) time: 0.1824 data: 0.0900 max mem: 9390 +Train: [64] [6100/6250] eta: 0:00:26 lr: 0.000037 grad: 0.1007 (0.1088) loss: 0.8179 (0.8155) time: 0.2050 data: 0.1167 max mem: 9390 +Train: [64] [6200/6250] eta: 0:00:08 lr: 0.000037 grad: 0.1074 (0.1089) loss: 0.8118 (0.8155) time: 0.1569 data: 0.0653 max mem: 9390 +Train: [64] [6249/6250] eta: 0:00:00 lr: 0.000037 grad: 0.1085 (0.1089) loss: 0.8190 (0.8155) time: 0.1986 data: 0.1130 max mem: 9390 +Train: [64] Total time: 0:18:15 (0.1752 s / it) +Averaged stats: lr: 0.000037 grad: 0.1085 (0.1089) loss: 0.8190 (0.8155) +Eval (hcp-train-subset): [64] [ 0/62] eta: 0:05:52 loss: 0.8356 (0.8356) time: 5.6920 data: 5.6609 max mem: 9390 +Eval (hcp-train-subset): [64] [61/62] eta: 0:00:00 loss: 0.8307 (0.8325) time: 0.2053 data: 0.1788 max mem: 9390 +Eval (hcp-train-subset): [64] Total time: 0:00:17 (0.2760 s / it) +Averaged stats (hcp-train-subset): loss: 0.8307 (0.8325) +Making plots (hcp-train-subset): example=44 +Eval (hcp-val): [64] [ 0/62] eta: 0:03:35 loss: 0.8307 (0.8307) time: 3.4804 data: 3.3780 max mem: 9390 +Eval (hcp-val): [64] [61/62] eta: 0:00:00 loss: 0.8317 (0.8341) time: 0.1619 data: 0.1346 max mem: 9390 +Eval (hcp-val): [64] Total time: 0:00:14 (0.2389 s / it) +Averaged stats (hcp-val): loss: 0.8317 (0.8341) +Making plots (hcp-val): example=59 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +Train: [65] [ 0/6250] eta: 8:46:07 lr: 0.000037 grad: 0.1214 (0.1214) loss: 0.8528 (0.8528) time: 5.0508 data: 4.7446 max mem: 9390 +Train: [65] [ 100/6250] eta: 0:26:08 lr: 0.000037 grad: 0.1241 (0.1305) loss: 0.8241 (0.8250) time: 0.2180 data: 0.0738 max mem: 9390 +Train: [65] [ 200/6250] eta: 0:23:18 lr: 0.000037 grad: 0.1194 (0.1279) loss: 0.8087 (0.8184) time: 0.2478 data: 0.1500 max mem: 9390 +Train: [65] [ 300/6250] eta: 0:21:15 lr: 0.000037 grad: 0.0911 (0.1211) loss: 0.8254 (0.8184) time: 0.2118 data: 0.1205 max mem: 9390 +Train: [65] [ 400/6250] eta: 0:20:41 lr: 0.000037 grad: 0.0949 (0.1183) loss: 0.8275 (0.8183) time: 0.2072 data: 0.1053 max mem: 9390 +Train: [65] [ 500/6250] eta: 0:20:12 lr: 0.000037 grad: 0.1052 (0.1162) loss: 0.8169 (0.8182) time: 0.1939 data: 0.0844 max mem: 9390 +Train: [65] [ 600/6250] eta: 0:19:40 lr: 0.000037 grad: 0.1066 (0.1157) loss: 0.8138 (0.8176) time: 0.1865 data: 0.0735 max mem: 9390 +Train: [65] [ 700/6250] eta: 0:19:21 lr: 0.000037 grad: 0.1101 (0.1150) loss: 0.8158 (0.8174) time: 0.2459 data: 0.1436 max mem: 9390 +Train: [65] [ 800/6250] eta: 0:18:35 lr: 0.000037 grad: 0.1067 (0.1143) loss: 0.8136 (0.8171) time: 0.1858 data: 0.0923 max mem: 9390 +Train: [65] [ 900/6250] eta: 0:18:07 lr: 0.000037 grad: 0.1007 (0.1136) loss: 0.8198 (0.8173) time: 0.2030 data: 0.1119 max mem: 9390 +Train: [65] [1000/6250] eta: 0:17:33 lr: 0.000037 grad: 0.1075 (0.1129) loss: 0.8182 (0.8173) time: 0.1861 data: 0.0910 max mem: 9390 +Train: [65] [1100/6250] eta: 0:16:59 lr: 0.000037 grad: 0.0952 (0.1120) loss: 0.8272 (0.8173) time: 0.1767 data: 0.0820 max mem: 9390 +Train: [65] [1200/6250] eta: 0:16:27 lr: 0.000037 grad: 0.1115 (0.1119) loss: 0.7987 (0.8169) time: 0.1563 data: 0.0692 max mem: 9390 +Train: [65] [1300/6250] eta: 0:16:03 lr: 0.000037 grad: 0.1067 (0.1116) loss: 0.8096 (0.8166) time: 0.2531 data: 0.1567 max mem: 9390 +Train: [65] [1400/6250] eta: 0:15:33 lr: 0.000037 grad: 0.1094 (0.1117) loss: 0.8184 (0.8163) time: 0.2038 data: 0.0701 max mem: 9390 +Train: [65] [1500/6250] eta: 0:15:05 lr: 0.000037 grad: 0.1114 (0.1114) loss: 0.8066 (0.8160) time: 0.1789 data: 0.0946 max mem: 9390 +Train: [65] [1600/6250] eta: 0:14:38 lr: 0.000037 grad: 0.1129 (0.1113) loss: 0.8081 (0.8158) time: 0.1859 data: 0.0999 max mem: 9390 +Train: [65] [1700/6250] eta: 0:14:16 lr: 0.000037 grad: 0.0995 (0.1111) loss: 0.8190 (0.8156) time: 0.2031 data: 0.1182 max mem: 9390 +Train: [65] [1800/6250] eta: 0:13:53 lr: 0.000037 grad: 0.1016 (0.1109) loss: 0.8181 (0.8155) time: 0.1764 data: 0.0722 max mem: 9390 +Train: [65] [1900/6250] eta: 0:13:29 lr: 0.000037 grad: 0.1015 (0.1108) loss: 0.8111 (0.8153) time: 0.1752 data: 0.0832 max mem: 9390 +Train: [65] [2000/6250] eta: 0:13:07 lr: 0.000037 grad: 0.1020 (0.1105) loss: 0.8233 (0.8153) time: 0.1455 data: 0.0496 max mem: 9390 +Train: [65] [2100/6250] eta: 0:12:44 lr: 0.000037 grad: 0.1072 (0.1105) loss: 0.8145 (0.8153) time: 0.1766 data: 0.0910 max mem: 9390 +Train: [65] [2200/6250] eta: 0:12:21 lr: 0.000037 grad: 0.0968 (0.1103) loss: 0.8162 (0.8153) time: 0.1814 data: 0.0965 max mem: 9390 +Train: [65] [2300/6250] eta: 0:12:04 lr: 0.000037 grad: 0.1012 (0.1101) loss: 0.8176 (0.8154) time: 0.1197 data: 0.0005 max mem: 9390 +Train: [65] [2400/6250] eta: 0:11:42 lr: 0.000037 grad: 0.1072 (0.1100) loss: 0.8097 (0.8153) time: 0.1586 data: 0.0694 max mem: 9390 +Train: [65] [2500/6250] eta: 0:11:23 lr: 0.000037 grad: 0.1041 (0.1101) loss: 0.8127 (0.8153) time: 0.2077 data: 0.1254 max mem: 9390 +Train: [65] [2600/6250] eta: 0:11:02 lr: 0.000037 grad: 0.1037 (0.1101) loss: 0.8075 (0.8152) time: 0.1673 data: 0.0813 max mem: 9390 +Train: [65] [2700/6250] eta: 0:10:46 lr: 0.000037 grad: 0.1076 (0.1102) loss: 0.8079 (0.8152) time: 0.1204 data: 0.0002 max mem: 9390 +Train: [65] [2800/6250] eta: 0:10:27 lr: 0.000037 grad: 0.1132 (0.1103) loss: 0.8098 (0.8151) time: 0.2026 data: 0.1191 max mem: 9390 +Train: [65] [2900/6250] eta: 0:10:07 lr: 0.000037 grad: 0.1096 (0.1104) loss: 0.8103 (0.8149) time: 0.1767 data: 0.0843 max mem: 9390 +Train: [65] [3000/6250] eta: 0:09:50 lr: 0.000036 grad: 0.1073 (0.1105) loss: 0.8131 (0.8148) time: 0.2010 data: 0.1087 max mem: 9390 +Train: [65] [3100/6250] eta: 0:09:30 lr: 0.000036 grad: 0.1059 (0.1105) loss: 0.8197 (0.8148) time: 0.1807 data: 0.0886 max mem: 9390 +Train: [65] [3200/6250] eta: 0:09:10 lr: 0.000036 grad: 0.1002 (0.1105) loss: 0.8156 (0.8147) time: 0.1499 data: 0.0684 max mem: 9390 +Train: [65] [3300/6250] eta: 0:08:52 lr: 0.000036 grad: 0.1132 (0.1105) loss: 0.8123 (0.8146) time: 0.1251 data: 0.0370 max mem: 9390 +Train: [65] [3400/6250] eta: 0:08:32 lr: 0.000036 grad: 0.0994 (0.1105) loss: 0.8192 (0.8146) time: 0.1740 data: 0.0849 max mem: 9390 +Train: [65] [3500/6250] eta: 0:08:14 lr: 0.000036 grad: 0.0988 (0.1105) loss: 0.8114 (0.8146) time: 0.1987 data: 0.1117 max mem: 9390 +Train: [65] [3600/6250] eta: 0:07:58 lr: 0.000036 grad: 0.1032 (0.1105) loss: 0.8245 (0.8147) time: 0.4102 data: 0.2836 max mem: 9390 +Train: [65] [3700/6250] eta: 0:07:39 lr: 0.000036 grad: 0.1056 (0.1104) loss: 0.8196 (0.8147) time: 0.1946 data: 0.1001 max mem: 9390 +Train: [65] [3800/6250] eta: 0:07:21 lr: 0.000036 grad: 0.1054 (0.1104) loss: 0.8134 (0.8148) time: 0.1745 data: 0.0742 max mem: 9390 +Train: [65] [3900/6250] eta: 0:07:02 lr: 0.000036 grad: 0.1114 (0.1104) loss: 0.8120 (0.8148) time: 0.1596 data: 0.0725 max mem: 9390 +Train: [65] [4000/6250] eta: 0:06:44 lr: 0.000036 grad: 0.1059 (0.1104) loss: 0.8111 (0.8147) time: 0.1728 data: 0.0896 max mem: 9390 +Train: [65] [4100/6250] eta: 0:06:25 lr: 0.000036 grad: 0.1067 (0.1104) loss: 0.8189 (0.8147) time: 0.1754 data: 0.0842 max mem: 9390 +Train: [65] [4200/6250] eta: 0:06:07 lr: 0.000036 grad: 0.1077 (0.1103) loss: 0.8149 (0.8147) time: 0.1673 data: 0.0871 max mem: 9390 +Train: [65] [4300/6250] eta: 0:05:48 lr: 0.000036 grad: 0.1003 (0.1103) loss: 0.8129 (0.8147) time: 0.1680 data: 0.0837 max mem: 9390 +Train: [65] [4400/6250] eta: 0:05:30 lr: 0.000036 grad: 0.1098 (0.1103) loss: 0.8169 (0.8147) time: 0.1843 data: 0.1010 max mem: 9390 +Train: [65] [4500/6250] eta: 0:05:12 lr: 0.000036 grad: 0.1038 (0.1103) loss: 0.8138 (0.8146) time: 0.1739 data: 0.0854 max mem: 9390 +Train: [65] [4600/6250] eta: 0:04:54 lr: 0.000036 grad: 0.1071 (0.1103) loss: 0.8218 (0.8146) time: 0.1639 data: 0.0706 max mem: 9390 +Train: [65] [4700/6250] eta: 0:04:36 lr: 0.000036 grad: 0.1079 (0.1103) loss: 0.8139 (0.8146) time: 0.1890 data: 0.1038 max mem: 9390 +Train: [65] [4800/6250] eta: 0:04:18 lr: 0.000036 grad: 0.1099 (0.1103) loss: 0.8085 (0.8146) time: 0.1769 data: 0.0935 max mem: 9390 +Train: [65] [4900/6250] eta: 0:04:00 lr: 0.000036 grad: 0.1083 (0.1104) loss: 0.8133 (0.8145) time: 0.1298 data: 0.0376 max mem: 9390 +Train: [65] [5000/6250] eta: 0:03:43 lr: 0.000036 grad: 0.1106 (0.1104) loss: 0.8089 (0.8145) time: 0.2607 data: 0.1795 max mem: 9390 +Train: [65] [5100/6250] eta: 0:03:25 lr: 0.000036 grad: 0.1021 (0.1104) loss: 0.8099 (0.8144) time: 0.1761 data: 0.0812 max mem: 9390 +Train: [65] [5200/6250] eta: 0:03:07 lr: 0.000036 grad: 0.1078 (0.1105) loss: 0.8146 (0.8143) time: 0.1720 data: 0.0894 max mem: 9390 +Train: [65] [5300/6250] eta: 0:02:49 lr: 0.000036 grad: 0.1120 (0.1105) loss: 0.8094 (0.8143) time: 0.1572 data: 0.0664 max mem: 9390 +Train: [65] [5400/6250] eta: 0:02:31 lr: 0.000036 grad: 0.1068 (0.1106) loss: 0.8123 (0.8142) time: 0.2049 data: 0.0970 max mem: 9390 +Train: [65] [5500/6250] eta: 0:02:13 lr: 0.000036 grad: 0.1103 (0.1106) loss: 0.8139 (0.8142) time: 0.1437 data: 0.0396 max mem: 9390 +Train: [65] [5600/6250] eta: 0:01:55 lr: 0.000036 grad: 0.1084 (0.1106) loss: 0.8142 (0.8142) time: 0.1581 data: 0.0761 max mem: 9390 +Train: [65] [5700/6250] eta: 0:01:38 lr: 0.000036 grad: 0.1077 (0.1107) loss: 0.8184 (0.8142) time: 0.3488 data: 0.2591 max mem: 9390 +Train: [65] [5800/6250] eta: 0:01:20 lr: 0.000036 grad: 0.1035 (0.1106) loss: 0.8188 (0.8143) time: 0.0993 data: 0.0002 max mem: 9390 +Train: [65] [5900/6250] eta: 0:01:02 lr: 0.000036 grad: 0.1099 (0.1106) loss: 0.8149 (0.8143) time: 0.1659 data: 0.0803 max mem: 9390 +Train: [65] [6000/6250] eta: 0:00:44 lr: 0.000036 grad: 0.1080 (0.1106) loss: 0.8173 (0.8144) time: 0.1774 data: 0.0920 max mem: 9390 +Train: [65] [6100/6250] eta: 0:00:26 lr: 0.000036 grad: 0.1117 (0.1106) loss: 0.8166 (0.8144) time: 0.1732 data: 0.0824 max mem: 9390 +Train: [65] [6200/6250] eta: 0:00:08 lr: 0.000036 grad: 0.1095 (0.1106) loss: 0.8156 (0.8144) time: 0.1912 data: 0.1042 max mem: 9390 +Train: [65] [6249/6250] eta: 0:00:00 lr: 0.000036 grad: 0.1201 (0.1106) loss: 0.8178 (0.8144) time: 0.2698 data: 0.1834 max mem: 9390 +Train: [65] Total time: 0:18:47 (0.1804 s / it) +Averaged stats: lr: 0.000036 grad: 0.1201 (0.1106) loss: 0.8178 (0.8144) +Eval (hcp-train-subset): [65] [ 0/62] eta: 0:04:24 loss: 0.8422 (0.8422) time: 4.2663 data: 4.2353 max mem: 9390 +Eval (hcp-train-subset): [65] [61/62] eta: 0:00:00 loss: 0.8293 (0.8310) time: 0.1443 data: 0.1188 max mem: 9390 +Eval (hcp-train-subset): [65] Total time: 0:00:13 (0.2238 s / it) +Averaged stats (hcp-train-subset): loss: 0.8293 (0.8310) +Eval (hcp-val): [65] [ 0/62] eta: 0:02:48 loss: 0.8323 (0.8323) time: 2.7255 data: 2.6244 max mem: 9390 +Eval (hcp-val): [65] [61/62] eta: 0:00:00 loss: 0.8323 (0.8331) time: 0.1422 data: 0.1135 max mem: 9390 +Eval (hcp-val): [65] Total time: 0:00:14 (0.2318 s / it) +Averaged stats (hcp-val): loss: 0.8323 (0.8331) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +Train: [66] [ 0/6250] eta: 9:28:16 lr: 0.000036 grad: nan (nan) loss: 0.8358 (0.8358) time: 5.4555 data: 5.2783 max mem: 9390 +Train: [66] [ 100/6250] eta: 0:24:43 lr: 0.000035 grad: 0.1019 (0.1224) loss: 0.8301 (0.8303) time: 0.1858 data: 0.0859 max mem: 9390 +Train: [66] [ 200/6250] eta: 0:21:23 lr: 0.000035 grad: 0.1015 (0.1177) loss: 0.8225 (0.8258) time: 0.1711 data: 0.0645 max mem: 9390 +Train: [66] [ 300/6250] eta: 0:20:29 lr: 0.000035 grad: 0.0938 (0.1138) loss: 0.8241 (0.8233) time: 0.1947 data: 0.0918 max mem: 9390 +Train: [66] [ 400/6250] eta: 0:19:37 lr: 0.000035 grad: 0.0979 (0.1118) loss: 0.8096 (0.8218) time: 0.1710 data: 0.0626 max mem: 9390 +Train: [66] [ 500/6250] eta: 0:19:02 lr: 0.000035 grad: 0.0980 (0.1112) loss: 0.8223 (0.8203) time: 0.2037 data: 0.0961 max mem: 9390 +Train: [66] [ 600/6250] eta: 0:18:29 lr: 0.000035 grad: 0.1032 (0.1103) loss: 0.8184 (0.8190) time: 0.1912 data: 0.0882 max mem: 9390 +Train: [66] [ 700/6250] eta: 0:18:00 lr: 0.000035 grad: 0.0988 (0.1093) loss: 0.8164 (0.8190) time: 0.1893 data: 0.0803 max mem: 9390 +Train: [66] [ 800/6250] eta: 0:17:39 lr: 0.000035 grad: 0.1060 (0.1087) loss: 0.8137 (0.8185) time: 0.2019 data: 0.0960 max mem: 9390 +Train: [66] [ 900/6250] eta: 0:17:07 lr: 0.000035 grad: 0.1027 (0.1085) loss: 0.8172 (0.8180) time: 0.1834 data: 0.0858 max mem: 9390 +Train: [66] [1000/6250] eta: 0:16:36 lr: 0.000035 grad: 0.1040 (0.1085) loss: 0.8157 (0.8177) time: 0.1458 data: 0.0464 max mem: 9390 +Train: [66] [1100/6250] eta: 0:16:08 lr: 0.000035 grad: 0.1122 (0.1088) loss: 0.8141 (0.8173) time: 0.1882 data: 0.0991 max mem: 9390 +Train: [66] [1200/6250] eta: 0:15:40 lr: 0.000035 grad: 0.1103 (0.1090) loss: 0.8096 (0.8170) time: 0.1564 data: 0.0686 max mem: 9390 +Train: [66] [1300/6250] eta: 0:15:11 lr: 0.000035 grad: 0.1120 (0.1090) loss: 0.8147 (0.8167) time: 0.1416 data: 0.0518 max mem: 9390 +Train: [66] [1400/6250] eta: 0:14:45 lr: 0.000035 grad: 0.1117 (0.1090) loss: 0.8128 (0.8165) time: 0.1794 data: 0.0788 max mem: 9390 +Train: [66] [1500/6250] eta: 0:14:20 lr: 0.000035 grad: 0.1111 (0.1091) loss: 0.8110 (0.8162) time: 0.1510 data: 0.0655 max mem: 9390 +Train: [66] [1600/6250] eta: 0:13:56 lr: 0.000035 grad: 0.1014 (0.1090) loss: 0.8214 (0.8163) time: 0.1714 data: 0.0887 max mem: 9390 +Train: [66] [1700/6250] eta: 0:13:34 lr: 0.000035 grad: 0.1032 (0.1089) loss: 0.8162 (0.8161) time: 0.1861 data: 0.1014 max mem: 9390 +Train: [66] [1800/6250] eta: 0:13:12 lr: 0.000035 grad: 0.1035 (0.1089) loss: 0.8172 (0.8159) time: 0.1506 data: 0.0556 max mem: 9390 +Train: [66] [1900/6250] eta: 0:12:51 lr: 0.000035 grad: 0.1055 (0.1088) loss: 0.8121 (0.8158) time: 0.1217 data: 0.0290 max mem: 9390 +Train: [66] [2000/6250] eta: 0:12:31 lr: 0.000035 grad: 0.1060 (0.1090) loss: 0.8139 (0.8155) time: 0.1683 data: 0.0762 max mem: 9390 +Train: [66] [2100/6250] eta: 0:12:14 lr: 0.000035 grad: 0.1062 (0.1091) loss: 0.8113 (0.8153) time: 0.1668 data: 0.0776 max mem: 9390 +Train: [66] [2200/6250] eta: 0:11:53 lr: 0.000035 grad: 0.1064 (0.1092) loss: 0.8073 (0.8150) time: 0.1558 data: 0.0652 max mem: 9390 +Train: [66] [2300/6250] eta: 0:11:34 lr: 0.000035 grad: 0.1057 (0.1094) loss: 0.8173 (0.8148) time: 0.1912 data: 0.1082 max mem: 9390 +Train: [66] [2400/6250] eta: 0:11:17 lr: 0.000035 grad: 0.1112 (0.1096) loss: 0.8139 (0.8146) time: 0.1787 data: 0.0960 max mem: 9390 +Train: [66] [2500/6250] eta: 0:11:01 lr: 0.000035 grad: 0.1077 (0.1100) loss: 0.8168 (0.8145) time: 0.2092 data: 0.1202 max mem: 9390 +Train: [66] [2600/6250] eta: 0:10:46 lr: 0.000035 grad: 0.1042 (0.1102) loss: 0.8118 (0.8144) time: 0.1441 data: 0.0552 max mem: 9390 +Train: [66] [2700/6250] eta: 0:10:28 lr: 0.000035 grad: 0.1164 (0.1104) loss: 0.8124 (0.8142) time: 0.1641 data: 0.0846 max mem: 9390 +Train: [66] [2800/6250] eta: 0:10:09 lr: 0.000035 grad: 0.1170 (0.1105) loss: 0.8111 (0.8142) time: 0.1802 data: 0.0984 max mem: 9390 +Train: [66] [2900/6250] eta: 0:09:50 lr: 0.000035 grad: 0.1037 (0.1104) loss: 0.8176 (0.8142) time: 0.1587 data: 0.0739 max mem: 9390 +Train: [66] [3000/6250] eta: 0:09:32 lr: 0.000035 grad: 0.1083 (0.1104) loss: 0.8133 (0.8142) time: 0.1351 data: 0.0190 max mem: 9390 +Train: [66] [3100/6250] eta: 0:09:17 lr: 0.000035 grad: 0.1136 (0.1106) loss: 0.8118 (0.8142) time: 0.3310 data: 0.2156 max mem: 9390 +Train: [66] [3200/6250] eta: 0:08:59 lr: 0.000035 grad: 0.1081 (0.1105) loss: 0.8091 (0.8142) time: 0.2714 data: 0.1383 max mem: 9390 +Train: [66] [3300/6250] eta: 0:08:40 lr: 0.000035 grad: 0.1039 (0.1105) loss: 0.8177 (0.8143) time: 0.1765 data: 0.0567 max mem: 9390 +Train: [66] [3400/6250] eta: 0:08:21 lr: 0.000035 grad: 0.1061 (0.1104) loss: 0.8104 (0.8144) time: 0.1682 data: 0.0835 max mem: 9390 +Train: [66] [3500/6250] eta: 0:08:03 lr: 0.000034 grad: 0.1049 (0.1103) loss: 0.8179 (0.8144) time: 0.1795 data: 0.0998 max mem: 9390 +Train: [66] [3600/6250] eta: 0:07:44 lr: 0.000034 grad: 0.1118 (0.1104) loss: 0.8128 (0.8144) time: 0.1663 data: 0.0753 max mem: 9390 +Train: [66] [3700/6250] eta: 0:07:25 lr: 0.000034 grad: 0.1087 (0.1104) loss: 0.8148 (0.8145) time: 0.1580 data: 0.0762 max mem: 9390 +Train: [66] [3800/6250] eta: 0:07:07 lr: 0.000034 grad: 0.1081 (0.1104) loss: 0.8182 (0.8146) time: 0.1513 data: 0.0566 max mem: 9390 +Train: [66] [3900/6250] eta: 0:06:49 lr: 0.000034 grad: 0.1077 (0.1104) loss: 0.8128 (0.8146) time: 0.1679 data: 0.0838 max mem: 9390 +Train: [66] [4000/6250] eta: 0:06:32 lr: 0.000034 grad: 0.1076 (0.1104) loss: 0.8114 (0.8146) time: 0.1536 data: 0.0682 max mem: 9390 +Train: [66] [4100/6250] eta: 0:06:14 lr: 0.000034 grad: 0.1044 (0.1104) loss: 0.8185 (0.8147) time: 0.1669 data: 0.0680 max mem: 9390 +Train: [66] [4200/6250] eta: 0:05:57 lr: 0.000034 grad: 0.1118 (0.1105) loss: 0.8180 (0.8146) time: 0.2010 data: 0.1056 max mem: 9390 +Train: [66] [4300/6250] eta: 0:05:40 lr: 0.000034 grad: 0.1062 (0.1105) loss: 0.8173 (0.8146) time: 0.1136 data: 0.0002 max mem: 9390 +Train: [66] [4400/6250] eta: 0:05:22 lr: 0.000034 grad: 0.1092 (0.1105) loss: 0.8167 (0.8146) time: 0.1705 data: 0.0900 max mem: 9390 +Train: [66] [4500/6250] eta: 0:05:04 lr: 0.000034 grad: 0.1076 (0.1105) loss: 0.8134 (0.8146) time: 0.1582 data: 0.0630 max mem: 9390 +Train: [66] [4600/6250] eta: 0:04:47 lr: 0.000034 grad: 0.1098 (0.1105) loss: 0.8136 (0.8146) time: 0.1683 data: 0.0511 max mem: 9390 +Train: [66] [4700/6250] eta: 0:04:30 lr: 0.000034 grad: 0.1093 (0.1105) loss: 0.8068 (0.8145) time: 0.2455 data: 0.1603 max mem: 9390 +Train: [66] [4800/6250] eta: 0:04:13 lr: 0.000034 grad: 0.1098 (0.1106) loss: 0.8133 (0.8145) time: 0.2076 data: 0.1174 max mem: 9390 +Train: [66] [4900/6250] eta: 0:03:55 lr: 0.000034 grad: 0.1106 (0.1106) loss: 0.8126 (0.8144) time: 0.1810 data: 0.0864 max mem: 9390 +Train: [66] [5000/6250] eta: 0:03:38 lr: 0.000034 grad: 0.1165 (0.1107) loss: 0.8108 (0.8143) time: 0.1659 data: 0.0669 max mem: 9390 +Train: [66] [5100/6250] eta: 0:03:20 lr: 0.000034 grad: 0.1127 (0.1108) loss: 0.8098 (0.8142) time: 0.2061 data: 0.1177 max mem: 9390 +Train: [66] [5200/6250] eta: 0:03:03 lr: 0.000034 grad: 0.1101 (0.1109) loss: 0.8101 (0.8142) time: 0.1680 data: 0.0463 max mem: 9390 +Train: [66] [5300/6250] eta: 0:02:46 lr: 0.000034 grad: 0.1127 (0.1110) loss: 0.8106 (0.8141) time: 0.1637 data: 0.0628 max mem: 9390 +Train: [66] [5400/6250] eta: 0:02:28 lr: 0.000034 grad: 0.1098 (0.1111) loss: 0.8128 (0.8140) time: 0.1422 data: 0.0557 max mem: 9390 +Train: [66] [5500/6250] eta: 0:02:11 lr: 0.000034 grad: 0.1106 (0.1112) loss: 0.8159 (0.8140) time: 0.1822 data: 0.0996 max mem: 9390 +Train: [66] [5600/6250] eta: 0:01:53 lr: 0.000034 grad: 0.1111 (0.1112) loss: 0.8117 (0.8139) time: 0.1537 data: 0.0681 max mem: 9390 +Train: [66] [5700/6250] eta: 0:01:36 lr: 0.000034 grad: 0.1114 (0.1112) loss: 0.8086 (0.8139) time: 0.2733 data: 0.1717 max mem: 9390 +Train: [66] [5800/6250] eta: 0:01:18 lr: 0.000034 grad: 0.1094 (0.1112) loss: 0.8076 (0.8138) time: 0.1872 data: 0.0988 max mem: 9390 +Train: [66] [5900/6250] eta: 0:01:01 lr: 0.000034 grad: 0.1142 (0.1113) loss: 0.8093 (0.8138) time: 0.1729 data: 0.0893 max mem: 9390 +Train: [66] [6000/6250] eta: 0:00:43 lr: 0.000034 grad: 0.1073 (0.1113) loss: 0.8132 (0.8137) time: 0.1965 data: 0.1085 max mem: 9390 +Train: [66] [6100/6250] eta: 0:00:26 lr: 0.000034 grad: 0.1158 (0.1114) loss: 0.8071 (0.8137) time: 0.1632 data: 0.0666 max mem: 9390 +Train: [66] [6200/6250] eta: 0:00:08 lr: 0.000034 grad: 0.1034 (0.1114) loss: 0.8172 (0.8137) time: 0.1813 data: 0.1013 max mem: 9390 +Train: [66] [6249/6250] eta: 0:00:00 lr: 0.000034 grad: 0.1055 (0.1113) loss: 0.8160 (0.8137) time: 0.2370 data: 0.1560 max mem: 9390 +Train: [66] Total time: 0:18:22 (0.1764 s / it) +Averaged stats: lr: 0.000034 grad: 0.1055 (0.1113) loss: 0.8160 (0.8137) +Eval (hcp-train-subset): [66] [ 0/62] eta: 0:05:12 loss: 0.8348 (0.8348) time: 5.0466 data: 5.0133 max mem: 9390 +Eval (hcp-train-subset): [66] [61/62] eta: 0:00:00 loss: 0.8294 (0.8297) time: 0.1603 data: 0.1336 max mem: 9390 +Eval (hcp-train-subset): [66] Total time: 0:00:14 (0.2286 s / it) +Averaged stats (hcp-train-subset): loss: 0.8294 (0.8297) +Eval (hcp-val): [66] [ 0/62] eta: 0:04:23 loss: 0.8295 (0.8295) time: 4.2576 data: 4.1699 max mem: 9390 +Eval (hcp-val): [66] [61/62] eta: 0:00:00 loss: 0.8321 (0.8330) time: 0.1653 data: 0.1406 max mem: 9390 +Eval (hcp-val): [66] Total time: 0:00:14 (0.2375 s / it) +Averaged stats (hcp-val): loss: 0.8321 (0.8330) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +Train: [67] [ 0/6250] eta: 7:58:37 lr: 0.000034 grad: 0.2307 (0.2307) loss: 0.8054 (0.8054) time: 4.5947 data: 4.2633 max mem: 9390 +Train: [67] [ 100/6250] eta: 0:23:32 lr: 0.000034 grad: 0.1125 (0.1373) loss: 0.8055 (0.8228) time: 0.1538 data: 0.0608 max mem: 9390 +Train: [67] [ 200/6250] eta: 0:21:13 lr: 0.000034 grad: 0.1051 (0.1273) loss: 0.8167 (0.8183) time: 0.1842 data: 0.0740 max mem: 9390 +Train: [67] [ 300/6250] eta: 0:19:45 lr: 0.000034 grad: 0.1092 (0.1211) loss: 0.8237 (0.8186) time: 0.1817 data: 0.0897 max mem: 9390 +Train: [67] [ 400/6250] eta: 0:19:03 lr: 0.000034 grad: 0.1042 (0.1191) loss: 0.8185 (0.8183) time: 0.1908 data: 0.0867 max mem: 9390 +Train: [67] [ 500/6250] eta: 0:18:26 lr: 0.000034 grad: 0.1070 (0.1181) loss: 0.8155 (0.8175) time: 0.1763 data: 0.0545 max mem: 9390 +Train: [67] [ 600/6250] eta: 0:18:04 lr: 0.000033 grad: 0.0976 (0.1163) loss: 0.8260 (0.8175) time: 0.1977 data: 0.0869 max mem: 9390 +Train: [67] [ 700/6250] eta: 0:17:35 lr: 0.000033 grad: 0.1151 (0.1158) loss: 0.8137 (0.8171) time: 0.1460 data: 0.0531 max mem: 9390 +Train: [67] [ 800/6250] eta: 0:17:08 lr: 0.000033 grad: 0.1049 (0.1153) loss: 0.8141 (0.8165) time: 0.1673 data: 0.0733 max mem: 9390 +Train: [67] [ 900/6250] eta: 0:16:48 lr: 0.000033 grad: 0.1055 (0.1146) loss: 0.8175 (0.8164) time: 0.1930 data: 0.0915 max mem: 9390 +Train: [67] [1000/6250] eta: 0:16:17 lr: 0.000033 grad: 0.1055 (0.1142) loss: 0.8194 (0.8165) time: 0.1767 data: 0.0881 max mem: 9390 +Train: [67] [1100/6250] eta: 0:15:45 lr: 0.000033 grad: 0.1095 (0.1140) loss: 0.8119 (0.8164) time: 0.1720 data: 0.0828 max mem: 9390 +Train: [67] [1200/6250] eta: 0:15:22 lr: 0.000033 grad: 0.1024 (0.1137) loss: 0.8143 (0.8164) time: 0.1457 data: 0.0483 max mem: 9390 +Train: [67] [1300/6250] eta: 0:14:55 lr: 0.000033 grad: 0.1098 (0.1136) loss: 0.8106 (0.8162) time: 0.1541 data: 0.0613 max mem: 9390 +Train: [67] [1400/6250] eta: 0:14:29 lr: 0.000033 grad: 0.1091 (0.1136) loss: 0.8115 (0.8160) time: 0.1535 data: 0.0624 max mem: 9390 +Train: [67] [1500/6250] eta: 0:14:07 lr: 0.000033 grad: 0.1048 (0.1135) loss: 0.8236 (0.8161) time: 0.1644 data: 0.0556 max mem: 9390 +Train: [67] [1600/6250] eta: 0:13:52 lr: 0.000033 grad: 0.1094 (0.1133) loss: 0.8105 (0.8160) time: 0.1183 data: 0.0003 max mem: 9390 +Train: [67] [1700/6250] eta: 0:13:31 lr: 0.000033 grad: 0.1233 (0.1134) loss: 0.8077 (0.8159) time: 0.1739 data: 0.0877 max mem: 9390 +Train: [67] [1800/6250] eta: 0:13:11 lr: 0.000033 grad: 0.1081 (0.1134) loss: 0.8172 (0.8158) time: 0.1658 data: 0.0715 max mem: 9390 +Train: [67] [1900/6250] eta: 0:12:50 lr: 0.000033 grad: 0.1021 (0.1131) loss: 0.8139 (0.8157) time: 0.1760 data: 0.0936 max mem: 9390 +Train: [67] [2000/6250] eta: 0:12:29 lr: 0.000033 grad: 0.1124 (0.1132) loss: 0.8140 (0.8157) time: 0.1373 data: 0.0478 max mem: 9390 +Train: [67] [2100/6250] eta: 0:12:08 lr: 0.000033 grad: 0.1113 (0.1130) loss: 0.8183 (0.8157) time: 0.1721 data: 0.0764 max mem: 9390 +Train: [67] [2200/6250] eta: 0:11:49 lr: 0.000033 grad: 0.1147 (0.1130) loss: 0.8147 (0.8158) time: 0.1102 data: 0.0099 max mem: 9390 +Train: [67] [2300/6250] eta: 0:11:32 lr: 0.000033 grad: 0.1107 (0.1129) loss: 0.8176 (0.8159) time: 0.2343 data: 0.1476 max mem: 9390 +Train: [67] [2400/6250] eta: 0:11:13 lr: 0.000033 grad: 0.1001 (0.1128) loss: 0.8191 (0.8159) time: 0.1731 data: 0.0744 max mem: 9390 +Train: [67] [2500/6250] eta: 0:10:56 lr: 0.000033 grad: 0.1032 (0.1127) loss: 0.8174 (0.8159) time: 0.2591 data: 0.1243 max mem: 9390 +Train: [67] [2600/6250] eta: 0:10:40 lr: 0.000033 grad: 0.1048 (0.1126) loss: 0.8141 (0.8158) time: 0.2241 data: 0.1310 max mem: 9390 +Train: [67] [2700/6250] eta: 0:10:24 lr: 0.000033 grad: 0.1027 (0.1125) loss: 0.8145 (0.8157) time: 0.1903 data: 0.0969 max mem: 9390 +Train: [67] [2800/6250] eta: 0:10:04 lr: 0.000033 grad: 0.1099 (0.1125) loss: 0.8103 (0.8156) time: 0.1608 data: 0.0641 max mem: 9390 +Train: [67] [2900/6250] eta: 0:09:45 lr: 0.000033 grad: 0.1108 (0.1124) loss: 0.8159 (0.8156) time: 0.1331 data: 0.0456 max mem: 9390 +Train: [67] [3000/6250] eta: 0:09:27 lr: 0.000033 grad: 0.1108 (0.1123) loss: 0.8094 (0.8156) time: 0.1805 data: 0.0940 max mem: 9390 +Train: [67] [3100/6250] eta: 0:09:10 lr: 0.000033 grad: 0.1066 (0.1123) loss: 0.8134 (0.8155) time: 0.1109 data: 0.0003 max mem: 9390 +Train: [67] [3200/6250] eta: 0:08:54 lr: 0.000033 grad: 0.1096 (0.1123) loss: 0.8164 (0.8154) time: 0.1881 data: 0.1026 max mem: 9390 +Train: [67] [3300/6250] eta: 0:08:36 lr: 0.000033 grad: 0.1024 (0.1123) loss: 0.8133 (0.8153) time: 0.1936 data: 0.1119 max mem: 9390 +Train: [67] [3400/6250] eta: 0:08:18 lr: 0.000033 grad: 0.1116 (0.1122) loss: 0.8109 (0.8152) time: 0.2051 data: 0.1176 max mem: 9390 +Train: [67] [3500/6250] eta: 0:07:59 lr: 0.000033 grad: 0.1103 (0.1123) loss: 0.8159 (0.8152) time: 0.1612 data: 0.0771 max mem: 9390 +Train: [67] [3600/6250] eta: 0:07:41 lr: 0.000033 grad: 0.1078 (0.1124) loss: 0.8171 (0.8151) time: 0.1819 data: 0.0906 max mem: 9390 +Train: [67] [3700/6250] eta: 0:07:24 lr: 0.000033 grad: 0.1040 (0.1123) loss: 0.8111 (0.8151) time: 0.1724 data: 0.0815 max mem: 9390 +Train: [67] [3800/6250] eta: 0:07:07 lr: 0.000033 grad: 0.1038 (0.1123) loss: 0.8159 (0.8150) time: 0.1387 data: 0.0465 max mem: 9390 +Train: [67] [3900/6250] eta: 0:06:49 lr: 0.000033 grad: 0.1064 (0.1123) loss: 0.8136 (0.8150) time: 0.1393 data: 0.0388 max mem: 9390 +Train: [67] [4000/6250] eta: 0:06:31 lr: 0.000032 grad: 0.1093 (0.1124) loss: 0.8138 (0.8149) time: 0.1688 data: 0.0753 max mem: 9390 +Train: [67] [4100/6250] eta: 0:06:13 lr: 0.000032 grad: 0.1092 (0.1123) loss: 0.8157 (0.8148) time: 0.2030 data: 0.1197 max mem: 9390 +Train: [67] [4200/6250] eta: 0:05:56 lr: 0.000032 grad: 0.1109 (0.1124) loss: 0.8081 (0.8147) time: 0.1719 data: 0.0904 max mem: 9390 +Train: [67] [4300/6250] eta: 0:05:39 lr: 0.000032 grad: 0.1033 (0.1123) loss: 0.8161 (0.8147) time: 0.2109 data: 0.1214 max mem: 9390 +Train: [67] [4400/6250] eta: 0:05:22 lr: 0.000032 grad: 0.1063 (0.1124) loss: 0.8173 (0.8146) time: 0.2456 data: 0.1540 max mem: 9390 +Train: [67] [4500/6250] eta: 0:05:04 lr: 0.000032 grad: 0.1165 (0.1124) loss: 0.8124 (0.8146) time: 0.1588 data: 0.0703 max mem: 9390 +Train: [67] [4600/6250] eta: 0:04:47 lr: 0.000032 grad: 0.1133 (0.1124) loss: 0.8219 (0.8145) time: 0.1412 data: 0.0494 max mem: 9390 +Train: [67] [4700/6250] eta: 0:04:29 lr: 0.000032 grad: 0.1057 (0.1124) loss: 0.8107 (0.8145) time: 0.1721 data: 0.0779 max mem: 9390 +Train: [67] [4800/6250] eta: 0:04:12 lr: 0.000032 grad: 0.1071 (0.1124) loss: 0.8158 (0.8145) time: 0.1656 data: 0.0828 max mem: 9390 +Train: [67] [4900/6250] eta: 0:03:55 lr: 0.000032 grad: 0.1090 (0.1123) loss: 0.8159 (0.8146) time: 0.2293 data: 0.1413 max mem: 9390 +Train: [67] [5000/6250] eta: 0:03:37 lr: 0.000032 grad: 0.1071 (0.1123) loss: 0.8154 (0.8146) time: 0.1785 data: 0.0888 max mem: 9390 +Train: [67] [5100/6250] eta: 0:03:19 lr: 0.000032 grad: 0.1050 (0.1123) loss: 0.8158 (0.8147) time: 0.1857 data: 0.1024 max mem: 9390 +Train: [67] [5200/6250] eta: 0:03:02 lr: 0.000032 grad: 0.0957 (0.1122) loss: 0.8188 (0.8148) time: 0.1598 data: 0.0687 max mem: 9390 +Train: [67] [5300/6250] eta: 0:02:44 lr: 0.000032 grad: 0.1050 (0.1122) loss: 0.8207 (0.8148) time: 0.1691 data: 0.0853 max mem: 9390 +Train: [67] [5400/6250] eta: 0:02:27 lr: 0.000032 grad: 0.1061 (0.1123) loss: 0.8176 (0.8149) time: 0.1652 data: 0.0834 max mem: 9390 +Train: [67] [5500/6250] eta: 0:02:10 lr: 0.000032 grad: 0.1031 (0.1122) loss: 0.8188 (0.8149) time: 0.2009 data: 0.1121 max mem: 9390 +Train: [67] [5600/6250] eta: 0:01:52 lr: 0.000032 grad: 0.1086 (0.1122) loss: 0.8277 (0.8150) time: 0.2300 data: 0.1522 max mem: 9390 +Train: [67] [5700/6250] eta: 0:01:35 lr: 0.000032 grad: 0.1022 (0.1121) loss: 0.8210 (0.8150) time: 0.1885 data: 0.0882 max mem: 9390 +Train: [67] [5800/6250] eta: 0:01:18 lr: 0.000032 grad: 0.1126 (0.1120) loss: 0.8203 (0.8151) time: 0.1623 data: 0.0736 max mem: 9390 +Train: [67] [5900/6250] eta: 0:01:00 lr: 0.000032 grad: 0.1038 (0.1120) loss: 0.8222 (0.8152) time: 0.1669 data: 0.0719 max mem: 9390 +Train: [67] [6000/6250] eta: 0:00:43 lr: 0.000032 grad: 0.1112 (0.1119) loss: 0.8175 (0.8153) time: 0.1962 data: 0.0950 max mem: 9390 +Train: [67] [6100/6250] eta: 0:00:26 lr: 0.000032 grad: 0.1121 (0.1119) loss: 0.8123 (0.8153) time: 0.1843 data: 0.0825 max mem: 9390 +Train: [67] [6200/6250] eta: 0:00:08 lr: 0.000032 grad: 0.1145 (0.1120) loss: 0.8116 (0.8153) time: 0.2156 data: 0.1335 max mem: 9390 +Train: [67] [6249/6250] eta: 0:00:00 lr: 0.000032 grad: 0.1044 (0.1120) loss: 0.8200 (0.8153) time: 0.1705 data: 0.0798 max mem: 9390 +Train: [67] Total time: 0:18:13 (0.1749 s / it) +Averaged stats: lr: 0.000032 grad: 0.1044 (0.1120) loss: 0.8200 (0.8153) +Eval (hcp-train-subset): [67] [ 0/62] eta: 0:03:00 loss: 0.8355 (0.8355) time: 2.9089 data: 2.8177 max mem: 9390 +Eval (hcp-train-subset): [67] [61/62] eta: 0:00:00 loss: 0.8278 (0.8289) time: 0.1478 data: 0.1203 max mem: 9390 +Eval (hcp-train-subset): [67] Total time: 0:00:14 (0.2321 s / it) +Averaged stats (hcp-train-subset): loss: 0.8278 (0.8289) +Eval (hcp-val): [67] [ 0/62] eta: 0:03:00 loss: 0.8311 (0.8311) time: 2.9094 data: 2.8436 max mem: 9390 +Eval (hcp-val): [67] [61/62] eta: 0:00:00 loss: 0.8317 (0.8328) time: 0.1673 data: 0.1396 max mem: 9390 +Eval (hcp-val): [67] Total time: 0:00:15 (0.2474 s / it) +Averaged stats (hcp-val): loss: 0.8317 (0.8328) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +Train: [68] [ 0/6250] eta: 11:28:06 lr: 0.000032 grad: 0.4676 (0.4676) loss: 0.7925 (0.7925) time: 6.6059 data: 6.4557 max mem: 9390 +Train: [68] [ 100/6250] eta: 0:23:08 lr: 0.000032 grad: 0.1286 (0.1273) loss: 0.8182 (0.8312) time: 0.1638 data: 0.0709 max mem: 9390 +Train: [68] [ 200/6250] eta: 0:20:47 lr: 0.000032 grad: 0.0988 (0.1180) loss: 0.8301 (0.8294) time: 0.1862 data: 0.0804 max mem: 9390 +Train: [68] [ 300/6250] eta: 0:19:45 lr: 0.000032 grad: 0.1064 (0.1161) loss: 0.8201 (0.8256) time: 0.1663 data: 0.0534 max mem: 9390 +Train: [68] [ 400/6250] eta: 0:19:06 lr: 0.000032 grad: 0.0962 (0.1140) loss: 0.8170 (0.8236) time: 0.1818 data: 0.0746 max mem: 9390 +Train: [68] [ 500/6250] eta: 0:18:22 lr: 0.000032 grad: 0.1005 (0.1128) loss: 0.8160 (0.8226) time: 0.1651 data: 0.0646 max mem: 9390 +Train: [68] [ 600/6250] eta: 0:17:51 lr: 0.000032 grad: 0.1027 (0.1115) loss: 0.8146 (0.8220) time: 0.1672 data: 0.0539 max mem: 9390 +Train: [68] [ 700/6250] eta: 0:17:31 lr: 0.000032 grad: 0.1044 (0.1108) loss: 0.8175 (0.8217) time: 0.2046 data: 0.1071 max mem: 9390 +Train: [68] [ 800/6250] eta: 0:17:13 lr: 0.000032 grad: 0.1089 (0.1102) loss: 0.8153 (0.8215) time: 0.2053 data: 0.1059 max mem: 9390 +Train: [68] [ 900/6250] eta: 0:17:05 lr: 0.000032 grad: 0.1013 (0.1099) loss: 0.8123 (0.8210) time: 0.1706 data: 0.0762 max mem: 9390 +Train: [68] [1000/6250] eta: 0:16:43 lr: 0.000032 grad: 0.1009 (0.1099) loss: 0.8202 (0.8205) time: 0.1730 data: 0.0988 max mem: 9390 +Train: [68] [1100/6250] eta: 0:16:23 lr: 0.000032 grad: 0.1068 (0.1097) loss: 0.8137 (0.8202) time: 0.1878 data: 0.1018 max mem: 9390 +Train: [68] [1200/6250] eta: 0:16:09 lr: 0.000032 grad: 0.1016 (0.1094) loss: 0.8168 (0.8198) time: 0.2500 data: 0.1774 max mem: 9390 +Train: [68] [1300/6250] eta: 0:16:15 lr: 0.000031 grad: 0.1059 (0.1092) loss: 0.8119 (0.8195) time: 0.3338 data: 0.2490 max mem: 9390 +Train: [68] [1400/6250] eta: 0:15:45 lr: 0.000031 grad: 0.1020 (0.1092) loss: 0.8161 (0.8191) time: 0.1824 data: 0.0900 max mem: 9390 +Train: [68] [1500/6250] eta: 0:15:13 lr: 0.000031 grad: 0.1070 (0.1093) loss: 0.8125 (0.8188) time: 0.1429 data: 0.0460 max mem: 9390 +Train: [68] [1600/6250] eta: 0:14:43 lr: 0.000031 grad: 0.1072 (0.1095) loss: 0.8119 (0.8185) time: 0.1629 data: 0.0683 max mem: 9390 +Train: [68] [1700/6250] eta: 0:14:16 lr: 0.000031 grad: 0.1058 (0.1094) loss: 0.8137 (0.8183) time: 0.1479 data: 0.0540 max mem: 9390 +Train: [68] [1800/6250] eta: 0:13:50 lr: 0.000031 grad: 0.1135 (0.1096) loss: 0.8099 (0.8180) time: 0.1745 data: 0.0831 max mem: 9390 +Train: [68] [1900/6250] eta: 0:13:26 lr: 0.000031 grad: 0.1152 (0.1097) loss: 0.8098 (0.8178) time: 0.1747 data: 0.0827 max mem: 9390 +Train: [68] [2000/6250] eta: 0:13:02 lr: 0.000031 grad: 0.1026 (0.1097) loss: 0.8150 (0.8176) time: 0.1527 data: 0.0625 max mem: 9390 +Train: [68] [2100/6250] eta: 0:12:40 lr: 0.000031 grad: 0.1082 (0.1098) loss: 0.8115 (0.8174) time: 0.1618 data: 0.0732 max mem: 9390 +Train: [68] [2200/6250] eta: 0:12:18 lr: 0.000031 grad: 0.1037 (0.1099) loss: 0.8120 (0.8172) time: 0.1612 data: 0.0768 max mem: 9390 +Train: [68] [2300/6250] eta: 0:11:57 lr: 0.000031 grad: 0.1070 (0.1099) loss: 0.8091 (0.8171) time: 0.1146 data: 0.0019 max mem: 9390 +Train: [68] [2400/6250] eta: 0:11:36 lr: 0.000031 grad: 0.1068 (0.1099) loss: 0.8176 (0.8170) time: 0.1655 data: 0.0791 max mem: 9390 +Train: [68] [2500/6250] eta: 0:11:14 lr: 0.000031 grad: 0.1151 (0.1100) loss: 0.8099 (0.8168) time: 0.1652 data: 0.0703 max mem: 9390 +Train: [68] [2600/6250] eta: 0:10:53 lr: 0.000031 grad: 0.1108 (0.1100) loss: 0.8150 (0.8167) time: 0.1473 data: 0.0664 max mem: 9390 +Train: [68] [2700/6250] eta: 0:10:35 lr: 0.000031 grad: 0.1012 (0.1100) loss: 0.8196 (0.8166) time: 0.1814 data: 0.0909 max mem: 9390 +Train: [68] [2800/6250] eta: 0:10:15 lr: 0.000031 grad: 0.1045 (0.1101) loss: 0.8123 (0.8165) time: 0.1666 data: 0.0858 max mem: 9390 +Train: [68] [2900/6250] eta: 0:09:58 lr: 0.000031 grad: 0.1035 (0.1101) loss: 0.8178 (0.8165) time: 0.1098 data: 0.0002 max mem: 9390 +Train: [68] [3000/6250] eta: 0:09:38 lr: 0.000031 grad: 0.1038 (0.1102) loss: 0.8170 (0.8164) time: 0.1702 data: 0.0798 max mem: 9390 +Train: [68] [3100/6250] eta: 0:09:18 lr: 0.000031 grad: 0.1158 (0.1103) loss: 0.8142 (0.8163) time: 0.1800 data: 0.0949 max mem: 9390 +Train: [68] [3200/6250] eta: 0:08:59 lr: 0.000031 grad: 0.1017 (0.1104) loss: 0.8144 (0.8163) time: 0.1480 data: 0.0588 max mem: 9390 +Train: [68] [3300/6250] eta: 0:08:41 lr: 0.000031 grad: 0.1099 (0.1104) loss: 0.8150 (0.8162) time: 0.1157 data: 0.0271 max mem: 9390 +Train: [68] [3400/6250] eta: 0:08:23 lr: 0.000031 grad: 0.1130 (0.1105) loss: 0.8113 (0.8162) time: 0.1499 data: 0.0678 max mem: 9390 +Train: [68] [3500/6250] eta: 0:08:05 lr: 0.000031 grad: 0.1119 (0.1106) loss: 0.8137 (0.8161) time: 0.1468 data: 0.0577 max mem: 9390 +Train: [68] [3600/6250] eta: 0:07:47 lr: 0.000031 grad: 0.1094 (0.1107) loss: 0.8118 (0.8160) time: 0.1548 data: 0.0734 max mem: 9390 +Train: [68] [3700/6250] eta: 0:07:29 lr: 0.000031 grad: 0.1074 (0.1108) loss: 0.8156 (0.8159) time: 0.1596 data: 0.0727 max mem: 9390 +Train: [68] [3800/6250] eta: 0:07:11 lr: 0.000031 grad: 0.1179 (0.1110) loss: 0.8089 (0.8158) time: 0.1477 data: 0.0602 max mem: 9390 +Train: [68] [3900/6250] eta: 0:06:53 lr: 0.000031 grad: 0.1126 (0.1112) loss: 0.8116 (0.8157) time: 0.1720 data: 0.0831 max mem: 9390 +Train: [68] [4000/6250] eta: 0:06:35 lr: 0.000031 grad: 0.1112 (0.1113) loss: 0.8129 (0.8156) time: 0.1758 data: 0.0848 max mem: 9390 +Train: [68] [4100/6250] eta: 0:06:17 lr: 0.000031 grad: 0.1134 (0.1114) loss: 0.8149 (0.8155) time: 0.1904 data: 0.1019 max mem: 9390 +Train: [68] [4200/6250] eta: 0:05:59 lr: 0.000031 grad: 0.1179 (0.1116) loss: 0.8160 (0.8154) time: 0.2045 data: 0.1306 max mem: 9390 +Train: [68] [4300/6250] eta: 0:05:42 lr: 0.000031 grad: 0.1113 (0.1117) loss: 0.8198 (0.8153) time: 0.1678 data: 0.0749 max mem: 9390 +Train: [68] [4400/6250] eta: 0:05:24 lr: 0.000031 grad: 0.1193 (0.1119) loss: 0.8140 (0.8152) time: 0.1820 data: 0.0946 max mem: 9390 +Train: [68] [4500/6250] eta: 0:05:06 lr: 0.000031 grad: 0.1198 (0.1121) loss: 0.8139 (0.8151) time: 0.1955 data: 0.1105 max mem: 9390 +Train: [68] [4600/6250] eta: 0:04:49 lr: 0.000031 grad: 0.1155 (0.1122) loss: 0.8129 (0.8151) time: 0.1515 data: 0.0620 max mem: 9390 +Train: [68] [4700/6250] eta: 0:04:31 lr: 0.000031 grad: 0.1140 (0.1123) loss: 0.8200 (0.8151) time: 0.2013 data: 0.1084 max mem: 9390 +Train: [68] [4800/6250] eta: 0:04:14 lr: 0.000030 grad: 0.1108 (0.1124) loss: 0.8193 (0.8151) time: 0.1689 data: 0.0842 max mem: 9390 +Train: [68] [4900/6250] eta: 0:03:56 lr: 0.000030 grad: 0.1112 (0.1125) loss: 0.8153 (0.8151) time: 0.1632 data: 0.0759 max mem: 9390 +Train: [68] [5000/6250] eta: 0:03:38 lr: 0.000030 grad: 0.1129 (0.1126) loss: 0.8177 (0.8150) time: 0.1852 data: 0.0881 max mem: 9390 +Train: [68] [5100/6250] eta: 0:03:21 lr: 0.000030 grad: 0.1148 (0.1127) loss: 0.8116 (0.8150) time: 0.1637 data: 0.0308 max mem: 9390 +Train: [68] [5200/6250] eta: 0:03:03 lr: 0.000030 grad: 0.1091 (0.1127) loss: 0.8219 (0.8151) time: 0.1823 data: 0.0910 max mem: 9390 +Train: [68] [5300/6250] eta: 0:02:46 lr: 0.000030 grad: 0.1214 (0.1129) loss: 0.8080 (0.8150) time: 0.1564 data: 0.0654 max mem: 9390 +Train: [68] [5400/6250] eta: 0:02:28 lr: 0.000030 grad: 0.1122 (0.1129) loss: 0.8124 (0.8150) time: 0.2019 data: 0.1178 max mem: 9390 +Train: [68] [5500/6250] eta: 0:02:11 lr: 0.000030 grad: 0.1131 (0.1130) loss: 0.8116 (0.8150) time: 0.1785 data: 0.0801 max mem: 9390 +Train: [68] [5600/6250] eta: 0:01:53 lr: 0.000030 grad: 0.1122 (0.1130) loss: 0.8118 (0.8150) time: 0.1461 data: 0.0613 max mem: 9390 +Train: [68] [5700/6250] eta: 0:01:36 lr: 0.000030 grad: 0.1169 (0.1131) loss: 0.8108 (0.8150) time: 0.1265 data: 0.0371 max mem: 9390 +Train: [68] [5800/6250] eta: 0:01:18 lr: 0.000030 grad: 0.1102 (0.1130) loss: 0.8194 (0.8150) time: 0.1692 data: 0.0817 max mem: 9390 +Train: [68] [5900/6250] eta: 0:01:01 lr: 0.000030 grad: 0.1125 (0.1131) loss: 0.8130 (0.8150) time: 0.1110 data: 0.0003 max mem: 9390 +Train: [68] [6000/6250] eta: 0:00:43 lr: 0.000030 grad: 0.1087 (0.1132) loss: 0.8157 (0.8150) time: 0.1700 data: 0.0809 max mem: 9390 +Train: [68] [6100/6250] eta: 0:00:26 lr: 0.000030 grad: 0.1113 (0.1132) loss: 0.8137 (0.8150) time: 0.1891 data: 0.1028 max mem: 9390 +Train: [68] [6200/6250] eta: 0:00:08 lr: 0.000030 grad: 0.1125 (0.1133) loss: 0.8069 (0.8149) time: 0.2009 data: 0.1240 max mem: 9390 +Train: [68] [6249/6250] eta: 0:00:00 lr: 0.000030 grad: 0.1164 (0.1133) loss: 0.8127 (0.8149) time: 0.1892 data: 0.1054 max mem: 9390 +Train: [68] Total time: 0:18:26 (0.1770 s / it) +Averaged stats: lr: 0.000030 grad: 0.1164 (0.1133) loss: 0.8127 (0.8149) +Eval (hcp-train-subset): [68] [ 0/62] eta: 0:04:54 loss: 0.8433 (0.8433) time: 4.7553 data: 4.7217 max mem: 9390 +Eval (hcp-train-subset): [68] [61/62] eta: 0:00:00 loss: 0.8305 (0.8307) time: 0.1740 data: 0.1476 max mem: 9390 +Eval (hcp-train-subset): [68] Total time: 0:00:15 (0.2426 s / it) +Averaged stats (hcp-train-subset): loss: 0.8305 (0.8307) +Eval (hcp-val): [68] [ 0/62] eta: 0:04:52 loss: 0.8289 (0.8289) time: 4.7202 data: 4.6895 max mem: 9390 +Eval (hcp-val): [68] [61/62] eta: 0:00:00 loss: 0.8313 (0.8327) time: 0.1460 data: 0.1183 max mem: 9390 +Eval (hcp-val): [68] Total time: 0:00:14 (0.2335 s / it) +Averaged stats (hcp-val): loss: 0.8313 (0.8327) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +Train: [69] [ 0/6250] eta: 11:15:35 lr: 0.000030 grad: 0.1357 (0.1357) loss: 0.8296 (0.8296) time: 6.4856 data: 6.3833 max mem: 9390 +Train: [69] [ 100/6250] eta: 0:22:58 lr: 0.000030 grad: 0.1045 (0.1173) loss: 0.8283 (0.8306) time: 0.1551 data: 0.0484 max mem: 9390 +Train: [69] [ 200/6250] eta: 0:20:22 lr: 0.000030 grad: 0.1008 (0.1144) loss: 0.8311 (0.8282) time: 0.1817 data: 0.0805 max mem: 9390 +Train: [69] [ 300/6250] eta: 0:19:39 lr: 0.000030 grad: 0.1076 (0.1143) loss: 0.8211 (0.8255) time: 0.2058 data: 0.1073 max mem: 9390 +Train: [69] [ 400/6250] eta: 0:18:45 lr: 0.000030 grad: 0.1158 (0.1145) loss: 0.8091 (0.8215) time: 0.1452 data: 0.0289 max mem: 9390 +Train: [69] [ 500/6250] eta: 0:18:04 lr: 0.000030 grad: 0.1099 (0.1139) loss: 0.8169 (0.8199) time: 0.1728 data: 0.0661 max mem: 9390 +Train: [69] [ 600/6250] eta: 0:17:35 lr: 0.000030 grad: 0.1081 (0.1135) loss: 0.8180 (0.8191) time: 0.1974 data: 0.0954 max mem: 9390 +Train: [69] [ 700/6250] eta: 0:17:11 lr: 0.000030 grad: 0.1032 (0.1129) loss: 0.8153 (0.8188) time: 0.1838 data: 0.0856 max mem: 9390 +Train: [69] [ 800/6250] eta: 0:16:41 lr: 0.000030 grad: 0.1108 (0.1123) loss: 0.8171 (0.8188) time: 0.1548 data: 0.0519 max mem: 9390 +Train: [69] [ 900/6250] eta: 0:16:15 lr: 0.000030 grad: 0.0997 (0.1118) loss: 0.8205 (0.8190) time: 0.1628 data: 0.0727 max mem: 9390 +Train: [69] [1000/6250] eta: 0:15:56 lr: 0.000030 grad: 0.0982 (0.1112) loss: 0.8216 (0.8192) time: 0.2169 data: 0.1255 max mem: 9390 +Train: [69] [1100/6250] eta: 0:15:27 lr: 0.000030 grad: 0.1038 (0.1107) loss: 0.8165 (0.8192) time: 0.1749 data: 0.0861 max mem: 9390 +Train: [69] [1200/6250] eta: 0:15:01 lr: 0.000030 grad: 0.1081 (0.1104) loss: 0.8208 (0.8193) time: 0.1678 data: 0.0720 max mem: 9390 +Train: [69] [1300/6250] eta: 0:14:36 lr: 0.000030 grad: 0.0992 (0.1101) loss: 0.8171 (0.8192) time: 0.1463 data: 0.0530 max mem: 9390 +Train: [69] [1400/6250] eta: 0:14:15 lr: 0.000030 grad: 0.1055 (0.1100) loss: 0.8186 (0.8191) time: 0.1593 data: 0.0751 max mem: 9390 +Train: [69] [1500/6250] eta: 0:13:53 lr: 0.000030 grad: 0.1063 (0.1102) loss: 0.8166 (0.8189) time: 0.1575 data: 0.0600 max mem: 9390 +Train: [69] [1600/6250] eta: 0:13:32 lr: 0.000030 grad: 0.1105 (0.1102) loss: 0.8177 (0.8186) time: 0.1663 data: 0.0847 max mem: 9390 +Train: [69] [1700/6250] eta: 0:13:17 lr: 0.000030 grad: 0.1075 (0.1104) loss: 0.8131 (0.8183) time: 0.2247 data: 0.0915 max mem: 9390 +Train: [69] [1800/6250] eta: 0:13:00 lr: 0.000030 grad: 0.1084 (0.1106) loss: 0.8125 (0.8180) time: 0.1187 data: 0.0256 max mem: 9390 +Train: [69] [1900/6250] eta: 0:12:40 lr: 0.000030 grad: 0.1142 (0.1108) loss: 0.8102 (0.8175) time: 0.1711 data: 0.0870 max mem: 9390 +Train: [69] [2000/6250] eta: 0:12:19 lr: 0.000030 grad: 0.1136 (0.1111) loss: 0.8157 (0.8172) time: 0.1678 data: 0.0755 max mem: 9390 +Train: [69] [2100/6250] eta: 0:12:01 lr: 0.000029 grad: 0.1202 (0.1113) loss: 0.8062 (0.8169) time: 0.1114 data: 0.0077 max mem: 9390 +Train: [69] [2200/6250] eta: 0:11:41 lr: 0.000029 grad: 0.1085 (0.1114) loss: 0.8178 (0.8166) time: 0.1615 data: 0.0575 max mem: 9390 +Train: [69] [2300/6250] eta: 0:11:23 lr: 0.000029 grad: 0.1083 (0.1114) loss: 0.8090 (0.8165) time: 0.1634 data: 0.0142 max mem: 9390 +Train: [69] [2400/6250] eta: 0:11:05 lr: 0.000029 grad: 0.1063 (0.1113) loss: 0.8172 (0.8165) time: 0.1787 data: 0.0975 max mem: 9390 +Train: [69] [2500/6250] eta: 0:10:47 lr: 0.000029 grad: 0.1031 (0.1112) loss: 0.8161 (0.8165) time: 0.1892 data: 0.0987 max mem: 9390 +Train: [69] [2600/6250] eta: 0:10:28 lr: 0.000029 grad: 0.1045 (0.1111) loss: 0.8191 (0.8165) time: 0.1734 data: 0.0652 max mem: 9390 +Train: [69] [2700/6250] eta: 0:10:09 lr: 0.000029 grad: 0.1093 (0.1112) loss: 0.8140 (0.8165) time: 0.1309 data: 0.0215 max mem: 9390 +Train: [69] [2800/6250] eta: 0:09:54 lr: 0.000029 grad: 0.1177 (0.1113) loss: 0.8112 (0.8165) time: 0.1168 data: 0.0199 max mem: 9390 +Train: [69] [2900/6250] eta: 0:09:35 lr: 0.000029 grad: 0.1227 (0.1116) loss: 0.8045 (0.8163) time: 0.1328 data: 0.0438 max mem: 9390 +Train: [69] [3000/6250] eta: 0:09:17 lr: 0.000029 grad: 0.1111 (0.1118) loss: 0.8161 (0.8163) time: 0.1519 data: 0.0592 max mem: 9390 +Train: [69] [3100/6250] eta: 0:09:00 lr: 0.000029 grad: 0.1208 (0.1120) loss: 0.8145 (0.8161) time: 0.1714 data: 0.0882 max mem: 9390 +Train: [69] [3200/6250] eta: 0:08:42 lr: 0.000029 grad: 0.1222 (0.1121) loss: 0.8075 (0.8161) time: 0.1617 data: 0.0673 max mem: 9390 +Train: [69] [3300/6250] eta: 0:08:25 lr: 0.000029 grad: 0.1115 (0.1122) loss: 0.8153 (0.8161) time: 0.1352 data: 0.0446 max mem: 9390 +Train: [69] [3400/6250] eta: 0:08:07 lr: 0.000029 grad: 0.1021 (0.1122) loss: 0.8194 (0.8161) time: 0.1685 data: 0.0750 max mem: 9390 +Train: [69] [3500/6250] eta: 0:07:49 lr: 0.000029 grad: 0.1081 (0.1123) loss: 0.8191 (0.8162) time: 0.1500 data: 0.0620 max mem: 9390 +Train: [69] [3600/6250] eta: 0:07:32 lr: 0.000029 grad: 0.1188 (0.1124) loss: 0.8134 (0.8162) time: 0.1635 data: 0.0733 max mem: 9390 +Train: [69] [3700/6250] eta: 0:07:15 lr: 0.000029 grad: 0.1078 (0.1124) loss: 0.8191 (0.8162) time: 0.1707 data: 0.0695 max mem: 9390 +Train: [69] [3800/6250] eta: 0:06:58 lr: 0.000029 grad: 0.1064 (0.1125) loss: 0.8240 (0.8162) time: 0.1770 data: 0.0981 max mem: 9390 +Train: [69] [3900/6250] eta: 0:06:41 lr: 0.000029 grad: 0.1048 (0.1125) loss: 0.8197 (0.8163) time: 0.1747 data: 0.0791 max mem: 9390 +Train: [69] [4000/6250] eta: 0:06:26 lr: 0.000029 grad: 0.1137 (0.1126) loss: 0.8167 (0.8163) time: 0.2966 data: 0.1921 max mem: 9390 +Train: [69] [4100/6250] eta: 0:06:08 lr: 0.000029 grad: 0.1183 (0.1126) loss: 0.8204 (0.8163) time: 0.1614 data: 0.0769 max mem: 9390 +Train: [69] [4200/6250] eta: 0:05:51 lr: 0.000029 grad: 0.1098 (0.1127) loss: 0.8157 (0.8163) time: 0.1730 data: 0.0928 max mem: 9390 +Train: [69] [4300/6250] eta: 0:05:33 lr: 0.000029 grad: 0.1141 (0.1127) loss: 0.8177 (0.8163) time: 0.1912 data: 0.1008 max mem: 9390 +Train: [69] [4400/6250] eta: 0:05:16 lr: 0.000029 grad: 0.1144 (0.1128) loss: 0.8217 (0.8163) time: 0.1693 data: 0.0779 max mem: 9390 +Train: [69] [4500/6250] eta: 0:05:00 lr: 0.000029 grad: 0.1137 (0.1129) loss: 0.8138 (0.8163) time: 0.1707 data: 0.0816 max mem: 9390 +Train: [69] [4600/6250] eta: 0:04:43 lr: 0.000029 grad: 0.1148 (0.1130) loss: 0.8180 (0.8163) time: 0.1720 data: 0.0789 max mem: 9390 +Train: [69] [4700/6250] eta: 0:04:27 lr: 0.000029 grad: 0.1130 (0.1130) loss: 0.8130 (0.8163) time: 0.2419 data: 0.1620 max mem: 9390 +Train: [69] [4800/6250] eta: 0:04:09 lr: 0.000029 grad: 0.1162 (0.1131) loss: 0.8107 (0.8163) time: 0.1881 data: 0.1116 max mem: 9390 +Train: [69] [4900/6250] eta: 0:03:52 lr: 0.000029 grad: 0.1192 (0.1132) loss: 0.8122 (0.8162) time: 0.1743 data: 0.0706 max mem: 9390 +Train: [69] [5000/6250] eta: 0:03:35 lr: 0.000029 grad: 0.1172 (0.1133) loss: 0.8159 (0.8162) time: 0.1785 data: 0.0802 max mem: 9390 +Train: [69] [5100/6250] eta: 0:03:18 lr: 0.000029 grad: 0.1046 (0.1133) loss: 0.8176 (0.8162) time: 0.1630 data: 0.0699 max mem: 9390 +Train: [69] [5200/6250] eta: 0:03:01 lr: 0.000029 grad: 0.1062 (0.1134) loss: 0.8152 (0.8162) time: 0.1640 data: 0.0589 max mem: 9390 +Train: [69] [5300/6250] eta: 0:02:44 lr: 0.000029 grad: 0.1152 (0.1134) loss: 0.8190 (0.8161) time: 0.1599 data: 0.0605 max mem: 9390 +Train: [69] [5400/6250] eta: 0:02:26 lr: 0.000029 grad: 0.1104 (0.1134) loss: 0.8154 (0.8161) time: 0.1573 data: 0.0682 max mem: 9390 +Train: [69] [5500/6250] eta: 0:02:09 lr: 0.000029 grad: 0.1045 (0.1134) loss: 0.8147 (0.8162) time: 0.1959 data: 0.1038 max mem: 9390 +Train: [69] [5600/6250] eta: 0:01:52 lr: 0.000028 grad: 0.1037 (0.1133) loss: 0.8211 (0.8162) time: 0.1632 data: 0.0796 max mem: 9390 +Train: [69] [5700/6250] eta: 0:01:34 lr: 0.000028 grad: 0.1118 (0.1133) loss: 0.8145 (0.8163) time: 0.1677 data: 0.0768 max mem: 9390 +Train: [69] [5800/6250] eta: 0:01:17 lr: 0.000028 grad: 0.1101 (0.1133) loss: 0.8195 (0.8163) time: 0.1862 data: 0.0992 max mem: 9390 +Train: [69] [5900/6250] eta: 0:01:00 lr: 0.000028 grad: 0.1056 (0.1132) loss: 0.8200 (0.8163) time: 0.1611 data: 0.0706 max mem: 9390 +Train: [69] [6000/6250] eta: 0:00:43 lr: 0.000028 grad: 0.1059 (0.1132) loss: 0.8177 (0.8164) time: 0.1594 data: 0.0673 max mem: 9390 +Train: [69] [6100/6250] eta: 0:00:25 lr: 0.000028 grad: 0.1092 (0.1132) loss: 0.8181 (0.8165) time: 0.1331 data: 0.0469 max mem: 9390 +Train: [69] [6200/6250] eta: 0:00:08 lr: 0.000028 grad: 0.1049 (0.1132) loss: 0.8223 (0.8165) time: 0.1139 data: 0.0210 max mem: 9390 +Train: [69] [6249/6250] eta: 0:00:00 lr: 0.000028 grad: 0.1106 (0.1132) loss: 0.8160 (0.8165) time: 0.1645 data: 0.0766 max mem: 9390 +Train: [69] Total time: 0:18:11 (0.1746 s / it) +Averaged stats: lr: 0.000028 grad: 0.1106 (0.1132) loss: 0.8160 (0.8165) +Eval (hcp-train-subset): [69] [ 0/62] eta: 0:03:50 loss: 0.8385 (0.8385) time: 3.7107 data: 3.6504 max mem: 9390 +Eval (hcp-train-subset): [69] [61/62] eta: 0:00:00 loss: 0.8289 (0.8307) time: 0.1182 data: 0.0923 max mem: 9390 +Eval (hcp-train-subset): [69] Total time: 0:00:13 (0.2203 s / it) +Averaged stats (hcp-train-subset): loss: 0.8289 (0.8307) +Making plots (hcp-train-subset): example=14 +Eval (hcp-val): [69] [ 0/62] eta: 0:04:14 loss: 0.8273 (0.8273) time: 4.1104 data: 4.0332 max mem: 9390 +Eval (hcp-val): [69] [61/62] eta: 0:00:00 loss: 0.8313 (0.8325) time: 0.1043 data: 0.0792 max mem: 9390 +Eval (hcp-val): [69] Total time: 0:00:13 (0.2221 s / it) +Averaged stats (hcp-val): loss: 0.8313 (0.8325) +Making plots (hcp-val): example=23 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +Train: [70] [ 0/6250] eta: 12:15:02 lr: 0.000028 grad: 0.8458 (0.8458) loss: 0.8183 (0.8183) time: 7.0564 data: 6.9339 max mem: 9390 +Train: [70] [ 100/6250] eta: 0:24:02 lr: 0.000028 grad: 0.1090 (0.1320) loss: 0.8222 (0.8312) time: 0.1938 data: 0.0844 max mem: 9390 +Train: [70] [ 200/6250] eta: 0:20:32 lr: 0.000028 grad: 0.1033 (0.1236) loss: 0.8219 (0.8271) time: 0.1730 data: 0.0720 max mem: 9390 +Train: [70] [ 300/6250] eta: 0:18:57 lr: 0.000028 grad: 0.0986 (0.1193) loss: 0.8286 (0.8253) time: 0.1481 data: 0.0534 max mem: 9390 +Train: [70] [ 400/6250] eta: 0:17:48 lr: 0.000028 grad: 0.1021 (0.1172) loss: 0.8166 (0.8232) time: 0.1521 data: 0.0527 max mem: 9390 +Train: [70] [ 500/6250] eta: 0:17:04 lr: 0.000028 grad: 0.0984 (0.1148) loss: 0.8191 (0.8223) time: 0.1558 data: 0.0545 max mem: 9390 +Train: [70] [ 600/6250] eta: 0:16:32 lr: 0.000028 grad: 0.0997 (0.1129) loss: 0.8200 (0.8224) time: 0.1283 data: 0.0184 max mem: 9390 +Train: [70] [ 700/6250] eta: 0:16:04 lr: 0.000028 grad: 0.1038 (0.1119) loss: 0.8246 (0.8226) time: 0.1335 data: 0.0263 max mem: 9390 +Train: [70] [ 800/6250] eta: 0:15:49 lr: 0.000028 grad: 0.0991 (0.1115) loss: 0.8253 (0.8224) time: 0.1920 data: 0.1039 max mem: 9390 +Train: [70] [ 900/6250] eta: 0:15:38 lr: 0.000028 grad: 0.1099 (0.1109) loss: 0.8204 (0.8223) time: 0.1955 data: 0.1005 max mem: 9390 +Train: [70] [1000/6250] eta: 0:15:15 lr: 0.000028 grad: 0.1024 (0.1105) loss: 0.8196 (0.8221) time: 0.1772 data: 0.0924 max mem: 9390 +Train: [70] [1100/6250] eta: 0:14:48 lr: 0.000028 grad: 0.1030 (0.1100) loss: 0.8246 (0.8220) time: 0.1397 data: 0.0436 max mem: 9390 +Train: [70] [1200/6250] eta: 0:14:22 lr: 0.000028 grad: 0.1110 (0.1099) loss: 0.8188 (0.8218) time: 0.1521 data: 0.0654 max mem: 9390 +Train: [70] [1300/6250] eta: 0:14:00 lr: 0.000028 grad: 0.1080 (0.1096) loss: 0.8193 (0.8215) time: 0.1450 data: 0.0511 max mem: 9390 +Train: [70] [1400/6250] eta: 0:13:46 lr: 0.000028 grad: 0.1043 (0.1094) loss: 0.8174 (0.8212) time: 0.1795 data: 0.0878 max mem: 9390 +Train: [70] [1500/6250] eta: 0:13:31 lr: 0.000028 grad: 0.1049 (0.1094) loss: 0.8174 (0.8209) time: 0.1846 data: 0.0919 max mem: 9390 +Train: [70] [1600/6250] eta: 0:13:13 lr: 0.000028 grad: 0.1091 (0.1095) loss: 0.8184 (0.8205) time: 0.1780 data: 0.0907 max mem: 9390 +Train: [70] [1700/6250] eta: 0:12:55 lr: 0.000028 grad: 0.1094 (0.1095) loss: 0.8189 (0.8204) time: 0.1916 data: 0.1021 max mem: 9390 +Train: [70] [1800/6250] eta: 0:12:36 lr: 0.000028 grad: 0.1028 (0.1094) loss: 0.8164 (0.8202) time: 0.1544 data: 0.0660 max mem: 9390 +Train: [70] [1900/6250] eta: 0:12:19 lr: 0.000028 grad: 0.1031 (0.1094) loss: 0.8198 (0.8201) time: 0.1657 data: 0.0836 max mem: 9390 +Train: [70] [2000/6250] eta: 0:12:00 lr: 0.000028 grad: 0.1142 (0.1094) loss: 0.8136 (0.8199) time: 0.1707 data: 0.0751 max mem: 9390 +Train: [70] [2100/6250] eta: 0:11:42 lr: 0.000028 grad: 0.1038 (0.1093) loss: 0.8196 (0.8198) time: 0.1496 data: 0.0636 max mem: 9390 +Train: [70] [2200/6250] eta: 0:11:26 lr: 0.000028 grad: 0.1005 (0.1092) loss: 0.8215 (0.8196) time: 0.1724 data: 0.0803 max mem: 9390 +Train: [70] [2300/6250] eta: 0:11:09 lr: 0.000028 grad: 0.1086 (0.1093) loss: 0.8177 (0.8195) time: 0.1879 data: 0.1080 max mem: 9390 +Train: [70] [2400/6250] eta: 0:10:52 lr: 0.000028 grad: 0.1100 (0.1093) loss: 0.8198 (0.8193) time: 0.1486 data: 0.0583 max mem: 9390 +Train: [70] [2500/6250] eta: 0:10:40 lr: 0.000028 grad: 0.1154 (0.1095) loss: 0.8063 (0.8191) time: 0.1434 data: 0.0535 max mem: 9390 +Train: [70] [2600/6250] eta: 0:10:26 lr: 0.000028 grad: 0.1103 (0.1097) loss: 0.8135 (0.8190) time: 0.1825 data: 0.0881 max mem: 9390 +Train: [70] [2700/6250] eta: 0:10:10 lr: 0.000028 grad: 0.1112 (0.1098) loss: 0.8127 (0.8189) time: 0.1828 data: 0.1026 max mem: 9390 +Train: [70] [2800/6250] eta: 0:09:53 lr: 0.000028 grad: 0.1107 (0.1100) loss: 0.8169 (0.8186) time: 0.1793 data: 0.0959 max mem: 9390 +Train: [70] [2900/6250] eta: 0:09:37 lr: 0.000028 grad: 0.1081 (0.1101) loss: 0.8114 (0.8185) time: 0.1602 data: 0.0768 max mem: 9390 +Train: [70] [3000/6250] eta: 0:09:20 lr: 0.000027 grad: 0.1092 (0.1102) loss: 0.8145 (0.8184) time: 0.1827 data: 0.1003 max mem: 9390 +Train: [70] [3100/6250] eta: 0:09:03 lr: 0.000027 grad: 0.1024 (0.1103) loss: 0.8189 (0.8183) time: 0.1779 data: 0.0928 max mem: 9390 +Train: [70] [3200/6250] eta: 0:08:45 lr: 0.000027 grad: 0.1119 (0.1104) loss: 0.8153 (0.8183) time: 0.1739 data: 0.0869 max mem: 9390 +Train: [70] [3300/6250] eta: 0:08:27 lr: 0.000027 grad: 0.1126 (0.1106) loss: 0.8191 (0.8182) time: 0.1665 data: 0.0855 max mem: 9390 +Train: [70] [3400/6250] eta: 0:08:10 lr: 0.000027 grad: 0.1175 (0.1107) loss: 0.8115 (0.8181) time: 0.2073 data: 0.1189 max mem: 9390 +Train: [70] [3500/6250] eta: 0:07:53 lr: 0.000027 grad: 0.1070 (0.1108) loss: 0.8199 (0.8181) time: 0.1850 data: 0.0782 max mem: 9390 +Train: [70] [3600/6250] eta: 0:07:35 lr: 0.000027 grad: 0.1115 (0.1110) loss: 0.8083 (0.8180) time: 0.1808 data: 0.0960 max mem: 9390 +Train: [70] [3700/6250] eta: 0:07:20 lr: 0.000027 grad: 0.1126 (0.1111) loss: 0.8153 (0.8178) time: 0.1910 data: 0.1015 max mem: 9390 +Train: [70] [3800/6250] eta: 0:07:02 lr: 0.000027 grad: 0.1033 (0.1113) loss: 0.8171 (0.8178) time: 0.1717 data: 0.0843 max mem: 9390 +Train: [70] [3900/6250] eta: 0:06:45 lr: 0.000027 grad: 0.1071 (0.1114) loss: 0.8169 (0.8178) time: 0.1890 data: 0.1076 max mem: 9390 +Train: [70] [4000/6250] eta: 0:06:28 lr: 0.000027 grad: 0.1179 (0.1116) loss: 0.8208 (0.8178) time: 0.1086 data: 0.0152 max mem: 9390 +Train: [70] [4100/6250] eta: 0:06:10 lr: 0.000027 grad: 0.1153 (0.1118) loss: 0.8094 (0.8177) time: 0.1550 data: 0.0569 max mem: 9390 +Train: [70] [4200/6250] eta: 0:05:53 lr: 0.000027 grad: 0.1124 (0.1120) loss: 0.8066 (0.8175) time: 0.1683 data: 0.0777 max mem: 9390 +Train: [70] [4300/6250] eta: 0:05:36 lr: 0.000027 grad: 0.1165 (0.1121) loss: 0.8137 (0.8174) time: 0.2037 data: 0.1218 max mem: 9390 +Train: [70] [4400/6250] eta: 0:05:20 lr: 0.000027 grad: 0.1129 (0.1123) loss: 0.8159 (0.8174) time: 0.1571 data: 0.0540 max mem: 9390 +Train: [70] [4500/6250] eta: 0:05:02 lr: 0.000027 grad: 0.1259 (0.1125) loss: 0.8074 (0.8172) time: 0.1678 data: 0.0717 max mem: 9390 +Train: [70] [4600/6250] eta: 0:04:45 lr: 0.000027 grad: 0.1141 (0.1126) loss: 0.8096 (0.8171) time: 0.2076 data: 0.0945 max mem: 9390 +Train: [70] [4700/6250] eta: 0:04:28 lr: 0.000027 grad: 0.1168 (0.1128) loss: 0.8088 (0.8169) time: 0.1205 data: 0.0074 max mem: 9390 +Train: [70] [4800/6250] eta: 0:04:11 lr: 0.000027 grad: 0.1173 (0.1130) loss: 0.8074 (0.8167) time: 0.1452 data: 0.0553 max mem: 9390 +Train: [70] [4900/6250] eta: 0:03:53 lr: 0.000027 grad: 0.1216 (0.1131) loss: 0.8091 (0.8166) time: 0.1980 data: 0.1118 max mem: 9390 +Train: [70] [5000/6250] eta: 0:03:36 lr: 0.000027 grad: 0.1165 (0.1133) loss: 0.8127 (0.8166) time: 0.1506 data: 0.0441 max mem: 9390 +Train: [70] [5100/6250] eta: 0:03:18 lr: 0.000027 grad: 0.1242 (0.1134) loss: 0.8126 (0.8165) time: 0.1564 data: 0.0556 max mem: 9390 +Train: [70] [5200/6250] eta: 0:03:02 lr: 0.000027 grad: 0.1178 (0.1135) loss: 0.8053 (0.8164) time: 0.1614 data: 0.0529 max mem: 9390 +Train: [70] [5300/6250] eta: 0:02:44 lr: 0.000027 grad: 0.1154 (0.1136) loss: 0.8100 (0.8163) time: 0.1740 data: 0.0831 max mem: 9390 +Train: [70] [5400/6250] eta: 0:02:27 lr: 0.000027 grad: 0.1088 (0.1136) loss: 0.8208 (0.8163) time: 0.1688 data: 0.0828 max mem: 9390 +Train: [70] [5500/6250] eta: 0:02:09 lr: 0.000027 grad: 0.1108 (0.1137) loss: 0.8122 (0.8162) time: 0.1719 data: 0.0918 max mem: 9390 +Train: [70] [5600/6250] eta: 0:01:52 lr: 0.000027 grad: 0.1135 (0.1137) loss: 0.8137 (0.8162) time: 0.1639 data: 0.0728 max mem: 9390 +Train: [70] [5700/6250] eta: 0:01:35 lr: 0.000027 grad: 0.1185 (0.1138) loss: 0.8081 (0.8162) time: 0.1596 data: 0.0653 max mem: 9390 +Train: [70] [5800/6250] eta: 0:01:18 lr: 0.000027 grad: 0.1176 (0.1139) loss: 0.8173 (0.8161) time: 0.2779 data: 0.1670 max mem: 9390 +Train: [70] [5900/6250] eta: 0:01:01 lr: 0.000027 grad: 0.1165 (0.1139) loss: 0.8098 (0.8161) time: 0.3305 data: 0.2209 max mem: 9390 +Train: [70] [6000/6250] eta: 0:00:43 lr: 0.000027 grad: 0.1144 (0.1140) loss: 0.8080 (0.8160) time: 0.1564 data: 0.0665 max mem: 9390 +Train: [70] [6100/6250] eta: 0:00:26 lr: 0.000027 grad: 0.1155 (0.1141) loss: 0.8061 (0.8160) time: 0.1490 data: 0.0395 max mem: 9390 +Train: [70] [6200/6250] eta: 0:00:08 lr: 0.000027 grad: 0.1106 (0.1141) loss: 0.8122 (0.8159) time: 0.1644 data: 0.0788 max mem: 9390 +Train: [70] [6249/6250] eta: 0:00:00 lr: 0.000027 grad: 0.1207 (0.1142) loss: 0.8117 (0.8159) time: 0.1676 data: 0.0872 max mem: 9390 +Train: [70] Total time: 0:18:19 (0.1758 s / it) +Averaged stats: lr: 0.000027 grad: 0.1207 (0.1142) loss: 0.8117 (0.8159) +Eval (hcp-train-subset): [70] [ 0/62] eta: 0:05:19 loss: 0.8395 (0.8395) time: 5.1563 data: 5.1204 max mem: 9390 +Eval (hcp-train-subset): [70] [61/62] eta: 0:00:00 loss: 0.8290 (0.8311) time: 0.1408 data: 0.1158 max mem: 9390 +Eval (hcp-train-subset): [70] Total time: 0:00:13 (0.2249 s / it) +Averaged stats (hcp-train-subset): loss: 0.8290 (0.8311) +Eval (hcp-val): [70] [ 0/62] eta: 0:04:16 loss: 0.8275 (0.8275) time: 4.1317 data: 4.0616 max mem: 9390 +Eval (hcp-val): [70] [61/62] eta: 0:00:00 loss: 0.8317 (0.8326) time: 0.1385 data: 0.1134 max mem: 9390 +Eval (hcp-val): [70] Total time: 0:00:14 (0.2386 s / it) +Averaged stats (hcp-val): loss: 0.8317 (0.8326) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +Train: [71] [ 0/6250] eta: 7:13:36 lr: 0.000027 grad: 0.3718 (0.3718) loss: 0.8450 (0.8450) time: 4.1627 data: 3.9630 max mem: 9390 +Train: [71] [ 100/6250] eta: 0:24:40 lr: 0.000027 grad: 0.1298 (0.1635) loss: 0.8195 (0.8254) time: 0.1722 data: 0.0443 max mem: 9390 +Train: [71] [ 200/6250] eta: 0:21:28 lr: 0.000027 grad: 0.1351 (0.1524) loss: 0.8102 (0.8181) time: 0.1785 data: 0.0827 max mem: 9390 +Train: [71] [ 300/6250] eta: 0:20:11 lr: 0.000027 grad: 0.1299 (0.1433) loss: 0.8141 (0.8162) time: 0.1673 data: 0.0549 max mem: 9390 +Train: [71] [ 400/6250] eta: 0:19:24 lr: 0.000026 grad: 0.1186 (0.1382) loss: 0.8127 (0.8162) time: 0.1808 data: 0.0713 max mem: 9390 +Train: [71] [ 500/6250] eta: 0:18:42 lr: 0.000026 grad: 0.1141 (0.1338) loss: 0.8187 (0.8169) time: 0.1810 data: 0.0838 max mem: 9390 +Train: [71] [ 600/6250] eta: 0:18:20 lr: 0.000026 grad: 0.1069 (0.1303) loss: 0.8205 (0.8173) time: 0.1871 data: 0.0844 max mem: 9390 +Train: [71] [ 700/6250] eta: 0:17:49 lr: 0.000026 grad: 0.1101 (0.1284) loss: 0.8210 (0.8172) time: 0.1557 data: 0.0668 max mem: 9390 +Train: [71] [ 800/6250] eta: 0:17:23 lr: 0.000026 grad: 0.1169 (0.1274) loss: 0.8116 (0.8170) time: 0.2183 data: 0.1078 max mem: 9390 +Train: [71] [ 900/6250] eta: 0:16:52 lr: 0.000026 grad: 0.1139 (0.1266) loss: 0.8111 (0.8167) time: 0.1813 data: 0.0867 max mem: 9390 +Train: [71] [1000/6250] eta: 0:16:28 lr: 0.000026 grad: 0.1098 (0.1254) loss: 0.8150 (0.8165) time: 0.2104 data: 0.1286 max mem: 9390 +Train: [71] [1100/6250] eta: 0:15:56 lr: 0.000026 grad: 0.1114 (0.1246) loss: 0.8177 (0.8164) time: 0.1604 data: 0.0749 max mem: 9390 +Train: [71] [1200/6250] eta: 0:15:29 lr: 0.000026 grad: 0.1223 (0.1240) loss: 0.8102 (0.8161) time: 0.1658 data: 0.0785 max mem: 9390 +Train: [71] [1300/6250] eta: 0:15:07 lr: 0.000026 grad: 0.1127 (0.1234) loss: 0.8050 (0.8158) time: 0.1588 data: 0.0565 max mem: 9390 +Train: [71] [1400/6250] eta: 0:14:49 lr: 0.000026 grad: 0.1189 (0.1233) loss: 0.8112 (0.8154) time: 0.1609 data: 0.0632 max mem: 9390 +Train: [71] [1500/6250] eta: 0:14:29 lr: 0.000026 grad: 0.1195 (0.1232) loss: 0.8071 (0.8148) time: 0.1614 data: 0.0812 max mem: 9390 +Train: [71] [1600/6250] eta: 0:14:06 lr: 0.000026 grad: 0.1205 (0.1230) loss: 0.8116 (0.8144) time: 0.1603 data: 0.0770 max mem: 9390 +Train: [71] [1700/6250] eta: 0:13:45 lr: 0.000026 grad: 0.1234 (0.1229) loss: 0.8064 (0.8139) time: 0.1656 data: 0.0736 max mem: 9390 +Train: [71] [1800/6250] eta: 0:13:22 lr: 0.000026 grad: 0.1164 (0.1227) loss: 0.8057 (0.8136) time: 0.1840 data: 0.1013 max mem: 9390 +Train: [71] [1900/6250] eta: 0:13:01 lr: 0.000026 grad: 0.1156 (0.1224) loss: 0.8109 (0.8134) time: 0.1678 data: 0.0869 max mem: 9390 +Train: [71] [2000/6250] eta: 0:12:40 lr: 0.000026 grad: 0.1208 (0.1225) loss: 0.8078 (0.8131) time: 0.1655 data: 0.0821 max mem: 9390 +Train: [71] [2100/6250] eta: 0:12:23 lr: 0.000026 grad: 0.1134 (0.1223) loss: 0.8107 (0.8129) time: 0.2233 data: 0.1403 max mem: 9390 +Train: [71] [2200/6250] eta: 0:12:01 lr: 0.000026 grad: 0.1209 (0.1222) loss: 0.8069 (0.8128) time: 0.1899 data: 0.0821 max mem: 9390 +Train: [71] [2300/6250] eta: 0:11:41 lr: 0.000026 grad: 0.1113 (0.1221) loss: 0.8128 (0.8127) time: 0.1600 data: 0.0724 max mem: 9390 +Train: [71] [2400/6250] eta: 0:11:23 lr: 0.000026 grad: 0.1158 (0.1219) loss: 0.8057 (0.8126) time: 0.1783 data: 0.0931 max mem: 9390 +Train: [71] [2500/6250] eta: 0:11:03 lr: 0.000026 grad: 0.1196 (0.1218) loss: 0.8121 (0.8125) time: 0.1656 data: 0.0798 max mem: 9390 +Train: [71] [2600/6250] eta: 0:10:43 lr: 0.000026 grad: 0.1158 (0.1216) loss: 0.8113 (0.8125) time: 0.1690 data: 0.0864 max mem: 9390 +Train: [71] [2700/6250] eta: 0:10:25 lr: 0.000026 grad: 0.1106 (0.1215) loss: 0.8140 (0.8125) time: 0.1978 data: 0.1220 max mem: 9390 +Train: [71] [2800/6250] eta: 0:10:07 lr: 0.000026 grad: 0.1133 (0.1215) loss: 0.8137 (0.8125) time: 0.1735 data: 0.0904 max mem: 9390 +Train: [71] [2900/6250] eta: 0:09:48 lr: 0.000026 grad: 0.1098 (0.1214) loss: 0.8088 (0.8124) time: 0.1523 data: 0.0650 max mem: 9390 +Train: [71] [3000/6250] eta: 0:09:32 lr: 0.000026 grad: 0.1207 (0.1213) loss: 0.8113 (0.8124) time: 0.2641 data: 0.1747 max mem: 9390 +Train: [71] [3100/6250] eta: 0:09:14 lr: 0.000026 grad: 0.1162 (0.1211) loss: 0.8122 (0.8124) time: 0.1979 data: 0.0829 max mem: 9390 +Train: [71] [3200/6250] eta: 0:08:55 lr: 0.000026 grad: 0.1149 (0.1212) loss: 0.8107 (0.8125) time: 0.1864 data: 0.0968 max mem: 9390 +Train: [71] [3300/6250] eta: 0:08:37 lr: 0.000026 grad: 0.1140 (0.1212) loss: 0.8180 (0.8125) time: 0.1522 data: 0.0669 max mem: 9390 +Train: [71] [3400/6250] eta: 0:08:20 lr: 0.000026 grad: 0.1172 (0.1212) loss: 0.8160 (0.8126) time: 0.1265 data: 0.0116 max mem: 9390 +Train: [71] [3500/6250] eta: 0:08:02 lr: 0.000026 grad: 0.1117 (0.1211) loss: 0.8228 (0.8126) time: 0.1703 data: 0.0880 max mem: 9390 +Train: [71] [3600/6250] eta: 0:07:48 lr: 0.000026 grad: 0.1216 (0.1210) loss: 0.8093 (0.8127) time: 0.1855 data: 0.0726 max mem: 9390 +Train: [71] [3700/6250] eta: 0:07:29 lr: 0.000026 grad: 0.1107 (0.1209) loss: 0.8173 (0.8128) time: 0.1663 data: 0.0785 max mem: 9390 +Train: [71] [3800/6250] eta: 0:07:14 lr: 0.000026 grad: 0.1205 (0.1208) loss: 0.8139 (0.8128) time: 0.2099 data: 0.1342 max mem: 9390 +Train: [71] [3900/6250] eta: 0:06:55 lr: 0.000026 grad: 0.1263 (0.1209) loss: 0.8053 (0.8128) time: 0.1999 data: 0.1123 max mem: 9390 +Train: [71] [4000/6250] eta: 0:06:38 lr: 0.000026 grad: 0.1146 (0.1208) loss: 0.8063 (0.8127) time: 0.1787 data: 0.0959 max mem: 9390 +Train: [71] [4100/6250] eta: 0:06:21 lr: 0.000026 grad: 0.1151 (0.1208) loss: 0.8126 (0.8127) time: 0.1852 data: 0.0903 max mem: 9390 +Train: [71] [4200/6250] eta: 0:06:03 lr: 0.000025 grad: 0.1229 (0.1208) loss: 0.8089 (0.8127) time: 0.1850 data: 0.0898 max mem: 9390 +Train: [71] [4300/6250] eta: 0:05:46 lr: 0.000025 grad: 0.1204 (0.1208) loss: 0.8104 (0.8127) time: 0.1807 data: 0.0897 max mem: 9390 +Train: [71] [4400/6250] eta: 0:05:28 lr: 0.000025 grad: 0.1161 (0.1208) loss: 0.8120 (0.8126) time: 0.1808 data: 0.0940 max mem: 9390 +Train: [71] [4500/6250] eta: 0:05:10 lr: 0.000025 grad: 0.1251 (0.1209) loss: 0.8132 (0.8126) time: 0.1713 data: 0.0729 max mem: 9390 +Train: [71] [4600/6250] eta: 0:04:52 lr: 0.000025 grad: 0.1157 (0.1209) loss: 0.8174 (0.8126) time: 0.1837 data: 0.0937 max mem: 9390 +Train: [71] [4700/6250] eta: 0:04:35 lr: 0.000025 grad: 0.1127 (0.1210) loss: 0.8115 (0.8126) time: 0.2128 data: 0.1277 max mem: 9390 +Train: [71] [4800/6250] eta: 0:04:16 lr: 0.000025 grad: 0.1204 (0.1210) loss: 0.8098 (0.8126) time: 0.1776 data: 0.0865 max mem: 9390 +Train: [71] [4900/6250] eta: 0:03:59 lr: 0.000025 grad: 0.1198 (0.1210) loss: 0.8114 (0.8125) time: 0.1715 data: 0.0809 max mem: 9390 +Train: [71] [5000/6250] eta: 0:03:41 lr: 0.000025 grad: 0.1126 (0.1209) loss: 0.8116 (0.8125) time: 0.1906 data: 0.0920 max mem: 9390 +Train: [71] [5100/6250] eta: 0:03:23 lr: 0.000025 grad: 0.1243 (0.1209) loss: 0.8033 (0.8125) time: 0.1690 data: 0.0793 max mem: 9390 +Train: [71] [5200/6250] eta: 0:03:05 lr: 0.000025 grad: 0.1151 (0.1209) loss: 0.8100 (0.8126) time: 0.1665 data: 0.0797 max mem: 9390 +Train: [71] [5300/6250] eta: 0:02:48 lr: 0.000025 grad: 0.1179 (0.1210) loss: 0.8156 (0.8126) time: 0.1719 data: 0.0895 max mem: 9390 +Train: [71] [5400/6250] eta: 0:02:30 lr: 0.000025 grad: 0.1156 (0.1210) loss: 0.8095 (0.8126) time: 0.1627 data: 0.0810 max mem: 9390 +Train: [71] [5500/6250] eta: 0:02:13 lr: 0.000025 grad: 0.1329 (0.1209) loss: 0.8126 (0.8126) time: 0.0995 data: 0.0003 max mem: 9390 +Train: [71] [5600/6250] eta: 0:01:56 lr: 0.000025 grad: 0.1194 (0.1210) loss: 0.8140 (0.8126) time: 0.2118 data: 0.1242 max mem: 9390 +Train: [71] [5700/6250] eta: 0:01:38 lr: 0.000025 grad: 0.1228 (0.1210) loss: 0.8119 (0.8126) time: 0.1541 data: 0.0738 max mem: 9390 +Train: [71] [5800/6250] eta: 0:01:20 lr: 0.000025 grad: 0.1186 (0.1211) loss: 0.8153 (0.8126) time: 0.1710 data: 0.0822 max mem: 9390 +Train: [71] [5900/6250] eta: 0:01:02 lr: 0.000025 grad: 0.1267 (0.1212) loss: 0.8074 (0.8126) time: 0.1534 data: 0.0570 max mem: 9390 +Train: [71] [6000/6250] eta: 0:00:44 lr: 0.000025 grad: 0.1261 (0.1213) loss: 0.8069 (0.8126) time: 0.1731 data: 0.0844 max mem: 9390 +Train: [71] [6100/6250] eta: 0:00:26 lr: 0.000025 grad: 0.1219 (0.1214) loss: 0.8085 (0.8125) time: 0.1880 data: 0.0828 max mem: 9390 +Train: [71] [6200/6250] eta: 0:00:08 lr: 0.000025 grad: 0.1256 (0.1215) loss: 0.8106 (0.8125) time: 0.1603 data: 0.0765 max mem: 9390 +Train: [71] [6249/6250] eta: 0:00:00 lr: 0.000025 grad: 0.1307 (0.1215) loss: 0.8171 (0.8125) time: 0.2422 data: 0.1645 max mem: 9390 +Train: [71] Total time: 0:18:47 (0.1805 s / it) +Averaged stats: lr: 0.000025 grad: 0.1307 (0.1215) loss: 0.8171 (0.8125) +Eval (hcp-train-subset): [71] [ 0/62] eta: 0:04:46 loss: 0.8419 (0.8419) time: 4.6280 data: 4.5804 max mem: 9390 +Eval (hcp-train-subset): [71] [61/62] eta: 0:00:00 loss: 0.8256 (0.8286) time: 0.1344 data: 0.1073 max mem: 9390 +Eval (hcp-train-subset): [71] Total time: 0:00:13 (0.2222 s / it) +Averaged stats (hcp-train-subset): loss: 0.8256 (0.8286) +Eval (hcp-val): [71] [ 0/62] eta: 0:03:41 loss: 0.8310 (0.8310) time: 3.5734 data: 3.4866 max mem: 9390 +Eval (hcp-val): [71] [61/62] eta: 0:00:00 loss: 0.8311 (0.8324) time: 0.1262 data: 0.1003 max mem: 9390 +Eval (hcp-val): [71] Total time: 0:00:14 (0.2268 s / it) +Averaged stats (hcp-val): loss: 0.8311 (0.8324) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +Train: [72] [ 0/6250] eta: 10:03:01 lr: 0.000025 grad: 0.3326 (0.3326) loss: 0.8146 (0.8146) time: 5.7890 data: 5.5237 max mem: 9390 +Train: [72] [ 100/6250] eta: 0:25:39 lr: 0.000025 grad: 0.1073 (0.1351) loss: 0.8231 (0.8287) time: 0.2039 data: 0.0970 max mem: 9390 +Train: [72] [ 200/6250] eta: 0:22:47 lr: 0.000025 grad: 0.1280 (0.1303) loss: 0.8069 (0.8239) time: 0.1827 data: 0.0801 max mem: 9390 +Train: [72] [ 300/6250] eta: 0:21:47 lr: 0.000025 grad: 0.1179 (0.1276) loss: 0.8111 (0.8211) time: 0.2213 data: 0.1060 max mem: 9390 +Train: [72] [ 400/6250] eta: 0:21:08 lr: 0.000025 grad: 0.1223 (0.1253) loss: 0.8199 (0.8202) time: 0.2303 data: 0.1216 max mem: 9390 +Train: [72] [ 500/6250] eta: 0:20:18 lr: 0.000025 grad: 0.1303 (0.1255) loss: 0.8117 (0.8189) time: 0.1730 data: 0.0579 max mem: 9390 +Train: [72] [ 600/6250] eta: 0:19:36 lr: 0.000025 grad: 0.1079 (0.1253) loss: 0.8151 (0.8180) time: 0.2141 data: 0.1249 max mem: 9390 +Train: [72] [ 700/6250] eta: 0:18:58 lr: 0.000025 grad: 0.1202 (0.1247) loss: 0.8140 (0.8172) time: 0.1144 data: 0.0243 max mem: 9390 +Train: [72] [ 800/6250] eta: 0:18:30 lr: 0.000025 grad: 0.1162 (0.1243) loss: 0.8139 (0.8166) time: 0.1824 data: 0.0953 max mem: 9390 +Train: [72] [ 900/6250] eta: 0:17:49 lr: 0.000025 grad: 0.1186 (0.1242) loss: 0.8082 (0.8160) time: 0.2024 data: 0.1179 max mem: 9390 +Train: [72] [1000/6250] eta: 0:17:23 lr: 0.000025 grad: 0.1062 (0.1236) loss: 0.8151 (0.8159) time: 0.1659 data: 0.0729 max mem: 9390 +Train: [72] [1100/6250] eta: 0:17:07 lr: 0.000025 grad: 0.1163 (0.1236) loss: 0.8065 (0.8154) time: 0.1279 data: 0.0123 max mem: 9390 +Train: [72] [1200/6250] eta: 0:16:46 lr: 0.000025 grad: 0.1186 (0.1235) loss: 0.8112 (0.8148) time: 0.2217 data: 0.1366 max mem: 9390 +Train: [72] [1300/6250] eta: 0:16:23 lr: 0.000025 grad: 0.1143 (0.1233) loss: 0.8125 (0.8145) time: 0.1823 data: 0.0932 max mem: 9390 +Train: [72] [1400/6250] eta: 0:16:10 lr: 0.000025 grad: 0.1187 (0.1230) loss: 0.8076 (0.8140) time: 0.1500 data: 0.0626 max mem: 9390 +Train: [72] [1500/6250] eta: 0:15:41 lr: 0.000025 grad: 0.1233 (0.1228) loss: 0.8109 (0.8138) time: 0.1716 data: 0.0817 max mem: 9390 +Train: [72] [1600/6250] eta: 0:15:09 lr: 0.000025 grad: 0.1139 (0.1225) loss: 0.8126 (0.8136) time: 0.1419 data: 0.0569 max mem: 9390 +Train: [72] [1700/6250] eta: 0:14:41 lr: 0.000024 grad: 0.1105 (0.1224) loss: 0.8210 (0.8135) time: 0.1486 data: 0.0617 max mem: 9390 +Train: [72] [1800/6250] eta: 0:14:14 lr: 0.000024 grad: 0.1141 (0.1223) loss: 0.8141 (0.8134) time: 0.1532 data: 0.0604 max mem: 9390 +Train: [72] [1900/6250] eta: 0:13:49 lr: 0.000024 grad: 0.1185 (0.1220) loss: 0.8098 (0.8133) time: 0.1715 data: 0.0842 max mem: 9390 +Train: [72] [2000/6250] eta: 0:13:24 lr: 0.000024 grad: 0.1199 (0.1219) loss: 0.8128 (0.8132) time: 0.1606 data: 0.0740 max mem: 9390 +Train: [72] [2100/6250] eta: 0:13:02 lr: 0.000024 grad: 0.1206 (0.1219) loss: 0.8138 (0.8131) time: 0.1957 data: 0.1001 max mem: 9390 +Train: [72] [2200/6250] eta: 0:12:36 lr: 0.000024 grad: 0.1185 (0.1218) loss: 0.8113 (0.8130) time: 0.1663 data: 0.0769 max mem: 9390 +Train: [72] [2300/6250] eta: 0:12:12 lr: 0.000024 grad: 0.1186 (0.1216) loss: 0.8057 (0.8129) time: 0.1410 data: 0.0529 max mem: 9390 +Train: [72] [2400/6250] eta: 0:11:50 lr: 0.000024 grad: 0.1122 (0.1215) loss: 0.8113 (0.8128) time: 0.1710 data: 0.0896 max mem: 9390 +Train: [72] [2500/6250] eta: 0:11:29 lr: 0.000024 grad: 0.1198 (0.1214) loss: 0.8147 (0.8127) time: 0.1684 data: 0.0761 max mem: 9390 +Train: [72] [2600/6250] eta: 0:11:07 lr: 0.000024 grad: 0.1196 (0.1213) loss: 0.8146 (0.8127) time: 0.1688 data: 0.0806 max mem: 9390 +Train: [72] [2700/6250] eta: 0:10:47 lr: 0.000024 grad: 0.1235 (0.1212) loss: 0.8142 (0.8127) time: 0.1614 data: 0.0563 max mem: 9390 +Train: [72] [2800/6250] eta: 0:10:27 lr: 0.000024 grad: 0.1156 (0.1212) loss: 0.8131 (0.8127) time: 0.1584 data: 0.0692 max mem: 9390 +Train: [72] [2900/6250] eta: 0:10:09 lr: 0.000024 grad: 0.1151 (0.1210) loss: 0.8138 (0.8128) time: 0.1498 data: 0.0400 max mem: 9390 +Train: [72] [3000/6250] eta: 0:09:50 lr: 0.000024 grad: 0.1085 (0.1210) loss: 0.8194 (0.8127) time: 0.1688 data: 0.0770 max mem: 9390 +Train: [72] [3100/6250] eta: 0:09:33 lr: 0.000024 grad: 0.1152 (0.1209) loss: 0.8135 (0.8128) time: 0.2651 data: 0.1748 max mem: 9390 +Train: [72] [3200/6250] eta: 0:09:19 lr: 0.000024 grad: 0.1194 (0.1208) loss: 0.8117 (0.8128) time: 0.3569 data: 0.2455 max mem: 9390 +Train: [72] [3300/6250] eta: 0:08:57 lr: 0.000024 grad: 0.1124 (0.1207) loss: 0.8182 (0.8129) time: 0.1901 data: 0.0983 max mem: 9390 +Train: [72] [3400/6250] eta: 0:08:39 lr: 0.000024 grad: 0.1097 (0.1206) loss: 0.8174 (0.8129) time: 0.1999 data: 0.0813 max mem: 9390 +Train: [72] [3500/6250] eta: 0:08:21 lr: 0.000024 grad: 0.1155 (0.1206) loss: 0.8155 (0.8130) time: 0.1891 data: 0.0843 max mem: 9390 +Train: [72] [3600/6250] eta: 0:08:02 lr: 0.000024 grad: 0.1148 (0.1205) loss: 0.8072 (0.8129) time: 0.2083 data: 0.1027 max mem: 9390 +Train: [72] [3700/6250] eta: 0:07:44 lr: 0.000024 grad: 0.1145 (0.1204) loss: 0.8186 (0.8129) time: 0.1340 data: 0.0331 max mem: 9390 +Train: [72] [3800/6250] eta: 0:07:26 lr: 0.000024 grad: 0.1185 (0.1204) loss: 0.8147 (0.8129) time: 0.1240 data: 0.0175 max mem: 9390 +Train: [72] [3900/6250] eta: 0:07:07 lr: 0.000024 grad: 0.1093 (0.1204) loss: 0.8118 (0.8129) time: 0.1633 data: 0.0740 max mem: 9390 +Train: [72] [4000/6250] eta: 0:06:49 lr: 0.000024 grad: 0.1174 (0.1205) loss: 0.8114 (0.8128) time: 0.1881 data: 0.0988 max mem: 9390 +Train: [72] [4100/6250] eta: 0:06:31 lr: 0.000024 grad: 0.1130 (0.1205) loss: 0.8120 (0.8128) time: 0.2344 data: 0.1076 max mem: 9390 +Train: [72] [4200/6250] eta: 0:06:12 lr: 0.000024 grad: 0.1130 (0.1205) loss: 0.8174 (0.8127) time: 0.1836 data: 0.0939 max mem: 9390 +Train: [72] [4300/6250] eta: 0:05:53 lr: 0.000024 grad: 0.1153 (0.1205) loss: 0.8117 (0.8127) time: 0.1710 data: 0.0835 max mem: 9390 +Train: [72] [4400/6250] eta: 0:05:34 lr: 0.000024 grad: 0.1177 (0.1205) loss: 0.8080 (0.8126) time: 0.1831 data: 0.0936 max mem: 9390 +Train: [72] [4500/6250] eta: 0:05:16 lr: 0.000024 grad: 0.1185 (0.1205) loss: 0.8155 (0.8126) time: 0.1939 data: 0.0654 max mem: 9390 +Train: [72] [4600/6250] eta: 0:04:58 lr: 0.000024 grad: 0.1134 (0.1205) loss: 0.8145 (0.8125) time: 0.1868 data: 0.0971 max mem: 9390 +Train: [72] [4700/6250] eta: 0:04:40 lr: 0.000024 grad: 0.1245 (0.1205) loss: 0.8141 (0.8125) time: 0.2742 data: 0.1854 max mem: 9390 +Train: [72] [4800/6250] eta: 0:04:21 lr: 0.000024 grad: 0.1236 (0.1205) loss: 0.8061 (0.8124) time: 0.1667 data: 0.0781 max mem: 9390 +Train: [72] [4900/6250] eta: 0:04:03 lr: 0.000024 grad: 0.1168 (0.1205) loss: 0.8091 (0.8124) time: 0.2098 data: 0.1035 max mem: 9390 +Train: [72] [5000/6250] eta: 0:03:46 lr: 0.000024 grad: 0.1179 (0.1205) loss: 0.8064 (0.8124) time: 0.1128 data: 0.0004 max mem: 9390 +Train: [72] [5100/6250] eta: 0:03:29 lr: 0.000024 grad: 0.1220 (0.1205) loss: 0.8049 (0.8123) time: 0.3077 data: 0.2254 max mem: 9390 +Train: [72] [5200/6250] eta: 0:03:10 lr: 0.000024 grad: 0.1180 (0.1205) loss: 0.8013 (0.8123) time: 0.1700 data: 0.0798 max mem: 9390 +Train: [72] [5300/6250] eta: 0:02:52 lr: 0.000024 grad: 0.1119 (0.1205) loss: 0.8124 (0.8123) time: 0.1599 data: 0.0797 max mem: 9390 +Train: [72] [5400/6250] eta: 0:02:34 lr: 0.000024 grad: 0.1062 (0.1204) loss: 0.8106 (0.8123) time: 0.1358 data: 0.0409 max mem: 9390 +Train: [72] [5500/6250] eta: 0:02:16 lr: 0.000023 grad: 0.1152 (0.1204) loss: 0.8077 (0.8123) time: 0.1941 data: 0.1092 max mem: 9390 +Train: [72] [5600/6250] eta: 0:01:57 lr: 0.000023 grad: 0.1121 (0.1204) loss: 0.8153 (0.8123) time: 0.1790 data: 0.0817 max mem: 9390 +Train: [72] [5700/6250] eta: 0:01:39 lr: 0.000023 grad: 0.1161 (0.1204) loss: 0.8168 (0.8123) time: 0.1724 data: 0.0700 max mem: 9390 +Train: [72] [5800/6250] eta: 0:01:21 lr: 0.000023 grad: 0.1157 (0.1204) loss: 0.8089 (0.8123) time: 0.1353 data: 0.0505 max mem: 9390 +Train: [72] [5900/6250] eta: 0:01:03 lr: 0.000023 grad: 0.1185 (0.1204) loss: 0.8111 (0.8123) time: 0.1755 data: 0.0859 max mem: 9390 +Train: [72] [6000/6250] eta: 0:00:45 lr: 0.000023 grad: 0.1195 (0.1204) loss: 0.8110 (0.8123) time: 0.1813 data: 0.0985 max mem: 9390 +Train: [72] [6100/6250] eta: 0:00:27 lr: 0.000023 grad: 0.1166 (0.1204) loss: 0.8082 (0.8123) time: 0.1693 data: 0.0830 max mem: 9390 +Train: [72] [6200/6250] eta: 0:00:09 lr: 0.000023 grad: 0.1230 (0.1205) loss: 0.8113 (0.8122) time: 0.1743 data: 0.0875 max mem: 9390 +Train: [72] [6249/6250] eta: 0:00:00 lr: 0.000023 grad: 0.1242 (0.1205) loss: 0.8052 (0.8122) time: 0.1688 data: 0.0928 max mem: 9390 +Train: [72] Total time: 0:18:57 (0.1820 s / it) +Averaged stats: lr: 0.000023 grad: 0.1242 (0.1205) loss: 0.8052 (0.8122) +Eval (hcp-train-subset): [72] [ 0/62] eta: 0:04:39 loss: 0.8351 (0.8351) time: 4.5047 data: 4.4596 max mem: 9390 +Eval (hcp-train-subset): [72] [61/62] eta: 0:00:00 loss: 0.8277 (0.8291) time: 0.1510 data: 0.1261 max mem: 9390 +Eval (hcp-train-subset): [72] Total time: 0:00:14 (0.2295 s / it) +Averaged stats (hcp-train-subset): loss: 0.8277 (0.8291) +Eval (hcp-val): [72] [ 0/62] eta: 0:04:42 loss: 0.8275 (0.8275) time: 4.5488 data: 4.5023 max mem: 9390 +Eval (hcp-val): [72] [61/62] eta: 0:00:00 loss: 0.8307 (0.8319) time: 0.1477 data: 0.1207 max mem: 9390 +Eval (hcp-val): [72] Total time: 0:00:13 (0.2253 s / it) +Averaged stats (hcp-val): loss: 0.8307 (0.8319) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +Train: [73] [ 0/6250] eta: 11:02:19 lr: 0.000023 grad: 0.2620 (0.2620) loss: 0.8171 (0.8171) time: 6.3583 data: 6.2290 max mem: 9390 +Train: [73] [ 100/6250] eta: 0:24:34 lr: 0.000023 grad: 0.1279 (0.1547) loss: 0.8236 (0.8251) time: 0.1953 data: 0.0917 max mem: 9390 +Train: [73] [ 200/6250] eta: 0:21:34 lr: 0.000023 grad: 0.1296 (0.1457) loss: 0.8105 (0.8203) time: 0.1447 data: 0.0389 max mem: 9390 +Train: [73] [ 300/6250] eta: 0:20:07 lr: 0.000023 grad: 0.1219 (0.1398) loss: 0.8062 (0.8167) time: 0.1627 data: 0.0517 max mem: 9390 +Train: [73] [ 400/6250] eta: 0:19:28 lr: 0.000023 grad: 0.1337 (0.1368) loss: 0.8017 (0.8147) time: 0.1959 data: 0.0930 max mem: 9390 +Train: [73] [ 500/6250] eta: 0:18:40 lr: 0.000023 grad: 0.1216 (0.1341) loss: 0.8061 (0.8134) time: 0.1952 data: 0.0802 max mem: 9390 +Train: [73] [ 600/6250] eta: 0:18:10 lr: 0.000023 grad: 0.1212 (0.1322) loss: 0.8111 (0.8128) time: 0.1809 data: 0.0878 max mem: 9390 +Train: [73] [ 700/6250] eta: 0:17:43 lr: 0.000023 grad: 0.1147 (0.1304) loss: 0.8180 (0.8129) time: 0.1561 data: 0.0479 max mem: 9390 +Train: [73] [ 800/6250] eta: 0:17:31 lr: 0.000023 grad: 0.1147 (0.1294) loss: 0.8073 (0.8129) time: 0.2511 data: 0.1606 max mem: 9390 +Train: [73] [ 900/6250] eta: 0:17:02 lr: 0.000023 grad: 0.1107 (0.1281) loss: 0.8190 (0.8131) time: 0.1813 data: 0.0730 max mem: 9390 +Train: [73] [1000/6250] eta: 0:16:45 lr: 0.000023 grad: 0.1244 (0.1271) loss: 0.8072 (0.8131) time: 0.1110 data: 0.0005 max mem: 9390 +Train: [73] [1100/6250] eta: 0:16:10 lr: 0.000023 grad: 0.1104 (0.1262) loss: 0.8135 (0.8130) time: 0.1609 data: 0.0715 max mem: 9390 +Train: [73] [1200/6250] eta: 0:15:40 lr: 0.000023 grad: 0.1097 (0.1254) loss: 0.8165 (0.8132) time: 0.1746 data: 0.0887 max mem: 9390 +Train: [73] [1300/6250] eta: 0:15:15 lr: 0.000023 grad: 0.1153 (0.1248) loss: 0.8128 (0.8133) time: 0.1923 data: 0.1026 max mem: 9390 +Train: [73] [1400/6250] eta: 0:14:46 lr: 0.000023 grad: 0.1102 (0.1241) loss: 0.8137 (0.8133) time: 0.1584 data: 0.0710 max mem: 9390 +Train: [73] [1500/6250] eta: 0:14:27 lr: 0.000023 grad: 0.1178 (0.1236) loss: 0.8107 (0.8132) time: 0.2204 data: 0.1109 max mem: 9390 +Train: [73] [1600/6250] eta: 0:14:08 lr: 0.000023 grad: 0.1146 (0.1233) loss: 0.8058 (0.8129) time: 0.1760 data: 0.0894 max mem: 9390 +Train: [73] [1700/6250] eta: 0:13:45 lr: 0.000023 grad: 0.1207 (0.1229) loss: 0.8114 (0.8127) time: 0.1137 data: 0.0216 max mem: 9390 +Train: [73] [1800/6250] eta: 0:13:22 lr: 0.000023 grad: 0.1151 (0.1227) loss: 0.8124 (0.8127) time: 0.1714 data: 0.0812 max mem: 9390 +Train: [73] [1900/6250] eta: 0:12:59 lr: 0.000023 grad: 0.1174 (0.1226) loss: 0.8103 (0.8126) time: 0.1894 data: 0.1014 max mem: 9390 +Train: [73] [2000/6250] eta: 0:12:36 lr: 0.000023 grad: 0.1144 (0.1224) loss: 0.8135 (0.8125) time: 0.1559 data: 0.0687 max mem: 9390 +Train: [73] [2100/6250] eta: 0:12:15 lr: 0.000023 grad: 0.1117 (0.1223) loss: 0.8111 (0.8124) time: 0.1595 data: 0.0718 max mem: 9390 +Train: [73] [2200/6250] eta: 0:11:57 lr: 0.000023 grad: 0.1225 (0.1221) loss: 0.8123 (0.8125) time: 0.1592 data: 0.0800 max mem: 9390 +Train: [73] [2300/6250] eta: 0:11:39 lr: 0.000023 grad: 0.1182 (0.1220) loss: 0.8170 (0.8124) time: 0.1983 data: 0.1062 max mem: 9390 +Train: [73] [2400/6250] eta: 0:11:24 lr: 0.000023 grad: 0.1160 (0.1221) loss: 0.8112 (0.8123) time: 0.1994 data: 0.1020 max mem: 9390 +Train: [73] [2500/6250] eta: 0:11:04 lr: 0.000023 grad: 0.1132 (0.1220) loss: 0.8123 (0.8123) time: 0.1581 data: 0.0697 max mem: 9390 +Train: [73] [2600/6250] eta: 0:10:48 lr: 0.000023 grad: 0.1215 (0.1220) loss: 0.8161 (0.8122) time: 0.1985 data: 0.0756 max mem: 9390 +Train: [73] [2700/6250] eta: 0:10:28 lr: 0.000023 grad: 0.1172 (0.1219) loss: 0.8101 (0.8122) time: 0.1959 data: 0.1168 max mem: 9390 +Train: [73] [2800/6250] eta: 0:10:10 lr: 0.000023 grad: 0.1151 (0.1219) loss: 0.8150 (0.8121) time: 0.1819 data: 0.1015 max mem: 9390 +Train: [73] [2900/6250] eta: 0:09:51 lr: 0.000023 grad: 0.1205 (0.1219) loss: 0.8031 (0.8120) time: 0.1362 data: 0.0478 max mem: 9390 +Train: [73] [3000/6250] eta: 0:09:33 lr: 0.000023 grad: 0.1167 (0.1219) loss: 0.8088 (0.8119) time: 0.1767 data: 0.0937 max mem: 9390 +Train: [73] [3100/6250] eta: 0:09:17 lr: 0.000023 grad: 0.1326 (0.1221) loss: 0.8093 (0.8118) time: 0.1946 data: 0.1085 max mem: 9390 +Train: [73] [3200/6250] eta: 0:08:59 lr: 0.000022 grad: 0.1213 (0.1222) loss: 0.8088 (0.8117) time: 0.1574 data: 0.0756 max mem: 9390 +Train: [73] [3300/6250] eta: 0:08:42 lr: 0.000022 grad: 0.1212 (0.1222) loss: 0.8050 (0.8117) time: 0.1875 data: 0.1005 max mem: 9390 +Train: [73] [3400/6250] eta: 0:08:24 lr: 0.000022 grad: 0.1233 (0.1223) loss: 0.8094 (0.8116) time: 0.1924 data: 0.0957 max mem: 9390 +Train: [73] [3500/6250] eta: 0:08:07 lr: 0.000022 grad: 0.1173 (0.1224) loss: 0.8096 (0.8115) time: 0.1944 data: 0.1105 max mem: 9390 +Train: [73] [3600/6250] eta: 0:07:49 lr: 0.000022 grad: 0.1218 (0.1225) loss: 0.8163 (0.8115) time: 0.1762 data: 0.0851 max mem: 9390 +Train: [73] [3700/6250] eta: 0:07:32 lr: 0.000022 grad: 0.1186 (0.1225) loss: 0.8102 (0.8114) time: 0.1942 data: 0.1105 max mem: 9390 +Train: [73] [3800/6250] eta: 0:07:14 lr: 0.000022 grad: 0.1163 (0.1225) loss: 0.8102 (0.8114) time: 0.1807 data: 0.0859 max mem: 9390 +Train: [73] [3900/6250] eta: 0:06:56 lr: 0.000022 grad: 0.1174 (0.1226) loss: 0.8093 (0.8113) time: 0.1625 data: 0.0696 max mem: 9390 +Train: [73] [4000/6250] eta: 0:06:38 lr: 0.000022 grad: 0.1149 (0.1225) loss: 0.8133 (0.8113) time: 0.1701 data: 0.0856 max mem: 9390 +Train: [73] [4100/6250] eta: 0:06:20 lr: 0.000022 grad: 0.1224 (0.1225) loss: 0.8055 (0.8113) time: 0.1639 data: 0.0695 max mem: 9390 +Train: [73] [4200/6250] eta: 0:06:02 lr: 0.000022 grad: 0.1209 (0.1225) loss: 0.8091 (0.8113) time: 0.1815 data: 0.1006 max mem: 9390 +Train: [73] [4300/6250] eta: 0:05:44 lr: 0.000022 grad: 0.1154 (0.1226) loss: 0.8182 (0.8113) time: 0.1885 data: 0.1141 max mem: 9390 +Train: [73] [4400/6250] eta: 0:05:26 lr: 0.000022 grad: 0.1195 (0.1226) loss: 0.8138 (0.8113) time: 0.1985 data: 0.1191 max mem: 9390 +Train: [73] [4500/6250] eta: 0:05:10 lr: 0.000022 grad: 0.1173 (0.1226) loss: 0.8133 (0.8113) time: 0.3091 data: 0.2096 max mem: 9390 +Train: [73] [4600/6250] eta: 0:04:53 lr: 0.000022 grad: 0.1224 (0.1226) loss: 0.8095 (0.8113) time: 0.2206 data: 0.1302 max mem: 9390 +Train: [73] [4700/6250] eta: 0:04:36 lr: 0.000022 grad: 0.1126 (0.1226) loss: 0.8173 (0.8114) time: 0.2109 data: 0.1051 max mem: 9390 +Train: [73] [4800/6250] eta: 0:04:18 lr: 0.000022 grad: 0.1159 (0.1226) loss: 0.8102 (0.8114) time: 0.1926 data: 0.1071 max mem: 9390 +Train: [73] [4900/6250] eta: 0:04:00 lr: 0.000022 grad: 0.1192 (0.1225) loss: 0.8145 (0.8115) time: 0.1769 data: 0.0908 max mem: 9390 +Train: [73] [5000/6250] eta: 0:03:42 lr: 0.000022 grad: 0.1129 (0.1225) loss: 0.8249 (0.8116) time: 0.2058 data: 0.1116 max mem: 9390 +Train: [73] [5100/6250] eta: 0:03:25 lr: 0.000022 grad: 0.1138 (0.1225) loss: 0.8151 (0.8116) time: 0.1856 data: 0.0974 max mem: 9390 +Train: [73] [5200/6250] eta: 0:03:06 lr: 0.000022 grad: 0.1183 (0.1224) loss: 0.8135 (0.8117) time: 0.1590 data: 0.0674 max mem: 9390 +Train: [73] [5300/6250] eta: 0:02:49 lr: 0.000022 grad: 0.1157 (0.1223) loss: 0.8196 (0.8118) time: 0.1794 data: 0.0877 max mem: 9390 +Train: [73] [5400/6250] eta: 0:02:31 lr: 0.000022 grad: 0.1265 (0.1223) loss: 0.8044 (0.8118) time: 0.1515 data: 0.0579 max mem: 9390 +Train: [73] [5500/6250] eta: 0:02:13 lr: 0.000022 grad: 0.1208 (0.1223) loss: 0.8134 (0.8119) time: 0.1226 data: 0.0323 max mem: 9390 +Train: [73] [5600/6250] eta: 0:01:55 lr: 0.000022 grad: 0.1135 (0.1223) loss: 0.8175 (0.8119) time: 0.1690 data: 0.0871 max mem: 9390 +Train: [73] [5700/6250] eta: 0:01:37 lr: 0.000022 grad: 0.1137 (0.1223) loss: 0.8164 (0.8120) time: 0.1679 data: 0.0728 max mem: 9390 +Train: [73] [5800/6250] eta: 0:01:19 lr: 0.000022 grad: 0.1159 (0.1223) loss: 0.8130 (0.8121) time: 0.1534 data: 0.0614 max mem: 9390 +Train: [73] [5900/6250] eta: 0:01:02 lr: 0.000022 grad: 0.1111 (0.1223) loss: 0.8188 (0.8121) time: 0.1973 data: 0.1060 max mem: 9390 +Train: [73] [6000/6250] eta: 0:00:44 lr: 0.000022 grad: 0.1125 (0.1223) loss: 0.8106 (0.8121) time: 0.1692 data: 0.0844 max mem: 9390 +Train: [73] [6100/6250] eta: 0:00:26 lr: 0.000022 grad: 0.1218 (0.1223) loss: 0.8097 (0.8122) time: 0.2027 data: 0.1194 max mem: 9390 +Train: [73] [6200/6250] eta: 0:00:08 lr: 0.000022 grad: 0.1172 (0.1222) loss: 0.8217 (0.8123) time: 0.2526 data: 0.1767 max mem: 9390 +Train: [73] [6249/6250] eta: 0:00:00 lr: 0.000022 grad: 0.1220 (0.1223) loss: 0.8154 (0.8123) time: 0.2594 data: 0.1738 max mem: 9390 +Train: [73] Total time: 0:18:48 (0.1806 s / it) +Averaged stats: lr: 0.000022 grad: 0.1220 (0.1223) loss: 0.8154 (0.8123) +Eval (hcp-train-subset): [73] [ 0/62] eta: 0:04:48 loss: 0.8350 (0.8350) time: 4.6552 data: 4.5748 max mem: 9390 +Eval (hcp-train-subset): [73] [61/62] eta: 0:00:00 loss: 0.8239 (0.8270) time: 0.1698 data: 0.1443 max mem: 9390 +Eval (hcp-train-subset): [73] Total time: 0:00:15 (0.2534 s / it) +Averaged stats (hcp-train-subset): loss: 0.8239 (0.8270) +Eval (hcp-val): [73] [ 0/62] eta: 0:04:16 loss: 0.8305 (0.8305) time: 4.1309 data: 4.0541 max mem: 9390 +Eval (hcp-val): [73] [61/62] eta: 0:00:00 loss: 0.8296 (0.8317) time: 0.1454 data: 0.1193 max mem: 9390 +Eval (hcp-val): [73] Total time: 0:00:14 (0.2417 s / it) +Averaged stats (hcp-val): loss: 0.8296 (0.8317) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +Train: [74] [ 0/6250] eta: 10:20:13 lr: 0.000022 grad: 0.2971 (0.2971) loss: 0.8170 (0.8170) time: 5.9542 data: 5.7741 max mem: 9390 +Train: [74] [ 100/6250] eta: 0:24:05 lr: 0.000022 grad: 0.1331 (0.1438) loss: 0.8274 (0.8271) time: 0.1647 data: 0.0492 max mem: 9390 +Train: [74] [ 200/6250] eta: 0:21:18 lr: 0.000022 grad: 0.1200 (0.1380) loss: 0.8142 (0.8199) time: 0.1759 data: 0.0646 max mem: 9390 +Train: [74] [ 300/6250] eta: 0:19:41 lr: 0.000022 grad: 0.1240 (0.1368) loss: 0.8166 (0.8161) time: 0.1739 data: 0.0735 max mem: 9390 +Train: [74] [ 400/6250] eta: 0:18:48 lr: 0.000022 grad: 0.1217 (0.1340) loss: 0.8087 (0.8138) time: 0.1477 data: 0.0490 max mem: 9390 +Train: [74] [ 500/6250] eta: 0:18:07 lr: 0.000022 grad: 0.1135 (0.1319) loss: 0.8183 (0.8137) time: 0.1947 data: 0.0926 max mem: 9390 +Train: [74] [ 600/6250] eta: 0:17:23 lr: 0.000022 grad: 0.1165 (0.1299) loss: 0.8190 (0.8140) time: 0.1980 data: 0.1023 max mem: 9390 +Train: [74] [ 700/6250] eta: 0:17:03 lr: 0.000022 grad: 0.1219 (0.1284) loss: 0.8098 (0.8144) time: 0.2125 data: 0.1196 max mem: 9390 +Train: [74] [ 800/6250] eta: 0:16:34 lr: 0.000022 grad: 0.1147 (0.1273) loss: 0.8136 (0.8147) time: 0.1892 data: 0.0867 max mem: 9390 +Train: [74] [ 900/6250] eta: 0:16:13 lr: 0.000021 grad: 0.1165 (0.1264) loss: 0.8141 (0.8148) time: 0.1930 data: 0.1035 max mem: 9390 +Train: [74] [1000/6250] eta: 0:15:58 lr: 0.000021 grad: 0.1135 (0.1255) loss: 0.8083 (0.8149) time: 0.1385 data: 0.0422 max mem: 9390 +Train: [74] [1100/6250] eta: 0:15:32 lr: 0.000021 grad: 0.1116 (0.1250) loss: 0.8175 (0.8148) time: 0.1650 data: 0.0687 max mem: 9390 +Train: [74] [1200/6250] eta: 0:15:14 lr: 0.000021 grad: 0.1189 (0.1248) loss: 0.8123 (0.8147) time: 0.1801 data: 0.0831 max mem: 9390 +Train: [74] [1300/6250] eta: 0:14:45 lr: 0.000021 grad: 0.1090 (0.1242) loss: 0.8191 (0.8147) time: 0.1718 data: 0.0858 max mem: 9390 +Train: [74] [1400/6250] eta: 0:14:23 lr: 0.000021 grad: 0.1201 (0.1238) loss: 0.8135 (0.8148) time: 0.1697 data: 0.0804 max mem: 9390 +Train: [74] [1500/6250] eta: 0:14:02 lr: 0.000021 grad: 0.1138 (0.1236) loss: 0.8131 (0.8148) time: 0.1698 data: 0.0863 max mem: 9390 +Train: [74] [1600/6250] eta: 0:13:40 lr: 0.000021 grad: 0.1148 (0.1232) loss: 0.8153 (0.8147) time: 0.1910 data: 0.1012 max mem: 9390 +Train: [74] [1700/6250] eta: 0:13:17 lr: 0.000021 grad: 0.1154 (0.1229) loss: 0.8165 (0.8147) time: 0.1773 data: 0.0915 max mem: 9390 +Train: [74] [1800/6250] eta: 0:12:58 lr: 0.000021 grad: 0.1179 (0.1226) loss: 0.8118 (0.8146) time: 0.1525 data: 0.0691 max mem: 9390 +Train: [74] [1900/6250] eta: 0:12:40 lr: 0.000021 grad: 0.1124 (0.1223) loss: 0.8134 (0.8147) time: 0.1500 data: 0.0546 max mem: 9390 +Train: [74] [2000/6250] eta: 0:12:21 lr: 0.000021 grad: 0.1150 (0.1221) loss: 0.8109 (0.8146) time: 0.1323 data: 0.0447 max mem: 9390 +Train: [74] [2100/6250] eta: 0:12:01 lr: 0.000021 grad: 0.1072 (0.1218) loss: 0.8184 (0.8146) time: 0.1544 data: 0.0615 max mem: 9390 +Train: [74] [2200/6250] eta: 0:11:44 lr: 0.000021 grad: 0.1158 (0.1217) loss: 0.8162 (0.8147) time: 0.1469 data: 0.0494 max mem: 9390 +Train: [74] [2300/6250] eta: 0:11:30 lr: 0.000021 grad: 0.1142 (0.1216) loss: 0.8149 (0.8148) time: 0.1824 data: 0.0900 max mem: 9390 +Train: [74] [2400/6250] eta: 0:11:14 lr: 0.000021 grad: 0.1155 (0.1215) loss: 0.8170 (0.8148) time: 0.1748 data: 0.0840 max mem: 9390 +Train: [74] [2500/6250] eta: 0:10:59 lr: 0.000021 grad: 0.1125 (0.1214) loss: 0.8112 (0.8147) time: 0.1849 data: 0.0959 max mem: 9390 +Train: [74] [2600/6250] eta: 0:10:45 lr: 0.000021 grad: 0.1137 (0.1212) loss: 0.8144 (0.8148) time: 0.2837 data: 0.1882 max mem: 9390 +Train: [74] [2700/6250] eta: 0:10:26 lr: 0.000021 grad: 0.1186 (0.1212) loss: 0.8093 (0.8147) time: 0.1978 data: 0.1067 max mem: 9390 +Train: [74] [2800/6250] eta: 0:10:09 lr: 0.000021 grad: 0.1190 (0.1211) loss: 0.8173 (0.8146) time: 0.2499 data: 0.1156 max mem: 9390 +Train: [74] [2900/6250] eta: 0:09:51 lr: 0.000021 grad: 0.1199 (0.1211) loss: 0.8108 (0.8145) time: 0.1808 data: 0.0966 max mem: 9390 +Train: [74] [3000/6250] eta: 0:09:35 lr: 0.000021 grad: 0.1147 (0.1210) loss: 0.8164 (0.8144) time: 0.1089 data: 0.0003 max mem: 9390 +Train: [74] [3100/6250] eta: 0:09:16 lr: 0.000021 grad: 0.1100 (0.1209) loss: 0.8125 (0.8144) time: 0.1769 data: 0.0898 max mem: 9390 +Train: [74] [3200/6250] eta: 0:08:58 lr: 0.000021 grad: 0.1123 (0.1207) loss: 0.8131 (0.8143) time: 0.1641 data: 0.0776 max mem: 9390 +Train: [74] [3300/6250] eta: 0:08:41 lr: 0.000021 grad: 0.1186 (0.1207) loss: 0.8132 (0.8142) time: 0.1584 data: 0.0664 max mem: 9390 +Train: [74] [3400/6250] eta: 0:08:23 lr: 0.000021 grad: 0.1116 (0.1206) loss: 0.8189 (0.8142) time: 0.1738 data: 0.0871 max mem: 9390 +Train: [74] [3500/6250] eta: 0:08:06 lr: 0.000021 grad: 0.1087 (0.1205) loss: 0.8121 (0.8141) time: 0.1224 data: 0.0005 max mem: 9390 +Train: [74] [3600/6250] eta: 0:07:48 lr: 0.000021 grad: 0.1176 (0.1204) loss: 0.8159 (0.8142) time: 0.1877 data: 0.0968 max mem: 9390 +Train: [74] [3700/6250] eta: 0:07:31 lr: 0.000021 grad: 0.1172 (0.1203) loss: 0.8109 (0.8142) time: 0.3011 data: 0.2035 max mem: 9390 +Train: [74] [3800/6250] eta: 0:07:13 lr: 0.000021 grad: 0.1130 (0.1202) loss: 0.8127 (0.8142) time: 0.1105 data: 0.0003 max mem: 9390 +Train: [74] [3900/6250] eta: 0:06:56 lr: 0.000021 grad: 0.1157 (0.1201) loss: 0.8173 (0.8142) time: 0.1706 data: 0.0584 max mem: 9390 +Train: [74] [4000/6250] eta: 0:06:39 lr: 0.000021 grad: 0.1170 (0.1200) loss: 0.8123 (0.8143) time: 0.1723 data: 0.0711 max mem: 9390 +Train: [74] [4100/6250] eta: 0:06:23 lr: 0.000021 grad: 0.1175 (0.1200) loss: 0.8102 (0.8144) time: 0.3177 data: 0.1977 max mem: 9390 +Train: [74] [4200/6250] eta: 0:06:05 lr: 0.000021 grad: 0.1151 (0.1200) loss: 0.8209 (0.8143) time: 0.3133 data: 0.2142 max mem: 9390 +Train: [74] [4300/6250] eta: 0:05:47 lr: 0.000021 grad: 0.1141 (0.1199) loss: 0.8206 (0.8143) time: 0.1585 data: 0.0692 max mem: 9390 +Train: [74] [4400/6250] eta: 0:05:29 lr: 0.000021 grad: 0.1236 (0.1200) loss: 0.8163 (0.8143) time: 0.2103 data: 0.0920 max mem: 9390 +Train: [74] [4500/6250] eta: 0:05:12 lr: 0.000021 grad: 0.1231 (0.1201) loss: 0.8161 (0.8143) time: 0.1994 data: 0.1102 max mem: 9390 +Train: [74] [4600/6250] eta: 0:04:54 lr: 0.000021 grad: 0.1245 (0.1201) loss: 0.8134 (0.8143) time: 0.1783 data: 0.0842 max mem: 9390 +Train: [74] [4700/6250] eta: 0:04:37 lr: 0.000021 grad: 0.1179 (0.1202) loss: 0.8138 (0.8143) time: 0.3268 data: 0.2335 max mem: 9390 +Train: [74] [4800/6250] eta: 0:04:18 lr: 0.000021 grad: 0.1189 (0.1202) loss: 0.8096 (0.8143) time: 0.1665 data: 0.0803 max mem: 9390 +Train: [74] [4900/6250] eta: 0:04:01 lr: 0.000020 grad: 0.1187 (0.1202) loss: 0.8144 (0.8143) time: 0.1694 data: 0.0756 max mem: 9390 +Train: [74] [5000/6250] eta: 0:03:43 lr: 0.000020 grad: 0.1228 (0.1202) loss: 0.8136 (0.8143) time: 0.1598 data: 0.0429 max mem: 9390 +Train: [74] [5100/6250] eta: 0:03:25 lr: 0.000020 grad: 0.1162 (0.1203) loss: 0.8172 (0.8143) time: 0.1474 data: 0.0554 max mem: 9390 +Train: [74] [5200/6250] eta: 0:03:07 lr: 0.000020 grad: 0.1218 (0.1203) loss: 0.8118 (0.8143) time: 0.1711 data: 0.0764 max mem: 9390 +Train: [74] [5300/6250] eta: 0:02:49 lr: 0.000020 grad: 0.1166 (0.1203) loss: 0.8129 (0.8143) time: 0.2053 data: 0.1232 max mem: 9390 +Train: [74] [5400/6250] eta: 0:02:31 lr: 0.000020 grad: 0.1215 (0.1203) loss: 0.8075 (0.8143) time: 0.1252 data: 0.0402 max mem: 9390 +Train: [74] [5500/6250] eta: 0:02:13 lr: 0.000020 grad: 0.1192 (0.1203) loss: 0.8126 (0.8143) time: 0.1063 data: 0.0037 max mem: 9390 +Train: [74] [5600/6250] eta: 0:01:56 lr: 0.000020 grad: 0.1158 (0.1203) loss: 0.8172 (0.8143) time: 0.1862 data: 0.0918 max mem: 9390 +Train: [74] [5700/6250] eta: 0:01:38 lr: 0.000020 grad: 0.1131 (0.1203) loss: 0.8206 (0.8143) time: 0.1798 data: 0.0920 max mem: 9390 +Train: [74] [5800/6250] eta: 0:01:20 lr: 0.000020 grad: 0.1172 (0.1203) loss: 0.8122 (0.8143) time: 0.1578 data: 0.0510 max mem: 9390 +Train: [74] [5900/6250] eta: 0:01:02 lr: 0.000020 grad: 0.1162 (0.1203) loss: 0.8232 (0.8143) time: 0.2038 data: 0.1011 max mem: 9390 +Train: [74] [6000/6250] eta: 0:00:44 lr: 0.000020 grad: 0.1109 (0.1202) loss: 0.8214 (0.8144) time: 0.1558 data: 0.0651 max mem: 9390 +Train: [74] [6100/6250] eta: 0:00:26 lr: 0.000020 grad: 0.1107 (0.1202) loss: 0.8200 (0.8144) time: 0.1913 data: 0.1100 max mem: 9390 +Train: [74] [6200/6250] eta: 0:00:08 lr: 0.000020 grad: 0.1148 (0.1201) loss: 0.8160 (0.8145) time: 0.1775 data: 0.0933 max mem: 9390 +Train: [74] [6249/6250] eta: 0:00:00 lr: 0.000020 grad: 0.1084 (0.1201) loss: 0.8213 (0.8146) time: 0.1733 data: 0.0858 max mem: 9390 +Train: [74] Total time: 0:18:45 (0.1802 s / it) +Averaged stats: lr: 0.000020 grad: 0.1084 (0.1201) loss: 0.8213 (0.8146) +Eval (hcp-train-subset): [74] [ 0/62] eta: 0:03:31 loss: 0.8300 (0.8300) time: 3.4072 data: 3.3349 max mem: 9390 +Eval (hcp-train-subset): [74] [61/62] eta: 0:00:00 loss: 0.8235 (0.8266) time: 0.1381 data: 0.1115 max mem: 9390 +Eval (hcp-train-subset): [74] Total time: 0:00:13 (0.2148 s / it) +Averaged stats (hcp-train-subset): loss: 0.8235 (0.8266) +Making plots (hcp-train-subset): example=4 +Eval (hcp-val): [74] [ 0/62] eta: 0:05:48 loss: 0.8255 (0.8255) time: 5.6206 data: 5.5895 max mem: 9390 +Eval (hcp-val): [74] [61/62] eta: 0:00:00 loss: 0.8288 (0.8307) time: 0.1565 data: 0.1310 max mem: 9390 +Eval (hcp-val): [74] Total time: 0:00:14 (0.2300 s / it) +Averaged stats (hcp-val): loss: 0.8288 (0.8307) +Making plots (hcp-val): example=16 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +Train: [75] [ 0/6250] eta: 11:20:03 lr: 0.000020 grad: nan (nan) loss: 0.7999 (0.7999) time: 6.5285 data: 6.4005 max mem: 9390 +Train: [75] [ 100/6250] eta: 0:24:32 lr: 0.000020 grad: 0.1372 (0.1762) loss: 0.7980 (0.8064) time: 0.1683 data: 0.0707 max mem: 9390 +Train: [75] [ 200/6250] eta: 0:21:21 lr: 0.000020 grad: 0.1243 (0.1550) loss: 0.8190 (0.8081) time: 0.2139 data: 0.1075 max mem: 9390 +Train: [75] [ 300/6250] eta: 0:20:11 lr: 0.000020 grad: 0.1237 (0.1473) loss: 0.8111 (0.8088) time: 0.1930 data: 0.0878 max mem: 9390 +Train: [75] [ 400/6250] eta: 0:19:13 lr: 0.000020 grad: 0.1085 (0.1416) loss: 0.8154 (0.8094) time: 0.1660 data: 0.0622 max mem: 9390 +Train: [75] [ 500/6250] eta: 0:18:39 lr: 0.000020 grad: 0.1191 (0.1375) loss: 0.8201 (0.8108) time: 0.1596 data: 0.0718 max mem: 9390 +Train: [75] [ 600/6250] eta: 0:18:09 lr: 0.000020 grad: 0.1151 (0.1342) loss: 0.8126 (0.8118) time: 0.1807 data: 0.0905 max mem: 9390 +Train: [75] [ 700/6250] eta: 0:17:38 lr: 0.000020 grad: 0.1092 (0.1324) loss: 0.8188 (0.8125) time: 0.1603 data: 0.0564 max mem: 9390 +Train: [75] [ 800/6250] eta: 0:17:09 lr: 0.000020 grad: 0.1168 (0.1313) loss: 0.8135 (0.8126) time: 0.1732 data: 0.0908 max mem: 9390 +Train: [75] [ 900/6250] eta: 0:16:36 lr: 0.000020 grad: 0.1138 (0.1300) loss: 0.8203 (0.8131) time: 0.1626 data: 0.0778 max mem: 9390 +Train: [75] [1000/6250] eta: 0:16:29 lr: 0.000020 grad: 0.1169 (0.1293) loss: 0.8107 (0.8129) time: 0.2684 data: 0.1855 max mem: 9390 +Train: [75] [1100/6250] eta: 0:16:02 lr: 0.000020 grad: 0.1090 (0.1286) loss: 0.8159 (0.8129) time: 0.1787 data: 0.0839 max mem: 9390 +Train: [75] [1200/6250] eta: 0:15:36 lr: 0.000020 grad: 0.1163 (0.1280) loss: 0.8100 (0.8129) time: 0.1444 data: 0.0505 max mem: 9390 +Train: [75] [1300/6250] eta: 0:15:09 lr: 0.000020 grad: 0.1249 (0.1278) loss: 0.8116 (0.8129) time: 0.1688 data: 0.0862 max mem: 9390 +Train: [75] [1400/6250] eta: 0:14:43 lr: 0.000020 grad: 0.1175 (0.1280) loss: 0.8139 (0.8128) time: 0.1681 data: 0.0868 max mem: 9390 +Train: [75] [1500/6250] eta: 0:14:20 lr: 0.000020 grad: 0.1178 (0.1278) loss: 0.8090 (0.8128) time: 0.1449 data: 0.0548 max mem: 9390 +Train: [75] [1600/6250] eta: 0:13:59 lr: 0.000020 grad: 0.1227 (0.1276) loss: 0.8143 (0.8125) time: 0.1801 data: 0.0963 max mem: 9390 +Train: [75] [1700/6250] eta: 0:13:42 lr: 0.000020 grad: 0.1311 (0.1275) loss: 0.8084 (0.8122) time: 0.1318 data: 0.0218 max mem: 9390 +Train: [75] [1800/6250] eta: 0:13:22 lr: 0.000020 grad: 0.1253 (0.1275) loss: 0.8106 (0.8120) time: 0.1935 data: 0.1036 max mem: 9390 +Train: [75] [1900/6250] eta: 0:13:01 lr: 0.000020 grad: 0.1289 (0.1275) loss: 0.8071 (0.8118) time: 0.1734 data: 0.0922 max mem: 9390 +Train: [75] [2000/6250] eta: 0:12:42 lr: 0.000020 grad: 0.1265 (0.1276) loss: 0.8043 (0.8116) time: 0.2535 data: 0.1638 max mem: 9390 +Train: [75] [2100/6250] eta: 0:12:23 lr: 0.000020 grad: 0.1312 (0.1275) loss: 0.8108 (0.8115) time: 0.2489 data: 0.1573 max mem: 9390 +Train: [75] [2200/6250] eta: 0:12:08 lr: 0.000020 grad: 0.1273 (0.1278) loss: 0.8108 (0.8114) time: 0.2191 data: 0.1327 max mem: 9390 +Train: [75] [2300/6250] eta: 0:11:47 lr: 0.000020 grad: 0.1247 (0.1278) loss: 0.8118 (0.8113) time: 0.1793 data: 0.0942 max mem: 9390 +Train: [75] [2400/6250] eta: 0:11:28 lr: 0.000020 grad: 0.1260 (0.1277) loss: 0.8118 (0.8113) time: 0.1961 data: 0.1113 max mem: 9390 +Train: [75] [2500/6250] eta: 0:11:14 lr: 0.000020 grad: 0.1277 (0.1278) loss: 0.8082 (0.8111) time: 0.2006 data: 0.1159 max mem: 9390 +Train: [75] [2600/6250] eta: 0:10:55 lr: 0.000020 grad: 0.1260 (0.1278) loss: 0.8051 (0.8110) time: 0.1703 data: 0.0846 max mem: 9390 +Train: [75] [2700/6250] eta: 0:10:37 lr: 0.000020 grad: 0.1157 (0.1276) loss: 0.8175 (0.8111) time: 0.1967 data: 0.1178 max mem: 9390 +Train: [75] [2800/6250] eta: 0:10:19 lr: 0.000019 grad: 0.1269 (0.1276) loss: 0.8106 (0.8111) time: 0.1926 data: 0.1003 max mem: 9390 +Train: [75] [2900/6250] eta: 0:10:03 lr: 0.000019 grad: 0.1307 (0.1277) loss: 0.8084 (0.8111) time: 0.2279 data: 0.1376 max mem: 9390 +Train: [75] [3000/6250] eta: 0:09:44 lr: 0.000019 grad: 0.1216 (0.1276) loss: 0.8069 (0.8111) time: 0.1779 data: 0.0822 max mem: 9390 +Train: [75] [3100/6250] eta: 0:09:25 lr: 0.000019 grad: 0.1189 (0.1274) loss: 0.8079 (0.8111) time: 0.1624 data: 0.0722 max mem: 9390 +Train: [75] [3200/6250] eta: 0:09:05 lr: 0.000019 grad: 0.1181 (0.1272) loss: 0.8114 (0.8112) time: 0.1622 data: 0.0738 max mem: 9390 +Train: [75] [3300/6250] eta: 0:08:45 lr: 0.000019 grad: 0.1256 (0.1271) loss: 0.8079 (0.8113) time: 0.1466 data: 0.0572 max mem: 9390 +Train: [75] [3400/6250] eta: 0:08:26 lr: 0.000019 grad: 0.1257 (0.1270) loss: 0.8162 (0.8114) time: 0.1582 data: 0.0686 max mem: 9390 +Train: [75] [3500/6250] eta: 0:08:07 lr: 0.000019 grad: 0.1113 (0.1268) loss: 0.8222 (0.8115) time: 0.1711 data: 0.0719 max mem: 9390 +Train: [75] [3600/6250] eta: 0:07:49 lr: 0.000019 grad: 0.1191 (0.1267) loss: 0.8152 (0.8116) time: 0.1535 data: 0.0531 max mem: 9390 +Train: [75] [3700/6250] eta: 0:07:31 lr: 0.000019 grad: 0.1222 (0.1267) loss: 0.8108 (0.8116) time: 0.1377 data: 0.0438 max mem: 9390 +Train: [75] [3800/6250] eta: 0:07:13 lr: 0.000019 grad: 0.1218 (0.1266) loss: 0.8147 (0.8117) time: 0.1410 data: 0.0511 max mem: 9390 +Train: [75] [3900/6250] eta: 0:06:56 lr: 0.000019 grad: 0.1181 (0.1266) loss: 0.8189 (0.8117) time: 0.1228 data: 0.0239 max mem: 9390 +Train: [75] [4000/6250] eta: 0:06:38 lr: 0.000019 grad: 0.1240 (0.1266) loss: 0.8170 (0.8118) time: 0.1726 data: 0.0900 max mem: 9390 +Train: [75] [4100/6250] eta: 0:06:20 lr: 0.000019 grad: 0.1232 (0.1266) loss: 0.8152 (0.8118) time: 0.1750 data: 0.0880 max mem: 9390 +Train: [75] [4200/6250] eta: 0:06:03 lr: 0.000019 grad: 0.1236 (0.1265) loss: 0.8186 (0.8118) time: 0.3033 data: 0.1579 max mem: 9390 +Train: [75] [4300/6250] eta: 0:05:45 lr: 0.000019 grad: 0.1253 (0.1265) loss: 0.8140 (0.8119) time: 0.1824 data: 0.0927 max mem: 9390 +Train: [75] [4400/6250] eta: 0:05:27 lr: 0.000019 grad: 0.1210 (0.1265) loss: 0.8181 (0.8120) time: 0.1746 data: 0.0801 max mem: 9390 +Train: [75] [4500/6250] eta: 0:05:09 lr: 0.000019 grad: 0.1192 (0.1264) loss: 0.8066 (0.8120) time: 0.1711 data: 0.0877 max mem: 9390 +Train: [75] [4600/6250] eta: 0:04:51 lr: 0.000019 grad: 0.1228 (0.1265) loss: 0.8179 (0.8121) time: 0.1652 data: 0.0785 max mem: 9390 +Train: [75] [4700/6250] eta: 0:04:33 lr: 0.000019 grad: 0.1228 (0.1264) loss: 0.8150 (0.8121) time: 0.1789 data: 0.0915 max mem: 9390 +Train: [75] [4800/6250] eta: 0:04:16 lr: 0.000019 grad: 0.1207 (0.1263) loss: 0.8214 (0.8122) time: 0.1933 data: 0.0707 max mem: 9390 +Train: [75] [4900/6250] eta: 0:03:58 lr: 0.000019 grad: 0.1180 (0.1263) loss: 0.8101 (0.8123) time: 0.1715 data: 0.0819 max mem: 9390 +Train: [75] [5000/6250] eta: 0:03:41 lr: 0.000019 grad: 0.1218 (0.1262) loss: 0.8181 (0.8124) time: 0.3249 data: 0.2349 max mem: 9390 +Train: [75] [5100/6250] eta: 0:03:23 lr: 0.000019 grad: 0.1190 (0.1262) loss: 0.8171 (0.8125) time: 0.1544 data: 0.0707 max mem: 9390 +Train: [75] [5200/6250] eta: 0:03:05 lr: 0.000019 grad: 0.1141 (0.1262) loss: 0.8229 (0.8125) time: 0.1440 data: 0.0553 max mem: 9390 +Train: [75] [5300/6250] eta: 0:02:47 lr: 0.000019 grad: 0.1250 (0.1262) loss: 0.8155 (0.8125) time: 0.1643 data: 0.0766 max mem: 9390 +Train: [75] [5400/6250] eta: 0:02:30 lr: 0.000019 grad: 0.1235 (0.1262) loss: 0.8143 (0.8125) time: 0.1531 data: 0.0624 max mem: 9390 +Train: [75] [5500/6250] eta: 0:02:13 lr: 0.000019 grad: 0.1283 (0.1263) loss: 0.8106 (0.8125) time: 0.2406 data: 0.1308 max mem: 9390 +Train: [75] [5600/6250] eta: 0:01:54 lr: 0.000019 grad: 0.1234 (0.1264) loss: 0.8068 (0.8124) time: 0.1556 data: 0.0633 max mem: 9390 +Train: [75] [5700/6250] eta: 0:01:37 lr: 0.000019 grad: 0.1309 (0.1264) loss: 0.8089 (0.8124) time: 0.2092 data: 0.1118 max mem: 9390 +Train: [75] [5800/6250] eta: 0:01:19 lr: 0.000019 grad: 0.1286 (0.1264) loss: 0.8156 (0.8124) time: 0.1881 data: 0.1070 max mem: 9390 +Train: [75] [5900/6250] eta: 0:01:01 lr: 0.000019 grad: 0.1244 (0.1265) loss: 0.8112 (0.8123) time: 0.1631 data: 0.0821 max mem: 9390 +Train: [75] [6000/6250] eta: 0:00:44 lr: 0.000019 grad: 0.1200 (0.1265) loss: 0.8109 (0.8123) time: 0.1556 data: 0.0711 max mem: 9390 +Train: [75] [6100/6250] eta: 0:00:26 lr: 0.000019 grad: 0.1125 (0.1265) loss: 0.8131 (0.8123) time: 0.1478 data: 0.0660 max mem: 9390 +Train: [75] [6200/6250] eta: 0:00:08 lr: 0.000019 grad: 0.1285 (0.1266) loss: 0.8119 (0.8123) time: 0.1951 data: 0.0953 max mem: 9390 +Train: [75] [6249/6250] eta: 0:00:00 lr: 0.000019 grad: 0.1235 (0.1265) loss: 0.8117 (0.8123) time: 0.1510 data: 0.0620 max mem: 9390 +Train: [75] Total time: 0:18:32 (0.1780 s / it) +Averaged stats: lr: 0.000019 grad: 0.1235 (0.1265) loss: 0.8117 (0.8123) +Eval (hcp-train-subset): [75] [ 0/62] eta: 0:03:26 loss: 0.8362 (0.8362) time: 3.3251 data: 3.2013 max mem: 9390 +Eval (hcp-train-subset): [75] [61/62] eta: 0:00:00 loss: 0.8256 (0.8273) time: 0.1266 data: 0.1011 max mem: 9390 +Eval (hcp-train-subset): [75] Total time: 0:00:14 (0.2297 s / it) +Averaged stats (hcp-train-subset): loss: 0.8256 (0.8273) +Eval (hcp-val): [75] [ 0/62] eta: 0:04:10 loss: 0.8294 (0.8294) time: 4.0358 data: 3.9690 max mem: 9390 +Eval (hcp-val): [75] [61/62] eta: 0:00:00 loss: 0.8293 (0.8313) time: 0.1278 data: 0.1028 max mem: 9390 +Eval (hcp-val): [75] Total time: 0:00:13 (0.2168 s / it) +Averaged stats (hcp-val): loss: 0.8293 (0.8313) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +Train: [76] [ 0/6250] eta: 9:17:20 lr: 0.000019 grad: 0.0795 (0.0795) loss: 0.8583 (0.8583) time: 5.3505 data: 5.1018 max mem: 9390 +Train: [76] [ 100/6250] eta: 0:23:56 lr: 0.000019 grad: 0.1272 (0.1446) loss: 0.8143 (0.8227) time: 0.1886 data: 0.0807 max mem: 9390 +Train: [76] [ 200/6250] eta: 0:20:28 lr: 0.000019 grad: 0.1121 (0.1364) loss: 0.8174 (0.8189) time: 0.1717 data: 0.0715 max mem: 9390 +Train: [76] [ 300/6250] eta: 0:18:58 lr: 0.000019 grad: 0.1194 (0.1336) loss: 0.8112 (0.8177) time: 0.1645 data: 0.0657 max mem: 9390 +Train: [76] [ 400/6250] eta: 0:18:14 lr: 0.000019 grad: 0.1207 (0.1318) loss: 0.8121 (0.8159) time: 0.1546 data: 0.0484 max mem: 9390 +Train: [76] [ 500/6250] eta: 0:17:31 lr: 0.000019 grad: 0.1241 (0.1300) loss: 0.8072 (0.8146) time: 0.1699 data: 0.0456 max mem: 9390 +Train: [76] [ 600/6250] eta: 0:17:05 lr: 0.000019 grad: 0.1173 (0.1295) loss: 0.8138 (0.8140) time: 0.1534 data: 0.0631 max mem: 9390 +Train: [76] [ 700/6250] eta: 0:16:50 lr: 0.000019 grad: 0.1238 (0.1294) loss: 0.8118 (0.8132) time: 0.1607 data: 0.0662 max mem: 9390 +Train: [76] [ 800/6250] eta: 0:16:28 lr: 0.000018 grad: 0.1268 (0.1293) loss: 0.8096 (0.8126) time: 0.1649 data: 0.0788 max mem: 9390 +Train: [76] [ 900/6250] eta: 0:16:03 lr: 0.000018 grad: 0.1223 (0.1291) loss: 0.8140 (0.8122) time: 0.1798 data: 0.0853 max mem: 9390 +Train: [76] [1000/6250] eta: 0:15:35 lr: 0.000018 grad: 0.1238 (0.1291) loss: 0.8145 (0.8121) time: 0.1272 data: 0.0376 max mem: 9390 +Train: [76] [1100/6250] eta: 0:15:14 lr: 0.000018 grad: 0.1227 (0.1288) loss: 0.8156 (0.8118) time: 0.1839 data: 0.1005 max mem: 9390 +Train: [76] [1200/6250] eta: 0:14:53 lr: 0.000018 grad: 0.1238 (0.1287) loss: 0.8108 (0.8114) time: 0.1956 data: 0.1097 max mem: 9390 +Train: [76] [1300/6250] eta: 0:14:32 lr: 0.000018 grad: 0.1248 (0.1287) loss: 0.8065 (0.8111) time: 0.1758 data: 0.0943 max mem: 9390 +Train: [76] [1400/6250] eta: 0:14:11 lr: 0.000018 grad: 0.1167 (0.1283) loss: 0.8165 (0.8112) time: 0.1470 data: 0.0626 max mem: 9390 +Train: [76] [1500/6250] eta: 0:13:48 lr: 0.000018 grad: 0.1240 (0.1280) loss: 0.8066 (0.8112) time: 0.1561 data: 0.0759 max mem: 9390 +Train: [76] [1600/6250] eta: 0:13:29 lr: 0.000018 grad: 0.1198 (0.1277) loss: 0.8063 (0.8112) time: 0.1847 data: 0.0958 max mem: 9390 +Train: [76] [1700/6250] eta: 0:13:08 lr: 0.000018 grad: 0.1212 (0.1276) loss: 0.8100 (0.8112) time: 0.1694 data: 0.0805 max mem: 9390 +Train: [76] [1800/6250] eta: 0:12:54 lr: 0.000018 grad: 0.1170 (0.1274) loss: 0.8116 (0.8112) time: 0.1808 data: 0.0899 max mem: 9390 +Train: [76] [1900/6250] eta: 0:12:36 lr: 0.000018 grad: 0.1234 (0.1273) loss: 0.8140 (0.8112) time: 0.1651 data: 0.0642 max mem: 9390 +Train: [76] [2000/6250] eta: 0:12:17 lr: 0.000018 grad: 0.1269 (0.1273) loss: 0.8083 (0.8111) time: 0.1760 data: 0.0778 max mem: 9390 +Train: [76] [2100/6250] eta: 0:12:01 lr: 0.000018 grad: 0.1225 (0.1272) loss: 0.8108 (0.8112) time: 0.1503 data: 0.0257 max mem: 9390 +Train: [76] [2200/6250] eta: 0:11:46 lr: 0.000018 grad: 0.1200 (0.1271) loss: 0.8121 (0.8112) time: 0.1809 data: 0.0875 max mem: 9390 +Train: [76] [2300/6250] eta: 0:11:33 lr: 0.000018 grad: 0.1229 (0.1269) loss: 0.8130 (0.8113) time: 0.1588 data: 0.0503 max mem: 9390 +Train: [76] [2400/6250] eta: 0:11:14 lr: 0.000018 grad: 0.1264 (0.1269) loss: 0.8078 (0.8113) time: 0.1635 data: 0.0773 max mem: 9390 +Train: [76] [2500/6250] eta: 0:10:57 lr: 0.000018 grad: 0.1323 (0.1270) loss: 0.8074 (0.8112) time: 0.1191 data: 0.0003 max mem: 9390 +Train: [76] [2600/6250] eta: 0:10:39 lr: 0.000018 grad: 0.1220 (0.1270) loss: 0.8077 (0.8112) time: 0.1924 data: 0.0939 max mem: 9390 +Train: [76] [2700/6250] eta: 0:10:20 lr: 0.000018 grad: 0.1249 (0.1271) loss: 0.8173 (0.8111) time: 0.1609 data: 0.0711 max mem: 9390 +Train: [76] [2800/6250] eta: 0:10:03 lr: 0.000018 grad: 0.1313 (0.1273) loss: 0.8039 (0.8110) time: 0.1396 data: 0.0530 max mem: 9390 +Train: [76] [2900/6250] eta: 0:09:44 lr: 0.000018 grad: 0.1227 (0.1273) loss: 0.8079 (0.8109) time: 0.1705 data: 0.0836 max mem: 9390 +Train: [76] [3000/6250] eta: 0:09:28 lr: 0.000018 grad: 0.1230 (0.1274) loss: 0.8051 (0.8108) time: 0.2511 data: 0.1555 max mem: 9390 +Train: [76] [3100/6250] eta: 0:09:09 lr: 0.000018 grad: 0.1288 (0.1274) loss: 0.8095 (0.8107) time: 0.1198 data: 0.0230 max mem: 9390 +Train: [76] [3200/6250] eta: 0:08:52 lr: 0.000018 grad: 0.1258 (0.1276) loss: 0.8053 (0.8106) time: 0.1935 data: 0.1012 max mem: 9390 +Train: [76] [3300/6250] eta: 0:08:37 lr: 0.000018 grad: 0.1311 (0.1277) loss: 0.8073 (0.8105) time: 0.1143 data: 0.0002 max mem: 9390 +Train: [76] [3400/6250] eta: 0:08:18 lr: 0.000018 grad: 0.1234 (0.1277) loss: 0.8131 (0.8105) time: 0.1693 data: 0.0748 max mem: 9390 +Train: [76] [3500/6250] eta: 0:08:01 lr: 0.000018 grad: 0.1249 (0.1276) loss: 0.8081 (0.8105) time: 0.1469 data: 0.0580 max mem: 9390 +Train: [76] [3600/6250] eta: 0:07:44 lr: 0.000018 grad: 0.1161 (0.1275) loss: 0.8118 (0.8105) time: 0.1609 data: 0.0738 max mem: 9390 +Train: [76] [3700/6250] eta: 0:07:26 lr: 0.000018 grad: 0.1278 (0.1275) loss: 0.8060 (0.8105) time: 0.1600 data: 0.0679 max mem: 9390 +Train: [76] [3800/6250] eta: 0:07:08 lr: 0.000018 grad: 0.1308 (0.1275) loss: 0.8084 (0.8104) time: 0.1740 data: 0.0890 max mem: 9390 +Train: [76] [3900/6250] eta: 0:06:51 lr: 0.000018 grad: 0.1243 (0.1276) loss: 0.8088 (0.8103) time: 0.1744 data: 0.0931 max mem: 9390 +Train: [76] [4000/6250] eta: 0:06:33 lr: 0.000018 grad: 0.1212 (0.1276) loss: 0.8025 (0.8102) time: 0.1694 data: 0.0809 max mem: 9390 +Train: [76] [4100/6250] eta: 0:06:16 lr: 0.000018 grad: 0.1282 (0.1277) loss: 0.8023 (0.8100) time: 0.1452 data: 0.0483 max mem: 9390 +Train: [76] [4200/6250] eta: 0:05:59 lr: 0.000018 grad: 0.1245 (0.1278) loss: 0.8043 (0.8100) time: 0.1525 data: 0.0602 max mem: 9390 +Train: [76] [4300/6250] eta: 0:05:41 lr: 0.000018 grad: 0.1312 (0.1278) loss: 0.8049 (0.8099) time: 0.1839 data: 0.0966 max mem: 9390 +Train: [76] [4400/6250] eta: 0:05:24 lr: 0.000018 grad: 0.1206 (0.1278) loss: 0.8100 (0.8098) time: 0.1672 data: 0.0796 max mem: 9390 +Train: [76] [4500/6250] eta: 0:05:06 lr: 0.000018 grad: 0.1308 (0.1279) loss: 0.8037 (0.8098) time: 0.1447 data: 0.0574 max mem: 9390 +Train: [76] [4600/6250] eta: 0:04:50 lr: 0.000018 grad: 0.1222 (0.1280) loss: 0.8094 (0.8097) time: 0.2701 data: 0.1802 max mem: 9390 +Train: [76] [4700/6250] eta: 0:04:31 lr: 0.000018 grad: 0.1311 (0.1280) loss: 0.8058 (0.8098) time: 0.1682 data: 0.0772 max mem: 9390 +Train: [76] [4800/6250] eta: 0:04:15 lr: 0.000018 grad: 0.1228 (0.1280) loss: 0.8081 (0.8098) time: 0.3414 data: 0.2041 max mem: 9390 +Train: [76] [4900/6250] eta: 0:03:57 lr: 0.000018 grad: 0.1239 (0.1280) loss: 0.8102 (0.8098) time: 0.1365 data: 0.0143 max mem: 9390 +Train: [76] [5000/6250] eta: 0:03:39 lr: 0.000018 grad: 0.1204 (0.1281) loss: 0.8121 (0.8098) time: 0.1793 data: 0.0850 max mem: 9390 +Train: [76] [5100/6250] eta: 0:03:22 lr: 0.000017 grad: 0.1215 (0.1280) loss: 0.8187 (0.8098) time: 0.2176 data: 0.1178 max mem: 9390 +Train: [76] [5200/6250] eta: 0:03:04 lr: 0.000017 grad: 0.1191 (0.1280) loss: 0.8150 (0.8098) time: 0.2521 data: 0.1597 max mem: 9390 +Train: [76] [5300/6250] eta: 0:02:47 lr: 0.000017 grad: 0.1320 (0.1280) loss: 0.8119 (0.8099) time: 0.2051 data: 0.0980 max mem: 9390 +Train: [76] [5400/6250] eta: 0:02:30 lr: 0.000017 grad: 0.1254 (0.1280) loss: 0.8144 (0.8099) time: 0.1123 data: 0.0156 max mem: 9390 +Train: [76] [5500/6250] eta: 0:02:13 lr: 0.000017 grad: 0.1191 (0.1281) loss: 0.8148 (0.8100) time: 0.4151 data: 0.3066 max mem: 9390 +Train: [76] [5600/6250] eta: 0:01:55 lr: 0.000017 grad: 0.1339 (0.1281) loss: 0.8124 (0.8100) time: 0.1858 data: 0.0717 max mem: 9390 +Train: [76] [5700/6250] eta: 0:01:37 lr: 0.000017 grad: 0.1325 (0.1281) loss: 0.8073 (0.8100) time: 0.1931 data: 0.1007 max mem: 9390 +Train: [76] [5800/6250] eta: 0:01:19 lr: 0.000017 grad: 0.1260 (0.1281) loss: 0.8137 (0.8100) time: 0.1642 data: 0.0786 max mem: 9390 +Train: [76] [5900/6250] eta: 0:01:02 lr: 0.000017 grad: 0.1175 (0.1281) loss: 0.8090 (0.8101) time: 0.1890 data: 0.1025 max mem: 9390 +Train: [76] [6000/6250] eta: 0:00:44 lr: 0.000017 grad: 0.1287 (0.1281) loss: 0.8124 (0.8102) time: 0.1718 data: 0.0894 max mem: 9390 +Train: [76] [6100/6250] eta: 0:00:26 lr: 0.000017 grad: 0.1326 (0.1281) loss: 0.8075 (0.8102) time: 0.1872 data: 0.1135 max mem: 9390 +Train: [76] [6200/6250] eta: 0:00:08 lr: 0.000017 grad: 0.1240 (0.1280) loss: 0.8150 (0.8103) time: 0.2015 data: 0.1132 max mem: 9390 +Train: [76] [6249/6250] eta: 0:00:00 lr: 0.000017 grad: 0.1205 (0.1280) loss: 0.8180 (0.8103) time: 0.1561 data: 0.0733 max mem: 9390 +Train: [76] Total time: 0:18:41 (0.1795 s / it) +Averaged stats: lr: 0.000017 grad: 0.1205 (0.1280) loss: 0.8180 (0.8103) +Eval (hcp-train-subset): [76] [ 0/62] eta: 0:04:48 loss: 0.8339 (0.8339) time: 4.6587 data: 4.5979 max mem: 9390 +Eval (hcp-train-subset): [76] [61/62] eta: 0:00:00 loss: 0.8236 (0.8267) time: 0.1514 data: 0.1257 max mem: 9390 +Eval (hcp-train-subset): [76] Total time: 0:00:15 (0.2419 s / it) +Averaged stats (hcp-train-subset): loss: 0.8236 (0.8267) +Eval (hcp-val): [76] [ 0/62] eta: 0:04:59 loss: 0.8247 (0.8247) time: 4.8277 data: 4.7786 max mem: 9390 +Eval (hcp-val): [76] [61/62] eta: 0:00:00 loss: 0.8280 (0.8306) time: 0.1491 data: 0.1232 max mem: 9390 +Eval (hcp-val): [76] Total time: 0:00:14 (0.2390 s / it) +Averaged stats (hcp-val): loss: 0.8280 (0.8306) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +Train: [77] [ 0/6250] eta: 8:11:25 lr: 0.000017 grad: 0.0770 (0.0770) loss: 0.8829 (0.8829) time: 4.7177 data: 4.3263 max mem: 9390 +Train: [77] [ 100/6250] eta: 0:24:58 lr: 0.000017 grad: 0.1242 (0.1633) loss: 0.8150 (0.8262) time: 0.1936 data: 0.0791 max mem: 9390 +Train: [77] [ 200/6250] eta: 0:21:49 lr: 0.000017 grad: 0.1205 (0.1447) loss: 0.8191 (0.8251) time: 0.1975 data: 0.0954 max mem: 9390 +Train: [77] [ 300/6250] eta: 0:20:31 lr: 0.000017 grad: 0.1229 (0.1385) loss: 0.8247 (0.8240) time: 0.2018 data: 0.1021 max mem: 9390 +Train: [77] [ 400/6250] eta: 0:19:40 lr: 0.000017 grad: 0.1110 (0.1345) loss: 0.8218 (0.8232) time: 0.1987 data: 0.0998 max mem: 9390 +Train: [77] [ 500/6250] eta: 0:18:56 lr: 0.000017 grad: 0.1075 (0.1317) loss: 0.8196 (0.8226) time: 0.1591 data: 0.0567 max mem: 9390 +Train: [77] [ 600/6250] eta: 0:18:24 lr: 0.000017 grad: 0.1174 (0.1298) loss: 0.8189 (0.8220) time: 0.1880 data: 0.0962 max mem: 9390 +Train: [77] [ 700/6250] eta: 0:18:03 lr: 0.000017 grad: 0.1125 (0.1286) loss: 0.8234 (0.8213) time: 0.1973 data: 0.1064 max mem: 9390 +Train: [77] [ 800/6250] eta: 0:17:36 lr: 0.000017 grad: 0.1150 (0.1279) loss: 0.8118 (0.8202) time: 0.1704 data: 0.0832 max mem: 9390 +Train: [77] [ 900/6250] eta: 0:17:18 lr: 0.000017 grad: 0.1218 (0.1275) loss: 0.8151 (0.8193) time: 0.1971 data: 0.1153 max mem: 9390 +Train: [77] [1000/6250] eta: 0:16:56 lr: 0.000017 grad: 0.1231 (0.1277) loss: 0.7992 (0.8183) time: 0.1736 data: 0.0849 max mem: 9390 +Train: [77] [1100/6250] eta: 0:16:37 lr: 0.000017 grad: 0.1117 (0.1275) loss: 0.8048 (0.8176) time: 0.1974 data: 0.1177 max mem: 9390 +Train: [77] [1200/6250] eta: 0:16:12 lr: 0.000017 grad: 0.1178 (0.1269) loss: 0.8154 (0.8174) time: 0.1217 data: 0.0248 max mem: 9390 +Train: [77] [1300/6250] eta: 0:15:44 lr: 0.000017 grad: 0.1221 (0.1264) loss: 0.8149 (0.8171) time: 0.1695 data: 0.0800 max mem: 9390 +Train: [77] [1400/6250] eta: 0:15:21 lr: 0.000017 grad: 0.1217 (0.1260) loss: 0.8046 (0.8169) time: 0.1724 data: 0.0833 max mem: 9390 +Train: [77] [1500/6250] eta: 0:14:52 lr: 0.000017 grad: 0.1203 (0.1259) loss: 0.8137 (0.8165) time: 0.1245 data: 0.0320 max mem: 9390 +Train: [77] [1600/6250] eta: 0:14:30 lr: 0.000017 grad: 0.1132 (0.1253) loss: 0.8214 (0.8164) time: 0.1571 data: 0.0583 max mem: 9390 +Train: [77] [1700/6250] eta: 0:14:09 lr: 0.000017 grad: 0.1159 (0.1251) loss: 0.8094 (0.8161) time: 0.1823 data: 0.0829 max mem: 9390 +Train: [77] [1800/6250] eta: 0:13:53 lr: 0.000017 grad: 0.1272 (0.1250) loss: 0.8101 (0.8158) time: 0.1027 data: 0.0004 max mem: 9390 +Train: [77] [1900/6250] eta: 0:13:30 lr: 0.000017 grad: 0.1264 (0.1250) loss: 0.8083 (0.8158) time: 0.2006 data: 0.1125 max mem: 9390 +Train: [77] [2000/6250] eta: 0:13:09 lr: 0.000017 grad: 0.1184 (0.1249) loss: 0.8165 (0.8156) time: 0.2127 data: 0.1358 max mem: 9390 +Train: [77] [2100/6250] eta: 0:12:50 lr: 0.000017 grad: 0.1171 (0.1248) loss: 0.8197 (0.8155) time: 0.1708 data: 0.0791 max mem: 9390 +Train: [77] [2200/6250] eta: 0:12:28 lr: 0.000017 grad: 0.1196 (0.1248) loss: 0.8095 (0.8154) time: 0.1669 data: 0.0742 max mem: 9390 +Train: [77] [2300/6250] eta: 0:12:07 lr: 0.000017 grad: 0.1271 (0.1249) loss: 0.8107 (0.8153) time: 0.1551 data: 0.0706 max mem: 9390 +Train: [77] [2400/6250] eta: 0:11:47 lr: 0.000017 grad: 0.1171 (0.1250) loss: 0.8135 (0.8151) time: 0.1712 data: 0.0895 max mem: 9390 +Train: [77] [2500/6250] eta: 0:11:26 lr: 0.000017 grad: 0.1218 (0.1249) loss: 0.8164 (0.8151) time: 0.1627 data: 0.0682 max mem: 9390 +Train: [77] [2600/6250] eta: 0:11:06 lr: 0.000017 grad: 0.1150 (0.1247) loss: 0.8158 (0.8151) time: 0.1622 data: 0.0738 max mem: 9390 +Train: [77] [2700/6250] eta: 0:10:45 lr: 0.000017 grad: 0.1294 (0.1248) loss: 0.8106 (0.8149) time: 0.1599 data: 0.0653 max mem: 9390 +Train: [77] [2800/6250] eta: 0:10:26 lr: 0.000017 grad: 0.1224 (0.1249) loss: 0.8140 (0.8149) time: 0.1897 data: 0.0965 max mem: 9390 +Train: [77] [2900/6250] eta: 0:10:04 lr: 0.000017 grad: 0.1220 (0.1249) loss: 0.8123 (0.8148) time: 0.1601 data: 0.0700 max mem: 9390 +Train: [77] [3000/6250] eta: 0:09:44 lr: 0.000017 grad: 0.1174 (0.1248) loss: 0.8121 (0.8148) time: 0.1585 data: 0.0653 max mem: 9390 +Train: [77] [3100/6250] eta: 0:09:24 lr: 0.000017 grad: 0.1183 (0.1247) loss: 0.8130 (0.8147) time: 0.1653 data: 0.0711 max mem: 9390 +Train: [77] [3200/6250] eta: 0:09:05 lr: 0.000017 grad: 0.1217 (0.1248) loss: 0.8195 (0.8147) time: 0.1240 data: 0.0361 max mem: 9390 +Train: [77] [3300/6250] eta: 0:08:46 lr: 0.000016 grad: 0.1255 (0.1248) loss: 0.8096 (0.8146) time: 0.1469 data: 0.0586 max mem: 9390 +Train: [77] [3400/6250] eta: 0:08:30 lr: 0.000016 grad: 0.1293 (0.1249) loss: 0.8122 (0.8145) time: 0.2951 data: 0.2018 max mem: 9390 +Train: [77] [3500/6250] eta: 0:08:10 lr: 0.000016 grad: 0.1199 (0.1248) loss: 0.8205 (0.8146) time: 0.1703 data: 0.0760 max mem: 9390 +Train: [77] [3600/6250] eta: 0:07:53 lr: 0.000016 grad: 0.1215 (0.1249) loss: 0.8123 (0.8145) time: 0.1097 data: 0.0002 max mem: 9390 +Train: [77] [3700/6250] eta: 0:07:36 lr: 0.000016 grad: 0.1175 (0.1249) loss: 0.8222 (0.8145) time: 0.1937 data: 0.1039 max mem: 9390 +Train: [77] [3800/6250] eta: 0:07:18 lr: 0.000016 grad: 0.1259 (0.1249) loss: 0.8110 (0.8145) time: 0.1679 data: 0.0816 max mem: 9390 +Train: [77] [3900/6250] eta: 0:07:00 lr: 0.000016 grad: 0.1235 (0.1249) loss: 0.8121 (0.8145) time: 0.1876 data: 0.0869 max mem: 9390 +Train: [77] [4000/6250] eta: 0:06:42 lr: 0.000016 grad: 0.1208 (0.1250) loss: 0.8137 (0.8146) time: 0.2170 data: 0.1319 max mem: 9390 +Train: [77] [4100/6250] eta: 0:06:24 lr: 0.000016 grad: 0.1243 (0.1249) loss: 0.8143 (0.8146) time: 0.1161 data: 0.0102 max mem: 9390 +Train: [77] [4200/6250] eta: 0:06:06 lr: 0.000016 grad: 0.1266 (0.1250) loss: 0.8182 (0.8146) time: 0.1845 data: 0.0870 max mem: 9390 +Train: [77] [4300/6250] eta: 0:05:48 lr: 0.000016 grad: 0.1210 (0.1249) loss: 0.8188 (0.8147) time: 0.1787 data: 0.0783 max mem: 9390 +Train: [77] [4400/6250] eta: 0:05:30 lr: 0.000016 grad: 0.1236 (0.1249) loss: 0.8160 (0.8147) time: 0.1749 data: 0.0863 max mem: 9390 +Train: [77] [4500/6250] eta: 0:05:12 lr: 0.000016 grad: 0.1240 (0.1249) loss: 0.8089 (0.8147) time: 0.1913 data: 0.1043 max mem: 9390 +Train: [77] [4600/6250] eta: 0:04:54 lr: 0.000016 grad: 0.1184 (0.1249) loss: 0.8134 (0.8148) time: 0.1773 data: 0.0845 max mem: 9390 +Train: [77] [4700/6250] eta: 0:04:36 lr: 0.000016 grad: 0.1170 (0.1249) loss: 0.8132 (0.8148) time: 0.1444 data: 0.0597 max mem: 9390 +Train: [77] [4800/6250] eta: 0:04:20 lr: 0.000016 grad: 0.1142 (0.1249) loss: 0.8188 (0.8149) time: 0.1677 data: 0.0416 max mem: 9390 +Train: [77] [4900/6250] eta: 0:04:01 lr: 0.000016 grad: 0.1271 (0.1249) loss: 0.8156 (0.8149) time: 0.1707 data: 0.0828 max mem: 9390 +Train: [77] [5000/6250] eta: 0:03:44 lr: 0.000016 grad: 0.1186 (0.1248) loss: 0.8184 (0.8149) time: 0.0941 data: 0.0002 max mem: 9390 +Train: [77] [5100/6250] eta: 0:03:25 lr: 0.000016 grad: 0.1060 (0.1247) loss: 0.8239 (0.8150) time: 0.1465 data: 0.0621 max mem: 9390 +Train: [77] [5200/6250] eta: 0:03:07 lr: 0.000016 grad: 0.1212 (0.1247) loss: 0.8180 (0.8150) time: 0.1520 data: 0.0641 max mem: 9390 +Train: [77] [5300/6250] eta: 0:02:49 lr: 0.000016 grad: 0.1211 (0.1247) loss: 0.8197 (0.8150) time: 0.1470 data: 0.0566 max mem: 9390 +Train: [77] [5400/6250] eta: 0:02:31 lr: 0.000016 grad: 0.1221 (0.1247) loss: 0.8205 (0.8151) time: 0.1524 data: 0.0575 max mem: 9390 +Train: [77] [5500/6250] eta: 0:02:13 lr: 0.000016 grad: 0.1217 (0.1247) loss: 0.8141 (0.8151) time: 0.1939 data: 0.1032 max mem: 9390 +Train: [77] [5600/6250] eta: 0:01:55 lr: 0.000016 grad: 0.1254 (0.1247) loss: 0.8118 (0.8151) time: 0.1903 data: 0.1020 max mem: 9390 +Train: [77] [5700/6250] eta: 0:01:38 lr: 0.000016 grad: 0.1172 (0.1247) loss: 0.8146 (0.8151) time: 0.1946 data: 0.1124 max mem: 9390 +Train: [77] [5800/6250] eta: 0:01:20 lr: 0.000016 grad: 0.1224 (0.1247) loss: 0.8125 (0.8151) time: 0.2705 data: 0.1825 max mem: 9390 +Train: [77] [5900/6250] eta: 0:01:02 lr: 0.000016 grad: 0.1192 (0.1246) loss: 0.8098 (0.8151) time: 0.1624 data: 0.0808 max mem: 9390 +Train: [77] [6000/6250] eta: 0:00:44 lr: 0.000016 grad: 0.1229 (0.1246) loss: 0.8158 (0.8151) time: 0.1599 data: 0.0841 max mem: 9390 +Train: [77] [6100/6250] eta: 0:00:26 lr: 0.000016 grad: 0.1155 (0.1246) loss: 0.8192 (0.8152) time: 0.1843 data: 0.0926 max mem: 9390 +Train: [77] [6200/6250] eta: 0:00:08 lr: 0.000016 grad: 0.1306 (0.1246) loss: 0.8139 (0.8151) time: 0.1785 data: 0.0898 max mem: 9390 +Train: [77] [6249/6250] eta: 0:00:00 lr: 0.000016 grad: 0.1250 (0.1246) loss: 0.8104 (0.8151) time: 0.1558 data: 0.0754 max mem: 9390 +Train: [77] Total time: 0:18:43 (0.1797 s / it) +Averaged stats: lr: 0.000016 grad: 0.1250 (0.1246) loss: 0.8104 (0.8151) +Eval (hcp-train-subset): [77] [ 0/62] eta: 0:04:46 loss: 0.8329 (0.8329) time: 4.6195 data: 4.5877 max mem: 9390 +Eval (hcp-train-subset): [77] [61/62] eta: 0:00:00 loss: 0.8226 (0.8263) time: 0.1515 data: 0.1258 max mem: 9390 +Eval (hcp-train-subset): [77] Total time: 0:00:14 (0.2309 s / it) +Averaged stats (hcp-train-subset): loss: 0.8226 (0.8263) +Eval (hcp-val): [77] [ 0/62] eta: 0:05:12 loss: 0.8295 (0.8295) time: 5.0350 data: 5.0005 max mem: 9390 +Eval (hcp-val): [77] [61/62] eta: 0:00:00 loss: 0.8304 (0.8311) time: 0.1186 data: 0.0932 max mem: 9390 +Eval (hcp-val): [77] Total time: 0:00:14 (0.2275 s / it) +Averaged stats (hcp-val): loss: 0.8304 (0.8311) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +Train: [78] [ 0/6250] eta: 7:50:16 lr: 0.000016 grad: 0.0894 (0.0894) loss: 0.8586 (0.8586) time: 4.5146 data: 4.3102 max mem: 9390 +Train: [78] [ 100/6250] eta: 0:23:57 lr: 0.000016 grad: 0.1451 (0.1332) loss: 0.8297 (0.8343) time: 0.2086 data: 0.0946 max mem: 9390 +Train: [78] [ 200/6250] eta: 0:20:55 lr: 0.000016 grad: 0.1095 (0.1277) loss: 0.8327 (0.8325) time: 0.1985 data: 0.0915 max mem: 9390 +Train: [78] [ 300/6250] eta: 0:20:06 lr: 0.000016 grad: 0.1140 (0.1248) loss: 0.8234 (0.8320) time: 0.2173 data: 0.1157 max mem: 9390 +Train: [78] [ 400/6250] eta: 0:19:20 lr: 0.000016 grad: 0.1150 (0.1234) loss: 0.8198 (0.8296) time: 0.1869 data: 0.0973 max mem: 9390 +Train: [78] [ 500/6250] eta: 0:18:34 lr: 0.000016 grad: 0.1159 (0.1230) loss: 0.8227 (0.8283) time: 0.1560 data: 0.0667 max mem: 9390 +Train: [78] [ 600/6250] eta: 0:18:11 lr: 0.000016 grad: 0.1226 (0.1233) loss: 0.8200 (0.8268) time: 0.2074 data: 0.1138 max mem: 9390 +Train: [78] [ 700/6250] eta: 0:17:52 lr: 0.000016 grad: 0.1181 (0.1239) loss: 0.8186 (0.8252) time: 0.1854 data: 0.0984 max mem: 9390 +Train: [78] [ 800/6250] eta: 0:17:49 lr: 0.000016 grad: 0.1282 (0.1240) loss: 0.8088 (0.8242) time: 0.1291 data: 0.0501 max mem: 9390 +Train: [78] [ 900/6250] eta: 0:17:36 lr: 0.000016 grad: 0.1255 (0.1244) loss: 0.8179 (0.8234) time: 0.1827 data: 0.1030 max mem: 9390 +Train: [78] [1000/6250] eta: 0:17:13 lr: 0.000016 grad: 0.1193 (0.1246) loss: 0.8098 (0.8226) time: 0.2312 data: 0.1445 max mem: 9390 +Train: [78] [1100/6250] eta: 0:16:36 lr: 0.000016 grad: 0.1168 (0.1245) loss: 0.8167 (0.8219) time: 0.1434 data: 0.0467 max mem: 9390 +Train: [78] [1200/6250] eta: 0:16:18 lr: 0.000016 grad: 0.1242 (0.1243) loss: 0.8135 (0.8214) time: 0.2897 data: 0.2029 max mem: 9390 +Train: [78] [1300/6250] eta: 0:15:50 lr: 0.000016 grad: 0.1230 (0.1243) loss: 0.8117 (0.8208) time: 0.1653 data: 0.0618 max mem: 9390 +Train: [78] [1400/6250] eta: 0:15:26 lr: 0.000016 grad: 0.1276 (0.1244) loss: 0.8155 (0.8203) time: 0.1040 data: 0.0004 max mem: 9390 +Train: [78] [1500/6250] eta: 0:15:05 lr: 0.000015 grad: 0.1205 (0.1247) loss: 0.8141 (0.8197) time: 0.2049 data: 0.1103 max mem: 9390 +Train: [78] [1600/6250] eta: 0:14:40 lr: 0.000015 grad: 0.1170 (0.1248) loss: 0.8153 (0.8193) time: 0.1497 data: 0.0542 max mem: 9390 +Train: [78] [1700/6250] eta: 0:14:21 lr: 0.000015 grad: 0.1243 (0.1248) loss: 0.8105 (0.8189) time: 0.2051 data: 0.1175 max mem: 9390 +Train: [78] [1800/6250] eta: 0:14:06 lr: 0.000015 grad: 0.1238 (0.1248) loss: 0.8097 (0.8186) time: 0.2141 data: 0.1212 max mem: 9390 +Train: [78] [1900/6250] eta: 0:13:43 lr: 0.000015 grad: 0.1275 (0.1250) loss: 0.8090 (0.8182) time: 0.1902 data: 0.0702 max mem: 9390 +Train: [78] [2000/6250] eta: 0:13:38 lr: 0.000015 grad: 0.1275 (0.1254) loss: 0.8088 (0.8177) time: 0.1732 data: 0.0551 max mem: 9390 +Train: [78] [2100/6250] eta: 0:13:13 lr: 0.000015 grad: 0.1325 (0.1256) loss: 0.8095 (0.8175) time: 0.1035 data: 0.0101 max mem: 9390 +Train: [78] [2200/6250] eta: 0:12:49 lr: 0.000015 grad: 0.1440 (0.1259) loss: 0.8146 (0.8171) time: 0.1783 data: 0.0960 max mem: 9390 +Train: [78] [2300/6250] eta: 0:12:27 lr: 0.000015 grad: 0.1261 (0.1261) loss: 0.8067 (0.8168) time: 0.1494 data: 0.0686 max mem: 9390 +Train: [78] [2400/6250] eta: 0:12:06 lr: 0.000015 grad: 0.1307 (0.1263) loss: 0.8146 (0.8165) time: 0.1538 data: 0.0614 max mem: 9390 +Train: [78] [2500/6250] eta: 0:11:45 lr: 0.000015 grad: 0.1299 (0.1265) loss: 0.8114 (0.8163) time: 0.1695 data: 0.0648 max mem: 9390 +Train: [78] [2600/6250] eta: 0:11:27 lr: 0.000015 grad: 0.1323 (0.1267) loss: 0.8039 (0.8160) time: 0.1918 data: 0.0956 max mem: 9390 +Train: [78] [2700/6250] eta: 0:11:08 lr: 0.000015 grad: 0.1248 (0.1269) loss: 0.8121 (0.8158) time: 0.1726 data: 0.0721 max mem: 9390 +Train: [78] [2800/6250] eta: 0:10:54 lr: 0.000015 grad: 0.1230 (0.1270) loss: 0.8088 (0.8156) time: 0.1007 data: 0.0002 max mem: 9390 +Train: [78] [2900/6250] eta: 0:10:31 lr: 0.000015 grad: 0.1329 (0.1271) loss: 0.8069 (0.8154) time: 0.1320 data: 0.0358 max mem: 9390 +Train: [78] [3000/6250] eta: 0:10:11 lr: 0.000015 grad: 0.1293 (0.1272) loss: 0.8064 (0.8153) time: 0.2000 data: 0.1149 max mem: 9390 +Train: [78] [3100/6250] eta: 0:09:56 lr: 0.000015 grad: 0.1201 (0.1273) loss: 0.8189 (0.8152) time: 0.1271 data: 0.0003 max mem: 9390 +Train: [78] [3200/6250] eta: 0:09:39 lr: 0.000015 grad: 0.1261 (0.1273) loss: 0.8137 (0.8151) time: 0.3793 data: 0.2927 max mem: 9390 +Train: [78] [3300/6250] eta: 0:09:17 lr: 0.000015 grad: 0.1221 (0.1273) loss: 0.8109 (0.8150) time: 0.1965 data: 0.1053 max mem: 9390 +Train: [78] [3400/6250] eta: 0:08:56 lr: 0.000015 grad: 0.1224 (0.1273) loss: 0.8135 (0.8149) time: 0.1669 data: 0.0773 max mem: 9390 +Train: [78] [3500/6250] eta: 0:08:37 lr: 0.000015 grad: 0.1150 (0.1273) loss: 0.8139 (0.8149) time: 0.1822 data: 0.0751 max mem: 9390 +Train: [78] [3600/6250] eta: 0:08:17 lr: 0.000015 grad: 0.1196 (0.1272) loss: 0.8139 (0.8149) time: 0.1920 data: 0.0782 max mem: 9390 +Train: [78] [3700/6250] eta: 0:07:59 lr: 0.000015 grad: 0.1321 (0.1273) loss: 0.8106 (0.8148) time: 0.1483 data: 0.0561 max mem: 9390 +Train: [78] [3800/6250] eta: 0:07:40 lr: 0.000015 grad: 0.1280 (0.1272) loss: 0.8108 (0.8147) time: 0.1697 data: 0.0754 max mem: 9390 +Train: [78] [3900/6250] eta: 0:07:20 lr: 0.000015 grad: 0.1215 (0.1272) loss: 0.8088 (0.8146) time: 0.1296 data: 0.0409 max mem: 9390 +Train: [78] [4000/6250] eta: 0:07:05 lr: 0.000015 grad: 0.1188 (0.1274) loss: 0.8156 (0.8145) time: 0.4863 data: 0.3940 max mem: 9390 +Train: [78] [4100/6250] eta: 0:06:44 lr: 0.000015 grad: 0.1341 (0.1275) loss: 0.8094 (0.8144) time: 0.1810 data: 0.0922 max mem: 9390 +Train: [78] [4200/6250] eta: 0:06:26 lr: 0.000015 grad: 0.1309 (0.1277) loss: 0.8092 (0.8143) time: 0.1026 data: 0.0002 max mem: 9390 +Train: [78] [4300/6250] eta: 0:06:05 lr: 0.000015 grad: 0.1342 (0.1278) loss: 0.8079 (0.8142) time: 0.1600 data: 0.0760 max mem: 9390 +Train: [78] [4400/6250] eta: 0:05:46 lr: 0.000015 grad: 0.1317 (0.1278) loss: 0.8039 (0.8142) time: 0.2116 data: 0.1293 max mem: 9390 +Train: [78] [4500/6250] eta: 0:05:28 lr: 0.000015 grad: 0.1329 (0.1279) loss: 0.8118 (0.8141) time: 0.1100 data: 0.0002 max mem: 9390 +Train: [78] [4600/6250] eta: 0:05:10 lr: 0.000015 grad: 0.1267 (0.1279) loss: 0.8114 (0.8141) time: 0.1229 data: 0.0330 max mem: 9390 +Train: [78] [4700/6250] eta: 0:04:50 lr: 0.000015 grad: 0.1293 (0.1280) loss: 0.8145 (0.8140) time: 0.1761 data: 0.0719 max mem: 9390 +Train: [78] [4800/6250] eta: 0:04:32 lr: 0.000015 grad: 0.1248 (0.1280) loss: 0.8090 (0.8140) time: 0.1521 data: 0.0529 max mem: 9390 +Train: [78] [4900/6250] eta: 0:04:13 lr: 0.000015 grad: 0.1251 (0.1280) loss: 0.8098 (0.8140) time: 0.2191 data: 0.1000 max mem: 9390 +Train: [78] [5000/6250] eta: 0:03:55 lr: 0.000015 grad: 0.1350 (0.1281) loss: 0.8124 (0.8140) time: 0.2532 data: 0.1532 max mem: 9390 +Train: [78] [5100/6250] eta: 0:03:36 lr: 0.000015 grad: 0.1218 (0.1281) loss: 0.8162 (0.8139) time: 0.1821 data: 0.0870 max mem: 9390 +Train: [78] [5200/6250] eta: 0:03:17 lr: 0.000015 grad: 0.1157 (0.1281) loss: 0.8167 (0.8139) time: 0.1593 data: 0.0716 max mem: 9390 +Train: [78] [5300/6250] eta: 0:02:58 lr: 0.000015 grad: 0.1206 (0.1281) loss: 0.8163 (0.8139) time: 0.1017 data: 0.0002 max mem: 9390 +Train: [78] [5400/6250] eta: 0:02:39 lr: 0.000015 grad: 0.1305 (0.1281) loss: 0.8116 (0.8139) time: 0.2074 data: 0.1257 max mem: 9390 +Train: [78] [5500/6250] eta: 0:02:20 lr: 0.000015 grad: 0.1269 (0.1281) loss: 0.8086 (0.8138) time: 0.1364 data: 0.0432 max mem: 9390 +Train: [78] [5600/6250] eta: 0:02:02 lr: 0.000015 grad: 0.1217 (0.1280) loss: 0.8131 (0.8138) time: 0.1382 data: 0.0457 max mem: 9390 +Train: [78] [5700/6250] eta: 0:01:43 lr: 0.000015 grad: 0.1248 (0.1280) loss: 0.8120 (0.8138) time: 0.2521 data: 0.1642 max mem: 9390 +Train: [78] [5800/6250] eta: 0:01:24 lr: 0.000015 grad: 0.1207 (0.1280) loss: 0.8143 (0.8138) time: 0.1934 data: 0.1101 max mem: 9390 +Train: [78] [5900/6250] eta: 0:01:05 lr: 0.000015 grad: 0.1193 (0.1280) loss: 0.8150 (0.8138) time: 0.1807 data: 0.0980 max mem: 9390 +Train: [78] [6000/6250] eta: 0:00:47 lr: 0.000015 grad: 0.1260 (0.1279) loss: 0.8157 (0.8138) time: 0.1862 data: 0.0982 max mem: 9390 +Train: [78] [6100/6250] eta: 0:00:28 lr: 0.000015 grad: 0.1257 (0.1280) loss: 0.8116 (0.8138) time: 0.1944 data: 0.1130 max mem: 9390 +Train: [78] [6200/6250] eta: 0:00:09 lr: 0.000014 grad: 0.1273 (0.1280) loss: 0.8097 (0.8138) time: 0.1707 data: 0.0844 max mem: 9390 +Train: [78] [6249/6250] eta: 0:00:00 lr: 0.000014 grad: 0.1263 (0.1280) loss: 0.8123 (0.8138) time: 0.1754 data: 0.0859 max mem: 9390 +Train: [78] Total time: 0:19:42 (0.1892 s / it) +Averaged stats: lr: 0.000014 grad: 0.1263 (0.1280) loss: 0.8123 (0.8138) +Eval (hcp-train-subset): [78] [ 0/62] eta: 0:05:45 loss: 0.8341 (0.8341) time: 5.5646 data: 5.5325 max mem: 9390 +Eval (hcp-train-subset): [78] [61/62] eta: 0:00:00 loss: 0.8224 (0.8248) time: 0.1389 data: 0.1121 max mem: 9390 +Eval (hcp-train-subset): [78] Total time: 0:00:14 (0.2268 s / it) +Averaged stats (hcp-train-subset): loss: 0.8224 (0.8248) +Eval (hcp-val): [78] [ 0/62] eta: 0:03:54 loss: 0.8283 (0.8283) time: 3.7888 data: 3.7054 max mem: 9390 +Eval (hcp-val): [78] [61/62] eta: 0:00:00 loss: 0.8298 (0.8302) time: 0.1403 data: 0.1148 max mem: 9390 +Eval (hcp-val): [78] Total time: 0:00:14 (0.2284 s / it) +Averaged stats (hcp-val): loss: 0.8298 (0.8302) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +Train: [79] [ 0/6250] eta: 11:25:57 lr: 0.000014 grad: 0.1507 (0.1507) loss: 0.8309 (0.8309) time: 6.5852 data: 6.4083 max mem: 9390 +Train: [79] [ 100/6250] eta: 0:25:27 lr: 0.000014 grad: 0.1342 (0.1560) loss: 0.8246 (0.8233) time: 0.2050 data: 0.0935 max mem: 9390 +Train: [79] [ 200/6250] eta: 0:21:20 lr: 0.000014 grad: 0.1283 (0.1505) loss: 0.8193 (0.8213) time: 0.1667 data: 0.0571 max mem: 9390 +Train: [79] [ 300/6250] eta: 0:19:39 lr: 0.000014 grad: 0.1294 (0.1444) loss: 0.8178 (0.8208) time: 0.1700 data: 0.0728 max mem: 9390 +Train: [79] [ 400/6250] eta: 0:18:31 lr: 0.000014 grad: 0.1237 (0.1398) loss: 0.8185 (0.8205) time: 0.1776 data: 0.0833 max mem: 9390 +Train: [79] [ 500/6250] eta: 0:18:14 lr: 0.000014 grad: 0.1200 (0.1371) loss: 0.8208 (0.8202) time: 0.1867 data: 0.0898 max mem: 9390 +Train: [79] [ 600/6250] eta: 0:20:11 lr: 0.000014 grad: 0.1159 (0.1344) loss: 0.8224 (0.8205) time: 0.2057 data: 0.0772 max mem: 9390 +Train: [79] [ 700/6250] eta: 0:20:30 lr: 0.000014 grad: 0.1310 (0.1328) loss: 0.8195 (0.8205) time: 0.1637 data: 0.0004 max mem: 9390 +Train: [79] [ 800/6250] eta: 0:19:53 lr: 0.000014 grad: 0.1190 (0.1317) loss: 0.8227 (0.8205) time: 0.1752 data: 0.0850 max mem: 9390 +Train: [79] [ 900/6250] eta: 0:19:19 lr: 0.000014 grad: 0.1180 (0.1310) loss: 0.8191 (0.8203) time: 0.1799 data: 0.0796 max mem: 9390 +Train: [79] [1000/6250] eta: 0:18:38 lr: 0.000014 grad: 0.1160 (0.1303) loss: 0.8246 (0.8200) time: 0.1775 data: 0.0936 max mem: 9390 +Train: [79] [1100/6250] eta: 0:18:04 lr: 0.000014 grad: 0.1255 (0.1301) loss: 0.8137 (0.8194) time: 0.2006 data: 0.1115 max mem: 9390 +Train: [79] [1200/6250] eta: 0:17:18 lr: 0.000014 grad: 0.1248 (0.1298) loss: 0.8166 (0.8188) time: 0.1479 data: 0.0513 max mem: 9390 +Train: [79] [1300/6250] eta: 0:16:39 lr: 0.000014 grad: 0.1170 (0.1292) loss: 0.8173 (0.8186) time: 0.1321 data: 0.0429 max mem: 9390 +Train: [79] [1400/6250] eta: 0:16:07 lr: 0.000014 grad: 0.1138 (0.1288) loss: 0.8203 (0.8184) time: 0.1675 data: 0.0818 max mem: 9390 +Train: [79] [1500/6250] eta: 0:15:44 lr: 0.000014 grad: 0.1203 (0.1284) loss: 0.8127 (0.8183) time: 0.1854 data: 0.1027 max mem: 9390 +Train: [79] [1600/6250] eta: 0:15:18 lr: 0.000014 grad: 0.1251 (0.1283) loss: 0.8138 (0.8180) time: 0.1870 data: 0.1030 max mem: 9390 +Train: [79] [1700/6250] eta: 0:14:52 lr: 0.000014 grad: 0.1260 (0.1280) loss: 0.8129 (0.8178) time: 0.1895 data: 0.1088 max mem: 9390 +Train: [79] [1800/6250] eta: 0:14:25 lr: 0.000014 grad: 0.1227 (0.1277) loss: 0.8150 (0.8176) time: 0.1564 data: 0.0710 max mem: 9390 +Train: [79] [1900/6250] eta: 0:14:04 lr: 0.000014 grad: 0.1246 (0.1276) loss: 0.8135 (0.8175) time: 0.1990 data: 0.1078 max mem: 9390 +Train: [79] [2000/6250] eta: 0:13:42 lr: 0.000014 grad: 0.1246 (0.1276) loss: 0.8147 (0.8174) time: 0.1803 data: 0.0906 max mem: 9390 +Train: [79] [2100/6250] eta: 0:13:20 lr: 0.000014 grad: 0.1192 (0.1275) loss: 0.8198 (0.8173) time: 0.1850 data: 0.0849 max mem: 9390 +Train: [79] [2200/6250] eta: 0:13:00 lr: 0.000014 grad: 0.1223 (0.1275) loss: 0.8112 (0.8172) time: 0.1731 data: 0.0779 max mem: 9390 +Train: [79] [2300/6250] eta: 0:12:37 lr: 0.000014 grad: 0.1276 (0.1275) loss: 0.8078 (0.8169) time: 0.1358 data: 0.0365 max mem: 9390 +Train: [79] [2400/6250] eta: 0:12:17 lr: 0.000014 grad: 0.1329 (0.1276) loss: 0.8072 (0.8168) time: 0.1756 data: 0.0708 max mem: 9390 +Train: [79] [2500/6250] eta: 0:11:56 lr: 0.000014 grad: 0.1268 (0.1277) loss: 0.8150 (0.8165) time: 0.1887 data: 0.0965 max mem: 9390 +Train: [79] [2600/6250] eta: 0:11:37 lr: 0.000014 grad: 0.1244 (0.1277) loss: 0.8139 (0.8164) time: 0.1062 data: 0.0003 max mem: 9390 +Train: [79] [2700/6250] eta: 0:11:18 lr: 0.000014 grad: 0.1233 (0.1278) loss: 0.8148 (0.8163) time: 0.1946 data: 0.0757 max mem: 9390 +Train: [79] [2800/6250] eta: 0:11:01 lr: 0.000014 grad: 0.1275 (0.1279) loss: 0.8171 (0.8161) time: 0.1426 data: 0.0312 max mem: 9390 +Train: [79] [2900/6250] eta: 0:10:39 lr: 0.000014 grad: 0.1251 (0.1280) loss: 0.8156 (0.8160) time: 0.1709 data: 0.0734 max mem: 9390 +Train: [79] [3000/6250] eta: 0:10:20 lr: 0.000014 grad: 0.1336 (0.1281) loss: 0.8106 (0.8159) time: 0.1567 data: 0.0620 max mem: 9390 +Train: [79] [3100/6250] eta: 0:10:06 lr: 0.000014 grad: 0.1263 (0.1281) loss: 0.8150 (0.8157) time: 0.1233 data: 0.0003 max mem: 9390 +Train: [79] [3200/6250] eta: 0:09:45 lr: 0.000014 grad: 0.1237 (0.1282) loss: 0.8169 (0.8157) time: 0.1638 data: 0.0701 max mem: 9390 +Train: [79] [3300/6250] eta: 0:09:26 lr: 0.000014 grad: 0.1217 (0.1281) loss: 0.8169 (0.8157) time: 0.1580 data: 0.0544 max mem: 9390 +Train: [79] [3400/6250] eta: 0:09:08 lr: 0.000014 grad: 0.1274 (0.1282) loss: 0.8177 (0.8156) time: 0.3415 data: 0.2348 max mem: 9390 +Train: [79] [3500/6250] eta: 0:08:50 lr: 0.000014 grad: 0.1247 (0.1282) loss: 0.8177 (0.8155) time: 0.1636 data: 0.0619 max mem: 9390 +Train: [79] [3600/6250] eta: 0:08:30 lr: 0.000014 grad: 0.1196 (0.1283) loss: 0.8116 (0.8154) time: 0.1407 data: 0.0387 max mem: 9390 +Train: [79] [3700/6250] eta: 0:08:11 lr: 0.000014 grad: 0.1305 (0.1282) loss: 0.8002 (0.8153) time: 0.1120 data: 0.0003 max mem: 9390 +Train: [79] [3800/6250] eta: 0:07:52 lr: 0.000014 grad: 0.1284 (0.1283) loss: 0.8119 (0.8153) time: 0.1675 data: 0.0756 max mem: 9390 +Train: [79] [3900/6250] eta: 0:07:35 lr: 0.000014 grad: 0.1220 (0.1283) loss: 0.8096 (0.8152) time: 0.1405 data: 0.0285 max mem: 9390 +Train: [79] [4000/6250] eta: 0:07:15 lr: 0.000014 grad: 0.1214 (0.1282) loss: 0.8150 (0.8151) time: 0.1964 data: 0.1010 max mem: 9390 +Train: [79] [4100/6250] eta: 0:06:54 lr: 0.000014 grad: 0.1256 (0.1283) loss: 0.8114 (0.8150) time: 0.1619 data: 0.0700 max mem: 9390 +Train: [79] [4200/6250] eta: 0:06:35 lr: 0.000014 grad: 0.1310 (0.1283) loss: 0.8116 (0.8150) time: 0.1638 data: 0.0763 max mem: 9390 +Train: [79] [4300/6250] eta: 0:06:16 lr: 0.000014 grad: 0.1225 (0.1283) loss: 0.8080 (0.8149) time: 0.1026 data: 0.0002 max mem: 9390 +Train: [79] [4400/6250] eta: 0:05:56 lr: 0.000014 grad: 0.1222 (0.1284) loss: 0.8169 (0.8148) time: 0.1565 data: 0.0695 max mem: 9390 +Train: [79] [4500/6250] eta: 0:05:36 lr: 0.000014 grad: 0.1294 (0.1284) loss: 0.8089 (0.8147) time: 0.1782 data: 0.0890 max mem: 9390 +Train: [79] [4600/6250] eta: 0:05:15 lr: 0.000014 grad: 0.1199 (0.1284) loss: 0.8128 (0.8147) time: 0.1566 data: 0.0698 max mem: 9390 +Train: [79] [4700/6250] eta: 0:04:55 lr: 0.000013 grad: 0.1232 (0.1285) loss: 0.8116 (0.8146) time: 0.1782 data: 0.0856 max mem: 9390 +Train: [79] [4800/6250] eta: 0:04:35 lr: 0.000013 grad: 0.1206 (0.1284) loss: 0.8127 (0.8146) time: 0.1523 data: 0.0602 max mem: 9390 +Train: [79] [4900/6250] eta: 0:04:16 lr: 0.000013 grad: 0.1281 (0.1284) loss: 0.8158 (0.8146) time: 0.1681 data: 0.0792 max mem: 9390 +Train: [79] [5000/6250] eta: 0:03:57 lr: 0.000013 grad: 0.1264 (0.1284) loss: 0.8157 (0.8146) time: 0.2967 data: 0.2094 max mem: 9390 +Train: [79] [5100/6250] eta: 0:03:38 lr: 0.000013 grad: 0.1278 (0.1284) loss: 0.8060 (0.8146) time: 0.1623 data: 0.0608 max mem: 9390 +Train: [79] [5200/6250] eta: 0:03:19 lr: 0.000013 grad: 0.1254 (0.1283) loss: 0.8179 (0.8146) time: 0.3630 data: 0.2512 max mem: 9390 +Train: [79] [5300/6250] eta: 0:03:00 lr: 0.000013 grad: 0.1295 (0.1283) loss: 0.8132 (0.8146) time: 0.1739 data: 0.0865 max mem: 9390 +Train: [79] [5400/6250] eta: 0:02:40 lr: 0.000013 grad: 0.1272 (0.1283) loss: 0.8177 (0.8146) time: 0.1564 data: 0.0672 max mem: 9390 +Train: [79] [5500/6250] eta: 0:02:21 lr: 0.000013 grad: 0.1243 (0.1283) loss: 0.8141 (0.8146) time: 0.1702 data: 0.0947 max mem: 9390 +Train: [79] [5600/6250] eta: 0:02:02 lr: 0.000013 grad: 0.1202 (0.1282) loss: 0.8105 (0.8146) time: 0.3061 data: 0.2144 max mem: 9390 +Train: [79] [5700/6250] eta: 0:01:43 lr: 0.000013 grad: 0.1257 (0.1282) loss: 0.8136 (0.8146) time: 0.1891 data: 0.1082 max mem: 9390 +Train: [79] [5800/6250] eta: 0:01:24 lr: 0.000013 grad: 0.1233 (0.1282) loss: 0.8100 (0.8145) time: 0.1850 data: 0.0972 max mem: 9390 +Train: [79] [5900/6250] eta: 0:01:06 lr: 0.000013 grad: 0.1263 (0.1282) loss: 0.8145 (0.8145) time: 0.1637 data: 0.0673 max mem: 9390 +Train: [79] [6000/6250] eta: 0:00:47 lr: 0.000013 grad: 0.1253 (0.1281) loss: 0.8112 (0.8145) time: 0.1785 data: 0.0878 max mem: 9390 +Train: [79] [6100/6250] eta: 0:00:28 lr: 0.000013 grad: 0.1307 (0.1282) loss: 0.8087 (0.8144) time: 0.1893 data: 0.1006 max mem: 9390 +Train: [79] [6200/6250] eta: 0:00:09 lr: 0.000013 grad: 0.1217 (0.1282) loss: 0.8101 (0.8143) time: 0.2031 data: 0.0910 max mem: 9390 +Train: [79] [6249/6250] eta: 0:00:00 lr: 0.000013 grad: 0.1315 (0.1282) loss: 0.8039 (0.8143) time: 0.1956 data: 0.1073 max mem: 9390 +Train: [79] Total time: 0:19:56 (0.1915 s / it) +Averaged stats: lr: 0.000013 grad: 0.1315 (0.1282) loss: 0.8039 (0.8143) +Eval (hcp-train-subset): [79] [ 0/62] eta: 0:05:03 loss: 0.8326 (0.8326) time: 4.8927 data: 4.8485 max mem: 9390 +Eval (hcp-train-subset): [79] [61/62] eta: 0:00:00 loss: 0.8220 (0.8239) time: 0.1284 data: 0.1013 max mem: 9390 +Eval (hcp-train-subset): [79] Total time: 0:00:14 (0.2323 s / it) +Averaged stats (hcp-train-subset): loss: 0.8220 (0.8239) +Making plots (hcp-train-subset): example=61 +Eval (hcp-val): [79] [ 0/62] eta: 0:03:41 loss: 0.8296 (0.8296) time: 3.5803 data: 3.4628 max mem: 9390 +Eval (hcp-val): [79] [61/62] eta: 0:00:00 loss: 0.8291 (0.8307) time: 0.1333 data: 0.1083 max mem: 9390 +Eval (hcp-val): [79] Total time: 0:00:14 (0.2338 s / it) +Averaged stats (hcp-val): loss: 0.8291 (0.8307) +Making plots (hcp-val): example=36 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +Train: [80] [ 0/6250] eta: 11:42:27 lr: 0.000013 grad: 0.5808 (0.5808) loss: 0.8211 (0.8211) time: 6.7437 data: 6.6150 max mem: 9390 +Train: [80] [ 100/6250] eta: 0:22:56 lr: 0.000013 grad: 0.1441 (0.1591) loss: 0.8256 (0.8274) time: 0.1608 data: 0.0548 max mem: 9390 +Train: [80] [ 200/6250] eta: 0:20:12 lr: 0.000013 grad: 0.1232 (0.1505) loss: 0.8213 (0.8233) time: 0.1784 data: 0.0790 max mem: 9390 +Train: [80] [ 300/6250] eta: 0:19:22 lr: 0.000013 grad: 0.1269 (0.1478) loss: 0.8170 (0.8200) time: 0.2275 data: 0.1368 max mem: 9390 +Train: [80] [ 400/6250] eta: 0:18:23 lr: 0.000013 grad: 0.1489 (0.1459) loss: 0.8012 (0.8177) time: 0.1829 data: 0.0679 max mem: 9390 +Train: [80] [ 500/6250] eta: 0:18:20 lr: 0.000013 grad: 0.1325 (0.1446) loss: 0.8215 (0.8165) time: 0.2096 data: 0.1184 max mem: 9390 +Train: [80] [ 600/6250] eta: 0:17:57 lr: 0.000013 grad: 0.1367 (0.1438) loss: 0.8167 (0.8154) time: 0.2035 data: 0.1228 max mem: 9390 +Train: [80] [ 700/6250] eta: 0:17:47 lr: 0.000013 grad: 0.1394 (0.1429) loss: 0.8048 (0.8145) time: 0.2166 data: 0.1248 max mem: 9390 +Train: [80] [ 800/6250] eta: 0:17:42 lr: 0.000013 grad: 0.1273 (0.1419) loss: 0.8088 (0.8142) time: 0.2735 data: 0.1676 max mem: 9390 +Train: [80] [ 900/6250] eta: 0:17:34 lr: 0.000013 grad: 0.1354 (0.1413) loss: 0.8119 (0.8139) time: 0.1547 data: 0.0503 max mem: 9390 +Train: [80] [1000/6250] eta: 0:17:06 lr: 0.000013 grad: 0.1256 (0.1401) loss: 0.8122 (0.8139) time: 0.1884 data: 0.1075 max mem: 9390 +Train: [80] [1100/6250] eta: 0:16:48 lr: 0.000013 grad: 0.1243 (0.1393) loss: 0.8133 (0.8138) time: 0.1377 data: 0.0384 max mem: 9390 +Train: [80] [1200/6250] eta: 0:16:19 lr: 0.000013 grad: 0.1276 (0.1386) loss: 0.8078 (0.8135) time: 0.1516 data: 0.0560 max mem: 9390 +Train: [80] [1300/6250] eta: 0:15:55 lr: 0.000013 grad: 0.1266 (0.1380) loss: 0.8093 (0.8132) time: 0.1532 data: 0.0714 max mem: 9390 +Train: [80] [1400/6250] eta: 0:15:31 lr: 0.000013 grad: 0.1294 (0.1375) loss: 0.8161 (0.8130) time: 0.1862 data: 0.1024 max mem: 9390 +Train: [80] [1500/6250] eta: 0:15:12 lr: 0.000013 grad: 0.1303 (0.1373) loss: 0.8140 (0.8128) time: 0.1127 data: 0.0004 max mem: 9390 +Train: [80] [1600/6250] eta: 0:14:46 lr: 0.000013 grad: 0.1340 (0.1370) loss: 0.8132 (0.8127) time: 0.1806 data: 0.0998 max mem: 9390 +Train: [80] [1700/6250] eta: 0:14:28 lr: 0.000013 grad: 0.1211 (0.1368) loss: 0.8139 (0.8125) time: 0.1520 data: 0.0542 max mem: 9390 +Train: [80] [1800/6250] eta: 0:14:10 lr: 0.000013 grad: 0.1312 (0.1365) loss: 0.8108 (0.8124) time: 0.2592 data: 0.1702 max mem: 9390 +Train: [80] [1900/6250] eta: 0:13:49 lr: 0.000013 grad: 0.1310 (0.1361) loss: 0.8146 (0.8124) time: 0.3029 data: 0.1764 max mem: 9390 +Train: [80] [2000/6250] eta: 0:13:26 lr: 0.000013 grad: 0.1262 (0.1356) loss: 0.8154 (0.8125) time: 0.2049 data: 0.1194 max mem: 9390 +Train: [80] [2100/6250] eta: 0:13:05 lr: 0.000013 grad: 0.1222 (0.1352) loss: 0.8175 (0.8126) time: 0.2138 data: 0.1254 max mem: 9390 +Train: [80] [2200/6250] eta: 0:12:49 lr: 0.000013 grad: 0.1219 (0.1348) loss: 0.8144 (0.8127) time: 0.1157 data: 0.0003 max mem: 9390 +Train: [80] [2300/6250] eta: 0:12:27 lr: 0.000013 grad: 0.1214 (0.1344) loss: 0.8177 (0.8127) time: 0.1935 data: 0.0884 max mem: 9390 +Train: [80] [2400/6250] eta: 0:12:07 lr: 0.000013 grad: 0.1199 (0.1341) loss: 0.8175 (0.8128) time: 0.1487 data: 0.0307 max mem: 9390 +Train: [80] [2500/6250] eta: 0:11:53 lr: 0.000013 grad: 0.1197 (0.1339) loss: 0.8159 (0.8128) time: 0.1864 data: 0.0855 max mem: 9390 +Train: [80] [2600/6250] eta: 0:11:32 lr: 0.000013 grad: 0.1298 (0.1337) loss: 0.8132 (0.8129) time: 0.1669 data: 0.0828 max mem: 9390 +Train: [80] [2700/6250] eta: 0:11:16 lr: 0.000013 grad: 0.1229 (0.1336) loss: 0.8128 (0.8128) time: 0.3606 data: 0.2611 max mem: 9390 +Train: [80] [2800/6250] eta: 0:10:54 lr: 0.000013 grad: 0.1281 (0.1335) loss: 0.8178 (0.8129) time: 0.1812 data: 0.0937 max mem: 9390 +Train: [80] [2900/6250] eta: 0:10:34 lr: 0.000013 grad: 0.1291 (0.1334) loss: 0.8095 (0.8129) time: 0.1648 data: 0.0432 max mem: 9390 +Train: [80] [3000/6250] eta: 0:10:14 lr: 0.000013 grad: 0.1326 (0.1334) loss: 0.8136 (0.8129) time: 0.1193 data: 0.0003 max mem: 9390 +Train: [80] [3100/6250] eta: 0:09:57 lr: 0.000013 grad: 0.1292 (0.1333) loss: 0.8061 (0.8130) time: 0.3312 data: 0.2179 max mem: 9390 +Train: [80] [3200/6250] eta: 0:09:36 lr: 0.000013 grad: 0.1245 (0.1331) loss: 0.8126 (0.8130) time: 0.1295 data: 0.0308 max mem: 9390 +Train: [80] [3300/6250] eta: 0:09:17 lr: 0.000013 grad: 0.1266 (0.1330) loss: 0.8119 (0.8130) time: 0.1749 data: 0.0868 max mem: 9390 +Train: [80] [3400/6250] eta: 0:09:03 lr: 0.000012 grad: 0.1277 (0.1331) loss: 0.8134 (0.8130) time: 0.5731 data: 0.4722 max mem: 9390 +Train: [80] [3500/6250] eta: 0:08:41 lr: 0.000012 grad: 0.1227 (0.1330) loss: 0.8199 (0.8130) time: 0.1082 data: 0.0004 max mem: 9390 +Train: [80] [3600/6250] eta: 0:08:21 lr: 0.000012 grad: 0.1250 (0.1329) loss: 0.8151 (0.8130) time: 0.1526 data: 0.0589 max mem: 9390 +Train: [80] [3700/6250] eta: 0:08:02 lr: 0.000012 grad: 0.1185 (0.1327) loss: 0.8189 (0.8131) time: 0.2590 data: 0.1654 max mem: 9390 +Train: [80] [3800/6250] eta: 0:07:42 lr: 0.000012 grad: 0.1250 (0.1325) loss: 0.8152 (0.8132) time: 0.1911 data: 0.1028 max mem: 9390 +Train: [80] [3900/6250] eta: 0:07:23 lr: 0.000012 grad: 0.1288 (0.1324) loss: 0.8129 (0.8133) time: 0.1203 data: 0.0003 max mem: 9390 +Train: [80] [4000/6250] eta: 0:07:05 lr: 0.000012 grad: 0.1230 (0.1322) loss: 0.8188 (0.8134) time: 0.1254 data: 0.0247 max mem: 9390 +Train: [80] [4100/6250] eta: 0:06:47 lr: 0.000012 grad: 0.1250 (0.1322) loss: 0.8173 (0.8134) time: 0.3056 data: 0.2027 max mem: 9390 +Train: [80] [4200/6250] eta: 0:06:27 lr: 0.000012 grad: 0.1342 (0.1322) loss: 0.8117 (0.8134) time: 0.1933 data: 0.1097 max mem: 9390 +Train: [80] [4300/6250] eta: 0:06:08 lr: 0.000012 grad: 0.1240 (0.1323) loss: 0.8169 (0.8134) time: 0.1633 data: 0.0503 max mem: 9390 +Train: [80] [4400/6250] eta: 0:05:50 lr: 0.000012 grad: 0.1261 (0.1322) loss: 0.8134 (0.8135) time: 0.2517 data: 0.1568 max mem: 9390 +Train: [80] [4500/6250] eta: 0:05:31 lr: 0.000012 grad: 0.1294 (0.1321) loss: 0.8130 (0.8135) time: 0.1486 data: 0.0616 max mem: 9390 +Train: [80] [4600/6250] eta: 0:05:11 lr: 0.000012 grad: 0.1279 (0.1320) loss: 0.8155 (0.8135) time: 0.1823 data: 0.0790 max mem: 9390 +Train: [80] [4700/6250] eta: 0:04:53 lr: 0.000012 grad: 0.1253 (0.1321) loss: 0.8139 (0.8136) time: 0.1379 data: 0.0422 max mem: 9390 +Train: [80] [4800/6250] eta: 0:04:33 lr: 0.000012 grad: 0.1300 (0.1321) loss: 0.8131 (0.8136) time: 0.2345 data: 0.1438 max mem: 9390 +Train: [80] [4900/6250] eta: 0:04:14 lr: 0.000012 grad: 0.1177 (0.1320) loss: 0.8191 (0.8136) time: 0.1594 data: 0.0772 max mem: 9390 +Train: [80] [5000/6250] eta: 0:03:55 lr: 0.000012 grad: 0.1280 (0.1319) loss: 0.8163 (0.8137) time: 0.1172 data: 0.0212 max mem: 9390 +Train: [80] [5100/6250] eta: 0:03:37 lr: 0.000012 grad: 0.1247 (0.1318) loss: 0.8154 (0.8137) time: 0.3453 data: 0.2282 max mem: 9390 +Train: [80] [5200/6250] eta: 0:03:18 lr: 0.000012 grad: 0.1220 (0.1318) loss: 0.8213 (0.8137) time: 0.2422 data: 0.1591 max mem: 9390 +Train: [80] [5300/6250] eta: 0:03:00 lr: 0.000012 grad: 0.1241 (0.1317) loss: 0.8156 (0.8137) time: 0.4411 data: 0.3318 max mem: 9390 +Train: [80] [5400/6250] eta: 0:02:40 lr: 0.000012 grad: 0.1312 (0.1317) loss: 0.8091 (0.8137) time: 0.1843 data: 0.0968 max mem: 9390 +Train: [80] [5500/6250] eta: 0:02:21 lr: 0.000012 grad: 0.1198 (0.1316) loss: 0.8158 (0.8137) time: 0.1868 data: 0.1035 max mem: 9390 +Train: [80] [5600/6250] eta: 0:02:02 lr: 0.000012 grad: 0.1227 (0.1316) loss: 0.8126 (0.8137) time: 0.1964 data: 0.1121 max mem: 9390 +Train: [80] [5700/6250] eta: 0:01:43 lr: 0.000012 grad: 0.1277 (0.1316) loss: 0.8099 (0.8137) time: 0.2307 data: 0.1456 max mem: 9390 +Train: [80] [5800/6250] eta: 0:01:25 lr: 0.000012 grad: 0.1309 (0.1315) loss: 0.8099 (0.8137) time: 0.1701 data: 0.0890 max mem: 9390 +Train: [80] [5900/6250] eta: 0:01:06 lr: 0.000012 grad: 0.1189 (0.1315) loss: 0.8121 (0.8137) time: 0.2053 data: 0.1153 max mem: 9390 +Train: [80] [6000/6250] eta: 0:00:47 lr: 0.000012 grad: 0.1277 (0.1315) loss: 0.8072 (0.8136) time: 0.1863 data: 0.0928 max mem: 9390 +Train: [80] [6100/6250] eta: 0:00:28 lr: 0.000012 grad: 0.1349 (0.1315) loss: 0.8079 (0.8136) time: 0.1766 data: 0.0936 max mem: 9390 +Train: [80] [6200/6250] eta: 0:00:09 lr: 0.000012 grad: 0.1270 (0.1315) loss: 0.8072 (0.8136) time: 0.1714 data: 0.0781 max mem: 9390 +Train: [80] [6249/6250] eta: 0:00:00 lr: 0.000012 grad: 0.1360 (0.1316) loss: 0.8142 (0.8136) time: 0.1621 data: 0.0738 max mem: 9390 +Train: [80] Total time: 0:19:43 (0.1894 s / it) +Averaged stats: lr: 0.000012 grad: 0.1360 (0.1316) loss: 0.8142 (0.8136) +Eval (hcp-train-subset): [80] [ 0/62] eta: 0:04:01 loss: 0.8284 (0.8284) time: 3.8927 data: 3.7870 max mem: 9390 +Eval (hcp-train-subset): [80] [61/62] eta: 0:00:00 loss: 0.8205 (0.8235) time: 0.1231 data: 0.0939 max mem: 9390 +Eval (hcp-train-subset): [80] Total time: 0:00:13 (0.2239 s / it) +Averaged stats (hcp-train-subset): loss: 0.8205 (0.8235) +Eval (hcp-val): [80] [ 0/62] eta: 0:04:12 loss: 0.8271 (0.8271) time: 4.0702 data: 3.9659 max mem: 9390 +Eval (hcp-val): [80] [61/62] eta: 0:00:00 loss: 0.8303 (0.8310) time: 0.1071 data: 0.0804 max mem: 9390 +Eval (hcp-val): [80] Total time: 0:00:14 (0.2267 s / it) +Averaged stats (hcp-val): loss: 0.8303 (0.8310) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +Train: [81] [ 0/6250] eta: 10:22:47 lr: 0.000012 grad: 0.0852 (0.0852) loss: 0.8680 (0.8680) time: 5.9788 data: 5.8026 max mem: 9390 +Train: [81] [ 100/6250] eta: 0:23:22 lr: 0.000012 grad: 0.1372 (0.1699) loss: 0.8162 (0.8293) time: 0.1760 data: 0.0600 max mem: 9390 +Train: [81] [ 200/6250] eta: 0:19:35 lr: 0.000012 grad: 0.1218 (0.1512) loss: 0.8201 (0.8231) time: 0.1612 data: 0.0565 max mem: 9390 +Train: [81] [ 300/6250] eta: 0:18:12 lr: 0.000012 grad: 0.1210 (0.1441) loss: 0.8080 (0.8201) time: 0.1599 data: 0.0602 max mem: 9390 +Train: [81] [ 400/6250] eta: 0:17:57 lr: 0.000012 grad: 0.1266 (0.1408) loss: 0.8206 (0.8185) time: 0.1250 data: 0.0003 max mem: 9390 +Train: [81] [ 500/6250] eta: 0:18:44 lr: 0.000012 grad: 0.1344 (0.1393) loss: 0.8104 (0.8175) time: 0.4316 data: 0.3176 max mem: 9390 +Train: [81] [ 600/6250] eta: 0:18:42 lr: 0.000012 grad: 0.1315 (0.1382) loss: 0.8120 (0.8170) time: 0.2101 data: 0.1051 max mem: 9390 +Train: [81] [ 700/6250] eta: 0:18:17 lr: 0.000012 grad: 0.1275 (0.1375) loss: 0.8072 (0.8165) time: 0.2109 data: 0.1248 max mem: 9390 +Train: [81] [ 800/6250] eta: 0:17:47 lr: 0.000012 grad: 0.1274 (0.1363) loss: 0.8151 (0.8162) time: 0.1909 data: 0.1046 max mem: 9390 +Train: [81] [ 900/6250] eta: 0:17:25 lr: 0.000012 grad: 0.1252 (0.1356) loss: 0.8146 (0.8163) time: 0.1616 data: 0.0594 max mem: 9390 +Train: [81] [1000/6250] eta: 0:17:13 lr: 0.000012 grad: 0.1238 (0.1349) loss: 0.8091 (0.8162) time: 0.0872 data: 0.0003 max mem: 9390 +Train: [81] [1100/6250] eta: 0:16:49 lr: 0.000012 grad: 0.1305 (0.1342) loss: 0.8167 (0.8162) time: 0.2011 data: 0.1168 max mem: 9390 +Train: [81] [1200/6250] eta: 0:16:27 lr: 0.000012 grad: 0.1261 (0.1338) loss: 0.8111 (0.8160) time: 0.2148 data: 0.1293 max mem: 9390 +Train: [81] [1300/6250] eta: 0:16:08 lr: 0.000012 grad: 0.1273 (0.1335) loss: 0.8154 (0.8156) time: 0.2270 data: 0.1372 max mem: 9390 +Train: [81] [1400/6250] eta: 0:15:48 lr: 0.000012 grad: 0.1223 (0.1332) loss: 0.8198 (0.8156) time: 0.1880 data: 0.0988 max mem: 9390 +Train: [81] [1500/6250] eta: 0:15:32 lr: 0.000012 grad: 0.1262 (0.1327) loss: 0.8112 (0.8156) time: 0.2230 data: 0.1312 max mem: 9390 +Train: [81] [1600/6250] eta: 0:15:15 lr: 0.000012 grad: 0.1332 (0.1325) loss: 0.8100 (0.8154) time: 0.2143 data: 0.1262 max mem: 9390 +Train: [81] [1700/6250] eta: 0:14:53 lr: 0.000012 grad: 0.1257 (0.1323) loss: 0.8105 (0.8152) time: 0.1779 data: 0.0867 max mem: 9390 +Train: [81] [1800/6250] eta: 0:14:36 lr: 0.000012 grad: 0.1206 (0.1320) loss: 0.8151 (0.8151) time: 0.3033 data: 0.2121 max mem: 9390 +Train: [81] [1900/6250] eta: 0:14:09 lr: 0.000012 grad: 0.1309 (0.1321) loss: 0.8104 (0.8149) time: 0.1676 data: 0.0750 max mem: 9390 +Train: [81] [2000/6250] eta: 0:13:45 lr: 0.000012 grad: 0.1252 (0.1320) loss: 0.8067 (0.8146) time: 0.1607 data: 0.0806 max mem: 9390 +Train: [81] [2100/6250] eta: 0:13:24 lr: 0.000012 grad: 0.1207 (0.1320) loss: 0.8140 (0.8144) time: 0.2418 data: 0.1493 max mem: 9390 +Train: [81] [2200/6250] eta: 0:13:08 lr: 0.000012 grad: 0.1321 (0.1318) loss: 0.8140 (0.8144) time: 0.2717 data: 0.1593 max mem: 9390 +Train: [81] [2300/6250] eta: 0:12:44 lr: 0.000011 grad: 0.1215 (0.1317) loss: 0.8143 (0.8144) time: 0.1832 data: 0.0925 max mem: 9390 +Train: [81] [2400/6250] eta: 0:12:24 lr: 0.000011 grad: 0.1276 (0.1316) loss: 0.8075 (0.8142) time: 0.1417 data: 0.0430 max mem: 9390 +Train: [81] [2500/6250] eta: 0:12:08 lr: 0.000011 grad: 0.1363 (0.1316) loss: 0.8048 (0.8141) time: 0.2139 data: 0.1163 max mem: 9390 +Train: [81] [2600/6250] eta: 0:11:45 lr: 0.000011 grad: 0.1261 (0.1315) loss: 0.8205 (0.8141) time: 0.1747 data: 0.0880 max mem: 9390 +Train: [81] [2700/6250] eta: 0:11:29 lr: 0.000011 grad: 0.1334 (0.1315) loss: 0.8159 (0.8141) time: 0.3303 data: 0.2348 max mem: 9390 +Train: [81] [2800/6250] eta: 0:11:05 lr: 0.000011 grad: 0.1288 (0.1317) loss: 0.8133 (0.8141) time: 0.1922 data: 0.1090 max mem: 9390 +Train: [81] [2900/6250] eta: 0:10:43 lr: 0.000011 grad: 0.1281 (0.1317) loss: 0.8223 (0.8141) time: 0.1445 data: 0.0605 max mem: 9390 +Train: [81] [3000/6250] eta: 0:10:24 lr: 0.000011 grad: 0.1337 (0.1318) loss: 0.8104 (0.8140) time: 0.1714 data: 0.0683 max mem: 9390 +Train: [81] [3100/6250] eta: 0:10:05 lr: 0.000011 grad: 0.1328 (0.1318) loss: 0.8188 (0.8141) time: 0.2180 data: 0.1243 max mem: 9390 +Train: [81] [3200/6250] eta: 0:09:44 lr: 0.000011 grad: 0.1269 (0.1318) loss: 0.8129 (0.8140) time: 0.1558 data: 0.0545 max mem: 9390 +Train: [81] [3300/6250] eta: 0:09:23 lr: 0.000011 grad: 0.1375 (0.1319) loss: 0.8127 (0.8140) time: 0.1847 data: 0.1012 max mem: 9390 +Train: [81] [3400/6250] eta: 0:09:03 lr: 0.000011 grad: 0.1307 (0.1320) loss: 0.8123 (0.8139) time: 0.2087 data: 0.1262 max mem: 9390 +Train: [81] [3500/6250] eta: 0:08:43 lr: 0.000011 grad: 0.1292 (0.1320) loss: 0.8108 (0.8139) time: 0.2056 data: 0.1019 max mem: 9390 +Train: [81] [3600/6250] eta: 0:08:24 lr: 0.000011 grad: 0.1344 (0.1319) loss: 0.8131 (0.8139) time: 0.1201 data: 0.0003 max mem: 9390 +Train: [81] [3700/6250] eta: 0:08:06 lr: 0.000011 grad: 0.1238 (0.1319) loss: 0.8134 (0.8139) time: 0.1920 data: 0.1080 max mem: 9390 +Train: [81] [3800/6250] eta: 0:07:45 lr: 0.000011 grad: 0.1326 (0.1319) loss: 0.8118 (0.8139) time: 0.1951 data: 0.1106 max mem: 9390 +Train: [81] [3900/6250] eta: 0:07:24 lr: 0.000011 grad: 0.1278 (0.1319) loss: 0.8140 (0.8140) time: 0.1716 data: 0.0887 max mem: 9390 +Train: [81] [4000/6250] eta: 0:07:05 lr: 0.000011 grad: 0.1303 (0.1319) loss: 0.8082 (0.8139) time: 0.1512 data: 0.0675 max mem: 9390 +Train: [81] [4100/6250] eta: 0:06:45 lr: 0.000011 grad: 0.1315 (0.1320) loss: 0.8092 (0.8139) time: 0.1850 data: 0.1035 max mem: 9390 +Train: [81] [4200/6250] eta: 0:06:29 lr: 0.000011 grad: 0.1357 (0.1320) loss: 0.8074 (0.8139) time: 0.1274 data: 0.0256 max mem: 9390 +Train: [81] [4300/6250] eta: 0:06:09 lr: 0.000011 grad: 0.1255 (0.1321) loss: 0.8133 (0.8138) time: 0.1587 data: 0.0662 max mem: 9390 +Train: [81] [4400/6250] eta: 0:05:55 lr: 0.000011 grad: 0.1337 (0.1320) loss: 0.8170 (0.8139) time: 0.6772 data: 0.5823 max mem: 9390 +Train: [81] [4500/6250] eta: 0:05:35 lr: 0.000011 grad: 0.1326 (0.1321) loss: 0.8080 (0.8139) time: 0.1357 data: 0.0433 max mem: 9390 +Train: [81] [4600/6250] eta: 0:05:16 lr: 0.000011 grad: 0.1299 (0.1322) loss: 0.8131 (0.8139) time: 0.1890 data: 0.0890 max mem: 9390 +Train: [81] [4700/6250] eta: 0:04:57 lr: 0.000011 grad: 0.1281 (0.1322) loss: 0.8169 (0.8139) time: 0.2985 data: 0.1980 max mem: 9390 +Train: [81] [4800/6250] eta: 0:04:37 lr: 0.000011 grad: 0.1336 (0.1322) loss: 0.8101 (0.8139) time: 0.1928 data: 0.1088 max mem: 9390 +Train: [81] [4900/6250] eta: 0:04:18 lr: 0.000011 grad: 0.1284 (0.1322) loss: 0.8137 (0.8139) time: 0.1382 data: 0.0132 max mem: 9390 +Train: [81] [5000/6250] eta: 0:03:58 lr: 0.000011 grad: 0.1328 (0.1322) loss: 0.8098 (0.8139) time: 0.1772 data: 0.0839 max mem: 9390 +Train: [81] [5100/6250] eta: 0:03:39 lr: 0.000011 grad: 0.1268 (0.1322) loss: 0.8208 (0.8140) time: 0.1938 data: 0.1064 max mem: 9390 +Train: [81] [5200/6250] eta: 0:03:20 lr: 0.000011 grad: 0.1320 (0.1321) loss: 0.8100 (0.8140) time: 0.1549 data: 0.0478 max mem: 9390 +Train: [81] [5300/6250] eta: 0:03:01 lr: 0.000011 grad: 0.1240 (0.1321) loss: 0.8195 (0.8140) time: 0.1613 data: 0.0667 max mem: 9390 +Train: [81] [5400/6250] eta: 0:02:42 lr: 0.000011 grad: 0.1240 (0.1321) loss: 0.8185 (0.8140) time: 0.1450 data: 0.0477 max mem: 9390 +Train: [81] [5500/6250] eta: 0:02:23 lr: 0.000011 grad: 0.1239 (0.1321) loss: 0.8096 (0.8140) time: 0.1808 data: 0.0966 max mem: 9390 +Train: [81] [5600/6250] eta: 0:02:04 lr: 0.000011 grad: 0.1354 (0.1322) loss: 0.8097 (0.8140) time: 0.2103 data: 0.1217 max mem: 9390 +Train: [81] [5700/6250] eta: 0:01:45 lr: 0.000011 grad: 0.1295 (0.1322) loss: 0.8137 (0.8140) time: 0.2020 data: 0.1252 max mem: 9390 +Train: [81] [5800/6250] eta: 0:01:26 lr: 0.000011 grad: 0.1233 (0.1322) loss: 0.8132 (0.8140) time: 0.1882 data: 0.0965 max mem: 9390 +Train: [81] [5900/6250] eta: 0:01:06 lr: 0.000011 grad: 0.1269 (0.1322) loss: 0.8129 (0.8140) time: 0.1655 data: 0.0810 max mem: 9390 +Train: [81] [6000/6250] eta: 0:00:47 lr: 0.000011 grad: 0.1241 (0.1322) loss: 0.8130 (0.8140) time: 0.1929 data: 0.1065 max mem: 9390 +Train: [81] [6100/6250] eta: 0:00:28 lr: 0.000011 grad: 0.1256 (0.1322) loss: 0.8166 (0.8141) time: 0.1632 data: 0.0792 max mem: 9390 +Train: [81] [6200/6250] eta: 0:00:09 lr: 0.000011 grad: 0.1222 (0.1322) loss: 0.8105 (0.8141) time: 0.1540 data: 0.0681 max mem: 9390 +Train: [81] [6249/6250] eta: 0:00:00 lr: 0.000011 grad: 0.1309 (0.1322) loss: 0.8117 (0.8141) time: 0.1432 data: 0.0441 max mem: 9390 +Train: [81] Total time: 0:19:54 (0.1911 s / it) +Averaged stats: lr: 0.000011 grad: 0.1309 (0.1322) loss: 0.8117 (0.8141) +Eval (hcp-train-subset): [81] [ 0/62] eta: 0:03:30 loss: 0.8299 (0.8299) time: 3.3932 data: 3.2792 max mem: 9390 +Eval (hcp-train-subset): [81] [61/62] eta: 0:00:00 loss: 0.8225 (0.8249) time: 0.1540 data: 0.1264 max mem: 9390 +Eval (hcp-train-subset): [81] Total time: 0:00:14 (0.2265 s / it) +Averaged stats (hcp-train-subset): loss: 0.8225 (0.8249) +Eval (hcp-val): [81] [ 0/62] eta: 0:05:14 loss: 0.8307 (0.8307) time: 5.0799 data: 5.0285 max mem: 9390 +Eval (hcp-val): [81] [61/62] eta: 0:00:00 loss: 0.8290 (0.8302) time: 0.1335 data: 0.1084 max mem: 9390 +Eval (hcp-val): [81] Total time: 0:00:14 (0.2333 s / it) +Averaged stats (hcp-val): loss: 0.8290 (0.8302) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +Train: [82] [ 0/6250] eta: 12:24:09 lr: 0.000011 grad: 0.3909 (0.3909) loss: 0.8168 (0.8168) time: 7.1439 data: 6.9785 max mem: 9390 +Train: [82] [ 100/6250] eta: 0:24:28 lr: 0.000011 grad: 0.1531 (0.1809) loss: 0.8222 (0.8224) time: 0.1904 data: 0.0653 max mem: 9390 +Train: [82] [ 200/6250] eta: 0:21:45 lr: 0.000011 grad: 0.1401 (0.1589) loss: 0.8232 (0.8247) time: 0.1970 data: 0.1058 max mem: 9390 +Train: [82] [ 300/6250] eta: 0:20:45 lr: 0.000011 grad: 0.1375 (0.1540) loss: 0.8174 (0.8233) time: 0.2504 data: 0.1525 max mem: 9390 +Train: [82] [ 400/6250] eta: 0:19:45 lr: 0.000011 grad: 0.1295 (0.1499) loss: 0.8141 (0.8217) time: 0.1679 data: 0.0695 max mem: 9390 +Train: [82] [ 500/6250] eta: 0:19:04 lr: 0.000011 grad: 0.1281 (0.1460) loss: 0.8182 (0.8207) time: 0.1888 data: 0.0948 max mem: 9390 +Train: [82] [ 600/6250] eta: 0:18:36 lr: 0.000011 grad: 0.1371 (0.1442) loss: 0.8141 (0.8195) time: 0.2114 data: 0.1218 max mem: 9390 +Train: [82] [ 700/6250] eta: 0:18:04 lr: 0.000011 grad: 0.1255 (0.1425) loss: 0.8123 (0.8182) time: 0.1041 data: 0.0004 max mem: 9390 +Train: [82] [ 800/6250] eta: 0:17:32 lr: 0.000011 grad: 0.1249 (0.1408) loss: 0.8185 (0.8175) time: 0.1732 data: 0.0790 max mem: 9390 +Train: [82] [ 900/6250] eta: 0:17:32 lr: 0.000011 grad: 0.1293 (0.1400) loss: 0.8113 (0.8165) time: 0.1927 data: 0.0950 max mem: 9390 +Train: [82] [1000/6250] eta: 0:17:13 lr: 0.000011 grad: 0.1188 (0.1391) loss: 0.8115 (0.8161) time: 0.2056 data: 0.1115 max mem: 9390 +Train: [82] [1100/6250] eta: 0:16:34 lr: 0.000011 grad: 0.1289 (0.1385) loss: 0.8061 (0.8156) time: 0.1718 data: 0.0907 max mem: 9390 +Train: [82] [1200/6250] eta: 0:16:17 lr: 0.000011 grad: 0.1274 (0.1379) loss: 0.8057 (0.8150) time: 0.2122 data: 0.1116 max mem: 9390 +Train: [82] [1300/6250] eta: 0:15:50 lr: 0.000011 grad: 0.1377 (0.1373) loss: 0.8099 (0.8146) time: 0.1541 data: 0.0479 max mem: 9390 +Train: [82] [1400/6250] eta: 0:15:24 lr: 0.000010 grad: 0.1266 (0.1370) loss: 0.8077 (0.8143) time: 0.1723 data: 0.0858 max mem: 9390 +Train: [82] [1500/6250] eta: 0:15:02 lr: 0.000010 grad: 0.1202 (0.1364) loss: 0.8173 (0.8141) time: 0.1981 data: 0.1128 max mem: 9390 +Train: [82] [1600/6250] eta: 0:14:42 lr: 0.000010 grad: 0.1181 (0.1358) loss: 0.8208 (0.8140) time: 0.1347 data: 0.0560 max mem: 9390 +Train: [82] [1700/6250] eta: 0:14:19 lr: 0.000010 grad: 0.1292 (0.1354) loss: 0.8053 (0.8139) time: 0.1926 data: 0.1140 max mem: 9390 +Train: [82] [1800/6250] eta: 0:13:57 lr: 0.000010 grad: 0.1274 (0.1355) loss: 0.8131 (0.8138) time: 0.1581 data: 0.0642 max mem: 9390 +Train: [82] [1900/6250] eta: 0:13:39 lr: 0.000010 grad: 0.1344 (0.1353) loss: 0.8122 (0.8137) time: 0.2195 data: 0.1377 max mem: 9390 +Train: [82] [2000/6250] eta: 0:13:15 lr: 0.000010 grad: 0.1309 (0.1349) loss: 0.8190 (0.8136) time: 0.1797 data: 0.0956 max mem: 9390 +Train: [82] [2100/6250] eta: 0:12:57 lr: 0.000010 grad: 0.1196 (0.1347) loss: 0.8163 (0.8136) time: 0.1956 data: 0.1093 max mem: 9390 +Train: [82] [2200/6250] eta: 0:12:34 lr: 0.000010 grad: 0.1224 (0.1346) loss: 0.8118 (0.8136) time: 0.1492 data: 0.0560 max mem: 9390 +Train: [82] [2300/6250] eta: 0:12:15 lr: 0.000010 grad: 0.1336 (0.1344) loss: 0.8094 (0.8135) time: 0.1520 data: 0.0596 max mem: 9390 +Train: [82] [2400/6250] eta: 0:11:55 lr: 0.000010 grad: 0.1288 (0.1343) loss: 0.8106 (0.8135) time: 0.1869 data: 0.0919 max mem: 9390 +Train: [82] [2500/6250] eta: 0:11:38 lr: 0.000010 grad: 0.1259 (0.1341) loss: 0.8108 (0.8135) time: 0.1198 data: 0.0003 max mem: 9390 +Train: [82] [2600/6250] eta: 0:11:18 lr: 0.000010 grad: 0.1169 (0.1338) loss: 0.8173 (0.8136) time: 0.1702 data: 0.0852 max mem: 9390 +Train: [82] [2700/6250] eta: 0:10:59 lr: 0.000010 grad: 0.1236 (0.1337) loss: 0.8177 (0.8136) time: 0.1690 data: 0.0766 max mem: 9390 +Train: [82] [2800/6250] eta: 0:10:38 lr: 0.000010 grad: 0.1252 (0.1337) loss: 0.8149 (0.8136) time: 0.1570 data: 0.0756 max mem: 9390 +Train: [82] [2900/6250] eta: 0:10:21 lr: 0.000010 grad: 0.1357 (0.1336) loss: 0.8123 (0.8135) time: 0.1815 data: 0.0851 max mem: 9390 +Train: [82] [3000/6250] eta: 0:10:04 lr: 0.000010 grad: 0.1376 (0.1335) loss: 0.8115 (0.8134) time: 0.1384 data: 0.0137 max mem: 9390 +Train: [82] [3100/6250] eta: 0:09:48 lr: 0.000010 grad: 0.1216 (0.1333) loss: 0.8112 (0.8134) time: 0.2441 data: 0.1586 max mem: 9390 +Train: [82] [3200/6250] eta: 0:09:27 lr: 0.000010 grad: 0.1321 (0.1333) loss: 0.8096 (0.8133) time: 0.1969 data: 0.1153 max mem: 9390 +Train: [82] [3300/6250] eta: 0:09:07 lr: 0.000010 grad: 0.1228 (0.1332) loss: 0.8133 (0.8133) time: 0.1718 data: 0.0895 max mem: 9390 +Train: [82] [3400/6250] eta: 0:08:47 lr: 0.000010 grad: 0.1271 (0.1330) loss: 0.8116 (0.8133) time: 0.1574 data: 0.0710 max mem: 9390 +Train: [82] [3500/6250] eta: 0:08:31 lr: 0.000010 grad: 0.1231 (0.1330) loss: 0.8138 (0.8132) time: 0.2735 data: 0.1839 max mem: 9390 +Train: [82] [3600/6250] eta: 0:08:13 lr: 0.000010 grad: 0.1269 (0.1329) loss: 0.8098 (0.8133) time: 0.2746 data: 0.1759 max mem: 9390 +Train: [82] [3700/6250] eta: 0:07:55 lr: 0.000010 grad: 0.1213 (0.1327) loss: 0.8088 (0.8133) time: 0.1883 data: 0.0698 max mem: 9390 +Train: [82] [3800/6250] eta: 0:07:38 lr: 0.000010 grad: 0.1223 (0.1326) loss: 0.8146 (0.8133) time: 0.1995 data: 0.0720 max mem: 9390 +Train: [82] [3900/6250] eta: 0:07:18 lr: 0.000010 grad: 0.1266 (0.1325) loss: 0.8131 (0.8134) time: 0.1592 data: 0.0707 max mem: 9390 +Train: [82] [4000/6250] eta: 0:06:58 lr: 0.000010 grad: 0.1285 (0.1324) loss: 0.8176 (0.8134) time: 0.1646 data: 0.0776 max mem: 9390 +Train: [82] [4100/6250] eta: 0:06:41 lr: 0.000010 grad: 0.1224 (0.1323) loss: 0.8130 (0.8135) time: 0.1121 data: 0.0003 max mem: 9390 +Train: [82] [4200/6250] eta: 0:06:24 lr: 0.000010 grad: 0.1256 (0.1322) loss: 0.8121 (0.8135) time: 0.3117 data: 0.2204 max mem: 9390 +Train: [82] [4300/6250] eta: 0:06:04 lr: 0.000010 grad: 0.1228 (0.1321) loss: 0.8176 (0.8136) time: 0.1980 data: 0.1090 max mem: 9390 +Train: [82] [4400/6250] eta: 0:05:46 lr: 0.000010 grad: 0.1356 (0.1322) loss: 0.8150 (0.8137) time: 0.2456 data: 0.1630 max mem: 9390 +Train: [82] [4500/6250] eta: 0:05:27 lr: 0.000010 grad: 0.1295 (0.1322) loss: 0.8197 (0.8137) time: 0.1681 data: 0.0897 max mem: 9390 +Train: [82] [4600/6250] eta: 0:05:08 lr: 0.000010 grad: 0.1278 (0.1323) loss: 0.8140 (0.8137) time: 0.1829 data: 0.0823 max mem: 9390 +Train: [82] [4700/6250] eta: 0:04:49 lr: 0.000010 grad: 0.1291 (0.1322) loss: 0.8159 (0.8138) time: 0.1700 data: 0.0750 max mem: 9390 +Train: [82] [4800/6250] eta: 0:04:30 lr: 0.000010 grad: 0.1321 (0.1322) loss: 0.8134 (0.8138) time: 0.2142 data: 0.1226 max mem: 9390 +Train: [82] [4900/6250] eta: 0:04:12 lr: 0.000010 grad: 0.1343 (0.1322) loss: 0.8108 (0.8138) time: 0.3036 data: 0.1949 max mem: 9390 +Train: [82] [5000/6250] eta: 0:03:54 lr: 0.000010 grad: 0.1338 (0.1322) loss: 0.8123 (0.8137) time: 0.2984 data: 0.1846 max mem: 9390 +Train: [82] [5100/6250] eta: 0:03:35 lr: 0.000010 grad: 0.1279 (0.1322) loss: 0.8127 (0.8137) time: 0.1511 data: 0.0529 max mem: 9390 +Train: [82] [5200/6250] eta: 0:03:16 lr: 0.000010 grad: 0.1318 (0.1323) loss: 0.8135 (0.8137) time: 0.1338 data: 0.0474 max mem: 9390 +Train: [82] [5300/6250] eta: 0:02:57 lr: 0.000010 grad: 0.1372 (0.1323) loss: 0.8069 (0.8137) time: 0.2999 data: 0.2265 max mem: 9390 +Train: [82] [5400/6250] eta: 0:02:38 lr: 0.000010 grad: 0.1224 (0.1322) loss: 0.8176 (0.8137) time: 0.1682 data: 0.0823 max mem: 9390 +Train: [82] [5500/6250] eta: 0:02:20 lr: 0.000010 grad: 0.1315 (0.1323) loss: 0.8063 (0.8136) time: 0.2103 data: 0.1302 max mem: 9390 +Train: [82] [5600/6250] eta: 0:02:01 lr: 0.000010 grad: 0.1297 (0.1323) loss: 0.8146 (0.8136) time: 0.1580 data: 0.0622 max mem: 9390 +Train: [82] [5700/6250] eta: 0:01:42 lr: 0.000010 grad: 0.1290 (0.1322) loss: 0.8117 (0.8135) time: 0.1728 data: 0.0875 max mem: 9390 +Train: [82] [5800/6250] eta: 0:01:23 lr: 0.000010 grad: 0.1320 (0.1322) loss: 0.8115 (0.8135) time: 0.1873 data: 0.1010 max mem: 9390 +Train: [82] [5900/6250] eta: 0:01:05 lr: 0.000010 grad: 0.1249 (0.1322) loss: 0.8107 (0.8134) time: 0.1759 data: 0.0800 max mem: 9390 +Train: [82] [6000/6250] eta: 0:00:46 lr: 0.000010 grad: 0.1302 (0.1323) loss: 0.8125 (0.8134) time: 0.1712 data: 0.0818 max mem: 9390 +Train: [82] [6100/6250] eta: 0:00:27 lr: 0.000010 grad: 0.1359 (0.1324) loss: 0.8056 (0.8133) time: 0.2078 data: 0.1224 max mem: 9390 +Train: [82] [6200/6250] eta: 0:00:09 lr: 0.000010 grad: 0.1403 (0.1325) loss: 0.8081 (0.8132) time: 0.1720 data: 0.0797 max mem: 9390 +Train: [82] [6249/6250] eta: 0:00:00 lr: 0.000010 grad: 0.1335 (0.1325) loss: 0.8121 (0.8132) time: 0.1884 data: 0.0987 max mem: 9390 +Train: [82] Total time: 0:19:25 (0.1864 s / it) +Averaged stats: lr: 0.000010 grad: 0.1335 (0.1325) loss: 0.8121 (0.8132) +Eval (hcp-train-subset): [82] [ 0/62] eta: 0:04:57 loss: 0.8292 (0.8292) time: 4.8053 data: 4.7731 max mem: 9390 +Eval (hcp-train-subset): [82] [61/62] eta: 0:00:00 loss: 0.8221 (0.8243) time: 0.1345 data: 0.1089 max mem: 9390 +Eval (hcp-train-subset): [82] Total time: 0:00:14 (0.2317 s / it) +Averaged stats (hcp-train-subset): loss: 0.8221 (0.8243) +Eval (hcp-val): [82] [ 0/62] eta: 0:05:21 loss: 0.8279 (0.8279) time: 5.1836 data: 5.1496 max mem: 9390 +Eval (hcp-val): [82] [61/62] eta: 0:00:00 loss: 0.8282 (0.8299) time: 0.1452 data: 0.1191 max mem: 9390 +Eval (hcp-val): [82] Total time: 0:00:14 (0.2281 s / it) +Averaged stats (hcp-val): loss: 0.8282 (0.8299) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +Train: [83] [ 0/6250] eta: 9:06:59 lr: 0.000010 grad: 0.1090 (0.1090) loss: 0.8524 (0.8524) time: 5.2511 data: 5.0411 max mem: 9390 +Train: [83] [ 100/6250] eta: 0:23:06 lr: 0.000010 grad: 0.1261 (0.1405) loss: 0.8274 (0.8350) time: 0.1670 data: 0.0624 max mem: 9390 +Train: [83] [ 200/6250] eta: 0:20:43 lr: 0.000010 grad: 0.1345 (0.1371) loss: 0.8189 (0.8298) time: 0.1886 data: 0.0761 max mem: 9390 +Train: [83] [ 300/6250] eta: 0:19:42 lr: 0.000010 grad: 0.1233 (0.1345) loss: 0.8260 (0.8281) time: 0.1934 data: 0.0934 max mem: 9390 +Train: [83] [ 400/6250] eta: 0:18:55 lr: 0.000010 grad: 0.1275 (0.1352) loss: 0.8224 (0.8261) time: 0.1209 data: 0.0181 max mem: 9390 +Train: [83] [ 500/6250] eta: 0:18:40 lr: 0.000010 grad: 0.1274 (0.1344) loss: 0.8165 (0.8250) time: 0.2683 data: 0.1824 max mem: 9390 +Train: [83] [ 600/6250] eta: 0:17:53 lr: 0.000010 grad: 0.1347 (0.1348) loss: 0.8168 (0.8235) time: 0.1706 data: 0.0765 max mem: 9390 +Train: [83] [ 700/6250] eta: 0:17:25 lr: 0.000009 grad: 0.1297 (0.1350) loss: 0.8205 (0.8227) time: 0.1377 data: 0.0554 max mem: 9390 +Train: [83] [ 800/6250] eta: 0:17:16 lr: 0.000009 grad: 0.1354 (0.1347) loss: 0.8100 (0.8221) time: 0.2195 data: 0.1290 max mem: 9390 +Train: [83] [ 900/6250] eta: 0:16:59 lr: 0.000009 grad: 0.1374 (0.1349) loss: 0.8130 (0.8214) time: 0.2007 data: 0.1197 max mem: 9390 +Train: [83] [1000/6250] eta: 0:16:39 lr: 0.000009 grad: 0.1234 (0.1344) loss: 0.8189 (0.8208) time: 0.1632 data: 0.0687 max mem: 9390 +Train: [83] [1100/6250] eta: 0:16:20 lr: 0.000009 grad: 0.1289 (0.1341) loss: 0.8212 (0.8205) time: 0.2140 data: 0.1230 max mem: 9390 +Train: [83] [1200/6250] eta: 0:16:18 lr: 0.000009 grad: 0.1345 (0.1339) loss: 0.8108 (0.8201) time: 0.2478 data: 0.1333 max mem: 9390 +Train: [83] [1300/6250] eta: 0:15:59 lr: 0.000009 grad: 0.1281 (0.1337) loss: 0.8148 (0.8197) time: 0.2089 data: 0.1114 max mem: 9390 +Train: [83] [1400/6250] eta: 0:15:34 lr: 0.000009 grad: 0.1353 (0.1335) loss: 0.8093 (0.8192) time: 0.1860 data: 0.0881 max mem: 9390 +Train: [83] [1500/6250] eta: 0:15:19 lr: 0.000009 grad: 0.1262 (0.1334) loss: 0.8146 (0.8188) time: 0.1371 data: 0.0341 max mem: 9390 +Train: [83] [1600/6250] eta: 0:14:53 lr: 0.000009 grad: 0.1338 (0.1335) loss: 0.8092 (0.8183) time: 0.1514 data: 0.0605 max mem: 9390 +Train: [83] [1700/6250] eta: 0:14:31 lr: 0.000009 grad: 0.1239 (0.1335) loss: 0.8182 (0.8180) time: 0.1661 data: 0.0708 max mem: 9390 +Train: [83] [1800/6250] eta: 0:14:08 lr: 0.000009 grad: 0.1225 (0.1334) loss: 0.8124 (0.8179) time: 0.1859 data: 0.0933 max mem: 9390 +Train: [83] [1900/6250] eta: 0:13:43 lr: 0.000009 grad: 0.1356 (0.1335) loss: 0.8116 (0.8176) time: 0.1598 data: 0.0683 max mem: 9390 +Train: [83] [2000/6250] eta: 0:13:22 lr: 0.000009 grad: 0.1235 (0.1335) loss: 0.8146 (0.8173) time: 0.1383 data: 0.0533 max mem: 9390 +Train: [83] [2100/6250] eta: 0:13:09 lr: 0.000009 grad: 0.1245 (0.1333) loss: 0.8159 (0.8172) time: 0.2018 data: 0.1134 max mem: 9390 +Train: [83] [2200/6250] eta: 0:12:45 lr: 0.000009 grad: 0.1306 (0.1332) loss: 0.8146 (0.8170) time: 0.1763 data: 0.0846 max mem: 9390 +Train: [83] [2300/6250] eta: 0:12:27 lr: 0.000009 grad: 0.1210 (0.1330) loss: 0.8202 (0.8169) time: 0.2106 data: 0.1250 max mem: 9390 +Train: [83] [2400/6250] eta: 0:12:10 lr: 0.000009 grad: 0.1296 (0.1329) loss: 0.8147 (0.8168) time: 0.1067 data: 0.0012 max mem: 9390 +Train: [83] [2500/6250] eta: 0:11:48 lr: 0.000009 grad: 0.1349 (0.1328) loss: 0.8127 (0.8167) time: 0.1652 data: 0.0769 max mem: 9390 +Train: [83] [2600/6250] eta: 0:11:28 lr: 0.000009 grad: 0.1361 (0.1329) loss: 0.8076 (0.8163) time: 0.1731 data: 0.0757 max mem: 9390 +Train: [83] [2700/6250] eta: 0:11:15 lr: 0.000009 grad: 0.1350 (0.1329) loss: 0.8106 (0.8162) time: 0.3197 data: 0.2161 max mem: 9390 +Train: [83] [2800/6250] eta: 0:10:55 lr: 0.000009 grad: 0.1335 (0.1330) loss: 0.8104 (0.8161) time: 0.2688 data: 0.1765 max mem: 9390 +Train: [83] [2900/6250] eta: 0:10:33 lr: 0.000009 grad: 0.1265 (0.1331) loss: 0.8160 (0.8159) time: 0.1895 data: 0.0935 max mem: 9390 +Train: [83] [3000/6250] eta: 0:10:18 lr: 0.000009 grad: 0.1312 (0.1332) loss: 0.8062 (0.8157) time: 0.3179 data: 0.2198 max mem: 9390 +Train: [83] [3100/6250] eta: 0:09:55 lr: 0.000009 grad: 0.1337 (0.1332) loss: 0.8110 (0.8155) time: 0.2044 data: 0.1227 max mem: 9390 +Train: [83] [3200/6250] eta: 0:09:36 lr: 0.000009 grad: 0.1319 (0.1332) loss: 0.8157 (0.8154) time: 0.1543 data: 0.0681 max mem: 9390 +Train: [83] [3300/6250] eta: 0:09:28 lr: 0.000009 grad: 0.1313 (0.1332) loss: 0.8088 (0.8153) time: 0.1746 data: 0.0538 max mem: 9390 +Train: [83] [3400/6250] eta: 0:09:07 lr: 0.000009 grad: 0.1266 (0.1332) loss: 0.8120 (0.8151) time: 0.2126 data: 0.1261 max mem: 9390 +Train: [83] [3500/6250] eta: 0:08:46 lr: 0.000009 grad: 0.1384 (0.1334) loss: 0.8035 (0.8148) time: 0.1497 data: 0.0646 max mem: 9390 +Train: [83] [3600/6250] eta: 0:08:24 lr: 0.000009 grad: 0.1277 (0.1333) loss: 0.8064 (0.8147) time: 0.1217 data: 0.0294 max mem: 9390 +Train: [83] [3700/6250] eta: 0:08:04 lr: 0.000009 grad: 0.1349 (0.1333) loss: 0.8051 (0.8145) time: 0.1188 data: 0.0232 max mem: 9390 +Train: [83] [3800/6250] eta: 0:07:44 lr: 0.000009 grad: 0.1236 (0.1333) loss: 0.8088 (0.8144) time: 0.1463 data: 0.0487 max mem: 9390 +Train: [83] [3900/6250] eta: 0:07:24 lr: 0.000009 grad: 0.1208 (0.1332) loss: 0.8137 (0.8143) time: 0.2341 data: 0.1347 max mem: 9390 +Train: [83] [4000/6250] eta: 0:07:05 lr: 0.000009 grad: 0.1302 (0.1332) loss: 0.8187 (0.8142) time: 0.2541 data: 0.1797 max mem: 9390 +Train: [83] [4100/6250] eta: 0:06:46 lr: 0.000009 grad: 0.1315 (0.1332) loss: 0.8066 (0.8141) time: 0.1554 data: 0.0539 max mem: 9390 +Train: [83] [4200/6250] eta: 0:06:26 lr: 0.000009 grad: 0.1267 (0.1332) loss: 0.8098 (0.8140) time: 0.1635 data: 0.0676 max mem: 9390 +Train: [83] [4300/6250] eta: 0:06:07 lr: 0.000009 grad: 0.1317 (0.1331) loss: 0.8130 (0.8140) time: 0.1875 data: 0.0992 max mem: 9390 +Train: [83] [4400/6250] eta: 0:05:47 lr: 0.000009 grad: 0.1226 (0.1330) loss: 0.8159 (0.8140) time: 0.1606 data: 0.0758 max mem: 9390 +Train: [83] [4500/6250] eta: 0:05:28 lr: 0.000009 grad: 0.1248 (0.1330) loss: 0.8167 (0.8140) time: 0.1365 data: 0.0303 max mem: 9390 +Train: [83] [4600/6250] eta: 0:05:09 lr: 0.000009 grad: 0.1177 (0.1329) loss: 0.8184 (0.8141) time: 0.1695 data: 0.0831 max mem: 9390 +Train: [83] [4700/6250] eta: 0:04:50 lr: 0.000009 grad: 0.1290 (0.1328) loss: 0.8174 (0.8142) time: 0.1707 data: 0.0811 max mem: 9390 +Train: [83] [4800/6250] eta: 0:04:31 lr: 0.000009 grad: 0.1292 (0.1327) loss: 0.8149 (0.8142) time: 0.1626 data: 0.0727 max mem: 9390 +Train: [83] [4900/6250] eta: 0:04:12 lr: 0.000009 grad: 0.1234 (0.1327) loss: 0.8144 (0.8142) time: 0.1029 data: 0.0003 max mem: 9390 +Train: [83] [5000/6250] eta: 0:03:53 lr: 0.000009 grad: 0.1220 (0.1326) loss: 0.8157 (0.8142) time: 0.1657 data: 0.0719 max mem: 9390 +Train: [83] [5100/6250] eta: 0:03:34 lr: 0.000009 grad: 0.1239 (0.1325) loss: 0.8168 (0.8142) time: 0.1774 data: 0.0975 max mem: 9390 +Train: [83] [5200/6250] eta: 0:03:15 lr: 0.000009 grad: 0.1306 (0.1325) loss: 0.8180 (0.8143) time: 0.1416 data: 0.0525 max mem: 9390 +Train: [83] [5300/6250] eta: 0:02:56 lr: 0.000009 grad: 0.1273 (0.1324) loss: 0.8182 (0.8143) time: 0.1672 data: 0.0811 max mem: 9390 +Train: [83] [5400/6250] eta: 0:02:38 lr: 0.000009 grad: 0.1225 (0.1323) loss: 0.8177 (0.8143) time: 0.1759 data: 0.1009 max mem: 9390 +Train: [83] [5500/6250] eta: 0:02:19 lr: 0.000009 grad: 0.1241 (0.1322) loss: 0.8166 (0.8144) time: 0.1705 data: 0.0868 max mem: 9390 +Train: [83] [5600/6250] eta: 0:02:00 lr: 0.000009 grad: 0.1307 (0.1321) loss: 0.8123 (0.8144) time: 0.2049 data: 0.1243 max mem: 9390 +Train: [83] [5700/6250] eta: 0:01:42 lr: 0.000009 grad: 0.1255 (0.1322) loss: 0.8126 (0.8144) time: 0.2183 data: 0.1285 max mem: 9390 +Train: [83] [5800/6250] eta: 0:01:23 lr: 0.000009 grad: 0.1280 (0.1321) loss: 0.8097 (0.8144) time: 0.2244 data: 0.1326 max mem: 9390 +Train: [83] [5900/6250] eta: 0:01:05 lr: 0.000009 grad: 0.1360 (0.1321) loss: 0.8061 (0.8143) time: 0.2146 data: 0.1116 max mem: 9390 +Train: [83] [6000/6250] eta: 0:00:46 lr: 0.000009 grad: 0.1288 (0.1321) loss: 0.8128 (0.8143) time: 0.1977 data: 0.1078 max mem: 9390 +Train: [83] [6100/6250] eta: 0:00:28 lr: 0.000009 grad: 0.1282 (0.1321) loss: 0.8134 (0.8143) time: 0.1826 data: 0.0807 max mem: 9390 +Train: [83] [6200/6250] eta: 0:00:09 lr: 0.000009 grad: 0.1282 (0.1322) loss: 0.8092 (0.8142) time: 0.1792 data: 0.0857 max mem: 9390 +Train: [83] [6249/6250] eta: 0:00:00 lr: 0.000009 grad: 0.1387 (0.1322) loss: 0.8077 (0.8141) time: 0.1423 data: 0.0393 max mem: 9390 +Train: [83] Total time: 0:19:36 (0.1882 s / it) +Averaged stats: lr: 0.000009 grad: 0.1387 (0.1322) loss: 0.8077 (0.8141) +Eval (hcp-train-subset): [83] [ 0/62] eta: 0:03:46 loss: 0.8288 (0.8288) time: 3.6504 data: 3.5444 max mem: 9390 +Eval (hcp-train-subset): [83] [61/62] eta: 0:00:00 loss: 0.8211 (0.8239) time: 0.1136 data: 0.0884 max mem: 9390 +Eval (hcp-train-subset): [83] Total time: 0:00:14 (0.2384 s / it) +Averaged stats (hcp-train-subset): loss: 0.8211 (0.8239) +Eval (hcp-val): [83] [ 0/62] eta: 0:03:29 loss: 0.8273 (0.8273) time: 3.3715 data: 3.2665 max mem: 9390 +Eval (hcp-val): [83] [61/62] eta: 0:00:00 loss: 0.8283 (0.8296) time: 0.1237 data: 0.0988 max mem: 9390 +Eval (hcp-val): [83] Total time: 0:00:14 (0.2301 s / it) +Averaged stats (hcp-val): loss: 0.8283 (0.8296) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +Train: [84] [ 0/6250] eta: 10:23:16 lr: 0.000009 grad: 0.0916 (0.0916) loss: 0.8739 (0.8739) time: 5.9835 data: 5.8093 max mem: 9390 +Train: [84] [ 100/6250] eta: 0:23:54 lr: 0.000009 grad: 0.1233 (0.1492) loss: 0.8329 (0.8307) time: 0.1812 data: 0.0662 max mem: 9390 +Train: [84] [ 200/6250] eta: 0:20:34 lr: 0.000009 grad: 0.1266 (0.1447) loss: 0.8341 (0.8294) time: 0.1949 data: 0.0902 max mem: 9390 +Train: [84] [ 300/6250] eta: 0:19:44 lr: 0.000008 grad: 0.1257 (0.1420) loss: 0.8261 (0.8273) time: 0.1972 data: 0.0951 max mem: 9390 +Train: [84] [ 400/6250] eta: 0:19:22 lr: 0.000008 grad: 0.1317 (0.1396) loss: 0.8184 (0.8260) time: 0.2241 data: 0.1285 max mem: 9390 +Train: [84] [ 500/6250] eta: 0:19:10 lr: 0.000008 grad: 0.1162 (0.1372) loss: 0.8156 (0.8253) time: 0.1697 data: 0.0602 max mem: 9390 +Train: [84] [ 600/6250] eta: 0:18:40 lr: 0.000008 grad: 0.1273 (0.1361) loss: 0.8227 (0.8249) time: 0.1850 data: 0.0885 max mem: 9390 +Train: [84] [ 700/6250] eta: 0:18:02 lr: 0.000008 grad: 0.1281 (0.1357) loss: 0.8225 (0.8241) time: 0.1645 data: 0.0807 max mem: 9390 +Train: [84] [ 800/6250] eta: 0:18:05 lr: 0.000008 grad: 0.1293 (0.1352) loss: 0.8178 (0.8233) time: 0.3936 data: 0.2728 max mem: 9390 +Train: [84] [ 900/6250] eta: 0:17:35 lr: 0.000008 grad: 0.1324 (0.1351) loss: 0.8179 (0.8223) time: 0.1380 data: 0.0003 max mem: 9390 +Train: [84] [1000/6250] eta: 0:17:11 lr: 0.000008 grad: 0.1359 (0.1352) loss: 0.8161 (0.8215) time: 0.1256 data: 0.0274 max mem: 9390 +Train: [84] [1100/6250] eta: 0:16:54 lr: 0.000008 grad: 0.1282 (0.1351) loss: 0.8182 (0.8210) time: 0.2365 data: 0.1336 max mem: 9390 +Train: [84] [1200/6250] eta: 0:16:51 lr: 0.000008 grad: 0.1281 (0.1348) loss: 0.8146 (0.8204) time: 0.1051 data: 0.0003 max mem: 9390 +Train: [84] [1300/6250] eta: 0:16:17 lr: 0.000008 grad: 0.1337 (0.1349) loss: 0.8136 (0.8199) time: 0.1737 data: 0.0787 max mem: 9390 +Train: [84] [1400/6250] eta: 0:15:50 lr: 0.000008 grad: 0.1278 (0.1349) loss: 0.8130 (0.8196) time: 0.1049 data: 0.0137 max mem: 9390 +Train: [84] [1500/6250] eta: 0:15:23 lr: 0.000008 grad: 0.1176 (0.1346) loss: 0.8157 (0.8192) time: 0.1679 data: 0.0831 max mem: 9390 +Train: [84] [1600/6250] eta: 0:15:03 lr: 0.000008 grad: 0.1295 (0.1344) loss: 0.8162 (0.8189) time: 0.2672 data: 0.1737 max mem: 9390 +Train: [84] [1700/6250] eta: 0:14:36 lr: 0.000008 grad: 0.1313 (0.1344) loss: 0.8076 (0.8184) time: 0.1636 data: 0.0770 max mem: 9390 +Train: [84] [1800/6250] eta: 0:14:16 lr: 0.000008 grad: 0.1287 (0.1344) loss: 0.8175 (0.8181) time: 0.1040 data: 0.0002 max mem: 9390 +Train: [84] [1900/6250] eta: 0:14:02 lr: 0.000008 grad: 0.1307 (0.1344) loss: 0.8159 (0.8178) time: 0.1070 data: 0.0002 max mem: 9390 +Train: [84] [2000/6250] eta: 0:13:36 lr: 0.000008 grad: 0.1259 (0.1345) loss: 0.8058 (0.8173) time: 0.1479 data: 0.0652 max mem: 9390 +Train: [84] [2100/6250] eta: 0:13:20 lr: 0.000008 grad: 0.1358 (0.1345) loss: 0.8122 (0.8170) time: 0.1671 data: 0.0666 max mem: 9390 +Train: [84] [2200/6250] eta: 0:13:03 lr: 0.000008 grad: 0.1344 (0.1347) loss: 0.8127 (0.8166) time: 0.2946 data: 0.1915 max mem: 9390 +Train: [84] [2300/6250] eta: 0:12:48 lr: 0.000008 grad: 0.1360 (0.1347) loss: 0.8047 (0.8162) time: 0.3954 data: 0.2769 max mem: 9390 +Train: [84] [2400/6250] eta: 0:12:23 lr: 0.000008 grad: 0.1267 (0.1347) loss: 0.8122 (0.8160) time: 0.1865 data: 0.0976 max mem: 9390 +Train: [84] [2500/6250] eta: 0:12:03 lr: 0.000008 grad: 0.1334 (0.1347) loss: 0.8155 (0.8158) time: 0.1022 data: 0.0004 max mem: 9390 +Train: [84] [2600/6250] eta: 0:11:43 lr: 0.000008 grad: 0.1305 (0.1348) loss: 0.8127 (0.8156) time: 0.1862 data: 0.0825 max mem: 9390 +Train: [84] [2700/6250] eta: 0:11:27 lr: 0.000008 grad: 0.1335 (0.1349) loss: 0.8086 (0.8154) time: 0.1622 data: 0.0649 max mem: 9390 +Train: [84] [2800/6250] eta: 0:11:04 lr: 0.000008 grad: 0.1302 (0.1349) loss: 0.8104 (0.8152) time: 0.1889 data: 0.0979 max mem: 9390 +Train: [84] [2900/6250] eta: 0:10:48 lr: 0.000008 grad: 0.1339 (0.1349) loss: 0.8019 (0.8151) time: 0.1676 data: 0.0447 max mem: 9390 +Train: [84] [3000/6250] eta: 0:10:26 lr: 0.000008 grad: 0.1391 (0.1349) loss: 0.8103 (0.8150) time: 0.1121 data: 0.0089 max mem: 9390 +Train: [84] [3100/6250] eta: 0:10:08 lr: 0.000008 grad: 0.1337 (0.1349) loss: 0.8081 (0.8149) time: 0.1735 data: 0.0793 max mem: 9390 +Train: [84] [3200/6250] eta: 0:09:46 lr: 0.000008 grad: 0.1367 (0.1349) loss: 0.8093 (0.8148) time: 0.1778 data: 0.0943 max mem: 9390 +Train: [84] [3300/6250] eta: 0:09:25 lr: 0.000008 grad: 0.1320 (0.1349) loss: 0.8094 (0.8148) time: 0.1619 data: 0.0745 max mem: 9390 +Train: [84] [3400/6250] eta: 0:09:07 lr: 0.000008 grad: 0.1336 (0.1349) loss: 0.8118 (0.8147) time: 0.1809 data: 0.0894 max mem: 9390 +Train: [84] [3500/6250] eta: 0:08:48 lr: 0.000008 grad: 0.1335 (0.1349) loss: 0.8100 (0.8146) time: 0.1385 data: 0.0362 max mem: 9390 +Train: [84] [3600/6250] eta: 0:08:31 lr: 0.000008 grad: 0.1229 (0.1348) loss: 0.8178 (0.8146) time: 0.3693 data: 0.2747 max mem: 9390 +Train: [84] [3700/6250] eta: 0:08:12 lr: 0.000008 grad: 0.1460 (0.1349) loss: 0.8012 (0.8145) time: 0.2894 data: 0.1905 max mem: 9390 +Train: [84] [3800/6250] eta: 0:07:52 lr: 0.000008 grad: 0.1310 (0.1351) loss: 0.8061 (0.8144) time: 0.1997 data: 0.1022 max mem: 9390 +Train: [84] [3900/6250] eta: 0:07:32 lr: 0.000008 grad: 0.1302 (0.1350) loss: 0.8123 (0.8143) time: 0.1492 data: 0.0566 max mem: 9390 +Train: [84] [4000/6250] eta: 0:07:13 lr: 0.000008 grad: 0.1298 (0.1350) loss: 0.8109 (0.8142) time: 0.1485 data: 0.0523 max mem: 9390 +Train: [84] [4100/6250] eta: 0:06:52 lr: 0.000008 grad: 0.1252 (0.1350) loss: 0.8154 (0.8141) time: 0.1585 data: 0.0658 max mem: 9390 +Train: [84] [4200/6250] eta: 0:06:33 lr: 0.000008 grad: 0.1369 (0.1350) loss: 0.8097 (0.8140) time: 0.2334 data: 0.1459 max mem: 9390 +Train: [84] [4300/6250] eta: 0:06:14 lr: 0.000008 grad: 0.1280 (0.1349) loss: 0.8172 (0.8140) time: 0.2060 data: 0.0811 max mem: 9390 +Train: [84] [4400/6250] eta: 0:05:54 lr: 0.000008 grad: 0.1333 (0.1349) loss: 0.8073 (0.8140) time: 0.2267 data: 0.1397 max mem: 9390 +Train: [84] [4500/6250] eta: 0:05:35 lr: 0.000008 grad: 0.1241 (0.1350) loss: 0.8160 (0.8139) time: 0.2907 data: 0.2033 max mem: 9390 +Train: [84] [4600/6250] eta: 0:05:15 lr: 0.000008 grad: 0.1340 (0.1350) loss: 0.8080 (0.8139) time: 0.1642 data: 0.0780 max mem: 9390 +Train: [84] [4700/6250] eta: 0:04:55 lr: 0.000008 grad: 0.1336 (0.1351) loss: 0.8177 (0.8139) time: 0.1550 data: 0.0678 max mem: 9390 +Train: [84] [4800/6250] eta: 0:04:35 lr: 0.000008 grad: 0.1382 (0.1351) loss: 0.8110 (0.8139) time: 0.1319 data: 0.0477 max mem: 9390 +Train: [84] [4900/6250] eta: 0:04:16 lr: 0.000008 grad: 0.1287 (0.1352) loss: 0.8138 (0.8139) time: 0.1654 data: 0.0805 max mem: 9390 +Train: [84] [5000/6250] eta: 0:03:56 lr: 0.000008 grad: 0.1335 (0.1352) loss: 0.8157 (0.8139) time: 0.1585 data: 0.0709 max mem: 9390 +Train: [84] [5100/6250] eta: 0:03:37 lr: 0.000008 grad: 0.1388 (0.1353) loss: 0.8136 (0.8138) time: 0.1816 data: 0.0959 max mem: 9390 +Train: [84] [5200/6250] eta: 0:03:18 lr: 0.000008 grad: 0.1362 (0.1354) loss: 0.8123 (0.8138) time: 0.1688 data: 0.0868 max mem: 9390 +Train: [84] [5300/6250] eta: 0:02:59 lr: 0.000008 grad: 0.1324 (0.1354) loss: 0.8112 (0.8138) time: 0.1836 data: 0.1006 max mem: 9390 +Train: [84] [5400/6250] eta: 0:02:39 lr: 0.000008 grad: 0.1311 (0.1354) loss: 0.8151 (0.8138) time: 0.1590 data: 0.0689 max mem: 9390 +Train: [84] [5500/6250] eta: 0:02:21 lr: 0.000008 grad: 0.1343 (0.1354) loss: 0.8132 (0.8137) time: 0.2073 data: 0.1271 max mem: 9390 +Train: [84] [5600/6250] eta: 0:02:02 lr: 0.000008 grad: 0.1399 (0.1354) loss: 0.8156 (0.8137) time: 0.1951 data: 0.1130 max mem: 9390 +Train: [84] [5700/6250] eta: 0:01:43 lr: 0.000008 grad: 0.1309 (0.1354) loss: 0.8138 (0.8138) time: 0.2056 data: 0.1232 max mem: 9390 +Train: [84] [5800/6250] eta: 0:01:24 lr: 0.000008 grad: 0.1341 (0.1355) loss: 0.8162 (0.8137) time: 0.2301 data: 0.1349 max mem: 9390 +Train: [84] [5900/6250] eta: 0:01:06 lr: 0.000008 grad: 0.1384 (0.1355) loss: 0.8107 (0.8137) time: 0.1990 data: 0.1102 max mem: 9390 +Train: [84] [6000/6250] eta: 0:00:47 lr: 0.000008 grad: 0.1360 (0.1356) loss: 0.8099 (0.8137) time: 0.2095 data: 0.1110 max mem: 9390 +Train: [84] [6100/6250] eta: 0:00:28 lr: 0.000008 grad: 0.1410 (0.1356) loss: 0.8056 (0.8136) time: 0.1664 data: 0.0652 max mem: 9390 +Train: [84] [6200/6250] eta: 0:00:09 lr: 0.000008 grad: 0.1342 (0.1357) loss: 0.8127 (0.8136) time: 0.1846 data: 0.1006 max mem: 9390 +Train: [84] [6249/6250] eta: 0:00:00 lr: 0.000008 grad: 0.1343 (0.1357) loss: 0.8135 (0.8136) time: 0.1685 data: 0.0757 max mem: 9390 +Train: [84] Total time: 0:19:47 (0.1900 s / it) +Averaged stats: lr: 0.000008 grad: 0.1343 (0.1357) loss: 0.8135 (0.8136) +Eval (hcp-train-subset): [84] [ 0/62] eta: 0:05:11 loss: 0.8277 (0.8277) time: 5.0316 data: 4.9929 max mem: 9390 +Eval (hcp-train-subset): [84] [61/62] eta: 0:00:00 loss: 0.8207 (0.8231) time: 0.1300 data: 0.1045 max mem: 9390 +Eval (hcp-train-subset): [84] Total time: 0:00:15 (0.2452 s / it) +Averaged stats (hcp-train-subset): loss: 0.8207 (0.8231) +Making plots (hcp-train-subset): example=32 +Eval (hcp-val): [84] [ 0/62] eta: 0:05:02 loss: 0.8269 (0.8269) time: 4.8789 data: 4.8053 max mem: 9390 +Eval (hcp-val): [84] [61/62] eta: 0:00:00 loss: 0.8279 (0.8297) time: 0.1436 data: 0.1170 max mem: 9390 +Eval (hcp-val): [84] Total time: 0:00:15 (0.2445 s / it) +Averaged stats (hcp-val): loss: 0.8279 (0.8297) +Making plots (hcp-val): example=42 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +Train: [85] [ 0/6250] eta: 9:55:20 lr: 0.000008 grad: 0.5910 (0.5910) loss: 0.8531 (0.8531) time: 5.7153 data: 5.3855 max mem: 9390 +Train: [85] [ 100/6250] eta: 0:26:30 lr: 0.000008 grad: 0.1431 (0.1716) loss: 0.8316 (0.8249) time: 0.1928 data: 0.0791 max mem: 9390 +Train: [85] [ 200/6250] eta: 0:22:47 lr: 0.000008 grad: 0.1324 (0.1593) loss: 0.8172 (0.8210) time: 0.2134 data: 0.1189 max mem: 9390 +Train: [85] [ 300/6250] eta: 0:20:57 lr: 0.000007 grad: 0.1511 (0.1561) loss: 0.8125 (0.8192) time: 0.1854 data: 0.0922 max mem: 9390 +Train: [85] [ 400/6250] eta: 0:20:09 lr: 0.000007 grad: 0.1348 (0.1526) loss: 0.8167 (0.8179) time: 0.1724 data: 0.0609 max mem: 9390 +Train: [85] [ 500/6250] eta: 0:19:47 lr: 0.000007 grad: 0.1256 (0.1491) loss: 0.8182 (0.8177) time: 0.1724 data: 0.0786 max mem: 9390 +Train: [85] [ 600/6250] eta: 0:19:14 lr: 0.000007 grad: 0.1281 (0.1462) loss: 0.8223 (0.8180) time: 0.2336 data: 0.1326 max mem: 9390 +Train: [85] [ 700/6250] eta: 0:18:37 lr: 0.000007 grad: 0.1260 (0.1441) loss: 0.8160 (0.8181) time: 0.1787 data: 0.0917 max mem: 9390 +Train: [85] [ 800/6250] eta: 0:18:32 lr: 0.000007 grad: 0.1221 (0.1422) loss: 0.8226 (0.8180) time: 0.3320 data: 0.2354 max mem: 9390 +Train: [85] [ 900/6250] eta: 0:18:05 lr: 0.000007 grad: 0.1218 (0.1410) loss: 0.8187 (0.8179) time: 0.1983 data: 0.1059 max mem: 9390 +Train: [85] [1000/6250] eta: 0:17:44 lr: 0.000007 grad: 0.1326 (0.1403) loss: 0.8187 (0.8175) time: 0.1328 data: 0.0458 max mem: 9390 +Train: [85] [1100/6250] eta: 0:17:19 lr: 0.000007 grad: 0.1346 (0.1398) loss: 0.8132 (0.8174) time: 0.1219 data: 0.0003 max mem: 9390 +Train: [85] [1200/6250] eta: 0:16:49 lr: 0.000007 grad: 0.1273 (0.1392) loss: 0.8163 (0.8173) time: 0.2199 data: 0.0993 max mem: 9390 +Train: [85] [1300/6250] eta: 0:16:25 lr: 0.000007 grad: 0.1293 (0.1388) loss: 0.8134 (0.8170) time: 0.1918 data: 0.0934 max mem: 9390 +Train: [85] [1400/6250] eta: 0:16:13 lr: 0.000007 grad: 0.1308 (0.1384) loss: 0.8153 (0.8168) time: 0.3162 data: 0.1968 max mem: 9390 +Train: [85] [1500/6250] eta: 0:15:45 lr: 0.000007 grad: 0.1273 (0.1379) loss: 0.8173 (0.8168) time: 0.2230 data: 0.1263 max mem: 9390 +Train: [85] [1600/6250] eta: 0:15:12 lr: 0.000007 grad: 0.1388 (0.1377) loss: 0.8059 (0.8165) time: 0.1606 data: 0.0780 max mem: 9390 +Train: [85] [1700/6250] eta: 0:14:48 lr: 0.000007 grad: 0.1325 (0.1373) loss: 0.8099 (0.8164) time: 0.1883 data: 0.0668 max mem: 9390 +Train: [85] [1800/6250] eta: 0:14:30 lr: 0.000007 grad: 0.1318 (0.1370) loss: 0.8177 (0.8162) time: 0.1880 data: 0.0833 max mem: 9390 +Train: [85] [1900/6250] eta: 0:14:07 lr: 0.000007 grad: 0.1242 (0.1367) loss: 0.8194 (0.8162) time: 0.1629 data: 0.0852 max mem: 9390 +Train: [85] [2000/6250] eta: 0:13:45 lr: 0.000007 grad: 0.1251 (0.1364) loss: 0.8140 (0.8161) time: 0.2174 data: 0.1366 max mem: 9390 +Train: [85] [2100/6250] eta: 0:13:24 lr: 0.000007 grad: 0.1234 (0.1361) loss: 0.8224 (0.8162) time: 0.2081 data: 0.1227 max mem: 9390 +Train: [85] [2200/6250] eta: 0:13:05 lr: 0.000007 grad: 0.1356 (0.1362) loss: 0.8189 (0.8161) time: 0.2149 data: 0.1327 max mem: 9390 +Train: [85] [2300/6250] eta: 0:12:48 lr: 0.000007 grad: 0.1275 (0.1363) loss: 0.8149 (0.8160) time: 0.2299 data: 0.1378 max mem: 9390 +Train: [85] [2400/6250] eta: 0:12:28 lr: 0.000007 grad: 0.1321 (0.1362) loss: 0.8164 (0.8160) time: 0.1545 data: 0.0589 max mem: 9390 +Train: [85] [2500/6250] eta: 0:12:07 lr: 0.000007 grad: 0.1166 (0.1361) loss: 0.8225 (0.8160) time: 0.1989 data: 0.1234 max mem: 9390 +Train: [85] [2600/6250] eta: 0:11:45 lr: 0.000007 grad: 0.1245 (0.1361) loss: 0.8163 (0.8159) time: 0.1693 data: 0.0798 max mem: 9390 +Train: [85] [2700/6250] eta: 0:11:23 lr: 0.000007 grad: 0.1337 (0.1360) loss: 0.8174 (0.8158) time: 0.1994 data: 0.1094 max mem: 9390 +Train: [85] [2800/6250] eta: 0:11:01 lr: 0.000007 grad: 0.1295 (0.1360) loss: 0.8162 (0.8158) time: 0.1451 data: 0.0489 max mem: 9390 +Train: [85] [2900/6250] eta: 0:10:41 lr: 0.000007 grad: 0.1279 (0.1359) loss: 0.8158 (0.8157) time: 0.1302 data: 0.0217 max mem: 9390 +Train: [85] [3000/6250] eta: 0:10:19 lr: 0.000007 grad: 0.1308 (0.1360) loss: 0.8100 (0.8156) time: 0.1429 data: 0.0434 max mem: 9390 +Train: [85] [3100/6250] eta: 0:09:58 lr: 0.000007 grad: 0.1296 (0.1360) loss: 0.8116 (0.8155) time: 0.1390 data: 0.0459 max mem: 9390 +Train: [85] [3200/6250] eta: 0:09:41 lr: 0.000007 grad: 0.1348 (0.1359) loss: 0.8045 (0.8154) time: 0.1228 data: 0.0003 max mem: 9390 +Train: [85] [3300/6250] eta: 0:09:20 lr: 0.000007 grad: 0.1313 (0.1359) loss: 0.8113 (0.8153) time: 0.1769 data: 0.0830 max mem: 9390 +Train: [85] [3400/6250] eta: 0:08:59 lr: 0.000007 grad: 0.1202 (0.1359) loss: 0.8154 (0.8152) time: 0.1647 data: 0.0714 max mem: 9390 +Train: [85] [3500/6250] eta: 0:08:40 lr: 0.000007 grad: 0.1271 (0.1358) loss: 0.8145 (0.8151) time: 0.1836 data: 0.0921 max mem: 9390 +Train: [85] [3600/6250] eta: 0:08:20 lr: 0.000007 grad: 0.1243 (0.1358) loss: 0.8150 (0.8151) time: 0.1917 data: 0.1052 max mem: 9390 +Train: [85] [3700/6250] eta: 0:08:01 lr: 0.000007 grad: 0.1295 (0.1358) loss: 0.8195 (0.8150) time: 0.1927 data: 0.1112 max mem: 9390 +Train: [85] [3800/6250] eta: 0:07:42 lr: 0.000007 grad: 0.1332 (0.1358) loss: 0.8176 (0.8150) time: 0.1659 data: 0.0612 max mem: 9390 +Train: [85] [3900/6250] eta: 0:07:24 lr: 0.000007 grad: 0.1350 (0.1358) loss: 0.8136 (0.8149) time: 0.1182 data: 0.0256 max mem: 9390 +Train: [85] [4000/6250] eta: 0:07:05 lr: 0.000007 grad: 0.1259 (0.1358) loss: 0.8162 (0.8149) time: 0.1934 data: 0.1067 max mem: 9390 +Train: [85] [4100/6250] eta: 0:06:45 lr: 0.000007 grad: 0.1324 (0.1358) loss: 0.8124 (0.8148) time: 0.1786 data: 0.0839 max mem: 9390 +Train: [85] [4200/6250] eta: 0:06:27 lr: 0.000007 grad: 0.1288 (0.1358) loss: 0.8170 (0.8148) time: 0.2342 data: 0.1511 max mem: 9390 +Train: [85] [4300/6250] eta: 0:06:07 lr: 0.000007 grad: 0.1335 (0.1358) loss: 0.8138 (0.8147) time: 0.1813 data: 0.0921 max mem: 9390 +Train: [85] [4400/6250] eta: 0:05:47 lr: 0.000007 grad: 0.1399 (0.1359) loss: 0.8111 (0.8147) time: 0.1675 data: 0.0787 max mem: 9390 +Train: [85] [4500/6250] eta: 0:05:27 lr: 0.000007 grad: 0.1377 (0.1359) loss: 0.8085 (0.8146) time: 0.1758 data: 0.0825 max mem: 9390 +Train: [85] [4600/6250] eta: 0:05:08 lr: 0.000007 grad: 0.1334 (0.1359) loss: 0.8085 (0.8145) time: 0.1567 data: 0.0731 max mem: 9390 +Train: [85] [4700/6250] eta: 0:04:49 lr: 0.000007 grad: 0.1343 (0.1359) loss: 0.8126 (0.8145) time: 0.1804 data: 0.0653 max mem: 9390 +Train: [85] [4800/6250] eta: 0:04:32 lr: 0.000007 grad: 0.1407 (0.1361) loss: 0.8090 (0.8143) time: 0.1826 data: 0.0902 max mem: 9390 +Train: [85] [4900/6250] eta: 0:04:13 lr: 0.000007 grad: 0.1304 (0.1362) loss: 0.8061 (0.8142) time: 0.1687 data: 0.0825 max mem: 9390 +Train: [85] [5000/6250] eta: 0:03:54 lr: 0.000007 grad: 0.1385 (0.1363) loss: 0.8140 (0.8141) time: 0.1611 data: 0.0745 max mem: 9390 +Train: [85] [5100/6250] eta: 0:03:37 lr: 0.000007 grad: 0.1237 (0.1364) loss: 0.8211 (0.8141) time: 0.2519 data: 0.1774 max mem: 9390 +Train: [85] [5200/6250] eta: 0:03:18 lr: 0.000007 grad: 0.1318 (0.1365) loss: 0.8130 (0.8140) time: 0.1893 data: 0.0963 max mem: 9390 +Train: [85] [5300/6250] eta: 0:03:00 lr: 0.000007 grad: 0.1291 (0.1365) loss: 0.8097 (0.8140) time: 0.1836 data: 0.0980 max mem: 9390 +Train: [85] [5400/6250] eta: 0:02:42 lr: 0.000007 grad: 0.1396 (0.1366) loss: 0.8125 (0.8139) time: 0.2118 data: 0.1370 max mem: 9390 +Train: [85] [5500/6250] eta: 0:02:23 lr: 0.000007 grad: 0.1417 (0.1367) loss: 0.8088 (0.8138) time: 0.2363 data: 0.1416 max mem: 9390 +Train: [85] [5600/6250] eta: 0:02:04 lr: 0.000007 grad: 0.1327 (0.1368) loss: 0.8069 (0.8137) time: 0.2038 data: 0.1204 max mem: 9390 +Train: [85] [5700/6250] eta: 0:01:45 lr: 0.000007 grad: 0.1305 (0.1367) loss: 0.8112 (0.8137) time: 0.2724 data: 0.1816 max mem: 9390 +Train: [85] [5800/6250] eta: 0:01:26 lr: 0.000007 grad: 0.1285 (0.1367) loss: 0.8170 (0.8137) time: 0.1684 data: 0.0678 max mem: 9390 +Train: [85] [5900/6250] eta: 0:01:07 lr: 0.000007 grad: 0.1341 (0.1368) loss: 0.8168 (0.8136) time: 0.1862 data: 0.0939 max mem: 9390 +Train: [85] [6000/6250] eta: 0:00:47 lr: 0.000007 grad: 0.1342 (0.1368) loss: 0.8129 (0.8136) time: 0.1229 data: 0.0188 max mem: 9390 +Train: [85] [6100/6250] eta: 0:00:28 lr: 0.000007 grad: 0.1286 (0.1367) loss: 0.8132 (0.8136) time: 0.1087 data: 0.0157 max mem: 9390 +Train: [85] [6200/6250] eta: 0:00:09 lr: 0.000007 grad: 0.1363 (0.1368) loss: 0.8141 (0.8135) time: 0.2780 data: 0.1596 max mem: 9390 +Train: [85] [6249/6250] eta: 0:00:00 lr: 0.000007 grad: 0.1324 (0.1368) loss: 0.8109 (0.8135) time: 0.2103 data: 0.1234 max mem: 9390 +Train: [85] Total time: 0:20:12 (0.1939 s / it) +Averaged stats: lr: 0.000007 grad: 0.1324 (0.1368) loss: 0.8109 (0.8135) +Eval (hcp-train-subset): [85] [ 0/62] eta: 0:04:54 loss: 0.8296 (0.8296) time: 4.7542 data: 4.7203 max mem: 9390 +Eval (hcp-train-subset): [85] [61/62] eta: 0:00:00 loss: 0.8199 (0.8222) time: 0.1368 data: 0.1093 max mem: 9390 +Eval (hcp-train-subset): [85] Total time: 0:00:15 (0.2488 s / it) +Averaged stats (hcp-train-subset): loss: 0.8199 (0.8222) +Eval (hcp-val): [85] [ 0/62] eta: 0:03:21 loss: 0.8263 (0.8263) time: 3.2558 data: 3.1496 max mem: 9390 +Eval (hcp-val): [85] [61/62] eta: 0:00:00 loss: 0.8276 (0.8293) time: 0.1384 data: 0.1130 max mem: 9390 +Eval (hcp-val): [85] Total time: 0:00:14 (0.2383 s / it) +Averaged stats (hcp-val): loss: 0.8276 (0.8293) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +Train: [86] [ 0/6250] eta: 11:59:25 lr: 0.000007 grad: 0.3426 (0.3426) loss: 0.8095 (0.8095) time: 6.9065 data: 6.7979 max mem: 9390 +Train: [86] [ 100/6250] eta: 0:25:38 lr: 0.000007 grad: 0.1799 (0.2197) loss: 0.8203 (0.8144) time: 0.1887 data: 0.0694 max mem: 9390 +Train: [86] [ 200/6250] eta: 0:22:22 lr: 0.000007 grad: 0.1612 (0.1951) loss: 0.8083 (0.8126) time: 0.1803 data: 0.0854 max mem: 9390 +Train: [86] [ 300/6250] eta: 0:20:49 lr: 0.000007 grad: 0.1539 (0.1835) loss: 0.8119 (0.8125) time: 0.1545 data: 0.0567 max mem: 9390 +Train: [86] [ 400/6250] eta: 0:20:22 lr: 0.000007 grad: 0.1445 (0.1749) loss: 0.8114 (0.8128) time: 0.1862 data: 0.0737 max mem: 9390 +Train: [86] [ 500/6250] eta: 0:20:38 lr: 0.000007 grad: 0.1408 (0.1685) loss: 0.8128 (0.8134) time: 0.3593 data: 0.2383 max mem: 9390 +Train: [86] [ 600/6250] eta: 0:19:34 lr: 0.000006 grad: 0.1410 (0.1641) loss: 0.8128 (0.8135) time: 0.1711 data: 0.0825 max mem: 9390 +Train: [86] [ 700/6250] eta: 0:19:25 lr: 0.000006 grad: 0.1417 (0.1612) loss: 0.8148 (0.8135) time: 0.1961 data: 0.0893 max mem: 9390 +Train: [86] [ 800/6250] eta: 0:18:57 lr: 0.000006 grad: 0.1349 (0.1586) loss: 0.8141 (0.8138) time: 0.2274 data: 0.1300 max mem: 9390 +Train: [86] [ 900/6250] eta: 0:19:21 lr: 0.000006 grad: 0.1278 (0.1563) loss: 0.8185 (0.8141) time: 0.1931 data: 0.0910 max mem: 9390 +Train: [86] [1000/6250] eta: 0:18:43 lr: 0.000006 grad: 0.1348 (0.1544) loss: 0.8143 (0.8140) time: 0.1601 data: 0.0742 max mem: 9390 +Train: [86] [1100/6250] eta: 0:18:31 lr: 0.000006 grad: 0.1387 (0.1526) loss: 0.8137 (0.8142) time: 0.0937 data: 0.0002 max mem: 9390 +Train: [86] [1200/6250] eta: 0:17:56 lr: 0.000006 grad: 0.1324 (0.1514) loss: 0.8163 (0.8142) time: 0.2229 data: 0.1175 max mem: 9390 +Train: [86] [1300/6250] eta: 0:17:40 lr: 0.000006 grad: 0.1277 (0.1498) loss: 0.8173 (0.8144) time: 0.4223 data: 0.3092 max mem: 9390 +Train: [86] [1400/6250] eta: 0:17:12 lr: 0.000006 grad: 0.1314 (0.1486) loss: 0.8134 (0.8146) time: 0.1515 data: 0.0530 max mem: 9390 +Train: [86] [1500/6250] eta: 0:16:40 lr: 0.000006 grad: 0.1315 (0.1477) loss: 0.8128 (0.8148) time: 0.1294 data: 0.0061 max mem: 9390 +Train: [86] [1600/6250] eta: 0:16:13 lr: 0.000006 grad: 0.1362 (0.1471) loss: 0.8098 (0.8146) time: 0.1473 data: 0.0352 max mem: 9390 +Train: [86] [1700/6250] eta: 0:15:44 lr: 0.000006 grad: 0.1244 (0.1464) loss: 0.8159 (0.8146) time: 0.1603 data: 0.0797 max mem: 9390 +Train: [86] [1800/6250] eta: 0:15:22 lr: 0.000006 grad: 0.1364 (0.1458) loss: 0.8117 (0.8145) time: 0.1351 data: 0.0366 max mem: 9390 +Train: [86] [1900/6250] eta: 0:14:48 lr: 0.000006 grad: 0.1379 (0.1455) loss: 0.8088 (0.8144) time: 0.1646 data: 0.0744 max mem: 9390 +Train: [86] [2000/6250] eta: 0:14:22 lr: 0.000006 grad: 0.1375 (0.1450) loss: 0.8184 (0.8145) time: 0.1890 data: 0.0896 max mem: 9390 +Train: [86] [2100/6250] eta: 0:13:57 lr: 0.000006 grad: 0.1366 (0.1448) loss: 0.8086 (0.8144) time: 0.2295 data: 0.1392 max mem: 9390 +Train: [86] [2200/6250] eta: 0:13:40 lr: 0.000006 grad: 0.1336 (0.1444) loss: 0.8157 (0.8144) time: 0.2866 data: 0.1842 max mem: 9390 +Train: [86] [2300/6250] eta: 0:13:13 lr: 0.000006 grad: 0.1277 (0.1437) loss: 0.8164 (0.8145) time: 0.2146 data: 0.1127 max mem: 9390 +Train: [86] [2400/6250] eta: 0:12:57 lr: 0.000006 grad: 0.1279 (0.1434) loss: 0.8179 (0.8146) time: 0.1881 data: 0.0904 max mem: 9390 +Train: [86] [2500/6250] eta: 0:12:33 lr: 0.000006 grad: 0.1363 (0.1432) loss: 0.8123 (0.8147) time: 0.1898 data: 0.0838 max mem: 9390 +Train: [86] [2600/6250] eta: 0:12:12 lr: 0.000006 grad: 0.1217 (0.1428) loss: 0.8259 (0.8148) time: 0.1186 data: 0.0005 max mem: 9390 +Train: [86] [2700/6250] eta: 0:11:49 lr: 0.000006 grad: 0.1305 (0.1425) loss: 0.8178 (0.8150) time: 0.1658 data: 0.0743 max mem: 9390 +Train: [86] [2800/6250] eta: 0:11:30 lr: 0.000006 grad: 0.1301 (0.1422) loss: 0.8133 (0.8150) time: 0.1165 data: 0.0003 max mem: 9390 +Train: [86] [2900/6250] eta: 0:11:10 lr: 0.000006 grad: 0.1327 (0.1419) loss: 0.8124 (0.8150) time: 0.1472 data: 0.0497 max mem: 9390 +Train: [86] [3000/6250] eta: 0:10:47 lr: 0.000006 grad: 0.1373 (0.1418) loss: 0.8139 (0.8151) time: 0.1713 data: 0.0848 max mem: 9390 +Train: [86] [3100/6250] eta: 0:10:25 lr: 0.000006 grad: 0.1344 (0.1417) loss: 0.8198 (0.8151) time: 0.1776 data: 0.0821 max mem: 9390 +Train: [86] [3200/6250] eta: 0:10:04 lr: 0.000006 grad: 0.1297 (0.1416) loss: 0.8152 (0.8151) time: 0.1241 data: 0.0208 max mem: 9390 +Train: [86] [3300/6250] eta: 0:09:41 lr: 0.000006 grad: 0.1375 (0.1415) loss: 0.8109 (0.8151) time: 0.1628 data: 0.0758 max mem: 9390 +Train: [86] [3400/6250] eta: 0:09:19 lr: 0.000006 grad: 0.1385 (0.1414) loss: 0.8139 (0.8151) time: 0.1707 data: 0.0888 max mem: 9390 +Train: [86] [3500/6250] eta: 0:08:57 lr: 0.000006 grad: 0.1402 (0.1413) loss: 0.8118 (0.8151) time: 0.1792 data: 0.1040 max mem: 9390 +Train: [86] [3600/6250] eta: 0:08:37 lr: 0.000006 grad: 0.1329 (0.1412) loss: 0.8125 (0.8150) time: 0.1817 data: 0.0947 max mem: 9390 +Train: [86] [3700/6250] eta: 0:08:17 lr: 0.000006 grad: 0.1396 (0.1413) loss: 0.8078 (0.8149) time: 0.1565 data: 0.0705 max mem: 9390 +Train: [86] [3800/6250] eta: 0:07:58 lr: 0.000006 grad: 0.1323 (0.1414) loss: 0.8143 (0.8148) time: 0.3336 data: 0.2385 max mem: 9390 +Train: [86] [3900/6250] eta: 0:07:37 lr: 0.000006 grad: 0.1408 (0.1415) loss: 0.8098 (0.8148) time: 0.1546 data: 0.0753 max mem: 9390 +Train: [86] [4000/6250] eta: 0:07:16 lr: 0.000006 grad: 0.1426 (0.1417) loss: 0.8127 (0.8147) time: 0.1526 data: 0.0714 max mem: 9390 +Train: [86] [4100/6250] eta: 0:06:56 lr: 0.000006 grad: 0.1516 (0.1418) loss: 0.8107 (0.8145) time: 0.1695 data: 0.0915 max mem: 9390 +Train: [86] [4200/6250] eta: 0:06:36 lr: 0.000006 grad: 0.1426 (0.1419) loss: 0.8208 (0.8145) time: 0.2568 data: 0.1732 max mem: 9390 +Train: [86] [4300/6250] eta: 0:06:16 lr: 0.000006 grad: 0.1327 (0.1419) loss: 0.8169 (0.8145) time: 0.1647 data: 0.0729 max mem: 9390 +Train: [86] [4400/6250] eta: 0:05:56 lr: 0.000006 grad: 0.1343 (0.1418) loss: 0.8170 (0.8145) time: 0.2316 data: 0.0709 max mem: 9390 +Train: [86] [4500/6250] eta: 0:05:35 lr: 0.000006 grad: 0.1426 (0.1417) loss: 0.8130 (0.8145) time: 0.1635 data: 0.0765 max mem: 9390 +Train: [86] [4600/6250] eta: 0:05:15 lr: 0.000006 grad: 0.1360 (0.1418) loss: 0.8136 (0.8145) time: 0.1615 data: 0.0713 max mem: 9390 +Train: [86] [4700/6250] eta: 0:04:56 lr: 0.000006 grad: 0.1340 (0.1417) loss: 0.8182 (0.8145) time: 0.1764 data: 0.0831 max mem: 9390 +Train: [86] [4800/6250] eta: 0:04:36 lr: 0.000006 grad: 0.1373 (0.1417) loss: 0.8109 (0.8144) time: 0.1935 data: 0.1130 max mem: 9390 +Train: [86] [4900/6250] eta: 0:04:18 lr: 0.000006 grad: 0.1307 (0.1416) loss: 0.8135 (0.8144) time: 0.3738 data: 0.2804 max mem: 9390 +Train: [86] [5000/6250] eta: 0:03:59 lr: 0.000006 grad: 0.1382 (0.1416) loss: 0.8112 (0.8144) time: 0.1849 data: 0.0934 max mem: 9390 +Train: [86] [5100/6250] eta: 0:03:40 lr: 0.000006 grad: 0.1379 (0.1415) loss: 0.8118 (0.8144) time: 0.2056 data: 0.1198 max mem: 9390 +Train: [86] [5200/6250] eta: 0:03:21 lr: 0.000006 grad: 0.1401 (0.1415) loss: 0.8124 (0.8144) time: 0.2437 data: 0.1513 max mem: 9390 +Train: [86] [5300/6250] eta: 0:03:03 lr: 0.000006 grad: 0.1344 (0.1415) loss: 0.8168 (0.8143) time: 0.1884 data: 0.1023 max mem: 9390 +Train: [86] [5400/6250] eta: 0:02:44 lr: 0.000006 grad: 0.1476 (0.1415) loss: 0.8065 (0.8143) time: 0.2254 data: 0.1352 max mem: 9390 +Train: [86] [5500/6250] eta: 0:02:25 lr: 0.000006 grad: 0.1423 (0.1414) loss: 0.8090 (0.8143) time: 0.2553 data: 0.1705 max mem: 9390 +Train: [86] [5600/6250] eta: 0:02:06 lr: 0.000006 grad: 0.1434 (0.1414) loss: 0.8080 (0.8142) time: 0.2024 data: 0.1124 max mem: 9390 +Train: [86] [5700/6250] eta: 0:01:46 lr: 0.000006 grad: 0.1420 (0.1414) loss: 0.8077 (0.8142) time: 0.2239 data: 0.1289 max mem: 9390 +Train: [86] [5800/6250] eta: 0:01:27 lr: 0.000006 grad: 0.1383 (0.1414) loss: 0.8145 (0.8142) time: 0.1746 data: 0.0831 max mem: 9390 +Train: [86] [5900/6250] eta: 0:01:08 lr: 0.000006 grad: 0.1414 (0.1415) loss: 0.8140 (0.8141) time: 0.1986 data: 0.1122 max mem: 9390 +Train: [86] [6000/6250] eta: 0:00:48 lr: 0.000006 grad: 0.1402 (0.1415) loss: 0.8122 (0.8141) time: 0.2446 data: 0.0961 max mem: 9390 +Train: [86] [6100/6250] eta: 0:00:29 lr: 0.000006 grad: 0.1390 (0.1415) loss: 0.8112 (0.8140) time: 0.1092 data: 0.0002 max mem: 9390 +Train: [86] [6200/6250] eta: 0:00:09 lr: 0.000006 grad: 0.1310 (0.1415) loss: 0.8056 (0.8140) time: 0.1384 data: 0.0484 max mem: 9390 +Train: [86] [6249/6250] eta: 0:00:00 lr: 0.000006 grad: 0.1368 (0.1415) loss: 0.8151 (0.8140) time: 0.1666 data: 0.0738 max mem: 9390 +Train: [86] Total time: 0:20:23 (0.1957 s / it) +Averaged stats: lr: 0.000006 grad: 0.1368 (0.1415) loss: 0.8151 (0.8140) +Eval (hcp-train-subset): [86] [ 0/62] eta: 0:03:21 loss: 0.8222 (0.8222) time: 3.2575 data: 3.1891 max mem: 9390 +Eval (hcp-train-subset): [86] [61/62] eta: 0:00:00 loss: 0.8172 (0.8200) time: 0.1353 data: 0.1103 max mem: 9390 +Eval (hcp-train-subset): [86] Total time: 0:00:14 (0.2326 s / it) +Averaged stats (hcp-train-subset): loss: 0.8172 (0.8200) +Eval (hcp-val): [86] [ 0/62] eta: 0:03:45 loss: 0.8247 (0.8247) time: 3.6443 data: 3.5834 max mem: 9390 +Eval (hcp-val): [86] [61/62] eta: 0:00:00 loss: 0.8279 (0.8292) time: 0.1505 data: 0.1249 max mem: 9390 +Eval (hcp-val): [86] Total time: 0:00:14 (0.2303 s / it) +Averaged stats (hcp-val): loss: 0.8279 (0.8292) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +Train: [87] [ 0/6250] eta: 7:56:32 lr: 0.000006 grad: 0.1516 (0.1516) loss: 0.8457 (0.8457) time: 4.5747 data: 4.2927 max mem: 9390 +Train: [87] [ 100/6250] eta: 0:30:19 lr: 0.000006 grad: 0.1331 (0.1748) loss: 0.8378 (0.8283) time: 0.1637 data: 0.0436 max mem: 9390 +Train: [87] [ 200/6250] eta: 0:23:53 lr: 0.000006 grad: 0.1303 (0.1612) loss: 0.8336 (0.8280) time: 0.1823 data: 0.0924 max mem: 9390 +Train: [87] [ 300/6250] eta: 0:22:36 lr: 0.000006 grad: 0.1219 (0.1540) loss: 0.8200 (0.8268) time: 0.2177 data: 0.1209 max mem: 9390 +Train: [87] [ 400/6250] eta: 0:20:53 lr: 0.000006 grad: 0.1310 (0.1495) loss: 0.8252 (0.8264) time: 0.1879 data: 0.0704 max mem: 9390 +Train: [87] [ 500/6250] eta: 0:20:08 lr: 0.000006 grad: 0.1331 (0.1458) loss: 0.8259 (0.8256) time: 0.2472 data: 0.1449 max mem: 9390 +Train: [87] [ 600/6250] eta: 0:19:23 lr: 0.000006 grad: 0.1340 (0.1438) loss: 0.8185 (0.8250) time: 0.1666 data: 0.0477 max mem: 9390 +Train: [87] [ 700/6250] eta: 0:18:51 lr: 0.000006 grad: 0.1338 (0.1432) loss: 0.8160 (0.8239) time: 0.1949 data: 0.0920 max mem: 9390 +Train: [87] [ 800/6250] eta: 0:18:17 lr: 0.000006 grad: 0.1317 (0.1427) loss: 0.8156 (0.8231) time: 0.1410 data: 0.0270 max mem: 9390 +Train: [87] [ 900/6250] eta: 0:17:51 lr: 0.000006 grad: 0.1307 (0.1423) loss: 0.8201 (0.8221) time: 0.1884 data: 0.0977 max mem: 9390 +Train: [87] [1000/6250] eta: 0:17:22 lr: 0.000006 grad: 0.1420 (0.1423) loss: 0.8116 (0.8215) time: 0.1594 data: 0.0738 max mem: 9390 +Train: [87] [1100/6250] eta: 0:17:02 lr: 0.000006 grad: 0.1325 (0.1421) loss: 0.8111 (0.8208) time: 0.2150 data: 0.1344 max mem: 9390 +Train: [87] [1200/6250] eta: 0:16:42 lr: 0.000006 grad: 0.1337 (0.1418) loss: 0.8143 (0.8201) time: 0.1843 data: 0.1014 max mem: 9390 +Train: [87] [1300/6250] eta: 0:16:19 lr: 0.000006 grad: 0.1295 (0.1414) loss: 0.8143 (0.8197) time: 0.2018 data: 0.1165 max mem: 9390 +Train: [87] [1400/6250] eta: 0:16:04 lr: 0.000005 grad: 0.1390 (0.1416) loss: 0.8125 (0.8191) time: 0.1688 data: 0.0810 max mem: 9390 +Train: [87] [1500/6250] eta: 0:15:46 lr: 0.000005 grad: 0.1377 (0.1415) loss: 0.8167 (0.8185) time: 0.1673 data: 0.0653 max mem: 9390 +Train: [87] [1600/6250] eta: 0:15:40 lr: 0.000005 grad: 0.1320 (0.1411) loss: 0.8122 (0.8181) time: 0.3756 data: 0.2436 max mem: 9390 +Train: [87] [1700/6250] eta: 0:15:14 lr: 0.000005 grad: 0.1366 (0.1408) loss: 0.8122 (0.8178) time: 0.1226 data: 0.0003 max mem: 9390 +Train: [87] [1800/6250] eta: 0:14:47 lr: 0.000005 grad: 0.1300 (0.1406) loss: 0.8178 (0.8176) time: 0.1940 data: 0.0474 max mem: 9390 +Train: [87] [1900/6250] eta: 0:14:25 lr: 0.000005 grad: 0.1238 (0.1403) loss: 0.8176 (0.8175) time: 0.1632 data: 0.0740 max mem: 9390 +Train: [87] [2000/6250] eta: 0:14:04 lr: 0.000005 grad: 0.1330 (0.1400) loss: 0.8064 (0.8174) time: 0.1923 data: 0.0941 max mem: 9390 +Train: [87] [2100/6250] eta: 0:13:41 lr: 0.000005 grad: 0.1383 (0.1398) loss: 0.8143 (0.8173) time: 0.1532 data: 0.0575 max mem: 9390 +Train: [87] [2200/6250] eta: 0:13:17 lr: 0.000005 grad: 0.1385 (0.1396) loss: 0.8088 (0.8172) time: 0.1857 data: 0.0920 max mem: 9390 +Train: [87] [2300/6250] eta: 0:12:54 lr: 0.000005 grad: 0.1249 (0.1393) loss: 0.8166 (0.8172) time: 0.1730 data: 0.0773 max mem: 9390 +Train: [87] [2400/6250] eta: 0:12:39 lr: 0.000005 grad: 0.1352 (0.1390) loss: 0.8202 (0.8172) time: 0.1542 data: 0.0552 max mem: 9390 +Train: [87] [2500/6250] eta: 0:12:19 lr: 0.000005 grad: 0.1313 (0.1388) loss: 0.8156 (0.8173) time: 0.1350 data: 0.0379 max mem: 9390 +Train: [87] [2600/6250] eta: 0:11:58 lr: 0.000005 grad: 0.1355 (0.1387) loss: 0.8138 (0.8172) time: 0.2522 data: 0.1101 max mem: 9390 +Train: [87] [2700/6250] eta: 0:11:37 lr: 0.000005 grad: 0.1264 (0.1385) loss: 0.8179 (0.8173) time: 0.1541 data: 0.0648 max mem: 9390 +Train: [87] [2800/6250] eta: 0:11:16 lr: 0.000005 grad: 0.1319 (0.1383) loss: 0.8141 (0.8174) time: 0.1681 data: 0.0791 max mem: 9390 +Train: [87] [2900/6250] eta: 0:10:57 lr: 0.000005 grad: 0.1326 (0.1382) loss: 0.8153 (0.8173) time: 0.2427 data: 0.1159 max mem: 9390 +Train: [87] [3000/6250] eta: 0:10:37 lr: 0.000005 grad: 0.1340 (0.1380) loss: 0.8137 (0.8173) time: 0.2628 data: 0.1698 max mem: 9390 +Train: [87] [3100/6250] eta: 0:10:15 lr: 0.000005 grad: 0.1371 (0.1378) loss: 0.8120 (0.8173) time: 0.1838 data: 0.0899 max mem: 9390 +Train: [87] [3200/6250] eta: 0:09:54 lr: 0.000005 grad: 0.1335 (0.1377) loss: 0.8135 (0.8172) time: 0.1263 data: 0.0366 max mem: 9390 +Train: [87] [3300/6250] eta: 0:09:35 lr: 0.000005 grad: 0.1263 (0.1375) loss: 0.8169 (0.8172) time: 0.1533 data: 0.0184 max mem: 9390 +Train: [87] [3400/6250] eta: 0:09:14 lr: 0.000005 grad: 0.1263 (0.1374) loss: 0.8160 (0.8173) time: 0.1878 data: 0.0877 max mem: 9390 +Train: [87] [3500/6250] eta: 0:08:55 lr: 0.000005 grad: 0.1320 (0.1373) loss: 0.8183 (0.8173) time: 0.2245 data: 0.1270 max mem: 9390 +Train: [87] [3600/6250] eta: 0:08:33 lr: 0.000005 grad: 0.1312 (0.1371) loss: 0.8156 (0.8173) time: 0.1310 data: 0.0457 max mem: 9390 +Train: [87] [3700/6250] eta: 0:08:12 lr: 0.000005 grad: 0.1246 (0.1371) loss: 0.8212 (0.8173) time: 0.1728 data: 0.0849 max mem: 9390 +Train: [87] [3800/6250] eta: 0:07:51 lr: 0.000005 grad: 0.1291 (0.1370) loss: 0.8234 (0.8173) time: 0.1833 data: 0.1008 max mem: 9390 +Train: [87] [3900/6250] eta: 0:07:30 lr: 0.000005 grad: 0.1292 (0.1368) loss: 0.8165 (0.8173) time: 0.1790 data: 0.0903 max mem: 9390 +Train: [87] [4000/6250] eta: 0:07:10 lr: 0.000005 grad: 0.1245 (0.1367) loss: 0.8137 (0.8173) time: 0.1664 data: 0.0824 max mem: 9390 +Train: [87] [4100/6250] eta: 0:06:53 lr: 0.000005 grad: 0.1305 (0.1366) loss: 0.8149 (0.8173) time: 0.4926 data: 0.3943 max mem: 9390 +Train: [87] [4200/6250] eta: 0:06:32 lr: 0.000005 grad: 0.1327 (0.1366) loss: 0.8076 (0.8173) time: 0.1855 data: 0.0955 max mem: 9390 +Train: [87] [4300/6250] eta: 0:06:13 lr: 0.000005 grad: 0.1310 (0.1365) loss: 0.8171 (0.8173) time: 0.1089 data: 0.0003 max mem: 9390 +Train: [87] [4400/6250] eta: 0:05:53 lr: 0.000005 grad: 0.1383 (0.1365) loss: 0.8132 (0.8172) time: 0.1826 data: 0.0839 max mem: 9390 +Train: [87] [4500/6250] eta: 0:05:34 lr: 0.000005 grad: 0.1415 (0.1365) loss: 0.8164 (0.8172) time: 0.1073 data: 0.0017 max mem: 9390 +Train: [87] [4600/6250] eta: 0:05:18 lr: 0.000005 grad: 0.1315 (0.1364) loss: 0.8152 (0.8171) time: 0.4579 data: 0.3455 max mem: 9390 +Train: [87] [4700/6250] eta: 0:04:58 lr: 0.000005 grad: 0.1255 (0.1364) loss: 0.8240 (0.8172) time: 0.1802 data: 0.0918 max mem: 9390 +Train: [87] [4800/6250] eta: 0:04:38 lr: 0.000005 grad: 0.1335 (0.1364) loss: 0.8161 (0.8171) time: 0.1818 data: 0.0973 max mem: 9390 +Train: [87] [4900/6250] eta: 0:04:19 lr: 0.000005 grad: 0.1343 (0.1364) loss: 0.8142 (0.8171) time: 0.1628 data: 0.0780 max mem: 9390 +Train: [87] [5000/6250] eta: 0:03:59 lr: 0.000005 grad: 0.1193 (0.1364) loss: 0.8174 (0.8171) time: 0.1681 data: 0.0799 max mem: 9390 +Train: [87] [5100/6250] eta: 0:03:40 lr: 0.000005 grad: 0.1266 (0.1364) loss: 0.8137 (0.8170) time: 0.1537 data: 0.0684 max mem: 9390 +Train: [87] [5200/6250] eta: 0:03:21 lr: 0.000005 grad: 0.1350 (0.1363) loss: 0.8127 (0.8170) time: 0.2211 data: 0.1472 max mem: 9390 +Train: [87] [5300/6250] eta: 0:03:02 lr: 0.000005 grad: 0.1343 (0.1364) loss: 0.8118 (0.8169) time: 0.1653 data: 0.0838 max mem: 9390 +Train: [87] [5400/6250] eta: 0:02:43 lr: 0.000005 grad: 0.1318 (0.1364) loss: 0.8163 (0.8168) time: 0.1898 data: 0.1047 max mem: 9390 +Train: [87] [5500/6250] eta: 0:02:23 lr: 0.000005 grad: 0.1249 (0.1363) loss: 0.8230 (0.8167) time: 0.2304 data: 0.1381 max mem: 9390 +Train: [87] [5600/6250] eta: 0:02:04 lr: 0.000005 grad: 0.1357 (0.1363) loss: 0.8073 (0.8166) time: 0.2006 data: 0.1089 max mem: 9390 +Train: [87] [5700/6250] eta: 0:01:45 lr: 0.000005 grad: 0.1433 (0.1364) loss: 0.8136 (0.8165) time: 0.1895 data: 0.0894 max mem: 9390 +Train: [87] [5800/6250] eta: 0:01:26 lr: 0.000005 grad: 0.1379 (0.1365) loss: 0.8116 (0.8164) time: 0.1677 data: 0.0683 max mem: 9390 +Train: [87] [5900/6250] eta: 0:01:07 lr: 0.000005 grad: 0.1333 (0.1365) loss: 0.8132 (0.8163) time: 0.1393 data: 0.0488 max mem: 9390 +Train: [87] [6000/6250] eta: 0:00:47 lr: 0.000005 grad: 0.1383 (0.1365) loss: 0.8122 (0.8163) time: 0.1469 data: 0.0656 max mem: 9390 +Train: [87] [6100/6250] eta: 0:00:28 lr: 0.000005 grad: 0.1403 (0.1365) loss: 0.8121 (0.8162) time: 0.2156 data: 0.1311 max mem: 9390 +Train: [87] [6200/6250] eta: 0:00:09 lr: 0.000005 grad: 0.1314 (0.1366) loss: 0.8186 (0.8162) time: 0.1807 data: 0.0854 max mem: 9390 +Train: [87] [6249/6250] eta: 0:00:00 lr: 0.000005 grad: 0.1334 (0.1366) loss: 0.8180 (0.8162) time: 0.1808 data: 0.0800 max mem: 9390 +Train: [87] Total time: 0:20:00 (0.1920 s / it) +Averaged stats: lr: 0.000005 grad: 0.1334 (0.1366) loss: 0.8180 (0.8162) +Eval (hcp-train-subset): [87] [ 0/62] eta: 0:05:52 loss: 0.8202 (0.8202) time: 5.6778 data: 5.6431 max mem: 9390 +Eval (hcp-train-subset): [87] [61/62] eta: 0:00:00 loss: 0.8182 (0.8204) time: 0.1429 data: 0.1177 max mem: 9390 +Eval (hcp-train-subset): [87] Total time: 0:00:14 (0.2404 s / it) +Averaged stats (hcp-train-subset): loss: 0.8182 (0.8204) +Eval (hcp-val): [87] [ 0/62] eta: 0:03:56 loss: 0.8252 (0.8252) time: 3.8172 data: 3.7250 max mem: 9390 +Eval (hcp-val): [87] [61/62] eta: 0:00:00 loss: 0.8260 (0.8291) time: 0.1583 data: 0.1333 max mem: 9390 +Eval (hcp-val): [87] Total time: 0:00:14 (0.2350 s / it) +Averaged stats (hcp-val): loss: 0.8260 (0.8291) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +Train: [88] [ 0/6250] eta: 9:52:09 lr: 0.000005 grad: 0.0838 (0.0838) loss: 0.8378 (0.8378) time: 5.6847 data: 5.5142 max mem: 9390 +Train: [88] [ 100/6250] eta: 0:24:32 lr: 0.000005 grad: 0.1178 (0.1522) loss: 0.8249 (0.8170) time: 0.1940 data: 0.0886 max mem: 9390 +Train: [88] [ 200/6250] eta: 0:21:26 lr: 0.000005 grad: 0.1352 (0.1479) loss: 0.8285 (0.8183) time: 0.2108 data: 0.1112 max mem: 9390 +Train: [88] [ 300/6250] eta: 0:19:55 lr: 0.000005 grad: 0.1315 (0.1419) loss: 0.8256 (0.8204) time: 0.1564 data: 0.0611 max mem: 9390 +Train: [88] [ 400/6250] eta: 0:18:54 lr: 0.000005 grad: 0.1217 (0.1379) loss: 0.8207 (0.8212) time: 0.1990 data: 0.0960 max mem: 9390 +Train: [88] [ 500/6250] eta: 0:18:15 lr: 0.000005 grad: 0.1175 (0.1346) loss: 0.8282 (0.8228) time: 0.1816 data: 0.0844 max mem: 9390 +Train: [88] [ 600/6250] eta: 0:18:16 lr: 0.000005 grad: 0.1330 (0.1337) loss: 0.8195 (0.8231) time: 0.1656 data: 0.0586 max mem: 9390 +Train: [88] [ 700/6250] eta: 0:17:56 lr: 0.000005 grad: 0.1261 (0.1336) loss: 0.8224 (0.8229) time: 0.1637 data: 0.0671 max mem: 9390 +Train: [88] [ 800/6250] eta: 0:17:51 lr: 0.000005 grad: 0.1328 (0.1335) loss: 0.8170 (0.8226) time: 0.1795 data: 0.0733 max mem: 9390 +Train: [88] [ 900/6250] eta: 0:17:21 lr: 0.000005 grad: 0.1316 (0.1338) loss: 0.8163 (0.8220) time: 0.1928 data: 0.0965 max mem: 9390 +Train: [88] [1000/6250] eta: 0:17:02 lr: 0.000005 grad: 0.1274 (0.1337) loss: 0.8219 (0.8217) time: 0.1492 data: 0.0599 max mem: 9390 +Train: [88] [1100/6250] eta: 0:16:42 lr: 0.000005 grad: 0.1279 (0.1335) loss: 0.8149 (0.8214) time: 0.2130 data: 0.0973 max mem: 9390 +Train: [88] [1200/6250] eta: 0:16:13 lr: 0.000005 grad: 0.1265 (0.1332) loss: 0.8196 (0.8212) time: 0.1942 data: 0.1055 max mem: 9390 +Train: [88] [1300/6250] eta: 0:16:04 lr: 0.000005 grad: 0.1306 (0.1329) loss: 0.8214 (0.8211) time: 0.1501 data: 0.0571 max mem: 9390 +Train: [88] [1400/6250] eta: 0:15:53 lr: 0.000005 grad: 0.1302 (0.1326) loss: 0.8152 (0.8209) time: 0.3203 data: 0.2215 max mem: 9390 +Train: [88] [1500/6250] eta: 0:15:21 lr: 0.000005 grad: 0.1270 (0.1324) loss: 0.8137 (0.8206) time: 0.1742 data: 0.0726 max mem: 9390 +Train: [88] [1600/6250] eta: 0:14:57 lr: 0.000005 grad: 0.1287 (0.1325) loss: 0.8102 (0.8203) time: 0.1436 data: 0.0113 max mem: 9390 +Train: [88] [1700/6250] eta: 0:14:50 lr: 0.000005 grad: 0.1325 (0.1325) loss: 0.8152 (0.8201) time: 0.2948 data: 0.1750 max mem: 9390 +Train: [88] [1800/6250] eta: 0:14:20 lr: 0.000005 grad: 0.1373 (0.1325) loss: 0.8155 (0.8199) time: 0.1965 data: 0.0984 max mem: 9390 +Train: [88] [1900/6250] eta: 0:13:58 lr: 0.000005 grad: 0.1263 (0.1325) loss: 0.8211 (0.8196) time: 0.1712 data: 0.0866 max mem: 9390 +Train: [88] [2000/6250] eta: 0:13:32 lr: 0.000005 grad: 0.1268 (0.1324) loss: 0.8135 (0.8194) time: 0.1607 data: 0.0778 max mem: 9390 +Train: [88] [2100/6250] eta: 0:13:08 lr: 0.000005 grad: 0.1247 (0.1322) loss: 0.8195 (0.8193) time: 0.1623 data: 0.0776 max mem: 9390 +Train: [88] [2200/6250] eta: 0:12:49 lr: 0.000005 grad: 0.1247 (0.1322) loss: 0.8175 (0.8191) time: 0.1281 data: 0.0412 max mem: 9390 +Train: [88] [2300/6250] eta: 0:12:34 lr: 0.000005 grad: 0.1287 (0.1321) loss: 0.8148 (0.8190) time: 0.3612 data: 0.2691 max mem: 9390 +Train: [88] [2400/6250] eta: 0:12:09 lr: 0.000005 grad: 0.1272 (0.1320) loss: 0.8096 (0.8189) time: 0.1729 data: 0.0855 max mem: 9390 +Train: [88] [2500/6250] eta: 0:11:48 lr: 0.000005 grad: 0.1259 (0.1321) loss: 0.8131 (0.8187) time: 0.1751 data: 0.0914 max mem: 9390 +Train: [88] [2600/6250] eta: 0:11:28 lr: 0.000005 grad: 0.1288 (0.1321) loss: 0.8167 (0.8185) time: 0.1724 data: 0.0735 max mem: 9390 +Train: [88] [2700/6250] eta: 0:11:26 lr: 0.000005 grad: 0.1264 (0.1322) loss: 0.8160 (0.8184) time: 0.2023 data: 0.1167 max mem: 9390 +Train: [88] [2800/6250] eta: 0:11:02 lr: 0.000005 grad: 0.1245 (0.1322) loss: 0.8140 (0.8183) time: 0.1759 data: 0.0799 max mem: 9390 +Train: [88] [2900/6250] eta: 0:10:43 lr: 0.000004 grad: 0.1238 (0.1322) loss: 0.8149 (0.8182) time: 0.3004 data: 0.2065 max mem: 9390 +Train: [88] [3000/6250] eta: 0:10:20 lr: 0.000004 grad: 0.1271 (0.1323) loss: 0.8132 (0.8181) time: 0.1828 data: 0.1040 max mem: 9390 +Train: [88] [3100/6250] eta: 0:10:03 lr: 0.000004 grad: 0.1301 (0.1323) loss: 0.8179 (0.8180) time: 0.1723 data: 0.0777 max mem: 9390 +Train: [88] [3200/6250] eta: 0:09:45 lr: 0.000004 grad: 0.1348 (0.1324) loss: 0.8134 (0.8179) time: 0.1021 data: 0.0003 max mem: 9390 +Train: [88] [3300/6250] eta: 0:09:23 lr: 0.000004 grad: 0.1178 (0.1324) loss: 0.8264 (0.8180) time: 0.1517 data: 0.0683 max mem: 9390 +Train: [88] [3400/6250] eta: 0:09:02 lr: 0.000004 grad: 0.1377 (0.1324) loss: 0.8178 (0.8180) time: 0.1604 data: 0.0723 max mem: 9390 +Train: [88] [3500/6250] eta: 0:08:41 lr: 0.000004 grad: 0.1250 (0.1325) loss: 0.8155 (0.8181) time: 0.1773 data: 0.0967 max mem: 9390 +Train: [88] [3600/6250] eta: 0:08:21 lr: 0.000004 grad: 0.1295 (0.1325) loss: 0.8205 (0.8181) time: 0.1879 data: 0.0980 max mem: 9390 +Train: [88] [3700/6250] eta: 0:08:01 lr: 0.000004 grad: 0.1346 (0.1325) loss: 0.8222 (0.8181) time: 0.1973 data: 0.1126 max mem: 9390 +Train: [88] [3800/6250] eta: 0:07:41 lr: 0.000004 grad: 0.1358 (0.1326) loss: 0.8130 (0.8180) time: 0.1590 data: 0.0832 max mem: 9390 +Train: [88] [3900/6250] eta: 0:07:22 lr: 0.000004 grad: 0.1340 (0.1327) loss: 0.8120 (0.8179) time: 0.2146 data: 0.1290 max mem: 9390 +Train: [88] [4000/6250] eta: 0:07:04 lr: 0.000004 grad: 0.1302 (0.1327) loss: 0.8174 (0.8178) time: 0.1756 data: 0.0810 max mem: 9390 +Train: [88] [4100/6250] eta: 0:06:45 lr: 0.000004 grad: 0.1276 (0.1328) loss: 0.8135 (0.8177) time: 0.1643 data: 0.0741 max mem: 9390 +Train: [88] [4200/6250] eta: 0:06:26 lr: 0.000004 grad: 0.1385 (0.1329) loss: 0.8093 (0.8176) time: 0.1999 data: 0.1031 max mem: 9390 +Train: [88] [4300/6250] eta: 0:06:08 lr: 0.000004 grad: 0.1371 (0.1331) loss: 0.8101 (0.8175) time: 0.1314 data: 0.0339 max mem: 9390 +Train: [88] [4400/6250] eta: 0:05:50 lr: 0.000004 grad: 0.1369 (0.1332) loss: 0.8165 (0.8174) time: 0.1447 data: 0.0003 max mem: 9390 +Train: [88] [4500/6250] eta: 0:05:32 lr: 0.000004 grad: 0.1274 (0.1333) loss: 0.8137 (0.8173) time: 0.1454 data: 0.0454 max mem: 9390 +Train: [88] [4600/6250] eta: 0:05:12 lr: 0.000004 grad: 0.1374 (0.1333) loss: 0.8152 (0.8173) time: 0.1751 data: 0.0853 max mem: 9390 +Train: [88] [4700/6250] eta: 0:04:53 lr: 0.000004 grad: 0.1345 (0.1334) loss: 0.8146 (0.8173) time: 0.2257 data: 0.1310 max mem: 9390 +Train: [88] [4800/6250] eta: 0:04:34 lr: 0.000004 grad: 0.1341 (0.1335) loss: 0.8131 (0.8172) time: 0.0946 data: 0.0004 max mem: 9390 +Train: [88] [4900/6250] eta: 0:04:15 lr: 0.000004 grad: 0.1354 (0.1336) loss: 0.8157 (0.8171) time: 0.2010 data: 0.1130 max mem: 9390 +Train: [88] [5000/6250] eta: 0:03:56 lr: 0.000004 grad: 0.1396 (0.1337) loss: 0.8099 (0.8170) time: 0.1717 data: 0.0829 max mem: 9390 +Train: [88] [5100/6250] eta: 0:03:37 lr: 0.000004 grad: 0.1345 (0.1338) loss: 0.8191 (0.8170) time: 0.2236 data: 0.1221 max mem: 9390 +Train: [88] [5200/6250] eta: 0:03:18 lr: 0.000004 grad: 0.1493 (0.1340) loss: 0.8076 (0.8169) time: 0.2119 data: 0.1314 max mem: 9390 +Train: [88] [5300/6250] eta: 0:02:59 lr: 0.000004 grad: 0.1382 (0.1342) loss: 0.8145 (0.8168) time: 0.1989 data: 0.1179 max mem: 9390 +Train: [88] [5400/6250] eta: 0:02:40 lr: 0.000004 grad: 0.1427 (0.1343) loss: 0.8141 (0.8168) time: 0.1917 data: 0.1138 max mem: 9390 +Train: [88] [5500/6250] eta: 0:02:22 lr: 0.000004 grad: 0.1348 (0.1344) loss: 0.8162 (0.8167) time: 0.1898 data: 0.1028 max mem: 9390 +Train: [88] [5600/6250] eta: 0:02:03 lr: 0.000004 grad: 0.1366 (0.1346) loss: 0.8108 (0.8167) time: 0.2043 data: 0.1140 max mem: 9390 +Train: [88] [5700/6250] eta: 0:01:44 lr: 0.000004 grad: 0.1501 (0.1347) loss: 0.8092 (0.8166) time: 0.2523 data: 0.1544 max mem: 9390 +Train: [88] [5800/6250] eta: 0:01:25 lr: 0.000004 grad: 0.1395 (0.1348) loss: 0.8111 (0.8166) time: 0.1900 data: 0.0811 max mem: 9390 +Train: [88] [5900/6250] eta: 0:01:06 lr: 0.000004 grad: 0.1354 (0.1349) loss: 0.8182 (0.8166) time: 0.1788 data: 0.0888 max mem: 9390 +Train: [88] [6000/6250] eta: 0:00:47 lr: 0.000004 grad: 0.1325 (0.1350) loss: 0.8127 (0.8166) time: 0.1155 data: 0.0002 max mem: 9390 +Train: [88] [6100/6250] eta: 0:00:28 lr: 0.000004 grad: 0.1327 (0.1350) loss: 0.8173 (0.8166) time: 0.1807 data: 0.0997 max mem: 9390 +Train: [88] [6200/6250] eta: 0:00:09 lr: 0.000004 grad: 0.1419 (0.1351) loss: 0.8087 (0.8165) time: 0.1716 data: 0.0829 max mem: 9390 +Train: [88] [6249/6250] eta: 0:00:00 lr: 0.000004 grad: 0.1398 (0.1351) loss: 0.8105 (0.8165) time: 0.2254 data: 0.1470 max mem: 9390 +Train: [88] Total time: 0:19:51 (0.1906 s / it) +Averaged stats: lr: 0.000004 grad: 0.1398 (0.1351) loss: 0.8105 (0.8165) +Eval (hcp-train-subset): [88] [ 0/62] eta: 0:05:03 loss: 0.8212 (0.8212) time: 4.9013 data: 4.8658 max mem: 9390 +Eval (hcp-train-subset): [88] [61/62] eta: 0:00:00 loss: 0.8177 (0.8195) time: 0.1447 data: 0.1182 max mem: 9390 +Eval (hcp-train-subset): [88] Total time: 0:00:14 (0.2289 s / it) +Averaged stats (hcp-train-subset): loss: 0.8177 (0.8195) +Eval (hcp-val): [88] [ 0/62] eta: 0:03:56 loss: 0.8264 (0.8264) time: 3.8081 data: 3.7259 max mem: 9390 +Eval (hcp-val): [88] [61/62] eta: 0:00:00 loss: 0.8268 (0.8287) time: 0.1693 data: 0.1440 max mem: 9390 +Eval (hcp-val): [88] Total time: 0:00:14 (0.2309 s / it) +Averaged stats (hcp-val): loss: 0.8268 (0.8287) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +Train: [89] [ 0/6250] eta: 10:10:00 lr: 0.000004 grad: 0.4720 (0.4720) loss: 0.7827 (0.7827) time: 5.8561 data: 5.6742 max mem: 9390 +Train: [89] [ 100/6250] eta: 0:23:18 lr: 0.000004 grad: 0.1383 (0.1662) loss: 0.8194 (0.8213) time: 0.1638 data: 0.0485 max mem: 9390 +Train: [89] [ 200/6250] eta: 0:20:15 lr: 0.000004 grad: 0.1358 (0.1590) loss: 0.8126 (0.8186) time: 0.1596 data: 0.0593 max mem: 9390 +Train: [89] [ 300/6250] eta: 0:18:55 lr: 0.000004 grad: 0.1385 (0.1566) loss: 0.8104 (0.8172) time: 0.1738 data: 0.0801 max mem: 9390 +Train: [89] [ 400/6250] eta: 0:18:03 lr: 0.000004 grad: 0.1338 (0.1530) loss: 0.8150 (0.8160) time: 0.1708 data: 0.0779 max mem: 9390 +Train: [89] [ 500/6250] eta: 0:17:23 lr: 0.000004 grad: 0.1452 (0.1519) loss: 0.8159 (0.8154) time: 0.1903 data: 0.0925 max mem: 9390 +Train: [89] [ 600/6250] eta: 0:16:53 lr: 0.000004 grad: 0.1322 (0.1514) loss: 0.8073 (0.8146) time: 0.1503 data: 0.0587 max mem: 9390 +Train: [89] [ 700/6250] eta: 0:16:30 lr: 0.000004 grad: 0.1453 (0.1504) loss: 0.8069 (0.8144) time: 0.1740 data: 0.0812 max mem: 9390 +Train: [89] [ 800/6250] eta: 0:16:15 lr: 0.000004 grad: 0.1490 (0.1498) loss: 0.8172 (0.8143) time: 0.2173 data: 0.1296 max mem: 9390 +Train: [89] [ 900/6250] eta: 0:16:26 lr: 0.000004 grad: 0.1333 (0.1485) loss: 0.8151 (0.8145) time: 0.1967 data: 0.0672 max mem: 9390 +Train: [89] [1000/6250] eta: 0:16:13 lr: 0.000004 grad: 0.1381 (0.1477) loss: 0.8180 (0.8144) time: 0.2365 data: 0.1322 max mem: 9390 +Train: [89] [1100/6250] eta: 0:16:06 lr: 0.000004 grad: 0.1387 (0.1470) loss: 0.8176 (0.8145) time: 0.1111 data: 0.0002 max mem: 9390 +Train: [89] [1200/6250] eta: 0:15:39 lr: 0.000004 grad: 0.1323 (0.1463) loss: 0.8181 (0.8146) time: 0.1972 data: 0.1123 max mem: 9390 +Train: [89] [1300/6250] eta: 0:15:17 lr: 0.000004 grad: 0.1394 (0.1458) loss: 0.8128 (0.8147) time: 0.2062 data: 0.1135 max mem: 9390 +Train: [89] [1400/6250] eta: 0:14:57 lr: 0.000004 grad: 0.1418 (0.1456) loss: 0.8128 (0.8147) time: 0.1806 data: 0.0934 max mem: 9390 +Train: [89] [1500/6250] eta: 0:14:31 lr: 0.000004 grad: 0.1384 (0.1453) loss: 0.8124 (0.8145) time: 0.1551 data: 0.0675 max mem: 9390 +Train: [89] [1600/6250] eta: 0:14:17 lr: 0.000004 grad: 0.1356 (0.1447) loss: 0.8103 (0.8145) time: 0.1282 data: 0.0417 max mem: 9390 +Train: [89] [1700/6250] eta: 0:13:53 lr: 0.000004 grad: 0.1382 (0.1444) loss: 0.8084 (0.8145) time: 0.1790 data: 0.0861 max mem: 9390 +Train: [89] [1800/6250] eta: 0:13:32 lr: 0.000004 grad: 0.1378 (0.1441) loss: 0.8111 (0.8143) time: 0.1676 data: 0.0777 max mem: 9390 +Train: [89] [1900/6250] eta: 0:13:14 lr: 0.000004 grad: 0.1366 (0.1437) loss: 0.8098 (0.8142) time: 0.2263 data: 0.1131 max mem: 9390 +Train: [89] [2000/6250] eta: 0:12:57 lr: 0.000004 grad: 0.1310 (0.1433) loss: 0.8204 (0.8144) time: 0.2533 data: 0.1400 max mem: 9390 +Train: [89] [2100/6250] eta: 0:12:35 lr: 0.000004 grad: 0.1355 (0.1428) loss: 0.8180 (0.8145) time: 0.1688 data: 0.0791 max mem: 9390 +Train: [89] [2200/6250] eta: 0:12:23 lr: 0.000004 grad: 0.1333 (0.1424) loss: 0.8161 (0.8145) time: 0.1324 data: 0.0234 max mem: 9390 +Train: [89] [2300/6250] eta: 0:12:11 lr: 0.000004 grad: 0.1406 (0.1421) loss: 0.8171 (0.8147) time: 0.1082 data: 0.0233 max mem: 9390 +Train: [89] [2400/6250] eta: 0:11:54 lr: 0.000004 grad: 0.1278 (0.1418) loss: 0.8161 (0.8148) time: 0.1411 data: 0.0469 max mem: 9390 +Train: [89] [2500/6250] eta: 0:11:35 lr: 0.000004 grad: 0.1349 (0.1415) loss: 0.8180 (0.8148) time: 0.1274 data: 0.0441 max mem: 9390 +Train: [89] [2600/6250] eta: 0:11:16 lr: 0.000004 grad: 0.1357 (0.1414) loss: 0.8141 (0.8149) time: 0.1768 data: 0.0713 max mem: 9390 +Train: [89] [2700/6250] eta: 0:11:01 lr: 0.000004 grad: 0.1353 (0.1412) loss: 0.8152 (0.8150) time: 0.1651 data: 0.0739 max mem: 9390 +Train: [89] [2800/6250] eta: 0:10:47 lr: 0.000004 grad: 0.1343 (0.1411) loss: 0.8183 (0.8149) time: 0.2326 data: 0.1211 max mem: 9390 +Train: [89] [2900/6250] eta: 0:10:27 lr: 0.000004 grad: 0.1396 (0.1410) loss: 0.8139 (0.8149) time: 0.1593 data: 0.0613 max mem: 9390 +Train: [89] [3000/6250] eta: 0:10:08 lr: 0.000004 grad: 0.1431 (0.1410) loss: 0.8106 (0.8148) time: 0.1749 data: 0.0833 max mem: 9390 +Train: [89] [3100/6250] eta: 0:09:46 lr: 0.000004 grad: 0.1339 (0.1409) loss: 0.8085 (0.8147) time: 0.1747 data: 0.0761 max mem: 9390 +Train: [89] [3200/6250] eta: 0:09:26 lr: 0.000004 grad: 0.1286 (0.1408) loss: 0.8130 (0.8147) time: 0.1938 data: 0.1106 max mem: 9390 +Train: [89] [3300/6250] eta: 0:09:06 lr: 0.000004 grad: 0.1280 (0.1408) loss: 0.8093 (0.8145) time: 0.1684 data: 0.0836 max mem: 9390 +Train: [89] [3400/6250] eta: 0:08:47 lr: 0.000004 grad: 0.1330 (0.1408) loss: 0.8108 (0.8145) time: 0.1607 data: 0.0598 max mem: 9390 +Train: [89] [3500/6250] eta: 0:08:27 lr: 0.000004 grad: 0.1349 (0.1406) loss: 0.8111 (0.8144) time: 0.1503 data: 0.0560 max mem: 9390 +Train: [89] [3600/6250] eta: 0:08:13 lr: 0.000004 grad: 0.1318 (0.1406) loss: 0.8110 (0.8143) time: 0.1591 data: 0.0411 max mem: 9390 +Train: [89] [3700/6250] eta: 0:07:57 lr: 0.000004 grad: 0.1360 (0.1406) loss: 0.8052 (0.8143) time: 0.1260 data: 0.0285 max mem: 9390 +Train: [89] [3800/6250] eta: 0:07:39 lr: 0.000004 grad: 0.1354 (0.1405) loss: 0.8152 (0.8143) time: 0.1402 data: 0.0341 max mem: 9390 +Train: [89] [3900/6250] eta: 0:07:20 lr: 0.000004 grad: 0.1373 (0.1404) loss: 0.8124 (0.8142) time: 0.1997 data: 0.1132 max mem: 9390 +Train: [89] [4000/6250] eta: 0:07:02 lr: 0.000004 grad: 0.1350 (0.1403) loss: 0.8093 (0.8141) time: 0.1625 data: 0.0779 max mem: 9390 +Train: [89] [4100/6250] eta: 0:06:46 lr: 0.000004 grad: 0.1293 (0.1403) loss: 0.8125 (0.8141) time: 0.2974 data: 0.1735 max mem: 9390 +Train: [89] [4200/6250] eta: 0:06:26 lr: 0.000004 grad: 0.1330 (0.1402) loss: 0.8163 (0.8140) time: 0.1177 data: 0.0003 max mem: 9390 +Train: [89] [4300/6250] eta: 0:06:08 lr: 0.000004 grad: 0.1352 (0.1401) loss: 0.8078 (0.8139) time: 0.2737 data: 0.1749 max mem: 9390 +Train: [89] [4400/6250] eta: 0:05:51 lr: 0.000004 grad: 0.1405 (0.1401) loss: 0.8110 (0.8138) time: 0.1793 data: 0.0706 max mem: 9390 +Train: [89] [4500/6250] eta: 0:05:31 lr: 0.000004 grad: 0.1336 (0.1400) loss: 0.8123 (0.8138) time: 0.1510 data: 0.0409 max mem: 9390 +Train: [89] [4600/6250] eta: 0:05:12 lr: 0.000004 grad: 0.1306 (0.1401) loss: 0.8157 (0.8137) time: 0.1381 data: 0.0545 max mem: 9390 +Train: [89] [4700/6250] eta: 0:04:54 lr: 0.000004 grad: 0.1383 (0.1401) loss: 0.8088 (0.8135) time: 0.1172 data: 0.0003 max mem: 9390 +Train: [89] [4800/6250] eta: 0:04:35 lr: 0.000004 grad: 0.1384 (0.1402) loss: 0.8099 (0.8134) time: 0.1460 data: 0.0558 max mem: 9390 +Train: [89] [4900/6250] eta: 0:04:16 lr: 0.000004 grad: 0.1388 (0.1402) loss: 0.8091 (0.8133) time: 0.2100 data: 0.1258 max mem: 9390 +Train: [89] [5000/6250] eta: 0:03:57 lr: 0.000004 grad: 0.1349 (0.1402) loss: 0.8122 (0.8132) time: 0.2077 data: 0.1151 max mem: 9390 +Train: [89] [5100/6250] eta: 0:03:38 lr: 0.000004 grad: 0.1301 (0.1402) loss: 0.8097 (0.8132) time: 0.1921 data: 0.0995 max mem: 9390 +Train: [89] [5200/6250] eta: 0:03:20 lr: 0.000003 grad: 0.1394 (0.1402) loss: 0.8089 (0.8131) time: 0.2393 data: 0.1588 max mem: 9390 +Train: [89] [5300/6250] eta: 0:03:00 lr: 0.000003 grad: 0.1424 (0.1401) loss: 0.8095 (0.8131) time: 0.1817 data: 0.0980 max mem: 9390 +Train: [89] [5400/6250] eta: 0:02:41 lr: 0.000003 grad: 0.1353 (0.1401) loss: 0.8169 (0.8131) time: 0.2058 data: 0.1182 max mem: 9390 +Train: [89] [5500/6250] eta: 0:02:22 lr: 0.000003 grad: 0.1378 (0.1401) loss: 0.8133 (0.8131) time: 0.1792 data: 0.0925 max mem: 9390 +Train: [89] [5600/6250] eta: 0:02:03 lr: 0.000003 grad: 0.1456 (0.1401) loss: 0.8123 (0.8131) time: 0.1858 data: 0.0827 max mem: 9390 +Train: [89] [5700/6250] eta: 0:01:44 lr: 0.000003 grad: 0.1300 (0.1400) loss: 0.8167 (0.8131) time: 0.1870 data: 0.0900 max mem: 9390 +Train: [89] [5800/6250] eta: 0:01:25 lr: 0.000003 grad: 0.1402 (0.1400) loss: 0.8095 (0.8131) time: 0.1872 data: 0.0988 max mem: 9390 +Train: [89] [5900/6250] eta: 0:01:06 lr: 0.000003 grad: 0.1370 (0.1400) loss: 0.8126 (0.8132) time: 0.1898 data: 0.0963 max mem: 9390 +Train: [89] [6000/6250] eta: 0:00:47 lr: 0.000003 grad: 0.1467 (0.1400) loss: 0.8090 (0.8132) time: 0.1785 data: 0.0782 max mem: 9390 +Train: [89] [6100/6250] eta: 0:00:28 lr: 0.000003 grad: 0.1428 (0.1401) loss: 0.8093 (0.8132) time: 0.1407 data: 0.0431 max mem: 9390 +Train: [89] [6200/6250] eta: 0:00:09 lr: 0.000003 grad: 0.1449 (0.1401) loss: 0.8160 (0.8132) time: 0.1248 data: 0.0298 max mem: 9390 +Train: [89] [6249/6250] eta: 0:00:00 lr: 0.000003 grad: 0.1392 (0.1401) loss: 0.8113 (0.8132) time: 0.1909 data: 0.0892 max mem: 9390 +Train: [89] Total time: 0:19:53 (0.1909 s / it) +Averaged stats: lr: 0.000003 grad: 0.1392 (0.1401) loss: 0.8113 (0.8132) +Eval (hcp-train-subset): [89] [ 0/62] eta: 0:05:03 loss: 0.8234 (0.8234) time: 4.8959 data: 4.8533 max mem: 9390 +Eval (hcp-train-subset): [89] [61/62] eta: 0:00:00 loss: 0.8174 (0.8191) time: 0.1245 data: 0.0995 max mem: 9390 +Eval (hcp-train-subset): [89] Total time: 0:00:15 (0.2441 s / it) +Averaged stats (hcp-train-subset): loss: 0.8174 (0.8191) +Making plots (hcp-train-subset): example=32 +Eval (hcp-val): [89] [ 0/62] eta: 0:05:11 loss: 0.8260 (0.8260) time: 5.0255 data: 4.9884 max mem: 9390 +Eval (hcp-val): [89] [61/62] eta: 0:00:00 loss: 0.8275 (0.8285) time: 0.1233 data: 0.0961 max mem: 9390 +Eval (hcp-val): [89] Total time: 0:00:14 (0.2322 s / it) +Averaged stats (hcp-val): loss: 0.8275 (0.8285) +Making plots (hcp-val): example=55 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +Train: [90] [ 0/6250] eta: 12:20:11 lr: 0.000003 grad: 0.0948 (0.0948) loss: 0.8431 (0.8431) time: 7.1059 data: 6.9629 max mem: 9390 +Train: [90] [ 100/6250] eta: 0:24:00 lr: 0.000003 grad: 0.1524 (0.1631) loss: 0.8182 (0.8125) time: 0.1962 data: 0.1036 max mem: 9390 +Train: [90] [ 200/6250] eta: 0:21:03 lr: 0.000003 grad: 0.1374 (0.1505) loss: 0.8257 (0.8161) time: 0.2067 data: 0.1038 max mem: 9390 +Train: [90] [ 300/6250] eta: 0:19:35 lr: 0.000003 grad: 0.1358 (0.1461) loss: 0.8167 (0.8160) time: 0.1678 data: 0.0677 max mem: 9390 +Train: [90] [ 400/6250] eta: 0:18:41 lr: 0.000003 grad: 0.1274 (0.1420) loss: 0.8214 (0.8165) time: 0.1605 data: 0.0712 max mem: 9390 +Train: [90] [ 500/6250] eta: 0:18:05 lr: 0.000003 grad: 0.1196 (0.1402) loss: 0.8216 (0.8172) time: 0.1938 data: 0.1106 max mem: 9390 +Train: [90] [ 600/6250] eta: 0:17:34 lr: 0.000003 grad: 0.1219 (0.1391) loss: 0.8174 (0.8176) time: 0.1854 data: 0.0955 max mem: 9390 +Train: [90] [ 700/6250] eta: 0:17:35 lr: 0.000003 grad: 0.1409 (0.1384) loss: 0.8193 (0.8176) time: 0.2112 data: 0.1269 max mem: 9390 +Train: [90] [ 800/6250] eta: 0:17:50 lr: 0.000003 grad: 0.1326 (0.1379) loss: 0.8184 (0.8175) time: 0.3616 data: 0.2663 max mem: 9390 +Train: [90] [ 900/6250] eta: 0:18:31 lr: 0.000003 grad: 0.1338 (0.1376) loss: 0.8157 (0.8174) time: 0.1733 data: 0.0722 max mem: 9390 +Train: [90] [1000/6250] eta: 0:18:29 lr: 0.000003 grad: 0.1343 (0.1379) loss: 0.8117 (0.8169) time: 0.0977 data: 0.0002 max mem: 9390 +Train: [90] [1100/6250] eta: 0:17:49 lr: 0.000003 grad: 0.1287 (0.1384) loss: 0.8156 (0.8164) time: 0.1830 data: 0.0913 max mem: 9390 +Train: [90] [1200/6250] eta: 0:17:15 lr: 0.000003 grad: 0.1314 (0.1385) loss: 0.8189 (0.8161) time: 0.1850 data: 0.0922 max mem: 9390 +Train: [90] [1300/6250] eta: 0:17:02 lr: 0.000003 grad: 0.1393 (0.1382) loss: 0.8104 (0.8160) time: 0.3533 data: 0.2607 max mem: 9390 +Train: [90] [1400/6250] eta: 0:16:29 lr: 0.000003 grad: 0.1308 (0.1380) loss: 0.8203 (0.8159) time: 0.2525 data: 0.1233 max mem: 9390 +Train: [90] [1500/6250] eta: 0:15:58 lr: 0.000003 grad: 0.1259 (0.1380) loss: 0.8142 (0.8159) time: 0.1651 data: 0.0821 max mem: 9390 +Train: [90] [1600/6250] eta: 0:15:42 lr: 0.000003 grad: 0.1332 (0.1381) loss: 0.8131 (0.8157) time: 0.3858 data: 0.2960 max mem: 9390 +Train: [90] [1700/6250] eta: 0:15:09 lr: 0.000003 grad: 0.1358 (0.1382) loss: 0.8125 (0.8156) time: 0.1189 data: 0.0051 max mem: 9390 +Train: [90] [1800/6250] eta: 0:14:44 lr: 0.000003 grad: 0.1424 (0.1385) loss: 0.8126 (0.8155) time: 0.1843 data: 0.0560 max mem: 9390 +Train: [90] [1900/6250] eta: 0:14:33 lr: 0.000003 grad: 0.1387 (0.1385) loss: 0.8133 (0.8154) time: 0.1710 data: 0.0772 max mem: 9390 +Train: [90] [2000/6250] eta: 0:14:06 lr: 0.000003 grad: 0.1384 (0.1388) loss: 0.8126 (0.8152) time: 0.1539 data: 0.0679 max mem: 9390 +Train: [90] [2100/6250] eta: 0:13:43 lr: 0.000003 grad: 0.1411 (0.1389) loss: 0.8144 (0.8152) time: 0.2014 data: 0.1184 max mem: 9390 +Train: [90] [2200/6250] eta: 0:13:22 lr: 0.000003 grad: 0.1392 (0.1390) loss: 0.8142 (0.8151) time: 0.2430 data: 0.1442 max mem: 9390 +Train: [90] [2300/6250] eta: 0:13:12 lr: 0.000003 grad: 0.1307 (0.1391) loss: 0.8157 (0.8151) time: 0.1542 data: 0.0035 max mem: 9390 +Train: [90] [2400/6250] eta: 0:12:53 lr: 0.000003 grad: 0.1418 (0.1393) loss: 0.8114 (0.8150) time: 0.1205 data: 0.0324 max mem: 9390 +Train: [90] [2500/6250] eta: 0:12:31 lr: 0.000003 grad: 0.1365 (0.1394) loss: 0.8125 (0.8149) time: 0.2286 data: 0.1257 max mem: 9390 +Train: [90] [2600/6250] eta: 0:12:05 lr: 0.000003 grad: 0.1350 (0.1397) loss: 0.8074 (0.8148) time: 0.1638 data: 0.0733 max mem: 9390 +Train: [90] [2700/6250] eta: 0:11:41 lr: 0.000003 grad: 0.1407 (0.1398) loss: 0.8064 (0.8146) time: 0.1662 data: 0.0826 max mem: 9390 +Train: [90] [2800/6250] eta: 0:11:18 lr: 0.000003 grad: 0.1448 (0.1399) loss: 0.8135 (0.8145) time: 0.0994 data: 0.0004 max mem: 9390 +Train: [90] [2900/6250] eta: 0:10:56 lr: 0.000003 grad: 0.1385 (0.1400) loss: 0.8120 (0.8144) time: 0.1739 data: 0.0892 max mem: 9390 +Train: [90] [3000/6250] eta: 0:10:36 lr: 0.000003 grad: 0.1420 (0.1402) loss: 0.8098 (0.8142) time: 0.2145 data: 0.1139 max mem: 9390 +Train: [90] [3100/6250] eta: 0:10:15 lr: 0.000003 grad: 0.1415 (0.1403) loss: 0.8139 (0.8142) time: 0.1697 data: 0.0823 max mem: 9390 +Train: [90] [3200/6250] eta: 0:09:53 lr: 0.000003 grad: 0.1389 (0.1405) loss: 0.8184 (0.8141) time: 0.1766 data: 0.0836 max mem: 9390 +Train: [90] [3300/6250] eta: 0:09:33 lr: 0.000003 grad: 0.1322 (0.1404) loss: 0.8239 (0.8142) time: 0.2228 data: 0.1099 max mem: 9390 +Train: [90] [3400/6250] eta: 0:09:20 lr: 0.000003 grad: 0.1344 (0.1404) loss: 0.8089 (0.8142) time: 0.2187 data: 0.1083 max mem: 9390 +Train: [90] [3500/6250] eta: 0:08:59 lr: 0.000003 grad: 0.1301 (0.1403) loss: 0.8187 (0.8142) time: 0.2060 data: 0.1047 max mem: 9390 +Train: [90] [3600/6250] eta: 0:08:39 lr: 0.000003 grad: 0.1307 (0.1402) loss: 0.8092 (0.8142) time: 0.1609 data: 0.0769 max mem: 9390 +Train: [90] [3700/6250] eta: 0:08:18 lr: 0.000003 grad: 0.1330 (0.1401) loss: 0.8121 (0.8142) time: 0.1845 data: 0.0791 max mem: 9390 +Train: [90] [3800/6250] eta: 0:07:58 lr: 0.000003 grad: 0.1322 (0.1401) loss: 0.8161 (0.8143) time: 0.1692 data: 0.0587 max mem: 9390 +Train: [90] [3900/6250] eta: 0:07:38 lr: 0.000003 grad: 0.1263 (0.1401) loss: 0.8145 (0.8143) time: 0.2250 data: 0.1151 max mem: 9390 +Train: [90] [4000/6250] eta: 0:07:19 lr: 0.000003 grad: 0.1382 (0.1400) loss: 0.8093 (0.8143) time: 0.1888 data: 0.0843 max mem: 9390 +Train: [90] [4100/6250] eta: 0:06:58 lr: 0.000003 grad: 0.1406 (0.1400) loss: 0.8163 (0.8142) time: 0.1714 data: 0.0779 max mem: 9390 +Train: [90] [4200/6250] eta: 0:06:38 lr: 0.000003 grad: 0.1370 (0.1400) loss: 0.8147 (0.8141) time: 0.1769 data: 0.0892 max mem: 9390 +Train: [90] [4300/6250] eta: 0:06:17 lr: 0.000003 grad: 0.1537 (0.1402) loss: 0.8051 (0.8140) time: 0.2042 data: 0.1157 max mem: 9390 +Train: [90] [4400/6250] eta: 0:05:57 lr: 0.000003 grad: 0.1315 (0.1401) loss: 0.8129 (0.8140) time: 0.2240 data: 0.1245 max mem: 9390 +Train: [90] [4500/6250] eta: 0:05:38 lr: 0.000003 grad: 0.1386 (0.1401) loss: 0.8148 (0.8139) time: 0.1106 data: 0.0003 max mem: 9390 +Train: [90] [4600/6250] eta: 0:05:19 lr: 0.000003 grad: 0.1423 (0.1402) loss: 0.8144 (0.8138) time: 0.1703 data: 0.0813 max mem: 9390 +Train: [90] [4700/6250] eta: 0:04:59 lr: 0.000003 grad: 0.1382 (0.1402) loss: 0.8112 (0.8138) time: 0.1896 data: 0.1038 max mem: 9390 +Train: [90] [4800/6250] eta: 0:04:39 lr: 0.000003 grad: 0.1541 (0.1403) loss: 0.8061 (0.8137) time: 0.1700 data: 0.0875 max mem: 9390 +Train: [90] [4900/6250] eta: 0:04:20 lr: 0.000003 grad: 0.1368 (0.1403) loss: 0.8071 (0.8136) time: 0.2363 data: 0.1537 max mem: 9390 +Train: [90] [5000/6250] eta: 0:04:01 lr: 0.000003 grad: 0.1405 (0.1404) loss: 0.8069 (0.8135) time: 0.1798 data: 0.0923 max mem: 9390 +Train: [90] [5100/6250] eta: 0:03:42 lr: 0.000003 grad: 0.1374 (0.1404) loss: 0.8123 (0.8135) time: 0.2035 data: 0.1254 max mem: 9390 +Train: [90] [5200/6250] eta: 0:03:23 lr: 0.000003 grad: 0.1360 (0.1405) loss: 0.8127 (0.8135) time: 0.1923 data: 0.1100 max mem: 9390 +Train: [90] [5300/6250] eta: 0:03:03 lr: 0.000003 grad: 0.1382 (0.1405) loss: 0.8095 (0.8134) time: 0.2040 data: 0.1098 max mem: 9390 +Train: [90] [5400/6250] eta: 0:02:44 lr: 0.000003 grad: 0.1313 (0.1405) loss: 0.8161 (0.8134) time: 0.1718 data: 0.0811 max mem: 9390 +Train: [90] [5500/6250] eta: 0:02:25 lr: 0.000003 grad: 0.1301 (0.1405) loss: 0.8109 (0.8133) time: 0.1908 data: 0.1082 max mem: 9390 +Train: [90] [5600/6250] eta: 0:02:05 lr: 0.000003 grad: 0.1419 (0.1405) loss: 0.8080 (0.8133) time: 0.1535 data: 0.0604 max mem: 9390 +Train: [90] [5700/6250] eta: 0:01:45 lr: 0.000003 grad: 0.1299 (0.1405) loss: 0.8124 (0.8133) time: 0.1795 data: 0.0834 max mem: 9390 +Train: [90] [5800/6250] eta: 0:01:26 lr: 0.000003 grad: 0.1466 (0.1406) loss: 0.8043 (0.8132) time: 0.1914 data: 0.0999 max mem: 9390 +Train: [90] [5900/6250] eta: 0:01:07 lr: 0.000003 grad: 0.1340 (0.1406) loss: 0.8114 (0.8132) time: 0.1717 data: 0.0782 max mem: 9390 +Train: [90] [6000/6250] eta: 0:00:47 lr: 0.000003 grad: 0.1361 (0.1407) loss: 0.8162 (0.8131) time: 0.1659 data: 0.0640 max mem: 9390 +Train: [90] [6100/6250] eta: 0:00:28 lr: 0.000003 grad: 0.1447 (0.1408) loss: 0.8126 (0.8131) time: 0.1672 data: 0.0847 max mem: 9390 +Train: [90] [6200/6250] eta: 0:00:09 lr: 0.000003 grad: 0.1373 (0.1408) loss: 0.8145 (0.8131) time: 0.1802 data: 0.0791 max mem: 9390 +Train: [90] [6249/6250] eta: 0:00:00 lr: 0.000003 grad: 0.1341 (0.1408) loss: 0.8138 (0.8131) time: 0.1217 data: 0.0212 max mem: 9390 +Train: [90] Total time: 0:19:58 (0.1917 s / it) +Averaged stats: lr: 0.000003 grad: 0.1341 (0.1408) loss: 0.8138 (0.8131) +Eval (hcp-train-subset): [90] [ 0/62] eta: 0:04:03 loss: 0.8219 (0.8219) time: 3.9276 data: 3.8305 max mem: 9390 +Eval (hcp-train-subset): [90] [61/62] eta: 0:00:00 loss: 0.8154 (0.8181) time: 0.1498 data: 0.1242 max mem: 9390 +Eval (hcp-train-subset): [90] Total time: 0:00:14 (0.2299 s / it) +Averaged stats (hcp-train-subset): loss: 0.8154 (0.8181) +Eval (hcp-val): [90] [ 0/62] eta: 0:05:42 loss: 0.8262 (0.8262) time: 5.5222 data: 5.4920 max mem: 9390 +Eval (hcp-val): [90] [61/62] eta: 0:00:00 loss: 0.8279 (0.8284) time: 0.1310 data: 0.1059 max mem: 9390 +Eval (hcp-val): [90] Total time: 0:00:14 (0.2339 s / it) +Averaged stats (hcp-val): loss: 0.8279 (0.8284) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +Train: [91] [ 0/6250] eta: 12:04:58 lr: 0.000003 grad: 0.5687 (0.5687) loss: 0.7916 (0.7916) time: 6.9598 data: 6.8528 max mem: 9390 +Train: [91] [ 100/6250] eta: 0:25:35 lr: 0.000003 grad: 0.1449 (0.1747) loss: 0.8209 (0.8246) time: 0.1890 data: 0.0800 max mem: 9390 +Train: [91] [ 200/6250] eta: 0:22:30 lr: 0.000003 grad: 0.1449 (0.1628) loss: 0.8165 (0.8228) time: 0.1977 data: 0.0968 max mem: 9390 +Train: [91] [ 300/6250] eta: 0:21:31 lr: 0.000003 grad: 0.1462 (0.1615) loss: 0.8049 (0.8193) time: 0.2886 data: 0.1836 max mem: 9390 +Train: [91] [ 400/6250] eta: 0:20:41 lr: 0.000003 grad: 0.1296 (0.1579) loss: 0.8156 (0.8190) time: 0.1877 data: 0.0552 max mem: 9390 +Train: [91] [ 500/6250] eta: 0:19:57 lr: 0.000003 grad: 0.1386 (0.1555) loss: 0.8188 (0.8185) time: 0.2049 data: 0.0963 max mem: 9390 +Train: [91] [ 600/6250] eta: 0:20:39 lr: 0.000003 grad: 0.1381 (0.1533) loss: 0.8152 (0.8185) time: 0.1615 data: 0.0014 max mem: 9390 +Train: [91] [ 700/6250] eta: 0:20:05 lr: 0.000003 grad: 0.1284 (0.1513) loss: 0.8182 (0.8184) time: 0.2025 data: 0.1094 max mem: 9390 +Train: [91] [ 800/6250] eta: 0:20:07 lr: 0.000003 grad: 0.1373 (0.1499) loss: 0.8151 (0.8182) time: 0.4398 data: 0.3263 max mem: 9390 +Train: [91] [ 900/6250] eta: 0:20:00 lr: 0.000003 grad: 0.1286 (0.1484) loss: 0.8232 (0.8181) time: 0.1221 data: 0.0186 max mem: 9390 +Train: [91] [1000/6250] eta: 0:19:21 lr: 0.000003 grad: 0.1273 (0.1471) loss: 0.8177 (0.8179) time: 0.2146 data: 0.0995 max mem: 9390 +Train: [91] [1100/6250] eta: 0:18:56 lr: 0.000003 grad: 0.1296 (0.1460) loss: 0.8172 (0.8177) time: 0.1052 data: 0.0006 max mem: 9390 +Train: [91] [1200/6250] eta: 0:18:18 lr: 0.000003 grad: 0.1292 (0.1451) loss: 0.8193 (0.8175) time: 0.1752 data: 0.0791 max mem: 9390 +Train: [91] [1300/6250] eta: 0:17:45 lr: 0.000003 grad: 0.1441 (0.1449) loss: 0.8101 (0.8172) time: 0.1685 data: 0.0734 max mem: 9390 +Train: [91] [1400/6250] eta: 0:17:14 lr: 0.000003 grad: 0.1326 (0.1443) loss: 0.8187 (0.8171) time: 0.1432 data: 0.0532 max mem: 9390 +Train: [91] [1500/6250] eta: 0:16:41 lr: 0.000003 grad: 0.1315 (0.1439) loss: 0.8101 (0.8170) time: 0.1496 data: 0.0588 max mem: 9390 +Train: [91] [1600/6250] eta: 0:16:22 lr: 0.000003 grad: 0.1325 (0.1434) loss: 0.8171 (0.8170) time: 0.1088 data: 0.0003 max mem: 9390 +Train: [91] [1700/6250] eta: 0:15:52 lr: 0.000003 grad: 0.1424 (0.1431) loss: 0.8142 (0.8170) time: 0.1032 data: 0.0005 max mem: 9390 +Train: [91] [1800/6250] eta: 0:15:21 lr: 0.000003 grad: 0.1357 (0.1428) loss: 0.8145 (0.8169) time: 0.1756 data: 0.0957 max mem: 9390 +Train: [91] [1900/6250] eta: 0:14:51 lr: 0.000003 grad: 0.1325 (0.1426) loss: 0.8155 (0.8169) time: 0.1720 data: 0.0783 max mem: 9390 +Train: [91] [2000/6250] eta: 0:14:26 lr: 0.000003 grad: 0.1331 (0.1424) loss: 0.8148 (0.8170) time: 0.2239 data: 0.1168 max mem: 9390 +Train: [91] [2100/6250] eta: 0:13:58 lr: 0.000003 grad: 0.1352 (0.1423) loss: 0.8165 (0.8171) time: 0.1451 data: 0.0350 max mem: 9390 +Train: [91] [2200/6250] eta: 0:13:34 lr: 0.000003 grad: 0.1277 (0.1419) loss: 0.8222 (0.8172) time: 0.1789 data: 0.0933 max mem: 9390 +Train: [91] [2300/6250] eta: 0:13:08 lr: 0.000003 grad: 0.1299 (0.1415) loss: 0.8137 (0.8172) time: 0.1731 data: 0.0836 max mem: 9390 +Train: [91] [2400/6250] eta: 0:12:43 lr: 0.000003 grad: 0.1309 (0.1411) loss: 0.8140 (0.8173) time: 0.1682 data: 0.0867 max mem: 9390 +Train: [91] [2500/6250] eta: 0:12:20 lr: 0.000003 grad: 0.1307 (0.1411) loss: 0.8247 (0.8173) time: 0.1761 data: 0.0942 max mem: 9390 +Train: [91] [2600/6250] eta: 0:12:00 lr: 0.000003 grad: 0.1302 (0.1409) loss: 0.8186 (0.8174) time: 0.2850 data: 0.1998 max mem: 9390 +Train: [91] [2700/6250] eta: 0:11:48 lr: 0.000002 grad: 0.1319 (0.1407) loss: 0.8209 (0.8174) time: 0.5403 data: 0.4481 max mem: 9390 +Train: [91] [2800/6250] eta: 0:11:23 lr: 0.000002 grad: 0.1343 (0.1406) loss: 0.8213 (0.8175) time: 0.1790 data: 0.1015 max mem: 9390 +Train: [91] [2900/6250] eta: 0:11:00 lr: 0.000002 grad: 0.1345 (0.1405) loss: 0.8120 (0.8174) time: 0.1614 data: 0.0623 max mem: 9390 +Train: [91] [3000/6250] eta: 0:10:43 lr: 0.000002 grad: 0.1424 (0.1405) loss: 0.8169 (0.8175) time: 0.3760 data: 0.2945 max mem: 9390 +Train: [91] [3100/6250] eta: 0:10:20 lr: 0.000002 grad: 0.1352 (0.1404) loss: 0.8081 (0.8174) time: 0.2107 data: 0.1157 max mem: 9390 +Train: [91] [3200/6250] eta: 0:10:00 lr: 0.000002 grad: 0.1349 (0.1402) loss: 0.8171 (0.8174) time: 0.1222 data: 0.0101 max mem: 9390 +Train: [91] [3300/6250] eta: 0:09:40 lr: 0.000002 grad: 0.1352 (0.1401) loss: 0.8171 (0.8174) time: 0.2312 data: 0.1419 max mem: 9390 +Train: [91] [3400/6250] eta: 0:09:20 lr: 0.000002 grad: 0.1353 (0.1401) loss: 0.8175 (0.8175) time: 0.1103 data: 0.0002 max mem: 9390 +Train: [91] [3500/6250] eta: 0:09:02 lr: 0.000002 grad: 0.1393 (0.1402) loss: 0.8143 (0.8174) time: 0.3224 data: 0.2326 max mem: 9390 +Train: [91] [3600/6250] eta: 0:08:44 lr: 0.000002 grad: 0.1411 (0.1401) loss: 0.8162 (0.8174) time: 0.4479 data: 0.3509 max mem: 9390 +Train: [91] [3700/6250] eta: 0:08:21 lr: 0.000002 grad: 0.1396 (0.1402) loss: 0.8144 (0.8174) time: 0.1175 data: 0.0219 max mem: 9390 +Train: [91] [3800/6250] eta: 0:08:01 lr: 0.000002 grad: 0.1384 (0.1403) loss: 0.8157 (0.8173) time: 0.1276 data: 0.0063 max mem: 9390 +Train: [91] [3900/6250] eta: 0:07:41 lr: 0.000002 grad: 0.1422 (0.1404) loss: 0.8114 (0.8172) time: 0.1587 data: 0.0461 max mem: 9390 +Train: [91] [4000/6250] eta: 0:07:22 lr: 0.000002 grad: 0.1513 (0.1405) loss: 0.8149 (0.8172) time: 0.1366 data: 0.0004 max mem: 9390 +Train: [91] [4100/6250] eta: 0:07:02 lr: 0.000002 grad: 0.1372 (0.1406) loss: 0.8113 (0.8171) time: 0.1808 data: 0.0758 max mem: 9390 +Train: [91] [4200/6250] eta: 0:06:42 lr: 0.000002 grad: 0.1337 (0.1407) loss: 0.8141 (0.8171) time: 0.2414 data: 0.1498 max mem: 9390 +Train: [91] [4300/6250] eta: 0:06:26 lr: 0.000002 grad: 0.1394 (0.1407) loss: 0.8178 (0.8170) time: 0.2671 data: 0.1728 max mem: 9390 +Train: [91] [4400/6250] eta: 0:06:05 lr: 0.000002 grad: 0.1403 (0.1408) loss: 0.8060 (0.8169) time: 0.1929 data: 0.1009 max mem: 9390 +Train: [91] [4500/6250] eta: 0:05:45 lr: 0.000002 grad: 0.1440 (0.1410) loss: 0.8100 (0.8167) time: 0.1740 data: 0.0861 max mem: 9390 +Train: [91] [4600/6250] eta: 0:05:24 lr: 0.000002 grad: 0.1500 (0.1412) loss: 0.8073 (0.8166) time: 0.1948 data: 0.1087 max mem: 9390 +Train: [91] [4700/6250] eta: 0:05:04 lr: 0.000002 grad: 0.1422 (0.1414) loss: 0.8166 (0.8165) time: 0.2023 data: 0.1210 max mem: 9390 +Train: [91] [4800/6250] eta: 0:04:45 lr: 0.000002 grad: 0.1453 (0.1416) loss: 0.8099 (0.8164) time: 0.1883 data: 0.0998 max mem: 9390 +Train: [91] [4900/6250] eta: 0:04:25 lr: 0.000002 grad: 0.1475 (0.1416) loss: 0.8084 (0.8163) time: 0.2549 data: 0.1806 max mem: 9390 +Train: [91] [5000/6250] eta: 0:04:06 lr: 0.000002 grad: 0.1521 (0.1417) loss: 0.8076 (0.8162) time: 0.1872 data: 0.0870 max mem: 9390 +Train: [91] [5100/6250] eta: 0:03:46 lr: 0.000002 grad: 0.1458 (0.1420) loss: 0.8119 (0.8161) time: 0.1683 data: 0.0868 max mem: 9390 +Train: [91] [5200/6250] eta: 0:03:26 lr: 0.000002 grad: 0.1584 (0.1423) loss: 0.8097 (0.8160) time: 0.1971 data: 0.1117 max mem: 9390 +Train: [91] [5300/6250] eta: 0:03:06 lr: 0.000002 grad: 0.1380 (0.1424) loss: 0.8115 (0.8159) time: 0.1863 data: 0.0861 max mem: 9390 +Train: [91] [5400/6250] eta: 0:02:46 lr: 0.000002 grad: 0.1397 (0.1425) loss: 0.8121 (0.8158) time: 0.1750 data: 0.0813 max mem: 9390 +Train: [91] [5500/6250] eta: 0:02:27 lr: 0.000002 grad: 0.1517 (0.1425) loss: 0.8092 (0.8157) time: 0.1823 data: 0.0970 max mem: 9390 +Train: [91] [5600/6250] eta: 0:02:07 lr: 0.000002 grad: 0.1329 (0.1426) loss: 0.8191 (0.8157) time: 0.1755 data: 0.0891 max mem: 9390 +Train: [91] [5700/6250] eta: 0:01:47 lr: 0.000002 grad: 0.1487 (0.1427) loss: 0.8071 (0.8156) time: 0.2129 data: 0.1283 max mem: 9390 +Train: [91] [5800/6250] eta: 0:01:27 lr: 0.000002 grad: 0.1346 (0.1427) loss: 0.8161 (0.8155) time: 0.1842 data: 0.0980 max mem: 9390 +Train: [91] [5900/6250] eta: 0:01:08 lr: 0.000002 grad: 0.1533 (0.1427) loss: 0.8101 (0.8155) time: 0.2009 data: 0.1210 max mem: 9390 +Train: [91] [6000/6250] eta: 0:00:48 lr: 0.000002 grad: 0.1448 (0.1428) loss: 0.8176 (0.8154) time: 0.2154 data: 0.1364 max mem: 9390 +Train: [91] [6100/6250] eta: 0:00:29 lr: 0.000002 grad: 0.1495 (0.1429) loss: 0.8131 (0.8153) time: 0.1751 data: 0.0845 max mem: 9390 +Train: [91] [6200/6250] eta: 0:00:09 lr: 0.000002 grad: 0.1501 (0.1430) loss: 0.8135 (0.8153) time: 0.2093 data: 0.1132 max mem: 9390 +Train: [91] [6249/6250] eta: 0:00:00 lr: 0.000002 grad: 0.1453 (0.1431) loss: 0.8134 (0.8153) time: 0.1689 data: 0.0851 max mem: 9390 +Train: [91] Total time: 0:20:27 (0.1963 s / it) +Averaged stats: lr: 0.000002 grad: 0.1453 (0.1431) loss: 0.8134 (0.8153) +Eval (hcp-train-subset): [91] [ 0/62] eta: 0:06:12 loss: 0.8230 (0.8230) time: 6.0136 data: 5.9824 max mem: 9390 +Eval (hcp-train-subset): [91] [61/62] eta: 0:00:00 loss: 0.8166 (0.8176) time: 0.1520 data: 0.1272 max mem: 9390 +Eval (hcp-train-subset): [91] Total time: 0:00:14 (0.2302 s / it) +Averaged stats (hcp-train-subset): loss: 0.8166 (0.8176) +Eval (hcp-val): [91] [ 0/62] eta: 0:03:57 loss: 0.8242 (0.8242) time: 3.8371 data: 3.7604 max mem: 9390 +Eval (hcp-val): [91] [61/62] eta: 0:00:00 loss: 0.8271 (0.8282) time: 0.1431 data: 0.1182 max mem: 9390 +Eval (hcp-val): [91] Total time: 0:00:13 (0.2252 s / it) +Averaged stats (hcp-val): loss: 0.8271 (0.8282) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +Train: [92] [ 0/6250] eta: 7:35:55 lr: 0.000002 grad: 0.0960 (0.0960) loss: 0.8587 (0.8587) time: 4.3770 data: 4.0438 max mem: 9390 +Train: [92] [ 100/6250] eta: 0:24:31 lr: 0.000002 grad: 0.1269 (0.1407) loss: 0.8246 (0.8278) time: 0.2427 data: 0.1393 max mem: 9390 +Train: [92] [ 200/6250] eta: 0:21:30 lr: 0.000002 grad: 0.1262 (0.1373) loss: 0.8359 (0.8281) time: 0.2070 data: 0.0952 max mem: 9390 +Train: [92] [ 300/6250] eta: 0:20:21 lr: 0.000002 grad: 0.1393 (0.1385) loss: 0.8238 (0.8272) time: 0.2066 data: 0.0835 max mem: 9390 +Train: [92] [ 400/6250] eta: 0:19:12 lr: 0.000002 grad: 0.1433 (0.1403) loss: 0.8225 (0.8263) time: 0.1756 data: 0.0711 max mem: 9390 +Train: [92] [ 500/6250] eta: 0:18:34 lr: 0.000002 grad: 0.1399 (0.1406) loss: 0.8224 (0.8256) time: 0.1225 data: 0.0369 max mem: 9390 +Train: [92] [ 600/6250] eta: 0:18:16 lr: 0.000002 grad: 0.1377 (0.1424) loss: 0.8194 (0.8239) time: 0.1771 data: 0.0633 max mem: 9390 +Train: [92] [ 700/6250] eta: 0:17:50 lr: 0.000002 grad: 0.1411 (0.1430) loss: 0.8142 (0.8229) time: 0.2153 data: 0.1182 max mem: 9390 +Train: [92] [ 800/6250] eta: 0:18:09 lr: 0.000002 grad: 0.1348 (0.1432) loss: 0.8180 (0.8218) time: 0.2211 data: 0.1182 max mem: 9390 +Train: [92] [ 900/6250] eta: 0:18:02 lr: 0.000002 grad: 0.1307 (0.1433) loss: 0.8190 (0.8211) time: 0.1964 data: 0.1035 max mem: 9390 +Train: [92] [1000/6250] eta: 0:17:21 lr: 0.000002 grad: 0.1366 (0.1435) loss: 0.8167 (0.8205) time: 0.1866 data: 0.0949 max mem: 9390 +Train: [92] [1100/6250] eta: 0:16:56 lr: 0.000002 grad: 0.1496 (0.1435) loss: 0.8143 (0.8200) time: 0.1678 data: 0.0601 max mem: 9390 +Train: [92] [1200/6250] eta: 0:16:37 lr: 0.000002 grad: 0.1356 (0.1432) loss: 0.8070 (0.8195) time: 0.1141 data: 0.0287 max mem: 9390 +Train: [92] [1300/6250] eta: 0:16:07 lr: 0.000002 grad: 0.1345 (0.1431) loss: 0.8054 (0.8191) time: 0.1597 data: 0.0716 max mem: 9390 +Train: [92] [1400/6250] eta: 0:15:40 lr: 0.000002 grad: 0.1494 (0.1434) loss: 0.8139 (0.8187) time: 0.1944 data: 0.0957 max mem: 9390 +Train: [92] [1500/6250] eta: 0:15:20 lr: 0.000002 grad: 0.1421 (0.1431) loss: 0.8170 (0.8185) time: 0.1201 data: 0.0106 max mem: 9390 +Train: [92] [1600/6250] eta: 0:14:54 lr: 0.000002 grad: 0.1397 (0.1432) loss: 0.8168 (0.8183) time: 0.1318 data: 0.0424 max mem: 9390 +Train: [92] [1700/6250] eta: 0:14:37 lr: 0.000002 grad: 0.1345 (0.1434) loss: 0.8113 (0.8181) time: 0.1168 data: 0.0003 max mem: 9390 +Train: [92] [1800/6250] eta: 0:14:10 lr: 0.000002 grad: 0.1441 (0.1433) loss: 0.8135 (0.8179) time: 0.1504 data: 0.0525 max mem: 9390 +Train: [92] [1900/6250] eta: 0:13:45 lr: 0.000002 grad: 0.1404 (0.1433) loss: 0.8176 (0.8177) time: 0.1697 data: 0.0823 max mem: 9390 +Train: [92] [2000/6250] eta: 0:13:22 lr: 0.000002 grad: 0.1398 (0.1434) loss: 0.8143 (0.8175) time: 0.1930 data: 0.1004 max mem: 9390 +Train: [92] [2100/6250] eta: 0:13:03 lr: 0.000002 grad: 0.1335 (0.1436) loss: 0.8108 (0.8173) time: 0.2692 data: 0.1705 max mem: 9390 +Train: [92] [2200/6250] eta: 0:12:42 lr: 0.000002 grad: 0.1507 (0.1437) loss: 0.8049 (0.8171) time: 0.1531 data: 0.0597 max mem: 9390 +Train: [92] [2300/6250] eta: 0:12:21 lr: 0.000002 grad: 0.1392 (0.1439) loss: 0.8124 (0.8168) time: 0.1749 data: 0.0891 max mem: 9390 +Train: [92] [2400/6250] eta: 0:11:58 lr: 0.000002 grad: 0.1472 (0.1439) loss: 0.8113 (0.8166) time: 0.1548 data: 0.0669 max mem: 9390 +Train: [92] [2500/6250] eta: 0:11:38 lr: 0.000002 grad: 0.1368 (0.1438) loss: 0.8104 (0.8164) time: 0.1462 data: 0.0090 max mem: 9390 +Train: [92] [2600/6250] eta: 0:11:19 lr: 0.000002 grad: 0.1423 (0.1437) loss: 0.8137 (0.8163) time: 0.1800 data: 0.0891 max mem: 9390 +Train: [92] [2700/6250] eta: 0:11:06 lr: 0.000002 grad: 0.1410 (0.1436) loss: 0.8140 (0.8163) time: 0.1213 data: 0.0243 max mem: 9390 +Train: [92] [2800/6250] eta: 0:10:46 lr: 0.000002 grad: 0.1392 (0.1435) loss: 0.8114 (0.8162) time: 0.1390 data: 0.0542 max mem: 9390 +Train: [92] [2900/6250] eta: 0:10:25 lr: 0.000002 grad: 0.1513 (0.1438) loss: 0.8129 (0.8162) time: 0.1512 data: 0.0453 max mem: 9390 +Train: [92] [3000/6250] eta: 0:10:05 lr: 0.000002 grad: 0.1489 (0.1438) loss: 0.8098 (0.8160) time: 0.1313 data: 0.0318 max mem: 9390 +Train: [92] [3100/6250] eta: 0:09:49 lr: 0.000002 grad: 0.1376 (0.1439) loss: 0.8067 (0.8159) time: 0.2033 data: 0.0638 max mem: 9390 +Train: [92] [3200/6250] eta: 0:09:29 lr: 0.000002 grad: 0.1572 (0.1441) loss: 0.8158 (0.8157) time: 0.1513 data: 0.0465 max mem: 9390 +Train: [92] [3300/6250] eta: 0:09:15 lr: 0.000002 grad: 0.1419 (0.1442) loss: 0.8152 (0.8156) time: 0.3473 data: 0.2286 max mem: 9390 +Train: [92] [3400/6250] eta: 0:08:56 lr: 0.000002 grad: 0.1482 (0.1444) loss: 0.8095 (0.8154) time: 0.2116 data: 0.1161 max mem: 9390 +Train: [92] [3500/6250] eta: 0:08:38 lr: 0.000002 grad: 0.1478 (0.1446) loss: 0.8087 (0.8152) time: 0.2776 data: 0.1761 max mem: 9390 +Train: [92] [3600/6250] eta: 0:08:18 lr: 0.000002 grad: 0.1379 (0.1447) loss: 0.8140 (0.8151) time: 0.1586 data: 0.0678 max mem: 9390 +Train: [92] [3700/6250] eta: 0:07:59 lr: 0.000002 grad: 0.1555 (0.1449) loss: 0.8091 (0.8149) time: 0.1381 data: 0.0340 max mem: 9390 +Train: [92] [3800/6250] eta: 0:07:41 lr: 0.000002 grad: 0.1475 (0.1450) loss: 0.8042 (0.8147) time: 0.2806 data: 0.1714 max mem: 9390 +Train: [92] [3900/6250] eta: 0:07:20 lr: 0.000002 grad: 0.1517 (0.1452) loss: 0.8123 (0.8146) time: 0.1889 data: 0.1000 max mem: 9390 +Train: [92] [4000/6250] eta: 0:07:02 lr: 0.000002 grad: 0.1462 (0.1453) loss: 0.8037 (0.8145) time: 0.1428 data: 0.0253 max mem: 9390 +Train: [92] [4100/6250] eta: 0:06:43 lr: 0.000002 grad: 0.1457 (0.1455) loss: 0.8061 (0.8144) time: 0.1637 data: 0.0708 max mem: 9390 +Train: [92] [4200/6250] eta: 0:06:26 lr: 0.000002 grad: 0.1501 (0.1455) loss: 0.8105 (0.8143) time: 0.1551 data: 0.0487 max mem: 9390 +Train: [92] [4300/6250] eta: 0:06:08 lr: 0.000002 grad: 0.1441 (0.1456) loss: 0.8075 (0.8142) time: 0.1465 data: 0.0538 max mem: 9390 +Train: [92] [4400/6250] eta: 0:05:48 lr: 0.000002 grad: 0.1442 (0.1456) loss: 0.8094 (0.8141) time: 0.1440 data: 0.0642 max mem: 9390 +Train: [92] [4500/6250] eta: 0:05:30 lr: 0.000002 grad: 0.1414 (0.1456) loss: 0.8101 (0.8141) time: 0.1706 data: 0.0814 max mem: 9390 +Train: [92] [4600/6250] eta: 0:05:10 lr: 0.000002 grad: 0.1367 (0.1457) loss: 0.8168 (0.8140) time: 0.1859 data: 0.0903 max mem: 9390 +Train: [92] [4700/6250] eta: 0:04:51 lr: 0.000002 grad: 0.1418 (0.1457) loss: 0.8149 (0.8139) time: 0.1662 data: 0.0770 max mem: 9390 +Train: [92] [4800/6250] eta: 0:04:32 lr: 0.000002 grad: 0.1368 (0.1456) loss: 0.8078 (0.8138) time: 0.1800 data: 0.0890 max mem: 9390 +Train: [92] [4900/6250] eta: 0:04:13 lr: 0.000002 grad: 0.1363 (0.1456) loss: 0.8118 (0.8138) time: 0.1717 data: 0.0806 max mem: 9390 +Train: [92] [5000/6250] eta: 0:03:54 lr: 0.000002 grad: 0.1383 (0.1456) loss: 0.8104 (0.8137) time: 0.1666 data: 0.0772 max mem: 9390 +Train: [92] [5100/6250] eta: 0:03:36 lr: 0.000002 grad: 0.1400 (0.1455) loss: 0.8063 (0.8137) time: 0.1706 data: 0.0839 max mem: 9390 +Train: [92] [5200/6250] eta: 0:03:17 lr: 0.000002 grad: 0.1383 (0.1455) loss: 0.8138 (0.8137) time: 0.1594 data: 0.0738 max mem: 9390 +Train: [92] [5300/6250] eta: 0:02:58 lr: 0.000002 grad: 0.1386 (0.1454) loss: 0.8113 (0.8136) time: 0.1562 data: 0.0637 max mem: 9390 +Train: [92] [5400/6250] eta: 0:02:39 lr: 0.000002 grad: 0.1511 (0.1454) loss: 0.8135 (0.8136) time: 0.1900 data: 0.1029 max mem: 9390 +Train: [92] [5500/6250] eta: 0:02:20 lr: 0.000002 grad: 0.1394 (0.1454) loss: 0.8141 (0.8136) time: 0.2042 data: 0.1122 max mem: 9390 +Train: [92] [5600/6250] eta: 0:02:01 lr: 0.000002 grad: 0.1438 (0.1453) loss: 0.8103 (0.8136) time: 0.1586 data: 0.0517 max mem: 9390 +Train: [92] [5700/6250] eta: 0:01:42 lr: 0.000002 grad: 0.1361 (0.1452) loss: 0.8153 (0.8137) time: 0.1817 data: 0.0859 max mem: 9390 +Train: [92] [5800/6250] eta: 0:01:23 lr: 0.000002 grad: 0.1384 (0.1451) loss: 0.8141 (0.8137) time: 0.1663 data: 0.0646 max mem: 9390 +Train: [92] [5900/6250] eta: 0:01:05 lr: 0.000002 grad: 0.1323 (0.1451) loss: 0.8176 (0.8137) time: 0.1814 data: 0.0848 max mem: 9390 +Train: [92] [6000/6250] eta: 0:00:46 lr: 0.000002 grad: 0.1462 (0.1450) loss: 0.8157 (0.8137) time: 0.1983 data: 0.1130 max mem: 9390 +Train: [92] [6100/6250] eta: 0:00:27 lr: 0.000002 grad: 0.1378 (0.1449) loss: 0.8174 (0.8138) time: 0.2146 data: 0.1200 max mem: 9390 +Train: [92] [6200/6250] eta: 0:00:09 lr: 0.000002 grad: 0.1349 (0.1449) loss: 0.8150 (0.8138) time: 0.2099 data: 0.1173 max mem: 9390 +Train: [92] [6249/6250] eta: 0:00:00 lr: 0.000002 grad: 0.1490 (0.1449) loss: 0.8154 (0.8138) time: 0.0945 data: 0.0002 max mem: 9390 +Train: [92] Total time: 0:19:29 (0.1871 s / it) +Averaged stats: lr: 0.000002 grad: 0.1490 (0.1449) loss: 0.8154 (0.8138) +Eval (hcp-train-subset): [92] [ 0/62] eta: 0:03:46 loss: 0.8207 (0.8207) time: 3.6543 data: 3.5490 max mem: 9390 +Eval (hcp-train-subset): [92] [61/62] eta: 0:00:00 loss: 0.8153 (0.8173) time: 0.1755 data: 0.1501 max mem: 9390 +Eval (hcp-train-subset): [92] Total time: 0:00:15 (0.2496 s / it) +Averaged stats (hcp-train-subset): loss: 0.8153 (0.8173) +Eval (hcp-val): [92] [ 0/62] eta: 0:05:24 loss: 0.8273 (0.8273) time: 5.2384 data: 5.2063 max mem: 9390 +Eval (hcp-val): [92] [61/62] eta: 0:00:00 loss: 0.8264 (0.8280) time: 0.1608 data: 0.1351 max mem: 9390 +Eval (hcp-val): [92] Total time: 0:00:16 (0.2676 s / it) +Averaged stats (hcp-val): loss: 0.8264 (0.8280) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +Train: [93] [ 0/6250] eta: 10:17:49 lr: 0.000002 grad: 0.2507 (0.2507) loss: 0.7948 (0.7948) time: 5.9312 data: 5.7532 max mem: 9390 +Train: [93] [ 100/6250] eta: 0:26:22 lr: 0.000002 grad: 0.1389 (0.2240) loss: 0.8250 (0.8184) time: 0.2144 data: 0.1073 max mem: 9390 +Train: [93] [ 200/6250] eta: 0:22:55 lr: 0.000002 grad: 0.1465 (0.1909) loss: 0.8210 (0.8230) time: 0.2012 data: 0.0965 max mem: 9390 +Train: [93] [ 300/6250] eta: 0:21:02 lr: 0.000002 grad: 0.1667 (0.1810) loss: 0.8308 (0.8231) time: 0.1408 data: 0.0277 max mem: 9390 +Train: [93] [ 400/6250] eta: 0:20:04 lr: 0.000002 grad: 0.1606 (0.1774) loss: 0.8188 (0.8218) time: 0.1547 data: 0.0549 max mem: 9390 +Train: [93] [ 500/6250] eta: 0:19:37 lr: 0.000002 grad: 0.1589 (0.1744) loss: 0.8136 (0.8208) time: 0.2142 data: 0.1055 max mem: 9390 +Train: [93] [ 600/6250] eta: 0:18:55 lr: 0.000002 grad: 0.1430 (0.1713) loss: 0.8161 (0.8196) time: 0.2057 data: 0.1027 max mem: 9390 +Train: [93] [ 700/6250] eta: 0:18:24 lr: 0.000002 grad: 0.1398 (0.1677) loss: 0.8223 (0.8195) time: 0.1172 data: 0.0043 max mem: 9390 +Train: [93] [ 800/6250] eta: 0:18:15 lr: 0.000002 grad: 0.1490 (0.1656) loss: 0.8121 (0.8191) time: 0.1612 data: 0.0643 max mem: 9390 +Train: [93] [ 900/6250] eta: 0:17:45 lr: 0.000002 grad: 0.1513 (0.1638) loss: 0.8196 (0.8187) time: 0.2023 data: 0.1022 max mem: 9390 +Train: [93] [1000/6250] eta: 0:17:12 lr: 0.000002 grad: 0.1464 (0.1622) loss: 0.8134 (0.8184) time: 0.1190 data: 0.0244 max mem: 9390 +Train: [93] [1100/6250] eta: 0:16:37 lr: 0.000002 grad: 0.1347 (0.1602) loss: 0.8189 (0.8185) time: 0.1660 data: 0.0697 max mem: 9390 +Train: [93] [1200/6250] eta: 0:16:07 lr: 0.000002 grad: 0.1379 (0.1588) loss: 0.8170 (0.8184) time: 0.1810 data: 0.0937 max mem: 9390 +Train: [93] [1300/6250] eta: 0:15:37 lr: 0.000002 grad: 0.1425 (0.1581) loss: 0.8165 (0.8182) time: 0.1601 data: 0.0645 max mem: 9390 +Train: [93] [1400/6250] eta: 0:15:11 lr: 0.000002 grad: 0.1451 (0.1573) loss: 0.8110 (0.8179) time: 0.1594 data: 0.0698 max mem: 9390 +Train: [93] [1500/6250] eta: 0:14:49 lr: 0.000002 grad: 0.1391 (0.1566) loss: 0.8101 (0.8175) time: 0.2048 data: 0.1223 max mem: 9390 +Train: [93] [1600/6250] eta: 0:14:30 lr: 0.000002 grad: 0.1357 (0.1560) loss: 0.8138 (0.8174) time: 0.1770 data: 0.0942 max mem: 9390 +Train: [93] [1700/6250] eta: 0:14:12 lr: 0.000002 grad: 0.1386 (0.1553) loss: 0.8184 (0.8173) time: 0.2159 data: 0.1237 max mem: 9390 +Train: [93] [1800/6250] eta: 0:14:00 lr: 0.000002 grad: 0.1392 (0.1547) loss: 0.8195 (0.8172) time: 0.2242 data: 0.0984 max mem: 9390 +Train: [93] [1900/6250] eta: 0:13:34 lr: 0.000002 grad: 0.1486 (0.1541) loss: 0.8185 (0.8171) time: 0.1988 data: 0.1012 max mem: 9390 +Train: [93] [2000/6250] eta: 0:13:12 lr: 0.000002 grad: 0.1449 (0.1536) loss: 0.8208 (0.8170) time: 0.2293 data: 0.1363 max mem: 9390 +Train: [93] [2100/6250] eta: 0:13:03 lr: 0.000002 grad: 0.1464 (0.1532) loss: 0.8123 (0.8169) time: 0.3533 data: 0.2479 max mem: 9390 +Train: [93] [2200/6250] eta: 0:12:39 lr: 0.000002 grad: 0.1472 (0.1530) loss: 0.8134 (0.8168) time: 0.1788 data: 0.0845 max mem: 9390 +Train: [93] [2300/6250] eta: 0:12:19 lr: 0.000001 grad: 0.1449 (0.1527) loss: 0.8129 (0.8167) time: 0.1692 data: 0.0695 max mem: 9390 +Train: [93] [2400/6250] eta: 0:11:59 lr: 0.000001 grad: 0.1426 (0.1525) loss: 0.8089 (0.8166) time: 0.2070 data: 0.1193 max mem: 9390 +Train: [93] [2500/6250] eta: 0:11:45 lr: 0.000001 grad: 0.1434 (0.1523) loss: 0.8128 (0.8165) time: 0.3052 data: 0.1900 max mem: 9390 +Train: [93] [2600/6250] eta: 0:11:26 lr: 0.000001 grad: 0.1370 (0.1521) loss: 0.8106 (0.8164) time: 0.1574 data: 0.0461 max mem: 9390 +Train: [93] [2700/6250] eta: 0:11:08 lr: 0.000001 grad: 0.1390 (0.1519) loss: 0.8125 (0.8163) time: 0.1200 data: 0.0180 max mem: 9390 +Train: [93] [2800/6250] eta: 0:10:47 lr: 0.000001 grad: 0.1382 (0.1517) loss: 0.8109 (0.8162) time: 0.1984 data: 0.0865 max mem: 9390 +Train: [93] [2900/6250] eta: 0:10:29 lr: 0.000001 grad: 0.1485 (0.1516) loss: 0.8118 (0.8160) time: 0.1659 data: 0.0516 max mem: 9390 +Train: [93] [3000/6250] eta: 0:10:10 lr: 0.000001 grad: 0.1439 (0.1515) loss: 0.8091 (0.8159) time: 0.2052 data: 0.1227 max mem: 9390 +Train: [93] [3100/6250] eta: 0:09:51 lr: 0.000001 grad: 0.1448 (0.1513) loss: 0.8170 (0.8158) time: 0.2838 data: 0.1916 max mem: 9390 +Train: [93] [3200/6250] eta: 0:09:30 lr: 0.000001 grad: 0.1431 (0.1513) loss: 0.8154 (0.8157) time: 0.1832 data: 0.0962 max mem: 9390 +Train: [93] [3300/6250] eta: 0:09:13 lr: 0.000001 grad: 0.1394 (0.1512) loss: 0.8130 (0.8155) time: 0.1153 data: 0.0037 max mem: 9390 +Train: [93] [3400/6250] eta: 0:08:56 lr: 0.000001 grad: 0.1410 (0.1512) loss: 0.8156 (0.8154) time: 0.3873 data: 0.2863 max mem: 9390 +Train: [93] [3500/6250] eta: 0:08:34 lr: 0.000001 grad: 0.1431 (0.1511) loss: 0.8083 (0.8153) time: 0.1670 data: 0.0825 max mem: 9390 +Train: [93] [3600/6250] eta: 0:08:14 lr: 0.000001 grad: 0.1407 (0.1510) loss: 0.8110 (0.8152) time: 0.1830 data: 0.0853 max mem: 9390 +Train: [93] [3700/6250] eta: 0:07:56 lr: 0.000001 grad: 0.1506 (0.1511) loss: 0.8086 (0.8151) time: 0.1852 data: 0.0920 max mem: 9390 +Train: [93] [3800/6250] eta: 0:07:36 lr: 0.000001 grad: 0.1293 (0.1510) loss: 0.8143 (0.8150) time: 0.1761 data: 0.0894 max mem: 9390 +Train: [93] [3900/6250] eta: 0:07:18 lr: 0.000001 grad: 0.1442 (0.1510) loss: 0.8109 (0.8149) time: 0.2530 data: 0.1627 max mem: 9390 +Train: [93] [4000/6250] eta: 0:07:00 lr: 0.000001 grad: 0.1402 (0.1509) loss: 0.8089 (0.8147) time: 0.1900 data: 0.0865 max mem: 9390 +Train: [93] [4100/6250] eta: 0:06:40 lr: 0.000001 grad: 0.1488 (0.1510) loss: 0.8156 (0.8146) time: 0.1744 data: 0.0774 max mem: 9390 +Train: [93] [4200/6250] eta: 0:06:21 lr: 0.000001 grad: 0.1373 (0.1509) loss: 0.8177 (0.8145) time: 0.1283 data: 0.0003 max mem: 9390 +Train: [93] [4300/6250] eta: 0:06:02 lr: 0.000001 grad: 0.1440 (0.1508) loss: 0.8095 (0.8144) time: 0.1445 data: 0.0615 max mem: 9390 +Train: [93] [4400/6250] eta: 0:05:44 lr: 0.000001 grad: 0.1297 (0.1506) loss: 0.8147 (0.8144) time: 0.1757 data: 0.0947 max mem: 9390 +Train: [93] [4500/6250] eta: 0:05:25 lr: 0.000001 grad: 0.1310 (0.1504) loss: 0.8173 (0.8144) time: 0.1696 data: 0.0854 max mem: 9390 +Train: [93] [4600/6250] eta: 0:05:06 lr: 0.000001 grad: 0.1359 (0.1502) loss: 0.8159 (0.8144) time: 0.1918 data: 0.1057 max mem: 9390 +Train: [93] [4700/6250] eta: 0:04:47 lr: 0.000001 grad: 0.1397 (0.1500) loss: 0.8113 (0.8144) time: 0.1724 data: 0.0775 max mem: 9390 +Train: [93] [4800/6250] eta: 0:04:29 lr: 0.000001 grad: 0.1466 (0.1499) loss: 0.8124 (0.8144) time: 0.2964 data: 0.2208 max mem: 9390 +Train: [93] [4900/6250] eta: 0:04:10 lr: 0.000001 grad: 0.1426 (0.1497) loss: 0.8166 (0.8144) time: 0.1744 data: 0.0937 max mem: 9390 +Train: [93] [5000/6250] eta: 0:03:51 lr: 0.000001 grad: 0.1418 (0.1495) loss: 0.8155 (0.8144) time: 0.1482 data: 0.0672 max mem: 9390 +Train: [93] [5100/6250] eta: 0:03:32 lr: 0.000001 grad: 0.1424 (0.1494) loss: 0.8124 (0.8143) time: 0.1630 data: 0.0681 max mem: 9390 +Train: [93] [5200/6250] eta: 0:03:14 lr: 0.000001 grad: 0.1390 (0.1492) loss: 0.8140 (0.8143) time: 0.1840 data: 0.0970 max mem: 9390 +Train: [93] [5300/6250] eta: 0:02:55 lr: 0.000001 grad: 0.1422 (0.1490) loss: 0.8145 (0.8143) time: 0.1953 data: 0.1111 max mem: 9390 +Train: [93] [5400/6250] eta: 0:02:36 lr: 0.000001 grad: 0.1346 (0.1488) loss: 0.8137 (0.8143) time: 0.1543 data: 0.0538 max mem: 9390 +Train: [93] [5500/6250] eta: 0:02:17 lr: 0.000001 grad: 0.1318 (0.1487) loss: 0.8144 (0.8143) time: 0.1835 data: 0.0930 max mem: 9390 +Train: [93] [5600/6250] eta: 0:01:59 lr: 0.000001 grad: 0.1403 (0.1485) loss: 0.8128 (0.8143) time: 0.1690 data: 0.0748 max mem: 9390 +Train: [93] [5700/6250] eta: 0:01:40 lr: 0.000001 grad: 0.1405 (0.1484) loss: 0.8106 (0.8143) time: 0.1826 data: 0.0945 max mem: 9390 +Train: [93] [5800/6250] eta: 0:01:22 lr: 0.000001 grad: 0.1305 (0.1483) loss: 0.8135 (0.8143) time: 0.2164 data: 0.1289 max mem: 9390 +Train: [93] [5900/6250] eta: 0:01:04 lr: 0.000001 grad: 0.1376 (0.1481) loss: 0.8175 (0.8143) time: 0.1828 data: 0.0845 max mem: 9390 +Train: [93] [6000/6250] eta: 0:00:45 lr: 0.000001 grad: 0.1417 (0.1480) loss: 0.8183 (0.8143) time: 0.1656 data: 0.0752 max mem: 9390 +Train: [93] [6100/6250] eta: 0:00:27 lr: 0.000001 grad: 0.1336 (0.1479) loss: 0.8135 (0.8143) time: 0.1831 data: 0.1000 max mem: 9390 +Train: [93] [6200/6250] eta: 0:00:09 lr: 0.000001 grad: 0.1343 (0.1478) loss: 0.8164 (0.8144) time: 0.1695 data: 0.0777 max mem: 9390 +Train: [93] [6249/6250] eta: 0:00:00 lr: 0.000001 grad: 0.1465 (0.1477) loss: 0.8135 (0.8144) time: 0.1560 data: 0.0674 max mem: 9390 +Train: [93] Total time: 0:19:12 (0.1844 s / it) +Averaged stats: lr: 0.000001 grad: 0.1465 (0.1477) loss: 0.8135 (0.8144) +Eval (hcp-train-subset): [93] [ 0/62] eta: 0:04:40 loss: 0.8169 (0.8169) time: 4.5164 data: 4.4161 max mem: 9390 +Eval (hcp-train-subset): [93] [61/62] eta: 0:00:00 loss: 0.8153 (0.8168) time: 0.1430 data: 0.1174 max mem: 9390 +Eval (hcp-train-subset): [93] Total time: 0:00:14 (0.2328 s / it) +Averaged stats (hcp-train-subset): loss: 0.8153 (0.8168) +Eval (hcp-val): [93] [ 0/62] eta: 0:03:55 loss: 0.8239 (0.8239) time: 3.8040 data: 3.7124 max mem: 9390 +Eval (hcp-val): [93] [61/62] eta: 0:00:00 loss: 0.8272 (0.8279) time: 0.1562 data: 0.1292 max mem: 9390 +Eval (hcp-val): [93] Total time: 0:00:16 (0.2652 s / it) +Averaged stats (hcp-val): loss: 0.8272 (0.8279) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +Train: [94] [ 0/6250] eta: 10:31:40 lr: 0.000001 grad: 0.3242 (0.3242) loss: 0.8674 (0.8674) time: 6.0640 data: 5.8733 max mem: 9390 +Train: [94] [ 100/6250] eta: 0:28:04 lr: 0.000001 grad: 0.1615 (0.1989) loss: 0.8101 (0.8076) time: 0.2225 data: 0.1113 max mem: 9390 +Train: [94] [ 200/6250] eta: 0:23:30 lr: 0.000001 grad: 0.1412 (0.1797) loss: 0.8181 (0.8120) time: 0.2169 data: 0.1191 max mem: 9390 +Train: [94] [ 300/6250] eta: 0:21:38 lr: 0.000001 grad: 0.1615 (0.1749) loss: 0.8181 (0.8133) time: 0.1552 data: 0.0632 max mem: 9390 +Train: [94] [ 400/6250] eta: 0:20:30 lr: 0.000001 grad: 0.1500 (0.1724) loss: 0.8154 (0.8133) time: 0.1981 data: 0.1031 max mem: 9390 +Train: [94] [ 500/6250] eta: 0:20:01 lr: 0.000001 grad: 0.1497 (0.1690) loss: 0.8111 (0.8132) time: 0.1806 data: 0.0927 max mem: 9390 +Train: [94] [ 600/6250] eta: 0:19:15 lr: 0.000001 grad: 0.1418 (0.1668) loss: 0.8235 (0.8133) time: 0.1889 data: 0.0942 max mem: 9390 +Train: [94] [ 700/6250] eta: 0:18:52 lr: 0.000001 grad: 0.1527 (0.1650) loss: 0.8178 (0.8140) time: 0.1569 data: 0.0375 max mem: 9390 +Train: [94] [ 800/6250] eta: 0:18:19 lr: 0.000001 grad: 0.1434 (0.1638) loss: 0.8131 (0.8140) time: 0.1796 data: 0.0852 max mem: 9390 +Train: [94] [ 900/6250] eta: 0:17:54 lr: 0.000001 grad: 0.1420 (0.1621) loss: 0.8168 (0.8141) time: 0.1994 data: 0.1127 max mem: 9390 +Train: [94] [1000/6250] eta: 0:17:27 lr: 0.000001 grad: 0.1457 (0.1608) loss: 0.8146 (0.8142) time: 0.2044 data: 0.1230 max mem: 9390 +Train: [94] [1100/6250] eta: 0:17:01 lr: 0.000001 grad: 0.1403 (0.1598) loss: 0.8156 (0.8141) time: 0.2215 data: 0.1152 max mem: 9390 +Train: [94] [1200/6250] eta: 0:16:39 lr: 0.000001 grad: 0.1473 (0.1590) loss: 0.8080 (0.8141) time: 0.1236 data: 0.0298 max mem: 9390 +Train: [94] [1300/6250] eta: 0:16:10 lr: 0.000001 grad: 0.1417 (0.1583) loss: 0.8130 (0.8140) time: 0.1862 data: 0.1027 max mem: 9390 +Train: [94] [1400/6250] eta: 0:15:43 lr: 0.000001 grad: 0.1458 (0.1576) loss: 0.8136 (0.8140) time: 0.1503 data: 0.0550 max mem: 9390 +Train: [94] [1500/6250] eta: 0:15:15 lr: 0.000001 grad: 0.1396 (0.1569) loss: 0.8145 (0.8140) time: 0.1873 data: 0.0865 max mem: 9390 +Train: [94] [1600/6250] eta: 0:14:52 lr: 0.000001 grad: 0.1479 (0.1561) loss: 0.8091 (0.8140) time: 0.1137 data: 0.0003 max mem: 9390 +Train: [94] [1700/6250] eta: 0:14:33 lr: 0.000001 grad: 0.1427 (0.1554) loss: 0.8137 (0.8139) time: 0.2340 data: 0.1500 max mem: 9390 +Train: [94] [1800/6250] eta: 0:14:13 lr: 0.000001 grad: 0.1404 (0.1547) loss: 0.8101 (0.8139) time: 0.2563 data: 0.1626 max mem: 9390 +Train: [94] [1900/6250] eta: 0:13:56 lr: 0.000001 grad: 0.1442 (0.1543) loss: 0.8182 (0.8140) time: 0.1995 data: 0.1043 max mem: 9390 +Train: [94] [2000/6250] eta: 0:13:37 lr: 0.000001 grad: 0.1449 (0.1538) loss: 0.8111 (0.8140) time: 0.1306 data: 0.0233 max mem: 9390 +Train: [94] [2100/6250] eta: 0:13:17 lr: 0.000001 grad: 0.1441 (0.1535) loss: 0.8133 (0.8139) time: 0.1678 data: 0.0770 max mem: 9390 +Train: [94] [2200/6250] eta: 0:12:55 lr: 0.000001 grad: 0.1537 (0.1534) loss: 0.8096 (0.8137) time: 0.1881 data: 0.0723 max mem: 9390 +Train: [94] [2300/6250] eta: 0:12:37 lr: 0.000001 grad: 0.1404 (0.1534) loss: 0.8146 (0.8137) time: 0.1616 data: 0.0584 max mem: 9390 +Train: [94] [2400/6250] eta: 0:12:24 lr: 0.000001 grad: 0.1425 (0.1532) loss: 0.8130 (0.8136) time: 0.1018 data: 0.0002 max mem: 9390 +Train: [94] [2500/6250] eta: 0:12:00 lr: 0.000001 grad: 0.1414 (0.1531) loss: 0.8186 (0.8136) time: 0.1641 data: 0.0684 max mem: 9390 +Train: [94] [2600/6250] eta: 0:11:39 lr: 0.000001 grad: 0.1564 (0.1531) loss: 0.8083 (0.8135) time: 0.2079 data: 0.1141 max mem: 9390 +Train: [94] [2700/6250] eta: 0:11:22 lr: 0.000001 grad: 0.1453 (0.1529) loss: 0.8191 (0.8135) time: 0.1499 data: 0.0593 max mem: 9390 +Train: [94] [2800/6250] eta: 0:10:59 lr: 0.000001 grad: 0.1406 (0.1526) loss: 0.8123 (0.8135) time: 0.1627 data: 0.0768 max mem: 9390 +Train: [94] [2900/6250] eta: 0:10:39 lr: 0.000001 grad: 0.1450 (0.1525) loss: 0.8127 (0.8135) time: 0.1450 data: 0.0423 max mem: 9390 +Train: [94] [3000/6250] eta: 0:10:20 lr: 0.000001 grad: 0.1417 (0.1523) loss: 0.8134 (0.8134) time: 0.0997 data: 0.0002 max mem: 9390 +Train: [94] [3100/6250] eta: 0:09:59 lr: 0.000001 grad: 0.1407 (0.1521) loss: 0.8151 (0.8134) time: 0.1752 data: 0.0847 max mem: 9390 +Train: [94] [3200/6250] eta: 0:09:42 lr: 0.000001 grad: 0.1447 (0.1519) loss: 0.8155 (0.8134) time: 0.1233 data: 0.0003 max mem: 9390 +Train: [94] [3300/6250] eta: 0:09:20 lr: 0.000001 grad: 0.1404 (0.1516) loss: 0.8167 (0.8135) time: 0.1574 data: 0.0613 max mem: 9390 +Train: [94] [3400/6250] eta: 0:09:00 lr: 0.000001 grad: 0.1415 (0.1513) loss: 0.8124 (0.8135) time: 0.1748 data: 0.0852 max mem: 9390 +Train: [94] [3500/6250] eta: 0:08:40 lr: 0.000001 grad: 0.1374 (0.1510) loss: 0.8141 (0.8136) time: 0.1483 data: 0.0561 max mem: 9390 +Train: [94] [3600/6250] eta: 0:08:19 lr: 0.000001 grad: 0.1388 (0.1509) loss: 0.8182 (0.8137) time: 0.1671 data: 0.0802 max mem: 9390 +Train: [94] [3700/6250] eta: 0:08:00 lr: 0.000001 grad: 0.1407 (0.1507) loss: 0.8193 (0.8138) time: 0.1784 data: 0.0948 max mem: 9390 +Train: [94] [3800/6250] eta: 0:07:39 lr: 0.000001 grad: 0.1468 (0.1505) loss: 0.8139 (0.8138) time: 0.1792 data: 0.0920 max mem: 9390 +Train: [94] [3900/6250] eta: 0:07:22 lr: 0.000001 grad: 0.1415 (0.1504) loss: 0.8130 (0.8139) time: 0.1403 data: 0.0434 max mem: 9390 +Train: [94] [4000/6250] eta: 0:07:07 lr: 0.000001 grad: 0.1463 (0.1503) loss: 0.8115 (0.8138) time: 0.6184 data: 0.5297 max mem: 9390 +Train: [94] [4100/6250] eta: 0:06:47 lr: 0.000001 grad: 0.1398 (0.1502) loss: 0.8087 (0.8138) time: 0.2111 data: 0.1271 max mem: 9390 +Train: [94] [4200/6250] eta: 0:06:26 lr: 0.000001 grad: 0.1324 (0.1499) loss: 0.8163 (0.8139) time: 0.1764 data: 0.0952 max mem: 9390 +Train: [94] [4300/6250] eta: 0:06:08 lr: 0.000001 grad: 0.1393 (0.1497) loss: 0.8146 (0.8140) time: 0.1859 data: 0.0907 max mem: 9390 +Train: [94] [4400/6250] eta: 0:05:48 lr: 0.000001 grad: 0.1398 (0.1495) loss: 0.8179 (0.8140) time: 0.1569 data: 0.0596 max mem: 9390 +Train: [94] [4500/6250] eta: 0:05:31 lr: 0.000001 grad: 0.1338 (0.1492) loss: 0.8183 (0.8140) time: 0.2733 data: 0.1843 max mem: 9390 +Train: [94] [4600/6250] eta: 0:05:12 lr: 0.000001 grad: 0.1429 (0.1491) loss: 0.8150 (0.8140) time: 0.1821 data: 0.1013 max mem: 9390 +Train: [94] [4700/6250] eta: 0:04:54 lr: 0.000001 grad: 0.1333 (0.1489) loss: 0.8116 (0.8140) time: 0.2030 data: 0.1224 max mem: 9390 +Train: [94] [4800/6250] eta: 0:04:36 lr: 0.000001 grad: 0.1366 (0.1487) loss: 0.8154 (0.8140) time: 0.2131 data: 0.1236 max mem: 9390 +Train: [94] [4900/6250] eta: 0:04:17 lr: 0.000001 grad: 0.1369 (0.1485) loss: 0.8119 (0.8140) time: 0.1920 data: 0.1007 max mem: 9390 +Train: [94] [5000/6250] eta: 0:03:58 lr: 0.000001 grad: 0.1420 (0.1483) loss: 0.8136 (0.8140) time: 0.1962 data: 0.1056 max mem: 9390 +Train: [94] [5100/6250] eta: 0:03:40 lr: 0.000001 grad: 0.1365 (0.1482) loss: 0.8146 (0.8141) time: 0.2308 data: 0.1364 max mem: 9390 +Train: [94] [5200/6250] eta: 0:03:21 lr: 0.000001 grad: 0.1397 (0.1481) loss: 0.8123 (0.8140) time: 0.2174 data: 0.1215 max mem: 9390 +Train: [94] [5300/6250] eta: 0:03:02 lr: 0.000001 grad: 0.1475 (0.1480) loss: 0.8092 (0.8140) time: 0.1875 data: 0.0946 max mem: 9390 +Train: [94] [5400/6250] eta: 0:02:42 lr: 0.000001 grad: 0.1328 (0.1479) loss: 0.8100 (0.8139) time: 0.1593 data: 0.0591 max mem: 9390 +Train: [94] [5500/6250] eta: 0:02:23 lr: 0.000001 grad: 0.1328 (0.1477) loss: 0.8173 (0.8140) time: 0.1823 data: 0.0832 max mem: 9390 +Train: [94] [5600/6250] eta: 0:02:04 lr: 0.000001 grad: 0.1338 (0.1476) loss: 0.8125 (0.8140) time: 0.1671 data: 0.0858 max mem: 9390 +Train: [94] [5700/6250] eta: 0:01:45 lr: 0.000001 grad: 0.1468 (0.1476) loss: 0.8097 (0.8139) time: 0.1767 data: 0.0843 max mem: 9390 +Train: [94] [5800/6250] eta: 0:01:26 lr: 0.000001 grad: 0.1542 (0.1475) loss: 0.8073 (0.8139) time: 0.1903 data: 0.0996 max mem: 9390 +Train: [94] [5900/6250] eta: 0:01:06 lr: 0.000001 grad: 0.1395 (0.1474) loss: 0.8168 (0.8140) time: 0.1946 data: 0.0929 max mem: 9390 +Train: [94] [6000/6250] eta: 0:00:47 lr: 0.000001 grad: 0.1400 (0.1474) loss: 0.8155 (0.8140) time: 0.2063 data: 0.1099 max mem: 9390 +Train: [94] [6100/6250] eta: 0:00:28 lr: 0.000001 grad: 0.1392 (0.1473) loss: 0.8185 (0.8140) time: 0.1338 data: 0.0005 max mem: 9390 +Train: [94] [6200/6250] eta: 0:00:09 lr: 0.000001 grad: 0.1444 (0.1474) loss: 0.8151 (0.8140) time: 0.1795 data: 0.0873 max mem: 9390 +Train: [94] [6249/6250] eta: 0:00:00 lr: 0.000001 grad: 0.1350 (0.1473) loss: 0.8137 (0.8140) time: 0.2144 data: 0.1226 max mem: 9390 +Train: [94] Total time: 0:20:01 (0.1923 s / it) +Averaged stats: lr: 0.000001 grad: 0.1350 (0.1473) loss: 0.8137 (0.8140) +Eval (hcp-train-subset): [94] [ 0/62] eta: 0:03:25 loss: 0.8218 (0.8218) time: 3.3212 data: 3.1781 max mem: 9390 +Eval (hcp-train-subset): [94] [61/62] eta: 0:00:00 loss: 0.8132 (0.8164) time: 0.1471 data: 0.1221 max mem: 9390 +Eval (hcp-train-subset): [94] Total time: 0:00:15 (0.2461 s / it) +Averaged stats (hcp-train-subset): loss: 0.8132 (0.8164) +Making plots (hcp-train-subset): example=1 +Eval (hcp-val): [94] [ 0/62] eta: 0:03:25 loss: 0.8249 (0.8249) time: 3.3112 data: 3.1926 max mem: 9390 +Eval (hcp-val): [94] [61/62] eta: 0:00:00 loss: 0.8265 (0.8276) time: 0.1428 data: 0.1177 max mem: 9390 +Eval (hcp-val): [94] Total time: 0:00:14 (0.2283 s / it) +Averaged stats (hcp-val): loss: 0.8265 (0.8276) +Making plots (hcp-val): example=3 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +Train: [95] [ 0/6250] eta: 10:23:41 lr: 0.000001 grad: 0.2029 (0.2029) loss: 0.8351 (0.8351) time: 5.9875 data: 5.6757 max mem: 9390 +Train: [95] [ 100/6250] eta: 0:24:40 lr: 0.000001 grad: 0.1742 (0.1923) loss: 0.8109 (0.8107) time: 0.1838 data: 0.0761 max mem: 9390 +Train: [95] [ 200/6250] eta: 0:21:26 lr: 0.000001 grad: 0.1464 (0.1795) loss: 0.8127 (0.8127) time: 0.1762 data: 0.0750 max mem: 9390 +Train: [95] [ 300/6250] eta: 0:20:15 lr: 0.000001 grad: 0.1568 (0.1740) loss: 0.8126 (0.8133) time: 0.1684 data: 0.0644 max mem: 9390 +Train: [95] [ 400/6250] eta: 0:19:28 lr: 0.000001 grad: 0.1446 (0.1679) loss: 0.8164 (0.8147) time: 0.1654 data: 0.0381 max mem: 9390 +Train: [95] [ 500/6250] eta: 0:21:01 lr: 0.000001 grad: 0.1410 (0.1644) loss: 0.8130 (0.8150) time: 0.1420 data: 0.0003 max mem: 9390 +Train: [95] [ 600/6250] eta: 0:20:11 lr: 0.000001 grad: 0.1395 (0.1613) loss: 0.8213 (0.8155) time: 0.1867 data: 0.0676 max mem: 9390 +Train: [95] [ 700/6250] eta: 0:19:22 lr: 0.000001 grad: 0.1392 (0.1590) loss: 0.8168 (0.8157) time: 0.1771 data: 0.0831 max mem: 9390 +Train: [95] [ 800/6250] eta: 0:18:53 lr: 0.000001 grad: 0.1451 (0.1580) loss: 0.8235 (0.8162) time: 0.1351 data: 0.0468 max mem: 9390 +Train: [95] [ 900/6250] eta: 0:19:32 lr: 0.000001 grad: 0.1299 (0.1559) loss: 0.8237 (0.8168) time: 0.3080 data: 0.1619 max mem: 9390 +Train: [95] [1000/6250] eta: 0:19:06 lr: 0.000001 grad: 0.1384 (0.1540) loss: 0.8213 (0.8173) time: 0.0991 data: 0.0002 max mem: 9390 +Train: [95] [1100/6250] eta: 0:18:27 lr: 0.000001 grad: 0.1398 (0.1526) loss: 0.8259 (0.8177) time: 0.1741 data: 0.0746 max mem: 9390 +Train: [95] [1200/6250] eta: 0:17:57 lr: 0.000001 grad: 0.1328 (0.1511) loss: 0.8238 (0.8181) time: 0.1635 data: 0.0739 max mem: 9390 +Train: [95] [1300/6250] eta: 0:17:17 lr: 0.000001 grad: 0.1256 (0.1502) loss: 0.8209 (0.8184) time: 0.1667 data: 0.0845 max mem: 9390 +Train: [95] [1400/6250] eta: 0:16:52 lr: 0.000001 grad: 0.1418 (0.1501) loss: 0.8160 (0.8184) time: 0.2910 data: 0.1997 max mem: 9390 +Train: [95] [1500/6250] eta: 0:16:21 lr: 0.000001 grad: 0.1423 (0.1496) loss: 0.8199 (0.8185) time: 0.1730 data: 0.0845 max mem: 9390 +Train: [95] [1600/6250] eta: 0:15:57 lr: 0.000001 grad: 0.1369 (0.1489) loss: 0.8184 (0.8186) time: 0.1693 data: 0.0707 max mem: 9390 +Train: [95] [1700/6250] eta: 0:15:39 lr: 0.000001 grad: 0.1371 (0.1484) loss: 0.8186 (0.8187) time: 0.2913 data: 0.1870 max mem: 9390 +Train: [95] [1800/6250] eta: 0:15:10 lr: 0.000001 grad: 0.1324 (0.1479) loss: 0.8212 (0.8189) time: 0.1455 data: 0.0004 max mem: 9390 +Train: [95] [1900/6250] eta: 0:14:51 lr: 0.000001 grad: 0.1409 (0.1474) loss: 0.8157 (0.8190) time: 0.1298 data: 0.0095 max mem: 9390 +Train: [95] [2000/6250] eta: 0:14:38 lr: 0.000001 grad: 0.1291 (0.1470) loss: 0.8209 (0.8191) time: 0.2847 data: 0.1699 max mem: 9390 +Train: [95] [2100/6250] eta: 0:14:10 lr: 0.000001 grad: 0.1423 (0.1467) loss: 0.8218 (0.8191) time: 0.2336 data: 0.1339 max mem: 9390 +Train: [95] [2200/6250] eta: 0:13:53 lr: 0.000001 grad: 0.1432 (0.1465) loss: 0.8153 (0.8191) time: 0.1166 data: 0.0002 max mem: 9390 +Train: [95] [2300/6250] eta: 0:13:27 lr: 0.000001 grad: 0.1420 (0.1463) loss: 0.8144 (0.8190) time: 0.1081 data: 0.0004 max mem: 9390 +Train: [95] [2400/6250] eta: 0:13:07 lr: 0.000001 grad: 0.1331 (0.1460) loss: 0.8161 (0.8191) time: 0.1074 data: 0.0003 max mem: 9390 +Train: [95] [2500/6250] eta: 0:12:54 lr: 0.000001 grad: 0.1337 (0.1458) loss: 0.8184 (0.8191) time: 0.2407 data: 0.1249 max mem: 9390 +Train: [95] [2600/6250] eta: 0:12:25 lr: 0.000001 grad: 0.1322 (0.1455) loss: 0.8215 (0.8191) time: 0.1607 data: 0.0743 max mem: 9390 +Train: [95] [2700/6250] eta: 0:12:01 lr: 0.000001 grad: 0.1309 (0.1453) loss: 0.8133 (0.8190) time: 0.1788 data: 0.0842 max mem: 9390 +Train: [95] [2800/6250] eta: 0:11:41 lr: 0.000001 grad: 0.1322 (0.1450) loss: 0.8216 (0.8190) time: 0.1108 data: 0.0002 max mem: 9390 +Train: [95] [2900/6250] eta: 0:11:17 lr: 0.000001 grad: 0.1317 (0.1448) loss: 0.8173 (0.8189) time: 0.1549 data: 0.0599 max mem: 9390 +Train: [95] [3000/6250] eta: 0:10:54 lr: 0.000001 grad: 0.1400 (0.1446) loss: 0.8148 (0.8188) time: 0.2009 data: 0.1131 max mem: 9390 +Train: [95] [3100/6250] eta: 0:10:33 lr: 0.000001 grad: 0.1383 (0.1445) loss: 0.8171 (0.8186) time: 0.2364 data: 0.1438 max mem: 9390 +Train: [95] [3200/6250] eta: 0:10:11 lr: 0.000001 grad: 0.1491 (0.1445) loss: 0.8065 (0.8185) time: 0.1660 data: 0.0833 max mem: 9390 +Train: [95] [3300/6250] eta: 0:09:48 lr: 0.000001 grad: 0.1423 (0.1444) loss: 0.8158 (0.8183) time: 0.1715 data: 0.0834 max mem: 9390 +Train: [95] [3400/6250] eta: 0:09:26 lr: 0.000001 grad: 0.1372 (0.1445) loss: 0.8124 (0.8180) time: 0.1599 data: 0.0736 max mem: 9390 +Train: [95] [3500/6250] eta: 0:09:04 lr: 0.000001 grad: 0.1377 (0.1445) loss: 0.8078 (0.8178) time: 0.2004 data: 0.1200 max mem: 9390 +Train: [95] [3600/6250] eta: 0:08:45 lr: 0.000001 grad: 0.1348 (0.1444) loss: 0.8119 (0.8176) time: 0.2923 data: 0.1921 max mem: 9390 +Train: [95] [3700/6250] eta: 0:08:23 lr: 0.000001 grad: 0.1351 (0.1443) loss: 0.8213 (0.8175) time: 0.2014 data: 0.1249 max mem: 9390 +Train: [95] [3800/6250] eta: 0:08:03 lr: 0.000001 grad: 0.1381 (0.1443) loss: 0.8120 (0.8174) time: 0.1061 data: 0.0003 max mem: 9390 +Train: [95] [3900/6250] eta: 0:07:44 lr: 0.000001 grad: 0.1334 (0.1442) loss: 0.8150 (0.8173) time: 0.1521 data: 0.0644 max mem: 9390 +Train: [95] [4000/6250] eta: 0:07:22 lr: 0.000001 grad: 0.1379 (0.1440) loss: 0.8130 (0.8173) time: 0.1510 data: 0.0657 max mem: 9390 +Train: [95] [4100/6250] eta: 0:07:03 lr: 0.000001 grad: 0.1341 (0.1439) loss: 0.8142 (0.8173) time: 0.2624 data: 0.1720 max mem: 9390 +Train: [95] [4200/6250] eta: 0:06:42 lr: 0.000001 grad: 0.1421 (0.1438) loss: 0.8113 (0.8173) time: 0.1717 data: 0.0891 max mem: 9390 +Train: [95] [4300/6250] eta: 0:06:22 lr: 0.000001 grad: 0.1421 (0.1438) loss: 0.8144 (0.8172) time: 0.1686 data: 0.0832 max mem: 9390 +Train: [95] [4400/6250] eta: 0:06:03 lr: 0.000001 grad: 0.1360 (0.1437) loss: 0.8158 (0.8172) time: 0.2101 data: 0.1217 max mem: 9390 +Train: [95] [4500/6250] eta: 0:05:43 lr: 0.000001 grad: 0.1341 (0.1436) loss: 0.8166 (0.8172) time: 0.2286 data: 0.1293 max mem: 9390 +Train: [95] [4600/6250] eta: 0:05:25 lr: 0.000001 grad: 0.1426 (0.1435) loss: 0.8117 (0.8172) time: 0.1948 data: 0.1008 max mem: 9390 +Train: [95] [4700/6250] eta: 0:05:05 lr: 0.000001 grad: 0.1422 (0.1436) loss: 0.8136 (0.8171) time: 0.1855 data: 0.0989 max mem: 9390 +Train: [95] [4800/6250] eta: 0:04:46 lr: 0.000001 grad: 0.1419 (0.1435) loss: 0.8185 (0.8171) time: 0.2072 data: 0.1097 max mem: 9390 +Train: [95] [4900/6250] eta: 0:04:26 lr: 0.000001 grad: 0.1422 (0.1435) loss: 0.8143 (0.8171) time: 0.2193 data: 0.1293 max mem: 9390 +Train: [95] [5000/6250] eta: 0:04:06 lr: 0.000001 grad: 0.1370 (0.1436) loss: 0.8074 (0.8170) time: 0.1851 data: 0.0905 max mem: 9390 +Train: [95] [5100/6250] eta: 0:03:47 lr: 0.000001 grad: 0.1413 (0.1435) loss: 0.8165 (0.8170) time: 0.2759 data: 0.1571 max mem: 9390 +Train: [95] [5200/6250] eta: 0:03:27 lr: 0.000001 grad: 0.1361 (0.1435) loss: 0.8151 (0.8169) time: 0.1949 data: 0.1133 max mem: 9390 +Train: [95] [5300/6250] eta: 0:03:07 lr: 0.000001 grad: 0.1364 (0.1435) loss: 0.8123 (0.8169) time: 0.1585 data: 0.0605 max mem: 9390 +Train: [95] [5400/6250] eta: 0:02:47 lr: 0.000001 grad: 0.1366 (0.1436) loss: 0.8198 (0.8168) time: 0.2963 data: 0.1945 max mem: 9390 +Train: [95] [5500/6250] eta: 0:02:28 lr: 0.000001 grad: 0.1436 (0.1436) loss: 0.8137 (0.8167) time: 0.3161 data: 0.2078 max mem: 9390 +Train: [95] [5600/6250] eta: 0:02:07 lr: 0.000001 grad: 0.1370 (0.1437) loss: 0.8156 (0.8167) time: 0.1387 data: 0.0298 max mem: 9390 +Train: [95] [5700/6250] eta: 0:01:48 lr: 0.000001 grad: 0.1387 (0.1436) loss: 0.8146 (0.8166) time: 0.3464 data: 0.2633 max mem: 9390 +Train: [95] [5800/6250] eta: 0:01:29 lr: 0.000001 grad: 0.1438 (0.1437) loss: 0.8129 (0.8166) time: 0.1674 data: 0.0409 max mem: 9390 +Train: [95] [5900/6250] eta: 0:01:09 lr: 0.000001 grad: 0.1456 (0.1436) loss: 0.8204 (0.8166) time: 0.1347 data: 0.0500 max mem: 9390 +Train: [95] [6000/6250] eta: 0:00:49 lr: 0.000001 grad: 0.1381 (0.1436) loss: 0.8169 (0.8166) time: 0.1545 data: 0.0647 max mem: 9390 +Train: [95] [6100/6250] eta: 0:00:29 lr: 0.000001 grad: 0.1329 (0.1435) loss: 0.8149 (0.8166) time: 0.1379 data: 0.0003 max mem: 9390 +Train: [95] [6200/6250] eta: 0:00:09 lr: 0.000001 grad: 0.1371 (0.1435) loss: 0.8140 (0.8167) time: 0.3970 data: 0.2819 max mem: 9390 +Train: [95] [6249/6250] eta: 0:00:00 lr: 0.000001 grad: 0.1310 (0.1434) loss: 0.8172 (0.8167) time: 0.1654 data: 0.0592 max mem: 9390 +Train: [95] Total time: 0:20:48 (0.1997 s / it) +Averaged stats: lr: 0.000001 grad: 0.1310 (0.1434) loss: 0.8172 (0.8167) +Eval (hcp-train-subset): [95] [ 0/62] eta: 0:05:28 loss: 0.8181 (0.8181) time: 5.3040 data: 5.2583 max mem: 9390 +Eval (hcp-train-subset): [95] [61/62] eta: 0:00:00 loss: 0.8130 (0.8165) time: 0.1488 data: 0.1215 max mem: 9390 +Eval (hcp-train-subset): [95] Total time: 0:00:14 (0.2346 s / it) +Averaged stats (hcp-train-subset): loss: 0.8130 (0.8165) +Eval (hcp-val): [95] [ 0/62] eta: 0:05:31 loss: 0.8239 (0.8239) time: 5.3538 data: 5.3222 max mem: 9390 +Eval (hcp-val): [95] [61/62] eta: 0:00:00 loss: 0.8255 (0.8273) time: 0.1450 data: 0.1177 max mem: 9390 +Eval (hcp-val): [95] Total time: 0:00:14 (0.2311 s / it) +Averaged stats (hcp-val): loss: 0.8255 (0.8273) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +Train: [96] [ 0/6250] eta: 11:38:20 lr: 0.000001 grad: 0.1375 (0.1375) loss: 0.8268 (0.8268) time: 6.7041 data: 6.5271 max mem: 9390 +Train: [96] [ 100/6250] eta: 0:25:03 lr: 0.000001 grad: 0.1649 (0.1978) loss: 0.8169 (0.8186) time: 0.1898 data: 0.0730 max mem: 9390 +Train: [96] [ 200/6250] eta: 0:21:25 lr: 0.000001 grad: 0.1513 (0.1863) loss: 0.8164 (0.8150) time: 0.1800 data: 0.0626 max mem: 9390 +Train: [96] [ 300/6250] eta: 0:20:10 lr: 0.000001 grad: 0.1713 (0.1802) loss: 0.8201 (0.8158) time: 0.1867 data: 0.0819 max mem: 9390 +Train: [96] [ 400/6250] eta: 0:19:01 lr: 0.000001 grad: 0.1682 (0.1769) loss: 0.8202 (0.8164) time: 0.1927 data: 0.0949 max mem: 9390 +Train: [96] [ 500/6250] eta: 0:18:08 lr: 0.000001 grad: 0.1505 (0.1741) loss: 0.8126 (0.8160) time: 0.1728 data: 0.0838 max mem: 9390 +Train: [96] [ 600/6250] eta: 0:17:52 lr: 0.000001 grad: 0.1519 (0.1705) loss: 0.8145 (0.8161) time: 0.2407 data: 0.1429 max mem: 9390 +Train: [96] [ 700/6250] eta: 0:17:24 lr: 0.000001 grad: 0.1475 (0.1680) loss: 0.8200 (0.8161) time: 0.1985 data: 0.1060 max mem: 9390 +Train: [96] [ 800/6250] eta: 0:17:27 lr: 0.000001 grad: 0.1557 (0.1664) loss: 0.8179 (0.8158) time: 0.2594 data: 0.1694 max mem: 9390 +Train: [96] [ 900/6250] eta: 0:16:57 lr: 0.000001 grad: 0.1483 (0.1651) loss: 0.8158 (0.8159) time: 0.1992 data: 0.1052 max mem: 9390 +Train: [96] [1000/6250] eta: 0:16:30 lr: 0.000001 grad: 0.1455 (0.1639) loss: 0.8186 (0.8160) time: 0.1506 data: 0.0509 max mem: 9390 +Train: [96] [1100/6250] eta: 0:16:08 lr: 0.000000 grad: 0.1483 (0.1626) loss: 0.8178 (0.8161) time: 0.1523 data: 0.0473 max mem: 9390 +Train: [96] [1200/6250] eta: 0:15:54 lr: 0.000000 grad: 0.1444 (0.1613) loss: 0.8165 (0.8162) time: 0.1129 data: 0.0003 max mem: 9390 +Train: [96] [1300/6250] eta: 0:15:45 lr: 0.000000 grad: 0.1419 (0.1604) loss: 0.8167 (0.8162) time: 0.2231 data: 0.1294 max mem: 9390 +Train: [96] [1400/6250] eta: 0:15:22 lr: 0.000000 grad: 0.1449 (0.1597) loss: 0.8181 (0.8163) time: 0.2037 data: 0.1182 max mem: 9390 +Train: [96] [1500/6250] eta: 0:15:11 lr: 0.000000 grad: 0.1472 (0.1591) loss: 0.8153 (0.8163) time: 0.1293 data: 0.0258 max mem: 9390 +Train: [96] [1600/6250] eta: 0:14:48 lr: 0.000000 grad: 0.1446 (0.1585) loss: 0.8140 (0.8164) time: 0.1751 data: 0.0821 max mem: 9390 +Train: [96] [1700/6250] eta: 0:14:28 lr: 0.000000 grad: 0.1492 (0.1580) loss: 0.8215 (0.8165) time: 0.1796 data: 0.0947 max mem: 9390 +Train: [96] [1800/6250] eta: 0:14:06 lr: 0.000000 grad: 0.1487 (0.1575) loss: 0.8152 (0.8166) time: 0.2080 data: 0.1248 max mem: 9390 +Train: [96] [1900/6250] eta: 0:13:56 lr: 0.000000 grad: 0.1493 (0.1571) loss: 0.8131 (0.8165) time: 0.1226 data: 0.0003 max mem: 9390 +Train: [96] [2000/6250] eta: 0:13:31 lr: 0.000000 grad: 0.1527 (0.1568) loss: 0.8153 (0.8166) time: 0.1428 data: 0.0484 max mem: 9390 +Train: [96] [2100/6250] eta: 0:13:13 lr: 0.000000 grad: 0.1498 (0.1563) loss: 0.8237 (0.8166) time: 0.1257 data: 0.0370 max mem: 9390 +Train: [96] [2200/6250] eta: 0:12:52 lr: 0.000000 grad: 0.1462 (0.1559) loss: 0.8177 (0.8166) time: 0.1213 data: 0.0202 max mem: 9390 +Train: [96] [2300/6250] eta: 0:12:37 lr: 0.000000 grad: 0.1349 (0.1556) loss: 0.8200 (0.8166) time: 0.1043 data: 0.0002 max mem: 9390 +Train: [96] [2400/6250] eta: 0:12:13 lr: 0.000000 grad: 0.1350 (0.1552) loss: 0.8158 (0.8166) time: 0.1708 data: 0.0856 max mem: 9390 +Train: [96] [2500/6250] eta: 0:11:51 lr: 0.000000 grad: 0.1425 (0.1548) loss: 0.8155 (0.8166) time: 0.1809 data: 0.0977 max mem: 9390 +Train: [96] [2600/6250] eta: 0:11:37 lr: 0.000000 grad: 0.1410 (0.1544) loss: 0.8184 (0.8165) time: 0.2971 data: 0.2045 max mem: 9390 +Train: [96] [2700/6250] eta: 0:11:12 lr: 0.000000 grad: 0.1348 (0.1540) loss: 0.8206 (0.8166) time: 0.1696 data: 0.0777 max mem: 9390 +Train: [96] [2800/6250] eta: 0:10:50 lr: 0.000000 grad: 0.1295 (0.1537) loss: 0.8232 (0.8166) time: 0.1761 data: 0.0866 max mem: 9390 +Train: [96] [2900/6250] eta: 0:10:29 lr: 0.000000 grad: 0.1389 (0.1533) loss: 0.8217 (0.8166) time: 0.1855 data: 0.1055 max mem: 9390 +Train: [96] [3000/6250] eta: 0:10:08 lr: 0.000000 grad: 0.1409 (0.1529) loss: 0.8163 (0.8166) time: 0.1897 data: 0.1064 max mem: 9390 +Train: [96] [3100/6250] eta: 0:09:57 lr: 0.000000 grad: 0.1440 (0.1526) loss: 0.8163 (0.8167) time: 0.1086 data: 0.0003 max mem: 9390 +Train: [96] [3200/6250] eta: 0:09:35 lr: 0.000000 grad: 0.1339 (0.1522) loss: 0.8172 (0.8167) time: 0.1679 data: 0.0732 max mem: 9390 +Train: [96] [3300/6250] eta: 0:09:16 lr: 0.000000 grad: 0.1424 (0.1520) loss: 0.8176 (0.8167) time: 0.2528 data: 0.1590 max mem: 9390 +Train: [96] [3400/6250] eta: 0:08:54 lr: 0.000000 grad: 0.1345 (0.1516) loss: 0.8190 (0.8168) time: 0.1575 data: 0.0539 max mem: 9390 +Train: [96] [3500/6250] eta: 0:08:34 lr: 0.000000 grad: 0.1303 (0.1512) loss: 0.8232 (0.8168) time: 0.1613 data: 0.0735 max mem: 9390 +Train: [96] [3600/6250] eta: 0:08:17 lr: 0.000000 grad: 0.1372 (0.1510) loss: 0.8132 (0.8168) time: 0.1581 data: 0.0696 max mem: 9390 +Train: [96] [3700/6250] eta: 0:07:57 lr: 0.000000 grad: 0.1397 (0.1509) loss: 0.8146 (0.8167) time: 0.1742 data: 0.0819 max mem: 9390 +Train: [96] [3800/6250] eta: 0:07:39 lr: 0.000000 grad: 0.1460 (0.1507) loss: 0.8123 (0.8166) time: 0.1799 data: 0.0799 max mem: 9390 +Train: [96] [3900/6250] eta: 0:07:20 lr: 0.000000 grad: 0.1417 (0.1506) loss: 0.8156 (0.8166) time: 0.1645 data: 0.0805 max mem: 9390 +Train: [96] [4000/6250] eta: 0:07:02 lr: 0.000000 grad: 0.1385 (0.1505) loss: 0.8166 (0.8166) time: 0.1807 data: 0.1008 max mem: 9390 +Train: [96] [4100/6250] eta: 0:06:46 lr: 0.000000 grad: 0.1247 (0.1503) loss: 0.8196 (0.8165) time: 0.2099 data: 0.1315 max mem: 9390 +Train: [96] [4200/6250] eta: 0:06:27 lr: 0.000000 grad: 0.1374 (0.1500) loss: 0.8170 (0.8166) time: 0.2560 data: 0.1735 max mem: 9390 +Train: [96] [4300/6250] eta: 0:06:10 lr: 0.000000 grad: 0.1349 (0.1499) loss: 0.8152 (0.8166) time: 0.2069 data: 0.1108 max mem: 9390 +Train: [96] [4400/6250] eta: 0:05:51 lr: 0.000000 grad: 0.1369 (0.1497) loss: 0.8185 (0.8165) time: 0.2272 data: 0.1287 max mem: 9390 +Train: [96] [4500/6250] eta: 0:05:34 lr: 0.000000 grad: 0.1367 (0.1496) loss: 0.8154 (0.8165) time: 0.3339 data: 0.2567 max mem: 9390 +Train: [96] [4600/6250] eta: 0:05:16 lr: 0.000000 grad: 0.1399 (0.1496) loss: 0.8226 (0.8165) time: 0.2571 data: 0.1727 max mem: 9390 +Train: [96] [4700/6250] eta: 0:04:57 lr: 0.000000 grad: 0.1382 (0.1495) loss: 0.8185 (0.8165) time: 0.1706 data: 0.0870 max mem: 9390 +Train: [96] [4800/6250] eta: 0:04:39 lr: 0.000000 grad: 0.1319 (0.1493) loss: 0.8228 (0.8165) time: 0.2242 data: 0.1219 max mem: 9390 +Train: [96] [4900/6250] eta: 0:04:20 lr: 0.000000 grad: 0.1375 (0.1491) loss: 0.8195 (0.8166) time: 0.2124 data: 0.1173 max mem: 9390 +Train: [96] [5000/6250] eta: 0:04:01 lr: 0.000000 grad: 0.1352 (0.1490) loss: 0.8151 (0.8166) time: 0.1729 data: 0.0663 max mem: 9390 +Train: [96] [5100/6250] eta: 0:03:42 lr: 0.000000 grad: 0.1520 (0.1490) loss: 0.8166 (0.8166) time: 0.2440 data: 0.1430 max mem: 9390 +Train: [96] [5200/6250] eta: 0:03:24 lr: 0.000000 grad: 0.1377 (0.1490) loss: 0.8152 (0.8166) time: 0.1104 data: 0.0003 max mem: 9390 +Train: [96] [5300/6250] eta: 0:03:04 lr: 0.000000 grad: 0.1430 (0.1489) loss: 0.8116 (0.8165) time: 0.1245 data: 0.0004 max mem: 9390 +Train: [96] [5400/6250] eta: 0:02:45 lr: 0.000000 grad: 0.1412 (0.1488) loss: 0.8094 (0.8165) time: 0.1595 data: 0.0371 max mem: 9390 +Train: [96] [5500/6250] eta: 0:02:26 lr: 0.000000 grad: 0.1449 (0.1487) loss: 0.8187 (0.8165) time: 0.1079 data: 0.0003 max mem: 9390 +Train: [96] [5600/6250] eta: 0:02:06 lr: 0.000000 grad: 0.1430 (0.1487) loss: 0.8180 (0.8165) time: 0.1196 data: 0.0004 max mem: 9390 +Train: [96] [5700/6250] eta: 0:01:47 lr: 0.000000 grad: 0.1363 (0.1487) loss: 0.8132 (0.8165) time: 0.2051 data: 0.1232 max mem: 9390 +Train: [96] [5800/6250] eta: 0:01:27 lr: 0.000000 grad: 0.1447 (0.1486) loss: 0.8121 (0.8164) time: 0.1540 data: 0.0683 max mem: 9390 +Train: [96] [5900/6250] eta: 0:01:08 lr: 0.000000 grad: 0.1441 (0.1486) loss: 0.8144 (0.8164) time: 0.2148 data: 0.1250 max mem: 9390 +Train: [96] [6000/6250] eta: 0:00:48 lr: 0.000000 grad: 0.1467 (0.1486) loss: 0.8105 (0.8163) time: 0.1682 data: 0.0736 max mem: 9390 +Train: [96] [6100/6250] eta: 0:00:29 lr: 0.000000 grad: 0.1451 (0.1486) loss: 0.8124 (0.8163) time: 0.1770 data: 0.0857 max mem: 9390 +Train: [96] [6200/6250] eta: 0:00:09 lr: 0.000000 grad: 0.1386 (0.1486) loss: 0.8214 (0.8163) time: 0.1849 data: 0.0937 max mem: 9390 +Train: [96] [6249/6250] eta: 0:00:00 lr: 0.000000 grad: 0.1489 (0.1486) loss: 0.8090 (0.8162) time: 0.3279 data: 0.2075 max mem: 9390 +Train: [96] Total time: 0:20:21 (0.1955 s / it) +Averaged stats: lr: 0.000000 grad: 0.1489 (0.1486) loss: 0.8090 (0.8162) +Eval (hcp-train-subset): [96] [ 0/62] eta: 0:03:38 loss: 0.8182 (0.8182) time: 3.5195 data: 3.4628 max mem: 9390 +Eval (hcp-train-subset): [96] [61/62] eta: 0:00:00 loss: 0.8142 (0.8158) time: 0.1561 data: 0.1208 max mem: 9390 +Eval (hcp-train-subset): [96] Total time: 0:00:15 (0.2513 s / it) +Averaged stats (hcp-train-subset): loss: 0.8142 (0.8158) +Eval (hcp-val): [96] [ 0/62] eta: 0:06:30 loss: 0.8248 (0.8248) time: 6.2970 data: 6.2649 max mem: 9390 +Eval (hcp-val): [96] [61/62] eta: 0:00:00 loss: 0.8270 (0.8276) time: 0.0914 data: 0.0663 max mem: 9390 +Eval (hcp-val): [96] Total time: 0:00:15 (0.2480 s / it) +Averaged stats (hcp-val): loss: 0.8270 (0.8276) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +Train: [97] [ 0/6250] eta: 9:14:33 lr: 0.000000 grad: 0.1669 (0.1669) loss: 0.8088 (0.8088) time: 5.3238 data: 5.1007 max mem: 9390 +Train: [97] [ 100/6250] eta: 0:23:14 lr: 0.000000 grad: 0.1608 (0.2098) loss: 0.8170 (0.8173) time: 0.1708 data: 0.0582 max mem: 9390 +Train: [97] [ 200/6250] eta: 0:19:59 lr: 0.000000 grad: 0.1734 (0.2031) loss: 0.8162 (0.8154) time: 0.1380 data: 0.0366 max mem: 9390 +Train: [97] [ 300/6250] eta: 0:18:44 lr: 0.000000 grad: 0.1588 (0.1969) loss: 0.8164 (0.8151) time: 0.1795 data: 0.0803 max mem: 9390 +Train: [97] [ 400/6250] eta: 0:17:48 lr: 0.000000 grad: 0.1559 (0.1911) loss: 0.8145 (0.8144) time: 0.1570 data: 0.0570 max mem: 9390 +Train: [97] [ 500/6250] eta: 0:17:12 lr: 0.000000 grad: 0.1459 (0.1853) loss: 0.8142 (0.8136) time: 0.1688 data: 0.0721 max mem: 9390 +Train: [97] [ 600/6250] eta: 0:16:48 lr: 0.000000 grad: 0.1529 (0.1816) loss: 0.8140 (0.8134) time: 0.2062 data: 0.1190 max mem: 9390 +Train: [97] [ 700/6250] eta: 0:16:23 lr: 0.000000 grad: 0.1530 (0.1786) loss: 0.8191 (0.8138) time: 0.1970 data: 0.1014 max mem: 9390 +Train: [97] [ 800/6250] eta: 0:16:00 lr: 0.000000 grad: 0.1504 (0.1754) loss: 0.8237 (0.8146) time: 0.1583 data: 0.0615 max mem: 9390 +Train: [97] [ 900/6250] eta: 0:15:44 lr: 0.000000 grad: 0.1436 (0.1735) loss: 0.8230 (0.8148) time: 0.1441 data: 0.0526 max mem: 9390 +Train: [97] [1000/6250] eta: 0:15:27 lr: 0.000000 grad: 0.1388 (0.1710) loss: 0.8148 (0.8151) time: 0.1669 data: 0.0749 max mem: 9390 +Train: [97] [1100/6250] eta: 0:15:05 lr: 0.000000 grad: 0.1491 (0.1697) loss: 0.8212 (0.8153) time: 0.1881 data: 0.1044 max mem: 9390 +Train: [97] [1200/6250] eta: 0:14:42 lr: 0.000000 grad: 0.1479 (0.1682) loss: 0.8215 (0.8156) time: 0.1570 data: 0.0630 max mem: 9390 +Train: [97] [1300/6250] eta: 0:14:20 lr: 0.000000 grad: 0.1434 (0.1667) loss: 0.8195 (0.8159) time: 0.1545 data: 0.0607 max mem: 9390 +Train: [97] [1400/6250] eta: 0:13:59 lr: 0.000000 grad: 0.1425 (0.1656) loss: 0.8213 (0.8160) time: 0.1411 data: 0.0461 max mem: 9390 +Train: [97] [1500/6250] eta: 0:13:37 lr: 0.000000 grad: 0.1546 (0.1646) loss: 0.8129 (0.8162) time: 0.1478 data: 0.0567 max mem: 9390 +Train: [97] [1600/6250] eta: 0:13:19 lr: 0.000000 grad: 0.1476 (0.1636) loss: 0.8115 (0.8163) time: 0.2059 data: 0.1143 max mem: 9390 +Train: [97] [1700/6250] eta: 0:12:59 lr: 0.000000 grad: 0.1364 (0.1627) loss: 0.8228 (0.8164) time: 0.1706 data: 0.0821 max mem: 9390 +Train: [97] [1800/6250] eta: 0:12:42 lr: 0.000000 grad: 0.1524 (0.1620) loss: 0.8154 (0.8164) time: 0.1845 data: 0.0964 max mem: 9390 +Train: [97] [1900/6250] eta: 0:12:22 lr: 0.000000 grad: 0.1480 (0.1612) loss: 0.8210 (0.8165) time: 0.1569 data: 0.0641 max mem: 9390 +Train: [97] [2000/6250] eta: 0:12:04 lr: 0.000000 grad: 0.1414 (0.1604) loss: 0.8157 (0.8166) time: 0.1703 data: 0.0898 max mem: 9390 +Train: [97] [2100/6250] eta: 0:11:45 lr: 0.000000 grad: 0.1493 (0.1597) loss: 0.8207 (0.8167) time: 0.1405 data: 0.0538 max mem: 9390 +Train: [97] [2200/6250] eta: 0:11:29 lr: 0.000000 grad: 0.1512 (0.1592) loss: 0.8162 (0.8167) time: 0.1834 data: 0.0939 max mem: 9390 +Train: [97] [2300/6250] eta: 0:11:11 lr: 0.000000 grad: 0.1511 (0.1587) loss: 0.8221 (0.8168) time: 0.1628 data: 0.0755 max mem: 9390 +Train: [97] [2400/6250] eta: 0:10:53 lr: 0.000000 grad: 0.1430 (0.1584) loss: 0.8168 (0.8169) time: 0.1706 data: 0.0885 max mem: 9390 +Train: [97] [2500/6250] eta: 0:10:37 lr: 0.000000 grad: 0.1422 (0.1581) loss: 0.8231 (0.8170) time: 0.2036 data: 0.1259 max mem: 9390 +Train: [97] [2600/6250] eta: 0:10:19 lr: 0.000000 grad: 0.1378 (0.1578) loss: 0.8176 (0.8171) time: 0.1931 data: 0.1122 max mem: 9390 +Train: [97] [2700/6250] eta: 0:10:00 lr: 0.000000 grad: 0.1374 (0.1574) loss: 0.8225 (0.8172) time: 0.1466 data: 0.0560 max mem: 9390 +Train: [97] [2800/6250] eta: 0:09:44 lr: 0.000000 grad: 0.1371 (0.1568) loss: 0.8262 (0.8174) time: 0.2173 data: 0.1326 max mem: 9390 +Train: [97] [2900/6250] eta: 0:09:27 lr: 0.000000 grad: 0.1309 (0.1563) loss: 0.8216 (0.8175) time: 0.1263 data: 0.0379 max mem: 9390 +Train: [97] [3000/6250] eta: 0:09:09 lr: 0.000000 grad: 0.1321 (0.1560) loss: 0.8221 (0.8175) time: 0.1621 data: 0.0709 max mem: 9390 +Train: [97] [3100/6250] eta: 0:08:53 lr: 0.000000 grad: 0.1511 (0.1556) loss: 0.8209 (0.8176) time: 0.1564 data: 0.0678 max mem: 9390 +Train: [97] [3200/6250] eta: 0:08:37 lr: 0.000000 grad: 0.1477 (0.1552) loss: 0.8171 (0.8178) time: 0.1695 data: 0.0822 max mem: 9390 +Train: [97] [3300/6250] eta: 0:08:24 lr: 0.000000 grad: 0.1451 (0.1549) loss: 0.8155 (0.8178) time: 0.3696 data: 0.2585 max mem: 9390 +Train: [97] [3400/6250] eta: 0:08:07 lr: 0.000000 grad: 0.1470 (0.1546) loss: 0.8203 (0.8179) time: 0.1037 data: 0.0003 max mem: 9390 +Train: [97] [3500/6250] eta: 0:07:50 lr: 0.000000 grad: 0.1328 (0.1546) loss: 0.8249 (0.8179) time: 0.1126 data: 0.0085 max mem: 9390 +Train: [97] [3600/6250] eta: 0:07:35 lr: 0.000000 grad: 0.1490 (0.1544) loss: 0.8150 (0.8179) time: 0.2363 data: 0.1406 max mem: 9390 +Train: [97] [3700/6250] eta: 0:07:16 lr: 0.000000 grad: 0.1394 (0.1542) loss: 0.8207 (0.8179) time: 0.1564 data: 0.0648 max mem: 9390 +Train: [97] [3800/6250] eta: 0:07:01 lr: 0.000000 grad: 0.1432 (0.1540) loss: 0.8182 (0.8179) time: 0.2358 data: 0.1485 max mem: 9390 +Train: [97] [3900/6250] eta: 0:06:44 lr: 0.000000 grad: 0.1399 (0.1539) loss: 0.8178 (0.8179) time: 0.1993 data: 0.1001 max mem: 9390 +Train: [97] [4000/6250] eta: 0:06:27 lr: 0.000000 grad: 0.1536 (0.1537) loss: 0.8123 (0.8179) time: 0.1684 data: 0.0804 max mem: 9390 +Train: [97] [4100/6250] eta: 0:06:10 lr: 0.000000 grad: 0.1397 (0.1536) loss: 0.8150 (0.8179) time: 0.1706 data: 0.0781 max mem: 9390 +Train: [97] [4200/6250] eta: 0:05:53 lr: 0.000000 grad: 0.1426 (0.1534) loss: 0.8155 (0.8178) time: 0.1970 data: 0.1056 max mem: 9390 +Train: [97] [4300/6250] eta: 0:05:36 lr: 0.000000 grad: 0.1463 (0.1534) loss: 0.8174 (0.8178) time: 0.1843 data: 0.0817 max mem: 9390 +Train: [97] [4400/6250] eta: 0:05:19 lr: 0.000000 grad: 0.1458 (0.1533) loss: 0.8156 (0.8176) time: 0.1844 data: 0.0895 max mem: 9390 +Train: [97] [4500/6250] eta: 0:05:02 lr: 0.000000 grad: 0.1413 (0.1532) loss: 0.8156 (0.8176) time: 0.1562 data: 0.0758 max mem: 9390 +Train: [97] [4600/6250] eta: 0:04:45 lr: 0.000000 grad: 0.1423 (0.1531) loss: 0.8168 (0.8175) time: 0.1908 data: 0.0967 max mem: 9390 +Train: [97] [4700/6250] eta: 0:04:28 lr: 0.000000 grad: 0.1376 (0.1529) loss: 0.8088 (0.8174) time: 0.1553 data: 0.0737 max mem: 9390 +Train: [97] [4800/6250] eta: 0:04:10 lr: 0.000000 grad: 0.1427 (0.1528) loss: 0.8156 (0.8174) time: 0.1518 data: 0.0519 max mem: 9390 +Train: [97] [4900/6250] eta: 0:03:52 lr: 0.000000 grad: 0.1442 (0.1526) loss: 0.8169 (0.8173) time: 0.1468 data: 0.0666 max mem: 9390 +Train: [97] [5000/6250] eta: 0:03:34 lr: 0.000000 grad: 0.1488 (0.1526) loss: 0.8135 (0.8172) time: 0.1515 data: 0.0623 max mem: 9390 +Train: [97] [5100/6250] eta: 0:03:16 lr: 0.000000 grad: 0.1398 (0.1525) loss: 0.8188 (0.8172) time: 0.1580 data: 0.0709 max mem: 9390 +Train: [97] [5200/6250] eta: 0:02:59 lr: 0.000000 grad: 0.1499 (0.1524) loss: 0.8147 (0.8171) time: 0.1447 data: 0.0549 max mem: 9390 +Train: [97] [5300/6250] eta: 0:02:41 lr: 0.000000 grad: 0.1428 (0.1523) loss: 0.8126 (0.8171) time: 0.1374 data: 0.0413 max mem: 9390 +Train: [97] [5400/6250] eta: 0:02:24 lr: 0.000000 grad: 0.1345 (0.1522) loss: 0.8236 (0.8171) time: 0.1404 data: 0.0503 max mem: 9390 +Train: [97] [5500/6250] eta: 0:02:06 lr: 0.000000 grad: 0.1606 (0.1522) loss: 0.8175 (0.8171) time: 0.1603 data: 0.0690 max mem: 9390 +Train: [97] [5600/6250] eta: 0:01:49 lr: 0.000000 grad: 0.1536 (0.1522) loss: 0.8173 (0.8171) time: 0.1503 data: 0.0648 max mem: 9390 +Train: [97] [5700/6250] eta: 0:01:32 lr: 0.000000 grad: 0.1483 (0.1523) loss: 0.8147 (0.8170) time: 0.1499 data: 0.0702 max mem: 9390 +Train: [97] [5800/6250] eta: 0:01:15 lr: 0.000000 grad: 0.1498 (0.1523) loss: 0.8154 (0.8170) time: 0.1449 data: 0.0583 max mem: 9390 +Train: [97] [5900/6250] eta: 0:00:58 lr: 0.000000 grad: 0.1391 (0.1523) loss: 0.8181 (0.8169) time: 0.1492 data: 0.0553 max mem: 9390 +Train: [97] [6000/6250] eta: 0:00:41 lr: 0.000000 grad: 0.1433 (0.1522) loss: 0.8179 (0.8169) time: 0.1556 data: 0.0668 max mem: 9390 +Train: [97] [6100/6250] eta: 0:00:25 lr: 0.000000 grad: 0.1423 (0.1522) loss: 0.8114 (0.8168) time: 0.1413 data: 0.0567 max mem: 9390 +Train: [97] [6200/6250] eta: 0:00:08 lr: 0.000000 grad: 0.1348 (0.1523) loss: 0.8126 (0.8168) time: 0.1517 data: 0.0579 max mem: 9390 +Train: [97] [6249/6250] eta: 0:00:00 lr: 0.000000 grad: 0.1441 (0.1522) loss: 0.8164 (0.8167) time: 0.1574 data: 0.0726 max mem: 9390 +Train: [97] Total time: 0:17:26 (0.1674 s / it) +Averaged stats: lr: 0.000000 grad: 0.1441 (0.1522) loss: 0.8164 (0.8167) +Eval (hcp-train-subset): [97] [ 0/62] eta: 0:03:15 loss: 0.8156 (0.8156) time: 3.1523 data: 3.0768 max mem: 9390 +Eval (hcp-train-subset): [97] [61/62] eta: 0:00:00 loss: 0.8135 (0.8155) time: 0.1225 data: 0.0979 max mem: 9390 +Eval (hcp-train-subset): [97] Total time: 0:00:12 (0.2039 s / it) +Averaged stats (hcp-train-subset): loss: 0.8135 (0.8155) +Eval (hcp-val): [97] [ 0/62] eta: 0:04:22 loss: 0.8234 (0.8234) time: 4.2299 data: 4.1928 max mem: 9390 +Eval (hcp-val): [97] [61/62] eta: 0:00:00 loss: 0.8243 (0.8272) time: 0.1256 data: 0.1007 max mem: 9390 +Eval (hcp-val): [97] Total time: 0:00:13 (0.2172 s / it) +Averaged stats (hcp-val): loss: 0.8243 (0.8272) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +Train: [98] [ 0/6250] eta: 7:36:40 lr: 0.000000 grad: 0.0968 (0.0968) loss: 0.8449 (0.8449) time: 4.3842 data: 4.1246 max mem: 9390 +Train: [98] [ 100/6250] eta: 0:22:17 lr: 0.000000 grad: 0.1791 (0.2104) loss: 0.8117 (0.8102) time: 0.1888 data: 0.0939 max mem: 9390 +Train: [98] [ 200/6250] eta: 0:19:06 lr: 0.000000 grad: 0.1762 (0.1992) loss: 0.7985 (0.8102) time: 0.1598 data: 0.0580 max mem: 9390 +Train: [98] [ 300/6250] eta: 0:17:49 lr: 0.000000 grad: 0.1652 (0.1884) loss: 0.8146 (0.8114) time: 0.1466 data: 0.0622 max mem: 9390 +Train: [98] [ 400/6250] eta: 0:16:48 lr: 0.000000 grad: 0.1552 (0.1804) loss: 0.8176 (0.8133) time: 0.1451 data: 0.0595 max mem: 9390 +Train: [98] [ 500/6250] eta: 0:16:03 lr: 0.000000 grad: 0.1399 (0.1736) loss: 0.8185 (0.8149) time: 0.1040 data: 0.0062 max mem: 9390 +Train: [98] [ 600/6250] eta: 0:15:37 lr: 0.000000 grad: 0.1414 (0.1694) loss: 0.8227 (0.8157) time: 0.1699 data: 0.0830 max mem: 9390 +Train: [98] [ 700/6250] eta: 0:15:05 lr: 0.000000 grad: 0.1403 (0.1662) loss: 0.8184 (0.8163) time: 0.1408 data: 0.0553 max mem: 9390 +Train: [98] [ 800/6250] eta: 0:14:46 lr: 0.000000 grad: 0.1540 (0.1643) loss: 0.8117 (0.8161) time: 0.1483 data: 0.0625 max mem: 9390 +Train: [98] [ 900/6250] eta: 0:14:30 lr: 0.000000 grad: 0.1438 (0.1631) loss: 0.8140 (0.8158) time: 0.1710 data: 0.0860 max mem: 9390 +Train: [98] [1000/6250] eta: 0:14:27 lr: 0.000000 grad: 0.1524 (0.1618) loss: 0.8120 (0.8158) time: 0.3515 data: 0.2641 max mem: 9390 +Train: [98] [1100/6250] eta: 0:13:57 lr: 0.000000 grad: 0.1494 (0.1607) loss: 0.8143 (0.8156) time: 0.1706 data: 0.0905 max mem: 9390 +Train: [98] [1200/6250] eta: 0:13:34 lr: 0.000000 grad: 0.1509 (0.1595) loss: 0.8203 (0.8156) time: 0.1407 data: 0.0598 max mem: 9390 +Train: [98] [1300/6250] eta: 0:13:15 lr: 0.000000 grad: 0.1375 (0.1585) loss: 0.8164 (0.8157) time: 0.1201 data: 0.0243 max mem: 9390 +Train: [98] [1400/6250] eta: 0:12:53 lr: 0.000000 grad: 0.1432 (0.1576) loss: 0.8178 (0.8159) time: 0.1442 data: 0.0629 max mem: 9390 +Train: [98] [1500/6250] eta: 0:12:31 lr: 0.000000 grad: 0.1412 (0.1566) loss: 0.8164 (0.8161) time: 0.1339 data: 0.0567 max mem: 9390 +Train: [98] [1600/6250] eta: 0:12:11 lr: 0.000000 grad: 0.1440 (0.1561) loss: 0.8177 (0.8161) time: 0.1485 data: 0.0705 max mem: 9390 +Train: [98] [1700/6250] eta: 0:11:56 lr: 0.000000 grad: 0.1345 (0.1554) loss: 0.8174 (0.8162) time: 0.1618 data: 0.0824 max mem: 9390 +Train: [98] [1800/6250] eta: 0:11:40 lr: 0.000000 grad: 0.1451 (0.1550) loss: 0.8126 (0.8163) time: 0.1620 data: 0.0839 max mem: 9390 +Train: [98] [1900/6250] eta: 0:11:25 lr: 0.000000 grad: 0.1422 (0.1544) loss: 0.8188 (0.8164) time: 0.1577 data: 0.0849 max mem: 9390 +Train: [98] [2000/6250] eta: 0:11:07 lr: 0.000000 grad: 0.1425 (0.1541) loss: 0.8167 (0.8164) time: 0.1506 data: 0.0699 max mem: 9390 +Train: [98] [2100/6250] eta: 0:10:49 lr: 0.000000 grad: 0.1445 (0.1537) loss: 0.8188 (0.8164) time: 0.1131 data: 0.0249 max mem: 9390 +Train: [98] [2200/6250] eta: 0:10:32 lr: 0.000000 grad: 0.1508 (0.1536) loss: 0.8175 (0.8164) time: 0.1476 data: 0.0634 max mem: 9390 +Train: [98] [2300/6250] eta: 0:10:14 lr: 0.000000 grad: 0.1414 (0.1533) loss: 0.8204 (0.8164) time: 0.1202 data: 0.0452 max mem: 9390 +Train: [98] [2400/6250] eta: 0:09:56 lr: 0.000000 grad: 0.1459 (0.1532) loss: 0.8130 (0.8163) time: 0.1516 data: 0.0606 max mem: 9390 +Train: [98] [2500/6250] eta: 0:09:38 lr: 0.000000 grad: 0.1409 (0.1531) loss: 0.8237 (0.8164) time: 0.1425 data: 0.0565 max mem: 9390 +Train: [98] [2600/6250] eta: 0:09:21 lr: 0.000000 grad: 0.1494 (0.1531) loss: 0.8165 (0.8163) time: 0.1422 data: 0.0547 max mem: 9390 +Train: [98] [2700/6250] eta: 0:09:05 lr: 0.000000 grad: 0.1405 (0.1530) loss: 0.8184 (0.8164) time: 0.1313 data: 0.0477 max mem: 9390 +Train: [98] [2800/6250] eta: 0:08:48 lr: 0.000000 grad: 0.1513 (0.1529) loss: 0.8086 (0.8165) time: 0.1317 data: 0.0485 max mem: 9390 +Train: [98] [2900/6250] eta: 0:08:32 lr: 0.000000 grad: 0.1396 (0.1528) loss: 0.8141 (0.8165) time: 0.1380 data: 0.0557 max mem: 9390 +Train: [98] [3000/6250] eta: 0:08:16 lr: 0.000000 grad: 0.1438 (0.1526) loss: 0.8168 (0.8165) time: 0.1273 data: 0.0389 max mem: 9390 +Train: [98] [3100/6250] eta: 0:08:04 lr: 0.000000 grad: 0.1503 (0.1526) loss: 0.8198 (0.8165) time: 0.1718 data: 0.0894 max mem: 9390 +Train: [98] [3200/6250] eta: 0:07:50 lr: 0.000000 grad: 0.1478 (0.1525) loss: 0.8197 (0.8165) time: 0.1840 data: 0.1054 max mem: 9390 +Train: [98] [3300/6250] eta: 0:07:35 lr: 0.000000 grad: 0.1379 (0.1524) loss: 0.8205 (0.8164) time: 0.1777 data: 0.0902 max mem: 9390 +Train: [98] [3400/6250] eta: 0:07:20 lr: 0.000000 grad: 0.1463 (0.1524) loss: 0.8114 (0.8164) time: 0.1481 data: 0.0679 max mem: 9390 +Train: [98] [3500/6250] eta: 0:07:05 lr: 0.000000 grad: 0.1527 (0.1523) loss: 0.8199 (0.8165) time: 0.1794 data: 0.0909 max mem: 9390 +Train: [98] [3600/6250] eta: 0:06:50 lr: 0.000000 grad: 0.1447 (0.1523) loss: 0.8203 (0.8165) time: 0.1419 data: 0.0600 max mem: 9390 +Train: [98] [3700/6250] eta: 0:06:35 lr: 0.000000 grad: 0.1360 (0.1523) loss: 0.8183 (0.8166) time: 0.1545 data: 0.0695 max mem: 9390 +Train: [98] [3800/6250] eta: 0:06:20 lr: 0.000000 grad: 0.1336 (0.1523) loss: 0.8248 (0.8166) time: 0.1665 data: 0.0772 max mem: 9390 +Train: [98] [3900/6250] eta: 0:06:04 lr: 0.000000 grad: 0.1427 (0.1521) loss: 0.8233 (0.8167) time: 0.1297 data: 0.0406 max mem: 9390 +Train: [98] [4000/6250] eta: 0:05:51 lr: 0.000000 grad: 0.1378 (0.1521) loss: 0.8168 (0.8167) time: 0.1848 data: 0.0973 max mem: 9390 +Train: [98] [4100/6250] eta: 0:05:36 lr: 0.000000 grad: 0.1358 (0.1519) loss: 0.8183 (0.8168) time: 0.1359 data: 0.0547 max mem: 9390 +Train: [98] [4200/6250] eta: 0:05:21 lr: 0.000000 grad: 0.1353 (0.1518) loss: 0.8169 (0.8169) time: 0.1693 data: 0.0870 max mem: 9390 +Train: [98] [4300/6250] eta: 0:05:05 lr: 0.000000 grad: 0.1313 (0.1517) loss: 0.8216 (0.8169) time: 0.1557 data: 0.0653 max mem: 9390 +Train: [98] [4400/6250] eta: 0:04:50 lr: 0.000000 grad: 0.1426 (0.1515) loss: 0.8213 (0.8170) time: 0.1410 data: 0.0592 max mem: 9390 +Train: [98] [4500/6250] eta: 0:04:34 lr: 0.000000 grad: 0.1386 (0.1513) loss: 0.8223 (0.8171) time: 0.1837 data: 0.0945 max mem: 9390 +Train: [98] [4600/6250] eta: 0:04:18 lr: 0.000000 grad: 0.1332 (0.1513) loss: 0.8173 (0.8172) time: 0.1467 data: 0.0630 max mem: 9390 +Train: [98] [4700/6250] eta: 0:04:02 lr: 0.000000 grad: 0.1382 (0.1511) loss: 0.8166 (0.8172) time: 0.1503 data: 0.0605 max mem: 9390 +Train: [98] [4800/6250] eta: 0:03:47 lr: 0.000000 grad: 0.1415 (0.1511) loss: 0.8230 (0.8173) time: 0.1722 data: 0.0873 max mem: 9390 +Train: [98] [4900/6250] eta: 0:03:31 lr: 0.000000 grad: 0.1316 (0.1510) loss: 0.8192 (0.8174) time: 0.1620 data: 0.0848 max mem: 9390 +Train: [98] [5000/6250] eta: 0:03:15 lr: 0.000000 grad: 0.1447 (0.1509) loss: 0.8208 (0.8174) time: 0.1743 data: 0.0887 max mem: 9390 +Train: [98] [5100/6250] eta: 0:03:00 lr: 0.000000 grad: 0.1477 (0.1509) loss: 0.8148 (0.8174) time: 0.2523 data: 0.1678 max mem: 9390 +Train: [98] [5200/6250] eta: 0:02:44 lr: 0.000000 grad: 0.1441 (0.1508) loss: 0.8174 (0.8174) time: 0.1595 data: 0.0828 max mem: 9390 +Train: [98] [5300/6250] eta: 0:02:28 lr: 0.000000 grad: 0.1414 (0.1508) loss: 0.8153 (0.8174) time: 0.1558 data: 0.0667 max mem: 9390 +Train: [98] [5400/6250] eta: 0:02:12 lr: 0.000000 grad: 0.1385 (0.1508) loss: 0.8193 (0.8174) time: 0.1555 data: 0.0743 max mem: 9390 +Train: [98] [5500/6250] eta: 0:01:57 lr: 0.000000 grad: 0.1408 (0.1507) loss: 0.8204 (0.8173) time: 0.1489 data: 0.0626 max mem: 9390 +Train: [98] [5600/6250] eta: 0:01:41 lr: 0.000000 grad: 0.1430 (0.1507) loss: 0.8186 (0.8173) time: 0.1469 data: 0.0603 max mem: 9390 +Train: [98] [5700/6250] eta: 0:01:26 lr: 0.000000 grad: 0.1500 (0.1507) loss: 0.8226 (0.8173) time: 0.1575 data: 0.0776 max mem: 9390 +Train: [98] [5800/6250] eta: 0:01:10 lr: 0.000000 grad: 0.1429 (0.1506) loss: 0.8190 (0.8173) time: 0.1454 data: 0.0604 max mem: 9390 +Train: [98] [5900/6250] eta: 0:00:54 lr: 0.000000 grad: 0.1469 (0.1506) loss: 0.8199 (0.8173) time: 0.1334 data: 0.0476 max mem: 9390 +Train: [98] [6000/6250] eta: 0:00:39 lr: 0.000000 grad: 0.1430 (0.1505) loss: 0.8102 (0.8172) time: 0.1995 data: 0.1175 max mem: 9390 +Train: [98] [6100/6250] eta: 0:00:23 lr: 0.000000 grad: 0.1416 (0.1505) loss: 0.8233 (0.8172) time: 0.1347 data: 0.0520 max mem: 9390 +Train: [98] [6200/6250] eta: 0:00:07 lr: 0.000000 grad: 0.1468 (0.1505) loss: 0.8154 (0.8172) time: 0.1319 data: 0.0469 max mem: 9390 +Train: [98] [6249/6250] eta: 0:00:00 lr: 0.000000 grad: 0.1402 (0.1505) loss: 0.8168 (0.8172) time: 0.1656 data: 0.0837 max mem: 9390 +Train: [98] Total time: 0:16:19 (0.1567 s / it) +Averaged stats: lr: 0.000000 grad: 0.1402 (0.1505) loss: 0.8168 (0.8172) +Eval (hcp-train-subset): [98] [ 0/62] eta: 0:04:21 loss: 0.8169 (0.8169) time: 4.2220 data: 4.1480 max mem: 9390 +Eval (hcp-train-subset): [98] [61/62] eta: 0:00:00 loss: 0.8134 (0.8157) time: 0.1331 data: 0.1084 max mem: 9390 +Eval (hcp-train-subset): [98] Total time: 0:00:13 (0.2128 s / it) +Averaged stats (hcp-train-subset): loss: 0.8134 (0.8157) +Eval (hcp-val): [98] [ 0/62] eta: 0:03:50 loss: 0.8255 (0.8255) time: 3.7249 data: 3.6528 max mem: 9390 +Eval (hcp-val): [98] [61/62] eta: 0:00:00 loss: 0.8263 (0.8274) time: 0.1027 data: 0.0778 max mem: 9390 +Eval (hcp-val): [98] Total time: 0:00:13 (0.2164 s / it) +Averaged stats (hcp-val): loss: 0.8263 (0.8274) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +Train: [99] [ 0/6250] eta: 8:35:31 lr: 0.000000 grad: 0.1505 (0.1505) loss: 0.8387 (0.8387) time: 4.9490 data: 4.5394 max mem: 9390 +Train: [99] [ 100/6250] eta: 0:22:08 lr: 0.000000 grad: 0.1793 (0.2240) loss: 0.8103 (0.8130) time: 0.1600 data: 0.0576 max mem: 9390 +Train: [99] [ 200/6250] eta: 0:18:57 lr: 0.000000 grad: 0.1529 (0.1982) loss: 0.8195 (0.8153) time: 0.1652 data: 0.0663 max mem: 9390 +Train: [99] [ 300/6250] eta: 0:17:21 lr: 0.000000 grad: 0.1353 (0.1828) loss: 0.8270 (0.8180) time: 0.1526 data: 0.0642 max mem: 9390 +Train: [99] [ 400/6250] eta: 0:16:18 lr: 0.000000 grad: 0.1380 (0.1750) loss: 0.8227 (0.8196) time: 0.1435 data: 0.0613 max mem: 9390 +Train: [99] [ 500/6250] eta: 0:15:33 lr: 0.000000 grad: 0.1318 (0.1701) loss: 0.8215 (0.8207) time: 0.1241 data: 0.0337 max mem: 9390 +Train: [99] [ 600/6250] eta: 0:15:01 lr: 0.000000 grad: 0.1611 (0.1674) loss: 0.8175 (0.8210) time: 0.1466 data: 0.0543 max mem: 9390 +Train: [99] [ 700/6250] eta: 0:14:40 lr: 0.000000 grad: 0.1515 (0.1651) loss: 0.8232 (0.8211) time: 0.1636 data: 0.0810 max mem: 9390 +Train: [99] [ 800/6250] eta: 0:14:28 lr: 0.000000 grad: 0.1505 (0.1641) loss: 0.8145 (0.8209) time: 0.1591 data: 0.0700 max mem: 9390 +Train: [99] [ 900/6250] eta: 0:14:15 lr: 0.000000 grad: 0.1521 (0.1631) loss: 0.8170 (0.8207) time: 0.1734 data: 0.0885 max mem: 9390 +Train: [99] [1000/6250] eta: 0:13:56 lr: 0.000000 grad: 0.1390 (0.1622) loss: 0.8147 (0.8203) time: 0.1073 data: 0.0269 max mem: 9390 +Train: [99] [1100/6250] eta: 0:13:40 lr: 0.000000 grad: 0.1577 (0.1617) loss: 0.8150 (0.8197) time: 0.1414 data: 0.0581 max mem: 9390 +Train: [99] [1200/6250] eta: 0:13:16 lr: 0.000000 grad: 0.1467 (0.1610) loss: 0.8128 (0.8192) time: 0.1312 data: 0.0489 max mem: 9390 +Train: [99] [1300/6250] eta: 0:12:58 lr: 0.000000 grad: 0.1417 (0.1601) loss: 0.8161 (0.8189) time: 0.1453 data: 0.0528 max mem: 9390 +Train: [99] [1400/6250] eta: 0:12:35 lr: 0.000000 grad: 0.1584 (0.1602) loss: 0.8168 (0.8186) time: 0.1314 data: 0.0429 max mem: 9390 +Train: [99] [1500/6250] eta: 0:12:16 lr: 0.000000 grad: 0.1495 (0.1599) loss: 0.8158 (0.8184) time: 0.1468 data: 0.0648 max mem: 9390 +Train: [99] [1600/6250] eta: 0:11:58 lr: 0.000000 grad: 0.1549 (0.1599) loss: 0.8115 (0.8182) time: 0.1414 data: 0.0617 max mem: 9390 +Train: [99] [1700/6250] eta: 0:11:40 lr: 0.000000 grad: 0.1419 (0.1599) loss: 0.8170 (0.8178) time: 0.1392 data: 0.0604 max mem: 9390 +Train: [99] [1800/6250] eta: 0:11:24 lr: 0.000000 grad: 0.1525 (0.1598) loss: 0.8172 (0.8175) time: 0.1513 data: 0.0684 max mem: 9390 +Train: [99] [1900/6250] eta: 0:11:08 lr: 0.000000 grad: 0.1546 (0.1597) loss: 0.8201 (0.8172) time: 0.1440 data: 0.0595 max mem: 9390 +Train: [99] [2000/6250] eta: 0:10:52 lr: 0.000000 grad: 0.1597 (0.1595) loss: 0.8083 (0.8170) time: 0.1439 data: 0.0627 max mem: 9390 +Train: [99] [2100/6250] eta: 0:10:37 lr: 0.000000 grad: 0.1516 (0.1595) loss: 0.8068 (0.8167) time: 0.1774 data: 0.0982 max mem: 9390 +Train: [99] [2200/6250] eta: 0:10:20 lr: 0.000000 grad: 0.1512 (0.1593) loss: 0.8069 (0.8166) time: 0.1592 data: 0.0759 max mem: 9390 +Train: [99] [2300/6250] eta: 0:10:04 lr: 0.000000 grad: 0.1427 (0.1592) loss: 0.8087 (0.8163) time: 0.1658 data: 0.0791 max mem: 9390 +Train: [99] [2400/6250] eta: 0:09:50 lr: 0.000000 grad: 0.1458 (0.1589) loss: 0.8158 (0.8162) time: 0.1982 data: 0.1167 max mem: 9390 +Train: [99] [2500/6250] eta: 0:09:32 lr: 0.000000 grad: 0.1332 (0.1586) loss: 0.8158 (0.8161) time: 0.1622 data: 0.0840 max mem: 9390 +Train: [99] [2600/6250] eta: 0:09:16 lr: 0.000000 grad: 0.1454 (0.1585) loss: 0.8177 (0.8160) time: 0.1417 data: 0.0573 max mem: 9390 +Train: [99] [2700/6250] eta: 0:09:01 lr: 0.000000 grad: 0.1452 (0.1582) loss: 0.8129 (0.8159) time: 0.1624 data: 0.0801 max mem: 9390 +Train: [99] [2800/6250] eta: 0:08:46 lr: 0.000000 grad: 0.1388 (0.1578) loss: 0.8179 (0.8158) time: 0.1796 data: 0.0997 max mem: 9390 +Train: [99] [2900/6250] eta: 0:08:28 lr: 0.000000 grad: 0.1470 (0.1576) loss: 0.8081 (0.8157) time: 0.1496 data: 0.0675 max mem: 9390 +Train: [99] [3000/6250] eta: 0:08:15 lr: 0.000000 grad: 0.1428 (0.1573) loss: 0.8158 (0.8156) time: 0.1231 data: 0.0408 max mem: 9390 +Train: [99] [3100/6250] eta: 0:07:59 lr: 0.000000 grad: 0.1496 (0.1570) loss: 0.8145 (0.8156) time: 0.1360 data: 0.0533 max mem: 9390 +Train: [99] [3200/6250] eta: 0:07:43 lr: 0.000000 grad: 0.1494 (0.1566) loss: 0.8133 (0.8157) time: 0.1463 data: 0.0640 max mem: 9390 +Train: [99] [3300/6250] eta: 0:07:27 lr: 0.000000 grad: 0.1349 (0.1563) loss: 0.8164 (0.8157) time: 0.1290 data: 0.0456 max mem: 9390 +Train: [99] [3400/6250] eta: 0:07:11 lr: 0.000000 grad: 0.1462 (0.1560) loss: 0.8174 (0.8157) time: 0.1339 data: 0.0544 max mem: 9390 +Train: [99] [3500/6250] eta: 0:06:56 lr: 0.000000 grad: 0.1485 (0.1559) loss: 0.8126 (0.8157) time: 0.1443 data: 0.0610 max mem: 9390 +Train: [99] [3600/6250] eta: 0:06:41 lr: 0.000000 grad: 0.1393 (0.1556) loss: 0.8169 (0.8158) time: 0.1664 data: 0.0917 max mem: 9390 +Train: [99] [3700/6250] eta: 0:06:25 lr: 0.000000 grad: 0.1340 (0.1554) loss: 0.8232 (0.8158) time: 0.1609 data: 0.0844 max mem: 9390 +Train: [99] [3800/6250] eta: 0:06:10 lr: 0.000000 grad: 0.1486 (0.1552) loss: 0.8178 (0.8158) time: 0.1327 data: 0.0507 max mem: 9390 +Train: [99] [3900/6250] eta: 0:05:55 lr: 0.000000 grad: 0.1480 (0.1552) loss: 0.8111 (0.8159) time: 0.1737 data: 0.0920 max mem: 9390 +Train: [99] [4000/6250] eta: 0:05:40 lr: 0.000000 grad: 0.1369 (0.1550) loss: 0.8162 (0.8158) time: 0.1552 data: 0.0723 max mem: 9390 +Train: [99] [4100/6250] eta: 0:05:25 lr: 0.000000 grad: 0.1397 (0.1548) loss: 0.8209 (0.8158) time: 0.1573 data: 0.0634 max mem: 9390 +Train: [99] [4200/6250] eta: 0:05:11 lr: 0.000000 grad: 0.1458 (0.1547) loss: 0.8141 (0.8158) time: 0.1935 data: 0.1054 max mem: 9390 +Train: [99] [4300/6250] eta: 0:04:56 lr: 0.000000 grad: 0.1448 (0.1546) loss: 0.8137 (0.8156) time: 0.1450 data: 0.0614 max mem: 9390 +Train: [99] [4400/6250] eta: 0:04:40 lr: 0.000000 grad: 0.1345 (0.1546) loss: 0.8101 (0.8155) time: 0.1486 data: 0.0702 max mem: 9390 +Train: [99] [4500/6250] eta: 0:04:25 lr: 0.000000 grad: 0.1452 (0.1545) loss: 0.8090 (0.8154) time: 0.1378 data: 0.0419 max mem: 9390 +Train: [99] [4600/6250] eta: 0:04:09 lr: 0.000000 grad: 0.1551 (0.1543) loss: 0.8124 (0.8154) time: 0.1418 data: 0.0567 max mem: 9390 +Train: [99] [4700/6250] eta: 0:03:54 lr: 0.000000 grad: 0.1451 (0.1542) loss: 0.8088 (0.8153) time: 0.1384 data: 0.0616 max mem: 9390 +Train: [99] [4800/6250] eta: 0:03:38 lr: 0.000000 grad: 0.1410 (0.1540) loss: 0.8215 (0.8153) time: 0.1475 data: 0.0682 max mem: 9390 +Train: [99] [4900/6250] eta: 0:03:23 lr: 0.000000 grad: 0.1508 (0.1539) loss: 0.8128 (0.8152) time: 0.1455 data: 0.0673 max mem: 9390 +Train: [99] [5000/6250] eta: 0:03:09 lr: 0.000000 grad: 0.1397 (0.1538) loss: 0.8147 (0.8152) time: 0.2249 data: 0.1413 max mem: 9390 +Train: [99] [5100/6250] eta: 0:02:53 lr: 0.000000 grad: 0.1422 (0.1538) loss: 0.8201 (0.8151) time: 0.1307 data: 0.0601 max mem: 9390 +Train: [99] [5200/6250] eta: 0:02:38 lr: 0.000000 grad: 0.1368 (0.1537) loss: 0.8111 (0.8151) time: 0.1458 data: 0.0558 max mem: 9390 +Train: [99] [5300/6250] eta: 0:02:23 lr: 0.000000 grad: 0.1443 (0.1536) loss: 0.8098 (0.8150) time: 0.1027 data: 0.0230 max mem: 9390 +Train: [99] [5400/6250] eta: 0:02:08 lr: 0.000000 grad: 0.1467 (0.1535) loss: 0.8105 (0.8150) time: 0.1576 data: 0.0805 max mem: 9390 +Train: [99] [5500/6250] eta: 0:01:53 lr: 0.000000 grad: 0.1557 (0.1535) loss: 0.8080 (0.8149) time: 0.1310 data: 0.0428 max mem: 9390 +Train: [99] [5600/6250] eta: 0:01:38 lr: 0.000000 grad: 0.1487 (0.1535) loss: 0.8090 (0.8148) time: 0.2392 data: 0.1554 max mem: 9390 +Train: [99] [5700/6250] eta: 0:01:23 lr: 0.000000 grad: 0.1552 (0.1535) loss: 0.8056 (0.8148) time: 0.1493 data: 0.0728 max mem: 9390 +Train: [99] [5800/6250] eta: 0:01:07 lr: 0.000000 grad: 0.1514 (0.1535) loss: 0.8030 (0.8147) time: 0.1337 data: 0.0468 max mem: 9390 +Train: [99] [5900/6250] eta: 0:00:52 lr: 0.000000 grad: 0.1486 (0.1534) loss: 0.8009 (0.8147) time: 0.1460 data: 0.0672 max mem: 9390 +Train: [99] [6000/6250] eta: 0:00:37 lr: 0.000000 grad: 0.1515 (0.1534) loss: 0.8179 (0.8146) time: 0.1547 data: 0.0644 max mem: 9390 +Train: [99] [6100/6250] eta: 0:00:22 lr: 0.000000 grad: 0.1455 (0.1534) loss: 0.8120 (0.8146) time: 0.1689 data: 0.0931 max mem: 9390 +Train: [99] [6200/6250] eta: 0:00:07 lr: 0.000000 grad: 0.1489 (0.1533) loss: 0.8075 (0.8145) time: 0.1604 data: 0.0784 max mem: 9390 +Train: [99] [6249/6250] eta: 0:00:00 lr: 0.000000 grad: 0.1365 (0.1533) loss: 0.8111 (0.8145) time: 0.1606 data: 0.0795 max mem: 9390 +Train: [99] Total time: 0:15:47 (0.1516 s / it) +Averaged stats: lr: 0.000000 grad: 0.1365 (0.1533) loss: 0.8111 (0.8145) +Eval (hcp-train-subset): [99] [ 0/62] eta: 0:03:17 loss: 0.8181 (0.8181) time: 3.1852 data: 3.0934 max mem: 9390 +Eval (hcp-train-subset): [99] [61/62] eta: 0:00:00 loss: 0.8127 (0.8158) time: 0.1347 data: 0.1099 max mem: 9390 +Eval (hcp-train-subset): [99] Total time: 0:00:12 (0.2080 s / it) +Averaged stats (hcp-train-subset): loss: 0.8127 (0.8158) +Making plots (hcp-train-subset): example=8 +Eval (hcp-val): [99] [ 0/62] eta: 0:04:46 loss: 0.8242 (0.8242) time: 4.6233 data: 4.5918 max mem: 9390 +Eval (hcp-val): [99] [61/62] eta: 0:00:00 loss: 0.8256 (0.8272) time: 0.1334 data: 0.1069 max mem: 9390 +Eval (hcp-val): [99] Total time: 0:00:12 (0.2068 s / it) +Averaged stats (hcp-val): loss: 0.8256 (0.8272) +Making plots (hcp-val): example=52 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_5/pretrain/checkpoint-last.pth +done! training time: 17:53:22 diff --git a/input_space_v3/flat_lr1e-3_6/eval_v2/aabc_age__patch__logistic/config.yaml b/input_space_v3/flat_lr1e-3_6/eval_v2/aabc_age__patch__logistic/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..9ed2956eecf81df77e21da9604dacfa89f6b295d --- /dev/null +++ b/input_space_v3/flat_lr1e-3_6/eval_v2/aabc_age__patch__logistic/config.yaml @@ -0,0 +1,30 @@ +output_root: experiments/input_space_v3/output +name_prefix: eval_logistic +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_6; eval v2 (aabc_age patch logistic) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: input_space_v3/flat_lr1e-3_6/eval_v2/aabc_age__patch__logistic +model: flat_mae +representation: patch +dataset: aabc_age +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/eval_v2/aabc_age__patch__logistic +remote_dir: null diff --git a/input_space_v3/flat_lr1e-3_6/eval_v2/aabc_age__patch__logistic/eval_table.csv b/input_space_v3/flat_lr1e-3_6/eval_v2/aabc_age__patch__logistic/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..59cbcbee31bc70dfe216832d919bd1783df72642 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_6/eval_v2/aabc_age__patch__logistic/eval_table.csv @@ -0,0 +1,203 @@ +model,repr,clf,dataset,trial,C,split,acc,acc_std,f1,f1_std,bacc,bacc_std +flat_mae,patch,logistic,aabc_age,,0.005994842503189409,train,0.65748031496063,0.022054280021858223,0.6552488568685237,0.022510334536299675,0.6584901594959888,0.021983464330402904 +flat_mae,patch,logistic,aabc_age,,0.005994842503189409,test,0.4230769230769231,0.06462008911445236,0.405459257893335,0.06823688463173469,0.4168956043956044,0.06425876781368485 +flat_mae,patch,logistic,aabc_age,1,0.046415888336127774,train,0.8267716535433071,0.016296193470618937,0.8275570177156703,0.01629510435979666,0.8274904869492835,0.01630573257799912 +flat_mae,patch,logistic,aabc_age,1,0.046415888336127774,test,0.4807692307692308,0.06342599237596318,0.4768518518518518,0.06407323651954998,0.48168498168498164,0.06335359562275787 +flat_mae,patch,logistic,aabc_age,2,9.999999999999999e-05,train,0.4881889763779528,0.020135419076100763,0.46776906329143086,0.020908391616344817,0.4864226853654373,0.020045958280548143 +flat_mae,patch,logistic,aabc_age,2,9.999999999999999e-05,test,0.46153846153846156,0.06292096103269647,0.4366013071895425,0.06440377669882659,0.45650183150183155,0.0620165166594045 +flat_mae,patch,logistic,aabc_age,3,0.046415888336127774,train,0.8307086614173228,0.016082616929502944,0.8317105695593938,0.01603267358641354,0.8326429498896217,0.015986143516630427 +flat_mae,patch,logistic,aabc_age,3,0.046415888336127774,test,0.5192307692307693,0.06548041624213001,0.5089400183150183,0.06707999089586247,0.5187728937728937,0.06540738112373858 +flat_mae,patch,logistic,aabc_age,4,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,4,2.782559402207126,test,0.46153846153846156,0.06318265060345368,0.47110158862876256,0.06001277097146709,0.46543040293040294,0.06390527918927776 +flat_mae,patch,logistic,aabc_age,5,9.999999999999999e-05,train,0.5098425196850394,0.019601901208022195,0.482894895064805,0.020184701765374815,0.5065420204492231,0.019415037992985756 +flat_mae,patch,logistic,aabc_age,5,9.999999999999999e-05,test,0.4807692307692308,0.059662400814968194,0.4488479262672811,0.06352926026527948,0.47847985347985345,0.05908409814553934 +flat_mae,patch,logistic,aabc_age,6,0.005994842503189409,train,0.655511811023622,0.020368468566611085,0.6539328253265339,0.020667059712749705,0.6561268314061095,0.02035930018245392 +flat_mae,patch,logistic,aabc_age,6,0.005994842503189409,test,0.5384615384615384,0.0623368402856989,0.5218808511468247,0.0673262930914047,0.5336538461538461,0.06213877650592559 +flat_mae,patch,logistic,aabc_age,7,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,7,21.54434690031882,test,0.4807692307692308,0.06849967606713023,0.47644370122630997,0.06880498062356352,0.4777930402930403,0.06860835119669721 +flat_mae,patch,logistic,aabc_age,8,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,8,2.782559402207126,test,0.4807692307692308,0.06615031296468252,0.4835164835164836,0.06574575548010583,0.4835164835164835,0.06619719476483318 +flat_mae,patch,logistic,aabc_age,9,0.046415888336127774,train,0.8346456692913385,0.01559185550894815,0.8349619048078657,0.015665768022869543,0.8359725176403797,0.015470781805705209 +flat_mae,patch,logistic,aabc_age,9,0.046415888336127774,test,0.4230769230769231,0.06347999731546622,0.41550116550116545,0.06132277275971671,0.41941391941391937,0.06285088878374989 +flat_mae,patch,logistic,aabc_age,10,0.000774263682681127,train,0.5669291338582677,0.020562950667885195,0.5627620368658851,0.021089446428960625,0.5670620927944394,0.02053464293588562 +flat_mae,patch,logistic,aabc_age,10,0.000774263682681127,test,0.5,0.06510119569157984,0.491991341991342,0.06538203246100761,0.4965659340659341,0.06485537299895242 +flat_mae,patch,logistic,aabc_age,11,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,11,166.81005372000556,test,0.5384615384615384,0.06931699758245559,0.5516883116883117,0.06751642901218378,0.5370879120879121,0.06938548831450281 +flat_mae,patch,logistic,aabc_age,12,0.000774263682681127,train,0.5551181102362205,0.02127291228472477,0.5490813609104997,0.021843732230789344,0.555468062233764,0.02122697871010047 +flat_mae,patch,logistic,aabc_age,12,0.000774263682681127,test,0.4423076923076923,0.06384967552845322,0.4366589026915114,0.06489871643919556,0.44047619047619047,0.06385638628490728 +flat_mae,patch,logistic,aabc_age,13,0.005994842503189409,train,0.6811023622047244,0.01922170100297002,0.6791374556104197,0.01965776649540171,0.6817837785223702,0.01922425859107028 +flat_mae,patch,logistic,aabc_age,13,0.005994842503189409,test,0.4423076923076923,0.06159305270898524,0.43395976004671655,0.0610052394480305,0.4429945054945055,0.0619843680637154 +flat_mae,patch,logistic,aabc_age,14,0.005994842503189409,train,0.6850393700787402,0.02005494962352208,0.6817939665471614,0.020584284652007796,0.6859336311276225,0.019977648200065205 +flat_mae,patch,logistic,aabc_age,14,0.005994842503189409,test,0.5384615384615384,0.06585302803801164,0.5294675925925926,0.06929548050567615,0.5396062271062271,0.06586473760887991 +flat_mae,patch,logistic,aabc_age,15,0.000774263682681127,train,0.5649606299212598,0.02183580097235748,0.5562773523087614,0.022687461092932962,0.5632230685726013,0.021863077050335827 +flat_mae,patch,logistic,aabc_age,15,0.000774263682681127,test,0.5,0.06699425922592747,0.49896551724137933,0.06745061934556784,0.5009157509157509,0.06739133874937511 +flat_mae,patch,logistic,aabc_age,16,0.000774263682681127,train,0.5708661417322834,0.02095761372253878,0.562792388094943,0.021358783875067084,0.5702417005345337,0.02080612589735396 +flat_mae,patch,logistic,aabc_age,16,0.000774263682681127,test,0.40384615384615385,0.06220413997143437,0.38475568004979765,0.058678630169417025,0.39720695970695963,0.0614337779696145 +flat_mae,patch,logistic,aabc_age,17,0.000774263682681127,train,0.5688976377952756,0.020809852392554663,0.5640903405842268,0.02138499368284172,0.5688606539455187,0.020796699045414535 +flat_mae,patch,logistic,aabc_age,17,0.000774263682681127,test,0.4230769230769231,0.060749217736702596,0.3891223155929039,0.05853187937116895,0.4178113553113553,0.059620292149024263 +flat_mae,patch,logistic,aabc_age,18,9.999999999999999e-05,train,0.5078740157480315,0.020660967202702094,0.4910715283071786,0.021860407997456737,0.5061812053955876,0.020557908957976847 +flat_mae,patch,logistic,aabc_age,18,9.999999999999999e-05,test,0.5,0.05718681107516614,0.4421344421344421,0.04918022587452232,0.4876373626373626,0.05579319918820855 +flat_mae,patch,logistic,aabc_age,19,0.046415888336127774,train,0.8484251968503937,0.016017309499675895,0.8490589759561133,0.016016856740672204,0.849532690563092,0.01595465459413841 +flat_mae,patch,logistic,aabc_age,19,0.046415888336127774,test,0.4230769230769231,0.06930675317386437,0.4231634182908546,0.06975734259271019,0.42422161172161177,0.06975873876646804 +flat_mae,patch,logistic,aabc_age,20,0.005994842503189409,train,0.6712598425196851,0.02099273550278495,0.6699694911200611,0.02127179509715163,0.672890946107417,0.020964889191216696 +flat_mae,patch,logistic,aabc_age,20,0.005994842503189409,test,0.4807692307692308,0.05870143088686749,0.44965686274509803,0.06393342742195805,0.4771062271062271,0.05833019363743638 +flat_mae,patch,logistic,aabc_age,21,0.000774263682681127,train,0.5669291338582677,0.02078982440843591,0.5605999464095947,0.021262458986983424,0.5656067254967021,0.02084687009199606 +flat_mae,patch,logistic,aabc_age,21,0.000774263682681127,test,0.38461538461538464,0.055845769759221696,0.3537545787545787,0.058461494694228455,0.3864468864468864,0.056396293232473596 +flat_mae,patch,logistic,aabc_age,22,10000.0,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,22,10000.0,test,0.3269230769230769,0.06075378333362551,0.32116977225672877,0.06036341101423359,0.32348901098901095,0.06054361659955399 +flat_mae,patch,logistic,aabc_age,23,0.000774263682681127,train,0.5452755905511811,0.02142897545152306,0.5382670540727413,0.02208207697024866,0.544802321299452,0.021406213642779177 +flat_mae,patch,logistic,aabc_age,23,0.000774263682681127,test,0.46153846153846156,0.059776148000874774,0.444544220945083,0.06180223791698779,0.4592490842490842,0.05949119280358305 +flat_mae,patch,logistic,aabc_age,24,0.046415888336127774,train,0.844488188976378,0.016641099854048387,0.8448852089008826,0.016640928563077393,0.8453504724879121,0.01658208339454827 +flat_mae,patch,logistic,aabc_age,24,0.046415888336127774,test,0.38461538461538464,0.061431288887975236,0.3706249051076637,0.05747057432972352,0.37934981684981683,0.06048908233835105 +flat_mae,patch,logistic,aabc_age,25,9.999999999999999e-05,train,0.5118110236220472,0.020919866951815604,0.48968281846095224,0.021633291204651958,0.5091432452545028,0.02079282363359766 +flat_mae,patch,logistic,aabc_age,25,9.999999999999999e-05,test,0.3076923076923077,0.0566156459024071,0.2783711386652563,0.054703245810436965,0.30654761904761907,0.056439262164470635 +flat_mae,patch,logistic,aabc_age,26,0.000774263682681127,train,0.5688976377952756,0.021947404353980345,0.5622014278052625,0.022384692584525755,0.568275558172497,0.02184576004685022 +flat_mae,patch,logistic,aabc_age,26,0.000774263682681127,test,0.4423076923076923,0.06077666702310904,0.4173109243697479,0.06376755681035445,0.440018315018315,0.060665001564867316 +flat_mae,patch,logistic,aabc_age,27,0.000774263682681127,train,0.5688976377952756,0.021025415005087342,0.5600576571731507,0.02185393210596399,0.568343166043012,0.020968726148542564 +flat_mae,patch,logistic,aabc_age,27,0.000774263682681127,test,0.40384615384615385,0.0601430616931204,0.37950759251068844,0.06231193872785755,0.39903846153846156,0.05980991710216118 +flat_mae,patch,logistic,aabc_age,28,0.3593813663804626,train,0.9803149606299213,0.006333009727927508,0.9800891285236587,0.006413709655820638,0.9800738987588922,0.0064254354430035975 +flat_mae,patch,logistic,aabc_age,28,0.3593813663804626,test,0.4423076923076923,0.0677428133265548,0.4488095238095238,0.06800986830542088,0.44345238095238093,0.06799370889600091 +flat_mae,patch,logistic,aabc_age,29,9.999999999999999e-05,train,0.5118110236220472,0.020302933936213578,0.4865030036928367,0.020840757394390792,0.5090932585842816,0.020157201940113927 +flat_mae,patch,logistic,aabc_age,29,9.999999999999999e-05,test,0.4230769230769231,0.059459336709161925,0.40297165200391005,0.0559197746607423,0.4191849816849817,0.05867284224812532 +flat_mae,patch,logistic,aabc_age,30,0.046415888336127774,train,0.8366141732283464,0.016995144605736093,0.8375428346401737,0.016945555642294937,0.837771078791459,0.0169514484534268 +flat_mae,patch,logistic,aabc_age,30,0.046415888336127774,test,0.5384615384615384,0.07112053274206255,0.5475,0.06922572183493143,0.5398351648351648,0.07090906690063847 +flat_mae,patch,logistic,aabc_age,31,9.999999999999999e-05,train,0.4940944881889764,0.01972888777802808,0.46613915261039895,0.020590554482384463,0.491450840926832,0.01964355589763586 +flat_mae,patch,logistic,aabc_age,31,9.999999999999999e-05,test,0.5576923076923077,0.0603237812133959,0.5249193548387097,0.06361205439831025,0.549908424908425,0.059683697637371434 +flat_mae,patch,logistic,aabc_age,32,0.046415888336127774,train,0.8385826771653543,0.017205008646456573,0.8394440425992125,0.01715400065087987,0.839284464190844,0.017121864163532667 +flat_mae,patch,logistic,aabc_age,32,0.046415888336127774,test,0.5,0.06598676351041836,0.4926262626262626,0.06492546307996634,0.4965659340659341,0.06574039163450209 +flat_mae,patch,logistic,aabc_age,33,0.005994842503189409,train,0.6673228346456693,0.02027857022673988,0.6655283623678709,0.02061571600902812,0.6665330492204476,0.020301600100071145 +flat_mae,patch,logistic,aabc_age,33,0.005994842503189409,test,0.5192307692307693,0.061243173753169795,0.5212215320910972,0.062190957263810596,0.5203754578754579,0.06166103981819946 +flat_mae,patch,logistic,aabc_age,34,0.3593813663804626,train,0.9803149606299213,0.006019337419089073,0.979886381827409,0.006172636420909993,0.9796887496667556,0.006210319274688151 +flat_mae,patch,logistic,aabc_age,34,0.3593813663804626,test,0.5192307692307693,0.06881868811826862,0.53125,0.06765326872735347,0.5206043956043955,0.06874346136170084 +flat_mae,patch,logistic,aabc_age,35,0.046415888336127774,train,0.8346456692913385,0.016409936214745426,0.8348418399840255,0.01650890196465092,0.8350022727752217,0.016428608875918457 +flat_mae,patch,logistic,aabc_age,35,0.046415888336127774,test,0.38461538461538464,0.06308924598202044,0.3968567664219838,0.06116302248290686,0.3825549450549451,0.06274218300010324 +flat_mae,patch,logistic,aabc_age,36,0.005994842503189409,train,0.6732283464566929,0.020354540503647784,0.6725085767347385,0.02046692229683731,0.6744719393773171,0.020316764870974096 +flat_mae,patch,logistic,aabc_age,36,0.005994842503189409,test,0.4807692307692308,0.06313196472797437,0.4654761904761905,0.06446708061470025,0.4800824175824176,0.06322326560909891 +flat_mae,patch,logistic,aabc_age,37,0.046415888336127774,train,0.8366141732283464,0.01712642546268481,0.8371193139757449,0.01718146912218933,0.8389089048675749,0.016949423659515562 +flat_mae,patch,logistic,aabc_age,37,0.046415888336127774,test,0.36538461538461536,0.06066914835507565,0.3532230911263169,0.057271289433190334,0.3573717948717949,0.05978750781125011 +flat_mae,patch,logistic,aabc_age,38,9.999999999999999e-05,train,0.4822834645669291,0.01906099993818365,0.45110926337169466,0.019136510644044626,0.47985681036615657,0.018883212054991282 +flat_mae,patch,logistic,aabc_age,38,9.999999999999999e-05,test,0.46153846153846156,0.0637150066389851,0.43466880341880343,0.06030898065435152,0.4535256410256411,0.06263471720436749 +flat_mae,patch,logistic,aabc_age,39,0.005994842503189409,train,0.6850393700787402,0.019700851523401244,0.6836600525626457,0.019870910053480018,0.6866187002410867,0.019628446047331275 +flat_mae,patch,logistic,aabc_age,39,0.005994842503189409,test,0.46153846153846156,0.06426013837998938,0.4443809585999739,0.06321199582586463,0.4551282051282051,0.06350526549472431 +flat_mae,patch,logistic,aabc_age,40,0.000774263682681127,train,0.5433070866141733,0.019874004439269528,0.5312519466565353,0.020442225813606107,0.5413984328399717,0.019806332068261535 +flat_mae,patch,logistic,aabc_age,40,0.000774263682681127,test,0.5,0.06360803603728628,0.49522546419098146,0.06414915504653712,0.5009157509157509,0.06396368307545974 +flat_mae,patch,logistic,aabc_age,41,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,41,166.81005372000556,test,0.46153846153846156,0.06388871380360767,0.4455139915497972,0.06365041312019633,0.4652014652014652,0.06473947213197759 +flat_mae,patch,logistic,aabc_age,42,0.000774263682681127,train,0.5748031496062992,0.02123594274880512,0.5702980802952679,0.021358178707726695,0.5746914731611139,0.021228702437114305 +flat_mae,patch,logistic,aabc_age,42,0.000774263682681127,test,0.4807692307692308,0.06126780625124615,0.4631469979296066,0.06671235466048085,0.48031135531135527,0.06140604698501656 +flat_mae,patch,logistic,aabc_age,43,0.005994842503189409,train,0.6653543307086615,0.020165005362133746,0.6648520208255846,0.020352413212812843,0.6670101402216004,0.020203151524496598 +flat_mae,patch,logistic,aabc_age,43,0.005994842503189409,test,0.46153846153846156,0.06361864004320389,0.4504046677959721,0.0626452215984143,0.45375457875457875,0.06317135454184072 +flat_mae,patch,logistic,aabc_age,44,0.3593813663804626,train,0.9803149606299213,0.0065866730045238,0.9802546660851377,0.006604424121176942,0.9806090078616926,0.006500888527087735 +flat_mae,patch,logistic,aabc_age,44,0.3593813663804626,test,0.46153846153846156,0.06615635057871233,0.4604558404558404,0.06686030169402246,0.4626831501831502,0.0665753728167823 +flat_mae,patch,logistic,aabc_age,45,0.000774263682681127,train,0.5649606299212598,0.020119929960692277,0.5564237768052218,0.020987402012181283,0.5640933400973169,0.02002379532440719 +flat_mae,patch,logistic,aabc_age,45,0.000774263682681127,test,0.4807692307692308,0.06510374061004574,0.4734719941616493,0.0661352978596558,0.48168498168498164,0.0652268631771833 +flat_mae,patch,logistic,aabc_age,46,0.005994842503189409,train,0.6653543307086615,0.02049211501659982,0.6628616980331029,0.02091545567155656,0.6652872183724627,0.020531302510635417 +flat_mae,patch,logistic,aabc_age,46,0.005994842503189409,test,0.4807692307692308,0.06898969779877909,0.48001567398119127,0.07060297582067282,0.4835164835164835,0.06905538184712583 +flat_mae,patch,logistic,aabc_age,47,0.005994842503189409,train,0.6850393700787402,0.019651339263527794,0.6847351158037717,0.019860846710332957,0.6870362148031508,0.0196091420960043 +flat_mae,patch,logistic,aabc_age,47,0.005994842503189409,test,0.4807692307692308,0.06496265426923488,0.46597771190162496,0.06808613237651137,0.4773351648351648,0.06480677364527632 +flat_mae,patch,logistic,aabc_age,48,0.005994842503189409,train,0.6791338582677166,0.02086956256315122,0.6781848897643801,0.02118900854900828,0.6803527452631336,0.02082263746756604 +flat_mae,patch,logistic,aabc_age,48,0.005994842503189409,test,0.4423076923076923,0.07017417047021954,0.4462731481481481,0.0706278947180325,0.44184981684981683,0.07025501691540043 +flat_mae,patch,logistic,aabc_age,49,9.999999999999999e-05,train,0.5137795275590551,0.019262158149113855,0.49050044977826324,0.02029771730535992,0.5113769421679399,0.01917863246418286 +flat_mae,patch,logistic,aabc_age,49,9.999999999999999e-05,test,0.38461538461538464,0.06161076281523023,0.3844039174921528,0.0632962107238896,0.38095238095238093,0.061575707189448756 +flat_mae,patch,logistic,aabc_age,50,0.3593813663804626,train,0.984251968503937,0.005358583015016543,0.9842232122310228,0.005377419901535133,0.9842561168340721,0.005359223437285509 +flat_mae,patch,logistic,aabc_age,50,0.3593813663804626,test,0.46153846153846156,0.06422099188596023,0.4633333333333333,0.06327228201801259,0.4597069597069597,0.06401637831887858 +flat_mae,patch,logistic,aabc_age,51,0.005994842503189409,train,0.6889763779527559,0.020077147922046523,0.688508632851632,0.020269822178665978,0.6909008916567093,0.020028538603875767 +flat_mae,patch,logistic,aabc_age,51,0.005994842503189409,test,0.4807692307692308,0.0730420564595105,0.47619047619047616,0.07325573513836017,0.4789377289377289,0.07300413037026988 +flat_mae,patch,logistic,aabc_age,52,0.005994842503189409,train,0.65748031496063,0.0206576791527852,0.6560092777652771,0.02102668621718446,0.6590132319630833,0.02054351005407444 +flat_mae,patch,logistic,aabc_age,52,0.005994842503189409,test,0.40384615384615385,0.0686600837502527,0.4114097496706193,0.06846911675271058,0.4033882783882784,0.06864462410474251 +flat_mae,patch,logistic,aabc_age,53,9.999999999999999e-05,train,0.5019685039370079,0.020913781228474454,0.48923781137911715,0.021284390488056623,0.5000152237580769,0.0208135225472616 +flat_mae,patch,logistic,aabc_age,53,9.999999999999999e-05,test,0.5384615384615384,0.05883303021081764,0.49775124069478904,0.057766028658066,0.530448717948718,0.057794218278287283 +flat_mae,patch,logistic,aabc_age,54,0.000774263682681127,train,0.5688976377952756,0.02007650558817826,0.5649733842511628,0.02055849734312736,0.5697809121404556,0.020047083321585606 +flat_mae,patch,logistic,aabc_age,54,0.000774263682681127,test,0.46153846153846156,0.05958381297995933,0.43348669877307644,0.061106866855819446,0.4578754578754579,0.05913210568282574 +flat_mae,patch,logistic,aabc_age,55,0.000774263682681127,train,0.5688976377952756,0.02213043185326549,0.5598619336176249,0.022810847087401335,0.5679580169508754,0.02209218649068827 +flat_mae,patch,logistic,aabc_age,55,0.000774263682681127,test,0.4807692307692308,0.0653386263604811,0.4780952380952381,0.06632982217495896,0.4789377289377289,0.06547343429449655 +flat_mae,patch,logistic,aabc_age,56,9.999999999999999e-05,train,0.5078740157480315,0.020618661650514965,0.4831023256642751,0.021583979910298444,0.5046258647574076,0.020556548808919557 +flat_mae,patch,logistic,aabc_age,56,9.999999999999999e-05,test,0.40384615384615385,0.0633434682537529,0.38433706816059754,0.0645829419314376,0.4015567765567766,0.06308143682259199 +flat_mae,patch,logistic,aabc_age,57,9.999999999999999e-05,train,0.5039370078740157,0.02073135003027415,0.4795711678185863,0.021480795099536005,0.5008111745740704,0.020517389994158683 +flat_mae,patch,logistic,aabc_age,57,9.999999999999999e-05,test,0.46153846153846156,0.06148520532105899,0.41005291005291,0.052001883319933405,0.45329670329670335,0.05988855193809884 +flat_mae,patch,logistic,aabc_age,58,0.000774263682681127,train,0.5610236220472441,0.020944602153125717,0.5516156208499335,0.021554372731529436,0.5595759596002217,0.0208576861972899 +flat_mae,patch,logistic,aabc_age,58,0.000774263682681127,test,0.4423076923076923,0.06391650433672996,0.43070120812056295,0.06904337465715248,0.43864468864468864,0.06360196164414714 +flat_mae,patch,logistic,aabc_age,59,0.046415888336127774,train,0.8464566929133859,0.016158015121384983,0.8464677595339916,0.016214327307833752,0.8474165881903915,0.016075790880515164 +flat_mae,patch,logistic,aabc_age,59,0.046415888336127774,test,0.34615384615384615,0.06772476276166836,0.3489785174567783,0.06775448982678092,0.34867216117216115,0.06804446926011799 +flat_mae,patch,logistic,aabc_age,60,0.000774263682681127,train,0.562992125984252,0.021476202572953944,0.5579705846756129,0.02200382492604967,0.563197415940881,0.021417857086365205 +flat_mae,patch,logistic,aabc_age,60,0.000774263682681127,test,0.36538461538461536,0.056077978253236044,0.3405982905982906,0.055281918723151524,0.3628663003663004,0.05551746424980148 +flat_mae,patch,logistic,aabc_age,61,0.046415888336127774,train,0.860236220472441,0.015875948982391957,0.8604338072864304,0.015938849229878847,0.8602740707993456,0.015844296411370275 +flat_mae,patch,logistic,aabc_age,61,0.046415888336127774,test,0.4230769230769231,0.06633579629297055,0.4304620111071724,0.06674839770475924,0.42422161172161177,0.06651232214303306 +flat_mae,patch,logistic,aabc_age,62,0.005994842503189409,train,0.6633858267716536,0.019453759454087893,0.6634300261133691,0.019629985138863076,0.6658466615137643,0.019514881449982157 +flat_mae,patch,logistic,aabc_age,62,0.005994842503189409,test,0.4230769230769231,0.0674432810133534,0.423036223036223,0.06668660903480098,0.4182692307692307,0.06730131678926288 +flat_mae,patch,logistic,aabc_age,63,0.005994842503189409,train,0.6811023622047244,0.01904694137051802,0.6793879883295942,0.019371076162011197,0.6825364555063494,0.01907354824737244 +flat_mae,patch,logistic,aabc_age,63,0.005994842503189409,test,0.4230769230769231,0.058063727487168294,0.3974753694581281,0.058456914714168036,0.4251373626373627,0.05863375182831778 +flat_mae,patch,logistic,aabc_age,64,0.046415888336127774,train,0.8464566929133859,0.01507313684668554,0.8465132029900425,0.015121959450003233,0.8468638578872972,0.01511386159337765 +flat_mae,patch,logistic,aabc_age,64,0.046415888336127774,test,0.38461538461538464,0.06571971820501626,0.3915343915343915,0.06516588186827757,0.3855311355311355,0.06590195946389009 +flat_mae,patch,logistic,aabc_age,65,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,65,21.54434690031882,test,0.40384615384615385,0.06534614252727751,0.403448275862069,0.0630477208673662,0.39880952380952384,0.06468739812463575 +flat_mae,patch,logistic,aabc_age,66,0.005994842503189409,train,0.6771653543307087,0.019881217732463898,0.6761915576921059,0.020036122056986422,0.6787717519932335,0.019733563452898294 +flat_mae,patch,logistic,aabc_age,66,0.005994842503189409,test,0.5,0.06510859158532652,0.4997624090366026,0.06622957333005959,0.49977106227106227,0.06550333471740312 +flat_mae,patch,logistic,aabc_age,67,0.000774263682681127,train,0.5590551181102362,0.021320960559194278,0.5542791191181448,0.021669103641116298,0.5591651578763648,0.021195946761134052 +flat_mae,patch,logistic,aabc_age,67,0.000774263682681127,test,0.5384615384615384,0.05792684378394209,0.48571428571428565,0.06154641953180524,0.530448717948718,0.05696564197338571 +flat_mae,patch,logistic,aabc_age,68,0.005994842503189409,train,0.6673228346456693,0.0203761100525032,0.6657150683116648,0.02053572320209474,0.6672857262044269,0.020404153610695613 +flat_mae,patch,logistic,aabc_age,68,0.005994842503189409,test,0.4423076923076923,0.06280451261441114,0.4351851851851851,0.06275279503602807,0.4416208791208791,0.06296079226510022 +flat_mae,patch,logistic,aabc_age,69,0.005994842503189409,train,0.6751968503937008,0.019947501856264118,0.6732525814697263,0.02022624719728407,0.6765556762800903,0.019925893734995502 +flat_mae,patch,logistic,aabc_age,69,0.005994842503189409,test,0.36538461538461536,0.06878742660669607,0.3662687886825818,0.06937554694299121,0.36790293040293043,0.06922065082916092 +flat_mae,patch,logistic,aabc_age,70,0.3593813663804626,train,0.9881889763779528,0.004720937044114555,0.9882622146160873,0.004687507994341244,0.9885059427797671,0.004599453011319235 +flat_mae,patch,logistic,aabc_age,70,0.3593813663804626,test,0.4230769230769231,0.06688575440265165,0.4220196068022155,0.067329202795983,0.42719780219780223,0.06754125565583671 +flat_mae,patch,logistic,aabc_age,71,0.000774263682681127,train,0.5551181102362205,0.020599536965229245,0.5465042735042736,0.021032949076069708,0.5539627082658054,0.020524722764578805 +flat_mae,patch,logistic,aabc_age,71,0.000774263682681127,test,0.4807692307692308,0.06705738071004792,0.4768981481481482,0.06735640110330483,0.47733516483516486,0.06699462310045028 +flat_mae,patch,logistic,aabc_age,72,0.046415888336127774,train,0.8484251968503937,0.015616013566840928,0.8495668738491705,0.015571128069642521,0.850167773006335,0.015548715266286397 +flat_mae,patch,logistic,aabc_age,72,0.046415888336127774,test,0.46153846153846156,0.06643281964983287,0.4619444444444445,0.06573222597011964,0.45833333333333337,0.06647204854441477 +flat_mae,patch,logistic,aabc_age,73,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,73,166.81005372000556,test,0.4230769230769231,0.06524559882229967,0.42879948914431676,0.06451895624528432,0.42422161172161177,0.06548237696349339 +flat_mae,patch,logistic,aabc_age,74,0.000774263682681127,train,0.5452755905511811,0.020737583468059536,0.5401180646175605,0.021040591764716402,0.5450698758508523,0.02062625323995004 +flat_mae,patch,logistic,aabc_age,74,0.000774263682681127,test,0.5384615384615384,0.053805740328590326,0.4621415770609319,0.048529122632210916,0.5247252747252747,0.05259479598693791 +flat_mae,patch,logistic,aabc_age,75,0.005994842503189409,train,0.6948818897637795,0.019658752133161216,0.6942482892138195,0.019757544403172705,0.6964641563209044,0.019600320207150364 +flat_mae,patch,logistic,aabc_age,75,0.005994842503189409,test,0.4423076923076923,0.06234656906804265,0.43534562211981565,0.06337219337368345,0.44459706959706957,0.0629249880869516 +flat_mae,patch,logistic,aabc_age,76,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,76,2.782559402207126,test,0.5384615384615384,0.0672777845641337,0.5425,0.06761964030266779,0.5384615384615384,0.06755113903100086 +flat_mae,patch,logistic,aabc_age,77,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,77,2.782559402207126,test,0.38461538461538464,0.06616676975732111,0.3851851851851852,0.0679399737838436,0.38873626373626374,0.06675605586019177 +flat_mae,patch,logistic,aabc_age,78,0.046415888336127774,train,0.8346456692913385,0.01637759832672221,0.8353362268151463,0.016384145117293362,0.8361400988513374,0.016253958245969223 +flat_mae,patch,logistic,aabc_age,78,0.046415888336127774,test,0.5192307692307693,0.06770214089419037,0.5251068376068376,0.06621504863311409,0.5219780219780219,0.06799421044323695 +flat_mae,patch,logistic,aabc_age,79,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,79,2.782559402207126,test,0.40384615384615385,0.06367143610087594,0.38887189469781236,0.06420555797804028,0.39880952380952384,0.06329599229234485 +flat_mae,patch,logistic,aabc_age,80,0.000774263682681127,train,0.5433070866141733,0.02123493583331487,0.5321281357771019,0.022069450879027515,0.5418835552725507,0.02112866931439967 +flat_mae,patch,logistic,aabc_age,80,0.000774263682681127,test,0.5384615384615384,0.06591275388163018,0.533305485937065,0.06839327793844896,0.5366300366300366,0.06604943131418395 +flat_mae,patch,logistic,aabc_age,81,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,81,166.81005372000556,test,0.4230769230769231,0.06612856180494577,0.42108306763479175,0.06695344119731468,0.4226190476190476,0.06596965489167567 +flat_mae,patch,logistic,aabc_age,82,0.005994842503189409,train,0.6712598425196851,0.019506602292943438,0.6697934164548305,0.019804936250493833,0.672890946107417,0.01949937644035737 +flat_mae,patch,logistic,aabc_age,82,0.005994842503189409,test,0.46153846153846156,0.06694959686742005,0.45106023009248813,0.06774669358238025,0.459478021978022,0.06711575742924177 +flat_mae,patch,logistic,aabc_age,83,0.005994842503189409,train,0.6830708661417323,0.021103280330244417,0.681347913593503,0.0213580793798691,0.6831472039110913,0.021059214662968673 +flat_mae,patch,logistic,aabc_age,83,0.005994842503189409,test,0.4230769230769231,0.06233622328732959,0.41452254641909814,0.06304978703035773,0.4223901098901099,0.06224945719795456 +flat_mae,patch,logistic,aabc_age,84,0.005994842503189409,train,0.6594488188976378,0.020776466045097346,0.6586012594009713,0.021010941151725828,0.6604266440220258,0.0207460013285753 +flat_mae,patch,logistic,aabc_age,84,0.005994842503189409,test,0.5576923076923077,0.06552486090370359,0.5428152492668621,0.07056172826174288,0.553113553113553,0.0657028781378846 +flat_mae,patch,logistic,aabc_age,85,9.999999999999999e-05,train,0.5118110236220472,0.020027538545827357,0.4838032034307849,0.02106405512944349,0.5085581494814813,0.01990284128432755 +flat_mae,patch,logistic,aabc_age,85,9.999999999999999e-05,test,0.4807692307692308,0.05440240161771489,0.4220924908424909,0.06343330551435565,0.4741300366300366,0.053230099325330446 +flat_mae,patch,logistic,aabc_age,86,0.046415888336127774,train,0.8346456692913385,0.015957166454678692,0.8352228070440879,0.015905015530786926,0.8350522594454428,0.015956289737632207 +flat_mae,patch,logistic,aabc_age,86,0.046415888336127774,test,0.5769230769230769,0.05804553405447002,0.5541666666666667,0.06281099603173654,0.5721153846153846,0.05786108819152752 +flat_mae,patch,logistic,aabc_age,87,0.005994842503189409,train,0.6692913385826772,0.019880759303637804,0.6684598393766512,0.02014043407634552,0.6694694364476428,0.01994603760871996 +flat_mae,patch,logistic,aabc_age,87,0.005994842503189409,test,0.4423076923076923,0.06340207003881734,0.4306857658470562,0.06376078500893331,0.44459706959706957,0.06394419235401709 +flat_mae,patch,logistic,aabc_age,88,0.005994842503189409,train,0.6653543307086615,0.018638942910486796,0.6639677630896067,0.018946358193573865,0.6670101402216003,0.01857145594193201 +flat_mae,patch,logistic,aabc_age,88,0.005994842503189409,test,0.5384615384615384,0.06661150948046644,0.5339544650751548,0.06812983189793362,0.5368589743589743,0.0668637376666129 +flat_mae,patch,logistic,aabc_age,89,0.000774263682681127,train,0.5708661417322834,0.02129316250108326,0.5630527816261298,0.021905658987048014,0.5708944041780705,0.0212916555151198 +flat_mae,patch,logistic,aabc_age,89,0.000774263682681127,test,0.46153846153846156,0.06579895864358251,0.45407563573947274,0.0681364427209172,0.4624542124542125,0.06595745632593424 +flat_mae,patch,logistic,aabc_age,90,0.046415888336127774,train,0.8385826771653543,0.01618073787355066,0.8385535831691207,0.016282923243887536,0.8390345308397377,0.016196302639053087 +flat_mae,patch,logistic,aabc_age,90,0.046415888336127774,test,0.5384615384615384,0.06043553707887301,0.5231336405529954,0.061525803919423215,0.5423534798534798,0.06087824452480814 +flat_mae,patch,logistic,aabc_age,91,9.999999999999999e-05,train,0.5,0.02123265212240412,0.467599191121273,0.021554045116588608,0.4964789964882267,0.020988393318979642 +flat_mae,patch,logistic,aabc_age,91,9.999999999999999e-05,test,0.4807692307692308,0.06228556112182305,0.44781037083268316,0.06653599562841063,0.4771062271062272,0.061823327880311495 +flat_mae,patch,logistic,aabc_age,92,0.046415888336127774,train,0.8405511811023622,0.015668030555062225,0.8411726867942043,0.015668018374263848,0.8413682010936172,0.015618050414730836 +flat_mae,patch,logistic,aabc_age,92,0.046415888336127774,test,0.5192307692307693,0.05453269742784961,0.49319419237749546,0.06081965374103299,0.5215201465201466,0.054937268104739666 +flat_mae,patch,logistic,aabc_age,93,0.005994842503189409,train,0.6889763779527559,0.021106232383968738,0.6901430850351411,0.021048809860789965,0.6905157425645727,0.021121096681451765 +flat_mae,patch,logistic,aabc_age,93,0.005994842503189409,test,0.46153846153846156,0.060211707367770366,0.4557851568721134,0.05929305859794223,0.45947802197802196,0.060180357320159736 +flat_mae,patch,logistic,aabc_age,94,0.000774263682681127,train,0.5787401574803149,0.021387780690719775,0.5737317467782129,0.021681080128678015,0.5787737178958513,0.021299147626566983 +flat_mae,patch,logistic,aabc_age,94,0.000774263682681127,test,0.40384615384615385,0.06204277728324025,0.39073928944618597,0.06547239709435346,0.40453296703296704,0.062224121560807984 +flat_mae,patch,logistic,aabc_age,95,0.000774263682681127,train,0.5688976377952756,0.020393276680599103,0.5649893841130645,0.021089886852165923,0.5684255181831608,0.020452994541140423 +flat_mae,patch,logistic,aabc_age,95,0.000774263682681127,test,0.5,0.06581868361207201,0.490952380952381,0.06572663629895469,0.4951923076923077,0.06557785358501912 +flat_mae,patch,logistic,aabc_age,96,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,96,166.81005372000556,test,0.36538461538461536,0.06567780419972216,0.3698371812852879,0.0635808742575646,0.36034798534798534,0.06494804315768009 +flat_mae,patch,logistic,aabc_age,97,9.999999999999999e-05,train,0.5059055118110236,0.019658096128096606,0.4784990025955815,0.02034204703010793,0.5027273302658859,0.019517375101975758 +flat_mae,patch,logistic,aabc_age,97,9.999999999999999e-05,test,0.40384615384615385,0.06276866515582268,0.3926242236024845,0.06487373277030235,0.4001831501831502,0.06230947879044853 +flat_mae,patch,logistic,aabc_age,98,0.005994842503189409,train,0.687007874015748,0.020248519501560692,0.6854536147084839,0.020651960626209297,0.6883172880517234,0.020185627546645338 +flat_mae,patch,logistic,aabc_age,98,0.005994842503189409,test,0.4230769230769231,0.051149782950252964,0.3856421356421357,0.061627653962604015,0.42376373626373626,0.05157839484724506 +flat_mae,patch,logistic,aabc_age,99,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,99,2.782559402207126,test,0.5192307692307693,0.06805926541968738,0.5148809523809523,0.06790195380768724,0.5217490842490842,0.06856635974923782 +flat_mae,patch,logistic,aabc_age,100,0.3593813663804626,train,0.9921259842519685,0.0038523395723949762,0.9920867443145884,0.0038663920591456608,0.9921030650819254,0.0038659863619088923 +flat_mae,patch,logistic,aabc_age,100,0.3593813663804626,test,0.4423076923076923,0.06621655123007188,0.4371426259574927,0.06847526642404167,0.44826007326007333,0.06609632436690742 diff --git a/input_space_v3/flat_lr1e-3_6/eval_v2/aabc_age__patch__logistic/log.txt b/input_space_v3/flat_lr1e-3_6/eval_v2/aabc_age__patch__logistic/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..9ea73836010c77a33f3252786da1e89619190f36 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_6/eval_v2/aabc_age__patch__logistic/log.txt @@ -0,0 +1,245 @@ +fMRI foundation model logistic probe eval +version: 0.1.dev86+gf97f52698 +sha: bcce2b486277d3a5b520775efd9cdf1a2affce36, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-04-08 22:54:04 +config: +output_root: experiments/input_space_v3/output +name_prefix: eval_logistic +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_6; eval v2 (aabc_age patch logistic) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: input_space_v3/flat_lr1e-3_6/eval_v2/aabc_age__patch__logistic +model: flat_mae +representation: patch +dataset: aabc_age +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/eval_v2/aabc_age__patch__logistic +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=True, reg_tokens=0, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: aabc_age (flat) +train (n=455): +HFDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'segment', 'bold', 'mean', 'std'], + num_rows: 471 +}), + labels=[0 1 2 3], + counts=[110 127 109 109] +) + +validation (n=53): +HFDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'segment', 'bold', 'mean', 'std'], + num_rows: 58 +}), + labels=[0 1 2 3], + counts=[14 13 12 14] +) + +test (n=52): +HFDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'segment', 'bold', 'mean', 'std'], + num_rows: 55 +}), + labels=[0 1 2 3], + counts=[13 13 12 14] +) + +extracting features for all splits +extract (train) [ 0/228] eta: 0:19:40 time: 5.1760 data: 4.1040 max mem: 3205 +extract (train) [ 20/228] eta: 0:01:36 time: 0.2281 data: 0.0802 max mem: 3393 +extract (train) [ 40/228] eta: 0:01:01 time: 0.1845 data: 0.0567 max mem: 3393 +extract (train) [ 60/228] eta: 0:00:48 time: 0.2032 data: 0.0676 max mem: 3393 +extract (train) [ 80/228] eta: 0:00:39 time: 0.1960 data: 0.0633 max mem: 3393 +extract (train) [100/228] eta: 0:00:32 time: 0.1981 data: 0.0635 max mem: 3393 +extract (train) [120/228] eta: 0:00:25 time: 0.1854 data: 0.0569 max mem: 3393 +extract (train) [140/228] eta: 0:00:20 time: 0.1917 data: 0.0591 max mem: 3393 +extract (train) [160/228] eta: 0:00:15 time: 0.2007 data: 0.0673 max mem: 3393 +extract (train) [180/228] eta: 0:00:10 time: 0.2083 data: 0.0694 max mem: 3393 +extract (train) [200/228] eta: 0:00:06 time: 0.1909 data: 0.0611 max mem: 3393 +extract (train) [220/228] eta: 0:00:01 time: 0.1614 data: 0.0436 max mem: 3393 +extract (train) [227/228] eta: 0:00:00 time: 0.1574 data: 0.0429 max mem: 3393 +extract (train) Total time: 0:00:49 (0.2182 s / it) +extract (validation) [ 0/27] eta: 0:02:03 time: 4.5722 data: 4.4072 max mem: 3393 +extract (validation) [20/27] eta: 0:00:02 time: 0.1812 data: 0.0554 max mem: 3393 +extract (validation) [26/27] eta: 0:00:00 time: 0.1675 data: 0.0501 max mem: 3393 +extract (validation) Total time: 0:00:09 (0.3514 s / it) +extract (test) [ 0/26] eta: 0:01:59 time: 4.5893 data: 4.4135 max mem: 3393 +extract (test) [20/26] eta: 0:00:02 time: 0.2154 data: 0.0731 max mem: 3393 +extract (test) [25/26] eta: 0:00:00 time: 0.1952 data: 0.0638 max mem: 3393 +extract (test) Total time: 0:00:10 (0.3896 s / it) +feature extraction time: 0:01:09 +train features: (455, 768) +validation features: (53, 768) +test features: (52, 768) +evaluating fixed splits +eval results (fixed splits): + +| model | repr | clf | dataset | trial | C | split | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|----------:|:--------|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | aabc_age | | 0.0059948 | train | 0.65748 | 0.022054 | 0.65525 | 0.02251 | 0.65849 | 0.021983 | +| flat_mae | patch | logistic | aabc_age | | 0.0059948 | test | 0.42308 | 0.06462 | 0.40546 | 0.068237 | 0.4169 | 0.064259 | + + +evaluating random splits (n=100) +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 1, "C": 0.046415888336127774, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.06342599237596318, "f1": 0.4768518518518518, "f1_std": 0.06407323651954998, "bacc": 0.48168498168498164, "bacc_std": 0.06335359562275787} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 2, "C": 9.999999999999999e-05, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.06292096103269647, "f1": 0.4366013071895425, "f1_std": 0.06440377669882659, "bacc": 0.45650183150183155, "bacc_std": 0.0620165166594045} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 3, "C": 0.046415888336127774, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.06548041624213001, "f1": 0.5089400183150183, "f1_std": 0.06707999089586247, "bacc": 0.5187728937728937, "bacc_std": 0.06540738112373858} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 4, "C": 2.782559402207126, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.06318265060345368, "f1": 0.47110158862876256, "f1_std": 0.06001277097146709, "bacc": 0.46543040293040294, "bacc_std": 0.06390527918927776} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 5, "C": 9.999999999999999e-05, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.059662400814968194, "f1": 0.4488479262672811, "f1_std": 0.06352926026527948, "bacc": 0.47847985347985345, "bacc_std": 0.05908409814553934} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 6, "C": 0.005994842503189409, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.0623368402856989, "f1": 0.5218808511468247, "f1_std": 0.0673262930914047, "bacc": 0.5336538461538461, "bacc_std": 0.06213877650592559} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 7, "C": 21.54434690031882, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.06849967606713023, "f1": 0.47644370122630997, "f1_std": 0.06880498062356352, "bacc": 0.4777930402930403, "bacc_std": 0.06860835119669721} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 8, "C": 2.782559402207126, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.06615031296468252, "f1": 0.4835164835164836, "f1_std": 0.06574575548010583, "bacc": 0.4835164835164835, "bacc_std": 0.06619719476483318} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 9, "C": 0.046415888336127774, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.06347999731546622, "f1": 0.41550116550116545, "f1_std": 0.06132277275971671, "bacc": 0.41941391941391937, "bacc_std": 0.06285088878374989} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 10, "C": 0.000774263682681127, "split": "test", "acc": 0.5, "acc_std": 0.06510119569157984, "f1": 0.491991341991342, "f1_std": 0.06538203246100761, "bacc": 0.4965659340659341, "bacc_std": 0.06485537299895242} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 11, "C": 166.81005372000556, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.06931699758245559, "f1": 0.5516883116883117, "f1_std": 0.06751642901218378, "bacc": 0.5370879120879121, "bacc_std": 0.06938548831450281} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 12, "C": 0.000774263682681127, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.06384967552845322, "f1": 0.4366589026915114, "f1_std": 0.06489871643919556, "bacc": 0.44047619047619047, "bacc_std": 0.06385638628490728} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 13, "C": 0.005994842503189409, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.06159305270898524, "f1": 0.43395976004671655, "f1_std": 0.0610052394480305, "bacc": 0.4429945054945055, "bacc_std": 0.0619843680637154} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 14, "C": 0.005994842503189409, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.06585302803801164, "f1": 0.5294675925925926, "f1_std": 0.06929548050567615, "bacc": 0.5396062271062271, "bacc_std": 0.06586473760887991} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 15, "C": 0.000774263682681127, "split": "test", "acc": 0.5, "acc_std": 0.06699425922592747, "f1": 0.49896551724137933, "f1_std": 0.06745061934556784, "bacc": 0.5009157509157509, "bacc_std": 0.06739133874937511} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 16, "C": 0.000774263682681127, "split": "test", "acc": 0.40384615384615385, "acc_std": 0.06220413997143437, "f1": 0.38475568004979765, "f1_std": 0.058678630169417025, "bacc": 0.39720695970695963, "bacc_std": 0.0614337779696145} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 17, "C": 0.000774263682681127, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.060749217736702596, "f1": 0.3891223155929039, "f1_std": 0.05853187937116895, "bacc": 0.4178113553113553, "bacc_std": 0.059620292149024263} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 18, "C": 9.999999999999999e-05, "split": "test", "acc": 0.5, "acc_std": 0.05718681107516614, "f1": 0.4421344421344421, "f1_std": 0.04918022587452232, "bacc": 0.4876373626373626, "bacc_std": 0.05579319918820855} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 19, "C": 0.046415888336127774, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.06930675317386437, "f1": 0.4231634182908546, "f1_std": 0.06975734259271019, "bacc": 0.42422161172161177, "bacc_std": 0.06975873876646804} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 20, "C": 0.005994842503189409, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.05870143088686749, "f1": 0.44965686274509803, "f1_std": 0.06393342742195805, "bacc": 0.4771062271062271, "bacc_std": 0.05833019363743638} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 21, "C": 0.000774263682681127, "split": "test", "acc": 0.38461538461538464, "acc_std": 0.055845769759221696, "f1": 0.3537545787545787, "f1_std": 0.058461494694228455, "bacc": 0.3864468864468864, "bacc_std": 0.056396293232473596} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 22, "C": 10000.0, "split": "test", "acc": 0.3269230769230769, "acc_std": 0.06075378333362551, "f1": 0.32116977225672877, "f1_std": 0.06036341101423359, "bacc": 0.32348901098901095, "bacc_std": 0.06054361659955399} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 23, "C": 0.000774263682681127, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.059776148000874774, "f1": 0.444544220945083, "f1_std": 0.06180223791698779, "bacc": 0.4592490842490842, "bacc_std": 0.05949119280358305} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 24, "C": 0.046415888336127774, "split": "test", "acc": 0.38461538461538464, "acc_std": 0.061431288887975236, "f1": 0.3706249051076637, "f1_std": 0.05747057432972352, "bacc": 0.37934981684981683, "bacc_std": 0.06048908233835105} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 25, "C": 9.999999999999999e-05, "split": "test", "acc": 0.3076923076923077, "acc_std": 0.0566156459024071, "f1": 0.2783711386652563, "f1_std": 0.054703245810436965, "bacc": 0.30654761904761907, "bacc_std": 0.056439262164470635} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 26, "C": 0.000774263682681127, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.06077666702310904, "f1": 0.4173109243697479, "f1_std": 0.06376755681035445, "bacc": 0.440018315018315, "bacc_std": 0.060665001564867316} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 27, "C": 0.000774263682681127, "split": "test", "acc": 0.40384615384615385, "acc_std": 0.0601430616931204, "f1": 0.37950759251068844, "f1_std": 0.06231193872785755, "bacc": 0.39903846153846156, "bacc_std": 0.05980991710216118} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 28, "C": 0.3593813663804626, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.0677428133265548, "f1": 0.4488095238095238, "f1_std": 0.06800986830542088, "bacc": 0.44345238095238093, "bacc_std": 0.06799370889600091} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 29, "C": 9.999999999999999e-05, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.059459336709161925, "f1": 0.40297165200391005, "f1_std": 0.0559197746607423, "bacc": 0.4191849816849817, "bacc_std": 0.05867284224812532} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 30, "C": 0.046415888336127774, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.07112053274206255, "f1": 0.5475, "f1_std": 0.06922572183493143, "bacc": 0.5398351648351648, "bacc_std": 0.07090906690063847} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 31, "C": 9.999999999999999e-05, "split": "test", "acc": 0.5576923076923077, "acc_std": 0.0603237812133959, "f1": 0.5249193548387097, "f1_std": 0.06361205439831025, "bacc": 0.549908424908425, "bacc_std": 0.059683697637371434} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 32, "C": 0.046415888336127774, "split": "test", "acc": 0.5, "acc_std": 0.06598676351041836, "f1": 0.4926262626262626, "f1_std": 0.06492546307996634, "bacc": 0.4965659340659341, "bacc_std": 0.06574039163450209} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 33, "C": 0.005994842503189409, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.061243173753169795, "f1": 0.5212215320910972, "f1_std": 0.062190957263810596, "bacc": 0.5203754578754579, "bacc_std": 0.06166103981819946} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 34, "C": 0.3593813663804626, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.06881868811826862, "f1": 0.53125, "f1_std": 0.06765326872735347, "bacc": 0.5206043956043955, "bacc_std": 0.06874346136170084} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 35, "C": 0.046415888336127774, "split": "test", "acc": 0.38461538461538464, "acc_std": 0.06308924598202044, "f1": 0.3968567664219838, "f1_std": 0.06116302248290686, "bacc": 0.3825549450549451, "bacc_std": 0.06274218300010324} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 36, "C": 0.005994842503189409, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.06313196472797437, "f1": 0.4654761904761905, "f1_std": 0.06446708061470025, "bacc": 0.4800824175824176, "bacc_std": 0.06322326560909891} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 37, "C": 0.046415888336127774, "split": "test", "acc": 0.36538461538461536, "acc_std": 0.06066914835507565, "f1": 0.3532230911263169, "f1_std": 0.057271289433190334, "bacc": 0.3573717948717949, "bacc_std": 0.05978750781125011} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 38, "C": 9.999999999999999e-05, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.0637150066389851, "f1": 0.43466880341880343, "f1_std": 0.06030898065435152, "bacc": 0.4535256410256411, "bacc_std": 0.06263471720436749} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 39, "C": 0.005994842503189409, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.06426013837998938, "f1": 0.4443809585999739, "f1_std": 0.06321199582586463, "bacc": 0.4551282051282051, "bacc_std": 0.06350526549472431} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 40, "C": 0.000774263682681127, "split": "test", "acc": 0.5, "acc_std": 0.06360803603728628, "f1": 0.49522546419098146, "f1_std": 0.06414915504653712, "bacc": 0.5009157509157509, "bacc_std": 0.06396368307545974} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 41, "C": 166.81005372000556, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.06388871380360767, "f1": 0.4455139915497972, "f1_std": 0.06365041312019633, "bacc": 0.4652014652014652, "bacc_std": 0.06473947213197759} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 42, "C": 0.000774263682681127, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.06126780625124615, "f1": 0.4631469979296066, "f1_std": 0.06671235466048085, "bacc": 0.48031135531135527, "bacc_std": 0.06140604698501656} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 43, "C": 0.005994842503189409, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.06361864004320389, "f1": 0.4504046677959721, "f1_std": 0.0626452215984143, "bacc": 0.45375457875457875, "bacc_std": 0.06317135454184072} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 44, "C": 0.3593813663804626, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.06615635057871233, "f1": 0.4604558404558404, "f1_std": 0.06686030169402246, "bacc": 0.4626831501831502, "bacc_std": 0.0665753728167823} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 45, "C": 0.000774263682681127, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.06510374061004574, "f1": 0.4734719941616493, "f1_std": 0.0661352978596558, "bacc": 0.48168498168498164, "bacc_std": 0.0652268631771833} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 46, "C": 0.005994842503189409, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.06898969779877909, "f1": 0.48001567398119127, "f1_std": 0.07060297582067282, "bacc": 0.4835164835164835, "bacc_std": 0.06905538184712583} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 47, "C": 0.005994842503189409, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.06496265426923488, "f1": 0.46597771190162496, "f1_std": 0.06808613237651137, "bacc": 0.4773351648351648, "bacc_std": 0.06480677364527632} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 48, "C": 0.005994842503189409, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.07017417047021954, "f1": 0.4462731481481481, "f1_std": 0.0706278947180325, "bacc": 0.44184981684981683, "bacc_std": 0.07025501691540043} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 49, "C": 9.999999999999999e-05, "split": "test", "acc": 0.38461538461538464, "acc_std": 0.06161076281523023, "f1": 0.3844039174921528, "f1_std": 0.0632962107238896, "bacc": 0.38095238095238093, "bacc_std": 0.061575707189448756} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 50, "C": 0.3593813663804626, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.06422099188596023, "f1": 0.4633333333333333, "f1_std": 0.06327228201801259, "bacc": 0.4597069597069597, "bacc_std": 0.06401637831887858} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 51, "C": 0.005994842503189409, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.0730420564595105, "f1": 0.47619047619047616, "f1_std": 0.07325573513836017, "bacc": 0.4789377289377289, "bacc_std": 0.07300413037026988} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 52, "C": 0.005994842503189409, "split": "test", "acc": 0.40384615384615385, "acc_std": 0.0686600837502527, "f1": 0.4114097496706193, "f1_std": 0.06846911675271058, "bacc": 0.4033882783882784, "bacc_std": 0.06864462410474251} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 53, "C": 9.999999999999999e-05, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.05883303021081764, "f1": 0.49775124069478904, "f1_std": 0.057766028658066, "bacc": 0.530448717948718, "bacc_std": 0.057794218278287283} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 54, "C": 0.000774263682681127, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.05958381297995933, "f1": 0.43348669877307644, "f1_std": 0.061106866855819446, "bacc": 0.4578754578754579, "bacc_std": 0.05913210568282574} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 55, "C": 0.000774263682681127, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.0653386263604811, "f1": 0.4780952380952381, "f1_std": 0.06632982217495896, "bacc": 0.4789377289377289, "bacc_std": 0.06547343429449655} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 56, "C": 9.999999999999999e-05, "split": "test", "acc": 0.40384615384615385, "acc_std": 0.0633434682537529, "f1": 0.38433706816059754, "f1_std": 0.0645829419314376, "bacc": 0.4015567765567766, "bacc_std": 0.06308143682259199} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 57, "C": 9.999999999999999e-05, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.06148520532105899, "f1": 0.41005291005291, "f1_std": 0.052001883319933405, "bacc": 0.45329670329670335, "bacc_std": 0.05988855193809884} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 58, "C": 0.000774263682681127, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.06391650433672996, "f1": 0.43070120812056295, "f1_std": 0.06904337465715248, "bacc": 0.43864468864468864, "bacc_std": 0.06360196164414714} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 59, "C": 0.046415888336127774, "split": "test", "acc": 0.34615384615384615, "acc_std": 0.06772476276166836, "f1": 0.3489785174567783, "f1_std": 0.06775448982678092, "bacc": 0.34867216117216115, "bacc_std": 0.06804446926011799} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 60, "C": 0.000774263682681127, "split": "test", "acc": 0.36538461538461536, "acc_std": 0.056077978253236044, "f1": 0.3405982905982906, "f1_std": 0.055281918723151524, "bacc": 0.3628663003663004, "bacc_std": 0.05551746424980148} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 61, "C": 0.046415888336127774, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.06633579629297055, "f1": 0.4304620111071724, "f1_std": 0.06674839770475924, "bacc": 0.42422161172161177, "bacc_std": 0.06651232214303306} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 62, "C": 0.005994842503189409, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.0674432810133534, "f1": 0.423036223036223, "f1_std": 0.06668660903480098, "bacc": 0.4182692307692307, "bacc_std": 0.06730131678926288} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 63, "C": 0.005994842503189409, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.058063727487168294, "f1": 0.3974753694581281, "f1_std": 0.058456914714168036, "bacc": 0.4251373626373627, "bacc_std": 0.05863375182831778} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 64, "C": 0.046415888336127774, "split": "test", "acc": 0.38461538461538464, "acc_std": 0.06571971820501626, "f1": 0.3915343915343915, "f1_std": 0.06516588186827757, "bacc": 0.3855311355311355, "bacc_std": 0.06590195946389009} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 65, "C": 21.54434690031882, "split": "test", "acc": 0.40384615384615385, "acc_std": 0.06534614252727751, "f1": 0.403448275862069, "f1_std": 0.0630477208673662, "bacc": 0.39880952380952384, "bacc_std": 0.06468739812463575} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 66, "C": 0.005994842503189409, "split": "test", "acc": 0.5, "acc_std": 0.06510859158532652, "f1": 0.4997624090366026, "f1_std": 0.06622957333005959, "bacc": 0.49977106227106227, "bacc_std": 0.06550333471740312} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 67, "C": 0.000774263682681127, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.05792684378394209, "f1": 0.48571428571428565, "f1_std": 0.06154641953180524, "bacc": 0.530448717948718, "bacc_std": 0.05696564197338571} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 68, "C": 0.005994842503189409, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.06280451261441114, "f1": 0.4351851851851851, "f1_std": 0.06275279503602807, "bacc": 0.4416208791208791, "bacc_std": 0.06296079226510022} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 69, "C": 0.005994842503189409, "split": "test", "acc": 0.36538461538461536, "acc_std": 0.06878742660669607, "f1": 0.3662687886825818, "f1_std": 0.06937554694299121, "bacc": 0.36790293040293043, "bacc_std": 0.06922065082916092} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 70, "C": 0.3593813663804626, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.06688575440265165, "f1": 0.4220196068022155, "f1_std": 0.067329202795983, "bacc": 0.42719780219780223, "bacc_std": 0.06754125565583671} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 71, "C": 0.000774263682681127, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.06705738071004792, "f1": 0.4768981481481482, "f1_std": 0.06735640110330483, "bacc": 0.47733516483516486, "bacc_std": 0.06699462310045028} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 72, "C": 0.046415888336127774, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.06643281964983287, "f1": 0.4619444444444445, "f1_std": 0.06573222597011964, "bacc": 0.45833333333333337, "bacc_std": 0.06647204854441477} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 73, "C": 166.81005372000556, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.06524559882229967, "f1": 0.42879948914431676, "f1_std": 0.06451895624528432, "bacc": 0.42422161172161177, "bacc_std": 0.06548237696349339} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 74, "C": 0.000774263682681127, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.053805740328590326, "f1": 0.4621415770609319, "f1_std": 0.048529122632210916, "bacc": 0.5247252747252747, "bacc_std": 0.05259479598693791} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 75, "C": 0.005994842503189409, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.06234656906804265, "f1": 0.43534562211981565, "f1_std": 0.06337219337368345, "bacc": 0.44459706959706957, "bacc_std": 0.0629249880869516} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 76, "C": 2.782559402207126, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.0672777845641337, "f1": 0.5425, "f1_std": 0.06761964030266779, "bacc": 0.5384615384615384, "bacc_std": 0.06755113903100086} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 77, "C": 2.782559402207126, "split": "test", "acc": 0.38461538461538464, "acc_std": 0.06616676975732111, "f1": 0.3851851851851852, "f1_std": 0.0679399737838436, "bacc": 0.38873626373626374, "bacc_std": 0.06675605586019177} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 78, "C": 0.046415888336127774, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.06770214089419037, "f1": 0.5251068376068376, "f1_std": 0.06621504863311409, "bacc": 0.5219780219780219, "bacc_std": 0.06799421044323695} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 79, "C": 2.782559402207126, "split": "test", "acc": 0.40384615384615385, "acc_std": 0.06367143610087594, "f1": 0.38887189469781236, "f1_std": 0.06420555797804028, "bacc": 0.39880952380952384, "bacc_std": 0.06329599229234485} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 80, "C": 0.000774263682681127, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.06591275388163018, "f1": 0.533305485937065, "f1_std": 0.06839327793844896, "bacc": 0.5366300366300366, "bacc_std": 0.06604943131418395} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 81, "C": 166.81005372000556, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.06612856180494577, "f1": 0.42108306763479175, "f1_std": 0.06695344119731468, "bacc": 0.4226190476190476, "bacc_std": 0.06596965489167567} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 82, "C": 0.005994842503189409, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.06694959686742005, "f1": 0.45106023009248813, "f1_std": 0.06774669358238025, "bacc": 0.459478021978022, "bacc_std": 0.06711575742924177} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 83, "C": 0.005994842503189409, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.06233622328732959, "f1": 0.41452254641909814, "f1_std": 0.06304978703035773, "bacc": 0.4223901098901099, "bacc_std": 0.06224945719795456} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 84, "C": 0.005994842503189409, "split": "test", "acc": 0.5576923076923077, "acc_std": 0.06552486090370359, "f1": 0.5428152492668621, "f1_std": 0.07056172826174288, "bacc": 0.553113553113553, "bacc_std": 0.0657028781378846} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 85, "C": 9.999999999999999e-05, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.05440240161771489, "f1": 0.4220924908424909, "f1_std": 0.06343330551435565, "bacc": 0.4741300366300366, "bacc_std": 0.053230099325330446} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 86, "C": 0.046415888336127774, "split": "test", "acc": 0.5769230769230769, "acc_std": 0.05804553405447002, "f1": 0.5541666666666667, "f1_std": 0.06281099603173654, "bacc": 0.5721153846153846, "bacc_std": 0.05786108819152752} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 87, "C": 0.005994842503189409, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.06340207003881734, "f1": 0.4306857658470562, "f1_std": 0.06376078500893331, "bacc": 0.44459706959706957, "bacc_std": 0.06394419235401709} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 88, "C": 0.005994842503189409, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.06661150948046644, "f1": 0.5339544650751548, "f1_std": 0.06812983189793362, "bacc": 0.5368589743589743, "bacc_std": 0.0668637376666129} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 89, "C": 0.000774263682681127, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.06579895864358251, "f1": 0.45407563573947274, "f1_std": 0.0681364427209172, "bacc": 0.4624542124542125, "bacc_std": 0.06595745632593424} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 90, "C": 0.046415888336127774, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.06043553707887301, "f1": 0.5231336405529954, "f1_std": 0.061525803919423215, "bacc": 0.5423534798534798, "bacc_std": 0.06087824452480814} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 91, "C": 9.999999999999999e-05, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.06228556112182305, "f1": 0.44781037083268316, "f1_std": 0.06653599562841063, "bacc": 0.4771062271062272, "bacc_std": 0.061823327880311495} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 92, "C": 0.046415888336127774, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.05453269742784961, "f1": 0.49319419237749546, "f1_std": 0.06081965374103299, "bacc": 0.5215201465201466, "bacc_std": 0.054937268104739666} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 93, "C": 0.005994842503189409, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.060211707367770366, "f1": 0.4557851568721134, "f1_std": 0.05929305859794223, "bacc": 0.45947802197802196, "bacc_std": 0.060180357320159736} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 94, "C": 0.000774263682681127, "split": "test", "acc": 0.40384615384615385, "acc_std": 0.06204277728324025, "f1": 0.39073928944618597, "f1_std": 0.06547239709435346, "bacc": 0.40453296703296704, "bacc_std": 0.062224121560807984} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 95, "C": 0.000774263682681127, "split": "test", "acc": 0.5, "acc_std": 0.06581868361207201, "f1": 0.490952380952381, "f1_std": 0.06572663629895469, "bacc": 0.4951923076923077, "bacc_std": 0.06557785358501912} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 96, "C": 166.81005372000556, "split": "test", "acc": 0.36538461538461536, "acc_std": 0.06567780419972216, "f1": 0.3698371812852879, "f1_std": 0.0635808742575646, "bacc": 0.36034798534798534, "bacc_std": 0.06494804315768009} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 97, "C": 9.999999999999999e-05, "split": "test", "acc": 0.40384615384615385, "acc_std": 0.06276866515582268, "f1": 0.3926242236024845, "f1_std": 0.06487373277030235, "bacc": 0.4001831501831502, "bacc_std": 0.06230947879044853} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 98, "C": 0.005994842503189409, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.051149782950252964, "f1": 0.3856421356421357, "f1_std": 0.061627653962604015, "bacc": 0.42376373626373626, "bacc_std": 0.05157839484724506} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 99, "C": 2.782559402207126, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.06805926541968738, "f1": 0.5148809523809523, "f1_std": 0.06790195380768724, "bacc": 0.5217490842490842, "bacc_std": 0.06856635974923782} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 100, "C": 0.3593813663804626, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.06621655123007188, "f1": 0.4371426259574927, "f1_std": 0.06847526642404167, "bacc": 0.44826007326007333, "bacc_std": 0.06609632436690742} +eval results (random splits): + +| model | repr | clf | dataset | split | n_trials | C | C_std | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|-----------:|-------:|--------:|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | aabc_age | train | 100 | 108.97 | 999.76 | 0.71724 | 0.1754 | 0.71198 | 0.18131 | 0.71721 | 0.17603 | +| flat_mae | patch | logistic | aabc_age | test | 100 | 108.97 | 999.76 | 0.45846 | 0.055731 | 0.44661 | 0.055777 | 0.45667 | 0.055518 | + + +done! total time: 0:05:49 diff --git a/input_space_v3/flat_lr1e-3_6/eval_v2/aabc_sex__patch__logistic/config.yaml b/input_space_v3/flat_lr1e-3_6/eval_v2/aabc_sex__patch__logistic/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..977adb842a460b2d69a95655fddb83a003ddfee8 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_6/eval_v2/aabc_sex__patch__logistic/config.yaml @@ -0,0 +1,30 @@ +output_root: experiments/input_space_v3/output +name_prefix: eval_logistic +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_6; eval v2 (aabc_sex patch logistic) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: input_space_v3/flat_lr1e-3_6/eval_v2/aabc_sex__patch__logistic +model: flat_mae +representation: patch +dataset: aabc_sex +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/eval_v2/aabc_sex__patch__logistic +remote_dir: null diff --git a/input_space_v3/flat_lr1e-3_6/eval_v2/aabc_sex__patch__logistic/eval_table.csv b/input_space_v3/flat_lr1e-3_6/eval_v2/aabc_sex__patch__logistic/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..2471f08e6ae73f0e611ee4c11dc0cfcf77ef7fa0 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_6/eval_v2/aabc_sex__patch__logistic/eval_table.csv @@ -0,0 +1,203 @@ +model,repr,clf,dataset,trial,C,split,acc,acc_std,f1,f1_std,bacc,bacc_std +flat_mae,patch,logistic,aabc_sex,,0.005994842503189409,train,0.9035916824196597,0.013052185253112815,0.9007179630604141,0.013507395166949909,0.8986094847775176,0.013782458258980328 +flat_mae,patch,logistic,aabc_sex,,0.005994842503189409,test,0.9090909090909091,0.03899965670541853,0.905982905982906,0.04033393447602251,0.9090909090909091,0.040069831147981315 +flat_mae,patch,logistic,aabc_sex,1,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,1,2.782559402207126,test,0.7272727272727273,0.060481637128570416,0.717948717948718,0.06255583965749219,0.7167119565217391,0.062243918668036316 +flat_mae,patch,logistic,aabc_sex,2,0.3593813663804626,train,0.9867674858223062,0.005136943129837027,0.9864417081324122,0.005259806772891232,0.9867375948884786,0.005193492467830685 +flat_mae,patch,logistic,aabc_sex,2,0.3593813663804626,test,0.9090909090909091,0.040611442429423106,0.9071259709557582,0.04134577365904692,0.9096467391304348,0.04072304096085218 +flat_mae,patch,logistic,aabc_sex,3,0.046415888336127774,train,0.941398865784499,0.01072524956845004,0.9398080346491953,0.011056200470558109,0.9390075910782849,0.011353861481965584 +flat_mae,patch,logistic,aabc_sex,3,0.046415888336127774,test,0.8,0.05435476972387552,0.7931623931623932,0.056619840118301394,0.7914402173913043,0.056569751161206355 +flat_mae,patch,logistic,aabc_sex,4,0.3593813663804626,train,0.9905482041587902,0.004203070672857557,0.9903037190461352,0.004312814128218306,0.9900055687446877,0.004418365433470003 +flat_mae,patch,logistic,aabc_sex,4,0.3593813663804626,test,0.8181818181818182,0.05363451460603322,0.8151881720430108,0.054054196054455966,0.8192934782608696,0.05329102495580865 +flat_mae,patch,logistic,aabc_sex,5,0.005994842503189409,train,0.9092627599243857,0.012904926440691432,0.9067403185050245,0.01330070202667954,0.9057563234561388,0.013548990689087851 +flat_mae,patch,logistic,aabc_sex,5,0.005994842503189409,test,0.8181818181818182,0.051549222244856266,0.8106060606060606,0.05471023624922614,0.8070652173913043,0.05459919211959854 +flat_mae,patch,logistic,aabc_sex,6,0.3593813663804626,train,0.9867674858223062,0.004874628981935131,0.9864417081324122,0.0049911401601483605,0.9867375948884786,0.004946987826414274 +flat_mae,patch,logistic,aabc_sex,6,0.3593813663804626,test,0.9272727272727272,0.03665158718221091,0.9252717391304348,0.037676477828171816,0.9252717391304348,0.03793582409885245 +flat_mae,patch,logistic,aabc_sex,7,0.3593813663804626,train,0.9905482041587902,0.004432116287924327,0.9903155058088658,0.004537369782184068,0.9906137342829509,0.004419124731828675 +flat_mae,patch,logistic,aabc_sex,7,0.3593813663804626,test,0.8181818181818182,0.050861484234265064,0.8166666666666667,0.05092691006868968,0.8254076086956521,0.04974360775303029 +flat_mae,patch,logistic,aabc_sex,8,0.046415888336127774,train,0.941398865784499,0.009863617356699994,0.9398080346491953,0.010141654830339875,0.9390075910782849,0.010300668279906089 +flat_mae,patch,logistic,aabc_sex,8,0.046415888336127774,test,0.8181818181818182,0.04946304739753948,0.8166666666666667,0.04954797759546828,0.8254076086956521,0.048523674487442034 +flat_mae,patch,logistic,aabc_sex,9,0.3593813663804626,train,0.9886578449905482,0.0047438283670562815,0.9883715818165831,0.004862060965230323,0.9883715818165831,0.004893301347092659 +flat_mae,patch,logistic,aabc_sex,9,0.3593813663804626,test,0.8909090909090909,0.040138915804783154,0.8891129032258065,0.04056988176541941,0.8940217391304348,0.039765424073392806 +flat_mae,patch,logistic,aabc_sex,10,0.046415888336127774,train,0.9357277882797732,0.01074766859576978,0.9338555457487496,0.011106391424951513,0.9322811336791816,0.011401543883143857 +flat_mae,patch,logistic,aabc_sex,10,0.046415888336127774,test,0.8545454545454545,0.04861338114600011,0.8533333333333333,0.04858860131088121,0.8627717391304348,0.046422910791813654 +flat_mae,patch,logistic,aabc_sex,11,0.046415888336127774,train,0.9338374291115312,0.010965845631110136,0.9320413294426397,0.011286275578768304,0.9312553122893402,0.011499970075247464 +flat_mae,patch,logistic,aabc_sex,11,0.046415888336127774,test,0.9454545454545454,0.03152899229870662,0.9442755825734549,0.032007574786975454,0.9470108695652174,0.030700553569440875 +flat_mae,patch,logistic,aabc_sex,12,0.005994842503189409,train,0.9130434782608695,0.012267193030884143,0.9105104442483083,0.012636081019029539,0.9090242973123479,0.012733533028051846 +flat_mae,patch,logistic,aabc_sex,12,0.005994842503189409,test,0.8,0.05311793832502184,0.790003471017008,0.057460511757611854,0.7853260869565217,0.05701289687081716 +flat_mae,patch,logistic,aabc_sex,13,0.005994842503189409,train,0.9111531190926276,0.012374721968776417,0.9086244978812703,0.012760309009893216,0.9073903103842433,0.012962978169431663 +flat_mae,patch,logistic,aabc_sex,13,0.005994842503189409,test,0.8727272727272727,0.04311339651057065,0.8683760683760684,0.04480368712293577,0.8661684782608696,0.0450411926785977 +flat_mae,patch,logistic,aabc_sex,14,0.046415888336127774,train,0.9376181474480151,0.010432675604376428,0.9360045457044925,0.010711032638104157,0.9357396172220757,0.010881388914927171 +flat_mae,patch,logistic,aabc_sex,14,0.046415888336127774,test,0.8727272727272727,0.04261414811813924,0.8711943793911007,0.04279801355862537,0.8783967391304348,0.04166899483492409 +flat_mae,patch,logistic,aabc_sex,15,0.3593813663804626,train,0.9886578449905482,0.004793430526407108,0.9883572497579012,0.0049286734639915,0.98776341627832,0.0052381109362295295 +flat_mae,patch,logistic,aabc_sex,15,0.3593813663804626,test,0.8909090909090909,0.0409522358343804,0.8879076086956521,0.04216199251420086,0.8879076086956521,0.04225007969701995 +flat_mae,patch,logistic,aabc_sex,16,0.005994842503189409,train,0.9073724007561437,0.012415097866559604,0.9044834307992202,0.01286831530700699,0.9022978399132449,0.0131597108534291 +flat_mae,patch,logistic,aabc_sex,16,0.005994842503189409,test,0.8909090909090909,0.04235192971298029,0.8863636363636364,0.0451746648712071,0.8817934782608696,0.04628407330682398 +flat_mae,patch,logistic,aabc_sex,17,0.046415888336127774,train,0.9376181474480151,0.010319668598298212,0.9360045457044925,0.010606092985220866,0.9357396172220757,0.010799227378004298 +flat_mae,patch,logistic,aabc_sex,17,0.046415888336127774,test,0.8909090909090909,0.03974969618886964,0.884453781512605,0.044023137653841256,0.8756793478260869,0.04503130792582813 +flat_mae,patch,logistic,aabc_sex,18,0.000774263682681127,train,0.8733459357277883,0.014344089214522135,0.8686522804169863,0.015028441979259136,0.8649799232099417,0.015258121001064596 +flat_mae,patch,logistic,aabc_sex,18,0.000774263682681127,test,0.8727272727272727,0.0430640499337233,0.8720505151213027,0.04296424454498886,0.8845108695652174,0.03978355522380163 +flat_mae,patch,logistic,aabc_sex,19,0.3593813663804626,train,0.9905482041587902,0.004366392510653536,0.9903155058088658,0.004470402719222456,0.9906137342829509,0.004397311819054003 +flat_mae,patch,logistic,aabc_sex,19,0.3593813663804626,test,0.8363636363636363,0.04740204689237348,0.8343927735028438,0.047640318543602705,0.8410326086956521,0.04669813008312935 +flat_mae,patch,logistic,aabc_sex,20,0.3593813663804626,train,0.9886578449905482,0.004725860113270321,0.9883715818165831,0.004845280748309823,0.9883715818165831,0.0049081540220823165 +flat_mae,patch,logistic,aabc_sex,20,0.3593813663804626,test,0.8727272727272727,0.042816541176829155,0.8683760683760684,0.044816458135809346,0.8661684782608696,0.04537927253376938 +flat_mae,patch,logistic,aabc_sex,21,0.046415888336127774,train,0.9508506616257089,0.009095968323092736,0.9494189467490438,0.009394640851322,0.9477856912570708,0.009700637528313471 +flat_mae,patch,logistic,aabc_sex,21,0.046415888336127774,test,0.8,0.05056260010052507,0.790003471017008,0.05432362021564443,0.7853260869565217,0.05397605415812188 +flat_mae,patch,logistic,aabc_sex,22,0.005994842503189409,train,0.9035916824196597,0.012633201161689991,0.9005847953216375,0.013101143368768164,0.8984217005187725,0.013387342421443243 +flat_mae,patch,logistic,aabc_sex,22,0.005994842503189409,test,0.9636363636363636,0.026259757729900295,0.9626358695652174,0.027077372978828982,0.9626358695652174,0.027412093937197488 +flat_mae,patch,logistic,aabc_sex,23,0.3593813663804626,train,0.994328922495274,0.003212498417580026,0.9941893034853195,0.003289627878642117,0.9944898736774231,0.003183037494179563 +flat_mae,patch,logistic,aabc_sex,23,0.3593813663804626,test,0.8545454545454545,0.04861690349852736,0.8521505376344086,0.04932561927776499,0.8566576086956521,0.04879558473847078 +flat_mae,patch,logistic,aabc_sex,24,0.046415888336127774,train,0.9489603024574669,0.010192925316210008,0.9477656971705049,0.010415265481280302,0.9485843664820188,0.010361801209974666 +flat_mae,patch,logistic,aabc_sex,24,0.046415888336127774,test,0.8727272727272727,0.04537832154361486,0.8683760683760684,0.04737382673023963,0.8661684782608696,0.0477618326091286 +flat_mae,patch,logistic,aabc_sex,25,0.005994842503189409,train,0.9073724007561437,0.012322778021448214,0.9044834307992202,0.012770491081759264,0.9022978399132449,0.0130091505520135 +flat_mae,patch,logistic,aabc_sex,25,0.005994842503189409,test,0.9090909090909091,0.0358301779634509,0.9071259709557582,0.036540718182256016,0.9096467391304348,0.03613360759004897 +flat_mae,patch,logistic,aabc_sex,26,0.005994842503189409,train,0.9130434782608695,0.011836662316927801,0.9102702144606035,0.012264991898124656,0.9078079662358216,0.012493954838193707 +flat_mae,patch,logistic,aabc_sex,26,0.005994842503189409,test,0.8181818181818182,0.04847866021114616,0.8106060606060606,0.051597052806010305,0.8070652173913043,0.05156378485539002 +flat_mae,patch,logistic,aabc_sex,27,0.046415888336127774,train,0.9319470699432892,0.011216913448070437,0.9300552388787683,0.011574183369198644,0.9290131598229725,0.011898534249688045 +flat_mae,patch,logistic,aabc_sex,27,0.046415888336127774,test,0.9090909090909091,0.03829204867509099,0.9071259709557582,0.03896359943367959,0.9096467391304348,0.03825473718765804 +flat_mae,patch,logistic,aabc_sex,28,0.046415888336127774,train,0.9489603024574669,0.009517271137541578,0.9476400828491303,0.009775503447027135,0.9473680354054925,0.009974873839530858 +flat_mae,patch,logistic,aabc_sex,28,0.046415888336127774,test,0.8181818181818182,0.04909595933618665,0.8074229691876751,0.05406177796370216,0.8009510869565217,0.0536109799828851 +flat_mae,patch,logistic,aabc_sex,29,0.046415888336127774,train,0.9357277882797732,0.011293138571341805,0.9340244152947736,0.011630229667324462,0.9334974647557079,0.011941023130618185 +flat_mae,patch,logistic,aabc_sex,29,0.046415888336127774,test,0.8363636363636363,0.04990292725642783,0.8307692307692308,0.05197642751542167,0.8288043478260869,0.05218421447781265 +flat_mae,patch,logistic,aabc_sex,30,0.046415888336127774,train,0.947069943289225,0.009556235088565736,0.9455280964989703,0.009867535325936724,0.9439095518625986,0.010158436920336704 +flat_mae,patch,logistic,aabc_sex,30,0.046415888336127774,test,0.8181818181818182,0.0538679254141994,0.8151881720430108,0.054559368840229834,0.8192934782608696,0.054258014701665414 +flat_mae,patch,logistic,aabc_sex,31,0.005994842503189409,train,0.9168241965973535,0.011906055318673378,0.9145119586296058,0.012261958948926266,0.9135086022450833,0.012457770668308582 +flat_mae,patch,logistic,aabc_sex,31,0.005994842503189409,test,0.8,0.05061081451087844,0.795677136102668,0.0515024264673852,0.7975543478260869,0.05120847342094255 +flat_mae,patch,logistic,aabc_sex,32,0.005994842503189409,train,0.9017013232514177,0.013593572121631755,0.898703785535425,0.014090503070035234,0.8967877135906679,0.014399277557782007 +flat_mae,patch,logistic,aabc_sex,32,0.005994842503189409,test,0.9090909090909091,0.03865293762156843,0.905982905982906,0.04040128853507368,0.9035326086956521,0.041108932938236385 +flat_mae,patch,logistic,aabc_sex,33,0.005994842503189409,train,0.9035916824196597,0.012489422055778514,0.9004483312116013,0.012967864278991324,0.8978135349805094,0.013235714083482968 +flat_mae,patch,logistic,aabc_sex,33,0.005994842503189409,test,0.8727272727272727,0.043303869618856704,0.8683760683760684,0.04542174302633156,0.8661684782608696,0.04611253880384598 +flat_mae,patch,logistic,aabc_sex,34,0.005994842503189409,train,0.9054820415879017,0.012455673960430869,0.9025997937840624,0.012909518080748457,0.9006638529851403,0.013211659180561924 +flat_mae,patch,logistic,aabc_sex,34,0.005994842503189409,test,0.8727272727272727,0.045922233942263004,0.8683760683760684,0.04788517997172794,0.8661684782608696,0.04843819727454098 +flat_mae,patch,logistic,aabc_sex,35,0.000774263682681127,train,0.8752362948960303,0.014517389324069877,0.8710785182559376,0.015153120567872996,0.8684384067528357,0.015496198441855465 +flat_mae,patch,logistic,aabc_sex,35,0.000774263682681127,test,0.8727272727272727,0.04164066670896303,0.8639095086603039,0.047221697124500875,0.8539402173913043,0.04792605512151892 +flat_mae,patch,logistic,aabc_sex,36,0.046415888336127774,train,0.9376181474480151,0.009895447954659596,0.9358427325549344,0.010217383712115313,0.9345232861455495,0.010515395495025724 +flat_mae,patch,logistic,aabc_sex,36,0.046415888336127774,test,0.9272727272727272,0.034559537799174374,0.9252717391304348,0.03560738203564243,0.9252717391304348,0.03601125106836722 +flat_mae,patch,logistic,aabc_sex,37,0.046415888336127774,train,0.9508506616257089,0.009388259797690828,0.9495480822842386,0.009648875574712319,0.9490020223335971,0.009806596782075775 +flat_mae,patch,logistic,aabc_sex,37,0.046415888336127774,test,0.7454545454545455,0.05906013184504179,0.7348484848484849,0.06276834011903022,0.7323369565217391,0.06205603772393027 +flat_mae,patch,logistic,aabc_sex,38,0.005994842503189409,train,0.9149338374291115,0.012232371472417895,0.9125128171203651,0.012618719243570907,0.9112664497787157,0.012850757041285606 +flat_mae,patch,logistic,aabc_sex,38,0.005994842503189409,test,0.8363636363636363,0.04659650609396897,0.8250265111346766,0.05198963088297774,0.8165760869565217,0.05135661534994906 +flat_mae,patch,logistic,aabc_sex,39,0.005994842503189409,train,0.9092627599243857,0.012685909539416718,0.9066195939982348,0.0131189167604199,0.9051481579178757,0.013399126070426879 +flat_mae,patch,logistic,aabc_sex,39,0.005994842503189409,test,0.8363636363636363,0.048779822410297505,0.8328267477203647,0.049768398416467484,0.8349184782608696,0.049634241182752954 +flat_mae,patch,logistic,aabc_sex,40,0.3593813663804626,train,0.9886578449905482,0.004559646630263872,0.9883855386416862,0.004661879406807455,0.9889797473548463,0.00445449399739549 +flat_mae,patch,logistic,aabc_sex,40,0.3593813663804626,test,0.8909090909090909,0.03951271790237996,0.8863636363636364,0.04192597383083158,0.8817934782608696,0.04297229640374421 +flat_mae,patch,logistic,aabc_sex,41,0.005994842503189409,train,0.9017013232514177,0.013207104959047405,0.8985663293902475,0.013696683227927938,0.8961795480524049,0.013969751721076227 +flat_mae,patch,logistic,aabc_sex,41,0.005994842503189409,test,0.9272727272727272,0.03416641819435285,0.9252717391304348,0.03524888199023617,0.9252717391304348,0.035489316032539533 +flat_mae,patch,logistic,aabc_sex,42,0.005994842503189409,train,0.9149338374291115,0.011897200961198982,0.9122807017543859,0.012362125064861135,0.9100501187021894,0.012769341500269635 +flat_mae,patch,logistic,aabc_sex,42,0.005994842503189409,test,0.7818181818181819,0.055553961556563156,0.78,0.05575604123498008,0.7880434782608696,0.055271686943538054 +flat_mae,patch,logistic,aabc_sex,43,0.046415888336127774,train,0.9357277882797732,0.010522001997793651,0.9340244152947736,0.010810807899517024,0.9334974647557079,0.011019493621982396 +flat_mae,patch,logistic,aabc_sex,43,0.046415888336127774,test,0.9090909090909091,0.03857830504097751,0.905982905982906,0.04035654079224684,0.9035326086956521,0.04129492372734036 +flat_mae,patch,logistic,aabc_sex,44,0.3593813663804626,train,0.9905482041587902,0.004312299996633587,0.9903037190461352,0.004426217248866082,0.9900055687446877,0.0045561927838712445 +flat_mae,patch,logistic,aabc_sex,44,0.3593813663804626,test,0.8181818181818182,0.04974857778605871,0.8106060606060606,0.052994106057173446,0.8070652173913043,0.05280661215375753 +flat_mae,patch,logistic,aabc_sex,45,0.3593813663804626,train,0.9867674858223062,0.005187458311734048,0.986408265888528,0.00534355121069417,0.9855212638119524,0.005763852943140825 +flat_mae,patch,logistic,aabc_sex,45,0.3593813663804626,test,0.9636363636363636,0.02440745042735182,0.9630376344086022,0.024547986237309635,0.96875,0.02097515271100547 +flat_mae,patch,logistic,aabc_sex,46,0.046415888336127774,train,0.9357277882797732,0.010553996282242802,0.9338555457487496,0.010905388643516157,0.9322811336791816,0.011208885481518573 +flat_mae,patch,logistic,aabc_sex,46,0.046415888336127774,test,0.9272727272727272,0.034906723404567436,0.9260752688172043,0.03522824108267527,0.9313858695652174,0.033434340676321145 +flat_mae,patch,logistic,aabc_sex,47,0.005994842503189409,train,0.9054820415879017,0.011969548258511882,0.9027287437481613,0.0123696416815866,0.9012720185234033,0.01263420686774507 +flat_mae,patch,logistic,aabc_sex,47,0.005994842503189409,test,0.8545454545454545,0.04417958842110063,0.84593837535014,0.04852819167835517,0.8383152173913043,0.04881317694160748 +flat_mae,patch,logistic,aabc_sex,48,0.005994842503189409,train,0.9035916824196597,0.01298308585407634,0.9005847953216375,0.013470506227150828,0.8984217005187725,0.013814314999715619 +flat_mae,patch,logistic,aabc_sex,48,0.005994842503189409,test,0.9090909090909091,0.037959456405203075,0.905982905982906,0.03961412854866127,0.9035326086956521,0.04038021936568441 +flat_mae,patch,logistic,aabc_sex,49,0.3593813663804626,train,0.9905482041587902,0.00399979809453942,0.9903155058088658,0.004096237908834859,0.9906137342829509,0.004049504813893181 +flat_mae,patch,logistic,aabc_sex,49,0.3593813663804626,test,0.7636363636363637,0.05427777957296982,0.7585275244849713,0.05579002867496969,0.7601902173913043,0.05589765731580848 +flat_mae,patch,logistic,aabc_sex,50,0.005994842503189409,train,0.9149338374291115,0.012019547569076016,0.9121602922455305,0.012511756685525338,0.9094419531639262,0.012904415052439035 +flat_mae,patch,logistic,aabc_sex,50,0.005994842503189409,test,0.8727272727272727,0.046454228783834366,0.8699763593380614,0.04718162108323934,0.8722826086956521,0.04653830899278279 +flat_mae,patch,logistic,aabc_sex,51,0.046415888336127774,train,0.9376181474480151,0.010240050314162,0.9360045457044925,0.010525322527049703,0.9357396172220757,0.01074218565064715 +flat_mae,patch,logistic,aabc_sex,51,0.046415888336127774,test,0.8545454545454545,0.0455616918978547,0.84593837535014,0.050231793174224076,0.8383152173913043,0.05035120327983549 +flat_mae,patch,logistic,aabc_sex,52,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,52,21.54434690031882,test,0.8909090909090909,0.0425894256072293,0.89,0.04258686213604708,0.9001358695652174,0.03956235488181784 +flat_mae,patch,logistic,aabc_sex,53,0.005994842503189409,train,0.9035916824196597,0.01400543825700556,0.9008478594030804,0.014426090225403273,0.8996380315952988,0.014532478686941729 +flat_mae,patch,logistic,aabc_sex,53,0.005994842503189409,test,0.8909090909090909,0.04093083866376314,0.8863636363636364,0.04342861173201066,0.8817934782608696,0.04433725770130579 +flat_mae,patch,logistic,aabc_sex,54,0.046415888336127774,train,0.943289224952741,0.009794962018388713,0.9417862487895061,0.010076026695290083,0.9412497435446525,0.01031773345657231 +flat_mae,patch,logistic,aabc_sex,54,0.046415888336127774,test,0.8545454545454545,0.04825840910749933,0.8533333333333333,0.048308465850341015,0.8627717391304348,0.04604639753169467 +flat_mae,patch,logistic,aabc_sex,55,0.3593813663804626,train,0.9886578449905482,0.004663782335202663,0.9883855386416862,0.004769900007566217,0.9889797473548463,0.004604706751639365 +flat_mae,patch,logistic,aabc_sex,55,0.3593813663804626,test,0.8545454545454545,0.0470537445484741,0.8533333333333333,0.04706467595969562,0.8627717391304348,0.045215097038727316 +flat_mae,patch,logistic,aabc_sex,56,0.005994842503189409,train,0.9111531190926276,0.012623258029226439,0.9083820662768032,0.013100379170969597,0.906173979307717,0.013449988393612443 +flat_mae,patch,logistic,aabc_sex,56,0.005994842503189409,test,0.8545454545454545,0.04632761524063477,0.8484848484848485,0.04905817950146303,0.8444293478260869,0.04938723308278298 +flat_mae,patch,logistic,aabc_sex,57,0.005994842503189409,train,0.9092627599243857,0.012411342247143445,0.9066195939982348,0.012825893124072934,0.9051481579178757,0.01307004704641569 +flat_mae,patch,logistic,aabc_sex,57,0.005994842503189409,test,0.8727272727272727,0.04480925229134146,0.8683760683760684,0.046790184117893,0.8661684782608696,0.04726722659822225 +flat_mae,patch,logistic,aabc_sex,58,0.046415888336127774,train,0.9489603024574669,0.009291282808144709,0.9476400828491303,0.009544015260950868,0.9473680354054925,0.009721337319549758 +flat_mae,patch,logistic,aabc_sex,58,0.046415888336127774,test,0.7636363636363637,0.05635189320483026,0.7607895617263298,0.05671739718438392,0.7663043478260869,0.05643110238812051 +flat_mae,patch,logistic,aabc_sex,59,0.046415888336127774,train,0.941398865784499,0.010334727560236156,0.9397310517940294,0.010674309139875895,0.9383994255400216,0.010974575971043971 +flat_mae,patch,logistic,aabc_sex,59,0.046415888336127774,test,0.9272727272727272,0.033619435543759395,0.9252717391304348,0.034638595839659024,0.9252717391304348,0.03489629992152492 +flat_mae,patch,logistic,aabc_sex,60,0.046415888336127774,train,0.947069943289225,0.009177786235149579,0.9457991803278689,0.0094018271545545,0.9463422140156511,0.009499787907756258 +flat_mae,patch,logistic,aabc_sex,60,0.046415888336127774,test,0.8545454545454545,0.04779984439270635,0.8484848484848485,0.05073800049883608,0.8444293478260869,0.05115539203447407 +flat_mae,patch,logistic,aabc_sex,61,0.005994842503189409,train,0.9035916824196597,0.013135085559723668,0.9008478594030804,0.013561368245461886,0.8996380315952988,0.013806791219534183 +flat_mae,patch,logistic,aabc_sex,61,0.005994842503189409,test,0.9272727272727272,0.032823515053934556,0.9260752688172043,0.03316966016285463,0.9313858695652174,0.03158574847045793 +flat_mae,patch,logistic,aabc_sex,62,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,62,2.782559402207126,test,0.8727272727272727,0.045108075911046056,0.8683760683760684,0.04706592411856217,0.8661684782608696,0.0474099885728901 +flat_mae,patch,logistic,aabc_sex,63,0.005994842503189409,train,0.9054820415879017,0.012895839047051971,0.9025997937840624,0.013371492006431488,0.9006638529851403,0.013669269018025131 +flat_mae,patch,logistic,aabc_sex,63,0.005994842503189409,test,0.9090909090909091,0.037622061401951803,0.9045470322804582,0.040951887774074026,0.8974184782608696,0.04270890941832561 +flat_mae,patch,logistic,aabc_sex,64,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,64,21.54434690031882,test,0.8363636363636363,0.04860696137607116,0.8354935194416749,0.04851662531448197,0.8471467391304348,0.04662987694998631 +flat_mae,patch,logistic,aabc_sex,65,0.005994842503189409,train,0.9054820415879017,0.012610950844534072,0.9027287437481613,0.013042359476862834,0.9012720185234033,0.013299200495215548 +flat_mae,patch,logistic,aabc_sex,65,0.005994842503189409,test,0.8909090909090909,0.04264651555820473,0.8863636363636364,0.04525859058188483,0.8817934782608696,0.04609796839176517 +flat_mae,patch,logistic,aabc_sex,66,0.005994842503189409,train,0.9092627599243857,0.01205118425355311,0.9067403185050245,0.012399512961149365,0.9057563234561388,0.012537681243171405 +flat_mae,patch,logistic,aabc_sex,66,0.005994842503189409,test,0.8545454545454545,0.04598634364300874,0.8484848484848485,0.04866559315095088,0.8444293478260869,0.049021139820730475 +flat_mae,patch,logistic,aabc_sex,67,0.005994842503189409,train,0.9035916824196597,0.01252753443418607,0.9007179630604141,0.012990318460424167,0.8990298660570357,0.013322903657002267 +flat_mae,patch,logistic,aabc_sex,67,0.005994842503189409,test,0.9090909090909091,0.03833111935156345,0.905982905982906,0.04004672554671995,0.9035326086956521,0.0408511969041459 +flat_mae,patch,logistic,aabc_sex,68,0.046415888336127774,train,0.9357277882797732,0.010710582206200846,0.9338555457487496,0.011088807567305518,0.9322811336791816,0.011525142233825182 +flat_mae,patch,logistic,aabc_sex,68,0.046415888336127774,test,0.9272727272727272,0.03375211533009745,0.9229691876750701,0.037653732350501234,0.9130434782608696,0.040355790068594764 +flat_mae,patch,logistic,aabc_sex,69,0.046415888336127774,train,0.9376181474480151,0.010315373877161955,0.9359246820459175,0.01061150770679583,0.9351314516838125,0.0108179598774479 +flat_mae,patch,logistic,aabc_sex,69,0.046415888336127774,test,0.9818181818181818,0.018009180395353836,0.9811965811965813,0.0189197194632661,0.9782608695652174,0.021532715690096974 +flat_mae,patch,logistic,aabc_sex,70,0.3593813663804626,train,0.9886578449905482,0.004877816806138891,0.9883715818165831,0.00500233752822005,0.9883715818165831,0.0050804712739559174 +flat_mae,patch,logistic,aabc_sex,70,0.3593813663804626,test,0.9090909090909091,0.03965969288420451,0.9071259709557582,0.04042451554323483,0.9096467391304348,0.040007658082936964 +flat_mae,patch,logistic,aabc_sex,71,0.005994842503189409,train,0.9054820415879017,0.012525845079902303,0.9025997937840624,0.012924018454321194,0.9006638529851403,0.013054615200974463 +flat_mae,patch,logistic,aabc_sex,71,0.005994842503189409,test,0.8363636363636363,0.04600267329637725,0.8281846581048247,0.049665836522629875,0.8226902173913043,0.04934354741300053 +flat_mae,patch,logistic,aabc_sex,72,0.000774263682681127,train,0.8771266540642723,0.013724440306258323,0.8731204221324329,0.01433559870570277,0.8706805592192033,0.0147105064792701 +flat_mae,patch,logistic,aabc_sex,72,0.000774263682681127,test,0.8909090909090909,0.04253650255470913,0.8879076086956521,0.043836471921655844,0.8879076086956521,0.04410724994265836 +flat_mae,patch,logistic,aabc_sex,73,0.005994842503189409,train,0.9017013232514177,0.012618705197842825,0.898703785535425,0.013095947436588857,0.8967877135906679,0.013452849642075429 +flat_mae,patch,logistic,aabc_sex,73,0.005994842503189409,test,0.9272727272727272,0.034051667111286224,0.9242424242424243,0.03636431691754075,0.9191576086956521,0.03843751899483909 +flat_mae,patch,logistic,aabc_sex,74,0.005994842503189409,train,0.9092627599243857,0.012009524845072188,0.9064958020327,0.012457042884354983,0.9045399923796125,0.012787648099218327 +flat_mae,patch,logistic,aabc_sex,74,0.005994842503189409,test,0.9090909090909091,0.03945050670572994,0.905982905982906,0.04122527157904843,0.9035326086956521,0.04222734334658748 +flat_mae,patch,logistic,aabc_sex,75,0.046415888336127774,train,0.9300567107750473,0.011521587001264412,0.9281579768393621,0.011859169171080396,0.9273791728948679,0.012046740634823819 +flat_mae,patch,logistic,aabc_sex,75,0.046415888336127774,test,0.8545454545454545,0.043384119423837755,0.8505434782608696,0.04484254186318451,0.8505434782608696,0.04501957589196547 +flat_mae,patch,logistic,aabc_sex,76,0.046415888336127774,train,0.943289224952741,0.009921846826226176,0.9416372462488967,0.010267548906270465,0.9400334124681262,0.01070035889925167 +flat_mae,patch,logistic,aabc_sex,76,0.046415888336127774,test,0.8363636363636363,0.051283248436969464,0.8307692307692308,0.0534819904143214,0.8288043478260869,0.05346743432462892 +flat_mae,patch,logistic,aabc_sex,77,0.005994842503189409,train,0.9017013232514177,0.012874164787738672,0.8989686783804431,0.013254666970165755,0.8980040446671942,0.013463125447774693 +flat_mae,patch,logistic,aabc_sex,77,0.005994842503189409,test,0.8909090909090909,0.04053761032966385,0.884453781512605,0.04474255292926192,0.8756793478260869,0.046099985881089475 +flat_mae,patch,logistic,aabc_sex,78,0.3593813663804626,train,0.9867674858223062,0.004936182076212068,0.9864417081324122,0.005054408663729286,0.9867375948884786,0.005018870023714706 +flat_mae,patch,logistic,aabc_sex,78,0.3593813663804626,test,0.9636363636363636,0.02490248087478452,0.9626358695652174,0.025618440554011246,0.9626358695652174,0.02594622005779819 +flat_mae,patch,logistic,aabc_sex,79,0.005994842503189409,train,0.9017013232514177,0.012907376830419513,0.8989686783804431,0.013302332497607611,0.8980040446671942,0.013488169503627637 +flat_mae,patch,logistic,aabc_sex,79,0.005994842503189409,test,0.8545454545454545,0.0437509253739207,0.8428571428571429,0.05061221757674831,0.8322010869565217,0.050248001354363386 +flat_mae,patch,logistic,aabc_sex,80,0.046415888336127774,train,0.947069943289225,0.009890437210285043,0.9455280964989703,0.010238868323145835,0.9439095518625986,0.010651868524322186 +flat_mae,patch,logistic,aabc_sex,80,0.046415888336127774,test,0.8545454545454545,0.04809427381252073,0.8484848484848485,0.050906977356067494,0.8444293478260869,0.05130358950926657 +flat_mae,patch,logistic,aabc_sex,81,0.005994842503189409,train,0.8998109640831758,0.012851815032292168,0.8966861598440545,0.013277485640967679,0.8945455611243003,0.013430910594478651 +flat_mae,patch,logistic,aabc_sex,81,0.005994842503189409,test,0.9636363636363636,0.02580975534704621,0.9626358695652174,0.026566929023660795,0.9626358695652174,0.02698644775990158 +flat_mae,patch,logistic,aabc_sex,82,0.046415888336127774,train,0.9376181474480151,0.010778694703186667,0.9360823383385143,0.011038168099739624,0.9363477827603388,0.011087481091302668 +flat_mae,patch,logistic,aabc_sex,82,0.046415888336127774,test,0.9090909090909091,0.03585380784784349,0.9045470322804582,0.0386490359895269,0.8974184782608696,0.040520596997251974 +flat_mae,patch,logistic,aabc_sex,83,0.046415888336127774,train,0.9357277882797732,0.010279886480491586,0.9340244152947736,0.010569569986187624,0.9334974647557079,0.010743668090463034 +flat_mae,patch,logistic,aabc_sex,83,0.046415888336127774,test,0.8727272727272727,0.043031197600603074,0.8639095086603039,0.04880436308396927,0.8539402173913043,0.049118542708594726 +flat_mae,patch,logistic,aabc_sex,84,0.046415888336127774,train,0.9395085066162571,0.010857051397732822,0.9379817696884434,0.011130211258898317,0.9379817696884434,0.01119322745500554 +flat_mae,patch,logistic,aabc_sex,84,0.046415888336127774,test,0.7818181818181819,0.059201731044604466,0.7782258064516129,0.05988975594692057,0.7819293478260869,0.0598342398554756 +flat_mae,patch,logistic,aabc_sex,85,0.005994842503189409,train,0.9111531190926276,0.012815365936340571,0.9083820662768032,0.013314261271511332,0.906173979307717,0.013717766605594787 +flat_mae,patch,logistic,aabc_sex,85,0.005994842503189409,test,0.8909090909090909,0.041805152120302745,0.8879076086956521,0.043122878357793486,0.8879076086956521,0.043286929107459564 +flat_mae,patch,logistic,aabc_sex,86,0.046415888336127774,train,0.943289224952741,0.010488612148860823,0.9418579090829157,0.010742929556331385,0.9418579090829157,0.010780787400464611 +flat_mae,patch,logistic,aabc_sex,86,0.046415888336127774,test,0.9090909090909091,0.03964155095330494,0.905982905982906,0.0414572076291978,0.9035326086956521,0.04245339620666587 +flat_mae,patch,logistic,aabc_sex,87,0.046415888336127774,train,0.943289224952741,0.010317582418343409,0.9417862487895061,0.010596991148074535,0.9412497435446525,0.010741749617599574 +flat_mae,patch,logistic,aabc_sex,87,0.046415888336127774,test,0.9272727272727272,0.03397585919832586,0.9242424242424243,0.03616813579667084,0.9191576086956521,0.037972201182934096 +flat_mae,patch,logistic,aabc_sex,88,0.046415888336127774,train,0.943289224952741,0.009863501424261617,0.9418579090829157,0.010116078315687744,0.9418579090829157,0.010238084279186956 +flat_mae,patch,logistic,aabc_sex,88,0.046415888336127774,test,0.8545454545454545,0.0489584205438529,0.8505434782608696,0.05054704921229563,0.8505434782608696,0.05111774078274165 +flat_mae,patch,logistic,aabc_sex,89,0.005994842503189409,train,0.9092627599243857,0.012656148183478698,0.9067403185050245,0.013041281524857333,0.9057563234561388,0.013241922971790991 +flat_mae,patch,logistic,aabc_sex,89,0.005994842503189409,test,0.8909090909090909,0.036863097182470946,0.8821428571428571,0.04291354249608569,0.8695652173913043,0.04407544228338917 +flat_mae,patch,logistic,aabc_sex,90,0.3593813663804626,train,0.994328922495274,0.0032437153238263237,0.9941893034853195,0.0033212584574063768,0.9944898736774231,0.003215557947438436 +flat_mae,patch,logistic,aabc_sex,90,0.3593813663804626,test,0.7636363636363637,0.055809107938808875,0.7472605160834218,0.0629651604974415,0.7418478260869565,0.06063384062126817 +flat_mae,patch,logistic,aabc_sex,91,0.3593813663804626,train,0.9886578449905482,0.004564903886193219,0.9883715818165831,0.004679102528491746,0.9883715818165831,0.004727032035010211 +flat_mae,patch,logistic,aabc_sex,91,0.3593813663804626,test,0.8727272727272727,0.045084149053384245,0.8699763593380614,0.045880929692043694,0.8722826086956521,0.045412745510578875 +flat_mae,patch,logistic,aabc_sex,92,0.005994842503189409,train,0.9017013232514177,0.013482762513233748,0.8985663293902475,0.014027218454788102,0.8961795480524049,0.014386638927197038 +flat_mae,patch,logistic,aabc_sex,92,0.005994842503189409,test,0.8909090909090909,0.04115893002327875,0.8863636363636364,0.04375570414815548,0.8817934782608696,0.04481920836148059 +flat_mae,patch,logistic,aabc_sex,93,0.046415888336127774,train,0.941398865784499,0.010569671429327824,0.9397310517940294,0.010904788518918709,0.9383994255400216,0.011167248781458595 +flat_mae,patch,logistic,aabc_sex,93,0.046415888336127774,test,0.8727272727272727,0.0464672496416153,0.8663658451926415,0.0501099178385526,0.8600543478260869,0.05091722372875617 +flat_mae,patch,logistic,aabc_sex,94,0.005994842503189409,train,0.8998109640831758,0.012819065631001773,0.8966861598440545,0.013321457088497326,0.8945455611243003,0.013664660020044815 +flat_mae,patch,logistic,aabc_sex,94,0.005994842503189409,test,0.9636363636363636,0.02508827390641505,0.9626358695652174,0.02577476780701878,0.9626358695652174,0.025961225078379828 +flat_mae,patch,logistic,aabc_sex,95,0.046415888336127774,train,0.9376181474480151,0.010326265133231975,0.9359246820459175,0.010634041648624757,0.9351314516838125,0.010872550765457586 +flat_mae,patch,logistic,aabc_sex,95,0.046415888336127774,test,0.9090909090909091,0.03858618773988331,0.9071259709557582,0.039310523325167386,0.9096467391304348,0.03882445226517596 +flat_mae,patch,logistic,aabc_sex,96,0.005994842503189409,train,0.9054820415879017,0.012704066494008353,0.9025997937840624,0.013163988936806661,0.9006638529851403,0.013421258455651267 +flat_mae,patch,logistic,aabc_sex,96,0.005994842503189409,test,0.9090909090909091,0.03917496248818132,0.905982905982906,0.04082068657018065,0.9035326086956521,0.0415421272530122 +flat_mae,patch,logistic,aabc_sex,97,0.3593813663804626,train,0.9886578449905482,0.004954039570601042,0.9883572497579012,0.005092196100838554,0.98776341627832,0.005356499725167467 +flat_mae,patch,logistic,aabc_sex,97,0.3593813663804626,test,0.8727272727272727,0.04110556456267848,0.8683760683760684,0.043015714015057105,0.8661684782608696,0.04361811091395039 +flat_mae,patch,logistic,aabc_sex,98,0.005994842503189409,train,0.9092627599243857,0.012128772466495514,0.9066195939982348,0.012540248273860665,0.9051481579178757,0.012794018265289154 +flat_mae,patch,logistic,aabc_sex,98,0.005994842503189409,test,0.8181818181818182,0.04960805053301276,0.8074229691876751,0.05446396162114083,0.8009510869565217,0.0542416097934673 +flat_mae,patch,logistic,aabc_sex,99,0.046415888336127774,train,0.943289224952741,0.01037736593782101,0.9417126990656403,0.010689168625961493,0.9406415780063895,0.010924313222199543 +flat_mae,patch,logistic,aabc_sex,99,0.046415888336127774,test,0.8545454545454545,0.04808228484278256,0.8484848484848485,0.05143844365681967,0.8444293478260869,0.05201993285146099 +flat_mae,patch,logistic,aabc_sex,100,0.046415888336127774,train,0.943289224952741,0.010503226804510364,0.9417126990656403,0.010825374461274266,0.9406415780063895,0.011098900569378239 +flat_mae,patch,logistic,aabc_sex,100,0.046415888336127774,test,0.8909090909090909,0.040482641928617516,0.89,0.04040146520253775,0.9001358695652174,0.03739940062099162 diff --git a/input_space_v3/flat_lr1e-3_6/eval_v2/aabc_sex__patch__logistic/log.txt b/input_space_v3/flat_lr1e-3_6/eval_v2/aabc_sex__patch__logistic/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..a3a2d1d4d9fd9f0ce5f0efd35182ffa4d66c2156 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_6/eval_v2/aabc_sex__patch__logistic/log.txt @@ -0,0 +1,245 @@ +fMRI foundation model logistic probe eval +version: 0.1.dev86+gf97f52698 +sha: bcce2b486277d3a5b520775efd9cdf1a2affce36, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-04-08 22:54:18 +config: +output_root: experiments/input_space_v3/output +name_prefix: eval_logistic +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_6; eval v2 (aabc_sex patch logistic) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: input_space_v3/flat_lr1e-3_6/eval_v2/aabc_sex__patch__logistic +model: flat_mae +representation: patch +dataset: aabc_sex +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/eval_v2/aabc_sex__patch__logistic +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=True, reg_tokens=0, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: aabc_sex (flat) +train (n=471): +HFDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'segment', 'bold', 'mean', 'std'], + num_rows: 471 +}), + labels=[0 1], + counts=[269 202] +) + +validation (n=58): +HFDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'segment', 'bold', 'mean', 'std'], + num_rows: 58 +}), + labels=[0 1], + counts=[36 22] +) + +test (n=55): +HFDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'segment', 'bold', 'mean', 'std'], + num_rows: 55 +}), + labels=[0 1], + counts=[33 22] +) + +extracting features for all splits +extract (train) [ 0/236] eta: 0:23:57 time: 6.0924 data: 5.1649 max mem: 3205 +extract (train) [ 20/236] eta: 0:01:53 time: 0.2475 data: 0.0930 max mem: 3393 +extract (train) [ 40/236] eta: 0:01:13 time: 0.2211 data: 0.0756 max mem: 3393 +extract (train) [ 60/236] eta: 0:00:56 time: 0.2145 data: 0.0721 max mem: 3393 +extract (train) [ 80/236] eta: 0:00:46 time: 0.2303 data: 0.0816 max mem: 3393 +extract (train) [100/236] eta: 0:00:37 time: 0.1916 data: 0.0608 max mem: 3393 +extract (train) [120/236] eta: 0:00:31 time: 0.2100 data: 0.0716 max mem: 3393 +extract (train) [140/236] eta: 0:00:25 time: 0.2191 data: 0.0749 max mem: 3393 +extract (train) [160/236] eta: 0:00:19 time: 0.2289 data: 0.0798 max mem: 3393 +extract (train) [180/236] eta: 0:00:13 time: 0.1879 data: 0.0579 max mem: 3393 +extract (train) [200/236] eta: 0:00:08 time: 0.2250 data: 0.0818 max mem: 3393 +extract (train) [220/236] eta: 0:00:03 time: 0.1900 data: 0.0607 max mem: 3393 +extract (train) [235/236] eta: 0:00:00 time: 0.1802 data: 0.0567 max mem: 3393 +extract (train) Total time: 0:00:56 (0.2406 s / it) +extract (validation) [ 0/29] eta: 0:02:31 time: 5.2282 data: 5.0707 max mem: 3393 +extract (validation) [20/29] eta: 0:00:03 time: 0.1972 data: 0.0620 max mem: 3393 +extract (validation) [28/29] eta: 0:00:00 time: 0.1783 data: 0.0528 max mem: 3393 +extract (validation) Total time: 0:00:11 (0.3832 s / it) +extract (test) [ 0/28] eta: 0:02:19 time: 4.9908 data: 4.8393 max mem: 3393 +extract (test) [20/28] eta: 0:00:03 time: 0.1997 data: 0.0644 max mem: 3393 +extract (test) [27/28] eta: 0:00:00 time: 0.1717 data: 0.0515 max mem: 3393 +extract (test) Total time: 0:00:10 (0.3770 s / it) +feature extraction time: 0:01:18 +train features: (471, 768) +validation features: (58, 768) +test features: (55, 768) +evaluating fixed splits +eval results (fixed splits): + +| model | repr | clf | dataset | trial | C | split | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|----------:|:--------|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | aabc_sex | | 0.0059948 | train | 0.90359 | 0.013052 | 0.90072 | 0.013507 | 0.89861 | 0.013782 | +| flat_mae | patch | logistic | aabc_sex | | 0.0059948 | test | 0.90909 | 0.039 | 0.90598 | 0.040334 | 0.90909 | 0.04007 | + + +evaluating random splits (n=100) +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 1, "C": 2.782559402207126, "split": "test", "acc": 0.7272727272727273, "acc_std": 0.060481637128570416, "f1": 0.717948717948718, "f1_std": 0.06255583965749219, "bacc": 0.7167119565217391, "bacc_std": 0.062243918668036316} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 2, "C": 0.3593813663804626, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.040611442429423106, "f1": 0.9071259709557582, "f1_std": 0.04134577365904692, "bacc": 0.9096467391304348, "bacc_std": 0.04072304096085218} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 3, "C": 0.046415888336127774, "split": "test", "acc": 0.8, "acc_std": 0.05435476972387552, "f1": 0.7931623931623932, "f1_std": 0.056619840118301394, "bacc": 0.7914402173913043, "bacc_std": 0.056569751161206355} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 4, "C": 0.3593813663804626, "split": "test", "acc": 0.8181818181818182, "acc_std": 0.05363451460603322, "f1": 0.8151881720430108, "f1_std": 0.054054196054455966, "bacc": 0.8192934782608696, "bacc_std": 0.05329102495580865} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 5, "C": 0.005994842503189409, "split": "test", "acc": 0.8181818181818182, "acc_std": 0.051549222244856266, "f1": 0.8106060606060606, "f1_std": 0.05471023624922614, "bacc": 0.8070652173913043, "bacc_std": 0.05459919211959854} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 6, "C": 0.3593813663804626, "split": "test", "acc": 0.9272727272727272, "acc_std": 0.03665158718221091, "f1": 0.9252717391304348, "f1_std": 0.037676477828171816, "bacc": 0.9252717391304348, "bacc_std": 0.03793582409885245} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 7, "C": 0.3593813663804626, "split": "test", "acc": 0.8181818181818182, "acc_std": 0.050861484234265064, "f1": 0.8166666666666667, "f1_std": 0.05092691006868968, "bacc": 0.8254076086956521, "bacc_std": 0.04974360775303029} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 8, "C": 0.046415888336127774, "split": "test", "acc": 0.8181818181818182, "acc_std": 0.04946304739753948, "f1": 0.8166666666666667, "f1_std": 0.04954797759546828, "bacc": 0.8254076086956521, "bacc_std": 0.048523674487442034} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 9, "C": 0.3593813663804626, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.040138915804783154, "f1": 0.8891129032258065, "f1_std": 0.04056988176541941, "bacc": 0.8940217391304348, "bacc_std": 0.039765424073392806} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 10, "C": 0.046415888336127774, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.04861338114600011, "f1": 0.8533333333333333, "f1_std": 0.04858860131088121, "bacc": 0.8627717391304348, "bacc_std": 0.046422910791813654} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 11, "C": 0.046415888336127774, "split": "test", "acc": 0.9454545454545454, "acc_std": 0.03152899229870662, "f1": 0.9442755825734549, "f1_std": 0.032007574786975454, "bacc": 0.9470108695652174, "bacc_std": 0.030700553569440875} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 12, "C": 0.005994842503189409, "split": "test", "acc": 0.8, "acc_std": 0.05311793832502184, "f1": 0.790003471017008, "f1_std": 0.057460511757611854, "bacc": 0.7853260869565217, "bacc_std": 0.05701289687081716} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 13, "C": 0.005994842503189409, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.04311339651057065, "f1": 0.8683760683760684, "f1_std": 0.04480368712293577, "bacc": 0.8661684782608696, "bacc_std": 0.0450411926785977} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 14, "C": 0.046415888336127774, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.04261414811813924, "f1": 0.8711943793911007, "f1_std": 0.04279801355862537, "bacc": 0.8783967391304348, "bacc_std": 0.04166899483492409} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 15, "C": 0.3593813663804626, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.0409522358343804, "f1": 0.8879076086956521, "f1_std": 0.04216199251420086, "bacc": 0.8879076086956521, "bacc_std": 0.04225007969701995} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 16, "C": 0.005994842503189409, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.04235192971298029, "f1": 0.8863636363636364, "f1_std": 0.0451746648712071, "bacc": 0.8817934782608696, "bacc_std": 0.04628407330682398} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 17, "C": 0.046415888336127774, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.03974969618886964, "f1": 0.884453781512605, "f1_std": 0.044023137653841256, "bacc": 0.8756793478260869, "bacc_std": 0.04503130792582813} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 18, "C": 0.000774263682681127, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.0430640499337233, "f1": 0.8720505151213027, "f1_std": 0.04296424454498886, "bacc": 0.8845108695652174, "bacc_std": 0.03978355522380163} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 19, "C": 0.3593813663804626, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.04740204689237348, "f1": 0.8343927735028438, "f1_std": 0.047640318543602705, "bacc": 0.8410326086956521, "bacc_std": 0.04669813008312935} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 20, "C": 0.3593813663804626, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.042816541176829155, "f1": 0.8683760683760684, "f1_std": 0.044816458135809346, "bacc": 0.8661684782608696, "bacc_std": 0.04537927253376938} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 21, "C": 0.046415888336127774, "split": "test", "acc": 0.8, "acc_std": 0.05056260010052507, "f1": 0.790003471017008, "f1_std": 0.05432362021564443, "bacc": 0.7853260869565217, "bacc_std": 0.05397605415812188} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 22, "C": 0.005994842503189409, "split": "test", "acc": 0.9636363636363636, "acc_std": 0.026259757729900295, "f1": 0.9626358695652174, "f1_std": 0.027077372978828982, "bacc": 0.9626358695652174, "bacc_std": 0.027412093937197488} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 23, "C": 0.3593813663804626, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.04861690349852736, "f1": 0.8521505376344086, "f1_std": 0.04932561927776499, "bacc": 0.8566576086956521, "bacc_std": 0.04879558473847078} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 24, "C": 0.046415888336127774, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.04537832154361486, "f1": 0.8683760683760684, "f1_std": 0.04737382673023963, "bacc": 0.8661684782608696, "bacc_std": 0.0477618326091286} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 25, "C": 0.005994842503189409, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.0358301779634509, "f1": 0.9071259709557582, "f1_std": 0.036540718182256016, "bacc": 0.9096467391304348, "bacc_std": 0.03613360759004897} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 26, "C": 0.005994842503189409, "split": "test", "acc": 0.8181818181818182, "acc_std": 0.04847866021114616, "f1": 0.8106060606060606, "f1_std": 0.051597052806010305, "bacc": 0.8070652173913043, "bacc_std": 0.05156378485539002} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 27, "C": 0.046415888336127774, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.03829204867509099, "f1": 0.9071259709557582, "f1_std": 0.03896359943367959, "bacc": 0.9096467391304348, "bacc_std": 0.03825473718765804} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 28, "C": 0.046415888336127774, "split": "test", "acc": 0.8181818181818182, "acc_std": 0.04909595933618665, "f1": 0.8074229691876751, "f1_std": 0.05406177796370216, "bacc": 0.8009510869565217, "bacc_std": 0.0536109799828851} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 29, "C": 0.046415888336127774, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.04990292725642783, "f1": 0.8307692307692308, "f1_std": 0.05197642751542167, "bacc": 0.8288043478260869, "bacc_std": 0.05218421447781265} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 30, "C": 0.046415888336127774, "split": "test", "acc": 0.8181818181818182, "acc_std": 0.0538679254141994, "f1": 0.8151881720430108, "f1_std": 0.054559368840229834, "bacc": 0.8192934782608696, "bacc_std": 0.054258014701665414} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 31, "C": 0.005994842503189409, "split": "test", "acc": 0.8, "acc_std": 0.05061081451087844, "f1": 0.795677136102668, "f1_std": 0.0515024264673852, "bacc": 0.7975543478260869, "bacc_std": 0.05120847342094255} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 32, "C": 0.005994842503189409, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.03865293762156843, "f1": 0.905982905982906, "f1_std": 0.04040128853507368, "bacc": 0.9035326086956521, "bacc_std": 0.041108932938236385} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 33, "C": 0.005994842503189409, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.043303869618856704, "f1": 0.8683760683760684, "f1_std": 0.04542174302633156, "bacc": 0.8661684782608696, "bacc_std": 0.04611253880384598} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 34, "C": 0.005994842503189409, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.045922233942263004, "f1": 0.8683760683760684, "f1_std": 0.04788517997172794, "bacc": 0.8661684782608696, "bacc_std": 0.04843819727454098} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 35, "C": 0.000774263682681127, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.04164066670896303, "f1": 0.8639095086603039, "f1_std": 0.047221697124500875, "bacc": 0.8539402173913043, "bacc_std": 0.04792605512151892} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 36, "C": 0.046415888336127774, "split": "test", "acc": 0.9272727272727272, "acc_std": 0.034559537799174374, "f1": 0.9252717391304348, "f1_std": 0.03560738203564243, "bacc": 0.9252717391304348, "bacc_std": 0.03601125106836722} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 37, "C": 0.046415888336127774, "split": "test", "acc": 0.7454545454545455, "acc_std": 0.05906013184504179, "f1": 0.7348484848484849, "f1_std": 0.06276834011903022, "bacc": 0.7323369565217391, "bacc_std": 0.06205603772393027} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 38, "C": 0.005994842503189409, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.04659650609396897, "f1": 0.8250265111346766, "f1_std": 0.05198963088297774, "bacc": 0.8165760869565217, "bacc_std": 0.05135661534994906} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 39, "C": 0.005994842503189409, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.048779822410297505, "f1": 0.8328267477203647, "f1_std": 0.049768398416467484, "bacc": 0.8349184782608696, "bacc_std": 0.049634241182752954} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 40, "C": 0.3593813663804626, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.03951271790237996, "f1": 0.8863636363636364, "f1_std": 0.04192597383083158, "bacc": 0.8817934782608696, "bacc_std": 0.04297229640374421} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 41, "C": 0.005994842503189409, "split": "test", "acc": 0.9272727272727272, "acc_std": 0.03416641819435285, "f1": 0.9252717391304348, "f1_std": 0.03524888199023617, "bacc": 0.9252717391304348, "bacc_std": 0.035489316032539533} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 42, "C": 0.005994842503189409, "split": "test", "acc": 0.7818181818181819, "acc_std": 0.055553961556563156, "f1": 0.78, "f1_std": 0.05575604123498008, "bacc": 0.7880434782608696, "bacc_std": 0.055271686943538054} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 43, "C": 0.046415888336127774, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.03857830504097751, "f1": 0.905982905982906, "f1_std": 0.04035654079224684, "bacc": 0.9035326086956521, "bacc_std": 0.04129492372734036} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 44, "C": 0.3593813663804626, "split": "test", "acc": 0.8181818181818182, "acc_std": 0.04974857778605871, "f1": 0.8106060606060606, "f1_std": 0.052994106057173446, "bacc": 0.8070652173913043, "bacc_std": 0.05280661215375753} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 45, "C": 0.3593813663804626, "split": "test", "acc": 0.9636363636363636, "acc_std": 0.02440745042735182, "f1": 0.9630376344086022, "f1_std": 0.024547986237309635, "bacc": 0.96875, "bacc_std": 0.02097515271100547} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 46, "C": 0.046415888336127774, "split": "test", "acc": 0.9272727272727272, "acc_std": 0.034906723404567436, "f1": 0.9260752688172043, "f1_std": 0.03522824108267527, "bacc": 0.9313858695652174, "bacc_std": 0.033434340676321145} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 47, "C": 0.005994842503189409, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.04417958842110063, "f1": 0.84593837535014, "f1_std": 0.04852819167835517, "bacc": 0.8383152173913043, "bacc_std": 0.04881317694160748} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 48, "C": 0.005994842503189409, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.037959456405203075, "f1": 0.905982905982906, "f1_std": 0.03961412854866127, "bacc": 0.9035326086956521, "bacc_std": 0.04038021936568441} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 49, "C": 0.3593813663804626, "split": "test", "acc": 0.7636363636363637, "acc_std": 0.05427777957296982, "f1": 0.7585275244849713, "f1_std": 0.05579002867496969, "bacc": 0.7601902173913043, "bacc_std": 0.05589765731580848} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 50, "C": 0.005994842503189409, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.046454228783834366, "f1": 0.8699763593380614, "f1_std": 0.04718162108323934, "bacc": 0.8722826086956521, "bacc_std": 0.04653830899278279} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 51, "C": 0.046415888336127774, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.0455616918978547, "f1": 0.84593837535014, "f1_std": 0.050231793174224076, "bacc": 0.8383152173913043, "bacc_std": 0.05035120327983549} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 52, "C": 21.54434690031882, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.0425894256072293, "f1": 0.89, "f1_std": 0.04258686213604708, "bacc": 0.9001358695652174, "bacc_std": 0.03956235488181784} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 53, "C": 0.005994842503189409, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.04093083866376314, "f1": 0.8863636363636364, "f1_std": 0.04342861173201066, "bacc": 0.8817934782608696, "bacc_std": 0.04433725770130579} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 54, "C": 0.046415888336127774, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.04825840910749933, "f1": 0.8533333333333333, "f1_std": 0.048308465850341015, "bacc": 0.8627717391304348, "bacc_std": 0.04604639753169467} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 55, "C": 0.3593813663804626, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.0470537445484741, "f1": 0.8533333333333333, "f1_std": 0.04706467595969562, "bacc": 0.8627717391304348, "bacc_std": 0.045215097038727316} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 56, "C": 0.005994842503189409, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.04632761524063477, "f1": 0.8484848484848485, "f1_std": 0.04905817950146303, "bacc": 0.8444293478260869, "bacc_std": 0.04938723308278298} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 57, "C": 0.005994842503189409, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.04480925229134146, "f1": 0.8683760683760684, "f1_std": 0.046790184117893, "bacc": 0.8661684782608696, "bacc_std": 0.04726722659822225} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 58, "C": 0.046415888336127774, "split": "test", "acc": 0.7636363636363637, "acc_std": 0.05635189320483026, "f1": 0.7607895617263298, "f1_std": 0.05671739718438392, "bacc": 0.7663043478260869, "bacc_std": 0.05643110238812051} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 59, "C": 0.046415888336127774, "split": "test", "acc": 0.9272727272727272, "acc_std": 0.033619435543759395, "f1": 0.9252717391304348, "f1_std": 0.034638595839659024, "bacc": 0.9252717391304348, "bacc_std": 0.03489629992152492} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 60, "C": 0.046415888336127774, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.04779984439270635, "f1": 0.8484848484848485, "f1_std": 0.05073800049883608, "bacc": 0.8444293478260869, "bacc_std": 0.05115539203447407} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 61, "C": 0.005994842503189409, "split": "test", "acc": 0.9272727272727272, "acc_std": 0.032823515053934556, "f1": 0.9260752688172043, "f1_std": 0.03316966016285463, "bacc": 0.9313858695652174, "bacc_std": 0.03158574847045793} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 62, "C": 2.782559402207126, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.045108075911046056, "f1": 0.8683760683760684, "f1_std": 0.04706592411856217, "bacc": 0.8661684782608696, "bacc_std": 0.0474099885728901} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 63, "C": 0.005994842503189409, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.037622061401951803, "f1": 0.9045470322804582, "f1_std": 0.040951887774074026, "bacc": 0.8974184782608696, "bacc_std": 0.04270890941832561} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 64, "C": 21.54434690031882, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.04860696137607116, "f1": 0.8354935194416749, "f1_std": 0.04851662531448197, "bacc": 0.8471467391304348, "bacc_std": 0.04662987694998631} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 65, "C": 0.005994842503189409, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.04264651555820473, "f1": 0.8863636363636364, "f1_std": 0.04525859058188483, "bacc": 0.8817934782608696, "bacc_std": 0.04609796839176517} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 66, "C": 0.005994842503189409, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.04598634364300874, "f1": 0.8484848484848485, "f1_std": 0.04866559315095088, "bacc": 0.8444293478260869, "bacc_std": 0.049021139820730475} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 67, "C": 0.005994842503189409, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.03833111935156345, "f1": 0.905982905982906, "f1_std": 0.04004672554671995, "bacc": 0.9035326086956521, "bacc_std": 0.0408511969041459} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 68, "C": 0.046415888336127774, "split": "test", "acc": 0.9272727272727272, "acc_std": 0.03375211533009745, "f1": 0.9229691876750701, "f1_std": 0.037653732350501234, "bacc": 0.9130434782608696, "bacc_std": 0.040355790068594764} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 69, "C": 0.046415888336127774, "split": "test", "acc": 0.9818181818181818, "acc_std": 0.018009180395353836, "f1": 0.9811965811965813, "f1_std": 0.0189197194632661, "bacc": 0.9782608695652174, "bacc_std": 0.021532715690096974} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 70, "C": 0.3593813663804626, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.03965969288420451, "f1": 0.9071259709557582, "f1_std": 0.04042451554323483, "bacc": 0.9096467391304348, "bacc_std": 0.040007658082936964} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 71, "C": 0.005994842503189409, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.04600267329637725, "f1": 0.8281846581048247, "f1_std": 0.049665836522629875, "bacc": 0.8226902173913043, "bacc_std": 0.04934354741300053} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 72, "C": 0.000774263682681127, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.04253650255470913, "f1": 0.8879076086956521, "f1_std": 0.043836471921655844, "bacc": 0.8879076086956521, "bacc_std": 0.04410724994265836} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 73, "C": 0.005994842503189409, "split": "test", "acc": 0.9272727272727272, "acc_std": 0.034051667111286224, "f1": 0.9242424242424243, "f1_std": 0.03636431691754075, "bacc": 0.9191576086956521, "bacc_std": 0.03843751899483909} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 74, "C": 0.005994842503189409, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.03945050670572994, "f1": 0.905982905982906, "f1_std": 0.04122527157904843, "bacc": 0.9035326086956521, "bacc_std": 0.04222734334658748} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 75, "C": 0.046415888336127774, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.043384119423837755, "f1": 0.8505434782608696, "f1_std": 0.04484254186318451, "bacc": 0.8505434782608696, "bacc_std": 0.04501957589196547} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 76, "C": 0.046415888336127774, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.051283248436969464, "f1": 0.8307692307692308, "f1_std": 0.0534819904143214, "bacc": 0.8288043478260869, "bacc_std": 0.05346743432462892} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 77, "C": 0.005994842503189409, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.04053761032966385, "f1": 0.884453781512605, "f1_std": 0.04474255292926192, "bacc": 0.8756793478260869, "bacc_std": 0.046099985881089475} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 78, "C": 0.3593813663804626, "split": "test", "acc": 0.9636363636363636, "acc_std": 0.02490248087478452, "f1": 0.9626358695652174, "f1_std": 0.025618440554011246, "bacc": 0.9626358695652174, "bacc_std": 0.02594622005779819} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 79, "C": 0.005994842503189409, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.0437509253739207, "f1": 0.8428571428571429, "f1_std": 0.05061221757674831, "bacc": 0.8322010869565217, "bacc_std": 0.050248001354363386} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 80, "C": 0.046415888336127774, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.04809427381252073, "f1": 0.8484848484848485, "f1_std": 0.050906977356067494, "bacc": 0.8444293478260869, "bacc_std": 0.05130358950926657} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 81, "C": 0.005994842503189409, "split": "test", "acc": 0.9636363636363636, "acc_std": 0.02580975534704621, "f1": 0.9626358695652174, "f1_std": 0.026566929023660795, "bacc": 0.9626358695652174, "bacc_std": 0.02698644775990158} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 82, "C": 0.046415888336127774, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.03585380784784349, "f1": 0.9045470322804582, "f1_std": 0.0386490359895269, "bacc": 0.8974184782608696, "bacc_std": 0.040520596997251974} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 83, "C": 0.046415888336127774, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.043031197600603074, "f1": 0.8639095086603039, "f1_std": 0.04880436308396927, "bacc": 0.8539402173913043, "bacc_std": 0.049118542708594726} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 84, "C": 0.046415888336127774, "split": "test", "acc": 0.7818181818181819, "acc_std": 0.059201731044604466, "f1": 0.7782258064516129, "f1_std": 0.05988975594692057, "bacc": 0.7819293478260869, "bacc_std": 0.0598342398554756} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 85, "C": 0.005994842503189409, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.041805152120302745, "f1": 0.8879076086956521, "f1_std": 0.043122878357793486, "bacc": 0.8879076086956521, "bacc_std": 0.043286929107459564} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 86, "C": 0.046415888336127774, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.03964155095330494, "f1": 0.905982905982906, "f1_std": 0.0414572076291978, "bacc": 0.9035326086956521, "bacc_std": 0.04245339620666587} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 87, "C": 0.046415888336127774, "split": "test", "acc": 0.9272727272727272, "acc_std": 0.03397585919832586, "f1": 0.9242424242424243, "f1_std": 0.03616813579667084, "bacc": 0.9191576086956521, "bacc_std": 0.037972201182934096} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 88, "C": 0.046415888336127774, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.0489584205438529, "f1": 0.8505434782608696, "f1_std": 0.05054704921229563, "bacc": 0.8505434782608696, "bacc_std": 0.05111774078274165} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 89, "C": 0.005994842503189409, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.036863097182470946, "f1": 0.8821428571428571, "f1_std": 0.04291354249608569, "bacc": 0.8695652173913043, "bacc_std": 0.04407544228338917} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 90, "C": 0.3593813663804626, "split": "test", "acc": 0.7636363636363637, "acc_std": 0.055809107938808875, "f1": 0.7472605160834218, "f1_std": 0.0629651604974415, "bacc": 0.7418478260869565, "bacc_std": 0.06063384062126817} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 91, "C": 0.3593813663804626, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.045084149053384245, "f1": 0.8699763593380614, "f1_std": 0.045880929692043694, "bacc": 0.8722826086956521, "bacc_std": 0.045412745510578875} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 92, "C": 0.005994842503189409, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.04115893002327875, "f1": 0.8863636363636364, "f1_std": 0.04375570414815548, "bacc": 0.8817934782608696, "bacc_std": 0.04481920836148059} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 93, "C": 0.046415888336127774, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.0464672496416153, "f1": 0.8663658451926415, "f1_std": 0.0501099178385526, "bacc": 0.8600543478260869, "bacc_std": 0.05091722372875617} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 94, "C": 0.005994842503189409, "split": "test", "acc": 0.9636363636363636, "acc_std": 0.02508827390641505, "f1": 0.9626358695652174, "f1_std": 0.02577476780701878, "bacc": 0.9626358695652174, "bacc_std": 0.025961225078379828} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 95, "C": 0.046415888336127774, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.03858618773988331, "f1": 0.9071259709557582, "f1_std": 0.039310523325167386, "bacc": 0.9096467391304348, "bacc_std": 0.03882445226517596} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 96, "C": 0.005994842503189409, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.03917496248818132, "f1": 0.905982905982906, "f1_std": 0.04082068657018065, "bacc": 0.9035326086956521, "bacc_std": 0.0415421272530122} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 97, "C": 0.3593813663804626, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.04110556456267848, "f1": 0.8683760683760684, "f1_std": 0.043015714015057105, "bacc": 0.8661684782608696, "bacc_std": 0.04361811091395039} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 98, "C": 0.005994842503189409, "split": "test", "acc": 0.8181818181818182, "acc_std": 0.04960805053301276, "f1": 0.8074229691876751, "f1_std": 0.05446396162114083, "bacc": 0.8009510869565217, "bacc_std": 0.0542416097934673} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 99, "C": 0.046415888336127774, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.04808228484278256, "f1": 0.8484848484848485, "f1_std": 0.05143844365681967, "bacc": 0.8444293478260869, "bacc_std": 0.05201993285146099} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 100, "C": 0.046415888336127774, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.040482641928617516, "f1": 0.89, "f1_std": 0.04040146520253775, "bacc": 0.9001358695652174, "bacc_std": 0.03739940062099162} +eval results (random splits): + +| model | repr | clf | dataset | split | n_trials | C | C_std | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|-----------:|--------:|--------:|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | aabc_sex | train | 100 | 0.57383 | 3.0375 | 0.9376 | 0.034244 | 0.93578 | 0.035324 | 0.93477 | 0.036095 | +| flat_mae | patch | logistic | aabc_sex | test | 100 | 0.57383 | 3.0375 | 0.87091 | 0.051198 | 0.86655 | 0.052975 | 0.86577 | 0.053189 | + + +done! total time: 0:05:16 diff --git a/input_space_v3/flat_lr1e-3_6/eval_v2/abide_dx__patch__logistic/config.yaml b/input_space_v3/flat_lr1e-3_6/eval_v2/abide_dx__patch__logistic/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..3e1160bdf3e8b0fe02558bd347389fd083532521 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_6/eval_v2/abide_dx__patch__logistic/config.yaml @@ -0,0 +1,30 @@ +output_root: experiments/input_space_v3/output +name_prefix: eval_logistic +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_6; eval v2 (abide_dx patch logistic) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: input_space_v3/flat_lr1e-3_6/eval_v2/abide_dx__patch__logistic +model: flat_mae +representation: patch +dataset: abide_dx +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/eval_v2/abide_dx__patch__logistic +remote_dir: null diff --git a/input_space_v3/flat_lr1e-3_6/eval_v2/abide_dx__patch__logistic/eval_table.csv b/input_space_v3/flat_lr1e-3_6/eval_v2/abide_dx__patch__logistic/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..13287a3ca8d99528f0e53914eb7223266ce77aa6 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_6/eval_v2/abide_dx__patch__logistic/eval_table.csv @@ -0,0 +1,203 @@ +model,repr,clf,dataset,trial,C,split,acc,acc_std,f1,f1_std,bacc,bacc_std +flat_mae,patch,logistic,abide_dx,,0.3593813663804626,train,0.9045584045584045,0.010657479546169774,0.9033961489088576,0.01080032350818768,0.903030402521505,0.010853482648742679 +flat_mae,patch,logistic,abide_dx,,0.3593813663804626,test,0.6209677419354839,0.04400031631236222,0.6118548118548119,0.0456322194980315,0.6125949201361613,0.044515917886905065 +flat_mae,patch,logistic,abide_dx,1,10000.0,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,1,10000.0,test,0.6935483870967742,0.04100518989512265,0.6906512605042017,0.04171533381799067,0.6906512605042017,0.0416045406720658 +flat_mae,patch,logistic,abide_dx,2,2.782559402207126,train,0.9886039886039886,0.0037815659546637332,0.988482834994463,0.003821989846315336,0.988482834994463,0.0038379391824785326 +flat_mae,patch,logistic,abide_dx,2,2.782559402207126,test,0.5887096774193549,0.04237183343295808,0.5826018084614877,0.04294961038666298,0.5824579831932774,0.042589278343597256 +flat_mae,patch,logistic,abide_dx,3,2.782559402207126,train,0.9829059829059829,0.005217092119003091,0.9827343083885354,0.005266860014225505,0.9830195644149132,0.0052323351404269264 +flat_mae,patch,logistic,abide_dx,3,2.782559402207126,test,0.5887096774193549,0.0444514607422837,0.5880398671096345,0.04459863847002808,0.5903361344537814,0.044813088426808034 +flat_mae,patch,logistic,abide_dx,4,0.046415888336127774,train,0.7948717948717948,0.01475319862498522,0.7900857199813941,0.015284544196697348,0.7876707272056109,0.015223471675995194 +flat_mae,patch,logistic,abide_dx,4,0.046415888336127774,test,0.6935483870967742,0.04051234058721267,0.6906512605042017,0.04115921260523214,0.6906512605042017,0.041249183569094676 +flat_mae,patch,logistic,abide_dx,5,0.005994842503189409,train,0.7065527065527065,0.017015627239706163,0.6974137931034483,0.01770137315751341,0.6960502030269472,0.017339909840427326 +flat_mae,patch,logistic,abide_dx,5,0.005994842503189409,test,0.6451612903225806,0.04124195756114816,0.6418067226890756,0.04156853578794491,0.6418067226890756,0.04148794601533934 +flat_mae,patch,logistic,abide_dx,6,0.3593813663804626,train,0.886039886039886,0.011569411201864525,0.884303513745138,0.011808898673903445,0.8827611664820967,0.011947610960174456 +flat_mae,patch,logistic,abide_dx,6,0.3593813663804626,test,0.6854838709677419,0.04111651928566638,0.6794591370053689,0.04185664788720785,0.6785714285714286,0.0412881195132079 +flat_mae,patch,logistic,abide_dx,7,10000.0,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,7,10000.0,test,0.5725806451612904,0.04256437555746936,0.5662332519305657,0.04281259606573496,0.5661764705882353,0.04246396387800449 +flat_mae,patch,logistic,abide_dx,8,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,8,166.81005372000556,test,0.5645161290322581,0.044970692271428164,0.5626959247648903,0.04506747087228388,0.5635504201680672,0.04516471155944109 +flat_mae,patch,logistic,abide_dx,9,0.046415888336127774,train,0.7849002849002849,0.015684411205525148,0.7803536239932201,0.016142191095509826,0.7783314876338132,0.016083924962042393 +flat_mae,patch,logistic,abide_dx,9,0.046415888336127774,test,0.6370967741935484,0.041625854448705396,0.6217205613178767,0.044806041058216124,0.6234243697478992,0.042665082708657015 +flat_mae,patch,logistic,abide_dx,10,0.046415888336127774,train,0.8034188034188035,0.016261977241389874,0.7990074441687345,0.016820320063094904,0.7966039128829827,0.016769106200215395 +flat_mae,patch,logistic,abide_dx,10,0.046415888336127774,test,0.6774193548387096,0.04257483770269748,0.6669352672575879,0.044529235285979886,0.6664915966386555,0.043325875500551315 +flat_mae,patch,logistic,abide_dx,11,0.3593813663804626,train,0.9131054131054132,0.010869696740090423,0.9119329224276751,0.011058010848197568,0.9108527131782945,0.011222768569250958 +flat_mae,patch,logistic,abide_dx,11,0.3593813663804626,test,0.532258064516129,0.04458790380195792,0.5262187088274045,0.04522928372624911,0.5262605042016807,0.044785511313902564 +flat_mae,patch,logistic,abide_dx,12,2.782559402207126,train,0.99002849002849,0.003597507770469214,0.9899194830504128,0.003638762142192064,0.9897748246585456,0.0037303710754518537 +flat_mae,patch,logistic,abide_dx,12,2.782559402207126,test,0.5645161290322581,0.04525336236580693,0.5626959247648903,0.04525619704712528,0.5635504201680672,0.04524015376952791 +flat_mae,patch,logistic,abide_dx,13,2.782559402207126,train,0.9871794871794872,0.00426482975256955,0.9870544193851771,0.004302429011192567,0.9874861572535991,0.004184466822768768 +flat_mae,patch,logistic,abide_dx,13,2.782559402207126,test,0.5967741935483871,0.04460749156644157,0.5915678524374176,0.04560078192517349,0.5913865546218487,0.045388244323292186 +flat_mae,patch,logistic,abide_dx,14,2.782559402207126,train,0.9843304843304843,0.004439305963732526,0.9841495630969315,0.004495524265034509,0.9837209302325581,0.004657233896250126 +flat_mae,patch,logistic,abide_dx,14,2.782559402207126,test,0.5725806451612904,0.044137225706064674,0.5712141971683957,0.044266150144600454,0.5724789915966386,0.044372543199504344 +flat_mae,patch,logistic,abide_dx,15,0.3593813663804626,train,0.8974358974358975,0.011138592284596968,0.8960863808685784,0.011336055551916711,0.8951642672572906,0.011505369529070653 +flat_mae,patch,logistic,abide_dx,15,0.3593813663804626,test,0.6209677419354839,0.044529275758581184,0.6153389215233318,0.04555885546300393,0.6150210084033614,0.04514827310806652 +flat_mae,patch,logistic,abide_dx,16,0.046415888336127774,train,0.8034188034188035,0.01451813834832578,0.7998297408093097,0.014899829099296278,0.7980804724990771,0.01488584447869666 +flat_mae,patch,logistic,abide_dx,16,0.046415888336127774,test,0.6048387096774194,0.04168364517066423,0.5989703649924097,0.04258175926723472,0.5987394957983193,0.0422140699735118 +flat_mae,patch,logistic,abide_dx,17,0.046415888336127774,train,0.7962962962962963,0.014669923731348622,0.7914512158386222,0.015212436929444876,0.7889627168696935,0.015165129200708555 +flat_mae,patch,logistic,abide_dx,17,0.046415888336127774,test,0.6209677419354839,0.043155443453726954,0.6153389215233318,0.04425074453261452,0.6150210084033614,0.04393632871950525 +flat_mae,patch,logistic,abide_dx,18,0.046415888336127774,train,0.7934472934472935,0.015528100281786392,0.7881506733849064,0.01616844197798275,0.7854928017718716,0.016079513225147158 +flat_mae,patch,logistic,abide_dx,18,0.046415888336127774,test,0.6854838709677419,0.04121518806662571,0.6742776318448171,0.04382384580351308,0.6738445378151261,0.0422963287701514 +flat_mae,patch,logistic,abide_dx,19,0.005994842503189409,train,0.717948717948718,0.015935569862144113,0.7069499144016125,0.016942284987235674,0.705500184569952,0.01642794602474404 +flat_mae,patch,logistic,abide_dx,19,0.005994842503189409,test,0.5645161290322581,0.0421670128406586,0.5334448160535117,0.04761549324790839,0.5446428571428572,0.04316840497746991 +flat_mae,patch,logistic,abide_dx,20,0.3593813663804626,train,0.9045584045584045,0.011639501331675298,0.9031383152895821,0.011870659877470408,0.9016242155777039,0.012045829547006904 +flat_mae,patch,logistic,abide_dx,20,0.3593813663804626,test,0.6209677419354839,0.04128115762700961,0.6097756946769334,0.04329176735459851,0.6102941176470589,0.04199018551355735 +flat_mae,patch,logistic,abide_dx,21,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,21,21.54434690031882,test,0.532258064516129,0.04312018873310705,0.532258064516129,0.04312423504635699,0.5372899159663865,0.04297053527516574 +flat_mae,patch,logistic,abide_dx,22,2.782559402207126,train,0.99002849002849,0.0036398294429429642,0.9899194830504128,0.0036806245421559746,0.9897748246585456,0.0037436004326620795 +flat_mae,patch,logistic,abide_dx,22,2.782559402207126,test,0.6612903225806451,0.04161040252551119,0.6555555555555556,0.04277247507773221,0.654936974789916,0.04246566562530085 +flat_mae,patch,logistic,abide_dx,23,0.3593813663804626,train,0.9031339031339032,0.010903057596937434,0.9017268213147558,0.011102628305620789,0.9003322259136213,0.011252084551938251 +flat_mae,patch,logistic,abide_dx,23,0.3593813663804626,test,0.6370967741935484,0.04290654850097347,0.6317074780542539,0.04385795469017977,0.6313025210084033,0.04359522462484963 +flat_mae,patch,logistic,abide_dx,24,0.046415888336127774,train,0.8190883190883191,0.013992141875101496,0.8149483476863874,0.014503510283915699,0.8122923588039868,0.014514975646798368 +flat_mae,patch,logistic,abide_dx,24,0.046415888336127774,test,0.5887096774193549,0.041922985110093285,0.5841388834089565,0.04220357971141707,0.5840336134453781,0.04211561086431409 +flat_mae,patch,logistic,abide_dx,25,0.3593813663804626,train,0.9188034188034188,0.00995826348473463,0.9176522642849059,0.010132736790340692,0.9163159837578443,0.010245727180969234 +flat_mae,patch,logistic,abide_dx,25,0.3593813663804626,test,0.5806451612903226,0.046985759017688145,0.5778999738151349,0.04721033487687813,0.5782563025210083,0.04725184500638371 +flat_mae,patch,logistic,abide_dx,26,0.046415888336127774,train,0.8091168091168092,0.014574518432102612,0.8053228476821193,0.014959001656260795,0.8032484311554079,0.014949124875397422 +flat_mae,patch,logistic,abide_dx,26,0.046415888336127774,test,0.5564516129032258,0.04301315047079809,0.543354536324071,0.04478185711573367,0.5451680672268907,0.04348390021682187 +flat_mae,patch,logistic,abide_dx,27,0.3593813663804626,train,0.9088319088319088,0.010497691767959933,0.9076323385498475,0.010664031825824604,0.9066814322628276,0.010765253750772153 +flat_mae,patch,logistic,abide_dx,27,0.3593813663804626,test,0.6048387096774194,0.04327697981964653,0.5989703649924097,0.04455205361985132,0.5987394957983193,0.04422036067444605 +flat_mae,patch,logistic,abide_dx,28,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,28,21.54434690031882,test,0.6129032258064516,0.04374363637382007,0.6092436974789917,0.044372819335520355,0.6092436974789917,0.04434384761930968 +flat_mae,patch,logistic,abide_dx,29,2.782559402207126,train,0.98005698005698,0.00548656409172307,0.9798328846280123,0.005552238679868653,0.9795496493170912,0.005654918527524597 +flat_mae,patch,logistic,abide_dx,29,2.782559402207126,test,0.5967741935483871,0.04283517219653937,0.5915678524374176,0.043702715746508296,0.5913865546218487,0.043396364809437926 +flat_mae,patch,logistic,abide_dx,30,0.046415888336127774,train,0.8034188034188035,0.014964760298073894,0.79934714708246,0.015457975893697597,0.7971945367294204,0.015458311418715027 +flat_mae,patch,logistic,abide_dx,30,0.046415888336127774,test,0.6290322580645161,0.04159002872172464,0.6169755573462261,0.04383672125607176,0.6176470588235294,0.04229400905428208 +flat_mae,patch,logistic,abide_dx,31,0.3593813663804626,train,0.9045584045584045,0.011447318973422917,0.9032705869287578,0.011653375666767173,0.9022148394241418,0.011827260290625566 +flat_mae,patch,logistic,abide_dx,31,0.3593813663804626,test,0.6129032258064516,0.04332408183213227,0.6125,0.043403773794600774,0.615546218487395,0.04353240854019973 +flat_mae,patch,logistic,abide_dx,32,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,32,21.54434690031882,test,0.6532258064516129,0.041092554981674675,0.6448884448884449,0.042487740760431984,0.6444327731092437,0.04177310389492214 +flat_mae,patch,logistic,abide_dx,33,10000.0,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,33,10000.0,test,0.5725806451612904,0.04230574753758454,0.5718845677806006,0.04242556854459463,0.5740546218487395,0.0425264279328296 +flat_mae,patch,logistic,abide_dx,34,0.3593813663804626,train,0.9102564102564102,0.010334828421458492,0.9091635430038512,0.010489996488825317,0.9085640457733482,0.010617727177139913 +flat_mae,patch,logistic,abide_dx,34,0.3593813663804626,test,0.6290322580645161,0.042962001941507094,0.6274817136886102,0.04309982294749376,0.6286764705882353,0.043203965278280826 +flat_mae,patch,logistic,abide_dx,35,2.782559402207126,train,0.98005698005698,0.005216164772322828,0.979856693119958,0.005266674252643746,0.9801402731635289,0.0052342733727657785 +flat_mae,patch,logistic,abide_dx,35,2.782559402207126,test,0.6451612903225806,0.041748291882783325,0.6428384393820372,0.04207261062016932,0.6433823529411764,0.04213367522945534 +flat_mae,patch,logistic,abide_dx,36,0.3593813663804626,train,0.9045584045584045,0.011172049998964985,0.9033342033816792,0.011333735653168598,0.9025101513473606,0.011414433912645416 +flat_mae,patch,logistic,abide_dx,36,0.3593813663804626,test,0.5967741935483871,0.041167015983609945,0.571704890853827,0.044474470487799254,0.578781512605042,0.04163799436000547 +flat_mae,patch,logistic,abide_dx,37,2.782559402207126,train,0.9857549857549858,0.004418041047311002,0.9855860443342066,0.004477891011222775,0.9850129198966409,0.004705959677491123 +flat_mae,patch,logistic,abide_dx,37,2.782559402207126,test,0.5887096774193549,0.04422312113915346,0.5841388834089565,0.044936039155145824,0.5840336134453781,0.04480203302041285 +flat_mae,patch,logistic,abide_dx,38,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,38,1291.5496650148827,test,0.5806451612903226,0.0453412629386294,0.5778999738151349,0.04572218113555856,0.5782563025210083,0.045772151378530156 +flat_mae,patch,logistic,abide_dx,39,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,39,21.54434690031882,test,0.5483870967741935,0.0456557579173686,0.5425559947299078,0.04588586778683427,0.5425420168067226,0.045640712194522794 +flat_mae,patch,logistic,abide_dx,40,2.782559402207126,train,0.9886039886039886,0.003915150881546266,0.9884759340731499,0.00396172466443798,0.988187523071244,0.004072258834681859 +flat_mae,patch,logistic,abide_dx,40,2.782559402207126,test,0.5403225806451613,0.043185859611027694,0.5239442311578096,0.045639705103464226,0.5273109243697479,0.04392684846206549 +flat_mae,patch,logistic,abide_dx,41,0.046415888336127774,train,0.7934472934472935,0.015515736215464319,0.7897574123989218,0.01595845908782806,0.7881506090808417,0.015995712019236212 +flat_mae,patch,logistic,abide_dx,41,0.046415888336127774,test,0.6048387096774194,0.04122291309448954,0.5907590759075907,0.043766345016033145,0.592436974789916,0.042075348542084084 +flat_mae,patch,logistic,abide_dx,42,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,42,21.54434690031882,test,0.6774193548387096,0.04088944766417074,0.6743697478991597,0.04130028911687566,0.6743697478991597,0.041288216360767065 +flat_mae,patch,logistic,abide_dx,43,10000.0,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,43,10000.0,test,0.6290322580645161,0.04169816222053723,0.6169755573462261,0.04382050528798807,0.6176470588235294,0.04247905632574509 +flat_mae,patch,logistic,abide_dx,44,0.005994842503189409,train,0.7165242165242165,0.01672831416591779,0.7087070117749109,0.017301966080843178,0.7071613141380584,0.017034418816243565 +flat_mae,patch,logistic,abide_dx,44,0.005994842503189409,test,0.6129032258064516,0.04034366867920415,0.5852842809364549,0.045481684781924325,0.5934873949579832,0.04134160073761376 +flat_mae,patch,logistic,abide_dx,45,0.3593813663804626,train,0.9202279202279202,0.01034129011838715,0.9192818482715572,0.01047548032205104,0.9187892211148025,0.010544987602567304 +flat_mae,patch,logistic,abide_dx,45,0.3593813663804626,test,0.6209677419354839,0.043224711107932266,0.6167554415729598,0.043725754198179506,0.6165966386554622,0.04361516942966314 +flat_mae,patch,logistic,abide_dx,46,0.005994842503189409,train,0.7122507122507122,0.016304914741329977,0.7050076554386899,0.016954924157834946,0.7035806570690292,0.01673522911495945 +flat_mae,patch,logistic,abide_dx,46,0.005994842503189409,test,0.5645161290322581,0.043402608451513856,0.555142173797502,0.04445074891630646,0.555672268907563,0.04380040977672063 +flat_mae,patch,logistic,abide_dx,47,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,47,166.81005372000556,test,0.6612903225806451,0.04200513756299037,0.6569169960474308,0.042552823672859806,0.6565126050420168,0.04241482308322162 +flat_mae,patch,logistic,abide_dx,48,0.3593813663804626,train,0.9230769230769231,0.009951032698214972,0.9221646394047159,0.010070645442512868,0.9216685123661867,0.010120109066259372 +flat_mae,patch,logistic,abide_dx,48,0.3593813663804626,test,0.6129032258064516,0.043467340952127384,0.6045708211533352,0.04449848437252694,0.6045168067226891,0.043792464486505554 +flat_mae,patch,logistic,abide_dx,49,2.782559402207126,train,0.9871794871794872,0.003804991298649984,0.9870469879839183,0.003842939885327289,0.9871908453303803,0.0038199909847096768 +flat_mae,patch,logistic,abide_dx,49,2.782559402207126,test,0.6209677419354839,0.04328767839624254,0.6167554415729598,0.043910238352954156,0.6165966386554622,0.04371162175939059 +flat_mae,patch,logistic,abide_dx,50,0.3593813663804626,train,0.9216524216524217,0.00959842336479513,0.9206474803879456,0.009746972096513625,0.9197858988556663,0.009875523384771384 +flat_mae,patch,logistic,abide_dx,50,0.3593813663804626,test,0.6290322580645161,0.0413329511551821,0.6119727891156463,0.04506561323453554,0.6144957983193278,0.04261731456169171 +flat_mae,patch,logistic,abide_dx,51,0.046415888336127774,train,0.792022792022792,0.01606809192329236,0.7880592570535249,0.016439208982741222,0.7862679955703211,0.016379625878365923 +flat_mae,patch,logistic,abide_dx,51,0.046415888336127774,test,0.6209677419354839,0.042766757856113106,0.6097756946769334,0.044827492802796534,0.6102941176470589,0.04355326491244055 +flat_mae,patch,logistic,abide_dx,52,0.3593813663804626,train,0.9031339031339032,0.011121398919033663,0.9019230769230769,0.011268904023227545,0.901218161683278,0.011330955400385916 +flat_mae,patch,logistic,abide_dx,52,0.3593813663804626,test,0.5483870967741935,0.04494428276866826,0.5425559947299078,0.04567209392223294,0.5425420168067226,0.045389299067877704 +flat_mae,patch,logistic,abide_dx,53,0.3593813663804626,train,0.9145299145299145,0.010682186398731976,0.9135162660052399,0.010812943387049754,0.9130306386120339,0.010848748569581087 +flat_mae,patch,logistic,abide_dx,53,0.3593813663804626,test,0.5887096774193549,0.044853359755692435,0.5826018084614877,0.04585715745538094,0.5824579831932774,0.045467586353344226 +flat_mae,patch,logistic,abide_dx,54,0.046415888336127774,train,0.7905982905982906,0.014405281906890617,0.7871775252999178,0.01472748563644855,0.7858619416758952,0.014747741108560567 +flat_mae,patch,logistic,abide_dx,54,0.046415888336127774,test,0.6532258064516129,0.043168594781881044,0.6429862738533645,0.04523857003971165,0.6428571428571428,0.044056022086161516 +flat_mae,patch,logistic,abide_dx,55,2.782559402207126,train,0.9829059829059829,0.0047927646271398085,0.9827242524916944,0.004844774821946499,0.9827242524916944,0.004879255797291866 +flat_mae,patch,logistic,abide_dx,55,2.782559402207126,test,0.5967741935483871,0.04418757612106297,0.5929621848739496,0.04485082291761298,0.5929621848739496,0.044713731481453786 +flat_mae,patch,logistic,abide_dx,56,0.000774263682681127,train,0.6581196581196581,0.017282432412997328,0.6323067253299811,0.019648102730818427,0.6376522702104097,0.017903995451357117 +flat_mae,patch,logistic,abide_dx,56,0.000774263682681127,test,0.6290322580645161,0.03686879103444145,0.5988748241912799,0.04185528834943587,0.6081932773109243,0.03775532554221459 +flat_mae,patch,logistic,abide_dx,57,2.782559402207126,train,0.9857549857549858,0.004459477643486156,0.9856119236571128,0.0045006466347342735,0.9858988556662975,0.004419319183482115 +flat_mae,patch,logistic,abide_dx,57,2.782559402207126,test,0.5645161290322581,0.043598474779764355,0.5588932806324111,0.04433151085861639,0.5588235294117647,0.04409161146533494 +flat_mae,patch,logistic,abide_dx,58,10000.0,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,58,10000.0,test,0.5483870967741935,0.04289759846674824,0.5464994775339603,0.0428785079362013,0.5472689075630253,0.04293762137833104 +flat_mae,patch,logistic,abide_dx,59,0.005994842503189409,train,0.6866096866096866,0.016817018761703675,0.676849681955139,0.01750511906095633,0.6758951642672573,0.017128132979418068 +flat_mae,patch,logistic,abide_dx,59,0.005994842503189409,test,0.6451612903225806,0.04391130439290038,0.6418067226890756,0.04443698592772596,0.6418067226890756,0.04426192757839346 +flat_mae,patch,logistic,abide_dx,60,0.3593813663804626,train,0.8974358974358975,0.011370688032249164,0.8960863808685784,0.011552355227506757,0.8951642672572906,0.011688771286300937 +flat_mae,patch,logistic,abide_dx,60,0.3593813663804626,test,0.6774193548387096,0.0406996434646271,0.6732542819499341,0.04144749971258257,0.6727941176470589,0.04128551630252522 +flat_mae,patch,logistic,abide_dx,61,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,61,166.81005372000556,test,0.5161290322580645,0.04765550153154077,0.514993481095176,0.04781944566061977,0.516281512605042,0.04805926336444161 +flat_mae,patch,logistic,abide_dx,62,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,62,1291.5496650148827,test,0.5241935483870968,0.043308887418733025,0.5204195345788266,0.04336345314380184,0.520483193277311,0.04323499021950999 +flat_mae,patch,logistic,abide_dx,63,2.782559402207126,train,0.9814814814814815,0.005267937237104169,0.9812676654781918,0.005335638370788812,0.9808416389811738,0.005498396894606433 +flat_mae,patch,logistic,abide_dx,63,2.782559402207126,test,0.5967741935483871,0.04658130137595139,0.5966692688004163,0.046652966951357115,0.6008403361344539,0.04622240017576178 +flat_mae,patch,logistic,abide_dx,64,2.782559402207126,train,0.9843304843304843,0.005040087350368703,0.9841495630969315,0.005103839096240342,0.9837209302325581,0.005256810468831212 +flat_mae,patch,logistic,abide_dx,64,2.782559402207126,test,0.6774193548387096,0.039054059493927845,0.6732542819499341,0.039558355812793,0.6727941176470589,0.0392780648391298 +flat_mae,patch,logistic,abide_dx,65,0.3593813663804626,train,0.9145299145299145,0.010626366634924604,0.9135162660052399,0.010773970897608192,0.9130306386120339,0.010892019399005495 +flat_mae,patch,logistic,abide_dx,65,0.3593813663804626,test,0.6048387096774194,0.042080453516545754,0.5931704050887178,0.043859351876263414,0.5940126050420168,0.04270083437436806 +flat_mae,patch,logistic,abide_dx,66,0.046415888336127774,train,0.8048433048433048,0.014394716515879568,0.8010446942976241,0.01480352029543547,0.799077150239941,0.014785636407076282 +flat_mae,patch,logistic,abide_dx,66,0.046415888336127774,test,0.5887096774193549,0.04393170605708784,0.5841388834089565,0.0446551078693842,0.5840336134453781,0.04452366038498799 +flat_mae,patch,logistic,abide_dx,67,10000.0,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,67,10000.0,test,0.5806451612903226,0.04272336784769829,0.5796610169491525,0.04272091596638783,0.58140756302521,0.04277181554605289 +flat_mae,patch,logistic,abide_dx,68,0.3593813663804626,train,0.9088319088319088,0.011207998933956525,0.9076323385498475,0.01138909197197788,0.9066814322628276,0.011526563508631332 +flat_mae,patch,logistic,abide_dx,68,0.3593813663804626,test,0.6774193548387096,0.04222176167818152,0.6753076721654884,0.042624212535737296,0.6759453781512605,0.04268457885069977 +flat_mae,patch,logistic,abide_dx,69,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,69,21.54434690031882,test,0.6209677419354839,0.04531922556747168,0.607462787095036,0.04756622120913608,0.608718487394958,0.04598404150488914 +flat_mae,patch,logistic,abide_dx,70,0.3593813663804626,train,0.9031339031339032,0.011334768128687046,0.9021610808683675,0.011450386791064752,0.9023994093761536,0.01149284569557096 +flat_mae,patch,logistic,abide_dx,70,0.3593813663804626,test,0.6048387096774194,0.04428146129901626,0.5953379953379954,0.04521475043610554,0.5955882352941176,0.044438074794953555 +flat_mae,patch,logistic,abide_dx,71,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,71,166.81005372000556,test,0.5725806451612904,0.047906093104151615,0.5662332519305657,0.04848804012656488,0.5661764705882353,0.0480752033620932 +flat_mae,patch,logistic,abide_dx,72,0.3593813663804626,train,0.9131054131054132,0.0100886179837948,0.9119908418848124,0.01025250051400957,0.9111480251015135,0.010402000070710678 +flat_mae,patch,logistic,abide_dx,72,0.3593813663804626,test,0.6290322580645161,0.042693143179036636,0.6274817136886102,0.04281191678076969,0.6286764705882353,0.042754406682701675 +flat_mae,patch,logistic,abide_dx,73,0.3593813663804626,train,0.9002849002849003,0.011101377868518033,0.8991644231400617,0.011248058880606012,0.8989294942783315,0.011375420097884297 +flat_mae,patch,logistic,abide_dx,73,0.3593813663804626,test,0.6290322580645161,0.039843198780643616,0.6091008771929824,0.044122332821227926,0.6129201680672269,0.04120212950324298 +flat_mae,patch,logistic,abide_dx,74,0.3593813663804626,train,0.9216524216524217,0.009887671564978037,0.9205416585205232,0.010061516684249651,0.9191952750092285,0.010204783949686588 +flat_mae,patch,logistic,abide_dx,74,0.3593813663804626,test,0.6209677419354839,0.04576409616062075,0.6167554415729598,0.04635473933402379,0.6165966386554622,0.046129226305681365 +flat_mae,patch,logistic,abide_dx,75,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,75,1291.5496650148827,test,0.6048387096774194,0.044718346224719464,0.6041951664386684,0.04476646698029722,0.6066176470588236,0.044765057121997 +flat_mae,patch,logistic,abide_dx,76,0.3593813663804626,train,0.8988603988603988,0.011464805178368282,0.8973555281426915,0.011680225904207444,0.8958656330749355,0.011780256328574911 +flat_mae,patch,logistic,abide_dx,76,0.3593813663804626,test,0.5806451612903226,0.04269699097713516,0.5716183895827798,0.04382039739581149,0.571953781512605,0.04311082640129932 +flat_mae,patch,logistic,abide_dx,77,0.3593813663804626,train,0.9116809116809117,0.010474926105465382,0.9104591836734695,0.010656079166484075,0.909265411590993,0.010808686121815111 +flat_mae,patch,logistic,abide_dx,77,0.3593813663804626,test,0.6370967741935484,0.04191727582378168,0.635936582501468,0.042058437490899964,0.6376050420168067,0.042072152873068334 +flat_mae,patch,logistic,abide_dx,78,0.3593813663804626,train,0.9074074074074074,0.011051535439968516,0.9062197495493903,0.011201221841252749,0.905389442598745,0.011239785534812183 +flat_mae,patch,logistic,abide_dx,78,0.3593813663804626,test,0.5564516129032258,0.041380684892906694,0.5457875457875458,0.04234986123049047,0.5467436974789917,0.04165156921564284 +flat_mae,patch,logistic,abide_dx,79,0.3593813663804626,train,0.8903133903133903,0.011820870914627342,0.8889064725431239,0.012005550263896055,0.8881136950904394,0.0121067881164553 +flat_mae,patch,logistic,abide_dx,79,0.3593813663804626,test,0.6290322580645161,0.040899978883034566,0.6145945945945945,0.04442401408516104,0.6160714285714286,0.04221145694996958 +flat_mae,patch,logistic,abide_dx,80,0.000774263682681127,train,0.6566951566951567,0.01645283333874026,0.6350398974896616,0.018268503674958705,0.6384274640088593,0.01697661866292523 +flat_mae,patch,logistic,abide_dx,80,0.000774263682681127,test,0.6048387096774194,0.042110463106188815,0.5819745442036464,0.0451926037274348,0.5877100840336134,0.04259836856796115 +flat_mae,patch,logistic,abide_dx,81,2.782559402207126,train,0.98005698005698,0.0050438415255561145,0.9798449612403101,0.005099363047356941,0.9798449612403101,0.005146769234746229 +flat_mae,patch,logistic,abide_dx,81,2.782559402207126,test,0.6290322580645161,0.041579131081820965,0.6227513227513227,0.04241944962967937,0.6223739495798319,0.041956746727645586 +flat_mae,patch,logistic,abide_dx,82,0.046415888336127774,train,0.7977207977207977,0.015325183029659843,0.7938658527506885,0.015762346239505,0.7920265780730897,0.01578035868060876 +flat_mae,patch,logistic,abide_dx,82,0.046415888336127774,test,0.6532258064516129,0.041360512418404674,0.6408702094699266,0.043233660991421716,0.641281512605042,0.0419221063039954 +flat_mae,patch,logistic,abide_dx,83,0.046415888336127774,train,0.8005698005698005,0.014694984085885826,0.7962686567164179,0.015207288920019164,0.7940199335548173,0.015198557021096971 +flat_mae,patch,logistic,abide_dx,83,0.046415888336127774,test,0.6048387096774194,0.043784972642956305,0.602745995423341,0.04388633809386253,0.6034663865546219,0.043825298120482865 +flat_mae,patch,logistic,abide_dx,84,2.782559402207126,train,0.9843304843304843,0.00476679215498255,0.9841591876506488,0.004819822679997121,0.984016242155777,0.0048592927803407055 +flat_mae,patch,logistic,abide_dx,84,2.782559402207126,test,0.6048387096774194,0.04527350976878863,0.6041951664386684,0.045423180823928495,0.6066176470588236,0.045481395592009075 +flat_mae,patch,logistic,abide_dx,85,0.3593813663804626,train,0.9088319088319088,0.010773623593437523,0.9073764070424277,0.011006352624191586,0.905500184569952,0.011175487523070158 +flat_mae,patch,logistic,abide_dx,85,0.3593813663804626,test,0.6451612903225806,0.04158181822214763,0.6375232527238905,0.0429976355871984,0.6370798319327731,0.04231371832212898 +flat_mae,patch,logistic,abide_dx,86,0.046415888336127774,train,0.8105413105413105,0.014133889925458037,0.8065366357026376,0.014562637873495222,0.8042451088962717,0.014544141481926743 +flat_mae,patch,logistic,abide_dx,86,0.046415888336127774,test,0.5967741935483871,0.04268095162521233,0.5836690840719849,0.044813925329022834,0.5850840336134454,0.0433301902709909 +flat_mae,patch,logistic,abide_dx,87,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,87,166.81005372000556,test,0.5645161290322581,0.04751969579062243,0.5626959247648903,0.047732848637779705,0.5635504201680672,0.04788154341212144 +flat_mae,patch,logistic,abide_dx,88,0.3593813663804626,train,0.9031339031339032,0.010693146494510801,0.9019851014726052,0.01082446384887633,0.9015134736064969,0.01086231328233489 +flat_mae,patch,logistic,abide_dx,88,0.3593813663804626,test,0.5564516129032258,0.04380396626994123,0.5479551932126997,0.04515466144564911,0.5483193277310925,0.04437306131143814 +flat_mae,patch,logistic,abide_dx,89,0.3593813663804626,train,0.9031339031339032,0.011332399025285067,0.9019851014726052,0.011495239177661428,0.9015134736064969,0.011603401647654225 +flat_mae,patch,logistic,abide_dx,89,0.3593813663804626,test,0.6209677419354839,0.04229952103403342,0.6203504657677024,0.042511911555052524,0.6228991596638656,0.04252307981884489 +flat_mae,patch,logistic,abide_dx,90,0.3593813663804626,train,0.8988603988603988,0.011009710068742112,0.8972827598998423,0.011233345564653363,0.8955703211517165,0.011375211271111019 +flat_mae,patch,logistic,abide_dx,90,0.3593813663804626,test,0.6693548387096774,0.03939868987400116,0.6553454003118433,0.041716416889067805,0.6559873949579832,0.04008652602666359 +flat_mae,patch,logistic,abide_dx,91,0.046415888336127774,train,0.8005698005698005,0.014551953566537296,0.7964391347213362,0.015014316844996758,0.7943152454780362,0.015003867468250618 +flat_mae,patch,logistic,abide_dx,91,0.046415888336127774,test,0.6209677419354839,0.04163035393035092,0.6118548118548119,0.04297659524114211,0.6118697478991597,0.042167892173943594 +flat_mae,patch,logistic,abide_dx,92,2.782559402207126,train,0.9715099715099715,0.005974882015887304,0.9712070874861573,0.006040895012675308,0.9712070874861573,0.006108388851766042 +flat_mae,patch,logistic,abide_dx,92,2.782559402207126,test,0.6370967741935484,0.04169245646539222,0.6365057650967364,0.04174307378412951,0.6391806722689075,0.04186309989302108 +flat_mae,patch,logistic,abide_dx,93,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,93,166.81005372000556,test,0.6370967741935484,0.04278395986399716,0.6342182890855457,0.042939043863899774,0.634453781512605,0.04279870597620228 +flat_mae,patch,logistic,abide_dx,94,0.046415888336127774,train,0.7934472934472935,0.015245033944703524,0.7894268662274124,0.015734131846845634,0.7875599852344037,0.015755138372764606 +flat_mae,patch,logistic,abide_dx,94,0.046415888336127774,test,0.6048387096774194,0.043199570757492874,0.6004471624909581,0.04375192703383753,0.6003151260504203,0.04348384743781532 +flat_mae,patch,logistic,abide_dx,95,0.3593813663804626,train,0.9131054131054132,0.011016941509291682,0.9120472400513479,0.011168012213293615,0.9114433370247323,0.01126011559413089 +flat_mae,patch,logistic,abide_dx,95,0.3593813663804626,test,0.6693548387096774,0.04233414414708266,0.6630211440312852,0.043321818468876165,0.6622899159663866,0.042851067123190104 +flat_mae,patch,logistic,abide_dx,96,2.782559402207126,train,0.99002849002849,0.0035222928647090958,0.989913358334411,0.0035662159981751855,0.9894795127353266,0.0037290255670334766 +flat_mae,patch,logistic,abide_dx,96,2.782559402207126,test,0.6209677419354839,0.04391423388338951,0.6153389215233318,0.04487454299844114,0.6150210084033614,0.04447860113551036 +flat_mae,patch,logistic,abide_dx,97,0.046415888336127774,train,0.7991452991452992,0.014582164029944352,0.7947261999813353,0.015044085913942688,0.7924326319675157,0.015008912841714439 +flat_mae,patch,logistic,abide_dx,97,0.046415888336127774,test,0.6854838709677419,0.04078145032912551,0.6819885579009667,0.04156549039666065,0.6817226890756303,0.04153599394433276 +flat_mae,patch,logistic,abide_dx,98,0.046415888336127774,train,0.811965811965812,0.014750146772649183,0.808228476821192,0.015175168994074506,0.8061277224067922,0.015182848693503923 +flat_mae,patch,logistic,abide_dx,98,0.046415888336127774,test,0.5887096774193549,0.04551777219776991,0.5808311791608669,0.046302493627905804,0.5808823529411764,0.04578973201236585 +flat_mae,patch,logistic,abide_dx,99,0.3593813663804626,train,0.915954415954416,0.010777447158841902,0.9146434201984606,0.01100179137721497,0.9128460686600222,0.011185672060113458 +flat_mae,patch,logistic,abide_dx,99,0.3593813663804626,test,0.5967741935483871,0.04389340922700353,0.5836690840719849,0.04597664918721441,0.5850840336134454,0.04459692204236576 +flat_mae,patch,logistic,abide_dx,100,0.005994842503189409,train,0.6937321937321937,0.01766944010325143,0.6837035996973881,0.01867043864776838,0.6826504245108895,0.018216201784762756 +flat_mae,patch,logistic,abide_dx,100,0.005994842503189409,test,0.6854838709677419,0.040503629030250954,0.6721578198088265,0.043040512182370524,0.6722689075630253,0.04140942254958124 diff --git a/input_space_v3/flat_lr1e-3_6/eval_v2/abide_dx__patch__logistic/log.txt b/input_space_v3/flat_lr1e-3_6/eval_v2/abide_dx__patch__logistic/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..e5385cdc69e05d43f4aaa3ed6818324c4264f326 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_6/eval_v2/abide_dx__patch__logistic/log.txt @@ -0,0 +1,252 @@ +fMRI foundation model logistic probe eval +version: 0.1.dev86+gf97f52698 +sha: bcce2b486277d3a5b520775efd9cdf1a2affce36, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-04-08 22:53:11 +config: +output_root: experiments/input_space_v3/output +name_prefix: eval_logistic +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_6; eval v2 (abide_dx patch logistic) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: input_space_v3/flat_lr1e-3_6/eval_v2/abide_dx__patch__logistic +model: flat_mae +representation: patch +dataset: abide_dx +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/eval_v2/abide_dx__patch__logistic +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=True, reg_tokens=0, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: abide_dx (flat) +train (n=578): +HFDataset( + dataset=Dataset({ + features: ['sub', 'site', 'dataset', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 578 +}), + labels=['Autism' 'Control'], + counts=[260 318] +) + +validation (n=124): +HFDataset( + dataset=Dataset({ + features: ['sub', 'site', 'dataset', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 124 +}), + labels=['Autism' 'Control'], + counts=[54 70] +) + +test (n=124): +HFDataset( + dataset=Dataset({ + features: ['sub', 'site', 'dataset', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 124 +}), + labels=['Autism' 'Control'], + counts=[57 67] +) + +extracting features for all splits +extract (train) [ 0/289] eta: 0:21:17 time: 4.4221 data: 3.3946 max mem: 2698 +extract (train) [ 20/289] eta: 0:01:44 time: 0.1853 data: 0.0635 max mem: 2851 +extract (train) [ 40/289] eta: 0:01:12 time: 0.1869 data: 0.0663 max mem: 2851 +extract (train) [ 60/289] eta: 0:00:57 time: 0.1671 data: 0.0544 max mem: 2851 +extract (train) [ 80/289] eta: 0:00:47 time: 0.1573 data: 0.0517 max mem: 2851 +extract (train) [100/289] eta: 0:00:40 time: 0.1597 data: 0.0511 max mem: 2851 +extract (train) [120/289] eta: 0:00:35 time: 0.1759 data: 0.0610 max mem: 2851 +extract (train) [140/289] eta: 0:00:29 time: 0.1647 data: 0.0532 max mem: 2851 +extract (train) [160/289] eta: 0:00:25 time: 0.1714 data: 0.0561 max mem: 2851 +extract (train) [180/289] eta: 0:00:21 time: 0.1712 data: 0.0570 max mem: 2851 +extract (train) [200/289] eta: 0:00:17 time: 0.1726 data: 0.0595 max mem: 2851 +extract (train) [220/289] eta: 0:00:13 time: 0.1640 data: 0.0529 max mem: 2851 +extract (train) [240/289] eta: 0:00:09 time: 0.1798 data: 0.0624 max mem: 2851 +extract (train) [260/289] eta: 0:00:05 time: 0.1691 data: 0.0552 max mem: 2851 +extract (train) [280/289] eta: 0:00:01 time: 0.1618 data: 0.0521 max mem: 2851 +extract (train) [288/289] eta: 0:00:00 time: 0.1625 data: 0.0520 max mem: 2851 +extract (train) Total time: 0:00:53 (0.1865 s / it) +extract (validation) [ 0/62] eta: 0:03:55 time: 3.8050 data: 3.6581 max mem: 2851 +extract (validation) [20/62] eta: 0:00:16 time: 0.2106 data: 0.0741 max mem: 2851 +extract (validation) [40/62] eta: 0:00:06 time: 0.1586 data: 0.0493 max mem: 2851 +extract (validation) [60/62] eta: 0:00:00 time: 0.1608 data: 0.0513 max mem: 2851 +extract (validation) [61/62] eta: 0:00:00 time: 0.1610 data: 0.0513 max mem: 2851 +extract (validation) Total time: 0:00:14 (0.2405 s / it) +extract (test) [ 0/62] eta: 0:03:59 time: 3.8570 data: 3.6625 max mem: 2851 +extract (test) [20/62] eta: 0:00:16 time: 0.2287 data: 0.0862 max mem: 2851 +extract (test) [40/62] eta: 0:00:06 time: 0.1749 data: 0.0597 max mem: 2851 +extract (test) [60/62] eta: 0:00:00 time: 0.1592 data: 0.0516 max mem: 2851 +extract (test) [61/62] eta: 0:00:00 time: 0.1587 data: 0.0510 max mem: 2851 +extract (test) Total time: 0:00:15 (0.2512 s / it) +feature extraction time: 0:01:24 +train features: (578, 768) +validation features: (124, 768) +test features: (124, 768) +evaluating fixed splits +eval results (fixed splits): + +| model | repr | clf | dataset | trial | C | split | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|--------:|:--------|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | abide_dx | | 0.35938 | train | 0.90456 | 0.010657 | 0.9034 | 0.0108 | 0.90303 | 0.010853 | +| flat_mae | patch | logistic | abide_dx | | 0.35938 | test | 0.62097 | 0.044 | 0.61185 | 0.045632 | 0.61259 | 0.044516 | + + +evaluating random splits (n=100) +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 1, "C": 10000.0, "split": "test", "acc": 0.6935483870967742, "acc_std": 0.04100518989512265, "f1": 0.6906512605042017, "f1_std": 0.04171533381799067, "bacc": 0.6906512605042017, "bacc_std": 0.0416045406720658} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 2, "C": 2.782559402207126, "split": "test", "acc": 0.5887096774193549, "acc_std": 0.04237183343295808, "f1": 0.5826018084614877, "f1_std": 0.04294961038666298, "bacc": 0.5824579831932774, "bacc_std": 0.042589278343597256} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 3, "C": 2.782559402207126, "split": "test", "acc": 0.5887096774193549, "acc_std": 0.0444514607422837, "f1": 0.5880398671096345, "f1_std": 0.04459863847002808, "bacc": 0.5903361344537814, "bacc_std": 0.044813088426808034} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 4, "C": 0.046415888336127774, "split": "test", "acc": 0.6935483870967742, "acc_std": 0.04051234058721267, "f1": 0.6906512605042017, "f1_std": 0.04115921260523214, "bacc": 0.6906512605042017, "bacc_std": 0.041249183569094676} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 5, "C": 0.005994842503189409, "split": "test", "acc": 0.6451612903225806, "acc_std": 0.04124195756114816, "f1": 0.6418067226890756, "f1_std": 0.04156853578794491, "bacc": 0.6418067226890756, "bacc_std": 0.04148794601533934} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 6, "C": 0.3593813663804626, "split": "test", "acc": 0.6854838709677419, "acc_std": 0.04111651928566638, "f1": 0.6794591370053689, "f1_std": 0.04185664788720785, "bacc": 0.6785714285714286, "bacc_std": 0.0412881195132079} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 7, "C": 10000.0, "split": "test", "acc": 0.5725806451612904, "acc_std": 0.04256437555746936, "f1": 0.5662332519305657, "f1_std": 0.04281259606573496, "bacc": 0.5661764705882353, "bacc_std": 0.04246396387800449} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 8, "C": 166.81005372000556, "split": "test", "acc": 0.5645161290322581, "acc_std": 0.044970692271428164, "f1": 0.5626959247648903, "f1_std": 0.04506747087228388, "bacc": 0.5635504201680672, "bacc_std": 0.04516471155944109} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 9, "C": 0.046415888336127774, "split": "test", "acc": 0.6370967741935484, "acc_std": 0.041625854448705396, "f1": 0.6217205613178767, "f1_std": 0.044806041058216124, "bacc": 0.6234243697478992, "bacc_std": 0.042665082708657015} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 10, "C": 0.046415888336127774, "split": "test", "acc": 0.6774193548387096, "acc_std": 0.04257483770269748, "f1": 0.6669352672575879, "f1_std": 0.044529235285979886, "bacc": 0.6664915966386555, "bacc_std": 0.043325875500551315} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 11, "C": 0.3593813663804626, "split": "test", "acc": 0.532258064516129, "acc_std": 0.04458790380195792, "f1": 0.5262187088274045, "f1_std": 0.04522928372624911, "bacc": 0.5262605042016807, "bacc_std": 0.044785511313902564} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 12, "C": 2.782559402207126, "split": "test", "acc": 0.5645161290322581, "acc_std": 0.04525336236580693, "f1": 0.5626959247648903, "f1_std": 0.04525619704712528, "bacc": 0.5635504201680672, "bacc_std": 0.04524015376952791} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 13, "C": 2.782559402207126, "split": "test", "acc": 0.5967741935483871, "acc_std": 0.04460749156644157, "f1": 0.5915678524374176, "f1_std": 0.04560078192517349, "bacc": 0.5913865546218487, "bacc_std": 0.045388244323292186} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 14, "C": 2.782559402207126, "split": "test", "acc": 0.5725806451612904, "acc_std": 0.044137225706064674, "f1": 0.5712141971683957, "f1_std": 0.044266150144600454, "bacc": 0.5724789915966386, "bacc_std": 0.044372543199504344} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 15, "C": 0.3593813663804626, "split": "test", "acc": 0.6209677419354839, "acc_std": 0.044529275758581184, "f1": 0.6153389215233318, "f1_std": 0.04555885546300393, "bacc": 0.6150210084033614, "bacc_std": 0.04514827310806652} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 16, "C": 0.046415888336127774, "split": "test", "acc": 0.6048387096774194, "acc_std": 0.04168364517066423, "f1": 0.5989703649924097, "f1_std": 0.04258175926723472, "bacc": 0.5987394957983193, "bacc_std": 0.0422140699735118} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 17, "C": 0.046415888336127774, "split": "test", "acc": 0.6209677419354839, "acc_std": 0.043155443453726954, "f1": 0.6153389215233318, "f1_std": 0.04425074453261452, "bacc": 0.6150210084033614, "bacc_std": 0.04393632871950525} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 18, "C": 0.046415888336127774, "split": "test", "acc": 0.6854838709677419, "acc_std": 0.04121518806662571, "f1": 0.6742776318448171, "f1_std": 0.04382384580351308, "bacc": 0.6738445378151261, "bacc_std": 0.0422963287701514} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 19, "C": 0.005994842503189409, "split": "test", "acc": 0.5645161290322581, "acc_std": 0.0421670128406586, "f1": 0.5334448160535117, "f1_std": 0.04761549324790839, "bacc": 0.5446428571428572, "bacc_std": 0.04316840497746991} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 20, "C": 0.3593813663804626, "split": "test", "acc": 0.6209677419354839, "acc_std": 0.04128115762700961, "f1": 0.6097756946769334, "f1_std": 0.04329176735459851, "bacc": 0.6102941176470589, "bacc_std": 0.04199018551355735} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 21, "C": 21.54434690031882, "split": "test", "acc": 0.532258064516129, "acc_std": 0.04312018873310705, "f1": 0.532258064516129, "f1_std": 0.04312423504635699, "bacc": 0.5372899159663865, "bacc_std": 0.04297053527516574} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 22, "C": 2.782559402207126, "split": "test", "acc": 0.6612903225806451, "acc_std": 0.04161040252551119, "f1": 0.6555555555555556, "f1_std": 0.04277247507773221, "bacc": 0.654936974789916, "bacc_std": 0.04246566562530085} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 23, "C": 0.3593813663804626, "split": "test", "acc": 0.6370967741935484, "acc_std": 0.04290654850097347, "f1": 0.6317074780542539, "f1_std": 0.04385795469017977, "bacc": 0.6313025210084033, "bacc_std": 0.04359522462484963} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 24, "C": 0.046415888336127774, "split": "test", "acc": 0.5887096774193549, "acc_std": 0.041922985110093285, "f1": 0.5841388834089565, "f1_std": 0.04220357971141707, "bacc": 0.5840336134453781, "bacc_std": 0.04211561086431409} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 25, "C": 0.3593813663804626, "split": "test", "acc": 0.5806451612903226, "acc_std": 0.046985759017688145, "f1": 0.5778999738151349, "f1_std": 0.04721033487687813, "bacc": 0.5782563025210083, "bacc_std": 0.04725184500638371} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 26, "C": 0.046415888336127774, "split": "test", "acc": 0.5564516129032258, "acc_std": 0.04301315047079809, "f1": 0.543354536324071, "f1_std": 0.04478185711573367, "bacc": 0.5451680672268907, "bacc_std": 0.04348390021682187} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 27, "C": 0.3593813663804626, "split": "test", "acc": 0.6048387096774194, "acc_std": 0.04327697981964653, "f1": 0.5989703649924097, "f1_std": 0.04455205361985132, "bacc": 0.5987394957983193, "bacc_std": 0.04422036067444605} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 28, "C": 21.54434690031882, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.04374363637382007, "f1": 0.6092436974789917, "f1_std": 0.044372819335520355, "bacc": 0.6092436974789917, "bacc_std": 0.04434384761930968} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 29, "C": 2.782559402207126, "split": "test", "acc": 0.5967741935483871, "acc_std": 0.04283517219653937, "f1": 0.5915678524374176, "f1_std": 0.043702715746508296, "bacc": 0.5913865546218487, "bacc_std": 0.043396364809437926} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 30, "C": 0.046415888336127774, "split": "test", "acc": 0.6290322580645161, "acc_std": 0.04159002872172464, "f1": 0.6169755573462261, "f1_std": 0.04383672125607176, "bacc": 0.6176470588235294, "bacc_std": 0.04229400905428208} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 31, "C": 0.3593813663804626, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.04332408183213227, "f1": 0.6125, "f1_std": 0.043403773794600774, "bacc": 0.615546218487395, "bacc_std": 0.04353240854019973} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 32, "C": 21.54434690031882, "split": "test", "acc": 0.6532258064516129, "acc_std": 0.041092554981674675, "f1": 0.6448884448884449, "f1_std": 0.042487740760431984, "bacc": 0.6444327731092437, "bacc_std": 0.04177310389492214} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 33, "C": 10000.0, "split": "test", "acc": 0.5725806451612904, "acc_std": 0.04230574753758454, "f1": 0.5718845677806006, "f1_std": 0.04242556854459463, "bacc": 0.5740546218487395, "bacc_std": 0.0425264279328296} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 34, "C": 0.3593813663804626, "split": "test", "acc": 0.6290322580645161, "acc_std": 0.042962001941507094, "f1": 0.6274817136886102, "f1_std": 0.04309982294749376, "bacc": 0.6286764705882353, "bacc_std": 0.043203965278280826} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 35, "C": 2.782559402207126, "split": "test", "acc": 0.6451612903225806, "acc_std": 0.041748291882783325, "f1": 0.6428384393820372, "f1_std": 0.04207261062016932, "bacc": 0.6433823529411764, "bacc_std": 0.04213367522945534} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 36, "C": 0.3593813663804626, "split": "test", "acc": 0.5967741935483871, "acc_std": 0.041167015983609945, "f1": 0.571704890853827, "f1_std": 0.044474470487799254, "bacc": 0.578781512605042, "bacc_std": 0.04163799436000547} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 37, "C": 2.782559402207126, "split": "test", "acc": 0.5887096774193549, "acc_std": 0.04422312113915346, "f1": 0.5841388834089565, "f1_std": 0.044936039155145824, "bacc": 0.5840336134453781, "bacc_std": 0.04480203302041285} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 38, "C": 1291.5496650148827, "split": "test", "acc": 0.5806451612903226, "acc_std": 0.0453412629386294, "f1": 0.5778999738151349, "f1_std": 0.04572218113555856, "bacc": 0.5782563025210083, "bacc_std": 0.045772151378530156} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 39, "C": 21.54434690031882, "split": "test", "acc": 0.5483870967741935, "acc_std": 0.0456557579173686, "f1": 0.5425559947299078, "f1_std": 0.04588586778683427, "bacc": 0.5425420168067226, "bacc_std": 0.045640712194522794} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 40, "C": 2.782559402207126, "split": "test", "acc": 0.5403225806451613, "acc_std": 0.043185859611027694, "f1": 0.5239442311578096, "f1_std": 0.045639705103464226, "bacc": 0.5273109243697479, "bacc_std": 0.04392684846206549} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 41, "C": 0.046415888336127774, "split": "test", "acc": 0.6048387096774194, "acc_std": 0.04122291309448954, "f1": 0.5907590759075907, "f1_std": 0.043766345016033145, "bacc": 0.592436974789916, "bacc_std": 0.042075348542084084} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 42, "C": 21.54434690031882, "split": "test", "acc": 0.6774193548387096, "acc_std": 0.04088944766417074, "f1": 0.6743697478991597, "f1_std": 0.04130028911687566, "bacc": 0.6743697478991597, "bacc_std": 0.041288216360767065} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 43, "C": 10000.0, "split": "test", "acc": 0.6290322580645161, "acc_std": 0.04169816222053723, "f1": 0.6169755573462261, "f1_std": 0.04382050528798807, "bacc": 0.6176470588235294, "bacc_std": 0.04247905632574509} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 44, "C": 0.005994842503189409, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.04034366867920415, "f1": 0.5852842809364549, "f1_std": 0.045481684781924325, "bacc": 0.5934873949579832, "bacc_std": 0.04134160073761376} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 45, "C": 0.3593813663804626, "split": "test", "acc": 0.6209677419354839, "acc_std": 0.043224711107932266, "f1": 0.6167554415729598, "f1_std": 0.043725754198179506, "bacc": 0.6165966386554622, "bacc_std": 0.04361516942966314} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 46, "C": 0.005994842503189409, "split": "test", "acc": 0.5645161290322581, "acc_std": 0.043402608451513856, "f1": 0.555142173797502, "f1_std": 0.04445074891630646, "bacc": 0.555672268907563, "bacc_std": 0.04380040977672063} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 47, "C": 166.81005372000556, "split": "test", "acc": 0.6612903225806451, "acc_std": 0.04200513756299037, "f1": 0.6569169960474308, "f1_std": 0.042552823672859806, "bacc": 0.6565126050420168, "bacc_std": 0.04241482308322162} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 48, "C": 0.3593813663804626, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.043467340952127384, "f1": 0.6045708211533352, "f1_std": 0.04449848437252694, "bacc": 0.6045168067226891, "bacc_std": 0.043792464486505554} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 49, "C": 2.782559402207126, "split": "test", "acc": 0.6209677419354839, "acc_std": 0.04328767839624254, "f1": 0.6167554415729598, "f1_std": 0.043910238352954156, "bacc": 0.6165966386554622, "bacc_std": 0.04371162175939059} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 50, "C": 0.3593813663804626, "split": "test", "acc": 0.6290322580645161, "acc_std": 0.0413329511551821, "f1": 0.6119727891156463, "f1_std": 0.04506561323453554, "bacc": 0.6144957983193278, "bacc_std": 0.04261731456169171} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 51, "C": 0.046415888336127774, "split": "test", "acc": 0.6209677419354839, "acc_std": 0.042766757856113106, "f1": 0.6097756946769334, "f1_std": 0.044827492802796534, "bacc": 0.6102941176470589, "bacc_std": 0.04355326491244055} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 52, "C": 0.3593813663804626, "split": "test", "acc": 0.5483870967741935, "acc_std": 0.04494428276866826, "f1": 0.5425559947299078, "f1_std": 0.04567209392223294, "bacc": 0.5425420168067226, "bacc_std": 0.045389299067877704} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 53, "C": 0.3593813663804626, "split": "test", "acc": 0.5887096774193549, "acc_std": 0.044853359755692435, "f1": 0.5826018084614877, "f1_std": 0.04585715745538094, "bacc": 0.5824579831932774, "bacc_std": 0.045467586353344226} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 54, "C": 0.046415888336127774, "split": "test", "acc": 0.6532258064516129, "acc_std": 0.043168594781881044, "f1": 0.6429862738533645, "f1_std": 0.04523857003971165, "bacc": 0.6428571428571428, "bacc_std": 0.044056022086161516} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 55, "C": 2.782559402207126, "split": "test", "acc": 0.5967741935483871, "acc_std": 0.04418757612106297, "f1": 0.5929621848739496, "f1_std": 0.04485082291761298, "bacc": 0.5929621848739496, "bacc_std": 0.044713731481453786} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 56, "C": 0.000774263682681127, "split": "test", "acc": 0.6290322580645161, "acc_std": 0.03686879103444145, "f1": 0.5988748241912799, "f1_std": 0.04185528834943587, "bacc": 0.6081932773109243, "bacc_std": 0.03775532554221459} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 57, "C": 2.782559402207126, "split": "test", "acc": 0.5645161290322581, "acc_std": 0.043598474779764355, "f1": 0.5588932806324111, "f1_std": 0.04433151085861639, "bacc": 0.5588235294117647, "bacc_std": 0.04409161146533494} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 58, "C": 10000.0, "split": "test", "acc": 0.5483870967741935, "acc_std": 0.04289759846674824, "f1": 0.5464994775339603, "f1_std": 0.0428785079362013, "bacc": 0.5472689075630253, "bacc_std": 0.04293762137833104} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 59, "C": 0.005994842503189409, "split": "test", "acc": 0.6451612903225806, "acc_std": 0.04391130439290038, "f1": 0.6418067226890756, "f1_std": 0.04443698592772596, "bacc": 0.6418067226890756, "bacc_std": 0.04426192757839346} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 60, "C": 0.3593813663804626, "split": "test", "acc": 0.6774193548387096, "acc_std": 0.0406996434646271, "f1": 0.6732542819499341, "f1_std": 0.04144749971258257, "bacc": 0.6727941176470589, "bacc_std": 0.04128551630252522} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 61, "C": 166.81005372000556, "split": "test", "acc": 0.5161290322580645, "acc_std": 0.04765550153154077, "f1": 0.514993481095176, "f1_std": 0.04781944566061977, "bacc": 0.516281512605042, "bacc_std": 0.04805926336444161} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 62, "C": 1291.5496650148827, "split": "test", "acc": 0.5241935483870968, "acc_std": 0.043308887418733025, "f1": 0.5204195345788266, "f1_std": 0.04336345314380184, "bacc": 0.520483193277311, "bacc_std": 0.04323499021950999} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 63, "C": 2.782559402207126, "split": "test", "acc": 0.5967741935483871, "acc_std": 0.04658130137595139, "f1": 0.5966692688004163, "f1_std": 0.046652966951357115, "bacc": 0.6008403361344539, "bacc_std": 0.04622240017576178} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 64, "C": 2.782559402207126, "split": "test", "acc": 0.6774193548387096, "acc_std": 0.039054059493927845, "f1": 0.6732542819499341, "f1_std": 0.039558355812793, "bacc": 0.6727941176470589, "bacc_std": 0.0392780648391298} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 65, "C": 0.3593813663804626, "split": "test", "acc": 0.6048387096774194, "acc_std": 0.042080453516545754, "f1": 0.5931704050887178, "f1_std": 0.043859351876263414, "bacc": 0.5940126050420168, "bacc_std": 0.04270083437436806} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 66, "C": 0.046415888336127774, "split": "test", "acc": 0.5887096774193549, "acc_std": 0.04393170605708784, "f1": 0.5841388834089565, "f1_std": 0.0446551078693842, "bacc": 0.5840336134453781, "bacc_std": 0.04452366038498799} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 67, "C": 10000.0, "split": "test", "acc": 0.5806451612903226, "acc_std": 0.04272336784769829, "f1": 0.5796610169491525, "f1_std": 0.04272091596638783, "bacc": 0.58140756302521, "bacc_std": 0.04277181554605289} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 68, "C": 0.3593813663804626, "split": "test", "acc": 0.6774193548387096, "acc_std": 0.04222176167818152, "f1": 0.6753076721654884, "f1_std": 0.042624212535737296, "bacc": 0.6759453781512605, "bacc_std": 0.04268457885069977} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 69, "C": 21.54434690031882, "split": "test", "acc": 0.6209677419354839, "acc_std": 0.04531922556747168, "f1": 0.607462787095036, "f1_std": 0.04756622120913608, "bacc": 0.608718487394958, "bacc_std": 0.04598404150488914} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 70, "C": 0.3593813663804626, "split": "test", "acc": 0.6048387096774194, "acc_std": 0.04428146129901626, "f1": 0.5953379953379954, "f1_std": 0.04521475043610554, "bacc": 0.5955882352941176, "bacc_std": 0.044438074794953555} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 71, "C": 166.81005372000556, "split": "test", "acc": 0.5725806451612904, "acc_std": 0.047906093104151615, "f1": 0.5662332519305657, "f1_std": 0.04848804012656488, "bacc": 0.5661764705882353, "bacc_std": 0.0480752033620932} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 72, "C": 0.3593813663804626, "split": "test", "acc": 0.6290322580645161, "acc_std": 0.042693143179036636, "f1": 0.6274817136886102, "f1_std": 0.04281191678076969, "bacc": 0.6286764705882353, "bacc_std": 0.042754406682701675} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 73, "C": 0.3593813663804626, "split": "test", "acc": 0.6290322580645161, "acc_std": 0.039843198780643616, "f1": 0.6091008771929824, "f1_std": 0.044122332821227926, "bacc": 0.6129201680672269, "bacc_std": 0.04120212950324298} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 74, "C": 0.3593813663804626, "split": "test", "acc": 0.6209677419354839, "acc_std": 0.04576409616062075, "f1": 0.6167554415729598, "f1_std": 0.04635473933402379, "bacc": 0.6165966386554622, "bacc_std": 0.046129226305681365} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 75, "C": 1291.5496650148827, "split": "test", "acc": 0.6048387096774194, "acc_std": 0.044718346224719464, "f1": 0.6041951664386684, "f1_std": 0.04476646698029722, "bacc": 0.6066176470588236, "bacc_std": 0.044765057121997} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 76, "C": 0.3593813663804626, "split": "test", "acc": 0.5806451612903226, "acc_std": 0.04269699097713516, "f1": 0.5716183895827798, "f1_std": 0.04382039739581149, "bacc": 0.571953781512605, "bacc_std": 0.04311082640129932} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 77, "C": 0.3593813663804626, "split": "test", "acc": 0.6370967741935484, "acc_std": 0.04191727582378168, "f1": 0.635936582501468, "f1_std": 0.042058437490899964, "bacc": 0.6376050420168067, "bacc_std": 0.042072152873068334} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 78, "C": 0.3593813663804626, "split": "test", "acc": 0.5564516129032258, "acc_std": 0.041380684892906694, "f1": 0.5457875457875458, "f1_std": 0.04234986123049047, "bacc": 0.5467436974789917, "bacc_std": 0.04165156921564284} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 79, "C": 0.3593813663804626, "split": "test", "acc": 0.6290322580645161, "acc_std": 0.040899978883034566, "f1": 0.6145945945945945, "f1_std": 0.04442401408516104, "bacc": 0.6160714285714286, "bacc_std": 0.04221145694996958} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 80, "C": 0.000774263682681127, "split": "test", "acc": 0.6048387096774194, "acc_std": 0.042110463106188815, "f1": 0.5819745442036464, "f1_std": 0.0451926037274348, "bacc": 0.5877100840336134, "bacc_std": 0.04259836856796115} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 81, "C": 2.782559402207126, "split": "test", "acc": 0.6290322580645161, "acc_std": 0.041579131081820965, "f1": 0.6227513227513227, "f1_std": 0.04241944962967937, "bacc": 0.6223739495798319, "bacc_std": 0.041956746727645586} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 82, "C": 0.046415888336127774, "split": "test", "acc": 0.6532258064516129, "acc_std": 0.041360512418404674, "f1": 0.6408702094699266, "f1_std": 0.043233660991421716, "bacc": 0.641281512605042, "bacc_std": 0.0419221063039954} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 83, "C": 0.046415888336127774, "split": "test", "acc": 0.6048387096774194, "acc_std": 0.043784972642956305, "f1": 0.602745995423341, "f1_std": 0.04388633809386253, "bacc": 0.6034663865546219, "bacc_std": 0.043825298120482865} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 84, "C": 2.782559402207126, "split": "test", "acc": 0.6048387096774194, "acc_std": 0.04527350976878863, "f1": 0.6041951664386684, "f1_std": 0.045423180823928495, "bacc": 0.6066176470588236, "bacc_std": 0.045481395592009075} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 85, "C": 0.3593813663804626, "split": "test", "acc": 0.6451612903225806, "acc_std": 0.04158181822214763, "f1": 0.6375232527238905, "f1_std": 0.0429976355871984, "bacc": 0.6370798319327731, "bacc_std": 0.04231371832212898} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 86, "C": 0.046415888336127774, "split": "test", "acc": 0.5967741935483871, "acc_std": 0.04268095162521233, "f1": 0.5836690840719849, "f1_std": 0.044813925329022834, "bacc": 0.5850840336134454, "bacc_std": 0.0433301902709909} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 87, "C": 166.81005372000556, "split": "test", "acc": 0.5645161290322581, "acc_std": 0.04751969579062243, "f1": 0.5626959247648903, "f1_std": 0.047732848637779705, "bacc": 0.5635504201680672, "bacc_std": 0.04788154341212144} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 88, "C": 0.3593813663804626, "split": "test", "acc": 0.5564516129032258, "acc_std": 0.04380396626994123, "f1": 0.5479551932126997, "f1_std": 0.04515466144564911, "bacc": 0.5483193277310925, "bacc_std": 0.04437306131143814} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 89, "C": 0.3593813663804626, "split": "test", "acc": 0.6209677419354839, "acc_std": 0.04229952103403342, "f1": 0.6203504657677024, "f1_std": 0.042511911555052524, "bacc": 0.6228991596638656, "bacc_std": 0.04252307981884489} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 90, "C": 0.3593813663804626, "split": "test", "acc": 0.6693548387096774, "acc_std": 0.03939868987400116, "f1": 0.6553454003118433, "f1_std": 0.041716416889067805, "bacc": 0.6559873949579832, "bacc_std": 0.04008652602666359} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 91, "C": 0.046415888336127774, "split": "test", "acc": 0.6209677419354839, "acc_std": 0.04163035393035092, "f1": 0.6118548118548119, "f1_std": 0.04297659524114211, "bacc": 0.6118697478991597, "bacc_std": 0.042167892173943594} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 92, "C": 2.782559402207126, "split": "test", "acc": 0.6370967741935484, "acc_std": 0.04169245646539222, "f1": 0.6365057650967364, "f1_std": 0.04174307378412951, "bacc": 0.6391806722689075, "bacc_std": 0.04186309989302108} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 93, "C": 166.81005372000556, "split": "test", "acc": 0.6370967741935484, "acc_std": 0.04278395986399716, "f1": 0.6342182890855457, "f1_std": 0.042939043863899774, "bacc": 0.634453781512605, "bacc_std": 0.04279870597620228} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 94, "C": 0.046415888336127774, "split": "test", "acc": 0.6048387096774194, "acc_std": 0.043199570757492874, "f1": 0.6004471624909581, "f1_std": 0.04375192703383753, "bacc": 0.6003151260504203, "bacc_std": 0.04348384743781532} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 95, "C": 0.3593813663804626, "split": "test", "acc": 0.6693548387096774, "acc_std": 0.04233414414708266, "f1": 0.6630211440312852, "f1_std": 0.043321818468876165, "bacc": 0.6622899159663866, "bacc_std": 0.042851067123190104} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 96, "C": 2.782559402207126, "split": "test", "acc": 0.6209677419354839, "acc_std": 0.04391423388338951, "f1": 0.6153389215233318, "f1_std": 0.04487454299844114, "bacc": 0.6150210084033614, "bacc_std": 0.04447860113551036} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 97, "C": 0.046415888336127774, "split": "test", "acc": 0.6854838709677419, "acc_std": 0.04078145032912551, "f1": 0.6819885579009667, "f1_std": 0.04156549039666065, "bacc": 0.6817226890756303, "bacc_std": 0.04153599394433276} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 98, "C": 0.046415888336127774, "split": "test", "acc": 0.5887096774193549, "acc_std": 0.04551777219776991, "f1": 0.5808311791608669, "f1_std": 0.046302493627905804, "bacc": 0.5808823529411764, "bacc_std": 0.04578973201236585} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 99, "C": 0.3593813663804626, "split": "test", "acc": 0.5967741935483871, "acc_std": 0.04389340922700353, "f1": 0.5836690840719849, "f1_std": 0.04597664918721441, "bacc": 0.5850840336134454, "bacc_std": 0.04459692204236576} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 100, "C": 0.005994842503189409, "split": "test", "acc": 0.6854838709677419, "acc_std": 0.040503629030250954, "f1": 0.6721578198088265, "f1_std": 0.043040512182370524, "bacc": 0.6722689075630253, "bacc_std": 0.04140942254958124} +eval results (random splits): + +| model | repr | clf | dataset | split | n_trials | C | C_std | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|-----------:|------:|--------:|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | abide_dx | train | 100 | 650.7 | 2384.4 | 0.90301 | 0.095106 | 0.90073 | 0.098388 | 0.9 | 0.098734 | +| flat_mae | patch | logistic | abide_dx | test | 100 | 650.7 | 2384.4 | 0.61153 | 0.041393 | 0.60423 | 0.041636 | 0.60524 | 0.041035 | + + +done! total time: 0:05:58 diff --git a/input_space_v3/flat_lr1e-3_6/eval_v2/adhd200_dx__patch__logistic/config.yaml b/input_space_v3/flat_lr1e-3_6/eval_v2/adhd200_dx__patch__logistic/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..2a4a0cacaaf2c86b17c17e84c34f440be60e432d --- /dev/null +++ b/input_space_v3/flat_lr1e-3_6/eval_v2/adhd200_dx__patch__logistic/config.yaml @@ -0,0 +1,30 @@ +output_root: experiments/input_space_v3/output +name_prefix: eval_logistic +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_6; eval v2 (adhd200_dx patch logistic) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: input_space_v3/flat_lr1e-3_6/eval_v2/adhd200_dx__patch__logistic +model: flat_mae +representation: patch +dataset: adhd200_dx +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/eval_v2/adhd200_dx__patch__logistic +remote_dir: null diff --git a/input_space_v3/flat_lr1e-3_6/eval_v2/adhd200_dx__patch__logistic/eval_table.csv b/input_space_v3/flat_lr1e-3_6/eval_v2/adhd200_dx__patch__logistic/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..6bf441b96ae331a5775a52ae74f48f45cda40e96 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_6/eval_v2/adhd200_dx__patch__logistic/eval_table.csv @@ -0,0 +1,203 @@ +model,repr,clf,dataset,trial,C,split,acc,acc_std,f1,f1_std,bacc,bacc_std +flat_mae,patch,logistic,adhd200_dx,,0.000774263682681127,train,0.6821917808219178,0.023527679246979148,0.6673893916540976,0.02523112757759981,0.6660713195334921,0.02441124714701826 +flat_mae,patch,logistic,adhd200_dx,,0.000774263682681127,test,0.5692307692307692,0.06064923693525255,0.545,0.06545993585263281,0.5477799227799228,0.062334250715750904 +flat_mae,patch,logistic,adhd200_dx,1,0.046415888336127774,train,0.8301369863013699,0.019111904607584388,0.8252563627378304,0.01985584026959232,0.8222507174696221,0.01990715165454536 +flat_mae,patch,logistic,adhd200_dx,1,0.046415888336127774,test,0.5384615384615384,0.06379096038796511,0.5248538011695907,0.06504972264506238,0.525096525096525,0.06414061229081829 +flat_mae,patch,logistic,adhd200_dx,2,0.046415888336127774,train,0.8356164383561644,0.019918599596119198,0.8320758189179243,0.020507198797157254,0.8306924345118154,0.02064544992800482 +flat_mae,patch,logistic,adhd200_dx,2,0.046415888336127774,test,0.6307692307692307,0.05900292641423632,0.6153846153846154,0.062253990162742384,0.6148648648648649,0.060437897852586187 +flat_mae,patch,logistic,adhd200_dx,3,0.005994842503189409,train,0.7808219178082192,0.021680424076580333,0.7722024589652374,0.02316506797960392,0.7685168223728399,0.02296423901577081 +flat_mae,patch,logistic,adhd200_dx,3,0.005994842503189409,test,0.5384615384615384,0.05808921112998645,0.5192307692307693,0.06129904701798908,0.5207528957528957,0.05932643900449705 +flat_mae,patch,logistic,adhd200_dx,4,0.005994842503189409,train,0.736986301369863,0.021800125158671878,0.7272387594968239,0.022976941977238572,0.724659583562313,0.022628135799794818 +flat_mae,patch,logistic,adhd200_dx,4,0.005994842503189409,test,0.6461538461538462,0.0541291814460894,0.6375757575757576,0.056077987384371177,0.6370656370656371,0.0557584919473334 +flat_mae,patch,logistic,adhd200_dx,5,0.005994842503189409,train,0.7643835616438356,0.022020065569185593,0.7551176433876303,0.02358504893561198,0.7518013067106307,0.023265713968785 +flat_mae,patch,logistic,adhd200_dx,5,0.005994842503189409,test,0.49230769230769234,0.06131216854617294,0.49037776193870275,0.06161975717131911,0.49324324324324326,0.06284104395352116 +flat_mae,patch,logistic,adhd200_dx,6,0.005994842503189409,train,0.7616438356164383,0.020263603420150867,0.7508415130758186,0.021612393270428798,0.7472217133785186,0.02113831950019128 +flat_mae,patch,logistic,adhd200_dx,6,0.005994842503189409,test,0.6307692307692307,0.057145304258675256,0.61,0.062210675490069936,0.6105212355212355,0.059256732535068926 +flat_mae,patch,logistic,adhd200_dx,7,0.046415888336127774,train,0.8383561643835616,0.018994344893271883,0.8347389666101344,0.01952361476108305,0.8331196189778347,0.019687735440126815 +flat_mae,patch,logistic,adhd200_dx,7,0.046415888336127774,test,0.6461538461538462,0.0562750977539705,0.6375757575757576,0.05758125135408943,0.6370656370656371,0.057115289276165306 +flat_mae,patch,logistic,adhd200_dx,8,0.046415888336127774,train,0.8383561643835616,0.018832101091636445,0.8350073934462654,0.019335199364792197,0.8338370885998656,0.019498408418281026 +flat_mae,patch,logistic,adhd200_dx,8,0.046415888336127774,test,0.6,0.06092571089877171,0.5833333333333333,0.06434671824032219,0.5834942084942085,0.062509136576709 +flat_mae,patch,logistic,adhd200_dx,9,0.005994842503189409,train,0.7561643835616438,0.02415299703770831,0.7484298647089345,0.025038841346366216,0.7459546925566343,0.024766628008515375 +flat_mae,patch,logistic,adhd200_dx,9,0.005994842503189409,test,0.6461538461538462,0.05974319005038524,0.6289401836684041,0.06381283947778622,0.6283783783783784,0.06161501676018539 +flat_mae,patch,logistic,adhd200_dx,10,0.3593813663804626,train,0.9452054794520548,0.011674667961917247,0.943932411674347,0.01201853967698502,0.9414117359711791,0.012477361121648805 +flat_mae,patch,logistic,adhd200_dx,10,0.3593813663804626,test,0.49230769230769234,0.06280646708494521,0.48000000000000004,0.0639852187712292,0.48021235521235517,0.06355140174291135 +flat_mae,patch,logistic,adhd200_dx,11,0.005994842503189409,train,0.7534246575342466,0.02208924391963801,0.7431506849315068,0.023426630059692404,0.7399401599804604,0.022974139111502544 +flat_mae,patch,logistic,adhd200_dx,11,0.005994842503189409,test,0.5538461538461539,0.05815094823874403,0.5321419707123356,0.06168330629898703,0.5342664092664092,0.05927685420864215 +flat_mae,patch,logistic,adhd200_dx,12,0.046415888336127774,train,0.8246575342465754,0.01958417412477155,0.8196194712132444,0.020325688222433223,0.8166788789155524,0.020352814192335138 +flat_mae,patch,logistic,adhd200_dx,12,0.046415888336127774,test,0.5230769230769231,0.05794998864048165,0.49987589972697943,0.061304328228338555,0.502895752895753,0.05899291324516247 +flat_mae,patch,logistic,adhd200_dx,13,0.046415888336127774,train,0.8465753424657534,0.018657227684404375,0.8424589961770872,0.0193009964262921,0.8396837027538622,0.019416830529806244 +flat_mae,patch,logistic,adhd200_dx,13,0.046415888336127774,test,0.5538461538461539,0.058819398643685,0.543030303030303,0.059912409726456575,0.542953667953668,0.05951531824369584 +flat_mae,patch,logistic,adhd200_dx,14,0.000774263682681127,train,0.6904109589041096,0.02198776779985673,0.6730971950320601,0.02385053749066411,0.6719179336874885,0.022831394584906642 +flat_mae,patch,logistic,adhd200_dx,14,0.000774263682681127,test,0.5846153846153846,0.05500122860381388,0.5501153550371699,0.06161642754086492,0.556949806949807,0.05652938408111811 +flat_mae,patch,logistic,adhd200_dx,15,0.005994842503189409,train,0.7424657534246575,0.022999823606004013,0.7311128526645768,0.02470350706445553,0.72807901325029,0.024175135960152708 +flat_mae,patch,logistic,adhd200_dx,15,0.005994842503189409,test,0.6153846153846154,0.059615334987572405,0.6094688776736361,0.06041576546176785,0.61003861003861,0.06056459940349946 +flat_mae,patch,logistic,adhd200_dx,16,0.005994842503189409,train,0.7643835616438356,0.021194928528039163,0.7561676609495401,0.022230366915239934,0.7532362459546925,0.021994813712907006 +flat_mae,patch,logistic,adhd200_dx,16,0.005994842503189409,test,0.5846153846153846,0.059487865601701946,0.5699583435432491,0.06199535660693942,0.5699806949806949,0.06060371528838815 +flat_mae,patch,logistic,adhd200_dx,17,0.005994842503189409,train,0.7616438356164383,0.021018294580543353,0.7530734597709193,0.02200406916971856,0.7500915918666422,0.021754405139916812 +flat_mae,patch,logistic,adhd200_dx,17,0.005994842503189409,test,0.5846153846153846,0.06145027527489968,0.5644080416976918,0.06462685130494607,0.5656370656370656,0.06247240242057693 +flat_mae,patch,logistic,adhd200_dx,18,0.046415888336127774,train,0.8301369863013699,0.019376894346825917,0.8255796029103466,0.020105896891973646,0.822968187091653,0.020212330314242015 +flat_mae,patch,logistic,adhd200_dx,18,0.046415888336127774,test,0.6461538461538462,0.05835237581550223,0.6336682185738789,0.060901898504657444,0.6327220077220077,0.05955890948400323 +flat_mae,patch,logistic,adhd200_dx,19,0.005994842503189409,train,0.7342465753424657,0.023251093917529858,0.7222026065328092,0.025107648106410148,0.71936252060817,0.02448171906012516 +flat_mae,patch,logistic,adhd200_dx,19,0.005994842503189409,test,0.676923076923077,0.0556149058389861,0.6500897205844656,0.06278949461980171,0.6510617760617761,0.0581088940607964 +flat_mae,patch,logistic,adhd200_dx,20,0.046415888336127774,train,0.8164383561643835,0.01983656699455529,0.8120133139619798,0.02039958710860215,0.8101147951395249,0.02041808828314482 +flat_mae,patch,logistic,adhd200_dx,20,0.046415888336127774,test,0.6,0.06022757629811748,0.5833333333333333,0.06321434966070338,0.5834942084942085,0.06150715225677129 +flat_mae,patch,logistic,adhd200_dx,21,0.005994842503189409,train,0.7232876712328767,0.022313539811577965,0.7114263125347361,0.023602411419240663,0.7089363131220614,0.02302811725694248 +flat_mae,patch,logistic,adhd200_dx,21,0.005994842503189409,test,0.676923076923077,0.05536385080836918,0.6690909090909091,0.05708448531571689,0.6684362934362934,0.05687262005512693 +flat_mae,patch,logistic,adhd200_dx,22,0.005994842503189409,train,0.7506849315068493,0.02171103561249983,0.7411650107149814,0.02297280170956314,0.7382304451364718,0.022629432840314396 +flat_mae,patch,logistic,adhd200_dx,22,0.005994842503189409,test,0.6461538461538462,0.057933967716570355,0.6375757575757576,0.059810611592933896,0.6370656370656371,0.059352360697828885 +flat_mae,patch,logistic,adhd200_dx,23,0.005994842503189409,train,0.7506849315068493,0.021302724883123517,0.74059090447591,0.02267127796447727,0.737512975514441,0.022255767801072423 +flat_mae,patch,logistic,adhd200_dx,23,0.005994842503189409,test,0.6307692307692307,0.05131816062046121,0.5962732919254659,0.05942552394330014,0.6018339768339769,0.05353518604302158 +flat_mae,patch,logistic,adhd200_dx,24,0.046415888336127774,train,0.8301369863013699,0.020081317890122796,0.8258909337108389,0.020611738407471915,0.8236856567136839,0.020580190732758345 +flat_mae,patch,logistic,adhd200_dx,24,0.046415888336127774,test,0.6923076923076923,0.05498216171185775,0.675,0.05975574700984638,0.6732625482625483,0.057047802107877174 +flat_mae,patch,logistic,adhd200_dx,25,0.046415888336127774,train,0.8493150684931506,0.01793238400064829,0.8445353096515887,0.0188129773049217,0.8406759479758198,0.018999782608589998 +flat_mae,patch,logistic,adhd200_dx,25,0.046415888336127774,test,0.6,0.061817827420431466,0.5953065134099617,0.06264512178840714,0.5965250965250966,0.06266284448641171 +flat_mae,patch,logistic,adhd200_dx,26,0.005994842503189409,train,0.7534246575342466,0.02133761951062451,0.7437277663358921,0.022545078612767288,0.7406576296024913,0.022167646313364105 +flat_mae,patch,logistic,adhd200_dx,26,0.005994842503189409,test,0.6307692307692307,0.05843338593403583,0.6153846153846154,0.061876016281656926,0.6148648648648649,0.060053755926424694 +flat_mae,patch,logistic,adhd200_dx,27,0.005994842503189409,train,0.7479452054794521,0.021005034737677033,0.7374429223744292,0.022438266332885082,0.7343683214263906,0.02205603873621063 +flat_mae,patch,logistic,adhd200_dx,27,0.005994842503189409,test,0.6,0.05705908906537516,0.588206627680312,0.05912324622632005,0.5878378378378378,0.0580308730913315 +flat_mae,patch,logistic,adhd200_dx,28,0.000774263682681127,train,0.6712328767123288,0.02353252804416413,0.6567398119122256,0.024857636203884405,0.6556451120473835,0.02415607924021646 +flat_mae,patch,logistic,adhd200_dx,28,0.000774263682681127,test,0.6,0.05108777456553742,0.5427489177489178,0.06251818322906079,0.5617760617760618,0.05300875217760594 +flat_mae,patch,logistic,adhd200_dx,29,0.005994842503189409,train,0.7479452054794521,0.022453724811895167,0.7380328278100231,0.023608165910329423,0.7350857910484215,0.02314662632377721 +flat_mae,patch,logistic,adhd200_dx,29,0.005994842503189409,test,0.5846153846153846,0.06277932799631292,0.5699583435432491,0.06534995932329632,0.5699806949806949,0.06382967672320136 +flat_mae,patch,logistic,adhd200_dx,30,0.000774263682681127,train,0.6794520547945205,0.023198219174442095,0.6672121566335476,0.024889708422481078,0.6657965439335654,0.024269085375580177 +flat_mae,patch,logistic,adhd200_dx,30,0.000774263682681127,test,0.5384615384615384,0.05653119995230366,0.5192307692307693,0.058631327442240755,0.5207528957528957,0.05716678490309635 +flat_mae,patch,logistic,adhd200_dx,31,0.046415888336127774,train,0.8465753424657534,0.018461030248356606,0.8415503875968993,0.01929171725895628,0.8375312938877695,0.01932478736770052 +flat_mae,patch,logistic,adhd200_dx,31,0.046415888336127774,test,0.6461538461538462,0.05711215997113091,0.6375757575757576,0.05906367349239588,0.6370656370656371,0.05852185384505157 +flat_mae,patch,logistic,adhd200_dx,32,0.046415888336127774,train,0.8383561643835616,0.018538607552230163,0.8344594854292062,0.019093413980078786,0.8324021493558039,0.01915258798069171 +flat_mae,patch,logistic,adhd200_dx,32,0.046415888336127774,test,0.5692307692307692,0.06604836671381156,0.5608108108108107,0.06705737113497467,0.5608108108108107,0.06674519161295112 +flat_mae,patch,logistic,adhd200_dx,33,0.3593813663804626,train,0.9534246575342465,0.01125153812382994,0.9525339453050297,0.011501658061445753,0.951563167857361,0.011807858410613761 +flat_mae,patch,logistic,adhd200_dx,33,0.3593813663804626,test,0.49230769230769234,0.06388963116511316,0.4918265813788202,0.06403702836135002,0.4975868725868726,0.06459760636125493 +flat_mae,patch,logistic,adhd200_dx,34,10000.0,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adhd200_dx,34,10000.0,test,0.49230769230769234,0.06296256049168139,0.49230769230769234,0.06338046109539525,0.5019305019305019,0.06306982066842745 +flat_mae,patch,logistic,adhd200_dx,35,0.000774263682681127,train,0.6547945205479452,0.023378132118763398,0.6297101449275362,0.025743852439678836,0.6317549001648654,0.02407235451376707 +flat_mae,patch,logistic,adhd200_dx,35,0.000774263682681127,test,0.5846153846153846,0.05541110477642887,0.5411764705882354,0.06492821500970017,0.5526061776061776,0.05754876362012925 +flat_mae,patch,logistic,adhd200_dx,36,0.046415888336127774,train,0.8438356164383561,0.018457926880885118,0.8394985535197685,0.01921824470494145,0.8365390486658119,0.01944464368542428 +flat_mae,patch,logistic,adhd200_dx,36,0.046415888336127774,test,0.6307692307692307,0.05773390090414355,0.6153846153846154,0.0608874317167682,0.6148648648648649,0.0593826335459954 +flat_mae,patch,logistic,adhd200_dx,37,0.005994842503189409,train,0.7287671232876712,0.02126369411834739,0.7157879834199825,0.02270489734052767,0.7130732124320693,0.022081166384734167 +flat_mae,patch,logistic,adhd200_dx,37,0.005994842503189409,test,0.6461538461538462,0.05383824117686007,0.6233308138070043,0.059632848965607506,0.6240347490347491,0.056114182776049605 +flat_mae,patch,logistic,adhd200_dx,38,0.005994842503189409,train,0.7643835616438356,0.022440840847929345,0.7561676609495401,0.023720808615734605,0.7532362459546925,0.023437363331484037 +flat_mae,patch,logistic,adhd200_dx,38,0.005994842503189409,test,0.6153846153846154,0.058032914553705066,0.6018132810585641,0.06053421021619187,0.6013513513513513,0.05906878076739633 +flat_mae,patch,logistic,adhd200_dx,39,0.005994842503189409,train,0.7506849315068493,0.0230574789050849,0.74059090447591,0.024351459044705596,0.737512975514441,0.02388612420360526 +flat_mae,patch,logistic,adhd200_dx,39,0.005994842503189409,test,0.6461538461538462,0.057466339002438596,0.6289401836684041,0.061401781981396744,0.6283783783783784,0.05930840383173033 +flat_mae,patch,logistic,adhd200_dx,40,0.005994842503189409,train,0.7506849315068493,0.021552915327845847,0.7417205153925708,0.022598348851612694,0.7389479147585027,0.022297513669771563 +flat_mae,patch,logistic,adhd200_dx,40,0.005994842503189409,test,0.6615384615384615,0.05589606585006491,0.6425000000000001,0.06049041346754467,0.6418918918918919,0.05775306930002199 +flat_mae,patch,logistic,adhd200_dx,41,0.000774263682681127,train,0.6712328767123288,0.023449174064527317,0.6504501053438039,0.026041455327188,0.6506228246931672,0.024551036611958656 +flat_mae,patch,logistic,adhd200_dx,41,0.000774263682681127,test,0.6153846153846154,0.05739967630776925,0.5966741126830479,0.060975104016606864,0.597007722007722,0.05855920564084475 +flat_mae,patch,logistic,adhd200_dx,42,0.046415888336127774,train,0.8356164383561644,0.018903403600079003,0.8323432141107301,0.01932960611406091,0.8314099041338463,0.019416781182385625 +flat_mae,patch,logistic,adhd200_dx,42,0.046415888336127774,test,0.5538461538461539,0.0640301334386059,0.5521501544309813,0.06397782295368544,0.555984555984556,0.06400902267862511 +flat_mae,patch,logistic,adhd200_dx,43,0.005994842503189409,train,0.7342465753424657,0.021694768578489964,0.7234870080677283,0.022931380756540005,0.7207974598522318,0.022446924464744 +flat_mae,patch,logistic,adhd200_dx,43,0.005994842503189409,test,0.6307692307692307,0.06325950311002934,0.6198830409356726,0.06531659154970372,0.6192084942084942,0.06454309418831344 +flat_mae,patch,logistic,adhd200_dx,44,0.3593813663804626,train,0.9616438356164384,0.010317752929816437,0.9606850495476088,0.010687480949632896,0.9574097820113574,0.011502910427384215 +flat_mae,patch,logistic,adhd200_dx,44,0.3593813663804626,test,0.6153846153846154,0.05962641882995496,0.606060606060606,0.06121761485256468,0.6056949806949807,0.06099210167042304 +flat_mae,patch,logistic,adhd200_dx,45,0.005994842503189409,train,0.7753424657534247,0.021833085568596908,0.7665075204393684,0.02327368850231371,0.7629449838187702,0.023021442817382387 +flat_mae,patch,logistic,adhd200_dx,45,0.005994842503189409,test,0.5076923076923077,0.05026237431906046,0.4503171247357294,0.05726468657443414,0.472007722007722,0.05082611113644956 +flat_mae,patch,logistic,adhd200_dx,46,0.3593813663804626,train,0.958904109589041,0.010521974789087271,0.9579844830364749,0.010819214227129838,0.9557000671673689,0.011320942513784555 +flat_mae,patch,logistic,adhd200_dx,46,0.3593813663804626,test,0.5538461538461539,0.05992105259738599,0.5500119360229172,0.06011169300277538,0.5516409266409266,0.06001126525823453 +flat_mae,patch,logistic,adhd200_dx,47,0.005994842503189409,train,0.7534246575342466,0.022367308530506197,0.7442863370282725,0.023755910529970687,0.7413750992245222,0.023452209927132036 +flat_mae,patch,logistic,adhd200_dx,47,0.005994842503189409,test,0.5692307692307692,0.060155813463796864,0.5512820512820513,0.06208002824792844,0.5521235521235521,0.060539724380874765 +flat_mae,patch,logistic,adhd200_dx,48,0.005994842503189409,train,0.7287671232876712,0.02262083128183851,0.7157879834199825,0.024219226412619654,0.7130732124320693,0.023522501784130744 +flat_mae,patch,logistic,adhd200_dx,48,0.005994842503189409,test,0.7230769230769231,0.056136064624083604,0.7198275862068966,0.05649990734600446,0.722007722007722,0.05636801770282752 +flat_mae,patch,logistic,adhd200_dx,49,0.046415888336127774,train,0.8383561643835616,0.01909099286658537,0.8341688420695975,0.0197756507668417,0.831684679733773,0.019916355195137268 +flat_mae,patch,logistic,adhd200_dx,49,0.046415888336127774,test,0.5538461538461539,0.06037875718766184,0.5521501544309813,0.06080838149531733,0.555984555984556,0.06164622101764491 +flat_mae,patch,logistic,adhd200_dx,50,0.005994842503189409,train,0.7287671232876712,0.023706432479170553,0.7171406429795928,0.025395781757386576,0.7145081516761311,0.024812796215785006 +flat_mae,patch,logistic,adhd200_dx,50,0.005994842503189409,test,0.6,0.05713370594517378,0.5833333333333333,0.06020123736627451,0.5834942084942085,0.05832214598327408 +flat_mae,patch,logistic,adhd200_dx,51,0.046415888336127774,train,0.852054794520548,0.018344710390857936,0.8493395707209686,0.018704952363778022,0.8488428894180864,0.018799287650957366 +flat_mae,patch,logistic,adhd200_dx,51,0.046415888336127774,test,0.5846153846153846,0.061061683818653664,0.5810455956075435,0.06161775160752307,0.583011583011583,0.0621509669707407 +flat_mae,patch,logistic,adhd200_dx,52,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adhd200_dx,52,1291.5496650148827,test,0.6615384615384615,0.056437001585209985,0.6515594541910331,0.05868769223654657,0.6505791505791505,0.058097473749193454 +flat_mae,patch,logistic,adhd200_dx,53,0.005994842503189409,train,0.7616438356164383,0.02252041462480952,0.7530734597709193,0.023671987107552472,0.7500915918666422,0.02336468310555691 +flat_mae,patch,logistic,adhd200_dx,53,0.005994842503189409,test,0.6,0.055021579413748495,0.5626293995859213,0.06274989197371136,0.5704633204633205,0.056964707788190724 +flat_mae,patch,logistic,adhd200_dx,54,0.000774263682681127,train,0.6904109589041096,0.02310345120721942,0.6812128519643534,0.024085525667857523,0.6798100995298284,0.023797417756659032 +flat_mae,patch,logistic,adhd200_dx,54,0.000774263682681127,test,0.47692307692307695,0.061873120795084155,0.4551282051282051,0.06358886497545307,0.45801158301158307,0.062157727507646976 +flat_mae,patch,logistic,adhd200_dx,55,0.005994842503189409,train,0.7616438356164383,0.022442422900744146,0.7530734597709193,0.023653828260845673,0.7500915918666422,0.023442196926047855 +flat_mae,patch,logistic,adhd200_dx,55,0.005994842503189409,test,0.6,0.059277376268506585,0.5953065134099617,0.06003196231924114,0.5965250965250966,0.06027547488002844 +flat_mae,patch,logistic,adhd200_dx,56,0.005994842503189409,train,0.7095890410958904,0.022176893365888326,0.6967868338557994,0.023524462939330817,0.6946479819258716,0.022925403991899865 +flat_mae,patch,logistic,adhd200_dx,56,0.005994842503189409,test,0.6153846153846154,0.06007477785985765,0.606060606060606,0.06150401464554483,0.6056949806949807,0.06098286998803646 +flat_mae,patch,logistic,adhd200_dx,57,0.005994842503189409,train,0.7561643835616438,0.022063811651094358,0.7468536917981687,0.023300892505400937,0.7438022836905416,0.02294411112254093 +flat_mae,patch,logistic,adhd200_dx,57,0.005994842503189409,test,0.5692307692307692,0.057907814926707414,0.545,0.0616079501698831,0.5477799227799228,0.058791910500438645 +flat_mae,patch,logistic,adhd200_dx,58,0.005994842503189409,train,0.7753424657534247,0.02049162399997868,0.7688874474919694,0.02134046882387648,0.7665323319289247,0.021313506645198262 +flat_mae,patch,logistic,adhd200_dx,58,0.005994842503189409,test,0.6153846153846154,0.05986022377616496,0.6094688776736361,0.06059810015911256,0.61003861003861,0.06039242814947532 +flat_mae,patch,logistic,adhd200_dx,59,0.005994842503189409,train,0.7616438356164383,0.02187443585311201,0.7519935020813646,0.02307715591515561,0.7486566526225804,0.022660094435277285 +flat_mae,patch,logistic,adhd200_dx,59,0.005994842503189409,test,0.5538461538461539,0.060067023709170955,0.543030303030303,0.06173741501884506,0.542953667953668,0.061100600224087594 +flat_mae,patch,logistic,adhd200_dx,60,0.005994842503189409,train,0.7616438356164383,0.021602840315607403,0.7535869759212843,0.02253386150969037,0.7508090614886731,0.02223436214079548 +flat_mae,patch,logistic,adhd200_dx,60,0.005994842503189409,test,0.6307692307692307,0.05952117419469136,0.6153846153846154,0.06250793951211188,0.6148648648648649,0.06087780255379145 +flat_mae,patch,logistic,adhd200_dx,61,0.005994842503189409,train,0.7424657534246575,0.023157916678702543,0.732337889284154,0.024367230240169596,0.7295139524943518,0.023953898162363384 +flat_mae,patch,logistic,adhd200_dx,61,0.005994842503189409,test,0.5846153846153846,0.0593101486072211,0.5644080416976918,0.06272747681976858,0.5656370656370656,0.06063885889226721 +flat_mae,patch,logistic,adhd200_dx,62,0.3593813663804626,train,0.9534246575342465,0.011205022598450588,0.9524597574336697,0.011483280667382797,0.95084569823533,0.011861593656228292 +flat_mae,patch,logistic,adhd200_dx,62,0.3593813663804626,test,0.49230769230769234,0.061131539231049914,0.4918265813788202,0.061499482042368124,0.4975868725868726,0.0624962052186472 +flat_mae,patch,logistic,adhd200_dx,63,0.005994842503189409,train,0.7506849315068493,0.02313272806058256,0.7422576414808837,0.024332954278679233,0.7396653843805336,0.024162195121165776 +flat_mae,patch,logistic,adhd200_dx,63,0.005994842503189409,test,0.5846153846153846,0.05799427843641946,0.5699583435432491,0.06006157500353187,0.5699806949806949,0.05888497869797474 +flat_mae,patch,logistic,adhd200_dx,64,0.005994842503189409,train,0.7397260273972602,0.021260347408431284,0.7285693038693062,0.022610588577683163,0.7256518287842706,0.02213105331843909 +flat_mae,patch,logistic,adhd200_dx,64,0.005994842503189409,test,0.7076923076923077,0.054275702061968085,0.6934723256391164,0.058268355925866454,0.6911196911196911,0.05621078703888354 +flat_mae,patch,logistic,adhd200_dx,65,0.005994842503189409,train,0.7479452054794521,0.021150272549035388,0.7348891555611696,0.022877015662771533,0.731498442938267,0.02222356231659625 +flat_mae,patch,logistic,adhd200_dx,65,0.005994842503189409,test,0.6923076923076923,0.0569473461777315,0.6794871794871795,0.06061295739590483,0.6776061776061776,0.0590761323383148 +flat_mae,patch,logistic,adhd200_dx,66,0.000774263682681127,train,0.6876712328767123,0.024311149365807097,0.6731240573152337,0.025922625882424156,0.6716431580875618,0.02511791344768796 +flat_mae,patch,logistic,adhd200_dx,66,0.000774263682681127,test,0.6615384615384615,0.05634970269737757,0.6515594541910331,0.05799078242744701,0.6505791505791505,0.057331952554935915 +flat_mae,patch,logistic,adhd200_dx,67,0.046415888336127774,train,0.8301369863013699,0.019998621832794106,0.8264783462151883,0.02056085210753423,0.8251205959577457,0.020708726154669243 +flat_mae,patch,logistic,adhd200_dx,67,0.046415888336127774,test,0.5846153846153846,0.0637962659588777,0.5745454545454545,0.06566186760577263,0.5743243243243243,0.06486931534505905 +flat_mae,patch,logistic,adhd200_dx,68,0.005994842503189409,train,0.7452054794520548,0.023088121672343007,0.7330129541218018,0.02485483127104554,0.7297887280942785,0.024185682855589884 +flat_mae,patch,logistic,adhd200_dx,68,0.005994842503189409,test,0.6923076923076923,0.05498071528503824,0.6697154471544715,0.06162827691928485,0.6689189189189189,0.0577167290751472 +flat_mae,patch,logistic,adhd200_dx,69,0.000774263682681127,train,0.6931506849315069,0.02292343092764397,0.6810834425513325,0.024229820828409392,0.6793674055077242,0.023713774816032773 +flat_mae,patch,logistic,adhd200_dx,69,0.000774263682681127,test,0.5230769230769231,0.06147227209633942,0.5115151515151515,0.06256879605084496,0.5115830115830116,0.06200599402814998 +flat_mae,patch,logistic,adhd200_dx,70,0.005994842503189409,train,0.7534246575342466,0.021565816727324105,0.7431506849315068,0.023058692789243444,0.7399401599804604,0.022679154408084427 +flat_mae,patch,logistic,adhd200_dx,70,0.005994842503189409,test,0.5384615384615384,0.06306670836615791,0.5294401544401545,0.06463679991909065,0.5294401544401545,0.06421257227882796 +flat_mae,patch,logistic,adhd200_dx,71,0.000774263682681127,train,0.6904109589041096,0.023252988839299625,0.6747880938300808,0.025024154323342505,0.6733528729315503,0.02412632613293302 +flat_mae,patch,logistic,adhd200_dx,71,0.000774263682681127,test,0.5538461538461539,0.058035133207312725,0.5167905665214048,0.06312983552887898,0.5255791505791506,0.05868344241649786 +flat_mae,patch,logistic,adhd200_dx,72,0.005994842503189409,train,0.7424657534246575,0.02279957465043911,0.7329212853406402,0.023907340160393583,0.7302314221163827,0.023521733044468605 +flat_mae,patch,logistic,adhd200_dx,72,0.005994842503189409,test,0.6615384615384615,0.05558922887452124,0.6474358974358974,0.05865705490069454,0.6462355212355213,0.056987625719098906 +flat_mae,patch,logistic,adhd200_dx,73,0.000774263682681127,train,0.6767123287671233,0.023994291558561594,0.6581746031746032,0.025919587832765406,0.6576296024912988,0.024762976105278195 +flat_mae,patch,logistic,adhd200_dx,73,0.000774263682681127,test,0.5384615384615384,0.060705126851325356,0.5045731707317074,0.06532552065358074,0.5120656370656371,0.06158759120327949 +flat_mae,patch,logistic,adhd200_dx,74,10000.0,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adhd200_dx,74,10000.0,test,0.5230769230769231,0.05813231998827274,0.5189782764382908,0.060554235504142545,0.5463320463320464,0.05790707675862508 +flat_mae,patch,logistic,adhd200_dx,75,0.046415888336127774,train,0.8602739726027397,0.017812898015490474,0.8563934426229508,0.018456717701152522,0.853254564328021,0.0185496621456346 +flat_mae,patch,logistic,adhd200_dx,75,0.046415888336127774,test,0.5076923076923077,0.06424641172951484,0.5019157088122606,0.06486328020070385,0.5024131274131274,0.06518211335666634 +flat_mae,patch,logistic,adhd200_dx,76,0.005994842503189409,train,0.7534246575342466,0.021956811871031642,0.7419400452488687,0.02355108404949059,0.7385052207363986,0.02294544130902653 +flat_mae,patch,logistic,adhd200_dx,76,0.005994842503189409,test,0.5692307692307692,0.051239999168548975,0.5075757575757576,0.060905811709938536,0.5304054054054055,0.0521888730822872 +flat_mae,patch,logistic,adhd200_dx,77,0.005994842503189409,train,0.726027397260274,0.022170694531362847,0.7125622125622125,0.024086929724322442,0.709928558344019,0.023310947318610588 +flat_mae,patch,logistic,adhd200_dx,77,0.005994842503189409,test,0.6615384615384615,0.05096276399106968,0.622093023255814,0.06318531787761687,0.6288610038610039,0.054214489390002805 +flat_mae,patch,logistic,adhd200_dx,78,0.046415888336127774,train,0.8191780821917808,0.01948726968728278,0.8143266740658528,0.02021720810077057,0.8118245099835135,0.020332351650457534 +flat_mae,patch,logistic,adhd200_dx,78,0.046415888336127774,test,0.6153846153846154,0.05863940553635247,0.5966741126830479,0.06195026725201978,0.597007722007722,0.05981558237703973 +flat_mae,patch,logistic,adhd200_dx,79,0.005994842503189409,train,0.7534246575342466,0.021420848205650087,0.7442863370282725,0.022623511376017525,0.7413750992245222,0.02232421710042233 +flat_mae,patch,logistic,adhd200_dx,79,0.005994842503189409,test,0.6,0.06022263232196831,0.5921814671814671,0.061955156733891154,0.5921814671814671,0.06185160797579859 +flat_mae,patch,logistic,adhd200_dx,80,0.000774263682681127,train,0.6876712328767123,0.022277796433305814,0.6714930840649277,0.023903213084920456,0.6702082188435,0.02302946313263851 +flat_mae,patch,logistic,adhd200_dx,80,0.000774263682681127,test,0.5384615384615384,0.05988766604551139,0.5125,0.06283700979082794,0.5164092664092664,0.060547466150965935 +flat_mae,patch,logistic,adhd200_dx,81,0.046415888336127774,train,0.8493150684931506,0.018744162736831504,0.8454116324377604,0.019345664811399783,0.8428283568419125,0.019438154310482125 +flat_mae,patch,logistic,adhd200_dx,81,0.046415888336127774,test,0.5538461538461539,0.05642626439531034,0.5250692869740489,0.0605464686790807,0.5299227799227799,0.057376481254745745 +flat_mae,patch,logistic,adhd200_dx,82,0.046415888336127774,train,0.8356164383561644,0.018387133964814773,0.8308932542624166,0.019172680562063952,0.8278225560236918,0.01931803088685524 +flat_mae,patch,logistic,adhd200_dx,82,0.046415888336127774,test,0.6307692307692307,0.05714799638766228,0.6306818181818181,0.05733017633384551,0.640926640926641,0.05717991422082825 +flat_mae,patch,logistic,adhd200_dx,83,0.005994842503189409,train,0.7452054794520548,0.022190698434621785,0.7365929742606834,0.023255465027498496,0.7340935458264639,0.02300396621813848 +flat_mae,patch,logistic,adhd200_dx,83,0.005994842503189409,test,0.6461538461538462,0.0553125941980945,0.6233308138070043,0.06052316685767508,0.6240347490347491,0.05718663618122895 +flat_mae,patch,logistic,adhd200_dx,84,0.005994842503189409,train,0.7397260273972602,0.021609194404055617,0.7291883068704555,0.022792737119227635,0.7263692984063015,0.022318528029244958 +flat_mae,patch,logistic,adhd200_dx,84,0.005994842503189409,test,0.6461538461538462,0.06040005486105898,0.6431129147767964,0.06108818628152491,0.6457528957528957,0.061476506133144926 +flat_mae,patch,logistic,adhd200_dx,85,0.005994842503189409,train,0.7342465753424657,0.022776270354782854,0.7234870080677283,0.024259987424525238,0.7207974598522318,0.023799498683182714 +flat_mae,patch,logistic,adhd200_dx,85,0.005994842503189409,test,0.6461538461538462,0.05922157770840109,0.6289401836684041,0.06247336516095856,0.6283783783783784,0.06043540615491193 +flat_mae,patch,logistic,adhd200_dx,86,0.005994842503189409,train,0.7479452054794521,0.02258475398978552,0.7374429223744292,0.024189697099051957,0.7343683214263906,0.023749482759430524 +flat_mae,patch,logistic,adhd200_dx,86,0.005994842503189409,test,0.5538461538461539,0.05919580186617866,0.5167905665214048,0.06498504424494862,0.5255791505791506,0.06036567541679717 +flat_mae,patch,logistic,adhd200_dx,87,0.046415888336127774,train,0.8246575342465754,0.018962517669722928,0.8202745122176403,0.01950550494601728,0.8181138181596141,0.019500544172068698 +flat_mae,patch,logistic,adhd200_dx,87,0.046415888336127774,test,0.6,0.06265941373949739,0.5921814671814671,0.0641847335495413,0.5921814671814671,0.06390811494969031 +flat_mae,patch,logistic,adhd200_dx,88,0.005994842503189409,train,0.7589041095890411,0.022332662236948016,0.7504971414367387,0.023581551904764866,0.7476644074006228,0.023390465024393525 +flat_mae,patch,logistic,adhd200_dx,88,0.005994842503189409,test,0.6307692307692307,0.05931263074321079,0.6198830409356726,0.062012785691306374,0.6192084942084942,0.06111178524565383 +flat_mae,patch,logistic,adhd200_dx,89,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adhd200_dx,89,2.782559402207126,test,0.5230769230769231,0.06044383377500237,0.5226249703861644,0.06063694357749275,0.528957528957529,0.06086927889562604 +flat_mae,patch,logistic,adhd200_dx,90,0.005994842503189409,train,0.7479452054794521,0.02271038939453685,0.7396899224806202,0.023718645620428535,0.7372381999145142,0.02346247839415891 +flat_mae,patch,logistic,adhd200_dx,90,0.005994842503189409,test,0.6307692307692307,0.05761632740319321,0.6036585365853658,0.06474643703406564,0.6061776061776062,0.05994124927917422 +flat_mae,patch,logistic,adhd200_dx,91,0.005994842503189409,train,0.7424657534246575,0.021080869941737912,0.7317351598173516,0.022329848868593957,0.7287964828723209,0.02189250729524996 +flat_mae,patch,logistic,adhd200_dx,91,0.005994842503189409,test,0.5846153846153846,0.05466285261145179,0.5501153550371699,0.060180216643763204,0.556949806949807,0.055798123705704354 +flat_mae,patch,logistic,adhd200_dx,92,0.005994842503189409,train,0.7424657534246575,0.0201252329878386,0.7298084798084798,0.02161725700315579,0.7266440740062282,0.020986877231903383 +flat_mae,patch,logistic,adhd200_dx,92,0.005994842503189409,test,0.6153846153846154,0.06074020728533192,0.5905769715293525,0.06587685167014463,0.5926640926640927,0.062491824862990666 +flat_mae,patch,logistic,adhd200_dx,93,0.005994842503189409,train,0.7506849315068493,0.02161823976382027,0.7393859504586148,0.02308236879496513,0.7360780362703792,0.022608038225131195 +flat_mae,patch,logistic,adhd200_dx,93,0.005994842503189409,test,0.6461538461538462,0.052271652742890896,0.6091503267973856,0.06194623854594414,0.6153474903474904,0.05487389457611892 +flat_mae,patch,logistic,adhd200_dx,94,0.046415888336127774,train,0.8438356164383561,0.01846918711215993,0.839195863380249,0.019345394626395566,0.835821579043781,0.01960006732020828 +flat_mae,patch,logistic,adhd200_dx,94,0.046415888336127774,test,0.5076923076923077,0.05614776784805898,0.4616977225672878,0.061435638906790144,0.47635135135135137,0.056481173224446624 +flat_mae,patch,logistic,adhd200_dx,95,0.046415888336127774,train,0.8465753424657534,0.01959520087078588,0.8424589961770872,0.02032807015247886,0.8396837027538622,0.020495574095677677 +flat_mae,patch,logistic,adhd200_dx,95,0.046415888336127774,test,0.5846153846153846,0.058711820528940216,0.5699583435432491,0.06092017244319253,0.5699806949806949,0.05976638067584281 +flat_mae,patch,logistic,adhd200_dx,96,0.046415888336127774,train,0.8493150684931506,0.01940784170792324,0.8451301832208293,0.020249438961303302,0.8421108872198816,0.020528669748107055 +flat_mae,patch,logistic,adhd200_dx,96,0.046415888336127774,test,0.6307692307692307,0.059057841469641055,0.6235521235521235,0.06051403748733361,0.6235521235521235,0.06037007413681276 +flat_mae,patch,logistic,adhd200_dx,97,0.046415888336127774,train,0.8575342465753425,0.018367413441327994,0.8534408203607611,0.019198689748866304,0.8501099102399707,0.019459464666499733 +flat_mae,patch,logistic,adhd200_dx,97,0.046415888336127774,test,0.5538461538461539,0.055751426335669096,0.5167905665214048,0.06119495371182997,0.5255791505791506,0.05655198334771486 +flat_mae,patch,logistic,adhd200_dx,98,0.005994842503189409,train,0.7424657534246575,0.021598614802369204,0.7304707139265962,0.022981902209253013,0.7273615436282591,0.022407907856137853 +flat_mae,patch,logistic,adhd200_dx,98,0.005994842503189409,test,0.676923076923077,0.05730562515631614,0.656084656084656,0.06246366726281485,0.6554054054054055,0.05912137656556257 +flat_mae,patch,logistic,adhd200_dx,99,0.000774263682681127,train,0.6904109589041096,0.024256313190441657,0.680590727102355,0.025328575249602598,0.6790926299077975,0.02502258771349295 +flat_mae,patch,logistic,adhd200_dx,99,0.000774263682681127,test,0.5384615384615384,0.06160288166624836,0.5192307692307693,0.06501446501173067,0.5207528957528957,0.06270190103852319 +flat_mae,patch,logistic,adhd200_dx,100,0.005994842503189409,train,0.7534246575342466,0.022364094081184206,0.7419400452488687,0.02398094407282536,0.7385052207363986,0.02338338345151954 +flat_mae,patch,logistic,adhd200_dx,100,0.005994842503189409,test,0.6461538461538462,0.053772256985380254,0.6167649320687003,0.060701259422197985,0.6196911196911197,0.05605330829498735 diff --git a/input_space_v3/flat_lr1e-3_6/eval_v2/adhd200_dx__patch__logistic/log.txt b/input_space_v3/flat_lr1e-3_6/eval_v2/adhd200_dx__patch__logistic/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..1f60347d0865193ec261eb87ffc98fbbdc032214 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_6/eval_v2/adhd200_dx__patch__logistic/log.txt @@ -0,0 +1,241 @@ +fMRI foundation model logistic probe eval +version: 0.1.dev86+gf97f52698 +sha: bcce2b486277d3a5b520775efd9cdf1a2affce36, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-04-08 22:53:34 +config: +output_root: experiments/input_space_v3/output +name_prefix: eval_logistic +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_6; eval v2 (adhd200_dx patch logistic) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: input_space_v3/flat_lr1e-3_6/eval_v2/adhd200_dx__patch__logistic +model: flat_mae +representation: patch +dataset: adhd200_dx +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/eval_v2/adhd200_dx__patch__logistic +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=True, reg_tokens=0, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: adhd200_dx (flat) +train (n=301): +HFDataset( + dataset=Dataset({ + features: ['sub', 'site', 'gender', 'dx', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 301 +}), + labels=['ADHD' 'Control'], + counts=[131 170] +) + +validation (n=64): +HFDataset( + dataset=Dataset({ + features: ['sub', 'site', 'gender', 'dx', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 64 +}), + labels=['ADHD' 'Control'], + counts=[28 36] +) + +test (n=65): +HFDataset( + dataset=Dataset({ + features: ['sub', 'site', 'gender', 'dx', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 65 +}), + labels=['ADHD' 'Control'], + counts=[28 37] +) + +extracting features for all splits +extract (train) [ 0/151] eta: 0:10:25 time: 4.1411 data: 3.4865 max mem: 2698 +extract (train) [ 20/151] eta: 0:00:49 time: 0.1916 data: 0.0684 max mem: 2851 +extract (train) [ 40/151] eta: 0:00:30 time: 0.1698 data: 0.0570 max mem: 2851 +extract (train) [ 60/151] eta: 0:00:21 time: 0.1469 data: 0.0454 max mem: 2851 +extract (train) [ 80/151] eta: 0:00:15 time: 0.1650 data: 0.0553 max mem: 2851 +extract (train) [100/151] eta: 0:00:10 time: 0.1677 data: 0.0558 max mem: 2851 +extract (train) [120/151] eta: 0:00:06 time: 0.1614 data: 0.0523 max mem: 2851 +extract (train) [140/151] eta: 0:00:02 time: 0.1440 data: 0.0436 max mem: 2851 +extract (train) [150/151] eta: 0:00:00 time: 0.1492 data: 0.0480 max mem: 2851 +extract (train) Total time: 0:00:29 (0.1922 s / it) +extract (validation) [ 0/32] eta: 0:02:03 time: 3.8496 data: 3.6882 max mem: 2851 +extract (validation) [20/32] eta: 0:00:04 time: 0.1714 data: 0.0521 max mem: 2851 +extract (validation) [31/32] eta: 0:00:00 time: 0.1303 data: 0.0316 max mem: 2851 +extract (validation) Total time: 0:00:08 (0.2801 s / it) +extract (test) [ 0/33] eta: 0:02:04 time: 3.7610 data: 3.5645 max mem: 2851 +extract (test) [20/33] eta: 0:00:04 time: 0.1647 data: 0.0477 max mem: 2851 +extract (test) [32/33] eta: 0:00:00 time: 0.1299 data: 0.0324 max mem: 2851 +extract (test) Total time: 0:00:08 (0.2701 s / it) +feature extraction time: 0:00:46 +train features: (301, 768) +validation features: (64, 768) +test features: (65, 768) +evaluating fixed splits +eval results (fixed splits): + +| model | repr | clf | dataset | trial | C | split | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:-----------|:--------|-----------:|:--------|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | adhd200_dx | | 0.00077426 | train | 0.68219 | 0.023528 | 0.66739 | 0.025231 | 0.66607 | 0.024411 | +| flat_mae | patch | logistic | adhd200_dx | | 0.00077426 | test | 0.56923 | 0.060649 | 0.545 | 0.06546 | 0.54778 | 0.062334 | + + +evaluating random splits (n=100) +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 1, "C": 0.046415888336127774, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.06379096038796511, "f1": 0.5248538011695907, "f1_std": 0.06504972264506238, "bacc": 0.525096525096525, "bacc_std": 0.06414061229081829} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 2, "C": 0.046415888336127774, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.05900292641423632, "f1": 0.6153846153846154, "f1_std": 0.062253990162742384, "bacc": 0.6148648648648649, "bacc_std": 0.060437897852586187} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 3, "C": 0.005994842503189409, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.05808921112998645, "f1": 0.5192307692307693, "f1_std": 0.06129904701798908, "bacc": 0.5207528957528957, "bacc_std": 0.05932643900449705} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 4, "C": 0.005994842503189409, "split": "test", "acc": 0.6461538461538462, "acc_std": 0.0541291814460894, "f1": 0.6375757575757576, "f1_std": 0.056077987384371177, "bacc": 0.6370656370656371, "bacc_std": 0.0557584919473334} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 5, "C": 0.005994842503189409, "split": "test", "acc": 0.49230769230769234, "acc_std": 0.06131216854617294, "f1": 0.49037776193870275, "f1_std": 0.06161975717131911, "bacc": 0.49324324324324326, "bacc_std": 0.06284104395352116} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 6, "C": 0.005994842503189409, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.057145304258675256, "f1": 0.61, "f1_std": 0.062210675490069936, "bacc": 0.6105212355212355, "bacc_std": 0.059256732535068926} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 7, "C": 0.046415888336127774, "split": "test", "acc": 0.6461538461538462, "acc_std": 0.0562750977539705, "f1": 0.6375757575757576, "f1_std": 0.05758125135408943, "bacc": 0.6370656370656371, "bacc_std": 0.057115289276165306} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 8, "C": 0.046415888336127774, "split": "test", "acc": 0.6, "acc_std": 0.06092571089877171, "f1": 0.5833333333333333, "f1_std": 0.06434671824032219, "bacc": 0.5834942084942085, "bacc_std": 0.062509136576709} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 9, "C": 0.005994842503189409, "split": "test", "acc": 0.6461538461538462, "acc_std": 0.05974319005038524, "f1": 0.6289401836684041, "f1_std": 0.06381283947778622, "bacc": 0.6283783783783784, "bacc_std": 0.06161501676018539} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 10, "C": 0.3593813663804626, "split": "test", "acc": 0.49230769230769234, "acc_std": 0.06280646708494521, "f1": 0.48000000000000004, "f1_std": 0.0639852187712292, "bacc": 0.48021235521235517, "bacc_std": 0.06355140174291135} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 11, "C": 0.005994842503189409, "split": "test", "acc": 0.5538461538461539, "acc_std": 0.05815094823874403, "f1": 0.5321419707123356, "f1_std": 0.06168330629898703, "bacc": 0.5342664092664092, "bacc_std": 0.05927685420864215} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 12, "C": 0.046415888336127774, "split": "test", "acc": 0.5230769230769231, "acc_std": 0.05794998864048165, "f1": 0.49987589972697943, "f1_std": 0.061304328228338555, "bacc": 0.502895752895753, "bacc_std": 0.05899291324516247} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 13, "C": 0.046415888336127774, "split": "test", "acc": 0.5538461538461539, "acc_std": 0.058819398643685, "f1": 0.543030303030303, "f1_std": 0.059912409726456575, "bacc": 0.542953667953668, "bacc_std": 0.05951531824369584} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 14, "C": 0.000774263682681127, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.05500122860381388, "f1": 0.5501153550371699, "f1_std": 0.06161642754086492, "bacc": 0.556949806949807, "bacc_std": 0.05652938408111811} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 15, "C": 0.005994842503189409, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.059615334987572405, "f1": 0.6094688776736361, "f1_std": 0.06041576546176785, "bacc": 0.61003861003861, "bacc_std": 0.06056459940349946} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 16, "C": 0.005994842503189409, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.059487865601701946, "f1": 0.5699583435432491, "f1_std": 0.06199535660693942, "bacc": 0.5699806949806949, "bacc_std": 0.06060371528838815} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 17, "C": 0.005994842503189409, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.06145027527489968, "f1": 0.5644080416976918, "f1_std": 0.06462685130494607, "bacc": 0.5656370656370656, "bacc_std": 0.06247240242057693} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 18, "C": 0.046415888336127774, "split": "test", "acc": 0.6461538461538462, "acc_std": 0.05835237581550223, "f1": 0.6336682185738789, "f1_std": 0.060901898504657444, "bacc": 0.6327220077220077, "bacc_std": 0.05955890948400323} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 19, "C": 0.005994842503189409, "split": "test", "acc": 0.676923076923077, "acc_std": 0.0556149058389861, "f1": 0.6500897205844656, "f1_std": 0.06278949461980171, "bacc": 0.6510617760617761, "bacc_std": 0.0581088940607964} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 20, "C": 0.046415888336127774, "split": "test", "acc": 0.6, "acc_std": 0.06022757629811748, "f1": 0.5833333333333333, "f1_std": 0.06321434966070338, "bacc": 0.5834942084942085, "bacc_std": 0.06150715225677129} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 21, "C": 0.005994842503189409, "split": "test", "acc": 0.676923076923077, "acc_std": 0.05536385080836918, "f1": 0.6690909090909091, "f1_std": 0.05708448531571689, "bacc": 0.6684362934362934, "bacc_std": 0.05687262005512693} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 22, "C": 0.005994842503189409, "split": "test", "acc": 0.6461538461538462, "acc_std": 0.057933967716570355, "f1": 0.6375757575757576, "f1_std": 0.059810611592933896, "bacc": 0.6370656370656371, "bacc_std": 0.059352360697828885} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 23, "C": 0.005994842503189409, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.05131816062046121, "f1": 0.5962732919254659, "f1_std": 0.05942552394330014, "bacc": 0.6018339768339769, "bacc_std": 0.05353518604302158} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 24, "C": 0.046415888336127774, "split": "test", "acc": 0.6923076923076923, "acc_std": 0.05498216171185775, "f1": 0.675, "f1_std": 0.05975574700984638, "bacc": 0.6732625482625483, "bacc_std": 0.057047802107877174} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 25, "C": 0.046415888336127774, "split": "test", "acc": 0.6, "acc_std": 0.061817827420431466, "f1": 0.5953065134099617, "f1_std": 0.06264512178840714, "bacc": 0.5965250965250966, "bacc_std": 0.06266284448641171} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 26, "C": 0.005994842503189409, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.05843338593403583, "f1": 0.6153846153846154, "f1_std": 0.061876016281656926, "bacc": 0.6148648648648649, "bacc_std": 0.060053755926424694} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 27, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.05705908906537516, "f1": 0.588206627680312, "f1_std": 0.05912324622632005, "bacc": 0.5878378378378378, "bacc_std": 0.0580308730913315} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 28, "C": 0.000774263682681127, "split": "test", "acc": 0.6, "acc_std": 0.05108777456553742, "f1": 0.5427489177489178, "f1_std": 0.06251818322906079, "bacc": 0.5617760617760618, "bacc_std": 0.05300875217760594} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 29, "C": 0.005994842503189409, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.06277932799631292, "f1": 0.5699583435432491, "f1_std": 0.06534995932329632, "bacc": 0.5699806949806949, "bacc_std": 0.06382967672320136} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 30, "C": 0.000774263682681127, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.05653119995230366, "f1": 0.5192307692307693, "f1_std": 0.058631327442240755, "bacc": 0.5207528957528957, "bacc_std": 0.05716678490309635} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 31, "C": 0.046415888336127774, "split": "test", "acc": 0.6461538461538462, "acc_std": 0.05711215997113091, "f1": 0.6375757575757576, "f1_std": 0.05906367349239588, "bacc": 0.6370656370656371, "bacc_std": 0.05852185384505157} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 32, "C": 0.046415888336127774, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.06604836671381156, "f1": 0.5608108108108107, "f1_std": 0.06705737113497467, "bacc": 0.5608108108108107, "bacc_std": 0.06674519161295112} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 33, "C": 0.3593813663804626, "split": "test", "acc": 0.49230769230769234, "acc_std": 0.06388963116511316, "f1": 0.4918265813788202, "f1_std": 0.06403702836135002, "bacc": 0.4975868725868726, "bacc_std": 0.06459760636125493} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 34, "C": 10000.0, "split": "test", "acc": 0.49230769230769234, "acc_std": 0.06296256049168139, "f1": 0.49230769230769234, "f1_std": 0.06338046109539525, "bacc": 0.5019305019305019, "bacc_std": 0.06306982066842745} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 35, "C": 0.000774263682681127, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.05541110477642887, "f1": 0.5411764705882354, "f1_std": 0.06492821500970017, "bacc": 0.5526061776061776, "bacc_std": 0.05754876362012925} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 36, "C": 0.046415888336127774, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.05773390090414355, "f1": 0.6153846153846154, "f1_std": 0.0608874317167682, "bacc": 0.6148648648648649, "bacc_std": 0.0593826335459954} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 37, "C": 0.005994842503189409, "split": "test", "acc": 0.6461538461538462, "acc_std": 0.05383824117686007, "f1": 0.6233308138070043, "f1_std": 0.059632848965607506, "bacc": 0.6240347490347491, "bacc_std": 0.056114182776049605} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 38, "C": 0.005994842503189409, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.058032914553705066, "f1": 0.6018132810585641, "f1_std": 0.06053421021619187, "bacc": 0.6013513513513513, "bacc_std": 0.05906878076739633} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 39, "C": 0.005994842503189409, "split": "test", "acc": 0.6461538461538462, "acc_std": 0.057466339002438596, "f1": 0.6289401836684041, "f1_std": 0.061401781981396744, "bacc": 0.6283783783783784, "bacc_std": 0.05930840383173033} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 40, "C": 0.005994842503189409, "split": "test", "acc": 0.6615384615384615, "acc_std": 0.05589606585006491, "f1": 0.6425000000000001, "f1_std": 0.06049041346754467, "bacc": 0.6418918918918919, "bacc_std": 0.05775306930002199} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 41, "C": 0.000774263682681127, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.05739967630776925, "f1": 0.5966741126830479, "f1_std": 0.060975104016606864, "bacc": 0.597007722007722, "bacc_std": 0.05855920564084475} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 42, "C": 0.046415888336127774, "split": "test", "acc": 0.5538461538461539, "acc_std": 0.0640301334386059, "f1": 0.5521501544309813, "f1_std": 0.06397782295368544, "bacc": 0.555984555984556, "bacc_std": 0.06400902267862511} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 43, "C": 0.005994842503189409, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.06325950311002934, "f1": 0.6198830409356726, "f1_std": 0.06531659154970372, "bacc": 0.6192084942084942, "bacc_std": 0.06454309418831344} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 44, "C": 0.3593813663804626, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.05962641882995496, "f1": 0.606060606060606, "f1_std": 0.06121761485256468, "bacc": 0.6056949806949807, "bacc_std": 0.06099210167042304} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 45, "C": 0.005994842503189409, "split": "test", "acc": 0.5076923076923077, "acc_std": 0.05026237431906046, "f1": 0.4503171247357294, "f1_std": 0.05726468657443414, "bacc": 0.472007722007722, "bacc_std": 0.05082611113644956} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 46, "C": 0.3593813663804626, "split": "test", "acc": 0.5538461538461539, "acc_std": 0.05992105259738599, "f1": 0.5500119360229172, "f1_std": 0.06011169300277538, "bacc": 0.5516409266409266, "bacc_std": 0.06001126525823453} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 47, "C": 0.005994842503189409, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.060155813463796864, "f1": 0.5512820512820513, "f1_std": 0.06208002824792844, "bacc": 0.5521235521235521, "bacc_std": 0.060539724380874765} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 48, "C": 0.005994842503189409, "split": "test", "acc": 0.7230769230769231, "acc_std": 0.056136064624083604, "f1": 0.7198275862068966, "f1_std": 0.05649990734600446, "bacc": 0.722007722007722, "bacc_std": 0.05636801770282752} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 49, "C": 0.046415888336127774, "split": "test", "acc": 0.5538461538461539, "acc_std": 0.06037875718766184, "f1": 0.5521501544309813, "f1_std": 0.06080838149531733, "bacc": 0.555984555984556, "bacc_std": 0.06164622101764491} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 50, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.05713370594517378, "f1": 0.5833333333333333, "f1_std": 0.06020123736627451, "bacc": 0.5834942084942085, "bacc_std": 0.05832214598327408} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 51, "C": 0.046415888336127774, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.061061683818653664, "f1": 0.5810455956075435, "f1_std": 0.06161775160752307, "bacc": 0.583011583011583, "bacc_std": 0.0621509669707407} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 52, "C": 1291.5496650148827, "split": "test", "acc": 0.6615384615384615, "acc_std": 0.056437001585209985, "f1": 0.6515594541910331, "f1_std": 0.05868769223654657, "bacc": 0.6505791505791505, "bacc_std": 0.058097473749193454} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 53, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.055021579413748495, "f1": 0.5626293995859213, "f1_std": 0.06274989197371136, "bacc": 0.5704633204633205, "bacc_std": 0.056964707788190724} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 54, "C": 0.000774263682681127, "split": "test", "acc": 0.47692307692307695, "acc_std": 0.061873120795084155, "f1": 0.4551282051282051, "f1_std": 0.06358886497545307, "bacc": 0.45801158301158307, "bacc_std": 0.062157727507646976} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 55, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.059277376268506585, "f1": 0.5953065134099617, "f1_std": 0.06003196231924114, "bacc": 0.5965250965250966, "bacc_std": 0.06027547488002844} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 56, "C": 0.005994842503189409, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.06007477785985765, "f1": 0.606060606060606, "f1_std": 0.06150401464554483, "bacc": 0.6056949806949807, "bacc_std": 0.06098286998803646} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 57, "C": 0.005994842503189409, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.057907814926707414, "f1": 0.545, "f1_std": 0.0616079501698831, "bacc": 0.5477799227799228, "bacc_std": 0.058791910500438645} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 58, "C": 0.005994842503189409, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.05986022377616496, "f1": 0.6094688776736361, "f1_std": 0.06059810015911256, "bacc": 0.61003861003861, "bacc_std": 0.06039242814947532} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 59, "C": 0.005994842503189409, "split": "test", "acc": 0.5538461538461539, "acc_std": 0.060067023709170955, "f1": 0.543030303030303, "f1_std": 0.06173741501884506, "bacc": 0.542953667953668, "bacc_std": 0.061100600224087594} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 60, "C": 0.005994842503189409, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.05952117419469136, "f1": 0.6153846153846154, "f1_std": 0.06250793951211188, "bacc": 0.6148648648648649, "bacc_std": 0.06087780255379145} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 61, "C": 0.005994842503189409, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.0593101486072211, "f1": 0.5644080416976918, "f1_std": 0.06272747681976858, "bacc": 0.5656370656370656, "bacc_std": 0.06063885889226721} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 62, "C": 0.3593813663804626, "split": "test", "acc": 0.49230769230769234, "acc_std": 0.061131539231049914, "f1": 0.4918265813788202, "f1_std": 0.061499482042368124, "bacc": 0.4975868725868726, "bacc_std": 0.0624962052186472} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 63, "C": 0.005994842503189409, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.05799427843641946, "f1": 0.5699583435432491, "f1_std": 0.06006157500353187, "bacc": 0.5699806949806949, "bacc_std": 0.05888497869797474} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 64, "C": 0.005994842503189409, "split": "test", "acc": 0.7076923076923077, "acc_std": 0.054275702061968085, "f1": 0.6934723256391164, "f1_std": 0.058268355925866454, "bacc": 0.6911196911196911, "bacc_std": 0.05621078703888354} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 65, "C": 0.005994842503189409, "split": "test", "acc": 0.6923076923076923, "acc_std": 0.0569473461777315, "f1": 0.6794871794871795, "f1_std": 0.06061295739590483, "bacc": 0.6776061776061776, "bacc_std": 0.0590761323383148} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 66, "C": 0.000774263682681127, "split": "test", "acc": 0.6615384615384615, "acc_std": 0.05634970269737757, "f1": 0.6515594541910331, "f1_std": 0.05799078242744701, "bacc": 0.6505791505791505, "bacc_std": 0.057331952554935915} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 67, "C": 0.046415888336127774, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.0637962659588777, "f1": 0.5745454545454545, "f1_std": 0.06566186760577263, "bacc": 0.5743243243243243, "bacc_std": 0.06486931534505905} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 68, "C": 0.005994842503189409, "split": "test", "acc": 0.6923076923076923, "acc_std": 0.05498071528503824, "f1": 0.6697154471544715, "f1_std": 0.06162827691928485, "bacc": 0.6689189189189189, "bacc_std": 0.0577167290751472} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 69, "C": 0.000774263682681127, "split": "test", "acc": 0.5230769230769231, "acc_std": 0.06147227209633942, "f1": 0.5115151515151515, "f1_std": 0.06256879605084496, "bacc": 0.5115830115830116, "bacc_std": 0.06200599402814998} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 70, "C": 0.005994842503189409, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.06306670836615791, "f1": 0.5294401544401545, "f1_std": 0.06463679991909065, "bacc": 0.5294401544401545, "bacc_std": 0.06421257227882796} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 71, "C": 0.000774263682681127, "split": "test", "acc": 0.5538461538461539, "acc_std": 0.058035133207312725, "f1": 0.5167905665214048, "f1_std": 0.06312983552887898, "bacc": 0.5255791505791506, "bacc_std": 0.05868344241649786} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 72, "C": 0.005994842503189409, "split": "test", "acc": 0.6615384615384615, "acc_std": 0.05558922887452124, "f1": 0.6474358974358974, "f1_std": 0.05865705490069454, "bacc": 0.6462355212355213, "bacc_std": 0.056987625719098906} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 73, "C": 0.000774263682681127, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.060705126851325356, "f1": 0.5045731707317074, "f1_std": 0.06532552065358074, "bacc": 0.5120656370656371, "bacc_std": 0.06158759120327949} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 74, "C": 10000.0, "split": "test", "acc": 0.5230769230769231, "acc_std": 0.05813231998827274, "f1": 0.5189782764382908, "f1_std": 0.060554235504142545, "bacc": 0.5463320463320464, "bacc_std": 0.05790707675862508} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 75, "C": 0.046415888336127774, "split": "test", "acc": 0.5076923076923077, "acc_std": 0.06424641172951484, "f1": 0.5019157088122606, "f1_std": 0.06486328020070385, "bacc": 0.5024131274131274, "bacc_std": 0.06518211335666634} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 76, "C": 0.005994842503189409, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.051239999168548975, "f1": 0.5075757575757576, "f1_std": 0.060905811709938536, "bacc": 0.5304054054054055, "bacc_std": 0.0521888730822872} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 77, "C": 0.005994842503189409, "split": "test", "acc": 0.6615384615384615, "acc_std": 0.05096276399106968, "f1": 0.622093023255814, "f1_std": 0.06318531787761687, "bacc": 0.6288610038610039, "bacc_std": 0.054214489390002805} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 78, "C": 0.046415888336127774, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.05863940553635247, "f1": 0.5966741126830479, "f1_std": 0.06195026725201978, "bacc": 0.597007722007722, "bacc_std": 0.05981558237703973} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 79, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.06022263232196831, "f1": 0.5921814671814671, "f1_std": 0.061955156733891154, "bacc": 0.5921814671814671, "bacc_std": 0.06185160797579859} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 80, "C": 0.000774263682681127, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.05988766604551139, "f1": 0.5125, "f1_std": 0.06283700979082794, "bacc": 0.5164092664092664, "bacc_std": 0.060547466150965935} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 81, "C": 0.046415888336127774, "split": "test", "acc": 0.5538461538461539, "acc_std": 0.05642626439531034, "f1": 0.5250692869740489, "f1_std": 0.0605464686790807, "bacc": 0.5299227799227799, "bacc_std": 0.057376481254745745} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 82, "C": 0.046415888336127774, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.05714799638766228, "f1": 0.6306818181818181, "f1_std": 0.05733017633384551, "bacc": 0.640926640926641, "bacc_std": 0.05717991422082825} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 83, "C": 0.005994842503189409, "split": "test", "acc": 0.6461538461538462, "acc_std": 0.0553125941980945, "f1": 0.6233308138070043, "f1_std": 0.06052316685767508, "bacc": 0.6240347490347491, "bacc_std": 0.05718663618122895} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 84, "C": 0.005994842503189409, "split": "test", "acc": 0.6461538461538462, "acc_std": 0.06040005486105898, "f1": 0.6431129147767964, "f1_std": 0.06108818628152491, "bacc": 0.6457528957528957, "bacc_std": 0.061476506133144926} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 85, "C": 0.005994842503189409, "split": "test", "acc": 0.6461538461538462, "acc_std": 0.05922157770840109, "f1": 0.6289401836684041, "f1_std": 0.06247336516095856, "bacc": 0.6283783783783784, "bacc_std": 0.06043540615491193} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 86, "C": 0.005994842503189409, "split": "test", "acc": 0.5538461538461539, "acc_std": 0.05919580186617866, "f1": 0.5167905665214048, "f1_std": 0.06498504424494862, "bacc": 0.5255791505791506, "bacc_std": 0.06036567541679717} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 87, "C": 0.046415888336127774, "split": "test", "acc": 0.6, "acc_std": 0.06265941373949739, "f1": 0.5921814671814671, "f1_std": 0.0641847335495413, "bacc": 0.5921814671814671, "bacc_std": 0.06390811494969031} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 88, "C": 0.005994842503189409, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.05931263074321079, "f1": 0.6198830409356726, "f1_std": 0.062012785691306374, "bacc": 0.6192084942084942, "bacc_std": 0.06111178524565383} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 89, "C": 2.782559402207126, "split": "test", "acc": 0.5230769230769231, "acc_std": 0.06044383377500237, "f1": 0.5226249703861644, "f1_std": 0.06063694357749275, "bacc": 0.528957528957529, "bacc_std": 0.06086927889562604} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 90, "C": 0.005994842503189409, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.05761632740319321, "f1": 0.6036585365853658, "f1_std": 0.06474643703406564, "bacc": 0.6061776061776062, "bacc_std": 0.05994124927917422} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 91, "C": 0.005994842503189409, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.05466285261145179, "f1": 0.5501153550371699, "f1_std": 0.060180216643763204, "bacc": 0.556949806949807, "bacc_std": 0.055798123705704354} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 92, "C": 0.005994842503189409, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.06074020728533192, "f1": 0.5905769715293525, "f1_std": 0.06587685167014463, "bacc": 0.5926640926640927, "bacc_std": 0.062491824862990666} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 93, "C": 0.005994842503189409, "split": "test", "acc": 0.6461538461538462, "acc_std": 0.052271652742890896, "f1": 0.6091503267973856, "f1_std": 0.06194623854594414, "bacc": 0.6153474903474904, "bacc_std": 0.05487389457611892} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 94, "C": 0.046415888336127774, "split": "test", "acc": 0.5076923076923077, "acc_std": 0.05614776784805898, "f1": 0.4616977225672878, "f1_std": 0.061435638906790144, "bacc": 0.47635135135135137, "bacc_std": 0.056481173224446624} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 95, "C": 0.046415888336127774, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.058711820528940216, "f1": 0.5699583435432491, "f1_std": 0.06092017244319253, "bacc": 0.5699806949806949, "bacc_std": 0.05976638067584281} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 96, "C": 0.046415888336127774, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.059057841469641055, "f1": 0.6235521235521235, "f1_std": 0.06051403748733361, "bacc": 0.6235521235521235, "bacc_std": 0.06037007413681276} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 97, "C": 0.046415888336127774, "split": "test", "acc": 0.5538461538461539, "acc_std": 0.055751426335669096, "f1": 0.5167905665214048, "f1_std": 0.06119495371182997, "bacc": 0.5255791505791506, "bacc_std": 0.05655198334771486} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 98, "C": 0.005994842503189409, "split": "test", "acc": 0.676923076923077, "acc_std": 0.05730562515631614, "f1": 0.656084656084656, "f1_std": 0.06246366726281485, "bacc": 0.6554054054054055, "bacc_std": 0.05912137656556257} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 99, "C": 0.000774263682681127, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.06160288166624836, "f1": 0.5192307692307693, "f1_std": 0.06501446501173067, "bacc": 0.5207528957528957, "bacc_std": 0.06270190103852319} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 100, "C": 0.005994842503189409, "split": "test", "acc": 0.6461538461538462, "acc_std": 0.053772256985380254, "f1": 0.6167649320687003, "f1_std": 0.060701259422197985, "bacc": 0.6196911196911197, "bacc_std": 0.05605330829498735} +eval results (random splits): + +| model | repr | clf | dataset | split | n_trials | C | C_std | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:-----------|:--------|-----------:|-------:|--------:|--------:|----------:|--------:|---------:|-------:|-----------:| +| flat_mae | patch | logistic | adhd200_dx | train | 100 | 212.98 | 1411.1 | 0.7846 | 0.078809 | 0.77622 | 0.083053 | 0.7738 | 0.083188 | +| flat_mae | patch | logistic | adhd200_dx | test | 100 | 212.98 | 1411.1 | 0.59677 | 0.055461 | 0.57931 | 0.057391 | 0.582 | 0.054831 | + + +done! total time: 0:04:36 diff --git a/input_space_v3/flat_lr1e-3_6/eval_v2/adni_ad_vs_cn__patch__logistic/config.yaml b/input_space_v3/flat_lr1e-3_6/eval_v2/adni_ad_vs_cn__patch__logistic/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..9d11a9cffdc2598a6bdfe2bdc27ab19a899960f5 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_6/eval_v2/adni_ad_vs_cn__patch__logistic/config.yaml @@ -0,0 +1,30 @@ +output_root: experiments/input_space_v3/output +name_prefix: eval_logistic +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_6; eval v2 (adni_ad_vs_cn patch logistic) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: input_space_v3/flat_lr1e-3_6/eval_v2/adni_ad_vs_cn__patch__logistic +model: flat_mae +representation: patch +dataset: adni_ad_vs_cn +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/eval_v2/adni_ad_vs_cn__patch__logistic +remote_dir: null diff --git a/input_space_v3/flat_lr1e-3_6/eval_v2/adni_ad_vs_cn__patch__logistic/eval_table.csv b/input_space_v3/flat_lr1e-3_6/eval_v2/adni_ad_vs_cn__patch__logistic/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..35ef0f836bef8b70338b3b88c6c0996a5a0cd12f --- /dev/null +++ b/input_space_v3/flat_lr1e-3_6/eval_v2/adni_ad_vs_cn__patch__logistic/eval_table.csv @@ -0,0 +1,203 @@ +model,repr,clf,dataset,trial,C,split,acc,acc_std,f1,f1_std,bacc,bacc_std +flat_mae,patch,logistic,adni_ad_vs_cn,,0.3593813663804626,train,0.9728997289972899,0.007971195416948042,0.9611382593310305,0.011879086641380016,0.9465028124235755,0.015878020341113155 +flat_mae,patch,logistic,adni_ad_vs_cn,,0.3593813663804626,test,0.7804878048780488,0.0653713139328434,0.6917293233082706,0.08728609936548408,0.6996527777777778,0.09179320095418773 +flat_mae,patch,logistic,adni_ad_vs_cn,1,0.3593813663804626,train,0.978319783197832,0.007431388462297416,0.969172932330827,0.01072798034736683,0.9615827101651737,0.013719956538091672 +flat_mae,patch,logistic,adni_ad_vs_cn,1,0.3593813663804626,test,0.7804878048780488,0.056777302735242285,0.6660633484162897,0.0918901860847624,0.6516129032258065,0.08469408597884437 +flat_mae,patch,logistic,adni_ad_vs_cn,2,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,2,21.54434690031882,test,0.7073170731707317,0.06474497630834652,0.603225806451613,0.08596418001238873,0.603225806451613,0.0857876001605776 +flat_mae,patch,logistic,adni_ad_vs_cn,3,0.005994842503189409,train,0.8428184281842819,0.014169994450894325,0.7258965163934425,0.03021711954053787,0.6911208809269456,0.026530214903269452 +flat_mae,patch,logistic,adni_ad_vs_cn,3,0.005994842503189409,test,0.7073170731707317,0.0462250398908317,0.4831932773109243,0.0716509834840611,0.5016129032258064,0.05500797586667784 +flat_mae,patch,logistic,adni_ad_vs_cn,4,0.046415888336127774,train,0.8970189701897019,0.014914676432749626,0.8394182317911132,0.02563242614800844,0.8073999506943874,0.02741299479917308 +flat_mae,patch,logistic,adni_ad_vs_cn,4,0.046415888336127774,test,0.8292682926829268,0.05664158267180503,0.7602339181286549,0.08453071587056449,0.7516129032258064,0.08566494632050925 +flat_mae,patch,logistic,adni_ad_vs_cn,5,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,5,21.54434690031882,test,0.7560975609756098,0.053022841990545105,0.6117424242424243,0.09259939721924956,0.6016129032258064,0.07859472409498693 +flat_mae,patch,logistic,adni_ad_vs_cn,6,0.3593813663804626,train,0.9701897018970189,0.008379025152977488,0.9570680628272251,0.012441569440011612,0.9441408497000575,0.016218729474168154 +flat_mae,patch,logistic,adni_ad_vs_cn,6,0.3593813663804626,test,0.7804878048780488,0.05623260521576052,0.6660633484162897,0.09115413497899383,0.6516129032258065,0.08346742091258198 +flat_mae,patch,logistic,adni_ad_vs_cn,7,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,7,2.782559402207126,test,0.7804878048780488,0.05903194871983235,0.6917293233082706,0.08702051388096967,0.685483870967742,0.0865153334619792 +flat_mae,patch,logistic,adni_ad_vs_cn,8,0.046415888336127774,train,0.9051490514905149,0.014792415260514533,0.8557063851181499,0.024135155782469945,0.828888980195579,0.02649906258587598 +flat_mae,patch,logistic,adni_ad_vs_cn,8,0.046415888336127774,test,0.7560975609756098,0.05469671939369925,0.6117424242424243,0.09348347877303971,0.6016129032258064,0.08048179608160029 +flat_mae,patch,logistic,adni_ad_vs_cn,9,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,9,2.782559402207126,test,0.6585365853658537,0.07135321562572267,0.5651515151515152,0.08191108023151765,0.5709677419354839,0.08715949205422714 +flat_mae,patch,logistic,adni_ad_vs_cn,10,0.046415888336127774,train,0.9024390243902439,0.014210468406356381,0.8478699038021071,0.024715323408425385,0.8149806886350563,0.02731655235521889 +flat_mae,patch,logistic,adni_ad_vs_cn,10,0.046415888336127774,test,0.7560975609756098,0.05620331495152888,0.6117424242424243,0.09331303010835147,0.6016129032258064,0.08068002317450142 +flat_mae,patch,logistic,adni_ad_vs_cn,11,0.046415888336127774,train,0.9105691056910569,0.013203051782693856,0.8612481626234888,0.02264229077426999,0.8283753800640973,0.02524388353261405 +flat_mae,patch,logistic,adni_ad_vs_cn,11,0.046415888336127774,test,0.7560975609756098,0.03263192234209673,0.5119047619047619,0.07753044814406698,0.5338709677419355,0.0502993105833598 +flat_mae,patch,logistic,adni_ad_vs_cn,12,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,12,166.81005372000556,test,0.6585365853658537,0.06004438176118303,0.5017361111111112,0.07770942535294129,0.5032258064516129,0.07207407010628541 +flat_mae,patch,logistic,adni_ad_vs_cn,13,0.046415888336127774,train,0.8997289972899729,0.014818450982590312,0.8459672597222379,0.024478878868162097,0.8172610732188348,0.02630932661157094 +flat_mae,patch,logistic,adni_ad_vs_cn,13,0.046415888336127774,test,0.8292682926829268,0.05035835885888401,0.7402714932126697,0.08562307184607955,0.717741935483871,0.08353963156265 +flat_mae,patch,logistic,adni_ad_vs_cn,14,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,14,166.81005372000556,test,0.7804878048780488,0.06607512894486327,0.7410526315789474,0.070926079455639,0.7870967741935484,0.07445149521989917 +flat_mae,patch,logistic,adni_ad_vs_cn,15,0.046415888336127774,train,0.8997289972899729,0.015213136312239667,0.8489127427654513,0.024651188323879542,0.8253554112909853,0.02710070238263182 +flat_mae,patch,logistic,adni_ad_vs_cn,15,0.046415888336127774,test,0.7560975609756098,0.05375324236585507,0.6117424242424243,0.09087886751002897,0.6016129032258064,0.07800846454778493 +flat_mae,patch,logistic,adni_ad_vs_cn,16,0.046415888336127774,train,0.9051490514905149,0.013735768013445454,0.851341551849166,0.024004979789233535,0.8167474730873532,0.026387544994832566 +flat_mae,patch,logistic,adni_ad_vs_cn,16,0.046415888336127774,test,0.7804878048780488,0.03783793990968802,0.5886287625418061,0.09200822912538997,0.5838709677419355,0.06419406710764647 +flat_mae,patch,logistic,adni_ad_vs_cn,17,0.046415888336127774,train,0.8970189701897019,0.014453364949875083,0.8440891300480342,0.023384627291330347,0.8195414578026132,0.025512260575031316 +flat_mae,patch,logistic,adni_ad_vs_cn,17,0.046415888336127774,test,0.8292682926829268,0.044931675276897676,0.7144278606965174,0.09590969060854648,0.6838709677419355,0.08164433437849941 +flat_mae,patch,logistic,adni_ad_vs_cn,18,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,18,2.782559402207126,test,0.7804878048780488,0.04942395115978782,0.6328358208955224,0.09572457373510859,0.6177419354838709,0.07841563027738926 +flat_mae,patch,logistic,adni_ad_vs_cn,19,0.046415888336127774,train,0.9051490514905149,0.014098679950465206,0.8570796215348863,0.022817205056442424,0.8329361492316543,0.025412525066898395 +flat_mae,patch,logistic,adni_ad_vs_cn,19,0.046415888336127774,test,0.6829268292682927,0.06870971969097164,0.5547201336675021,0.08446923034397216,0.5532258064516129,0.08082334611877678 +flat_mae,patch,logistic,adni_ad_vs_cn,20,0.046415888336127774,train,0.9132791327913279,0.012613964877416112,0.8674330878390515,0.02115258704589128,0.8382365025885447,0.024389590802672823 +flat_mae,patch,logistic,adni_ad_vs_cn,20,0.046415888336127774,test,0.7560975609756098,0.06292448473605515,0.6693548387096775,0.08124251375463665,0.6693548387096775,0.08280770667709417 +flat_mae,patch,logistic,adni_ad_vs_cn,21,0.3593813663804626,train,0.978319783197832,0.007389064693158471,0.969172932330827,0.0106743011015579,0.9615827101651737,0.013716696208194934 +flat_mae,patch,logistic,adni_ad_vs_cn,21,0.3593813663804626,test,0.7804878048780488,0.05056529931038283,0.6328358208955224,0.09743545351671429,0.6177419354838709,0.0794998227080661 +flat_mae,patch,logistic,adni_ad_vs_cn,22,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,22,2.782559402207126,test,0.7073170731707317,0.057449250811462585,0.5340909090909092,0.08486392093583857,0.535483870967742,0.07275478149928956 +flat_mae,patch,logistic,adni_ad_vs_cn,23,0.3593813663804626,train,0.983739837398374,0.006805568201887298,0.9766829555986183,0.010077330870923662,0.9651162790697674,0.0146003178284675 +flat_mae,patch,logistic,adni_ad_vs_cn,23,0.3593813663804626,test,0.6585365853658537,0.06390214112758714,0.5370967741935484,0.08193220238854117,0.5370967741935484,0.08276975348260547 +flat_mae,patch,logistic,adni_ad_vs_cn,24,0.3593813663804626,train,0.983739837398374,0.006664427764265068,0.9766829555986183,0.009848700934855797,0.9651162790697674,0.014297522354731442 +flat_mae,patch,logistic,adni_ad_vs_cn,24,0.3593813663804626,test,0.7560975609756098,0.06337129851369873,0.6693548387096775,0.08382396757817713,0.6693548387096775,0.08484839488442959 +flat_mae,patch,logistic,adni_ad_vs_cn,25,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,25,2.782559402207126,test,0.7073170731707317,0.06153917127673821,0.603225806451613,0.07969912285078558,0.603225806451613,0.08094078564257357 +flat_mae,patch,logistic,adni_ad_vs_cn,26,0.046415888336127774,train,0.907859078590786,0.013746303594361436,0.8591476558289923,0.023062941379253254,0.8306557646478758,0.026235286917811206 +flat_mae,patch,logistic,adni_ad_vs_cn,26,0.046415888336127774,test,0.7317073170731707,0.06425653152902351,0.6232247284878863,0.08930649857330457,0.6193548387096774,0.08804018776564833 +flat_mae,patch,logistic,adni_ad_vs_cn,27,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,27,166.81005372000556,test,0.7560975609756098,0.06096538450849701,0.6693548387096775,0.08176045272795313,0.6693548387096775,0.08479524828145396 +flat_mae,patch,logistic,adni_ad_vs_cn,28,0.046415888336127774,train,0.907859078590786,0.012987693974275315,0.8591476558289923,0.02151355717886216,0.8306557646478758,0.02427135708943305 +flat_mae,patch,logistic,adni_ad_vs_cn,28,0.046415888336127774,test,0.7804878048780488,0.055427085512837065,0.6660633484162897,0.0893645933844759,0.6516129032258065,0.08287161591428983 +flat_mae,patch,logistic,adni_ad_vs_cn,29,0.046415888336127774,train,0.8997289972899729,0.014585061715153358,0.8474610356963298,0.023781088148177414,0.8213082422549101,0.02587097329571428 +flat_mae,patch,logistic,adni_ad_vs_cn,29,0.046415888336127774,test,0.8292682926829268,0.053445497264693075,0.7602339181286549,0.079380553610426,0.7516129032258064,0.08167792252558663 +flat_mae,patch,logistic,adni_ad_vs_cn,30,0.046415888336127774,train,0.8997289972899729,0.014015865075742989,0.8489127427654513,0.022476403232585852,0.8253554112909853,0.024352792659840073 +flat_mae,patch,logistic,adni_ad_vs_cn,30,0.046415888336127774,test,0.7317073170731707,0.05701477103871648,0.5918552036199095,0.09062024307000272,0.5854838709677419,0.07993216791268484 +flat_mae,patch,logistic,adni_ad_vs_cn,31,0.046415888336127774,train,0.9105691056910569,0.01339642244669602,0.8639517345399699,0.022272423464071496,0.8364697181362479,0.025161473532286798 +flat_mae,patch,logistic,adni_ad_vs_cn,31,0.046415888336127774,test,0.7073170731707317,0.05561540407775266,0.5340909090909092,0.08416775828487492,0.535483870967742,0.07142128526982816 +flat_mae,patch,logistic,adni_ad_vs_cn,32,0.3593813663804626,train,0.964769647696477,0.009606310245078612,0.9496943066581374,0.014050400072191667,0.940607280795464,0.017395668785574542 +flat_mae,patch,logistic,adni_ad_vs_cn,32,0.3593813663804626,test,0.6097560975609756,0.07557952188585837,0.5287356321839081,0.0789751204845968,0.5387096774193548,0.08637400825948494 +flat_mae,patch,logistic,adni_ad_vs_cn,33,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,33,2.782559402207126,test,0.6829268292682927,0.07528989778915712,0.6259649122807017,0.0814172261774457,0.6548387096774193,0.08993065538711413 +flat_mae,patch,logistic,adni_ad_vs_cn,34,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,34,21.54434690031882,test,0.6585365853658537,0.07306742300492475,0.5876436781609196,0.0824722942105637,0.6048387096774194,0.09185936741505386 +flat_mae,patch,logistic,adni_ad_vs_cn,35,0.046415888336127774,train,0.8970189701897019,0.01371843878165561,0.8410204081632653,0.02297829015792659,0.8114471197304627,0.024926239353913995 +flat_mae,patch,logistic,adni_ad_vs_cn,35,0.046415888336127774,test,0.8048780487804879,0.05313715655081452,0.6893939393939394,0.09638344319220633,0.667741935483871,0.08632810598788053 +flat_mae,patch,logistic,adni_ad_vs_cn,36,10000.0,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,36,10000.0,test,0.6341463414634146,0.07540074967634544,0.5467943994104643,0.08452142376981145,0.5548387096774194,0.09197821893005009 +flat_mae,patch,logistic,adni_ad_vs_cn,37,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,37,166.81005372000556,test,0.7317073170731707,0.06017709339855881,0.6232247284878863,0.08684467740140013,0.6193548387096774,0.08495921008184767 +flat_mae,patch,logistic,adni_ad_vs_cn,38,0.046415888336127774,train,0.9214092140921409,0.012339256634005952,0.8815802578431915,0.01993526414587909,0.8556783630536609,0.023179562255560806 +flat_mae,patch,logistic,adni_ad_vs_cn,38,0.046415888336127774,test,0.8048780487804879,0.06386288107204473,0.7354838709677419,0.08885928033897642,0.7354838709677419,0.09066003230098596 +flat_mae,patch,logistic,adni_ad_vs_cn,39,0.046415888336127774,train,0.9186991869918699,0.012298202113397704,0.8757185198491109,0.020624438614417564,0.8458172405292136,0.024185087468824255 +flat_mae,patch,logistic,adni_ad_vs_cn,39,0.046415888336127774,test,0.6585365853658537,0.060150495376112,0.5017361111111112,0.07409008156455914,0.5032258064516129,0.06858331588281359 +flat_mae,patch,logistic,adni_ad_vs_cn,40,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,40,166.81005372000556,test,0.5853658536585366,0.07072161408221543,0.5108771929824562,0.07402768430105099,0.5225806451612903,0.08523774818048828 +flat_mae,patch,logistic,adni_ad_vs_cn,41,0.046415888336127774,train,0.9051490514905149,0.013933966375464076,0.8542933537913061,0.023363157056289222,0.8248418111595037,0.02600756050120033 +flat_mae,patch,logistic,adni_ad_vs_cn,41,0.046415888336127774,test,0.8292682926829268,0.055624195814625445,0.7602339181286549,0.08061611267826164,0.7516129032258064,0.0841698720880916 +flat_mae,patch,logistic,adni_ad_vs_cn,42,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,42,166.81005372000556,test,0.7560975609756098,0.05698218722474701,0.6117424242424243,0.09639764448376878,0.6016129032258064,0.08248484684096037 +flat_mae,patch,logistic,adni_ad_vs_cn,43,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,43,166.81005372000556,test,0.7804878048780488,0.05532971851851849,0.6660633484162897,0.08895932230298935,0.6516129032258065,0.08323101577845249 +flat_mae,patch,logistic,adni_ad_vs_cn,44,0.046415888336127774,train,0.8997289972899729,0.014670339665508642,0.8474610356963298,0.024296578364673416,0.8213082422549101,0.026655670679694553 +flat_mae,patch,logistic,adni_ad_vs_cn,44,0.046415888336127774,test,0.926829268292683,0.03515888978951709,0.8886877828054298,0.06313048531501687,0.85,0.07207572406851005 +flat_mae,patch,logistic,adni_ad_vs_cn,45,0.005994842503189409,train,0.8265582655826558,0.013580021243028213,0.6857568660847349,0.03135245602484499,0.656237159996713,0.025673108576189988 +flat_mae,patch,logistic,adni_ad_vs_cn,45,0.005994842503189409,test,0.8048780487804879,0.042804593147547455,0.6554621848739496,0.0973881805612465,0.6338709677419355,0.07568486192536661 +flat_mae,patch,logistic,adni_ad_vs_cn,46,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,46,21.54434690031882,test,0.8292682926829268,0.05655137751312312,0.7602339181286549,0.0816480998887171,0.7516129032258064,0.08253971036853185 +flat_mae,patch,logistic,adni_ad_vs_cn,47,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,47,21.54434690031882,test,0.7073170731707317,0.06987736346660925,0.603225806451613,0.09173214444073939,0.603225806451613,0.09197901538716367 +flat_mae,patch,logistic,adni_ad_vs_cn,48,0.046415888336127774,train,0.9105691056910569,0.013733235533285811,0.8639517345399699,0.02267171083219262,0.8364697181362479,0.025476664985182088 +flat_mae,patch,logistic,adni_ad_vs_cn,48,0.046415888336127774,test,0.6829268292682927,0.05547943651718291,0.5176470588235295,0.078837803024788,0.5193548387096775,0.07010683470698613 +flat_mae,patch,logistic,adni_ad_vs_cn,49,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,49,2.782559402207126,test,0.6585365853658537,0.06453603229672865,0.5017361111111112,0.0845180832535193,0.5032258064516129,0.07788377336779623 +flat_mae,patch,logistic,adni_ad_vs_cn,50,0.046415888336127774,train,0.9132791327913279,0.013689833803324643,0.8674330878390515,0.022857035932308388,0.8382365025885447,0.025711426169218194 +flat_mae,patch,logistic,adni_ad_vs_cn,50,0.046415888336127774,test,0.7560975609756098,0.062339306806470374,0.6693548387096775,0.08387006308651135,0.6693548387096775,0.08282927108071605 +flat_mae,patch,logistic,adni_ad_vs_cn,51,0.3593813663804626,train,0.981029810298103,0.006577049853161355,0.9729123189697663,0.009606180969996627,0.9633494946174705,0.01309952214144569 +flat_mae,patch,logistic,adni_ad_vs_cn,51,0.3593813663804626,test,0.6829268292682927,0.07013372117551617,0.6072218128224024,0.08216361470176779,0.6209677419354839,0.08960173523618896 +flat_mae,patch,logistic,adni_ad_vs_cn,52,0.005994842503189409,train,0.8428184281842819,0.014789033795246414,0.7292257085020243,0.030583089772483817,0.6951680499630208,0.027431735678046052 +flat_mae,patch,logistic,adni_ad_vs_cn,52,0.005994842503189409,test,0.7317073170731707,0.05025278159762534,0.5512437810945273,0.0874832722981575,0.5516129032258065,0.06946497324410605 +flat_mae,patch,logistic,adni_ad_vs_cn,53,0.046415888336127774,train,0.9051490514905149,0.013794448963906305,0.8528389603582457,0.023500899570307612,0.8207946421234283,0.025785202506267188 +flat_mae,patch,logistic,adni_ad_vs_cn,53,0.046415888336127774,test,0.7560975609756098,0.06262517981560091,0.6693548387096775,0.08476517664920384,0.6693548387096775,0.08516410619733678 +flat_mae,patch,logistic,adni_ad_vs_cn,54,0.3593813663804626,train,0.978319783197832,0.007328656895288999,0.9689106074648244,0.010825678557662425,0.9575355411290984,0.014753726198102151 +flat_mae,patch,logistic,adni_ad_vs_cn,54,0.3593813663804626,test,0.7317073170731707,0.06757946387869665,0.6479313036690086,0.08491253815867307,0.6532258064516129,0.08907384833864762 +flat_mae,patch,logistic,adni_ad_vs_cn,55,0.3593813663804626,train,0.967479674796748,0.009198537803906294,0.9529616724738676,0.013771337821500982,0.9383268962116854,0.01761839528737676 +flat_mae,patch,logistic,adni_ad_vs_cn,55,0.3593813663804626,test,0.7560975609756098,0.05826561265518859,0.6440972222222222,0.0875284452484059,0.635483870967742,0.0828444249862399 +flat_mae,patch,logistic,adni_ad_vs_cn,56,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,56,166.81005372000556,test,0.7317073170731707,0.0663438127274126,0.6232247284878863,0.09165971470014568,0.6193548387096774,0.08932714436319593 +flat_mae,patch,logistic,adni_ad_vs_cn,57,0.046415888336127774,train,0.8997289972899729,0.014188806462562114,0.8444297580930026,0.024461162272750924,0.8132139041827595,0.02686889944025501 +flat_mae,patch,logistic,adni_ad_vs_cn,57,0.046415888336127774,test,0.7317073170731707,0.05313034939998667,0.5512437810945273,0.08782320740542782,0.5516129032258065,0.07005881281367536 +flat_mae,patch,logistic,adni_ad_vs_cn,58,0.046415888336127774,train,0.8915989159891599,0.014452571222692914,0.8342913597988144,0.02414282485022934,0.807913550825869,0.026262636987837092 +flat_mae,patch,logistic,adni_ad_vs_cn,58,0.046415888336127774,test,0.8292682926829268,0.04441435957108307,0.7144278606965174,0.09087195558940975,0.6838709677419355,0.07786548040371652 +flat_mae,patch,logistic,adni_ad_vs_cn,59,0.046415888336127774,train,0.9051490514905149,0.014068659820195742,0.8542933537913061,0.023682785344226284,0.8248418111595037,0.02608335074537318 +flat_mae,patch,logistic,adni_ad_vs_cn,59,0.046415888336127774,test,0.7560975609756098,0.05953705997952329,0.6440972222222222,0.09110070906098997,0.635483870967742,0.08704094841712581 +flat_mae,patch,logistic,adni_ad_vs_cn,60,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,60,2.782559402207126,test,0.7560975609756098,0.06423825372873851,0.6893939393939394,0.07983275474525367,0.7032258064516128,0.08526702478149714 +flat_mae,patch,logistic,adni_ad_vs_cn,61,0.046415888336127774,train,0.9159891598915989,0.01375882653743491,0.8757454296607684,0.021496651965823416,0.8561919631851426,0.02433816729913318 +flat_mae,patch,logistic,adni_ad_vs_cn,61,0.046415888336127774,test,0.6341463414634146,0.06758969188080778,0.48621553884711777,0.08025411898918883,0.48709677419354835,0.07719784783734585 +flat_mae,patch,logistic,adni_ad_vs_cn,62,0.046415888336127774,train,0.9024390243902439,0.013650378257773604,0.850862223818933,0.02293478291005174,0.8230750267072069,0.025715871626760783 +flat_mae,patch,logistic,adni_ad_vs_cn,62,0.046415888336127774,test,0.7804878048780488,0.05707131537530443,0.6660633484162897,0.09384228631227812,0.6516129032258065,0.08589419785879866 +flat_mae,patch,logistic,adni_ad_vs_cn,63,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,63,21.54434690031882,test,0.8292682926829268,0.05527177996876997,0.7759562841530054,0.07220423092927852,0.7854838709677419,0.07700499727016788 +flat_mae,patch,logistic,adni_ad_vs_cn,64,0.005994842503189409,train,0.8373983739837398,0.014367060876063802,0.7164446721311475,0.029951486333201233,0.6835401429862766,0.02603571004849564 +flat_mae,patch,logistic,adni_ad_vs_cn,64,0.005994842503189409,test,0.7317073170731707,0.050115274613173943,0.5512437810945273,0.08444237000934565,0.5516129032258065,0.06829927410208697 +flat_mae,patch,logistic,adni_ad_vs_cn,65,0.3593813663804626,train,0.978319783197832,0.007327793010670992,0.969172932330827,0.010582498276967174,0.9615827101651737,0.013285679961734883 +flat_mae,patch,logistic,adni_ad_vs_cn,65,0.3593813663804626,test,0.7317073170731707,0.0654639962171105,0.6232247284878863,0.08927818133359565,0.6193548387096774,0.08652184220149063 +flat_mae,patch,logistic,adni_ad_vs_cn,66,0.046415888336127774,train,0.9024390243902439,0.01360304035117266,0.8493877551020408,0.02322655285207857,0.8190278576711316,0.02568897154554533 +flat_mae,patch,logistic,adni_ad_vs_cn,66,0.046415888336127774,test,0.7804878048780488,0.058749936398006256,0.6917293233082706,0.08319838334221297,0.685483870967742,0.0821351570075161 +flat_mae,patch,logistic,adni_ad_vs_cn,67,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,67,2.782559402207126,test,0.7317073170731707,0.06121949276066157,0.6479313036690086,0.0772430061592202,0.6532258064516129,0.08019379979458682 +flat_mae,patch,logistic,adni_ad_vs_cn,68,0.046415888336127774,train,0.907859078590786,0.013444702006536437,0.8577551020408163,0.02282764468056445,0.8266085956118004,0.02515915199840472 +flat_mae,patch,logistic,adni_ad_vs_cn,68,0.046415888336127774,test,0.7073170731707317,0.06429547719602341,0.603225806451613,0.08449949898311071,0.603225806451613,0.08582379760399615 +flat_mae,patch,logistic,adni_ad_vs_cn,69,0.046415888336127774,train,0.8997289972899729,0.014690102796074073,0.8489127427654513,0.023422718525587916,0.8253554112909853,0.025181633473814732 +flat_mae,patch,logistic,adni_ad_vs_cn,69,0.046415888336127774,test,0.8292682926829268,0.056262218581728994,0.7759562841530054,0.07421202367295644,0.7854838709677419,0.0788217960712651 +flat_mae,patch,logistic,adni_ad_vs_cn,70,0.046415888336127774,train,0.9051490514905149,0.013363158745146134,0.8528389603582457,0.023213566158538743,0.8207946421234283,0.025800669404921754 +flat_mae,patch,logistic,adni_ad_vs_cn,70,0.046415888336127774,test,0.8048780487804879,0.0442484736929116,0.6554621848739496,0.09666570476936415,0.6338709677419355,0.07625314131807351 +flat_mae,patch,logistic,adni_ad_vs_cn,71,0.046415888336127774,train,0.907859078590786,0.012748810878576995,0.8577551020408163,0.02172447864612567,0.8266085956118004,0.02451519762090832 +flat_mae,patch,logistic,adni_ad_vs_cn,71,0.046415888336127774,test,0.7073170731707317,0.04674980554887712,0.4831932773109243,0.07063349867255511,0.5016129032258064,0.05467920588954962 +flat_mae,patch,logistic,adni_ad_vs_cn,72,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,72,166.81005372000556,test,0.7073170731707317,0.05439625910082593,0.5340909090909092,0.08347922599310839,0.535483870967742,0.07018913974532945 +flat_mae,patch,logistic,adni_ad_vs_cn,73,0.046415888336127774,train,0.9051490514905149,0.013827724664740313,0.8570796215348863,0.0226662602917459,0.8329361492316543,0.02579359039182498 +flat_mae,patch,logistic,adni_ad_vs_cn,73,0.046415888336127774,test,0.7804878048780488,0.05182554362513193,0.6660633484162897,0.08560068467145669,0.6516129032258065,0.07863050618965924 +flat_mae,patch,logistic,adni_ad_vs_cn,74,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,74,2.782559402207126,test,0.7560975609756098,0.048544208250519846,0.6117424242424243,0.0856261546513437,0.6016129032258064,0.072853289420564 +flat_mae,patch,logistic,adni_ad_vs_cn,75,0.3593813663804626,train,0.981029810298103,0.0070902326689156695,0.9729123189697663,0.010391759021215356,0.9633494946174705,0.014325498309544882 +flat_mae,patch,logistic,adni_ad_vs_cn,75,0.3593813663804626,test,0.7317073170731707,0.054262213964843424,0.5512437810945273,0.09177864758379295,0.5516129032258065,0.07444532846512908 +flat_mae,patch,logistic,adni_ad_vs_cn,76,0.3593813663804626,train,0.975609756097561,0.007605894680397101,0.9648738695859115,0.011296503369014355,0.9517215876407263,0.015239961124499218 +flat_mae,patch,logistic,adni_ad_vs_cn,76,0.3593813663804626,test,0.7317073170731707,0.05475561409966371,0.5918552036199095,0.08717342146568872,0.5854838709677419,0.07749445040719104 +flat_mae,patch,logistic,adni_ad_vs_cn,77,0.046415888336127774,train,0.8943089430894309,0.014808130666534134,0.8376411656531697,0.024804745042827963,0.8096803352781659,0.027003296138106335 +flat_mae,patch,logistic,adni_ad_vs_cn,77,0.046415888336127774,test,0.8048780487804879,0.049088079003943935,0.6893939393939394,0.08999185366061344,0.667741935483871,0.08057546381751003 +flat_mae,patch,logistic,adni_ad_vs_cn,78,0.046415888336127774,train,0.9132791327913279,0.012048988949624622,0.8674330878390515,0.02016320741282763,0.8382365025885447,0.02307803744294692 +flat_mae,patch,logistic,adni_ad_vs_cn,78,0.046415888336127774,test,0.6829268292682927,0.06042268327683236,0.5176470588235295,0.08377333481201364,0.5193548387096775,0.07411694636028357 +flat_mae,patch,logistic,adni_ad_vs_cn,79,0.046415888336127774,train,0.8970189701897019,0.013731700631589258,0.8410204081632653,0.022965232107253375,0.8114471197304627,0.024951187751091317 +flat_mae,patch,logistic,adni_ad_vs_cn,79,0.046415888336127774,test,0.8780487804878049,0.04486383656190078,0.8144796380090498,0.07830214823007461,0.7838709677419355,0.07978521661838658 +flat_mae,patch,logistic,adni_ad_vs_cn,80,0.3593813663804626,train,0.9701897018970189,0.00855596200704496,0.957433644095347,0.012491573555566588,0.9481880187361328,0.01580332692902486 +flat_mae,patch,logistic,adni_ad_vs_cn,80,0.3593813663804626,test,0.7317073170731707,0.06102936167385063,0.6232247284878863,0.08445268760659484,0.6193548387096774,0.08202727243738614 +flat_mae,patch,logistic,adni_ad_vs_cn,81,0.3593813663804626,train,0.9701897018970189,0.009102365827222486,0.9570680628272251,0.01356218872916154,0.9441408497000575,0.017615061844097953 +flat_mae,patch,logistic,adni_ad_vs_cn,81,0.3593813663804626,test,0.7317073170731707,0.06291782881369468,0.6232247284878863,0.08777846972326891,0.6193548387096774,0.0860375792710733 +flat_mae,patch,logistic,adni_ad_vs_cn,82,0.046415888336127774,train,0.9024390243902439,0.013741173638673568,0.8478699038021071,0.023630766300995972,0.8149806886350563,0.02614882181919822 +flat_mae,patch,logistic,adni_ad_vs_cn,82,0.046415888336127774,test,0.8048780487804879,0.04929994153722763,0.6893939393939394,0.091605225241605,0.667741935483871,0.08154920860141544 +flat_mae,patch,logistic,adni_ad_vs_cn,83,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,83,166.81005372000556,test,0.7804878048780488,0.0566242717384583,0.6660633484162897,0.09071192226566561,0.6516129032258065,0.08321644477229907 +flat_mae,patch,logistic,adni_ad_vs_cn,84,0.046415888336127774,train,0.8997289972899729,0.014999563990206494,0.8444297580930026,0.025711871143618392,0.8132139041827595,0.028310111106516087 +flat_mae,patch,logistic,adni_ad_vs_cn,84,0.046415888336127774,test,0.7560975609756098,0.04762844495246643,0.569327731092437,0.09002029727165198,0.567741935483871,0.06843856979502076 +flat_mae,patch,logistic,adni_ad_vs_cn,85,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,85,1291.5496650148827,test,0.7804878048780488,0.06374911787424356,0.7119437939110069,0.08137868755159147,0.7193548387096774,0.08658305030071213 +flat_mae,patch,logistic,adni_ad_vs_cn,86,0.046415888336127774,train,0.9159891598915989,0.013710877472795919,0.874595744214346,0.02172032551664435,0.8521447941490673,0.024343472386527176 +flat_mae,patch,logistic,adni_ad_vs_cn,86,0.046415888336127774,test,0.7073170731707317,0.06406233950807655,0.603225806451613,0.08361427023511157,0.603225806451613,0.08405969702474414 +flat_mae,patch,logistic,adni_ad_vs_cn,87,0.046415888336127774,train,0.8943089430894309,0.01358492120299661,0.8360205558277596,0.0231983174417733,0.8056331662420906,0.025171235003417336 +flat_mae,patch,logistic,adni_ad_vs_cn,87,0.046415888336127774,test,0.8292682926829268,0.03695034209696424,0.6800445930880714,0.10170758721376494,0.65,0.07574820129877671 +flat_mae,patch,logistic,adni_ad_vs_cn,88,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,88,2.782559402207126,test,0.7560975609756098,0.06202797242755983,0.6693548387096775,0.08161223707213297,0.6693548387096775,0.08314445955712758 +flat_mae,patch,logistic,adni_ad_vs_cn,89,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,89,166.81005372000556,test,0.7073170731707317,0.06712726864927336,0.603225806451613,0.08858769271479208,0.603225806451613,0.0895727530297455 +flat_mae,patch,logistic,adni_ad_vs_cn,90,0.046415888336127774,train,0.907859078590786,0.01368034027748897,0.8618160190325139,0.021822232707663303,0.8387501027200264,0.024214675183078828 +flat_mae,patch,logistic,adni_ad_vs_cn,90,0.046415888336127774,test,0.7804878048780488,0.057421306365731305,0.6660633484162897,0.0940792722959424,0.6516129032258065,0.08473083359870186 +flat_mae,patch,logistic,adni_ad_vs_cn,91,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,91,2.782559402207126,test,0.7073170731707317,0.06882183500336372,0.603225806451613,0.0891319215544285,0.603225806451613,0.09073738850802916 +flat_mae,patch,logistic,adni_ad_vs_cn,92,0.3593813663804626,train,0.981029810298103,0.006837167969462379,0.9731387984733936,0.009802663638679062,0.9673966636535458,0.012345917723089383 +flat_mae,patch,logistic,adni_ad_vs_cn,92,0.3593813663804626,test,0.7317073170731707,0.06187417909970478,0.5918552036199095,0.0935682212324786,0.5854838709677419,0.08385778376527067 +flat_mae,patch,logistic,adni_ad_vs_cn,93,0.3593813663804626,train,0.981029810298103,0.006812764503559654,0.9726796763445977,0.010154984664567018,0.9593023255813953,0.014615756405892471 +flat_mae,patch,logistic,adni_ad_vs_cn,93,0.3593813663804626,test,0.6585365853658537,0.07253740547701784,0.5651515151515152,0.08451121590977838,0.5709677419354839,0.08976745329558958 +flat_mae,patch,logistic,adni_ad_vs_cn,94,0.3593813663804626,train,0.989159891598916,0.005361140521314419,0.9847141673570836,0.007644429077622543,0.9807913550825869,0.010066447708646125 +flat_mae,patch,logistic,adni_ad_vs_cn,94,0.3593813663804626,test,0.6585365853658537,0.06899256354929931,0.5370967741935484,0.0830066972343742,0.5370967741935484,0.08204523833980355 +flat_mae,patch,logistic,adni_ad_vs_cn,95,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,95,166.81005372000556,test,0.8048780487804879,0.05505897546538654,0.7152777777777778,0.08563849952990228,0.7016129032258065,0.08247490325555723 +flat_mae,patch,logistic,adni_ad_vs_cn,96,0.3593813663804626,train,0.978319783197832,0.007015987479798128,0.9689106074648244,0.010337065615400057,0.9575355411290984,0.014151906915361402 +flat_mae,patch,logistic,adni_ad_vs_cn,96,0.3593813663804626,test,0.7804878048780488,0.053255671693438755,0.6660633484162897,0.08911950846399921,0.6516129032258065,0.08299672122205083 +flat_mae,patch,logistic,adni_ad_vs_cn,97,0.3593813663804626,train,0.962059620596206,0.008937200984964002,0.9451219512195121,0.013337110337842314,0.9307461582710166,0.016986132760260175 +flat_mae,patch,logistic,adni_ad_vs_cn,97,0.3593813663804626,test,0.8048780487804879,0.055455498501940724,0.7152777777777778,0.08638243283818432,0.7016129032258065,0.0859956242988164 +flat_mae,patch,logistic,adni_ad_vs_cn,98,0.3593813663804626,train,0.981029810298103,0.007090746419966529,0.9731387984733936,0.010189974000347926,0.9673966636535458,0.013053689082273539 +flat_mae,patch,logistic,adni_ad_vs_cn,98,0.3593813663804626,test,0.7804878048780488,0.05447002788811535,0.6660633484162897,0.09094705758028766,0.6516129032258065,0.08366466755623 +flat_mae,patch,logistic,adni_ad_vs_cn,99,0.046415888336127774,train,0.9214092140921409,0.011942159302551386,0.8804424333836098,0.019642320970448716,0.8516311940175856,0.022585403044682307 +flat_mae,patch,logistic,adni_ad_vs_cn,99,0.046415888336127774,test,0.7073170731707317,0.05855062839682676,0.5729166666666666,0.08365350427319664,0.5693548387096774,0.07731306379588616 +flat_mae,patch,logistic,adni_ad_vs_cn,100,0.3593813663804626,train,0.981029810298103,0.007064929940722,0.9731387984733936,0.01012904058364935,0.9673966636535458,0.012759600508912871 +flat_mae,patch,logistic,adni_ad_vs_cn,100,0.3593813663804626,test,0.6341463414634146,0.06508309793733516,0.5199063231850116,0.07768625087962247,0.5209677419354839,0.08066571989566027 diff --git a/input_space_v3/flat_lr1e-3_6/eval_v2/adni_ad_vs_cn__patch__logistic/log.txt b/input_space_v3/flat_lr1e-3_6/eval_v2/adni_ad_vs_cn__patch__logistic/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..c50146492abc66cdc16b84be31b48f6bebf75274 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_6/eval_v2/adni_ad_vs_cn__patch__logistic/log.txt @@ -0,0 +1,240 @@ +fMRI foundation model logistic probe eval +version: 0.1.dev86+gf97f52698 +sha: bcce2b486277d3a5b520775efd9cdf1a2affce36, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-04-08 22:53:52 +config: +output_root: experiments/input_space_v3/output +name_prefix: eval_logistic +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_6; eval v2 (adni_ad_vs_cn patch logistic) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: input_space_v3/flat_lr1e-3_6/eval_v2/adni_ad_vs_cn__patch__logistic +model: flat_mae +representation: patch +dataset: adni_ad_vs_cn +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/eval_v2/adni_ad_vs_cn__patch__logistic +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=True, reg_tokens=0, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: adni_ad_vs_cn (flat) +train (n=328): +ADNIDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'bold', 'mean', 'std'], + num_rows: 525 +}), + labels=[0 1], + counts=[251 77] +) + +validation (n=41): +ADNIDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'bold', 'mean', 'std'], + num_rows: 66 +}), + labels=[0 1], + counts=[31 10] +) + +test (n=41): +ADNIDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'bold', 'mean', 'std'], + num_rows: 66 +}), + labels=[0 1], + counts=[32 9] +) + +extracting features for all splits +extract (train) [ 0/164] eta: 0:13:19 time: 4.8759 data: 3.7384 max mem: 2698 +extract (train) [ 20/164] eta: 0:01:01 time: 0.2040 data: 0.0749 max mem: 2851 +extract (train) [ 40/164] eta: 0:00:38 time: 0.1839 data: 0.0621 max mem: 2851 +extract (train) [ 60/164] eta: 0:00:27 time: 0.1833 data: 0.0599 max mem: 2851 +extract (train) [ 80/164] eta: 0:00:20 time: 0.1586 data: 0.0500 max mem: 2851 +extract (train) [100/164] eta: 0:00:14 time: 0.1713 data: 0.0571 max mem: 2851 +extract (train) [120/164] eta: 0:00:09 time: 0.1671 data: 0.0540 max mem: 2851 +extract (train) [140/164] eta: 0:00:05 time: 0.1662 data: 0.0552 max mem: 2851 +extract (train) [160/164] eta: 0:00:00 time: 0.1515 data: 0.0434 max mem: 2851 +extract (train) [163/164] eta: 0:00:00 time: 0.1526 data: 0.0444 max mem: 2851 +extract (train) Total time: 0:00:33 (0.2040 s / it) +extract (validation) [ 0/21] eta: 0:01:16 time: 3.6392 data: 3.4986 max mem: 2851 +extract (validation) [20/21] eta: 0:00:00 time: 0.1489 data: 0.0441 max mem: 2851 +extract (validation) Total time: 0:00:06 (0.3299 s / it) +extract (test) [ 0/21] eta: 0:01:14 time: 3.5608 data: 3.4453 max mem: 2851 +extract (test) [20/21] eta: 0:00:00 time: 0.1505 data: 0.0429 max mem: 2851 +extract (test) Total time: 0:00:06 (0.3278 s / it) +feature extraction time: 0:00:47 +train features: (328, 768) +validation features: (41, 768) +test features: (41, 768) +evaluating fixed splits +eval results (fixed splits): + +| model | repr | clf | dataset | trial | C | split | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:--------------|:--------|--------:|:--------|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | adni_ad_vs_cn | | 0.35938 | train | 0.9729 | 0.0079712 | 0.96114 | 0.011879 | 0.9465 | 0.015878 | +| flat_mae | patch | logistic | adni_ad_vs_cn | | 0.35938 | test | 0.78049 | 0.065371 | 0.69173 | 0.087286 | 0.69965 | 0.091793 | + + +evaluating random splits (n=100) +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 1, "C": 0.3593813663804626, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.056777302735242285, "f1": 0.6660633484162897, "f1_std": 0.0918901860847624, "bacc": 0.6516129032258065, "bacc_std": 0.08469408597884437} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 2, "C": 21.54434690031882, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.06474497630834652, "f1": 0.603225806451613, "f1_std": 0.08596418001238873, "bacc": 0.603225806451613, "bacc_std": 0.0857876001605776} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 3, "C": 0.005994842503189409, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.0462250398908317, "f1": 0.4831932773109243, "f1_std": 0.0716509834840611, "bacc": 0.5016129032258064, "bacc_std": 0.05500797586667784} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 4, "C": 0.046415888336127774, "split": "test", "acc": 0.8292682926829268, "acc_std": 0.05664158267180503, "f1": 0.7602339181286549, "f1_std": 0.08453071587056449, "bacc": 0.7516129032258064, "bacc_std": 0.08566494632050925} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 5, "C": 21.54434690031882, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.053022841990545105, "f1": 0.6117424242424243, "f1_std": 0.09259939721924956, "bacc": 0.6016129032258064, "bacc_std": 0.07859472409498693} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 6, "C": 0.3593813663804626, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.05623260521576052, "f1": 0.6660633484162897, "f1_std": 0.09115413497899383, "bacc": 0.6516129032258065, "bacc_std": 0.08346742091258198} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 7, "C": 2.782559402207126, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.05903194871983235, "f1": 0.6917293233082706, "f1_std": 0.08702051388096967, "bacc": 0.685483870967742, "bacc_std": 0.0865153334619792} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 8, "C": 0.046415888336127774, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.05469671939369925, "f1": 0.6117424242424243, "f1_std": 0.09348347877303971, "bacc": 0.6016129032258064, "bacc_std": 0.08048179608160029} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 9, "C": 2.782559402207126, "split": "test", "acc": 0.6585365853658537, "acc_std": 0.07135321562572267, "f1": 0.5651515151515152, "f1_std": 0.08191108023151765, "bacc": 0.5709677419354839, "bacc_std": 0.08715949205422714} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 10, "C": 0.046415888336127774, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.05620331495152888, "f1": 0.6117424242424243, "f1_std": 0.09331303010835147, "bacc": 0.6016129032258064, "bacc_std": 0.08068002317450142} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 11, "C": 0.046415888336127774, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.03263192234209673, "f1": 0.5119047619047619, "f1_std": 0.07753044814406698, "bacc": 0.5338709677419355, "bacc_std": 0.0502993105833598} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 12, "C": 166.81005372000556, "split": "test", "acc": 0.6585365853658537, "acc_std": 0.06004438176118303, "f1": 0.5017361111111112, "f1_std": 0.07770942535294129, "bacc": 0.5032258064516129, "bacc_std": 0.07207407010628541} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 13, "C": 0.046415888336127774, "split": "test", "acc": 0.8292682926829268, "acc_std": 0.05035835885888401, "f1": 0.7402714932126697, "f1_std": 0.08562307184607955, "bacc": 0.717741935483871, "bacc_std": 0.08353963156265} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 14, "C": 166.81005372000556, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.06607512894486327, "f1": 0.7410526315789474, "f1_std": 0.070926079455639, "bacc": 0.7870967741935484, "bacc_std": 0.07445149521989917} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 15, "C": 0.046415888336127774, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.05375324236585507, "f1": 0.6117424242424243, "f1_std": 0.09087886751002897, "bacc": 0.6016129032258064, "bacc_std": 0.07800846454778493} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 16, "C": 0.046415888336127774, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.03783793990968802, "f1": 0.5886287625418061, "f1_std": 0.09200822912538997, "bacc": 0.5838709677419355, "bacc_std": 0.06419406710764647} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 17, "C": 0.046415888336127774, "split": "test", "acc": 0.8292682926829268, "acc_std": 0.044931675276897676, "f1": 0.7144278606965174, "f1_std": 0.09590969060854648, "bacc": 0.6838709677419355, "bacc_std": 0.08164433437849941} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 18, "C": 2.782559402207126, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.04942395115978782, "f1": 0.6328358208955224, "f1_std": 0.09572457373510859, "bacc": 0.6177419354838709, "bacc_std": 0.07841563027738926} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 19, "C": 0.046415888336127774, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.06870971969097164, "f1": 0.5547201336675021, "f1_std": 0.08446923034397216, "bacc": 0.5532258064516129, "bacc_std": 0.08082334611877678} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 20, "C": 0.046415888336127774, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.06292448473605515, "f1": 0.6693548387096775, "f1_std": 0.08124251375463665, "bacc": 0.6693548387096775, "bacc_std": 0.08280770667709417} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 21, "C": 0.3593813663804626, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.05056529931038283, "f1": 0.6328358208955224, "f1_std": 0.09743545351671429, "bacc": 0.6177419354838709, "bacc_std": 0.0794998227080661} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 22, "C": 2.782559402207126, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.057449250811462585, "f1": 0.5340909090909092, "f1_std": 0.08486392093583857, "bacc": 0.535483870967742, "bacc_std": 0.07275478149928956} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 23, "C": 0.3593813663804626, "split": "test", "acc": 0.6585365853658537, "acc_std": 0.06390214112758714, "f1": 0.5370967741935484, "f1_std": 0.08193220238854117, "bacc": 0.5370967741935484, "bacc_std": 0.08276975348260547} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 24, "C": 0.3593813663804626, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.06337129851369873, "f1": 0.6693548387096775, "f1_std": 0.08382396757817713, "bacc": 0.6693548387096775, "bacc_std": 0.08484839488442959} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 25, "C": 2.782559402207126, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.06153917127673821, "f1": 0.603225806451613, "f1_std": 0.07969912285078558, "bacc": 0.603225806451613, "bacc_std": 0.08094078564257357} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 26, "C": 0.046415888336127774, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.06425653152902351, "f1": 0.6232247284878863, "f1_std": 0.08930649857330457, "bacc": 0.6193548387096774, "bacc_std": 0.08804018776564833} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 27, "C": 166.81005372000556, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.06096538450849701, "f1": 0.6693548387096775, "f1_std": 0.08176045272795313, "bacc": 0.6693548387096775, "bacc_std": 0.08479524828145396} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 28, "C": 0.046415888336127774, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.055427085512837065, "f1": 0.6660633484162897, "f1_std": 0.0893645933844759, "bacc": 0.6516129032258065, "bacc_std": 0.08287161591428983} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 29, "C": 0.046415888336127774, "split": "test", "acc": 0.8292682926829268, "acc_std": 0.053445497264693075, "f1": 0.7602339181286549, "f1_std": 0.079380553610426, "bacc": 0.7516129032258064, "bacc_std": 0.08167792252558663} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 30, "C": 0.046415888336127774, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.05701477103871648, "f1": 0.5918552036199095, "f1_std": 0.09062024307000272, "bacc": 0.5854838709677419, "bacc_std": 0.07993216791268484} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 31, "C": 0.046415888336127774, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.05561540407775266, "f1": 0.5340909090909092, "f1_std": 0.08416775828487492, "bacc": 0.535483870967742, "bacc_std": 0.07142128526982816} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 32, "C": 0.3593813663804626, "split": "test", "acc": 0.6097560975609756, "acc_std": 0.07557952188585837, "f1": 0.5287356321839081, "f1_std": 0.0789751204845968, "bacc": 0.5387096774193548, "bacc_std": 0.08637400825948494} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 33, "C": 2.782559402207126, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.07528989778915712, "f1": 0.6259649122807017, "f1_std": 0.0814172261774457, "bacc": 0.6548387096774193, "bacc_std": 0.08993065538711413} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 34, "C": 21.54434690031882, "split": "test", "acc": 0.6585365853658537, "acc_std": 0.07306742300492475, "f1": 0.5876436781609196, "f1_std": 0.0824722942105637, "bacc": 0.6048387096774194, "bacc_std": 0.09185936741505386} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 35, "C": 0.046415888336127774, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.05313715655081452, "f1": 0.6893939393939394, "f1_std": 0.09638344319220633, "bacc": 0.667741935483871, "bacc_std": 0.08632810598788053} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 36, "C": 10000.0, "split": "test", "acc": 0.6341463414634146, "acc_std": 0.07540074967634544, "f1": 0.5467943994104643, "f1_std": 0.08452142376981145, "bacc": 0.5548387096774194, "bacc_std": 0.09197821893005009} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 37, "C": 166.81005372000556, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.06017709339855881, "f1": 0.6232247284878863, "f1_std": 0.08684467740140013, "bacc": 0.6193548387096774, "bacc_std": 0.08495921008184767} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 38, "C": 0.046415888336127774, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.06386288107204473, "f1": 0.7354838709677419, "f1_std": 0.08885928033897642, "bacc": 0.7354838709677419, "bacc_std": 0.09066003230098596} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 39, "C": 0.046415888336127774, "split": "test", "acc": 0.6585365853658537, "acc_std": 0.060150495376112, "f1": 0.5017361111111112, "f1_std": 0.07409008156455914, "bacc": 0.5032258064516129, "bacc_std": 0.06858331588281359} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 40, "C": 166.81005372000556, "split": "test", "acc": 0.5853658536585366, "acc_std": 0.07072161408221543, "f1": 0.5108771929824562, "f1_std": 0.07402768430105099, "bacc": 0.5225806451612903, "bacc_std": 0.08523774818048828} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 41, "C": 0.046415888336127774, "split": "test", "acc": 0.8292682926829268, "acc_std": 0.055624195814625445, "f1": 0.7602339181286549, "f1_std": 0.08061611267826164, "bacc": 0.7516129032258064, "bacc_std": 0.0841698720880916} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 42, "C": 166.81005372000556, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.05698218722474701, "f1": 0.6117424242424243, "f1_std": 0.09639764448376878, "bacc": 0.6016129032258064, "bacc_std": 0.08248484684096037} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 43, "C": 166.81005372000556, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.05532971851851849, "f1": 0.6660633484162897, "f1_std": 0.08895932230298935, "bacc": 0.6516129032258065, "bacc_std": 0.08323101577845249} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 44, "C": 0.046415888336127774, "split": "test", "acc": 0.926829268292683, "acc_std": 0.03515888978951709, "f1": 0.8886877828054298, "f1_std": 0.06313048531501687, "bacc": 0.85, "bacc_std": 0.07207572406851005} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 45, "C": 0.005994842503189409, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.042804593147547455, "f1": 0.6554621848739496, "f1_std": 0.0973881805612465, "bacc": 0.6338709677419355, "bacc_std": 0.07568486192536661} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 46, "C": 21.54434690031882, "split": "test", "acc": 0.8292682926829268, "acc_std": 0.05655137751312312, "f1": 0.7602339181286549, "f1_std": 0.0816480998887171, "bacc": 0.7516129032258064, "bacc_std": 0.08253971036853185} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 47, "C": 21.54434690031882, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.06987736346660925, "f1": 0.603225806451613, "f1_std": 0.09173214444073939, "bacc": 0.603225806451613, "bacc_std": 0.09197901538716367} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 48, "C": 0.046415888336127774, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.05547943651718291, "f1": 0.5176470588235295, "f1_std": 0.078837803024788, "bacc": 0.5193548387096775, "bacc_std": 0.07010683470698613} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 49, "C": 2.782559402207126, "split": "test", "acc": 0.6585365853658537, "acc_std": 0.06453603229672865, "f1": 0.5017361111111112, "f1_std": 0.0845180832535193, "bacc": 0.5032258064516129, "bacc_std": 0.07788377336779623} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 50, "C": 0.046415888336127774, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.062339306806470374, "f1": 0.6693548387096775, "f1_std": 0.08387006308651135, "bacc": 0.6693548387096775, "bacc_std": 0.08282927108071605} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 51, "C": 0.3593813663804626, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.07013372117551617, "f1": 0.6072218128224024, "f1_std": 0.08216361470176779, "bacc": 0.6209677419354839, "bacc_std": 0.08960173523618896} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 52, "C": 0.005994842503189409, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.05025278159762534, "f1": 0.5512437810945273, "f1_std": 0.0874832722981575, "bacc": 0.5516129032258065, "bacc_std": 0.06946497324410605} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 53, "C": 0.046415888336127774, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.06262517981560091, "f1": 0.6693548387096775, "f1_std": 0.08476517664920384, "bacc": 0.6693548387096775, "bacc_std": 0.08516410619733678} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 54, "C": 0.3593813663804626, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.06757946387869665, "f1": 0.6479313036690086, "f1_std": 0.08491253815867307, "bacc": 0.6532258064516129, "bacc_std": 0.08907384833864762} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 55, "C": 0.3593813663804626, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.05826561265518859, "f1": 0.6440972222222222, "f1_std": 0.0875284452484059, "bacc": 0.635483870967742, "bacc_std": 0.0828444249862399} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 56, "C": 166.81005372000556, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.0663438127274126, "f1": 0.6232247284878863, "f1_std": 0.09165971470014568, "bacc": 0.6193548387096774, "bacc_std": 0.08932714436319593} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 57, "C": 0.046415888336127774, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.05313034939998667, "f1": 0.5512437810945273, "f1_std": 0.08782320740542782, "bacc": 0.5516129032258065, "bacc_std": 0.07005881281367536} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 58, "C": 0.046415888336127774, "split": "test", "acc": 0.8292682926829268, "acc_std": 0.04441435957108307, "f1": 0.7144278606965174, "f1_std": 0.09087195558940975, "bacc": 0.6838709677419355, "bacc_std": 0.07786548040371652} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 59, "C": 0.046415888336127774, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.05953705997952329, "f1": 0.6440972222222222, "f1_std": 0.09110070906098997, "bacc": 0.635483870967742, "bacc_std": 0.08704094841712581} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 60, "C": 2.782559402207126, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.06423825372873851, "f1": 0.6893939393939394, "f1_std": 0.07983275474525367, "bacc": 0.7032258064516128, "bacc_std": 0.08526702478149714} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 61, "C": 0.046415888336127774, "split": "test", "acc": 0.6341463414634146, "acc_std": 0.06758969188080778, "f1": 0.48621553884711777, "f1_std": 0.08025411898918883, "bacc": 0.48709677419354835, "bacc_std": 0.07719784783734585} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 62, "C": 0.046415888336127774, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.05707131537530443, "f1": 0.6660633484162897, "f1_std": 0.09384228631227812, "bacc": 0.6516129032258065, "bacc_std": 0.08589419785879866} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 63, "C": 21.54434690031882, "split": "test", "acc": 0.8292682926829268, "acc_std": 0.05527177996876997, "f1": 0.7759562841530054, "f1_std": 0.07220423092927852, "bacc": 0.7854838709677419, "bacc_std": 0.07700499727016788} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 64, "C": 0.005994842503189409, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.050115274613173943, "f1": 0.5512437810945273, "f1_std": 0.08444237000934565, "bacc": 0.5516129032258065, "bacc_std": 0.06829927410208697} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 65, "C": 0.3593813663804626, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.0654639962171105, "f1": 0.6232247284878863, "f1_std": 0.08927818133359565, "bacc": 0.6193548387096774, "bacc_std": 0.08652184220149063} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 66, "C": 0.046415888336127774, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.058749936398006256, "f1": 0.6917293233082706, "f1_std": 0.08319838334221297, "bacc": 0.685483870967742, "bacc_std": 0.0821351570075161} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 67, "C": 2.782559402207126, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.06121949276066157, "f1": 0.6479313036690086, "f1_std": 0.0772430061592202, "bacc": 0.6532258064516129, "bacc_std": 0.08019379979458682} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 68, "C": 0.046415888336127774, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.06429547719602341, "f1": 0.603225806451613, "f1_std": 0.08449949898311071, "bacc": 0.603225806451613, "bacc_std": 0.08582379760399615} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 69, "C": 0.046415888336127774, "split": "test", "acc": 0.8292682926829268, "acc_std": 0.056262218581728994, "f1": 0.7759562841530054, "f1_std": 0.07421202367295644, "bacc": 0.7854838709677419, "bacc_std": 0.0788217960712651} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 70, "C": 0.046415888336127774, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.0442484736929116, "f1": 0.6554621848739496, "f1_std": 0.09666570476936415, "bacc": 0.6338709677419355, "bacc_std": 0.07625314131807351} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 71, "C": 0.046415888336127774, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.04674980554887712, "f1": 0.4831932773109243, "f1_std": 0.07063349867255511, "bacc": 0.5016129032258064, "bacc_std": 0.05467920588954962} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 72, "C": 166.81005372000556, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.05439625910082593, "f1": 0.5340909090909092, "f1_std": 0.08347922599310839, "bacc": 0.535483870967742, "bacc_std": 0.07018913974532945} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 73, "C": 0.046415888336127774, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.05182554362513193, "f1": 0.6660633484162897, "f1_std": 0.08560068467145669, "bacc": 0.6516129032258065, "bacc_std": 0.07863050618965924} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 74, "C": 2.782559402207126, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.048544208250519846, "f1": 0.6117424242424243, "f1_std": 0.0856261546513437, "bacc": 0.6016129032258064, "bacc_std": 0.072853289420564} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 75, "C": 0.3593813663804626, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.054262213964843424, "f1": 0.5512437810945273, "f1_std": 0.09177864758379295, "bacc": 0.5516129032258065, "bacc_std": 0.07444532846512908} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 76, "C": 0.3593813663804626, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.05475561409966371, "f1": 0.5918552036199095, "f1_std": 0.08717342146568872, "bacc": 0.5854838709677419, "bacc_std": 0.07749445040719104} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 77, "C": 0.046415888336127774, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.049088079003943935, "f1": 0.6893939393939394, "f1_std": 0.08999185366061344, "bacc": 0.667741935483871, "bacc_std": 0.08057546381751003} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 78, "C": 0.046415888336127774, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.06042268327683236, "f1": 0.5176470588235295, "f1_std": 0.08377333481201364, "bacc": 0.5193548387096775, "bacc_std": 0.07411694636028357} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 79, "C": 0.046415888336127774, "split": "test", "acc": 0.8780487804878049, "acc_std": 0.04486383656190078, "f1": 0.8144796380090498, "f1_std": 0.07830214823007461, "bacc": 0.7838709677419355, "bacc_std": 0.07978521661838658} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 80, "C": 0.3593813663804626, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.06102936167385063, "f1": 0.6232247284878863, "f1_std": 0.08445268760659484, "bacc": 0.6193548387096774, "bacc_std": 0.08202727243738614} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 81, "C": 0.3593813663804626, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.06291782881369468, "f1": 0.6232247284878863, "f1_std": 0.08777846972326891, "bacc": 0.6193548387096774, "bacc_std": 0.0860375792710733} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 82, "C": 0.046415888336127774, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.04929994153722763, "f1": 0.6893939393939394, "f1_std": 0.091605225241605, "bacc": 0.667741935483871, "bacc_std": 0.08154920860141544} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 83, "C": 166.81005372000556, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.0566242717384583, "f1": 0.6660633484162897, "f1_std": 0.09071192226566561, "bacc": 0.6516129032258065, "bacc_std": 0.08321644477229907} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 84, "C": 0.046415888336127774, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.04762844495246643, "f1": 0.569327731092437, "f1_std": 0.09002029727165198, "bacc": 0.567741935483871, "bacc_std": 0.06843856979502076} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 85, "C": 1291.5496650148827, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.06374911787424356, "f1": 0.7119437939110069, "f1_std": 0.08137868755159147, "bacc": 0.7193548387096774, "bacc_std": 0.08658305030071213} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 86, "C": 0.046415888336127774, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.06406233950807655, "f1": 0.603225806451613, "f1_std": 0.08361427023511157, "bacc": 0.603225806451613, "bacc_std": 0.08405969702474414} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 87, "C": 0.046415888336127774, "split": "test", "acc": 0.8292682926829268, "acc_std": 0.03695034209696424, "f1": 0.6800445930880714, "f1_std": 0.10170758721376494, "bacc": 0.65, "bacc_std": 0.07574820129877671} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 88, "C": 2.782559402207126, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.06202797242755983, "f1": 0.6693548387096775, "f1_std": 0.08161223707213297, "bacc": 0.6693548387096775, "bacc_std": 0.08314445955712758} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 89, "C": 166.81005372000556, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.06712726864927336, "f1": 0.603225806451613, "f1_std": 0.08858769271479208, "bacc": 0.603225806451613, "bacc_std": 0.0895727530297455} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 90, "C": 0.046415888336127774, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.057421306365731305, "f1": 0.6660633484162897, "f1_std": 0.0940792722959424, "bacc": 0.6516129032258065, "bacc_std": 0.08473083359870186} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 91, "C": 2.782559402207126, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.06882183500336372, "f1": 0.603225806451613, "f1_std": 0.0891319215544285, "bacc": 0.603225806451613, "bacc_std": 0.09073738850802916} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 92, "C": 0.3593813663804626, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.06187417909970478, "f1": 0.5918552036199095, "f1_std": 0.0935682212324786, "bacc": 0.5854838709677419, "bacc_std": 0.08385778376527067} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 93, "C": 0.3593813663804626, "split": "test", "acc": 0.6585365853658537, "acc_std": 0.07253740547701784, "f1": 0.5651515151515152, "f1_std": 0.08451121590977838, "bacc": 0.5709677419354839, "bacc_std": 0.08976745329558958} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 94, "C": 0.3593813663804626, "split": "test", "acc": 0.6585365853658537, "acc_std": 0.06899256354929931, "f1": 0.5370967741935484, "f1_std": 0.0830066972343742, "bacc": 0.5370967741935484, "bacc_std": 0.08204523833980355} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 95, "C": 166.81005372000556, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.05505897546538654, "f1": 0.7152777777777778, "f1_std": 0.08563849952990228, "bacc": 0.7016129032258065, "bacc_std": 0.08247490325555723} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 96, "C": 0.3593813663804626, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.053255671693438755, "f1": 0.6660633484162897, "f1_std": 0.08911950846399921, "bacc": 0.6516129032258065, "bacc_std": 0.08299672122205083} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 97, "C": 0.3593813663804626, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.055455498501940724, "f1": 0.7152777777777778, "f1_std": 0.08638243283818432, "bacc": 0.7016129032258065, "bacc_std": 0.0859956242988164} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 98, "C": 0.3593813663804626, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.05447002788811535, "f1": 0.6660633484162897, "f1_std": 0.09094705758028766, "bacc": 0.6516129032258065, "bacc_std": 0.08366466755623} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 99, "C": 0.046415888336127774, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.05855062839682676, "f1": 0.5729166666666666, "f1_std": 0.08365350427319664, "bacc": 0.5693548387096774, "bacc_std": 0.07731306379588616} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 100, "C": 0.3593813663804626, "split": "test", "acc": 0.6341463414634146, "acc_std": 0.06508309793733516, "f1": 0.5199063231850116, "f1_std": 0.07768625087962247, "bacc": 0.5209677419354839, "bacc_std": 0.08066571989566027} +eval results (random splits): + +| model | repr | clf | dataset | split | n_trials | C | C_std | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:--------------|:--------|-----------:|-------:|--------:|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | adni_ad_vs_cn | train | 100 | 134.65 | 1006 | 0.94786 | 0.048752 | 0.91919 | 0.078628 | 0.90364 | 0.091063 | +| flat_mae | patch | logistic | adni_ad_vs_cn | test | 100 | 134.65 | 1006 | 0.7461 | 0.059854 | 0.6288 | 0.079992 | 0.62481 | 0.075062 | + + +done! total time: 0:04:42 diff --git a/input_space_v3/flat_lr1e-3_6/eval_v2/hcpya_task21__patch__attn/config.yaml b/input_space_v3/flat_lr1e-3_6/eval_v2/hcpya_task21__patch__attn/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..4fe3d8f56e4e493e3b2b04e318faed04c92070f9 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_6/eval_v2/hcpya_task21__patch__attn/config.yaml @@ -0,0 +1,96 @@ +output_root: experiments/input_space_v3/output +name_prefix: eval_probe +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_6; eval v2 (hcpya_task21 patch attn) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +dataset_kwargs: {} +classifier_kwargs: + embed_dim: null + dropout: 0.0 + xavier_init: true + norm: true +lr_scale_grid: +- 0.02 +- 0.023 +- 0.028 +- 0.033 +- 0.038 +- 0.045 +- 0.053 +- 0.062 +- 0.074 +- 0.087 +- 0.1 +- 0.12 +- 0.14 +- 0.17 +- 0.2 +- 0.23 +- 0.27 +- 0.32 +- 0.38 +- 0.44 +- 0.52 +- 0.61 +- 0.72 +- 0.85 +- 1 +- 1.2 +- 1.4 +- 1.6 +- 1.9 +- 2.3 +- 2.7 +- 3.1 +- 3.7 +- 4.3 +- 5.1 +- 6 +- 7.1 +- 8.3 +- 9.8 +- 12 +- 14 +- 16 +- 19 +- 22 +- 26 +- 31 +- 36 +- 43 +- 50 +wd_scale_grid: +- 1.0 +num_workers: 8 +prefetch_factor: null +balanced_sampling: false +epochs: 20 +steps_per_epoch: 200 +batch_size: 64 +accum_iter: 2 +lr: 0.0003 +warmup_epochs: 5 +no_decay: false +weight_decay: 0.05 +clip_grad: 1.0 +metrics: +- acc +- f1 +cv_metric: acc +early_stopping: true +amp: true +device: cuda +seed: 4466 +debug: false +wandb: false +wandb_entity: null +wandb_project: fMRI-fm-eval +name: input_space_v3/flat_lr1e-3_6/eval_v2/hcpya_task21__patch__attn +model: flat_mae +representation: patch +classifier: attn +dataset: hcpya_task21 +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/eval_v2/hcpya_task21__patch__attn +remote_dir: null diff --git a/input_space_v3/flat_lr1e-3_6/eval_v2/hcpya_task21__patch__attn/eval_log.json b/input_space_v3/flat_lr1e-3_6/eval_v2/hcpya_task21__patch__attn/eval_log.json new file mode 100644 index 0000000000000000000000000000000000000000..779ab2dc18702ab747c27c33ebf22dda0151dfdb --- /dev/null +++ b/input_space_v3/flat_lr1e-3_6/eval_v2/hcpya_task21__patch__attn/eval_log.json @@ -0,0 +1 @@ +{"eval/epoch": 15, "eval/id_best": 23, "eval/lr_best": 0.00025499999999999996, "eval/wd_best": 0.05, "eval/train/loss": 0.007370820734649897, "eval/train/acc": 0.998842044318122, "eval/train/acc_std": 0.00024793216731712345, "eval/train/f1": 0.9989592042327925, "eval/train/f1_std": 0.00023890972300818076, "eval/validation/loss": 0.025197792798280716, "eval/validation/acc": 0.9928075396825397, "eval/validation/acc_std": 0.0013201249140421193, "eval/validation/f1": 0.9918747267244115, "eval/validation/f1_std": 0.0016735179355156133, "eval/test/loss": 0.037296611815690994, "eval/test/acc": 0.989484126984127, "eval/test/acc_std": 0.0013996636478220414, "eval/test/f1": 0.9874937975034098, "eval/test/f1_std": 0.001833265930145017} diff --git a/input_space_v3/flat_lr1e-3_6/eval_v2/hcpya_task21__patch__attn/eval_log_best.json b/input_space_v3/flat_lr1e-3_6/eval_v2/hcpya_task21__patch__attn/eval_log_best.json new file mode 100644 index 0000000000000000000000000000000000000000..2ceda125ce244000068aa29b5b66648473555dd5 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_6/eval_v2/hcpya_task21__patch__attn/eval_log_best.json @@ -0,0 +1 @@ +{"eval/best/epoch": 15, "eval/best/id_best": 23, "eval/best/lr_best": 0.00025499999999999996, "eval/best/wd_best": 0.05, "eval/best/train/loss": 0.007370820734649897, "eval/best/train/acc": 0.998842044318122, "eval/best/train/acc_std": 0.00024793216731712345, "eval/best/train/f1": 0.9989592042327925, "eval/best/train/f1_std": 0.00023890972300818076, "eval/best/validation/loss": 0.025197792798280716, "eval/best/validation/acc": 0.9928075396825397, "eval/best/validation/acc_std": 0.0013201249140421193, "eval/best/validation/f1": 0.9918747267244115, "eval/best/validation/f1_std": 0.0016735179355156133, "eval/best/test/loss": 0.037296611815690994, "eval/best/test/acc": 0.989484126984127, "eval/best/test/acc_std": 0.0013996636478220414, "eval/best/test/f1": 0.9874937975034098, "eval/best/test/f1_std": 0.001833265930145017} diff --git a/input_space_v3/flat_lr1e-3_6/eval_v2/hcpya_task21__patch__attn/eval_log_last.json b/input_space_v3/flat_lr1e-3_6/eval_v2/hcpya_task21__patch__attn/eval_log_last.json new file mode 100644 index 0000000000000000000000000000000000000000..add69b6215f4b3d7620e2d3ef2806d5efbbb60c3 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_6/eval_v2/hcpya_task21__patch__attn/eval_log_last.json @@ -0,0 +1 @@ +{"eval/last/epoch": 19, "eval/last/id_best": 27, "eval/last/lr_best": 0.00047999999999999996, "eval/last/wd_best": 0.05, "eval/last/train/loss": 0.000978027586825192, "eval/last/train/acc": 1.0, "eval/last/train/acc_std": 0.0, "eval/last/train/f1": 1.0, "eval/last/train/f1_std": 0.0, "eval/last/validation/loss": 0.029679344967007637, "eval/last/validation/acc": 0.9923115079365079, "eval/last/validation/acc_std": 0.001371974313055474, "eval/last/validation/f1": 0.9906093996383457, "eval/last/validation/f1_std": 0.0018549785249156923, "eval/last/test/loss": 0.043238621205091476, "eval/last/test/acc": 0.9878968253968254, "eval/last/test/acc_std": 0.0014766454218735215, "eval/last/test/f1": 0.9853474270335302, "eval/last/test/f1_std": 0.001981690511882912} diff --git a/input_space_v3/flat_lr1e-3_6/eval_v2/hcpya_task21__patch__attn/eval_table.csv b/input_space_v3/flat_lr1e-3_6/eval_v2/hcpya_task21__patch__attn/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..370915805dc842837069632c00f6e91e6c2c777f --- /dev/null +++ b/input_space_v3/flat_lr1e-3_6/eval_v2/hcpya_task21__patch__attn/eval_table.csv @@ -0,0 +1,4 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,patch,attn,hcpya_task21,best,15,0.00025499999999999996,0.05,23,"[0.85, 1.0]",train,0.007370820734649897,0.998842044318122,0.00024793216731712345,0.9989592042327925,0.00023890972300818076 +flat_mae,patch,attn,hcpya_task21,best,15,0.00025499999999999996,0.05,23,"[0.85, 1.0]",validation,0.025197792798280716,0.9928075396825397,0.0013201249140421193,0.9918747267244115,0.0016735179355156133 +flat_mae,patch,attn,hcpya_task21,best,15,0.00025499999999999996,0.05,23,"[0.85, 1.0]",test,0.037296611815690994,0.989484126984127,0.0013996636478220414,0.9874937975034098,0.001833265930145017 diff --git a/input_space_v3/flat_lr1e-3_6/eval_v2/hcpya_task21__patch__attn/eval_table_best.csv b/input_space_v3/flat_lr1e-3_6/eval_v2/hcpya_task21__patch__attn/eval_table_best.csv new file mode 100644 index 0000000000000000000000000000000000000000..370915805dc842837069632c00f6e91e6c2c777f --- /dev/null +++ b/input_space_v3/flat_lr1e-3_6/eval_v2/hcpya_task21__patch__attn/eval_table_best.csv @@ -0,0 +1,4 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,patch,attn,hcpya_task21,best,15,0.00025499999999999996,0.05,23,"[0.85, 1.0]",train,0.007370820734649897,0.998842044318122,0.00024793216731712345,0.9989592042327925,0.00023890972300818076 +flat_mae,patch,attn,hcpya_task21,best,15,0.00025499999999999996,0.05,23,"[0.85, 1.0]",validation,0.025197792798280716,0.9928075396825397,0.0013201249140421193,0.9918747267244115,0.0016735179355156133 +flat_mae,patch,attn,hcpya_task21,best,15,0.00025499999999999996,0.05,23,"[0.85, 1.0]",test,0.037296611815690994,0.989484126984127,0.0013996636478220414,0.9874937975034098,0.001833265930145017 diff --git a/input_space_v3/flat_lr1e-3_6/eval_v2/hcpya_task21__patch__attn/eval_table_last.csv b/input_space_v3/flat_lr1e-3_6/eval_v2/hcpya_task21__patch__attn/eval_table_last.csv new file mode 100644 index 0000000000000000000000000000000000000000..b32d25a89eee38d5ebb40cf80ccc7dac3a14df7f --- /dev/null +++ b/input_space_v3/flat_lr1e-3_6/eval_v2/hcpya_task21__patch__attn/eval_table_last.csv @@ -0,0 +1,4 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,patch,attn,hcpya_task21,last,19,0.00047999999999999996,0.05,27,"[1.6, 1.0]",train,0.000978027586825192,1.0,0.0,1.0,0.0 +flat_mae,patch,attn,hcpya_task21,last,19,0.00047999999999999996,0.05,27,"[1.6, 1.0]",validation,0.029679344967007637,0.9923115079365079,0.001371974313055474,0.9906093996383457,0.0018549785249156923 +flat_mae,patch,attn,hcpya_task21,last,19,0.00047999999999999996,0.05,27,"[1.6, 1.0]",test,0.043238621205091476,0.9878968253968254,0.0014766454218735215,0.9853474270335302,0.001981690511882912 diff --git a/input_space_v3/flat_lr1e-3_6/eval_v2/hcpya_task21__patch__attn/log.txt b/input_space_v3/flat_lr1e-3_6/eval_v2/hcpya_task21__patch__attn/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..a6ce053d53084ec2b8dbbbc4ab24325af6d0f55a --- /dev/null +++ b/input_space_v3/flat_lr1e-3_6/eval_v2/hcpya_task21__patch__attn/log.txt @@ -0,0 +1,887 @@ +fMRI foundation model probe eval +version: 0.1.dev86+gf97f52698 +sha: bcce2b486277d3a5b520775efd9cdf1a2affce36, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-04-08 21:11:19 +config: +output_root: experiments/input_space_v3/output +name_prefix: eval_probe +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_6; eval v2 (hcpya_task21 patch attn) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +dataset_kwargs: {} +classifier_kwargs: + embed_dim: null + dropout: 0.0 + xavier_init: true + norm: true +lr_scale_grid: +- 0.02 +- 0.023 +- 0.028 +- 0.033 +- 0.038 +- 0.045 +- 0.053 +- 0.062 +- 0.074 +- 0.087 +- 0.1 +- 0.12 +- 0.14 +- 0.17 +- 0.2 +- 0.23 +- 0.27 +- 0.32 +- 0.38 +- 0.44 +- 0.52 +- 0.61 +- 0.72 +- 0.85 +- 1 +- 1.2 +- 1.4 +- 1.6 +- 1.9 +- 2.3 +- 2.7 +- 3.1 +- 3.7 +- 4.3 +- 5.1 +- 6 +- 7.1 +- 8.3 +- 9.8 +- 12 +- 14 +- 16 +- 19 +- 22 +- 26 +- 31 +- 36 +- 43 +- 50 +wd_scale_grid: +- 1.0 +num_workers: 8 +prefetch_factor: null +balanced_sampling: false +epochs: 20 +steps_per_epoch: 200 +batch_size: 64 +accum_iter: 2 +lr: 0.0003 +warmup_epochs: 5 +no_decay: false +weight_decay: 0.05 +clip_grad: 1.0 +metrics: +- acc +- f1 +cv_metric: acc +early_stopping: true +amp: true +device: cuda +seed: 4466 +debug: false +wandb: false +wandb_entity: null +wandb_project: fMRI-fm-eval +name: input_space_v3/flat_lr1e-3_6/eval_v2/hcpya_task21__patch__attn +model: flat_mae +representation: patch +classifier: attn +dataset: hcpya_task21 +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/eval_v2/hcpya_task21__patch__attn +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=True, reg_tokens=0, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: hcpya_task21 (flat) +train (n=18999): +HFDataset( + dataset=Dataset({ + features: ['sub', 'task', 'cond', 'cond_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 18999 +}), + labels=[ 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20], + counts=[ 832 1248 3201 1660 832 832 832 832 832 1248 1247 1243 832 416 + 416 416 416 416 416 416 416] +) + +validation (n=4032): +HFDataset( + dataset=Dataset({ + features: ['sub', 'task', 'cond', 'cond_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 4032 +}), + labels=[ 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20], + counts=[176 264 688 352 176 176 176 176 176 264 264 264 176 88 88 88 88 88 + 88 88 88] +) + +test (n=5040): +HFDataset( + dataset=Dataset({ + features: ['sub', 'task', 'cond', 'cond_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 5040 +}), + labels=[ 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20], + counts=[220 330 860 440 220 220 220 220 220 330 330 330 220 110 110 110 110 110 + 110 110 110] +) + +running backbone on example batch to get embedding dim +embedding feature dim (patch): 768 +initializing sweep of classifier heads +classifiers: +ModuleList( + (0-48): 49 x AttnPoolClassifier( + (kv): Linear(in_features=768, out_features=1536, bias=True) + (linear): Linear(in_features=768, out_features=21, bias=True) + ) +) +classifier params (train): 58.7M (58.7M) +setting up optimizer +total batch size: 128 = 64 bs per gpu x 2 accum +lr: 3.00e-04 +full schedule: epochs = 20 (steps = 4000) (decay = True) +warmup: epochs = 5 (steps = 1000) +start training for 20 epochs +train: [0] [ 0/400] eta: 0:30:29 lr: nan time: 4.5732 data: 4.0692 max mem: 21740 +train: [0] [ 20/400] eta: 0:04:09 lr: 0.000003 loss: 3.0490 (3.0439) grad: 0.2507 (0.2598) time: 0.4596 data: 0.0035 max mem: 22446 +train: [0] [ 40/400] eta: 0:03:24 lr: 0.000006 loss: 3.0056 (3.0037) grad: 0.2507 (0.2586) time: 0.4755 data: 0.0030 max mem: 22446 +train: [0] [ 60/400] eta: 0:03:04 lr: 0.000009 loss: 2.8853 (2.9471) grad: 0.2493 (0.2548) time: 0.4926 data: 0.0036 max mem: 22446 +train: [0] [ 80/400] eta: 0:02:48 lr: 0.000012 loss: 2.7777 (2.8908) grad: 0.2385 (0.2485) time: 0.4814 data: 0.0036 max mem: 22446 +train: [0] [100/400] eta: 0:02:35 lr: 0.000015 loss: 2.6239 (2.8253) grad: 0.2250 (0.2448) time: 0.4741 data: 0.0036 max mem: 22446 +train: [0] [120/400] eta: 0:02:22 lr: 0.000018 loss: 2.5216 (2.7591) grad: 0.2254 (0.2408) time: 0.4717 data: 0.0034 max mem: 22446 +train: [0] [140/400] eta: 0:02:10 lr: 0.000021 loss: 2.3556 (2.6935) grad: 0.2232 (0.2392) time: 0.4545 data: 0.0035 max mem: 22446 +train: [0] [160/400] eta: 0:01:59 lr: 0.000024 loss: 2.2548 (2.6355) grad: 0.2137 (0.2348) time: 0.4608 data: 0.0033 max mem: 22446 +train: [0] [180/400] eta: 0:01:48 lr: 0.000027 loss: 2.1519 (2.5761) grad: 0.1968 (0.2306) time: 0.4593 data: 0.0033 max mem: 22446 +train: [0] [200/400] eta: 0:01:37 lr: 0.000030 loss: 2.0881 (2.5210) grad: 0.1986 (0.2277) time: 0.4653 data: 0.0033 max mem: 22446 +train: [0] [220/400] eta: 0:01:27 lr: 0.000033 loss: 1.9656 (2.4678) grad: 0.1903 (0.2241) time: 0.4559 data: 0.0033 max mem: 22446 +train: [0] [240/400] eta: 0:01:17 lr: 0.000036 loss: 1.8772 (2.4144) grad: 0.1924 (0.2221) time: 0.4409 data: 0.0033 max mem: 22446 +train: [0] [260/400] eta: 0:01:07 lr: 0.000039 loss: 1.8072 (2.3664) grad: 0.1941 (0.2199) time: 0.4531 data: 0.0034 max mem: 22446 +train: [0] [280/400] eta: 0:00:57 lr: 0.000042 loss: 1.7801 (2.3237) grad: 0.1803 (0.2168) time: 0.4936 data: 0.0035 max mem: 22446 +train: [0] [300/400] eta: 0:00:49 lr: 0.000045 loss: 1.7425 (2.2824) grad: 0.1685 (0.2138) time: 0.6557 data: 0.1726 max mem: 22446 +train: [0] [320/400] eta: 0:00:39 lr: 0.000048 loss: 1.6734 (2.2419) grad: 0.1676 (0.2111) time: 0.4765 data: 0.0030 max mem: 22446 +train: [0] [340/400] eta: 0:00:29 lr: 0.000051 loss: 1.6060 (2.2035) grad: 0.1769 (0.2094) time: 0.4696 data: 0.0035 max mem: 22446 +train: [0] [360/400] eta: 0:00:19 lr: 0.000054 loss: 1.5651 (2.1680) grad: 0.1738 (0.2071) time: 0.4754 data: 0.0035 max mem: 22446 +train: [0] [380/400] eta: 0:00:09 lr: 0.000057 loss: 1.5355 (2.1338) grad: 0.1659 (0.2050) time: 0.4752 data: 0.0036 max mem: 22446 +train: [0] [399/400] eta: 0:00:00 lr: 0.000060 loss: 1.4890 (2.0995) grad: 0.1651 (0.2033) time: 0.4713 data: 0.0035 max mem: 22446 +train: [0] Total time: 0:03:15 (0.4886 s / it) +train: [0] Summary: lr: 0.000060 loss: 1.4890 (2.0995) grad: 0.1651 (0.2033) +eval (validation): [0] [ 0/63] eta: 0:03:21 time: 3.1993 data: 2.9645 max mem: 22446 +eval (validation): [0] [20/63] eta: 0:00:20 time: 0.3430 data: 0.0030 max mem: 22446 +eval (validation): [0] [40/63] eta: 0:00:10 time: 0.3955 data: 0.0037 max mem: 22446 +eval (validation): [0] [60/63] eta: 0:00:01 time: 0.3525 data: 0.0034 max mem: 22446 +eval (validation): [0] [62/63] eta: 0:00:00 time: 0.3522 data: 0.0034 max mem: 22446 +eval (validation): [0] Total time: 0:00:26 (0.4137 s / it) +cv: [0] best hparam: (26, 1.0) (044) ('044_lr2.6e+01_wd1.0e+00') loss: 0.049 acc: 0.984 f1: 0.984 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/eval_v2/hcpya_task21__patch__attn/checkpoint-best.pth +train: [1] [ 0/400] eta: 0:25:07 lr: nan time: 3.7688 data: 3.3654 max mem: 22446 +train: [1] [ 20/400] eta: 0:04:18 lr: 0.000063 loss: 1.4265 (1.4399) grad: 0.1569 (0.1648) time: 0.5261 data: 0.0035 max mem: 22446 +train: [1] [ 40/400] eta: 0:03:27 lr: 0.000066 loss: 1.4130 (1.4151) grad: 0.1618 (0.1636) time: 0.4643 data: 0.0033 max mem: 22446 +train: [1] [ 60/400] eta: 0:03:02 lr: 0.000069 loss: 1.3738 (1.3930) grad: 0.1582 (0.1604) time: 0.4581 data: 0.0035 max mem: 22446 +train: [1] [ 80/400] eta: 0:02:46 lr: 0.000072 loss: 1.3228 (1.3746) grad: 0.1481 (0.1581) time: 0.4756 data: 0.0034 max mem: 22446 +train: [1] [100/400] eta: 0:02:34 lr: 0.000075 loss: 1.3079 (1.3625) grad: 0.1507 (0.1579) time: 0.4883 data: 0.0034 max mem: 22446 +train: [1] [120/400] eta: 0:02:22 lr: 0.000078 loss: 1.2804 (1.3455) grad: 0.1475 (0.1571) time: 0.4748 data: 0.0035 max mem: 22446 +train: [1] [140/400] eta: 0:02:11 lr: 0.000081 loss: 1.2509 (1.3308) grad: 0.1474 (0.1556) time: 0.4813 data: 0.0034 max mem: 22446 +train: [1] [160/400] eta: 0:02:00 lr: 0.000084 loss: 1.2193 (1.3146) grad: 0.1443 (0.1543) time: 0.4702 data: 0.0034 max mem: 22446 +train: [1] [180/400] eta: 0:01:49 lr: 0.000087 loss: 1.2031 (1.3006) grad: 0.1448 (0.1540) time: 0.4704 data: 0.0033 max mem: 22446 +train: [1] [200/400] eta: 0:01:39 lr: 0.000090 loss: 1.1722 (1.2868) grad: 0.1448 (0.1530) time: 0.4835 data: 0.0033 max mem: 22446 +train: [1] [220/400] eta: 0:01:28 lr: 0.000093 loss: 1.1289 (1.2712) grad: 0.1452 (0.1530) time: 0.4780 data: 0.0033 max mem: 22446 +train: [1] [240/400] eta: 0:01:18 lr: 0.000096 loss: 1.1111 (1.2579) grad: 0.1480 (0.1521) time: 0.4736 data: 0.0034 max mem: 22446 +train: [1] [260/400] eta: 0:01:08 lr: 0.000099 loss: 1.1145 (1.2458) grad: 0.1421 (0.1512) time: 0.4703 data: 0.0035 max mem: 22446 +train: [1] [280/400] eta: 0:00:58 lr: 0.000102 loss: 1.0687 (1.2329) grad: 0.1374 (0.1507) time: 0.4670 data: 0.0036 max mem: 22446 +train: [1] [300/400] eta: 0:00:49 lr: 0.000105 loss: 1.0487 (1.2205) grad: 0.1317 (0.1493) time: 0.6392 data: 0.1753 max mem: 22446 +train: [1] [320/400] eta: 0:00:39 lr: 0.000108 loss: 1.0444 (1.2091) grad: 0.1317 (0.1484) time: 0.4693 data: 0.0038 max mem: 22446 +train: [1] [340/400] eta: 0:00:29 lr: 0.000111 loss: 1.0057 (1.1962) grad: 0.1278 (0.1471) time: 0.4658 data: 0.0035 max mem: 22446 +train: [1] [360/400] eta: 0:00:19 lr: 0.000114 loss: 1.0057 (1.1861) grad: 0.1278 (0.1469) time: 0.4745 data: 0.0035 max mem: 22446 +train: [1] [380/400] eta: 0:00:09 lr: 0.000117 loss: 0.9946 (1.1757) grad: 0.1337 (0.1465) time: 0.4626 data: 0.0034 max mem: 22446 +train: [1] [399/400] eta: 0:00:00 lr: 0.000120 loss: 0.9733 (1.1655) grad: 0.1333 (0.1455) time: 0.4736 data: 0.0035 max mem: 22446 +train: [1] Total time: 0:03:16 (0.4919 s / it) +train: [1] Summary: lr: 0.000120 loss: 0.9733 (1.1655) grad: 0.1333 (0.1455) +eval (validation): [1] [ 0/63] eta: 0:03:22 time: 3.2137 data: 2.9079 max mem: 22446 +eval (validation): [1] [20/63] eta: 0:00:22 time: 0.3967 data: 0.0032 max mem: 22446 +eval (validation): [1] [40/63] eta: 0:00:10 time: 0.3607 data: 0.0036 max mem: 22446 +eval (validation): [1] [60/63] eta: 0:00:01 time: 0.3500 data: 0.0034 max mem: 22446 +eval (validation): [1] [62/63] eta: 0:00:00 time: 0.3450 data: 0.0034 max mem: 22446 +eval (validation): [1] Total time: 0:00:26 (0.4173 s / it) +cv: [1] best hparam: (5.1, 1.0) (034) ('034_lr5.1e+00_wd1.0e+00') loss: 0.038 acc: 0.990 f1: 0.989 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/eval_v2/hcpya_task21__patch__attn/checkpoint-best.pth +train: [2] [ 0/400] eta: 0:22:51 lr: nan time: 3.4290 data: 3.0603 max mem: 22446 +train: [2] [ 20/400] eta: 0:03:57 lr: 0.000123 loss: 0.8932 (0.9174) grad: 0.1393 (0.1355) time: 0.4839 data: 0.0027 max mem: 22446 +train: [2] [ 40/400] eta: 0:03:15 lr: 0.000126 loss: 0.9250 (0.9258) grad: 0.1399 (0.1416) time: 0.4551 data: 0.0034 max mem: 22446 +train: [2] [ 60/400] eta: 0:02:55 lr: 0.000129 loss: 0.9127 (0.9148) grad: 0.1406 (0.1416) time: 0.4628 data: 0.0033 max mem: 22446 +train: [2] [ 80/400] eta: 0:02:41 lr: 0.000132 loss: 0.8954 (0.9104) grad: 0.1354 (0.1403) time: 0.4701 data: 0.0034 max mem: 22446 +train: [2] [100/400] eta: 0:02:29 lr: 0.000135 loss: 0.8791 (0.9038) grad: 0.1344 (0.1395) time: 0.4730 data: 0.0034 max mem: 22446 +train: [2] [120/400] eta: 0:02:18 lr: 0.000138 loss: 0.8643 (0.9017) grad: 0.1361 (0.1424) time: 0.4722 data: 0.0033 max mem: 22446 +train: [2] [140/400] eta: 0:02:07 lr: 0.000141 loss: 0.8613 (0.8961) grad: 0.1499 (0.1459) time: 0.4721 data: 0.0035 max mem: 22446 +train: [2] [160/400] eta: 0:01:57 lr: 0.000144 loss: 0.8538 (0.8932) grad: 0.1811 (0.1528) time: 0.4641 data: 0.0035 max mem: 22446 +train: [2] [180/400] eta: 0:01:46 lr: 0.000147 loss: 0.8548 (0.8894) grad: 0.1870 (0.1556) time: 0.4644 data: 0.0033 max mem: 22446 +train: [2] [200/400] eta: 0:01:36 lr: 0.000150 loss: 0.8387 (0.8840) grad: 0.1733 (0.1598) time: 0.4619 data: 0.0034 max mem: 22446 +train: [2] [220/400] eta: 0:01:26 lr: 0.000153 loss: 0.8503 (0.8840) grad: 0.1899 (0.1659) time: 0.4634 data: 0.0033 max mem: 22446 +train: [2] [240/400] eta: 0:01:16 lr: 0.000156 loss: 0.8620 (0.8817) grad: 0.2019 (0.1722) time: 0.4628 data: 0.0034 max mem: 22446 +train: [2] [260/400] eta: 0:01:06 lr: 0.000159 loss: 0.8353 (0.8788) grad: 0.1959 (0.1745) time: 0.4609 data: 0.0034 max mem: 22446 +train: [2] [280/400] eta: 0:00:57 lr: 0.000162 loss: 0.8110 (0.8754) grad: 0.1959 (0.1769) time: 0.4646 data: 0.0034 max mem: 22446 +train: [2] [300/400] eta: 0:00:48 lr: 0.000165 loss: 0.8302 (0.8731) grad: 0.2031 (0.1811) time: 0.6138 data: 0.1631 max mem: 22446 +train: [2] [320/400] eta: 0:00:38 lr: 0.000168 loss: 0.8302 (0.8699) grad: 0.2084 (0.1828) time: 0.4498 data: 0.0026 max mem: 22446 +train: [2] [340/400] eta: 0:00:28 lr: 0.000171 loss: 0.8387 (0.8692) grad: 0.1929 (0.1833) time: 0.4627 data: 0.0035 max mem: 22446 +train: [2] [360/400] eta: 0:00:19 lr: 0.000174 loss: 0.8511 (0.8674) grad: 0.1929 (0.1843) time: 0.4734 data: 0.0035 max mem: 22446 +train: [2] [380/400] eta: 0:00:09 lr: 0.000177 loss: 0.7753 (0.8609) grad: 0.2006 (0.1853) time: 0.4713 data: 0.0034 max mem: 22446 +train: [2] [399/400] eta: 0:00:00 lr: 0.000180 loss: 0.7015 (0.8534) grad: 0.2075 (0.1866) time: 0.4735 data: 0.0034 max mem: 22446 +train: [2] Total time: 0:03:12 (0.4815 s / it) +train: [2] Summary: lr: 0.000180 loss: 0.7015 (0.8534) grad: 0.2075 (0.1866) +eval (validation): [2] [ 0/63] eta: 0:03:29 time: 3.3254 data: 3.0646 max mem: 22446 +eval (validation): [2] [20/63] eta: 0:00:22 time: 0.3825 data: 0.0025 max mem: 22446 +eval (validation): [2] [40/63] eta: 0:00:10 time: 0.3497 data: 0.0033 max mem: 22446 +eval (validation): [2] [60/63] eta: 0:00:01 time: 0.3432 data: 0.0032 max mem: 22446 +eval (validation): [2] [62/63] eta: 0:00:00 time: 0.3411 data: 0.0032 max mem: 22446 +eval (validation): [2] Total time: 0:00:25 (0.4096 s / it) +cv: [2] best hparam: (4.3, 1.0) (033) ('033_lr4.3e+00_wd1.0e+00') loss: 0.034 acc: 0.990 f1: 0.989 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/eval_v2/hcpya_task21__patch__attn/checkpoint-best.pth +train: [3] [ 0/400] eta: 0:23:23 lr: nan time: 3.5082 data: 3.0653 max mem: 22446 +train: [3] [ 20/400] eta: 0:04:14 lr: 0.000183 loss: 0.6066 (0.6728) grad: 0.1827 (0.1914) time: 0.5272 data: 0.0039 max mem: 22446 +train: [3] [ 40/400] eta: 0:03:26 lr: 0.000186 loss: 0.6661 (0.6838) grad: 0.1851 (0.1908) time: 0.4724 data: 0.0034 max mem: 22446 +train: [3] [ 60/400] eta: 0:03:03 lr: 0.000189 loss: 0.6933 (0.6979) grad: 0.1835 (0.1874) time: 0.4740 data: 0.0034 max mem: 22446 +train: [3] [ 80/400] eta: 0:02:46 lr: 0.000192 loss: 0.6911 (0.7148) grad: 0.1797 (0.1921) time: 0.4560 data: 0.0034 max mem: 22446 +train: [3] [100/400] eta: 0:02:33 lr: 0.000195 loss: 0.6781 (0.7166) grad: 0.1769 (0.1959) time: 0.4743 data: 0.0035 max mem: 22446 +train: [3] [120/400] eta: 0:02:21 lr: 0.000198 loss: 0.6813 (0.7206) grad: 0.2305 (0.2067) time: 0.4840 data: 0.0033 max mem: 22446 +train: [3] [140/400] eta: 0:02:10 lr: 0.000201 loss: 0.6876 (0.7333) grad: 0.2398 (0.2111) time: 0.4707 data: 0.0033 max mem: 22446 +train: [3] [160/400] eta: 0:01:59 lr: 0.000204 loss: 0.7826 (0.7354) grad: 0.2473 (0.2257) time: 0.4716 data: 0.0033 max mem: 22446 +train: [3] [180/400] eta: 0:01:48 lr: 0.000207 loss: 0.7342 (0.7344) grad: 0.2503 (0.2306) time: 0.4774 data: 0.0034 max mem: 22446 +train: [3] [200/400] eta: 0:01:38 lr: 0.000210 loss: 0.6856 (0.7394) grad: 0.2355 (0.2296) time: 0.4711 data: 0.0033 max mem: 22446 +train: [3] [220/400] eta: 0:01:28 lr: 0.000213 loss: 0.6667 (0.7308) grad: 0.1937 (0.2280) time: 0.4763 data: 0.0034 max mem: 22446 +train: [3] [240/400] eta: 0:01:18 lr: 0.000216 loss: 0.6496 (0.7398) grad: 0.2141 (0.2288) time: 0.4702 data: 0.0036 max mem: 22446 +train: [3] [260/400] eta: 0:01:08 lr: 0.000219 loss: 0.6514 (0.7361) grad: 0.2573 (0.2353) time: 0.4721 data: 0.0035 max mem: 22446 +train: [3] [280/400] eta: 0:00:58 lr: 0.000222 loss: 0.6457 (0.7378) grad: 0.2615 (0.2383) time: 0.4791 data: 0.0034 max mem: 22446 +train: [3] [300/400] eta: 0:00:49 lr: 0.000225 loss: 0.6690 (0.7399) grad: 0.2801 (0.2428) time: 0.6326 data: 0.1639 max mem: 22446 +train: [3] [320/400] eta: 0:00:39 lr: 0.000228 loss: 0.7421 (0.7386) grad: 0.3066 (0.2462) time: 0.4471 data: 0.0033 max mem: 22446 +train: [3] [340/400] eta: 0:00:29 lr: 0.000231 loss: 0.5943 (0.7306) grad: 0.3007 (0.2480) time: 0.4593 data: 0.0035 max mem: 22446 +train: [3] [360/400] eta: 0:00:19 lr: 0.000234 loss: 0.5737 (0.7229) grad: 0.2847 (0.2508) time: 0.4684 data: 0.0034 max mem: 22446 +train: [3] [380/400] eta: 0:00:09 lr: 0.000237 loss: 0.6133 (0.7240) grad: 0.2847 (0.2557) time: 0.4715 data: 0.0034 max mem: 22446 +train: [3] [399/400] eta: 0:00:00 lr: 0.000240 loss: 0.7304 (0.7244) grad: 0.3378 (0.2605) time: 0.4682 data: 0.0035 max mem: 22446 +train: [3] Total time: 0:03:15 (0.4890 s / it) +train: [3] Summary: lr: 0.000240 loss: 0.7304 (0.7244) grad: 0.3378 (0.2605) +eval (validation): [3] [ 0/63] eta: 0:03:24 time: 3.2539 data: 2.9404 max mem: 22446 +eval (validation): [3] [20/63] eta: 0:00:22 time: 0.3841 data: 0.0034 max mem: 22446 +eval (validation): [3] [40/63] eta: 0:00:10 time: 0.3490 data: 0.0033 max mem: 22446 +eval (validation): [3] [60/63] eta: 0:00:01 time: 0.3453 data: 0.0032 max mem: 22446 +eval (validation): [3] [62/63] eta: 0:00:00 time: 0.3409 data: 0.0032 max mem: 22446 +eval (validation): [3] Total time: 0:00:25 (0.4086 s / it) +cv: [3] best hparam: (2.7, 1.0) (030) ('030_lr2.7e+00_wd1.0e+00') loss: 0.038 acc: 0.988 f1: 0.988 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [4] [ 0/400] eta: 0:21:27 lr: nan time: 3.2179 data: 2.8849 max mem: 22446 +train: [4] [ 20/400] eta: 0:03:45 lr: 0.000243 loss: 0.6884 (0.7511) grad: 0.3038 (0.3462) time: 0.4623 data: 0.0036 max mem: 22446 +train: [4] [ 40/400] eta: 0:03:13 lr: 0.000246 loss: 0.6917 (0.7949) grad: 0.3444 (0.3469) time: 0.4803 data: 0.0031 max mem: 22446 +train: [4] [ 60/400] eta: 0:02:55 lr: 0.000249 loss: 0.6847 (0.7440) grad: 0.3923 (0.3977) time: 0.4732 data: 0.0036 max mem: 22446 +train: [4] [ 80/400] eta: 0:02:40 lr: 0.000252 loss: 0.6112 (0.7317) grad: 0.4382 (0.4054) time: 0.4570 data: 0.0033 max mem: 22446 +train: [4] [100/400] eta: 0:02:27 lr: 0.000255 loss: 0.6345 (0.7569) grad: 0.4179 (0.4234) time: 0.4573 data: 0.0035 max mem: 22446 +train: [4] [120/400] eta: 0:02:16 lr: 0.000258 loss: 0.6523 (0.7610) grad: 0.4134 (0.4200) time: 0.4592 data: 0.0032 max mem: 22446 +train: [4] [140/400] eta: 0:02:05 lr: 0.000261 loss: 0.7870 (0.7793) grad: 0.3805 (0.4218) time: 0.4579 data: 0.0033 max mem: 22446 +train: [4] [160/400] eta: 0:01:55 lr: 0.000264 loss: 0.8252 (0.8078) grad: 0.4039 (0.4256) time: 0.4549 data: 0.0033 max mem: 22446 +train: [4] [180/400] eta: 0:01:45 lr: 0.000267 loss: 0.8971 (0.8150) grad: 0.4024 (0.4241) time: 0.4666 data: 0.0033 max mem: 22446 +train: [4] [200/400] eta: 0:01:35 lr: 0.000270 loss: 0.9162 (0.8251) grad: 0.4024 (0.4328) time: 0.4719 data: 0.0032 max mem: 22446 +train: [4] [220/400] eta: 0:01:25 lr: 0.000273 loss: 0.7922 (0.8204) grad: 0.4000 (0.4278) time: 0.4732 data: 0.0033 max mem: 22446 +train: [4] [240/400] eta: 0:01:16 lr: 0.000276 loss: 0.6947 (0.8184) grad: 0.4182 (0.4415) time: 0.4726 data: 0.0034 max mem: 22446 +train: [4] [260/400] eta: 0:01:06 lr: 0.000279 loss: 0.9254 (0.8453) grad: 0.4770 (0.4437) time: 0.4736 data: 0.0033 max mem: 22446 +train: [4] [280/400] eta: 0:00:57 lr: 0.000282 loss: 1.0530 (0.8629) grad: 0.5329 (0.4552) time: 0.4740 data: 0.0035 max mem: 22446 +train: [4] [300/400] eta: 0:00:48 lr: 0.000285 loss: 0.7496 (0.8722) grad: 0.5431 (0.4619) time: 0.6636 data: 0.1751 max mem: 22446 +train: [4] [320/400] eta: 0:00:39 lr: 0.000288 loss: 0.5790 (0.8530) grad: 0.4115 (0.4641) time: 0.4831 data: 0.0027 max mem: 22446 +train: [4] [340/400] eta: 0:00:29 lr: 0.000291 loss: 0.5439 (0.8361) grad: 0.4099 (0.4717) time: 0.4660 data: 0.0034 max mem: 22446 +train: [4] [360/400] eta: 0:00:19 lr: 0.000294 loss: 0.5939 (0.8373) grad: 0.4263 (0.4700) time: 0.4761 data: 0.0034 max mem: 22446 +train: [4] [380/400] eta: 0:00:09 lr: 0.000297 loss: 0.7701 (0.8407) grad: 0.4325 (0.4710) time: 0.4708 data: 0.0035 max mem: 22446 +train: [4] [399/400] eta: 0:00:00 lr: 0.000300 loss: 0.7461 (0.8388) grad: 0.4192 (0.4679) time: 0.4610 data: 0.0034 max mem: 22446 +train: [4] Total time: 0:03:13 (0.4849 s / it) +train: [4] Summary: lr: 0.000300 loss: 0.7461 (0.8388) grad: 0.4192 (0.4679) +eval (validation): [4] [ 0/63] eta: 0:03:16 time: 3.1167 data: 2.8788 max mem: 22446 +eval (validation): [4] [20/63] eta: 0:00:20 time: 0.3402 data: 0.0038 max mem: 22446 +eval (validation): [4] [40/63] eta: 0:00:09 time: 0.3431 data: 0.0032 max mem: 22446 +eval (validation): [4] [60/63] eta: 0:00:01 time: 0.3419 data: 0.0028 max mem: 22446 +eval (validation): [4] [62/63] eta: 0:00:00 time: 0.3386 data: 0.0032 max mem: 22446 +eval (validation): [4] Total time: 0:00:24 (0.3896 s / it) +cv: [4] best hparam: (3.1, 1.0) (031) ('031_lr3.1e+00_wd1.0e+00') loss: 0.032 acc: 0.991 f1: 0.989 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/eval_v2/hcpya_task21__patch__attn/checkpoint-best.pth +train: [5] [ 0/400] eta: 0:21:17 lr: nan time: 3.1937 data: 2.8431 max mem: 22446 +train: [5] [ 20/400] eta: 0:03:46 lr: 0.000300 loss: 0.5012 (0.6804) grad: 0.3669 (0.3750) time: 0.4666 data: 0.0038 max mem: 22446 +train: [5] [ 40/400] eta: 0:03:13 lr: 0.000300 loss: 0.5206 (0.7000) grad: 0.3737 (0.3767) time: 0.4752 data: 0.0032 max mem: 22446 +train: [5] [ 60/400] eta: 0:02:54 lr: 0.000300 loss: 0.7249 (0.7652) grad: 0.3951 (0.4329) time: 0.4627 data: 0.0034 max mem: 22446 +train: [5] [ 80/400] eta: 0:02:39 lr: 0.000300 loss: 0.6719 (0.7566) grad: 0.4298 (0.4447) time: 0.4554 data: 0.0033 max mem: 22446 +train: [5] [100/400] eta: 0:02:27 lr: 0.000300 loss: 0.6791 (0.8211) grad: 0.4449 (0.4570) time: 0.4588 data: 0.0034 max mem: 22446 +train: [5] [120/400] eta: 0:02:15 lr: 0.000300 loss: 0.9002 (0.8438) grad: 0.4822 (0.4610) time: 0.4540 data: 0.0032 max mem: 22446 +train: [5] [140/400] eta: 0:02:05 lr: 0.000300 loss: 0.9297 (0.8667) grad: 0.4822 (0.4678) time: 0.4672 data: 0.0034 max mem: 22446 +train: [5] [160/400] eta: 0:01:55 lr: 0.000299 loss: 0.9882 (0.8928) grad: 0.5008 (0.4718) time: 0.4590 data: 0.0034 max mem: 22446 +train: [5] [180/400] eta: 0:01:45 lr: 0.000299 loss: 0.6607 (0.8661) grad: 0.4837 (0.4742) time: 0.4709 data: 0.0034 max mem: 22446 +train: [5] [200/400] eta: 0:01:35 lr: 0.000299 loss: 0.5768 (0.8652) grad: 0.4985 (0.4804) time: 0.4716 data: 0.0033 max mem: 22446 +train: [5] [220/400] eta: 0:01:25 lr: 0.000299 loss: 0.5465 (0.8565) grad: 0.4705 (0.4863) time: 0.4734 data: 0.0033 max mem: 22446 +train: [5] [240/400] eta: 0:01:16 lr: 0.000299 loss: 0.6696 (0.8535) grad: 0.4492 (0.4857) time: 0.4675 data: 0.0033 max mem: 22446 +train: [5] [260/400] eta: 0:01:06 lr: 0.000299 loss: 0.8103 (0.8716) grad: 0.4704 (0.4881) time: 0.4697 data: 0.0033 max mem: 22446 +train: [5] [280/400] eta: 0:00:57 lr: 0.000298 loss: 1.0721 (0.8810) grad: 0.4802 (0.4850) time: 0.4710 data: 0.0035 max mem: 22446 +train: [5] [300/400] eta: 0:00:48 lr: 0.000298 loss: 0.7331 (0.8669) grad: 0.4787 (0.4853) time: 0.6225 data: 0.1690 max mem: 22446 +train: [5] [320/400] eta: 0:00:38 lr: 0.000298 loss: 0.5430 (0.8514) grad: 0.4643 (0.4803) time: 0.4503 data: 0.0028 max mem: 22446 +train: [5] [340/400] eta: 0:00:28 lr: 0.000298 loss: 0.5333 (0.8412) grad: 0.4250 (0.4785) time: 0.4566 data: 0.0033 max mem: 22446 +train: [5] [360/400] eta: 0:00:19 lr: 0.000297 loss: 0.5398 (0.8306) grad: 0.4395 (0.4740) time: 0.4704 data: 0.0035 max mem: 22446 +train: [5] [380/400] eta: 0:00:09 lr: 0.000297 loss: 0.5555 (0.8190) grad: 0.4233 (0.4702) time: 0.4711 data: 0.0035 max mem: 22446 +train: [5] [399/400] eta: 0:00:00 lr: 0.000297 loss: 0.5456 (0.8072) grad: 0.4007 (0.4684) time: 0.4537 data: 0.0033 max mem: 22446 +train: [5] Total time: 0:03:11 (0.4796 s / it) +train: [5] Summary: lr: 0.000297 loss: 0.5456 (0.8072) grad: 0.4007 (0.4684) +eval (validation): [5] [ 0/63] eta: 0:03:19 time: 3.1718 data: 2.9282 max mem: 22446 +eval (validation): [5] [20/63] eta: 0:00:21 time: 0.3735 data: 0.0037 max mem: 22446 +eval (validation): [5] [40/63] eta: 0:00:09 time: 0.3479 data: 0.0031 max mem: 22446 +eval (validation): [5] [60/63] eta: 0:00:01 time: 0.3417 data: 0.0033 max mem: 22446 +eval (validation): [5] [62/63] eta: 0:00:00 time: 0.3365 data: 0.0033 max mem: 22446 +eval (validation): [5] Total time: 0:00:25 (0.4024 s / it) +cv: [5] best hparam: (3.7, 1.0) (032) ('032_lr3.7e+00_wd1.0e+00') loss: 0.029 acc: 0.990 f1: 0.988 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [6] [ 0/400] eta: 0:22:03 lr: nan time: 3.3083 data: 2.9695 max mem: 22446 +train: [6] [ 20/400] eta: 0:03:54 lr: 0.000296 loss: 0.4318 (0.5015) grad: 0.4176 (0.4489) time: 0.4823 data: 0.0021 max mem: 22446 +train: [6] [ 40/400] eta: 0:03:15 lr: 0.000296 loss: 0.4476 (0.5518) grad: 0.3923 (0.4059) time: 0.4675 data: 0.0034 max mem: 22446 +train: [6] [ 60/400] eta: 0:02:56 lr: 0.000296 loss: 0.5566 (0.6134) grad: 0.3987 (0.4277) time: 0.4683 data: 0.0034 max mem: 22446 +train: [6] [ 80/400] eta: 0:02:41 lr: 0.000295 loss: 0.6985 (0.6533) grad: 0.4762 (0.4400) time: 0.4620 data: 0.0032 max mem: 22446 +train: [6] [100/400] eta: 0:02:28 lr: 0.000295 loss: 0.6763 (0.6423) grad: 0.4532 (0.4328) time: 0.4513 data: 0.0033 max mem: 22446 +train: [6] [120/400] eta: 0:02:17 lr: 0.000295 loss: 0.4718 (0.6239) grad: 0.3589 (0.4236) time: 0.4656 data: 0.0034 max mem: 22446 +train: [6] [140/400] eta: 0:02:06 lr: 0.000294 loss: 0.4718 (0.6314) grad: 0.3647 (0.4224) time: 0.4600 data: 0.0035 max mem: 22446 +train: [6] [160/400] eta: 0:01:55 lr: 0.000294 loss: 0.5316 (0.6203) grad: 0.3867 (0.4167) time: 0.4668 data: 0.0034 max mem: 22446 +train: [6] [180/400] eta: 0:01:45 lr: 0.000293 loss: 0.5770 (0.6282) grad: 0.3769 (0.4167) time: 0.4610 data: 0.0035 max mem: 22446 +train: [6] [200/400] eta: 0:01:35 lr: 0.000293 loss: 0.6687 (0.6570) grad: 0.3769 (0.4157) time: 0.4626 data: 0.0035 max mem: 22446 +train: [6] [220/400] eta: 0:01:25 lr: 0.000292 loss: 0.6005 (0.6528) grad: 0.3918 (0.4237) time: 0.4514 data: 0.0034 max mem: 22446 +train: [6] [240/400] eta: 0:01:15 lr: 0.000292 loss: 0.4002 (0.6320) grad: 0.3338 (0.4143) time: 0.4592 data: 0.0034 max mem: 22446 +train: [6] [260/400] eta: 0:01:06 lr: 0.000291 loss: 0.4114 (0.6234) grad: 0.3540 (0.4126) time: 0.4587 data: 0.0034 max mem: 22446 +train: [6] [280/400] eta: 0:00:56 lr: 0.000291 loss: 0.4948 (0.6325) grad: 0.3857 (0.4163) time: 0.4620 data: 0.0035 max mem: 22446 +train: [6] [300/400] eta: 0:00:48 lr: 0.000290 loss: 0.4948 (0.6216) grad: 0.3367 (0.4104) time: 0.6222 data: 0.1752 max mem: 22446 +train: [6] [320/400] eta: 0:00:38 lr: 0.000290 loss: 0.4253 (0.6144) grad: 0.3314 (0.4075) time: 0.4742 data: 0.0043 max mem: 22446 +train: [6] [340/400] eta: 0:00:28 lr: 0.000289 loss: 0.4373 (0.6072) grad: 0.2749 (0.4002) time: 0.4670 data: 0.0035 max mem: 22446 +train: [6] [360/400] eta: 0:00:19 lr: 0.000288 loss: 0.3651 (0.5981) grad: 0.2641 (0.3962) time: 0.4585 data: 0.0034 max mem: 22446 +train: [6] [380/400] eta: 0:00:09 lr: 0.000288 loss: 0.3599 (0.5896) grad: 0.3064 (0.3912) time: 0.4670 data: 0.0034 max mem: 22446 +train: [6] [399/400] eta: 0:00:00 lr: 0.000287 loss: 0.3360 (0.5750) grad: 0.3122 (0.3865) time: 0.4570 data: 0.0034 max mem: 22446 +train: [6] Total time: 0:03:11 (0.4786 s / it) +train: [6] Summary: lr: 0.000287 loss: 0.3360 (0.5750) grad: 0.3122 (0.3865) +eval (validation): [6] [ 0/63] eta: 0:03:23 time: 3.2297 data: 2.9907 max mem: 22446 +eval (validation): [6] [20/63] eta: 0:00:20 time: 0.3496 data: 0.0035 max mem: 22446 +eval (validation): [6] [40/63] eta: 0:00:09 time: 0.3467 data: 0.0030 max mem: 22446 +eval (validation): [6] [60/63] eta: 0:00:01 time: 0.3329 data: 0.0028 max mem: 22446 +eval (validation): [6] [62/63] eta: 0:00:00 time: 0.3311 data: 0.0026 max mem: 22446 +eval (validation): [6] Total time: 0:00:24 (0.3928 s / it) +cv: [6] best hparam: (6, 1.0) (035) ('035_lr6.0e+00_wd1.0e+00') loss: 0.045 acc: 0.992 f1: 0.989 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/eval_v2/hcpya_task21__patch__attn/checkpoint-best.pth +train: [7] [ 0/400] eta: 0:22:31 lr: nan time: 3.3798 data: 3.0138 max mem: 22446 +train: [7] [ 20/400] eta: 0:03:53 lr: 0.000286 loss: 0.2993 (0.4384) grad: 0.3069 (0.4130) time: 0.4749 data: 0.0032 max mem: 22446 +train: [7] [ 40/400] eta: 0:03:15 lr: 0.000286 loss: 0.2993 (0.3601) grad: 0.3104 (0.3594) time: 0.4673 data: 0.0036 max mem: 22446 +train: [7] [ 60/400] eta: 0:02:55 lr: 0.000285 loss: 0.3523 (0.4296) grad: 0.3104 (0.3571) time: 0.4663 data: 0.0035 max mem: 22446 +train: [7] [ 80/400] eta: 0:02:41 lr: 0.000284 loss: 0.4508 (0.4299) grad: 0.2973 (0.3455) time: 0.4611 data: 0.0033 max mem: 22446 +train: [7] [100/400] eta: 0:02:28 lr: 0.000284 loss: 0.3567 (0.4289) grad: 0.3183 (0.3466) time: 0.4620 data: 0.0034 max mem: 22446 +train: [7] [120/400] eta: 0:02:17 lr: 0.000283 loss: 0.3518 (0.4187) grad: 0.3099 (0.3346) time: 0.4675 data: 0.0033 max mem: 22446 +train: [7] [140/400] eta: 0:02:06 lr: 0.000282 loss: 0.3234 (0.4157) grad: 0.2626 (0.3355) time: 0.4637 data: 0.0033 max mem: 22446 +train: [7] [160/400] eta: 0:01:55 lr: 0.000282 loss: 0.4079 (0.4296) grad: 0.2770 (0.3406) time: 0.4581 data: 0.0034 max mem: 22446 +train: [7] [180/400] eta: 0:01:45 lr: 0.000281 loss: 0.3591 (0.4299) grad: 0.3038 (0.3417) time: 0.4606 data: 0.0033 max mem: 22446 +train: [7] [200/400] eta: 0:01:35 lr: 0.000280 loss: 0.3389 (0.4212) grad: 0.3184 (0.3448) time: 0.4532 data: 0.0029 max mem: 22446 +train: [7] [220/400] eta: 0:01:25 lr: 0.000279 loss: 0.3097 (0.4283) grad: 0.3333 (0.3439) time: 0.4638 data: 0.0034 max mem: 22446 +train: [7] [240/400] eta: 0:01:16 lr: 0.000278 loss: 0.3719 (0.4304) grad: 0.3333 (0.3467) time: 0.4623 data: 0.0034 max mem: 22446 +train: [7] [260/400] eta: 0:01:06 lr: 0.000278 loss: 0.3719 (0.4227) grad: 0.3348 (0.3442) time: 0.4674 data: 0.0033 max mem: 22446 +train: [7] [280/400] eta: 0:00:56 lr: 0.000277 loss: 0.3230 (0.4324) grad: 0.3005 (0.3405) time: 0.4666 data: 0.0035 max mem: 22446 +train: [7] [300/400] eta: 0:00:48 lr: 0.000276 loss: 0.3449 (0.4354) grad: 0.2878 (0.3371) time: 0.6516 data: 0.1731 max mem: 22446 +train: [7] [320/400] eta: 0:00:38 lr: 0.000275 loss: 0.3373 (0.4362) grad: 0.2760 (0.3341) time: 0.4671 data: 0.0032 max mem: 22446 +train: [7] [340/400] eta: 0:00:29 lr: 0.000274 loss: 0.2950 (0.4276) grad: 0.2431 (0.3282) time: 0.4678 data: 0.0034 max mem: 22446 +train: [7] [360/400] eta: 0:00:19 lr: 0.000273 loss: 0.2639 (0.4219) grad: 0.2527 (0.3250) time: 0.4645 data: 0.0034 max mem: 22446 +train: [7] [380/400] eta: 0:00:09 lr: 0.000272 loss: 0.2272 (0.4120) grad: 0.2613 (0.3207) time: 0.4639 data: 0.0035 max mem: 22446 +train: [7] [399/400] eta: 0:00:00 lr: 0.000271 loss: 0.1837 (0.4025) grad: 0.2188 (0.3168) time: 0.4710 data: 0.0035 max mem: 22446 +train: [7] Total time: 0:03:12 (0.4816 s / it) +train: [7] Summary: lr: 0.000271 loss: 0.1837 (0.4025) grad: 0.2188 (0.3168) +eval (validation): [7] [ 0/63] eta: 0:03:17 time: 3.1331 data: 2.8973 max mem: 22446 +eval (validation): [7] [20/63] eta: 0:00:20 time: 0.3472 data: 0.0038 max mem: 22446 +eval (validation): [7] [40/63] eta: 0:00:09 time: 0.3410 data: 0.0030 max mem: 22446 +eval (validation): [7] [60/63] eta: 0:00:01 time: 0.3414 data: 0.0033 max mem: 22446 +eval (validation): [7] [62/63] eta: 0:00:00 time: 0.3388 data: 0.0033 max mem: 22446 +eval (validation): [7] Total time: 0:00:24 (0.3913 s / it) +cv: [7] best hparam: (3.7, 1.0) (032) ('032_lr3.7e+00_wd1.0e+00') loss: 0.033 acc: 0.991 f1: 0.990 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [8] [ 0/400] eta: 0:22:43 lr: nan time: 3.4080 data: 2.9826 max mem: 22446 +train: [8] [ 20/400] eta: 0:03:54 lr: 0.000270 loss: 0.2030 (0.2183) grad: 0.1958 (0.1927) time: 0.4773 data: 0.0029 max mem: 22446 +train: [8] [ 40/400] eta: 0:03:15 lr: 0.000270 loss: 0.1974 (0.2240) grad: 0.2001 (0.1902) time: 0.4636 data: 0.0034 max mem: 22446 +train: [8] [ 60/400] eta: 0:02:55 lr: 0.000269 loss: 0.1995 (0.2252) grad: 0.2001 (0.1962) time: 0.4626 data: 0.0034 max mem: 22446 +train: [8] [ 80/400] eta: 0:02:41 lr: 0.000268 loss: 0.2043 (0.2401) grad: 0.2091 (0.2004) time: 0.4645 data: 0.0033 max mem: 22446 +train: [8] [100/400] eta: 0:02:28 lr: 0.000267 loss: 0.2478 (0.2415) grad: 0.2166 (0.2039) time: 0.4620 data: 0.0034 max mem: 22446 +train: [8] [120/400] eta: 0:02:17 lr: 0.000266 loss: 0.2610 (0.2649) grad: 0.2364 (0.2163) time: 0.4613 data: 0.0034 max mem: 22446 +train: [8] [140/400] eta: 0:02:06 lr: 0.000265 loss: 0.3229 (0.2729) grad: 0.2394 (0.2203) time: 0.4664 data: 0.0034 max mem: 22446 +train: [8] [160/400] eta: 0:01:56 lr: 0.000264 loss: 0.2330 (0.2686) grad: 0.2091 (0.2234) time: 0.4691 data: 0.0033 max mem: 22446 +train: [8] [180/400] eta: 0:01:46 lr: 0.000263 loss: 0.2330 (0.2710) grad: 0.2059 (0.2243) time: 0.4637 data: 0.0033 max mem: 22446 +train: [8] [200/400] eta: 0:01:35 lr: 0.000262 loss: 0.2341 (0.2717) grad: 0.2485 (0.2268) time: 0.4494 data: 0.0032 max mem: 22446 +train: [8] [220/400] eta: 0:01:25 lr: 0.000260 loss: 0.2190 (0.2694) grad: 0.2192 (0.2271) time: 0.4649 data: 0.0033 max mem: 22446 +train: [8] [240/400] eta: 0:01:16 lr: 0.000259 loss: 0.2123 (0.2654) grad: 0.2192 (0.2291) time: 0.4600 data: 0.0033 max mem: 22446 +train: [8] [260/400] eta: 0:01:06 lr: 0.000258 loss: 0.2123 (0.2669) grad: 0.2174 (0.2283) time: 0.4656 data: 0.0033 max mem: 22446 +train: [8] [280/400] eta: 0:00:56 lr: 0.000257 loss: 0.2326 (0.2664) grad: 0.2387 (0.2301) time: 0.4674 data: 0.0033 max mem: 22446 +train: [8] [300/400] eta: 0:00:48 lr: 0.000256 loss: 0.2449 (0.2707) grad: 0.2764 (0.2337) time: 0.6232 data: 0.1686 max mem: 22446 +train: [8] [320/400] eta: 0:00:38 lr: 0.000255 loss: 0.2443 (0.2690) grad: 0.2566 (0.2317) time: 0.4671 data: 0.0028 max mem: 22446 +train: [8] [340/400] eta: 0:00:28 lr: 0.000254 loss: 0.2063 (0.2647) grad: 0.1727 (0.2320) time: 0.4680 data: 0.0034 max mem: 22446 +train: [8] [360/400] eta: 0:00:19 lr: 0.000253 loss: 0.1720 (0.2598) grad: 0.1634 (0.2288) time: 0.4691 data: 0.0035 max mem: 22446 +train: [8] [380/400] eta: 0:00:09 lr: 0.000252 loss: 0.1645 (0.2558) grad: 0.1851 (0.2275) time: 0.4662 data: 0.0036 max mem: 22446 +train: [8] [399/400] eta: 0:00:00 lr: 0.000250 loss: 0.1889 (0.2548) grad: 0.1851 (0.2262) time: 0.4726 data: 0.0035 max mem: 22446 +train: [8] Total time: 0:03:12 (0.4808 s / it) +train: [8] Summary: lr: 0.000250 loss: 0.1889 (0.2548) grad: 0.1851 (0.2262) +eval (validation): [8] [ 0/63] eta: 0:03:24 time: 3.2428 data: 2.9898 max mem: 22446 +eval (validation): [8] [20/63] eta: 0:00:21 time: 0.3606 data: 0.0039 max mem: 22446 +eval (validation): [8] [40/63] eta: 0:00:09 time: 0.3533 data: 0.0029 max mem: 22446 +eval (validation): [8] [60/63] eta: 0:00:01 time: 0.3438 data: 0.0030 max mem: 22446 +eval (validation): [8] [62/63] eta: 0:00:00 time: 0.3384 data: 0.0033 max mem: 22446 +eval (validation): [8] Total time: 0:00:25 (0.4012 s / it) +cv: [8] best hparam: (2.3, 1.0) (029) ('029_lr2.3e+00_wd1.0e+00') loss: 0.029 acc: 0.992 f1: 0.990 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [9] [ 0/400] eta: 0:21:20 lr: nan time: 3.2011 data: 2.8580 max mem: 22446 +train: [9] [ 20/400] eta: 0:03:47 lr: 0.000249 loss: 0.1835 (0.2302) grad: 0.1620 (0.1975) time: 0.4691 data: 0.0024 max mem: 22446 +train: [9] [ 40/400] eta: 0:03:12 lr: 0.000248 loss: 0.1950 (0.2251) grad: 0.1760 (0.1874) time: 0.4684 data: 0.0036 max mem: 22446 +train: [9] [ 60/400] eta: 0:02:53 lr: 0.000247 loss: 0.1950 (0.2126) grad: 0.1611 (0.1761) time: 0.4631 data: 0.0034 max mem: 22446 +train: [9] [ 80/400] eta: 0:02:39 lr: 0.000246 loss: 0.1437 (0.2022) grad: 0.1383 (0.1643) time: 0.4540 data: 0.0035 max mem: 22446 +train: [9] [100/400] eta: 0:02:27 lr: 0.000244 loss: 0.1338 (0.1990) grad: 0.1419 (0.1640) time: 0.4607 data: 0.0033 max mem: 22446 +train: [9] [120/400] eta: 0:02:16 lr: 0.000243 loss: 0.2001 (0.2016) grad: 0.1675 (0.1678) time: 0.4680 data: 0.0034 max mem: 22446 +train: [9] [140/400] eta: 0:02:05 lr: 0.000242 loss: 0.1930 (0.2004) grad: 0.1752 (0.1726) time: 0.4643 data: 0.0033 max mem: 22446 +train: [9] [160/400] eta: 0:01:55 lr: 0.000241 loss: 0.1704 (0.1986) grad: 0.1752 (0.1750) time: 0.4661 data: 0.0034 max mem: 22446 +train: [9] [180/400] eta: 0:01:45 lr: 0.000240 loss: 0.1555 (0.1934) grad: 0.1644 (0.1738) time: 0.4666 data: 0.0033 max mem: 22446 +train: [9] [200/400] eta: 0:01:35 lr: 0.000238 loss: 0.1425 (0.1919) grad: 0.1506 (0.1722) time: 0.4596 data: 0.0034 max mem: 22446 +train: [9] [220/400] eta: 0:01:25 lr: 0.000237 loss: 0.1542 (0.1905) grad: 0.1702 (0.1715) time: 0.4600 data: 0.0034 max mem: 22446 +train: [9] [240/400] eta: 0:01:15 lr: 0.000236 loss: 0.1389 (0.1878) grad: 0.1702 (0.1705) time: 0.4610 data: 0.0034 max mem: 22446 +train: [9] [260/400] eta: 0:01:06 lr: 0.000234 loss: 0.1309 (0.1902) grad: 0.1749 (0.1740) time: 0.4627 data: 0.0033 max mem: 22446 +train: [9] [280/400] eta: 0:00:56 lr: 0.000233 loss: 0.1753 (0.1919) grad: 0.2209 (0.1757) time: 0.4682 data: 0.0034 max mem: 22446 +train: [9] [300/400] eta: 0:00:48 lr: 0.000232 loss: 0.1672 (0.1903) grad: 0.1744 (0.1766) time: 0.6269 data: 0.1766 max mem: 22446 +train: [9] [320/400] eta: 0:00:38 lr: 0.000230 loss: 0.1396 (0.1878) grad: 0.1671 (0.1761) time: 0.4647 data: 0.0030 max mem: 22446 +train: [9] [340/400] eta: 0:00:28 lr: 0.000229 loss: 0.1677 (0.1876) grad: 0.1676 (0.1760) time: 0.4689 data: 0.0036 max mem: 22446 +train: [9] [360/400] eta: 0:00:19 lr: 0.000228 loss: 0.1689 (0.1869) grad: 0.1737 (0.1751) time: 0.4587 data: 0.0035 max mem: 22446 +train: [9] [380/400] eta: 0:00:09 lr: 0.000226 loss: 0.1289 (0.1839) grad: 0.1401 (0.1731) time: 0.4606 data: 0.0034 max mem: 22446 +train: [9] [399/400] eta: 0:00:00 lr: 0.000225 loss: 0.1289 (0.1822) grad: 0.1381 (0.1718) time: 0.4664 data: 0.0035 max mem: 22446 +train: [9] Total time: 0:03:11 (0.4790 s / it) +train: [9] Summary: lr: 0.000225 loss: 0.1289 (0.1822) grad: 0.1381 (0.1718) +eval (validation): [9] [ 0/63] eta: 0:03:21 time: 3.1986 data: 2.9187 max mem: 22446 +eval (validation): [9] [20/63] eta: 0:00:20 time: 0.3457 data: 0.0039 max mem: 22446 +eval (validation): [9] [40/63] eta: 0:00:09 time: 0.3458 data: 0.0028 max mem: 22446 +eval (validation): [9] [60/63] eta: 0:00:01 time: 0.3311 data: 0.0033 max mem: 22446 +eval (validation): [9] [62/63] eta: 0:00:00 time: 0.3311 data: 0.0033 max mem: 22446 +eval (validation): [9] Total time: 0:00:24 (0.3900 s / it) +cv: [9] best hparam: (4.3, 1.0) (033) ('033_lr4.3e+00_wd1.0e+00') loss: 0.036 acc: 0.992 f1: 0.991 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/eval_v2/hcpya_task21__patch__attn/checkpoint-best.pth +train: [10] [ 0/400] eta: 0:21:20 lr: nan time: 3.2021 data: 2.8612 max mem: 22446 +train: [10] [ 20/400] eta: 0:03:47 lr: 0.000224 loss: 0.1543 (0.1695) grad: 0.1175 (0.1189) time: 0.4694 data: 0.0030 max mem: 22446 +train: [10] [ 40/400] eta: 0:03:12 lr: 0.000222 loss: 0.1329 (0.1525) grad: 0.1139 (0.1199) time: 0.4642 data: 0.0033 max mem: 22446 +train: [10] [ 60/400] eta: 0:02:52 lr: 0.000221 loss: 0.1300 (0.1556) grad: 0.1159 (0.1430) time: 0.4553 data: 0.0034 max mem: 22446 +train: [10] [ 80/400] eta: 0:02:37 lr: 0.000220 loss: 0.1203 (0.1484) grad: 0.1171 (0.1409) time: 0.4481 data: 0.0033 max mem: 22446 +train: [10] [100/400] eta: 0:02:25 lr: 0.000218 loss: 0.1043 (0.1476) grad: 0.1320 (0.1400) time: 0.4505 data: 0.0033 max mem: 22446 +train: [10] [120/400] eta: 0:02:14 lr: 0.000217 loss: 0.1501 (0.1464) grad: 0.1322 (0.1554) time: 0.4635 data: 0.0033 max mem: 22446 +train: [10] [140/400] eta: 0:02:04 lr: 0.000215 loss: 0.1501 (0.1481) grad: 0.1436 (0.1550) time: 0.4571 data: 0.0033 max mem: 22446 +train: [10] [160/400] eta: 0:01:54 lr: 0.000214 loss: 0.1234 (0.1457) grad: 0.1497 (0.1547) time: 0.4633 data: 0.0034 max mem: 22446 +train: [10] [180/400] eta: 0:01:44 lr: 0.000213 loss: 0.1175 (0.1447) grad: 0.1201 (0.1496) time: 0.4593 data: 0.0034 max mem: 22446 +train: [10] [200/400] eta: 0:01:34 lr: 0.000211 loss: 0.1270 (0.1442) grad: 0.1471 (0.1520) time: 0.4646 data: 0.0034 max mem: 22446 +train: [10] [220/400] eta: 0:01:24 lr: 0.000210 loss: 0.1285 (0.1433) grad: 0.1569 (0.1492) time: 0.4591 data: 0.0033 max mem: 22446 +train: [10] [240/400] eta: 0:01:15 lr: 0.000208 loss: 0.1213 (0.1428) grad: 0.1518 (0.1500) time: 0.4701 data: 0.0033 max mem: 22446 +train: [10] [260/400] eta: 0:01:05 lr: 0.000207 loss: 0.1391 (0.1453) grad: 0.1575 (0.1507) time: 0.4549 data: 0.0034 max mem: 22446 +train: [10] [280/400] eta: 0:00:56 lr: 0.000205 loss: 0.1203 (0.1431) grad: 0.1387 (0.1479) time: 0.4451 data: 0.0033 max mem: 22446 +train: [10] [300/400] eta: 0:00:47 lr: 0.000204 loss: 0.0929 (0.1433) grad: 0.1387 (0.1479) time: 0.6226 data: 0.1777 max mem: 22446 +train: [10] [320/400] eta: 0:00:38 lr: 0.000202 loss: 0.1071 (0.1425) grad: 0.1387 (0.1475) time: 0.4533 data: 0.0031 max mem: 22446 +train: [10] [340/400] eta: 0:00:28 lr: 0.000201 loss: 0.1118 (0.1409) grad: 0.1387 (0.1481) time: 0.4606 data: 0.0034 max mem: 22446 +train: [10] [360/400] eta: 0:00:19 lr: 0.000199 loss: 0.1012 (0.1401) grad: 0.1324 (0.1460) time: 0.4686 data: 0.0034 max mem: 22446 +train: [10] [380/400] eta: 0:00:09 lr: 0.000198 loss: 0.1097 (0.1405) grad: 0.1147 (0.1448) time: 0.4610 data: 0.0034 max mem: 22446 +train: [10] [399/400] eta: 0:00:00 lr: 0.000196 loss: 0.1227 (0.1391) grad: 0.1095 (0.1419) time: 0.4599 data: 0.0034 max mem: 22446 +train: [10] Total time: 0:03:09 (0.4747 s / it) +train: [10] Summary: lr: 0.000196 loss: 0.1227 (0.1391) grad: 0.1095 (0.1419) +eval (validation): [10] [ 0/63] eta: 0:03:49 time: 3.6505 data: 3.3585 max mem: 22446 +eval (validation): [10] [20/63] eta: 0:00:25 time: 0.4292 data: 0.0038 max mem: 22446 +eval (validation): [10] [40/63] eta: 0:00:11 time: 0.4057 data: 0.0033 max mem: 22446 +eval (validation): [10] [60/63] eta: 0:00:01 time: 0.3732 data: 0.0032 max mem: 22446 +eval (validation): [10] [62/63] eta: 0:00:00 time: 0.3761 data: 0.0032 max mem: 22446 +eval (validation): [10] Total time: 0:00:28 (0.4574 s / it) +cv: [10] best hparam: (4.3, 1.0) (033) ('033_lr4.3e+00_wd1.0e+00') loss: 0.034 acc: 0.993 f1: 0.991 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/eval_v2/hcpya_task21__patch__attn/checkpoint-best.pth +train: [11] [ 0/400] eta: 0:23:14 lr: nan time: 3.4862 data: 3.0962 max mem: 22446 +train: [11] [ 20/400] eta: 0:04:08 lr: 0.000195 loss: 0.1068 (0.1160) grad: 0.0826 (0.0896) time: 0.5119 data: 0.0026 max mem: 22446 +train: [11] [ 40/400] eta: 0:03:26 lr: 0.000193 loss: 0.1068 (0.1168) grad: 0.0826 (0.0872) time: 0.4880 data: 0.0032 max mem: 22446 +train: [11] [ 60/400] eta: 0:03:08 lr: 0.000192 loss: 0.1089 (0.1188) grad: 0.0835 (0.0913) time: 0.5124 data: 0.0032 max mem: 22446 +train: [11] [ 80/400] eta: 0:02:52 lr: 0.000190 loss: 0.1055 (0.1183) grad: 0.0835 (0.0915) time: 0.4918 data: 0.0034 max mem: 22446 +train: [11] [100/400] eta: 0:02:38 lr: 0.000189 loss: 0.1005 (0.1153) grad: 0.0916 (0.0923) time: 0.4925 data: 0.0034 max mem: 22446 +train: [11] [120/400] eta: 0:02:27 lr: 0.000187 loss: 0.1019 (0.1138) grad: 0.1125 (0.0965) time: 0.5116 data: 0.0035 max mem: 22446 +train: [11] [140/400] eta: 0:02:15 lr: 0.000186 loss: 0.1019 (0.1144) grad: 0.1102 (0.0980) time: 0.4860 data: 0.0033 max mem: 22446 +train: [11] [160/400] eta: 0:02:04 lr: 0.000184 loss: 0.1111 (0.1149) grad: 0.1061 (0.0989) time: 0.5001 data: 0.0034 max mem: 22446 +train: [11] [180/400] eta: 0:01:53 lr: 0.000183 loss: 0.1023 (0.1141) grad: 0.0994 (0.1005) time: 0.4963 data: 0.0034 max mem: 22446 +train: [11] [200/400] eta: 0:01:42 lr: 0.000181 loss: 0.0877 (0.1136) grad: 0.1001 (0.1009) time: 0.4880 data: 0.0033 max mem: 22446 +train: [11] [220/400] eta: 0:01:31 lr: 0.000180 loss: 0.0864 (0.1117) grad: 0.1001 (0.1008) time: 0.4843 data: 0.0034 max mem: 22446 +train: [11] [240/400] eta: 0:01:21 lr: 0.000178 loss: 0.0948 (0.1110) grad: 0.0939 (0.1011) time: 0.4868 data: 0.0034 max mem: 22446 +train: [11] [260/400] eta: 0:01:10 lr: 0.000177 loss: 0.0984 (0.1108) grad: 0.0868 (0.1000) time: 0.4786 data: 0.0032 max mem: 22446 +train: [11] [280/400] eta: 0:01:00 lr: 0.000175 loss: 0.0989 (0.1104) grad: 0.0859 (0.1004) time: 0.4616 data: 0.0034 max mem: 22446 +train: [11] [300/400] eta: 0:00:51 lr: 0.000174 loss: 0.0995 (0.1097) grad: 0.0859 (0.0992) time: 0.6612 data: 0.1831 max mem: 22446 +train: [11] [320/400] eta: 0:00:41 lr: 0.000172 loss: 0.0959 (0.1090) grad: 0.0830 (0.0987) time: 0.5082 data: 0.0029 max mem: 22446 +train: [11] [340/400] eta: 0:00:30 lr: 0.000170 loss: 0.0945 (0.1084) grad: 0.0879 (0.0979) time: 0.4833 data: 0.0035 max mem: 22446 +train: [11] [360/400] eta: 0:00:20 lr: 0.000169 loss: 0.0924 (0.1076) grad: 0.0649 (0.0968) time: 0.4947 data: 0.0034 max mem: 22446 +train: [11] [380/400] eta: 0:00:10 lr: 0.000167 loss: 0.0865 (0.1068) grad: 0.0790 (0.0962) time: 0.4878 data: 0.0034 max mem: 22446 +train: [11] [399/400] eta: 0:00:00 lr: 0.000166 loss: 0.0925 (0.1065) grad: 0.0789 (0.0952) time: 0.4729 data: 0.0033 max mem: 22446 +train: [11] Total time: 0:03:23 (0.5077 s / it) +train: [11] Summary: lr: 0.000166 loss: 0.0925 (0.1065) grad: 0.0789 (0.0952) +eval (validation): [11] [ 0/63] eta: 0:03:41 time: 3.5174 data: 3.1921 max mem: 22446 +eval (validation): [11] [20/63] eta: 0:00:24 time: 0.4318 data: 0.0041 max mem: 22446 +eval (validation): [11] [40/63] eta: 0:00:11 time: 0.3810 data: 0.0033 max mem: 22446 +eval (validation): [11] [60/63] eta: 0:00:01 time: 0.3503 data: 0.0034 max mem: 22446 +eval (validation): [11] [62/63] eta: 0:00:00 time: 0.3446 data: 0.0034 max mem: 22446 +eval (validation): [11] Total time: 0:00:27 (0.4401 s / it) +cv: [11] best hparam: (5.1, 1.0) (034) ('034_lr5.1e+00_wd1.0e+00') loss: 0.036 acc: 0.992 f1: 0.990 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [12] [ 0/400] eta: 0:24:00 lr: nan time: 3.6012 data: 3.1530 max mem: 22446 +train: [12] [ 20/400] eta: 0:04:11 lr: 0.000164 loss: 0.0893 (0.0906) grad: 0.0679 (0.0703) time: 0.5151 data: 0.0032 max mem: 22446 +train: [12] [ 40/400] eta: 0:03:28 lr: 0.000163 loss: 0.0884 (0.0922) grad: 0.0695 (0.0726) time: 0.4895 data: 0.0035 max mem: 22446 +train: [12] [ 60/400] eta: 0:03:07 lr: 0.000161 loss: 0.0825 (0.0886) grad: 0.0733 (0.0697) time: 0.5007 data: 0.0036 max mem: 22446 +train: [12] [ 80/400] eta: 0:02:50 lr: 0.000160 loss: 0.0811 (0.0883) grad: 0.0685 (0.0681) time: 0.4694 data: 0.0037 max mem: 22446 +train: [12] [100/400] eta: 0:02:36 lr: 0.000158 loss: 0.0957 (0.0906) grad: 0.0634 (0.0689) time: 0.4862 data: 0.0037 max mem: 22446 +train: [12] [120/400] eta: 0:02:24 lr: 0.000156 loss: 0.1004 (0.0946) grad: 0.0781 (0.0715) time: 0.4800 data: 0.0036 max mem: 22446 +train: [12] [140/400] eta: 0:02:12 lr: 0.000155 loss: 0.0983 (0.0939) grad: 0.0597 (0.0693) time: 0.4825 data: 0.0036 max mem: 22446 +train: [12] [160/400] eta: 0:02:02 lr: 0.000153 loss: 0.0838 (0.0932) grad: 0.0507 (0.0699) time: 0.4993 data: 0.0035 max mem: 22446 +train: [12] [180/400] eta: 0:01:51 lr: 0.000152 loss: 0.0838 (0.0925) grad: 0.0667 (0.0683) time: 0.4899 data: 0.0034 max mem: 22446 +train: [12] [200/400] eta: 0:01:41 lr: 0.000150 loss: 0.0791 (0.0917) grad: 0.0657 (0.0679) time: 0.4838 data: 0.0035 max mem: 22446 +train: [12] [220/400] eta: 0:01:30 lr: 0.000149 loss: 0.0786 (0.0932) grad: 0.0694 (0.0679) time: 0.4661 data: 0.0037 max mem: 22446 +train: [12] [240/400] eta: 0:01:20 lr: 0.000147 loss: 0.0948 (0.0938) grad: 0.0692 (0.0687) time: 0.4913 data: 0.0036 max mem: 22446 +train: [12] [260/400] eta: 0:01:09 lr: 0.000145 loss: 0.0850 (0.0932) grad: 0.0687 (0.0690) time: 0.4911 data: 0.0036 max mem: 22446 +train: [12] [280/400] eta: 0:00:59 lr: 0.000144 loss: 0.0835 (0.0924) grad: 0.0690 (0.0692) time: 0.4965 data: 0.0036 max mem: 22446 +train: [12] [300/400] eta: 0:00:51 lr: 0.000142 loss: 0.0821 (0.0922) grad: 0.0494 (0.0684) time: 0.7078 data: 0.1886 max mem: 22446 +train: [12] [320/400] eta: 0:00:40 lr: 0.000141 loss: 0.0821 (0.0917) grad: 0.0445 (0.0671) time: 0.4953 data: 0.0030 max mem: 22446 +train: [12] [340/400] eta: 0:00:30 lr: 0.000139 loss: 0.0865 (0.0915) grad: 0.0464 (0.0669) time: 0.4996 data: 0.0036 max mem: 22446 +train: [12] [360/400] eta: 0:00:20 lr: 0.000138 loss: 0.0833 (0.0913) grad: 0.0651 (0.0664) time: 0.4878 data: 0.0036 max mem: 22446 +train: [12] [380/400] eta: 0:00:10 lr: 0.000136 loss: 0.0821 (0.0912) grad: 0.0476 (0.0660) time: 0.4786 data: 0.0036 max mem: 22446 +train: [12] [399/400] eta: 0:00:00 lr: 0.000134 loss: 0.0799 (0.0909) grad: 0.0474 (0.0654) time: 0.4758 data: 0.0036 max mem: 22446 +train: [12] Total time: 0:03:22 (0.5074 s / it) +train: [12] Summary: lr: 0.000134 loss: 0.0799 (0.0909) grad: 0.0474 (0.0654) +eval (validation): [12] [ 0/63] eta: 0:03:32 time: 3.3738 data: 3.0942 max mem: 22446 +eval (validation): [12] [20/63] eta: 0:00:22 time: 0.3849 data: 0.0039 max mem: 22446 +eval (validation): [12] [40/63] eta: 0:00:10 time: 0.3746 data: 0.0028 max mem: 22446 +eval (validation): [12] [60/63] eta: 0:00:01 time: 0.3580 data: 0.0035 max mem: 22446 +eval (validation): [12] [62/63] eta: 0:00:00 time: 0.3581 data: 0.0035 max mem: 22446 +eval (validation): [12] Total time: 0:00:26 (0.4238 s / it) +cv: [12] best hparam: (2.7, 1.0) (030) ('030_lr2.7e+00_wd1.0e+00') loss: 0.032 acc: 0.993 f1: 0.991 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [13] [ 0/400] eta: 0:24:05 lr: nan time: 3.6140 data: 3.1871 max mem: 22446 +train: [13] [ 20/400] eta: 0:04:04 lr: 0.000133 loss: 0.0897 (0.0903) grad: 0.0392 (0.0543) time: 0.4949 data: 0.0025 max mem: 22446 +train: [13] [ 40/400] eta: 0:03:23 lr: 0.000131 loss: 0.0801 (0.0832) grad: 0.0392 (0.0526) time: 0.4861 data: 0.0032 max mem: 22446 +train: [13] [ 60/400] eta: 0:03:03 lr: 0.000130 loss: 0.0746 (0.0814) grad: 0.0428 (0.0510) time: 0.4812 data: 0.0034 max mem: 22446 +train: [13] [ 80/400] eta: 0:02:46 lr: 0.000128 loss: 0.0807 (0.0818) grad: 0.0454 (0.0522) time: 0.4671 data: 0.0035 max mem: 22446 +train: [13] [100/400] eta: 0:02:33 lr: 0.000127 loss: 0.0771 (0.0815) grad: 0.0454 (0.0516) time: 0.4757 data: 0.0036 max mem: 22446 +train: [13] [120/400] eta: 0:02:21 lr: 0.000125 loss: 0.0747 (0.0807) grad: 0.0418 (0.0525) time: 0.4823 data: 0.0034 max mem: 22446 +train: [13] [140/400] eta: 0:02:11 lr: 0.000124 loss: 0.0740 (0.0806) grad: 0.0498 (0.0528) time: 0.4842 data: 0.0034 max mem: 22446 +train: [13] [160/400] eta: 0:02:00 lr: 0.000122 loss: 0.0753 (0.0802) grad: 0.0487 (0.0521) time: 0.4930 data: 0.0034 max mem: 22446 +train: [13] [180/400] eta: 0:01:50 lr: 0.000120 loss: 0.0776 (0.0810) grad: 0.0454 (0.0524) time: 0.4868 data: 0.0034 max mem: 22446 +train: [13] [200/400] eta: 0:01:39 lr: 0.000119 loss: 0.0814 (0.0816) grad: 0.0584 (0.0531) time: 0.4832 data: 0.0034 max mem: 22446 +train: [13] [220/400] eta: 0:01:29 lr: 0.000117 loss: 0.0785 (0.0815) grad: 0.0597 (0.0534) time: 0.4709 data: 0.0035 max mem: 22446 +train: [13] [240/400] eta: 0:01:19 lr: 0.000116 loss: 0.0758 (0.0810) grad: 0.0435 (0.0525) time: 0.4699 data: 0.0035 max mem: 22446 +train: [13] [260/400] eta: 0:01:09 lr: 0.000114 loss: 0.0714 (0.0806) grad: 0.0415 (0.0520) time: 0.4879 data: 0.0033 max mem: 22446 +train: [13] [280/400] eta: 0:00:59 lr: 0.000113 loss: 0.0691 (0.0802) grad: 0.0420 (0.0525) time: 0.4821 data: 0.0035 max mem: 22446 +train: [13] [300/400] eta: 0:00:50 lr: 0.000111 loss: 0.0750 (0.0802) grad: 0.0472 (0.0525) time: 0.6689 data: 0.1880 max mem: 22446 +train: [13] [320/400] eta: 0:00:40 lr: 0.000110 loss: 0.0750 (0.0800) grad: 0.0434 (0.0518) time: 0.5056 data: 0.0033 max mem: 22446 +train: [13] [340/400] eta: 0:00:30 lr: 0.000108 loss: 0.0778 (0.0800) grad: 0.0407 (0.0518) time: 0.4860 data: 0.0032 max mem: 22446 +train: [13] [360/400] eta: 0:00:20 lr: 0.000107 loss: 0.0723 (0.0793) grad: 0.0429 (0.0513) time: 0.4655 data: 0.0035 max mem: 22446 +train: [13] [380/400] eta: 0:00:10 lr: 0.000105 loss: 0.0723 (0.0794) grad: 0.0429 (0.0510) time: 0.4846 data: 0.0037 max mem: 22446 +train: [13] [399/400] eta: 0:00:00 lr: 0.000104 loss: 0.0806 (0.0796) grad: 0.0399 (0.0508) time: 0.4797 data: 0.0035 max mem: 22446 +train: [13] Total time: 0:03:19 (0.4999 s / it) +train: [13] Summary: lr: 0.000104 loss: 0.0806 (0.0796) grad: 0.0399 (0.0508) +eval (validation): [13] [ 0/63] eta: 0:03:40 time: 3.5016 data: 3.1753 max mem: 22446 +eval (validation): [13] [20/63] eta: 0:00:24 time: 0.4206 data: 0.0043 max mem: 22446 +eval (validation): [13] [40/63] eta: 0:00:10 time: 0.3660 data: 0.0037 max mem: 22446 +eval (validation): [13] [60/63] eta: 0:00:01 time: 0.3763 data: 0.0035 max mem: 22446 +eval (validation): [13] [62/63] eta: 0:00:00 time: 0.3689 data: 0.0035 max mem: 22446 +eval (validation): [13] Total time: 0:00:27 (0.4398 s / it) +cv: [13] best hparam: (0.85, 1.0) (023) ('023_lr8.5e-01_wd1.0e+00') loss: 0.026 acc: 0.992 f1: 0.991 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [14] [ 0/400] eta: 0:23:56 lr: nan time: 3.5902 data: 3.2196 max mem: 22446 +train: [14] [ 20/400] eta: 0:03:59 lr: 0.000102 loss: 0.0762 (0.0778) grad: 0.0377 (0.0380) time: 0.4825 data: 0.0025 max mem: 22446 +train: [14] [ 40/400] eta: 0:03:20 lr: 0.000101 loss: 0.0762 (0.0768) grad: 0.0411 (0.0427) time: 0.4775 data: 0.0036 max mem: 22446 +train: [14] [ 60/400] eta: 0:03:00 lr: 0.000099 loss: 0.0733 (0.0754) grad: 0.0419 (0.0429) time: 0.4812 data: 0.0033 max mem: 22446 +train: [14] [ 80/400] eta: 0:02:45 lr: 0.000098 loss: 0.0646 (0.0756) grad: 0.0424 (0.0450) time: 0.4779 data: 0.0035 max mem: 22446 +train: [14] [100/400] eta: 0:02:33 lr: 0.000096 loss: 0.0640 (0.0749) grad: 0.0400 (0.0440) time: 0.4880 data: 0.0035 max mem: 22446 +train: [14] [120/400] eta: 0:02:22 lr: 0.000095 loss: 0.0721 (0.0766) grad: 0.0384 (0.0436) time: 0.4948 data: 0.0035 max mem: 22446 +train: [14] [140/400] eta: 0:02:11 lr: 0.000093 loss: 0.0816 (0.0782) grad: 0.0418 (0.0440) time: 0.4894 data: 0.0034 max mem: 22446 +train: [14] [160/400] eta: 0:02:01 lr: 0.000092 loss: 0.0657 (0.0770) grad: 0.0356 (0.0433) time: 0.4915 data: 0.0034 max mem: 22446 +train: [14] [180/400] eta: 0:01:50 lr: 0.000090 loss: 0.0633 (0.0761) grad: 0.0349 (0.0426) time: 0.4892 data: 0.0034 max mem: 22446 +train: [14] [200/400] eta: 0:01:40 lr: 0.000089 loss: 0.0714 (0.0763) grad: 0.0387 (0.0427) time: 0.4832 data: 0.0034 max mem: 22446 +train: [14] [220/400] eta: 0:01:30 lr: 0.000088 loss: 0.0701 (0.0760) grad: 0.0428 (0.0427) time: 0.4918 data: 0.0034 max mem: 22446 +train: [14] [240/400] eta: 0:01:19 lr: 0.000086 loss: 0.0701 (0.0757) grad: 0.0407 (0.0425) time: 0.4887 data: 0.0035 max mem: 22446 +train: [14] [260/400] eta: 0:01:09 lr: 0.000085 loss: 0.0685 (0.0750) grad: 0.0428 (0.0430) time: 0.4970 data: 0.0036 max mem: 22446 +train: [14] [280/400] eta: 0:00:59 lr: 0.000083 loss: 0.0708 (0.0757) grad: 0.0416 (0.0427) time: 0.4884 data: 0.0036 max mem: 22446 +train: [14] [300/400] eta: 0:00:50 lr: 0.000082 loss: 0.0775 (0.0757) grad: 0.0389 (0.0429) time: 0.6593 data: 0.1853 max mem: 22446 +train: [14] [320/400] eta: 0:00:40 lr: 0.000081 loss: 0.0720 (0.0755) grad: 0.0380 (0.0425) time: 0.4842 data: 0.0035 max mem: 22446 +train: [14] [340/400] eta: 0:00:30 lr: 0.000079 loss: 0.0771 (0.0758) grad: 0.0380 (0.0423) time: 0.4843 data: 0.0038 max mem: 22446 +train: [14] [360/400] eta: 0:00:20 lr: 0.000078 loss: 0.0771 (0.0759) grad: 0.0413 (0.0422) time: 0.4698 data: 0.0036 max mem: 22446 +train: [14] [380/400] eta: 0:00:10 lr: 0.000076 loss: 0.0756 (0.0761) grad: 0.0417 (0.0423) time: 0.4811 data: 0.0036 max mem: 22446 +train: [14] [399/400] eta: 0:00:00 lr: 0.000075 loss: 0.0679 (0.0760) grad: 0.0377 (0.0420) time: 0.4803 data: 0.0037 max mem: 22446 +train: [14] Total time: 0:03:20 (0.5021 s / it) +train: [14] Summary: lr: 0.000075 loss: 0.0679 (0.0760) grad: 0.0377 (0.0420) +eval (validation): [14] [ 0/63] eta: 0:03:31 time: 3.3634 data: 3.0912 max mem: 22446 +eval (validation): [14] [20/63] eta: 0:00:24 time: 0.4223 data: 0.0044 max mem: 22446 +eval (validation): [14] [40/63] eta: 0:00:11 time: 0.3940 data: 0.0029 max mem: 22446 +eval (validation): [14] [60/63] eta: 0:00:01 time: 0.3595 data: 0.0033 max mem: 22446 +eval (validation): [14] [62/63] eta: 0:00:00 time: 0.3588 data: 0.0034 max mem: 22446 +eval (validation): [14] Total time: 0:00:27 (0.4417 s / it) +cv: [14] best hparam: (1.4, 1.0) (026) ('026_lr1.4e+00_wd1.0e+00') loss: 0.028 acc: 0.992 f1: 0.991 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [15] [ 0/400] eta: 0:24:10 lr: nan time: 3.6256 data: 3.1917 max mem: 22446 +train: [15] [ 20/400] eta: 0:04:03 lr: 0.000074 loss: 0.0735 (0.0755) grad: 0.0411 (0.0470) time: 0.4927 data: 0.0038 max mem: 22446 +train: [15] [ 40/400] eta: 0:03:22 lr: 0.000072 loss: 0.0735 (0.0752) grad: 0.0442 (0.0464) time: 0.4804 data: 0.0034 max mem: 22446 +train: [15] [ 60/400] eta: 0:03:03 lr: 0.000071 loss: 0.0645 (0.0713) grad: 0.0402 (0.0445) time: 0.4909 data: 0.0036 max mem: 22446 +train: [15] [ 80/400] eta: 0:02:47 lr: 0.000070 loss: 0.0619 (0.0705) grad: 0.0345 (0.0423) time: 0.4774 data: 0.0036 max mem: 22446 +train: [15] [100/400] eta: 0:02:34 lr: 0.000068 loss: 0.0629 (0.0704) grad: 0.0375 (0.0441) time: 0.4842 data: 0.0036 max mem: 22446 +train: [15] [120/400] eta: 0:02:23 lr: 0.000067 loss: 0.0648 (0.0703) grad: 0.0389 (0.0449) time: 0.4888 data: 0.0034 max mem: 22446 +train: [15] [140/400] eta: 0:02:12 lr: 0.000066 loss: 0.0678 (0.0704) grad: 0.0374 (0.0440) time: 0.4865 data: 0.0033 max mem: 22446 +train: [15] [160/400] eta: 0:02:01 lr: 0.000064 loss: 0.0639 (0.0697) grad: 0.0370 (0.0438) time: 0.4776 data: 0.0035 max mem: 22446 +train: [15] [180/400] eta: 0:01:49 lr: 0.000063 loss: 0.0635 (0.0703) grad: 0.0377 (0.0434) time: 0.4630 data: 0.0036 max mem: 22446 +train: [15] [200/400] eta: 0:01:39 lr: 0.000062 loss: 0.0753 (0.0709) grad: 0.0377 (0.0429) time: 0.4767 data: 0.0036 max mem: 22446 +train: [15] [220/400] eta: 0:01:29 lr: 0.000061 loss: 0.0690 (0.0703) grad: 0.0367 (0.0424) time: 0.4898 data: 0.0035 max mem: 22446 +train: [15] [240/400] eta: 0:01:19 lr: 0.000059 loss: 0.0650 (0.0699) grad: 0.0368 (0.0422) time: 0.4851 data: 0.0035 max mem: 22446 +train: [15] [260/400] eta: 0:01:09 lr: 0.000058 loss: 0.0600 (0.0701) grad: 0.0368 (0.0417) time: 0.4835 data: 0.0034 max mem: 22446 +train: [15] [280/400] eta: 0:00:59 lr: 0.000057 loss: 0.0604 (0.0702) grad: 0.0360 (0.0415) time: 0.4911 data: 0.0036 max mem: 22446 +train: [15] [300/400] eta: 0:00:50 lr: 0.000056 loss: 0.0619 (0.0702) grad: 0.0358 (0.0413) time: 0.6318 data: 0.1727 max mem: 22446 +train: [15] [320/400] eta: 0:00:40 lr: 0.000054 loss: 0.0636 (0.0699) grad: 0.0373 (0.0414) time: 0.4648 data: 0.0034 max mem: 22446 +train: [15] [340/400] eta: 0:00:30 lr: 0.000053 loss: 0.0636 (0.0700) grad: 0.0404 (0.0414) time: 0.4836 data: 0.0036 max mem: 22446 +train: [15] [360/400] eta: 0:00:19 lr: 0.000052 loss: 0.0658 (0.0702) grad: 0.0398 (0.0414) time: 0.4888 data: 0.0035 max mem: 22446 +train: [15] [380/400] eta: 0:00:09 lr: 0.000051 loss: 0.0635 (0.0698) grad: 0.0394 (0.0411) time: 0.4886 data: 0.0034 max mem: 22446 +train: [15] [399/400] eta: 0:00:00 lr: 0.000050 loss: 0.0666 (0.0701) grad: 0.0354 (0.0409) time: 0.4859 data: 0.0035 max mem: 22446 +train: [15] Total time: 0:03:19 (0.4987 s / it) +train: [15] Summary: lr: 0.000050 loss: 0.0666 (0.0701) grad: 0.0354 (0.0409) +eval (validation): [15] [ 0/63] eta: 0:03:33 time: 3.3910 data: 3.1264 max mem: 22446 +eval (validation): [15] [20/63] eta: 0:00:23 time: 0.4110 data: 0.0039 max mem: 22446 +eval (validation): [15] [40/63] eta: 0:00:10 time: 0.3782 data: 0.0033 max mem: 22446 +eval (validation): [15] [60/63] eta: 0:00:01 time: 0.3644 data: 0.0037 max mem: 22446 +eval (validation): [15] [62/63] eta: 0:00:00 time: 0.3645 data: 0.0036 max mem: 22446 +eval (validation): [15] Total time: 0:00:27 (0.4362 s / it) +cv: [15] best hparam: (0.85, 1.0) (023) ('023_lr8.5e-01_wd1.0e+00') loss: 0.025 acc: 0.993 f1: 0.992 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/eval_v2/hcpya_task21__patch__attn/checkpoint-best.pth +train: [16] [ 0/400] eta: 0:23:35 lr: nan time: 3.5379 data: 3.1571 max mem: 22446 +train: [16] [ 20/400] eta: 0:04:06 lr: 0.000048 loss: 0.0644 (0.0706) grad: 0.0345 (0.0362) time: 0.5043 data: 0.0030 max mem: 22446 +train: [16] [ 40/400] eta: 0:03:24 lr: 0.000047 loss: 0.0644 (0.0696) grad: 0.0358 (0.0372) time: 0.4858 data: 0.0035 max mem: 22446 +train: [16] [ 60/400] eta: 0:03:03 lr: 0.000046 loss: 0.0666 (0.0695) grad: 0.0336 (0.0362) time: 0.4753 data: 0.0034 max mem: 22446 +train: [16] [ 80/400] eta: 0:02:48 lr: 0.000045 loss: 0.0695 (0.0699) grad: 0.0336 (0.0365) time: 0.4868 data: 0.0035 max mem: 22446 +train: [16] [100/400] eta: 0:02:35 lr: 0.000044 loss: 0.0655 (0.0699) grad: 0.0351 (0.0366) time: 0.4859 data: 0.0034 max mem: 22446 +train: [16] [120/400] eta: 0:02:23 lr: 0.000043 loss: 0.0653 (0.0697) grad: 0.0351 (0.0374) time: 0.4835 data: 0.0034 max mem: 22446 +train: [16] [140/400] eta: 0:02:11 lr: 0.000042 loss: 0.0666 (0.0699) grad: 0.0391 (0.0381) time: 0.4807 data: 0.0036 max mem: 22446 +train: [16] [160/400] eta: 0:02:00 lr: 0.000041 loss: 0.0625 (0.0698) grad: 0.0400 (0.0382) time: 0.4740 data: 0.0034 max mem: 22446 +train: [16] [180/400] eta: 0:01:49 lr: 0.000040 loss: 0.0717 (0.0701) grad: 0.0354 (0.0378) time: 0.4664 data: 0.0034 max mem: 22446 +train: [16] [200/400] eta: 0:01:39 lr: 0.000039 loss: 0.0717 (0.0709) grad: 0.0359 (0.0384) time: 0.4772 data: 0.0035 max mem: 22446 +train: [16] [220/400] eta: 0:01:29 lr: 0.000038 loss: 0.0676 (0.0706) grad: 0.0378 (0.0382) time: 0.4842 data: 0.0034 max mem: 22446 +train: [16] [240/400] eta: 0:01:19 lr: 0.000036 loss: 0.0609 (0.0701) grad: 0.0331 (0.0377) time: 0.4855 data: 0.0034 max mem: 22446 +train: [16] [260/400] eta: 0:01:09 lr: 0.000035 loss: 0.0638 (0.0703) grad: 0.0333 (0.0378) time: 0.4832 data: 0.0034 max mem: 22446 +train: [16] [280/400] eta: 0:00:59 lr: 0.000034 loss: 0.0634 (0.0702) grad: 0.0372 (0.0382) time: 0.4796 data: 0.0035 max mem: 22446 +train: [16] [300/400] eta: 0:00:50 lr: 0.000033 loss: 0.0623 (0.0702) grad: 0.0406 (0.0384) time: 0.6331 data: 0.1717 max mem: 22446 +train: [16] [320/400] eta: 0:00:40 lr: 0.000032 loss: 0.0656 (0.0701) grad: 0.0378 (0.0385) time: 0.4719 data: 0.0033 max mem: 22446 +train: [16] [340/400] eta: 0:00:29 lr: 0.000031 loss: 0.0745 (0.0708) grad: 0.0377 (0.0387) time: 0.4827 data: 0.0036 max mem: 22446 +train: [16] [360/400] eta: 0:00:19 lr: 0.000031 loss: 0.0709 (0.0706) grad: 0.0359 (0.0386) time: 0.4756 data: 0.0037 max mem: 22446 +train: [16] [380/400] eta: 0:00:09 lr: 0.000030 loss: 0.0623 (0.0701) grad: 0.0354 (0.0385) time: 0.4757 data: 0.0035 max mem: 22446 +train: [16] [399/400] eta: 0:00:00 lr: 0.000029 loss: 0.0577 (0.0699) grad: 0.0418 (0.0387) time: 0.4848 data: 0.0034 max mem: 22446 +train: [16] Total time: 0:03:18 (0.4967 s / it) +train: [16] Summary: lr: 0.000029 loss: 0.0577 (0.0699) grad: 0.0418 (0.0387) +eval (validation): [16] [ 0/63] eta: 0:03:35 time: 3.4129 data: 3.1392 max mem: 22446 +eval (validation): [16] [20/63] eta: 0:00:23 time: 0.3926 data: 0.0031 max mem: 22446 +eval (validation): [16] [40/63] eta: 0:00:10 time: 0.3565 data: 0.0029 max mem: 22446 +eval (validation): [16] [60/63] eta: 0:00:01 time: 0.3507 data: 0.0034 max mem: 22446 +eval (validation): [16] [62/63] eta: 0:00:00 time: 0.3538 data: 0.0034 max mem: 22446 +eval (validation): [16] Total time: 0:00:26 (0.4208 s / it) +cv: [16] best hparam: (1.2, 1.0) (025) ('025_lr1.2e+00_wd1.0e+00') loss: 0.028 acc: 0.992 f1: 0.991 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [17] [ 0/400] eta: 0:23:45 lr: nan time: 3.5640 data: 3.1503 max mem: 22446 +train: [17] [ 20/400] eta: 0:04:05 lr: 0.000028 loss: 0.0569 (0.0653) grad: 0.0371 (0.0376) time: 0.5004 data: 0.0033 max mem: 22446 +train: [17] [ 40/400] eta: 0:03:23 lr: 0.000027 loss: 0.0639 (0.0703) grad: 0.0373 (0.0390) time: 0.4798 data: 0.0035 max mem: 22446 +train: [17] [ 60/400] eta: 0:03:02 lr: 0.000026 loss: 0.0701 (0.0718) grad: 0.0385 (0.0383) time: 0.4825 data: 0.0036 max mem: 22446 +train: [17] [ 80/400] eta: 0:02:47 lr: 0.000025 loss: 0.0741 (0.0723) grad: 0.0372 (0.0380) time: 0.4844 data: 0.0034 max mem: 22446 +train: [17] [100/400] eta: 0:02:34 lr: 0.000024 loss: 0.0696 (0.0715) grad: 0.0360 (0.0378) time: 0.4774 data: 0.0033 max mem: 22446 +train: [17] [120/400] eta: 0:02:21 lr: 0.000023 loss: 0.0681 (0.0712) grad: 0.0359 (0.0377) time: 0.4634 data: 0.0034 max mem: 22446 +train: [17] [140/400] eta: 0:02:10 lr: 0.000023 loss: 0.0660 (0.0707) grad: 0.0344 (0.0379) time: 0.4857 data: 0.0035 max mem: 22446 +train: [17] [160/400] eta: 0:02:00 lr: 0.000022 loss: 0.0687 (0.0704) grad: 0.0344 (0.0379) time: 0.4825 data: 0.0035 max mem: 22446 +train: [17] [180/400] eta: 0:01:49 lr: 0.000021 loss: 0.0669 (0.0697) grad: 0.0378 (0.0377) time: 0.4783 data: 0.0035 max mem: 22446 +train: [17] [200/400] eta: 0:01:39 lr: 0.000020 loss: 0.0608 (0.0694) grad: 0.0381 (0.0378) time: 0.4844 data: 0.0035 max mem: 22446 +train: [17] [220/400] eta: 0:01:29 lr: 0.000019 loss: 0.0620 (0.0692) grad: 0.0366 (0.0377) time: 0.4855 data: 0.0037 max mem: 22446 +train: [17] [240/400] eta: 0:01:19 lr: 0.000019 loss: 0.0609 (0.0689) grad: 0.0324 (0.0376) time: 0.4859 data: 0.0035 max mem: 22446 +train: [17] [260/400] eta: 0:01:09 lr: 0.000018 loss: 0.0606 (0.0692) grad: 0.0360 (0.0376) time: 0.4958 data: 0.0036 max mem: 22446 +train: [17] [280/400] eta: 0:00:59 lr: 0.000017 loss: 0.0681 (0.0692) grad: 0.0360 (0.0374) time: 0.4896 data: 0.0036 max mem: 22446 +train: [17] [300/400] eta: 0:00:50 lr: 0.000016 loss: 0.0677 (0.0692) grad: 0.0357 (0.0376) time: 0.6573 data: 0.1841 max mem: 22446 +train: [17] [320/400] eta: 0:00:40 lr: 0.000016 loss: 0.0644 (0.0693) grad: 0.0394 (0.0378) time: 0.4867 data: 0.0038 max mem: 22446 +train: [17] [340/400] eta: 0:00:30 lr: 0.000015 loss: 0.0650 (0.0692) grad: 0.0348 (0.0376) time: 0.4908 data: 0.0034 max mem: 22446 +train: [17] [360/400] eta: 0:00:20 lr: 0.000014 loss: 0.0602 (0.0688) grad: 0.0338 (0.0374) time: 0.4816 data: 0.0037 max mem: 22446 +train: [17] [380/400] eta: 0:00:10 lr: 0.000014 loss: 0.0602 (0.0690) grad: 0.0347 (0.0373) time: 0.4798 data: 0.0036 max mem: 22446 +train: [17] [399/400] eta: 0:00:00 lr: 0.000013 loss: 0.0620 (0.0688) grad: 0.0365 (0.0372) time: 0.4778 data: 0.0036 max mem: 22446 +train: [17] Total time: 0:03:20 (0.5005 s / it) +train: [17] Summary: lr: 0.000013 loss: 0.0620 (0.0688) grad: 0.0365 (0.0372) +eval (validation): [17] [ 0/63] eta: 0:03:35 time: 3.4229 data: 3.0981 max mem: 22446 +eval (validation): [17] [20/63] eta: 0:00:22 time: 0.3890 data: 0.0032 max mem: 22446 +eval (validation): [17] [40/63] eta: 0:00:10 time: 0.3488 data: 0.0032 max mem: 22446 +eval (validation): [17] [60/63] eta: 0:00:01 time: 0.3612 data: 0.0034 max mem: 22446 +eval (validation): [17] [62/63] eta: 0:00:00 time: 0.3544 data: 0.0034 max mem: 22446 +eval (validation): [17] Total time: 0:00:26 (0.4188 s / it) +cv: [17] best hparam: (1.6, 1.0) (027) ('027_lr1.6e+00_wd1.0e+00') loss: 0.030 acc: 0.992 f1: 0.991 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [18] [ 0/400] eta: 0:24:08 lr: nan time: 3.6202 data: 3.2443 max mem: 22446 +train: [18] [ 20/400] eta: 0:04:03 lr: 0.000012 loss: 0.0616 (0.0653) grad: 0.0329 (0.0353) time: 0.4911 data: 0.0029 max mem: 22446 +train: [18] [ 40/400] eta: 0:03:22 lr: 0.000012 loss: 0.0625 (0.0694) grad: 0.0360 (0.0366) time: 0.4789 data: 0.0031 max mem: 22446 +train: [18] [ 60/400] eta: 0:03:00 lr: 0.000011 loss: 0.0666 (0.0692) grad: 0.0364 (0.0367) time: 0.4693 data: 0.0037 max mem: 22446 +train: [18] [ 80/400] eta: 0:02:45 lr: 0.000011 loss: 0.0697 (0.0696) grad: 0.0359 (0.0369) time: 0.4754 data: 0.0035 max mem: 22446 +train: [18] [100/400] eta: 0:02:32 lr: 0.000010 loss: 0.0697 (0.0696) grad: 0.0367 (0.0370) time: 0.4737 data: 0.0034 max mem: 22446 +train: [18] [120/400] eta: 0:02:20 lr: 0.000009 loss: 0.0621 (0.0677) grad: 0.0347 (0.0367) time: 0.4642 data: 0.0033 max mem: 22446 +train: [18] [140/400] eta: 0:02:09 lr: 0.000009 loss: 0.0661 (0.0684) grad: 0.0351 (0.0371) time: 0.4691 data: 0.0034 max mem: 22446 +train: [18] [160/400] eta: 0:01:58 lr: 0.000008 loss: 0.0685 (0.0679) grad: 0.0356 (0.0370) time: 0.4769 data: 0.0033 max mem: 22446 +train: [18] [180/400] eta: 0:01:48 lr: 0.000008 loss: 0.0596 (0.0675) grad: 0.0360 (0.0373) time: 0.4794 data: 0.0033 max mem: 22446 +train: [18] [200/400] eta: 0:01:38 lr: 0.000007 loss: 0.0640 (0.0674) grad: 0.0363 (0.0373) time: 0.4808 data: 0.0034 max mem: 22446 +train: [18] [220/400] eta: 0:01:28 lr: 0.000007 loss: 0.0649 (0.0671) grad: 0.0365 (0.0372) time: 0.4852 data: 0.0034 max mem: 22446 +train: [18] [240/400] eta: 0:01:18 lr: 0.000006 loss: 0.0603 (0.0669) grad: 0.0376 (0.0372) time: 0.4799 data: 0.0034 max mem: 22446 +train: [18] [260/400] eta: 0:01:08 lr: 0.000006 loss: 0.0606 (0.0672) grad: 0.0343 (0.0371) time: 0.4665 data: 0.0033 max mem: 22446 +train: [18] [280/400] eta: 0:00:58 lr: 0.000006 loss: 0.0640 (0.0671) grad: 0.0368 (0.0372) time: 0.4782 data: 0.0034 max mem: 22446 +train: [18] [300/400] eta: 0:00:49 lr: 0.000005 loss: 0.0629 (0.0668) grad: 0.0369 (0.0372) time: 0.6329 data: 0.1739 max mem: 22446 +train: [18] [320/400] eta: 0:00:39 lr: 0.000005 loss: 0.0595 (0.0669) grad: 0.0368 (0.0372) time: 0.4817 data: 0.0060 max mem: 22446 +train: [18] [340/400] eta: 0:00:29 lr: 0.000004 loss: 0.0638 (0.0670) grad: 0.0349 (0.0372) time: 0.4834 data: 0.0034 max mem: 22446 +train: [18] [360/400] eta: 0:00:19 lr: 0.000004 loss: 0.0631 (0.0667) grad: 0.0347 (0.0372) time: 0.4812 data: 0.0034 max mem: 22446 +train: [18] [380/400] eta: 0:00:09 lr: 0.000004 loss: 0.0600 (0.0663) grad: 0.0343 (0.0371) time: 0.4899 data: 0.0033 max mem: 22446 +train: [18] [399/400] eta: 0:00:00 lr: 0.000003 loss: 0.0600 (0.0662) grad: 0.0364 (0.0370) time: 0.4742 data: 0.0034 max mem: 22446 +train: [18] Total time: 0:03:17 (0.4938 s / it) +train: [18] Summary: lr: 0.000003 loss: 0.0600 (0.0662) grad: 0.0364 (0.0370) +eval (validation): [18] [ 0/63] eta: 0:03:22 time: 3.2112 data: 2.9164 max mem: 22446 +eval (validation): [18] [20/63] eta: 0:00:23 time: 0.4193 data: 0.0046 max mem: 22446 +eval (validation): [18] [40/63] eta: 0:00:10 time: 0.3705 data: 0.0033 max mem: 22446 +eval (validation): [18] [60/63] eta: 0:00:01 time: 0.3571 data: 0.0034 max mem: 22446 +eval (validation): [18] [62/63] eta: 0:00:00 time: 0.3543 data: 0.0035 max mem: 22446 +eval (validation): [18] Total time: 0:00:27 (0.4302 s / it) +cv: [18] best hparam: (1.6, 1.0) (027) ('027_lr1.6e+00_wd1.0e+00') loss: 0.030 acc: 0.993 f1: 0.991 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [19] [ 0/400] eta: 0:23:57 lr: nan time: 3.5948 data: 3.2312 max mem: 22446 +train: [19] [ 20/400] eta: 0:04:08 lr: 0.000003 loss: 0.0657 (0.0629) grad: 0.0332 (0.0345) time: 0.5076 data: 0.0026 max mem: 22446 +train: [19] [ 40/400] eta: 0:03:24 lr: 0.000003 loss: 0.0629 (0.0629) grad: 0.0343 (0.0357) time: 0.4758 data: 0.0033 max mem: 22446 +train: [19] [ 60/400] eta: 0:03:01 lr: 0.000002 loss: 0.0629 (0.0640) grad: 0.0345 (0.0355) time: 0.4677 data: 0.0037 max mem: 22446 +train: [19] [ 80/400] eta: 0:02:46 lr: 0.000002 loss: 0.0655 (0.0654) grad: 0.0365 (0.0363) time: 0.4793 data: 0.0034 max mem: 22446 +train: [19] [100/400] eta: 0:02:33 lr: 0.000002 loss: 0.0646 (0.0672) grad: 0.0369 (0.0362) time: 0.4722 data: 0.0035 max mem: 22446 +train: [19] [120/400] eta: 0:02:22 lr: 0.000002 loss: 0.0645 (0.0666) grad: 0.0353 (0.0361) time: 0.4940 data: 0.0036 max mem: 22446 +train: [19] [140/400] eta: 0:02:11 lr: 0.000001 loss: 0.0631 (0.0660) grad: 0.0340 (0.0362) time: 0.4846 data: 0.0034 max mem: 22446 +train: [19] [160/400] eta: 0:02:00 lr: 0.000001 loss: 0.0653 (0.0664) grad: 0.0339 (0.0360) time: 0.4799 data: 0.0034 max mem: 22446 +train: [19] [180/400] eta: 0:01:49 lr: 0.000001 loss: 0.0640 (0.0665) grad: 0.0332 (0.0361) time: 0.4744 data: 0.0034 max mem: 22446 +train: [19] [200/400] eta: 0:01:39 lr: 0.000001 loss: 0.0631 (0.0665) grad: 0.0332 (0.0361) time: 0.4798 data: 0.0034 max mem: 22446 +train: [19] [220/400] eta: 0:01:29 lr: 0.000001 loss: 0.0647 (0.0671) grad: 0.0361 (0.0363) time: 0.4750 data: 0.0034 max mem: 22446 +train: [19] [240/400] eta: 0:01:18 lr: 0.000001 loss: 0.0678 (0.0669) grad: 0.0361 (0.0363) time: 0.4770 data: 0.0034 max mem: 22446 +train: [19] [260/400] eta: 0:01:08 lr: 0.000000 loss: 0.0608 (0.0668) grad: 0.0366 (0.0363) time: 0.4560 data: 0.0033 max mem: 22446 +train: [19] [280/400] eta: 0:00:58 lr: 0.000000 loss: 0.0632 (0.0672) grad: 0.0366 (0.0364) time: 0.4685 data: 0.0036 max mem: 22446 +train: [19] [300/400] eta: 0:00:49 lr: 0.000000 loss: 0.0633 (0.0670) grad: 0.0382 (0.0366) time: 0.6488 data: 0.1833 max mem: 22446 +train: [19] [320/400] eta: 0:00:39 lr: 0.000000 loss: 0.0615 (0.0669) grad: 0.0395 (0.0368) time: 0.4862 data: 0.0036 max mem: 22446 +train: [19] [340/400] eta: 0:00:29 lr: 0.000000 loss: 0.0632 (0.0668) grad: 0.0382 (0.0368) time: 0.4790 data: 0.0034 max mem: 22446 +train: [19] [360/400] eta: 0:00:19 lr: 0.000000 loss: 0.0653 (0.0670) grad: 0.0361 (0.0369) time: 0.4754 data: 0.0036 max mem: 22446 +train: [19] [380/400] eta: 0:00:09 lr: 0.000000 loss: 0.0624 (0.0667) grad: 0.0365 (0.0369) time: 0.4743 data: 0.0037 max mem: 22446 +train: [19] [399/400] eta: 0:00:00 lr: 0.000000 loss: 0.0573 (0.0665) grad: 0.0338 (0.0369) time: 0.4761 data: 0.0035 max mem: 22446 +train: [19] Total time: 0:03:17 (0.4947 s / it) +train: [19] Summary: lr: 0.000000 loss: 0.0573 (0.0665) grad: 0.0338 (0.0369) +eval (validation): [19] [ 0/63] eta: 0:03:23 time: 3.2303 data: 2.9788 max mem: 22446 +eval (validation): [19] [20/63] eta: 0:00:21 time: 0.3639 data: 0.0115 max mem: 22446 +eval (validation): [19] [40/63] eta: 0:00:10 time: 0.3690 data: 0.0030 max mem: 22446 +eval (validation): [19] [60/63] eta: 0:00:01 time: 0.3603 data: 0.0034 max mem: 22446 +eval (validation): [19] [62/63] eta: 0:00:00 time: 0.3604 data: 0.0034 max mem: 22446 +eval (validation): [19] Total time: 0:00:26 (0.4145 s / it) +cv: [19] best hparam: (1.6, 1.0) (027) ('027_lr1.6e+00_wd1.0e+00') loss: 0.030 acc: 0.992 f1: 0.991 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +evaluating last checkpoint: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +eval model info: +{"score": 0.9923115079365079, "hparam": [1.6, 1.0], "hparam_id": 27, "epoch": 19, "is_best": false, "best_score": 0.9928075396825397} +eval (train): [20] [ 0/297] eta: 0:15:50 time: 3.2006 data: 2.9328 max mem: 22446 +eval (train): [20] [ 20/297] eta: 0:02:34 time: 0.4238 data: 0.0045 max mem: 22446 +eval (train): [20] [ 40/297] eta: 0:01:59 time: 0.3712 data: 0.0029 max mem: 22446 +eval (train): [20] [ 60/297] eta: 0:01:41 time: 0.3561 data: 0.0035 max mem: 22446 +eval (train): [20] [ 80/297] eta: 0:01:29 time: 0.3577 data: 0.0042 max mem: 22446 +eval (train): [20] [100/297] eta: 0:01:19 time: 0.3631 data: 0.0039 max mem: 22446 +eval (train): [20] [120/297] eta: 0:01:10 time: 0.3880 data: 0.0035 max mem: 22446 +eval (train): [20] [140/297] eta: 0:01:02 time: 0.3904 data: 0.0032 max mem: 22446 +eval (train): [20] [160/297] eta: 0:00:54 time: 0.3895 data: 0.0036 max mem: 22446 +eval (train): [20] [180/297] eta: 0:00:46 time: 0.3836 data: 0.0039 max mem: 22446 +eval (train): [20] [200/297] eta: 0:00:38 time: 0.3832 data: 0.0036 max mem: 22446 +eval (train): [20] [220/297] eta: 0:00:30 time: 0.3938 data: 0.0038 max mem: 22446 +eval (train): [20] [240/297] eta: 0:00:22 time: 0.3947 data: 0.0039 max mem: 22446 +eval (train): [20] [260/297] eta: 0:00:14 time: 0.3775 data: 0.0035 max mem: 22446 +eval (train): [20] [280/297] eta: 0:00:06 time: 0.3568 data: 0.0033 max mem: 22446 +eval (train): [20] [296/297] eta: 0:00:00 time: 0.3549 data: 0.0033 max mem: 22446 +eval (train): [20] Total time: 0:01:55 (0.3905 s / it) +eval (validation): [20] [ 0/63] eta: 0:03:30 time: 3.3368 data: 3.0209 max mem: 22446 +eval (validation): [20] [20/63] eta: 0:00:24 time: 0.4261 data: 0.0034 max mem: 22446 +eval (validation): [20] [40/63] eta: 0:00:11 time: 0.4038 data: 0.0036 max mem: 22446 +eval (validation): [20] [60/63] eta: 0:00:01 time: 0.3667 data: 0.0032 max mem: 22446 +eval (validation): [20] [62/63] eta: 0:00:00 time: 0.3652 data: 0.0033 max mem: 22446 +eval (validation): [20] Total time: 0:00:28 (0.4475 s / it) +eval (test): [20] [ 0/79] eta: 0:04:19 time: 3.2865 data: 3.0037 max mem: 22446 +eval (test): [20] [20/79] eta: 0:00:31 time: 0.4027 data: 0.0179 max mem: 22446 +eval (test): [20] [40/79] eta: 0:00:20 time: 0.4958 data: 0.0616 max mem: 22446 +eval (test): [20] [60/79] eta: 0:00:09 time: 0.4106 data: 0.0031 max mem: 22446 +eval (test): [20] [78/79] eta: 0:00:00 time: 0.3823 data: 0.0034 max mem: 22446 +eval (test): [20] Total time: 0:00:36 (0.4627 s / it) +evaluating best checkpoint: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/eval_v2/hcpya_task21__patch__attn/checkpoint-best.pth +eval model info: +{"score": 0.9928075396825397, "hparam": [0.85, 1.0], "hparam_id": 23, "epoch": 15, "is_best": true, "best_score": 0.9928075396825397} +eval (train): [20] [ 0/297] eta: 0:16:25 time: 3.3186 data: 3.0432 max mem: 22446 +eval (train): [20] [ 20/297] eta: 0:02:27 time: 0.3922 data: 0.0034 max mem: 22446 +eval (train): [20] [ 40/297] eta: 0:01:58 time: 0.3864 data: 0.0030 max mem: 22446 +eval (train): [20] [ 60/297] eta: 0:01:43 time: 0.3915 data: 0.0225 max mem: 22446 +eval (train): [20] [ 80/297] eta: 0:01:32 time: 0.3871 data: 0.0020 max mem: 22446 +eval (train): [20] [100/297] eta: 0:01:20 time: 0.3518 data: 0.0031 max mem: 22446 +eval (train): [20] [120/297] eta: 0:01:11 time: 0.3605 data: 0.0035 max mem: 22446 +eval (train): [20] [140/297] eta: 0:01:02 time: 0.3709 data: 0.0038 max mem: 22446 +eval (train): [20] [160/297] eta: 0:00:54 time: 0.3865 data: 0.0034 max mem: 22446 +eval (train): [20] [180/297] eta: 0:00:46 time: 0.3868 data: 0.0035 max mem: 22446 +eval (train): [20] [200/297] eta: 0:00:38 time: 0.3933 data: 0.0034 max mem: 22446 +eval (train): [20] [220/297] eta: 0:00:30 time: 0.3665 data: 0.0034 max mem: 22446 +eval (train): [20] [240/297] eta: 0:00:22 time: 0.4071 data: 0.0037 max mem: 22446 +eval (train): [20] [260/297] eta: 0:00:14 time: 0.3755 data: 0.0034 max mem: 22446 +eval (train): [20] [280/297] eta: 0:00:06 time: 0.3859 data: 0.0037 max mem: 22446 +eval (train): [20] [296/297] eta: 0:00:00 time: 0.3928 data: 0.0035 max mem: 22446 +eval (train): [20] Total time: 0:01:56 (0.3932 s / it) +eval (validation): [20] [ 0/63] eta: 0:03:26 time: 3.2832 data: 3.0092 max mem: 22446 +eval (validation): [20] [20/63] eta: 0:00:26 time: 0.4893 data: 0.0038 max mem: 22446 +eval (validation): [20] [40/63] eta: 0:00:12 time: 0.4196 data: 0.0032 max mem: 22446 +eval (validation): [20] [60/63] eta: 0:00:01 time: 0.3993 data: 0.0035 max mem: 22446 +eval (validation): [20] [62/63] eta: 0:00:00 time: 0.3987 data: 0.0035 max mem: 22446 +eval (validation): [20] Total time: 0:00:30 (0.4831 s / it) +eval (test): [20] [ 0/79] eta: 0:04:19 time: 3.2904 data: 3.0224 max mem: 22446 +eval (test): [20] [20/79] eta: 0:00:30 time: 0.3750 data: 0.0136 max mem: 22446 +eval (test): [20] [40/79] eta: 0:00:17 time: 0.3714 data: 0.0030 max mem: 22446 +eval (test): [20] [60/79] eta: 0:00:08 time: 0.4145 data: 0.0039 max mem: 22446 +eval (test): [20] [78/79] eta: 0:00:00 time: 0.3996 data: 0.0031 max mem: 22446 +eval (test): [20] Total time: 0:00:33 (0.4294 s / it) +eval results: + +| model | repr | clf | dataset | ckpt | epoch | lr | wd | hparam_id | hparam | split | loss | acc | acc_std | f1 | f1_std | +|:---------|:-------|:------|:-------------|:-------|--------:|---------:|-----:|------------:|:------------|:-----------|----------:|--------:|-----------:|--------:|-----------:| +| flat_mae | patch | attn | hcpya_task21 | best | 15 | 0.000255 | 0.05 | 23 | [0.85, 1.0] | train | 0.0073708 | 0.99884 | 0.00024793 | 0.99896 | 0.00023891 | +| flat_mae | patch | attn | hcpya_task21 | best | 15 | 0.000255 | 0.05 | 23 | [0.85, 1.0] | validation | 0.025198 | 0.99281 | 0.0013201 | 0.99187 | 0.0016735 | +| flat_mae | patch | attn | hcpya_task21 | best | 15 | 0.000255 | 0.05 | 23 | [0.85, 1.0] | test | 0.037297 | 0.98948 | 0.0013997 | 0.98749 | 0.0018333 | + + +done! total time: 1:22:36 diff --git a/input_space_v3/flat_lr1e-3_6/eval_v2/hcpya_task21__patch__attn/train_log.json b/input_space_v3/flat_lr1e-3_6/eval_v2/hcpya_task21__patch__attn/train_log.json new file mode 100644 index 0000000000000000000000000000000000000000..0184c47efb6d8f2f5afa66f9182b3e67174f60dd --- /dev/null +++ b/input_space_v3/flat_lr1e-3_6/eval_v2/hcpya_task21__patch__attn/train_log.json @@ -0,0 +1,20 @@ +{"epoch": 0, "train/lr": 2.987987987987988e-05, "train/loss": 2.0995398432016374, "train/grad": 0.20330245196819305, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.033687744140625, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.0309130859375, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.026328125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.021728515625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.0173095703125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.0109716796875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.003892822265625, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.995975341796875, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.98548583984375, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.97449462890625, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.963458251953125, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.947030029296875, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.9309161376953123, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.9074322509765627, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.8848577880859376, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.862996826171875, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.83504638671875, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.801577453613281, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.7633233642578126, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.7267242431640626, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.6801132202148437, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.6300947570800783, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.571766357421875, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.506185302734375, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.434544448852539, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.3451649856567385, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.2622708892822265, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.185464172363281, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.080880603790283, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.958596429824829, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.8527921485900878, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.7602635216712952, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.641668281853199, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.5426059391349554, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.4340485787019133, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.3353838252276182, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.2393730062339454, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.1565945804771036, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.0751561255007982, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.9841156256012619, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.9194838174805046, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.8672729836031795, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.8057042936608195, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.757766497861594, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.7075752863287925, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.6613219870813191, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.6241580411884934, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.5817716155666858, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.5511673052236438, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.038110281750559805, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.03804785846732557, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.03794493168592453, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.037840674594044686, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.037739101657643916, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.03759744669310749, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.0374378015100956, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.037258753553032875, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.037022639587521555, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.03677036282606423, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.03652040533721447, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.03614390332251787, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.0357759865000844, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.035241541750729084, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.03473097963258624, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.0342480559553951, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.03365609637461603, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.032995139341801406, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.03231739812530577, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.03174474054947495, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.031106741186231374, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.030513401785865427, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.029905684171244503, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.029294766997918487, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.02868255065754056, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.027956996848806738, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.02730164905078709, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.026698848782107234, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.025882662809453904, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.02493536177556962, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.02412841732148081, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.023417769432999194, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.022462329249829053, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.021647014967165888, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.020750945282634346, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.019880698793567717, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.019006361663341523, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.01829511234187521, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.017586174303432928, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.016903767674812116, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.016150100872037002, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.015551794021739625, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.015031061072950252, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.014690286015975289, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.014386935355432798, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.014479553492856212, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.014317314767977223, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.014232252243091352, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.014503902492579072, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.995708703994751, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.9874963760375977, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.9738852977752686, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.9605162143707275, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.9473023414611816, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.9290359020233154, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.9084222316741943, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.8857007026672363, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.8559446334838867, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.824697256088257, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.794390916824341, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.749138355255127, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.7057881355285645, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.6440885066986084, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.5859458446502686, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.5306949615478516, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.460960865020752, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.3784635066986084, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.284705877304077, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.1950700283050537, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.0803914070129395, "validation/loss_021_lr6.1e-01_wd1.0e+00": 1.9570541381835938, "validation/loss_022_lr7.2e-01_wd1.0e+00": 1.8141357898712158, "validation/loss_023_lr8.5e-01_wd1.0e+00": 1.6558436155319214, "validation/loss_024_lr1.0e+00_wd1.0e+00": 1.4883091449737549, "validation/loss_025_lr1.2e+00_wd1.0e+00": 1.2902271747589111, "validation/loss_026_lr1.4e+00_wd1.0e+00": 1.1199437379837036, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.9752142429351807, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.7977185845375061, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.6167832612991333, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.47834864258766174, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.36918413639068604, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.25334346294403076, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.18228846788406372, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.12595169246196747, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.08879441767930984, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.07184695452451706, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.06762602925300598, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.06605453789234161, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.06690984219312668, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.06677587330341339, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.06131478399038315, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.05418159067630768, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.05241510644555092, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.049349233508110046, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.06355714052915573, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.060536790639162064, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.08314958959817886, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.10392636060714722, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.05853174603174603, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.07217261904761904, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.11433531746031746, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.17212301587301587, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.2296626984126984, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.2708333333333333, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.27827380952380953, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.27628968253968256, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.2586805555555556, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.23363095238095238, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.21279761904761904, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.19419642857142858, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.1865079365079365, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.18427579365079366, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.18625992063492064, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.19146825396825398, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.20684523809523808, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.24801587301587302, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.3333333333333333, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.41716269841269843, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.4905753968253968, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.5560515873015873, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.5882936507936508, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.6212797619047619, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.6612103174603174, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.7477678571428571, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.816468253968254, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.8566468253968254, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.8821924603174603, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9007936507936508, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9025297619047619, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9122023809523809, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9327876984126984, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9608134920634921, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9682539682539683, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9747023809523809, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9771825396825397, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9774305555555556, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9774305555555556, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9774305555555556, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9769345238095238, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9779265873015873, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9813988095238095, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9818948412698413, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.984375, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9784226190476191, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9789186507936508, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.972718253968254, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9680059523809523, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.020321756682608633, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.02714415013747351, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.04466876473311694, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.06165326797580635, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.07480280193337513, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.0814663862504612, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.0817723644012497, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.08433810050315177, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.0812934293970628, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.07065456700203039, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.05714526903785293, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.0402227074552851, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.03195659047665425, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.029859434451067635, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.03157882712744705, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.03628532600224542, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.050012706991076454, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.08509114548956188, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.14393133813619935, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.19682250503032087, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.2530607632027698, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.3060259959979873, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.33061581080402586, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.36372583598227864, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.45240839079885314, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.6216045664099503, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.7389950103606614, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.8098009523752755, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.8519252848403825, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.8776804170638528, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.8801042364565694, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.8936120183489574, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.92253584409294, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9568399497131284, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.965052450282875, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9724071507664344, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.974528299291712, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9756440163840365, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.976301825189472, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9768251330334382, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9770832370934802, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9778691403333009, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9806901607357373, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.981111384966819, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9840413151480119, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9775321200437694, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9785047484878928, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9708613521932712, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9633952768895613, "id_best": 44, "lr_best": 0.0078, "wd_best": 0.05, "train/loss_best": 0.7075752863287925, "validation/loss_best": 0.049349233508110046, "validation/acc_best": 0.984375, "validation/f1_best": 0.9840413151480119} +{"epoch": 1, "train/lr": 8.993993993993998e-05, "train/loss": 1.1655035603046418, "train/grad": 0.14554597064852715, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.927584228515625, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.9100732421875, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.88161376953125, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.8538348388671877, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.8268402099609373, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.79027587890625, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.749959716796875, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.7064178466796873, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.6509716796875, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.5939532470703126, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.5393612670898436, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.4593716430664063, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.3832992553710937, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.2748677062988283, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.172044677734375, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.074070816040039, "train/loss_016_lr2.7e-01_wd1.0e+00": 1.950425796508789, "train/loss_017_lr3.2e-01_wd1.0e+00": 1.806568603515625, "train/loss_018_lr3.8e-01_wd1.0e+00": 1.6487499618530272, "train/loss_019_lr4.4e-01_wd1.0e+00": 1.5063831901550293, "train/loss_020_lr5.2e-01_wd1.0e+00": 1.338688154220581, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.1760867357254028, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.0084118676185607, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.8461433601379394, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.6976261129975319, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.5479100041091443, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.4371934108063579, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.3548108623735607, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.26770256425254046, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.19343080773949622, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.14732761337421835, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.11800174220465123, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.09163039954379201, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.07717553855851293, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.06732185911387205, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.06226517492905259, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.05953777125105262, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.05778249871917069, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.056887375079095366, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.05717325247824192, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.05691561363637447, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.05662522772327065, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.06063233616761863, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.061532472101971505, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.06116575492545962, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.07353893452323973, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.08602203108370304, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.1100605697836727, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.17340799683704972, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.03535126321949065, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.034962948048487305, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.034331106953322886, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.033719100812450054, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.033128172950819136, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.03233874096535146, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.03149517006240785, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.030629192562773824, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.02961085634306073, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.02867713092826307, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.027897504791617393, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.026934968195855617, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.026184111312031747, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.02532597673125565, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.024662805683910848, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.02410857249982655, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.0234580737631768, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.022705705128610133, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.02183607278391719, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.020991514632478357, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.019927407959476114, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.01883453925140202, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.01763168852776289, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.01634671540465206, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.015044403106439858, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.013576847636140883, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.012323639998212456, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.011318350669462234, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.010237985010026023, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.009185536609729752, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.00848812028998509, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.008036039377911948, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.007539509968482889, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.007278290515532717, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.007087161201925482, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.006940229143656325, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.006871507547912188, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.006841241172514856, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.006861262869206257, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.006977633328642696, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.006941684306075331, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.00696515593357617, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.007411753527994733, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.007687135269807186, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.007946677486688713, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.009282627417705953, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.011382956264424138, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.013956930938875303, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.01878632117455709, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.8426308631896973, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.814288377761841, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.768554449081421, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.724672794342041, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.682565927505493, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.626312017440796, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.5650932788848877, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.4999990463256836, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.417926073074341, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.3336479663848877, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.252885103225708, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.133847236633301, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.0200631618499756, "validation/loss_013_lr1.7e-01_wd1.0e+00": 1.8579308986663818, "validation/loss_014_lr2.0e-01_wd1.0e+00": 1.7057037353515625, "validation/loss_015_lr2.3e-01_wd1.0e+00": 1.56349778175354, "validation/loss_016_lr2.7e-01_wd1.0e+00": 1.3901455402374268, "validation/loss_017_lr3.2e-01_wd1.0e+00": 1.1993931531906128, "validation/loss_018_lr3.8e-01_wd1.0e+00": 1.0062246322631836, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.8469399213790894, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.6762681603431702, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.5250909924507141, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.382700651884079, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.2667311131954193, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.18378977477550507, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.11788079142570496, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.08301907032728195, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.06855934113264084, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.05917838588356972, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.05305629223585129, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.04899865388870239, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.04596246778964996, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.04230837523937225, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.03987133130431175, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.03757868707180023, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.036185119301080704, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.03497001901268959, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.034523483365774155, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.03575471043586731, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.04585305601358414, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.05281156301498413, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.0514967180788517, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.06513627618551254, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.06236272305250168, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.058846134692430496, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.07276074588298798, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.09755764156579971, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.2724587619304657, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.29427021741867065, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.25967261904761907, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.23883928571428573, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.21329365079365079, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.20188492063492064, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.19940476190476192, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.19791666666666666, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.2041170634920635, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.2170138888888889, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.24677579365079366, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.29910714285714285, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.3913690476190476, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.5096726190476191, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.5778769841269841, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.6076388888888888, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.6187996031746031, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.6490575396825397, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.7244543650793651, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.8100198412698413, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.8526785714285714, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.8740079365079365, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9010416666666666, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9186507936507936, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9332837301587301, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9513888888888888, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9685019841269841, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9779265873015873, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9813988095238095, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9826388888888888, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9836309523809523, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9846230158730159, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9856150793650794, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9866071428571429, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.988343253968254, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9895833333333334, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9898313492063492, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9890873015873016, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9893353174603174, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9895833333333334, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9888392857142857, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9838789682539683, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9821428571428571, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9818948412698413, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9789186507936508, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9786706349206349, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9821428571428571, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9821428571428571, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9784226190476191, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9620535714285714, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.970734126984127, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.08148951776850974, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.0717727101057097, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.05495128174840048, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.045252504370113585, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.04293715486172679, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.04140755321729454, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.04560396048704073, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.05488798341821572, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.07911874852299099, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.1228474631507743, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.197745501447364, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.27739505278883053, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.3214339159118984, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.33801676706967126, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.3537600463284929, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.43260781473888776, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.5887027664691842, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.723743119825462, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.7940234488011078, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.8300629252858661, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.8743214523054907, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9014818853647103, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9225168811016047, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.943588977542836, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9628870697385178, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9733841687073861, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9768501248912071, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.978656104686543, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9796611938435456, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9815685909778414, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9825773216800284, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9842130230806377, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9868307149217428, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9882717279101565, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9888254552146456, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9881248012634112, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9882496337790213, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9882403941361213, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9871595768865847, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.982767313272692, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9818848413250666, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9819836209848469, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9795981885602087, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9788896698171476, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9814848545763688, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9809756817638862, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9749470364129774, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9616906305319404, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9657409573765067, "id_best": 34, "lr_best": 0.0015299999999999997, "wd_best": 0.05, "train/loss_best": 0.06732185911387205, "validation/loss_best": 0.03757868707180023, "validation/acc_best": 0.9898313492063492, "validation/f1_best": 0.9888254552146456} +{"epoch": 2, "train/lr": 0.00014999999999999988, "train/loss": 0.8533923244476318, "train/grad": 0.18659948259592057, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.738370361328125, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.69818359375, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.6344232177734375, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.5741448974609376, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.5167071533203127, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.440205383300781, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.3572372436523437, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.26812255859375, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.155049591064453, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.0384173583984375, "train/loss_010_lr1.0e-01_wd1.0e+00": 1.9272847747802735, "train/loss_011_lr1.2e-01_wd1.0e+00": 1.7664874267578126, "train/loss_012_lr1.4e-01_wd1.0e+00": 1.6179170608520508, "train/loss_013_lr1.7e-01_wd1.0e+00": 1.4175411033630372, "train/loss_014_lr2.0e-01_wd1.0e+00": 1.242933702468872, "train/loss_015_lr2.3e-01_wd1.0e+00": 1.0915916538238526, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.9208223485946655, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.7473016428947449, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.584753291606903, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.46141784951090814, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.3415245681256056, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.248688328191638, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.17619481101632117, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.12705040249973534, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.09622755333781242, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.07604384898208082, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.06727011818438769, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.06281883648596703, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.05881958918645978, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.05552049171179533, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.05335508150048554, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.05211883589625359, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.051279937475919725, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.05092727212235332, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.05114014329388738, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.05114944221451879, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.04907411781139672, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.04813959999941289, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.05077249454334378, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.05467255621217191, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.06350534200668335, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.061166357016190886, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.07135128109715878, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.11858291562646628, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.17264956529252232, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.3026041140221059, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.4706165149062872, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.8684881512634456, "train/loss_048_lr5.0e+01_wd1.0e+00": 1.6655601363908499, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.03171249285340309, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.03087420449592173, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.029614997943863273, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.028543349923565983, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.027650498962029816, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.026659639133140445, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.02581669949926436, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.025121906474232673, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.024438242632895707, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.023854801449924707, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.023332324866205453, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.022547243321314456, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.021747359158471227, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.020527565069496632, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.01933912768959999, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.01824387004133314, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.0169596246490255, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.015593646545894443, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.014181160614825786, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.01297326121944934, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.011630759797990322, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.010380942197516561, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.009115427368087695, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.008019294861005619, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.007239668143447489, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.006659096406074241, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.006445079734548926, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0063953694584779446, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.006392262644949369, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.006385171143338084, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.006379807300982065, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0064110903433174824, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.006501072138198651, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.006553185739903711, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.006608518923749216, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.006593533481936902, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.00652118803729536, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.006446617230903939, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.007283170421142131, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.007995230468513909, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.009117071713553741, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.008776077447400894, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.01037694278798881, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.015718431818968384, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.021820020657614805, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.032235513265186456, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.046044882759451865, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.06126905898850767, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.09373326087576242, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.624284029006958, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.5723609924316406, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.4909329414367676, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.414154529571533, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.341036796569824, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.2431530952453613, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.1362111568450928, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.0209262371063232, "validation/loss_008_lr7.4e-02_wd1.0e+00": 1.8744075298309326, "validation/loss_009_lr8.7e-02_wd1.0e+00": 1.7246925830841064, "validation/loss_010_lr1.0e-01_wd1.0e+00": 1.584419846534729, "validation/loss_011_lr1.2e-01_wd1.0e+00": 1.3880034685134888, "validation/loss_012_lr1.4e-01_wd1.0e+00": 1.2149181365966797, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.9962005019187927, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.8195304870605469, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.6765101552009583, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.5232362747192383, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.3766167163848877, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.2584845721721649, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.18476974964141846, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.12335602939128876, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.08535416424274445, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.06783686578273773, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.05922170728445053, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.053684767335653305, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.04928234592080116, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.046823352575302124, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.04580509290099144, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.04564349725842476, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.041428036987781525, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.03690312057733536, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.0350797213613987, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.03426137566566467, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.03413233533501625, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.03619207814335823, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.039103101938962936, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.03603968769311905, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.04324745759367943, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.06175236776471138, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.10393403470516205, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.08730515837669373, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.06659642606973648, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.14351068437099457, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.23302562534809113, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.4740130603313446, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.9665837287902832, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.9824709296226501, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.9202637076377869, "validation/loss_048_lr5.0e+01_wd1.0e+00": 2.6506507396698, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.18675595238095238, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.18898809523809523, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.2013888888888889, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.23214285714285715, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.283234126984127, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.3787202380952381, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.48313492063492064, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.5570436507936508, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.6059027777777778, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.6284722222222222, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.6560019841269841, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.7333829365079365, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.8003472222222222, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.8479662698412699, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.8722718253968254, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.8965773809523809, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9154265873015873, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9340277777777778, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9561011904761905, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9699900793650794, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9786706349206349, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9811507936507936, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9826388888888888, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9836309523809523, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9846230158730159, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9851190476190477, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9851190476190477, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9856150793650794, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9858630952380952, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9871031746031746, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9880952380952381, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9888392857142857, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9890873015873016, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9900793650793651, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.988343253968254, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9878472222222222, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9890873015873016, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9878472222222222, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9836309523809523, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9749503968253969, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9769345238095238, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9836309523809523, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9747023809523809, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9699900793650794, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9672619047619048, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9580853174603174, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9692460317460317, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9764384920634921, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9742063492063492, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.03239565541509188, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.034613082856180435, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.0455109470686442, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.07331984333645639, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.11256952255542242, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.18246296490802927, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.25791378300119117, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.31096310857919235, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.34430306258759247, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.36965255769102257, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.42486847153714824, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.5808277302959062, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.6879335243761042, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.7796393070129044, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.8230291472017092, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.86889410624685, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.8997160293343285, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9247907312423551, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9504801473231184, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9655803024106182, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9762154348444285, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9779936668607209, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9797500097475788, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9810918019355451, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9819805364750473, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9825586757954686, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9831036357256482, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9833853351797002, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9846748220498973, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9861622751103364, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9869786753487143, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9878414208638323, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9881884511637096, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9891829261031981, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9877378679879372, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9874158040655734, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9883211008369925, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9867468494076845, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9837870766120012, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9643504286078837, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9675651076094527, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.983150276396354, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.975697423531234, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9596198385341422, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9621080591228017, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9495701249931023, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9629303669266565, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9667882328504699, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9714921542257412, "id_best": 33, "lr_best": 0.00129, "wd_best": 0.05, "train/loss_best": 0.05092727212235332, "validation/loss_best": 0.03413233533501625, "validation/acc_best": 0.9900793650793651, "validation/f1_best": 0.9891829261031981} +{"epoch": 3, "train/lr": 0.0002100600600600602, "train/loss": 0.7243697308003902, "train/grad": 0.2604648282378912, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.5108001708984373, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.447503967285156, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.34713134765625, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.2516412353515625, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.159793701171875, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.0366563415527343, "train/loss_006_lr5.3e-02_wd1.0e+00": 1.9025953674316407, "train/loss_007_lr6.2e-02_wd1.0e+00": 1.7603639984130859, "train/loss_008_lr7.4e-02_wd1.0e+00": 1.5847602462768555, "train/loss_009_lr8.7e-02_wd1.0e+00": 1.412751693725586, "train/loss_010_lr1.0e-01_wd1.0e+00": 1.2594518280029297, "train/loss_011_lr1.2e-01_wd1.0e+00": 1.0571997547149659, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.8900718164443969, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.6907898330688477, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.537937525510788, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.4213535541296005, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.30871385112404826, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.21539582155644893, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.14876417817547918, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.11138871494680642, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.08548817930743098, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.07265334839001297, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.06570351137779654, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.06117732285521924, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.057689451444894076, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.054428030075505375, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.05190366796217859, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.049857913441956045, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.04741290634498, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.04482276137918234, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.04291651234030724, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.041713349046185615, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.04041919919662178, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.039586719991639256, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.03914029874838889, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.03760731207206845, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.038299864511936905, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.04229345363564789, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.046357726091518996, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.06001219353638589, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.07987896850332618, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.09909791489131749, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.20930057173594832, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.38210301409475506, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.424778762916103, "train/loss_045_lr3.1e+01_wd1.0e+00": 1.1676166380476207, "train/loss_046_lr3.6e+01_wd1.0e+00": 1.1214870250876994, "train/loss_047_lr4.3e+01_wd1.0e+00": 1.800264325523749, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.1350419676490127, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.027052939282730223, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.02626109518110752, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.02531317646615207, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.02466686263680458, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.02418659007176757, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.023638804713264107, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.023065506741404534, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.022407939927652477, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.02147929187864065, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.020428996621631085, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.019382324921898543, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.01787897345609963, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.0165810063527897, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.014994702893309295, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.013670654492452741, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.01250261961016804, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.011130307097919285, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.009609404981601984, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.008201744261896238, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.007298694838536904, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.006626819297671318, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.006325455239275471, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0062489290372468535, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.006246395067428238, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.006208379908348434, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.006098748702206649, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.006000307545182295, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.005953144826344214, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.005873871682561003, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.005730508170236135, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.005658784891711548, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.005646982879552525, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.005647951701539569, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.005668330228654667, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.005672011919086799, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.005616011427555349, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.006042784416495124, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.006798994782984664, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.007207353253470501, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.009856300534302136, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.010453904771638918, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.01380858506563527, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.021747567873829966, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.03668013027215693, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.03956117360682696, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.07639572632690154, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.07663701937986268, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.10362368049797359, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.15040093215130462, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.376288414001465, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.299726724624634, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.17791748046875, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.061755418777466, "validation/loss_004_lr3.8e-02_wd1.0e+00": 1.9503878355026245, "validation/loss_005_lr4.5e-02_wd1.0e+00": 1.8019858598709106, "validation/loss_006_lr5.3e-02_wd1.0e+00": 1.6430399417877197, "validation/loss_007_lr6.2e-02_wd1.0e+00": 1.4785667657852173, "validation/loss_008_lr7.4e-02_wd1.0e+00": 1.2827904224395752, "validation/loss_009_lr8.7e-02_wd1.0e+00": 1.100092887878418, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.9450152516365051, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.7509693503379822, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.5981288552284241, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.4218580424785614, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.29921990633010864, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.21953345835208893, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.15096698701381683, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.0993422269821167, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.07415544986724854, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.0643312856554985, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.057308379560709, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.05259832739830017, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.04857972636818886, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.045296560972929, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.04221024736762047, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.03894880786538124, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.03684846684336662, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.03602848947048187, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.03756162151694298, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.039754319936037064, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.03838475048542023, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.038504526019096375, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.042485710233449936, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.04977862164378166, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.05452575534582138, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.05664282664656639, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.059721674770116806, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.07699380815029144, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.06324837356805801, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.10208483785390854, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.09455627202987671, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.27098348736763, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.2962191104888916, "validation/loss_043_lr2.2e+01_wd1.0e+00": 1.2318549156188965, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.47068408131599426, "validation/loss_045_lr3.1e+01_wd1.0e+00": 1.2079546451568604, "validation/loss_046_lr3.6e+01_wd1.0e+00": 2.131897449493408, "validation/loss_047_lr4.3e+01_wd1.0e+00": 6.382692813873291, "validation/loss_048_lr5.0e+01_wd1.0e+00": 4.56634521484375, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.27033730158730157, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.33581349206349204, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.4623015873015873, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.5434027777777778, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.5855654761904762, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.6121031746031746, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.6316964285714286, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.6822916666666666, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.7755456349206349, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.8313492063492064, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.8601190476190477, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.8888888888888888, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9055059523809523, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9241071428571429, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9397321428571429, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9580853174603174, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9751984126984127, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9794146825396826, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9821428571428571, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9821428571428571, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9848710317460317, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9856150793650794, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9853670634920635, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9861111111111112, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.986359126984127, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9871031746031746, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9873511904761905, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9873511904761905, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9871031746031746, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9873511904761905, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.988343253968254, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9875992063492064, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.986359126984127, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9851190476190477, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9848710317460317, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.984375, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9848710317460317, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9801587301587301, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9846230158730159, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9799107142857143, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9831349206349206, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9580853174603174, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9794146825396826, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9578373015873016, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9811507936507936, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9791666666666666, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9702380952380952, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9553571428571429, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9734623015873016, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.10135176256786259, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.1499034586685099, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.23941128992741398, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.2986049767405162, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.3261548742558726, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.3456580203179527, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.3854418341683504, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.5062829187592418, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.6685519886208537, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.7597826782335894, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.8084934691445256, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.8563131266807311, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.8847464624048678, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.911690095297407, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9316460958213333, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9527029859154441, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9717344110940467, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9757052581645949, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9785924470367056, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9782516537820559, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9812448500765087, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9827163378594745, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9825773514042202, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9847550122860687, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9849355215675928, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9851697707289653, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.984985820911622, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9855448109970927, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9861189940205071, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9869717029608053, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9879669114839613, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9871751580110849, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9863048173525623, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9855526803891995, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.985779179342766, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9850843326296568, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9844072570075953, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9799822826191315, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9840039816747518, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9760135026279354, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9829281194675753, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.924284244060587, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9779203103521859, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9322102445734851, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9802562034557555, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.97150182157164, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9514802998768114, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9376485543602138, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9689497654777239, "id_best": 30, "lr_best": 0.00081, "wd_best": 0.05, "train/loss_best": 0.04291651234030724, "validation/loss_best": 0.03838475048542023, "validation/acc_best": 0.988343253968254, "validation/f1_best": 0.9879669114839613} +{"epoch": 4, "train/lr": 0.0002701201201201201, "train/loss": 0.8387561239302158, "train/grad": 0.4678950520604849, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.2472134399414063, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.156183166503906, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.011396026611328, "train/loss_003_lr3.3e-02_wd1.0e+00": 1.874197998046875, "train/loss_004_lr3.8e-02_wd1.0e+00": 1.7444329071044922, "train/loss_005_lr4.5e-02_wd1.0e+00": 1.5756345367431641, "train/loss_006_lr5.3e-02_wd1.0e+00": 1.4010467910766602, "train/loss_007_lr6.2e-02_wd1.0e+00": 1.227495002746582, "train/loss_008_lr7.4e-02_wd1.0e+00": 1.030812463760376, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.8558053398132324, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.7126087713241577, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.5386953818798065, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.40867600560188294, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.2761675253510475, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.19404400169849395, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.14281918022781612, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.10402599226683379, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.08146903790533543, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.07043040893040597, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.06468335194513201, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.059883278692141176, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.05617234881035984, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.05280904605053365, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.04987181662581861, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.047216873597353694, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.04481085320003331, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.0431527846492827, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.04199741811491549, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.04038296594284475, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0387011412717402, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.036647341018542647, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.03567608947865665, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.035180725092068314, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.035572687769308685, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.0367312597297132, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.03994269042275846, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.046469505205750467, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.05266806847415864, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.05981693490408361, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.11633160892874002, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.22090166743844747, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.32803951364010575, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.5747514914162457, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.8026850164402276, "train/loss_044_lr2.6e+01_wd1.0e+00": 1.5855479918420314, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.4001604620274155, "train/loss_046_lr3.6e+01_wd1.0e+00": 4.013370939223096, "train/loss_047_lr4.3e+01_wd1.0e+00": 6.472926363246516, "train/loss_048_lr5.0e+01_wd1.0e+00": 5.0127947633434085, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.02467110929079354, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.024202313777059316, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.023581320634111762, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.023009603368118404, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.022420740807428955, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.021548667466267945, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.0205014365632087, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.019325744262896478, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.017865780359134078, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.016506262011826037, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.015376259963959455, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.013917132951319218, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.012590001760981977, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.010799964067991823, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.009281431168783456, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.008024824889143928, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.006885968077694997, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.0062260276719462125, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.00602539254236035, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.005954325616476126, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.00590721917222254, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.0058556416124338284, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.005810202498105354, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.005771852463367395, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0057542589114746075, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.005811505119199864, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.005971795447985642, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.006098653144726995, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0061081623120117, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.006067954148747958, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.005904715530341491, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.005915449840249494, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.005891505555191543, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.005930075642245356, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.006162329784565372, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.006753468113747658, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.007650694053882035, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.008694177303477773, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.010621963138255523, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.017116889242906837, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.024798624859726174, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.03567740243238141, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.04887490150214116, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.05894118704088343, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.09506499462592476, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.12080172232308622, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.18466484012492274, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.22151531658766543, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.24168247195051634, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.101053237915039, "validation/loss_001_lr2.3e-02_wd1.0e+00": 1.9949266910552979, "validation/loss_002_lr2.8e-02_wd1.0e+00": 1.8268390893936157, "validation/loss_003_lr3.3e-02_wd1.0e+00": 1.6698442697525024, "validation/loss_004_lr3.8e-02_wd1.0e+00": 1.524153232574463, "validation/loss_005_lr4.5e-02_wd1.0e+00": 1.339638113975525, "validation/loss_006_lr5.3e-02_wd1.0e+00": 1.1559042930603027, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.9807127714157104, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.7909850478172302, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.6286619901657104, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.4981604218482971, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.3464969992637634, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.2471628487110138, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.15806065499782562, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.10549984127283096, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.08015639334917068, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.06645430624485016, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.05831164866685867, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.052729424089193344, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.04920952022075653, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.045886825770139694, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.04301229491829872, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.040547676384449005, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.03835213556885719, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.03657759353518486, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.035389140248298645, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.03458061069250107, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.03383335471153259, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.03313795104622841, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.03315935656428337, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.031711261719465256, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.03165052458643913, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.03466842323541641, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.03567330166697502, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.038444098085165024, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.04323085770010948, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.047185007482767105, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.11317653208971024, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.2562547028064728, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.24883587658405304, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.33623239398002625, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.8350163102149963, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.8045247197151184, "validation/loss_043_lr2.2e+01_wd1.0e+00": 1.8663533926010132, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.8739285469055176, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.137108087539673, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.864410877227783, "validation/loss_047_lr4.3e+01_wd1.0e+00": 5.021092891693115, "validation/loss_048_lr5.0e+01_wd1.0e+00": 4.558049201965332, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.5166170634920635, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.5711805555555556, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.6118551587301587, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.6272321428571429, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.6661706349206349, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.7544642857142857, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.8147321428571429, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.8531746031746031, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.8849206349206349, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9057539682539683, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9166666666666666, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9377480158730159, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9580853174603174, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9759424603174603, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9811507936507936, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9821428571428571, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9836309523809523, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9841269841269841, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.984375, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9851190476190477, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9853670634920635, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9868551587301587, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9871031746031746, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9885912698412699, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9878472222222222, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9888392857142857, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9893353174603174, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9898313492063492, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9898313492063492, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9890873015873016, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9900793650793651, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9905753968253969, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9890873015873016, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9898313492063492, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9898313492063492, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9890873015873016, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.988343253968254, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9801587301587301, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9632936507936508, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9789186507936508, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9796626984126984, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9637896825396826, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9764384920634921, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9494047619047619, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9670138888888888, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9776785714285714, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9766865079365079, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9781746031746031, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9791666666666666, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.2783929071212529, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.31216362906910977, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.34126899928537235, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.369214877001158, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.46527696014597797, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.6242413849981411, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.7262186729198141, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.8004925846405276, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.8527018985008474, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.8863949542971468, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9003611113429815, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9304085874445749, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9536690609837442, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9721661154607811, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9781198127202512, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9793173248666671, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9805407796074774, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9810348532699991, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9817300399276977, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9825503103497615, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9828981022246088, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.985053240192674, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9850055689326537, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9869491929240253, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9864666844371709, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9881647816321159, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.988525136977246, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.98890914261719, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9885867809077785, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9880473404833998, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9888795986634694, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9893175830949791, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9871105922485429, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9878639376981003, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9871441584906858, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9867914078803958, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9844792468385342, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9686263847035835, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9591385668180847, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9774046838040258, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9767919300801137, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9505856876251024, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9717051946237867, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9420069371247263, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9610535064473883, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9741546127463758, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9731012149755387, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9749766462446976, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9760454789885253, "id_best": 31, "lr_best": 0.0009299999999999999, "wd_best": 0.05, "train/loss_best": 0.03567608947865665, "validation/loss_best": 0.03165052458643913, "validation/acc_best": 0.9905753968253969, "validation/f1_best": 0.9893175830949791} +{"epoch": 5, "train/lr": 0.00029891323817685334, "train/loss": 0.8071592515707016, "train/grad": 0.468359452188015, "train/loss_000_lr2.0e-02_wd1.0e+00": 1.969862823486328, "train/loss_001_lr2.3e-02_wd1.0e+00": 1.849742431640625, "train/loss_002_lr2.8e-02_wd1.0e+00": 1.6626141357421875, "train/loss_003_lr3.3e-02_wd1.0e+00": 1.4920217132568359, "train/loss_004_lr3.8e-02_wd1.0e+00": 1.3382409286499024, "train/loss_005_lr4.5e-02_wd1.0e+00": 1.1499397850036621, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.9695217895507813, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.8034911775588989, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.6278039526939392, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.4802020359039307, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.3686232078075409, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.2524642500281334, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.17990657664835452, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.11711723042652011, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.08871483275666833, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.0766180472727865, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.06873222618363797, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.06320019166916609, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.05890688545070589, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.05580230567604303, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.0526390419434756, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.049832591991871594, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.047182558793574574, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.044770175376906994, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.04256045472808182, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.040214225137606266, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.03835518972948194, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.03654033908620477, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.03408377683721483, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.031239763954654335, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.02968883777037263, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.028947957213968038, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.028401295244693755, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.026684142658486964, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.030347920190542936, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.03256177713163197, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.03584549988619983, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.06889389618299901, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.16400878097862004, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.27028271633200346, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.29264976306818424, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.7804287577234209, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.7548561140522361, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.6847778824251145, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.2352475014608353, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.8348099248390644, "train/loss_046_lr3.6e+01_wd1.0e+00": 4.076844475185498, "train/loss_047_lr4.3e+01_wd1.0e+00": 5.366771875405684, "train/loss_048_lr5.0e+01_wd1.0e+00": 7.717810492366552, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.023306254567578434, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.022801260724663736, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.021911191288381815, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.02094884420745075, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.019955526627600192, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.018593637850135566, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.01718592980876565, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.015860203043557702, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.014468876430764794, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.013181137372739613, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.011944274078123271, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.010267744064331055, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.008909060414880514, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.007296273976098746, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.0064428287866758185, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.006148606070200913, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.006025389687274583, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.00597363667387981, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.005936049429001286, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.0059135779432835985, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.00588182568695629, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.005850665917387232, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.005836886708129896, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.005832613559323363, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.005821418894920498, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.005763733496132772, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.005701103593455627, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.005603741867525968, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.005462095775728812, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0052602917001058815, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.005217887601756957, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.005264768758788705, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.005346668038255302, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.005175523293873993, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.005849838130452554, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.00626986611789107, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.007066435293381801, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.011609106577716376, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.019342631113249808, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.027609488120080315, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.02706325774509196, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.05995391565840902, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.052405305705582876, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.053123431439205004, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.12842339044173864, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.13460167857329353, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.1962020577024456, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.2015192391160929, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.23139032296836404, "validation/loss_000_lr2.0e-02_wd1.0e+00": 1.8278402090072632, "validation/loss_001_lr2.3e-02_wd1.0e+00": 1.695724368095398, "validation/loss_002_lr2.8e-02_wd1.0e+00": 1.4930601119995117, "validation/loss_003_lr3.3e-02_wd1.0e+00": 1.3130214214324951, "validation/loss_004_lr3.8e-02_wd1.0e+00": 1.1551631689071655, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.9675347208976746, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.793365478515625, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.636397659778595, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.4722050130367279, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.3408060669898987, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.25142431259155273, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.16553331911563873, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.1127803847193718, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.0768558457493782, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.06429637968540192, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.05776521936058998, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.05237787589430809, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.047880519181489944, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.044106874614953995, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.041405998170375824, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.038707103580236435, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.036964818835258484, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.03685044124722481, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.03832482919096947, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.038521502166986465, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.03653261810541153, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.03605728596448898, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.03676023706793785, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.0380997397005558, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.038042712956666946, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.03578265756368637, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.03272946923971176, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.0289682075381279, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.03162587434053421, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.040516097098588943, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.04263416305184364, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.06276951730251312, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.12347634881734848, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.22041596472263336, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.33802953362464905, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.2782045304775238, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.521049439907074, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.9650261402130127, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.8662959337234497, "validation/loss_044_lr2.6e+01_wd1.0e+00": 1.7250781059265137, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.610795497894287, "validation/loss_046_lr3.6e+01_wd1.0e+00": 4.552351951599121, "validation/loss_047_lr4.3e+01_wd1.0e+00": 5.703041076660156, "validation/loss_048_lr5.0e+01_wd1.0e+00": 6.490594863891602, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.6108630952380952, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.6254960317460317, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.6790674603174603, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.7686011904761905, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.8318452380952381, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.8717757936507936, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.8908730158730159, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.9072420634920635, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9206349206349206, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9357638888888888, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9526289682539683, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9749503968253969, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9796626984126984, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9816468253968254, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9831349206349206, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9841269841269841, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.984375, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9858630952380952, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9866071428571429, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9878472222222222, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9880952380952381, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9890873015873016, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9885912698412699, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9873511904761905, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9871031746031746, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9878472222222222, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9875992063492064, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9871031746031746, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9853670634920635, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9858630952380952, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9871031746031746, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9885912698412699, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9900793650793651, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9898313492063492, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.988343253968254, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9898313492063492, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9848710317460317, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9818948412698413, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9781746031746031, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9769345238095238, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9776785714285714, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9816468253968254, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9729662698412699, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9799107142857143, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9833829365079365, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9764384920634921, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9751984126984127, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9747023809523809, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9754464285714286, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.342546420718613, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.3635369656974981, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.49305360640090906, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.6622796321227912, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.7696857591476199, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.8380549840510276, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.8692060801567352, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.8906062355047424, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.909408826810935, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9275773143008634, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9468078506964352, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9708578668615243, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9763882022371677, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9789212580952867, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9802350967027196, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9816110061479785, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9819324197454723, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9836870980121946, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9845849628792016, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9861614101829684, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9867961177746819, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.98864646422127, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9880239741372824, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9875599924301255, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9871950453064806, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9874469497847449, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9869087247976372, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9862233327276206, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9840560201655398, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9838040125543938, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9851390537141695, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9868036608254571, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9877200092498238, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9873606312908539, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9839402293491385, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9891554104339607, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9832270650075566, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9775687231103001, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9761518008662199, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9723680572808636, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9729949443905704, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9777005002615528, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9700275951900211, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9749419251696472, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9802202359963327, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9745679451682915, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9723018065696772, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9691051091244745, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9731301216527909, "id_best": 32, "lr_best": 0.0011099999999999999, "wd_best": 0.05, "train/loss_best": 0.028401295244693755, "validation/loss_best": 0.0289682075381279, "validation/acc_best": 0.9900793650793651, "validation/f1_best": 0.9877200092498238} +{"epoch": 6, "train/lr": 0.0002924170901991409, "train/loss": 0.5750416573137045, "train/grad": 0.386512750685215, "train/loss_000_lr2.0e-02_wd1.0e+00": 1.7120604705810547, "train/loss_001_lr2.3e-02_wd1.0e+00": 1.5706979370117187, "train/loss_002_lr2.8e-02_wd1.0e+00": 1.3589323806762694, "train/loss_003_lr3.3e-02_wd1.0e+00": 1.1760507011413575, "train/loss_004_lr3.8e-02_wd1.0e+00": 1.0195662117004394, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.838116397857666, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.6727043581008911, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.5251330542564392, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.37725880384445193, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.2698199000954628, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.19976905912160872, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.13183654107153417, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.09604342613369227, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.07532736611552536, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.0669371578656137, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.06203130567446351, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.057553955996409056, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.05358497523702681, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.05002215083688497, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.04720856240019202, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.04414047591388225, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.041283190017566085, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.03849097073078155, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.03561445946805179, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.03275270248763263, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.029447502577677368, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.026847557295113803, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.024759945198893546, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.022307420223951338, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.019609027402475478, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0168353127874434, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.015598775213584304, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.012758027138188481, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.014675123626366257, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.017225118968635798, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.02536008439026773, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.030081871282309294, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.06985424443148076, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.1392575154826045, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.15362522626295685, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.16023832880891858, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.23981563903391362, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.3528825621213764, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.5090713316295296, "train/loss_044_lr2.6e+01_wd1.0e+00": 1.3863403887674213, "train/loss_045_lr3.1e+01_wd1.0e+00": 1.9760672741383314, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.4856171026825904, "train/loss_047_lr4.3e+01_wd1.0e+00": 4.106804208084941, "train/loss_048_lr5.0e+01_wd1.0e+00": 5.7890256105735896, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.02216629815287888, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.02141330048441887, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.02009617635048926, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.018799252449534832, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.01760648368857801, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.01617964491713792, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.014883967698551714, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.013677705614827573, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.01213124740170315, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.01057409521425143, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.00930043518077582, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.00768506413209252, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.006590862784069031, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.006040814527659677, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.005920844589127228, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.005875542092253454, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.005827472593518905, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.0057666984345996755, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.005698964063194581, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.0056338888706522995, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.0055580300494330005, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.005473996020737104, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.005386932540859562, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.005238529662601649, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.005043746668088715, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.004810237470956054, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.004619849906302989, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.004474617469095392, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.004349090204486856, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.004180170197068947, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0038776051702006952, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.00371163572955993, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0033196713844517944, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.003812850889189576, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.00429605938928944, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.005907665043832821, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.008218968660366954, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.010611767638790468, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.016005537959334983, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.021696735668404302, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.019422534426241273, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.027877931194698148, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.035010108998328716, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.043467769718628736, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.09929646070116938, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.10826604243541571, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.1495306430240726, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.1603594439268007, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.21482459745707566, "validation/loss_000_lr2.0e-02_wd1.0e+00": 1.5893068313598633, "validation/loss_001_lr2.3e-02_wd1.0e+00": 1.4413598775863647, "validation/loss_002_lr2.8e-02_wd1.0e+00": 1.2243895530700684, "validation/loss_003_lr3.3e-02_wd1.0e+00": 1.042054533958435, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.8893439173698425, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.7154799103736877, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.5580576062202454, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.41921380162239075, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.2889138460159302, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.20117615163326263, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.14395225048065186, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.09210686385631561, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.07203789800405502, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.059925440698862076, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.0537576787173748, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.049604982137680054, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.0458514578640461, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.04236503690481186, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.03946040943264961, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.037380658090114594, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.03529662638902664, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.03390452638268471, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.03279677778482437, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.03236747160553932, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.03222152218222618, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.03224676474928856, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.03175682947039604, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.03155495598912239, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.03191373869776726, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.034171491861343384, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.03482365980744362, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.03409510478377342, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.0332295224070549, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.037126027047634125, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.03318217769265175, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.04517005383968353, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.08831639587879181, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.12333828210830688, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.13803930580615997, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.21329008042812347, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.23886826634407043, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.40785419940948486, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.5451593995094299, "validation/loss_043_lr2.2e+01_wd1.0e+00": 1.1143423318862915, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.3964884281158447, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.7426602840423584, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.2342476844787598, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.2162177562713623, "validation/loss_048_lr5.0e+01_wd1.0e+00": 6.073165416717529, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.6438492063492064, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.7053571428571429, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.8043154761904762, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.8561507936507936, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.8826884920634921, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.9052579365079365, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9206349206349206, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.9340277777777778, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9541170634920635, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9672619047619048, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9771825396825397, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9821428571428571, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9828869047619048, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9833829365079365, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9838789682539683, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9848710317460317, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.986359126984127, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9866071428571429, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9880952380952381, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.988343253968254, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9898313492063492, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9888392857142857, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9893353174603174, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9893353174603174, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9893353174603174, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9895833333333334, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9890873015873016, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9893353174603174, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9913194444444444, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9910714285714286, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9905753968253969, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9898313492063492, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9910714285714286, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9908234126984127, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9903273809523809, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9915674603174603, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9848710317460317, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.986359126984127, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9868551587301587, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9851190476190477, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9836309523809523, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9831349206349206, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9821428571428571, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9734623015873016, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9781746031746031, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9781746031746031, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.980406746031746, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.984375, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9749503968253969, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.41513403505065694, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.5543759120649551, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.7207894626912581, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.8107663139392529, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.8551292534398043, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.8879010368384687, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.9083086128274276, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9258435540946269, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9492518857124665, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9633181997004415, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9737080482455761, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9785367131460118, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9797647533692485, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9807592245259459, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9813633271122216, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9825520411368603, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9848836869013278, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9850536184022839, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9864921143892543, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9870457151398992, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9887171259922483, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9875902242158154, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9879511190705363, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.988304535248638, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9880786319664154, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9884018554772934, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9876977910065777, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9878777323833416, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9895545103792546, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9892245247585366, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9889401142211975, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9876715975890579, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9889048407675434, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9891102425600952, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9872023185293692, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.989234821300859, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9841396432465594, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9828009130763304, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9869879777243695, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9806057400540223, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9820967567270431, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9806744487874232, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.982207254762725, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.965084185305018, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9782367492912705, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9761450638469592, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9759180394559777, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9821882132830928, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9675312961901835, "id_best": 35, "lr_best": 0.0018, "wd_best": 0.05, "train/loss_best": 0.02536008439026773, "validation/loss_best": 0.04517005383968353, "validation/acc_best": 0.9915674603174603, "validation/f1_best": 0.989234821300859} +{"epoch": 7, "train/lr": 0.00027969249556793234, "train/loss": 0.4025047985836864, "train/grad": 0.3167829542607069, "train/loss_000_lr2.0e-02_wd1.0e+00": 1.4865953826904297, "train/loss_001_lr2.3e-02_wd1.0e+00": 1.3352703475952148, "train/loss_002_lr2.8e-02_wd1.0e+00": 1.1183038711547852, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.9402673530578614, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.7937932014465332, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.6285876083374023, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.4803238582611084, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.35501757383346555, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.24471507757902144, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.17100305423140527, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.12378983374685049, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.0881114012375474, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.07472265928052366, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.06550407264381647, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.06014013169333339, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.056381461769342424, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.052566590066999194, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.048957048216834664, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.04560317050665617, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.04283827626146376, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.03982757121324539, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.037049598880112174, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.034087304789572954, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.031132169514894486, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.028155968859791755, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.024757874337956308, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.02175388635136187, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.019178791604936123, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.01591679877601564, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.012529412340372801, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.009984502987936138, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.007522331019863486, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.004660015692934394, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.005135030103847384, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.00806725861504674, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.025430302331224085, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.027109440928325058, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.052675901018083095, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.05431046343408525, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.06306319078430533, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.11133579232729972, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.09888874299824238, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.22272434524260462, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.3225229813996702, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.7758505838084966, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.9996439164225012, "train/loss_046_lr3.6e+01_wd1.0e+00": 1.814433715334162, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.1002086514700204, "train/loss_048_lr5.0e+01_wd1.0e+00": 4.542286950722337, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.021149447923526167, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.020162538280710577, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.018566343197599054, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.017146384385414423, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.015955279865302145, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.014616699409671127, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.013311258195899426, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.011871256390586496, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.010193478867877274, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.008739553519990294, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.007494509957032278, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.006446003075689077, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.006170469924109056, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.0060400925669819115, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.005952793282340281, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.005877809692174196, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.005771189879742451, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.00564007118169684, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.005493765540304594, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.005370096814294812, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.00521154285146622, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.0050728936014638746, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.004924071306013502, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.004777527026599273, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.00463496077893069, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.004459409756527748, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.004264459292026004, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.004061521331313997, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0038043753679085058, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0035423672721663023, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.003242013243943802, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.002685317069699522, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0020551517341118597, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0022122321681945323, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0027027254157019343, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.005830197364589367, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.006963031232924095, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.010204398550891511, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.008582288622298087, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.013177981850745509, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.016082591669634775, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.019209251166279626, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.025771559044177727, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.03591266047441459, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.07424227710354886, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0798255277050392, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.11246317319187972, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.11092578137458603, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.18626496483701638, "validation/loss_000_lr2.0e-02_wd1.0e+00": 1.3887158632278442, "validation/loss_001_lr2.3e-02_wd1.0e+00": 1.2349846363067627, "validation/loss_002_lr2.8e-02_wd1.0e+00": 1.0187026262283325, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.8442195057868958, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.7020990252494812, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.5419687628746033, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.4002661406993866, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.2869764566421509, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.19269604980945587, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.12955588102340698, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.092335045337677, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.06970001757144928, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.06033124774694443, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.052983060479164124, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.04846630617976189, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.04538732394576073, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.042565926909446716, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.040139298886060715, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.03790351003408432, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.036327335983514786, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.03460373356938362, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.033356305211782455, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.032247576862573624, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.03124558925628662, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.030278297141194344, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.02909928932785988, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.0285793486982584, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.028246941044926643, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.029134996235370636, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.03280578553676605, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.03663821145892143, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.03462330624461174, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.03273778781294823, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.036503881216049194, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.044856201857328415, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.07417043298482895, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.08798406273126602, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.10720901191234589, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.14924503862857819, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.16414351761341095, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.2896939516067505, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.43842431902885437, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.43361493945121765, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.93980872631073, "validation/loss_044_lr2.6e+01_wd1.0e+00": 1.9833589792251587, "validation/loss_045_lr3.1e+01_wd1.0e+00": 1.7230342626571655, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.6448910236358643, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.6022305488586426, "validation/loss_048_lr5.0e+01_wd1.0e+00": 5.570596218109131, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.7338789682539683, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.8020833333333334, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.8611111111111112, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.8876488095238095, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9055059523809523, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.921875, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9372519841269841, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.9538690476190477, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9685019841269841, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9774305555555556, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9813988095238095, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9818948412698413, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9838789682539683, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.984375, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.986359126984127, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.986359126984127, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9871031746031746, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.988343253968254, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9888392857142857, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9895833333333334, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9895833333333334, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9898313492063492, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9903273809523809, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9898313492063492, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9908234126984127, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9910714285714286, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9910714285714286, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9908234126984127, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9905753968253969, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9898313492063492, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9895833333333334, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9908234126984127, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9913194444444444, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9913194444444444, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9905753968253969, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9885912698412699, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9885912698412699, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.988343253968254, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9871031746031746, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9878472222222222, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9848710317460317, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9841269841269841, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9858630952380952, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9766865079365079, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9789186507936508, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9831349206349206, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9759424603174603, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9774305555555556, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9749503968253969, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.6047204421084927, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.7154509367365277, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.8211201576293373, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.8643948828701846, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.8898665366369529, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.9119194972343608, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.9298773035437046, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9488885894879421, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9642369552377904, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9738858198677173, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9780513152978944, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9791727206077144, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9806389562850629, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9814982277712703, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9847197511353595, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9847185748214609, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9856587727717642, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9873385411764837, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9882743941935043, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9888130501642132, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9888130501642132, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9890824712202165, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9894538867238728, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9890319049369658, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9899749348026206, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9902447332900772, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9905167408393425, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9904113981990945, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9896057861469243, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9883087656526784, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9871230688333965, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.98907638591564, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9896423678468933, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9897613613865253, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9899733271641671, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9838790673785159, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9883463782710449, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9867970698652958, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9827355226451586, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9868261205868718, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9843026720673519, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9823719249200964, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9824842645155653, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.976131728961993, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9770208409942481, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9800652594071987, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9745861381972473, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9738320484236267, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9720865741013024, "id_best": 32, "lr_best": 0.0011099999999999999, "wd_best": 0.05, "train/loss_best": 0.004660015692934394, "validation/loss_best": 0.03273778781294823, "validation/acc_best": 0.9913194444444444, "validation/f1_best": 0.9896423678468933} +{"epoch": 8, "train/lr": 0.0002612959497061927, "train/loss": 0.25475235417485237, "train/grad": 0.22618723191320897, "train/loss_000_lr2.0e-02_wd1.0e+00": 1.2950301742553711, "train/loss_001_lr2.3e-02_wd1.0e+00": 1.141669750213623, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.9298636054992676, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.7619394874572754, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.6262310838699341, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.47482527017593384, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.34593358159065246, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.24838108837604522, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.16736341588199138, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.11393216397613287, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.0873931260406971, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.07146586468443275, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.06407858615741134, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.05771440734155476, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.053505737278610466, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.050291886171326045, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.04697695180773735, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.04362577369436622, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.04022743681445718, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.037368076797574756, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.034167429450899366, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.031165718557313083, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.02802914663217962, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.024881833465769887, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.021813940042629838, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.018296032724902034, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.015440158769488335, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.012987080067396163, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.009894472686573863, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.006480878526344895, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0039815020747482775, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.0034354542661458255, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.0029186261631548405, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.0019095924776047469, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.002467338601127267, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.019117303155362607, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.023785105859860777, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.025818859515711664, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.03302910544909537, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.03715843829326332, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.0505897806212306, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.0825146481860429, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.12852725923992694, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.2455866026878357, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.2928582048416138, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.49351731640286745, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.8170382543839514, "train/loss_047_lr4.3e+01_wd1.0e+00": 1.2620171217992902, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.0956210976373404, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.019692981685511767, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.01853544364217669, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.016790718771517277, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.015365851987153291, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.014235653267242014, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.012905294001102447, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.01144892520038411, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.009990762718953192, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.008430331943091006, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.007016931530088187, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.006205473378067836, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.005833455078536645, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.0057215255044866355, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.005646377418306656, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.005587858335929923, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.005524722640984692, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.005436648373142816, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.005327022976125591, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.0051699755628942514, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.005035440007341094, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.004859084047784563, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.004695077194046462, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.004522010232321918, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.004343981881538639, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.00414750297779392, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.003886538993319846, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.003608089111476147, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0032963844711048295, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0028368105156550884, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0022321060615104215, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.001666097780353084, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0015515702460879765, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0013506793533838391, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0007594238717956614, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0011204269056423754, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.005295223197697397, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.005522969350306113, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.006630440104025776, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.006506679053302342, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.00918592145411571, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.009504116837018932, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.014400285012426784, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.01851183956740986, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.030632396146329944, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.03214623107996378, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.04926078058281462, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0807873684555171, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.08487750573065718, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.12270838533451707, "validation/loss_000_lr2.0e-02_wd1.0e+00": 1.2264612913131714, "validation/loss_001_lr2.3e-02_wd1.0e+00": 1.0732237100601196, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.8642629384994507, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.6997931003570557, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.5667215585708618, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.41871336102485657, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.2973818778991699, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.20936930179595947, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.13599099218845367, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.09133480489253998, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.0727032870054245, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.06066573038697243, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.054498180747032166, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.04866650700569153, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.04497708007693291, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.042173102498054504, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.03958095982670784, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.037177398800849915, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.035326920449733734, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.03391413763165474, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.03251120075583458, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.03136514127254486, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.030412457883358, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.029464833438396454, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.028419213369488716, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.027597302570939064, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.027286546304821968, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.027202848345041275, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.027640322223305702, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.028906548395752907, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.0315077006816864, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.032500009983778, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.03263816609978676, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.036253638565540314, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.03758968785405159, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.05108167976140976, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.09566684067249298, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.09306865930557251, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.13382188975811005, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.2088831663131714, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.28173333406448364, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.32580363750457764, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.44471272826194763, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.49856507778167725, "validation/loss_044_lr2.6e+01_wd1.0e+00": 1.445003628730774, "validation/loss_045_lr3.1e+01_wd1.0e+00": 1.6172385215759277, "validation/loss_046_lr3.6e+01_wd1.0e+00": 2.4247050285339355, "validation/loss_047_lr4.3e+01_wd1.0e+00": 2.5962045192718506, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.8314387798309326, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.7983630952380952, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.8392857142857143, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.8740079365079365, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.8955853174603174, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9119543650793651, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.9260912698412699, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9481646825396826, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.966765873015873, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9786706349206349, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9809027777777778, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9826388888888888, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9828869047619048, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9851190476190477, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9858630952380952, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9866071428571429, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9871031746031746, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9880952380952381, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9885912698412699, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9888392857142857, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9888392857142857, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9885912698412699, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9888392857142857, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9893353174603174, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9895833333333334, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9905753968253969, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9903273809523809, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9908234126984127, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9910714285714286, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9905753968253969, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9915674603174603, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9898313492063492, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9903273809523809, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9915674603174603, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9915674603174603, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9910714285714286, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9893353174603174, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9875992063492064, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9878472222222222, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9875992063492064, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9848710317460317, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9851190476190477, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9875992063492064, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9848710317460317, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9873511904761905, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.984375, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9846230158730159, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9821428571428571, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9809027777777778, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9779265873015873, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.7016477534539771, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.7768239778833219, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.8350730795844774, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.8732430098251588, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.8970321097924648, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.916520725236714, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.9424865063204235, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.962386344289351, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.975176861402406, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9777050729183501, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9790174120134919, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9799380247191758, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9830654583650464, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9841599216242093, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9846176286446633, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9852917517994452, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9864326087781153, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9875063131781621, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9882703623919372, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9882703623919372, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.987494566439266, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9878063686411284, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9884032399007447, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.988763185348972, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9898169787124605, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9890475099189622, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.989497033553185, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9900701952857267, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9890635072420576, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9902536676230577, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9886767370430375, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.988885395619804, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9901277634901026, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9898678576272284, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.989523816937547, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9874386690413669, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9856391949138396, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9869763352613106, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9854355642897821, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9828737517078888, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9826358906292961, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9871267666258647, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9813220642451148, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.984253964873926, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9841792022303961, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9817943324346095, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9792911518878897, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9788186766468984, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9753705654491786, "id_best": 29, "lr_best": 0.0006899999999999999, "wd_best": 0.05, "train/loss_best": 0.006480878526344895, "validation/loss_best": 0.028906548395752907, "validation/acc_best": 0.9915674603174603, "validation/f1_best": 0.9902536676230577} +{"epoch": 9, "train/lr": 0.00023803200426111704, "train/loss": 0.18222556971013545, "train/grad": 0.17183239951729776, "train/loss_000_lr2.0e-02_wd1.0e+00": 1.162638816833496, "train/loss_001_lr2.3e-02_wd1.0e+00": 1.0112296485900878, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.8070162677764893, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.647558159828186, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.5191245460510254, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.37922115564346315, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.2695490151643753, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.19073244735598563, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.12485563136637211, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.0894408387131989, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.07537648910656572, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.06563999340869486, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.06022300626151264, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.054909754917025565, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.05107244135811925, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.047993519408628345, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.04464776832610369, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.0412183500919491, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.037817831793799994, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.03500118830241263, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.031758034890517595, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.028681840086355805, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.02545506617985666, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.02224226566031575, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.019139587488025425, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.01531081022694707, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.012005894230678677, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.009207137059420348, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0062561745475977655, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0038578308187425135, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.002539178766310215, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.0017297251243144273, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.001234295517206192, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.0004624423012137413, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.0008596240915358066, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.0047959105856716635, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.013296533934772014, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.009324833657592535, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.021148766316473486, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.021035127574577928, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.04696302815340459, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.03606040269136429, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.06019434509798884, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.12384292899630964, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.21661640551872552, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.24651970274746418, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.5363733972702175, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.6899842702876776, "train/loss_048_lr5.0e+01_wd1.0e+00": 1.00689065316692, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.01877908194903284, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.017585804993286727, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.015917113134637475, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.014627494574524462, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.013548986683599652, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.012081512829754502, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.010475922510959208, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.009011329624336213, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.007413202094612643, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.006349693809170276, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.006005841357400641, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.005843478461029008, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.005783737048041075, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.005724457051255741, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.005670366587582976, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.005613535610318649, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.00553913531213766, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.005435574306902708, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.0053095189084706364, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.005176602168357931, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.004997635834297398, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.0048072926551685664, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.004591637878911569, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.004349225127443787, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.004077062350697816, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.003654987117770361, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0031893412063072903, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.002746519790161983, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0021916553074333932, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0016244063118483608, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0011313120440900092, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0007619438239316878, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0005281361371089587, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0002555935253099051, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.00044850031085729824, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0018544903439840254, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.004293096486925414, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0031228700693061028, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0060222061392144035, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.007252490904992141, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.009832746433948063, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.008715238293235998, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.011853917781835342, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.019773112742647547, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.02552715752731447, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.029172305825586956, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.058968504773789655, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.06462362426652511, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.08111946841713802, "validation/loss_000_lr2.0e-02_wd1.0e+00": 1.098185658454895, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.9485776424407959, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.7485339045524597, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.592388927936554, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.46649906039237976, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.3327403962612152, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.23211362957954407, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.16022324562072754, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.10175395756959915, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.07489636540412903, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.06395483762025833, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.05548736825585365, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.05068310722708702, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.04590103030204773, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.04255659133195877, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.040165457874536514, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.03747943788766861, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.03512211889028549, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.03307884931564331, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.03162945434451103, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.030258826911449432, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.02905413694679737, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.027781080454587936, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.026749087497591972, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.026249293237924576, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.026101313531398773, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.025966711342334747, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.026086322963237762, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.027045628055930138, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.029304785653948784, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.0322536826133728, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.03209887817502022, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.03309880197048187, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.035502996295690536, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.038220517337322235, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.052650392055511475, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.11860208958387375, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.0959702655673027, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.09368561953306198, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.1664973944425583, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.2822156846523285, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.3047409653663635, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.5397231578826904, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.5511387586593628, "validation/loss_044_lr2.6e+01_wd1.0e+00": 1.1210261583328247, "validation/loss_045_lr3.1e+01_wd1.0e+00": 1.1611112356185913, "validation/loss_046_lr3.6e+01_wd1.0e+00": 2.334073781967163, "validation/loss_047_lr4.3e+01_wd1.0e+00": 2.1349496841430664, "validation/loss_048_lr5.0e+01_wd1.0e+00": 2.593740224838257, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.8395337301587301, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.8702876984126984, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.8958333333333334, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.9131944444444444, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9260912698412699, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.9444444444444444, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9613095238095238, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.9749503968253969, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9796626984126984, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9828869047619048, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9828869047619048, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.984375, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9848710317460317, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9868551587301587, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9875992063492064, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9880952380952381, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9888392857142857, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9890873015873016, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9898313492063492, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9900793650793651, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9895833333333334, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9895833333333334, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9898313492063492, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9908234126984127, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9913194444444444, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9910714285714286, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9910714285714286, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9915674603174603, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9910714285714286, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9903273809523809, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9903273809523809, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9910714285714286, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9915674603174603, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9923115079365079, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9918154761904762, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9900793650793651, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9878472222222222, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9875992063492064, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9915674603174603, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9866071428571429, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9873511904761905, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9868551587301587, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9818948412698413, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9858630952380952, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9831349206349206, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9858630952380952, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9811507936507936, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9851190476190477, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9821428571428571, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.7762331940833065, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.8315469198605431, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.8761039719729605, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.9001283480807933, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.9165077440680566, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.9379378457241555, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.9568265868467297, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.971170149303485, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9759817560546845, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9797927511890363, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9798993086015225, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9816329506491318, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9824036810796347, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9854814388997445, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9860213966104694, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9864241316519291, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9873371601091964, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9877325665843218, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9886329984606105, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9891742113504917, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9884741609182661, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.988355776446686, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9881629913511366, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9892438910431098, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9897101212373419, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9894252515443589, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9893340951459306, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9897172868763173, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9898007550594871, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.98933075672912, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9888872934742442, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9900429612017826, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9902189492497937, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9911151101289855, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9908210041312904, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9878441343689087, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9851134470239041, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9871028526144705, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9902265793008092, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9849887025735639, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.984610061896283, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9866766311709627, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9789281452871592, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9841536512494405, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9816433288654727, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9848010830407635, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9810910246402168, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9836990985505777, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9766919085881792, "id_best": 33, "lr_best": 0.00129, "wd_best": 0.05, "train/loss_best": 0.0004624423012137413, "validation/loss_best": 0.035502996295690536, "validation/acc_best": 0.9923115079365079, "validation/f1_best": 0.9911151101289855} +{"epoch": 10, "train/lr": 0.00021091808096876188, "train/loss": 0.13914641905575992, "train/grad": 0.14185000156983732, "train/loss_000_lr2.0e-02_wd1.0e+00": 1.0499726104736329, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.9036654949188232, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.7089356374740601, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.5569216871261596, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.4352495765686035, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.30929591953754426, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.2168016839027405, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.15041178479790687, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.09946477001532912, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.07844996355473995, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.06949783871881664, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.06223525322042406, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.05773864664137363, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.0531396655831486, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.04964469539001584, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.04671924866735935, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.04344656352885067, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.03996015244163573, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.036387028750032184, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.03320092011243105, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.02948249913752079, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.0257824513874948, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.02183752925135195, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.017886030804365873, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.01414780386723578, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.01004342976026237, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.006893000230193138, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.004638092014938593, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0025553386192768814, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0014704354479908944, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0009910598769783973, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.0006382384896278381, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.00042371878400444986, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.000284113185480237, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.00029794360511004926, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.0011069994047284127, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.005967835178598762, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.0026207496039569378, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.0058796868845820425, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.014491590717807413, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.03369513827376067, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.009904174339026213, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.029090169193223117, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.08802558537572622, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.09219200992025435, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.10177729266695679, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.21794513667002322, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.26896525305695834, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.8080022379662841, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.017803709032014014, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.016641815514303743, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.015119007779285312, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.01393898888491094, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.012855952568352223, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.011319883991964161, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.009787507238797843, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.008316102384123952, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.006703432821668684, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.006040153117501177, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.005832722834893503, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.00568384199636057, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.0055944489914691075, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.005494617134099826, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.005395304281264544, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.005301668548490852, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.005180697683244944, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.005039665054937359, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.0048819795636518394, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.004740184963593492, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.004549780355882831, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.004325086145981914, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0040409424898098225, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0037075636126974133, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0033207922388100997, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0027852084613550687, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0022615939545357834, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0017793177382191062, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0011869169581586903, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0007936942709329741, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0005673883874942476, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.00039277039953503843, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.00024955688759746407, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.00013255250762540528, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.00019514527603973876, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0005503081368052243, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0024623780012641063, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0017976558987536301, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0033359791222182444, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.005780300292108737, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.00861310304520111, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.005443664079243357, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.009100587368280426, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.015528976726402141, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.022666957949787108, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.018515118203766858, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.03183303890905213, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.03463126755788868, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.07963076044599625, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.998336672782898, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.8534262776374817, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.6612508296966553, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.5114274024963379, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.3931531012058258, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.27431362867355347, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.18878009915351868, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.1271614283323288, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.08370348811149597, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.06686470657587051, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.05908843129873276, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.05235498771071434, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.048093631863594055, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.0437350794672966, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.04070368409156799, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.03842264786362648, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.036166850477457047, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.03408266231417656, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.032441645860672, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.031240226700901985, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.030054999515414238, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.029348568990826607, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.02879924140870571, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.028617089614272118, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.028831658884882927, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.029558854177594185, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.030585477128624916, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.030673619359731674, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.02956356480717659, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.03093731962144375, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.031833965331315994, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.032565005123615265, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.03319638967514038, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.03439672663807869, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.03597527742385864, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.057873424142599106, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.08858584612607956, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.08389333635568619, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.09922589361667633, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.19877715408802032, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.2137639820575714, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.3292744755744934, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.32703691720962524, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.5847252011299133, "validation/loss_044_lr2.6e+01_wd1.0e+00": 1.054715871810913, "validation/loss_045_lr3.1e+01_wd1.0e+00": 1.072331428527832, "validation/loss_046_lr3.6e+01_wd1.0e+00": 1.3779644966125488, "validation/loss_047_lr4.3e+01_wd1.0e+00": 1.9868344068527222, "validation/loss_048_lr5.0e+01_wd1.0e+00": 2.304556131362915, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.8591269841269841, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.8812003968253969, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.9035218253968254, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.9196428571428571, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9340277777777778, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.9541170634920635, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9702380952380952, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.9789186507936508, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9813988095238095, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9831349206349206, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9838789682539683, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9846230158730159, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9856150793650794, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9858630952380952, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9875992063492064, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9890873015873016, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9898313492063492, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9900793650793651, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9898313492063492, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9895833333333334, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9898313492063492, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9905753968253969, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9903273809523809, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9903273809523809, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9898313492063492, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9893353174603174, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9895833333333334, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9890873015873016, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9910714285714286, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9915674603174603, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9913194444444444, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9913194444444444, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9915674603174603, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9925595238095238, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9923115079365079, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9893353174603174, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9900793650793651, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9913194444444444, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9918154761904762, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9873511904761905, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9880952380952381, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9868551587301587, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9868551587301587, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.982390873015873, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9871031746031746, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9873511904761905, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9856150793650794, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9833829365079365, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9816468253968254, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.8152602381018456, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.8523351449612848, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.88682877265781, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.909124909307616, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.926889190107386, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.9492699655689203, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.9654046336864232, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9751273363376453, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9774801284744568, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9797153257246803, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9809273488664557, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9818586306430538, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9834998969786992, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9836729807337521, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9860159958433196, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9875561516803288, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9887456848145433, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9889261573374372, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9890676806869607, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9887044178188299, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9886961205852922, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9890849024499957, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9889042332983855, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9890211936588431, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9884158903112669, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9881495566390428, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9885132432033414, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.988226826017663, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9895681114881941, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.990161449985835, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9900630839331712, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9904830976292845, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9902143462610453, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9908875335605135, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9907483075362984, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9875156888553571, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9884571716412309, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9897561432855019, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9902547343395993, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9856042768037092, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.987198273595656, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9859915930139681, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9833510065191111, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9812588980034698, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9860549133586775, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9856989845682241, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9844225118664892, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9798804181261651, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9802610635612241, "id_best": 33, "lr_best": 0.00129, "wd_best": 0.05, "train/loss_best": 0.000284113185480237, "validation/loss_best": 0.03439672663807869, "validation/acc_best": 0.9925595238095238, "validation/f1_best": 0.9908875335605135} +{"epoch": 11, "train/lr": 0.00018113997589164516, "train/loss": 0.10647004544734955, "train/grad": 0.09520728431642056, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.9584317970275879, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.8174790191650391, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.6311495399475098, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.4864065718650818, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.3735215282440186, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.26283576220273974, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.182635265737772, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.12448739640414715, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.08681420924142003, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.0724620782211423, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.0655001792125404, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.059224948482587934, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.05506097165867686, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.0504927490465343, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.046962436875328424, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.04410253744572401, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.040899019120261074, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.037495381580665704, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.03402895033359528, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.031139688026160003, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.02757303119637072, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.024023972461000086, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.020220040371641518, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.016191683737561108, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.012091718586161733, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.007604792341589927, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.004682930205017328, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.003057641955092549, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0018123596720397471, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0010874113813042641, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0006646861135959626, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.00047572812996804714, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.000316057363525033, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.0002220758143812418, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.00013454219326376914, "train/loss_035_lr6.0e+00_wd1.0e+00": 8.164162747561932e-05, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.0021333552710711954, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.005305419648066163, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.0073213375266641375, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.011499020662158728, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.007552691223099828, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.003656360534951091, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.022735323989763856, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.034645687928423284, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.035055163353681563, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.060708468006923796, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.04739290081895888, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.1060825000796467, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.29157376183196904, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.017023224607110022, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.01582228475715965, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.01425120561849326, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.01295582122169435, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.011682045790366828, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.010016782572492958, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.00855302514275536, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.007234572997549549, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.0061755609640385956, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.0058673941367305815, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.005771737270988524, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.005687385849305429, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.005624977952684276, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.00552206663414836, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.005435958714224398, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.005362302456051111, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.005257322726829443, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.005135442918690387, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.004981646201049444, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.004828158505551983, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.004624282756994944, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.004397496474120998, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.004118084276415175, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.003744812711374834, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0032658946279843803, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0025635471443092683, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0018863639266783138, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0014013843213251675, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0009321459256898379, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0005311476595306886, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.00030601460829529967, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.00022015877023932263, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.00013873096450652155, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0001028257664938792, "train/grad_034_lr5.1e+00_wd1.0e+00": 6.557194507422537e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 6.015881146293367e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0009045034322402789, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0014483385094267499, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.00210539736561499, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0035453418249670253, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.003167012179615203, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0025710171579976897, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.006450964698499504, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.009298410589617811, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.009394027240927319, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.015753616763658416, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.012809676155515749, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.02279288506520914, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.04252192156037978, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.9221838712692261, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.781512975692749, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.5954620838165283, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.4512180984020233, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.3403138816356659, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.23426710069179535, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.15878261625766754, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.10535139590501785, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.0739925280213356, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.06200144812464714, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.05572432279586792, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.049940261989831924, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.04622983559966087, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.0423908494412899, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.03979902341961861, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.03776779770851135, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.035857923328876495, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.034099239856004715, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.032330095767974854, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.031072305515408516, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.02985714189708233, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.028914785012602806, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.028115665540099144, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.02780276909470558, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.027916142717003822, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.0281702671200037, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.02858862653374672, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.02923043817281723, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.030040720477700233, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.031617533415555954, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.03329749405384064, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.03444434329867363, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.034658223390579224, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.035870522260665894, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.03634793683886528, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.05386621505022049, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.07787826657295227, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.08607517927885056, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.11550737172365189, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.16241824626922607, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.17632192373275757, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.2463192343711853, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.433193564414978, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.3619956970214844, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.9733599424362183, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.8203370571136475, "validation/loss_046_lr3.6e+01_wd1.0e+00": 1.1739431619644165, "validation/loss_047_lr4.3e+01_wd1.0e+00": 1.3597285747528076, "validation/loss_048_lr5.0e+01_wd1.0e+00": 1.460306167602539, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.8712797619047619, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.8881448412698413, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.9094742063492064, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.9255952380952381, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9412202380952381, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.9610615079365079, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9751984126984127, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.9796626984126984, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.982390873015873, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9841269841269841, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.984375, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9848710317460317, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9858630952380952, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9871031746031746, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9875992063492064, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.988343253968254, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9885912698412699, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9893353174603174, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9900793650793651, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9900793650793651, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9900793650793651, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9900793650793651, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9903273809523809, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9905753968253969, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9908234126984127, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9913194444444444, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9918154761904762, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9915674603174603, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9913194444444444, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9915674603174603, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9908234126984127, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9913194444444444, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9910714285714286, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9918154761904762, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9895833333333334, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9905753968253969, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9903273809523809, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9890873015873016, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9885912698412699, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9875992063492064, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.988343253968254, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9846230158730159, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9871031746031746, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9873511904761905, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.984375, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9848710317460317, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9873511904761905, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9856150793650794, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.8366166475065493, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.863625741209992, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.8950554800869859, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.91614461723192, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.9345838302049367, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.9560531133212868, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.9709777246229678, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9758914843866506, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9792327605269721, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.981027184117476, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9818496828097042, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9820855317444646, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9835277747175825, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.98546967727884, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.98620331770506, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9873215463377556, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9875913448252123, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9885424212417404, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9892845021677493, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9891949873057787, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9892003359033833, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9890519941803436, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9895896052216914, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9896686977744364, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9897116967417541, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9900606496433861, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9902332047610911, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9899657375831388, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9897864250769322, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9901002336015706, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9892468541377861, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9898871477774475, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.989468868564724, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9903034322291578, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9904230793415826, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9878099307451412, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9897962712640158, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9890162138316521, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9875881615939742, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9865074766102017, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9863901020444114, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9875732423346232, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9798241473802818, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9847501133243532, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9858813766760095, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9828958947985017, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9841793837961037, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9858464497143556, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9834745311833311, "id_best": 34, "lr_best": 0.0015299999999999997, "wd_best": 0.05, "train/loss_best": 0.00013454219326376914, "validation/loss_best": 0.03634793683886528, "validation/acc_best": 0.9920634920634921, "validation/f1_best": 0.9904230793415826} +{"epoch": 12, "train/lr": 0.0001499999999999999, "train/loss": 0.09094948632642627, "train/grad": 0.06543044065125286, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.9008958721160889, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.7627641487121583, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.5804730248451233, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.43954201459884645, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.3327775478363037, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.23188133418560028, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.15858960807323455, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.10722158562391997, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.07919941347092391, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.06807973781600594, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.06207610479556024, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.05629166943952441, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.05232489020563662, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.04780877771787345, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.04427641353569925, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.04138644867576659, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.038134097987785935, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.034776122756302354, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.031373323723673824, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.02841437396593392, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.024878477239981295, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.021216627797111868, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.017303102370351552, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.013280683178454638, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.009456506352871657, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.00573064655996859, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.0035517627838999033, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0022813407983630894, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.001323653571307659, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0007295238133519888, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0005041662231087685, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.00038743031211197377, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.000282819252461195, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.0002110319957137108, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.0001265988126397133, "train/loss_035_lr6.0e+00_wd1.0e+00": 5.300670862197876e-05, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.00014571111649274826, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.0018508570082485677, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.0013684229459613561, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.0015973117295652627, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.00047951423563063144, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.001372717535123229, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.0054919595923274755, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.010719250068068504, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.020688826274126767, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.01749115844257176, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.03260097755119205, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.06001950036734342, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.10309485456906259, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.016524340943433344, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.015405624280683696, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.01393822455778718, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.01263423246331513, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.011335240949410946, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.009751355976331979, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.008265475251246244, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.00681357215391472, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.0060193655942566695, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.005825103990500793, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.005741231477586552, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.005658501421567053, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.005570248885778711, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.0054418119339970875, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.0053094395902007815, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.005184215798508376, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.005036729502608068, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.004855029666796327, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.004664520531368907, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.004482759783568327, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.00425388540053973, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.003971393383108079, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0036102192169346382, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.003173072382924147, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0026658130127179902, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0019468449527630582, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.001359444381105277, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.000931602665596074, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0005480092617290211, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.00029267302913467576, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.00020112362345571456, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0001544315215687675, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.00011128878207273374, "train/grad_033_lr4.3e+00_wd1.0e+00": 8.549200412630853e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 5.59905073163236e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 3.7708775802194335e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 8.216867910556606e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0007537632461102717, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0004254685649413128, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.000890022268245376, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0007691668899355415, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.000610298183300648, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.002937526111664509, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.003949653984106019, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.005979169947914852, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.00480447936513498, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.007057785931113952, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.012342169312584335, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.018651788468825214, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.8642323017120361, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.7269629240036011, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.545837938785553, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.40654969215393066, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.3030978739261627, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.20688967406749725, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.13788291811943054, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.09190857410430908, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.0686219185590744, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.05873938649892807, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.053349174559116364, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.0480860099196434, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.04452476650476456, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.04094001650810242, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.03843268007040024, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.036621879786252975, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.03479297459125519, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.03329018875956535, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.031957466155290604, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.030930982902646065, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.030204076319932938, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.029560990631580353, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.029126694425940514, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.029149465262889862, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.02908274531364441, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.028946856036782265, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.02930631674826145, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.0296428594738245, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.030055757611989975, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.03120688535273075, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.032420750707387924, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.03317401558160782, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.03399619832634926, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.03486747667193413, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.0358884260058403, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.05253783240914345, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.0705856904387474, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.07789669185876846, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.09694185853004456, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.14870591461658478, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.15413200855255127, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.24551203846931458, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.3508606553077698, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.29610675573349, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.8892732858657837, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.7821326851844788, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.8348877429962158, "validation/loss_047_lr4.3e+01_wd1.0e+00": 1.0592573881149292, "validation/loss_048_lr5.0e+01_wd1.0e+00": 1.4972680807113647, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.8779761904761905, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.8973214285714286, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.917906746031746, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.9332837301587301, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9508928571428571, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.9652777777777778, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9779265873015873, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.9801587301587301, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9833829365079365, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9846230158730159, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9848710317460317, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9853670634920635, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9861111111111112, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9873511904761905, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9880952380952381, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9880952380952381, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9890873015873016, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9885912698412699, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9888392857142857, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9890873015873016, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9893353174603174, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9900793650793651, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9900793650793651, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9900793650793651, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9905753968253969, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9908234126984127, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9910714285714286, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9910714285714286, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9918154761904762, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9925595238095238, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9910714285714286, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9910714285714286, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9923115079365079, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9895833333333334, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9910714285714286, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9905753968253969, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9913194444444444, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9880952380952381, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.988343253968254, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9888392857142857, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9866071428571429, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9893353174603174, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9851190476190477, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9866071428571429, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9873511904761905, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.986359126984127, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9838789682539683, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.8477720092165972, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.8783594234038236, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.90716342923713, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.9261460747794944, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.9456016946770939, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.9604098375072235, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.9745048675277462, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9763340043185471, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9803754887723473, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9818450922629703, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9820821907235731, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9831624030711168, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9842146117722215, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9858378467522131, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9869669824354717, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9869669824354717, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9881848844202972, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9877353710871427, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9878688377452327, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9880516563469777, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9882283563761012, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9889302007936384, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.988908900989392, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.988908900989392, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9891744109935868, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9893978753211053, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9895338849444038, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9893468911486406, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9902477355962882, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9906939754812351, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9913668159488582, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9896645135245757, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9892959694426189, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9903366809427919, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9907831281244636, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9878564418492852, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9906425750894876, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9893401326059661, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9895013680297244, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9867394821992868, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.987736954634676, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9883880268495124, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.983874985478141, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9874113897902378, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9843932026452615, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9849186666525936, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9853809686762611, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9843788919742796, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.981318801618639, "id_best": 30, "lr_best": 0.00081, "wd_best": 0.05, "train/loss_best": 0.0005041662231087685, "validation/loss_best": 0.032420750707387924, "validation/acc_best": 0.9925595238095238, "validation/f1_best": 0.9913668159488582} +{"epoch": 13, "train/lr": 0.00011886002410835478, "train/loss": 0.07955300761386752, "train/grad": 0.050773622896522284, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.8410068225860595, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.7052751398086547, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.5267925834655762, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.3910625112056732, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.2920266926288605, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.20106208354234695, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.13509400457143783, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.09268181782215834, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.07201785292476416, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.06322596260346472, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.05816710322163999, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.05303829032927752, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.049263127837330105, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.045078453095629814, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.041708887498825786, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.03887211156077683, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.03570578955113888, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.03238323397934437, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.028947996580973266, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.0259467332996428, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.022292821099981666, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.018701750012114646, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.014959866302087904, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.011130311004817485, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.007577829016372562, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.0043469397909939285, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.0026225536596029995, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0017154313903301954, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.001030799699947238, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0006101703364402056, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0004212039336562157, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.00031549833714962006, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.00023400474339723586, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.00017690595239400864, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.0001142689399421215, "train/loss_035_lr6.0e+00_wd1.0e+00": 5.1915459334850314e-05, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.20609812438488e-05, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.0004793931916356087, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.00037028637714684007, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.0504940077662468e-05, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.00020671513862907887, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.0017181207239627839, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.0009762539993971586, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.0021798413805663584, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.0057191421557217835, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.00083819598890841, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.0034633118659257887, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.029805972641333937, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.03663825023919344, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.015982468584552406, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.014887753766961396, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.013447051285766065, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.012128724243957549, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.01084534582681954, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.00935255266726017, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.007889108874369413, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.00652486152946949, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.005925100930035114, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.005757513955468312, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.005685460750828497, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.0056144052115269, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.0055397471296601, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.005434533292427659, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.0053173518422408965, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.0051975121992290955, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.00504166856961092, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.0048466883832588795, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.004618451628193725, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.004391624459967716, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.004109601404488785, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.003783125649788417, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0033822886936832218, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.00289785684843082, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0022989415103802455, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0015686841944989283, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0010318224789443776, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0006934638109396474, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.00041472372035059377, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0002437281682136927, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.00017040381046967923, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.00013285947507711172, "train/grad_032_lr3.7e+00_wd1.0e+00": 9.781229974066719e-05, "train/grad_033_lr4.3e+00_wd1.0e+00": 7.602520081803732e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 5.2520389850201355e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 3.645529474441745e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 3.3288880803991616e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.00020799936090909354, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.00030295175601883166, "train/grad_039_lr1.2e+01_wd1.0e+00": 7.15961115342603e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.00014008074009086902, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.00042314498236424006, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0010187492813737823, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0013609728385008157, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0012607520630166572, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.001331162102152477, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0012943872878840611, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.00796584368035118, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.008996846329129792, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.8215098977088928, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.6870324611663818, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.5094807147979736, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.3745467960834503, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.2769107222557068, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.1876499354839325, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.12323617190122604, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.08379843831062317, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.06495200842618942, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.05657748132944107, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.05152630805969238, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.04670022428035736, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.04344211891293526, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.04013296589255333, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.03770488500595093, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.035968080163002014, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.034195054322481155, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.03242356330156326, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.03071124479174614, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.02941707707941532, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.027979828417301178, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.026977848261594772, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.02628675289452076, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.025942595675587654, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.026255669072270393, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.0271300096064806, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.028148414567112923, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.029129885137081146, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.030519764870405197, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.03221113607287407, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.033529043197631836, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.034301672130823135, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.034864190965890884, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.03520844504237175, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.03576423600316048, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.05146424099802971, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.06818704307079315, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.07757200300693512, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.09438826888799667, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.1359529197216034, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.16171246767044067, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.23009711503982544, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.2833694815635681, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.2716606855392456, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.8195966482162476, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.6696920394897461, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.7533774971961975, "validation/loss_047_lr4.3e+01_wd1.0e+00": 1.0258389711380005, "validation/loss_048_lr5.0e+01_wd1.0e+00": 1.135736107826233, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.8836805555555556, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.9017857142857143, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.9221230158730159, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.935515873015873, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9541170634920635, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.9704861111111112, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9791666666666666, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.9816468253968254, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9833829365079365, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9841269841269841, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9848710317460317, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.986359126984127, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9871031746031746, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9880952380952381, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9878472222222222, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9885912698412699, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.988343253968254, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9890873015873016, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9895833333333334, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9898313492063492, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9905753968253969, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9908234126984127, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9918154761904762, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9923115079365079, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9918154761904762, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9923115079365079, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9918154761904762, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9913194444444444, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9918154761904762, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9905753968253969, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9915674603174603, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9915674603174603, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9915674603174603, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9900793650793651, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9910714285714286, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9895833333333334, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9908234126984127, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.988343253968254, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9885912698412699, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9893353174603174, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9873511904761905, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9890873015873016, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9868551587301587, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9866071428571429, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9873511904761905, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9858630952380952, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9851190476190477, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.8574652935972292, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.885174581819148, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.912213998380492, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.9280698752098191, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.948906590154827, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.9656764398502822, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.9753511166146445, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9780650044927913, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9806702140569735, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9811521167768052, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.982083332085976, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9844431756911851, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9852970198055063, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9871528664578015, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9871038630162565, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9880949746058226, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.987915203448035, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9887766949981825, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9891362683677717, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9889269282090731, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9896050310881221, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.989763908157301, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.990755777764866, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9913434972886718, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9904356481741655, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9908393479244884, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9902925911690291, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.990785855751352, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9898412887522307, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9907772268616765, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9896444018955842, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9904252504627602, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9900567569140951, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9899309889779124, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9905568454381405, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9885769688488762, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9904417260099285, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9882738271032678, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9897793941964826, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9868171641180294, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9877027218653792, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9890537042000206, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9854862210113589, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.988269425199599, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9856242834385449, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9847155222588866, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9853809686762611, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9853781779972272, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9815160732534972, "id_best": 23, "lr_best": 0.00025499999999999996, "wd_best": 0.05, "train/loss_best": 0.011130311004817485, "validation/loss_best": 0.025942595675587654, "validation/acc_best": 0.9923115079365079, "validation/f1_best": 0.9913434972886718} +{"epoch": 14, "train/lr": 8.9081919031238e-05, "train/loss": 0.07595035770907999, "train/grad": 0.04204582661390305, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.812743968963623, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.6799603652954102, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.5053140950202942, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.37337751626968385, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.2788984912633896, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.19230709388852119, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.12914708375930786, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.0915953360311687, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.07369261275976896, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.06536650366149843, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.060374605413526294, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.05515644436702132, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.05132653064094484, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.046859237058088185, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.04327913627028465, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.04022711426950991, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.036733874138444665, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.03299498618580401, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.029180160835385324, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.02571636318229139, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.02165913858450949, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.017664514472708105, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.013529956424608826, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.00968891873024404, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.006343403281643987, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.00359319981187582, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.0021870440989732744, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0014552119188010692, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0009017523285001516, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0005497346445918083, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0003915482945740223, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.000302421897649765, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.00023326097056269645, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.0001779375970363617, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.00011504235677421092, "train/loss_035_lr6.0e+00_wd1.0e+00": 5.4527437314391136e-05, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.3611782342195512e-05, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.939968205988407e-05, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.4544548466801644e-05, "train/loss_039_lr1.2e+01_wd1.0e+00": 7.616318762302399e-06, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.0010387427546083928, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.5829969197511673e-06, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.8517635762691498e-05, "train/loss_043_lr2.2e+01_wd1.0e+00": 4.1477847844362256e-06, "train/loss_044_lr2.6e+01_wd1.0e+00": 7.62584526091814e-05, "train/loss_045_lr3.1e+01_wd1.0e+00": 4.8456015065312386e-05, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.6984682083129883e-07, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.002680909838527441, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.01454431631602347, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.015899968086741864, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.014814489604905248, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.013348784996196628, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.011974904381204396, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.010673767598345875, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.009172094170935452, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.007610394458752125, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.006409506696509197, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.005999638899229467, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.005888839625986293, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.005832461768295616, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.0057430964149534705, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.005658549937943462, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.0055206726843607615, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.005370964512403589, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.005233097560849273, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.005050489642017055, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.004841349740454462, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.00460796787563595, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.004367850749549689, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.004065072454977781, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.003723017601587344, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0033032983823795803, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0027964944931954962, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0021413114449751447, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0013783704716661305, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0008942593463689264, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0006085429192899028, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0003749633518009432, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.00022654336950836296, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.00015966982765348804, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0001238558868317341, "train/grad_032_lr3.7e+00_wd1.0e+00": 9.267739647043527e-05, "train/grad_033_lr4.3e+00_wd1.0e+00": 7.50530203447397e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 5.04390713660996e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 3.300693377319419e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 1.573877094518339e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 2.0196805344212644e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 9.208216246325489e-05, "train/grad_039_lr1.2e+01_wd1.0e+00": 1.6253655256137725e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.00010800057902680506, "train/grad_041_lr1.6e+01_wd1.0e+00": 1.7190448353152947e-05, "train/grad_042_lr1.9e+01_wd1.0e+00": 4.940241442864105e-05, "train/grad_043_lr2.2e+01_wd1.0e+00": 7.211561433966456e-05, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0006225989205979516, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.00039934138096865766, "train/grad_046_lr3.6e+01_wd1.0e+00": 1.4661465237150965e-06, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0016631649651347744, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.002671354536680326, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.7910478115081787, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.6584886908531189, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.48378002643585205, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.3522603511810303, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.259187251329422, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.17428188025951385, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.11344710737466812, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.07908960431814194, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.06289953738451004, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.05508669465780258, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.050405170768499374, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.04570640251040459, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.04247843474149704, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.03909101337194443, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.03670813515782356, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.0348881259560585, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.03326493501663208, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.03172016516327858, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.030368857085704803, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.029338540509343147, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.0283626951277256, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.027665333822369576, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.026999464258551598, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.026724129915237427, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.026767419651150703, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.027250653132796288, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.02802835777401924, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.02900576777756214, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.030201060697436333, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.03160247206687927, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.03275149315595627, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.03365488350391388, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.03462998569011688, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.035016439855098724, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.03586979955434799, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.05079498142004013, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.06672940403223038, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.07614385336637497, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.09264538437128067, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.1322895884513855, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.1387375146150589, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.22007736563682556, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.26196572184562683, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.24825574457645416, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.7627735733985901, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.6125783324241638, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.7028046250343323, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.8651293516159058, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.9809268712997437, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.8891369047619048, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.9052579365079365, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.9228670634920635, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.9412202380952381, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.957093253968254, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.9729662698412699, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9794146825396826, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.982390873015873, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9836309523809523, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.984375, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9851190476190477, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9861111111111112, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9866071428571429, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9880952380952381, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9890873015873016, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9895833333333334, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9900793650793651, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9900793650793651, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9898313492063492, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9905753968253969, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9908234126984127, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9903273809523809, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9915674603174603, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9918154761904762, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9918154761904762, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9918154761904762, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9923115079365079, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9918154761904762, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9918154761904762, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9910714285714286, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9913194444444444, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9918154761904762, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9923115079365079, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9900793650793651, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9908234126984127, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9898313492063492, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9905753968253969, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9885912698412699, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9890873015873016, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9895833333333334, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9878472222222222, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9898313492063492, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.986359126984127, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9880952380952381, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9871031746031746, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9866071428571429, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9871031746031746, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.866423069773679, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.8898295225650856, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.9133257112831824, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.9341376966190812, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.9520840652916672, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.9686505174416409, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.975909057454144, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9783763244165591, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.980683085825144, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9814961078578678, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9824576867168103, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9842135979647618, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9846149732966412, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9866051091455154, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9880470929466679, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9888610054804288, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9895821940855649, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9896326134257216, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9889552182995189, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9896950723447434, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9897347120235311, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9894253263514986, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9903555603849833, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.990535062509168, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.990348659093697, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9901634212062699, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9906087495323154, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9902493312253472, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9903236994395799, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9906948393106828, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.990645984111158, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9896645135245757, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9894715203955587, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9901100432836245, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9907831281244636, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9886211041780955, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9902631135846007, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9886334203212753, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.98978428004789, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9870435772937867, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9884617206894181, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9892324342279115, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9858457955873048, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9888089262502698, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9857451567740703, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9863587023548325, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9852012627070573, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9850549389941086, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.985240792593217, "id_best": 26, "lr_best": 0.00041999999999999996, "wd_best": 0.05, "train/loss_best": 0.0021870440989732744, "validation/loss_best": 0.02802835777401924, "validation/acc_best": 0.9923115079365079, "validation/f1_best": 0.9906087495323154} +{"epoch": 15, "train/lr": 6.196799573888289e-05, "train/loss": 0.07014416886493563, "train/grad": 0.04085801263339817, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.778273515701294, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.6468030786514283, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.47406391382217405, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.345361020565033, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.2548949494957924, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.17245292976498605, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.11301463566720486, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.08052242405712605, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.06537462486885488, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.05810695476830006, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.05363466403447092, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.0489412441290915, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.04542514973320067, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.04131088787689805, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.03799224776215851, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.035218835584819315, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.03204669895581901, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.028670848729088903, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.025222131023183464, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.02208495667204261, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.018410341059789063, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.014936552764847875, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.011393200205639005, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.008026435077190398, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.005167122567072511, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.002889497745782137, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.0017860214971005916, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0012216745503246785, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0007762819342315197, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0004871004726737738, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0003455810435116291, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.00026933980174362657, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.00020554392598569392, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.00015686636790633203, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.00010118693113327026, "train/loss_035_lr6.0e+00_wd1.0e+00": 4.623728804290295e-05, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.2652929872274398e-05, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.5259068459272384e-05, "train/loss_038_lr9.8e+00_wd1.0e+00": 7.296493276953697e-06, "train/loss_039_lr1.2e+01_wd1.0e+00": 8.781962096691131e-06, "train/loss_040_lr1.4e+01_wd1.0e+00": 4.213135689496994e-06, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.3657473027706147e-06, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.130037173628807e-06, "train/loss_043_lr2.2e+01_wd1.0e+00": 1.5928037464618683e-06, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.4486808106303214e-05, "train/loss_045_lr3.1e+01_wd1.0e+00": 6.338581442832947e-08, "train/loss_046_lr3.6e+01_wd1.0e+00": 5.2712857723236085e-08, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.002353592114523053, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.008998165782541036, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.01559115070849657, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.014544817809946835, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.013086212133057416, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.011665040822699667, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.010320972800254822, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008781964522786439, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.007279644384980201, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.0063221042428631335, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.006009182561538182, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.005906049106270075, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.005836480549769476, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.005739873999264091, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.005637369108735584, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.0054753982895636, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.005329371919506229, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.0051757844811072574, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.004999791931477375, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.0047912603024451526, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.004566301182203461, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.00433830586145632, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.004045534561955719, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.0037118307852506403, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0032676469289435774, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0026803693336842115, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.001980336961096327, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0012335880142927635, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0007898277001368115, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0005409136696653149, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0003380314386959071, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0002073892038424674, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.00014644426659288, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.00011590045769935387, "train/grad_032_lr3.7e+00_wd1.0e+00": 8.643844109428755e-05, "train/grad_033_lr4.3e+00_wd1.0e+00": 6.826074359878476e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 4.859054319922507e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 2.9521783220864962e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 1.570238823293088e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 1.7247534122613213e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 1.3519258060643506e-05, "train/grad_039_lr1.2e+01_wd1.0e+00": 1.7179241969115317e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 8.287593826333086e-06, "train/grad_041_lr1.6e+01_wd1.0e+00": 5.559668436971861e-06, "train/grad_042_lr1.9e+01_wd1.0e+00": 4.764580398748692e-06, "train/grad_043_lr2.2e+01_wd1.0e+00": 4.366188434683886e-06, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.00025697503072967054, "train/grad_045_lr3.1e+01_wd1.0e+00": 2.588707519725881e-07, "train/grad_046_lr3.6e+01_wd1.0e+00": 6.770301588649233e-07, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0015157622360899617, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.002325892689970174, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.7706103920936584, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.6392204761505127, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.46631428599357605, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.3376002907752991, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.24741314351558685, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.16549044847488403, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.10719713568687439, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.07607723772525787, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.06136893481016159, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.054061755537986755, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.04965345561504364, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.045102111995220184, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.04196394234895706, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.03861287981271744, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.03624064475297928, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.034420862793922424, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.03264230489730835, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.031034497544169426, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.029429055750370026, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.02825012244284153, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.02689712680876255, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.025983113795518875, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.025386856868863106, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.025197792798280716, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.025688115507364273, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.026674680411815643, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.027739407494664192, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.02874317578971386, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.030109276995062828, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.03153935819864273, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.032701704651117325, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.033361900597810745, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.034146618098020554, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.034642670303583145, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.035659078508615494, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.05032578855752945, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.06553453207015991, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.07537522166967392, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.09086018055677414, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.12925846874713898, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.13437752425670624, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.21343794465065002, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.2521357834339142, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.2398441582918167, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.7315526604652405, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.5827624201774597, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.6665636897087097, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.7833771705627441, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.9203164577484131, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.8901289682539683, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.9064980158730159, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.9233630952380952, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.9429563492063492, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9595734126984127, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.9739583333333334, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9801587301587301, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.9821428571428571, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9836309523809523, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.984375, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9848710317460317, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9858630952380952, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9873511904761905, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9885912698412699, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9890873015873016, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9898313492063492, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9900793650793651, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9898313492063492, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9905753968253969, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9905753968253969, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9913194444444444, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9915674603174603, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9925595238095238, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9928075396825397, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9925595238095238, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9925595238095238, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9923115079365079, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9918154761904762, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9918154761904762, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9918154761904762, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9915674603174603, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9913194444444444, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9923115079365079, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9900793650793651, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9910714285714286, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9898313492063492, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9908234126984127, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.988343253968254, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9890873015873016, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9895833333333334, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9880952380952381, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9898313492063492, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9873511904761905, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.988343253968254, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9871031746031746, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9873511904761905, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9871031746031746, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.8680037978784332, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.8912702151411099, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.9137214973844414, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.9358117361758137, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.9546736209211453, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.9698127820049824, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.976804920826744, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9785577360319302, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9809407833785344, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9816773990276187, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.982083332085976, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9840821127235658, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9862019104062802, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9876905321115185, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9881399188089484, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9890409124944154, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9892678436390779, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9890884481479002, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9896944321100773, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9896915438608489, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.990047979548886, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9903960064148233, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9917001243661354, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9918747267244115, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.991330609134221, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.991148119063687, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9910458008027002, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9908661456823802, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9908152396609796, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9909029408851199, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9909042283012177, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9903817393199846, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9898310062608431, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9902890780301059, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9907831281244636, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9885769688488762, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9904421988086919, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9886357359398728, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9899403289186454, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9864983825241334, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9884617206894181, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9892324342279115, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9861980268210793, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9888089262502698, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9865085365068585, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9865366324235649, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9852012627070573, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9853266001815835, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.985564021036244, "id_best": 23, "lr_best": 0.00025499999999999996, "wd_best": 0.05, "train/loss_best": 0.008026435077190398, "validation/loss_best": 0.025197792798280716, "validation/acc_best": 0.9928075396825397, "validation/f1_best": 0.9918747267244115} +{"epoch": 16, "train/lr": 3.870405029380728e-05, "train/loss": 0.06988177914172411, "train/grad": 0.03868596402928233, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.7679393482208252, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.6378147649765015, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.46656081199645993, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.3396259117126465, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.2513679966330528, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.17109410911798478, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.11365918315947056, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.08362321142107249, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.06933122985996305, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.062124731643125417, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.057435128986835476, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.05233963609673083, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.04855020249262452, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.044019992919638755, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.04050184088759124, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.03750036397948861, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.03410554089583456, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.030419949917122723, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.02655998562462628, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.023149242382496594, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.019104183297604323, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.015221973592415452, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.011335003795102239, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.007740059895440936, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.004786664703860879, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.002624704847112298, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.0016527791786938905, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0011467988695949315, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0007437355164438487, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0004712044633924961, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.00034077495336532593, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.0002684140577912331, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.0002042491268366575, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.00015623466111719609, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.00010720064863562585, "train/loss_035_lr6.0e+00_wd1.0e+00": 4.5132720842957496e-05, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.2234421446919442e-05, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.3833660632371903e-05, "train/loss_038_lr9.8e+00_wd1.0e+00": 5.090776830911637e-06, "train/loss_039_lr1.2e+01_wd1.0e+00": 9.127454832196236e-06, "train/loss_040_lr1.4e+01_wd1.0e+00": 4.3758377432823185e-06, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.4553312212228776e-06, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.9761902987957e-06, "train/loss_043_lr2.2e+01_wd1.0e+00": 7.600616663694382e-07, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.795800730586052e-06, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.590939402580261e-07, "train/loss_046_lr3.6e+01_wd1.0e+00": 9.329058229923248e-08, "train/loss_047_lr4.3e+01_wd1.0e+00": 4.0233135223388675e-09, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.0004809672012925148, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.015568602988496423, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.014530548295006156, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.013067957796156406, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.011635439461097121, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.010337994210422039, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008857988866511733, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.007310690764570609, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.0063296296133194116, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.006008645785041154, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.005891631793347187, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.005812493223929778, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.005697354372241534, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.005581131842627656, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.005393607218866237, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.005217408531752881, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.005044155355426483, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.00484066833043471, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.00459536756388843, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.004343487111036666, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.0040932292796787804, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.0037664852298621553, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.003403834835553425, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.00295408614052576, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0023676506856281777, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0016849787061073585, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0010158693973062328, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0006624095428196596, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0004644848260977597, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.00029674583417545365, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.00018646095941221574, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.00013377075931202852, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0001058208719018694, "train/grad_032_lr3.7e+00_wd1.0e+00": 8.14072278308231e-05, "train/grad_033_lr4.3e+00_wd1.0e+00": 6.340040413874704e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 4.587761271295676e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 3.105831165903794e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 1.4174990612774163e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 1.7450152868980218e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 8.471177322354912e-06, "train/grad_039_lr1.2e+01_wd1.0e+00": 1.715989405487964e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 7.932136004826522e-06, "train/grad_041_lr1.6e+01_wd1.0e+00": 4.739977774527791e-06, "train/grad_042_lr1.9e+01_wd1.0e+00": 6.886911764752066e-06, "train/grad_043_lr2.2e+01_wd1.0e+00": 1.859181534995054e-06, "train/grad_044_lr2.6e+01_wd1.0e+00": 1.0019691427698755e-05, "train/grad_045_lr3.1e+01_wd1.0e+00": 2.2536310549191672e-06, "train/grad_046_lr3.6e+01_wd1.0e+00": 5.541728837550049e-06, "train/grad_047_lr4.3e+01_wd1.0e+00": 1.2832588256303111e-08, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0007121674922802486, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.7579392194747925, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.6274875998497009, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.45566827058792114, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.3284977376461029, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.240237757563591, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.1601007878780365, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.10343264788389206, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.0743357464671135, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.06050172820687294, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.05350186675786972, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.04919227585196495, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.04485570266842842, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.041724007576704025, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.038447290658950806, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.03627033159136772, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.034555669873952866, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.03295569866895676, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.031389445066452026, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.030163802206516266, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.029162874445319176, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.02825046516954899, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.02745123952627182, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.0270405076444149, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.026899682357907295, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.02728206105530262, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.028204094618558884, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.02902924455702305, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.02994266338646412, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.031044306233525276, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.03227867931127548, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.03356480970978737, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.03416253998875618, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.03494307026267052, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.035373665392398834, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.03586622327566147, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.05035294219851494, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.06543740630149841, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.07469787448644638, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.08986665308475494, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.12776800990104675, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.13228236138820648, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.20876197516918182, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.2462015599012375, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.2351229041814804, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.7084566354751587, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.5656070113182068, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.6471078395843506, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.7555177211761475, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.8863644599914551, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.8913690476190477, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.9077380952380952, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.9248511904761905, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.9459325396825397, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9600694444444444, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.9749503968253969, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9801587301587301, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.9821428571428571, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9841269841269841, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.984375, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9848710317460317, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9856150793650794, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9871031746031746, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9885912698412699, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9893353174603174, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9898313492063492, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9895833333333334, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9900793650793651, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9903273809523809, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9908234126984127, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9903273809523809, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9903273809523809, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9910714285714286, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9908234126984127, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9915674603174603, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9923115079365079, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9918154761904762, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9923115079365079, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9918154761904762, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9913194444444444, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9915674603174603, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9915674603174603, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9923115079365079, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9898313492063492, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9910714285714286, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9898313492063492, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9908234126984127, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.988343253968254, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9895833333333334, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9895833333333334, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.988343253968254, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9900793650793651, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9873511904761905, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.988343253968254, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9871031746031746, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9873511904761905, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9866071428571429, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.8705907628964675, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.8930589993114921, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.9155389125089398, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.9396324413208759, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.9550267228974992, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.9708036672851621, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.9766001191788738, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9785577360319302, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9813957332153869, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9816773990276187, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.982083332085976, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.983852212301124, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9856578807972892, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9876905321115185, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9883198015391408, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9890882746281251, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9889086608526434, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9892685449709822, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9896056798075747, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9899648708322001, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9895339165323029, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.989191410495644, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.990132491223832, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9897070468692956, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9906110546399101, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9909671688070139, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9907866841671478, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9906069055990103, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9907367125705936, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9910398058048416, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9906360209609607, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9902026162098885, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9900096230808715, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9899309889779124, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9907831281244636, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9883975499206595, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9904417260099285, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9886357359398728, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9899403289186454, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9864919638056678, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9888227216678629, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9892314450169095, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9867365617389255, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9890802422352281, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9865085365068585, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9865868110947915, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9852012627070573, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9853266001815835, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9848487441578291, "id_best": 25, "lr_best": 0.00035999999999999997, "wd_best": 0.05, "train/loss_best": 0.002624704847112298, "validation/loss_best": 0.028204094618558884, "validation/acc_best": 0.9923115079365079, "validation/f1_best": 0.9909671688070139} +{"epoch": 17, "train/lr": 2.030750443206766e-05, "train/loss": 0.06883266968652606, "train/grad": 0.03723823429085314, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.7593557262420654, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.6298940086364746, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.4597392296791077, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.33409280598163604, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.2467603227496147, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.16701363533735275, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.11020118206739425, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.0812501041777432, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.0675711486954242, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.06059772189706564, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.0561503647454083, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.05133769007399678, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.04775382378138602, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.043524028090760114, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.04013882538303733, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.03731501751579344, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.03401997889392078, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.03052549543790519, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.02679552056826651, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.02346641772426665, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.019443824924528598, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.015446011004969477, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.011255909521132708, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.007376419994980097, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.0044233390036970376, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.0024253291636705397, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.0015280123054981231, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0010632230248302222, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0007026723399758339, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0004485944751650095, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.00032470437698066233, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.0002561538480222225, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.00019807549193501473, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.00015773700550198556, "train/loss_034_lr5.1e+00_wd1.0e+00": 9.722055867314339e-05, "train/loss_035_lr6.0e+00_wd1.0e+00": 4.075957462191582e-05, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.1973576620221139e-05, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.5776064246892927e-05, "train/loss_038_lr9.8e+00_wd1.0e+00": 4.415269941091537e-06, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.19058508425951e-05, "train/loss_040_lr1.4e+01_wd1.0e+00": 5.1636435091495515e-06, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.860354095697403e-06, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.8587522208690643e-06, "train/loss_043_lr2.2e+01_wd1.0e+00": 1.5893019735813141e-07, "train/loss_044_lr2.6e+01_wd1.0e+00": 9.780749678611755e-08, "train/loss_045_lr3.1e+01_wd1.0e+00": 7.743760943412781e-07, "train/loss_046_lr3.6e+01_wd1.0e+00": 7.658358663320541e-07, "train/loss_047_lr4.3e+01_wd1.0e+00": 1.1920928955078126e-08, "train/loss_048_lr5.0e+01_wd1.0e+00": 5.5065639317035674e-05, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.015058610681444406, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.014043195946142078, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.01264526563230902, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.011291406783275306, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.010018667585682125, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008497147087473423, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.006973069394007325, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.006086626525502652, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.005780641797464341, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.005663215883541853, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.005583894219016656, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.005473946438287385, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.0053689028619555755, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.005208299572695978, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.005052152622665744, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.004906055955216288, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.004725767060008366, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.004519036115088966, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.004281260335410479, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.004050784422433935, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.003737503960437607, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.0033657775631581897, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.002878094103944022, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.002243807628547074, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0015615327283740044, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0009346012120658997, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0006109397783620806, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0004299268207341811, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.00028336388385469035, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.00017895697507810837, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.00012882570505553303, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0001022647631180007, "train/grad_032_lr3.7e+00_wd1.0e+00": 7.882760396796585e-05, "train/grad_033_lr4.3e+00_wd1.0e+00": 6.30451608662952e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 4.5072905452343546e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 3.0057885438132814e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 1.2234182421177465e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 1.753529807283969e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 7.777404805797793e-06, "train/grad_039_lr1.2e+01_wd1.0e+00": 1.6188567459943328e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 8.129753818081462e-06, "train/grad_041_lr1.6e+01_wd1.0e+00": 4.444867907855885e-06, "train/grad_042_lr1.9e+01_wd1.0e+00": 4.1689976711135345e-06, "train/grad_043_lr2.2e+01_wd1.0e+00": 2.093667409728548e-06, "train/grad_044_lr2.6e+01_wd1.0e+00": 1.8933142754352986e-06, "train/grad_045_lr3.1e+01_wd1.0e+00": 2.201448948419483e-06, "train/grad_046_lr3.6e+01_wd1.0e+00": 5.1559330868754145e-06, "train/grad_047_lr4.3e+01_wd1.0e+00": 3.70427932871542e-08, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.00013940313280773182, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.751209557056427, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.6212815642356873, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.45020508766174316, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.32399070262908936, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.23660863935947418, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.15739037096500397, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.1015951931476593, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.07346552610397339, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.06003688648343086, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.05318337678909302, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.048915665596723557, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.04457501322031021, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.04149898141622543, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.038145191967487335, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.035892974585294724, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.03412706404924393, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.032427556812763214, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.03072235733270645, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.029208334162831306, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.02815673127770424, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.027026914060115814, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.02627192623913288, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.025807883590459824, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.025972863659262657, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.026575377210974693, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.027651658281683922, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.02850710041821003, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.029510140419006348, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.030635183677077293, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.032021112740039825, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.033171653747558594, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.03389355167746544, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.03461163491010666, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.035042375326156616, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.035682883113622665, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.050093021243810654, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.06496092677116394, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.07437671720981598, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.08937066793441772, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.12705625593662262, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.13104121387004852, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.20721280574798584, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.24281096458435059, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.23281648755073547, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.6973883509635925, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.5564202666282654, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.6358048319816589, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.7375892996788025, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.8574965596199036, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.8918650793650794, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.910218253968254, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.9246031746031746, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.9461805555555556, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9605654761904762, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.9751984126984127, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9799107142857143, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.9826388888888888, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9841269841269841, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9846230158730159, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9848710317460317, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9858630952380952, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9871031746031746, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9888392857142857, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9895833333333334, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9900793650793651, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9903273809523809, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9900793650793651, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9908234126984127, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9908234126984127, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9913194444444444, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9918154761904762, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9913194444444444, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9915674603174603, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9918154761904762, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9918154761904762, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9923115079365079, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9918154761904762, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9918154761904762, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9913194444444444, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9913194444444444, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9923115079365079, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9903273809523809, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9908234126984127, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9898313492063492, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9905753968253969, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9875992063492064, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9898313492063492, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9893353174603174, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.988343253968254, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9900793650793651, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9873511904761905, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.988343253968254, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9871031746031746, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9873511904761905, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9868551587301587, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.8715427709784672, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.896280975581823, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.9157271450755433, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.9398094688729747, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.9555682556657229, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.9713453880703222, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.9766178834824412, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9789158345107696, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9813957332153869, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9819030790215406, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.982083332085976, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9840316767918406, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9856578807972892, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9875056354396593, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9888610054804288, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9892674417108746, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9898087233020241, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9892676152306498, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9900075091182184, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9899147331126169, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.990281289135327, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9906195779935425, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9897163466386399, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9902562333785332, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.990615638366684, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9902946227233917, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9902506823263341, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9906093996383457, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9902001115924665, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9911285512744064, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.990466198739863, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.989843636634672, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9898310062608431, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9902890780301059, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9907831281244636, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9888005231063123, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9902631135846007, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9886357359398728, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.98978428004789, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9854979621505874, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9888782090911225, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9890527631764462, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9867365617389255, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9890802422352281, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9865085365068585, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9865366324235649, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9852012627070573, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9853266001815835, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9850275619379484, "id_best": 27, "lr_best": 0.00047999999999999996, "wd_best": 0.05, "train/loss_best": 0.0010632230248302222, "validation/loss_best": 0.029510140419006348, "validation/acc_best": 0.9923115079365079, "validation/f1_best": 0.9906093996383457} +{"epoch": 18, "train/lr": 7.5829098008590064e-06, "train/loss": 0.06618768687359988, "train/grad": 0.0370198459085077, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.7451206111907959, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.6171865129470825, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.4491956090927124, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.32527902603149417, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.23906311333179475, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.15996949762105941, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.10412259262055158, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.0760586911253631, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.0626740293763578, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.05585859849117696, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.05147127610631287, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.046767332768067715, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.043342996584251524, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.03932150146923959, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.03608374864794314, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.033443162152543664, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.030357577595859764, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.02712618129327893, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.023652781676501037, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.020545194717124106, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.016872013974934815, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.013315010983496904, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.009719113251194358, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.006417318116873503, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.0038459695596247912, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.00211352645419538, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.0013410454895347356, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0009342491440474987, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.000612831525504589, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.000390147352591157, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0002844186592847109, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.00022374214604496955, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.00016988455317914485, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.0001347988285124302, "train/loss_034_lr5.1e+00_wd1.0e+00": 9.025486186146736e-05, "train/loss_035_lr6.0e+00_wd1.0e+00": 4.084019921720028e-05, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.0111946612596513e-05, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.243380829691887e-05, "train/loss_038_lr9.8e+00_wd1.0e+00": 6.057741120457649e-06, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.054215244948864e-05, "train/loss_040_lr1.4e+01_wd1.0e+00": 4.755798727273941e-06, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.817874774336815e-06, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.344278618693352e-06, "train/loss_043_lr2.2e+01_wd1.0e+00": 7.027853280305863e-07, "train/loss_044_lr2.6e+01_wd1.0e+00": 5.408376455307007e-07, "train/loss_045_lr3.1e+01_wd1.0e+00": 4.3433159589767457e-07, "train/loss_046_lr3.6e+01_wd1.0e+00": 6.262212991714477e-08, "train/loss_047_lr4.3e+01_wd1.0e+00": 5.029141902923584e-10, "train/loss_048_lr5.0e+01_wd1.0e+00": 7.272884249687194e-07, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.015230770856142044, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.014198452369309961, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.012770562185905873, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.011379623143002391, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.01008797672810033, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008551602622028441, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.006917660308536142, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.005965214535244741, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.005656070206896402, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.0055404182762140404, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.005455443254031706, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.005340151898853947, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.005228356639272533, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.005054417673964053, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.004888851151772542, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.004742713342566276, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.004558407635631739, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.004346974919753848, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.004108048967027571, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.00387240104508237, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.003558117449938436, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.003186557402150356, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0027011958121147474, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.002088123362373153, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.00143412820303638, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0008633839193134918, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0005707937835632038, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0004064322040949264, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.00027073841805304256, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.00017130453063600725, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0001230625613607117, "train/grad_031_lr3.1e+00_wd1.0e+00": 9.760342869640226e-05, "train/grad_032_lr3.7e+00_wd1.0e+00": 7.53465359071015e-05, "train/grad_033_lr4.3e+00_wd1.0e+00": 5.945123184460499e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 4.384103890913593e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 2.76121777249827e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 1.211454927422806e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 1.6066845382294443e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 9.172289184451767e-06, "train/grad_039_lr1.2e+01_wd1.0e+00": 1.7578087915665772e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 8.307048310853543e-06, "train/grad_041_lr1.6e+01_wd1.0e+00": 5.303578245488712e-06, "train/grad_042_lr1.9e+01_wd1.0e+00": 4.336121317081336e-06, "train/grad_043_lr2.2e+01_wd1.0e+00": 2.7951640157126613e-06, "train/grad_044_lr2.6e+01_wd1.0e+00": 1.6037872719923612e-06, "train/grad_045_lr3.1e+01_wd1.0e+00": 2.1879587019454307e-06, "train/grad_046_lr3.6e+01_wd1.0e+00": 7.347334323342289e-06, "train/grad_047_lr4.3e+01_wd1.0e+00": 8.98921346875211e-08, "train/grad_048_lr5.0e+01_wd1.0e+00": 2.1608498339186224e-06, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.74876469373703, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.6189591288566589, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.44816964864730835, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.322237104177475, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.235210120677948, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.1562882512807846, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.10078702121973038, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.07316610962152481, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.05985889583826065, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.05311615765094757, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.04882087558507919, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.044464610517024994, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.04140268638730049, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.03819113224744797, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.03581628575921059, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.03414900600910187, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.03246891126036644, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.030871745198965073, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.029436562210321426, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.02829691208899021, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.027273334562778473, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.026486752554774284, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.026102742180228233, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.026119519025087357, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.02671509049832821, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.02781105414032936, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.02874758467078209, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.02965489961206913, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.030810896307229996, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.03212931379675865, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.03325311094522476, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.033953651785850525, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.034625500440597534, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.03512293100357056, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.035750195384025574, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.05012231320142746, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.06481508165597916, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.07444492727518082, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.08907667547464371, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.1265954077243805, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.13057687878608704, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.2069353610277176, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.24224089086055756, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.2313457876443863, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.6952571272850037, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.5538004636764526, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.6301602721214294, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.7325785160064697, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.8493458032608032, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.8923611111111112, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.9094742063492064, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.9248511904761905, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.9459325396825397, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9605654761904762, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.9754464285714286, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9801587301587301, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.9821428571428571, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.984375, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9846230158730159, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9851190476190477, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9858630952380952, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9871031746031746, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9885912698412699, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9893353174603174, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9895833333333334, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9903273809523809, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9900793650793651, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9908234126984127, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9908234126984127, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9905753968253969, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9913194444444444, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9910714285714286, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9918154761904762, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9923115079365079, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9925595238095238, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9918154761904762, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9923115079365079, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9915674603174603, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9913194444444444, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9913194444444444, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9923115079365079, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9903273809523809, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9908234126984127, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9898313492063492, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9908234126984127, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9875992063492064, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9895833333333334, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9893353174603174, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.988343253968254, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9900793650793651, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9873511904761905, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.988343253968254, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9871031746031746, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9873511904761905, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9868551587301587, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.8721612370450222, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.8956844561214836, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.9158180664811211, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.9395479010423657, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.9554774832749195, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.9712506948172613, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.9769642431939102, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9785577360319302, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9814086436749605, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9819030790215406, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9826311498007421, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9840316767918406, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9856578807972892, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9873260907125007, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9886814607532701, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9888610054804288, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9898091252302275, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9892683270739536, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9900081670765823, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9899147331126169, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9892904360138386, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9902599893310806, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.989354190662778, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9904355614142779, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.990615638366684, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9904736645923135, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9906087495323154, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9907884376905843, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9903784409441249, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9913072051829234, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.990097918275648, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.989843636634672, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9898310062608431, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9902890780301059, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9907831281244636, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9888005231063123, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9902631135846007, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9886357359398728, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9899403289186454, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9854979621505874, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9886988970141498, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9890527631764462, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9867365617389255, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9890802422352281, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9865085365068585, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9865366324235649, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9852012627070573, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9853266001815835, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9850275619379484, "id_best": 27, "lr_best": 0.00047999999999999996, "wd_best": 0.05, "train/loss_best": 0.0009342491440474987, "validation/loss_best": 0.02965489961206913, "validation/acc_best": 0.9925595238095238, "validation/f1_best": 0.9907884376905843} +{"epoch": 19, "train/lr": 1.0867618231465446e-06, "train/loss": 0.06646346338093281, "train/grad": 0.036901661073789, "train/loss_000_lr2.0e-02_wd1.0e+00": 0.7476754283905029, "train/loss_001_lr2.3e-02_wd1.0e+00": 0.6190612125396728, "train/loss_002_lr2.8e-02_wd1.0e+00": 0.450105140209198, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.3254783982038498, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.23909198820590974, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.16051282718777657, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.10511574395000935, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.07734854051843286, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.06412600067444146, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.057279712688177824, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.05288312889635563, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.048069952884688974, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.04444236359558999, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.04012387752532959, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.03662078105844557, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.033684525080025195, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.030381981609389187, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.026859734980389474, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.023260106816887855, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.02004824047908187, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.016313682505860926, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.012745173657312989, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.009225868852809072, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.006067553088068962, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.003713895892724395, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.002101886048913002, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.001347499918192625, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0009497764054685831, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0006365042831748724, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0004124731570482254, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0002942785248160362, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.00023368845693767071, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.00017816836945712565, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.00013926069252192974, "train/loss_034_lr5.1e+00_wd1.0e+00": 9.22851637005806e-05, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.54550126940012e-05, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.067478209733963e-05, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.4595119282603263e-05, "train/loss_038_lr9.8e+00_wd1.0e+00": 6.333505734801293e-06, "train/loss_039_lr1.2e+01_wd1.0e+00": 9.997570887207984e-06, "train/loss_040_lr1.4e+01_wd1.0e+00": 5.781520158052444e-06, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.676836982369423e-06, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.172749325633049e-06, "train/loss_043_lr2.2e+01_wd1.0e+00": 5.721673369407654e-07, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.2261013984680176e-08, "train/loss_045_lr3.1e+01_wd1.0e+00": 5.988124758005142e-07, "train/loss_046_lr3.6e+01_wd1.0e+00": 1.1723488569259643e-06, "train/loss_047_lr4.3e+01_wd1.0e+00": 4.908069968223571e-09, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.057291567325592e-08, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.0149589104950428, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.013933762963861228, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.012529404242523015, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.011152799052651971, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.00988440478220582, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008391913224477321, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.006912747885799035, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.006098626359598711, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.005851241629570723, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.00575482830114197, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.0056842704687733205, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.005567325201118365, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.005450180585612543, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.00527388716727728, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.005104749398306012, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.004949581118999049, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.004762724784377496, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.004538477682508528, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.00428914609568892, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.004033637197862845, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.0036931896102032624, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.003289165183523437, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0027849547529331174, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0021246229491953274, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0014434642932974384, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0008648129554421757, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0005665110401059792, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0004037908728423645, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0002692261439642607, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.00017086487482174563, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.00012359433196252212, "train/grad_031_lr3.1e+00_wd1.0e+00": 9.7351449467169e-05, "train/grad_032_lr3.7e+00_wd1.0e+00": 7.501435920630684e-05, "train/grad_033_lr4.3e+00_wd1.0e+00": 6.136257221328378e-05, "train/grad_034_lr5.1e+00_wd1.0e+00": 4.397621773591709e-05, "train/grad_035_lr6.0e+00_wd1.0e+00": 3.0356700517089054e-05, "train/grad_036_lr7.1e+00_wd1.0e+00": 1.1871959943422495e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 1.7947727087979647e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 8.412709366637655e-06, "train/grad_039_lr1.2e+01_wd1.0e+00": 1.4390124661011116e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 8.549708573492411e-06, "train/grad_041_lr1.6e+01_wd1.0e+00": 3.444372857501614e-06, "train/grad_042_lr1.9e+01_wd1.0e+00": 5.247439789516103e-06, "train/grad_043_lr2.2e+01_wd1.0e+00": 2.621280771572164e-06, "train/grad_044_lr2.6e+01_wd1.0e+00": 3.198753601309638e-06, "train/grad_045_lr3.1e+01_wd1.0e+00": 4.413228782004473e-06, "train/grad_046_lr3.6e+01_wd1.0e+00": 4.053301456133554e-06, "train/grad_047_lr4.3e+01_wd1.0e+00": 1.8294989419823905e-08, "train/grad_048_lr5.0e+01_wd1.0e+00": 1.592576886745742e-06, "validation/loss_000_lr2.0e-02_wd1.0e+00": 0.7484545111656189, "validation/loss_001_lr2.3e-02_wd1.0e+00": 0.6185985207557678, "validation/loss_002_lr2.8e-02_wd1.0e+00": 0.4478139579296112, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.32192808389663696, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.23501184582710266, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.15616901218891144, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.10066547989845276, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.07310393452644348, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.059857212007045746, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.05309922248125076, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.04881389066576958, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.04445353150367737, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.041416317224502563, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.03817075490951538, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.03577062487602234, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.034155748784542084, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.03245612606406212, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.03089485876262188, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.02947813831269741, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.028274208307266235, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.027262825518846512, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.026476824656128883, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.02606780454516411, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.026167945936322212, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.02668667398393154, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.027791425585746765, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.0286945141851902, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.029679344967007637, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.030783040449023247, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.03213363513350487, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.03324979543685913, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.03397432714700699, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.034687139093875885, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.03515792265534401, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.035764992237091064, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.05009128153324127, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.0648580864071846, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.07441439479589462, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.08906566351652145, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.12650066614151, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.13046520948410034, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.20681360363960266, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.2418663650751114, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.2316202074289322, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.695480465888977, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.5529024004936218, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.6306365132331848, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.7330631613731384, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.8486624956130981, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.8936011904761905, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.9099702380952381, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.9253472222222222, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.9456845238095238, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9603174603174603, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.9756944444444444, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.980406746031746, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.982390873015873, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.984375, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9846230158730159, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9853670634920635, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9858630952380952, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9871031746031746, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9885912698412699, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9893353174603174, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9895833333333334, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9903273809523809, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9900793650793651, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9908234126984127, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9908234126984127, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9908234126984127, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9910714285714286, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9910714285714286, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9918154761904762, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9923115079365079, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9915674603174603, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9923115079365079, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9915674603174603, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9913194444444444, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9913194444444444, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9920634920634921, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9923115079365079, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9903273809523809, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9910714285714286, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9898313492063492, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9905753968253969, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9878472222222222, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9895833333333334, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9893353174603174, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.988343253968254, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9900793650793651, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9873511904761905, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.988343253968254, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9871031746031746, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9873511904761905, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9868551587301587, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.8739807560351617, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.8961233683970706, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.9163849415738186, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.9393676410511917, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.9552062765593865, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.9717060915478959, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.9773424437544794, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9791047889220499, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9814086436749605, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9819030790215406, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9831692187378258, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9840316767918406, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9856578807972892, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9873260907125007, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9886814607532701, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9888610054804288, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9898091252302275, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9892683270739536, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9900081670765823, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9895500802592646, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9895602345012953, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9897187770300675, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.989354190662778, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9904355614142779, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.990615638366684, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9904297241952559, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9904297241952559, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9906093996383457, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.990276122683138, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9913072051829234, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.990097918275648, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.989843636634672, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9898310062608431, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9902890780301059, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9907831281244636, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9888005231063123, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9904417260099285, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9886357359398728, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.98978428004789, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9860452707366111, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9887756039293665, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9890527631764462, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9867365617389255, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9890802422352281, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9865085365068585, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9865366324235649, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9852012627070573, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9853266001815835, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9850275619379484, "id_best": 27, "lr_best": 0.00047999999999999996, "wd_best": 0.05, "train/loss_best": 0.0009497764054685831, "validation/loss_best": 0.029679344967007637, "validation/acc_best": 0.9923115079365079, "validation/f1_best": 0.9906093996383457} diff --git a/input_space_v3/flat_lr1e-3_6/eval_v2/nsd_cococlip__patch__attn/config.yaml b/input_space_v3/flat_lr1e-3_6/eval_v2/nsd_cococlip__patch__attn/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..b8d2493d45011b1c2d00e2d82cdc3731cfe76236 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_6/eval_v2/nsd_cococlip__patch__attn/config.yaml @@ -0,0 +1,96 @@ +output_root: experiments/input_space_v3/output +name_prefix: eval_probe +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_6; eval v2 (nsd_cococlip patch attn) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +dataset_kwargs: {} +classifier_kwargs: + embed_dim: null + dropout: 0.0 + xavier_init: true + norm: true +lr_scale_grid: +- 0.02 +- 0.023 +- 0.028 +- 0.033 +- 0.038 +- 0.045 +- 0.053 +- 0.062 +- 0.074 +- 0.087 +- 0.1 +- 0.12 +- 0.14 +- 0.17 +- 0.2 +- 0.23 +- 0.27 +- 0.32 +- 0.38 +- 0.44 +- 0.52 +- 0.61 +- 0.72 +- 0.85 +- 1 +- 1.2 +- 1.4 +- 1.6 +- 1.9 +- 2.3 +- 2.7 +- 3.1 +- 3.7 +- 4.3 +- 5.1 +- 6 +- 7.1 +- 8.3 +- 9.8 +- 12 +- 14 +- 16 +- 19 +- 22 +- 26 +- 31 +- 36 +- 43 +- 50 +wd_scale_grid: +- 1.0 +num_workers: 8 +prefetch_factor: null +balanced_sampling: false +epochs: 20 +steps_per_epoch: 200 +batch_size: 64 +accum_iter: 2 +lr: 0.0003 +warmup_epochs: 5 +no_decay: false +weight_decay: 0.05 +clip_grad: 1.0 +metrics: +- acc +- f1 +cv_metric: acc +early_stopping: true +amp: true +device: cuda +seed: 4466 +debug: false +wandb: false +wandb_entity: null +wandb_project: fMRI-fm-eval +name: input_space_v3/flat_lr1e-3_6/eval_v2/nsd_cococlip__patch__attn +model: flat_mae +representation: patch +classifier: attn +dataset: nsd_cococlip +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/eval_v2/nsd_cococlip__patch__attn +remote_dir: null diff --git a/input_space_v3/flat_lr1e-3_6/eval_v2/nsd_cococlip__patch__attn/eval_log.json b/input_space_v3/flat_lr1e-3_6/eval_v2/nsd_cococlip__patch__attn/eval_log.json new file mode 100644 index 0000000000000000000000000000000000000000..70a50e033506b224ed70d4463105a6e430128caa --- /dev/null +++ b/input_space_v3/flat_lr1e-3_6/eval_v2/nsd_cococlip__patch__attn/eval_log.json @@ -0,0 +1 @@ +{"eval/epoch": 5, "eval/id_best": 24, "eval/lr_best": 0.0003, "eval/wd_best": 0.05, "eval/train/loss": 2.119817018508911, "eval/train/acc": 0.3613817265435324, "eval/train/acc_std": 0.002279727059759347, "eval/train/f1": 0.29933332115783245, "eval/train/f1_std": 0.0024405093637882695, "eval/validation/loss": 2.366896867752075, "eval/validation/acc": 0.28497600590623845, "eval/validation/acc_std": 0.005301576249482847, "eval/validation/f1": 0.21435956293708777, "eval/validation/f1_std": 0.004917629178123139, "eval/test/loss": 2.2387547492980957, "eval/test/acc": 0.3202226345083488, "eval/test/acc_std": 0.005466550266750012, "eval/test/f1": 0.2477525933249812, "eval/test/f1_std": 0.00544484651737398, "eval/testid/loss": 2.289742946624756, "eval/testid/acc": 0.30711393869288606, "eval/testid/acc_std": 0.005744093891808626, "eval/testid/f1": 0.24561069465660465, "eval/testid/f1_std": 0.00562214236692606} diff --git a/input_space_v3/flat_lr1e-3_6/eval_v2/nsd_cococlip__patch__attn/eval_log_best.json b/input_space_v3/flat_lr1e-3_6/eval_v2/nsd_cococlip__patch__attn/eval_log_best.json new file mode 100644 index 0000000000000000000000000000000000000000..f5fc965d991a06144e36f4711d3aed7ebe2ea2a9 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_6/eval_v2/nsd_cococlip__patch__attn/eval_log_best.json @@ -0,0 +1 @@ +{"eval/best/epoch": 5, "eval/best/id_best": 24, "eval/best/lr_best": 0.0003, "eval/best/wd_best": 0.05, "eval/best/train/loss": 2.119817018508911, "eval/best/train/acc": 0.3613817265435324, "eval/best/train/acc_std": 0.002279727059759347, "eval/best/train/f1": 0.29933332115783245, "eval/best/train/f1_std": 0.0024405093637882695, "eval/best/validation/loss": 2.366896867752075, "eval/best/validation/acc": 0.28497600590623845, "eval/best/validation/acc_std": 0.005301576249482847, "eval/best/validation/f1": 0.21435956293708777, "eval/best/validation/f1_std": 0.004917629178123139, "eval/best/test/loss": 2.2387547492980957, "eval/best/test/acc": 0.3202226345083488, "eval/best/test/acc_std": 0.005466550266750012, "eval/best/test/f1": 0.2477525933249812, "eval/best/test/f1_std": 0.00544484651737398, "eval/best/testid/loss": 2.289742946624756, "eval/best/testid/acc": 0.30711393869288606, "eval/best/testid/acc_std": 0.005744093891808626, "eval/best/testid/f1": 0.24561069465660465, "eval/best/testid/f1_std": 0.00562214236692606} diff --git a/input_space_v3/flat_lr1e-3_6/eval_v2/nsd_cococlip__patch__attn/eval_log_last.json b/input_space_v3/flat_lr1e-3_6/eval_v2/nsd_cococlip__patch__attn/eval_log_last.json new file mode 100644 index 0000000000000000000000000000000000000000..4c674ecc0d39ddecebf8ff62a493409076690b21 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_6/eval_v2/nsd_cococlip__patch__attn/eval_log_last.json @@ -0,0 +1 @@ +{"eval/last/epoch": 19, "eval/last/id_best": 17, "eval/last/lr_best": 9.599999999999999e-05, "eval/last/wd_best": 0.05, "eval/last/train/loss": 2.092256546020508, "eval/last/train/acc": 0.3720151203171579, "eval/last/train/acc_std": 0.002380044597658343, "eval/last/train/f1": 0.3132636881308741, "eval/last/train/f1_std": 0.00257375755274064, "eval/last/validation/loss": 2.4113306999206543, "eval/last/validation/acc": 0.27611664820967147, "eval/last/validation/acc_std": 0.005453893599491371, "eval/last/validation/f1": 0.21601639128796082, "eval/last/validation/f1_std": 0.005197242738447557, "eval/last/test/loss": 2.229515314102173, "eval/last/test/acc": 0.31910946196660483, "eval/last/test/acc_std": 0.005433152537788364, "eval/last/test/f1": 0.2522805002750143, "eval/last/test/f1_std": 0.005426987146728296, "eval/last/testid/loss": 2.2600860595703125, "eval/last/testid/acc": 0.3152111046847889, "eval/last/testid/acc_std": 0.005636563477077144, "eval/last/testid/f1": 0.25453339201431885, "eval/last/testid/f1_std": 0.005586151987847107} diff --git a/input_space_v3/flat_lr1e-3_6/eval_v2/nsd_cococlip__patch__attn/eval_table.csv b/input_space_v3/flat_lr1e-3_6/eval_v2/nsd_cococlip__patch__attn/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..116d883e0057d331345f22364a9aac28acbf8ae1 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_6/eval_v2/nsd_cococlip__patch__attn/eval_table.csv @@ -0,0 +1,5 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,patch,attn,nsd_cococlip,best,5,0.0003,0.05,24,"[1, 1.0]",train,2.119817018508911,0.3613817265435324,0.002279727059759347,0.29933332115783245,0.0024405093637882695 +flat_mae,patch,attn,nsd_cococlip,best,5,0.0003,0.05,24,"[1, 1.0]",validation,2.366896867752075,0.28497600590623845,0.005301576249482847,0.21435956293708777,0.004917629178123139 +flat_mae,patch,attn,nsd_cococlip,best,5,0.0003,0.05,24,"[1, 1.0]",test,2.2387547492980957,0.3202226345083488,0.005466550266750012,0.2477525933249812,0.00544484651737398 +flat_mae,patch,attn,nsd_cococlip,best,5,0.0003,0.05,24,"[1, 1.0]",testid,2.289742946624756,0.30711393869288606,0.005744093891808626,0.24561069465660465,0.00562214236692606 diff --git a/input_space_v3/flat_lr1e-3_6/eval_v2/nsd_cococlip__patch__attn/eval_table_best.csv b/input_space_v3/flat_lr1e-3_6/eval_v2/nsd_cococlip__patch__attn/eval_table_best.csv new file mode 100644 index 0000000000000000000000000000000000000000..116d883e0057d331345f22364a9aac28acbf8ae1 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_6/eval_v2/nsd_cococlip__patch__attn/eval_table_best.csv @@ -0,0 +1,5 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,patch,attn,nsd_cococlip,best,5,0.0003,0.05,24,"[1, 1.0]",train,2.119817018508911,0.3613817265435324,0.002279727059759347,0.29933332115783245,0.0024405093637882695 +flat_mae,patch,attn,nsd_cococlip,best,5,0.0003,0.05,24,"[1, 1.0]",validation,2.366896867752075,0.28497600590623845,0.005301576249482847,0.21435956293708777,0.004917629178123139 +flat_mae,patch,attn,nsd_cococlip,best,5,0.0003,0.05,24,"[1, 1.0]",test,2.2387547492980957,0.3202226345083488,0.005466550266750012,0.2477525933249812,0.00544484651737398 +flat_mae,patch,attn,nsd_cococlip,best,5,0.0003,0.05,24,"[1, 1.0]",testid,2.289742946624756,0.30711393869288606,0.005744093891808626,0.24561069465660465,0.00562214236692606 diff --git a/input_space_v3/flat_lr1e-3_6/eval_v2/nsd_cococlip__patch__attn/eval_table_last.csv b/input_space_v3/flat_lr1e-3_6/eval_v2/nsd_cococlip__patch__attn/eval_table_last.csv new file mode 100644 index 0000000000000000000000000000000000000000..a56f32d44c8c8fb355cdc48b9b07e3bf594786bf --- /dev/null +++ b/input_space_v3/flat_lr1e-3_6/eval_v2/nsd_cococlip__patch__attn/eval_table_last.csv @@ -0,0 +1,5 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,patch,attn,nsd_cococlip,last,19,9.599999999999999e-05,0.05,17,"[0.32, 1.0]",train,2.092256546020508,0.3720151203171579,0.002380044597658343,0.3132636881308741,0.00257375755274064 +flat_mae,patch,attn,nsd_cococlip,last,19,9.599999999999999e-05,0.05,17,"[0.32, 1.0]",validation,2.4113306999206543,0.27611664820967147,0.005453893599491371,0.21601639128796082,0.005197242738447557 +flat_mae,patch,attn,nsd_cococlip,last,19,9.599999999999999e-05,0.05,17,"[0.32, 1.0]",test,2.229515314102173,0.31910946196660483,0.005433152537788364,0.2522805002750143,0.005426987146728296 +flat_mae,patch,attn,nsd_cococlip,last,19,9.599999999999999e-05,0.05,17,"[0.32, 1.0]",testid,2.2600860595703125,0.3152111046847889,0.005636563477077144,0.25453339201431885,0.005586151987847107 diff --git a/input_space_v3/flat_lr1e-3_6/eval_v2/nsd_cococlip__patch__attn/log.txt b/input_space_v3/flat_lr1e-3_6/eval_v2/nsd_cococlip__patch__attn/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..ee52a8d0ac549ed646536f8d5e6935e515563e43 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_6/eval_v2/nsd_cococlip__patch__attn/log.txt @@ -0,0 +1,963 @@ +fMRI foundation model probe eval +version: 0.1.dev86+gf97f52698 +sha: bcce2b486277d3a5b520775efd9cdf1a2affce36, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-04-08 21:11:26 +config: +output_root: experiments/input_space_v3/output +name_prefix: eval_probe +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_6; eval v2 (nsd_cococlip patch attn) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +dataset_kwargs: {} +classifier_kwargs: + embed_dim: null + dropout: 0.0 + xavier_init: true + norm: true +lr_scale_grid: +- 0.02 +- 0.023 +- 0.028 +- 0.033 +- 0.038 +- 0.045 +- 0.053 +- 0.062 +- 0.074 +- 0.087 +- 0.1 +- 0.12 +- 0.14 +- 0.17 +- 0.2 +- 0.23 +- 0.27 +- 0.32 +- 0.38 +- 0.44 +- 0.52 +- 0.61 +- 0.72 +- 0.85 +- 1 +- 1.2 +- 1.4 +- 1.6 +- 1.9 +- 2.3 +- 2.7 +- 3.1 +- 3.7 +- 4.3 +- 5.1 +- 6 +- 7.1 +- 8.3 +- 9.8 +- 12 +- 14 +- 16 +- 19 +- 22 +- 26 +- 31 +- 36 +- 43 +- 50 +wd_scale_grid: +- 1.0 +num_workers: 8 +prefetch_factor: null +balanced_sampling: false +epochs: 20 +steps_per_epoch: 200 +batch_size: 64 +accum_iter: 2 +lr: 0.0003 +warmup_epochs: 5 +no_decay: false +weight_decay: 0.05 +clip_grad: 1.0 +metrics: +- acc +- f1 +cv_metric: acc +early_stopping: true +amp: true +device: cuda +seed: 4466 +debug: false +wandb: false +wandb_entity: null +wandb_project: fMRI-fm-eval +name: input_space_v3/flat_lr1e-3_6/eval_v2/nsd_cococlip__patch__attn +model: flat_mae +representation: patch +classifier: attn +dataset: nsd_cococlip +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/eval_v2/nsd_cococlip__patch__attn +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=True, reg_tokens=0, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: nsd_cococlip (flat) +train (n=32539): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'run', 'trial_id', 'nsd_id', 'category_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 32539 +}), + labels=[ 3 4 5 6 10 11 17 18 19 20 22 23 25 30 31 33 36 37 38 53 55 59 61 74], + counts=[1286 1180 1639 1868 834 824 1026 1042 913 1853 1503 2092 1001 1410 + 794 1241 1904 1872 2267 1428 889 904 1447 1322] +) + +validation (n=5418): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'run', 'trial_id', 'nsd_id', 'category_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 5418 +}), + labels=[ 3 4 5 6 10 11 17 18 19 20 22 23 25 30 31 33 36 37 38 53 55 59 61 74], + counts=[197 161 276 345 126 142 143 185 112 295 285 387 169 250 159 193 316 334 + 343 215 172 141 226 246] +) + +test (n=5390): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'run', 'trial_id', 'nsd_id', 'category_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 5390 +}), + labels=[ 3 4 5 6 10 11 17 18 19 20 22 23 25 30 31 33 36 37 38 53 55 59 61 74], + counts=[202 172 274 298 144 180 134 182 186 293 218 343 165 185 140 177 346 333 + 345 271 165 140 251 246] +) + +testid (n=5187): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'run', 'trial_id', 'nsd_id', 'category_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 5187 +}), + labels=[ 3 4 5 6 10 11 17 18 19 20 22 23 25 30 31 33 36 37 38 53 55 59 61 74], + counts=[197 159 267 273 123 153 175 184 139 310 215 386 153 230 118 192 330 306 + 349 223 143 127 249 186] +) + +running backbone on example batch to get embedding dim +embedding feature dim (patch): 768 +initializing sweep of classifier heads +classifiers: +ModuleList( + (0-48): 49 x AttnPoolClassifier( + (kv): Linear(in_features=768, out_features=1536, bias=True) + (linear): Linear(in_features=768, out_features=24, bias=True) + ) +) +classifier params (train): 58.8M (58.8M) +setting up optimizer +total batch size: 128 = 64 bs per gpu x 2 accum +lr: 3.00e-04 +full schedule: epochs = 20 (steps = 4000) (decay = True) +warmup: epochs = 5 (steps = 1000) +start training for 20 epochs +train: [0] [ 0/400] eta: 0:36:27 lr: nan time: 5.4699 data: 4.8458 max mem: 21740 +train: [0] [ 20/400] eta: 0:04:46 lr: 0.000003 loss: 3.1576 (3.1720) grad: 0.1607 (0.1606) time: 0.5168 data: 0.0065 max mem: 22448 +train: [0] [ 40/400] eta: 0:03:45 lr: 0.000006 loss: 3.1557 (3.1621) grad: 0.1607 (0.1609) time: 0.4954 data: 0.0040 max mem: 22448 +train: [0] [ 60/400] eta: 0:03:16 lr: 0.000009 loss: 3.1557 (3.1623) grad: 0.1576 (0.1612) time: 0.4740 data: 0.0045 max mem: 22448 +train: [0] [ 80/400] eta: 0:02:56 lr: 0.000012 loss: 3.1525 (3.1601) grad: 0.1553 (0.1608) time: 0.4707 data: 0.0045 max mem: 22448 +train: [0] [100/400] eta: 0:02:39 lr: 0.000015 loss: 3.1625 (3.1610) grad: 0.1553 (0.1600) time: 0.4586 data: 0.0045 max mem: 22448 +train: [0] [120/400] eta: 0:02:25 lr: 0.000018 loss: 3.1625 (3.1589) grad: 0.1459 (0.1578) time: 0.4656 data: 0.0044 max mem: 22448 +train: [0] [140/400] eta: 0:02:13 lr: 0.000021 loss: 3.1454 (3.1573) grad: 0.1474 (0.1577) time: 0.4669 data: 0.0043 max mem: 22448 +train: [0] [160/400] eta: 0:02:02 lr: 0.000024 loss: 3.1499 (3.1551) grad: 0.1643 (0.1593) time: 0.4724 data: 0.0042 max mem: 22448 +train: [0] [180/400] eta: 0:01:50 lr: 0.000027 loss: 3.1253 (3.1528) grad: 0.1605 (0.1592) time: 0.4637 data: 0.0041 max mem: 22448 +train: [0] [200/400] eta: 0:01:39 lr: 0.000030 loss: 3.1366 (3.1528) grad: 0.1510 (0.1579) time: 0.4534 data: 0.0043 max mem: 22448 +train: [0] [220/400] eta: 0:01:29 lr: 0.000033 loss: 3.1509 (3.1521) grad: 0.1525 (0.1576) time: 0.4625 data: 0.0043 max mem: 22448 +train: [0] [240/400] eta: 0:01:18 lr: 0.000036 loss: 3.1339 (3.1503) grad: 0.1547 (0.1572) time: 0.4641 data: 0.0042 max mem: 22448 +train: [0] [260/400] eta: 0:01:08 lr: 0.000039 loss: 3.1140 (3.1480) grad: 0.1503 (0.1566) time: 0.4621 data: 0.0041 max mem: 22448 +train: [0] [280/400] eta: 0:00:58 lr: 0.000042 loss: 3.1033 (3.1445) grad: 0.1501 (0.1564) time: 0.4624 data: 0.0042 max mem: 22448 +train: [0] [300/400] eta: 0:00:48 lr: 0.000045 loss: 3.0885 (3.1399) grad: 0.1524 (0.1565) time: 0.4735 data: 0.0042 max mem: 22448 +train: [0] [320/400] eta: 0:00:38 lr: 0.000048 loss: 3.0730 (3.1364) grad: 0.1613 (0.1574) time: 0.4775 data: 0.0041 max mem: 22448 +train: [0] [340/400] eta: 0:00:29 lr: 0.000051 loss: 3.0731 (3.1330) grad: 0.1624 (0.1577) time: 0.4771 data: 0.0042 max mem: 22448 +train: [0] [360/400] eta: 0:00:19 lr: 0.000054 loss: 3.0570 (3.1285) grad: 0.1627 (0.1585) time: 0.4687 data: 0.0041 max mem: 22448 +train: [0] [380/400] eta: 0:00:09 lr: 0.000057 loss: 3.0528 (3.1246) grad: 0.1782 (0.1594) time: 0.4753 data: 0.0041 max mem: 22448 +train: [0] [399/400] eta: 0:00:00 lr: 0.000060 loss: 3.0528 (3.1217) grad: 0.1795 (0.1605) time: 0.4667 data: 0.0043 max mem: 22448 +train: [0] Total time: 0:03:13 (0.4841 s / it) +train: [0] Summary: lr: 0.000060 loss: 3.0528 (3.1217) grad: 0.1795 (0.1605) +eval (validation): [0] [ 0/85] eta: 0:05:20 time: 3.7717 data: 3.4539 max mem: 22448 +eval (validation): [0] [20/85] eta: 0:00:35 time: 0.3792 data: 0.0042 max mem: 22448 +eval (validation): [0] [40/85] eta: 0:00:20 time: 0.3746 data: 0.0044 max mem: 22448 +eval (validation): [0] [60/85] eta: 0:00:10 time: 0.3924 data: 0.0044 max mem: 22448 +eval (validation): [0] [80/85] eta: 0:00:02 time: 0.3485 data: 0.0037 max mem: 22448 +eval (validation): [0] [84/85] eta: 0:00:00 time: 0.3325 data: 0.0039 max mem: 22448 +eval (validation): [0] Total time: 0:00:35 (0.4147 s / it) +cv: [0] best hparam: (31, 1.0) (045) ('045_lr3.1e+01_wd1.0e+00') loss: 2.582 acc: 0.240 f1: 0.171 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/eval_v2/nsd_cococlip__patch__attn/checkpoint-best.pth +train: [1] [ 0/400] eta: 0:24:06 lr: nan time: 3.6163 data: 3.1917 max mem: 22448 +train: [1] [ 20/400] eta: 0:04:06 lr: 0.000063 loss: 3.0035 (3.0091) grad: 0.1746 (0.1708) time: 0.4998 data: 0.0033 max mem: 22448 +train: [1] [ 40/400] eta: 0:03:27 lr: 0.000066 loss: 3.0040 (3.0068) grad: 0.1659 (0.1663) time: 0.5021 data: 0.0043 max mem: 22448 +train: [1] [ 60/400] eta: 0:03:03 lr: 0.000069 loss: 2.9934 (2.9950) grad: 0.1618 (0.1680) time: 0.4626 data: 0.0042 max mem: 22448 +train: [1] [ 80/400] eta: 0:02:47 lr: 0.000072 loss: 2.9846 (2.9953) grad: 0.1728 (0.1714) time: 0.4764 data: 0.0041 max mem: 22448 +train: [1] [100/400] eta: 0:02:34 lr: 0.000075 loss: 2.9915 (2.9899) grad: 0.1749 (0.1738) time: 0.4716 data: 0.0041 max mem: 22448 +train: [1] [120/400] eta: 0:02:21 lr: 0.000078 loss: 2.9776 (2.9873) grad: 0.1874 (0.1756) time: 0.4701 data: 0.0044 max mem: 22448 +train: [1] [140/400] eta: 0:02:10 lr: 0.000081 loss: 2.9675 (2.9862) grad: 0.1855 (0.1768) time: 0.4752 data: 0.0042 max mem: 22448 +train: [1] [160/400] eta: 0:01:59 lr: 0.000084 loss: 2.9683 (2.9873) grad: 0.1816 (0.1771) time: 0.4737 data: 0.0041 max mem: 22448 +train: [1] [180/400] eta: 0:01:48 lr: 0.000087 loss: 2.9933 (2.9866) grad: 0.1744 (0.1776) time: 0.4634 data: 0.0041 max mem: 22448 +train: [1] [200/400] eta: 0:01:38 lr: 0.000090 loss: 2.9485 (2.9834) grad: 0.1767 (0.1784) time: 0.4691 data: 0.0042 max mem: 22448 +train: [1] [220/400] eta: 0:01:28 lr: 0.000093 loss: 2.9161 (2.9763) grad: 0.1916 (0.1802) time: 0.4747 data: 0.0043 max mem: 22448 +train: [1] [240/400] eta: 0:01:18 lr: 0.000096 loss: 2.9159 (2.9730) grad: 0.1916 (0.1806) time: 0.4608 data: 0.0042 max mem: 22448 +train: [1] [260/400] eta: 0:01:08 lr: 0.000099 loss: 2.9377 (2.9714) grad: 0.1873 (0.1814) time: 0.4591 data: 0.0043 max mem: 22448 +train: [1] [280/400] eta: 0:00:58 lr: 0.000102 loss: 2.9265 (2.9675) grad: 0.1811 (0.1814) time: 0.4733 data: 0.0041 max mem: 22448 +train: [1] [300/400] eta: 0:00:48 lr: 0.000105 loss: 2.9265 (2.9666) grad: 0.1814 (0.1819) time: 0.4725 data: 0.0042 max mem: 22448 +train: [1] [320/400] eta: 0:00:38 lr: 0.000108 loss: 2.9082 (2.9625) grad: 0.1916 (0.1828) time: 0.4805 data: 0.0043 max mem: 22448 +train: [1] [340/400] eta: 0:00:28 lr: 0.000111 loss: 2.8761 (2.9578) grad: 0.1934 (0.1834) time: 0.4717 data: 0.0042 max mem: 22448 +train: [1] [360/400] eta: 0:00:19 lr: 0.000114 loss: 2.8761 (2.9561) grad: 0.1869 (0.1840) time: 0.4693 data: 0.0042 max mem: 22448 +train: [1] [380/400] eta: 0:00:09 lr: 0.000117 loss: 2.8979 (2.9528) grad: 0.1890 (0.1850) time: 0.4679 data: 0.0041 max mem: 22448 +train: [1] [399/400] eta: 0:00:00 lr: 0.000120 loss: 2.8968 (2.9513) grad: 0.2067 (0.1866) time: 0.4679 data: 0.0041 max mem: 22448 +train: [1] Total time: 0:03:12 (0.4812 s / it) +train: [1] Summary: lr: 0.000120 loss: 2.8968 (2.9513) grad: 0.2067 (0.1866) +eval (validation): [1] [ 0/85] eta: 0:04:22 time: 3.0837 data: 2.8535 max mem: 22448 +eval (validation): [1] [20/85] eta: 0:00:30 time: 0.3364 data: 0.0041 max mem: 22448 +eval (validation): [1] [40/85] eta: 0:00:18 time: 0.3528 data: 0.0037 max mem: 22448 +eval (validation): [1] [60/85] eta: 0:00:09 time: 0.3447 data: 0.0041 max mem: 22448 +eval (validation): [1] [80/85] eta: 0:00:01 time: 0.3300 data: 0.0041 max mem: 22448 +eval (validation): [1] [84/85] eta: 0:00:00 time: 0.3238 data: 0.0040 max mem: 22448 +eval (validation): [1] Total time: 0:00:31 (0.3753 s / it) +cv: [1] best hparam: (12, 1.0) (039) ('039_lr1.2e+01_wd1.0e+00') loss: 2.479 acc: 0.255 f1: 0.184 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/eval_v2/nsd_cococlip__patch__attn/checkpoint-best.pth +train: [2] [ 0/400] eta: 0:23:19 lr: nan time: 3.4990 data: 3.0768 max mem: 22448 +train: [2] [ 20/400] eta: 0:04:04 lr: 0.000123 loss: 2.9099 (2.9065) grad: 0.2707 (0.2666) time: 0.4993 data: 0.0050 max mem: 22448 +train: [2] [ 40/400] eta: 0:03:21 lr: 0.000126 loss: 2.9557 (2.9524) grad: 0.2869 (0.3689) time: 0.4727 data: 0.0040 max mem: 22448 +train: [2] [ 60/400] eta: 0:03:00 lr: 0.000129 loss: 3.0959 (3.0673) grad: 0.5490 (0.5522) time: 0.4740 data: 0.0043 max mem: 22448 +train: [2] [ 80/400] eta: 0:02:45 lr: 0.000132 loss: 3.4633 (3.2209) grad: 1.1470 (0.7889) time: 0.4753 data: 0.0043 max mem: 22448 +train: [2] [100/400] eta: 0:02:32 lr: 0.000135 loss: 3.6564 (3.3030) grad: 1.4453 (0.9185) time: 0.4704 data: 0.0042 max mem: 22448 +WARNING: classifier 48 (50, 1.0) diverged (loss=72.32 > 63.56) at step 451. Freezing. +train: [2] [120/400] eta: 0:02:20 lr: 0.000138 loss: 3.4358 (3.2499) grad: 0.8098 (0.8313) time: 0.4639 data: 0.0041 max mem: 22448 +train: [2] [140/400] eta: 0:02:09 lr: 0.000141 loss: 2.8897 (3.1996) grad: 0.2084 (0.7434) time: 0.4721 data: 0.0041 max mem: 22448 +train: [2] [160/400] eta: 0:01:58 lr: 0.000144 loss: 2.8484 (3.1530) grad: 0.2136 (0.6774) time: 0.4660 data: 0.0040 max mem: 22448 +train: [2] [180/400] eta: 0:01:48 lr: 0.000147 loss: 2.8104 (3.1139) grad: 0.2136 (0.6258) time: 0.4743 data: 0.0043 max mem: 22448 +train: [2] [200/400] eta: 0:01:37 lr: 0.000150 loss: 2.8222 (3.0853) grad: 0.2129 (0.5846) time: 0.4657 data: 0.0042 max mem: 22448 +train: [2] [220/400] eta: 0:01:27 lr: 0.000153 loss: 2.8507 (3.0643) grad: 0.2211 (0.5530) time: 0.4650 data: 0.0043 max mem: 22448 +train: [2] [240/400] eta: 0:01:17 lr: 0.000156 loss: 2.8586 (3.0478) grad: 0.2261 (0.5259) time: 0.4547 data: 0.0041 max mem: 22448 +train: [2] [260/400] eta: 0:01:07 lr: 0.000159 loss: 2.8586 (3.0313) grad: 0.2238 (0.5029) time: 0.4580 data: 0.0042 max mem: 22448 +train: [2] [280/400] eta: 0:00:57 lr: 0.000162 loss: 2.8280 (3.0185) grad: 0.2487 (0.4875) time: 0.4631 data: 0.0043 max mem: 22448 +train: [2] [300/400] eta: 0:00:47 lr: 0.000165 loss: 2.8888 (3.0246) grad: 0.3521 (0.5102) time: 0.4740 data: 0.0042 max mem: 22448 +WARNING: classifier 47 (43, 1.0) diverged (loss=63.90 > 63.56) at step 555. Freezing. +train: [2] [320/400] eta: 0:00:38 lr: 0.000168 loss: 3.0520 (3.0375) grad: 0.8193 (0.5288) time: 0.4699 data: 0.0040 max mem: 22448 +train: [2] [340/400] eta: 0:00:28 lr: 0.000171 loss: 2.8585 (3.0263) grad: 0.2258 (0.5110) time: 0.4714 data: 0.0042 max mem: 22448 +train: [2] [360/400] eta: 0:00:19 lr: 0.000174 loss: 2.8211 (3.0155) grad: 0.2199 (0.4951) time: 0.4750 data: 0.0041 max mem: 22448 +train: [2] [380/400] eta: 0:00:09 lr: 0.000177 loss: 2.8265 (3.0059) grad: 0.2283 (0.4813) time: 0.4656 data: 0.0042 max mem: 22448 +train: [2] [399/400] eta: 0:00:00 lr: 0.000180 loss: 2.8255 (2.9966) grad: 0.2328 (0.4692) time: 0.4649 data: 0.0041 max mem: 22448 +train: [2] Total time: 0:03:11 (0.4776 s / it) +train: [2] Summary: lr: 0.000180 loss: 2.8255 (2.9966) grad: 0.2328 (0.4692) +eval (validation): [2] [ 0/85] eta: 0:04:25 time: 3.1267 data: 2.8569 max mem: 22448 +eval (validation): [2] [20/85] eta: 0:00:31 time: 0.3544 data: 0.0050 max mem: 22448 +eval (validation): [2] [40/85] eta: 0:00:19 time: 0.3754 data: 0.0041 max mem: 22448 +eval (validation): [2] [60/85] eta: 0:00:10 time: 0.3687 data: 0.0046 max mem: 22448 +eval (validation): [2] [80/85] eta: 0:00:01 time: 0.3511 data: 0.0042 max mem: 22448 +eval (validation): [2] [84/85] eta: 0:00:00 time: 0.3492 data: 0.0040 max mem: 22448 +eval (validation): [2] Total time: 0:00:33 (0.3978 s / it) +cv: [2] best hparam: (3.1, 1.0) (031) ('031_lr3.1e+00_wd1.0e+00') loss: 2.426 acc: 0.269 f1: 0.201 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/eval_v2/nsd_cococlip__patch__attn/checkpoint-best.pth +train: [3] [ 0/400] eta: 0:22:56 lr: nan time: 3.4412 data: 3.0296 max mem: 22448 +train: [3] [ 20/400] eta: 0:03:56 lr: 0.000183 loss: 2.7943 (2.8155) grad: 0.2500 (0.2738) time: 0.4819 data: 0.0050 max mem: 22448 +train: [3] [ 40/400] eta: 0:03:17 lr: 0.000186 loss: 2.8774 (2.9264) grad: 0.3344 (0.4541) time: 0.4711 data: 0.0037 max mem: 22448 +WARNING: classifier 46 (36, 1.0) diverged (loss=64.73 > 63.56) at step 628. Freezing. +train: [3] [ 60/400] eta: 0:02:58 lr: 0.000189 loss: 3.0357 (3.0661) grad: 0.7436 (0.6873) time: 0.4756 data: 0.0042 max mem: 22448 +train: [3] [ 80/400] eta: 0:02:43 lr: 0.000192 loss: 2.9247 (3.0182) grad: 0.5498 (0.6229) time: 0.4706 data: 0.0042 max mem: 22448 +train: [3] [100/400] eta: 0:02:30 lr: 0.000195 loss: 2.9839 (3.0733) grad: 0.7137 (0.7129) time: 0.4642 data: 0.0042 max mem: 22448 +WARNING: classifier 45 (31, 1.0) diverged (loss=79.86 > 63.56) at step 656. Freezing. +train: [3] [120/400] eta: 0:02:18 lr: 0.000198 loss: 3.2492 (3.1269) grad: 0.9832 (0.7680) time: 0.4632 data: 0.0042 max mem: 22448 +train: [3] [140/400] eta: 0:02:07 lr: 0.000201 loss: 2.8223 (3.0809) grad: 0.2365 (0.6907) time: 0.4575 data: 0.0042 max mem: 22448 +train: [3] [160/400] eta: 0:01:56 lr: 0.000204 loss: 2.8097 (3.0509) grad: 0.2221 (0.6322) time: 0.4607 data: 0.0043 max mem: 22448 +train: [3] [180/400] eta: 0:01:46 lr: 0.000207 loss: 2.8065 (3.0202) grad: 0.2186 (0.5862) time: 0.4728 data: 0.0043 max mem: 22448 +train: [3] [200/400] eta: 0:01:36 lr: 0.000210 loss: 2.7914 (2.9996) grad: 0.2152 (0.5496) time: 0.4670 data: 0.0043 max mem: 22448 +train: [3] [220/400] eta: 0:01:26 lr: 0.000213 loss: 2.7960 (2.9800) grad: 0.2242 (0.5201) time: 0.4652 data: 0.0044 max mem: 22448 +train: [3] [240/400] eta: 0:01:16 lr: 0.000216 loss: 2.7968 (2.9634) grad: 0.2297 (0.4962) time: 0.4486 data: 0.0040 max mem: 22448 +train: [3] [260/400] eta: 0:01:06 lr: 0.000219 loss: 2.7968 (2.9496) grad: 0.2367 (0.4767) time: 0.4548 data: 0.0040 max mem: 22448 +train: [3] [280/400] eta: 0:00:57 lr: 0.000222 loss: 2.7868 (2.9369) grad: 0.2286 (0.4592) time: 0.4556 data: 0.0041 max mem: 22448 +train: [3] [300/400] eta: 0:00:47 lr: 0.000225 loss: 2.8040 (2.9292) grad: 0.2482 (0.4472) time: 0.4627 data: 0.0043 max mem: 22448 +train: [3] [320/400] eta: 0:00:37 lr: 0.000228 loss: 2.8578 (2.9341) grad: 0.3187 (0.4705) time: 0.4672 data: 0.0042 max mem: 22448 +WARNING: classifier 44 (26, 1.0) diverged (loss=96.08 > 63.56) at step 765. Freezing. +train: [3] [340/400] eta: 0:00:28 lr: 0.000231 loss: 3.0137 (2.9568) grad: 0.7303 (0.5019) time: 0.4754 data: 0.0042 max mem: 22448 +train: [3] [360/400] eta: 0:00:18 lr: 0.000234 loss: 2.8229 (2.9494) grad: 0.2300 (0.4865) time: 0.4585 data: 0.0041 max mem: 22448 +train: [3] [380/400] eta: 0:00:09 lr: 0.000237 loss: 2.7920 (2.9401) grad: 0.2269 (0.4728) time: 0.4767 data: 0.0043 max mem: 22448 +train: [3] [399/400] eta: 0:00:00 lr: 0.000240 loss: 2.7410 (2.9300) grad: 0.2203 (0.4598) time: 0.4520 data: 0.0041 max mem: 22448 +train: [3] Total time: 0:03:09 (0.4728 s / it) +train: [3] Summary: lr: 0.000240 loss: 2.7410 (2.9300) grad: 0.2203 (0.4598) +eval (validation): [3] [ 0/85] eta: 0:04:40 time: 3.3008 data: 3.0038 max mem: 22448 +eval (validation): [3] [20/85] eta: 0:00:34 time: 0.3997 data: 0.0044 max mem: 22448 +eval (validation): [3] [40/85] eta: 0:00:20 time: 0.3491 data: 0.0043 max mem: 22448 +eval (validation): [3] [60/85] eta: 0:00:10 time: 0.3579 data: 0.0045 max mem: 22448 +eval (validation): [3] [80/85] eta: 0:00:01 time: 0.3460 data: 0.0044 max mem: 22448 +eval (validation): [3] [84/85] eta: 0:00:00 time: 0.3399 data: 0.0043 max mem: 22448 +eval (validation): [3] Total time: 0:00:33 (0.3995 s / it) +cv: [3] best hparam: (4.3, 1.0) (033) ('033_lr4.3e+00_wd1.0e+00') loss: 2.443 acc: 0.270 f1: 0.194 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/eval_v2/nsd_cococlip__patch__attn/checkpoint-best.pth +train: [4] [ 0/400] eta: 0:23:06 lr: nan time: 3.4673 data: 3.0581 max mem: 22448 +train: [4] [ 20/400] eta: 0:04:00 lr: 0.000243 loss: 2.6842 (2.7171) grad: 0.2200 (0.2206) time: 0.4905 data: 0.0041 max mem: 22448 +train: [4] [ 40/400] eta: 0:03:13 lr: 0.000246 loss: 2.7225 (2.7283) grad: 0.2224 (0.2212) time: 0.4373 data: 0.0042 max mem: 22448 +train: [4] [ 60/400] eta: 0:02:53 lr: 0.000249 loss: 2.7225 (2.7277) grad: 0.2224 (0.2218) time: 0.4509 data: 0.0041 max mem: 22448 +train: [4] [ 80/400] eta: 0:02:38 lr: 0.000252 loss: 2.7133 (2.7294) grad: 0.2171 (0.2202) time: 0.4491 data: 0.0043 max mem: 22448 +train: [4] [100/400] eta: 0:02:26 lr: 0.000255 loss: 2.7701 (2.7427) grad: 0.2237 (0.2229) time: 0.4630 data: 0.0042 max mem: 22448 +train: [4] [120/400] eta: 0:02:15 lr: 0.000258 loss: 2.7571 (2.7383) grad: 0.2358 (0.2276) time: 0.4581 data: 0.0040 max mem: 22448 +train: [4] [140/400] eta: 0:02:04 lr: 0.000261 loss: 2.7442 (2.7431) grad: 0.2767 (0.2410) time: 0.4619 data: 0.0040 max mem: 22448 +train: [4] [160/400] eta: 0:01:54 lr: 0.000264 loss: 2.8246 (2.7782) grad: 0.4227 (0.3039) time: 0.4651 data: 0.0041 max mem: 22448 +WARNING: classifier 43 (22, 1.0) diverged (loss=76.77 > 63.56) at step 888. Freezing. +train: [4] [180/400] eta: 0:01:44 lr: 0.000267 loss: 3.0364 (2.8413) grad: 0.8480 (0.3859) time: 0.4565 data: 0.0041 max mem: 22448 +train: [4] [200/400] eta: 0:01:34 lr: 0.000270 loss: 2.7761 (2.8282) grad: 0.2261 (0.3692) time: 0.4594 data: 0.0041 max mem: 22448 +train: [4] [220/400] eta: 0:01:24 lr: 0.000273 loss: 2.7259 (2.8218) grad: 0.2241 (0.3568) time: 0.4494 data: 0.0041 max mem: 22448 +train: [4] [240/400] eta: 0:01:15 lr: 0.000276 loss: 2.7294 (2.8155) grad: 0.2270 (0.3463) time: 0.4499 data: 0.0042 max mem: 22448 +train: [4] [260/400] eta: 0:01:05 lr: 0.000279 loss: 2.7772 (2.8122) grad: 0.2253 (0.3372) time: 0.4550 data: 0.0041 max mem: 22448 +train: [4] [280/400] eta: 0:00:56 lr: 0.000282 loss: 2.7772 (2.8076) grad: 0.2239 (0.3299) time: 0.4589 data: 0.0041 max mem: 22448 +train: [4] [300/400] eta: 0:00:46 lr: 0.000285 loss: 2.7516 (2.8034) grad: 0.2241 (0.3229) time: 0.4636 data: 0.0042 max mem: 22448 +train: [4] [320/400] eta: 0:00:37 lr: 0.000288 loss: 2.7496 (2.7987) grad: 0.2118 (0.3159) time: 0.4539 data: 0.0042 max mem: 22448 +train: [4] [340/400] eta: 0:00:27 lr: 0.000291 loss: 2.7222 (2.7949) grad: 0.2081 (0.3102) time: 0.4540 data: 0.0042 max mem: 22448 +train: [4] [360/400] eta: 0:00:18 lr: 0.000294 loss: 2.7222 (2.7933) grad: 0.2218 (0.3057) time: 0.4512 data: 0.0044 max mem: 22448 +train: [4] [380/400] eta: 0:00:09 lr: 0.000297 loss: 2.7240 (2.7891) grad: 0.2283 (0.3016) time: 0.4506 data: 0.0044 max mem: 22448 +train: [4] [399/400] eta: 0:00:00 lr: 0.000300 loss: 2.7257 (2.7858) grad: 0.2278 (0.2979) time: 0.4398 data: 0.0041 max mem: 22448 +train: [4] Total time: 0:03:05 (0.4637 s / it) +train: [4] Summary: lr: 0.000300 loss: 2.7257 (2.7858) grad: 0.2278 (0.2979) +eval (validation): [4] [ 0/85] eta: 0:04:40 time: 3.3005 data: 3.0115 max mem: 22448 +eval (validation): [4] [20/85] eta: 0:00:32 time: 0.3672 data: 0.0052 max mem: 22448 +eval (validation): [4] [40/85] eta: 0:00:19 time: 0.3538 data: 0.0036 max mem: 22448 +eval (validation): [4] [60/85] eta: 0:00:10 time: 0.3481 data: 0.0042 max mem: 22448 +eval (validation): [4] [80/85] eta: 0:00:01 time: 0.3456 data: 0.0043 max mem: 22448 +eval (validation): [4] [84/85] eta: 0:00:00 time: 0.3429 data: 0.0042 max mem: 22448 +eval (validation): [4] Total time: 0:00:33 (0.3902 s / it) +cv: [4] best hparam: (1, 1.0) (024) ('024_lr1.0e+00_wd1.0e+00') loss: 2.432 acc: 0.272 f1: 0.208 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/eval_v2/nsd_cococlip__patch__attn/checkpoint-best.pth +train: [5] [ 0/400] eta: 0:22:33 lr: nan time: 3.3842 data: 3.0264 max mem: 22448 +train: [5] [ 20/400] eta: 0:03:46 lr: 0.000300 loss: 2.6178 (2.6094) grad: 0.2279 (0.2300) time: 0.4568 data: 0.0034 max mem: 22448 +train: [5] [ 40/400] eta: 0:03:07 lr: 0.000300 loss: 2.6385 (2.6621) grad: 0.2278 (0.2335) time: 0.4426 data: 0.0038 max mem: 22448 +train: [5] [ 60/400] eta: 0:02:49 lr: 0.000300 loss: 2.6880 (2.6743) grad: 0.2362 (0.2357) time: 0.4488 data: 0.0044 max mem: 22448 +train: [5] [ 80/400] eta: 0:02:35 lr: 0.000300 loss: 2.7012 (2.6738) grad: 0.2303 (0.2344) time: 0.4544 data: 0.0043 max mem: 22448 +train: [5] [100/400] eta: 0:02:23 lr: 0.000300 loss: 2.6833 (2.6792) grad: 0.2347 (0.2373) time: 0.4514 data: 0.0041 max mem: 22448 +train: [5] [120/400] eta: 0:02:13 lr: 0.000300 loss: 2.6448 (2.6705) grad: 0.2376 (0.2363) time: 0.4539 data: 0.0043 max mem: 22448 +train: [5] [140/400] eta: 0:02:03 lr: 0.000300 loss: 2.6152 (2.6633) grad: 0.2266 (0.2345) time: 0.4609 data: 0.0041 max mem: 22448 +train: [5] [160/400] eta: 0:01:52 lr: 0.000299 loss: 2.6280 (2.6636) grad: 0.2218 (0.2341) time: 0.4505 data: 0.0042 max mem: 22448 +train: [5] [180/400] eta: 0:01:43 lr: 0.000299 loss: 2.6844 (2.6675) grad: 0.2292 (0.2336) time: 0.4518 data: 0.0042 max mem: 22448 +train: [5] [200/400] eta: 0:01:33 lr: 0.000299 loss: 2.6774 (2.6657) grad: 0.2318 (0.2334) time: 0.4580 data: 0.0044 max mem: 22448 +train: [5] [220/400] eta: 0:01:23 lr: 0.000299 loss: 2.6196 (2.6650) grad: 0.2332 (0.2327) time: 0.4512 data: 0.0044 max mem: 22448 +train: [5] [240/400] eta: 0:01:14 lr: 0.000299 loss: 2.6309 (2.6649) grad: 0.2360 (0.2334) time: 0.4568 data: 0.0044 max mem: 22448 +train: [5] [260/400] eta: 0:01:05 lr: 0.000299 loss: 2.6361 (2.6622) grad: 0.2353 (0.2329) time: 0.4559 data: 0.0045 max mem: 22448 +train: [5] [280/400] eta: 0:00:55 lr: 0.000298 loss: 2.6405 (2.6637) grad: 0.2353 (0.2334) time: 0.4509 data: 0.0045 max mem: 22448 +train: [5] [300/400] eta: 0:00:46 lr: 0.000298 loss: 2.6585 (2.6594) grad: 0.2327 (0.2331) time: 0.4636 data: 0.0043 max mem: 22448 +train: [5] [320/400] eta: 0:00:36 lr: 0.000298 loss: 2.6394 (2.6604) grad: 0.2336 (0.2337) time: 0.4445 data: 0.0041 max mem: 22448 +train: [5] [340/400] eta: 0:00:27 lr: 0.000298 loss: 2.6524 (2.6591) grad: 0.2381 (0.2337) time: 0.4501 data: 0.0045 max mem: 22448 +train: [5] [360/400] eta: 0:00:18 lr: 0.000297 loss: 2.6484 (2.6584) grad: 0.2379 (0.2338) time: 0.4512 data: 0.0042 max mem: 22448 +train: [5] [380/400] eta: 0:00:09 lr: 0.000297 loss: 2.6287 (2.6587) grad: 0.2345 (0.2339) time: 0.4498 data: 0.0042 max mem: 22448 +train: [5] [399/400] eta: 0:00:00 lr: 0.000297 loss: 2.5702 (2.6556) grad: 0.2280 (0.2334) time: 0.4424 data: 0.0041 max mem: 22448 +train: [5] Total time: 0:03:03 (0.4600 s / it) +train: [5] Summary: lr: 0.000297 loss: 2.5702 (2.6556) grad: 0.2280 (0.2334) +eval (validation): [5] [ 0/85] eta: 0:05:49 time: 4.1063 data: 3.8440 max mem: 22448 +eval (validation): [5] [20/85] eta: 0:00:35 time: 0.3647 data: 0.0038 max mem: 22448 +eval (validation): [5] [40/85] eta: 0:00:20 time: 0.3641 data: 0.0036 max mem: 22448 +eval (validation): [5] [60/85] eta: 0:00:10 time: 0.3616 data: 0.0044 max mem: 22448 +eval (validation): [5] [80/85] eta: 0:00:02 time: 0.3439 data: 0.0042 max mem: 22448 +eval (validation): [5] [84/85] eta: 0:00:00 time: 0.3334 data: 0.0040 max mem: 22448 +eval (validation): [5] Total time: 0:00:34 (0.4046 s / it) +cv: [5] best hparam: (1, 1.0) (024) ('024_lr1.0e+00_wd1.0e+00') loss: 2.367 acc: 0.285 f1: 0.214 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/eval_v2/nsd_cococlip__patch__attn/checkpoint-best.pth +train: [6] [ 0/400] eta: 0:22:10 lr: nan time: 3.3256 data: 2.9806 max mem: 22448 +train: [6] [ 20/400] eta: 0:03:46 lr: 0.000296 loss: 2.5964 (2.5787) grad: 0.2272 (0.2290) time: 0.4593 data: 0.0053 max mem: 22448 +train: [6] [ 40/400] eta: 0:03:07 lr: 0.000296 loss: 2.5964 (2.5936) grad: 0.2287 (0.2320) time: 0.4418 data: 0.0040 max mem: 22448 +train: [6] [ 60/400] eta: 0:02:49 lr: 0.000296 loss: 2.5711 (2.5891) grad: 0.2298 (0.2350) time: 0.4491 data: 0.0042 max mem: 22448 +train: [6] [ 80/400] eta: 0:02:35 lr: 0.000295 loss: 2.5533 (2.5796) grad: 0.2368 (0.2367) time: 0.4482 data: 0.0042 max mem: 22448 +train: [6] [100/400] eta: 0:02:23 lr: 0.000295 loss: 2.5940 (2.5814) grad: 0.2414 (0.2374) time: 0.4500 data: 0.0044 max mem: 22448 +train: [6] [120/400] eta: 0:02:13 lr: 0.000295 loss: 2.5940 (2.5831) grad: 0.2420 (0.2386) time: 0.4592 data: 0.0042 max mem: 22448 +train: [6] [140/400] eta: 0:02:02 lr: 0.000294 loss: 2.6014 (2.5896) grad: 0.2427 (0.2395) time: 0.4459 data: 0.0044 max mem: 22448 +train: [6] [160/400] eta: 0:01:52 lr: 0.000294 loss: 2.6385 (2.5951) grad: 0.2427 (0.2397) time: 0.4460 data: 0.0044 max mem: 22448 +train: [6] [180/400] eta: 0:01:42 lr: 0.000293 loss: 2.5999 (2.5951) grad: 0.2463 (0.2409) time: 0.4471 data: 0.0041 max mem: 22448 +train: [6] [200/400] eta: 0:01:32 lr: 0.000293 loss: 2.6106 (2.5960) grad: 0.2484 (0.2415) time: 0.4464 data: 0.0041 max mem: 22448 +train: [6] [220/400] eta: 0:01:23 lr: 0.000292 loss: 2.6106 (2.5940) grad: 0.2476 (0.2425) time: 0.4426 data: 0.0042 max mem: 22448 +train: [6] [240/400] eta: 0:01:13 lr: 0.000292 loss: 2.5964 (2.5958) grad: 0.2485 (0.2432) time: 0.4505 data: 0.0044 max mem: 22448 +train: [6] [260/400] eta: 0:01:04 lr: 0.000291 loss: 2.5837 (2.5922) grad: 0.2456 (0.2428) time: 0.4566 data: 0.0042 max mem: 22448 +train: [6] [280/400] eta: 0:00:55 lr: 0.000291 loss: 2.5719 (2.5927) grad: 0.2369 (0.2430) time: 0.4467 data: 0.0041 max mem: 22448 +train: [6] [300/400] eta: 0:00:45 lr: 0.000290 loss: 2.6202 (2.5934) grad: 0.2374 (0.2431) time: 0.4521 data: 0.0041 max mem: 22448 +train: [6] [320/400] eta: 0:00:36 lr: 0.000290 loss: 2.6221 (2.5946) grad: 0.2423 (0.2434) time: 0.4404 data: 0.0040 max mem: 22448 +train: [6] [340/400] eta: 0:00:27 lr: 0.000289 loss: 2.6179 (2.5962) grad: 0.2450 (0.2435) time: 0.4721 data: 0.0044 max mem: 22448 +train: [6] [360/400] eta: 0:00:18 lr: 0.000288 loss: 2.5746 (2.5937) grad: 0.2418 (0.2435) time: 0.4516 data: 0.0045 max mem: 22448 +train: [6] [380/400] eta: 0:00:09 lr: 0.000288 loss: 2.5548 (2.5948) grad: 0.2406 (0.2436) time: 0.4438 data: 0.0043 max mem: 22448 +train: [6] [399/400] eta: 0:00:00 lr: 0.000287 loss: 2.6097 (2.5950) grad: 0.2388 (0.2434) time: 0.4446 data: 0.0044 max mem: 22448 +train: [6] Total time: 0:03:02 (0.4572 s / it) +train: [6] Summary: lr: 0.000287 loss: 2.6097 (2.5950) grad: 0.2388 (0.2434) +eval (validation): [6] [ 0/85] eta: 0:04:48 time: 3.3955 data: 3.0778 max mem: 22448 +eval (validation): [6] [20/85] eta: 0:00:33 time: 0.3763 data: 0.0030 max mem: 22448 +eval (validation): [6] [40/85] eta: 0:00:19 time: 0.3503 data: 0.0041 max mem: 22448 +eval (validation): [6] [60/85] eta: 0:00:10 time: 0.3527 data: 0.0043 max mem: 22448 +eval (validation): [6] [80/85] eta: 0:00:01 time: 0.3595 data: 0.0041 max mem: 22448 +eval (validation): [6] [84/85] eta: 0:00:00 time: 0.3539 data: 0.0041 max mem: 22448 +eval (validation): [6] Total time: 0:00:33 (0.3976 s / it) +cv: [6] best hparam: (0.61, 1.0) (021) ('021_lr6.1e-01_wd1.0e+00') loss: 2.414 acc: 0.276 f1: 0.216 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [7] [ 0/400] eta: 0:22:28 lr: nan time: 3.3720 data: 3.0235 max mem: 22448 +train: [7] [ 20/400] eta: 0:03:50 lr: 0.000286 loss: 2.5080 (2.5203) grad: 0.2379 (0.2429) time: 0.4694 data: 0.0041 max mem: 22448 +train: [7] [ 40/400] eta: 0:03:10 lr: 0.000286 loss: 2.5107 (2.5185) grad: 0.2401 (0.2450) time: 0.4495 data: 0.0042 max mem: 22448 +train: [7] [ 60/400] eta: 0:02:51 lr: 0.000285 loss: 2.5107 (2.5093) grad: 0.2459 (0.2465) time: 0.4534 data: 0.0044 max mem: 22448 +train: [7] [ 80/400] eta: 0:02:37 lr: 0.000284 loss: 2.5045 (2.5174) grad: 0.2440 (0.2443) time: 0.4566 data: 0.0042 max mem: 22448 +train: [7] [100/400] eta: 0:02:24 lr: 0.000284 loss: 2.4895 (2.5090) grad: 0.2410 (0.2436) time: 0.4420 data: 0.0041 max mem: 22448 +train: [7] [120/400] eta: 0:02:13 lr: 0.000283 loss: 2.4877 (2.5082) grad: 0.2462 (0.2446) time: 0.4430 data: 0.0041 max mem: 22448 +train: [7] [140/400] eta: 0:02:02 lr: 0.000282 loss: 2.5067 (2.5106) grad: 0.2446 (0.2445) time: 0.4507 data: 0.0043 max mem: 22448 +train: [7] [160/400] eta: 0:01:52 lr: 0.000282 loss: 2.5241 (2.5123) grad: 0.2439 (0.2444) time: 0.4469 data: 0.0045 max mem: 22448 +train: [7] [180/400] eta: 0:01:42 lr: 0.000281 loss: 2.5663 (2.5201) grad: 0.2473 (0.2458) time: 0.4486 data: 0.0042 max mem: 22448 +train: [7] [200/400] eta: 0:01:33 lr: 0.000280 loss: 2.5689 (2.5202) grad: 0.2474 (0.2455) time: 0.4511 data: 0.0041 max mem: 22448 +train: [7] [220/400] eta: 0:01:23 lr: 0.000279 loss: 2.5252 (2.5184) grad: 0.2440 (0.2455) time: 0.4513 data: 0.0041 max mem: 22448 +train: [7] [240/400] eta: 0:01:14 lr: 0.000278 loss: 2.5340 (2.5215) grad: 0.2455 (0.2458) time: 0.4474 data: 0.0043 max mem: 22448 +train: [7] [260/400] eta: 0:01:04 lr: 0.000278 loss: 2.5322 (2.5203) grad: 0.2437 (0.2450) time: 0.4565 data: 0.0041 max mem: 22448 +train: [7] [280/400] eta: 0:00:55 lr: 0.000277 loss: 2.5019 (2.5177) grad: 0.2353 (0.2447) time: 0.4703 data: 0.0042 max mem: 22448 +train: [7] [300/400] eta: 0:00:46 lr: 0.000276 loss: 2.4443 (2.5161) grad: 0.2400 (0.2449) time: 0.4506 data: 0.0043 max mem: 22448 +train: [7] [320/400] eta: 0:00:36 lr: 0.000275 loss: 2.5060 (2.5171) grad: 0.2482 (0.2448) time: 0.4533 data: 0.0043 max mem: 22448 +train: [7] [340/400] eta: 0:00:27 lr: 0.000274 loss: 2.4859 (2.5151) grad: 0.2442 (0.2445) time: 0.4589 data: 0.0042 max mem: 22448 +train: [7] [360/400] eta: 0:00:18 lr: 0.000273 loss: 2.4880 (2.5153) grad: 0.2442 (0.2445) time: 0.4482 data: 0.0042 max mem: 22448 +train: [7] [380/400] eta: 0:00:09 lr: 0.000272 loss: 2.4953 (2.5145) grad: 0.2395 (0.2448) time: 0.4474 data: 0.0042 max mem: 22448 +train: [7] [399/400] eta: 0:00:00 lr: 0.000271 loss: 2.5251 (2.5161) grad: 0.2462 (0.2454) time: 0.4495 data: 0.0042 max mem: 22448 +train: [7] Total time: 0:03:03 (0.4597 s / it) +train: [7] Summary: lr: 0.000271 loss: 2.5251 (2.5161) grad: 0.2462 (0.2454) +eval (validation): [7] [ 0/85] eta: 0:04:46 time: 3.3713 data: 3.0435 max mem: 22448 +eval (validation): [7] [20/85] eta: 0:00:34 time: 0.3959 data: 0.0044 max mem: 22448 +eval (validation): [7] [40/85] eta: 0:00:19 time: 0.3450 data: 0.0043 max mem: 22448 +eval (validation): [7] [60/85] eta: 0:00:10 time: 0.3448 data: 0.0043 max mem: 22448 +eval (validation): [7] [80/85] eta: 0:00:01 time: 0.3453 data: 0.0040 max mem: 22448 +eval (validation): [7] [84/85] eta: 0:00:00 time: 0.3370 data: 0.0039 max mem: 22448 +eval (validation): [7] Total time: 0:00:33 (0.3954 s / it) +cv: [7] best hparam: (0.52, 1.0) (020) ('020_lr5.2e-01_wd1.0e+00') loss: 2.399 acc: 0.279 f1: 0.219 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [8] [ 0/400] eta: 0:22:49 lr: nan time: 3.4237 data: 3.0153 max mem: 22448 +train: [8] [ 20/400] eta: 0:03:51 lr: 0.000270 loss: 2.3871 (2.4055) grad: 0.2327 (0.2340) time: 0.4678 data: 0.0046 max mem: 22448 +train: [8] [ 40/400] eta: 0:03:11 lr: 0.000270 loss: 2.4076 (2.4208) grad: 0.2362 (0.2388) time: 0.4509 data: 0.0040 max mem: 22448 +train: [8] [ 60/400] eta: 0:02:52 lr: 0.000269 loss: 2.4530 (2.4313) grad: 0.2422 (0.2397) time: 0.4614 data: 0.0043 max mem: 22448 +train: [8] [ 80/400] eta: 0:02:38 lr: 0.000268 loss: 2.4705 (2.4407) grad: 0.2443 (0.2425) time: 0.4571 data: 0.0042 max mem: 22448 +train: [8] [100/400] eta: 0:02:25 lr: 0.000267 loss: 2.4705 (2.4402) grad: 0.2566 (0.2468) time: 0.4411 data: 0.0041 max mem: 22448 +train: [8] [120/400] eta: 0:02:14 lr: 0.000266 loss: 2.4586 (2.4412) grad: 0.2668 (0.2500) time: 0.4494 data: 0.0041 max mem: 22448 +train: [8] [140/400] eta: 0:02:03 lr: 0.000265 loss: 2.4524 (2.4443) grad: 0.2641 (0.2510) time: 0.4558 data: 0.0043 max mem: 22448 +train: [8] [160/400] eta: 0:01:53 lr: 0.000264 loss: 2.4524 (2.4471) grad: 0.2645 (0.2542) time: 0.4546 data: 0.0041 max mem: 22448 +train: [8] [180/400] eta: 0:01:43 lr: 0.000263 loss: 2.4436 (2.4427) grad: 0.2589 (0.2540) time: 0.4532 data: 0.0042 max mem: 22448 +train: [8] [200/400] eta: 0:01:33 lr: 0.000262 loss: 2.4136 (2.4454) grad: 0.2528 (0.2542) time: 0.4496 data: 0.0042 max mem: 22448 +train: [8] [220/400] eta: 0:01:24 lr: 0.000260 loss: 2.4727 (2.4480) grad: 0.2546 (0.2541) time: 0.4447 data: 0.0041 max mem: 22448 +train: [8] [240/400] eta: 0:01:14 lr: 0.000259 loss: 2.4679 (2.4470) grad: 0.2530 (0.2542) time: 0.4454 data: 0.0042 max mem: 22448 +train: [8] [260/400] eta: 0:01:04 lr: 0.000258 loss: 2.4831 (2.4507) grad: 0.2520 (0.2546) time: 0.4530 data: 0.0042 max mem: 22448 +train: [8] [280/400] eta: 0:00:55 lr: 0.000257 loss: 2.4621 (2.4508) grad: 0.2494 (0.2550) time: 0.4551 data: 0.0042 max mem: 22448 +train: [8] [300/400] eta: 0:00:46 lr: 0.000256 loss: 2.4526 (2.4515) grad: 0.2523 (0.2553) time: 0.4503 data: 0.0042 max mem: 22448 +train: [8] [320/400] eta: 0:00:36 lr: 0.000255 loss: 2.4514 (2.4513) grad: 0.2503 (0.2545) time: 0.4564 data: 0.0041 max mem: 22448 +train: [8] [340/400] eta: 0:00:27 lr: 0.000254 loss: 2.4254 (2.4505) grad: 0.2488 (0.2551) time: 0.4540 data: 0.0042 max mem: 22448 +train: [8] [360/400] eta: 0:00:18 lr: 0.000253 loss: 2.4235 (2.4507) grad: 0.2522 (0.2548) time: 0.4512 data: 0.0042 max mem: 22448 +train: [8] [380/400] eta: 0:00:09 lr: 0.000252 loss: 2.4831 (2.4514) grad: 0.2479 (0.2545) time: 0.4523 data: 0.0042 max mem: 22448 +train: [8] [399/400] eta: 0:00:00 lr: 0.000250 loss: 2.4831 (2.4516) grad: 0.2536 (0.2550) time: 0.4396 data: 0.0039 max mem: 22448 +train: [8] Total time: 0:03:03 (0.4599 s / it) +train: [8] Summary: lr: 0.000250 loss: 2.4831 (2.4516) grad: 0.2536 (0.2550) +eval (validation): [8] [ 0/85] eta: 0:04:31 time: 3.1984 data: 2.9161 max mem: 22448 +eval (validation): [8] [20/85] eta: 0:00:33 time: 0.3770 data: 0.0045 max mem: 22448 +eval (validation): [8] [40/85] eta: 0:00:19 time: 0.3663 data: 0.0042 max mem: 22448 +eval (validation): [8] [60/85] eta: 0:00:10 time: 0.3570 data: 0.0045 max mem: 22448 +eval (validation): [8] [80/85] eta: 0:00:01 time: 0.3421 data: 0.0039 max mem: 22448 +eval (validation): [8] [84/85] eta: 0:00:00 time: 0.3375 data: 0.0039 max mem: 22448 +eval (validation): [8] Total time: 0:00:33 (0.3956 s / it) +cv: [8] best hparam: (0.38, 1.0) (018) ('018_lr3.8e-01_wd1.0e+00') loss: 2.425 acc: 0.271 f1: 0.212 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [9] [ 0/400] eta: 0:22:56 lr: nan time: 3.4413 data: 3.0751 max mem: 22448 +train: [9] [ 20/400] eta: 0:03:57 lr: 0.000249 loss: 2.3836 (2.3953) grad: 0.2492 (0.2574) time: 0.4853 data: 0.0043 max mem: 22448 +train: [9] [ 40/400] eta: 0:03:15 lr: 0.000248 loss: 2.3940 (2.4005) grad: 0.2483 (0.2534) time: 0.4542 data: 0.0043 max mem: 22448 +train: [9] [ 60/400] eta: 0:02:54 lr: 0.000247 loss: 2.3979 (2.3998) grad: 0.2462 (0.2511) time: 0.4527 data: 0.0043 max mem: 22448 +train: [9] [ 80/400] eta: 0:02:40 lr: 0.000246 loss: 2.4204 (2.4074) grad: 0.2477 (0.2514) time: 0.4628 data: 0.0041 max mem: 22448 +train: [9] [100/400] eta: 0:02:27 lr: 0.000244 loss: 2.3976 (2.4068) grad: 0.2513 (0.2520) time: 0.4502 data: 0.0042 max mem: 22448 +train: [9] [120/400] eta: 0:02:15 lr: 0.000243 loss: 2.3949 (2.4041) grad: 0.2532 (0.2524) time: 0.4447 data: 0.0042 max mem: 22448 +train: [9] [140/400] eta: 0:02:04 lr: 0.000242 loss: 2.3818 (2.4036) grad: 0.2568 (0.2539) time: 0.4465 data: 0.0041 max mem: 22448 +train: [9] [160/400] eta: 0:01:53 lr: 0.000241 loss: 2.4069 (2.4022) grad: 0.2571 (0.2549) time: 0.4485 data: 0.0043 max mem: 22448 +train: [9] [180/400] eta: 0:01:43 lr: 0.000240 loss: 2.3944 (2.4063) grad: 0.2534 (0.2560) time: 0.4472 data: 0.0042 max mem: 22448 +train: [9] [200/400] eta: 0:01:33 lr: 0.000238 loss: 2.3682 (2.4027) grad: 0.2607 (0.2567) time: 0.4464 data: 0.0041 max mem: 22448 +train: [9] [220/400] eta: 0:01:23 lr: 0.000237 loss: 2.3644 (2.3974) grad: 0.2651 (0.2574) time: 0.4422 data: 0.0041 max mem: 22448 +train: [9] [240/400] eta: 0:01:14 lr: 0.000236 loss: 2.3897 (2.4013) grad: 0.2616 (0.2572) time: 0.4454 data: 0.0041 max mem: 22448 +train: [9] [260/400] eta: 0:01:04 lr: 0.000234 loss: 2.4199 (2.4002) grad: 0.2468 (0.2562) time: 0.4485 data: 0.0042 max mem: 22448 +train: [9] [280/400] eta: 0:00:55 lr: 0.000233 loss: 2.3722 (2.3991) grad: 0.2478 (0.2563) time: 0.4503 data: 0.0042 max mem: 22448 +train: [9] [300/400] eta: 0:00:46 lr: 0.000232 loss: 2.4044 (2.4002) grad: 0.2619 (0.2570) time: 0.4467 data: 0.0041 max mem: 22448 +train: [9] [320/400] eta: 0:00:36 lr: 0.000230 loss: 2.4044 (2.4003) grad: 0.2619 (0.2570) time: 0.4474 data: 0.0041 max mem: 22448 +train: [9] [340/400] eta: 0:00:27 lr: 0.000229 loss: 2.3645 (2.3982) grad: 0.2558 (0.2573) time: 0.4612 data: 0.0041 max mem: 22448 +train: [9] [360/400] eta: 0:00:18 lr: 0.000228 loss: 2.4032 (2.4002) grad: 0.2714 (0.2581) time: 0.4445 data: 0.0042 max mem: 22448 +train: [9] [380/400] eta: 0:00:09 lr: 0.000226 loss: 2.3811 (2.3988) grad: 0.2668 (0.2581) time: 0.4414 data: 0.0040 max mem: 22448 +train: [9] [399/400] eta: 0:00:00 lr: 0.000225 loss: 2.3855 (2.3991) grad: 0.2582 (0.2583) time: 0.4330 data: 0.0038 max mem: 22448 +train: [9] Total time: 0:03:03 (0.4578 s / it) +train: [9] Summary: lr: 0.000225 loss: 2.3855 (2.3991) grad: 0.2582 (0.2583) +eval (validation): [9] [ 0/85] eta: 0:04:37 time: 3.2658 data: 3.0233 max mem: 22448 +eval (validation): [9] [20/85] eta: 0:00:31 time: 0.3515 data: 0.0057 max mem: 22448 +eval (validation): [9] [40/85] eta: 0:00:18 time: 0.3388 data: 0.0034 max mem: 22448 +eval (validation): [9] [60/85] eta: 0:00:09 time: 0.3331 data: 0.0041 max mem: 22448 +eval (validation): [9] [80/85] eta: 0:00:01 time: 0.3413 data: 0.0042 max mem: 22448 +eval (validation): [9] [84/85] eta: 0:00:00 time: 0.3326 data: 0.0040 max mem: 22448 +eval (validation): [9] Total time: 0:00:32 (0.3781 s / it) +cv: [9] best hparam: (0.44, 1.0) (019) ('019_lr4.4e-01_wd1.0e+00') loss: 2.405 acc: 0.274 f1: 0.211 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [10] [ 0/400] eta: 0:21:59 lr: nan time: 3.2997 data: 2.9285 max mem: 22448 +train: [10] [ 20/400] eta: 0:03:41 lr: 0.000224 loss: 2.3286 (2.3344) grad: 0.2629 (0.2636) time: 0.4476 data: 0.0048 max mem: 22448 +train: [10] [ 40/400] eta: 0:03:06 lr: 0.000222 loss: 2.3286 (2.3354) grad: 0.2589 (0.2597) time: 0.4470 data: 0.0037 max mem: 22448 +train: [10] [ 60/400] eta: 0:02:47 lr: 0.000221 loss: 2.3480 (2.3536) grad: 0.2536 (0.2560) time: 0.4444 data: 0.0042 max mem: 22448 +train: [10] [ 80/400] eta: 0:02:33 lr: 0.000220 loss: 2.3336 (2.3435) grad: 0.2466 (0.2537) time: 0.4445 data: 0.0043 max mem: 22448 +train: [10] [100/400] eta: 0:02:22 lr: 0.000218 loss: 2.3242 (2.3383) grad: 0.2505 (0.2536) time: 0.4556 data: 0.0042 max mem: 22448 +train: [10] [120/400] eta: 0:02:12 lr: 0.000217 loss: 2.3253 (2.3403) grad: 0.2558 (0.2548) time: 0.4600 data: 0.0043 max mem: 22448 +train: [10] [140/400] eta: 0:02:02 lr: 0.000215 loss: 2.3357 (2.3442) grad: 0.2566 (0.2554) time: 0.4499 data: 0.0043 max mem: 22448 +train: [10] [160/400] eta: 0:01:52 lr: 0.000214 loss: 2.3454 (2.3439) grad: 0.2553 (0.2554) time: 0.4575 data: 0.0042 max mem: 22448 +train: [10] [180/400] eta: 0:01:42 lr: 0.000213 loss: 2.3395 (2.3457) grad: 0.2553 (0.2559) time: 0.4437 data: 0.0042 max mem: 22448 +train: [10] [200/400] eta: 0:01:32 lr: 0.000211 loss: 2.3730 (2.3468) grad: 0.2579 (0.2568) time: 0.4300 data: 0.0039 max mem: 22448 +train: [10] [220/400] eta: 0:01:23 lr: 0.000210 loss: 2.3595 (2.3465) grad: 0.2600 (0.2572) time: 0.4520 data: 0.0042 max mem: 22448 +train: [10] [240/400] eta: 0:01:13 lr: 0.000208 loss: 2.3295 (2.3466) grad: 0.2536 (0.2568) time: 0.4577 data: 0.0043 max mem: 22448 +train: [10] [260/400] eta: 0:01:04 lr: 0.000207 loss: 2.3299 (2.3456) grad: 0.2536 (0.2568) time: 0.4473 data: 0.0043 max mem: 22448 +train: [10] [280/400] eta: 0:00:55 lr: 0.000205 loss: 2.3638 (2.3462) grad: 0.2540 (0.2568) time: 0.4517 data: 0.0042 max mem: 22448 +train: [10] [300/400] eta: 0:00:45 lr: 0.000204 loss: 2.3037 (2.3425) grad: 0.2521 (0.2567) time: 0.4499 data: 0.0042 max mem: 22448 +train: [10] [320/400] eta: 0:00:36 lr: 0.000202 loss: 2.3037 (2.3400) grad: 0.2560 (0.2570) time: 0.4469 data: 0.0042 max mem: 22448 +train: [10] [340/400] eta: 0:00:27 lr: 0.000201 loss: 2.3274 (2.3398) grad: 0.2570 (0.2570) time: 0.4530 data: 0.0041 max mem: 22448 +train: [10] [360/400] eta: 0:00:18 lr: 0.000199 loss: 2.3135 (2.3383) grad: 0.2524 (0.2569) time: 0.4781 data: 0.0044 max mem: 22448 +train: [10] [380/400] eta: 0:00:09 lr: 0.000198 loss: 2.2826 (2.3372) grad: 0.2538 (0.2570) time: 0.4855 data: 0.0044 max mem: 22448 +train: [10] [399/400] eta: 0:00:00 lr: 0.000196 loss: 2.3158 (2.3384) grad: 0.2621 (0.2574) time: 0.4896 data: 0.0042 max mem: 22448 +train: [10] Total time: 0:03:04 (0.4620 s / it) +train: [10] Summary: lr: 0.000196 loss: 2.3158 (2.3384) grad: 0.2621 (0.2574) +eval (validation): [10] [ 0/85] eta: 0:05:15 time: 3.7106 data: 3.3597 max mem: 22448 +eval (validation): [10] [20/85] eta: 0:00:38 time: 0.4403 data: 0.0049 max mem: 22448 +eval (validation): [10] [40/85] eta: 0:00:21 time: 0.3712 data: 0.0043 max mem: 22448 +eval (validation): [10] [60/85] eta: 0:00:11 time: 0.3937 data: 0.0044 max mem: 22448 +eval (validation): [10] [80/85] eta: 0:00:02 time: 0.3835 data: 0.0046 max mem: 22448 +eval (validation): [10] [84/85] eta: 0:00:00 time: 0.3719 data: 0.0044 max mem: 22448 +eval (validation): [10] Total time: 0:00:37 (0.4377 s / it) +cv: [10] best hparam: (0.44, 1.0) (019) ('019_lr4.4e-01_wd1.0e+00') loss: 2.410 acc: 0.273 f1: 0.214 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [11] [ 0/400] eta: 0:24:46 lr: nan time: 3.7160 data: 3.2809 max mem: 22448 +train: [11] [ 20/400] eta: 0:04:09 lr: 0.000195 loss: 2.2169 (2.2526) grad: 0.2483 (0.2515) time: 0.5035 data: 0.0044 max mem: 22448 +train: [11] [ 40/400] eta: 0:03:29 lr: 0.000193 loss: 2.2615 (2.2689) grad: 0.2500 (0.2536) time: 0.5038 data: 0.0042 max mem: 22448 +train: [11] [ 60/400] eta: 0:03:06 lr: 0.000192 loss: 2.2615 (2.2636) grad: 0.2504 (0.2563) time: 0.4806 data: 0.0044 max mem: 22448 +train: [11] [ 80/400] eta: 0:02:50 lr: 0.000190 loss: 2.2674 (2.2823) grad: 0.2592 (0.2583) time: 0.4816 data: 0.0043 max mem: 22448 +train: [11] [100/400] eta: 0:02:36 lr: 0.000189 loss: 2.2737 (2.2758) grad: 0.2565 (0.2577) time: 0.4752 data: 0.0044 max mem: 22448 +train: [11] [120/400] eta: 0:02:23 lr: 0.000187 loss: 2.1984 (2.2651) grad: 0.2581 (0.2579) time: 0.4779 data: 0.0043 max mem: 22448 +train: [11] [140/400] eta: 0:02:12 lr: 0.000186 loss: 2.2659 (2.2688) grad: 0.2601 (0.2584) time: 0.4801 data: 0.0043 max mem: 22448 +train: [11] [160/400] eta: 0:02:01 lr: 0.000184 loss: 2.2890 (2.2720) grad: 0.2640 (0.2590) time: 0.4721 data: 0.0042 max mem: 22448 +train: [11] [180/400] eta: 0:01:50 lr: 0.000183 loss: 2.2890 (2.2745) grad: 0.2675 (0.2612) time: 0.4719 data: 0.0044 max mem: 22448 +train: [11] [200/400] eta: 0:01:39 lr: 0.000181 loss: 2.3003 (2.2772) grad: 0.2723 (0.2613) time: 0.4561 data: 0.0044 max mem: 22448 +train: [11] [220/400] eta: 0:01:28 lr: 0.000180 loss: 2.3232 (2.2832) grad: 0.2562 (0.2608) time: 0.4622 data: 0.0044 max mem: 22448 +train: [11] [240/400] eta: 0:01:18 lr: 0.000178 loss: 2.3495 (2.2856) grad: 0.2598 (0.2614) time: 0.4693 data: 0.0045 max mem: 22448 +train: [11] [260/400] eta: 0:01:08 lr: 0.000177 loss: 2.2751 (2.2844) grad: 0.2632 (0.2620) time: 0.4797 data: 0.0043 max mem: 22448 +train: [11] [280/400] eta: 0:00:58 lr: 0.000175 loss: 2.2802 (2.2861) grad: 0.2665 (0.2625) time: 0.4763 data: 0.0041 max mem: 22448 +train: [11] [300/400] eta: 0:00:48 lr: 0.000174 loss: 2.3182 (2.2913) grad: 0.2614 (0.2626) time: 0.4752 data: 0.0043 max mem: 22448 +train: [11] [320/400] eta: 0:00:39 lr: 0.000172 loss: 2.3386 (2.2933) grad: 0.2616 (0.2633) time: 0.4798 data: 0.0044 max mem: 22448 +train: [11] [340/400] eta: 0:00:29 lr: 0.000170 loss: 2.3274 (2.2949) grad: 0.2655 (0.2640) time: 0.4519 data: 0.0042 max mem: 22448 +train: [11] [360/400] eta: 0:00:19 lr: 0.000169 loss: 2.3014 (2.2949) grad: 0.2619 (0.2642) time: 0.4712 data: 0.0043 max mem: 22448 +train: [11] [380/400] eta: 0:00:09 lr: 0.000167 loss: 2.2719 (2.2930) grad: 0.2561 (0.2639) time: 0.4828 data: 0.0041 max mem: 22448 +train: [11] [399/400] eta: 0:00:00 lr: 0.000166 loss: 2.2793 (2.2959) grad: 0.2565 (0.2636) time: 0.4594 data: 0.0041 max mem: 22448 +train: [11] Total time: 0:03:13 (0.4839 s / it) +train: [11] Summary: lr: 0.000166 loss: 2.2793 (2.2959) grad: 0.2565 (0.2636) +eval (validation): [11] [ 0/85] eta: 0:05:08 time: 3.6350 data: 3.3635 max mem: 22448 +eval (validation): [11] [20/85] eta: 0:00:35 time: 0.3896 data: 0.0048 max mem: 22448 +eval (validation): [11] [40/85] eta: 0:00:20 time: 0.3836 data: 0.0038 max mem: 22448 +eval (validation): [11] [60/85] eta: 0:00:11 time: 0.4008 data: 0.0045 max mem: 22448 +eval (validation): [11] [80/85] eta: 0:00:02 time: 0.3678 data: 0.0040 max mem: 22448 +eval (validation): [11] [84/85] eta: 0:00:00 time: 0.3533 data: 0.0040 max mem: 22448 +eval (validation): [11] Total time: 0:00:36 (0.4247 s / it) +cv: [11] best hparam: (0.27, 1.0) (016) ('016_lr2.7e-01_wd1.0e+00') loss: 2.431 acc: 0.273 f1: 0.207 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [12] [ 0/400] eta: 0:22:39 lr: nan time: 3.3979 data: 3.0575 max mem: 22448 +train: [12] [ 20/400] eta: 0:03:53 lr: 0.000164 loss: 2.1588 (2.1873) grad: 0.2447 (0.2476) time: 0.4756 data: 0.0037 max mem: 22448 +train: [12] [ 40/400] eta: 0:03:15 lr: 0.000163 loss: 2.1927 (2.2000) grad: 0.2530 (0.2521) time: 0.4667 data: 0.0041 max mem: 22448 +train: [12] [ 60/400] eta: 0:02:56 lr: 0.000161 loss: 2.2138 (2.2039) grad: 0.2557 (0.2527) time: 0.4677 data: 0.0043 max mem: 22448 +train: [12] [ 80/400] eta: 0:02:42 lr: 0.000160 loss: 2.2144 (2.2109) grad: 0.2569 (0.2531) time: 0.4793 data: 0.0044 max mem: 22448 +train: [12] [100/400] eta: 0:02:30 lr: 0.000158 loss: 2.2313 (2.2166) grad: 0.2583 (0.2546) time: 0.4715 data: 0.0042 max mem: 22448 +train: [12] [120/400] eta: 0:02:18 lr: 0.000156 loss: 2.2235 (2.2214) grad: 0.2525 (0.2536) time: 0.4694 data: 0.0041 max mem: 22448 +train: [12] [140/400] eta: 0:02:07 lr: 0.000155 loss: 2.2073 (2.2179) grad: 0.2525 (0.2557) time: 0.4509 data: 0.0041 max mem: 22448 +train: [12] [160/400] eta: 0:01:57 lr: 0.000153 loss: 2.2182 (2.2211) grad: 0.2716 (0.2581) time: 0.4759 data: 0.0045 max mem: 22448 +train: [12] [180/400] eta: 0:01:46 lr: 0.000152 loss: 2.2429 (2.2243) grad: 0.2694 (0.2592) time: 0.4714 data: 0.0043 max mem: 22448 +train: [12] [200/400] eta: 0:01:37 lr: 0.000150 loss: 2.2429 (2.2310) grad: 0.2644 (0.2597) time: 0.4836 data: 0.0042 max mem: 22448 +train: [12] [220/400] eta: 0:01:27 lr: 0.000149 loss: 2.2573 (2.2345) grad: 0.2567 (0.2592) time: 0.4883 data: 0.0044 max mem: 22448 +train: [12] [240/400] eta: 0:01:17 lr: 0.000147 loss: 2.2468 (2.2322) grad: 0.2611 (0.2605) time: 0.4727 data: 0.0043 max mem: 22448 +train: [12] [260/400] eta: 0:01:07 lr: 0.000145 loss: 2.2051 (2.2320) grad: 0.2614 (0.2600) time: 0.4768 data: 0.0044 max mem: 22448 +train: [12] [280/400] eta: 0:00:58 lr: 0.000144 loss: 2.2028 (2.2280) grad: 0.2518 (0.2600) time: 0.4852 data: 0.0048 max mem: 22448 +train: [12] [300/400] eta: 0:00:48 lr: 0.000142 loss: 2.1915 (2.2302) grad: 0.2606 (0.2607) time: 0.4717 data: 0.0044 max mem: 22448 +train: [12] [320/400] eta: 0:00:38 lr: 0.000141 loss: 2.1902 (2.2311) grad: 0.2606 (0.2607) time: 0.4702 data: 0.0043 max mem: 22448 +train: [12] [340/400] eta: 0:00:28 lr: 0.000139 loss: 2.2131 (2.2302) grad: 0.2622 (0.2605) time: 0.4655 data: 0.0045 max mem: 22448 +train: [12] [360/400] eta: 0:00:19 lr: 0.000138 loss: 2.2100 (2.2292) grad: 0.2596 (0.2604) time: 0.4661 data: 0.0043 max mem: 22448 +train: [12] [380/400] eta: 0:00:09 lr: 0.000136 loss: 2.2100 (2.2296) grad: 0.2588 (0.2605) time: 0.4792 data: 0.0043 max mem: 22448 +train: [12] [399/400] eta: 0:00:00 lr: 0.000134 loss: 2.2209 (2.2296) grad: 0.2641 (0.2611) time: 0.4598 data: 0.0041 max mem: 22448 +train: [12] Total time: 0:03:12 (0.4800 s / it) +train: [12] Summary: lr: 0.000134 loss: 2.2209 (2.2296) grad: 0.2641 (0.2611) +eval (validation): [12] [ 0/85] eta: 0:04:45 time: 3.3550 data: 3.0878 max mem: 22448 +eval (validation): [12] [20/85] eta: 0:00:33 time: 0.3750 data: 0.0039 max mem: 22448 +eval (validation): [12] [40/85] eta: 0:00:20 time: 0.3721 data: 0.0038 max mem: 22448 +eval (validation): [12] [60/85] eta: 0:00:10 time: 0.3736 data: 0.0044 max mem: 22448 +eval (validation): [12] [80/85] eta: 0:00:02 time: 0.3560 data: 0.0042 max mem: 22448 +eval (validation): [12] [84/85] eta: 0:00:00 time: 0.3521 data: 0.0040 max mem: 22448 +eval (validation): [12] Total time: 0:00:34 (0.4062 s / it) +cv: [12] best hparam: (0.38, 1.0) (018) ('018_lr3.8e-01_wd1.0e+00') loss: 2.439 acc: 0.266 f1: 0.207 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [13] [ 0/400] eta: 0:22:16 lr: nan time: 3.3413 data: 2.9716 max mem: 22448 +train: [13] [ 20/400] eta: 0:03:57 lr: 0.000133 loss: 2.1616 (2.1743) grad: 0.2545 (0.2582) time: 0.4890 data: 0.0045 max mem: 22448 +train: [13] [ 40/400] eta: 0:03:19 lr: 0.000131 loss: 2.1791 (2.1761) grad: 0.2562 (0.2592) time: 0.4815 data: 0.0043 max mem: 22448 +train: [13] [ 60/400] eta: 0:02:59 lr: 0.000130 loss: 2.1920 (2.1836) grad: 0.2562 (0.2582) time: 0.4752 data: 0.0044 max mem: 22448 +train: [13] [ 80/400] eta: 0:02:45 lr: 0.000128 loss: 2.1554 (2.1782) grad: 0.2531 (0.2592) time: 0.4810 data: 0.0044 max mem: 22448 +train: [13] [100/400] eta: 0:02:32 lr: 0.000127 loss: 2.1570 (2.1747) grad: 0.2526 (0.2580) time: 0.4731 data: 0.0042 max mem: 22448 +train: [13] [120/400] eta: 0:02:20 lr: 0.000125 loss: 2.1742 (2.1699) grad: 0.2526 (0.2585) time: 0.4764 data: 0.0042 max mem: 22448 +train: [13] [140/400] eta: 0:02:09 lr: 0.000124 loss: 2.1963 (2.1805) grad: 0.2704 (0.2602) time: 0.4647 data: 0.0041 max mem: 22448 +train: [13] [160/400] eta: 0:01:58 lr: 0.000122 loss: 2.1882 (2.1790) grad: 0.2704 (0.2612) time: 0.4611 data: 0.0044 max mem: 22448 +train: [13] [180/400] eta: 0:01:47 lr: 0.000120 loss: 2.1882 (2.1845) grad: 0.2643 (0.2611) time: 0.4703 data: 0.0043 max mem: 22448 +train: [13] [200/400] eta: 0:01:37 lr: 0.000119 loss: 2.1502 (2.1791) grad: 0.2606 (0.2612) time: 0.4673 data: 0.0043 max mem: 22448 +train: [13] [220/400] eta: 0:01:27 lr: 0.000117 loss: 2.1445 (2.1813) grad: 0.2614 (0.2618) time: 0.4675 data: 0.0042 max mem: 22448 +train: [13] [240/400] eta: 0:01:17 lr: 0.000116 loss: 2.2170 (2.1821) grad: 0.2589 (0.2615) time: 0.4648 data: 0.0041 max mem: 22448 +train: [13] [260/400] eta: 0:01:07 lr: 0.000114 loss: 2.1831 (2.1850) grad: 0.2496 (0.2606) time: 0.4741 data: 0.0042 max mem: 22448 +train: [13] [280/400] eta: 0:00:57 lr: 0.000113 loss: 2.1530 (2.1819) grad: 0.2446 (0.2598) time: 0.4736 data: 0.0041 max mem: 22448 +train: [13] [300/400] eta: 0:00:48 lr: 0.000111 loss: 2.1519 (2.1810) grad: 0.2446 (0.2588) time: 0.4544 data: 0.0039 max mem: 22448 +train: [13] [320/400] eta: 0:00:38 lr: 0.000110 loss: 2.1722 (2.1820) grad: 0.2594 (0.2592) time: 0.4575 data: 0.0044 max mem: 22448 +train: [13] [340/400] eta: 0:00:28 lr: 0.000108 loss: 2.1722 (2.1810) grad: 0.2595 (0.2589) time: 0.4718 data: 0.0042 max mem: 22448 +train: [13] [360/400] eta: 0:00:19 lr: 0.000107 loss: 2.1604 (2.1812) grad: 0.2671 (0.2595) time: 0.4751 data: 0.0044 max mem: 22448 +train: [13] [380/400] eta: 0:00:09 lr: 0.000105 loss: 2.1686 (2.1806) grad: 0.2685 (0.2596) time: 0.4781 data: 0.0044 max mem: 22448 +train: [13] [399/400] eta: 0:00:00 lr: 0.000104 loss: 2.1746 (2.1816) grad: 0.2611 (0.2597) time: 0.4703 data: 0.0043 max mem: 22448 +train: [13] Total time: 0:03:11 (0.4787 s / it) +train: [13] Summary: lr: 0.000104 loss: 2.1746 (2.1816) grad: 0.2611 (0.2597) +eval (validation): [13] [ 0/85] eta: 0:04:37 time: 3.2702 data: 3.0259 max mem: 22448 +eval (validation): [13] [20/85] eta: 0:00:34 time: 0.3876 data: 0.0042 max mem: 22448 +eval (validation): [13] [40/85] eta: 0:00:19 time: 0.3544 data: 0.0036 max mem: 22448 +eval (validation): [13] [60/85] eta: 0:00:10 time: 0.3590 data: 0.0044 max mem: 22448 +eval (validation): [13] [80/85] eta: 0:00:02 time: 0.3630 data: 0.0040 max mem: 22448 +eval (validation): [13] [84/85] eta: 0:00:00 time: 0.3575 data: 0.0038 max mem: 22448 +eval (validation): [13] Total time: 0:00:34 (0.4023 s / it) +cv: [13] best hparam: (0.27, 1.0) (016) ('016_lr2.7e-01_wd1.0e+00') loss: 2.423 acc: 0.271 f1: 0.208 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [14] [ 0/400] eta: 0:25:08 lr: nan time: 3.7704 data: 3.3341 max mem: 22448 +train: [14] [ 20/400] eta: 0:04:15 lr: 0.000102 loss: 2.0710 (2.0898) grad: 0.2458 (0.2472) time: 0.5180 data: 0.0037 max mem: 22448 +train: [14] [ 40/400] eta: 0:03:27 lr: 0.000101 loss: 2.1019 (2.1102) grad: 0.2445 (0.2488) time: 0.4775 data: 0.0044 max mem: 22448 +train: [14] [ 60/400] eta: 0:03:04 lr: 0.000099 loss: 2.1159 (2.1183) grad: 0.2518 (0.2512) time: 0.4722 data: 0.0044 max mem: 22448 +train: [14] [ 80/400] eta: 0:02:48 lr: 0.000098 loss: 2.1186 (2.1256) grad: 0.2491 (0.2504) time: 0.4744 data: 0.0044 max mem: 22448 +train: [14] [100/400] eta: 0:02:34 lr: 0.000096 loss: 2.1419 (2.1301) grad: 0.2515 (0.2512) time: 0.4720 data: 0.0043 max mem: 22448 +train: [14] [120/400] eta: 0:02:22 lr: 0.000095 loss: 2.1100 (2.1231) grad: 0.2547 (0.2516) time: 0.4804 data: 0.0042 max mem: 22448 +train: [14] [140/400] eta: 0:02:11 lr: 0.000093 loss: 2.0798 (2.1201) grad: 0.2598 (0.2524) time: 0.4819 data: 0.0044 max mem: 22448 +train: [14] [160/400] eta: 0:02:00 lr: 0.000092 loss: 2.1072 (2.1193) grad: 0.2598 (0.2529) time: 0.4766 data: 0.0044 max mem: 22448 +train: [14] [180/400] eta: 0:01:49 lr: 0.000090 loss: 2.1072 (2.1174) grad: 0.2577 (0.2539) time: 0.4748 data: 0.0043 max mem: 22448 +train: [14] [200/400] eta: 0:01:39 lr: 0.000089 loss: 2.0922 (2.1186) grad: 0.2586 (0.2546) time: 0.4720 data: 0.0042 max mem: 22448 +train: [14] [220/400] eta: 0:01:28 lr: 0.000088 loss: 2.1092 (2.1187) grad: 0.2604 (0.2552) time: 0.4708 data: 0.0043 max mem: 22448 +train: [14] [240/400] eta: 0:01:18 lr: 0.000086 loss: 2.1286 (2.1227) grad: 0.2566 (0.2554) time: 0.4599 data: 0.0043 max mem: 22448 +train: [14] [260/400] eta: 0:01:08 lr: 0.000085 loss: 2.1286 (2.1241) grad: 0.2607 (0.2556) time: 0.4714 data: 0.0047 max mem: 22448 +train: [14] [280/400] eta: 0:00:58 lr: 0.000083 loss: 2.1476 (2.1249) grad: 0.2548 (0.2553) time: 0.4692 data: 0.0039 max mem: 22448 +train: [14] [300/400] eta: 0:00:48 lr: 0.000082 loss: 2.1480 (2.1298) grad: 0.2560 (0.2556) time: 0.4543 data: 0.0042 max mem: 22448 +train: [14] [320/400] eta: 0:00:38 lr: 0.000081 loss: 2.1685 (2.1313) grad: 0.2634 (0.2562) time: 0.4632 data: 0.0043 max mem: 22448 +train: [14] [340/400] eta: 0:00:29 lr: 0.000079 loss: 2.1410 (2.1320) grad: 0.2634 (0.2568) time: 0.4768 data: 0.0043 max mem: 22448 +train: [14] [360/400] eta: 0:00:19 lr: 0.000078 loss: 2.1366 (2.1328) grad: 0.2572 (0.2567) time: 0.4780 data: 0.0044 max mem: 22448 +train: [14] [380/400] eta: 0:00:09 lr: 0.000076 loss: 2.1191 (2.1317) grad: 0.2523 (0.2566) time: 0.4812 data: 0.0046 max mem: 22448 +train: [14] [399/400] eta: 0:00:00 lr: 0.000075 loss: 2.1218 (2.1328) grad: 0.2584 (0.2571) time: 0.4706 data: 0.0044 max mem: 22448 +train: [14] Total time: 0:03:13 (0.4833 s / it) +train: [14] Summary: lr: 0.000075 loss: 2.1218 (2.1328) grad: 0.2584 (0.2571) +eval (validation): [14] [ 0/85] eta: 0:04:29 time: 3.1696 data: 2.9370 max mem: 22448 +eval (validation): [14] [20/85] eta: 0:00:32 time: 0.3728 data: 0.0046 max mem: 22448 +eval (validation): [14] [40/85] eta: 0:00:19 time: 0.3588 data: 0.0038 max mem: 22448 +eval (validation): [14] [60/85] eta: 0:00:10 time: 0.3597 data: 0.0045 max mem: 22448 +eval (validation): [14] [80/85] eta: 0:00:01 time: 0.3601 data: 0.0046 max mem: 22448 +eval (validation): [14] [84/85] eta: 0:00:00 time: 0.3599 data: 0.0046 max mem: 22448 +eval (validation): [14] Total time: 0:00:33 (0.3995 s / it) +cv: [14] best hparam: (0.27, 1.0) (016) ('016_lr2.7e-01_wd1.0e+00') loss: 2.415 acc: 0.273 f1: 0.210 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [15] [ 0/400] eta: 0:23:02 lr: nan time: 3.4562 data: 3.0733 max mem: 22448 +train: [15] [ 20/400] eta: 0:03:45 lr: 0.000074 loss: 2.0732 (2.0921) grad: 0.2446 (0.2465) time: 0.4506 data: 0.0029 max mem: 22448 +train: [15] [ 40/400] eta: 0:03:12 lr: 0.000072 loss: 2.0787 (2.0897) grad: 0.2446 (0.2463) time: 0.4729 data: 0.0043 max mem: 22448 +train: [15] [ 60/400] eta: 0:02:55 lr: 0.000071 loss: 2.0787 (2.0840) grad: 0.2449 (0.2475) time: 0.4806 data: 0.0044 max mem: 22448 +train: [15] [ 80/400] eta: 0:02:41 lr: 0.000070 loss: 2.0501 (2.0762) grad: 0.2444 (0.2473) time: 0.4723 data: 0.0044 max mem: 22448 +train: [15] [100/400] eta: 0:02:29 lr: 0.000068 loss: 2.0501 (2.0686) grad: 0.2444 (0.2480) time: 0.4618 data: 0.0042 max mem: 22448 +train: [15] [120/400] eta: 0:02:17 lr: 0.000067 loss: 2.0771 (2.0737) grad: 0.2594 (0.2500) time: 0.4636 data: 0.0045 max mem: 22448 +train: [15] [140/400] eta: 0:02:07 lr: 0.000066 loss: 2.1040 (2.0814) grad: 0.2654 (0.2526) time: 0.4833 data: 0.0045 max mem: 22448 +train: [15] [160/400] eta: 0:01:56 lr: 0.000064 loss: 2.1040 (2.0826) grad: 0.2654 (0.2536) time: 0.4644 data: 0.0043 max mem: 22448 +train: [15] [180/400] eta: 0:01:46 lr: 0.000063 loss: 2.1089 (2.0916) grad: 0.2635 (0.2552) time: 0.4721 data: 0.0044 max mem: 22448 +train: [15] [200/400] eta: 0:01:36 lr: 0.000062 loss: 2.1079 (2.0912) grad: 0.2584 (0.2547) time: 0.4751 data: 0.0042 max mem: 22448 +train: [15] [220/400] eta: 0:01:27 lr: 0.000061 loss: 2.0957 (2.0903) grad: 0.2479 (0.2548) time: 0.4720 data: 0.0043 max mem: 22448 +train: [15] [240/400] eta: 0:01:16 lr: 0.000059 loss: 2.0921 (2.0893) grad: 0.2564 (0.2549) time: 0.4532 data: 0.0042 max mem: 22448 +train: [15] [260/400] eta: 0:01:07 lr: 0.000058 loss: 2.1065 (2.0934) grad: 0.2564 (0.2548) time: 0.4594 data: 0.0043 max mem: 22448 +train: [15] [280/400] eta: 0:00:57 lr: 0.000057 loss: 2.1041 (2.0909) grad: 0.2467 (0.2541) time: 0.4899 data: 0.0045 max mem: 22448 +train: [15] [300/400] eta: 0:00:47 lr: 0.000056 loss: 2.0753 (2.0913) grad: 0.2422 (0.2541) time: 0.4728 data: 0.0044 max mem: 22448 +train: [15] [320/400] eta: 0:00:38 lr: 0.000054 loss: 2.0987 (2.0912) grad: 0.2511 (0.2539) time: 0.4785 data: 0.0043 max mem: 22448 +train: [15] [340/400] eta: 0:00:28 lr: 0.000053 loss: 2.0938 (2.0920) grad: 0.2511 (0.2537) time: 0.4796 data: 0.0042 max mem: 22448 +train: [15] [360/400] eta: 0:00:19 lr: 0.000052 loss: 2.0721 (2.0918) grad: 0.2508 (0.2538) time: 0.4767 data: 0.0043 max mem: 22448 +train: [15] [380/400] eta: 0:00:09 lr: 0.000051 loss: 2.0613 (2.0898) grad: 0.2477 (0.2534) time: 0.4734 data: 0.0042 max mem: 22448 +train: [15] [399/400] eta: 0:00:00 lr: 0.000050 loss: 2.0715 (2.0909) grad: 0.2476 (0.2531) time: 0.4709 data: 0.0043 max mem: 22448 +train: [15] Total time: 0:03:11 (0.4789 s / it) +train: [15] Summary: lr: 0.000050 loss: 2.0715 (2.0909) grad: 0.2476 (0.2531) +eval (validation): [15] [ 0/85] eta: 0:04:35 time: 3.2381 data: 3.0043 max mem: 22448 +eval (validation): [15] [20/85] eta: 0:00:31 time: 0.3439 data: 0.0051 max mem: 22448 +eval (validation): [15] [40/85] eta: 0:00:19 time: 0.3738 data: 0.0039 max mem: 22448 +eval (validation): [15] [60/85] eta: 0:00:10 time: 0.3663 data: 0.0043 max mem: 22448 +eval (validation): [15] [80/85] eta: 0:00:01 time: 0.3656 data: 0.0045 max mem: 22448 +eval (validation): [15] [84/85] eta: 0:00:00 time: 0.3626 data: 0.0044 max mem: 22448 +eval (validation): [15] Total time: 0:00:33 (0.4000 s / it) +cv: [15] best hparam: (0.32, 1.0) (017) ('017_lr3.2e-01_wd1.0e+00') loss: 2.415 acc: 0.274 f1: 0.212 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [16] [ 0/400] eta: 0:23:55 lr: nan time: 3.5881 data: 3.1710 max mem: 22448 +train: [16] [ 20/400] eta: 0:04:04 lr: 0.000048 loss: 2.0130 (2.0597) grad: 0.2312 (0.2365) time: 0.4968 data: 0.0047 max mem: 22448 +train: [16] [ 40/400] eta: 0:03:21 lr: 0.000047 loss: 2.0138 (2.0417) grad: 0.2378 (0.2369) time: 0.4697 data: 0.0039 max mem: 22448 +train: [16] [ 60/400] eta: 0:02:59 lr: 0.000046 loss: 2.0186 (2.0352) grad: 0.2440 (0.2392) time: 0.4681 data: 0.0043 max mem: 22448 +train: [16] [ 80/400] eta: 0:02:44 lr: 0.000045 loss: 2.0684 (2.0509) grad: 0.2449 (0.2431) time: 0.4723 data: 0.0042 max mem: 22448 +train: [16] [100/400] eta: 0:02:31 lr: 0.000044 loss: 2.0779 (2.0470) grad: 0.2527 (0.2442) time: 0.4666 data: 0.0042 max mem: 22448 +train: [16] [120/400] eta: 0:02:19 lr: 0.000043 loss: 2.0483 (2.0495) grad: 0.2484 (0.2455) time: 0.4566 data: 0.0045 max mem: 22448 +train: [16] [140/400] eta: 0:02:08 lr: 0.000042 loss: 2.0478 (2.0521) grad: 0.2447 (0.2454) time: 0.4704 data: 0.0046 max mem: 22448 +train: [16] [160/400] eta: 0:01:57 lr: 0.000041 loss: 2.0667 (2.0592) grad: 0.2478 (0.2464) time: 0.4641 data: 0.0044 max mem: 22448 +train: [16] [180/400] eta: 0:01:47 lr: 0.000040 loss: 2.0800 (2.0590) grad: 0.2492 (0.2461) time: 0.4741 data: 0.0042 max mem: 22448 +train: [16] [200/400] eta: 0:01:37 lr: 0.000039 loss: 2.0297 (2.0543) grad: 0.2391 (0.2451) time: 0.4684 data: 0.0043 max mem: 22448 +train: [16] [220/400] eta: 0:01:27 lr: 0.000038 loss: 2.0330 (2.0548) grad: 0.2355 (0.2448) time: 0.4729 data: 0.0043 max mem: 22448 +train: [16] [240/400] eta: 0:01:17 lr: 0.000036 loss: 2.0571 (2.0539) grad: 0.2376 (0.2452) time: 0.4605 data: 0.0040 max mem: 22448 +train: [16] [260/400] eta: 0:01:07 lr: 0.000035 loss: 2.0387 (2.0566) grad: 0.2498 (0.2457) time: 0.4597 data: 0.0042 max mem: 22448 +train: [16] [280/400] eta: 0:00:57 lr: 0.000034 loss: 2.0539 (2.0564) grad: 0.2496 (0.2457) time: 0.4755 data: 0.0044 max mem: 22448 +train: [16] [300/400] eta: 0:00:47 lr: 0.000033 loss: 2.0539 (2.0579) grad: 0.2451 (0.2458) time: 0.4682 data: 0.0042 max mem: 22448 +train: [16] [320/400] eta: 0:00:38 lr: 0.000032 loss: 2.0859 (2.0611) grad: 0.2453 (0.2461) time: 0.4629 data: 0.0045 max mem: 22448 +train: [16] [340/400] eta: 0:00:28 lr: 0.000031 loss: 2.0697 (2.0604) grad: 0.2488 (0.2461) time: 0.4773 data: 0.0044 max mem: 22448 +train: [16] [360/400] eta: 0:00:19 lr: 0.000031 loss: 2.0277 (2.0603) grad: 0.2488 (0.2464) time: 0.4700 data: 0.0042 max mem: 22448 +train: [16] [380/400] eta: 0:00:09 lr: 0.000030 loss: 2.0517 (2.0590) grad: 0.2500 (0.2469) time: 0.4716 data: 0.0044 max mem: 22448 +train: [16] [399/400] eta: 0:00:00 lr: 0.000029 loss: 2.0517 (2.0587) grad: 0.2557 (0.2476) time: 0.4634 data: 0.0042 max mem: 22448 +train: [16] Total time: 0:03:11 (0.4776 s / it) +train: [16] Summary: lr: 0.000029 loss: 2.0517 (2.0587) grad: 0.2557 (0.2476) +eval (validation): [16] [ 0/85] eta: 0:04:39 time: 3.2912 data: 3.0546 max mem: 22448 +eval (validation): [16] [20/85] eta: 0:00:32 time: 0.3588 data: 0.0038 max mem: 22448 +eval (validation): [16] [40/85] eta: 0:00:19 time: 0.3688 data: 0.0037 max mem: 22448 +eval (validation): [16] [60/85] eta: 0:00:10 time: 0.3610 data: 0.0044 max mem: 22448 +eval (validation): [16] [80/85] eta: 0:00:01 time: 0.3578 data: 0.0042 max mem: 22448 +eval (validation): [16] [84/85] eta: 0:00:00 time: 0.3563 data: 0.0041 max mem: 22448 +eval (validation): [16] Total time: 0:00:33 (0.3993 s / it) +cv: [16] best hparam: (0.32, 1.0) (017) ('017_lr3.2e-01_wd1.0e+00') loss: 2.416 acc: 0.274 f1: 0.213 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [17] [ 0/400] eta: 0:24:27 lr: nan time: 3.6679 data: 3.2511 max mem: 22448 +train: [17] [ 20/400] eta: 0:04:11 lr: 0.000028 loss: 2.0155 (2.0019) grad: 0.2274 (0.2350) time: 0.5110 data: 0.0033 max mem: 22448 +train: [17] [ 40/400] eta: 0:03:22 lr: 0.000027 loss: 2.0155 (2.0150) grad: 0.2347 (0.2369) time: 0.4612 data: 0.0044 max mem: 22448 +train: [17] [ 60/400] eta: 0:02:58 lr: 0.000026 loss: 2.0454 (2.0314) grad: 0.2335 (0.2361) time: 0.4496 data: 0.0044 max mem: 22448 +train: [17] [ 80/400] eta: 0:02:44 lr: 0.000025 loss: 2.0108 (2.0205) grad: 0.2294 (0.2363) time: 0.4819 data: 0.0046 max mem: 22448 +train: [17] [100/400] eta: 0:02:32 lr: 0.000024 loss: 2.0207 (2.0296) grad: 0.2327 (0.2367) time: 0.4722 data: 0.0042 max mem: 22448 +train: [17] [120/400] eta: 0:02:20 lr: 0.000023 loss: 2.0347 (2.0286) grad: 0.2380 (0.2371) time: 0.4689 data: 0.0043 max mem: 22448 +train: [17] [140/400] eta: 0:02:09 lr: 0.000023 loss: 1.9998 (2.0261) grad: 0.2375 (0.2371) time: 0.4805 data: 0.0044 max mem: 22448 +train: [17] [160/400] eta: 0:01:58 lr: 0.000022 loss: 2.0202 (2.0257) grad: 0.2374 (0.2378) time: 0.4665 data: 0.0044 max mem: 22448 +train: [17] [180/400] eta: 0:01:48 lr: 0.000021 loss: 2.0054 (2.0242) grad: 0.2338 (0.2374) time: 0.4725 data: 0.0043 max mem: 22448 +train: [17] [200/400] eta: 0:01:37 lr: 0.000020 loss: 2.0051 (2.0235) grad: 0.2334 (0.2373) time: 0.4677 data: 0.0044 max mem: 22448 +train: [17] [220/400] eta: 0:01:27 lr: 0.000019 loss: 2.0387 (2.0266) grad: 0.2401 (0.2382) time: 0.4732 data: 0.0044 max mem: 22448 +train: [17] [240/400] eta: 0:01:17 lr: 0.000019 loss: 2.0559 (2.0254) grad: 0.2355 (0.2387) time: 0.4635 data: 0.0044 max mem: 22448 +train: [17] [260/400] eta: 0:01:07 lr: 0.000018 loss: 1.9848 (2.0244) grad: 0.2355 (0.2390) time: 0.4617 data: 0.0044 max mem: 22448 +train: [17] [280/400] eta: 0:00:57 lr: 0.000017 loss: 2.0163 (2.0266) grad: 0.2444 (0.2392) time: 0.4726 data: 0.0042 max mem: 22448 +train: [17] [300/400] eta: 0:00:48 lr: 0.000016 loss: 2.0515 (2.0284) grad: 0.2432 (0.2392) time: 0.4732 data: 0.0042 max mem: 22448 +train: [17] [320/400] eta: 0:00:38 lr: 0.000016 loss: 2.0470 (2.0285) grad: 0.2303 (0.2387) time: 0.4692 data: 0.0042 max mem: 22448 +train: [17] [340/400] eta: 0:00:28 lr: 0.000015 loss: 2.0062 (2.0292) grad: 0.2322 (0.2392) time: 0.4707 data: 0.0043 max mem: 22448 +train: [17] [360/400] eta: 0:00:19 lr: 0.000014 loss: 2.0552 (2.0312) grad: 0.2422 (0.2397) time: 0.4753 data: 0.0042 max mem: 22448 +train: [17] [380/400] eta: 0:00:09 lr: 0.000014 loss: 2.0290 (2.0298) grad: 0.2452 (0.2404) time: 0.4737 data: 0.0043 max mem: 22448 +train: [17] [399/400] eta: 0:00:00 lr: 0.000013 loss: 1.9911 (2.0285) grad: 0.2410 (0.2401) time: 0.4572 data: 0.0041 max mem: 22448 +train: [17] Total time: 0:03:11 (0.4794 s / it) +train: [17] Summary: lr: 0.000013 loss: 1.9911 (2.0285) grad: 0.2410 (0.2401) +eval (validation): [17] [ 0/85] eta: 0:04:49 time: 3.4092 data: 3.0978 max mem: 22448 +eval (validation): [17] [20/85] eta: 0:00:35 time: 0.4032 data: 0.0037 max mem: 22448 +eval (validation): [17] [40/85] eta: 0:00:20 time: 0.3650 data: 0.0042 max mem: 22448 +eval (validation): [17] [60/85] eta: 0:00:10 time: 0.3606 data: 0.0042 max mem: 22448 +eval (validation): [17] [80/85] eta: 0:00:02 time: 0.3582 data: 0.0043 max mem: 22448 +eval (validation): [17] [84/85] eta: 0:00:00 time: 0.3466 data: 0.0043 max mem: 22448 +eval (validation): [17] Total time: 0:00:34 (0.4095 s / it) +cv: [17] best hparam: (0.32, 1.0) (017) ('017_lr3.2e-01_wd1.0e+00') loss: 2.409 acc: 0.276 f1: 0.216 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [18] [ 0/400] eta: 0:24:04 lr: nan time: 3.6100 data: 3.2356 max mem: 22448 +train: [18] [ 20/400] eta: 0:03:58 lr: 0.000012 loss: 2.0125 (2.0318) grad: 0.2395 (0.2376) time: 0.4775 data: 0.0040 max mem: 22448 +train: [18] [ 40/400] eta: 0:03:16 lr: 0.000012 loss: 2.0117 (2.0034) grad: 0.2326 (0.2359) time: 0.4614 data: 0.0041 max mem: 22448 +train: [18] [ 60/400] eta: 0:02:54 lr: 0.000011 loss: 1.9553 (2.0037) grad: 0.2420 (0.2393) time: 0.4504 data: 0.0044 max mem: 22448 +train: [18] [ 80/400] eta: 0:02:40 lr: 0.000011 loss: 2.0007 (2.0048) grad: 0.2410 (0.2376) time: 0.4605 data: 0.0043 max mem: 22448 +train: [18] [100/400] eta: 0:02:28 lr: 0.000010 loss: 2.0048 (2.0065) grad: 0.2321 (0.2372) time: 0.4619 data: 0.0043 max mem: 22448 +train: [18] [120/400] eta: 0:02:17 lr: 0.000009 loss: 1.9950 (2.0009) grad: 0.2322 (0.2368) time: 0.4746 data: 0.0043 max mem: 22448 +train: [18] [140/400] eta: 0:02:06 lr: 0.000009 loss: 1.9816 (2.0045) grad: 0.2343 (0.2372) time: 0.4630 data: 0.0043 max mem: 22448 +train: [18] [160/400] eta: 0:01:56 lr: 0.000008 loss: 2.0263 (2.0061) grad: 0.2343 (0.2363) time: 0.4638 data: 0.0042 max mem: 22448 +train: [18] [180/400] eta: 0:01:46 lr: 0.000008 loss: 1.9985 (2.0038) grad: 0.2355 (0.2368) time: 0.4679 data: 0.0041 max mem: 22448 +train: [18] [200/400] eta: 0:01:35 lr: 0.000007 loss: 1.9960 (2.0046) grad: 0.2345 (0.2368) time: 0.4496 data: 0.0042 max mem: 22448 +train: [18] [220/400] eta: 0:01:25 lr: 0.000007 loss: 2.0046 (2.0065) grad: 0.2336 (0.2367) time: 0.4567 data: 0.0044 max mem: 22448 +train: [18] [240/400] eta: 0:01:16 lr: 0.000006 loss: 2.0485 (2.0103) grad: 0.2379 (0.2367) time: 0.4567 data: 0.0044 max mem: 22448 +train: [18] [260/400] eta: 0:01:06 lr: 0.000006 loss: 2.0229 (2.0099) grad: 0.2338 (0.2364) time: 0.4615 data: 0.0043 max mem: 22448 +train: [18] [280/400] eta: 0:00:56 lr: 0.000006 loss: 1.9981 (2.0097) grad: 0.2338 (0.2362) time: 0.4624 data: 0.0043 max mem: 22448 +train: [18] [300/400] eta: 0:00:47 lr: 0.000005 loss: 1.9912 (2.0082) grad: 0.2366 (0.2360) time: 0.4652 data: 0.0042 max mem: 22448 +train: [18] [320/400] eta: 0:00:37 lr: 0.000005 loss: 2.0125 (2.0108) grad: 0.2366 (0.2361) time: 0.4724 data: 0.0043 max mem: 22448 +train: [18] [340/400] eta: 0:00:28 lr: 0.000004 loss: 1.9906 (2.0082) grad: 0.2331 (0.2358) time: 0.4634 data: 0.0042 max mem: 22448 +train: [18] [360/400] eta: 0:00:18 lr: 0.000004 loss: 1.9809 (2.0077) grad: 0.2326 (0.2356) time: 0.4492 data: 0.0041 max mem: 22448 +train: [18] [380/400] eta: 0:00:09 lr: 0.000004 loss: 1.9888 (2.0081) grad: 0.2353 (0.2356) time: 0.4689 data: 0.0045 max mem: 22448 +train: [18] [399/400] eta: 0:00:00 lr: 0.000003 loss: 2.0019 (2.0071) grad: 0.2353 (0.2359) time: 0.4692 data: 0.0043 max mem: 22448 +train: [18] Total time: 0:03:08 (0.4710 s / it) +train: [18] Summary: lr: 0.000003 loss: 2.0019 (2.0071) grad: 0.2353 (0.2359) +eval (validation): [18] [ 0/85] eta: 0:04:48 time: 3.3988 data: 3.0844 max mem: 22448 +eval (validation): [18] [20/85] eta: 0:00:34 time: 0.3811 data: 0.0049 max mem: 22448 +eval (validation): [18] [40/85] eta: 0:00:20 time: 0.3698 data: 0.0045 max mem: 22448 +eval (validation): [18] [60/85] eta: 0:00:10 time: 0.3722 data: 0.0044 max mem: 22448 +eval (validation): [18] [80/85] eta: 0:00:02 time: 0.3673 data: 0.0042 max mem: 22448 +eval (validation): [18] [84/85] eta: 0:00:00 time: 0.3624 data: 0.0041 max mem: 22448 +eval (validation): [18] Total time: 0:00:34 (0.4105 s / it) +cv: [18] best hparam: (0.32, 1.0) (017) ('017_lr3.2e-01_wd1.0e+00') loss: 2.412 acc: 0.276 f1: 0.216 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [19] [ 0/400] eta: 0:23:49 lr: nan time: 3.5740 data: 3.1491 max mem: 22448 +train: [19] [ 20/400] eta: 0:04:08 lr: 0.000003 loss: 2.0119 (2.0100) grad: 0.2237 (0.2304) time: 0.5066 data: 0.0042 max mem: 22448 +train: [19] [ 40/400] eta: 0:03:22 lr: 0.000003 loss: 1.9822 (1.9888) grad: 0.2257 (0.2328) time: 0.4659 data: 0.0045 max mem: 22448 +train: [19] [ 60/400] eta: 0:03:00 lr: 0.000002 loss: 2.0080 (2.0073) grad: 0.2278 (0.2334) time: 0.4700 data: 0.0044 max mem: 22448 +train: [19] [ 80/400] eta: 0:02:45 lr: 0.000002 loss: 2.0253 (2.0101) grad: 0.2312 (0.2321) time: 0.4731 data: 0.0042 max mem: 22448 +train: [19] [100/400] eta: 0:02:31 lr: 0.000002 loss: 2.0071 (2.0089) grad: 0.2315 (0.2324) time: 0.4642 data: 0.0043 max mem: 22448 +train: [19] [120/400] eta: 0:02:19 lr: 0.000002 loss: 2.0071 (2.0121) grad: 0.2341 (0.2332) time: 0.4603 data: 0.0044 max mem: 22448 +train: [19] [140/400] eta: 0:02:08 lr: 0.000001 loss: 2.0295 (2.0080) grad: 0.2329 (0.2326) time: 0.4689 data: 0.0042 max mem: 22448 +train: [19] [160/400] eta: 0:01:57 lr: 0.000001 loss: 1.9884 (2.0029) grad: 0.2256 (0.2320) time: 0.4628 data: 0.0042 max mem: 22448 +train: [19] [180/400] eta: 0:01:47 lr: 0.000001 loss: 1.9629 (1.9995) grad: 0.2346 (0.2329) time: 0.4638 data: 0.0042 max mem: 22448 +train: [19] [200/400] eta: 0:01:36 lr: 0.000001 loss: 1.9785 (1.9984) grad: 0.2338 (0.2326) time: 0.4507 data: 0.0042 max mem: 22448 +train: [19] [220/400] eta: 0:01:26 lr: 0.000001 loss: 1.9896 (1.9969) grad: 0.2281 (0.2322) time: 0.4607 data: 0.0044 max mem: 22448 +train: [19] [240/400] eta: 0:01:16 lr: 0.000001 loss: 1.9904 (1.9966) grad: 0.2245 (0.2325) time: 0.4626 data: 0.0042 max mem: 22448 +train: [19] [260/400] eta: 0:01:07 lr: 0.000000 loss: 1.9784 (1.9958) grad: 0.2306 (0.2324) time: 0.4691 data: 0.0042 max mem: 22448 +train: [19] [280/400] eta: 0:00:57 lr: 0.000000 loss: 2.0273 (1.9980) grad: 0.2300 (0.2323) time: 0.4654 data: 0.0042 max mem: 22448 +train: [19] [300/400] eta: 0:00:47 lr: 0.000000 loss: 2.0293 (1.9987) grad: 0.2323 (0.2321) time: 0.4632 data: 0.0042 max mem: 22448 +train: [19] [320/400] eta: 0:00:38 lr: 0.000000 loss: 2.0134 (2.0002) grad: 0.2342 (0.2323) time: 0.4695 data: 0.0043 max mem: 22448 +train: [19] [340/400] eta: 0:00:28 lr: 0.000000 loss: 2.0503 (2.0037) grad: 0.2302 (0.2323) time: 0.4656 data: 0.0042 max mem: 22448 +train: [19] [360/400] eta: 0:00:18 lr: 0.000000 loss: 2.0503 (2.0037) grad: 0.2272 (0.2320) time: 0.4492 data: 0.0041 max mem: 22448 +train: [19] [380/400] eta: 0:00:09 lr: 0.000000 loss: 1.9923 (2.0036) grad: 0.2277 (0.2319) time: 0.4681 data: 0.0044 max mem: 22448 +train: [19] [399/400] eta: 0:00:00 lr: 0.000000 loss: 2.0060 (2.0053) grad: 0.2310 (0.2320) time: 0.4565 data: 0.0043 max mem: 22448 +train: [19] Total time: 0:03:09 (0.4740 s / it) +train: [19] Summary: lr: 0.000000 loss: 2.0060 (2.0053) grad: 0.2310 (0.2320) +eval (validation): [19] [ 0/85] eta: 0:04:50 time: 3.4139 data: 3.1149 max mem: 22448 +eval (validation): [19] [20/85] eta: 0:00:32 time: 0.3525 data: 0.0041 max mem: 22448 +eval (validation): [19] [40/85] eta: 0:00:19 time: 0.3640 data: 0.0038 max mem: 22448 +eval (validation): [19] [60/85] eta: 0:00:10 time: 0.3759 data: 0.0045 max mem: 22448 +eval (validation): [19] [80/85] eta: 0:00:02 time: 0.3616 data: 0.0041 max mem: 22448 +eval (validation): [19] [84/85] eta: 0:00:00 time: 0.3474 data: 0.0041 max mem: 22448 +eval (validation): [19] Total time: 0:00:34 (0.4016 s / it) +cv: [19] best hparam: (0.32, 1.0) (017) ('017_lr3.2e-01_wd1.0e+00') loss: 2.411 acc: 0.276 f1: 0.216 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +evaluating last checkpoint: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +eval model info: +{"score": 0.27611664820967147, "hparam": [0.32, 1.0], "hparam_id": 17, "epoch": 19, "is_best": false, "best_score": 0.28497600590623845} +eval (train): [20] [ 0/509] eta: 0:25:45 time: 3.0359 data: 2.7436 max mem: 22448 +eval (train): [20] [ 20/509] eta: 0:04:13 time: 0.3920 data: 0.0041 max mem: 22448 +eval (train): [20] [ 40/509] eta: 0:03:36 time: 0.4027 data: 0.0044 max mem: 22448 +eval (train): [20] [ 60/509] eta: 0:03:17 time: 0.3931 data: 0.0045 max mem: 22448 +eval (train): [20] [ 80/509] eta: 0:03:00 time: 0.3675 data: 0.0042 max mem: 22448 +eval (train): [20] [100/509] eta: 0:02:49 time: 0.3802 data: 0.0046 max mem: 22448 +eval (train): [20] [120/509] eta: 0:02:40 time: 0.4151 data: 0.0049 max mem: 22448 +eval (train): [20] [140/509] eta: 0:02:31 time: 0.3876 data: 0.0044 max mem: 22448 +eval (train): [20] [160/509] eta: 0:02:23 time: 0.4116 data: 0.0047 max mem: 22448 +eval (train): [20] [180/509] eta: 0:02:13 time: 0.3693 data: 0.0043 max mem: 22448 +eval (train): [20] [200/509] eta: 0:02:04 time: 0.3778 data: 0.0046 max mem: 22448 +eval (train): [20] [220/509] eta: 0:01:54 time: 0.3473 data: 0.0044 max mem: 22448 +eval (train): [20] [240/509] eta: 0:01:46 time: 0.3703 data: 0.0044 max mem: 22448 +eval (train): [20] [260/509] eta: 0:01:38 time: 0.3804 data: 0.0044 max mem: 22448 +eval (train): [20] [280/509] eta: 0:01:30 time: 0.3879 data: 0.0047 max mem: 22448 +eval (train): [20] [300/509] eta: 0:01:22 time: 0.3875 data: 0.0043 max mem: 22448 +eval (train): [20] [320/509] eta: 0:01:14 time: 0.3680 data: 0.0043 max mem: 22448 +eval (train): [20] [340/509] eta: 0:01:06 time: 0.3890 data: 0.0045 max mem: 22448 +eval (train): [20] [360/509] eta: 0:00:58 time: 0.3798 data: 0.0043 max mem: 22448 +eval (train): [20] [380/509] eta: 0:00:50 time: 0.3945 data: 0.0044 max mem: 22448 +eval (train): [20] [400/509] eta: 0:00:42 time: 0.3800 data: 0.0042 max mem: 22448 +eval (train): [20] [420/509] eta: 0:00:34 time: 0.3713 data: 0.0044 max mem: 22448 +eval (train): [20] [440/509] eta: 0:00:26 time: 0.3843 data: 0.0044 max mem: 22448 +eval (train): [20] [460/509] eta: 0:00:19 time: 0.4126 data: 0.0045 max mem: 22448 +eval (train): [20] [480/509] eta: 0:00:11 time: 0.3905 data: 0.0043 max mem: 22448 +eval (train): [20] [500/509] eta: 0:00:03 time: 0.3822 data: 0.0038 max mem: 22448 +eval (train): [20] [508/509] eta: 0:00:00 time: 0.3570 data: 0.0036 max mem: 22448 +eval (train): [20] Total time: 0:03:18 (0.3909 s / it) +eval (validation): [20] [ 0/85] eta: 0:04:30 time: 3.1771 data: 2.8674 max mem: 22448 +eval (validation): [20] [20/85] eta: 0:00:33 time: 0.3756 data: 0.0057 max mem: 22448 +eval (validation): [20] [40/85] eta: 0:00:21 time: 0.4284 data: 0.0044 max mem: 22448 +eval (validation): [20] [60/85] eta: 0:00:11 time: 0.3984 data: 0.0044 max mem: 22448 +eval (validation): [20] [80/85] eta: 0:00:02 time: 0.3730 data: 0.0043 max mem: 22448 +eval (validation): [20] [84/85] eta: 0:00:00 time: 0.3692 data: 0.0041 max mem: 22448 +eval (validation): [20] Total time: 0:00:36 (0.4277 s / it) +eval (test): [20] [ 0/85] eta: 0:05:03 time: 3.5744 data: 3.2364 max mem: 22448 +eval (test): [20] [20/85] eta: 0:00:39 time: 0.4555 data: 0.0065 max mem: 22448 +eval (test): [20] [40/85] eta: 0:00:22 time: 0.3811 data: 0.0041 max mem: 22448 +eval (test): [20] [60/85] eta: 0:00:11 time: 0.3884 data: 0.0045 max mem: 22448 +eval (test): [20] [80/85] eta: 0:00:02 time: 0.3924 data: 0.0045 max mem: 22448 +eval (test): [20] [84/85] eta: 0:00:00 time: 0.3701 data: 0.0041 max mem: 22448 +eval (test): [20] Total time: 0:00:37 (0.4410 s / it) +eval (testid): [20] [ 0/82] eta: 0:06:04 time: 4.4401 data: 4.1645 max mem: 22448 +eval (testid): [20] [20/82] eta: 0:00:40 time: 0.4588 data: 0.0052 max mem: 22448 +eval (testid): [20] [40/82] eta: 0:00:23 time: 0.4487 data: 0.0049 max mem: 22448 +eval (testid): [20] [60/82] eta: 0:00:11 time: 0.4105 data: 0.0046 max mem: 22448 +eval (testid): [20] [80/82] eta: 0:00:00 time: 0.3718 data: 0.0047 max mem: 22448 +eval (testid): [20] [81/82] eta: 0:00:00 time: 0.3589 data: 0.0045 max mem: 22448 +eval (testid): [20] Total time: 0:00:38 (0.4713 s / it) +evaluating best checkpoint: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/eval_v2/nsd_cococlip__patch__attn/checkpoint-best.pth +eval model info: +{"score": 0.28497600590623845, "hparam": [1, 1.0], "hparam_id": 24, "epoch": 5, "is_best": true, "best_score": 0.28497600590623845} +eval (train): [20] [ 0/509] eta: 0:26:28 time: 3.1213 data: 2.8703 max mem: 22448 +eval (train): [20] [ 20/509] eta: 0:04:36 time: 0.4373 data: 0.0156 max mem: 22448 +eval (train): [20] [ 40/509] eta: 0:03:53 time: 0.4285 data: 0.0037 max mem: 22448 +eval (train): [20] [ 60/509] eta: 0:03:25 time: 0.3755 data: 0.0041 max mem: 22448 +eval (train): [20] [ 80/509] eta: 0:03:08 time: 0.3867 data: 0.0051 max mem: 22448 +eval (train): [20] [100/509] eta: 0:02:54 time: 0.3657 data: 0.0044 max mem: 22448 +eval (train): [20] [120/509] eta: 0:02:41 time: 0.3586 data: 0.0046 max mem: 22448 +eval (train): [20] [140/509] eta: 0:02:31 time: 0.3833 data: 0.0044 max mem: 22448 +eval (train): [20] [160/509] eta: 0:02:21 time: 0.3811 data: 0.0046 max mem: 22448 +eval (train): [20] [180/509] eta: 0:02:11 time: 0.3566 data: 0.0043 max mem: 22448 +eval (train): [20] [200/509] eta: 0:02:03 time: 0.3972 data: 0.0043 max mem: 22448 +eval (train): [20] [220/509] eta: 0:01:54 time: 0.3697 data: 0.0044 max mem: 22448 +eval (train): [20] [240/509] eta: 0:01:48 time: 0.4504 data: 0.0051 max mem: 22448 +eval (train): [20] [260/509] eta: 0:01:40 time: 0.3961 data: 0.0041 max mem: 22448 +eval (train): [20] [280/509] eta: 0:01:32 time: 0.4082 data: 0.0043 max mem: 22448 +eval (train): [20] [300/509] eta: 0:01:23 time: 0.3934 data: 0.0046 max mem: 22448 +eval (train): [20] [320/509] eta: 0:01:15 time: 0.3998 data: 0.0043 max mem: 22448 +eval (train): [20] [340/509] eta: 0:01:07 time: 0.3686 data: 0.0044 max mem: 22448 +eval (train): [20] [360/509] eta: 0:00:59 time: 0.4005 data: 0.0050 max mem: 22448 +eval (train): [20] [380/509] eta: 0:00:51 time: 0.4354 data: 0.0045 max mem: 22448 +eval (train): [20] [400/509] eta: 0:00:43 time: 0.3900 data: 0.0043 max mem: 22448 +eval (train): [20] [420/509] eta: 0:00:35 time: 0.4190 data: 0.0045 max mem: 22448 +eval (train): [20] [440/509] eta: 0:00:27 time: 0.4069 data: 0.0046 max mem: 22448 +eval (train): [20] [460/509] eta: 0:00:19 time: 0.4149 data: 0.0046 max mem: 22448 +eval (train): [20] [480/509] eta: 0:00:11 time: 0.4092 data: 0.0047 max mem: 22448 +eval (train): [20] [500/509] eta: 0:00:03 time: 0.3777 data: 0.0044 max mem: 22448 +eval (train): [20] [508/509] eta: 0:00:00 time: 0.3611 data: 0.0041 max mem: 22448 +eval (train): [20] Total time: 0:03:25 (0.4030 s / it) +eval (validation): [20] [ 0/85] eta: 0:04:27 time: 3.1492 data: 2.8725 max mem: 22448 +eval (validation): [20] [20/85] eta: 0:00:33 time: 0.3873 data: 0.0049 max mem: 22448 +eval (validation): [20] [40/85] eta: 0:00:21 time: 0.4253 data: 0.0037 max mem: 22448 +eval (validation): [20] [60/85] eta: 0:00:11 time: 0.4262 data: 0.0045 max mem: 22448 +eval (validation): [20] [80/85] eta: 0:00:02 time: 0.4348 data: 0.0043 max mem: 22448 +eval (validation): [20] [84/85] eta: 0:00:00 time: 0.4158 data: 0.0037 max mem: 22448 +eval (validation): [20] Total time: 0:00:38 (0.4508 s / it) +eval (test): [20] [ 0/85] eta: 0:04:57 time: 3.4976 data: 3.2088 max mem: 22448 +eval (test): [20] [20/85] eta: 0:00:34 time: 0.3872 data: 0.0104 max mem: 22448 +eval (test): [20] [40/85] eta: 0:00:20 time: 0.3577 data: 0.0043 max mem: 22448 +eval (test): [20] [60/85] eta: 0:00:10 time: 0.4158 data: 0.0042 max mem: 22448 +eval (test): [20] [80/85] eta: 0:00:02 time: 0.3878 data: 0.0042 max mem: 22448 +eval (test): [20] [84/85] eta: 0:00:00 time: 0.3699 data: 0.0040 max mem: 22448 +eval (test): [20] Total time: 0:00:36 (0.4237 s / it) +eval (testid): [20] [ 0/82] eta: 0:04:31 time: 3.3120 data: 3.0190 max mem: 22448 +eval (testid): [20] [20/82] eta: 0:00:33 time: 0.4092 data: 0.0040 max mem: 22448 +eval (testid): [20] [40/82] eta: 0:00:19 time: 0.3948 data: 0.0043 max mem: 22448 +eval (testid): [20] [60/82] eta: 0:00:10 time: 0.4252 data: 0.0052 max mem: 22448 +eval (testid): [20] [80/82] eta: 0:00:00 time: 0.3431 data: 0.0039 max mem: 22448 +eval (testid): [20] [81/82] eta: 0:00:00 time: 0.3301 data: 0.0039 max mem: 22448 +eval (testid): [20] Total time: 0:00:35 (0.4284 s / it) +eval results: + +| model | repr | clf | dataset | ckpt | epoch | lr | wd | hparam_id | hparam | split | loss | acc | acc_std | f1 | f1_std | +|:---------|:-------|:------|:-------------|:-------|--------:|-------:|-----:|------------:|:---------|:-----------|-------:|--------:|----------:|--------:|----------:| +| flat_mae | patch | attn | nsd_cococlip | best | 5 | 0.0003 | 0.05 | 24 | [1, 1.0] | train | 2.1198 | 0.36138 | 0.0022797 | 0.29933 | 0.0024405 | +| flat_mae | patch | attn | nsd_cococlip | best | 5 | 0.0003 | 0.05 | 24 | [1, 1.0] | validation | 2.3669 | 0.28498 | 0.0053016 | 0.21436 | 0.0049176 | +| flat_mae | patch | attn | nsd_cococlip | best | 5 | 0.0003 | 0.05 | 24 | [1, 1.0] | test | 2.2388 | 0.32022 | 0.0054666 | 0.24775 | 0.0054448 | +| flat_mae | patch | attn | nsd_cococlip | best | 5 | 0.0003 | 0.05 | 24 | [1, 1.0] | testid | 2.2897 | 0.30711 | 0.0057441 | 0.24561 | 0.0056221 | + + +done! total time: 1:27:19 diff --git a/input_space_v3/flat_lr1e-3_6/eval_v2/nsd_cococlip__patch__attn/train_log.json b/input_space_v3/flat_lr1e-3_6/eval_v2/nsd_cococlip__patch__attn/train_log.json new file mode 100644 index 0000000000000000000000000000000000000000..021b3263453d013b14c5b9c778978573a604efed --- /dev/null +++ b/input_space_v3/flat_lr1e-3_6/eval_v2/nsd_cococlip__patch__attn/train_log.json @@ -0,0 +1,20 @@ +{"epoch": 0, "train/lr": 2.987987987987988e-05, "train/loss": 3.1217349195480346, "train/grad": 0.16045047394931317, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.167586669921875, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.167015380859375, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.16606201171875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.16512451171875, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.164285888671875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.163133544921875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.161995849609375, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.160706787109375, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.15916015625, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.157725830078125, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.156424560546875, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.154564208984375, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.153194580078125, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.15143798828125, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.149864501953125, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.148587646484375, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.147247314453125, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.14594970703125, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.144608154296875, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.143646240234375, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.14255859375, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.141533203125, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.140748291015625, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.139908447265625, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.13938232421875, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.138868408203125, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.138489990234375, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.13830322265625, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.138162841796875, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.138173828125, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.138214111328125, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.138353271484375, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.138394775390625, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.13853759765625, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.138607177734375, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.138470458984375, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.1382281494140627, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.136881103515625, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.131619873046875, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.1142779541015626, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.0967141723632814, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.078479080200195, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.0498616027832033, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.025373840332031, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.0052997207641603, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.982465934753418, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.965109634399414, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.948683052062988, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.9369919967651366, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.0234743557497859, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.02342367368284613, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.023341682539321482, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.023264498193748297, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.02318989754654467, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.023090767338871956, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.022986542317084968, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.022878013784065843, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.022746580047532917, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.0226213607378304, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.022511968701146544, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.022367777787148952, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.022247384139336645, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.0221036558970809, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.021993085024878383, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.021906225085258482, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.02181655023712665, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.02173142264597118, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.02165669502224773, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.02160183637868613, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.021548123294487596, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.02150597726460546, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.02147167761810124, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.02144615094177425, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.02142999471630901, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.021420774441212417, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.021421125545166432, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.021426847777329384, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.021438717357814312, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.02145453555509448, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.021463260906748473, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.021463802326470615, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.021443237084895372, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.021401417776942253, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.02131715452298522, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.021199590219184758, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.02105030609294772, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0209297287883237, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.02096595852635801, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.021480241692624986, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.022264176914468407, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0229214603966102, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.023627618527971208, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.024374534231610595, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.02559018971398473, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.02678250491153449, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.027363024242222308, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.02855015658773482, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.029951389022171496, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.153714418411255, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1520423889160156, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.149470329284668, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1471540927886963, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.145017623901367, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.142296552658081, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.139589786529541, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.136988639831543, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1341910362243652, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.131782293319702, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1299171447753906, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.127836227416992, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1264758110046387, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1251659393310547, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.124406576156616, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.123969078063965, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1235768795013428, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.123319387435913, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1231698989868164, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.123149871826172, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.1233139038085938, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.123772144317627, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.124574661254883, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.1257407665252686, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.1271846294403076, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.1289055347442627, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.130291223526001, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.131223440170288, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.131612539291382, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.1301448345184326, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.127157211303711, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.1239359378814697, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.119493246078491, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.115708827972412, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.111485719680786, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.1069915294647217, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.096385955810547, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.0616066455841064, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.9589152336120605, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.78497576713562, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.7098703384399414, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.6411685943603516, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.612184762954712, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.618534564971924, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.5899055004119873, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.5824859142303467, "validation/loss_046_lr3.6e+01_wd1.0e+00": 2.563124895095825, "validation/loss_047_lr4.3e+01_wd1.0e+00": 2.6284053325653076, "validation/loss_048_lr5.0e+01_wd1.0e+00": 2.6970181465148926, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.05444813584348468, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.05518641565153193, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.054817275747508304, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.05352528608342562, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.05537098560354374, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.056847545219638244, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.05647840531561462, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.05666297526762643, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.05887781469176818, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.060538944259874494, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06256921373200443, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06312292358803986, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06570690291620525, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.0664451827242525, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06662975267626431, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06699889258028793, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06552233296419344, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06496862310815799, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06570690291620525, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.06699889258028793, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.06755260243632337, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.06718346253229975, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.06755260243632337, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.062200073827980804, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.057770394979697305, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.054078995939461055, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.052417866371354746, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.05204872646733112, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.052417866371354746, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.054817275747508304, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.05998523440383906, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.0664451827242525, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.07308970099667775, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.07678110003691399, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.08010335917312661, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.08194905869324474, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.08157991878922112, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.09357696566998892, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.12809154669619785, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.1744186046511628, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.19878183831672203, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.21631598375784422, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.2159468438538206, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.22443706164636398, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.23237356958287192, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.2397563676633444, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.2349575489110373, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.21262458471760798, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.20007382798080472, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.010105289394705633, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.011403694405197584, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.01267900768402992, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.013243797395208217, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.014613874701033406, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.01645460774500433, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.016854627651504094, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.016963726622444004, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.017735357078579473, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.01789841630013214, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.017390293880434917, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.01586270226258436, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.014926191362663812, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.014053119292516077, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.013271384791244288, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.013076379676308631, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.012470640546590632, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.012296087899184243, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.01267813004401381, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.01322603308864384, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.014556113337312928, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.014137093159918864, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.014887354515165846, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.013567726020488056, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.01075760267650462, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.007592262666141558, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.005663359860240147, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.005237914723188239, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.005568917059942473, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.007385919876451882, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.009292477226123502, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.010445316456747976, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.012242653136124564, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.015257649539468154, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.021099920422128323, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.024855734931503035, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.023186472537114713, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.036040953330789584, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.06888195481889074, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.09434894215694815, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.11528646498692874, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.13259015784401104, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.14215951078868622, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.15870915359363488, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.170925894922039, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.17131315982720807, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.17036689731284957, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.1525049104201742, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.13239220821020278, "id_best": 45, "lr_best": 0.0093, "wd_best": 0.05, "train/loss_best": 2.982465934753418, "validation/loss_best": 2.5824859142303467, "validation/acc_best": 0.2397563676633444, "validation/f1_best": 0.17131315982720807} +{"epoch": 1, "train/lr": 8.993993993993998e-05, "train/loss": 2.9513470351696016, "train/grad": 0.18664297625422477, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.145087890625, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.142952880859375, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.14023193359375, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.13808837890625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.136119384765625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.1341357421875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.132398681640625, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.13099853515625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.129720458984375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.128763427734375, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.128236083984375, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.127598876953125, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.127232666015625, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.12687255859375, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.12664306640625, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.1264404296875, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.12624755859375, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.125955810546875, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.1255517578125, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.125126953125, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.124683837890625, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.124090576171875, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.123419189453125, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.1227587890625, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.12189697265625, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.120716552734375, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.1195751953125, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.1177752685546873, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.112491455078125, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.0890768432617186, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.044172821044922, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.996612091064453, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.9311629486083985, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.86992977142334, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.7968992233276366, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.7315329360961913, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.66796781539917, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.616762790679932, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.573581075668335, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.5441946506500246, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.5295824337005617, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.5193438816070555, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.5202385902404787, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.521630733013153, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.527420792579651, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.5426280903816223, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.570619722604752, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.6334420812129973, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.6773975121974947, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.02137756603304297, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.02119837294332683, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.02094953636173159, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.020753266210667788, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.020598038462921978, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.020435003759339453, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.020305149918422104, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.020208231266587974, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.02012915848288685, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.02008337781764567, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.02006246176082641, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.02005682104732841, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.020065045882947743, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.020087085627019406, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.020115173244848846, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.020141784898005426, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.02017497536726296, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.020210343548096716, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.020247952593490482, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.02028061500284821, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.020316868373192846, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.020348279331810774, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.02037211208604276, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.020377386026084424, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.02035426107235253, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.020273552727885544, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.020152157759293913, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.020006598411127924, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.019821493956260382, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.02002580394037068, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.02079671101178974, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.02172985384706408, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.023067418010905383, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.024172625257633626, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.025388913028873503, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.02667701137252152, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.02829233618453145, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.029636732530780138, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.030960800582543014, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.03268659600056708, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.03388033637776971, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.03461708878166973, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.036443602042272684, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0372018950432539, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.038294653138145805, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.039967708932235835, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.04261591990478337, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.047051497707143425, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.05166284216567874, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1329185962677, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1309986114501953, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.128633737564087, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.127095937728882, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1260807514190674, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1251914501190186, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1246564388275146, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.124319314956665, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1240882873535156, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.123964786529541, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1238436698913574, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.123667001724243, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1233937740325928, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1228926181793213, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1222894191741943, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.121689558029175, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.120957374572754, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1201889514923096, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1195425987243652, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.119168996810913, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.119018316268921, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.1190743446350098, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.119572877883911, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.120630979537964, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.1225314140319824, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.1249091625213623, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.1247987747192383, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.1185505390167236, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.0735204219818115, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.8813679218292236, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.7246060371398926, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.645965099334717, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.570336103439331, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.538174867630005, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.54052734375, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.519199848175049, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.47257924079895, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.469982624053955, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.498194932937622, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.47910213470459, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.482473134994507, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.48443341255188, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.5214169025421143, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.5249083042144775, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.6132290363311768, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.7995567321777344, "validation/loss_046_lr3.6e+01_wd1.0e+00": 2.752113103866577, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.0936174392700195, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.258267402648926, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.05887781469176818, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06164636397194537, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06127722406792174, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06256921373200443, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.060723514211886306, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06127722406792174, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.061461794019933555, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06164636397194537, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06256921373200443, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06293835363602805, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06312292358803986, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06275378368401624, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06386120339608711, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06423034330011074, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06570690291620525, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06736803248431156, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06921373200442968, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.07050572166851236, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.07198228128460686, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.07087486157253599, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.07235142118863049, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.07272056109265411, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.07493540051679587, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.07585825027685493, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.07788851974898486, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.08213362864525656, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.09892949427833149, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.15079365079365079, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.17995570321151716, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.19933554817275748, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.21982281284606867, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.23052787006275377, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.2264673311184939, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.23440383905500184, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.2484311554078996, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.24880029531192321, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.24658545588778147, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.2547065337763012, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.24769287559985234, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.2469545957918051, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.2397563676633444, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.24234034699150978, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.22240679217423404, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.2087486157253599, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.20837947582133629, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.17663344407530454, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.1566998892580288, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.018730992483331977, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.018728426171677623, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.0152630633952381, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.013240044481353415, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.010833758055461292, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.008801027429639742, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.007832625067841126, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.007257998248967578, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.007664615182022355, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.008190180631517236, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.008662683385305616, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.009439962866415606, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.00975351169490553, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.010428806842850432, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.0109710252139086, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.01186806888492273, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.013165356786208796, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.01376207569863321, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.014182434035164226, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.01516453588365038, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.015452622900192314, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.015441898155361613, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.016273084930198186, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.014752689150272398, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.014792666279262701, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.015153670861311905, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.016402594357487442, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.018264613391475126, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.03327540410438897, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.0693331047024135, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.09726663884783104, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.12068651817272835, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.1494157456897015, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.16361798743313277, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.16066184466937808, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.16724755343614053, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.17718265582530077, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.177530432331812, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.17579439962406543, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.183976313255063, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.17504033938324937, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.17857109216609143, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.16471316758812987, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.1763630106697134, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.1629569859100111, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.13364359846651094, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.13046241774501202, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.10317217337529666, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0924148903040836, "id_best": 39, "lr_best": 0.0036, "wd_best": 0.05, "train/loss_best": 2.5441946506500246, "validation/loss_best": 2.47910213470459, "validation/acc_best": 0.2547065337763012, "validation/f1_best": 0.183976313255063} +{"epoch": 2, "train/lr": 0.00014999999999999988, "train/loss": 2.9965800189971925, "train/grad": 0.46924072220921514, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.134315185546875, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.133162841796875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.13222900390625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.131563720703125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.1312744140625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.130916748046875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.130843505859375, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.13054931640625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.130325927734375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.13004638671875, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.12977783203125, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.129205322265625, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.1287548828125, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.1278125, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.126956787109375, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.12619384765625, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.125257568359375, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.124072265625, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.122725830078125, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.121373291015625, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.11966796875, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.117147216796875, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.112685546875, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.09964111328125, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.0591107177734376, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.9717176818847655, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.877101516723633, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.7918622207641604, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.6809605407714843, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.5771609115600587, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.5115488529205323, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.466859149932861, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.4217949676513673, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.3932397317886354, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.3713273763656617, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.351978135108948, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.333733313083649, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.3362937426567076, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.346358757019043, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.355731885433197, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.369878234863281, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.3917134594917298, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.423183461427689, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.450846951007843, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.5066102623939512, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.5902203953266145, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.7811293458938597, "train/loss_047_lr4.3e+01_wd1.0e+00": 4.692243694067002, "train/loss_048_lr5.0e+01_wd1.0e+00": 8.753319165706635, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.02035143321380019, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.020272721438668668, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.020203421525657177, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.02017800506670028, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.020173568706959487, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.020183816226199268, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.02020275474060327, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.020223916503600777, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.020250632409006358, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.020273988721892237, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.02029518201481551, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.0203207601653412, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.020343707287684084, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.020371529352851213, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.020394773865118624, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.020412040683440866, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.020427443590015172, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.020435903719626367, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.020425634756684304, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.02039619073737413, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.020329667553305626, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.020215167826972903, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.020044828881509602, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.01996680007316172, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.020646851425990462, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.022561643011868, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.024292256529442967, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.025827243472449482, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0279722042940557, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.029988165544345975, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.03098270408809185, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.03155199776403606, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.03258304233662784, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.03316362597048283, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.03363619870506227, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.03461225739680231, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.03586018757894635, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.036897196266800165, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.03807076727971435, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0391043156478554, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.04062462117522955, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0420174338389188, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0442790683824569, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.04563993563875556, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.04986693741753698, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.05543716615065932, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.06898462736979127, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.12460262710228562, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.22905453085899352, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.125396966934204, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1249241828918457, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1244847774505615, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1242668628692627, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.124131202697754, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1239631175994873, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.12381649017334, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1236684322357178, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1234819889068604, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1233277320861816, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.123220205307007, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1230931282043457, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1230361461639404, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1229138374328613, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.122668981552124, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1223337650299072, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1215033531188965, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1199769973754883, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1174380779266357, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.1143486499786377, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.109360694885254, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.101703405380249, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.0823144912719727, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.9991228580474854, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.7991702556610107, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.6437151432037354, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.5638034343719482, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.510585308074951, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.4658493995666504, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.4381027221679688, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.428776979446411, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.4256958961486816, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.4267261028289795, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.45265531539917, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.483975648880005, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.501483917236328, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.5186808109283447, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.5236377716064453, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.5123066902160645, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.501605749130249, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.53767466545105, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.5647778511047363, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.543701171875, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.623671531677246, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.609501838684082, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.935370445251465, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.694746971130371, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.062200073827980804, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.062200073827980804, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06275378368401624, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06533776301218161, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06626061277224068, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06755260243632337, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.0664451827242525, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06496862310815799, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06496862310815799, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06902916205241787, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06847545219638243, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.067921742340347, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06736803248431156, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06607604282022887, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06736803248431156, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06699889258028793, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.0681063122923588, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.06921373200442968, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.07069029162052418, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.07308970099667775, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.08324104835732743, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.11129568106312292, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.17386489479512734, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.21207087486157253, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.24067921742340348, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.2561830933923957, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.2648578811369509, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.2676264304171281, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.2678110003691399, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.26947212993724623, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.2663344407530454, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.26356589147286824, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.2574750830564784, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.24953857511997046, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.24455518641565152, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.24898486526393504, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.2440014765596161, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.24326319675156885, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.24197120708748615, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.23791066814322628, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.24492432631967515, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.22720561092654115, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.2427094868955334, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.20321151716500555, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.15946843853820597, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.010166635989491305, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.009828454731538263, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.009634266812901918, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.010004491598389944, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.010157951853865737, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.011061951304570841, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.011262241972493632, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.012311826201816804, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.012466368245576979, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.012300638876336903, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.012656046716347675, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.013618370417859703, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.01323036726528005, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.012438237451895803, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.01168253966282449, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.01092574036594024, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.011148541113129752, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.010936209935857517, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.012010418897063432, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.013227651441449606, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.014465260157462141, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.015185553028574208, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.01792339594565145, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.03858909013288855, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.08472080848448271, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.12802084289803342, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.16254100175158018, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.1782487464079218, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.18719774836238132, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.19369268163534403, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.1967502440880811, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.20135858384208016, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.20223981297495178, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.20291763664245857, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.19286480604696324, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.1863604222928412, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.18229105726290973, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.1881947340161095, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.180851560166044, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.18667143944287953, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.1808099082987286, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.17622118113990246, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.18459746409501346, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.15629858495003532, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.18419075926021047, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.13001553262749255, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.10117844735122777, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 31, "lr_best": 0.0009299999999999999, "wd_best": 0.05, "train/loss_best": 2.466859149932861, "validation/loss_best": 2.4256958961486816, "validation/acc_best": 0.26947212993724623, "validation/f1_best": 0.20135858384208016} +{"epoch": 3, "train/lr": 0.0002100600600600602, "train/loss": 2.9300305140018463, "train/grad": 0.4598119731992483, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.129111328125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.12872802734375, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.12819580078125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.127745361328125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.12742431640625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.126890869140625, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.12635498046875, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.12584228515625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.125078125, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.124287109375, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.12347412109375, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.122430419921875, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.121219482421875, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.1196533203125, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.118072509765625, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.11657470703125, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.114400634765625, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.11138671875, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.106458740234375, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.096568603515625, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.0567303466796876, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.9639564514160157, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.8363410949707033, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.7056872177124025, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.5952470779418944, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.5108316802978514, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.4560215663909912, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.416433115005493, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.3739301490783693, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.3369963359832764, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.3075065755844117, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.2867435789108277, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.2617631816864012, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.25285920381546, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.2567692255973815, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.2585695290565493, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.2604854273796082, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.278930962085724, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.2972251307964324, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.331078490018845, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.3816620826721193, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.416329274177551, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.468030507564545, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.545119194984436, "train/loss_044_lr2.6e+01_wd1.0e+00": 4.79866348028183, "train/loss_045_lr3.1e+01_wd1.0e+00": 6.120603396892547, "train/loss_046_lr3.6e+01_wd1.0e+00": 5.033337173461914, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.020098887938074766, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.020107896765694022, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.02012674924917519, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.020143376076593996, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.02015913979616016, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.02017581003718078, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.020194021710194646, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.020210572364740075, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.02022883438039571, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.020245765126310288, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.020259097404778003, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.020275469473563134, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.02028392016887665, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.020286926752887666, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.020276717264205216, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.020254174675792457, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.020206605633720755, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.020118811065331102, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.019975591376423837, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.019875055025331677, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.020391274956054986, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.022255510678514837, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.025042348057031632, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.027920853393152357, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.029973506135866045, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.030895429737865923, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.031579719725996255, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.032117294752970336, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.03317969954572618, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.03449122720398009, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.03545349584892392, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.03624244784936309, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.03771998457610607, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.03858672730624676, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.039248036155477166, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.03991633134894073, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.04141253632493317, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.04238480343483388, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.042965459264814855, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.044320593383163215, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.047948453444987535, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.04883576987311244, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.05220307672396302, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.05688368909060955, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.14013291090726854, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.132823052033782, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.09217033188790083, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.123690605163574, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.123432159423828, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.123049020767212, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1226484775543213, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1222639083862305, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1216983795166016, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1210451126098633, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.120344638824463, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1193687915802, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.118351936340332, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.117387533187866, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.116020917892456, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.114773988723755, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1130869388580322, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1116180419921875, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1102707386016846, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1083102226257324, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.104464530944824, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.092552900314331, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.048879384994507, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.8770720958709717, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.7073633670806885, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.600766181945801, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.5326952934265137, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.4971091747283936, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.465024471282959, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.4544613361358643, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.456942558288574, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.463923931121826, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.462207555770874, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.462432861328125, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.450800657272339, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.435661554336548, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.4426815509796143, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.5238587856292725, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.6053173542022705, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.642982244491577, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.604593276977539, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.5331692695617676, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.7162041664123535, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.581294059753418, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.6419661045074463, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.7147316932678223, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.669949531555176, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06404577334809892, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06478405315614617, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06681432262827612, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06736803248431156, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06773717238833518, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06736803248431156, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06662975267626431, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06552233296419344, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06626061277224068, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.0681063122923588, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06736803248431156, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06847545219638243, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.0710594315245478, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06939830195644149, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.07179771133259505, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.07124400147655961, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.0710594315245478, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.07327427094868956, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.07881136950904392, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.09929863418235511, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.15005537098560354, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.18180140273163528, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.20930232558139536, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.22757475083056478, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.24215577703949798, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.2530454042081949, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.25599852344038393, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.2530454042081949, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.25544481358434845, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.2572905131044666, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.262827611664821, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.26153562200073827, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.26744186046511625, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.26965669988925806, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.25489110372831303, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.2513842746400886, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.24160206718346253, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.24381690660760427, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.2556293835363603, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.21557770394979697, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.24067921742340348, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.2277593207825766, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.22517534145441123, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.23440383905500184, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.00998542645939571, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.010077001708236609, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.010458831205358836, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.010504091139126759, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.010625351623611464, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.010533354563527405, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.010598881467655199, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.010319282656620105, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.011461673417560436, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.012076272123143564, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.012625547634585907, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.013815097361361434, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.01568238745578316, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.015661033431012144, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.017662859792033306, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.017959841595969517, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.01927997038276134, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.023261410309742252, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.029154800223441676, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.04780218390473338, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.08166423562502763, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.10877537625460698, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.1343182956828866, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.15448820301241653, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.16780111997549804, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.18312258149261962, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.1919559481514553, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.19394131174349097, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.19439582448979106, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.18948413506804462, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.18957413242608892, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.18676072409176134, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.19525009777779054, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.19447080204653058, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.18376134452439521, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.17988015375495525, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.17915737883748253, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.18648973045745978, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.19433891959472527, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.17004858487789387, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.19272802219647256, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.1726553095081008, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.17418134009771455, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.1824382785836219, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 33, "lr_best": 0.00129, "wd_best": 0.05, "train/loss_best": 2.25285920381546, "validation/loss_best": 2.4426815509796143, "validation/acc_best": 0.26965669988925806, "validation/f1_best": 0.19447080204653058} +{"epoch": 4, "train/lr": 0.0002701201201201201, "train/loss": 2.7857808196544647, "train/grad": 0.29787308633327486, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.130889892578125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.130665283203125, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.130076904296875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.1294287109375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.128936767578125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.12808349609375, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.127244873046875, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.126343994140625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.125076904296875, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.12384033203125, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.122525634765625, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.12072998046875, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.11894775390625, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.11586181640625, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.1127685546875, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.1086529541015624, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.098577880859375, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.05788818359375, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.943973388671875, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.8148617553710937, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.669607162475586, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.5701129150390627, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.492931594848633, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.4342172241210935, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.3844219970703127, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.333881149291992, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.297419881820679, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.270648412704468, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.2380331134796143, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.2066484355926512, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.1844563055038453, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.171002912521362, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.1632097470760345, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.159505704641342, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.17108518242836, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.1836104083061216, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.1951170229911803, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.2322453236579896, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.277854106426239, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.34637766122818, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.404474058151245, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.4836335146427153, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.594604766368866, "train/loss_043_lr2.2e+01_wd1.0e+00": 5.283414214849472, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.01992712547071278, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.019938376429490746, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.01995205263607204, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.01996252271812409, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.019971552174538373, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.019982197852805257, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.0199926534621045, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.02000295531004667, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.020014886921271683, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.02002356670796871, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.020027940697036683, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.020024968408979476, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.020010209018364547, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.019959360496141016, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.01987827648408711, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.019772630319930613, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.019640177390538156, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.02003252970986068, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.022173006422817707, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.02507873684167862, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.028245153129100798, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.030083142090588808, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.03099942005239427, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.031525203678756955, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.03225585643202066, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.033497202964499595, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.034417101694270966, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.03511126208119095, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.036381967980414626, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.03748326621949673, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.038193370262160894, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.03910410555079579, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0405917639657855, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.041482284776866434, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.04225152565166354, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.04274938872084021, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.04380562493577599, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.044778312742710116, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.04651179326698184, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.05027842359617352, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.05341824233531952, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.05845049522817135, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.06561822636052966, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.12076489903032779, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1240029335021973, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1238701343536377, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.12363600730896, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1233954429626465, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1231131553649902, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.122666597366333, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1220908164978027, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1213266849517822, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.120211362838745, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.118870973587036, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1174838542938232, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.115304708480835, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1130905151367188, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.109663486480713, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.105461597442627, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.0981407165527344, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.0676369667053223, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.922590732574463, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.7154593467712402, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.6168935298919678, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.5466878414154053, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.5160293579101562, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.479400873184204, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.445300340652466, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.4315450191497803, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.4293911457061768, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.4285573959350586, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.4232842922210693, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.4313418865203857, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.4278573989868164, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.4384379386901855, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.477484941482544, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.5372517108917236, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.5586647987365723, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.6001358032226562, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.5822489261627197, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.594658851623535, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.564364433288574, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.6091713905334473, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.7766852378845215, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.832721710205078, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.898223400115967, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.813643455505371, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06293835363602805, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06293835363602805, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06293835363602805, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06275378368401624, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06441491325212255, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06570690291620525, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06607604282022887, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06662975267626431, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.067921742340347, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06902916205241787, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06902916205241787, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.07179771133259505, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.073827980804725, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.09136212624584718, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.13805832410483573, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.18973791066814322, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.2174234034699151, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.2351421188630491, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.24510889627168697, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.25802879291251385, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.2676264304171281, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.27205610926541157, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.2661498708010336, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.26707272056109266, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.2681801402731635, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.26301218161683276, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.26596530084902176, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.260797342192691, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.25193798449612403, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.24787744555186417, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.24326319675156885, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.24215577703949798, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.23938722775932078, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.24086378737541528, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.2441860465116279, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.2307124400147656, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.21834625322997417, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.22000738279808046, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.2129937246216316, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.21428571428571427, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.007488161795377878, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.00734550129834506, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.007404482972557782, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.007604365574040077, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.007384305676788188, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.008045028270555928, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.008775479332031539, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.009986473042878644, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.011106868676317341, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.012251096950914116, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.012970563210484337, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.014275784833953429, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.01477947041336243, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.01568734706049705, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.018084663495469094, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.020590252546931326, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.03830080130682559, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.07079279086558316, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.11427471274304124, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.1399540129916799, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.16148572897081973, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.17567706241274636, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.19276553904634056, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.20239445257292718, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.2075326279104274, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.20146994993553605, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.20561765589999537, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.20900436644324602, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.20906974953023796, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.21629858418831407, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.21425102210582925, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.2043134031748002, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.19600098882036546, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.1899732482989995, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.18236750190145512, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.17562636729076853, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.18462909168008101, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.18749146201256964, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.18262660683416868, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.1520269496781214, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.1660578966581638, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.1569694509496018, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.16397728500132544, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 24, "lr_best": 0.0003, "wd_best": 0.05, "train/loss_best": 2.3844219970703127, "validation/loss_best": 2.4315450191497803, "validation/acc_best": 0.27205610926541157, "validation/f1_best": 0.2075326279104274} +{"epoch": 5, "train/lr": 0.00029891323817685334, "train/loss": 2.6555644822120668, "train/grad": 0.23340014189481736, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.123701171875, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.123153076171875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.12236572265625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.121612548828125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.1208056640625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.119658203125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.11849853515625, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.1172998046875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.11553955078125, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.1136474609375, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.111885986328125, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.10896484375, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.105703125, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.0985369873046875, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.0812725830078125, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.0281027221679686, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.8846258544921874, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.7073887634277343, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.5818770599365233, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.5056024169921876, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.4358713531494143, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.3812947845458985, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.3275156688690184, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.2819814014434816, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.237683181762695, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.190108828544617, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.1567650508880614, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.1314554452896117, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.097304446697235, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.073410952091217, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.065752799510956, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.0562747967243196, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.0447182762622833, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.045711363554001, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.0764317864179613, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.10575612783432, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.128820662498474, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.176365824341774, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.2134852921962738, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.2728781372308733, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.32869571685791, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.382019671201706, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.4708684623241424, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.171875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.020203626626171173, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.020214268541894852, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.020230229482986032, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.02024454376194626, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.020256133824586867, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.020271843825466932, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.02028674672357738, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.020299627115018665, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.020310251782648267, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.020312653286382557, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.02030795273836702, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.020279382872395217, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.020230107619427146, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.020115589955821633, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.02011030326131731, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.020889258584938942, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.02360148777253926, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.027356405472382904, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.029871771475300193, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.031148828882724047, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.032227174136787655, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.032919507557526234, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.03372830084525049, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.03442558234557509, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.035289630340412256, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.03647224683314562, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.03734414819628, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.03779967662878334, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.03873721303418279, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.03994692709296942, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.041101556252688166, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.04226967269554734, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0435837210342288, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.04463801074773073, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.045882184486836196, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.045949514973908666, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.047771846503019334, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.04897772466763854, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.04973622297868133, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.051598680708557366, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.05455068737268448, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.05611052365973592, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.060613233409821984, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1216907501220703, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.121138334274292, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1202127933502197, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.119347095489502, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.118504762649536, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1173784732818604, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.116138219833374, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1147871017456055, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.113006591796875, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.111069917678833, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.109018087387085, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.105539321899414, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.100990056991577, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.0879039764404297, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.039168119430542, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.8939614295959473, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.700411558151245, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.5851223468780518, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.5079989433288574, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.4701850414276123, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.4451792240142822, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.4321818351745605, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.419421434402466, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.395437240600586, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.366896867752075, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.3659441471099854, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.3775081634521484, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.4173905849456787, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.479789972305298, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.462677478790283, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.4922070503234863, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.5072057247161865, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.5412683486938477, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.6003530025482178, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.6665241718292236, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.685070276260376, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.724618911743164, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.737352132797241, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.7174360752105713, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.7732787132263184, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.8232240676879883, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.852529287338257, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.875063180923462, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06404577334809892, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06441491325212255, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06423034330011074, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06478405315614617, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06589147286821706, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.0664451827242525, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06736803248431156, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06921373200442968, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.07142857142857142, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.08084163898117387, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.10483573274270949, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.14691768180140274, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.18696936138796605, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.2188999630860096, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.24012550756736803, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.25489110372831303, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.26411960132890366, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.2663344407530454, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.2672572905131045, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.27260981912144705, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.28497600590623845, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.2822074566260613, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.27353266888150607, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.2779623477297896, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.2652270210409745, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.268733850129199, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.26208933185677374, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.2622739018087855, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.25452196382428943, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.24363233665559247, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.23034330011074197, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.22609819121447028, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.21631598375784422, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.22148394241417496, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.21539313399778517, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.21668512366186785, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.19785898855666298, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.20450350682908822, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.18180140273163528, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.0067561994226304385, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.006743621363075009, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.006782543874199916, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.007012887955581454, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.007396918204909674, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.007335148805843368, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.007456336975984714, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.00838101762545066, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.009389418649307443, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.010493501551974734, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.011360087420357287, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.013413004023752048, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.014816717082694266, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.022913916312130873, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.044668772567239855, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.0700366237718562, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.1036178383154373, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.1365043670945324, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.1629531579730444, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.1814920829247321, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.19522138008055678, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.1978016951354491, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.1988555670356644, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.20330013825703352, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.21435956293708777, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.21504679018690584, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.20834308327022535, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.2144494204698475, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.20155615506312732, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.2091459606382319, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.20796902416351334, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.21354439537129707, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.20747562120041738, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.18956283603606672, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.17721537029509019, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.18518227685227903, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.17984151935755163, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.1804283271474155, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.17226367800005174, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.1804338412423483, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.16465868443284234, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.1670886793667878, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.15652306389747786, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 24, "lr_best": 0.0003, "wd_best": 0.05, "train/loss_best": 2.237683181762695, "validation/loss_best": 2.366896867752075, "validation/acc_best": 0.28497600590623845, "validation/f1_best": 0.21435956293708777} +{"epoch": 6, "train/lr": 0.0002924170901991409, "train/loss": 2.595023354291916, "train/grad": 0.2433805973827839, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.126966552734375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.1262451171875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.125062255859375, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.12395751953125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.12285400390625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.121278076171875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.11964599609375, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.117791748046875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.11525634765625, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.11260009765625, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.1097021484375, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.10427978515625, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.095406494140625, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.051812744140625, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.9112478637695314, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.7471745300292967, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.617327117919922, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.5196025466918943, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.4427026748657226, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.387873287200928, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.331292953491211, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.281217641830444, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.2248976373672487, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.178336639404297, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.1367907404899595, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.09117871761322, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.058936927318573, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.0335740554332733, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.9982036972045898, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.9748942244052887, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.962513427734375, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.9551824247837066, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.9599860227108001, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.9732229709625244, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.003174689412117, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.0401883935928344, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.0732250380516053, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.108195342421532, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.1606277257204054, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.2423070287704467, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.3109570187330246, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.3645063424110413, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.462700630426407, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.171875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.020178324235603215, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.0201825884450227, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.02018782281316817, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.020192029187455773, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.020194333787076177, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.02019475185312331, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.02019295352511108, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.0201854094536975, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.020166765018366277, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.020132728363387288, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.020084733446128666, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.01997502641286701, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.019841735269874334, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.02018463963177055, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.022684959098696708, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.026133240861818195, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.028938983641564844, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.030757666397839785, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.03208034975454211, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.032891329005360605, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.03352541098371148, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.034131709160283207, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.035125329047441485, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.03590695100836456, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.036637618783861396, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.037707448843866585, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.03861214390024543, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.03923790877684951, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.040513509903103116, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.041484556794166565, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.04261076530441642, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.04379439067095518, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.045515247266739604, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.04676334390416741, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.04784428833052516, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.04830194776877761, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.049937008190900085, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.050015721935778856, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.051203237064182755, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.05432064272463322, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.05700640074908733, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.058225902169942854, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.06417397065088153, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1210548877716064, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1204755306243896, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1195285320281982, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1186394691467285, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.117807626724243, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1166763305664062, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.115342617034912, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1138601303100586, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1117913722991943, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.109278440475464, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1061980724334717, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.0988428592681885, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.0814685821533203, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.966407537460327, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.744441032409668, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.624713182449341, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.53181529045105, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.4711387157440186, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.4405629634857178, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.425387382507324, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.415245294570923, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.414060115814209, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.4211463928222656, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.4298460483551025, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.4239416122436523, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.436638116836548, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.463653087615967, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.505686044692993, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.539370059967041, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.558648109436035, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.577138662338257, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.5751895904541016, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.6245734691619873, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.6526412963867188, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.6386260986328125, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.666243553161621, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.7451553344726562, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.7145979404449463, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.747973680496216, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.7754862308502197, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.7653512954711914, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.724592924118042, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.8236732482910156, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06459948320413436, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.0664451827242525, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.067921742340347, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.0695828719084533, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.07216685123661867, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.07364341085271318, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.07788851974898486, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.08951642672572906, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.13418235511258766, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.18604651162790697, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.21631598375784422, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.24289405684754523, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.2589516426725729, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.26707272056109266, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.27464008859357697, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.27500922849760057, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.2763012181616833, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.2733480989294943, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.26356589147286824, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.26854928017718716, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.266703580657069, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.26578073089701, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.257844222960502, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.25858250276854927, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.2517534145441122, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.25212255444813586, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.2410483573274271, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.2425249169435216, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.2397563676633444, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.24178663713547435, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.2395717977113326, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.22277593207825766, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.23661867847914358, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.22129937246216316, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.21797711332595054, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.21705426356589147, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.22739018087855298, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.22849760059062385, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.007969047740213625, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.007977561380634626, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.008033825152679116, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.008367128128634011, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.008542328853083453, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.010060803767068572, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.011871062230162127, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.01342399237221563, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.01595347137681332, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.018688860322970076, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.021158244776181067, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.02656886316918673, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.035172253217070175, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.06335782823080933, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.10720349587380973, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.1385057147848765, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.16922137132811713, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.1876270023209731, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.19990017228204401, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.20948806597617844, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.21288778572952646, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.2161155557811784, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.2157849858388998, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.2080885822975818, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.21269731560862784, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.20872046744304273, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.20510958657732178, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.19905151246183198, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.20242818186536302, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.19687696501814533, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.1992872633566618, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.1951079555640852, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.19794234743730396, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.19593972150204678, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.199785140926115, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.1933858340001869, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.19223162231876376, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.1962687466175116, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.182085324742852, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.18170237502957445, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.1823285252530884, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.17764067290537747, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.17807527555273073, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 21, "lr_best": 0.00018299999999999998, "wd_best": 0.05, "train/loss_best": 2.281217641830444, "validation/loss_best": 2.414060115814209, "validation/acc_best": 0.2763012181616833, "validation/f1_best": 0.2161155557811784} +{"epoch": 7, "train/lr": 0.00027969249556793234, "train/loss": 2.516128534078598, "train/grad": 0.245378035902977, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.12549072265625, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.12462646484375, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.123160400390625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.121661376953125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.120211181640625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.118284912109375, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.116046142578125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.113529052734375, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.10998779296875, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.105810546875, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.100535888671875, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.085968017578125, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.04080322265625, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.8432888793945312, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.6658880615234377, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.56799560546875, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.477334251403809, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.4012433433532716, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.3357852363586424, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.283817768096924, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.2292978668212893, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.1789651679992676, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.1199314117431642, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.0703646087646486, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.027740783691406, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.9755567216873169, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.942676204442978, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.9169577050209046, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.8834325277805328, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.859623265862465, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.852326484322548, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.8524214434623718, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.8451708287000657, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.852783973813057, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.8724351912736892, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.9185011011362076, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.966226492524147, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.0226229494810104, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.0727035570144654, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.1151926350593566, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.198675087094307, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.2165735965967177, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.2874023205041887, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.171875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.019689043541438876, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.019692345410585402, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.01969610509928316, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.019697301047854124, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.019696085113100708, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.019690413046628236, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.01967862873338163, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.019660026612691582, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.019619601909071208, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.019557281085290014, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.01947237961459905, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.019350618459284305, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.019791982076130806, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.02328636241145432, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.027253286652266978, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.029193268110975622, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.030836146073415876, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.032172409147024156, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.03308876005001366, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.03391566484235227, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.03462020834907889, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.03544252332299948, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.036591382753103974, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.037580123292282226, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.03814195290207863, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.03902686189860106, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.03996571376919746, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.04094876701012254, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.04285301698371768, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0441099601611495, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.04493881506845355, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0460991670563817, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.04685411617159843, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.04773939350619912, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0484126734547317, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.04899354742839932, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.050448784157633784, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.05137098401784897, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.052077722307294606, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.05197670185938477, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.05546007765457034, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.053096344266086816, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.056805671006441114, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1202311515808105, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1195709705352783, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1185264587402344, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1174986362457275, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.116499423980713, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1151082515716553, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.113539457321167, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.111776828765869, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.109163284301758, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.105583667755127, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.0999789237976074, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.077009677886963, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.9844961166381836, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.734947443008423, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.605468273162842, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.524287223815918, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.465132236480713, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.429269790649414, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.4107186794281006, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.403419017791748, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.399367570877075, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.4107089042663574, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.4288480281829834, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.44170880317688, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.4448163509368896, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.4597556591033936, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.4858551025390625, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.5368404388427734, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.6060173511505127, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.6334171295166016, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.677036762237549, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.687068223953247, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.699451446533203, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.7339963912963867, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.767979621887207, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.814223527908325, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.827413320541382, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.8305113315582275, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.8621301651000977, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.9283132553100586, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.8669958114624023, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.789350748062134, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.7773492336273193, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06404577334809892, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.0651531930601698, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06626061277224068, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06755260243632337, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.07013658176448874, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.07124400147655961, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.07124400147655961, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.07161314138058324, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.07308970099667775, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.07585825027685493, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.08564045773348099, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.12440014765596161, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.18992248062015504, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.21816168327796234, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.23920265780730898, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.25452196382428943, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.26836471022517533, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.2751937984496124, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.27722406792174237, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.27851605758582504, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.2727943890734588, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.26744186046511625, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.26854928017718716, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.2663344407530454, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.2643041712809155, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.2574750830564784, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.25544481358434845, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.2571059431524548, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.2561830933923957, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.24953857511997046, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.24363233665559247, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.24197120708748615, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.24510889627168697, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.24898486526393504, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.23569582871908454, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.23292727943890734, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.2222222222222222, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.21945367294204504, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.20930232558139536, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.2157622739018088, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.22702104097452935, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.23606496862310816, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.009077701215634856, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.00941483271710592, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.01027511649209452, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.011361052126728171, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.012713168224343077, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.014811427847897246, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.015432315026088278, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.015423157617954849, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.01559092712031634, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.016137707910434014, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.01704349679200314, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.022876960351644732, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.05192403368709991, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.10909459697094605, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.13747494882480385, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.16317634639861164, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.1823442953091162, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.20081721811098086, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.21152386042350302, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.21505241353697205, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.21861456627007012, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.21603666345666125, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.21254710647098415, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.2158956323930076, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.21724728932042295, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.2185502463632949, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.2124855343982878, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.20855499807970937, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.20271647738384765, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.20441738585325656, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.1995132497633546, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.19888318825611315, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.1972704594755554, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.19082747424872995, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.19552652890958655, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.1830156242997357, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.1772790962742902, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.1738039641577708, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.1667895958045631, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.1663290627443236, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.17074483948057928, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.17428366671115425, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.18445664432553496, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 20, "lr_best": 0.000156, "wd_best": 0.05, "train/loss_best": 2.2292978668212893, "validation/loss_best": 2.399367570877075, "validation/acc_best": 0.27851605758582504, "validation/f1_best": 0.21861456627007012} +{"epoch": 8, "train/lr": 0.0002612959497061927, "train/loss": 2.4516263151168824, "train/grad": 0.2550258560478687, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.12135009765625, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.120311279296875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.118662109375, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.117098388671875, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.11535888671875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.113133544921875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.110594482421875, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.107567138671875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.1032470703125, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.096959228515625, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.0865509033203127, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.0371881103515626, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.8871820068359373, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.662963104248047, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.5500518035888673, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.4727835845947266, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.401441993713379, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.3352471160888673, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.2713794708251953, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.2152395820617676, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.1557761573791505, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.1000159931182862, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.0348028898239137, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.98253533244133, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.9448239696025849, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.8914012706279755, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.8522445797920226, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.8205046510696412, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.7766503858566285, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.751492790579796, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.7466207176446915, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.7308123582601547, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.7331368511915206, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.731324155330658, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.7565694624185562, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.8114631247520447, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.865476450920105, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.9020736193656922, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.9632761281728746, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.0388289481401443, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.1113137340545656, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.15263188123703, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.2003563183546064, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.171875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.020351146208122374, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.02035638310946524, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.020360399237833917, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.020364050501957536, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.020363506521098317, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.020357084604911507, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.020343980388715863, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.020317214303649963, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.020260676937177778, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.02016911083832383, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.020073574134148658, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.020504783894866704, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.023025451013818383, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.02808833811432123, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.030528139201924206, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.03193178271874785, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.03312369699589908, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.03408471155911684, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.03496477220207453, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.035911483354866505, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.03653998845256865, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.037210976239293814, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0382057414855808, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.039208065327256916, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.04000964816659689, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.04140791902318597, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.04260041762143373, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.04350925931707025, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.04504760099574923, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.04585286827757955, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.04683175295591355, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.04794438786804676, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.049438619967550036, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.049991264306008816, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.05065565340220928, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.051118394248187544, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.05255412520840764, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.05144146390259266, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.05178272685036063, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.053633615858852866, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.055455103367567066, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.05382573487237096, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.05560139019042253, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1195602416992188, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.118708848953247, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.117330312728882, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.115980863571167, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1146113872528076, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.112717866897583, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1104516983032227, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.107710599899292, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.103240966796875, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.095750093460083, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.0800232887268066, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.9895544052124023, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.7945072650909424, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.6169257164001465, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.523865222930908, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.472323417663574, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.4406540393829346, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.426103353500366, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.4254071712493896, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.430741310119629, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.4401259422302246, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.4595601558685303, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.470365047454834, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.4688448905944824, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.4692580699920654, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.5005476474761963, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.5296990871429443, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.5539252758026123, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.5836923122406006, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.6260058879852295, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.6731066703796387, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.7096755504608154, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.7026805877685547, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.7850184440612793, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.883254051208496, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.8519153594970703, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.8608665466308594, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.9391326904296875, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.928776502609253, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.007032871246338, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.9883904457092285, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.835242748260498, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.941485643386841, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06459948320413436, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06423034330011074, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06607604282022887, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06736803248431156, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06866002214839424, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.07050572166851236, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.07272056109265411, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.0753045404208195, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.08047249907715023, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.0917312661498708, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.12458471760797342, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.16980435585086748, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.2146548541897379, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.23883351790328536, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.25193798449612403, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.26264304171280917, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.26799557032115173, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.2705795496493171, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.26799557032115173, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.2661498708010336, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.25987449243263194, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.25655223329641935, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.257844222960502, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.2576596530084902, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.25359911406423036, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.24935400516795866, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.24880029531192321, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.24806201550387597, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.2467700258397933, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.2497231450719823, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.24640088593576967, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.2556293835363603, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.24049464747139165, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.2264673311184939, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.2279438907345884, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.22591362126245848, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.20985603543743078, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.20985603543743078, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.20228866740494647, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.20136581764488742, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.22129937246216316, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.20837947582133629, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.009004121273794683, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.009865059423526756, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.010443385543605363, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.013271314129594364, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.015240502934358914, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.016569743235967122, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.01766333543047629, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.019201178080521946, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.02077798488102999, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.024641773036964104, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.037241749758534975, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.058774413951682807, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.09186486973557263, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.1367610114131569, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.1666835432112036, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.1823866616895767, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.19696764013206688, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.2070994332236944, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.21241059174819965, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.21221776782376664, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.21019638938235105, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.20534898162686857, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.20436214309553125, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.20506128459274184, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.2014350232815166, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.2006746214528069, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.19740636262104724, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.20273716788272123, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.20182200330364544, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.19999569148235066, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.1964467476485008, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.19495244523202293, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.20316593010237674, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.18917770609674708, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.17881067006747828, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.18061399377890094, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.18171189746357264, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.1723181563600599, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.17510431563346204, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.15532177843838638, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.1475666021585317, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.17129335392913878, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.1572571338819774, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 18, "lr_best": 0.00011399999999999999, "wd_best": 0.05, "train/loss_best": 2.2713794708251953, "validation/loss_best": 2.4254071712493896, "validation/acc_best": 0.2705795496493171, "validation/f1_best": 0.21241059174819965} +{"epoch": 9, "train/lr": 0.00023803200426111704, "train/loss": 2.3990626883506776, "train/grad": 0.25825693011283873, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.1188037109375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.117523193359375, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.115556640625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.11348388671875, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.1116357421875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.108831787109375, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.105682373046875, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.101953125, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.09571533203125, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.0848760986328125, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.05957275390625, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.92580322265625, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.727292022705078, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.5730622100830076, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.477575378417969, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.411871223449707, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.3484404563903807, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.28525447845459, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.221025514602661, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.162176694869995, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.1014969110488892, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.0443143701553343, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.981565809249878, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.9266774916648866, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.8849582934379578, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.8246218419075013, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.7756398433446885, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.7388360458612442, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.6873413926362992, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.6608922934532167, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.6455510544776917, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.6291628563404084, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.6254221451282502, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.6363798946142196, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.6634198564291, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.7195213866233825, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.756455027461052, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.8163188183307648, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.8940657126903533, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.9680876922607422, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.0425063294172285, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.086883276104927, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.1465698605775834, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.171875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.020242256950587033, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.020243177907541394, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.020244070645421743, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.020242410218343138, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.020235460852272808, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.020222937604412437, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.020198618862777948, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.020155261675827204, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.020071305772289633, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.019965533246286214, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.020058025219477714, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.02214656675234437, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.026150750080123544, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.02980458864942193, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.031597924763336775, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.03265918346121907, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.033544202717021104, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.03442273230291903, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.0353836646489799, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.03646656611934304, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.037214746698737144, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.03795920638367534, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.03900854142382741, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0400223689340055, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.04066177541390061, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.042030580267310144, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.043191314358264205, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.044072957187891004, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.04542088471353054, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.04680137408897281, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.047836774047464135, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.049049899931997064, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.04970473548397422, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.051419977732002735, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.05159026555716992, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.051337802000343796, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.05250565720722079, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.05189823791384697, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.052763232737779615, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.053756699971854685, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.055291714146733284, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.053973359242081645, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.05539335323497653, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.118640184402466, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1177127361297607, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.116241693496704, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.114776134490967, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.113309383392334, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.111236095428467, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1086504459381104, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.105238676071167, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.0988214015960693, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.084721326828003, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.0431864261627197, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.85585880279541, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.6775782108306885, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.54642915725708, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.4780757427215576, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.444171667098999, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.421847343444824, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.4094204902648926, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.4068803787231445, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.4050614833831787, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.4115514755249023, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.4300150871276855, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.440828800201416, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.451845169067383, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.4792747497558594, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.516233444213867, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.551438331604004, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.5976359844207764, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.6357860565185547, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.6853129863739014, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.718681573867798, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.766036033630371, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.775468587875366, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.8816840648651123, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.909742593765259, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.9305732250213623, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.9773991107940674, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.9619557857513428, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.925288438796997, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.8428261280059814, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.8838491439819336, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.7837486267089844, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.732595920562744, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06441491325212255, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06699889258028793, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06921373200442968, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.07087486157253599, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.07087486157253599, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.073827980804725, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.0753045404208195, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.07899593946105574, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.08600959763750461, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.10852713178294573, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.16076042820228867, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.19582871908453303, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.2336655592469546, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.24935400516795866, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.2617201919527501, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.26799557032115173, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.2705795496493171, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.27002583979328165, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.27353266888150607, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.2705795496493171, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.26448874123292726, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.26245847176079734, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.26448874123292726, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.26116648209671467, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.2511997046880768, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.24307862679955702, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.24031007751937986, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.23809523809523808, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.2351421188630491, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.23108157991878922, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.2233296419342931, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.23569582871908454, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.22259136212624583, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.2235142118863049, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.22849760059062385, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.22277593207825766, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.21410114433370248, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.2207456626061277, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.2292358803986711, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.2144702842377261, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.21631598375784422, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.2262827611664821, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.00914539930306924, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.009864659616876008, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.012061184638925873, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.014149250455610302, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.01629025477288717, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.017430780350933126, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.019636538881340367, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.021806585591849167, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.023953702984561034, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.029939303119788582, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.048729703108445065, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.07922564941574085, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.11474798758182479, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.152268115737795, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.1724560125534423, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.18765117676456247, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.1991726736590291, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.205282121591141, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.20598606759968616, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.2113397085093023, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.21191004143461137, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.211177103935413, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.21186635544106724, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.2179621036796954, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.21619901695331187, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.21167271712953153, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.2078910154557763, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.2084725271730442, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.21253948851700277, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.20844174152341907, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.20471819990158535, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.19823624877566137, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.20023807586480016, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.18493901091944998, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.18517161004083063, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.1845630478858075, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.1846255736323171, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.1701816514947324, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.17575861377328886, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.18206138831737975, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.17752419277802445, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.1816237692930701, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.19127423099652482, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 19, "lr_best": 0.00013199999999999998, "wd_best": 0.05, "train/loss_best": 2.162176694869995, "validation/loss_best": 2.4050614833831787, "validation/acc_best": 0.27353266888150607, "validation/f1_best": 0.2113397085093023} +{"epoch": 10, "train/lr": 0.00021091808096876188, "train/loss": 2.3384161865711213, "train/grad": 0.2574226551502943, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.11887451171875, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.117557373046875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.11528564453125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.11314453125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.110841064453125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.107799072265625, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.104127197265625, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.099471435546875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.090748291015625, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.07084228515625, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.011195068359375, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.799097595214844, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.64084716796875, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.5095450592041018, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.4253379821777346, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.36619441986084, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.30415132522583, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.2383966064453125, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.169241676330566, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.1077517318725585, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.0451094102859497, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.9878239583969117, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.9212300157546998, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.8597840547561646, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.8111507081985474, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.7414650565385819, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.6897420024871825, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.6503978973627091, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.590056256055832, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.5518306231498717, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.5278086042404175, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.515799467563629, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.5068716090917587, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.5125780349969864, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.5399530404806137, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.5944762361049651, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.6493931269645692, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.7142554014921187, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.7692082053422928, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.8468213874101638, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.9165889018774032, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.9661654978990555, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.0221858406066895, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.171875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.019928657584823668, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.0199283105134964, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.019926905347965658, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.019921413958072662, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.019912486663088202, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.01989384656306356, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.01985995863098651, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.01980525182094425, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.01970781958196312, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.01967510808259249, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.020391602334566414, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.024009449211880564, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.027860963074490427, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.030617372998967766, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.03220318167470396, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.03313727281987667, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.034010274009779094, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.03494495755061507, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.03602136886678636, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.03704528806731105, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.037645464427769185, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.03832434209063649, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.039274849221110346, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0404063437320292, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.04108868943527341, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.04237442776560783, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.04355367090553045, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0446317975781858, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.04608113467693329, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.046890615671873095, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.047646009214222435, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.04890385653823614, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.05009635537862778, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.051763226930052045, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.05272143078967929, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.05278955982998013, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.05311345521360636, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.05263851191848516, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.05232176106423139, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.05123255182057619, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.05137081652879715, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.050790087282657624, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.05179474126547575, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1182923316955566, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1173317432403564, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1157991886138916, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.11423659324646, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1126646995544434, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1103038787841797, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1072559356689453, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.102888345718384, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.093292236328125, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.065864324569702, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.978078842163086, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.748777151107788, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.615926504135132, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.5074000358581543, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.4595870971679688, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.436770439147949, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.4227077960968018, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.4141862392425537, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.411862373352051, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.4095542430877686, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.4206202030181885, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.4444870948791504, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.4667365550994873, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.4913272857666016, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.5382001399993896, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.579572916030884, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.6337156295776367, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.7054929733276367, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.784151077270508, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.8537216186523438, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.886061668395996, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.8863866329193115, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.914785861968994, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.9189605712890625, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.0132246017456055, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.150056838989258, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.1301276683807373, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.068932294845581, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.098233461380005, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.021589756011963, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.0100972652435303, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.909538507461548, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.9849843978881836, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06404577334809892, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06496862310815799, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06662975267626431, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.067921742340347, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06847545219638243, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.0695828719084533, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.07124400147655961, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.073827980804725, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.07918050941306755, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.09265411590992986, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.12550756736803248, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.1864156515319306, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.21760797342192692, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.2427094868955334, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.2567368032484312, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.2652270210409745, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.27113325950535255, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.2678110003691399, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.2698412698412698, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.2731635289774825, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.26578073089701, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.2622739018087855, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.25692137320044295, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.25489110372831303, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.25212255444813586, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.24732373569582872, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.23994093761535623, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.23237356958287192, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.22535991140642303, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.22388335179032853, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.22812846068660023, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.2321889996308601, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.22849760059062385, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.23274270948689554, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.2233296419342931, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.21557770394979697, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.2102251753414544, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.19878183831672203, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.21502399409376152, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.20228866740494647, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.20616463639719454, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.21114802510151348, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.20025839793281655, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.009606026491682523, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.01084219381118122, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.013317502848197486, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.014537341299460294, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.015052572085442367, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.01616359883800451, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.017776106586643723, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.019916810575543294, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.02261444460317236, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.03540047300422561, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.05709249134422833, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.10804295321416318, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.13528156579213804, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.16665628385500933, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.18386542983786244, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.19515648636895208, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.20616239541979686, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.20668799838393567, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.21084266889534872, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.2143452472633883, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.20991311132398405, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.2110586299196482, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.20729927344990676, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.20582209057328735, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.2016078314957603, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.2005219923891857, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.19652106380013878, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.19459050199446168, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.18986145438599644, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.19035443228014, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.19082191572153473, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.19541299828877592, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.19144558219995997, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.1909583950121652, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.18290285984427965, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.17453052657329146, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.17163881656336014, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.1641575600552374, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.17253065516236818, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.16771216212201123, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.16302030297134287, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.17522615884569412, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.1621534565034183, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 19, "lr_best": 0.00013199999999999998, "wd_best": 0.05, "train/loss_best": 2.1077517318725585, "validation/loss_best": 2.4095542430877686, "validation/acc_best": 0.2731635289774825, "validation/f1_best": 0.2143452472633883} +{"epoch": 11, "train/lr": 0.00018113997589164516, "train/loss": 2.2958590030670165, "train/grad": 0.2635741437971592, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.12268798828125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.121224365234375, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.118955078125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.116611328125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.1142431640625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.110994873046875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.106846923828125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.10103515625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.0887164306640624, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.05298095703125, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.946863098144531, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.718899841308594, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.596108245849609, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.476211624145508, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.3972337532043455, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.338739776611328, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.275044250488281, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.207316493988037, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.1351060104370116, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.070343728065491, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.0049100589752196, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.9442094492912292, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.8760631251335145, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.8115070521831513, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.7661441278457641, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.692208104133606, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.6354145139455796, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.5876279610395432, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.5291088807582855, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.4899977499246597, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.461182781457901, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.4282267916202545, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.4187790495157242, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.4145331823825835, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.4295849034190178, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.4778070646524428, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.5328485482931138, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.617431684732437, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.6942493027448655, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.7617274397611618, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.8259541130065917, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.8956296676397324, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.9545349866151809, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.171875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.02004770849365741, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.020044788499362767, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.020040320469997822, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.020033664307557045, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.020023377235047518, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.02000271955970675, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.019965448854491114, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.019900419786572456, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.01980425193440169, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.020025693089701237, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.02164898901246488, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.02616551745682955, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.029243334122002126, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.031722549507394435, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.03316081467084587, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.0340168768633157, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.03492604047060013, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.03594064415432513, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.03709308687597513, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.03809921832755208, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.03876004890538752, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.03944529756903648, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.04044057099148631, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.04166162030771375, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.042555177435278896, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.04400692690163851, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.04531849879771471, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.04637047978118062, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.04806729441508651, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.049403892531991005, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.05024537030607462, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.05105654593557119, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.05213896019384265, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.05274229034781456, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.05282314017415047, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.05321089394390583, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.05339166482910514, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0535035564750433, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.05337439708411693, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0516341301985085, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.051325369626283646, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.05138983823359013, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.05066185256466269, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.11785626411438, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.116769313812256, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1149773597717285, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1131651401519775, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1113133430480957, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1085331439971924, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.104830741882324, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.0991885662078857, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.0846898555755615, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.03483510017395, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.9011473655700684, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.6861486434936523, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.577972173690796, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.4896676540374756, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.455106496810913, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.438849925994873, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.431267738342285, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.4262444972991943, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.42364501953125, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.420942544937134, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.43353533744812, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.4568798542022705, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.470881462097168, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.481327533721924, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.5255520343780518, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.5674023628234863, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.627073287963867, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.6822938919067383, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.7199079990386963, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.800591230392456, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.851266622543335, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.897806406021118, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.927324056625366, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.9228708744049072, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.009183883666992, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.0372352600097656, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.0208451747894287, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.9434032440185547, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.9488136768341064, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.8126087188720703, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.853114128112793, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.728978157043457, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.7245967388153076, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.0651531930601698, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06589147286821706, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06755260243632337, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06921373200442968, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.07069029162052418, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.07087486157253599, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.07327427094868956, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.07585825027685493, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.08711701734957548, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.11443337024732374, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.14857881136950904, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.19767441860465115, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.22609819121447028, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.2497231450719823, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.26245847176079734, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.2707641196013289, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.27260981912144705, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.2691029900332226, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.2709486895533407, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.2676264304171281, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.26411960132890366, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.2633813215208564, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.257844222960502, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.2582133628645257, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.2558139534883721, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.2541528239202658, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.24732373569582872, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.2482465854558878, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.24621631598375784, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.2467700258397933, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.24787744555186417, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.24289405684754523, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.24049464747139165, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.23385012919896642, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.2368032484311554, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.22240679217423404, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.22831303063861202, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.23274270948689554, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.2159468438538206, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.2264673311184939, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.2159468438538206, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.2369878183831672, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.2334809892949428, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.010763907210996876, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.011965592657978101, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.013357733817588832, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.014948832487128501, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.01652244842780767, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.016943675430757133, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.019622486240348486, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.022825806232560527, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.0333083257706648, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.05253836123623012, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.07067584834002982, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.11600098963243854, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.14455595712591887, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.17181943898635788, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.18903235332429716, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.20054574448050919, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.20712526259123024, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.20549426795123193, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.21172794200011355, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.21183598457171568, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.21182424889200813, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.21463061605129485, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.21341785599440777, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.21822941192397086, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.21469287721929534, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.21619101762071521, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.20966355664329825, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.21094217317685293, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.20957272037057142, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.20824768762500132, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.20489279534443425, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.2014731926483633, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.2015186833730803, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.19656570152507455, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.19806765071806312, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.18571010513488462, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.18596562126285957, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.18937507412849638, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.1907604235152365, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.1992882499477923, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.1881026782851111, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.20141760464865013, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.20086049409593557, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 16, "lr_best": 8.1e-05, "wd_best": 0.05, "train/loss_best": 2.275044250488281, "validation/loss_best": 2.431267738342285, "validation/acc_best": 0.27260981912144705, "validation/f1_best": 0.20712526259123024} +{"epoch": 12, "train/lr": 0.0001499999999999999, "train/loss": 2.2296266478300093, "train/grad": 0.2611022566258907, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.11473388671875, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.113138427734375, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.11041259765625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.107822265625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.1050146484375, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.100970458984375, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.09583740234375, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.088194580078125, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.0695440673828127, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.0074212646484373, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.858285217285156, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.6491583251953124, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.540397491455078, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.4303916931152343, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.3578864479064943, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.3014748382568357, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.2381725025177004, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.168709578514099, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.0938977193832398, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.0271241641044617, "train/loss_020_lr5.2e-01_wd1.0e+00": 1.9586810994148254, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.8955761921405792, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.8223858761787415, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.7511362636089325, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.695657232403755, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.6173559772968291, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.5527604061365128, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.4948477017879487, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.41514728307724, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.3618989700078965, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.335712392926216, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.3045299047231673, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.2806970727443696, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.267265477180481, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.2772960478067399, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.319499071240425, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.3588936281204225, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.4438302576541902, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.5298960030078887, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.6401989144086837, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.7012002456188202, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.7781397902965546, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.8392644715309143, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.171875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.020022622984834017, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.020022267447784542, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.020018952898681164, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.02001359940972179, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.020000774720683692, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.019975851462222634, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.019930143477395176, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.019854790745303035, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.019792415187694132, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.020442644678987563, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.0228289015032351, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.02769182845018804, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.03027832793071866, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.032616012236103414, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.033897728640586135, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.03468953778035939, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.03557723449543118, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.03658651416189969, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.037731989677995445, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.03871137967333198, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.039323197808116675, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.040002537965774534, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.04095129188150168, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.04203496465459466, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.042716977056115865, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.04384651495143771, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.04495655095204711, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.04594157898798585, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.04721042772755027, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.048271721825003625, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.049264123532921075, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.05023119937628508, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.05109459703788161, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.05192568764090538, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.051668488327413796, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.05169076308608055, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.05179568868130446, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.05188626242801547, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.05153119781985879, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.050764640402048825, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.04993564689531922, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.04978629199787974, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.04938126193359494, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.117694616317749, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.116605281829834, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.114790916442871, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1129207611083984, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1109893321990967, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1079604625701904, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.103764772415161, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.0967960357666016, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.0763394832611084, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.0000479221343994, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.8405532836914062, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.649319887161255, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.5521562099456787, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.478590488433838, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.4522464275360107, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.44088077545166, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.437267303466797, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.435875415802002, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.438619375228882, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.446997880935669, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.470245599746704, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.5058324337005615, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.536395311355591, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.5449843406677246, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.5921037197113037, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.640979051589966, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.709505558013916, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.7880992889404297, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.837925910949707, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.927006483078003, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.977308988571167, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.9780943393707275, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.0189340114593506, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.0736775398254395, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.1328012943267822, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.1984548568725586, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.2065889835357666, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.077655553817749, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.0763583183288574, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.9802932739257812, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.989995241165161, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.856367826461792, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.9202561378479004, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06423034330011074, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06496862310815799, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06607604282022887, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06718346253229975, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.067921742340347, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06921373200442968, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.07142857142857142, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.07511997046880768, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.09080841638981174, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.12329272794389073, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.16039128829826504, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.20671834625322996, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.22886674049464747, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.24916943521594684, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.25950535252860835, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.2617201919527501, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.2661498708010336, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.26504245108896274, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.2663344407530454, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.26375046142488, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.25507567368032485, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.2513842746400886, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.24935400516795866, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.2515688445921004, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.2511997046880768, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.24861572535991142, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.24898486526393504, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.2397563676633444, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.2440014765596161, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.24178663713547435, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.24178663713547435, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.2517534145441122, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.2425249169435216, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.2364341085271318, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.23145071982281284, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.22702104097452935, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.21705426356589147, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.22369878183831673, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.2320044296788483, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.22997416020671835, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.21926910299003322, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.22886674049464747, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.2188999630860096, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.008752385218608738, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.009682201936808398, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.01113641969562608, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.012709282938424623, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.013368574337580416, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.01516693851374839, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.01765891954708727, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.021578661051880794, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.037234536498317684, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.05643027988481025, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.08028445600635019, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.12375461961193485, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.14646449153442972, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.17266006984493795, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.18713164097104948, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.1934100762856573, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.2021249986942427, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.20509582763308817, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.20720456435280488, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.20722119404392117, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.202314066120831, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.20162734390454648, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.20079971091259183, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.20411532645595284, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.20157041947789336, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.19721658288132107, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.19891792373152536, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.19097784729480125, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.19005385766555574, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.1880096813158144, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.1877567759024521, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.20249151506373111, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.19780545474739952, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.19256222461344652, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.19224719758609857, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.18247141220578045, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.175881187515014, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.18671892925162115, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.19680998110956027, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.1933057775623682, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.18448674332543616, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.18931615804600888, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.18411843608227665, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 18, "lr_best": 0.00011399999999999999, "wd_best": 0.05, "train/loss_best": 2.0938977193832398, "validation/loss_best": 2.438619375228882, "validation/acc_best": 0.2663344407530454, "validation/f1_best": 0.20720456435280488} +{"epoch": 13, "train/lr": 0.00011886002410835478, "train/loss": 2.181631699204445, "train/grad": 0.2597374845296144, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.11807861328125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.116326904296875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.113369140625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.11055908203125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.10756103515625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.103345947265625, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.09764892578125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.0887371826171877, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.064244384765625, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.97822021484375, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.8094993591308595, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.6230953216552733, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.5189521408081053, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.4132201576232912, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.3431223487854003, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.287348051071167, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.223701124191284, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.1527694606781007, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.0758878135681154, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.0056942224502565, "train/loss_020_lr5.2e-01_wd1.0e+00": 1.9346876311302186, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.868136715888977, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.790166289806366, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.7124888217449188, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.6507949578762053, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.5647661304473877, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.4907004004716873, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.4313133209943771, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.3472821044921874, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.2917126327753068, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.2448697865009308, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.197978668808937, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.1683501014113427, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.1358354845643044, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.152104818224907, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.1685235300660133, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.2186596766114235, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.2972359138727187, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.3820405969023704, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.4980480945110322, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.576754103899002, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.6624169993400573, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.7324571973085403, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.171875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.020393357863649725, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.020392351103946566, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.020385635709390046, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.020376623757183552, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.02035978006199002, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.020327564445324242, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.020271587362512947, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.020186683107167484, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.020178055386058987, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.02125107780098915, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.02401589822024107, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.028615835681557657, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.030895820744335653, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.03305419124662876, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.0342161238193512, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.03497881840914488, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.03588967967778444, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.03687753455713391, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.037892848001793024, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.03877676567062736, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.0393331434763968, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.039946439266204836, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.04090517727658152, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.04205422217026353, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.04287716530263424, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.04416202889755368, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.045286266151815656, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.04604799849912524, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.04705133790150285, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0481463741697371, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.04898119019344449, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.04943978901952505, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.04966804115101695, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.05009280582889915, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.05101990388706326, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.050309564396739004, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.05101406993344426, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.05123912286013365, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.05085261754691601, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.050198768880218264, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.04952275404706597, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.04897394213825464, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.04830653181299567, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1172242164611816, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1159920692443848, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.113938093185425, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1117870807647705, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.109557867050171, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1060707569122314, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1010820865631104, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.092562198638916, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.0651016235351562, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.964215040206909, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.7930185794830322, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.6210551261901855, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.531278371810913, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.466357469558716, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.4409165382385254, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.4281551837921143, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.4228527545928955, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.4202322959899902, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.424786329269409, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.431788682937622, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.4522080421447754, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.4805495738983154, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.5002501010894775, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.509031057357788, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.5526013374328613, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.6035492420196533, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.674691915512085, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.751471996307373, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.8122191429138184, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.9288437366485596, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.0171256065368652, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.086771011352539, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.1426217555999756, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.2112514972686768, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.2522008419036865, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.339747190475464, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.370286226272583, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.232002019882202, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.2117865085601807, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.170621871948242, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.13342022895813, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.984210729598999, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.997683048248291, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06496862310815799, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06626061277224068, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06921373200442968, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.07050572166851236, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.07161314138058324, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.07216685123661867, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.07493540051679587, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.07881136950904392, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.09745293466223699, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.12919896640826872, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.17183462532299743, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.21686969361387967, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.23846437799926173, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.2591362126245847, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.2672572905131045, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.26947212993724623, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.27113325950535255, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.2702104097452935, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.2703949796973053, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.26559616094499816, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.2591362126245847, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.2571059431524548, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.25858250276854927, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.25950535252860835, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.25341454411221853, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.24953857511997046, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.24529346622369877, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.23717238833517904, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.23772609819121446, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.23255813953488372, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.22425249169435216, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.22314507198228128, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.21686969361387967, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.22388335179032853, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.22314507198228128, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.2203765227021041, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.21280915466961978, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.22739018087855298, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.2188999630860096, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.21483942414174972, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.22259136212624583, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.2336655592469546, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.2187153931339978, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.010879086623629396, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.012221669393153113, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.015552895361989776, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.017003554589386242, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.018071193571238583, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.019505972518993317, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.02210056100379487, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.024894030645554538, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.04206634050759498, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.0583479589314758, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.0932378014104021, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.13423632412345657, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.15782010786912462, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.18269056580551232, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.19653650604406678, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.2035142406976244, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.20768849391740196, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.2088572542514663, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.21336877239096377, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.2094866659924294, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.20620005197911082, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.2064532750331239, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.2092649758866829, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.21364841480327798, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.20898260102025837, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.20664791830011556, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.20363952189197074, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.20009281683687788, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.20466237977159096, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.20085452242818583, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.18935996974816352, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.192436497151618, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.18450737749470023, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.18999175937822724, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.19419191468425465, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.18438977893383676, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.17589050782160318, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.18356115060457467, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.1738481584831194, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.170356762684475, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.1812176242120668, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.17801689480855973, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.1676772113185959, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 16, "lr_best": 8.1e-05, "wd_best": 0.05, "train/loss_best": 2.223701124191284, "validation/loss_best": 2.4228527545928955, "validation/acc_best": 0.27113325950535255, "validation/f1_best": 0.20768849391740196} +{"epoch": 14, "train/lr": 8.9081919031238e-05, "train/loss": 2.132834045290947, "train/grad": 0.25711212173104286, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.115902099609375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.114080810546875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.11115478515625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.108231201171875, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.105352783203125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.100806884765625, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.094833984375, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.084813232421875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.05457763671875, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.9481512451171876, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.7689834594726563, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.5931912231445313, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.492221221923828, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.3905604553222655, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.3211540031433104, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.2647233390808106, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.198866901397705, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.125951232910156, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.0479419136047365, "train/loss_019_lr4.4e-01_wd1.0e+00": 1.9777268743515015, "train/loss_020_lr5.2e-01_wd1.0e+00": 1.90532066822052, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.8366963386535644, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.7545538806915284, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.6750372493267058, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.6105455899238585, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.518251587152481, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.4416487103700637, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.3779123574495316, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.2869406777620316, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.2188359773159028, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.163918896317482, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.1091193377971649, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.0656492871046066, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.029056670665741, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.022185933291912, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.0420213249325752, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.0805095407366752, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.1591697564721108, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.2406502059102058, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.3539391231536866, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.4411892169713973, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.5161068427562714, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.6091355746984481, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.171875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.01996437941212207, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.019962701024487616, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.019954271572642027, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.019945515426807104, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.019928359929472207, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.019896052493713796, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.01984113109763712, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.019764140713959932, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.01985152592882514, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.02132846837863326, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.02440479550510645, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.02871525048278272, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.030866036536172033, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.03297733878716826, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.034112239442765716, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.034863237533718346, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.03579254373908043, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.03685798135586083, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.037920704567804935, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.03884641248732805, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.03944061441347003, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.04009457482025027, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.04106787456199527, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.04212996104732156, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.042950899191200737, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.04421916941180825, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.045287885814905164, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.04604782583191991, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.04715283187106252, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.04762471739202738, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.048090340383350846, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.04823807580396533, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.048515122644603254, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.04872418347746134, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.04889896189793944, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.04959066864103079, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.04969023495912552, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.04995955985039473, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.050295275077223776, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.05017155880108476, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.05009244343265891, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.04828635234385729, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.047417916245758536, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1165969371795654, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1152842044830322, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.113096237182617, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.110867500305176, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1085216999053955, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1048336029052734, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.099419355392456, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.0896108150482178, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.055666923522949, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.9360342025756836, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.761920690536499, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.601799964904785, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.5161855220794678, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.45650053024292, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.4329328536987305, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.420652151107788, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.4152469635009766, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.410036325454712, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.4119198322296143, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.4177474975585938, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.4339380264282227, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.4579696655273438, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.474672317504883, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.4860994815826416, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.53883957862854, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.6071605682373047, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.6930994987487793, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.783445119857788, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.860898733139038, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.947206497192383, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.04917573928833, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.1269164085388184, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.1741514205932617, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.2507331371307373, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.4015798568725586, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.4804604053497314, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.506314277648926, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.388301372528076, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.331163167953491, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.2127225399017334, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.170057773590088, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.008009195327759, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.977682113647461, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06626061277224068, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06681432262827612, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06773717238833518, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06902916205241787, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.0710594315245478, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.0725359911406423, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.0753045404208195, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.08250276854928018, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.10280546327057954, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.14119601328903655, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.18143226282761166, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.2203765227021041, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.24473975636766335, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.25987449243263194, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.26707272056109266, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.27113325950535255, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.27260981912144705, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.271686969361388, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.2722406792174234, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.2713178294573643, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.2643041712809155, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.2631967515688446, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.2663344407530454, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.26356589147286824, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.25839793281653745, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.25359911406423036, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.24529346622369877, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.23588039867109634, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.23588039867109634, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.22757475083056478, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.22185308231819859, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.22369878183831673, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.2117017349575489, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.2157622739018088, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.21096345514950166, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.19730527870062753, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.1939830195644149, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.2054263565891473, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.19767441860465115, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.20616463639719454, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.20450350682908822, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.21650055370985605, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.2248062015503876, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.010549915487089454, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.01128776142858666, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.013221824981498492, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.014526639655385561, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.01593255265207201, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.018172162528128328, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.021129508164715396, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.02727480418748147, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.0450092632267546, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.06576172660364736, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.10093252809678126, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.13737583233940423, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.16290893907461879, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.18338808418662114, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.19831073826353426, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.20571601268043327, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.20984932216380525, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.21110804699283367, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.2146740219669081, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.2169521744151234, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.21341923311543795, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.2139658703801175, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.22001876163296272, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.22004613049335786, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.2169094433342383, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.21328474444955403, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.20935771372521136, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.20297284971915477, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.202395835801063, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.19484664261629567, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.18898386502882536, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.19035007371068532, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.18372231359950256, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.18695687325664848, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.18908939156180662, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.17230485527625797, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.16750875590818928, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.17563784508175803, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.1729779534241607, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.18200510383936597, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.18166078825083112, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.18385713256086567, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.1855559024373751, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 16, "lr_best": 8.1e-05, "wd_best": 0.05, "train/loss_best": 2.198866901397705, "validation/loss_best": 2.4152469635009766, "validation/acc_best": 0.27260981912144705, "validation/f1_best": 0.20984932216380525} +{"epoch": 15, "train/lr": 6.196799573888289e-05, "train/loss": 2.0908574879169466, "train/grad": 0.25309502132236955, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.1115087890625, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.10976318359375, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.106790771484375, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.103843994140625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.100772705078125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.096236572265625, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.089908447265625, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.0790106201171876, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.0439947509765624, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.9237664794921874, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.74373779296875, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.581228256225586, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.4834864807128905, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.3847365951538086, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.314824867248535, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.2565025520324706, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.1887509536743166, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.114693078994751, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.0347748041152953, "train/loss_019_lr4.4e-01_wd1.0e+00": 1.9624241542816163, "train/loss_020_lr5.2e-01_wd1.0e+00": 1.8891618037223816, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.8190291178226472, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.735714040994644, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.6512594401836396, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.5827325004339219, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.4852337259054185, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.4031209641695022, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.3344917446374893, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.2335572510957717, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.1544712895154954, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.0961733520030976, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.0285730257630348, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.9716640907526016, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.9219176322221756, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.9133109495043754, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.936398307979107, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.9573998871445656, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.0253640910983086, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.0982720705866813, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.2130850273370744, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.2974461090564728, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.3723892998695373, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.4692475479841232, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.171875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.020387842999771238, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.02038452174514532, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.020374077088199556, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.02035918578505516, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.02033732442650944, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.020293830865994095, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.02022422176320106, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.020134173147380353, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.020268077258951963, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.021955693187192083, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.025205508060753345, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.02935671864077449, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.03145926477387548, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.0335076939035207, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.03459053440950811, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.03530880928039551, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.036200249688699844, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.037210695846006274, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.0382223248668015, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.039111188780516386, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.039616858921945095, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.040191594138741495, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.041105249486863615, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.04206882717087865, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.04265052756294608, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.04363244831562042, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.04440716793760657, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0449807502143085, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.045832735151052476, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.04615875033661723, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.04638528103008866, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.046769762709736824, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.046992194261401894, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.04670837225392461, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.04681873040273785, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.04744782637804747, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.04794309752061963, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.04795556537806988, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.04852679954841733, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.048486142437905076, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.048685336969792846, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.04761739041656256, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0464982420951128, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1164722442626953, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1152076721191406, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.113002300262451, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.110759735107422, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.108386516571045, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1045689582824707, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.0988292694091797, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.0880579948425293, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.0491385459899902, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.9178428649902344, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.7438714504241943, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.591047763824463, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.5086538791656494, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.452885389328003, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.4304850101470947, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.420208215713501, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.4173169136047363, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.415161609649658, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.4177799224853516, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.4227426052093506, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.4386863708496094, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.4642653465270996, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.4815750122070312, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.495352268218994, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.552272319793701, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.608152151107788, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.690476417541504, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.7762820720672607, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.8484814167022705, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.9678902626037598, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.0425074100494385, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.1269586086273193, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.186445951461792, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.2591052055358887, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.3852345943450928, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.4965879917144775, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.5136072635650635, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.4139983654022217, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.3718788623809814, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.2753496170043945, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.190526008605957, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.0436580181121826, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.0430939197540283, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06626061277224068, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06681432262827612, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.067921742340347, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06939830195644149, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.07069029162052418, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.07401255075673681, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.07678110003691399, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.08490217792543374, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.10428202288667406, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.14581026208933184, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.18715393133997785, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.2222222222222222, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.24621631598375784, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.2622739018087855, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.2691029900332226, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.2703949796973053, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.27002583979328165, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.2737172388335179, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.2727943890734588, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.2713178294573643, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.26651901070505724, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.26375046142488, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.26116648209671467, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.26651901070505724, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.2643041712809155, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.2574750830564784, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.24529346622369877, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.24234034699150978, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.23809523809523808, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.23052787006275377, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.2277593207825766, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.22831303063861202, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.21908453303802142, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.21779254337393872, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.21631598375784422, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.2009966777408638, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.20524178663713546, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.2081949058693245, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.1997046880767811, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.2041343669250646, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.2131782945736434, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.2220376522702104, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.21207087486157253, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.010799689725848917, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.012023627967379843, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.013835543573533041, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.01538710896339053, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.01725582190454469, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.020780079380199535, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.02329479997249311, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.029039479270673865, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.046075315196928146, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.07045403924590792, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.1083967531369106, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.14029521262558906, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.16549933062635225, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.18822894773276766, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.19999777525930607, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.2052144607523375, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.20798425862321515, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.21232122377729776, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.21449697996943148, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.21489802021741436, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.2136075642790272, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.21344748341768072, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.2132809479602035, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.22328650789970897, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.22176906434311894, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.21800368419364466, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.2081006477785695, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.2097825762989559, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.2064391671065622, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.20204157673047976, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.1964819683111174, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.19980411865880074, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.19705593935398466, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.19539168181255184, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.1977582722418982, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.1789922284853701, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.18318012900131195, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.18479256662885132, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.18395865608813414, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.1859312275450066, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.18970250100272648, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.19390035062692876, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.18889045524385764, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 17, "lr_best": 9.599999999999999e-05, "wd_best": 0.05, "train/loss_best": 2.114693078994751, "validation/loss_best": 2.415161609649658, "validation/acc_best": 0.2737172388335179, "validation/f1_best": 0.21232122377729776} +{"epoch": 16, "train/lr": 3.870405029380728e-05, "train/loss": 2.058681248426437, "train/grad": 0.2475945296138525, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.118763427734375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.11683837890625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.1136962890625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.11063720703125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.10734619140625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.102413330078125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.09550537109375, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.083564453125, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.0437884521484375, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.911715393066406, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.732156219482422, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.5795952606201173, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.484736442565918, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.3865840148925783, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.3167189598083495, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.2588327026367185, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.1905931568145753, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.1149277687072754, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.0328158044815066, "train/loss_019_lr4.4e-01_wd1.0e+00": 1.959686758518219, "train/loss_020_lr5.2e-01_wd1.0e+00": 1.8843009161949158, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.8127863311767578, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.7262370824813842, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.6407599556446075, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.5716447985172273, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.4705971211194993, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.3832594513893128, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.306785715818405, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.1992178916931153, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.1127051669359207, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.0468268176913262, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.9817104303836822, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.9158695045113564, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.8598650914430618, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.8377171894907951, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.8283562783896923, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.8482067477703095, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.8943800908327103, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.9546323698759079, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.0664341989159585, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.1211091792583465, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.2017262068390846, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.3180896705389022, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.171875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.020335645787417887, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.020330404513515532, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.02031857609283179, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.020302636600099504, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.020279905325733125, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.020237649683840574, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.02016943519935012, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.020086645078845323, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.02029172495007515, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.022183244386687874, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.025562769882380963, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.029640020076185464, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.031699185576289896, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.033703035460785034, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.03479464967735112, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.035543589927256106, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.03646333324722946, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.037461309181526306, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.03840466574765742, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.03922081450000405, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.039693686664104465, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.04020961917936802, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.041053600814193486, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.04200012966990471, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.042584557086229324, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.04342432413250208, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.044076701384037735, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.04457244368270039, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.04523222040385008, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.04541225822642445, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.045361860524863004, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.04529716096818447, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.045219763536006215, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.04485040321946144, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.04447672680020332, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.044521827902644875, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.04499453505501151, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.045440108980983496, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.045230491161346434, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.04600637780502439, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.04601953465491533, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.04577731246128678, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.04501095360144973, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1163907051086426, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.115083694458008, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.112889289855957, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.110643148422241, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.108234167098999, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1043550968170166, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.0984537601470947, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.0871050357818604, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.0450522899627686, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.906968116760254, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.733501434326172, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.58490252494812, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.504427433013916, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.450644016265869, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.429126024246216, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.4191267490386963, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.4164879322052, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.415619373321533, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.420811414718628, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.4293572902679443, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.4495601654052734, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.4808084964752197, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.503619432449341, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.517911195755005, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.589266538619995, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.6514201164245605, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.7455310821533203, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.8466577529907227, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.9225528240203857, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.023771047592163, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.1141319274902344, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.2069923877716064, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.266043186187744, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.3388617038726807, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.4694244861602783, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.57070255279541, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.6276021003723145, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.5566835403442383, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.5699288845062256, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.444577932357788, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.3526439666748047, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.1943140029907227, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.1547396183013916, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06459948320413436, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06607604282022887, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06755260243632337, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06847545219638243, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.07124400147655961, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.07401255075673681, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.07622739018087855, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.08194905869324474, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.10594315245478036, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.15079365079365079, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.18752307124400147, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.2262827611664821, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.24510889627168697, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.2648578811369509, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.2672572905131045, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.27150239940937615, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.27297895902547065, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.2739018087855297, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.27297895902547065, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.26707272056109266, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.25987449243263194, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.26116648209671467, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.2576596530084902, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.2593207825765965, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.25341454411221853, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.2469545957918051, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.23883351790328536, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.23717238833517904, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.2320044296788483, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.2262827611664821, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.21816168327796234, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.22443706164636398, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.21926910299003322, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.21853082318198597, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.2146548541897379, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.2059800664451827, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.19785898855666298, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.2054263565891473, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.1982281284606866, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.19564414913252123, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.20634920634920634, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.21262458471760798, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.20616463639719454, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.010105838999873431, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.011704001022461122, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.0139712848361037, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.014914241424490363, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.01732535302117902, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.020341319151173536, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.021754510661338117, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.026789223240533358, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.04738725777213864, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.07364016804570529, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.10829126546098955, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.14362512391936386, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.16520175046111507, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.19249088560584912, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.19935577400857926, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.20724551224840046, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.2106780901271504, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.21305235005513098, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.21514900292919892, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.2113874939709045, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.20822152005201047, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.2113915619187251, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.20997706297897986, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.2174789117496857, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.21156281913950092, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.20708038037900844, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.20276710201449188, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.20521985787951524, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.19960550057783719, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.19557791266086708, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.18608595833014938, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.19484428037704316, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.19173655918800558, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.19080085063223304, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.19252667843508034, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.18079400604409998, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.17197742584594858, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.17764808783284133, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.17333071928129387, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.1731028688083177, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.18193329390750712, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.18664935289293014, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.18075438494232876, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 17, "lr_best": 9.599999999999999e-05, "wd_best": 0.05, "train/loss_best": 2.1149277687072754, "validation/loss_best": 2.415619373321533, "validation/acc_best": 0.2739018087855297, "validation/f1_best": 0.21305235005513098} +{"epoch": 17, "train/lr": 2.030750443206766e-05, "train/loss": 2.02845097720623, "train/grad": 0.24012715704739093, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.11495849609375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.1130322265625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.1098681640625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.10684814453125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.103548583984375, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.09865234375, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.091640625, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.0793707275390627, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.0378997802734373, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.9016387939453123, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.721525115966797, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.567327117919922, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.4719470977783202, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.376093406677246, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.307077407836914, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.249282512664795, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.181284198760986, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.1050028514862063, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.022417411804199, "train/loss_019_lr4.4e-01_wd1.0e+00": 1.9476655292510987, "train/loss_020_lr5.2e-01_wd1.0e+00": 1.8696365904808045, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.796478590965271, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.7110498642921448, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.6222207534313202, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.5511913323402404, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.4474908709526062, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.356114646792412, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.2797696059942245, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.1753739023208618, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.0820381245017052, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.008507191836834, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.9313076481223106, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.8683235618472099, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.8052206411957741, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.7691057336330414, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.7653923565149308, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.7697852271795272, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.808580695092678, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.8545286008715629, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.9458079421520234, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.9909283384680748, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.0674236807227135, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.179493382871151, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.171875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.02011155643966049, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.02010504949837923, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.020091973613016307, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.020075496644712986, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.0200525899650529, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.0200107056600973, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.019943704009056092, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.01986762223765254, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.020117334108799696, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.02208856811746955, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.025495562804862856, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.029445246579125523, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.031474218405783176, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.03342217134311795, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.03448879523202777, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.03523581677116454, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.03615875422954559, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.03715358413755894, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.03810650520026684, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.038941738475114104, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.03944211632013321, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.03994414476677775, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.04076387457549572, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.04168747071176768, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.04213268687948585, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.042907498609274626, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.04351785451173782, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.04396365340799093, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.044406624510884285, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.044269470889121296, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.04409903323277831, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.043632189892232415, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.04323850052431226, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0427952116727829, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.042239780612289904, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.04181588845327497, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.04162714060395956, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.041712962593883275, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.04219880262389779, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.042686545215547086, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.043345052879303694, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.04329943673685193, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.042821053937077524, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.116339921951294, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1150310039520264, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1128029823303223, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1105077266693115, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1080570220947266, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.104097366333008, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.0980236530303955, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.086266279220581, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.0422799587249756, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.90065336227417, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.7275092601776123, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.5808963775634766, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.50126051902771, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.4479780197143555, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.425793170928955, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.4149551391601562, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.411217212677002, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.4087390899658203, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.4125003814697266, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.419459342956543, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.4387474060058594, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.468402624130249, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.490267753601074, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.506147861480713, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.567999839782715, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.6328327655792236, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.719938039779663, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.8112552165985107, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.8854033946990967, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.0025508403778076, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.0895917415618896, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.1789608001708984, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.252258777618408, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.338085174560547, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.46405291557312, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.6012415885925293, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.6532533168792725, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.5559701919555664, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.567549705505371, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.4451956748962402, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.3706324100494385, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.2117600440979004, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.1377720832824707, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06533776301218161, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06607604282022887, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06736803248431156, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06939830195644149, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.07198228128460686, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.07438169066076043, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.07770394979697305, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.08490217792543374, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.1094499815430048, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.15208564045773348, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.18973791066814322, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.22868217054263565, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.2456626061277224, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.26541159099298633, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.2678110003691399, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.2733480989294943, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.27500922849760057, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.27611664820967147, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.2731635289774825, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.2698412698412698, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.2646733111849391, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.2596899224806202, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.2602436323366556, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.26301218161683276, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.2561830933923957, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.2541528239202658, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.2467700258397933, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.23920265780730898, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.2368032484311554, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.2294204503506829, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.22185308231819859, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.22720561092654115, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.22259136212624583, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.22056109265411591, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.21483942414174972, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.20376522702104097, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.20764119601328904, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.20948689553340716, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.20173495754891105, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.20450350682908822, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.21114802510151348, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.22056109265411591, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.2262827611664821, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.011116824951055307, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.012098754898603454, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.014172929508418733, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.01633988500940116, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.01831328680888161, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.0207814085397274, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.02382215248027605, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.028993390519376314, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.050084771337358835, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.07457952526366461, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.11053043582911781, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.14652699357349658, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.1659776279366705, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.19355532619774793, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.2009296948153072, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.21055889991006357, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.21276006875222084, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.21597605639944203, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.21708518167588434, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.2152828316361908, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.21392120385546018, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.21107892356424163, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.21413482173572027, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.22016687111511601, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.2147090427480355, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.21635617499211116, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.21169638943734834, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.20763278231810212, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.2033948312046833, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.1975363821894782, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.18907666692364536, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.1953003540487228, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.1944457540663309, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.19105056934284226, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.19060469254165688, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.17700369221373213, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.17891958947935815, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.18037515619153532, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.17647285964901407, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.17849005958936082, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.1843830948331103, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.1875911449300051, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.19433450534958271, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 17, "lr_best": 9.599999999999999e-05, "wd_best": 0.05, "train/loss_best": 2.1050028514862063, "validation/loss_best": 2.4087390899658203, "validation/acc_best": 0.27611664820967147, "validation/f1_best": 0.21597605639944203} +{"epoch": 18, "train/lr": 7.5829098008590064e-06, "train/loss": 2.007068286538124, "train/grad": 0.23585161842405797, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.1163037109375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.1144140625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.11135986328125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.108218994140625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.1049755859375, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.100028076171875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.093004150390625, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.0806976318359376, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.03839111328125, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.9008383178710937, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.722703094482422, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.5692474365234377, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.4718210983276365, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.373160095214844, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.302679805755615, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.2432015991210936, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.1734784126281737, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.0964970111846926, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.0137514066696167, "train/loss_019_lr4.4e-01_wd1.0e+00": 1.9381271123886108, "train/loss_020_lr5.2e-01_wd1.0e+00": 1.8597338008880615, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.7856344437599183, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.6987137293815613, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.609299716949463, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.5374450552463532, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.4301661890745163, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.3370436477661132, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.2569781547784806, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.1459522944688798, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.0536676260828972, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.9792245057225227, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.9016910845041275, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.8297946715354919, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.7647907796502114, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.7231880494952202, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.7044620144367219, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.7152618663012982, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.7448304270207882, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.7797659873962403, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.8567796608805657, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.8990797460079193, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.9578034669160843, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.0708924594521523, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.171875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.020231524021364748, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.02022392626386136, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.020211570411920548, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.020192650142125786, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.020170321320183576, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.020126383891329168, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.020058378870598973, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.0199830526066944, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.020245647220872343, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.022242963192984463, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.02565417763777077, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.02955410834401846, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.031566655207425354, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.033503476325422527, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.0345698980987072, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.03530924621969461, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.0362050143070519, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.0371832428034395, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.03810701264068484, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.0388825667090714, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.03930186863988638, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.03975877396762371, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.040497270580381155, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.04137830575928092, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.04184462208300829, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.04261618856340647, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.043157409466803076, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.04350495930761099, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.043829479776322844, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.04368626579642296, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.043346006944775584, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.042883271388709544, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.042120465375483036, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0414415674097836, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.04063634006306529, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.039936921391636133, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.03973226075991988, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.039953916948288676, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.04024151595309377, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0408601213246584, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.04096284773200751, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.041027039885520936, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.04079484341666102, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.116321563720703, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1150104999542236, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.112797498703003, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1104817390441895, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1080117225646973, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.104031562805176, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.097914695739746, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.086024284362793, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.0413458347320557, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.898446559906006, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.7257041931152344, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.5800750255584717, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.5013041496276855, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.448775053024292, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.427448034286499, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.4173057079315186, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.4143524169921875, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.412165403366089, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.4161932468414307, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.4231128692626953, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.441596269607544, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.4710869789123535, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.491852045059204, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.5068717002868652, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.5694491863250732, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.631680965423584, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.7181925773620605, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.812330961227417, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.8913984298706055, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.0062947273254395, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.0936803817749023, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.1803901195526123, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.2563798427581787, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.342937469482422, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.4849424362182617, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.611818313598633, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.669060230255127, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.590303659439087, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.5993120670318604, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.4923887252807617, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.4482779502868652, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.2783148288726807, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.208230495452881, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06533776301218161, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06570690291620525, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.0681063122923588, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06921373200442968, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.07198228128460686, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.07419712070874862, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.07641196013289037, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.08564045773348099, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.10963455149501661, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.15208564045773348, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.18973791066814322, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.2277593207825766, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.24603174603174602, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.2652270210409745, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.26891842008121075, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.2722406792174234, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.27445551864156514, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.27556293835363604, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.2742709486895533, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.2698412698412698, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.26448874123292726, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.26153562200073827, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.26116648209671467, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.2633813215208564, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.25655223329641935, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.25489110372831303, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.24769287559985234, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.23994093761535623, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.23772609819121446, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.22886674049464747, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.2207456626061277, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.2292358803986711, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.22185308231819859, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.2172388335179033, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.21354743447766703, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.20191952750092285, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.2009966777408638, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.2070874861572536, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.19859726836471023, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.19804355850867478, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.2041343669250646, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.21834625322997417, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.21539313399778517, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.011144479731818408, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.011617379062847379, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.014528743514378453, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.016098131212488962, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.01833394653458947, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.020653740581768987, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.02277606901033095, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.029935436607035803, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.050204096794059905, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.0750574547805433, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.11065436329043937, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.1454260293131313, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.16647129011616701, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.19380745327329793, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.20122605016078132, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.20806053248407988, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.2130083451153342, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.21564565022245755, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.21837843644530064, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.21460370905588078, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.21350586814608227, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.21245703262758606, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.21403152270856587, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.21982331748139397, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.21437427821359786, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.21593000791768793, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.21196623407713644, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.20812715447517527, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.2048230157252798, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.19821846326336157, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.19016747694423544, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.19907501008667428, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.195432462592437, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.19256579773431562, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.1909476807665265, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.17843255330137264, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.17540433495597685, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.17933113220946198, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.17763875169542342, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.17639241702471023, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.1824319437319346, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.19046908832432732, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.1914671629256365, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 17, "lr_best": 9.599999999999999e-05, "wd_best": 0.05, "train/loss_best": 2.0964970111846926, "validation/loss_best": 2.412165403366089, "validation/acc_best": 0.27556293835363604, "validation/f1_best": 0.21564565022245755} +{"epoch": 19, "train/lr": 1.0867618231465446e-06, "train/loss": 2.005282021164894, "train/grad": 0.23202710412442684, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.117174072265625, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.11535400390625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.112286376953125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.10933837890625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.106126708984375, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.10126708984375, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.09427734375, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.0818341064453123, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.039033203125, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.9010296630859376, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.7225616455078123, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.571962356567383, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.4777678298950194, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.380350112915039, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.3097979736328127, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.2508139610290527, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.181085300445557, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.103514699935913, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.0197114324569703, "train/loss_019_lr4.4e-01_wd1.0e+00": 1.9441951251029967, "train/loss_020_lr5.2e-01_wd1.0e+00": 1.866508836746216, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.7929911184310914, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.7047341299057006, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.6142645955085755, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.5437843811511993, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.4358991086483002, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.34157848238945, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.2632820534706115, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.149956592321396, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.0561778971552849, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.9804042187333107, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.8997724014520645, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.8201684781908989, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.7539111748337746, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.7117234931886196, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.6955841413140297, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.6992917793989182, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.7284742739796638, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.7658341279625893, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.8379241093993187, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.8657874271273613, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.9293328806757927, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.0307043200731278, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.171875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.019848675900138914, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.019841104838997127, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.019826949196867644, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.01980876762419939, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.019784492612816392, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.019739353922195734, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.019669762626290322, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.019594554230570792, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.019857252282090485, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.021849099546670914, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.02524490164592862, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.029115502294152974, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.03112365698441863, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.03305276518687606, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.03409333920106292, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.03482997912913561, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.035751692038029435, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.03676174337975681, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.03770041599869728, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.03850937684997916, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.03900223789736629, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.03949814109131694, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.04024941872805357, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.04114404529333115, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.04164767485111952, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.04238612836226821, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.04288299851119518, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.04317033672705293, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.04347442593425512, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.04318224186077714, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.042833568062633276, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.04205872606486082, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.04112325023859739, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.040593544077128174, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.039765112288296225, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.03913158114999533, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.038767585661262274, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.038891827398911116, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.039080145154148344, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.03957575554028153, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.039649493843317035, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.039734441731125114, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.03957503328099847, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.116307497024536, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.115007162094116, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.112765312194824, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1104657649993896, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1079957485198975, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1039986610412598, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.0978612899780273, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.085954189300537, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.0412206649780273, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.8981571197509766, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.7253501415252686, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.5798680782318115, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.501016139984131, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.4485690593719482, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.427013635635376, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.416813373565674, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.413710355758667, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.4113306999206543, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.415330410003662, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.4223082065582275, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.4411582946777344, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.470700740814209, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.4922633171081543, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.5070807933807373, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.5690348148345947, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.632331132888794, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.7205240726470947, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.814419746398926, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.8932583332061768, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.0097615718841553, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.0967161655426025, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.1856470108032227, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.2595605850219727, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.349015712738037, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.495905637741089, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.6228833198547363, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.680734395980835, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.5971267223358154, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.60274338722229, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.4991650581359863, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.4563679695129395, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.295175552368164, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.2160940170288086, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.0651531930601698, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06570690291620525, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06847545219638243, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06921373200442968, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.07216685123661867, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.07419712070874862, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.07641196013289037, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.08564045773348099, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.11018826135105204, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.15227021040974528, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.19029162052417867, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.2279438907345884, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.24584717607973422, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.26541159099298633, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.268733850129199, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.27260981912144705, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.27408637873754155, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.27611664820967147, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.2731635289774825, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.2707641196013289, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.26393503137689184, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.26135105204872644, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.26098191214470284, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.26356589147286824, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.2589516426725729, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.25378368401624213, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.24732373569582872, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.23864894795127353, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.23661867847914358, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.22683647102251753, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.2222222222222222, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.22886674049464747, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.21926910299003322, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.21853082318198597, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.21373200442967885, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.20339608711701734, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.19785898855666298, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.2039497969730528, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.19896640826873385, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.19933554817275748, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.2039497969730528, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.2172388335179033, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.21483942414174972, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.010944827429061327, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.011508498687374705, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.01473756015118279, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.016094371012381575, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.018522532436086977, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.020568025110821127, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.02292082362832853, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.029770953083926004, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.0505792610465036, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.07512031325675338, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.11100536242358106, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.14560882873203332, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.1661104818105029, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.1939134942760481, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.20107153542136844, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.20838216202910753, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.21227813609379897, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.21601639128796082, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.21701992472721673, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.2151071876562609, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.21342564615912463, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.21210758003699506, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.21461639810672853, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.22006023868045363, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.21608396562414614, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.21565433861102376, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.21152544228508605, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.20715905156406467, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.20455538739290177, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.1961314542918312, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.19064510467731233, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.19793449990970405, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.1926694277901111, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.19283639302417668, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.1908207070049727, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.17874203065815256, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.17313054556338336, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.17651322835738922, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.177278038830322, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.17810281918015258, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.1815985850483212, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.18966167155520205, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.19128701423420888, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 17, "lr_best": 9.599999999999999e-05, "wd_best": 0.05, "train/loss_best": 2.103514699935913, "validation/loss_best": 2.4113306999206543, "validation/acc_best": 0.27611664820967147, "validation/f1_best": 0.21601639128796082} diff --git a/input_space_v3/flat_lr1e-3_6/eval_v2/ppmi_dx__patch__logistic/config.yaml b/input_space_v3/flat_lr1e-3_6/eval_v2/ppmi_dx__patch__logistic/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..15aa783be9810ba2a4a4207c8fc05112b03f509a --- /dev/null +++ b/input_space_v3/flat_lr1e-3_6/eval_v2/ppmi_dx__patch__logistic/config.yaml @@ -0,0 +1,30 @@ +output_root: experiments/input_space_v3/output +name_prefix: eval_logistic +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_6; eval v2 (ppmi_dx patch logistic) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: input_space_v3/flat_lr1e-3_6/eval_v2/ppmi_dx__patch__logistic +model: flat_mae +representation: patch +dataset: ppmi_dx +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/eval_v2/ppmi_dx__patch__logistic +remote_dir: null diff --git a/input_space_v3/flat_lr1e-3_6/eval_v2/ppmi_dx__patch__logistic/eval_table.csv b/input_space_v3/flat_lr1e-3_6/eval_v2/ppmi_dx__patch__logistic/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..758b47b1a60a6f2678b1da4a163146c3dcebb976 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_6/eval_v2/ppmi_dx__patch__logistic/eval_table.csv @@ -0,0 +1,203 @@ +model,repr,clf,dataset,trial,C,split,acc,acc_std,f1,f1_std,bacc,bacc_std +flat_mae,patch,logistic,ppmi_dx,,0.005994842503189409,train,0.7330960854092526,0.01726539293321715,0.6925915661420424,0.021279910504049218,0.6860081479997329,0.019522143666855046 +flat_mae,patch,logistic,ppmi_dx,,0.005994842503189409,test,0.63,0.040100967569374195,0.5552350042072365,0.04847081425232612,0.5613470613470614,0.04245616978258205 +flat_mae,patch,logistic,ppmi_dx,1,0.046415888336127774,train,0.8256227758007118,0.015917930674684784,0.8093913091628944,0.017916566479769934,0.8009794476557482,0.01799963268644851 +flat_mae,patch,logistic,ppmi_dx,1,0.046415888336127774,test,0.58,0.04660133474483322,0.5320855614973261,0.05176575962587245,0.533955857385399,0.04912325611805353 +flat_mae,patch,logistic,ppmi_dx,2,0.046415888336127774,train,0.797153024911032,0.01567570173963763,0.7756471313312416,0.01796707687922976,0.7665515949475488,0.017683307748376273 +flat_mae,patch,logistic,ppmi_dx,2,0.046415888336127774,test,0.68,0.04497458838055107,0.6483516483516483,0.05039782264356867,0.6451612903225806,0.048551681011941246 +flat_mae,patch,logistic,ppmi_dx,3,0.046415888336127774,train,0.798932384341637,0.016266767669040807,0.7773430241323334,0.018896771281750317,0.767996681652751,0.018712793829422963 +flat_mae,patch,logistic,ppmi_dx,3,0.046415888336127774,test,0.65,0.04756557999225911,0.6178622120318812,0.05209012325929326,0.615874363327674,0.05057320881386341 +flat_mae,patch,logistic,ppmi_dx,4,0.005994842503189409,train,0.7153024911032029,0.017143654504092824,0.6680693983019564,0.021630064548503112,0.6635490259045173,0.019381973359170978 +flat_mae,patch,logistic,ppmi_dx,4,0.005994842503189409,test,0.67,0.04428771387190808,0.6396986570586308,0.04891518223870444,0.6370967741935484,0.04751403084347118 +flat_mae,patch,logistic,ppmi_dx,5,0.046415888336127774,train,0.802491103202847,0.016509723359684297,0.7818162740674676,0.019024253094824802,0.7726263112823806,0.01879161807060379 +flat_mae,patch,logistic,ppmi_dx,5,0.046415888336127774,test,0.57,0.04630194812316216,0.5242836596968692,0.05010112055333546,0.5258913412563667,0.04770934868646893 +flat_mae,patch,logistic,ppmi_dx,6,0.005994842503189409,train,0.7295373665480427,0.01632980455911037,0.6875585205992509,0.020740440549207345,0.6811978163134232,0.018941751433631436 +flat_mae,patch,logistic,ppmi_dx,6,0.005994842503189409,test,0.6,0.04371957913795603,0.5404411764705883,0.052417179482480085,0.5449915110356536,0.047359284646267104 +flat_mae,patch,logistic,ppmi_dx,7,0.005994842503189409,train,0.7348754448398577,0.016804094108422693,0.6932617813513068,0.02094498585223462,0.6864028045386428,0.01916064573815845 +flat_mae,patch,logistic,ppmi_dx,7,0.005994842503189409,test,0.6,0.048089462463204974,0.5604395604395604,0.05300073107157988,0.5602716468590832,0.05084553856989655 +flat_mae,patch,logistic,ppmi_dx,8,0.3593813663804626,train,0.9074733096085409,0.011842985958336973,0.90116341991342,0.012785209820507331,0.8970241918218798,0.013335251933061515 +flat_mae,patch,logistic,ppmi_dx,8,0.3593813663804626,test,0.51,0.04784367878832062,0.4650070968446337,0.04999665079856131,0.4673174872665535,0.04851287545390451 +flat_mae,patch,logistic,ppmi_dx,9,0.046415888336127774,train,0.8042704626334519,0.015862228362481034,0.782987208110423,0.01853843350898081,0.7732016698779705,0.018454953875074512 +flat_mae,patch,logistic,ppmi_dx,9,0.046415888336127774,test,0.59,0.04481060588744588,0.539894512400404,0.050458058756134294,0.5420203735144312,0.04718799228833209 +flat_mae,patch,logistic,ppmi_dx,10,0.046415888336127774,train,0.7953736654804271,0.01667084727817628,0.7744964288580372,0.019122363740771312,0.7659762363519589,0.018961512541638723 +flat_mae,patch,logistic,ppmi_dx,10,0.046415888336127774,test,0.63,0.045389315923463756,0.5960257670051315,0.04952095580035658,0.5946519524617997,0.048059808698812566 +flat_mae,patch,logistic,ppmi_dx,11,0.3593813663804626,train,0.9074733096085409,0.011832994404997231,0.9009718475947789,0.012791703294216935,0.8961544637122671,0.013351075960185657 +flat_mae,patch,logistic,ppmi_dx,11,0.3593813663804626,test,0.64,0.04498929205933342,0.609375,0.04868474372730309,0.6078098471986417,0.047415609721737056 +flat_mae,patch,logistic,ppmi_dx,12,0.005994842503189409,train,0.7313167259786477,0.016200926810162383,0.6910007828572469,0.020189835428271654,0.6843823592378505,0.018623507878138507 +flat_mae,patch,logistic,ppmi_dx,12,0.005994842503189409,test,0.59,0.040240571566517294,0.4969942338363391,0.04915305095845323,0.516553480475382,0.04190412204625201 +flat_mae,patch,logistic,ppmi_dx,13,0.005994842503189409,train,0.7188612099644128,0.016513822191571235,0.6752253043071161,0.020398768402607303,0.6699181117533719,0.018609424510906716 +flat_mae,patch,logistic,ppmi_dx,13,0.005994842503189409,test,0.65,0.04095558569963321,0.5872154735228211,0.0507462687949308,0.5904074702886248,0.04435845448743415 +flat_mae,patch,logistic,ppmi_dx,14,0.005994842503189409,train,0.7384341637010676,0.015778351335504932,0.6973790728767926,0.0196385474329793,0.6901627060586598,0.018014908101259115 +flat_mae,patch,logistic,ppmi_dx,14,0.005994842503189409,test,0.61,0.04338144764758318,0.5481404240528328,0.052120742637302174,0.5530560271646858,0.046730846243111024 +flat_mae,patch,logistic,ppmi_dx,15,0.005994842503189409,train,0.7153024911032029,0.015308883461671823,0.6691003297220914,0.01927323660907982,0.6644187540141298,0.017385945879166337 +flat_mae,patch,logistic,ppmi_dx,15,0.005994842503189409,test,0.66,0.04401931848631915,0.6155585707824514,0.051069989802688696,0.6137521222410866,0.04757939958446529 +flat_mae,patch,logistic,ppmi_dx,16,0.3593813663804626,train,0.9110320284697508,0.01162274038780936,0.9045931116905693,0.012589725013270872,0.8990446371226718,0.01314331398385565 +flat_mae,patch,logistic,ppmi_dx,16,0.3593813663804626,test,0.57,0.0478549934698564,0.5601023017902813,0.048118226182940614,0.5666383701188455,0.049613872052592524 +flat_mae,patch,logistic,ppmi_dx,17,0.005994842503189409,train,0.7241992882562278,0.01663108387780151,0.6818701404942681,0.020958929580764462,0.6759928280882038,0.019186920344505046 +flat_mae,patch,logistic,ppmi_dx,17,0.005994842503189409,test,0.63,0.043295339241077674,0.5713127099988413,0.05077577387216064,0.5742784380305602,0.045973750788900224 +flat_mae,patch,logistic,ppmi_dx,18,0.046415888336127774,train,0.8167259786476868,0.01577691894311906,0.7998928355371187,0.01775287945590851,0.7920145579105117,0.017817923706808875 +flat_mae,patch,logistic,ppmi_dx,18,0.046415888336127774,test,0.6,0.04764092358466615,0.554367201426025,0.05170213639945616,0.5551782682512734,0.04899450173336097 +flat_mae,patch,logistic,ppmi_dx,19,0.3593813663804626,train,0.9128113879003559,0.01196058832389887,0.9064081431508828,0.01310709755278581,0.9004897238278742,0.01402476853031396 +flat_mae,patch,logistic,ppmi_dx,19,0.3593813663804626,test,0.54,0.04688617706744707,0.5208333333333334,0.04791023811715692,0.5220713073005093,0.048884007157280376 +flat_mae,patch,logistic,ppmi_dx,20,0.005994842503189409,train,0.7295373665480427,0.016550344614702575,0.6805910770105144,0.021478741662295974,0.6751097195461357,0.019041989155057122 +flat_mae,patch,logistic,ppmi_dx,20,0.005994842503189409,test,0.66,0.03972859927055068,0.5952380952380952,0.05072609987204646,0.5984719864176571,0.04382273468548006 +flat_mae,patch,logistic,ppmi_dx,21,0.046415888336127774,train,0.7953736654804271,0.016572957557482,0.7728415022055076,0.019151643932400007,0.7633670520231214,0.018787966170332335 +flat_mae,patch,logistic,ppmi_dx,21,0.046415888336127774,test,0.72,0.04150882315845632,0.6880570409982174,0.048165353701470966,0.6825127334465195,0.04605804764221196 +flat_mae,patch,logistic,ppmi_dx,22,0.046415888336127774,train,0.8167259786476868,0.015501063677684376,0.7985053066140357,0.01773404290152264,0.7894053735816742,0.017826951796827428 +flat_mae,patch,logistic,ppmi_dx,22,0.046415888336127774,test,0.55,0.047478715231143304,0.5021573182874212,0.050901953087246966,0.5046689303904923,0.04877692268086728 +flat_mae,patch,logistic,ppmi_dx,23,0.3593813663804626,train,0.9110320284697508,0.01186457014480781,0.9049648268398268,0.012843364670073618,0.9007840933418969,0.013529391215509487 +flat_mae,patch,logistic,ppmi_dx,23,0.3593813663804626,test,0.59,0.0467414334397224,0.539894512400404,0.05275522554754379,0.5420203735144312,0.04933886273735273 +flat_mae,patch,logistic,ppmi_dx,24,0.046415888336127774,train,0.798932384341637,0.01657676151812513,0.7784182300952887,0.018920655810664457,0.769736137871976,0.018718659503180086 +flat_mae,patch,logistic,ppmi_dx,24,0.046415888336127774,test,0.63,0.04958807921264949,0.5960257670051315,0.05403951352479992,0.5946519524617997,0.052347132914715176 +flat_mae,patch,logistic,ppmi_dx,25,0.046415888336127774,train,0.797153024911032,0.016214440124166035,0.774535472972973,0.018911068355055974,0.7648121387283238,0.018653557595564297 +flat_mae,patch,logistic,ppmi_dx,25,0.046415888336127774,test,0.61,0.03148263648425907,0.48677457560205295,0.04570286159679321,0.5224957555178268,0.033816438089549324 +flat_mae,patch,logistic,ppmi_dx,26,0.3593813663804626,train,0.9128113879003559,0.011537054799180456,0.9062194569596415,0.012667919963856081,0.8996199957182616,0.013463727866798477 +flat_mae,patch,logistic,ppmi_dx,26,0.3593813663804626,test,0.67,0.045178154012752665,0.648,0.04801809402048528,0.6472835314091681,0.047579966675409494 +flat_mae,patch,logistic,ppmi_dx,27,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,27,21.54434690031882,test,0.58,0.04854441265480508,0.5689655172413793,0.04888011660386603,0.5747028862478778,0.05048159869477411 +flat_mae,patch,logistic,ppmi_dx,28,0.3593813663804626,train,0.9217081850533808,0.011009746180594141,0.9155291384846622,0.012112720846482124,0.9077151573538857,0.012912731406590605 +flat_mae,patch,logistic,ppmi_dx,28,0.3593813663804626,test,0.66,0.04278307609324042,0.6155585707824514,0.05065039274993392,0.6137521222410866,0.04691816784927534 +flat_mae,patch,logistic,ppmi_dx,29,0.046415888336127774,train,0.800711743772242,0.016381838207043642,0.78064012490242,0.018780055769045005,0.7720509526867909,0.01862550560206721 +flat_mae,patch,logistic,ppmi_dx,29,0.046415888336127774,test,0.64,0.04313189075382622,0.5863970588235294,0.052045514845899594,0.5874363327674024,0.04701534503227411 +flat_mae,patch,logistic,ppmi_dx,30,10000.0,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,30,10000.0,test,0.52,0.05011080123087237,0.5,0.05160845611383304,0.5008488964346349,0.05241884392429196 +flat_mae,patch,logistic,ppmi_dx,31,0.046415888336127774,train,0.802491103202847,0.01584418173196833,0.7838603834120415,0.018007214870250893,0.7761052237208307,0.018110848879715844 +flat_mae,patch,logistic,ppmi_dx,31,0.046415888336127774,test,0.68,0.048259709903811066,0.6483516483516483,0.05332513984898903,0.6451612903225806,0.05159320039749484 +flat_mae,patch,logistic,ppmi_dx,32,0.046415888336127774,train,0.8185053380782918,0.016523908088171852,0.8002258280361325,0.019121806847160555,0.7908504602868764,0.019267213828923588 +flat_mae,patch,logistic,ppmi_dx,32,0.046415888336127774,test,0.59,0.04442339923958994,0.5523528769516323,0.04878235438006983,0.5522071307300509,0.047175146984217785 +flat_mae,patch,logistic,ppmi_dx,33,0.046415888336127774,train,0.800711743772242,0.01640349372698652,0.7801159784811011,0.019012725113282992,0.7711812245771783,0.01891881742956175 +flat_mae,patch,logistic,ppmi_dx,33,0.046415888336127774,test,0.65,0.04518942796716949,0.6224786970121885,0.048343332283195456,0.6209677419354839,0.04735814247153806 +flat_mae,patch,logistic,ppmi_dx,34,0.046415888336127774,train,0.802491103202847,0.015774189452209698,0.7807426673461857,0.018185409265196503,0.7708868550631557,0.017882960110869362 +flat_mae,patch,logistic,ppmi_dx,34,0.046415888336127774,test,0.66,0.04669074426478978,0.6212121212121212,0.05360118452841732,0.6188455008488964,0.051031177516194806 +flat_mae,patch,logistic,ppmi_dx,35,0.046415888336127774,train,0.798932384341637,0.015692364813688166,0.7756629681047609,0.018353258146308775,0.7653874973239134,0.0180231673093494 +flat_mae,patch,logistic,ppmi_dx,35,0.046415888336127774,test,0.58,0.04654632101466237,0.5320855614973261,0.050330225124594785,0.533955857385399,0.04761168840815089 +flat_mae,patch,logistic,ppmi_dx,36,0.046415888336127774,train,0.806049822064057,0.016181420309806353,0.7872653713253808,0.018114156482839303,0.7789953971312353,0.017916232807641333 +flat_mae,patch,logistic,ppmi_dx,36,0.046415888336127774,test,0.66,0.04182862177982918,0.609375,0.04929481151036894,0.6086587436332768,0.04513688430611474 +flat_mae,patch,logistic,ppmi_dx,37,0.005994842503189409,train,0.7295373665480427,0.016980450446604393,0.6884927870239363,0.020902702571822435,0.6820675444230357,0.019189318075329732 +flat_mae,patch,logistic,ppmi_dx,37,0.005994842503189409,test,0.61,0.04401465210586129,0.5555555555555556,0.05222600923540524,0.5581494057724957,0.047846027667249595 +flat_mae,patch,logistic,ppmi_dx,38,2.782559402207126,train,0.998220640569395,0.0017441752747982286,0.9981184064710746,0.0018474728743590103,0.9976851851851851,0.002269042834343988 +flat_mae,patch,logistic,ppmi_dx,38,2.782559402207126,test,0.58,0.047328718554383024,0.5625,0.04842253499225299,0.564516129032258,0.0491705209188936 +flat_mae,patch,logistic,ppmi_dx,39,0.046415888336127774,train,0.7846975088967971,0.01548210855186356,0.7615796984071889,0.018054515834735645,0.7529570755726824,0.01778120170155801 +flat_mae,patch,logistic,ppmi_dx,39,0.046415888336127774,test,0.65,0.04537444214533111,0.612789025334661,0.05084475211997903,0.6107809847198642,0.04848984150167517 +flat_mae,patch,logistic,ppmi_dx,40,0.005994842503189409,train,0.7259786476868327,0.01688808961446214,0.6805167958656331,0.02133169809502727,0.6748287304645686,0.019271713068267318 +flat_mae,patch,logistic,ppmi_dx,40,0.005994842503189409,test,0.69,0.04179364066457958,0.6408295678368672,0.05118201359223908,0.6379456706281834,0.046496184791916875 +flat_mae,patch,logistic,ppmi_dx,41,0.046415888336127774,train,0.7900355871886121,0.01691987109785742,0.767775100851636,0.019272482121410084,0.7590317919075145,0.0188554611681638 +flat_mae,patch,logistic,ppmi_dx,41,0.046415888336127774,test,0.7,0.04463047837520902,0.6703296703296704,0.05017891271118844,0.666383701188455,0.04829356279376383 +flat_mae,patch,logistic,ppmi_dx,42,2.782559402207126,train,0.9911032028469751,0.003932142792214179,0.9906083829373369,0.0041467494738902655,0.9910351102547634,0.004091887502701691 +flat_mae,patch,logistic,ppmi_dx,42,2.782559402207126,test,0.7,0.04286012132507326,0.66078697421981,0.050770861215871384,0.6561969439728353,0.04769077240605358 +flat_mae,patch,logistic,ppmi_dx,43,0.005994842503189409,train,0.7313167259786477,0.017065330089547328,0.6872288748097286,0.021585230038705164,0.6809034467994005,0.019570137325234275 +flat_mae,patch,logistic,ppmi_dx,43,0.005994842503189409,test,0.68,0.03934513947109604,0.6259934548854604,0.04974536632264634,0.6247877758913413,0.04443039888579244 +flat_mae,patch,logistic,ppmi_dx,44,0.005994842503189409,train,0.7099644128113879,0.016643727115924725,0.664440740672906,0.020820093452991354,0.6600834938985227,0.018867096260480776 +flat_mae,patch,logistic,ppmi_dx,44,0.005994842503189409,test,0.66,0.040907720542704404,0.5952380952380952,0.05248656123462312,0.5984719864176571,0.045741190653264534 +flat_mae,patch,logistic,ppmi_dx,45,0.046415888336127774,train,0.802491103202847,0.016525789192602666,0.7823400313325402,0.01890000678951726,0.7734960393919932,0.018738816749694024 +flat_mae,patch,logistic,ppmi_dx,45,0.046415888336127774,test,0.7,0.04061213611717561,0.6493688639551192,0.05147399579392377,0.6460101867572157,0.04614828413001342 +flat_mae,patch,logistic,ppmi_dx,46,0.046415888336127774,train,0.798932384341637,0.015505276819526192,0.7773430241323334,0.01772307009772328,0.767996681652751,0.017417049716822435 +flat_mae,patch,logistic,ppmi_dx,46,0.046415888336127774,test,0.61,0.04181327540387144,0.5623386825272135,0.04841200966980496,0.5632427843803056,0.04500502147630503 +flat_mae,patch,logistic,ppmi_dx,47,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,47,21.54434690031882,test,0.59,0.04904415969307661,0.5746446726838883,0.04983720463363063,0.5776740237691002,0.050702548638163016 +flat_mae,patch,logistic,ppmi_dx,48,0.046415888336127774,train,0.791814946619217,0.01644636423711485,0.7711176783868172,0.01862115145611809,0.7630860629415542,0.01837872756166759 +flat_mae,patch,logistic,ppmi_dx,48,0.046415888336127774,test,0.71,0.040630722366209536,0.6745595331612613,0.0483675834195765,0.6693548387096775,0.04568918125151079 +flat_mae,patch,logistic,ppmi_dx,49,0.046415888336127774,train,0.800711743772242,0.016201162885858468,0.7795831465710443,0.018518409278400483,0.7703114964675658,0.01825680515787128 +flat_mae,patch,logistic,ppmi_dx,49,0.046415888336127774,test,0.67,0.04121426452091556,0.6239316239316239,0.04940639805835933,0.6218166383701189,0.04535227735436443 +flat_mae,patch,logistic,ppmi_dx,50,2.782559402207126,train,0.998220640569395,0.0017461092626241419,0.9981184064710746,0.00184954188936297,0.9976851851851851,0.0022715588092471484 +flat_mae,patch,logistic,ppmi_dx,50,2.782559402207126,test,0.59,0.046017818288137044,0.5464100011063171,0.05059217614225692,0.5471137521222411,0.048420730238867976 +flat_mae,patch,logistic,ppmi_dx,51,0.046415888336127774,train,0.7953736654804271,0.016423454386289945,0.7739537974572863,0.01886037950395491,0.7651065082423465,0.018568620824630885 +flat_mae,patch,logistic,ppmi_dx,51,0.046415888336127774,test,0.64,0.04397155444147956,0.5792426367461431,0.05222625514827588,0.5823429541595926,0.04677527272826889 +flat_mae,patch,logistic,ppmi_dx,52,0.046415888336127774,train,0.8220640569395018,0.015533102999340982,0.8041429686628749,0.017531684845457515,0.7946103618068936,0.017351943784517466 +flat_mae,patch,logistic,ppmi_dx,52,0.046415888336127774,test,0.6,0.0448325060642387,0.554367201426025,0.04937328699233185,0.5551782682512734,0.04681806911201723 +flat_mae,patch,logistic,ppmi_dx,53,0.046415888336127774,train,0.8131672597864769,0.015279335289981084,0.7955436059303096,0.017304147120943216,0.787384928280882,0.017423531930150525 +flat_mae,patch,logistic,ppmi_dx,53,0.046415888336127774,test,0.67,0.04337266881343595,0.6349153667441089,0.048989945300461406,0.6320033955857385,0.046766556084593916 +flat_mae,patch,logistic,ppmi_dx,54,0.005994842503189409,train,0.7384341637010676,0.0171258607874583,0.6991861925828827,0.020809466944614493,0.6919021622778848,0.01916515222405446 +flat_mae,patch,logistic,ppmi_dx,54,0.005994842503189409,test,0.58,0.04676878873778964,0.5442708333333334,0.04843310216947664,0.5441426146010186,0.0472113603300133 +flat_mae,patch,logistic,ppmi_dx,55,0.046415888336127774,train,0.7829181494661922,0.01624138584610155,0.7593130853588328,0.018788735575357596,0.7506422607578678,0.018410470891413157 +flat_mae,patch,logistic,ppmi_dx,55,0.046415888336127774,test,0.7,0.0437165597914566,0.6782496782496783,0.047587679305436885,0.6765704584040747,0.047186696495035464 +flat_mae,patch,logistic,ppmi_dx,56,0.005994842503189409,train,0.7330960854092526,0.016131453562060003,0.6878332740846071,0.02075627982364855,0.6814788053949904,0.018704229869078024 +flat_mae,patch,logistic,ppmi_dx,56,0.005994842503189409,test,0.61,0.044149183457907804,0.5400400990682863,0.05253199091442738,0.547962648556876,0.04636255508727724 +flat_mae,patch,logistic,ppmi_dx,57,0.3593813663804626,train,0.9074733096085409,0.012090649262850592,0.900776836158192,0.013189893929918171,0.8952847356026546,0.01395026535540675 +flat_mae,patch,logistic,ppmi_dx,57,0.3593813663804626,test,0.6,0.05037013003755301,0.5659722222222222,0.05314433866528686,0.565365025466893,0.051863478250622645 +flat_mae,patch,logistic,ppmi_dx,58,0.3593813663804626,train,0.9217081850533808,0.011134750782637724,0.9163690476190476,0.01199025730876009,0.9120637979019481,0.012523897172458838 +flat_mae,patch,logistic,ppmi_dx,58,0.3593813663804626,test,0.6,0.04457899056730648,0.554367201426025,0.05069376388798931,0.5551782682512734,0.04761335818417384 +flat_mae,patch,logistic,ppmi_dx,59,0.3593813663804626,train,0.9181494661921709,0.011162468437231449,0.9123981728723043,0.012051575566941003,0.9074341682723186,0.012585439090926702 +flat_mae,patch,logistic,ppmi_dx,59,0.3593813663804626,test,0.65,0.04732516877941377,0.6224786970121885,0.05164255950736557,0.6209677419354839,0.05071289574401067 +flat_mae,patch,logistic,ppmi_dx,60,2.782559402207126,train,0.9928825622775801,0.003499225119432666,0.9924669928288989,0.003713394751238555,0.9916104688503533,0.004227232701225035 +flat_mae,patch,logistic,ppmi_dx,60,2.782559402207126,test,0.67,0.04799641236592585,0.648,0.05074042536937323,0.6472835314091681,0.050439675141716135 +flat_mae,patch,logistic,ppmi_dx,61,0.046415888336127774,train,0.800711743772242,0.015355974977283093,0.7795831465710443,0.017796760842318928,0.7703114964675658,0.017723797569483477 +flat_mae,patch,logistic,ppmi_dx,61,0.046415888336127774,test,0.66,0.041530634476251375,0.6155585707824514,0.04786967198183652,0.6137521222410866,0.04442562159042684 +flat_mae,patch,logistic,ppmi_dx,62,0.046415888336127774,train,0.8131672597864769,0.015132015744193388,0.7955436059303096,0.01707939490673443,0.787384928280882,0.01714441438123213 +flat_mae,patch,logistic,ppmi_dx,62,0.046415888336127774,test,0.64,0.04365945945611329,0.5863970588235294,0.052664391319532856,0.5874363327674024,0.04767517269032626 +flat_mae,patch,logistic,ppmi_dx,63,0.3593813663804626,train,0.9306049822064056,0.009943811953048828,0.9255085220996822,0.0108354233927683,0.9192892314279597,0.011595542941014472 +flat_mae,patch,logistic,ppmi_dx,63,0.3593813663804626,test,0.57,0.045768159237618455,0.5174503422735944,0.05119428797949125,0.5207979626485568,0.047648250702195354 +flat_mae,patch,logistic,ppmi_dx,64,0.046415888336127774,train,0.8131672597864769,0.01575144245339042,0.7945927882958616,0.018061113616121085,0.785645472061657,0.01817783366163335 +flat_mae,patch,logistic,ppmi_dx,64,0.046415888336127774,test,0.57,0.04313645326171357,0.50997150997151,0.04872982890562392,0.515704584040747,0.04488539784946234 +flat_mae,patch,logistic,ppmi_dx,65,0.046415888336127774,train,0.7935943060498221,0.015774590877551686,0.7733398233780683,0.018035804691981943,0.765400877756369,0.017997465000333116 +flat_mae,patch,logistic,ppmi_dx,65,0.046415888336127774,test,0.59,0.04651881339845203,0.5577607593571352,0.05002162701013753,0.5573005093378608,0.04890770644460969 +flat_mae,patch,logistic,ppmi_dx,66,0.046415888336127774,train,0.8042704626334519,0.01674296517620323,0.7835191618108471,0.019319954780169717,0.774071397987583,0.01911739111311755 +flat_mae,patch,logistic,ppmi_dx,66,0.046415888336127774,test,0.63,0.04657563311432277,0.5847828526540231,0.0528319816448317,0.5844651952461799,0.04925938926596651 +flat_mae,patch,logistic,ppmi_dx,67,2.782559402207126,train,0.998220640569395,0.0017904954023378542,0.9981184064710746,0.0018965794626401612,0.9976851851851851,0.002329301889152484 +flat_mae,patch,logistic,ppmi_dx,67,2.782559402207126,test,0.64,0.047085670856429354,0.625,0.048217977105482174,0.6281833616298811,0.04894235318991474 +flat_mae,patch,logistic,ppmi_dx,68,0.005994842503189409,train,0.7224199288256228,0.01636823291147421,0.6763676633444076,0.02119291191739391,0.6710688289445514,0.019088850931747964 +flat_mae,patch,logistic,ppmi_dx,68,0.005994842503189409,test,0.65,0.04604304073364399,0.6072270227808326,0.0527103434272268,0.6056876061120543,0.0495019600543411 +flat_mae,patch,logistic,ppmi_dx,69,0.046415888336127774,train,0.8185053380782918,0.014511853366196346,0.8011571761571762,0.016423501162352555,0.7925899165061014,0.01653267260941384 +flat_mae,patch,logistic,ppmi_dx,69,0.046415888336127774,test,0.63,0.0448329298618772,0.5847828526540231,0.051344467080479524,0.5844651952461799,0.048076036913162715 +flat_mae,patch,logistic,ppmi_dx,70,0.046415888336127774,train,0.8113879003558719,0.014098551409977508,0.7918954796338993,0.016143218640654797,0.7824609291372298,0.016119948561082273 +flat_mae,patch,logistic,ppmi_dx,70,0.046415888336127774,test,0.58,0.04615509072680932,0.5320855614973261,0.051298754793885806,0.533955857385399,0.04832132558967738 +flat_mae,patch,logistic,ppmi_dx,71,0.3593813663804626,train,0.9181494661921709,0.011200728274378883,0.9128975741239892,0.011968405535591501,0.9100433526011561,0.012340893845604547 +flat_mae,patch,logistic,ppmi_dx,71,0.3593813663804626,test,0.57,0.047585758373698314,0.5305164319248826,0.050916496296405815,0.5309847198641766,0.0492953846098646 +flat_mae,patch,logistic,ppmi_dx,72,0.046415888336127774,train,0.8042704626334519,0.016215586291860342,0.7835191618108471,0.018613822309647223,0.774071397987583,0.018376208380143356 +flat_mae,patch,logistic,ppmi_dx,72,0.046415888336127774,test,0.64,0.048324668648631205,0.6179966044142615,0.05058519279655213,0.6179966044142615,0.05049274201966999 +flat_mae,patch,logistic,ppmi_dx,73,0.046415888336127774,train,0.8042704626334519,0.016755610535470127,0.782987208110423,0.01944946088404476,0.7732016698779705,0.01921257663007098 +flat_mae,patch,logistic,ppmi_dx,73,0.046415888336127774,test,0.69,0.04841692266140011,0.6726850385386971,0.05055529417558738,0.6735993208828523,0.050938449588428074 +flat_mae,patch,logistic,ppmi_dx,74,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,74,166.81005372000556,test,0.56,0.05254868599689244,0.548440065681445,0.05341232084152345,0.5534804753820034,0.05514463189871017 +flat_mae,patch,logistic,ppmi_dx,75,0.046415888336127774,train,0.800711743772242,0.015592499785755153,0.7795831465710443,0.017806862750362473,0.7703114964675658,0.017598349315919474 +flat_mae,patch,logistic,ppmi_dx,75,0.046415888336127774,test,0.66,0.04147042801804679,0.609375,0.049994624945517936,0.6086587436332768,0.04566699049359916 +flat_mae,patch,logistic,ppmi_dx,76,0.3593813663804626,train,0.9145907473309609,0.011500486057974286,0.9087662337662337,0.012432792653191634,0.904543994861914,0.013084010081961113 +flat_mae,patch,logistic,ppmi_dx,76,0.3593813663804626,test,0.67,0.043527572870538045,0.6349153667441089,0.04928365525817913,0.6320033955857385,0.04754762518747834 +flat_mae,patch,logistic,ppmi_dx,77,0.046415888336127774,train,0.8113879003558719,0.01573205363039718,0.7933594183594184,0.01786044183087708,0.7850701134660671,0.017904047026443697 +flat_mae,patch,logistic,ppmi_dx,77,0.046415888336127774,test,0.66,0.04235474471650136,0.609375,0.05102865003392987,0.6086587436332768,0.046623749711630115 +flat_mae,patch,logistic,ppmi_dx,78,0.005994842503189409,train,0.7295373665480427,0.016762683659865017,0.6894124490983129,0.020921200981830607,0.6829372725326482,0.01934245600245569 +flat_mae,patch,logistic,ppmi_dx,78,0.005994842503189409,test,0.66,0.03958421402529043,0.5783730158730158,0.05342410921408157,0.5882852292020373,0.04384902507379352 +flat_mae,patch,logistic,ppmi_dx,79,0.005994842503189409,train,0.7277580071174378,0.01600061856873463,0.6800580454317129,0.02069949382746978,0.6745343609505459,0.018457777488347524 +flat_mae,patch,logistic,ppmi_dx,79,0.005994842503189409,test,0.68,0.03931356508891046,0.6114618746964546,0.05239203681279681,0.6146010186757216,0.044375930769482784 +flat_mae,patch,logistic,ppmi_dx,80,2.782559402207126,train,0.9928825622775801,0.0035058185627303497,0.9924669928288989,0.003718726577896445,0.9916104688503533,0.004179185884405046 +flat_mae,patch,logistic,ppmi_dx,80,2.782559402207126,test,0.59,0.05154018238229276,0.5710848415106182,0.053326632929123985,0.5725806451612903,0.05390279326833323 +flat_mae,patch,logistic,ppmi_dx,81,0.046415888336127774,train,0.798932384341637,0.015331021570275992,0.7767920847758466,0.01783116035273814,0.7671269535431385,0.017620485388232035 +flat_mae,patch,logistic,ppmi_dx,81,0.046415888336127774,test,0.7,0.04287626849435477,0.6782496782496783,0.046123649190583864,0.6765704584040747,0.04566370003181122 +flat_mae,patch,logistic,ppmi_dx,82,0.3593813663804626,train,0.9128113879003559,0.01105355722796981,0.9062194569596415,0.012079694785810037,0.8996199957182616,0.012730853860335884 +flat_mae,patch,logistic,ppmi_dx,82,0.3593813663804626,test,0.63,0.04586632315762842,0.5906626839252129,0.052068046247804985,0.5895585738539898,0.049881044551339064 +flat_mae,patch,logistic,ppmi_dx,83,0.005994842503189409,train,0.7384341637010676,0.016120996441281135,0.7000686167374013,0.019635928186410977,0.6927718903874973,0.01819222390726858 +flat_mae,patch,logistic,ppmi_dx,83,0.005994842503189409,test,0.56,0.04896923115590033,0.5280995280995281,0.0507596435937644,0.5280135823429541,0.050222570996855516 +flat_mae,patch,logistic,ppmi_dx,84,0.046415888336127774,train,0.8256227758007118,0.015528929213151191,0.8080601092896175,0.017784797975032747,0.7983702633269107,0.01791046856375204 +flat_mae,patch,logistic,ppmi_dx,84,0.046415888336127774,test,0.52,0.04661105019198773,0.47916666666666663,0.04936593711643355,0.48047538200339557,0.04819108479443751 +flat_mae,patch,logistic,ppmi_dx,85,0.046415888336127774,train,0.8131672597864769,0.015892488981856304,0.7915452358495565,0.018575020935372808,0.780427103403982,0.01822289146128712 +flat_mae,patch,logistic,ppmi_dx,85,0.046415888336127774,test,0.61,0.04288382445631453,0.5623386825272135,0.04884374748350454,0.5632427843803056,0.045799816179167556 +flat_mae,patch,logistic,ppmi_dx,86,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,86,166.81005372000556,test,0.51,0.049431888493157945,0.49541756770672435,0.049434823590217655,0.49787775891341257,0.05061705552475022 +flat_mae,patch,logistic,ppmi_dx,87,0.046415888336127774,train,0.8256227758007118,0.01598606617095629,0.8080601092896175,0.018230953701928322,0.7983702633269107,0.01823620409202537 +flat_mae,patch,logistic,ppmi_dx,87,0.046415888336127774,test,0.59,0.047800163179637783,0.539894512400404,0.05423964376841728,0.5420203735144312,0.05081695272402467 +flat_mae,patch,logistic,ppmi_dx,88,0.046415888336127774,train,0.8042704626334519,0.016701456620882023,0.7865331491712707,0.018721100081592626,0.779289766645258,0.018721703886257775 +flat_mae,patch,logistic,ppmi_dx,88,0.046415888336127774,test,0.64,0.04339172271297834,0.592944369063772,0.04976338530563623,0.5925297113752122,0.046291675657886215 +flat_mae,patch,logistic,ppmi_dx,89,0.046415888336127774,train,0.800711743772242,0.015700712707680965,0.78064012490242,0.01795814196416069,0.7720509526867909,0.017822190948999728 +flat_mae,patch,logistic,ppmi_dx,89,0.046415888336127774,test,0.62,0.04464815337726747,0.5703301673450927,0.051974738870276996,0.5713073005093379,0.04821664192238187 +flat_mae,patch,logistic,ppmi_dx,90,0.3593813663804626,train,0.905693950177936,0.01199118439459242,0.8989685196679997,0.01296088842697988,0.8938396488974524,0.013366691738697185 +flat_mae,patch,logistic,ppmi_dx,90,0.3593813663804626,test,0.61,0.04755750624244295,0.5793334052421529,0.050551801744011485,0.5785229202037352,0.04954168333857031 +flat_mae,patch,logistic,ppmi_dx,91,0.046415888336127774,train,0.8078291814946619,0.015390005073979026,0.7869328952356881,0.017952410207079935,0.7769615713979876,0.01785120998751394 +flat_mae,patch,logistic,ppmi_dx,91,0.046415888336127774,test,0.63,0.04354221399974972,0.5847828526540231,0.05016862441878902,0.5844651952461799,0.0469940530786375 +flat_mae,patch,logistic,ppmi_dx,92,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,92,166.81005372000556,test,0.58,0.0484552535851377,0.5625,0.0493809192233965,0.564516129032258,0.05030900285007103 +flat_mae,patch,logistic,ppmi_dx,93,0.046415888336127774,train,0.8167259786476868,0.014999736154347573,0.7985053066140357,0.017000576691530645,0.7894053735816742,0.016950527311174662 +flat_mae,patch,logistic,ppmi_dx,93,0.046415888336127774,test,0.58,0.047704926370344604,0.5586380832282472,0.04964033716653903,0.5594227504244482,0.05018699287285203 +flat_mae,patch,logistic,ppmi_dx,94,0.3593813663804626,train,0.9199288256227758,0.011164011330951183,0.9147115063586972,0.012004709507412016,0.9114884393063584,0.012605198647834449 +flat_mae,patch,logistic,ppmi_dx,94,0.3593813663804626,test,0.65,0.04683120327303154,0.6338529134846741,0.04813087561518597,0.6362478777589134,0.048647820196415434 +flat_mae,patch,logistic,ppmi_dx,95,0.005994842503189409,train,0.7437722419928826,0.01698215867762874,0.705759162303665,0.020842311235253815,0.6979768786127167,0.01930242369986129 +flat_mae,patch,logistic,ppmi_dx,95,0.005994842503189409,test,0.58,0.040227607435690226,0.5,0.04727424435494445,0.5135823429541596,0.04157005518064642 +flat_mae,patch,logistic,ppmi_dx,96,0.005994842503189409,train,0.7206405693950177,0.016620495732929515,0.6758045729948596,0.020993880075994852,0.6704934703489617,0.019026067252151987 +flat_mae,patch,logistic,ppmi_dx,96,0.005994842503189409,test,0.58,0.04177008977725568,0.5174632352941176,0.04733110602244182,0.5237691001697793,0.043350729623173906 +flat_mae,patch,logistic,ppmi_dx,97,0.005994842503189409,train,0.7206405693950177,0.01574650821181416,0.6716935498874439,0.020401448503118518,0.6670145579105117,0.018164824339054662 +flat_mae,patch,logistic,ppmi_dx,97,0.005994842503189409,test,0.69,0.04248600240079078,0.6408295678368672,0.05273014045827243,0.6379456706281834,0.04771189782501169 +flat_mae,patch,logistic,ppmi_dx,98,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,98,1291.5496650148827,test,0.53,0.050524841414892135,0.5123975516132379,0.05123246307513497,0.5140067911714771,0.052000230620326014 +flat_mae,patch,logistic,ppmi_dx,99,0.046415888336127774,train,0.8042704626334519,0.01599810140265903,0.7818969531900481,0.018763108134488112,0.7714622136587455,0.018494041771384147 +flat_mae,patch,logistic,ppmi_dx,99,0.046415888336127774,test,0.66,0.043718421746444594,0.6263736263736264,0.04886907479591619,0.6239388794567062,0.047176861103798595 +flat_mae,patch,logistic,ppmi_dx,100,0.046415888336127774,train,0.802491103202847,0.015499630172347355,0.7823400313325402,0.01776274279570208,0.7734960393919932,0.017678085056426034 +flat_mae,patch,logistic,ppmi_dx,100,0.046415888336127774,test,0.59,0.04718590891357291,0.5464100011063171,0.052794771730422276,0.5471137521222411,0.05013364277760485 diff --git a/input_space_v3/flat_lr1e-3_6/eval_v2/ppmi_dx__patch__logistic/log.txt b/input_space_v3/flat_lr1e-3_6/eval_v2/ppmi_dx__patch__logistic/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..5d09914a61d400c01ce2e483610f4cdf1a58835f --- /dev/null +++ b/input_space_v3/flat_lr1e-3_6/eval_v2/ppmi_dx__patch__logistic/log.txt @@ -0,0 +1,247 @@ +fMRI foundation model logistic probe eval +version: 0.1.dev86+gf97f52698 +sha: bcce2b486277d3a5b520775efd9cdf1a2affce36, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-04-08 22:53:56 +config: +output_root: experiments/input_space_v3/output +name_prefix: eval_logistic +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_6; eval v2 (ppmi_dx patch logistic) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: input_space_v3/flat_lr1e-3_6/eval_v2/ppmi_dx__patch__logistic +model: flat_mae +representation: patch +dataset: ppmi_dx +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/eval_v2/ppmi_dx__patch__logistic +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=True, reg_tokens=0, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: ppmi_dx (flat) +train (n=463): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'dir', 'sex', 'age', 'age_bin', 'dx', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 463 +}), + labels=['PD' 'Prodromal'], + counts=[178 285] +) + +validation (n=99): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'dir', 'sex', 'age', 'age_bin', 'dx', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 99 +}), + labels=['PD' 'Prodromal'], + counts=[39 60] +) + +test (n=100): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'dir', 'sex', 'age', 'age_bin', 'dx', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 100 +}), + labels=['PD' 'Prodromal'], + counts=[37 63] +) + +extracting features for all splits +extract (train) [ 0/232] eta: 0:15:28 time: 4.0011 data: 3.1578 max mem: 2698 +extract (train) [ 20/232] eta: 0:01:18 time: 0.1869 data: 0.0615 max mem: 2851 +extract (train) [ 40/232] eta: 0:00:51 time: 0.1628 data: 0.0515 max mem: 2851 +extract (train) [ 60/232] eta: 0:00:39 time: 0.1591 data: 0.0489 max mem: 2851 +extract (train) [ 80/232] eta: 0:00:32 time: 0.1608 data: 0.0486 max mem: 2851 +extract (train) [100/232] eta: 0:00:27 time: 0.1782 data: 0.0588 max mem: 2851 +extract (train) [120/232] eta: 0:00:22 time: 0.1439 data: 0.0400 max mem: 2851 +extract (train) [140/232] eta: 0:00:17 time: 0.1613 data: 0.0507 max mem: 2851 +extract (train) [160/232] eta: 0:00:13 time: 0.1594 data: 0.0505 max mem: 2851 +extract (train) [180/232] eta: 0:00:09 time: 0.1493 data: 0.0451 max mem: 2851 +extract (train) [200/232] eta: 0:00:05 time: 0.1687 data: 0.0534 max mem: 2851 +extract (train) [220/232] eta: 0:00:02 time: 0.1477 data: 0.0446 max mem: 2851 +extract (train) [231/232] eta: 0:00:00 time: 0.1396 data: 0.0401 max mem: 2851 +extract (train) Total time: 0:00:41 (0.1784 s / it) +extract (validation) [ 0/50] eta: 0:02:50 time: 3.4105 data: 3.2882 max mem: 2851 +extract (validation) [20/50] eta: 0:00:10 time: 0.1897 data: 0.0667 max mem: 2851 +extract (validation) [40/50] eta: 0:00:02 time: 0.1317 data: 0.0345 max mem: 2851 +extract (validation) [49/50] eta: 0:00:00 time: 0.1299 data: 0.0348 max mem: 2851 +extract (validation) Total time: 0:00:11 (0.2249 s / it) +extract (test) [ 0/50] eta: 0:02:40 time: 3.2034 data: 3.0519 max mem: 2851 +extract (test) [20/50] eta: 0:00:09 time: 0.1875 data: 0.0670 max mem: 2851 +extract (test) [40/50] eta: 0:00:02 time: 0.1310 data: 0.0340 max mem: 2851 +extract (test) [49/50] eta: 0:00:00 time: 0.1292 data: 0.0330 max mem: 2851 +extract (test) Total time: 0:00:10 (0.2199 s / it) +feature extraction time: 0:01:03 +train features: (463, 768) +validation features: (99, 768) +test features: (100, 768) +evaluating fixed splits +eval results (fixed splits): + +| model | repr | clf | dataset | trial | C | split | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|----------:|:--------|-------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | ppmi_dx | | 0.0059948 | train | 0.7331 | 0.017265 | 0.69259 | 0.02128 | 0.68601 | 0.019522 | +| flat_mae | patch | logistic | ppmi_dx | | 0.0059948 | test | 0.63 | 0.040101 | 0.55524 | 0.048471 | 0.56135 | 0.042456 | + + +evaluating random splits (n=100) +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 1, "C": 0.046415888336127774, "split": "test", "acc": 0.58, "acc_std": 0.04660133474483322, "f1": 0.5320855614973261, "f1_std": 0.05176575962587245, "bacc": 0.533955857385399, "bacc_std": 0.04912325611805353} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 2, "C": 0.046415888336127774, "split": "test", "acc": 0.68, "acc_std": 0.04497458838055107, "f1": 0.6483516483516483, "f1_std": 0.05039782264356867, "bacc": 0.6451612903225806, "bacc_std": 0.048551681011941246} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 3, "C": 0.046415888336127774, "split": "test", "acc": 0.65, "acc_std": 0.04756557999225911, "f1": 0.6178622120318812, "f1_std": 0.05209012325929326, "bacc": 0.615874363327674, "bacc_std": 0.05057320881386341} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 4, "C": 0.005994842503189409, "split": "test", "acc": 0.67, "acc_std": 0.04428771387190808, "f1": 0.6396986570586308, "f1_std": 0.04891518223870444, "bacc": 0.6370967741935484, "bacc_std": 0.04751403084347118} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 5, "C": 0.046415888336127774, "split": "test", "acc": 0.57, "acc_std": 0.04630194812316216, "f1": 0.5242836596968692, "f1_std": 0.05010112055333546, "bacc": 0.5258913412563667, "bacc_std": 0.04770934868646893} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 6, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.04371957913795603, "f1": 0.5404411764705883, "f1_std": 0.052417179482480085, "bacc": 0.5449915110356536, "bacc_std": 0.047359284646267104} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 7, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.048089462463204974, "f1": 0.5604395604395604, "f1_std": 0.05300073107157988, "bacc": 0.5602716468590832, "bacc_std": 0.05084553856989655} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 8, "C": 0.3593813663804626, "split": "test", "acc": 0.51, "acc_std": 0.04784367878832062, "f1": 0.4650070968446337, "f1_std": 0.04999665079856131, "bacc": 0.4673174872665535, "bacc_std": 0.04851287545390451} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 9, "C": 0.046415888336127774, "split": "test", "acc": 0.59, "acc_std": 0.04481060588744588, "f1": 0.539894512400404, "f1_std": 0.050458058756134294, "bacc": 0.5420203735144312, "bacc_std": 0.04718799228833209} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 10, "C": 0.046415888336127774, "split": "test", "acc": 0.63, "acc_std": 0.045389315923463756, "f1": 0.5960257670051315, "f1_std": 0.04952095580035658, "bacc": 0.5946519524617997, "bacc_std": 0.048059808698812566} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 11, "C": 0.3593813663804626, "split": "test", "acc": 0.64, "acc_std": 0.04498929205933342, "f1": 0.609375, "f1_std": 0.04868474372730309, "bacc": 0.6078098471986417, "bacc_std": 0.047415609721737056} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 12, "C": 0.005994842503189409, "split": "test", "acc": 0.59, "acc_std": 0.040240571566517294, "f1": 0.4969942338363391, "f1_std": 0.04915305095845323, "bacc": 0.516553480475382, "bacc_std": 0.04190412204625201} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 13, "C": 0.005994842503189409, "split": "test", "acc": 0.65, "acc_std": 0.04095558569963321, "f1": 0.5872154735228211, "f1_std": 0.0507462687949308, "bacc": 0.5904074702886248, "bacc_std": 0.04435845448743415} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 14, "C": 0.005994842503189409, "split": "test", "acc": 0.61, "acc_std": 0.04338144764758318, "f1": 0.5481404240528328, "f1_std": 0.052120742637302174, "bacc": 0.5530560271646858, "bacc_std": 0.046730846243111024} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 15, "C": 0.005994842503189409, "split": "test", "acc": 0.66, "acc_std": 0.04401931848631915, "f1": 0.6155585707824514, "f1_std": 0.051069989802688696, "bacc": 0.6137521222410866, "bacc_std": 0.04757939958446529} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 16, "C": 0.3593813663804626, "split": "test", "acc": 0.57, "acc_std": 0.0478549934698564, "f1": 0.5601023017902813, "f1_std": 0.048118226182940614, "bacc": 0.5666383701188455, "bacc_std": 0.049613872052592524} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 17, "C": 0.005994842503189409, "split": "test", "acc": 0.63, "acc_std": 0.043295339241077674, "f1": 0.5713127099988413, "f1_std": 0.05077577387216064, "bacc": 0.5742784380305602, "bacc_std": 0.045973750788900224} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 18, "C": 0.046415888336127774, "split": "test", "acc": 0.6, "acc_std": 0.04764092358466615, "f1": 0.554367201426025, "f1_std": 0.05170213639945616, "bacc": 0.5551782682512734, "bacc_std": 0.04899450173336097} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 19, "C": 0.3593813663804626, "split": "test", "acc": 0.54, "acc_std": 0.04688617706744707, "f1": 0.5208333333333334, "f1_std": 0.04791023811715692, "bacc": 0.5220713073005093, "bacc_std": 0.048884007157280376} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 20, "C": 0.005994842503189409, "split": "test", "acc": 0.66, "acc_std": 0.03972859927055068, "f1": 0.5952380952380952, "f1_std": 0.05072609987204646, "bacc": 0.5984719864176571, "bacc_std": 0.04382273468548006} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 21, "C": 0.046415888336127774, "split": "test", "acc": 0.72, "acc_std": 0.04150882315845632, "f1": 0.6880570409982174, "f1_std": 0.048165353701470966, "bacc": 0.6825127334465195, "bacc_std": 0.04605804764221196} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 22, "C": 0.046415888336127774, "split": "test", "acc": 0.55, "acc_std": 0.047478715231143304, "f1": 0.5021573182874212, "f1_std": 0.050901953087246966, "bacc": 0.5046689303904923, "bacc_std": 0.04877692268086728} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 23, "C": 0.3593813663804626, "split": "test", "acc": 0.59, "acc_std": 0.0467414334397224, "f1": 0.539894512400404, "f1_std": 0.05275522554754379, "bacc": 0.5420203735144312, "bacc_std": 0.04933886273735273} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 24, "C": 0.046415888336127774, "split": "test", "acc": 0.63, "acc_std": 0.04958807921264949, "f1": 0.5960257670051315, "f1_std": 0.05403951352479992, "bacc": 0.5946519524617997, "bacc_std": 0.052347132914715176} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 25, "C": 0.046415888336127774, "split": "test", "acc": 0.61, "acc_std": 0.03148263648425907, "f1": 0.48677457560205295, "f1_std": 0.04570286159679321, "bacc": 0.5224957555178268, "bacc_std": 0.033816438089549324} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 26, "C": 0.3593813663804626, "split": "test", "acc": 0.67, "acc_std": 0.045178154012752665, "f1": 0.648, "f1_std": 0.04801809402048528, "bacc": 0.6472835314091681, "bacc_std": 0.047579966675409494} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 27, "C": 21.54434690031882, "split": "test", "acc": 0.58, "acc_std": 0.04854441265480508, "f1": 0.5689655172413793, "f1_std": 0.04888011660386603, "bacc": 0.5747028862478778, "bacc_std": 0.05048159869477411} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 28, "C": 0.3593813663804626, "split": "test", "acc": 0.66, "acc_std": 0.04278307609324042, "f1": 0.6155585707824514, "f1_std": 0.05065039274993392, "bacc": 0.6137521222410866, "bacc_std": 0.04691816784927534} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 29, "C": 0.046415888336127774, "split": "test", "acc": 0.64, "acc_std": 0.04313189075382622, "f1": 0.5863970588235294, "f1_std": 0.052045514845899594, "bacc": 0.5874363327674024, "bacc_std": 0.04701534503227411} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 30, "C": 10000.0, "split": "test", "acc": 0.52, "acc_std": 0.05011080123087237, "f1": 0.5, "f1_std": 0.05160845611383304, "bacc": 0.5008488964346349, "bacc_std": 0.05241884392429196} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 31, "C": 0.046415888336127774, "split": "test", "acc": 0.68, "acc_std": 0.048259709903811066, "f1": 0.6483516483516483, "f1_std": 0.05332513984898903, "bacc": 0.6451612903225806, "bacc_std": 0.05159320039749484} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 32, "C": 0.046415888336127774, "split": "test", "acc": 0.59, "acc_std": 0.04442339923958994, "f1": 0.5523528769516323, "f1_std": 0.04878235438006983, "bacc": 0.5522071307300509, "bacc_std": 0.047175146984217785} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 33, "C": 0.046415888336127774, "split": "test", "acc": 0.65, "acc_std": 0.04518942796716949, "f1": 0.6224786970121885, "f1_std": 0.048343332283195456, "bacc": 0.6209677419354839, "bacc_std": 0.04735814247153806} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 34, "C": 0.046415888336127774, "split": "test", "acc": 0.66, "acc_std": 0.04669074426478978, "f1": 0.6212121212121212, "f1_std": 0.05360118452841732, "bacc": 0.6188455008488964, "bacc_std": 0.051031177516194806} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 35, "C": 0.046415888336127774, "split": "test", "acc": 0.58, "acc_std": 0.04654632101466237, "f1": 0.5320855614973261, "f1_std": 0.050330225124594785, "bacc": 0.533955857385399, "bacc_std": 0.04761168840815089} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 36, "C": 0.046415888336127774, "split": "test", "acc": 0.66, "acc_std": 0.04182862177982918, "f1": 0.609375, "f1_std": 0.04929481151036894, "bacc": 0.6086587436332768, "bacc_std": 0.04513688430611474} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 37, "C": 0.005994842503189409, "split": "test", "acc": 0.61, "acc_std": 0.04401465210586129, "f1": 0.5555555555555556, "f1_std": 0.05222600923540524, "bacc": 0.5581494057724957, "bacc_std": 0.047846027667249595} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 38, "C": 2.782559402207126, "split": "test", "acc": 0.58, "acc_std": 0.047328718554383024, "f1": 0.5625, "f1_std": 0.04842253499225299, "bacc": 0.564516129032258, "bacc_std": 0.0491705209188936} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 39, "C": 0.046415888336127774, "split": "test", "acc": 0.65, "acc_std": 0.04537444214533111, "f1": 0.612789025334661, "f1_std": 0.05084475211997903, "bacc": 0.6107809847198642, "bacc_std": 0.04848984150167517} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 40, "C": 0.005994842503189409, "split": "test", "acc": 0.69, "acc_std": 0.04179364066457958, "f1": 0.6408295678368672, "f1_std": 0.05118201359223908, "bacc": 0.6379456706281834, "bacc_std": 0.046496184791916875} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 41, "C": 0.046415888336127774, "split": "test", "acc": 0.7, "acc_std": 0.04463047837520902, "f1": 0.6703296703296704, "f1_std": 0.05017891271118844, "bacc": 0.666383701188455, "bacc_std": 0.04829356279376383} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 42, "C": 2.782559402207126, "split": "test", "acc": 0.7, "acc_std": 0.04286012132507326, "f1": 0.66078697421981, "f1_std": 0.050770861215871384, "bacc": 0.6561969439728353, "bacc_std": 0.04769077240605358} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 43, "C": 0.005994842503189409, "split": "test", "acc": 0.68, "acc_std": 0.03934513947109604, "f1": 0.6259934548854604, "f1_std": 0.04974536632264634, "bacc": 0.6247877758913413, "bacc_std": 0.04443039888579244} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 44, "C": 0.005994842503189409, "split": "test", "acc": 0.66, "acc_std": 0.040907720542704404, "f1": 0.5952380952380952, "f1_std": 0.05248656123462312, "bacc": 0.5984719864176571, "bacc_std": 0.045741190653264534} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 45, "C": 0.046415888336127774, "split": "test", "acc": 0.7, "acc_std": 0.04061213611717561, "f1": 0.6493688639551192, "f1_std": 0.05147399579392377, "bacc": 0.6460101867572157, "bacc_std": 0.04614828413001342} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 46, "C": 0.046415888336127774, "split": "test", "acc": 0.61, "acc_std": 0.04181327540387144, "f1": 0.5623386825272135, "f1_std": 0.04841200966980496, "bacc": 0.5632427843803056, "bacc_std": 0.04500502147630503} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 47, "C": 21.54434690031882, "split": "test", "acc": 0.59, "acc_std": 0.04904415969307661, "f1": 0.5746446726838883, "f1_std": 0.04983720463363063, "bacc": 0.5776740237691002, "bacc_std": 0.050702548638163016} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 48, "C": 0.046415888336127774, "split": "test", "acc": 0.71, "acc_std": 0.040630722366209536, "f1": 0.6745595331612613, "f1_std": 0.0483675834195765, "bacc": 0.6693548387096775, "bacc_std": 0.04568918125151079} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 49, "C": 0.046415888336127774, "split": "test", "acc": 0.67, "acc_std": 0.04121426452091556, "f1": 0.6239316239316239, "f1_std": 0.04940639805835933, "bacc": 0.6218166383701189, "bacc_std": 0.04535227735436443} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 50, "C": 2.782559402207126, "split": "test", "acc": 0.59, "acc_std": 0.046017818288137044, "f1": 0.5464100011063171, "f1_std": 0.05059217614225692, "bacc": 0.5471137521222411, "bacc_std": 0.048420730238867976} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 51, "C": 0.046415888336127774, "split": "test", "acc": 0.64, "acc_std": 0.04397155444147956, "f1": 0.5792426367461431, "f1_std": 0.05222625514827588, "bacc": 0.5823429541595926, "bacc_std": 0.04677527272826889} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 52, "C": 0.046415888336127774, "split": "test", "acc": 0.6, "acc_std": 0.0448325060642387, "f1": 0.554367201426025, "f1_std": 0.04937328699233185, "bacc": 0.5551782682512734, "bacc_std": 0.04681806911201723} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 53, "C": 0.046415888336127774, "split": "test", "acc": 0.67, "acc_std": 0.04337266881343595, "f1": 0.6349153667441089, "f1_std": 0.048989945300461406, "bacc": 0.6320033955857385, "bacc_std": 0.046766556084593916} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 54, "C": 0.005994842503189409, "split": "test", "acc": 0.58, "acc_std": 0.04676878873778964, "f1": 0.5442708333333334, "f1_std": 0.04843310216947664, "bacc": 0.5441426146010186, "bacc_std": 0.0472113603300133} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 55, "C": 0.046415888336127774, "split": "test", "acc": 0.7, "acc_std": 0.0437165597914566, "f1": 0.6782496782496783, "f1_std": 0.047587679305436885, "bacc": 0.6765704584040747, "bacc_std": 0.047186696495035464} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 56, "C": 0.005994842503189409, "split": "test", "acc": 0.61, "acc_std": 0.044149183457907804, "f1": 0.5400400990682863, "f1_std": 0.05253199091442738, "bacc": 0.547962648556876, "bacc_std": 0.04636255508727724} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 57, "C": 0.3593813663804626, "split": "test", "acc": 0.6, "acc_std": 0.05037013003755301, "f1": 0.5659722222222222, "f1_std": 0.05314433866528686, "bacc": 0.565365025466893, "bacc_std": 0.051863478250622645} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 58, "C": 0.3593813663804626, "split": "test", "acc": 0.6, "acc_std": 0.04457899056730648, "f1": 0.554367201426025, "f1_std": 0.05069376388798931, "bacc": 0.5551782682512734, "bacc_std": 0.04761335818417384} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 59, "C": 0.3593813663804626, "split": "test", "acc": 0.65, "acc_std": 0.04732516877941377, "f1": 0.6224786970121885, "f1_std": 0.05164255950736557, "bacc": 0.6209677419354839, "bacc_std": 0.05071289574401067} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 60, "C": 2.782559402207126, "split": "test", "acc": 0.67, "acc_std": 0.04799641236592585, "f1": 0.648, "f1_std": 0.05074042536937323, "bacc": 0.6472835314091681, "bacc_std": 0.050439675141716135} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 61, "C": 0.046415888336127774, "split": "test", "acc": 0.66, "acc_std": 0.041530634476251375, "f1": 0.6155585707824514, "f1_std": 0.04786967198183652, "bacc": 0.6137521222410866, "bacc_std": 0.04442562159042684} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 62, "C": 0.046415888336127774, "split": "test", "acc": 0.64, "acc_std": 0.04365945945611329, "f1": 0.5863970588235294, "f1_std": 0.052664391319532856, "bacc": 0.5874363327674024, "bacc_std": 0.04767517269032626} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 63, "C": 0.3593813663804626, "split": "test", "acc": 0.57, "acc_std": 0.045768159237618455, "f1": 0.5174503422735944, "f1_std": 0.05119428797949125, "bacc": 0.5207979626485568, "bacc_std": 0.047648250702195354} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 64, "C": 0.046415888336127774, "split": "test", "acc": 0.57, "acc_std": 0.04313645326171357, "f1": 0.50997150997151, "f1_std": 0.04872982890562392, "bacc": 0.515704584040747, "bacc_std": 0.04488539784946234} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 65, "C": 0.046415888336127774, "split": "test", "acc": 0.59, "acc_std": 0.04651881339845203, "f1": 0.5577607593571352, "f1_std": 0.05002162701013753, "bacc": 0.5573005093378608, "bacc_std": 0.04890770644460969} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 66, "C": 0.046415888336127774, "split": "test", "acc": 0.63, "acc_std": 0.04657563311432277, "f1": 0.5847828526540231, "f1_std": 0.0528319816448317, "bacc": 0.5844651952461799, "bacc_std": 0.04925938926596651} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 67, "C": 2.782559402207126, "split": "test", "acc": 0.64, "acc_std": 0.047085670856429354, "f1": 0.625, "f1_std": 0.048217977105482174, "bacc": 0.6281833616298811, "bacc_std": 0.04894235318991474} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 68, "C": 0.005994842503189409, "split": "test", "acc": 0.65, "acc_std": 0.04604304073364399, "f1": 0.6072270227808326, "f1_std": 0.0527103434272268, "bacc": 0.6056876061120543, "bacc_std": 0.0495019600543411} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 69, "C": 0.046415888336127774, "split": "test", "acc": 0.63, "acc_std": 0.0448329298618772, "f1": 0.5847828526540231, "f1_std": 0.051344467080479524, "bacc": 0.5844651952461799, "bacc_std": 0.048076036913162715} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 70, "C": 0.046415888336127774, "split": "test", "acc": 0.58, "acc_std": 0.04615509072680932, "f1": 0.5320855614973261, "f1_std": 0.051298754793885806, "bacc": 0.533955857385399, "bacc_std": 0.04832132558967738} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 71, "C": 0.3593813663804626, "split": "test", "acc": 0.57, "acc_std": 0.047585758373698314, "f1": 0.5305164319248826, "f1_std": 0.050916496296405815, "bacc": 0.5309847198641766, "bacc_std": 0.0492953846098646} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 72, "C": 0.046415888336127774, "split": "test", "acc": 0.64, "acc_std": 0.048324668648631205, "f1": 0.6179966044142615, "f1_std": 0.05058519279655213, "bacc": 0.6179966044142615, "bacc_std": 0.05049274201966999} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 73, "C": 0.046415888336127774, "split": "test", "acc": 0.69, "acc_std": 0.04841692266140011, "f1": 0.6726850385386971, "f1_std": 0.05055529417558738, "bacc": 0.6735993208828523, "bacc_std": 0.050938449588428074} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 74, "C": 166.81005372000556, "split": "test", "acc": 0.56, "acc_std": 0.05254868599689244, "f1": 0.548440065681445, "f1_std": 0.05341232084152345, "bacc": 0.5534804753820034, "bacc_std": 0.05514463189871017} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 75, "C": 0.046415888336127774, "split": "test", "acc": 0.66, "acc_std": 0.04147042801804679, "f1": 0.609375, "f1_std": 0.049994624945517936, "bacc": 0.6086587436332768, "bacc_std": 0.04566699049359916} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 76, "C": 0.3593813663804626, "split": "test", "acc": 0.67, "acc_std": 0.043527572870538045, "f1": 0.6349153667441089, "f1_std": 0.04928365525817913, "bacc": 0.6320033955857385, "bacc_std": 0.04754762518747834} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 77, "C": 0.046415888336127774, "split": "test", "acc": 0.66, "acc_std": 0.04235474471650136, "f1": 0.609375, "f1_std": 0.05102865003392987, "bacc": 0.6086587436332768, "bacc_std": 0.046623749711630115} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 78, "C": 0.005994842503189409, "split": "test", "acc": 0.66, "acc_std": 0.03958421402529043, "f1": 0.5783730158730158, "f1_std": 0.05342410921408157, "bacc": 0.5882852292020373, "bacc_std": 0.04384902507379352} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 79, "C": 0.005994842503189409, "split": "test", "acc": 0.68, "acc_std": 0.03931356508891046, "f1": 0.6114618746964546, "f1_std": 0.05239203681279681, "bacc": 0.6146010186757216, "bacc_std": 0.044375930769482784} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 80, "C": 2.782559402207126, "split": "test", "acc": 0.59, "acc_std": 0.05154018238229276, "f1": 0.5710848415106182, "f1_std": 0.053326632929123985, "bacc": 0.5725806451612903, "bacc_std": 0.05390279326833323} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 81, "C": 0.046415888336127774, "split": "test", "acc": 0.7, "acc_std": 0.04287626849435477, "f1": 0.6782496782496783, "f1_std": 0.046123649190583864, "bacc": 0.6765704584040747, "bacc_std": 0.04566370003181122} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 82, "C": 0.3593813663804626, "split": "test", "acc": 0.63, "acc_std": 0.04586632315762842, "f1": 0.5906626839252129, "f1_std": 0.052068046247804985, "bacc": 0.5895585738539898, "bacc_std": 0.049881044551339064} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 83, "C": 0.005994842503189409, "split": "test", "acc": 0.56, "acc_std": 0.04896923115590033, "f1": 0.5280995280995281, "f1_std": 0.0507596435937644, "bacc": 0.5280135823429541, "bacc_std": 0.050222570996855516} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 84, "C": 0.046415888336127774, "split": "test", "acc": 0.52, "acc_std": 0.04661105019198773, "f1": 0.47916666666666663, "f1_std": 0.04936593711643355, "bacc": 0.48047538200339557, "bacc_std": 0.04819108479443751} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 85, "C": 0.046415888336127774, "split": "test", "acc": 0.61, "acc_std": 0.04288382445631453, "f1": 0.5623386825272135, "f1_std": 0.04884374748350454, "bacc": 0.5632427843803056, "bacc_std": 0.045799816179167556} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 86, "C": 166.81005372000556, "split": "test", "acc": 0.51, "acc_std": 0.049431888493157945, "f1": 0.49541756770672435, "f1_std": 0.049434823590217655, "bacc": 0.49787775891341257, "bacc_std": 0.05061705552475022} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 87, "C": 0.046415888336127774, "split": "test", "acc": 0.59, "acc_std": 0.047800163179637783, "f1": 0.539894512400404, "f1_std": 0.05423964376841728, "bacc": 0.5420203735144312, "bacc_std": 0.05081695272402467} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 88, "C": 0.046415888336127774, "split": "test", "acc": 0.64, "acc_std": 0.04339172271297834, "f1": 0.592944369063772, "f1_std": 0.04976338530563623, "bacc": 0.5925297113752122, "bacc_std": 0.046291675657886215} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 89, "C": 0.046415888336127774, "split": "test", "acc": 0.62, "acc_std": 0.04464815337726747, "f1": 0.5703301673450927, "f1_std": 0.051974738870276996, "bacc": 0.5713073005093379, "bacc_std": 0.04821664192238187} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 90, "C": 0.3593813663804626, "split": "test", "acc": 0.61, "acc_std": 0.04755750624244295, "f1": 0.5793334052421529, "f1_std": 0.050551801744011485, "bacc": 0.5785229202037352, "bacc_std": 0.04954168333857031} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 91, "C": 0.046415888336127774, "split": "test", "acc": 0.63, "acc_std": 0.04354221399974972, "f1": 0.5847828526540231, "f1_std": 0.05016862441878902, "bacc": 0.5844651952461799, "bacc_std": 0.0469940530786375} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 92, "C": 166.81005372000556, "split": "test", "acc": 0.58, "acc_std": 0.0484552535851377, "f1": 0.5625, "f1_std": 0.0493809192233965, "bacc": 0.564516129032258, "bacc_std": 0.05030900285007103} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 93, "C": 0.046415888336127774, "split": "test", "acc": 0.58, "acc_std": 0.047704926370344604, "f1": 0.5586380832282472, "f1_std": 0.04964033716653903, "bacc": 0.5594227504244482, "bacc_std": 0.05018699287285203} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 94, "C": 0.3593813663804626, "split": "test", "acc": 0.65, "acc_std": 0.04683120327303154, "f1": 0.6338529134846741, "f1_std": 0.04813087561518597, "bacc": 0.6362478777589134, "bacc_std": 0.048647820196415434} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 95, "C": 0.005994842503189409, "split": "test", "acc": 0.58, "acc_std": 0.040227607435690226, "f1": 0.5, "f1_std": 0.04727424435494445, "bacc": 0.5135823429541596, "bacc_std": 0.04157005518064642} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 96, "C": 0.005994842503189409, "split": "test", "acc": 0.58, "acc_std": 0.04177008977725568, "f1": 0.5174632352941176, "f1_std": 0.04733110602244182, "bacc": 0.5237691001697793, "bacc_std": 0.043350729623173906} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 97, "C": 0.005994842503189409, "split": "test", "acc": 0.69, "acc_std": 0.04248600240079078, "f1": 0.6408295678368672, "f1_std": 0.05273014045827243, "bacc": 0.6379456706281834, "bacc_std": 0.04771189782501169} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 98, "C": 1291.5496650148827, "split": "test", "acc": 0.53, "acc_std": 0.050524841414892135, "f1": 0.5123975516132379, "f1_std": 0.05123246307513497, "bacc": 0.5140067911714771, "bacc_std": 0.052000230620326014} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 99, "C": 0.046415888336127774, "split": "test", "acc": 0.66, "acc_std": 0.043718421746444594, "f1": 0.6263736263736264, "f1_std": 0.04886907479591619, "bacc": 0.6239388794567062, "bacc_std": 0.047176861103798595} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 100, "C": 0.046415888336127774, "split": "test", "acc": 0.59, "acc_std": 0.04718590891357291, "f1": 0.5464100011063171, "f1_std": 0.052794771730422276, "bacc": 0.5471137521222411, "bacc_std": 0.05013364277760485} +eval results (random splits): + +| model | repr | clf | dataset | split | n_trials | C | C_std | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|-----------:|------:|--------:|-------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | ppmi_dx | train | 100 | 118.6 | 1006.8 | 0.8305 | 0.086992 | 0.81005 | 0.10067 | 0.80345 | 0.10261 | +| flat_mae | patch | logistic | ppmi_dx | test | 100 | 118.6 | 1006.8 | 0.6228 | 0.048432 | 0.58123 | 0.050813 | 0.58243 | 0.048123 | + + +done! total time: 0:05:03 diff --git a/input_space_v3/flat_lr1e-3_6/pretrain/config.yaml b/input_space_v3/flat_lr1e-3_6/pretrain/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..3dc78123b508d3e363e79d6d00d3bb154b45663b --- /dev/null +++ b/input_space_v3/flat_lr1e-3_6/pretrain/config.yaml @@ -0,0 +1,102 @@ +name: input_space_v3/flat_lr1e-3_6/pretrain +notes: input_space ablation v3 flat_lr1e-3_6; use tube masking and on-disk data (input_space=flat + base_lr=1e-3 seed=5406) +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain +input_space: flat +patch_size: 16 +num_frames: 16 +t_patch_size: 4 +mask_ratio: 0.9 +pred_mask_ratio: null +masking: tube +masking_kwargs: {} +mask_patch_size: null +model: mae_vit_base +model_kwargs: + decoding: attn + pos_embed: sep + target_norm: null + pca_norm_nc: 2 + t_pred_stride: 2 + no_decode_pos: true + mask_drop_scale: false + pred_edge_pad: 0 + gauss_sigma: null + class_token: true + reg_tokens: 0 + no_embed_class: true + head_init_scale: 0.0 + decoder_depth: 4 + drop_path_rate: 0.0 +datasets: + hcp-train: + type: wds + url: /data/fmri-datasets/pretrain/hcpya-all.${input_space}.wds/hcpya-all-${input_space}-{00000..01799}.tar + clipping: random + clipping_kwargs: + oversample: 4.0 + shuffle: true + buffer_size: 2000 + samples_per_epoch: 200000 + hcp-train-subset: + type: arrow + root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/validation + split_range: + - 0 + - 2000 + shuffle: false + hcp-val: + type: arrow + root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/test + split_range: + - 0 + - 2000 + shuffle: false +train_dataset: hcp-train +eval_datasets: +- hcp-train-subset +- hcp-val +val_dataset: null +clip_vmax: 3.0 +normalize: frame +tr_scale: null +crop_scale: null +crop_aspect: null +gray_jitter: null +num_workers: 16 +epochs: 100 +batch_size: 32 +accum_iter: 1 +base_lr: 0.001 +min_lr: 0.0 +warmup_epochs: 5 +weight_decay: 0.05 +betas: +- 0.9 +- 0.95 +clip_grad: 1.0 +amp: true +amp_dtype: float16 +ckpt: null +resume: true +auto_resume: true +start_epoch: 0 +max_checkpoints: 0 +checkpoint_period: null +plot_period: 5 +device: cuda +presend_cuda: false +seed: 5406 +debug: false +wandb: true +wandb_entity: null +wandb_project: fMRI-foundation-model +rank: 0 +world_size: 1 +gpu: 0 +distributed: true +dist_backend: nccl +in_chans: 1 +img_size: +- 224 +- 560 diff --git a/input_space_v3/flat_lr1e-3_6/pretrain/log.json b/input_space_v3/flat_lr1e-3_6/pretrain/log.json new file mode 100644 index 0000000000000000000000000000000000000000..b66569ba3f563a9e190c882717065856a18ea663 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_6/pretrain/log.json @@ -0,0 +1,100 @@ +{"epoch": 0, "train/lr": 1.2502400076802458e-05, "train/grad": 0.05297370727136731, "train/loss": 0.9932270253753662, "eval/hcp-train-subset/loss": 0.991073360366206, "eval/hcp-val/loss": 0.989056775646825} +{"epoch": 1, "train/lr": 3.750320010240327e-05, "train/grad": 0.08136776958942413, "train/loss": 0.9882140498924256, "eval/hcp-train-subset/loss": 0.9890231336316755, "eval/hcp-val/loss": 0.9866888407737978} +{"epoch": 2, "train/lr": 6.250400012800409e-05, "train/grad": 0.11542759730603436, "train/loss": 0.9848215614700317, "eval/hcp-train-subset/loss": 0.9896896596877806, "eval/hcp-val/loss": 0.9873241541847106} +{"epoch": 3, "train/lr": 8.75048001536049e-05, "train/grad": 0.19678799178696949, "train/loss": 0.977917546749115, "eval/hcp-train-subset/loss": 0.9769882338662301, "eval/hcp-val/loss": 0.9736994216519017} +{"epoch": 4, "train/lr": 0.00011250559953918529, "train/grad": 0.20432350582356126, "train/loss": 0.9529263496017456, "eval/hcp-train-subset/loss": 0.9294796480286506, "eval/hcp-val/loss": 0.9240545505477537} +{"epoch": 5, "train/lr": 0.00012498860637884563, "train/grad": 0.16006844657116717, "train/loss": 0.908236672000885, "eval/hcp-train-subset/loss": 0.8884781666340367, "eval/hcp-val/loss": 0.8828447364991711} +{"epoch": 6, "train/lr": 0.0001249202705377922, "train/grad": 0.11172349795243522, "train/loss": 0.8759741143608093, "eval/hcp-train-subset/loss": 0.8709241055673168, "eval/hcp-val/loss": 0.8646897048719467} +{"epoch": 7, "train/lr": 0.0001247836790473516, "train/grad": 0.0886837012246585, "train/loss": 0.8626153476810455, "eval/hcp-train-subset/loss": 0.8639625041715561, "eval/hcp-val/loss": 0.858037906308328} +{"epoch": 8, "train/lr": 0.000124578981268311, "train/grad": 0.08014311806877385, "train/loss": 0.8565653409385681, "eval/hcp-train-subset/loss": 0.8592434592785374, "eval/hcp-val/loss": 0.8533922212739145} +{"epoch": 9, "train/lr": 0.00012430640103468907, "train/grad": 0.07459918428612011, "train/loss": 0.8521338410186767, "eval/hcp-train-subset/loss": 0.8576540812369315, "eval/hcp-val/loss": 0.8519973043472536} +{"epoch": 10, "train/lr": 0.00012396623640896796, "train/grad": 0.07061451092620019, "train/loss": 0.8495869540977478, "eval/hcp-train-subset/loss": 0.8548817490377734, "eval/hcp-val/loss": 0.8487892977653011} +{"epoch": 11, "train/lr": 0.0001235588593561712, "train/grad": 0.06826981248467608, "train/loss": 0.8481180062675476, "eval/hcp-train-subset/loss": 0.8530562106640108, "eval/hcp-val/loss": 0.8475235883266695} +{"epoch": 12, "train/lr": 0.00012308471533712604, "train/grad": 0.06654154197295005, "train/loss": 0.8465968098545075, "eval/hcp-train-subset/loss": 0.8506049033134214, "eval/hcp-val/loss": 0.8463050040506548} +{"epoch": 13, "train/lr": 0.00012254432282135565, "train/grad": 0.0663193708259455, "train/loss": 0.8450949523448944, "eval/hcp-train-subset/loss": 0.8498505921133103, "eval/hcp-val/loss": 0.8451907702030674} +{"epoch": 14, "train/lr": 0.00012193827272014171, "train/grad": 0.0670930247444362, "train/loss": 0.8439878785133362, "eval/hcp-train-subset/loss": 0.8492885952995669, "eval/hcp-val/loss": 0.8443832589733985} +{"epoch": 15, "train/lr": 0.00012126722774037197, "train/grad": 0.06809601009073316, "train/loss": 0.8390118423366547, "eval/hcp-train-subset/loss": 0.8492520893773725, "eval/hcp-val/loss": 0.8437070644670918} +{"epoch": 16, "train/lr": 0.00012053192165988122, "train/grad": 0.06563895170199541, "train/loss": 0.8414186610794068, "eval/hcp-train-subset/loss": 0.8486154848529447, "eval/hcp-val/loss": 0.8431656139512216} +{"epoch": 17, "train/lr": 0.00011973315852507104, "train/grad": 0.06622469752595286, "train/loss": 0.8394707677078247, "eval/hcp-train-subset/loss": 0.8476645542729285, "eval/hcp-val/loss": 0.8422922395890758} +{"epoch": 18, "train/lr": 0.00011887181177170142, "train/grad": 0.0661078068122468, "train/loss": 0.8397296275138855, "eval/hcp-train-subset/loss": 0.847655669335396, "eval/hcp-val/loss": 0.8424869006679904} +{"epoch": 19, "train/lr": 0.00011794882326980209, "train/grad": 0.06449670130090274, "train/loss": 0.8402369032192231, "eval/hcp-train-subset/loss": 0.8456250467608052, "eval/hcp-val/loss": 0.8416197501843975} +{"epoch": 20, "train/lr": 0.00011696520229374954, "train/grad": 0.06676809777874974, "train/loss": 0.8367129416179657, "eval/hcp-train-subset/loss": 0.8464771547625142, "eval/hcp-val/loss": 0.8418304929810185} +{"epoch": 21, "train/lr": 0.00011592202441863837, "train/grad": 0.06610709598086081, "train/loss": 0.838213967037201, "eval/hcp-train-subset/loss": 0.8447459320868215, "eval/hcp-val/loss": 0.8404281091305518} +{"epoch": 22, "train/lr": 0.00011482043034415979, "train/grad": 0.0670415622920003, "train/loss": 0.8358176145553589, "eval/hcp-train-subset/loss": 0.8440707912368159, "eval/hcp-val/loss": 0.8407692716967675} +{"epoch": 23, "train/lr": 0.00011366162464726024, "train/grad": 0.06747484298437242, "train/loss": 0.8363395930099488, "eval/hcp-train-subset/loss": 0.844263082550418, "eval/hcp-val/loss": 0.8404302212499803} +{"epoch": 24, "train/lr": 0.0001124468744649569, "train/grad": 0.06827216273860555, "train/loss": 0.8340362187862396, "eval/hcp-train-subset/loss": 0.8458217622772339, "eval/hcp-val/loss": 0.8417121383451647} +{"epoch": 25, "train/lr": 0.0001111775081087387, "train/grad": 0.06873942813051115, "train/loss": 0.8364814417743683, "eval/hcp-train-subset/loss": 0.842797524506046, "eval/hcp-val/loss": 0.8402899224911967} +{"epoch": 26, "train/lr": 0.0001098549136120796, "train/grad": 0.06986960559420373, "train/loss": 0.833443611459732, "eval/hcp-train-subset/loss": 0.8427364307065164, "eval/hcp-val/loss": 0.8388467517591292} +{"epoch": 27, "train/lr": 0.00010848053721264312, "train/grad": 0.07022716262654646, "train/loss": 0.8326709211444855, "eval/hcp-train-subset/loss": 0.8433119029768051, "eval/hcp-val/loss": 0.840205208909127} +{"epoch": 28, "train/lr": 0.00010705588177084458, "train/grad": 0.07033231129894567, "train/loss": 0.833445308046341, "eval/hcp-train-subset/loss": 0.8420664014354828, "eval/hcp-val/loss": 0.8394090946643583} +{"epoch": 29, "train/lr": 0.00010558250512649171, "train/grad": 0.07275445484625581, "train/loss": 0.8303346433925629, "eval/hcp-train-subset/loss": 0.8423685210366403, "eval/hcp-val/loss": 0.8394025919898864} +{"epoch": 30, "train/lr": 0.00010406201839531515, "train/grad": 0.0738831023833501, "train/loss": 0.8282977026462555, "eval/hcp-train-subset/loss": 0.8433695464364944, "eval/hcp-val/loss": 0.8390307416838985} +{"epoch": 31, "train/lr": 0.00010249608420723018, "train/grad": 0.07397236149774201, "train/loss": 0.8297283594894409, "eval/hcp-train-subset/loss": 0.8411788921202382, "eval/hcp-val/loss": 0.8390525790952867} +{"epoch": 32, "train/lr": 0.00010088641488828097, "train/grad": 0.07562816348379996, "train/loss": 0.8282333237743378, "eval/hcp-train-subset/loss": 0.8420022831809136, "eval/hcp-val/loss": 0.8387329366899305} +{"epoch": 33, "train/lr": 9.923477058823526e-05, "train/grad": 0.07554322953955481, "train/loss": 0.8297091648674011, "eval/hcp-train-subset/loss": 0.8419081953264052, "eval/hcp-val/loss": 0.839713050473121} +{"epoch": 34, "train/lr": 9.754295735588547e-05, "train/grad": 0.07528134589542596, "train/loss": 0.8285428802776337, "eval/hcp-train-subset/loss": 0.8414291768304764, "eval/hcp-val/loss": 0.8386386777124097} +{"epoch": 35, "train/lr": 9.581282516416285e-05, "train/grad": 0.07613900345352037, "train/loss": 0.8276645287513733, "eval/hcp-train-subset/loss": 0.8417515437449178, "eval/hcp-val/loss": 0.8385778492496859} +{"epoch": 36, "train/lr": 9.404626588721676e-05, "train/grad": 0.07760856827522186, "train/loss": 0.8275255076313018, "eval/hcp-train-subset/loss": 0.8410702136255079, "eval/hcp-val/loss": 0.8387755347836402} +{"epoch": 37, "train/lr": 9.224521123168153e-05, "train/grad": 0.07884478429488913, "train/loss": 0.8264019971847534, "eval/hcp-train-subset/loss": 0.841603111836218, "eval/hcp-val/loss": 0.83841063418696} +{"epoch": 38, "train/lr": 9.041163062437843e-05, "train/grad": 0.07913745870914805, "train/loss": 0.8289636766052246, "eval/hcp-train-subset/loss": 0.8404232734634031, "eval/hcp-val/loss": 0.8366473461351087} +{"epoch": 39, "train/lr": 8.85475290587822e-05, "train/grad": 0.07982666605592213, "train/loss": 0.8270816187381744, "eval/hcp-train-subset/loss": 0.8409985707652184, "eval/hcp-val/loss": 0.8372001551812694} +{"epoch": 40, "train/lr": 8.665494490258622e-05, "train/grad": 0.08206940310197511, "train/loss": 0.8251847616004944, "eval/hcp-train-subset/loss": 0.841510264142867, "eval/hcp-val/loss": 0.8369094094922466} +{"epoch": 41, "train/lr": 8.473594766877838e-05, "train/grad": 0.08180150833223579, "train/loss": 0.824891240568161, "eval/hcp-train-subset/loss": 0.8405684203870835, "eval/hcp-val/loss": 0.8385542871490601} +{"epoch": 42, "train/lr": 8.279263575265999e-05, "train/grad": 0.08351115625299199, "train/loss": 0.8240607167625428, "eval/hcp-train-subset/loss": 0.8403288154832779, "eval/hcp-val/loss": 0.8372004416681105} +{"epoch": 43, "train/lr": 8.082713413727944e-05, "train/grad": 0.08419858947248411, "train/loss": 0.8230657298088073, "eval/hcp-train-subset/loss": 0.840221623259206, "eval/hcp-val/loss": 0.8366030214294311} +{"epoch": 44, "train/lr": 7.884159206979602e-05, "train/grad": 0.08580505676723793, "train/loss": 0.8229929925346374, "eval/hcp-train-subset/loss": 0.8400685450723094, "eval/hcp-val/loss": 0.8363231737767497} +{"epoch": 45, "train/lr": 7.683818071130916e-05, "train/grad": 0.0870618888204251, "train/loss": 0.8214467516422271, "eval/hcp-train-subset/loss": 0.8404907170803316, "eval/hcp-val/loss": 0.8364923894405365} +{"epoch": 46, "train/lr": 7.481909076272522e-05, "train/grad": 0.08647992900333029, "train/loss": 0.8233431646537781, "eval/hcp-train-subset/loss": 0.8385200933102639, "eval/hcp-val/loss": 0.8375018392839739} +{"epoch": 47, "train/lr": 7.278653006925963e-05, "train/grad": 0.08589237972698022, "train/loss": 0.8241998307037354, "eval/hcp-train-subset/loss": 0.8375773054938163, "eval/hcp-val/loss": 0.8352352217320473} +{"epoch": 48, "train/lr": 7.074272120618864e-05, "train/grad": 0.0878607905449715, "train/loss": 0.8216606795597077, "eval/hcp-train-subset/loss": 0.8392121561111943, "eval/hcp-val/loss": 0.8363652527332306} +{"epoch": 49, "train/lr": 6.868989904849677e-05, "train/grad": 0.0876607788682871, "train/loss": 0.8219860344409943, "eval/hcp-train-subset/loss": 0.8393052460685853, "eval/hcp-val/loss": 0.8366140079113745} +{"epoch": 50, "train/lr": 6.6630308327075e-05, "train/grad": 0.09165800824207994, "train/loss": 0.8198702712631225, "eval/hcp-train-subset/loss": 0.8387373820427926, "eval/hcp-val/loss": 0.835751312394296} +{"epoch": 51, "train/lr": 6.456620117413798e-05, "train/grad": 0.09169677045617373, "train/loss": 0.8194582284450531, "eval/hcp-train-subset/loss": 0.8370354540886418, "eval/hcp-val/loss": 0.8348656642821527} +{"epoch": 52, "train/lr": 6.249983466055255e-05, "train/grad": 0.09456454811560186, "train/loss": 0.8200439221191407, "eval/hcp-train-subset/loss": 0.8364260081321963, "eval/hcp-val/loss": 0.8362061400567332} +{"epoch": 53, "train/lr": 6.0433468327763305e-05, "train/grad": 0.09516402097604602, "train/loss": 0.820385323009491, "eval/hcp-train-subset/loss": 0.8361072790238165, "eval/hcp-val/loss": 0.8363673456253544} +{"epoch": 54, "train/lr": 5.83693617170174e-05, "train/grad": 0.09281155846776887, "train/loss": 0.8215635716152191, "eval/hcp-train-subset/loss": 0.835267040998705, "eval/hcp-val/loss": 0.8351321633785002} +{"epoch": 55, "train/lr": 5.6309771898588165e-05, "train/grad": 0.09759635510102299, "train/loss": 0.8199956506729126, "eval/hcp-train-subset/loss": 0.8339868130222443, "eval/hcp-val/loss": 0.8353206399948366} +{"epoch": 56, "train/lr": 5.4256951003704155e-05, "train/grad": 0.09571826031906161, "train/loss": 0.8196602447223663, "eval/hcp-train-subset/loss": 0.835429544410398, "eval/hcp-val/loss": 0.8344326730697386} +{"epoch": 57, "train/lr": 5.221314376187425e-05, "train/grad": 0.09992481742075689, "train/loss": 0.8175271823883057, "eval/hcp-train-subset/loss": 0.8352578503470267, "eval/hcp-val/loss": 0.8347892799685078} +{"epoch": 58, "train/lr": 5.018058504631059e-05, "train/grad": 0.10017026216030198, "train/loss": 0.8187388918876648, "eval/hcp-train-subset/loss": 0.8349023490182815, "eval/hcp-val/loss": 0.8336496708854553} +{"epoch": 59, "train/lr": 4.816149743012713e-05, "train/grad": 0.10105322739979904, "train/loss": 0.8175229668045044, "eval/hcp-train-subset/loss": 0.8342211361854307, "eval/hcp-val/loss": 0.8342525411036706} +{"epoch": 60, "train/lr": 4.615808875598772e-05, "train/grad": 0.1033432631426647, "train/loss": 0.8179095898246765, "eval/hcp-train-subset/loss": 0.8344268548873163, "eval/hcp-val/loss": 0.8346008235408414} +{"epoch": 61, "train/lr": 4.417254972186445e-05, "train/grad": 0.10265305513977928, "train/loss": 0.818266072101593, "eval/hcp-train-subset/loss": 0.833210842263314, "eval/hcp-val/loss": 0.8341638811172978} +{"epoch": 62, "train/lr": 4.220705148553925e-05, "train/grad": 0.10537900413216772, "train/loss": 0.8162737333869934, "eval/hcp-train-subset/loss": 0.8317804346161504, "eval/hcp-val/loss": 0.8332366827995547} +{"epoch": 63, "train/lr": 4.026374329047657e-05, "train/grad": 0.10695245400743808, "train/loss": 0.8170218088722229, "eval/hcp-train-subset/loss": 0.8317832639140468, "eval/hcp-val/loss": 0.833401600199361} +{"epoch": 64, "train/lr": 3.834475011565652e-05, "train/grad": 0.10809327658055953, "train/loss": 0.8169680414199829, "eval/hcp-train-subset/loss": 0.8321883813027413, "eval/hcp-val/loss": 0.8340863220153316} +{"epoch": 65, "train/lr": 3.6452170351940815e-05, "train/grad": 0.10867176050280625, "train/loss": 0.8168584689235687, "eval/hcp-train-subset/loss": 0.832299328619434, "eval/hcp-val/loss": 0.8336228747521678} +{"epoch": 66, "train/lr": 3.458807350751516e-05, "train/grad": 0.1096330421429759, "train/loss": 0.8185550809288025, "eval/hcp-train-subset/loss": 0.8311814348543843, "eval/hcp-val/loss": 0.8331201451440011} +{"epoch": 67, "train/lr": 3.2754497944910164e-05, "train/grad": 0.11258760056602703, "train/loss": 0.8142858922386169, "eval/hcp-train-subset/loss": 0.8315027394602376, "eval/hcp-val/loss": 0.8326457113988938} +{"epoch": 68, "train/lr": 3.0953448652083367e-05, "train/grad": 0.11227808557349395, "train/loss": 0.8160205033302307, "eval/hcp-train-subset/loss": 0.8319668202630935, "eval/hcp-val/loss": 0.832201301090179} +{"epoch": 69, "train/lr": 2.9186895049993948e-05, "train/grad": 0.11679077646733094, "train/loss": 0.8120144665050507, "eval/hcp-train-subset/loss": 0.8316001017247477, "eval/hcp-val/loss": 0.8323074348511235} +{"epoch": 70, "train/lr": 2.7456768839068717e-05, "train/grad": 0.1171515812135483, "train/loss": 0.8138238740062713, "eval/hcp-train-subset/loss": 0.8300691958396665, "eval/hcp-val/loss": 0.8323752783959911} +{"epoch": 71, "train/lr": 2.5764961886919063e-05, "train/grad": 0.11579444991343876, "train/loss": 0.8149957064723968, "eval/hcp-train-subset/loss": 0.8312656254537644, "eval/hcp-val/loss": 0.8321821256991355} +{"epoch": 72, "train/lr": 2.411332415960724e-05, "train/grad": 0.11918857463845563, "train/loss": 0.8142354238796234, "eval/hcp-train-subset/loss": 0.8302408725984635, "eval/hcp-val/loss": 0.8323774270472988} +{"epoch": 73, "train/lr": 2.2503661698739544e-05, "train/grad": 0.11830038511612848, "train/loss": 0.815796880159378, "eval/hcp-train-subset/loss": 0.82809107342074, "eval/hcp-val/loss": 0.8309337737098816} +{"epoch": 74, "train/lr": 2.0937734646583902e-05, "train/grad": 0.11974390781938878, "train/loss": 0.8159463187503815, "eval/hcp-train-subset/loss": 0.8278660899208438, "eval/hcp-val/loss": 0.8321983785398545} +{"epoch": 75, "train/lr": 1.9417255321381202e-05, "train/grad": 0.12277498305029928, "train/loss": 0.8149043825912475, "eval/hcp-train-subset/loss": 0.8260350179287695, "eval/hcp-val/loss": 0.8311477832255825} +{"epoch": 76, "train/lr": 1.7943886344950134e-05, "train/grad": 0.12306335668015599, "train/loss": 0.8146058094596863, "eval/hcp-train-subset/loss": 0.8273872002478568, "eval/hcp-val/loss": 0.8308605445969489} +{"epoch": 77, "train/lr": 1.651923882463461e-05, "train/grad": 0.1270874162945954, "train/loss": 0.8131833356666565, "eval/hcp-train-subset/loss": 0.8257011646224607, "eval/hcp-val/loss": 0.8306482395818157} +{"epoch": 78, "train/lr": 1.5144870591581508e-05, "train/grad": 0.13044425247120223, "train/loss": 0.810251419839859, "eval/hcp-train-subset/loss": 0.824785400782862, "eval/hcp-val/loss": 0.8307501317993287} +{"epoch": 79, "train/lr": 1.3822284497275662e-05, "train/grad": 0.12874253276854175, "train/loss": 0.8138550273895264, "eval/hcp-train-subset/loss": 0.8248286968277346, "eval/hcp-val/loss": 0.8303697022699541} +{"epoch": 80, "train/lr": 1.2552926770192975e-05, "train/grad": 0.13241023960658527, "train/loss": 0.8099106230068207, "eval/hcp-train-subset/loss": 0.8248569840385068, "eval/hcp-val/loss": 0.8302559650713398} +{"epoch": 81, "train/lr": 1.1338185434371453e-05, "train/grad": 0.13035372539605855, "train/loss": 0.8145914227867126, "eval/hcp-train-subset/loss": 0.8241380097404603, "eval/hcp-val/loss": 0.8295710144504425} +{"epoch": 82, "train/lr": 1.0179388791627326e-05, "train/grad": 0.12979528064014664, "train/loss": 0.8148806981086731, "eval/hcp-train-subset/loss": 0.8225722466745684, "eval/hcp-val/loss": 0.8300488898831029} +{"epoch": 83, "train/lr": 9.07780396907607e-06, "train/grad": 0.1345284611997928, "train/loss": 0.8128445739650726, "eval/hcp-train-subset/loss": 0.8230910224299277, "eval/hcp-val/loss": 0.8300405308123557} +{"epoch": 84, "train/lr": 8.034635533547902e-06, "train/grad": 0.13431559012971447, "train/loss": 0.8149870326137543, "eval/hcp-train-subset/loss": 0.8218867846073643, "eval/hcp-val/loss": 0.8292702859447848} +{"epoch": 85, "train/lr": 7.051024174411275e-06, "train/grad": 0.13782812675008854, "train/loss": 0.812082691078186, "eval/hcp-train-subset/loss": 0.8214568822614609, "eval/hcp-val/loss": 0.8297767629546504} +{"epoch": 86, "train/lr": 6.1280454562463606e-06, "train/grad": 0.13969197132828598, "train/loss": 0.811908978176117, "eval/hcp-train-subset/loss": 0.8203396422247733, "eval/hcp-val/loss": 0.8292167071373232} +{"epoch": 87, "train/lr": 5.266708642730326e-06, "train/grad": 0.1407733973146687, "train/loss": 0.814467184305191, "eval/hcp-train-subset/loss": 0.8203872326881655, "eval/hcp-val/loss": 0.8291604124730633} +{"epoch": 88, "train/lr": 4.467955593022733e-06, "train/grad": 0.13892616000904126, "train/loss": 0.8151339881515502, "eval/hcp-train-subset/loss": 0.8194900010862658, "eval/hcp-val/loss": 0.8286967181390331} +{"epoch": 89, "train/lr": 3.732659731856291e-06, "train/grad": 0.1411842387059278, "train/loss": 0.8155731038570404, "eval/hcp-train-subset/loss": 0.8180373464861224, "eval/hcp-val/loss": 0.8294894176144754} +{"epoch": 90, "train/lr": 3.0616250944596583e-06, "train/grad": 0.14483430883137655, "train/loss": 0.812865262670517, "eval/hcp-train-subset/loss": 0.8180384155242674, "eval/hcp-val/loss": 0.8284807474382462} +{"epoch": 91, "train/lr": 2.4555854473568305e-06, "train/grad": 0.1448389720162748, "train/loss": 0.8127812893581391, "eval/hcp-train-subset/loss": 0.8180206023877666, "eval/hcp-val/loss": 0.8280393865800673} +{"epoch": 92, "train/lr": 1.915203486004091e-06, "train/grad": 0.14801302508220898, "train/loss": 0.812814897403717, "eval/hcp-train-subset/loss": 0.8172879545919357, "eval/hcp-val/loss": 0.8286503197685364} +{"epoch": 93, "train/lr": 1.4410701101423926e-06, "train/grad": 0.14722818729089168, "train/loss": 0.8139189223766327, "eval/hcp-train-subset/loss": 0.81677276376755, "eval/hcp-val/loss": 0.8287390720459723} +{"epoch": 94, "train/lr": 1.0337037776570775e-06, "train/grad": 0.14199356140304123, "train/loss": 0.8181023046875, "eval/hcp-train-subset/loss": 0.8169757252739321, "eval/hcp-val/loss": 0.8278290071795064} +{"epoch": 95, "train/lr": 6.935499376518293e-07, "train/grad": 0.15005414385803037, "train/loss": 0.8154234522724152, "eval/hcp-train-subset/loss": 0.8168500796441109, "eval/hcp-val/loss": 0.8279076853106099} +{"epoch": 96, "train/lr": 4.209805433566085e-07, "train/grad": 0.14875421904757255, "train/loss": 0.816857365732193, "eval/hcp-train-subset/loss": 0.8170246664554842, "eval/hcp-val/loss": 0.8276570420111379} +{"epoch": 97, "train/lr": 2.1629364540224422e-07, "train/grad": 0.14690094251572017, "train/loss": 0.8169037616252899, "eval/hcp-train-subset/loss": 0.816599158510085, "eval/hcp-val/loss": 0.8275504660221839} +{"epoch": 98, "train/lr": 7.971306590647406e-08, "train/grad": 0.14571506571312684, "train/loss": 0.8182094388198853, "eval/hcp-train-subset/loss": 0.816299557685852, "eval/hcp-val/loss": 0.8276200928995686} +{"epoch": 99, "train/lr": 1.1388153727718725e-08, "train/grad": 0.1501392203486893, "train/loss": 0.8161201977157593, "eval/hcp-train-subset/loss": 0.8163474221383372, "eval/hcp-val/loss": 0.8275095205153188} diff --git a/input_space_v3/flat_lr1e-3_6/pretrain/log.txt b/input_space_v3/flat_lr1e-3_6/pretrain/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..1d43a27a4e6997709a92a12cb07562efc97e9624 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_6/pretrain/log.txt @@ -0,0 +1,9156 @@ +pretraining fmri mae +start: 2026-04-01 11:59:18 +cwd: /data/connor/fmri-fm +sha: 7f4cedc35609f6857314e0d1ea6657523f17ddeb, status: has uncommitted changes, branch: dev/clane9 +config: +name: input_space_v3/flat_lr1e-3_6/pretrain +notes: input_space ablation v3 flat_lr1e-3_6; use tube masking and on-disk data (input_space=flat + base_lr=1e-3 seed=5406) +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain +input_space: flat +patch_size: 16 +num_frames: 16 +t_patch_size: 4 +mask_ratio: 0.9 +pred_mask_ratio: null +masking: tube +masking_kwargs: {} +mask_patch_size: null +model: mae_vit_base +model_kwargs: + decoding: attn + pos_embed: sep + target_norm: null + pca_norm_nc: 2 + t_pred_stride: 2 + no_decode_pos: true + mask_drop_scale: false + pred_edge_pad: 0 + gauss_sigma: null + class_token: true + reg_tokens: 0 + no_embed_class: true + head_init_scale: 0.0 + decoder_depth: 4 + drop_path_rate: 0.0 +datasets: + hcp-train: + type: wds + url: /data/fmri-datasets/pretrain/hcpya-all.${input_space}.wds/hcpya-all-${input_space}-{00000..01799}.tar + clipping: random + clipping_kwargs: + oversample: 4.0 + shuffle: true + buffer_size: 2000 + samples_per_epoch: 200000 + hcp-train-subset: + type: arrow + root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/validation + split_range: + - 0 + - 2000 + shuffle: false + hcp-val: + type: arrow + root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/test + split_range: + - 0 + - 2000 + shuffle: false +train_dataset: hcp-train +eval_datasets: +- hcp-train-subset +- hcp-val +val_dataset: null +clip_vmax: 3.0 +normalize: frame +tr_scale: null +crop_scale: null +crop_aspect: null +gray_jitter: null +num_workers: 16 +epochs: 100 +batch_size: 32 +accum_iter: 1 +base_lr: 0.001 +min_lr: 0.0 +warmup_epochs: 5 +weight_decay: 0.05 +betas: +- 0.9 +- 0.95 +clip_grad: 1.0 +amp: true +amp_dtype: float16 +ckpt: null +resume: true +auto_resume: true +start_epoch: 0 +max_checkpoints: 0 +checkpoint_period: null +plot_period: 5 +device: cuda +presend_cuda: false +seed: 5406 +debug: false +wandb: true +wandb_entity: null +wandb_project: fMRI-foundation-model +rank: 0 +world_size: 1 +gpu: 0 +distributed: true +dist_backend: nccl +in_chans: 1 +img_size: +- 224 +- 560 + +train transform: +Compose( + ToTensor() + TemporalCenterCrop(num_frames=16) + Normalize(mode='frame') + Clip(vmax=3.0) + FlatUnmask((224, 560)) +) +val transform: +Compose( + ToTensor() + TemporalCenterCrop(num_frames=16) + Normalize(mode='frame') + Clip(vmax=3.0) + FlatUnmask((224, 560)) +) +mask generator: +TubeMasking( + mask_ratio=0.9 + (patchify): Patchify2D((224, 560), (16, 16), in_chans=1) +) +loading dataset: hcp-train + +type: wds +url: /data/fmri-datasets/pretrain/hcpya-all.${input_space}.wds/hcpya-all-${input_space}-{00000..01799}.tar +clipping: random +clipping_kwargs: + oversample: 4.0 +shuffle: true +buffer_size: 2000 +samples_per_epoch: 200000 + +loading dataset: hcp-train-subset + +type: arrow +root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/validation +split_range: +- 0 +- 2000 +shuffle: false + +split indices: [899, 472, 767, 116, 1265, 1852, 300, 1335, 361, 1560] +loading dataset: hcp-val + +type: arrow +root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/test +split_range: +- 0 +- 2000 +shuffle: false + +split indices: [1075, 1189, 738, 1350, 965, 1964, 1367, 1183, 1619, 1407] +model: +MaskedAutoencoderViT( + decoding=attn, t_pred_stride=2, pred_edge_pad=0, no_decode_pos=True + (encoder): MaskedEncoder( + class_token=True, reg_tokens=0, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) + (pred_patchify): StridedPatchify3D((16, 224, 560), (2, 16, 16), in_chans=1, t_stride=2) + (decoder): MaskedDecoder( + cross_decode=False, class_token=True, no_embed_class=True + (pos_embed): SeparablePosEmbed(512, (4, 14, 35)) + (proj): Linear(in_features=768, out_features=512, bias=True) + (blocks): ModuleList( + (0-3): 4 x Block( + (norm1): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=16 + (q): Linear(in_features=512, out_features=512, bias=True) + (k): Linear(in_features=512, out_features=512, bias=True) + (v): Linear(in_features=512, out_features=512, bias=True) + (proj): Linear(in_features=512, out_features=512, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=512, out_features=2048, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=2048, out_features=512, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (head): Linear(in_features=512, out_features=512, bias=True) + ) +) +num params: 99.7M +total batch size: 32 = 32 bs per gpu x 1 accum x 1 gpus +lr: 1.25e-04 = 1.00e-03 x 32 / 256 +full schedule: epochs = 100 (steps = 625000) +warmup: epochs = 5 (steps = 31250) +start training for 100 epochs +Train: [0] [ 0/6250] eta: 20:17:07 lr: 0.000000 grad: 0.0215 (0.0215) loss: 0.9985 (0.9985) time: 11.6844 data: 10.1553 max mem: 8589 +Train: [0] [ 100/6250] eta: 0:33:40 lr: 0.000000 grad: 0.0140 (0.0161) loss: 0.9962 (0.9960) time: 0.2384 data: 0.1538 max mem: 9394 +Train: [0] [ 200/6250] eta: 0:27:22 lr: 0.000001 grad: 0.0127 (0.0148) loss: 0.9960 (0.9959) time: 0.2280 data: 0.1328 max mem: 9394 +Train: [0] [ 300/6250] eta: 0:25:15 lr: 0.000001 grad: 0.0126 (0.0142) loss: 0.9961 (0.9959) time: 0.1733 data: 0.0719 max mem: 9394 +Train: [0] [ 400/6250] eta: 0:25:23 lr: 0.000002 grad: 0.0122 (0.0138) loss: 0.9955 (0.9958) time: 0.4018 data: 0.3064 max mem: 9394 +Train: [0] [ 500/6250] eta: 0:25:03 lr: 0.000002 grad: 0.0127 (0.0136) loss: 0.9955 (0.9958) time: 0.1213 data: 0.0005 max mem: 9394 +Train: [0] [ 600/6250] eta: 0:24:24 lr: 0.000002 grad: 0.0127 (0.0135) loss: 0.9958 (0.9958) time: 0.2341 data: 0.1188 max mem: 9394 +Train: [0] [ 700/6250] eta: 0:23:47 lr: 0.000003 grad: 0.0130 (0.0134) loss: 0.9959 (0.9958) time: 0.3934 data: 0.2987 max mem: 9394 +Train: [0] [ 800/6250] eta: 0:23:22 lr: 0.000003 grad: 0.0130 (0.0133) loss: 0.9959 (0.9958) time: 0.2290 data: 0.1403 max mem: 9394 +Train: [0] [ 900/6250] eta: 0:22:24 lr: 0.000004 grad: 0.0132 (0.0133) loss: 0.9960 (0.9958) time: 0.2137 data: 0.1110 max mem: 9394 +Train: [0] [1000/6250] eta: 0:21:26 lr: 0.000004 grad: 0.0132 (0.0133) loss: 0.9956 (0.9958) time: 0.1412 data: 0.0416 max mem: 9394 +Train: [0] [1100/6250] eta: 0:20:40 lr: 0.000004 grad: 0.0146 (0.0135) loss: 0.9961 (0.9958) time: 0.1693 data: 0.0571 max mem: 9394 +Train: [0] [1200/6250] eta: 0:20:02 lr: 0.000005 grad: 0.0192 (0.0139) loss: 0.9957 (0.9958) time: 0.1591 data: 0.0424 max mem: 9394 +Train: [0] [1300/6250] eta: 0:19:17 lr: 0.000005 grad: 0.0187 (0.0142) loss: 0.9959 (0.9958) time: 0.1910 data: 0.1036 max mem: 9394 +Train: [0] [1400/6250] eta: 0:18:44 lr: 0.000006 grad: 0.0262 (0.0148) loss: 0.9956 (0.9958) time: 0.3191 data: 0.2279 max mem: 9394 +Train: [0] [1500/6250] eta: 0:17:56 lr: 0.000006 grad: 0.0251 (0.0156) loss: 0.9958 (0.9958) time: 0.1278 data: 0.0400 max mem: 9394 +Train: [0] [1600/6250] eta: 0:17:28 lr: 0.000006 grad: 0.0214 (0.0164) loss: 0.9955 (0.9958) time: 0.2779 data: 0.1832 max mem: 9394 +Train: [0] [1700/6250] eta: 0:16:57 lr: 0.000007 grad: 0.0319 (0.0175) loss: 0.9946 (0.9957) time: 0.1991 data: 0.0669 max mem: 9394 +Train: [0] [1800/6250] eta: 0:16:31 lr: 0.000007 grad: 0.0400 (0.0189) loss: 0.9949 (0.9957) time: 0.1291 data: 0.0337 max mem: 9394 +Train: [0] [1900/6250] eta: 0:16:02 lr: 0.000008 grad: 0.0583 (0.0204) loss: 0.9946 (0.9956) time: 0.2346 data: 0.1392 max mem: 9394 +Train: [0] [2000/6250] eta: 0:15:32 lr: 0.000008 grad: 0.0402 (0.0213) loss: 0.9949 (0.9956) time: 0.1705 data: 0.0901 max mem: 9394 +Train: [0] [2100/6250] eta: 0:15:04 lr: 0.000008 grad: 0.0345 (0.0224) loss: 0.9949 (0.9956) time: 0.2121 data: 0.1308 max mem: 9394 +Train: [0] [2200/6250] eta: 0:14:37 lr: 0.000009 grad: 0.0476 (0.0234) loss: 0.9947 (0.9955) time: 0.1345 data: 0.0150 max mem: 9394 +Train: [0] [2300/6250] eta: 0:14:13 lr: 0.000009 grad: 0.0436 (0.0246) loss: 0.9941 (0.9955) time: 0.1677 data: 0.0821 max mem: 9394 +Train: [0] [2400/6250] eta: 0:13:50 lr: 0.000010 grad: 0.0537 (0.0258) loss: 0.9933 (0.9954) time: 0.0992 data: 0.0003 max mem: 9394 +Train: [0] [2500/6250] eta: 0:13:26 lr: 0.000010 grad: 0.0567 (0.0269) loss: 0.9939 (0.9954) time: 0.1730 data: 0.0717 max mem: 9394 +Train: [0] [2600/6250] eta: 0:13:03 lr: 0.000010 grad: 0.0540 (0.0279) loss: 0.9934 (0.9953) time: 0.3022 data: 0.2077 max mem: 9394 +Train: [0] [2700/6250] eta: 0:12:35 lr: 0.000011 grad: 0.0461 (0.0288) loss: 0.9942 (0.9953) time: 0.1986 data: 0.1073 max mem: 9394 +Train: [0] [2800/6250] eta: 0:12:11 lr: 0.000011 grad: 0.0496 (0.0297) loss: 0.9947 (0.9953) time: 0.1736 data: 0.0842 max mem: 9394 +Train: [0] [2900/6250] eta: 0:11:48 lr: 0.000012 grad: 0.0477 (0.0303) loss: 0.9941 (0.9952) time: 0.2161 data: 0.1299 max mem: 9394 +Train: [0] [3000/6250] eta: 0:11:24 lr: 0.000012 grad: 0.0460 (0.0311) loss: 0.9943 (0.9952) time: 0.2305 data: 0.1493 max mem: 9394 +Train: [0] [3100/6250] eta: 0:11:01 lr: 0.000012 grad: 0.0568 (0.0321) loss: 0.9940 (0.9951) time: 0.1701 data: 0.0854 max mem: 9394 +Train: [0] [3200/6250] eta: 0:10:40 lr: 0.000013 grad: 0.0739 (0.0331) loss: 0.9924 (0.9951) time: 0.2506 data: 0.1530 max mem: 9394 +Train: [0] [3300/6250] eta: 0:10:15 lr: 0.000013 grad: 0.0656 (0.0340) loss: 0.9927 (0.9950) time: 0.1857 data: 0.1039 max mem: 9394 +Train: [0] [3400/6250] eta: 0:09:53 lr: 0.000014 grad: 0.0679 (0.0349) loss: 0.9918 (0.9949) time: 0.1316 data: 0.0376 max mem: 9394 +Train: [0] [3500/6250] eta: 0:09:31 lr: 0.000014 grad: 0.0590 (0.0359) loss: 0.9924 (0.9949) time: 0.1993 data: 0.1221 max mem: 9394 +Train: [0] [3600/6250] eta: 0:09:08 lr: 0.000014 grad: 0.0694 (0.0369) loss: 0.9921 (0.9948) time: 0.1712 data: 0.0877 max mem: 9394 +Train: [0] [3700/6250] eta: 0:08:45 lr: 0.000015 grad: 0.0724 (0.0379) loss: 0.9922 (0.9947) time: 0.1602 data: 0.0770 max mem: 9394 +Train: [0] [3800/6250] eta: 0:08:22 lr: 0.000015 grad: 0.0649 (0.0387) loss: 0.9918 (0.9947) time: 0.1872 data: 0.0972 max mem: 9394 +Train: [0] [3900/6250] eta: 0:08:00 lr: 0.000016 grad: 0.0632 (0.0396) loss: 0.9916 (0.9946) time: 0.1719 data: 0.0926 max mem: 9394 +Train: [0] [4000/6250] eta: 0:07:38 lr: 0.000016 grad: 0.0668 (0.0404) loss: 0.9921 (0.9945) time: 0.2088 data: 0.1206 max mem: 9394 +Train: [0] [4100/6250] eta: 0:07:16 lr: 0.000016 grad: 0.0642 (0.0411) loss: 0.9925 (0.9945) time: 0.1680 data: 0.0775 max mem: 9394 +Train: [0] [4200/6250] eta: 0:06:54 lr: 0.000017 grad: 0.0718 (0.0419) loss: 0.9916 (0.9944) time: 0.1616 data: 0.0749 max mem: 9394 +Train: [0] [4300/6250] eta: 0:06:32 lr: 0.000017 grad: 0.0628 (0.0426) loss: 0.9916 (0.9944) time: 0.1875 data: 0.0958 max mem: 9394 +Train: [0] [4400/6250] eta: 0:06:11 lr: 0.000018 grad: 0.0577 (0.0432) loss: 0.9921 (0.9943) time: 0.1273 data: 0.0396 max mem: 9394 +Train: [0] [4500/6250] eta: 0:05:50 lr: 0.000018 grad: 0.0739 (0.0439) loss: 0.9912 (0.9942) time: 0.1239 data: 0.0353 max mem: 9394 +Train: [0] [4600/6250] eta: 0:05:29 lr: 0.000018 grad: 0.0592 (0.0444) loss: 0.9913 (0.9942) time: 0.1483 data: 0.0552 max mem: 9394 +Train: [0] [4700/6250] eta: 0:05:08 lr: 0.000019 grad: 0.0625 (0.0449) loss: 0.9930 (0.9941) time: 0.1783 data: 0.0879 max mem: 9394 +Train: [0] [4800/6250] eta: 0:04:47 lr: 0.000019 grad: 0.0753 (0.0455) loss: 0.9914 (0.9941) time: 0.1592 data: 0.0722 max mem: 9394 +Train: [0] [4900/6250] eta: 0:04:27 lr: 0.000020 grad: 0.0658 (0.0461) loss: 0.9916 (0.9940) time: 0.1255 data: 0.0255 max mem: 9394 +Train: [0] [5000/6250] eta: 0:04:06 lr: 0.000020 grad: 0.0754 (0.0466) loss: 0.9911 (0.9940) time: 0.1708 data: 0.0829 max mem: 9394 +Train: [0] [5100/6250] eta: 0:03:46 lr: 0.000020 grad: 0.0697 (0.0472) loss: 0.9912 (0.9939) time: 0.2111 data: 0.1264 max mem: 9394 +Train: [0] [5200/6250] eta: 0:03:27 lr: 0.000021 grad: 0.0724 (0.0478) loss: 0.9915 (0.9938) time: 0.2578 data: 0.1667 max mem: 9394 +Train: [0] [5300/6250] eta: 0:03:07 lr: 0.000021 grad: 0.0717 (0.0484) loss: 0.9896 (0.9938) time: 0.2444 data: 0.1441 max mem: 9394 +Train: [0] [5400/6250] eta: 0:02:48 lr: 0.000022 grad: 0.0761 (0.0490) loss: 0.9897 (0.9937) time: 0.2045 data: 0.1144 max mem: 9394 +Train: [0] [5500/6250] eta: 0:02:28 lr: 0.000022 grad: 0.0768 (0.0495) loss: 0.9899 (0.9936) time: 0.1846 data: 0.0987 max mem: 9394 +Train: [0] [5600/6250] eta: 0:02:08 lr: 0.000022 grad: 0.0741 (0.0500) loss: 0.9906 (0.9936) time: 0.1968 data: 0.1051 max mem: 9394 +Train: [0] [5700/6250] eta: 0:01:48 lr: 0.000023 grad: 0.0803 (0.0506) loss: 0.9909 (0.9935) time: 0.2112 data: 0.1340 max mem: 9394 +Train: [0] [5800/6250] eta: 0:01:28 lr: 0.000023 grad: 0.0731 (0.0511) loss: 0.9897 (0.9935) time: 0.1901 data: 0.1030 max mem: 9394 +Train: [0] [5900/6250] eta: 0:01:08 lr: 0.000024 grad: 0.0767 (0.0516) loss: 0.9880 (0.9934) time: 0.1934 data: 0.1071 max mem: 9394 +Train: [0] [6000/6250] eta: 0:00:49 lr: 0.000024 grad: 0.0713 (0.0521) loss: 0.9898 (0.9933) time: 0.1994 data: 0.1131 max mem: 9394 +Train: [0] [6100/6250] eta: 0:00:29 lr: 0.000024 grad: 0.0694 (0.0525) loss: 0.9892 (0.9933) time: 0.1456 data: 0.0627 max mem: 9394 +Train: [0] [6200/6250] eta: 0:00:09 lr: 0.000025 grad: 0.0742 (0.0528) loss: 0.9911 (0.9932) time: 0.1260 data: 0.0379 max mem: 9394 +Train: [0] [6249/6250] eta: 0:00:00 lr: 0.000025 grad: 0.0669 (0.0530) loss: 0.9901 (0.9932) time: 0.1977 data: 0.1034 max mem: 9394 +Train: [0] Total time: 0:20:33 (0.1974 s / it) +Averaged stats: lr: 0.000025 grad: 0.0669 (0.0530) loss: 0.9901 (0.9932) +Eval (hcp-train-subset): [0] [ 0/62] eta: 0:03:27 loss: 0.9912 (0.9912) time: 3.3504 data: 3.2542 max mem: 9394 +Eval (hcp-train-subset): [0] [61/62] eta: 0:00:00 loss: 0.9907 (0.9911) time: 0.1294 data: 0.1043 max mem: 9394 +Eval (hcp-train-subset): [0] Total time: 0:00:14 (0.2398 s / it) +Averaged stats (hcp-train-subset): loss: 0.9907 (0.9911) +Eval (hcp-val): [0] [ 0/62] eta: 0:05:49 loss: 0.9829 (0.9829) time: 5.6361 data: 5.6049 max mem: 9394 +Eval (hcp-val): [0] [61/62] eta: 0:00:00 loss: 0.9887 (0.9891) time: 0.1429 data: 0.1154 max mem: 9394 +Eval (hcp-val): [0] Total time: 0:00:14 (0.2338 s / it) +Averaged stats (hcp-val): loss: 0.9887 (0.9891) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +Train: [1] [ 0/6250] eta: 9:25:02 lr: 0.000025 grad: 0.1177 (0.1177) loss: 0.9925 (0.9925) time: 5.4244 data: 5.2241 max mem: 9394 +Train: [1] [ 100/6250] eta: 0:23:28 lr: 0.000025 grad: 0.0688 (0.0819) loss: 0.9911 (0.9909) time: 0.2048 data: 0.1082 max mem: 9394 +Train: [1] [ 200/6250] eta: 0:19:46 lr: 0.000026 grad: 0.0658 (0.0802) loss: 0.9895 (0.9906) time: 0.1625 data: 0.0732 max mem: 9394 +Train: [1] [ 300/6250] eta: 0:18:46 lr: 0.000026 grad: 0.0835 (0.0815) loss: 0.9891 (0.9903) time: 0.1640 data: 0.0650 max mem: 9394 +Train: [1] [ 400/6250] eta: 0:18:08 lr: 0.000027 grad: 0.0753 (0.0813) loss: 0.9924 (0.9902) time: 0.1688 data: 0.0740 max mem: 9394 +Train: [1] [ 500/6250] eta: 0:18:20 lr: 0.000027 grad: 0.0776 (0.0810) loss: 0.9891 (0.9902) time: 0.2951 data: 0.2090 max mem: 9394 +Train: [1] [ 600/6250] eta: 0:18:46 lr: 0.000027 grad: 0.0658 (0.0798) loss: 0.9900 (0.9902) time: 0.3886 data: 0.2849 max mem: 9394 +Train: [1] [ 700/6250] eta: 0:18:51 lr: 0.000028 grad: 0.0717 (0.0793) loss: 0.9907 (0.9903) time: 0.2793 data: 0.1487 max mem: 9394 +Train: [1] [ 800/6250] eta: 0:19:11 lr: 0.000028 grad: 0.0843 (0.0805) loss: 0.9905 (0.9901) time: 0.2558 data: 0.1399 max mem: 9394 +Train: [1] [ 900/6250] eta: 0:19:01 lr: 0.000029 grad: 0.0735 (0.0812) loss: 0.9889 (0.9901) time: 0.2938 data: 0.1959 max mem: 9394 +Train: [1] [1000/6250] eta: 0:18:26 lr: 0.000029 grad: 0.0783 (0.0814) loss: 0.9898 (0.9900) time: 0.0922 data: 0.0002 max mem: 9394 +Train: [1] [1100/6250] eta: 0:17:59 lr: 0.000029 grad: 0.0818 (0.0815) loss: 0.9892 (0.9899) time: 0.2257 data: 0.1335 max mem: 9394 +Train: [1] [1200/6250] eta: 0:18:01 lr: 0.000030 grad: 0.0890 (0.0818) loss: 0.9872 (0.9898) time: 0.1630 data: 0.0350 max mem: 9394 +Train: [1] [1300/6250] eta: 0:17:25 lr: 0.000030 grad: 0.0856 (0.0824) loss: 0.9893 (0.9898) time: 0.1893 data: 0.0972 max mem: 9394 +Train: [1] [1400/6250] eta: 0:16:56 lr: 0.000031 grad: 0.0778 (0.0825) loss: 0.9895 (0.9897) time: 0.1879 data: 0.0958 max mem: 9394 +Train: [1] [1500/6250] eta: 0:16:28 lr: 0.000031 grad: 0.0813 (0.0824) loss: 0.9889 (0.9896) time: 0.1163 data: 0.0005 max mem: 9394 +Train: [1] [1600/6250] eta: 0:15:59 lr: 0.000031 grad: 0.0810 (0.0826) loss: 0.9879 (0.9896) time: 0.1843 data: 0.1049 max mem: 9394 +Train: [1] [1700/6250] eta: 0:15:44 lr: 0.000032 grad: 0.0813 (0.0829) loss: 0.9875 (0.9895) time: 0.1748 data: 0.0784 max mem: 9394 +Train: [1] [1800/6250] eta: 0:15:20 lr: 0.000032 grad: 0.0794 (0.0833) loss: 0.9899 (0.9894) time: 0.3036 data: 0.2156 max mem: 9394 +Train: [1] [1900/6250] eta: 0:14:51 lr: 0.000033 grad: 0.0785 (0.0834) loss: 0.9900 (0.9894) time: 0.2078 data: 0.1331 max mem: 9394 +Train: [1] [2000/6250] eta: 0:14:28 lr: 0.000033 grad: 0.0779 (0.0833) loss: 0.9891 (0.9893) time: 0.2179 data: 0.1255 max mem: 9394 +Train: [1] [2100/6250] eta: 0:14:19 lr: 0.000033 grad: 0.0768 (0.0833) loss: 0.9883 (0.9893) time: 0.1897 data: 0.0839 max mem: 9394 +Train: [1] [2200/6250] eta: 0:13:51 lr: 0.000034 grad: 0.0901 (0.0834) loss: 0.9879 (0.9892) time: 0.1699 data: 0.0785 max mem: 9394 +Train: [1] [2300/6250] eta: 0:13:32 lr: 0.000034 grad: 0.0862 (0.0835) loss: 0.9883 (0.9892) time: 0.3627 data: 0.2723 max mem: 9394 +Train: [1] [2400/6250] eta: 0:13:06 lr: 0.000035 grad: 0.0661 (0.0833) loss: 0.9893 (0.9892) time: 0.1791 data: 0.0778 max mem: 9394 +Train: [1] [2500/6250] eta: 0:12:43 lr: 0.000035 grad: 0.0706 (0.0831) loss: 0.9896 (0.9891) time: 0.1031 data: 0.0043 max mem: 9394 +Train: [1] [2600/6250] eta: 0:12:21 lr: 0.000035 grad: 0.0774 (0.0829) loss: 0.9891 (0.9891) time: 0.2162 data: 0.1184 max mem: 9394 +Train: [1] [2700/6250] eta: 0:11:59 lr: 0.000036 grad: 0.0718 (0.0827) loss: 0.9892 (0.9891) time: 0.1533 data: 0.0698 max mem: 9394 +Train: [1] [2800/6250] eta: 0:11:38 lr: 0.000036 grad: 0.0614 (0.0823) loss: 0.9897 (0.9891) time: 0.2544 data: 0.1662 max mem: 9394 +Train: [1] [2900/6250] eta: 0:11:14 lr: 0.000037 grad: 0.0625 (0.0821) loss: 0.9900 (0.9891) time: 0.1480 data: 0.0602 max mem: 9394 +Train: [1] [3000/6250] eta: 0:10:53 lr: 0.000037 grad: 0.0687 (0.0818) loss: 0.9902 (0.9891) time: 0.2001 data: 0.1218 max mem: 9394 +Train: [1] [3100/6250] eta: 0:10:31 lr: 0.000037 grad: 0.0746 (0.0816) loss: 0.9885 (0.9891) time: 0.1569 data: 0.0602 max mem: 9394 +Train: [1] [3200/6250] eta: 0:10:13 lr: 0.000038 grad: 0.0643 (0.0815) loss: 0.9899 (0.9891) time: 0.1246 data: 0.0153 max mem: 9394 +Train: [1] [3300/6250] eta: 0:09:50 lr: 0.000038 grad: 0.0752 (0.0816) loss: 0.9879 (0.9890) time: 0.1639 data: 0.0783 max mem: 9394 +Train: [1] [3400/6250] eta: 0:09:28 lr: 0.000039 grad: 0.0781 (0.0816) loss: 0.9865 (0.9890) time: 0.1583 data: 0.0636 max mem: 9394 +Train: [1] [3500/6250] eta: 0:09:08 lr: 0.000039 grad: 0.0739 (0.0816) loss: 0.9880 (0.9890) time: 0.1679 data: 0.0540 max mem: 9394 +Train: [1] [3600/6250] eta: 0:08:49 lr: 0.000039 grad: 0.0874 (0.0817) loss: 0.9873 (0.9889) time: 0.1798 data: 0.0939 max mem: 9394 +Train: [1] [3700/6250] eta: 0:08:29 lr: 0.000040 grad: 0.0761 (0.0818) loss: 0.9876 (0.9889) time: 0.1582 data: 0.0729 max mem: 9394 +Train: [1] [3800/6250] eta: 0:08:08 lr: 0.000040 grad: 0.0729 (0.0817) loss: 0.9893 (0.9889) time: 0.2171 data: 0.1351 max mem: 9394 +Train: [1] [3900/6250] eta: 0:07:50 lr: 0.000041 grad: 0.0839 (0.0817) loss: 0.9868 (0.9888) time: 0.3136 data: 0.2167 max mem: 9394 +Train: [1] [4000/6250] eta: 0:07:28 lr: 0.000041 grad: 0.0823 (0.0816) loss: 0.9876 (0.9888) time: 0.1992 data: 0.1081 max mem: 9394 +Train: [1] [4100/6250] eta: 0:07:08 lr: 0.000041 grad: 0.0796 (0.0817) loss: 0.9863 (0.9888) time: 0.1647 data: 0.0735 max mem: 9394 +Train: [1] [4200/6250] eta: 0:06:47 lr: 0.000042 grad: 0.0808 (0.0818) loss: 0.9865 (0.9887) time: 0.1643 data: 0.0725 max mem: 9394 +Train: [1] [4300/6250] eta: 0:06:25 lr: 0.000042 grad: 0.0812 (0.0817) loss: 0.9865 (0.9887) time: 0.1517 data: 0.0618 max mem: 9394 +Train: [1] [4400/6250] eta: 0:06:05 lr: 0.000043 grad: 0.0728 (0.0818) loss: 0.9878 (0.9887) time: 0.2712 data: 0.1849 max mem: 9394 +Train: [1] [4500/6250] eta: 0:05:46 lr: 0.000043 grad: 0.0783 (0.0818) loss: 0.9874 (0.9886) time: 0.2579 data: 0.1832 max mem: 9394 +Train: [1] [4600/6250] eta: 0:05:26 lr: 0.000043 grad: 0.0840 (0.0818) loss: 0.9864 (0.9886) time: 0.2178 data: 0.1346 max mem: 9394 +Train: [1] [4700/6250] eta: 0:05:07 lr: 0.000044 grad: 0.0909 (0.0817) loss: 0.9865 (0.9886) time: 0.3000 data: 0.2044 max mem: 9394 +Train: [1] [4800/6250] eta: 0:04:47 lr: 0.000044 grad: 0.0741 (0.0817) loss: 0.9885 (0.9886) time: 0.1794 data: 0.0969 max mem: 9394 +Train: [1] [4900/6250] eta: 0:04:27 lr: 0.000045 grad: 0.0791 (0.0817) loss: 0.9863 (0.9885) time: 0.1946 data: 0.1060 max mem: 9394 +Train: [1] [5000/6250] eta: 0:04:08 lr: 0.000045 grad: 0.0858 (0.0817) loss: 0.9850 (0.9885) time: 0.2128 data: 0.1297 max mem: 9394 +Train: [1] [5100/6250] eta: 0:03:48 lr: 0.000045 grad: 0.0806 (0.0817) loss: 0.9885 (0.9885) time: 0.2310 data: 0.1462 max mem: 9394 +Train: [1] [5200/6250] eta: 0:03:29 lr: 0.000046 grad: 0.0722 (0.0816) loss: 0.9879 (0.9884) time: 0.1916 data: 0.1059 max mem: 9394 +Train: [1] [5300/6250] eta: 0:03:10 lr: 0.000046 grad: 0.0694 (0.0816) loss: 0.9886 (0.9884) time: 0.5447 data: 0.4635 max mem: 9394 +Train: [1] [5400/6250] eta: 0:02:50 lr: 0.000047 grad: 0.0734 (0.0815) loss: 0.9875 (0.9884) time: 0.1226 data: 0.0002 max mem: 9394 +Train: [1] [5500/6250] eta: 0:02:30 lr: 0.000047 grad: 0.0706 (0.0815) loss: 0.9876 (0.9884) time: 0.1856 data: 0.0857 max mem: 9394 +Train: [1] [5600/6250] eta: 0:02:10 lr: 0.000047 grad: 0.0662 (0.0814) loss: 0.9884 (0.9884) time: 0.1725 data: 0.0862 max mem: 9394 +Train: [1] [5700/6250] eta: 0:01:49 lr: 0.000048 grad: 0.0763 (0.0814) loss: 0.9872 (0.9883) time: 0.1606 data: 0.0662 max mem: 9394 +Train: [1] [5800/6250] eta: 0:01:29 lr: 0.000048 grad: 0.0767 (0.0814) loss: 0.9863 (0.9883) time: 0.1722 data: 0.0943 max mem: 9394 +Train: [1] [5900/6250] eta: 0:01:09 lr: 0.000049 grad: 0.0744 (0.0814) loss: 0.9858 (0.9883) time: 0.1979 data: 0.1165 max mem: 9394 +Train: [1] [6000/6250] eta: 0:00:49 lr: 0.000049 grad: 0.0762 (0.0814) loss: 0.9879 (0.9883) time: 0.1894 data: 0.1034 max mem: 9394 +Train: [1] [6100/6250] eta: 0:00:29 lr: 0.000049 grad: 0.0765 (0.0814) loss: 0.9883 (0.9883) time: 0.1733 data: 0.0756 max mem: 9394 +Train: [1] [6200/6250] eta: 0:00:09 lr: 0.000050 grad: 0.0761 (0.0814) loss: 0.9887 (0.9882) time: 0.1415 data: 0.0529 max mem: 9394 +Train: [1] [6249/6250] eta: 0:00:00 lr: 0.000050 grad: 0.0724 (0.0814) loss: 0.9869 (0.9882) time: 0.1783 data: 0.0961 max mem: 9394 +Train: [1] Total time: 0:20:48 (0.1997 s / it) +Averaged stats: lr: 0.000050 grad: 0.0724 (0.0814) loss: 0.9869 (0.9882) +Eval (hcp-train-subset): [1] [ 0/62] eta: 0:04:14 loss: 0.9905 (0.9905) time: 4.1124 data: 4.0458 max mem: 9394 +Eval (hcp-train-subset): [1] [61/62] eta: 0:00:00 loss: 0.9891 (0.9890) time: 0.1498 data: 0.1240 max mem: 9394 +Eval (hcp-train-subset): [1] Total time: 0:00:14 (0.2398 s / it) +Averaged stats (hcp-train-subset): loss: 0.9891 (0.9890) +Eval (hcp-val): [1] [ 0/62] eta: 0:03:51 loss: 0.9832 (0.9832) time: 3.7377 data: 3.6685 max mem: 9394 +Eval (hcp-val): [1] [61/62] eta: 0:00:00 loss: 0.9871 (0.9867) time: 0.1451 data: 0.1197 max mem: 9394 +Eval (hcp-val): [1] Total time: 0:00:14 (0.2333 s / it) +Averaged stats (hcp-val): loss: 0.9871 (0.9867) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +Train: [2] [ 0/6250] eta: 8:20:46 lr: 0.000050 grad: 0.1810 (0.1810) loss: 0.9772 (0.9772) time: 4.8075 data: 4.5015 max mem: 9394 +Train: [2] [ 100/6250] eta: 0:23:26 lr: 0.000050 grad: 0.0873 (0.0868) loss: 0.9857 (0.9874) time: 0.1773 data: 0.0877 max mem: 9394 +Train: [2] [ 200/6250] eta: 0:20:14 lr: 0.000051 grad: 0.0788 (0.0872) loss: 0.9857 (0.9865) time: 0.1710 data: 0.0715 max mem: 9394 +Train: [2] [ 300/6250] eta: 0:19:38 lr: 0.000051 grad: 0.0771 (0.0865) loss: 0.9857 (0.9863) time: 0.1936 data: 0.1031 max mem: 9394 +Train: [2] [ 400/6250] eta: 0:19:14 lr: 0.000052 grad: 0.0938 (0.0872) loss: 0.9857 (0.9861) time: 0.2045 data: 0.1096 max mem: 9394 +Train: [2] [ 500/6250] eta: 0:19:04 lr: 0.000052 grad: 0.0839 (0.0870) loss: 0.9872 (0.9862) time: 0.1489 data: 0.0401 max mem: 9394 +Train: [2] [ 600/6250] eta: 0:19:10 lr: 0.000052 grad: 0.0823 (0.0873) loss: 0.9856 (0.9861) time: 0.1982 data: 0.0970 max mem: 9394 +Train: [2] [ 700/6250] eta: 0:19:21 lr: 0.000053 grad: 0.0804 (0.0865) loss: 0.9863 (0.9861) time: 0.3326 data: 0.2417 max mem: 9394 +Train: [2] [ 800/6250] eta: 0:19:04 lr: 0.000053 grad: 0.0769 (0.0864) loss: 0.9868 (0.9862) time: 0.0859 data: 0.0002 max mem: 9394 +Train: [2] [ 900/6250] eta: 0:18:56 lr: 0.000054 grad: 0.0683 (0.0864) loss: 0.9884 (0.9862) time: 0.2665 data: 0.1498 max mem: 9394 +Train: [2] [1000/6250] eta: 0:18:26 lr: 0.000054 grad: 0.0732 (0.0861) loss: 0.9865 (0.9863) time: 0.0949 data: 0.0002 max mem: 9394 +Train: [2] [1100/6250] eta: 0:17:48 lr: 0.000054 grad: 0.0793 (0.0860) loss: 0.9846 (0.9862) time: 0.1162 data: 0.0303 max mem: 9394 +Train: [2] [1200/6250] eta: 0:17:21 lr: 0.000055 grad: 0.0792 (0.0860) loss: 0.9864 (0.9862) time: 0.1132 data: 0.0002 max mem: 9394 +Train: [2] [1300/6250] eta: 0:17:08 lr: 0.000055 grad: 0.0821 (0.0857) loss: 0.9856 (0.9862) time: 0.4065 data: 0.2988 max mem: 9394 +Train: [2] [1400/6250] eta: 0:16:38 lr: 0.000056 grad: 0.0631 (0.0854) loss: 0.9871 (0.9863) time: 0.2593 data: 0.1614 max mem: 9394 +Train: [2] [1500/6250] eta: 0:16:15 lr: 0.000056 grad: 0.0779 (0.0851) loss: 0.9868 (0.9863) time: 0.1020 data: 0.0003 max mem: 9394 +Train: [2] [1600/6250] eta: 0:15:54 lr: 0.000056 grad: 0.0828 (0.0852) loss: 0.9864 (0.9862) time: 0.2200 data: 0.1354 max mem: 9394 +Train: [2] [1700/6250] eta: 0:15:26 lr: 0.000057 grad: 0.0734 (0.0853) loss: 0.9872 (0.9862) time: 0.2633 data: 0.1707 max mem: 9394 +Train: [2] [1800/6250] eta: 0:15:00 lr: 0.000057 grad: 0.0793 (0.0852) loss: 0.9861 (0.9861) time: 0.1532 data: 0.0455 max mem: 9394 +Train: [2] [1900/6250] eta: 0:14:39 lr: 0.000058 grad: 0.0797 (0.0856) loss: 0.9856 (0.9861) time: 0.1546 data: 0.0627 max mem: 9394 +Train: [2] [2000/6250] eta: 0:14:26 lr: 0.000058 grad: 0.0690 (0.0853) loss: 0.9890 (0.9861) time: 0.3853 data: 0.2808 max mem: 9394 +Train: [2] [2100/6250] eta: 0:14:05 lr: 0.000058 grad: 0.0825 (0.0852) loss: 0.9845 (0.9861) time: 0.1813 data: 0.0638 max mem: 9394 +Train: [2] [2200/6250] eta: 0:13:38 lr: 0.000059 grad: 0.0734 (0.0852) loss: 0.9851 (0.9861) time: 0.1754 data: 0.0876 max mem: 9394 +Train: [2] [2300/6250] eta: 0:13:15 lr: 0.000059 grad: 0.0807 (0.0851) loss: 0.9864 (0.9861) time: 0.1816 data: 0.0858 max mem: 9394 +Train: [2] [2400/6250] eta: 0:12:54 lr: 0.000060 grad: 0.0770 (0.0848) loss: 0.9873 (0.9861) time: 0.1106 data: 0.0002 max mem: 9394 +Train: [2] [2500/6250] eta: 0:12:29 lr: 0.000060 grad: 0.0844 (0.0847) loss: 0.9862 (0.9861) time: 0.1380 data: 0.0445 max mem: 9394 +Train: [2] [2600/6250] eta: 0:12:07 lr: 0.000060 grad: 0.0807 (0.0846) loss: 0.9849 (0.9861) time: 0.1153 data: 0.0275 max mem: 9394 +Train: [2] [2700/6250] eta: 0:11:46 lr: 0.000061 grad: 0.0819 (0.0845) loss: 0.9865 (0.9860) time: 0.2070 data: 0.1260 max mem: 9394 +Train: [2] [2800/6250] eta: 0:11:27 lr: 0.000061 grad: 0.0672 (0.0846) loss: 0.9871 (0.9860) time: 0.1777 data: 0.0829 max mem: 9394 +Train: [2] [2900/6250] eta: 0:11:06 lr: 0.000062 grad: 0.0804 (0.0845) loss: 0.9848 (0.9860) time: 0.1737 data: 0.0837 max mem: 9394 +Train: [2] [3000/6250] eta: 0:10:44 lr: 0.000062 grad: 0.0811 (0.0845) loss: 0.9839 (0.9860) time: 0.1841 data: 0.0867 max mem: 9394 +Train: [2] [3100/6250] eta: 0:10:24 lr: 0.000062 grad: 0.0858 (0.0845) loss: 0.9865 (0.9860) time: 0.1841 data: 0.0915 max mem: 9394 +Train: [2] [3200/6250] eta: 0:10:06 lr: 0.000063 grad: 0.0834 (0.0845) loss: 0.9854 (0.9860) time: 0.1447 data: 0.0645 max mem: 9394 +Train: [2] [3300/6250] eta: 0:09:44 lr: 0.000063 grad: 0.0943 (0.0847) loss: 0.9857 (0.9859) time: 0.2039 data: 0.0921 max mem: 9394 +Train: [2] [3400/6250] eta: 0:09:23 lr: 0.000064 grad: 0.0823 (0.0848) loss: 0.9843 (0.9859) time: 0.2100 data: 0.0909 max mem: 9394 +Train: [2] [3500/6250] eta: 0:09:04 lr: 0.000064 grad: 0.0758 (0.0849) loss: 0.9840 (0.9859) time: 0.1825 data: 0.0870 max mem: 9394 +Train: [2] [3600/6250] eta: 0:08:43 lr: 0.000064 grad: 0.0845 (0.0850) loss: 0.9858 (0.9858) time: 0.1545 data: 0.0638 max mem: 9394 +Train: [2] [3700/6250] eta: 0:08:24 lr: 0.000065 grad: 0.0996 (0.0851) loss: 0.9840 (0.9858) time: 0.2045 data: 0.1253 max mem: 9394 +Train: [2] [3800/6250] eta: 0:08:03 lr: 0.000065 grad: 0.0897 (0.0854) loss: 0.9851 (0.9858) time: 0.1760 data: 0.0953 max mem: 9394 +Train: [2] [3900/6250] eta: 0:07:43 lr: 0.000066 grad: 0.0803 (0.0855) loss: 0.9862 (0.9858) time: 0.1556 data: 0.0706 max mem: 9394 +Train: [2] [4000/6250] eta: 0:07:22 lr: 0.000066 grad: 0.0831 (0.0856) loss: 0.9851 (0.9858) time: 0.1937 data: 0.1075 max mem: 9394 +Train: [2] [4100/6250] eta: 0:07:03 lr: 0.000066 grad: 0.0973 (0.0859) loss: 0.9845 (0.9857) time: 0.1768 data: 0.0849 max mem: 9394 +Train: [2] [4200/6250] eta: 0:06:44 lr: 0.000067 grad: 0.1023 (0.0862) loss: 0.9840 (0.9857) time: 0.3688 data: 0.2773 max mem: 9394 +Train: [2] [4300/6250] eta: 0:06:23 lr: 0.000067 grad: 0.0920 (0.0867) loss: 0.9821 (0.9857) time: 0.1843 data: 0.0905 max mem: 9394 +Train: [2] [4400/6250] eta: 0:06:02 lr: 0.000068 grad: 0.0957 (0.0874) loss: 0.9871 (0.9856) time: 0.1597 data: 0.0680 max mem: 9394 +Train: [2] [4500/6250] eta: 0:05:41 lr: 0.000068 grad: 0.1055 (0.0880) loss: 0.9858 (0.9856) time: 0.1680 data: 0.0789 max mem: 9394 +Train: [2] [4600/6250] eta: 0:05:21 lr: 0.000068 grad: 0.1155 (0.0887) loss: 0.9849 (0.9856) time: 0.1755 data: 0.0861 max mem: 9394 +Train: [2] [4700/6250] eta: 0:05:01 lr: 0.000069 grad: 0.1111 (0.0894) loss: 0.9857 (0.9855) time: 0.1852 data: 0.1052 max mem: 9394 +Train: [2] [4800/6250] eta: 0:04:42 lr: 0.000069 grad: 0.1094 (0.0901) loss: 0.9828 (0.9855) time: 0.2659 data: 0.1762 max mem: 9394 +Train: [2] [4900/6250] eta: 0:04:23 lr: 0.000070 grad: 0.0951 (0.0909) loss: 0.9827 (0.9854) time: 0.2497 data: 0.1358 max mem: 9394 +Train: [2] [5000/6250] eta: 0:04:04 lr: 0.000070 grad: 0.1445 (0.0920) loss: 0.9828 (0.9854) time: 0.1661 data: 0.0854 max mem: 9394 +Train: [2] [5100/6250] eta: 0:03:45 lr: 0.000070 grad: 0.1064 (0.0931) loss: 0.9834 (0.9854) time: 0.1162 data: 0.0003 max mem: 9394 +Train: [2] [5200/6250] eta: 0:03:25 lr: 0.000071 grad: 0.1662 (0.0949) loss: 0.9825 (0.9853) time: 0.1044 data: 0.0005 max mem: 9394 +Train: [2] [5300/6250] eta: 0:03:06 lr: 0.000071 grad: 0.1103 (0.0963) loss: 0.9829 (0.9853) time: 0.2513 data: 0.1603 max mem: 9394 +Train: [2] [5400/6250] eta: 0:02:47 lr: 0.000072 grad: 0.1580 (0.0983) loss: 0.9831 (0.9852) time: 0.1276 data: 0.0332 max mem: 9394 +Train: [2] [5500/6250] eta: 0:02:28 lr: 0.000072 grad: 0.1427 (0.1006) loss: 0.9841 (0.9852) time: 0.4146 data: 0.3186 max mem: 9394 +Train: [2] [5600/6250] eta: 0:02:08 lr: 0.000072 grad: 0.1863 (0.1026) loss: 0.9821 (0.9851) time: 0.1440 data: 0.0427 max mem: 9394 +Train: [2] [5700/6250] eta: 0:01:49 lr: 0.000073 grad: 0.1686 (0.1049) loss: 0.9819 (0.9851) time: 0.1258 data: 0.0365 max mem: 9394 +Train: [2] [5800/6250] eta: 0:01:29 lr: 0.000073 grad: 0.1631 (0.1068) loss: 0.9815 (0.9851) time: 0.2256 data: 0.1227 max mem: 9394 +Train: [2] [5900/6250] eta: 0:01:09 lr: 0.000074 grad: 0.1957 (0.1090) loss: 0.9825 (0.9850) time: 0.1451 data: 0.0536 max mem: 9394 +Train: [2] [6000/6250] eta: 0:00:49 lr: 0.000074 grad: 0.1409 (0.1110) loss: 0.9833 (0.9850) time: 0.1777 data: 0.0919 max mem: 9394 +Train: [2] [6100/6250] eta: 0:00:29 lr: 0.000074 grad: 0.1149 (0.1124) loss: 0.9795 (0.9849) time: 0.1777 data: 0.0902 max mem: 9394 +Train: [2] [6200/6250] eta: 0:00:09 lr: 0.000075 grad: 0.1505 (0.1145) loss: 0.9818 (0.9848) time: 0.1636 data: 0.0785 max mem: 9394 +Train: [2] [6249/6250] eta: 0:00:00 lr: 0.000075 grad: 0.1448 (0.1154) loss: 0.9798 (0.9848) time: 0.1774 data: 0.0938 max mem: 9394 +Train: [2] Total time: 0:20:38 (0.1982 s / it) +Averaged stats: lr: 0.000075 grad: 0.1448 (0.1154) loss: 0.9798 (0.9848) +Eval (hcp-train-subset): [2] [ 0/62] eta: 0:04:53 loss: 0.9857 (0.9857) time: 4.7341 data: 4.7020 max mem: 9394 +Eval (hcp-train-subset): [2] [61/62] eta: 0:00:00 loss: 0.9891 (0.9897) time: 0.1368 data: 0.1119 max mem: 9394 +Eval (hcp-train-subset): [2] Total time: 0:00:15 (0.2429 s / it) +Averaged stats (hcp-train-subset): loss: 0.9891 (0.9897) +Eval (hcp-val): [2] [ 0/62] eta: 0:03:55 loss: 0.9901 (0.9901) time: 3.7950 data: 3.7098 max mem: 9394 +Eval (hcp-val): [2] [61/62] eta: 0:00:00 loss: 0.9873 (0.9873) time: 0.1661 data: 0.1401 max mem: 9394 +Eval (hcp-val): [2] Total time: 0:00:14 (0.2408 s / it) +Averaged stats (hcp-val): loss: 0.9873 (0.9873) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +Train: [3] [ 0/6250] eta: 11:05:46 lr: 0.000075 grad: 0.9882 (0.9882) loss: 0.9930 (0.9930) time: 6.3914 data: 6.2693 max mem: 9394 +Train: [3] [ 100/6250] eta: 0:23:13 lr: 0.000075 grad: 0.1510 (0.2685) loss: 0.9773 (0.9803) time: 0.1532 data: 0.0545 max mem: 9394 +Train: [3] [ 200/6250] eta: 0:20:19 lr: 0.000076 grad: 0.2598 (0.2604) loss: 0.9848 (0.9791) time: 0.1800 data: 0.0866 max mem: 9394 +Train: [3] [ 300/6250] eta: 0:19:15 lr: 0.000076 grad: 0.2257 (0.2469) loss: 0.9804 (0.9795) time: 0.1935 data: 0.0972 max mem: 9394 +Train: [3] [ 400/6250] eta: 0:18:15 lr: 0.000077 grad: 0.1621 (0.2417) loss: 0.9822 (0.9795) time: 0.1487 data: 0.0500 max mem: 9394 +Train: [3] [ 500/6250] eta: 0:17:46 lr: 0.000077 grad: 0.2559 (0.2364) loss: 0.9836 (0.9798) time: 0.1817 data: 0.0928 max mem: 9394 +Train: [3] [ 600/6250] eta: 0:17:24 lr: 0.000077 grad: 0.1240 (0.2323) loss: 0.9780 (0.9800) time: 0.1928 data: 0.0988 max mem: 9394 +Train: [3] [ 700/6250] eta: 0:17:07 lr: 0.000078 grad: 0.1784 (0.2290) loss: 0.9815 (0.9803) time: 0.1833 data: 0.0930 max mem: 9394 +Train: [3] [ 800/6250] eta: 0:17:03 lr: 0.000078 grad: 0.2042 (0.2256) loss: 0.9799 (0.9804) time: 0.2406 data: 0.1286 max mem: 9394 +pretraining fmri mae +start: 2026-04-01 13:11:32 +cwd: /data/connor/fmri-fm +sha: 7f4cedc35609f6857314e0d1ea6657523f17ddeb, status: has uncommitted changes, branch: dev/clane9 +config: +name: input_space_v3/flat_lr1e-3_6/pretrain +notes: input_space ablation v3 flat_lr1e-3_6; use tube masking and on-disk data (input_space=flat + base_lr=1e-3 seed=5406) +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain +input_space: flat +patch_size: 16 +num_frames: 16 +t_patch_size: 4 +mask_ratio: 0.9 +pred_mask_ratio: null +masking: tube +masking_kwargs: {} +mask_patch_size: null +model: mae_vit_base +model_kwargs: + decoding: attn + pos_embed: sep + target_norm: null + pca_norm_nc: 2 + t_pred_stride: 2 + no_decode_pos: true + mask_drop_scale: false + pred_edge_pad: 0 + gauss_sigma: null + class_token: true + reg_tokens: 0 + no_embed_class: true + head_init_scale: 0.0 + decoder_depth: 4 + drop_path_rate: 0.0 +datasets: + hcp-train: + type: wds + url: /data/fmri-datasets/pretrain/hcpya-all.${input_space}.wds/hcpya-all-${input_space}-{00000..01799}.tar + clipping: random + clipping_kwargs: + oversample: 4.0 + shuffle: true + buffer_size: 2000 + samples_per_epoch: 200000 + hcp-train-subset: + type: arrow + root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/validation + split_range: + - 0 + - 2000 + shuffle: false + hcp-val: + type: arrow + root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/test + split_range: + - 0 + - 2000 + shuffle: false +train_dataset: hcp-train +eval_datasets: +- hcp-train-subset +- hcp-val +val_dataset: null +clip_vmax: 3.0 +normalize: frame +tr_scale: null +crop_scale: null +crop_aspect: null +gray_jitter: null +num_workers: 16 +epochs: 100 +batch_size: 32 +accum_iter: 1 +base_lr: 0.001 +min_lr: 0.0 +warmup_epochs: 5 +weight_decay: 0.05 +betas: +- 0.9 +- 0.95 +clip_grad: 1.0 +amp: true +amp_dtype: float16 +ckpt: null +resume: true +auto_resume: true +start_epoch: 0 +max_checkpoints: 0 +checkpoint_period: null +plot_period: 5 +device: cuda +presend_cuda: false +seed: 5406 +debug: false +wandb: true +wandb_entity: null +wandb_project: fMRI-foundation-model +rank: 0 +world_size: 1 +gpu: 0 +distributed: true +dist_backend: nccl +in_chans: 1 +img_size: +- 224 +- 560 + +train transform: +Compose( + ToTensor() + TemporalCenterCrop(num_frames=16) + Normalize(mode='frame') + Clip(vmax=3.0) + FlatUnmask((224, 560)) +) +val transform: +Compose( + ToTensor() + TemporalCenterCrop(num_frames=16) + Normalize(mode='frame') + Clip(vmax=3.0) + FlatUnmask((224, 560)) +) +mask generator: +TubeMasking( + mask_ratio=0.9 + (patchify): Patchify2D((224, 560), (16, 16), in_chans=1) +) +loading dataset: hcp-train + +type: wds +url: /data/fmri-datasets/pretrain/hcpya-all.${input_space}.wds/hcpya-all-${input_space}-{00000..01799}.tar +clipping: random +clipping_kwargs: + oversample: 4.0 +shuffle: true +buffer_size: 2000 +samples_per_epoch: 200000 + +loading dataset: hcp-train-subset + +type: arrow +root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/validation +split_range: +- 0 +- 2000 +shuffle: false + +split indices: [899, 472, 767, 116, 1265, 1852, 300, 1335, 361, 1560] +loading dataset: hcp-val + +type: arrow +root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/test +split_range: +- 0 +- 2000 +shuffle: false + +split indices: [1075, 1189, 738, 1350, 965, 1964, 1367, 1183, 1619, 1407] +model: +MaskedAutoencoderViT( + decoding=attn, t_pred_stride=2, pred_edge_pad=0, no_decode_pos=True + (encoder): MaskedEncoder( + class_token=True, reg_tokens=0, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) + (pred_patchify): StridedPatchify3D((16, 224, 560), (2, 16, 16), in_chans=1, t_stride=2) + (decoder): MaskedDecoder( + cross_decode=False, class_token=True, no_embed_class=True + (pos_embed): SeparablePosEmbed(512, (4, 14, 35)) + (proj): Linear(in_features=768, out_features=512, bias=True) + (blocks): ModuleList( + (0-3): 4 x Block( + (norm1): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=16 + (q): Linear(in_features=512, out_features=512, bias=True) + (k): Linear(in_features=512, out_features=512, bias=True) + (v): Linear(in_features=512, out_features=512, bias=True) + (proj): Linear(in_features=512, out_features=512, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=512, out_features=2048, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=2048, out_features=512, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (head): Linear(in_features=512, out_features=512, bias=True) + ) +) +num params: 99.7M +total batch size: 32 = 32 bs per gpu x 1 accum x 1 gpus +lr: 1.25e-04 = 1.00e-03 x 32 / 256 +full schedule: epochs = 100 (steps = 625000) +warmup: epochs = 5 (steps = 31250) +loaded model state from checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +loaded optimizer state, resuming training from 3 +start training for 100 epochs +Train: [3] [ 0/6250] eta: 12:25:18 lr: 0.000075 grad: 0.4555 (0.4555) loss: 0.9938 (0.9938) time: 7.1550 data: 6.1037 max mem: 9353 +Train: [3] [ 100/6250] eta: 0:25:09 lr: 0.000075 grad: 0.1498 (0.2011) loss: 0.9779 (0.9818) time: 0.1550 data: 0.0630 max mem: 9390 +Train: [3] [ 200/6250] eta: 0:20:51 lr: 0.000076 grad: 0.2690 (0.2284) loss: 0.9821 (0.9791) time: 0.1713 data: 0.0759 max mem: 9390 +Train: [3] [ 300/6250] eta: 0:19:04 lr: 0.000076 grad: 0.1372 (0.2262) loss: 0.9832 (0.9790) time: 0.1260 data: 0.0327 max mem: 9390 +Train: [3] [ 400/6250] eta: 0:18:22 lr: 0.000077 grad: 0.1396 (0.2200) loss: 0.9828 (0.9791) time: 0.2078 data: 0.1213 max mem: 9390 +Train: [3] [ 500/6250] eta: 0:17:39 lr: 0.000077 grad: 0.2354 (0.2229) loss: 0.9826 (0.9794) time: 0.1638 data: 0.0694 max mem: 9390 +Train: [3] [ 600/6250] eta: 0:17:05 lr: 0.000077 grad: 0.1249 (0.2251) loss: 0.9808 (0.9796) time: 0.1576 data: 0.0647 max mem: 9390 +Train: [3] [ 700/6250] eta: 0:16:44 lr: 0.000078 grad: 0.1219 (0.2217) loss: 0.9817 (0.9797) time: 0.1956 data: 0.1079 max mem: 9390 +Train: [3] [ 800/6250] eta: 0:16:14 lr: 0.000078 grad: 0.1334 (0.2199) loss: 0.9820 (0.9799) time: 0.1605 data: 0.0627 max mem: 9390 +Train: [3] [ 900/6250] eta: 0:15:52 lr: 0.000079 grad: 0.1536 (0.2197) loss: 0.9808 (0.9800) time: 0.1941 data: 0.1052 max mem: 9390 +Train: [3] [1000/6250] eta: 0:15:19 lr: 0.000079 grad: 0.1576 (0.2159) loss: 0.9792 (0.9802) time: 0.1501 data: 0.0638 max mem: 9390 +Train: [3] [1100/6250] eta: 0:14:52 lr: 0.000079 grad: 0.1463 (0.2140) loss: 0.9810 (0.9803) time: 0.1458 data: 0.0541 max mem: 9390 +Train: [3] [1200/6250] eta: 0:14:30 lr: 0.000080 grad: 0.1203 (0.2117) loss: 0.9806 (0.9804) time: 0.1438 data: 0.0551 max mem: 9390 +Train: [3] [1300/6250] eta: 0:14:07 lr: 0.000080 grad: 0.2123 (0.2114) loss: 0.9811 (0.9804) time: 0.1472 data: 0.0551 max mem: 9390 +Train: [3] [1400/6250] eta: 0:13:46 lr: 0.000081 grad: 0.2346 (0.2106) loss: 0.9813 (0.9805) time: 0.1684 data: 0.0793 max mem: 9390 +Train: [3] [1500/6250] eta: 0:13:27 lr: 0.000081 grad: 0.1633 (0.2122) loss: 0.9818 (0.9805) time: 0.1657 data: 0.0779 max mem: 9390 +Train: [3] [1600/6250] eta: 0:13:06 lr: 0.000081 grad: 0.1384 (0.2108) loss: 0.9796 (0.9804) time: 0.1510 data: 0.0601 max mem: 9390 +Train: [3] [1700/6250] eta: 0:12:49 lr: 0.000082 grad: 0.1843 (0.2108) loss: 0.9788 (0.9803) time: 0.1897 data: 0.1055 max mem: 9390 +Train: [3] [1800/6250] eta: 0:12:27 lr: 0.000082 grad: 0.1282 (0.2099) loss: 0.9779 (0.9803) time: 0.1565 data: 0.0671 max mem: 9390 +Train: [3] [1900/6250] eta: 0:12:08 lr: 0.000083 grad: 0.1467 (0.2097) loss: 0.9771 (0.9802) time: 0.1604 data: 0.0715 max mem: 9390 +Train: [3] [2000/6250] eta: 0:11:50 lr: 0.000083 grad: 0.1732 (0.2082) loss: 0.9794 (0.9801) time: 0.1704 data: 0.0784 max mem: 9390 +Train: [3] [2100/6250] eta: 0:11:31 lr: 0.000083 grad: 0.1692 (0.2083) loss: 0.9788 (0.9801) time: 0.1537 data: 0.0723 max mem: 9390 +Train: [3] [2200/6250] eta: 0:11:12 lr: 0.000084 grad: 0.1441 (0.2082) loss: 0.9776 (0.9801) time: 0.1337 data: 0.0467 max mem: 9390 +Train: [3] [2300/6250] eta: 0:10:55 lr: 0.000084 grad: 0.1633 (0.2075) loss: 0.9799 (0.9800) time: 0.1742 data: 0.0942 max mem: 9390 +Train: [3] [2400/6250] eta: 0:10:37 lr: 0.000085 grad: 0.1690 (0.2084) loss: 0.9783 (0.9800) time: 0.1651 data: 0.0806 max mem: 9390 +Train: [3] [2500/6250] eta: 0:10:20 lr: 0.000085 grad: 0.1617 (0.2089) loss: 0.9784 (0.9799) time: 0.1661 data: 0.0776 max mem: 9390 +Train: [3] [2600/6250] eta: 0:10:02 lr: 0.000085 grad: 0.1898 (0.2093) loss: 0.9789 (0.9799) time: 0.1578 data: 0.0698 max mem: 9390 +Train: [3] [2700/6250] eta: 0:09:44 lr: 0.000086 grad: 0.1807 (0.2081) loss: 0.9784 (0.9798) time: 0.1593 data: 0.0705 max mem: 9390 +Train: [3] [2800/6250] eta: 0:09:26 lr: 0.000086 grad: 0.1889 (0.2077) loss: 0.9782 (0.9797) time: 0.1531 data: 0.0652 max mem: 9390 +Train: [3] [2900/6250] eta: 0:09:09 lr: 0.000087 grad: 0.1473 (0.2074) loss: 0.9772 (0.9797) time: 0.1725 data: 0.0800 max mem: 9390 +Train: [3] [3000/6250] eta: 0:08:52 lr: 0.000087 grad: 0.1415 (0.2071) loss: 0.9783 (0.9796) time: 0.1660 data: 0.0814 max mem: 9390 +Train: [3] [3100/6250] eta: 0:08:36 lr: 0.000087 grad: 0.1330 (0.2062) loss: 0.9773 (0.9795) time: 0.1510 data: 0.0601 max mem: 9390 +Train: [3] [3200/6250] eta: 0:08:20 lr: 0.000088 grad: 0.1224 (0.2065) loss: 0.9754 (0.9795) time: 0.1976 data: 0.1059 max mem: 9390 +Train: [3] [3300/6250] eta: 0:08:02 lr: 0.000088 grad: 0.1520 (0.2062) loss: 0.9773 (0.9794) time: 0.1245 data: 0.0388 max mem: 9390 +Train: [3] [3400/6250] eta: 0:07:46 lr: 0.000089 grad: 0.1604 (0.2056) loss: 0.9786 (0.9794) time: 0.1607 data: 0.0693 max mem: 9390 +Train: [3] [3500/6250] eta: 0:07:28 lr: 0.000089 grad: 0.1601 (0.2052) loss: 0.9785 (0.9793) time: 0.1440 data: 0.0495 max mem: 9390 +Train: [3] [3600/6250] eta: 0:07:12 lr: 0.000089 grad: 0.1333 (0.2050) loss: 0.9775 (0.9793) time: 0.1678 data: 0.0851 max mem: 9390 +Train: [3] [3700/6250] eta: 0:06:55 lr: 0.000090 grad: 0.1521 (0.2044) loss: 0.9767 (0.9792) time: 0.1171 data: 0.0254 max mem: 9390 +Train: [3] [3800/6250] eta: 0:06:38 lr: 0.000090 grad: 0.1830 (0.2042) loss: 0.9769 (0.9792) time: 0.1296 data: 0.0457 max mem: 9390 +Train: [3] [3900/6250] eta: 0:06:21 lr: 0.000091 grad: 0.2084 (0.2039) loss: 0.9777 (0.9791) time: 0.1402 data: 0.0577 max mem: 9390 +Train: [3] [4000/6250] eta: 0:06:03 lr: 0.000091 grad: 0.1842 (0.2037) loss: 0.9759 (0.9791) time: 0.1435 data: 0.0598 max mem: 9390 +Train: [3] [4100/6250] eta: 0:05:46 lr: 0.000091 grad: 0.1474 (0.2034) loss: 0.9759 (0.9790) time: 0.1436 data: 0.0561 max mem: 9390 +Train: [3] [4200/6250] eta: 0:05:29 lr: 0.000092 grad: 0.1346 (0.2025) loss: 0.9775 (0.9790) time: 0.1413 data: 0.0554 max mem: 9390 +Train: [3] [4300/6250] eta: 0:05:12 lr: 0.000092 grad: 0.2081 (0.2023) loss: 0.9778 (0.9790) time: 0.1368 data: 0.0562 max mem: 9390 +Train: [3] [4400/6250] eta: 0:04:55 lr: 0.000093 grad: 0.1778 (0.2021) loss: 0.9770 (0.9789) time: 0.1542 data: 0.0778 max mem: 9390 +Train: [3] [4500/6250] eta: 0:04:38 lr: 0.000093 grad: 0.1215 (0.2021) loss: 0.9773 (0.9789) time: 0.1287 data: 0.0471 max mem: 9390 +Train: [3] [4600/6250] eta: 0:04:21 lr: 0.000093 grad: 0.1284 (0.2012) loss: 0.9752 (0.9788) time: 0.1413 data: 0.0580 max mem: 9390 +Train: [3] [4700/6250] eta: 0:04:04 lr: 0.000094 grad: 0.2031 (0.2014) loss: 0.9773 (0.9788) time: 0.1334 data: 0.0454 max mem: 9390 +Train: [3] [4800/6250] eta: 0:03:48 lr: 0.000094 grad: 0.2101 (0.2014) loss: 0.9791 (0.9787) time: 0.1284 data: 0.0450 max mem: 9390 +Train: [3] [4900/6250] eta: 0:03:31 lr: 0.000095 grad: 0.1546 (0.2010) loss: 0.9770 (0.9787) time: 0.1355 data: 0.0501 max mem: 9390 +Train: [3] [5000/6250] eta: 0:03:15 lr: 0.000095 grad: 0.1572 (0.2007) loss: 0.9773 (0.9786) time: 0.1226 data: 0.0383 max mem: 9390 +Train: [3] [5100/6250] eta: 0:02:59 lr: 0.000095 grad: 0.1574 (0.2007) loss: 0.9763 (0.9786) time: 0.1285 data: 0.0406 max mem: 9390 +Train: [3] [5200/6250] eta: 0:02:43 lr: 0.000096 grad: 0.1240 (0.2005) loss: 0.9737 (0.9785) time: 0.1176 data: 0.0348 max mem: 9390 +Train: [3] [5300/6250] eta: 0:02:27 lr: 0.000096 grad: 0.1643 (0.2002) loss: 0.9760 (0.9785) time: 0.1373 data: 0.0348 max mem: 9390 +Train: [3] [5400/6250] eta: 0:02:11 lr: 0.000097 grad: 0.1622 (0.2001) loss: 0.9747 (0.9784) time: 0.1437 data: 0.0581 max mem: 9390 +Train: [3] [5500/6250] eta: 0:01:55 lr: 0.000097 grad: 0.1737 (0.1997) loss: 0.9756 (0.9784) time: 0.1336 data: 0.0487 max mem: 9390 +Train: [3] [5600/6250] eta: 0:01:40 lr: 0.000097 grad: 0.1617 (0.1993) loss: 0.9755 (0.9783) time: 0.1513 data: 0.0639 max mem: 9390 +Train: [3] [5700/6250] eta: 0:01:24 lr: 0.000098 grad: 0.1745 (0.1987) loss: 0.9754 (0.9783) time: 0.1432 data: 0.0552 max mem: 9390 +Train: [3] [5800/6250] eta: 0:01:09 lr: 0.000098 grad: 0.1323 (0.1982) loss: 0.9749 (0.9782) time: 0.1316 data: 0.0457 max mem: 9390 +Train: [3] [5900/6250] eta: 0:00:53 lr: 0.000099 grad: 0.1262 (0.1980) loss: 0.9751 (0.9782) time: 0.1447 data: 0.0671 max mem: 9390 +Train: [3] [6000/6250] eta: 0:00:38 lr: 0.000099 grad: 0.1487 (0.1974) loss: 0.9752 (0.9781) time: 0.1430 data: 0.0630 max mem: 9390 +Train: [3] [6100/6250] eta: 0:00:22 lr: 0.000099 grad: 0.1608 (0.1971) loss: 0.9758 (0.9780) time: 0.1342 data: 0.0522 max mem: 9390 +Train: [3] [6200/6250] eta: 0:00:07 lr: 0.000100 grad: 0.1402 (0.1969) loss: 0.9749 (0.9779) time: 0.1564 data: 0.0728 max mem: 9390 +Train: [3] [6249/6250] eta: 0:00:00 lr: 0.000100 grad: 0.1423 (0.1968) loss: 0.9745 (0.9779) time: 0.1835 data: 0.0996 max mem: 9390 +Train: [3] Total time: 0:15:58 (0.1534 s / it) +Averaged stats: lr: 0.000100 grad: 0.1423 (0.1968) loss: 0.9745 (0.9779) +Eval (hcp-train-subset): [3] [ 0/62] eta: 0:02:57 loss: 0.9755 (0.9755) time: 2.8686 data: 2.8197 max mem: 9390 +Eval (hcp-train-subset): [3] [61/62] eta: 0:00:00 loss: 0.9787 (0.9770) time: 0.1063 data: 0.0816 max mem: 9390 +Eval (hcp-train-subset): [3] Total time: 0:00:12 (0.2076 s / it) +Averaged stats (hcp-train-subset): loss: 0.9787 (0.9770) +Eval (hcp-val): [3] [ 0/62] eta: 0:04:28 loss: 0.9671 (0.9671) time: 4.3237 data: 4.2933 max mem: 9390 +Eval (hcp-val): [3] [61/62] eta: 0:00:00 loss: 0.9734 (0.9737) time: 0.1225 data: 0.0961 max mem: 9390 +Eval (hcp-val): [3] Total time: 0:00:12 (0.1983 s / it) +Averaged stats (hcp-val): loss: 0.9734 (0.9737) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +Train: [4] [ 0/6250] eta: 9:37:17 lr: 0.000100 grad: 0.1611 (0.1611) loss: 0.9664 (0.9664) time: 5.5420 data: 5.4163 max mem: 9390 +Train: [4] [ 100/6250] eta: 0:20:38 lr: 0.000100 grad: 0.1386 (0.1949) loss: 0.9747 (0.9761) time: 0.1445 data: 0.0574 max mem: 9390 +Train: [4] [ 200/6250] eta: 0:17:30 lr: 0.000101 grad: 0.1790 (0.1973) loss: 0.9735 (0.9749) time: 0.1366 data: 0.0465 max mem: 9390 +Train: [4] [ 300/6250] eta: 0:16:25 lr: 0.000101 grad: 0.1485 (0.1977) loss: 0.9750 (0.9747) time: 0.1432 data: 0.0469 max mem: 9390 +Train: [4] [ 400/6250] eta: 0:16:18 lr: 0.000102 grad: 0.1107 (0.1904) loss: 0.9727 (0.9747) time: 0.1672 data: 0.0839 max mem: 9390 +Train: [4] [ 500/6250] eta: 0:16:04 lr: 0.000102 grad: 0.1564 (0.1836) loss: 0.9700 (0.9744) time: 0.1575 data: 0.0693 max mem: 9390 +Train: [4] [ 600/6250] eta: 0:15:46 lr: 0.000102 grad: 0.1935 (0.1829) loss: 0.9706 (0.9740) time: 0.1817 data: 0.0975 max mem: 9390 +Train: [4] [ 700/6250] eta: 0:15:30 lr: 0.000103 grad: 0.1248 (0.1861) loss: 0.9713 (0.9738) time: 0.1624 data: 0.0746 max mem: 9390 +Train: [4] [ 800/6250] eta: 0:15:19 lr: 0.000103 grad: 0.1402 (0.1850) loss: 0.9705 (0.9734) time: 0.1796 data: 0.0888 max mem: 9390 +Train: [4] [ 900/6250] eta: 0:15:11 lr: 0.000104 grad: 0.1968 (0.1854) loss: 0.9702 (0.9730) time: 0.1386 data: 0.0361 max mem: 9390 +Train: [4] [1000/6250] eta: 0:14:51 lr: 0.000104 grad: 0.1349 (0.1853) loss: 0.9701 (0.9729) time: 0.1083 data: 0.0201 max mem: 9390 +Train: [4] [1100/6250] eta: 0:14:30 lr: 0.000104 grad: 0.1918 (0.1857) loss: 0.9695 (0.9726) time: 0.1664 data: 0.0820 max mem: 9390 +Train: [4] [1200/6250] eta: 0:14:13 lr: 0.000105 grad: 0.1963 (0.1856) loss: 0.9718 (0.9725) time: 0.1755 data: 0.1000 max mem: 9390 +Train: [4] [1300/6250] eta: 0:13:49 lr: 0.000105 grad: 0.1504 (0.1853) loss: 0.9698 (0.9723) time: 0.1373 data: 0.0542 max mem: 9390 +Train: [4] [1400/6250] eta: 0:13:30 lr: 0.000106 grad: 0.1525 (0.1855) loss: 0.9683 (0.9722) time: 0.1611 data: 0.0672 max mem: 9390 +Train: [4] [1500/6250] eta: 0:13:11 lr: 0.000106 grad: 0.1387 (0.1854) loss: 0.9709 (0.9721) time: 0.1511 data: 0.0625 max mem: 9390 +Train: [4] [1600/6250] eta: 0:12:51 lr: 0.000106 grad: 0.1472 (0.1854) loss: 0.9673 (0.9719) time: 0.1706 data: 0.0830 max mem: 9390 +Train: [4] [1700/6250] eta: 0:12:30 lr: 0.000107 grad: 0.1983 (0.1856) loss: 0.9685 (0.9717) time: 0.1519 data: 0.0642 max mem: 9390 +Train: [4] [1800/6250] eta: 0:12:11 lr: 0.000107 grad: 0.1690 (0.1861) loss: 0.9689 (0.9715) time: 0.1693 data: 0.0844 max mem: 9390 +Train: [4] [1900/6250] eta: 0:11:53 lr: 0.000108 grad: 0.1793 (0.1867) loss: 0.9659 (0.9713) time: 0.1328 data: 0.0470 max mem: 9390 +Train: [4] [2000/6250] eta: 0:11:35 lr: 0.000108 grad: 0.1765 (0.1858) loss: 0.9657 (0.9711) time: 0.1366 data: 0.0462 max mem: 9390 +Train: [4] [2100/6250] eta: 0:11:18 lr: 0.000108 grad: 0.1882 (0.1863) loss: 0.9652 (0.9708) time: 0.1708 data: 0.0886 max mem: 9390 +Train: [4] [2200/6250] eta: 0:11:35 lr: 0.000109 grad: 0.1583 (0.1867) loss: 0.9638 (0.9705) time: 0.1644 data: 0.0765 max mem: 9390 +Train: [4] [2300/6250] eta: 0:11:16 lr: 0.000109 grad: 0.1582 (0.1866) loss: 0.9638 (0.9702) time: 0.1743 data: 0.0908 max mem: 9390 +Train: [4] [2400/6250] eta: 0:10:56 lr: 0.000110 grad: 0.1908 (0.1869) loss: 0.9654 (0.9699) time: 0.1509 data: 0.0608 max mem: 9390 +Train: [4] [2500/6250] eta: 0:10:38 lr: 0.000110 grad: 0.1570 (0.1869) loss: 0.9612 (0.9696) time: 0.1455 data: 0.0534 max mem: 9390 +Train: [4] [2600/6250] eta: 0:10:19 lr: 0.000110 grad: 0.1747 (0.1864) loss: 0.9623 (0.9693) time: 0.1648 data: 0.0857 max mem: 9390 +Train: [4] [2700/6250] eta: 0:10:00 lr: 0.000111 grad: 0.1342 (0.1865) loss: 0.9615 (0.9690) time: 0.1522 data: 0.0672 max mem: 9390 +Train: [4] [2800/6250] eta: 0:09:41 lr: 0.000111 grad: 0.1994 (0.1874) loss: 0.9576 (0.9686) time: 0.1596 data: 0.0577 max mem: 9390 +Train: [4] [2900/6250] eta: 0:09:21 lr: 0.000112 grad: 0.2383 (0.1879) loss: 0.9593 (0.9683) time: 0.1524 data: 0.0620 max mem: 9390 +Train: [4] [3000/6250] eta: 0:09:03 lr: 0.000112 grad: 0.1643 (0.1885) loss: 0.9572 (0.9679) time: 0.1334 data: 0.0419 max mem: 9390 +Train: [4] [3100/6250] eta: 0:08:44 lr: 0.000112 grad: 0.1613 (0.1894) loss: 0.9543 (0.9676) time: 0.1455 data: 0.0621 max mem: 9390 +Train: [4] [3200/6250] eta: 0:08:24 lr: 0.000113 grad: 0.2326 (0.1903) loss: 0.9575 (0.9672) time: 0.1249 data: 0.0452 max mem: 9390 +Train: [4] [3300/6250] eta: 0:08:05 lr: 0.000113 grad: 0.2187 (0.1908) loss: 0.9505 (0.9668) time: 0.1368 data: 0.0553 max mem: 9390 +Train: [4] [3400/6250] eta: 0:07:47 lr: 0.000114 grad: 0.1699 (0.1911) loss: 0.9525 (0.9664) time: 0.1445 data: 0.0654 max mem: 9390 +Train: [4] [3500/6250] eta: 0:07:28 lr: 0.000114 grad: 0.2032 (0.1917) loss: 0.9521 (0.9660) time: 0.1411 data: 0.0585 max mem: 9390 +Train: [4] [3600/6250] eta: 0:07:10 lr: 0.000114 grad: 0.1965 (0.1927) loss: 0.9506 (0.9655) time: 0.1247 data: 0.0370 max mem: 9390 +Train: [4] [3700/6250] eta: 0:06:52 lr: 0.000115 grad: 0.1706 (0.1936) loss: 0.9484 (0.9651) time: 0.1372 data: 0.0503 max mem: 9390 +Train: [4] [3800/6250] eta: 0:06:35 lr: 0.000115 grad: 0.2061 (0.1950) loss: 0.9439 (0.9646) time: 0.1559 data: 0.0703 max mem: 9390 +Train: [4] [3900/6250] eta: 0:06:17 lr: 0.000116 grad: 0.2159 (0.1961) loss: 0.9445 (0.9641) time: 0.1144 data: 0.0343 max mem: 9390 +Train: [4] [4000/6250] eta: 0:06:00 lr: 0.000116 grad: 0.2022 (0.1970) loss: 0.9431 (0.9636) time: 0.1482 data: 0.0608 max mem: 9390 +Train: [4] [4100/6250] eta: 0:05:43 lr: 0.000116 grad: 0.2077 (0.1980) loss: 0.9436 (0.9631) time: 0.1305 data: 0.0483 max mem: 9390 +Train: [4] [4200/6250] eta: 0:05:26 lr: 0.000117 grad: 0.2392 (0.1990) loss: 0.9407 (0.9626) time: 0.1397 data: 0.0529 max mem: 9390 +Train: [4] [4300/6250] eta: 0:05:09 lr: 0.000117 grad: 0.1951 (0.1997) loss: 0.9384 (0.9620) time: 0.1267 data: 0.0461 max mem: 9390 +Train: [4] [4400/6250] eta: 0:04:52 lr: 0.000118 grad: 0.2756 (0.2007) loss: 0.9402 (0.9615) time: 0.1288 data: 0.0436 max mem: 9390 +Train: [4] [4500/6250] eta: 0:04:36 lr: 0.000118 grad: 0.1921 (0.2012) loss: 0.9374 (0.9609) time: 0.1810 data: 0.0916 max mem: 9390 +Train: [4] [4600/6250] eta: 0:04:28 lr: 0.000118 grad: 0.1790 (0.2019) loss: 0.9368 (0.9604) time: 0.2136 data: 0.0942 max mem: 9390 +Train: [4] [4700/6250] eta: 0:04:17 lr: 0.000119 grad: 0.1655 (0.2025) loss: 0.9346 (0.9599) time: 0.3725 data: 0.2557 max mem: 9390 +Train: [4] [4800/6250] eta: 0:04:05 lr: 0.000119 grad: 0.1923 (0.2030) loss: 0.9368 (0.9594) time: 0.1146 data: 0.0003 max mem: 9390 +Train: [4] [4900/6250] eta: 0:03:52 lr: 0.000120 grad: 0.1791 (0.2031) loss: 0.9346 (0.9589) time: 0.2164 data: 0.1366 max mem: 9390 +Train: [4] [5000/6250] eta: 0:03:38 lr: 0.000120 grad: 0.2069 (0.2034) loss: 0.9367 (0.9585) time: 0.1389 data: 0.0056 max mem: 9390 +Train: [4] [5100/6250] eta: 0:03:23 lr: 0.000120 grad: 0.1432 (0.2034) loss: 0.9329 (0.9580) time: 0.1805 data: 0.0875 max mem: 9390 +Train: [4] [5200/6250] eta: 0:03:09 lr: 0.000121 grad: 0.2195 (0.2035) loss: 0.9334 (0.9575) time: 0.1974 data: 0.0912 max mem: 9390 +Train: [4] [5300/6250] eta: 0:02:53 lr: 0.000121 grad: 0.2144 (0.2035) loss: 0.9335 (0.9571) time: 0.4307 data: 0.3024 max mem: 9390 +Train: [4] [5400/6250] eta: 0:02:35 lr: 0.000122 grad: 0.1887 (0.2037) loss: 0.9312 (0.9566) time: 0.1860 data: 0.1072 max mem: 9390 +Train: [4] [5500/6250] eta: 0:02:16 lr: 0.000122 grad: 0.1634 (0.2036) loss: 0.9306 (0.9562) time: 0.1633 data: 0.0721 max mem: 9390 +Train: [4] [5600/6250] eta: 0:01:58 lr: 0.000122 grad: 0.1559 (0.2039) loss: 0.9312 (0.9557) time: 0.1763 data: 0.0917 max mem: 9390 +Train: [4] [5700/6250] eta: 0:01:39 lr: 0.000123 grad: 0.1992 (0.2038) loss: 0.9281 (0.9552) time: 0.1693 data: 0.0877 max mem: 9390 +Train: [4] [5800/6250] eta: 0:01:21 lr: 0.000123 grad: 0.1921 (0.2041) loss: 0.9296 (0.9548) time: 0.1657 data: 0.0868 max mem: 9390 +Train: [4] [5900/6250] eta: 0:01:03 lr: 0.000124 grad: 0.2484 (0.2042) loss: 0.9302 (0.9544) time: 0.1502 data: 0.0630 max mem: 9390 +Train: [4] [6000/6250] eta: 0:00:45 lr: 0.000124 grad: 0.2153 (0.2043) loss: 0.9275 (0.9539) time: 0.1417 data: 0.0540 max mem: 9390 +Train: [4] [6100/6250] eta: 0:00:26 lr: 0.000124 grad: 0.1996 (0.2044) loss: 0.9296 (0.9535) time: 0.1715 data: 0.0872 max mem: 9390 +Train: [4] [6200/6250] eta: 0:00:08 lr: 0.000125 grad: 0.1649 (0.2045) loss: 0.9274 (0.9531) time: 0.1768 data: 0.0932 max mem: 9390 +Train: [4] [6249/6250] eta: 0:00:00 lr: 0.000125 grad: 0.1526 (0.2043) loss: 0.9258 (0.9529) time: 0.1475 data: 0.0685 max mem: 9390 +Train: [4] Total time: 0:18:44 (0.1800 s / it) +Averaged stats: lr: 0.000125 grad: 0.1526 (0.2043) loss: 0.9258 (0.9529) +Eval (hcp-train-subset): [4] [ 0/62] eta: 0:04:03 loss: 0.9344 (0.9344) time: 3.9326 data: 3.9018 max mem: 9390 +Eval (hcp-train-subset): [4] [61/62] eta: 0:00:00 loss: 0.9281 (0.9295) time: 0.1464 data: 0.1212 max mem: 9390 +Eval (hcp-train-subset): [4] Total time: 0:00:12 (0.2040 s / it) +Averaged stats (hcp-train-subset): loss: 0.9281 (0.9295) +Making plots (hcp-train-subset): example=34 +Eval (hcp-val): [4] [ 0/62] eta: 0:03:48 loss: 0.9219 (0.9219) time: 3.6863 data: 3.6074 max mem: 9390 +Eval (hcp-val): [4] [61/62] eta: 0:00:00 loss: 0.9243 (0.9241) time: 0.1266 data: 0.1006 max mem: 9390 +Eval (hcp-val): [4] Total time: 0:00:13 (0.2102 s / it) +Averaged stats (hcp-val): loss: 0.9243 (0.9241) +Making plots (hcp-val): example=33 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +Train: [5] [ 0/6250] eta: 10:25:34 lr: 0.000125 grad: 0.2850 (0.2850) loss: 0.9224 (0.9224) time: 6.0055 data: 5.9089 max mem: 9390 +Train: [5] [ 100/6250] eta: 0:20:13 lr: 0.000125 grad: 0.1400 (0.1814) loss: 0.9330 (0.9337) time: 0.1553 data: 0.0697 max mem: 9390 +Train: [5] [ 200/6250] eta: 0:17:57 lr: 0.000125 grad: 0.1574 (0.1912) loss: 0.9297 (0.9318) time: 0.1452 data: 0.0582 max mem: 9390 +Train: [5] [ 300/6250] eta: 0:16:32 lr: 0.000125 grad: 0.2232 (0.1879) loss: 0.9265 (0.9300) time: 0.1592 data: 0.0729 max mem: 9390 +Train: [5] [ 400/6250] eta: 0:15:33 lr: 0.000125 grad: 0.1928 (0.1865) loss: 0.9207 (0.9289) time: 0.1145 data: 0.0256 max mem: 9390 +Train: [5] [ 500/6250] eta: 0:14:58 lr: 0.000125 grad: 0.1772 (0.1867) loss: 0.9252 (0.9282) time: 0.1392 data: 0.0427 max mem: 9390 +Train: [5] [ 600/6250] eta: 0:14:33 lr: 0.000125 grad: 0.1642 (0.1856) loss: 0.9274 (0.9277) time: 0.1670 data: 0.0791 max mem: 9390 +Train: [5] [ 700/6250] eta: 0:14:14 lr: 0.000125 grad: 0.1745 (0.1856) loss: 0.9273 (0.9274) time: 0.1118 data: 0.0241 max mem: 9390 +Train: [5] [ 800/6250] eta: 0:14:07 lr: 0.000125 grad: 0.1522 (0.1850) loss: 0.9246 (0.9269) time: 0.1545 data: 0.0724 max mem: 9390 +Train: [5] [ 900/6250] eta: 0:13:56 lr: 0.000125 grad: 0.1965 (0.1843) loss: 0.9242 (0.9265) time: 0.1709 data: 0.0824 max mem: 9390 +Train: [5] [1000/6250] eta: 0:13:46 lr: 0.000125 grad: 0.1809 (0.1836) loss: 0.9223 (0.9262) time: 0.2199 data: 0.1356 max mem: 9390 +Train: [5] [1100/6250] eta: 0:13:18 lr: 0.000125 grad: 0.1849 (0.1856) loss: 0.9240 (0.9258) time: 0.1271 data: 0.0411 max mem: 9390 +Train: [5] [1200/6250] eta: 0:13:00 lr: 0.000125 grad: 0.1566 (0.1841) loss: 0.9214 (0.9254) time: 0.1447 data: 0.0618 max mem: 9390 +Train: [5] [1300/6250] eta: 0:12:38 lr: 0.000125 grad: 0.1551 (0.1826) loss: 0.9200 (0.9251) time: 0.1535 data: 0.0705 max mem: 9390 +Train: [5] [1400/6250] eta: 0:12:19 lr: 0.000125 grad: 0.1452 (0.1809) loss: 0.9233 (0.9248) time: 0.1384 data: 0.0580 max mem: 9390 +Train: [5] [1500/6250] eta: 0:12:04 lr: 0.000125 grad: 0.1576 (0.1802) loss: 0.9209 (0.9244) time: 0.1250 data: 0.0464 max mem: 9390 +Train: [5] [1600/6250] eta: 0:11:46 lr: 0.000125 grad: 0.1502 (0.1793) loss: 0.9156 (0.9241) time: 0.1397 data: 0.0606 max mem: 9390 +Train: [5] [1700/6250] eta: 0:11:31 lr: 0.000125 grad: 0.1792 (0.1784) loss: 0.9180 (0.9238) time: 0.1556 data: 0.0803 max mem: 9390 +Train: [5] [1800/6250] eta: 0:11:16 lr: 0.000125 grad: 0.1498 (0.1774) loss: 0.9191 (0.9235) time: 0.1531 data: 0.0704 max mem: 9390 +Train: [5] [1900/6250] eta: 0:10:59 lr: 0.000125 grad: 0.1409 (0.1772) loss: 0.9142 (0.9231) time: 0.1418 data: 0.0564 max mem: 9390 +Train: [5] [2000/6250] eta: 0:10:45 lr: 0.000125 grad: 0.1699 (0.1764) loss: 0.9177 (0.9228) time: 0.1752 data: 0.0963 max mem: 9390 +Train: [5] [2100/6250] eta: 0:10:30 lr: 0.000125 grad: 0.1621 (0.1757) loss: 0.9179 (0.9225) time: 0.1747 data: 0.0925 max mem: 9390 +Train: [5] [2200/6250] eta: 0:10:13 lr: 0.000125 grad: 0.1256 (0.1748) loss: 0.9138 (0.9222) time: 0.1530 data: 0.0620 max mem: 9390 +Train: [5] [2300/6250] eta: 0:09:57 lr: 0.000125 grad: 0.1595 (0.1743) loss: 0.9159 (0.9219) time: 0.1512 data: 0.0669 max mem: 9390 +Train: [5] [2400/6250] eta: 0:09:40 lr: 0.000125 grad: 0.1787 (0.1740) loss: 0.9126 (0.9216) time: 0.1548 data: 0.0639 max mem: 9390 +Train: [5] [2500/6250] eta: 0:09:27 lr: 0.000125 grad: 0.1555 (0.1736) loss: 0.9129 (0.9213) time: 0.1929 data: 0.1032 max mem: 9390 +Train: [5] [2600/6250] eta: 0:09:12 lr: 0.000125 grad: 0.1660 (0.1728) loss: 0.9175 (0.9211) time: 0.1316 data: 0.0528 max mem: 9390 +Train: [5] [2700/6250] eta: 0:08:57 lr: 0.000125 grad: 0.1500 (0.1721) loss: 0.9114 (0.9208) time: 0.1853 data: 0.1014 max mem: 9390 +Train: [5] [2800/6250] eta: 0:08:43 lr: 0.000125 grad: 0.1557 (0.1719) loss: 0.9108 (0.9205) time: 0.1692 data: 0.0889 max mem: 9390 +Train: [5] [2900/6250] eta: 0:08:27 lr: 0.000125 grad: 0.1383 (0.1716) loss: 0.9141 (0.9201) time: 0.1746 data: 0.0865 max mem: 9390 +Train: [5] [3000/6250] eta: 0:08:13 lr: 0.000125 grad: 0.1605 (0.1715) loss: 0.9132 (0.9198) time: 0.2098 data: 0.1260 max mem: 9390 +Train: [5] [3100/6250] eta: 0:07:57 lr: 0.000125 grad: 0.1392 (0.1711) loss: 0.9061 (0.9195) time: 0.1406 data: 0.0608 max mem: 9390 +Train: [5] [3200/6250] eta: 0:07:47 lr: 0.000125 grad: 0.1657 (0.1717) loss: 0.9089 (0.9191) time: 0.2387 data: 0.1486 max mem: 9390 +Train: [5] [3300/6250] eta: 0:07:34 lr: 0.000125 grad: 0.1668 (0.1715) loss: 0.9044 (0.9188) time: 0.1100 data: 0.0055 max mem: 9390 +Train: [5] [3400/6250] eta: 0:07:21 lr: 0.000125 grad: 0.1905 (0.1712) loss: 0.9056 (0.9184) time: 0.2353 data: 0.1459 max mem: 9390 +Train: [5] [3500/6250] eta: 0:07:08 lr: 0.000125 grad: 0.1463 (0.1710) loss: 0.9031 (0.9180) time: 0.1980 data: 0.1036 max mem: 9390 +Train: [5] [3600/6250] eta: 0:06:52 lr: 0.000125 grad: 0.1284 (0.1705) loss: 0.9093 (0.9177) time: 0.1496 data: 0.0656 max mem: 9390 +Train: [5] [3700/6250] eta: 0:06:38 lr: 0.000125 grad: 0.1292 (0.1701) loss: 0.9015 (0.9173) time: 0.1688 data: 0.0872 max mem: 9390 +Train: [5] [3800/6250] eta: 0:06:23 lr: 0.000125 grad: 0.1711 (0.1699) loss: 0.9007 (0.9170) time: 0.1717 data: 0.0910 max mem: 9390 +Train: [5] [3900/6250] eta: 0:06:07 lr: 0.000125 grad: 0.1229 (0.1697) loss: 0.9024 (0.9166) time: 0.1699 data: 0.0897 max mem: 9390 +Train: [5] [4000/6250] eta: 0:05:51 lr: 0.000125 grad: 0.1418 (0.1697) loss: 0.8978 (0.9162) time: 0.1517 data: 0.0702 max mem: 9390 +Train: [5] [4100/6250] eta: 0:05:37 lr: 0.000125 grad: 0.1315 (0.1694) loss: 0.9021 (0.9158) time: 0.1312 data: 0.0480 max mem: 9390 +Train: [5] [4200/6250] eta: 0:05:22 lr: 0.000125 grad: 0.1432 (0.1689) loss: 0.9001 (0.9155) time: 0.1821 data: 0.0925 max mem: 9390 +Train: [5] [4300/6250] eta: 0:05:07 lr: 0.000125 grad: 0.1343 (0.1684) loss: 0.8982 (0.9151) time: 0.1336 data: 0.0351 max mem: 9390 +Train: [5] [4400/6250] eta: 0:04:53 lr: 0.000125 grad: 0.1383 (0.1678) loss: 0.8991 (0.9148) time: 0.1589 data: 0.0606 max mem: 9390 +Train: [5] [4500/6250] eta: 0:04:38 lr: 0.000125 grad: 0.1326 (0.1675) loss: 0.8986 (0.9144) time: 0.2072 data: 0.1121 max mem: 9390 +Train: [5] [4600/6250] eta: 0:04:23 lr: 0.000125 grad: 0.1563 (0.1673) loss: 0.8961 (0.9140) time: 0.1907 data: 0.0887 max mem: 9390 +Train: [5] [4700/6250] eta: 0:04:09 lr: 0.000125 grad: 0.1319 (0.1671) loss: 0.8965 (0.9137) time: 0.1123 data: 0.0002 max mem: 9390 +Train: [5] [4800/6250] eta: 0:03:53 lr: 0.000125 grad: 0.1505 (0.1668) loss: 0.8936 (0.9133) time: 0.1577 data: 0.0756 max mem: 9390 +Train: [5] [4900/6250] eta: 0:03:38 lr: 0.000125 grad: 0.1416 (0.1662) loss: 0.8942 (0.9129) time: 0.1905 data: 0.0887 max mem: 9390 +Train: [5] [5000/6250] eta: 0:03:22 lr: 0.000125 grad: 0.1444 (0.1657) loss: 0.8954 (0.9125) time: 0.2313 data: 0.1488 max mem: 9390 +Train: [5] [5100/6250] eta: 0:03:06 lr: 0.000125 grad: 0.1240 (0.1653) loss: 0.8915 (0.9122) time: 0.2678 data: 0.1443 max mem: 9390 +Train: [5] [5200/6250] eta: 0:02:50 lr: 0.000125 grad: 0.1258 (0.1648) loss: 0.8925 (0.9118) time: 0.1246 data: 0.0256 max mem: 9390 +Train: [5] [5300/6250] eta: 0:02:34 lr: 0.000125 grad: 0.1222 (0.1644) loss: 0.8951 (0.9115) time: 0.0970 data: 0.0160 max mem: 9390 +Train: [5] [5400/6250] eta: 0:02:18 lr: 0.000125 grad: 0.1280 (0.1639) loss: 0.8900 (0.9111) time: 0.2145 data: 0.1348 max mem: 9390 +Train: [5] [5500/6250] eta: 0:02:01 lr: 0.000125 grad: 0.1431 (0.1634) loss: 0.8907 (0.9108) time: 0.1200 data: 0.0283 max mem: 9390 +Train: [5] [5600/6250] eta: 0:01:45 lr: 0.000125 grad: 0.1354 (0.1629) loss: 0.8882 (0.9104) time: 0.1598 data: 0.0759 max mem: 9390 +Train: [5] [5700/6250] eta: 0:01:29 lr: 0.000125 grad: 0.1353 (0.1625) loss: 0.8882 (0.9100) time: 0.1553 data: 0.0746 max mem: 9390 +Train: [5] [5800/6250] eta: 0:01:13 lr: 0.000125 grad: 0.1283 (0.1620) loss: 0.8892 (0.9097) time: 0.1283 data: 0.0444 max mem: 9390 +Train: [5] [5900/6250] eta: 0:00:56 lr: 0.000125 grad: 0.1187 (0.1617) loss: 0.8887 (0.9094) time: 0.1329 data: 0.0442 max mem: 9390 +Train: [5] [6000/6250] eta: 0:00:40 lr: 0.000125 grad: 0.1173 (0.1614) loss: 0.8886 (0.9090) time: 0.1756 data: 0.0982 max mem: 9390 +Train: [5] [6100/6250] eta: 0:00:24 lr: 0.000125 grad: 0.1165 (0.1607) loss: 0.8880 (0.9087) time: 0.2068 data: 0.1242 max mem: 9390 +Train: [5] [6200/6250] eta: 0:00:08 lr: 0.000125 grad: 0.1152 (0.1602) loss: 0.8908 (0.9084) time: 0.1539 data: 0.0708 max mem: 9390 +Train: [5] [6249/6250] eta: 0:00:00 lr: 0.000125 grad: 0.1336 (0.1601) loss: 0.8886 (0.9082) time: 0.1549 data: 0.0748 max mem: 9390 +Train: [5] Total time: 0:17:04 (0.1639 s / it) +Averaged stats: lr: 0.000125 grad: 0.1336 (0.1601) loss: 0.8886 (0.9082) +Eval (hcp-train-subset): [5] [ 0/62] eta: 0:03:54 loss: 0.8992 (0.8992) time: 3.7745 data: 3.6938 max mem: 9390 +Eval (hcp-train-subset): [5] [61/62] eta: 0:00:00 loss: 0.8907 (0.8885) time: 0.1330 data: 0.1080 max mem: 9390 +Eval (hcp-train-subset): [5] Total time: 0:00:13 (0.2185 s / it) +Averaged stats (hcp-train-subset): loss: 0.8907 (0.8885) +Eval (hcp-val): [5] [ 0/62] eta: 0:03:06 loss: 0.8812 (0.8812) time: 3.0090 data: 2.9284 max mem: 9390 +Eval (hcp-val): [5] [61/62] eta: 0:00:00 loss: 0.8829 (0.8828) time: 0.1370 data: 0.1116 max mem: 9390 +Eval (hcp-val): [5] Total time: 0:00:13 (0.2112 s / it) +Averaged stats (hcp-val): loss: 0.8829 (0.8828) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +Train: [6] [ 0/6250] eta: 10:04:12 lr: 0.000125 grad: 0.0997 (0.0997) loss: 0.9056 (0.9056) time: 5.8004 data: 5.6275 max mem: 9390 +Train: [6] [ 100/6250] eta: 0:22:00 lr: 0.000125 grad: 0.1356 (0.1432) loss: 0.8937 (0.8950) time: 0.1448 data: 0.0588 max mem: 9390 +Train: [6] [ 200/6250] eta: 0:18:56 lr: 0.000125 grad: 0.1262 (0.1452) loss: 0.8871 (0.8913) time: 0.1367 data: 0.0480 max mem: 9390 +Train: [6] [ 300/6250] eta: 0:17:33 lr: 0.000125 grad: 0.1388 (0.1438) loss: 0.8886 (0.8893) time: 0.1547 data: 0.0655 max mem: 9390 +Train: [6] [ 400/6250] eta: 0:16:31 lr: 0.000125 grad: 0.1418 (0.1439) loss: 0.8791 (0.8886) time: 0.1384 data: 0.0364 max mem: 9390 +Train: [6] [ 500/6250] eta: 0:15:55 lr: 0.000125 grad: 0.1375 (0.1436) loss: 0.8797 (0.8872) time: 0.1549 data: 0.0704 max mem: 9390 +Train: [6] [ 600/6250] eta: 0:15:30 lr: 0.000125 grad: 0.1241 (0.1424) loss: 0.8796 (0.8860) time: 0.1685 data: 0.0923 max mem: 9390 +Train: [6] [ 700/6250] eta: 0:15:13 lr: 0.000125 grad: 0.1142 (0.1397) loss: 0.8811 (0.8851) time: 0.1617 data: 0.0721 max mem: 9390 +Train: [6] [ 800/6250] eta: 0:15:08 lr: 0.000125 grad: 0.1180 (0.1373) loss: 0.8801 (0.8847) time: 0.1711 data: 0.0801 max mem: 9390 +Train: [6] [ 900/6250] eta: 0:14:59 lr: 0.000125 grad: 0.1148 (0.1357) loss: 0.8782 (0.8843) time: 0.1556 data: 0.0610 max mem: 9390 +Train: [6] [1000/6250] eta: 0:14:43 lr: 0.000125 grad: 0.1134 (0.1355) loss: 0.8800 (0.8839) time: 0.1619 data: 0.0755 max mem: 9390 +Train: [6] [1100/6250] eta: 0:14:24 lr: 0.000125 grad: 0.1033 (0.1341) loss: 0.8812 (0.8838) time: 0.1733 data: 0.0880 max mem: 9390 +Train: [6] [1200/6250] eta: 0:14:03 lr: 0.000125 grad: 0.1026 (0.1325) loss: 0.8823 (0.8836) time: 0.1577 data: 0.0739 max mem: 9390 +Train: [6] [1300/6250] eta: 0:13:43 lr: 0.000125 grad: 0.1077 (0.1312) loss: 0.8809 (0.8836) time: 0.1613 data: 0.0813 max mem: 9390 +Train: [6] [1400/6250] eta: 0:13:23 lr: 0.000125 grad: 0.1052 (0.1297) loss: 0.8767 (0.8833) time: 0.1526 data: 0.0595 max mem: 9390 +Train: [6] [1500/6250] eta: 0:13:06 lr: 0.000125 grad: 0.1088 (0.1288) loss: 0.8791 (0.8831) time: 0.1561 data: 0.0782 max mem: 9390 +Train: [6] [1600/6250] eta: 0:12:49 lr: 0.000125 grad: 0.1095 (0.1278) loss: 0.8788 (0.8830) time: 0.1663 data: 0.0889 max mem: 9390 +Train: [6] [1700/6250] eta: 0:12:31 lr: 0.000125 grad: 0.1077 (0.1265) loss: 0.8834 (0.8829) time: 0.1675 data: 0.0761 max mem: 9390 +Train: [6] [1800/6250] eta: 0:12:14 lr: 0.000125 grad: 0.1191 (0.1260) loss: 0.8808 (0.8827) time: 0.1530 data: 0.0666 max mem: 9390 +Train: [6] [1900/6250] eta: 0:11:56 lr: 0.000125 grad: 0.0919 (0.1256) loss: 0.8799 (0.8825) time: 0.1689 data: 0.0854 max mem: 9390 +Train: [6] [2000/6250] eta: 0:11:40 lr: 0.000125 grad: 0.1043 (0.1253) loss: 0.8806 (0.8823) time: 0.1566 data: 0.0688 max mem: 9390 +Train: [6] [2100/6250] eta: 0:11:23 lr: 0.000125 grad: 0.0988 (0.1246) loss: 0.8795 (0.8824) time: 0.1665 data: 0.0914 max mem: 9390 +Train: [6] [2200/6250] eta: 0:11:09 lr: 0.000125 grad: 0.1042 (0.1239) loss: 0.8811 (0.8823) time: 0.1376 data: 0.0445 max mem: 9390 +Train: [6] [2300/6250] eta: 0:10:52 lr: 0.000125 grad: 0.1013 (0.1235) loss: 0.8791 (0.8821) time: 0.2043 data: 0.0958 max mem: 9390 +Train: [6] [2400/6250] eta: 0:10:36 lr: 0.000125 grad: 0.1063 (0.1232) loss: 0.8753 (0.8819) time: 0.1351 data: 0.0520 max mem: 9390 +Train: [6] [2500/6250] eta: 0:10:19 lr: 0.000125 grad: 0.1016 (0.1224) loss: 0.8793 (0.8817) time: 0.1920 data: 0.1073 max mem: 9390 +Train: [6] [2600/6250] eta: 0:10:04 lr: 0.000125 grad: 0.0918 (0.1219) loss: 0.8730 (0.8815) time: 0.1171 data: 0.0382 max mem: 9390 +Train: [6] [2700/6250] eta: 0:09:51 lr: 0.000125 grad: 0.0964 (0.1213) loss: 0.8761 (0.8813) time: 0.3045 data: 0.2196 max mem: 9390 +Train: [6] [2800/6250] eta: 0:09:31 lr: 0.000125 grad: 0.1048 (0.1210) loss: 0.8718 (0.8811) time: 0.1626 data: 0.0837 max mem: 9390 +Train: [6] [2900/6250] eta: 0:09:14 lr: 0.000125 grad: 0.0906 (0.1206) loss: 0.8798 (0.8809) time: 0.1168 data: 0.0260 max mem: 9390 +Train: [6] [3000/6250] eta: 0:09:01 lr: 0.000125 grad: 0.0882 (0.1205) loss: 0.8764 (0.8808) time: 0.2478 data: 0.1586 max mem: 9390 +Train: [6] [3100/6250] eta: 0:08:41 lr: 0.000125 grad: 0.0908 (0.1200) loss: 0.8786 (0.8806) time: 0.1543 data: 0.0566 max mem: 9390 +Train: [6] [3200/6250] eta: 0:08:24 lr: 0.000125 grad: 0.1022 (0.1199) loss: 0.8759 (0.8805) time: 0.1550 data: 0.0697 max mem: 9390 +Train: [6] [3300/6250] eta: 0:08:07 lr: 0.000125 grad: 0.1181 (0.1197) loss: 0.8769 (0.8804) time: 0.1552 data: 0.0716 max mem: 9390 +Train: [6] [3400/6250] eta: 0:07:50 lr: 0.000125 grad: 0.1018 (0.1195) loss: 0.8764 (0.8802) time: 0.1591 data: 0.0741 max mem: 9390 +Train: [6] [3500/6250] eta: 0:07:34 lr: 0.000125 grad: 0.0979 (0.1191) loss: 0.8715 (0.8800) time: 0.1728 data: 0.0913 max mem: 9390 +Train: [6] [3600/6250] eta: 0:07:16 lr: 0.000125 grad: 0.0978 (0.1191) loss: 0.8777 (0.8798) time: 0.1510 data: 0.0621 max mem: 9390 +Train: [6] [3700/6250] eta: 0:06:59 lr: 0.000125 grad: 0.1007 (0.1186) loss: 0.8730 (0.8795) time: 0.1539 data: 0.0703 max mem: 9390 +Train: [6] [3800/6250] eta: 0:06:42 lr: 0.000125 grad: 0.1036 (0.1182) loss: 0.8683 (0.8794) time: 0.1808 data: 0.0996 max mem: 9390 +Train: [6] [3900/6250] eta: 0:06:25 lr: 0.000125 grad: 0.0971 (0.1179) loss: 0.8702 (0.8792) time: 0.1457 data: 0.0686 max mem: 9390 +Train: [6] [4000/6250] eta: 0:06:08 lr: 0.000125 grad: 0.1016 (0.1180) loss: 0.8668 (0.8789) time: 0.1520 data: 0.0662 max mem: 9390 +Train: [6] [4100/6250] eta: 0:05:52 lr: 0.000125 grad: 0.0924 (0.1176) loss: 0.8696 (0.8788) time: 0.1743 data: 0.0979 max mem: 9390 +Train: [6] [4200/6250] eta: 0:05:35 lr: 0.000125 grad: 0.0994 (0.1172) loss: 0.8674 (0.8786) time: 0.1615 data: 0.0789 max mem: 9390 +Train: [6] [4300/6250] eta: 0:05:19 lr: 0.000125 grad: 0.0906 (0.1167) loss: 0.8712 (0.8784) time: 0.1628 data: 0.0814 max mem: 9390 +Train: [6] [4400/6250] eta: 0:05:03 lr: 0.000125 grad: 0.1027 (0.1166) loss: 0.8720 (0.8782) time: 0.2010 data: 0.1137 max mem: 9390 +Train: [6] [4500/6250] eta: 0:04:47 lr: 0.000125 grad: 0.0905 (0.1162) loss: 0.8679 (0.8780) time: 0.1865 data: 0.1037 max mem: 9390 +Train: [6] [4600/6250] eta: 0:04:30 lr: 0.000125 grad: 0.0989 (0.1159) loss: 0.8716 (0.8779) time: 0.1511 data: 0.0681 max mem: 9390 +Train: [6] [4700/6250] eta: 0:04:14 lr: 0.000125 grad: 0.1010 (0.1158) loss: 0.8666 (0.8777) time: 0.1616 data: 0.0710 max mem: 9390 +Train: [6] [4800/6250] eta: 0:03:57 lr: 0.000125 grad: 0.0902 (0.1155) loss: 0.8705 (0.8776) time: 0.1489 data: 0.0551 max mem: 9390 +Train: [6] [4900/6250] eta: 0:03:40 lr: 0.000125 grad: 0.1040 (0.1154) loss: 0.8715 (0.8774) time: 0.1841 data: 0.0989 max mem: 9390 +Train: [6] [5000/6250] eta: 0:03:23 lr: 0.000125 grad: 0.0948 (0.1150) loss: 0.8754 (0.8773) time: 0.1479 data: 0.0700 max mem: 9390 +Train: [6] [5100/6250] eta: 0:03:07 lr: 0.000125 grad: 0.0878 (0.1146) loss: 0.8700 (0.8772) time: 0.1472 data: 0.0655 max mem: 9390 +Train: [6] [5200/6250] eta: 0:02:50 lr: 0.000125 grad: 0.0890 (0.1145) loss: 0.8711 (0.8770) time: 0.1674 data: 0.0880 max mem: 9390 +Train: [6] [5300/6250] eta: 0:02:34 lr: 0.000125 grad: 0.1023 (0.1142) loss: 0.8721 (0.8769) time: 0.1922 data: 0.1131 max mem: 9390 +Train: [6] [5400/6250] eta: 0:02:18 lr: 0.000125 grad: 0.0885 (0.1142) loss: 0.8700 (0.8768) time: 0.1383 data: 0.0514 max mem: 9390 +Train: [6] [5500/6250] eta: 0:02:01 lr: 0.000125 grad: 0.0894 (0.1138) loss: 0.8711 (0.8767) time: 0.1635 data: 0.0743 max mem: 9390 +Train: [6] [5600/6250] eta: 0:01:45 lr: 0.000125 grad: 0.0887 (0.1136) loss: 0.8730 (0.8766) time: 0.1319 data: 0.0460 max mem: 9390 +Train: [6] [5700/6250] eta: 0:01:29 lr: 0.000125 grad: 0.0915 (0.1133) loss: 0.8727 (0.8765) time: 0.1328 data: 0.0535 max mem: 9390 +Train: [6] [5800/6250] eta: 0:01:13 lr: 0.000125 grad: 0.0911 (0.1129) loss: 0.8699 (0.8764) time: 0.1926 data: 0.1046 max mem: 9390 +Train: [6] [5900/6250] eta: 0:00:56 lr: 0.000125 grad: 0.0931 (0.1126) loss: 0.8648 (0.8763) time: 0.1685 data: 0.0881 max mem: 9390 +Train: [6] [6000/6250] eta: 0:00:40 lr: 0.000125 grad: 0.0855 (0.1124) loss: 0.8703 (0.8762) time: 0.1600 data: 0.0835 max mem: 9390 +Train: [6] [6100/6250] eta: 0:00:24 lr: 0.000125 grad: 0.0895 (0.1121) loss: 0.8688 (0.8761) time: 0.1716 data: 0.0891 max mem: 9390 +Train: [6] [6200/6250] eta: 0:00:08 lr: 0.000125 grad: 0.0880 (0.1119) loss: 0.8721 (0.8760) time: 0.1556 data: 0.0722 max mem: 9390 +Train: [6] [6249/6250] eta: 0:00:00 lr: 0.000125 grad: 0.0929 (0.1117) loss: 0.8671 (0.8760) time: 0.1452 data: 0.0639 max mem: 9390 +Train: [6] Total time: 0:16:57 (0.1629 s / it) +Averaged stats: lr: 0.000125 grad: 0.0929 (0.1117) loss: 0.8671 (0.8760) +Eval (hcp-train-subset): [6] [ 0/62] eta: 0:04:43 loss: 0.8787 (0.8787) time: 4.5789 data: 4.5487 max mem: 9390 +Eval (hcp-train-subset): [6] [61/62] eta: 0:00:00 loss: 0.8697 (0.8709) time: 0.1373 data: 0.1102 max mem: 9390 +Eval (hcp-train-subset): [6] Total time: 0:00:13 (0.2184 s / it) +Averaged stats (hcp-train-subset): loss: 0.8697 (0.8709) +Eval (hcp-val): [6] [ 0/62] eta: 0:03:45 loss: 0.8552 (0.8552) time: 3.6321 data: 3.5584 max mem: 9390 +Eval (hcp-val): [6] [61/62] eta: 0:00:00 loss: 0.8650 (0.8647) time: 0.1182 data: 0.0915 max mem: 9390 +Eval (hcp-val): [6] Total time: 0:00:12 (0.2074 s / it) +Averaged stats (hcp-val): loss: 0.8650 (0.8647) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +Train: [7] [ 0/6250] eta: 9:40:26 lr: 0.000125 grad: 0.1095 (0.1095) loss: 0.8772 (0.8772) time: 5.5723 data: 5.4571 max mem: 9390 +Train: [7] [ 100/6250] eta: 0:21:24 lr: 0.000125 grad: 0.0960 (0.0980) loss: 0.8624 (0.8714) time: 0.1691 data: 0.0781 max mem: 9390 +Train: [7] [ 200/6250] eta: 0:18:26 lr: 0.000125 grad: 0.0914 (0.1038) loss: 0.8610 (0.8655) time: 0.1369 data: 0.0375 max mem: 9390 +Train: [7] [ 300/6250] eta: 0:17:05 lr: 0.000125 grad: 0.0870 (0.1015) loss: 0.8554 (0.8638) time: 0.1406 data: 0.0566 max mem: 9390 +Train: [7] [ 400/6250] eta: 0:15:58 lr: 0.000125 grad: 0.0816 (0.1003) loss: 0.8638 (0.8635) time: 0.1311 data: 0.0409 max mem: 9390 +Train: [7] [ 500/6250] eta: 0:15:11 lr: 0.000125 grad: 0.0863 (0.1004) loss: 0.8597 (0.8635) time: 0.1420 data: 0.0493 max mem: 9390 +Train: [7] [ 600/6250] eta: 0:15:02 lr: 0.000125 grad: 0.0882 (0.0993) loss: 0.8626 (0.8634) time: 0.1975 data: 0.1120 max mem: 9390 +Train: [7] [ 700/6250] eta: 0:15:56 lr: 0.000125 grad: 0.0919 (0.0987) loss: 0.8634 (0.8632) time: 0.1287 data: 0.0003 max mem: 9390 +Train: [7] [ 800/6250] eta: 0:16:13 lr: 0.000125 grad: 0.0913 (0.0996) loss: 0.8700 (0.8634) time: 0.1372 data: 0.0325 max mem: 9390 +Train: [7] [ 900/6250] eta: 0:16:03 lr: 0.000125 grad: 0.0923 (0.0995) loss: 0.8626 (0.8633) time: 0.1056 data: 0.0002 max mem: 9390 +Train: [7] [1000/6250] eta: 0:15:56 lr: 0.000125 grad: 0.0894 (0.0989) loss: 0.8570 (0.8631) time: 0.1712 data: 0.0848 max mem: 9390 +Train: [7] [1100/6250] eta: 0:15:30 lr: 0.000125 grad: 0.0967 (0.0986) loss: 0.8660 (0.8632) time: 0.1189 data: 0.0341 max mem: 9390 +Train: [7] [1200/6250] eta: 0:15:01 lr: 0.000125 grad: 0.0886 (0.0983) loss: 0.8644 (0.8632) time: 0.1712 data: 0.0917 max mem: 9390 +Train: [7] [1300/6250] eta: 0:14:37 lr: 0.000125 grad: 0.0890 (0.0980) loss: 0.8663 (0.8633) time: 0.1691 data: 0.0863 max mem: 9390 +Train: [7] [1400/6250] eta: 0:14:18 lr: 0.000125 grad: 0.0916 (0.0976) loss: 0.8682 (0.8634) time: 0.1788 data: 0.0914 max mem: 9390 +Train: [7] [1500/6250] eta: 0:13:58 lr: 0.000125 grad: 0.0905 (0.0975) loss: 0.8631 (0.8636) time: 0.2237 data: 0.0965 max mem: 9390 +Train: [7] [1600/6250] eta: 0:13:45 lr: 0.000125 grad: 0.0848 (0.0974) loss: 0.8599 (0.8636) time: 0.2443 data: 0.1373 max mem: 9390 +Train: [7] [1700/6250] eta: 0:13:25 lr: 0.000125 grad: 0.0851 (0.0970) loss: 0.8666 (0.8638) time: 0.1692 data: 0.0919 max mem: 9390 +Train: [7] [1800/6250] eta: 0:13:05 lr: 0.000125 grad: 0.1007 (0.0969) loss: 0.8663 (0.8639) time: 0.1325 data: 0.0381 max mem: 9390 +Train: [7] [1900/6250] eta: 0:12:44 lr: 0.000125 grad: 0.0829 (0.0963) loss: 0.8675 (0.8640) time: 0.1718 data: 0.0758 max mem: 9390 +Train: [7] [2000/6250] eta: 0:12:26 lr: 0.000125 grad: 0.0920 (0.0965) loss: 0.8680 (0.8641) time: 0.1097 data: 0.0267 max mem: 9390 +Train: [7] [2100/6250] eta: 0:12:09 lr: 0.000125 grad: 0.0944 (0.0961) loss: 0.8644 (0.8641) time: 0.2109 data: 0.1245 max mem: 9390 +Train: [7] [2200/6250] eta: 0:11:54 lr: 0.000125 grad: 0.0967 (0.0958) loss: 0.8662 (0.8641) time: 0.2603 data: 0.1760 max mem: 9390 +Train: [7] [2300/6250] eta: 0:11:31 lr: 0.000125 grad: 0.0916 (0.0959) loss: 0.8663 (0.8641) time: 0.1766 data: 0.0860 max mem: 9390 +Train: [7] [2400/6250] eta: 0:11:22 lr: 0.000125 grad: 0.0856 (0.0956) loss: 0.8651 (0.8641) time: 0.2986 data: 0.2013 max mem: 9390 +Train: [7] [2500/6250] eta: 0:11:03 lr: 0.000125 grad: 0.0817 (0.0952) loss: 0.8637 (0.8641) time: 0.1807 data: 0.1030 max mem: 9390 +Train: [7] [2600/6250] eta: 0:10:43 lr: 0.000125 grad: 0.0820 (0.0949) loss: 0.8620 (0.8641) time: 0.1644 data: 0.0778 max mem: 9390 +Train: [7] [2700/6250] eta: 0:10:24 lr: 0.000125 grad: 0.0805 (0.0947) loss: 0.8631 (0.8641) time: 0.1488 data: 0.0649 max mem: 9390 +Train: [7] [2800/6250] eta: 0:10:11 lr: 0.000125 grad: 0.0828 (0.0945) loss: 0.8672 (0.8642) time: 0.2383 data: 0.1373 max mem: 9390 +Train: [7] [2900/6250] eta: 0:09:51 lr: 0.000125 grad: 0.0934 (0.0943) loss: 0.8608 (0.8642) time: 0.1864 data: 0.0904 max mem: 9390 +Train: [7] [3000/6250] eta: 0:09:39 lr: 0.000125 grad: 0.0796 (0.0940) loss: 0.8673 (0.8642) time: 0.0967 data: 0.0002 max mem: 9390 +Train: [7] [3100/6250] eta: 0:09:19 lr: 0.000125 grad: 0.0834 (0.0938) loss: 0.8623 (0.8642) time: 0.1725 data: 0.0851 max mem: 9390 +Train: [7] [3200/6250] eta: 0:09:00 lr: 0.000125 grad: 0.0757 (0.0934) loss: 0.8673 (0.8642) time: 0.1475 data: 0.0681 max mem: 9390 +Train: [7] [3300/6250] eta: 0:08:40 lr: 0.000125 grad: 0.0735 (0.0932) loss: 0.8619 (0.8642) time: 0.1676 data: 0.0843 max mem: 9390 +Train: [7] [3400/6250] eta: 0:08:20 lr: 0.000125 grad: 0.0833 (0.0929) loss: 0.8660 (0.8642) time: 0.1652 data: 0.0864 max mem: 9390 +Train: [7] [3500/6250] eta: 0:08:02 lr: 0.000125 grad: 0.0796 (0.0927) loss: 0.8650 (0.8642) time: 0.1751 data: 0.0892 max mem: 9390 +Train: [7] [3600/6250] eta: 0:07:43 lr: 0.000125 grad: 0.0807 (0.0924) loss: 0.8651 (0.8643) time: 0.1608 data: 0.0706 max mem: 9390 +Train: [7] [3700/6250] eta: 0:07:25 lr: 0.000125 grad: 0.0788 (0.0921) loss: 0.8585 (0.8643) time: 0.2013 data: 0.1167 max mem: 9390 +Train: [7] [3800/6250] eta: 0:07:06 lr: 0.000125 grad: 0.0842 (0.0919) loss: 0.8622 (0.8642) time: 0.1189 data: 0.0408 max mem: 9390 +Train: [7] [3900/6250] eta: 0:06:48 lr: 0.000125 grad: 0.0872 (0.0919) loss: 0.8619 (0.8641) time: 0.1220 data: 0.0378 max mem: 9390 +Train: [7] [4000/6250] eta: 0:06:30 lr: 0.000125 grad: 0.0747 (0.0918) loss: 0.8597 (0.8640) time: 0.2129 data: 0.1356 max mem: 9390 +Train: [7] [4100/6250] eta: 0:06:12 lr: 0.000125 grad: 0.0734 (0.0917) loss: 0.8582 (0.8639) time: 0.1579 data: 0.0634 max mem: 9390 +Train: [7] [4200/6250] eta: 0:05:55 lr: 0.000125 grad: 0.0716 (0.0916) loss: 0.8598 (0.8638) time: 0.1024 data: 0.0003 max mem: 9390 +Train: [7] [4300/6250] eta: 0:05:40 lr: 0.000125 grad: 0.0838 (0.0914) loss: 0.8620 (0.8638) time: 0.3162 data: 0.1966 max mem: 9390 +Train: [7] [4400/6250] eta: 0:05:22 lr: 0.000125 grad: 0.0802 (0.0913) loss: 0.8613 (0.8637) time: 0.1409 data: 0.0573 max mem: 9390 +Train: [7] [4500/6250] eta: 0:05:04 lr: 0.000125 grad: 0.0739 (0.0910) loss: 0.8643 (0.8637) time: 0.1719 data: 0.0854 max mem: 9390 +Train: [7] [4600/6250] eta: 0:04:46 lr: 0.000125 grad: 0.0738 (0.0909) loss: 0.8609 (0.8636) time: 0.1420 data: 0.0597 max mem: 9390 +Train: [7] [4700/6250] eta: 0:04:29 lr: 0.000125 grad: 0.0765 (0.0907) loss: 0.8588 (0.8635) time: 0.1369 data: 0.0577 max mem: 9390 +Train: [7] [4800/6250] eta: 0:04:12 lr: 0.000125 grad: 0.0792 (0.0904) loss: 0.8578 (0.8635) time: 0.1692 data: 0.0836 max mem: 9390 +Train: [7] [4900/6250] eta: 0:03:54 lr: 0.000125 grad: 0.0863 (0.0903) loss: 0.8606 (0.8634) time: 0.1646 data: 0.0722 max mem: 9390 +Train: [7] [5000/6250] eta: 0:03:36 lr: 0.000125 grad: 0.0790 (0.0902) loss: 0.8581 (0.8634) time: 0.1526 data: 0.0684 max mem: 9390 +Train: [7] [5100/6250] eta: 0:03:19 lr: 0.000125 grad: 0.0855 (0.0901) loss: 0.8611 (0.8633) time: 0.1391 data: 0.0572 max mem: 9390 +Train: [7] [5200/6250] eta: 0:03:03 lr: 0.000125 grad: 0.0755 (0.0900) loss: 0.8600 (0.8632) time: 0.2856 data: 0.1919 max mem: 9390 +Train: [7] [5300/6250] eta: 0:02:44 lr: 0.000125 grad: 0.0743 (0.0898) loss: 0.8621 (0.8632) time: 0.1578 data: 0.0735 max mem: 9390 +Train: [7] [5400/6250] eta: 0:02:27 lr: 0.000125 grad: 0.0822 (0.0897) loss: 0.8616 (0.8631) time: 0.1553 data: 0.0696 max mem: 9390 +Train: [7] [5500/6250] eta: 0:02:10 lr: 0.000125 grad: 0.0749 (0.0895) loss: 0.8611 (0.8631) time: 0.1537 data: 0.0696 max mem: 9390 +Train: [7] [5600/6250] eta: 0:01:52 lr: 0.000125 grad: 0.0762 (0.0893) loss: 0.8583 (0.8630) time: 0.1483 data: 0.0626 max mem: 9390 +Train: [7] [5700/6250] eta: 0:01:35 lr: 0.000125 grad: 0.0805 (0.0892) loss: 0.8594 (0.8630) time: 0.1369 data: 0.0119 max mem: 9390 +Train: [7] [5800/6250] eta: 0:01:18 lr: 0.000125 grad: 0.0874 (0.0892) loss: 0.8623 (0.8630) time: 0.1676 data: 0.0734 max mem: 9390 +Train: [7] [5900/6250] eta: 0:01:00 lr: 0.000125 grad: 0.0779 (0.0890) loss: 0.8578 (0.8629) time: 0.1531 data: 0.0715 max mem: 9390 +Train: [7] [6000/6250] eta: 0:00:43 lr: 0.000125 grad: 0.0807 (0.0890) loss: 0.8560 (0.8628) time: 0.1594 data: 0.0779 max mem: 9390 +Train: [7] [6100/6250] eta: 0:00:26 lr: 0.000125 grad: 0.0753 (0.0888) loss: 0.8607 (0.8627) time: 0.2393 data: 0.1595 max mem: 9390 +Train: [7] [6200/6250] eta: 0:00:08 lr: 0.000125 grad: 0.0755 (0.0887) loss: 0.8559 (0.8626) time: 0.2071 data: 0.1117 max mem: 9390 +Train: [7] [6249/6250] eta: 0:00:00 lr: 0.000125 grad: 0.0857 (0.0887) loss: 0.8633 (0.8626) time: 0.2647 data: 0.1875 max mem: 9390 +Train: [7] Total time: 0:18:12 (0.1748 s / it) +Averaged stats: lr: 0.000125 grad: 0.0857 (0.0887) loss: 0.8633 (0.8626) +Eval (hcp-train-subset): [7] [ 0/62] eta: 0:04:11 loss: 0.8754 (0.8754) time: 4.0574 data: 3.9934 max mem: 9390 +Eval (hcp-train-subset): [7] [61/62] eta: 0:00:00 loss: 0.8640 (0.8640) time: 0.1515 data: 0.1234 max mem: 9390 +Eval (hcp-train-subset): [7] Total time: 0:00:14 (0.2416 s / it) +Averaged stats (hcp-train-subset): loss: 0.8640 (0.8640) +Eval (hcp-val): [7] [ 0/62] eta: 0:05:31 loss: 0.8536 (0.8536) time: 5.3487 data: 5.3149 max mem: 9390 +Eval (hcp-val): [7] [61/62] eta: 0:00:00 loss: 0.8580 (0.8580) time: 0.1363 data: 0.1088 max mem: 9390 +Eval (hcp-val): [7] Total time: 0:00:13 (0.2217 s / it) +Averaged stats (hcp-val): loss: 0.8580 (0.8580) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +Train: [8] [ 0/6250] eta: 23:27:20 lr: 0.000125 grad: 0.0877 (0.0877) loss: 0.8718 (0.8718) time: 13.5104 data: 13.3512 max mem: 9390 +Train: [8] [ 100/6250] eta: 0:31:14 lr: 0.000125 grad: 0.0969 (0.0925) loss: 0.8630 (0.8665) time: 0.1684 data: 0.0720 max mem: 9390 +Train: [8] [ 200/6250] eta: 0:23:24 lr: 0.000125 grad: 0.0687 (0.0847) loss: 0.8652 (0.8634) time: 0.1437 data: 0.0436 max mem: 9390 +Train: [8] [ 300/6250] eta: 0:20:31 lr: 0.000125 grad: 0.0841 (0.0862) loss: 0.8517 (0.8607) time: 0.1484 data: 0.0535 max mem: 9390 +Train: [8] [ 400/6250] eta: 0:18:54 lr: 0.000125 grad: 0.0687 (0.0865) loss: 0.8591 (0.8592) time: 0.1741 data: 0.0807 max mem: 9390 +Train: [8] [ 500/6250] eta: 0:17:29 lr: 0.000125 grad: 0.0768 (0.0849) loss: 0.8510 (0.8581) time: 0.1465 data: 0.0497 max mem: 9390 +Train: [8] [ 600/6250] eta: 0:16:53 lr: 0.000125 grad: 0.0821 (0.0853) loss: 0.8609 (0.8577) time: 0.1723 data: 0.0911 max mem: 9390 +Train: [8] [ 700/6250] eta: 0:16:51 lr: 0.000125 grad: 0.0790 (0.0845) loss: 0.8572 (0.8576) time: 0.3011 data: 0.1895 max mem: 9390 +Train: [8] [ 800/6250] eta: 0:16:29 lr: 0.000125 grad: 0.0713 (0.0840) loss: 0.8563 (0.8573) time: 0.1541 data: 0.0623 max mem: 9390 +Train: [8] [ 900/6250] eta: 0:16:33 lr: 0.000125 grad: 0.0761 (0.0836) loss: 0.8579 (0.8572) time: 0.2532 data: 0.1335 max mem: 9390 +Train: [8] [1000/6250] eta: 0:16:45 lr: 0.000125 grad: 0.0719 (0.0839) loss: 0.8567 (0.8572) time: 0.1573 data: 0.0727 max mem: 9390 +Train: [8] [1100/6250] eta: 0:16:31 lr: 0.000125 grad: 0.0752 (0.0840) loss: 0.8540 (0.8572) time: 0.0904 data: 0.0002 max mem: 9390 +Train: [8] [1200/6250] eta: 0:16:21 lr: 0.000125 grad: 0.0733 (0.0838) loss: 0.8603 (0.8573) time: 0.2637 data: 0.1617 max mem: 9390 +Train: [8] [1300/6250] eta: 0:15:50 lr: 0.000125 grad: 0.0739 (0.0837) loss: 0.8591 (0.8574) time: 0.1679 data: 0.0931 max mem: 9390 +Train: [8] [1400/6250] eta: 0:15:23 lr: 0.000125 grad: 0.0768 (0.0835) loss: 0.8587 (0.8573) time: 0.1724 data: 0.0925 max mem: 9390 +Train: [8] [1500/6250] eta: 0:15:00 lr: 0.000125 grad: 0.0769 (0.0831) loss: 0.8593 (0.8574) time: 0.2044 data: 0.1165 max mem: 9390 +Train: [8] [1600/6250] eta: 0:14:33 lr: 0.000125 grad: 0.0833 (0.0827) loss: 0.8567 (0.8573) time: 0.1417 data: 0.0613 max mem: 9390 +Train: [8] [1700/6250] eta: 0:14:12 lr: 0.000125 grad: 0.0725 (0.0826) loss: 0.8598 (0.8573) time: 0.1316 data: 0.0510 max mem: 9390 +Train: [8] [1800/6250] eta: 0:13:46 lr: 0.000125 grad: 0.0763 (0.0823) loss: 0.8547 (0.8573) time: 0.1911 data: 0.0985 max mem: 9390 +Train: [8] [1900/6250] eta: 0:13:23 lr: 0.000125 grad: 0.0761 (0.0822) loss: 0.8573 (0.8573) time: 0.1777 data: 0.0899 max mem: 9390 +Train: [8] [2000/6250] eta: 0:12:59 lr: 0.000125 grad: 0.0723 (0.0821) loss: 0.8535 (0.8573) time: 0.1625 data: 0.0788 max mem: 9390 +Train: [8] [2100/6250] eta: 0:12:35 lr: 0.000125 grad: 0.0691 (0.0820) loss: 0.8560 (0.8573) time: 0.1604 data: 0.0859 max mem: 9390 +Train: [8] [2200/6250] eta: 0:12:15 lr: 0.000125 grad: 0.0781 (0.0817) loss: 0.8562 (0.8573) time: 0.1610 data: 0.0813 max mem: 9390 +Train: [8] [2300/6250] eta: 0:11:54 lr: 0.000125 grad: 0.0672 (0.0819) loss: 0.8611 (0.8573) time: 0.1631 data: 0.0771 max mem: 9390 +Train: [8] [2400/6250] eta: 0:11:35 lr: 0.000125 grad: 0.0794 (0.0818) loss: 0.8554 (0.8573) time: 0.1924 data: 0.1143 max mem: 9390 +Train: [8] [2500/6250] eta: 0:11:14 lr: 0.000125 grad: 0.0760 (0.0819) loss: 0.8566 (0.8573) time: 0.1690 data: 0.0933 max mem: 9390 +Train: [8] [2600/6250] eta: 0:10:54 lr: 0.000125 grad: 0.0761 (0.0818) loss: 0.8601 (0.8574) time: 0.1780 data: 0.0994 max mem: 9390 +Train: [8] [2700/6250] eta: 0:10:33 lr: 0.000125 grad: 0.0763 (0.0821) loss: 0.8602 (0.8575) time: 0.1514 data: 0.0722 max mem: 9390 +Train: [8] [2800/6250] eta: 0:10:14 lr: 0.000125 grad: 0.0750 (0.0819) loss: 0.8599 (0.8575) time: 0.1875 data: 0.1081 max mem: 9390 +Train: [8] [2900/6250] eta: 0:09:56 lr: 0.000125 grad: 0.0801 (0.0818) loss: 0.8595 (0.8576) time: 0.2303 data: 0.1559 max mem: 9390 +Train: [8] [3000/6250] eta: 0:09:35 lr: 0.000125 grad: 0.0726 (0.0816) loss: 0.8567 (0.8576) time: 0.1507 data: 0.0667 max mem: 9390 +Train: [8] [3100/6250] eta: 0:09:15 lr: 0.000125 grad: 0.0824 (0.0818) loss: 0.8560 (0.8576) time: 0.1693 data: 0.0936 max mem: 9390 +Train: [8] [3200/6250] eta: 0:08:57 lr: 0.000125 grad: 0.0725 (0.0817) loss: 0.8553 (0.8576) time: 0.1639 data: 0.0897 max mem: 9390 +Train: [8] [3300/6250] eta: 0:08:37 lr: 0.000125 grad: 0.0806 (0.0816) loss: 0.8572 (0.8575) time: 0.1281 data: 0.0489 max mem: 9390 +Train: [8] [3400/6250] eta: 0:08:18 lr: 0.000125 grad: 0.0738 (0.0815) loss: 0.8575 (0.8575) time: 0.1717 data: 0.0991 max mem: 9390 +Train: [8] [3500/6250] eta: 0:07:59 lr: 0.000125 grad: 0.0747 (0.0815) loss: 0.8570 (0.8574) time: 0.1808 data: 0.0934 max mem: 9390 +Train: [8] [3600/6250] eta: 0:07:40 lr: 0.000125 grad: 0.0750 (0.0814) loss: 0.8550 (0.8575) time: 0.1425 data: 0.0475 max mem: 9390 +Train: [8] [3700/6250] eta: 0:07:21 lr: 0.000125 grad: 0.0757 (0.0813) loss: 0.8567 (0.8574) time: 0.1358 data: 0.0483 max mem: 9390 +Train: [8] [3800/6250] eta: 0:07:02 lr: 0.000125 grad: 0.0712 (0.0812) loss: 0.8572 (0.8574) time: 0.1517 data: 0.0647 max mem: 9390 +Train: [8] [3900/6250] eta: 0:06:43 lr: 0.000125 grad: 0.0748 (0.0814) loss: 0.8563 (0.8574) time: 0.1449 data: 0.0536 max mem: 9390 +Train: [8] [4000/6250] eta: 0:06:25 lr: 0.000125 grad: 0.0807 (0.0813) loss: 0.8561 (0.8574) time: 0.1547 data: 0.0736 max mem: 9390 +Train: [8] [4100/6250] eta: 0:06:06 lr: 0.000125 grad: 0.0851 (0.0813) loss: 0.8538 (0.8574) time: 0.1565 data: 0.0770 max mem: 9390 +Train: [8] [4200/6250] eta: 0:05:47 lr: 0.000125 grad: 0.0702 (0.0812) loss: 0.8550 (0.8573) time: 0.1215 data: 0.0351 max mem: 9390 +Train: [8] [4300/6250] eta: 0:05:29 lr: 0.000125 grad: 0.0744 (0.0811) loss: 0.8612 (0.8573) time: 0.1375 data: 0.0475 max mem: 9390 +Train: [8] [4400/6250] eta: 0:05:11 lr: 0.000125 grad: 0.0775 (0.0811) loss: 0.8598 (0.8573) time: 0.1457 data: 0.0669 max mem: 9390 +Train: [8] [4500/6250] eta: 0:04:53 lr: 0.000125 grad: 0.0729 (0.0809) loss: 0.8577 (0.8573) time: 0.1519 data: 0.0718 max mem: 9390 +Train: [8] [4600/6250] eta: 0:04:36 lr: 0.000125 grad: 0.0794 (0.0809) loss: 0.8569 (0.8572) time: 0.1430 data: 0.0591 max mem: 9390 +Train: [8] [4700/6250] eta: 0:04:18 lr: 0.000125 grad: 0.0764 (0.0809) loss: 0.8581 (0.8572) time: 0.1356 data: 0.0577 max mem: 9390 +Train: [8] [4800/6250] eta: 0:04:01 lr: 0.000125 grad: 0.0767 (0.0808) loss: 0.8572 (0.8572) time: 0.1300 data: 0.0484 max mem: 9390 +Train: [8] [4900/6250] eta: 0:03:44 lr: 0.000125 grad: 0.0734 (0.0808) loss: 0.8554 (0.8572) time: 0.1329 data: 0.0432 max mem: 9390 +Train: [8] [5000/6250] eta: 0:03:26 lr: 0.000125 grad: 0.0727 (0.0807) loss: 0.8548 (0.8571) time: 0.1445 data: 0.0591 max mem: 9390 +Train: [8] [5100/6250] eta: 0:03:09 lr: 0.000125 grad: 0.0745 (0.0807) loss: 0.8569 (0.8571) time: 0.1476 data: 0.0622 max mem: 9390 +Train: [8] [5200/6250] eta: 0:02:52 lr: 0.000124 grad: 0.0707 (0.0807) loss: 0.8567 (0.8570) time: 0.1441 data: 0.0668 max mem: 9390 +Train: [8] [5300/6250] eta: 0:02:35 lr: 0.000124 grad: 0.0720 (0.0808) loss: 0.8562 (0.8570) time: 0.1228 data: 0.0398 max mem: 9390 +Train: [8] [5400/6250] eta: 0:02:19 lr: 0.000124 grad: 0.0762 (0.0806) loss: 0.8529 (0.8569) time: 0.1228 data: 0.0407 max mem: 9390 +Train: [8] [5500/6250] eta: 0:02:02 lr: 0.000124 grad: 0.0728 (0.0805) loss: 0.8514 (0.8568) time: 0.1443 data: 0.0608 max mem: 9390 +Train: [8] [5600/6250] eta: 0:01:45 lr: 0.000124 grad: 0.0737 (0.0806) loss: 0.8533 (0.8568) time: 0.1316 data: 0.0539 max mem: 9390 +Train: [8] [5700/6250] eta: 0:01:29 lr: 0.000124 grad: 0.0882 (0.0806) loss: 0.8564 (0.8567) time: 0.1411 data: 0.0600 max mem: 9390 +Train: [8] [5800/6250] eta: 0:01:12 lr: 0.000124 grad: 0.0674 (0.0807) loss: 0.8528 (0.8567) time: 0.1557 data: 0.0773 max mem: 9390 +Train: [8] [5900/6250] eta: 0:00:56 lr: 0.000124 grad: 0.0693 (0.0805) loss: 0.8489 (0.8567) time: 0.1544 data: 0.0718 max mem: 9390 +Train: [8] [6000/6250] eta: 0:00:40 lr: 0.000124 grad: 0.0690 (0.0804) loss: 0.8559 (0.8566) time: 0.1645 data: 0.0845 max mem: 9390 +Train: [8] [6100/6250] eta: 0:00:24 lr: 0.000124 grad: 0.0691 (0.0803) loss: 0.8542 (0.8566) time: 0.1244 data: 0.0455 max mem: 9390 +Train: [8] [6200/6250] eta: 0:00:08 lr: 0.000124 grad: 0.0687 (0.0802) loss: 0.8542 (0.8566) time: 0.1416 data: 0.0603 max mem: 9390 +Train: [8] [6249/6250] eta: 0:00:00 lr: 0.000124 grad: 0.0677 (0.0801) loss: 0.8584 (0.8566) time: 0.1950 data: 0.1184 max mem: 9390 +Train: [8] Total time: 0:16:53 (0.1621 s / it) +Averaged stats: lr: 0.000124 grad: 0.0677 (0.0801) loss: 0.8584 (0.8566) +Eval (hcp-train-subset): [8] [ 0/62] eta: 0:03:09 loss: 0.8686 (0.8686) time: 3.0528 data: 2.9717 max mem: 9390 +Eval (hcp-train-subset): [8] [61/62] eta: 0:00:00 loss: 0.8586 (0.8592) time: 0.1320 data: 0.1069 max mem: 9390 +Eval (hcp-train-subset): [8] Total time: 0:00:12 (0.2052 s / it) +Averaged stats (hcp-train-subset): loss: 0.8586 (0.8592) +Eval (hcp-val): [8] [ 0/62] eta: 0:03:07 loss: 0.8516 (0.8516) time: 3.0206 data: 2.9548 max mem: 9390 +Eval (hcp-val): [8] [61/62] eta: 0:00:00 loss: 0.8516 (0.8534) time: 0.1150 data: 0.0899 max mem: 9390 +Eval (hcp-val): [8] Total time: 0:00:12 (0.1977 s / it) +Averaged stats (hcp-val): loss: 0.8516 (0.8534) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +Train: [9] [ 0/6250] eta: 9:38:12 lr: 0.000124 grad: 0.0755 (0.0755) loss: 0.8851 (0.8851) time: 5.5508 data: 5.4445 max mem: 9390 +Train: [9] [ 100/6250] eta: 0:19:44 lr: 0.000124 grad: 0.0755 (0.1112) loss: 0.8568 (0.8579) time: 0.1445 data: 0.0572 max mem: 9390 +Train: [9] [ 200/6250] eta: 0:17:27 lr: 0.000124 grad: 0.0878 (0.0979) loss: 0.8493 (0.8544) time: 0.1513 data: 0.0553 max mem: 9390 +Train: [9] [ 300/6250] eta: 0:16:09 lr: 0.000124 grad: 0.0726 (0.0917) loss: 0.8534 (0.8542) time: 0.1301 data: 0.0440 max mem: 9390 +Train: [9] [ 400/6250] eta: 0:15:26 lr: 0.000124 grad: 0.0704 (0.0876) loss: 0.8490 (0.8542) time: 0.1559 data: 0.0683 max mem: 9390 +Train: [9] [ 500/6250] eta: 0:14:53 lr: 0.000124 grad: 0.0755 (0.0862) loss: 0.8575 (0.8546) time: 0.1508 data: 0.0585 max mem: 9390 +Train: [9] [ 600/6250] eta: 0:14:37 lr: 0.000124 grad: 0.1003 (0.0863) loss: 0.8532 (0.8543) time: 0.1508 data: 0.0621 max mem: 9390 +Train: [9] [ 700/6250] eta: 0:14:20 lr: 0.000124 grad: 0.0711 (0.0854) loss: 0.8516 (0.8537) time: 0.1521 data: 0.0506 max mem: 9390 +Train: [9] [ 800/6250] eta: 0:14:09 lr: 0.000124 grad: 0.0707 (0.0842) loss: 0.8542 (0.8532) time: 0.1249 data: 0.0143 max mem: 9390 +Train: [9] [ 900/6250] eta: 0:13:56 lr: 0.000124 grad: 0.0730 (0.0833) loss: 0.8523 (0.8531) time: 0.1648 data: 0.0769 max mem: 9390 +Train: [9] [1000/6250] eta: 0:13:35 lr: 0.000124 grad: 0.0655 (0.0825) loss: 0.8586 (0.8531) time: 0.1391 data: 0.0537 max mem: 9390 +Train: [9] [1100/6250] eta: 0:13:11 lr: 0.000124 grad: 0.0738 (0.0818) loss: 0.8525 (0.8530) time: 0.1188 data: 0.0255 max mem: 9390 +Train: [9] [1200/6250] eta: 0:12:57 lr: 0.000124 grad: 0.0711 (0.0809) loss: 0.8536 (0.8529) time: 0.1751 data: 0.0832 max mem: 9390 +Train: [9] [1300/6250] eta: 0:12:38 lr: 0.000124 grad: 0.0736 (0.0807) loss: 0.8525 (0.8528) time: 0.1403 data: 0.0535 max mem: 9390 +Train: [9] [1400/6250] eta: 0:12:21 lr: 0.000124 grad: 0.0750 (0.0803) loss: 0.8579 (0.8529) time: 0.1624 data: 0.0798 max mem: 9390 +Train: [9] [1500/6250] eta: 0:12:05 lr: 0.000124 grad: 0.0740 (0.0800) loss: 0.8504 (0.8529) time: 0.1354 data: 0.0492 max mem: 9390 +Train: [9] [1600/6250] eta: 0:11:50 lr: 0.000124 grad: 0.0688 (0.0795) loss: 0.8509 (0.8529) time: 0.1522 data: 0.0763 max mem: 9390 +Train: [9] [1700/6250] eta: 0:11:35 lr: 0.000124 grad: 0.0731 (0.0792) loss: 0.8530 (0.8529) time: 0.1619 data: 0.0825 max mem: 9390 +Train: [9] [1800/6250] eta: 0:11:21 lr: 0.000124 grad: 0.0669 (0.0788) loss: 0.8525 (0.8528) time: 0.1691 data: 0.0829 max mem: 9390 +Train: [9] [1900/6250] eta: 0:11:07 lr: 0.000124 grad: 0.0680 (0.0785) loss: 0.8507 (0.8527) time: 0.1235 data: 0.0423 max mem: 9390 +Train: [9] [2000/6250] eta: 0:10:52 lr: 0.000124 grad: 0.0677 (0.0783) loss: 0.8516 (0.8526) time: 0.1340 data: 0.0414 max mem: 9390 +Train: [9] [2100/6250] eta: 0:10:41 lr: 0.000124 grad: 0.0756 (0.0781) loss: 0.8510 (0.8525) time: 0.1549 data: 0.0719 max mem: 9390 +Train: [9] [2200/6250] eta: 0:10:24 lr: 0.000124 grad: 0.0678 (0.0782) loss: 0.8511 (0.8524) time: 0.1523 data: 0.0662 max mem: 9390 +Train: [9] [2300/6250] eta: 0:10:07 lr: 0.000124 grad: 0.0622 (0.0779) loss: 0.8537 (0.8524) time: 0.1303 data: 0.0513 max mem: 9390 +Train: [9] [2400/6250] eta: 0:09:55 lr: 0.000124 grad: 0.0663 (0.0778) loss: 0.8486 (0.8523) time: 0.2254 data: 0.1470 max mem: 9390 +Train: [9] [2500/6250] eta: 0:09:40 lr: 0.000124 grad: 0.0697 (0.0777) loss: 0.8502 (0.8523) time: 0.1708 data: 0.0899 max mem: 9390 +Train: [9] [2600/6250] eta: 0:09:25 lr: 0.000124 grad: 0.0727 (0.0777) loss: 0.8521 (0.8522) time: 0.1583 data: 0.0708 max mem: 9390 +Train: [9] [2700/6250] eta: 0:09:11 lr: 0.000124 grad: 0.0659 (0.0774) loss: 0.8521 (0.8522) time: 0.1454 data: 0.0589 max mem: 9390 +Train: [9] [2800/6250] eta: 0:08:55 lr: 0.000124 grad: 0.0751 (0.0774) loss: 0.8537 (0.8522) time: 0.1428 data: 0.0565 max mem: 9390 +Train: [9] [2900/6250] eta: 0:08:40 lr: 0.000124 grad: 0.0694 (0.0772) loss: 0.8507 (0.8522) time: 0.1142 data: 0.0324 max mem: 9390 +Train: [9] [3000/6250] eta: 0:08:24 lr: 0.000124 grad: 0.0788 (0.0773) loss: 0.8522 (0.8522) time: 0.1304 data: 0.0328 max mem: 9390 +Train: [9] [3100/6250] eta: 0:08:08 lr: 0.000124 grad: 0.0740 (0.0771) loss: 0.8522 (0.8522) time: 0.1632 data: 0.0828 max mem: 9390 +Train: [9] [3200/6250] eta: 0:07:53 lr: 0.000124 grad: 0.0686 (0.0768) loss: 0.8550 (0.8522) time: 0.1378 data: 0.0537 max mem: 9390 +Train: [9] [3300/6250] eta: 0:07:37 lr: 0.000124 grad: 0.0700 (0.0767) loss: 0.8532 (0.8522) time: 0.1354 data: 0.0517 max mem: 9390 +Train: [9] [3400/6250] eta: 0:07:20 lr: 0.000124 grad: 0.0723 (0.0767) loss: 0.8572 (0.8522) time: 0.1596 data: 0.0730 max mem: 9390 +Train: [9] [3500/6250] eta: 0:07:05 lr: 0.000124 grad: 0.0689 (0.0766) loss: 0.8514 (0.8522) time: 0.1362 data: 0.0540 max mem: 9390 +Train: [9] [3600/6250] eta: 0:06:49 lr: 0.000124 grad: 0.0638 (0.0767) loss: 0.8517 (0.8523) time: 0.1582 data: 0.0772 max mem: 9390 +Train: [9] [3700/6250] eta: 0:06:34 lr: 0.000124 grad: 0.0721 (0.0766) loss: 0.8487 (0.8523) time: 0.1597 data: 0.0836 max mem: 9390 +Train: [9] [3800/6250] eta: 0:06:18 lr: 0.000124 grad: 0.0665 (0.0765) loss: 0.8529 (0.8523) time: 0.1419 data: 0.0584 max mem: 9390 +Train: [9] [3900/6250] eta: 0:06:03 lr: 0.000124 grad: 0.0663 (0.0763) loss: 0.8508 (0.8523) time: 0.1604 data: 0.0754 max mem: 9390 +Train: [9] [4000/6250] eta: 0:05:47 lr: 0.000124 grad: 0.0705 (0.0761) loss: 0.8507 (0.8523) time: 0.1519 data: 0.0768 max mem: 9390 +Train: [9] [4100/6250] eta: 0:05:32 lr: 0.000124 grad: 0.0655 (0.0761) loss: 0.8525 (0.8523) time: 0.1166 data: 0.0290 max mem: 9390 +Train: [9] [4200/6250] eta: 0:05:16 lr: 0.000124 grad: 0.0739 (0.0760) loss: 0.8503 (0.8523) time: 0.1251 data: 0.0435 max mem: 9390 +Train: [9] [4300/6250] eta: 0:05:01 lr: 0.000124 grad: 0.0650 (0.0759) loss: 0.8482 (0.8523) time: 0.1510 data: 0.0631 max mem: 9390 +Train: [9] [4400/6250] eta: 0:04:46 lr: 0.000124 grad: 0.0747 (0.0758) loss: 0.8517 (0.8523) time: 0.1920 data: 0.1111 max mem: 9390 +Train: [9] [4500/6250] eta: 0:04:31 lr: 0.000124 grad: 0.0685 (0.0758) loss: 0.8566 (0.8523) time: 0.1763 data: 0.0966 max mem: 9390 +Train: [9] [4600/6250] eta: 0:04:15 lr: 0.000124 grad: 0.0771 (0.0758) loss: 0.8452 (0.8523) time: 0.1631 data: 0.0795 max mem: 9390 +Train: [9] [4700/6250] eta: 0:04:00 lr: 0.000124 grad: 0.0704 (0.0757) loss: 0.8525 (0.8523) time: 0.1641 data: 0.0795 max mem: 9390 +Train: [9] [4800/6250] eta: 0:03:44 lr: 0.000124 grad: 0.0665 (0.0755) loss: 0.8532 (0.8523) time: 0.1484 data: 0.0678 max mem: 9390 +Train: [9] [4900/6250] eta: 0:03:29 lr: 0.000124 grad: 0.0706 (0.0755) loss: 0.8528 (0.8523) time: 0.1248 data: 0.0377 max mem: 9390 +Train: [9] [5000/6250] eta: 0:03:13 lr: 0.000124 grad: 0.0704 (0.0754) loss: 0.8522 (0.8523) time: 0.1403 data: 0.0554 max mem: 9390 +Train: [9] [5100/6250] eta: 0:02:57 lr: 0.000124 grad: 0.0655 (0.0752) loss: 0.8571 (0.8523) time: 0.1153 data: 0.0295 max mem: 9390 +Train: [9] [5200/6250] eta: 0:02:42 lr: 0.000124 grad: 0.0658 (0.0752) loss: 0.8551 (0.8523) time: 0.1583 data: 0.0727 max mem: 9390 +Train: [9] [5300/6250] eta: 0:02:26 lr: 0.000124 grad: 0.0692 (0.0752) loss: 0.8485 (0.8523) time: 0.1439 data: 0.0564 max mem: 9390 +Train: [9] [5400/6250] eta: 0:02:10 lr: 0.000124 grad: 0.0687 (0.0750) loss: 0.8500 (0.8523) time: 0.1473 data: 0.0730 max mem: 9390 +Train: [9] [5500/6250] eta: 0:01:55 lr: 0.000124 grad: 0.0670 (0.0750) loss: 0.8551 (0.8523) time: 0.1580 data: 0.0708 max mem: 9390 +Train: [9] [5600/6250] eta: 0:01:40 lr: 0.000124 grad: 0.0706 (0.0750) loss: 0.8539 (0.8523) time: 0.1692 data: 0.0869 max mem: 9390 +Train: [9] [5700/6250] eta: 0:01:24 lr: 0.000124 grad: 0.0664 (0.0749) loss: 0.8470 (0.8523) time: 0.2067 data: 0.1248 max mem: 9390 +Train: [9] [5800/6250] eta: 0:01:09 lr: 0.000124 grad: 0.0653 (0.0748) loss: 0.8564 (0.8523) time: 0.1711 data: 0.0927 max mem: 9390 +Train: [9] [5900/6250] eta: 0:00:53 lr: 0.000124 grad: 0.0679 (0.0747) loss: 0.8500 (0.8522) time: 0.1538 data: 0.0679 max mem: 9390 +Train: [9] [6000/6250] eta: 0:00:38 lr: 0.000124 grad: 0.0682 (0.0747) loss: 0.8451 (0.8522) time: 0.1721 data: 0.0877 max mem: 9390 +Train: [9] [6100/6250] eta: 0:00:23 lr: 0.000124 grad: 0.0658 (0.0746) loss: 0.8559 (0.8522) time: 0.1481 data: 0.0731 max mem: 9390 +Train: [9] [6200/6250] eta: 0:00:07 lr: 0.000124 grad: 0.0705 (0.0746) loss: 0.8510 (0.8522) time: 0.1522 data: 0.0718 max mem: 9390 +Train: [9] [6249/6250] eta: 0:00:00 lr: 0.000124 grad: 0.0705 (0.0746) loss: 0.8453 (0.8521) time: 0.1520 data: 0.0687 max mem: 9390 +Train: [9] Total time: 0:16:06 (0.1546 s / it) +Averaged stats: lr: 0.000124 grad: 0.0705 (0.0746) loss: 0.8453 (0.8521) +Eval (hcp-train-subset): [9] [ 0/62] eta: 0:02:57 loss: 0.8674 (0.8674) time: 2.8643 data: 2.8198 max mem: 9390 +Eval (hcp-train-subset): [9] [61/62] eta: 0:00:00 loss: 0.8573 (0.8577) time: 0.1421 data: 0.1155 max mem: 9390 +Eval (hcp-train-subset): [9] Total time: 0:00:12 (0.2078 s / it) +Averaged stats (hcp-train-subset): loss: 0.8573 (0.8577) +Making plots (hcp-train-subset): example=47 +Eval (hcp-val): [9] [ 0/62] eta: 0:04:29 loss: 0.8506 (0.8506) time: 4.3406 data: 4.3087 max mem: 9390 +Eval (hcp-val): [9] [61/62] eta: 0:00:00 loss: 0.8516 (0.8520) time: 0.1204 data: 0.0945 max mem: 9390 +Eval (hcp-val): [9] Total time: 0:00:12 (0.2020 s / it) +Averaged stats (hcp-val): loss: 0.8516 (0.8520) +Making plots (hcp-val): example=17 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +Train: [10] [ 0/6250] eta: 6:09:57 lr: 0.000124 grad: 0.0673 (0.0673) loss: 0.8456 (0.8456) time: 3.5515 data: 3.2125 max mem: 9390 +Train: [10] [ 100/6250] eta: 0:19:46 lr: 0.000124 grad: 0.0706 (0.0921) loss: 0.8536 (0.8545) time: 0.1581 data: 0.0737 max mem: 9390 +Train: [10] [ 200/6250] eta: 0:16:55 lr: 0.000124 grad: 0.0671 (0.0830) loss: 0.8462 (0.8509) time: 0.1275 data: 0.0404 max mem: 9390 +Train: [10] [ 300/6250] eta: 0:15:48 lr: 0.000124 grad: 0.0643 (0.0829) loss: 0.8477 (0.8511) time: 0.1384 data: 0.0442 max mem: 9390 +Train: [10] [ 400/6250] eta: 0:15:00 lr: 0.000124 grad: 0.0640 (0.0792) loss: 0.8558 (0.8514) time: 0.1423 data: 0.0532 max mem: 9390 +Train: [10] [ 500/6250] eta: 0:14:35 lr: 0.000124 grad: 0.0631 (0.0766) loss: 0.8545 (0.8519) time: 0.1498 data: 0.0729 max mem: 9390 +Train: [10] [ 600/6250] eta: 0:14:16 lr: 0.000124 grad: 0.0659 (0.0751) loss: 0.8452 (0.8514) time: 0.1557 data: 0.0675 max mem: 9390 +Train: [10] [ 700/6250] eta: 0:14:18 lr: 0.000124 grad: 0.0646 (0.0744) loss: 0.8523 (0.8517) time: 0.2141 data: 0.1291 max mem: 9390 +Train: [10] [ 800/6250] eta: 0:14:18 lr: 0.000124 grad: 0.0646 (0.0736) loss: 0.8567 (0.8517) time: 0.2401 data: 0.1543 max mem: 9390 +Train: [10] [ 900/6250] eta: 0:14:04 lr: 0.000124 grad: 0.0689 (0.0735) loss: 0.8547 (0.8516) time: 0.1195 data: 0.0173 max mem: 9390 +Train: [10] [1000/6250] eta: 0:13:52 lr: 0.000124 grad: 0.0678 (0.0732) loss: 0.8504 (0.8515) time: 0.1447 data: 0.0581 max mem: 9390 +Train: [10] [1100/6250] eta: 0:13:34 lr: 0.000124 grad: 0.0695 (0.0730) loss: 0.8475 (0.8514) time: 0.1403 data: 0.0483 max mem: 9390 +Train: [10] [1200/6250] eta: 0:13:22 lr: 0.000124 grad: 0.0852 (0.0733) loss: 0.8519 (0.8514) time: 0.1361 data: 0.0448 max mem: 9390 +Train: [10] [1300/6250] eta: 0:13:01 lr: 0.000124 grad: 0.0663 (0.0728) loss: 0.8489 (0.8514) time: 0.1422 data: 0.0635 max mem: 9390 +Train: [10] [1400/6250] eta: 0:12:45 lr: 0.000124 grad: 0.0710 (0.0726) loss: 0.8527 (0.8514) time: 0.1427 data: 0.0521 max mem: 9390 +Train: [10] [1500/6250] eta: 0:12:29 lr: 0.000124 grad: 0.0654 (0.0724) loss: 0.8487 (0.8512) time: 0.1615 data: 0.0771 max mem: 9390 +Train: [10] [1600/6250] eta: 0:12:11 lr: 0.000124 grad: 0.0686 (0.0727) loss: 0.8460 (0.8511) time: 0.1243 data: 0.0373 max mem: 9390 +Train: [10] [1700/6250] eta: 0:11:54 lr: 0.000124 grad: 0.0657 (0.0725) loss: 0.8541 (0.8510) time: 0.1491 data: 0.0635 max mem: 9390 +Train: [10] [1800/6250] eta: 0:11:36 lr: 0.000124 grad: 0.0687 (0.0724) loss: 0.8504 (0.8510) time: 0.1094 data: 0.0290 max mem: 9390 +Train: [10] [1900/6250] eta: 0:11:18 lr: 0.000124 grad: 0.0688 (0.0723) loss: 0.8504 (0.8509) time: 0.1634 data: 0.0819 max mem: 9390 +Train: [10] [2000/6250] eta: 0:11:04 lr: 0.000124 grad: 0.0632 (0.0721) loss: 0.8488 (0.8508) time: 0.1739 data: 0.1022 max mem: 9390 +Train: [10] [2100/6250] eta: 0:10:47 lr: 0.000124 grad: 0.0640 (0.0719) loss: 0.8469 (0.8507) time: 0.1344 data: 0.0535 max mem: 9390 +Train: [10] [2200/6250] eta: 0:10:31 lr: 0.000124 grad: 0.0668 (0.0718) loss: 0.8558 (0.8507) time: 0.1610 data: 0.0766 max mem: 9390 +Train: [10] [2300/6250] eta: 0:10:15 lr: 0.000124 grad: 0.0666 (0.0716) loss: 0.8493 (0.8507) time: 0.1452 data: 0.0635 max mem: 9390 +Train: [10] [2400/6250] eta: 0:10:02 lr: 0.000124 grad: 0.0701 (0.0716) loss: 0.8454 (0.8505) time: 0.1642 data: 0.0769 max mem: 9390 +Train: [10] [2500/6250] eta: 0:09:47 lr: 0.000124 grad: 0.0641 (0.0716) loss: 0.8498 (0.8505) time: 0.1754 data: 0.0924 max mem: 9390 +Train: [10] [2600/6250] eta: 0:09:30 lr: 0.000124 grad: 0.0626 (0.0714) loss: 0.8507 (0.8504) time: 0.1637 data: 0.0852 max mem: 9390 +Train: [10] [2700/6250] eta: 0:09:13 lr: 0.000124 grad: 0.0857 (0.0716) loss: 0.8431 (0.8503) time: 0.1343 data: 0.0537 max mem: 9390 +Train: [10] [2800/6250] eta: 0:08:56 lr: 0.000124 grad: 0.0709 (0.0717) loss: 0.8438 (0.8502) time: 0.1487 data: 0.0735 max mem: 9390 +Train: [10] [2900/6250] eta: 0:08:38 lr: 0.000124 grad: 0.0701 (0.0716) loss: 0.8484 (0.8501) time: 0.1258 data: 0.0325 max mem: 9390 +Train: [10] [3000/6250] eta: 0:08:21 lr: 0.000124 grad: 0.0752 (0.0716) loss: 0.8468 (0.8500) time: 0.1392 data: 0.0532 max mem: 9390 +Train: [10] [3100/6250] eta: 0:08:04 lr: 0.000124 grad: 0.0673 (0.0716) loss: 0.8463 (0.8500) time: 0.1481 data: 0.0645 max mem: 9390 +Train: [10] [3200/6250] eta: 0:07:47 lr: 0.000124 grad: 0.0661 (0.0715) loss: 0.8465 (0.8500) time: 0.1307 data: 0.0441 max mem: 9390 +Train: [10] [3300/6250] eta: 0:07:30 lr: 0.000124 grad: 0.0679 (0.0715) loss: 0.8496 (0.8500) time: 0.1498 data: 0.0691 max mem: 9390 +Train: [10] [3400/6250] eta: 0:07:15 lr: 0.000124 grad: 0.0638 (0.0716) loss: 0.8520 (0.8500) time: 0.1564 data: 0.0755 max mem: 9390 +Train: [10] [3500/6250] eta: 0:06:59 lr: 0.000124 grad: 0.0672 (0.0714) loss: 0.8501 (0.8500) time: 0.1570 data: 0.0710 max mem: 9390 +Train: [10] [3600/6250] eta: 0:06:47 lr: 0.000124 grad: 0.0681 (0.0716) loss: 0.8514 (0.8501) time: 0.1922 data: 0.0944 max mem: 9390 +Train: [10] [3700/6250] eta: 0:06:31 lr: 0.000124 grad: 0.0636 (0.0715) loss: 0.8491 (0.8501) time: 0.1110 data: 0.0322 max mem: 9390 +Train: [10] [3800/6250] eta: 0:06:17 lr: 0.000124 grad: 0.0736 (0.0715) loss: 0.8560 (0.8501) time: 0.1892 data: 0.1078 max mem: 9390 +Train: [10] [3900/6250] eta: 0:06:03 lr: 0.000124 grad: 0.0666 (0.0714) loss: 0.8492 (0.8501) time: 0.1656 data: 0.0707 max mem: 9390 +Train: [10] [4000/6250] eta: 0:05:51 lr: 0.000124 grad: 0.0665 (0.0714) loss: 0.8509 (0.8501) time: 0.3296 data: 0.2418 max mem: 9390 +Train: [10] [4100/6250] eta: 0:05:41 lr: 0.000124 grad: 0.0614 (0.0713) loss: 0.8491 (0.8501) time: 0.1040 data: 0.0003 max mem: 9390 +Train: [10] [4200/6250] eta: 0:05:26 lr: 0.000124 grad: 0.0660 (0.0712) loss: 0.8517 (0.8500) time: 0.1679 data: 0.0853 max mem: 9390 +Train: [10] [4300/6250] eta: 0:05:10 lr: 0.000124 grad: 0.0654 (0.0712) loss: 0.8485 (0.8500) time: 0.1741 data: 0.0944 max mem: 9390 +Train: [10] [4400/6250] eta: 0:04:54 lr: 0.000124 grad: 0.0693 (0.0712) loss: 0.8465 (0.8500) time: 0.1900 data: 0.1078 max mem: 9390 +Train: [10] [4500/6250] eta: 0:04:38 lr: 0.000124 grad: 0.0662 (0.0712) loss: 0.8476 (0.8500) time: 0.1389 data: 0.0573 max mem: 9390 +Train: [10] [4600/6250] eta: 0:04:23 lr: 0.000124 grad: 0.0654 (0.0712) loss: 0.8480 (0.8500) time: 0.1348 data: 0.0440 max mem: 9390 +Train: [10] [4700/6250] eta: 0:04:08 lr: 0.000124 grad: 0.0654 (0.0711) loss: 0.8442 (0.8499) time: 0.1852 data: 0.0962 max mem: 9390 +Train: [10] [4800/6250] eta: 0:03:53 lr: 0.000124 grad: 0.0639 (0.0710) loss: 0.8472 (0.8499) time: 0.3339 data: 0.2403 max mem: 9390 +Train: [10] [4900/6250] eta: 0:03:38 lr: 0.000124 grad: 0.0692 (0.0710) loss: 0.8512 (0.8499) time: 0.1874 data: 0.0996 max mem: 9390 +Train: [10] [5000/6250] eta: 0:03:22 lr: 0.000124 grad: 0.0646 (0.0709) loss: 0.8469 (0.8498) time: 0.2125 data: 0.1238 max mem: 9390 +Train: [10] [5100/6250] eta: 0:03:07 lr: 0.000124 grad: 0.0666 (0.0710) loss: 0.8531 (0.8498) time: 0.1533 data: 0.0708 max mem: 9390 +Train: [10] [5200/6250] eta: 0:02:50 lr: 0.000124 grad: 0.0634 (0.0710) loss: 0.8478 (0.8498) time: 0.1422 data: 0.0530 max mem: 9390 +Train: [10] [5300/6250] eta: 0:02:34 lr: 0.000124 grad: 0.0682 (0.0710) loss: 0.8487 (0.8498) time: 0.1518 data: 0.0729 max mem: 9390 +Train: [10] [5400/6250] eta: 0:02:18 lr: 0.000124 grad: 0.0638 (0.0709) loss: 0.8483 (0.8498) time: 0.1049 data: 0.0210 max mem: 9390 +Train: [10] [5500/6250] eta: 0:02:02 lr: 0.000124 grad: 0.0685 (0.0708) loss: 0.8512 (0.8497) time: 0.2375 data: 0.1473 max mem: 9390 +Train: [10] [5600/6250] eta: 0:01:45 lr: 0.000124 grad: 0.0652 (0.0708) loss: 0.8478 (0.8497) time: 0.1608 data: 0.0744 max mem: 9390 +Train: [10] [5700/6250] eta: 0:01:29 lr: 0.000124 grad: 0.0584 (0.0707) loss: 0.8515 (0.8497) time: 0.1678 data: 0.0720 max mem: 9390 +Train: [10] [5800/6250] eta: 0:01:13 lr: 0.000124 grad: 0.0677 (0.0707) loss: 0.8478 (0.8497) time: 0.1539 data: 0.0669 max mem: 9390 +Train: [10] [5900/6250] eta: 0:00:56 lr: 0.000124 grad: 0.0686 (0.0707) loss: 0.8469 (0.8496) time: 0.1514 data: 0.0725 max mem: 9390 +Train: [10] [6000/6250] eta: 0:00:40 lr: 0.000124 grad: 0.0640 (0.0708) loss: 0.8489 (0.8496) time: 0.1566 data: 0.0821 max mem: 9390 +Train: [10] [6100/6250] eta: 0:00:24 lr: 0.000124 grad: 0.0640 (0.0707) loss: 0.8490 (0.8496) time: 0.1735 data: 0.0918 max mem: 9390 +Train: [10] [6200/6250] eta: 0:00:08 lr: 0.000124 grad: 0.0638 (0.0706) loss: 0.8451 (0.8496) time: 0.1899 data: 0.1056 max mem: 9390 +Train: [10] [6249/6250] eta: 0:00:00 lr: 0.000124 grad: 0.0644 (0.0706) loss: 0.8482 (0.8496) time: 0.1738 data: 0.0946 max mem: 9390 +Train: [10] Total time: 0:17:06 (0.1642 s / it) +Averaged stats: lr: 0.000124 grad: 0.0644 (0.0706) loss: 0.8482 (0.8496) +Eval (hcp-train-subset): [10] [ 0/62] eta: 0:03:17 loss: 0.8617 (0.8617) time: 3.1778 data: 3.0922 max mem: 9390 +Eval (hcp-train-subset): [10] [61/62] eta: 0:00:00 loss: 0.8539 (0.8549) time: 0.1633 data: 0.1379 max mem: 9390 +Eval (hcp-train-subset): [10] Total time: 0:00:14 (0.2285 s / it) +Averaged stats (hcp-train-subset): loss: 0.8539 (0.8549) +Eval (hcp-val): [10] [ 0/62] eta: 0:03:15 loss: 0.8476 (0.8476) time: 3.1511 data: 3.0780 max mem: 9390 +Eval (hcp-val): [10] [61/62] eta: 0:00:00 loss: 0.8475 (0.8488) time: 0.1372 data: 0.1119 max mem: 9390 +Eval (hcp-val): [10] Total time: 0:00:14 (0.2271 s / it) +Averaged stats (hcp-val): loss: 0.8475 (0.8488) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +Train: [11] [ 0/6250] eta: 11:43:17 lr: 0.000124 grad: 0.0975 (0.0975) loss: 0.8576 (0.8576) time: 6.7517 data: 6.6519 max mem: 9390 +Train: [11] [ 100/6250] eta: 0:23:11 lr: 0.000124 grad: 0.0616 (0.0703) loss: 0.8575 (0.8572) time: 0.2083 data: 0.1079 max mem: 9390 +Train: [11] [ 200/6250] eta: 0:19:48 lr: 0.000124 grad: 0.0769 (0.0752) loss: 0.8525 (0.8547) time: 0.1939 data: 0.1009 max mem: 9390 +Train: [11] [ 300/6250] eta: 0:18:07 lr: 0.000124 grad: 0.0697 (0.0754) loss: 0.8521 (0.8527) time: 0.1312 data: 0.0366 max mem: 9390 +Train: [11] [ 400/6250] eta: 0:17:09 lr: 0.000124 grad: 0.0695 (0.0743) loss: 0.8482 (0.8518) time: 0.1513 data: 0.0635 max mem: 9390 +Train: [11] [ 500/6250] eta: 0:16:44 lr: 0.000124 grad: 0.0629 (0.0737) loss: 0.8584 (0.8521) time: 0.1424 data: 0.0597 max mem: 9390 +Train: [11] [ 600/6250] eta: 0:16:21 lr: 0.000124 grad: 0.0609 (0.0731) loss: 0.8589 (0.8519) time: 0.1597 data: 0.0768 max mem: 9390 +Train: [11] [ 700/6250] eta: 0:15:59 lr: 0.000124 grad: 0.0642 (0.0722) loss: 0.8519 (0.8521) time: 0.1804 data: 0.0983 max mem: 9390 +Train: [11] [ 800/6250] eta: 0:16:22 lr: 0.000124 grad: 0.0670 (0.0718) loss: 0.8504 (0.8519) time: 0.1879 data: 0.0997 max mem: 9390 +Train: [11] [ 900/6250] eta: 0:16:01 lr: 0.000124 grad: 0.0662 (0.0717) loss: 0.8487 (0.8518) time: 0.1521 data: 0.0624 max mem: 9390 +Train: [11] [1000/6250] eta: 0:15:38 lr: 0.000124 grad: 0.0673 (0.0714) loss: 0.8502 (0.8518) time: 0.1763 data: 0.0966 max mem: 9390 +Train: [11] [1100/6250] eta: 0:15:12 lr: 0.000124 grad: 0.0650 (0.0714) loss: 0.8505 (0.8516) time: 0.1515 data: 0.0680 max mem: 9390 +Train: [11] [1200/6250] eta: 0:15:03 lr: 0.000124 grad: 0.0682 (0.0714) loss: 0.8497 (0.8514) time: 0.2189 data: 0.0985 max mem: 9390 +Train: [11] [1300/6250] eta: 0:14:28 lr: 0.000124 grad: 0.0663 (0.0713) loss: 0.8499 (0.8512) time: 0.1583 data: 0.0799 max mem: 9390 +Train: [11] [1400/6250] eta: 0:14:09 lr: 0.000124 grad: 0.0640 (0.0709) loss: 0.8465 (0.8510) time: 0.2133 data: 0.1334 max mem: 9390 +Train: [11] [1500/6250] eta: 0:13:51 lr: 0.000124 grad: 0.0682 (0.0708) loss: 0.8484 (0.8509) time: 0.1546 data: 0.0776 max mem: 9390 +Train: [11] [1600/6250] eta: 0:13:28 lr: 0.000124 grad: 0.0667 (0.0706) loss: 0.8489 (0.8508) time: 0.1191 data: 0.0337 max mem: 9390 +pretraining fmri mae +start: 2026-04-01 16:17:00 +cwd: /data/connor/fmri-fm +sha: 7f4cedc35609f6857314e0d1ea6657523f17ddeb, status: has uncommitted changes, branch: dev/clane9 +config: +name: input_space_v3/flat_lr1e-3_6/pretrain +notes: input_space ablation v3 flat_lr1e-3_6; use tube masking and on-disk data (input_space=flat + base_lr=1e-3 seed=5406) +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain +input_space: flat +patch_size: 16 +num_frames: 16 +t_patch_size: 4 +mask_ratio: 0.9 +pred_mask_ratio: null +masking: tube +masking_kwargs: {} +mask_patch_size: null +model: mae_vit_base +model_kwargs: + decoding: attn + pos_embed: sep + target_norm: null + pca_norm_nc: 2 + t_pred_stride: 2 + no_decode_pos: true + mask_drop_scale: false + pred_edge_pad: 0 + gauss_sigma: null + class_token: true + reg_tokens: 0 + no_embed_class: true + head_init_scale: 0.0 + decoder_depth: 4 + drop_path_rate: 0.0 +datasets: + hcp-train: + type: wds + url: /data/fmri-datasets/pretrain/hcpya-all.${input_space}.wds/hcpya-all-${input_space}-{00000..01799}.tar + clipping: random + clipping_kwargs: + oversample: 4.0 + shuffle: true + buffer_size: 2000 + samples_per_epoch: 200000 + hcp-train-subset: + type: arrow + root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/validation + split_range: + - 0 + - 2000 + shuffle: false + hcp-val: + type: arrow + root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/test + split_range: + - 0 + - 2000 + shuffle: false +train_dataset: hcp-train +eval_datasets: +- hcp-train-subset +- hcp-val +val_dataset: null +clip_vmax: 3.0 +normalize: frame +tr_scale: null +crop_scale: null +crop_aspect: null +gray_jitter: null +num_workers: 16 +epochs: 100 +batch_size: 32 +accum_iter: 1 +base_lr: 0.001 +min_lr: 0.0 +warmup_epochs: 5 +weight_decay: 0.05 +betas: +- 0.9 +- 0.95 +clip_grad: 1.0 +amp: true +amp_dtype: float16 +ckpt: null +resume: true +auto_resume: true +start_epoch: 0 +max_checkpoints: 0 +checkpoint_period: null +plot_period: 5 +device: cuda +presend_cuda: false +seed: 5406 +debug: false +wandb: true +wandb_entity: null +wandb_project: fMRI-foundation-model +rank: 0 +world_size: 1 +gpu: 0 +distributed: true +dist_backend: nccl +in_chans: 1 +img_size: +- 224 +- 560 + +train transform: +Compose( + ToTensor() + TemporalCenterCrop(num_frames=16) + Normalize(mode='frame') + Clip(vmax=3.0) + FlatUnmask((224, 560)) +) +val transform: +Compose( + ToTensor() + TemporalCenterCrop(num_frames=16) + Normalize(mode='frame') + Clip(vmax=3.0) + FlatUnmask((224, 560)) +) +mask generator: +TubeMasking( + mask_ratio=0.9 + (patchify): Patchify2D((224, 560), (16, 16), in_chans=1) +) +loading dataset: hcp-train + +type: wds +url: /data/fmri-datasets/pretrain/hcpya-all.${input_space}.wds/hcpya-all-${input_space}-{00000..01799}.tar +clipping: random +clipping_kwargs: + oversample: 4.0 +shuffle: true +buffer_size: 2000 +samples_per_epoch: 200000 + +loading dataset: hcp-train-subset + +type: arrow +root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/validation +split_range: +- 0 +- 2000 +shuffle: false + +split indices: [899, 472, 767, 116, 1265, 1852, 300, 1335, 361, 1560] +loading dataset: hcp-val + +type: arrow +root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/test +split_range: +- 0 +- 2000 +shuffle: false + +split indices: [1075, 1189, 738, 1350, 965, 1964, 1367, 1183, 1619, 1407] +model: +MaskedAutoencoderViT( + decoding=attn, t_pred_stride=2, pred_edge_pad=0, no_decode_pos=True + (encoder): MaskedEncoder( + class_token=True, reg_tokens=0, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) + (pred_patchify): StridedPatchify3D((16, 224, 560), (2, 16, 16), in_chans=1, t_stride=2) + (decoder): MaskedDecoder( + cross_decode=False, class_token=True, no_embed_class=True + (pos_embed): SeparablePosEmbed(512, (4, 14, 35)) + (proj): Linear(in_features=768, out_features=512, bias=True) + (blocks): ModuleList( + (0-3): 4 x Block( + (norm1): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=16 + (q): Linear(in_features=512, out_features=512, bias=True) + (k): Linear(in_features=512, out_features=512, bias=True) + (v): Linear(in_features=512, out_features=512, bias=True) + (proj): Linear(in_features=512, out_features=512, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=512, out_features=2048, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=2048, out_features=512, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (head): Linear(in_features=512, out_features=512, bias=True) + ) +) +num params: 99.7M +total batch size: 32 = 32 bs per gpu x 1 accum x 1 gpus +lr: 1.25e-04 = 1.00e-03 x 32 / 256 +full schedule: epochs = 100 (steps = 625000) +warmup: epochs = 5 (steps = 31250) +loaded model state from checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +loaded optimizer state, resuming training from 11 +start training for 100 epochs +Train: [11] [ 0/6250] eta: 14:38:45 lr: 0.000124 grad: 0.0484 (0.0484) loss: 0.8966 (0.8966) time: 8.4361 data: 7.3656 max mem: 9353 +Train: [11] [ 100/6250] eta: 0:22:24 lr: 0.000124 grad: 0.0613 (0.0665) loss: 0.8568 (0.8606) time: 0.1547 data: 0.0610 max mem: 9390 +Train: [11] [ 200/6250] eta: 0:18:05 lr: 0.000124 grad: 0.0621 (0.0652) loss: 0.8515 (0.8564) time: 0.1581 data: 0.0613 max mem: 9390 +Train: [11] [ 300/6250] eta: 0:16:25 lr: 0.000124 grad: 0.0647 (0.0663) loss: 0.8494 (0.8546) time: 0.1402 data: 0.0449 max mem: 9390 +Train: [11] [ 400/6250] eta: 0:15:32 lr: 0.000124 grad: 0.0697 (0.0677) loss: 0.8483 (0.8532) time: 0.1401 data: 0.0455 max mem: 9390 +Train: [11] [ 500/6250] eta: 0:14:55 lr: 0.000124 grad: 0.0705 (0.0682) loss: 0.8486 (0.8522) time: 0.1210 data: 0.0367 max mem: 9390 +Train: [11] [ 600/6250] eta: 0:14:30 lr: 0.000124 grad: 0.0688 (0.0687) loss: 0.8422 (0.8511) time: 0.1615 data: 0.0750 max mem: 9390 +Train: [11] [ 700/6250] eta: 0:14:05 lr: 0.000124 grad: 0.0624 (0.0686) loss: 0.8425 (0.8503) time: 0.1403 data: 0.0461 max mem: 9390 +Train: [11] [ 800/6250] eta: 0:13:43 lr: 0.000124 grad: 0.0685 (0.0685) loss: 0.8485 (0.8499) time: 0.1340 data: 0.0482 max mem: 9390 +Train: [11] [ 900/6250] eta: 0:13:23 lr: 0.000124 grad: 0.0617 (0.0683) loss: 0.8495 (0.8497) time: 0.1347 data: 0.0475 max mem: 9390 +Train: [11] [1000/6250] eta: 0:12:59 lr: 0.000124 grad: 0.0700 (0.0682) loss: 0.8518 (0.8498) time: 0.1092 data: 0.0263 max mem: 9390 +Train: [11] [1100/6250] eta: 0:12:39 lr: 0.000124 grad: 0.0641 (0.0682) loss: 0.8512 (0.8499) time: 0.1656 data: 0.0776 max mem: 9390 +Train: [11] [1200/6250] eta: 0:12:18 lr: 0.000124 grad: 0.0725 (0.0683) loss: 0.8469 (0.8499) time: 0.1219 data: 0.0388 max mem: 9390 +Train: [11] [1300/6250] eta: 0:12:00 lr: 0.000124 grad: 0.0641 (0.0683) loss: 0.8477 (0.8497) time: 0.1348 data: 0.0439 max mem: 9390 +Train: [11] [1400/6250] eta: 0:11:41 lr: 0.000124 grad: 0.0662 (0.0681) loss: 0.8487 (0.8496) time: 0.1212 data: 0.0387 max mem: 9390 +Train: [11] [1500/6250] eta: 0:11:22 lr: 0.000124 grad: 0.0664 (0.0682) loss: 0.8464 (0.8495) time: 0.1332 data: 0.0511 max mem: 9390 +Train: [11] [1600/6250] eta: 0:11:06 lr: 0.000124 grad: 0.0629 (0.0680) loss: 0.8487 (0.8493) time: 0.1444 data: 0.0681 max mem: 9390 +Train: [11] [1700/6250] eta: 0:10:48 lr: 0.000124 grad: 0.0696 (0.0682) loss: 0.8463 (0.8493) time: 0.1362 data: 0.0571 max mem: 9390 +Train: [11] [1800/6250] eta: 0:10:31 lr: 0.000124 grad: 0.0631 (0.0680) loss: 0.8511 (0.8494) time: 0.1261 data: 0.0478 max mem: 9390 +Train: [11] [1900/6250] eta: 0:10:14 lr: 0.000124 grad: 0.0623 (0.0679) loss: 0.8509 (0.8494) time: 0.1056 data: 0.0179 max mem: 9390 +Train: [11] [2000/6250] eta: 0:09:59 lr: 0.000124 grad: 0.0653 (0.0678) loss: 0.8479 (0.8494) time: 0.1315 data: 0.0544 max mem: 9390 +Train: [11] [2100/6250] eta: 0:09:43 lr: 0.000124 grad: 0.0674 (0.0678) loss: 0.8508 (0.8494) time: 0.1184 data: 0.0349 max mem: 9390 +Train: [11] [2200/6250] eta: 0:09:27 lr: 0.000124 grad: 0.0623 (0.0679) loss: 0.8516 (0.8494) time: 0.1371 data: 0.0557 max mem: 9390 +Train: [11] [2300/6250] eta: 0:09:12 lr: 0.000124 grad: 0.0594 (0.0677) loss: 0.8507 (0.8493) time: 0.1493 data: 0.0641 max mem: 9390 +Train: [11] [2400/6250] eta: 0:08:56 lr: 0.000124 grad: 0.0623 (0.0677) loss: 0.8493 (0.8493) time: 0.1176 data: 0.0324 max mem: 9390 +Train: [11] [2500/6250] eta: 0:08:40 lr: 0.000124 grad: 0.0641 (0.0676) loss: 0.8488 (0.8494) time: 0.1285 data: 0.0526 max mem: 9390 +Train: [11] [2600/6250] eta: 0:08:26 lr: 0.000124 grad: 0.0648 (0.0676) loss: 0.8510 (0.8494) time: 0.1379 data: 0.0590 max mem: 9390 +pretraining fmri mae +start: 2026-04-02 10:17:16 +cwd: /data/connor/fmri-fm +sha: 7f4cedc35609f6857314e0d1ea6657523f17ddeb, status: has uncommitted changes, branch: dev/clane9 +config: +name: input_space_v3/flat_lr1e-3_6/pretrain +notes: input_space ablation v3 flat_lr1e-3_6; use tube masking and on-disk data (input_space=flat + base_lr=1e-3 seed=5406) +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain +input_space: flat +patch_size: 16 +num_frames: 16 +t_patch_size: 4 +mask_ratio: 0.9 +pred_mask_ratio: null +masking: tube +masking_kwargs: {} +mask_patch_size: null +model: mae_vit_base +model_kwargs: + decoding: attn + pos_embed: sep + target_norm: null + pca_norm_nc: 2 + t_pred_stride: 2 + no_decode_pos: true + mask_drop_scale: false + pred_edge_pad: 0 + gauss_sigma: null + class_token: true + reg_tokens: 0 + no_embed_class: true + head_init_scale: 0.0 + decoder_depth: 4 + drop_path_rate: 0.0 +datasets: + hcp-train: + type: wds + url: /data/fmri-datasets/pretrain/hcpya-all.${input_space}.wds/hcpya-all-${input_space}-{00000..01799}.tar + clipping: random + clipping_kwargs: + oversample: 4.0 + shuffle: true + buffer_size: 2000 + samples_per_epoch: 200000 + hcp-train-subset: + type: arrow + root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/validation + split_range: + - 0 + - 2000 + shuffle: false + hcp-val: + type: arrow + root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/test + split_range: + - 0 + - 2000 + shuffle: false +train_dataset: hcp-train +eval_datasets: +- hcp-train-subset +- hcp-val +val_dataset: null +clip_vmax: 3.0 +normalize: frame +tr_scale: null +crop_scale: null +crop_aspect: null +gray_jitter: null +num_workers: 16 +epochs: 100 +batch_size: 32 +accum_iter: 1 +base_lr: 0.001 +min_lr: 0.0 +warmup_epochs: 5 +weight_decay: 0.05 +betas: +- 0.9 +- 0.95 +clip_grad: 1.0 +amp: true +amp_dtype: float16 +ckpt: null +resume: true +auto_resume: true +start_epoch: 0 +max_checkpoints: 0 +checkpoint_period: null +plot_period: 5 +device: cuda +presend_cuda: false +seed: 5406 +debug: false +wandb: true +wandb_entity: null +wandb_project: fMRI-foundation-model +rank: 0 +world_size: 1 +gpu: 0 +distributed: true +dist_backend: nccl +in_chans: 1 +img_size: +- 224 +- 560 + +train transform: +Compose( + ToTensor() + TemporalCenterCrop(num_frames=16) + Normalize(mode='frame') + Clip(vmax=3.0) + FlatUnmask((224, 560)) +) +val transform: +Compose( + ToTensor() + TemporalCenterCrop(num_frames=16) + Normalize(mode='frame') + Clip(vmax=3.0) + FlatUnmask((224, 560)) +) +mask generator: +TubeMasking( + mask_ratio=0.9 + (patchify): Patchify2D((224, 560), (16, 16), in_chans=1) +) +loading dataset: hcp-train + +type: wds +url: /data/fmri-datasets/pretrain/hcpya-all.${input_space}.wds/hcpya-all-${input_space}-{00000..01799}.tar +clipping: random +clipping_kwargs: + oversample: 4.0 +shuffle: true +buffer_size: 2000 +samples_per_epoch: 200000 + +loading dataset: hcp-train-subset + +type: arrow +root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/validation +split_range: +- 0 +- 2000 +shuffle: false + +split indices: [899, 472, 767, 116, 1265, 1852, 300, 1335, 361, 1560] +loading dataset: hcp-val + +type: arrow +root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/test +split_range: +- 0 +- 2000 +shuffle: false + +split indices: [1075, 1189, 738, 1350, 965, 1964, 1367, 1183, 1619, 1407] +model: +MaskedAutoencoderViT( + decoding=attn, t_pred_stride=2, pred_edge_pad=0, no_decode_pos=True + (encoder): MaskedEncoder( + class_token=True, reg_tokens=0, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) + (pred_patchify): StridedPatchify3D((16, 224, 560), (2, 16, 16), in_chans=1, t_stride=2) + (decoder): MaskedDecoder( + cross_decode=False, class_token=True, no_embed_class=True + (pos_embed): SeparablePosEmbed(512, (4, 14, 35)) + (proj): Linear(in_features=768, out_features=512, bias=True) + (blocks): ModuleList( + (0-3): 4 x Block( + (norm1): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=16 + (q): Linear(in_features=512, out_features=512, bias=True) + (k): Linear(in_features=512, out_features=512, bias=True) + (v): Linear(in_features=512, out_features=512, bias=True) + (proj): Linear(in_features=512, out_features=512, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=512, out_features=2048, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=2048, out_features=512, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (head): Linear(in_features=512, out_features=512, bias=True) + ) +) +num params: 99.7M +total batch size: 32 = 32 bs per gpu x 1 accum x 1 gpus +lr: 1.25e-04 = 1.00e-03 x 32 / 256 +full schedule: epochs = 100 (steps = 625000) +warmup: epochs = 5 (steps = 31250) +loaded model state from checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +loaded optimizer state, resuming training from 11 +start training for 100 epochs +Train: [11] [ 0/6250] eta: 14:26:02 lr: 0.000124 grad: 0.0651 (0.0651) loss: 0.8641 (0.8641) time: 8.3139 data: 7.2962 max mem: 9353 +Train: [11] [ 100/6250] eta: 0:23:53 lr: 0.000124 grad: 0.0642 (0.0734) loss: 0.8424 (0.8552) time: 0.1349 data: 0.0306 max mem: 9390 +Train: [11] [ 200/6250] eta: 0:20:14 lr: 0.000124 grad: 0.0648 (0.0733) loss: 0.8348 (0.8489) time: 0.1473 data: 0.0383 max mem: 9390 +Train: [11] [ 300/6250] eta: 0:18:58 lr: 0.000124 grad: 0.0709 (0.0761) loss: 0.8497 (0.8484) time: 0.1400 data: 0.0422 max mem: 9390 +Train: [11] [ 400/6250] eta: 0:18:08 lr: 0.000124 grad: 0.0659 (0.0740) loss: 0.8492 (0.8486) time: 0.1830 data: 0.0873 max mem: 9390 +Train: [11] [ 500/6250] eta: 0:17:28 lr: 0.000124 grad: 0.0636 (0.0726) loss: 0.8505 (0.8487) time: 0.1691 data: 0.0723 max mem: 9390 +Train: [11] [ 600/6250] eta: 0:16:55 lr: 0.000124 grad: 0.0645 (0.0721) loss: 0.8525 (0.8486) time: 0.1643 data: 0.0623 max mem: 9390 +Train: [11] [ 700/6250] eta: 0:16:25 lr: 0.000124 grad: 0.0640 (0.0714) loss: 0.8487 (0.8484) time: 0.1740 data: 0.0750 max mem: 9390 +Train: [11] [ 800/6250] eta: 0:16:02 lr: 0.000124 grad: 0.0685 (0.0708) loss: 0.8501 (0.8485) time: 0.1800 data: 0.0891 max mem: 9390 +Train: [11] [ 900/6250] eta: 0:15:36 lr: 0.000124 grad: 0.0594 (0.0704) loss: 0.8469 (0.8487) time: 0.1828 data: 0.0844 max mem: 9390 +Train: [11] [1000/6250] eta: 0:15:10 lr: 0.000124 grad: 0.0638 (0.0699) loss: 0.8500 (0.8488) time: 0.1676 data: 0.0735 max mem: 9390 +Train: [11] [1100/6250] eta: 0:14:44 lr: 0.000124 grad: 0.0680 (0.0699) loss: 0.8521 (0.8489) time: 0.1470 data: 0.0554 max mem: 9390 +Train: [11] [1200/6250] eta: 0:14:24 lr: 0.000124 grad: 0.0703 (0.0696) loss: 0.8478 (0.8491) time: 0.1865 data: 0.0957 max mem: 9390 +Train: [11] [1300/6250] eta: 0:14:01 lr: 0.000124 grad: 0.0653 (0.0697) loss: 0.8511 (0.8493) time: 0.1553 data: 0.0572 max mem: 9390 +Train: [11] [1400/6250] eta: 0:13:44 lr: 0.000124 grad: 0.0662 (0.0695) loss: 0.8466 (0.8493) time: 0.1666 data: 0.0715 max mem: 9390 +Train: [11] [1500/6250] eta: 0:13:24 lr: 0.000124 grad: 0.0684 (0.0698) loss: 0.8486 (0.8492) time: 0.1505 data: 0.0472 max mem: 9390 +Train: [11] [1600/6250] eta: 0:13:05 lr: 0.000124 grad: 0.0699 (0.0701) loss: 0.8462 (0.8492) time: 0.1809 data: 0.0808 max mem: 9390 +Train: [11] [1700/6250] eta: 0:12:47 lr: 0.000124 grad: 0.0661 (0.0700) loss: 0.8474 (0.8491) time: 0.1879 data: 0.0965 max mem: 9390 +Train: [11] [1800/6250] eta: 0:12:26 lr: 0.000124 grad: 0.0686 (0.0701) loss: 0.8463 (0.8490) time: 0.1643 data: 0.0761 max mem: 9390 +Train: [11] [1900/6250] eta: 0:12:05 lr: 0.000124 grad: 0.0689 (0.0701) loss: 0.8491 (0.8489) time: 0.1514 data: 0.0620 max mem: 9390 +Train: [11] [2000/6250] eta: 0:11:47 lr: 0.000124 grad: 0.0663 (0.0701) loss: 0.8477 (0.8489) time: 0.1522 data: 0.0640 max mem: 9390 +Train: [11] [2100/6250] eta: 0:11:30 lr: 0.000124 grad: 0.0670 (0.0701) loss: 0.8494 (0.8488) time: 0.1554 data: 0.0701 max mem: 9390 +Train: [11] [2200/6250] eta: 0:11:11 lr: 0.000124 grad: 0.0645 (0.0701) loss: 0.8474 (0.8487) time: 0.1591 data: 0.0727 max mem: 9390 +Train: [11] [2300/6250] eta: 0:10:53 lr: 0.000124 grad: 0.0703 (0.0701) loss: 0.8488 (0.8486) time: 0.1512 data: 0.0625 max mem: 9390 +Train: [11] [2400/6250] eta: 0:10:35 lr: 0.000124 grad: 0.0669 (0.0700) loss: 0.8424 (0.8485) time: 0.1484 data: 0.0601 max mem: 9390 +Train: [11] [2500/6250] eta: 0:10:17 lr: 0.000124 grad: 0.0695 (0.0699) loss: 0.8466 (0.8485) time: 0.1393 data: 0.0455 max mem: 9390 +Train: [11] [2600/6250] eta: 0:09:59 lr: 0.000124 grad: 0.0760 (0.0700) loss: 0.8432 (0.8484) time: 0.1684 data: 0.0757 max mem: 9390 +Train: [11] [2700/6250] eta: 0:09:41 lr: 0.000124 grad: 0.0655 (0.0699) loss: 0.8460 (0.8483) time: 0.1684 data: 0.0813 max mem: 9390 +Train: [11] [2800/6250] eta: 0:09:24 lr: 0.000124 grad: 0.0689 (0.0698) loss: 0.8478 (0.8483) time: 0.1648 data: 0.0832 max mem: 9390 +Train: [11] [2900/6250] eta: 0:09:07 lr: 0.000124 grad: 0.0675 (0.0698) loss: 0.8451 (0.8483) time: 0.1632 data: 0.0713 max mem: 9390 +Train: [11] [3000/6250] eta: 0:08:50 lr: 0.000124 grad: 0.0684 (0.0697) loss: 0.8456 (0.8483) time: 0.1466 data: 0.0630 max mem: 9390 +Train: [11] [3100/6250] eta: 0:08:33 lr: 0.000124 grad: 0.0635 (0.0696) loss: 0.8468 (0.8483) time: 0.1790 data: 0.0974 max mem: 9390 +Train: [11] [3200/6250] eta: 0:08:16 lr: 0.000124 grad: 0.0662 (0.0694) loss: 0.8480 (0.8483) time: 0.1526 data: 0.0621 max mem: 9390 +Train: [11] [3300/6250] eta: 0:07:59 lr: 0.000124 grad: 0.0622 (0.0693) loss: 0.8491 (0.8483) time: 0.1355 data: 0.0487 max mem: 9390 +Train: [11] [3400/6250] eta: 0:07:43 lr: 0.000124 grad: 0.0657 (0.0692) loss: 0.8422 (0.8483) time: 0.1608 data: 0.0792 max mem: 9390 +Train: [11] [3500/6250] eta: 0:07:26 lr: 0.000124 grad: 0.0700 (0.0692) loss: 0.8474 (0.8483) time: 0.1353 data: 0.0460 max mem: 9390 +Train: [11] [3600/6250] eta: 0:07:10 lr: 0.000124 grad: 0.0631 (0.0690) loss: 0.8561 (0.8483) time: 0.1582 data: 0.0686 max mem: 9390 +Train: [11] [3700/6250] eta: 0:06:54 lr: 0.000124 grad: 0.0654 (0.0690) loss: 0.8460 (0.8482) time: 0.1839 data: 0.1025 max mem: 9390 +Train: [11] [3800/6250] eta: 0:06:37 lr: 0.000124 grad: 0.0613 (0.0689) loss: 0.8466 (0.8482) time: 0.1671 data: 0.0790 max mem: 9390 +Train: [11] [3900/6250] eta: 0:06:21 lr: 0.000124 grad: 0.0656 (0.0689) loss: 0.8444 (0.8482) time: 0.1486 data: 0.0630 max mem: 9390 +Train: [11] [4000/6250] eta: 0:06:04 lr: 0.000123 grad: 0.0688 (0.0689) loss: 0.8440 (0.8481) time: 0.1875 data: 0.1004 max mem: 9390 +Train: [11] [4100/6250] eta: 0:05:48 lr: 0.000123 grad: 0.0648 (0.0688) loss: 0.8470 (0.8481) time: 0.1489 data: 0.0676 max mem: 9390 +Train: [11] [4200/6250] eta: 0:05:32 lr: 0.000123 grad: 0.0652 (0.0688) loss: 0.8469 (0.8481) time: 0.1945 data: 0.1069 max mem: 9390 +Train: [11] [4300/6250] eta: 0:05:15 lr: 0.000123 grad: 0.0652 (0.0688) loss: 0.8471 (0.8480) time: 0.1393 data: 0.0553 max mem: 9390 +Train: [11] [4400/6250] eta: 0:04:59 lr: 0.000123 grad: 0.0626 (0.0688) loss: 0.8479 (0.8480) time: 0.1738 data: 0.0906 max mem: 9390 +Train: [11] [4500/6250] eta: 0:04:43 lr: 0.000123 grad: 0.0655 (0.0687) loss: 0.8462 (0.8480) time: 0.1666 data: 0.0791 max mem: 9390 +Train: [11] [4600/6250] eta: 0:04:27 lr: 0.000123 grad: 0.0671 (0.0687) loss: 0.8475 (0.8480) time: 0.1649 data: 0.0838 max mem: 9390 +Train: [11] [4700/6250] eta: 0:04:10 lr: 0.000123 grad: 0.0657 (0.0686) loss: 0.8461 (0.8480) time: 0.1613 data: 0.0790 max mem: 9390 +Train: [11] [4800/6250] eta: 0:03:54 lr: 0.000123 grad: 0.0621 (0.0686) loss: 0.8484 (0.8480) time: 0.1354 data: 0.0498 max mem: 9390 +Train: [11] [4900/6250] eta: 0:03:38 lr: 0.000123 grad: 0.0627 (0.0685) loss: 0.8509 (0.8480) time: 0.1636 data: 0.0810 max mem: 9390 +Train: [11] [5000/6250] eta: 0:03:22 lr: 0.000123 grad: 0.0632 (0.0685) loss: 0.8464 (0.8480) time: 0.1824 data: 0.0909 max mem: 9390 +Train: [11] [5100/6250] eta: 0:03:05 lr: 0.000123 grad: 0.0669 (0.0685) loss: 0.8466 (0.8480) time: 0.1617 data: 0.0735 max mem: 9390 +Train: [11] [5200/6250] eta: 0:02:49 lr: 0.000123 grad: 0.0652 (0.0684) loss: 0.8453 (0.8480) time: 0.1707 data: 0.0753 max mem: 9390 +Train: [11] [5300/6250] eta: 0:02:33 lr: 0.000123 grad: 0.0686 (0.0685) loss: 0.8532 (0.8480) time: 0.1560 data: 0.0669 max mem: 9390 +Train: [11] [5400/6250] eta: 0:02:17 lr: 0.000123 grad: 0.0656 (0.0684) loss: 0.8476 (0.8480) time: 0.1354 data: 0.0515 max mem: 9390 +Train: [11] [5500/6250] eta: 0:02:01 lr: 0.000123 grad: 0.0614 (0.0684) loss: 0.8474 (0.8481) time: 0.1657 data: 0.0852 max mem: 9390 +Train: [11] [5600/6250] eta: 0:01:45 lr: 0.000123 grad: 0.0629 (0.0684) loss: 0.8483 (0.8481) time: 0.1520 data: 0.0678 max mem: 9390 +Train: [11] [5700/6250] eta: 0:01:28 lr: 0.000123 grad: 0.0638 (0.0684) loss: 0.8498 (0.8481) time: 0.1376 data: 0.0467 max mem: 9390 +Train: [11] [5800/6250] eta: 0:01:12 lr: 0.000123 grad: 0.0621 (0.0683) loss: 0.8506 (0.8481) time: 0.1569 data: 0.0757 max mem: 9390 +Train: [11] [5900/6250] eta: 0:00:56 lr: 0.000123 grad: 0.0642 (0.0683) loss: 0.8475 (0.8481) time: 0.1603 data: 0.0739 max mem: 9390 +Train: [11] [6000/6250] eta: 0:00:40 lr: 0.000123 grad: 0.0628 (0.0682) loss: 0.8508 (0.8482) time: 0.1723 data: 0.0897 max mem: 9390 +Train: [11] [6100/6250] eta: 0:00:24 lr: 0.000123 grad: 0.0670 (0.0683) loss: 0.8426 (0.8481) time: 0.1598 data: 0.0756 max mem: 9390 +Train: [11] [6200/6250] eta: 0:00:08 lr: 0.000123 grad: 0.0695 (0.0683) loss: 0.8483 (0.8481) time: 0.1711 data: 0.0907 max mem: 9390 +Train: [11] [6249/6250] eta: 0:00:00 lr: 0.000123 grad: 0.0700 (0.0683) loss: 0.8459 (0.8481) time: 0.1625 data: 0.0757 max mem: 9390 +Train: [11] Total time: 0:16:52 (0.1620 s / it) +Averaged stats: lr: 0.000123 grad: 0.0700 (0.0683) loss: 0.8459 (0.8481) +Eval (hcp-train-subset): [11] [ 0/62] eta: 0:04:55 loss: 0.8593 (0.8593) time: 4.7607 data: 4.7310 max mem: 9390 +Eval (hcp-train-subset): [11] [61/62] eta: 0:00:00 loss: 0.8525 (0.8531) time: 0.0876 data: 0.0618 max mem: 9390 +Eval (hcp-train-subset): [11] Total time: 0:00:12 (0.2048 s / it) +Averaged stats (hcp-train-subset): loss: 0.8525 (0.8531) +Eval (hcp-val): [11] [ 0/62] eta: 0:03:14 loss: 0.8460 (0.8460) time: 3.1397 data: 3.0706 max mem: 9390 +Eval (hcp-val): [11] [61/62] eta: 0:00:00 loss: 0.8461 (0.8475) time: 0.1133 data: 0.0866 max mem: 9390 +Eval (hcp-val): [11] Total time: 0:00:11 (0.1926 s / it) +Averaged stats (hcp-val): loss: 0.8461 (0.8475) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +Train: [12] [ 0/6250] eta: 8:39:32 lr: 0.000123 grad: 0.0789 (0.0789) loss: 0.8610 (0.8610) time: 4.9875 data: 4.8325 max mem: 9390 +Train: [12] [ 100/6250] eta: 0:20:26 lr: 0.000123 grad: 0.0669 (0.0731) loss: 0.8422 (0.8555) time: 0.1814 data: 0.0946 max mem: 9390 +Train: [12] [ 200/6250] eta: 0:18:19 lr: 0.000123 grad: 0.0632 (0.0704) loss: 0.8497 (0.8514) time: 0.1561 data: 0.0471 max mem: 9390 +Train: [12] [ 300/6250] eta: 0:17:40 lr: 0.000123 grad: 0.0691 (0.0707) loss: 0.8450 (0.8497) time: 0.1793 data: 0.0817 max mem: 9390 +Train: [12] [ 400/6250] eta: 0:16:59 lr: 0.000123 grad: 0.0605 (0.0696) loss: 0.8468 (0.8492) time: 0.1561 data: 0.0555 max mem: 9390 +Train: [12] [ 500/6250] eta: 0:16:24 lr: 0.000123 grad: 0.0660 (0.0690) loss: 0.8485 (0.8494) time: 0.1602 data: 0.0590 max mem: 9390 +Train: [12] [ 600/6250] eta: 0:16:14 lr: 0.000123 grad: 0.0650 (0.0694) loss: 0.8492 (0.8491) time: 0.1959 data: 0.0948 max mem: 9390 +Train: [12] [ 700/6250] eta: 0:15:57 lr: 0.000123 grad: 0.0682 (0.0698) loss: 0.8434 (0.8488) time: 0.1639 data: 0.0687 max mem: 9390 +Train: [12] [ 800/6250] eta: 0:15:43 lr: 0.000123 grad: 0.0694 (0.0698) loss: 0.8446 (0.8485) time: 0.1764 data: 0.0826 max mem: 9390 +Train: [12] [ 900/6250] eta: 0:15:24 lr: 0.000123 grad: 0.0634 (0.0694) loss: 0.8413 (0.8482) time: 0.1849 data: 0.0954 max mem: 9390 +Train: [12] [1000/6250] eta: 0:15:02 lr: 0.000123 grad: 0.0626 (0.0691) loss: 0.8430 (0.8478) time: 0.1762 data: 0.0877 max mem: 9390 +Train: [12] [1100/6250] eta: 0:14:38 lr: 0.000123 grad: 0.0640 (0.0690) loss: 0.8480 (0.8477) time: 0.1649 data: 0.0741 max mem: 9390 +Train: [12] [1200/6250] eta: 0:14:18 lr: 0.000123 grad: 0.0616 (0.0690) loss: 0.8444 (0.8477) time: 0.1483 data: 0.0535 max mem: 9390 +Train: [12] [1300/6250] eta: 0:13:55 lr: 0.000123 grad: 0.0624 (0.0688) loss: 0.8476 (0.8476) time: 0.1575 data: 0.0735 max mem: 9390 +Train: [12] [1400/6250] eta: 0:13:36 lr: 0.000123 grad: 0.0648 (0.0685) loss: 0.8426 (0.8475) time: 0.1527 data: 0.0680 max mem: 9390 +Train: [12] [1500/6250] eta: 0:13:17 lr: 0.000123 grad: 0.0609 (0.0682) loss: 0.8488 (0.8474) time: 0.1560 data: 0.0716 max mem: 9390 +Train: [12] [1600/6250] eta: 0:12:58 lr: 0.000123 grad: 0.0639 (0.0680) loss: 0.8442 (0.8473) time: 0.1523 data: 0.0726 max mem: 9390 +Train: [12] [1700/6250] eta: 0:12:41 lr: 0.000123 grad: 0.0631 (0.0678) loss: 0.8450 (0.8472) time: 0.1704 data: 0.0834 max mem: 9390 +Train: [12] [1800/6250] eta: 0:12:22 lr: 0.000123 grad: 0.0623 (0.0677) loss: 0.8482 (0.8471) time: 0.1582 data: 0.0620 max mem: 9390 +Train: [12] [1900/6250] eta: 0:12:06 lr: 0.000123 grad: 0.0640 (0.0676) loss: 0.8405 (0.8470) time: 0.2054 data: 0.1169 max mem: 9390 +Train: [12] [2000/6250] eta: 0:11:46 lr: 0.000123 grad: 0.0642 (0.0677) loss: 0.8460 (0.8469) time: 0.1711 data: 0.0787 max mem: 9390 +Train: [12] [2100/6250] eta: 0:11:27 lr: 0.000123 grad: 0.0603 (0.0676) loss: 0.8476 (0.8468) time: 0.1660 data: 0.0763 max mem: 9390 +Train: [12] [2200/6250] eta: 0:11:11 lr: 0.000123 grad: 0.0631 (0.0674) loss: 0.8505 (0.8467) time: 0.1551 data: 0.0668 max mem: 9390 +Train: [12] [2300/6250] eta: 0:10:54 lr: 0.000123 grad: 0.0639 (0.0674) loss: 0.8423 (0.8466) time: 0.1333 data: 0.0498 max mem: 9390 +Train: [12] [2400/6250] eta: 0:10:37 lr: 0.000123 grad: 0.0670 (0.0673) loss: 0.8414 (0.8465) time: 0.1680 data: 0.0746 max mem: 9390 +Train: [12] [2500/6250] eta: 0:10:20 lr: 0.000123 grad: 0.0645 (0.0672) loss: 0.8471 (0.8465) time: 0.1510 data: 0.0706 max mem: 9390 +Train: [12] [2600/6250] eta: 0:10:02 lr: 0.000123 grad: 0.0638 (0.0671) loss: 0.8479 (0.8465) time: 0.1473 data: 0.0606 max mem: 9390 +Train: [12] [2700/6250] eta: 0:09:46 lr: 0.000123 grad: 0.0648 (0.0671) loss: 0.8446 (0.8465) time: 0.1625 data: 0.0704 max mem: 9390 +Train: [12] [2800/6250] eta: 0:09:29 lr: 0.000123 grad: 0.0648 (0.0670) loss: 0.8432 (0.8465) time: 0.1750 data: 0.0775 max mem: 9390 +Train: [12] [2900/6250] eta: 0:09:11 lr: 0.000123 grad: 0.0622 (0.0671) loss: 0.8440 (0.8465) time: 0.1557 data: 0.0680 max mem: 9390 +Train: [12] [3000/6250] eta: 0:08:55 lr: 0.000123 grad: 0.0620 (0.0670) loss: 0.8472 (0.8465) time: 0.1853 data: 0.1017 max mem: 9390 +Train: [12] [3100/6250] eta: 0:08:38 lr: 0.000123 grad: 0.0665 (0.0670) loss: 0.8502 (0.8465) time: 0.1756 data: 0.0857 max mem: 9390 +Train: [12] [3200/6250] eta: 0:08:21 lr: 0.000123 grad: 0.0627 (0.0668) loss: 0.8445 (0.8466) time: 0.1724 data: 0.0827 max mem: 9390 +Train: [12] [3300/6250] eta: 0:08:05 lr: 0.000123 grad: 0.0634 (0.0668) loss: 0.8457 (0.8466) time: 0.1700 data: 0.0859 max mem: 9390 +Train: [12] [3400/6250] eta: 0:07:48 lr: 0.000123 grad: 0.0595 (0.0668) loss: 0.8485 (0.8466) time: 0.1686 data: 0.0847 max mem: 9390 +Train: [12] [3500/6250] eta: 0:07:32 lr: 0.000123 grad: 0.0625 (0.0667) loss: 0.8485 (0.8466) time: 0.1788 data: 0.1009 max mem: 9390 +Train: [12] [3600/6250] eta: 0:07:15 lr: 0.000123 grad: 0.0701 (0.0668) loss: 0.8466 (0.8466) time: 0.1619 data: 0.0812 max mem: 9390 +Train: [12] [3700/6250] eta: 0:06:58 lr: 0.000123 grad: 0.0634 (0.0667) loss: 0.8395 (0.8466) time: 0.1662 data: 0.0882 max mem: 9390 +Train: [12] [3800/6250] eta: 0:06:41 lr: 0.000123 grad: 0.0646 (0.0667) loss: 0.8425 (0.8465) time: 0.1717 data: 0.0836 max mem: 9390 +Train: [12] [3900/6250] eta: 0:06:25 lr: 0.000123 grad: 0.0633 (0.0667) loss: 0.8471 (0.8465) time: 0.1603 data: 0.0715 max mem: 9390 +Train: [12] [4000/6250] eta: 0:06:08 lr: 0.000123 grad: 0.0648 (0.0667) loss: 0.8447 (0.8464) time: 0.1590 data: 0.0675 max mem: 9390 +Train: [12] [4100/6250] eta: 0:05:52 lr: 0.000123 grad: 0.0617 (0.0667) loss: 0.8454 (0.8464) time: 0.1733 data: 0.0914 max mem: 9390 +Train: [12] [4200/6250] eta: 0:05:36 lr: 0.000123 grad: 0.0663 (0.0668) loss: 0.8439 (0.8464) time: 0.1784 data: 0.0908 max mem: 9390 +Train: [12] [4300/6250] eta: 0:05:19 lr: 0.000123 grad: 0.0673 (0.0669) loss: 0.8396 (0.8463) time: 0.1535 data: 0.0636 max mem: 9390 +Train: [12] [4400/6250] eta: 0:05:03 lr: 0.000123 grad: 0.0618 (0.0669) loss: 0.8425 (0.8463) time: 0.1808 data: 0.0907 max mem: 9390 +Train: [12] [4500/6250] eta: 0:04:46 lr: 0.000123 grad: 0.0610 (0.0668) loss: 0.8457 (0.8463) time: 0.1637 data: 0.0751 max mem: 9390 +Train: [12] [4600/6250] eta: 0:04:30 lr: 0.000123 grad: 0.0614 (0.0668) loss: 0.8452 (0.8463) time: 0.1523 data: 0.0651 max mem: 9390 +Train: [12] [4700/6250] eta: 0:04:13 lr: 0.000123 grad: 0.0627 (0.0668) loss: 0.8442 (0.8462) time: 0.1586 data: 0.0682 max mem: 9390 +Train: [12] [4800/6250] eta: 0:03:57 lr: 0.000123 grad: 0.0643 (0.0668) loss: 0.8439 (0.8462) time: 0.1731 data: 0.0849 max mem: 9390 +Train: [12] [4900/6250] eta: 0:03:41 lr: 0.000123 grad: 0.0615 (0.0668) loss: 0.8470 (0.8462) time: 0.1465 data: 0.0657 max mem: 9390 +Train: [12] [5000/6250] eta: 0:03:24 lr: 0.000123 grad: 0.0638 (0.0668) loss: 0.8506 (0.8462) time: 0.1615 data: 0.0794 max mem: 9390 +Train: [12] [5100/6250] eta: 0:03:08 lr: 0.000123 grad: 0.0629 (0.0667) loss: 0.8443 (0.8462) time: 0.1511 data: 0.0723 max mem: 9390 +Train: [12] [5200/6250] eta: 0:02:51 lr: 0.000123 grad: 0.0669 (0.0667) loss: 0.8473 (0.8462) time: 0.1744 data: 0.0873 max mem: 9390 +Train: [12] [5300/6250] eta: 0:02:35 lr: 0.000123 grad: 0.0625 (0.0667) loss: 0.8508 (0.8462) time: 0.1747 data: 0.0877 max mem: 9390 +Train: [12] [5400/6250] eta: 0:02:19 lr: 0.000123 grad: 0.0619 (0.0667) loss: 0.8488 (0.8463) time: 0.1595 data: 0.0744 max mem: 9390 +Train: [12] [5500/6250] eta: 0:02:02 lr: 0.000123 grad: 0.0609 (0.0666) loss: 0.8491 (0.8463) time: 0.1576 data: 0.0625 max mem: 9390 +Train: [12] [5600/6250] eta: 0:01:46 lr: 0.000123 grad: 0.0629 (0.0666) loss: 0.8436 (0.8463) time: 0.1788 data: 0.0797 max mem: 9390 +Train: [12] [5700/6250] eta: 0:01:29 lr: 0.000123 grad: 0.0638 (0.0666) loss: 0.8474 (0.8464) time: 0.1538 data: 0.0579 max mem: 9390 +Train: [12] [5800/6250] eta: 0:01:13 lr: 0.000123 grad: 0.0600 (0.0666) loss: 0.8469 (0.8464) time: 0.1545 data: 0.0560 max mem: 9390 +Train: [12] [5900/6250] eta: 0:00:57 lr: 0.000123 grad: 0.0633 (0.0665) loss: 0.8467 (0.8464) time: 0.1405 data: 0.0485 max mem: 9390 +Train: [12] [6000/6250] eta: 0:00:40 lr: 0.000123 grad: 0.0622 (0.0665) loss: 0.8501 (0.8465) time: 0.1672 data: 0.0606 max mem: 9390 +Train: [12] [6100/6250] eta: 0:00:24 lr: 0.000123 grad: 0.0652 (0.0665) loss: 0.8505 (0.8465) time: 0.1657 data: 0.0737 max mem: 9390 +Train: [12] [6200/6250] eta: 0:00:08 lr: 0.000123 grad: 0.0627 (0.0665) loss: 0.8526 (0.8466) time: 0.1619 data: 0.0758 max mem: 9390 +Train: [12] [6249/6250] eta: 0:00:00 lr: 0.000123 grad: 0.0709 (0.0665) loss: 0.8511 (0.8466) time: 0.1872 data: 0.0970 max mem: 9390 +Train: [12] Total time: 0:17:03 (0.1638 s / it) +Averaged stats: lr: 0.000123 grad: 0.0709 (0.0665) loss: 0.8511 (0.8466) +Eval (hcp-train-subset): [12] [ 0/62] eta: 0:03:29 loss: 0.8612 (0.8612) time: 3.3765 data: 3.3100 max mem: 9390 +Eval (hcp-train-subset): [12] [61/62] eta: 0:00:00 loss: 0.8490 (0.8506) time: 0.1322 data: 0.1066 max mem: 9390 +Eval (hcp-train-subset): [12] Total time: 0:00:13 (0.2097 s / it) +Averaged stats (hcp-train-subset): loss: 0.8490 (0.8506) +Eval (hcp-val): [12] [ 0/62] eta: 0:03:43 loss: 0.8429 (0.8429) time: 3.6029 data: 3.5481 max mem: 9390 +Eval (hcp-val): [12] [61/62] eta: 0:00:00 loss: 0.8454 (0.8463) time: 0.1391 data: 0.1133 max mem: 9390 +Eval (hcp-val): [12] Total time: 0:00:13 (0.2114 s / it) +Averaged stats (hcp-val): loss: 0.8454 (0.8463) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +Train: [13] [ 0/6250] eta: 9:05:43 lr: 0.000123 grad: 0.0668 (0.0668) loss: 0.8708 (0.8708) time: 5.2389 data: 5.0826 max mem: 9390 +Train: [13] [ 100/6250] eta: 0:20:22 lr: 0.000123 grad: 0.0707 (0.0723) loss: 0.8471 (0.8450) time: 0.1346 data: 0.0503 max mem: 9390 +Train: [13] [ 200/6250] eta: 0:18:33 lr: 0.000123 grad: 0.0644 (0.0697) loss: 0.8432 (0.8438) time: 0.1664 data: 0.0646 max mem: 9390 +Train: [13] [ 300/6250] eta: 0:17:44 lr: 0.000123 grad: 0.0669 (0.0703) loss: 0.8378 (0.8423) time: 0.1962 data: 0.1060 max mem: 9390 +Train: [13] [ 400/6250] eta: 0:17:02 lr: 0.000123 grad: 0.0643 (0.0700) loss: 0.8488 (0.8427) time: 0.1822 data: 0.0900 max mem: 9390 +Train: [13] [ 500/6250] eta: 0:16:40 lr: 0.000123 grad: 0.0678 (0.0697) loss: 0.8429 (0.8431) time: 0.1474 data: 0.0524 max mem: 9390 +Train: [13] [ 600/6250] eta: 0:16:22 lr: 0.000123 grad: 0.0644 (0.0692) loss: 0.8420 (0.8436) time: 0.1860 data: 0.0918 max mem: 9390 +Train: [13] [ 700/6250] eta: 0:15:57 lr: 0.000123 grad: 0.0628 (0.0690) loss: 0.8452 (0.8440) time: 0.1743 data: 0.0831 max mem: 9390 +Train: [13] [ 800/6250] eta: 0:15:42 lr: 0.000123 grad: 0.0610 (0.0685) loss: 0.8466 (0.8442) time: 0.1896 data: 0.0954 max mem: 9390 +Train: [13] [ 900/6250] eta: 0:15:22 lr: 0.000123 grad: 0.0622 (0.0680) loss: 0.8430 (0.8444) time: 0.1413 data: 0.0458 max mem: 9390 +Train: [13] [1000/6250] eta: 0:15:04 lr: 0.000123 grad: 0.0635 (0.0678) loss: 0.8471 (0.8446) time: 0.1775 data: 0.0878 max mem: 9390 +Train: [13] [1100/6250] eta: 0:14:38 lr: 0.000123 grad: 0.0645 (0.0675) loss: 0.8451 (0.8446) time: 0.1449 data: 0.0546 max mem: 9390 +Train: [13] [1200/6250] eta: 0:14:14 lr: 0.000123 grad: 0.0629 (0.0673) loss: 0.8440 (0.8447) time: 0.1513 data: 0.0531 max mem: 9390 +Train: [13] [1300/6250] eta: 0:13:55 lr: 0.000123 grad: 0.0607 (0.0672) loss: 0.8454 (0.8447) time: 0.1659 data: 0.0805 max mem: 9390 +Train: [13] [1400/6250] eta: 0:13:34 lr: 0.000123 grad: 0.0588 (0.0675) loss: 0.8447 (0.8447) time: 0.1709 data: 0.0817 max mem: 9390 +Train: [13] [1500/6250] eta: 0:13:14 lr: 0.000123 grad: 0.0618 (0.0674) loss: 0.8434 (0.8447) time: 0.1526 data: 0.0660 max mem: 9390 +Train: [13] [1600/6250] eta: 0:12:55 lr: 0.000123 grad: 0.0655 (0.0674) loss: 0.8415 (0.8446) time: 0.1559 data: 0.0708 max mem: 9390 +Train: [13] [1700/6250] eta: 0:12:37 lr: 0.000123 grad: 0.0628 (0.0672) loss: 0.8467 (0.8447) time: 0.1520 data: 0.0610 max mem: 9390 +Train: [13] [1800/6250] eta: 0:12:19 lr: 0.000123 grad: 0.0647 (0.0672) loss: 0.8460 (0.8448) time: 0.1673 data: 0.0787 max mem: 9390 +Train: [13] [1900/6250] eta: 0:12:02 lr: 0.000123 grad: 0.0671 (0.0671) loss: 0.8440 (0.8448) time: 0.1636 data: 0.0762 max mem: 9390 +Train: [13] [2000/6250] eta: 0:11:45 lr: 0.000123 grad: 0.0638 (0.0671) loss: 0.8466 (0.8447) time: 0.1637 data: 0.0721 max mem: 9390 +Train: [13] [2100/6250] eta: 0:11:27 lr: 0.000123 grad: 0.0662 (0.0670) loss: 0.8439 (0.8447) time: 0.1506 data: 0.0628 max mem: 9390 +Train: [13] [2200/6250] eta: 0:11:09 lr: 0.000123 grad: 0.0612 (0.0670) loss: 0.8434 (0.8447) time: 0.1235 data: 0.0382 max mem: 9390 +Train: [13] [2300/6250] eta: 0:10:53 lr: 0.000123 grad: 0.0662 (0.0670) loss: 0.8466 (0.8447) time: 0.1599 data: 0.0707 max mem: 9390 +Train: [13] [2400/6250] eta: 0:10:36 lr: 0.000123 grad: 0.0640 (0.0669) loss: 0.8475 (0.8448) time: 0.1788 data: 0.0916 max mem: 9390 +Train: [13] [2500/6250] eta: 0:10:18 lr: 0.000123 grad: 0.0635 (0.0668) loss: 0.8425 (0.8448) time: 0.1606 data: 0.0712 max mem: 9390 +Train: [13] [2600/6250] eta: 0:10:01 lr: 0.000123 grad: 0.0692 (0.0668) loss: 0.8457 (0.8449) time: 0.1544 data: 0.0659 max mem: 9390 +Train: [13] [2700/6250] eta: 0:09:44 lr: 0.000123 grad: 0.0657 (0.0668) loss: 0.8437 (0.8448) time: 0.1495 data: 0.0646 max mem: 9390 +Train: [13] [2800/6250] eta: 0:09:27 lr: 0.000123 grad: 0.0655 (0.0668) loss: 0.8440 (0.8448) time: 0.1645 data: 0.0729 max mem: 9390 +Train: [13] [2900/6250] eta: 0:09:11 lr: 0.000123 grad: 0.0642 (0.0668) loss: 0.8462 (0.8448) time: 0.1393 data: 0.0582 max mem: 9390 +Train: [13] [3000/6250] eta: 0:08:54 lr: 0.000123 grad: 0.0624 (0.0667) loss: 0.8456 (0.8448) time: 0.1537 data: 0.0655 max mem: 9390 +Train: [13] [3100/6250] eta: 0:08:37 lr: 0.000123 grad: 0.0600 (0.0667) loss: 0.8448 (0.8448) time: 0.1527 data: 0.0592 max mem: 9390 +Train: [13] [3200/6250] eta: 0:08:21 lr: 0.000123 grad: 0.0674 (0.0666) loss: 0.8447 (0.8449) time: 0.1551 data: 0.0646 max mem: 9390 +Train: [13] [3300/6250] eta: 0:08:05 lr: 0.000123 grad: 0.0655 (0.0666) loss: 0.8486 (0.8449) time: 0.1582 data: 0.0682 max mem: 9390 +Train: [13] [3400/6250] eta: 0:07:48 lr: 0.000123 grad: 0.0618 (0.0665) loss: 0.8462 (0.8449) time: 0.1512 data: 0.0631 max mem: 9390 +Train: [13] [3500/6250] eta: 0:07:31 lr: 0.000123 grad: 0.0612 (0.0664) loss: 0.8465 (0.8450) time: 0.1379 data: 0.0521 max mem: 9390 +Train: [13] [3600/6250] eta: 0:07:15 lr: 0.000123 grad: 0.0634 (0.0665) loss: 0.8461 (0.8450) time: 0.1653 data: 0.0760 max mem: 9390 +Train: [13] [3700/6250] eta: 0:06:58 lr: 0.000122 grad: 0.0632 (0.0664) loss: 0.8494 (0.8450) time: 0.1709 data: 0.0822 max mem: 9390 +Train: [13] [3800/6250] eta: 0:06:42 lr: 0.000122 grad: 0.0664 (0.0664) loss: 0.8463 (0.8450) time: 0.1552 data: 0.0656 max mem: 9390 +Train: [13] [3900/6250] eta: 0:06:25 lr: 0.000122 grad: 0.0628 (0.0664) loss: 0.8470 (0.8450) time: 0.1733 data: 0.0917 max mem: 9390 +Train: [13] [4000/6250] eta: 0:06:09 lr: 0.000122 grad: 0.0689 (0.0665) loss: 0.8436 (0.8450) time: 0.1880 data: 0.0992 max mem: 9390 +Train: [13] [4100/6250] eta: 0:05:53 lr: 0.000122 grad: 0.0629 (0.0665) loss: 0.8433 (0.8449) time: 0.1308 data: 0.0475 max mem: 9390 +Train: [13] [4200/6250] eta: 0:05:36 lr: 0.000122 grad: 0.0635 (0.0665) loss: 0.8494 (0.8450) time: 0.1756 data: 0.0841 max mem: 9390 +Train: [13] [4300/6250] eta: 0:05:20 lr: 0.000122 grad: 0.0609 (0.0664) loss: 0.8420 (0.8449) time: 0.1428 data: 0.0520 max mem: 9390 +Train: [13] [4400/6250] eta: 0:05:04 lr: 0.000122 grad: 0.0637 (0.0664) loss: 0.8430 (0.8449) time: 0.1530 data: 0.0650 max mem: 9390 +Train: [13] [4500/6250] eta: 0:04:47 lr: 0.000122 grad: 0.0620 (0.0664) loss: 0.8487 (0.8450) time: 0.1537 data: 0.0661 max mem: 9390 +Train: [13] [4600/6250] eta: 0:04:31 lr: 0.000122 grad: 0.0611 (0.0663) loss: 0.8442 (0.8450) time: 0.1554 data: 0.0746 max mem: 9390 +Train: [13] [4700/6250] eta: 0:04:14 lr: 0.000122 grad: 0.0613 (0.0663) loss: 0.8455 (0.8450) time: 0.1520 data: 0.0630 max mem: 9390 +Train: [13] [4800/6250] eta: 0:03:58 lr: 0.000122 grad: 0.0634 (0.0663) loss: 0.8493 (0.8451) time: 0.1739 data: 0.0884 max mem: 9390 +Train: [13] [4900/6250] eta: 0:03:41 lr: 0.000122 grad: 0.0616 (0.0663) loss: 0.8470 (0.8451) time: 0.1496 data: 0.0622 max mem: 9390 +Train: [13] [5000/6250] eta: 0:03:25 lr: 0.000122 grad: 0.0613 (0.0663) loss: 0.8510 (0.8451) time: 0.1881 data: 0.1005 max mem: 9390 +Train: [13] [5100/6250] eta: 0:03:09 lr: 0.000122 grad: 0.0655 (0.0664) loss: 0.8456 (0.8451) time: 0.1696 data: 0.0834 max mem: 9390 +Train: [13] [5200/6250] eta: 0:02:52 lr: 0.000122 grad: 0.0583 (0.0664) loss: 0.8456 (0.8452) time: 0.1726 data: 0.0889 max mem: 9390 +Train: [13] [5300/6250] eta: 0:02:36 lr: 0.000122 grad: 0.0597 (0.0663) loss: 0.8505 (0.8452) time: 0.1685 data: 0.0840 max mem: 9390 +Train: [13] [5400/6250] eta: 0:02:19 lr: 0.000122 grad: 0.0612 (0.0663) loss: 0.8462 (0.8452) time: 0.1695 data: 0.0864 max mem: 9390 +Train: [13] [5500/6250] eta: 0:02:03 lr: 0.000122 grad: 0.0642 (0.0662) loss: 0.8447 (0.8452) time: 0.1520 data: 0.0545 max mem: 9390 +Train: [13] [5600/6250] eta: 0:01:46 lr: 0.000122 grad: 0.0622 (0.0662) loss: 0.8478 (0.8452) time: 0.1472 data: 0.0568 max mem: 9390 +Train: [13] [5700/6250] eta: 0:01:30 lr: 0.000122 grad: 0.0656 (0.0662) loss: 0.8408 (0.8452) time: 0.1513 data: 0.0688 max mem: 9390 +Train: [13] [5800/6250] eta: 0:01:13 lr: 0.000122 grad: 0.0662 (0.0662) loss: 0.8440 (0.8452) time: 0.1595 data: 0.0705 max mem: 9390 +Train: [13] [5900/6250] eta: 0:00:57 lr: 0.000122 grad: 0.0619 (0.0662) loss: 0.8443 (0.8452) time: 0.1804 data: 0.0997 max mem: 9390 +Train: [13] [6000/6250] eta: 0:00:41 lr: 0.000122 grad: 0.0629 (0.0663) loss: 0.8454 (0.8452) time: 0.1690 data: 0.0745 max mem: 9390 +Train: [13] [6100/6250] eta: 0:00:24 lr: 0.000122 grad: 0.0614 (0.0663) loss: 0.8465 (0.8451) time: 0.1619 data: 0.0705 max mem: 9390 +Train: [13] [6200/6250] eta: 0:00:08 lr: 0.000122 grad: 0.0652 (0.0663) loss: 0.8454 (0.8451) time: 0.1523 data: 0.0686 max mem: 9390 +Train: [13] [6249/6250] eta: 0:00:00 lr: 0.000122 grad: 0.0608 (0.0663) loss: 0.8476 (0.8451) time: 0.1532 data: 0.0681 max mem: 9390 +Train: [13] Total time: 0:17:12 (0.1653 s / it) +Averaged stats: lr: 0.000122 grad: 0.0608 (0.0663) loss: 0.8476 (0.8451) +Eval (hcp-train-subset): [13] [ 0/62] eta: 0:03:43 loss: 0.8601 (0.8601) time: 3.6110 data: 3.5236 max mem: 9390 +Eval (hcp-train-subset): [13] [61/62] eta: 0:00:00 loss: 0.8491 (0.8499) time: 0.1384 data: 0.1126 max mem: 9390 +Eval (hcp-train-subset): [13] Total time: 0:00:12 (0.2068 s / it) +Averaged stats (hcp-train-subset): loss: 0.8491 (0.8499) +Eval (hcp-val): [13] [ 0/62] eta: 0:04:48 loss: 0.8430 (0.8430) time: 4.6491 data: 4.6199 max mem: 9390 +Eval (hcp-val): [13] [61/62] eta: 0:00:00 loss: 0.8461 (0.8452) time: 0.1418 data: 0.1164 max mem: 9390 +Eval (hcp-val): [13] Total time: 0:00:13 (0.2146 s / it) +Averaged stats (hcp-val): loss: 0.8461 (0.8452) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +Train: [14] [ 0/6250] eta: 8:37:29 lr: 0.000122 grad: 0.0923 (0.0923) loss: 0.8680 (0.8680) time: 4.9680 data: 4.7039 max mem: 9390 +Train: [14] [ 100/6250] eta: 0:22:08 lr: 0.000122 grad: 0.0682 (0.0777) loss: 0.8493 (0.8489) time: 0.1951 data: 0.1046 max mem: 9390 +Train: [14] [ 200/6250] eta: 0:19:31 lr: 0.000122 grad: 0.0704 (0.0751) loss: 0.8428 (0.8484) time: 0.1300 data: 0.0259 max mem: 9390 +Train: [14] [ 300/6250] eta: 0:18:17 lr: 0.000122 grad: 0.0651 (0.0746) loss: 0.8514 (0.8470) time: 0.1915 data: 0.0962 max mem: 9390 +Train: [14] [ 400/6250] eta: 0:17:31 lr: 0.000122 grad: 0.0630 (0.0739) loss: 0.8458 (0.8456) time: 0.1640 data: 0.0624 max mem: 9390 +Train: [14] [ 500/6250] eta: 0:16:54 lr: 0.000122 grad: 0.0605 (0.0725) loss: 0.8429 (0.8447) time: 0.1403 data: 0.0445 max mem: 9390 +Train: [14] [ 600/6250] eta: 0:16:28 lr: 0.000122 grad: 0.0671 (0.0715) loss: 0.8404 (0.8443) time: 0.1730 data: 0.0804 max mem: 9390 +Train: [14] [ 700/6250] eta: 0:16:04 lr: 0.000122 grad: 0.0659 (0.0711) loss: 0.8417 (0.8441) time: 0.1646 data: 0.0703 max mem: 9390 +Train: [14] [ 800/6250] eta: 0:15:47 lr: 0.000122 grad: 0.0655 (0.0704) loss: 0.8476 (0.8442) time: 0.1766 data: 0.0894 max mem: 9390 +Train: [14] [ 900/6250] eta: 0:15:29 lr: 0.000122 grad: 0.0621 (0.0698) loss: 0.8455 (0.8446) time: 0.1784 data: 0.0783 max mem: 9390 +Train: [14] [1000/6250] eta: 0:15:08 lr: 0.000122 grad: 0.0621 (0.0691) loss: 0.8420 (0.8448) time: 0.1610 data: 0.0700 max mem: 9390 +Train: [14] [1100/6250] eta: 0:14:46 lr: 0.000122 grad: 0.0588 (0.0689) loss: 0.8473 (0.8450) time: 0.1617 data: 0.0748 max mem: 9390 +Train: [14] [1200/6250] eta: 0:14:27 lr: 0.000122 grad: 0.0638 (0.0686) loss: 0.8482 (0.8452) time: 0.1759 data: 0.0939 max mem: 9390 +Train: [14] [1300/6250] eta: 0:14:05 lr: 0.000122 grad: 0.0635 (0.0687) loss: 0.8454 (0.8451) time: 0.1593 data: 0.0688 max mem: 9390 +Train: [14] [1400/6250] eta: 0:13:47 lr: 0.000122 grad: 0.0669 (0.0686) loss: 0.8475 (0.8452) time: 0.1711 data: 0.0887 max mem: 9390 +Train: [14] [1500/6250] eta: 0:13:27 lr: 0.000122 grad: 0.0629 (0.0684) loss: 0.8418 (0.8452) time: 0.1541 data: 0.0649 max mem: 9390 +Train: [14] [1600/6250] eta: 0:13:07 lr: 0.000122 grad: 0.0658 (0.0681) loss: 0.8440 (0.8453) time: 0.1648 data: 0.0711 max mem: 9390 +Train: [14] [1700/6250] eta: 0:12:48 lr: 0.000122 grad: 0.0631 (0.0680) loss: 0.8452 (0.8452) time: 0.1802 data: 0.0917 max mem: 9390 +Train: [14] [1800/6250] eta: 0:12:29 lr: 0.000122 grad: 0.0620 (0.0677) loss: 0.8457 (0.8451) time: 0.1675 data: 0.0865 max mem: 9390 +Train: [14] [1900/6250] eta: 0:12:11 lr: 0.000122 grad: 0.0643 (0.0676) loss: 0.8439 (0.8449) time: 0.1341 data: 0.0446 max mem: 9390 +Train: [14] [2000/6250] eta: 0:11:53 lr: 0.000122 grad: 0.0781 (0.0679) loss: 0.8446 (0.8449) time: 0.1510 data: 0.0637 max mem: 9390 +Train: [14] [2100/6250] eta: 0:11:36 lr: 0.000122 grad: 0.0636 (0.0678) loss: 0.8436 (0.8448) time: 0.1692 data: 0.0823 max mem: 9390 +Train: [14] [2200/6250] eta: 0:11:18 lr: 0.000122 grad: 0.0635 (0.0676) loss: 0.8415 (0.8448) time: 0.1767 data: 0.0953 max mem: 9390 +Train: [14] [2300/6250] eta: 0:10:59 lr: 0.000122 grad: 0.0647 (0.0675) loss: 0.8459 (0.8446) time: 0.1480 data: 0.0554 max mem: 9390 +Train: [14] [2400/6250] eta: 0:10:42 lr: 0.000122 grad: 0.0640 (0.0674) loss: 0.8487 (0.8445) time: 0.1750 data: 0.0884 max mem: 9390 +Train: [14] [2500/6250] eta: 0:10:26 lr: 0.000122 grad: 0.0593 (0.0675) loss: 0.8444 (0.8444) time: 0.1769 data: 0.0811 max mem: 9390 +Train: [14] [2600/6250] eta: 0:10:08 lr: 0.000122 grad: 0.0602 (0.0675) loss: 0.8431 (0.8444) time: 0.1457 data: 0.0675 max mem: 9390 +Train: [14] [2700/6250] eta: 0:09:50 lr: 0.000122 grad: 0.0659 (0.0676) loss: 0.8434 (0.8443) time: 0.1689 data: 0.0811 max mem: 9390 +Train: [14] [2800/6250] eta: 0:09:33 lr: 0.000122 grad: 0.0701 (0.0676) loss: 0.8407 (0.8442) time: 0.1291 data: 0.0312 max mem: 9390 +Train: [14] [2900/6250] eta: 0:09:17 lr: 0.000122 grad: 0.0616 (0.0676) loss: 0.8447 (0.8441) time: 0.2008 data: 0.1174 max mem: 9390 +Train: [14] [3000/6250] eta: 0:09:00 lr: 0.000122 grad: 0.0628 (0.0675) loss: 0.8421 (0.8441) time: 0.1658 data: 0.0791 max mem: 9390 +Train: [14] [3100/6250] eta: 0:08:43 lr: 0.000122 grad: 0.0636 (0.0676) loss: 0.8437 (0.8440) time: 0.1493 data: 0.0625 max mem: 9390 +Train: [14] [3200/6250] eta: 0:08:26 lr: 0.000122 grad: 0.0650 (0.0676) loss: 0.8458 (0.8440) time: 0.1728 data: 0.0839 max mem: 9390 +Train: [14] [3300/6250] eta: 0:08:10 lr: 0.000122 grad: 0.0641 (0.0676) loss: 0.8445 (0.8441) time: 0.1764 data: 0.0867 max mem: 9390 +Train: [14] [3400/6250] eta: 0:07:53 lr: 0.000122 grad: 0.0666 (0.0677) loss: 0.8381 (0.8441) time: 0.1703 data: 0.0758 max mem: 9390 +Train: [14] [3500/6250] eta: 0:07:36 lr: 0.000122 grad: 0.0694 (0.0678) loss: 0.8449 (0.8440) time: 0.1756 data: 0.0831 max mem: 9390 +Train: [14] [3600/6250] eta: 0:07:18 lr: 0.000122 grad: 0.0610 (0.0678) loss: 0.8448 (0.8441) time: 0.1501 data: 0.0576 max mem: 9390 +Train: [14] [3700/6250] eta: 0:07:02 lr: 0.000122 grad: 0.0641 (0.0677) loss: 0.8459 (0.8441) time: 0.1731 data: 0.0962 max mem: 9390 +Train: [14] [3800/6250] eta: 0:06:46 lr: 0.000122 grad: 0.0610 (0.0676) loss: 0.8472 (0.8441) time: 0.1808 data: 0.0910 max mem: 9390 +Train: [14] [3900/6250] eta: 0:06:29 lr: 0.000122 grad: 0.0671 (0.0676) loss: 0.8438 (0.8441) time: 0.1640 data: 0.0766 max mem: 9390 +Train: [14] [4000/6250] eta: 0:06:12 lr: 0.000122 grad: 0.0606 (0.0675) loss: 0.8422 (0.8441) time: 0.1479 data: 0.0593 max mem: 9390 +Train: [14] [4100/6250] eta: 0:05:55 lr: 0.000122 grad: 0.0632 (0.0675) loss: 0.8456 (0.8441) time: 0.1886 data: 0.1023 max mem: 9390 +Train: [14] [4200/6250] eta: 0:05:38 lr: 0.000122 grad: 0.0657 (0.0675) loss: 0.8457 (0.8441) time: 0.1455 data: 0.0540 max mem: 9390 +Train: [14] [4300/6250] eta: 0:05:22 lr: 0.000122 grad: 0.0680 (0.0675) loss: 0.8406 (0.8441) time: 0.1730 data: 0.0789 max mem: 9390 +Train: [14] [4400/6250] eta: 0:05:06 lr: 0.000122 grad: 0.0627 (0.0675) loss: 0.8503 (0.8442) time: 0.1929 data: 0.1030 max mem: 9390 +Train: [14] [4500/6250] eta: 0:04:49 lr: 0.000122 grad: 0.0601 (0.0674) loss: 0.8500 (0.8442) time: 0.1708 data: 0.0734 max mem: 9390 +Train: [14] [4600/6250] eta: 0:04:32 lr: 0.000122 grad: 0.0640 (0.0674) loss: 0.8517 (0.8442) time: 0.1661 data: 0.0577 max mem: 9390 +Train: [14] [4700/6250] eta: 0:04:15 lr: 0.000122 grad: 0.0639 (0.0674) loss: 0.8478 (0.8442) time: 0.1556 data: 0.0638 max mem: 9390 +Train: [14] [4800/6250] eta: 0:03:58 lr: 0.000122 grad: 0.0659 (0.0674) loss: 0.8433 (0.8442) time: 0.1589 data: 0.0591 max mem: 9390 +Train: [14] [4900/6250] eta: 0:03:42 lr: 0.000122 grad: 0.0602 (0.0673) loss: 0.8462 (0.8443) time: 0.1498 data: 0.0556 max mem: 9390 +Train: [14] [5000/6250] eta: 0:03:25 lr: 0.000122 grad: 0.0662 (0.0674) loss: 0.8419 (0.8443) time: 0.1710 data: 0.0801 max mem: 9390 +Train: [14] [5100/6250] eta: 0:03:09 lr: 0.000122 grad: 0.0625 (0.0673) loss: 0.8389 (0.8442) time: 0.1332 data: 0.0444 max mem: 9390 +Train: [14] [5200/6250] eta: 0:02:52 lr: 0.000122 grad: 0.0637 (0.0672) loss: 0.8411 (0.8442) time: 0.1353 data: 0.0538 max mem: 9390 +Train: [14] [5300/6250] eta: 0:02:36 lr: 0.000122 grad: 0.0619 (0.0672) loss: 0.8488 (0.8442) time: 0.1776 data: 0.0923 max mem: 9390 +Train: [14] [5400/6250] eta: 0:02:20 lr: 0.000122 grad: 0.0646 (0.0671) loss: 0.8433 (0.8442) time: 0.1572 data: 0.0678 max mem: 9390 +Train: [14] [5500/6250] eta: 0:02:03 lr: 0.000122 grad: 0.0682 (0.0671) loss: 0.8462 (0.8441) time: 0.1646 data: 0.0772 max mem: 9390 +Train: [14] [5600/6250] eta: 0:01:47 lr: 0.000122 grad: 0.0658 (0.0671) loss: 0.8433 (0.8441) time: 0.1451 data: 0.0460 max mem: 9390 +Train: [14] [5700/6250] eta: 0:01:30 lr: 0.000122 grad: 0.0657 (0.0671) loss: 0.8429 (0.8441) time: 0.1701 data: 0.0853 max mem: 9390 +Train: [14] [5800/6250] eta: 0:01:14 lr: 0.000122 grad: 0.0659 (0.0672) loss: 0.8422 (0.8441) time: 0.1615 data: 0.0767 max mem: 9390 +Train: [14] [5900/6250] eta: 0:00:57 lr: 0.000122 grad: 0.0675 (0.0672) loss: 0.8428 (0.8441) time: 0.1559 data: 0.0739 max mem: 9390 +Train: [14] [6000/6250] eta: 0:00:41 lr: 0.000122 grad: 0.0608 (0.0672) loss: 0.8425 (0.8440) time: 0.1684 data: 0.0767 max mem: 9390 +Train: [14] [6100/6250] eta: 0:00:24 lr: 0.000122 grad: 0.0625 (0.0671) loss: 0.8443 (0.8440) time: 0.1707 data: 0.0792 max mem: 9390 +Train: [14] [6200/6250] eta: 0:00:08 lr: 0.000122 grad: 0.0610 (0.0671) loss: 0.8424 (0.8440) time: 0.1572 data: 0.0640 max mem: 9390 +Train: [14] [6249/6250] eta: 0:00:00 lr: 0.000122 grad: 0.0648 (0.0671) loss: 0.8463 (0.8440) time: 0.1620 data: 0.0750 max mem: 9390 +Train: [14] Total time: 0:17:13 (0.1654 s / it) +Averaged stats: lr: 0.000122 grad: 0.0648 (0.0671) loss: 0.8463 (0.8440) +Eval (hcp-train-subset): [14] [ 0/62] eta: 0:04:16 loss: 0.8598 (0.8598) time: 4.1432 data: 4.1111 max mem: 9390 +Eval (hcp-train-subset): [14] [61/62] eta: 0:00:00 loss: 0.8484 (0.8493) time: 0.1322 data: 0.1044 max mem: 9390 +Eval (hcp-train-subset): [14] Total time: 0:00:13 (0.2149 s / it) +Averaged stats (hcp-train-subset): loss: 0.8484 (0.8493) +Making plots (hcp-train-subset): example=53 +Eval (hcp-val): [14] [ 0/62] eta: 0:04:58 loss: 0.8389 (0.8389) time: 4.8068 data: 4.7720 max mem: 9390 +Eval (hcp-val): [14] [61/62] eta: 0:00:00 loss: 0.8449 (0.8444) time: 0.1323 data: 0.1054 max mem: 9390 +Eval (hcp-val): [14] Total time: 0:00:13 (0.2178 s / it) +Averaged stats (hcp-val): loss: 0.8449 (0.8444) +Making plots (hcp-val): example=54 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +Train: [15] [ 0/6250] eta: 10:35:43 lr: 0.000122 grad: 0.0760 (0.0760) loss: 0.8777 (0.8777) time: 6.1029 data: 6.0000 max mem: 9390 +Train: [15] [ 100/6250] eta: 0:22:00 lr: 0.000122 grad: 0.0601 (0.0719) loss: 0.8483 (0.8488) time: 0.1812 data: 0.0938 max mem: 9390 +Train: [15] [ 200/6250] eta: 0:19:23 lr: 0.000122 grad: 0.0699 (0.0695) loss: 0.8350 (0.8463) time: 0.1549 data: 0.0642 max mem: 9390 +Train: [15] [ 300/6250] eta: 0:18:21 lr: 0.000122 grad: 0.0692 (0.0687) loss: 0.8393 (0.8446) time: 0.1729 data: 0.0754 max mem: 9390 +Train: [15] [ 400/6250] eta: 0:17:28 lr: 0.000122 grad: 0.0714 (0.0694) loss: 0.8402 (0.8435) time: 0.1660 data: 0.0770 max mem: 9390 +Train: [15] [ 500/6250] eta: 0:16:50 lr: 0.000122 grad: 0.0635 (0.0692) loss: 0.8359 (0.8426) time: 0.1736 data: 0.0774 max mem: 9390 +Train: [15] [ 600/6250] eta: 0:16:20 lr: 0.000122 grad: 0.0615 (0.0691) loss: 0.8411 (0.8421) time: 0.1647 data: 0.0668 max mem: 9390 +Train: [15] [ 700/6250] eta: 0:16:08 lr: 0.000122 grad: 0.0639 (0.0686) loss: 0.8443 (0.8417) time: 0.2041 data: 0.1160 max mem: 9390 +Train: [15] [ 800/6250] eta: 0:15:46 lr: 0.000122 grad: 0.0679 (0.0686) loss: 0.8394 (0.8411) time: 0.1858 data: 0.0907 max mem: 9390 +Train: [15] [ 900/6250] eta: 0:15:29 lr: 0.000122 grad: 0.0596 (0.0683) loss: 0.8404 (0.8410) time: 0.1389 data: 0.0479 max mem: 9390 +Train: [15] [1000/6250] eta: 0:15:03 lr: 0.000122 grad: 0.0651 (0.0680) loss: 0.8444 (0.8409) time: 0.1441 data: 0.0532 max mem: 9390 +Train: [15] [1100/6250] eta: 0:14:44 lr: 0.000121 grad: 0.0641 (0.0679) loss: 0.8426 (0.8408) time: 0.1659 data: 0.0727 max mem: 9390 +Train: [15] [1200/6250] eta: 0:14:24 lr: 0.000121 grad: 0.0628 (0.0680) loss: 0.8375 (0.8407) time: 0.1604 data: 0.0699 max mem: 9390 +Train: [15] [1300/6250] eta: 0:14:04 lr: 0.000121 grad: 0.0670 (0.0682) loss: 0.8373 (0.8405) time: 0.1604 data: 0.0736 max mem: 9390 +Train: [15] [1400/6250] eta: 0:13:42 lr: 0.000121 grad: 0.0632 (0.0683) loss: 0.8435 (0.8405) time: 0.1495 data: 0.0514 max mem: 9390 +Train: [15] [1500/6250] eta: 0:13:22 lr: 0.000121 grad: 0.0593 (0.0681) loss: 0.8477 (0.8404) time: 0.1673 data: 0.0755 max mem: 9390 +Train: [15] [1600/6250] eta: 0:13:03 lr: 0.000121 grad: 0.0636 (0.0679) loss: 0.8377 (0.8404) time: 0.1634 data: 0.0853 max mem: 9390 +Train: [15] [1700/6250] eta: 0:12:45 lr: 0.000121 grad: 0.0658 (0.0679) loss: 0.8457 (0.8403) time: 0.1687 data: 0.0843 max mem: 9390 +Train: [15] [1800/6250] eta: 0:12:27 lr: 0.000121 grad: 0.0620 (0.0679) loss: 0.8351 (0.8403) time: 0.1540 data: 0.0638 max mem: 9390 +Train: [15] [1900/6250] eta: 0:12:08 lr: 0.000121 grad: 0.0668 (0.0680) loss: 0.8334 (0.8401) time: 0.1662 data: 0.0775 max mem: 9390 +Train: [15] [2000/6250] eta: 0:11:51 lr: 0.000121 grad: 0.0692 (0.0680) loss: 0.8387 (0.8400) time: 0.1700 data: 0.0829 max mem: 9390 +Train: [15] [2100/6250] eta: 0:11:35 lr: 0.000121 grad: 0.0667 (0.0679) loss: 0.8378 (0.8400) time: 0.1369 data: 0.0488 max mem: 9390 +Train: [15] [2200/6250] eta: 0:11:17 lr: 0.000121 grad: 0.0707 (0.0692) loss: 0.8368 (0.8398) time: 0.1616 data: 0.0722 max mem: 9390 +Train: [15] [2300/6250] eta: 0:11:00 lr: 0.000121 grad: 0.0655 (0.0692) loss: 0.8394 (0.8397) time: 0.1522 data: 0.0697 max mem: 9390 +Train: [15] [2400/6250] eta: 0:10:43 lr: 0.000121 grad: 0.0690 (0.0692) loss: 0.8398 (0.8396) time: 0.1606 data: 0.0681 max mem: 9390 +Train: [15] [2500/6250] eta: 0:10:26 lr: 0.000121 grad: 0.0678 (0.0693) loss: 0.8413 (0.8396) time: 0.1522 data: 0.0706 max mem: 9390 +Train: [15] [2600/6250] eta: 0:10:09 lr: 0.000121 grad: 0.0666 (0.0693) loss: 0.8396 (0.8396) time: 0.1977 data: 0.1036 max mem: 9390 +Train: [15] [2700/6250] eta: 0:09:50 lr: 0.000121 grad: 0.0654 (0.0693) loss: 0.8353 (0.8395) time: 0.1668 data: 0.0737 max mem: 9390 +Train: [15] [2800/6250] eta: 0:09:33 lr: 0.000121 grad: 0.0692 (0.0694) loss: 0.8363 (0.8395) time: 0.1621 data: 0.0733 max mem: 9390 +Train: [15] [2900/6250] eta: 0:09:16 lr: 0.000121 grad: 0.0661 (0.0694) loss: 0.8427 (0.8395) time: 0.1699 data: 0.0887 max mem: 9390 +Train: [15] [3000/6250] eta: 0:09:00 lr: 0.000121 grad: 0.0635 (0.0693) loss: 0.8401 (0.8394) time: 0.1848 data: 0.0981 max mem: 9390 +Train: [15] [3100/6250] eta: 0:08:43 lr: 0.000121 grad: 0.0679 (0.0693) loss: 0.8411 (0.8395) time: 0.1827 data: 0.0953 max mem: 9390 +Train: [15] [3200/6250] eta: 0:08:26 lr: 0.000121 grad: 0.0636 (0.0692) loss: 0.8415 (0.8395) time: 0.1475 data: 0.0535 max mem: 9390 +Train: [15] [3300/6250] eta: 0:08:09 lr: 0.000121 grad: 0.0653 (0.0692) loss: 0.8429 (0.8395) time: 0.1523 data: 0.0634 max mem: 9390 +Train: [15] [3400/6250] eta: 0:07:52 lr: 0.000121 grad: 0.0704 (0.0692) loss: 0.8364 (0.8395) time: 0.1678 data: 0.0789 max mem: 9390 +Train: [15] [3500/6250] eta: 0:07:36 lr: 0.000121 grad: 0.0660 (0.0692) loss: 0.8409 (0.8395) time: 0.1875 data: 0.1050 max mem: 9390 +Train: [15] [3600/6250] eta: 0:07:19 lr: 0.000121 grad: 0.0620 (0.0691) loss: 0.8387 (0.8395) time: 0.1629 data: 0.0711 max mem: 9390 +Train: [15] [3700/6250] eta: 0:07:02 lr: 0.000121 grad: 0.0666 (0.0690) loss: 0.8361 (0.8394) time: 0.1889 data: 0.1126 max mem: 9390 +Train: [15] [3800/6250] eta: 0:06:46 lr: 0.000121 grad: 0.0658 (0.0690) loss: 0.8400 (0.8393) time: 0.1571 data: 0.0689 max mem: 9390 +Train: [15] [3900/6250] eta: 0:06:29 lr: 0.000121 grad: 0.0653 (0.0690) loss: 0.8396 (0.8393) time: 0.1815 data: 0.0996 max mem: 9390 +Train: [15] [4000/6250] eta: 0:06:12 lr: 0.000121 grad: 0.0646 (0.0690) loss: 0.8376 (0.8392) time: 0.1808 data: 0.0957 max mem: 9390 +Train: [15] [4100/6250] eta: 0:05:56 lr: 0.000121 grad: 0.0662 (0.0689) loss: 0.8421 (0.8392) time: 0.1866 data: 0.1055 max mem: 9390 +Train: [15] [4200/6250] eta: 0:05:40 lr: 0.000121 grad: 0.0599 (0.0689) loss: 0.8434 (0.8392) time: 0.1851 data: 0.1011 max mem: 9390 +Train: [15] [4300/6250] eta: 0:05:23 lr: 0.000121 grad: 0.0659 (0.0689) loss: 0.8387 (0.8392) time: 0.1788 data: 0.0947 max mem: 9390 +Train: [15] [4400/6250] eta: 0:05:06 lr: 0.000121 grad: 0.0612 (0.0688) loss: 0.8356 (0.8391) time: 0.1869 data: 0.1049 max mem: 9390 +Train: [15] [4500/6250] eta: 0:04:50 lr: 0.000121 grad: 0.0619 (0.0688) loss: 0.8399 (0.8391) time: 0.1741 data: 0.0810 max mem: 9390 +Train: [15] [4600/6250] eta: 0:04:33 lr: 0.000121 grad: 0.0658 (0.0687) loss: 0.8392 (0.8391) time: 0.1597 data: 0.0738 max mem: 9390 +Train: [15] [4700/6250] eta: 0:04:16 lr: 0.000121 grad: 0.0583 (0.0686) loss: 0.8415 (0.8391) time: 0.1694 data: 0.0791 max mem: 9390 +Train: [15] [4800/6250] eta: 0:04:00 lr: 0.000121 grad: 0.0631 (0.0686) loss: 0.8401 (0.8391) time: 0.1679 data: 0.0805 max mem: 9390 +Train: [15] [4900/6250] eta: 0:03:43 lr: 0.000121 grad: 0.0604 (0.0685) loss: 0.8375 (0.8390) time: 0.1820 data: 0.0969 max mem: 9390 +Train: [15] [5000/6250] eta: 0:03:27 lr: 0.000121 grad: 0.0634 (0.0686) loss: 0.8347 (0.8390) time: 0.1837 data: 0.0951 max mem: 9390 +Train: [15] [5100/6250] eta: 0:03:10 lr: 0.000121 grad: 0.0643 (0.0686) loss: 0.8407 (0.8390) time: 0.1659 data: 0.0820 max mem: 9390 +Train: [15] [5200/6250] eta: 0:02:53 lr: 0.000121 grad: 0.0640 (0.0686) loss: 0.8401 (0.8390) time: 0.1385 data: 0.0515 max mem: 9390 +Train: [15] [5300/6250] eta: 0:02:37 lr: 0.000121 grad: 0.0638 (0.0685) loss: 0.8365 (0.8389) time: 0.1594 data: 0.0761 max mem: 9390 +Train: [15] [5400/6250] eta: 0:02:20 lr: 0.000121 grad: 0.0648 (0.0684) loss: 0.8363 (0.8389) time: 0.1698 data: 0.0852 max mem: 9390 +Train: [15] [5500/6250] eta: 0:02:04 lr: 0.000121 grad: 0.0626 (0.0684) loss: 0.8400 (0.8389) time: 0.1590 data: 0.0719 max mem: 9390 +Train: [15] [5600/6250] eta: 0:01:47 lr: 0.000121 grad: 0.0635 (0.0683) loss: 0.8374 (0.8390) time: 0.1619 data: 0.0789 max mem: 9390 +Train: [15] [5700/6250] eta: 0:01:31 lr: 0.000121 grad: 0.0650 (0.0683) loss: 0.8362 (0.8390) time: 0.1687 data: 0.0829 max mem: 9390 +Train: [15] [5800/6250] eta: 0:01:14 lr: 0.000121 grad: 0.0630 (0.0682) loss: 0.8351 (0.8389) time: 0.1339 data: 0.0522 max mem: 9390 +Train: [15] [5900/6250] eta: 0:00:57 lr: 0.000121 grad: 0.0642 (0.0682) loss: 0.8391 (0.8389) time: 0.1639 data: 0.0775 max mem: 9390 +Train: [15] [6000/6250] eta: 0:00:41 lr: 0.000121 grad: 0.0627 (0.0681) loss: 0.8418 (0.8390) time: 0.1594 data: 0.0745 max mem: 9390 +Train: [15] [6100/6250] eta: 0:00:24 lr: 0.000121 grad: 0.0631 (0.0682) loss: 0.8370 (0.8390) time: 0.1390 data: 0.0474 max mem: 9390 +Train: [15] [6200/6250] eta: 0:00:08 lr: 0.000121 grad: 0.0628 (0.0681) loss: 0.8404 (0.8390) time: 0.1693 data: 0.0846 max mem: 9390 +Train: [15] [6249/6250] eta: 0:00:00 lr: 0.000121 grad: 0.0658 (0.0681) loss: 0.8408 (0.8390) time: 0.1334 data: 0.0506 max mem: 9390 +Train: [15] Total time: 0:17:21 (0.1666 s / it) +Averaged stats: lr: 0.000121 grad: 0.0658 (0.0681) loss: 0.8408 (0.8390) +Eval (hcp-train-subset): [15] [ 0/62] eta: 0:05:01 loss: 0.8636 (0.8636) time: 4.8699 data: 4.8397 max mem: 9390 +Eval (hcp-train-subset): [15] [61/62] eta: 0:00:00 loss: 0.8484 (0.8493) time: 0.1532 data: 0.1266 max mem: 9390 +Eval (hcp-train-subset): [15] Total time: 0:00:14 (0.2308 s / it) +Averaged stats (hcp-train-subset): loss: 0.8484 (0.8493) +Eval (hcp-val): [15] [ 0/62] eta: 0:04:11 loss: 0.8391 (0.8391) time: 4.0644 data: 4.0170 max mem: 9390 +Eval (hcp-val): [15] [61/62] eta: 0:00:00 loss: 0.8425 (0.8437) time: 0.1295 data: 0.1029 max mem: 9390 +Eval (hcp-val): [15] Total time: 0:00:13 (0.2135 s / it) +Averaged stats (hcp-val): loss: 0.8425 (0.8437) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +Train: [16] [ 0/6250] eta: 9:13:10 lr: 0.000121 grad: 0.0591 (0.0591) loss: 0.8643 (0.8643) time: 5.3104 data: 5.1173 max mem: 9390 +Train: [16] [ 100/6250] eta: 0:21:07 lr: 0.000121 grad: 0.0661 (0.0783) loss: 0.8409 (0.8439) time: 0.1604 data: 0.0814 max mem: 9390 +Train: [16] [ 200/6250] eta: 0:19:23 lr: 0.000121 grad: 0.0656 (0.0737) loss: 0.8399 (0.8431) time: 0.1335 data: 0.0430 max mem: 9390 +Train: [16] [ 300/6250] eta: 0:18:24 lr: 0.000121 grad: 0.0589 (0.0727) loss: 0.8380 (0.8421) time: 0.1740 data: 0.0756 max mem: 9390 +Train: [16] [ 400/6250] eta: 0:17:38 lr: 0.000121 grad: 0.0631 (0.0716) loss: 0.8433 (0.8416) time: 0.1672 data: 0.0744 max mem: 9390 +Train: [16] [ 500/6250] eta: 0:16:58 lr: 0.000121 grad: 0.0638 (0.0707) loss: 0.8410 (0.8417) time: 0.1613 data: 0.0661 max mem: 9390 +Train: [16] [ 600/6250] eta: 0:16:24 lr: 0.000121 grad: 0.0647 (0.0704) loss: 0.8486 (0.8418) time: 0.1449 data: 0.0430 max mem: 9390 +Train: [16] [ 700/6250] eta: 0:16:00 lr: 0.000121 grad: 0.0643 (0.0703) loss: 0.8427 (0.8421) time: 0.1698 data: 0.0700 max mem: 9390 +Train: [16] [ 800/6250] eta: 0:15:40 lr: 0.000121 grad: 0.0601 (0.0698) loss: 0.8472 (0.8425) time: 0.1837 data: 0.0926 max mem: 9390 +Train: [16] [ 900/6250] eta: 0:15:25 lr: 0.000121 grad: 0.0612 (0.0690) loss: 0.8433 (0.8425) time: 0.1465 data: 0.0488 max mem: 9390 +Train: [16] [1000/6250] eta: 0:15:07 lr: 0.000121 grad: 0.0606 (0.0684) loss: 0.8365 (0.8424) time: 0.1675 data: 0.0807 max mem: 9390 +Train: [16] [1100/6250] eta: 0:14:44 lr: 0.000121 grad: 0.0601 (0.0681) loss: 0.8382 (0.8425) time: 0.1599 data: 0.0721 max mem: 9390 +Train: [16] [1200/6250] eta: 0:14:25 lr: 0.000121 grad: 0.0605 (0.0678) loss: 0.8404 (0.8425) time: 0.1370 data: 0.0571 max mem: 9390 +Train: [16] [1300/6250] eta: 0:14:06 lr: 0.000121 grad: 0.0572 (0.0674) loss: 0.8477 (0.8425) time: 0.1592 data: 0.0661 max mem: 9390 +Train: [16] [1400/6250] eta: 0:13:46 lr: 0.000121 grad: 0.0695 (0.0679) loss: 0.8427 (0.8424) time: 0.1858 data: 0.1005 max mem: 9390 +Train: [16] [1500/6250] eta: 0:13:25 lr: 0.000121 grad: 0.0635 (0.0678) loss: 0.8376 (0.8422) time: 0.1220 data: 0.0341 max mem: 9390 +Train: [16] [1600/6250] eta: 0:13:05 lr: 0.000121 grad: 0.0664 (0.0675) loss: 0.8378 (0.8421) time: 0.1545 data: 0.0710 max mem: 9390 +Train: [16] [1700/6250] eta: 0:12:47 lr: 0.000121 grad: 0.0638 (0.0674) loss: 0.8400 (0.8420) time: 0.1618 data: 0.0732 max mem: 9390 +Train: [16] [1800/6250] eta: 0:12:28 lr: 0.000121 grad: 0.0653 (0.0673) loss: 0.8342 (0.8419) time: 0.1587 data: 0.0742 max mem: 9390 +Train: [16] [1900/6250] eta: 0:12:12 lr: 0.000121 grad: 0.0656 (0.0672) loss: 0.8443 (0.8419) time: 0.1620 data: 0.0770 max mem: 9390 +Train: [16] [2000/6250] eta: 0:11:53 lr: 0.000121 grad: 0.0597 (0.0674) loss: 0.8345 (0.8417) time: 0.1599 data: 0.0722 max mem: 9390 +Train: [16] [2100/6250] eta: 0:11:36 lr: 0.000121 grad: 0.0649 (0.0673) loss: 0.8377 (0.8415) time: 0.1676 data: 0.0777 max mem: 9390 +Train: [16] [2200/6250] eta: 0:11:20 lr: 0.000121 grad: 0.0672 (0.0672) loss: 0.8369 (0.8413) time: 0.1615 data: 0.0778 max mem: 9390 +Train: [16] [2300/6250] eta: 0:11:02 lr: 0.000121 grad: 0.0632 (0.0671) loss: 0.8384 (0.8413) time: 0.1653 data: 0.0801 max mem: 9390 +Train: [16] [2400/6250] eta: 0:10:45 lr: 0.000121 grad: 0.0609 (0.0671) loss: 0.8364 (0.8412) time: 0.1785 data: 0.0979 max mem: 9390 +Train: [16] [2500/6250] eta: 0:10:29 lr: 0.000121 grad: 0.0600 (0.0670) loss: 0.8445 (0.8411) time: 0.1632 data: 0.0759 max mem: 9390 +Train: [16] [2600/6250] eta: 0:10:11 lr: 0.000121 grad: 0.0652 (0.0669) loss: 0.8418 (0.8411) time: 0.1951 data: 0.1057 max mem: 9390 +Train: [16] [2700/6250] eta: 0:09:55 lr: 0.000121 grad: 0.0643 (0.0669) loss: 0.8427 (0.8410) time: 0.1417 data: 0.0622 max mem: 9390 +Train: [16] [2800/6250] eta: 0:09:39 lr: 0.000121 grad: 0.0597 (0.0670) loss: 0.8367 (0.8409) time: 0.1961 data: 0.1096 max mem: 9390 +Train: [16] [2900/6250] eta: 0:09:23 lr: 0.000121 grad: 0.0610 (0.0669) loss: 0.8440 (0.8409) time: 0.1526 data: 0.0754 max mem: 9390 +Train: [16] [3000/6250] eta: 0:09:05 lr: 0.000121 grad: 0.0640 (0.0668) loss: 0.8387 (0.8409) time: 0.1561 data: 0.0653 max mem: 9390 +Train: [16] [3100/6250] eta: 0:08:48 lr: 0.000121 grad: 0.0637 (0.0668) loss: 0.8345 (0.8408) time: 0.1672 data: 0.0749 max mem: 9390 +Train: [16] [3200/6250] eta: 0:08:31 lr: 0.000121 grad: 0.0660 (0.0668) loss: 0.8402 (0.8408) time: 0.1531 data: 0.0636 max mem: 9390 +Train: [16] [3300/6250] eta: 0:08:13 lr: 0.000121 grad: 0.0627 (0.0668) loss: 0.8401 (0.8408) time: 0.1521 data: 0.0616 max mem: 9390 +Train: [16] [3400/6250] eta: 0:07:55 lr: 0.000121 grad: 0.0605 (0.0667) loss: 0.8394 (0.8408) time: 0.1435 data: 0.0541 max mem: 9390 +Train: [16] [3500/6250] eta: 0:07:39 lr: 0.000120 grad: 0.0613 (0.0666) loss: 0.8465 (0.8408) time: 0.2072 data: 0.1181 max mem: 9390 +Train: [16] [3600/6250] eta: 0:07:20 lr: 0.000120 grad: 0.0667 (0.0666) loss: 0.8408 (0.8408) time: 0.1449 data: 0.0562 max mem: 9390 +Train: [16] [3700/6250] eta: 0:07:03 lr: 0.000120 grad: 0.0605 (0.0666) loss: 0.8410 (0.8409) time: 0.1606 data: 0.0656 max mem: 9390 +Train: [16] [3800/6250] eta: 0:06:46 lr: 0.000120 grad: 0.0638 (0.0665) loss: 0.8398 (0.8409) time: 0.1660 data: 0.0689 max mem: 9390 +Train: [16] [3900/6250] eta: 0:06:30 lr: 0.000120 grad: 0.0607 (0.0664) loss: 0.8415 (0.8409) time: 0.1495 data: 0.0607 max mem: 9390 +Train: [16] [4000/6250] eta: 0:06:13 lr: 0.000120 grad: 0.0666 (0.0664) loss: 0.8396 (0.8408) time: 0.1676 data: 0.0716 max mem: 9390 +Train: [16] [4100/6250] eta: 0:05:57 lr: 0.000120 grad: 0.0608 (0.0663) loss: 0.8396 (0.8409) time: 0.1566 data: 0.0630 max mem: 9390 +Train: [16] [4200/6250] eta: 0:05:41 lr: 0.000120 grad: 0.0606 (0.0663) loss: 0.8383 (0.8408) time: 0.1778 data: 0.0912 max mem: 9390 +Train: [16] [4300/6250] eta: 0:05:25 lr: 0.000120 grad: 0.0631 (0.0663) loss: 0.8376 (0.8408) time: 0.2103 data: 0.1250 max mem: 9390 +Train: [16] [4400/6250] eta: 0:05:08 lr: 0.000120 grad: 0.0599 (0.0662) loss: 0.8394 (0.8408) time: 0.1403 data: 0.0456 max mem: 9390 +Train: [16] [4500/6250] eta: 0:04:51 lr: 0.000120 grad: 0.0634 (0.0662) loss: 0.8396 (0.8409) time: 0.1615 data: 0.0712 max mem: 9390 +Train: [16] [4600/6250] eta: 0:04:34 lr: 0.000120 grad: 0.0644 (0.0662) loss: 0.8388 (0.8409) time: 0.1395 data: 0.0493 max mem: 9390 +Train: [16] [4700/6250] eta: 0:04:17 lr: 0.000120 grad: 0.0610 (0.0661) loss: 0.8430 (0.8409) time: 0.1905 data: 0.1008 max mem: 9390 +Train: [16] [4800/6250] eta: 0:04:01 lr: 0.000120 grad: 0.0633 (0.0661) loss: 0.8446 (0.8410) time: 0.1670 data: 0.0767 max mem: 9390 +Train: [16] [4900/6250] eta: 0:03:44 lr: 0.000120 grad: 0.0578 (0.0660) loss: 0.8464 (0.8411) time: 0.1568 data: 0.0660 max mem: 9390 +Train: [16] [5000/6250] eta: 0:03:27 lr: 0.000120 grad: 0.0634 (0.0660) loss: 0.8379 (0.8411) time: 0.1435 data: 0.0572 max mem: 9390 +Train: [16] [5100/6250] eta: 0:03:10 lr: 0.000120 grad: 0.0637 (0.0659) loss: 0.8420 (0.8412) time: 0.1541 data: 0.0656 max mem: 9390 +Train: [16] [5200/6250] eta: 0:02:54 lr: 0.000120 grad: 0.0592 (0.0659) loss: 0.8391 (0.8412) time: 0.1540 data: 0.0605 max mem: 9390 +Train: [16] [5300/6250] eta: 0:02:37 lr: 0.000120 grad: 0.0609 (0.0659) loss: 0.8434 (0.8412) time: 0.1683 data: 0.0801 max mem: 9390 +Train: [16] [5400/6250] eta: 0:02:20 lr: 0.000120 grad: 0.0621 (0.0658) loss: 0.8412 (0.8412) time: 0.1541 data: 0.0699 max mem: 9390 +Train: [16] [5500/6250] eta: 0:02:04 lr: 0.000120 grad: 0.0625 (0.0659) loss: 0.8402 (0.8412) time: 0.1518 data: 0.0623 max mem: 9390 +Train: [16] [5600/6250] eta: 0:01:47 lr: 0.000120 grad: 0.0621 (0.0659) loss: 0.8419 (0.8413) time: 0.1456 data: 0.0574 max mem: 9390 +Train: [16] [5700/6250] eta: 0:01:31 lr: 0.000120 grad: 0.0639 (0.0659) loss: 0.8411 (0.8413) time: 0.1717 data: 0.0788 max mem: 9390 +Train: [16] [5800/6250] eta: 0:01:14 lr: 0.000120 grad: 0.0620 (0.0659) loss: 0.8458 (0.8413) time: 0.1539 data: 0.0656 max mem: 9390 +Train: [16] [5900/6250] eta: 0:00:57 lr: 0.000120 grad: 0.0598 (0.0658) loss: 0.8368 (0.8413) time: 0.1730 data: 0.0879 max mem: 9390 +Train: [16] [6000/6250] eta: 0:00:41 lr: 0.000120 grad: 0.0633 (0.0658) loss: 0.8420 (0.8413) time: 0.1474 data: 0.0548 max mem: 9390 +Train: [16] [6100/6250] eta: 0:00:24 lr: 0.000120 grad: 0.0596 (0.0657) loss: 0.8467 (0.8414) time: 0.1579 data: 0.0776 max mem: 9390 +Train: [16] [6200/6250] eta: 0:00:08 lr: 0.000120 grad: 0.0587 (0.0657) loss: 0.8425 (0.8414) time: 0.1713 data: 0.0898 max mem: 9390 +Train: [16] [6249/6250] eta: 0:00:00 lr: 0.000120 grad: 0.0633 (0.0656) loss: 0.8459 (0.8414) time: 0.1607 data: 0.0672 max mem: 9390 +Train: [16] Total time: 0:17:18 (0.1661 s / it) +Averaged stats: lr: 0.000120 grad: 0.0633 (0.0656) loss: 0.8459 (0.8414) +Eval (hcp-train-subset): [16] [ 0/62] eta: 0:05:56 loss: 0.8617 (0.8617) time: 5.7544 data: 5.7243 max mem: 9390 +Eval (hcp-train-subset): [16] [61/62] eta: 0:00:00 loss: 0.8464 (0.8486) time: 0.1324 data: 0.1068 max mem: 9390 +Eval (hcp-train-subset): [16] Total time: 0:00:13 (0.2229 s / it) +Averaged stats (hcp-train-subset): loss: 0.8464 (0.8486) +Eval (hcp-val): [16] [ 0/62] eta: 0:04:46 loss: 0.8416 (0.8416) time: 4.6134 data: 4.5616 max mem: 9390 +Eval (hcp-val): [16] [61/62] eta: 0:00:00 loss: 0.8426 (0.8432) time: 0.1372 data: 0.1120 max mem: 9390 +Eval (hcp-val): [16] Total time: 0:00:13 (0.2238 s / it) +Averaged stats (hcp-val): loss: 0.8426 (0.8432) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +Train: [17] [ 0/6250] eta: 9:27:51 lr: 0.000120 grad: 0.0507 (0.0507) loss: 0.8606 (0.8606) time: 5.4514 data: 5.2861 max mem: 9390 +Train: [17] [ 100/6250] eta: 0:22:29 lr: 0.000120 grad: 0.0679 (0.0681) loss: 0.8457 (0.8485) time: 0.1661 data: 0.0740 max mem: 9390 +Train: [17] [ 200/6250] eta: 0:20:01 lr: 0.000120 grad: 0.0657 (0.0675) loss: 0.8385 (0.8459) time: 0.1892 data: 0.1023 max mem: 9390 +Train: [17] [ 300/6250] eta: 0:18:32 lr: 0.000120 grad: 0.0649 (0.0681) loss: 0.8376 (0.8439) time: 0.1554 data: 0.0559 max mem: 9390 +Train: [17] [ 400/6250] eta: 0:17:48 lr: 0.000120 grad: 0.0632 (0.0674) loss: 0.8399 (0.8438) time: 0.1686 data: 0.0709 max mem: 9390 +Train: [17] [ 500/6250] eta: 0:17:05 lr: 0.000120 grad: 0.0689 (0.0672) loss: 0.8450 (0.8436) time: 0.1646 data: 0.0512 max mem: 9390 +Train: [17] [ 600/6250] eta: 0:16:31 lr: 0.000120 grad: 0.0701 (0.0672) loss: 0.8332 (0.8430) time: 0.1290 data: 0.0398 max mem: 9390 +Train: [17] [ 700/6250] eta: 0:16:07 lr: 0.000120 grad: 0.0596 (0.0673) loss: 0.8388 (0.8424) time: 0.1252 data: 0.0402 max mem: 9390 +Train: [17] [ 800/6250] eta: 0:15:54 lr: 0.000120 grad: 0.0583 (0.0670) loss: 0.8462 (0.8423) time: 0.1749 data: 0.0934 max mem: 9390 +Train: [17] [ 900/6250] eta: 0:15:42 lr: 0.000120 grad: 0.0624 (0.0667) loss: 0.8393 (0.8421) time: 0.2208 data: 0.1355 max mem: 9390 +Train: [17] [1000/6250] eta: 0:15:20 lr: 0.000120 grad: 0.0613 (0.0667) loss: 0.8407 (0.8419) time: 0.1832 data: 0.1003 max mem: 9390 +Train: [17] [1100/6250] eta: 0:14:57 lr: 0.000120 grad: 0.0634 (0.0665) loss: 0.8425 (0.8418) time: 0.1363 data: 0.0518 max mem: 9390 +Train: [17] [1200/6250] eta: 0:14:36 lr: 0.000120 grad: 0.0604 (0.0662) loss: 0.8368 (0.8417) time: 0.1647 data: 0.0710 max mem: 9390 +Train: [17] [1300/6250] eta: 0:14:16 lr: 0.000120 grad: 0.0627 (0.0659) loss: 0.8385 (0.8416) time: 0.1726 data: 0.0797 max mem: 9390 +Train: [17] [1400/6250] eta: 0:13:56 lr: 0.000120 grad: 0.0638 (0.0660) loss: 0.8426 (0.8415) time: 0.1688 data: 0.0772 max mem: 9390 +Train: [17] [1500/6250] eta: 0:13:35 lr: 0.000120 grad: 0.0606 (0.0658) loss: 0.8429 (0.8415) time: 0.1723 data: 0.0865 max mem: 9390 +Train: [17] [1600/6250] eta: 0:13:13 lr: 0.000120 grad: 0.0591 (0.0656) loss: 0.8438 (0.8415) time: 0.1586 data: 0.0697 max mem: 9390 +Train: [17] [1700/6250] eta: 0:12:52 lr: 0.000120 grad: 0.0684 (0.0655) loss: 0.8392 (0.8413) time: 0.1528 data: 0.0681 max mem: 9390 +Train: [17] [1800/6250] eta: 0:12:35 lr: 0.000120 grad: 0.0645 (0.0656) loss: 0.8404 (0.8413) time: 0.1915 data: 0.1017 max mem: 9390 +Train: [17] [1900/6250] eta: 0:12:17 lr: 0.000120 grad: 0.0604 (0.0657) loss: 0.8402 (0.8411) time: 0.1715 data: 0.0849 max mem: 9390 +Train: [17] [2000/6250] eta: 0:12:00 lr: 0.000120 grad: 0.0638 (0.0656) loss: 0.8402 (0.8410) time: 0.1701 data: 0.0839 max mem: 9390 +Train: [17] [2100/6250] eta: 0:11:43 lr: 0.000120 grad: 0.0675 (0.0657) loss: 0.8390 (0.8410) time: 0.1499 data: 0.0592 max mem: 9390 +Train: [17] [2200/6250] eta: 0:11:25 lr: 0.000120 grad: 0.0622 (0.0658) loss: 0.8349 (0.8409) time: 0.1537 data: 0.0661 max mem: 9390 +Train: [17] [2300/6250] eta: 0:11:08 lr: 0.000120 grad: 0.0676 (0.0658) loss: 0.8382 (0.8408) time: 0.1638 data: 0.0816 max mem: 9390 +Train: [17] [2400/6250] eta: 0:10:50 lr: 0.000120 grad: 0.0609 (0.0657) loss: 0.8334 (0.8408) time: 0.1632 data: 0.0700 max mem: 9390 +Train: [17] [2500/6250] eta: 0:10:32 lr: 0.000120 grad: 0.0653 (0.0657) loss: 0.8388 (0.8407) time: 0.1304 data: 0.0383 max mem: 9390 +Train: [17] [2600/6250] eta: 0:10:14 lr: 0.000120 grad: 0.0629 (0.0657) loss: 0.8426 (0.8408) time: 0.1622 data: 0.0770 max mem: 9390 +Train: [17] [2700/6250] eta: 0:09:56 lr: 0.000120 grad: 0.0644 (0.0656) loss: 0.8388 (0.8408) time: 0.1821 data: 0.0954 max mem: 9390 +Train: [17] [2800/6250] eta: 0:09:39 lr: 0.000120 grad: 0.0615 (0.0655) loss: 0.8468 (0.8409) time: 0.1563 data: 0.0657 max mem: 9390 +Train: [17] [2900/6250] eta: 0:09:21 lr: 0.000120 grad: 0.0635 (0.0656) loss: 0.8397 (0.8409) time: 0.1592 data: 0.0708 max mem: 9390 +Train: [17] [3000/6250] eta: 0:09:03 lr: 0.000120 grad: 0.0603 (0.0655) loss: 0.8372 (0.8408) time: 0.1187 data: 0.0346 max mem: 9390 +Train: [17] [3100/6250] eta: 0:08:47 lr: 0.000120 grad: 0.0623 (0.0655) loss: 0.8384 (0.8408) time: 0.1654 data: 0.0815 max mem: 9390 +Train: [17] [3200/6250] eta: 0:08:29 lr: 0.000120 grad: 0.0687 (0.0654) loss: 0.8390 (0.8408) time: 0.1442 data: 0.0557 max mem: 9390 +Train: [17] [3300/6250] eta: 0:08:12 lr: 0.000120 grad: 0.0635 (0.0654) loss: 0.8440 (0.8408) time: 0.1717 data: 0.0832 max mem: 9390 +Train: [17] [3400/6250] eta: 0:07:55 lr: 0.000120 grad: 0.0642 (0.0654) loss: 0.8429 (0.8407) time: 0.1534 data: 0.0670 max mem: 9390 +Train: [17] [3500/6250] eta: 0:07:38 lr: 0.000120 grad: 0.0585 (0.0654) loss: 0.8460 (0.8408) time: 0.1378 data: 0.0457 max mem: 9390 +Train: [17] [3600/6250] eta: 0:07:21 lr: 0.000120 grad: 0.0614 (0.0655) loss: 0.8412 (0.8408) time: 0.1577 data: 0.0741 max mem: 9390 +Train: [17] [3700/6250] eta: 0:07:05 lr: 0.000120 grad: 0.0655 (0.0655) loss: 0.8341 (0.8408) time: 0.1640 data: 0.0799 max mem: 9390 +Train: [17] [3800/6250] eta: 0:06:48 lr: 0.000120 grad: 0.0661 (0.0656) loss: 0.8369 (0.8407) time: 0.1841 data: 0.0999 max mem: 9390 +Train: [17] [3900/6250] eta: 0:06:32 lr: 0.000120 grad: 0.0631 (0.0656) loss: 0.8396 (0.8406) time: 0.1805 data: 0.0878 max mem: 9390 +Train: [17] [4000/6250] eta: 0:06:16 lr: 0.000120 grad: 0.0665 (0.0657) loss: 0.8359 (0.8406) time: 0.1833 data: 0.0958 max mem: 9390 +Train: [17] [4100/6250] eta: 0:05:59 lr: 0.000120 grad: 0.0682 (0.0657) loss: 0.8361 (0.8405) time: 0.1708 data: 0.0863 max mem: 9390 +Train: [17] [4200/6250] eta: 0:05:42 lr: 0.000120 grad: 0.0643 (0.0659) loss: 0.8370 (0.8404) time: 0.1694 data: 0.0744 max mem: 9390 +Train: [17] [4300/6250] eta: 0:05:25 lr: 0.000120 grad: 0.0630 (0.0660) loss: 0.8406 (0.8403) time: 0.1657 data: 0.0826 max mem: 9390 +Train: [17] [4400/6250] eta: 0:05:09 lr: 0.000120 grad: 0.0652 (0.0660) loss: 0.8306 (0.8403) time: 0.1777 data: 0.0891 max mem: 9390 +Train: [17] [4500/6250] eta: 0:04:52 lr: 0.000120 grad: 0.0666 (0.0661) loss: 0.8407 (0.8402) time: 0.1826 data: 0.0990 max mem: 9390 +Train: [17] [4600/6250] eta: 0:04:35 lr: 0.000120 grad: 0.0630 (0.0661) loss: 0.8342 (0.8402) time: 0.1794 data: 0.0938 max mem: 9390 +Train: [17] [4700/6250] eta: 0:04:19 lr: 0.000120 grad: 0.0655 (0.0660) loss: 0.8380 (0.8401) time: 0.1547 data: 0.0659 max mem: 9390 +Train: [17] [4800/6250] eta: 0:04:02 lr: 0.000120 grad: 0.0653 (0.0661) loss: 0.8359 (0.8401) time: 0.1725 data: 0.0890 max mem: 9390 +Train: [17] [4900/6250] eta: 0:03:45 lr: 0.000119 grad: 0.0655 (0.0661) loss: 0.8371 (0.8400) time: 0.1694 data: 0.0827 max mem: 9390 +Train: [17] [5000/6250] eta: 0:03:28 lr: 0.000119 grad: 0.0645 (0.0661) loss: 0.8344 (0.8400) time: 0.1744 data: 0.0918 max mem: 9390 +Train: [17] [5100/6250] eta: 0:03:12 lr: 0.000119 grad: 0.0653 (0.0662) loss: 0.8355 (0.8399) time: 0.1675 data: 0.0797 max mem: 9390 +Train: [17] [5200/6250] eta: 0:02:55 lr: 0.000119 grad: 0.0646 (0.0662) loss: 0.8379 (0.8399) time: 0.1726 data: 0.0951 max mem: 9390 +Train: [17] [5300/6250] eta: 0:02:38 lr: 0.000119 grad: 0.0648 (0.0662) loss: 0.8388 (0.8398) time: 0.1750 data: 0.0835 max mem: 9390 +Train: [17] [5400/6250] eta: 0:02:22 lr: 0.000119 grad: 0.0649 (0.0662) loss: 0.8353 (0.8398) time: 0.1818 data: 0.0986 max mem: 9390 +Train: [17] [5500/6250] eta: 0:02:05 lr: 0.000119 grad: 0.0671 (0.0662) loss: 0.8381 (0.8397) time: 0.1430 data: 0.0594 max mem: 9390 +Train: [17] [5600/6250] eta: 0:01:48 lr: 0.000119 grad: 0.0630 (0.0662) loss: 0.8373 (0.8397) time: 0.1624 data: 0.0797 max mem: 9390 +Train: [17] [5700/6250] eta: 0:01:31 lr: 0.000119 grad: 0.0627 (0.0662) loss: 0.8319 (0.8396) time: 0.1410 data: 0.0568 max mem: 9390 +Train: [17] [5800/6250] eta: 0:01:15 lr: 0.000119 grad: 0.0671 (0.0663) loss: 0.8348 (0.8396) time: 0.1575 data: 0.0694 max mem: 9390 +Train: [17] [5900/6250] eta: 0:00:58 lr: 0.000119 grad: 0.0637 (0.0662) loss: 0.8410 (0.8395) time: 0.1604 data: 0.0782 max mem: 9390 +Train: [17] [6000/6250] eta: 0:00:41 lr: 0.000119 grad: 0.0678 (0.0663) loss: 0.8411 (0.8395) time: 0.1632 data: 0.0695 max mem: 9390 +Train: [17] [6100/6250] eta: 0:00:25 lr: 0.000119 grad: 0.0635 (0.0662) loss: 0.8393 (0.8395) time: 0.1602 data: 0.0737 max mem: 9390 +Train: [17] [6200/6250] eta: 0:00:08 lr: 0.000119 grad: 0.0694 (0.0662) loss: 0.8393 (0.8395) time: 0.1555 data: 0.0683 max mem: 9390 +Train: [17] [6249/6250] eta: 0:00:00 lr: 0.000119 grad: 0.0614 (0.0662) loss: 0.8372 (0.8395) time: 0.1737 data: 0.0861 max mem: 9390 +Train: [17] Total time: 0:17:29 (0.1679 s / it) +Averaged stats: lr: 0.000119 grad: 0.0614 (0.0662) loss: 0.8372 (0.8395) +Eval (hcp-train-subset): [17] [ 0/62] eta: 0:05:27 loss: 0.8587 (0.8587) time: 5.2747 data: 5.2397 max mem: 9390 +Eval (hcp-train-subset): [17] [61/62] eta: 0:00:00 loss: 0.8466 (0.8477) time: 0.1367 data: 0.1102 max mem: 9390 +Eval (hcp-train-subset): [17] Total time: 0:00:13 (0.2231 s / it) +Averaged stats (hcp-train-subset): loss: 0.8466 (0.8477) +Eval (hcp-val): [17] [ 0/62] eta: 0:03:21 loss: 0.8392 (0.8392) time: 3.2494 data: 3.1873 max mem: 9390 +Eval (hcp-val): [17] [61/62] eta: 0:00:00 loss: 0.8420 (0.8423) time: 0.1871 data: 0.1622 max mem: 9390 +Eval (hcp-val): [17] Total time: 0:00:15 (0.2457 s / it) +Averaged stats (hcp-val): loss: 0.8420 (0.8423) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +Train: [18] [ 0/6250] eta: 9:32:13 lr: 0.000119 grad: 0.0500 (0.0500) loss: 0.8709 (0.8709) time: 5.4934 data: 5.3825 max mem: 9390 +Train: [18] [ 100/6250] eta: 0:22:13 lr: 0.000119 grad: 0.0630 (0.0668) loss: 0.8485 (0.8479) time: 0.1681 data: 0.0837 max mem: 9390 +Train: [18] [ 200/6250] eta: 0:19:41 lr: 0.000119 grad: 0.0656 (0.0668) loss: 0.8359 (0.8435) time: 0.1717 data: 0.0837 max mem: 9390 +Train: [18] [ 300/6250] eta: 0:18:31 lr: 0.000119 grad: 0.0680 (0.0674) loss: 0.8350 (0.8415) time: 0.1492 data: 0.0528 max mem: 9390 +Train: [18] [ 400/6250] eta: 0:17:53 lr: 0.000119 grad: 0.0615 (0.0675) loss: 0.8354 (0.8396) time: 0.1801 data: 0.0910 max mem: 9390 +Train: [18] [ 500/6250] eta: 0:17:07 lr: 0.000119 grad: 0.0614 (0.0670) loss: 0.8389 (0.8391) time: 0.1529 data: 0.0477 max mem: 9390 +Train: [18] [ 600/6250] eta: 0:16:36 lr: 0.000119 grad: 0.0634 (0.0664) loss: 0.8372 (0.8389) time: 0.1665 data: 0.0720 max mem: 9390 +Train: [18] [ 700/6250] eta: 0:16:05 lr: 0.000119 grad: 0.0614 (0.0662) loss: 0.8400 (0.8392) time: 0.1232 data: 0.0262 max mem: 9390 +Train: [18] [ 800/6250] eta: 0:15:45 lr: 0.000119 grad: 0.0611 (0.0657) loss: 0.8382 (0.8395) time: 0.1687 data: 0.0776 max mem: 9390 +Train: [18] [ 900/6250] eta: 0:15:28 lr: 0.000119 grad: 0.0618 (0.0653) loss: 0.8420 (0.8400) time: 0.2067 data: 0.1109 max mem: 9390 +Train: [18] [1000/6250] eta: 0:15:06 lr: 0.000119 grad: 0.0605 (0.0650) loss: 0.8350 (0.8404) time: 0.1524 data: 0.0593 max mem: 9390 +Train: [18] [1100/6250] eta: 0:14:48 lr: 0.000119 grad: 0.0591 (0.0649) loss: 0.8436 (0.8405) time: 0.1972 data: 0.1095 max mem: 9390 +Train: [18] [1200/6250] eta: 0:14:26 lr: 0.000119 grad: 0.0624 (0.0647) loss: 0.8368 (0.8406) time: 0.1678 data: 0.0806 max mem: 9390 +Train: [18] [1300/6250] eta: 0:14:12 lr: 0.000119 grad: 0.0635 (0.0647) loss: 0.8421 (0.8407) time: 0.1733 data: 0.0838 max mem: 9390 +Train: [18] [1400/6250] eta: 0:13:53 lr: 0.000119 grad: 0.0679 (0.0647) loss: 0.8391 (0.8408) time: 0.1593 data: 0.0800 max mem: 9390 +Train: [18] [1500/6250] eta: 0:13:40 lr: 0.000119 grad: 0.0621 (0.0645) loss: 0.8391 (0.8408) time: 0.1682 data: 0.0916 max mem: 9390 +Train: [18] [1600/6250] eta: 0:13:19 lr: 0.000119 grad: 0.0639 (0.0648) loss: 0.8406 (0.8407) time: 0.1726 data: 0.0984 max mem: 9390 +Train: [18] [1700/6250] eta: 0:13:03 lr: 0.000119 grad: 0.0647 (0.0648) loss: 0.8399 (0.8407) time: 0.1767 data: 0.0956 max mem: 9390 +Train: [18] [1800/6250] eta: 0:12:40 lr: 0.000119 grad: 0.0647 (0.0648) loss: 0.8428 (0.8407) time: 0.1373 data: 0.0514 max mem: 9390 +Train: [18] [1900/6250] eta: 0:12:24 lr: 0.000119 grad: 0.0612 (0.0648) loss: 0.8465 (0.8408) time: 0.1554 data: 0.0639 max mem: 9390 +Train: [18] [2000/6250] eta: 0:12:05 lr: 0.000119 grad: 0.0645 (0.0648) loss: 0.8440 (0.8408) time: 0.1896 data: 0.0997 max mem: 9390 +Train: [18] [2100/6250] eta: 0:11:47 lr: 0.000119 grad: 0.0593 (0.0648) loss: 0.8409 (0.8409) time: 0.1619 data: 0.0679 max mem: 9390 +Train: [18] [2200/6250] eta: 0:11:28 lr: 0.000119 grad: 0.0656 (0.0649) loss: 0.8394 (0.8409) time: 0.1611 data: 0.0624 max mem: 9390 +Train: [18] [2300/6250] eta: 0:11:10 lr: 0.000119 grad: 0.0607 (0.0649) loss: 0.8395 (0.8409) time: 0.1704 data: 0.0768 max mem: 9390 +Train: [18] [2400/6250] eta: 0:10:52 lr: 0.000119 grad: 0.0610 (0.0649) loss: 0.8455 (0.8411) time: 0.1848 data: 0.0935 max mem: 9390 +Train: [18] [2500/6250] eta: 0:10:33 lr: 0.000119 grad: 0.0628 (0.0648) loss: 0.8408 (0.8411) time: 0.1545 data: 0.0585 max mem: 9390 +Train: [18] [2600/6250] eta: 0:10:15 lr: 0.000119 grad: 0.0630 (0.0649) loss: 0.8403 (0.8410) time: 0.1733 data: 0.0800 max mem: 9390 +Train: [18] [2700/6250] eta: 0:09:58 lr: 0.000119 grad: 0.0658 (0.0649) loss: 0.8405 (0.8410) time: 0.1890 data: 0.0966 max mem: 9390 +Train: [18] [2800/6250] eta: 0:09:41 lr: 0.000119 grad: 0.0621 (0.0648) loss: 0.8431 (0.8411) time: 0.1715 data: 0.0830 max mem: 9390 +Train: [18] [2900/6250] eta: 0:09:24 lr: 0.000119 grad: 0.0640 (0.0648) loss: 0.8412 (0.8411) time: 0.1520 data: 0.0593 max mem: 9390 +Train: [18] [3000/6250] eta: 0:09:08 lr: 0.000119 grad: 0.0640 (0.0648) loss: 0.8406 (0.8411) time: 0.1791 data: 0.0791 max mem: 9390 +Train: [18] [3100/6250] eta: 0:08:50 lr: 0.000119 grad: 0.0664 (0.0648) loss: 0.8384 (0.8411) time: 0.1389 data: 0.0409 max mem: 9390 +Train: [18] [3200/6250] eta: 0:08:33 lr: 0.000119 grad: 0.0610 (0.0649) loss: 0.8470 (0.8411) time: 0.1901 data: 0.0923 max mem: 9390 +Train: [18] [3300/6250] eta: 0:08:15 lr: 0.000119 grad: 0.0653 (0.0649) loss: 0.8382 (0.8411) time: 0.1558 data: 0.0573 max mem: 9390 +Train: [18] [3400/6250] eta: 0:07:59 lr: 0.000119 grad: 0.0650 (0.0650) loss: 0.8383 (0.8410) time: 0.1814 data: 0.0861 max mem: 9390 +Train: [18] [3500/6250] eta: 0:07:42 lr: 0.000119 grad: 0.0677 (0.0652) loss: 0.8379 (0.8409) time: 0.1713 data: 0.0849 max mem: 9390 +Train: [18] [3600/6250] eta: 0:07:25 lr: 0.000119 grad: 0.0647 (0.0652) loss: 0.8421 (0.8409) time: 0.1438 data: 0.0539 max mem: 9390 +Train: [18] [3700/6250] eta: 0:07:08 lr: 0.000119 grad: 0.0698 (0.0654) loss: 0.8472 (0.8408) time: 0.1593 data: 0.0692 max mem: 9390 +Train: [18] [3800/6250] eta: 0:06:51 lr: 0.000119 grad: 0.0643 (0.0655) loss: 0.8423 (0.8407) time: 0.1686 data: 0.0774 max mem: 9390 +Train: [18] [3900/6250] eta: 0:06:34 lr: 0.000119 grad: 0.0674 (0.0656) loss: 0.8409 (0.8407) time: 0.1307 data: 0.0460 max mem: 9390 +Train: [18] [4000/6250] eta: 0:06:17 lr: 0.000119 grad: 0.0647 (0.0657) loss: 0.8412 (0.8406) time: 0.1721 data: 0.0878 max mem: 9390 +Train: [18] [4100/6250] eta: 0:06:00 lr: 0.000119 grad: 0.0639 (0.0657) loss: 0.8379 (0.8406) time: 0.1449 data: 0.0506 max mem: 9390 +Train: [18] [4200/6250] eta: 0:05:43 lr: 0.000119 grad: 0.0691 (0.0658) loss: 0.8419 (0.8405) time: 0.1523 data: 0.0715 max mem: 9390 +Train: [18] [4300/6250] eta: 0:05:26 lr: 0.000119 grad: 0.0640 (0.0658) loss: 0.8390 (0.8404) time: 0.1313 data: 0.0472 max mem: 9390 +Train: [18] [4400/6250] eta: 0:05:10 lr: 0.000119 grad: 0.0652 (0.0658) loss: 0.8396 (0.8404) time: 0.1381 data: 0.0573 max mem: 9390 +Train: [18] [4500/6250] eta: 0:04:53 lr: 0.000119 grad: 0.0618 (0.0659) loss: 0.8390 (0.8403) time: 0.1732 data: 0.0846 max mem: 9390 +Train: [18] [4600/6250] eta: 0:04:36 lr: 0.000119 grad: 0.0656 (0.0659) loss: 0.8387 (0.8402) time: 0.1610 data: 0.0740 max mem: 9390 +Train: [18] [4700/6250] eta: 0:04:19 lr: 0.000119 grad: 0.0634 (0.0660) loss: 0.8399 (0.8402) time: 0.1568 data: 0.0737 max mem: 9390 +Train: [18] [4800/6250] eta: 0:04:03 lr: 0.000119 grad: 0.0695 (0.0660) loss: 0.8355 (0.8401) time: 0.1727 data: 0.0840 max mem: 9390 +Train: [18] [4900/6250] eta: 0:03:46 lr: 0.000119 grad: 0.0630 (0.0661) loss: 0.8421 (0.8401) time: 0.1731 data: 0.0894 max mem: 9390 +Train: [18] [5000/6250] eta: 0:03:29 lr: 0.000119 grad: 0.0685 (0.0661) loss: 0.8344 (0.8400) time: 0.1696 data: 0.0733 max mem: 9390 +Train: [18] [5100/6250] eta: 0:03:12 lr: 0.000119 grad: 0.0605 (0.0661) loss: 0.8409 (0.8401) time: 0.1689 data: 0.0812 max mem: 9390 +Train: [18] [5200/6250] eta: 0:02:55 lr: 0.000119 grad: 0.0672 (0.0661) loss: 0.8395 (0.8400) time: 0.1519 data: 0.0579 max mem: 9390 +Train: [18] [5300/6250] eta: 0:02:39 lr: 0.000119 grad: 0.0623 (0.0661) loss: 0.8422 (0.8400) time: 0.1614 data: 0.0750 max mem: 9390 +Train: [18] [5400/6250] eta: 0:02:22 lr: 0.000119 grad: 0.0639 (0.0661) loss: 0.8386 (0.8400) time: 0.1584 data: 0.0800 max mem: 9390 +Train: [18] [5500/6250] eta: 0:02:05 lr: 0.000119 grad: 0.0643 (0.0661) loss: 0.8465 (0.8400) time: 0.1604 data: 0.0740 max mem: 9390 +Train: [18] [5600/6250] eta: 0:01:48 lr: 0.000119 grad: 0.0614 (0.0660) loss: 0.8414 (0.8400) time: 0.1835 data: 0.0854 max mem: 9390 +Train: [18] [5700/6250] eta: 0:01:32 lr: 0.000119 grad: 0.0604 (0.0660) loss: 0.8422 (0.8400) time: 0.1588 data: 0.0734 max mem: 9390 +Train: [18] [5800/6250] eta: 0:01:15 lr: 0.000118 grad: 0.0671 (0.0661) loss: 0.8387 (0.8399) time: 0.1879 data: 0.1029 max mem: 9390 +Train: [18] [5900/6250] eta: 0:00:58 lr: 0.000118 grad: 0.0631 (0.0661) loss: 0.8432 (0.8399) time: 0.1747 data: 0.0897 max mem: 9390 +Train: [18] [6000/6250] eta: 0:00:41 lr: 0.000118 grad: 0.0660 (0.0661) loss: 0.8371 (0.8398) time: 0.1713 data: 0.0831 max mem: 9390 +Train: [18] [6100/6250] eta: 0:00:25 lr: 0.000118 grad: 0.0626 (0.0661) loss: 0.8421 (0.8398) time: 0.1962 data: 0.1227 max mem: 9390 +Train: [18] [6200/6250] eta: 0:00:08 lr: 0.000118 grad: 0.0647 (0.0661) loss: 0.8391 (0.8397) time: 0.1610 data: 0.0731 max mem: 9390 +Train: [18] [6249/6250] eta: 0:00:00 lr: 0.000118 grad: 0.0680 (0.0661) loss: 0.8385 (0.8397) time: 0.1702 data: 0.0827 max mem: 9390 +Train: [18] Total time: 0:17:32 (0.1685 s / it) +Averaged stats: lr: 0.000118 grad: 0.0680 (0.0661) loss: 0.8385 (0.8397) +Eval (hcp-train-subset): [18] [ 0/62] eta: 0:04:50 loss: 0.8562 (0.8562) time: 4.6910 data: 4.5926 max mem: 9390 +Eval (hcp-train-subset): [18] [61/62] eta: 0:00:00 loss: 0.8465 (0.8477) time: 0.1373 data: 0.1113 max mem: 9390 +Eval (hcp-train-subset): [18] Total time: 0:00:14 (0.2259 s / it) +Averaged stats (hcp-train-subset): loss: 0.8465 (0.8477) +Eval (hcp-val): [18] [ 0/62] eta: 0:05:07 loss: 0.8403 (0.8403) time: 4.9618 data: 4.9070 max mem: 9390 +Eval (hcp-val): [18] [61/62] eta: 0:00:00 loss: 0.8411 (0.8425) time: 0.1468 data: 0.1220 max mem: 9390 +Eval (hcp-val): [18] Total time: 0:00:14 (0.2262 s / it) +Averaged stats (hcp-val): loss: 0.8411 (0.8425) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +Train: [19] [ 0/6250] eta: 8:11:33 lr: 0.000118 grad: 0.0683 (0.0683) loss: 0.8669 (0.8669) time: 4.7189 data: 4.5102 max mem: 9390 +Train: [19] [ 100/6250] eta: 0:22:39 lr: 0.000118 grad: 0.0611 (0.0651) loss: 0.8578 (0.8557) time: 0.1717 data: 0.0799 max mem: 9390 +Train: [19] [ 200/6250] eta: 0:19:40 lr: 0.000118 grad: 0.0639 (0.0654) loss: 0.8447 (0.8502) time: 0.1625 data: 0.0675 max mem: 9390 +Train: [19] [ 300/6250] eta: 0:18:43 lr: 0.000118 grad: 0.0680 (0.0653) loss: 0.8352 (0.8468) time: 0.1811 data: 0.0937 max mem: 9390 +Train: [19] [ 400/6250] eta: 0:17:52 lr: 0.000118 grad: 0.0578 (0.0651) loss: 0.8446 (0.8452) time: 0.2056 data: 0.1091 max mem: 9390 +Train: [19] [ 500/6250] eta: 0:17:06 lr: 0.000118 grad: 0.0623 (0.0650) loss: 0.8415 (0.8446) time: 0.1615 data: 0.0612 max mem: 9390 +Train: [19] [ 600/6250] eta: 0:16:32 lr: 0.000118 grad: 0.0593 (0.0653) loss: 0.8452 (0.8443) time: 0.1702 data: 0.0680 max mem: 9390 +Train: [19] [ 700/6250] eta: 0:16:06 lr: 0.000118 grad: 0.0639 (0.0649) loss: 0.8402 (0.8438) time: 0.1510 data: 0.0470 max mem: 9390 +Train: [19] [ 800/6250] eta: 0:15:47 lr: 0.000118 grad: 0.0638 (0.0649) loss: 0.8368 (0.8434) time: 0.1647 data: 0.0774 max mem: 9390 +Train: [19] [ 900/6250] eta: 0:15:29 lr: 0.000118 grad: 0.0631 (0.0648) loss: 0.8352 (0.8430) time: 0.1588 data: 0.0594 max mem: 9390 +Train: [19] [1000/6250] eta: 0:15:09 lr: 0.000118 grad: 0.0622 (0.0649) loss: 0.8400 (0.8426) time: 0.1627 data: 0.0675 max mem: 9390 +Train: [19] [1100/6250] eta: 0:14:48 lr: 0.000118 grad: 0.0625 (0.0648) loss: 0.8388 (0.8422) time: 0.1678 data: 0.0775 max mem: 9390 +Train: [19] [1200/6250] eta: 0:14:26 lr: 0.000118 grad: 0.0629 (0.0649) loss: 0.8358 (0.8418) time: 0.1518 data: 0.0640 max mem: 9390 +Train: [19] [1300/6250] eta: 0:14:04 lr: 0.000118 grad: 0.0654 (0.0648) loss: 0.8357 (0.8414) time: 0.1519 data: 0.0597 max mem: 9390 +Train: [19] [1400/6250] eta: 0:13:49 lr: 0.000118 grad: 0.0650 (0.0648) loss: 0.8321 (0.8410) time: 0.1634 data: 0.0735 max mem: 9390 +Train: [19] [1500/6250] eta: 0:13:33 lr: 0.000118 grad: 0.0651 (0.0650) loss: 0.8370 (0.8408) time: 0.1882 data: 0.1092 max mem: 9390 +Train: [19] [1600/6250] eta: 0:13:18 lr: 0.000118 grad: 0.0636 (0.0650) loss: 0.8394 (0.8407) time: 0.1839 data: 0.0966 max mem: 9390 +Train: [19] [1700/6250] eta: 0:13:01 lr: 0.000118 grad: 0.0648 (0.0649) loss: 0.8402 (0.8407) time: 0.1746 data: 0.0925 max mem: 9390 +Train: [19] [1800/6250] eta: 0:12:44 lr: 0.000118 grad: 0.0628 (0.0649) loss: 0.8367 (0.8405) time: 0.1700 data: 0.0821 max mem: 9390 +Train: [19] [1900/6250] eta: 0:12:28 lr: 0.000118 grad: 0.0622 (0.0648) loss: 0.8421 (0.8404) time: 0.1886 data: 0.1044 max mem: 9390 +Train: [19] [2000/6250] eta: 0:12:11 lr: 0.000118 grad: 0.0641 (0.0648) loss: 0.8403 (0.8404) time: 0.1750 data: 0.0854 max mem: 9390 +Train: [19] [2100/6250] eta: 0:11:55 lr: 0.000118 grad: 0.0609 (0.0648) loss: 0.8387 (0.8403) time: 0.1826 data: 0.0943 max mem: 9390 +Train: [19] [2200/6250] eta: 0:11:36 lr: 0.000118 grad: 0.0607 (0.0647) loss: 0.8444 (0.8402) time: 0.1719 data: 0.0812 max mem: 9390 +Train: [19] [2300/6250] eta: 0:11:20 lr: 0.000118 grad: 0.0600 (0.0647) loss: 0.8406 (0.8402) time: 0.1554 data: 0.0584 max mem: 9390 +Train: [19] [2400/6250] eta: 0:11:04 lr: 0.000118 grad: 0.0660 (0.0647) loss: 0.8383 (0.8400) time: 0.1551 data: 0.0673 max mem: 9390 +Train: [19] [2500/6250] eta: 0:10:47 lr: 0.000118 grad: 0.0625 (0.0647) loss: 0.8394 (0.8399) time: 0.1766 data: 0.0890 max mem: 9390 +Train: [19] [2600/6250] eta: 0:10:29 lr: 0.000118 grad: 0.0647 (0.0647) loss: 0.8420 (0.8399) time: 0.2017 data: 0.1147 max mem: 9390 +Train: [19] [2700/6250] eta: 0:10:12 lr: 0.000118 grad: 0.0585 (0.0646) loss: 0.8447 (0.8399) time: 0.1715 data: 0.0878 max mem: 9390 +Train: [19] [2800/6250] eta: 0:09:55 lr: 0.000118 grad: 0.0633 (0.0646) loss: 0.8392 (0.8400) time: 0.1795 data: 0.0931 max mem: 9390 +Train: [19] [2900/6250] eta: 0:09:37 lr: 0.000118 grad: 0.0605 (0.0645) loss: 0.8415 (0.8400) time: 0.1565 data: 0.0689 max mem: 9390 +Train: [19] [3000/6250] eta: 0:09:20 lr: 0.000118 grad: 0.0633 (0.0645) loss: 0.8392 (0.8400) time: 0.1766 data: 0.0987 max mem: 9390 +Train: [19] [3100/6250] eta: 0:09:03 lr: 0.000118 grad: 0.0616 (0.0645) loss: 0.8430 (0.8401) time: 0.1635 data: 0.0776 max mem: 9390 +Train: [19] [3200/6250] eta: 0:08:46 lr: 0.000118 grad: 0.0592 (0.0644) loss: 0.8471 (0.8402) time: 0.1628 data: 0.0743 max mem: 9390 +Train: [19] [3300/6250] eta: 0:08:29 lr: 0.000118 grad: 0.0629 (0.0644) loss: 0.8412 (0.8402) time: 0.1757 data: 0.0859 max mem: 9390 +Train: [19] [3400/6250] eta: 0:08:11 lr: 0.000118 grad: 0.0624 (0.0644) loss: 0.8427 (0.8402) time: 0.1511 data: 0.0654 max mem: 9390 +Train: [19] [3500/6250] eta: 0:07:54 lr: 0.000118 grad: 0.0564 (0.0643) loss: 0.8445 (0.8403) time: 0.1770 data: 0.0882 max mem: 9390 +Train: [19] [3600/6250] eta: 0:07:37 lr: 0.000118 grad: 0.0618 (0.0643) loss: 0.8441 (0.8403) time: 0.1933 data: 0.1111 max mem: 9390 +Train: [19] [3700/6250] eta: 0:07:20 lr: 0.000118 grad: 0.0598 (0.0642) loss: 0.8404 (0.8402) time: 0.1711 data: 0.0886 max mem: 9390 +Train: [19] [3800/6250] eta: 0:07:03 lr: 0.000118 grad: 0.0674 (0.0642) loss: 0.8351 (0.8402) time: 0.1752 data: 0.0900 max mem: 9390 +Train: [19] [3900/6250] eta: 0:06:46 lr: 0.000118 grad: 0.0612 (0.0642) loss: 0.8409 (0.8402) time: 0.1744 data: 0.0856 max mem: 9390 +Train: [19] [4000/6250] eta: 0:06:28 lr: 0.000118 grad: 0.0587 (0.0642) loss: 0.8420 (0.8402) time: 0.1655 data: 0.0778 max mem: 9390 +Train: [19] [4100/6250] eta: 0:06:11 lr: 0.000118 grad: 0.0609 (0.0641) loss: 0.8460 (0.8402) time: 0.1669 data: 0.0848 max mem: 9390 +Train: [19] [4200/6250] eta: 0:05:54 lr: 0.000118 grad: 0.0620 (0.0641) loss: 0.8405 (0.8403) time: 0.1893 data: 0.1029 max mem: 9390 +Train: [19] [4300/6250] eta: 0:05:36 lr: 0.000118 grad: 0.0625 (0.0641) loss: 0.8403 (0.8403) time: 0.1525 data: 0.0594 max mem: 9390 +Train: [19] [4400/6250] eta: 0:05:19 lr: 0.000118 grad: 0.0622 (0.0641) loss: 0.8430 (0.8403) time: 0.1585 data: 0.0578 max mem: 9390 +Train: [19] [4500/6250] eta: 0:05:02 lr: 0.000118 grad: 0.0606 (0.0641) loss: 0.8400 (0.8404) time: 0.1767 data: 0.0877 max mem: 9390 +Train: [19] [4600/6250] eta: 0:04:45 lr: 0.000118 grad: 0.0636 (0.0641) loss: 0.8394 (0.8404) time: 0.1837 data: 0.0964 max mem: 9390 +Train: [19] [4700/6250] eta: 0:04:28 lr: 0.000118 grad: 0.0621 (0.0641) loss: 0.8391 (0.8403) time: 0.1592 data: 0.0698 max mem: 9390 +Train: [19] [4800/6250] eta: 0:04:10 lr: 0.000118 grad: 0.0616 (0.0642) loss: 0.8415 (0.8403) time: 0.1800 data: 0.0982 max mem: 9390 +Train: [19] [4900/6250] eta: 0:03:53 lr: 0.000118 grad: 0.0673 (0.0642) loss: 0.8350 (0.8403) time: 0.1930 data: 0.1105 max mem: 9390 +Train: [19] [5000/6250] eta: 0:03:36 lr: 0.000118 grad: 0.0632 (0.0642) loss: 0.8379 (0.8403) time: 0.1642 data: 0.0706 max mem: 9390 +Train: [19] [5100/6250] eta: 0:03:18 lr: 0.000118 grad: 0.0609 (0.0643) loss: 0.8390 (0.8402) time: 0.1752 data: 0.0905 max mem: 9390 +Train: [19] [5200/6250] eta: 0:03:01 lr: 0.000118 grad: 0.0691 (0.0643) loss: 0.8385 (0.8402) time: 0.1766 data: 0.0831 max mem: 9390 +Train: [19] [5300/6250] eta: 0:02:44 lr: 0.000118 grad: 0.0602 (0.0644) loss: 0.8391 (0.8402) time: 0.1444 data: 0.0528 max mem: 9390 +Train: [19] [5400/6250] eta: 0:02:26 lr: 0.000118 grad: 0.0640 (0.0644) loss: 0.8399 (0.8402) time: 0.1761 data: 0.0900 max mem: 9390 +Train: [19] [5500/6250] eta: 0:02:09 lr: 0.000118 grad: 0.0639 (0.0644) loss: 0.8400 (0.8402) time: 0.1857 data: 0.1021 max mem: 9390 +Train: [19] [5600/6250] eta: 0:01:52 lr: 0.000118 grad: 0.0672 (0.0644) loss: 0.8400 (0.8402) time: 0.1490 data: 0.0680 max mem: 9390 +Train: [19] [5700/6250] eta: 0:01:35 lr: 0.000118 grad: 0.0625 (0.0645) loss: 0.8446 (0.8402) time: 0.1781 data: 0.0931 max mem: 9390 +Train: [19] [5800/6250] eta: 0:01:17 lr: 0.000118 grad: 0.0603 (0.0645) loss: 0.8397 (0.8402) time: 0.1438 data: 0.0550 max mem: 9390 +Train: [19] [5900/6250] eta: 0:01:00 lr: 0.000118 grad: 0.0650 (0.0645) loss: 0.8378 (0.8402) time: 0.1789 data: 0.0952 max mem: 9390 +Train: [19] [6000/6250] eta: 0:00:43 lr: 0.000118 grad: 0.0613 (0.0645) loss: 0.8388 (0.8402) time: 0.1645 data: 0.0815 max mem: 9390 +Train: [19] [6100/6250] eta: 0:00:25 lr: 0.000117 grad: 0.0633 (0.0645) loss: 0.8411 (0.8402) time: 0.2043 data: 0.1176 max mem: 9390 +Train: [19] [6200/6250] eta: 0:00:08 lr: 0.000117 grad: 0.0626 (0.0645) loss: 0.8398 (0.8402) time: 0.1637 data: 0.0722 max mem: 9390 +Train: [19] [6249/6250] eta: 0:00:00 lr: 0.000117 grad: 0.0610 (0.0645) loss: 0.8447 (0.8402) time: 0.1741 data: 0.0881 max mem: 9390 +Train: [19] Total time: 0:18:04 (0.1735 s / it) +Averaged stats: lr: 0.000117 grad: 0.0610 (0.0645) loss: 0.8447 (0.8402) +Eval (hcp-train-subset): [19] [ 0/62] eta: 0:03:54 loss: 0.8549 (0.8549) time: 3.7750 data: 3.7166 max mem: 9390 +Eval (hcp-train-subset): [19] [61/62] eta: 0:00:00 loss: 0.8456 (0.8456) time: 0.1336 data: 0.1078 max mem: 9390 +Eval (hcp-train-subset): [19] Total time: 0:00:13 (0.2146 s / it) +Averaged stats (hcp-train-subset): loss: 0.8456 (0.8456) +Making plots (hcp-train-subset): example=22 +Eval (hcp-val): [19] [ 0/62] eta: 0:05:13 loss: 0.8372 (0.8372) time: 5.0580 data: 5.0282 max mem: 9390 +Eval (hcp-val): [19] [61/62] eta: 0:00:00 loss: 0.8410 (0.8416) time: 0.1464 data: 0.1199 max mem: 9390 +Eval (hcp-val): [19] Total time: 0:00:13 (0.2233 s / it) +Averaged stats (hcp-val): loss: 0.8410 (0.8416) +Making plots (hcp-val): example=61 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +Train: [20] [ 0/6250] eta: 10:06:02 lr: 0.000117 grad: 0.0634 (0.0634) loss: 0.8586 (0.8586) time: 5.8180 data: 5.6492 max mem: 9390 +Train: [20] [ 100/6250] eta: 0:23:07 lr: 0.000117 grad: 0.0682 (0.0785) loss: 0.8374 (0.8369) time: 0.1682 data: 0.0805 max mem: 9390 +Train: [20] [ 200/6250] eta: 0:20:10 lr: 0.000117 grad: 0.0664 (0.0736) loss: 0.8345 (0.8355) time: 0.1726 data: 0.0874 max mem: 9390 +Train: [20] [ 300/6250] eta: 0:19:15 lr: 0.000117 grad: 0.0671 (0.0721) loss: 0.8292 (0.8358) time: 0.1524 data: 0.0737 max mem: 9390 +Train: [20] [ 400/6250] eta: 0:18:35 lr: 0.000117 grad: 0.0603 (0.0697) loss: 0.8427 (0.8375) time: 0.1541 data: 0.0620 max mem: 9390 +Train: [20] [ 500/6250] eta: 0:17:57 lr: 0.000117 grad: 0.0639 (0.0691) loss: 0.8394 (0.8381) time: 0.1617 data: 0.0670 max mem: 9390 +Train: [20] [ 600/6250] eta: 0:17:15 lr: 0.000117 grad: 0.0621 (0.0691) loss: 0.8352 (0.8378) time: 0.1620 data: 0.0741 max mem: 9390 +Train: [20] [ 700/6250] eta: 0:16:48 lr: 0.000117 grad: 0.0663 (0.0687) loss: 0.8360 (0.8376) time: 0.1585 data: 0.0554 max mem: 9390 +Train: [20] [ 800/6250] eta: 0:16:27 lr: 0.000117 grad: 0.0668 (0.0683) loss: 0.8367 (0.8377) time: 0.1661 data: 0.0660 max mem: 9390 +Train: [20] [ 900/6250] eta: 0:16:02 lr: 0.000117 grad: 0.0636 (0.0683) loss: 0.8412 (0.8378) time: 0.1445 data: 0.0392 max mem: 9390 +Train: [20] [1000/6250] eta: 0:15:36 lr: 0.000117 grad: 0.0598 (0.0677) loss: 0.8392 (0.8380) time: 0.1590 data: 0.0523 max mem: 9390 +Train: [20] [1100/6250] eta: 0:15:07 lr: 0.000117 grad: 0.0637 (0.0672) loss: 0.8351 (0.8380) time: 0.1662 data: 0.0610 max mem: 9390 +Train: [20] [1200/6250] eta: 0:14:48 lr: 0.000117 grad: 0.0590 (0.0670) loss: 0.8432 (0.8383) time: 0.1695 data: 0.0652 max mem: 9390 +Train: [20] [1300/6250] eta: 0:14:29 lr: 0.000117 grad: 0.0636 (0.0666) loss: 0.8425 (0.8386) time: 0.1668 data: 0.0797 max mem: 9390 +Train: [20] [1400/6250] eta: 0:14:11 lr: 0.000117 grad: 0.0640 (0.0664) loss: 0.8374 (0.8387) time: 0.1763 data: 0.0873 max mem: 9390 +Train: [20] [1500/6250] eta: 0:13:50 lr: 0.000117 grad: 0.0604 (0.0662) loss: 0.8418 (0.8390) time: 0.1630 data: 0.0724 max mem: 9390 +Train: [20] [1600/6250] eta: 0:13:32 lr: 0.000117 grad: 0.0640 (0.0661) loss: 0.8385 (0.8391) time: 0.1654 data: 0.0820 max mem: 9390 +Train: [20] [1700/6250] eta: 0:13:13 lr: 0.000117 grad: 0.0619 (0.0660) loss: 0.8427 (0.8392) time: 0.1664 data: 0.0767 max mem: 9390 +Train: [20] [1800/6250] eta: 0:12:55 lr: 0.000117 grad: 0.0670 (0.0661) loss: 0.8355 (0.8391) time: 0.1632 data: 0.0690 max mem: 9390 +Train: [20] [1900/6250] eta: 0:12:37 lr: 0.000117 grad: 0.0660 (0.0662) loss: 0.8357 (0.8390) time: 0.1825 data: 0.0936 max mem: 9390 +Train: [20] [2000/6250] eta: 0:12:18 lr: 0.000117 grad: 0.0665 (0.0663) loss: 0.8357 (0.8388) time: 0.1696 data: 0.0787 max mem: 9390 +Train: [20] [2100/6250] eta: 0:12:00 lr: 0.000117 grad: 0.0629 (0.0663) loss: 0.8362 (0.8386) time: 0.1495 data: 0.0607 max mem: 9390 +Train: [20] [2200/6250] eta: 0:11:42 lr: 0.000117 grad: 0.0610 (0.0663) loss: 0.8390 (0.8386) time: 0.1790 data: 0.0868 max mem: 9390 +Train: [20] [2300/6250] eta: 0:11:22 lr: 0.000117 grad: 0.0637 (0.0664) loss: 0.8385 (0.8385) time: 0.1575 data: 0.0665 max mem: 9390 +Train: [20] [2400/6250] eta: 0:11:03 lr: 0.000117 grad: 0.0640 (0.0665) loss: 0.8376 (0.8383) time: 0.1401 data: 0.0500 max mem: 9390 +Train: [20] [2500/6250] eta: 0:10:45 lr: 0.000117 grad: 0.0666 (0.0664) loss: 0.8320 (0.8382) time: 0.1642 data: 0.0709 max mem: 9390 +Train: [20] [2600/6250] eta: 0:10:26 lr: 0.000117 grad: 0.0639 (0.0664) loss: 0.8404 (0.8381) time: 0.1495 data: 0.0592 max mem: 9390 +Train: [20] [2700/6250] eta: 0:10:08 lr: 0.000117 grad: 0.0637 (0.0664) loss: 0.8353 (0.8381) time: 0.1597 data: 0.0736 max mem: 9390 +Train: [20] [2800/6250] eta: 0:09:49 lr: 0.000117 grad: 0.0650 (0.0664) loss: 0.8373 (0.8381) time: 0.1454 data: 0.0518 max mem: 9390 +Train: [20] [2900/6250] eta: 0:09:32 lr: 0.000117 grad: 0.0640 (0.0665) loss: 0.8375 (0.8380) time: 0.1622 data: 0.0682 max mem: 9390 +Train: [20] [3000/6250] eta: 0:09:14 lr: 0.000117 grad: 0.0653 (0.0665) loss: 0.8359 (0.8379) time: 0.1641 data: 0.0795 max mem: 9390 +Train: [20] [3100/6250] eta: 0:08:56 lr: 0.000117 grad: 0.0654 (0.0666) loss: 0.8351 (0.8378) time: 0.1383 data: 0.0499 max mem: 9390 +Train: [20] [3200/6250] eta: 0:08:38 lr: 0.000117 grad: 0.0677 (0.0667) loss: 0.8358 (0.8376) time: 0.1483 data: 0.0575 max mem: 9390 +Train: [20] [3300/6250] eta: 0:08:20 lr: 0.000117 grad: 0.0639 (0.0667) loss: 0.8329 (0.8375) time: 0.1520 data: 0.0663 max mem: 9390 +Train: [20] [3400/6250] eta: 0:08:03 lr: 0.000117 grad: 0.0696 (0.0668) loss: 0.8306 (0.8373) time: 0.1338 data: 0.0421 max mem: 9390 +Train: [20] [3500/6250] eta: 0:07:46 lr: 0.000117 grad: 0.0668 (0.0668) loss: 0.8331 (0.8372) time: 0.1517 data: 0.0639 max mem: 9390 +Train: [20] [3600/6250] eta: 0:07:29 lr: 0.000117 grad: 0.0685 (0.0668) loss: 0.8336 (0.8371) time: 0.1656 data: 0.0763 max mem: 9390 +Train: [20] [3700/6250] eta: 0:07:11 lr: 0.000117 grad: 0.0689 (0.0669) loss: 0.8340 (0.8370) time: 0.1552 data: 0.0703 max mem: 9390 +Train: [20] [3800/6250] eta: 0:06:54 lr: 0.000117 grad: 0.0671 (0.0669) loss: 0.8367 (0.8370) time: 0.1618 data: 0.0783 max mem: 9390 +Train: [20] [3900/6250] eta: 0:06:37 lr: 0.000117 grad: 0.0669 (0.0669) loss: 0.8323 (0.8369) time: 0.1330 data: 0.0341 max mem: 9390 +Train: [20] [4000/6250] eta: 0:06:20 lr: 0.000117 grad: 0.0646 (0.0669) loss: 0.8367 (0.8368) time: 0.1736 data: 0.0873 max mem: 9390 +Train: [20] [4100/6250] eta: 0:06:03 lr: 0.000117 grad: 0.0671 (0.0669) loss: 0.8328 (0.8367) time: 0.1582 data: 0.0762 max mem: 9390 +Train: [20] [4200/6250] eta: 0:05:46 lr: 0.000117 grad: 0.0648 (0.0672) loss: 0.8358 (0.8367) time: 0.1718 data: 0.0826 max mem: 9390 +Train: [20] [4300/6250] eta: 0:05:29 lr: 0.000117 grad: 0.0613 (0.0672) loss: 0.8322 (0.8366) time: 0.1701 data: 0.0753 max mem: 9390 +Train: [20] [4400/6250] eta: 0:05:11 lr: 0.000117 grad: 0.0678 (0.0672) loss: 0.8313 (0.8365) time: 0.1509 data: 0.0650 max mem: 9390 +Train: [20] [4500/6250] eta: 0:04:54 lr: 0.000117 grad: 0.0657 (0.0672) loss: 0.8369 (0.8364) time: 0.1451 data: 0.0531 max mem: 9390 +Train: [20] [4600/6250] eta: 0:04:37 lr: 0.000117 grad: 0.0653 (0.0672) loss: 0.8362 (0.8364) time: 0.1632 data: 0.0753 max mem: 9390 +Train: [20] [4700/6250] eta: 0:04:20 lr: 0.000117 grad: 0.0634 (0.0672) loss: 0.8328 (0.8364) time: 0.1577 data: 0.0728 max mem: 9390 +Train: [20] [4800/6250] eta: 0:04:03 lr: 0.000117 grad: 0.0643 (0.0672) loss: 0.8390 (0.8363) time: 0.1699 data: 0.0835 max mem: 9390 +Train: [20] [4900/6250] eta: 0:03:47 lr: 0.000117 grad: 0.0644 (0.0672) loss: 0.8357 (0.8363) time: 0.1967 data: 0.1190 max mem: 9390 +Train: [20] [5000/6250] eta: 0:03:30 lr: 0.000117 grad: 0.0628 (0.0671) loss: 0.8399 (0.8364) time: 0.1717 data: 0.0875 max mem: 9390 +Train: [20] [5100/6250] eta: 0:03:13 lr: 0.000117 grad: 0.0621 (0.0671) loss: 0.8346 (0.8364) time: 0.1504 data: 0.0665 max mem: 9390 +Train: [20] [5200/6250] eta: 0:02:56 lr: 0.000117 grad: 0.0664 (0.0670) loss: 0.8395 (0.8364) time: 0.1779 data: 0.0964 max mem: 9390 +Train: [20] [5300/6250] eta: 0:02:39 lr: 0.000117 grad: 0.0656 (0.0670) loss: 0.8359 (0.8364) time: 0.1799 data: 0.1008 max mem: 9390 +Train: [20] [5400/6250] eta: 0:02:22 lr: 0.000117 grad: 0.0648 (0.0669) loss: 0.8384 (0.8365) time: 0.1662 data: 0.0720 max mem: 9390 +Train: [20] [5500/6250] eta: 0:02:05 lr: 0.000117 grad: 0.0623 (0.0669) loss: 0.8350 (0.8365) time: 0.1366 data: 0.0441 max mem: 9390 +Train: [20] [5600/6250] eta: 0:01:49 lr: 0.000117 grad: 0.0663 (0.0668) loss: 0.8322 (0.8366) time: 0.1771 data: 0.0928 max mem: 9390 +Train: [20] [5700/6250] eta: 0:01:32 lr: 0.000117 grad: 0.0661 (0.0668) loss: 0.8311 (0.8366) time: 0.1660 data: 0.0782 max mem: 9390 +Train: [20] [5800/6250] eta: 0:01:15 lr: 0.000117 grad: 0.0660 (0.0668) loss: 0.8398 (0.8366) time: 0.1648 data: 0.0726 max mem: 9390 +Train: [20] [5900/6250] eta: 0:00:58 lr: 0.000117 grad: 0.0668 (0.0668) loss: 0.8361 (0.8367) time: 0.1503 data: 0.0603 max mem: 9390 +Train: [20] [6000/6250] eta: 0:00:41 lr: 0.000116 grad: 0.0622 (0.0668) loss: 0.8365 (0.8367) time: 0.1664 data: 0.0825 max mem: 9390 +Train: [20] [6100/6250] eta: 0:00:25 lr: 0.000116 grad: 0.0630 (0.0668) loss: 0.8374 (0.8367) time: 0.1560 data: 0.0705 max mem: 9390 +Train: [20] [6200/6250] eta: 0:00:08 lr: 0.000116 grad: 0.0627 (0.0668) loss: 0.8369 (0.8367) time: 0.2326 data: 0.1397 max mem: 9390 +Train: [20] [6249/6250] eta: 0:00:00 lr: 0.000116 grad: 0.0627 (0.0668) loss: 0.8391 (0.8367) time: 0.1613 data: 0.0778 max mem: 9390 +Train: [20] Total time: 0:17:33 (0.1686 s / it) +Averaged stats: lr: 0.000116 grad: 0.0627 (0.0668) loss: 0.8391 (0.8367) +Eval (hcp-train-subset): [20] [ 0/62] eta: 0:04:24 loss: 0.8599 (0.8599) time: 4.2723 data: 4.2327 max mem: 9390 +Eval (hcp-train-subset): [20] [61/62] eta: 0:00:00 loss: 0.8466 (0.8465) time: 0.1027 data: 0.0779 max mem: 9390 +Eval (hcp-train-subset): [20] Total time: 0:00:15 (0.2436 s / it) +Averaged stats (hcp-train-subset): loss: 0.8466 (0.8465) +Eval (hcp-val): [20] [ 0/62] eta: 0:04:59 loss: 0.8396 (0.8396) time: 4.8368 data: 4.8060 max mem: 9390 +Eval (hcp-val): [20] [61/62] eta: 0:00:00 loss: 0.8408 (0.8418) time: 0.1307 data: 0.1055 max mem: 9390 +Eval (hcp-val): [20] Total time: 0:00:13 (0.2133 s / it) +Averaged stats (hcp-val): loss: 0.8408 (0.8418) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +Train: [21] [ 0/6250] eta: 9:01:03 lr: 0.000116 grad: nan (nan) loss: 0.8325 (0.8325) time: 5.1942 data: 4.9481 max mem: 9390 +Train: [21] [ 100/6250] eta: 0:21:41 lr: 0.000116 grad: 0.0738 (0.0781) loss: 0.8370 (0.8429) time: 0.1881 data: 0.0909 max mem: 9390 +Train: [21] [ 200/6250] eta: 0:19:38 lr: 0.000116 grad: 0.0654 (0.0729) loss: 0.8395 (0.8404) time: 0.1673 data: 0.0755 max mem: 9390 +Train: [21] [ 300/6250] eta: 0:18:54 lr: 0.000116 grad: 0.0628 (0.0703) loss: 0.8356 (0.8392) time: 0.2202 data: 0.1306 max mem: 9390 +Train: [21] [ 400/6250] eta: 0:17:52 lr: 0.000116 grad: 0.0596 (0.0689) loss: 0.8386 (0.8390) time: 0.1461 data: 0.0425 max mem: 9390 +Train: [21] [ 500/6250] eta: 0:17:16 lr: 0.000116 grad: 0.0636 (0.0681) loss: 0.8365 (0.8390) time: 0.1691 data: 0.0766 max mem: 9390 +Train: [21] [ 600/6250] eta: 0:16:45 lr: 0.000116 grad: 0.0627 (0.0676) loss: 0.8412 (0.8391) time: 0.1627 data: 0.0685 max mem: 9390 +Train: [21] [ 700/6250] eta: 0:16:25 lr: 0.000116 grad: 0.0619 (0.0670) loss: 0.8406 (0.8394) time: 0.1846 data: 0.0967 max mem: 9390 +Train: [21] [ 800/6250] eta: 0:16:03 lr: 0.000116 grad: 0.0619 (0.0666) loss: 0.8443 (0.8395) time: 0.1739 data: 0.0893 max mem: 9390 +Train: [21] [ 900/6250] eta: 0:15:48 lr: 0.000116 grad: 0.0666 (0.0665) loss: 0.8358 (0.8394) time: 0.1861 data: 0.1014 max mem: 9390 +Train: [21] [1000/6250] eta: 0:15:24 lr: 0.000116 grad: 0.0649 (0.0662) loss: 0.8383 (0.8395) time: 0.1586 data: 0.0747 max mem: 9390 +Train: [21] [1100/6250] eta: 0:15:05 lr: 0.000116 grad: 0.0618 (0.0659) loss: 0.8402 (0.8395) time: 0.1575 data: 0.0691 max mem: 9390 +Train: [21] [1200/6250] eta: 0:14:45 lr: 0.000116 grad: 0.0604 (0.0658) loss: 0.8451 (0.8396) time: 0.1588 data: 0.0744 max mem: 9390 +Train: [21] [1300/6250] eta: 0:14:26 lr: 0.000116 grad: 0.0612 (0.0656) loss: 0.8385 (0.8395) time: 0.1695 data: 0.0788 max mem: 9390 +Train: [21] [1400/6250] eta: 0:14:06 lr: 0.000116 grad: 0.0622 (0.0655) loss: 0.8386 (0.8394) time: 0.1723 data: 0.0858 max mem: 9390 +Train: [21] [1500/6250] eta: 0:13:50 lr: 0.000116 grad: 0.0622 (0.0654) loss: 0.8419 (0.8395) time: 0.1870 data: 0.1034 max mem: 9390 +Train: [21] [1600/6250] eta: 0:13:31 lr: 0.000116 grad: 0.0579 (0.0653) loss: 0.8430 (0.8395) time: 0.1588 data: 0.0662 max mem: 9390 +Train: [21] [1700/6250] eta: 0:13:11 lr: 0.000116 grad: 0.0629 (0.0653) loss: 0.8342 (0.8394) time: 0.1721 data: 0.0822 max mem: 9390 +Train: [21] [1800/6250] eta: 0:12:50 lr: 0.000116 grad: 0.0624 (0.0652) loss: 0.8397 (0.8392) time: 0.1469 data: 0.0519 max mem: 9390 +Train: [21] [1900/6250] eta: 0:12:30 lr: 0.000116 grad: 0.0662 (0.0654) loss: 0.8359 (0.8392) time: 0.1532 data: 0.0627 max mem: 9390 +Train: [21] [2000/6250] eta: 0:12:11 lr: 0.000116 grad: 0.0622 (0.0653) loss: 0.8394 (0.8391) time: 0.1762 data: 0.0852 max mem: 9390 +Train: [21] [2100/6250] eta: 0:11:52 lr: 0.000116 grad: 0.0688 (0.0653) loss: 0.8353 (0.8391) time: 0.1503 data: 0.0595 max mem: 9390 +Train: [21] [2200/6250] eta: 0:11:34 lr: 0.000116 grad: 0.0600 (0.0653) loss: 0.8396 (0.8389) time: 0.1609 data: 0.0733 max mem: 9390 +Train: [21] [2300/6250] eta: 0:11:16 lr: 0.000116 grad: 0.0629 (0.0653) loss: 0.8416 (0.8389) time: 0.1592 data: 0.0693 max mem: 9390 +Train: [21] [2400/6250] eta: 0:10:58 lr: 0.000116 grad: 0.0637 (0.0653) loss: 0.8395 (0.8388) time: 0.1427 data: 0.0508 max mem: 9390 +Train: [21] [2500/6250] eta: 0:10:40 lr: 0.000116 grad: 0.0634 (0.0653) loss: 0.8386 (0.8388) time: 0.1611 data: 0.0625 max mem: 9390 +Train: [21] [2600/6250] eta: 0:10:22 lr: 0.000116 grad: 0.0628 (0.0653) loss: 0.8375 (0.8387) time: 0.1810 data: 0.0951 max mem: 9390 +Train: [21] [2700/6250] eta: 0:10:05 lr: 0.000116 grad: 0.0636 (0.0653) loss: 0.8397 (0.8387) time: 0.1964 data: 0.0975 max mem: 9390 +Train: [21] [2800/6250] eta: 0:09:46 lr: 0.000116 grad: 0.0640 (0.0654) loss: 0.8364 (0.8387) time: 0.1622 data: 0.0677 max mem: 9390 +Train: [21] [2900/6250] eta: 0:09:29 lr: 0.000116 grad: 0.0658 (0.0655) loss: 0.8387 (0.8387) time: 0.1729 data: 0.0820 max mem: 9390 +Train: [21] [3000/6250] eta: 0:09:12 lr: 0.000116 grad: 0.0672 (0.0656) loss: 0.8362 (0.8387) time: 0.1761 data: 0.0902 max mem: 9390 +Train: [21] [3100/6250] eta: 0:08:55 lr: 0.000116 grad: 0.0648 (0.0656) loss: 0.8372 (0.8387) time: 0.1579 data: 0.0755 max mem: 9390 +Train: [21] [3200/6250] eta: 0:08:37 lr: 0.000116 grad: 0.0615 (0.0656) loss: 0.8427 (0.8386) time: 0.1639 data: 0.0781 max mem: 9390 +Train: [21] [3300/6250] eta: 0:08:20 lr: 0.000116 grad: 0.0636 (0.0656) loss: 0.8348 (0.8385) time: 0.1407 data: 0.0498 max mem: 9390 +Train: [21] [3400/6250] eta: 0:08:03 lr: 0.000116 grad: 0.0649 (0.0656) loss: 0.8350 (0.8384) time: 0.1711 data: 0.0813 max mem: 9390 +Train: [21] [3500/6250] eta: 0:07:45 lr: 0.000116 grad: 0.0708 (0.0657) loss: 0.8353 (0.8384) time: 0.1722 data: 0.0854 max mem: 9390 +Train: [21] [3600/6250] eta: 0:07:28 lr: 0.000116 grad: 0.0626 (0.0658) loss: 0.8362 (0.8383) time: 0.1760 data: 0.0878 max mem: 9390 +Train: [21] [3700/6250] eta: 0:07:11 lr: 0.000116 grad: 0.0615 (0.0657) loss: 0.8370 (0.8382) time: 0.1306 data: 0.0396 max mem: 9390 +Train: [21] [3800/6250] eta: 0:06:54 lr: 0.000116 grad: 0.0666 (0.0658) loss: 0.8328 (0.8382) time: 0.1770 data: 0.0937 max mem: 9390 +Train: [21] [3900/6250] eta: 0:06:37 lr: 0.000116 grad: 0.0606 (0.0658) loss: 0.8405 (0.8381) time: 0.1819 data: 0.0999 max mem: 9390 +Train: [21] [4000/6250] eta: 0:06:20 lr: 0.000116 grad: 0.0631 (0.0659) loss: 0.8372 (0.8380) time: 0.1486 data: 0.0583 max mem: 9390 +Train: [21] [4100/6250] eta: 0:06:03 lr: 0.000116 grad: 0.0671 (0.0659) loss: 0.8389 (0.8380) time: 0.1594 data: 0.0705 max mem: 9390 +Train: [21] [4200/6250] eta: 0:05:46 lr: 0.000116 grad: 0.0662 (0.0660) loss: 0.8331 (0.8379) time: 0.1821 data: 0.0927 max mem: 9390 +Train: [21] [4300/6250] eta: 0:05:29 lr: 0.000116 grad: 0.0636 (0.0660) loss: 0.8405 (0.8379) time: 0.1682 data: 0.0741 max mem: 9390 +Train: [21] [4400/6250] eta: 0:05:12 lr: 0.000116 grad: 0.0652 (0.0661) loss: 0.8350 (0.8378) time: 0.1680 data: 0.0798 max mem: 9390 +Train: [21] [4500/6250] eta: 0:04:55 lr: 0.000116 grad: 0.0639 (0.0661) loss: 0.8362 (0.8378) time: 0.1847 data: 0.1035 max mem: 9390 +Train: [21] [4600/6250] eta: 0:04:38 lr: 0.000116 grad: 0.0628 (0.0661) loss: 0.8377 (0.8378) time: 0.1704 data: 0.0832 max mem: 9390 +Train: [21] [4700/6250] eta: 0:04:21 lr: 0.000116 grad: 0.0638 (0.0661) loss: 0.8394 (0.8378) time: 0.1923 data: 0.1051 max mem: 9390 +Train: [21] [4800/6250] eta: 0:04:04 lr: 0.000116 grad: 0.0642 (0.0661) loss: 0.8347 (0.8378) time: 0.1571 data: 0.0672 max mem: 9390 +Train: [21] [4900/6250] eta: 0:03:47 lr: 0.000116 grad: 0.0647 (0.0661) loss: 0.8424 (0.8379) time: 0.1732 data: 0.0790 max mem: 9390 +Train: [21] [5000/6250] eta: 0:03:30 lr: 0.000116 grad: 0.0588 (0.0661) loss: 0.8410 (0.8379) time: 0.1733 data: 0.0842 max mem: 9390 +Train: [21] [5100/6250] eta: 0:03:13 lr: 0.000116 grad: 0.0624 (0.0661) loss: 0.8385 (0.8379) time: 0.1686 data: 0.0820 max mem: 9390 +Train: [21] [5200/6250] eta: 0:02:56 lr: 0.000116 grad: 0.0659 (0.0661) loss: 0.8376 (0.8379) time: 0.1235 data: 0.0399 max mem: 9390 +Train: [21] [5300/6250] eta: 0:02:39 lr: 0.000116 grad: 0.0645 (0.0661) loss: 0.8412 (0.8379) time: 0.1548 data: 0.0695 max mem: 9390 +Train: [21] [5400/6250] eta: 0:02:22 lr: 0.000116 grad: 0.0635 (0.0661) loss: 0.8402 (0.8380) time: 0.1638 data: 0.0682 max mem: 9390 +Train: [21] [5500/6250] eta: 0:02:06 lr: 0.000116 grad: 0.0656 (0.0661) loss: 0.8388 (0.8381) time: 0.1501 data: 0.0558 max mem: 9390 +Train: [21] [5600/6250] eta: 0:01:49 lr: 0.000115 grad: 0.0628 (0.0661) loss: 0.8399 (0.8381) time: 0.2036 data: 0.1217 max mem: 9390 +Train: [21] [5700/6250] eta: 0:01:32 lr: 0.000115 grad: 0.0651 (0.0661) loss: 0.8397 (0.8381) time: 0.1355 data: 0.0538 max mem: 9390 +Train: [21] [5800/6250] eta: 0:01:15 lr: 0.000115 grad: 0.0638 (0.0661) loss: 0.8435 (0.8382) time: 0.1636 data: 0.0682 max mem: 9390 +Train: [21] [5900/6250] eta: 0:00:58 lr: 0.000115 grad: 0.0631 (0.0661) loss: 0.8378 (0.8382) time: 0.1562 data: 0.0680 max mem: 9390 +Train: [21] [6000/6250] eta: 0:00:42 lr: 0.000115 grad: 0.0674 (0.0661) loss: 0.8394 (0.8382) time: 0.1686 data: 0.0744 max mem: 9390 +Train: [21] [6100/6250] eta: 0:00:25 lr: 0.000115 grad: 0.0662 (0.0661) loss: 0.8338 (0.8382) time: 0.1519 data: 0.0516 max mem: 9390 +Train: [21] [6200/6250] eta: 0:00:08 lr: 0.000115 grad: 0.0659 (0.0661) loss: 0.8358 (0.8382) time: 0.1616 data: 0.0686 max mem: 9390 +Train: [21] [6249/6250] eta: 0:00:00 lr: 0.000115 grad: 0.0664 (0.0661) loss: 0.8404 (0.8382) time: 0.1629 data: 0.0712 max mem: 9390 +Train: [21] Total time: 0:17:38 (0.1693 s / it) +Averaged stats: lr: 0.000115 grad: 0.0664 (0.0661) loss: 0.8404 (0.8382) +Eval (hcp-train-subset): [21] [ 0/62] eta: 0:05:57 loss: 0.8569 (0.8569) time: 5.7607 data: 5.7294 max mem: 9390 +Eval (hcp-train-subset): [21] [61/62] eta: 0:00:00 loss: 0.8443 (0.8447) time: 0.1813 data: 0.1547 max mem: 9390 +Eval (hcp-train-subset): [21] Total time: 0:00:15 (0.2465 s / it) +Averaged stats (hcp-train-subset): loss: 0.8443 (0.8447) +Eval (hcp-val): [21] [ 0/62] eta: 0:05:36 loss: 0.8408 (0.8408) time: 5.4240 data: 5.3944 max mem: 9390 +Eval (hcp-val): [21] [61/62] eta: 0:00:00 loss: 0.8395 (0.8404) time: 0.1012 data: 0.0759 max mem: 9390 +Eval (hcp-val): [21] Total time: 0:00:13 (0.2204 s / it) +Averaged stats (hcp-val): loss: 0.8395 (0.8404) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +Train: [22] [ 0/6250] eta: 11:19:56 lr: 0.000115 grad: 0.1150 (0.1150) loss: 0.8320 (0.8320) time: 6.5274 data: 6.4356 max mem: 9390 +Train: [22] [ 100/6250] eta: 0:22:08 lr: 0.000115 grad: 0.0670 (0.0715) loss: 0.8494 (0.8464) time: 0.1743 data: 0.0907 max mem: 9390 +Train: [22] [ 200/6250] eta: 0:19:27 lr: 0.000115 grad: 0.0682 (0.0704) loss: 0.8345 (0.8418) time: 0.1415 data: 0.0424 max mem: 9390 +Train: [22] [ 300/6250] eta: 0:18:30 lr: 0.000115 grad: 0.0627 (0.0686) loss: 0.8395 (0.8411) time: 0.1803 data: 0.0865 max mem: 9390 +Train: [22] [ 400/6250] eta: 0:17:48 lr: 0.000115 grad: 0.0646 (0.0673) loss: 0.8335 (0.8406) time: 0.1710 data: 0.0672 max mem: 9390 +Train: [22] [ 500/6250] eta: 0:17:21 lr: 0.000115 grad: 0.0595 (0.0668) loss: 0.8377 (0.8404) time: 0.1686 data: 0.0560 max mem: 9390 +Train: [22] [ 600/6250] eta: 0:16:52 lr: 0.000115 grad: 0.0623 (0.0671) loss: 0.8357 (0.8400) time: 0.1339 data: 0.0371 max mem: 9390 +Train: [22] [ 700/6250] eta: 0:16:33 lr: 0.000115 grad: 0.0690 (0.0670) loss: 0.8351 (0.8395) time: 0.1615 data: 0.0697 max mem: 9390 +Train: [22] [ 800/6250] eta: 0:16:19 lr: 0.000115 grad: 0.0645 (0.0669) loss: 0.8385 (0.8392) time: 0.1694 data: 0.0807 max mem: 9390 +Train: [22] [ 900/6250] eta: 0:16:02 lr: 0.000115 grad: 0.0622 (0.0668) loss: 0.8396 (0.8390) time: 0.1644 data: 0.0704 max mem: 9390 +Train: [22] [1000/6250] eta: 0:15:44 lr: 0.000115 grad: 0.0611 (0.0664) loss: 0.8416 (0.8390) time: 0.1620 data: 0.0728 max mem: 9390 +Train: [22] [1100/6250] eta: 0:15:24 lr: 0.000115 grad: 0.0640 (0.0662) loss: 0.8449 (0.8390) time: 0.1719 data: 0.0814 max mem: 9390 +Train: [22] [1200/6250] eta: 0:14:59 lr: 0.000115 grad: 0.0632 (0.0661) loss: 0.8356 (0.8389) time: 0.1603 data: 0.0748 max mem: 9390 +Train: [22] [1300/6250] eta: 0:14:41 lr: 0.000115 grad: 0.0616 (0.0661) loss: 0.8367 (0.8386) time: 0.1939 data: 0.1086 max mem: 9390 +Train: [22] [1400/6250] eta: 0:14:19 lr: 0.000115 grad: 0.0619 (0.0662) loss: 0.8391 (0.8385) time: 0.1768 data: 0.0830 max mem: 9390 +Train: [22] [1500/6250] eta: 0:13:56 lr: 0.000115 grad: 0.0629 (0.0660) loss: 0.8392 (0.8384) time: 0.1468 data: 0.0625 max mem: 9390 +Train: [22] [1600/6250] eta: 0:13:34 lr: 0.000115 grad: 0.0647 (0.0661) loss: 0.8357 (0.8381) time: 0.1685 data: 0.0780 max mem: 9390 +Train: [22] [1700/6250] eta: 0:13:12 lr: 0.000115 grad: 0.0645 (0.0660) loss: 0.8326 (0.8380) time: 0.1670 data: 0.0864 max mem: 9390 +Train: [22] [1800/6250] eta: 0:12:52 lr: 0.000115 grad: 0.0625 (0.0660) loss: 0.8370 (0.8378) time: 0.1725 data: 0.0817 max mem: 9390 +Train: [22] [1900/6250] eta: 0:12:33 lr: 0.000115 grad: 0.0620 (0.0660) loss: 0.8291 (0.8376) time: 0.1629 data: 0.0724 max mem: 9390 +Train: [22] [2000/6250] eta: 0:12:15 lr: 0.000115 grad: 0.0654 (0.0660) loss: 0.8332 (0.8374) time: 0.2015 data: 0.1252 max mem: 9390 +Train: [22] [2100/6250] eta: 0:11:54 lr: 0.000115 grad: 0.0639 (0.0661) loss: 0.8320 (0.8372) time: 0.1482 data: 0.0522 max mem: 9390 +Train: [22] [2200/6250] eta: 0:11:35 lr: 0.000115 grad: 0.0673 (0.0662) loss: 0.8332 (0.8370) time: 0.1156 data: 0.0235 max mem: 9390 +Train: [22] [2300/6250] eta: 0:11:17 lr: 0.000115 grad: 0.0655 (0.0663) loss: 0.8387 (0.8369) time: 0.1692 data: 0.0762 max mem: 9390 +Train: [22] [2400/6250] eta: 0:10:59 lr: 0.000115 grad: 0.0613 (0.0662) loss: 0.8331 (0.8368) time: 0.1801 data: 0.0922 max mem: 9390 +Train: [22] [2500/6250] eta: 0:10:40 lr: 0.000115 grad: 0.0634 (0.0662) loss: 0.8374 (0.8367) time: 0.1752 data: 0.0944 max mem: 9390 +Train: [22] [2600/6250] eta: 0:10:22 lr: 0.000115 grad: 0.0638 (0.0662) loss: 0.8385 (0.8366) time: 0.1418 data: 0.0596 max mem: 9390 +Train: [22] [2700/6250] eta: 0:10:05 lr: 0.000115 grad: 0.0610 (0.0661) loss: 0.8329 (0.8365) time: 0.1903 data: 0.1059 max mem: 9390 +Train: [22] [2800/6250] eta: 0:09:46 lr: 0.000115 grad: 0.0623 (0.0661) loss: 0.8346 (0.8365) time: 0.1631 data: 0.0736 max mem: 9390 +Train: [22] [2900/6250] eta: 0:09:28 lr: 0.000115 grad: 0.0672 (0.0661) loss: 0.8312 (0.8364) time: 0.1531 data: 0.0712 max mem: 9390 +Train: [22] [3000/6250] eta: 0:09:11 lr: 0.000115 grad: 0.0642 (0.0662) loss: 0.8368 (0.8364) time: 0.1561 data: 0.0678 max mem: 9390 +Train: [22] [3100/6250] eta: 0:08:54 lr: 0.000115 grad: 0.0652 (0.0661) loss: 0.8379 (0.8364) time: 0.1497 data: 0.0620 max mem: 9390 +Train: [22] [3200/6250] eta: 0:08:37 lr: 0.000115 grad: 0.0648 (0.0662) loss: 0.8347 (0.8364) time: 0.1716 data: 0.0821 max mem: 9390 +Train: [22] [3300/6250] eta: 0:08:20 lr: 0.000115 grad: 0.0626 (0.0662) loss: 0.8331 (0.8364) time: 0.1780 data: 0.0950 max mem: 9390 +Train: [22] [3400/6250] eta: 0:08:02 lr: 0.000115 grad: 0.0631 (0.0661) loss: 0.8356 (0.8364) time: 0.1838 data: 0.0865 max mem: 9390 +Train: [22] [3500/6250] eta: 0:07:45 lr: 0.000115 grad: 0.0650 (0.0661) loss: 0.8366 (0.8363) time: 0.1776 data: 0.0859 max mem: 9390 +Train: [22] [3600/6250] eta: 0:07:28 lr: 0.000115 grad: 0.0650 (0.0661) loss: 0.8368 (0.8363) time: 0.2119 data: 0.1234 max mem: 9390 +Train: [22] [3700/6250] eta: 0:07:11 lr: 0.000115 grad: 0.0590 (0.0661) loss: 0.8363 (0.8363) time: 0.1425 data: 0.0549 max mem: 9390 +Train: [22] [3800/6250] eta: 0:06:54 lr: 0.000115 grad: 0.0640 (0.0661) loss: 0.8362 (0.8363) time: 0.1730 data: 0.0883 max mem: 9390 +Train: [22] [3900/6250] eta: 0:06:37 lr: 0.000115 grad: 0.0648 (0.0660) loss: 0.8370 (0.8363) time: 0.1511 data: 0.0638 max mem: 9390 +Train: [22] [4000/6250] eta: 0:06:20 lr: 0.000115 grad: 0.0604 (0.0661) loss: 0.8411 (0.8363) time: 0.1756 data: 0.0929 max mem: 9390 +Train: [22] [4100/6250] eta: 0:06:03 lr: 0.000115 grad: 0.0602 (0.0660) loss: 0.8352 (0.8363) time: 0.1765 data: 0.0920 max mem: 9390 +Train: [22] [4200/6250] eta: 0:05:46 lr: 0.000115 grad: 0.0641 (0.0660) loss: 0.8422 (0.8363) time: 0.1830 data: 0.0980 max mem: 9390 +Train: [22] [4300/6250] eta: 0:05:29 lr: 0.000115 grad: 0.0658 (0.0661) loss: 0.8318 (0.8363) time: 0.1672 data: 0.0834 max mem: 9390 +Train: [22] [4400/6250] eta: 0:05:12 lr: 0.000115 grad: 0.0672 (0.0661) loss: 0.8338 (0.8362) time: 0.1988 data: 0.1176 max mem: 9390 +Train: [22] [4500/6250] eta: 0:04:55 lr: 0.000115 grad: 0.0654 (0.0661) loss: 0.8383 (0.8362) time: 0.1251 data: 0.0353 max mem: 9390 +Train: [22] [4600/6250] eta: 0:04:38 lr: 0.000115 grad: 0.0626 (0.0663) loss: 0.8340 (0.8362) time: 0.1678 data: 0.0804 max mem: 9390 +Train: [22] [4700/6250] eta: 0:04:21 lr: 0.000115 grad: 0.0630 (0.0663) loss: 0.8385 (0.8361) time: 0.1623 data: 0.0774 max mem: 9390 +Train: [22] [4800/6250] eta: 0:04:04 lr: 0.000115 grad: 0.0630 (0.0664) loss: 0.8354 (0.8361) time: 0.2070 data: 0.1241 max mem: 9390 +Train: [22] [4900/6250] eta: 0:03:47 lr: 0.000114 grad: 0.0660 (0.0664) loss: 0.8364 (0.8361) time: 0.1466 data: 0.0539 max mem: 9390 +Train: [22] [5000/6250] eta: 0:03:30 lr: 0.000114 grad: 0.0662 (0.0665) loss: 0.8344 (0.8360) time: 0.1449 data: 0.0627 max mem: 9390 +Train: [22] [5100/6250] eta: 0:03:13 lr: 0.000114 grad: 0.0679 (0.0665) loss: 0.8358 (0.8360) time: 0.1521 data: 0.0655 max mem: 9390 +Train: [22] [5200/6250] eta: 0:02:56 lr: 0.000114 grad: 0.0655 (0.0666) loss: 0.8299 (0.8359) time: 0.1607 data: 0.0802 max mem: 9390 +Train: [22] [5300/6250] eta: 0:02:40 lr: 0.000114 grad: 0.0695 (0.0666) loss: 0.8359 (0.8359) time: 0.1813 data: 0.0912 max mem: 9390 +Train: [22] [5400/6250] eta: 0:02:23 lr: 0.000114 grad: 0.0714 (0.0667) loss: 0.8347 (0.8359) time: 0.1812 data: 0.0974 max mem: 9390 +Train: [22] [5500/6250] eta: 0:02:06 lr: 0.000114 grad: 0.0697 (0.0668) loss: 0.8359 (0.8359) time: 0.1884 data: 0.1065 max mem: 9390 +Train: [22] [5600/6250] eta: 0:01:49 lr: 0.000114 grad: 0.0637 (0.0668) loss: 0.8352 (0.8359) time: 0.1612 data: 0.0782 max mem: 9390 +Train: [22] [5700/6250] eta: 0:01:32 lr: 0.000114 grad: 0.0665 (0.0669) loss: 0.8318 (0.8359) time: 0.1760 data: 0.0940 max mem: 9390 +Train: [22] [5800/6250] eta: 0:01:15 lr: 0.000114 grad: 0.0635 (0.0669) loss: 0.8315 (0.8359) time: 0.1819 data: 0.0958 max mem: 9390 +Train: [22] [5900/6250] eta: 0:00:58 lr: 0.000114 grad: 0.0683 (0.0670) loss: 0.8350 (0.8358) time: 0.1580 data: 0.0717 max mem: 9390 +Train: [22] [6000/6250] eta: 0:00:42 lr: 0.000114 grad: 0.0689 (0.0670) loss: 0.8247 (0.8358) time: 0.1710 data: 0.0896 max mem: 9390 +Train: [22] [6100/6250] eta: 0:00:25 lr: 0.000114 grad: 0.0665 (0.0670) loss: 0.8393 (0.8358) time: 0.1474 data: 0.0657 max mem: 9390 +Train: [22] [6200/6250] eta: 0:00:08 lr: 0.000114 grad: 0.0650 (0.0670) loss: 0.8363 (0.8358) time: 0.1819 data: 0.0981 max mem: 9390 +Train: [22] [6249/6250] eta: 0:00:00 lr: 0.000114 grad: 0.0633 (0.0670) loss: 0.8348 (0.8358) time: 0.1747 data: 0.0926 max mem: 9390 +Train: [22] Total time: 0:17:38 (0.1693 s / it) +Averaged stats: lr: 0.000114 grad: 0.0633 (0.0670) loss: 0.8348 (0.8358) +Eval (hcp-train-subset): [22] [ 0/62] eta: 0:05:29 loss: 0.8566 (0.8566) time: 5.3170 data: 5.2839 max mem: 9390 +Eval (hcp-train-subset): [22] [61/62] eta: 0:00:00 loss: 0.8425 (0.8441) time: 0.1132 data: 0.0885 max mem: 9390 +Eval (hcp-train-subset): [22] Total time: 0:00:14 (0.2397 s / it) +Averaged stats (hcp-train-subset): loss: 0.8425 (0.8441) +Eval (hcp-val): [22] [ 0/62] eta: 0:03:55 loss: 0.8389 (0.8389) time: 3.7954 data: 3.7193 max mem: 9390 +Eval (hcp-val): [22] [61/62] eta: 0:00:00 loss: 0.8402 (0.8408) time: 0.1238 data: 0.0985 max mem: 9390 +Eval (hcp-val): [22] Total time: 0:00:13 (0.2166 s / it) +Averaged stats (hcp-val): loss: 0.8402 (0.8408) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +Train: [23] [ 0/6250] eta: 6:45:46 lr: 0.000114 grad: 0.0477 (0.0477) loss: 0.8702 (0.8702) time: 3.8954 data: 3.6440 max mem: 9390 +Train: [23] [ 100/6250] eta: 0:21:44 lr: 0.000114 grad: 0.0667 (0.0744) loss: 0.8368 (0.8353) time: 0.1519 data: 0.0620 max mem: 9390 +Train: [23] [ 200/6250] eta: 0:19:47 lr: 0.000114 grad: 0.0681 (0.0702) loss: 0.8367 (0.8357) time: 0.1751 data: 0.0832 max mem: 9390 +Train: [23] [ 300/6250] eta: 0:18:38 lr: 0.000114 grad: 0.0619 (0.0693) loss: 0.8422 (0.8361) time: 0.1790 data: 0.0843 max mem: 9390 +Train: [23] [ 400/6250] eta: 0:17:35 lr: 0.000114 grad: 0.0645 (0.0685) loss: 0.8332 (0.8370) time: 0.1644 data: 0.0668 max mem: 9390 +Train: [23] [ 500/6250] eta: 0:17:04 lr: 0.000114 grad: 0.0621 (0.0674) loss: 0.8422 (0.8375) time: 0.1721 data: 0.0713 max mem: 9390 +Train: [23] [ 600/6250] eta: 0:16:35 lr: 0.000114 grad: 0.0575 (0.0665) loss: 0.8455 (0.8383) time: 0.1735 data: 0.0822 max mem: 9390 +Train: [23] [ 700/6250] eta: 0:16:06 lr: 0.000114 grad: 0.0602 (0.0660) loss: 0.8373 (0.8386) time: 0.1417 data: 0.0352 max mem: 9390 +Train: [23] [ 800/6250] eta: 0:15:45 lr: 0.000114 grad: 0.0649 (0.0659) loss: 0.8438 (0.8390) time: 0.1848 data: 0.0872 max mem: 9390 +Train: [23] [ 900/6250] eta: 0:15:28 lr: 0.000114 grad: 0.0660 (0.0658) loss: 0.8359 (0.8389) time: 0.1462 data: 0.0510 max mem: 9390 +Train: [23] [1000/6250] eta: 0:15:05 lr: 0.000114 grad: 0.0626 (0.0656) loss: 0.8384 (0.8388) time: 0.1480 data: 0.0565 max mem: 9390 +Train: [23] [1100/6250] eta: 0:14:44 lr: 0.000114 grad: 0.0631 (0.0654) loss: 0.8365 (0.8386) time: 0.1772 data: 0.0860 max mem: 9390 +Train: [23] [1200/6250] eta: 0:14:22 lr: 0.000114 grad: 0.0594 (0.0652) loss: 0.8325 (0.8385) time: 0.1610 data: 0.0658 max mem: 9390 +Train: [23] [1300/6250] eta: 0:14:01 lr: 0.000114 grad: 0.0700 (0.0654) loss: 0.8340 (0.8380) time: 0.1558 data: 0.0676 max mem: 9390 +Train: [23] [1400/6250] eta: 0:13:42 lr: 0.000114 grad: 0.0643 (0.0654) loss: 0.8355 (0.8379) time: 0.1629 data: 0.0595 max mem: 9390 +Train: [23] [1500/6250] eta: 0:13:23 lr: 0.000114 grad: 0.0642 (0.0654) loss: 0.8435 (0.8378) time: 0.1689 data: 0.0712 max mem: 9390 +Train: [23] [1600/6250] eta: 0:13:06 lr: 0.000114 grad: 0.0633 (0.0655) loss: 0.8396 (0.8376) time: 0.1460 data: 0.0629 max mem: 9390 +Train: [23] [1700/6250] eta: 0:12:47 lr: 0.000114 grad: 0.0659 (0.0656) loss: 0.8317 (0.8374) time: 0.1541 data: 0.0603 max mem: 9390 +Train: [23] [1800/6250] eta: 0:12:29 lr: 0.000114 grad: 0.0650 (0.0657) loss: 0.8351 (0.8372) time: 0.1813 data: 0.0910 max mem: 9390 +Train: [23] [1900/6250] eta: 0:12:12 lr: 0.000114 grad: 0.0692 (0.0658) loss: 0.8320 (0.8370) time: 0.1600 data: 0.0784 max mem: 9390 +Train: [23] [2000/6250] eta: 0:11:55 lr: 0.000114 grad: 0.0630 (0.0659) loss: 0.8301 (0.8369) time: 0.1664 data: 0.0809 max mem: 9390 +Train: [23] [2100/6250] eta: 0:11:37 lr: 0.000114 grad: 0.0646 (0.0658) loss: 0.8371 (0.8368) time: 0.1636 data: 0.0771 max mem: 9390 +Train: [23] [2200/6250] eta: 0:11:21 lr: 0.000114 grad: 0.0631 (0.0659) loss: 0.8366 (0.8368) time: 0.1600 data: 0.0718 max mem: 9390 +Train: [23] [2300/6250] eta: 0:11:03 lr: 0.000114 grad: 0.0636 (0.0659) loss: 0.8363 (0.8369) time: 0.1656 data: 0.0740 max mem: 9390 +Train: [23] [2400/6250] eta: 0:10:46 lr: 0.000114 grad: 0.0592 (0.0658) loss: 0.8323 (0.8369) time: 0.1690 data: 0.0740 max mem: 9390 +Train: [23] [2500/6250] eta: 0:10:28 lr: 0.000114 grad: 0.0615 (0.0659) loss: 0.8370 (0.8369) time: 0.1577 data: 0.0645 max mem: 9390 +Train: [23] [2600/6250] eta: 0:10:11 lr: 0.000114 grad: 0.0670 (0.0662) loss: 0.8347 (0.8369) time: 0.1564 data: 0.0678 max mem: 9390 +Train: [23] [2700/6250] eta: 0:09:53 lr: 0.000114 grad: 0.0724 (0.0665) loss: 0.8348 (0.8369) time: 0.1543 data: 0.0590 max mem: 9390 +Train: [23] [2800/6250] eta: 0:09:37 lr: 0.000114 grad: 0.0659 (0.0664) loss: 0.8350 (0.8369) time: 0.1806 data: 0.0875 max mem: 9390 +Train: [23] [2900/6250] eta: 0:09:20 lr: 0.000114 grad: 0.0662 (0.0664) loss: 0.8341 (0.8368) time: 0.1608 data: 0.0728 max mem: 9390 +Train: [23] [3000/6250] eta: 0:09:02 lr: 0.000114 grad: 0.0651 (0.0664) loss: 0.8394 (0.8367) time: 0.1551 data: 0.0599 max mem: 9390 +Train: [23] [3100/6250] eta: 0:08:46 lr: 0.000114 grad: 0.0670 (0.0665) loss: 0.8343 (0.8367) time: 0.1955 data: 0.1137 max mem: 9390 +Train: [23] [3200/6250] eta: 0:08:28 lr: 0.000114 grad: 0.0628 (0.0665) loss: 0.8376 (0.8366) time: 0.1655 data: 0.0750 max mem: 9390 +Train: [23] [3300/6250] eta: 0:08:12 lr: 0.000114 grad: 0.0631 (0.0665) loss: 0.8383 (0.8367) time: 0.1658 data: 0.0745 max mem: 9390 +Train: [23] [3400/6250] eta: 0:07:55 lr: 0.000114 grad: 0.0626 (0.0665) loss: 0.8359 (0.8366) time: 0.1712 data: 0.0823 max mem: 9390 +Train: [23] [3500/6250] eta: 0:07:38 lr: 0.000114 grad: 0.0640 (0.0665) loss: 0.8344 (0.8365) time: 0.1733 data: 0.0915 max mem: 9390 +Train: [23] [3600/6250] eta: 0:07:21 lr: 0.000114 grad: 0.0646 (0.0665) loss: 0.8368 (0.8365) time: 0.1711 data: 0.0821 max mem: 9390 +Train: [23] [3700/6250] eta: 0:07:04 lr: 0.000114 grad: 0.0620 (0.0665) loss: 0.8322 (0.8365) time: 0.1659 data: 0.0803 max mem: 9390 +Train: [23] [3800/6250] eta: 0:06:48 lr: 0.000114 grad: 0.0626 (0.0666) loss: 0.8323 (0.8364) time: 0.1837 data: 0.0943 max mem: 9390 +Train: [23] [3900/6250] eta: 0:06:31 lr: 0.000114 grad: 0.0631 (0.0667) loss: 0.8324 (0.8364) time: 0.1651 data: 0.0758 max mem: 9390 +Train: [23] [4000/6250] eta: 0:06:14 lr: 0.000113 grad: 0.0659 (0.0668) loss: 0.8350 (0.8363) time: 0.1634 data: 0.0766 max mem: 9390 +Train: [23] [4100/6250] eta: 0:05:58 lr: 0.000113 grad: 0.0665 (0.0668) loss: 0.8382 (0.8363) time: 0.1673 data: 0.0826 max mem: 9390 +Train: [23] [4200/6250] eta: 0:05:41 lr: 0.000113 grad: 0.0690 (0.0669) loss: 0.8363 (0.8363) time: 0.2049 data: 0.1176 max mem: 9390 +Train: [23] [4300/6250] eta: 0:05:25 lr: 0.000113 grad: 0.0660 (0.0669) loss: 0.8340 (0.8363) time: 0.1749 data: 0.0754 max mem: 9390 +Train: [23] [4400/6250] eta: 0:05:08 lr: 0.000113 grad: 0.0654 (0.0670) loss: 0.8354 (0.8362) time: 0.1505 data: 0.0691 max mem: 9390 +Train: [23] [4500/6250] eta: 0:04:52 lr: 0.000113 grad: 0.0653 (0.0670) loss: 0.8356 (0.8362) time: 0.1707 data: 0.0834 max mem: 9390 +Train: [23] [4600/6250] eta: 0:04:35 lr: 0.000113 grad: 0.0649 (0.0670) loss: 0.8381 (0.8362) time: 0.1772 data: 0.0906 max mem: 9390 +Train: [23] [4700/6250] eta: 0:04:19 lr: 0.000113 grad: 0.0633 (0.0671) loss: 0.8357 (0.8362) time: 0.1819 data: 0.1000 max mem: 9390 +Train: [23] [4800/6250] eta: 0:04:02 lr: 0.000113 grad: 0.0709 (0.0671) loss: 0.8356 (0.8362) time: 0.1780 data: 0.0945 max mem: 9390 +Train: [23] [4900/6250] eta: 0:03:45 lr: 0.000113 grad: 0.0701 (0.0672) loss: 0.8367 (0.8362) time: 0.1737 data: 0.0815 max mem: 9390 +Train: [23] [5000/6250] eta: 0:03:28 lr: 0.000113 grad: 0.0666 (0.0673) loss: 0.8376 (0.8362) time: 0.1727 data: 0.0860 max mem: 9390 +Train: [23] [5100/6250] eta: 0:03:12 lr: 0.000113 grad: 0.0709 (0.0674) loss: 0.8348 (0.8362) time: 0.1543 data: 0.0558 max mem: 9390 +Train: [23] [5200/6250] eta: 0:02:55 lr: 0.000113 grad: 0.0630 (0.0674) loss: 0.8378 (0.8362) time: 0.1603 data: 0.0626 max mem: 9390 +Train: [23] [5300/6250] eta: 0:02:38 lr: 0.000113 grad: 0.0691 (0.0674) loss: 0.8422 (0.8362) time: 0.1740 data: 0.0788 max mem: 9390 +Train: [23] [5400/6250] eta: 0:02:21 lr: 0.000113 grad: 0.0662 (0.0675) loss: 0.8327 (0.8362) time: 0.1836 data: 0.0912 max mem: 9390 +Train: [23] [5500/6250] eta: 0:02:04 lr: 0.000113 grad: 0.0659 (0.0675) loss: 0.8320 (0.8361) time: 0.1641 data: 0.0700 max mem: 9390 +Train: [23] [5600/6250] eta: 0:01:48 lr: 0.000113 grad: 0.0618 (0.0675) loss: 0.8365 (0.8361) time: 0.1474 data: 0.0447 max mem: 9390 +Train: [23] [5700/6250] eta: 0:01:31 lr: 0.000113 grad: 0.0659 (0.0676) loss: 0.8388 (0.8362) time: 0.1731 data: 0.0726 max mem: 9390 +Train: [23] [5800/6250] eta: 0:01:14 lr: 0.000113 grad: 0.0630 (0.0676) loss: 0.8370 (0.8362) time: 0.1553 data: 0.0583 max mem: 9390 +Train: [23] [5900/6250] eta: 0:00:58 lr: 0.000113 grad: 0.0629 (0.0676) loss: 0.8359 (0.8362) time: 0.1799 data: 0.0950 max mem: 9390 +Train: [23] [6000/6250] eta: 0:00:41 lr: 0.000113 grad: 0.0621 (0.0675) loss: 0.8370 (0.8363) time: 0.1781 data: 0.0898 max mem: 9390 +Train: [23] [6100/6250] eta: 0:00:25 lr: 0.000113 grad: 0.0699 (0.0675) loss: 0.8370 (0.8363) time: 0.1595 data: 0.0637 max mem: 9390 +Train: [23] [6200/6250] eta: 0:00:08 lr: 0.000113 grad: 0.0652 (0.0675) loss: 0.8376 (0.8363) time: 0.1714 data: 0.0818 max mem: 9390 +Train: [23] [6249/6250] eta: 0:00:00 lr: 0.000113 grad: 0.0698 (0.0675) loss: 0.8381 (0.8363) time: 0.1550 data: 0.0594 max mem: 9390 +Train: [23] Total time: 0:17:27 (0.1677 s / it) +Averaged stats: lr: 0.000113 grad: 0.0698 (0.0675) loss: 0.8381 (0.8363) +Eval (hcp-train-subset): [23] [ 0/62] eta: 0:05:52 loss: 0.8545 (0.8545) time: 5.6806 data: 5.6507 max mem: 9390 +Eval (hcp-train-subset): [23] [61/62] eta: 0:00:00 loss: 0.8422 (0.8443) time: 0.1598 data: 0.1352 max mem: 9390 +Eval (hcp-train-subset): [23] Total time: 0:00:14 (0.2416 s / it) +Averaged stats (hcp-train-subset): loss: 0.8422 (0.8443) +Eval (hcp-val): [23] [ 0/62] eta: 0:06:15 loss: 0.8360 (0.8360) time: 6.0594 data: 6.0242 max mem: 9390 +Eval (hcp-val): [23] [61/62] eta: 0:00:00 loss: 0.8419 (0.8404) time: 0.1292 data: 0.1043 max mem: 9390 +Eval (hcp-val): [23] Total time: 0:00:13 (0.2229 s / it) +Averaged stats (hcp-val): loss: 0.8419 (0.8404) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +Train: [24] [ 0/6250] eta: 10:30:46 lr: 0.000113 grad: 0.0554 (0.0554) loss: 0.8447 (0.8447) time: 6.0554 data: 5.9121 max mem: 9390 +Train: [24] [ 100/6250] eta: 0:22:12 lr: 0.000113 grad: 0.0605 (0.0753) loss: 0.8342 (0.8371) time: 0.1629 data: 0.0656 max mem: 9390 +Train: [24] [ 200/6250] eta: 0:19:42 lr: 0.000113 grad: 0.0622 (0.0711) loss: 0.8373 (0.8344) time: 0.1811 data: 0.0832 max mem: 9390 +Train: [24] [ 300/6250] eta: 0:18:34 lr: 0.000113 grad: 0.0653 (0.0704) loss: 0.8230 (0.8330) time: 0.1656 data: 0.0679 max mem: 9390 +Train: [24] [ 400/6250] eta: 0:17:45 lr: 0.000113 grad: 0.0641 (0.0697) loss: 0.8334 (0.8330) time: 0.1502 data: 0.0556 max mem: 9390 +Train: [24] [ 500/6250] eta: 0:17:17 lr: 0.000113 grad: 0.0708 (0.0694) loss: 0.8282 (0.8330) time: 0.1961 data: 0.0881 max mem: 9390 +Train: [24] [ 600/6250] eta: 0:16:55 lr: 0.000113 grad: 0.0646 (0.0693) loss: 0.8312 (0.8327) time: 0.2032 data: 0.1161 max mem: 9390 +Train: [24] [ 700/6250] eta: 0:16:35 lr: 0.000113 grad: 0.0669 (0.0691) loss: 0.8294 (0.8327) time: 0.1834 data: 0.0970 max mem: 9390 +Train: [24] [ 800/6250] eta: 0:16:17 lr: 0.000113 grad: 0.0634 (0.0689) loss: 0.8258 (0.8326) time: 0.1745 data: 0.0755 max mem: 9390 +Train: [24] [ 900/6250] eta: 0:15:54 lr: 0.000113 grad: 0.0628 (0.0687) loss: 0.8314 (0.8326) time: 0.1461 data: 0.0473 max mem: 9390 +Train: [24] [1000/6250] eta: 0:15:34 lr: 0.000113 grad: 0.0638 (0.0684) loss: 0.8339 (0.8328) time: 0.1595 data: 0.0723 max mem: 9390 +Train: [24] [1100/6250] eta: 0:15:10 lr: 0.000113 grad: 0.0639 (0.0681) loss: 0.8341 (0.8329) time: 0.1476 data: 0.0603 max mem: 9390 +Train: [24] [1200/6250] eta: 0:14:48 lr: 0.000113 grad: 0.0651 (0.0680) loss: 0.8308 (0.8329) time: 0.1768 data: 0.0900 max mem: 9390 +Train: [24] [1300/6250] eta: 0:14:26 lr: 0.000113 grad: 0.0626 (0.0679) loss: 0.8372 (0.8329) time: 0.1678 data: 0.0769 max mem: 9390 +Train: [24] [1400/6250] eta: 0:14:07 lr: 0.000113 grad: 0.0617 (0.0678) loss: 0.8369 (0.8329) time: 0.1757 data: 0.0820 max mem: 9390 +Train: [24] [1500/6250] eta: 0:13:47 lr: 0.000113 grad: 0.0625 (0.0676) loss: 0.8321 (0.8330) time: 0.1451 data: 0.0510 max mem: 9390 +Train: [24] [1600/6250] eta: 0:13:26 lr: 0.000113 grad: 0.0651 (0.0676) loss: 0.8342 (0.8331) time: 0.1779 data: 0.0965 max mem: 9390 +Train: [24] [1700/6250] eta: 0:13:07 lr: 0.000113 grad: 0.0638 (0.0676) loss: 0.8334 (0.8332) time: 0.1710 data: 0.0870 max mem: 9390 +Train: [24] [1800/6250] eta: 0:12:48 lr: 0.000113 grad: 0.0636 (0.0676) loss: 0.8313 (0.8333) time: 0.1540 data: 0.0673 max mem: 9390 +Train: [24] [1900/6250] eta: 0:12:28 lr: 0.000113 grad: 0.0656 (0.0675) loss: 0.8316 (0.8333) time: 0.1674 data: 0.0790 max mem: 9390 +Train: [24] [2000/6250] eta: 0:12:11 lr: 0.000113 grad: 0.0688 (0.0674) loss: 0.8332 (0.8334) time: 0.1595 data: 0.0645 max mem: 9390 +Train: [24] [2100/6250] eta: 0:11:53 lr: 0.000113 grad: 0.0646 (0.0675) loss: 0.8349 (0.8335) time: 0.1759 data: 0.0883 max mem: 9390 +Train: [24] [2200/6250] eta: 0:11:34 lr: 0.000113 grad: 0.0668 (0.0675) loss: 0.8316 (0.8335) time: 0.1678 data: 0.0848 max mem: 9390 +Train: [24] [2300/6250] eta: 0:11:16 lr: 0.000113 grad: 0.0683 (0.0675) loss: 0.8312 (0.8335) time: 0.1494 data: 0.0672 max mem: 9390 +Train: [24] [2400/6250] eta: 0:10:58 lr: 0.000113 grad: 0.0633 (0.0674) loss: 0.8339 (0.8336) time: 0.1483 data: 0.0625 max mem: 9390 +Train: [24] [2500/6250] eta: 0:10:39 lr: 0.000113 grad: 0.0647 (0.0674) loss: 0.8362 (0.8336) time: 0.1636 data: 0.0747 max mem: 9390 +Train: [24] [2600/6250] eta: 0:10:22 lr: 0.000113 grad: 0.0669 (0.0674) loss: 0.8280 (0.8336) time: 0.2094 data: 0.1178 max mem: 9390 +Train: [24] [2700/6250] eta: 0:10:04 lr: 0.000113 grad: 0.0652 (0.0677) loss: 0.8291 (0.8334) time: 0.1806 data: 0.0983 max mem: 9390 +Train: [24] [2800/6250] eta: 0:09:47 lr: 0.000113 grad: 0.0646 (0.0676) loss: 0.8305 (0.8334) time: 0.1506 data: 0.0590 max mem: 9390 +Train: [24] [2900/6250] eta: 0:09:30 lr: 0.000112 grad: 0.0680 (0.0677) loss: 0.8348 (0.8334) time: 0.1530 data: 0.0671 max mem: 9390 +Train: [24] [3000/6250] eta: 0:09:12 lr: 0.000112 grad: 0.0703 (0.0677) loss: 0.8291 (0.8334) time: 0.1570 data: 0.0729 max mem: 9390 +Train: [24] [3100/6250] eta: 0:08:54 lr: 0.000112 grad: 0.0684 (0.0678) loss: 0.8318 (0.8334) time: 0.1565 data: 0.0705 max mem: 9390 +Train: [24] [3200/6250] eta: 0:08:37 lr: 0.000112 grad: 0.0591 (0.0678) loss: 0.8339 (0.8334) time: 0.1628 data: 0.0739 max mem: 9390 +Train: [24] [3300/6250] eta: 0:08:20 lr: 0.000112 grad: 0.0709 (0.0678) loss: 0.8310 (0.8334) time: 0.1558 data: 0.0743 max mem: 9390 +Train: [24] [3400/6250] eta: 0:08:03 lr: 0.000112 grad: 0.0639 (0.0678) loss: 0.8313 (0.8335) time: 0.1515 data: 0.0676 max mem: 9390 +Train: [24] [3500/6250] eta: 0:07:46 lr: 0.000112 grad: 0.0668 (0.0678) loss: 0.8317 (0.8334) time: 0.1787 data: 0.0754 max mem: 9390 +Train: [24] [3600/6250] eta: 0:07:28 lr: 0.000112 grad: 0.0605 (0.0678) loss: 0.8387 (0.8335) time: 0.1591 data: 0.0648 max mem: 9390 +Train: [24] [3700/6250] eta: 0:07:12 lr: 0.000112 grad: 0.0656 (0.0679) loss: 0.8359 (0.8335) time: 0.1570 data: 0.0637 max mem: 9390 +Train: [24] [3800/6250] eta: 0:06:54 lr: 0.000112 grad: 0.0663 (0.0678) loss: 0.8415 (0.8336) time: 0.1744 data: 0.0913 max mem: 9390 +Train: [24] [3900/6250] eta: 0:06:37 lr: 0.000112 grad: 0.0651 (0.0679) loss: 0.8349 (0.8336) time: 0.1571 data: 0.0624 max mem: 9390 +Train: [24] [4000/6250] eta: 0:06:20 lr: 0.000112 grad: 0.0603 (0.0678) loss: 0.8360 (0.8337) time: 0.1391 data: 0.0562 max mem: 9390 +Train: [24] [4100/6250] eta: 0:06:03 lr: 0.000112 grad: 0.0660 (0.0678) loss: 0.8427 (0.8338) time: 0.1627 data: 0.0735 max mem: 9390 +Train: [24] [4200/6250] eta: 0:05:46 lr: 0.000112 grad: 0.0670 (0.0678) loss: 0.8306 (0.8338) time: 0.1684 data: 0.0865 max mem: 9390 +Train: [24] [4300/6250] eta: 0:05:29 lr: 0.000112 grad: 0.0674 (0.0678) loss: 0.8344 (0.8338) time: 0.2151 data: 0.1292 max mem: 9390 +Train: [24] [4400/6250] eta: 0:05:12 lr: 0.000112 grad: 0.0676 (0.0678) loss: 0.8378 (0.8339) time: 0.1664 data: 0.0764 max mem: 9390 +Train: [24] [4500/6250] eta: 0:04:55 lr: 0.000112 grad: 0.0660 (0.0677) loss: 0.8340 (0.8339) time: 0.1588 data: 0.0729 max mem: 9390 +Train: [24] [4600/6250] eta: 0:04:38 lr: 0.000112 grad: 0.0614 (0.0677) loss: 0.8403 (0.8339) time: 0.1671 data: 0.0826 max mem: 9390 +Train: [24] [4700/6250] eta: 0:04:21 lr: 0.000112 grad: 0.0657 (0.0677) loss: 0.8349 (0.8340) time: 0.1630 data: 0.0739 max mem: 9390 +Train: [24] [4800/6250] eta: 0:04:04 lr: 0.000112 grad: 0.0713 (0.0678) loss: 0.8350 (0.8340) time: 0.1578 data: 0.0741 max mem: 9390 +Train: [24] [4900/6250] eta: 0:03:47 lr: 0.000112 grad: 0.0686 (0.0678) loss: 0.8340 (0.8340) time: 0.1810 data: 0.0996 max mem: 9390 +Train: [24] [5000/6250] eta: 0:03:30 lr: 0.000112 grad: 0.0671 (0.0678) loss: 0.8339 (0.8340) time: 0.1488 data: 0.0572 max mem: 9390 +Train: [24] [5100/6250] eta: 0:03:13 lr: 0.000112 grad: 0.0673 (0.0678) loss: 0.8326 (0.8340) time: 0.1919 data: 0.1061 max mem: 9390 +Train: [24] [5200/6250] eta: 0:02:56 lr: 0.000112 grad: 0.0652 (0.0679) loss: 0.8330 (0.8340) time: 0.1702 data: 0.0853 max mem: 9390 +Train: [24] [5300/6250] eta: 0:02:39 lr: 0.000112 grad: 0.0610 (0.0679) loss: 0.8350 (0.8340) time: 0.1708 data: 0.0845 max mem: 9390 +Train: [24] [5400/6250] eta: 0:02:23 lr: 0.000112 grad: 0.0717 (0.0679) loss: 0.8328 (0.8341) time: 0.1572 data: 0.0745 max mem: 9390 +Train: [24] [5500/6250] eta: 0:02:06 lr: 0.000112 grad: 0.0673 (0.0679) loss: 0.8340 (0.8341) time: 0.1572 data: 0.0682 max mem: 9390 +Train: [24] [5600/6250] eta: 0:01:49 lr: 0.000112 grad: 0.0655 (0.0679) loss: 0.8382 (0.8341) time: 0.1827 data: 0.0958 max mem: 9390 +Train: [24] [5700/6250] eta: 0:01:32 lr: 0.000112 grad: 0.0637 (0.0680) loss: 0.8329 (0.8341) time: 0.1530 data: 0.0613 max mem: 9390 +Train: [24] [5800/6250] eta: 0:01:15 lr: 0.000112 grad: 0.0739 (0.0681) loss: 0.8334 (0.8341) time: 0.1643 data: 0.0760 max mem: 9390 +Train: [24] [5900/6250] eta: 0:00:58 lr: 0.000112 grad: 0.0732 (0.0681) loss: 0.8333 (0.8340) time: 0.1842 data: 0.0960 max mem: 9390 +Train: [24] [6000/6250] eta: 0:00:42 lr: 0.000112 grad: 0.0645 (0.0682) loss: 0.8360 (0.8340) time: 0.1532 data: 0.0656 max mem: 9390 +Train: [24] [6100/6250] eta: 0:00:25 lr: 0.000112 grad: 0.0705 (0.0682) loss: 0.8392 (0.8340) time: 0.1678 data: 0.0816 max mem: 9390 +Train: [24] [6200/6250] eta: 0:00:08 lr: 0.000112 grad: 0.0644 (0.0683) loss: 0.8374 (0.8340) time: 0.1867 data: 0.1010 max mem: 9390 +Train: [24] [6249/6250] eta: 0:00:00 lr: 0.000112 grad: 0.0727 (0.0683) loss: 0.8305 (0.8340) time: 0.1741 data: 0.0888 max mem: 9390 +Train: [24] Total time: 0:17:38 (0.1693 s / it) +Averaged stats: lr: 0.000112 grad: 0.0727 (0.0683) loss: 0.8305 (0.8340) +Eval (hcp-train-subset): [24] [ 0/62] eta: 0:06:40 loss: 0.8582 (0.8582) time: 6.4551 data: 6.2760 max mem: 9390 +Eval (hcp-train-subset): [24] [61/62] eta: 0:00:00 loss: 0.8449 (0.8458) time: 0.1438 data: 0.1191 max mem: 9390 +Eval (hcp-train-subset): [24] Total time: 0:00:15 (0.2438 s / it) +Averaged stats (hcp-train-subset): loss: 0.8449 (0.8458) +Making plots (hcp-train-subset): example=1 +Eval (hcp-val): [24] [ 0/62] eta: 0:05:17 loss: 0.8412 (0.8412) time: 5.1221 data: 5.0775 max mem: 9390 +Eval (hcp-val): [24] [61/62] eta: 0:00:00 loss: 0.8406 (0.8417) time: 0.1458 data: 0.1207 max mem: 9390 +Eval (hcp-val): [24] Total time: 0:00:13 (0.2185 s / it) +Averaged stats (hcp-val): loss: 0.8406 (0.8417) +Making plots (hcp-val): example=10 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +Train: [25] [ 0/6250] eta: 10:04:50 lr: 0.000112 grad: 0.1262 (0.1262) loss: 0.8340 (0.8340) time: 5.8064 data: 5.6937 max mem: 9390 +Train: [25] [ 100/6250] eta: 0:22:13 lr: 0.000112 grad: 0.0641 (0.0697) loss: 0.8446 (0.8477) time: 0.1495 data: 0.0577 max mem: 9390 +Train: [25] [ 200/6250] eta: 0:19:56 lr: 0.000112 grad: 0.0631 (0.0686) loss: 0.8351 (0.8412) time: 0.1934 data: 0.0957 max mem: 9390 +Train: [25] [ 300/6250] eta: 0:18:33 lr: 0.000112 grad: 0.0663 (0.0684) loss: 0.8420 (0.8407) time: 0.1580 data: 0.0716 max mem: 9390 +Train: [25] [ 400/6250] eta: 0:17:45 lr: 0.000112 grad: 0.0641 (0.0680) loss: 0.8442 (0.8405) time: 0.1586 data: 0.0619 max mem: 9390 +Train: [25] [ 500/6250] eta: 0:17:04 lr: 0.000112 grad: 0.0651 (0.0677) loss: 0.8409 (0.8404) time: 0.1652 data: 0.0758 max mem: 9390 +Train: [25] [ 600/6250] eta: 0:16:26 lr: 0.000112 grad: 0.0660 (0.0676) loss: 0.8388 (0.8401) time: 0.1447 data: 0.0467 max mem: 9390 +Train: [25] [ 700/6250] eta: 0:16:05 lr: 0.000112 grad: 0.0639 (0.0678) loss: 0.8441 (0.8400) time: 0.1626 data: 0.0704 max mem: 9390 +Train: [25] [ 800/6250] eta: 0:15:55 lr: 0.000112 grad: 0.0646 (0.0679) loss: 0.8380 (0.8395) time: 0.2222 data: 0.1287 max mem: 9390 +Train: [25] [ 900/6250] eta: 0:15:37 lr: 0.000112 grad: 0.0644 (0.0679) loss: 0.8385 (0.8392) time: 0.1689 data: 0.0798 max mem: 9390 +Train: [25] [1000/6250] eta: 0:15:20 lr: 0.000112 grad: 0.0662 (0.0682) loss: 0.8375 (0.8388) time: 0.1688 data: 0.0799 max mem: 9390 +Train: [25] [1100/6250] eta: 0:14:56 lr: 0.000112 grad: 0.0707 (0.0684) loss: 0.8344 (0.8386) time: 0.1465 data: 0.0585 max mem: 9390 +Train: [25] [1200/6250] eta: 0:14:36 lr: 0.000112 grad: 0.0665 (0.0686) loss: 0.8377 (0.8383) time: 0.1814 data: 0.0936 max mem: 9390 +Train: [25] [1300/6250] eta: 0:14:16 lr: 0.000112 grad: 0.0646 (0.0686) loss: 0.8396 (0.8383) time: 0.1588 data: 0.0672 max mem: 9390 +Train: [25] [1400/6250] eta: 0:13:58 lr: 0.000112 grad: 0.0669 (0.0686) loss: 0.8360 (0.8382) time: 0.1587 data: 0.0777 max mem: 9390 +Train: [25] [1500/6250] eta: 0:13:40 lr: 0.000112 grad: 0.0652 (0.0688) loss: 0.8358 (0.8381) time: 0.1776 data: 0.0898 max mem: 9390 +Train: [25] [1600/6250] eta: 0:13:22 lr: 0.000111 grad: 0.0674 (0.0688) loss: 0.8374 (0.8380) time: 0.1625 data: 0.0717 max mem: 9390 +Train: [25] [1700/6250] eta: 0:13:02 lr: 0.000111 grad: 0.0684 (0.0689) loss: 0.8313 (0.8377) time: 0.1669 data: 0.0775 max mem: 9390 +Train: [25] [1800/6250] eta: 0:12:47 lr: 0.000111 grad: 0.0659 (0.0688) loss: 0.8280 (0.8374) time: 0.1761 data: 0.0797 max mem: 9390 +Train: [25] [1900/6250] eta: 0:12:29 lr: 0.000111 grad: 0.0653 (0.0691) loss: 0.8337 (0.8373) time: 0.1653 data: 0.0621 max mem: 9390 +Train: [25] [2000/6250] eta: 0:12:13 lr: 0.000111 grad: 0.0690 (0.0693) loss: 0.8314 (0.8370) time: 0.1796 data: 0.0842 max mem: 9390 +Train: [25] [2100/6250] eta: 0:11:56 lr: 0.000111 grad: 0.0683 (0.0694) loss: 0.8327 (0.8368) time: 0.2160 data: 0.1239 max mem: 9390 +Train: [25] [2200/6250] eta: 0:11:35 lr: 0.000111 grad: 0.0655 (0.0692) loss: 0.8344 (0.8367) time: 0.1425 data: 0.0557 max mem: 9390 +Train: [25] [2300/6250] eta: 0:11:18 lr: 0.000111 grad: 0.0711 (0.0693) loss: 0.8321 (0.8365) time: 0.1849 data: 0.0974 max mem: 9390 +Train: [25] [2400/6250] eta: 0:11:01 lr: 0.000111 grad: 0.0686 (0.0693) loss: 0.8366 (0.8364) time: 0.1705 data: 0.0826 max mem: 9390 +Train: [25] [2500/6250] eta: 0:10:44 lr: 0.000111 grad: 0.0648 (0.0691) loss: 0.8290 (0.8363) time: 0.1880 data: 0.0984 max mem: 9390 +Train: [25] [2600/6250] eta: 0:10:27 lr: 0.000111 grad: 0.0663 (0.0691) loss: 0.8354 (0.8362) time: 0.1812 data: 0.0940 max mem: 9390 +Train: [25] [2700/6250] eta: 0:10:10 lr: 0.000111 grad: 0.0724 (0.0693) loss: 0.8338 (0.8361) time: 0.1184 data: 0.0308 max mem: 9390 +Train: [25] [2800/6250] eta: 0:09:52 lr: 0.000111 grad: 0.0675 (0.0693) loss: 0.8308 (0.8360) time: 0.1782 data: 0.0960 max mem: 9390 +Train: [25] [2900/6250] eta: 0:09:36 lr: 0.000111 grad: 0.0666 (0.0692) loss: 0.8320 (0.8359) time: 0.1912 data: 0.1016 max mem: 9390 +Train: [25] [3000/6250] eta: 0:09:18 lr: 0.000111 grad: 0.0677 (0.0692) loss: 0.8323 (0.8359) time: 0.1690 data: 0.0852 max mem: 9390 +Train: [25] [3100/6250] eta: 0:09:04 lr: 0.000111 grad: 0.0700 (0.0692) loss: 0.8268 (0.8358) time: 0.1783 data: 0.0953 max mem: 9390 +Train: [25] [3200/6250] eta: 0:08:46 lr: 0.000111 grad: 0.0679 (0.0691) loss: 0.8315 (0.8358) time: 0.1964 data: 0.1182 max mem: 9390 +Train: [25] [3300/6250] eta: 0:08:29 lr: 0.000111 grad: 0.0669 (0.0691) loss: 0.8342 (0.8358) time: 0.1758 data: 0.0985 max mem: 9390 +Train: [25] [3400/6250] eta: 0:08:12 lr: 0.000111 grad: 0.0662 (0.0691) loss: 0.8336 (0.8359) time: 0.1799 data: 0.0909 max mem: 9390 +Train: [25] [3500/6250] eta: 0:07:54 lr: 0.000111 grad: 0.0634 (0.0691) loss: 0.8384 (0.8360) time: 0.1631 data: 0.0764 max mem: 9390 +Train: [25] [3600/6250] eta: 0:07:36 lr: 0.000111 grad: 0.0688 (0.0691) loss: 0.8350 (0.8360) time: 0.1607 data: 0.0773 max mem: 9390 +Train: [25] [3700/6250] eta: 0:07:19 lr: 0.000111 grad: 0.0684 (0.0691) loss: 0.8360 (0.8360) time: 0.1769 data: 0.0841 max mem: 9390 +Train: [25] [3800/6250] eta: 0:07:01 lr: 0.000111 grad: 0.0645 (0.0691) loss: 0.8397 (0.8360) time: 0.1509 data: 0.0617 max mem: 9390 +Train: [25] [3900/6250] eta: 0:06:43 lr: 0.000111 grad: 0.0651 (0.0690) loss: 0.8346 (0.8361) time: 0.1573 data: 0.0694 max mem: 9390 +Train: [25] [4000/6250] eta: 0:06:26 lr: 0.000111 grad: 0.0674 (0.0689) loss: 0.8329 (0.8361) time: 0.1622 data: 0.0690 max mem: 9390 +Train: [25] [4100/6250] eta: 0:06:08 lr: 0.000111 grad: 0.0654 (0.0689) loss: 0.8383 (0.8361) time: 0.1439 data: 0.0435 max mem: 9390 +Train: [25] [4200/6250] eta: 0:05:51 lr: 0.000111 grad: 0.0669 (0.0689) loss: 0.8444 (0.8362) time: 0.1656 data: 0.0698 max mem: 9390 +Train: [25] [4300/6250] eta: 0:05:33 lr: 0.000111 grad: 0.0620 (0.0688) loss: 0.8412 (0.8363) time: 0.1502 data: 0.0539 max mem: 9390 +Train: [25] [4400/6250] eta: 0:05:16 lr: 0.000111 grad: 0.0685 (0.0688) loss: 0.8370 (0.8364) time: 0.1656 data: 0.0765 max mem: 9390 +Train: [25] [4500/6250] eta: 0:04:58 lr: 0.000111 grad: 0.0678 (0.0687) loss: 0.8400 (0.8364) time: 0.1526 data: 0.0610 max mem: 9390 +Train: [25] [4600/6250] eta: 0:04:41 lr: 0.000111 grad: 0.0675 (0.0688) loss: 0.8402 (0.8365) time: 0.1685 data: 0.0728 max mem: 9390 +Train: [25] [4700/6250] eta: 0:04:24 lr: 0.000111 grad: 0.0664 (0.0687) loss: 0.8444 (0.8366) time: 0.1780 data: 0.0974 max mem: 9390 +Train: [25] [4800/6250] eta: 0:04:07 lr: 0.000111 grad: 0.0655 (0.0687) loss: 0.8406 (0.8366) time: 0.1581 data: 0.0681 max mem: 9390 +Train: [25] [4900/6250] eta: 0:03:50 lr: 0.000111 grad: 0.0668 (0.0687) loss: 0.8393 (0.8367) time: 0.1922 data: 0.0970 max mem: 9390 +Train: [25] [5000/6250] eta: 0:03:33 lr: 0.000111 grad: 0.0662 (0.0688) loss: 0.8348 (0.8367) time: 0.1612 data: 0.0678 max mem: 9390 +Train: [25] [5100/6250] eta: 0:03:16 lr: 0.000111 grad: 0.0642 (0.0688) loss: 0.8316 (0.8367) time: 0.1773 data: 0.0896 max mem: 9390 +Train: [25] [5200/6250] eta: 0:02:59 lr: 0.000111 grad: 0.0650 (0.0688) loss: 0.8338 (0.8367) time: 0.1941 data: 0.1068 max mem: 9390 +Train: [25] [5300/6250] eta: 0:02:41 lr: 0.000111 grad: 0.0659 (0.0688) loss: 0.8423 (0.8367) time: 0.1962 data: 0.1062 max mem: 9390 +Train: [25] [5400/6250] eta: 0:02:24 lr: 0.000111 grad: 0.0641 (0.0688) loss: 0.8373 (0.8367) time: 0.1874 data: 0.0981 max mem: 9390 +Train: [25] [5500/6250] eta: 0:02:07 lr: 0.000111 grad: 0.0621 (0.0687) loss: 0.8359 (0.8367) time: 0.1587 data: 0.0718 max mem: 9390 +Train: [25] [5600/6250] eta: 0:01:50 lr: 0.000111 grad: 0.0662 (0.0687) loss: 0.8324 (0.8367) time: 0.1627 data: 0.0682 max mem: 9390 +Train: [25] [5700/6250] eta: 0:01:33 lr: 0.000111 grad: 0.0652 (0.0688) loss: 0.8400 (0.8367) time: 0.1643 data: 0.0796 max mem: 9390 +Train: [25] [5800/6250] eta: 0:01:16 lr: 0.000111 grad: 0.0699 (0.0688) loss: 0.8346 (0.8367) time: 0.1716 data: 0.0686 max mem: 9390 +Train: [25] [5900/6250] eta: 0:00:59 lr: 0.000111 grad: 0.0650 (0.0688) loss: 0.8332 (0.8366) time: 0.1882 data: 0.0991 max mem: 9390 +Train: [25] [6000/6250] eta: 0:00:42 lr: 0.000111 grad: 0.0689 (0.0688) loss: 0.8328 (0.8365) time: 0.1764 data: 0.0927 max mem: 9390 +Train: [25] [6100/6250] eta: 0:00:25 lr: 0.000111 grad: 0.0657 (0.0687) loss: 0.8348 (0.8365) time: 0.1490 data: 0.0501 max mem: 9390 +Train: [25] [6200/6250] eta: 0:00:08 lr: 0.000111 grad: 0.0664 (0.0687) loss: 0.8347 (0.8365) time: 0.1984 data: 0.1093 max mem: 9390 +Train: [25] [6249/6250] eta: 0:00:00 lr: 0.000111 grad: 0.0673 (0.0687) loss: 0.8340 (0.8365) time: 0.2038 data: 0.1215 max mem: 9390 +Train: [25] Total time: 0:17:50 (0.1713 s / it) +Averaged stats: lr: 0.000111 grad: 0.0673 (0.0687) loss: 0.8340 (0.8365) +Eval (hcp-train-subset): [25] [ 0/62] eta: 0:04:43 loss: 0.8597 (0.8597) time: 4.5694 data: 4.5389 max mem: 9390 +Eval (hcp-train-subset): [25] [61/62] eta: 0:00:00 loss: 0.8406 (0.8428) time: 0.1174 data: 0.0927 max mem: 9390 +Eval (hcp-train-subset): [25] Total time: 0:00:13 (0.2171 s / it) +Averaged stats (hcp-train-subset): loss: 0.8406 (0.8428) +Eval (hcp-val): [25] [ 0/62] eta: 0:05:28 loss: 0.8408 (0.8408) time: 5.3034 data: 5.2724 max mem: 9390 +Eval (hcp-val): [25] [61/62] eta: 0:00:00 loss: 0.8386 (0.8403) time: 0.1302 data: 0.1048 max mem: 9390 +Eval (hcp-val): [25] Total time: 0:00:13 (0.2187 s / it) +Averaged stats (hcp-val): loss: 0.8386 (0.8403) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +Train: [26] [ 0/6250] eta: 10:58:28 lr: 0.000111 grad: 0.0741 (0.0741) loss: 0.8690 (0.8690) time: 6.3213 data: 6.2123 max mem: 9390 +Train: [26] [ 100/6250] eta: 0:21:47 lr: 0.000111 grad: 0.0678 (0.0802) loss: 0.8454 (0.8408) time: 0.1797 data: 0.0838 max mem: 9390 +Train: [26] [ 200/6250] eta: 0:19:02 lr: 0.000110 grad: 0.0619 (0.0739) loss: 0.8446 (0.8418) time: 0.1469 data: 0.0512 max mem: 9390 +Train: [26] [ 300/6250] eta: 0:18:08 lr: 0.000110 grad: 0.0633 (0.0717) loss: 0.8420 (0.8408) time: 0.1981 data: 0.1056 max mem: 9390 +Train: [26] [ 400/6250] eta: 0:17:32 lr: 0.000110 grad: 0.0638 (0.0705) loss: 0.8373 (0.8403) time: 0.1812 data: 0.0790 max mem: 9390 +Train: [26] [ 500/6250] eta: 0:16:44 lr: 0.000110 grad: 0.0586 (0.0696) loss: 0.8450 (0.8403) time: 0.1503 data: 0.0535 max mem: 9390 +Train: [26] [ 600/6250] eta: 0:16:17 lr: 0.000110 grad: 0.0622 (0.0692) loss: 0.8406 (0.8401) time: 0.1167 data: 0.0203 max mem: 9390 +Train: [26] [ 700/6250] eta: 0:16:06 lr: 0.000110 grad: 0.0632 (0.0694) loss: 0.8353 (0.8393) time: 0.1868 data: 0.0940 max mem: 9390 +Train: [26] [ 800/6250] eta: 0:15:48 lr: 0.000110 grad: 0.0656 (0.0690) loss: 0.8341 (0.8387) time: 0.1816 data: 0.0938 max mem: 9390 +Train: [26] [ 900/6250] eta: 0:15:38 lr: 0.000110 grad: 0.0713 (0.0691) loss: 0.8319 (0.8381) time: 0.1955 data: 0.1078 max mem: 9390 +Train: [26] [1000/6250] eta: 0:15:15 lr: 0.000110 grad: 0.0659 (0.0691) loss: 0.8289 (0.8374) time: 0.1824 data: 0.0921 max mem: 9390 +Train: [26] [1100/6250] eta: 0:14:54 lr: 0.000110 grad: 0.0722 (0.0691) loss: 0.8254 (0.8368) time: 0.1535 data: 0.0643 max mem: 9390 +Train: [26] [1200/6250] eta: 0:14:36 lr: 0.000110 grad: 0.0633 (0.0691) loss: 0.8330 (0.8366) time: 0.1597 data: 0.0755 max mem: 9390 +Train: [26] [1300/6250] eta: 0:14:14 lr: 0.000110 grad: 0.0659 (0.0689) loss: 0.8319 (0.8363) time: 0.1655 data: 0.0828 max mem: 9390 +Train: [26] [1400/6250] eta: 0:13:56 lr: 0.000110 grad: 0.0741 (0.0690) loss: 0.8288 (0.8359) time: 0.1723 data: 0.0828 max mem: 9390 +Train: [26] [1500/6250] eta: 0:13:39 lr: 0.000110 grad: 0.0669 (0.0693) loss: 0.8326 (0.8356) time: 0.1893 data: 0.1085 max mem: 9390 +Train: [26] [1600/6250] eta: 0:13:20 lr: 0.000110 grad: 0.0678 (0.0694) loss: 0.8318 (0.8354) time: 0.1501 data: 0.0616 max mem: 9390 +Train: [26] [1700/6250] eta: 0:13:02 lr: 0.000110 grad: 0.0621 (0.0694) loss: 0.8300 (0.8352) time: 0.1486 data: 0.0611 max mem: 9390 +Train: [26] [1800/6250] eta: 0:12:43 lr: 0.000110 grad: 0.0678 (0.0695) loss: 0.8326 (0.8350) time: 0.1900 data: 0.1023 max mem: 9390 +Train: [26] [1900/6250] eta: 0:12:26 lr: 0.000110 grad: 0.0668 (0.0695) loss: 0.8312 (0.8347) time: 0.1623 data: 0.0774 max mem: 9390 +Train: [26] [2000/6250] eta: 0:12:09 lr: 0.000110 grad: 0.0683 (0.0695) loss: 0.8319 (0.8345) time: 0.1915 data: 0.1074 max mem: 9390 +Train: [26] [2100/6250] eta: 0:11:49 lr: 0.000110 grad: 0.0667 (0.0695) loss: 0.8348 (0.8344) time: 0.1597 data: 0.0764 max mem: 9390 +Train: [26] [2200/6250] eta: 0:11:31 lr: 0.000110 grad: 0.0676 (0.0695) loss: 0.8309 (0.8343) time: 0.1643 data: 0.0698 max mem: 9390 +Train: [26] [2300/6250] eta: 0:11:12 lr: 0.000110 grad: 0.0669 (0.0695) loss: 0.8344 (0.8342) time: 0.1545 data: 0.0741 max mem: 9390 +Train: [26] [2400/6250] eta: 0:10:55 lr: 0.000110 grad: 0.0665 (0.0696) loss: 0.8286 (0.8341) time: 0.1895 data: 0.1053 max mem: 9390 +Train: [26] [2500/6250] eta: 0:10:36 lr: 0.000110 grad: 0.0676 (0.0695) loss: 0.8344 (0.8340) time: 0.1543 data: 0.0684 max mem: 9390 +Train: [26] [2600/6250] eta: 0:10:19 lr: 0.000110 grad: 0.0686 (0.0695) loss: 0.8324 (0.8340) time: 0.1701 data: 0.0827 max mem: 9390 +Train: [26] [2700/6250] eta: 0:10:02 lr: 0.000110 grad: 0.0682 (0.0694) loss: 0.8361 (0.8340) time: 0.1882 data: 0.1092 max mem: 9390 +Train: [26] [2800/6250] eta: 0:09:44 lr: 0.000110 grad: 0.0655 (0.0695) loss: 0.8359 (0.8339) time: 0.1721 data: 0.0834 max mem: 9390 +Train: [26] [2900/6250] eta: 0:09:27 lr: 0.000110 grad: 0.0669 (0.0695) loss: 0.8330 (0.8338) time: 0.1615 data: 0.0690 max mem: 9390 +Train: [26] [3000/6250] eta: 0:09:09 lr: 0.000110 grad: 0.0711 (0.0695) loss: 0.8314 (0.8338) time: 0.1610 data: 0.0799 max mem: 9390 +Train: [26] [3100/6250] eta: 0:08:53 lr: 0.000110 grad: 0.0654 (0.0695) loss: 0.8353 (0.8337) time: 0.1625 data: 0.0750 max mem: 9390 +Train: [26] [3200/6250] eta: 0:08:36 lr: 0.000110 grad: 0.0710 (0.0695) loss: 0.8289 (0.8336) time: 0.1631 data: 0.0722 max mem: 9390 +Train: [26] [3300/6250] eta: 0:08:19 lr: 0.000110 grad: 0.0722 (0.0695) loss: 0.8366 (0.8336) time: 0.1716 data: 0.0890 max mem: 9390 +Train: [26] [3400/6250] eta: 0:08:02 lr: 0.000110 grad: 0.0643 (0.0696) loss: 0.8312 (0.8336) time: 0.1742 data: 0.0849 max mem: 9390 +Train: [26] [3500/6250] eta: 0:07:45 lr: 0.000110 grad: 0.0672 (0.0696) loss: 0.8273 (0.8336) time: 0.1452 data: 0.0559 max mem: 9390 +Train: [26] [3600/6250] eta: 0:07:28 lr: 0.000110 grad: 0.0636 (0.0696) loss: 0.8318 (0.8336) time: 0.1747 data: 0.0892 max mem: 9390 +Train: [26] [3700/6250] eta: 0:07:10 lr: 0.000110 grad: 0.0653 (0.0696) loss: 0.8316 (0.8336) time: 0.1557 data: 0.0676 max mem: 9390 +Train: [26] [3800/6250] eta: 0:06:54 lr: 0.000110 grad: 0.0668 (0.0696) loss: 0.8291 (0.8335) time: 0.1862 data: 0.1007 max mem: 9390 +Train: [26] [3900/6250] eta: 0:06:36 lr: 0.000110 grad: 0.0667 (0.0696) loss: 0.8330 (0.8335) time: 0.1568 data: 0.0716 max mem: 9390 +Train: [26] [4000/6250] eta: 0:06:19 lr: 0.000110 grad: 0.0660 (0.0695) loss: 0.8333 (0.8335) time: 0.1754 data: 0.0942 max mem: 9390 +Train: [26] [4100/6250] eta: 0:06:02 lr: 0.000110 grad: 0.0712 (0.0695) loss: 0.8270 (0.8335) time: 0.1488 data: 0.0648 max mem: 9390 +Train: [26] [4200/6250] eta: 0:05:45 lr: 0.000110 grad: 0.0671 (0.0696) loss: 0.8324 (0.8335) time: 0.1743 data: 0.0880 max mem: 9390 +Train: [26] [4300/6250] eta: 0:05:28 lr: 0.000110 grad: 0.0625 (0.0695) loss: 0.8430 (0.8336) time: 0.1809 data: 0.0914 max mem: 9390 +Train: [26] [4400/6250] eta: 0:05:12 lr: 0.000110 grad: 0.0681 (0.0695) loss: 0.8314 (0.8336) time: 0.2014 data: 0.1184 max mem: 9390 +Train: [26] [4500/6250] eta: 0:04:55 lr: 0.000110 grad: 0.0675 (0.0697) loss: 0.8317 (0.8336) time: 0.1605 data: 0.0755 max mem: 9390 +Train: [26] [4600/6250] eta: 0:04:38 lr: 0.000110 grad: 0.0684 (0.0697) loss: 0.8371 (0.8336) time: 0.1592 data: 0.0654 max mem: 9390 +Train: [26] [4700/6250] eta: 0:04:21 lr: 0.000110 grad: 0.0718 (0.0698) loss: 0.8338 (0.8336) time: 0.1707 data: 0.0824 max mem: 9390 +Train: [26] [4800/6250] eta: 0:04:04 lr: 0.000109 grad: 0.0660 (0.0698) loss: 0.8334 (0.8336) time: 0.1519 data: 0.0666 max mem: 9390 +Train: [26] [4900/6250] eta: 0:03:47 lr: 0.000109 grad: 0.0680 (0.0697) loss: 0.8422 (0.8336) time: 0.1557 data: 0.0705 max mem: 9390 +Train: [26] [5000/6250] eta: 0:03:30 lr: 0.000109 grad: 0.0683 (0.0698) loss: 0.8375 (0.8337) time: 0.1570 data: 0.0793 max mem: 9390 +Train: [26] [5100/6250] eta: 0:03:13 lr: 0.000109 grad: 0.0685 (0.0698) loss: 0.8301 (0.8337) time: 0.1836 data: 0.0931 max mem: 9390 +Train: [26] [5200/6250] eta: 0:02:57 lr: 0.000109 grad: 0.0681 (0.0698) loss: 0.8287 (0.8337) time: 0.2128 data: 0.1207 max mem: 9390 +Train: [26] [5300/6250] eta: 0:02:40 lr: 0.000109 grad: 0.0666 (0.0698) loss: 0.8313 (0.8336) time: 0.1777 data: 0.0927 max mem: 9390 +Train: [26] [5400/6250] eta: 0:02:23 lr: 0.000109 grad: 0.0672 (0.0699) loss: 0.8310 (0.8336) time: 0.1651 data: 0.0769 max mem: 9390 +Train: [26] [5500/6250] eta: 0:02:06 lr: 0.000109 grad: 0.0753 (0.0700) loss: 0.8263 (0.8335) time: 0.1595 data: 0.0705 max mem: 9390 +Train: [26] [5600/6250] eta: 0:01:49 lr: 0.000109 grad: 0.0682 (0.0699) loss: 0.8342 (0.8335) time: 0.1501 data: 0.0671 max mem: 9390 +Train: [26] [5700/6250] eta: 0:01:32 lr: 0.000109 grad: 0.0674 (0.0699) loss: 0.8249 (0.8334) time: 0.1928 data: 0.1199 max mem: 9390 +Train: [26] [5800/6250] eta: 0:01:15 lr: 0.000109 grad: 0.0710 (0.0700) loss: 0.8354 (0.8334) time: 0.1783 data: 0.1004 max mem: 9390 +Train: [26] [5900/6250] eta: 0:00:58 lr: 0.000109 grad: 0.0637 (0.0699) loss: 0.8305 (0.8334) time: 0.1837 data: 0.0955 max mem: 9390 +Train: [26] [6000/6250] eta: 0:00:42 lr: 0.000109 grad: 0.0683 (0.0699) loss: 0.8316 (0.8335) time: 0.1500 data: 0.0643 max mem: 9390 +Train: [26] [6100/6250] eta: 0:00:25 lr: 0.000109 grad: 0.0689 (0.0699) loss: 0.8313 (0.8334) time: 0.1737 data: 0.0848 max mem: 9390 +Train: [26] [6200/6250] eta: 0:00:08 lr: 0.000109 grad: 0.0656 (0.0699) loss: 0.8349 (0.8334) time: 0.1516 data: 0.0648 max mem: 9390 +Train: [26] [6249/6250] eta: 0:00:00 lr: 0.000109 grad: 0.0663 (0.0699) loss: 0.8325 (0.8334) time: 0.1652 data: 0.0768 max mem: 9390 +Train: [26] Total time: 0:17:37 (0.1692 s / it) +Averaged stats: lr: 0.000109 grad: 0.0663 (0.0699) loss: 0.8325 (0.8334) +Eval (hcp-train-subset): [26] [ 0/62] eta: 0:05:07 loss: 0.8543 (0.8543) time: 4.9600 data: 4.8945 max mem: 9390 +Eval (hcp-train-subset): [26] [61/62] eta: 0:00:00 loss: 0.8423 (0.8427) time: 0.1266 data: 0.1013 max mem: 9390 +Eval (hcp-train-subset): [26] Total time: 0:00:14 (0.2397 s / it) +Averaged stats (hcp-train-subset): loss: 0.8423 (0.8427) +Eval (hcp-val): [26] [ 0/62] eta: 0:03:39 loss: 0.8367 (0.8367) time: 3.5411 data: 3.4801 max mem: 9390 +Eval (hcp-val): [26] [61/62] eta: 0:00:00 loss: 0.8373 (0.8388) time: 0.1437 data: 0.1166 max mem: 9390 +Eval (hcp-val): [26] Total time: 0:00:13 (0.2169 s / it) +Averaged stats (hcp-val): loss: 0.8373 (0.8388) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +Train: [27] [ 0/6250] eta: 9:49:24 lr: 0.000109 grad: 0.0859 (0.0859) loss: 0.8453 (0.8453) time: 5.6583 data: 5.5320 max mem: 9390 +Train: [27] [ 100/6250] eta: 0:22:52 lr: 0.000109 grad: 0.0669 (0.0744) loss: 0.8330 (0.8400) time: 0.1746 data: 0.0825 max mem: 9390 +Train: [27] [ 200/6250] eta: 0:19:45 lr: 0.000109 grad: 0.0699 (0.0769) loss: 0.8330 (0.8364) time: 0.1664 data: 0.0654 max mem: 9390 +Train: [27] [ 300/6250] eta: 0:18:30 lr: 0.000109 grad: 0.0708 (0.0751) loss: 0.8310 (0.8356) time: 0.1564 data: 0.0604 max mem: 9390 +Train: [27] [ 400/6250] eta: 0:17:51 lr: 0.000109 grad: 0.0635 (0.0737) loss: 0.8409 (0.8356) time: 0.1895 data: 0.0961 max mem: 9390 +Train: [27] [ 500/6250] eta: 0:17:12 lr: 0.000109 grad: 0.0637 (0.0723) loss: 0.8385 (0.8362) time: 0.1838 data: 0.0900 max mem: 9390 +Train: [27] [ 600/6250] eta: 0:16:37 lr: 0.000109 grad: 0.0630 (0.0719) loss: 0.8367 (0.8362) time: 0.1641 data: 0.0674 max mem: 9390 +Train: [27] [ 700/6250] eta: 0:16:24 lr: 0.000109 grad: 0.0631 (0.0709) loss: 0.8318 (0.8360) time: 0.1977 data: 0.1098 max mem: 9390 +Train: [27] [ 800/6250] eta: 0:16:16 lr: 0.000109 grad: 0.0668 (0.0702) loss: 0.8399 (0.8359) time: 0.1750 data: 0.0839 max mem: 9390 +Train: [27] [ 900/6250] eta: 0:15:54 lr: 0.000109 grad: 0.0607 (0.0696) loss: 0.8339 (0.8359) time: 0.1673 data: 0.0800 max mem: 9390 +Train: [27] [1000/6250] eta: 0:15:33 lr: 0.000109 grad: 0.0632 (0.0692) loss: 0.8368 (0.8359) time: 0.1521 data: 0.0571 max mem: 9390 +Train: [27] [1100/6250] eta: 0:15:10 lr: 0.000109 grad: 0.0675 (0.0691) loss: 0.8324 (0.8356) time: 0.1602 data: 0.0671 max mem: 9390 +Train: [27] [1200/6250] eta: 0:14:46 lr: 0.000109 grad: 0.0658 (0.0691) loss: 0.8364 (0.8355) time: 0.1593 data: 0.0708 max mem: 9390 +Train: [27] [1300/6250] eta: 0:14:25 lr: 0.000109 grad: 0.0616 (0.0688) loss: 0.8333 (0.8353) time: 0.1700 data: 0.0881 max mem: 9390 +Train: [27] [1400/6250] eta: 0:14:04 lr: 0.000109 grad: 0.0666 (0.0687) loss: 0.8313 (0.8351) time: 0.1655 data: 0.0705 max mem: 9390 +Train: [27] [1500/6250] eta: 0:13:46 lr: 0.000109 grad: 0.0684 (0.0688) loss: 0.8330 (0.8349) time: 0.1705 data: 0.0817 max mem: 9390 +Train: [27] [1600/6250] eta: 0:13:28 lr: 0.000109 grad: 0.0664 (0.0688) loss: 0.8293 (0.8346) time: 0.1594 data: 0.0688 max mem: 9390 +Train: [27] [1700/6250] eta: 0:13:09 lr: 0.000109 grad: 0.0642 (0.0687) loss: 0.8329 (0.8345) time: 0.1730 data: 0.0817 max mem: 9390 +Train: [27] [1800/6250] eta: 0:12:51 lr: 0.000109 grad: 0.0671 (0.0689) loss: 0.8276 (0.8341) time: 0.1823 data: 0.0977 max mem: 9390 +Train: [27] [1900/6250] eta: 0:12:42 lr: 0.000109 grad: 0.0662 (0.0689) loss: 0.8323 (0.8340) time: 0.1734 data: 0.0909 max mem: 9390 +Train: [27] [2000/6250] eta: 0:12:24 lr: 0.000109 grad: 0.0658 (0.0689) loss: 0.8341 (0.8338) time: 0.1859 data: 0.0854 max mem: 9390 +Train: [27] [2100/6250] eta: 0:12:07 lr: 0.000109 grad: 0.0624 (0.0688) loss: 0.8298 (0.8338) time: 0.2035 data: 0.1297 max mem: 9390 +Train: [27] [2200/6250] eta: 0:11:49 lr: 0.000109 grad: 0.0642 (0.0688) loss: 0.8292 (0.8337) time: 0.1538 data: 0.0691 max mem: 9390 +Train: [27] [2300/6250] eta: 0:11:31 lr: 0.000109 grad: 0.0653 (0.0688) loss: 0.8321 (0.8336) time: 0.1766 data: 0.0942 max mem: 9390 +Train: [27] [2400/6250] eta: 0:11:12 lr: 0.000109 grad: 0.0706 (0.0687) loss: 0.8279 (0.8335) time: 0.1361 data: 0.0608 max mem: 9390 +Train: [27] [2500/6250] eta: 0:10:55 lr: 0.000109 grad: 0.0678 (0.0687) loss: 0.8335 (0.8335) time: 0.1978 data: 0.1031 max mem: 9390 +Train: [27] [2600/6250] eta: 0:10:36 lr: 0.000109 grad: 0.0653 (0.0688) loss: 0.8303 (0.8335) time: 0.1750 data: 0.0862 max mem: 9390 +Train: [27] [2700/6250] eta: 0:10:19 lr: 0.000109 grad: 0.0686 (0.0688) loss: 0.8317 (0.8334) time: 0.1967 data: 0.1058 max mem: 9390 +Train: [27] [2800/6250] eta: 0:09:59 lr: 0.000109 grad: 0.0684 (0.0688) loss: 0.8356 (0.8333) time: 0.1667 data: 0.0770 max mem: 9390 +Train: [27] [2900/6250] eta: 0:09:41 lr: 0.000109 grad: 0.0667 (0.0688) loss: 0.8335 (0.8333) time: 0.1596 data: 0.0754 max mem: 9390 +Train: [27] [3000/6250] eta: 0:09:22 lr: 0.000109 grad: 0.0659 (0.0688) loss: 0.8299 (0.8333) time: 0.1217 data: 0.0217 max mem: 9390 +Train: [27] [3100/6250] eta: 0:09:04 lr: 0.000108 grad: 0.0711 (0.0688) loss: 0.8286 (0.8332) time: 0.1815 data: 0.0986 max mem: 9390 +Train: [27] [3200/6250] eta: 0:08:45 lr: 0.000108 grad: 0.0650 (0.0689) loss: 0.8344 (0.8332) time: 0.1621 data: 0.0726 max mem: 9390 +Train: [27] [3300/6250] eta: 0:08:27 lr: 0.000108 grad: 0.0715 (0.0689) loss: 0.8273 (0.8331) time: 0.1673 data: 0.0762 max mem: 9390 +Train: [27] [3400/6250] eta: 0:08:10 lr: 0.000108 grad: 0.0663 (0.0689) loss: 0.8304 (0.8330) time: 0.1626 data: 0.0703 max mem: 9390 +Train: [27] [3500/6250] eta: 0:07:52 lr: 0.000108 grad: 0.0732 (0.0690) loss: 0.8289 (0.8330) time: 0.1574 data: 0.0669 max mem: 9390 +Train: [27] [3600/6250] eta: 0:07:35 lr: 0.000108 grad: 0.0700 (0.0690) loss: 0.8280 (0.8329) time: 0.1562 data: 0.0637 max mem: 9390 +Train: [27] [3700/6250] eta: 0:07:18 lr: 0.000108 grad: 0.0683 (0.0691) loss: 0.8249 (0.8329) time: 0.1883 data: 0.0958 max mem: 9390 +Train: [27] [3800/6250] eta: 0:07:00 lr: 0.000108 grad: 0.0663 (0.0691) loss: 0.8369 (0.8329) time: 0.1672 data: 0.0832 max mem: 9390 +Train: [27] [3900/6250] eta: 0:06:44 lr: 0.000108 grad: 0.0667 (0.0692) loss: 0.8300 (0.8328) time: 0.1873 data: 0.1078 max mem: 9390 +Train: [27] [4000/6250] eta: 0:06:26 lr: 0.000108 grad: 0.0697 (0.0693) loss: 0.8334 (0.8327) time: 0.1541 data: 0.0689 max mem: 9390 +Train: [27] [4100/6250] eta: 0:06:09 lr: 0.000108 grad: 0.0694 (0.0694) loss: 0.8307 (0.8327) time: 0.1522 data: 0.0621 max mem: 9390 +Train: [27] [4200/6250] eta: 0:05:51 lr: 0.000108 grad: 0.0716 (0.0694) loss: 0.8318 (0.8326) time: 0.1696 data: 0.0886 max mem: 9390 +Train: [27] [4300/6250] eta: 0:05:34 lr: 0.000108 grad: 0.0667 (0.0695) loss: 0.8340 (0.8326) time: 0.1970 data: 0.1149 max mem: 9390 +Train: [27] [4400/6250] eta: 0:05:16 lr: 0.000108 grad: 0.0673 (0.0695) loss: 0.8317 (0.8326) time: 0.1437 data: 0.0570 max mem: 9390 +Train: [27] [4500/6250] eta: 0:04:59 lr: 0.000108 grad: 0.0698 (0.0695) loss: 0.8305 (0.8326) time: 0.1529 data: 0.0677 max mem: 9390 +Train: [27] [4600/6250] eta: 0:04:42 lr: 0.000108 grad: 0.0706 (0.0695) loss: 0.8286 (0.8326) time: 0.1984 data: 0.1124 max mem: 9390 +Train: [27] [4700/6250] eta: 0:04:25 lr: 0.000108 grad: 0.0695 (0.0696) loss: 0.8318 (0.8326) time: 0.1843 data: 0.1017 max mem: 9390 +Train: [27] [4800/6250] eta: 0:04:07 lr: 0.000108 grad: 0.0703 (0.0697) loss: 0.8331 (0.8326) time: 0.1534 data: 0.0661 max mem: 9390 +Train: [27] [4900/6250] eta: 0:03:50 lr: 0.000108 grad: 0.0718 (0.0697) loss: 0.8337 (0.8326) time: 0.1669 data: 0.0797 max mem: 9390 +Train: [27] [5000/6250] eta: 0:03:33 lr: 0.000108 grad: 0.0670 (0.0698) loss: 0.8383 (0.8326) time: 0.1712 data: 0.0872 max mem: 9390 +Train: [27] [5100/6250] eta: 0:03:16 lr: 0.000108 grad: 0.0687 (0.0698) loss: 0.8367 (0.8326) time: 0.1682 data: 0.0874 max mem: 9390 +Train: [27] [5200/6250] eta: 0:02:59 lr: 0.000108 grad: 0.0679 (0.0698) loss: 0.8366 (0.8326) time: 0.1701 data: 0.0870 max mem: 9390 +Train: [27] [5300/6250] eta: 0:02:42 lr: 0.000108 grad: 0.0662 (0.0698) loss: 0.8283 (0.8327) time: 0.1926 data: 0.1065 max mem: 9390 +Train: [27] [5400/6250] eta: 0:02:25 lr: 0.000108 grad: 0.0704 (0.0698) loss: 0.8300 (0.8328) time: 0.1804 data: 0.0926 max mem: 9390 +Train: [27] [5500/6250] eta: 0:02:08 lr: 0.000108 grad: 0.0680 (0.0699) loss: 0.8292 (0.8328) time: 0.1821 data: 0.0964 max mem: 9390 +Train: [27] [5600/6250] eta: 0:01:50 lr: 0.000108 grad: 0.0724 (0.0699) loss: 0.8382 (0.8328) time: 0.1669 data: 0.0850 max mem: 9390 +Train: [27] [5700/6250] eta: 0:01:33 lr: 0.000108 grad: 0.0691 (0.0699) loss: 0.8284 (0.8328) time: 0.1597 data: 0.0715 max mem: 9390 +Train: [27] [5800/6250] eta: 0:01:16 lr: 0.000108 grad: 0.0710 (0.0700) loss: 0.8364 (0.8328) time: 0.1557 data: 0.0768 max mem: 9390 +Train: [27] [5900/6250] eta: 0:00:59 lr: 0.000108 grad: 0.0698 (0.0700) loss: 0.8322 (0.8328) time: 0.1886 data: 0.1037 max mem: 9390 +Train: [27] [6000/6250] eta: 0:00:42 lr: 0.000108 grad: 0.0699 (0.0700) loss: 0.8359 (0.8328) time: 0.1559 data: 0.0702 max mem: 9390 +Train: [27] [6100/6250] eta: 0:00:25 lr: 0.000108 grad: 0.0723 (0.0701) loss: 0.8340 (0.8327) time: 0.1530 data: 0.0651 max mem: 9390 +Train: [27] [6200/6250] eta: 0:00:08 lr: 0.000108 grad: 0.0778 (0.0702) loss: 0.8247 (0.8327) time: 0.1639 data: 0.0675 max mem: 9390 +Train: [27] [6249/6250] eta: 0:00:00 lr: 0.000108 grad: 0.0710 (0.0702) loss: 0.8295 (0.8327) time: 0.1712 data: 0.0857 max mem: 9390 +Train: [27] Total time: 0:17:53 (0.1718 s / it) +Averaged stats: lr: 0.000108 grad: 0.0710 (0.0702) loss: 0.8295 (0.8327) +Eval (hcp-train-subset): [27] [ 0/62] eta: 0:05:58 loss: 0.8580 (0.8580) time: 5.7847 data: 5.7551 max mem: 9390 +Eval (hcp-train-subset): [27] [61/62] eta: 0:00:00 loss: 0.8422 (0.8433) time: 0.1156 data: 0.0905 max mem: 9390 +Eval (hcp-train-subset): [27] Total time: 0:00:14 (0.2309 s / it) +Averaged stats (hcp-train-subset): loss: 0.8422 (0.8433) +Eval (hcp-val): [27] [ 0/62] eta: 0:04:30 loss: 0.8373 (0.8373) time: 4.3654 data: 4.2958 max mem: 9390 +Eval (hcp-val): [27] [61/62] eta: 0:00:00 loss: 0.8406 (0.8402) time: 0.1296 data: 0.1026 max mem: 9390 +Eval (hcp-val): [27] Total time: 0:00:13 (0.2178 s / it) +Averaged stats (hcp-val): loss: 0.8406 (0.8402) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +Train: [28] [ 0/6250] eta: 11:09:05 lr: 0.000108 grad: 0.0511 (0.0511) loss: 0.8849 (0.8849) time: 6.4233 data: 6.2878 max mem: 9390 +Train: [28] [ 100/6250] eta: 0:22:55 lr: 0.000108 grad: 0.0773 (0.0876) loss: 0.8361 (0.8358) time: 0.1633 data: 0.0761 max mem: 9390 +Train: [28] [ 200/6250] eta: 0:19:54 lr: 0.000108 grad: 0.0675 (0.0804) loss: 0.8347 (0.8345) time: 0.1712 data: 0.0804 max mem: 9390 +Train: [28] [ 300/6250] eta: 0:18:33 lr: 0.000108 grad: 0.0740 (0.0778) loss: 0.8268 (0.8324) time: 0.1475 data: 0.0527 max mem: 9390 +Train: [28] [ 400/6250] eta: 0:17:55 lr: 0.000108 grad: 0.0675 (0.0769) loss: 0.8374 (0.8323) time: 0.1742 data: 0.0880 max mem: 9390 +Train: [28] [ 500/6250] eta: 0:17:14 lr: 0.000108 grad: 0.0739 (0.0756) loss: 0.8299 (0.8320) time: 0.1740 data: 0.0735 max mem: 9390 +Train: [28] [ 600/6250] eta: 0:16:34 lr: 0.000108 grad: 0.0654 (0.0743) loss: 0.8379 (0.8320) time: 0.1410 data: 0.0406 max mem: 9390 +Train: [28] [ 700/6250] eta: 0:16:23 lr: 0.000108 grad: 0.0665 (0.0734) loss: 0.8269 (0.8320) time: 0.1779 data: 0.0940 max mem: 9390 +Train: [28] [ 800/6250] eta: 0:16:20 lr: 0.000108 grad: 0.0647 (0.0726) loss: 0.8368 (0.8324) time: 0.2040 data: 0.1167 max mem: 9390 +Train: [28] [ 900/6250] eta: 0:16:09 lr: 0.000108 grad: 0.0689 (0.0726) loss: 0.8331 (0.8324) time: 0.2050 data: 0.1121 max mem: 9390 +Train: [28] [1000/6250] eta: 0:15:43 lr: 0.000108 grad: 0.0715 (0.0724) loss: 0.8247 (0.8322) time: 0.1898 data: 0.0965 max mem: 9390 +Train: [28] [1100/6250] eta: 0:15:20 lr: 0.000108 grad: 0.0723 (0.0724) loss: 0.8301 (0.8321) time: 0.1353 data: 0.0512 max mem: 9390 +Train: [28] [1200/6250] eta: 0:14:55 lr: 0.000108 grad: 0.0713 (0.0722) loss: 0.8257 (0.8320) time: 0.1499 data: 0.0611 max mem: 9390 +Train: [28] [1300/6250] eta: 0:14:34 lr: 0.000107 grad: 0.0715 (0.0723) loss: 0.8317 (0.8317) time: 0.1669 data: 0.0772 max mem: 9390 +Train: [28] [1400/6250] eta: 0:14:15 lr: 0.000107 grad: 0.0695 (0.0725) loss: 0.8343 (0.8315) time: 0.1788 data: 0.0858 max mem: 9390 +Train: [28] [1500/6250] eta: 0:13:54 lr: 0.000107 grad: 0.0716 (0.0724) loss: 0.8262 (0.8314) time: 0.1719 data: 0.0881 max mem: 9390 +Train: [28] [1600/6250] eta: 0:13:34 lr: 0.000107 grad: 0.0634 (0.0722) loss: 0.8304 (0.8314) time: 0.1770 data: 0.0889 max mem: 9390 +Train: [28] [1700/6250] eta: 0:13:16 lr: 0.000107 grad: 0.0696 (0.0720) loss: 0.8280 (0.8312) time: 0.1830 data: 0.0891 max mem: 9390 +Train: [28] [1800/6250] eta: 0:12:57 lr: 0.000107 grad: 0.0690 (0.0719) loss: 0.8269 (0.8312) time: 0.1405 data: 0.0504 max mem: 9390 +Train: [28] [1900/6250] eta: 0:12:39 lr: 0.000107 grad: 0.0633 (0.0721) loss: 0.8314 (0.8312) time: 0.1782 data: 0.0843 max mem: 9390 +Train: [28] [2000/6250] eta: 0:12:22 lr: 0.000107 grad: 0.0723 (0.0719) loss: 0.8281 (0.8311) time: 0.1845 data: 0.0985 max mem: 9390 +Train: [28] [2100/6250] eta: 0:12:06 lr: 0.000107 grad: 0.0691 (0.0718) loss: 0.8347 (0.8311) time: 0.1624 data: 0.0714 max mem: 9390 +Train: [28] [2200/6250] eta: 0:11:49 lr: 0.000107 grad: 0.0664 (0.0717) loss: 0.8325 (0.8312) time: 0.1900 data: 0.1006 max mem: 9390 +Train: [28] [2300/6250] eta: 0:11:30 lr: 0.000107 grad: 0.0659 (0.0715) loss: 0.8390 (0.8313) time: 0.1753 data: 0.0807 max mem: 9390 +Train: [28] [2400/6250] eta: 0:11:12 lr: 0.000107 grad: 0.0612 (0.0714) loss: 0.8351 (0.8314) time: 0.1765 data: 0.0864 max mem: 9390 +Train: [28] [2500/6250] eta: 0:10:54 lr: 0.000107 grad: 0.0692 (0.0714) loss: 0.8334 (0.8315) time: 0.1696 data: 0.0833 max mem: 9390 +Train: [28] [2600/6250] eta: 0:10:35 lr: 0.000107 grad: 0.0645 (0.0713) loss: 0.8325 (0.8316) time: 0.1690 data: 0.0907 max mem: 9390 +Train: [28] [2700/6250] eta: 0:10:17 lr: 0.000107 grad: 0.0687 (0.0712) loss: 0.8321 (0.8317) time: 0.1910 data: 0.1025 max mem: 9390 +Train: [28] [2800/6250] eta: 0:09:59 lr: 0.000107 grad: 0.0641 (0.0711) loss: 0.8298 (0.8317) time: 0.1702 data: 0.0808 max mem: 9390 +Train: [28] [2900/6250] eta: 0:09:42 lr: 0.000107 grad: 0.0626 (0.0710) loss: 0.8318 (0.8317) time: 0.1612 data: 0.0779 max mem: 9390 +Train: [28] [3000/6250] eta: 0:09:24 lr: 0.000107 grad: 0.0632 (0.0709) loss: 0.8362 (0.8317) time: 0.1741 data: 0.0898 max mem: 9390 +Train: [28] [3100/6250] eta: 0:09:06 lr: 0.000107 grad: 0.0667 (0.0708) loss: 0.8369 (0.8318) time: 0.1529 data: 0.0632 max mem: 9390 +Train: [28] [3200/6250] eta: 0:08:48 lr: 0.000107 grad: 0.0688 (0.0708) loss: 0.8336 (0.8319) time: 0.1741 data: 0.0852 max mem: 9390 +Train: [28] [3300/6250] eta: 0:08:31 lr: 0.000107 grad: 0.0639 (0.0707) loss: 0.8359 (0.8320) time: 0.1677 data: 0.0815 max mem: 9390 +Train: [28] [3400/6250] eta: 0:08:13 lr: 0.000107 grad: 0.0660 (0.0706) loss: 0.8380 (0.8321) time: 0.1523 data: 0.0589 max mem: 9390 +Train: [28] [3500/6250] eta: 0:07:56 lr: 0.000107 grad: 0.0651 (0.0705) loss: 0.8393 (0.8323) time: 0.1743 data: 0.0916 max mem: 9390 +Train: [28] [3600/6250] eta: 0:07:38 lr: 0.000107 grad: 0.0681 (0.0704) loss: 0.8362 (0.8324) time: 0.1721 data: 0.0859 max mem: 9390 +Train: [28] [3700/6250] eta: 0:07:21 lr: 0.000107 grad: 0.0703 (0.0704) loss: 0.8330 (0.8325) time: 0.1726 data: 0.0941 max mem: 9390 +Train: [28] [3800/6250] eta: 0:07:04 lr: 0.000107 grad: 0.0671 (0.0703) loss: 0.8323 (0.8326) time: 0.1686 data: 0.0849 max mem: 9390 +Train: [28] [3900/6250] eta: 0:06:47 lr: 0.000107 grad: 0.0682 (0.0703) loss: 0.8376 (0.8327) time: 0.1777 data: 0.0924 max mem: 9390 +Train: [28] [4000/6250] eta: 0:06:29 lr: 0.000107 grad: 0.0710 (0.0703) loss: 0.8317 (0.8327) time: 0.1868 data: 0.0991 max mem: 9390 +Train: [28] [4100/6250] eta: 0:06:12 lr: 0.000107 grad: 0.0651 (0.0703) loss: 0.8341 (0.8328) time: 0.1541 data: 0.0670 max mem: 9390 +Train: [28] [4200/6250] eta: 0:05:54 lr: 0.000107 grad: 0.0717 (0.0703) loss: 0.8357 (0.8328) time: 0.1821 data: 0.0954 max mem: 9390 +Train: [28] [4300/6250] eta: 0:05:37 lr: 0.000107 grad: 0.0675 (0.0703) loss: 0.8372 (0.8329) time: 0.1608 data: 0.0761 max mem: 9390 +Train: [28] [4400/6250] eta: 0:05:20 lr: 0.000107 grad: 0.0670 (0.0703) loss: 0.8348 (0.8329) time: 0.1496 data: 0.0627 max mem: 9390 +Train: [28] [4500/6250] eta: 0:05:02 lr: 0.000107 grad: 0.0694 (0.0703) loss: 0.8358 (0.8329) time: 0.1635 data: 0.0808 max mem: 9390 +Train: [28] [4600/6250] eta: 0:04:45 lr: 0.000107 grad: 0.0668 (0.0703) loss: 0.8295 (0.8330) time: 0.1783 data: 0.0993 max mem: 9390 +Train: [28] [4700/6250] eta: 0:04:27 lr: 0.000107 grad: 0.0666 (0.0703) loss: 0.8332 (0.8330) time: 0.1724 data: 0.0863 max mem: 9390 +Train: [28] [4800/6250] eta: 0:04:10 lr: 0.000107 grad: 0.0739 (0.0703) loss: 0.8384 (0.8330) time: 0.1801 data: 0.0915 max mem: 9390 +Train: [28] [4900/6250] eta: 0:03:52 lr: 0.000107 grad: 0.0656 (0.0703) loss: 0.8303 (0.8330) time: 0.1584 data: 0.0590 max mem: 9390 +Train: [28] [5000/6250] eta: 0:03:35 lr: 0.000107 grad: 0.0662 (0.0703) loss: 0.8400 (0.8331) time: 0.1608 data: 0.0784 max mem: 9390 +Train: [28] [5100/6250] eta: 0:03:18 lr: 0.000107 grad: 0.0701 (0.0703) loss: 0.8391 (0.8331) time: 0.1990 data: 0.1150 max mem: 9390 +Train: [28] [5200/6250] eta: 0:03:00 lr: 0.000107 grad: 0.0656 (0.0703) loss: 0.8310 (0.8332) time: 0.1710 data: 0.0900 max mem: 9390 +Train: [28] [5300/6250] eta: 0:02:43 lr: 0.000107 grad: 0.0670 (0.0703) loss: 0.8413 (0.8332) time: 0.1610 data: 0.0671 max mem: 9390 +Train: [28] [5400/6250] eta: 0:02:26 lr: 0.000107 grad: 0.0692 (0.0703) loss: 0.8346 (0.8333) time: 0.1728 data: 0.0856 max mem: 9390 +Train: [28] [5500/6250] eta: 0:02:09 lr: 0.000107 grad: 0.0708 (0.0702) loss: 0.8295 (0.8333) time: 0.1640 data: 0.0810 max mem: 9390 +Train: [28] [5600/6250] eta: 0:01:51 lr: 0.000106 grad: 0.0729 (0.0703) loss: 0.8355 (0.8333) time: 0.1707 data: 0.0803 max mem: 9390 +Train: [28] [5700/6250] eta: 0:01:34 lr: 0.000106 grad: 0.0669 (0.0702) loss: 0.8366 (0.8333) time: 0.1847 data: 0.1048 max mem: 9390 +Train: [28] [5800/6250] eta: 0:01:17 lr: 0.000106 grad: 0.0733 (0.0703) loss: 0.8296 (0.8333) time: 0.1709 data: 0.0820 max mem: 9390 +Train: [28] [5900/6250] eta: 0:01:00 lr: 0.000106 grad: 0.0702 (0.0703) loss: 0.8366 (0.8334) time: 0.2376 data: 0.1495 max mem: 9390 +Train: [28] [6000/6250] eta: 0:00:42 lr: 0.000106 grad: 0.0693 (0.0703) loss: 0.8333 (0.8334) time: 0.1665 data: 0.0784 max mem: 9390 +Train: [28] [6100/6250] eta: 0:00:25 lr: 0.000106 grad: 0.0672 (0.0703) loss: 0.8424 (0.8334) time: 0.1698 data: 0.0818 max mem: 9390 +Train: [28] [6200/6250] eta: 0:00:08 lr: 0.000106 grad: 0.0685 (0.0703) loss: 0.8350 (0.8334) time: 0.1662 data: 0.0841 max mem: 9390 +Train: [28] [6249/6250] eta: 0:00:00 lr: 0.000106 grad: 0.0689 (0.0703) loss: 0.8346 (0.8334) time: 0.1791 data: 0.0919 max mem: 9390 +Train: [28] Total time: 0:18:02 (0.1732 s / it) +Averaged stats: lr: 0.000106 grad: 0.0689 (0.0703) loss: 0.8346 (0.8334) +Eval (hcp-train-subset): [28] [ 0/62] eta: 0:04:52 loss: 0.8551 (0.8551) time: 4.7152 data: 4.6833 max mem: 9390 +Eval (hcp-train-subset): [28] [61/62] eta: 0:00:00 loss: 0.8403 (0.8421) time: 0.1413 data: 0.1155 max mem: 9390 +Eval (hcp-train-subset): [28] Total time: 0:00:13 (0.2208 s / it) +Averaged stats (hcp-train-subset): loss: 0.8403 (0.8421) +Eval (hcp-val): [28] [ 0/62] eta: 0:04:37 loss: 0.8385 (0.8385) time: 4.4722 data: 4.4427 max mem: 9390 +Eval (hcp-val): [28] [61/62] eta: 0:00:00 loss: 0.8380 (0.8394) time: 0.1188 data: 0.0922 max mem: 9390 +Eval (hcp-val): [28] Total time: 0:00:13 (0.2116 s / it) +Averaged stats (hcp-val): loss: 0.8380 (0.8394) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +Train: [29] [ 0/6250] eta: 9:07:23 lr: 0.000106 grad: 0.0584 (0.0584) loss: 0.8295 (0.8295) time: 5.2549 data: 4.9794 max mem: 9390 +Train: [29] [ 100/6250] eta: 0:22:45 lr: 0.000106 grad: 0.0695 (0.0815) loss: 0.8449 (0.8489) time: 0.1660 data: 0.0754 max mem: 9390 +Train: [29] [ 200/6250] eta: 0:20:01 lr: 0.000106 grad: 0.0615 (0.0761) loss: 0.8362 (0.8424) time: 0.1778 data: 0.0824 max mem: 9390 +Train: [29] [ 300/6250] eta: 0:18:43 lr: 0.000106 grad: 0.0704 (0.0752) loss: 0.8318 (0.8403) time: 0.1635 data: 0.0688 max mem: 9390 +Train: [29] [ 400/6250] eta: 0:17:52 lr: 0.000106 grad: 0.0817 (0.0760) loss: 0.8283 (0.8380) time: 0.1837 data: 0.0818 max mem: 9390 +Train: [29] [ 500/6250] eta: 0:17:09 lr: 0.000106 grad: 0.0704 (0.0754) loss: 0.8281 (0.8365) time: 0.1684 data: 0.0682 max mem: 9390 +Train: [29] [ 600/6250] eta: 0:16:38 lr: 0.000106 grad: 0.0698 (0.0745) loss: 0.8342 (0.8358) time: 0.1758 data: 0.0851 max mem: 9390 +Train: [29] [ 700/6250] eta: 0:16:30 lr: 0.000106 grad: 0.0724 (0.0740) loss: 0.8283 (0.8351) time: 0.1778 data: 0.0761 max mem: 9390 +Train: [29] [ 800/6250] eta: 0:16:03 lr: 0.000106 grad: 0.0676 (0.0735) loss: 0.8305 (0.8348) time: 0.1604 data: 0.0751 max mem: 9390 +Train: [29] [ 900/6250] eta: 0:15:45 lr: 0.000106 grad: 0.0725 (0.0734) loss: 0.8315 (0.8341) time: 0.1310 data: 0.0384 max mem: 9390 +Train: [29] [1000/6250] eta: 0:15:15 lr: 0.000106 grad: 0.0683 (0.0733) loss: 0.8294 (0.8335) time: 0.1935 data: 0.1185 max mem: 9390 +Train: [29] [1100/6250] eta: 0:14:58 lr: 0.000106 grad: 0.0697 (0.0731) loss: 0.8289 (0.8330) time: 0.1701 data: 0.0830 max mem: 9390 +Train: [29] [1200/6250] eta: 0:14:38 lr: 0.000106 grad: 0.0676 (0.0729) loss: 0.8310 (0.8326) time: 0.1761 data: 0.0873 max mem: 9390 +Train: [29] [1300/6250] eta: 0:14:15 lr: 0.000106 grad: 0.0709 (0.0729) loss: 0.8280 (0.8322) time: 0.1402 data: 0.0573 max mem: 9390 +Train: [29] [1400/6250] eta: 0:13:55 lr: 0.000106 grad: 0.0707 (0.0729) loss: 0.8257 (0.8317) time: 0.1878 data: 0.0932 max mem: 9390 +Train: [29] [1500/6250] eta: 0:13:36 lr: 0.000106 grad: 0.0688 (0.0728) loss: 0.8275 (0.8315) time: 0.1638 data: 0.0644 max mem: 9390 +Train: [29] [1600/6250] eta: 0:13:17 lr: 0.000106 grad: 0.0795 (0.0732) loss: 0.8238 (0.8312) time: 0.1660 data: 0.0661 max mem: 9390 +Train: [29] [1700/6250] eta: 0:12:57 lr: 0.000106 grad: 0.0682 (0.0731) loss: 0.8285 (0.8310) time: 0.1568 data: 0.0686 max mem: 9390 +Train: [29] [1800/6250] eta: 0:12:41 lr: 0.000106 grad: 0.0651 (0.0732) loss: 0.8279 (0.8307) time: 0.1620 data: 0.0718 max mem: 9390 +Train: [29] [1900/6250] eta: 0:12:23 lr: 0.000106 grad: 0.0721 (0.0731) loss: 0.8307 (0.8306) time: 0.1659 data: 0.0735 max mem: 9390 +Train: [29] [2000/6250] eta: 0:12:06 lr: 0.000106 grad: 0.0670 (0.0731) loss: 0.8301 (0.8305) time: 0.1690 data: 0.0789 max mem: 9390 +Train: [29] [2100/6250] eta: 0:11:49 lr: 0.000106 grad: 0.0746 (0.0731) loss: 0.8234 (0.8305) time: 0.1611 data: 0.0719 max mem: 9390 +Train: [29] [2200/6250] eta: 0:11:32 lr: 0.000106 grad: 0.0716 (0.0731) loss: 0.8265 (0.8305) time: 0.1784 data: 0.0930 max mem: 9390 +Train: [29] [2300/6250] eta: 0:11:14 lr: 0.000106 grad: 0.0682 (0.0730) loss: 0.8308 (0.8305) time: 0.1434 data: 0.0586 max mem: 9390 +Train: [29] [2400/6250] eta: 0:10:57 lr: 0.000106 grad: 0.0668 (0.0729) loss: 0.8350 (0.8305) time: 0.1703 data: 0.0789 max mem: 9390 +Train: [29] [2500/6250] eta: 0:10:40 lr: 0.000106 grad: 0.0704 (0.0728) loss: 0.8355 (0.8305) time: 0.1642 data: 0.0746 max mem: 9390 +Train: [29] [2600/6250] eta: 0:10:23 lr: 0.000106 grad: 0.0697 (0.0728) loss: 0.8314 (0.8305) time: 0.1692 data: 0.0882 max mem: 9390 +Train: [29] [2700/6250] eta: 0:10:06 lr: 0.000106 grad: 0.0680 (0.0727) loss: 0.8324 (0.8305) time: 0.1805 data: 0.0867 max mem: 9390 +Train: [29] [2800/6250] eta: 0:09:48 lr: 0.000106 grad: 0.0693 (0.0728) loss: 0.8279 (0.8305) time: 0.1748 data: 0.0794 max mem: 9390 +Train: [29] [2900/6250] eta: 0:09:31 lr: 0.000106 grad: 0.0681 (0.0728) loss: 0.8276 (0.8305) time: 0.1921 data: 0.1018 max mem: 9390 +Train: [29] [3000/6250] eta: 0:09:13 lr: 0.000106 grad: 0.0675 (0.0727) loss: 0.8270 (0.8305) time: 0.2059 data: 0.1167 max mem: 9390 +Train: [29] [3100/6250] eta: 0:08:56 lr: 0.000106 grad: 0.0652 (0.0726) loss: 0.8316 (0.8305) time: 0.1878 data: 0.0965 max mem: 9390 +Train: [29] [3200/6250] eta: 0:08:38 lr: 0.000106 grad: 0.0663 (0.0725) loss: 0.8320 (0.8305) time: 0.1696 data: 0.0875 max mem: 9390 +Train: [29] [3300/6250] eta: 0:08:21 lr: 0.000106 grad: 0.0667 (0.0724) loss: 0.8292 (0.8305) time: 0.1883 data: 0.1057 max mem: 9390 +Train: [29] [3400/6250] eta: 0:08:03 lr: 0.000106 grad: 0.0685 (0.0723) loss: 0.8245 (0.8305) time: 0.1682 data: 0.0852 max mem: 9390 +Train: [29] [3500/6250] eta: 0:07:46 lr: 0.000105 grad: 0.0677 (0.0723) loss: 0.8313 (0.8304) time: 0.1738 data: 0.0891 max mem: 9390 +Train: [29] [3600/6250] eta: 0:07:29 lr: 0.000105 grad: 0.0666 (0.0723) loss: 0.8320 (0.8304) time: 0.1559 data: 0.0684 max mem: 9390 +Train: [29] [3700/6250] eta: 0:07:12 lr: 0.000105 grad: 0.0705 (0.0722) loss: 0.8258 (0.8303) time: 0.1443 data: 0.0568 max mem: 9390 +Train: [29] [3800/6250] eta: 0:06:54 lr: 0.000105 grad: 0.0697 (0.0722) loss: 0.8245 (0.8303) time: 0.1470 data: 0.0575 max mem: 9390 +Train: [29] [3900/6250] eta: 0:06:38 lr: 0.000105 grad: 0.0699 (0.0722) loss: 0.8327 (0.8304) time: 0.1573 data: 0.0711 max mem: 9390 +Train: [29] [4000/6250] eta: 0:06:21 lr: 0.000105 grad: 0.0741 (0.0722) loss: 0.8289 (0.8304) time: 0.1693 data: 0.0893 max mem: 9390 +Train: [29] [4100/6250] eta: 0:06:04 lr: 0.000105 grad: 0.0691 (0.0722) loss: 0.8290 (0.8304) time: 0.1812 data: 0.0937 max mem: 9390 +Train: [29] [4200/6250] eta: 0:05:46 lr: 0.000105 grad: 0.0703 (0.0721) loss: 0.8304 (0.8304) time: 0.1549 data: 0.0676 max mem: 9390 +Train: [29] [4300/6250] eta: 0:05:29 lr: 0.000105 grad: 0.0709 (0.0721) loss: 0.8295 (0.8304) time: 0.1814 data: 0.0982 max mem: 9390 +Train: [29] [4400/6250] eta: 0:05:12 lr: 0.000105 grad: 0.0755 (0.0722) loss: 0.8306 (0.8304) time: 0.1688 data: 0.0828 max mem: 9390 +Train: [29] [4500/6250] eta: 0:04:56 lr: 0.000105 grad: 0.0664 (0.0722) loss: 0.8291 (0.8304) time: 0.2067 data: 0.1220 max mem: 9390 +Train: [29] [4600/6250] eta: 0:04:39 lr: 0.000105 grad: 0.0726 (0.0722) loss: 0.8315 (0.8304) time: 0.1574 data: 0.0742 max mem: 9390 +Train: [29] [4700/6250] eta: 0:04:22 lr: 0.000105 grad: 0.0728 (0.0723) loss: 0.8306 (0.8304) time: 0.1692 data: 0.0838 max mem: 9390 +Train: [29] [4800/6250] eta: 0:04:05 lr: 0.000105 grad: 0.0692 (0.0723) loss: 0.8302 (0.8304) time: 0.1751 data: 0.0927 max mem: 9390 +Train: [29] [4900/6250] eta: 0:03:48 lr: 0.000105 grad: 0.0704 (0.0723) loss: 0.8252 (0.8304) time: 0.1729 data: 0.0870 max mem: 9390 +Train: [29] [5000/6250] eta: 0:03:31 lr: 0.000105 grad: 0.0702 (0.0724) loss: 0.8344 (0.8304) time: 0.1678 data: 0.0730 max mem: 9390 +Train: [29] [5100/6250] eta: 0:03:14 lr: 0.000105 grad: 0.0712 (0.0724) loss: 0.8323 (0.8304) time: 0.1585 data: 0.0819 max mem: 9390 +Train: [29] [5200/6250] eta: 0:02:57 lr: 0.000105 grad: 0.0703 (0.0724) loss: 0.8306 (0.8304) time: 0.1745 data: 0.0884 max mem: 9390 +Train: [29] [5300/6250] eta: 0:02:40 lr: 0.000105 grad: 0.0702 (0.0724) loss: 0.8261 (0.8304) time: 0.1591 data: 0.0702 max mem: 9390 +Train: [29] [5400/6250] eta: 0:02:23 lr: 0.000105 grad: 0.0729 (0.0724) loss: 0.8310 (0.8304) time: 0.1736 data: 0.0926 max mem: 9390 +Train: [29] [5500/6250] eta: 0:02:06 lr: 0.000105 grad: 0.0726 (0.0725) loss: 0.8207 (0.8304) time: 0.1456 data: 0.0528 max mem: 9390 +Train: [29] [5600/6250] eta: 0:01:49 lr: 0.000105 grad: 0.0694 (0.0724) loss: 0.8278 (0.8304) time: 0.1719 data: 0.0921 max mem: 9390 +Train: [29] [5700/6250] eta: 0:01:33 lr: 0.000105 grad: 0.0668 (0.0724) loss: 0.8289 (0.8305) time: 0.1616 data: 0.0681 max mem: 9390 +Train: [29] [5800/6250] eta: 0:01:16 lr: 0.000105 grad: 0.0739 (0.0725) loss: 0.8266 (0.8304) time: 0.1947 data: 0.1023 max mem: 9390 +Train: [29] [5900/6250] eta: 0:00:59 lr: 0.000105 grad: 0.0728 (0.0725) loss: 0.8280 (0.8304) time: 0.1726 data: 0.0779 max mem: 9390 +Train: [29] [6000/6250] eta: 0:00:42 lr: 0.000105 grad: 0.0735 (0.0727) loss: 0.8245 (0.8304) time: 0.1686 data: 0.0755 max mem: 9390 +Train: [29] [6100/6250] eta: 0:00:25 lr: 0.000105 grad: 0.0752 (0.0727) loss: 0.8258 (0.8304) time: 0.1693 data: 0.0807 max mem: 9390 +Train: [29] [6200/6250] eta: 0:00:08 lr: 0.000105 grad: 0.0706 (0.0728) loss: 0.8297 (0.8303) time: 0.1711 data: 0.0884 max mem: 9390 +Train: [29] [6249/6250] eta: 0:00:00 lr: 0.000105 grad: 0.0698 (0.0728) loss: 0.8289 (0.8303) time: 0.1565 data: 0.0624 max mem: 9390 +Train: [29] Total time: 0:17:46 (0.1706 s / it) +Averaged stats: lr: 0.000105 grad: 0.0698 (0.0728) loss: 0.8289 (0.8303) +Eval (hcp-train-subset): [29] [ 0/62] eta: 0:03:34 loss: 0.8518 (0.8518) time: 3.4627 data: 3.3404 max mem: 9390 +Eval (hcp-train-subset): [29] [61/62] eta: 0:00:00 loss: 0.8396 (0.8424) time: 0.1116 data: 0.0867 max mem: 9390 +Eval (hcp-train-subset): [29] Total time: 0:00:13 (0.2243 s / it) +Averaged stats (hcp-train-subset): loss: 0.8396 (0.8424) +Making plots (hcp-train-subset): example=14 +Eval (hcp-val): [29] [ 0/62] eta: 0:05:20 loss: 0.8341 (0.8341) time: 5.1686 data: 5.1368 max mem: 9390 +Eval (hcp-val): [29] [61/62] eta: 0:00:00 loss: 0.8388 (0.8394) time: 0.1292 data: 0.1026 max mem: 9390 +Eval (hcp-val): [29] Total time: 0:00:13 (0.2163 s / it) +Averaged stats (hcp-val): loss: 0.8388 (0.8394) +Making plots (hcp-val): example=53 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +Train: [30] [ 0/6250] eta: 11:02:38 lr: 0.000105 grad: 0.0543 (0.0543) loss: 0.8419 (0.8419) time: 6.3613 data: 6.2605 max mem: 9390 +Train: [30] [ 100/6250] eta: 0:21:58 lr: 0.000105 grad: 0.0659 (0.0759) loss: 0.8410 (0.8459) time: 0.1563 data: 0.0607 max mem: 9390 +Train: [30] [ 200/6250] eta: 0:19:23 lr: 0.000105 grad: 0.0677 (0.0736) loss: 0.8326 (0.8416) time: 0.1744 data: 0.0820 max mem: 9390 +Train: [30] [ 300/6250] eta: 0:18:25 lr: 0.000105 grad: 0.0638 (0.0718) loss: 0.8368 (0.8394) time: 0.1725 data: 0.0828 max mem: 9390 +Train: [30] [ 400/6250] eta: 0:17:43 lr: 0.000105 grad: 0.0648 (0.0709) loss: 0.8326 (0.8374) time: 0.1653 data: 0.0736 max mem: 9390 +Train: [30] [ 500/6250] eta: 0:17:11 lr: 0.000105 grad: 0.0653 (0.0705) loss: 0.8334 (0.8359) time: 0.1835 data: 0.0915 max mem: 9390 +Train: [30] [ 600/6250] eta: 0:16:39 lr: 0.000105 grad: 0.0669 (0.0707) loss: 0.8276 (0.8348) time: 0.1611 data: 0.0644 max mem: 9390 +Train: [30] [ 700/6250] eta: 0:16:20 lr: 0.000105 grad: 0.0697 (0.0710) loss: 0.8249 (0.8339) time: 0.1940 data: 0.1036 max mem: 9390 +Train: [30] [ 800/6250] eta: 0:16:03 lr: 0.000105 grad: 0.0716 (0.0713) loss: 0.8256 (0.8332) time: 0.1602 data: 0.0625 max mem: 9390 +Train: [30] [ 900/6250] eta: 0:15:48 lr: 0.000105 grad: 0.0697 (0.0716) loss: 0.8275 (0.8325) time: 0.1717 data: 0.0814 max mem: 9390 +Train: [30] [1000/6250] eta: 0:15:24 lr: 0.000105 grad: 0.0686 (0.0717) loss: 0.8248 (0.8320) time: 0.1733 data: 0.0901 max mem: 9390 +Train: [30] [1100/6250] eta: 0:15:04 lr: 0.000105 grad: 0.0685 (0.0717) loss: 0.8292 (0.8316) time: 0.1579 data: 0.0686 max mem: 9390 +Train: [30] [1200/6250] eta: 0:14:44 lr: 0.000105 grad: 0.0692 (0.0716) loss: 0.8302 (0.8313) time: 0.1608 data: 0.0726 max mem: 9390 +Train: [30] [1300/6250] eta: 0:14:22 lr: 0.000105 grad: 0.0668 (0.0717) loss: 0.8319 (0.8310) time: 0.1519 data: 0.0708 max mem: 9390 +Train: [30] [1400/6250] eta: 0:14:04 lr: 0.000104 grad: 0.0700 (0.0716) loss: 0.8232 (0.8307) time: 0.1827 data: 0.0912 max mem: 9390 +Train: [30] [1500/6250] eta: 0:13:47 lr: 0.000104 grad: 0.0685 (0.0716) loss: 0.8235 (0.8305) time: 0.1772 data: 0.0811 max mem: 9390 +Train: [30] [1600/6250] eta: 0:13:27 lr: 0.000104 grad: 0.0713 (0.0718) loss: 0.8289 (0.8302) time: 0.1584 data: 0.0714 max mem: 9390 +Train: [30] [1700/6250] eta: 0:13:10 lr: 0.000104 grad: 0.0693 (0.0718) loss: 0.8215 (0.8299) time: 0.1605 data: 0.0711 max mem: 9390 +Train: [30] [1800/6250] eta: 0:12:51 lr: 0.000104 grad: 0.0746 (0.0720) loss: 0.8219 (0.8296) time: 0.1802 data: 0.0951 max mem: 9390 +Train: [30] [1900/6250] eta: 0:12:32 lr: 0.000104 grad: 0.0719 (0.0722) loss: 0.8257 (0.8294) time: 0.1725 data: 0.0825 max mem: 9390 +Train: [30] [2000/6250] eta: 0:12:12 lr: 0.000104 grad: 0.0693 (0.0724) loss: 0.8260 (0.8292) time: 0.1625 data: 0.0725 max mem: 9390 +Train: [30] [2100/6250] eta: 0:11:54 lr: 0.000104 grad: 0.0734 (0.0725) loss: 0.8274 (0.8291) time: 0.1706 data: 0.0820 max mem: 9390 +Train: [30] [2200/6250] eta: 0:11:35 lr: 0.000104 grad: 0.0672 (0.0726) loss: 0.8300 (0.8290) time: 0.1442 data: 0.0544 max mem: 9390 +Train: [30] [2300/6250] eta: 0:11:17 lr: 0.000104 grad: 0.0751 (0.0726) loss: 0.8269 (0.8290) time: 0.1798 data: 0.0917 max mem: 9390 +Train: [30] [2400/6250] eta: 0:10:58 lr: 0.000104 grad: 0.0731 (0.0728) loss: 0.8254 (0.8289) time: 0.1708 data: 0.0809 max mem: 9390 +Train: [30] [2500/6250] eta: 0:10:41 lr: 0.000104 grad: 0.0665 (0.0728) loss: 0.8368 (0.8290) time: 0.1745 data: 0.0944 max mem: 9390 +Train: [30] [2600/6250] eta: 0:10:23 lr: 0.000104 grad: 0.0669 (0.0728) loss: 0.8335 (0.8290) time: 0.1713 data: 0.0852 max mem: 9390 +Train: [30] [2700/6250] eta: 0:10:05 lr: 0.000104 grad: 0.0689 (0.0727) loss: 0.8287 (0.8291) time: 0.1675 data: 0.0813 max mem: 9390 +Train: [30] [2800/6250] eta: 0:09:48 lr: 0.000104 grad: 0.0684 (0.0727) loss: 0.8256 (0.8291) time: 0.1829 data: 0.0959 max mem: 9390 +Train: [30] [2900/6250] eta: 0:09:30 lr: 0.000104 grad: 0.0701 (0.0727) loss: 0.8259 (0.8291) time: 0.1486 data: 0.0626 max mem: 9390 +Train: [30] [3000/6250] eta: 0:09:12 lr: 0.000104 grad: 0.0706 (0.0727) loss: 0.8310 (0.8291) time: 0.1355 data: 0.0453 max mem: 9390 +Train: [30] [3100/6250] eta: 0:08:54 lr: 0.000104 grad: 0.0707 (0.0726) loss: 0.8301 (0.8292) time: 0.1585 data: 0.0742 max mem: 9390 +Train: [30] [3200/6250] eta: 0:08:36 lr: 0.000104 grad: 0.0700 (0.0727) loss: 0.8257 (0.8291) time: 0.1717 data: 0.0886 max mem: 9390 +Train: [30] [3300/6250] eta: 0:08:19 lr: 0.000104 grad: 0.0696 (0.0727) loss: 0.8282 (0.8292) time: 0.1735 data: 0.0898 max mem: 9390 +Train: [30] [3400/6250] eta: 0:08:01 lr: 0.000104 grad: 0.0680 (0.0727) loss: 0.8314 (0.8292) time: 0.1483 data: 0.0640 max mem: 9390 +Train: [30] [3500/6250] eta: 0:07:44 lr: 0.000104 grad: 0.0773 (0.0728) loss: 0.8239 (0.8292) time: 0.1805 data: 0.0966 max mem: 9390 +Train: [30] [3600/6250] eta: 0:07:27 lr: 0.000104 grad: 0.0801 (0.0729) loss: 0.8255 (0.8291) time: 0.1611 data: 0.0690 max mem: 9390 +Train: [30] [3700/6250] eta: 0:07:10 lr: 0.000104 grad: 0.0761 (0.0731) loss: 0.8285 (0.8290) time: 0.1822 data: 0.0973 max mem: 9390 +Train: [30] [3800/6250] eta: 0:06:53 lr: 0.000104 grad: 0.0704 (0.0731) loss: 0.8310 (0.8290) time: 0.1575 data: 0.0690 max mem: 9390 +Train: [30] [3900/6250] eta: 0:06:35 lr: 0.000104 grad: 0.0699 (0.0731) loss: 0.8286 (0.8289) time: 0.1469 data: 0.0636 max mem: 9390 +Train: [30] [4000/6250] eta: 0:06:18 lr: 0.000104 grad: 0.0780 (0.0733) loss: 0.8249 (0.8289) time: 0.1630 data: 0.0756 max mem: 9390 +Train: [30] [4100/6250] eta: 0:06:01 lr: 0.000104 grad: 0.0747 (0.0733) loss: 0.8303 (0.8288) time: 0.1610 data: 0.0775 max mem: 9390 +Train: [30] [4200/6250] eta: 0:05:44 lr: 0.000104 grad: 0.0728 (0.0734) loss: 0.8261 (0.8288) time: 0.1699 data: 0.0817 max mem: 9390 +Train: [30] [4300/6250] eta: 0:05:27 lr: 0.000104 grad: 0.0717 (0.0735) loss: 0.8235 (0.8288) time: 0.1597 data: 0.0783 max mem: 9390 +Train: [30] [4400/6250] eta: 0:05:10 lr: 0.000104 grad: 0.0684 (0.0735) loss: 0.8285 (0.8288) time: 0.1723 data: 0.0891 max mem: 9390 +Train: [30] [4500/6250] eta: 0:04:53 lr: 0.000104 grad: 0.0736 (0.0736) loss: 0.8208 (0.8287) time: 0.1400 data: 0.0480 max mem: 9390 +Train: [30] [4600/6250] eta: 0:04:37 lr: 0.000104 grad: 0.0801 (0.0737) loss: 0.8255 (0.8287) time: 0.1890 data: 0.1079 max mem: 9390 +Train: [30] [4700/6250] eta: 0:04:20 lr: 0.000104 grad: 0.0734 (0.0737) loss: 0.8253 (0.8286) time: 0.1298 data: 0.0397 max mem: 9390 +Train: [30] [4800/6250] eta: 0:04:03 lr: 0.000104 grad: 0.0732 (0.0738) loss: 0.8278 (0.8286) time: 0.1679 data: 0.0849 max mem: 9390 +Train: [30] [4900/6250] eta: 0:03:46 lr: 0.000104 grad: 0.0746 (0.0738) loss: 0.8294 (0.8285) time: 0.1641 data: 0.0799 max mem: 9390 +Train: [30] [5000/6250] eta: 0:03:29 lr: 0.000104 grad: 0.0674 (0.0739) loss: 0.8307 (0.8285) time: 0.1759 data: 0.0853 max mem: 9390 +Train: [30] [5100/6250] eta: 0:03:13 lr: 0.000104 grad: 0.0698 (0.0739) loss: 0.8283 (0.8284) time: 0.1683 data: 0.0831 max mem: 9390 +Train: [30] [5200/6250] eta: 0:02:56 lr: 0.000104 grad: 0.0718 (0.0739) loss: 0.8268 (0.8284) time: 0.1772 data: 0.0927 max mem: 9390 +Train: [30] [5300/6250] eta: 0:02:39 lr: 0.000104 grad: 0.0705 (0.0739) loss: 0.8220 (0.8284) time: 0.1679 data: 0.0864 max mem: 9390 +Train: [30] [5400/6250] eta: 0:02:22 lr: 0.000103 grad: 0.0707 (0.0739) loss: 0.8258 (0.8283) time: 0.1741 data: 0.0908 max mem: 9390 +Train: [30] [5500/6250] eta: 0:02:05 lr: 0.000103 grad: 0.0751 (0.0740) loss: 0.8284 (0.8283) time: 0.1701 data: 0.0843 max mem: 9390 +Train: [30] [5600/6250] eta: 0:01:49 lr: 0.000103 grad: 0.0778 (0.0740) loss: 0.8271 (0.8283) time: 0.1741 data: 0.0887 max mem: 9390 +Train: [30] [5700/6250] eta: 0:01:32 lr: 0.000103 grad: 0.0676 (0.0739) loss: 0.8328 (0.8283) time: 0.1669 data: 0.0804 max mem: 9390 +Train: [30] [5800/6250] eta: 0:01:15 lr: 0.000103 grad: 0.0688 (0.0740) loss: 0.8269 (0.8283) time: 0.1449 data: 0.0544 max mem: 9390 +Train: [30] [5900/6250] eta: 0:00:58 lr: 0.000103 grad: 0.0698 (0.0740) loss: 0.8322 (0.8283) time: 0.1757 data: 0.0938 max mem: 9390 +Train: [30] [6000/6250] eta: 0:00:42 lr: 0.000103 grad: 0.0693 (0.0739) loss: 0.8247 (0.8283) time: 0.1975 data: 0.1152 max mem: 9390 +Train: [30] [6100/6250] eta: 0:00:25 lr: 0.000103 grad: 0.0739 (0.0739) loss: 0.8212 (0.8283) time: 0.1849 data: 0.1005 max mem: 9390 +Train: [30] [6200/6250] eta: 0:00:08 lr: 0.000103 grad: 0.0645 (0.0739) loss: 0.8293 (0.8283) time: 0.1599 data: 0.0664 max mem: 9390 +Train: [30] [6249/6250] eta: 0:00:00 lr: 0.000103 grad: 0.0682 (0.0739) loss: 0.8305 (0.8283) time: 0.1996 data: 0.1219 max mem: 9390 +Train: [30] Total time: 0:17:42 (0.1700 s / it) +Averaged stats: lr: 0.000103 grad: 0.0682 (0.0739) loss: 0.8305 (0.8283) +Eval (hcp-train-subset): [30] [ 0/62] eta: 0:04:48 loss: 0.8568 (0.8568) time: 4.6523 data: 4.6222 max mem: 9390 +Eval (hcp-train-subset): [30] [61/62] eta: 0:00:00 loss: 0.8419 (0.8434) time: 0.1717 data: 0.1452 max mem: 9390 +Eval (hcp-train-subset): [30] Total time: 0:00:14 (0.2352 s / it) +Averaged stats (hcp-train-subset): loss: 0.8419 (0.8434) +Eval (hcp-val): [30] [ 0/62] eta: 0:04:01 loss: 0.8360 (0.8360) time: 3.8954 data: 3.8410 max mem: 9390 +Eval (hcp-val): [30] [61/62] eta: 0:00:00 loss: 0.8374 (0.8390) time: 0.1356 data: 0.1106 max mem: 9390 +Eval (hcp-val): [30] Total time: 0:00:14 (0.2341 s / it) +Averaged stats (hcp-val): loss: 0.8374 (0.8390) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +Train: [31] [ 0/6250] eta: 10:55:38 lr: 0.000103 grad: 0.0893 (0.0893) loss: 0.8302 (0.8302) time: 6.2942 data: 6.1604 max mem: 9390 +Train: [31] [ 100/6250] eta: 0:23:38 lr: 0.000103 grad: 0.0717 (0.0814) loss: 0.8443 (0.8386) time: 0.1788 data: 0.0906 max mem: 9390 +Train: [31] [ 200/6250] eta: 0:20:34 lr: 0.000103 grad: 0.0676 (0.0767) loss: 0.8336 (0.8370) time: 0.1728 data: 0.0755 max mem: 9390 +Train: [31] [ 300/6250] eta: 0:19:39 lr: 0.000103 grad: 0.0724 (0.0772) loss: 0.8341 (0.8341) time: 0.1918 data: 0.0955 max mem: 9390 +Train: [31] [ 400/6250] eta: 0:18:44 lr: 0.000103 grad: 0.0665 (0.0757) loss: 0.8249 (0.8330) time: 0.1734 data: 0.0693 max mem: 9390 +Train: [31] [ 500/6250] eta: 0:17:55 lr: 0.000103 grad: 0.0646 (0.0742) loss: 0.8323 (0.8328) time: 0.1651 data: 0.0659 max mem: 9390 +Train: [31] [ 600/6250] eta: 0:17:14 lr: 0.000103 grad: 0.0664 (0.0732) loss: 0.8305 (0.8325) time: 0.1358 data: 0.0381 max mem: 9390 +Train: [31] [ 700/6250] eta: 0:16:51 lr: 0.000103 grad: 0.0702 (0.0724) loss: 0.8350 (0.8326) time: 0.2052 data: 0.1027 max mem: 9390 +Train: [31] [ 800/6250] eta: 0:16:18 lr: 0.000103 grad: 0.0638 (0.0720) loss: 0.8378 (0.8328) time: 0.1736 data: 0.0728 max mem: 9390 +Train: [31] [ 900/6250] eta: 0:15:52 lr: 0.000103 grad: 0.0651 (0.0717) loss: 0.8327 (0.8328) time: 0.1610 data: 0.0489 max mem: 9390 +Train: [31] [1000/6250] eta: 0:15:34 lr: 0.000103 grad: 0.0679 (0.0714) loss: 0.8320 (0.8327) time: 0.1541 data: 0.0664 max mem: 9390 +Train: [31] [1100/6250] eta: 0:15:18 lr: 0.000103 grad: 0.0697 (0.0713) loss: 0.8334 (0.8326) time: 0.1638 data: 0.0721 max mem: 9390 +Train: [31] [1200/6250] eta: 0:14:55 lr: 0.000103 grad: 0.0708 (0.0712) loss: 0.8285 (0.8324) time: 0.1570 data: 0.0708 max mem: 9390 +Train: [31] [1300/6250] eta: 0:14:35 lr: 0.000103 grad: 0.0678 (0.0711) loss: 0.8321 (0.8323) time: 0.1551 data: 0.0653 max mem: 9390 +Train: [31] [1400/6250] eta: 0:14:14 lr: 0.000103 grad: 0.0682 (0.0711) loss: 0.8323 (0.8322) time: 0.1486 data: 0.0551 max mem: 9390 +Train: [31] [1500/6250] eta: 0:13:54 lr: 0.000103 grad: 0.0698 (0.0711) loss: 0.8311 (0.8321) time: 0.1828 data: 0.0919 max mem: 9390 +Train: [31] [1600/6250] eta: 0:13:34 lr: 0.000103 grad: 0.0673 (0.0713) loss: 0.8250 (0.8319) time: 0.1569 data: 0.0631 max mem: 9390 +Train: [31] [1700/6250] eta: 0:13:15 lr: 0.000103 grad: 0.0668 (0.0713) loss: 0.8314 (0.8317) time: 0.1590 data: 0.0695 max mem: 9390 +Train: [31] [1800/6250] eta: 0:12:55 lr: 0.000103 grad: 0.0720 (0.0714) loss: 0.8234 (0.8314) time: 0.1537 data: 0.0630 max mem: 9390 +Train: [31] [1900/6250] eta: 0:12:35 lr: 0.000103 grad: 0.0763 (0.0717) loss: 0.8232 (0.8312) time: 0.1742 data: 0.0867 max mem: 9390 +Train: [31] [2000/6250] eta: 0:12:16 lr: 0.000103 grad: 0.0721 (0.0718) loss: 0.8239 (0.8309) time: 0.1685 data: 0.0862 max mem: 9390 +Train: [31] [2100/6250] eta: 0:11:58 lr: 0.000103 grad: 0.0715 (0.0720) loss: 0.8262 (0.8307) time: 0.1698 data: 0.0886 max mem: 9390 +Train: [31] [2200/6250] eta: 0:11:38 lr: 0.000103 grad: 0.0729 (0.0721) loss: 0.8282 (0.8305) time: 0.1719 data: 0.0897 max mem: 9390 +Train: [31] [2300/6250] eta: 0:11:20 lr: 0.000103 grad: 0.0726 (0.0722) loss: 0.8276 (0.8303) time: 0.1648 data: 0.0825 max mem: 9390 +Train: [31] [2400/6250] eta: 0:11:00 lr: 0.000103 grad: 0.0718 (0.0723) loss: 0.8288 (0.8302) time: 0.1566 data: 0.0696 max mem: 9390 +Train: [31] [2500/6250] eta: 0:10:41 lr: 0.000103 grad: 0.0667 (0.0723) loss: 0.8327 (0.8302) time: 0.1580 data: 0.0691 max mem: 9390 +Train: [31] [2600/6250] eta: 0:10:23 lr: 0.000103 grad: 0.0698 (0.0724) loss: 0.8340 (0.8302) time: 0.1709 data: 0.0887 max mem: 9390 +Train: [31] [2700/6250] eta: 0:10:05 lr: 0.000103 grad: 0.0716 (0.0725) loss: 0.8274 (0.8302) time: 0.1627 data: 0.0817 max mem: 9390 +Train: [31] [2800/6250] eta: 0:09:48 lr: 0.000103 grad: 0.0760 (0.0726) loss: 0.8238 (0.8301) time: 0.1552 data: 0.0681 max mem: 9390 +Train: [31] [2900/6250] eta: 0:09:30 lr: 0.000103 grad: 0.0719 (0.0726) loss: 0.8295 (0.8301) time: 0.1658 data: 0.0809 max mem: 9390 +Train: [31] [3000/6250] eta: 0:09:12 lr: 0.000103 grad: 0.0712 (0.0727) loss: 0.8289 (0.8301) time: 0.1515 data: 0.0661 max mem: 9390 +Train: [31] [3100/6250] eta: 0:08:54 lr: 0.000103 grad: 0.0737 (0.0727) loss: 0.8244 (0.8301) time: 0.1681 data: 0.0802 max mem: 9390 +Train: [31] [3200/6250] eta: 0:08:37 lr: 0.000102 grad: 0.0709 (0.0728) loss: 0.8321 (0.8301) time: 0.1813 data: 0.0938 max mem: 9390 +Train: [31] [3300/6250] eta: 0:08:20 lr: 0.000102 grad: 0.0699 (0.0729) loss: 0.8330 (0.8301) time: 0.1701 data: 0.0787 max mem: 9390 +Train: [31] [3400/6250] eta: 0:08:03 lr: 0.000102 grad: 0.0706 (0.0729) loss: 0.8293 (0.8301) time: 0.1748 data: 0.0885 max mem: 9390 +Train: [31] [3500/6250] eta: 0:07:46 lr: 0.000102 grad: 0.0711 (0.0729) loss: 0.8283 (0.8301) time: 0.1867 data: 0.1016 max mem: 9390 +Train: [31] [3600/6250] eta: 0:07:29 lr: 0.000102 grad: 0.0695 (0.0730) loss: 0.8276 (0.8301) time: 0.1415 data: 0.0564 max mem: 9390 +Train: [31] [3700/6250] eta: 0:07:12 lr: 0.000102 grad: 0.0736 (0.0730) loss: 0.8290 (0.8302) time: 0.1696 data: 0.0876 max mem: 9390 +Train: [31] [3800/6250] eta: 0:06:56 lr: 0.000102 grad: 0.0647 (0.0730) loss: 0.8341 (0.8302) time: 0.1762 data: 0.0873 max mem: 9390 +Train: [31] [3900/6250] eta: 0:06:39 lr: 0.000102 grad: 0.0728 (0.0730) loss: 0.8308 (0.8302) time: 0.1726 data: 0.0831 max mem: 9390 +Train: [31] [4000/6250] eta: 0:06:22 lr: 0.000102 grad: 0.0697 (0.0731) loss: 0.8322 (0.8301) time: 0.1966 data: 0.1060 max mem: 9390 +Train: [31] [4100/6250] eta: 0:06:05 lr: 0.000102 grad: 0.0754 (0.0732) loss: 0.8319 (0.8302) time: 0.1845 data: 0.1029 max mem: 9390 +Train: [31] [4200/6250] eta: 0:05:47 lr: 0.000102 grad: 0.0708 (0.0733) loss: 0.8276 (0.8302) time: 0.1604 data: 0.0757 max mem: 9390 +Train: [31] [4300/6250] eta: 0:05:30 lr: 0.000102 grad: 0.0702 (0.0733) loss: 0.8293 (0.8302) time: 0.1968 data: 0.1046 max mem: 9390 +Train: [31] [4400/6250] eta: 0:05:13 lr: 0.000102 grad: 0.0775 (0.0733) loss: 0.8224 (0.8302) time: 0.1716 data: 0.0844 max mem: 9390 +Train: [31] [4500/6250] eta: 0:04:56 lr: 0.000102 grad: 0.0720 (0.0734) loss: 0.8371 (0.8302) time: 0.1746 data: 0.0901 max mem: 9390 +Train: [31] [4600/6250] eta: 0:04:39 lr: 0.000102 grad: 0.0739 (0.0735) loss: 0.8313 (0.8302) time: 0.2097 data: 0.1208 max mem: 9390 +Train: [31] [4700/6250] eta: 0:04:22 lr: 0.000102 grad: 0.0712 (0.0735) loss: 0.8346 (0.8302) time: 0.1620 data: 0.0786 max mem: 9390 +Train: [31] [4800/6250] eta: 0:04:05 lr: 0.000102 grad: 0.0716 (0.0735) loss: 0.8300 (0.8302) time: 0.1742 data: 0.0889 max mem: 9390 +Train: [31] [4900/6250] eta: 0:03:48 lr: 0.000102 grad: 0.0749 (0.0735) loss: 0.8334 (0.8302) time: 0.1645 data: 0.0796 max mem: 9390 +Train: [31] [5000/6250] eta: 0:03:31 lr: 0.000102 grad: 0.0699 (0.0735) loss: 0.8303 (0.8302) time: 0.1628 data: 0.0743 max mem: 9390 +Train: [31] [5100/6250] eta: 0:03:14 lr: 0.000102 grad: 0.0743 (0.0736) loss: 0.8337 (0.8302) time: 0.1590 data: 0.0693 max mem: 9390 +Train: [31] [5200/6250] eta: 0:02:58 lr: 0.000102 grad: 0.0742 (0.0736) loss: 0.8250 (0.8301) time: 0.2203 data: 0.1379 max mem: 9390 +Train: [31] [5300/6250] eta: 0:02:41 lr: 0.000102 grad: 0.0724 (0.0736) loss: 0.8276 (0.8301) time: 0.2020 data: 0.1152 max mem: 9390 +Train: [31] [5400/6250] eta: 0:02:24 lr: 0.000102 grad: 0.0726 (0.0737) loss: 0.8292 (0.8301) time: 0.1656 data: 0.0786 max mem: 9390 +Train: [31] [5500/6250] eta: 0:02:07 lr: 0.000102 grad: 0.0689 (0.0738) loss: 0.8256 (0.8301) time: 0.1883 data: 0.1021 max mem: 9390 +Train: [31] [5600/6250] eta: 0:01:50 lr: 0.000102 grad: 0.0765 (0.0738) loss: 0.8249 (0.8300) time: 0.1388 data: 0.0512 max mem: 9390 +Train: [31] [5700/6250] eta: 0:01:33 lr: 0.000102 grad: 0.0720 (0.0738) loss: 0.8293 (0.8300) time: 0.1703 data: 0.0834 max mem: 9390 +Train: [31] [5800/6250] eta: 0:01:16 lr: 0.000102 grad: 0.0754 (0.0739) loss: 0.8312 (0.8299) time: 0.1436 data: 0.0608 max mem: 9390 +Train: [31] [5900/6250] eta: 0:00:59 lr: 0.000102 grad: 0.0708 (0.0739) loss: 0.8226 (0.8299) time: 0.1512 data: 0.0675 max mem: 9390 +Train: [31] [6000/6250] eta: 0:00:42 lr: 0.000102 grad: 0.0745 (0.0740) loss: 0.8285 (0.8299) time: 0.1902 data: 0.1099 max mem: 9390 +Train: [31] [6100/6250] eta: 0:00:25 lr: 0.000102 grad: 0.0705 (0.0740) loss: 0.8299 (0.8298) time: 0.1611 data: 0.0799 max mem: 9390 +Train: [31] [6200/6250] eta: 0:00:08 lr: 0.000102 grad: 0.0755 (0.0740) loss: 0.8285 (0.8297) time: 0.1533 data: 0.0616 max mem: 9390 +Train: [31] [6249/6250] eta: 0:00:00 lr: 0.000102 grad: 0.0719 (0.0740) loss: 0.8261 (0.8297) time: 0.1744 data: 0.0927 max mem: 9390 +Train: [31] Total time: 0:17:46 (0.1706 s / it) +Averaged stats: lr: 0.000102 grad: 0.0719 (0.0740) loss: 0.8261 (0.8297) +Eval (hcp-train-subset): [31] [ 0/62] eta: 0:06:25 loss: 0.8522 (0.8522) time: 6.2224 data: 6.1810 max mem: 9390 +Eval (hcp-train-subset): [31] [61/62] eta: 0:00:00 loss: 0.8399 (0.8412) time: 0.1101 data: 0.0851 max mem: 9390 +Eval (hcp-train-subset): [31] Total time: 0:00:15 (0.2426 s / it) +Averaged stats (hcp-train-subset): loss: 0.8399 (0.8412) +Eval (hcp-val): [31] [ 0/62] eta: 0:05:32 loss: 0.8365 (0.8365) time: 5.3565 data: 5.3256 max mem: 9390 +Eval (hcp-val): [31] [61/62] eta: 0:00:00 loss: 0.8381 (0.8391) time: 0.1143 data: 0.0894 max mem: 9390 +Eval (hcp-val): [31] Total time: 0:00:13 (0.2185 s / it) +Averaged stats (hcp-val): loss: 0.8381 (0.8391) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +Train: [32] [ 0/6250] eta: 6:38:31 lr: 0.000102 grad: 0.0418 (0.0418) loss: 0.8776 (0.8776) time: 3.8258 data: 3.6379 max mem: 9390 +Train: [32] [ 100/6250] eta: 0:22:35 lr: 0.000102 grad: 0.0708 (0.0860) loss: 0.8330 (0.8367) time: 0.1737 data: 0.0840 max mem: 9390 +Train: [32] [ 200/6250] eta: 0:19:58 lr: 0.000102 grad: 0.0792 (0.0820) loss: 0.8263 (0.8331) time: 0.1917 data: 0.1112 max mem: 9390 +Train: [32] [ 300/6250] eta: 0:18:31 lr: 0.000102 grad: 0.0760 (0.0793) loss: 0.8307 (0.8321) time: 0.1474 data: 0.0566 max mem: 9390 +Train: [32] [ 400/6250] eta: 0:17:45 lr: 0.000102 grad: 0.0708 (0.0776) loss: 0.8321 (0.8328) time: 0.1441 data: 0.0379 max mem: 9390 +Train: [32] [ 500/6250] eta: 0:17:02 lr: 0.000102 grad: 0.0667 (0.0764) loss: 0.8389 (0.8333) time: 0.1555 data: 0.0639 max mem: 9390 +Train: [32] [ 600/6250] eta: 0:16:35 lr: 0.000102 grad: 0.0732 (0.0760) loss: 0.8274 (0.8330) time: 0.1691 data: 0.0676 max mem: 9390 +Train: [32] [ 700/6250] eta: 0:16:16 lr: 0.000102 grad: 0.0684 (0.0760) loss: 0.8348 (0.8328) time: 0.2046 data: 0.1151 max mem: 9390 +Train: [32] [ 800/6250] eta: 0:15:53 lr: 0.000101 grad: 0.0751 (0.0757) loss: 0.8324 (0.8328) time: 0.1622 data: 0.0764 max mem: 9390 +Train: [32] [ 900/6250] eta: 0:15:50 lr: 0.000101 grad: 0.0703 (0.0756) loss: 0.8371 (0.8326) time: 0.2103 data: 0.1228 max mem: 9390 +Train: [32] [1000/6250] eta: 0:15:37 lr: 0.000101 grad: 0.0738 (0.0754) loss: 0.8237 (0.8321) time: 0.1666 data: 0.0820 max mem: 9390 +Train: [32] [1100/6250] eta: 0:15:16 lr: 0.000101 grad: 0.0793 (0.0755) loss: 0.8249 (0.8317) time: 0.1677 data: 0.0864 max mem: 9390 +Train: [32] [1200/6250] eta: 0:14:51 lr: 0.000101 grad: 0.0750 (0.0755) loss: 0.8253 (0.8312) time: 0.1615 data: 0.0721 max mem: 9390 +Train: [32] [1300/6250] eta: 0:14:25 lr: 0.000101 grad: 0.0679 (0.0754) loss: 0.8257 (0.8308) time: 0.1612 data: 0.0709 max mem: 9390 +Train: [32] [1400/6250] eta: 0:14:05 lr: 0.000101 grad: 0.0703 (0.0753) loss: 0.8263 (0.8305) time: 0.1454 data: 0.0579 max mem: 9390 +Train: [32] [1500/6250] eta: 0:13:46 lr: 0.000101 grad: 0.0727 (0.0754) loss: 0.8293 (0.8302) time: 0.1925 data: 0.1076 max mem: 9390 +Train: [32] [1600/6250] eta: 0:13:25 lr: 0.000101 grad: 0.0721 (0.0755) loss: 0.8216 (0.8298) time: 0.1626 data: 0.0751 max mem: 9390 +Train: [32] [1700/6250] eta: 0:13:06 lr: 0.000101 grad: 0.0741 (0.0756) loss: 0.8223 (0.8295) time: 0.1784 data: 0.0918 max mem: 9390 +Train: [32] [1800/6250] eta: 0:12:46 lr: 0.000101 grad: 0.0789 (0.0758) loss: 0.8240 (0.8292) time: 0.1566 data: 0.0724 max mem: 9390 +Train: [32] [1900/6250] eta: 0:12:27 lr: 0.000101 grad: 0.0750 (0.0759) loss: 0.8259 (0.8291) time: 0.1687 data: 0.0837 max mem: 9390 +Train: [32] [2000/6250] eta: 0:12:08 lr: 0.000101 grad: 0.0807 (0.0761) loss: 0.8226 (0.8288) time: 0.1558 data: 0.0743 max mem: 9390 +Train: [32] [2100/6250] eta: 0:11:53 lr: 0.000101 grad: 0.0709 (0.0760) loss: 0.8269 (0.8286) time: 0.1695 data: 0.0756 max mem: 9390 +Train: [32] [2200/6250] eta: 0:11:34 lr: 0.000101 grad: 0.0748 (0.0760) loss: 0.8236 (0.8284) time: 0.1742 data: 0.0845 max mem: 9390 +Train: [32] [2300/6250] eta: 0:11:16 lr: 0.000101 grad: 0.0771 (0.0759) loss: 0.8224 (0.8283) time: 0.1599 data: 0.0633 max mem: 9390 +Train: [32] [2400/6250] eta: 0:11:00 lr: 0.000101 grad: 0.0735 (0.0758) loss: 0.8252 (0.8282) time: 0.1749 data: 0.0889 max mem: 9390 +Train: [32] [2500/6250] eta: 0:10:43 lr: 0.000101 grad: 0.0732 (0.0759) loss: 0.8246 (0.8281) time: 0.1628 data: 0.0799 max mem: 9390 +Train: [32] [2600/6250] eta: 0:10:26 lr: 0.000101 grad: 0.0734 (0.0758) loss: 0.8299 (0.8280) time: 0.1895 data: 0.1098 max mem: 9390 +Train: [32] [2700/6250] eta: 0:10:09 lr: 0.000101 grad: 0.0740 (0.0758) loss: 0.8291 (0.8280) time: 0.2078 data: 0.1233 max mem: 9390 +Train: [32] [2800/6250] eta: 0:09:50 lr: 0.000101 grad: 0.0706 (0.0757) loss: 0.8247 (0.8279) time: 0.1559 data: 0.0716 max mem: 9390 +Train: [32] [2900/6250] eta: 0:09:33 lr: 0.000101 grad: 0.0750 (0.0757) loss: 0.8249 (0.8279) time: 0.1844 data: 0.0980 max mem: 9390 +Train: [32] [3000/6250] eta: 0:09:15 lr: 0.000101 grad: 0.0731 (0.0756) loss: 0.8287 (0.8279) time: 0.1787 data: 0.0959 max mem: 9390 +Train: [32] [3100/6250] eta: 0:08:57 lr: 0.000101 grad: 0.0737 (0.0756) loss: 0.8242 (0.8279) time: 0.1576 data: 0.0773 max mem: 9390 +Train: [32] [3200/6250] eta: 0:08:40 lr: 0.000101 grad: 0.0723 (0.0756) loss: 0.8286 (0.8279) time: 0.1588 data: 0.0754 max mem: 9390 +Train: [32] [3300/6250] eta: 0:08:23 lr: 0.000101 grad: 0.0722 (0.0756) loss: 0.8217 (0.8279) time: 0.1659 data: 0.0823 max mem: 9390 +Train: [32] [3400/6250] eta: 0:08:06 lr: 0.000101 grad: 0.0751 (0.0757) loss: 0.8236 (0.8279) time: 0.1737 data: 0.0833 max mem: 9390 +Train: [32] [3500/6250] eta: 0:07:49 lr: 0.000101 grad: 0.0730 (0.0758) loss: 0.8270 (0.8278) time: 0.1877 data: 0.1012 max mem: 9390 +Train: [32] [3600/6250] eta: 0:07:32 lr: 0.000101 grad: 0.0746 (0.0758) loss: 0.8311 (0.8279) time: 0.1701 data: 0.0876 max mem: 9390 +Train: [32] [3700/6250] eta: 0:07:15 lr: 0.000101 grad: 0.0762 (0.0758) loss: 0.8275 (0.8278) time: 0.1703 data: 0.0934 max mem: 9390 +Train: [32] [3800/6250] eta: 0:06:58 lr: 0.000101 grad: 0.0728 (0.0758) loss: 0.8257 (0.8278) time: 0.1854 data: 0.0984 max mem: 9390 +Train: [32] [3900/6250] eta: 0:06:41 lr: 0.000101 grad: 0.0711 (0.0758) loss: 0.8329 (0.8279) time: 0.1577 data: 0.0703 max mem: 9390 +Train: [32] [4000/6250] eta: 0:06:24 lr: 0.000101 grad: 0.0718 (0.0758) loss: 0.8339 (0.8279) time: 0.1858 data: 0.1036 max mem: 9390 +Train: [32] [4100/6250] eta: 0:06:07 lr: 0.000101 grad: 0.0682 (0.0758) loss: 0.8304 (0.8280) time: 0.1517 data: 0.0657 max mem: 9390 +Train: [32] [4200/6250] eta: 0:05:50 lr: 0.000101 grad: 0.0758 (0.0758) loss: 0.8270 (0.8279) time: 0.1602 data: 0.0729 max mem: 9390 +Train: [32] [4300/6250] eta: 0:05:32 lr: 0.000101 grad: 0.0703 (0.0758) loss: 0.8281 (0.8279) time: 0.1534 data: 0.0598 max mem: 9390 +Train: [32] [4400/6250] eta: 0:05:15 lr: 0.000101 grad: 0.0729 (0.0758) loss: 0.8299 (0.8279) time: 0.1837 data: 0.0965 max mem: 9390 +Train: [32] [4500/6250] eta: 0:04:58 lr: 0.000101 grad: 0.0694 (0.0758) loss: 0.8297 (0.8279) time: 0.1495 data: 0.0616 max mem: 9390 +Train: [32] [4600/6250] eta: 0:04:41 lr: 0.000101 grad: 0.0667 (0.0758) loss: 0.8342 (0.8279) time: 0.1828 data: 0.1024 max mem: 9390 +Train: [32] [4700/6250] eta: 0:04:24 lr: 0.000100 grad: 0.0722 (0.0758) loss: 0.8321 (0.8280) time: 0.1568 data: 0.0712 max mem: 9390 +Train: [32] [4800/6250] eta: 0:04:07 lr: 0.000100 grad: 0.0741 (0.0758) loss: 0.8302 (0.8280) time: 0.1743 data: 0.0858 max mem: 9390 +Train: [32] [4900/6250] eta: 0:03:50 lr: 0.000100 grad: 0.0702 (0.0758) loss: 0.8302 (0.8280) time: 0.2088 data: 0.1284 max mem: 9390 +Train: [32] [5000/6250] eta: 0:03:33 lr: 0.000100 grad: 0.0761 (0.0758) loss: 0.8293 (0.8280) time: 0.1690 data: 0.0918 max mem: 9390 +Train: [32] [5100/6250] eta: 0:03:16 lr: 0.000100 grad: 0.0743 (0.0758) loss: 0.8328 (0.8280) time: 0.1736 data: 0.0915 max mem: 9390 +Train: [32] [5200/6250] eta: 0:02:59 lr: 0.000100 grad: 0.0703 (0.0758) loss: 0.8313 (0.8280) time: 0.1895 data: 0.1141 max mem: 9390 +Train: [32] [5300/6250] eta: 0:02:42 lr: 0.000100 grad: 0.0743 (0.0758) loss: 0.8296 (0.8281) time: 0.2003 data: 0.1168 max mem: 9390 +Train: [32] [5400/6250] eta: 0:02:25 lr: 0.000100 grad: 0.0703 (0.0758) loss: 0.8244 (0.8281) time: 0.1600 data: 0.0712 max mem: 9390 +Train: [32] [5500/6250] eta: 0:02:08 lr: 0.000100 grad: 0.0763 (0.0758) loss: 0.8234 (0.8281) time: 0.1556 data: 0.0707 max mem: 9390 +Train: [32] [5600/6250] eta: 0:01:50 lr: 0.000100 grad: 0.0706 (0.0758) loss: 0.8285 (0.8281) time: 0.1917 data: 0.0950 max mem: 9390 +Train: [32] [5700/6250] eta: 0:01:33 lr: 0.000100 grad: 0.0734 (0.0758) loss: 0.8278 (0.8281) time: 0.1739 data: 0.0817 max mem: 9390 +Train: [32] [5800/6250] eta: 0:01:16 lr: 0.000100 grad: 0.0705 (0.0758) loss: 0.8306 (0.8281) time: 0.1742 data: 0.0731 max mem: 9390 +Train: [32] [5900/6250] eta: 0:00:59 lr: 0.000100 grad: 0.0701 (0.0757) loss: 0.8261 (0.8281) time: 0.1555 data: 0.0667 max mem: 9390 +Train: [32] [6000/6250] eta: 0:00:42 lr: 0.000100 grad: 0.0707 (0.0757) loss: 0.8363 (0.8281) time: 0.1765 data: 0.0856 max mem: 9390 +Train: [32] [6100/6250] eta: 0:00:25 lr: 0.000100 grad: 0.0726 (0.0757) loss: 0.8274 (0.8282) time: 0.1565 data: 0.0557 max mem: 9390 +Train: [32] [6200/6250] eta: 0:00:08 lr: 0.000100 grad: 0.0724 (0.0757) loss: 0.8269 (0.8282) time: 0.1652 data: 0.0700 max mem: 9390 +Train: [32] [6249/6250] eta: 0:00:00 lr: 0.000100 grad: 0.0709 (0.0756) loss: 0.8328 (0.8282) time: 0.1610 data: 0.0662 max mem: 9390 +Train: [32] Total time: 0:17:46 (0.1707 s / it) +Averaged stats: lr: 0.000100 grad: 0.0709 (0.0756) loss: 0.8328 (0.8282) +Eval (hcp-train-subset): [32] [ 0/62] eta: 0:04:57 loss: 0.8528 (0.8528) time: 4.8003 data: 4.7669 max mem: 9390 +Eval (hcp-train-subset): [32] [61/62] eta: 0:00:00 loss: 0.8409 (0.8420) time: 0.1302 data: 0.1045 max mem: 9390 +Eval (hcp-train-subset): [32] Total time: 0:00:14 (0.2345 s / it) +Averaged stats (hcp-train-subset): loss: 0.8409 (0.8420) +Eval (hcp-val): [32] [ 0/62] eta: 0:03:41 loss: 0.8337 (0.8337) time: 3.5719 data: 3.4821 max mem: 9390 +Eval (hcp-val): [32] [61/62] eta: 0:00:00 loss: 0.8382 (0.8387) time: 0.1240 data: 0.0967 max mem: 9390 +Eval (hcp-val): [32] Total time: 0:00:13 (0.2211 s / it) +Averaged stats (hcp-val): loss: 0.8382 (0.8387) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +Train: [33] [ 0/6250] eta: 9:09:58 lr: 0.000100 grad: 0.0990 (0.0990) loss: 0.8763 (0.8763) time: 5.2798 data: 5.1309 max mem: 9390 +Train: [33] [ 100/6250] eta: 0:22:24 lr: 0.000100 grad: 0.0699 (0.0786) loss: 0.8354 (0.8330) time: 0.1729 data: 0.0751 max mem: 9390 +Train: [33] [ 200/6250] eta: 0:19:53 lr: 0.000100 grad: 0.0711 (0.0751) loss: 0.8362 (0.8343) time: 0.1982 data: 0.0984 max mem: 9390 +Train: [33] [ 300/6250] eta: 0:18:23 lr: 0.000100 grad: 0.0656 (0.0742) loss: 0.8307 (0.8337) time: 0.1564 data: 0.0533 max mem: 9390 +Train: [33] [ 400/6250] eta: 0:17:44 lr: 0.000100 grad: 0.0768 (0.0741) loss: 0.8257 (0.8330) time: 0.1468 data: 0.0413 max mem: 9390 +Train: [33] [ 500/6250] eta: 0:17:28 lr: 0.000100 grad: 0.0732 (0.0752) loss: 0.8307 (0.8314) time: 0.1763 data: 0.0878 max mem: 9390 +Train: [33] [ 600/6250] eta: 0:17:12 lr: 0.000100 grad: 0.0714 (0.0752) loss: 0.8197 (0.8310) time: 0.1651 data: 0.0767 max mem: 9390 +Train: [33] [ 700/6250] eta: 0:16:48 lr: 0.000100 grad: 0.0702 (0.0748) loss: 0.8286 (0.8310) time: 0.1727 data: 0.0757 max mem: 9390 +Train: [33] [ 800/6250] eta: 0:16:32 lr: 0.000100 grad: 0.0740 (0.0745) loss: 0.8280 (0.8307) time: 0.1870 data: 0.0994 max mem: 9390 +Train: [33] [ 900/6250] eta: 0:16:12 lr: 0.000100 grad: 0.0714 (0.0745) loss: 0.8281 (0.8304) time: 0.1869 data: 0.1027 max mem: 9390 +Train: [33] [1000/6250] eta: 0:15:46 lr: 0.000100 grad: 0.0680 (0.0742) loss: 0.8328 (0.8303) time: 0.1814 data: 0.0957 max mem: 9390 +Train: [33] [1100/6250] eta: 0:15:32 lr: 0.000100 grad: 0.0698 (0.0739) loss: 0.8253 (0.8301) time: 0.2030 data: 0.1251 max mem: 9390 +Train: [33] [1200/6250] eta: 0:15:10 lr: 0.000100 grad: 0.0705 (0.0737) loss: 0.8297 (0.8300) time: 0.1589 data: 0.0770 max mem: 9390 +Train: [33] [1300/6250] eta: 0:14:47 lr: 0.000100 grad: 0.0708 (0.0734) loss: 0.8271 (0.8299) time: 0.1593 data: 0.0796 max mem: 9390 +Train: [33] [1400/6250] eta: 0:14:21 lr: 0.000100 grad: 0.0688 (0.0733) loss: 0.8316 (0.8299) time: 0.1532 data: 0.0648 max mem: 9390 +Train: [33] [1500/6250] eta: 0:13:59 lr: 0.000100 grad: 0.0703 (0.0732) loss: 0.8241 (0.8299) time: 0.1687 data: 0.0835 max mem: 9390 +Train: [33] [1600/6250] eta: 0:13:37 lr: 0.000100 grad: 0.0708 (0.0731) loss: 0.8310 (0.8299) time: 0.1892 data: 0.1016 max mem: 9390 +Train: [33] [1700/6250] eta: 0:13:15 lr: 0.000100 grad: 0.0701 (0.0732) loss: 0.8263 (0.8298) time: 0.1438 data: 0.0565 max mem: 9390 +Train: [33] [1800/6250] eta: 0:12:57 lr: 0.000100 grad: 0.0685 (0.0732) loss: 0.8302 (0.8299) time: 0.1685 data: 0.0814 max mem: 9390 +Train: [33] [1900/6250] eta: 0:12:38 lr: 0.000100 grad: 0.0740 (0.0733) loss: 0.8304 (0.8299) time: 0.1857 data: 0.1005 max mem: 9390 +Train: [33] [2000/6250] eta: 0:12:19 lr: 0.000100 grad: 0.0722 (0.0734) loss: 0.8298 (0.8298) time: 0.1716 data: 0.0867 max mem: 9390 +Train: [33] [2100/6250] eta: 0:12:01 lr: 0.000100 grad: 0.0720 (0.0734) loss: 0.8212 (0.8297) time: 0.1772 data: 0.0905 max mem: 9390 +Train: [33] [2200/6250] eta: 0:11:42 lr: 0.000099 grad: 0.0741 (0.0736) loss: 0.8287 (0.8297) time: 0.1812 data: 0.0961 max mem: 9390 +Train: [33] [2300/6250] eta: 0:11:23 lr: 0.000099 grad: 0.0777 (0.0737) loss: 0.8251 (0.8296) time: 0.1679 data: 0.0813 max mem: 9390 +Train: [33] [2400/6250] eta: 0:11:06 lr: 0.000099 grad: 0.0721 (0.0737) loss: 0.8319 (0.8297) time: 0.1845 data: 0.1003 max mem: 9390 +Train: [33] [2500/6250] eta: 0:10:47 lr: 0.000099 grad: 0.0708 (0.0737) loss: 0.8325 (0.8297) time: 0.1772 data: 0.0898 max mem: 9390 +Train: [33] [2600/6250] eta: 0:10:28 lr: 0.000099 grad: 0.0722 (0.0738) loss: 0.8276 (0.8297) time: 0.1667 data: 0.0752 max mem: 9390 +Train: [33] [2700/6250] eta: 0:10:09 lr: 0.000099 grad: 0.0746 (0.0738) loss: 0.8259 (0.8297) time: 0.1529 data: 0.0726 max mem: 9390 +Train: [33] [2800/6250] eta: 0:09:52 lr: 0.000099 grad: 0.0709 (0.0739) loss: 0.8342 (0.8297) time: 0.1906 data: 0.1050 max mem: 9390 +Train: [33] [2900/6250] eta: 0:09:33 lr: 0.000099 grad: 0.0768 (0.0742) loss: 0.8321 (0.8297) time: 0.1620 data: 0.0758 max mem: 9390 +Train: [33] [3000/6250] eta: 0:09:16 lr: 0.000099 grad: 0.0702 (0.0742) loss: 0.8330 (0.8298) time: 0.1438 data: 0.0502 max mem: 9390 +Train: [33] [3100/6250] eta: 0:08:59 lr: 0.000099 grad: 0.0711 (0.0742) loss: 0.8341 (0.8298) time: 0.1893 data: 0.1089 max mem: 9390 +Train: [33] [3200/6250] eta: 0:08:41 lr: 0.000099 grad: 0.0693 (0.0742) loss: 0.8235 (0.8298) time: 0.1749 data: 0.0934 max mem: 9390 +Train: [33] [3300/6250] eta: 0:08:24 lr: 0.000099 grad: 0.0724 (0.0743) loss: 0.8313 (0.8298) time: 0.1698 data: 0.0777 max mem: 9390 +Train: [33] [3400/6250] eta: 0:08:06 lr: 0.000099 grad: 0.0782 (0.0743) loss: 0.8322 (0.8299) time: 0.1581 data: 0.0685 max mem: 9390 +Train: [33] [3500/6250] eta: 0:07:49 lr: 0.000099 grad: 0.0714 (0.0743) loss: 0.8342 (0.8300) time: 0.1738 data: 0.0822 max mem: 9390 +Train: [33] [3600/6250] eta: 0:07:32 lr: 0.000099 grad: 0.0734 (0.0744) loss: 0.8312 (0.8300) time: 0.1547 data: 0.0628 max mem: 9390 +Train: [33] [3700/6250] eta: 0:07:15 lr: 0.000099 grad: 0.0719 (0.0744) loss: 0.8297 (0.8301) time: 0.1874 data: 0.1011 max mem: 9390 +Train: [33] [3800/6250] eta: 0:06:57 lr: 0.000099 grad: 0.0700 (0.0744) loss: 0.8315 (0.8301) time: 0.1784 data: 0.0949 max mem: 9390 +Train: [33] [3900/6250] eta: 0:06:40 lr: 0.000099 grad: 0.0761 (0.0744) loss: 0.8312 (0.8301) time: 0.1744 data: 0.0877 max mem: 9390 +Train: [33] [4000/6250] eta: 0:06:23 lr: 0.000099 grad: 0.0723 (0.0745) loss: 0.8298 (0.8301) time: 0.1422 data: 0.0553 max mem: 9390 +Train: [33] [4100/6250] eta: 0:06:06 lr: 0.000099 grad: 0.0820 (0.0746) loss: 0.8202 (0.8301) time: 0.1670 data: 0.0804 max mem: 9390 +Train: [33] [4200/6250] eta: 0:05:49 lr: 0.000099 grad: 0.0743 (0.0747) loss: 0.8262 (0.8300) time: 0.1850 data: 0.0987 max mem: 9390 +Train: [33] [4300/6250] eta: 0:05:32 lr: 0.000099 grad: 0.0702 (0.0747) loss: 0.8283 (0.8299) time: 0.1661 data: 0.0742 max mem: 9390 +Train: [33] [4400/6250] eta: 0:05:15 lr: 0.000099 grad: 0.0757 (0.0748) loss: 0.8317 (0.8298) time: 0.1839 data: 0.1036 max mem: 9390 +Train: [33] [4500/6250] eta: 0:04:57 lr: 0.000099 grad: 0.0775 (0.0748) loss: 0.8318 (0.8298) time: 0.1838 data: 0.1032 max mem: 9390 +Train: [33] [4600/6250] eta: 0:04:40 lr: 0.000099 grad: 0.0734 (0.0749) loss: 0.8249 (0.8297) time: 0.1554 data: 0.0687 max mem: 9390 +Train: [33] [4700/6250] eta: 0:04:23 lr: 0.000099 grad: 0.0810 (0.0750) loss: 0.8253 (0.8296) time: 0.1354 data: 0.0517 max mem: 9390 +Train: [33] [4800/6250] eta: 0:04:06 lr: 0.000099 grad: 0.0742 (0.0752) loss: 0.8310 (0.8296) time: 0.1757 data: 0.0926 max mem: 9390 +Train: [33] [4900/6250] eta: 0:03:49 lr: 0.000099 grad: 0.0775 (0.0753) loss: 0.8310 (0.8296) time: 0.1588 data: 0.0701 max mem: 9390 +Train: [33] [5000/6250] eta: 0:03:32 lr: 0.000099 grad: 0.0737 (0.0753) loss: 0.8334 (0.8296) time: 0.1821 data: 0.0947 max mem: 9390 +Train: [33] [5100/6250] eta: 0:03:15 lr: 0.000099 grad: 0.0738 (0.0753) loss: 0.8266 (0.8295) time: 0.1553 data: 0.0668 max mem: 9390 +Train: [33] [5200/6250] eta: 0:02:58 lr: 0.000099 grad: 0.0716 (0.0754) loss: 0.8281 (0.8295) time: 0.1644 data: 0.0774 max mem: 9390 +Train: [33] [5300/6250] eta: 0:02:41 lr: 0.000099 grad: 0.0725 (0.0754) loss: 0.8325 (0.8295) time: 0.1591 data: 0.0740 max mem: 9390 +Train: [33] [5400/6250] eta: 0:02:24 lr: 0.000099 grad: 0.0775 (0.0754) loss: 0.8359 (0.8296) time: 0.1673 data: 0.0758 max mem: 9390 +Train: [33] [5500/6250] eta: 0:02:07 lr: 0.000099 grad: 0.0698 (0.0753) loss: 0.8329 (0.8296) time: 0.1466 data: 0.0551 max mem: 9390 +Train: [33] [5600/6250] eta: 0:01:50 lr: 0.000099 grad: 0.0761 (0.0753) loss: 0.8285 (0.8296) time: 0.1829 data: 0.0960 max mem: 9390 +Train: [33] [5700/6250] eta: 0:01:33 lr: 0.000099 grad: 0.0711 (0.0753) loss: 0.8359 (0.8297) time: 0.2010 data: 0.1209 max mem: 9390 +Train: [33] [5800/6250] eta: 0:01:16 lr: 0.000099 grad: 0.0688 (0.0754) loss: 0.8321 (0.8297) time: 0.2043 data: 0.1217 max mem: 9390 +Train: [33] [5900/6250] eta: 0:00:59 lr: 0.000098 grad: 0.0717 (0.0754) loss: 0.8338 (0.8297) time: 0.1823 data: 0.0964 max mem: 9390 +Train: [33] [6000/6250] eta: 0:00:42 lr: 0.000098 grad: 0.0796 (0.0754) loss: 0.8252 (0.8297) time: 0.1436 data: 0.0557 max mem: 9390 +Train: [33] [6100/6250] eta: 0:00:25 lr: 0.000098 grad: 0.0718 (0.0755) loss: 0.8336 (0.8297) time: 0.1491 data: 0.0627 max mem: 9390 +Train: [33] [6200/6250] eta: 0:00:08 lr: 0.000098 grad: 0.0703 (0.0755) loss: 0.8356 (0.8297) time: 0.1703 data: 0.0851 max mem: 9390 +Train: [33] [6249/6250] eta: 0:00:00 lr: 0.000098 grad: 0.0793 (0.0755) loss: 0.8319 (0.8297) time: 0.1601 data: 0.0696 max mem: 9390 +Train: [33] Total time: 0:17:48 (0.1710 s / it) +Averaged stats: lr: 0.000098 grad: 0.0793 (0.0755) loss: 0.8319 (0.8297) +Eval (hcp-train-subset): [33] [ 0/62] eta: 0:05:38 loss: 0.8518 (0.8518) time: 5.4569 data: 5.3889 max mem: 9390 +Eval (hcp-train-subset): [33] [61/62] eta: 0:00:00 loss: 0.8409 (0.8419) time: 0.1316 data: 0.1063 max mem: 9390 +Eval (hcp-train-subset): [33] Total time: 0:00:14 (0.2304 s / it) +Averaged stats (hcp-train-subset): loss: 0.8409 (0.8419) +Eval (hcp-val): [33] [ 0/62] eta: 0:05:04 loss: 0.8380 (0.8380) time: 4.9072 data: 4.8535 max mem: 9390 +Eval (hcp-val): [33] [61/62] eta: 0:00:00 loss: 0.8386 (0.8397) time: 0.1488 data: 0.1230 max mem: 9390 +Eval (hcp-val): [33] Total time: 0:00:14 (0.2303 s / it) +Averaged stats (hcp-val): loss: 0.8386 (0.8397) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +Train: [34] [ 0/6250] eta: 6:56:55 lr: 0.000098 grad: 0.0684 (0.0684) loss: 0.8550 (0.8550) time: 4.0025 data: 3.7261 max mem: 9390 +Train: [34] [ 100/6250] eta: 0:23:21 lr: 0.000098 grad: 0.0735 (0.0830) loss: 0.8360 (0.8325) time: 0.1948 data: 0.0991 max mem: 9390 +Train: [34] [ 200/6250] eta: 0:20:44 lr: 0.000098 grad: 0.0683 (0.0821) loss: 0.8320 (0.8296) time: 0.2128 data: 0.1255 max mem: 9390 +Train: [34] [ 300/6250] eta: 0:19:00 lr: 0.000098 grad: 0.0686 (0.0804) loss: 0.8277 (0.8287) time: 0.1419 data: 0.0413 max mem: 9390 +Train: [34] [ 400/6250] eta: 0:18:05 lr: 0.000098 grad: 0.0700 (0.0784) loss: 0.8302 (0.8293) time: 0.1668 data: 0.0750 max mem: 9390 +Train: [34] [ 500/6250] eta: 0:17:26 lr: 0.000098 grad: 0.0700 (0.0771) loss: 0.8234 (0.8292) time: 0.1911 data: 0.0944 max mem: 9390 +Train: [34] [ 600/6250] eta: 0:16:48 lr: 0.000098 grad: 0.0735 (0.0763) loss: 0.8227 (0.8289) time: 0.1586 data: 0.0611 max mem: 9390 +Train: [34] [ 700/6250] eta: 0:16:27 lr: 0.000098 grad: 0.0664 (0.0755) loss: 0.8302 (0.8291) time: 0.1503 data: 0.0625 max mem: 9390 +Train: [34] [ 800/6250] eta: 0:16:12 lr: 0.000098 grad: 0.0684 (0.0749) loss: 0.8291 (0.8294) time: 0.1773 data: 0.0851 max mem: 9390 +Train: [34] [ 900/6250] eta: 0:15:56 lr: 0.000098 grad: 0.0649 (0.0742) loss: 0.8324 (0.8300) time: 0.1828 data: 0.0981 max mem: 9390 +Train: [34] [1000/6250] eta: 0:15:29 lr: 0.000098 grad: 0.0651 (0.0737) loss: 0.8334 (0.8302) time: 0.1535 data: 0.0628 max mem: 9390 +Train: [34] [1100/6250] eta: 0:15:16 lr: 0.000098 grad: 0.0679 (0.0733) loss: 0.8346 (0.8305) time: 0.1112 data: 0.0003 max mem: 9390 +Train: [34] [1200/6250] eta: 0:14:52 lr: 0.000098 grad: 0.0668 (0.0730) loss: 0.8315 (0.8305) time: 0.1824 data: 0.0943 max mem: 9390 +Train: [34] [1300/6250] eta: 0:14:32 lr: 0.000098 grad: 0.0639 (0.0730) loss: 0.8317 (0.8303) time: 0.1682 data: 0.0957 max mem: 9390 +Train: [34] [1400/6250] eta: 0:14:13 lr: 0.000098 grad: 0.0671 (0.0729) loss: 0.8327 (0.8304) time: 0.1616 data: 0.0726 max mem: 9390 +Train: [34] [1500/6250] eta: 0:13:51 lr: 0.000098 grad: 0.0727 (0.0728) loss: 0.8234 (0.8303) time: 0.1454 data: 0.0618 max mem: 9390 +Train: [34] [1600/6250] eta: 0:13:32 lr: 0.000098 grad: 0.0692 (0.0728) loss: 0.8300 (0.8302) time: 0.1716 data: 0.0841 max mem: 9390 +Train: [34] [1700/6250] eta: 0:13:15 lr: 0.000098 grad: 0.0700 (0.0727) loss: 0.8313 (0.8302) time: 0.1689 data: 0.0832 max mem: 9390 +Train: [34] [1800/6250] eta: 0:12:54 lr: 0.000098 grad: 0.0713 (0.0729) loss: 0.8257 (0.8301) time: 0.1722 data: 0.0920 max mem: 9390 +Train: [34] [1900/6250] eta: 0:12:34 lr: 0.000098 grad: 0.0754 (0.0731) loss: 0.8298 (0.8300) time: 0.1680 data: 0.0826 max mem: 9390 +Train: [34] [2000/6250] eta: 0:12:17 lr: 0.000098 grad: 0.0721 (0.0732) loss: 0.8317 (0.8299) time: 0.1683 data: 0.0858 max mem: 9390 +Train: [34] [2100/6250] eta: 0:12:00 lr: 0.000098 grad: 0.0736 (0.0733) loss: 0.8294 (0.8299) time: 0.1529 data: 0.0636 max mem: 9390 +Train: [34] [2200/6250] eta: 0:11:43 lr: 0.000098 grad: 0.0696 (0.0734) loss: 0.8275 (0.8298) time: 0.1774 data: 0.0928 max mem: 9390 +Train: [34] [2300/6250] eta: 0:11:26 lr: 0.000098 grad: 0.0722 (0.0734) loss: 0.8238 (0.8297) time: 0.1734 data: 0.0921 max mem: 9390 +Train: [34] [2400/6250] eta: 0:11:07 lr: 0.000098 grad: 0.0707 (0.0734) loss: 0.8296 (0.8297) time: 0.1409 data: 0.0566 max mem: 9390 +Train: [34] [2500/6250] eta: 0:10:50 lr: 0.000098 grad: 0.0713 (0.0735) loss: 0.8245 (0.8297) time: 0.1931 data: 0.1127 max mem: 9390 +Train: [34] [2600/6250] eta: 0:10:31 lr: 0.000098 grad: 0.0736 (0.0736) loss: 0.8288 (0.8297) time: 0.1262 data: 0.0409 max mem: 9390 +Train: [34] [2700/6250] eta: 0:10:14 lr: 0.000098 grad: 0.0734 (0.0737) loss: 0.8205 (0.8296) time: 0.1901 data: 0.1038 max mem: 9390 +Train: [34] [2800/6250] eta: 0:09:55 lr: 0.000098 grad: 0.0697 (0.0736) loss: 0.8345 (0.8297) time: 0.1568 data: 0.0707 max mem: 9390 +Train: [34] [2900/6250] eta: 0:09:37 lr: 0.000098 grad: 0.0756 (0.0737) loss: 0.8287 (0.8298) time: 0.1681 data: 0.0910 max mem: 9390 +Train: [34] [3000/6250] eta: 0:09:20 lr: 0.000098 grad: 0.0745 (0.0737) loss: 0.8314 (0.8298) time: 0.1516 data: 0.0612 max mem: 9390 +Train: [34] [3100/6250] eta: 0:09:02 lr: 0.000098 grad: 0.0698 (0.0738) loss: 0.8264 (0.8298) time: 0.1489 data: 0.0627 max mem: 9390 +Train: [34] [3200/6250] eta: 0:08:46 lr: 0.000098 grad: 0.0685 (0.0737) loss: 0.8338 (0.8299) time: 0.1705 data: 0.0859 max mem: 9390 +Train: [34] [3300/6250] eta: 0:08:29 lr: 0.000097 grad: 0.0752 (0.0738) loss: 0.8262 (0.8299) time: 0.2144 data: 0.1285 max mem: 9390 +Train: [34] [3400/6250] eta: 0:08:11 lr: 0.000097 grad: 0.0698 (0.0738) loss: 0.8296 (0.8299) time: 0.1700 data: 0.0865 max mem: 9390 +Train: [34] [3500/6250] eta: 0:07:53 lr: 0.000097 grad: 0.0762 (0.0738) loss: 0.8286 (0.8299) time: 0.1683 data: 0.0820 max mem: 9390 +Train: [34] [3600/6250] eta: 0:07:36 lr: 0.000097 grad: 0.0685 (0.0738) loss: 0.8307 (0.8299) time: 0.1485 data: 0.0590 max mem: 9390 +Train: [34] [3700/6250] eta: 0:07:21 lr: 0.000097 grad: 0.0721 (0.0738) loss: 0.8285 (0.8298) time: 0.1832 data: 0.0988 max mem: 9390 +Train: [34] [3800/6250] eta: 0:07:04 lr: 0.000097 grad: 0.0708 (0.0738) loss: 0.8278 (0.8298) time: 0.1831 data: 0.0983 max mem: 9390 +Train: [34] [3900/6250] eta: 0:06:47 lr: 0.000097 grad: 0.0732 (0.0739) loss: 0.8320 (0.8298) time: 0.1855 data: 0.1066 max mem: 9390 +Train: [34] [4000/6250] eta: 0:06:30 lr: 0.000097 grad: 0.0756 (0.0740) loss: 0.8267 (0.8298) time: 0.1910 data: 0.0959 max mem: 9390 +Train: [34] [4100/6250] eta: 0:06:13 lr: 0.000097 grad: 0.0758 (0.0741) loss: 0.8275 (0.8297) time: 0.1996 data: 0.1101 max mem: 9390 +Train: [34] [4200/6250] eta: 0:05:55 lr: 0.000097 grad: 0.0737 (0.0742) loss: 0.8331 (0.8297) time: 0.1502 data: 0.0626 max mem: 9390 +Train: [34] [4300/6250] eta: 0:05:38 lr: 0.000097 grad: 0.0754 (0.0742) loss: 0.8243 (0.8296) time: 0.1608 data: 0.0774 max mem: 9390 +Train: [34] [4400/6250] eta: 0:05:20 lr: 0.000097 grad: 0.0744 (0.0743) loss: 0.8245 (0.8295) time: 0.1592 data: 0.0743 max mem: 9390 +Train: [34] [4500/6250] eta: 0:05:02 lr: 0.000097 grad: 0.0773 (0.0744) loss: 0.8184 (0.8294) time: 0.1490 data: 0.0557 max mem: 9390 +Train: [34] [4600/6250] eta: 0:04:45 lr: 0.000097 grad: 0.0739 (0.0745) loss: 0.8341 (0.8293) time: 0.1333 data: 0.0383 max mem: 9390 +Train: [34] [4700/6250] eta: 0:04:27 lr: 0.000097 grad: 0.0761 (0.0746) loss: 0.8286 (0.8292) time: 0.1540 data: 0.0560 max mem: 9390 +Train: [34] [4800/6250] eta: 0:04:09 lr: 0.000097 grad: 0.0702 (0.0746) loss: 0.8263 (0.8291) time: 0.1657 data: 0.0707 max mem: 9390 +Train: [34] [4900/6250] eta: 0:03:52 lr: 0.000097 grad: 0.0769 (0.0747) loss: 0.8264 (0.8290) time: 0.1394 data: 0.0447 max mem: 9390 +Train: [34] [5000/6250] eta: 0:03:34 lr: 0.000097 grad: 0.0793 (0.0748) loss: 0.8224 (0.8289) time: 0.1585 data: 0.0714 max mem: 9390 +Train: [34] [5100/6250] eta: 0:03:17 lr: 0.000097 grad: 0.0748 (0.0749) loss: 0.8243 (0.8288) time: 0.1496 data: 0.0576 max mem: 9390 +Train: [34] [5200/6250] eta: 0:02:59 lr: 0.000097 grad: 0.0783 (0.0749) loss: 0.8255 (0.8287) time: 0.1472 data: 0.0567 max mem: 9390 +Train: [34] [5300/6250] eta: 0:02:42 lr: 0.000097 grad: 0.0694 (0.0749) loss: 0.8288 (0.8286) time: 0.1699 data: 0.0815 max mem: 9390 +Train: [34] [5400/6250] eta: 0:02:25 lr: 0.000097 grad: 0.0745 (0.0749) loss: 0.8250 (0.8286) time: 0.1435 data: 0.0512 max mem: 9390 +Train: [34] [5500/6250] eta: 0:02:08 lr: 0.000097 grad: 0.0731 (0.0749) loss: 0.8296 (0.8287) time: 0.1457 data: 0.0526 max mem: 9390 +Train: [34] [5600/6250] eta: 0:01:51 lr: 0.000097 grad: 0.0692 (0.0749) loss: 0.8312 (0.8287) time: 0.2047 data: 0.1241 max mem: 9390 +Train: [34] [5700/6250] eta: 0:01:34 lr: 0.000097 grad: 0.0744 (0.0750) loss: 0.8266 (0.8286) time: 0.1764 data: 0.0944 max mem: 9390 +Train: [34] [5800/6250] eta: 0:01:17 lr: 0.000097 grad: 0.0777 (0.0750) loss: 0.8296 (0.8286) time: 0.1632 data: 0.0755 max mem: 9390 +Train: [34] [5900/6250] eta: 0:00:59 lr: 0.000097 grad: 0.0729 (0.0750) loss: 0.8262 (0.8286) time: 0.1849 data: 0.0977 max mem: 9390 +Train: [34] [6000/6250] eta: 0:00:42 lr: 0.000097 grad: 0.0753 (0.0750) loss: 0.8316 (0.8286) time: 0.1699 data: 0.0830 max mem: 9390 +Train: [34] [6100/6250] eta: 0:00:25 lr: 0.000097 grad: 0.0748 (0.0752) loss: 0.8333 (0.8286) time: 0.1596 data: 0.0722 max mem: 9390 +Train: [34] [6200/6250] eta: 0:00:08 lr: 0.000097 grad: 0.0714 (0.0753) loss: 0.8257 (0.8285) time: 0.1663 data: 0.0842 max mem: 9390 +Train: [34] [6249/6250] eta: 0:00:00 lr: 0.000097 grad: 0.0748 (0.0753) loss: 0.8316 (0.8285) time: 0.1297 data: 0.0313 max mem: 9390 +Train: [34] Total time: 0:17:54 (0.1720 s / it) +Averaged stats: lr: 0.000097 grad: 0.0748 (0.0753) loss: 0.8316 (0.8285) +Eval (hcp-train-subset): [34] [ 0/62] eta: 0:05:52 loss: 0.8519 (0.8519) time: 5.6863 data: 5.6567 max mem: 9390 +Eval (hcp-train-subset): [34] [61/62] eta: 0:00:00 loss: 0.8394 (0.8414) time: 0.1391 data: 0.1132 max mem: 9390 +Eval (hcp-train-subset): [34] Total time: 0:00:14 (0.2413 s / it) +Averaged stats (hcp-train-subset): loss: 0.8394 (0.8414) +Making plots (hcp-train-subset): example=40 +Eval (hcp-val): [34] [ 0/62] eta: 0:04:44 loss: 0.8334 (0.8334) time: 4.5831 data: 4.5157 max mem: 9390 +Eval (hcp-val): [34] [61/62] eta: 0:00:00 loss: 0.8384 (0.8386) time: 0.1469 data: 0.1212 max mem: 9390 +Eval (hcp-val): [34] Total time: 0:00:15 (0.2502 s / it) +Averaged stats (hcp-val): loss: 0.8384 (0.8386) +Making plots (hcp-val): example=40 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +Train: [35] [ 0/6250] eta: 12:22:54 lr: 0.000097 grad: 0.0606 (0.0606) loss: 0.8516 (0.8516) time: 7.1319 data: 7.0132 max mem: 9390 +Train: [35] [ 100/6250] eta: 0:26:27 lr: 0.000097 grad: 0.0778 (0.0808) loss: 0.8330 (0.8416) time: 0.2282 data: 0.1241 max mem: 9390 +Train: [35] [ 200/6250] eta: 0:22:09 lr: 0.000097 grad: 0.0715 (0.0791) loss: 0.8344 (0.8372) time: 0.1883 data: 0.0952 max mem: 9390 +Train: [35] [ 300/6250] eta: 0:20:20 lr: 0.000097 grad: 0.0704 (0.0779) loss: 0.8382 (0.8361) time: 0.1886 data: 0.1006 max mem: 9390 +Train: [35] [ 400/6250] eta: 0:19:30 lr: 0.000097 grad: 0.0703 (0.0768) loss: 0.8365 (0.8352) time: 0.1945 data: 0.0959 max mem: 9390 +Train: [35] [ 500/6250] eta: 0:18:22 lr: 0.000097 grad: 0.0703 (0.0765) loss: 0.8277 (0.8341) time: 0.1352 data: 0.0463 max mem: 9390 +Train: [35] [ 600/6250] eta: 0:17:41 lr: 0.000097 grad: 0.0714 (0.0763) loss: 0.8300 (0.8331) time: 0.1725 data: 0.0751 max mem: 9390 +Train: [35] [ 700/6250] eta: 0:17:20 lr: 0.000096 grad: 0.0745 (0.0760) loss: 0.8248 (0.8324) time: 0.1978 data: 0.1037 max mem: 9390 +Train: [35] [ 800/6250] eta: 0:16:54 lr: 0.000096 grad: 0.0728 (0.0761) loss: 0.8244 (0.8315) time: 0.1585 data: 0.0750 max mem: 9390 +Train: [35] [ 900/6250] eta: 0:16:28 lr: 0.000096 grad: 0.0699 (0.0757) loss: 0.8259 (0.8308) time: 0.1751 data: 0.0807 max mem: 9390 +Train: [35] [1000/6250] eta: 0:16:03 lr: 0.000096 grad: 0.0686 (0.0755) loss: 0.8296 (0.8306) time: 0.1794 data: 0.0859 max mem: 9390 +Train: [35] [1100/6250] eta: 0:15:36 lr: 0.000096 grad: 0.0678 (0.0753) loss: 0.8263 (0.8301) time: 0.1560 data: 0.0622 max mem: 9390 +Train: [35] [1200/6250] eta: 0:15:10 lr: 0.000096 grad: 0.0733 (0.0754) loss: 0.8235 (0.8297) time: 0.1575 data: 0.0717 max mem: 9390 +Train: [35] [1300/6250] eta: 0:14:48 lr: 0.000096 grad: 0.0746 (0.0753) loss: 0.8258 (0.8293) time: 0.1887 data: 0.1031 max mem: 9390 +Train: [35] [1400/6250] eta: 0:14:27 lr: 0.000096 grad: 0.0752 (0.0753) loss: 0.8222 (0.8290) time: 0.1984 data: 0.1123 max mem: 9390 +Train: [35] [1500/6250] eta: 0:14:06 lr: 0.000096 grad: 0.0683 (0.0752) loss: 0.8300 (0.8287) time: 0.1805 data: 0.0973 max mem: 9390 +Train: [35] [1600/6250] eta: 0:13:43 lr: 0.000096 grad: 0.0752 (0.0753) loss: 0.8266 (0.8286) time: 0.1552 data: 0.0748 max mem: 9390 +Train: [35] [1700/6250] eta: 0:13:24 lr: 0.000096 grad: 0.0725 (0.0753) loss: 0.8232 (0.8283) time: 0.1811 data: 0.0973 max mem: 9390 +Train: [35] [1800/6250] eta: 0:13:05 lr: 0.000096 grad: 0.0726 (0.0753) loss: 0.8248 (0.8280) time: 0.1806 data: 0.1025 max mem: 9390 +Train: [35] [1900/6250] eta: 0:12:48 lr: 0.000096 grad: 0.0746 (0.0755) loss: 0.8279 (0.8278) time: 0.1955 data: 0.1072 max mem: 9390 +Train: [35] [2000/6250] eta: 0:12:29 lr: 0.000096 grad: 0.0687 (0.0756) loss: 0.8284 (0.8277) time: 0.1669 data: 0.0837 max mem: 9390 +Train: [35] [2100/6250] eta: 0:12:11 lr: 0.000096 grad: 0.0730 (0.0756) loss: 0.8281 (0.8276) time: 0.1775 data: 0.0885 max mem: 9390 +Train: [35] [2200/6250] eta: 0:11:52 lr: 0.000096 grad: 0.0776 (0.0757) loss: 0.8221 (0.8275) time: 0.1805 data: 0.0921 max mem: 9390 +Train: [35] [2300/6250] eta: 0:11:35 lr: 0.000096 grad: 0.0695 (0.0758) loss: 0.8253 (0.8274) time: 0.1723 data: 0.0841 max mem: 9390 +Train: [35] [2400/6250] eta: 0:11:18 lr: 0.000096 grad: 0.0776 (0.0759) loss: 0.8218 (0.8273) time: 0.1932 data: 0.1065 max mem: 9390 +Train: [35] [2500/6250] eta: 0:10:58 lr: 0.000096 grad: 0.0780 (0.0760) loss: 0.8203 (0.8271) time: 0.1597 data: 0.0789 max mem: 9390 +Train: [35] [2600/6250] eta: 0:10:40 lr: 0.000096 grad: 0.0745 (0.0761) loss: 0.8243 (0.8268) time: 0.1857 data: 0.1037 max mem: 9390 +Train: [35] [2700/6250] eta: 0:10:21 lr: 0.000096 grad: 0.0729 (0.0761) loss: 0.8235 (0.8267) time: 0.1752 data: 0.0887 max mem: 9390 +Train: [35] [2800/6250] eta: 0:10:02 lr: 0.000096 grad: 0.0759 (0.0762) loss: 0.8256 (0.8266) time: 0.1662 data: 0.0811 max mem: 9390 +Train: [35] [2900/6250] eta: 0:09:44 lr: 0.000096 grad: 0.0776 (0.0763) loss: 0.8223 (0.8264) time: 0.1458 data: 0.0590 max mem: 9390 +Train: [35] [3000/6250] eta: 0:09:27 lr: 0.000096 grad: 0.0722 (0.0764) loss: 0.8212 (0.8263) time: 0.1809 data: 0.0939 max mem: 9390 +Train: [35] [3100/6250] eta: 0:09:08 lr: 0.000096 grad: 0.0710 (0.0764) loss: 0.8270 (0.8263) time: 0.1624 data: 0.0760 max mem: 9390 +Train: [35] [3200/6250] eta: 0:08:50 lr: 0.000096 grad: 0.0707 (0.0764) loss: 0.8230 (0.8263) time: 0.1926 data: 0.1089 max mem: 9390 +Train: [35] [3300/6250] eta: 0:08:32 lr: 0.000096 grad: 0.0785 (0.0765) loss: 0.8260 (0.8263) time: 0.1736 data: 0.0939 max mem: 9390 +Train: [35] [3400/6250] eta: 0:08:15 lr: 0.000096 grad: 0.0698 (0.0764) loss: 0.8285 (0.8263) time: 0.1704 data: 0.0830 max mem: 9390 +Train: [35] [3500/6250] eta: 0:07:57 lr: 0.000096 grad: 0.0767 (0.0764) loss: 0.8307 (0.8264) time: 0.1894 data: 0.1006 max mem: 9390 +Train: [35] [3600/6250] eta: 0:07:39 lr: 0.000096 grad: 0.0714 (0.0764) loss: 0.8244 (0.8264) time: 0.1688 data: 0.0820 max mem: 9390 +Train: [35] [3700/6250] eta: 0:07:22 lr: 0.000096 grad: 0.0731 (0.0766) loss: 0.8287 (0.8265) time: 0.1403 data: 0.0491 max mem: 9390 +Train: [35] [3800/6250] eta: 0:07:04 lr: 0.000096 grad: 0.0737 (0.0766) loss: 0.8271 (0.8266) time: 0.1621 data: 0.0737 max mem: 9390 +Train: [35] [3900/6250] eta: 0:06:47 lr: 0.000096 grad: 0.0737 (0.0766) loss: 0.8233 (0.8266) time: 0.1626 data: 0.0789 max mem: 9390 +Train: [35] [4000/6250] eta: 0:06:29 lr: 0.000096 grad: 0.0732 (0.0766) loss: 0.8312 (0.8267) time: 0.1825 data: 0.0989 max mem: 9390 +Train: [35] [4100/6250] eta: 0:06:12 lr: 0.000096 grad: 0.0783 (0.0766) loss: 0.8268 (0.8267) time: 0.1558 data: 0.0722 max mem: 9390 +Train: [35] [4200/6250] eta: 0:05:54 lr: 0.000096 grad: 0.0731 (0.0766) loss: 0.8316 (0.8268) time: 0.1753 data: 0.0944 max mem: 9390 +Train: [35] [4300/6250] eta: 0:05:37 lr: 0.000095 grad: 0.0717 (0.0765) loss: 0.8297 (0.8268) time: 0.1306 data: 0.0389 max mem: 9390 +Train: [35] [4400/6250] eta: 0:05:19 lr: 0.000095 grad: 0.0731 (0.0765) loss: 0.8262 (0.8269) time: 0.1646 data: 0.0825 max mem: 9390 +Train: [35] [4500/6250] eta: 0:05:02 lr: 0.000095 grad: 0.0773 (0.0765) loss: 0.8236 (0.8269) time: 0.1585 data: 0.0747 max mem: 9390 +Train: [35] [4600/6250] eta: 0:04:44 lr: 0.000095 grad: 0.0680 (0.0764) loss: 0.8309 (0.8270) time: 0.1514 data: 0.0610 max mem: 9390 +Train: [35] [4700/6250] eta: 0:04:27 lr: 0.000095 grad: 0.0669 (0.0764) loss: 0.8261 (0.8270) time: 0.1471 data: 0.0580 max mem: 9390 +Train: [35] [4800/6250] eta: 0:04:10 lr: 0.000095 grad: 0.0678 (0.0763) loss: 0.8358 (0.8271) time: 0.1828 data: 0.0978 max mem: 9390 +Train: [35] [4900/6250] eta: 0:03:52 lr: 0.000095 grad: 0.0760 (0.0763) loss: 0.8306 (0.8272) time: 0.1677 data: 0.0778 max mem: 9390 +Train: [35] [5000/6250] eta: 0:03:35 lr: 0.000095 grad: 0.0685 (0.0763) loss: 0.8310 (0.8272) time: 0.1952 data: 0.1157 max mem: 9390 +Train: [35] [5100/6250] eta: 0:03:18 lr: 0.000095 grad: 0.0748 (0.0763) loss: 0.8227 (0.8272) time: 0.1596 data: 0.0649 max mem: 9390 +Train: [35] [5200/6250] eta: 0:03:00 lr: 0.000095 grad: 0.0707 (0.0762) loss: 0.8319 (0.8273) time: 0.1841 data: 0.0933 max mem: 9390 +Train: [35] [5300/6250] eta: 0:02:43 lr: 0.000095 grad: 0.0748 (0.0762) loss: 0.8243 (0.8273) time: 0.1475 data: 0.0670 max mem: 9390 +Train: [35] [5400/6250] eta: 0:02:26 lr: 0.000095 grad: 0.0728 (0.0762) loss: 0.8230 (0.8273) time: 0.1777 data: 0.0843 max mem: 9390 +Train: [35] [5500/6250] eta: 0:02:09 lr: 0.000095 grad: 0.0703 (0.0762) loss: 0.8282 (0.8273) time: 0.1871 data: 0.1045 max mem: 9390 +Train: [35] [5600/6250] eta: 0:01:51 lr: 0.000095 grad: 0.0713 (0.0762) loss: 0.8325 (0.8274) time: 0.1592 data: 0.0774 max mem: 9390 +Train: [35] [5700/6250] eta: 0:01:34 lr: 0.000095 grad: 0.0695 (0.0762) loss: 0.8273 (0.8274) time: 0.1655 data: 0.0794 max mem: 9390 +Train: [35] [5800/6250] eta: 0:01:17 lr: 0.000095 grad: 0.0719 (0.0762) loss: 0.8288 (0.8274) time: 0.1925 data: 0.1032 max mem: 9390 +Train: [35] [5900/6250] eta: 0:01:00 lr: 0.000095 grad: 0.0726 (0.0762) loss: 0.8320 (0.8275) time: 0.1793 data: 0.0882 max mem: 9390 +Train: [35] [6000/6250] eta: 0:00:42 lr: 0.000095 grad: 0.0679 (0.0761) loss: 0.8319 (0.8276) time: 0.1631 data: 0.0746 max mem: 9390 +Train: [35] [6100/6250] eta: 0:00:25 lr: 0.000095 grad: 0.0715 (0.0761) loss: 0.8340 (0.8276) time: 0.1771 data: 0.0948 max mem: 9390 +Train: [35] [6200/6250] eta: 0:00:08 lr: 0.000095 grad: 0.0734 (0.0761) loss: 0.8275 (0.8276) time: 0.1732 data: 0.0917 max mem: 9390 +Train: [35] [6249/6250] eta: 0:00:00 lr: 0.000095 grad: 0.0765 (0.0761) loss: 0.8288 (0.8277) time: 0.1658 data: 0.0826 max mem: 9390 +Train: [35] Total time: 0:18:05 (0.1736 s / it) +Averaged stats: lr: 0.000095 grad: 0.0765 (0.0761) loss: 0.8288 (0.8277) +Eval (hcp-train-subset): [35] [ 0/62] eta: 0:04:09 loss: 0.8521 (0.8521) time: 4.0258 data: 3.9433 max mem: 9390 +Eval (hcp-train-subset): [35] [61/62] eta: 0:00:00 loss: 0.8408 (0.8418) time: 0.1273 data: 0.1022 max mem: 9390 +Eval (hcp-train-subset): [35] Total time: 0:00:14 (0.2278 s / it) +Averaged stats (hcp-train-subset): loss: 0.8408 (0.8418) +Eval (hcp-val): [35] [ 0/62] eta: 0:03:44 loss: 0.8359 (0.8359) time: 3.6237 data: 3.5747 max mem: 9390 +Eval (hcp-val): [35] [61/62] eta: 0:00:00 loss: 0.8383 (0.8386) time: 0.1275 data: 0.1005 max mem: 9390 +Eval (hcp-val): [35] Total time: 0:00:14 (0.2263 s / it) +Averaged stats (hcp-val): loss: 0.8383 (0.8386) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +Train: [36] [ 0/6250] eta: 7:39:28 lr: 0.000095 grad: 0.0883 (0.0883) loss: 0.8522 (0.8522) time: 4.4110 data: 4.2748 max mem: 9390 +Train: [36] [ 100/6250] eta: 0:23:32 lr: 0.000095 grad: 0.0713 (0.0842) loss: 0.8400 (0.8422) time: 0.2014 data: 0.1166 max mem: 9390 +Train: [36] [ 200/6250] eta: 0:20:47 lr: 0.000095 grad: 0.0725 (0.0844) loss: 0.8295 (0.8361) time: 0.1845 data: 0.0835 max mem: 9390 +Train: [36] [ 300/6250] eta: 0:19:25 lr: 0.000095 grad: 0.0749 (0.0817) loss: 0.8274 (0.8337) time: 0.1961 data: 0.0969 max mem: 9390 +Train: [36] [ 400/6250] eta: 0:18:21 lr: 0.000095 grad: 0.0704 (0.0804) loss: 0.8253 (0.8326) time: 0.1548 data: 0.0657 max mem: 9390 +Train: [36] [ 500/6250] eta: 0:17:36 lr: 0.000095 grad: 0.0694 (0.0790) loss: 0.8396 (0.8325) time: 0.1317 data: 0.0413 max mem: 9390 +Train: [36] [ 600/6250] eta: 0:17:02 lr: 0.000095 grad: 0.0684 (0.0791) loss: 0.8360 (0.8327) time: 0.1676 data: 0.0692 max mem: 9390 +Train: [36] [ 700/6250] eta: 0:16:36 lr: 0.000095 grad: 0.0717 (0.0784) loss: 0.8323 (0.8323) time: 0.1853 data: 0.0936 max mem: 9390 +Train: [36] [ 800/6250] eta: 0:16:15 lr: 0.000095 grad: 0.0729 (0.0786) loss: 0.8308 (0.8319) time: 0.1721 data: 0.0769 max mem: 9390 +Train: [36] [ 900/6250] eta: 0:15:54 lr: 0.000095 grad: 0.0773 (0.0782) loss: 0.8205 (0.8317) time: 0.1622 data: 0.0677 max mem: 9390 +Train: [36] [1000/6250] eta: 0:15:32 lr: 0.000095 grad: 0.0771 (0.0781) loss: 0.8333 (0.8316) time: 0.1390 data: 0.0556 max mem: 9390 +Train: [36] [1100/6250] eta: 0:15:09 lr: 0.000095 grad: 0.0719 (0.0777) loss: 0.8318 (0.8314) time: 0.1520 data: 0.0684 max mem: 9390 +Train: [36] [1200/6250] eta: 0:14:45 lr: 0.000095 grad: 0.0768 (0.0776) loss: 0.8302 (0.8311) time: 0.1600 data: 0.0725 max mem: 9390 +Train: [36] [1300/6250] eta: 0:14:22 lr: 0.000095 grad: 0.0753 (0.0779) loss: 0.8271 (0.8307) time: 0.1541 data: 0.0694 max mem: 9390 +Train: [36] [1400/6250] eta: 0:14:01 lr: 0.000095 grad: 0.0768 (0.0780) loss: 0.8207 (0.8302) time: 0.1797 data: 0.0946 max mem: 9390 +Train: [36] [1500/6250] eta: 0:13:42 lr: 0.000095 grad: 0.0848 (0.0781) loss: 0.8271 (0.8298) time: 0.1915 data: 0.1072 max mem: 9390 +Train: [36] [1600/6250] eta: 0:13:21 lr: 0.000094 grad: 0.0742 (0.0781) loss: 0.8273 (0.8295) time: 0.1690 data: 0.0805 max mem: 9390 +Train: [36] [1700/6250] eta: 0:13:01 lr: 0.000094 grad: 0.0754 (0.0781) loss: 0.8254 (0.8294) time: 0.1537 data: 0.0683 max mem: 9390 +Train: [36] [1800/6250] eta: 0:12:46 lr: 0.000094 grad: 0.0713 (0.0780) loss: 0.8249 (0.8293) time: 0.1860 data: 0.0991 max mem: 9390 +Train: [36] [1900/6250] eta: 0:12:28 lr: 0.000094 grad: 0.0763 (0.0779) loss: 0.8206 (0.8291) time: 0.1505 data: 0.0662 max mem: 9390 +Train: [36] [2000/6250] eta: 0:12:10 lr: 0.000094 grad: 0.0800 (0.0778) loss: 0.8262 (0.8289) time: 0.1439 data: 0.0535 max mem: 9390 +Train: [36] [2100/6250] eta: 0:11:52 lr: 0.000094 grad: 0.0784 (0.0779) loss: 0.8198 (0.8286) time: 0.1630 data: 0.0722 max mem: 9390 +Train: [36] [2200/6250] eta: 0:11:33 lr: 0.000094 grad: 0.0749 (0.0778) loss: 0.8282 (0.8285) time: 0.1583 data: 0.0719 max mem: 9390 +Train: [36] [2300/6250] eta: 0:11:17 lr: 0.000094 grad: 0.0769 (0.0779) loss: 0.8218 (0.8284) time: 0.1860 data: 0.1038 max mem: 9390 +Train: [36] [2400/6250] eta: 0:10:59 lr: 0.000094 grad: 0.0736 (0.0779) loss: 0.8271 (0.8283) time: 0.1794 data: 0.1068 max mem: 9390 +Train: [36] [2500/6250] eta: 0:10:49 lr: 0.000094 grad: 0.0821 (0.0779) loss: 0.8248 (0.8282) time: 0.1834 data: 0.0963 max mem: 9390 +Train: [36] [2600/6250] eta: 0:10:31 lr: 0.000094 grad: 0.0830 (0.0780) loss: 0.8197 (0.8281) time: 0.1679 data: 0.0902 max mem: 9390 +Train: [36] [2700/6250] eta: 0:10:15 lr: 0.000094 grad: 0.0762 (0.0781) loss: 0.8230 (0.8280) time: 0.1821 data: 0.0981 max mem: 9390 +Train: [36] [2800/6250] eta: 0:09:58 lr: 0.000094 grad: 0.0810 (0.0781) loss: 0.8216 (0.8278) time: 0.1940 data: 0.1016 max mem: 9390 +Train: [36] [2900/6250] eta: 0:09:41 lr: 0.000094 grad: 0.0734 (0.0780) loss: 0.8236 (0.8277) time: 0.2279 data: 0.1462 max mem: 9390 +Train: [36] [3000/6250] eta: 0:09:25 lr: 0.000094 grad: 0.0705 (0.0780) loss: 0.8227 (0.8276) time: 0.1658 data: 0.0776 max mem: 9390 +Train: [36] [3100/6250] eta: 0:09:08 lr: 0.000094 grad: 0.0782 (0.0780) loss: 0.8153 (0.8275) time: 0.1630 data: 0.0787 max mem: 9390 +Train: [36] [3200/6250] eta: 0:08:49 lr: 0.000094 grad: 0.0722 (0.0779) loss: 0.8343 (0.8275) time: 0.1613 data: 0.0863 max mem: 9390 +Train: [36] [3300/6250] eta: 0:08:31 lr: 0.000094 grad: 0.0727 (0.0779) loss: 0.8279 (0.8274) time: 0.1696 data: 0.0814 max mem: 9390 +Train: [36] [3400/6250] eta: 0:08:13 lr: 0.000094 grad: 0.0778 (0.0779) loss: 0.8231 (0.8274) time: 0.1515 data: 0.0576 max mem: 9390 +Train: [36] [3500/6250] eta: 0:07:55 lr: 0.000094 grad: 0.0753 (0.0779) loss: 0.8276 (0.8273) time: 0.1310 data: 0.0352 max mem: 9390 +Train: [36] [3600/6250] eta: 0:07:37 lr: 0.000094 grad: 0.0681 (0.0780) loss: 0.8307 (0.8272) time: 0.1688 data: 0.0828 max mem: 9390 +Train: [36] [3700/6250] eta: 0:07:19 lr: 0.000094 grad: 0.0825 (0.0780) loss: 0.8181 (0.8271) time: 0.1365 data: 0.0301 max mem: 9390 +Train: [36] [3800/6250] eta: 0:07:01 lr: 0.000094 grad: 0.0767 (0.0781) loss: 0.8310 (0.8270) time: 0.1634 data: 0.0558 max mem: 9390 +Train: [36] [3900/6250] eta: 0:06:43 lr: 0.000094 grad: 0.0791 (0.0781) loss: 0.8232 (0.8268) time: 0.1745 data: 0.0887 max mem: 9390 +Train: [36] [4000/6250] eta: 0:06:25 lr: 0.000094 grad: 0.0784 (0.0782) loss: 0.8233 (0.8268) time: 0.1673 data: 0.0872 max mem: 9390 +Train: [36] [4100/6250] eta: 0:06:08 lr: 0.000094 grad: 0.0732 (0.0783) loss: 0.8292 (0.8268) time: 0.1552 data: 0.0695 max mem: 9390 +Train: [36] [4200/6250] eta: 0:05:51 lr: 0.000094 grad: 0.0757 (0.0782) loss: 0.8223 (0.8268) time: 0.1995 data: 0.1182 max mem: 9390 +Train: [36] [4300/6250] eta: 0:05:33 lr: 0.000094 grad: 0.0772 (0.0782) loss: 0.8237 (0.8268) time: 0.1813 data: 0.0970 max mem: 9390 +Train: [36] [4400/6250] eta: 0:05:16 lr: 0.000094 grad: 0.0804 (0.0782) loss: 0.8241 (0.8267) time: 0.1543 data: 0.0630 max mem: 9390 +Train: [36] [4500/6250] eta: 0:04:59 lr: 0.000094 grad: 0.0733 (0.0782) loss: 0.8325 (0.8268) time: 0.1790 data: 0.0903 max mem: 9390 +Train: [36] [4600/6250] eta: 0:04:42 lr: 0.000094 grad: 0.0706 (0.0781) loss: 0.8296 (0.8268) time: 0.1707 data: 0.0826 max mem: 9390 +Train: [36] [4700/6250] eta: 0:04:25 lr: 0.000094 grad: 0.0741 (0.0781) loss: 0.8244 (0.8268) time: 0.1803 data: 0.0895 max mem: 9390 +Train: [36] [4800/6250] eta: 0:04:07 lr: 0.000094 grad: 0.0775 (0.0781) loss: 0.8277 (0.8268) time: 0.1458 data: 0.0639 max mem: 9390 +Train: [36] [4900/6250] eta: 0:03:50 lr: 0.000094 grad: 0.0750 (0.0781) loss: 0.8270 (0.8268) time: 0.1601 data: 0.0761 max mem: 9390 +Train: [36] [5000/6250] eta: 0:03:33 lr: 0.000094 grad: 0.0708 (0.0780) loss: 0.8274 (0.8269) time: 0.1715 data: 0.0801 max mem: 9390 +Train: [36] [5100/6250] eta: 0:03:16 lr: 0.000093 grad: 0.0719 (0.0780) loss: 0.8307 (0.8270) time: 0.1618 data: 0.0753 max mem: 9390 +Train: [36] [5200/6250] eta: 0:02:59 lr: 0.000093 grad: 0.0756 (0.0780) loss: 0.8257 (0.8270) time: 0.1649 data: 0.0777 max mem: 9390 +Train: [36] [5300/6250] eta: 0:02:41 lr: 0.000093 grad: 0.0684 (0.0779) loss: 0.8356 (0.8272) time: 0.1601 data: 0.0713 max mem: 9390 +Train: [36] [5400/6250] eta: 0:02:24 lr: 0.000093 grad: 0.0714 (0.0779) loss: 0.8277 (0.8272) time: 0.1726 data: 0.0853 max mem: 9390 +Train: [36] [5500/6250] eta: 0:02:07 lr: 0.000093 grad: 0.0747 (0.0778) loss: 0.8252 (0.8273) time: 0.1673 data: 0.0887 max mem: 9390 +Train: [36] [5600/6250] eta: 0:01:50 lr: 0.000093 grad: 0.0731 (0.0777) loss: 0.8325 (0.8274) time: 0.1694 data: 0.0773 max mem: 9390 +Train: [36] [5700/6250] eta: 0:01:33 lr: 0.000093 grad: 0.0735 (0.0777) loss: 0.8306 (0.8274) time: 0.1682 data: 0.0777 max mem: 9390 +Train: [36] [5800/6250] eta: 0:01:16 lr: 0.000093 grad: 0.0695 (0.0776) loss: 0.8312 (0.8275) time: 0.1726 data: 0.0840 max mem: 9390 +Train: [36] [5900/6250] eta: 0:00:59 lr: 0.000093 grad: 0.0764 (0.0775) loss: 0.8241 (0.8276) time: 0.1541 data: 0.0608 max mem: 9390 +Train: [36] [6000/6250] eta: 0:00:42 lr: 0.000093 grad: 0.0761 (0.0775) loss: 0.8290 (0.8276) time: 0.1744 data: 0.0809 max mem: 9390 +Train: [36] [6100/6250] eta: 0:00:25 lr: 0.000093 grad: 0.0745 (0.0775) loss: 0.8241 (0.8276) time: 0.1463 data: 0.0665 max mem: 9390 +Train: [36] [6200/6250] eta: 0:00:08 lr: 0.000093 grad: 0.0789 (0.0776) loss: 0.8262 (0.8275) time: 0.1593 data: 0.0701 max mem: 9390 +Train: [36] [6249/6250] eta: 0:00:00 lr: 0.000093 grad: 0.0770 (0.0776) loss: 0.8292 (0.8275) time: 0.1790 data: 0.0905 max mem: 9390 +Train: [36] Total time: 0:17:51 (0.1715 s / it) +Averaged stats: lr: 0.000093 grad: 0.0770 (0.0776) loss: 0.8292 (0.8275) +Eval (hcp-train-subset): [36] [ 0/62] eta: 0:05:35 loss: 0.8474 (0.8474) time: 5.4181 data: 5.2938 max mem: 9390 +Eval (hcp-train-subset): [36] [61/62] eta: 0:00:00 loss: 0.8393 (0.8411) time: 0.1481 data: 0.1232 max mem: 9390 +Eval (hcp-train-subset): [36] Total time: 0:00:16 (0.2611 s / it) +Averaged stats (hcp-train-subset): loss: 0.8393 (0.8411) +Eval (hcp-val): [36] [ 0/62] eta: 0:05:02 loss: 0.8337 (0.8337) time: 4.8755 data: 4.8200 max mem: 9390 +Eval (hcp-val): [36] [61/62] eta: 0:00:00 loss: 0.8377 (0.8388) time: 0.1460 data: 0.1189 max mem: 9390 +Eval (hcp-val): [36] Total time: 0:00:14 (0.2355 s / it) +Averaged stats (hcp-val): loss: 0.8377 (0.8388) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +Train: [37] [ 0/6250] eta: 8:10:35 lr: 0.000093 grad: 0.0558 (0.0558) loss: 0.8366 (0.8366) time: 4.7097 data: 4.3816 max mem: 9390 +Train: [37] [ 100/6250] eta: 0:24:15 lr: 0.000093 grad: 0.0745 (0.0996) loss: 0.8196 (0.8330) time: 0.1775 data: 0.0761 max mem: 9390 +Train: [37] [ 200/6250] eta: 0:21:42 lr: 0.000093 grad: 0.0734 (0.0909) loss: 0.8316 (0.8318) time: 0.1834 data: 0.0878 max mem: 9390 +Train: [37] [ 300/6250] eta: 0:20:01 lr: 0.000093 grad: 0.0688 (0.0856) loss: 0.8319 (0.8320) time: 0.1628 data: 0.0629 max mem: 9390 +Train: [37] [ 400/6250] eta: 0:19:12 lr: 0.000093 grad: 0.0661 (0.0828) loss: 0.8349 (0.8318) time: 0.1594 data: 0.0649 max mem: 9390 +Train: [37] [ 500/6250] eta: 0:18:23 lr: 0.000093 grad: 0.0658 (0.0809) loss: 0.8300 (0.8319) time: 0.1813 data: 0.0881 max mem: 9390 +Train: [37] [ 600/6250] eta: 0:17:36 lr: 0.000093 grad: 0.0705 (0.0796) loss: 0.8232 (0.8316) time: 0.1695 data: 0.0778 max mem: 9390 +Train: [37] [ 700/6250] eta: 0:17:05 lr: 0.000093 grad: 0.0696 (0.0787) loss: 0.8347 (0.8315) time: 0.1833 data: 0.0878 max mem: 9390 +Train: [37] [ 800/6250] eta: 0:16:42 lr: 0.000093 grad: 0.0721 (0.0784) loss: 0.8289 (0.8311) time: 0.1892 data: 0.0989 max mem: 9390 +Train: [37] [ 900/6250] eta: 0:16:16 lr: 0.000093 grad: 0.0706 (0.0783) loss: 0.8207 (0.8307) time: 0.1705 data: 0.0803 max mem: 9390 +Train: [37] [1000/6250] eta: 0:15:55 lr: 0.000093 grad: 0.0723 (0.0779) loss: 0.8279 (0.8305) time: 0.1845 data: 0.1031 max mem: 9390 +Train: [37] [1100/6250] eta: 0:15:28 lr: 0.000093 grad: 0.0763 (0.0777) loss: 0.8235 (0.8302) time: 0.1802 data: 0.0942 max mem: 9390 +Train: [37] [1200/6250] eta: 0:15:03 lr: 0.000093 grad: 0.0753 (0.0777) loss: 0.8289 (0.8300) time: 0.1560 data: 0.0681 max mem: 9390 +Train: [37] [1300/6250] eta: 0:14:41 lr: 0.000093 grad: 0.0747 (0.0777) loss: 0.8278 (0.8297) time: 0.1760 data: 0.0889 max mem: 9390 +Train: [37] [1400/6250] eta: 0:14:20 lr: 0.000093 grad: 0.0799 (0.0781) loss: 0.8295 (0.8294) time: 0.1504 data: 0.0661 max mem: 9390 +Train: [37] [1500/6250] eta: 0:13:58 lr: 0.000093 grad: 0.0787 (0.0780) loss: 0.8184 (0.8292) time: 0.1552 data: 0.0723 max mem: 9390 +Train: [37] [1600/6250] eta: 0:13:39 lr: 0.000093 grad: 0.0741 (0.0779) loss: 0.8242 (0.8290) time: 0.1459 data: 0.0591 max mem: 9390 +Train: [37] [1700/6250] eta: 0:13:18 lr: 0.000093 grad: 0.0749 (0.0781) loss: 0.8293 (0.8289) time: 0.1591 data: 0.0683 max mem: 9390 +Train: [37] [1800/6250] eta: 0:12:58 lr: 0.000093 grad: 0.0733 (0.0780) loss: 0.8304 (0.8288) time: 0.1660 data: 0.0722 max mem: 9390 +Train: [37] [1900/6250] eta: 0:12:39 lr: 0.000093 grad: 0.0738 (0.0779) loss: 0.8258 (0.8288) time: 0.1712 data: 0.0820 max mem: 9390 +Train: [37] [2000/6250] eta: 0:12:19 lr: 0.000093 grad: 0.0754 (0.0779) loss: 0.8246 (0.8286) time: 0.1494 data: 0.0584 max mem: 9390 +Train: [37] [2100/6250] eta: 0:12:00 lr: 0.000093 grad: 0.0691 (0.0779) loss: 0.8346 (0.8286) time: 0.1600 data: 0.0719 max mem: 9390 +Train: [37] [2200/6250] eta: 0:11:42 lr: 0.000093 grad: 0.0707 (0.0779) loss: 0.8312 (0.8286) time: 0.1270 data: 0.0348 max mem: 9390 +Train: [37] [2300/6250] eta: 0:11:24 lr: 0.000092 grad: 0.0747 (0.0780) loss: 0.8240 (0.8286) time: 0.1949 data: 0.1109 max mem: 9390 +Train: [37] [2400/6250] eta: 0:11:07 lr: 0.000092 grad: 0.0746 (0.0778) loss: 0.8284 (0.8287) time: 0.1750 data: 0.0839 max mem: 9390 +Train: [37] [2500/6250] eta: 0:10:51 lr: 0.000092 grad: 0.0782 (0.0778) loss: 0.8271 (0.8286) time: 0.1812 data: 0.0988 max mem: 9390 +Train: [37] [2600/6250] eta: 0:10:33 lr: 0.000092 grad: 0.0795 (0.0778) loss: 0.8255 (0.8286) time: 0.1735 data: 0.0852 max mem: 9390 +Train: [37] [2700/6250] eta: 0:10:16 lr: 0.000092 grad: 0.0767 (0.0778) loss: 0.8299 (0.8285) time: 0.1562 data: 0.0664 max mem: 9390 +Train: [37] [2800/6250] eta: 0:09:59 lr: 0.000092 grad: 0.0755 (0.0779) loss: 0.8313 (0.8285) time: 0.1413 data: 0.0615 max mem: 9390 +Train: [37] [2900/6250] eta: 0:09:41 lr: 0.000092 grad: 0.0754 (0.0779) loss: 0.8259 (0.8286) time: 0.1592 data: 0.0685 max mem: 9390 +Train: [37] [3000/6250] eta: 0:09:24 lr: 0.000092 grad: 0.0711 (0.0779) loss: 0.8347 (0.8285) time: 0.1856 data: 0.0961 max mem: 9390 +Train: [37] [3100/6250] eta: 0:09:07 lr: 0.000092 grad: 0.0719 (0.0778) loss: 0.8247 (0.8285) time: 0.1579 data: 0.0669 max mem: 9390 +Train: [37] [3200/6250] eta: 0:08:49 lr: 0.000092 grad: 0.0746 (0.0778) loss: 0.8201 (0.8285) time: 0.1845 data: 0.0999 max mem: 9390 +Train: [37] [3300/6250] eta: 0:08:31 lr: 0.000092 grad: 0.0713 (0.0778) loss: 0.8268 (0.8283) time: 0.1746 data: 0.0892 max mem: 9390 +Train: [37] [3400/6250] eta: 0:08:14 lr: 0.000092 grad: 0.0744 (0.0778) loss: 0.8247 (0.8283) time: 0.1617 data: 0.0779 max mem: 9390 +Train: [37] [3500/6250] eta: 0:07:57 lr: 0.000092 grad: 0.0827 (0.0779) loss: 0.8181 (0.8282) time: 0.1858 data: 0.1043 max mem: 9390 +Train: [37] [3600/6250] eta: 0:07:39 lr: 0.000092 grad: 0.0756 (0.0778) loss: 0.8296 (0.8282) time: 0.1291 data: 0.0293 max mem: 9390 +Train: [37] [3700/6250] eta: 0:07:22 lr: 0.000092 grad: 0.0756 (0.0778) loss: 0.8247 (0.8282) time: 0.1913 data: 0.1067 max mem: 9390 +Train: [37] [3800/6250] eta: 0:07:04 lr: 0.000092 grad: 0.0765 (0.0778) loss: 0.8280 (0.8282) time: 0.1505 data: 0.0605 max mem: 9390 +Train: [37] [3900/6250] eta: 0:06:47 lr: 0.000092 grad: 0.0777 (0.0779) loss: 0.8281 (0.8281) time: 0.1542 data: 0.0680 max mem: 9390 +Train: [37] [4000/6250] eta: 0:06:30 lr: 0.000092 grad: 0.0766 (0.0780) loss: 0.8260 (0.8280) time: 0.1636 data: 0.0776 max mem: 9390 +Train: [37] [4100/6250] eta: 0:06:12 lr: 0.000092 grad: 0.0775 (0.0780) loss: 0.8283 (0.8279) time: 0.1853 data: 0.0975 max mem: 9390 +Train: [37] [4200/6250] eta: 0:05:55 lr: 0.000092 grad: 0.0754 (0.0781) loss: 0.8198 (0.8278) time: 0.1702 data: 0.0859 max mem: 9390 +Train: [37] [4300/6250] eta: 0:05:38 lr: 0.000092 grad: 0.0791 (0.0781) loss: 0.8142 (0.8277) time: 0.1677 data: 0.0880 max mem: 9390 +Train: [37] [4400/6250] eta: 0:05:20 lr: 0.000092 grad: 0.0753 (0.0782) loss: 0.8212 (0.8276) time: 0.2056 data: 0.1172 max mem: 9390 +Train: [37] [4500/6250] eta: 0:05:03 lr: 0.000092 grad: 0.0793 (0.0781) loss: 0.8261 (0.8276) time: 0.1570 data: 0.0610 max mem: 9390 +Train: [37] [4600/6250] eta: 0:04:45 lr: 0.000092 grad: 0.0736 (0.0781) loss: 0.8325 (0.8276) time: 0.1706 data: 0.0810 max mem: 9390 +Train: [37] [4700/6250] eta: 0:04:28 lr: 0.000092 grad: 0.0783 (0.0782) loss: 0.8213 (0.8275) time: 0.1576 data: 0.0579 max mem: 9390 +Train: [37] [4800/6250] eta: 0:04:11 lr: 0.000092 grad: 0.0769 (0.0782) loss: 0.8212 (0.8274) time: 0.2103 data: 0.1252 max mem: 9390 +Train: [37] [4900/6250] eta: 0:03:54 lr: 0.000092 grad: 0.0784 (0.0782) loss: 0.8261 (0.8274) time: 0.1370 data: 0.0308 max mem: 9390 +Train: [37] [5000/6250] eta: 0:03:37 lr: 0.000092 grad: 0.0763 (0.0782) loss: 0.8261 (0.8274) time: 0.1648 data: 0.0843 max mem: 9390 +Train: [37] [5100/6250] eta: 0:03:19 lr: 0.000092 grad: 0.0807 (0.0783) loss: 0.8243 (0.8273) time: 0.2287 data: 0.1441 max mem: 9390 +Train: [37] [5200/6250] eta: 0:03:02 lr: 0.000092 grad: 0.0798 (0.0784) loss: 0.8256 (0.8273) time: 0.1724 data: 0.0849 max mem: 9390 +Train: [37] [5300/6250] eta: 0:02:44 lr: 0.000092 grad: 0.0728 (0.0784) loss: 0.8247 (0.8272) time: 0.1669 data: 0.0875 max mem: 9390 +Train: [37] [5400/6250] eta: 0:02:27 lr: 0.000092 grad: 0.0744 (0.0784) loss: 0.8235 (0.8271) time: 0.1420 data: 0.0591 max mem: 9390 +Train: [37] [5500/6250] eta: 0:02:10 lr: 0.000092 grad: 0.0776 (0.0784) loss: 0.8166 (0.8270) time: 0.1580 data: 0.0716 max mem: 9390 +Train: [37] [5600/6250] eta: 0:01:52 lr: 0.000092 grad: 0.0809 (0.0785) loss: 0.8182 (0.8268) time: 0.1660 data: 0.0785 max mem: 9390 +Train: [37] [5700/6250] eta: 0:01:35 lr: 0.000091 grad: 0.0778 (0.0786) loss: 0.8202 (0.8268) time: 0.1658 data: 0.0739 max mem: 9390 +Train: [37] [5800/6250] eta: 0:01:18 lr: 0.000091 grad: 0.0805 (0.0786) loss: 0.8252 (0.8267) time: 0.1577 data: 0.0716 max mem: 9390 +Train: [37] [5900/6250] eta: 0:01:00 lr: 0.000091 grad: 0.0804 (0.0786) loss: 0.8180 (0.8267) time: 0.1568 data: 0.0674 max mem: 9390 +Train: [37] [6000/6250] eta: 0:00:43 lr: 0.000091 grad: 0.0856 (0.0787) loss: 0.8251 (0.8266) time: 0.1990 data: 0.1194 max mem: 9390 +Train: [37] [6100/6250] eta: 0:00:26 lr: 0.000091 grad: 0.0834 (0.0788) loss: 0.8225 (0.8265) time: 0.1824 data: 0.0986 max mem: 9390 +Train: [37] [6200/6250] eta: 0:00:08 lr: 0.000091 grad: 0.0797 (0.0788) loss: 0.8278 (0.8264) time: 0.1725 data: 0.0791 max mem: 9390 +Train: [37] [6249/6250] eta: 0:00:00 lr: 0.000091 grad: 0.0850 (0.0788) loss: 0.8199 (0.8264) time: 0.1799 data: 0.0923 max mem: 9390 +Train: [37] Total time: 0:18:13 (0.1750 s / it) +Averaged stats: lr: 0.000091 grad: 0.0850 (0.0788) loss: 0.8199 (0.8264) +Eval (hcp-train-subset): [37] [ 0/62] eta: 0:05:35 loss: 0.8531 (0.8531) time: 5.4069 data: 5.3763 max mem: 9390 +Eval (hcp-train-subset): [37] [61/62] eta: 0:00:00 loss: 0.8415 (0.8416) time: 0.1463 data: 0.1213 max mem: 9390 +Eval (hcp-train-subset): [37] Total time: 0:00:14 (0.2378 s / it) +Averaged stats (hcp-train-subset): loss: 0.8415 (0.8416) +Eval (hcp-val): [37] [ 0/62] eta: 0:04:50 loss: 0.8397 (0.8397) time: 4.6816 data: 4.6285 max mem: 9390 +Eval (hcp-val): [37] [61/62] eta: 0:00:00 loss: 0.8368 (0.8384) time: 0.1483 data: 0.1232 max mem: 9390 +Eval (hcp-val): [37] Total time: 0:00:15 (0.2443 s / it) +Averaged stats (hcp-val): loss: 0.8368 (0.8384) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +Train: [38] [ 0/6250] eta: 12:12:15 lr: 0.000091 grad: 0.3514 (0.3514) loss: 0.8168 (0.8168) time: 7.0296 data: 6.8919 max mem: 9390 +Train: [38] [ 100/6250] eta: 0:24:22 lr: 0.000091 grad: 0.0826 (0.0980) loss: 0.8307 (0.8299) time: 0.1973 data: 0.0920 max mem: 9390 +Train: [38] [ 200/6250] eta: 0:21:59 lr: 0.000091 grad: 0.0800 (0.0886) loss: 0.8218 (0.8279) time: 0.2029 data: 0.1069 max mem: 9390 +Train: [38] [ 300/6250] eta: 0:20:20 lr: 0.000091 grad: 0.0715 (0.0857) loss: 0.8250 (0.8274) time: 0.1936 data: 0.0936 max mem: 9390 +Train: [38] [ 400/6250] eta: 0:19:07 lr: 0.000091 grad: 0.0732 (0.0828) loss: 0.8280 (0.8280) time: 0.1615 data: 0.0732 max mem: 9390 +Train: [38] [ 500/6250] eta: 0:18:12 lr: 0.000091 grad: 0.0743 (0.0814) loss: 0.8265 (0.8285) time: 0.1664 data: 0.0642 max mem: 9390 +Train: [38] [ 600/6250] eta: 0:17:27 lr: 0.000091 grad: 0.0729 (0.0801) loss: 0.8334 (0.8289) time: 0.1733 data: 0.0700 max mem: 9390 +Train: [38] [ 700/6250] eta: 0:17:12 lr: 0.000091 grad: 0.0714 (0.0794) loss: 0.8340 (0.8292) time: 0.1916 data: 0.0993 max mem: 9390 +Train: [38] [ 800/6250] eta: 0:16:57 lr: 0.000091 grad: 0.0703 (0.0787) loss: 0.8299 (0.8295) time: 0.1982 data: 0.1103 max mem: 9390 +Train: [38] [ 900/6250] eta: 0:16:32 lr: 0.000091 grad: 0.0695 (0.0780) loss: 0.8305 (0.8296) time: 0.1851 data: 0.0906 max mem: 9390 +Train: [38] [1000/6250] eta: 0:16:06 lr: 0.000091 grad: 0.0715 (0.0774) loss: 0.8338 (0.8301) time: 0.1692 data: 0.0758 max mem: 9390 +Train: [38] [1100/6250] eta: 0:15:43 lr: 0.000091 grad: 0.0723 (0.0769) loss: 0.8289 (0.8302) time: 0.1770 data: 0.0897 max mem: 9390 +Train: [38] [1200/6250] eta: 0:15:18 lr: 0.000091 grad: 0.0730 (0.0765) loss: 0.8305 (0.8303) time: 0.1552 data: 0.0680 max mem: 9390 +Train: [38] [1300/6250] eta: 0:14:52 lr: 0.000091 grad: 0.0726 (0.0764) loss: 0.8362 (0.8305) time: 0.1585 data: 0.0665 max mem: 9390 +Train: [38] [1400/6250] eta: 0:14:44 lr: 0.000091 grad: 0.0786 (0.0764) loss: 0.8317 (0.8306) time: 0.2015 data: 0.1027 max mem: 9390 +Train: [38] [1500/6250] eta: 0:14:18 lr: 0.000091 grad: 0.0729 (0.0765) loss: 0.8282 (0.8304) time: 0.1626 data: 0.0757 max mem: 9390 +Train: [38] [1600/6250] eta: 0:13:58 lr: 0.000091 grad: 0.0731 (0.0765) loss: 0.8263 (0.8303) time: 0.1677 data: 0.0807 max mem: 9390 +Train: [38] [1700/6250] eta: 0:13:34 lr: 0.000091 grad: 0.0801 (0.0765) loss: 0.8290 (0.8303) time: 0.1562 data: 0.0717 max mem: 9390 +Train: [38] [1800/6250] eta: 0:13:14 lr: 0.000091 grad: 0.0796 (0.0766) loss: 0.8215 (0.8303) time: 0.1798 data: 0.0909 max mem: 9390 +Train: [38] [1900/6250] eta: 0:12:59 lr: 0.000091 grad: 0.0716 (0.0765) loss: 0.8312 (0.8303) time: 0.1557 data: 0.0654 max mem: 9390 +Train: [38] [2000/6250] eta: 0:12:39 lr: 0.000091 grad: 0.0706 (0.0765) loss: 0.8346 (0.8303) time: 0.1786 data: 0.0769 max mem: 9390 +Train: [38] [2100/6250] eta: 0:12:18 lr: 0.000091 grad: 0.0772 (0.0766) loss: 0.8258 (0.8303) time: 0.1540 data: 0.0708 max mem: 9390 +Train: [38] [2200/6250] eta: 0:11:59 lr: 0.000091 grad: 0.0715 (0.0767) loss: 0.8323 (0.8303) time: 0.2002 data: 0.1132 max mem: 9390 +Train: [38] [2300/6250] eta: 0:11:41 lr: 0.000091 grad: 0.0734 (0.0768) loss: 0.8311 (0.8304) time: 0.1862 data: 0.0887 max mem: 9390 +Train: [38] [2400/6250] eta: 0:11:21 lr: 0.000091 grad: 0.0751 (0.0767) loss: 0.8327 (0.8304) time: 0.1623 data: 0.0730 max mem: 9390 +Train: [38] [2500/6250] eta: 0:11:01 lr: 0.000091 grad: 0.0766 (0.0768) loss: 0.8302 (0.8304) time: 0.1647 data: 0.0751 max mem: 9390 +Train: [38] [2600/6250] eta: 0:10:41 lr: 0.000091 grad: 0.0742 (0.0770) loss: 0.8236 (0.8304) time: 0.1517 data: 0.0557 max mem: 9390 +Train: [38] [2700/6250] eta: 0:10:22 lr: 0.000091 grad: 0.0739 (0.0771) loss: 0.8276 (0.8303) time: 0.1652 data: 0.0781 max mem: 9390 +Train: [38] [2800/6250] eta: 0:10:03 lr: 0.000091 grad: 0.0764 (0.0773) loss: 0.8302 (0.8302) time: 0.1722 data: 0.0909 max mem: 9390 +Train: [38] [2900/6250] eta: 0:09:45 lr: 0.000090 grad: 0.0760 (0.0773) loss: 0.8327 (0.8301) time: 0.1785 data: 0.0913 max mem: 9390 +Train: [38] [3000/6250] eta: 0:09:28 lr: 0.000090 grad: 0.0777 (0.0774) loss: 0.8296 (0.8301) time: 0.1869 data: 0.1079 max mem: 9390 +Train: [38] [3100/6250] eta: 0:09:11 lr: 0.000090 grad: 0.0720 (0.0774) loss: 0.8365 (0.8301) time: 0.1852 data: 0.0954 max mem: 9390 +Train: [38] [3200/6250] eta: 0:08:53 lr: 0.000090 grad: 0.0768 (0.0775) loss: 0.8323 (0.8301) time: 0.1863 data: 0.1013 max mem: 9390 +Train: [38] [3300/6250] eta: 0:08:36 lr: 0.000090 grad: 0.0724 (0.0775) loss: 0.8325 (0.8301) time: 0.2068 data: 0.1161 max mem: 9390 +Train: [38] [3400/6250] eta: 0:08:18 lr: 0.000090 grad: 0.0743 (0.0776) loss: 0.8301 (0.8302) time: 0.1636 data: 0.0687 max mem: 9390 +Train: [38] [3500/6250] eta: 0:08:01 lr: 0.000090 grad: 0.0802 (0.0776) loss: 0.8334 (0.8302) time: 0.1639 data: 0.0725 max mem: 9390 +Train: [38] [3600/6250] eta: 0:07:43 lr: 0.000090 grad: 0.0797 (0.0779) loss: 0.8279 (0.8302) time: 0.1625 data: 0.0731 max mem: 9390 +Train: [38] [3700/6250] eta: 0:07:26 lr: 0.000090 grad: 0.0761 (0.0780) loss: 0.8335 (0.8302) time: 0.1757 data: 0.0837 max mem: 9390 +Train: [38] [3800/6250] eta: 0:07:08 lr: 0.000090 grad: 0.0753 (0.0780) loss: 0.8274 (0.8302) time: 0.1598 data: 0.0747 max mem: 9390 +Train: [38] [3900/6250] eta: 0:06:51 lr: 0.000090 grad: 0.0770 (0.0781) loss: 0.8299 (0.8302) time: 0.1961 data: 0.1144 max mem: 9390 +Train: [38] [4000/6250] eta: 0:06:33 lr: 0.000090 grad: 0.0756 (0.0781) loss: 0.8280 (0.8301) time: 0.1796 data: 0.0980 max mem: 9390 +Train: [38] [4100/6250] eta: 0:06:15 lr: 0.000090 grad: 0.0822 (0.0782) loss: 0.8299 (0.8301) time: 0.1842 data: 0.0846 max mem: 9390 +Train: [38] [4200/6250] eta: 0:05:58 lr: 0.000090 grad: 0.0764 (0.0782) loss: 0.8299 (0.8300) time: 0.1812 data: 0.0952 max mem: 9390 +Train: [38] [4300/6250] eta: 0:05:40 lr: 0.000090 grad: 0.0819 (0.0783) loss: 0.8227 (0.8300) time: 0.1611 data: 0.0718 max mem: 9390 +Train: [38] [4400/6250] eta: 0:05:22 lr: 0.000090 grad: 0.0752 (0.0783) loss: 0.8248 (0.8299) time: 0.1943 data: 0.1170 max mem: 9390 +Train: [38] [4500/6250] eta: 0:05:05 lr: 0.000090 grad: 0.0808 (0.0783) loss: 0.8256 (0.8298) time: 0.2098 data: 0.1202 max mem: 9390 +Train: [38] [4600/6250] eta: 0:04:48 lr: 0.000090 grad: 0.0803 (0.0785) loss: 0.8215 (0.8297) time: 0.1831 data: 0.1011 max mem: 9390 +Train: [38] [4700/6250] eta: 0:04:30 lr: 0.000090 grad: 0.0752 (0.0785) loss: 0.8297 (0.8297) time: 0.1944 data: 0.1070 max mem: 9390 +Train: [38] [4800/6250] eta: 0:04:14 lr: 0.000090 grad: 0.0750 (0.0785) loss: 0.8318 (0.8296) time: 0.2398 data: 0.1459 max mem: 9390 +Train: [38] [4900/6250] eta: 0:03:57 lr: 0.000090 grad: 0.0773 (0.0786) loss: 0.8264 (0.8296) time: 0.2217 data: 0.1354 max mem: 9390 +Train: [38] [5000/6250] eta: 0:03:40 lr: 0.000090 grad: 0.0770 (0.0786) loss: 0.8247 (0.8295) time: 0.1761 data: 0.0817 max mem: 9390 +Train: [38] [5100/6250] eta: 0:03:23 lr: 0.000090 grad: 0.0706 (0.0787) loss: 0.8361 (0.8294) time: 0.2019 data: 0.1194 max mem: 9390 +Train: [38] [5200/6250] eta: 0:03:06 lr: 0.000090 grad: 0.0744 (0.0787) loss: 0.8260 (0.8294) time: 0.1990 data: 0.1130 max mem: 9390 +Train: [38] [5300/6250] eta: 0:02:48 lr: 0.000090 grad: 0.0754 (0.0787) loss: 0.8243 (0.8294) time: 0.2562 data: 0.1644 max mem: 9390 +Train: [38] [5400/6250] eta: 0:02:31 lr: 0.000090 grad: 0.0795 (0.0787) loss: 0.8201 (0.8293) time: 0.1938 data: 0.1022 max mem: 9390 +Train: [38] [5500/6250] eta: 0:02:13 lr: 0.000090 grad: 0.0775 (0.0787) loss: 0.8250 (0.8292) time: 0.1778 data: 0.0788 max mem: 9390 +Train: [38] [5600/6250] eta: 0:01:55 lr: 0.000090 grad: 0.0774 (0.0790) loss: 0.8309 (0.8292) time: 0.1596 data: 0.0748 max mem: 9390 +Train: [38] [5700/6250] eta: 0:01:38 lr: 0.000090 grad: 0.0760 (0.0792) loss: 0.8305 (0.8292) time: 0.2052 data: 0.1166 max mem: 9390 +Train: [38] [5800/6250] eta: 0:01:20 lr: 0.000090 grad: 0.0761 (0.0792) loss: 0.8334 (0.8291) time: 0.1308 data: 0.0374 max mem: 9390 +Train: [38] [5900/6250] eta: 0:01:02 lr: 0.000090 grad: 0.0774 (0.0792) loss: 0.8332 (0.8291) time: 0.1922 data: 0.1064 max mem: 9390 +Train: [38] [6000/6250] eta: 0:00:44 lr: 0.000090 grad: 0.0780 (0.0792) loss: 0.8239 (0.8290) time: 0.1839 data: 0.0942 max mem: 9390 +Train: [38] [6100/6250] eta: 0:00:26 lr: 0.000090 grad: 0.0729 (0.0791) loss: 0.8308 (0.8290) time: 0.2112 data: 0.1130 max mem: 9390 +Train: [38] [6200/6250] eta: 0:00:09 lr: 0.000089 grad: 0.0816 (0.0791) loss: 0.8205 (0.8290) time: 0.2325 data: 0.1419 max mem: 9390 +Train: [38] [6249/6250] eta: 0:00:00 lr: 0.000089 grad: 0.0741 (0.0791) loss: 0.8278 (0.8290) time: 0.1764 data: 0.0888 max mem: 9390 +Train: [38] Total time: 0:18:53 (0.1813 s / it) +Averaged stats: lr: 0.000089 grad: 0.0741 (0.0791) loss: 0.8278 (0.8290) +Eval (hcp-train-subset): [38] [ 0/62] eta: 0:05:27 loss: 0.8551 (0.8551) time: 5.2781 data: 5.1739 max mem: 9390 +Eval (hcp-train-subset): [38] [61/62] eta: 0:00:00 loss: 0.8395 (0.8404) time: 0.1302 data: 0.1045 max mem: 9390 +Eval (hcp-train-subset): [38] Total time: 0:00:15 (0.2562 s / it) +Averaged stats (hcp-train-subset): loss: 0.8395 (0.8404) +Eval (hcp-val): [38] [ 0/62] eta: 0:04:52 loss: 0.8337 (0.8337) time: 4.7192 data: 4.6038 max mem: 9390 +Eval (hcp-val): [38] [61/62] eta: 0:00:00 loss: 0.8364 (0.8366) time: 0.1326 data: 0.1074 max mem: 9390 +Eval (hcp-val): [38] Total time: 0:00:17 (0.2851 s / it) +Averaged stats (hcp-val): loss: 0.8364 (0.8366) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +Train: [39] [ 0/6250] eta: 8:51:12 lr: 0.000089 grad: 0.1765 (0.1765) loss: 0.8255 (0.8255) time: 5.0997 data: 4.9479 max mem: 9390 +Train: [39] [ 100/6250] eta: 0:24:24 lr: 0.000089 grad: 0.0668 (0.0909) loss: 0.8399 (0.8403) time: 0.1592 data: 0.0685 max mem: 9390 +Train: [39] [ 200/6250] eta: 0:22:30 lr: 0.000089 grad: 0.0696 (0.0851) loss: 0.8324 (0.8369) time: 0.2158 data: 0.1110 max mem: 9390 +Train: [39] [ 300/6250] eta: 0:21:11 lr: 0.000089 grad: 0.0722 (0.0825) loss: 0.8308 (0.8344) time: 0.2000 data: 0.0884 max mem: 9390 +Train: [39] [ 400/6250] eta: 0:20:06 lr: 0.000089 grad: 0.0753 (0.0815) loss: 0.8224 (0.8317) time: 0.1640 data: 0.0738 max mem: 9390 +Train: [39] [ 500/6250] eta: 0:19:06 lr: 0.000089 grad: 0.0752 (0.0807) loss: 0.8180 (0.8295) time: 0.1590 data: 0.0596 max mem: 9390 +Train: [39] [ 600/6250] eta: 0:18:18 lr: 0.000089 grad: 0.0740 (0.0796) loss: 0.8283 (0.8285) time: 0.1517 data: 0.0557 max mem: 9390 +Train: [39] [ 700/6250] eta: 0:17:45 lr: 0.000089 grad: 0.0720 (0.0791) loss: 0.8293 (0.8281) time: 0.1744 data: 0.0843 max mem: 9390 +Train: [39] [ 800/6250] eta: 0:17:25 lr: 0.000089 grad: 0.0719 (0.0787) loss: 0.8226 (0.8279) time: 0.1997 data: 0.1060 max mem: 9390 +Train: [39] [ 900/6250] eta: 0:17:07 lr: 0.000089 grad: 0.0753 (0.0783) loss: 0.8291 (0.8279) time: 0.1653 data: 0.0777 max mem: 9390 +Train: [39] [1000/6250] eta: 0:16:45 lr: 0.000089 grad: 0.0715 (0.0778) loss: 0.8275 (0.8280) time: 0.1718 data: 0.0817 max mem: 9390 +Train: [39] [1100/6250] eta: 0:16:19 lr: 0.000089 grad: 0.0683 (0.0775) loss: 0.8316 (0.8281) time: 0.1508 data: 0.0614 max mem: 9390 +Train: [39] [1200/6250] eta: 0:15:53 lr: 0.000089 grad: 0.0755 (0.0774) loss: 0.8286 (0.8281) time: 0.1887 data: 0.0998 max mem: 9390 +Train: [39] [1300/6250] eta: 0:15:33 lr: 0.000089 grad: 0.0768 (0.0775) loss: 0.8254 (0.8281) time: 0.1590 data: 0.0730 max mem: 9390 +Train: [39] [1400/6250] eta: 0:15:09 lr: 0.000089 grad: 0.0778 (0.0775) loss: 0.8276 (0.8280) time: 0.1732 data: 0.0892 max mem: 9390 +Train: [39] [1500/6250] eta: 0:14:43 lr: 0.000089 grad: 0.0765 (0.0776) loss: 0.8258 (0.8280) time: 0.1797 data: 0.0974 max mem: 9390 +Train: [39] [1600/6250] eta: 0:14:19 lr: 0.000089 grad: 0.0770 (0.0777) loss: 0.8257 (0.8280) time: 0.1834 data: 0.0912 max mem: 9390 +Train: [39] [1700/6250] eta: 0:13:56 lr: 0.000089 grad: 0.0763 (0.0778) loss: 0.8297 (0.8280) time: 0.1848 data: 0.0964 max mem: 9390 +Train: [39] [1800/6250] eta: 0:13:34 lr: 0.000089 grad: 0.0775 (0.0779) loss: 0.8223 (0.8280) time: 0.1646 data: 0.0802 max mem: 9390 +Train: [39] [1900/6250] eta: 0:13:15 lr: 0.000089 grad: 0.0787 (0.0780) loss: 0.8224 (0.8278) time: 0.1311 data: 0.0515 max mem: 9390 +Train: [39] [2000/6250] eta: 0:12:55 lr: 0.000089 grad: 0.0776 (0.0781) loss: 0.8279 (0.8278) time: 0.1593 data: 0.0652 max mem: 9390 +Train: [39] [2100/6250] eta: 0:12:36 lr: 0.000089 grad: 0.0831 (0.0781) loss: 0.8225 (0.8277) time: 0.1715 data: 0.0867 max mem: 9390 +Train: [39] [2200/6250] eta: 0:12:19 lr: 0.000089 grad: 0.0834 (0.0784) loss: 0.8216 (0.8276) time: 0.2656 data: 0.1776 max mem: 9390 +Train: [39] [2300/6250] eta: 0:11:56 lr: 0.000089 grad: 0.0770 (0.0786) loss: 0.8247 (0.8275) time: 0.1787 data: 0.0949 max mem: 9390 +Train: [39] [2400/6250] eta: 0:11:38 lr: 0.000089 grad: 0.0762 (0.0787) loss: 0.8267 (0.8275) time: 0.1024 data: 0.0002 max mem: 9390 +Train: [39] [2500/6250] eta: 0:11:20 lr: 0.000089 grad: 0.0732 (0.0788) loss: 0.8318 (0.8275) time: 0.1948 data: 0.1055 max mem: 9390 +Train: [39] [2600/6250] eta: 0:11:04 lr: 0.000089 grad: 0.0789 (0.0788) loss: 0.8284 (0.8274) time: 0.2626 data: 0.1717 max mem: 9390 +Train: [39] [2700/6250] eta: 0:10:44 lr: 0.000089 grad: 0.0759 (0.0787) loss: 0.8223 (0.8275) time: 0.1924 data: 0.1033 max mem: 9390 +Train: [39] [2800/6250] eta: 0:10:29 lr: 0.000089 grad: 0.0811 (0.0788) loss: 0.8228 (0.8274) time: 0.2752 data: 0.1845 max mem: 9390 +Train: [39] [2900/6250] eta: 0:10:09 lr: 0.000089 grad: 0.0783 (0.0789) loss: 0.8354 (0.8275) time: 0.1693 data: 0.0774 max mem: 9390 +Train: [39] [3000/6250] eta: 0:09:51 lr: 0.000089 grad: 0.0757 (0.0789) loss: 0.8247 (0.8275) time: 0.1525 data: 0.0606 max mem: 9390 +Train: [39] [3100/6250] eta: 0:09:35 lr: 0.000089 grad: 0.0740 (0.0789) loss: 0.8282 (0.8275) time: 0.2462 data: 0.1614 max mem: 9390 +Train: [39] [3200/6250] eta: 0:09:19 lr: 0.000089 grad: 0.0794 (0.0789) loss: 0.8255 (0.8275) time: 0.3034 data: 0.2067 max mem: 9390 +Train: [39] [3300/6250] eta: 0:08:59 lr: 0.000088 grad: 0.0723 (0.0790) loss: 0.8300 (0.8276) time: 0.2157 data: 0.1312 max mem: 9390 +Train: [39] [3400/6250] eta: 0:08:42 lr: 0.000088 grad: 0.0712 (0.0790) loss: 0.8301 (0.8275) time: 0.1693 data: 0.0790 max mem: 9390 +Train: [39] [3500/6250] eta: 0:08:24 lr: 0.000088 grad: 0.0804 (0.0791) loss: 0.8288 (0.8275) time: 0.1769 data: 0.0935 max mem: 9390 +Train: [39] [3600/6250] eta: 0:08:05 lr: 0.000088 grad: 0.0741 (0.0792) loss: 0.8265 (0.8275) time: 0.0938 data: 0.0003 max mem: 9390 +Train: [39] [3700/6250] eta: 0:07:47 lr: 0.000088 grad: 0.0750 (0.0791) loss: 0.8248 (0.8275) time: 0.1582 data: 0.0712 max mem: 9390 +Train: [39] [3800/6250] eta: 0:07:28 lr: 0.000088 grad: 0.0806 (0.0792) loss: 0.8249 (0.8274) time: 0.1791 data: 0.0940 max mem: 9390 +Train: [39] [3900/6250] eta: 0:07:10 lr: 0.000088 grad: 0.0775 (0.0792) loss: 0.8321 (0.8274) time: 0.1376 data: 0.0464 max mem: 9390 +Train: [39] [4000/6250] eta: 0:06:51 lr: 0.000088 grad: 0.0736 (0.0792) loss: 0.8296 (0.8275) time: 0.1831 data: 0.0992 max mem: 9390 +Train: [39] [4100/6250] eta: 0:06:33 lr: 0.000088 grad: 0.0725 (0.0793) loss: 0.8303 (0.8276) time: 0.2057 data: 0.1203 max mem: 9390 +Train: [39] [4200/6250] eta: 0:06:16 lr: 0.000088 grad: 0.0808 (0.0793) loss: 0.8288 (0.8275) time: 0.1138 data: 0.0002 max mem: 9390 +Train: [39] [4300/6250] eta: 0:05:57 lr: 0.000088 grad: 0.0773 (0.0794) loss: 0.8241 (0.8275) time: 0.1759 data: 0.0881 max mem: 9390 +Train: [39] [4400/6250] eta: 0:05:39 lr: 0.000088 grad: 0.0795 (0.0794) loss: 0.8258 (0.8275) time: 0.1724 data: 0.0802 max mem: 9390 +Train: [39] [4500/6250] eta: 0:05:20 lr: 0.000088 grad: 0.0797 (0.0795) loss: 0.8268 (0.8275) time: 0.1257 data: 0.0351 max mem: 9390 +Train: [39] [4600/6250] eta: 0:05:02 lr: 0.000088 grad: 0.0800 (0.0795) loss: 0.8241 (0.8274) time: 0.2065 data: 0.1197 max mem: 9390 +Train: [39] [4700/6250] eta: 0:04:44 lr: 0.000088 grad: 0.0830 (0.0795) loss: 0.8286 (0.8274) time: 0.1615 data: 0.0738 max mem: 9390 +Train: [39] [4800/6250] eta: 0:04:26 lr: 0.000088 grad: 0.0736 (0.0795) loss: 0.8215 (0.8274) time: 0.1166 data: 0.0311 max mem: 9390 +Train: [39] [4900/6250] eta: 0:04:07 lr: 0.000088 grad: 0.0781 (0.0795) loss: 0.8280 (0.8274) time: 0.1617 data: 0.0812 max mem: 9390 +Train: [39] [5000/6250] eta: 0:03:49 lr: 0.000088 grad: 0.0768 (0.0795) loss: 0.8285 (0.8274) time: 0.2088 data: 0.1153 max mem: 9390 +Train: [39] [5100/6250] eta: 0:03:31 lr: 0.000088 grad: 0.0813 (0.0795) loss: 0.8275 (0.8274) time: 0.1740 data: 0.0742 max mem: 9390 +Train: [39] [5200/6250] eta: 0:03:12 lr: 0.000088 grad: 0.0701 (0.0795) loss: 0.8271 (0.8274) time: 0.2276 data: 0.1421 max mem: 9390 +Train: [39] [5300/6250] eta: 0:02:54 lr: 0.000088 grad: 0.0736 (0.0795) loss: 0.8286 (0.8274) time: 0.2084 data: 0.1260 max mem: 9390 +Train: [39] [5400/6250] eta: 0:02:35 lr: 0.000088 grad: 0.0760 (0.0795) loss: 0.8237 (0.8273) time: 0.1524 data: 0.0574 max mem: 9390 +Train: [39] [5500/6250] eta: 0:02:17 lr: 0.000088 grad: 0.0780 (0.0796) loss: 0.8286 (0.8273) time: 0.2199 data: 0.1129 max mem: 9390 +Train: [39] [5600/6250] eta: 0:01:59 lr: 0.000088 grad: 0.0773 (0.0795) loss: 0.8317 (0.8273) time: 0.1724 data: 0.0891 max mem: 9390 +Train: [39] [5700/6250] eta: 0:01:41 lr: 0.000088 grad: 0.0778 (0.0796) loss: 0.8268 (0.8273) time: 0.1163 data: 0.0002 max mem: 9390 +Train: [39] [5800/6250] eta: 0:01:22 lr: 0.000088 grad: 0.0880 (0.0797) loss: 0.8301 (0.8272) time: 0.1832 data: 0.0965 max mem: 9390 +Train: [39] [5900/6250] eta: 0:01:04 lr: 0.000088 grad: 0.0835 (0.0797) loss: 0.8232 (0.8272) time: 0.1939 data: 0.1055 max mem: 9390 +Train: [39] [6000/6250] eta: 0:00:46 lr: 0.000088 grad: 0.0802 (0.0797) loss: 0.8282 (0.8272) time: 0.2573 data: 0.1701 max mem: 9390 +Train: [39] [6100/6250] eta: 0:00:27 lr: 0.000088 grad: 0.0786 (0.0798) loss: 0.8302 (0.8272) time: 0.1733 data: 0.0962 max mem: 9390 +Train: [39] [6200/6250] eta: 0:00:09 lr: 0.000088 grad: 0.0789 (0.0798) loss: 0.8222 (0.8271) time: 0.1810 data: 0.0777 max mem: 9390 +Train: [39] [6249/6250] eta: 0:00:00 lr: 0.000088 grad: 0.0743 (0.0798) loss: 0.8278 (0.8271) time: 0.1273 data: 0.0474 max mem: 9390 +Train: [39] Total time: 0:19:23 (0.1861 s / it) +Averaged stats: lr: 0.000088 grad: 0.0743 (0.0798) loss: 0.8278 (0.8271) +Eval (hcp-train-subset): [39] [ 0/62] eta: 0:05:59 loss: 0.8547 (0.8547) time: 5.8047 data: 5.7566 max mem: 9390 +Eval (hcp-train-subset): [39] [61/62] eta: 0:00:00 loss: 0.8387 (0.8410) time: 0.1337 data: 0.1083 max mem: 9390 +Eval (hcp-train-subset): [39] Total time: 0:00:15 (0.2530 s / it) +Averaged stats (hcp-train-subset): loss: 0.8387 (0.8410) +Making plots (hcp-train-subset): example=39 +Eval (hcp-val): [39] [ 0/62] eta: 0:05:25 loss: 0.8366 (0.8366) time: 5.2525 data: 5.1957 max mem: 9390 +Eval (hcp-val): [39] [61/62] eta: 0:00:00 loss: 0.8356 (0.8372) time: 0.1605 data: 0.1346 max mem: 9390 +Eval (hcp-val): [39] Total time: 0:00:14 (0.2370 s / it) +Averaged stats (hcp-val): loss: 0.8356 (0.8372) +Making plots (hcp-val): example=23 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +Train: [40] [ 0/6250] eta: 7:12:55 lr: 0.000088 grad: 0.0592 (0.0592) loss: 0.8612 (0.8612) time: 4.1560 data: 3.9510 max mem: 9390 +Train: [40] [ 100/6250] eta: 0:25:50 lr: 0.000088 grad: 0.0778 (0.0896) loss: 0.8335 (0.8390) time: 0.1786 data: 0.0822 max mem: 9390 +Train: [40] [ 200/6250] eta: 0:22:25 lr: 0.000088 grad: 0.0787 (0.0899) loss: 0.8183 (0.8320) time: 0.2009 data: 0.1170 max mem: 9390 +Train: [40] [ 300/6250] eta: 0:20:59 lr: 0.000088 grad: 0.0802 (0.0878) loss: 0.8250 (0.8295) time: 0.2161 data: 0.1166 max mem: 9390 +Train: [40] [ 400/6250] eta: 0:20:51 lr: 0.000087 grad: 0.0721 (0.0866) loss: 0.8232 (0.8279) time: 0.2768 data: 0.1929 max mem: 9390 +Train: [40] [ 500/6250] eta: 0:19:53 lr: 0.000087 grad: 0.0703 (0.0849) loss: 0.8334 (0.8282) time: 0.1619 data: 0.0734 max mem: 9390 +Train: [40] [ 600/6250] eta: 0:19:07 lr: 0.000087 grad: 0.0753 (0.0832) loss: 0.8317 (0.8284) time: 0.1761 data: 0.0921 max mem: 9390 +Train: [40] [ 700/6250] eta: 0:18:26 lr: 0.000087 grad: 0.0798 (0.0824) loss: 0.8221 (0.8281) time: 0.2278 data: 0.1469 max mem: 9390 +Train: [40] [ 800/6250] eta: 0:17:59 lr: 0.000087 grad: 0.0788 (0.0820) loss: 0.8239 (0.8279) time: 0.2202 data: 0.1317 max mem: 9390 +Train: [40] [ 900/6250] eta: 0:17:25 lr: 0.000087 grad: 0.0772 (0.0816) loss: 0.8275 (0.8276) time: 0.1947 data: 0.0907 max mem: 9390 +Train: [40] [1000/6250] eta: 0:16:45 lr: 0.000087 grad: 0.0717 (0.0812) loss: 0.8291 (0.8276) time: 0.1497 data: 0.0701 max mem: 9390 +Train: [40] [1100/6250] eta: 0:16:15 lr: 0.000087 grad: 0.0809 (0.0812) loss: 0.8263 (0.8274) time: 0.1681 data: 0.0740 max mem: 9390 +Train: [40] [1200/6250] eta: 0:15:48 lr: 0.000087 grad: 0.0779 (0.0816) loss: 0.8181 (0.8270) time: 0.1685 data: 0.0696 max mem: 9390 +Train: [40] [1300/6250] eta: 0:15:21 lr: 0.000087 grad: 0.0740 (0.0814) loss: 0.8275 (0.8268) time: 0.1606 data: 0.0511 max mem: 9390 +Train: [40] [1400/6250] eta: 0:14:55 lr: 0.000087 grad: 0.0782 (0.0815) loss: 0.8253 (0.8264) time: 0.1602 data: 0.0729 max mem: 9390 +Train: [40] [1500/6250] eta: 0:14:35 lr: 0.000087 grad: 0.0772 (0.0815) loss: 0.8204 (0.8262) time: 0.1533 data: 0.0682 max mem: 9390 +Train: [40] [1600/6250] eta: 0:14:15 lr: 0.000087 grad: 0.0770 (0.0817) loss: 0.8223 (0.8261) time: 0.1799 data: 0.0959 max mem: 9390 +Train: [40] [1700/6250] eta: 0:13:56 lr: 0.000087 grad: 0.0769 (0.0816) loss: 0.8265 (0.8261) time: 0.1651 data: 0.0842 max mem: 9390 +Train: [40] [1800/6250] eta: 0:13:38 lr: 0.000087 grad: 0.0795 (0.0816) loss: 0.8313 (0.8261) time: 0.2022 data: 0.1213 max mem: 9390 +Train: [40] [1900/6250] eta: 0:13:22 lr: 0.000087 grad: 0.0760 (0.0816) loss: 0.8262 (0.8260) time: 0.2203 data: 0.1372 max mem: 9390 +Train: [40] [2000/6250] eta: 0:13:05 lr: 0.000087 grad: 0.0743 (0.0816) loss: 0.8281 (0.8260) time: 0.2031 data: 0.1262 max mem: 9390 +Train: [40] [2100/6250] eta: 0:12:56 lr: 0.000087 grad: 0.0800 (0.0815) loss: 0.8247 (0.8260) time: 0.2427 data: 0.1699 max mem: 9390 +Train: [40] [2200/6250] eta: 0:12:44 lr: 0.000087 grad: 0.0774 (0.0815) loss: 0.8259 (0.8259) time: 0.1992 data: 0.1180 max mem: 9390 +Train: [40] [2300/6250] eta: 0:12:28 lr: 0.000087 grad: 0.0782 (0.0815) loss: 0.8305 (0.8259) time: 0.2216 data: 0.1450 max mem: 9390 +Train: [40] [2400/6250] eta: 0:12:13 lr: 0.000087 grad: 0.0768 (0.0816) loss: 0.8255 (0.8259) time: 0.2067 data: 0.1297 max mem: 9390 +Train: [40] [2500/6250] eta: 0:11:56 lr: 0.000087 grad: 0.0783 (0.0816) loss: 0.8246 (0.8259) time: 0.1943 data: 0.1189 max mem: 9390 +Train: [40] [2600/6250] eta: 0:11:35 lr: 0.000087 grad: 0.0771 (0.0815) loss: 0.8268 (0.8258) time: 0.1463 data: 0.0615 max mem: 9390 +Train: [40] [2700/6250] eta: 0:11:12 lr: 0.000087 grad: 0.0808 (0.0816) loss: 0.8251 (0.8258) time: 0.1408 data: 0.0541 max mem: 9390 +Train: [40] [2800/6250] eta: 0:10:51 lr: 0.000087 grad: 0.0728 (0.0815) loss: 0.8286 (0.8258) time: 0.1517 data: 0.0663 max mem: 9390 +Train: [40] [2900/6250] eta: 0:10:30 lr: 0.000087 grad: 0.0770 (0.0814) loss: 0.8269 (0.8258) time: 0.1836 data: 0.0937 max mem: 9390 +Train: [40] [3000/6250] eta: 0:10:08 lr: 0.000087 grad: 0.0785 (0.0814) loss: 0.8288 (0.8259) time: 0.1550 data: 0.0649 max mem: 9390 +Train: [40] [3100/6250] eta: 0:09:48 lr: 0.000087 grad: 0.0778 (0.0813) loss: 0.8233 (0.8259) time: 0.1473 data: 0.0629 max mem: 9390 +Train: [40] [3200/6250] eta: 0:09:27 lr: 0.000087 grad: 0.0796 (0.0813) loss: 0.8303 (0.8259) time: 0.1703 data: 0.0777 max mem: 9390 +Train: [40] [3300/6250] eta: 0:09:07 lr: 0.000087 grad: 0.0758 (0.0812) loss: 0.8289 (0.8260) time: 0.1639 data: 0.0743 max mem: 9390 +Train: [40] [3400/6250] eta: 0:08:47 lr: 0.000087 grad: 0.0816 (0.0812) loss: 0.8278 (0.8260) time: 0.1972 data: 0.1126 max mem: 9390 +Train: [40] [3500/6250] eta: 0:08:27 lr: 0.000087 grad: 0.0768 (0.0813) loss: 0.8270 (0.8260) time: 0.1346 data: 0.0438 max mem: 9390 +Train: [40] [3600/6250] eta: 0:08:07 lr: 0.000087 grad: 0.0751 (0.0812) loss: 0.8324 (0.8261) time: 0.1854 data: 0.1005 max mem: 9390 +Train: [40] [3700/6250] eta: 0:07:48 lr: 0.000086 grad: 0.0734 (0.0811) loss: 0.8297 (0.8261) time: 0.1823 data: 0.1061 max mem: 9390 +Train: [40] [3800/6250] eta: 0:07:29 lr: 0.000086 grad: 0.0756 (0.0811) loss: 0.8267 (0.8262) time: 0.1729 data: 0.0793 max mem: 9390 +Train: [40] [3900/6250] eta: 0:07:10 lr: 0.000086 grad: 0.0791 (0.0811) loss: 0.8235 (0.8261) time: 0.1874 data: 0.0927 max mem: 9390 +Train: [40] [4000/6250] eta: 0:06:51 lr: 0.000086 grad: 0.0828 (0.0812) loss: 0.8255 (0.8261) time: 0.1686 data: 0.0801 max mem: 9390 +Train: [40] [4100/6250] eta: 0:06:33 lr: 0.000086 grad: 0.0828 (0.0812) loss: 0.8277 (0.8261) time: 0.1781 data: 0.0937 max mem: 9390 +Train: [40] [4200/6250] eta: 0:06:14 lr: 0.000086 grad: 0.0761 (0.0812) loss: 0.8267 (0.8261) time: 0.2008 data: 0.1028 max mem: 9390 +Train: [40] [4300/6250] eta: 0:05:56 lr: 0.000086 grad: 0.0830 (0.0813) loss: 0.8286 (0.8261) time: 0.1901 data: 0.1035 max mem: 9390 +Train: [40] [4400/6250] eta: 0:05:38 lr: 0.000086 grad: 0.0805 (0.0813) loss: 0.8202 (0.8261) time: 0.2255 data: 0.1434 max mem: 9390 +Train: [40] [4500/6250] eta: 0:05:19 lr: 0.000086 grad: 0.0780 (0.0814) loss: 0.8226 (0.8260) time: 0.1730 data: 0.0766 max mem: 9390 +Train: [40] [4600/6250] eta: 0:05:02 lr: 0.000086 grad: 0.0773 (0.0814) loss: 0.8227 (0.8260) time: 0.2490 data: 0.1536 max mem: 9390 +Train: [40] [4700/6250] eta: 0:04:43 lr: 0.000086 grad: 0.0828 (0.0815) loss: 0.8222 (0.8259) time: 0.1695 data: 0.0610 max mem: 9390 +Train: [40] [4800/6250] eta: 0:04:25 lr: 0.000086 grad: 0.0835 (0.0815) loss: 0.8234 (0.8259) time: 0.2020 data: 0.1153 max mem: 9390 +Train: [40] [4900/6250] eta: 0:04:07 lr: 0.000086 grad: 0.0841 (0.0815) loss: 0.8209 (0.8258) time: 0.2008 data: 0.1148 max mem: 9390 +Train: [40] [5000/6250] eta: 0:03:49 lr: 0.000086 grad: 0.0777 (0.0815) loss: 0.8275 (0.8258) time: 0.1875 data: 0.1011 max mem: 9390 +Train: [40] [5100/6250] eta: 0:03:30 lr: 0.000086 grad: 0.0862 (0.0816) loss: 0.8198 (0.8257) time: 0.1960 data: 0.1096 max mem: 9390 +Train: [40] [5200/6250] eta: 0:03:12 lr: 0.000086 grad: 0.0828 (0.0816) loss: 0.8229 (0.8257) time: 0.2533 data: 0.1679 max mem: 9390 +Train: [40] [5300/6250] eta: 0:02:54 lr: 0.000086 grad: 0.0817 (0.0817) loss: 0.8236 (0.8256) time: 0.1862 data: 0.1042 max mem: 9390 +Train: [40] [5400/6250] eta: 0:02:36 lr: 0.000086 grad: 0.0845 (0.0818) loss: 0.8217 (0.8255) time: 0.1682 data: 0.0782 max mem: 9390 +Train: [40] [5500/6250] eta: 0:02:17 lr: 0.000086 grad: 0.0844 (0.0819) loss: 0.8201 (0.8255) time: 0.1741 data: 0.0849 max mem: 9390 +Train: [40] [5600/6250] eta: 0:01:59 lr: 0.000086 grad: 0.0810 (0.0819) loss: 0.8224 (0.8254) time: 0.1733 data: 0.0859 max mem: 9390 +Train: [40] [5700/6250] eta: 0:01:41 lr: 0.000086 grad: 0.0839 (0.0819) loss: 0.8155 (0.8254) time: 0.2507 data: 0.1026 max mem: 9390 +Train: [40] [5800/6250] eta: 0:01:22 lr: 0.000086 grad: 0.0808 (0.0819) loss: 0.8246 (0.8253) time: 0.1947 data: 0.1166 max mem: 9390 +Train: [40] [5900/6250] eta: 0:01:04 lr: 0.000086 grad: 0.0808 (0.0819) loss: 0.8197 (0.8253) time: 0.1884 data: 0.1036 max mem: 9390 +Train: [40] [6000/6250] eta: 0:00:45 lr: 0.000086 grad: 0.0831 (0.0820) loss: 0.8255 (0.8253) time: 0.1576 data: 0.0690 max mem: 9390 +Train: [40] [6100/6250] eta: 0:00:27 lr: 0.000086 grad: 0.0840 (0.0820) loss: 0.8268 (0.8252) time: 0.1956 data: 0.1050 max mem: 9390 +Train: [40] [6200/6250] eta: 0:00:09 lr: 0.000086 grad: 0.0746 (0.0820) loss: 0.8274 (0.8252) time: 0.1538 data: 0.0592 max mem: 9390 +Train: [40] [6249/6250] eta: 0:00:00 lr: 0.000086 grad: 0.0810 (0.0821) loss: 0.8314 (0.8252) time: 0.1805 data: 0.0843 max mem: 9390 +Train: [40] Total time: 0:19:15 (0.1849 s / it) +Averaged stats: lr: 0.000086 grad: 0.0810 (0.0821) loss: 0.8314 (0.8252) +Eval (hcp-train-subset): [40] [ 0/62] eta: 0:06:20 loss: 0.8517 (0.8517) time: 6.1408 data: 6.0943 max mem: 9390 +Eval (hcp-train-subset): [40] [61/62] eta: 0:00:00 loss: 0.8409 (0.8415) time: 0.1101 data: 0.0850 max mem: 9390 +Eval (hcp-train-subset): [40] Total time: 0:00:15 (0.2541 s / it) +Averaged stats (hcp-train-subset): loss: 0.8409 (0.8415) +Eval (hcp-val): [40] [ 0/62] eta: 0:05:55 loss: 0.8335 (0.8335) time: 5.7330 data: 5.6461 max mem: 9390 +Eval (hcp-val): [40] [61/62] eta: 0:00:00 loss: 0.8354 (0.8369) time: 0.1547 data: 0.1288 max mem: 9390 +Eval (hcp-val): [40] Total time: 0:00:16 (0.2595 s / it) +Averaged stats (hcp-val): loss: 0.8354 (0.8369) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +Train: [41] [ 0/6250] eta: 8:59:21 lr: 0.000086 grad: 0.3019 (0.3019) loss: 0.8172 (0.8172) time: 5.1779 data: 4.9893 max mem: 9390 +Train: [41] [ 100/6250] eta: 0:26:24 lr: 0.000086 grad: 0.0849 (0.0937) loss: 0.8250 (0.8370) time: 0.1708 data: 0.0690 max mem: 9390 +Train: [41] [ 200/6250] eta: 0:22:25 lr: 0.000086 grad: 0.0802 (0.0919) loss: 0.8233 (0.8309) time: 0.1720 data: 0.0825 max mem: 9390 +Train: [41] [ 300/6250] eta: 0:20:58 lr: 0.000086 grad: 0.0780 (0.0877) loss: 0.8196 (0.8293) time: 0.1892 data: 0.0938 max mem: 9390 +Train: [41] [ 400/6250] eta: 0:19:59 lr: 0.000086 grad: 0.0737 (0.0856) loss: 0.8321 (0.8290) time: 0.1765 data: 0.0843 max mem: 9390 +Train: [41] [ 500/6250] eta: 0:19:18 lr: 0.000086 grad: 0.0784 (0.0841) loss: 0.8331 (0.8283) time: 0.1956 data: 0.1038 max mem: 9390 +Train: [41] [ 600/6250] eta: 0:18:42 lr: 0.000086 grad: 0.0745 (0.0826) loss: 0.8254 (0.8282) time: 0.1787 data: 0.0796 max mem: 9390 +Train: [41] [ 700/6250] eta: 0:18:18 lr: 0.000085 grad: 0.0730 (0.0819) loss: 0.8261 (0.8283) time: 0.2096 data: 0.1180 max mem: 9390 +Train: [41] [ 800/6250] eta: 0:17:45 lr: 0.000085 grad: 0.0691 (0.0811) loss: 0.8319 (0.8284) time: 0.2099 data: 0.1245 max mem: 9390 +Train: [41] [ 900/6250] eta: 0:17:29 lr: 0.000085 grad: 0.0795 (0.0805) loss: 0.8261 (0.8283) time: 0.1883 data: 0.1042 max mem: 9390 +Train: [41] [1000/6250] eta: 0:17:11 lr: 0.000085 grad: 0.0781 (0.0802) loss: 0.8272 (0.8283) time: 0.2141 data: 0.1346 max mem: 9390 +Train: [41] [1100/6250] eta: 0:17:01 lr: 0.000085 grad: 0.0729 (0.0797) loss: 0.8264 (0.8282) time: 0.1940 data: 0.1080 max mem: 9390 +Train: [41] [1200/6250] eta: 0:16:53 lr: 0.000085 grad: 0.0745 (0.0794) loss: 0.8285 (0.8281) time: 0.1962 data: 0.1108 max mem: 9390 +Train: [41] [1300/6250] eta: 0:16:32 lr: 0.000085 grad: 0.0725 (0.0790) loss: 0.8272 (0.8281) time: 0.1792 data: 0.0676 max mem: 9390 +Train: [41] [1400/6250] eta: 0:16:00 lr: 0.000085 grad: 0.0723 (0.0788) loss: 0.8278 (0.8281) time: 0.1646 data: 0.0824 max mem: 9390 +Train: [41] [1500/6250] eta: 0:15:34 lr: 0.000085 grad: 0.0744 (0.0788) loss: 0.8281 (0.8280) time: 0.1814 data: 0.0938 max mem: 9390 +Train: [41] [1600/6250] eta: 0:15:08 lr: 0.000085 grad: 0.0721 (0.0786) loss: 0.8308 (0.8279) time: 0.1811 data: 0.0942 max mem: 9390 +Train: [41] [1700/6250] eta: 0:14:44 lr: 0.000085 grad: 0.0711 (0.0785) loss: 0.8288 (0.8278) time: 0.1821 data: 0.0955 max mem: 9390 +Train: [41] [1800/6250] eta: 0:14:20 lr: 0.000085 grad: 0.0757 (0.0784) loss: 0.8241 (0.8277) time: 0.1583 data: 0.0692 max mem: 9390 +Train: [41] [1900/6250] eta: 0:14:01 lr: 0.000085 grad: 0.0795 (0.0785) loss: 0.8241 (0.8275) time: 0.1745 data: 0.0832 max mem: 9390 +Train: [41] [2000/6250] eta: 0:13:37 lr: 0.000085 grad: 0.0840 (0.0786) loss: 0.8246 (0.8273) time: 0.1662 data: 0.0783 max mem: 9390 +Train: [41] [2100/6250] eta: 0:13:14 lr: 0.000085 grad: 0.0742 (0.0786) loss: 0.8257 (0.8272) time: 0.1860 data: 0.1008 max mem: 9390 +Train: [41] [2200/6250] eta: 0:12:53 lr: 0.000085 grad: 0.0798 (0.0788) loss: 0.8182 (0.8270) time: 0.2086 data: 0.1218 max mem: 9390 +Train: [41] [2300/6250] eta: 0:12:29 lr: 0.000085 grad: 0.0750 (0.0788) loss: 0.8196 (0.8268) time: 0.1672 data: 0.0821 max mem: 9390 +Train: [41] [2400/6250] eta: 0:12:06 lr: 0.000085 grad: 0.0823 (0.0790) loss: 0.8185 (0.8266) time: 0.1374 data: 0.0450 max mem: 9390 +Train: [41] [2500/6250] eta: 0:11:46 lr: 0.000085 grad: 0.0747 (0.0791) loss: 0.8249 (0.8263) time: 0.1611 data: 0.0771 max mem: 9390 +Train: [41] [2600/6250] eta: 0:11:25 lr: 0.000085 grad: 0.0797 (0.0792) loss: 0.8208 (0.8262) time: 0.1588 data: 0.0589 max mem: 9390 +Train: [41] [2700/6250] eta: 0:11:05 lr: 0.000085 grad: 0.0800 (0.0794) loss: 0.8261 (0.8261) time: 0.1802 data: 0.1013 max mem: 9390 +Train: [41] [2800/6250] eta: 0:10:48 lr: 0.000085 grad: 0.0783 (0.0794) loss: 0.8158 (0.8259) time: 0.2849 data: 0.1972 max mem: 9390 +Train: [41] [2900/6250] eta: 0:10:27 lr: 0.000085 grad: 0.0775 (0.0795) loss: 0.8208 (0.8258) time: 0.1810 data: 0.0844 max mem: 9390 +Train: [41] [3000/6250] eta: 0:10:08 lr: 0.000085 grad: 0.0814 (0.0796) loss: 0.8210 (0.8256) time: 0.2114 data: 0.1283 max mem: 9390 +Train: [41] [3100/6250] eta: 0:09:50 lr: 0.000085 grad: 0.0815 (0.0797) loss: 0.8210 (0.8255) time: 0.2065 data: 0.1174 max mem: 9390 +Train: [41] [3200/6250] eta: 0:09:35 lr: 0.000085 grad: 0.0765 (0.0799) loss: 0.8264 (0.8254) time: 0.2470 data: 0.1533 max mem: 9390 +Train: [41] [3300/6250] eta: 0:09:18 lr: 0.000085 grad: 0.0825 (0.0802) loss: 0.8225 (0.8253) time: 0.1598 data: 0.0689 max mem: 9390 +Train: [41] [3400/6250] eta: 0:09:03 lr: 0.000085 grad: 0.0825 (0.0803) loss: 0.8205 (0.8252) time: 0.2822 data: 0.1887 max mem: 9390 +Train: [41] [3500/6250] eta: 0:08:43 lr: 0.000085 grad: 0.0826 (0.0804) loss: 0.8298 (0.8252) time: 0.1286 data: 0.0384 max mem: 9390 +Train: [41] [3600/6250] eta: 0:08:24 lr: 0.000085 grad: 0.0803 (0.0805) loss: 0.8208 (0.8251) time: 0.1777 data: 0.0931 max mem: 9390 +Train: [41] [3700/6250] eta: 0:08:06 lr: 0.000085 grad: 0.0830 (0.0806) loss: 0.8200 (0.8251) time: 0.0973 data: 0.0002 max mem: 9390 +Train: [41] [3800/6250] eta: 0:07:48 lr: 0.000085 grad: 0.0867 (0.0807) loss: 0.8219 (0.8251) time: 0.2194 data: 0.1307 max mem: 9390 +Train: [41] [3900/6250] eta: 0:07:30 lr: 0.000084 grad: 0.0803 (0.0808) loss: 0.8247 (0.8250) time: 0.2806 data: 0.1853 max mem: 9390 +Train: [41] [4000/6250] eta: 0:07:09 lr: 0.000084 grad: 0.0822 (0.0808) loss: 0.8216 (0.8250) time: 0.1428 data: 0.0511 max mem: 9390 +Train: [41] [4100/6250] eta: 0:06:50 lr: 0.000084 grad: 0.0813 (0.0809) loss: 0.8256 (0.8251) time: 0.1818 data: 0.0817 max mem: 9390 +Train: [41] [4200/6250] eta: 0:06:31 lr: 0.000084 grad: 0.0789 (0.0809) loss: 0.8295 (0.8251) time: 0.1746 data: 0.0767 max mem: 9390 +Train: [41] [4300/6250] eta: 0:06:12 lr: 0.000084 grad: 0.0812 (0.0810) loss: 0.8241 (0.8251) time: 0.2019 data: 0.1212 max mem: 9390 +Train: [41] [4400/6250] eta: 0:05:53 lr: 0.000084 grad: 0.0796 (0.0810) loss: 0.8253 (0.8251) time: 0.1746 data: 0.0826 max mem: 9390 +Train: [41] [4500/6250] eta: 0:05:34 lr: 0.000084 grad: 0.0807 (0.0810) loss: 0.8244 (0.8251) time: 0.2131 data: 0.1209 max mem: 9390 +Train: [41] [4600/6250] eta: 0:05:16 lr: 0.000084 grad: 0.0758 (0.0810) loss: 0.8201 (0.8251) time: 0.3260 data: 0.2232 max mem: 9390 +Train: [41] [4700/6250] eta: 0:04:56 lr: 0.000084 grad: 0.0805 (0.0811) loss: 0.8289 (0.8251) time: 0.1985 data: 0.1127 max mem: 9390 +Train: [41] [4800/6250] eta: 0:04:36 lr: 0.000084 grad: 0.0809 (0.0813) loss: 0.8257 (0.8251) time: 0.1677 data: 0.0669 max mem: 9390 +Train: [41] [4900/6250] eta: 0:04:18 lr: 0.000084 grad: 0.0806 (0.0812) loss: 0.8217 (0.8251) time: 0.2159 data: 0.1314 max mem: 9390 +Train: [41] [5000/6250] eta: 0:03:59 lr: 0.000084 grad: 0.0764 (0.0813) loss: 0.8262 (0.8251) time: 0.1935 data: 0.1049 max mem: 9390 +Train: [41] [5100/6250] eta: 0:03:40 lr: 0.000084 grad: 0.0816 (0.0814) loss: 0.8291 (0.8251) time: 0.2081 data: 0.1061 max mem: 9390 +Train: [41] [5200/6250] eta: 0:03:21 lr: 0.000084 grad: 0.0801 (0.0814) loss: 0.8212 (0.8251) time: 0.1193 data: 0.0335 max mem: 9390 +Train: [41] [5300/6250] eta: 0:03:02 lr: 0.000084 grad: 0.0824 (0.0814) loss: 0.8196 (0.8251) time: 0.1712 data: 0.0882 max mem: 9390 +Train: [41] [5400/6250] eta: 0:02:42 lr: 0.000084 grad: 0.0801 (0.0815) loss: 0.8246 (0.8250) time: 0.1596 data: 0.0787 max mem: 9390 +Train: [41] [5500/6250] eta: 0:02:23 lr: 0.000084 grad: 0.0809 (0.0815) loss: 0.8289 (0.8251) time: 0.2007 data: 0.1193 max mem: 9390 +Train: [41] [5600/6250] eta: 0:02:04 lr: 0.000084 grad: 0.0777 (0.0816) loss: 0.8286 (0.8251) time: 0.1876 data: 0.1036 max mem: 9390 +Train: [41] [5700/6250] eta: 0:01:45 lr: 0.000084 grad: 0.0854 (0.0817) loss: 0.8220 (0.8250) time: 0.2890 data: 0.1782 max mem: 9390 +Train: [41] [5800/6250] eta: 0:01:26 lr: 0.000084 grad: 0.0836 (0.0817) loss: 0.8259 (0.8250) time: 0.2561 data: 0.1773 max mem: 9390 +Train: [41] [5900/6250] eta: 0:01:07 lr: 0.000084 grad: 0.0816 (0.0817) loss: 0.8188 (0.8250) time: 0.2004 data: 0.1153 max mem: 9390 +Train: [41] [6000/6250] eta: 0:00:48 lr: 0.000084 grad: 0.0804 (0.0817) loss: 0.8269 (0.8250) time: 0.2108 data: 0.1234 max mem: 9390 +Train: [41] [6100/6250] eta: 0:00:28 lr: 0.000084 grad: 0.0829 (0.0818) loss: 0.8197 (0.8250) time: 0.1772 data: 0.0951 max mem: 9390 +Train: [41] [6200/6250] eta: 0:00:09 lr: 0.000084 grad: 0.0778 (0.0818) loss: 0.8182 (0.8249) time: 0.1676 data: 0.0850 max mem: 9390 +Train: [41] [6249/6250] eta: 0:00:00 lr: 0.000084 grad: 0.0834 (0.0818) loss: 0.8217 (0.8249) time: 0.1684 data: 0.0824 max mem: 9390 +Train: [41] Total time: 0:20:12 (0.1940 s / it) +Averaged stats: lr: 0.000084 grad: 0.0834 (0.0818) loss: 0.8217 (0.8249) +Eval (hcp-train-subset): [41] [ 0/62] eta: 0:06:54 loss: 0.8551 (0.8551) time: 6.6856 data: 6.6552 max mem: 9390 +Eval (hcp-train-subset): [41] [61/62] eta: 0:00:00 loss: 0.8386 (0.8406) time: 0.1459 data: 0.1174 max mem: 9390 +Eval (hcp-train-subset): [41] Total time: 0:00:16 (0.2629 s / it) +Averaged stats (hcp-train-subset): loss: 0.8386 (0.8406) +Eval (hcp-val): [41] [ 0/62] eta: 0:05:03 loss: 0.8345 (0.8345) time: 4.8931 data: 4.7987 max mem: 9390 +Eval (hcp-val): [41] [61/62] eta: 0:00:00 loss: 0.8377 (0.8386) time: 0.1271 data: 0.1022 max mem: 9390 +Eval (hcp-val): [41] Total time: 0:00:14 (0.2348 s / it) +Averaged stats (hcp-val): loss: 0.8377 (0.8386) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +Train: [42] [ 0/6250] eta: 12:31:00 lr: 0.000084 grad: 0.1588 (0.1588) loss: 0.8120 (0.8120) time: 7.2098 data: 7.0781 max mem: 9390 +Train: [42] [ 100/6250] eta: 0:26:08 lr: 0.000084 grad: 0.0803 (0.1108) loss: 0.8260 (0.8262) time: 0.1873 data: 0.0924 max mem: 9390 +Train: [42] [ 200/6250] eta: 0:23:54 lr: 0.000084 grad: 0.0804 (0.0976) loss: 0.8359 (0.8268) time: 0.1762 data: 0.0785 max mem: 9390 +Train: [42] [ 300/6250] eta: 0:21:45 lr: 0.000084 grad: 0.0777 (0.0912) loss: 0.8300 (0.8278) time: 0.1792 data: 0.0819 max mem: 9390 +Train: [42] [ 400/6250] eta: 0:20:43 lr: 0.000084 grad: 0.0741 (0.0879) loss: 0.8311 (0.8277) time: 0.1915 data: 0.0857 max mem: 9390 +Train: [42] [ 500/6250] eta: 0:19:59 lr: 0.000084 grad: 0.0719 (0.0858) loss: 0.8381 (0.8280) time: 0.2065 data: 0.1108 max mem: 9390 +Train: [42] [ 600/6250] eta: 0:19:15 lr: 0.000084 grad: 0.0731 (0.0842) loss: 0.8378 (0.8288) time: 0.1661 data: 0.0585 max mem: 9390 +Train: [42] [ 700/6250] eta: 0:18:43 lr: 0.000084 grad: 0.0779 (0.0830) loss: 0.8244 (0.8289) time: 0.1738 data: 0.0654 max mem: 9390 +Train: [42] [ 800/6250] eta: 0:18:01 lr: 0.000084 grad: 0.0775 (0.0825) loss: 0.8332 (0.8289) time: 0.1626 data: 0.0620 max mem: 9390 +Train: [42] [ 900/6250] eta: 0:17:45 lr: 0.000083 grad: 0.0834 (0.0823) loss: 0.8217 (0.8286) time: 0.2061 data: 0.1185 max mem: 9390 +Train: [42] [1000/6250] eta: 0:17:36 lr: 0.000083 grad: 0.0742 (0.0817) loss: 0.8267 (0.8286) time: 0.2209 data: 0.1402 max mem: 9390 +Train: [42] [1100/6250] eta: 0:17:49 lr: 0.000083 grad: 0.0797 (0.0813) loss: 0.8214 (0.8285) time: 0.4867 data: 0.4082 max mem: 9390 +Train: [42] [1200/6250] eta: 0:17:18 lr: 0.000083 grad: 0.0763 (0.0811) loss: 0.8242 (0.8284) time: 0.1916 data: 0.0829 max mem: 9390 +Train: [42] [1300/6250] eta: 0:16:50 lr: 0.000083 grad: 0.0768 (0.0811) loss: 0.8259 (0.8283) time: 0.2236 data: 0.1377 max mem: 9390 +Train: [42] [1400/6250] eta: 0:16:22 lr: 0.000083 grad: 0.0779 (0.0811) loss: 0.8220 (0.8282) time: 0.2028 data: 0.1231 max mem: 9390 +Train: [42] [1500/6250] eta: 0:15:55 lr: 0.000083 grad: 0.0800 (0.0810) loss: 0.8241 (0.8280) time: 0.1746 data: 0.0873 max mem: 9390 +Train: [42] [1600/6250] eta: 0:15:41 lr: 0.000083 grad: 0.0778 (0.0811) loss: 0.8257 (0.8279) time: 0.2035 data: 0.1184 max mem: 9390 +Train: [42] [1700/6250] eta: 0:15:18 lr: 0.000083 grad: 0.0744 (0.0812) loss: 0.8298 (0.8278) time: 0.1496 data: 0.0659 max mem: 9390 +Train: [42] [1800/6250] eta: 0:14:52 lr: 0.000083 grad: 0.0790 (0.0812) loss: 0.8226 (0.8277) time: 0.2008 data: 0.1048 max mem: 9390 +Train: [42] [1900/6250] eta: 0:14:27 lr: 0.000083 grad: 0.0816 (0.0814) loss: 0.8269 (0.8276) time: 0.1477 data: 0.0591 max mem: 9390 +Train: [42] [2000/6250] eta: 0:14:01 lr: 0.000083 grad: 0.0796 (0.0814) loss: 0.8267 (0.8274) time: 0.1514 data: 0.0676 max mem: 9390 +Train: [42] [2100/6250] eta: 0:13:42 lr: 0.000083 grad: 0.0801 (0.0815) loss: 0.8257 (0.8274) time: 0.2392 data: 0.1595 max mem: 9390 +Train: [42] [2200/6250] eta: 0:13:17 lr: 0.000083 grad: 0.0805 (0.0815) loss: 0.8275 (0.8274) time: 0.1716 data: 0.0808 max mem: 9390 +Train: [42] [2300/6250] eta: 0:12:55 lr: 0.000083 grad: 0.0745 (0.0815) loss: 0.8304 (0.8273) time: 0.2069 data: 0.1256 max mem: 9390 +Train: [42] [2400/6250] eta: 0:12:35 lr: 0.000083 grad: 0.0800 (0.0816) loss: 0.8250 (0.8272) time: 0.2269 data: 0.1432 max mem: 9390 +Train: [42] [2500/6250] eta: 0:12:13 lr: 0.000083 grad: 0.0863 (0.0817) loss: 0.8222 (0.8271) time: 0.1530 data: 0.0589 max mem: 9390 +Train: [42] [2600/6250] eta: 0:11:52 lr: 0.000083 grad: 0.0803 (0.0818) loss: 0.8230 (0.8271) time: 0.2061 data: 0.1279 max mem: 9390 +Train: [42] [2700/6250] eta: 0:11:29 lr: 0.000083 grad: 0.0732 (0.0817) loss: 0.8231 (0.8270) time: 0.1866 data: 0.1033 max mem: 9390 +Train: [42] [2800/6250] eta: 0:11:08 lr: 0.000083 grad: 0.0795 (0.0819) loss: 0.8259 (0.8268) time: 0.1561 data: 0.0507 max mem: 9390 +Train: [42] [2900/6250] eta: 0:10:48 lr: 0.000083 grad: 0.0814 (0.0819) loss: 0.8252 (0.8268) time: 0.1912 data: 0.0980 max mem: 9390 +Train: [42] [3000/6250] eta: 0:10:27 lr: 0.000083 grad: 0.0829 (0.0819) loss: 0.8193 (0.8267) time: 0.1582 data: 0.0595 max mem: 9390 +Train: [42] [3100/6250] eta: 0:10:05 lr: 0.000083 grad: 0.0817 (0.0820) loss: 0.8302 (0.8266) time: 0.1753 data: 0.0900 max mem: 9390 +Train: [42] [3200/6250] eta: 0:09:44 lr: 0.000083 grad: 0.0844 (0.0820) loss: 0.8223 (0.8265) time: 0.1912 data: 0.0998 max mem: 9390 +Train: [42] [3300/6250] eta: 0:09:24 lr: 0.000083 grad: 0.0930 (0.0822) loss: 0.8180 (0.8263) time: 0.1775 data: 0.0866 max mem: 9390 +Train: [42] [3400/6250] eta: 0:09:06 lr: 0.000083 grad: 0.0877 (0.0823) loss: 0.8152 (0.8262) time: 0.2249 data: 0.1423 max mem: 9390 +Train: [42] [3500/6250] eta: 0:08:44 lr: 0.000083 grad: 0.0792 (0.0824) loss: 0.8212 (0.8260) time: 0.1776 data: 0.0899 max mem: 9390 +Train: [42] [3600/6250] eta: 0:08:24 lr: 0.000083 grad: 0.0805 (0.0825) loss: 0.8224 (0.8258) time: 0.1588 data: 0.0677 max mem: 9390 +Train: [42] [3700/6250] eta: 0:08:05 lr: 0.000083 grad: 0.0858 (0.0826) loss: 0.8208 (0.8256) time: 0.1999 data: 0.1154 max mem: 9390 +Train: [42] [3800/6250] eta: 0:07:46 lr: 0.000083 grad: 0.0830 (0.0827) loss: 0.8233 (0.8254) time: 0.1441 data: 0.0519 max mem: 9390 +Train: [42] [3900/6250] eta: 0:07:28 lr: 0.000083 grad: 0.0814 (0.0828) loss: 0.8198 (0.8252) time: 0.2180 data: 0.1366 max mem: 9390 +Train: [42] [4000/6250] eta: 0:07:10 lr: 0.000083 grad: 0.0948 (0.0830) loss: 0.8116 (0.8250) time: 0.1708 data: 0.0802 max mem: 9390 +Train: [42] [4100/6250] eta: 0:06:53 lr: 0.000082 grad: 0.0890 (0.0831) loss: 0.8175 (0.8248) time: 0.2796 data: 0.1939 max mem: 9390 +Train: [42] [4200/6250] eta: 0:06:34 lr: 0.000082 grad: 0.0802 (0.0831) loss: 0.8301 (0.8247) time: 0.2306 data: 0.1447 max mem: 9390 +Train: [42] [4300/6250] eta: 0:06:15 lr: 0.000082 grad: 0.0851 (0.0832) loss: 0.8161 (0.8246) time: 0.2136 data: 0.1329 max mem: 9390 +Train: [42] [4400/6250] eta: 0:05:57 lr: 0.000082 grad: 0.0833 (0.0832) loss: 0.8274 (0.8245) time: 0.3629 data: 0.2814 max mem: 9390 +Train: [42] [4500/6250] eta: 0:05:38 lr: 0.000082 grad: 0.0813 (0.0832) loss: 0.8222 (0.8245) time: 0.2822 data: 0.1786 max mem: 9390 +Train: [42] [4600/6250] eta: 0:05:19 lr: 0.000082 grad: 0.0838 (0.0832) loss: 0.8172 (0.8244) time: 0.2184 data: 0.1310 max mem: 9390 +Train: [42] [4700/6250] eta: 0:05:00 lr: 0.000082 grad: 0.0752 (0.0831) loss: 0.8198 (0.8244) time: 0.2542 data: 0.1706 max mem: 9390 +Train: [42] [4800/6250] eta: 0:04:40 lr: 0.000082 grad: 0.0807 (0.0831) loss: 0.8247 (0.8243) time: 0.1458 data: 0.0530 max mem: 9390 +Train: [42] [4900/6250] eta: 0:04:21 lr: 0.000082 grad: 0.0862 (0.0831) loss: 0.8255 (0.8243) time: 0.1914 data: 0.1078 max mem: 9390 +Train: [42] [5000/6250] eta: 0:04:02 lr: 0.000082 grad: 0.0821 (0.0831) loss: 0.8232 (0.8243) time: 0.1782 data: 0.0989 max mem: 9390 +Train: [42] [5100/6250] eta: 0:03:43 lr: 0.000082 grad: 0.0812 (0.0831) loss: 0.8247 (0.8243) time: 0.2055 data: 0.1159 max mem: 9390 +Train: [42] [5200/6250] eta: 0:03:23 lr: 0.000082 grad: 0.0771 (0.0831) loss: 0.8254 (0.8243) time: 0.2165 data: 0.1316 max mem: 9390 +Train: [42] [5300/6250] eta: 0:03:04 lr: 0.000082 grad: 0.0816 (0.0831) loss: 0.8274 (0.8243) time: 0.1568 data: 0.0731 max mem: 9390 +Train: [42] [5400/6250] eta: 0:02:45 lr: 0.000082 grad: 0.0820 (0.0832) loss: 0.8217 (0.8242) time: 0.2149 data: 0.1272 max mem: 9390 +Train: [42] [5500/6250] eta: 0:02:26 lr: 0.000082 grad: 0.0903 (0.0833) loss: 0.8200 (0.8242) time: 0.3217 data: 0.2081 max mem: 9390 +Train: [42] [5600/6250] eta: 0:02:06 lr: 0.000082 grad: 0.0866 (0.0834) loss: 0.8228 (0.8242) time: 0.1935 data: 0.1124 max mem: 9390 +Train: [42] [5700/6250] eta: 0:01:47 lr: 0.000082 grad: 0.0790 (0.0834) loss: 0.8202 (0.8242) time: 0.1926 data: 0.0964 max mem: 9390 +Train: [42] [5800/6250] eta: 0:01:27 lr: 0.000082 grad: 0.0807 (0.0834) loss: 0.8250 (0.8242) time: 0.1589 data: 0.0643 max mem: 9390 +Train: [42] [5900/6250] eta: 0:01:08 lr: 0.000082 grad: 0.0788 (0.0834) loss: 0.8254 (0.8242) time: 0.1952 data: 0.1095 max mem: 9390 +Train: [42] [6000/6250] eta: 0:00:48 lr: 0.000082 grad: 0.0851 (0.0834) loss: 0.8206 (0.8242) time: 0.1752 data: 0.0860 max mem: 9390 +Train: [42] [6100/6250] eta: 0:00:29 lr: 0.000082 grad: 0.0803 (0.0834) loss: 0.8267 (0.8241) time: 0.1279 data: 0.0365 max mem: 9390 +Train: [42] [6200/6250] eta: 0:00:09 lr: 0.000082 grad: 0.0852 (0.0835) loss: 0.8225 (0.8241) time: 0.1744 data: 0.0886 max mem: 9390 +Train: [42] [6249/6250] eta: 0:00:00 lr: 0.000082 grad: 0.0843 (0.0835) loss: 0.8210 (0.8241) time: 0.1677 data: 0.0740 max mem: 9390 +Train: [42] Total time: 0:20:23 (0.1958 s / it) +Averaged stats: lr: 0.000082 grad: 0.0843 (0.0835) loss: 0.8210 (0.8241) +Eval (hcp-train-subset): [42] [ 0/62] eta: 0:05:55 loss: 0.8517 (0.8517) time: 5.7381 data: 5.6897 max mem: 9390 +Eval (hcp-train-subset): [42] [61/62] eta: 0:00:00 loss: 0.8372 (0.8403) time: 0.1195 data: 0.0941 max mem: 9390 +Eval (hcp-train-subset): [42] Total time: 0:00:15 (0.2486 s / it) +Averaged stats (hcp-train-subset): loss: 0.8372 (0.8403) +Eval (hcp-val): [42] [ 0/62] eta: 0:05:37 loss: 0.8407 (0.8407) time: 5.4393 data: 5.3960 max mem: 9390 +Eval (hcp-val): [42] [61/62] eta: 0:00:00 loss: 0.8361 (0.8372) time: 0.1663 data: 0.1389 max mem: 9390 +Eval (hcp-val): [42] Total time: 0:00:15 (0.2509 s / it) +Averaged stats (hcp-val): loss: 0.8361 (0.8372) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +Train: [43] [ 0/6250] eta: 11:32:58 lr: 0.000082 grad: 0.0921 (0.0921) loss: 0.8181 (0.8181) time: 6.6526 data: 6.5148 max mem: 9390 +Train: [43] [ 100/6250] eta: 0:25:47 lr: 0.000082 grad: 0.0748 (0.0937) loss: 0.8300 (0.8334) time: 0.2060 data: 0.1005 max mem: 9390 +Train: [43] [ 200/6250] eta: 0:22:19 lr: 0.000082 grad: 0.0764 (0.0861) loss: 0.8369 (0.8322) time: 0.1915 data: 0.1002 max mem: 9390 +Train: [43] [ 300/6250] eta: 0:21:18 lr: 0.000082 grad: 0.0732 (0.0830) loss: 0.8286 (0.8319) time: 0.2031 data: 0.1045 max mem: 9390 +Train: [43] [ 400/6250] eta: 0:20:11 lr: 0.000082 grad: 0.0743 (0.0822) loss: 0.8319 (0.8309) time: 0.1722 data: 0.0860 max mem: 9390 +Train: [43] [ 500/6250] eta: 0:19:28 lr: 0.000082 grad: 0.0795 (0.0820) loss: 0.8262 (0.8294) time: 0.2247 data: 0.1287 max mem: 9390 +Train: [43] [ 600/6250] eta: 0:18:43 lr: 0.000082 grad: 0.0788 (0.0819) loss: 0.8164 (0.8282) time: 0.1709 data: 0.0782 max mem: 9390 +Train: [43] [ 700/6250] eta: 0:18:12 lr: 0.000082 grad: 0.0831 (0.0818) loss: 0.8300 (0.8280) time: 0.2015 data: 0.1090 max mem: 9390 +Train: [43] [ 800/6250] eta: 0:17:37 lr: 0.000082 grad: 0.0759 (0.0818) loss: 0.8230 (0.8273) time: 0.1588 data: 0.0613 max mem: 9390 +Train: [43] [ 900/6250] eta: 0:17:13 lr: 0.000082 grad: 0.0869 (0.0821) loss: 0.8106 (0.8266) time: 0.1577 data: 0.0699 max mem: 9390 +Train: [43] [1000/6250] eta: 0:16:52 lr: 0.000081 grad: 0.0805 (0.0824) loss: 0.8246 (0.8260) time: 0.2191 data: 0.1411 max mem: 9390 +Train: [43] [1100/6250] eta: 0:16:25 lr: 0.000081 grad: 0.0842 (0.0825) loss: 0.8224 (0.8255) time: 0.1715 data: 0.0873 max mem: 9390 +Train: [43] [1200/6250] eta: 0:16:09 lr: 0.000081 grad: 0.0784 (0.0825) loss: 0.8249 (0.8253) time: 0.2104 data: 0.1356 max mem: 9390 +Train: [43] [1300/6250] eta: 0:15:57 lr: 0.000081 grad: 0.0828 (0.0826) loss: 0.8258 (0.8251) time: 0.2220 data: 0.1464 max mem: 9390 +Train: [43] [1400/6250] eta: 0:15:43 lr: 0.000081 grad: 0.0829 (0.0826) loss: 0.8260 (0.8249) time: 0.2095 data: 0.1301 max mem: 9390 +Train: [43] [1500/6250] eta: 0:15:19 lr: 0.000081 grad: 0.0833 (0.0827) loss: 0.8239 (0.8246) time: 0.1750 data: 0.0890 max mem: 9390 +Train: [43] [1600/6250] eta: 0:14:53 lr: 0.000081 grad: 0.0814 (0.0828) loss: 0.8247 (0.8245) time: 0.1835 data: 0.0935 max mem: 9390 +Train: [43] [1700/6250] eta: 0:14:24 lr: 0.000081 grad: 0.0851 (0.0829) loss: 0.8202 (0.8243) time: 0.1641 data: 0.0703 max mem: 9390 +Train: [43] [1800/6250] eta: 0:13:59 lr: 0.000081 grad: 0.0821 (0.0829) loss: 0.8212 (0.8242) time: 0.1508 data: 0.0607 max mem: 9390 +Train: [43] [1900/6250] eta: 0:13:34 lr: 0.000081 grad: 0.0763 (0.0830) loss: 0.8235 (0.8240) time: 0.1064 data: 0.0149 max mem: 9390 +Train: [43] [2000/6250] eta: 0:13:12 lr: 0.000081 grad: 0.0789 (0.0830) loss: 0.8250 (0.8239) time: 0.1936 data: 0.1034 max mem: 9390 +Train: [43] [2100/6250] eta: 0:12:49 lr: 0.000081 grad: 0.0857 (0.0830) loss: 0.8153 (0.8237) time: 0.1653 data: 0.0790 max mem: 9390 +Train: [43] [2200/6250] eta: 0:12:32 lr: 0.000081 grad: 0.0798 (0.0830) loss: 0.8232 (0.8237) time: 0.2156 data: 0.1128 max mem: 9390 +Train: [43] [2300/6250] eta: 0:12:10 lr: 0.000081 grad: 0.0767 (0.0830) loss: 0.8245 (0.8237) time: 0.1628 data: 0.0766 max mem: 9390 +Train: [43] [2400/6250] eta: 0:11:49 lr: 0.000081 grad: 0.0808 (0.0833) loss: 0.8298 (0.8237) time: 0.1838 data: 0.1026 max mem: 9390 +Train: [43] [2500/6250] eta: 0:11:28 lr: 0.000081 grad: 0.0792 (0.0832) loss: 0.8218 (0.8238) time: 0.1552 data: 0.0709 max mem: 9390 +Train: [43] [2600/6250] eta: 0:11:11 lr: 0.000081 grad: 0.0758 (0.0831) loss: 0.8241 (0.8239) time: 0.2472 data: 0.1580 max mem: 9390 +Train: [43] [2700/6250] eta: 0:10:49 lr: 0.000081 grad: 0.0763 (0.0832) loss: 0.8314 (0.8240) time: 0.1431 data: 0.0611 max mem: 9390 +Train: [43] [2800/6250] eta: 0:10:30 lr: 0.000081 grad: 0.0768 (0.0832) loss: 0.8226 (0.8240) time: 0.1825 data: 0.0984 max mem: 9390 +Train: [43] [2900/6250] eta: 0:10:10 lr: 0.000081 grad: 0.0743 (0.0831) loss: 0.8272 (0.8241) time: 0.1678 data: 0.0599 max mem: 9390 +Train: [43] [3000/6250] eta: 0:09:52 lr: 0.000081 grad: 0.0776 (0.0832) loss: 0.8245 (0.8241) time: 0.1904 data: 0.0972 max mem: 9390 +Train: [43] [3100/6250] eta: 0:09:33 lr: 0.000081 grad: 0.0764 (0.0832) loss: 0.8315 (0.8241) time: 0.1637 data: 0.0813 max mem: 9390 +Train: [43] [3200/6250] eta: 0:09:14 lr: 0.000081 grad: 0.0852 (0.0832) loss: 0.8208 (0.8240) time: 0.1384 data: 0.0458 max mem: 9390 +Train: [43] [3300/6250] eta: 0:08:57 lr: 0.000081 grad: 0.0817 (0.0832) loss: 0.8211 (0.8240) time: 0.2037 data: 0.1142 max mem: 9390 +Train: [43] [3400/6250] eta: 0:08:39 lr: 0.000081 grad: 0.0809 (0.0832) loss: 0.8269 (0.8240) time: 0.1818 data: 0.0956 max mem: 9390 +Train: [43] [3500/6250] eta: 0:08:23 lr: 0.000081 grad: 0.0866 (0.0833) loss: 0.8204 (0.8240) time: 0.2417 data: 0.1523 max mem: 9390 +Train: [43] [3600/6250] eta: 0:08:13 lr: 0.000081 grad: 0.0853 (0.0834) loss: 0.8232 (0.8239) time: 0.1825 data: 0.1050 max mem: 9390 +Train: [43] [3700/6250] eta: 0:07:54 lr: 0.000081 grad: 0.0764 (0.0833) loss: 0.8204 (0.8238) time: 0.1825 data: 0.1088 max mem: 9390 +Train: [43] [3800/6250] eta: 0:07:36 lr: 0.000081 grad: 0.0837 (0.0834) loss: 0.8243 (0.8237) time: 0.1658 data: 0.0873 max mem: 9390 +Train: [43] [3900/6250] eta: 0:07:16 lr: 0.000081 grad: 0.0824 (0.0835) loss: 0.8184 (0.8236) time: 0.1761 data: 0.0899 max mem: 9390 +Train: [43] [4000/6250] eta: 0:06:57 lr: 0.000081 grad: 0.0828 (0.0835) loss: 0.8237 (0.8236) time: 0.2067 data: 0.1208 max mem: 9390 +Train: [43] [4100/6250] eta: 0:06:38 lr: 0.000081 grad: 0.0772 (0.0836) loss: 0.8249 (0.8236) time: 0.1349 data: 0.0494 max mem: 9390 +Train: [43] [4200/6250] eta: 0:06:19 lr: 0.000080 grad: 0.0837 (0.0836) loss: 0.8243 (0.8236) time: 0.1723 data: 0.0854 max mem: 9390 +Train: [43] [4300/6250] eta: 0:06:00 lr: 0.000080 grad: 0.0820 (0.0837) loss: 0.8196 (0.8236) time: 0.1819 data: 0.0985 max mem: 9390 +Train: [43] [4400/6250] eta: 0:05:41 lr: 0.000080 grad: 0.0838 (0.0837) loss: 0.8255 (0.8236) time: 0.1423 data: 0.0588 max mem: 9390 +Train: [43] [4500/6250] eta: 0:05:22 lr: 0.000080 grad: 0.0854 (0.0837) loss: 0.8280 (0.8236) time: 0.1547 data: 0.0624 max mem: 9390 +Train: [43] [4600/6250] eta: 0:05:03 lr: 0.000080 grad: 0.0872 (0.0837) loss: 0.8186 (0.8236) time: 0.1849 data: 0.1039 max mem: 9390 +Train: [43] [4700/6250] eta: 0:04:44 lr: 0.000080 grad: 0.0821 (0.0837) loss: 0.8222 (0.8236) time: 0.1697 data: 0.0854 max mem: 9390 +Train: [43] [4800/6250] eta: 0:04:25 lr: 0.000080 grad: 0.0816 (0.0837) loss: 0.8258 (0.8236) time: 0.1692 data: 0.0772 max mem: 9390 +Train: [43] [4900/6250] eta: 0:04:06 lr: 0.000080 grad: 0.0796 (0.0838) loss: 0.8289 (0.8237) time: 0.1525 data: 0.0663 max mem: 9390 +Train: [43] [5000/6250] eta: 0:03:47 lr: 0.000080 grad: 0.0845 (0.0838) loss: 0.8264 (0.8237) time: 0.1597 data: 0.0697 max mem: 9390 +Train: [43] [5100/6250] eta: 0:03:29 lr: 0.000080 grad: 0.0842 (0.0839) loss: 0.8255 (0.8237) time: 0.1526 data: 0.0726 max mem: 9390 +Train: [43] [5200/6250] eta: 0:03:11 lr: 0.000080 grad: 0.0878 (0.0839) loss: 0.8235 (0.8237) time: 0.1951 data: 0.1165 max mem: 9390 +Train: [43] [5300/6250] eta: 0:02:52 lr: 0.000080 grad: 0.0818 (0.0840) loss: 0.8220 (0.8236) time: 0.1541 data: 0.0741 max mem: 9390 +Train: [43] [5400/6250] eta: 0:02:34 lr: 0.000080 grad: 0.0830 (0.0840) loss: 0.8194 (0.8235) time: 0.1764 data: 0.0941 max mem: 9390 +Train: [43] [5500/6250] eta: 0:02:16 lr: 0.000080 grad: 0.0825 (0.0841) loss: 0.8215 (0.8235) time: 0.1664 data: 0.0779 max mem: 9390 +Train: [43] [5600/6250] eta: 0:01:57 lr: 0.000080 grad: 0.0820 (0.0841) loss: 0.8191 (0.8234) time: 0.1743 data: 0.0866 max mem: 9390 +Train: [43] [5700/6250] eta: 0:01:39 lr: 0.000080 grad: 0.0864 (0.0841) loss: 0.8152 (0.8233) time: 0.1634 data: 0.0753 max mem: 9390 +Train: [43] [5800/6250] eta: 0:01:21 lr: 0.000080 grad: 0.0892 (0.0842) loss: 0.8175 (0.8233) time: 0.1631 data: 0.0707 max mem: 9390 +Train: [43] [5900/6250] eta: 0:01:03 lr: 0.000080 grad: 0.0834 (0.0842) loss: 0.8139 (0.8232) time: 0.1754 data: 0.0849 max mem: 9390 +Train: [43] [6000/6250] eta: 0:00:45 lr: 0.000080 grad: 0.0850 (0.0842) loss: 0.8224 (0.8232) time: 0.1798 data: 0.0840 max mem: 9390 +Train: [43] [6100/6250] eta: 0:00:27 lr: 0.000080 grad: 0.0842 (0.0842) loss: 0.8270 (0.8231) time: 0.1788 data: 0.0857 max mem: 9390 +Train: [43] [6200/6250] eta: 0:00:08 lr: 0.000080 grad: 0.0851 (0.0842) loss: 0.8208 (0.8231) time: 0.1489 data: 0.0565 max mem: 9390 +Train: [43] [6249/6250] eta: 0:00:00 lr: 0.000080 grad: 0.0811 (0.0842) loss: 0.8210 (0.8231) time: 0.1788 data: 0.0909 max mem: 9390 +Train: [43] Total time: 0:18:51 (0.1811 s / it) +Averaged stats: lr: 0.000080 grad: 0.0811 (0.0842) loss: 0.8210 (0.8231) +Eval (hcp-train-subset): [43] [ 0/62] eta: 0:04:45 loss: 0.8545 (0.8545) time: 4.6005 data: 4.5275 max mem: 9390 +Eval (hcp-train-subset): [43] [61/62] eta: 0:00:00 loss: 0.8408 (0.8402) time: 0.1187 data: 0.0907 max mem: 9390 +Eval (hcp-train-subset): [43] Total time: 0:00:14 (0.2335 s / it) +Averaged stats (hcp-train-subset): loss: 0.8408 (0.8402) +Eval (hcp-val): [43] [ 0/62] eta: 0:05:39 loss: 0.8349 (0.8349) time: 5.4717 data: 5.4420 max mem: 9390 +Eval (hcp-val): [43] [61/62] eta: 0:00:00 loss: 0.8340 (0.8366) time: 0.1223 data: 0.0951 max mem: 9390 +Eval (hcp-val): [43] Total time: 0:00:14 (0.2352 s / it) +Averaged stats (hcp-val): loss: 0.8340 (0.8366) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +Train: [44] [ 0/6250] eta: 10:30:47 lr: 0.000080 grad: 0.0681 (0.0681) loss: 0.8448 (0.8448) time: 6.0557 data: 5.9323 max mem: 9390 +Train: [44] [ 100/6250] eta: 0:21:55 lr: 0.000080 grad: 0.0740 (0.0826) loss: 0.8431 (0.8428) time: 0.1527 data: 0.0466 max mem: 9390 +Train: [44] [ 200/6250] eta: 0:19:02 lr: 0.000080 grad: 0.0823 (0.0836) loss: 0.8328 (0.8396) time: 0.1675 data: 0.0716 max mem: 9390 +Train: [44] [ 300/6250] eta: 0:18:10 lr: 0.000080 grad: 0.0781 (0.0835) loss: 0.8312 (0.8370) time: 0.1805 data: 0.0964 max mem: 9390 +Train: [44] [ 400/6250] eta: 0:17:31 lr: 0.000080 grad: 0.0845 (0.0828) loss: 0.8321 (0.8359) time: 0.1706 data: 0.0782 max mem: 9390 +Train: [44] [ 500/6250] eta: 0:16:45 lr: 0.000080 grad: 0.0766 (0.0823) loss: 0.8347 (0.8356) time: 0.1674 data: 0.0796 max mem: 9390 +Train: [44] [ 600/6250] eta: 0:16:11 lr: 0.000080 grad: 0.0791 (0.0819) loss: 0.8260 (0.8347) time: 0.1581 data: 0.0679 max mem: 9390 +Train: [44] [ 700/6250] eta: 0:15:46 lr: 0.000080 grad: 0.0766 (0.0815) loss: 0.8344 (0.8341) time: 0.1594 data: 0.0674 max mem: 9390 +Train: [44] [ 800/6250] eta: 0:15:20 lr: 0.000080 grad: 0.0751 (0.0813) loss: 0.8356 (0.8337) time: 0.1473 data: 0.0617 max mem: 9390 +Train: [44] [ 900/6250] eta: 0:15:02 lr: 0.000080 grad: 0.0755 (0.0810) loss: 0.8336 (0.8331) time: 0.1385 data: 0.0488 max mem: 9390 +Train: [44] [1000/6250] eta: 0:14:44 lr: 0.000080 grad: 0.0773 (0.0810) loss: 0.8239 (0.8327) time: 0.1733 data: 0.0968 max mem: 9390 +Train: [44] [1100/6250] eta: 0:14:16 lr: 0.000079 grad: 0.0769 (0.0811) loss: 0.8303 (0.8322) time: 0.1524 data: 0.0732 max mem: 9390 +Train: [44] [1200/6250] eta: 0:14:00 lr: 0.000079 grad: 0.0815 (0.0812) loss: 0.8188 (0.8316) time: 0.1664 data: 0.0893 max mem: 9390 +Train: [44] [1300/6250] eta: 0:13:44 lr: 0.000079 grad: 0.0795 (0.0816) loss: 0.8196 (0.8310) time: 0.1957 data: 0.1159 max mem: 9390 +Train: [44] [1400/6250] eta: 0:13:50 lr: 0.000079 grad: 0.0789 (0.0817) loss: 0.8209 (0.8304) time: 0.1748 data: 0.0972 max mem: 9390 +Train: [44] [1500/6250] eta: 0:13:44 lr: 0.000079 grad: 0.0798 (0.0817) loss: 0.8259 (0.8300) time: 0.1643 data: 0.0910 max mem: 9390 +Train: [44] [1600/6250] eta: 0:13:34 lr: 0.000079 grad: 0.0833 (0.0821) loss: 0.8155 (0.8294) time: 0.2222 data: 0.1479 max mem: 9390 +Train: [44] [1700/6250] eta: 0:13:21 lr: 0.000079 grad: 0.0852 (0.0822) loss: 0.8227 (0.8290) time: 0.1841 data: 0.1072 max mem: 9390 +Train: [44] [1800/6250] eta: 0:13:08 lr: 0.000079 grad: 0.0827 (0.0823) loss: 0.8193 (0.8285) time: 0.2090 data: 0.1342 max mem: 9390 +Train: [44] [1900/6250] eta: 0:12:51 lr: 0.000079 grad: 0.0837 (0.0824) loss: 0.8158 (0.8281) time: 0.1790 data: 0.1026 max mem: 9390 +Train: [44] [2000/6250] eta: 0:12:35 lr: 0.000079 grad: 0.0837 (0.0826) loss: 0.8239 (0.8277) time: 0.1630 data: 0.0860 max mem: 9390 +Train: [44] [2100/6250] eta: 0:12:16 lr: 0.000079 grad: 0.0837 (0.0828) loss: 0.8187 (0.8274) time: 0.1623 data: 0.0818 max mem: 9390 +Train: [44] [2200/6250] eta: 0:11:58 lr: 0.000079 grad: 0.0867 (0.0830) loss: 0.8224 (0.8271) time: 0.1599 data: 0.0787 max mem: 9390 +Train: [44] [2300/6250] eta: 0:11:36 lr: 0.000079 grad: 0.0895 (0.0832) loss: 0.8150 (0.8268) time: 0.1567 data: 0.0783 max mem: 9390 +Train: [44] [2400/6250] eta: 0:11:13 lr: 0.000079 grad: 0.0839 (0.0834) loss: 0.8211 (0.8266) time: 0.1246 data: 0.0445 max mem: 9390 +Train: [44] [2500/6250] eta: 0:10:51 lr: 0.000079 grad: 0.0914 (0.0836) loss: 0.8151 (0.8264) time: 0.1265 data: 0.0461 max mem: 9390 +Train: [44] [2600/6250] eta: 0:10:30 lr: 0.000079 grad: 0.0813 (0.0836) loss: 0.8256 (0.8262) time: 0.1537 data: 0.0707 max mem: 9390 +Train: [44] [2700/6250] eta: 0:10:10 lr: 0.000079 grad: 0.0800 (0.0836) loss: 0.8222 (0.8261) time: 0.1463 data: 0.0585 max mem: 9390 +Train: [44] [2800/6250] eta: 0:09:50 lr: 0.000079 grad: 0.0846 (0.0835) loss: 0.8286 (0.8260) time: 0.1420 data: 0.0585 max mem: 9390 +Train: [44] [2900/6250] eta: 0:09:31 lr: 0.000079 grad: 0.0755 (0.0835) loss: 0.8267 (0.8259) time: 0.1575 data: 0.0738 max mem: 9390 +pretraining fmri mae +start: 2026-04-02 20:43:07 +cwd: /data/connor/fmri-fm +sha: bcce2b486277d3a5b520775efd9cdf1a2affce36, status: has uncommitted changes, branch: dev/clane9 +config: +name: input_space_v3/flat_lr1e-3_6/pretrain +notes: input_space ablation v3 flat_lr1e-3_6; use tube masking and on-disk data (input_space=flat + base_lr=1e-3 seed=5406) +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain +input_space: flat +patch_size: 16 +num_frames: 16 +t_patch_size: 4 +mask_ratio: 0.9 +pred_mask_ratio: null +masking: tube +masking_kwargs: {} +mask_patch_size: null +model: mae_vit_base +model_kwargs: + decoding: attn + pos_embed: sep + target_norm: null + pca_norm_nc: 2 + t_pred_stride: 2 + no_decode_pos: true + mask_drop_scale: false + pred_edge_pad: 0 + gauss_sigma: null + class_token: true + reg_tokens: 0 + no_embed_class: true + head_init_scale: 0.0 + decoder_depth: 4 + drop_path_rate: 0.0 +datasets: + hcp-train: + type: wds + url: /data/fmri-datasets/pretrain/hcpya-all.${input_space}.wds/hcpya-all-${input_space}-{00000..01799}.tar + clipping: random + clipping_kwargs: + oversample: 4.0 + shuffle: true + buffer_size: 2000 + samples_per_epoch: 200000 + hcp-train-subset: + type: arrow + root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/validation + split_range: + - 0 + - 2000 + shuffle: false + hcp-val: + type: arrow + root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/test + split_range: + - 0 + - 2000 + shuffle: false +train_dataset: hcp-train +eval_datasets: +- hcp-train-subset +- hcp-val +val_dataset: null +clip_vmax: 3.0 +normalize: frame +tr_scale: null +crop_scale: null +crop_aspect: null +gray_jitter: null +num_workers: 16 +epochs: 100 +batch_size: 32 +accum_iter: 1 +base_lr: 0.001 +min_lr: 0.0 +warmup_epochs: 5 +weight_decay: 0.05 +betas: +- 0.9 +- 0.95 +clip_grad: 1.0 +amp: true +amp_dtype: float16 +ckpt: null +resume: true +auto_resume: true +start_epoch: 0 +max_checkpoints: 0 +checkpoint_period: null +plot_period: 5 +device: cuda +presend_cuda: false +seed: 5406 +debug: false +wandb: true +wandb_entity: null +wandb_project: fMRI-foundation-model +rank: 0 +world_size: 1 +gpu: 0 +distributed: true +dist_backend: nccl +in_chans: 1 +img_size: +- 224 +- 560 + +train transform: +Compose( + ToTensor() + TemporalCenterCrop(num_frames=16) + Normalize(mode='frame') + Clip(vmax=3.0) + FlatUnmask((224, 560)) +) +val transform: +Compose( + ToTensor() + TemporalCenterCrop(num_frames=16) + Normalize(mode='frame') + Clip(vmax=3.0) + FlatUnmask((224, 560)) +) +mask generator: +TubeMasking( + mask_ratio=0.9 + (patchify): Patchify2D((224, 560), (16, 16), in_chans=1) +) +loading dataset: hcp-train + +type: wds +url: /data/fmri-datasets/pretrain/hcpya-all.${input_space}.wds/hcpya-all-${input_space}-{00000..01799}.tar +clipping: random +clipping_kwargs: + oversample: 4.0 +shuffle: true +buffer_size: 2000 +samples_per_epoch: 200000 + +loading dataset: hcp-train-subset + +type: arrow +root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/validation +split_range: +- 0 +- 2000 +shuffle: false + +pretraining fmri mae +start: 2026-04-02 20:47:32 +cwd: /data/connor/fmri-fm +sha: bcce2b486277d3a5b520775efd9cdf1a2affce36, status: has uncommitted changes, branch: dev/clane9 +config: +name: input_space_v3/flat_lr1e-3_6/pretrain +notes: input_space ablation v3 flat_lr1e-3_6; use tube masking and on-disk data (input_space=flat + base_lr=1e-3 seed=5406) +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain +input_space: flat +patch_size: 16 +num_frames: 16 +t_patch_size: 4 +mask_ratio: 0.9 +pred_mask_ratio: null +masking: tube +masking_kwargs: {} +mask_patch_size: null +model: mae_vit_base +model_kwargs: + decoding: attn + pos_embed: sep + target_norm: null + pca_norm_nc: 2 + t_pred_stride: 2 + no_decode_pos: true + mask_drop_scale: false + pred_edge_pad: 0 + gauss_sigma: null + class_token: true + reg_tokens: 0 + no_embed_class: true + head_init_scale: 0.0 + decoder_depth: 4 + drop_path_rate: 0.0 +datasets: + hcp-train: + type: wds + url: /data/fmri-datasets/pretrain/hcpya-all.${input_space}.wds/hcpya-all-${input_space}-{00000..01799}.tar + clipping: random + clipping_kwargs: + oversample: 4.0 + shuffle: true + buffer_size: 2000 + samples_per_epoch: 200000 + hcp-train-subset: + type: arrow + root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/validation + split_range: + - 0 + - 2000 + shuffle: false + hcp-val: + type: arrow + root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/test + split_range: + - 0 + - 2000 + shuffle: false +train_dataset: hcp-train +eval_datasets: +- hcp-train-subset +- hcp-val +val_dataset: null +clip_vmax: 3.0 +normalize: frame +tr_scale: null +crop_scale: null +crop_aspect: null +gray_jitter: null +num_workers: 16 +epochs: 100 +batch_size: 32 +accum_iter: 1 +base_lr: 0.001 +min_lr: 0.0 +warmup_epochs: 5 +weight_decay: 0.05 +betas: +- 0.9 +- 0.95 +clip_grad: 1.0 +amp: true +amp_dtype: float16 +ckpt: null +resume: true +auto_resume: true +start_epoch: 0 +max_checkpoints: 0 +checkpoint_period: null +plot_period: 5 +device: cuda +presend_cuda: false +seed: 5406 +debug: false +wandb: true +wandb_entity: null +wandb_project: fMRI-foundation-model +rank: 0 +world_size: 1 +gpu: 0 +distributed: true +dist_backend: nccl +in_chans: 1 +img_size: +- 224 +- 560 + +train transform: +Compose( + ToTensor() + TemporalCenterCrop(num_frames=16) + Normalize(mode='frame') + Clip(vmax=3.0) + FlatUnmask((224, 560)) +) +val transform: +Compose( + ToTensor() + TemporalCenterCrop(num_frames=16) + Normalize(mode='frame') + Clip(vmax=3.0) + FlatUnmask((224, 560)) +) +mask generator: +TubeMasking( + mask_ratio=0.9 + (patchify): Patchify2D((224, 560), (16, 16), in_chans=1) +) +loading dataset: hcp-train + +type: wds +url: /data/fmri-datasets/pretrain/hcpya-all.${input_space}.wds/hcpya-all-${input_space}-{00000..01799}.tar +clipping: random +clipping_kwargs: + oversample: 4.0 +shuffle: true +buffer_size: 2000 +samples_per_epoch: 200000 + +loading dataset: hcp-train-subset + +type: arrow +root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/validation +split_range: +- 0 +- 2000 +shuffle: false + +split indices: [899, 472, 767, 116, 1265, 1852, 300, 1335, 361, 1560] +loading dataset: hcp-val + +type: arrow +root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/test +split_range: +- 0 +- 2000 +shuffle: false + +split indices: [1075, 1189, 738, 1350, 965, 1964, 1367, 1183, 1619, 1407] +model: +MaskedAutoencoderViT( + decoding=attn, t_pred_stride=2, pred_edge_pad=0, no_decode_pos=True + (encoder): MaskedEncoder( + class_token=True, reg_tokens=0, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) + (pred_patchify): StridedPatchify3D((16, 224, 560), (2, 16, 16), in_chans=1, t_stride=2) + (decoder): MaskedDecoder( + cross_decode=False, class_token=True, no_embed_class=True + (pos_embed): SeparablePosEmbed(512, (4, 14, 35)) + (proj): Linear(in_features=768, out_features=512, bias=True) + (blocks): ModuleList( + (0-3): 4 x Block( + (norm1): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=16 + (q): Linear(in_features=512, out_features=512, bias=True) + (k): Linear(in_features=512, out_features=512, bias=True) + (v): Linear(in_features=512, out_features=512, bias=True) + (proj): Linear(in_features=512, out_features=512, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=512, out_features=2048, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=2048, out_features=512, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (head): Linear(in_features=512, out_features=512, bias=True) + ) +) +num params: 99.7M +total batch size: 32 = 32 bs per gpu x 1 accum x 1 gpus +lr: 1.25e-04 = 1.00e-03 x 32 / 256 +full schedule: epochs = 100 (steps = 625000) +warmup: epochs = 5 (steps = 31250) +loaded model state from checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +loaded optimizer state, resuming training from 44 +start training for 100 epochs +Train: [44] [ 0/6250] eta: 12:15:55 lr: 0.000080 grad: 0.0906 (0.0906) loss: 0.8535 (0.8535) time: 7.0648 data: 5.8036 max mem: 9353 +Train: [44] [ 100/6250] eta: 0:22:27 lr: 0.000080 grad: 0.0827 (0.0844) loss: 0.8274 (0.8339) time: 0.1428 data: 0.0292 max mem: 9390 +Train: [44] [ 200/6250] eta: 0:19:26 lr: 0.000080 grad: 0.0755 (0.0847) loss: 0.8230 (0.8319) time: 0.1735 data: 0.0717 max mem: 9390 +Train: [44] [ 300/6250] eta: 0:18:12 lr: 0.000080 grad: 0.0799 (0.0846) loss: 0.8194 (0.8286) time: 0.1412 data: 0.0325 max mem: 9390 +Train: [44] [ 400/6250] eta: 0:17:33 lr: 0.000080 grad: 0.0769 (0.0837) loss: 0.8280 (0.8275) time: 0.1477 data: 0.0342 max mem: 9390 +Train: [44] [ 500/6250] eta: 0:17:08 lr: 0.000080 grad: 0.0774 (0.0831) loss: 0.8182 (0.8270) time: 0.1567 data: 0.0610 max mem: 9390 +Train: [44] [ 600/6250] eta: 0:16:34 lr: 0.000080 grad: 0.0740 (0.0826) loss: 0.8256 (0.8261) time: 0.1653 data: 0.0703 max mem: 9390 +Train: [44] [ 700/6250] eta: 0:16:22 lr: 0.000080 grad: 0.0765 (0.0819) loss: 0.8226 (0.8256) time: 0.1630 data: 0.0422 max mem: 9390 +Train: [44] [ 800/6250] eta: 0:16:02 lr: 0.000080 grad: 0.0770 (0.0816) loss: 0.8308 (0.8254) time: 0.1862 data: 0.0912 max mem: 9390 +Train: [44] [ 900/6250] eta: 0:15:41 lr: 0.000080 grad: 0.0774 (0.0815) loss: 0.8266 (0.8251) time: 0.1834 data: 0.0905 max mem: 9390 +Train: [44] [1000/6250] eta: 0:15:22 lr: 0.000080 grad: 0.0818 (0.0818) loss: 0.8222 (0.8249) time: 0.1691 data: 0.0734 max mem: 9390 +Train: [44] [1100/6250] eta: 0:15:00 lr: 0.000079 grad: 0.0762 (0.0816) loss: 0.8200 (0.8248) time: 0.1501 data: 0.0566 max mem: 9390 +Train: [44] [1200/6250] eta: 0:14:41 lr: 0.000079 grad: 0.0780 (0.0816) loss: 0.8203 (0.8244) time: 0.1828 data: 0.0993 max mem: 9390 +Train: [44] [1300/6250] eta: 0:14:20 lr: 0.000079 grad: 0.0829 (0.0815) loss: 0.8230 (0.8240) time: 0.1745 data: 0.0824 max mem: 9390 +Train: [44] [1400/6250] eta: 0:13:59 lr: 0.000079 grad: 0.0796 (0.0816) loss: 0.8191 (0.8238) time: 0.1761 data: 0.0770 max mem: 9390 +Train: [44] [1500/6250] eta: 0:13:37 lr: 0.000079 grad: 0.0777 (0.0816) loss: 0.8267 (0.8237) time: 0.1485 data: 0.0549 max mem: 9390 +Train: [44] [1600/6250] eta: 0:13:15 lr: 0.000079 grad: 0.0817 (0.0818) loss: 0.8131 (0.8235) time: 0.1694 data: 0.0843 max mem: 9390 +Train: [44] [1700/6250] eta: 0:12:54 lr: 0.000079 grad: 0.0788 (0.0819) loss: 0.8191 (0.8233) time: 0.1780 data: 0.0837 max mem: 9390 +Train: [44] [1800/6250] eta: 0:12:32 lr: 0.000079 grad: 0.0862 (0.0821) loss: 0.8167 (0.8230) time: 0.1329 data: 0.0443 max mem: 9390 +Train: [44] [1900/6250] eta: 0:12:11 lr: 0.000079 grad: 0.0862 (0.0823) loss: 0.8180 (0.8229) time: 0.1517 data: 0.0674 max mem: 9390 +Train: [44] [2000/6250] eta: 0:11:53 lr: 0.000079 grad: 0.0822 (0.0824) loss: 0.8145 (0.8226) time: 0.1737 data: 0.0870 max mem: 9390 +Train: [44] [2100/6250] eta: 0:11:35 lr: 0.000079 grad: 0.0901 (0.0826) loss: 0.8142 (0.8225) time: 0.1666 data: 0.0793 max mem: 9390 +Train: [44] [2200/6250] eta: 0:11:16 lr: 0.000079 grad: 0.0873 (0.0830) loss: 0.8145 (0.8223) time: 0.1600 data: 0.0693 max mem: 9390 +pretraining fmri mae +start: 2026-04-02 21:02:10 +cwd: /data/connor/fmri-fm +sha: bcce2b486277d3a5b520775efd9cdf1a2affce36, status: has uncommitted changes, branch: dev/clane9 +config: +name: input_space_v3/flat_lr1e-3_6/pretrain +notes: input_space ablation v3 flat_lr1e-3_6; use tube masking and on-disk data (input_space=flat + base_lr=1e-3 seed=5406) +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain +input_space: flat +patch_size: 16 +num_frames: 16 +t_patch_size: 4 +mask_ratio: 0.9 +pred_mask_ratio: null +masking: tube +masking_kwargs: {} +mask_patch_size: null +model: mae_vit_base +model_kwargs: + decoding: attn + pos_embed: sep + target_norm: null + pca_norm_nc: 2 + t_pred_stride: 2 + no_decode_pos: true + mask_drop_scale: false + pred_edge_pad: 0 + gauss_sigma: null + class_token: true + reg_tokens: 0 + no_embed_class: true + head_init_scale: 0.0 + decoder_depth: 4 + drop_path_rate: 0.0 +datasets: + hcp-train: + type: wds + url: /data/fmri-datasets/pretrain/hcpya-all.${input_space}.wds/hcpya-all-${input_space}-{00000..01799}.tar + clipping: random + clipping_kwargs: + oversample: 4.0 + shuffle: true + buffer_size: 2000 + samples_per_epoch: 200000 + hcp-train-subset: + type: arrow + root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/validation + split_range: + - 0 + - 2000 + shuffle: false + hcp-val: + type: arrow + root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/test + split_range: + - 0 + - 2000 + shuffle: false +train_dataset: hcp-train +eval_datasets: +- hcp-train-subset +- hcp-val +val_dataset: null +clip_vmax: 3.0 +normalize: frame +tr_scale: null +crop_scale: null +crop_aspect: null +gray_jitter: null +num_workers: 16 +epochs: 100 +batch_size: 32 +accum_iter: 1 +base_lr: 0.001 +min_lr: 0.0 +warmup_epochs: 5 +weight_decay: 0.05 +betas: +- 0.9 +- 0.95 +clip_grad: 1.0 +amp: true +amp_dtype: float16 +ckpt: null +resume: true +auto_resume: true +start_epoch: 0 +max_checkpoints: 0 +checkpoint_period: null +plot_period: 5 +device: cuda +presend_cuda: false +seed: 5406 +debug: false +wandb: true +wandb_entity: null +wandb_project: fMRI-foundation-model +rank: 0 +world_size: 1 +gpu: 0 +distributed: true +dist_backend: nccl +in_chans: 1 +img_size: +- 224 +- 560 + +train transform: +Compose( + ToTensor() + TemporalCenterCrop(num_frames=16) + Normalize(mode='frame') + Clip(vmax=3.0) + FlatUnmask((224, 560)) +) +val transform: +Compose( + ToTensor() + TemporalCenterCrop(num_frames=16) + Normalize(mode='frame') + Clip(vmax=3.0) + FlatUnmask((224, 560)) +) +mask generator: +TubeMasking( + mask_ratio=0.9 + (patchify): Patchify2D((224, 560), (16, 16), in_chans=1) +) +loading dataset: hcp-train + +type: wds +url: /data/fmri-datasets/pretrain/hcpya-all.${input_space}.wds/hcpya-all-${input_space}-{00000..01799}.tar +clipping: random +clipping_kwargs: + oversample: 4.0 +shuffle: true +buffer_size: 2000 +samples_per_epoch: 200000 + +loading dataset: hcp-train-subset + +type: arrow +root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/validation +split_range: +- 0 +- 2000 +shuffle: false + +split indices: [899, 472, 767, 116, 1265, 1852, 300, 1335, 361, 1560] +loading dataset: hcp-val + +type: arrow +root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/test +split_range: +- 0 +- 2000 +shuffle: false + +split indices: [1075, 1189, 738, 1350, 965, 1964, 1367, 1183, 1619, 1407] +model: +MaskedAutoencoderViT( + decoding=attn, t_pred_stride=2, pred_edge_pad=0, no_decode_pos=True + (encoder): MaskedEncoder( + class_token=True, reg_tokens=0, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) + (pred_patchify): StridedPatchify3D((16, 224, 560), (2, 16, 16), in_chans=1, t_stride=2) + (decoder): MaskedDecoder( + cross_decode=False, class_token=True, no_embed_class=True + (pos_embed): SeparablePosEmbed(512, (4, 14, 35)) + (proj): Linear(in_features=768, out_features=512, bias=True) + (blocks): ModuleList( + (0-3): 4 x Block( + (norm1): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=16 + (q): Linear(in_features=512, out_features=512, bias=True) + (k): Linear(in_features=512, out_features=512, bias=True) + (v): Linear(in_features=512, out_features=512, bias=True) + (proj): Linear(in_features=512, out_features=512, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=512, out_features=2048, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=2048, out_features=512, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (head): Linear(in_features=512, out_features=512, bias=True) + ) +) +num params: 99.7M +total batch size: 32 = 32 bs per gpu x 1 accum x 1 gpus +lr: 1.25e-04 = 1.00e-03 x 32 / 256 +full schedule: epochs = 100 (steps = 625000) +warmup: epochs = 5 (steps = 31250) +loaded model state from checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +loaded optimizer state, resuming training from 44 +start training for 100 epochs +Train: [44] [ 0/6250] eta: 15:47:45 lr: 0.000080 grad: 0.1275 (0.1275) loss: 0.8228 (0.8228) time: 9.0985 data: 7.9862 max mem: 9353 +Train: [44] [ 100/6250] eta: 0:22:45 lr: 0.000080 grad: 0.0859 (0.0924) loss: 0.8359 (0.8385) time: 0.1582 data: 0.0694 max mem: 9390 +Train: [44] [ 200/6250] eta: 0:18:22 lr: 0.000080 grad: 0.0814 (0.0897) loss: 0.8275 (0.8326) time: 0.1415 data: 0.0579 max mem: 9390 +Train: [44] [ 300/6250] eta: 0:17:20 lr: 0.000080 grad: 0.0808 (0.0876) loss: 0.8245 (0.8308) time: 0.1708 data: 0.0816 max mem: 9390 +Train: [44] [ 400/6250] eta: 0:17:19 lr: 0.000080 grad: 0.0818 (0.0864) loss: 0.8236 (0.8305) time: 0.1640 data: 0.0760 max mem: 9390 +Train: [44] [ 500/6250] eta: 0:16:28 lr: 0.000080 grad: 0.0834 (0.0857) loss: 0.8259 (0.8299) time: 0.1568 data: 0.0701 max mem: 9390 +Train: [44] [ 600/6250] eta: 0:15:54 lr: 0.000080 grad: 0.0815 (0.0853) loss: 0.8273 (0.8294) time: 0.1590 data: 0.0684 max mem: 9390 +Train: [44] [ 700/6250] eta: 0:15:27 lr: 0.000080 grad: 0.0756 (0.0854) loss: 0.8283 (0.8291) time: 0.1428 data: 0.0591 max mem: 9390 +Train: [44] [ 800/6250] eta: 0:15:04 lr: 0.000080 grad: 0.0760 (0.0846) loss: 0.8275 (0.8291) time: 0.1366 data: 0.0502 max mem: 9390 +Train: [44] [ 900/6250] eta: 0:14:46 lr: 0.000080 grad: 0.0770 (0.0842) loss: 0.8255 (0.8291) time: 0.1692 data: 0.0812 max mem: 9390 +Train: [44] [1000/6250] eta: 0:14:27 lr: 0.000080 grad: 0.0739 (0.0837) loss: 0.8298 (0.8290) time: 0.1510 data: 0.0604 max mem: 9390 +Train: [44] [1100/6250] eta: 0:14:03 lr: 0.000079 grad: 0.0830 (0.0836) loss: 0.8201 (0.8283) time: 0.1529 data: 0.0681 max mem: 9390 +Train: [44] [1200/6250] eta: 0:13:42 lr: 0.000079 grad: 0.0788 (0.0836) loss: 0.8246 (0.8278) time: 0.1459 data: 0.0542 max mem: 9390 +Train: [44] [1300/6250] eta: 0:13:21 lr: 0.000079 grad: 0.0852 (0.0836) loss: 0.8217 (0.8275) time: 0.1521 data: 0.0680 max mem: 9390 +Train: [44] [1400/6250] eta: 0:13:00 lr: 0.000079 grad: 0.0805 (0.0837) loss: 0.8214 (0.8270) time: 0.1319 data: 0.0513 max mem: 9390 +Train: [44] [1500/6250] eta: 0:12:42 lr: 0.000079 grad: 0.0834 (0.0838) loss: 0.8232 (0.8266) time: 0.1693 data: 0.0894 max mem: 9390 +Train: [44] [1600/6250] eta: 0:12:20 lr: 0.000079 grad: 0.0841 (0.0837) loss: 0.8193 (0.8263) time: 0.1491 data: 0.0644 max mem: 9390 +Train: [44] [1700/6250] eta: 0:12:01 lr: 0.000079 grad: 0.0837 (0.0838) loss: 0.8159 (0.8259) time: 0.1510 data: 0.0732 max mem: 9390 +Train: [44] [1800/6250] eta: 0:11:42 lr: 0.000079 grad: 0.0821 (0.0838) loss: 0.8225 (0.8257) time: 0.1428 data: 0.0624 max mem: 9390 +Train: [44] [1900/6250] eta: 0:11:24 lr: 0.000079 grad: 0.0830 (0.0839) loss: 0.8165 (0.8255) time: 0.1557 data: 0.0723 max mem: 9390 +Train: [44] [2000/6250] eta: 0:11:05 lr: 0.000079 grad: 0.0790 (0.0841) loss: 0.8205 (0.8252) time: 0.1516 data: 0.0656 max mem: 9390 +Train: [44] [2100/6250] eta: 0:10:46 lr: 0.000079 grad: 0.0878 (0.0841) loss: 0.8187 (0.8250) time: 0.1502 data: 0.0689 max mem: 9390 +Train: [44] [2200/6250] eta: 0:10:30 lr: 0.000079 grad: 0.0819 (0.0841) loss: 0.8155 (0.8247) time: 0.1443 data: 0.0633 max mem: 9390 +Train: [44] [2300/6250] eta: 0:10:13 lr: 0.000079 grad: 0.0837 (0.0843) loss: 0.8178 (0.8245) time: 0.1418 data: 0.0615 max mem: 9390 +Train: [44] [2400/6250] eta: 0:09:56 lr: 0.000079 grad: 0.0830 (0.0843) loss: 0.8223 (0.8244) time: 0.1426 data: 0.0633 max mem: 9390 +Train: [44] [2500/6250] eta: 0:09:40 lr: 0.000079 grad: 0.0823 (0.0842) loss: 0.8176 (0.8242) time: 0.1494 data: 0.0622 max mem: 9390 +Train: [44] [2600/6250] eta: 0:09:23 lr: 0.000079 grad: 0.0793 (0.0842) loss: 0.8224 (0.8241) time: 0.1392 data: 0.0456 max mem: 9390 +Train: [44] [2700/6250] eta: 0:09:08 lr: 0.000079 grad: 0.0830 (0.0841) loss: 0.8249 (0.8241) time: 0.1679 data: 0.0918 max mem: 9390 +Train: [44] [2800/6250] eta: 0:08:52 lr: 0.000079 grad: 0.0766 (0.0841) loss: 0.8262 (0.8240) time: 0.1290 data: 0.0435 max mem: 9390 +Train: [44] [2900/6250] eta: 0:08:37 lr: 0.000079 grad: 0.0819 (0.0840) loss: 0.8286 (0.8240) time: 0.1439 data: 0.0722 max mem: 9390 +Train: [44] [3000/6250] eta: 0:08:21 lr: 0.000079 grad: 0.0811 (0.0840) loss: 0.8234 (0.8240) time: 0.1570 data: 0.0754 max mem: 9390 +Train: [44] [3100/6250] eta: 0:08:06 lr: 0.000079 grad: 0.0810 (0.0840) loss: 0.8209 (0.8240) time: 0.2050 data: 0.1267 max mem: 9390 +Train: [44] [3200/6250] eta: 0:07:50 lr: 0.000079 grad: 0.0799 (0.0840) loss: 0.8156 (0.8239) time: 0.1566 data: 0.0749 max mem: 9390 +Train: [44] [3300/6250] eta: 0:07:34 lr: 0.000079 grad: 0.0797 (0.0840) loss: 0.8219 (0.8239) time: 0.1634 data: 0.0836 max mem: 9390 +Train: [44] [3400/6250] eta: 0:07:19 lr: 0.000079 grad: 0.0852 (0.0840) loss: 0.8234 (0.8239) time: 0.1764 data: 0.0989 max mem: 9390 +Train: [44] [3500/6250] eta: 0:07:03 lr: 0.000079 grad: 0.0792 (0.0840) loss: 0.8309 (0.8240) time: 0.1552 data: 0.0770 max mem: 9390 +Train: [44] [3600/6250] eta: 0:06:47 lr: 0.000079 grad: 0.0813 (0.0839) loss: 0.8190 (0.8240) time: 0.1320 data: 0.0507 max mem: 9390 +Train: [44] [3700/6250] eta: 0:06:32 lr: 0.000079 grad: 0.0791 (0.0839) loss: 0.8246 (0.8240) time: 0.1230 data: 0.0459 max mem: 9390 +Train: [44] [3800/6250] eta: 0:06:16 lr: 0.000079 grad: 0.0821 (0.0839) loss: 0.8252 (0.8239) time: 0.1427 data: 0.0575 max mem: 9390 +Train: [44] [3900/6250] eta: 0:06:00 lr: 0.000079 grad: 0.0778 (0.0839) loss: 0.8229 (0.8239) time: 0.1445 data: 0.0641 max mem: 9390 +Train: [44] [4000/6250] eta: 0:05:45 lr: 0.000079 grad: 0.0773 (0.0838) loss: 0.8263 (0.8240) time: 0.1619 data: 0.0831 max mem: 9390 +Train: [44] [4100/6250] eta: 0:05:29 lr: 0.000079 grad: 0.0830 (0.0839) loss: 0.8243 (0.8240) time: 0.1532 data: 0.0753 max mem: 9390 +Train: [44] [4200/6250] eta: 0:05:13 lr: 0.000078 grad: 0.0837 (0.0838) loss: 0.8269 (0.8241) time: 0.1515 data: 0.0726 max mem: 9390 +Train: [44] [4300/6250] eta: 0:04:58 lr: 0.000078 grad: 0.0796 (0.0838) loss: 0.8259 (0.8241) time: 0.1380 data: 0.0554 max mem: 9390 +Train: [44] [4400/6250] eta: 0:04:43 lr: 0.000078 grad: 0.0852 (0.0838) loss: 0.8241 (0.8241) time: 0.1502 data: 0.0697 max mem: 9390 +Train: [44] [4500/6250] eta: 0:04:27 lr: 0.000078 grad: 0.0812 (0.0840) loss: 0.8228 (0.8240) time: 0.1555 data: 0.0749 max mem: 9390 +Train: [44] [4600/6250] eta: 0:04:12 lr: 0.000078 grad: 0.0801 (0.0841) loss: 0.8216 (0.8240) time: 0.1420 data: 0.0624 max mem: 9390 +Train: [44] [4700/6250] eta: 0:03:57 lr: 0.000078 grad: 0.0858 (0.0841) loss: 0.8218 (0.8240) time: 0.1660 data: 0.0820 max mem: 9390 +Train: [44] [4800/6250] eta: 0:03:41 lr: 0.000078 grad: 0.0825 (0.0842) loss: 0.8251 (0.8240) time: 0.1704 data: 0.0915 max mem: 9390 +Train: [44] [4900/6250] eta: 0:03:26 lr: 0.000078 grad: 0.0903 (0.0843) loss: 0.8211 (0.8239) time: 0.1523 data: 0.0663 max mem: 9390 +Train: [44] [5000/6250] eta: 0:03:11 lr: 0.000078 grad: 0.0847 (0.0844) loss: 0.8249 (0.8239) time: 0.1517 data: 0.0735 max mem: 9390 +Train: [44] [5100/6250] eta: 0:02:55 lr: 0.000078 grad: 0.0881 (0.0846) loss: 0.8176 (0.8238) time: 0.1426 data: 0.0606 max mem: 9390 +Train: [44] [5200/6250] eta: 0:02:40 lr: 0.000078 grad: 0.0925 (0.0847) loss: 0.8176 (0.8237) time: 0.1425 data: 0.0607 max mem: 9390 +Train: [44] [5300/6250] eta: 0:02:24 lr: 0.000078 grad: 0.0868 (0.0850) loss: 0.8207 (0.8236) time: 0.1491 data: 0.0712 max mem: 9390 +Train: [44] [5400/6250] eta: 0:02:09 lr: 0.000078 grad: 0.0822 (0.0851) loss: 0.8257 (0.8236) time: 0.1493 data: 0.0650 max mem: 9390 +Train: [44] [5500/6250] eta: 0:01:54 lr: 0.000078 grad: 0.0873 (0.0852) loss: 0.8188 (0.8235) time: 0.1542 data: 0.0716 max mem: 9390 +Train: [44] [5600/6250] eta: 0:01:39 lr: 0.000078 grad: 0.0862 (0.0853) loss: 0.8255 (0.8234) time: 0.1524 data: 0.0761 max mem: 9390 +Train: [44] [5700/6250] eta: 0:01:23 lr: 0.000078 grad: 0.0819 (0.0854) loss: 0.8212 (0.8233) time: 0.1537 data: 0.0670 max mem: 9390 +Train: [44] [5800/6250] eta: 0:01:08 lr: 0.000078 grad: 0.0885 (0.0855) loss: 0.8175 (0.8233) time: 0.1431 data: 0.0645 max mem: 9390 +Train: [44] [5900/6250] eta: 0:00:53 lr: 0.000078 grad: 0.0866 (0.0855) loss: 0.8154 (0.8232) time: 0.1532 data: 0.0723 max mem: 9390 +Train: [44] [6000/6250] eta: 0:00:38 lr: 0.000078 grad: 0.0852 (0.0856) loss: 0.8227 (0.8232) time: 0.1602 data: 0.0799 max mem: 9390 +Train: [44] [6100/6250] eta: 0:00:22 lr: 0.000078 grad: 0.0907 (0.0857) loss: 0.8182 (0.8231) time: 0.1613 data: 0.0800 max mem: 9390 +Train: [44] [6200/6250] eta: 0:00:07 lr: 0.000078 grad: 0.0881 (0.0858) loss: 0.8282 (0.8230) time: 0.1497 data: 0.0662 max mem: 9390 +Train: [44] [6249/6250] eta: 0:00:00 lr: 0.000078 grad: 0.0829 (0.0858) loss: 0.8173 (0.8230) time: 0.1527 data: 0.0732 max mem: 9390 +Train: [44] Total time: 0:15:54 (0.1528 s / it) +Averaged stats: lr: 0.000078 grad: 0.0829 (0.0858) loss: 0.8173 (0.8230) +Eval (hcp-train-subset): [44] [ 0/62] eta: 0:04:29 loss: 0.8461 (0.8461) time: 4.3490 data: 4.2442 max mem: 9390 +Eval (hcp-train-subset): [44] [61/62] eta: 0:00:00 loss: 0.8394 (0.8401) time: 0.1124 data: 0.0874 max mem: 9390 +Eval (hcp-train-subset): [44] Total time: 0:00:12 (0.2041 s / it) +Averaged stats (hcp-train-subset): loss: 0.8394 (0.8401) +Making plots (hcp-train-subset): example=2 +Eval (hcp-val): [44] [ 0/62] eta: 0:03:26 loss: 0.8386 (0.8386) time: 3.3307 data: 3.2783 max mem: 9390 +Eval (hcp-val): [44] [61/62] eta: 0:00:00 loss: 0.8345 (0.8363) time: 0.1131 data: 0.0868 max mem: 9390 +Eval (hcp-val): [44] Total time: 0:00:12 (0.2048 s / it) +Averaged stats (hcp-val): loss: 0.8345 (0.8363) +Making plots (hcp-val): example=59 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +Train: [45] [ 0/6250] eta: 8:08:18 lr: 0.000078 grad: 0.1883 (0.1883) loss: 0.8190 (0.8190) time: 4.6877 data: 4.4422 max mem: 9390 +Train: [45] [ 100/6250] eta: 0:20:10 lr: 0.000078 grad: 0.0793 (0.0882) loss: 0.8369 (0.8432) time: 0.1737 data: 0.0860 max mem: 9390 +Train: [45] [ 200/6250] eta: 0:17:39 lr: 0.000078 grad: 0.0725 (0.0856) loss: 0.8340 (0.8376) time: 0.1613 data: 0.0748 max mem: 9390 +Train: [45] [ 300/6250] eta: 0:16:17 lr: 0.000078 grad: 0.0784 (0.0836) loss: 0.8264 (0.8351) time: 0.1403 data: 0.0578 max mem: 9390 +Train: [45] [ 400/6250] eta: 0:15:53 lr: 0.000078 grad: 0.0757 (0.0832) loss: 0.8292 (0.8337) time: 0.1738 data: 0.0928 max mem: 9390 +Train: [45] [ 500/6250] eta: 0:15:32 lr: 0.000078 grad: 0.0809 (0.0829) loss: 0.8248 (0.8324) time: 0.1660 data: 0.0883 max mem: 9390 +Train: [45] [ 600/6250] eta: 0:15:19 lr: 0.000078 grad: 0.0797 (0.0828) loss: 0.8279 (0.8316) time: 0.1432 data: 0.0610 max mem: 9390 +Train: [45] [ 700/6250] eta: 0:15:17 lr: 0.000078 grad: 0.0774 (0.0825) loss: 0.8310 (0.8309) time: 0.1641 data: 0.0807 max mem: 9390 +Train: [45] [ 800/6250] eta: 0:15:09 lr: 0.000078 grad: 0.0818 (0.0828) loss: 0.8292 (0.8301) time: 0.1957 data: 0.1093 max mem: 9390 +Train: [45] [ 900/6250] eta: 0:15:02 lr: 0.000078 grad: 0.0756 (0.0828) loss: 0.8231 (0.8296) time: 0.1963 data: 0.1012 max mem: 9390 +Train: [45] [1000/6250] eta: 0:14:43 lr: 0.000078 grad: 0.0818 (0.0828) loss: 0.8270 (0.8291) time: 0.1700 data: 0.0834 max mem: 9390 +Train: [45] [1100/6250] eta: 0:14:22 lr: 0.000077 grad: 0.0745 (0.0827) loss: 0.8218 (0.8286) time: 0.1482 data: 0.0650 max mem: 9390 +Train: [45] [1200/6250] eta: 0:14:01 lr: 0.000077 grad: 0.0832 (0.0827) loss: 0.8200 (0.8281) time: 0.1726 data: 0.0814 max mem: 9390 +Train: [45] [1300/6250] eta: 0:13:39 lr: 0.000077 grad: 0.0808 (0.0828) loss: 0.8275 (0.8277) time: 0.1728 data: 0.0877 max mem: 9390 +Train: [45] [1400/6250] eta: 0:13:21 lr: 0.000077 grad: 0.0840 (0.0830) loss: 0.8273 (0.8273) time: 0.1525 data: 0.0683 max mem: 9390 +Train: [45] [1500/6250] eta: 0:13:06 lr: 0.000077 grad: 0.0895 (0.0832) loss: 0.8257 (0.8269) time: 0.1649 data: 0.0830 max mem: 9390 +Train: [45] [1600/6250] eta: 0:12:48 lr: 0.000077 grad: 0.0812 (0.0834) loss: 0.8148 (0.8265) time: 0.1663 data: 0.0845 max mem: 9390 +Train: [45] [1700/6250] eta: 0:12:30 lr: 0.000077 grad: 0.0876 (0.0836) loss: 0.8238 (0.8261) time: 0.1408 data: 0.0615 max mem: 9390 +Train: [45] [1800/6250] eta: 0:12:12 lr: 0.000077 grad: 0.0834 (0.0838) loss: 0.8203 (0.8256) time: 0.1446 data: 0.0595 max mem: 9390 +Train: [45] [1900/6250] eta: 0:11:54 lr: 0.000077 grad: 0.0879 (0.0840) loss: 0.8125 (0.8252) time: 0.1511 data: 0.0635 max mem: 9390 +Train: [45] [2000/6250] eta: 0:11:34 lr: 0.000077 grad: 0.0850 (0.0843) loss: 0.8159 (0.8247) time: 0.1597 data: 0.0726 max mem: 9390 +Train: [45] [2100/6250] eta: 0:11:16 lr: 0.000077 grad: 0.0842 (0.0844) loss: 0.8229 (0.8245) time: 0.1338 data: 0.0504 max mem: 9390 +Train: [45] [2200/6250] eta: 0:10:57 lr: 0.000077 grad: 0.0801 (0.0845) loss: 0.8211 (0.8242) time: 0.1400 data: 0.0581 max mem: 9390 +Train: [45] [2300/6250] eta: 0:10:38 lr: 0.000077 grad: 0.0820 (0.0846) loss: 0.8199 (0.8239) time: 0.1029 data: 0.0179 max mem: 9390 +Train: [45] [2400/6250] eta: 0:10:21 lr: 0.000077 grad: 0.0849 (0.0848) loss: 0.8144 (0.8236) time: 0.1672 data: 0.0894 max mem: 9390 +Train: [45] [2500/6250] eta: 0:10:04 lr: 0.000077 grad: 0.0828 (0.0848) loss: 0.8224 (0.8235) time: 0.1650 data: 0.0826 max mem: 9390 +Train: [45] [2600/6250] eta: 0:09:46 lr: 0.000077 grad: 0.0858 (0.0849) loss: 0.8243 (0.8233) time: 0.1494 data: 0.0677 max mem: 9390 +Train: [45] [2700/6250] eta: 0:09:28 lr: 0.000077 grad: 0.0867 (0.0851) loss: 0.8134 (0.8232) time: 0.1507 data: 0.0651 max mem: 9390 +Train: [45] [2800/6250] eta: 0:09:11 lr: 0.000077 grad: 0.0862 (0.0851) loss: 0.8169 (0.8231) time: 0.1582 data: 0.0759 max mem: 9390 +Train: [45] [2900/6250] eta: 0:08:54 lr: 0.000077 grad: 0.0811 (0.0851) loss: 0.8212 (0.8229) time: 0.1482 data: 0.0726 max mem: 9390 +Train: [45] [3000/6250] eta: 0:08:36 lr: 0.000077 grad: 0.0865 (0.0852) loss: 0.8206 (0.8228) time: 0.1403 data: 0.0613 max mem: 9390 +Train: [45] [3100/6250] eta: 0:08:20 lr: 0.000077 grad: 0.0851 (0.0852) loss: 0.8148 (0.8226) time: 0.1748 data: 0.0899 max mem: 9390 +Train: [45] [3200/6250] eta: 0:08:03 lr: 0.000077 grad: 0.0852 (0.0854) loss: 0.8178 (0.8224) time: 0.1501 data: 0.0651 max mem: 9390 +Train: [45] [3300/6250] eta: 0:07:46 lr: 0.000077 grad: 0.0872 (0.0855) loss: 0.8207 (0.8222) time: 0.1429 data: 0.0620 max mem: 9390 +Train: [45] [3400/6250] eta: 0:07:29 lr: 0.000077 grad: 0.0828 (0.0856) loss: 0.8185 (0.8219) time: 0.1486 data: 0.0623 max mem: 9390 +Train: [45] [3500/6250] eta: 0:07:13 lr: 0.000077 grad: 0.0948 (0.0858) loss: 0.8161 (0.8218) time: 0.1483 data: 0.0634 max mem: 9390 +Train: [45] [3600/6250] eta: 0:06:57 lr: 0.000077 grad: 0.0896 (0.0860) loss: 0.8170 (0.8216) time: 0.1440 data: 0.0612 max mem: 9390 +Train: [45] [3700/6250] eta: 0:06:41 lr: 0.000077 grad: 0.0862 (0.0861) loss: 0.8202 (0.8215) time: 0.1581 data: 0.0812 max mem: 9390 +Train: [45] [3800/6250] eta: 0:06:24 lr: 0.000077 grad: 0.0864 (0.0862) loss: 0.8226 (0.8215) time: 0.1514 data: 0.0625 max mem: 9390 +Train: [45] [3900/6250] eta: 0:06:08 lr: 0.000077 grad: 0.0877 (0.0864) loss: 0.8181 (0.8214) time: 0.1543 data: 0.0710 max mem: 9390 +Train: [45] [4000/6250] eta: 0:05:52 lr: 0.000077 grad: 0.0861 (0.0864) loss: 0.8213 (0.8213) time: 0.1602 data: 0.0711 max mem: 9390 +Train: [45] [4100/6250] eta: 0:05:36 lr: 0.000077 grad: 0.0860 (0.0866) loss: 0.8242 (0.8212) time: 0.1401 data: 0.0586 max mem: 9390 +Train: [45] [4200/6250] eta: 0:05:20 lr: 0.000076 grad: 0.0842 (0.0866) loss: 0.8295 (0.8212) time: 0.1407 data: 0.0604 max mem: 9390 +Train: [45] [4300/6250] eta: 0:05:04 lr: 0.000076 grad: 0.0821 (0.0867) loss: 0.8224 (0.8212) time: 0.1483 data: 0.0672 max mem: 9390 +Train: [45] [4400/6250] eta: 0:04:48 lr: 0.000076 grad: 0.0875 (0.0867) loss: 0.8201 (0.8212) time: 0.1509 data: 0.0721 max mem: 9390 +Train: [45] [4500/6250] eta: 0:04:33 lr: 0.000076 grad: 0.0920 (0.0868) loss: 0.8217 (0.8213) time: 0.1444 data: 0.0618 max mem: 9390 +Train: [45] [4600/6250] eta: 0:04:17 lr: 0.000076 grad: 0.0838 (0.0868) loss: 0.8231 (0.8213) time: 0.1352 data: 0.0542 max mem: 9390 +Train: [45] [4700/6250] eta: 0:04:01 lr: 0.000076 grad: 0.0828 (0.0868) loss: 0.8205 (0.8213) time: 0.1593 data: 0.0780 max mem: 9390 +Train: [45] [4800/6250] eta: 0:03:46 lr: 0.000076 grad: 0.0887 (0.0868) loss: 0.8202 (0.8212) time: 0.1742 data: 0.0936 max mem: 9390 +Train: [45] [4900/6250] eta: 0:03:30 lr: 0.000076 grad: 0.0859 (0.0869) loss: 0.8219 (0.8212) time: 0.1601 data: 0.0855 max mem: 9390 +Train: [45] [5000/6250] eta: 0:03:15 lr: 0.000076 grad: 0.0865 (0.0869) loss: 0.8247 (0.8213) time: 0.1554 data: 0.0718 max mem: 9390 +Train: [45] [5100/6250] eta: 0:02:59 lr: 0.000076 grad: 0.0787 (0.0869) loss: 0.8210 (0.8212) time: 0.1289 data: 0.0571 max mem: 9390 +Train: [45] [5200/6250] eta: 0:02:44 lr: 0.000076 grad: 0.0802 (0.0870) loss: 0.8226 (0.8212) time: 0.1301 data: 0.0326 max mem: 9390 +Train: [45] [5300/6250] eta: 0:02:29 lr: 0.000076 grad: 0.0830 (0.0870) loss: 0.8258 (0.8212) time: 0.1458 data: 0.0522 max mem: 9390 +Train: [45] [5400/6250] eta: 0:02:13 lr: 0.000076 grad: 0.0800 (0.0870) loss: 0.8256 (0.8213) time: 0.1703 data: 0.0832 max mem: 9390 +Train: [45] [5500/6250] eta: 0:01:57 lr: 0.000076 grad: 0.0844 (0.0870) loss: 0.8250 (0.8213) time: 0.1263 data: 0.0378 max mem: 9390 +Train: [45] [5600/6250] eta: 0:01:42 lr: 0.000076 grad: 0.0838 (0.0870) loss: 0.8202 (0.8213) time: 0.1506 data: 0.0651 max mem: 9390 +Train: [45] [5700/6250] eta: 0:01:26 lr: 0.000076 grad: 0.0823 (0.0870) loss: 0.8229 (0.8213) time: 0.1583 data: 0.0686 max mem: 9390 +Train: [45] [5800/6250] eta: 0:01:10 lr: 0.000076 grad: 0.0888 (0.0870) loss: 0.8228 (0.8213) time: 0.1449 data: 0.0464 max mem: 9390 +Train: [45] [5900/6250] eta: 0:00:54 lr: 0.000076 grad: 0.0780 (0.0870) loss: 0.8255 (0.8213) time: 0.1501 data: 0.0679 max mem: 9390 +Train: [45] [6000/6250] eta: 0:00:38 lr: 0.000076 grad: 0.0844 (0.0870) loss: 0.8197 (0.8214) time: 0.1295 data: 0.0364 max mem: 9390 +Train: [45] [6100/6250] eta: 0:00:23 lr: 0.000076 grad: 0.0910 (0.0870) loss: 0.8193 (0.8214) time: 0.1709 data: 0.0713 max mem: 9390 +Train: [45] [6200/6250] eta: 0:00:07 lr: 0.000076 grad: 0.0833 (0.0871) loss: 0.8256 (0.8214) time: 0.1540 data: 0.0661 max mem: 9390 +Train: [45] [6249/6250] eta: 0:00:00 lr: 0.000076 grad: 0.0864 (0.0871) loss: 0.8207 (0.8214) time: 0.1570 data: 0.0726 max mem: 9390 +Train: [45] Total time: 0:16:14 (0.1560 s / it) +Averaged stats: lr: 0.000076 grad: 0.0864 (0.0871) loss: 0.8207 (0.8214) +Eval (hcp-train-subset): [45] [ 0/62] eta: 0:03:52 loss: 0.8530 (0.8530) time: 3.7544 data: 3.6769 max mem: 9390 +Eval (hcp-train-subset): [45] [61/62] eta: 0:00:00 loss: 0.8410 (0.8405) time: 0.0868 data: 0.0611 max mem: 9390 +Eval (hcp-train-subset): [45] Total time: 0:00:12 (0.2017 s / it) +Averaged stats (hcp-train-subset): loss: 0.8410 (0.8405) +Eval (hcp-val): [45] [ 0/62] eta: 0:03:25 loss: 0.8340 (0.8340) time: 3.3161 data: 3.2130 max mem: 9390 +Eval (hcp-val): [45] [61/62] eta: 0:00:00 loss: 0.8357 (0.8365) time: 0.1084 data: 0.0837 max mem: 9390 +Eval (hcp-val): [45] Total time: 0:00:11 (0.1896 s / it) +Averaged stats (hcp-val): loss: 0.8357 (0.8365) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +Train: [46] [ 0/6250] eta: 6:25:03 lr: 0.000076 grad: 0.0690 (0.0690) loss: 0.8731 (0.8731) time: 3.6966 data: 3.4931 max mem: 9390 +Train: [46] [ 100/6250] eta: 0:19:15 lr: 0.000076 grad: 0.0887 (0.0915) loss: 0.8255 (0.8348) time: 0.1460 data: 0.0555 max mem: 9390 +Train: [46] [ 200/6250] eta: 0:17:17 lr: 0.000076 grad: 0.0852 (0.0916) loss: 0.8253 (0.8307) time: 0.1772 data: 0.0919 max mem: 9390 +Train: [46] [ 300/6250] eta: 0:16:27 lr: 0.000076 grad: 0.0810 (0.0906) loss: 0.8263 (0.8293) time: 0.1575 data: 0.0738 max mem: 9390 +Train: [46] [ 400/6250] eta: 0:15:55 lr: 0.000076 grad: 0.0815 (0.0885) loss: 0.8354 (0.8289) time: 0.1797 data: 0.0965 max mem: 9390 +Train: [46] [ 500/6250] eta: 0:15:22 lr: 0.000076 grad: 0.0784 (0.0870) loss: 0.8287 (0.8290) time: 0.1361 data: 0.0554 max mem: 9390 +Train: [46] [ 600/6250] eta: 0:15:01 lr: 0.000076 grad: 0.0795 (0.0864) loss: 0.8314 (0.8289) time: 0.1524 data: 0.0625 max mem: 9390 +Train: [46] [ 700/6250] eta: 0:14:44 lr: 0.000076 grad: 0.0789 (0.0860) loss: 0.8239 (0.8286) time: 0.1772 data: 0.0950 max mem: 9390 +Train: [46] [ 800/6250] eta: 0:14:27 lr: 0.000076 grad: 0.0758 (0.0852) loss: 0.8312 (0.8285) time: 0.1774 data: 0.0961 max mem: 9390 +Train: [46] [ 900/6250] eta: 0:14:15 lr: 0.000076 grad: 0.0784 (0.0846) loss: 0.8310 (0.8282) time: 0.2049 data: 0.1265 max mem: 9390 +Train: [46] [1000/6250] eta: 0:14:01 lr: 0.000076 grad: 0.0802 (0.0841) loss: 0.8226 (0.8281) time: 0.1420 data: 0.0624 max mem: 9390 +Train: [46] [1100/6250] eta: 0:13:42 lr: 0.000075 grad: 0.0837 (0.0840) loss: 0.8256 (0.8278) time: 0.1522 data: 0.0717 max mem: 9390 +Train: [46] [1200/6250] eta: 0:13:25 lr: 0.000075 grad: 0.0812 (0.0838) loss: 0.8250 (0.8276) time: 0.1614 data: 0.0782 max mem: 9390 +Train: [46] [1300/6250] eta: 0:13:06 lr: 0.000075 grad: 0.0815 (0.0837) loss: 0.8234 (0.8276) time: 0.1463 data: 0.0641 max mem: 9390 +Train: [46] [1400/6250] eta: 0:12:48 lr: 0.000075 grad: 0.0868 (0.0839) loss: 0.8228 (0.8272) time: 0.1732 data: 0.0952 max mem: 9390 +Train: [46] [1500/6250] eta: 0:12:29 lr: 0.000075 grad: 0.0816 (0.0838) loss: 0.8201 (0.8269) time: 0.1385 data: 0.0539 max mem: 9390 +Train: [46] [1600/6250] eta: 0:12:11 lr: 0.000075 grad: 0.0838 (0.0839) loss: 0.8274 (0.8267) time: 0.1152 data: 0.0300 max mem: 9390 +Train: [46] [1700/6250] eta: 0:11:53 lr: 0.000075 grad: 0.0821 (0.0841) loss: 0.8195 (0.8263) time: 0.1538 data: 0.0675 max mem: 9390 +Train: [46] [1800/6250] eta: 0:11:38 lr: 0.000075 grad: 0.0896 (0.0843) loss: 0.8236 (0.8259) time: 0.1603 data: 0.0779 max mem: 9390 +Train: [46] [1900/6250] eta: 0:11:20 lr: 0.000075 grad: 0.0867 (0.0845) loss: 0.8191 (0.8257) time: 0.1690 data: 0.0904 max mem: 9390 +Train: [46] [2000/6250] eta: 0:11:02 lr: 0.000075 grad: 0.0849 (0.0847) loss: 0.8234 (0.8253) time: 0.1485 data: 0.0614 max mem: 9390 +Train: [46] [2100/6250] eta: 0:10:48 lr: 0.000075 grad: 0.0852 (0.0848) loss: 0.8130 (0.8251) time: 0.1603 data: 0.0773 max mem: 9390 +Train: [46] [2200/6250] eta: 0:10:32 lr: 0.000075 grad: 0.0837 (0.0849) loss: 0.8222 (0.8249) time: 0.1459 data: 0.0633 max mem: 9390 +Train: [46] [2300/6250] eta: 0:10:17 lr: 0.000075 grad: 0.0906 (0.0850) loss: 0.8166 (0.8247) time: 0.1690 data: 0.0910 max mem: 9390 +Train: [46] [2400/6250] eta: 0:10:01 lr: 0.000075 grad: 0.0834 (0.0851) loss: 0.8254 (0.8245) time: 0.1680 data: 0.0928 max mem: 9390 +Train: [46] [2500/6250] eta: 0:09:44 lr: 0.000075 grad: 0.0864 (0.0851) loss: 0.8224 (0.8244) time: 0.1492 data: 0.0614 max mem: 9390 +Train: [46] [2600/6250] eta: 0:09:26 lr: 0.000075 grad: 0.0863 (0.0851) loss: 0.8210 (0.8244) time: 0.1416 data: 0.0544 max mem: 9390 +Train: [46] [2700/6250] eta: 0:09:10 lr: 0.000075 grad: 0.0846 (0.0852) loss: 0.8207 (0.8244) time: 0.1324 data: 0.0502 max mem: 9390 +Train: [46] [2800/6250] eta: 0:08:54 lr: 0.000075 grad: 0.0842 (0.0852) loss: 0.8250 (0.8244) time: 0.1567 data: 0.0724 max mem: 9390 +Train: [46] [2900/6250] eta: 0:08:37 lr: 0.000075 grad: 0.0883 (0.0852) loss: 0.8229 (0.8243) time: 0.1443 data: 0.0692 max mem: 9390 +Train: [46] [3000/6250] eta: 0:08:21 lr: 0.000075 grad: 0.0881 (0.0853) loss: 0.8282 (0.8242) time: 0.1575 data: 0.0792 max mem: 9390 +Train: [46] [3100/6250] eta: 0:08:05 lr: 0.000075 grad: 0.0942 (0.0854) loss: 0.8163 (0.8242) time: 0.1269 data: 0.0441 max mem: 9390 +Train: [46] [3200/6250] eta: 0:07:49 lr: 0.000075 grad: 0.0825 (0.0855) loss: 0.8227 (0.8241) time: 0.1431 data: 0.0570 max mem: 9390 +Train: [46] [3300/6250] eta: 0:07:33 lr: 0.000075 grad: 0.0863 (0.0856) loss: 0.8231 (0.8240) time: 0.1555 data: 0.0702 max mem: 9390 +Train: [46] [3400/6250] eta: 0:07:17 lr: 0.000075 grad: 0.0824 (0.0856) loss: 0.8215 (0.8239) time: 0.1440 data: 0.0647 max mem: 9390 +Train: [46] [3500/6250] eta: 0:07:01 lr: 0.000075 grad: 0.0897 (0.0858) loss: 0.8151 (0.8238) time: 0.1632 data: 0.0809 max mem: 9390 +Train: [46] [3600/6250] eta: 0:06:45 lr: 0.000075 grad: 0.0812 (0.0858) loss: 0.8251 (0.8238) time: 0.1443 data: 0.0609 max mem: 9390 +Train: [46] [3700/6250] eta: 0:06:29 lr: 0.000075 grad: 0.0821 (0.0858) loss: 0.8265 (0.8238) time: 0.1542 data: 0.0719 max mem: 9390 +Train: [46] [3800/6250] eta: 0:06:14 lr: 0.000075 grad: 0.0837 (0.0859) loss: 0.8245 (0.8238) time: 0.1491 data: 0.0605 max mem: 9390 +Train: [46] [3900/6250] eta: 0:05:58 lr: 0.000075 grad: 0.0830 (0.0859) loss: 0.8201 (0.8237) time: 0.1709 data: 0.0921 max mem: 9390 +Train: [46] [4000/6250] eta: 0:05:43 lr: 0.000075 grad: 0.0899 (0.0859) loss: 0.8206 (0.8237) time: 0.1441 data: 0.0645 max mem: 9390 +Train: [46] [4100/6250] eta: 0:05:27 lr: 0.000075 grad: 0.0798 (0.0859) loss: 0.8203 (0.8237) time: 0.1431 data: 0.0568 max mem: 9390 +Train: [46] [4200/6250] eta: 0:05:11 lr: 0.000074 grad: 0.0839 (0.0858) loss: 0.8274 (0.8237) time: 0.1292 data: 0.0449 max mem: 9390 +Train: [46] [4300/6250] eta: 0:04:56 lr: 0.000074 grad: 0.0830 (0.0858) loss: 0.8228 (0.8238) time: 0.1319 data: 0.0528 max mem: 9390 +Train: [46] [4400/6250] eta: 0:04:41 lr: 0.000074 grad: 0.0902 (0.0860) loss: 0.8254 (0.8238) time: 0.1468 data: 0.0673 max mem: 9390 +Train: [46] [4500/6250] eta: 0:04:25 lr: 0.000074 grad: 0.0827 (0.0860) loss: 0.8213 (0.8238) time: 0.1437 data: 0.0649 max mem: 9390 +Train: [46] [4600/6250] eta: 0:04:10 lr: 0.000074 grad: 0.0803 (0.0860) loss: 0.8319 (0.8238) time: 0.1229 data: 0.0318 max mem: 9390 +Train: [46] [4700/6250] eta: 0:03:54 lr: 0.000074 grad: 0.0779 (0.0860) loss: 0.8200 (0.8238) time: 0.1413 data: 0.0578 max mem: 9390 +Train: [46] [4800/6250] eta: 0:03:39 lr: 0.000074 grad: 0.0848 (0.0861) loss: 0.8212 (0.8238) time: 0.1497 data: 0.0667 max mem: 9390 +Train: [46] [4900/6250] eta: 0:03:24 lr: 0.000074 grad: 0.0933 (0.0862) loss: 0.8213 (0.8238) time: 0.1269 data: 0.0412 max mem: 9390 +Train: [46] [5000/6250] eta: 0:03:09 lr: 0.000074 grad: 0.0796 (0.0862) loss: 0.8236 (0.8238) time: 0.1595 data: 0.0736 max mem: 9390 +Train: [46] [5100/6250] eta: 0:02:53 lr: 0.000074 grad: 0.0829 (0.0862) loss: 0.8242 (0.8237) time: 0.1549 data: 0.0690 max mem: 9390 +Train: [46] [5200/6250] eta: 0:02:38 lr: 0.000074 grad: 0.0853 (0.0862) loss: 0.8221 (0.8237) time: 0.1457 data: 0.0628 max mem: 9390 +Train: [46] [5300/6250] eta: 0:02:23 lr: 0.000074 grad: 0.0812 (0.0862) loss: 0.8267 (0.8237) time: 0.1540 data: 0.0747 max mem: 9390 +Train: [46] [5400/6250] eta: 0:02:08 lr: 0.000074 grad: 0.0792 (0.0862) loss: 0.8262 (0.8237) time: 0.1551 data: 0.0774 max mem: 9390 +Train: [46] [5500/6250] eta: 0:01:53 lr: 0.000074 grad: 0.0806 (0.0862) loss: 0.8201 (0.8236) time: 0.1265 data: 0.0478 max mem: 9390 +Train: [46] [5600/6250] eta: 0:01:37 lr: 0.000074 grad: 0.0854 (0.0862) loss: 0.8238 (0.8236) time: 0.1495 data: 0.0656 max mem: 9390 +Train: [46] [5700/6250] eta: 0:01:22 lr: 0.000074 grad: 0.0831 (0.0863) loss: 0.8222 (0.8235) time: 0.1501 data: 0.0691 max mem: 9390 +Train: [46] [5800/6250] eta: 0:01:07 lr: 0.000074 grad: 0.0843 (0.0863) loss: 0.8226 (0.8235) time: 0.1572 data: 0.0698 max mem: 9390 +Train: [46] [5900/6250] eta: 0:00:52 lr: 0.000074 grad: 0.0821 (0.0863) loss: 0.8200 (0.8235) time: 0.1574 data: 0.0736 max mem: 9390 +Train: [46] [6000/6250] eta: 0:00:37 lr: 0.000074 grad: 0.0841 (0.0863) loss: 0.8233 (0.8235) time: 0.1665 data: 0.0865 max mem: 9390 +Train: [46] [6100/6250] eta: 0:00:22 lr: 0.000074 grad: 0.0899 (0.0864) loss: 0.8132 (0.8234) time: 0.1532 data: 0.0734 max mem: 9390 +Train: [46] [6200/6250] eta: 0:00:07 lr: 0.000074 grad: 0.0879 (0.0865) loss: 0.8202 (0.8234) time: 0.1338 data: 0.0495 max mem: 9390 +Train: [46] [6249/6250] eta: 0:00:00 lr: 0.000074 grad: 0.0875 (0.0865) loss: 0.8218 (0.8233) time: 0.1502 data: 0.0641 max mem: 9390 +Train: [46] Total time: 0:15:46 (0.1514 s / it) +Averaged stats: lr: 0.000074 grad: 0.0875 (0.0865) loss: 0.8218 (0.8233) +Eval (hcp-train-subset): [46] [ 0/62] eta: 0:03:53 loss: 0.8418 (0.8418) time: 3.7663 data: 3.7034 max mem: 9390 +Eval (hcp-train-subset): [46] [61/62] eta: 0:00:00 loss: 0.8381 (0.8385) time: 0.1355 data: 0.1107 max mem: 9390 +Eval (hcp-train-subset): [46] Total time: 0:00:12 (0.2014 s / it) +Averaged stats (hcp-train-subset): loss: 0.8381 (0.8385) +Eval (hcp-val): [46] [ 0/62] eta: 0:03:36 loss: 0.8338 (0.8338) time: 3.4923 data: 3.4185 max mem: 9390 +Eval (hcp-val): [46] [61/62] eta: 0:00:00 loss: 0.8371 (0.8375) time: 0.1186 data: 0.0937 max mem: 9390 +Eval (hcp-val): [46] Total time: 0:00:13 (0.2097 s / it) +Averaged stats (hcp-val): loss: 0.8371 (0.8375) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +Train: [47] [ 0/6250] eta: 8:43:46 lr: 0.000074 grad: 0.1667 (0.1667) loss: 0.8287 (0.8287) time: 5.0283 data: 4.6964 max mem: 9390 +Train: [47] [ 100/6250] eta: 0:22:08 lr: 0.000074 grad: 0.0842 (0.0923) loss: 0.8217 (0.8346) time: 0.1669 data: 0.0832 max mem: 9390 +Train: [47] [ 200/6250] eta: 0:19:06 lr: 0.000074 grad: 0.0843 (0.0891) loss: 0.8153 (0.8278) time: 0.1485 data: 0.0589 max mem: 9390 +Train: [47] [ 300/6250] eta: 0:17:59 lr: 0.000074 grad: 0.0832 (0.0870) loss: 0.8262 (0.8269) time: 0.1830 data: 0.0885 max mem: 9390 +Train: [47] [ 400/6250] eta: 0:17:04 lr: 0.000074 grad: 0.0777 (0.0851) loss: 0.8202 (0.8269) time: 0.1633 data: 0.0700 max mem: 9390 +Train: [47] [ 500/6250] eta: 0:16:20 lr: 0.000074 grad: 0.0785 (0.0844) loss: 0.8241 (0.8269) time: 0.1407 data: 0.0564 max mem: 9390 +Train: [47] [ 600/6250] eta: 0:15:39 lr: 0.000074 grad: 0.0777 (0.0842) loss: 0.8261 (0.8273) time: 0.1277 data: 0.0451 max mem: 9390 +Train: [47] [ 700/6250] eta: 0:15:10 lr: 0.000074 grad: 0.0799 (0.0836) loss: 0.8333 (0.8280) time: 0.1509 data: 0.0658 max mem: 9390 +Train: [47] [ 800/6250] eta: 0:14:48 lr: 0.000074 grad: 0.0752 (0.0834) loss: 0.8296 (0.8281) time: 0.1525 data: 0.0707 max mem: 9390 +Train: [47] [ 900/6250] eta: 0:14:25 lr: 0.000074 grad: 0.0781 (0.0832) loss: 0.8292 (0.8282) time: 0.1543 data: 0.0721 max mem: 9390 +Train: [47] [1000/6250] eta: 0:14:03 lr: 0.000073 grad: 0.0777 (0.0830) loss: 0.8251 (0.8284) time: 0.1419 data: 0.0590 max mem: 9390 +Train: [47] [1100/6250] eta: 0:13:41 lr: 0.000073 grad: 0.0808 (0.0830) loss: 0.8285 (0.8283) time: 0.1238 data: 0.0392 max mem: 9390 +Train: [47] [1200/6250] eta: 0:13:20 lr: 0.000073 grad: 0.0802 (0.0830) loss: 0.8242 (0.8281) time: 0.1659 data: 0.0808 max mem: 9390 +Train: [47] [1300/6250] eta: 0:12:59 lr: 0.000073 grad: 0.0810 (0.0830) loss: 0.8263 (0.8280) time: 0.1327 data: 0.0416 max mem: 9390 +Train: [47] [1400/6250] eta: 0:12:41 lr: 0.000073 grad: 0.0753 (0.0828) loss: 0.8291 (0.8279) time: 0.1478 data: 0.0637 max mem: 9390 +Train: [47] [1500/6250] eta: 0:12:23 lr: 0.000073 grad: 0.0826 (0.0828) loss: 0.8260 (0.8279) time: 0.1202 data: 0.0341 max mem: 9390 +Train: [47] [1600/6250] eta: 0:12:03 lr: 0.000073 grad: 0.0798 (0.0827) loss: 0.8247 (0.8278) time: 0.1607 data: 0.0782 max mem: 9390 +Train: [47] [1700/6250] eta: 0:11:45 lr: 0.000073 grad: 0.0786 (0.0828) loss: 0.8252 (0.8278) time: 0.1222 data: 0.0451 max mem: 9390 +Train: [47] [1800/6250] eta: 0:11:28 lr: 0.000073 grad: 0.0810 (0.0828) loss: 0.8284 (0.8279) time: 0.1471 data: 0.0639 max mem: 9390 +Train: [47] [1900/6250] eta: 0:11:13 lr: 0.000073 grad: 0.0772 (0.0828) loss: 0.8313 (0.8279) time: 0.1511 data: 0.0682 max mem: 9390 +Train: [47] [2000/6250] eta: 0:10:58 lr: 0.000073 grad: 0.0813 (0.0829) loss: 0.8268 (0.8278) time: 0.1652 data: 0.0853 max mem: 9390 +Train: [47] [2100/6250] eta: 0:10:41 lr: 0.000073 grad: 0.0788 (0.0831) loss: 0.8246 (0.8277) time: 0.1532 data: 0.0695 max mem: 9390 +Train: [47] [2200/6250] eta: 0:10:24 lr: 0.000073 grad: 0.0735 (0.0832) loss: 0.8242 (0.8277) time: 0.1280 data: 0.0467 max mem: 9390 +Train: [47] [2300/6250] eta: 0:10:07 lr: 0.000073 grad: 0.0850 (0.0832) loss: 0.8253 (0.8276) time: 0.1417 data: 0.0617 max mem: 9390 +Train: [47] [2400/6250] eta: 0:09:50 lr: 0.000073 grad: 0.0906 (0.0833) loss: 0.8262 (0.8276) time: 0.1479 data: 0.0621 max mem: 9390 +Train: [47] [2500/6250] eta: 0:09:35 lr: 0.000073 grad: 0.0841 (0.0834) loss: 0.8230 (0.8275) time: 0.1590 data: 0.0682 max mem: 9390 +Train: [47] [2600/6250] eta: 0:09:19 lr: 0.000073 grad: 0.0807 (0.0835) loss: 0.8213 (0.8273) time: 0.1299 data: 0.0482 max mem: 9390 +Train: [47] [2700/6250] eta: 0:09:02 lr: 0.000073 grad: 0.0901 (0.0837) loss: 0.8191 (0.8270) time: 0.1278 data: 0.0430 max mem: 9390 +Train: [47] [2800/6250] eta: 0:08:47 lr: 0.000073 grad: 0.0856 (0.0838) loss: 0.8249 (0.8269) time: 0.1780 data: 0.0980 max mem: 9390 +Train: [47] [2900/6250] eta: 0:08:32 lr: 0.000073 grad: 0.0828 (0.0838) loss: 0.8238 (0.8267) time: 0.1075 data: 0.0182 max mem: 9390 +Train: [47] [3000/6250] eta: 0:08:16 lr: 0.000073 grad: 0.0843 (0.0838) loss: 0.8233 (0.8266) time: 0.1444 data: 0.0545 max mem: 9390 +Train: [47] [3100/6250] eta: 0:08:01 lr: 0.000073 grad: 0.0801 (0.0839) loss: 0.8231 (0.8264) time: 0.1147 data: 0.0258 max mem: 9390 +Train: [47] [3200/6250] eta: 0:07:45 lr: 0.000073 grad: 0.0878 (0.0841) loss: 0.8220 (0.8263) time: 0.1455 data: 0.0609 max mem: 9390 +Train: [47] [3300/6250] eta: 0:07:30 lr: 0.000073 grad: 0.0853 (0.0841) loss: 0.8194 (0.8262) time: 0.1438 data: 0.0570 max mem: 9390 +Train: [47] [3400/6250] eta: 0:07:15 lr: 0.000073 grad: 0.0848 (0.0842) loss: 0.8262 (0.8261) time: 0.1413 data: 0.0570 max mem: 9390 +Train: [47] [3500/6250] eta: 0:07:00 lr: 0.000073 grad: 0.0812 (0.0842) loss: 0.8223 (0.8260) time: 0.1466 data: 0.0694 max mem: 9390 +Train: [47] [3600/6250] eta: 0:06:44 lr: 0.000073 grad: 0.0769 (0.0842) loss: 0.8227 (0.8259) time: 0.1524 data: 0.0645 max mem: 9390 +Train: [47] [3700/6250] eta: 0:06:31 lr: 0.000073 grad: 0.0867 (0.0843) loss: 0.8213 (0.8258) time: 0.1910 data: 0.1037 max mem: 9390 +Train: [47] [3800/6250] eta: 0:06:17 lr: 0.000073 grad: 0.0829 (0.0844) loss: 0.8270 (0.8258) time: 0.1695 data: 0.0901 max mem: 9390 +Train: [47] [3900/6250] eta: 0:06:02 lr: 0.000073 grad: 0.0803 (0.0846) loss: 0.8240 (0.8257) time: 0.1544 data: 0.0719 max mem: 9390 +Train: [47] [4000/6250] eta: 0:05:47 lr: 0.000073 grad: 0.0938 (0.0847) loss: 0.8184 (0.8256) time: 0.1530 data: 0.0724 max mem: 9390 +Train: [47] [4100/6250] eta: 0:05:33 lr: 0.000072 grad: 0.0824 (0.0847) loss: 0.8259 (0.8256) time: 0.1702 data: 0.0861 max mem: 9390 +Train: [47] [4200/6250] eta: 0:05:19 lr: 0.000072 grad: 0.0852 (0.0849) loss: 0.8149 (0.8255) time: 0.1786 data: 0.0891 max mem: 9390 +Train: [47] [4300/6250] eta: 0:05:03 lr: 0.000072 grad: 0.0835 (0.0850) loss: 0.8188 (0.8254) time: 0.1761 data: 0.0891 max mem: 9390 +Train: [47] [4400/6250] eta: 0:04:48 lr: 0.000072 grad: 0.0857 (0.0851) loss: 0.8195 (0.8252) time: 0.1281 data: 0.0270 max mem: 9390 +Train: [47] [4500/6250] eta: 0:04:33 lr: 0.000072 grad: 0.0836 (0.0852) loss: 0.8218 (0.8251) time: 0.1623 data: 0.0550 max mem: 9390 +Train: [47] [4600/6250] eta: 0:04:17 lr: 0.000072 grad: 0.0834 (0.0852) loss: 0.8299 (0.8250) time: 0.1573 data: 0.0595 max mem: 9390 +Train: [47] [4700/6250] eta: 0:04:02 lr: 0.000072 grad: 0.0828 (0.0852) loss: 0.8290 (0.8250) time: 0.1570 data: 0.0669 max mem: 9390 +Train: [47] [4800/6250] eta: 0:03:47 lr: 0.000072 grad: 0.0850 (0.0852) loss: 0.8221 (0.8249) time: 0.1567 data: 0.0571 max mem: 9390 +Train: [47] [4900/6250] eta: 0:03:31 lr: 0.000072 grad: 0.0807 (0.0852) loss: 0.8258 (0.8248) time: 0.1649 data: 0.0782 max mem: 9390 +Train: [47] [5000/6250] eta: 0:03:15 lr: 0.000072 grad: 0.0846 (0.0852) loss: 0.8236 (0.8248) time: 0.1422 data: 0.0591 max mem: 9390 +Train: [47] [5100/6250] eta: 0:02:59 lr: 0.000072 grad: 0.0853 (0.0852) loss: 0.8280 (0.8248) time: 0.1737 data: 0.0855 max mem: 9390 +Train: [47] [5200/6250] eta: 0:02:43 lr: 0.000072 grad: 0.0849 (0.0853) loss: 0.8195 (0.8248) time: 0.1222 data: 0.0352 max mem: 9390 +Train: [47] [5300/6250] eta: 0:02:28 lr: 0.000072 grad: 0.0849 (0.0854) loss: 0.8260 (0.8247) time: 0.1676 data: 0.0896 max mem: 9390 +Train: [47] [5400/6250] eta: 0:02:12 lr: 0.000072 grad: 0.0827 (0.0856) loss: 0.8288 (0.8247) time: 0.1391 data: 0.0549 max mem: 9390 +Train: [47] [5500/6250] eta: 0:01:57 lr: 0.000072 grad: 0.0827 (0.0856) loss: 0.8234 (0.8247) time: 0.1610 data: 0.0753 max mem: 9390 +Train: [47] [5600/6250] eta: 0:01:41 lr: 0.000072 grad: 0.0872 (0.0857) loss: 0.8284 (0.8246) time: 0.1826 data: 0.1038 max mem: 9390 +Train: [47] [5700/6250] eta: 0:01:25 lr: 0.000072 grad: 0.0899 (0.0857) loss: 0.8203 (0.8246) time: 0.1760 data: 0.0999 max mem: 9390 +Train: [47] [5800/6250] eta: 0:01:10 lr: 0.000072 grad: 0.0852 (0.0858) loss: 0.8200 (0.8245) time: 0.1718 data: 0.0959 max mem: 9390 +Train: [47] [5900/6250] eta: 0:00:54 lr: 0.000072 grad: 0.0855 (0.0858) loss: 0.8162 (0.8244) time: 0.1584 data: 0.0833 max mem: 9390 +Train: [47] [6000/6250] eta: 0:00:39 lr: 0.000072 grad: 0.0825 (0.0858) loss: 0.8215 (0.8244) time: 0.1849 data: 0.1091 max mem: 9390 +Train: [47] [6100/6250] eta: 0:00:23 lr: 0.000072 grad: 0.0802 (0.0859) loss: 0.8215 (0.8243) time: 0.1561 data: 0.0749 max mem: 9390 +Train: [47] [6200/6250] eta: 0:00:07 lr: 0.000072 grad: 0.0803 (0.0859) loss: 0.8282 (0.8242) time: 0.1334 data: 0.0500 max mem: 9390 +Train: [47] [6249/6250] eta: 0:00:00 lr: 0.000072 grad: 0.0816 (0.0859) loss: 0.8255 (0.8242) time: 0.1300 data: 0.0472 max mem: 9390 +Train: [47] Total time: 0:16:26 (0.1578 s / it) +Averaged stats: lr: 0.000072 grad: 0.0816 (0.0859) loss: 0.8255 (0.8242) +Eval (hcp-train-subset): [47] [ 0/62] eta: 0:04:12 loss: 0.8468 (0.8468) time: 4.0722 data: 4.0420 max mem: 9390 +Eval (hcp-train-subset): [47] [61/62] eta: 0:00:00 loss: 0.8354 (0.8376) time: 0.0955 data: 0.0692 max mem: 9390 +Eval (hcp-train-subset): [47] Total time: 0:00:12 (0.1983 s / it) +Averaged stats (hcp-train-subset): loss: 0.8354 (0.8376) +Eval (hcp-val): [47] [ 0/62] eta: 0:03:12 loss: 0.8300 (0.8300) time: 3.1111 data: 3.0428 max mem: 9390 +Eval (hcp-val): [47] [61/62] eta: 0:00:00 loss: 0.8348 (0.8352) time: 0.1281 data: 0.1016 max mem: 9390 +Eval (hcp-val): [47] Total time: 0:00:12 (0.1997 s / it) +Averaged stats (hcp-val): loss: 0.8348 (0.8352) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +Train: [48] [ 0/6250] eta: 6:14:07 lr: 0.000072 grad: 0.0700 (0.0700) loss: 0.8583 (0.8583) time: 3.5917 data: 3.3791 max mem: 9390 +Train: [48] [ 100/6250] eta: 0:21:15 lr: 0.000072 grad: 0.0901 (0.1025) loss: 0.8311 (0.8387) time: 0.1663 data: 0.0761 max mem: 9390 +Train: [48] [ 200/6250] eta: 0:18:59 lr: 0.000072 grad: 0.0747 (0.0945) loss: 0.8317 (0.8352) time: 0.1447 data: 0.0430 max mem: 9390 +Train: [48] [ 300/6250] eta: 0:17:54 lr: 0.000072 grad: 0.0792 (0.0927) loss: 0.8268 (0.8320) time: 0.1554 data: 0.0705 max mem: 9390 +Train: [48] [ 400/6250] eta: 0:16:55 lr: 0.000072 grad: 0.0831 (0.0915) loss: 0.8213 (0.8294) time: 0.1404 data: 0.0512 max mem: 9390 +Train: [48] [ 500/6250] eta: 0:16:12 lr: 0.000072 grad: 0.0813 (0.0912) loss: 0.8196 (0.8270) time: 0.1554 data: 0.0699 max mem: 9390 +Train: [48] [ 600/6250] eta: 0:15:35 lr: 0.000072 grad: 0.0830 (0.0906) loss: 0.8190 (0.8253) time: 0.1559 data: 0.0655 max mem: 9390 +Train: [48] [ 700/6250] eta: 0:15:04 lr: 0.000072 grad: 0.0881 (0.0902) loss: 0.8186 (0.8243) time: 0.1616 data: 0.0771 max mem: 9390 +Train: [48] [ 800/6250] eta: 0:14:40 lr: 0.000072 grad: 0.0849 (0.0900) loss: 0.8148 (0.8235) time: 0.1456 data: 0.0644 max mem: 9390 +Train: [48] [ 900/6250] eta: 0:14:19 lr: 0.000071 grad: 0.0855 (0.0898) loss: 0.8173 (0.8230) time: 0.1558 data: 0.0750 max mem: 9390 +Train: [48] [1000/6250] eta: 0:13:55 lr: 0.000071 grad: 0.0807 (0.0892) loss: 0.8222 (0.8228) time: 0.1546 data: 0.0729 max mem: 9390 +Train: [48] [1100/6250] eta: 0:13:35 lr: 0.000071 grad: 0.0846 (0.0890) loss: 0.8216 (0.8225) time: 0.1256 data: 0.0448 max mem: 9390 +Train: [48] [1200/6250] eta: 0:13:13 lr: 0.000071 grad: 0.0827 (0.0885) loss: 0.8199 (0.8224) time: 0.1363 data: 0.0461 max mem: 9390 +Train: [48] [1300/6250] eta: 0:12:56 lr: 0.000071 grad: 0.0824 (0.0883) loss: 0.8223 (0.8222) time: 0.1599 data: 0.0769 max mem: 9390 +Train: [48] [1400/6250] eta: 0:12:36 lr: 0.000071 grad: 0.0814 (0.0881) loss: 0.8231 (0.8220) time: 0.1319 data: 0.0454 max mem: 9390 +Train: [48] [1500/6250] eta: 0:12:16 lr: 0.000071 grad: 0.0869 (0.0880) loss: 0.8150 (0.8218) time: 0.1441 data: 0.0580 max mem: 9390 +Train: [48] [1600/6250] eta: 0:11:59 lr: 0.000071 grad: 0.0821 (0.0880) loss: 0.8171 (0.8216) time: 0.1492 data: 0.0658 max mem: 9390 +Train: [48] [1700/6250] eta: 0:11:42 lr: 0.000071 grad: 0.0828 (0.0879) loss: 0.8233 (0.8216) time: 0.1247 data: 0.0361 max mem: 9390 +Train: [48] [1800/6250] eta: 0:11:23 lr: 0.000071 grad: 0.0844 (0.0880) loss: 0.8219 (0.8216) time: 0.1519 data: 0.0750 max mem: 9390 +Train: [48] [1900/6250] eta: 0:11:04 lr: 0.000071 grad: 0.0792 (0.0880) loss: 0.8223 (0.8216) time: 0.1358 data: 0.0485 max mem: 9390 +Train: [48] [2000/6250] eta: 0:10:47 lr: 0.000071 grad: 0.0834 (0.0879) loss: 0.8184 (0.8215) time: 0.1387 data: 0.0530 max mem: 9390 +Train: [48] [2100/6250] eta: 0:10:33 lr: 0.000071 grad: 0.0797 (0.0879) loss: 0.8245 (0.8215) time: 0.1619 data: 0.0815 max mem: 9390 +Train: [48] [2200/6250] eta: 0:10:18 lr: 0.000071 grad: 0.0828 (0.0878) loss: 0.8203 (0.8214) time: 0.1819 data: 0.1006 max mem: 9390 +Train: [48] [2300/6250] eta: 0:10:03 lr: 0.000071 grad: 0.0817 (0.0878) loss: 0.8203 (0.8214) time: 0.1765 data: 0.0961 max mem: 9390 +Train: [48] [2400/6250] eta: 0:09:48 lr: 0.000071 grad: 0.0828 (0.0877) loss: 0.8212 (0.8214) time: 0.1371 data: 0.0556 max mem: 9390 +Train: [48] [2500/6250] eta: 0:09:32 lr: 0.000071 grad: 0.0898 (0.0878) loss: 0.8254 (0.8213) time: 0.1667 data: 0.0886 max mem: 9390 +Train: [48] [2600/6250] eta: 0:09:16 lr: 0.000071 grad: 0.0902 (0.0879) loss: 0.8136 (0.8212) time: 0.1482 data: 0.0661 max mem: 9390 +Train: [48] [2700/6250] eta: 0:09:01 lr: 0.000071 grad: 0.0915 (0.0879) loss: 0.8180 (0.8212) time: 0.1232 data: 0.0422 max mem: 9390 +Train: [48] [2800/6250] eta: 0:08:45 lr: 0.000071 grad: 0.0805 (0.0879) loss: 0.8238 (0.8211) time: 0.1449 data: 0.0623 max mem: 9390 +Train: [48] [2900/6250] eta: 0:08:29 lr: 0.000071 grad: 0.0844 (0.0879) loss: 0.8231 (0.8211) time: 0.1179 data: 0.0360 max mem: 9390 +Train: [48] [3000/6250] eta: 0:08:14 lr: 0.000071 grad: 0.0870 (0.0878) loss: 0.8146 (0.8211) time: 0.1575 data: 0.0747 max mem: 9390 +Train: [48] [3100/6250] eta: 0:07:58 lr: 0.000071 grad: 0.0859 (0.0878) loss: 0.8180 (0.8211) time: 0.1370 data: 0.0512 max mem: 9390 +Train: [48] [3200/6250] eta: 0:07:43 lr: 0.000071 grad: 0.0842 (0.0877) loss: 0.8203 (0.8211) time: 0.1527 data: 0.0671 max mem: 9390 +Train: [48] [3300/6250] eta: 0:07:28 lr: 0.000071 grad: 0.0857 (0.0878) loss: 0.8260 (0.8212) time: 0.1672 data: 0.0855 max mem: 9390 +Train: [48] [3400/6250] eta: 0:07:13 lr: 0.000071 grad: 0.0842 (0.0878) loss: 0.8222 (0.8211) time: 0.1627 data: 0.0778 max mem: 9390 +Train: [48] [3500/6250] eta: 0:06:58 lr: 0.000071 grad: 0.0893 (0.0879) loss: 0.8251 (0.8212) time: 0.1338 data: 0.0513 max mem: 9390 +Train: [48] [3600/6250] eta: 0:06:43 lr: 0.000071 grad: 0.0897 (0.0880) loss: 0.8201 (0.8211) time: 0.1476 data: 0.0615 max mem: 9390 +Train: [48] [3700/6250] eta: 0:06:28 lr: 0.000071 grad: 0.0826 (0.0880) loss: 0.8214 (0.8211) time: 0.1467 data: 0.0657 max mem: 9390 +Train: [48] [3800/6250] eta: 0:06:12 lr: 0.000071 grad: 0.0819 (0.0881) loss: 0.8234 (0.8212) time: 0.1568 data: 0.0707 max mem: 9390 +Train: [48] [3900/6250] eta: 0:05:57 lr: 0.000070 grad: 0.0872 (0.0881) loss: 0.8169 (0.8211) time: 0.1473 data: 0.0640 max mem: 9390 +Train: [48] [4000/6250] eta: 0:05:41 lr: 0.000070 grad: 0.0866 (0.0881) loss: 0.8237 (0.8210) time: 0.1369 data: 0.0538 max mem: 9390 +Train: [48] [4100/6250] eta: 0:05:26 lr: 0.000070 grad: 0.0804 (0.0880) loss: 0.8234 (0.8211) time: 0.1302 data: 0.0438 max mem: 9390 +Train: [48] [4200/6250] eta: 0:05:10 lr: 0.000070 grad: 0.0849 (0.0880) loss: 0.8201 (0.8210) time: 0.1463 data: 0.0605 max mem: 9390 +Train: [48] [4300/6250] eta: 0:04:55 lr: 0.000070 grad: 0.0904 (0.0880) loss: 0.8186 (0.8210) time: 0.1243 data: 0.0427 max mem: 9390 +Train: [48] [4400/6250] eta: 0:04:40 lr: 0.000070 grad: 0.0808 (0.0880) loss: 0.8207 (0.8210) time: 0.1520 data: 0.0584 max mem: 9390 +Train: [48] [4500/6250] eta: 0:04:25 lr: 0.000070 grad: 0.0825 (0.0880) loss: 0.8305 (0.8210) time: 0.1550 data: 0.0659 max mem: 9390 +Train: [48] [4600/6250] eta: 0:04:09 lr: 0.000070 grad: 0.0849 (0.0879) loss: 0.8280 (0.8211) time: 0.1457 data: 0.0622 max mem: 9390 +Train: [48] [4700/6250] eta: 0:03:54 lr: 0.000070 grad: 0.0873 (0.0879) loss: 0.8232 (0.8212) time: 0.1333 data: 0.0513 max mem: 9390 +Train: [48] [4800/6250] eta: 0:03:39 lr: 0.000070 grad: 0.0795 (0.0880) loss: 0.8327 (0.8213) time: 0.1572 data: 0.0766 max mem: 9390 +Train: [48] [4900/6250] eta: 0:03:24 lr: 0.000070 grad: 0.0842 (0.0879) loss: 0.8259 (0.8214) time: 0.1394 data: 0.0570 max mem: 9390 +Train: [48] [5000/6250] eta: 0:03:09 lr: 0.000070 grad: 0.0861 (0.0878) loss: 0.8289 (0.8215) time: 0.1464 data: 0.0613 max mem: 9390 +Train: [48] [5100/6250] eta: 0:02:53 lr: 0.000070 grad: 0.0852 (0.0877) loss: 0.8275 (0.8215) time: 0.1643 data: 0.0819 max mem: 9390 +Train: [48] [5200/6250] eta: 0:02:38 lr: 0.000070 grad: 0.0835 (0.0877) loss: 0.8222 (0.8216) time: 0.1716 data: 0.0963 max mem: 9390 +Train: [48] [5300/6250] eta: 0:02:23 lr: 0.000070 grad: 0.0803 (0.0876) loss: 0.8279 (0.8217) time: 0.1413 data: 0.0587 max mem: 9390 +Train: [48] [5400/6250] eta: 0:02:08 lr: 0.000070 grad: 0.0843 (0.0876) loss: 0.8262 (0.8217) time: 0.1431 data: 0.0613 max mem: 9390 +Train: [48] [5500/6250] eta: 0:01:53 lr: 0.000070 grad: 0.0880 (0.0876) loss: 0.8235 (0.8217) time: 0.1691 data: 0.0860 max mem: 9390 +Train: [48] [5600/6250] eta: 0:01:38 lr: 0.000070 grad: 0.0892 (0.0876) loss: 0.8231 (0.8217) time: 0.1547 data: 0.0753 max mem: 9390 +Train: [48] [5700/6250] eta: 0:01:23 lr: 0.000070 grad: 0.0835 (0.0876) loss: 0.8243 (0.8218) time: 0.1586 data: 0.0723 max mem: 9390 +Train: [48] [5800/6250] eta: 0:01:07 lr: 0.000070 grad: 0.0844 (0.0876) loss: 0.8238 (0.8218) time: 0.1316 data: 0.0453 max mem: 9390 +Train: [48] [5900/6250] eta: 0:00:52 lr: 0.000070 grad: 0.0898 (0.0876) loss: 0.8170 (0.8218) time: 0.1519 data: 0.0716 max mem: 9390 +Train: [48] [6000/6250] eta: 0:00:37 lr: 0.000070 grad: 0.0858 (0.0877) loss: 0.8204 (0.8218) time: 0.1519 data: 0.0661 max mem: 9390 +Train: [48] [6100/6250] eta: 0:00:22 lr: 0.000070 grad: 0.0848 (0.0878) loss: 0.8216 (0.8217) time: 0.1440 data: 0.0584 max mem: 9390 +Train: [48] [6200/6250] eta: 0:00:07 lr: 0.000070 grad: 0.0815 (0.0878) loss: 0.8222 (0.8217) time: 0.1260 data: 0.0511 max mem: 9390 +Train: [48] [6249/6250] eta: 0:00:00 lr: 0.000070 grad: 0.0831 (0.0879) loss: 0.8258 (0.8217) time: 0.1447 data: 0.0569 max mem: 9390 +Train: [48] Total time: 0:15:48 (0.1517 s / it) +Averaged stats: lr: 0.000070 grad: 0.0831 (0.0879) loss: 0.8258 (0.8217) +Eval (hcp-train-subset): [48] [ 0/62] eta: 0:04:39 loss: 0.8519 (0.8519) time: 4.5032 data: 4.4727 max mem: 9390 +Eval (hcp-train-subset): [48] [61/62] eta: 0:00:00 loss: 0.8390 (0.8392) time: 0.1177 data: 0.0912 max mem: 9390 +Eval (hcp-train-subset): [48] Total time: 0:00:12 (0.2059 s / it) +Averaged stats (hcp-train-subset): loss: 0.8390 (0.8392) +Eval (hcp-val): [48] [ 0/62] eta: 0:02:59 loss: 0.8310 (0.8310) time: 2.8959 data: 2.8071 max mem: 9390 +Eval (hcp-val): [48] [61/62] eta: 0:00:00 loss: 0.8350 (0.8364) time: 0.1257 data: 0.0987 max mem: 9390 +Eval (hcp-val): [48] Total time: 0:00:13 (0.2143 s / it) +Averaged stats (hcp-val): loss: 0.8350 (0.8364) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +Train: [49] [ 0/6250] eta: 8:25:26 lr: 0.000070 grad: 0.1064 (0.1064) loss: 0.8584 (0.8584) time: 4.8522 data: 4.6156 max mem: 9390 +Train: [49] [ 100/6250] eta: 0:21:14 lr: 0.000070 grad: 0.0850 (0.1021) loss: 0.8219 (0.8303) time: 0.1663 data: 0.0771 max mem: 9390 +Train: [49] [ 200/6250] eta: 0:18:39 lr: 0.000070 grad: 0.0878 (0.0960) loss: 0.8148 (0.8258) time: 0.1543 data: 0.0641 max mem: 9390 +Train: [49] [ 300/6250] eta: 0:17:38 lr: 0.000070 grad: 0.0848 (0.0922) loss: 0.8181 (0.8249) time: 0.1729 data: 0.0796 max mem: 9390 +Train: [49] [ 400/6250] eta: 0:16:57 lr: 0.000070 grad: 0.0813 (0.0903) loss: 0.8257 (0.8255) time: 0.1775 data: 0.0870 max mem: 9390 +Train: [49] [ 500/6250] eta: 0:16:09 lr: 0.000070 grad: 0.0801 (0.0898) loss: 0.8231 (0.8251) time: 0.1499 data: 0.0603 max mem: 9390 +Train: [49] [ 600/6250] eta: 0:15:44 lr: 0.000070 grad: 0.0872 (0.0899) loss: 0.8212 (0.8247) time: 0.1669 data: 0.0813 max mem: 9390 +Train: [49] [ 700/6250] eta: 0:15:14 lr: 0.000069 grad: 0.0853 (0.0898) loss: 0.8236 (0.8241) time: 0.1668 data: 0.0854 max mem: 9390 +Train: [49] [ 800/6250] eta: 0:14:48 lr: 0.000069 grad: 0.0836 (0.0896) loss: 0.8236 (0.8241) time: 0.1753 data: 0.0875 max mem: 9390 +Train: [49] [ 900/6250] eta: 0:14:24 lr: 0.000069 grad: 0.0774 (0.0891) loss: 0.8326 (0.8242) time: 0.1432 data: 0.0558 max mem: 9390 +Train: [49] [1000/6250] eta: 0:14:03 lr: 0.000069 grad: 0.0822 (0.0886) loss: 0.8286 (0.8244) time: 0.1582 data: 0.0779 max mem: 9390 +Train: [49] [1100/6250] eta: 0:13:44 lr: 0.000069 grad: 0.0818 (0.0881) loss: 0.8199 (0.8244) time: 0.1767 data: 0.0955 max mem: 9390 +Train: [49] [1200/6250] eta: 0:13:22 lr: 0.000069 grad: 0.0843 (0.0878) loss: 0.8196 (0.8242) time: 0.1631 data: 0.0828 max mem: 9390 +Train: [49] [1300/6250] eta: 0:12:59 lr: 0.000069 grad: 0.0773 (0.0877) loss: 0.8224 (0.8240) time: 0.1501 data: 0.0642 max mem: 9390 +Train: [49] [1400/6250] eta: 0:12:39 lr: 0.000069 grad: 0.0870 (0.0878) loss: 0.8195 (0.8238) time: 0.1345 data: 0.0565 max mem: 9390 +Train: [49] [1500/6250] eta: 0:12:20 lr: 0.000069 grad: 0.0804 (0.0877) loss: 0.8242 (0.8237) time: 0.1512 data: 0.0694 max mem: 9390 +Train: [49] [1600/6250] eta: 0:12:04 lr: 0.000069 grad: 0.0882 (0.0874) loss: 0.8212 (0.8237) time: 0.1284 data: 0.0419 max mem: 9390 +Train: [49] [1700/6250] eta: 0:11:46 lr: 0.000069 grad: 0.0890 (0.0874) loss: 0.8177 (0.8235) time: 0.1477 data: 0.0643 max mem: 9390 +Train: [49] [1800/6250] eta: 0:11:28 lr: 0.000069 grad: 0.0796 (0.0873) loss: 0.8213 (0.8234) time: 0.1423 data: 0.0568 max mem: 9390 +Train: [49] [1900/6250] eta: 0:11:11 lr: 0.000069 grad: 0.0839 (0.0872) loss: 0.8231 (0.8234) time: 0.1491 data: 0.0673 max mem: 9390 +Train: [49] [2000/6250] eta: 0:10:53 lr: 0.000069 grad: 0.0845 (0.0872) loss: 0.8178 (0.8234) time: 0.1529 data: 0.0673 max mem: 9390 +Train: [49] [2100/6250] eta: 0:10:38 lr: 0.000069 grad: 0.0871 (0.0871) loss: 0.8219 (0.8233) time: 0.1559 data: 0.0755 max mem: 9390 +Train: [49] [2200/6250] eta: 0:10:23 lr: 0.000069 grad: 0.0798 (0.0871) loss: 0.8291 (0.8234) time: 0.1965 data: 0.1166 max mem: 9390 +Train: [49] [2300/6250] eta: 0:10:05 lr: 0.000069 grad: 0.0809 (0.0870) loss: 0.8249 (0.8235) time: 0.1052 data: 0.0170 max mem: 9390 +Train: [49] [2400/6250] eta: 0:09:48 lr: 0.000069 grad: 0.0828 (0.0870) loss: 0.8220 (0.8235) time: 0.1399 data: 0.0468 max mem: 9390 +Train: [49] [2500/6250] eta: 0:09:34 lr: 0.000069 grad: 0.0880 (0.0869) loss: 0.8204 (0.8235) time: 0.1678 data: 0.0874 max mem: 9390 +Train: [49] [2600/6250] eta: 0:09:21 lr: 0.000069 grad: 0.0856 (0.0869) loss: 0.8237 (0.8235) time: 0.1745 data: 0.0951 max mem: 9390 +Train: [49] [2700/6250] eta: 0:09:05 lr: 0.000069 grad: 0.0904 (0.0869) loss: 0.8270 (0.8234) time: 0.1374 data: 0.0578 max mem: 9390 +Train: [49] [2800/6250] eta: 0:08:49 lr: 0.000069 grad: 0.0900 (0.0870) loss: 0.8264 (0.8234) time: 0.1352 data: 0.0529 max mem: 9390 +Train: [49] [2900/6250] eta: 0:08:33 lr: 0.000069 grad: 0.0838 (0.0871) loss: 0.8273 (0.8234) time: 0.1431 data: 0.0653 max mem: 9390 +Train: [49] [3000/6250] eta: 0:08:18 lr: 0.000069 grad: 0.0877 (0.0871) loss: 0.8230 (0.8233) time: 0.1394 data: 0.0493 max mem: 9390 +Train: [49] [3100/6250] eta: 0:08:02 lr: 0.000069 grad: 0.0853 (0.0871) loss: 0.8255 (0.8233) time: 0.1401 data: 0.0538 max mem: 9390 +Train: [49] [3200/6250] eta: 0:07:46 lr: 0.000069 grad: 0.0875 (0.0873) loss: 0.8144 (0.8232) time: 0.1637 data: 0.0764 max mem: 9390 +Train: [49] [3300/6250] eta: 0:07:29 lr: 0.000069 grad: 0.0871 (0.0873) loss: 0.8204 (0.8231) time: 0.1348 data: 0.0439 max mem: 9390 +Train: [49] [3400/6250] eta: 0:07:14 lr: 0.000069 grad: 0.0805 (0.0874) loss: 0.8267 (0.8229) time: 0.1661 data: 0.0824 max mem: 9390 +Train: [49] [3500/6250] eta: 0:06:57 lr: 0.000069 grad: 0.0829 (0.0875) loss: 0.8143 (0.8227) time: 0.1318 data: 0.0429 max mem: 9390 +Train: [49] [3600/6250] eta: 0:06:42 lr: 0.000069 grad: 0.0909 (0.0876) loss: 0.8115 (0.8225) time: 0.1472 data: 0.0456 max mem: 9390 +Train: [49] [3700/6250] eta: 0:06:30 lr: 0.000069 grad: 0.0922 (0.0877) loss: 0.8085 (0.8223) time: 0.1461 data: 0.0545 max mem: 9390 +Train: [49] [3800/6250] eta: 0:06:15 lr: 0.000068 grad: 0.0860 (0.0877) loss: 0.8118 (0.8221) time: 0.1515 data: 0.0691 max mem: 9390 +Train: [49] [3900/6250] eta: 0:06:00 lr: 0.000068 grad: 0.0893 (0.0877) loss: 0.8120 (0.8220) time: 0.1598 data: 0.0757 max mem: 9390 +Train: [49] [4000/6250] eta: 0:05:45 lr: 0.000068 grad: 0.0852 (0.0877) loss: 0.8229 (0.8220) time: 0.1557 data: 0.0694 max mem: 9390 +Train: [49] [4100/6250] eta: 0:05:29 lr: 0.000068 grad: 0.0872 (0.0877) loss: 0.8129 (0.8219) time: 0.1452 data: 0.0525 max mem: 9390 +Train: [49] [4200/6250] eta: 0:05:14 lr: 0.000068 grad: 0.0918 (0.0878) loss: 0.8161 (0.8219) time: 0.1390 data: 0.0496 max mem: 9390 +Train: [49] [4300/6250] eta: 0:04:58 lr: 0.000068 grad: 0.0936 (0.0878) loss: 0.8196 (0.8218) time: 0.1641 data: 0.0787 max mem: 9390 +Train: [49] [4400/6250] eta: 0:04:43 lr: 0.000068 grad: 0.0865 (0.0879) loss: 0.8190 (0.8218) time: 0.1617 data: 0.0798 max mem: 9390 +Train: [49] [4500/6250] eta: 0:04:27 lr: 0.000068 grad: 0.0876 (0.0879) loss: 0.8189 (0.8218) time: 0.1474 data: 0.0636 max mem: 9390 +Train: [49] [4600/6250] eta: 0:04:12 lr: 0.000068 grad: 0.0830 (0.0879) loss: 0.8257 (0.8218) time: 0.1578 data: 0.0775 max mem: 9390 +Train: [49] [4700/6250] eta: 0:03:57 lr: 0.000068 grad: 0.0835 (0.0879) loss: 0.8234 (0.8218) time: 0.1423 data: 0.0592 max mem: 9390 +Train: [49] [4800/6250] eta: 0:03:41 lr: 0.000068 grad: 0.0902 (0.0879) loss: 0.8168 (0.8218) time: 0.1543 data: 0.0668 max mem: 9390 +Train: [49] [4900/6250] eta: 0:03:26 lr: 0.000068 grad: 0.0845 (0.0879) loss: 0.8261 (0.8218) time: 0.1559 data: 0.0718 max mem: 9390 +Train: [49] [5000/6250] eta: 0:03:10 lr: 0.000068 grad: 0.0854 (0.0878) loss: 0.8230 (0.8219) time: 0.1220 data: 0.0363 max mem: 9390 +Train: [49] [5100/6250] eta: 0:02:55 lr: 0.000068 grad: 0.0865 (0.0879) loss: 0.8270 (0.8219) time: 0.1265 data: 0.0391 max mem: 9390 +Train: [49] [5200/6250] eta: 0:02:39 lr: 0.000068 grad: 0.0843 (0.0878) loss: 0.8225 (0.8220) time: 0.1459 data: 0.0631 max mem: 9390 +Train: [49] [5300/6250] eta: 0:02:24 lr: 0.000068 grad: 0.0866 (0.0878) loss: 0.8283 (0.8220) time: 0.1501 data: 0.0614 max mem: 9390 +Train: [49] [5400/6250] eta: 0:02:09 lr: 0.000068 grad: 0.0849 (0.0878) loss: 0.8262 (0.8220) time: 0.1494 data: 0.0638 max mem: 9390 +Train: [49] [5500/6250] eta: 0:01:53 lr: 0.000068 grad: 0.0807 (0.0878) loss: 0.8222 (0.8220) time: 0.1286 data: 0.0417 max mem: 9390 +Train: [49] [5600/6250] eta: 0:01:38 lr: 0.000068 grad: 0.0877 (0.0878) loss: 0.8206 (0.8221) time: 0.1569 data: 0.0712 max mem: 9390 +Train: [49] [5700/6250] eta: 0:01:23 lr: 0.000068 grad: 0.0809 (0.0877) loss: 0.8254 (0.8221) time: 0.1282 data: 0.0437 max mem: 9390 +Train: [49] [5800/6250] eta: 0:01:08 lr: 0.000068 grad: 0.0821 (0.0877) loss: 0.8240 (0.8221) time: 0.1650 data: 0.0827 max mem: 9390 +Train: [49] [5900/6250] eta: 0:00:52 lr: 0.000068 grad: 0.0858 (0.0876) loss: 0.8220 (0.8221) time: 0.1918 data: 0.1136 max mem: 9390 +Train: [49] [6000/6250] eta: 0:00:37 lr: 0.000068 grad: 0.0800 (0.0876) loss: 0.8201 (0.8221) time: 0.1510 data: 0.0694 max mem: 9390 +Train: [49] [6100/6250] eta: 0:00:22 lr: 0.000068 grad: 0.0828 (0.0876) loss: 0.8195 (0.8221) time: 0.1740 data: 0.0960 max mem: 9390 +Train: [49] [6200/6250] eta: 0:00:07 lr: 0.000068 grad: 0.0884 (0.0876) loss: 0.8194 (0.8220) time: 0.1422 data: 0.0578 max mem: 9390 +Train: [49] [6249/6250] eta: 0:00:00 lr: 0.000068 grad: 0.0859 (0.0877) loss: 0.8206 (0.8220) time: 0.1629 data: 0.0836 max mem: 9390 +Train: [49] Total time: 0:15:49 (0.1520 s / it) +Averaged stats: lr: 0.000068 grad: 0.0859 (0.0877) loss: 0.8206 (0.8220) +Eval (hcp-train-subset): [49] [ 0/62] eta: 0:03:14 loss: 0.8510 (0.8510) time: 3.1444 data: 3.0723 max mem: 9390 +Eval (hcp-train-subset): [49] [61/62] eta: 0:00:00 loss: 0.8399 (0.8393) time: 0.1071 data: 0.0822 max mem: 9390 +Eval (hcp-train-subset): [49] Total time: 0:00:12 (0.1973 s / it) +Averaged stats (hcp-train-subset): loss: 0.8399 (0.8393) +Making plots (hcp-train-subset): example=7 +Eval (hcp-val): [49] [ 0/62] eta: 0:02:54 loss: 0.8339 (0.8339) time: 2.8120 data: 2.7298 max mem: 9390 +Eval (hcp-val): [49] [61/62] eta: 0:00:00 loss: 0.8353 (0.8366) time: 0.1082 data: 0.0824 max mem: 9390 +Eval (hcp-val): [49] Total time: 0:00:12 (0.2041 s / it) +Averaged stats (hcp-val): loss: 0.8353 (0.8366) +Making plots (hcp-val): example=12 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +Train: [50] [ 0/6250] eta: 8:28:54 lr: 0.000068 grad: 0.1183 (0.1183) loss: 0.8375 (0.8375) time: 4.8855 data: 4.7508 max mem: 9390 +Train: [50] [ 100/6250] eta: 0:20:29 lr: 0.000068 grad: 0.0893 (0.0985) loss: 0.8171 (0.8242) time: 0.1716 data: 0.0871 max mem: 9390 +Train: [50] [ 200/6250] eta: 0:18:15 lr: 0.000068 grad: 0.0932 (0.0954) loss: 0.8071 (0.8195) time: 0.1641 data: 0.0750 max mem: 9390 +Train: [50] [ 300/6250] eta: 0:17:33 lr: 0.000068 grad: 0.0903 (0.0933) loss: 0.8260 (0.8191) time: 0.1884 data: 0.1037 max mem: 9390 +Train: [50] [ 400/6250] eta: 0:16:59 lr: 0.000068 grad: 0.0910 (0.0933) loss: 0.8213 (0.8186) time: 0.1506 data: 0.0637 max mem: 9390 +Train: [50] [ 500/6250] eta: 0:16:17 lr: 0.000067 grad: 0.0978 (0.0934) loss: 0.8219 (0.8190) time: 0.1470 data: 0.0574 max mem: 9390 +Train: [50] [ 600/6250] eta: 0:15:44 lr: 0.000067 grad: 0.0889 (0.0938) loss: 0.8181 (0.8193) time: 0.1387 data: 0.0547 max mem: 9390 +Train: [50] [ 700/6250] eta: 0:15:10 lr: 0.000067 grad: 0.0975 (0.0943) loss: 0.8167 (0.8188) time: 0.1306 data: 0.0428 max mem: 9390 +Train: [50] [ 800/6250] eta: 0:14:46 lr: 0.000067 grad: 0.0840 (0.0940) loss: 0.8260 (0.8188) time: 0.1589 data: 0.0845 max mem: 9390 +Train: [50] [ 900/6250] eta: 0:14:23 lr: 0.000067 grad: 0.0868 (0.0941) loss: 0.8208 (0.8187) time: 0.1525 data: 0.0668 max mem: 9390 +Train: [50] [1000/6250] eta: 0:13:59 lr: 0.000067 grad: 0.0857 (0.0938) loss: 0.8145 (0.8187) time: 0.1346 data: 0.0533 max mem: 9390 +Train: [50] [1100/6250] eta: 0:13:38 lr: 0.000067 grad: 0.0911 (0.0936) loss: 0.8166 (0.8186) time: 0.1267 data: 0.0361 max mem: 9390 +Train: [50] [1200/6250] eta: 0:13:15 lr: 0.000067 grad: 0.0839 (0.0930) loss: 0.8199 (0.8187) time: 0.1304 data: 0.0478 max mem: 9390 +Train: [50] [1300/6250] eta: 0:12:56 lr: 0.000067 grad: 0.0893 (0.0928) loss: 0.8215 (0.8187) time: 0.1423 data: 0.0586 max mem: 9390 +Train: [50] [1400/6250] eta: 0:12:38 lr: 0.000067 grad: 0.0888 (0.0926) loss: 0.8178 (0.8186) time: 0.1522 data: 0.0756 max mem: 9390 +Train: [50] [1500/6250] eta: 0:12:18 lr: 0.000067 grad: 0.0937 (0.0924) loss: 0.8205 (0.8187) time: 0.1428 data: 0.0562 max mem: 9390 +Train: [50] [1600/6250] eta: 0:12:00 lr: 0.000067 grad: 0.0891 (0.0923) loss: 0.8174 (0.8187) time: 0.1485 data: 0.0601 max mem: 9390 +Train: [50] [1700/6250] eta: 0:11:46 lr: 0.000067 grad: 0.0899 (0.0923) loss: 0.8143 (0.8186) time: 0.1783 data: 0.0950 max mem: 9390 +Train: [50] [1800/6250] eta: 0:11:28 lr: 0.000067 grad: 0.0873 (0.0925) loss: 0.8187 (0.8184) time: 0.1306 data: 0.0391 max mem: 9390 +Train: [50] [1900/6250] eta: 0:11:11 lr: 0.000067 grad: 0.0855 (0.0927) loss: 0.8181 (0.8183) time: 0.1277 data: 0.0486 max mem: 9390 +Train: [50] [2000/6250] eta: 0:10:54 lr: 0.000067 grad: 0.0879 (0.0927) loss: 0.8195 (0.8184) time: 0.1412 data: 0.0590 max mem: 9390 +Train: [50] [2100/6250] eta: 0:10:38 lr: 0.000067 grad: 0.0926 (0.0927) loss: 0.8082 (0.8184) time: 0.1398 data: 0.0489 max mem: 9390 +Train: [50] [2200/6250] eta: 0:10:21 lr: 0.000067 grad: 0.0883 (0.0926) loss: 0.8268 (0.8185) time: 0.1604 data: 0.0749 max mem: 9390 +Train: [50] [2300/6250] eta: 0:10:05 lr: 0.000067 grad: 0.0883 (0.0925) loss: 0.8224 (0.8186) time: 0.1669 data: 0.0839 max mem: 9390 +Train: [50] [2400/6250] eta: 0:09:49 lr: 0.000067 grad: 0.0879 (0.0925) loss: 0.8210 (0.8187) time: 0.1458 data: 0.0695 max mem: 9390 +Train: [50] [2500/6250] eta: 0:09:33 lr: 0.000067 grad: 0.0867 (0.0924) loss: 0.8190 (0.8188) time: 0.1437 data: 0.0668 max mem: 9390 +Train: [50] [2600/6250] eta: 0:09:17 lr: 0.000067 grad: 0.0946 (0.0924) loss: 0.8182 (0.8190) time: 0.1494 data: 0.0645 max mem: 9390 +Train: [50] [2700/6250] eta: 0:09:02 lr: 0.000067 grad: 0.0868 (0.0923) loss: 0.8230 (0.8191) time: 0.1542 data: 0.0719 max mem: 9390 +Train: [50] [2800/6250] eta: 0:08:45 lr: 0.000067 grad: 0.0845 (0.0923) loss: 0.8253 (0.8193) time: 0.1375 data: 0.0556 max mem: 9390 +Train: [50] [2900/6250] eta: 0:08:29 lr: 0.000067 grad: 0.0933 (0.0923) loss: 0.8198 (0.8193) time: 0.1295 data: 0.0441 max mem: 9390 +Train: [50] [3000/6250] eta: 0:08:13 lr: 0.000067 grad: 0.0839 (0.0922) loss: 0.8243 (0.8195) time: 0.1232 data: 0.0418 max mem: 9390 +Train: [50] [3100/6250] eta: 0:07:57 lr: 0.000067 grad: 0.0878 (0.0921) loss: 0.8184 (0.8195) time: 0.1541 data: 0.0721 max mem: 9390 +Train: [50] [3200/6250] eta: 0:07:41 lr: 0.000067 grad: 0.0898 (0.0921) loss: 0.8147 (0.8196) time: 0.1336 data: 0.0479 max mem: 9390 +Train: [50] [3300/6250] eta: 0:07:25 lr: 0.000067 grad: 0.0925 (0.0921) loss: 0.8225 (0.8196) time: 0.1327 data: 0.0464 max mem: 9390 +Train: [50] [3400/6250] eta: 0:07:09 lr: 0.000067 grad: 0.0858 (0.0922) loss: 0.8191 (0.8196) time: 0.1534 data: 0.0727 max mem: 9390 +Train: [50] [3500/6250] eta: 0:06:53 lr: 0.000067 grad: 0.0858 (0.0922) loss: 0.8199 (0.8196) time: 0.1443 data: 0.0564 max mem: 9390 +Train: [50] [3600/6250] eta: 0:06:38 lr: 0.000066 grad: 0.0866 (0.0922) loss: 0.8292 (0.8196) time: 0.1469 data: 0.0617 max mem: 9390 +Train: [50] [3700/6250] eta: 0:06:23 lr: 0.000066 grad: 0.0855 (0.0921) loss: 0.8191 (0.8197) time: 0.1470 data: 0.0636 max mem: 9390 +Train: [50] [3800/6250] eta: 0:06:07 lr: 0.000066 grad: 0.0821 (0.0921) loss: 0.8263 (0.8197) time: 0.1504 data: 0.0710 max mem: 9390 +Train: [50] [3900/6250] eta: 0:05:52 lr: 0.000066 grad: 0.0904 (0.0920) loss: 0.8225 (0.8198) time: 0.1417 data: 0.0576 max mem: 9390 +Train: [50] [4000/6250] eta: 0:05:37 lr: 0.000066 grad: 0.0823 (0.0919) loss: 0.8224 (0.8198) time: 0.1533 data: 0.0707 max mem: 9390 +Train: [50] [4100/6250] eta: 0:05:21 lr: 0.000066 grad: 0.0882 (0.0919) loss: 0.8144 (0.8198) time: 0.1434 data: 0.0641 max mem: 9390 +Train: [50] [4200/6250] eta: 0:05:06 lr: 0.000066 grad: 0.0855 (0.0919) loss: 0.8206 (0.8198) time: 0.1517 data: 0.0740 max mem: 9390 +Train: [50] [4300/6250] eta: 0:04:51 lr: 0.000066 grad: 0.0852 (0.0919) loss: 0.8252 (0.8198) time: 0.1288 data: 0.0460 max mem: 9390 +Train: [50] [4400/6250] eta: 0:04:36 lr: 0.000066 grad: 0.0924 (0.0918) loss: 0.8147 (0.8198) time: 0.1702 data: 0.0842 max mem: 9390 +Train: [50] [4500/6250] eta: 0:04:22 lr: 0.000066 grad: 0.0950 (0.0919) loss: 0.8171 (0.8198) time: 0.1601 data: 0.0705 max mem: 9390 +Train: [50] [4600/6250] eta: 0:04:07 lr: 0.000066 grad: 0.0905 (0.0919) loss: 0.8227 (0.8198) time: 0.1517 data: 0.0725 max mem: 9390 +Train: [50] [4700/6250] eta: 0:03:52 lr: 0.000066 grad: 0.0898 (0.0918) loss: 0.8207 (0.8198) time: 0.1601 data: 0.0737 max mem: 9390 +Train: [50] [4800/6250] eta: 0:03:37 lr: 0.000066 grad: 0.0847 (0.0918) loss: 0.8136 (0.8198) time: 0.1439 data: 0.0581 max mem: 9390 +Train: [50] [4900/6250] eta: 0:03:22 lr: 0.000066 grad: 0.0856 (0.0918) loss: 0.8166 (0.8198) time: 0.1585 data: 0.0776 max mem: 9390 +Train: [50] [5000/6250] eta: 0:03:07 lr: 0.000066 grad: 0.0917 (0.0918) loss: 0.8186 (0.8198) time: 0.1495 data: 0.0674 max mem: 9390 +Train: [50] [5100/6250] eta: 0:02:52 lr: 0.000066 grad: 0.0898 (0.0919) loss: 0.8179 (0.8198) time: 0.1578 data: 0.0723 max mem: 9390 +Train: [50] [5200/6250] eta: 0:02:37 lr: 0.000066 grad: 0.0863 (0.0919) loss: 0.8181 (0.8198) time: 0.1299 data: 0.0452 max mem: 9390 +Train: [50] [5300/6250] eta: 0:02:22 lr: 0.000066 grad: 0.0854 (0.0919) loss: 0.8200 (0.8198) time: 0.1330 data: 0.0475 max mem: 9390 +Train: [50] [5400/6250] eta: 0:02:07 lr: 0.000066 grad: 0.0858 (0.0919) loss: 0.8178 (0.8197) time: 0.1444 data: 0.0605 max mem: 9390 +Train: [50] [5500/6250] eta: 0:01:52 lr: 0.000066 grad: 0.0902 (0.0919) loss: 0.8170 (0.8197) time: 0.1497 data: 0.0636 max mem: 9390 +Train: [50] [5600/6250] eta: 0:01:37 lr: 0.000066 grad: 0.0877 (0.0919) loss: 0.8229 (0.8197) time: 0.1487 data: 0.0629 max mem: 9390 +Train: [50] [5700/6250] eta: 0:01:22 lr: 0.000066 grad: 0.0879 (0.0919) loss: 0.8208 (0.8197) time: 0.1265 data: 0.0441 max mem: 9390 +Train: [50] [5800/6250] eta: 0:01:07 lr: 0.000066 grad: 0.0888 (0.0918) loss: 0.8199 (0.8198) time: 0.1350 data: 0.0511 max mem: 9390 +Train: [50] [5900/6250] eta: 0:00:52 lr: 0.000066 grad: 0.0866 (0.0918) loss: 0.8177 (0.8198) time: 0.1479 data: 0.0575 max mem: 9390 +Train: [50] [6000/6250] eta: 0:00:37 lr: 0.000066 grad: 0.0843 (0.0918) loss: 0.8211 (0.8198) time: 0.1543 data: 0.0752 max mem: 9390 +Train: [50] [6100/6250] eta: 0:00:22 lr: 0.000066 grad: 0.0849 (0.0917) loss: 0.8231 (0.8198) time: 0.1288 data: 0.0473 max mem: 9390 +Train: [50] [6200/6250] eta: 0:00:07 lr: 0.000066 grad: 0.0850 (0.0917) loss: 0.8227 (0.8199) time: 0.1534 data: 0.0729 max mem: 9390 +Train: [50] [6249/6250] eta: 0:00:00 lr: 0.000066 grad: 0.0881 (0.0917) loss: 0.8239 (0.8199) time: 0.1534 data: 0.0725 max mem: 9390 +Train: [50] Total time: 0:15:39 (0.1503 s / it) +Averaged stats: lr: 0.000066 grad: 0.0881 (0.0917) loss: 0.8239 (0.8199) +Eval (hcp-train-subset): [50] [ 0/62] eta: 0:05:06 loss: 0.8508 (0.8508) time: 4.9494 data: 4.9191 max mem: 9390 +Eval (hcp-train-subset): [50] [61/62] eta: 0:00:00 loss: 0.8378 (0.8387) time: 0.1326 data: 0.1058 max mem: 9390 +Eval (hcp-train-subset): [50] Total time: 0:00:13 (0.2129 s / it) +Averaged stats (hcp-train-subset): loss: 0.8378 (0.8387) +Eval (hcp-val): [50] [ 0/62] eta: 0:03:00 loss: 0.8330 (0.8330) time: 2.9187 data: 2.8418 max mem: 9390 +Eval (hcp-val): [50] [61/62] eta: 0:00:00 loss: 0.8347 (0.8358) time: 0.1293 data: 0.1041 max mem: 9390 +Eval (hcp-val): [50] Total time: 0:00:12 (0.2093 s / it) +Averaged stats (hcp-val): loss: 0.8347 (0.8358) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +Train: [51] [ 0/6250] eta: 9:55:18 lr: 0.000066 grad: 0.1578 (0.1578) loss: 0.8528 (0.8528) time: 5.7149 data: 5.6061 max mem: 9390 +Train: [51] [ 100/6250] eta: 0:21:03 lr: 0.000066 grad: 0.0871 (0.0929) loss: 0.8250 (0.8335) time: 0.1459 data: 0.0577 max mem: 9390 +Train: [51] [ 200/6250] eta: 0:18:39 lr: 0.000066 grad: 0.0792 (0.0897) loss: 0.8344 (0.8324) time: 0.1423 data: 0.0523 max mem: 9390 +Train: [51] [ 300/6250] eta: 0:17:52 lr: 0.000065 grad: 0.0858 (0.0900) loss: 0.8272 (0.8307) time: 0.1906 data: 0.1086 max mem: 9390 +Train: [51] [ 400/6250] eta: 0:17:04 lr: 0.000065 grad: 0.0809 (0.0901) loss: 0.8289 (0.8299) time: 0.1778 data: 0.0942 max mem: 9390 +Train: [51] [ 500/6250] eta: 0:16:14 lr: 0.000065 grad: 0.0814 (0.0899) loss: 0.8230 (0.8288) time: 0.1190 data: 0.0281 max mem: 9390 +Train: [51] [ 600/6250] eta: 0:15:41 lr: 0.000065 grad: 0.0851 (0.0895) loss: 0.8285 (0.8279) time: 0.1703 data: 0.0863 max mem: 9390 +Train: [51] [ 700/6250] eta: 0:15:10 lr: 0.000065 grad: 0.0827 (0.0889) loss: 0.8292 (0.8275) time: 0.1562 data: 0.0762 max mem: 9390 +Train: [51] [ 800/6250] eta: 0:14:49 lr: 0.000065 grad: 0.0905 (0.0883) loss: 0.8196 (0.8274) time: 0.1588 data: 0.0763 max mem: 9390 +Train: [51] [ 900/6250] eta: 0:14:23 lr: 0.000065 grad: 0.0813 (0.0877) loss: 0.8256 (0.8273) time: 0.1367 data: 0.0507 max mem: 9390 +Train: [51] [1000/6250] eta: 0:14:02 lr: 0.000065 grad: 0.0857 (0.0873) loss: 0.8241 (0.8272) time: 0.1575 data: 0.0738 max mem: 9390 +Train: [51] [1100/6250] eta: 0:13:44 lr: 0.000065 grad: 0.0817 (0.0870) loss: 0.8227 (0.8270) time: 0.1706 data: 0.0855 max mem: 9390 +Train: [51] [1200/6250] eta: 0:13:21 lr: 0.000065 grad: 0.0834 (0.0868) loss: 0.8293 (0.8269) time: 0.1433 data: 0.0635 max mem: 9390 +Train: [51] [1300/6250] eta: 0:13:02 lr: 0.000065 grad: 0.0908 (0.0870) loss: 0.8178 (0.8264) time: 0.1674 data: 0.0837 max mem: 9390 +Train: [51] [1400/6250] eta: 0:12:42 lr: 0.000065 grad: 0.0926 (0.0873) loss: 0.8229 (0.8259) time: 0.1346 data: 0.0529 max mem: 9390 +Train: [51] [1500/6250] eta: 0:12:39 lr: 0.000065 grad: 0.0895 (0.0875) loss: 0.8212 (0.8255) time: 0.1957 data: 0.1177 max mem: 9390 +Train: [51] [1600/6250] eta: 0:12:24 lr: 0.000065 grad: 0.0880 (0.0877) loss: 0.8175 (0.8251) time: 0.1358 data: 0.0578 max mem: 9390 +Train: [51] [1700/6250] eta: 0:12:10 lr: 0.000065 grad: 0.0895 (0.0880) loss: 0.8187 (0.8248) time: 0.1803 data: 0.0873 max mem: 9390 +Train: [51] [1800/6250] eta: 0:11:52 lr: 0.000065 grad: 0.0851 (0.0881) loss: 0.8241 (0.8245) time: 0.1623 data: 0.0859 max mem: 9390 +Train: [51] [1900/6250] eta: 0:11:38 lr: 0.000065 grad: 0.0913 (0.0882) loss: 0.8196 (0.8243) time: 0.1524 data: 0.0647 max mem: 9390 +Train: [51] [2000/6250] eta: 0:11:25 lr: 0.000065 grad: 0.0854 (0.0882) loss: 0.8179 (0.8241) time: 0.1667 data: 0.0768 max mem: 9390 +Train: [51] [2100/6250] eta: 0:11:10 lr: 0.000065 grad: 0.0884 (0.0882) loss: 0.8205 (0.8240) time: 0.1544 data: 0.0693 max mem: 9390 +Train: [51] [2200/6250] eta: 0:10:53 lr: 0.000065 grad: 0.0837 (0.0883) loss: 0.8171 (0.8238) time: 0.1613 data: 0.0740 max mem: 9390 +Train: [51] [2300/6250] eta: 0:10:37 lr: 0.000065 grad: 0.0871 (0.0885) loss: 0.8236 (0.8237) time: 0.1410 data: 0.0508 max mem: 9390 +Train: [51] [2400/6250] eta: 0:10:20 lr: 0.000065 grad: 0.0882 (0.0886) loss: 0.8228 (0.8235) time: 0.1402 data: 0.0546 max mem: 9390 +Train: [51] [2500/6250] eta: 0:10:04 lr: 0.000065 grad: 0.0946 (0.0888) loss: 0.8166 (0.8233) time: 0.1680 data: 0.0772 max mem: 9390 +Train: [51] [2600/6250] eta: 0:09:47 lr: 0.000065 grad: 0.0879 (0.0888) loss: 0.8227 (0.8232) time: 0.1340 data: 0.0372 max mem: 9390 +Train: [51] [2700/6250] eta: 0:09:30 lr: 0.000065 grad: 0.0914 (0.0889) loss: 0.8234 (0.8231) time: 0.1341 data: 0.0412 max mem: 9390 +Train: [51] [2800/6250] eta: 0:09:11 lr: 0.000065 grad: 0.0915 (0.0889) loss: 0.8126 (0.8229) time: 0.1546 data: 0.0738 max mem: 9390 +Train: [51] [2900/6250] eta: 0:08:54 lr: 0.000065 grad: 0.0892 (0.0890) loss: 0.8192 (0.8227) time: 0.1494 data: 0.0689 max mem: 9390 +Train: [51] [3000/6250] eta: 0:08:36 lr: 0.000065 grad: 0.0815 (0.0890) loss: 0.8277 (0.8226) time: 0.1395 data: 0.0581 max mem: 9390 +Train: [51] [3100/6250] eta: 0:08:20 lr: 0.000065 grad: 0.0929 (0.0891) loss: 0.8195 (0.8225) time: 0.1534 data: 0.0731 max mem: 9390 +Train: [51] [3200/6250] eta: 0:08:02 lr: 0.000065 grad: 0.0873 (0.0892) loss: 0.8239 (0.8224) time: 0.1446 data: 0.0672 max mem: 9390 +Train: [51] [3300/6250] eta: 0:07:46 lr: 0.000065 grad: 0.0867 (0.0892) loss: 0.8227 (0.8224) time: 0.1668 data: 0.0880 max mem: 9390 +Train: [51] [3400/6250] eta: 0:07:30 lr: 0.000064 grad: 0.0818 (0.0892) loss: 0.8219 (0.8224) time: 0.1323 data: 0.0517 max mem: 9390 +Train: [51] [3500/6250] eta: 0:07:13 lr: 0.000064 grad: 0.0886 (0.0892) loss: 0.8167 (0.8223) time: 0.1443 data: 0.0614 max mem: 9390 +Train: [51] [3600/6250] eta: 0:06:58 lr: 0.000064 grad: 0.0867 (0.0893) loss: 0.8257 (0.8223) time: 0.1538 data: 0.0777 max mem: 9390 +Train: [51] [3700/6250] eta: 0:06:44 lr: 0.000064 grad: 0.0865 (0.0892) loss: 0.8194 (0.8222) time: 0.2080 data: 0.1279 max mem: 9390 +Train: [51] [3800/6250] eta: 0:06:29 lr: 0.000064 grad: 0.0874 (0.0893) loss: 0.8261 (0.8222) time: 0.1849 data: 0.1090 max mem: 9390 +Train: [51] [3900/6250] eta: 0:06:14 lr: 0.000064 grad: 0.0923 (0.0893) loss: 0.8165 (0.8221) time: 0.1415 data: 0.0642 max mem: 9390 +Train: [51] [4000/6250] eta: 0:05:58 lr: 0.000064 grad: 0.0907 (0.0894) loss: 0.8203 (0.8220) time: 0.1626 data: 0.0834 max mem: 9390 +Train: [51] [4100/6250] eta: 0:05:43 lr: 0.000064 grad: 0.0927 (0.0894) loss: 0.8147 (0.8218) time: 0.1772 data: 0.0967 max mem: 9390 +Train: [51] [4200/6250] eta: 0:05:28 lr: 0.000064 grad: 0.0847 (0.0895) loss: 0.8192 (0.8217) time: 0.1631 data: 0.0757 max mem: 9390 +Train: [51] [4300/6250] eta: 0:05:11 lr: 0.000064 grad: 0.0949 (0.0897) loss: 0.8130 (0.8215) time: 0.1496 data: 0.0709 max mem: 9390 +Train: [51] [4400/6250] eta: 0:04:55 lr: 0.000064 grad: 0.0939 (0.0898) loss: 0.8181 (0.8214) time: 0.1307 data: 0.0462 max mem: 9390 +Train: [51] [4500/6250] eta: 0:04:39 lr: 0.000064 grad: 0.0849 (0.0899) loss: 0.8226 (0.8213) time: 0.1360 data: 0.0570 max mem: 9390 +Train: [51] [4600/6250] eta: 0:04:22 lr: 0.000064 grad: 0.0917 (0.0900) loss: 0.8154 (0.8211) time: 0.1434 data: 0.0619 max mem: 9390 +Train: [51] [4700/6250] eta: 0:04:06 lr: 0.000064 grad: 0.0934 (0.0902) loss: 0.8139 (0.8210) time: 0.1477 data: 0.0569 max mem: 9390 +Train: [51] [4800/6250] eta: 0:03:50 lr: 0.000064 grad: 0.0940 (0.0903) loss: 0.8156 (0.8209) time: 0.1542 data: 0.0770 max mem: 9390 +Train: [51] [4900/6250] eta: 0:03:34 lr: 0.000064 grad: 0.1023 (0.0904) loss: 0.8170 (0.8208) time: 0.1442 data: 0.0653 max mem: 9390 +Train: [51] [5000/6250] eta: 0:03:17 lr: 0.000064 grad: 0.0906 (0.0906) loss: 0.8201 (0.8207) time: 0.1471 data: 0.0608 max mem: 9390 +Train: [51] [5100/6250] eta: 0:03:01 lr: 0.000064 grad: 0.0948 (0.0907) loss: 0.8129 (0.8205) time: 0.1399 data: 0.0560 max mem: 9390 +Train: [51] [5200/6250] eta: 0:02:45 lr: 0.000064 grad: 0.0918 (0.0909) loss: 0.8188 (0.8203) time: 0.1573 data: 0.0799 max mem: 9390 +Train: [51] [5300/6250] eta: 0:02:29 lr: 0.000064 grad: 0.0870 (0.0909) loss: 0.8132 (0.8202) time: 0.1466 data: 0.0584 max mem: 9390 +Train: [51] [5400/6250] eta: 0:02:14 lr: 0.000064 grad: 0.0927 (0.0909) loss: 0.8132 (0.8201) time: 0.1448 data: 0.0595 max mem: 9390 +Train: [51] [5500/6250] eta: 0:01:58 lr: 0.000064 grad: 0.0938 (0.0910) loss: 0.8139 (0.8200) time: 0.1445 data: 0.0639 max mem: 9390 +Train: [51] [5600/6250] eta: 0:01:42 lr: 0.000064 grad: 0.0911 (0.0912) loss: 0.8172 (0.8199) time: 0.1596 data: 0.0809 max mem: 9390 +Train: [51] [5700/6250] eta: 0:01:26 lr: 0.000064 grad: 0.0886 (0.0912) loss: 0.8124 (0.8198) time: 0.1060 data: 0.0149 max mem: 9390 +Train: [51] [5800/6250] eta: 0:01:10 lr: 0.000064 grad: 0.0880 (0.0913) loss: 0.8184 (0.8197) time: 0.1613 data: 0.0817 max mem: 9390 +Train: [51] [5900/6250] eta: 0:00:54 lr: 0.000064 grad: 0.0986 (0.0914) loss: 0.8135 (0.8196) time: 0.1448 data: 0.0594 max mem: 9390 +Train: [51] [6000/6250] eta: 0:00:39 lr: 0.000064 grad: 0.0929 (0.0915) loss: 0.8193 (0.8196) time: 0.1679 data: 0.0859 max mem: 9390 +Train: [51] [6100/6250] eta: 0:00:23 lr: 0.000064 grad: 0.0914 (0.0916) loss: 0.8182 (0.8195) time: 0.1585 data: 0.0844 max mem: 9390 +Train: [51] [6200/6250] eta: 0:00:07 lr: 0.000064 grad: 0.0930 (0.0916) loss: 0.8218 (0.8195) time: 0.1484 data: 0.0704 max mem: 9390 +Train: [51] [6249/6250] eta: 0:00:00 lr: 0.000064 grad: 0.0905 (0.0917) loss: 0.8186 (0.8195) time: 0.1351 data: 0.0577 max mem: 9390 +Train: [51] Total time: 0:16:22 (0.1571 s / it) +Averaged stats: lr: 0.000064 grad: 0.0905 (0.0917) loss: 0.8186 (0.8195) +Eval (hcp-train-subset): [51] [ 0/62] eta: 0:02:55 loss: 0.8436 (0.8436) time: 2.8294 data: 2.7400 max mem: 9390 +Eval (hcp-train-subset): [51] [61/62] eta: 0:00:00 loss: 0.8369 (0.8370) time: 0.1231 data: 0.0982 max mem: 9390 +Eval (hcp-train-subset): [51] Total time: 0:00:12 (0.1992 s / it) +Averaged stats (hcp-train-subset): loss: 0.8369 (0.8370) +Eval (hcp-val): [51] [ 0/62] eta: 0:02:48 loss: 0.8346 (0.8346) time: 2.7165 data: 2.6096 max mem: 9390 +Eval (hcp-val): [51] [61/62] eta: 0:00:00 loss: 0.8328 (0.8349) time: 0.1297 data: 0.1044 max mem: 9390 +Eval (hcp-val): [51] Total time: 0:00:12 (0.1956 s / it) +Averaged stats (hcp-val): loss: 0.8328 (0.8349) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +Train: [52] [ 0/6250] eta: 8:19:13 lr: 0.000064 grad: 0.0918 (0.0918) loss: 0.8678 (0.8678) time: 4.7925 data: 4.5840 max mem: 9390 +Train: [52] [ 100/6250] eta: 0:20:03 lr: 0.000063 grad: 0.0952 (0.0991) loss: 0.8177 (0.8351) time: 0.1370 data: 0.0498 max mem: 9390 +Train: [52] [ 200/6250] eta: 0:18:15 lr: 0.000063 grad: 0.0876 (0.0946) loss: 0.8258 (0.8304) time: 0.1715 data: 0.0820 max mem: 9390 +Train: [52] [ 300/6250] eta: 0:17:23 lr: 0.000063 grad: 0.0827 (0.0922) loss: 0.8248 (0.8301) time: 0.1735 data: 0.0775 max mem: 9390 +Train: [52] [ 400/6250] eta: 0:16:36 lr: 0.000063 grad: 0.0883 (0.0909) loss: 0.8287 (0.8300) time: 0.1483 data: 0.0611 max mem: 9390 +Train: [52] [ 500/6250] eta: 0:16:06 lr: 0.000063 grad: 0.0863 (0.0901) loss: 0.8232 (0.8293) time: 0.1418 data: 0.0501 max mem: 9390 +Train: [52] [ 600/6250] eta: 0:15:37 lr: 0.000063 grad: 0.0773 (0.0897) loss: 0.8286 (0.8291) time: 0.1730 data: 0.0884 max mem: 9390 +Train: [52] [ 700/6250] eta: 0:15:12 lr: 0.000063 grad: 0.0914 (0.0897) loss: 0.8267 (0.8287) time: 0.1536 data: 0.0713 max mem: 9390 +Train: [52] [ 800/6250] eta: 0:14:53 lr: 0.000063 grad: 0.0902 (0.0897) loss: 0.8205 (0.8282) time: 0.1678 data: 0.0856 max mem: 9390 +Train: [52] [ 900/6250] eta: 0:14:31 lr: 0.000063 grad: 0.0853 (0.0894) loss: 0.8260 (0.8278) time: 0.1573 data: 0.0730 max mem: 9390 +Train: [52] [1000/6250] eta: 0:14:07 lr: 0.000063 grad: 0.0835 (0.0891) loss: 0.8216 (0.8274) time: 0.1441 data: 0.0598 max mem: 9390 +Train: [52] [1100/6250] eta: 0:13:43 lr: 0.000063 grad: 0.0889 (0.0891) loss: 0.8254 (0.8269) time: 0.1429 data: 0.0609 max mem: 9390 +Train: [52] [1200/6250] eta: 0:13:23 lr: 0.000063 grad: 0.0870 (0.0892) loss: 0.8201 (0.8263) time: 0.1542 data: 0.0561 max mem: 9390 +Train: [52] [1300/6250] eta: 0:13:06 lr: 0.000063 grad: 0.0893 (0.0892) loss: 0.8135 (0.8257) time: 0.1705 data: 0.0851 max mem: 9390 +Train: [52] [1400/6250] eta: 0:12:48 lr: 0.000063 grad: 0.0845 (0.0895) loss: 0.8227 (0.8251) time: 0.1465 data: 0.0628 max mem: 9390 +Train: [52] [1500/6250] eta: 0:12:30 lr: 0.000063 grad: 0.0873 (0.0895) loss: 0.8198 (0.8247) time: 0.1474 data: 0.0662 max mem: 9390 +Train: [52] [1600/6250] eta: 0:12:14 lr: 0.000063 grad: 0.0936 (0.0897) loss: 0.8119 (0.8244) time: 0.1398 data: 0.0563 max mem: 9390 +Train: [52] [1700/6250] eta: 0:11:56 lr: 0.000063 grad: 0.1033 (0.0899) loss: 0.8264 (0.8240) time: 0.1490 data: 0.0633 max mem: 9390 +Train: [52] [1800/6250] eta: 0:11:39 lr: 0.000063 grad: 0.0886 (0.0901) loss: 0.8275 (0.8238) time: 0.1565 data: 0.0769 max mem: 9390 +Train: [52] [1900/6250] eta: 0:11:21 lr: 0.000063 grad: 0.0881 (0.0902) loss: 0.8182 (0.8235) time: 0.1318 data: 0.0518 max mem: 9390 +Train: [52] [2000/6250] eta: 0:11:05 lr: 0.000063 grad: 0.0903 (0.0903) loss: 0.8211 (0.8233) time: 0.1543 data: 0.0773 max mem: 9390 +Train: [52] [2100/6250] eta: 0:10:48 lr: 0.000063 grad: 0.0908 (0.0905) loss: 0.8156 (0.8230) time: 0.1584 data: 0.0749 max mem: 9390 +Train: [52] [2200/6250] eta: 0:10:32 lr: 0.000063 grad: 0.0878 (0.0906) loss: 0.8178 (0.8228) time: 0.1212 data: 0.0328 max mem: 9390 +Train: [52] [2300/6250] eta: 0:10:14 lr: 0.000063 grad: 0.0923 (0.0908) loss: 0.8213 (0.8225) time: 0.1388 data: 0.0474 max mem: 9390 +Train: [52] [2400/6250] eta: 0:09:57 lr: 0.000063 grad: 0.0957 (0.0909) loss: 0.8147 (0.8223) time: 0.1495 data: 0.0625 max mem: 9390 +Train: [52] [2500/6250] eta: 0:09:41 lr: 0.000063 grad: 0.0929 (0.0911) loss: 0.8127 (0.8221) time: 0.1351 data: 0.0536 max mem: 9390 +Train: [52] [2600/6250] eta: 0:09:24 lr: 0.000063 grad: 0.0918 (0.0912) loss: 0.8262 (0.8220) time: 0.1331 data: 0.0490 max mem: 9390 +Train: [52] [2700/6250] eta: 0:09:08 lr: 0.000063 grad: 0.0903 (0.0912) loss: 0.8224 (0.8219) time: 0.1677 data: 0.0862 max mem: 9390 +Train: [52] [2800/6250] eta: 0:08:51 lr: 0.000063 grad: 0.0918 (0.0914) loss: 0.8151 (0.8216) time: 0.1495 data: 0.0652 max mem: 9390 +Train: [52] [2900/6250] eta: 0:08:35 lr: 0.000063 grad: 0.0924 (0.0916) loss: 0.8235 (0.8214) time: 0.1444 data: 0.0590 max mem: 9390 +Train: [52] [3000/6250] eta: 0:08:20 lr: 0.000063 grad: 0.0881 (0.0917) loss: 0.8245 (0.8214) time: 0.1754 data: 0.0945 max mem: 9390 +Train: [52] [3100/6250] eta: 0:08:04 lr: 0.000063 grad: 0.0954 (0.0918) loss: 0.8134 (0.8212) time: 0.1714 data: 0.0912 max mem: 9390 +Train: [52] [3200/6250] eta: 0:07:48 lr: 0.000062 grad: 0.0876 (0.0919) loss: 0.8216 (0.8211) time: 0.1327 data: 0.0553 max mem: 9390 +Train: [52] [3300/6250] eta: 0:07:33 lr: 0.000062 grad: 0.0965 (0.0920) loss: 0.8032 (0.8210) time: 0.1604 data: 0.0804 max mem: 9390 +Train: [52] [3400/6250] eta: 0:07:17 lr: 0.000062 grad: 0.0908 (0.0921) loss: 0.8202 (0.8209) time: 0.1321 data: 0.0464 max mem: 9390 +Train: [52] [3500/6250] eta: 0:07:00 lr: 0.000062 grad: 0.1024 (0.0923) loss: 0.8212 (0.8208) time: 0.1364 data: 0.0526 max mem: 9390 +Train: [52] [3600/6250] eta: 0:06:45 lr: 0.000062 grad: 0.0879 (0.0924) loss: 0.8194 (0.8207) time: 0.1508 data: 0.0668 max mem: 9390 +Train: [52] [3700/6250] eta: 0:06:29 lr: 0.000062 grad: 0.0888 (0.0925) loss: 0.8212 (0.8206) time: 0.1384 data: 0.0527 max mem: 9390 +Train: [52] [3800/6250] eta: 0:06:14 lr: 0.000062 grad: 0.0922 (0.0927) loss: 0.8185 (0.8205) time: 0.1479 data: 0.0679 max mem: 9390 +Train: [52] [3900/6250] eta: 0:05:58 lr: 0.000062 grad: 0.0939 (0.0929) loss: 0.8189 (0.8204) time: 0.1348 data: 0.0475 max mem: 9390 +Train: [52] [4000/6250] eta: 0:05:42 lr: 0.000062 grad: 0.0893 (0.0929) loss: 0.8265 (0.8203) time: 0.1407 data: 0.0504 max mem: 9390 +Train: [52] [4100/6250] eta: 0:05:27 lr: 0.000062 grad: 0.0973 (0.0931) loss: 0.8148 (0.8203) time: 0.1498 data: 0.0680 max mem: 9390 +Train: [52] [4200/6250] eta: 0:05:11 lr: 0.000062 grad: 0.0887 (0.0931) loss: 0.8203 (0.8203) time: 0.1596 data: 0.0692 max mem: 9390 +Train: [52] [4300/6250] eta: 0:04:55 lr: 0.000062 grad: 0.0924 (0.0931) loss: 0.8200 (0.8203) time: 0.1512 data: 0.0705 max mem: 9390 +Train: [52] [4400/6250] eta: 0:04:40 lr: 0.000062 grad: 0.0918 (0.0932) loss: 0.8235 (0.8203) time: 0.1667 data: 0.0891 max mem: 9390 +Train: [52] [4500/6250] eta: 0:04:25 lr: 0.000062 grad: 0.0923 (0.0933) loss: 0.8239 (0.8204) time: 0.1313 data: 0.0507 max mem: 9390 +Train: [52] [4600/6250] eta: 0:04:10 lr: 0.000062 grad: 0.0905 (0.0934) loss: 0.8224 (0.8204) time: 0.1678 data: 0.0847 max mem: 9390 +Train: [52] [4700/6250] eta: 0:03:55 lr: 0.000062 grad: 0.0879 (0.0935) loss: 0.8212 (0.8203) time: 0.1758 data: 0.0957 max mem: 9390 +Train: [52] [4800/6250] eta: 0:03:40 lr: 0.000062 grad: 0.0935 (0.0935) loss: 0.8175 (0.8203) time: 0.1477 data: 0.0657 max mem: 9390 +Train: [52] [4900/6250] eta: 0:03:25 lr: 0.000062 grad: 0.0933 (0.0936) loss: 0.8214 (0.8203) time: 0.1345 data: 0.0338 max mem: 9390 +Train: [52] [5000/6250] eta: 0:03:10 lr: 0.000062 grad: 0.0922 (0.0937) loss: 0.8186 (0.8203) time: 0.1555 data: 0.0773 max mem: 9390 +Train: [52] [5100/6250] eta: 0:02:54 lr: 0.000062 grad: 0.0995 (0.0938) loss: 0.8206 (0.8203) time: 0.1314 data: 0.0431 max mem: 9390 +Train: [52] [5200/6250] eta: 0:02:39 lr: 0.000062 grad: 0.0891 (0.0939) loss: 0.8242 (0.8203) time: 0.1547 data: 0.0734 max mem: 9390 +Train: [52] [5300/6250] eta: 0:02:24 lr: 0.000062 grad: 0.0914 (0.0940) loss: 0.8257 (0.8203) time: 0.1562 data: 0.0776 max mem: 9390 +Train: [52] [5400/6250] eta: 0:02:09 lr: 0.000062 grad: 0.0942 (0.0940) loss: 0.8188 (0.8203) time: 0.1565 data: 0.0642 max mem: 9390 +Train: [52] [5500/6250] eta: 0:01:54 lr: 0.000062 grad: 0.0889 (0.0940) loss: 0.8206 (0.8203) time: 0.2462 data: 0.1661 max mem: 9390 +Train: [52] [5600/6250] eta: 0:01:38 lr: 0.000062 grad: 0.0893 (0.0941) loss: 0.8206 (0.8203) time: 0.1629 data: 0.0845 max mem: 9390 +Train: [52] [5700/6250] eta: 0:01:23 lr: 0.000062 grad: 0.0887 (0.0941) loss: 0.8206 (0.8203) time: 0.1560 data: 0.0752 max mem: 9390 +Train: [52] [5800/6250] eta: 0:01:08 lr: 0.000062 grad: 0.0904 (0.0941) loss: 0.8154 (0.8203) time: 0.1485 data: 0.0630 max mem: 9390 +Train: [52] [5900/6250] eta: 0:00:53 lr: 0.000062 grad: 0.0970 (0.0942) loss: 0.8202 (0.8203) time: 0.1666 data: 0.0866 max mem: 9390 +Train: [52] [6000/6250] eta: 0:00:38 lr: 0.000062 grad: 0.0963 (0.0943) loss: 0.8130 (0.8202) time: 0.1660 data: 0.0881 max mem: 9390 +Train: [52] [6100/6250] eta: 0:00:22 lr: 0.000062 grad: 0.0963 (0.0944) loss: 0.8135 (0.8202) time: 0.1676 data: 0.0861 max mem: 9390 +Train: [52] [6200/6250] eta: 0:00:07 lr: 0.000061 grad: 0.0984 (0.0945) loss: 0.8145 (0.8201) time: 0.1518 data: 0.0694 max mem: 9390 +Train: [52] [6249/6250] eta: 0:00:00 lr: 0.000061 grad: 0.1024 (0.0946) loss: 0.8194 (0.8200) time: 0.1348 data: 0.0429 max mem: 9390 +Train: [52] Total time: 0:15:57 (0.1531 s / it) +Averaged stats: lr: 0.000061 grad: 0.1024 (0.0946) loss: 0.8194 (0.8200) +Eval (hcp-train-subset): [52] [ 0/62] eta: 0:04:30 loss: 0.8500 (0.8500) time: 4.3611 data: 4.3308 max mem: 9390 +Eval (hcp-train-subset): [52] [61/62] eta: 0:00:00 loss: 0.8371 (0.8364) time: 0.1387 data: 0.1136 max mem: 9390 +Eval (hcp-train-subset): [52] Total time: 0:00:13 (0.2098 s / it) +Averaged stats (hcp-train-subset): loss: 0.8371 (0.8364) +Eval (hcp-val): [52] [ 0/62] eta: 0:05:28 loss: 0.8320 (0.8320) time: 5.2937 data: 5.2626 max mem: 9390 +Eval (hcp-val): [52] [61/62] eta: 0:00:00 loss: 0.8353 (0.8362) time: 0.1350 data: 0.1084 max mem: 9390 +Eval (hcp-val): [52] Total time: 0:00:13 (0.2175 s / it) +Averaged stats (hcp-val): loss: 0.8353 (0.8362) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +Train: [53] [ 0/6250] eta: 7:50:51 lr: 0.000061 grad: 0.5705 (0.5705) loss: 0.8594 (0.8594) time: 4.5202 data: 4.1676 max mem: 9390 +Train: [53] [ 100/6250] eta: 0:21:33 lr: 0.000061 grad: 0.0837 (0.1108) loss: 0.8417 (0.8390) time: 0.1454 data: 0.0601 max mem: 9390 +Train: [53] [ 200/6250] eta: 0:19:20 lr: 0.000061 grad: 0.0925 (0.1053) loss: 0.8278 (0.8332) time: 0.1653 data: 0.0816 max mem: 9390 +Train: [53] [ 300/6250] eta: 0:18:24 lr: 0.000061 grad: 0.0865 (0.1043) loss: 0.8316 (0.8294) time: 0.1677 data: 0.0765 max mem: 9390 +Train: [53] [ 400/6250] eta: 0:17:33 lr: 0.000061 grad: 0.0884 (0.1013) loss: 0.8313 (0.8283) time: 0.1416 data: 0.0511 max mem: 9390 +Train: [53] [ 500/6250] eta: 0:17:14 lr: 0.000061 grad: 0.0899 (0.0996) loss: 0.8218 (0.8264) time: 0.1659 data: 0.0792 max mem: 9390 +Train: [53] [ 600/6250] eta: 0:17:05 lr: 0.000061 grad: 0.0837 (0.0983) loss: 0.8242 (0.8255) time: 0.1494 data: 0.0654 max mem: 9390 +Train: [53] [ 700/6250] eta: 0:16:37 lr: 0.000061 grad: 0.0872 (0.0976) loss: 0.8235 (0.8248) time: 0.1491 data: 0.0684 max mem: 9390 +Train: [53] [ 800/6250] eta: 0:16:11 lr: 0.000061 grad: 0.0877 (0.0965) loss: 0.8222 (0.8244) time: 0.1603 data: 0.0800 max mem: 9390 +Train: [53] [ 900/6250] eta: 0:15:57 lr: 0.000061 grad: 0.0893 (0.0958) loss: 0.8261 (0.8241) time: 0.2080 data: 0.1159 max mem: 9390 +Train: [53] [1000/6250] eta: 0:15:35 lr: 0.000061 grad: 0.0920 (0.0955) loss: 0.8126 (0.8237) time: 0.1615 data: 0.0743 max mem: 9390 +Train: [53] [1100/6250] eta: 0:15:11 lr: 0.000061 grad: 0.0976 (0.0952) loss: 0.8211 (0.8233) time: 0.1601 data: 0.0717 max mem: 9390 +Train: [53] [1200/6250] eta: 0:14:51 lr: 0.000061 grad: 0.0921 (0.0951) loss: 0.8181 (0.8230) time: 0.1836 data: 0.0951 max mem: 9390 +Train: [53] [1300/6250] eta: 0:14:27 lr: 0.000061 grad: 0.0853 (0.0948) loss: 0.8214 (0.8227) time: 0.1642 data: 0.0652 max mem: 9390 +Train: [53] [1400/6250] eta: 0:14:04 lr: 0.000061 grad: 0.0909 (0.0947) loss: 0.8189 (0.8225) time: 0.1570 data: 0.0680 max mem: 9390 +Train: [53] [1500/6250] eta: 0:13:40 lr: 0.000061 grad: 0.0938 (0.0944) loss: 0.8212 (0.8223) time: 0.1631 data: 0.0653 max mem: 9390 +Train: [53] [1600/6250] eta: 0:13:16 lr: 0.000061 grad: 0.0900 (0.0942) loss: 0.8162 (0.8222) time: 0.1565 data: 0.0745 max mem: 9390 +Train: [53] [1700/6250] eta: 0:12:53 lr: 0.000061 grad: 0.0959 (0.0943) loss: 0.8208 (0.8220) time: 0.1274 data: 0.0413 max mem: 9390 +Train: [53] [1800/6250] eta: 0:12:32 lr: 0.000061 grad: 0.0870 (0.0941) loss: 0.8202 (0.8219) time: 0.1467 data: 0.0632 max mem: 9390 +Train: [53] [1900/6250] eta: 0:12:11 lr: 0.000061 grad: 0.1000 (0.0942) loss: 0.8125 (0.8217) time: 0.1445 data: 0.0658 max mem: 9390 +Train: [53] [2000/6250] eta: 0:11:51 lr: 0.000061 grad: 0.0982 (0.0944) loss: 0.8181 (0.8215) time: 0.1619 data: 0.0788 max mem: 9390 +Train: [53] [2100/6250] eta: 0:11:33 lr: 0.000061 grad: 0.0871 (0.0944) loss: 0.8137 (0.8214) time: 0.1732 data: 0.0886 max mem: 9390 +Train: [53] [2200/6250] eta: 0:11:12 lr: 0.000061 grad: 0.0929 (0.0943) loss: 0.8227 (0.8213) time: 0.1599 data: 0.0803 max mem: 9390 +Train: [53] [2300/6250] eta: 0:10:53 lr: 0.000061 grad: 0.0976 (0.0945) loss: 0.8186 (0.8213) time: 0.1371 data: 0.0556 max mem: 9390 +Train: [53] [2400/6250] eta: 0:10:35 lr: 0.000061 grad: 0.0937 (0.0947) loss: 0.8170 (0.8211) time: 0.1538 data: 0.0690 max mem: 9390 +Train: [53] [2500/6250] eta: 0:10:17 lr: 0.000061 grad: 0.0915 (0.0947) loss: 0.8208 (0.8211) time: 0.1870 data: 0.0970 max mem: 9390 +Train: [53] [2600/6250] eta: 0:09:57 lr: 0.000061 grad: 0.0901 (0.0948) loss: 0.8174 (0.8209) time: 0.1465 data: 0.0617 max mem: 9390 +Train: [53] [2700/6250] eta: 0:09:39 lr: 0.000061 grad: 0.0965 (0.0948) loss: 0.8130 (0.8207) time: 0.1473 data: 0.0653 max mem: 9390 +Train: [53] [2800/6250] eta: 0:09:21 lr: 0.000061 grad: 0.1004 (0.0948) loss: 0.8160 (0.8207) time: 0.1522 data: 0.0689 max mem: 9390 +Train: [53] [2900/6250] eta: 0:09:03 lr: 0.000061 grad: 0.0941 (0.0950) loss: 0.8177 (0.8205) time: 0.1447 data: 0.0589 max mem: 9390 +Train: [53] [3000/6250] eta: 0:08:45 lr: 0.000060 grad: 0.0941 (0.0950) loss: 0.8217 (0.8205) time: 0.1269 data: 0.0433 max mem: 9390 +Train: [53] [3100/6250] eta: 0:08:27 lr: 0.000060 grad: 0.0936 (0.0950) loss: 0.8158 (0.8204) time: 0.1299 data: 0.0485 max mem: 9390 +Train: [53] [3200/6250] eta: 0:08:10 lr: 0.000060 grad: 0.0890 (0.0950) loss: 0.8177 (0.8203) time: 0.1420 data: 0.0543 max mem: 9390 +Train: [53] [3300/6250] eta: 0:07:52 lr: 0.000060 grad: 0.0931 (0.0950) loss: 0.8197 (0.8203) time: 0.1447 data: 0.0659 max mem: 9390 +Train: [53] [3400/6250] eta: 0:07:36 lr: 0.000060 grad: 0.0948 (0.0951) loss: 0.8111 (0.8202) time: 0.1592 data: 0.0656 max mem: 9390 +Train: [53] [3500/6250] eta: 0:07:18 lr: 0.000060 grad: 0.0872 (0.0950) loss: 0.8185 (0.8201) time: 0.1643 data: 0.0888 max mem: 9390 +Train: [53] [3600/6250] eta: 0:07:02 lr: 0.000060 grad: 0.0946 (0.0950) loss: 0.8203 (0.8202) time: 0.1566 data: 0.0706 max mem: 9390 +Train: [53] [3700/6250] eta: 0:06:45 lr: 0.000060 grad: 0.0905 (0.0950) loss: 0.8288 (0.8202) time: 0.1397 data: 0.0548 max mem: 9390 +Train: [53] [3800/6250] eta: 0:06:29 lr: 0.000060 grad: 0.0897 (0.0950) loss: 0.8227 (0.8202) time: 0.1574 data: 0.0716 max mem: 9390 +Train: [53] [3900/6250] eta: 0:06:12 lr: 0.000060 grad: 0.0884 (0.0950) loss: 0.8178 (0.8202) time: 0.1514 data: 0.0717 max mem: 9390 +Train: [53] [4000/6250] eta: 0:05:56 lr: 0.000060 grad: 0.0952 (0.0952) loss: 0.8219 (0.8201) time: 0.1697 data: 0.0905 max mem: 9390 +Train: [53] [4100/6250] eta: 0:05:39 lr: 0.000060 grad: 0.0933 (0.0952) loss: 0.8146 (0.8201) time: 0.1250 data: 0.0430 max mem: 9390 +Train: [53] [4200/6250] eta: 0:05:23 lr: 0.000060 grad: 0.0933 (0.0952) loss: 0.8233 (0.8201) time: 0.1456 data: 0.0645 max mem: 9390 +Train: [53] [4300/6250] eta: 0:05:07 lr: 0.000060 grad: 0.0926 (0.0951) loss: 0.8188 (0.8201) time: 0.1426 data: 0.0573 max mem: 9390 +Train: [53] [4400/6250] eta: 0:04:50 lr: 0.000060 grad: 0.0951 (0.0951) loss: 0.8194 (0.8201) time: 0.1226 data: 0.0365 max mem: 9390 +Train: [53] [4500/6250] eta: 0:04:34 lr: 0.000060 grad: 0.0953 (0.0953) loss: 0.8201 (0.8201) time: 0.1388 data: 0.0541 max mem: 9390 +Train: [53] [4600/6250] eta: 0:04:18 lr: 0.000060 grad: 0.0914 (0.0954) loss: 0.8172 (0.8200) time: 0.1448 data: 0.0672 max mem: 9390 +Train: [53] [4700/6250] eta: 0:04:02 lr: 0.000060 grad: 0.0919 (0.0953) loss: 0.8220 (0.8201) time: 0.1482 data: 0.0643 max mem: 9390 +Train: [53] [4800/6250] eta: 0:03:47 lr: 0.000060 grad: 0.0922 (0.0953) loss: 0.8235 (0.8201) time: 0.1875 data: 0.1055 max mem: 9390 +Train: [53] [4900/6250] eta: 0:03:31 lr: 0.000060 grad: 0.0924 (0.0953) loss: 0.8159 (0.8201) time: 0.1141 data: 0.0189 max mem: 9390 +Train: [53] [5000/6250] eta: 0:03:16 lr: 0.000060 grad: 0.0939 (0.0953) loss: 0.8210 (0.8202) time: 0.1260 data: 0.0411 max mem: 9390 +Train: [53] [5100/6250] eta: 0:03:00 lr: 0.000060 grad: 0.0863 (0.0953) loss: 0.8272 (0.8202) time: 0.1650 data: 0.0778 max mem: 9390 +Train: [53] [5200/6250] eta: 0:02:44 lr: 0.000060 grad: 0.0905 (0.0952) loss: 0.8201 (0.8203) time: 0.1417 data: 0.0582 max mem: 9390 +Train: [53] [5300/6250] eta: 0:02:29 lr: 0.000060 grad: 0.0909 (0.0952) loss: 0.8239 (0.8203) time: 0.1941 data: 0.1124 max mem: 9390 +Train: [53] [5400/6250] eta: 0:02:13 lr: 0.000060 grad: 0.1029 (0.0953) loss: 0.8275 (0.8203) time: 0.1834 data: 0.1072 max mem: 9390 +Train: [53] [5500/6250] eta: 0:01:58 lr: 0.000060 grad: 0.0896 (0.0952) loss: 0.8210 (0.8204) time: 0.1646 data: 0.0883 max mem: 9390 +Train: [53] [5600/6250] eta: 0:01:42 lr: 0.000060 grad: 0.0934 (0.0952) loss: 0.8189 (0.8204) time: 0.1783 data: 0.0925 max mem: 9390 +Train: [53] [5700/6250] eta: 0:01:26 lr: 0.000060 grad: 0.0920 (0.0951) loss: 0.8255 (0.8204) time: 0.2044 data: 0.1294 max mem: 9390 +Train: [53] [5800/6250] eta: 0:01:10 lr: 0.000060 grad: 0.0894 (0.0952) loss: 0.8213 (0.8204) time: 0.1393 data: 0.0602 max mem: 9390 +Train: [53] [5900/6250] eta: 0:00:55 lr: 0.000060 grad: 0.0918 (0.0952) loss: 0.8191 (0.8204) time: 0.1363 data: 0.0492 max mem: 9390 +Train: [53] [6000/6250] eta: 0:00:39 lr: 0.000059 grad: 0.0919 (0.0952) loss: 0.8207 (0.8204) time: 0.1598 data: 0.0744 max mem: 9390 +Train: [53] [6100/6250] eta: 0:00:23 lr: 0.000059 grad: 0.0965 (0.0951) loss: 0.8205 (0.8204) time: 0.1409 data: 0.0531 max mem: 9390 +Train: [53] [6200/6250] eta: 0:00:07 lr: 0.000059 grad: 0.0932 (0.0952) loss: 0.8246 (0.8204) time: 0.1325 data: 0.0512 max mem: 9390 +Train: [53] [6249/6250] eta: 0:00:00 lr: 0.000059 grad: 0.0940 (0.0952) loss: 0.8163 (0.8204) time: 0.1594 data: 0.0681 max mem: 9390 +Train: [53] Total time: 0:16:30 (0.1585 s / it) +Averaged stats: lr: 0.000059 grad: 0.0940 (0.0952) loss: 0.8163 (0.8204) +Eval (hcp-train-subset): [53] [ 0/62] eta: 0:05:19 loss: 0.8488 (0.8488) time: 5.1550 data: 5.1231 max mem: 9390 +Eval (hcp-train-subset): [53] [61/62] eta: 0:00:00 loss: 0.8353 (0.8361) time: 0.1583 data: 0.1328 max mem: 9390 +Eval (hcp-train-subset): [53] Total time: 0:00:14 (0.2411 s / it) +Averaged stats (hcp-train-subset): loss: 0.8353 (0.8361) +Eval (hcp-val): [53] [ 0/62] eta: 0:06:13 loss: 0.8344 (0.8344) time: 6.0275 data: 5.9950 max mem: 9390 +Eval (hcp-val): [53] [61/62] eta: 0:00:00 loss: 0.8360 (0.8364) time: 0.1566 data: 0.1308 max mem: 9390 +Eval (hcp-val): [53] Total time: 0:00:15 (0.2469 s / it) +Averaged stats (hcp-val): loss: 0.8360 (0.8364) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +Train: [54] [ 0/6250] eta: 8:24:12 lr: 0.000059 grad: 0.0477 (0.0477) loss: 0.8815 (0.8815) time: 4.8403 data: 4.4211 max mem: 9390 +Train: [54] [ 100/6250] eta: 0:24:26 lr: 0.000059 grad: 0.0780 (0.1002) loss: 0.8389 (0.8437) time: 0.2008 data: 0.1126 max mem: 9390 +Train: [54] [ 200/6250] eta: 0:21:17 lr: 0.000059 grad: 0.0883 (0.0966) loss: 0.8349 (0.8378) time: 0.1549 data: 0.0584 max mem: 9390 +Train: [54] [ 300/6250] eta: 0:19:29 lr: 0.000059 grad: 0.0942 (0.0983) loss: 0.8286 (0.8347) time: 0.1759 data: 0.0891 max mem: 9390 +Train: [54] [ 400/6250] eta: 0:18:26 lr: 0.000059 grad: 0.0947 (0.0975) loss: 0.8257 (0.8324) time: 0.1705 data: 0.0791 max mem: 9390 +Train: [54] [ 500/6250] eta: 0:17:27 lr: 0.000059 grad: 0.0913 (0.0962) loss: 0.8165 (0.8303) time: 0.1654 data: 0.0807 max mem: 9390 +Train: [54] [ 600/6250] eta: 0:16:57 lr: 0.000059 grad: 0.0916 (0.0953) loss: 0.8108 (0.8289) time: 0.1764 data: 0.0911 max mem: 9390 +Train: [54] [ 700/6250] eta: 0:16:23 lr: 0.000059 grad: 0.0939 (0.0948) loss: 0.8174 (0.8277) time: 0.1566 data: 0.0744 max mem: 9390 +Train: [54] [ 800/6250] eta: 0:15:57 lr: 0.000059 grad: 0.0862 (0.0943) loss: 0.8170 (0.8269) time: 0.1600 data: 0.0737 max mem: 9390 +Train: [54] [ 900/6250] eta: 0:15:30 lr: 0.000059 grad: 0.0855 (0.0938) loss: 0.8180 (0.8261) time: 0.1507 data: 0.0621 max mem: 9390 +Train: [54] [1000/6250] eta: 0:15:07 lr: 0.000059 grad: 0.0858 (0.0935) loss: 0.8117 (0.8256) time: 0.1609 data: 0.0828 max mem: 9390 +Train: [54] [1100/6250] eta: 0:14:44 lr: 0.000059 grad: 0.0871 (0.0932) loss: 0.8231 (0.8251) time: 0.1697 data: 0.0850 max mem: 9390 +Train: [54] [1200/6250] eta: 0:14:19 lr: 0.000059 grad: 0.0834 (0.0929) loss: 0.8220 (0.8248) time: 0.1572 data: 0.0652 max mem: 9390 +Train: [54] [1300/6250] eta: 0:13:58 lr: 0.000059 grad: 0.0827 (0.0925) loss: 0.8229 (0.8247) time: 0.1610 data: 0.0805 max mem: 9390 +Train: [54] [1400/6250] eta: 0:13:38 lr: 0.000059 grad: 0.0918 (0.0924) loss: 0.8171 (0.8244) time: 0.1749 data: 0.0892 max mem: 9390 +Train: [54] [1500/6250] eta: 0:13:20 lr: 0.000059 grad: 0.0928 (0.0924) loss: 0.8214 (0.8243) time: 0.1650 data: 0.0709 max mem: 9390 +Train: [54] [1600/6250] eta: 0:12:57 lr: 0.000059 grad: 0.0810 (0.0922) loss: 0.8285 (0.8240) time: 0.1473 data: 0.0582 max mem: 9390 +Train: [54] [1700/6250] eta: 0:12:36 lr: 0.000059 grad: 0.0912 (0.0921) loss: 0.8186 (0.8239) time: 0.1331 data: 0.0374 max mem: 9390 +Train: [54] [1800/6250] eta: 0:12:19 lr: 0.000059 grad: 0.0867 (0.0919) loss: 0.8168 (0.8238) time: 0.1381 data: 0.0510 max mem: 9390 +Train: [54] [1900/6250] eta: 0:12:00 lr: 0.000059 grad: 0.0868 (0.0919) loss: 0.8221 (0.8236) time: 0.1441 data: 0.0603 max mem: 9390 +Train: [54] [2000/6250] eta: 0:11:42 lr: 0.000059 grad: 0.0909 (0.0919) loss: 0.8235 (0.8235) time: 0.1795 data: 0.1002 max mem: 9390 +Train: [54] [2100/6250] eta: 0:11:22 lr: 0.000059 grad: 0.0894 (0.0918) loss: 0.8226 (0.8234) time: 0.1612 data: 0.0664 max mem: 9390 +Train: [54] [2200/6250] eta: 0:11:04 lr: 0.000059 grad: 0.0859 (0.0918) loss: 0.8234 (0.8234) time: 0.1685 data: 0.0800 max mem: 9390 +Train: [54] [2300/6250] eta: 0:10:46 lr: 0.000059 grad: 0.0879 (0.0917) loss: 0.8174 (0.8234) time: 0.1724 data: 0.0902 max mem: 9390 +Train: [54] [2400/6250] eta: 0:10:29 lr: 0.000059 grad: 0.0879 (0.0916) loss: 0.8197 (0.8235) time: 0.1846 data: 0.1031 max mem: 9390 +Train: [54] [2500/6250] eta: 0:10:11 lr: 0.000059 grad: 0.0878 (0.0916) loss: 0.8263 (0.8235) time: 0.1890 data: 0.1022 max mem: 9390 +Train: [54] [2600/6250] eta: 0:09:53 lr: 0.000059 grad: 0.0887 (0.0915) loss: 0.8233 (0.8235) time: 0.1645 data: 0.0832 max mem: 9390 +Train: [54] [2700/6250] eta: 0:09:35 lr: 0.000059 grad: 0.0898 (0.0915) loss: 0.8236 (0.8235) time: 0.1084 data: 0.0259 max mem: 9390 +Train: [54] [2800/6250] eta: 0:09:18 lr: 0.000058 grad: 0.0867 (0.0914) loss: 0.8230 (0.8236) time: 0.1545 data: 0.0673 max mem: 9390 +Train: [54] [2900/6250] eta: 0:09:01 lr: 0.000058 grad: 0.0927 (0.0913) loss: 0.8203 (0.8237) time: 0.1445 data: 0.0568 max mem: 9390 +Train: [54] [3000/6250] eta: 0:08:45 lr: 0.000058 grad: 0.0866 (0.0913) loss: 0.8265 (0.8237) time: 0.1535 data: 0.0705 max mem: 9390 +Train: [54] [3100/6250] eta: 0:08:28 lr: 0.000058 grad: 0.0887 (0.0912) loss: 0.8204 (0.8237) time: 0.1628 data: 0.0815 max mem: 9390 +Train: [54] [3200/6250] eta: 0:08:12 lr: 0.000058 grad: 0.0940 (0.0911) loss: 0.8221 (0.8237) time: 0.1618 data: 0.0877 max mem: 9390 +Train: [54] [3300/6250] eta: 0:07:56 lr: 0.000058 grad: 0.0848 (0.0911) loss: 0.8226 (0.8237) time: 0.1778 data: 0.0966 max mem: 9390 +Train: [54] [3400/6250] eta: 0:07:39 lr: 0.000058 grad: 0.0917 (0.0912) loss: 0.8200 (0.8236) time: 0.1618 data: 0.0672 max mem: 9390 +Train: [54] [3500/6250] eta: 0:07:23 lr: 0.000058 grad: 0.0959 (0.0913) loss: 0.8200 (0.8235) time: 0.1794 data: 0.0911 max mem: 9390 +Train: [54] [3600/6250] eta: 0:07:06 lr: 0.000058 grad: 0.0918 (0.0914) loss: 0.8203 (0.8234) time: 0.1508 data: 0.0650 max mem: 9390 +Train: [54] [3700/6250] eta: 0:06:50 lr: 0.000058 grad: 0.0923 (0.0914) loss: 0.8217 (0.8233) time: 0.1539 data: 0.0681 max mem: 9390 +Train: [54] [3800/6250] eta: 0:06:33 lr: 0.000058 grad: 0.0949 (0.0915) loss: 0.8141 (0.8232) time: 0.1637 data: 0.0725 max mem: 9390 +Train: [54] [3900/6250] eta: 0:06:17 lr: 0.000058 grad: 0.0928 (0.0916) loss: 0.8186 (0.8232) time: 0.1506 data: 0.0615 max mem: 9390 +Train: [54] [4000/6250] eta: 0:06:01 lr: 0.000058 grad: 0.0945 (0.0917) loss: 0.8163 (0.8231) time: 0.1591 data: 0.0730 max mem: 9390 +Train: [54] [4100/6250] eta: 0:05:45 lr: 0.000058 grad: 0.0903 (0.0918) loss: 0.8156 (0.8230) time: 0.1136 data: 0.0295 max mem: 9390 +Train: [54] [4200/6250] eta: 0:05:28 lr: 0.000058 grad: 0.0928 (0.0918) loss: 0.8157 (0.8229) time: 0.1724 data: 0.0949 max mem: 9390 +Train: [54] [4300/6250] eta: 0:05:12 lr: 0.000058 grad: 0.0934 (0.0919) loss: 0.8195 (0.8228) time: 0.1569 data: 0.0746 max mem: 9390 +Train: [54] [4400/6250] eta: 0:04:56 lr: 0.000058 grad: 0.0944 (0.0920) loss: 0.8122 (0.8227) time: 0.1575 data: 0.0707 max mem: 9390 +Train: [54] [4500/6250] eta: 0:04:41 lr: 0.000058 grad: 0.0974 (0.0921) loss: 0.8138 (0.8225) time: 0.2456 data: 0.1438 max mem: 9390 +Train: [54] [4600/6250] eta: 0:04:25 lr: 0.000058 grad: 0.0894 (0.0921) loss: 0.8210 (0.8225) time: 0.1208 data: 0.0132 max mem: 9390 +Train: [54] [4700/6250] eta: 0:04:09 lr: 0.000058 grad: 0.0933 (0.0922) loss: 0.8241 (0.8224) time: 0.1787 data: 0.0837 max mem: 9390 +Train: [54] [4800/6250] eta: 0:03:53 lr: 0.000058 grad: 0.0917 (0.0923) loss: 0.8176 (0.8224) time: 0.1798 data: 0.0976 max mem: 9390 +Train: [54] [4900/6250] eta: 0:03:37 lr: 0.000058 grad: 0.0840 (0.0923) loss: 0.8245 (0.8223) time: 0.1497 data: 0.0558 max mem: 9390 +Train: [54] [5000/6250] eta: 0:03:20 lr: 0.000058 grad: 0.1005 (0.0923) loss: 0.8118 (0.8223) time: 0.1458 data: 0.0582 max mem: 9390 +Train: [54] [5100/6250] eta: 0:03:04 lr: 0.000058 grad: 0.0957 (0.0924) loss: 0.8132 (0.8222) time: 0.1501 data: 0.0654 max mem: 9390 +Train: [54] [5200/6250] eta: 0:02:48 lr: 0.000058 grad: 0.0896 (0.0925) loss: 0.8213 (0.8221) time: 0.1008 data: 0.0037 max mem: 9390 +Train: [54] [5300/6250] eta: 0:02:33 lr: 0.000058 grad: 0.0925 (0.0926) loss: 0.8230 (0.8220) time: 0.1060 data: 0.0238 max mem: 9390 +Train: [54] [5400/6250] eta: 0:02:17 lr: 0.000058 grad: 0.0900 (0.0926) loss: 0.8180 (0.8219) time: 0.2665 data: 0.1849 max mem: 9390 +Train: [54] [5500/6250] eta: 0:02:00 lr: 0.000058 grad: 0.0969 (0.0927) loss: 0.8221 (0.8219) time: 0.1763 data: 0.0904 max mem: 9390 +Train: [54] [5600/6250] eta: 0:01:44 lr: 0.000058 grad: 0.0910 (0.0927) loss: 0.8227 (0.8218) time: 0.1610 data: 0.0773 max mem: 9390 +Train: [54] [5700/6250] eta: 0:01:28 lr: 0.000058 grad: 0.0873 (0.0927) loss: 0.8134 (0.8217) time: 0.1545 data: 0.0750 max mem: 9390 +Train: [54] [5800/6250] eta: 0:01:12 lr: 0.000057 grad: 0.0956 (0.0927) loss: 0.8210 (0.8217) time: 0.1705 data: 0.0741 max mem: 9390 +Train: [54] [5900/6250] eta: 0:00:56 lr: 0.000057 grad: 0.0911 (0.0928) loss: 0.8220 (0.8216) time: 0.1694 data: 0.0956 max mem: 9390 +Train: [54] [6000/6250] eta: 0:00:40 lr: 0.000057 grad: 0.0936 (0.0928) loss: 0.8198 (0.8216) time: 0.1686 data: 0.0862 max mem: 9390 +Train: [54] [6100/6250] eta: 0:00:24 lr: 0.000057 grad: 0.0931 (0.0928) loss: 0.8223 (0.8216) time: 0.1719 data: 0.0807 max mem: 9390 +Train: [54] [6200/6250] eta: 0:00:08 lr: 0.000057 grad: 0.0941 (0.0928) loss: 0.8143 (0.8216) time: 0.1752 data: 0.0655 max mem: 9390 +Train: [54] [6249/6250] eta: 0:00:00 lr: 0.000057 grad: 0.0906 (0.0928) loss: 0.8246 (0.8216) time: 0.2325 data: 0.1193 max mem: 9390 +Train: [54] Total time: 0:17:03 (0.1637 s / it) +Averaged stats: lr: 0.000057 grad: 0.0906 (0.0928) loss: 0.8246 (0.8216) +Eval (hcp-train-subset): [54] [ 0/62] eta: 0:07:11 loss: 0.8518 (0.8518) time: 6.9584 data: 6.9240 max mem: 9390 +Eval (hcp-train-subset): [54] [61/62] eta: 0:00:00 loss: 0.8340 (0.8353) time: 0.1788 data: 0.1500 max mem: 9390 +Eval (hcp-train-subset): [54] Total time: 0:00:17 (0.2886 s / it) +Averaged stats (hcp-train-subset): loss: 0.8340 (0.8353) +Making plots (hcp-train-subset): example=45 +Eval (hcp-val): [54] [ 0/62] eta: 0:06:37 loss: 0.8364 (0.8364) time: 6.4063 data: 6.3700 max mem: 9390 +Eval (hcp-val): [54] [61/62] eta: 0:00:00 loss: 0.8322 (0.8351) time: 0.1825 data: 0.1554 max mem: 9390 +Eval (hcp-val): [54] Total time: 0:00:17 (0.2823 s / it) +Averaged stats (hcp-val): loss: 0.8322 (0.8351) +Making plots (hcp-val): example=42 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +Train: [55] [ 0/6250] eta: 11:14:34 lr: 0.000057 grad: 0.0648 (0.0648) loss: 0.8567 (0.8567) time: 6.4759 data: 6.3104 max mem: 9390 +Train: [55] [ 100/6250] eta: 0:27:04 lr: 0.000057 grad: 0.0977 (0.1086) loss: 0.8336 (0.8264) time: 0.2134 data: 0.1124 max mem: 9390 +Train: [55] [ 200/6250] eta: 0:23:52 lr: 0.000057 grad: 0.0944 (0.1038) loss: 0.8243 (0.8240) time: 0.2084 data: 0.0913 max mem: 9390 +Train: [55] [ 300/6250] eta: 0:22:09 lr: 0.000057 grad: 0.0962 (0.1032) loss: 0.8288 (0.8231) time: 0.1867 data: 0.0818 max mem: 9390 +Train: [55] [ 400/6250] eta: 0:20:54 lr: 0.000057 grad: 0.0973 (0.1070) loss: 0.8067 (0.8214) time: 0.1584 data: 0.0582 max mem: 9390 +Train: [55] [ 500/6250] eta: 0:19:49 lr: 0.000057 grad: 0.0899 (0.1047) loss: 0.8120 (0.8198) time: 0.1743 data: 0.0872 max mem: 9390 +Train: [55] [ 600/6250] eta: 0:18:56 lr: 0.000057 grad: 0.0947 (0.1033) loss: 0.8133 (0.8188) time: 0.1704 data: 0.0762 max mem: 9390 +Train: [55] [ 700/6250] eta: 0:18:18 lr: 0.000057 grad: 0.0977 (0.1021) loss: 0.8200 (0.8185) time: 0.1700 data: 0.0827 max mem: 9390 +Train: [55] [ 800/6250] eta: 0:17:41 lr: 0.000057 grad: 0.0985 (0.1016) loss: 0.8211 (0.8181) time: 0.1950 data: 0.1121 max mem: 9390 +Train: [55] [ 900/6250] eta: 0:17:07 lr: 0.000057 grad: 0.0947 (0.1007) loss: 0.8167 (0.8181) time: 0.1837 data: 0.0977 max mem: 9390 +Train: [55] [1000/6250] eta: 0:16:31 lr: 0.000057 grad: 0.0891 (0.1001) loss: 0.8167 (0.8182) time: 0.1714 data: 0.0897 max mem: 9390 +Train: [55] [1100/6250] eta: 0:15:56 lr: 0.000057 grad: 0.0900 (0.0996) loss: 0.8224 (0.8184) time: 0.1447 data: 0.0583 max mem: 9390 +Train: [55] [1200/6250] eta: 0:15:29 lr: 0.000057 grad: 0.0916 (0.0995) loss: 0.8114 (0.8183) time: 0.1610 data: 0.0799 max mem: 9390 +Train: [55] [1300/6250] eta: 0:15:01 lr: 0.000057 grad: 0.0962 (0.0991) loss: 0.8127 (0.8184) time: 0.1395 data: 0.0512 max mem: 9390 +Train: [55] [1400/6250] eta: 0:14:34 lr: 0.000057 grad: 0.0915 (0.0989) loss: 0.8110 (0.8184) time: 0.1440 data: 0.0604 max mem: 9390 +Train: [55] [1500/6250] eta: 0:14:06 lr: 0.000057 grad: 0.0960 (0.0988) loss: 0.8089 (0.8181) time: 0.1630 data: 0.0676 max mem: 9390 +Train: [55] [1600/6250] eta: 0:13:40 lr: 0.000057 grad: 0.0917 (0.0988) loss: 0.8213 (0.8180) time: 0.1591 data: 0.0754 max mem: 9390 +Train: [55] [1700/6250] eta: 0:13:15 lr: 0.000057 grad: 0.0924 (0.0987) loss: 0.8154 (0.8180) time: 0.1435 data: 0.0590 max mem: 9390 +Train: [55] [1800/6250] eta: 0:12:51 lr: 0.000057 grad: 0.1073 (0.0989) loss: 0.8096 (0.8179) time: 0.1351 data: 0.0549 max mem: 9390 +Train: [55] [1900/6250] eta: 0:12:29 lr: 0.000057 grad: 0.0914 (0.0988) loss: 0.8149 (0.8179) time: 0.1466 data: 0.0703 max mem: 9390 +Train: [55] [2000/6250] eta: 0:12:06 lr: 0.000057 grad: 0.0901 (0.0986) loss: 0.8209 (0.8179) time: 0.1467 data: 0.0615 max mem: 9390 +Train: [55] [2100/6250] eta: 0:11:46 lr: 0.000057 grad: 0.0918 (0.0985) loss: 0.8158 (0.8179) time: 0.1487 data: 0.0628 max mem: 9390 +Train: [55] [2200/6250] eta: 0:11:26 lr: 0.000057 grad: 0.1052 (0.0985) loss: 0.8185 (0.8179) time: 0.1505 data: 0.0627 max mem: 9390 +Train: [55] [2300/6250] eta: 0:11:06 lr: 0.000057 grad: 0.0958 (0.0985) loss: 0.8112 (0.8179) time: 0.1593 data: 0.0805 max mem: 9390 +Train: [55] [2400/6250] eta: 0:10:46 lr: 0.000057 grad: 0.0971 (0.0983) loss: 0.8203 (0.8180) time: 0.1450 data: 0.0577 max mem: 9390 +Train: [55] [2500/6250] eta: 0:10:29 lr: 0.000057 grad: 0.0930 (0.0983) loss: 0.8151 (0.8180) time: 0.1709 data: 0.0835 max mem: 9390 +Train: [55] [2600/6250] eta: 0:10:09 lr: 0.000056 grad: 0.0956 (0.0983) loss: 0.8192 (0.8180) time: 0.1562 data: 0.0745 max mem: 9390 +Train: [55] [2700/6250] eta: 0:09:50 lr: 0.000056 grad: 0.0917 (0.0982) loss: 0.8236 (0.8181) time: 0.1545 data: 0.0767 max mem: 9390 +Train: [55] [2800/6250] eta: 0:09:32 lr: 0.000056 grad: 0.0980 (0.0982) loss: 0.8225 (0.8181) time: 0.1572 data: 0.0769 max mem: 9390 +Train: [55] [2900/6250] eta: 0:09:14 lr: 0.000056 grad: 0.0919 (0.0981) loss: 0.8271 (0.8182) time: 0.1317 data: 0.0413 max mem: 9390 +Train: [55] [3000/6250] eta: 0:08:56 lr: 0.000056 grad: 0.0972 (0.0981) loss: 0.8236 (0.8183) time: 0.1690 data: 0.0840 max mem: 9390 +Train: [55] [3100/6250] eta: 0:08:38 lr: 0.000056 grad: 0.0911 (0.0980) loss: 0.8203 (0.8185) time: 0.1618 data: 0.0784 max mem: 9390 +Train: [55] [3200/6250] eta: 0:08:20 lr: 0.000056 grad: 0.0957 (0.0980) loss: 0.8195 (0.8186) time: 0.1482 data: 0.0639 max mem: 9390 +Train: [55] [3300/6250] eta: 0:08:03 lr: 0.000056 grad: 0.0973 (0.0980) loss: 0.8193 (0.8187) time: 0.1529 data: 0.0682 max mem: 9390 +Train: [55] [3400/6250] eta: 0:07:46 lr: 0.000056 grad: 0.0953 (0.0979) loss: 0.8223 (0.8188) time: 0.1611 data: 0.0857 max mem: 9390 +Train: [55] [3500/6250] eta: 0:07:28 lr: 0.000056 grad: 0.0875 (0.0979) loss: 0.8279 (0.8189) time: 0.1422 data: 0.0607 max mem: 9390 +Train: [55] [3600/6250] eta: 0:07:11 lr: 0.000056 grad: 0.0865 (0.0978) loss: 0.8295 (0.8190) time: 0.0996 data: 0.0234 max mem: 9390 +Train: [55] [3700/6250] eta: 0:06:55 lr: 0.000056 grad: 0.0982 (0.0978) loss: 0.8232 (0.8191) time: 0.1534 data: 0.0755 max mem: 9390 +Train: [55] [3800/6250] eta: 0:06:37 lr: 0.000056 grad: 0.0956 (0.0978) loss: 0.8197 (0.8193) time: 0.1467 data: 0.0675 max mem: 9390 +Train: [55] [3900/6250] eta: 0:06:21 lr: 0.000056 grad: 0.0913 (0.0977) loss: 0.8236 (0.8194) time: 0.1467 data: 0.0636 max mem: 9390 +Train: [55] [4000/6250] eta: 0:06:04 lr: 0.000056 grad: 0.0940 (0.0977) loss: 0.8205 (0.8195) time: 0.1516 data: 0.0719 max mem: 9390 +Train: [55] [4100/6250] eta: 0:05:47 lr: 0.000056 grad: 0.0992 (0.0978) loss: 0.8196 (0.8195) time: 0.1395 data: 0.0575 max mem: 9390 +Train: [55] [4200/6250] eta: 0:05:30 lr: 0.000056 grad: 0.0965 (0.0978) loss: 0.8211 (0.8195) time: 0.1303 data: 0.0453 max mem: 9390 +Train: [55] [4300/6250] eta: 0:05:14 lr: 0.000056 grad: 0.0954 (0.0978) loss: 0.8221 (0.8196) time: 0.1576 data: 0.0737 max mem: 9390 +Train: [55] [4400/6250] eta: 0:04:58 lr: 0.000056 grad: 0.0948 (0.0978) loss: 0.8218 (0.8196) time: 0.1533 data: 0.0710 max mem: 9390 +Train: [55] [4500/6250] eta: 0:04:41 lr: 0.000056 grad: 0.0976 (0.0978) loss: 0.8174 (0.8197) time: 0.1600 data: 0.0764 max mem: 9390 +Train: [55] [4600/6250] eta: 0:04:25 lr: 0.000056 grad: 0.0970 (0.0978) loss: 0.8154 (0.8197) time: 0.1719 data: 0.0947 max mem: 9390 +Train: [55] [4700/6250] eta: 0:04:08 lr: 0.000056 grad: 0.0963 (0.0978) loss: 0.8252 (0.8197) time: 0.1401 data: 0.0605 max mem: 9390 +Train: [55] [4800/6250] eta: 0:03:52 lr: 0.000056 grad: 0.0948 (0.0977) loss: 0.8227 (0.8198) time: 0.1510 data: 0.0674 max mem: 9390 +Train: [55] [4900/6250] eta: 0:03:36 lr: 0.000056 grad: 0.0877 (0.0977) loss: 0.8214 (0.8198) time: 0.1502 data: 0.0683 max mem: 9390 +Train: [55] [5000/6250] eta: 0:03:19 lr: 0.000056 grad: 0.0944 (0.0978) loss: 0.8256 (0.8198) time: 0.1318 data: 0.0516 max mem: 9390 +Train: [55] [5100/6250] eta: 0:03:03 lr: 0.000056 grad: 0.0985 (0.0978) loss: 0.8229 (0.8198) time: 0.1313 data: 0.0485 max mem: 9390 +Train: [55] [5200/6250] eta: 0:02:47 lr: 0.000056 grad: 0.0956 (0.0978) loss: 0.8243 (0.8198) time: 0.1714 data: 0.0842 max mem: 9390 +Train: [55] [5300/6250] eta: 0:02:31 lr: 0.000056 grad: 0.0936 (0.0977) loss: 0.8203 (0.8199) time: 0.1594 data: 0.0832 max mem: 9390 +Train: [55] [5400/6250] eta: 0:02:15 lr: 0.000056 grad: 0.1000 (0.0977) loss: 0.8259 (0.8199) time: 0.1540 data: 0.0780 max mem: 9390 +Train: [55] [5500/6250] eta: 0:01:59 lr: 0.000056 grad: 0.0923 (0.0977) loss: 0.8252 (0.8199) time: 0.1337 data: 0.0502 max mem: 9390 +Train: [55] [5600/6250] eta: 0:01:44 lr: 0.000055 grad: 0.0984 (0.0977) loss: 0.8160 (0.8199) time: 0.2005 data: 0.1210 max mem: 9390 +Train: [55] [5700/6250] eta: 0:01:28 lr: 0.000055 grad: 0.0934 (0.0977) loss: 0.8171 (0.8199) time: 0.1633 data: 0.0811 max mem: 9390 +Train: [55] [5800/6250] eta: 0:01:12 lr: 0.000055 grad: 0.0965 (0.0977) loss: 0.8180 (0.8199) time: 0.1615 data: 0.0684 max mem: 9390 +Train: [55] [5900/6250] eta: 0:00:55 lr: 0.000055 grad: 0.0972 (0.0977) loss: 0.8201 (0.8199) time: 0.1338 data: 0.0403 max mem: 9390 +Train: [55] [6000/6250] eta: 0:00:39 lr: 0.000055 grad: 0.0982 (0.0977) loss: 0.8235 (0.8199) time: 0.1481 data: 0.0677 max mem: 9390 +Train: [55] [6100/6250] eta: 0:00:23 lr: 0.000055 grad: 0.0893 (0.0977) loss: 0.8232 (0.8199) time: 0.1406 data: 0.0602 max mem: 9390 +Train: [55] [6200/6250] eta: 0:00:07 lr: 0.000055 grad: 0.0960 (0.0976) loss: 0.8248 (0.8200) time: 0.1260 data: 0.0458 max mem: 9390 +Train: [55] [6249/6250] eta: 0:00:00 lr: 0.000055 grad: 0.0960 (0.0976) loss: 0.8254 (0.8200) time: 0.1650 data: 0.0832 max mem: 9390 +Train: [55] Total time: 0:16:41 (0.1603 s / it) +Averaged stats: lr: 0.000055 grad: 0.0960 (0.0976) loss: 0.8254 (0.8200) +Eval (hcp-train-subset): [55] [ 0/62] eta: 0:04:02 loss: 0.8445 (0.8445) time: 3.9099 data: 3.8083 max mem: 9390 +Eval (hcp-train-subset): [55] [61/62] eta: 0:00:00 loss: 0.8334 (0.8340) time: 0.1540 data: 0.1274 max mem: 9390 +Eval (hcp-train-subset): [55] Total time: 0:00:15 (0.2523 s / it) +Averaged stats (hcp-train-subset): loss: 0.8334 (0.8340) +Eval (hcp-val): [55] [ 0/62] eta: 0:06:30 loss: 0.8362 (0.8362) time: 6.2950 data: 6.2607 max mem: 9390 +Eval (hcp-val): [55] [61/62] eta: 0:00:00 loss: 0.8340 (0.8353) time: 0.1815 data: 0.1533 max mem: 9390 +Eval (hcp-val): [55] Total time: 0:00:17 (0.2869 s / it) +Averaged stats (hcp-val): loss: 0.8340 (0.8353) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +Train: [56] [ 0/6250] eta: 12:05:08 lr: 0.000055 grad: 0.0740 (0.0740) loss: 0.8497 (0.8497) time: 6.9614 data: 6.7541 max mem: 9390 +Train: [56] [ 100/6250] eta: 0:26:29 lr: 0.000055 grad: 0.0908 (0.0904) loss: 0.8245 (0.8388) time: 0.1997 data: 0.1006 max mem: 9390 +Train: [56] [ 200/6250] eta: 0:21:47 lr: 0.000055 grad: 0.0815 (0.0900) loss: 0.8256 (0.8314) time: 0.1674 data: 0.0811 max mem: 9390 +Train: [56] [ 300/6250] eta: 0:19:53 lr: 0.000055 grad: 0.1030 (0.0916) loss: 0.8140 (0.8279) time: 0.1624 data: 0.0808 max mem: 9390 +Train: [56] [ 400/6250] eta: 0:18:52 lr: 0.000055 grad: 0.0857 (0.0919) loss: 0.8194 (0.8260) time: 0.1933 data: 0.1045 max mem: 9390 +Train: [56] [ 500/6250] eta: 0:17:59 lr: 0.000055 grad: 0.0948 (0.0921) loss: 0.8144 (0.8244) time: 0.1388 data: 0.0578 max mem: 9390 +Train: [56] [ 600/6250] eta: 0:17:19 lr: 0.000055 grad: 0.0868 (0.0921) loss: 0.8190 (0.8233) time: 0.1502 data: 0.0660 max mem: 9390 +Train: [56] [ 700/6250] eta: 0:16:50 lr: 0.000055 grad: 0.0828 (0.0920) loss: 0.8226 (0.8227) time: 0.1634 data: 0.0716 max mem: 9390 +Train: [56] [ 800/6250] eta: 0:16:21 lr: 0.000055 grad: 0.0842 (0.0915) loss: 0.8220 (0.8227) time: 0.1855 data: 0.0930 max mem: 9390 +Train: [56] [ 900/6250] eta: 0:16:01 lr: 0.000055 grad: 0.0857 (0.0913) loss: 0.8238 (0.8226) time: 0.2013 data: 0.1206 max mem: 9390 +Train: [56] [1000/6250] eta: 0:15:27 lr: 0.000055 grad: 0.0865 (0.0912) loss: 0.8197 (0.8224) time: 0.1726 data: 0.0891 max mem: 9390 +Train: [56] [1100/6250] eta: 0:14:57 lr: 0.000055 grad: 0.0915 (0.0914) loss: 0.8251 (0.8221) time: 0.1486 data: 0.0691 max mem: 9390 +Train: [56] [1200/6250] eta: 0:14:33 lr: 0.000055 grad: 0.0882 (0.0914) loss: 0.8211 (0.8219) time: 0.1583 data: 0.0766 max mem: 9390 +Train: [56] [1300/6250] eta: 0:14:07 lr: 0.000055 grad: 0.0860 (0.0915) loss: 0.8133 (0.8217) time: 0.1290 data: 0.0441 max mem: 9390 +Train: [56] [1400/6250] eta: 0:13:48 lr: 0.000055 grad: 0.0922 (0.0916) loss: 0.8204 (0.8213) time: 0.1699 data: 0.0853 max mem: 9390 +Train: [56] [1500/6250] eta: 0:13:25 lr: 0.000055 grad: 0.0870 (0.0916) loss: 0.8202 (0.8213) time: 0.1599 data: 0.0704 max mem: 9390 +Train: [56] [1600/6250] eta: 0:13:04 lr: 0.000055 grad: 0.0945 (0.0920) loss: 0.8237 (0.8211) time: 0.1542 data: 0.0685 max mem: 9390 +Train: [56] [1700/6250] eta: 0:12:46 lr: 0.000055 grad: 0.0949 (0.0920) loss: 0.8190 (0.8210) time: 0.1678 data: 0.0780 max mem: 9390 +Train: [56] [1800/6250] eta: 0:12:27 lr: 0.000055 grad: 0.0868 (0.0920) loss: 0.8149 (0.8210) time: 0.1752 data: 0.0981 max mem: 9390 +Train: [56] [1900/6250] eta: 0:12:09 lr: 0.000055 grad: 0.0887 (0.0922) loss: 0.8213 (0.8208) time: 0.1388 data: 0.0598 max mem: 9390 +Train: [56] [2000/6250] eta: 0:11:50 lr: 0.000055 grad: 0.0921 (0.0922) loss: 0.8206 (0.8207) time: 0.1757 data: 0.0867 max mem: 9390 +Train: [56] [2100/6250] eta: 0:11:30 lr: 0.000055 grad: 0.0915 (0.0923) loss: 0.8244 (0.8207) time: 0.1529 data: 0.0676 max mem: 9390 +Train: [56] [2200/6250] eta: 0:11:14 lr: 0.000055 grad: 0.0902 (0.0924) loss: 0.8194 (0.8206) time: 0.1630 data: 0.0811 max mem: 9390 +Train: [56] [2300/6250] eta: 0:10:57 lr: 0.000055 grad: 0.0857 (0.0924) loss: 0.8219 (0.8206) time: 0.1884 data: 0.1082 max mem: 9390 +Train: [56] [2400/6250] eta: 0:10:37 lr: 0.000054 grad: 0.0841 (0.0925) loss: 0.8240 (0.8205) time: 0.1387 data: 0.0565 max mem: 9390 +Train: [56] [2500/6250] eta: 0:10:21 lr: 0.000054 grad: 0.0896 (0.0927) loss: 0.8206 (0.8204) time: 0.1910 data: 0.1052 max mem: 9390 +Train: [56] [2600/6250] eta: 0:10:03 lr: 0.000054 grad: 0.0907 (0.0928) loss: 0.8174 (0.8204) time: 0.1459 data: 0.0614 max mem: 9390 +Train: [56] [2700/6250] eta: 0:09:45 lr: 0.000054 grad: 0.0992 (0.0929) loss: 0.8133 (0.8204) time: 0.1567 data: 0.0747 max mem: 9390 +Train: [56] [2800/6250] eta: 0:09:28 lr: 0.000054 grad: 0.0952 (0.0930) loss: 0.8168 (0.8203) time: 0.1673 data: 0.0892 max mem: 9390 +Train: [56] [2900/6250] eta: 0:09:10 lr: 0.000054 grad: 0.0955 (0.0930) loss: 0.8165 (0.8202) time: 0.1317 data: 0.0548 max mem: 9390 +Train: [56] [3000/6250] eta: 0:08:53 lr: 0.000054 grad: 0.0906 (0.0931) loss: 0.8172 (0.8201) time: 0.1772 data: 0.0873 max mem: 9390 +Train: [56] [3100/6250] eta: 0:08:36 lr: 0.000054 grad: 0.0905 (0.0932) loss: 0.8173 (0.8201) time: 0.1658 data: 0.0785 max mem: 9390 +Train: [56] [3200/6250] eta: 0:08:19 lr: 0.000054 grad: 0.0958 (0.0933) loss: 0.8226 (0.8201) time: 0.1570 data: 0.0638 max mem: 9390 +Train: [56] [3300/6250] eta: 0:08:02 lr: 0.000054 grad: 0.0947 (0.0934) loss: 0.8184 (0.8201) time: 0.1718 data: 0.0821 max mem: 9390 +Train: [56] [3400/6250] eta: 0:07:46 lr: 0.000054 grad: 0.0915 (0.0936) loss: 0.8168 (0.8200) time: 0.2224 data: 0.1444 max mem: 9390 +Train: [56] [3500/6250] eta: 0:07:29 lr: 0.000054 grad: 0.0976 (0.0937) loss: 0.8123 (0.8199) time: 0.1315 data: 0.0382 max mem: 9390 +Train: [56] [3600/6250] eta: 0:07:12 lr: 0.000054 grad: 0.0945 (0.0938) loss: 0.8225 (0.8198) time: 0.1536 data: 0.0698 max mem: 9390 +Train: [56] [3700/6250] eta: 0:06:55 lr: 0.000054 grad: 0.0962 (0.0939) loss: 0.8155 (0.8198) time: 0.1563 data: 0.0704 max mem: 9390 +Train: [56] [3800/6250] eta: 0:06:39 lr: 0.000054 grad: 0.0909 (0.0940) loss: 0.8200 (0.8198) time: 0.1666 data: 0.0857 max mem: 9390 +Train: [56] [3900/6250] eta: 0:06:22 lr: 0.000054 grad: 0.0939 (0.0941) loss: 0.8193 (0.8197) time: 0.1747 data: 0.0883 max mem: 9390 +Train: [56] [4000/6250] eta: 0:06:05 lr: 0.000054 grad: 0.0980 (0.0942) loss: 0.8182 (0.8197) time: 0.1524 data: 0.0614 max mem: 9390 +Train: [56] [4100/6250] eta: 0:05:49 lr: 0.000054 grad: 0.0936 (0.0942) loss: 0.8187 (0.8197) time: 0.1671 data: 0.0920 max mem: 9390 +Train: [56] [4200/6250] eta: 0:05:32 lr: 0.000054 grad: 0.0881 (0.0942) loss: 0.8280 (0.8197) time: 0.1624 data: 0.0841 max mem: 9390 +Train: [56] [4300/6250] eta: 0:05:16 lr: 0.000054 grad: 0.0949 (0.0943) loss: 0.8215 (0.8197) time: 0.1401 data: 0.0522 max mem: 9390 +Train: [56] [4400/6250] eta: 0:05:00 lr: 0.000054 grad: 0.0922 (0.0943) loss: 0.8162 (0.8197) time: 0.1933 data: 0.1130 max mem: 9390 +Train: [56] [4500/6250] eta: 0:04:44 lr: 0.000054 grad: 0.0942 (0.0945) loss: 0.8183 (0.8197) time: 0.1732 data: 0.0953 max mem: 9390 +Train: [56] [4600/6250] eta: 0:04:28 lr: 0.000054 grad: 0.0931 (0.0945) loss: 0.8176 (0.8197) time: 0.1963 data: 0.1191 max mem: 9390 +Train: [56] [4700/6250] eta: 0:04:12 lr: 0.000054 grad: 0.0913 (0.0946) loss: 0.8198 (0.8196) time: 0.1571 data: 0.0739 max mem: 9390 +Train: [56] [4800/6250] eta: 0:03:56 lr: 0.000054 grad: 0.0898 (0.0947) loss: 0.8209 (0.8196) time: 0.1847 data: 0.1020 max mem: 9390 +Train: [56] [4900/6250] eta: 0:03:41 lr: 0.000054 grad: 0.0939 (0.0948) loss: 0.8135 (0.8196) time: 0.1632 data: 0.0858 max mem: 9390 +Train: [56] [5000/6250] eta: 0:03:25 lr: 0.000054 grad: 0.0956 (0.0948) loss: 0.8224 (0.8196) time: 0.1633 data: 0.0852 max mem: 9390 +Train: [56] [5100/6250] eta: 0:03:09 lr: 0.000054 grad: 0.0960 (0.0949) loss: 0.8192 (0.8196) time: 0.1766 data: 0.0989 max mem: 9390 +Train: [56] [5200/6250] eta: 0:02:52 lr: 0.000054 grad: 0.0914 (0.0950) loss: 0.8229 (0.8196) time: 0.1733 data: 0.0925 max mem: 9390 +Train: [56] [5300/6250] eta: 0:02:36 lr: 0.000054 grad: 0.0992 (0.0951) loss: 0.8195 (0.8196) time: 0.1599 data: 0.0719 max mem: 9390 +Train: [56] [5400/6250] eta: 0:02:19 lr: 0.000054 grad: 0.0962 (0.0952) loss: 0.8180 (0.8195) time: 0.1581 data: 0.0671 max mem: 9390 +Train: [56] [5500/6250] eta: 0:02:03 lr: 0.000053 grad: 0.0996 (0.0953) loss: 0.8239 (0.8196) time: 0.1485 data: 0.0605 max mem: 9390 +Train: [56] [5600/6250] eta: 0:01:46 lr: 0.000053 grad: 0.0874 (0.0953) loss: 0.8263 (0.8196) time: 0.1486 data: 0.0623 max mem: 9390 +Train: [56] [5700/6250] eta: 0:01:30 lr: 0.000053 grad: 0.0934 (0.0954) loss: 0.8155 (0.8196) time: 0.1480 data: 0.0582 max mem: 9390 +Train: [56] [5800/6250] eta: 0:01:13 lr: 0.000053 grad: 0.0962 (0.0955) loss: 0.8208 (0.8196) time: 0.1556 data: 0.0720 max mem: 9390 +Train: [56] [5900/6250] eta: 0:00:57 lr: 0.000053 grad: 0.0955 (0.0955) loss: 0.8175 (0.8196) time: 0.1513 data: 0.0585 max mem: 9390 +Train: [56] [6000/6250] eta: 0:00:40 lr: 0.000053 grad: 0.0957 (0.0956) loss: 0.8245 (0.8196) time: 0.1393 data: 0.0535 max mem: 9390 +Train: [56] [6100/6250] eta: 0:00:24 lr: 0.000053 grad: 0.0959 (0.0956) loss: 0.8210 (0.8197) time: 0.1279 data: 0.0410 max mem: 9390 +Train: [56] [6200/6250] eta: 0:00:08 lr: 0.000053 grad: 0.0994 (0.0957) loss: 0.8192 (0.8197) time: 0.1354 data: 0.0546 max mem: 9390 +Train: [56] [6249/6250] eta: 0:00:00 lr: 0.000053 grad: 0.0942 (0.0957) loss: 0.8194 (0.8197) time: 0.1419 data: 0.0609 max mem: 9390 +Train: [56] Total time: 0:17:00 (0.1633 s / it) +Averaged stats: lr: 0.000053 grad: 0.0942 (0.0957) loss: 0.8194 (0.8197) +Eval (hcp-train-subset): [56] [ 0/62] eta: 0:04:51 loss: 0.8464 (0.8464) time: 4.7069 data: 4.6763 max mem: 9390 +Eval (hcp-train-subset): [56] [61/62] eta: 0:00:00 loss: 0.8341 (0.8354) time: 0.1204 data: 0.0937 max mem: 9390 +Eval (hcp-train-subset): [56] Total time: 0:00:13 (0.2132 s / it) +Averaged stats (hcp-train-subset): loss: 0.8341 (0.8354) +Eval (hcp-val): [56] [ 0/62] eta: 0:04:58 loss: 0.8337 (0.8337) time: 4.8076 data: 4.7765 max mem: 9390 +Eval (hcp-val): [56] [61/62] eta: 0:00:00 loss: 0.8349 (0.8344) time: 0.1600 data: 0.1337 max mem: 9390 +Eval (hcp-val): [56] Total time: 0:00:15 (0.2562 s / it) +Averaged stats (hcp-val): loss: 0.8349 (0.8344) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +Train: [57] [ 0/6250] eta: 15:04:38 lr: 0.000053 grad: 0.3222 (0.3222) loss: 0.8296 (0.8296) time: 8.6846 data: 8.5721 max mem: 9390 +Train: [57] [ 100/6250] eta: 0:25:46 lr: 0.000053 grad: 0.0922 (0.1263) loss: 0.8223 (0.8221) time: 0.1942 data: 0.1042 max mem: 9390 +Train: [57] [ 200/6250] eta: 0:20:58 lr: 0.000053 grad: 0.0978 (0.1141) loss: 0.8200 (0.8180) time: 0.1834 data: 0.1008 max mem: 9390 +Train: [57] [ 300/6250] eta: 0:19:18 lr: 0.000053 grad: 0.0928 (0.1103) loss: 0.8099 (0.8179) time: 0.1663 data: 0.0769 max mem: 9390 +Train: [57] [ 400/6250] eta: 0:18:05 lr: 0.000053 grad: 0.0884 (0.1076) loss: 0.8210 (0.8187) time: 0.1570 data: 0.0757 max mem: 9390 +Train: [57] [ 500/6250] eta: 0:17:33 lr: 0.000053 grad: 0.0909 (0.1052) loss: 0.8204 (0.8188) time: 0.1509 data: 0.0612 max mem: 9390 +Train: [57] [ 600/6250] eta: 0:16:54 lr: 0.000053 grad: 0.0952 (0.1037) loss: 0.8205 (0.8186) time: 0.1451 data: 0.0647 max mem: 9390 +Train: [57] [ 700/6250] eta: 0:16:25 lr: 0.000053 grad: 0.0980 (0.1023) loss: 0.8241 (0.8191) time: 0.1948 data: 0.1158 max mem: 9390 +Train: [57] [ 800/6250] eta: 0:16:04 lr: 0.000053 grad: 0.0984 (0.1014) loss: 0.8185 (0.8193) time: 0.2304 data: 0.1421 max mem: 9390 +Train: [57] [ 900/6250] eta: 0:15:26 lr: 0.000053 grad: 0.0883 (0.1009) loss: 0.8194 (0.8194) time: 0.1406 data: 0.0579 max mem: 9390 +Train: [57] [1000/6250] eta: 0:15:02 lr: 0.000053 grad: 0.0875 (0.1004) loss: 0.8183 (0.8196) time: 0.1862 data: 0.1115 max mem: 9390 +Train: [57] [1100/6250] eta: 0:14:35 lr: 0.000053 grad: 0.0952 (0.1000) loss: 0.8211 (0.8195) time: 0.1770 data: 0.0974 max mem: 9390 +Train: [57] [1200/6250] eta: 0:14:07 lr: 0.000053 grad: 0.0984 (0.0997) loss: 0.8156 (0.8196) time: 0.1548 data: 0.0728 max mem: 9390 +Train: [57] [1300/6250] eta: 0:13:43 lr: 0.000053 grad: 0.0946 (0.0996) loss: 0.8209 (0.8195) time: 0.1573 data: 0.0680 max mem: 9390 +Train: [57] [1400/6250] eta: 0:13:23 lr: 0.000053 grad: 0.1036 (0.0996) loss: 0.8077 (0.8194) time: 0.1590 data: 0.0792 max mem: 9390 +Train: [57] [1500/6250] eta: 0:13:03 lr: 0.000053 grad: 0.0965 (0.0995) loss: 0.8236 (0.8193) time: 0.1631 data: 0.0850 max mem: 9390 +Train: [57] [1600/6250] eta: 0:12:42 lr: 0.000053 grad: 0.0939 (0.0993) loss: 0.8126 (0.8192) time: 0.1556 data: 0.0748 max mem: 9390 +Train: [57] [1700/6250] eta: 0:12:25 lr: 0.000053 grad: 0.0981 (0.0994) loss: 0.8142 (0.8189) time: 0.1442 data: 0.0599 max mem: 9390 +Train: [57] [1800/6250] eta: 0:12:06 lr: 0.000053 grad: 0.0952 (0.0992) loss: 0.8179 (0.8188) time: 0.1584 data: 0.0787 max mem: 9390 +Train: [57] [1900/6250] eta: 0:11:48 lr: 0.000053 grad: 0.0924 (0.0993) loss: 0.8161 (0.8186) time: 0.1370 data: 0.0497 max mem: 9390 +Train: [57] [2000/6250] eta: 0:11:28 lr: 0.000053 grad: 0.0969 (0.0994) loss: 0.8113 (0.8184) time: 0.1441 data: 0.0548 max mem: 9390 +Train: [57] [2100/6250] eta: 0:11:10 lr: 0.000053 grad: 0.0988 (0.0993) loss: 0.8156 (0.8184) time: 0.1469 data: 0.0656 max mem: 9390 +Train: [57] [2200/6250] eta: 0:10:54 lr: 0.000053 grad: 0.0951 (0.0992) loss: 0.8217 (0.8183) time: 0.1644 data: 0.0778 max mem: 9390 +Train: [57] [2300/6250] eta: 0:10:36 lr: 0.000052 grad: 0.0979 (0.0993) loss: 0.8150 (0.8182) time: 0.1247 data: 0.0375 max mem: 9390 +Train: [57] [2400/6250] eta: 0:10:19 lr: 0.000052 grad: 0.0933 (0.0993) loss: 0.8169 (0.8182) time: 0.1552 data: 0.0762 max mem: 9390 +Train: [57] [2500/6250] eta: 0:10:02 lr: 0.000052 grad: 0.1007 (0.0993) loss: 0.8125 (0.8181) time: 0.1323 data: 0.0434 max mem: 9390 +Train: [57] [2600/6250] eta: 0:09:45 lr: 0.000052 grad: 0.0967 (0.0993) loss: 0.8115 (0.8180) time: 0.1629 data: 0.0743 max mem: 9390 +Train: [57] [2700/6250] eta: 0:09:28 lr: 0.000052 grad: 0.0995 (0.0993) loss: 0.8190 (0.8180) time: 0.1438 data: 0.0545 max mem: 9390 +Train: [57] [2800/6250] eta: 0:09:11 lr: 0.000052 grad: 0.0991 (0.0994) loss: 0.8189 (0.8180) time: 0.1466 data: 0.0542 max mem: 9390 +Train: [57] [2900/6250] eta: 0:08:54 lr: 0.000052 grad: 0.0948 (0.0993) loss: 0.8182 (0.8181) time: 0.1271 data: 0.0475 max mem: 9390 +Train: [57] [3000/6250] eta: 0:08:38 lr: 0.000052 grad: 0.1008 (0.0994) loss: 0.8184 (0.8181) time: 0.1587 data: 0.0809 max mem: 9390 +Train: [57] [3100/6250] eta: 0:08:22 lr: 0.000052 grad: 0.0985 (0.0995) loss: 0.8162 (0.8181) time: 0.1439 data: 0.0639 max mem: 9390 +Train: [57] [3200/6250] eta: 0:08:06 lr: 0.000052 grad: 0.0990 (0.0995) loss: 0.8175 (0.8181) time: 0.1711 data: 0.0828 max mem: 9390 +Train: [57] [3300/6250] eta: 0:07:50 lr: 0.000052 grad: 0.1004 (0.0995) loss: 0.8183 (0.8180) time: 0.1638 data: 0.0747 max mem: 9390 +Train: [57] [3400/6250] eta: 0:07:34 lr: 0.000052 grad: 0.1008 (0.0995) loss: 0.8173 (0.8180) time: 0.1695 data: 0.0847 max mem: 9390 +Train: [57] [3500/6250] eta: 0:07:17 lr: 0.000052 grad: 0.0964 (0.0996) loss: 0.8150 (0.8180) time: 0.1688 data: 0.0755 max mem: 9390 +Train: [57] [3600/6250] eta: 0:07:01 lr: 0.000052 grad: 0.1006 (0.0996) loss: 0.8141 (0.8180) time: 0.1663 data: 0.0890 max mem: 9390 +Train: [57] [3700/6250] eta: 0:06:46 lr: 0.000052 grad: 0.0968 (0.0996) loss: 0.8174 (0.8180) time: 0.1292 data: 0.0334 max mem: 9390 +Train: [57] [3800/6250] eta: 0:06:29 lr: 0.000052 grad: 0.1017 (0.0996) loss: 0.8135 (0.8180) time: 0.1428 data: 0.0577 max mem: 9390 +Train: [57] [3900/6250] eta: 0:06:13 lr: 0.000052 grad: 0.1031 (0.0996) loss: 0.8154 (0.8180) time: 0.1397 data: 0.0428 max mem: 9390 +Train: [57] [4000/6250] eta: 0:05:57 lr: 0.000052 grad: 0.0955 (0.0996) loss: 0.8152 (0.8179) time: 0.1605 data: 0.0782 max mem: 9390 +Train: [57] [4100/6250] eta: 0:05:41 lr: 0.000052 grad: 0.0994 (0.0997) loss: 0.8236 (0.8179) time: 0.1658 data: 0.0752 max mem: 9390 +Train: [57] [4200/6250] eta: 0:05:24 lr: 0.000052 grad: 0.0927 (0.0997) loss: 0.8148 (0.8178) time: 0.1353 data: 0.0504 max mem: 9390 +Train: [57] [4300/6250] eta: 0:05:08 lr: 0.000052 grad: 0.0987 (0.0997) loss: 0.8212 (0.8178) time: 0.1644 data: 0.0860 max mem: 9390 +Train: [57] [4400/6250] eta: 0:04:52 lr: 0.000052 grad: 0.1056 (0.0997) loss: 0.8220 (0.8179) time: 0.1574 data: 0.0800 max mem: 9390 +Train: [57] [4500/6250] eta: 0:04:36 lr: 0.000052 grad: 0.0912 (0.0997) loss: 0.8164 (0.8179) time: 0.1886 data: 0.1092 max mem: 9390 +Train: [57] [4600/6250] eta: 0:04:20 lr: 0.000052 grad: 0.1020 (0.0998) loss: 0.8123 (0.8179) time: 0.1733 data: 0.0943 max mem: 9390 +Train: [57] [4700/6250] eta: 0:04:04 lr: 0.000052 grad: 0.1000 (0.0998) loss: 0.8201 (0.8178) time: 0.1685 data: 0.0894 max mem: 9390 +Train: [57] [4800/6250] eta: 0:03:48 lr: 0.000052 grad: 0.0985 (0.0998) loss: 0.8246 (0.8179) time: 0.1490 data: 0.0682 max mem: 9390 +Train: [57] [4900/6250] eta: 0:03:33 lr: 0.000052 grad: 0.0976 (0.0999) loss: 0.8145 (0.8178) time: 0.1704 data: 0.0945 max mem: 9390 +Train: [57] [5000/6250] eta: 0:03:17 lr: 0.000052 grad: 0.0960 (0.0999) loss: 0.8148 (0.8178) time: 0.1699 data: 0.0924 max mem: 9390 +Train: [57] [5100/6250] eta: 0:03:01 lr: 0.000052 grad: 0.0965 (0.0998) loss: 0.8213 (0.8178) time: 0.1511 data: 0.0734 max mem: 9390 +Train: [57] [5200/6250] eta: 0:02:45 lr: 0.000052 grad: 0.0963 (0.0998) loss: 0.8168 (0.8178) time: 0.1181 data: 0.0290 max mem: 9390 +Train: [57] [5300/6250] eta: 0:02:29 lr: 0.000052 grad: 0.0991 (0.0999) loss: 0.8114 (0.8177) time: 0.1406 data: 0.0513 max mem: 9390 +Train: [57] [5400/6250] eta: 0:02:14 lr: 0.000051 grad: 0.0959 (0.0999) loss: 0.8156 (0.8177) time: 0.1535 data: 0.0695 max mem: 9390 +Train: [57] [5500/6250] eta: 0:01:58 lr: 0.000051 grad: 0.0932 (0.0999) loss: 0.8199 (0.8177) time: 0.2074 data: 0.1275 max mem: 9390 +Train: [57] [5600/6250] eta: 0:01:42 lr: 0.000051 grad: 0.0962 (0.0999) loss: 0.8180 (0.8177) time: 0.1437 data: 0.0458 max mem: 9390 +Train: [57] [5700/6250] eta: 0:01:26 lr: 0.000051 grad: 0.1061 (0.1000) loss: 0.8088 (0.8176) time: 0.1451 data: 0.0525 max mem: 9390 +Train: [57] [5800/6250] eta: 0:01:11 lr: 0.000051 grad: 0.0968 (0.1000) loss: 0.8119 (0.8175) time: 0.1464 data: 0.0641 max mem: 9390 +Train: [57] [5900/6250] eta: 0:00:55 lr: 0.000051 grad: 0.0969 (0.1000) loss: 0.8134 (0.8175) time: 0.1535 data: 0.0733 max mem: 9390 +Train: [57] [6000/6250] eta: 0:00:39 lr: 0.000051 grad: 0.0947 (0.1000) loss: 0.8173 (0.8175) time: 0.1485 data: 0.0691 max mem: 9390 +Train: [57] [6100/6250] eta: 0:00:23 lr: 0.000051 grad: 0.0962 (0.1000) loss: 0.8158 (0.8175) time: 0.1385 data: 0.0529 max mem: 9390 +Train: [57] [6200/6250] eta: 0:00:07 lr: 0.000051 grad: 0.0915 (0.0999) loss: 0.8155 (0.8175) time: 0.1383 data: 0.0519 max mem: 9390 +Train: [57] [6249/6250] eta: 0:00:00 lr: 0.000051 grad: 0.0980 (0.0999) loss: 0.8153 (0.8175) time: 0.1660 data: 0.0831 max mem: 9390 +Train: [57] Total time: 0:16:30 (0.1586 s / it) +Averaged stats: lr: 0.000051 grad: 0.0980 (0.0999) loss: 0.8153 (0.8175) +Eval (hcp-train-subset): [57] [ 0/62] eta: 0:05:27 loss: 0.8421 (0.8421) time: 5.2807 data: 5.2173 max mem: 9390 +Eval (hcp-train-subset): [57] [61/62] eta: 0:00:00 loss: 0.8338 (0.8353) time: 0.1289 data: 0.1040 max mem: 9390 +Eval (hcp-train-subset): [57] Total time: 0:00:13 (0.2125 s / it) +Averaged stats (hcp-train-subset): loss: 0.8338 (0.8353) +Eval (hcp-val): [57] [ 0/62] eta: 0:05:18 loss: 0.8338 (0.8338) time: 5.1444 data: 5.1142 max mem: 9390 +Eval (hcp-val): [57] [61/62] eta: 0:00:00 loss: 0.8346 (0.8348) time: 0.1432 data: 0.1158 max mem: 9390 +Eval (hcp-val): [57] Total time: 0:00:12 (0.2089 s / it) +Averaged stats (hcp-val): loss: 0.8346 (0.8348) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +Train: [58] [ 0/6250] eta: 8:46:06 lr: 0.000051 grad: 0.1711 (0.1711) loss: 0.8361 (0.8361) time: 5.0507 data: 4.8835 max mem: 9390 +Train: [58] [ 100/6250] eta: 0:20:53 lr: 0.000051 grad: 0.1053 (0.1298) loss: 0.8258 (0.8305) time: 0.1655 data: 0.0843 max mem: 9390 +Train: [58] [ 200/6250] eta: 0:18:27 lr: 0.000051 grad: 0.0882 (0.1133) loss: 0.8235 (0.8295) time: 0.1694 data: 0.0876 max mem: 9390 +Train: [58] [ 300/6250] eta: 0:17:50 lr: 0.000051 grad: 0.0932 (0.1081) loss: 0.8185 (0.8267) time: 0.1917 data: 0.0949 max mem: 9390 +Train: [58] [ 400/6250] eta: 0:17:37 lr: 0.000051 grad: 0.0964 (0.1050) loss: 0.8224 (0.8256) time: 0.1766 data: 0.0895 max mem: 9390 +Train: [58] [ 500/6250] eta: 0:16:55 lr: 0.000051 grad: 0.0995 (0.1041) loss: 0.8152 (0.8246) time: 0.1771 data: 0.0928 max mem: 9390 +Train: [58] [ 600/6250] eta: 0:16:29 lr: 0.000051 grad: 0.0891 (0.1025) loss: 0.8247 (0.8242) time: 0.2118 data: 0.1302 max mem: 9390 +Train: [58] [ 700/6250] eta: 0:15:58 lr: 0.000051 grad: 0.0946 (0.1017) loss: 0.8106 (0.8239) time: 0.1785 data: 0.0937 max mem: 9390 +Train: [58] [ 800/6250] eta: 0:15:35 lr: 0.000051 grad: 0.1038 (0.1011) loss: 0.8173 (0.8234) time: 0.1383 data: 0.0279 max mem: 9390 +Train: [58] [ 900/6250] eta: 0:15:13 lr: 0.000051 grad: 0.0922 (0.1008) loss: 0.8222 (0.8234) time: 0.1516 data: 0.0559 max mem: 9390 +Train: [58] [1000/6250] eta: 0:14:49 lr: 0.000051 grad: 0.0908 (0.1003) loss: 0.8259 (0.8233) time: 0.1655 data: 0.0799 max mem: 9390 +Train: [58] [1100/6250] eta: 0:14:25 lr: 0.000051 grad: 0.0964 (0.1000) loss: 0.8182 (0.8231) time: 0.1623 data: 0.0750 max mem: 9390 +Train: [58] [1200/6250] eta: 0:14:01 lr: 0.000051 grad: 0.0964 (0.0996) loss: 0.8144 (0.8228) time: 0.1535 data: 0.0694 max mem: 9390 +Train: [58] [1300/6250] eta: 0:13:47 lr: 0.000051 grad: 0.0955 (0.0994) loss: 0.8225 (0.8227) time: 0.1832 data: 0.0951 max mem: 9390 +Train: [58] [1400/6250] eta: 0:13:27 lr: 0.000051 grad: 0.0921 (0.0992) loss: 0.8237 (0.8226) time: 0.1798 data: 0.0810 max mem: 9390 +Train: [58] [1500/6250] eta: 0:13:08 lr: 0.000051 grad: 0.1000 (0.0991) loss: 0.8141 (0.8224) time: 0.1300 data: 0.0446 max mem: 9390 +Train: [58] [1600/6250] eta: 0:12:49 lr: 0.000051 grad: 0.1013 (0.0991) loss: 0.8191 (0.8223) time: 0.1759 data: 0.0908 max mem: 9390 +Train: [58] [1700/6250] eta: 0:12:30 lr: 0.000051 grad: 0.0996 (0.0990) loss: 0.8223 (0.8221) time: 0.1565 data: 0.0673 max mem: 9390 +Train: [58] [1800/6250] eta: 0:12:14 lr: 0.000051 grad: 0.0991 (0.0990) loss: 0.8242 (0.8220) time: 0.1711 data: 0.0857 max mem: 9390 +Train: [58] [1900/6250] eta: 0:11:55 lr: 0.000051 grad: 0.0987 (0.0990) loss: 0.8169 (0.8217) time: 0.1609 data: 0.0757 max mem: 9390 +Train: [58] [2000/6250] eta: 0:11:37 lr: 0.000051 grad: 0.0937 (0.0991) loss: 0.8146 (0.8215) time: 0.1398 data: 0.0576 max mem: 9390 +Train: [58] [2100/6250] eta: 0:11:20 lr: 0.000051 grad: 0.0951 (0.0991) loss: 0.8131 (0.8212) time: 0.1596 data: 0.0799 max mem: 9390 +Train: [58] [2200/6250] eta: 0:11:02 lr: 0.000050 grad: 0.0975 (0.0990) loss: 0.8162 (0.8211) time: 0.1661 data: 0.0822 max mem: 9390 +Train: [58] [2300/6250] eta: 0:10:45 lr: 0.000050 grad: 0.0998 (0.0992) loss: 0.8233 (0.8208) time: 0.1426 data: 0.0637 max mem: 9390 +Train: [58] [2400/6250] eta: 0:10:26 lr: 0.000050 grad: 0.0994 (0.0992) loss: 0.8164 (0.8207) time: 0.1121 data: 0.0120 max mem: 9390 +Train: [58] [2500/6250] eta: 0:10:10 lr: 0.000050 grad: 0.0950 (0.0992) loss: 0.8180 (0.8206) time: 0.1530 data: 0.0661 max mem: 9390 +Train: [58] [2600/6250] eta: 0:09:53 lr: 0.000050 grad: 0.1008 (0.0992) loss: 0.8172 (0.8204) time: 0.1634 data: 0.0794 max mem: 9390 +Train: [58] [2700/6250] eta: 0:09:35 lr: 0.000050 grad: 0.0956 (0.0992) loss: 0.8230 (0.8203) time: 0.1659 data: 0.0820 max mem: 9390 +Train: [58] [2800/6250] eta: 0:09:18 lr: 0.000050 grad: 0.1022 (0.0993) loss: 0.8199 (0.8202) time: 0.1299 data: 0.0380 max mem: 9390 +Train: [58] [2900/6250] eta: 0:09:00 lr: 0.000050 grad: 0.0927 (0.0993) loss: 0.8160 (0.8201) time: 0.1645 data: 0.0749 max mem: 9390 +Train: [58] [3000/6250] eta: 0:08:43 lr: 0.000050 grad: 0.0928 (0.0993) loss: 0.8274 (0.8200) time: 0.1538 data: 0.0722 max mem: 9390 +Train: [58] [3100/6250] eta: 0:08:26 lr: 0.000050 grad: 0.1013 (0.0993) loss: 0.8158 (0.8199) time: 0.1558 data: 0.0632 max mem: 9390 +Train: [58] [3200/6250] eta: 0:08:09 lr: 0.000050 grad: 0.0910 (0.0993) loss: 0.8226 (0.8198) time: 0.1544 data: 0.0777 max mem: 9390 +Train: [58] [3300/6250] eta: 0:07:53 lr: 0.000050 grad: 0.0997 (0.0994) loss: 0.8129 (0.8197) time: 0.1531 data: 0.0684 max mem: 9390 +Train: [58] [3400/6250] eta: 0:07:39 lr: 0.000050 grad: 0.0994 (0.0995) loss: 0.8186 (0.8196) time: 0.1683 data: 0.0775 max mem: 9390 +Train: [58] [3500/6250] eta: 0:07:24 lr: 0.000050 grad: 0.0994 (0.0995) loss: 0.8242 (0.8196) time: 0.1560 data: 0.0678 max mem: 9390 +Train: [58] [3600/6250] eta: 0:07:09 lr: 0.000050 grad: 0.0960 (0.0995) loss: 0.8171 (0.8196) time: 0.1965 data: 0.1152 max mem: 9390 +Train: [58] [3700/6250] eta: 0:06:52 lr: 0.000050 grad: 0.0943 (0.0995) loss: 0.8227 (0.8195) time: 0.1473 data: 0.0669 max mem: 9390 +Train: [58] [3800/6250] eta: 0:06:37 lr: 0.000050 grad: 0.0979 (0.0995) loss: 0.8181 (0.8195) time: 0.1888 data: 0.1034 max mem: 9390 +Train: [58] [3900/6250] eta: 0:06:22 lr: 0.000050 grad: 0.0937 (0.0995) loss: 0.8186 (0.8194) time: 0.2152 data: 0.1387 max mem: 9390 +Train: [58] [4000/6250] eta: 0:06:08 lr: 0.000050 grad: 0.0983 (0.0996) loss: 0.8189 (0.8194) time: 0.1654 data: 0.0764 max mem: 9390 +Train: [58] [4100/6250] eta: 0:05:52 lr: 0.000050 grad: 0.0978 (0.0996) loss: 0.8210 (0.8194) time: 0.1764 data: 0.0874 max mem: 9390 +Train: [58] [4200/6250] eta: 0:05:36 lr: 0.000050 grad: 0.1029 (0.0996) loss: 0.8199 (0.8195) time: 0.1864 data: 0.0976 max mem: 9390 +Train: [58] [4300/6250] eta: 0:05:20 lr: 0.000050 grad: 0.0959 (0.0996) loss: 0.8212 (0.8196) time: 0.1736 data: 0.0767 max mem: 9390 +Train: [58] [4400/6250] eta: 0:05:04 lr: 0.000050 grad: 0.1029 (0.0996) loss: 0.8217 (0.8196) time: 0.1859 data: 0.0908 max mem: 9390 +Train: [58] [4500/6250] eta: 0:04:48 lr: 0.000050 grad: 0.0975 (0.0997) loss: 0.8194 (0.8195) time: 0.1797 data: 0.0817 max mem: 9390 +Train: [58] [4600/6250] eta: 0:04:32 lr: 0.000050 grad: 0.0953 (0.0998) loss: 0.8156 (0.8195) time: 0.1898 data: 0.0916 max mem: 9390 +Train: [58] [4700/6250] eta: 0:04:15 lr: 0.000050 grad: 0.0998 (0.0998) loss: 0.8156 (0.8194) time: 0.1388 data: 0.0552 max mem: 9390 +Train: [58] [4800/6250] eta: 0:03:58 lr: 0.000050 grad: 0.0986 (0.0999) loss: 0.8140 (0.8192) time: 0.1657 data: 0.0760 max mem: 9390 +Train: [58] [4900/6250] eta: 0:03:41 lr: 0.000050 grad: 0.1009 (0.0999) loss: 0.8145 (0.8192) time: 0.1527 data: 0.0656 max mem: 9390 +Train: [58] [5000/6250] eta: 0:03:25 lr: 0.000050 grad: 0.0974 (0.0999) loss: 0.8184 (0.8191) time: 0.1397 data: 0.0524 max mem: 9390 +Train: [58] [5100/6250] eta: 0:03:08 lr: 0.000050 grad: 0.1027 (0.1000) loss: 0.8121 (0.8190) time: 0.1474 data: 0.0633 max mem: 9390 +Train: [58] [5200/6250] eta: 0:02:51 lr: 0.000050 grad: 0.0914 (0.1000) loss: 0.8191 (0.8190) time: 0.1653 data: 0.0835 max mem: 9390 +Train: [58] [5300/6250] eta: 0:02:35 lr: 0.000049 grad: 0.0982 (0.1001) loss: 0.8163 (0.8189) time: 0.1425 data: 0.0459 max mem: 9390 +Train: [58] [5400/6250] eta: 0:02:18 lr: 0.000049 grad: 0.0910 (0.1001) loss: 0.8162 (0.8189) time: 0.1478 data: 0.0646 max mem: 9390 +Train: [58] [5500/6250] eta: 0:02:02 lr: 0.000049 grad: 0.1011 (0.1001) loss: 0.8217 (0.8188) time: 0.1407 data: 0.0575 max mem: 9390 +Train: [58] [5600/6250] eta: 0:01:45 lr: 0.000049 grad: 0.0989 (0.1001) loss: 0.8199 (0.8188) time: 0.1623 data: 0.0774 max mem: 9390 +Train: [58] [5700/6250] eta: 0:01:29 lr: 0.000049 grad: 0.0995 (0.1002) loss: 0.8207 (0.8188) time: 0.1565 data: 0.0765 max mem: 9390 +Train: [58] [5800/6250] eta: 0:01:13 lr: 0.000049 grad: 0.0967 (0.1002) loss: 0.8207 (0.8188) time: 0.1573 data: 0.0736 max mem: 9390 +Train: [58] [5900/6250] eta: 0:00:56 lr: 0.000049 grad: 0.0965 (0.1002) loss: 0.8150 (0.8188) time: 0.1575 data: 0.0681 max mem: 9390 +Train: [58] [6000/6250] eta: 0:00:40 lr: 0.000049 grad: 0.0946 (0.1002) loss: 0.8190 (0.8188) time: 0.1365 data: 0.0501 max mem: 9390 +Train: [58] [6100/6250] eta: 0:00:24 lr: 0.000049 grad: 0.0916 (0.1002) loss: 0.8219 (0.8188) time: 0.1363 data: 0.0468 max mem: 9390 +Train: [58] [6200/6250] eta: 0:00:08 lr: 0.000049 grad: 0.1076 (0.1002) loss: 0.8093 (0.8188) time: 0.1425 data: 0.0586 max mem: 9390 +Train: [58] [6249/6250] eta: 0:00:00 lr: 0.000049 grad: 0.0986 (0.1002) loss: 0.8098 (0.8187) time: 0.1392 data: 0.0567 max mem: 9390 +Train: [58] Total time: 0:16:56 (0.1627 s / it) +Averaged stats: lr: 0.000049 grad: 0.0986 (0.1002) loss: 0.8098 (0.8187) +Eval (hcp-train-subset): [58] [ 0/62] eta: 0:03:39 loss: 0.8482 (0.8482) time: 3.5370 data: 3.4501 max mem: 9390 +Eval (hcp-train-subset): [58] [61/62] eta: 0:00:00 loss: 0.8339 (0.8349) time: 0.1373 data: 0.1118 max mem: 9390 +Eval (hcp-train-subset): [58] Total time: 0:00:13 (0.2144 s / it) +Averaged stats (hcp-train-subset): loss: 0.8339 (0.8349) +Eval (hcp-val): [58] [ 0/62] eta: 0:03:26 loss: 0.8312 (0.8312) time: 3.3349 data: 3.2674 max mem: 9390 +Eval (hcp-val): [58] [61/62] eta: 0:00:00 loss: 0.8327 (0.8336) time: 0.1158 data: 0.0908 max mem: 9390 +Eval (hcp-val): [58] Total time: 0:00:12 (0.2039 s / it) +Averaged stats (hcp-val): loss: 0.8327 (0.8336) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +Train: [59] [ 0/6250] eta: 9:06:49 lr: 0.000049 grad: 0.0605 (0.0605) loss: 0.8407 (0.8407) time: 5.2495 data: 5.1097 max mem: 9390 +Train: [59] [ 100/6250] eta: 0:20:35 lr: 0.000049 grad: 0.0902 (0.1295) loss: 0.8243 (0.8169) time: 0.1565 data: 0.0678 max mem: 9390 +Train: [59] [ 200/6250] eta: 0:17:55 lr: 0.000049 grad: 0.0905 (0.1166) loss: 0.8115 (0.8170) time: 0.1616 data: 0.0810 max mem: 9390 +Train: [59] [ 300/6250] eta: 0:16:41 lr: 0.000049 grad: 0.0964 (0.1117) loss: 0.8201 (0.8173) time: 0.1529 data: 0.0647 max mem: 9390 +Train: [59] [ 400/6250] eta: 0:15:40 lr: 0.000049 grad: 0.0889 (0.1077) loss: 0.8244 (0.8185) time: 0.1344 data: 0.0506 max mem: 9390 +Train: [59] [ 500/6250] eta: 0:15:14 lr: 0.000049 grad: 0.0909 (0.1048) loss: 0.8258 (0.8195) time: 0.1365 data: 0.0434 max mem: 9390 +Train: [59] [ 600/6250] eta: 0:14:49 lr: 0.000049 grad: 0.0900 (0.1033) loss: 0.8254 (0.8201) time: 0.1668 data: 0.0761 max mem: 9390 +Train: [59] [ 700/6250] eta: 0:14:36 lr: 0.000049 grad: 0.0965 (0.1027) loss: 0.8138 (0.8196) time: 0.1873 data: 0.1078 max mem: 9390 +Train: [59] [ 800/6250] eta: 0:14:18 lr: 0.000049 grad: 0.0909 (0.1022) loss: 0.8149 (0.8190) time: 0.1571 data: 0.0710 max mem: 9390 +Train: [59] [ 900/6250] eta: 0:14:10 lr: 0.000049 grad: 0.0939 (0.1019) loss: 0.8168 (0.8187) time: 0.1598 data: 0.0722 max mem: 9390 +Train: [59] [1000/6250] eta: 0:13:55 lr: 0.000049 grad: 0.1007 (0.1016) loss: 0.8139 (0.8184) time: 0.1580 data: 0.0750 max mem: 9390 +Train: [59] [1100/6250] eta: 0:13:41 lr: 0.000049 grad: 0.1003 (0.1014) loss: 0.8128 (0.8181) time: 0.1884 data: 0.1052 max mem: 9390 +Train: [59] [1200/6250] eta: 0:13:22 lr: 0.000049 grad: 0.0912 (0.1012) loss: 0.8201 (0.8178) time: 0.1545 data: 0.0652 max mem: 9390 +Train: [59] [1300/6250] eta: 0:13:06 lr: 0.000049 grad: 0.0952 (0.1009) loss: 0.8180 (0.8177) time: 0.1406 data: 0.0497 max mem: 9390 +Train: [59] [1400/6250] eta: 0:12:50 lr: 0.000049 grad: 0.0864 (0.1006) loss: 0.8216 (0.8175) time: 0.1329 data: 0.0432 max mem: 9390 +Train: [59] [1500/6250] eta: 0:12:31 lr: 0.000049 grad: 0.0953 (0.1006) loss: 0.8190 (0.8174) time: 0.1437 data: 0.0592 max mem: 9390 +Train: [59] [1600/6250] eta: 0:12:14 lr: 0.000049 grad: 0.0941 (0.1004) loss: 0.8181 (0.8173) time: 0.1376 data: 0.0365 max mem: 9390 +Train: [59] [1700/6250] eta: 0:11:59 lr: 0.000049 grad: 0.1027 (0.1005) loss: 0.8099 (0.8171) time: 0.1631 data: 0.0813 max mem: 9390 +Train: [59] [1800/6250] eta: 0:11:40 lr: 0.000049 grad: 0.0943 (0.1005) loss: 0.8161 (0.8169) time: 0.1483 data: 0.0687 max mem: 9390 +Train: [59] [1900/6250] eta: 0:11:22 lr: 0.000049 grad: 0.0919 (0.1005) loss: 0.8153 (0.8167) time: 0.1301 data: 0.0431 max mem: 9390 +Train: [59] [2000/6250] eta: 0:11:05 lr: 0.000049 grad: 0.0980 (0.1007) loss: 0.8186 (0.8167) time: 0.1188 data: 0.0243 max mem: 9390 +Train: [59] [2100/6250] eta: 0:10:49 lr: 0.000048 grad: 0.1004 (0.1008) loss: 0.8150 (0.8166) time: 0.1477 data: 0.0594 max mem: 9390 +Train: [59] [2200/6250] eta: 0:10:32 lr: 0.000048 grad: 0.0990 (0.1008) loss: 0.8103 (0.8166) time: 0.1141 data: 0.0238 max mem: 9390 +Train: [59] [2300/6250] eta: 0:10:16 lr: 0.000048 grad: 0.1012 (0.1009) loss: 0.8175 (0.8166) time: 0.1489 data: 0.0623 max mem: 9390 +Train: [59] [2400/6250] eta: 0:10:00 lr: 0.000048 grad: 0.0911 (0.1009) loss: 0.8176 (0.8166) time: 0.1468 data: 0.0631 max mem: 9390 +Train: [59] [2500/6250] eta: 0:09:44 lr: 0.000048 grad: 0.1008 (0.1010) loss: 0.8167 (0.8165) time: 0.1200 data: 0.0392 max mem: 9390 +Train: [59] [2600/6250] eta: 0:09:29 lr: 0.000048 grad: 0.0980 (0.1010) loss: 0.8158 (0.8165) time: 0.1520 data: 0.0686 max mem: 9390 +Train: [59] [2700/6250] eta: 0:09:13 lr: 0.000048 grad: 0.1074 (0.1011) loss: 0.8063 (0.8164) time: 0.1466 data: 0.0556 max mem: 9390 +Train: [59] [2800/6250] eta: 0:08:57 lr: 0.000048 grad: 0.0955 (0.1013) loss: 0.8183 (0.8163) time: 0.1626 data: 0.0689 max mem: 9390 +Train: [59] [2900/6250] eta: 0:08:44 lr: 0.000048 grad: 0.1031 (0.1013) loss: 0.8126 (0.8163) time: 0.1219 data: 0.0371 max mem: 9390 +Train: [59] [3000/6250] eta: 0:08:27 lr: 0.000048 grad: 0.1024 (0.1014) loss: 0.8175 (0.8163) time: 0.1444 data: 0.0615 max mem: 9390 +Train: [59] [3100/6250] eta: 0:08:11 lr: 0.000048 grad: 0.0969 (0.1016) loss: 0.8213 (0.8163) time: 0.1542 data: 0.0576 max mem: 9390 +Train: [59] [3200/6250] eta: 0:07:55 lr: 0.000048 grad: 0.1037 (0.1016) loss: 0.8175 (0.8162) time: 0.1551 data: 0.0703 max mem: 9390 +Train: [59] [3300/6250] eta: 0:07:40 lr: 0.000048 grad: 0.0969 (0.1016) loss: 0.8143 (0.8162) time: 0.1376 data: 0.0474 max mem: 9390 +Train: [59] [3400/6250] eta: 0:07:25 lr: 0.000048 grad: 0.0944 (0.1016) loss: 0.8196 (0.8162) time: 0.2073 data: 0.1208 max mem: 9390 +Train: [59] [3500/6250] eta: 0:07:09 lr: 0.000048 grad: 0.0992 (0.1016) loss: 0.8184 (0.8163) time: 0.1579 data: 0.0702 max mem: 9390 +Train: [59] [3600/6250] eta: 0:06:53 lr: 0.000048 grad: 0.0976 (0.1016) loss: 0.8217 (0.8163) time: 0.1301 data: 0.0386 max mem: 9390 +Train: [59] [3700/6250] eta: 0:06:37 lr: 0.000048 grad: 0.0989 (0.1016) loss: 0.8168 (0.8163) time: 0.1539 data: 0.0694 max mem: 9390 +Train: [59] [3800/6250] eta: 0:06:22 lr: 0.000048 grad: 0.1021 (0.1016) loss: 0.8160 (0.8163) time: 0.1628 data: 0.0796 max mem: 9390 +Train: [59] [3900/6250] eta: 0:06:06 lr: 0.000048 grad: 0.1028 (0.1016) loss: 0.8213 (0.8163) time: 0.1666 data: 0.0828 max mem: 9390 +Train: [59] [4000/6250] eta: 0:05:50 lr: 0.000048 grad: 0.1006 (0.1017) loss: 0.8203 (0.8164) time: 0.1737 data: 0.0957 max mem: 9390 +Train: [59] [4100/6250] eta: 0:05:35 lr: 0.000048 grad: 0.1017 (0.1017) loss: 0.8162 (0.8165) time: 0.1679 data: 0.0949 max mem: 9390 +Train: [59] [4200/6250] eta: 0:05:20 lr: 0.000048 grad: 0.0962 (0.1017) loss: 0.8212 (0.8165) time: 0.2068 data: 0.1243 max mem: 9390 +Train: [59] [4300/6250] eta: 0:05:04 lr: 0.000048 grad: 0.1005 (0.1017) loss: 0.8145 (0.8166) time: 0.1085 data: 0.0315 max mem: 9390 +Train: [59] [4400/6250] eta: 0:04:49 lr: 0.000048 grad: 0.0969 (0.1017) loss: 0.8165 (0.8166) time: 0.1451 data: 0.0630 max mem: 9390 +Train: [59] [4500/6250] eta: 0:04:33 lr: 0.000048 grad: 0.0952 (0.1017) loss: 0.8211 (0.8167) time: 0.1427 data: 0.0531 max mem: 9390 +Train: [59] [4600/6250] eta: 0:04:17 lr: 0.000048 grad: 0.0954 (0.1016) loss: 0.8196 (0.8167) time: 0.1176 data: 0.0197 max mem: 9390 +Train: [59] [4700/6250] eta: 0:04:02 lr: 0.000048 grad: 0.0987 (0.1016) loss: 0.8220 (0.8167) time: 0.1661 data: 0.0822 max mem: 9390 +Train: [59] [4800/6250] eta: 0:03:46 lr: 0.000048 grad: 0.0967 (0.1016) loss: 0.8214 (0.8168) time: 0.1454 data: 0.0599 max mem: 9390 +Train: [59] [4900/6250] eta: 0:03:31 lr: 0.000048 grad: 0.0991 (0.1016) loss: 0.8233 (0.8168) time: 0.1919 data: 0.1001 max mem: 9390 +Train: [59] [5000/6250] eta: 0:03:15 lr: 0.000048 grad: 0.0949 (0.1015) loss: 0.8179 (0.8168) time: 0.1302 data: 0.0439 max mem: 9390 +Train: [59] [5100/6250] eta: 0:03:00 lr: 0.000048 grad: 0.0948 (0.1015) loss: 0.8187 (0.8169) time: 0.1610 data: 0.0801 max mem: 9390 +Train: [59] [5200/6250] eta: 0:02:44 lr: 0.000047 grad: 0.0945 (0.1015) loss: 0.8185 (0.8169) time: 0.1504 data: 0.0727 max mem: 9390 +Train: [59] [5300/6250] eta: 0:02:28 lr: 0.000047 grad: 0.0974 (0.1015) loss: 0.8199 (0.8170) time: 0.1940 data: 0.1046 max mem: 9390 +Train: [59] [5400/6250] eta: 0:02:13 lr: 0.000047 grad: 0.0967 (0.1014) loss: 0.8208 (0.8171) time: 0.1494 data: 0.0629 max mem: 9390 +Train: [59] [5500/6250] eta: 0:01:57 lr: 0.000047 grad: 0.0974 (0.1013) loss: 0.8217 (0.8172) time: 0.1464 data: 0.0662 max mem: 9390 +Train: [59] [5600/6250] eta: 0:01:41 lr: 0.000047 grad: 0.0932 (0.1013) loss: 0.8177 (0.8172) time: 0.1861 data: 0.0981 max mem: 9390 +Train: [59] [5700/6250] eta: 0:01:26 lr: 0.000047 grad: 0.0967 (0.1012) loss: 0.8210 (0.8173) time: 0.1624 data: 0.0790 max mem: 9390 +Train: [59] [5800/6250] eta: 0:01:10 lr: 0.000047 grad: 0.0916 (0.1012) loss: 0.8190 (0.8174) time: 0.1937 data: 0.1031 max mem: 9390 +Train: [59] [5900/6250] eta: 0:00:55 lr: 0.000047 grad: 0.0999 (0.1012) loss: 0.8220 (0.8174) time: 0.1735 data: 0.0963 max mem: 9390 +Train: [59] [6000/6250] eta: 0:00:39 lr: 0.000047 grad: 0.0956 (0.1012) loss: 0.8213 (0.8174) time: 0.1568 data: 0.0716 max mem: 9390 +Train: [59] [6100/6250] eta: 0:00:23 lr: 0.000047 grad: 0.0905 (0.1011) loss: 0.8215 (0.8175) time: 0.1370 data: 0.0441 max mem: 9390 +Train: [59] [6200/6250] eta: 0:00:07 lr: 0.000047 grad: 0.0952 (0.1011) loss: 0.8161 (0.8175) time: 0.1322 data: 0.0424 max mem: 9390 +Train: [59] [6249/6250] eta: 0:00:00 lr: 0.000047 grad: 0.0994 (0.1011) loss: 0.8138 (0.8175) time: 0.1825 data: 0.0898 max mem: 9390 +Train: [59] Total time: 0:16:29 (0.1583 s / it) +Averaged stats: lr: 0.000047 grad: 0.0994 (0.1011) loss: 0.8138 (0.8175) +Eval (hcp-train-subset): [59] [ 0/62] eta: 0:03:14 loss: 0.8452 (0.8452) time: 3.1373 data: 3.0616 max mem: 9390 +Eval (hcp-train-subset): [59] [61/62] eta: 0:00:00 loss: 0.8350 (0.8342) time: 0.1363 data: 0.1113 max mem: 9390 +Eval (hcp-train-subset): [59] Total time: 0:00:13 (0.2170 s / it) +Averaged stats (hcp-train-subset): loss: 0.8350 (0.8342) +Making plots (hcp-train-subset): example=28 +Eval (hcp-val): [59] [ 0/62] eta: 0:04:27 loss: 0.8333 (0.8333) time: 4.3141 data: 4.2830 max mem: 9390 +Eval (hcp-val): [59] [61/62] eta: 0:00:00 loss: 0.8326 (0.8343) time: 0.1182 data: 0.0911 max mem: 9390 +Eval (hcp-val): [59] Total time: 0:00:13 (0.2141 s / it) +Averaged stats (hcp-val): loss: 0.8326 (0.8343) +Making plots (hcp-val): example=57 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +Train: [60] [ 0/6250] eta: 8:47:18 lr: 0.000047 grad: 0.0856 (0.0856) loss: 0.8718 (0.8718) time: 5.0622 data: 4.8439 max mem: 9390 +Train: [60] [ 100/6250] eta: 0:22:15 lr: 0.000047 grad: 0.0990 (0.1105) loss: 0.8269 (0.8324) time: 0.1475 data: 0.0530 max mem: 9390 +Train: [60] [ 200/6250] eta: 0:18:50 lr: 0.000047 grad: 0.1058 (0.1149) loss: 0.8217 (0.8242) time: 0.1681 data: 0.0823 max mem: 9390 +Train: [60] [ 300/6250] eta: 0:17:32 lr: 0.000047 grad: 0.1020 (0.1124) loss: 0.8136 (0.8217) time: 0.1520 data: 0.0725 max mem: 9390 +Train: [60] [ 400/6250] eta: 0:16:32 lr: 0.000047 grad: 0.0948 (0.1095) loss: 0.8215 (0.8215) time: 0.1415 data: 0.0571 max mem: 9390 +Train: [60] [ 500/6250] eta: 0:15:54 lr: 0.000047 grad: 0.0977 (0.1075) loss: 0.8277 (0.8213) time: 0.1639 data: 0.0751 max mem: 9390 +Train: [60] [ 600/6250] eta: 0:15:19 lr: 0.000047 grad: 0.0966 (0.1061) loss: 0.8167 (0.8212) time: 0.1494 data: 0.0614 max mem: 9390 +Train: [60] [ 700/6250] eta: 0:14:54 lr: 0.000047 grad: 0.0972 (0.1046) loss: 0.8266 (0.8215) time: 0.1558 data: 0.0695 max mem: 9390 +Train: [60] [ 800/6250] eta: 0:14:37 lr: 0.000047 grad: 0.0972 (0.1036) loss: 0.8179 (0.8213) time: 0.1453 data: 0.0592 max mem: 9390 +Train: [60] [ 900/6250] eta: 0:14:22 lr: 0.000047 grad: 0.0922 (0.1026) loss: 0.8197 (0.8215) time: 0.1498 data: 0.0617 max mem: 9390 +Train: [60] [1000/6250] eta: 0:14:09 lr: 0.000047 grad: 0.0945 (0.1020) loss: 0.8120 (0.8215) time: 0.1779 data: 0.0957 max mem: 9390 +Train: [60] [1100/6250] eta: 0:13:51 lr: 0.000047 grad: 0.0971 (0.1017) loss: 0.8245 (0.8215) time: 0.1468 data: 0.0592 max mem: 9390 +Train: [60] [1200/6250] eta: 0:13:36 lr: 0.000047 grad: 0.0939 (0.1017) loss: 0.8271 (0.8214) time: 0.1575 data: 0.0745 max mem: 9390 +Train: [60] [1300/6250] eta: 0:13:23 lr: 0.000047 grad: 0.1000 (0.1017) loss: 0.8151 (0.8209) time: 0.1676 data: 0.0818 max mem: 9390 +Train: [60] [1400/6250] eta: 0:13:06 lr: 0.000047 grad: 0.1046 (0.1018) loss: 0.8136 (0.8206) time: 0.1598 data: 0.0749 max mem: 9390 +Train: [60] [1500/6250] eta: 0:12:54 lr: 0.000047 grad: 0.0995 (0.1018) loss: 0.8163 (0.8203) time: 0.2204 data: 0.1343 max mem: 9390 +Train: [60] [1600/6250] eta: 0:12:38 lr: 0.000047 grad: 0.0976 (0.1019) loss: 0.8206 (0.8202) time: 0.1588 data: 0.0865 max mem: 9390 +Train: [60] [1700/6250] eta: 0:12:20 lr: 0.000047 grad: 0.0982 (0.1018) loss: 0.8212 (0.8201) time: 0.1641 data: 0.0731 max mem: 9390 +Train: [60] [1800/6250] eta: 0:12:04 lr: 0.000047 grad: 0.0964 (0.1018) loss: 0.8178 (0.8201) time: 0.1558 data: 0.0655 max mem: 9390 +Train: [60] [1900/6250] eta: 0:11:49 lr: 0.000047 grad: 0.0985 (0.1017) loss: 0.8198 (0.8201) time: 0.2350 data: 0.1518 max mem: 9390 +Train: [60] [2000/6250] eta: 0:11:29 lr: 0.000047 grad: 0.1000 (0.1016) loss: 0.8159 (0.8200) time: 0.1645 data: 0.0800 max mem: 9390 +Train: [60] [2100/6250] eta: 0:11:13 lr: 0.000046 grad: 0.0995 (0.1014) loss: 0.8168 (0.8201) time: 0.1796 data: 0.0984 max mem: 9390 +Train: [60] [2200/6250] eta: 0:11:01 lr: 0.000046 grad: 0.0994 (0.1013) loss: 0.8175 (0.8201) time: 0.2797 data: 0.1944 max mem: 9390 +Train: [60] [2300/6250] eta: 0:10:46 lr: 0.000046 grad: 0.0971 (0.1012) loss: 0.8178 (0.8201) time: 0.1850 data: 0.1053 max mem: 9390 +Train: [60] [2400/6250] eta: 0:10:31 lr: 0.000046 grad: 0.0995 (0.1012) loss: 0.8147 (0.8200) time: 0.1378 data: 0.0533 max mem: 9390 +Train: [60] [2500/6250] eta: 0:10:15 lr: 0.000046 grad: 0.0984 (0.1011) loss: 0.8179 (0.8200) time: 0.1475 data: 0.0700 max mem: 9390 +Train: [60] [2600/6250] eta: 0:10:01 lr: 0.000046 grad: 0.0929 (0.1012) loss: 0.8175 (0.8199) time: 0.1510 data: 0.0643 max mem: 9390 +Train: [60] [2700/6250] eta: 0:09:47 lr: 0.000046 grad: 0.0971 (0.1012) loss: 0.8202 (0.8198) time: 0.1921 data: 0.1079 max mem: 9390 +Train: [60] [2800/6250] eta: 0:09:31 lr: 0.000046 grad: 0.1032 (0.1013) loss: 0.8157 (0.8197) time: 0.1574 data: 0.0567 max mem: 9390 +Train: [60] [2900/6250] eta: 0:09:18 lr: 0.000046 grad: 0.0987 (0.1013) loss: 0.8131 (0.8196) time: 0.2448 data: 0.1678 max mem: 9390 +Train: [60] [3000/6250] eta: 0:09:05 lr: 0.000046 grad: 0.0978 (0.1013) loss: 0.8182 (0.8195) time: 0.1911 data: 0.1078 max mem: 9390 +Train: [60] [3100/6250] eta: 0:08:49 lr: 0.000046 grad: 0.0937 (0.1013) loss: 0.8162 (0.8194) time: 0.1904 data: 0.1076 max mem: 9390 +Train: [60] [3200/6250] eta: 0:08:34 lr: 0.000046 grad: 0.1035 (0.1013) loss: 0.8110 (0.8193) time: 0.1732 data: 0.0903 max mem: 9390 +Train: [60] [3300/6250] eta: 0:08:17 lr: 0.000046 grad: 0.0988 (0.1015) loss: 0.8136 (0.8192) time: 0.2130 data: 0.1242 max mem: 9390 +Train: [60] [3400/6250] eta: 0:08:02 lr: 0.000046 grad: 0.1034 (0.1016) loss: 0.8197 (0.8191) time: 0.1968 data: 0.0983 max mem: 9390 +Train: [60] [3500/6250] eta: 0:07:46 lr: 0.000046 grad: 0.0994 (0.1016) loss: 0.8198 (0.8190) time: 0.1723 data: 0.0693 max mem: 9390 +Train: [60] [3600/6250] eta: 0:07:29 lr: 0.000046 grad: 0.1021 (0.1017) loss: 0.8162 (0.8189) time: 0.1753 data: 0.0907 max mem: 9390 +Train: [60] [3700/6250] eta: 0:07:12 lr: 0.000046 grad: 0.0975 (0.1018) loss: 0.8153 (0.8188) time: 0.1626 data: 0.0750 max mem: 9390 +Train: [60] [3800/6250] eta: 0:06:54 lr: 0.000046 grad: 0.0999 (0.1019) loss: 0.8198 (0.8188) time: 0.1522 data: 0.0712 max mem: 9390 +Train: [60] [3900/6250] eta: 0:06:37 lr: 0.000046 grad: 0.1023 (0.1019) loss: 0.8176 (0.8188) time: 0.1284 data: 0.0439 max mem: 9390 +Train: [60] [4000/6250] eta: 0:06:20 lr: 0.000046 grad: 0.0994 (0.1019) loss: 0.8133 (0.8188) time: 0.1767 data: 0.0927 max mem: 9390 +Train: [60] [4100/6250] eta: 0:06:02 lr: 0.000046 grad: 0.1127 (0.1021) loss: 0.8230 (0.8187) time: 0.1631 data: 0.0828 max mem: 9390 +Train: [60] [4200/6250] eta: 0:05:44 lr: 0.000046 grad: 0.1021 (0.1022) loss: 0.8169 (0.8186) time: 0.1388 data: 0.0539 max mem: 9390 +Train: [60] [4300/6250] eta: 0:05:27 lr: 0.000046 grad: 0.0956 (0.1022) loss: 0.8246 (0.8187) time: 0.1607 data: 0.0749 max mem: 9390 +Train: [60] [4400/6250] eta: 0:05:10 lr: 0.000046 grad: 0.1071 (0.1022) loss: 0.8152 (0.8186) time: 0.1665 data: 0.0793 max mem: 9390 +Train: [60] [4500/6250] eta: 0:04:52 lr: 0.000046 grad: 0.1021 (0.1023) loss: 0.8132 (0.8186) time: 0.1518 data: 0.0699 max mem: 9390 +Train: [60] [4600/6250] eta: 0:04:35 lr: 0.000046 grad: 0.1047 (0.1024) loss: 0.8191 (0.8186) time: 0.1701 data: 0.0898 max mem: 9390 +Train: [60] [4700/6250] eta: 0:04:18 lr: 0.000046 grad: 0.1044 (0.1025) loss: 0.8123 (0.8185) time: 0.1445 data: 0.0616 max mem: 9390 +Train: [60] [4800/6250] eta: 0:04:01 lr: 0.000046 grad: 0.1035 (0.1026) loss: 0.8161 (0.8185) time: 0.1581 data: 0.0769 max mem: 9390 +Train: [60] [4900/6250] eta: 0:03:44 lr: 0.000046 grad: 0.1123 (0.1027) loss: 0.8159 (0.8184) time: 0.1310 data: 0.0540 max mem: 9390 +Train: [60] [5000/6250] eta: 0:03:27 lr: 0.000046 grad: 0.1073 (0.1027) loss: 0.8193 (0.8184) time: 0.1422 data: 0.0607 max mem: 9390 +Train: [60] [5100/6250] eta: 0:03:10 lr: 0.000046 grad: 0.1057 (0.1027) loss: 0.8186 (0.8184) time: 0.1404 data: 0.0574 max mem: 9390 +Train: [60] [5200/6250] eta: 0:02:53 lr: 0.000045 grad: 0.1020 (0.1028) loss: 0.8138 (0.8184) time: 0.1723 data: 0.0869 max mem: 9390 +Train: [60] [5300/6250] eta: 0:02:37 lr: 0.000045 grad: 0.0974 (0.1028) loss: 0.8171 (0.8183) time: 0.1756 data: 0.0970 max mem: 9390 +Train: [60] [5400/6250] eta: 0:02:20 lr: 0.000045 grad: 0.1006 (0.1028) loss: 0.8077 (0.8183) time: 0.1567 data: 0.0787 max mem: 9390 +Train: [60] [5500/6250] eta: 0:02:03 lr: 0.000045 grad: 0.1019 (0.1029) loss: 0.8158 (0.8183) time: 0.1273 data: 0.0337 max mem: 9390 +Train: [60] [5600/6250] eta: 0:01:47 lr: 0.000045 grad: 0.1028 (0.1030) loss: 0.8167 (0.8183) time: 0.1996 data: 0.1035 max mem: 9390 +Train: [60] [5700/6250] eta: 0:01:30 lr: 0.000045 grad: 0.1098 (0.1030) loss: 0.8152 (0.8182) time: 0.1462 data: 0.0566 max mem: 9390 +Train: [60] [5800/6250] eta: 0:01:13 lr: 0.000045 grad: 0.1063 (0.1031) loss: 0.8082 (0.8181) time: 0.1929 data: 0.1129 max mem: 9390 +Train: [60] [5900/6250] eta: 0:00:57 lr: 0.000045 grad: 0.1031 (0.1032) loss: 0.8194 (0.8181) time: 0.1477 data: 0.0619 max mem: 9390 +Train: [60] [6000/6250] eta: 0:00:41 lr: 0.000045 grad: 0.1035 (0.1032) loss: 0.8088 (0.8180) time: 0.1745 data: 0.0908 max mem: 9390 +Train: [60] [6100/6250] eta: 0:00:24 lr: 0.000045 grad: 0.0986 (0.1033) loss: 0.8123 (0.8180) time: 0.2058 data: 0.1278 max mem: 9390 +Train: [60] [6200/6250] eta: 0:00:08 lr: 0.000045 grad: 0.1088 (0.1033) loss: 0.8162 (0.8179) time: 0.1951 data: 0.1102 max mem: 9390 +Train: [60] [6249/6250] eta: 0:00:00 lr: 0.000045 grad: 0.1071 (0.1033) loss: 0.8059 (0.8179) time: 0.1484 data: 0.0588 max mem: 9390 +Train: [60] Total time: 0:17:11 (0.1651 s / it) +Averaged stats: lr: 0.000045 grad: 0.1071 (0.1033) loss: 0.8059 (0.8179) +Eval (hcp-train-subset): [60] [ 0/62] eta: 0:04:49 loss: 0.8436 (0.8436) time: 4.6639 data: 4.6326 max mem: 9390 +Eval (hcp-train-subset): [60] [61/62] eta: 0:00:00 loss: 0.8322 (0.8344) time: 0.1357 data: 0.1103 max mem: 9390 +Eval (hcp-train-subset): [60] Total time: 0:00:13 (0.2143 s / it) +Averaged stats (hcp-train-subset): loss: 0.8322 (0.8344) +Eval (hcp-val): [60] [ 0/62] eta: 0:05:28 loss: 0.8309 (0.8309) time: 5.2991 data: 5.2689 max mem: 9390 +Eval (hcp-val): [60] [61/62] eta: 0:00:00 loss: 0.8334 (0.8346) time: 0.1094 data: 0.0830 max mem: 9390 +Eval (hcp-val): [60] Total time: 0:00:13 (0.2112 s / it) +Averaged stats (hcp-val): loss: 0.8334 (0.8346) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +Train: [61] [ 0/6250] eta: 7:35:24 lr: 0.000045 grad: nan (nan) loss: 0.7931 (0.7931) time: 4.3718 data: 4.1185 max mem: 9390 +Train: [61] [ 100/6250] eta: 0:21:57 lr: 0.000045 grad: 0.0843 (0.1053) loss: 0.8348 (0.8356) time: 0.1866 data: 0.0941 max mem: 9390 +Train: [61] [ 200/6250] eta: 0:18:47 lr: 0.000045 grad: 0.0889 (0.1005) loss: 0.8290 (0.8307) time: 0.1507 data: 0.0601 max mem: 9390 +Train: [61] [ 300/6250] eta: 0:17:36 lr: 0.000045 grad: 0.0921 (0.0994) loss: 0.8230 (0.8283) time: 0.1577 data: 0.0702 max mem: 9390 +Train: [61] [ 400/6250] eta: 0:16:31 lr: 0.000045 grad: 0.0979 (0.0992) loss: 0.8196 (0.8265) time: 0.1280 data: 0.0245 max mem: 9390 +Train: [61] [ 500/6250] eta: 0:15:52 lr: 0.000045 grad: 0.0984 (0.0988) loss: 0.8158 (0.8252) time: 0.1469 data: 0.0521 max mem: 9390 +Train: [61] [ 600/6250] eta: 0:15:27 lr: 0.000045 grad: 0.0985 (0.0993) loss: 0.8153 (0.8239) time: 0.1728 data: 0.0847 max mem: 9390 +Train: [61] [ 700/6250] eta: 0:15:22 lr: 0.000045 grad: 0.0954 (0.0996) loss: 0.8219 (0.8230) time: 0.2067 data: 0.1209 max mem: 9390 +Train: [61] [ 800/6250] eta: 0:15:15 lr: 0.000045 grad: 0.0922 (0.0992) loss: 0.8235 (0.8229) time: 0.1708 data: 0.0875 max mem: 9390 +Train: [61] [ 900/6250] eta: 0:15:28 lr: 0.000045 grad: 0.0978 (0.0990) loss: 0.8205 (0.8230) time: 0.2918 data: 0.2084 max mem: 9390 +Train: [61] [1000/6250] eta: 0:15:00 lr: 0.000045 grad: 0.0963 (0.0992) loss: 0.8213 (0.8228) time: 0.1609 data: 0.0594 max mem: 9390 +Train: [61] [1100/6250] eta: 0:14:43 lr: 0.000045 grad: 0.0924 (0.0992) loss: 0.8219 (0.8227) time: 0.1608 data: 0.0803 max mem: 9390 +Train: [61] [1200/6250] eta: 0:14:26 lr: 0.000045 grad: 0.0976 (0.0991) loss: 0.8204 (0.8226) time: 0.1655 data: 0.0804 max mem: 9390 +Train: [61] [1300/6250] eta: 0:14:01 lr: 0.000045 grad: 0.0952 (0.0992) loss: 0.8166 (0.8224) time: 0.1477 data: 0.0609 max mem: 9390 +Train: [61] [1400/6250] eta: 0:13:46 lr: 0.000045 grad: 0.0952 (0.0992) loss: 0.8198 (0.8221) time: 0.1648 data: 0.0726 max mem: 9390 +Train: [61] [1500/6250] eta: 0:13:28 lr: 0.000045 grad: 0.0964 (0.0995) loss: 0.8211 (0.8219) time: 0.1533 data: 0.0645 max mem: 9390 +Train: [61] [1600/6250] eta: 0:13:19 lr: 0.000045 grad: 0.1033 (0.0997) loss: 0.8130 (0.8216) time: 0.2810 data: 0.1842 max mem: 9390 +Train: [61] [1700/6250] eta: 0:13:00 lr: 0.000045 grad: 0.1024 (0.0999) loss: 0.8216 (0.8213) time: 0.2293 data: 0.1335 max mem: 9390 +Train: [61] [1800/6250] eta: 0:12:38 lr: 0.000045 grad: 0.1019 (0.1003) loss: 0.8177 (0.8211) time: 0.1553 data: 0.0649 max mem: 9390 +Train: [61] [1900/6250] eta: 0:12:19 lr: 0.000045 grad: 0.1105 (0.1005) loss: 0.8146 (0.8208) time: 0.1405 data: 0.0541 max mem: 9390 +Train: [61] [2000/6250] eta: 0:12:01 lr: 0.000045 grad: 0.0992 (0.1008) loss: 0.8152 (0.8205) time: 0.2159 data: 0.1370 max mem: 9390 +Train: [61] [2100/6250] eta: 0:11:41 lr: 0.000044 grad: 0.1024 (0.1010) loss: 0.8153 (0.8203) time: 0.1716 data: 0.0856 max mem: 9390 +Train: [61] [2200/6250] eta: 0:11:21 lr: 0.000044 grad: 0.1031 (0.1010) loss: 0.8145 (0.8202) time: 0.1503 data: 0.0740 max mem: 9390 +Train: [61] [2300/6250] eta: 0:11:06 lr: 0.000044 grad: 0.0982 (0.1010) loss: 0.8201 (0.8201) time: 0.2338 data: 0.1567 max mem: 9390 +Train: [61] [2400/6250] eta: 0:10:45 lr: 0.000044 grad: 0.0986 (0.1012) loss: 0.8180 (0.8199) time: 0.1463 data: 0.0655 max mem: 9390 +Train: [61] [2500/6250] eta: 0:10:26 lr: 0.000044 grad: 0.1008 (0.1013) loss: 0.8162 (0.8199) time: 0.1568 data: 0.0741 max mem: 9390 +Train: [61] [2600/6250] eta: 0:10:09 lr: 0.000044 grad: 0.0942 (0.1013) loss: 0.8253 (0.8199) time: 0.1282 data: 0.0365 max mem: 9390 +Train: [61] [2700/6250] eta: 0:09:51 lr: 0.000044 grad: 0.0997 (0.1013) loss: 0.8159 (0.8199) time: 0.1524 data: 0.0697 max mem: 9390 +Train: [61] [2800/6250] eta: 0:09:36 lr: 0.000044 grad: 0.1042 (0.1014) loss: 0.8121 (0.8197) time: 0.1939 data: 0.1160 max mem: 9390 +Train: [61] [2900/6250] eta: 0:09:18 lr: 0.000044 grad: 0.1030 (0.1015) loss: 0.8147 (0.8195) time: 0.1934 data: 0.1124 max mem: 9390 +Train: [61] [3000/6250] eta: 0:09:00 lr: 0.000044 grad: 0.1008 (0.1016) loss: 0.8177 (0.8194) time: 0.1777 data: 0.0965 max mem: 9390 +Train: [61] [3100/6250] eta: 0:08:42 lr: 0.000044 grad: 0.0971 (0.1016) loss: 0.8199 (0.8193) time: 0.1670 data: 0.0815 max mem: 9390 +Train: [61] [3200/6250] eta: 0:08:25 lr: 0.000044 grad: 0.1024 (0.1017) loss: 0.8121 (0.8192) time: 0.1493 data: 0.0614 max mem: 9390 +Train: [61] [3300/6250] eta: 0:08:08 lr: 0.000044 grad: 0.1001 (0.1017) loss: 0.8158 (0.8191) time: 0.1801 data: 0.0928 max mem: 9390 +Train: [61] [3400/6250] eta: 0:07:50 lr: 0.000044 grad: 0.1017 (0.1018) loss: 0.8169 (0.8191) time: 0.1557 data: 0.0796 max mem: 9390 +Train: [61] [3500/6250] eta: 0:07:33 lr: 0.000044 grad: 0.1010 (0.1019) loss: 0.8195 (0.8191) time: 0.1587 data: 0.0833 max mem: 9390 +Train: [61] [3600/6250] eta: 0:07:16 lr: 0.000044 grad: 0.0960 (0.1019) loss: 0.8189 (0.8191) time: 0.1837 data: 0.0995 max mem: 9390 +Train: [61] [3700/6250] eta: 0:07:00 lr: 0.000044 grad: 0.0923 (0.1020) loss: 0.8171 (0.8191) time: 0.2219 data: 0.1420 max mem: 9390 +Train: [61] [3800/6250] eta: 0:06:44 lr: 0.000044 grad: 0.1026 (0.1020) loss: 0.8134 (0.8190) time: 0.2674 data: 0.1883 max mem: 9390 +Train: [61] [3900/6250] eta: 0:06:27 lr: 0.000044 grad: 0.0984 (0.1020) loss: 0.8191 (0.8190) time: 0.2062 data: 0.1235 max mem: 9390 +Train: [61] [4000/6250] eta: 0:06:09 lr: 0.000044 grad: 0.0959 (0.1020) loss: 0.8201 (0.8190) time: 0.1841 data: 0.1019 max mem: 9390 +Train: [61] [4100/6250] eta: 0:05:52 lr: 0.000044 grad: 0.1003 (0.1020) loss: 0.8190 (0.8189) time: 0.1530 data: 0.0640 max mem: 9390 +Train: [61] [4200/6250] eta: 0:05:36 lr: 0.000044 grad: 0.0909 (0.1020) loss: 0.8241 (0.8189) time: 0.1825 data: 0.1006 max mem: 9390 +Train: [61] [4300/6250] eta: 0:05:19 lr: 0.000044 grad: 0.0982 (0.1020) loss: 0.8212 (0.8189) time: 0.1485 data: 0.0660 max mem: 9390 +Train: [61] [4400/6250] eta: 0:05:02 lr: 0.000044 grad: 0.0986 (0.1020) loss: 0.8159 (0.8189) time: 0.1476 data: 0.0678 max mem: 9390 +Train: [61] [4500/6250] eta: 0:04:46 lr: 0.000044 grad: 0.0964 (0.1021) loss: 0.8192 (0.8189) time: 0.2082 data: 0.1205 max mem: 9390 +Train: [61] [4600/6250] eta: 0:04:29 lr: 0.000044 grad: 0.1092 (0.1021) loss: 0.8157 (0.8189) time: 0.1574 data: 0.0769 max mem: 9390 +Train: [61] [4700/6250] eta: 0:04:14 lr: 0.000044 grad: 0.0983 (0.1021) loss: 0.8203 (0.8189) time: 0.2422 data: 0.1514 max mem: 9390 +Train: [61] [4800/6250] eta: 0:03:57 lr: 0.000044 grad: 0.1127 (0.1022) loss: 0.8186 (0.8189) time: 0.1595 data: 0.0689 max mem: 9390 +Train: [61] [4900/6250] eta: 0:03:40 lr: 0.000044 grad: 0.1024 (0.1023) loss: 0.8134 (0.8189) time: 0.1647 data: 0.0876 max mem: 9390 +Train: [61] [5000/6250] eta: 0:03:24 lr: 0.000044 grad: 0.1040 (0.1024) loss: 0.8119 (0.8188) time: 0.1456 data: 0.0642 max mem: 9390 +Train: [61] [5100/6250] eta: 0:03:08 lr: 0.000044 grad: 0.1035 (0.1024) loss: 0.8108 (0.8187) time: 0.1157 data: 0.0261 max mem: 9390 +Train: [61] [5200/6250] eta: 0:02:51 lr: 0.000044 grad: 0.1045 (0.1025) loss: 0.8141 (0.8186) time: 0.1669 data: 0.0738 max mem: 9390 +Train: [61] [5300/6250] eta: 0:02:35 lr: 0.000043 grad: 0.1024 (0.1025) loss: 0.8168 (0.8186) time: 0.1699 data: 0.0776 max mem: 9390 +Train: [61] [5400/6250] eta: 0:02:19 lr: 0.000043 grad: 0.0993 (0.1025) loss: 0.8088 (0.8185) time: 0.1143 data: 0.0290 max mem: 9390 +Train: [61] [5500/6250] eta: 0:02:02 lr: 0.000043 grad: 0.0929 (0.1025) loss: 0.8134 (0.8185) time: 0.1576 data: 0.0754 max mem: 9390 +Train: [61] [5600/6250] eta: 0:01:46 lr: 0.000043 grad: 0.1045 (0.1026) loss: 0.8167 (0.8184) time: 0.2345 data: 0.1409 max mem: 9390 +Train: [61] [5700/6250] eta: 0:01:30 lr: 0.000043 grad: 0.1052 (0.1026) loss: 0.8139 (0.8184) time: 0.1686 data: 0.0946 max mem: 9390 +Train: [61] [5800/6250] eta: 0:01:13 lr: 0.000043 grad: 0.1019 (0.1026) loss: 0.8187 (0.8183) time: 0.1525 data: 0.0651 max mem: 9390 +Train: [61] [5900/6250] eta: 0:00:57 lr: 0.000043 grad: 0.0991 (0.1026) loss: 0.8168 (0.8183) time: 0.1553 data: 0.0750 max mem: 9390 +Train: [61] [6000/6250] eta: 0:00:40 lr: 0.000043 grad: 0.0991 (0.1026) loss: 0.8224 (0.8183) time: 0.1356 data: 0.0486 max mem: 9390 +Train: [61] [6100/6250] eta: 0:00:24 lr: 0.000043 grad: 0.0996 (0.1026) loss: 0.8169 (0.8183) time: 0.1586 data: 0.0756 max mem: 9390 +Train: [61] [6200/6250] eta: 0:00:08 lr: 0.000043 grad: 0.1018 (0.1027) loss: 0.8101 (0.8183) time: 0.1865 data: 0.0993 max mem: 9390 +Train: [61] [6249/6250] eta: 0:00:00 lr: 0.000043 grad: 0.1020 (0.1027) loss: 0.8142 (0.8183) time: 0.2035 data: 0.1101 max mem: 9390 +Train: [61] Total time: 0:17:12 (0.1651 s / it) +Averaged stats: lr: 0.000043 grad: 0.1020 (0.1027) loss: 0.8142 (0.8183) +Eval (hcp-train-subset): [61] [ 0/62] eta: 0:05:06 loss: 0.8446 (0.8446) time: 4.9372 data: 4.9050 max mem: 9390 +Eval (hcp-train-subset): [61] [61/62] eta: 0:00:00 loss: 0.8322 (0.8332) time: 0.1332 data: 0.1083 max mem: 9390 +Eval (hcp-train-subset): [61] Total time: 0:00:13 (0.2162 s / it) +Averaged stats (hcp-train-subset): loss: 0.8322 (0.8332) +Eval (hcp-val): [61] [ 0/62] eta: 0:04:46 loss: 0.8341 (0.8341) time: 4.6151 data: 4.5767 max mem: 9390 +Eval (hcp-val): [61] [61/62] eta: 0:00:00 loss: 0.8337 (0.8342) time: 0.1225 data: 0.0959 max mem: 9390 +Eval (hcp-val): [61] Total time: 0:00:13 (0.2113 s / it) +Averaged stats (hcp-val): loss: 0.8337 (0.8342) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +Train: [62] [ 0/6250] eta: 10:27:21 lr: 0.000043 grad: 0.1237 (0.1237) loss: 0.8898 (0.8898) time: 6.0226 data: 5.9191 max mem: 9390 +Train: [62] [ 100/6250] eta: 0:21:44 lr: 0.000043 grad: 0.1130 (0.1321) loss: 0.8225 (0.8221) time: 0.1532 data: 0.0700 max mem: 9390 +Train: [62] [ 200/6250] eta: 0:19:11 lr: 0.000043 grad: 0.0911 (0.1159) loss: 0.8263 (0.8248) time: 0.1492 data: 0.0637 max mem: 9390 +Train: [62] [ 300/6250] eta: 0:18:10 lr: 0.000043 grad: 0.1004 (0.1111) loss: 0.8180 (0.8244) time: 0.1768 data: 0.0868 max mem: 9390 +Train: [62] [ 400/6250] eta: 0:17:23 lr: 0.000043 grad: 0.0991 (0.1102) loss: 0.8244 (0.8232) time: 0.1855 data: 0.0868 max mem: 9390 +Train: [62] [ 500/6250] eta: 0:16:47 lr: 0.000043 grad: 0.1151 (0.1117) loss: 0.8186 (0.8221) time: 0.1714 data: 0.0828 max mem: 9390 +Train: [62] [ 600/6250] eta: 0:16:19 lr: 0.000043 grad: 0.1010 (0.1102) loss: 0.8172 (0.8211) time: 0.1400 data: 0.0542 max mem: 9390 +Train: [62] [ 700/6250] eta: 0:16:04 lr: 0.000043 grad: 0.1020 (0.1088) loss: 0.8149 (0.8205) time: 0.1443 data: 0.0537 max mem: 9390 +Train: [62] [ 800/6250] eta: 0:15:55 lr: 0.000043 grad: 0.0962 (0.1076) loss: 0.8189 (0.8203) time: 0.1782 data: 0.0685 max mem: 9390 +Train: [62] [ 900/6250] eta: 0:16:17 lr: 0.000043 grad: 0.1009 (0.1070) loss: 0.8157 (0.8203) time: 0.4023 data: 0.3206 max mem: 9390 +Train: [62] [1000/6250] eta: 0:15:51 lr: 0.000043 grad: 0.0983 (0.1064) loss: 0.8211 (0.8202) time: 0.1744 data: 0.0867 max mem: 9390 +Train: [62] [1100/6250] eta: 0:15:20 lr: 0.000043 grad: 0.0972 (0.1058) loss: 0.8252 (0.8201) time: 0.1490 data: 0.0696 max mem: 9390 +Train: [62] [1200/6250] eta: 0:14:54 lr: 0.000043 grad: 0.0961 (0.1052) loss: 0.8224 (0.8201) time: 0.1659 data: 0.0840 max mem: 9390 +Train: [62] [1300/6250] eta: 0:14:29 lr: 0.000043 grad: 0.0986 (0.1052) loss: 0.8160 (0.8198) time: 0.1791 data: 0.0966 max mem: 9390 +Train: [62] [1400/6250] eta: 0:14:07 lr: 0.000043 grad: 0.1015 (0.1051) loss: 0.8089 (0.8196) time: 0.1616 data: 0.0762 max mem: 9390 +Train: [62] [1500/6250] eta: 0:13:43 lr: 0.000043 grad: 0.1008 (0.1049) loss: 0.8119 (0.8194) time: 0.1646 data: 0.0733 max mem: 9390 +Train: [62] [1600/6250] eta: 0:13:19 lr: 0.000043 grad: 0.1001 (0.1049) loss: 0.8213 (0.8193) time: 0.1557 data: 0.0645 max mem: 9390 +Train: [62] [1700/6250] eta: 0:13:04 lr: 0.000043 grad: 0.1027 (0.1048) loss: 0.8157 (0.8190) time: 0.2058 data: 0.1056 max mem: 9390 +Train: [62] [1800/6250] eta: 0:12:44 lr: 0.000043 grad: 0.1014 (0.1048) loss: 0.8231 (0.8188) time: 0.1447 data: 0.0488 max mem: 9390 +Train: [62] [1900/6250] eta: 0:12:22 lr: 0.000043 grad: 0.1057 (0.1048) loss: 0.8138 (0.8186) time: 0.1398 data: 0.0586 max mem: 9390 +Train: [62] [2000/6250] eta: 0:12:02 lr: 0.000043 grad: 0.1005 (0.1049) loss: 0.8217 (0.8185) time: 0.1305 data: 0.0443 max mem: 9390 +Train: [62] [2100/6250] eta: 0:11:51 lr: 0.000043 grad: 0.0976 (0.1048) loss: 0.8144 (0.8184) time: 0.1779 data: 0.0925 max mem: 9390 +Train: [62] [2200/6250] eta: 0:11:34 lr: 0.000042 grad: 0.0982 (0.1048) loss: 0.8207 (0.8184) time: 0.1679 data: 0.0875 max mem: 9390 +Train: [62] [2300/6250] eta: 0:11:20 lr: 0.000042 grad: 0.0995 (0.1047) loss: 0.8145 (0.8183) time: 0.1836 data: 0.1006 max mem: 9390 +Train: [62] [2400/6250] eta: 0:11:02 lr: 0.000042 grad: 0.1009 (0.1048) loss: 0.8153 (0.8182) time: 0.1861 data: 0.0995 max mem: 9390 +Train: [62] [2500/6250] eta: 0:10:50 lr: 0.000042 grad: 0.0980 (0.1047) loss: 0.8176 (0.8181) time: 0.2081 data: 0.1200 max mem: 9390 +Train: [62] [2600/6250] eta: 0:10:33 lr: 0.000042 grad: 0.1050 (0.1046) loss: 0.8119 (0.8180) time: 0.1564 data: 0.0702 max mem: 9390 +Train: [62] [2700/6250] eta: 0:10:15 lr: 0.000042 grad: 0.1034 (0.1046) loss: 0.8157 (0.8179) time: 0.1620 data: 0.0667 max mem: 9390 +Train: [62] [2800/6250] eta: 0:09:55 lr: 0.000042 grad: 0.1025 (0.1046) loss: 0.8069 (0.8177) time: 0.1650 data: 0.0716 max mem: 9390 +Train: [62] [2900/6250] eta: 0:09:36 lr: 0.000042 grad: 0.0983 (0.1045) loss: 0.8135 (0.8176) time: 0.1607 data: 0.0748 max mem: 9390 +Train: [62] [3000/6250] eta: 0:09:17 lr: 0.000042 grad: 0.1031 (0.1045) loss: 0.8122 (0.8174) time: 0.1784 data: 0.0855 max mem: 9390 +Train: [62] [3100/6250] eta: 0:08:58 lr: 0.000042 grad: 0.1009 (0.1044) loss: 0.8155 (0.8173) time: 0.1335 data: 0.0463 max mem: 9390 +Train: [62] [3200/6250] eta: 0:08:40 lr: 0.000042 grad: 0.0982 (0.1043) loss: 0.8131 (0.8172) time: 0.1637 data: 0.0731 max mem: 9390 +Train: [62] [3300/6250] eta: 0:08:21 lr: 0.000042 grad: 0.0998 (0.1043) loss: 0.8198 (0.8172) time: 0.1558 data: 0.0681 max mem: 9390 +Train: [62] [3400/6250] eta: 0:08:04 lr: 0.000042 grad: 0.1061 (0.1044) loss: 0.8170 (0.8172) time: 0.1621 data: 0.0790 max mem: 9390 +Train: [62] [3500/6250] eta: 0:07:45 lr: 0.000042 grad: 0.1013 (0.1044) loss: 0.8185 (0.8171) time: 0.1668 data: 0.0776 max mem: 9390 +Train: [62] [3600/6250] eta: 0:07:29 lr: 0.000042 grad: 0.0936 (0.1043) loss: 0.8176 (0.8172) time: 0.2556 data: 0.1703 max mem: 9390 +Train: [62] [3700/6250] eta: 0:07:11 lr: 0.000042 grad: 0.0947 (0.1043) loss: 0.8188 (0.8171) time: 0.2295 data: 0.1437 max mem: 9390 +Train: [62] [3800/6250] eta: 0:06:53 lr: 0.000042 grad: 0.1022 (0.1043) loss: 0.8163 (0.8170) time: 0.1900 data: 0.0984 max mem: 9390 +Train: [62] [3900/6250] eta: 0:06:36 lr: 0.000042 grad: 0.1058 (0.1044) loss: 0.8166 (0.8170) time: 0.1264 data: 0.0295 max mem: 9390 +Train: [62] [4000/6250] eta: 0:06:19 lr: 0.000042 grad: 0.1051 (0.1044) loss: 0.8157 (0.8170) time: 0.1056 data: 0.0204 max mem: 9390 +Train: [62] [4100/6250] eta: 0:06:02 lr: 0.000042 grad: 0.1104 (0.1045) loss: 0.8213 (0.8170) time: 0.1558 data: 0.0696 max mem: 9390 +Train: [62] [4200/6250] eta: 0:05:44 lr: 0.000042 grad: 0.0995 (0.1045) loss: 0.8217 (0.8169) time: 0.1445 data: 0.0569 max mem: 9390 +Train: [62] [4300/6250] eta: 0:05:27 lr: 0.000042 grad: 0.0996 (0.1046) loss: 0.8176 (0.8169) time: 0.1579 data: 0.0656 max mem: 9390 +Train: [62] [4400/6250] eta: 0:05:09 lr: 0.000042 grad: 0.1061 (0.1046) loss: 0.8169 (0.8169) time: 0.1484 data: 0.0631 max mem: 9390 +Train: [62] [4500/6250] eta: 0:04:53 lr: 0.000042 grad: 0.1064 (0.1047) loss: 0.8157 (0.8169) time: 0.2463 data: 0.1479 max mem: 9390 +Train: [62] [4600/6250] eta: 0:04:36 lr: 0.000042 grad: 0.1057 (0.1047) loss: 0.8158 (0.8169) time: 0.1302 data: 0.0489 max mem: 9390 +Train: [62] [4700/6250] eta: 0:04:19 lr: 0.000042 grad: 0.1054 (0.1048) loss: 0.8161 (0.8169) time: 0.1727 data: 0.0887 max mem: 9390 +Train: [62] [4800/6250] eta: 0:04:02 lr: 0.000042 grad: 0.1054 (0.1049) loss: 0.8189 (0.8169) time: 0.1657 data: 0.0769 max mem: 9390 +Train: [62] [4900/6250] eta: 0:03:45 lr: 0.000042 grad: 0.1026 (0.1049) loss: 0.8254 (0.8168) time: 0.1660 data: 0.0808 max mem: 9390 +Train: [62] [5000/6250] eta: 0:03:28 lr: 0.000042 grad: 0.1017 (0.1050) loss: 0.8196 (0.8168) time: 0.1689 data: 0.0915 max mem: 9390 +Train: [62] [5100/6250] eta: 0:03:11 lr: 0.000042 grad: 0.1049 (0.1051) loss: 0.8111 (0.8167) time: 0.1597 data: 0.0801 max mem: 9390 +Train: [62] [5200/6250] eta: 0:02:54 lr: 0.000042 grad: 0.1006 (0.1051) loss: 0.8186 (0.8167) time: 0.1525 data: 0.0615 max mem: 9390 +Train: [62] [5300/6250] eta: 0:02:37 lr: 0.000042 grad: 0.1050 (0.1052) loss: 0.8084 (0.8166) time: 0.1587 data: 0.0751 max mem: 9390 +Train: [62] [5400/6250] eta: 0:02:21 lr: 0.000041 grad: 0.0974 (0.1052) loss: 0.8165 (0.8166) time: 0.1589 data: 0.0722 max mem: 9390 +Train: [62] [5500/6250] eta: 0:02:04 lr: 0.000041 grad: 0.1002 (0.1052) loss: 0.8110 (0.8166) time: 0.1705 data: 0.0861 max mem: 9390 +Train: [62] [5600/6250] eta: 0:01:47 lr: 0.000041 grad: 0.1046 (0.1052) loss: 0.8178 (0.8166) time: 0.1725 data: 0.0838 max mem: 9390 +Train: [62] [5700/6250] eta: 0:01:31 lr: 0.000041 grad: 0.1011 (0.1052) loss: 0.8194 (0.8165) time: 0.1540 data: 0.0690 max mem: 9390 +Train: [62] [5800/6250] eta: 0:01:14 lr: 0.000041 grad: 0.1013 (0.1053) loss: 0.8113 (0.8164) time: 0.1355 data: 0.0509 max mem: 9390 +Train: [62] [5900/6250] eta: 0:00:57 lr: 0.000041 grad: 0.1019 (0.1053) loss: 0.8089 (0.8164) time: 0.1101 data: 0.0280 max mem: 9390 +Train: [62] [6000/6250] eta: 0:00:41 lr: 0.000041 grad: 0.1015 (0.1053) loss: 0.8189 (0.8164) time: 0.1499 data: 0.0622 max mem: 9390 +Train: [62] [6100/6250] eta: 0:00:24 lr: 0.000041 grad: 0.1095 (0.1054) loss: 0.8130 (0.8163) time: 0.1731 data: 0.0894 max mem: 9390 +Train: [62] [6200/6250] eta: 0:00:08 lr: 0.000041 grad: 0.1003 (0.1053) loss: 0.8177 (0.8163) time: 0.1732 data: 0.0917 max mem: 9390 +Train: [62] [6249/6250] eta: 0:00:00 lr: 0.000041 grad: 0.1069 (0.1054) loss: 0.8111 (0.8163) time: 0.1658 data: 0.0854 max mem: 9390 +Train: [62] Total time: 0:17:16 (0.1658 s / it) +Averaged stats: lr: 0.000041 grad: 0.1069 (0.1054) loss: 0.8111 (0.8163) +Eval (hcp-train-subset): [62] [ 0/62] eta: 0:04:57 loss: 0.8460 (0.8460) time: 4.8049 data: 4.7755 max mem: 9390 +Eval (hcp-train-subset): [62] [61/62] eta: 0:00:00 loss: 0.8312 (0.8318) time: 0.1331 data: 0.1083 max mem: 9390 +Eval (hcp-train-subset): [62] Total time: 0:00:13 (0.2122 s / it) +Averaged stats (hcp-train-subset): loss: 0.8312 (0.8318) +Eval (hcp-val): [62] [ 0/62] eta: 0:03:19 loss: 0.8263 (0.8263) time: 3.2153 data: 3.1688 max mem: 9390 +Eval (hcp-val): [62] [61/62] eta: 0:00:00 loss: 0.8316 (0.8332) time: 0.1213 data: 0.0946 max mem: 9390 +Eval (hcp-val): [62] Total time: 0:00:13 (0.2118 s / it) +Averaged stats (hcp-val): loss: 0.8316 (0.8332) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +Train: [63] [ 0/6250] eta: 6:59:40 lr: 0.000041 grad: 0.0721 (0.0721) loss: 0.8463 (0.8463) time: 4.0288 data: 3.8189 max mem: 9390 +Train: [63] [ 100/6250] eta: 0:22:21 lr: 0.000041 grad: 0.1098 (0.1281) loss: 0.8329 (0.8292) time: 0.1800 data: 0.0903 max mem: 9390 +Train: [63] [ 200/6250] eta: 0:19:49 lr: 0.000041 grad: 0.1014 (0.1169) loss: 0.8161 (0.8271) time: 0.1929 data: 0.1036 max mem: 9390 +Train: [63] [ 300/6250] eta: 0:18:22 lr: 0.000041 grad: 0.0972 (0.1140) loss: 0.8208 (0.8250) time: 0.1599 data: 0.0662 max mem: 9390 +Train: [63] [ 400/6250] eta: 0:17:35 lr: 0.000041 grad: 0.0993 (0.1130) loss: 0.8115 (0.8226) time: 0.1789 data: 0.0885 max mem: 9390 +Train: [63] [ 500/6250] eta: 0:16:50 lr: 0.000041 grad: 0.0974 (0.1125) loss: 0.8161 (0.8210) time: 0.1436 data: 0.0474 max mem: 9390 +Train: [63] [ 600/6250] eta: 0:16:19 lr: 0.000041 grad: 0.1035 (0.1119) loss: 0.8090 (0.8198) time: 0.1930 data: 0.1090 max mem: 9390 +Train: [63] [ 700/6250] eta: 0:15:57 lr: 0.000041 grad: 0.0985 (0.1111) loss: 0.8166 (0.8193) time: 0.1619 data: 0.0685 max mem: 9390 +Train: [63] [ 800/6250] eta: 0:15:35 lr: 0.000041 grad: 0.0957 (0.1099) loss: 0.8185 (0.8192) time: 0.1636 data: 0.0723 max mem: 9390 +Train: [63] [ 900/6250] eta: 0:15:17 lr: 0.000041 grad: 0.0981 (0.1088) loss: 0.8184 (0.8192) time: 0.1109 data: 0.0239 max mem: 9390 +Train: [63] [1000/6250] eta: 0:15:06 lr: 0.000041 grad: 0.0991 (0.1077) loss: 0.8199 (0.8195) time: 0.1376 data: 0.0433 max mem: 9390 +Train: [63] [1100/6250] eta: 0:14:41 lr: 0.000041 grad: 0.0969 (0.1069) loss: 0.8179 (0.8198) time: 0.1623 data: 0.0789 max mem: 9390 +Train: [63] [1200/6250] eta: 0:14:28 lr: 0.000041 grad: 0.1024 (0.1065) loss: 0.8183 (0.8197) time: 0.1965 data: 0.1156 max mem: 9390 +Train: [63] [1300/6250] eta: 0:14:05 lr: 0.000041 grad: 0.0993 (0.1065) loss: 0.8099 (0.8194) time: 0.1515 data: 0.0716 max mem: 9390 +Train: [63] [1400/6250] eta: 0:13:46 lr: 0.000041 grad: 0.1125 (0.1064) loss: 0.8108 (0.8191) time: 0.1966 data: 0.1127 max mem: 9390 +Train: [63] [1500/6250] eta: 0:13:28 lr: 0.000041 grad: 0.0970 (0.1064) loss: 0.8187 (0.8188) time: 0.1683 data: 0.0902 max mem: 9390 +Train: [63] [1600/6250] eta: 0:13:05 lr: 0.000041 grad: 0.1034 (0.1061) loss: 0.8147 (0.8186) time: 0.1762 data: 0.0923 max mem: 9390 +Train: [63] [1700/6250] eta: 0:12:46 lr: 0.000041 grad: 0.1026 (0.1061) loss: 0.8153 (0.8184) time: 0.1485 data: 0.0705 max mem: 9390 +Train: [63] [1800/6250] eta: 0:12:26 lr: 0.000041 grad: 0.1060 (0.1061) loss: 0.8091 (0.8181) time: 0.1539 data: 0.0721 max mem: 9390 +Train: [63] [1900/6250] eta: 0:12:07 lr: 0.000041 grad: 0.0986 (0.1061) loss: 0.8158 (0.8178) time: 0.1552 data: 0.0755 max mem: 9390 +Train: [63] [2000/6250] eta: 0:11:47 lr: 0.000041 grad: 0.1076 (0.1060) loss: 0.8153 (0.8176) time: 0.1513 data: 0.0668 max mem: 9390 +Train: [63] [2100/6250] eta: 0:11:29 lr: 0.000041 grad: 0.1011 (0.1061) loss: 0.8131 (0.8174) time: 0.1545 data: 0.0764 max mem: 9390 +Train: [63] [2200/6250] eta: 0:11:15 lr: 0.000041 grad: 0.1059 (0.1062) loss: 0.8105 (0.8172) time: 0.1717 data: 0.0926 max mem: 9390 +Train: [63] [2300/6250] eta: 0:10:58 lr: 0.000041 grad: 0.1040 (0.1062) loss: 0.8133 (0.8171) time: 0.1771 data: 0.0828 max mem: 9390 +Train: [63] [2400/6250] eta: 0:10:43 lr: 0.000040 grad: 0.1015 (0.1061) loss: 0.8156 (0.8170) time: 0.1926 data: 0.1039 max mem: 9390 +Train: [63] [2500/6250] eta: 0:10:25 lr: 0.000040 grad: 0.1029 (0.1059) loss: 0.8172 (0.8170) time: 0.1296 data: 0.0487 max mem: 9390 +Train: [63] [2600/6250] eta: 0:10:09 lr: 0.000040 grad: 0.1058 (0.1059) loss: 0.8209 (0.8170) time: 0.1089 data: 0.0196 max mem: 9390 +Train: [63] [2700/6250] eta: 0:09:57 lr: 0.000040 grad: 0.1002 (0.1059) loss: 0.8176 (0.8170) time: 0.3793 data: 0.2759 max mem: 9390 +Train: [63] [2800/6250] eta: 0:09:36 lr: 0.000040 grad: 0.1024 (0.1059) loss: 0.8181 (0.8170) time: 0.1466 data: 0.0495 max mem: 9390 +Train: [63] [2900/6250] eta: 0:09:18 lr: 0.000040 grad: 0.1012 (0.1060) loss: 0.8182 (0.8170) time: 0.1628 data: 0.0835 max mem: 9390 +Train: [63] [3000/6250] eta: 0:09:01 lr: 0.000040 grad: 0.1052 (0.1060) loss: 0.8162 (0.8171) time: 0.1556 data: 0.0668 max mem: 9390 +Train: [63] [3100/6250] eta: 0:08:43 lr: 0.000040 grad: 0.1017 (0.1060) loss: 0.8205 (0.8172) time: 0.1524 data: 0.0715 max mem: 9390 +Train: [63] [3200/6250] eta: 0:08:25 lr: 0.000040 grad: 0.1068 (0.1061) loss: 0.8156 (0.8172) time: 0.1650 data: 0.0826 max mem: 9390 +Train: [63] [3300/6250] eta: 0:08:08 lr: 0.000040 grad: 0.1079 (0.1062) loss: 0.8186 (0.8172) time: 0.1815 data: 0.0932 max mem: 9390 +Train: [63] [3400/6250] eta: 0:07:51 lr: 0.000040 grad: 0.1025 (0.1062) loss: 0.8146 (0.8172) time: 0.1628 data: 0.0840 max mem: 9390 +Train: [63] [3500/6250] eta: 0:07:34 lr: 0.000040 grad: 0.1044 (0.1063) loss: 0.8202 (0.8172) time: 0.1636 data: 0.0818 max mem: 9390 +Train: [63] [3600/6250] eta: 0:07:18 lr: 0.000040 grad: 0.1129 (0.1063) loss: 0.8166 (0.8173) time: 0.1399 data: 0.0496 max mem: 9390 +Train: [63] [3700/6250] eta: 0:07:01 lr: 0.000040 grad: 0.1104 (0.1063) loss: 0.8170 (0.8173) time: 0.1718 data: 0.0863 max mem: 9390 +Train: [63] [3800/6250] eta: 0:06:43 lr: 0.000040 grad: 0.1083 (0.1064) loss: 0.8159 (0.8174) time: 0.1672 data: 0.0868 max mem: 9390 +Train: [63] [3900/6250] eta: 0:06:26 lr: 0.000040 grad: 0.1005 (0.1064) loss: 0.8165 (0.8174) time: 0.1802 data: 0.0937 max mem: 9390 +Train: [63] [4000/6250] eta: 0:06:09 lr: 0.000040 grad: 0.1007 (0.1064) loss: 0.8234 (0.8174) time: 0.1640 data: 0.0836 max mem: 9390 +Train: [63] [4100/6250] eta: 0:05:53 lr: 0.000040 grad: 0.1020 (0.1064) loss: 0.8208 (0.8174) time: 0.1443 data: 0.0569 max mem: 9390 +Train: [63] [4200/6250] eta: 0:05:36 lr: 0.000040 grad: 0.1007 (0.1065) loss: 0.8236 (0.8174) time: 0.1527 data: 0.0658 max mem: 9390 +Train: [63] [4300/6250] eta: 0:05:20 lr: 0.000040 grad: 0.1013 (0.1065) loss: 0.8176 (0.8174) time: 0.1232 data: 0.0423 max mem: 9390 +Train: [63] [4400/6250] eta: 0:05:04 lr: 0.000040 grad: 0.0989 (0.1065) loss: 0.8147 (0.8173) time: 0.1415 data: 0.0361 max mem: 9390 +Train: [63] [4500/6250] eta: 0:04:47 lr: 0.000040 grad: 0.1046 (0.1066) loss: 0.8181 (0.8173) time: 0.1790 data: 0.0953 max mem: 9390 +Train: [63] [4600/6250] eta: 0:04:31 lr: 0.000040 grad: 0.1095 (0.1067) loss: 0.8219 (0.8173) time: 0.1750 data: 0.0915 max mem: 9390 +Train: [63] [4700/6250] eta: 0:04:14 lr: 0.000040 grad: 0.1003 (0.1067) loss: 0.8237 (0.8173) time: 0.1796 data: 0.0696 max mem: 9390 +Train: [63] [4800/6250] eta: 0:03:58 lr: 0.000040 grad: 0.1088 (0.1068) loss: 0.8119 (0.8173) time: 0.1323 data: 0.0486 max mem: 9390 +Train: [63] [4900/6250] eta: 0:03:42 lr: 0.000040 grad: 0.1056 (0.1068) loss: 0.8138 (0.8172) time: 0.1368 data: 0.0492 max mem: 9390 +Train: [63] [5000/6250] eta: 0:03:25 lr: 0.000040 grad: 0.1057 (0.1068) loss: 0.8169 (0.8172) time: 0.1002 data: 0.0080 max mem: 9390 +Train: [63] [5100/6250] eta: 0:03:09 lr: 0.000040 grad: 0.1020 (0.1068) loss: 0.8194 (0.8172) time: 0.1515 data: 0.0631 max mem: 9390 +Train: [63] [5200/6250] eta: 0:02:52 lr: 0.000040 grad: 0.1058 (0.1068) loss: 0.8159 (0.8171) time: 0.1593 data: 0.0804 max mem: 9390 +Train: [63] [5300/6250] eta: 0:02:36 lr: 0.000040 grad: 0.1064 (0.1068) loss: 0.8173 (0.8171) time: 0.1746 data: 0.0855 max mem: 9390 +Train: [63] [5400/6250] eta: 0:02:20 lr: 0.000040 grad: 0.1055 (0.1068) loss: 0.8197 (0.8171) time: 0.1592 data: 0.0596 max mem: 9390 +Train: [63] [5500/6250] eta: 0:02:03 lr: 0.000040 grad: 0.1062 (0.1068) loss: 0.8137 (0.8172) time: 0.1151 data: 0.0146 max mem: 9390 +Train: [63] [5600/6250] eta: 0:01:47 lr: 0.000039 grad: 0.1021 (0.1068) loss: 0.8146 (0.8171) time: 0.0984 data: 0.0116 max mem: 9390 +Train: [63] [5700/6250] eta: 0:01:30 lr: 0.000039 grad: 0.1017 (0.1068) loss: 0.8178 (0.8171) time: 0.1942 data: 0.1164 max mem: 9390 +Train: [63] [5800/6250] eta: 0:01:14 lr: 0.000039 grad: 0.1097 (0.1068) loss: 0.8163 (0.8171) time: 0.1831 data: 0.0875 max mem: 9390 +Train: [63] [5900/6250] eta: 0:00:57 lr: 0.000039 grad: 0.1154 (0.1069) loss: 0.8134 (0.8171) time: 0.0865 data: 0.0002 max mem: 9390 +Train: [63] [6000/6250] eta: 0:00:41 lr: 0.000039 grad: 0.1001 (0.1069) loss: 0.8162 (0.8170) time: 0.1084 data: 0.0112 max mem: 9390 +Train: [63] [6100/6250] eta: 0:00:24 lr: 0.000039 grad: 0.1045 (0.1069) loss: 0.8164 (0.8170) time: 0.1538 data: 0.0626 max mem: 9390 +Train: [63] [6200/6250] eta: 0:00:08 lr: 0.000039 grad: 0.1036 (0.1069) loss: 0.8152 (0.8170) time: 0.1288 data: 0.0328 max mem: 9390 +Train: [63] [6249/6250] eta: 0:00:00 lr: 0.000039 grad: 0.1063 (0.1070) loss: 0.8189 (0.8170) time: 0.1493 data: 0.0685 max mem: 9390 +Train: [63] Total time: 0:17:15 (0.1657 s / it) +Averaged stats: lr: 0.000039 grad: 0.1063 (0.1070) loss: 0.8189 (0.8170) +Eval (hcp-train-subset): [63] [ 0/62] eta: 0:03:30 loss: 0.8499 (0.8499) time: 3.3987 data: 3.3399 max mem: 9390 +Eval (hcp-train-subset): [63] [61/62] eta: 0:00:00 loss: 0.8292 (0.8318) time: 0.1150 data: 0.0884 max mem: 9390 +Eval (hcp-train-subset): [63] Total time: 0:00:13 (0.2109 s / it) +Averaged stats (hcp-train-subset): loss: 0.8292 (0.8318) +Eval (hcp-val): [63] [ 0/62] eta: 0:03:59 loss: 0.8275 (0.8275) time: 3.8576 data: 3.7620 max mem: 9390 +Eval (hcp-val): [63] [61/62] eta: 0:00:00 loss: 0.8316 (0.8334) time: 0.1121 data: 0.0868 max mem: 9390 +Eval (hcp-val): [63] Total time: 0:00:16 (0.2639 s / it) +Averaged stats (hcp-val): loss: 0.8316 (0.8334) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +Train: [64] [ 0/6250] eta: 9:02:06 lr: 0.000039 grad: 0.1239 (0.1239) loss: 0.8506 (0.8506) time: 5.2042 data: 5.1079 max mem: 9390 +Train: [64] [ 100/6250] eta: 0:22:00 lr: 0.000039 grad: 0.1156 (0.1331) loss: 0.8182 (0.8243) time: 0.1772 data: 0.0805 max mem: 9390 +Train: [64] [ 200/6250] eta: 0:20:17 lr: 0.000039 grad: 0.1151 (0.1262) loss: 0.8153 (0.8207) time: 0.1686 data: 0.0810 max mem: 9390 +Train: [64] [ 300/6250] eta: 0:18:27 lr: 0.000039 grad: 0.1051 (0.1211) loss: 0.8170 (0.8187) time: 0.1883 data: 0.0956 max mem: 9390 +Train: [64] [ 400/6250] eta: 0:17:58 lr: 0.000039 grad: 0.1073 (0.1172) loss: 0.8213 (0.8187) time: 0.1835 data: 0.0949 max mem: 9390 +Train: [64] [ 500/6250] eta: 0:17:30 lr: 0.000039 grad: 0.0966 (0.1149) loss: 0.8239 (0.8196) time: 0.2056 data: 0.1203 max mem: 9390 +Train: [64] [ 600/6250] eta: 0:17:05 lr: 0.000039 grad: 0.1002 (0.1136) loss: 0.8247 (0.8194) time: 0.1795 data: 0.0912 max mem: 9390 +Train: [64] [ 700/6250] eta: 0:16:39 lr: 0.000039 grad: 0.1106 (0.1124) loss: 0.8169 (0.8194) time: 0.1710 data: 0.0722 max mem: 9390 +Train: [64] [ 800/6250] eta: 0:16:10 lr: 0.000039 grad: 0.1004 (0.1115) loss: 0.8186 (0.8195) time: 0.1624 data: 0.0624 max mem: 9390 +Train: [64] [ 900/6250] eta: 0:15:45 lr: 0.000039 grad: 0.1050 (0.1109) loss: 0.8188 (0.8195) time: 0.1935 data: 0.0902 max mem: 9390 +Train: [64] [1000/6250] eta: 0:15:29 lr: 0.000039 grad: 0.1025 (0.1101) loss: 0.8169 (0.8196) time: 0.2480 data: 0.1561 max mem: 9390 +Train: [64] [1100/6250] eta: 0:14:53 lr: 0.000039 grad: 0.0986 (0.1097) loss: 0.8149 (0.8194) time: 0.1359 data: 0.0506 max mem: 9390 +Train: [64] [1200/6250] eta: 0:14:43 lr: 0.000039 grad: 0.1084 (0.1093) loss: 0.8151 (0.8192) time: 0.2458 data: 0.1606 max mem: 9390 +Train: [64] [1300/6250] eta: 0:14:20 lr: 0.000039 grad: 0.0992 (0.1090) loss: 0.8196 (0.8190) time: 0.1755 data: 0.0924 max mem: 9390 +Train: [64] [1400/6250] eta: 0:13:56 lr: 0.000039 grad: 0.1010 (0.1085) loss: 0.8158 (0.8188) time: 0.1742 data: 0.0896 max mem: 9390 +Train: [64] [1500/6250] eta: 0:13:31 lr: 0.000039 grad: 0.1038 (0.1085) loss: 0.8123 (0.8187) time: 0.1478 data: 0.0677 max mem: 9390 +Train: [64] [1600/6250] eta: 0:13:11 lr: 0.000039 grad: 0.1069 (0.1083) loss: 0.8196 (0.8187) time: 0.1580 data: 0.0732 max mem: 9390 +Train: [64] [1700/6250] eta: 0:12:52 lr: 0.000039 grad: 0.1058 (0.1082) loss: 0.8200 (0.8187) time: 0.1697 data: 0.0901 max mem: 9390 +Train: [64] [1800/6250] eta: 0:12:29 lr: 0.000039 grad: 0.1035 (0.1083) loss: 0.8208 (0.8186) time: 0.1550 data: 0.0655 max mem: 9390 +Train: [64] [1900/6250] eta: 0:12:07 lr: 0.000039 grad: 0.1035 (0.1084) loss: 0.8180 (0.8185) time: 0.1527 data: 0.0715 max mem: 9390 +Train: [64] [2000/6250] eta: 0:11:45 lr: 0.000039 grad: 0.1085 (0.1082) loss: 0.8228 (0.8185) time: 0.1541 data: 0.0643 max mem: 9390 +Train: [64] [2100/6250] eta: 0:11:26 lr: 0.000039 grad: 0.0998 (0.1081) loss: 0.8214 (0.8184) time: 0.1352 data: 0.0544 max mem: 9390 +Train: [64] [2200/6250] eta: 0:11:08 lr: 0.000039 grad: 0.1101 (0.1080) loss: 0.8094 (0.8183) time: 0.1483 data: 0.0664 max mem: 9390 +Train: [64] [2300/6250] eta: 0:10:52 lr: 0.000039 grad: 0.1015 (0.1079) loss: 0.8224 (0.8183) time: 0.1482 data: 0.0621 max mem: 9390 +Train: [64] [2400/6250] eta: 0:10:34 lr: 0.000039 grad: 0.0988 (0.1076) loss: 0.8214 (0.8184) time: 0.1853 data: 0.1070 max mem: 9390 +Train: [64] [2500/6250] eta: 0:10:15 lr: 0.000039 grad: 0.1016 (0.1074) loss: 0.8143 (0.8184) time: 0.1707 data: 0.0877 max mem: 9390 +Train: [64] [2600/6250] eta: 0:09:59 lr: 0.000039 grad: 0.0995 (0.1073) loss: 0.8198 (0.8184) time: 0.1777 data: 0.0882 max mem: 9390 +Train: [64] [2700/6250] eta: 0:09:42 lr: 0.000038 grad: 0.1006 (0.1072) loss: 0.8137 (0.8183) time: 0.1588 data: 0.0687 max mem: 9390 +Train: [64] [2800/6250] eta: 0:09:27 lr: 0.000038 grad: 0.1022 (0.1072) loss: 0.8192 (0.8183) time: 0.1588 data: 0.0755 max mem: 9390 +Train: [64] [2900/6250] eta: 0:09:10 lr: 0.000038 grad: 0.0989 (0.1073) loss: 0.8101 (0.8182) time: 0.1284 data: 0.0362 max mem: 9390 +Train: [64] [3000/6250] eta: 0:08:53 lr: 0.000038 grad: 0.1078 (0.1072) loss: 0.8144 (0.8182) time: 0.1683 data: 0.0822 max mem: 9390 +Train: [64] [3100/6250] eta: 0:08:37 lr: 0.000038 grad: 0.0985 (0.1072) loss: 0.8165 (0.8180) time: 0.1712 data: 0.0946 max mem: 9390 +Train: [64] [3200/6250] eta: 0:08:19 lr: 0.000038 grad: 0.1010 (0.1072) loss: 0.8181 (0.8180) time: 0.1473 data: 0.0701 max mem: 9390 +Train: [64] [3300/6250] eta: 0:08:02 lr: 0.000038 grad: 0.1066 (0.1073) loss: 0.8181 (0.8179) time: 0.1952 data: 0.1141 max mem: 9390 +Train: [64] [3400/6250] eta: 0:07:44 lr: 0.000038 grad: 0.1042 (0.1073) loss: 0.8128 (0.8179) time: 0.1465 data: 0.0628 max mem: 9390 +Train: [64] [3500/6250] eta: 0:07:27 lr: 0.000038 grad: 0.1041 (0.1074) loss: 0.8169 (0.8178) time: 0.1308 data: 0.0463 max mem: 9390 +Train: [64] [3600/6250] eta: 0:07:10 lr: 0.000038 grad: 0.1103 (0.1076) loss: 0.8174 (0.8177) time: 0.1539 data: 0.0750 max mem: 9390 +Train: [64] [3700/6250] eta: 0:06:53 lr: 0.000038 grad: 0.1037 (0.1077) loss: 0.8080 (0.8176) time: 0.1537 data: 0.0741 max mem: 9390 +Train: [64] [3800/6250] eta: 0:06:37 lr: 0.000038 grad: 0.1084 (0.1077) loss: 0.8065 (0.8174) time: 0.1474 data: 0.0673 max mem: 9390 +Train: [64] [3900/6250] eta: 0:06:22 lr: 0.000038 grad: 0.1033 (0.1077) loss: 0.8115 (0.8173) time: 0.1249 data: 0.0215 max mem: 9390 +Train: [64] [4000/6250] eta: 0:06:05 lr: 0.000038 grad: 0.1074 (0.1078) loss: 0.8159 (0.8172) time: 0.1535 data: 0.0785 max mem: 9390 +Train: [64] [4100/6250] eta: 0:05:48 lr: 0.000038 grad: 0.1122 (0.1078) loss: 0.8108 (0.8171) time: 0.1040 data: 0.0133 max mem: 9390 +Train: [64] [4200/6250] eta: 0:05:32 lr: 0.000038 grad: 0.1057 (0.1079) loss: 0.8187 (0.8171) time: 0.2087 data: 0.1245 max mem: 9390 +Train: [64] [4300/6250] eta: 0:05:16 lr: 0.000038 grad: 0.1109 (0.1079) loss: 0.8152 (0.8170) time: 0.1518 data: 0.0656 max mem: 9390 +Train: [64] [4400/6250] eta: 0:04:59 lr: 0.000038 grad: 0.1056 (0.1079) loss: 0.8191 (0.8170) time: 0.1175 data: 0.0320 max mem: 9390 +Train: [64] [4500/6250] eta: 0:04:43 lr: 0.000038 grad: 0.1036 (0.1079) loss: 0.8164 (0.8170) time: 0.1652 data: 0.0845 max mem: 9390 +Train: [64] [4600/6250] eta: 0:04:27 lr: 0.000038 grad: 0.1088 (0.1079) loss: 0.8189 (0.8169) time: 0.1500 data: 0.0685 max mem: 9390 +Train: [64] [4700/6250] eta: 0:04:10 lr: 0.000038 grad: 0.1026 (0.1079) loss: 0.8124 (0.8169) time: 0.1550 data: 0.0688 max mem: 9390 +Train: [64] [4800/6250] eta: 0:03:54 lr: 0.000038 grad: 0.1055 (0.1080) loss: 0.8142 (0.8168) time: 0.1274 data: 0.0448 max mem: 9390 +Train: [64] [4900/6250] eta: 0:03:37 lr: 0.000038 grad: 0.1063 (0.1080) loss: 0.8148 (0.8169) time: 0.1649 data: 0.0750 max mem: 9390 +Train: [64] [5000/6250] eta: 0:03:22 lr: 0.000038 grad: 0.1050 (0.1080) loss: 0.8168 (0.8169) time: 0.1599 data: 0.0687 max mem: 9390 +Train: [64] [5100/6250] eta: 0:03:05 lr: 0.000038 grad: 0.1004 (0.1080) loss: 0.8146 (0.8169) time: 0.1349 data: 0.0449 max mem: 9390 +Train: [64] [5200/6250] eta: 0:02:49 lr: 0.000038 grad: 0.1056 (0.1080) loss: 0.8220 (0.8169) time: 0.1211 data: 0.0455 max mem: 9390 +Train: [64] [5300/6250] eta: 0:02:33 lr: 0.000038 grad: 0.1044 (0.1080) loss: 0.8195 (0.8169) time: 0.1598 data: 0.0758 max mem: 9390 +Train: [64] [5400/6250] eta: 0:02:16 lr: 0.000038 grad: 0.1054 (0.1080) loss: 0.8159 (0.8170) time: 0.1458 data: 0.0631 max mem: 9390 +Train: [64] [5500/6250] eta: 0:02:00 lr: 0.000038 grad: 0.1025 (0.1079) loss: 0.8246 (0.8170) time: 0.1827 data: 0.0930 max mem: 9390 +Train: [64] [5600/6250] eta: 0:01:44 lr: 0.000038 grad: 0.1047 (0.1079) loss: 0.8218 (0.8170) time: 0.1585 data: 0.0460 max mem: 9390 +Train: [64] [5700/6250] eta: 0:01:28 lr: 0.000038 grad: 0.1117 (0.1080) loss: 0.8192 (0.8170) time: 0.1565 data: 0.0702 max mem: 9390 +Train: [64] [5800/6250] eta: 0:01:12 lr: 0.000038 grad: 0.1076 (0.1080) loss: 0.8180 (0.8170) time: 0.1607 data: 0.0698 max mem: 9390 +Train: [64] [5900/6250] eta: 0:00:56 lr: 0.000037 grad: 0.1054 (0.1080) loss: 0.8144 (0.8170) time: 0.1838 data: 0.1064 max mem: 9390 +Train: [64] [6000/6250] eta: 0:00:40 lr: 0.000037 grad: 0.1053 (0.1080) loss: 0.8091 (0.8170) time: 0.1496 data: 0.0623 max mem: 9390 +Train: [64] [6100/6250] eta: 0:00:24 lr: 0.000037 grad: 0.1035 (0.1080) loss: 0.8125 (0.8170) time: 0.1234 data: 0.0397 max mem: 9390 +Train: [64] [6200/6250] eta: 0:00:08 lr: 0.000037 grad: 0.1069 (0.1081) loss: 0.8131 (0.8170) time: 0.1597 data: 0.0709 max mem: 9390 +Train: [64] [6249/6250] eta: 0:00:00 lr: 0.000037 grad: 0.1063 (0.1081) loss: 0.8162 (0.8170) time: 0.1530 data: 0.0668 max mem: 9390 +Train: [64] Total time: 0:16:48 (0.1614 s / it) +Averaged stats: lr: 0.000037 grad: 0.1063 (0.1081) loss: 0.8162 (0.8170) +Eval (hcp-train-subset): [64] [ 0/62] eta: 0:03:38 loss: 0.8418 (0.8418) time: 3.5189 data: 3.4642 max mem: 9390 +Eval (hcp-train-subset): [64] [61/62] eta: 0:00:00 loss: 0.8291 (0.8322) time: 0.1525 data: 0.1276 max mem: 9390 +Eval (hcp-train-subset): [64] Total time: 0:00:13 (0.2203 s / it) +Averaged stats (hcp-train-subset): loss: 0.8291 (0.8322) +Making plots (hcp-train-subset): example=5 +Eval (hcp-val): [64] [ 0/62] eta: 0:03:23 loss: 0.8315 (0.8315) time: 3.2854 data: 3.1955 max mem: 9390 +Eval (hcp-val): [64] [61/62] eta: 0:00:00 loss: 0.8322 (0.8341) time: 0.1437 data: 0.1188 max mem: 9390 +Eval (hcp-val): [64] Total time: 0:00:13 (0.2234 s / it) +Averaged stats (hcp-val): loss: 0.8322 (0.8341) +Making plots (hcp-val): example=31 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +Train: [65] [ 0/6250] eta: 9:18:01 lr: 0.000037 grad: 0.3365 (0.3365) loss: 0.8187 (0.8187) time: 5.3571 data: 5.0812 max mem: 9390 +Train: [65] [ 100/6250] eta: 0:24:16 lr: 0.000037 grad: 0.1256 (0.1303) loss: 0.8224 (0.8250) time: 0.1859 data: 0.0890 max mem: 9390 +Train: [65] [ 200/6250] eta: 0:20:40 lr: 0.000037 grad: 0.1086 (0.1275) loss: 0.8132 (0.8207) time: 0.1762 data: 0.0839 max mem: 9390 +Train: [65] [ 300/6250] eta: 0:19:21 lr: 0.000037 grad: 0.1059 (0.1230) loss: 0.8246 (0.8188) time: 0.1990 data: 0.1108 max mem: 9390 +Train: [65] [ 400/6250] eta: 0:18:21 lr: 0.000037 grad: 0.0925 (0.1187) loss: 0.8242 (0.8187) time: 0.1577 data: 0.0647 max mem: 9390 +Train: [65] [ 500/6250] eta: 0:17:40 lr: 0.000037 grad: 0.0962 (0.1148) loss: 0.8252 (0.8197) time: 0.1887 data: 0.0995 max mem: 9390 +Train: [65] [ 600/6250] eta: 0:17:03 lr: 0.000037 grad: 0.0993 (0.1121) loss: 0.8246 (0.8203) time: 0.1816 data: 0.0859 max mem: 9390 +Train: [65] [ 700/6250] eta: 0:16:32 lr: 0.000037 grad: 0.1047 (0.1108) loss: 0.8227 (0.8206) time: 0.1769 data: 0.0902 max mem: 9390 +Train: [65] [ 800/6250] eta: 0:16:03 lr: 0.000037 grad: 0.1010 (0.1095) loss: 0.8185 (0.8208) time: 0.1867 data: 0.1019 max mem: 9390 +Train: [65] [ 900/6250] eta: 0:15:51 lr: 0.000037 grad: 0.1024 (0.1088) loss: 0.8169 (0.8207) time: 0.1183 data: 0.0005 max mem: 9390 +Train: [65] [1000/6250] eta: 0:15:21 lr: 0.000037 grad: 0.1021 (0.1084) loss: 0.8241 (0.8208) time: 0.1639 data: 0.0736 max mem: 9390 +Train: [65] [1100/6250] eta: 0:14:51 lr: 0.000037 grad: 0.1057 (0.1080) loss: 0.8178 (0.8206) time: 0.1670 data: 0.0863 max mem: 9390 +Train: [65] [1200/6250] eta: 0:14:25 lr: 0.000037 grad: 0.0993 (0.1076) loss: 0.8197 (0.8206) time: 0.1594 data: 0.0761 max mem: 9390 +Train: [65] [1300/6250] eta: 0:14:03 lr: 0.000037 grad: 0.0943 (0.1072) loss: 0.8209 (0.8205) time: 0.1571 data: 0.0695 max mem: 9390 +Train: [65] [1400/6250] eta: 0:13:42 lr: 0.000037 grad: 0.1023 (0.1071) loss: 0.8185 (0.8203) time: 0.0977 data: 0.0004 max mem: 9390 +Train: [65] [1500/6250] eta: 0:13:22 lr: 0.000037 grad: 0.1052 (0.1068) loss: 0.8181 (0.8203) time: 0.1520 data: 0.0628 max mem: 9390 +Train: [65] [1600/6250] eta: 0:13:03 lr: 0.000037 grad: 0.1048 (0.1068) loss: 0.8228 (0.8202) time: 0.1210 data: 0.0358 max mem: 9390 +Train: [65] [1700/6250] eta: 0:12:40 lr: 0.000037 grad: 0.1091 (0.1067) loss: 0.8163 (0.8201) time: 0.1487 data: 0.0693 max mem: 9390 +Train: [65] [1800/6250] eta: 0:12:20 lr: 0.000037 grad: 0.0971 (0.1066) loss: 0.8237 (0.8201) time: 0.1665 data: 0.0817 max mem: 9390 +Train: [65] [1900/6250] eta: 0:12:03 lr: 0.000037 grad: 0.1035 (0.1065) loss: 0.8170 (0.8200) time: 0.1769 data: 0.1029 max mem: 9390 +Train: [65] [2000/6250] eta: 0:11:51 lr: 0.000037 grad: 0.1006 (0.1064) loss: 0.8179 (0.8200) time: 0.3020 data: 0.2196 max mem: 9390 +Train: [65] [2100/6250] eta: 0:11:32 lr: 0.000037 grad: 0.1003 (0.1064) loss: 0.8211 (0.8198) time: 0.1634 data: 0.0801 max mem: 9390 +Train: [65] [2200/6250] eta: 0:11:18 lr: 0.000037 grad: 0.1016 (0.1064) loss: 0.8201 (0.8197) time: 0.2427 data: 0.1609 max mem: 9390 +Train: [65] [2300/6250] eta: 0:10:58 lr: 0.000037 grad: 0.1016 (0.1065) loss: 0.8200 (0.8195) time: 0.1703 data: 0.0865 max mem: 9390 +Train: [65] [2400/6250] eta: 0:10:40 lr: 0.000037 grad: 0.1085 (0.1066) loss: 0.8122 (0.8193) time: 0.1414 data: 0.0532 max mem: 9390 +Train: [65] [2500/6250] eta: 0:10:22 lr: 0.000037 grad: 0.1047 (0.1067) loss: 0.8133 (0.8192) time: 0.1386 data: 0.0593 max mem: 9390 +Train: [65] [2600/6250] eta: 0:10:06 lr: 0.000037 grad: 0.1108 (0.1070) loss: 0.8151 (0.8189) time: 0.1277 data: 0.0477 max mem: 9390 +Train: [65] [2700/6250] eta: 0:09:50 lr: 0.000037 grad: 0.1083 (0.1072) loss: 0.8164 (0.8187) time: 0.2282 data: 0.1567 max mem: 9390 +Train: [65] [2800/6250] eta: 0:09:34 lr: 0.000037 grad: 0.1059 (0.1073) loss: 0.8086 (0.8186) time: 0.1609 data: 0.0779 max mem: 9390 +Train: [65] [2900/6250] eta: 0:09:16 lr: 0.000037 grad: 0.1044 (0.1074) loss: 0.8176 (0.8184) time: 0.1641 data: 0.0821 max mem: 9390 +Train: [65] [3000/6250] eta: 0:08:58 lr: 0.000036 grad: 0.1060 (0.1076) loss: 0.8154 (0.8183) time: 0.1424 data: 0.0546 max mem: 9390 +Train: [65] [3100/6250] eta: 0:08:40 lr: 0.000036 grad: 0.1071 (0.1078) loss: 0.8153 (0.8181) time: 0.1357 data: 0.0527 max mem: 9390 +Train: [65] [3200/6250] eta: 0:08:22 lr: 0.000036 grad: 0.1086 (0.1080) loss: 0.8132 (0.8179) time: 0.1683 data: 0.0831 max mem: 9390 +Train: [65] [3300/6250] eta: 0:08:05 lr: 0.000036 grad: 0.1066 (0.1081) loss: 0.8211 (0.8178) time: 0.1533 data: 0.0738 max mem: 9390 +Train: [65] [3400/6250] eta: 0:07:49 lr: 0.000036 grad: 0.1027 (0.1081) loss: 0.8186 (0.8177) time: 0.1632 data: 0.0737 max mem: 9390 +Train: [65] [3500/6250] eta: 0:07:32 lr: 0.000036 grad: 0.1015 (0.1082) loss: 0.8156 (0.8176) time: 0.1699 data: 0.0787 max mem: 9390 +Train: [65] [3600/6250] eta: 0:07:15 lr: 0.000036 grad: 0.1096 (0.1083) loss: 0.8109 (0.8175) time: 0.1503 data: 0.0653 max mem: 9390 +Train: [65] [3700/6250] eta: 0:06:59 lr: 0.000036 grad: 0.1145 (0.1084) loss: 0.8182 (0.8174) time: 0.1766 data: 0.0844 max mem: 9390 +Train: [65] [3800/6250] eta: 0:06:43 lr: 0.000036 grad: 0.1082 (0.1083) loss: 0.8115 (0.8174) time: 0.1449 data: 0.0581 max mem: 9390 +Train: [65] [3900/6250] eta: 0:06:26 lr: 0.000036 grad: 0.1022 (0.1083) loss: 0.8182 (0.8174) time: 0.1271 data: 0.0434 max mem: 9390 +Train: [65] [4000/6250] eta: 0:06:10 lr: 0.000036 grad: 0.1117 (0.1085) loss: 0.8192 (0.8174) time: 0.1944 data: 0.1153 max mem: 9390 +Train: [65] [4100/6250] eta: 0:05:53 lr: 0.000036 grad: 0.1052 (0.1085) loss: 0.8126 (0.8174) time: 0.1183 data: 0.0325 max mem: 9390 +Train: [65] [4200/6250] eta: 0:05:37 lr: 0.000036 grad: 0.1084 (0.1085) loss: 0.8128 (0.8174) time: 0.1521 data: 0.0591 max mem: 9390 +Train: [65] [4300/6250] eta: 0:05:21 lr: 0.000036 grad: 0.1030 (0.1085) loss: 0.8181 (0.8174) time: 0.1745 data: 0.1003 max mem: 9390 +Train: [65] [4400/6250] eta: 0:05:04 lr: 0.000036 grad: 0.1105 (0.1086) loss: 0.8169 (0.8174) time: 0.1090 data: 0.0123 max mem: 9390 +Train: [65] [4500/6250] eta: 0:04:48 lr: 0.000036 grad: 0.1063 (0.1086) loss: 0.8200 (0.8173) time: 0.1606 data: 0.0775 max mem: 9390 +Train: [65] [4600/6250] eta: 0:04:31 lr: 0.000036 grad: 0.1090 (0.1087) loss: 0.8091 (0.8172) time: 0.2083 data: 0.1284 max mem: 9390 +Train: [65] [4700/6250] eta: 0:04:15 lr: 0.000036 grad: 0.1035 (0.1087) loss: 0.8125 (0.8172) time: 0.1838 data: 0.0971 max mem: 9390 +Train: [65] [4800/6250] eta: 0:03:59 lr: 0.000036 grad: 0.1055 (0.1087) loss: 0.8154 (0.8171) time: 0.1315 data: 0.0432 max mem: 9390 +Train: [65] [4900/6250] eta: 0:03:42 lr: 0.000036 grad: 0.1030 (0.1087) loss: 0.8125 (0.8171) time: 0.2029 data: 0.1193 max mem: 9390 +Train: [65] [5000/6250] eta: 0:03:26 lr: 0.000036 grad: 0.1044 (0.1087) loss: 0.8185 (0.8171) time: 0.1223 data: 0.0272 max mem: 9390 +Train: [65] [5100/6250] eta: 0:03:09 lr: 0.000036 grad: 0.1053 (0.1087) loss: 0.8128 (0.8171) time: 0.1454 data: 0.0499 max mem: 9390 +Train: [65] [5200/6250] eta: 0:02:53 lr: 0.000036 grad: 0.1027 (0.1087) loss: 0.8171 (0.8171) time: 0.1319 data: 0.0474 max mem: 9390 +Train: [65] [5300/6250] eta: 0:02:36 lr: 0.000036 grad: 0.1057 (0.1087) loss: 0.8166 (0.8171) time: 0.1842 data: 0.0981 max mem: 9390 +Train: [65] [5400/6250] eta: 0:02:20 lr: 0.000036 grad: 0.1110 (0.1087) loss: 0.8156 (0.8170) time: 0.1247 data: 0.0449 max mem: 9390 +Train: [65] [5500/6250] eta: 0:02:03 lr: 0.000036 grad: 0.1062 (0.1087) loss: 0.8132 (0.8170) time: 0.1224 data: 0.0283 max mem: 9390 +Train: [65] [5600/6250] eta: 0:01:47 lr: 0.000036 grad: 0.1089 (0.1087) loss: 0.8180 (0.8169) time: 0.1902 data: 0.0957 max mem: 9390 +Train: [65] [5700/6250] eta: 0:01:31 lr: 0.000036 grad: 0.1042 (0.1087) loss: 0.8134 (0.8169) time: 0.1911 data: 0.0610 max mem: 9390 +Train: [65] [5800/6250] eta: 0:01:14 lr: 0.000036 grad: 0.1102 (0.1087) loss: 0.8170 (0.8169) time: 0.1536 data: 0.0686 max mem: 9390 +Train: [65] [5900/6250] eta: 0:00:57 lr: 0.000036 grad: 0.0988 (0.1087) loss: 0.8177 (0.8168) time: 0.1749 data: 0.0899 max mem: 9390 +Train: [65] [6000/6250] eta: 0:00:41 lr: 0.000036 grad: 0.1097 (0.1087) loss: 0.8155 (0.8168) time: 0.1994 data: 0.1161 max mem: 9390 +Train: [65] [6100/6250] eta: 0:00:24 lr: 0.000036 grad: 0.1066 (0.1087) loss: 0.8187 (0.8169) time: 0.1842 data: 0.0876 max mem: 9390 +Train: [65] [6200/6250] eta: 0:00:08 lr: 0.000036 grad: 0.1068 (0.1087) loss: 0.8158 (0.8169) time: 0.2120 data: 0.1311 max mem: 9390 +Train: [65] [6249/6250] eta: 0:00:00 lr: 0.000036 grad: 0.1085 (0.1087) loss: 0.8143 (0.8169) time: 0.1325 data: 0.0368 max mem: 9390 +Train: [65] Total time: 0:17:29 (0.1679 s / it) +Averaged stats: lr: 0.000036 grad: 0.1085 (0.1087) loss: 0.8143 (0.8169) +Eval (hcp-train-subset): [65] [ 0/62] eta: 0:06:12 loss: 0.8432 (0.8432) time: 6.0084 data: 5.9766 max mem: 9390 +Eval (hcp-train-subset): [65] [61/62] eta: 0:00:00 loss: 0.8308 (0.8323) time: 0.1636 data: 0.1384 max mem: 9390 +Eval (hcp-train-subset): [65] Total time: 0:00:14 (0.2389 s / it) +Averaged stats (hcp-train-subset): loss: 0.8308 (0.8323) +Eval (hcp-val): [65] [ 0/62] eta: 0:04:26 loss: 0.8277 (0.8277) time: 4.2997 data: 4.2364 max mem: 9390 +Eval (hcp-val): [65] [61/62] eta: 0:00:00 loss: 0.8334 (0.8336) time: 0.1329 data: 0.1047 max mem: 9390 +Eval (hcp-val): [65] Total time: 0:00:14 (0.2307 s / it) +Averaged stats (hcp-val): loss: 0.8334 (0.8336) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +Train: [66] [ 0/6250] eta: 10:54:06 lr: 0.000036 grad: 0.1681 (0.1681) loss: 0.8574 (0.8574) time: 6.2794 data: 6.1546 max mem: 9390 +Train: [66] [ 100/6250] eta: 0:23:51 lr: 0.000035 grad: 0.0981 (0.1331) loss: 0.8254 (0.8279) time: 0.1717 data: 0.0724 max mem: 9390 +Train: [66] [ 200/6250] eta: 0:20:58 lr: 0.000035 grad: 0.1016 (0.1251) loss: 0.8272 (0.8256) time: 0.1649 data: 0.0659 max mem: 9390 +Train: [66] [ 300/6250] eta: 0:19:40 lr: 0.000035 grad: 0.1144 (0.1225) loss: 0.8173 (0.8236) time: 0.1892 data: 0.1035 max mem: 9390 +Train: [66] [ 400/6250] eta: 0:19:15 lr: 0.000035 grad: 0.0986 (0.1188) loss: 0.8288 (0.8228) time: 0.1678 data: 0.0794 max mem: 9390 +Train: [66] [ 500/6250] eta: 0:18:34 lr: 0.000035 grad: 0.0940 (0.1166) loss: 0.8238 (0.8227) time: 0.1805 data: 0.0914 max mem: 9390 +Train: [66] [ 600/6250] eta: 0:17:51 lr: 0.000035 grad: 0.0975 (0.1150) loss: 0.8181 (0.8226) time: 0.1573 data: 0.0699 max mem: 9390 +Train: [66] [ 700/6250] eta: 0:17:25 lr: 0.000035 grad: 0.0984 (0.1134) loss: 0.8212 (0.8227) time: 0.1517 data: 0.0657 max mem: 9390 +Train: [66] [ 800/6250] eta: 0:16:48 lr: 0.000035 grad: 0.1071 (0.1127) loss: 0.8250 (0.8227) time: 0.1569 data: 0.0694 max mem: 9390 +Train: [66] [ 900/6250] eta: 0:16:18 lr: 0.000035 grad: 0.1008 (0.1121) loss: 0.8178 (0.8226) time: 0.1627 data: 0.0754 max mem: 9390 +Train: [66] [1000/6250] eta: 0:15:58 lr: 0.000035 grad: 0.1023 (0.1116) loss: 0.8202 (0.8224) time: 0.1892 data: 0.1012 max mem: 9390 +Train: [66] [1100/6250] eta: 0:15:30 lr: 0.000035 grad: 0.1011 (0.1114) loss: 0.8192 (0.8223) time: 0.1492 data: 0.0654 max mem: 9390 +Train: [66] [1200/6250] eta: 0:15:07 lr: 0.000035 grad: 0.1071 (0.1112) loss: 0.8168 (0.8220) time: 0.1579 data: 0.0703 max mem: 9390 +Train: [66] [1300/6250] eta: 0:14:44 lr: 0.000035 grad: 0.1076 (0.1108) loss: 0.8197 (0.8218) time: 0.1383 data: 0.0350 max mem: 9390 +Train: [66] [1400/6250] eta: 0:14:21 lr: 0.000035 grad: 0.1086 (0.1109) loss: 0.8099 (0.8213) time: 0.1627 data: 0.0792 max mem: 9390 +Train: [66] [1500/6250] eta: 0:14:01 lr: 0.000035 grad: 0.1008 (0.1107) loss: 0.8155 (0.8209) time: 0.1110 data: 0.0212 max mem: 9390 +Train: [66] [1600/6250] eta: 0:13:37 lr: 0.000035 grad: 0.1074 (0.1105) loss: 0.8193 (0.8206) time: 0.1466 data: 0.0684 max mem: 9390 +Train: [66] [1700/6250] eta: 0:13:14 lr: 0.000035 grad: 0.1014 (0.1104) loss: 0.8221 (0.8205) time: 0.1513 data: 0.0570 max mem: 9390 +Train: [66] [1800/6250] eta: 0:12:54 lr: 0.000035 grad: 0.1093 (0.1103) loss: 0.8121 (0.8204) time: 0.1783 data: 0.0911 max mem: 9390 +Train: [66] [1900/6250] eta: 0:12:32 lr: 0.000035 grad: 0.1042 (0.1105) loss: 0.8204 (0.8202) time: 0.1496 data: 0.0593 max mem: 9390 +Train: [66] [2000/6250] eta: 0:12:12 lr: 0.000035 grad: 0.1111 (0.1104) loss: 0.8170 (0.8201) time: 0.1956 data: 0.1076 max mem: 9390 +Train: [66] [2100/6250] eta: 0:11:52 lr: 0.000035 grad: 0.1076 (0.1103) loss: 0.8175 (0.8199) time: 0.1626 data: 0.0690 max mem: 9390 +Train: [66] [2200/6250] eta: 0:11:33 lr: 0.000035 grad: 0.1019 (0.1102) loss: 0.8225 (0.8199) time: 0.1527 data: 0.0673 max mem: 9390 +Train: [66] [2300/6250] eta: 0:11:17 lr: 0.000035 grad: 0.1062 (0.1102) loss: 0.8185 (0.8198) time: 0.1732 data: 0.0943 max mem: 9390 +Train: [66] [2400/6250] eta: 0:10:59 lr: 0.000035 grad: 0.1010 (0.1100) loss: 0.8226 (0.8197) time: 0.1653 data: 0.0846 max mem: 9390 +Train: [66] [2500/6250] eta: 0:10:41 lr: 0.000035 grad: 0.1021 (0.1099) loss: 0.8201 (0.8196) time: 0.1469 data: 0.0667 max mem: 9390 +Train: [66] [2600/6250] eta: 0:10:25 lr: 0.000035 grad: 0.1089 (0.1099) loss: 0.8223 (0.8196) time: 0.1746 data: 0.0953 max mem: 9390 +Train: [66] [2700/6250] eta: 0:10:08 lr: 0.000035 grad: 0.0988 (0.1098) loss: 0.8192 (0.8195) time: 0.2127 data: 0.1343 max mem: 9390 +Train: [66] [2800/6250] eta: 0:09:51 lr: 0.000035 grad: 0.1007 (0.1097) loss: 0.8222 (0.8195) time: 0.1672 data: 0.0843 max mem: 9390 +Train: [66] [2900/6250] eta: 0:09:33 lr: 0.000035 grad: 0.1034 (0.1095) loss: 0.8184 (0.8195) time: 0.1815 data: 0.1036 max mem: 9390 +Train: [66] [3000/6250] eta: 0:09:15 lr: 0.000035 grad: 0.1050 (0.1094) loss: 0.8170 (0.8195) time: 0.1035 data: 0.0150 max mem: 9390 +Train: [66] [3100/6250] eta: 0:08:57 lr: 0.000035 grad: 0.0996 (0.1093) loss: 0.8200 (0.8195) time: 0.1552 data: 0.0692 max mem: 9390 +Train: [66] [3200/6250] eta: 0:08:38 lr: 0.000035 grad: 0.1094 (0.1092) loss: 0.8155 (0.8196) time: 0.1595 data: 0.0739 max mem: 9390 +Train: [66] [3300/6250] eta: 0:08:20 lr: 0.000035 grad: 0.1019 (0.1091) loss: 0.8168 (0.8195) time: 0.1442 data: 0.0598 max mem: 9390 +Train: [66] [3400/6250] eta: 0:08:03 lr: 0.000035 grad: 0.1062 (0.1091) loss: 0.8184 (0.8195) time: 0.1236 data: 0.0271 max mem: 9390 +Train: [66] [3500/6250] eta: 0:07:49 lr: 0.000034 grad: 0.1037 (0.1090) loss: 0.8171 (0.8195) time: 0.3441 data: 0.2624 max mem: 9390 +Train: [66] [3600/6250] eta: 0:07:31 lr: 0.000034 grad: 0.1043 (0.1091) loss: 0.8220 (0.8194) time: 0.1467 data: 0.0635 max mem: 9390 +Train: [66] [3700/6250] eta: 0:07:14 lr: 0.000034 grad: 0.1168 (0.1092) loss: 0.8182 (0.8194) time: 0.1319 data: 0.0368 max mem: 9390 +Train: [66] [3800/6250] eta: 0:06:56 lr: 0.000034 grad: 0.1133 (0.1093) loss: 0.8112 (0.8193) time: 0.1504 data: 0.0650 max mem: 9390 +Train: [66] [3900/6250] eta: 0:06:38 lr: 0.000034 grad: 0.1110 (0.1093) loss: 0.8164 (0.8193) time: 0.1781 data: 0.0973 max mem: 9390 +Train: [66] [4000/6250] eta: 0:06:20 lr: 0.000034 grad: 0.1082 (0.1093) loss: 0.8225 (0.8192) time: 0.1673 data: 0.0866 max mem: 9390 +Train: [66] [4100/6250] eta: 0:06:04 lr: 0.000034 grad: 0.1065 (0.1093) loss: 0.8174 (0.8192) time: 0.2578 data: 0.1749 max mem: 9390 +Train: [66] [4200/6250] eta: 0:05:47 lr: 0.000034 grad: 0.1020 (0.1093) loss: 0.8175 (0.8192) time: 0.1589 data: 0.0751 max mem: 9390 +Train: [66] [4300/6250] eta: 0:05:29 lr: 0.000034 grad: 0.1052 (0.1094) loss: 0.8200 (0.8191) time: 0.2052 data: 0.1164 max mem: 9390 +Train: [66] [4400/6250] eta: 0:05:12 lr: 0.000034 grad: 0.1007 (0.1093) loss: 0.8161 (0.8191) time: 0.1425 data: 0.0584 max mem: 9390 +Train: [66] [4500/6250] eta: 0:04:55 lr: 0.000034 grad: 0.1026 (0.1092) loss: 0.8187 (0.8191) time: 0.1581 data: 0.0716 max mem: 9390 +Train: [66] [4600/6250] eta: 0:04:38 lr: 0.000034 grad: 0.1058 (0.1092) loss: 0.8188 (0.8191) time: 0.1733 data: 0.0702 max mem: 9390 +Train: [66] [4700/6250] eta: 0:04:21 lr: 0.000034 grad: 0.1114 (0.1091) loss: 0.8182 (0.8190) time: 0.0938 data: 0.0002 max mem: 9390 +Train: [66] [4800/6250] eta: 0:04:04 lr: 0.000034 grad: 0.1074 (0.1092) loss: 0.8192 (0.8190) time: 0.1609 data: 0.0729 max mem: 9390 +Train: [66] [4900/6250] eta: 0:03:47 lr: 0.000034 grad: 0.1085 (0.1092) loss: 0.8244 (0.8190) time: 0.1598 data: 0.0729 max mem: 9390 +Train: [66] [5000/6250] eta: 0:03:30 lr: 0.000034 grad: 0.1134 (0.1092) loss: 0.8182 (0.8190) time: 0.0834 data: 0.0005 max mem: 9390 +Train: [66] [5100/6250] eta: 0:03:13 lr: 0.000034 grad: 0.1094 (0.1094) loss: 0.8122 (0.8190) time: 0.2915 data: 0.2065 max mem: 9390 +Train: [66] [5200/6250] eta: 0:02:56 lr: 0.000034 grad: 0.1129 (0.1094) loss: 0.8103 (0.8189) time: 0.1367 data: 0.0448 max mem: 9390 +Train: [66] [5300/6250] eta: 0:02:39 lr: 0.000034 grad: 0.1089 (0.1094) loss: 0.8119 (0.8189) time: 0.1472 data: 0.0582 max mem: 9390 +Train: [66] [5400/6250] eta: 0:02:23 lr: 0.000034 grad: 0.1133 (0.1094) loss: 0.8151 (0.8188) time: 0.2767 data: 0.1840 max mem: 9390 +Train: [66] [5500/6250] eta: 0:02:06 lr: 0.000034 grad: 0.1106 (0.1095) loss: 0.8153 (0.8187) time: 0.1818 data: 0.0984 max mem: 9390 +Train: [66] [5600/6250] eta: 0:01:49 lr: 0.000034 grad: 0.1052 (0.1095) loss: 0.8115 (0.8187) time: 0.1512 data: 0.0498 max mem: 9390 +Train: [66] [5700/6250] eta: 0:01:32 lr: 0.000034 grad: 0.1092 (0.1095) loss: 0.8079 (0.8186) time: 0.1359 data: 0.0457 max mem: 9390 +Train: [66] [5800/6250] eta: 0:01:15 lr: 0.000034 grad: 0.1056 (0.1095) loss: 0.8176 (0.8185) time: 0.1383 data: 0.0467 max mem: 9390 +Train: [66] [5900/6250] eta: 0:00:58 lr: 0.000034 grad: 0.1110 (0.1096) loss: 0.8149 (0.8185) time: 0.1629 data: 0.0811 max mem: 9390 +Train: [66] [6000/6250] eta: 0:00:41 lr: 0.000034 grad: 0.1037 (0.1096) loss: 0.8189 (0.8185) time: 0.1664 data: 0.0825 max mem: 9390 +Train: [66] [6100/6250] eta: 0:00:25 lr: 0.000034 grad: 0.1051 (0.1096) loss: 0.8172 (0.8185) time: 0.1132 data: 0.0329 max mem: 9390 +Train: [66] [6200/6250] eta: 0:00:08 lr: 0.000034 grad: 0.1089 (0.1096) loss: 0.8256 (0.8185) time: 0.1578 data: 0.0680 max mem: 9390 +Train: [66] [6249/6250] eta: 0:00:00 lr: 0.000034 grad: 0.1021 (0.1096) loss: 0.8255 (0.8186) time: 0.1131 data: 0.0230 max mem: 9390 +Train: [66] Total time: 0:17:41 (0.1698 s / it) +Averaged stats: lr: 0.000034 grad: 0.1021 (0.1096) loss: 0.8255 (0.8186) +Eval (hcp-train-subset): [66] [ 0/62] eta: 0:04:03 loss: 0.8427 (0.8427) time: 3.9352 data: 3.8388 max mem: 9390 +Eval (hcp-train-subset): [66] [61/62] eta: 0:00:00 loss: 0.8300 (0.8312) time: 0.1443 data: 0.1194 max mem: 9390 +Eval (hcp-train-subset): [66] Total time: 0:00:13 (0.2187 s / it) +Averaged stats (hcp-train-subset): loss: 0.8300 (0.8312) +Eval (hcp-val): [66] [ 0/62] eta: 0:04:19 loss: 0.8306 (0.8306) time: 4.1929 data: 4.1289 max mem: 9390 +Eval (hcp-val): [66] [61/62] eta: 0:00:00 loss: 0.8312 (0.8331) time: 0.1165 data: 0.0892 max mem: 9390 +Eval (hcp-val): [66] Total time: 0:00:13 (0.2214 s / it) +Averaged stats (hcp-val): loss: 0.8312 (0.8331) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +Train: [67] [ 0/6250] eta: 11:38:07 lr: 0.000034 grad: 0.2003 (0.2003) loss: 0.7151 (0.7151) time: 6.7020 data: 6.6011 max mem: 9390 +Train: [67] [ 100/6250] eta: 0:23:31 lr: 0.000034 grad: 0.1261 (0.1294) loss: 0.8088 (0.8123) time: 0.2006 data: 0.1080 max mem: 9390 +Train: [67] [ 200/6250] eta: 0:19:57 lr: 0.000034 grad: 0.1011 (0.1274) loss: 0.8187 (0.8118) time: 0.1724 data: 0.0797 max mem: 9390 +Train: [67] [ 300/6250] eta: 0:19:01 lr: 0.000034 grad: 0.1146 (0.1239) loss: 0.8136 (0.8127) time: 0.1549 data: 0.0662 max mem: 9390 +Train: [67] [ 400/6250] eta: 0:18:15 lr: 0.000034 grad: 0.1074 (0.1208) loss: 0.8100 (0.8134) time: 0.1609 data: 0.0691 max mem: 9390 +Train: [67] [ 500/6250] eta: 0:17:34 lr: 0.000034 grad: 0.1098 (0.1205) loss: 0.8148 (0.8132) time: 0.1806 data: 0.0830 max mem: 9390 +Train: [67] [ 600/6250] eta: 0:16:58 lr: 0.000033 grad: 0.1130 (0.1191) loss: 0.8130 (0.8135) time: 0.1830 data: 0.0958 max mem: 9390 +Train: [67] [ 700/6250] eta: 0:16:22 lr: 0.000033 grad: 0.1096 (0.1176) loss: 0.8192 (0.8147) time: 0.1221 data: 0.0390 max mem: 9390 +Train: [67] [ 800/6250] eta: 0:15:52 lr: 0.000033 grad: 0.1068 (0.1167) loss: 0.8149 (0.8148) time: 0.1623 data: 0.0722 max mem: 9390 +Train: [67] [ 900/6250] eta: 0:15:32 lr: 0.000033 grad: 0.1062 (0.1155) loss: 0.8172 (0.8152) time: 0.1403 data: 0.0524 max mem: 9390 +Train: [67] [1000/6250] eta: 0:15:18 lr: 0.000033 grad: 0.1021 (0.1145) loss: 0.8174 (0.8154) time: 0.0964 data: 0.0003 max mem: 9390 +Train: [67] [1100/6250] eta: 0:14:50 lr: 0.000033 grad: 0.1102 (0.1143) loss: 0.8117 (0.8155) time: 0.2082 data: 0.1219 max mem: 9390 +Train: [67] [1200/6250] eta: 0:14:19 lr: 0.000033 grad: 0.1061 (0.1140) loss: 0.8147 (0.8156) time: 0.1388 data: 0.0442 max mem: 9390 +Train: [67] [1300/6250] eta: 0:13:58 lr: 0.000033 grad: 0.0990 (0.1134) loss: 0.8203 (0.8156) time: 0.1647 data: 0.0735 max mem: 9390 +Train: [67] [1400/6250] eta: 0:13:35 lr: 0.000033 grad: 0.1081 (0.1132) loss: 0.8142 (0.8155) time: 0.1469 data: 0.0352 max mem: 9390 +Train: [67] [1500/6250] eta: 0:13:28 lr: 0.000033 grad: 0.1035 (0.1128) loss: 0.8165 (0.8155) time: 0.1680 data: 0.0843 max mem: 9390 +Train: [67] [1600/6250] eta: 0:13:05 lr: 0.000033 grad: 0.1036 (0.1126) loss: 0.8137 (0.8154) time: 0.1736 data: 0.0944 max mem: 9390 +Train: [67] [1700/6250] eta: 0:12:45 lr: 0.000033 grad: 0.1033 (0.1124) loss: 0.8156 (0.8153) time: 0.1661 data: 0.0783 max mem: 9390 +Train: [67] [1800/6250] eta: 0:12:36 lr: 0.000033 grad: 0.1099 (0.1124) loss: 0.8138 (0.8151) time: 0.1645 data: 0.0693 max mem: 9390 +Train: [67] [1900/6250] eta: 0:12:13 lr: 0.000033 grad: 0.1065 (0.1122) loss: 0.8118 (0.8149) time: 0.2008 data: 0.1104 max mem: 9390 +Train: [67] [2000/6250] eta: 0:12:00 lr: 0.000033 grad: 0.1133 (0.1121) loss: 0.8121 (0.8148) time: 0.3099 data: 0.2091 max mem: 9390 +Train: [67] [2100/6250] eta: 0:11:36 lr: 0.000033 grad: 0.1062 (0.1121) loss: 0.8084 (0.8146) time: 0.1441 data: 0.0640 max mem: 9390 +Train: [67] [2200/6250] eta: 0:11:18 lr: 0.000033 grad: 0.1098 (0.1120) loss: 0.8105 (0.8145) time: 0.1913 data: 0.1132 max mem: 9390 +Train: [67] [2300/6250] eta: 0:11:00 lr: 0.000033 grad: 0.1063 (0.1119) loss: 0.8108 (0.8144) time: 0.1750 data: 0.0714 max mem: 9390 +Train: [67] [2400/6250] eta: 0:10:43 lr: 0.000033 grad: 0.1057 (0.1118) loss: 0.8102 (0.8144) time: 0.1636 data: 0.0810 max mem: 9390 +Train: [67] [2500/6250] eta: 0:10:23 lr: 0.000033 grad: 0.1106 (0.1117) loss: 0.8126 (0.8143) time: 0.1591 data: 0.0758 max mem: 9390 +Train: [67] [2600/6250] eta: 0:10:05 lr: 0.000033 grad: 0.1080 (0.1116) loss: 0.8158 (0.8144) time: 0.1398 data: 0.0533 max mem: 9390 +Train: [67] [2700/6250] eta: 0:09:49 lr: 0.000033 grad: 0.1065 (0.1115) loss: 0.8137 (0.8144) time: 0.1628 data: 0.0870 max mem: 9390 +Train: [67] [2800/6250] eta: 0:09:31 lr: 0.000033 grad: 0.1088 (0.1115) loss: 0.8167 (0.8144) time: 0.1255 data: 0.0413 max mem: 9390 +Train: [67] [2900/6250] eta: 0:09:14 lr: 0.000033 grad: 0.1141 (0.1116) loss: 0.8085 (0.8144) time: 0.1779 data: 0.0899 max mem: 9390 +Train: [67] [3000/6250] eta: 0:08:57 lr: 0.000033 grad: 0.1169 (0.1117) loss: 0.8111 (0.8144) time: 0.1485 data: 0.0690 max mem: 9390 +Train: [67] [3100/6250] eta: 0:08:40 lr: 0.000033 grad: 0.1143 (0.1117) loss: 0.8108 (0.8143) time: 0.1383 data: 0.0461 max mem: 9390 +Train: [67] [3200/6250] eta: 0:08:23 lr: 0.000033 grad: 0.1167 (0.1118) loss: 0.8122 (0.8142) time: 0.1644 data: 0.0813 max mem: 9390 +Train: [67] [3300/6250] eta: 0:08:06 lr: 0.000033 grad: 0.1099 (0.1118) loss: 0.8178 (0.8142) time: 0.1476 data: 0.0590 max mem: 9390 +Train: [67] [3400/6250] eta: 0:07:49 lr: 0.000033 grad: 0.1085 (0.1118) loss: 0.8135 (0.8141) time: 0.1648 data: 0.0859 max mem: 9390 +Train: [67] [3500/6250] eta: 0:07:32 lr: 0.000033 grad: 0.1111 (0.1118) loss: 0.8133 (0.8140) time: 0.1774 data: 0.0950 max mem: 9390 +Train: [67] [3600/6250] eta: 0:07:15 lr: 0.000033 grad: 0.1068 (0.1117) loss: 0.8116 (0.8141) time: 0.1338 data: 0.0492 max mem: 9390 +Train: [67] [3700/6250] eta: 0:06:58 lr: 0.000033 grad: 0.1114 (0.1116) loss: 0.8218 (0.8141) time: 0.1673 data: 0.0815 max mem: 9390 +Train: [67] [3800/6250] eta: 0:06:42 lr: 0.000033 grad: 0.1067 (0.1116) loss: 0.8197 (0.8141) time: 0.1774 data: 0.1002 max mem: 9390 +Train: [67] [3900/6250] eta: 0:06:25 lr: 0.000033 grad: 0.1098 (0.1116) loss: 0.8112 (0.8141) time: 0.1496 data: 0.0657 max mem: 9390 +Train: [67] [4000/6250] eta: 0:06:09 lr: 0.000032 grad: 0.1071 (0.1116) loss: 0.8208 (0.8141) time: 0.1547 data: 0.0732 max mem: 9390 +Train: [67] [4100/6250] eta: 0:05:53 lr: 0.000032 grad: 0.1057 (0.1115) loss: 0.8236 (0.8142) time: 0.1602 data: 0.0723 max mem: 9390 +Train: [67] [4200/6250] eta: 0:05:37 lr: 0.000032 grad: 0.1045 (0.1115) loss: 0.8151 (0.8143) time: 0.0968 data: 0.0004 max mem: 9390 +Train: [67] [4300/6250] eta: 0:05:21 lr: 0.000032 grad: 0.1117 (0.1115) loss: 0.8137 (0.8143) time: 0.1569 data: 0.0743 max mem: 9390 +Train: [67] [4400/6250] eta: 0:05:05 lr: 0.000032 grad: 0.1040 (0.1115) loss: 0.8136 (0.8144) time: 0.1963 data: 0.1006 max mem: 9390 +Train: [67] [4500/6250] eta: 0:04:49 lr: 0.000032 grad: 0.1017 (0.1115) loss: 0.8200 (0.8145) time: 0.1611 data: 0.0747 max mem: 9390 +Train: [67] [4600/6250] eta: 0:04:32 lr: 0.000032 grad: 0.1072 (0.1115) loss: 0.8171 (0.8145) time: 0.1422 data: 0.0519 max mem: 9390 +Train: [67] [4700/6250] eta: 0:04:16 lr: 0.000032 grad: 0.1159 (0.1116) loss: 0.8230 (0.8145) time: 0.1007 data: 0.0002 max mem: 9390 +Train: [67] [4800/6250] eta: 0:04:00 lr: 0.000032 grad: 0.1109 (0.1117) loss: 0.8150 (0.8145) time: 0.2323 data: 0.1544 max mem: 9390 +Train: [67] [4900/6250] eta: 0:03:43 lr: 0.000032 grad: 0.1048 (0.1116) loss: 0.8216 (0.8145) time: 0.1820 data: 0.1056 max mem: 9390 +Train: [67] [5000/6250] eta: 0:03:27 lr: 0.000032 grad: 0.1139 (0.1117) loss: 0.8111 (0.8146) time: 0.1750 data: 0.0882 max mem: 9390 +Train: [67] [5100/6250] eta: 0:03:10 lr: 0.000032 grad: 0.1012 (0.1117) loss: 0.8150 (0.8146) time: 0.1963 data: 0.1142 max mem: 9390 +Train: [67] [5200/6250] eta: 0:02:54 lr: 0.000032 grad: 0.1125 (0.1118) loss: 0.8138 (0.8146) time: 0.1410 data: 0.0607 max mem: 9390 +Train: [67] [5300/6250] eta: 0:02:38 lr: 0.000032 grad: 0.1055 (0.1118) loss: 0.8156 (0.8146) time: 0.1874 data: 0.1026 max mem: 9390 +Train: [67] [5400/6250] eta: 0:02:22 lr: 0.000032 grad: 0.1065 (0.1119) loss: 0.8141 (0.8146) time: 0.1823 data: 0.0972 max mem: 9390 +Train: [67] [5500/6250] eta: 0:02:05 lr: 0.000032 grad: 0.1171 (0.1120) loss: 0.8042 (0.8145) time: 0.1827 data: 0.0901 max mem: 9390 +Train: [67] [5600/6250] eta: 0:01:48 lr: 0.000032 grad: 0.1073 (0.1121) loss: 0.8189 (0.8145) time: 0.1618 data: 0.0612 max mem: 9390 +Train: [67] [5700/6250] eta: 0:01:32 lr: 0.000032 grad: 0.1106 (0.1122) loss: 0.8163 (0.8144) time: 0.1793 data: 0.0943 max mem: 9390 +Train: [67] [5800/6250] eta: 0:01:15 lr: 0.000032 grad: 0.1148 (0.1123) loss: 0.8098 (0.8144) time: 0.1754 data: 0.0983 max mem: 9390 +Train: [67] [5900/6250] eta: 0:00:58 lr: 0.000032 grad: 0.1131 (0.1124) loss: 0.8109 (0.8144) time: 0.2397 data: 0.1414 max mem: 9390 +Train: [67] [6000/6250] eta: 0:00:41 lr: 0.000032 grad: 0.1173 (0.1124) loss: 0.8120 (0.8144) time: 0.1511 data: 0.0625 max mem: 9390 +Train: [67] [6100/6250] eta: 0:00:25 lr: 0.000032 grad: 0.1146 (0.1125) loss: 0.8129 (0.8143) time: 0.2486 data: 0.1614 max mem: 9390 +Train: [67] [6200/6250] eta: 0:00:08 lr: 0.000032 grad: 0.1122 (0.1126) loss: 0.8134 (0.8143) time: 0.1669 data: 0.0894 max mem: 9390 +Train: [67] [6249/6250] eta: 0:00:00 lr: 0.000032 grad: 0.1110 (0.1126) loss: 0.8174 (0.8143) time: 0.1592 data: 0.0707 max mem: 9390 +Train: [67] Total time: 0:17:33 (0.1686 s / it) +Averaged stats: lr: 0.000032 grad: 0.1110 (0.1126) loss: 0.8174 (0.8143) +Eval (hcp-train-subset): [67] [ 0/62] eta: 0:05:06 loss: 0.8401 (0.8401) time: 4.9364 data: 4.8900 max mem: 9390 +Eval (hcp-train-subset): [67] [61/62] eta: 0:00:00 loss: 0.8287 (0.8315) time: 0.1284 data: 0.1036 max mem: 9390 +Eval (hcp-train-subset): [67] Total time: 0:00:13 (0.2167 s / it) +Averaged stats (hcp-train-subset): loss: 0.8287 (0.8315) +Eval (hcp-val): [67] [ 0/62] eta: 0:04:44 loss: 0.8275 (0.8275) time: 4.5909 data: 4.5610 max mem: 9390 +Eval (hcp-val): [67] [61/62] eta: 0:00:00 loss: 0.8325 (0.8326) time: 0.1285 data: 0.0988 max mem: 9390 +Eval (hcp-val): [67] Total time: 0:00:13 (0.2123 s / it) +Averaged stats (hcp-val): loss: 0.8325 (0.8326) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +Train: [68] [ 0/6250] eta: 11:16:23 lr: 0.000032 grad: 0.3256 (0.3256) loss: 0.8373 (0.8373) time: 6.4933 data: 6.3847 max mem: 9390 +Train: [68] [ 100/6250] eta: 0:25:35 lr: 0.000032 grad: 0.1063 (0.1257) loss: 0.8279 (0.8322) time: 0.2619 data: 0.1440 max mem: 9390 +Train: [68] [ 200/6250] eta: 0:21:46 lr: 0.000032 grad: 0.1157 (0.1258) loss: 0.8233 (0.8294) time: 0.1691 data: 0.0759 max mem: 9390 +Train: [68] [ 300/6250] eta: 0:19:58 lr: 0.000032 grad: 0.1015 (0.1219) loss: 0.8254 (0.8264) time: 0.1468 data: 0.0540 max mem: 9390 +Train: [68] [ 400/6250] eta: 0:18:58 lr: 0.000032 grad: 0.1083 (0.1185) loss: 0.8200 (0.8253) time: 0.1587 data: 0.0701 max mem: 9390 +Train: [68] [ 500/6250] eta: 0:18:32 lr: 0.000032 grad: 0.1018 (0.1165) loss: 0.8227 (0.8246) time: 0.1853 data: 0.0994 max mem: 9390 +Train: [68] [ 600/6250] eta: 0:18:08 lr: 0.000032 grad: 0.1004 (0.1161) loss: 0.8225 (0.8235) time: 0.1767 data: 0.0675 max mem: 9390 +Train: [68] [ 700/6250] eta: 0:17:28 lr: 0.000032 grad: 0.1016 (0.1151) loss: 0.8145 (0.8225) time: 0.1531 data: 0.0657 max mem: 9390 +Train: [68] [ 800/6250] eta: 0:16:51 lr: 0.000032 grad: 0.1124 (0.1144) loss: 0.8208 (0.8219) time: 0.1788 data: 0.0949 max mem: 9390 +Train: [68] [ 900/6250] eta: 0:16:30 lr: 0.000032 grad: 0.1073 (0.1139) loss: 0.8153 (0.8213) time: 0.1835 data: 0.1025 max mem: 9390 +Train: [68] [1000/6250] eta: 0:16:03 lr: 0.000032 grad: 0.1102 (0.1136) loss: 0.8126 (0.8206) time: 0.1555 data: 0.0564 max mem: 9390 +Train: [68] [1100/6250] eta: 0:15:32 lr: 0.000032 grad: 0.1063 (0.1134) loss: 0.8170 (0.8201) time: 0.1672 data: 0.0737 max mem: 9390 +Train: [68] [1200/6250] eta: 0:15:03 lr: 0.000032 grad: 0.1059 (0.1130) loss: 0.8057 (0.8196) time: 0.1568 data: 0.0753 max mem: 9390 +Train: [68] [1300/6250] eta: 0:14:40 lr: 0.000031 grad: 0.1106 (0.1129) loss: 0.8093 (0.8192) time: 0.1778 data: 0.0987 max mem: 9390 +Train: [68] [1400/6250] eta: 0:14:13 lr: 0.000031 grad: 0.1087 (0.1130) loss: 0.8201 (0.8186) time: 0.1578 data: 0.0748 max mem: 9390 +Train: [68] [1500/6250] eta: 0:14:13 lr: 0.000031 grad: 0.1083 (0.1129) loss: 0.8173 (0.8183) time: 0.4558 data: 0.3661 max mem: 9390 +Train: [68] [1600/6250] eta: 0:13:48 lr: 0.000031 grad: 0.1116 (0.1129) loss: 0.8170 (0.8180) time: 0.2185 data: 0.1358 max mem: 9390 +Train: [68] [1700/6250] eta: 0:13:20 lr: 0.000031 grad: 0.1120 (0.1129) loss: 0.8098 (0.8179) time: 0.1414 data: 0.0572 max mem: 9390 +Train: [68] [1800/6250] eta: 0:12:57 lr: 0.000031 grad: 0.1013 (0.1129) loss: 0.8212 (0.8177) time: 0.1473 data: 0.0614 max mem: 9390 +Train: [68] [1900/6250] eta: 0:12:37 lr: 0.000031 grad: 0.1076 (0.1129) loss: 0.8152 (0.8174) time: 0.1154 data: 0.0003 max mem: 9390 +Train: [68] [2000/6250] eta: 0:12:15 lr: 0.000031 grad: 0.1085 (0.1127) loss: 0.8126 (0.8173) time: 0.1599 data: 0.0616 max mem: 9390 +Train: [68] [2100/6250] eta: 0:11:55 lr: 0.000031 grad: 0.1118 (0.1128) loss: 0.8155 (0.8171) time: 0.1528 data: 0.0696 max mem: 9390 +Train: [68] [2200/6250] eta: 0:11:37 lr: 0.000031 grad: 0.1104 (0.1129) loss: 0.8197 (0.8171) time: 0.1986 data: 0.1087 max mem: 9390 +Train: [68] [2300/6250] eta: 0:11:15 lr: 0.000031 grad: 0.1017 (0.1128) loss: 0.8150 (0.8169) time: 0.1419 data: 0.0580 max mem: 9390 +Train: [68] [2400/6250] eta: 0:10:58 lr: 0.000031 grad: 0.1103 (0.1127) loss: 0.8071 (0.8167) time: 0.1721 data: 0.0881 max mem: 9390 +Train: [68] [2500/6250] eta: 0:10:39 lr: 0.000031 grad: 0.1098 (0.1126) loss: 0.8111 (0.8166) time: 0.1700 data: 0.0861 max mem: 9390 +Train: [68] [2600/6250] eta: 0:10:20 lr: 0.000031 grad: 0.1107 (0.1127) loss: 0.8096 (0.8164) time: 0.1568 data: 0.0769 max mem: 9390 +Train: [68] [2700/6250] eta: 0:10:05 lr: 0.000031 grad: 0.1079 (0.1129) loss: 0.8161 (0.8163) time: 0.2741 data: 0.1930 max mem: 9390 +Train: [68] [2800/6250] eta: 0:09:45 lr: 0.000031 grad: 0.1098 (0.1130) loss: 0.8174 (0.8162) time: 0.1981 data: 0.1129 max mem: 9390 +Train: [68] [2900/6250] eta: 0:09:26 lr: 0.000031 grad: 0.1000 (0.1130) loss: 0.8142 (0.8160) time: 0.1401 data: 0.0624 max mem: 9390 +Train: [68] [3000/6250] eta: 0:09:09 lr: 0.000031 grad: 0.1122 (0.1130) loss: 0.8178 (0.8160) time: 0.1970 data: 0.1182 max mem: 9390 +Train: [68] [3100/6250] eta: 0:08:50 lr: 0.000031 grad: 0.1050 (0.1129) loss: 0.8188 (0.8160) time: 0.1712 data: 0.0786 max mem: 9390 +Train: [68] [3200/6250] eta: 0:08:34 lr: 0.000031 grad: 0.1101 (0.1129) loss: 0.8140 (0.8159) time: 0.2406 data: 0.1533 max mem: 9390 +Train: [68] [3300/6250] eta: 0:08:15 lr: 0.000031 grad: 0.1073 (0.1130) loss: 0.8154 (0.8159) time: 0.1465 data: 0.0621 max mem: 9390 +Train: [68] [3400/6250] eta: 0:07:57 lr: 0.000031 grad: 0.1097 (0.1129) loss: 0.8167 (0.8159) time: 0.1683 data: 0.0855 max mem: 9390 +Train: [68] [3500/6250] eta: 0:07:40 lr: 0.000031 grad: 0.1130 (0.1129) loss: 0.8119 (0.8160) time: 0.1652 data: 0.0876 max mem: 9390 +Train: [68] [3600/6250] eta: 0:07:22 lr: 0.000031 grad: 0.1060 (0.1129) loss: 0.8143 (0.8159) time: 0.1519 data: 0.0696 max mem: 9390 +Train: [68] [3700/6250] eta: 0:07:05 lr: 0.000031 grad: 0.1019 (0.1128) loss: 0.8214 (0.8159) time: 0.2013 data: 0.1134 max mem: 9390 +Train: [68] [3800/6250] eta: 0:06:48 lr: 0.000031 grad: 0.1026 (0.1128) loss: 0.8198 (0.8160) time: 0.1896 data: 0.1055 max mem: 9390 +Train: [68] [3900/6250] eta: 0:06:31 lr: 0.000031 grad: 0.1106 (0.1127) loss: 0.8203 (0.8161) time: 0.1671 data: 0.0746 max mem: 9390 +Train: [68] [4000/6250] eta: 0:06:15 lr: 0.000031 grad: 0.1102 (0.1126) loss: 0.8182 (0.8162) time: 0.1589 data: 0.0709 max mem: 9390 +Train: [68] [4100/6250] eta: 0:05:58 lr: 0.000031 grad: 0.1052 (0.1125) loss: 0.8188 (0.8162) time: 0.1875 data: 0.1117 max mem: 9390 +Train: [68] [4200/6250] eta: 0:05:42 lr: 0.000031 grad: 0.1063 (0.1125) loss: 0.8153 (0.8162) time: 0.2235 data: 0.1445 max mem: 9390 +Train: [68] [4300/6250] eta: 0:05:25 lr: 0.000031 grad: 0.1125 (0.1125) loss: 0.8099 (0.8162) time: 0.1360 data: 0.0520 max mem: 9390 +Train: [68] [4400/6250] eta: 0:05:08 lr: 0.000031 grad: 0.1094 (0.1125) loss: 0.8111 (0.8161) time: 0.2060 data: 0.1225 max mem: 9390 +Train: [68] [4500/6250] eta: 0:04:52 lr: 0.000031 grad: 0.1030 (0.1125) loss: 0.8175 (0.8161) time: 0.1889 data: 0.1132 max mem: 9390 +Train: [68] [4600/6250] eta: 0:04:38 lr: 0.000031 grad: 0.1072 (0.1126) loss: 0.8154 (0.8161) time: 0.4571 data: 0.3804 max mem: 9390 +Train: [68] [4700/6250] eta: 0:04:20 lr: 0.000031 grad: 0.1125 (0.1125) loss: 0.8179 (0.8161) time: 0.1615 data: 0.0827 max mem: 9390 +Train: [68] [4800/6250] eta: 0:04:03 lr: 0.000030 grad: 0.1101 (0.1125) loss: 0.8120 (0.8161) time: 0.1426 data: 0.0537 max mem: 9390 +Train: [68] [4900/6250] eta: 0:03:46 lr: 0.000030 grad: 0.1047 (0.1126) loss: 0.8154 (0.8160) time: 0.1914 data: 0.1033 max mem: 9390 +Train: [68] [5000/6250] eta: 0:03:29 lr: 0.000030 grad: 0.1065 (0.1126) loss: 0.8075 (0.8160) time: 0.1423 data: 0.0540 max mem: 9390 +Train: [68] [5100/6250] eta: 0:03:12 lr: 0.000030 grad: 0.1008 (0.1125) loss: 0.8164 (0.8160) time: 0.1557 data: 0.0775 max mem: 9390 +Train: [68] [5200/6250] eta: 0:02:55 lr: 0.000030 grad: 0.1148 (0.1125) loss: 0.8173 (0.8160) time: 0.1389 data: 0.0477 max mem: 9390 +Train: [68] [5300/6250] eta: 0:02:38 lr: 0.000030 grad: 0.1019 (0.1125) loss: 0.8151 (0.8160) time: 0.1708 data: 0.0820 max mem: 9390 +Train: [68] [5400/6250] eta: 0:02:22 lr: 0.000030 grad: 0.1000 (0.1125) loss: 0.8130 (0.8160) time: 0.1036 data: 0.0002 max mem: 9390 +Train: [68] [5500/6250] eta: 0:02:05 lr: 0.000030 grad: 0.1057 (0.1124) loss: 0.8166 (0.8160) time: 0.1773 data: 0.0871 max mem: 9390 +Train: [68] [5600/6250] eta: 0:01:48 lr: 0.000030 grad: 0.1075 (0.1124) loss: 0.8144 (0.8160) time: 0.1547 data: 0.0776 max mem: 9390 +Train: [68] [5700/6250] eta: 0:01:32 lr: 0.000030 grad: 0.1105 (0.1124) loss: 0.8162 (0.8160) time: 0.0992 data: 0.0002 max mem: 9390 +Train: [68] [5800/6250] eta: 0:01:15 lr: 0.000030 grad: 0.1126 (0.1124) loss: 0.8127 (0.8160) time: 0.1623 data: 0.0758 max mem: 9390 +Train: [68] [5900/6250] eta: 0:00:58 lr: 0.000030 grad: 0.1107 (0.1124) loss: 0.8189 (0.8160) time: 0.1597 data: 0.0774 max mem: 9390 +Train: [68] [6000/6250] eta: 0:00:41 lr: 0.000030 grad: 0.1037 (0.1124) loss: 0.8136 (0.8160) time: 0.1462 data: 0.0592 max mem: 9390 +Train: [68] [6100/6250] eta: 0:00:25 lr: 0.000030 grad: 0.1090 (0.1124) loss: 0.8137 (0.8160) time: 0.1346 data: 0.0516 max mem: 9390 +Train: [68] [6200/6250] eta: 0:00:08 lr: 0.000030 grad: 0.1098 (0.1123) loss: 0.8126 (0.8160) time: 0.1630 data: 0.0715 max mem: 9390 +Train: [68] [6249/6250] eta: 0:00:00 lr: 0.000030 grad: 0.0972 (0.1123) loss: 0.8185 (0.8160) time: 0.1899 data: 0.0960 max mem: 9390 +Train: [68] Total time: 0:17:33 (0.1686 s / it) +Averaged stats: lr: 0.000030 grad: 0.0972 (0.1123) loss: 0.8185 (0.8160) +Eval (hcp-train-subset): [68] [ 0/62] eta: 0:04:17 loss: 0.8425 (0.8425) time: 4.1534 data: 4.0807 max mem: 9390 +Eval (hcp-train-subset): [68] [61/62] eta: 0:00:00 loss: 0.8294 (0.8320) time: 0.1355 data: 0.1108 max mem: 9390 +Eval (hcp-train-subset): [68] Total time: 0:00:14 (0.2259 s / it) +Averaged stats (hcp-train-subset): loss: 0.8294 (0.8320) +Eval (hcp-val): [68] [ 0/62] eta: 0:03:10 loss: 0.8293 (0.8293) time: 3.0693 data: 2.9820 max mem: 9390 +Eval (hcp-val): [68] [61/62] eta: 0:00:00 loss: 0.8304 (0.8322) time: 0.1464 data: 0.1194 max mem: 9390 +Eval (hcp-val): [68] Total time: 0:00:13 (0.2243 s / it) +Averaged stats (hcp-val): loss: 0.8304 (0.8322) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +Train: [69] [ 0/6250] eta: 9:56:40 lr: 0.000030 grad: 0.1905 (0.1905) loss: 0.8120 (0.8120) time: 5.7281 data: 5.5701 max mem: 9390 +Train: [69] [ 100/6250] eta: 0:26:14 lr: 0.000030 grad: 0.1092 (0.1240) loss: 0.8197 (0.8215) time: 0.1191 data: 0.0072 max mem: 9390 +Train: [69] [ 200/6250] eta: 0:22:32 lr: 0.000030 grad: 0.1070 (0.1186) loss: 0.8246 (0.8205) time: 0.2126 data: 0.1243 max mem: 9390 +Train: [69] [ 300/6250] eta: 0:20:38 lr: 0.000030 grad: 0.1104 (0.1171) loss: 0.8171 (0.8198) time: 0.1867 data: 0.0758 max mem: 9390 +Train: [69] [ 400/6250] eta: 0:19:51 lr: 0.000030 grad: 0.1174 (0.1169) loss: 0.8151 (0.8192) time: 0.2614 data: 0.1625 max mem: 9390 +Train: [69] [ 500/6250] eta: 0:18:24 lr: 0.000030 grad: 0.1062 (0.1157) loss: 0.8188 (0.8188) time: 0.1543 data: 0.0592 max mem: 9390 +Train: [69] [ 600/6250] eta: 0:17:41 lr: 0.000030 grad: 0.1085 (0.1155) loss: 0.8131 (0.8185) time: 0.1546 data: 0.0473 max mem: 9390 +Train: [69] [ 700/6250] eta: 0:17:06 lr: 0.000030 grad: 0.1009 (0.1151) loss: 0.8109 (0.8182) time: 0.1857 data: 0.0993 max mem: 9390 +Train: [69] [ 800/6250] eta: 0:16:32 lr: 0.000030 grad: 0.1071 (0.1149) loss: 0.8150 (0.8182) time: 0.1760 data: 0.0893 max mem: 9390 +Train: [69] [ 900/6250] eta: 0:16:04 lr: 0.000030 grad: 0.1029 (0.1146) loss: 0.8170 (0.8181) time: 0.1577 data: 0.0671 max mem: 9390 +Train: [69] [1000/6250] eta: 0:15:47 lr: 0.000030 grad: 0.1138 (0.1146) loss: 0.8124 (0.8179) time: 0.1044 data: 0.0003 max mem: 9390 +Train: [69] [1100/6250] eta: 0:15:17 lr: 0.000030 grad: 0.1141 (0.1146) loss: 0.8098 (0.8175) time: 0.1296 data: 0.0383 max mem: 9390 +Train: [69] [1200/6250] eta: 0:14:54 lr: 0.000030 grad: 0.1152 (0.1148) loss: 0.8121 (0.8170) time: 0.1570 data: 0.0694 max mem: 9390 +Train: [69] [1300/6250] eta: 0:14:31 lr: 0.000030 grad: 0.1128 (0.1151) loss: 0.8064 (0.8164) time: 0.1705 data: 0.0895 max mem: 9390 +Train: [69] [1400/6250] eta: 0:14:05 lr: 0.000030 grad: 0.1122 (0.1153) loss: 0.8054 (0.8158) time: 0.1560 data: 0.0689 max mem: 9390 +Train: [69] [1500/6250] eta: 0:13:41 lr: 0.000030 grad: 0.1167 (0.1156) loss: 0.8021 (0.8153) time: 0.1611 data: 0.0780 max mem: 9390 +Train: [69] [1600/6250] eta: 0:13:18 lr: 0.000030 grad: 0.1169 (0.1158) loss: 0.8105 (0.8148) time: 0.1515 data: 0.0667 max mem: 9390 +Train: [69] [1700/6250] eta: 0:13:00 lr: 0.000030 grad: 0.1107 (0.1161) loss: 0.8082 (0.8144) time: 0.1257 data: 0.0477 max mem: 9390 +Train: [69] [1800/6250] eta: 0:12:36 lr: 0.000030 grad: 0.1110 (0.1161) loss: 0.8159 (0.8142) time: 0.1480 data: 0.0668 max mem: 9390 +Train: [69] [1900/6250] eta: 0:12:17 lr: 0.000030 grad: 0.1147 (0.1163) loss: 0.8121 (0.8139) time: 0.1453 data: 0.0642 max mem: 9390 +Train: [69] [2000/6250] eta: 0:11:58 lr: 0.000030 grad: 0.1196 (0.1162) loss: 0.8025 (0.8135) time: 0.1488 data: 0.0637 max mem: 9390 +Train: [69] [2100/6250] eta: 0:11:38 lr: 0.000029 grad: 0.1101 (0.1162) loss: 0.8126 (0.8133) time: 0.1793 data: 0.0971 max mem: 9390 +Train: [69] [2200/6250] eta: 0:11:19 lr: 0.000029 grad: 0.1117 (0.1163) loss: 0.8112 (0.8130) time: 0.1592 data: 0.0792 max mem: 9390 +Train: [69] [2300/6250] eta: 0:11:03 lr: 0.000029 grad: 0.1189 (0.1163) loss: 0.8063 (0.8128) time: 0.1826 data: 0.1040 max mem: 9390 +Train: [69] [2400/6250] eta: 0:10:45 lr: 0.000029 grad: 0.1079 (0.1163) loss: 0.8147 (0.8126) time: 0.1531 data: 0.0725 max mem: 9390 +Train: [69] [2500/6250] eta: 0:10:29 lr: 0.000029 grad: 0.1083 (0.1163) loss: 0.8109 (0.8124) time: 0.2016 data: 0.1197 max mem: 9390 +Train: [69] [2600/6250] eta: 0:10:10 lr: 0.000029 grad: 0.1166 (0.1164) loss: 0.8066 (0.8123) time: 0.1658 data: 0.0842 max mem: 9390 +Train: [69] [2700/6250] eta: 0:09:52 lr: 0.000029 grad: 0.1076 (0.1163) loss: 0.8071 (0.8122) time: 0.1440 data: 0.0642 max mem: 9390 +Train: [69] [2800/6250] eta: 0:09:35 lr: 0.000029 grad: 0.1107 (0.1163) loss: 0.8118 (0.8120) time: 0.1787 data: 0.0924 max mem: 9390 +Train: [69] [2900/6250] eta: 0:09:17 lr: 0.000029 grad: 0.1094 (0.1163) loss: 0.8105 (0.8119) time: 0.1659 data: 0.0807 max mem: 9390 +Train: [69] [3000/6250] eta: 0:09:02 lr: 0.000029 grad: 0.1151 (0.1163) loss: 0.8092 (0.8118) time: 0.0950 data: 0.0002 max mem: 9390 +Train: [69] [3100/6250] eta: 0:08:44 lr: 0.000029 grad: 0.1213 (0.1167) loss: 0.8082 (0.8117) time: 0.1627 data: 0.0817 max mem: 9390 +Train: [69] [3200/6250] eta: 0:08:27 lr: 0.000029 grad: 0.1146 (0.1168) loss: 0.8119 (0.8116) time: 0.1900 data: 0.1118 max mem: 9390 +Train: [69] [3300/6250] eta: 0:08:08 lr: 0.000029 grad: 0.1085 (0.1168) loss: 0.8108 (0.8116) time: 0.1354 data: 0.0512 max mem: 9390 +Train: [69] [3400/6250] eta: 0:07:51 lr: 0.000029 grad: 0.1171 (0.1167) loss: 0.8094 (0.8115) time: 0.1509 data: 0.0670 max mem: 9390 +Train: [69] [3500/6250] eta: 0:07:34 lr: 0.000029 grad: 0.1133 (0.1167) loss: 0.8137 (0.8115) time: 0.1362 data: 0.0569 max mem: 9390 +Train: [69] [3600/6250] eta: 0:07:16 lr: 0.000029 grad: 0.1113 (0.1167) loss: 0.8064 (0.8115) time: 0.1542 data: 0.0789 max mem: 9390 +Train: [69] [3700/6250] eta: 0:07:00 lr: 0.000029 grad: 0.1139 (0.1167) loss: 0.8086 (0.8114) time: 0.1948 data: 0.1139 max mem: 9390 +Train: [69] [3800/6250] eta: 0:06:42 lr: 0.000029 grad: 0.1196 (0.1167) loss: 0.8116 (0.8114) time: 0.1576 data: 0.0720 max mem: 9390 +Train: [69] [3900/6250] eta: 0:06:25 lr: 0.000029 grad: 0.1075 (0.1166) loss: 0.8116 (0.8114) time: 0.1632 data: 0.0757 max mem: 9390 +Train: [69] [4000/6250] eta: 0:06:08 lr: 0.000029 grad: 0.1113 (0.1165) loss: 0.8151 (0.8115) time: 0.1632 data: 0.0794 max mem: 9390 +Train: [69] [4100/6250] eta: 0:05:52 lr: 0.000029 grad: 0.1195 (0.1164) loss: 0.8096 (0.8116) time: 0.1275 data: 0.0468 max mem: 9390 +Train: [69] [4200/6250] eta: 0:05:39 lr: 0.000029 grad: 0.1100 (0.1164) loss: 0.8149 (0.8116) time: 0.1462 data: 0.0615 max mem: 9390 +Train: [69] [4300/6250] eta: 0:05:25 lr: 0.000029 grad: 0.1110 (0.1163) loss: 0.8139 (0.8116) time: 0.1974 data: 0.1164 max mem: 9390 +Train: [69] [4400/6250] eta: 0:05:10 lr: 0.000029 grad: 0.1100 (0.1163) loss: 0.8171 (0.8117) time: 0.2646 data: 0.1833 max mem: 9390 +Train: [69] [4500/6250] eta: 0:04:54 lr: 0.000029 grad: 0.1072 (0.1162) loss: 0.8174 (0.8117) time: 0.1768 data: 0.0920 max mem: 9390 +Train: [69] [4600/6250] eta: 0:04:41 lr: 0.000029 grad: 0.1096 (0.1162) loss: 0.8183 (0.8118) time: 0.1075 data: 0.0002 max mem: 9390 +Train: [69] [4700/6250] eta: 0:04:26 lr: 0.000029 grad: 0.1172 (0.1163) loss: 0.8094 (0.8118) time: 0.1287 data: 0.0317 max mem: 9390 +Train: [69] [4800/6250] eta: 0:04:09 lr: 0.000029 grad: 0.1191 (0.1162) loss: 0.8119 (0.8118) time: 0.1679 data: 0.0707 max mem: 9390 +Train: [69] [4900/6250] eta: 0:03:52 lr: 0.000029 grad: 0.1102 (0.1162) loss: 0.8095 (0.8118) time: 0.1482 data: 0.0629 max mem: 9390 +Train: [69] [5000/6250] eta: 0:03:34 lr: 0.000029 grad: 0.1116 (0.1163) loss: 0.8149 (0.8118) time: 0.1583 data: 0.0752 max mem: 9390 +Train: [69] [5100/6250] eta: 0:03:17 lr: 0.000029 grad: 0.1156 (0.1163) loss: 0.8083 (0.8118) time: 0.1712 data: 0.0818 max mem: 9390 +Train: [69] [5200/6250] eta: 0:03:00 lr: 0.000029 grad: 0.1136 (0.1163) loss: 0.8117 (0.8118) time: 0.1676 data: 0.0797 max mem: 9390 +Train: [69] [5300/6250] eta: 0:02:43 lr: 0.000029 grad: 0.1108 (0.1163) loss: 0.8166 (0.8118) time: 0.1769 data: 0.0966 max mem: 9390 +Train: [69] [5400/6250] eta: 0:02:25 lr: 0.000029 grad: 0.1162 (0.1164) loss: 0.8135 (0.8118) time: 0.1598 data: 0.0767 max mem: 9390 +Train: [69] [5500/6250] eta: 0:02:08 lr: 0.000029 grad: 0.1167 (0.1164) loss: 0.8147 (0.8119) time: 0.1611 data: 0.0640 max mem: 9390 +Train: [69] [5600/6250] eta: 0:01:51 lr: 0.000028 grad: 0.1200 (0.1165) loss: 0.8115 (0.8119) time: 0.1509 data: 0.0638 max mem: 9390 +Train: [69] [5700/6250] eta: 0:01:34 lr: 0.000028 grad: 0.1166 (0.1166) loss: 0.8163 (0.8119) time: 0.1735 data: 0.0927 max mem: 9390 +Train: [69] [5800/6250] eta: 0:01:16 lr: 0.000028 grad: 0.1143 (0.1166) loss: 0.8116 (0.8119) time: 0.1587 data: 0.0795 max mem: 9390 +Train: [69] [5900/6250] eta: 0:01:00 lr: 0.000028 grad: 0.1098 (0.1166) loss: 0.8146 (0.8119) time: 0.1645 data: 0.0700 max mem: 9390 +Train: [69] [6000/6250] eta: 0:00:42 lr: 0.000028 grad: 0.1119 (0.1166) loss: 0.8144 (0.8120) time: 0.1797 data: 0.0951 max mem: 9390 +Train: [69] [6100/6250] eta: 0:00:25 lr: 0.000028 grad: 0.1116 (0.1167) loss: 0.8082 (0.8120) time: 0.1624 data: 0.0727 max mem: 9390 +Train: [69] [6200/6250] eta: 0:00:08 lr: 0.000028 grad: 0.1133 (0.1168) loss: 0.8143 (0.8120) time: 0.1640 data: 0.0790 max mem: 9390 +Train: [69] [6249/6250] eta: 0:00:00 lr: 0.000028 grad: 0.1134 (0.1168) loss: 0.8165 (0.8120) time: 0.1861 data: 0.0994 max mem: 9390 +Train: [69] Total time: 0:18:01 (0.1731 s / it) +Averaged stats: lr: 0.000028 grad: 0.1134 (0.1168) loss: 0.8165 (0.8120) +Eval (hcp-train-subset): [69] [ 0/62] eta: 0:03:31 loss: 0.8412 (0.8412) time: 3.4122 data: 3.3479 max mem: 9390 +Eval (hcp-train-subset): [69] [61/62] eta: 0:00:00 loss: 0.8311 (0.8316) time: 0.1747 data: 0.1496 max mem: 9390 +Eval (hcp-train-subset): [69] Total time: 0:00:13 (0.2252 s / it) +Averaged stats (hcp-train-subset): loss: 0.8311 (0.8316) +Making plots (hcp-train-subset): example=32 +Eval (hcp-val): [69] [ 0/62] eta: 0:06:16 loss: 0.8279 (0.8279) time: 6.0669 data: 6.0290 max mem: 9390 +Eval (hcp-val): [69] [61/62] eta: 0:00:00 loss: 0.8307 (0.8323) time: 0.1537 data: 0.1272 max mem: 9390 +Eval (hcp-val): [69] Total time: 0:00:14 (0.2321 s / it) +Averaged stats (hcp-val): loss: 0.8307 (0.8323) +Making plots (hcp-val): example=55 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +Train: [70] [ 0/6250] eta: 9:19:24 lr: 0.000028 grad: 0.0679 (0.0679) loss: 0.8710 (0.8710) time: 5.3703 data: 5.2261 max mem: 9390 +Train: [70] [ 100/6250] eta: 0:25:12 lr: 0.000028 grad: 0.1370 (0.1261) loss: 0.8274 (0.8356) time: 0.1817 data: 0.0931 max mem: 9390 +Train: [70] [ 200/6250] eta: 0:22:04 lr: 0.000028 grad: 0.1088 (0.1285) loss: 0.8211 (0.8248) time: 0.1570 data: 0.0490 max mem: 9390 +Train: [70] [ 300/6250] eta: 0:20:31 lr: 0.000028 grad: 0.1139 (0.1278) loss: 0.8051 (0.8210) time: 0.1683 data: 0.0731 max mem: 9390 +Train: [70] [ 400/6250] eta: 0:19:30 lr: 0.000028 grad: 0.1158 (0.1262) loss: 0.8118 (0.8185) time: 0.1874 data: 0.0969 max mem: 9390 +Train: [70] [ 500/6250] eta: 0:18:47 lr: 0.000028 grad: 0.1163 (0.1255) loss: 0.8087 (0.8169) time: 0.1745 data: 0.0752 max mem: 9390 +Train: [70] [ 600/6250] eta: 0:18:30 lr: 0.000028 grad: 0.1105 (0.1240) loss: 0.8151 (0.8165) time: 0.2542 data: 0.1743 max mem: 9390 +Train: [70] [ 700/6250] eta: 0:17:45 lr: 0.000028 grad: 0.1116 (0.1224) loss: 0.8188 (0.8165) time: 0.1440 data: 0.0518 max mem: 9390 +Train: [70] [ 800/6250] eta: 0:17:18 lr: 0.000028 grad: 0.1124 (0.1212) loss: 0.8197 (0.8164) time: 0.1777 data: 0.0935 max mem: 9390 +Train: [70] [ 900/6250] eta: 0:16:44 lr: 0.000028 grad: 0.1139 (0.1206) loss: 0.8181 (0.8166) time: 0.1566 data: 0.0479 max mem: 9390 +Train: [70] [1000/6250] eta: 0:16:08 lr: 0.000028 grad: 0.1093 (0.1199) loss: 0.8187 (0.8167) time: 0.1479 data: 0.0670 max mem: 9390 +Train: [70] [1100/6250] eta: 0:15:38 lr: 0.000028 grad: 0.1037 (0.1191) loss: 0.8242 (0.8168) time: 0.1496 data: 0.0735 max mem: 9390 +Train: [70] [1200/6250] eta: 0:15:17 lr: 0.000028 grad: 0.1111 (0.1184) loss: 0.8194 (0.8168) time: 0.2539 data: 0.1637 max mem: 9390 +Train: [70] [1300/6250] eta: 0:14:45 lr: 0.000028 grad: 0.1151 (0.1179) loss: 0.8110 (0.8168) time: 0.1475 data: 0.0526 max mem: 9390 +Train: [70] [1400/6250] eta: 0:14:23 lr: 0.000028 grad: 0.1119 (0.1177) loss: 0.8089 (0.8167) time: 0.1660 data: 0.0758 max mem: 9390 +Train: [70] [1500/6250] eta: 0:13:58 lr: 0.000028 grad: 0.1034 (0.1173) loss: 0.8164 (0.8167) time: 0.1402 data: 0.0499 max mem: 9390 +Train: [70] [1600/6250] eta: 0:13:33 lr: 0.000028 grad: 0.1054 (0.1170) loss: 0.8175 (0.8166) time: 0.1507 data: 0.0674 max mem: 9390 +Train: [70] [1700/6250] eta: 0:13:15 lr: 0.000028 grad: 0.1080 (0.1168) loss: 0.8161 (0.8164) time: 0.2401 data: 0.1617 max mem: 9390 +Train: [70] [1800/6250] eta: 0:12:53 lr: 0.000028 grad: 0.1117 (0.1168) loss: 0.8119 (0.8161) time: 0.2137 data: 0.1341 max mem: 9390 +Train: [70] [1900/6250] eta: 0:12:29 lr: 0.000028 grad: 0.1131 (0.1167) loss: 0.8145 (0.8162) time: 0.1298 data: 0.0404 max mem: 9390 +Train: [70] [2000/6250] eta: 0:12:09 lr: 0.000028 grad: 0.1192 (0.1167) loss: 0.8115 (0.8160) time: 0.1762 data: 0.0937 max mem: 9390 +Train: [70] [2100/6250] eta: 0:11:48 lr: 0.000028 grad: 0.1085 (0.1166) loss: 0.8142 (0.8159) time: 0.1737 data: 0.0882 max mem: 9390 +Train: [70] [2200/6250] eta: 0:11:30 lr: 0.000028 grad: 0.1240 (0.1166) loss: 0.8070 (0.8157) time: 0.1392 data: 0.0567 max mem: 9390 +Train: [70] [2300/6250] eta: 0:11:13 lr: 0.000028 grad: 0.1156 (0.1167) loss: 0.8146 (0.8155) time: 0.1622 data: 0.0753 max mem: 9390 +Train: [70] [2400/6250] eta: 0:10:53 lr: 0.000028 grad: 0.1107 (0.1165) loss: 0.8159 (0.8154) time: 0.1735 data: 0.0881 max mem: 9390 +Train: [70] [2500/6250] eta: 0:10:34 lr: 0.000028 grad: 0.1140 (0.1165) loss: 0.8128 (0.8153) time: 0.1665 data: 0.0818 max mem: 9390 +Train: [70] [2600/6250] eta: 0:10:19 lr: 0.000028 grad: 0.1118 (0.1165) loss: 0.8200 (0.8151) time: 0.2718 data: 0.1572 max mem: 9390 +Train: [70] [2700/6250] eta: 0:10:02 lr: 0.000028 grad: 0.1157 (0.1165) loss: 0.8103 (0.8151) time: 0.1796 data: 0.0829 max mem: 9390 +Train: [70] [2800/6250] eta: 0:09:44 lr: 0.000028 grad: 0.1140 (0.1164) loss: 0.8169 (0.8150) time: 0.1524 data: 0.0685 max mem: 9390 +Train: [70] [2900/6250] eta: 0:09:32 lr: 0.000028 grad: 0.1157 (0.1163) loss: 0.8129 (0.8150) time: 0.1024 data: 0.0002 max mem: 9390 +Train: [70] [3000/6250] eta: 0:09:13 lr: 0.000027 grad: 0.1165 (0.1163) loss: 0.8109 (0.8149) time: 0.1330 data: 0.0484 max mem: 9390 +Train: [70] [3100/6250] eta: 0:08:54 lr: 0.000027 grad: 0.1115 (0.1163) loss: 0.8169 (0.8149) time: 0.1906 data: 0.1063 max mem: 9390 +Train: [70] [3200/6250] eta: 0:08:35 lr: 0.000027 grad: 0.1133 (0.1163) loss: 0.8193 (0.8149) time: 0.1372 data: 0.0575 max mem: 9390 +Train: [70] [3300/6250] eta: 0:08:17 lr: 0.000027 grad: 0.1112 (0.1162) loss: 0.8115 (0.8149) time: 0.1563 data: 0.0748 max mem: 9390 +Train: [70] [3400/6250] eta: 0:07:58 lr: 0.000027 grad: 0.1256 (0.1163) loss: 0.8119 (0.8149) time: 0.1757 data: 0.0967 max mem: 9390 +Train: [70] [3500/6250] eta: 0:07:41 lr: 0.000027 grad: 0.1090 (0.1163) loss: 0.8155 (0.8149) time: 0.1508 data: 0.0646 max mem: 9390 +Train: [70] [3600/6250] eta: 0:07:23 lr: 0.000027 grad: 0.1119 (0.1163) loss: 0.8180 (0.8149) time: 0.1586 data: 0.0699 max mem: 9390 +Train: [70] [3700/6250] eta: 0:07:06 lr: 0.000027 grad: 0.1097 (0.1163) loss: 0.8143 (0.8149) time: 0.1609 data: 0.0800 max mem: 9390 +Train: [70] [3800/6250] eta: 0:06:48 lr: 0.000027 grad: 0.1075 (0.1163) loss: 0.8171 (0.8149) time: 0.1609 data: 0.0736 max mem: 9390 +Train: [70] [3900/6250] eta: 0:06:31 lr: 0.000027 grad: 0.1194 (0.1164) loss: 0.8131 (0.8148) time: 0.1580 data: 0.0752 max mem: 9390 +Train: [70] [4000/6250] eta: 0:06:13 lr: 0.000027 grad: 0.1076 (0.1163) loss: 0.8137 (0.8148) time: 0.1483 data: 0.0644 max mem: 9390 +Train: [70] [4100/6250] eta: 0:05:56 lr: 0.000027 grad: 0.1082 (0.1163) loss: 0.8153 (0.8148) time: 0.1729 data: 0.0929 max mem: 9390 +Train: [70] [4200/6250] eta: 0:05:39 lr: 0.000027 grad: 0.1132 (0.1163) loss: 0.8144 (0.8148) time: 0.1713 data: 0.0882 max mem: 9390 +Train: [70] [4300/6250] eta: 0:05:23 lr: 0.000027 grad: 0.1092 (0.1163) loss: 0.8190 (0.8148) time: 0.1811 data: 0.0849 max mem: 9390 +Train: [70] [4400/6250] eta: 0:05:08 lr: 0.000027 grad: 0.1119 (0.1164) loss: 0.8096 (0.8147) time: 0.3219 data: 0.2266 max mem: 9390 +Train: [70] [4500/6250] eta: 0:04:50 lr: 0.000027 grad: 0.1128 (0.1164) loss: 0.8141 (0.8146) time: 0.1385 data: 0.0457 max mem: 9390 +Train: [70] [4600/6250] eta: 0:04:34 lr: 0.000027 grad: 0.1174 (0.1164) loss: 0.8176 (0.8146) time: 0.1848 data: 0.0997 max mem: 9390 +Train: [70] [4700/6250] eta: 0:04:17 lr: 0.000027 grad: 0.1099 (0.1164) loss: 0.8090 (0.8146) time: 0.2412 data: 0.1649 max mem: 9390 +Train: [70] [4800/6250] eta: 0:04:00 lr: 0.000027 grad: 0.1191 (0.1164) loss: 0.8129 (0.8145) time: 0.1497 data: 0.0680 max mem: 9390 +Train: [70] [4900/6250] eta: 0:03:43 lr: 0.000027 grad: 0.1173 (0.1165) loss: 0.8174 (0.8145) time: 0.1553 data: 0.0734 max mem: 9390 +Train: [70] [5000/6250] eta: 0:03:27 lr: 0.000027 grad: 0.1146 (0.1165) loss: 0.8120 (0.8145) time: 0.1605 data: 0.0794 max mem: 9390 +Train: [70] [5100/6250] eta: 0:03:10 lr: 0.000027 grad: 0.1161 (0.1166) loss: 0.8158 (0.8145) time: 0.1783 data: 0.0877 max mem: 9390 +Train: [70] [5200/6250] eta: 0:02:54 lr: 0.000027 grad: 0.1105 (0.1166) loss: 0.8147 (0.8144) time: 0.1644 data: 0.0763 max mem: 9390 +Train: [70] [5300/6250] eta: 0:02:37 lr: 0.000027 grad: 0.1243 (0.1167) loss: 0.8142 (0.8144) time: 0.1502 data: 0.0655 max mem: 9390 +Train: [70] [5400/6250] eta: 0:02:21 lr: 0.000027 grad: 0.1203 (0.1167) loss: 0.8180 (0.8144) time: 0.1721 data: 0.0892 max mem: 9390 +Train: [70] [5500/6250] eta: 0:02:04 lr: 0.000027 grad: 0.1164 (0.1168) loss: 0.8083 (0.8143) time: 0.1666 data: 0.0786 max mem: 9390 +Train: [70] [5600/6250] eta: 0:01:47 lr: 0.000027 grad: 0.1198 (0.1169) loss: 0.8068 (0.8142) time: 0.1162 data: 0.0365 max mem: 9390 +Train: [70] [5700/6250] eta: 0:01:31 lr: 0.000027 grad: 0.1197 (0.1170) loss: 0.8107 (0.8141) time: 0.1540 data: 0.0718 max mem: 9390 +Train: [70] [5800/6250] eta: 0:01:14 lr: 0.000027 grad: 0.1161 (0.1171) loss: 0.8081 (0.8140) time: 0.1270 data: 0.0401 max mem: 9390 +Train: [70] [5900/6250] eta: 0:00:58 lr: 0.000027 grad: 0.1162 (0.1171) loss: 0.8072 (0.8139) time: 0.1921 data: 0.1042 max mem: 9390 +Train: [70] [6000/6250] eta: 0:00:41 lr: 0.000027 grad: 0.1142 (0.1172) loss: 0.8068 (0.8139) time: 0.1433 data: 0.0524 max mem: 9390 +Train: [70] [6100/6250] eta: 0:00:24 lr: 0.000027 grad: 0.1119 (0.1172) loss: 0.8083 (0.8138) time: 0.1640 data: 0.0677 max mem: 9390 +Train: [70] [6200/6250] eta: 0:00:08 lr: 0.000027 grad: 0.1091 (0.1172) loss: 0.8222 (0.8138) time: 0.1496 data: 0.0580 max mem: 9390 +Train: [70] [6249/6250] eta: 0:00:00 lr: 0.000027 grad: 0.1095 (0.1172) loss: 0.8177 (0.8138) time: 0.1889 data: 0.0970 max mem: 9390 +Train: [70] Total time: 0:17:21 (0.1666 s / it) +Averaged stats: lr: 0.000027 grad: 0.1095 (0.1172) loss: 0.8177 (0.8138) +Eval (hcp-train-subset): [70] [ 0/62] eta: 0:05:28 loss: 0.8368 (0.8368) time: 5.3011 data: 5.2707 max mem: 9390 +Eval (hcp-train-subset): [70] [61/62] eta: 0:00:00 loss: 0.8288 (0.8301) time: 0.1239 data: 0.0991 max mem: 9390 +Eval (hcp-train-subset): [70] Total time: 0:00:13 (0.2150 s / it) +Averaged stats (hcp-train-subset): loss: 0.8288 (0.8301) +Eval (hcp-val): [70] [ 0/62] eta: 0:05:22 loss: 0.8329 (0.8329) time: 5.2084 data: 5.1780 max mem: 9390 +Eval (hcp-val): [70] [61/62] eta: 0:00:00 loss: 0.8298 (0.8324) time: 0.1426 data: 0.1175 max mem: 9390 +Eval (hcp-val): [70] Total time: 0:00:13 (0.2225 s / it) +Averaged stats (hcp-val): loss: 0.8298 (0.8324) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +Train: [71] [ 0/6250] eta: 7:08:53 lr: 0.000027 grad: 0.0741 (0.0741) loss: 0.8676 (0.8676) time: 4.1173 data: 3.7996 max mem: 9390 +Train: [71] [ 100/6250] eta: 0:22:59 lr: 0.000027 grad: 0.1218 (0.1310) loss: 0.8357 (0.8373) time: 0.1806 data: 0.0869 max mem: 9390 +Train: [71] [ 200/6250] eta: 0:20:57 lr: 0.000027 grad: 0.1024 (0.1226) loss: 0.8268 (0.8346) time: 0.2250 data: 0.1432 max mem: 9390 +Train: [71] [ 300/6250] eta: 0:19:18 lr: 0.000027 grad: 0.1105 (0.1202) loss: 0.8230 (0.8309) time: 0.1563 data: 0.0500 max mem: 9390 +Train: [71] [ 400/6250] eta: 0:18:12 lr: 0.000026 grad: 0.0998 (0.1178) loss: 0.8202 (0.8288) time: 0.1283 data: 0.0401 max mem: 9390 +Train: [71] [ 500/6250] eta: 0:18:04 lr: 0.000026 grad: 0.1083 (0.1162) loss: 0.8122 (0.8274) time: 0.1447 data: 0.0594 max mem: 9390 +Train: [71] [ 600/6250] eta: 0:17:24 lr: 0.000026 grad: 0.1078 (0.1158) loss: 0.8249 (0.8259) time: 0.1465 data: 0.0417 max mem: 9390 +Train: [71] [ 700/6250] eta: 0:16:52 lr: 0.000026 grad: 0.1067 (0.1157) loss: 0.8147 (0.8247) time: 0.1216 data: 0.0391 max mem: 9390 +Train: [71] [ 800/6250] eta: 0:16:27 lr: 0.000026 grad: 0.1122 (0.1157) loss: 0.8226 (0.8242) time: 0.1858 data: 0.1023 max mem: 9390 +Train: [71] [ 900/6250] eta: 0:16:09 lr: 0.000026 grad: 0.1149 (0.1154) loss: 0.8244 (0.8237) time: 0.1658 data: 0.0543 max mem: 9390 +Train: [71] [1000/6250] eta: 0:15:46 lr: 0.000026 grad: 0.1043 (0.1151) loss: 0.8252 (0.8232) time: 0.1747 data: 0.0902 max mem: 9390 +Train: [71] [1100/6250] eta: 0:15:14 lr: 0.000026 grad: 0.1154 (0.1151) loss: 0.8107 (0.8225) time: 0.1410 data: 0.0622 max mem: 9390 +Train: [71] [1200/6250] eta: 0:14:49 lr: 0.000026 grad: 0.1089 (0.1151) loss: 0.8222 (0.8221) time: 0.1760 data: 0.0878 max mem: 9390 +Train: [71] [1300/6250] eta: 0:14:23 lr: 0.000026 grad: 0.1080 (0.1151) loss: 0.8209 (0.8217) time: 0.1371 data: 0.0536 max mem: 9390 +Train: [71] [1400/6250] eta: 0:14:09 lr: 0.000026 grad: 0.1047 (0.1149) loss: 0.8244 (0.8213) time: 0.0968 data: 0.0002 max mem: 9390 +Train: [71] [1500/6250] eta: 0:13:42 lr: 0.000026 grad: 0.1214 (0.1150) loss: 0.8142 (0.8209) time: 0.1570 data: 0.0756 max mem: 9390 +Train: [71] [1600/6250] eta: 0:13:22 lr: 0.000026 grad: 0.1123 (0.1152) loss: 0.8145 (0.8205) time: 0.1511 data: 0.0741 max mem: 9390 +Train: [71] [1700/6250] eta: 0:13:01 lr: 0.000026 grad: 0.1156 (0.1153) loss: 0.8139 (0.8202) time: 0.1008 data: 0.0068 max mem: 9390 +Train: [71] [1800/6250] eta: 0:12:42 lr: 0.000026 grad: 0.1176 (0.1154) loss: 0.8128 (0.8199) time: 0.1856 data: 0.1040 max mem: 9390 +Train: [71] [1900/6250] eta: 0:12:22 lr: 0.000026 grad: 0.1094 (0.1153) loss: 0.8147 (0.8198) time: 0.1432 data: 0.0623 max mem: 9390 +Train: [71] [2000/6250] eta: 0:12:05 lr: 0.000026 grad: 0.1129 (0.1152) loss: 0.8185 (0.8196) time: 0.1746 data: 0.0913 max mem: 9390 +Train: [71] [2100/6250] eta: 0:11:49 lr: 0.000026 grad: 0.1123 (0.1152) loss: 0.8162 (0.8193) time: 0.2261 data: 0.1465 max mem: 9390 +Train: [71] [2200/6250] eta: 0:11:30 lr: 0.000026 grad: 0.1108 (0.1152) loss: 0.8173 (0.8190) time: 0.1640 data: 0.0771 max mem: 9390 +Train: [71] [2300/6250] eta: 0:11:11 lr: 0.000026 grad: 0.1143 (0.1154) loss: 0.8134 (0.8188) time: 0.1493 data: 0.0719 max mem: 9390 +Train: [71] [2400/6250] eta: 0:10:52 lr: 0.000026 grad: 0.1132 (0.1154) loss: 0.8118 (0.8186) time: 0.1523 data: 0.0692 max mem: 9390 +Train: [71] [2500/6250] eta: 0:10:34 lr: 0.000026 grad: 0.1108 (0.1155) loss: 0.8197 (0.8183) time: 0.1407 data: 0.0594 max mem: 9390 +Train: [71] [2600/6250] eta: 0:10:18 lr: 0.000026 grad: 0.1087 (0.1154) loss: 0.8142 (0.8181) time: 0.2178 data: 0.1322 max mem: 9390 +Train: [71] [2700/6250] eta: 0:10:02 lr: 0.000026 grad: 0.1141 (0.1153) loss: 0.8183 (0.8179) time: 0.2609 data: 0.1724 max mem: 9390 +Train: [71] [2800/6250] eta: 0:09:43 lr: 0.000026 grad: 0.1178 (0.1153) loss: 0.8126 (0.8177) time: 0.1338 data: 0.0407 max mem: 9390 +Train: [71] [2900/6250] eta: 0:09:30 lr: 0.000026 grad: 0.1134 (0.1154) loss: 0.8142 (0.8175) time: 0.3257 data: 0.2391 max mem: 9390 +Train: [71] [3000/6250] eta: 0:09:12 lr: 0.000026 grad: 0.1063 (0.1154) loss: 0.8144 (0.8173) time: 0.1762 data: 0.0858 max mem: 9390 +Train: [71] [3100/6250] eta: 0:09:01 lr: 0.000026 grad: 0.1103 (0.1155) loss: 0.8122 (0.8171) time: 0.0922 data: 0.0002 max mem: 9390 +Train: [71] [3200/6250] eta: 0:08:42 lr: 0.000026 grad: 0.1127 (0.1156) loss: 0.8154 (0.8169) time: 0.1169 data: 0.0309 max mem: 9390 +Train: [71] [3300/6250] eta: 0:08:23 lr: 0.000026 grad: 0.1136 (0.1156) loss: 0.8091 (0.8168) time: 0.1062 data: 0.0203 max mem: 9390 +Train: [71] [3400/6250] eta: 0:08:06 lr: 0.000026 grad: 0.1182 (0.1157) loss: 0.8118 (0.8166) time: 0.1357 data: 0.0531 max mem: 9390 +Train: [71] [3500/6250] eta: 0:07:48 lr: 0.000026 grad: 0.1079 (0.1156) loss: 0.8143 (0.8165) time: 0.1669 data: 0.0882 max mem: 9390 +Train: [71] [3600/6250] eta: 0:07:30 lr: 0.000026 grad: 0.1073 (0.1155) loss: 0.8179 (0.8164) time: 0.1568 data: 0.0779 max mem: 9390 +Train: [71] [3700/6250] eta: 0:07:12 lr: 0.000026 grad: 0.1076 (0.1155) loss: 0.8060 (0.8163) time: 0.1729 data: 0.0896 max mem: 9390 +Train: [71] [3800/6250] eta: 0:06:54 lr: 0.000026 grad: 0.1173 (0.1155) loss: 0.8150 (0.8163) time: 0.1610 data: 0.0789 max mem: 9390 +Train: [71] [3900/6250] eta: 0:06:37 lr: 0.000026 grad: 0.1170 (0.1156) loss: 0.8125 (0.8161) time: 0.1682 data: 0.0816 max mem: 9390 +Train: [71] [4000/6250] eta: 0:06:19 lr: 0.000026 grad: 0.1136 (0.1156) loss: 0.8146 (0.8161) time: 0.1455 data: 0.0616 max mem: 9390 +Train: [71] [4100/6250] eta: 0:06:02 lr: 0.000026 grad: 0.1139 (0.1156) loss: 0.8080 (0.8160) time: 0.1569 data: 0.0734 max mem: 9390 +Train: [71] [4200/6250] eta: 0:05:44 lr: 0.000025 grad: 0.1117 (0.1155) loss: 0.8159 (0.8160) time: 0.1267 data: 0.0384 max mem: 9390 +Train: [71] [4300/6250] eta: 0:05:27 lr: 0.000025 grad: 0.1153 (0.1154) loss: 0.8134 (0.8159) time: 0.1692 data: 0.0759 max mem: 9390 +Train: [71] [4400/6250] eta: 0:05:10 lr: 0.000025 grad: 0.1139 (0.1154) loss: 0.8180 (0.8159) time: 0.1446 data: 0.0542 max mem: 9390 +Train: [71] [4500/6250] eta: 0:04:53 lr: 0.000025 grad: 0.1123 (0.1154) loss: 0.8138 (0.8158) time: 0.1903 data: 0.1056 max mem: 9390 +Train: [71] [4600/6250] eta: 0:04:36 lr: 0.000025 grad: 0.1069 (0.1154) loss: 0.8152 (0.8157) time: 0.1990 data: 0.1180 max mem: 9390 +Train: [71] [4700/6250] eta: 0:04:19 lr: 0.000025 grad: 0.1109 (0.1154) loss: 0.8154 (0.8156) time: 0.1506 data: 0.0700 max mem: 9390 +Train: [71] [4800/6250] eta: 0:04:02 lr: 0.000025 grad: 0.1087 (0.1154) loss: 0.8147 (0.8155) time: 0.1998 data: 0.1153 max mem: 9390 +Train: [71] [4900/6250] eta: 0:03:45 lr: 0.000025 grad: 0.1128 (0.1154) loss: 0.8125 (0.8155) time: 0.1636 data: 0.0791 max mem: 9390 +Train: [71] [5000/6250] eta: 0:03:28 lr: 0.000025 grad: 0.1140 (0.1154) loss: 0.8054 (0.8154) time: 0.1572 data: 0.0768 max mem: 9390 +Train: [71] [5100/6250] eta: 0:03:11 lr: 0.000025 grad: 0.1171 (0.1155) loss: 0.8157 (0.8153) time: 0.1573 data: 0.0766 max mem: 9390 +Train: [71] [5200/6250] eta: 0:02:54 lr: 0.000025 grad: 0.1083 (0.1155) loss: 0.8090 (0.8152) time: 0.2339 data: 0.1350 max mem: 9390 +Train: [71] [5300/6250] eta: 0:02:37 lr: 0.000025 grad: 0.1142 (0.1156) loss: 0.8157 (0.8152) time: 0.1145 data: 0.0311 max mem: 9390 +Train: [71] [5400/6250] eta: 0:02:21 lr: 0.000025 grad: 0.1149 (0.1156) loss: 0.8149 (0.8151) time: 0.2385 data: 0.1468 max mem: 9390 +Train: [71] [5500/6250] eta: 0:02:04 lr: 0.000025 grad: 0.1148 (0.1157) loss: 0.8161 (0.8151) time: 0.1608 data: 0.0705 max mem: 9390 +Train: [71] [5600/6250] eta: 0:01:47 lr: 0.000025 grad: 0.1127 (0.1157) loss: 0.8136 (0.8151) time: 0.1637 data: 0.0748 max mem: 9390 +Train: [71] [5700/6250] eta: 0:01:31 lr: 0.000025 grad: 0.1163 (0.1157) loss: 0.8110 (0.8151) time: 0.1569 data: 0.0755 max mem: 9390 +Train: [71] [5800/6250] eta: 0:01:14 lr: 0.000025 grad: 0.1236 (0.1157) loss: 0.8115 (0.8151) time: 0.1775 data: 0.1039 max mem: 9390 +Train: [71] [5900/6250] eta: 0:00:58 lr: 0.000025 grad: 0.1160 (0.1157) loss: 0.8117 (0.8151) time: 0.1614 data: 0.0736 max mem: 9390 +Train: [71] [6000/6250] eta: 0:00:41 lr: 0.000025 grad: 0.1096 (0.1157) loss: 0.8094 (0.8151) time: 0.1927 data: 0.1097 max mem: 9390 +Train: [71] [6100/6250] eta: 0:00:24 lr: 0.000025 grad: 0.1187 (0.1157) loss: 0.8092 (0.8151) time: 0.1881 data: 0.0871 max mem: 9390 +Train: [71] [6200/6250] eta: 0:00:08 lr: 0.000025 grad: 0.1213 (0.1158) loss: 0.8107 (0.8150) time: 0.2035 data: 0.1096 max mem: 9390 +Train: [71] [6249/6250] eta: 0:00:00 lr: 0.000025 grad: 0.1213 (0.1158) loss: 0.8087 (0.8150) time: 0.2130 data: 0.1260 max mem: 9390 +Train: [71] Total time: 0:17:34 (0.1687 s / it) +Averaged stats: lr: 0.000025 grad: 0.1213 (0.1158) loss: 0.8087 (0.8150) +Eval (hcp-train-subset): [71] [ 0/62] eta: 0:05:17 loss: 0.8455 (0.8455) time: 5.1191 data: 5.0557 max mem: 9390 +Eval (hcp-train-subset): [71] [61/62] eta: 0:00:00 loss: 0.8299 (0.8313) time: 0.1170 data: 0.0919 max mem: 9390 +Eval (hcp-train-subset): [71] Total time: 0:00:15 (0.2558 s / it) +Averaged stats (hcp-train-subset): loss: 0.8299 (0.8313) +Eval (hcp-val): [71] [ 0/62] eta: 0:03:24 loss: 0.8310 (0.8310) time: 3.3059 data: 3.2435 max mem: 9390 +Eval (hcp-val): [71] [61/62] eta: 0:00:00 loss: 0.8311 (0.8322) time: 0.1508 data: 0.1254 max mem: 9390 +Eval (hcp-val): [71] Total time: 0:00:14 (0.2334 s / it) +Averaged stats (hcp-val): loss: 0.8311 (0.8322) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +Train: [72] [ 0/6250] eta: 11:48:42 lr: 0.000025 grad: 0.0984 (0.0984) loss: 0.8390 (0.8390) time: 6.8036 data: 6.6972 max mem: 9390 +Train: [72] [ 100/6250] eta: 0:24:37 lr: 0.000025 grad: 0.1174 (0.1376) loss: 0.8163 (0.8265) time: 0.1855 data: 0.0742 max mem: 9390 +Train: [72] [ 200/6250] eta: 0:21:25 lr: 0.000025 grad: 0.1199 (0.1333) loss: 0.8067 (0.8199) time: 0.1580 data: 0.0533 max mem: 9390 +Train: [72] [ 300/6250] eta: 0:19:56 lr: 0.000025 grad: 0.1108 (0.1291) loss: 0.8184 (0.8169) time: 0.2113 data: 0.1149 max mem: 9390 +Train: [72] [ 400/6250] eta: 0:18:56 lr: 0.000025 grad: 0.1040 (0.1254) loss: 0.8216 (0.8174) time: 0.1717 data: 0.0847 max mem: 9390 +Train: [72] [ 500/6250] eta: 0:17:58 lr: 0.000025 grad: 0.1061 (0.1233) loss: 0.8230 (0.8175) time: 0.1564 data: 0.0698 max mem: 9390 +Train: [72] [ 600/6250] eta: 0:17:30 lr: 0.000025 grad: 0.1071 (0.1217) loss: 0.8146 (0.8175) time: 0.1929 data: 0.1044 max mem: 9390 +Train: [72] [ 700/6250] eta: 0:17:02 lr: 0.000025 grad: 0.1074 (0.1205) loss: 0.8169 (0.8174) time: 0.1227 data: 0.0174 max mem: 9390 +Train: [72] [ 800/6250] eta: 0:16:29 lr: 0.000025 grad: 0.1072 (0.1194) loss: 0.8143 (0.8173) time: 0.1611 data: 0.0813 max mem: 9390 +Train: [72] [ 900/6250] eta: 0:16:06 lr: 0.000025 grad: 0.1080 (0.1190) loss: 0.8163 (0.8172) time: 0.1166 data: 0.0111 max mem: 9390 +Train: [72] [1000/6250] eta: 0:15:47 lr: 0.000025 grad: 0.1180 (0.1188) loss: 0.8152 (0.8170) time: 0.1533 data: 0.0697 max mem: 9390 +Train: [72] [1100/6250] eta: 0:15:17 lr: 0.000025 grad: 0.1126 (0.1188) loss: 0.8177 (0.8167) time: 0.1303 data: 0.0419 max mem: 9390 +Train: [72] [1200/6250] eta: 0:14:56 lr: 0.000025 grad: 0.1114 (0.1186) loss: 0.8146 (0.8165) time: 0.0990 data: 0.0003 max mem: 9390 +Train: [72] [1300/6250] eta: 0:14:35 lr: 0.000025 grad: 0.1167 (0.1185) loss: 0.8088 (0.8162) time: 0.1684 data: 0.0774 max mem: 9390 +Train: [72] [1400/6250] eta: 0:14:17 lr: 0.000025 grad: 0.1144 (0.1184) loss: 0.8123 (0.8161) time: 0.1907 data: 0.1088 max mem: 9390 +Train: [72] [1500/6250] eta: 0:13:59 lr: 0.000025 grad: 0.1135 (0.1184) loss: 0.8105 (0.8158) time: 0.1370 data: 0.0002 max mem: 9390 +Train: [72] [1600/6250] eta: 0:13:43 lr: 0.000025 grad: 0.1186 (0.1187) loss: 0.8086 (0.8155) time: 0.1214 data: 0.0285 max mem: 9390 +Train: [72] [1700/6250] eta: 0:13:22 lr: 0.000024 grad: 0.1137 (0.1187) loss: 0.8175 (0.8154) time: 0.2350 data: 0.1497 max mem: 9390 +Train: [72] [1800/6250] eta: 0:12:57 lr: 0.000024 grad: 0.1120 (0.1187) loss: 0.8178 (0.8151) time: 0.1409 data: 0.0552 max mem: 9390 +Train: [72] [1900/6250] eta: 0:12:42 lr: 0.000024 grad: 0.1158 (0.1188) loss: 0.8168 (0.8150) time: 0.2466 data: 0.1540 max mem: 9390 +Train: [72] [2000/6250] eta: 0:12:16 lr: 0.000024 grad: 0.1173 (0.1187) loss: 0.8132 (0.8149) time: 0.1387 data: 0.0473 max mem: 9390 +Train: [72] [2100/6250] eta: 0:11:56 lr: 0.000024 grad: 0.1183 (0.1187) loss: 0.8137 (0.8150) time: 0.1936 data: 0.1103 max mem: 9390 +Train: [72] [2200/6250] eta: 0:11:35 lr: 0.000024 grad: 0.1113 (0.1189) loss: 0.8079 (0.8148) time: 0.1450 data: 0.0655 max mem: 9390 +Train: [72] [2300/6250] eta: 0:11:15 lr: 0.000024 grad: 0.1195 (0.1189) loss: 0.8107 (0.8147) time: 0.1604 data: 0.0763 max mem: 9390 +Train: [72] [2400/6250] eta: 0:11:05 lr: 0.000024 grad: 0.1154 (0.1189) loss: 0.8141 (0.8146) time: 0.4634 data: 0.3740 max mem: 9390 +Train: [72] [2500/6250] eta: 0:10:46 lr: 0.000024 grad: 0.1135 (0.1189) loss: 0.8073 (0.8146) time: 0.1441 data: 0.0530 max mem: 9390 +Train: [72] [2600/6250] eta: 0:10:26 lr: 0.000024 grad: 0.1190 (0.1189) loss: 0.8155 (0.8145) time: 0.1478 data: 0.0645 max mem: 9390 +Train: [72] [2700/6250] eta: 0:10:07 lr: 0.000024 grad: 0.1198 (0.1188) loss: 0.8088 (0.8144) time: 0.1651 data: 0.0714 max mem: 9390 +Train: [72] [2800/6250] eta: 0:09:48 lr: 0.000024 grad: 0.1178 (0.1188) loss: 0.8148 (0.8143) time: 0.1383 data: 0.0517 max mem: 9390 +Train: [72] [2900/6250] eta: 0:09:29 lr: 0.000024 grad: 0.1237 (0.1188) loss: 0.8092 (0.8142) time: 0.1462 data: 0.0614 max mem: 9390 +Train: [72] [3000/6250] eta: 0:09:11 lr: 0.000024 grad: 0.1179 (0.1188) loss: 0.8177 (0.8141) time: 0.1631 data: 0.0793 max mem: 9390 +Train: [72] [3100/6250] eta: 0:08:59 lr: 0.000024 grad: 0.1151 (0.1188) loss: 0.8109 (0.8140) time: 0.3156 data: 0.2342 max mem: 9390 +Train: [72] [3200/6250] eta: 0:08:42 lr: 0.000024 grad: 0.1205 (0.1187) loss: 0.8078 (0.8140) time: 0.2666 data: 0.1573 max mem: 9390 +Train: [72] [3300/6250] eta: 0:08:23 lr: 0.000024 grad: 0.1123 (0.1188) loss: 0.8111 (0.8139) time: 0.1705 data: 0.0842 max mem: 9390 +Train: [72] [3400/6250] eta: 0:08:10 lr: 0.000024 grad: 0.1176 (0.1188) loss: 0.8123 (0.8139) time: 0.1140 data: 0.0266 max mem: 9390 +Train: [72] [3500/6250] eta: 0:07:51 lr: 0.000024 grad: 0.1231 (0.1188) loss: 0.8067 (0.8139) time: 0.1256 data: 0.0463 max mem: 9390 +Train: [72] [3600/6250] eta: 0:07:33 lr: 0.000024 grad: 0.1173 (0.1189) loss: 0.8160 (0.8139) time: 0.1625 data: 0.0845 max mem: 9390 +Train: [72] [3700/6250] eta: 0:07:15 lr: 0.000024 grad: 0.1197 (0.1191) loss: 0.8119 (0.8139) time: 0.1390 data: 0.0613 max mem: 9390 +Train: [72] [3800/6250] eta: 0:06:57 lr: 0.000024 grad: 0.1156 (0.1192) loss: 0.8159 (0.8139) time: 0.1284 data: 0.0403 max mem: 9390 +Train: [72] [3900/6250] eta: 0:06:40 lr: 0.000024 grad: 0.1135 (0.1192) loss: 0.8182 (0.8140) time: 0.1391 data: 0.0540 max mem: 9390 +Train: [72] [4000/6250] eta: 0:06:22 lr: 0.000024 grad: 0.1089 (0.1192) loss: 0.8116 (0.8140) time: 0.1578 data: 0.0715 max mem: 9390 +Train: [72] [4100/6250] eta: 0:06:05 lr: 0.000024 grad: 0.1164 (0.1191) loss: 0.8127 (0.8141) time: 0.1460 data: 0.0580 max mem: 9390 +Train: [72] [4200/6250] eta: 0:05:47 lr: 0.000024 grad: 0.1116 (0.1190) loss: 0.8252 (0.8141) time: 0.1574 data: 0.0776 max mem: 9390 +Train: [72] [4300/6250] eta: 0:05:30 lr: 0.000024 grad: 0.1154 (0.1190) loss: 0.8171 (0.8142) time: 0.1786 data: 0.0954 max mem: 9390 +Train: [72] [4400/6250] eta: 0:05:12 lr: 0.000024 grad: 0.1090 (0.1189) loss: 0.8259 (0.8142) time: 0.1641 data: 0.0826 max mem: 9390 +Train: [72] [4500/6250] eta: 0:04:55 lr: 0.000024 grad: 0.1151 (0.1189) loss: 0.8185 (0.8143) time: 0.1679 data: 0.0925 max mem: 9390 +Train: [72] [4600/6250] eta: 0:04:38 lr: 0.000024 grad: 0.1204 (0.1189) loss: 0.8132 (0.8143) time: 0.1243 data: 0.0295 max mem: 9390 +Train: [72] [4700/6250] eta: 0:04:21 lr: 0.000024 grad: 0.1087 (0.1189) loss: 0.8183 (0.8143) time: 0.1867 data: 0.1064 max mem: 9390 +Train: [72] [4800/6250] eta: 0:04:05 lr: 0.000024 grad: 0.1149 (0.1189) loss: 0.8118 (0.8143) time: 0.1449 data: 0.0510 max mem: 9390 +Train: [72] [4900/6250] eta: 0:03:48 lr: 0.000024 grad: 0.1214 (0.1190) loss: 0.8112 (0.8143) time: 0.1122 data: 0.0239 max mem: 9390 +Train: [72] [5000/6250] eta: 0:03:31 lr: 0.000024 grad: 0.1196 (0.1190) loss: 0.8141 (0.8142) time: 0.2045 data: 0.1021 max mem: 9390 +Train: [72] [5100/6250] eta: 0:03:14 lr: 0.000024 grad: 0.1207 (0.1190) loss: 0.8152 (0.8142) time: 0.1805 data: 0.0834 max mem: 9390 +Train: [72] [5200/6250] eta: 0:02:57 lr: 0.000024 grad: 0.1195 (0.1191) loss: 0.8136 (0.8142) time: 0.2186 data: 0.1346 max mem: 9390 +Train: [72] [5300/6250] eta: 0:02:41 lr: 0.000024 grad: 0.1258 (0.1191) loss: 0.8084 (0.8142) time: 0.3549 data: 0.2730 max mem: 9390 +Train: [72] [5400/6250] eta: 0:02:24 lr: 0.000024 grad: 0.1193 (0.1192) loss: 0.8126 (0.8143) time: 0.1503 data: 0.0648 max mem: 9390 +Train: [72] [5500/6250] eta: 0:02:06 lr: 0.000023 grad: 0.1165 (0.1192) loss: 0.8183 (0.8143) time: 0.1527 data: 0.0645 max mem: 9390 +Train: [72] [5600/6250] eta: 0:01:49 lr: 0.000023 grad: 0.1085 (0.1192) loss: 0.8134 (0.8143) time: 0.1561 data: 0.0685 max mem: 9390 +Train: [72] [5700/6250] eta: 0:01:32 lr: 0.000023 grad: 0.1189 (0.1192) loss: 0.8139 (0.8143) time: 0.1851 data: 0.1016 max mem: 9390 +Train: [72] [5800/6250] eta: 0:01:15 lr: 0.000023 grad: 0.1169 (0.1192) loss: 0.8176 (0.8143) time: 0.1242 data: 0.0376 max mem: 9390 +Train: [72] [5900/6250] eta: 0:00:59 lr: 0.000023 grad: 0.1151 (0.1192) loss: 0.8118 (0.8143) time: 0.1416 data: 0.0440 max mem: 9390 +Train: [72] [6000/6250] eta: 0:00:42 lr: 0.000023 grad: 0.1120 (0.1192) loss: 0.8108 (0.8143) time: 0.1821 data: 0.0984 max mem: 9390 +Train: [72] [6100/6250] eta: 0:00:25 lr: 0.000023 grad: 0.1150 (0.1192) loss: 0.8176 (0.8143) time: 0.2197 data: 0.1369 max mem: 9390 +Train: [72] [6200/6250] eta: 0:00:08 lr: 0.000023 grad: 0.1121 (0.1192) loss: 0.8103 (0.8142) time: 0.2155 data: 0.1407 max mem: 9390 +Train: [72] [6249/6250] eta: 0:00:00 lr: 0.000023 grad: 0.1156 (0.1192) loss: 0.8091 (0.8142) time: 0.2290 data: 0.1481 max mem: 9390 +Train: [72] Total time: 0:17:40 (0.1697 s / it) +Averaged stats: lr: 0.000023 grad: 0.1156 (0.1192) loss: 0.8091 (0.8142) +Eval (hcp-train-subset): [72] [ 0/62] eta: 0:03:47 loss: 0.8366 (0.8366) time: 3.6669 data: 3.5910 max mem: 9390 +Eval (hcp-train-subset): [72] [61/62] eta: 0:00:00 loss: 0.8274 (0.8302) time: 0.0851 data: 0.0600 max mem: 9390 +Eval (hcp-train-subset): [72] Total time: 0:00:13 (0.2176 s / it) +Averaged stats (hcp-train-subset): loss: 0.8274 (0.8302) +Eval (hcp-val): [72] [ 0/62] eta: 0:03:59 loss: 0.8317 (0.8317) time: 3.8583 data: 3.7726 max mem: 9390 +Eval (hcp-val): [72] [61/62] eta: 0:00:00 loss: 0.8312 (0.8324) time: 0.1235 data: 0.0975 max mem: 9390 +Eval (hcp-val): [72] Total time: 0:00:13 (0.2132 s / it) +Averaged stats (hcp-val): loss: 0.8312 (0.8324) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +Train: [73] [ 0/6250] eta: 9:07:18 lr: 0.000023 grad: 0.1326 (0.1326) loss: 0.8404 (0.8404) time: 5.2541 data: 5.0848 max mem: 9390 +Train: [73] [ 100/6250] eta: 0:22:39 lr: 0.000023 grad: 0.1215 (0.1347) loss: 0.8285 (0.8367) time: 0.1664 data: 0.0528 max mem: 9390 +Train: [73] [ 200/6250] eta: 0:20:04 lr: 0.000023 grad: 0.1155 (0.1296) loss: 0.8337 (0.8340) time: 0.1563 data: 0.0389 max mem: 9390 +Train: [73] [ 300/6250] eta: 0:18:55 lr: 0.000023 grad: 0.1149 (0.1276) loss: 0.8237 (0.8307) time: 0.1732 data: 0.0742 max mem: 9390 +Train: [73] [ 400/6250] eta: 0:18:15 lr: 0.000023 grad: 0.1174 (0.1249) loss: 0.8247 (0.8284) time: 0.1942 data: 0.0998 max mem: 9390 +Train: [73] [ 500/6250] eta: 0:18:29 lr: 0.000023 grad: 0.1181 (0.1235) loss: 0.8226 (0.8272) time: 0.3224 data: 0.2103 max mem: 9390 +Train: [73] [ 600/6250] eta: 0:17:24 lr: 0.000023 grad: 0.1116 (0.1221) loss: 0.8232 (0.8262) time: 0.1564 data: 0.0505 max mem: 9390 +Train: [73] [ 700/6250] eta: 0:16:57 lr: 0.000023 grad: 0.1057 (0.1208) loss: 0.8245 (0.8256) time: 0.1805 data: 0.0888 max mem: 9390 +Train: [73] [ 800/6250] eta: 0:16:24 lr: 0.000023 grad: 0.1066 (0.1200) loss: 0.8246 (0.8250) time: 0.1551 data: 0.0710 max mem: 9390 +Train: [73] [ 900/6250] eta: 0:16:02 lr: 0.000023 grad: 0.1032 (0.1192) loss: 0.8275 (0.8245) time: 0.2060 data: 0.1151 max mem: 9390 +Train: [73] [1000/6250] eta: 0:15:39 lr: 0.000023 grad: 0.1095 (0.1185) loss: 0.8197 (0.8241) time: 0.2287 data: 0.1299 max mem: 9390 +Train: [73] [1100/6250] eta: 0:15:44 lr: 0.000023 grad: 0.1084 (0.1181) loss: 0.8155 (0.8237) time: 0.1035 data: 0.0002 max mem: 9390 +Train: [73] [1200/6250] eta: 0:15:11 lr: 0.000023 grad: 0.1135 (0.1181) loss: 0.8170 (0.8231) time: 0.1729 data: 0.0924 max mem: 9390 +Train: [73] [1300/6250] eta: 0:14:48 lr: 0.000023 grad: 0.1172 (0.1178) loss: 0.8129 (0.8227) time: 0.1708 data: 0.0783 max mem: 9390 +Train: [73] [1400/6250] eta: 0:14:26 lr: 0.000023 grad: 0.1110 (0.1174) loss: 0.8159 (0.8224) time: 0.1195 data: 0.0291 max mem: 9390 +Train: [73] [1500/6250] eta: 0:14:00 lr: 0.000023 grad: 0.1106 (0.1171) loss: 0.8208 (0.8222) time: 0.1459 data: 0.0633 max mem: 9390 +Train: [73] [1600/6250] eta: 0:13:39 lr: 0.000023 grad: 0.1058 (0.1168) loss: 0.8199 (0.8219) time: 0.2062 data: 0.1267 max mem: 9390 +Train: [73] [1700/6250] eta: 0:13:15 lr: 0.000023 grad: 0.1161 (0.1169) loss: 0.8207 (0.8216) time: 0.1466 data: 0.0679 max mem: 9390 +Train: [73] [1800/6250] eta: 0:12:53 lr: 0.000023 grad: 0.1186 (0.1170) loss: 0.8145 (0.8212) time: 0.1356 data: 0.0551 max mem: 9390 +Train: [73] [1900/6250] eta: 0:12:34 lr: 0.000023 grad: 0.1174 (0.1171) loss: 0.8116 (0.8210) time: 0.1791 data: 0.0957 max mem: 9390 +Train: [73] [2000/6250] eta: 0:12:15 lr: 0.000023 grad: 0.1176 (0.1171) loss: 0.8183 (0.8207) time: 0.1526 data: 0.0716 max mem: 9390 +Train: [73] [2100/6250] eta: 0:11:56 lr: 0.000023 grad: 0.1131 (0.1171) loss: 0.8160 (0.8204) time: 0.1559 data: 0.0682 max mem: 9390 +Train: [73] [2200/6250] eta: 0:11:37 lr: 0.000023 grad: 0.1083 (0.1172) loss: 0.8148 (0.8202) time: 0.1740 data: 0.0899 max mem: 9390 +Train: [73] [2300/6250] eta: 0:11:18 lr: 0.000023 grad: 0.1162 (0.1174) loss: 0.8146 (0.8198) time: 0.1675 data: 0.0853 max mem: 9390 +Train: [73] [2400/6250] eta: 0:10:58 lr: 0.000023 grad: 0.1180 (0.1174) loss: 0.8099 (0.8196) time: 0.1469 data: 0.0565 max mem: 9390 +Train: [73] [2500/6250] eta: 0:10:39 lr: 0.000023 grad: 0.1106 (0.1174) loss: 0.8126 (0.8193) time: 0.1681 data: 0.0798 max mem: 9390 +Train: [73] [2600/6250] eta: 0:10:19 lr: 0.000023 grad: 0.1131 (0.1174) loss: 0.8152 (0.8191) time: 0.1619 data: 0.0854 max mem: 9390 +Train: [73] [2700/6250] eta: 0:10:07 lr: 0.000023 grad: 0.1110 (0.1173) loss: 0.8170 (0.8189) time: 0.2214 data: 0.1392 max mem: 9390 +Train: [73] [2800/6250] eta: 0:09:51 lr: 0.000023 grad: 0.1145 (0.1173) loss: 0.8151 (0.8188) time: 0.1566 data: 0.0771 max mem: 9390 +Train: [73] [2900/6250] eta: 0:09:36 lr: 0.000023 grad: 0.1208 (0.1173) loss: 0.8147 (0.8186) time: 0.1000 data: 0.0072 max mem: 9390 +Train: [73] [3000/6250] eta: 0:09:19 lr: 0.000023 grad: 0.1094 (0.1173) loss: 0.8091 (0.8184) time: 0.1765 data: 0.0933 max mem: 9390 +Train: [73] [3100/6250] eta: 0:09:09 lr: 0.000023 grad: 0.1114 (0.1172) loss: 0.8163 (0.8182) time: 0.4446 data: 0.3609 max mem: 9390 +Train: [73] [3200/6250] eta: 0:08:54 lr: 0.000022 grad: 0.1130 (0.1173) loss: 0.8089 (0.8181) time: 0.1185 data: 0.0003 max mem: 9390 +Train: [73] [3300/6250] eta: 0:08:40 lr: 0.000022 grad: 0.1111 (0.1173) loss: 0.8086 (0.8179) time: 0.3007 data: 0.2094 max mem: 9390 +Train: [73] [3400/6250] eta: 0:08:23 lr: 0.000022 grad: 0.1196 (0.1174) loss: 0.8121 (0.8177) time: 0.1703 data: 0.0803 max mem: 9390 +Train: [73] [3500/6250] eta: 0:08:05 lr: 0.000022 grad: 0.1190 (0.1174) loss: 0.8109 (0.8175) time: 0.1885 data: 0.0992 max mem: 9390 +Train: [73] [3600/6250] eta: 0:07:46 lr: 0.000022 grad: 0.1171 (0.1175) loss: 0.8098 (0.8173) time: 0.1596 data: 0.0745 max mem: 9390 +Train: [73] [3700/6250] eta: 0:07:27 lr: 0.000022 grad: 0.1192 (0.1176) loss: 0.8025 (0.8170) time: 0.1448 data: 0.0461 max mem: 9390 +Train: [73] [3800/6250] eta: 0:07:09 lr: 0.000022 grad: 0.1182 (0.1177) loss: 0.8076 (0.8168) time: 0.1453 data: 0.0631 max mem: 9390 +Train: [73] [3900/6250] eta: 0:06:52 lr: 0.000022 grad: 0.1164 (0.1177) loss: 0.8124 (0.8167) time: 0.1784 data: 0.1041 max mem: 9390 +Train: [73] [4000/6250] eta: 0:06:34 lr: 0.000022 grad: 0.1111 (0.1178) loss: 0.8143 (0.8165) time: 0.1898 data: 0.1036 max mem: 9390 +Train: [73] [4100/6250] eta: 0:06:16 lr: 0.000022 grad: 0.1138 (0.1178) loss: 0.8100 (0.8165) time: 0.1571 data: 0.0756 max mem: 9390 +Train: [73] [4200/6250] eta: 0:05:58 lr: 0.000022 grad: 0.1148 (0.1179) loss: 0.8158 (0.8164) time: 0.1580 data: 0.0802 max mem: 9390 +Train: [73] [4300/6250] eta: 0:05:41 lr: 0.000022 grad: 0.1184 (0.1179) loss: 0.8152 (0.8164) time: 0.2089 data: 0.1210 max mem: 9390 +Train: [73] [4400/6250] eta: 0:05:23 lr: 0.000022 grad: 0.1123 (0.1179) loss: 0.8144 (0.8163) time: 0.1481 data: 0.0712 max mem: 9390 +Train: [73] [4500/6250] eta: 0:05:06 lr: 0.000022 grad: 0.1169 (0.1180) loss: 0.8131 (0.8163) time: 0.1663 data: 0.0838 max mem: 9390 +Train: [73] [4600/6250] eta: 0:04:48 lr: 0.000022 grad: 0.1209 (0.1180) loss: 0.8152 (0.8162) time: 0.2192 data: 0.1410 max mem: 9390 +Train: [73] [4700/6250] eta: 0:04:31 lr: 0.000022 grad: 0.1120 (0.1180) loss: 0.8160 (0.8163) time: 0.2098 data: 0.1320 max mem: 9390 +Train: [73] [4800/6250] eta: 0:04:12 lr: 0.000022 grad: 0.1212 (0.1180) loss: 0.8223 (0.8163) time: 0.1725 data: 0.0860 max mem: 9390 +Train: [73] [4900/6250] eta: 0:03:55 lr: 0.000022 grad: 0.1127 (0.1180) loss: 0.8173 (0.8163) time: 0.1903 data: 0.1060 max mem: 9390 +Train: [73] [5000/6250] eta: 0:03:38 lr: 0.000022 grad: 0.1125 (0.1181) loss: 0.8192 (0.8163) time: 0.1599 data: 0.0578 max mem: 9390 +Train: [73] [5100/6250] eta: 0:03:22 lr: 0.000022 grad: 0.1154 (0.1182) loss: 0.8136 (0.8162) time: 0.1488 data: 0.0533 max mem: 9390 +Train: [73] [5200/6250] eta: 0:03:05 lr: 0.000022 grad: 0.1109 (0.1182) loss: 0.8224 (0.8162) time: 0.1854 data: 0.0947 max mem: 9390 +Train: [73] [5300/6250] eta: 0:02:48 lr: 0.000022 grad: 0.1242 (0.1182) loss: 0.8103 (0.8161) time: 0.1620 data: 0.0684 max mem: 9390 +Train: [73] [5400/6250] eta: 0:02:30 lr: 0.000022 grad: 0.1163 (0.1183) loss: 0.8164 (0.8161) time: 0.2360 data: 0.1501 max mem: 9390 +Train: [73] [5500/6250] eta: 0:02:13 lr: 0.000022 grad: 0.1179 (0.1184) loss: 0.8116 (0.8161) time: 0.1471 data: 0.0515 max mem: 9390 +Train: [73] [5600/6250] eta: 0:01:56 lr: 0.000022 grad: 0.1143 (0.1183) loss: 0.8196 (0.8160) time: 0.1375 data: 0.0460 max mem: 9390 +Train: [73] [5700/6250] eta: 0:01:38 lr: 0.000022 grad: 0.1155 (0.1183) loss: 0.8159 (0.8160) time: 0.1951 data: 0.1103 max mem: 9390 +Train: [73] [5800/6250] eta: 0:01:20 lr: 0.000022 grad: 0.1208 (0.1183) loss: 0.8103 (0.8160) time: 0.1392 data: 0.0542 max mem: 9390 +Train: [73] [5900/6250] eta: 0:01:02 lr: 0.000022 grad: 0.1148 (0.1184) loss: 0.8118 (0.8159) time: 0.1339 data: 0.0339 max mem: 9390 +Train: [73] [6000/6250] eta: 0:00:44 lr: 0.000022 grad: 0.1235 (0.1184) loss: 0.8085 (0.8159) time: 0.1682 data: 0.0864 max mem: 9390 +Train: [73] [6100/6250] eta: 0:00:26 lr: 0.000022 grad: 0.1158 (0.1184) loss: 0.8054 (0.8158) time: 0.1773 data: 0.0859 max mem: 9390 +Train: [73] [6200/6250] eta: 0:00:08 lr: 0.000022 grad: 0.1163 (0.1183) loss: 0.8156 (0.8158) time: 0.1883 data: 0.0956 max mem: 9390 +Train: [73] [6249/6250] eta: 0:00:00 lr: 0.000022 grad: 0.1077 (0.1183) loss: 0.8134 (0.8158) time: 0.1825 data: 0.0863 max mem: 9390 +Train: [73] Total time: 0:18:40 (0.1794 s / it) +Averaged stats: lr: 0.000022 grad: 0.1077 (0.1183) loss: 0.8134 (0.8158) +Eval (hcp-train-subset): [73] [ 0/62] eta: 0:04:57 loss: 0.8357 (0.8357) time: 4.7947 data: 4.7644 max mem: 9390 +Eval (hcp-train-subset): [73] [61/62] eta: 0:00:00 loss: 0.8255 (0.8281) time: 0.1327 data: 0.1076 max mem: 9390 +Eval (hcp-train-subset): [73] Total time: 0:00:13 (0.2233 s / it) +Averaged stats (hcp-train-subset): loss: 0.8255 (0.8281) +Eval (hcp-val): [73] [ 0/62] eta: 0:05:38 loss: 0.8285 (0.8285) time: 5.4586 data: 5.4281 max mem: 9390 +Eval (hcp-val): [73] [61/62] eta: 0:00:00 loss: 0.8291 (0.8309) time: 0.1444 data: 0.1190 max mem: 9390 +Eval (hcp-val): [73] Total time: 0:00:14 (0.2340 s / it) +Averaged stats (hcp-val): loss: 0.8291 (0.8309) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +Train: [74] [ 0/6250] eta: 11:37:57 lr: 0.000022 grad: 0.2559 (0.2559) loss: 0.7826 (0.7826) time: 6.7003 data: 6.5788 max mem: 9390 +Train: [74] [ 100/6250] eta: 0:23:11 lr: 0.000022 grad: 0.1117 (0.1453) loss: 0.8204 (0.8265) time: 0.1743 data: 0.0734 max mem: 9390 +Train: [74] [ 200/6250] eta: 0:21:16 lr: 0.000022 grad: 0.1129 (0.1368) loss: 0.8103 (0.8211) time: 0.1845 data: 0.0867 max mem: 9390 +Train: [74] [ 300/6250] eta: 0:19:40 lr: 0.000022 grad: 0.1347 (0.1353) loss: 0.8122 (0.8168) time: 0.1524 data: 0.0564 max mem: 9390 +Train: [74] [ 400/6250] eta: 0:18:33 lr: 0.000022 grad: 0.1160 (0.1333) loss: 0.8106 (0.8140) time: 0.1582 data: 0.0517 max mem: 9390 +Train: [74] [ 500/6250] eta: 0:18:21 lr: 0.000022 grad: 0.1198 (0.1316) loss: 0.8103 (0.8132) time: 0.1162 data: 0.0090 max mem: 9390 +Train: [74] [ 600/6250] eta: 0:17:35 lr: 0.000022 grad: 0.1170 (0.1295) loss: 0.8123 (0.8134) time: 0.1493 data: 0.0599 max mem: 9390 +Train: [74] [ 700/6250] eta: 0:17:09 lr: 0.000022 grad: 0.1152 (0.1282) loss: 0.8121 (0.8137) time: 0.1730 data: 0.0845 max mem: 9390 +Train: [74] [ 800/6250] eta: 0:16:58 lr: 0.000022 grad: 0.1136 (0.1274) loss: 0.8123 (0.8137) time: 0.1045 data: 0.0023 max mem: 9390 +Train: [74] [ 900/6250] eta: 0:16:47 lr: 0.000021 grad: 0.1220 (0.1263) loss: 0.8101 (0.8137) time: 0.2028 data: 0.1066 max mem: 9390 +Train: [74] [1000/6250] eta: 0:16:15 lr: 0.000021 grad: 0.1105 (0.1254) loss: 0.8168 (0.8138) time: 0.2078 data: 0.1176 max mem: 9390 +Train: [74] [1100/6250] eta: 0:15:59 lr: 0.000021 grad: 0.1188 (0.1250) loss: 0.8127 (0.8138) time: 0.1619 data: 0.0792 max mem: 9390 +Train: [74] [1200/6250] eta: 0:15:33 lr: 0.000021 grad: 0.1193 (0.1245) loss: 0.8097 (0.8138) time: 0.1095 data: 0.0141 max mem: 9390 +Train: [74] [1300/6250] eta: 0:15:10 lr: 0.000021 grad: 0.1190 (0.1241) loss: 0.8128 (0.8137) time: 0.2267 data: 0.1369 max mem: 9390 +Train: [74] [1400/6250] eta: 0:14:49 lr: 0.000021 grad: 0.1122 (0.1238) loss: 0.8221 (0.8137) time: 0.0951 data: 0.0003 max mem: 9390 +Train: [74] [1500/6250] eta: 0:14:20 lr: 0.000021 grad: 0.1136 (0.1235) loss: 0.8153 (0.8137) time: 0.1630 data: 0.0809 max mem: 9390 +Train: [74] [1600/6250] eta: 0:13:55 lr: 0.000021 grad: 0.1101 (0.1232) loss: 0.8182 (0.8138) time: 0.1709 data: 0.0838 max mem: 9390 +Train: [74] [1700/6250] eta: 0:13:35 lr: 0.000021 grad: 0.1216 (0.1228) loss: 0.8068 (0.8138) time: 0.2392 data: 0.1627 max mem: 9390 +Train: [74] [1800/6250] eta: 0:13:13 lr: 0.000021 grad: 0.1154 (0.1227) loss: 0.8216 (0.8138) time: 0.1025 data: 0.0002 max mem: 9390 +Train: [74] [1900/6250] eta: 0:12:52 lr: 0.000021 grad: 0.1172 (0.1223) loss: 0.8136 (0.8139) time: 0.1503 data: 0.0690 max mem: 9390 +Train: [74] [2000/6250] eta: 0:12:31 lr: 0.000021 grad: 0.1208 (0.1219) loss: 0.8130 (0.8140) time: 0.1664 data: 0.0842 max mem: 9390 +Train: [74] [2100/6250] eta: 0:12:10 lr: 0.000021 grad: 0.1101 (0.1216) loss: 0.8130 (0.8141) time: 0.1970 data: 0.1083 max mem: 9390 +Train: [74] [2200/6250] eta: 0:11:54 lr: 0.000021 grad: 0.1135 (0.1216) loss: 0.8132 (0.8141) time: 0.2546 data: 0.1565 max mem: 9390 +Train: [74] [2300/6250] eta: 0:11:30 lr: 0.000021 grad: 0.1154 (0.1214) loss: 0.8128 (0.8141) time: 0.1500 data: 0.0642 max mem: 9390 +Train: [74] [2400/6250] eta: 0:11:14 lr: 0.000021 grad: 0.1141 (0.1212) loss: 0.8132 (0.8141) time: 0.2600 data: 0.1699 max mem: 9390 +Train: [74] [2500/6250] eta: 0:10:51 lr: 0.000021 grad: 0.1123 (0.1211) loss: 0.8177 (0.8142) time: 0.1439 data: 0.0584 max mem: 9390 +Train: [74] [2600/6250] eta: 0:10:32 lr: 0.000021 grad: 0.1122 (0.1210) loss: 0.8211 (0.8143) time: 0.1733 data: 0.0812 max mem: 9390 +Train: [74] [2700/6250] eta: 0:10:19 lr: 0.000021 grad: 0.1172 (0.1209) loss: 0.8129 (0.8143) time: 0.1027 data: 0.0057 max mem: 9390 +Train: [74] [2800/6250] eta: 0:10:07 lr: 0.000021 grad: 0.1175 (0.1209) loss: 0.8099 (0.8143) time: 0.2847 data: 0.1911 max mem: 9390 +Train: [74] [2900/6250] eta: 0:09:47 lr: 0.000021 grad: 0.1141 (0.1208) loss: 0.8161 (0.8143) time: 0.1184 data: 0.0254 max mem: 9390 +Train: [74] [3000/6250] eta: 0:09:28 lr: 0.000021 grad: 0.1145 (0.1207) loss: 0.8232 (0.8143) time: 0.1053 data: 0.0018 max mem: 9390 +Train: [74] [3100/6250] eta: 0:09:10 lr: 0.000021 grad: 0.1165 (0.1207) loss: 0.8139 (0.8143) time: 0.1735 data: 0.0731 max mem: 9390 +Train: [74] [3200/6250] eta: 0:08:54 lr: 0.000021 grad: 0.1172 (0.1207) loss: 0.8146 (0.8143) time: 0.0843 data: 0.0002 max mem: 9390 +Train: [74] [3300/6250] eta: 0:08:36 lr: 0.000021 grad: 0.1146 (0.1207) loss: 0.8148 (0.8143) time: 0.2344 data: 0.1586 max mem: 9390 +Train: [74] [3400/6250] eta: 0:08:17 lr: 0.000021 grad: 0.1232 (0.1206) loss: 0.8086 (0.8143) time: 0.1658 data: 0.0764 max mem: 9390 +Train: [74] [3500/6250] eta: 0:07:58 lr: 0.000021 grad: 0.1167 (0.1205) loss: 0.8149 (0.8143) time: 0.2098 data: 0.1258 max mem: 9390 +Train: [74] [3600/6250] eta: 0:07:39 lr: 0.000021 grad: 0.1200 (0.1205) loss: 0.8146 (0.8144) time: 0.1462 data: 0.0607 max mem: 9390 +Train: [74] [3700/6250] eta: 0:07:22 lr: 0.000021 grad: 0.1154 (0.1204) loss: 0.8208 (0.8145) time: 0.1355 data: 0.0476 max mem: 9390 +Train: [74] [3800/6250] eta: 0:07:04 lr: 0.000021 grad: 0.1122 (0.1203) loss: 0.8197 (0.8145) time: 0.2182 data: 0.1263 max mem: 9390 +Train: [74] [3900/6250] eta: 0:06:46 lr: 0.000021 grad: 0.1239 (0.1203) loss: 0.8131 (0.8146) time: 0.2006 data: 0.1256 max mem: 9390 +Train: [74] [4000/6250] eta: 0:06:27 lr: 0.000021 grad: 0.1147 (0.1202) loss: 0.8231 (0.8147) time: 0.1439 data: 0.0579 max mem: 9390 +Train: [74] [4100/6250] eta: 0:06:10 lr: 0.000021 grad: 0.1138 (0.1201) loss: 0.8188 (0.8148) time: 0.1407 data: 0.0511 max mem: 9390 +Train: [74] [4200/6250] eta: 0:05:51 lr: 0.000021 grad: 0.1133 (0.1201) loss: 0.8200 (0.8149) time: 0.1186 data: 0.0216 max mem: 9390 +Train: [74] [4300/6250] eta: 0:05:34 lr: 0.000021 grad: 0.1193 (0.1201) loss: 0.8204 (0.8149) time: 0.1497 data: 0.0655 max mem: 9390 +Train: [74] [4400/6250] eta: 0:05:16 lr: 0.000021 grad: 0.1165 (0.1201) loss: 0.8151 (0.8150) time: 0.1530 data: 0.0669 max mem: 9390 +Train: [74] [4500/6250] eta: 0:04:58 lr: 0.000021 grad: 0.1091 (0.1201) loss: 0.8198 (0.8151) time: 0.1578 data: 0.0730 max mem: 9390 +Train: [74] [4600/6250] eta: 0:04:41 lr: 0.000021 grad: 0.1147 (0.1201) loss: 0.8230 (0.8152) time: 0.1608 data: 0.0830 max mem: 9390 +Train: [74] [4700/6250] eta: 0:04:24 lr: 0.000021 grad: 0.1141 (0.1200) loss: 0.8267 (0.8152) time: 0.2083 data: 0.1329 max mem: 9390 +Train: [74] [4800/6250] eta: 0:04:06 lr: 0.000021 grad: 0.1146 (0.1200) loss: 0.8192 (0.8153) time: 0.1383 data: 0.0437 max mem: 9390 +Train: [74] [4900/6250] eta: 0:03:48 lr: 0.000020 grad: 0.1189 (0.1200) loss: 0.8191 (0.8154) time: 0.1543 data: 0.0660 max mem: 9390 +Train: [74] [5000/6250] eta: 0:03:31 lr: 0.000020 grad: 0.1245 (0.1200) loss: 0.8179 (0.8155) time: 0.1943 data: 0.1161 max mem: 9390 +Train: [74] [5100/6250] eta: 0:03:14 lr: 0.000020 grad: 0.1141 (0.1199) loss: 0.8252 (0.8156) time: 0.1718 data: 0.0901 max mem: 9390 +Train: [74] [5200/6250] eta: 0:02:58 lr: 0.000020 grad: 0.1116 (0.1199) loss: 0.8195 (0.8157) time: 0.2432 data: 0.1479 max mem: 9390 +Train: [74] [5300/6250] eta: 0:02:41 lr: 0.000020 grad: 0.1161 (0.1198) loss: 0.8203 (0.8158) time: 0.1399 data: 0.0493 max mem: 9390 +Train: [74] [5400/6250] eta: 0:02:25 lr: 0.000020 grad: 0.1169 (0.1198) loss: 0.8184 (0.8159) time: 0.4236 data: 0.3122 max mem: 9390 +Train: [74] [5500/6250] eta: 0:02:08 lr: 0.000020 grad: 0.1153 (0.1197) loss: 0.8213 (0.8159) time: 0.1983 data: 0.1082 max mem: 9390 +Train: [74] [5600/6250] eta: 0:01:51 lr: 0.000020 grad: 0.1184 (0.1198) loss: 0.8212 (0.8160) time: 0.1904 data: 0.0998 max mem: 9390 +Train: [74] [5700/6250] eta: 0:01:33 lr: 0.000020 grad: 0.1146 (0.1197) loss: 0.8182 (0.8160) time: 0.2414 data: 0.1568 max mem: 9390 +Train: [74] [5800/6250] eta: 0:01:16 lr: 0.000020 grad: 0.1147 (0.1197) loss: 0.8162 (0.8160) time: 0.1722 data: 0.0832 max mem: 9390 +Train: [74] [5900/6250] eta: 0:00:59 lr: 0.000020 grad: 0.1142 (0.1197) loss: 0.8226 (0.8160) time: 0.1775 data: 0.0992 max mem: 9390 +Train: [74] [6000/6250] eta: 0:00:42 lr: 0.000020 grad: 0.1139 (0.1197) loss: 0.8131 (0.8160) time: 0.0820 data: 0.0002 max mem: 9390 +Train: [74] [6100/6250] eta: 0:00:25 lr: 0.000020 grad: 0.1161 (0.1198) loss: 0.8131 (0.8160) time: 0.1610 data: 0.0828 max mem: 9390 +Train: [74] [6200/6250] eta: 0:00:08 lr: 0.000020 grad: 0.1218 (0.1198) loss: 0.8179 (0.8159) time: 0.1509 data: 0.0664 max mem: 9390 +Train: [74] [6249/6250] eta: 0:00:00 lr: 0.000020 grad: 0.1122 (0.1197) loss: 0.8151 (0.8159) time: 0.1688 data: 0.0858 max mem: 9390 +Train: [74] Total time: 0:17:52 (0.1716 s / it) +Averaged stats: lr: 0.000020 grad: 0.1122 (0.1197) loss: 0.8151 (0.8159) +Eval (hcp-train-subset): [74] [ 0/62] eta: 0:04:50 loss: 0.8347 (0.8347) time: 4.6909 data: 4.6523 max mem: 9390 +Eval (hcp-train-subset): [74] [61/62] eta: 0:00:00 loss: 0.8256 (0.8279) time: 0.1197 data: 0.0913 max mem: 9390 +Eval (hcp-train-subset): [74] Total time: 0:00:13 (0.2163 s / it) +Averaged stats (hcp-train-subset): loss: 0.8256 (0.8279) +Making plots (hcp-train-subset): example=2 +Eval (hcp-val): [74] [ 0/62] eta: 0:04:42 loss: 0.8288 (0.8288) time: 4.5526 data: 4.5201 max mem: 9390 +Eval (hcp-val): [74] [61/62] eta: 0:00:00 loss: 0.8301 (0.8322) time: 0.1269 data: 0.1015 max mem: 9390 +Eval (hcp-val): [74] Total time: 0:00:13 (0.2156 s / it) +Averaged stats (hcp-val): loss: 0.8301 (0.8322) +Making plots (hcp-val): example=22 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +Train: [75] [ 0/6250] eta: 9:16:02 lr: 0.000020 grad: 0.1283 (0.1283) loss: 0.8525 (0.8525) time: 5.3380 data: 5.1030 max mem: 9390 +Train: [75] [ 100/6250] eta: 0:24:33 lr: 0.000020 grad: 0.1253 (0.1605) loss: 0.8322 (0.8247) time: 0.1850 data: 0.0905 max mem: 9390 +Train: [75] [ 200/6250] eta: 0:24:16 lr: 0.000020 grad: 0.1124 (0.1453) loss: 0.8150 (0.8219) time: 0.4884 data: 0.3921 max mem: 9390 +Train: [75] [ 300/6250] eta: 0:21:18 lr: 0.000020 grad: 0.1280 (0.1403) loss: 0.8075 (0.8187) time: 0.1664 data: 0.0667 max mem: 9390 +Train: [75] [ 400/6250] eta: 0:19:55 lr: 0.000020 grad: 0.1190 (0.1368) loss: 0.8073 (0.8163) time: 0.1589 data: 0.0368 max mem: 9390 +Train: [75] [ 500/6250] eta: 0:19:11 lr: 0.000020 grad: 0.1204 (0.1348) loss: 0.8188 (0.8144) time: 0.1659 data: 0.0681 max mem: 9390 +Train: [75] [ 600/6250] eta: 0:18:16 lr: 0.000020 grad: 0.1159 (0.1332) loss: 0.8190 (0.8135) time: 0.1598 data: 0.0817 max mem: 9390 +Train: [75] [ 700/6250] eta: 0:17:30 lr: 0.000020 grad: 0.1172 (0.1327) loss: 0.8114 (0.8132) time: 0.1625 data: 0.0833 max mem: 9390 +Train: [75] [ 800/6250] eta: 0:16:59 lr: 0.000020 grad: 0.1231 (0.1318) loss: 0.8132 (0.8127) time: 0.1596 data: 0.0707 max mem: 9390 +Train: [75] [ 900/6250] eta: 0:16:21 lr: 0.000020 grad: 0.1265 (0.1312) loss: 0.8069 (0.8125) time: 0.1326 data: 0.0517 max mem: 9390 +Train: [75] [1000/6250] eta: 0:15:54 lr: 0.000020 grad: 0.1146 (0.1302) loss: 0.8157 (0.8128) time: 0.1545 data: 0.0774 max mem: 9390 +Train: [75] [1100/6250] eta: 0:15:18 lr: 0.000020 grad: 0.1126 (0.1294) loss: 0.8113 (0.8130) time: 0.1402 data: 0.0549 max mem: 9390 +Train: [75] [1200/6250] eta: 0:14:51 lr: 0.000020 grad: 0.1211 (0.1285) loss: 0.8169 (0.8132) time: 0.1479 data: 0.0652 max mem: 9390 +Train: [75] [1300/6250] eta: 0:14:28 lr: 0.000020 grad: 0.1191 (0.1278) loss: 0.8128 (0.8133) time: 0.1842 data: 0.1022 max mem: 9390 +Train: [75] [1400/6250] eta: 0:14:06 lr: 0.000020 grad: 0.1145 (0.1274) loss: 0.8159 (0.8133) time: 0.1701 data: 0.0842 max mem: 9390 +Train: [75] [1500/6250] eta: 0:13:43 lr: 0.000020 grad: 0.1194 (0.1270) loss: 0.8132 (0.8134) time: 0.1538 data: 0.0788 max mem: 9390 +Train: [75] [1600/6250] eta: 0:13:22 lr: 0.000020 grad: 0.1209 (0.1265) loss: 0.8150 (0.8136) time: 0.1641 data: 0.0814 max mem: 9390 +Train: [75] [1700/6250] eta: 0:13:03 lr: 0.000020 grad: 0.1142 (0.1260) loss: 0.8130 (0.8138) time: 0.1950 data: 0.1140 max mem: 9390 +Train: [75] [1800/6250] eta: 0:12:40 lr: 0.000020 grad: 0.1167 (0.1257) loss: 0.8224 (0.8141) time: 0.1361 data: 0.0487 max mem: 9390 +Train: [75] [1900/6250] eta: 0:12:19 lr: 0.000020 grad: 0.1041 (0.1251) loss: 0.8220 (0.8143) time: 0.1457 data: 0.0642 max mem: 9390 +Train: [75] [2000/6250] eta: 0:11:58 lr: 0.000020 grad: 0.1161 (0.1247) loss: 0.8253 (0.8147) time: 0.1577 data: 0.0756 max mem: 9390 +Train: [75] [2100/6250] eta: 0:11:44 lr: 0.000020 grad: 0.1159 (0.1244) loss: 0.8201 (0.8149) time: 0.1510 data: 0.0634 max mem: 9390 +Train: [75] [2200/6250] eta: 0:11:27 lr: 0.000020 grad: 0.1152 (0.1240) loss: 0.8235 (0.8152) time: 0.1287 data: 0.0532 max mem: 9390 +Train: [75] [2300/6250] eta: 0:11:14 lr: 0.000020 grad: 0.1198 (0.1237) loss: 0.8150 (0.8155) time: 0.1923 data: 0.1000 max mem: 9390 +Train: [75] [2400/6250] eta: 0:10:57 lr: 0.000020 grad: 0.1124 (0.1234) loss: 0.8203 (0.8157) time: 0.1495 data: 0.0712 max mem: 9390 +Train: [75] [2500/6250] eta: 0:10:52 lr: 0.000020 grad: 0.1208 (0.1231) loss: 0.8148 (0.8158) time: 0.0856 data: 0.0002 max mem: 9390 +Train: [75] [2600/6250] eta: 0:10:40 lr: 0.000020 grad: 0.1124 (0.1228) loss: 0.8218 (0.8160) time: 0.3226 data: 0.2199 max mem: 9390 +Train: [75] [2700/6250] eta: 0:10:24 lr: 0.000020 grad: 0.1141 (0.1226) loss: 0.8190 (0.8161) time: 0.2769 data: 0.1743 max mem: 9390 +Train: [75] [2800/6250] eta: 0:10:05 lr: 0.000019 grad: 0.1220 (0.1226) loss: 0.8163 (0.8162) time: 0.1726 data: 0.0833 max mem: 9390 +Train: [75] [2900/6250] eta: 0:09:45 lr: 0.000019 grad: 0.1169 (0.1224) loss: 0.8183 (0.8162) time: 0.1512 data: 0.0692 max mem: 9390 +Train: [75] [3000/6250] eta: 0:09:26 lr: 0.000019 grad: 0.1141 (0.1224) loss: 0.8217 (0.8162) time: 0.1575 data: 0.0449 max mem: 9390 +Train: [75] [3100/6250] eta: 0:09:10 lr: 0.000019 grad: 0.1192 (0.1224) loss: 0.8093 (0.8161) time: 0.0989 data: 0.0002 max mem: 9390 +Train: [75] [3200/6250] eta: 0:08:50 lr: 0.000019 grad: 0.1127 (0.1225) loss: 0.8170 (0.8161) time: 0.1659 data: 0.0862 max mem: 9390 +Train: [75] [3300/6250] eta: 0:08:32 lr: 0.000019 grad: 0.1193 (0.1226) loss: 0.8164 (0.8160) time: 0.1682 data: 0.0860 max mem: 9390 +Train: [75] [3400/6250] eta: 0:08:12 lr: 0.000019 grad: 0.1261 (0.1227) loss: 0.8116 (0.8159) time: 0.1486 data: 0.0629 max mem: 9390 +Train: [75] [3500/6250] eta: 0:07:57 lr: 0.000019 grad: 0.1218 (0.1228) loss: 0.8138 (0.8158) time: 0.3360 data: 0.2225 max mem: 9390 +Train: [75] [3600/6250] eta: 0:07:37 lr: 0.000019 grad: 0.1195 (0.1229) loss: 0.8068 (0.8157) time: 0.1737 data: 0.0847 max mem: 9390 +Train: [75] [3700/6250] eta: 0:07:19 lr: 0.000019 grad: 0.1160 (0.1229) loss: 0.8182 (0.8156) time: 0.1790 data: 0.0950 max mem: 9390 +Train: [75] [3800/6250] eta: 0:07:02 lr: 0.000019 grad: 0.1196 (0.1230) loss: 0.8213 (0.8156) time: 0.1973 data: 0.1130 max mem: 9390 +Train: [75] [3900/6250] eta: 0:06:43 lr: 0.000019 grad: 0.1186 (0.1229) loss: 0.8106 (0.8156) time: 0.1700 data: 0.0912 max mem: 9390 +Train: [75] [4000/6250] eta: 0:06:27 lr: 0.000019 grad: 0.1192 (0.1229) loss: 0.8117 (0.8154) time: 0.0998 data: 0.0002 max mem: 9390 +Train: [75] [4100/6250] eta: 0:06:09 lr: 0.000019 grad: 0.1279 (0.1230) loss: 0.8139 (0.8154) time: 0.1828 data: 0.0991 max mem: 9390 +Train: [75] [4200/6250] eta: 0:05:51 lr: 0.000019 grad: 0.1147 (0.1230) loss: 0.8175 (0.8153) time: 0.1658 data: 0.0861 max mem: 9390 +Train: [75] [4300/6250] eta: 0:05:35 lr: 0.000019 grad: 0.1170 (0.1229) loss: 0.8139 (0.8153) time: 0.1905 data: 0.1092 max mem: 9390 +Train: [75] [4400/6250] eta: 0:05:19 lr: 0.000019 grad: 0.1129 (0.1229) loss: 0.8171 (0.8153) time: 0.1927 data: 0.1169 max mem: 9390 +Train: [75] [4500/6250] eta: 0:05:01 lr: 0.000019 grad: 0.1227 (0.1229) loss: 0.8077 (0.8152) time: 0.1867 data: 0.1086 max mem: 9390 +Train: [75] [4600/6250] eta: 0:04:44 lr: 0.000019 grad: 0.1138 (0.1229) loss: 0.8150 (0.8152) time: 0.1086 data: 0.0242 max mem: 9390 +Train: [75] [4700/6250] eta: 0:04:27 lr: 0.000019 grad: 0.1162 (0.1228) loss: 0.8182 (0.8152) time: 0.1668 data: 0.0818 max mem: 9390 +Train: [75] [4800/6250] eta: 0:04:09 lr: 0.000019 grad: 0.1192 (0.1228) loss: 0.8132 (0.8151) time: 0.1346 data: 0.0505 max mem: 9390 +Train: [75] [4900/6250] eta: 0:03:52 lr: 0.000019 grad: 0.1177 (0.1227) loss: 0.8164 (0.8151) time: 0.1656 data: 0.0830 max mem: 9390 +Train: [75] [5000/6250] eta: 0:03:34 lr: 0.000019 grad: 0.1178 (0.1227) loss: 0.8129 (0.8151) time: 0.1408 data: 0.0602 max mem: 9390 +Train: [75] [5100/6250] eta: 0:03:16 lr: 0.000019 grad: 0.1174 (0.1226) loss: 0.8166 (0.8151) time: 0.1405 data: 0.0514 max mem: 9390 +Train: [75] [5200/6250] eta: 0:02:59 lr: 0.000019 grad: 0.1157 (0.1226) loss: 0.8170 (0.8151) time: 0.1540 data: 0.0720 max mem: 9390 +Train: [75] [5300/6250] eta: 0:02:42 lr: 0.000019 grad: 0.1210 (0.1225) loss: 0.8103 (0.8151) time: 0.1849 data: 0.0785 max mem: 9390 +Train: [75] [5400/6250] eta: 0:02:25 lr: 0.000019 grad: 0.1176 (0.1225) loss: 0.8101 (0.8151) time: 0.1716 data: 0.0811 max mem: 9390 +Train: [75] [5500/6250] eta: 0:02:07 lr: 0.000019 grad: 0.1159 (0.1225) loss: 0.8138 (0.8151) time: 0.1582 data: 0.0694 max mem: 9390 +Train: [75] [5600/6250] eta: 0:01:50 lr: 0.000019 grad: 0.1298 (0.1226) loss: 0.8109 (0.8151) time: 0.1190 data: 0.0250 max mem: 9390 +Train: [75] [5700/6250] eta: 0:01:33 lr: 0.000019 grad: 0.1184 (0.1226) loss: 0.8156 (0.8150) time: 0.0922 data: 0.0002 max mem: 9390 +Train: [75] [5800/6250] eta: 0:01:16 lr: 0.000019 grad: 0.1254 (0.1227) loss: 0.8092 (0.8150) time: 0.0986 data: 0.0002 max mem: 9390 +Train: [75] [5900/6250] eta: 0:00:59 lr: 0.000019 grad: 0.1223 (0.1227) loss: 0.8142 (0.8149) time: 0.2066 data: 0.1302 max mem: 9390 +Train: [75] [6000/6250] eta: 0:00:42 lr: 0.000019 grad: 0.1201 (0.1227) loss: 0.8091 (0.8149) time: 0.1402 data: 0.0489 max mem: 9390 +Train: [75] [6100/6250] eta: 0:00:25 lr: 0.000019 grad: 0.1198 (0.1227) loss: 0.8169 (0.8149) time: 0.1571 data: 0.0676 max mem: 9390 +Train: [75] [6200/6250] eta: 0:00:08 lr: 0.000019 grad: 0.1121 (0.1228) loss: 0.8148 (0.8149) time: 0.1739 data: 0.0853 max mem: 9390 +Train: [75] [6249/6250] eta: 0:00:00 lr: 0.000019 grad: 0.1216 (0.1228) loss: 0.8106 (0.8149) time: 0.1404 data: 0.0557 max mem: 9390 +Train: [75] Total time: 0:17:50 (0.1713 s / it) +Averaged stats: lr: 0.000019 grad: 0.1216 (0.1228) loss: 0.8106 (0.8149) +Eval (hcp-train-subset): [75] [ 0/62] eta: 0:05:30 loss: 0.8357 (0.8357) time: 5.3241 data: 5.2917 max mem: 9390 +Eval (hcp-train-subset): [75] [61/62] eta: 0:00:00 loss: 0.8235 (0.8260) time: 0.1400 data: 0.1150 max mem: 9390 +Eval (hcp-train-subset): [75] Total time: 0:00:13 (0.2211 s / it) +Averaged stats (hcp-train-subset): loss: 0.8235 (0.8260) +Eval (hcp-val): [75] [ 0/62] eta: 0:03:20 loss: 0.8315 (0.8315) time: 3.2350 data: 3.1574 max mem: 9390 +Eval (hcp-val): [75] [61/62] eta: 0:00:00 loss: 0.8303 (0.8311) time: 0.1376 data: 0.1110 max mem: 9390 +Eval (hcp-val): [75] Total time: 0:00:13 (0.2222 s / it) +Averaged stats (hcp-val): loss: 0.8303 (0.8311) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +Train: [76] [ 0/6250] eta: 7:26:33 lr: 0.000019 grad: 0.0892 (0.0892) loss: 0.8296 (0.8296) time: 4.2870 data: 4.1081 max mem: 9390 +Train: [76] [ 100/6250] eta: 0:24:07 lr: 0.000019 grad: 0.1302 (0.1602) loss: 0.8298 (0.8203) time: 0.1708 data: 0.0727 max mem: 9390 +Train: [76] [ 200/6250] eta: 0:20:56 lr: 0.000019 grad: 0.1252 (0.1467) loss: 0.8173 (0.8212) time: 0.1902 data: 0.0919 max mem: 9390 +Train: [76] [ 300/6250] eta: 0:19:47 lr: 0.000019 grad: 0.1116 (0.1368) loss: 0.8277 (0.8233) time: 0.1128 data: 0.0002 max mem: 9390 +Train: [76] [ 400/6250] eta: 0:20:02 lr: 0.000019 grad: 0.1075 (0.1307) loss: 0.8291 (0.8246) time: 0.1942 data: 0.0562 max mem: 9390 +Train: [76] [ 500/6250] eta: 0:19:17 lr: 0.000019 grad: 0.1147 (0.1290) loss: 0.8208 (0.8243) time: 0.2117 data: 0.1220 max mem: 9390 +Train: [76] [ 600/6250] eta: 0:19:10 lr: 0.000019 grad: 0.1116 (0.1270) loss: 0.8188 (0.8237) time: 0.4327 data: 0.3295 max mem: 9390 +Train: [76] [ 700/6250] eta: 0:18:00 lr: 0.000019 grad: 0.1231 (0.1263) loss: 0.8096 (0.8226) time: 0.1446 data: 0.0563 max mem: 9390 +Train: [76] [ 800/6250] eta: 0:17:33 lr: 0.000018 grad: 0.1167 (0.1256) loss: 0.8155 (0.8215) time: 0.1339 data: 0.0367 max mem: 9390 +Train: [76] [ 900/6250] eta: 0:17:01 lr: 0.000018 grad: 0.1231 (0.1252) loss: 0.8128 (0.8208) time: 0.1891 data: 0.0993 max mem: 9390 +Train: [76] [1000/6250] eta: 0:16:26 lr: 0.000018 grad: 0.1145 (0.1244) loss: 0.8112 (0.8200) time: 0.1958 data: 0.1171 max mem: 9390 +Train: [76] [1100/6250] eta: 0:15:51 lr: 0.000018 grad: 0.1232 (0.1238) loss: 0.8080 (0.8192) time: 0.2000 data: 0.1233 max mem: 9390 +Train: [76] [1200/6250] eta: 0:15:47 lr: 0.000018 grad: 0.1138 (0.1234) loss: 0.8152 (0.8186) time: 0.0965 data: 0.0002 max mem: 9390 +Train: [76] [1300/6250] eta: 0:15:12 lr: 0.000018 grad: 0.1156 (0.1231) loss: 0.8050 (0.8180) time: 0.1473 data: 0.0583 max mem: 9390 +Train: [76] [1400/6250] eta: 0:14:46 lr: 0.000018 grad: 0.1224 (0.1227) loss: 0.8095 (0.8176) time: 0.1540 data: 0.0655 max mem: 9390 +Train: [76] [1500/6250] eta: 0:14:24 lr: 0.000018 grad: 0.1187 (0.1226) loss: 0.8120 (0.8172) time: 0.2271 data: 0.1381 max mem: 9390 +Train: [76] [1600/6250] eta: 0:13:54 lr: 0.000018 grad: 0.1153 (0.1226) loss: 0.8068 (0.8168) time: 0.1315 data: 0.0504 max mem: 9390 +Train: [76] [1700/6250] eta: 0:13:47 lr: 0.000018 grad: 0.1202 (0.1225) loss: 0.8129 (0.8165) time: 0.0866 data: 0.0002 max mem: 9390 +Train: [76] [1800/6250] eta: 0:13:19 lr: 0.000018 grad: 0.1184 (0.1225) loss: 0.8136 (0.8162) time: 0.1291 data: 0.0452 max mem: 9390 +Train: [76] [1900/6250] eta: 0:12:58 lr: 0.000018 grad: 0.1211 (0.1226) loss: 0.8122 (0.8160) time: 0.1821 data: 0.0951 max mem: 9390 +Train: [76] [2000/6250] eta: 0:12:51 lr: 0.000018 grad: 0.1214 (0.1226) loss: 0.8141 (0.8158) time: 0.2425 data: 0.1409 max mem: 9390 +Train: [76] [2100/6250] eta: 0:12:29 lr: 0.000018 grad: 0.1224 (0.1227) loss: 0.8067 (0.8156) time: 0.1999 data: 0.1245 max mem: 9390 +Train: [76] [2200/6250] eta: 0:12:15 lr: 0.000018 grad: 0.1195 (0.1227) loss: 0.8133 (0.8154) time: 0.3679 data: 0.2718 max mem: 9390 +Train: [76] [2300/6250] eta: 0:11:51 lr: 0.000018 grad: 0.1176 (0.1226) loss: 0.8127 (0.8153) time: 0.2084 data: 0.1052 max mem: 9390 +Train: [76] [2400/6250] eta: 0:11:34 lr: 0.000018 grad: 0.1186 (0.1225) loss: 0.8193 (0.8152) time: 0.1201 data: 0.0111 max mem: 9390 +Train: [76] [2500/6250] eta: 0:11:17 lr: 0.000018 grad: 0.1168 (0.1225) loss: 0.8160 (0.8152) time: 0.0919 data: 0.0002 max mem: 9390 +Train: [76] [2600/6250] eta: 0:10:55 lr: 0.000018 grad: 0.1111 (0.1224) loss: 0.8125 (0.8152) time: 0.1931 data: 0.1143 max mem: 9390 +Train: [76] [2700/6250] eta: 0:10:35 lr: 0.000018 grad: 0.1198 (0.1223) loss: 0.8152 (0.8153) time: 0.1057 data: 0.0002 max mem: 9390 +Train: [76] [2800/6250] eta: 0:10:16 lr: 0.000018 grad: 0.1114 (0.1222) loss: 0.8134 (0.8153) time: 0.1682 data: 0.0881 max mem: 9390 +Train: [76] [2900/6250] eta: 0:09:56 lr: 0.000018 grad: 0.1188 (0.1221) loss: 0.8177 (0.8154) time: 0.0976 data: 0.0002 max mem: 9390 +Train: [76] [3000/6250] eta: 0:09:39 lr: 0.000018 grad: 0.1222 (0.1221) loss: 0.8103 (0.8153) time: 0.1236 data: 0.0290 max mem: 9390 +Train: [76] [3100/6250] eta: 0:09:19 lr: 0.000018 grad: 0.1232 (0.1221) loss: 0.8188 (0.8152) time: 0.1703 data: 0.0870 max mem: 9390 +Train: [76] [3200/6250] eta: 0:09:00 lr: 0.000018 grad: 0.1186 (0.1222) loss: 0.8135 (0.8151) time: 0.1325 data: 0.0394 max mem: 9390 +Train: [76] [3300/6250] eta: 0:08:43 lr: 0.000018 grad: 0.1160 (0.1222) loss: 0.8116 (0.8150) time: 0.1438 data: 0.0577 max mem: 9390 +Train: [76] [3400/6250] eta: 0:08:27 lr: 0.000018 grad: 0.1242 (0.1223) loss: 0.8097 (0.8149) time: 0.2963 data: 0.2051 max mem: 9390 +Train: [76] [3500/6250] eta: 0:08:06 lr: 0.000018 grad: 0.1234 (0.1224) loss: 0.8098 (0.8148) time: 0.1253 data: 0.0332 max mem: 9390 +Train: [76] [3600/6250] eta: 0:07:47 lr: 0.000018 grad: 0.1198 (0.1224) loss: 0.8139 (0.8148) time: 0.1573 data: 0.0769 max mem: 9390 +Train: [76] [3700/6250] eta: 0:07:31 lr: 0.000018 grad: 0.1154 (0.1224) loss: 0.8175 (0.8148) time: 0.1651 data: 0.0684 max mem: 9390 +Train: [76] [3800/6250] eta: 0:07:14 lr: 0.000018 grad: 0.1188 (0.1224) loss: 0.8137 (0.8147) time: 0.0960 data: 0.0002 max mem: 9390 +Train: [76] [3900/6250] eta: 0:06:58 lr: 0.000018 grad: 0.1236 (0.1225) loss: 0.8169 (0.8147) time: 0.1195 data: 0.0378 max mem: 9390 +Train: [76] [4000/6250] eta: 0:06:38 lr: 0.000018 grad: 0.1175 (0.1224) loss: 0.8174 (0.8147) time: 0.1429 data: 0.0626 max mem: 9390 +Train: [76] [4100/6250] eta: 0:06:22 lr: 0.000018 grad: 0.1217 (0.1225) loss: 0.8142 (0.8147) time: 0.3633 data: 0.2622 max mem: 9390 +Train: [76] [4200/6250] eta: 0:06:02 lr: 0.000018 grad: 0.1263 (0.1225) loss: 0.8077 (0.8146) time: 0.1778 data: 0.0814 max mem: 9390 +Train: [76] [4300/6250] eta: 0:05:44 lr: 0.000018 grad: 0.1200 (0.1224) loss: 0.8151 (0.8146) time: 0.1249 data: 0.0468 max mem: 9390 +Train: [76] [4400/6250] eta: 0:05:25 lr: 0.000018 grad: 0.1233 (0.1225) loss: 0.8136 (0.8146) time: 0.1542 data: 0.0771 max mem: 9390 +Train: [76] [4500/6250] eta: 0:05:07 lr: 0.000018 grad: 0.1236 (0.1225) loss: 0.8171 (0.8146) time: 0.1712 data: 0.0944 max mem: 9390 +Train: [76] [4600/6250] eta: 0:04:49 lr: 0.000018 grad: 0.1196 (0.1226) loss: 0.8149 (0.8146) time: 0.1432 data: 0.0576 max mem: 9390 +Train: [76] [4700/6250] eta: 0:04:31 lr: 0.000018 grad: 0.1197 (0.1227) loss: 0.8103 (0.8145) time: 0.1388 data: 0.0533 max mem: 9390 +Train: [76] [4800/6250] eta: 0:04:13 lr: 0.000018 grad: 0.1222 (0.1227) loss: 0.8057 (0.8145) time: 0.1671 data: 0.0889 max mem: 9390 +Train: [76] [4900/6250] eta: 0:03:56 lr: 0.000018 grad: 0.1217 (0.1228) loss: 0.8127 (0.8145) time: 0.2117 data: 0.1374 max mem: 9390 +Train: [76] [5000/6250] eta: 0:03:37 lr: 0.000018 grad: 0.1286 (0.1229) loss: 0.8117 (0.8144) time: 0.1302 data: 0.0411 max mem: 9390 +Train: [76] [5100/6250] eta: 0:03:20 lr: 0.000017 grad: 0.1182 (0.1229) loss: 0.8159 (0.8143) time: 0.1662 data: 0.0904 max mem: 9390 +Train: [76] [5200/6250] eta: 0:03:02 lr: 0.000017 grad: 0.1223 (0.1230) loss: 0.8105 (0.8143) time: 0.1488 data: 0.0680 max mem: 9390 +Train: [76] [5300/6250] eta: 0:02:44 lr: 0.000017 grad: 0.1395 (0.1232) loss: 0.8101 (0.8143) time: 0.1646 data: 0.0831 max mem: 9390 +Train: [76] [5400/6250] eta: 0:02:26 lr: 0.000017 grad: 0.1286 (0.1232) loss: 0.8132 (0.8142) time: 0.1486 data: 0.0551 max mem: 9390 +Train: [76] [5500/6250] eta: 0:02:09 lr: 0.000017 grad: 0.1220 (0.1233) loss: 0.8111 (0.8142) time: 0.1395 data: 0.0544 max mem: 9390 +Train: [76] [5600/6250] eta: 0:01:52 lr: 0.000017 grad: 0.1228 (0.1233) loss: 0.8145 (0.8142) time: 0.1926 data: 0.1124 max mem: 9390 +Train: [76] [5700/6250] eta: 0:01:35 lr: 0.000017 grad: 0.1189 (0.1233) loss: 0.8135 (0.8142) time: 0.3057 data: 0.2132 max mem: 9390 +Train: [76] [5800/6250] eta: 0:01:17 lr: 0.000017 grad: 0.1178 (0.1233) loss: 0.8203 (0.8143) time: 0.1599 data: 0.0727 max mem: 9390 +Train: [76] [5900/6250] eta: 0:01:00 lr: 0.000017 grad: 0.1131 (0.1232) loss: 0.8210 (0.8143) time: 0.1817 data: 0.0986 max mem: 9390 +Train: [76] [6000/6250] eta: 0:00:43 lr: 0.000017 grad: 0.1176 (0.1232) loss: 0.8204 (0.8144) time: 0.0998 data: 0.0002 max mem: 9390 +Train: [76] [6100/6250] eta: 0:00:25 lr: 0.000017 grad: 0.1146 (0.1231) loss: 0.8214 (0.8145) time: 0.0880 data: 0.0002 max mem: 9390 +Train: [76] [6200/6250] eta: 0:00:08 lr: 0.000017 grad: 0.1111 (0.1231) loss: 0.8254 (0.8146) time: 0.1678 data: 0.0812 max mem: 9390 +Train: [76] [6249/6250] eta: 0:00:00 lr: 0.000017 grad: 0.1134 (0.1231) loss: 0.8209 (0.8146) time: 0.1516 data: 0.0619 max mem: 9390 +Train: [76] Total time: 0:18:10 (0.1744 s / it) +Averaged stats: lr: 0.000017 grad: 0.1134 (0.1231) loss: 0.8209 (0.8146) +Eval (hcp-train-subset): [76] [ 0/62] eta: 0:03:32 loss: 0.8380 (0.8380) time: 3.4258 data: 3.3362 max mem: 9390 +Eval (hcp-train-subset): [76] [61/62] eta: 0:00:00 loss: 0.8245 (0.8274) time: 0.1258 data: 0.0994 max mem: 9390 +Eval (hcp-train-subset): [76] Total time: 0:00:13 (0.2122 s / it) +Averaged stats (hcp-train-subset): loss: 0.8245 (0.8274) +Eval (hcp-val): [76] [ 0/62] eta: 0:03:22 loss: 0.8300 (0.8300) time: 3.2678 data: 3.1957 max mem: 9390 +Eval (hcp-val): [76] [61/62] eta: 0:00:00 loss: 0.8293 (0.8309) time: 0.1154 data: 0.0889 max mem: 9390 +Eval (hcp-val): [76] Total time: 0:00:13 (0.2184 s / it) +Averaged stats (hcp-val): loss: 0.8293 (0.8309) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +Train: [77] [ 0/6250] eta: 12:08:32 lr: 0.000017 grad: 0.1773 (0.1773) loss: 0.8091 (0.8091) time: 6.9941 data: 6.8612 max mem: 9390 +Train: [77] [ 100/6250] eta: 0:24:44 lr: 0.000017 grad: 0.1404 (0.1727) loss: 0.8192 (0.8243) time: 0.2012 data: 0.1067 max mem: 9390 +Train: [77] [ 200/6250] eta: 0:23:19 lr: 0.000017 grad: 0.1356 (0.1562) loss: 0.8073 (0.8190) time: 0.2801 data: 0.1811 max mem: 9390 +Train: [77] [ 300/6250] eta: 0:21:19 lr: 0.000017 grad: 0.1356 (0.1484) loss: 0.8068 (0.8162) time: 0.2179 data: 0.1271 max mem: 9390 +Train: [77] [ 400/6250] eta: 0:19:29 lr: 0.000017 grad: 0.1220 (0.1427) loss: 0.8092 (0.8148) time: 0.1581 data: 0.0604 max mem: 9390 +Train: [77] [ 500/6250] eta: 0:18:29 lr: 0.000017 grad: 0.1230 (0.1393) loss: 0.8162 (0.8145) time: 0.1726 data: 0.0839 max mem: 9390 +Train: [77] [ 600/6250] eta: 0:18:05 lr: 0.000017 grad: 0.1241 (0.1370) loss: 0.8201 (0.8149) time: 0.1374 data: 0.0416 max mem: 9390 +Train: [77] [ 700/6250] eta: 0:17:43 lr: 0.000017 grad: 0.1242 (0.1354) loss: 0.8104 (0.8148) time: 0.1515 data: 0.0462 max mem: 9390 +Train: [77] [ 800/6250] eta: 0:17:05 lr: 0.000017 grad: 0.1174 (0.1341) loss: 0.8153 (0.8149) time: 0.1773 data: 0.0960 max mem: 9390 +Train: [77] [ 900/6250] eta: 0:16:35 lr: 0.000017 grad: 0.1197 (0.1327) loss: 0.8160 (0.8150) time: 0.1881 data: 0.1020 max mem: 9390 +Train: [77] [1000/6250] eta: 0:16:10 lr: 0.000017 grad: 0.1225 (0.1315) loss: 0.8118 (0.8150) time: 0.1605 data: 0.0741 max mem: 9390 +Train: [77] [1100/6250] eta: 0:15:37 lr: 0.000017 grad: 0.1235 (0.1309) loss: 0.8083 (0.8149) time: 0.1926 data: 0.1160 max mem: 9390 +Train: [77] [1200/6250] eta: 0:15:09 lr: 0.000017 grad: 0.1194 (0.1302) loss: 0.8084 (0.8146) time: 0.1641 data: 0.0854 max mem: 9390 +Train: [77] [1300/6250] eta: 0:14:42 lr: 0.000017 grad: 0.1197 (0.1296) loss: 0.8103 (0.8143) time: 0.1660 data: 0.0870 max mem: 9390 +Train: [77] [1400/6250] eta: 0:14:25 lr: 0.000017 grad: 0.1247 (0.1292) loss: 0.8067 (0.8139) time: 0.1913 data: 0.1179 max mem: 9390 +Train: [77] [1500/6250] eta: 0:13:59 lr: 0.000017 grad: 0.1213 (0.1287) loss: 0.8088 (0.8135) time: 0.1964 data: 0.1151 max mem: 9390 +Train: [77] [1600/6250] eta: 0:13:40 lr: 0.000017 grad: 0.1173 (0.1283) loss: 0.8107 (0.8133) time: 0.1668 data: 0.0837 max mem: 9390 +Train: [77] [1700/6250] eta: 0:13:18 lr: 0.000017 grad: 0.1169 (0.1279) loss: 0.8093 (0.8133) time: 0.1829 data: 0.1053 max mem: 9390 +Train: [77] [1800/6250] eta: 0:12:56 lr: 0.000017 grad: 0.1241 (0.1277) loss: 0.8089 (0.8131) time: 0.1586 data: 0.0714 max mem: 9390 +Train: [77] [1900/6250] eta: 0:12:33 lr: 0.000017 grad: 0.1177 (0.1275) loss: 0.8117 (0.8130) time: 0.1549 data: 0.0685 max mem: 9390 +Train: [77] [2000/6250] eta: 0:12:14 lr: 0.000017 grad: 0.1157 (0.1273) loss: 0.8144 (0.8130) time: 0.1497 data: 0.0632 max mem: 9390 +Train: [77] [2100/6250] eta: 0:11:58 lr: 0.000017 grad: 0.1118 (0.1269) loss: 0.8138 (0.8130) time: 0.2169 data: 0.1339 max mem: 9390 +Train: [77] [2200/6250] eta: 0:11:44 lr: 0.000017 grad: 0.1228 (0.1267) loss: 0.8105 (0.8131) time: 0.1382 data: 0.0349 max mem: 9390 +Train: [77] [2300/6250] eta: 0:11:27 lr: 0.000017 grad: 0.1195 (0.1267) loss: 0.8075 (0.8130) time: 0.1265 data: 0.0180 max mem: 9390 +Train: [77] [2400/6250] eta: 0:11:15 lr: 0.000017 grad: 0.1236 (0.1266) loss: 0.8062 (0.8130) time: 0.3653 data: 0.2683 max mem: 9390 +Train: [77] [2500/6250] eta: 0:10:53 lr: 0.000017 grad: 0.1240 (0.1266) loss: 0.8096 (0.8129) time: 0.2023 data: 0.1113 max mem: 9390 +Train: [77] [2600/6250] eta: 0:10:33 lr: 0.000017 grad: 0.1210 (0.1265) loss: 0.8141 (0.8128) time: 0.1516 data: 0.0596 max mem: 9390 +Train: [77] [2700/6250] eta: 0:10:13 lr: 0.000017 grad: 0.1202 (0.1264) loss: 0.8084 (0.8128) time: 0.1748 data: 0.0911 max mem: 9390 +Train: [77] [2800/6250] eta: 0:10:04 lr: 0.000017 grad: 0.1229 (0.1264) loss: 0.8127 (0.8128) time: 0.2349 data: 0.1458 max mem: 9390 +Train: [77] [2900/6250] eta: 0:09:42 lr: 0.000017 grad: 0.1366 (0.1265) loss: 0.8090 (0.8127) time: 0.1551 data: 0.0757 max mem: 9390 +Train: [77] [3000/6250] eta: 0:09:25 lr: 0.000017 grad: 0.1184 (0.1265) loss: 0.8194 (0.8128) time: 0.2096 data: 0.1072 max mem: 9390 +Train: [77] [3100/6250] eta: 0:09:05 lr: 0.000017 grad: 0.1268 (0.1264) loss: 0.8130 (0.8128) time: 0.1510 data: 0.0678 max mem: 9390 +Train: [77] [3200/6250] eta: 0:08:47 lr: 0.000017 grad: 0.1257 (0.1263) loss: 0.8161 (0.8128) time: 0.2141 data: 0.1339 max mem: 9390 +Train: [77] [3300/6250] eta: 0:08:28 lr: 0.000016 grad: 0.1213 (0.1263) loss: 0.8156 (0.8129) time: 0.1846 data: 0.1080 max mem: 9390 +Train: [77] [3400/6250] eta: 0:08:10 lr: 0.000016 grad: 0.1256 (0.1262) loss: 0.8129 (0.8129) time: 0.1864 data: 0.0940 max mem: 9390 +Train: [77] [3500/6250] eta: 0:07:52 lr: 0.000016 grad: 0.1219 (0.1261) loss: 0.8189 (0.8130) time: 0.1520 data: 0.0666 max mem: 9390 +Train: [77] [3600/6250] eta: 0:07:36 lr: 0.000016 grad: 0.1258 (0.1261) loss: 0.8151 (0.8131) time: 0.1309 data: 0.0003 max mem: 9390 +Train: [77] [3700/6250] eta: 0:07:18 lr: 0.000016 grad: 0.1205 (0.1260) loss: 0.8143 (0.8131) time: 0.1310 data: 0.0252 max mem: 9390 +Train: [77] [3800/6250] eta: 0:07:01 lr: 0.000016 grad: 0.1167 (0.1259) loss: 0.8119 (0.8131) time: 0.2383 data: 0.1434 max mem: 9390 +Train: [77] [3900/6250] eta: 0:06:42 lr: 0.000016 grad: 0.1216 (0.1259) loss: 0.8161 (0.8131) time: 0.1631 data: 0.0824 max mem: 9390 +Train: [77] [4000/6250] eta: 0:06:25 lr: 0.000016 grad: 0.1192 (0.1260) loss: 0.8112 (0.8131) time: 0.1402 data: 0.0441 max mem: 9390 +Train: [77] [4100/6250] eta: 0:06:07 lr: 0.000016 grad: 0.1255 (0.1261) loss: 0.8142 (0.8131) time: 0.1725 data: 0.0825 max mem: 9390 +Train: [77] [4200/6250] eta: 0:05:52 lr: 0.000016 grad: 0.1263 (0.1261) loss: 0.8054 (0.8131) time: 0.1060 data: 0.0004 max mem: 9390 +Train: [77] [4300/6250] eta: 0:05:34 lr: 0.000016 grad: 0.1212 (0.1261) loss: 0.8200 (0.8132) time: 0.2376 data: 0.1440 max mem: 9390 +Train: [77] [4400/6250] eta: 0:05:16 lr: 0.000016 grad: 0.1257 (0.1261) loss: 0.8192 (0.8132) time: 0.1427 data: 0.0481 max mem: 9390 +Train: [77] [4500/6250] eta: 0:04:59 lr: 0.000016 grad: 0.1190 (0.1261) loss: 0.8188 (0.8133) time: 0.2453 data: 0.1668 max mem: 9390 +Train: [77] [4600/6250] eta: 0:04:42 lr: 0.000016 grad: 0.1296 (0.1261) loss: 0.8135 (0.8133) time: 0.1810 data: 0.1017 max mem: 9390 +Train: [77] [4700/6250] eta: 0:04:24 lr: 0.000016 grad: 0.1255 (0.1262) loss: 0.8144 (0.8133) time: 0.1721 data: 0.0907 max mem: 9390 +Train: [77] [4800/6250] eta: 0:04:07 lr: 0.000016 grad: 0.1186 (0.1263) loss: 0.8181 (0.8133) time: 0.1513 data: 0.0710 max mem: 9390 +Train: [77] [4900/6250] eta: 0:03:50 lr: 0.000016 grad: 0.1237 (0.1264) loss: 0.8133 (0.8133) time: 0.1648 data: 0.0781 max mem: 9390 +Train: [77] [5000/6250] eta: 0:03:32 lr: 0.000016 grad: 0.1337 (0.1265) loss: 0.8074 (0.8133) time: 0.1661 data: 0.0799 max mem: 9390 +Train: [77] [5100/6250] eta: 0:03:15 lr: 0.000016 grad: 0.1200 (0.1266) loss: 0.8096 (0.8132) time: 0.1621 data: 0.0736 max mem: 9390 +Train: [77] [5200/6250] eta: 0:02:57 lr: 0.000016 grad: 0.1212 (0.1267) loss: 0.8168 (0.8132) time: 0.1423 data: 0.0619 max mem: 9390 +Train: [77] [5300/6250] eta: 0:02:40 lr: 0.000016 grad: 0.1169 (0.1267) loss: 0.8155 (0.8132) time: 0.1305 data: 0.0467 max mem: 9390 +Train: [77] [5400/6250] eta: 0:02:23 lr: 0.000016 grad: 0.1194 (0.1267) loss: 0.8205 (0.8132) time: 0.1148 data: 0.0268 max mem: 9390 +Train: [77] [5500/6250] eta: 0:02:06 lr: 0.000016 grad: 0.1223 (0.1267) loss: 0.8141 (0.8132) time: 0.1616 data: 0.0711 max mem: 9390 +Train: [77] [5600/6250] eta: 0:01:49 lr: 0.000016 grad: 0.1238 (0.1268) loss: 0.8148 (0.8132) time: 0.1483 data: 0.0593 max mem: 9390 +Train: [77] [5700/6250] eta: 0:01:32 lr: 0.000016 grad: 0.1222 (0.1268) loss: 0.8161 (0.8132) time: 0.1455 data: 0.0525 max mem: 9390 +Train: [77] [5800/6250] eta: 0:01:15 lr: 0.000016 grad: 0.1266 (0.1269) loss: 0.8136 (0.8132) time: 0.1246 data: 0.0357 max mem: 9390 +Train: [77] [5900/6250] eta: 0:00:58 lr: 0.000016 grad: 0.1230 (0.1270) loss: 0.8180 (0.8132) time: 0.1738 data: 0.0791 max mem: 9390 +Train: [77] [6000/6250] eta: 0:00:41 lr: 0.000016 grad: 0.1195 (0.1271) loss: 0.8163 (0.8131) time: 0.1981 data: 0.0962 max mem: 9390 +Train: [77] [6100/6250] eta: 0:00:25 lr: 0.000016 grad: 0.1108 (0.1271) loss: 0.8221 (0.8131) time: 0.1456 data: 0.0507 max mem: 9390 +Train: [77] [6200/6250] eta: 0:00:08 lr: 0.000016 grad: 0.1190 (0.1271) loss: 0.8145 (0.8132) time: 0.1415 data: 0.0568 max mem: 9390 +Train: [77] [6249/6250] eta: 0:00:00 lr: 0.000016 grad: 0.1206 (0.1271) loss: 0.8175 (0.8132) time: 0.2207 data: 0.1227 max mem: 9390 +Train: [77] Total time: 0:17:34 (0.1687 s / it) +Averaged stats: lr: 0.000016 grad: 0.1206 (0.1271) loss: 0.8175 (0.8132) +Eval (hcp-train-subset): [77] [ 0/62] eta: 0:05:19 loss: 0.8347 (0.8347) time: 5.1583 data: 5.1261 max mem: 9390 +Eval (hcp-train-subset): [77] [61/62] eta: 0:00:00 loss: 0.8225 (0.8257) time: 0.1463 data: 0.1213 max mem: 9390 +Eval (hcp-train-subset): [77] Total time: 0:00:13 (0.2217 s / it) +Averaged stats (hcp-train-subset): loss: 0.8225 (0.8257) +Eval (hcp-val): [77] [ 0/62] eta: 0:05:29 loss: 0.8244 (0.8244) time: 5.3097 data: 5.2801 max mem: 9390 +Eval (hcp-val): [77] [61/62] eta: 0:00:00 loss: 0.8296 (0.8306) time: 0.1630 data: 0.1379 max mem: 9390 +Eval (hcp-val): [77] Total time: 0:00:14 (0.2373 s / it) +Averaged stats (hcp-val): loss: 0.8296 (0.8306) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +Train: [78] [ 0/6250] eta: 10:23:13 lr: 0.000016 grad: 0.0826 (0.0826) loss: 0.8795 (0.8795) time: 5.9829 data: 5.8744 max mem: 9390 +Train: [78] [ 100/6250] eta: 0:24:55 lr: 0.000016 grad: 0.1469 (0.1504) loss: 0.8303 (0.8314) time: 0.2389 data: 0.1377 max mem: 9390 +Train: [78] [ 200/6250] eta: 0:21:36 lr: 0.000016 grad: 0.1221 (0.1432) loss: 0.8194 (0.8256) time: 0.1632 data: 0.0505 max mem: 9390 +Train: [78] [ 300/6250] eta: 0:19:58 lr: 0.000016 grad: 0.1268 (0.1381) loss: 0.8236 (0.8224) time: 0.1872 data: 0.0917 max mem: 9390 +Train: [78] [ 400/6250] eta: 0:19:13 lr: 0.000016 grad: 0.1260 (0.1372) loss: 0.8057 (0.8202) time: 0.2048 data: 0.1092 max mem: 9390 +Train: [78] [ 500/6250] eta: 0:18:36 lr: 0.000016 grad: 0.1259 (0.1354) loss: 0.8160 (0.8190) time: 0.1043 data: 0.0206 max mem: 9390 +Train: [78] [ 600/6250] eta: 0:18:05 lr: 0.000016 grad: 0.1248 (0.1336) loss: 0.8053 (0.8184) time: 0.2532 data: 0.1502 max mem: 9390 +Train: [78] [ 700/6250] eta: 0:17:20 lr: 0.000016 grad: 0.1104 (0.1325) loss: 0.8209 (0.8183) time: 0.1665 data: 0.0868 max mem: 9390 +Train: [78] [ 800/6250] eta: 0:17:03 lr: 0.000016 grad: 0.1223 (0.1315) loss: 0.8127 (0.8182) time: 0.2502 data: 0.1446 max mem: 9390 +Train: [78] [ 900/6250] eta: 0:16:35 lr: 0.000016 grad: 0.1195 (0.1310) loss: 0.8182 (0.8178) time: 0.1156 data: 0.0002 max mem: 9390 +Train: [78] [1000/6250] eta: 0:16:05 lr: 0.000016 grad: 0.1339 (0.1307) loss: 0.8153 (0.8173) time: 0.1554 data: 0.0580 max mem: 9390 +Train: [78] [1100/6250] eta: 0:15:39 lr: 0.000016 grad: 0.1257 (0.1305) loss: 0.8130 (0.8171) time: 0.1454 data: 0.0646 max mem: 9390 +Train: [78] [1200/6250] eta: 0:15:12 lr: 0.000016 grad: 0.1236 (0.1302) loss: 0.8084 (0.8168) time: 0.1753 data: 0.0889 max mem: 9390 +Train: [78] [1300/6250] eta: 0:14:47 lr: 0.000016 grad: 0.1182 (0.1299) loss: 0.8085 (0.8166) time: 0.1467 data: 0.0659 max mem: 9390 +Train: [78] [1400/6250] eta: 0:14:20 lr: 0.000016 grad: 0.1231 (0.1296) loss: 0.8087 (0.8164) time: 0.1543 data: 0.0588 max mem: 9390 +Train: [78] [1500/6250] eta: 0:13:59 lr: 0.000015 grad: 0.1304 (0.1295) loss: 0.8099 (0.8162) time: 0.1667 data: 0.0805 max mem: 9390 +Train: [78] [1600/6250] eta: 0:13:44 lr: 0.000015 grad: 0.1234 (0.1292) loss: 0.8106 (0.8159) time: 0.2485 data: 0.1433 max mem: 9390 +Train: [78] [1700/6250] eta: 0:13:16 lr: 0.000015 grad: 0.1208 (0.1292) loss: 0.8114 (0.8156) time: 0.1704 data: 0.0765 max mem: 9390 +Train: [78] [1800/6250] eta: 0:13:01 lr: 0.000015 grad: 0.1264 (0.1292) loss: 0.8076 (0.8154) time: 0.1937 data: 0.0987 max mem: 9390 +Train: [78] [1900/6250] eta: 0:12:37 lr: 0.000015 grad: 0.1367 (0.1294) loss: 0.7979 (0.8151) time: 0.1821 data: 0.0690 max mem: 9390 +Train: [78] [2000/6250] eta: 0:12:21 lr: 0.000015 grad: 0.1332 (0.1296) loss: 0.8094 (0.8148) time: 0.2150 data: 0.1249 max mem: 9390 +Train: [78] [2100/6250] eta: 0:12:16 lr: 0.000015 grad: 0.1356 (0.1299) loss: 0.8100 (0.8145) time: 0.0893 data: 0.0002 max mem: 9390 +Train: [78] [2200/6250] eta: 0:11:57 lr: 0.000015 grad: 0.1279 (0.1300) loss: 0.8063 (0.8142) time: 0.2236 data: 0.1236 max mem: 9390 +Train: [78] [2300/6250] eta: 0:11:36 lr: 0.000015 grad: 0.1292 (0.1301) loss: 0.8082 (0.8139) time: 0.1817 data: 0.1014 max mem: 9390 +Train: [78] [2400/6250] eta: 0:11:22 lr: 0.000015 grad: 0.1316 (0.1303) loss: 0.8063 (0.8135) time: 0.1484 data: 0.0611 max mem: 9390 +Train: [78] [2500/6250] eta: 0:11:00 lr: 0.000015 grad: 0.1343 (0.1305) loss: 0.8017 (0.8131) time: 0.1370 data: 0.0548 max mem: 9390 +Train: [78] [2600/6250] eta: 0:10:41 lr: 0.000015 grad: 0.1315 (0.1306) loss: 0.8079 (0.8128) time: 0.1254 data: 0.0455 max mem: 9390 +Train: [78] [2700/6250] eta: 0:10:20 lr: 0.000015 grad: 0.1270 (0.1307) loss: 0.8051 (0.8125) time: 0.1354 data: 0.0516 max mem: 9390 +Train: [78] [2800/6250] eta: 0:10:00 lr: 0.000015 grad: 0.1287 (0.1306) loss: 0.8088 (0.8123) time: 0.1560 data: 0.0770 max mem: 9390 +Train: [78] [2900/6250] eta: 0:09:47 lr: 0.000015 grad: 0.1311 (0.1305) loss: 0.8142 (0.8121) time: 0.0919 data: 0.0002 max mem: 9390 +Train: [78] [3000/6250] eta: 0:09:27 lr: 0.000015 grad: 0.1213 (0.1305) loss: 0.8064 (0.8120) time: 0.1141 data: 0.0267 max mem: 9390 +Train: [78] [3100/6250] eta: 0:09:09 lr: 0.000015 grad: 0.1243 (0.1304) loss: 0.8039 (0.8118) time: 0.1518 data: 0.0690 max mem: 9390 +Train: [78] [3200/6250] eta: 0:08:50 lr: 0.000015 grad: 0.1318 (0.1305) loss: 0.8053 (0.8116) time: 0.2050 data: 0.1205 max mem: 9390 +Train: [78] [3300/6250] eta: 0:08:31 lr: 0.000015 grad: 0.1280 (0.1306) loss: 0.8081 (0.8114) time: 0.1808 data: 0.0864 max mem: 9390 +Train: [78] [3400/6250] eta: 0:08:16 lr: 0.000015 grad: 0.1262 (0.1306) loss: 0.8079 (0.8113) time: 0.3157 data: 0.2170 max mem: 9390 +Train: [78] [3500/6250] eta: 0:07:57 lr: 0.000015 grad: 0.1307 (0.1307) loss: 0.7967 (0.8111) time: 0.1113 data: 0.0002 max mem: 9390 +Train: [78] [3600/6250] eta: 0:07:39 lr: 0.000015 grad: 0.1357 (0.1308) loss: 0.8050 (0.8109) time: 0.1658 data: 0.0773 max mem: 9390 +Train: [78] [3700/6250] eta: 0:07:22 lr: 0.000015 grad: 0.1296 (0.1308) loss: 0.8008 (0.8107) time: 0.0934 data: 0.0002 max mem: 9390 +Train: [78] [3800/6250] eta: 0:07:05 lr: 0.000015 grad: 0.1303 (0.1308) loss: 0.8050 (0.8105) time: 0.1671 data: 0.0747 max mem: 9390 +Train: [78] [3900/6250] eta: 0:06:48 lr: 0.000015 grad: 0.1345 (0.1308) loss: 0.8057 (0.8104) time: 0.1960 data: 0.1031 max mem: 9390 +Train: [78] [4000/6250] eta: 0:06:30 lr: 0.000015 grad: 0.1213 (0.1309) loss: 0.8067 (0.8102) time: 0.0974 data: 0.0004 max mem: 9390 +Train: [78] [4100/6250] eta: 0:06:12 lr: 0.000015 grad: 0.1276 (0.1310) loss: 0.8146 (0.8102) time: 0.1037 data: 0.0158 max mem: 9390 +Train: [78] [4200/6250] eta: 0:05:55 lr: 0.000015 grad: 0.1288 (0.1309) loss: 0.8101 (0.8101) time: 0.1206 data: 0.0276 max mem: 9390 +Train: [78] [4300/6250] eta: 0:05:40 lr: 0.000015 grad: 0.1248 (0.1308) loss: 0.8077 (0.8100) time: 0.0788 data: 0.0001 max mem: 9390 +Train: [78] [4400/6250] eta: 0:05:24 lr: 0.000015 grad: 0.1226 (0.1308) loss: 0.8181 (0.8100) time: 0.4008 data: 0.3092 max mem: 9390 +Train: [78] [4500/6250] eta: 0:05:05 lr: 0.000015 grad: 0.1209 (0.1308) loss: 0.8169 (0.8100) time: 0.1669 data: 0.0670 max mem: 9390 +Train: [78] [4600/6250] eta: 0:04:47 lr: 0.000015 grad: 0.1206 (0.1306) loss: 0.8122 (0.8100) time: 0.2179 data: 0.1304 max mem: 9390 +Train: [78] [4700/6250] eta: 0:04:30 lr: 0.000015 grad: 0.1253 (0.1306) loss: 0.8064 (0.8100) time: 0.1455 data: 0.0599 max mem: 9390 +Train: [78] [4800/6250] eta: 0:04:12 lr: 0.000015 grad: 0.1181 (0.1305) loss: 0.8137 (0.8101) time: 0.0970 data: 0.0002 max mem: 9390 +Train: [78] [4900/6250] eta: 0:03:54 lr: 0.000015 grad: 0.1263 (0.1305) loss: 0.8098 (0.8101) time: 0.1720 data: 0.0909 max mem: 9390 +Train: [78] [5000/6250] eta: 0:03:36 lr: 0.000015 grad: 0.1282 (0.1305) loss: 0.8134 (0.8101) time: 0.1173 data: 0.0298 max mem: 9390 +Train: [78] [5100/6250] eta: 0:03:19 lr: 0.000015 grad: 0.1193 (0.1305) loss: 0.8225 (0.8102) time: 0.0939 data: 0.0004 max mem: 9390 +Train: [78] [5200/6250] eta: 0:03:01 lr: 0.000015 grad: 0.1233 (0.1304) loss: 0.8143 (0.8103) time: 0.1825 data: 0.1062 max mem: 9390 +Train: [78] [5300/6250] eta: 0:02:44 lr: 0.000015 grad: 0.1174 (0.1304) loss: 0.8127 (0.8103) time: 0.1974 data: 0.1200 max mem: 9390 +Train: [78] [5400/6250] eta: 0:02:26 lr: 0.000015 grad: 0.1209 (0.1303) loss: 0.8072 (0.8103) time: 0.1676 data: 0.0872 max mem: 9390 +Train: [78] [5500/6250] eta: 0:02:09 lr: 0.000015 grad: 0.1209 (0.1303) loss: 0.8197 (0.8104) time: 0.1801 data: 0.0960 max mem: 9390 +Train: [78] [5600/6250] eta: 0:01:52 lr: 0.000015 grad: 0.1289 (0.1303) loss: 0.8093 (0.8104) time: 0.1223 data: 0.0447 max mem: 9390 +Train: [78] [5700/6250] eta: 0:01:35 lr: 0.000015 grad: 0.1251 (0.1303) loss: 0.8061 (0.8104) time: 0.1327 data: 0.0461 max mem: 9390 +Train: [78] [5800/6250] eta: 0:01:17 lr: 0.000015 grad: 0.1273 (0.1302) loss: 0.8044 (0.8104) time: 0.1521 data: 0.0755 max mem: 9390 +Train: [78] [5900/6250] eta: 0:01:00 lr: 0.000015 grad: 0.1261 (0.1302) loss: 0.8114 (0.8103) time: 0.1682 data: 0.0850 max mem: 9390 +Train: [78] [6000/6250] eta: 0:00:43 lr: 0.000015 grad: 0.1361 (0.1303) loss: 0.8146 (0.8103) time: 0.1324 data: 0.0520 max mem: 9390 +Train: [78] [6100/6250] eta: 0:00:25 lr: 0.000015 grad: 0.1339 (0.1303) loss: 0.8060 (0.8103) time: 0.1643 data: 0.0831 max mem: 9390 +Train: [78] [6200/6250] eta: 0:00:08 lr: 0.000014 grad: 0.1296 (0.1304) loss: 0.8068 (0.8103) time: 0.2006 data: 0.1149 max mem: 9390 +Train: [78] [6249/6250] eta: 0:00:00 lr: 0.000014 grad: 0.1338 (0.1304) loss: 0.8068 (0.8103) time: 0.2531 data: 0.1515 max mem: 9390 +Train: [78] Total time: 0:18:04 (0.1735 s / it) +Averaged stats: lr: 0.000014 grad: 0.1338 (0.1304) loss: 0.8068 (0.8103) +Eval (hcp-train-subset): [78] [ 0/62] eta: 0:05:58 loss: 0.8286 (0.8286) time: 5.7864 data: 5.7553 max mem: 9390 +Eval (hcp-train-subset): [78] [61/62] eta: 0:00:00 loss: 0.8232 (0.8248) time: 0.1432 data: 0.1177 max mem: 9390 +Eval (hcp-train-subset): [78] Total time: 0:00:15 (0.2459 s / it) +Averaged stats (hcp-train-subset): loss: 0.8232 (0.8248) +Eval (hcp-val): [78] [ 0/62] eta: 0:03:35 loss: 0.8311 (0.8311) time: 3.4684 data: 3.3943 max mem: 9390 +Eval (hcp-val): [78] [61/62] eta: 0:00:00 loss: 0.8307 (0.8308) time: 0.1525 data: 0.1272 max mem: 9390 +Eval (hcp-val): [78] Total time: 0:00:15 (0.2470 s / it) +Averaged stats (hcp-val): loss: 0.8307 (0.8308) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +Train: [79] [ 0/6250] eta: 14:54:55 lr: 0.000014 grad: 0.1011 (0.1011) loss: 0.8565 (0.8565) time: 8.5912 data: 8.4803 max mem: 9390 +Train: [79] [ 100/6250] eta: 0:27:04 lr: 0.000014 grad: 0.1335 (0.1437) loss: 0.8157 (0.8281) time: 0.1816 data: 0.0641 max mem: 9390 +Train: [79] [ 200/6250] eta: 0:25:09 lr: 0.000014 grad: 0.1360 (0.1452) loss: 0.8097 (0.8225) time: 0.2441 data: 0.1313 max mem: 9390 +Train: [79] [ 300/6250] eta: 0:23:29 lr: 0.000014 grad: 0.1355 (0.1465) loss: 0.8060 (0.8179) time: 0.3007 data: 0.2015 max mem: 9390 +Train: [79] [ 400/6250] eta: 0:21:47 lr: 0.000014 grad: 0.1246 (0.1449) loss: 0.8169 (0.8159) time: 0.2317 data: 0.1429 max mem: 9390 +Train: [79] [ 500/6250] eta: 0:20:35 lr: 0.000014 grad: 0.1171 (0.1426) loss: 0.8204 (0.8152) time: 0.2543 data: 0.1648 max mem: 9390 +Train: [79] [ 600/6250] eta: 0:19:42 lr: 0.000014 grad: 0.1254 (0.1406) loss: 0.8109 (0.8153) time: 0.1444 data: 0.0494 max mem: 9390 +Train: [79] [ 700/6250] eta: 0:19:20 lr: 0.000014 grad: 0.1225 (0.1389) loss: 0.8077 (0.8151) time: 0.1184 data: 0.0003 max mem: 9390 +Train: [79] [ 800/6250] eta: 0:19:19 lr: 0.000014 grad: 0.1167 (0.1375) loss: 0.8206 (0.8152) time: 0.1627 data: 0.0759 max mem: 9390 +Train: [79] [ 900/6250] eta: 0:18:40 lr: 0.000014 grad: 0.1161 (0.1361) loss: 0.8193 (0.8153) time: 0.2165 data: 0.1257 max mem: 9390 +Train: [79] [1000/6250] eta: 0:18:12 lr: 0.000014 grad: 0.1332 (0.1354) loss: 0.8111 (0.8151) time: 0.3187 data: 0.2335 max mem: 9390 +Train: [79] [1100/6250] eta: 0:17:34 lr: 0.000014 grad: 0.1226 (0.1344) loss: 0.8165 (0.8150) time: 0.2991 data: 0.2228 max mem: 9390 +Train: [79] [1200/6250] eta: 0:16:55 lr: 0.000014 grad: 0.1302 (0.1337) loss: 0.8161 (0.8150) time: 0.1735 data: 0.0956 max mem: 9390 +Train: [79] [1300/6250] eta: 0:16:21 lr: 0.000014 grad: 0.1282 (0.1334) loss: 0.8152 (0.8147) time: 0.2105 data: 0.1309 max mem: 9390 +Train: [79] [1400/6250] eta: 0:15:44 lr: 0.000014 grad: 0.1293 (0.1328) loss: 0.8117 (0.8147) time: 0.1509 data: 0.0702 max mem: 9390 +Train: [79] [1500/6250] eta: 0:15:17 lr: 0.000014 grad: 0.1186 (0.1323) loss: 0.8175 (0.8148) time: 0.1950 data: 0.1050 max mem: 9390 +Train: [79] [1600/6250] eta: 0:14:46 lr: 0.000014 grad: 0.1252 (0.1319) loss: 0.8124 (0.8148) time: 0.1197 data: 0.0319 max mem: 9390 +Train: [79] [1700/6250] eta: 0:14:18 lr: 0.000014 grad: 0.1229 (0.1316) loss: 0.8214 (0.8148) time: 0.1361 data: 0.0529 max mem: 9390 +Train: [79] [1800/6250] eta: 0:13:51 lr: 0.000014 grad: 0.1268 (0.1315) loss: 0.8077 (0.8146) time: 0.1264 data: 0.0373 max mem: 9390 +Train: [79] [1900/6250] eta: 0:13:25 lr: 0.000014 grad: 0.1235 (0.1314) loss: 0.8180 (0.8145) time: 0.1332 data: 0.0444 max mem: 9390 +Train: [79] [2000/6250] eta: 0:13:01 lr: 0.000014 grad: 0.1214 (0.1311) loss: 0.8154 (0.8145) time: 0.1598 data: 0.0750 max mem: 9390 +Train: [79] [2100/6250] eta: 0:12:36 lr: 0.000014 grad: 0.1240 (0.1309) loss: 0.8105 (0.8145) time: 0.1510 data: 0.0689 max mem: 9390 +Train: [79] [2200/6250] eta: 0:12:15 lr: 0.000014 grad: 0.1203 (0.1306) loss: 0.8143 (0.8144) time: 0.2235 data: 0.1319 max mem: 9390 +Train: [79] [2300/6250] eta: 0:11:51 lr: 0.000014 grad: 0.1291 (0.1303) loss: 0.8172 (0.8144) time: 0.1562 data: 0.0659 max mem: 9390 +Train: [79] [2400/6250] eta: 0:11:31 lr: 0.000014 grad: 0.1224 (0.1300) loss: 0.8136 (0.8144) time: 0.1103 data: 0.0127 max mem: 9390 +Train: [79] [2500/6250] eta: 0:11:11 lr: 0.000014 grad: 0.1194 (0.1298) loss: 0.8195 (0.8145) time: 0.1740 data: 0.0840 max mem: 9390 +Train: [79] [2600/6250] eta: 0:10:52 lr: 0.000014 grad: 0.1213 (0.1296) loss: 0.8152 (0.8145) time: 0.2233 data: 0.1313 max mem: 9390 +Train: [79] [2700/6250] eta: 0:10:33 lr: 0.000014 grad: 0.1266 (0.1295) loss: 0.8188 (0.8146) time: 0.0960 data: 0.0003 max mem: 9390 +Train: [79] [2800/6250] eta: 0:10:13 lr: 0.000014 grad: 0.1264 (0.1293) loss: 0.8143 (0.8146) time: 0.1813 data: 0.0956 max mem: 9390 +Train: [79] [2900/6250] eta: 0:09:54 lr: 0.000014 grad: 0.1260 (0.1292) loss: 0.8215 (0.8146) time: 0.1138 data: 0.0203 max mem: 9390 +Train: [79] [3000/6250] eta: 0:09:39 lr: 0.000014 grad: 0.1172 (0.1291) loss: 0.8181 (0.8147) time: 0.3327 data: 0.2432 max mem: 9390 +Train: [79] [3100/6250] eta: 0:09:20 lr: 0.000014 grad: 0.1300 (0.1292) loss: 0.8120 (0.8147) time: 0.1804 data: 0.0869 max mem: 9390 +Train: [79] [3200/6250] eta: 0:09:03 lr: 0.000014 grad: 0.1184 (0.1291) loss: 0.8148 (0.8147) time: 0.2877 data: 0.2000 max mem: 9390 +Train: [79] [3300/6250] eta: 0:08:45 lr: 0.000014 grad: 0.1194 (0.1290) loss: 0.8226 (0.8147) time: 0.1177 data: 0.0003 max mem: 9390 +Train: [79] [3400/6250] eta: 0:08:27 lr: 0.000014 grad: 0.1287 (0.1290) loss: 0.8161 (0.8146) time: 0.0961 data: 0.0055 max mem: 9390 +Train: [79] [3500/6250] eta: 0:08:09 lr: 0.000014 grad: 0.1268 (0.1289) loss: 0.8067 (0.8145) time: 0.2411 data: 0.1657 max mem: 9390 +Train: [79] [3600/6250] eta: 0:07:49 lr: 0.000014 grad: 0.1290 (0.1290) loss: 0.8058 (0.8144) time: 0.1604 data: 0.0737 max mem: 9390 +Train: [79] [3700/6250] eta: 0:07:31 lr: 0.000014 grad: 0.1298 (0.1289) loss: 0.8105 (0.8144) time: 0.1302 data: 0.0310 max mem: 9390 +Train: [79] [3800/6250] eta: 0:07:13 lr: 0.000014 grad: 0.1275 (0.1290) loss: 0.8125 (0.8143) time: 0.1533 data: 0.0666 max mem: 9390 +Train: [79] [3900/6250] eta: 0:06:58 lr: 0.000014 grad: 0.1218 (0.1289) loss: 0.8114 (0.8143) time: 0.2102 data: 0.1249 max mem: 9390 +Train: [79] [4000/6250] eta: 0:06:39 lr: 0.000014 grad: 0.1207 (0.1289) loss: 0.8183 (0.8143) time: 0.2000 data: 0.1245 max mem: 9390 +Train: [79] [4100/6250] eta: 0:06:22 lr: 0.000014 grad: 0.1192 (0.1288) loss: 0.8127 (0.8142) time: 0.1085 data: 0.0004 max mem: 9390 +Train: [79] [4200/6250] eta: 0:06:03 lr: 0.000014 grad: 0.1358 (0.1288) loss: 0.8064 (0.8142) time: 0.1324 data: 0.0430 max mem: 9390 +Train: [79] [4300/6250] eta: 0:05:44 lr: 0.000014 grad: 0.1219 (0.1288) loss: 0.8114 (0.8142) time: 0.1440 data: 0.0583 max mem: 9390 +Train: [79] [4400/6250] eta: 0:05:26 lr: 0.000014 grad: 0.1256 (0.1287) loss: 0.8104 (0.8142) time: 0.1866 data: 0.1001 max mem: 9390 +Train: [79] [4500/6250] eta: 0:05:09 lr: 0.000014 grad: 0.1213 (0.1286) loss: 0.8181 (0.8143) time: 0.1784 data: 0.1009 max mem: 9390 +Train: [79] [4600/6250] eta: 0:04:51 lr: 0.000014 grad: 0.1226 (0.1286) loss: 0.8192 (0.8144) time: 0.1328 data: 0.0568 max mem: 9390 +Train: [79] [4700/6250] eta: 0:04:33 lr: 0.000013 grad: 0.1218 (0.1286) loss: 0.8151 (0.8144) time: 0.2226 data: 0.1224 max mem: 9390 +Train: [79] [4800/6250] eta: 0:04:16 lr: 0.000013 grad: 0.1269 (0.1286) loss: 0.8161 (0.8144) time: 0.1416 data: 0.0641 max mem: 9390 +Train: [79] [4900/6250] eta: 0:03:58 lr: 0.000013 grad: 0.1181 (0.1285) loss: 0.8111 (0.8144) time: 0.1407 data: 0.0519 max mem: 9390 +Train: [79] [5000/6250] eta: 0:03:40 lr: 0.000013 grad: 0.1251 (0.1285) loss: 0.8183 (0.8144) time: 0.1785 data: 0.0965 max mem: 9390 +Train: [79] [5100/6250] eta: 0:03:22 lr: 0.000013 grad: 0.1261 (0.1285) loss: 0.8091 (0.8144) time: 0.1290 data: 0.0439 max mem: 9390 +Train: [79] [5200/6250] eta: 0:03:04 lr: 0.000013 grad: 0.1219 (0.1284) loss: 0.8170 (0.8144) time: 0.1383 data: 0.0537 max mem: 9390 +Train: [79] [5300/6250] eta: 0:02:46 lr: 0.000013 grad: 0.1245 (0.1284) loss: 0.8116 (0.8144) time: 0.2143 data: 0.1338 max mem: 9390 +Train: [79] [5400/6250] eta: 0:02:28 lr: 0.000013 grad: 0.1267 (0.1284) loss: 0.8131 (0.8144) time: 0.1281 data: 0.0438 max mem: 9390 +Train: [79] [5500/6250] eta: 0:02:10 lr: 0.000013 grad: 0.1313 (0.1284) loss: 0.8076 (0.8143) time: 0.1360 data: 0.0478 max mem: 9390 +Train: [79] [5600/6250] eta: 0:01:53 lr: 0.000013 grad: 0.1289 (0.1285) loss: 0.8084 (0.8143) time: 0.1541 data: 0.0689 max mem: 9390 +Train: [79] [5700/6250] eta: 0:01:35 lr: 0.000013 grad: 0.1316 (0.1286) loss: 0.8048 (0.8142) time: 0.1684 data: 0.0842 max mem: 9390 +Train: [79] [5800/6250] eta: 0:01:17 lr: 0.000013 grad: 0.1301 (0.1286) loss: 0.8125 (0.8141) time: 0.1346 data: 0.0425 max mem: 9390 +Train: [79] [5900/6250] eta: 0:01:00 lr: 0.000013 grad: 0.1274 (0.1286) loss: 0.8156 (0.8141) time: 0.1480 data: 0.0591 max mem: 9390 +Train: [79] [6000/6250] eta: 0:00:43 lr: 0.000013 grad: 0.1318 (0.1287) loss: 0.8184 (0.8140) time: 0.1703 data: 0.0942 max mem: 9390 +Train: [79] [6100/6250] eta: 0:00:25 lr: 0.000013 grad: 0.1263 (0.1287) loss: 0.8110 (0.8139) time: 0.1403 data: 0.0549 max mem: 9390 +Train: [79] [6200/6250] eta: 0:00:08 lr: 0.000013 grad: 0.1238 (0.1287) loss: 0.8155 (0.8139) time: 0.1321 data: 0.0504 max mem: 9390 +Train: [79] [6249/6250] eta: 0:00:00 lr: 0.000013 grad: 0.1206 (0.1287) loss: 0.8084 (0.8139) time: 0.2109 data: 0.1208 max mem: 9390 +Train: [79] Total time: 0:18:02 (0.1732 s / it) +Averaged stats: lr: 0.000013 grad: 0.1206 (0.1287) loss: 0.8084 (0.8139) +Eval (hcp-train-subset): [79] [ 0/62] eta: 0:04:02 loss: 0.8317 (0.8317) time: 3.9048 data: 3.8127 max mem: 9390 +Eval (hcp-train-subset): [79] [61/62] eta: 0:00:00 loss: 0.8207 (0.8248) time: 0.1739 data: 0.1479 max mem: 9390 +Eval (hcp-train-subset): [79] Total time: 0:00:16 (0.2622 s / it) +Averaged stats (hcp-train-subset): loss: 0.8207 (0.8248) +Making plots (hcp-train-subset): example=17 +Eval (hcp-val): [79] [ 0/62] eta: 0:05:41 loss: 0.8277 (0.8277) time: 5.5011 data: 5.4625 max mem: 9390 +Eval (hcp-val): [79] [61/62] eta: 0:00:00 loss: 0.8288 (0.8304) time: 0.1855 data: 0.1587 max mem: 9390 +Eval (hcp-val): [79] Total time: 0:00:16 (0.2712 s / it) +Averaged stats (hcp-val): loss: 0.8288 (0.8304) +Making plots (hcp-val): example=5 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +Train: [80] [ 0/6250] eta: 1 day, 2:06:04 lr: 0.000013 grad: 0.3372 (0.3372) loss: 0.7998 (0.7998) time: 15.0343 data: 14.9199 max mem: 9390 +Train: [80] [ 100/6250] eta: 0:32:14 lr: 0.000013 grad: 0.1388 (0.1674) loss: 0.8115 (0.8098) time: 0.2266 data: 0.1218 max mem: 9390 +Train: [80] [ 200/6250] eta: 0:26:51 lr: 0.000013 grad: 0.1191 (0.1536) loss: 0.8248 (0.8125) time: 0.2527 data: 0.1567 max mem: 9390 +Train: [80] [ 300/6250] eta: 0:23:18 lr: 0.000013 grad: 0.1275 (0.1460) loss: 0.8133 (0.8144) time: 0.1952 data: 0.0986 max mem: 9390 +Train: [80] [ 400/6250] eta: 0:22:13 lr: 0.000013 grad: 0.1273 (0.1426) loss: 0.8210 (0.8155) time: 0.3064 data: 0.2092 max mem: 9390 +Train: [80] [ 500/6250] eta: 0:20:41 lr: 0.000013 grad: 0.1284 (0.1402) loss: 0.8077 (0.8154) time: 0.1300 data: 0.0289 max mem: 9390 +Train: [80] [ 600/6250] eta: 0:19:45 lr: 0.000013 grad: 0.1214 (0.1382) loss: 0.8082 (0.8153) time: 0.1632 data: 0.0622 max mem: 9390 +Train: [80] [ 700/6250] eta: 0:19:09 lr: 0.000013 grad: 0.1321 (0.1374) loss: 0.8112 (0.8147) time: 0.2320 data: 0.1248 max mem: 9390 +Train: [80] [ 800/6250] eta: 0:18:19 lr: 0.000013 grad: 0.1257 (0.1366) loss: 0.8095 (0.8144) time: 0.1628 data: 0.0674 max mem: 9390 +Train: [80] [ 900/6250] eta: 0:17:59 lr: 0.000013 grad: 0.1336 (0.1363) loss: 0.8070 (0.8139) time: 0.1469 data: 0.0525 max mem: 9390 +Train: [80] [1000/6250] eta: 0:17:38 lr: 0.000013 grad: 0.1223 (0.1359) loss: 0.8161 (0.8137) time: 0.1195 data: 0.0350 max mem: 9390 +Train: [80] [1100/6250] eta: 0:17:05 lr: 0.000013 grad: 0.1372 (0.1355) loss: 0.8105 (0.8133) time: 0.2198 data: 0.1046 max mem: 9390 +Train: [80] [1200/6250] eta: 0:16:55 lr: 0.000013 grad: 0.1333 (0.1352) loss: 0.8073 (0.8129) time: 0.1042 data: 0.0003 max mem: 9390 +Train: [80] [1300/6250] eta: 0:16:20 lr: 0.000013 grad: 0.1384 (0.1353) loss: 0.8052 (0.8124) time: 0.1835 data: 0.1023 max mem: 9390 +Train: [80] [1400/6250] eta: 0:15:46 lr: 0.000013 grad: 0.1337 (0.1351) loss: 0.8126 (0.8121) time: 0.1590 data: 0.0745 max mem: 9390 +Train: [80] [1500/6250] eta: 0:15:15 lr: 0.000013 grad: 0.1212 (0.1347) loss: 0.8148 (0.8121) time: 0.1491 data: 0.0628 max mem: 9390 +Train: [80] [1600/6250] eta: 0:14:47 lr: 0.000013 grad: 0.1270 (0.1345) loss: 0.8034 (0.8118) time: 0.1192 data: 0.0420 max mem: 9390 +Train: [80] [1700/6250] eta: 0:14:20 lr: 0.000013 grad: 0.1316 (0.1344) loss: 0.8073 (0.8114) time: 0.1510 data: 0.0664 max mem: 9390 +Train: [80] [1800/6250] eta: 0:13:58 lr: 0.000013 grad: 0.1279 (0.1343) loss: 0.8118 (0.8111) time: 0.1044 data: 0.0003 max mem: 9390 +Train: [80] [1900/6250] eta: 0:13:39 lr: 0.000013 grad: 0.1232 (0.1340) loss: 0.8127 (0.8110) time: 0.1484 data: 0.0630 max mem: 9390 +Train: [80] [2000/6250] eta: 0:13:14 lr: 0.000013 grad: 0.1216 (0.1337) loss: 0.8082 (0.8109) time: 0.1969 data: 0.1132 max mem: 9390 +Train: [80] [2100/6250] eta: 0:13:03 lr: 0.000013 grad: 0.1284 (0.1335) loss: 0.8066 (0.8107) time: 0.1356 data: 0.0585 max mem: 9390 +Train: [80] [2200/6250] eta: 0:12:41 lr: 0.000013 grad: 0.1270 (0.1334) loss: 0.8072 (0.8106) time: 0.1003 data: 0.0005 max mem: 9390 +Train: [80] [2300/6250] eta: 0:12:29 lr: 0.000013 grad: 0.1305 (0.1334) loss: 0.8062 (0.8106) time: 0.1845 data: 0.0836 max mem: 9390 +Train: [80] [2400/6250] eta: 0:12:16 lr: 0.000013 grad: 0.1203 (0.1333) loss: 0.8087 (0.8107) time: 0.1164 data: 0.0002 max mem: 9390 +Train: [80] [2500/6250] eta: 0:11:54 lr: 0.000013 grad: 0.1355 (0.1334) loss: 0.8052 (0.8107) time: 0.0937 data: 0.0004 max mem: 9390 +Train: [80] [2600/6250] eta: 0:11:30 lr: 0.000013 grad: 0.1282 (0.1335) loss: 0.8097 (0.8106) time: 0.1739 data: 0.0928 max mem: 9390 +Train: [80] [2700/6250] eta: 0:11:07 lr: 0.000013 grad: 0.1320 (0.1335) loss: 0.8058 (0.8106) time: 0.1669 data: 0.0822 max mem: 9390 +Train: [80] [2800/6250] eta: 0:10:46 lr: 0.000013 grad: 0.1278 (0.1335) loss: 0.8055 (0.8106) time: 0.1684 data: 0.0722 max mem: 9390 +Train: [80] [2900/6250] eta: 0:10:29 lr: 0.000013 grad: 0.1285 (0.1334) loss: 0.8139 (0.8106) time: 0.1667 data: 0.0866 max mem: 9390 +Train: [80] [3000/6250] eta: 0:10:07 lr: 0.000013 grad: 0.1304 (0.1334) loss: 0.8047 (0.8106) time: 0.1138 data: 0.0178 max mem: 9390 +Train: [80] [3100/6250] eta: 0:09:45 lr: 0.000013 grad: 0.1305 (0.1334) loss: 0.8057 (0.8105) time: 0.0913 data: 0.0035 max mem: 9390 +Train: [80] [3200/6250] eta: 0:09:25 lr: 0.000013 grad: 0.1408 (0.1336) loss: 0.8093 (0.8104) time: 0.1172 data: 0.0287 max mem: 9390 +Train: [80] [3300/6250] eta: 0:09:10 lr: 0.000013 grad: 0.1346 (0.1337) loss: 0.8138 (0.8104) time: 0.0927 data: 0.0002 max mem: 9390 +Train: [80] [3400/6250] eta: 0:08:48 lr: 0.000012 grad: 0.1360 (0.1338) loss: 0.8158 (0.8103) time: 0.1273 data: 0.0445 max mem: 9390 +Train: [80] [3500/6250] eta: 0:08:31 lr: 0.000012 grad: 0.1303 (0.1338) loss: 0.8080 (0.8102) time: 0.1943 data: 0.1165 max mem: 9390 +Train: [80] [3600/6250] eta: 0:08:10 lr: 0.000012 grad: 0.1217 (0.1338) loss: 0.8027 (0.8101) time: 0.1191 data: 0.0365 max mem: 9390 +Train: [80] [3700/6250] eta: 0:07:50 lr: 0.000012 grad: 0.1295 (0.1338) loss: 0.8106 (0.8101) time: 0.1312 data: 0.0439 max mem: 9390 +Train: [80] [3800/6250] eta: 0:07:33 lr: 0.000012 grad: 0.1334 (0.1339) loss: 0.8095 (0.8100) time: 0.0934 data: 0.0002 max mem: 9390 +Train: [80] [3900/6250] eta: 0:07:15 lr: 0.000012 grad: 0.1220 (0.1339) loss: 0.8037 (0.8099) time: 0.1142 data: 0.0315 max mem: 9390 +Train: [80] [4000/6250] eta: 0:06:56 lr: 0.000012 grad: 0.1327 (0.1339) loss: 0.8085 (0.8099) time: 0.1725 data: 0.0781 max mem: 9390 +Train: [80] [4100/6250] eta: 0:06:38 lr: 0.000012 grad: 0.1352 (0.1339) loss: 0.8008 (0.8098) time: 0.2329 data: 0.1388 max mem: 9390 +Train: [80] [4200/6250] eta: 0:06:18 lr: 0.000012 grad: 0.1303 (0.1338) loss: 0.8083 (0.8098) time: 0.1445 data: 0.0581 max mem: 9390 +Train: [80] [4300/6250] eta: 0:06:03 lr: 0.000012 grad: 0.1360 (0.1338) loss: 0.8105 (0.8098) time: 0.2051 data: 0.1157 max mem: 9390 +Train: [80] [4400/6250] eta: 0:05:43 lr: 0.000012 grad: 0.1274 (0.1338) loss: 0.8061 (0.8098) time: 0.1323 data: 0.0311 max mem: 9390 +Train: [80] [4500/6250] eta: 0:05:24 lr: 0.000012 grad: 0.1264 (0.1337) loss: 0.8103 (0.8098) time: 0.1273 data: 0.0313 max mem: 9390 +Train: [80] [4600/6250] eta: 0:05:06 lr: 0.000012 grad: 0.1385 (0.1336) loss: 0.8066 (0.8099) time: 0.3704 data: 0.2538 max mem: 9390 +Train: [80] [4700/6250] eta: 0:04:46 lr: 0.000012 grad: 0.1271 (0.1336) loss: 0.8068 (0.8098) time: 0.1847 data: 0.1029 max mem: 9390 +Train: [80] [4800/6250] eta: 0:04:27 lr: 0.000012 grad: 0.1330 (0.1335) loss: 0.8021 (0.8097) time: 0.1869 data: 0.0902 max mem: 9390 +Train: [80] [4900/6250] eta: 0:04:08 lr: 0.000012 grad: 0.1243 (0.1334) loss: 0.8090 (0.8097) time: 0.1527 data: 0.0645 max mem: 9390 +Train: [80] [5000/6250] eta: 0:03:50 lr: 0.000012 grad: 0.1342 (0.1334) loss: 0.8076 (0.8097) time: 0.1989 data: 0.1097 max mem: 9390 +Train: [80] [5100/6250] eta: 0:03:31 lr: 0.000012 grad: 0.1242 (0.1334) loss: 0.8106 (0.8097) time: 0.2646 data: 0.1868 max mem: 9390 +Train: [80] [5200/6250] eta: 0:03:12 lr: 0.000012 grad: 0.1308 (0.1333) loss: 0.8025 (0.8096) time: 0.1444 data: 0.0466 max mem: 9390 +Train: [80] [5300/6250] eta: 0:02:53 lr: 0.000012 grad: 0.1252 (0.1333) loss: 0.8100 (0.8096) time: 0.1630 data: 0.0752 max mem: 9390 +Train: [80] [5400/6250] eta: 0:02:35 lr: 0.000012 grad: 0.1254 (0.1332) loss: 0.8103 (0.8096) time: 0.1094 data: 0.0257 max mem: 9390 +Train: [80] [5500/6250] eta: 0:02:16 lr: 0.000012 grad: 0.1228 (0.1332) loss: 0.8112 (0.8096) time: 0.2133 data: 0.1240 max mem: 9390 +Train: [80] [5600/6250] eta: 0:01:57 lr: 0.000012 grad: 0.1225 (0.1331) loss: 0.8065 (0.8096) time: 0.1560 data: 0.0667 max mem: 9390 +Train: [80] [5700/6250] eta: 0:01:39 lr: 0.000012 grad: 0.1282 (0.1330) loss: 0.8081 (0.8097) time: 0.2415 data: 0.1649 max mem: 9390 +Train: [80] [5800/6250] eta: 0:01:21 lr: 0.000012 grad: 0.1250 (0.1329) loss: 0.8121 (0.8097) time: 0.2165 data: 0.1387 max mem: 9390 +Train: [80] [5900/6250] eta: 0:01:03 lr: 0.000012 grad: 0.1214 (0.1328) loss: 0.8131 (0.8097) time: 0.1624 data: 0.0700 max mem: 9390 +Train: [80] [6000/6250] eta: 0:00:45 lr: 0.000012 grad: 0.1282 (0.1328) loss: 0.8076 (0.8097) time: 0.2752 data: 0.1999 max mem: 9390 +Train: [80] [6100/6250] eta: 0:00:26 lr: 0.000012 grad: 0.1272 (0.1326) loss: 0.8113 (0.8098) time: 0.1788 data: 0.1002 max mem: 9390 +Train: [80] [6200/6250] eta: 0:00:08 lr: 0.000012 grad: 0.1185 (0.1325) loss: 0.8140 (0.8099) time: 0.2575 data: 0.1776 max mem: 9390 +Train: [80] [6249/6250] eta: 0:00:00 lr: 0.000012 grad: 0.1177 (0.1324) loss: 0.8168 (0.8099) time: 0.1458 data: 0.0599 max mem: 9390 +Train: [80] Total time: 0:18:47 (0.1803 s / it) +Averaged stats: lr: 0.000012 grad: 0.1177 (0.1324) loss: 0.8168 (0.8099) +Eval (hcp-train-subset): [80] [ 0/62] eta: 0:04:21 loss: 0.8362 (0.8362) time: 4.2201 data: 4.1358 max mem: 9390 +Eval (hcp-train-subset): [80] [61/62] eta: 0:00:00 loss: 0.8222 (0.8249) time: 0.1317 data: 0.1053 max mem: 9390 +Eval (hcp-train-subset): [80] Total time: 0:00:13 (0.2156 s / it) +Averaged stats (hcp-train-subset): loss: 0.8222 (0.8249) +Eval (hcp-val): [80] [ 0/62] eta: 0:04:47 loss: 0.8266 (0.8266) time: 4.6379 data: 4.6048 max mem: 9390 +Eval (hcp-val): [80] [61/62] eta: 0:00:00 loss: 0.8286 (0.8303) time: 0.1750 data: 0.1472 max mem: 9390 +Eval (hcp-val): [80] Total time: 0:00:15 (0.2573 s / it) +Averaged stats (hcp-val): loss: 0.8286 (0.8303) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +Train: [81] [ 0/6250] eta: 11:36:42 lr: 0.000012 grad: 0.1831 (0.1831) loss: 0.8571 (0.8571) time: 6.6884 data: 6.3112 max mem: 9390 +Train: [81] [ 100/6250] eta: 0:49:14 lr: 0.000012 grad: 0.1347 (0.1539) loss: 0.8278 (0.8264) time: 0.2066 data: 0.0679 max mem: 9390 +Train: [81] [ 200/6250] eta: 0:38:55 lr: 0.000012 grad: 0.1425 (0.1510) loss: 0.8139 (0.8226) time: 0.1048 data: 0.0002 max mem: 9390 +Train: [81] [ 300/6250] eta: 0:31:30 lr: 0.000012 grad: 0.1297 (0.1470) loss: 0.8085 (0.8216) time: 0.1635 data: 0.0590 max mem: 9390 +Train: [81] [ 400/6250] eta: 0:28:15 lr: 0.000012 grad: 0.1281 (0.1422) loss: 0.8234 (0.8215) time: 0.2746 data: 0.1830 max mem: 9390 +Train: [81] [ 500/6250] eta: 0:25:43 lr: 0.000012 grad: 0.1334 (0.1404) loss: 0.8223 (0.8209) time: 0.1712 data: 0.0738 max mem: 9390 +Train: [81] [ 600/6250] eta: 0:23:56 lr: 0.000012 grad: 0.1286 (0.1390) loss: 0.8189 (0.8199) time: 0.1824 data: 0.1041 max mem: 9390 +Train: [81] [ 700/6250] eta: 0:22:28 lr: 0.000012 grad: 0.1331 (0.1382) loss: 0.8118 (0.8188) time: 0.1759 data: 0.0938 max mem: 9390 +Train: [81] [ 800/6250] eta: 0:21:21 lr: 0.000012 grad: 0.1306 (0.1374) loss: 0.8097 (0.8182) time: 0.1973 data: 0.1118 max mem: 9390 +Train: [81] [ 900/6250] eta: 0:20:13 lr: 0.000012 grad: 0.1252 (0.1365) loss: 0.8182 (0.8178) time: 0.1499 data: 0.0685 max mem: 9390 +Train: [81] [1000/6250] eta: 0:19:21 lr: 0.000012 grad: 0.1240 (0.1356) loss: 0.8161 (0.8176) time: 0.1577 data: 0.0722 max mem: 9390 +Train: [81] [1100/6250] eta: 0:18:28 lr: 0.000012 grad: 0.1342 (0.1350) loss: 0.8136 (0.8173) time: 0.1666 data: 0.0815 max mem: 9390 +Train: [81] [1200/6250] eta: 0:17:46 lr: 0.000012 grad: 0.1225 (0.1343) loss: 0.8138 (0.8172) time: 0.1934 data: 0.1095 max mem: 9390 +Train: [81] [1300/6250] eta: 0:16:59 lr: 0.000012 grad: 0.1246 (0.1339) loss: 0.8140 (0.8170) time: 0.1438 data: 0.0652 max mem: 9390 +Train: [81] [1400/6250] eta: 0:16:18 lr: 0.000012 grad: 0.1256 (0.1337) loss: 0.8149 (0.8168) time: 0.1274 data: 0.0414 max mem: 9390 +Train: [81] [1500/6250] eta: 0:15:42 lr: 0.000012 grad: 0.1295 (0.1335) loss: 0.8052 (0.8165) time: 0.1379 data: 0.0420 max mem: 9390 +Train: [81] [1600/6250] eta: 0:15:12 lr: 0.000012 grad: 0.1223 (0.1332) loss: 0.8110 (0.8162) time: 0.1557 data: 0.0752 max mem: 9390 +Train: [81] [1700/6250] eta: 0:14:43 lr: 0.000012 grad: 0.1352 (0.1333) loss: 0.8117 (0.8159) time: 0.1664 data: 0.0803 max mem: 9390 +Train: [81] [1800/6250] eta: 0:14:17 lr: 0.000012 grad: 0.1284 (0.1332) loss: 0.8104 (0.8156) time: 0.1865 data: 0.1039 max mem: 9390 +Train: [81] [1900/6250] eta: 0:14:00 lr: 0.000012 grad: 0.1274 (0.1331) loss: 0.8170 (0.8153) time: 0.3150 data: 0.2196 max mem: 9390 +Train: [81] [2000/6250] eta: 0:13:29 lr: 0.000012 grad: 0.1290 (0.1334) loss: 0.8124 (0.8150) time: 0.1351 data: 0.0477 max mem: 9390 +Train: [81] [2100/6250] eta: 0:13:18 lr: 0.000012 grad: 0.1258 (0.1334) loss: 0.8131 (0.8148) time: 0.4385 data: 0.3403 max mem: 9390 +Train: [81] [2200/6250] eta: 0:12:53 lr: 0.000012 grad: 0.1335 (0.1336) loss: 0.8110 (0.8146) time: 0.2349 data: 0.1530 max mem: 9390 +Train: [81] [2300/6250] eta: 0:12:37 lr: 0.000011 grad: 0.1318 (0.1338) loss: 0.8131 (0.8143) time: 0.1971 data: 0.1009 max mem: 9390 +Train: [81] [2400/6250] eta: 0:12:12 lr: 0.000011 grad: 0.1263 (0.1338) loss: 0.8127 (0.8142) time: 0.1854 data: 0.0890 max mem: 9390 +Train: [81] [2500/6250] eta: 0:11:55 lr: 0.000011 grad: 0.1237 (0.1337) loss: 0.8113 (0.8142) time: 0.2859 data: 0.1943 max mem: 9390 +Train: [81] [2600/6250] eta: 0:11:32 lr: 0.000011 grad: 0.1342 (0.1338) loss: 0.8126 (0.8141) time: 0.2682 data: 0.1775 max mem: 9390 +Train: [81] [2700/6250] eta: 0:11:17 lr: 0.000011 grad: 0.1273 (0.1337) loss: 0.8182 (0.8140) time: 0.2529 data: 0.1514 max mem: 9390 +Train: [81] [2800/6250] eta: 0:10:53 lr: 0.000011 grad: 0.1267 (0.1337) loss: 0.8110 (0.8140) time: 0.1320 data: 0.0576 max mem: 9390 +Train: [81] [2900/6250] eta: 0:10:33 lr: 0.000011 grad: 0.1291 (0.1337) loss: 0.8093 (0.8139) time: 0.1557 data: 0.0711 max mem: 9390 +Train: [81] [3000/6250] eta: 0:10:15 lr: 0.000011 grad: 0.1235 (0.1335) loss: 0.8121 (0.8139) time: 0.1891 data: 0.0850 max mem: 9390 +Train: [81] [3100/6250] eta: 0:09:59 lr: 0.000011 grad: 0.1313 (0.1335) loss: 0.8160 (0.8138) time: 0.1391 data: 0.0426 max mem: 9390 +Train: [81] [3200/6250] eta: 0:09:40 lr: 0.000011 grad: 0.1242 (0.1334) loss: 0.8091 (0.8138) time: 0.2894 data: 0.1986 max mem: 9390 +Train: [81] [3300/6250] eta: 0:09:19 lr: 0.000011 grad: 0.1243 (0.1333) loss: 0.8168 (0.8138) time: 0.1065 data: 0.0002 max mem: 9390 +Train: [81] [3400/6250] eta: 0:08:59 lr: 0.000011 grad: 0.1352 (0.1332) loss: 0.8125 (0.8138) time: 0.1249 data: 0.0329 max mem: 9390 +Train: [81] [3500/6250] eta: 0:08:44 lr: 0.000011 grad: 0.1244 (0.1331) loss: 0.8111 (0.8138) time: 0.1142 data: 0.0134 max mem: 9390 +Train: [81] [3600/6250] eta: 0:08:23 lr: 0.000011 grad: 0.1370 (0.1331) loss: 0.8122 (0.8138) time: 0.1603 data: 0.0623 max mem: 9390 +Train: [81] [3700/6250] eta: 0:08:03 lr: 0.000011 grad: 0.1313 (0.1331) loss: 0.8101 (0.8138) time: 0.1708 data: 0.0924 max mem: 9390 +Train: [81] [3800/6250] eta: 0:07:42 lr: 0.000011 grad: 0.1357 (0.1330) loss: 0.8112 (0.8138) time: 0.1042 data: 0.0124 max mem: 9390 +Train: [81] [3900/6250] eta: 0:07:22 lr: 0.000011 grad: 0.1320 (0.1329) loss: 0.8038 (0.8138) time: 0.1945 data: 0.1075 max mem: 9390 +Train: [81] [4000/6250] eta: 0:07:02 lr: 0.000011 grad: 0.1298 (0.1329) loss: 0.8096 (0.8137) time: 0.2020 data: 0.1237 max mem: 9390 +Train: [81] [4100/6250] eta: 0:06:42 lr: 0.000011 grad: 0.1264 (0.1328) loss: 0.8173 (0.8137) time: 0.1291 data: 0.0552 max mem: 9390 +Train: [81] [4200/6250] eta: 0:06:22 lr: 0.000011 grad: 0.1213 (0.1327) loss: 0.8140 (0.8137) time: 0.1715 data: 0.0902 max mem: 9390 +Train: [81] [4300/6250] eta: 0:06:03 lr: 0.000011 grad: 0.1199 (0.1325) loss: 0.8138 (0.8137) time: 0.1508 data: 0.0691 max mem: 9390 +Train: [81] [4400/6250] eta: 0:05:43 lr: 0.000011 grad: 0.1215 (0.1324) loss: 0.8147 (0.8137) time: 0.1420 data: 0.0637 max mem: 9390 +Train: [81] [4500/6250] eta: 0:05:24 lr: 0.000011 grad: 0.1289 (0.1324) loss: 0.8116 (0.8137) time: 0.1708 data: 0.0892 max mem: 9390 +Train: [81] [4600/6250] eta: 0:05:05 lr: 0.000011 grad: 0.1241 (0.1323) loss: 0.8133 (0.8137) time: 0.2148 data: 0.1367 max mem: 9390 +Train: [81] [4700/6250] eta: 0:04:47 lr: 0.000011 grad: 0.1270 (0.1322) loss: 0.8159 (0.8137) time: 0.1861 data: 0.0788 max mem: 9390 +Train: [81] [4800/6250] eta: 0:04:28 lr: 0.000011 grad: 0.1197 (0.1321) loss: 0.8162 (0.8137) time: 0.1875 data: 0.1069 max mem: 9390 +Train: [81] [4900/6250] eta: 0:04:10 lr: 0.000011 grad: 0.1219 (0.1320) loss: 0.8133 (0.8137) time: 0.2453 data: 0.1609 max mem: 9390 +Train: [81] [5000/6250] eta: 0:03:51 lr: 0.000011 grad: 0.1137 (0.1319) loss: 0.8161 (0.8138) time: 0.1318 data: 0.0437 max mem: 9390 +Train: [81] [5100/6250] eta: 0:03:32 lr: 0.000011 grad: 0.1259 (0.1317) loss: 0.8193 (0.8138) time: 0.1499 data: 0.0529 max mem: 9390 +Train: [81] [5200/6250] eta: 0:03:13 lr: 0.000011 grad: 0.1257 (0.1316) loss: 0.8100 (0.8138) time: 0.1637 data: 0.0450 max mem: 9390 +Train: [81] [5300/6250] eta: 0:02:54 lr: 0.000011 grad: 0.1169 (0.1315) loss: 0.8155 (0.8138) time: 0.1427 data: 0.0614 max mem: 9390 +Train: [81] [5400/6250] eta: 0:02:35 lr: 0.000011 grad: 0.1212 (0.1314) loss: 0.8142 (0.8138) time: 0.1655 data: 0.0826 max mem: 9390 +Train: [81] [5500/6250] eta: 0:02:16 lr: 0.000011 grad: 0.1253 (0.1312) loss: 0.8166 (0.8139) time: 0.2121 data: 0.1315 max mem: 9390 +Train: [81] [5600/6250] eta: 0:01:58 lr: 0.000011 grad: 0.1204 (0.1311) loss: 0.8182 (0.8140) time: 0.1604 data: 0.0805 max mem: 9390 +Train: [81] [5700/6250] eta: 0:01:40 lr: 0.000011 grad: 0.1175 (0.1310) loss: 0.8212 (0.8141) time: 0.2206 data: 0.1457 max mem: 9390 +Train: [81] [5800/6250] eta: 0:01:21 lr: 0.000011 grad: 0.1191 (0.1308) loss: 0.8166 (0.8142) time: 0.1827 data: 0.1047 max mem: 9390 +Train: [81] [5900/6250] eta: 0:01:03 lr: 0.000011 grad: 0.1210 (0.1307) loss: 0.8197 (0.8143) time: 0.1770 data: 0.0982 max mem: 9390 +Train: [81] [6000/6250] eta: 0:00:45 lr: 0.000011 grad: 0.1224 (0.1307) loss: 0.8177 (0.8144) time: 0.1872 data: 0.1120 max mem: 9390 +Train: [81] [6100/6250] eta: 0:00:27 lr: 0.000011 grad: 0.1176 (0.1305) loss: 0.8215 (0.8145) time: 0.2022 data: 0.1280 max mem: 9390 +Train: [81] [6200/6250] eta: 0:00:09 lr: 0.000011 grad: 0.1177 (0.1304) loss: 0.8180 (0.8146) time: 0.1553 data: 0.0732 max mem: 9390 +Train: [81] [6249/6250] eta: 0:00:00 lr: 0.000011 grad: 0.1247 (0.1304) loss: 0.8175 (0.8146) time: 0.1569 data: 0.0773 max mem: 9390 +Train: [81] Total time: 0:19:01 (0.1827 s / it) +Averaged stats: lr: 0.000011 grad: 0.1247 (0.1304) loss: 0.8175 (0.8146) +Eval (hcp-train-subset): [81] [ 0/62] eta: 0:05:41 loss: 0.8299 (0.8299) time: 5.5014 data: 5.4691 max mem: 9390 +Eval (hcp-train-subset): [81] [61/62] eta: 0:00:00 loss: 0.8218 (0.8241) time: 0.1176 data: 0.0912 max mem: 9390 +Eval (hcp-train-subset): [81] Total time: 0:00:13 (0.2137 s / it) +Averaged stats (hcp-train-subset): loss: 0.8218 (0.8241) +Eval (hcp-val): [81] [ 0/62] eta: 0:05:51 loss: 0.8295 (0.8295) time: 5.6657 data: 5.6352 max mem: 9390 +Eval (hcp-val): [81] [61/62] eta: 0:00:00 loss: 0.8270 (0.8296) time: 0.1169 data: 0.0917 max mem: 9390 +Eval (hcp-val): [81] Total time: 0:00:13 (0.2199 s / it) +Averaged stats (hcp-val): loss: 0.8270 (0.8296) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +Train: [82] [ 0/6250] eta: 9:22:35 lr: 0.000011 grad: 0.1645 (0.1645) loss: 0.8396 (0.8396) time: 5.4009 data: 5.2453 max mem: 9390 +Train: [82] [ 100/6250] eta: 0:22:23 lr: 0.000011 grad: 0.1425 (0.1441) loss: 0.8205 (0.8270) time: 0.2027 data: 0.1070 max mem: 9390 +Train: [82] [ 200/6250] eta: 0:20:16 lr: 0.000011 grad: 0.1345 (0.1478) loss: 0.8118 (0.8220) time: 0.1453 data: 0.0561 max mem: 9390 +Train: [82] [ 300/6250] eta: 0:19:01 lr: 0.000011 grad: 0.1342 (0.1459) loss: 0.8090 (0.8180) time: 0.1094 data: 0.0003 max mem: 9390 +Train: [82] [ 400/6250] eta: 0:18:22 lr: 0.000011 grad: 0.1330 (0.1425) loss: 0.8126 (0.8167) time: 0.1396 data: 0.0333 max mem: 9390 +Train: [82] [ 500/6250] eta: 0:17:58 lr: 0.000011 grad: 0.1240 (0.1405) loss: 0.8158 (0.8164) time: 0.1472 data: 0.0653 max mem: 9390 +Train: [82] [ 600/6250] eta: 0:18:11 lr: 0.000011 grad: 0.1244 (0.1390) loss: 0.8173 (0.8160) time: 0.1973 data: 0.0983 max mem: 9390 +Train: [82] [ 700/6250] eta: 0:18:46 lr: 0.000011 grad: 0.1336 (0.1380) loss: 0.8081 (0.8156) time: 0.4594 data: 0.3462 max mem: 9390 +Train: [82] [ 800/6250] eta: 0:18:00 lr: 0.000011 grad: 0.1297 (0.1375) loss: 0.8153 (0.8152) time: 0.1962 data: 0.1070 max mem: 9390 +Train: [82] [ 900/6250] eta: 0:17:23 lr: 0.000011 grad: 0.1274 (0.1369) loss: 0.8103 (0.8151) time: 0.1580 data: 0.0536 max mem: 9390 +Train: [82] [1000/6250] eta: 0:16:58 lr: 0.000011 grad: 0.1285 (0.1365) loss: 0.8108 (0.8150) time: 0.1040 data: 0.0192 max mem: 9390 +Train: [82] [1100/6250] eta: 0:16:24 lr: 0.000011 grad: 0.1267 (0.1355) loss: 0.8116 (0.8149) time: 0.1302 data: 0.0391 max mem: 9390 +Train: [82] [1200/6250] eta: 0:15:58 lr: 0.000011 grad: 0.1264 (0.1349) loss: 0.8146 (0.8149) time: 0.1073 data: 0.0054 max mem: 9390 +Train: [82] [1300/6250] eta: 0:15:32 lr: 0.000011 grad: 0.1286 (0.1343) loss: 0.8137 (0.8149) time: 0.1720 data: 0.0898 max mem: 9390 +Train: [82] [1400/6250] eta: 0:15:05 lr: 0.000010 grad: 0.1252 (0.1337) loss: 0.8143 (0.8150) time: 0.0937 data: 0.0002 max mem: 9390 +Train: [82] [1500/6250] eta: 0:14:33 lr: 0.000010 grad: 0.1203 (0.1331) loss: 0.8178 (0.8151) time: 0.1472 data: 0.0596 max mem: 9390 +Train: [82] [1600/6250] eta: 0:14:12 lr: 0.000010 grad: 0.1147 (0.1326) loss: 0.8239 (0.8151) time: 0.1012 data: 0.0002 max mem: 9390 +Train: [82] [1700/6250] eta: 0:13:47 lr: 0.000010 grad: 0.1180 (0.1321) loss: 0.8152 (0.8152) time: 0.1530 data: 0.0663 max mem: 9390 +Train: [82] [1800/6250] eta: 0:13:28 lr: 0.000010 grad: 0.1150 (0.1315) loss: 0.8122 (0.8154) time: 0.2328 data: 0.1365 max mem: 9390 +Train: [82] [1900/6250] eta: 0:13:13 lr: 0.000010 grad: 0.1266 (0.1310) loss: 0.8201 (0.8155) time: 0.2195 data: 0.1339 max mem: 9390 +Train: [82] [2000/6250] eta: 0:12:47 lr: 0.000010 grad: 0.1172 (0.1307) loss: 0.8185 (0.8156) time: 0.1629 data: 0.0800 max mem: 9390 +Train: [82] [2100/6250] eta: 0:12:28 lr: 0.000010 grad: 0.1163 (0.1303) loss: 0.8136 (0.8157) time: 0.1883 data: 0.1024 max mem: 9390 +Train: [82] [2200/6250] eta: 0:12:09 lr: 0.000010 grad: 0.1248 (0.1300) loss: 0.8119 (0.8156) time: 0.1301 data: 0.0407 max mem: 9390 +Train: [82] [2300/6250] eta: 0:11:51 lr: 0.000010 grad: 0.1325 (0.1300) loss: 0.8095 (0.8155) time: 0.2164 data: 0.1347 max mem: 9390 +Train: [82] [2400/6250] eta: 0:11:27 lr: 0.000010 grad: 0.1188 (0.1300) loss: 0.8127 (0.8154) time: 0.1672 data: 0.0855 max mem: 9390 +Train: [82] [2500/6250] eta: 0:11:18 lr: 0.000010 grad: 0.1201 (0.1300) loss: 0.8174 (0.8154) time: 0.2450 data: 0.1602 max mem: 9390 +Train: [82] [2600/6250] eta: 0:10:54 lr: 0.000010 grad: 0.1268 (0.1299) loss: 0.8126 (0.8154) time: 0.1133 data: 0.0197 max mem: 9390 +Train: [82] [2700/6250] eta: 0:10:40 lr: 0.000010 grad: 0.1188 (0.1299) loss: 0.8185 (0.8154) time: 0.3574 data: 0.2652 max mem: 9390 +Train: [82] [2800/6250] eta: 0:10:20 lr: 0.000010 grad: 0.1196 (0.1297) loss: 0.8133 (0.8155) time: 0.0948 data: 0.0004 max mem: 9390 +Train: [82] [2900/6250] eta: 0:10:00 lr: 0.000010 grad: 0.1274 (0.1295) loss: 0.8175 (0.8155) time: 0.1558 data: 0.0758 max mem: 9390 +Train: [82] [3000/6250] eta: 0:09:43 lr: 0.000010 grad: 0.1271 (0.1296) loss: 0.8173 (0.8156) time: 0.1013 data: 0.0003 max mem: 9390 +Train: [82] [3100/6250] eta: 0:09:23 lr: 0.000010 grad: 0.1227 (0.1295) loss: 0.8163 (0.8156) time: 0.1449 data: 0.0646 max mem: 9390 +Train: [82] [3200/6250] eta: 0:09:08 lr: 0.000010 grad: 0.1333 (0.1295) loss: 0.8151 (0.8156) time: 0.2593 data: 0.1605 max mem: 9390 +Train: [82] [3300/6250] eta: 0:08:48 lr: 0.000010 grad: 0.1246 (0.1294) loss: 0.8201 (0.8156) time: 0.0928 data: 0.0002 max mem: 9390 +Train: [82] [3400/6250] eta: 0:08:27 lr: 0.000010 grad: 0.1338 (0.1295) loss: 0.8113 (0.8156) time: 0.1254 data: 0.0491 max mem: 9390 +Train: [82] [3500/6250] eta: 0:08:11 lr: 0.000010 grad: 0.1213 (0.1294) loss: 0.8174 (0.8157) time: 0.2042 data: 0.0898 max mem: 9390 +Train: [82] [3600/6250] eta: 0:07:51 lr: 0.000010 grad: 0.1247 (0.1294) loss: 0.8176 (0.8156) time: 0.1749 data: 0.0968 max mem: 9390 +Train: [82] [3700/6250] eta: 0:07:31 lr: 0.000010 grad: 0.1215 (0.1294) loss: 0.8191 (0.8156) time: 0.1431 data: 0.0521 max mem: 9390 +Train: [82] [3800/6250] eta: 0:07:14 lr: 0.000010 grad: 0.1293 (0.1294) loss: 0.8121 (0.8156) time: 0.1711 data: 0.0193 max mem: 9390 +Train: [82] [3900/6250] eta: 0:06:55 lr: 0.000010 grad: 0.1296 (0.1293) loss: 0.8110 (0.8156) time: 0.1864 data: 0.0987 max mem: 9390 +Train: [82] [4000/6250] eta: 0:06:38 lr: 0.000010 grad: 0.1207 (0.1292) loss: 0.8122 (0.8156) time: 0.2502 data: 0.1483 max mem: 9390 +Train: [82] [4100/6250] eta: 0:06:21 lr: 0.000010 grad: 0.1236 (0.1291) loss: 0.8147 (0.8156) time: 0.4602 data: 0.3589 max mem: 9390 +Train: [82] [4200/6250] eta: 0:06:01 lr: 0.000010 grad: 0.1322 (0.1291) loss: 0.8184 (0.8156) time: 0.1707 data: 0.0856 max mem: 9390 +Train: [82] [4300/6250] eta: 0:05:45 lr: 0.000010 grad: 0.1259 (0.1292) loss: 0.8204 (0.8156) time: 0.0998 data: 0.0002 max mem: 9390 +Train: [82] [4400/6250] eta: 0:05:26 lr: 0.000010 grad: 0.1266 (0.1292) loss: 0.8122 (0.8155) time: 0.1466 data: 0.0621 max mem: 9390 +Train: [82] [4500/6250] eta: 0:05:09 lr: 0.000010 grad: 0.1269 (0.1293) loss: 0.8094 (0.8155) time: 0.1288 data: 0.0418 max mem: 9390 +Train: [82] [4600/6250] eta: 0:04:52 lr: 0.000010 grad: 0.1270 (0.1293) loss: 0.8060 (0.8154) time: 0.1215 data: 0.0228 max mem: 9390 +Train: [82] [4700/6250] eta: 0:04:35 lr: 0.000010 grad: 0.1243 (0.1294) loss: 0.8157 (0.8153) time: 0.1482 data: 0.0593 max mem: 9390 +Train: [82] [4800/6250] eta: 0:04:17 lr: 0.000010 grad: 0.1318 (0.1295) loss: 0.8075 (0.8152) time: 0.1937 data: 0.0931 max mem: 9390 +Train: [82] [4900/6250] eta: 0:03:58 lr: 0.000010 grad: 0.1308 (0.1296) loss: 0.8094 (0.8151) time: 0.1429 data: 0.0550 max mem: 9390 +Train: [82] [5000/6250] eta: 0:03:41 lr: 0.000010 grad: 0.1264 (0.1296) loss: 0.8166 (0.8151) time: 0.0962 data: 0.0002 max mem: 9390 +Train: [82] [5100/6250] eta: 0:03:23 lr: 0.000010 grad: 0.1254 (0.1297) loss: 0.8132 (0.8150) time: 0.1543 data: 0.0654 max mem: 9390 +Train: [82] [5200/6250] eta: 0:03:05 lr: 0.000010 grad: 0.1206 (0.1296) loss: 0.8056 (0.8149) time: 0.0924 data: 0.0002 max mem: 9390 +Train: [82] [5300/6250] eta: 0:02:48 lr: 0.000010 grad: 0.1304 (0.1297) loss: 0.8163 (0.8149) time: 0.3649 data: 0.2737 max mem: 9390 +Train: [82] [5400/6250] eta: 0:02:30 lr: 0.000010 grad: 0.1209 (0.1297) loss: 0.8208 (0.8149) time: 0.1078 data: 0.0002 max mem: 9390 +Train: [82] [5500/6250] eta: 0:02:13 lr: 0.000010 grad: 0.1277 (0.1298) loss: 0.8138 (0.8149) time: 0.0986 data: 0.0002 max mem: 9390 +Train: [82] [5600/6250] eta: 0:01:55 lr: 0.000010 grad: 0.1209 (0.1298) loss: 0.8182 (0.8148) time: 0.1873 data: 0.0943 max mem: 9390 +Train: [82] [5700/6250] eta: 0:01:37 lr: 0.000010 grad: 0.1309 (0.1298) loss: 0.8114 (0.8148) time: 0.1739 data: 0.0901 max mem: 9390 +Train: [82] [5800/6250] eta: 0:01:19 lr: 0.000010 grad: 0.1289 (0.1298) loss: 0.8181 (0.8148) time: 0.1457 data: 0.0604 max mem: 9390 +Train: [82] [5900/6250] eta: 0:01:01 lr: 0.000010 grad: 0.1223 (0.1298) loss: 0.8179 (0.8148) time: 0.1709 data: 0.0906 max mem: 9390 +Train: [82] [6000/6250] eta: 0:00:44 lr: 0.000010 grad: 0.1240 (0.1298) loss: 0.8133 (0.8148) time: 0.1596 data: 0.0725 max mem: 9390 +Train: [82] [6100/6250] eta: 0:00:26 lr: 0.000010 grad: 0.1265 (0.1298) loss: 0.8086 (0.8148) time: 0.2147 data: 0.1230 max mem: 9390 +Train: [82] [6200/6250] eta: 0:00:08 lr: 0.000010 grad: 0.1252 (0.1298) loss: 0.8153 (0.8149) time: 0.1913 data: 0.1138 max mem: 9390 +Train: [82] [6249/6250] eta: 0:00:00 lr: 0.000010 grad: 0.1272 (0.1298) loss: 0.8162 (0.8149) time: 0.1743 data: 0.0920 max mem: 9390 +Train: [82] Total time: 0:18:26 (0.1770 s / it) +Averaged stats: lr: 0.000010 grad: 0.1272 (0.1298) loss: 0.8162 (0.8149) +Eval (hcp-train-subset): [82] [ 0/62] eta: 0:05:17 loss: 0.8280 (0.8280) time: 5.1218 data: 5.0887 max mem: 9390 +Eval (hcp-train-subset): [82] [61/62] eta: 0:00:00 loss: 0.8203 (0.8226) time: 0.1380 data: 0.1128 max mem: 9390 +Eval (hcp-train-subset): [82] Total time: 0:00:13 (0.2136 s / it) +Averaged stats (hcp-train-subset): loss: 0.8203 (0.8226) +Eval (hcp-val): [82] [ 0/62] eta: 0:04:53 loss: 0.8232 (0.8232) time: 4.7359 data: 4.7057 max mem: 9390 +Eval (hcp-val): [82] [61/62] eta: 0:00:00 loss: 0.8290 (0.8300) time: 0.1227 data: 0.0977 max mem: 9390 +Eval (hcp-val): [82] Total time: 0:00:12 (0.2096 s / it) +Averaged stats (hcp-val): loss: 0.8290 (0.8300) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +Train: [83] [ 0/6250] eta: 8:56:27 lr: 0.000010 grad: 0.2482 (0.2482) loss: 0.8526 (0.8526) time: 5.1500 data: 4.9213 max mem: 9390 +Train: [83] [ 100/6250] eta: 0:22:10 lr: 0.000010 grad: 0.1288 (0.1631) loss: 0.8220 (0.8125) time: 0.1656 data: 0.0701 max mem: 9390 +Train: [83] [ 200/6250] eta: 0:19:23 lr: 0.000010 grad: 0.1340 (0.1515) loss: 0.8206 (0.8151) time: 0.1382 data: 0.0457 max mem: 9390 +Train: [83] [ 300/6250] eta: 0:18:47 lr: 0.000010 grad: 0.1213 (0.1439) loss: 0.8218 (0.8179) time: 0.1514 data: 0.0689 max mem: 9390 +Train: [83] [ 400/6250] eta: 0:17:47 lr: 0.000010 grad: 0.1316 (0.1416) loss: 0.8082 (0.8178) time: 0.1709 data: 0.0844 max mem: 9390 +Train: [83] [ 500/6250] eta: 0:16:58 lr: 0.000010 grad: 0.1265 (0.1403) loss: 0.8128 (0.8175) time: 0.1493 data: 0.0628 max mem: 9390 +Train: [83] [ 600/6250] eta: 0:16:27 lr: 0.000010 grad: 0.1433 (0.1397) loss: 0.8158 (0.8171) time: 0.1665 data: 0.0796 max mem: 9390 +Train: [83] [ 700/6250] eta: 0:16:15 lr: 0.000009 grad: 0.1282 (0.1391) loss: 0.8133 (0.8165) time: 0.2338 data: 0.1364 max mem: 9390 +Train: [83] [ 800/6250] eta: 0:16:14 lr: 0.000009 grad: 0.1308 (0.1386) loss: 0.8090 (0.8159) time: 0.1697 data: 0.0529 max mem: 9390 +Train: [83] [ 900/6250] eta: 0:16:46 lr: 0.000009 grad: 0.1293 (0.1382) loss: 0.8134 (0.8154) time: 0.2637 data: 0.1453 max mem: 9390 +Train: [83] [1000/6250] eta: 0:16:16 lr: 0.000009 grad: 0.1289 (0.1373) loss: 0.8183 (0.8154) time: 0.1598 data: 0.0779 max mem: 9390 +Train: [83] [1100/6250] eta: 0:15:54 lr: 0.000009 grad: 0.1367 (0.1369) loss: 0.8148 (0.8155) time: 0.1219 data: 0.0202 max mem: 9390 +Train: [83] [1200/6250] eta: 0:15:23 lr: 0.000009 grad: 0.1369 (0.1368) loss: 0.8101 (0.8152) time: 0.1773 data: 0.0850 max mem: 9390 +Train: [83] [1300/6250] eta: 0:15:08 lr: 0.000009 grad: 0.1338 (0.1364) loss: 0.8119 (0.8152) time: 0.2416 data: 0.1579 max mem: 9390 +Train: [83] [1400/6250] eta: 0:15:00 lr: 0.000009 grad: 0.1299 (0.1363) loss: 0.8143 (0.8152) time: 0.1600 data: 0.0681 max mem: 9390 +Train: [83] [1500/6250] eta: 0:14:42 lr: 0.000009 grad: 0.1349 (0.1362) loss: 0.8093 (0.8149) time: 0.1175 data: 0.0207 max mem: 9390 +Train: [83] [1600/6250] eta: 0:14:27 lr: 0.000009 grad: 0.1360 (0.1363) loss: 0.8059 (0.8147) time: 0.2104 data: 0.1273 max mem: 9390 +Train: [83] [1700/6250] eta: 0:14:07 lr: 0.000009 grad: 0.1374 (0.1363) loss: 0.8100 (0.8144) time: 0.1607 data: 0.0846 max mem: 9390 +Train: [83] [1800/6250] eta: 0:13:49 lr: 0.000009 grad: 0.1382 (0.1363) loss: 0.8051 (0.8142) time: 0.1333 data: 0.0523 max mem: 9390 +Train: [83] [1900/6250] eta: 0:13:32 lr: 0.000009 grad: 0.1279 (0.1362) loss: 0.8105 (0.8141) time: 0.2128 data: 0.1327 max mem: 9390 +Train: [83] [2000/6250] eta: 0:13:12 lr: 0.000009 grad: 0.1308 (0.1360) loss: 0.8128 (0.8140) time: 0.1729 data: 0.0929 max mem: 9390 +Train: [83] [2100/6250] eta: 0:12:50 lr: 0.000009 grad: 0.1354 (0.1359) loss: 0.8088 (0.8139) time: 0.1952 data: 0.1146 max mem: 9390 +Train: [83] [2200/6250] eta: 0:12:35 lr: 0.000009 grad: 0.1312 (0.1357) loss: 0.8097 (0.8138) time: 0.4232 data: 0.3317 max mem: 9390 +Train: [83] [2300/6250] eta: 0:12:08 lr: 0.000009 grad: 0.1254 (0.1356) loss: 0.8148 (0.8137) time: 0.1388 data: 0.0560 max mem: 9390 +Train: [83] [2400/6250] eta: 0:11:48 lr: 0.000009 grad: 0.1319 (0.1356) loss: 0.8093 (0.8137) time: 0.1189 data: 0.0368 max mem: 9390 +Train: [83] [2500/6250] eta: 0:11:25 lr: 0.000009 grad: 0.1321 (0.1355) loss: 0.8102 (0.8136) time: 0.1654 data: 0.0633 max mem: 9390 +Train: [83] [2600/6250] eta: 0:11:06 lr: 0.000009 grad: 0.1349 (0.1355) loss: 0.8166 (0.8135) time: 0.1284 data: 0.0368 max mem: 9390 +Train: [83] [2700/6250] eta: 0:10:46 lr: 0.000009 grad: 0.1322 (0.1356) loss: 0.8121 (0.8134) time: 0.1759 data: 0.0913 max mem: 9390 +Train: [83] [2800/6250] eta: 0:10:30 lr: 0.000009 grad: 0.1325 (0.1355) loss: 0.8135 (0.8132) time: 0.3473 data: 0.2593 max mem: 9390 +Train: [83] [2900/6250] eta: 0:10:08 lr: 0.000009 grad: 0.1215 (0.1354) loss: 0.8176 (0.8131) time: 0.2169 data: 0.1382 max mem: 9390 +Train: [83] [3000/6250] eta: 0:09:48 lr: 0.000009 grad: 0.1249 (0.1354) loss: 0.8114 (0.8130) time: 0.1237 data: 0.0337 max mem: 9390 +Train: [83] [3100/6250] eta: 0:09:28 lr: 0.000009 grad: 0.1300 (0.1353) loss: 0.8128 (0.8129) time: 0.1588 data: 0.0799 max mem: 9390 +Train: [83] [3200/6250] eta: 0:09:11 lr: 0.000009 grad: 0.1271 (0.1353) loss: 0.8120 (0.8128) time: 0.0995 data: 0.0002 max mem: 9390 +Train: [83] [3300/6250] eta: 0:08:50 lr: 0.000009 grad: 0.1364 (0.1352) loss: 0.8088 (0.8127) time: 0.1184 data: 0.0307 max mem: 9390 +Train: [83] [3400/6250] eta: 0:08:32 lr: 0.000009 grad: 0.1313 (0.1352) loss: 0.8117 (0.8126) time: 0.0923 data: 0.0002 max mem: 9390 +Train: [83] [3500/6250] eta: 0:08:14 lr: 0.000009 grad: 0.1358 (0.1352) loss: 0.8114 (0.8125) time: 0.1436 data: 0.0545 max mem: 9390 +Train: [83] [3600/6250] eta: 0:07:59 lr: 0.000009 grad: 0.1331 (0.1351) loss: 0.8057 (0.8125) time: 0.3283 data: 0.2370 max mem: 9390 +Train: [83] [3700/6250] eta: 0:07:39 lr: 0.000009 grad: 0.1329 (0.1351) loss: 0.8053 (0.8125) time: 0.0894 data: 0.0002 max mem: 9390 +Train: [83] [3800/6250] eta: 0:07:19 lr: 0.000009 grad: 0.1330 (0.1351) loss: 0.8113 (0.8125) time: 0.1427 data: 0.0615 max mem: 9390 +Train: [83] [3900/6250] eta: 0:07:01 lr: 0.000009 grad: 0.1271 (0.1351) loss: 0.8126 (0.8124) time: 0.1695 data: 0.0820 max mem: 9390 +Train: [83] [4000/6250] eta: 0:06:45 lr: 0.000009 grad: 0.1226 (0.1351) loss: 0.8148 (0.8125) time: 0.4391 data: 0.3474 max mem: 9390 +Train: [83] [4100/6250] eta: 0:06:27 lr: 0.000009 grad: 0.1324 (0.1352) loss: 0.8161 (0.8125) time: 0.1074 data: 0.0002 max mem: 9390 +Train: [83] [4200/6250] eta: 0:06:09 lr: 0.000009 grad: 0.1246 (0.1352) loss: 0.8168 (0.8125) time: 0.1237 data: 0.0305 max mem: 9390 +Train: [83] [4300/6250] eta: 0:05:53 lr: 0.000009 grad: 0.1290 (0.1350) loss: 0.8166 (0.8126) time: 0.1495 data: 0.0622 max mem: 9390 +Train: [83] [4400/6250] eta: 0:05:34 lr: 0.000009 grad: 0.1233 (0.1350) loss: 0.8171 (0.8126) time: 0.1817 data: 0.0947 max mem: 9390 +Train: [83] [4500/6250] eta: 0:05:16 lr: 0.000009 grad: 0.1277 (0.1349) loss: 0.8187 (0.8126) time: 0.1782 data: 0.1020 max mem: 9390 +Train: [83] [4600/6250] eta: 0:05:02 lr: 0.000009 grad: 0.1288 (0.1348) loss: 0.8126 (0.8127) time: 0.7238 data: 0.6463 max mem: 9390 +Train: [83] [4700/6250] eta: 0:04:44 lr: 0.000009 grad: 0.1281 (0.1348) loss: 0.8163 (0.8128) time: 0.0966 data: 0.0002 max mem: 9390 +Train: [83] [4800/6250] eta: 0:04:26 lr: 0.000009 grad: 0.1221 (0.1347) loss: 0.8178 (0.8128) time: 0.1795 data: 0.0815 max mem: 9390 +Train: [83] [4900/6250] eta: 0:04:09 lr: 0.000009 grad: 0.1335 (0.1347) loss: 0.8155 (0.8129) time: 0.1313 data: 0.0448 max mem: 9390 +Train: [83] [5000/6250] eta: 0:03:51 lr: 0.000009 grad: 0.1351 (0.1347) loss: 0.8098 (0.8129) time: 0.2391 data: 0.1533 max mem: 9390 +Train: [83] [5100/6250] eta: 0:03:33 lr: 0.000009 grad: 0.1233 (0.1346) loss: 0.8191 (0.8129) time: 0.1740 data: 0.0778 max mem: 9390 +Train: [83] [5200/6250] eta: 0:03:14 lr: 0.000009 grad: 0.1377 (0.1347) loss: 0.8087 (0.8129) time: 0.1470 data: 0.0565 max mem: 9390 +Train: [83] [5300/6250] eta: 0:02:55 lr: 0.000009 grad: 0.1340 (0.1347) loss: 0.8066 (0.8129) time: 0.1488 data: 0.0465 max mem: 9390 +Train: [83] [5400/6250] eta: 0:02:36 lr: 0.000009 grad: 0.1375 (0.1347) loss: 0.8161 (0.8128) time: 0.1055 data: 0.0150 max mem: 9390 +Train: [83] [5500/6250] eta: 0:02:18 lr: 0.000009 grad: 0.1302 (0.1347) loss: 0.8136 (0.8129) time: 0.2184 data: 0.1361 max mem: 9390 +Train: [83] [5600/6250] eta: 0:01:59 lr: 0.000009 grad: 0.1292 (0.1347) loss: 0.8118 (0.8128) time: 0.1601 data: 0.0564 max mem: 9390 +Train: [83] [5700/6250] eta: 0:01:41 lr: 0.000009 grad: 0.1370 (0.1347) loss: 0.8083 (0.8128) time: 0.1146 data: 0.0143 max mem: 9390 +Train: [83] [5800/6250] eta: 0:01:22 lr: 0.000009 grad: 0.1282 (0.1347) loss: 0.8167 (0.8128) time: 0.1326 data: 0.0460 max mem: 9390 +Train: [83] [5900/6250] eta: 0:01:04 lr: 0.000009 grad: 0.1344 (0.1346) loss: 0.8077 (0.8128) time: 0.1066 data: 0.0131 max mem: 9390 +Train: [83] [6000/6250] eta: 0:00:45 lr: 0.000009 grad: 0.1201 (0.1346) loss: 0.8198 (0.8128) time: 0.1589 data: 0.0754 max mem: 9390 +Train: [83] [6100/6250] eta: 0:00:27 lr: 0.000009 grad: 0.1323 (0.1346) loss: 0.8057 (0.8128) time: 0.1928 data: 0.1110 max mem: 9390 +Train: [83] [6200/6250] eta: 0:00:09 lr: 0.000009 grad: 0.1319 (0.1345) loss: 0.8105 (0.8128) time: 0.2213 data: 0.1407 max mem: 9390 +Train: [83] [6249/6250] eta: 0:00:00 lr: 0.000009 grad: 0.1302 (0.1345) loss: 0.8164 (0.8128) time: 0.1970 data: 0.1202 max mem: 9390 +Train: [83] Total time: 0:19:10 (0.1841 s / it) +Averaged stats: lr: 0.000009 grad: 0.1302 (0.1345) loss: 0.8164 (0.8128) +Eval (hcp-train-subset): [83] [ 0/62] eta: 0:05:38 loss: 0.8318 (0.8318) time: 5.4517 data: 5.4153 max mem: 9390 +Eval (hcp-train-subset): [83] [61/62] eta: 0:00:00 loss: 0.8202 (0.8231) time: 0.1212 data: 0.0946 max mem: 9390 +Eval (hcp-train-subset): [83] Total time: 0:00:13 (0.2134 s / it) +Averaged stats (hcp-train-subset): loss: 0.8202 (0.8231) +Eval (hcp-val): [83] [ 0/62] eta: 0:05:10 loss: 0.8264 (0.8264) time: 5.0074 data: 4.9772 max mem: 9390 +Eval (hcp-val): [83] [61/62] eta: 0:00:00 loss: 0.8287 (0.8300) time: 0.1167 data: 0.0903 max mem: 9390 +Eval (hcp-val): [83] Total time: 0:00:13 (0.2172 s / it) +Averaged stats (hcp-val): loss: 0.8287 (0.8300) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +Train: [84] [ 0/6250] eta: 11:54:08 lr: 0.000009 grad: 0.4021 (0.4021) loss: 0.8156 (0.8156) time: 6.8558 data: 6.7536 max mem: 9390 +Train: [84] [ 100/6250] eta: 0:21:58 lr: 0.000009 grad: 0.1526 (0.1797) loss: 0.8221 (0.8232) time: 0.1870 data: 0.0890 max mem: 9390 +Train: [84] [ 200/6250] eta: 0:18:32 lr: 0.000009 grad: 0.1321 (0.1633) loss: 0.8259 (0.8226) time: 0.1406 data: 0.0490 max mem: 9390 +Train: [84] [ 300/6250] eta: 0:17:23 lr: 0.000008 grad: 0.1166 (0.1524) loss: 0.8194 (0.8231) time: 0.1590 data: 0.0652 max mem: 9390 +Train: [84] [ 400/6250] eta: 0:16:43 lr: 0.000008 grad: 0.1198 (0.1476) loss: 0.8320 (0.8227) time: 0.1952 data: 0.1063 max mem: 9390 +Train: [84] [ 500/6250] eta: 0:15:59 lr: 0.000008 grad: 0.1372 (0.1449) loss: 0.8169 (0.8220) time: 0.1650 data: 0.0639 max mem: 9390 +Train: [84] [ 600/6250] eta: 0:15:42 lr: 0.000008 grad: 0.1286 (0.1438) loss: 0.8202 (0.8208) time: 0.1694 data: 0.0879 max mem: 9390 +Train: [84] [ 700/6250] eta: 0:15:24 lr: 0.000008 grad: 0.1318 (0.1421) loss: 0.8160 (0.8202) time: 0.1655 data: 0.0730 max mem: 9390 +Train: [84] [ 800/6250] eta: 0:15:15 lr: 0.000008 grad: 0.1287 (0.1410) loss: 0.8133 (0.8195) time: 0.2207 data: 0.1332 max mem: 9390 +Train: [84] [ 900/6250] eta: 0:15:00 lr: 0.000008 grad: 0.1284 (0.1402) loss: 0.8100 (0.8188) time: 0.2290 data: 0.1458 max mem: 9390 +Train: [84] [1000/6250] eta: 0:14:53 lr: 0.000008 grad: 0.1293 (0.1395) loss: 0.8133 (0.8184) time: 0.2263 data: 0.1335 max mem: 9390 +Train: [84] [1100/6250] eta: 0:14:39 lr: 0.000008 grad: 0.1383 (0.1391) loss: 0.8100 (0.8178) time: 0.1914 data: 0.1048 max mem: 9390 +Train: [84] [1200/6250] eta: 0:14:19 lr: 0.000008 grad: 0.1313 (0.1388) loss: 0.8103 (0.8172) time: 0.1154 data: 0.0146 max mem: 9390 +Train: [84] [1300/6250] eta: 0:14:16 lr: 0.000008 grad: 0.1350 (0.1384) loss: 0.8059 (0.8167) time: 0.2720 data: 0.1728 max mem: 9390 +Train: [84] [1400/6250] eta: 0:13:52 lr: 0.000008 grad: 0.1252 (0.1379) loss: 0.8160 (0.8165) time: 0.1850 data: 0.0953 max mem: 9390 +Train: [84] [1500/6250] eta: 0:13:34 lr: 0.000008 grad: 0.1308 (0.1377) loss: 0.8094 (0.8162) time: 0.1752 data: 0.0806 max mem: 9390 +Train: [84] [1600/6250] eta: 0:13:40 lr: 0.000008 grad: 0.1308 (0.1374) loss: 0.8146 (0.8159) time: 0.3681 data: 0.2719 max mem: 9390 +Train: [84] [1700/6250] eta: 0:13:20 lr: 0.000008 grad: 0.1326 (0.1371) loss: 0.8116 (0.8159) time: 0.0981 data: 0.0002 max mem: 9390 +Train: [84] [1800/6250] eta: 0:12:55 lr: 0.000008 grad: 0.1322 (0.1368) loss: 0.8125 (0.8158) time: 0.1694 data: 0.0841 max mem: 9390 +Train: [84] [1900/6250] eta: 0:12:52 lr: 0.000008 grad: 0.1242 (0.1365) loss: 0.8199 (0.8157) time: 0.4042 data: 0.2697 max mem: 9390 +Train: [84] [2000/6250] eta: 0:12:27 lr: 0.000008 grad: 0.1270 (0.1362) loss: 0.8158 (0.8157) time: 0.1542 data: 0.0652 max mem: 9390 +Train: [84] [2100/6250] eta: 0:12:05 lr: 0.000008 grad: 0.1304 (0.1361) loss: 0.8198 (0.8157) time: 0.1661 data: 0.0867 max mem: 9390 +Train: [84] [2200/6250] eta: 0:11:43 lr: 0.000008 grad: 0.1243 (0.1359) loss: 0.8137 (0.8157) time: 0.1582 data: 0.0692 max mem: 9390 +Train: [84] [2300/6250] eta: 0:11:29 lr: 0.000008 grad: 0.1313 (0.1358) loss: 0.8111 (0.8156) time: 0.0932 data: 0.0002 max mem: 9390 +Train: [84] [2400/6250] eta: 0:11:12 lr: 0.000008 grad: 0.1345 (0.1357) loss: 0.8050 (0.8155) time: 0.2825 data: 0.1900 max mem: 9390 +Train: [84] [2500/6250] eta: 0:10:58 lr: 0.000008 grad: 0.1304 (0.1357) loss: 0.8145 (0.8154) time: 0.1930 data: 0.1116 max mem: 9390 +Train: [84] [2600/6250] eta: 0:10:43 lr: 0.000008 grad: 0.1279 (0.1355) loss: 0.8076 (0.8154) time: 0.1051 data: 0.0002 max mem: 9390 +Train: [84] [2700/6250] eta: 0:10:22 lr: 0.000008 grad: 0.1251 (0.1354) loss: 0.8153 (0.8154) time: 0.1414 data: 0.0591 max mem: 9390 +Train: [84] [2800/6250] eta: 0:10:05 lr: 0.000008 grad: 0.1229 (0.1353) loss: 0.8170 (0.8153) time: 0.1032 data: 0.0002 max mem: 9390 +Train: [84] [2900/6250] eta: 0:09:45 lr: 0.000008 grad: 0.1179 (0.1352) loss: 0.8195 (0.8154) time: 0.1011 data: 0.0002 max mem: 9390 +Train: [84] [3000/6250] eta: 0:09:30 lr: 0.000008 grad: 0.1226 (0.1350) loss: 0.8196 (0.8154) time: 0.3376 data: 0.2457 max mem: 9390 +Train: [84] [3100/6250] eta: 0:09:10 lr: 0.000008 grad: 0.1257 (0.1348) loss: 0.8169 (0.8155) time: 0.1600 data: 0.0710 max mem: 9390 +Train: [84] [3200/6250] eta: 0:08:55 lr: 0.000008 grad: 0.1254 (0.1347) loss: 0.8183 (0.8156) time: 0.3017 data: 0.2113 max mem: 9390 +Train: [84] [3300/6250] eta: 0:08:35 lr: 0.000008 grad: 0.1243 (0.1346) loss: 0.8204 (0.8156) time: 0.1414 data: 0.0425 max mem: 9390 +Train: [84] [3400/6250] eta: 0:08:17 lr: 0.000008 grad: 0.1270 (0.1345) loss: 0.8129 (0.8157) time: 0.1743 data: 0.0945 max mem: 9390 +Train: [84] [3500/6250] eta: 0:07:59 lr: 0.000008 grad: 0.1212 (0.1343) loss: 0.8255 (0.8158) time: 0.1451 data: 0.0595 max mem: 9390 +Train: [84] [3600/6250] eta: 0:07:46 lr: 0.000008 grad: 0.1221 (0.1343) loss: 0.8244 (0.8158) time: 0.1291 data: 0.0478 max mem: 9390 +Train: [84] [3700/6250] eta: 0:07:30 lr: 0.000008 grad: 0.1256 (0.1343) loss: 0.8213 (0.8158) time: 0.2915 data: 0.1900 max mem: 9390 +Train: [84] [3800/6250] eta: 0:07:11 lr: 0.000008 grad: 0.1289 (0.1342) loss: 0.8198 (0.8159) time: 0.1426 data: 0.0347 max mem: 9390 +Train: [84] [3900/6250] eta: 0:06:52 lr: 0.000008 grad: 0.1334 (0.1341) loss: 0.8202 (0.8160) time: 0.1363 data: 0.0526 max mem: 9390 +Train: [84] [4000/6250] eta: 0:06:35 lr: 0.000008 grad: 0.1273 (0.1340) loss: 0.8191 (0.8160) time: 0.1009 data: 0.0002 max mem: 9390 +Train: [84] [4100/6250] eta: 0:06:16 lr: 0.000008 grad: 0.1272 (0.1340) loss: 0.8188 (0.8160) time: 0.1595 data: 0.0747 max mem: 9390 +Train: [84] [4200/6250] eta: 0:05:58 lr: 0.000008 grad: 0.1319 (0.1340) loss: 0.8205 (0.8160) time: 0.1958 data: 0.0939 max mem: 9390 +Train: [84] [4300/6250] eta: 0:05:40 lr: 0.000008 grad: 0.1284 (0.1341) loss: 0.8150 (0.8159) time: 0.1039 data: 0.0004 max mem: 9390 +Train: [84] [4400/6250] eta: 0:05:26 lr: 0.000008 grad: 0.1321 (0.1341) loss: 0.8162 (0.8159) time: 0.4887 data: 0.3556 max mem: 9390 +Train: [84] [4500/6250] eta: 0:05:07 lr: 0.000008 grad: 0.1231 (0.1340) loss: 0.8174 (0.8158) time: 0.1884 data: 0.0943 max mem: 9390 +Train: [84] [4600/6250] eta: 0:04:50 lr: 0.000008 grad: 0.1232 (0.1340) loss: 0.8145 (0.8158) time: 0.1659 data: 0.0821 max mem: 9390 +Train: [84] [4700/6250] eta: 0:04:32 lr: 0.000008 grad: 0.1335 (0.1340) loss: 0.8145 (0.8157) time: 0.1767 data: 0.0894 max mem: 9390 +Train: [84] [4800/6250] eta: 0:04:14 lr: 0.000008 grad: 0.1236 (0.1340) loss: 0.8142 (0.8157) time: 0.1641 data: 0.0819 max mem: 9390 +Train: [84] [4900/6250] eta: 0:03:59 lr: 0.000008 grad: 0.1274 (0.1340) loss: 0.8174 (0.8157) time: 0.5457 data: 0.4532 max mem: 9390 +Train: [84] [5000/6250] eta: 0:03:41 lr: 0.000008 grad: 0.1251 (0.1339) loss: 0.8161 (0.8157) time: 0.0916 data: 0.0002 max mem: 9390 +Train: [84] [5100/6250] eta: 0:03:23 lr: 0.000008 grad: 0.1320 (0.1340) loss: 0.8164 (0.8156) time: 0.2112 data: 0.1201 max mem: 9390 +Train: [84] [5200/6250] eta: 0:03:05 lr: 0.000008 grad: 0.1422 (0.1340) loss: 0.8081 (0.8156) time: 0.1389 data: 0.0278 max mem: 9390 +Train: [84] [5300/6250] eta: 0:02:48 lr: 0.000008 grad: 0.1373 (0.1341) loss: 0.8042 (0.8155) time: 0.1406 data: 0.0413 max mem: 9390 +Train: [84] [5400/6250] eta: 0:02:30 lr: 0.000008 grad: 0.1330 (0.1342) loss: 0.8099 (0.8154) time: 0.1887 data: 0.1048 max mem: 9390 +Train: [84] [5500/6250] eta: 0:02:12 lr: 0.000008 grad: 0.1315 (0.1342) loss: 0.8124 (0.8154) time: 0.1896 data: 0.1026 max mem: 9390 +Train: [84] [5600/6250] eta: 0:01:54 lr: 0.000008 grad: 0.1287 (0.1342) loss: 0.8101 (0.8153) time: 0.1848 data: 0.0938 max mem: 9390 +Train: [84] [5700/6250] eta: 0:01:37 lr: 0.000008 grad: 0.1281 (0.1342) loss: 0.8201 (0.8153) time: 0.3598 data: 0.2616 max mem: 9390 +Train: [84] [5800/6250] eta: 0:01:19 lr: 0.000008 grad: 0.1272 (0.1342) loss: 0.8135 (0.8153) time: 0.1400 data: 0.0251 max mem: 9390 +Train: [84] [5900/6250] eta: 0:01:02 lr: 0.000008 grad: 0.1479 (0.1343) loss: 0.8085 (0.8152) time: 0.0869 data: 0.0002 max mem: 9390 +Train: [84] [6000/6250] eta: 0:00:44 lr: 0.000008 grad: 0.1327 (0.1343) loss: 0.8163 (0.8151) time: 0.1191 data: 0.0235 max mem: 9390 +Train: [84] [6100/6250] eta: 0:00:26 lr: 0.000008 grad: 0.1374 (0.1343) loss: 0.8090 (0.8151) time: 0.1323 data: 0.0445 max mem: 9390 +Train: [84] [6200/6250] eta: 0:00:08 lr: 0.000008 grad: 0.1306 (0.1343) loss: 0.8161 (0.8150) time: 0.1020 data: 0.0002 max mem: 9390 +Train: [84] [6249/6250] eta: 0:00:00 lr: 0.000008 grad: 0.1311 (0.1343) loss: 0.8120 (0.8150) time: 0.1610 data: 0.0746 max mem: 9390 +Train: [84] Total time: 0:18:32 (0.1780 s / it) +Averaged stats: lr: 0.000008 grad: 0.1311 (0.1343) loss: 0.8120 (0.8150) +Eval (hcp-train-subset): [84] [ 0/62] eta: 0:03:48 loss: 0.8309 (0.8309) time: 3.6903 data: 3.6220 max mem: 9390 +Eval (hcp-train-subset): [84] [61/62] eta: 0:00:00 loss: 0.8198 (0.8219) time: 0.1284 data: 0.1020 max mem: 9390 +Eval (hcp-train-subset): [84] Total time: 0:00:13 (0.2102 s / it) +Averaged stats (hcp-train-subset): loss: 0.8198 (0.8219) +Making plots (hcp-train-subset): example=56 +Eval (hcp-val): [84] [ 0/62] eta: 0:03:16 loss: 0.8284 (0.8284) time: 3.1769 data: 3.0966 max mem: 9390 +Eval (hcp-val): [84] [61/62] eta: 0:00:00 loss: 0.8269 (0.8293) time: 0.1218 data: 0.0967 max mem: 9390 +Eval (hcp-val): [84] Total time: 0:00:13 (0.2100 s / it) +Averaged stats (hcp-val): loss: 0.8269 (0.8293) +Making plots (hcp-val): example=25 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +Train: [85] [ 0/6250] eta: 9:05:15 lr: 0.000008 grad: 0.0976 (0.0976) loss: 0.8508 (0.8508) time: 5.2345 data: 5.0382 max mem: 9390 +Train: [85] [ 100/6250] eta: 0:23:22 lr: 0.000008 grad: 0.1076 (0.1397) loss: 0.8293 (0.8266) time: 0.1265 data: 0.0321 max mem: 9390 +Train: [85] [ 200/6250] eta: 0:19:53 lr: 0.000008 grad: 0.1117 (0.1306) loss: 0.8243 (0.8254) time: 0.1322 data: 0.0437 max mem: 9390 +Train: [85] [ 300/6250] eta: 0:18:27 lr: 0.000007 grad: 0.1199 (0.1294) loss: 0.8119 (0.8225) time: 0.1482 data: 0.0561 max mem: 9390 +Train: [85] [ 400/6250] eta: 0:17:26 lr: 0.000007 grad: 0.1234 (0.1271) loss: 0.8248 (0.8218) time: 0.1619 data: 0.0829 max mem: 9390 +Train: [85] [ 500/6250] eta: 0:16:49 lr: 0.000007 grad: 0.1208 (0.1277) loss: 0.8207 (0.8212) time: 0.1609 data: 0.0744 max mem: 9390 +Train: [85] [ 600/6250] eta: 0:16:19 lr: 0.000007 grad: 0.1208 (0.1273) loss: 0.8240 (0.8215) time: 0.1363 data: 0.0476 max mem: 9390 +Train: [85] [ 700/6250] eta: 0:16:06 lr: 0.000007 grad: 0.1228 (0.1279) loss: 0.8150 (0.8214) time: 0.1112 data: 0.0003 max mem: 9390 +Train: [85] [ 800/6250] eta: 0:15:34 lr: 0.000007 grad: 0.1333 (0.1290) loss: 0.8147 (0.8206) time: 0.2092 data: 0.1272 max mem: 9390 +Train: [85] [ 900/6250] eta: 0:15:02 lr: 0.000007 grad: 0.1279 (0.1298) loss: 0.8205 (0.8200) time: 0.1687 data: 0.0811 max mem: 9390 +Train: [85] [1000/6250] eta: 0:14:32 lr: 0.000007 grad: 0.1383 (0.1307) loss: 0.8163 (0.8195) time: 0.1408 data: 0.0531 max mem: 9390 +Train: [85] [1100/6250] eta: 0:14:03 lr: 0.000007 grad: 0.1294 (0.1316) loss: 0.8088 (0.8188) time: 0.1294 data: 0.0352 max mem: 9390 +Train: [85] [1200/6250] eta: 0:13:42 lr: 0.000007 grad: 0.1284 (0.1321) loss: 0.8064 (0.8182) time: 0.1499 data: 0.0686 max mem: 9390 +Train: [85] [1300/6250] eta: 0:13:25 lr: 0.000007 grad: 0.1345 (0.1325) loss: 0.8137 (0.8178) time: 0.1833 data: 0.0942 max mem: 9390 +Train: [85] [1400/6250] eta: 0:13:12 lr: 0.000007 grad: 0.1406 (0.1330) loss: 0.8053 (0.8172) time: 0.1192 data: 0.0204 max mem: 9390 +Train: [85] [1500/6250] eta: 0:13:02 lr: 0.000007 grad: 0.1331 (0.1334) loss: 0.8082 (0.8167) time: 0.2605 data: 0.1534 max mem: 9390 +Train: [85] [1600/6250] eta: 0:12:45 lr: 0.000007 grad: 0.1439 (0.1341) loss: 0.8082 (0.8163) time: 0.1059 data: 0.0187 max mem: 9390 +Train: [85] [1700/6250] eta: 0:12:35 lr: 0.000007 grad: 0.1406 (0.1343) loss: 0.8062 (0.8159) time: 0.2660 data: 0.1711 max mem: 9390 +Train: [85] [1800/6250] eta: 0:12:13 lr: 0.000007 grad: 0.1385 (0.1345) loss: 0.8013 (0.8156) time: 0.1606 data: 0.0709 max mem: 9390 +Train: [85] [1900/6250] eta: 0:11:53 lr: 0.000007 grad: 0.1350 (0.1348) loss: 0.8080 (0.8153) time: 0.1503 data: 0.0658 max mem: 9390 +Train: [85] [2000/6250] eta: 0:11:39 lr: 0.000007 grad: 0.1340 (0.1351) loss: 0.8093 (0.8148) time: 0.1769 data: 0.0938 max mem: 9390 +Train: [85] [2100/6250] eta: 0:11:27 lr: 0.000007 grad: 0.1331 (0.1356) loss: 0.8142 (0.8146) time: 0.2202 data: 0.1402 max mem: 9390 +Train: [85] [2200/6250] eta: 0:11:09 lr: 0.000007 grad: 0.1262 (0.1357) loss: 0.8040 (0.8143) time: 0.1947 data: 0.1048 max mem: 9390 +Train: [85] [2300/6250] eta: 0:11:01 lr: 0.000007 grad: 0.1334 (0.1359) loss: 0.8001 (0.8141) time: 0.2797 data: 0.1966 max mem: 9390 +Train: [85] [2400/6250] eta: 0:10:43 lr: 0.000007 grad: 0.1368 (0.1361) loss: 0.8174 (0.8138) time: 0.1425 data: 0.0585 max mem: 9390 +Train: [85] [2500/6250] eta: 0:10:24 lr: 0.000007 grad: 0.1370 (0.1363) loss: 0.8116 (0.8137) time: 0.1627 data: 0.0803 max mem: 9390 +Train: [85] [2600/6250] eta: 0:10:11 lr: 0.000007 grad: 0.1368 (0.1365) loss: 0.8114 (0.8136) time: 0.1048 data: 0.0002 max mem: 9390 +Train: [85] [2700/6250] eta: 0:09:54 lr: 0.000007 grad: 0.1378 (0.1366) loss: 0.8076 (0.8134) time: 0.1732 data: 0.0832 max mem: 9390 +Train: [85] [2800/6250] eta: 0:09:36 lr: 0.000007 grad: 0.1338 (0.1367) loss: 0.8088 (0.8132) time: 0.1218 data: 0.0324 max mem: 9390 +Train: [85] [2900/6250] eta: 0:09:19 lr: 0.000007 grad: 0.1439 (0.1369) loss: 0.8044 (0.8130) time: 0.1140 data: 0.0172 max mem: 9390 +Train: [85] [3000/6250] eta: 0:09:03 lr: 0.000007 grad: 0.1352 (0.1369) loss: 0.8111 (0.8130) time: 0.1740 data: 0.0817 max mem: 9390 +Train: [85] [3100/6250] eta: 0:08:44 lr: 0.000007 grad: 0.1323 (0.1370) loss: 0.8140 (0.8129) time: 0.1374 data: 0.0567 max mem: 9390 +Train: [85] [3200/6250] eta: 0:08:30 lr: 0.000007 grad: 0.1362 (0.1370) loss: 0.8108 (0.8129) time: 0.1537 data: 0.0665 max mem: 9390 +Train: [85] [3300/6250] eta: 0:08:15 lr: 0.000007 grad: 0.1330 (0.1371) loss: 0.8214 (0.8129) time: 0.2398 data: 0.1500 max mem: 9390 +Train: [85] [3400/6250] eta: 0:07:57 lr: 0.000007 grad: 0.1264 (0.1371) loss: 0.8186 (0.8130) time: 0.1769 data: 0.0938 max mem: 9390 +Train: [85] [3500/6250] eta: 0:07:40 lr: 0.000007 grad: 0.1346 (0.1372) loss: 0.8183 (0.8130) time: 0.1463 data: 0.0585 max mem: 9390 +Train: [85] [3600/6250] eta: 0:07:26 lr: 0.000007 grad: 0.1304 (0.1372) loss: 0.8120 (0.8130) time: 0.2069 data: 0.1255 max mem: 9390 +Train: [85] [3700/6250] eta: 0:07:08 lr: 0.000007 grad: 0.1381 (0.1373) loss: 0.8109 (0.8130) time: 0.1324 data: 0.0398 max mem: 9390 +Train: [85] [3800/6250] eta: 0:06:50 lr: 0.000007 grad: 0.1251 (0.1373) loss: 0.8189 (0.8130) time: 0.1166 data: 0.0204 max mem: 9390 +Train: [85] [3900/6250] eta: 0:06:34 lr: 0.000007 grad: 0.1339 (0.1373) loss: 0.8135 (0.8129) time: 0.1437 data: 0.0559 max mem: 9390 +Train: [85] [4000/6250] eta: 0:06:19 lr: 0.000007 grad: 0.1391 (0.1374) loss: 0.8069 (0.8129) time: 0.2922 data: 0.2006 max mem: 9390 +Train: [85] [4100/6250] eta: 0:06:01 lr: 0.000007 grad: 0.1350 (0.1374) loss: 0.8143 (0.8129) time: 0.1890 data: 0.0936 max mem: 9390 +Train: [85] [4200/6250] eta: 0:05:46 lr: 0.000007 grad: 0.1351 (0.1374) loss: 0.8115 (0.8129) time: 0.3438 data: 0.2644 max mem: 9390 +Train: [85] [4300/6250] eta: 0:05:30 lr: 0.000007 grad: 0.1411 (0.1375) loss: 0.8128 (0.8128) time: 0.1853 data: 0.1023 max mem: 9390 +Train: [85] [4400/6250] eta: 0:05:15 lr: 0.000007 grad: 0.1314 (0.1374) loss: 0.8109 (0.8128) time: 0.1637 data: 0.0820 max mem: 9390 +Train: [85] [4500/6250] eta: 0:04:59 lr: 0.000007 grad: 0.1467 (0.1375) loss: 0.8064 (0.8127) time: 0.1851 data: 0.0966 max mem: 9390 +Train: [85] [4600/6250] eta: 0:04:46 lr: 0.000007 grad: 0.1278 (0.1376) loss: 0.8123 (0.8126) time: 0.3039 data: 0.2232 max mem: 9390 +Train: [85] [4700/6250] eta: 0:04:28 lr: 0.000007 grad: 0.1299 (0.1376) loss: 0.8116 (0.8125) time: 0.1721 data: 0.0792 max mem: 9390 +Train: [85] [4800/6250] eta: 0:04:11 lr: 0.000007 grad: 0.1405 (0.1377) loss: 0.8079 (0.8124) time: 0.1258 data: 0.0339 max mem: 9390 +Train: [85] [4900/6250] eta: 0:03:54 lr: 0.000007 grad: 0.1422 (0.1378) loss: 0.8088 (0.8124) time: 0.2508 data: 0.1591 max mem: 9390 +Train: [85] [5000/6250] eta: 0:03:36 lr: 0.000007 grad: 0.1246 (0.1378) loss: 0.8133 (0.8123) time: 0.1972 data: 0.1158 max mem: 9390 +Train: [85] [5100/6250] eta: 0:03:18 lr: 0.000007 grad: 0.1366 (0.1379) loss: 0.8041 (0.8122) time: 0.1279 data: 0.0270 max mem: 9390 +Train: [85] [5200/6250] eta: 0:03:01 lr: 0.000007 grad: 0.1271 (0.1379) loss: 0.8153 (0.8122) time: 0.2399 data: 0.1489 max mem: 9390 +Train: [85] [5300/6250] eta: 0:02:44 lr: 0.000007 grad: 0.1319 (0.1380) loss: 0.8128 (0.8122) time: 0.0936 data: 0.0002 max mem: 9390 +Train: [85] [5400/6250] eta: 0:02:26 lr: 0.000007 grad: 0.1348 (0.1379) loss: 0.8093 (0.8121) time: 0.1530 data: 0.0721 max mem: 9390 +Train: [85] [5500/6250] eta: 0:02:09 lr: 0.000007 grad: 0.1359 (0.1379) loss: 0.8159 (0.8122) time: 0.1371 data: 0.0569 max mem: 9390 +Train: [85] [5600/6250] eta: 0:01:52 lr: 0.000007 grad: 0.1250 (0.1379) loss: 0.8127 (0.8122) time: 0.2010 data: 0.1086 max mem: 9390 +Train: [85] [5700/6250] eta: 0:01:34 lr: 0.000007 grad: 0.1346 (0.1379) loss: 0.8145 (0.8122) time: 0.1644 data: 0.0871 max mem: 9390 +Train: [85] [5800/6250] eta: 0:01:17 lr: 0.000007 grad: 0.1330 (0.1378) loss: 0.8107 (0.8121) time: 0.1160 data: 0.0291 max mem: 9390 +Train: [85] [5900/6250] eta: 0:01:00 lr: 0.000007 grad: 0.1378 (0.1378) loss: 0.8139 (0.8121) time: 0.1489 data: 0.0595 max mem: 9390 +Train: [85] [6000/6250] eta: 0:00:42 lr: 0.000007 grad: 0.1315 (0.1379) loss: 0.8109 (0.8121) time: 0.1696 data: 0.0876 max mem: 9390 +Train: [85] [6100/6250] eta: 0:00:25 lr: 0.000007 grad: 0.1321 (0.1378) loss: 0.8137 (0.8121) time: 0.2912 data: 0.1994 max mem: 9390 +Train: [85] [6200/6250] eta: 0:00:08 lr: 0.000007 grad: 0.1327 (0.1378) loss: 0.8162 (0.8121) time: 0.3125 data: 0.2274 max mem: 9390 +Train: [85] [6249/6250] eta: 0:00:00 lr: 0.000007 grad: 0.1330 (0.1378) loss: 0.8123 (0.8121) time: 0.2281 data: 0.1405 max mem: 9390 +Train: [85] Total time: 0:18:03 (0.1733 s / it) +Averaged stats: lr: 0.000007 grad: 0.1330 (0.1378) loss: 0.8123 (0.8121) +Eval (hcp-train-subset): [85] [ 0/62] eta: 0:05:12 loss: 0.8312 (0.8312) time: 5.0363 data: 5.0045 max mem: 9390 +Eval (hcp-train-subset): [85] [61/62] eta: 0:00:00 loss: 0.8166 (0.8215) time: 0.1308 data: 0.1040 max mem: 9390 +Eval (hcp-train-subset): [85] Total time: 0:00:13 (0.2241 s / it) +Averaged stats (hcp-train-subset): loss: 0.8166 (0.8215) +Eval (hcp-val): [85] [ 0/62] eta: 0:04:29 loss: 0.8278 (0.8278) time: 4.3506 data: 4.2825 max mem: 9390 +Eval (hcp-val): [85] [61/62] eta: 0:00:00 loss: 0.8291 (0.8298) time: 0.1620 data: 0.1354 max mem: 9390 +Eval (hcp-val): [85] Total time: 0:00:14 (0.2358 s / it) +Averaged stats (hcp-val): loss: 0.8291 (0.8298) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +Train: [86] [ 0/6250] eta: 9:58:57 lr: 0.000007 grad: 0.2886 (0.2886) loss: 0.8056 (0.8056) time: 5.7500 data: 5.5962 max mem: 9390 +Train: [86] [ 100/6250] eta: 0:22:54 lr: 0.000007 grad: 0.1997 (0.2066) loss: 0.7981 (0.8070) time: 0.1513 data: 0.0462 max mem: 9390 +Train: [86] [ 200/6250] eta: 0:19:16 lr: 0.000007 grad: 0.1405 (0.1875) loss: 0.8121 (0.8049) time: 0.1688 data: 0.0760 max mem: 9390 +Train: [86] [ 300/6250] eta: 0:17:36 lr: 0.000007 grad: 0.1311 (0.1726) loss: 0.8125 (0.8063) time: 0.1320 data: 0.0343 max mem: 9390 +Train: [86] [ 400/6250] eta: 0:16:52 lr: 0.000007 grad: 0.1211 (0.1629) loss: 0.8147 (0.8088) time: 0.1884 data: 0.0774 max mem: 9390 +Train: [86] [ 500/6250] eta: 0:16:26 lr: 0.000007 grad: 0.1338 (0.1591) loss: 0.8159 (0.8092) time: 0.1974 data: 0.0977 max mem: 9390 +Train: [86] [ 600/6250] eta: 0:16:24 lr: 0.000006 grad: 0.1303 (0.1557) loss: 0.8086 (0.8097) time: 0.2758 data: 0.1857 max mem: 9390 +Train: [86] [ 700/6250] eta: 0:15:57 lr: 0.000006 grad: 0.1320 (0.1537) loss: 0.8122 (0.8099) time: 0.1821 data: 0.0887 max mem: 9390 +Train: [86] [ 800/6250] eta: 0:15:47 lr: 0.000006 grad: 0.1437 (0.1522) loss: 0.8076 (0.8098) time: 0.1933 data: 0.1118 max mem: 9390 +Train: [86] [ 900/6250] eta: 0:15:32 lr: 0.000006 grad: 0.1360 (0.1506) loss: 0.8164 (0.8100) time: 0.1833 data: 0.0983 max mem: 9390 +Train: [86] [1000/6250] eta: 0:15:07 lr: 0.000006 grad: 0.1344 (0.1488) loss: 0.8150 (0.8104) time: 0.1609 data: 0.0754 max mem: 9390 +Train: [86] [1100/6250] eta: 0:14:47 lr: 0.000006 grad: 0.1285 (0.1476) loss: 0.8165 (0.8105) time: 0.1746 data: 0.0816 max mem: 9390 +Train: [86] [1200/6250] eta: 0:14:28 lr: 0.000006 grad: 0.1313 (0.1463) loss: 0.8107 (0.8107) time: 0.1722 data: 0.0809 max mem: 9390 +Train: [86] [1300/6250] eta: 0:14:08 lr: 0.000006 grad: 0.1249 (0.1454) loss: 0.8129 (0.8107) time: 0.1720 data: 0.0923 max mem: 9390 +Train: [86] [1400/6250] eta: 0:13:47 lr: 0.000006 grad: 0.1408 (0.1448) loss: 0.8125 (0.8107) time: 0.2071 data: 0.1241 max mem: 9390 +Train: [86] [1500/6250] eta: 0:13:23 lr: 0.000006 grad: 0.1342 (0.1444) loss: 0.8145 (0.8108) time: 0.1522 data: 0.0688 max mem: 9390 +Train: [86] [1600/6250] eta: 0:13:03 lr: 0.000006 grad: 0.1373 (0.1440) loss: 0.8112 (0.8107) time: 0.1433 data: 0.0631 max mem: 9390 +Train: [86] [1700/6250] eta: 0:12:44 lr: 0.000006 grad: 0.1326 (0.1434) loss: 0.8153 (0.8109) time: 0.1723 data: 0.0945 max mem: 9390 +Train: [86] [1800/6250] eta: 0:12:29 lr: 0.000006 grad: 0.1259 (0.1431) loss: 0.8102 (0.8110) time: 0.1191 data: 0.0353 max mem: 9390 +Train: [86] [1900/6250] eta: 0:12:11 lr: 0.000006 grad: 0.1324 (0.1429) loss: 0.8090 (0.8109) time: 0.1626 data: 0.0772 max mem: 9390 +Train: [86] [2000/6250] eta: 0:12:05 lr: 0.000006 grad: 0.1323 (0.1426) loss: 0.8166 (0.8110) time: 0.1235 data: 0.0376 max mem: 9390 +Train: [86] [2100/6250] eta: 0:11:55 lr: 0.000006 grad: 0.1423 (0.1423) loss: 0.8165 (0.8111) time: 0.2855 data: 0.1952 max mem: 9390 +Train: [86] [2200/6250] eta: 0:11:33 lr: 0.000006 grad: 0.1398 (0.1421) loss: 0.8142 (0.8112) time: 0.1651 data: 0.0782 max mem: 9390 +Train: [86] [2300/6250] eta: 0:11:17 lr: 0.000006 grad: 0.1338 (0.1419) loss: 0.8119 (0.8112) time: 0.2495 data: 0.1521 max mem: 9390 +Train: [86] [2400/6250] eta: 0:11:02 lr: 0.000006 grad: 0.1316 (0.1417) loss: 0.8113 (0.8112) time: 0.1301 data: 0.0329 max mem: 9390 +Train: [86] [2500/6250] eta: 0:10:48 lr: 0.000006 grad: 0.1329 (0.1414) loss: 0.8158 (0.8115) time: 0.1260 data: 0.0137 max mem: 9390 +Train: [86] [2600/6250] eta: 0:10:29 lr: 0.000006 grad: 0.1378 (0.1413) loss: 0.8129 (0.8115) time: 0.1878 data: 0.1008 max mem: 9390 +Train: [86] [2700/6250] eta: 0:10:24 lr: 0.000006 grad: 0.1312 (0.1411) loss: 0.8156 (0.8116) time: 0.0964 data: 0.0002 max mem: 9390 +Train: [86] [2800/6250] eta: 0:10:12 lr: 0.000006 grad: 0.1421 (0.1410) loss: 0.8087 (0.8116) time: 0.2083 data: 0.1099 max mem: 9390 +Train: [86] [2900/6250] eta: 0:09:53 lr: 0.000006 grad: 0.1327 (0.1411) loss: 0.8065 (0.8116) time: 0.1326 data: 0.0468 max mem: 9390 +Train: [86] [3000/6250] eta: 0:09:33 lr: 0.000006 grad: 0.1350 (0.1409) loss: 0.8141 (0.8116) time: 0.1864 data: 0.1005 max mem: 9390 +Train: [86] [3100/6250] eta: 0:09:13 lr: 0.000006 grad: 0.1283 (0.1407) loss: 0.8178 (0.8116) time: 0.1720 data: 0.0799 max mem: 9390 +Train: [86] [3200/6250] eta: 0:08:58 lr: 0.000006 grad: 0.1264 (0.1405) loss: 0.8158 (0.8117) time: 0.2907 data: 0.2013 max mem: 9390 +Train: [86] [3300/6250] eta: 0:08:38 lr: 0.000006 grad: 0.1306 (0.1403) loss: 0.8156 (0.8117) time: 0.1808 data: 0.0783 max mem: 9390 +Train: [86] [3400/6250] eta: 0:08:22 lr: 0.000006 grad: 0.1311 (0.1403) loss: 0.8167 (0.8117) time: 0.2735 data: 0.1881 max mem: 9390 +Train: [86] [3500/6250] eta: 0:08:06 lr: 0.000006 grad: 0.1352 (0.1401) loss: 0.8134 (0.8118) time: 0.1774 data: 0.0869 max mem: 9390 +Train: [86] [3600/6250] eta: 0:07:49 lr: 0.000006 grad: 0.1317 (0.1400) loss: 0.8187 (0.8119) time: 0.0949 data: 0.0003 max mem: 9390 +Train: [86] [3700/6250] eta: 0:07:32 lr: 0.000006 grad: 0.1327 (0.1398) loss: 0.8172 (0.8120) time: 0.2633 data: 0.1757 max mem: 9390 +Train: [86] [3800/6250] eta: 0:07:14 lr: 0.000006 grad: 0.1339 (0.1398) loss: 0.8135 (0.8120) time: 0.0920 data: 0.0002 max mem: 9390 +Train: [86] [3900/6250] eta: 0:07:01 lr: 0.000006 grad: 0.1374 (0.1398) loss: 0.8121 (0.8120) time: 0.1422 data: 0.0464 max mem: 9390 +Train: [86] [4000/6250] eta: 0:06:42 lr: 0.000006 grad: 0.1361 (0.1398) loss: 0.8143 (0.8120) time: 0.1434 data: 0.0464 max mem: 9390 +Train: [86] [4100/6250] eta: 0:06:23 lr: 0.000006 grad: 0.1335 (0.1398) loss: 0.8059 (0.8120) time: 0.1301 data: 0.0356 max mem: 9390 +Train: [86] [4200/6250] eta: 0:06:09 lr: 0.000006 grad: 0.1349 (0.1398) loss: 0.8137 (0.8120) time: 0.1767 data: 0.0140 max mem: 9390 +Train: [86] [4300/6250] eta: 0:05:50 lr: 0.000006 grad: 0.1373 (0.1398) loss: 0.8069 (0.8119) time: 0.1006 data: 0.0002 max mem: 9390 +Train: [86] [4400/6250] eta: 0:05:31 lr: 0.000006 grad: 0.1395 (0.1398) loss: 0.8063 (0.8119) time: 0.1355 data: 0.0343 max mem: 9390 +Train: [86] [4500/6250] eta: 0:05:15 lr: 0.000006 grad: 0.1299 (0.1398) loss: 0.8110 (0.8119) time: 0.1369 data: 0.0422 max mem: 9390 +Train: [86] [4600/6250] eta: 0:04:58 lr: 0.000006 grad: 0.1257 (0.1397) loss: 0.8162 (0.8119) time: 0.1160 data: 0.0312 max mem: 9390 +Train: [86] [4700/6250] eta: 0:04:39 lr: 0.000006 grad: 0.1316 (0.1396) loss: 0.8129 (0.8119) time: 0.0937 data: 0.0038 max mem: 9390 +Train: [86] [4800/6250] eta: 0:04:21 lr: 0.000006 grad: 0.1322 (0.1396) loss: 0.8092 (0.8120) time: 0.1653 data: 0.0811 max mem: 9390 +Train: [86] [4900/6250] eta: 0:04:02 lr: 0.000006 grad: 0.1386 (0.1396) loss: 0.8090 (0.8120) time: 0.1457 data: 0.0623 max mem: 9390 +Train: [86] [5000/6250] eta: 0:03:46 lr: 0.000006 grad: 0.1323 (0.1396) loss: 0.8144 (0.8120) time: 0.2559 data: 0.1482 max mem: 9390 +Train: [86] [5100/6250] eta: 0:03:28 lr: 0.000006 grad: 0.1406 (0.1397) loss: 0.8119 (0.8120) time: 0.1311 data: 0.0341 max mem: 9390 +Train: [86] [5200/6250] eta: 0:03:09 lr: 0.000006 grad: 0.1326 (0.1396) loss: 0.8100 (0.8120) time: 0.1282 data: 0.0228 max mem: 9390 +Train: [86] [5300/6250] eta: 0:02:53 lr: 0.000006 grad: 0.1412 (0.1398) loss: 0.8068 (0.8119) time: 0.6420 data: 0.5621 max mem: 9390 +Train: [86] [5400/6250] eta: 0:02:35 lr: 0.000006 grad: 0.1407 (0.1399) loss: 0.8130 (0.8119) time: 0.3997 data: 0.2979 max mem: 9390 +Train: [86] [5500/6250] eta: 0:02:17 lr: 0.000006 grad: 0.1353 (0.1400) loss: 0.8065 (0.8118) time: 0.1310 data: 0.0425 max mem: 9390 +Train: [86] [5600/6250] eta: 0:01:58 lr: 0.000006 grad: 0.1330 (0.1400) loss: 0.8165 (0.8118) time: 0.1587 data: 0.0765 max mem: 9390 +Train: [86] [5700/6250] eta: 0:01:40 lr: 0.000006 grad: 0.1469 (0.1400) loss: 0.8065 (0.8118) time: 0.2709 data: 0.1874 max mem: 9390 +Train: [86] [5800/6250] eta: 0:01:22 lr: 0.000006 grad: 0.1323 (0.1399) loss: 0.8134 (0.8118) time: 0.2356 data: 0.1453 max mem: 9390 +Train: [86] [5900/6250] eta: 0:01:03 lr: 0.000006 grad: 0.1248 (0.1399) loss: 0.8153 (0.8118) time: 0.1572 data: 0.0661 max mem: 9390 +Train: [86] [6000/6250] eta: 0:00:45 lr: 0.000006 grad: 0.1367 (0.1398) loss: 0.8115 (0.8118) time: 0.2587 data: 0.1817 max mem: 9390 +Train: [86] [6100/6250] eta: 0:00:27 lr: 0.000006 grad: 0.1335 (0.1397) loss: 0.8093 (0.8119) time: 0.1119 data: 0.0285 max mem: 9390 +Train: [86] [6200/6250] eta: 0:00:09 lr: 0.000006 grad: 0.1419 (0.1397) loss: 0.8114 (0.8119) time: 0.1687 data: 0.0815 max mem: 9390 +Train: [86] [6249/6250] eta: 0:00:00 lr: 0.000006 grad: 0.1354 (0.1397) loss: 0.8098 (0.8119) time: 0.1701 data: 0.0907 max mem: 9390 +Train: [86] Total time: 0:19:06 (0.1834 s / it) +Averaged stats: lr: 0.000006 grad: 0.1354 (0.1397) loss: 0.8098 (0.8119) +Eval (hcp-train-subset): [86] [ 0/62] eta: 0:04:27 loss: 0.8268 (0.8268) time: 4.3164 data: 4.2862 max mem: 9390 +Eval (hcp-train-subset): [86] [61/62] eta: 0:00:00 loss: 0.8168 (0.8203) time: 0.1317 data: 0.1066 max mem: 9390 +Eval (hcp-train-subset): [86] Total time: 0:00:13 (0.2134 s / it) +Averaged stats (hcp-train-subset): loss: 0.8168 (0.8203) +Eval (hcp-val): [86] [ 0/62] eta: 0:04:01 loss: 0.8280 (0.8280) time: 3.8883 data: 3.8341 max mem: 9390 +Eval (hcp-val): [86] [61/62] eta: 0:00:00 loss: 0.8275 (0.8292) time: 0.1242 data: 0.0976 max mem: 9390 +Eval (hcp-val): [86] Total time: 0:00:13 (0.2215 s / it) +Averaged stats (hcp-val): loss: 0.8275 (0.8292) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +Train: [87] [ 0/6250] eta: 7:12:49 lr: 0.000006 grad: 0.1026 (0.1026) loss: 0.8669 (0.8669) time: 4.1552 data: 3.8785 max mem: 9390 +Train: [87] [ 100/6250] eta: 0:23:19 lr: 0.000006 grad: 0.1340 (0.1633) loss: 0.8244 (0.8166) time: 0.1683 data: 0.0744 max mem: 9390 +Train: [87] [ 200/6250] eta: 0:20:10 lr: 0.000006 grad: 0.1513 (0.1582) loss: 0.8101 (0.8154) time: 0.1692 data: 0.0757 max mem: 9390 +Train: [87] [ 300/6250] eta: 0:18:40 lr: 0.000006 grad: 0.1449 (0.1554) loss: 0.8104 (0.8141) time: 0.1627 data: 0.0673 max mem: 9390 +Train: [87] [ 400/6250] eta: 0:17:34 lr: 0.000006 grad: 0.1278 (0.1521) loss: 0.8188 (0.8141) time: 0.1787 data: 0.0892 max mem: 9390 +Train: [87] [ 500/6250] eta: 0:16:47 lr: 0.000006 grad: 0.1373 (0.1503) loss: 0.8158 (0.8147) time: 0.1476 data: 0.0540 max mem: 9390 +Train: [87] [ 600/6250] eta: 0:16:39 lr: 0.000006 grad: 0.1374 (0.1494) loss: 0.8193 (0.8150) time: 0.1037 data: 0.0002 max mem: 9390 +Train: [87] [ 700/6250] eta: 0:15:52 lr: 0.000006 grad: 0.1385 (0.1485) loss: 0.8172 (0.8150) time: 0.1397 data: 0.0526 max mem: 9390 +Train: [87] [ 800/6250] eta: 0:15:19 lr: 0.000006 grad: 0.1346 (0.1477) loss: 0.8095 (0.8150) time: 0.1175 data: 0.0277 max mem: 9390 +Train: [87] [ 900/6250] eta: 0:15:01 lr: 0.000006 grad: 0.1393 (0.1473) loss: 0.8120 (0.8146) time: 0.1699 data: 0.0808 max mem: 9390 +Train: [87] [1000/6250] eta: 0:14:55 lr: 0.000006 grad: 0.1304 (0.1465) loss: 0.8132 (0.8146) time: 0.1963 data: 0.1136 max mem: 9390 +Train: [87] [1100/6250] eta: 0:14:39 lr: 0.000006 grad: 0.1290 (0.1457) loss: 0.8171 (0.8147) time: 0.2168 data: 0.1391 max mem: 9390 +Train: [87] [1200/6250] eta: 0:14:17 lr: 0.000006 grad: 0.1355 (0.1454) loss: 0.8079 (0.8144) time: 0.1579 data: 0.0780 max mem: 9390 +Train: [87] [1300/6250] eta: 0:13:59 lr: 0.000006 grad: 0.1358 (0.1446) loss: 0.8171 (0.8146) time: 0.1899 data: 0.0959 max mem: 9390 +Train: [87] [1400/6250] eta: 0:13:42 lr: 0.000005 grad: 0.1351 (0.1440) loss: 0.8166 (0.8147) time: 0.1694 data: 0.0883 max mem: 9390 +Train: [87] [1500/6250] eta: 0:13:23 lr: 0.000005 grad: 0.1370 (0.1434) loss: 0.8163 (0.8147) time: 0.1640 data: 0.0759 max mem: 9390 +Train: [87] [1600/6250] eta: 0:13:06 lr: 0.000005 grad: 0.1253 (0.1432) loss: 0.8130 (0.8147) time: 0.1013 data: 0.0150 max mem: 9390 +Train: [87] [1700/6250] eta: 0:12:45 lr: 0.000005 grad: 0.1258 (0.1428) loss: 0.8166 (0.8148) time: 0.1657 data: 0.0832 max mem: 9390 +Train: [87] [1800/6250] eta: 0:12:31 lr: 0.000005 grad: 0.1352 (0.1425) loss: 0.8129 (0.8146) time: 0.1925 data: 0.1146 max mem: 9390 +Train: [87] [1900/6250] eta: 0:12:13 lr: 0.000005 grad: 0.1384 (0.1422) loss: 0.8180 (0.8146) time: 0.1600 data: 0.0779 max mem: 9390 +Train: [87] [2000/6250] eta: 0:11:55 lr: 0.000005 grad: 0.1379 (0.1420) loss: 0.8117 (0.8144) time: 0.2267 data: 0.1326 max mem: 9390 +Train: [87] [2100/6250] eta: 0:11:33 lr: 0.000005 grad: 0.1366 (0.1418) loss: 0.8091 (0.8143) time: 0.1625 data: 0.0821 max mem: 9390 +Train: [87] [2200/6250] eta: 0:11:16 lr: 0.000005 grad: 0.1395 (0.1419) loss: 0.8116 (0.8142) time: 0.1527 data: 0.0490 max mem: 9390 +Train: [87] [2300/6250] eta: 0:11:01 lr: 0.000005 grad: 0.1385 (0.1420) loss: 0.8094 (0.8141) time: 0.2199 data: 0.1307 max mem: 9390 +Train: [87] [2400/6250] eta: 0:10:41 lr: 0.000005 grad: 0.1335 (0.1420) loss: 0.8120 (0.8140) time: 0.1725 data: 0.0895 max mem: 9390 +Train: [87] [2500/6250] eta: 0:10:22 lr: 0.000005 grad: 0.1303 (0.1420) loss: 0.8140 (0.8140) time: 0.1825 data: 0.0995 max mem: 9390 +Train: [87] [2600/6250] eta: 0:10:05 lr: 0.000005 grad: 0.1266 (0.1419) loss: 0.8154 (0.8140) time: 0.1107 data: 0.0186 max mem: 9390 +Train: [87] [2700/6250] eta: 0:09:47 lr: 0.000005 grad: 0.1396 (0.1418) loss: 0.8110 (0.8140) time: 0.1533 data: 0.0634 max mem: 9390 +Train: [87] [2800/6250] eta: 0:09:31 lr: 0.000005 grad: 0.1357 (0.1417) loss: 0.8163 (0.8140) time: 0.1655 data: 0.0875 max mem: 9390 +Train: [87] [2900/6250] eta: 0:09:19 lr: 0.000005 grad: 0.1377 (0.1416) loss: 0.8109 (0.8140) time: 0.3976 data: 0.2507 max mem: 9390 +Train: [87] [3000/6250] eta: 0:08:59 lr: 0.000005 grad: 0.1401 (0.1415) loss: 0.8151 (0.8141) time: 0.1829 data: 0.1015 max mem: 9390 +Train: [87] [3100/6250] eta: 0:08:44 lr: 0.000005 grad: 0.1354 (0.1414) loss: 0.8151 (0.8142) time: 0.0952 data: 0.0002 max mem: 9390 +Train: [87] [3200/6250] eta: 0:08:26 lr: 0.000005 grad: 0.1308 (0.1412) loss: 0.8190 (0.8143) time: 0.1800 data: 0.0801 max mem: 9390 +Train: [87] [3300/6250] eta: 0:08:11 lr: 0.000005 grad: 0.1247 (0.1410) loss: 0.8215 (0.8144) time: 0.1056 data: 0.0011 max mem: 9390 +Train: [87] [3400/6250] eta: 0:07:56 lr: 0.000005 grad: 0.1338 (0.1408) loss: 0.8184 (0.8145) time: 0.3055 data: 0.2049 max mem: 9390 +Train: [87] [3500/6250] eta: 0:07:38 lr: 0.000005 grad: 0.1357 (0.1406) loss: 0.8139 (0.8146) time: 0.1893 data: 0.0951 max mem: 9390 +Train: [87] [3600/6250] eta: 0:07:22 lr: 0.000005 grad: 0.1348 (0.1405) loss: 0.8200 (0.8148) time: 0.1913 data: 0.1029 max mem: 9390 +Train: [87] [3700/6250] eta: 0:07:05 lr: 0.000005 grad: 0.1346 (0.1403) loss: 0.8214 (0.8149) time: 0.1486 data: 0.0674 max mem: 9390 +Train: [87] [3800/6250] eta: 0:06:50 lr: 0.000005 grad: 0.1366 (0.1403) loss: 0.8125 (0.8150) time: 0.1345 data: 0.0498 max mem: 9390 +Train: [87] [3900/6250] eta: 0:06:34 lr: 0.000005 grad: 0.1425 (0.1403) loss: 0.8139 (0.8150) time: 0.1921 data: 0.1161 max mem: 9390 +Train: [87] [4000/6250] eta: 0:06:18 lr: 0.000005 grad: 0.1391 (0.1403) loss: 0.8174 (0.8150) time: 0.1793 data: 0.1002 max mem: 9390 +Train: [87] [4100/6250] eta: 0:06:04 lr: 0.000005 grad: 0.1348 (0.1403) loss: 0.8214 (0.8151) time: 0.1631 data: 0.0740 max mem: 9390 +Train: [87] [4200/6250] eta: 0:05:48 lr: 0.000005 grad: 0.1349 (0.1403) loss: 0.8162 (0.8151) time: 0.1696 data: 0.0889 max mem: 9390 +Train: [87] [4300/6250] eta: 0:05:33 lr: 0.000005 grad: 0.1363 (0.1404) loss: 0.8089 (0.8151) time: 0.0986 data: 0.0037 max mem: 9390 +Train: [87] [4400/6250] eta: 0:05:18 lr: 0.000005 grad: 0.1355 (0.1404) loss: 0.8188 (0.8151) time: 0.1449 data: 0.0386 max mem: 9390 +Train: [87] [4500/6250] eta: 0:05:02 lr: 0.000005 grad: 0.1334 (0.1403) loss: 0.8139 (0.8150) time: 0.1653 data: 0.0752 max mem: 9390 +Train: [87] [4600/6250] eta: 0:04:45 lr: 0.000005 grad: 0.1296 (0.1403) loss: 0.8185 (0.8150) time: 0.1477 data: 0.0524 max mem: 9390 +Train: [87] [4700/6250] eta: 0:04:28 lr: 0.000005 grad: 0.1342 (0.1402) loss: 0.8174 (0.8150) time: 0.1721 data: 0.0862 max mem: 9390 +Train: [87] [4800/6250] eta: 0:04:10 lr: 0.000005 grad: 0.1286 (0.1401) loss: 0.8135 (0.8150) time: 0.1480 data: 0.0675 max mem: 9390 +Train: [87] [4900/6250] eta: 0:03:53 lr: 0.000005 grad: 0.1348 (0.1402) loss: 0.8078 (0.8150) time: 0.1048 data: 0.0163 max mem: 9390 +Train: [87] [5000/6250] eta: 0:03:35 lr: 0.000005 grad: 0.1326 (0.1403) loss: 0.8146 (0.8150) time: 0.1646 data: 0.0796 max mem: 9390 +Train: [87] [5100/6250] eta: 0:03:18 lr: 0.000005 grad: 0.1439 (0.1404) loss: 0.8133 (0.8148) time: 0.1473 data: 0.0657 max mem: 9390 +Train: [87] [5200/6250] eta: 0:03:01 lr: 0.000005 grad: 0.1356 (0.1405) loss: 0.8117 (0.8148) time: 0.2412 data: 0.1671 max mem: 9390 +Train: [87] [5300/6250] eta: 0:02:44 lr: 0.000005 grad: 0.1504 (0.1406) loss: 0.8146 (0.8147) time: 0.1786 data: 0.0971 max mem: 9390 +Train: [87] [5400/6250] eta: 0:02:26 lr: 0.000005 grad: 0.1389 (0.1406) loss: 0.8149 (0.8146) time: 0.2077 data: 0.1259 max mem: 9390 +Train: [87] [5500/6250] eta: 0:02:09 lr: 0.000005 grad: 0.1465 (0.1407) loss: 0.8160 (0.8146) time: 0.1111 data: 0.0182 max mem: 9390 +Train: [87] [5600/6250] eta: 0:01:51 lr: 0.000005 grad: 0.1396 (0.1407) loss: 0.8105 (0.8145) time: 0.1970 data: 0.1134 max mem: 9390 +Train: [87] [5700/6250] eta: 0:01:34 lr: 0.000005 grad: 0.1410 (0.1407) loss: 0.8179 (0.8145) time: 0.1329 data: 0.0517 max mem: 9390 +Train: [87] [5800/6250] eta: 0:01:17 lr: 0.000005 grad: 0.1255 (0.1407) loss: 0.8185 (0.8145) time: 0.1201 data: 0.0259 max mem: 9390 +Train: [87] [5900/6250] eta: 0:01:00 lr: 0.000005 grad: 0.1381 (0.1407) loss: 0.8173 (0.8145) time: 0.3578 data: 0.2544 max mem: 9390 +Train: [87] [6000/6250] eta: 0:00:43 lr: 0.000005 grad: 0.1368 (0.1407) loss: 0.8153 (0.8145) time: 0.1331 data: 0.0468 max mem: 9390 +Train: [87] [6100/6250] eta: 0:00:25 lr: 0.000005 grad: 0.1416 (0.1408) loss: 0.8108 (0.8145) time: 0.1534 data: 0.0700 max mem: 9390 +Train: [87] [6200/6250] eta: 0:00:08 lr: 0.000005 grad: 0.1370 (0.1408) loss: 0.8116 (0.8145) time: 0.1207 data: 0.0002 max mem: 9390 +Train: [87] [6249/6250] eta: 0:00:00 lr: 0.000005 grad: 0.1284 (0.1408) loss: 0.8117 (0.8145) time: 0.0917 data: 0.0002 max mem: 9390 +Train: [87] Total time: 0:18:08 (0.1742 s / it) +Averaged stats: lr: 0.000005 grad: 0.1284 (0.1408) loss: 0.8117 (0.8145) +Eval (hcp-train-subset): [87] [ 0/62] eta: 0:04:44 loss: 0.8304 (0.8304) time: 4.5912 data: 4.5264 max mem: 9390 +Eval (hcp-train-subset): [87] [61/62] eta: 0:00:00 loss: 0.8157 (0.8204) time: 0.1222 data: 0.0974 max mem: 9390 +Eval (hcp-train-subset): [87] Total time: 0:00:13 (0.2170 s / it) +Averaged stats (hcp-train-subset): loss: 0.8157 (0.8204) +Eval (hcp-val): [87] [ 0/62] eta: 0:04:58 loss: 0.8293 (0.8293) time: 4.8135 data: 4.7836 max mem: 9390 +Eval (hcp-val): [87] [61/62] eta: 0:00:00 loss: 0.8275 (0.8292) time: 0.1276 data: 0.1020 max mem: 9390 +Eval (hcp-val): [87] Total time: 0:00:13 (0.2153 s / it) +Averaged stats (hcp-val): loss: 0.8275 (0.8292) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +Train: [88] [ 0/6250] eta: 10:46:46 lr: 0.000005 grad: 0.1171 (0.1171) loss: 0.8159 (0.8159) time: 6.2090 data: 6.1012 max mem: 9390 +Train: [88] [ 100/6250] eta: 0:23:31 lr: 0.000005 grad: 0.1667 (0.1760) loss: 0.8081 (0.8229) time: 0.1495 data: 0.0500 max mem: 9390 +Train: [88] [ 200/6250] eta: 0:20:04 lr: 0.000005 grad: 0.1711 (0.1781) loss: 0.7861 (0.8120) time: 0.1663 data: 0.0607 max mem: 9390 +Train: [88] [ 300/6250] eta: 0:20:54 lr: 0.000005 grad: 0.1505 (0.1733) loss: 0.7909 (0.8071) time: 0.1806 data: 0.0482 max mem: 9390 +Train: [88] [ 400/6250] eta: 0:19:38 lr: 0.000005 grad: 0.1354 (0.1669) loss: 0.8152 (0.8068) time: 0.2477 data: 0.1549 max mem: 9390 +Train: [88] [ 500/6250] eta: 0:18:25 lr: 0.000005 grad: 0.1464 (0.1633) loss: 0.8032 (0.8079) time: 0.1653 data: 0.0704 max mem: 9390 +Train: [88] [ 600/6250] eta: 0:17:55 lr: 0.000005 grad: 0.1360 (0.1598) loss: 0.8061 (0.8080) time: 0.1230 data: 0.0055 max mem: 9390 +Train: [88] [ 700/6250] eta: 0:18:52 lr: 0.000005 grad: 0.1406 (0.1573) loss: 0.8113 (0.8085) time: 0.3153 data: 0.2328 max mem: 9390 +Train: [88] [ 800/6250] eta: 0:17:59 lr: 0.000005 grad: 0.1323 (0.1555) loss: 0.8219 (0.8093) time: 0.1519 data: 0.0687 max mem: 9390 +Train: [88] [ 900/6250] eta: 0:17:39 lr: 0.000005 grad: 0.1390 (0.1536) loss: 0.8137 (0.8100) time: 0.1369 data: 0.0417 max mem: 9390 +Train: [88] [1000/6250] eta: 0:17:31 lr: 0.000005 grad: 0.1303 (0.1519) loss: 0.8162 (0.8109) time: 0.2452 data: 0.1599 max mem: 9390 +Train: [88] [1100/6250] eta: 0:17:13 lr: 0.000005 grad: 0.1365 (0.1506) loss: 0.8148 (0.8115) time: 0.1657 data: 0.0861 max mem: 9390 +Train: [88] [1200/6250] eta: 0:16:46 lr: 0.000005 grad: 0.1381 (0.1497) loss: 0.8180 (0.8118) time: 0.1489 data: 0.0667 max mem: 9390 +Train: [88] [1300/6250] eta: 0:16:35 lr: 0.000005 grad: 0.1207 (0.1484) loss: 0.8208 (0.8123) time: 0.2597 data: 0.1665 max mem: 9390 +Train: [88] [1400/6250] eta: 0:16:03 lr: 0.000005 grad: 0.1382 (0.1475) loss: 0.8139 (0.8127) time: 0.1827 data: 0.0957 max mem: 9390 +Train: [88] [1500/6250] eta: 0:15:36 lr: 0.000005 grad: 0.1338 (0.1470) loss: 0.8166 (0.8128) time: 0.1467 data: 0.0697 max mem: 9390 +Train: [88] [1600/6250] eta: 0:15:06 lr: 0.000005 grad: 0.1330 (0.1466) loss: 0.8166 (0.8130) time: 0.1610 data: 0.0779 max mem: 9390 +Train: [88] [1700/6250] eta: 0:14:39 lr: 0.000005 grad: 0.1291 (0.1460) loss: 0.8206 (0.8132) time: 0.1694 data: 0.0699 max mem: 9390 +Train: [88] [1800/6250] eta: 0:14:19 lr: 0.000005 grad: 0.1305 (0.1455) loss: 0.8164 (0.8135) time: 0.2439 data: 0.1348 max mem: 9390 +Train: [88] [1900/6250] eta: 0:13:55 lr: 0.000005 grad: 0.1347 (0.1453) loss: 0.8120 (0.8136) time: 0.2238 data: 0.1265 max mem: 9390 +Train: [88] [2000/6250] eta: 0:13:45 lr: 0.000005 grad: 0.1330 (0.1448) loss: 0.8131 (0.8137) time: 0.5424 data: 0.4688 max mem: 9390 +Train: [88] [2100/6250] eta: 0:13:15 lr: 0.000005 grad: 0.1375 (0.1445) loss: 0.8161 (0.8137) time: 0.1303 data: 0.0411 max mem: 9390 +Train: [88] [2200/6250] eta: 0:12:53 lr: 0.000005 grad: 0.1403 (0.1444) loss: 0.8117 (0.8138) time: 0.2162 data: 0.1363 max mem: 9390 +Train: [88] [2300/6250] eta: 0:12:28 lr: 0.000005 grad: 0.1320 (0.1441) loss: 0.8186 (0.8138) time: 0.1263 data: 0.0395 max mem: 9390 +Train: [88] [2400/6250] eta: 0:12:05 lr: 0.000005 grad: 0.1353 (0.1439) loss: 0.8168 (0.8137) time: 0.1257 data: 0.0464 max mem: 9390 +Train: [88] [2500/6250] eta: 0:11:42 lr: 0.000005 grad: 0.1358 (0.1438) loss: 0.8113 (0.8137) time: 0.1583 data: 0.0788 max mem: 9390 +Train: [88] [2600/6250] eta: 0:11:20 lr: 0.000005 grad: 0.1377 (0.1437) loss: 0.8105 (0.8137) time: 0.1616 data: 0.0759 max mem: 9390 +Train: [88] [2700/6250] eta: 0:11:01 lr: 0.000005 grad: 0.1409 (0.1436) loss: 0.8080 (0.8136) time: 0.1027 data: 0.0002 max mem: 9390 +Train: [88] [2800/6250] eta: 0:10:53 lr: 0.000005 grad: 0.1413 (0.1435) loss: 0.8110 (0.8135) time: 0.6462 data: 0.5566 max mem: 9390 +Train: [88] [2900/6250] eta: 0:10:29 lr: 0.000004 grad: 0.1355 (0.1434) loss: 0.8124 (0.8136) time: 0.2141 data: 0.1295 max mem: 9390 +Train: [88] [3000/6250] eta: 0:10:15 lr: 0.000004 grad: 0.1394 (0.1432) loss: 0.8103 (0.8136) time: 0.1849 data: 0.1062 max mem: 9390 +Train: [88] [3100/6250] eta: 0:09:58 lr: 0.000004 grad: 0.1362 (0.1431) loss: 0.8114 (0.8136) time: 0.3227 data: 0.2227 max mem: 9390 +Train: [88] [3200/6250] eta: 0:09:45 lr: 0.000004 grad: 0.1304 (0.1430) loss: 0.8123 (0.8137) time: 0.0881 data: 0.0002 max mem: 9390 +Train: [88] [3300/6250] eta: 0:09:25 lr: 0.000004 grad: 0.1418 (0.1430) loss: 0.8105 (0.8137) time: 0.1811 data: 0.0968 max mem: 9390 +Train: [88] [3400/6250] eta: 0:09:11 lr: 0.000004 grad: 0.1404 (0.1429) loss: 0.8090 (0.8136) time: 0.1912 data: 0.0930 max mem: 9390 +Train: [88] [3500/6250] eta: 0:08:49 lr: 0.000004 grad: 0.1408 (0.1427) loss: 0.8113 (0.8136) time: 0.1360 data: 0.0540 max mem: 9390 +Train: [88] [3600/6250] eta: 0:08:27 lr: 0.000004 grad: 0.1330 (0.1425) loss: 0.8181 (0.8137) time: 0.1781 data: 0.0771 max mem: 9390 +Train: [88] [3700/6250] eta: 0:08:14 lr: 0.000004 grad: 0.1292 (0.1422) loss: 0.8170 (0.8137) time: 0.3501 data: 0.2456 max mem: 9390 +Train: [88] [3800/6250] eta: 0:07:53 lr: 0.000004 grad: 0.1373 (0.1421) loss: 0.8180 (0.8137) time: 0.1768 data: 0.0746 max mem: 9390 +Train: [88] [3900/6250] eta: 0:07:32 lr: 0.000004 grad: 0.1297 (0.1420) loss: 0.8137 (0.8137) time: 0.1530 data: 0.0548 max mem: 9390 +Train: [88] [4000/6250] eta: 0:07:12 lr: 0.000004 grad: 0.1345 (0.1418) loss: 0.8170 (0.8138) time: 0.0961 data: 0.0002 max mem: 9390 +Train: [88] [4100/6250] eta: 0:06:52 lr: 0.000004 grad: 0.1336 (0.1417) loss: 0.8103 (0.8138) time: 0.0958 data: 0.0002 max mem: 9390 +Train: [88] [4200/6250] eta: 0:06:31 lr: 0.000004 grad: 0.1266 (0.1415) loss: 0.8156 (0.8139) time: 0.1459 data: 0.0590 max mem: 9390 +Train: [88] [4300/6250] eta: 0:06:12 lr: 0.000004 grad: 0.1395 (0.1414) loss: 0.8158 (0.8139) time: 0.1677 data: 0.0869 max mem: 9390 +Train: [88] [4400/6250] eta: 0:05:52 lr: 0.000004 grad: 0.1254 (0.1413) loss: 0.8212 (0.8140) time: 0.0884 data: 0.0019 max mem: 9390 +Train: [88] [4500/6250] eta: 0:05:32 lr: 0.000004 grad: 0.1326 (0.1411) loss: 0.8162 (0.8141) time: 0.3024 data: 0.2069 max mem: 9390 +Train: [88] [4600/6250] eta: 0:05:13 lr: 0.000004 grad: 0.1379 (0.1409) loss: 0.8167 (0.8142) time: 0.2192 data: 0.1283 max mem: 9390 +Train: [88] [4700/6250] eta: 0:04:55 lr: 0.000004 grad: 0.1321 (0.1408) loss: 0.8166 (0.8142) time: 0.1014 data: 0.0002 max mem: 9390 +Train: [88] [4800/6250] eta: 0:04:35 lr: 0.000004 grad: 0.1269 (0.1407) loss: 0.8146 (0.8143) time: 0.1714 data: 0.0952 max mem: 9390 +Train: [88] [4900/6250] eta: 0:04:17 lr: 0.000004 grad: 0.1328 (0.1406) loss: 0.8216 (0.8144) time: 0.4901 data: 0.3985 max mem: 9390 +Train: [88] [5000/6250] eta: 0:03:57 lr: 0.000004 grad: 0.1274 (0.1404) loss: 0.8195 (0.8145) time: 0.2715 data: 0.1870 max mem: 9390 +Train: [88] [5100/6250] eta: 0:03:37 lr: 0.000004 grad: 0.1244 (0.1403) loss: 0.8166 (0.8145) time: 0.1596 data: 0.0593 max mem: 9390 +Train: [88] [5200/6250] eta: 0:03:20 lr: 0.000004 grad: 0.1243 (0.1400) loss: 0.8171 (0.8146) time: 0.1793 data: 0.0878 max mem: 9390 +Train: [88] [5300/6250] eta: 0:03:00 lr: 0.000004 grad: 0.1292 (0.1399) loss: 0.8189 (0.8147) time: 0.1394 data: 0.0414 max mem: 9390 +Train: [88] [5400/6250] eta: 0:02:40 lr: 0.000004 grad: 0.1274 (0.1397) loss: 0.8164 (0.8147) time: 0.1619 data: 0.0623 max mem: 9390 +Train: [88] [5500/6250] eta: 0:02:21 lr: 0.000004 grad: 0.1261 (0.1395) loss: 0.8176 (0.8148) time: 0.2203 data: 0.1364 max mem: 9390 +Train: [88] [5600/6250] eta: 0:02:02 lr: 0.000004 grad: 0.1193 (0.1393) loss: 0.8173 (0.8148) time: 0.2252 data: 0.1509 max mem: 9390 +Train: [88] [5700/6250] eta: 0:01:43 lr: 0.000004 grad: 0.1208 (0.1392) loss: 0.8214 (0.8149) time: 0.1512 data: 0.0633 max mem: 9390 +Train: [88] [5800/6250] eta: 0:01:24 lr: 0.000004 grad: 0.1293 (0.1391) loss: 0.8143 (0.8150) time: 0.1904 data: 0.1095 max mem: 9390 +Train: [88] [5900/6250] eta: 0:01:05 lr: 0.000004 grad: 0.1318 (0.1391) loss: 0.8180 (0.8150) time: 0.1598 data: 0.0812 max mem: 9390 +Train: [88] [6000/6250] eta: 0:00:46 lr: 0.000004 grad: 0.1280 (0.1390) loss: 0.8172 (0.8151) time: 0.2870 data: 0.1939 max mem: 9390 +Train: [88] [6100/6250] eta: 0:00:28 lr: 0.000004 grad: 0.1325 (0.1390) loss: 0.8166 (0.8151) time: 0.1900 data: 0.1033 max mem: 9390 +Train: [88] [6200/6250] eta: 0:00:09 lr: 0.000004 grad: 0.1362 (0.1389) loss: 0.8120 (0.8151) time: 0.3719 data: 0.2769 max mem: 9390 +Train: [88] [6249/6250] eta: 0:00:00 lr: 0.000004 grad: 0.1386 (0.1389) loss: 0.8162 (0.8151) time: 0.2587 data: 0.1447 max mem: 9390 +Train: [88] Total time: 0:19:43 (0.1894 s / it) +Averaged stats: lr: 0.000004 grad: 0.1386 (0.1389) loss: 0.8162 (0.8151) +Eval (hcp-train-subset): [88] [ 0/62] eta: 0:04:22 loss: 0.8299 (0.8299) time: 4.2389 data: 4.1334 max mem: 9390 +Eval (hcp-train-subset): [88] [61/62] eta: 0:00:00 loss: 0.8156 (0.8195) time: 0.1210 data: 0.0941 max mem: 9390 +Eval (hcp-train-subset): [88] Total time: 0:00:15 (0.2439 s / it) +Averaged stats (hcp-train-subset): loss: 0.8156 (0.8195) +Eval (hcp-val): [88] [ 0/62] eta: 0:03:59 loss: 0.8250 (0.8250) time: 3.8616 data: 3.7997 max mem: 9390 +Eval (hcp-val): [88] [61/62] eta: 0:00:00 loss: 0.8269 (0.8287) time: 0.1594 data: 0.1343 max mem: 9390 +Eval (hcp-val): [88] Total time: 0:00:14 (0.2286 s / it) +Averaged stats (hcp-val): loss: 0.8269 (0.8287) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +Train: [89] [ 0/6250] eta: 11:33:14 lr: 0.000004 grad: 0.3378 (0.3378) loss: 0.8413 (0.8413) time: 6.6552 data: 6.5431 max mem: 9390 +Train: [89] [ 100/6250] eta: 0:24:57 lr: 0.000004 grad: 0.1405 (0.1648) loss: 0.8254 (0.8250) time: 0.2061 data: 0.1046 max mem: 9390 +Train: [89] [ 200/6250] eta: 0:20:51 lr: 0.000004 grad: 0.1467 (0.1608) loss: 0.8174 (0.8219) time: 0.1276 data: 0.0196 max mem: 9390 +Train: [89] [ 300/6250] eta: 0:19:38 lr: 0.000004 grad: 0.1370 (0.1568) loss: 0.8135 (0.8200) time: 0.2028 data: 0.0988 max mem: 9390 +Train: [89] [ 400/6250] eta: 0:18:37 lr: 0.000004 grad: 0.1400 (0.1538) loss: 0.8162 (0.8181) time: 0.1505 data: 0.0620 max mem: 9390 +Train: [89] [ 500/6250] eta: 0:17:48 lr: 0.000004 grad: 0.1504 (0.1524) loss: 0.8142 (0.8164) time: 0.1626 data: 0.0765 max mem: 9390 +Train: [89] [ 600/6250] eta: 0:17:08 lr: 0.000004 grad: 0.1450 (0.1517) loss: 0.8034 (0.8154) time: 0.1713 data: 0.0773 max mem: 9390 +Train: [89] [ 700/6250] eta: 0:16:35 lr: 0.000004 grad: 0.1432 (0.1511) loss: 0.8140 (0.8151) time: 0.1553 data: 0.0674 max mem: 9390 +Train: [89] [ 800/6250] eta: 0:16:21 lr: 0.000004 grad: 0.1355 (0.1502) loss: 0.8136 (0.8152) time: 0.1744 data: 0.0916 max mem: 9390 +Train: [89] [ 900/6250] eta: 0:16:25 lr: 0.000004 grad: 0.1450 (0.1493) loss: 0.8129 (0.8154) time: 0.1927 data: 0.1120 max mem: 9390 +Train: [89] [1000/6250] eta: 0:16:06 lr: 0.000004 grad: 0.1407 (0.1487) loss: 0.8149 (0.8153) time: 0.1978 data: 0.1220 max mem: 9390 +Train: [89] [1100/6250] eta: 0:15:46 lr: 0.000004 grad: 0.1344 (0.1483) loss: 0.8150 (0.8153) time: 0.2109 data: 0.1324 max mem: 9390 +Train: [89] [1200/6250] eta: 0:15:49 lr: 0.000004 grad: 0.1443 (0.1477) loss: 0.8137 (0.8151) time: 0.1738 data: 0.0832 max mem: 9390 +Train: [89] [1300/6250] eta: 0:15:31 lr: 0.000004 grad: 0.1344 (0.1472) loss: 0.8211 (0.8151) time: 0.1607 data: 0.0783 max mem: 9390 +Train: [89] [1400/6250] eta: 0:15:11 lr: 0.000004 grad: 0.1375 (0.1465) loss: 0.8158 (0.8152) time: 0.1923 data: 0.1146 max mem: 9390 +Train: [89] [1500/6250] eta: 0:14:56 lr: 0.000004 grad: 0.1301 (0.1461) loss: 0.8165 (0.8152) time: 0.2204 data: 0.1327 max mem: 9390 +Train: [89] [1600/6250] eta: 0:14:37 lr: 0.000004 grad: 0.1375 (0.1457) loss: 0.8143 (0.8152) time: 0.1679 data: 0.0846 max mem: 9390 +Train: [89] [1700/6250] eta: 0:14:18 lr: 0.000004 grad: 0.1305 (0.1454) loss: 0.8162 (0.8152) time: 0.1708 data: 0.0876 max mem: 9390 +Train: [89] [1800/6250] eta: 0:13:56 lr: 0.000004 grad: 0.1340 (0.1450) loss: 0.8168 (0.8153) time: 0.1607 data: 0.0668 max mem: 9390 +Train: [89] [1900/6250] eta: 0:13:31 lr: 0.000004 grad: 0.1361 (0.1448) loss: 0.8140 (0.8154) time: 0.1601 data: 0.0670 max mem: 9390 +Train: [89] [2000/6250] eta: 0:13:19 lr: 0.000004 grad: 0.1344 (0.1444) loss: 0.8101 (0.8154) time: 0.1974 data: 0.1046 max mem: 9390 +Train: [89] [2100/6250] eta: 0:13:04 lr: 0.000004 grad: 0.1359 (0.1442) loss: 0.8099 (0.8155) time: 0.1127 data: 0.0143 max mem: 9390 +Train: [89] [2200/6250] eta: 0:12:41 lr: 0.000004 grad: 0.1308 (0.1440) loss: 0.8203 (0.8154) time: 0.1685 data: 0.0814 max mem: 9390 +Train: [89] [2300/6250] eta: 0:12:16 lr: 0.000004 grad: 0.1289 (0.1436) loss: 0.8172 (0.8154) time: 0.1454 data: 0.0569 max mem: 9390 +Train: [89] [2400/6250] eta: 0:11:53 lr: 0.000004 grad: 0.1333 (0.1434) loss: 0.8203 (0.8154) time: 0.1856 data: 0.1058 max mem: 9390 +Train: [89] [2500/6250] eta: 0:11:30 lr: 0.000004 grad: 0.1329 (0.1431) loss: 0.8203 (0.8154) time: 0.1556 data: 0.0689 max mem: 9390 +Train: [89] [2600/6250] eta: 0:11:10 lr: 0.000004 grad: 0.1290 (0.1428) loss: 0.8191 (0.8155) time: 0.2025 data: 0.1208 max mem: 9390 +Train: [89] [2700/6250] eta: 0:10:49 lr: 0.000004 grad: 0.1348 (0.1425) loss: 0.8134 (0.8154) time: 0.1687 data: 0.0748 max mem: 9390 +Train: [89] [2800/6250] eta: 0:10:28 lr: 0.000004 grad: 0.1326 (0.1422) loss: 0.8159 (0.8155) time: 0.1664 data: 0.0822 max mem: 9390 +Train: [89] [2900/6250] eta: 0:10:08 lr: 0.000004 grad: 0.1336 (0.1419) loss: 0.8164 (0.8155) time: 0.1923 data: 0.1129 max mem: 9390 +Train: [89] [3000/6250] eta: 0:09:47 lr: 0.000004 grad: 0.1289 (0.1419) loss: 0.8141 (0.8155) time: 0.1606 data: 0.0724 max mem: 9390 +Train: [89] [3100/6250] eta: 0:09:27 lr: 0.000004 grad: 0.1321 (0.1418) loss: 0.8155 (0.8155) time: 0.1550 data: 0.0693 max mem: 9390 +Train: [89] [3200/6250] eta: 0:09:09 lr: 0.000004 grad: 0.1356 (0.1416) loss: 0.8101 (0.8154) time: 0.1751 data: 0.0852 max mem: 9390 +Train: [89] [3300/6250] eta: 0:08:48 lr: 0.000004 grad: 0.1272 (0.1416) loss: 0.8167 (0.8154) time: 0.1436 data: 0.0597 max mem: 9390 +Train: [89] [3400/6250] eta: 0:08:29 lr: 0.000004 grad: 0.1296 (0.1415) loss: 0.8143 (0.8153) time: 0.1317 data: 0.0421 max mem: 9390 +Train: [89] [3500/6250] eta: 0:08:10 lr: 0.000004 grad: 0.1350 (0.1414) loss: 0.8171 (0.8153) time: 0.1193 data: 0.0276 max mem: 9390 +Train: [89] [3600/6250] eta: 0:07:56 lr: 0.000004 grad: 0.1367 (0.1414) loss: 0.8178 (0.8152) time: 0.1745 data: 0.0809 max mem: 9390 +Train: [89] [3700/6250] eta: 0:07:38 lr: 0.000004 grad: 0.1260 (0.1413) loss: 0.8222 (0.8152) time: 0.1531 data: 0.0640 max mem: 9390 +Train: [89] [3800/6250] eta: 0:07:22 lr: 0.000004 grad: 0.1315 (0.1412) loss: 0.8158 (0.8152) time: 0.2586 data: 0.1629 max mem: 9390 +Train: [89] [3900/6250] eta: 0:07:04 lr: 0.000004 grad: 0.1275 (0.1411) loss: 0.8235 (0.8152) time: 0.1695 data: 0.0836 max mem: 9390 +Train: [89] [4000/6250] eta: 0:06:50 lr: 0.000004 grad: 0.1421 (0.1411) loss: 0.8208 (0.8152) time: 0.3923 data: 0.3067 max mem: 9390 +Train: [89] [4100/6250] eta: 0:06:36 lr: 0.000004 grad: 0.1346 (0.1411) loss: 0.8258 (0.8152) time: 0.1697 data: 0.0677 max mem: 9390 +Train: [89] [4200/6250] eta: 0:06:19 lr: 0.000004 grad: 0.1362 (0.1412) loss: 0.8148 (0.8153) time: 0.1097 data: 0.0002 max mem: 9390 +Train: [89] [4300/6250] eta: 0:06:03 lr: 0.000004 grad: 0.1319 (0.1412) loss: 0.8148 (0.8153) time: 0.1591 data: 0.0475 max mem: 9390 +Train: [89] [4400/6250] eta: 0:05:43 lr: 0.000004 grad: 0.1356 (0.1411) loss: 0.8180 (0.8154) time: 0.1722 data: 0.0873 max mem: 9390 +Train: [89] [4500/6250] eta: 0:05:24 lr: 0.000004 grad: 0.1300 (0.1410) loss: 0.8211 (0.8154) time: 0.1145 data: 0.0249 max mem: 9390 +Train: [89] [4600/6250] eta: 0:05:05 lr: 0.000004 grad: 0.1265 (0.1409) loss: 0.8171 (0.8155) time: 0.1584 data: 0.0468 max mem: 9390 +Train: [89] [4700/6250] eta: 0:04:47 lr: 0.000004 grad: 0.1381 (0.1409) loss: 0.8192 (0.8155) time: 0.1149 data: 0.0002 max mem: 9390 +Train: [89] [4800/6250] eta: 0:04:28 lr: 0.000004 grad: 0.1365 (0.1408) loss: 0.8205 (0.8155) time: 0.1791 data: 0.1001 max mem: 9390 +Train: [89] [4900/6250] eta: 0:04:09 lr: 0.000004 grad: 0.1357 (0.1409) loss: 0.8096 (0.8156) time: 0.1136 data: 0.0120 max mem: 9390 +Train: [89] [5000/6250] eta: 0:03:52 lr: 0.000004 grad: 0.1422 (0.1409) loss: 0.8112 (0.8155) time: 0.5505 data: 0.4540 max mem: 9390 +Train: [89] [5100/6250] eta: 0:03:33 lr: 0.000004 grad: 0.1332 (0.1409) loss: 0.8207 (0.8155) time: 0.1685 data: 0.0836 max mem: 9390 +Train: [89] [5200/6250] eta: 0:03:14 lr: 0.000003 grad: 0.1375 (0.1410) loss: 0.8146 (0.8155) time: 0.1688 data: 0.0679 max mem: 9390 +Train: [89] [5300/6250] eta: 0:02:55 lr: 0.000003 grad: 0.1505 (0.1411) loss: 0.8099 (0.8155) time: 0.1219 data: 0.0223 max mem: 9390 +Train: [89] [5400/6250] eta: 0:02:36 lr: 0.000003 grad: 0.1402 (0.1412) loss: 0.8043 (0.8154) time: 0.1688 data: 0.0720 max mem: 9390 +Train: [89] [5500/6250] eta: 0:02:18 lr: 0.000003 grad: 0.1408 (0.1412) loss: 0.8181 (0.8154) time: 0.1229 data: 0.0169 max mem: 9390 +Train: [89] [5600/6250] eta: 0:01:59 lr: 0.000003 grad: 0.1355 (0.1412) loss: 0.8216 (0.8155) time: 0.1962 data: 0.0925 max mem: 9390 +Train: [89] [5700/6250] eta: 0:01:41 lr: 0.000003 grad: 0.1369 (0.1412) loss: 0.8199 (0.8155) time: 0.2663 data: 0.1745 max mem: 9390 +Train: [89] [5800/6250] eta: 0:01:22 lr: 0.000003 grad: 0.1357 (0.1412) loss: 0.8173 (0.8155) time: 0.1572 data: 0.0774 max mem: 9390 +Train: [89] [5900/6250] eta: 0:01:04 lr: 0.000003 grad: 0.1433 (0.1411) loss: 0.8132 (0.8155) time: 0.1314 data: 0.0483 max mem: 9390 +Train: [89] [6000/6250] eta: 0:00:45 lr: 0.000003 grad: 0.1479 (0.1412) loss: 0.8205 (0.8155) time: 0.1329 data: 0.0389 max mem: 9390 +Train: [89] [6100/6250] eta: 0:00:27 lr: 0.000003 grad: 0.1374 (0.1412) loss: 0.8126 (0.8155) time: 0.1683 data: 0.0886 max mem: 9390 +Train: [89] [6200/6250] eta: 0:00:09 lr: 0.000003 grad: 0.1387 (0.1411) loss: 0.8139 (0.8156) time: 0.1394 data: 0.0360 max mem: 9390 +Train: [89] [6249/6250] eta: 0:00:00 lr: 0.000003 grad: 0.1383 (0.1412) loss: 0.8148 (0.8156) time: 0.1075 data: 0.0002 max mem: 9390 +Train: [89] Total time: 0:19:11 (0.1842 s / it) +Averaged stats: lr: 0.000003 grad: 0.1383 (0.1412) loss: 0.8148 (0.8156) +Eval (hcp-train-subset): [89] [ 0/62] eta: 0:05:41 loss: 0.8267 (0.8267) time: 5.5014 data: 5.4711 max mem: 9390 +Eval (hcp-train-subset): [89] [61/62] eta: 0:00:00 loss: 0.8153 (0.8180) time: 0.1078 data: 0.0829 max mem: 9390 +Eval (hcp-train-subset): [89] Total time: 0:00:13 (0.2170 s / it) +Averaged stats (hcp-train-subset): loss: 0.8153 (0.8180) +Making plots (hcp-train-subset): example=19 +Eval (hcp-val): [89] [ 0/62] eta: 0:03:26 loss: 0.8270 (0.8270) time: 3.3265 data: 3.2463 max mem: 9390 +Eval (hcp-val): [89] [61/62] eta: 0:00:00 loss: 0.8285 (0.8295) time: 0.1345 data: 0.1094 max mem: 9390 +Eval (hcp-val): [89] Total time: 0:00:13 (0.2178 s / it) +Averaged stats (hcp-val): loss: 0.8285 (0.8295) +Making plots (hcp-val): example=28 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +Train: [90] [ 0/6250] eta: 9:26:07 lr: 0.000003 grad: 0.3355 (0.3355) loss: 0.8085 (0.8085) time: 5.4348 data: 5.2387 max mem: 9390 +Train: [90] [ 100/6250] eta: 0:23:08 lr: 0.000003 grad: 0.1725 (0.1936) loss: 0.8075 (0.8052) time: 0.1708 data: 0.0628 max mem: 9390 +Train: [90] [ 200/6250] eta: 0:20:15 lr: 0.000003 grad: 0.1575 (0.1816) loss: 0.8015 (0.8049) time: 0.1829 data: 0.0871 max mem: 9390 +Train: [90] [ 300/6250] eta: 0:21:20 lr: 0.000003 grad: 0.1475 (0.1729) loss: 0.8157 (0.8066) time: 0.4063 data: 0.3173 max mem: 9390 +Train: [90] [ 400/6250] eta: 0:19:37 lr: 0.000003 grad: 0.1432 (0.1672) loss: 0.8173 (0.8082) time: 0.1434 data: 0.0233 max mem: 9390 +Train: [90] [ 500/6250] eta: 0:18:51 lr: 0.000003 grad: 0.1370 (0.1624) loss: 0.8166 (0.8096) time: 0.1289 data: 0.0457 max mem: 9390 +Train: [90] [ 600/6250] eta: 0:18:18 lr: 0.000003 grad: 0.1394 (0.1587) loss: 0.8203 (0.8112) time: 0.2168 data: 0.1308 max mem: 9390 +Train: [90] [ 700/6250] eta: 0:17:58 lr: 0.000003 grad: 0.1317 (0.1560) loss: 0.8241 (0.8123) time: 0.1808 data: 0.0690 max mem: 9390 +Train: [90] [ 800/6250] eta: 0:18:56 lr: 0.000003 grad: 0.1387 (0.1551) loss: 0.8161 (0.8126) time: 0.1712 data: 0.0774 max mem: 9390 +Train: [90] [ 900/6250] eta: 0:18:02 lr: 0.000003 grad: 0.1367 (0.1537) loss: 0.8169 (0.8129) time: 0.1605 data: 0.0731 max mem: 9390 +Train: [90] [1000/6250] eta: 0:17:22 lr: 0.000003 grad: 0.1372 (0.1521) loss: 0.8093 (0.8131) time: 0.1539 data: 0.0686 max mem: 9390 +Train: [90] [1100/6250] eta: 0:17:19 lr: 0.000003 grad: 0.1380 (0.1509) loss: 0.8109 (0.8132) time: 0.1478 data: 0.0630 max mem: 9390 +Train: [90] [1200/6250] eta: 0:16:38 lr: 0.000003 grad: 0.1457 (0.1500) loss: 0.8098 (0.8133) time: 0.1294 data: 0.0445 max mem: 9390 +Train: [90] [1300/6250] eta: 0:16:07 lr: 0.000003 grad: 0.1337 (0.1490) loss: 0.8146 (0.8134) time: 0.1778 data: 0.0888 max mem: 9390 +Train: [90] [1400/6250] eta: 0:15:52 lr: 0.000003 grad: 0.1338 (0.1483) loss: 0.8166 (0.8134) time: 0.3083 data: 0.2315 max mem: 9390 +Train: [90] [1500/6250] eta: 0:15:20 lr: 0.000003 grad: 0.1323 (0.1475) loss: 0.8189 (0.8136) time: 0.1694 data: 0.0924 max mem: 9390 +Train: [90] [1600/6250] eta: 0:14:51 lr: 0.000003 grad: 0.1333 (0.1471) loss: 0.8107 (0.8136) time: 0.1520 data: 0.0733 max mem: 9390 +Train: [90] [1700/6250] eta: 0:14:28 lr: 0.000003 grad: 0.1424 (0.1468) loss: 0.8116 (0.8136) time: 0.1394 data: 0.0565 max mem: 9390 +Train: [90] [1800/6250] eta: 0:14:04 lr: 0.000003 grad: 0.1398 (0.1465) loss: 0.8173 (0.8137) time: 0.1947 data: 0.1196 max mem: 9390 +Train: [90] [1900/6250] eta: 0:13:41 lr: 0.000003 grad: 0.1314 (0.1461) loss: 0.8116 (0.8139) time: 0.1014 data: 0.0088 max mem: 9390 +Train: [90] [2000/6250] eta: 0:13:17 lr: 0.000003 grad: 0.1370 (0.1458) loss: 0.8152 (0.8140) time: 0.1830 data: 0.1010 max mem: 9390 +Train: [90] [2100/6250] eta: 0:12:52 lr: 0.000003 grad: 0.1368 (0.1455) loss: 0.8212 (0.8141) time: 0.1512 data: 0.0535 max mem: 9390 +Train: [90] [2200/6250] eta: 0:12:32 lr: 0.000003 grad: 0.1387 (0.1454) loss: 0.8143 (0.8141) time: 0.0971 data: 0.0002 max mem: 9390 +Train: [90] [2300/6250] eta: 0:12:11 lr: 0.000003 grad: 0.1522 (0.1455) loss: 0.8048 (0.8140) time: 0.1633 data: 0.0749 max mem: 9390 +Train: [90] [2400/6250] eta: 0:11:52 lr: 0.000003 grad: 0.1376 (0.1455) loss: 0.8027 (0.8139) time: 0.1287 data: 0.0231 max mem: 9390 +Train: [90] [2500/6250] eta: 0:11:33 lr: 0.000003 grad: 0.1393 (0.1455) loss: 0.8136 (0.8138) time: 0.2006 data: 0.1021 max mem: 9390 +Train: [90] [2600/6250] eta: 0:11:13 lr: 0.000003 grad: 0.1458 (0.1454) loss: 0.8145 (0.8137) time: 0.1278 data: 0.0395 max mem: 9390 +Train: [90] [2700/6250] eta: 0:10:49 lr: 0.000003 grad: 0.1416 (0.1455) loss: 0.8153 (0.8136) time: 0.1481 data: 0.0601 max mem: 9390 +Train: [90] [2800/6250] eta: 0:10:28 lr: 0.000003 grad: 0.1356 (0.1457) loss: 0.8188 (0.8135) time: 0.2105 data: 0.1204 max mem: 9390 +Train: [90] [2900/6250] eta: 0:10:06 lr: 0.000003 grad: 0.1432 (0.1457) loss: 0.8099 (0.8135) time: 0.1264 data: 0.0415 max mem: 9390 +Train: [90] [3000/6250] eta: 0:09:47 lr: 0.000003 grad: 0.1386 (0.1458) loss: 0.8097 (0.8134) time: 0.1523 data: 0.0733 max mem: 9390 +Train: [90] [3100/6250] eta: 0:09:26 lr: 0.000003 grad: 0.1415 (0.1457) loss: 0.8167 (0.8133) time: 0.1634 data: 0.0850 max mem: 9390 +Train: [90] [3200/6250] eta: 0:09:06 lr: 0.000003 grad: 0.1452 (0.1458) loss: 0.8121 (0.8132) time: 0.1606 data: 0.0742 max mem: 9390 +Train: [90] [3300/6250] eta: 0:08:47 lr: 0.000003 grad: 0.1463 (0.1458) loss: 0.8142 (0.8132) time: 0.1692 data: 0.0889 max mem: 9390 +Train: [90] [3400/6250] eta: 0:08:28 lr: 0.000003 grad: 0.1421 (0.1458) loss: 0.8199 (0.8130) time: 0.1902 data: 0.0779 max mem: 9390 +Train: [90] [3500/6250] eta: 0:08:15 lr: 0.000003 grad: 0.1369 (0.1458) loss: 0.8131 (0.8130) time: 0.2355 data: 0.1481 max mem: 9390 +Train: [90] [3600/6250] eta: 0:07:56 lr: 0.000003 grad: 0.1307 (0.1457) loss: 0.8111 (0.8130) time: 0.1196 data: 0.0344 max mem: 9390 +Train: [90] [3700/6250] eta: 0:07:38 lr: 0.000003 grad: 0.1306 (0.1455) loss: 0.8134 (0.8130) time: 0.1438 data: 0.0581 max mem: 9390 +Train: [90] [3800/6250] eta: 0:07:21 lr: 0.000003 grad: 0.1388 (0.1454) loss: 0.8137 (0.8129) time: 0.2168 data: 0.1244 max mem: 9390 +Train: [90] [3900/6250] eta: 0:07:05 lr: 0.000003 grad: 0.1365 (0.1453) loss: 0.8121 (0.8129) time: 0.2129 data: 0.1218 max mem: 9390 +Train: [90] [4000/6250] eta: 0:06:47 lr: 0.000003 grad: 0.1388 (0.1453) loss: 0.8141 (0.8129) time: 0.1094 data: 0.0059 max mem: 9390 +Train: [90] [4100/6250] eta: 0:06:28 lr: 0.000003 grad: 0.1402 (0.1454) loss: 0.8132 (0.8129) time: 0.2091 data: 0.1199 max mem: 9390 +Train: [90] [4200/6250] eta: 0:06:11 lr: 0.000003 grad: 0.1350 (0.1453) loss: 0.8184 (0.8129) time: 0.1030 data: 0.0007 max mem: 9390 +Train: [90] [4300/6250] eta: 0:05:53 lr: 0.000003 grad: 0.1408 (0.1453) loss: 0.8140 (0.8129) time: 0.1545 data: 0.0554 max mem: 9390 +Train: [90] [4400/6250] eta: 0:05:34 lr: 0.000003 grad: 0.1406 (0.1452) loss: 0.8173 (0.8130) time: 0.1651 data: 0.0855 max mem: 9390 +Train: [90] [4500/6250] eta: 0:05:16 lr: 0.000003 grad: 0.1382 (0.1452) loss: 0.8145 (0.8130) time: 0.1048 data: 0.0003 max mem: 9390 +Train: [90] [4600/6250] eta: 0:04:58 lr: 0.000003 grad: 0.1408 (0.1451) loss: 0.8053 (0.8130) time: 0.1301 data: 0.0400 max mem: 9390 +Train: [90] [4700/6250] eta: 0:04:41 lr: 0.000003 grad: 0.1370 (0.1451) loss: 0.8181 (0.8130) time: 0.1509 data: 0.0613 max mem: 9390 +Train: [90] [4800/6250] eta: 0:04:22 lr: 0.000003 grad: 0.1397 (0.1451) loss: 0.8085 (0.8129) time: 0.1299 data: 0.0460 max mem: 9390 +Train: [90] [4900/6250] eta: 0:04:04 lr: 0.000003 grad: 0.1521 (0.1450) loss: 0.8090 (0.8129) time: 0.1552 data: 0.0782 max mem: 9390 +Train: [90] [5000/6250] eta: 0:03:45 lr: 0.000003 grad: 0.1357 (0.1450) loss: 0.8148 (0.8129) time: 0.1698 data: 0.0865 max mem: 9390 +Train: [90] [5100/6250] eta: 0:03:27 lr: 0.000003 grad: 0.1312 (0.1450) loss: 0.8154 (0.8129) time: 0.2198 data: 0.1372 max mem: 9390 +Train: [90] [5200/6250] eta: 0:03:09 lr: 0.000003 grad: 0.1304 (0.1450) loss: 0.8109 (0.8129) time: 0.2130 data: 0.1255 max mem: 9390 +Train: [90] [5300/6250] eta: 0:02:51 lr: 0.000003 grad: 0.1441 (0.1451) loss: 0.8154 (0.8129) time: 0.1892 data: 0.1008 max mem: 9390 +Train: [90] [5400/6250] eta: 0:02:33 lr: 0.000003 grad: 0.1369 (0.1451) loss: 0.8146 (0.8129) time: 0.1357 data: 0.0422 max mem: 9390 +Train: [90] [5500/6250] eta: 0:02:15 lr: 0.000003 grad: 0.1345 (0.1451) loss: 0.8131 (0.8129) time: 0.1663 data: 0.0818 max mem: 9390 +Train: [90] [5600/6250] eta: 0:01:58 lr: 0.000003 grad: 0.1468 (0.1451) loss: 0.8112 (0.8129) time: 0.0939 data: 0.0034 max mem: 9390 +Train: [90] [5700/6250] eta: 0:01:40 lr: 0.000003 grad: 0.1360 (0.1451) loss: 0.8170 (0.8129) time: 0.1563 data: 0.0654 max mem: 9390 +Train: [90] [5800/6250] eta: 0:01:21 lr: 0.000003 grad: 0.1267 (0.1450) loss: 0.8188 (0.8129) time: 0.1530 data: 0.0588 max mem: 9390 +Train: [90] [5900/6250] eta: 0:01:03 lr: 0.000003 grad: 0.1376 (0.1449) loss: 0.8135 (0.8129) time: 0.0899 data: 0.0002 max mem: 9390 +Train: [90] [6000/6250] eta: 0:00:45 lr: 0.000003 grad: 0.1388 (0.1449) loss: 0.8048 (0.8129) time: 0.1866 data: 0.0899 max mem: 9390 +Train: [90] [6100/6250] eta: 0:00:27 lr: 0.000003 grad: 0.1403 (0.1448) loss: 0.8121 (0.8129) time: 0.1494 data: 0.0451 max mem: 9390 +Train: [90] [6200/6250] eta: 0:00:09 lr: 0.000003 grad: 0.1468 (0.1448) loss: 0.8067 (0.8129) time: 0.0873 data: 0.0017 max mem: 9390 +Train: [90] [6249/6250] eta: 0:00:00 lr: 0.000003 grad: 0.1437 (0.1448) loss: 0.8137 (0.8129) time: 0.1265 data: 0.0281 max mem: 9390 +Train: [90] Total time: 0:18:57 (0.1820 s / it) +Averaged stats: lr: 0.000003 grad: 0.1437 (0.1448) loss: 0.8137 (0.8129) +Eval (hcp-train-subset): [90] [ 0/62] eta: 0:03:52 loss: 0.8291 (0.8291) time: 3.7497 data: 3.6826 max mem: 9390 +Eval (hcp-train-subset): [90] [61/62] eta: 0:00:00 loss: 0.8131 (0.8180) time: 0.1169 data: 0.0905 max mem: 9390 +Eval (hcp-train-subset): [90] Total time: 0:00:14 (0.2286 s / it) +Averaged stats (hcp-train-subset): loss: 0.8131 (0.8180) +Eval (hcp-val): [90] [ 0/62] eta: 0:04:07 loss: 0.8261 (0.8261) time: 3.9948 data: 3.9319 max mem: 9390 +Eval (hcp-val): [90] [61/62] eta: 0:00:00 loss: 0.8270 (0.8285) time: 0.1309 data: 0.1060 max mem: 9390 +Eval (hcp-val): [90] Total time: 0:00:13 (0.2202 s / it) +Averaged stats (hcp-val): loss: 0.8270 (0.8285) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +Train: [91] [ 0/6250] eta: 8:37:55 lr: 0.000003 grad: 0.0943 (0.0943) loss: 0.8500 (0.8500) time: 4.9721 data: 4.7245 max mem: 9390 +Train: [91] [ 100/6250] eta: 0:23:23 lr: 0.000003 grad: 0.1441 (0.1615) loss: 0.8206 (0.8234) time: 0.1660 data: 0.0695 max mem: 9390 +Train: [91] [ 200/6250] eta: 0:20:12 lr: 0.000003 grad: 0.1535 (0.1613) loss: 0.8037 (0.8167) time: 0.1662 data: 0.0633 max mem: 9390 +Train: [91] [ 300/6250] eta: 0:18:44 lr: 0.000003 grad: 0.1324 (0.1574) loss: 0.8137 (0.8157) time: 0.1576 data: 0.0678 max mem: 9390 +Train: [91] [ 400/6250] eta: 0:17:43 lr: 0.000003 grad: 0.1494 (0.1560) loss: 0.8154 (0.8147) time: 0.1724 data: 0.0702 max mem: 9390 +Train: [91] [ 500/6250] eta: 0:17:54 lr: 0.000003 grad: 0.1434 (0.1547) loss: 0.8122 (0.8142) time: 0.1398 data: 0.0417 max mem: 9390 +Train: [91] [ 600/6250] eta: 0:17:21 lr: 0.000003 grad: 0.1365 (0.1531) loss: 0.8118 (0.8141) time: 0.1465 data: 0.0632 max mem: 9390 +Train: [91] [ 700/6250] eta: 0:16:43 lr: 0.000003 grad: 0.1385 (0.1526) loss: 0.8203 (0.8137) time: 0.1703 data: 0.0876 max mem: 9390 +Train: [91] [ 800/6250] eta: 0:16:59 lr: 0.000003 grad: 0.1386 (0.1511) loss: 0.8117 (0.8139) time: 0.1868 data: 0.1101 max mem: 9390 +Train: [91] [ 900/6250] eta: 0:16:45 lr: 0.000003 grad: 0.1360 (0.1499) loss: 0.8148 (0.8140) time: 0.2286 data: 0.1275 max mem: 9390 +Train: [91] [1000/6250] eta: 0:16:29 lr: 0.000003 grad: 0.1389 (0.1492) loss: 0.8178 (0.8141) time: 0.1205 data: 0.0320 max mem: 9390 +Train: [91] [1100/6250] eta: 0:16:00 lr: 0.000003 grad: 0.1417 (0.1484) loss: 0.8094 (0.8142) time: 0.1517 data: 0.0744 max mem: 9390 +Train: [91] [1200/6250] eta: 0:15:29 lr: 0.000003 grad: 0.1368 (0.1476) loss: 0.8156 (0.8144) time: 0.1656 data: 0.0863 max mem: 9390 +Train: [91] [1300/6250] eta: 0:15:10 lr: 0.000003 grad: 0.1399 (0.1473) loss: 0.8118 (0.8143) time: 0.1317 data: 0.0003 max mem: 9390 +Train: [91] [1400/6250] eta: 0:14:48 lr: 0.000003 grad: 0.1315 (0.1468) loss: 0.8173 (0.8144) time: 0.1007 data: 0.0004 max mem: 9390 +Train: [91] [1500/6250] eta: 0:14:22 lr: 0.000003 grad: 0.1488 (0.1469) loss: 0.8139 (0.8143) time: 0.1808 data: 0.1034 max mem: 9390 +Train: [91] [1600/6250] eta: 0:13:58 lr: 0.000003 grad: 0.1436 (0.1466) loss: 0.8150 (0.8143) time: 0.1407 data: 0.0565 max mem: 9390 +Train: [91] [1700/6250] eta: 0:13:37 lr: 0.000003 grad: 0.1419 (0.1464) loss: 0.8152 (0.8143) time: 0.1553 data: 0.0720 max mem: 9390 +Train: [91] [1800/6250] eta: 0:13:21 lr: 0.000003 grad: 0.1351 (0.1462) loss: 0.8237 (0.8143) time: 0.1683 data: 0.0909 max mem: 9390 +Train: [91] [1900/6250] eta: 0:13:00 lr: 0.000003 grad: 0.1444 (0.1460) loss: 0.8154 (0.8142) time: 0.1645 data: 0.0832 max mem: 9390 +Train: [91] [2000/6250] eta: 0:12:39 lr: 0.000003 grad: 0.1307 (0.1457) loss: 0.8145 (0.8141) time: 0.1706 data: 0.0885 max mem: 9390 +Train: [91] [2100/6250] eta: 0:12:19 lr: 0.000003 grad: 0.1347 (0.1455) loss: 0.8160 (0.8141) time: 0.1245 data: 0.0354 max mem: 9390 +Train: [91] [2200/6250] eta: 0:12:04 lr: 0.000003 grad: 0.1348 (0.1455) loss: 0.8090 (0.8140) time: 0.1010 data: 0.0030 max mem: 9390 +Train: [91] [2300/6250] eta: 0:11:43 lr: 0.000003 grad: 0.1429 (0.1454) loss: 0.8082 (0.8139) time: 0.1651 data: 0.0819 max mem: 9390 +Train: [91] [2400/6250] eta: 0:11:25 lr: 0.000003 grad: 0.1320 (0.1452) loss: 0.8134 (0.8138) time: 0.1621 data: 0.0818 max mem: 9390 +Train: [91] [2500/6250] eta: 0:11:04 lr: 0.000003 grad: 0.1469 (0.1450) loss: 0.8094 (0.8137) time: 0.1177 data: 0.0392 max mem: 9390 +Train: [91] [2600/6250] eta: 0:10:45 lr: 0.000003 grad: 0.1334 (0.1449) loss: 0.8112 (0.8136) time: 0.1733 data: 0.0915 max mem: 9390 +Train: [91] [2700/6250] eta: 0:10:33 lr: 0.000002 grad: 0.1340 (0.1448) loss: 0.8072 (0.8135) time: 0.2816 data: 0.1952 max mem: 9390 +Train: [91] [2800/6250] eta: 0:10:11 lr: 0.000002 grad: 0.1374 (0.1448) loss: 0.8106 (0.8134) time: 0.1698 data: 0.0757 max mem: 9390 +Train: [91] [2900/6250] eta: 0:09:51 lr: 0.000002 grad: 0.1437 (0.1449) loss: 0.8103 (0.8134) time: 0.1711 data: 0.0859 max mem: 9390 +Train: [91] [3000/6250] eta: 0:09:32 lr: 0.000002 grad: 0.1383 (0.1448) loss: 0.8092 (0.8133) time: 0.1577 data: 0.0781 max mem: 9390 +Train: [91] [3100/6250] eta: 0:09:13 lr: 0.000002 grad: 0.1443 (0.1448) loss: 0.8080 (0.8132) time: 0.1948 data: 0.1133 max mem: 9390 +Train: [91] [3200/6250] eta: 0:08:53 lr: 0.000002 grad: 0.1373 (0.1447) loss: 0.8138 (0.8133) time: 0.1833 data: 0.0920 max mem: 9390 +Train: [91] [3300/6250] eta: 0:08:36 lr: 0.000002 grad: 0.1434 (0.1446) loss: 0.8138 (0.8133) time: 0.1767 data: 0.1004 max mem: 9390 +Train: [91] [3400/6250] eta: 0:08:17 lr: 0.000002 grad: 0.1372 (0.1447) loss: 0.8114 (0.8133) time: 0.1521 data: 0.0680 max mem: 9390 +Train: [91] [3500/6250] eta: 0:07:58 lr: 0.000002 grad: 0.1349 (0.1446) loss: 0.8154 (0.8133) time: 0.1539 data: 0.0665 max mem: 9390 +Train: [91] [3600/6250] eta: 0:07:40 lr: 0.000002 grad: 0.1409 (0.1447) loss: 0.8128 (0.8132) time: 0.2150 data: 0.1387 max mem: 9390 +Train: [91] [3700/6250] eta: 0:07:21 lr: 0.000002 grad: 0.1419 (0.1447) loss: 0.8154 (0.8132) time: 0.1360 data: 0.0438 max mem: 9390 +Train: [91] [3800/6250] eta: 0:07:03 lr: 0.000002 grad: 0.1351 (0.1447) loss: 0.8172 (0.8132) time: 0.1619 data: 0.0704 max mem: 9390 +Train: [91] [3900/6250] eta: 0:06:47 lr: 0.000002 grad: 0.1383 (0.1448) loss: 0.8099 (0.8132) time: 0.1727 data: 0.0823 max mem: 9390 +Train: [91] [4000/6250] eta: 0:06:30 lr: 0.000002 grad: 0.1328 (0.1449) loss: 0.8208 (0.8131) time: 0.1996 data: 0.1227 max mem: 9390 +Train: [91] [4100/6250] eta: 0:06:12 lr: 0.000002 grad: 0.1405 (0.1449) loss: 0.8066 (0.8131) time: 0.1169 data: 0.0268 max mem: 9390 +Train: [91] [4200/6250] eta: 0:05:55 lr: 0.000002 grad: 0.1334 (0.1449) loss: 0.8177 (0.8131) time: 0.1792 data: 0.0665 max mem: 9390 +Train: [91] [4300/6250] eta: 0:05:38 lr: 0.000002 grad: 0.1342 (0.1448) loss: 0.8160 (0.8131) time: 0.1734 data: 0.0809 max mem: 9390 +Train: [91] [4400/6250] eta: 0:05:23 lr: 0.000002 grad: 0.1390 (0.1447) loss: 0.8074 (0.8131) time: 0.4368 data: 0.3456 max mem: 9390 +Train: [91] [4500/6250] eta: 0:05:04 lr: 0.000002 grad: 0.1369 (0.1447) loss: 0.8127 (0.8131) time: 0.1543 data: 0.0718 max mem: 9390 +Train: [91] [4600/6250] eta: 0:04:47 lr: 0.000002 grad: 0.1398 (0.1446) loss: 0.8118 (0.8130) time: 0.1929 data: 0.0941 max mem: 9390 +Train: [91] [4700/6250] eta: 0:04:30 lr: 0.000002 grad: 0.1420 (0.1446) loss: 0.8194 (0.8130) time: 0.2168 data: 0.1273 max mem: 9390 +Train: [91] [4800/6250] eta: 0:04:12 lr: 0.000002 grad: 0.1320 (0.1447) loss: 0.8183 (0.8129) time: 0.1830 data: 0.0872 max mem: 9390 +Train: [91] [4900/6250] eta: 0:03:55 lr: 0.000002 grad: 0.1367 (0.1448) loss: 0.8075 (0.8129) time: 0.1672 data: 0.0791 max mem: 9390 +Train: [91] [5000/6250] eta: 0:03:37 lr: 0.000002 grad: 0.1319 (0.1449) loss: 0.8155 (0.8128) time: 0.1767 data: 0.0868 max mem: 9390 +Train: [91] [5100/6250] eta: 0:03:19 lr: 0.000002 grad: 0.1409 (0.1449) loss: 0.8124 (0.8128) time: 0.1177 data: 0.0233 max mem: 9390 +Train: [91] [5200/6250] eta: 0:03:02 lr: 0.000002 grad: 0.1453 (0.1449) loss: 0.8117 (0.8127) time: 0.1322 data: 0.0061 max mem: 9390 +Train: [91] [5300/6250] eta: 0:02:45 lr: 0.000002 grad: 0.1452 (0.1449) loss: 0.8063 (0.8127) time: 0.1193 data: 0.0189 max mem: 9390 +Train: [91] [5400/6250] eta: 0:02:28 lr: 0.000002 grad: 0.1388 (0.1449) loss: 0.8169 (0.8128) time: 0.2028 data: 0.1153 max mem: 9390 +Train: [91] [5500/6250] eta: 0:02:11 lr: 0.000002 grad: 0.1346 (0.1449) loss: 0.8171 (0.8128) time: 0.2814 data: 0.1825 max mem: 9390 +Train: [91] [5600/6250] eta: 0:01:53 lr: 0.000002 grad: 0.1322 (0.1448) loss: 0.8120 (0.8128) time: 0.1683 data: 0.0807 max mem: 9390 +Train: [91] [5700/6250] eta: 0:01:36 lr: 0.000002 grad: 0.1403 (0.1449) loss: 0.8151 (0.8128) time: 0.1477 data: 0.0626 max mem: 9390 +Train: [91] [5800/6250] eta: 0:01:19 lr: 0.000002 grad: 0.1355 (0.1449) loss: 0.8190 (0.8128) time: 0.4357 data: 0.3247 max mem: 9390 +Train: [91] [5900/6250] eta: 0:01:01 lr: 0.000002 grad: 0.1360 (0.1449) loss: 0.8169 (0.8128) time: 0.1834 data: 0.1029 max mem: 9390 +Train: [91] [6000/6250] eta: 0:00:44 lr: 0.000002 grad: 0.1370 (0.1449) loss: 0.8128 (0.8128) time: 0.1511 data: 0.0639 max mem: 9390 +Train: [91] [6100/6250] eta: 0:00:26 lr: 0.000002 grad: 0.1407 (0.1448) loss: 0.8162 (0.8128) time: 0.3318 data: 0.2291 max mem: 9390 +Train: [91] [6200/6250] eta: 0:00:08 lr: 0.000002 grad: 0.1365 (0.1448) loss: 0.8161 (0.8128) time: 0.1883 data: 0.1045 max mem: 9390 +Train: [91] [6249/6250] eta: 0:00:00 lr: 0.000002 grad: 0.1442 (0.1448) loss: 0.8084 (0.8128) time: 0.3176 data: 0.2058 max mem: 9390 +Train: [91] Total time: 0:18:31 (0.1778 s / it) +Averaged stats: lr: 0.000002 grad: 0.1442 (0.1448) loss: 0.8084 (0.8128) +Eval (hcp-train-subset): [91] [ 0/62] eta: 0:03:21 loss: 0.8276 (0.8276) time: 3.2510 data: 3.1671 max mem: 9390 +Eval (hcp-train-subset): [91] [61/62] eta: 0:00:00 loss: 0.8149 (0.8180) time: 0.1270 data: 0.1022 max mem: 9390 +Eval (hcp-train-subset): [91] Total time: 0:00:13 (0.2133 s / it) +Averaged stats (hcp-train-subset): loss: 0.8149 (0.8180) +Eval (hcp-val): [91] [ 0/62] eta: 0:04:20 loss: 0.8232 (0.8232) time: 4.2053 data: 4.1203 max mem: 9390 +Eval (hcp-val): [91] [61/62] eta: 0:00:00 loss: 0.8264 (0.8280) time: 0.1289 data: 0.1041 max mem: 9390 +Eval (hcp-val): [91] Total time: 0:00:13 (0.2210 s / it) +Averaged stats (hcp-val): loss: 0.8264 (0.8280) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +Train: [92] [ 0/6250] eta: 10:10:21 lr: 0.000002 grad: 0.3798 (0.3798) loss: 0.7451 (0.7451) time: 5.8594 data: 5.7010 max mem: 9390 +Train: [92] [ 100/6250] eta: 0:24:05 lr: 0.000002 grad: 0.1790 (0.2204) loss: 0.8049 (0.8071) time: 0.1903 data: 0.0940 max mem: 9390 +Train: [92] [ 200/6250] eta: 0:20:47 lr: 0.000002 grad: 0.1636 (0.2011) loss: 0.8008 (0.8046) time: 0.1757 data: 0.0767 max mem: 9390 +Train: [92] [ 300/6250] eta: 0:19:52 lr: 0.000002 grad: 0.1391 (0.1874) loss: 0.8152 (0.8050) time: 0.2206 data: 0.1261 max mem: 9390 +Train: [92] [ 400/6250] eta: 0:22:11 lr: 0.000002 grad: 0.1411 (0.1795) loss: 0.8116 (0.8055) time: 0.0930 data: 0.0003 max mem: 9390 +Train: [92] [ 500/6250] eta: 0:21:35 lr: 0.000002 grad: 0.1293 (0.1733) loss: 0.8173 (0.8063) time: 0.2365 data: 0.1400 max mem: 9390 +Train: [92] [ 600/6250] eta: 0:20:30 lr: 0.000002 grad: 0.1328 (0.1683) loss: 0.8123 (0.8071) time: 0.2704 data: 0.1713 max mem: 9390 +Train: [92] [ 700/6250] eta: 0:19:17 lr: 0.000002 grad: 0.1448 (0.1655) loss: 0.8095 (0.8075) time: 0.1622 data: 0.0756 max mem: 9390 +Train: [92] [ 800/6250] eta: 0:19:16 lr: 0.000002 grad: 0.1469 (0.1634) loss: 0.8156 (0.8080) time: 0.1556 data: 0.0630 max mem: 9390 +Train: [92] [ 900/6250] eta: 0:18:36 lr: 0.000002 grad: 0.1378 (0.1616) loss: 0.8158 (0.8084) time: 0.1619 data: 0.0591 max mem: 9390 +Train: [92] [1000/6250] eta: 0:17:55 lr: 0.000002 grad: 0.1494 (0.1600) loss: 0.8077 (0.8086) time: 0.1971 data: 0.1129 max mem: 9390 +Train: [92] [1100/6250] eta: 0:17:25 lr: 0.000002 grad: 0.1469 (0.1588) loss: 0.8074 (0.8087) time: 0.1066 data: 0.0007 max mem: 9390 +Train: [92] [1200/6250] eta: 0:17:42 lr: 0.000002 grad: 0.1504 (0.1579) loss: 0.8081 (0.8089) time: 0.6032 data: 0.5094 max mem: 9390 +Train: [92] [1300/6250] eta: 0:17:00 lr: 0.000002 grad: 0.1432 (0.1568) loss: 0.8107 (0.8091) time: 0.0896 data: 0.0002 max mem: 9390 +Train: [92] [1400/6250] eta: 0:16:39 lr: 0.000002 grad: 0.1590 (0.1562) loss: 0.8060 (0.8092) time: 0.1766 data: 0.0765 max mem: 9390 +Train: [92] [1500/6250] eta: 0:16:10 lr: 0.000002 grad: 0.1487 (0.1555) loss: 0.8135 (0.8094) time: 0.1131 data: 0.0003 max mem: 9390 +Train: [92] [1600/6250] eta: 0:15:53 lr: 0.000002 grad: 0.1400 (0.1551) loss: 0.8091 (0.8096) time: 0.3379 data: 0.2534 max mem: 9390 +Train: [92] [1700/6250] eta: 0:15:13 lr: 0.000002 grad: 0.1406 (0.1543) loss: 0.8148 (0.8099) time: 0.1615 data: 0.0834 max mem: 9390 +Train: [92] [1800/6250] eta: 0:14:44 lr: 0.000002 grad: 0.1472 (0.1537) loss: 0.8128 (0.8101) time: 0.1058 data: 0.0197 max mem: 9390 +Train: [92] [1900/6250] eta: 0:14:16 lr: 0.000002 grad: 0.1495 (0.1536) loss: 0.8178 (0.8103) time: 0.1555 data: 0.0683 max mem: 9390 +Train: [92] [2000/6250] eta: 0:13:52 lr: 0.000002 grad: 0.1361 (0.1533) loss: 0.8117 (0.8104) time: 0.1664 data: 0.0827 max mem: 9390 +Train: [92] [2100/6250] eta: 0:13:31 lr: 0.000002 grad: 0.1470 (0.1529) loss: 0.8149 (0.8106) time: 0.2043 data: 0.1213 max mem: 9390 +Train: [92] [2200/6250] eta: 0:13:05 lr: 0.000002 grad: 0.1526 (0.1525) loss: 0.8126 (0.8107) time: 0.1018 data: 0.0156 max mem: 9390 +Train: [92] [2300/6250] eta: 0:12:39 lr: 0.000002 grad: 0.1416 (0.1521) loss: 0.8145 (0.8109) time: 0.1564 data: 0.0728 max mem: 9390 +Train: [92] [2400/6250] eta: 0:12:17 lr: 0.000002 grad: 0.1515 (0.1518) loss: 0.8170 (0.8110) time: 0.1442 data: 0.0565 max mem: 9390 +Train: [92] [2500/6250] eta: 0:11:54 lr: 0.000002 grad: 0.1326 (0.1515) loss: 0.8184 (0.8113) time: 0.1875 data: 0.1103 max mem: 9390 +Train: [92] [2600/6250] eta: 0:11:31 lr: 0.000002 grad: 0.1381 (0.1512) loss: 0.8173 (0.8114) time: 0.1509 data: 0.0616 max mem: 9390 +Train: [92] [2700/6250] eta: 0:11:09 lr: 0.000002 grad: 0.1325 (0.1510) loss: 0.8163 (0.8116) time: 0.1678 data: 0.0908 max mem: 9390 +Train: [92] [2800/6250] eta: 0:10:48 lr: 0.000002 grad: 0.1428 (0.1507) loss: 0.8118 (0.8117) time: 0.2134 data: 0.1285 max mem: 9390 +Train: [92] [2900/6250] eta: 0:10:24 lr: 0.000002 grad: 0.1355 (0.1504) loss: 0.8084 (0.8118) time: 0.1494 data: 0.0672 max mem: 9390 +Train: [92] [3000/6250] eta: 0:10:04 lr: 0.000002 grad: 0.1395 (0.1501) loss: 0.8160 (0.8119) time: 0.1723 data: 0.0850 max mem: 9390 +Train: [92] [3100/6250] eta: 0:09:50 lr: 0.000002 grad: 0.1362 (0.1500) loss: 0.8196 (0.8119) time: 0.1454 data: 0.0405 max mem: 9390 +Train: [92] [3200/6250] eta: 0:09:33 lr: 0.000002 grad: 0.1372 (0.1499) loss: 0.8176 (0.8120) time: 0.1877 data: 0.0999 max mem: 9390 +Train: [92] [3300/6250] eta: 0:09:12 lr: 0.000002 grad: 0.1427 (0.1498) loss: 0.8097 (0.8121) time: 0.1391 data: 0.0529 max mem: 9390 +Train: [92] [3400/6250] eta: 0:08:51 lr: 0.000002 grad: 0.1490 (0.1500) loss: 0.8147 (0.8121) time: 0.1710 data: 0.0801 max mem: 9390 +Train: [92] [3500/6250] eta: 0:08:30 lr: 0.000002 grad: 0.1451 (0.1500) loss: 0.8132 (0.8122) time: 0.1431 data: 0.0492 max mem: 9390 +Train: [92] [3600/6250] eta: 0:08:09 lr: 0.000002 grad: 0.1408 (0.1499) loss: 0.8211 (0.8122) time: 0.1772 data: 0.0964 max mem: 9390 +Train: [92] [3700/6250] eta: 0:07:48 lr: 0.000002 grad: 0.1494 (0.1499) loss: 0.8121 (0.8122) time: 0.1322 data: 0.0506 max mem: 9390 +Train: [92] [3800/6250] eta: 0:07:28 lr: 0.000002 grad: 0.1549 (0.1500) loss: 0.8064 (0.8122) time: 0.1486 data: 0.0670 max mem: 9390 +Train: [92] [3900/6250] eta: 0:07:08 lr: 0.000002 grad: 0.1441 (0.1499) loss: 0.8109 (0.8122) time: 0.1535 data: 0.0675 max mem: 9390 +Train: [92] [4000/6250] eta: 0:06:48 lr: 0.000002 grad: 0.1418 (0.1498) loss: 0.8153 (0.8122) time: 0.1621 data: 0.0833 max mem: 9390 +Train: [92] [4100/6250] eta: 0:06:31 lr: 0.000002 grad: 0.1463 (0.1497) loss: 0.8104 (0.8123) time: 0.2009 data: 0.1157 max mem: 9390 +Train: [92] [4200/6250] eta: 0:06:12 lr: 0.000002 grad: 0.1418 (0.1496) loss: 0.8130 (0.8123) time: 0.1632 data: 0.0823 max mem: 9390 +Train: [92] [4300/6250] eta: 0:05:55 lr: 0.000002 grad: 0.1399 (0.1495) loss: 0.8145 (0.8123) time: 0.2404 data: 0.1632 max mem: 9390 +Train: [92] [4400/6250] eta: 0:05:36 lr: 0.000002 grad: 0.1395 (0.1493) loss: 0.8180 (0.8123) time: 0.1735 data: 0.0922 max mem: 9390 +Train: [92] [4500/6250] eta: 0:05:24 lr: 0.000002 grad: 0.1432 (0.1492) loss: 0.8122 (0.8124) time: 0.1654 data: 0.0805 max mem: 9390 +Train: [92] [4600/6250] eta: 0:05:06 lr: 0.000002 grad: 0.1388 (0.1491) loss: 0.8187 (0.8124) time: 0.1515 data: 0.0639 max mem: 9390 +Train: [92] [4700/6250] eta: 0:04:48 lr: 0.000002 grad: 0.1331 (0.1489) loss: 0.8153 (0.8125) time: 0.1715 data: 0.0845 max mem: 9390 +Train: [92] [4800/6250] eta: 0:04:29 lr: 0.000002 grad: 0.1376 (0.1488) loss: 0.8166 (0.8126) time: 0.1397 data: 0.0473 max mem: 9390 +Train: [92] [4900/6250] eta: 0:04:10 lr: 0.000002 grad: 0.1441 (0.1487) loss: 0.8105 (0.8126) time: 0.2394 data: 0.1523 max mem: 9390 +Train: [92] [5000/6250] eta: 0:03:51 lr: 0.000002 grad: 0.1475 (0.1486) loss: 0.8068 (0.8127) time: 0.1417 data: 0.0357 max mem: 9390 +Train: [92] [5100/6250] eta: 0:03:33 lr: 0.000002 grad: 0.1328 (0.1485) loss: 0.8199 (0.8127) time: 0.0898 data: 0.0002 max mem: 9390 +Train: [92] [5200/6250] eta: 0:03:13 lr: 0.000002 grad: 0.1417 (0.1484) loss: 0.8134 (0.8127) time: 0.1770 data: 0.0989 max mem: 9390 +Train: [92] [5300/6250] eta: 0:02:55 lr: 0.000002 grad: 0.1549 (0.1484) loss: 0.8080 (0.8127) time: 0.0893 data: 0.0002 max mem: 9390 +Train: [92] [5400/6250] eta: 0:02:36 lr: 0.000002 grad: 0.1448 (0.1483) loss: 0.8077 (0.8128) time: 0.0975 data: 0.0024 max mem: 9390 +Train: [92] [5500/6250] eta: 0:02:18 lr: 0.000002 grad: 0.1384 (0.1482) loss: 0.8122 (0.8128) time: 0.1212 data: 0.0184 max mem: 9390 +Train: [92] [5600/6250] eta: 0:01:59 lr: 0.000002 grad: 0.1359 (0.1481) loss: 0.8088 (0.8128) time: 0.1592 data: 0.0695 max mem: 9390 +Train: [92] [5700/6250] eta: 0:01:41 lr: 0.000002 grad: 0.1400 (0.1481) loss: 0.8153 (0.8128) time: 0.1584 data: 0.0716 max mem: 9390 +Train: [92] [5800/6250] eta: 0:01:22 lr: 0.000002 grad: 0.1427 (0.1481) loss: 0.8132 (0.8128) time: 0.1693 data: 0.0888 max mem: 9390 +Train: [92] [5900/6250] eta: 0:01:04 lr: 0.000002 grad: 0.1374 (0.1481) loss: 0.8146 (0.8128) time: 0.3888 data: 0.2832 max mem: 9390 +Train: [92] [6000/6250] eta: 0:00:46 lr: 0.000002 grad: 0.1443 (0.1480) loss: 0.8138 (0.8129) time: 0.7031 data: 0.5963 max mem: 9390 +Train: [92] [6100/6250] eta: 0:00:27 lr: 0.000002 grad: 0.1427 (0.1480) loss: 0.8117 (0.8128) time: 0.1628 data: 0.0798 max mem: 9390 +Train: [92] [6200/6250] eta: 0:00:09 lr: 0.000002 grad: 0.1413 (0.1480) loss: 0.8125 (0.8128) time: 0.1493 data: 0.0706 max mem: 9390 +Train: [92] [6249/6250] eta: 0:00:00 lr: 0.000002 grad: 0.1399 (0.1480) loss: 0.8119 (0.8128) time: 0.0918 data: 0.0067 max mem: 9390 +Train: [92] Total time: 0:19:24 (0.1864 s / it) +Averaged stats: lr: 0.000002 grad: 0.1399 (0.1480) loss: 0.8119 (0.8128) +Eval (hcp-train-subset): [92] [ 0/62] eta: 0:05:12 loss: 0.8256 (0.8256) time: 5.0482 data: 5.0157 max mem: 9390 +Eval (hcp-train-subset): [92] [61/62] eta: 0:00:00 loss: 0.8135 (0.8173) time: 0.1342 data: 0.1095 max mem: 9390 +Eval (hcp-train-subset): [92] Total time: 0:00:13 (0.2247 s / it) +Averaged stats (hcp-train-subset): loss: 0.8135 (0.8173) +Eval (hcp-val): [92] [ 0/62] eta: 0:04:57 loss: 0.8264 (0.8264) time: 4.8053 data: 4.7751 max mem: 9390 +Eval (hcp-val): [92] [61/62] eta: 0:00:00 loss: 0.8265 (0.8287) time: 0.1362 data: 0.1097 max mem: 9390 +Eval (hcp-val): [92] Total time: 0:00:14 (0.2258 s / it) +Averaged stats (hcp-val): loss: 0.8265 (0.8287) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +Train: [93] [ 0/6250] eta: 10:12:20 lr: 0.000002 grad: 0.2101 (0.2101) loss: 0.8067 (0.8067) time: 5.8785 data: 5.6682 max mem: 9390 +Train: [93] [ 100/6250] eta: 0:23:17 lr: 0.000002 grad: 0.1838 (0.2088) loss: 0.8055 (0.8070) time: 0.1807 data: 0.0840 max mem: 9390 +Train: [93] [ 200/6250] eta: 0:21:05 lr: 0.000002 grad: 0.1549 (0.1904) loss: 0.8073 (0.8089) time: 0.1567 data: 0.0430 max mem: 9390 +Train: [93] [ 300/6250] eta: 0:20:21 lr: 0.000002 grad: 0.1508 (0.1804) loss: 0.8109 (0.8093) time: 0.1696 data: 0.0620 max mem: 9390 +Train: [93] [ 400/6250] eta: 0:19:11 lr: 0.000002 grad: 0.1485 (0.1733) loss: 0.8109 (0.8102) time: 0.1541 data: 0.0554 max mem: 9390 +Train: [93] [ 500/6250] eta: 0:18:39 lr: 0.000002 grad: 0.1501 (0.1714) loss: 0.8105 (0.8101) time: 0.2393 data: 0.1400 max mem: 9390 +Train: [93] [ 600/6250] eta: 0:19:26 lr: 0.000002 grad: 0.1580 (0.1686) loss: 0.8090 (0.8105) time: 0.1211 data: 0.0276 max mem: 9390 +Train: [93] [ 700/6250] eta: 0:18:37 lr: 0.000002 grad: 0.1502 (0.1664) loss: 0.8175 (0.8111) time: 0.2041 data: 0.1247 max mem: 9390 +Train: [93] [ 800/6250] eta: 0:18:16 lr: 0.000002 grad: 0.1404 (0.1646) loss: 0.8207 (0.8116) time: 0.2249 data: 0.1282 max mem: 9390 +Train: [93] [ 900/6250] eta: 0:17:32 lr: 0.000002 grad: 0.1478 (0.1636) loss: 0.8148 (0.8115) time: 0.1767 data: 0.0860 max mem: 9390 +Train: [93] [1000/6250] eta: 0:16:56 lr: 0.000002 grad: 0.1401 (0.1618) loss: 0.8136 (0.8118) time: 0.1323 data: 0.0342 max mem: 9390 +Train: [93] [1100/6250] eta: 0:16:33 lr: 0.000002 grad: 0.1367 (0.1605) loss: 0.8180 (0.8120) time: 0.1612 data: 0.0739 max mem: 9390 +Train: [93] [1200/6250] eta: 0:16:05 lr: 0.000002 grad: 0.1467 (0.1589) loss: 0.8089 (0.8122) time: 0.1406 data: 0.0447 max mem: 9390 +Train: [93] [1300/6250] eta: 0:15:33 lr: 0.000002 grad: 0.1384 (0.1579) loss: 0.8164 (0.8123) time: 0.1495 data: 0.0705 max mem: 9390 +Train: [93] [1400/6250] eta: 0:15:04 lr: 0.000002 grad: 0.1306 (0.1568) loss: 0.8195 (0.8126) time: 0.1674 data: 0.0865 max mem: 9390 +Train: [93] [1500/6250] eta: 0:14:34 lr: 0.000002 grad: 0.1346 (0.1558) loss: 0.8125 (0.8127) time: 0.1414 data: 0.0550 max mem: 9390 +Train: [93] [1600/6250] eta: 0:14:07 lr: 0.000002 grad: 0.1396 (0.1550) loss: 0.8154 (0.8128) time: 0.1611 data: 0.0835 max mem: 9390 +Train: [93] [1700/6250] eta: 0:13:52 lr: 0.000002 grad: 0.1320 (0.1540) loss: 0.8212 (0.8132) time: 0.3185 data: 0.2282 max mem: 9390 +Train: [93] [1800/6250] eta: 0:13:25 lr: 0.000002 grad: 0.1364 (0.1533) loss: 0.8173 (0.8133) time: 0.1340 data: 0.0287 max mem: 9390 +Train: [93] [1900/6250] eta: 0:13:05 lr: 0.000002 grad: 0.1399 (0.1527) loss: 0.8113 (0.8134) time: 0.1385 data: 0.0531 max mem: 9390 +Train: [93] [2000/6250] eta: 0:12:45 lr: 0.000002 grad: 0.1319 (0.1522) loss: 0.8176 (0.8135) time: 0.2446 data: 0.1474 max mem: 9390 +Train: [93] [2100/6250] eta: 0:12:22 lr: 0.000002 grad: 0.1471 (0.1518) loss: 0.8123 (0.8136) time: 0.1795 data: 0.0985 max mem: 9390 +Train: [93] [2200/6250] eta: 0:11:59 lr: 0.000002 grad: 0.1315 (0.1514) loss: 0.8157 (0.8136) time: 0.1783 data: 0.0937 max mem: 9390 +Train: [93] [2300/6250] eta: 0:11:38 lr: 0.000001 grad: 0.1390 (0.1511) loss: 0.8150 (0.8136) time: 0.1269 data: 0.0439 max mem: 9390 +Train: [93] [2400/6250] eta: 0:11:17 lr: 0.000001 grad: 0.1384 (0.1508) loss: 0.8136 (0.8136) time: 0.1748 data: 0.0922 max mem: 9390 +Train: [93] [2500/6250] eta: 0:11:01 lr: 0.000001 grad: 0.1301 (0.1507) loss: 0.8148 (0.8136) time: 0.2498 data: 0.1707 max mem: 9390 +Train: [93] [2600/6250] eta: 0:10:39 lr: 0.000001 grad: 0.1399 (0.1505) loss: 0.8176 (0.8135) time: 0.1081 data: 0.0283 max mem: 9390 +Train: [93] [2700/6250] eta: 0:10:22 lr: 0.000001 grad: 0.1530 (0.1503) loss: 0.8121 (0.8135) time: 0.1859 data: 0.0982 max mem: 9390 +Train: [93] [2800/6250] eta: 0:10:03 lr: 0.000001 grad: 0.1455 (0.1501) loss: 0.8163 (0.8135) time: 0.1018 data: 0.0200 max mem: 9390 +Train: [93] [2900/6250] eta: 0:09:46 lr: 0.000001 grad: 0.1517 (0.1500) loss: 0.8153 (0.8134) time: 0.1567 data: 0.0806 max mem: 9390 +Train: [93] [3000/6250] eta: 0:09:28 lr: 0.000001 grad: 0.1362 (0.1498) loss: 0.8146 (0.8135) time: 0.2207 data: 0.1391 max mem: 9390 +Train: [93] [3100/6250] eta: 0:09:08 lr: 0.000001 grad: 0.1436 (0.1496) loss: 0.8052 (0.8135) time: 0.1513 data: 0.0668 max mem: 9390 +Train: [93] [3200/6250] eta: 0:08:48 lr: 0.000001 grad: 0.1362 (0.1495) loss: 0.8098 (0.8133) time: 0.1567 data: 0.0740 max mem: 9390 +Train: [93] [3300/6250] eta: 0:08:30 lr: 0.000001 grad: 0.1449 (0.1493) loss: 0.8125 (0.8132) time: 0.1548 data: 0.0695 max mem: 9390 +Train: [93] [3400/6250] eta: 0:08:12 lr: 0.000001 grad: 0.1371 (0.1493) loss: 0.8198 (0.8132) time: 0.1747 data: 0.0886 max mem: 9390 +Train: [93] [3500/6250] eta: 0:07:53 lr: 0.000001 grad: 0.1523 (0.1493) loss: 0.8104 (0.8130) time: 0.1555 data: 0.0666 max mem: 9390 +Train: [93] [3600/6250] eta: 0:07:35 lr: 0.000001 grad: 0.1439 (0.1494) loss: 0.8115 (0.8130) time: 0.1681 data: 0.0675 max mem: 9390 +Train: [93] [3700/6250] eta: 0:07:19 lr: 0.000001 grad: 0.1402 (0.1494) loss: 0.8156 (0.8129) time: 0.1960 data: 0.0778 max mem: 9390 +Train: [93] [3800/6250] eta: 0:07:01 lr: 0.000001 grad: 0.1474 (0.1494) loss: 0.8219 (0.8128) time: 0.1693 data: 0.0801 max mem: 9390 +Train: [93] [3900/6250] eta: 0:06:43 lr: 0.000001 grad: 0.1477 (0.1494) loss: 0.8130 (0.8128) time: 0.1409 data: 0.0583 max mem: 9390 +Train: [93] [4000/6250] eta: 0:06:25 lr: 0.000001 grad: 0.1385 (0.1492) loss: 0.8223 (0.8129) time: 0.1504 data: 0.0713 max mem: 9390 +Train: [93] [4100/6250] eta: 0:06:08 lr: 0.000001 grad: 0.1400 (0.1491) loss: 0.8163 (0.8129) time: 0.1926 data: 0.1146 max mem: 9390 +Train: [93] [4200/6250] eta: 0:05:50 lr: 0.000001 grad: 0.1528 (0.1492) loss: 0.8127 (0.8128) time: 0.1777 data: 0.0951 max mem: 9390 +Train: [93] [4300/6250] eta: 0:05:33 lr: 0.000001 grad: 0.1402 (0.1492) loss: 0.8176 (0.8129) time: 0.2421 data: 0.1533 max mem: 9390 +Train: [93] [4400/6250] eta: 0:05:16 lr: 0.000001 grad: 0.1388 (0.1491) loss: 0.8176 (0.8130) time: 0.2228 data: 0.1321 max mem: 9390 +Train: [93] [4500/6250] eta: 0:04:59 lr: 0.000001 grad: 0.1439 (0.1491) loss: 0.8138 (0.8131) time: 0.0998 data: 0.0002 max mem: 9390 +Train: [93] [4600/6250] eta: 0:04:44 lr: 0.000001 grad: 0.1372 (0.1491) loss: 0.8128 (0.8131) time: 0.2930 data: 0.1894 max mem: 9390 +Train: [93] [4700/6250] eta: 0:04:28 lr: 0.000001 grad: 0.1442 (0.1489) loss: 0.8197 (0.8132) time: 0.3719 data: 0.2752 max mem: 9390 +Train: [93] [4800/6250] eta: 0:04:11 lr: 0.000001 grad: 0.1382 (0.1489) loss: 0.8183 (0.8132) time: 0.1988 data: 0.1059 max mem: 9390 +Train: [93] [4900/6250] eta: 0:03:53 lr: 0.000001 grad: 0.1389 (0.1487) loss: 0.8163 (0.8133) time: 0.1624 data: 0.0578 max mem: 9390 +Train: [93] [5000/6250] eta: 0:03:38 lr: 0.000001 grad: 0.1419 (0.1487) loss: 0.8143 (0.8134) time: 0.1134 data: 0.0002 max mem: 9390 +Train: [93] [5100/6250] eta: 0:03:20 lr: 0.000001 grad: 0.1369 (0.1486) loss: 0.8149 (0.8134) time: 0.1176 data: 0.0256 max mem: 9390 +Train: [93] [5200/6250] eta: 0:03:03 lr: 0.000001 grad: 0.1323 (0.1486) loss: 0.8128 (0.8134) time: 0.1655 data: 0.0723 max mem: 9390 +Train: [93] [5300/6250] eta: 0:02:46 lr: 0.000001 grad: 0.1361 (0.1484) loss: 0.8183 (0.8134) time: 0.2022 data: 0.1131 max mem: 9390 +Train: [93] [5400/6250] eta: 0:02:28 lr: 0.000001 grad: 0.1342 (0.1483) loss: 0.8158 (0.8135) time: 0.1373 data: 0.0452 max mem: 9390 +Train: [93] [5500/6250] eta: 0:02:11 lr: 0.000001 grad: 0.1406 (0.1482) loss: 0.8201 (0.8136) time: 0.1284 data: 0.0207 max mem: 9390 +Train: [93] [5600/6250] eta: 0:01:54 lr: 0.000001 grad: 0.1418 (0.1480) loss: 0.8212 (0.8136) time: 0.1529 data: 0.0504 max mem: 9390 +Train: [93] [5700/6250] eta: 0:01:36 lr: 0.000001 grad: 0.1334 (0.1479) loss: 0.8211 (0.8137) time: 0.1485 data: 0.0622 max mem: 9390 +Train: [93] [5800/6250] eta: 0:01:19 lr: 0.000001 grad: 0.1377 (0.1477) loss: 0.8152 (0.8138) time: 0.4503 data: 0.3592 max mem: 9390 +Train: [93] [5900/6250] eta: 0:01:01 lr: 0.000001 grad: 0.1406 (0.1476) loss: 0.8130 (0.8138) time: 0.1023 data: 0.0003 max mem: 9390 +Train: [93] [6000/6250] eta: 0:00:44 lr: 0.000001 grad: 0.1382 (0.1475) loss: 0.8172 (0.8138) time: 0.1200 data: 0.0259 max mem: 9390 +Train: [93] [6100/6250] eta: 0:00:26 lr: 0.000001 grad: 0.1344 (0.1473) loss: 0.8212 (0.8139) time: 0.1762 data: 0.0905 max mem: 9390 +Train: [93] [6200/6250] eta: 0:00:08 lr: 0.000001 grad: 0.1308 (0.1472) loss: 0.8175 (0.8139) time: 0.1294 data: 0.0414 max mem: 9390 +Train: [93] [6249/6250] eta: 0:00:00 lr: 0.000001 grad: 0.1473 (0.1472) loss: 0.8127 (0.8139) time: 0.2288 data: 0.1074 max mem: 9390 +Train: [93] Total time: 0:18:29 (0.1775 s / it) +Averaged stats: lr: 0.000001 grad: 0.1473 (0.1472) loss: 0.8127 (0.8139) +Eval (hcp-train-subset): [93] [ 0/62] eta: 0:03:28 loss: 0.8265 (0.8265) time: 3.3672 data: 3.2871 max mem: 9390 +Eval (hcp-train-subset): [93] [61/62] eta: 0:00:00 loss: 0.8145 (0.8168) time: 0.1420 data: 0.1170 max mem: 9390 +Eval (hcp-train-subset): [93] Total time: 0:00:14 (0.2319 s / it) +Averaged stats (hcp-train-subset): loss: 0.8145 (0.8168) +Eval (hcp-val): [93] [ 0/62] eta: 0:04:09 loss: 0.8242 (0.8242) time: 4.0216 data: 3.9394 max mem: 9390 +Eval (hcp-val): [93] [61/62] eta: 0:00:00 loss: 0.8275 (0.8287) time: 0.1176 data: 0.0928 max mem: 9390 +Eval (hcp-val): [93] Total time: 0:00:13 (0.2250 s / it) +Averaged stats (hcp-val): loss: 0.8275 (0.8287) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +Train: [94] [ 0/6250] eta: 10:35:34 lr: 0.000001 grad: 0.0988 (0.0988) loss: 0.8720 (0.8720) time: 6.1015 data: 5.9435 max mem: 9390 +Train: [94] [ 100/6250] eta: 0:24:27 lr: 0.000001 grad: 0.1376 (0.1622) loss: 0.8419 (0.8393) time: 0.1729 data: 0.0734 max mem: 9390 +Train: [94] [ 200/6250] eta: 0:21:29 lr: 0.000001 grad: 0.1466 (0.1555) loss: 0.8286 (0.8341) time: 0.1800 data: 0.0833 max mem: 9390 +Train: [94] [ 300/6250] eta: 0:20:33 lr: 0.000001 grad: 0.1399 (0.1511) loss: 0.8222 (0.8313) time: 0.1758 data: 0.0851 max mem: 9390 +Train: [94] [ 400/6250] eta: 0:22:18 lr: 0.000001 grad: 0.1402 (0.1493) loss: 0.8225 (0.8294) time: 0.1239 data: 0.0003 max mem: 9390 +Train: [94] [ 500/6250] eta: 0:21:13 lr: 0.000001 grad: 0.1573 (0.1496) loss: 0.8166 (0.8274) time: 0.1122 data: 0.0003 max mem: 9390 +Train: [94] [ 600/6250] eta: 0:19:45 lr: 0.000001 grad: 0.1390 (0.1503) loss: 0.8241 (0.8262) time: 0.1842 data: 0.0909 max mem: 9390 +Train: [94] [ 700/6250] eta: 0:18:55 lr: 0.000001 grad: 0.1400 (0.1495) loss: 0.8192 (0.8254) time: 0.1332 data: 0.0236 max mem: 9390 +Train: [94] [ 800/6250] eta: 0:18:16 lr: 0.000001 grad: 0.1425 (0.1500) loss: 0.8147 (0.8244) time: 0.1213 data: 0.0355 max mem: 9390 +Train: [94] [ 900/6250] eta: 0:18:27 lr: 0.000001 grad: 0.1375 (0.1495) loss: 0.8198 (0.8236) time: 0.3807 data: 0.2850 max mem: 9390 +Train: [94] [1000/6250] eta: 0:17:35 lr: 0.000001 grad: 0.1456 (0.1490) loss: 0.8165 (0.8231) time: 0.1960 data: 0.1074 max mem: 9390 +Train: [94] [1100/6250] eta: 0:16:53 lr: 0.000001 grad: 0.1347 (0.1486) loss: 0.8161 (0.8226) time: 0.1207 data: 0.0227 max mem: 9390 +Train: [94] [1200/6250] eta: 0:16:31 lr: 0.000001 grad: 0.1403 (0.1482) loss: 0.8147 (0.8221) time: 0.0916 data: 0.0002 max mem: 9390 +Train: [94] [1300/6250] eta: 0:16:15 lr: 0.000001 grad: 0.1430 (0.1480) loss: 0.8186 (0.8217) time: 0.3667 data: 0.2681 max mem: 9390 +Train: [94] [1400/6250] eta: 0:15:38 lr: 0.000001 grad: 0.1382 (0.1476) loss: 0.8152 (0.8213) time: 0.1526 data: 0.0658 max mem: 9390 +Train: [94] [1500/6250] eta: 0:15:19 lr: 0.000001 grad: 0.1328 (0.1471) loss: 0.8243 (0.8210) time: 0.1021 data: 0.0002 max mem: 9390 +Train: [94] [1600/6250] eta: 0:14:55 lr: 0.000001 grad: 0.1323 (0.1465) loss: 0.8221 (0.8208) time: 0.3218 data: 0.2314 max mem: 9390 +Train: [94] [1700/6250] eta: 0:14:33 lr: 0.000001 grad: 0.1323 (0.1461) loss: 0.8177 (0.8207) time: 0.1139 data: 0.0029 max mem: 9390 +Train: [94] [1800/6250] eta: 0:14:05 lr: 0.000001 grad: 0.1369 (0.1458) loss: 0.8179 (0.8206) time: 0.1292 data: 0.0400 max mem: 9390 +Train: [94] [1900/6250] eta: 0:13:43 lr: 0.000001 grad: 0.1339 (0.1453) loss: 0.8206 (0.8206) time: 0.1543 data: 0.0559 max mem: 9390 +Train: [94] [2000/6250] eta: 0:13:22 lr: 0.000001 grad: 0.1383 (0.1450) loss: 0.8186 (0.8205) time: 0.2608 data: 0.1753 max mem: 9390 +Train: [94] [2100/6250] eta: 0:13:17 lr: 0.000001 grad: 0.1384 (0.1449) loss: 0.8185 (0.8204) time: 0.1730 data: 0.0552 max mem: 9390 +Train: [94] [2200/6250] eta: 0:12:53 lr: 0.000001 grad: 0.1389 (0.1448) loss: 0.8194 (0.8202) time: 0.1575 data: 0.0620 max mem: 9390 +Train: [94] [2300/6250] eta: 0:12:27 lr: 0.000001 grad: 0.1352 (0.1446) loss: 0.8176 (0.8201) time: 0.1530 data: 0.0637 max mem: 9390 +Train: [94] [2400/6250] eta: 0:12:03 lr: 0.000001 grad: 0.1367 (0.1444) loss: 0.8172 (0.8200) time: 0.1548 data: 0.0628 max mem: 9390 +Train: [94] [2500/6250] eta: 0:11:40 lr: 0.000001 grad: 0.1290 (0.1443) loss: 0.8152 (0.8199) time: 0.1819 data: 0.0996 max mem: 9390 +Train: [94] [2600/6250] eta: 0:11:19 lr: 0.000001 grad: 0.1340 (0.1442) loss: 0.8198 (0.8197) time: 0.1370 data: 0.0458 max mem: 9390 +Train: [94] [2700/6250] eta: 0:10:59 lr: 0.000001 grad: 0.1433 (0.1441) loss: 0.8117 (0.8195) time: 0.1685 data: 0.0846 max mem: 9390 +Train: [94] [2800/6250] eta: 0:10:40 lr: 0.000001 grad: 0.1284 (0.1439) loss: 0.8181 (0.8194) time: 0.1442 data: 0.0631 max mem: 9390 +Train: [94] [2900/6250] eta: 0:10:19 lr: 0.000001 grad: 0.1371 (0.1437) loss: 0.8136 (0.8192) time: 0.1592 data: 0.0757 max mem: 9390 +Train: [94] [3000/6250] eta: 0:09:59 lr: 0.000001 grad: 0.1402 (0.1435) loss: 0.8176 (0.8191) time: 0.1702 data: 0.0878 max mem: 9390 +Train: [94] [3100/6250] eta: 0:09:40 lr: 0.000001 grad: 0.1327 (0.1432) loss: 0.8220 (0.8191) time: 0.2447 data: 0.1658 max mem: 9390 +Train: [94] [3200/6250] eta: 0:09:22 lr: 0.000001 grad: 0.1415 (0.1432) loss: 0.8191 (0.8190) time: 0.1974 data: 0.1148 max mem: 9390 +Train: [94] [3300/6250] eta: 0:09:01 lr: 0.000001 grad: 0.1338 (0.1431) loss: 0.8113 (0.8189) time: 0.1620 data: 0.0773 max mem: 9390 +Train: [94] [3400/6250] eta: 0:08:40 lr: 0.000001 grad: 0.1373 (0.1430) loss: 0.8123 (0.8188) time: 0.1669 data: 0.0800 max mem: 9390 +Train: [94] [3500/6250] eta: 0:08:21 lr: 0.000001 grad: 0.1501 (0.1431) loss: 0.8167 (0.8187) time: 0.1321 data: 0.0499 max mem: 9390 +Train: [94] [3600/6250] eta: 0:08:02 lr: 0.000001 grad: 0.1461 (0.1431) loss: 0.8139 (0.8187) time: 0.1191 data: 0.0346 max mem: 9390 +Train: [94] [3700/6250] eta: 0:07:46 lr: 0.000001 grad: 0.1377 (0.1432) loss: 0.8150 (0.8185) time: 0.1824 data: 0.1037 max mem: 9390 +Train: [94] [3800/6250] eta: 0:07:29 lr: 0.000001 grad: 0.1451 (0.1434) loss: 0.8148 (0.8185) time: 0.1934 data: 0.1041 max mem: 9390 +Train: [94] [3900/6250] eta: 0:07:11 lr: 0.000001 grad: 0.1420 (0.1434) loss: 0.8129 (0.8184) time: 0.1770 data: 0.0960 max mem: 9390 +Train: [94] [4000/6250] eta: 0:06:53 lr: 0.000001 grad: 0.1430 (0.1434) loss: 0.8169 (0.8184) time: 0.2010 data: 0.1081 max mem: 9390 +Train: [94] [4100/6250] eta: 0:06:35 lr: 0.000001 grad: 0.1305 (0.1433) loss: 0.8170 (0.8183) time: 0.2068 data: 0.1178 max mem: 9390 +Train: [94] [4200/6250] eta: 0:06:17 lr: 0.000001 grad: 0.1289 (0.1433) loss: 0.8136 (0.8183) time: 0.1297 data: 0.0356 max mem: 9390 +Train: [94] [4300/6250] eta: 0:05:57 lr: 0.000001 grad: 0.1457 (0.1432) loss: 0.8162 (0.8183) time: 0.1559 data: 0.0723 max mem: 9390 +Train: [94] [4400/6250] eta: 0:05:37 lr: 0.000001 grad: 0.1394 (0.1432) loss: 0.8173 (0.8183) time: 0.1063 data: 0.0002 max mem: 9390 +Train: [94] [4500/6250] eta: 0:05:18 lr: 0.000001 grad: 0.1322 (0.1431) loss: 0.8185 (0.8183) time: 0.1370 data: 0.0380 max mem: 9390 +Train: [94] [4600/6250] eta: 0:04:58 lr: 0.000001 grad: 0.1360 (0.1430) loss: 0.8204 (0.8183) time: 0.1249 data: 0.0202 max mem: 9390 +Train: [94] [4700/6250] eta: 0:04:40 lr: 0.000001 grad: 0.1328 (0.1429) loss: 0.8191 (0.8184) time: 0.1274 data: 0.0402 max mem: 9390 +Train: [94] [4800/6250] eta: 0:04:21 lr: 0.000001 grad: 0.1354 (0.1428) loss: 0.8152 (0.8183) time: 0.1438 data: 0.0427 max mem: 9390 +Train: [94] [4900/6250] eta: 0:04:02 lr: 0.000001 grad: 0.1347 (0.1428) loss: 0.8213 (0.8183) time: 0.1709 data: 0.0882 max mem: 9390 +Train: [94] [5000/6250] eta: 0:03:44 lr: 0.000001 grad: 0.1413 (0.1428) loss: 0.8158 (0.8183) time: 0.1856 data: 0.0868 max mem: 9390 +Train: [94] [5100/6250] eta: 0:03:26 lr: 0.000001 grad: 0.1407 (0.1428) loss: 0.8211 (0.8183) time: 0.1331 data: 0.0301 max mem: 9390 +Train: [94] [5200/6250] eta: 0:03:08 lr: 0.000001 grad: 0.1353 (0.1427) loss: 0.8189 (0.8183) time: 0.1614 data: 0.0729 max mem: 9390 +Train: [94] [5300/6250] eta: 0:02:51 lr: 0.000001 grad: 0.1331 (0.1426) loss: 0.8166 (0.8183) time: 0.4243 data: 0.2662 max mem: 9390 +Train: [94] [5400/6250] eta: 0:02:33 lr: 0.000001 grad: 0.1427 (0.1425) loss: 0.8216 (0.8182) time: 0.2076 data: 0.1250 max mem: 9390 +Train: [94] [5500/6250] eta: 0:02:15 lr: 0.000001 grad: 0.1335 (0.1425) loss: 0.8180 (0.8182) time: 0.2193 data: 0.1161 max mem: 9390 +Train: [94] [5600/6250] eta: 0:01:57 lr: 0.000001 grad: 0.1308 (0.1424) loss: 0.8171 (0.8182) time: 0.1487 data: 0.0488 max mem: 9390 +Train: [94] [5700/6250] eta: 0:01:39 lr: 0.000001 grad: 0.1271 (0.1423) loss: 0.8235 (0.8182) time: 0.1389 data: 0.0521 max mem: 9390 +Train: [94] [5800/6250] eta: 0:01:21 lr: 0.000001 grad: 0.1265 (0.1422) loss: 0.8175 (0.8182) time: 0.1267 data: 0.0247 max mem: 9390 +Train: [94] [5900/6250] eta: 0:01:03 lr: 0.000001 grad: 0.1334 (0.1421) loss: 0.8204 (0.8182) time: 0.1674 data: 0.0825 max mem: 9390 +Train: [94] [6000/6250] eta: 0:00:45 lr: 0.000001 grad: 0.1372 (0.1421) loss: 0.8200 (0.8182) time: 0.1021 data: 0.0002 max mem: 9390 +Train: [94] [6100/6250] eta: 0:00:27 lr: 0.000001 grad: 0.1366 (0.1420) loss: 0.8185 (0.8181) time: 0.0831 data: 0.0002 max mem: 9390 +Train: [94] [6200/6250] eta: 0:00:09 lr: 0.000001 grad: 0.1320 (0.1420) loss: 0.8174 (0.8181) time: 0.2125 data: 0.1178 max mem: 9390 +Train: [94] [6249/6250] eta: 0:00:00 lr: 0.000001 grad: 0.1357 (0.1420) loss: 0.8141 (0.8181) time: 0.3556 data: 0.2752 max mem: 9390 +Train: [94] Total time: 0:18:59 (0.1824 s / it) +Averaged stats: lr: 0.000001 grad: 0.1357 (0.1420) loss: 0.8141 (0.8181) +Eval (hcp-train-subset): [94] [ 0/62] eta: 0:04:52 loss: 0.8287 (0.8287) time: 4.7172 data: 4.6870 max mem: 9390 +Eval (hcp-train-subset): [94] [61/62] eta: 0:00:00 loss: 0.8124 (0.8170) time: 0.1411 data: 0.1159 max mem: 9390 +Eval (hcp-train-subset): [94] Total time: 0:00:13 (0.2211 s / it) +Averaged stats (hcp-train-subset): loss: 0.8124 (0.8170) +Making plots (hcp-train-subset): example=23 +Eval (hcp-val): [94] [ 0/62] eta: 0:03:18 loss: 0.8229 (0.8229) time: 3.2010 data: 3.1478 max mem: 9390 +Eval (hcp-val): [94] [61/62] eta: 0:00:00 loss: 0.8268 (0.8278) time: 0.1352 data: 0.1085 max mem: 9390 +Eval (hcp-val): [94] Total time: 0:00:13 (0.2209 s / it) +Averaged stats (hcp-val): loss: 0.8268 (0.8278) +Making plots (hcp-val): example=49 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +Train: [95] [ 0/6250] eta: 10:11:11 lr: 0.000001 grad: 0.1507 (0.1507) loss: 0.8622 (0.8622) time: 5.8675 data: 5.4535 max mem: 9390 +Train: [95] [ 100/6250] eta: 0:24:21 lr: 0.000001 grad: 0.1674 (0.2133) loss: 0.8257 (0.8255) time: 0.2005 data: 0.1089 max mem: 9390 +Train: [95] [ 200/6250] eta: 0:21:24 lr: 0.000001 grad: 0.1525 (0.1877) loss: 0.8305 (0.8240) time: 0.1703 data: 0.0611 max mem: 9390 +Train: [95] [ 300/6250] eta: 0:19:49 lr: 0.000001 grad: 0.1619 (0.1801) loss: 0.8136 (0.8226) time: 0.1770 data: 0.0844 max mem: 9390 +Train: [95] [ 400/6250] eta: 0:18:49 lr: 0.000001 grad: 0.1661 (0.1785) loss: 0.8078 (0.8206) time: 0.1814 data: 0.0836 max mem: 9390 +Train: [95] [ 500/6250] eta: 0:19:04 lr: 0.000001 grad: 0.1526 (0.1756) loss: 0.8076 (0.8187) time: 0.4104 data: 0.3118 max mem: 9390 +Train: [95] [ 600/6250] eta: 0:18:10 lr: 0.000001 grad: 0.1612 (0.1749) loss: 0.8103 (0.8176) time: 0.1929 data: 0.1057 max mem: 9390 +Train: [95] [ 700/6250] eta: 0:18:14 lr: 0.000001 grad: 0.1498 (0.1732) loss: 0.8159 (0.8171) time: 0.1005 data: 0.0002 max mem: 9390 +Train: [95] [ 800/6250] eta: 0:17:34 lr: 0.000001 grad: 0.1466 (0.1708) loss: 0.8117 (0.8171) time: 0.1671 data: 0.0847 max mem: 9390 +Train: [95] [ 900/6250] eta: 0:17:16 lr: 0.000001 grad: 0.1379 (0.1685) loss: 0.8147 (0.8169) time: 0.2362 data: 0.1305 max mem: 9390 +Train: [95] [1000/6250] eta: 0:16:31 lr: 0.000001 grad: 0.1500 (0.1668) loss: 0.8162 (0.8167) time: 0.1283 data: 0.0459 max mem: 9390 +Train: [95] [1100/6250] eta: 0:16:24 lr: 0.000001 grad: 0.1514 (0.1650) loss: 0.8199 (0.8166) time: 0.3690 data: 0.2677 max mem: 9390 +Train: [95] [1200/6250] eta: 0:15:47 lr: 0.000001 grad: 0.1444 (0.1635) loss: 0.8159 (0.8165) time: 0.1615 data: 0.0678 max mem: 9390 +Train: [95] [1300/6250] eta: 0:15:26 lr: 0.000001 grad: 0.1461 (0.1626) loss: 0.8135 (0.8163) time: 0.2367 data: 0.1275 max mem: 9390 +Train: [95] [1400/6250] eta: 0:15:18 lr: 0.000001 grad: 0.1408 (0.1615) loss: 0.8193 (0.8162) time: 0.1792 data: 0.0925 max mem: 9390 +Train: [95] [1500/6250] eta: 0:14:50 lr: 0.000001 grad: 0.1419 (0.1604) loss: 0.8168 (0.8161) time: 0.1630 data: 0.0741 max mem: 9390 +Train: [95] [1600/6250] eta: 0:14:30 lr: 0.000001 grad: 0.1514 (0.1595) loss: 0.8075 (0.8161) time: 0.1787 data: 0.0954 max mem: 9390 +Train: [95] [1700/6250] eta: 0:14:06 lr: 0.000001 grad: 0.1331 (0.1584) loss: 0.8156 (0.8162) time: 0.1932 data: 0.0992 max mem: 9390 +Train: [95] [1800/6250] eta: 0:13:42 lr: 0.000001 grad: 0.1464 (0.1577) loss: 0.8078 (0.8161) time: 0.2027 data: 0.1125 max mem: 9390 +Train: [95] [1900/6250] eta: 0:13:21 lr: 0.000001 grad: 0.1412 (0.1570) loss: 0.8103 (0.8160) time: 0.1124 data: 0.0234 max mem: 9390 +Train: [95] [2000/6250] eta: 0:13:00 lr: 0.000001 grad: 0.1475 (0.1564) loss: 0.8161 (0.8160) time: 0.2284 data: 0.1391 max mem: 9390 +Train: [95] [2100/6250] eta: 0:12:45 lr: 0.000001 grad: 0.1452 (0.1559) loss: 0.8131 (0.8160) time: 0.3796 data: 0.2608 max mem: 9390 +Train: [95] [2200/6250] eta: 0:12:25 lr: 0.000001 grad: 0.1485 (0.1555) loss: 0.8146 (0.8160) time: 0.2092 data: 0.1149 max mem: 9390 +Train: [95] [2300/6250] eta: 0:12:08 lr: 0.000001 grad: 0.1457 (0.1551) loss: 0.8172 (0.8160) time: 0.1617 data: 0.0788 max mem: 9390 +Train: [95] [2400/6250] eta: 0:11:47 lr: 0.000001 grad: 0.1449 (0.1550) loss: 0.8152 (0.8158) time: 0.0882 data: 0.0002 max mem: 9390 +Train: [95] [2500/6250] eta: 0:11:25 lr: 0.000001 grad: 0.1524 (0.1547) loss: 0.8114 (0.8158) time: 0.1374 data: 0.0593 max mem: 9390 +Train: [95] [2600/6250] eta: 0:11:04 lr: 0.000001 grad: 0.1414 (0.1545) loss: 0.8059 (0.8157) time: 0.1388 data: 0.0587 max mem: 9390 +Train: [95] [2700/6250] eta: 0:10:48 lr: 0.000001 grad: 0.1377 (0.1544) loss: 0.8106 (0.8156) time: 0.0875 data: 0.0002 max mem: 9390 +Train: [95] [2800/6250] eta: 0:10:25 lr: 0.000001 grad: 0.1414 (0.1540) loss: 0.8154 (0.8156) time: 0.1567 data: 0.0737 max mem: 9390 +Train: [95] [2900/6250] eta: 0:10:04 lr: 0.000001 grad: 0.1454 (0.1538) loss: 0.8150 (0.8155) time: 0.1789 data: 0.1013 max mem: 9390 +Train: [95] [3000/6250] eta: 0:09:43 lr: 0.000001 grad: 0.1461 (0.1536) loss: 0.8144 (0.8154) time: 0.1534 data: 0.0705 max mem: 9390 +Train: [95] [3100/6250] eta: 0:09:24 lr: 0.000001 grad: 0.1452 (0.1535) loss: 0.8149 (0.8153) time: 0.1540 data: 0.0750 max mem: 9390 +Train: [95] [3200/6250] eta: 0:09:04 lr: 0.000001 grad: 0.1524 (0.1533) loss: 0.8108 (0.8152) time: 0.1574 data: 0.0679 max mem: 9390 +Train: [95] [3300/6250] eta: 0:08:44 lr: 0.000001 grad: 0.1415 (0.1532) loss: 0.8065 (0.8151) time: 0.1339 data: 0.0520 max mem: 9390 +Train: [95] [3400/6250] eta: 0:08:25 lr: 0.000001 grad: 0.1404 (0.1531) loss: 0.8103 (0.8151) time: 0.1690 data: 0.0893 max mem: 9390 +Train: [95] [3500/6250] eta: 0:08:06 lr: 0.000001 grad: 0.1479 (0.1529) loss: 0.8088 (0.8150) time: 0.1866 data: 0.1036 max mem: 9390 +Train: [95] [3600/6250] eta: 0:07:47 lr: 0.000001 grad: 0.1469 (0.1528) loss: 0.8123 (0.8149) time: 0.1916 data: 0.1067 max mem: 9390 +Train: [95] [3700/6250] eta: 0:07:26 lr: 0.000001 grad: 0.1423 (0.1526) loss: 0.8107 (0.8149) time: 0.1371 data: 0.0451 max mem: 9390 +Train: [95] [3800/6250] eta: 0:07:07 lr: 0.000001 grad: 0.1392 (0.1524) loss: 0.8092 (0.8149) time: 0.1376 data: 0.0461 max mem: 9390 +Train: [95] [3900/6250] eta: 0:06:48 lr: 0.000001 grad: 0.1324 (0.1523) loss: 0.8186 (0.8149) time: 0.1482 data: 0.0552 max mem: 9390 +Train: [95] [4000/6250] eta: 0:06:29 lr: 0.000001 grad: 0.1460 (0.1522) loss: 0.8197 (0.8149) time: 0.1369 data: 0.0498 max mem: 9390 +Train: [95] [4100/6250] eta: 0:06:10 lr: 0.000001 grad: 0.1461 (0.1520) loss: 0.8200 (0.8149) time: 0.1565 data: 0.0741 max mem: 9390 +Train: [95] [4200/6250] eta: 0:05:51 lr: 0.000001 grad: 0.1375 (0.1517) loss: 0.8135 (0.8149) time: 0.1443 data: 0.0597 max mem: 9390 +Train: [95] [4300/6250] eta: 0:05:34 lr: 0.000001 grad: 0.1397 (0.1516) loss: 0.8149 (0.8150) time: 0.1655 data: 0.0855 max mem: 9390 +Train: [95] [4400/6250] eta: 0:05:16 lr: 0.000001 grad: 0.1458 (0.1516) loss: 0.8141 (0.8149) time: 0.1827 data: 0.1034 max mem: 9390 +Train: [95] [4500/6250] eta: 0:04:59 lr: 0.000001 grad: 0.1537 (0.1515) loss: 0.8172 (0.8149) time: 0.1371 data: 0.0388 max mem: 9390 +Train: [95] [4600/6250] eta: 0:04:42 lr: 0.000001 grad: 0.1385 (0.1514) loss: 0.8215 (0.8149) time: 0.0933 data: 0.0002 max mem: 9390 +Train: [95] [4700/6250] eta: 0:04:25 lr: 0.000001 grad: 0.1394 (0.1513) loss: 0.8192 (0.8150) time: 0.1768 data: 0.0872 max mem: 9390 +Train: [95] [4800/6250] eta: 0:04:07 lr: 0.000001 grad: 0.1406 (0.1511) loss: 0.8235 (0.8150) time: 0.1232 data: 0.0271 max mem: 9390 +Train: [95] [4900/6250] eta: 0:03:50 lr: 0.000001 grad: 0.1453 (0.1509) loss: 0.8159 (0.8151) time: 0.1712 data: 0.0888 max mem: 9390 +Train: [95] [5000/6250] eta: 0:03:33 lr: 0.000001 grad: 0.1368 (0.1508) loss: 0.8151 (0.8152) time: 0.1748 data: 0.0914 max mem: 9390 +Train: [95] [5100/6250] eta: 0:03:16 lr: 0.000001 grad: 0.1433 (0.1507) loss: 0.8179 (0.8152) time: 0.1898 data: 0.0976 max mem: 9390 +Train: [95] [5200/6250] eta: 0:02:59 lr: 0.000001 grad: 0.1324 (0.1505) loss: 0.8200 (0.8153) time: 0.1664 data: 0.0836 max mem: 9390 +Train: [95] [5300/6250] eta: 0:02:42 lr: 0.000001 grad: 0.1373 (0.1504) loss: 0.8193 (0.8153) time: 0.1880 data: 0.1033 max mem: 9390 +Train: [95] [5400/6250] eta: 0:02:25 lr: 0.000001 grad: 0.1407 (0.1503) loss: 0.8143 (0.8154) time: 0.1633 data: 0.0754 max mem: 9390 +Train: [95] [5500/6250] eta: 0:02:07 lr: 0.000001 grad: 0.1425 (0.1501) loss: 0.8165 (0.8154) time: 0.1240 data: 0.0362 max mem: 9390 +Train: [95] [5600/6250] eta: 0:01:50 lr: 0.000001 grad: 0.1393 (0.1500) loss: 0.8174 (0.8154) time: 0.1847 data: 0.0921 max mem: 9390 +Train: [95] [5700/6250] eta: 0:01:33 lr: 0.000001 grad: 0.1386 (0.1499) loss: 0.8183 (0.8155) time: 0.1024 data: 0.0223 max mem: 9390 +Train: [95] [5800/6250] eta: 0:01:16 lr: 0.000001 grad: 0.1488 (0.1498) loss: 0.8119 (0.8155) time: 0.1067 data: 0.0144 max mem: 9390 +Train: [95] [5900/6250] eta: 0:00:59 lr: 0.000001 grad: 0.1509 (0.1499) loss: 0.8140 (0.8155) time: 0.1398 data: 0.0594 max mem: 9390 +Train: [95] [6000/6250] eta: 0:00:42 lr: 0.000001 grad: 0.1506 (0.1500) loss: 0.8169 (0.8155) time: 0.3541 data: 0.2659 max mem: 9390 +Train: [95] [6100/6250] eta: 0:00:25 lr: 0.000001 grad: 0.1471 (0.1500) loss: 0.8092 (0.8154) time: 0.1723 data: 0.0965 max mem: 9390 +Train: [95] [6200/6250] eta: 0:00:08 lr: 0.000001 grad: 0.1465 (0.1501) loss: 0.8134 (0.8154) time: 0.1083 data: 0.0231 max mem: 9390 +Train: [95] [6249/6250] eta: 0:00:00 lr: 0.000001 grad: 0.1384 (0.1501) loss: 0.8190 (0.8154) time: 0.1502 data: 0.0618 max mem: 9390 +Train: [95] Total time: 0:17:53 (0.1718 s / it) +Averaged stats: lr: 0.000001 grad: 0.1384 (0.1501) loss: 0.8190 (0.8154) +Eval (hcp-train-subset): [95] [ 0/62] eta: 0:05:33 loss: 0.8258 (0.8258) time: 5.3858 data: 5.3540 max mem: 9390 +Eval (hcp-train-subset): [95] [61/62] eta: 0:00:00 loss: 0.8141 (0.8169) time: 0.1191 data: 0.0926 max mem: 9390 +Eval (hcp-train-subset): [95] Total time: 0:00:14 (0.2319 s / it) +Averaged stats (hcp-train-subset): loss: 0.8141 (0.8169) +Eval (hcp-val): [95] [ 0/62] eta: 0:03:32 loss: 0.8256 (0.8256) time: 3.4218 data: 3.3380 max mem: 9390 +Eval (hcp-val): [95] [61/62] eta: 0:00:00 loss: 0.8265 (0.8279) time: 0.1416 data: 0.1165 max mem: 9390 +Eval (hcp-val): [95] Total time: 0:00:14 (0.2343 s / it) +Averaged stats (hcp-val): loss: 0.8265 (0.8279) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +Train: [96] [ 0/6250] eta: 11:14:39 lr: 0.000001 grad: 0.2631 (0.2631) loss: 0.8435 (0.8435) time: 6.4767 data: 6.2605 max mem: 9390 +Train: [96] [ 100/6250] eta: 0:26:20 lr: 0.000001 grad: 0.1590 (0.1988) loss: 0.8266 (0.8195) time: 0.1532 data: 0.0464 max mem: 9390 +Train: [96] [ 200/6250] eta: 0:23:07 lr: 0.000001 grad: 0.1623 (0.1833) loss: 0.8189 (0.8206) time: 0.2730 data: 0.1672 max mem: 9390 +Train: [96] [ 300/6250] eta: 0:22:18 lr: 0.000001 grad: 0.1478 (0.1778) loss: 0.8199 (0.8185) time: 0.2714 data: 0.1599 max mem: 9390 +Train: [96] [ 400/6250] eta: 0:20:50 lr: 0.000001 grad: 0.1686 (0.1751) loss: 0.8086 (0.8178) time: 0.2530 data: 0.1503 max mem: 9390 +Train: [96] [ 500/6250] eta: 0:19:24 lr: 0.000001 grad: 0.1513 (0.1726) loss: 0.8156 (0.8173) time: 0.1657 data: 0.0485 max mem: 9390 +Train: [96] [ 600/6250] eta: 0:20:35 lr: 0.000001 grad: 0.1492 (0.1697) loss: 0.8207 (0.8176) time: 0.2191 data: 0.1252 max mem: 9390 +Train: [96] [ 700/6250] eta: 0:19:34 lr: 0.000001 grad: 0.1452 (0.1669) loss: 0.8179 (0.8182) time: 0.1721 data: 0.0758 max mem: 9390 +Train: [96] [ 800/6250] eta: 0:18:46 lr: 0.000001 grad: 0.1389 (0.1652) loss: 0.8199 (0.8183) time: 0.2120 data: 0.1127 max mem: 9390 +Train: [96] [ 900/6250] eta: 0:18:26 lr: 0.000001 grad: 0.1351 (0.1629) loss: 0.8155 (0.8185) time: 0.3944 data: 0.3132 max mem: 9390 +Train: [96] [1000/6250] eta: 0:18:02 lr: 0.000001 grad: 0.1372 (0.1611) loss: 0.8179 (0.8185) time: 0.3336 data: 0.2184 max mem: 9390 +Train: [96] [1100/6250] eta: 0:17:14 lr: 0.000000 grad: 0.1366 (0.1597) loss: 0.8219 (0.8185) time: 0.1730 data: 0.0906 max mem: 9390 +Train: [96] [1200/6250] eta: 0:16:46 lr: 0.000000 grad: 0.1449 (0.1586) loss: 0.8201 (0.8184) time: 0.1673 data: 0.0727 max mem: 9390 +Train: [96] [1300/6250] eta: 0:16:06 lr: 0.000000 grad: 0.1450 (0.1576) loss: 0.8155 (0.8182) time: 0.1698 data: 0.0812 max mem: 9390 +Train: [96] [1400/6250] eta: 0:15:42 lr: 0.000000 grad: 0.1364 (0.1564) loss: 0.8187 (0.8182) time: 0.1055 data: 0.0002 max mem: 9390 +Train: [96] [1500/6250] eta: 0:15:13 lr: 0.000000 grad: 0.1418 (0.1556) loss: 0.8187 (0.8182) time: 0.1681 data: 0.0770 max mem: 9390 +Train: [96] [1600/6250] eta: 0:14:47 lr: 0.000000 grad: 0.1411 (0.1548) loss: 0.8172 (0.8183) time: 0.1877 data: 0.0932 max mem: 9390 +Train: [96] [1700/6250] eta: 0:14:19 lr: 0.000000 grad: 0.1479 (0.1542) loss: 0.8212 (0.8183) time: 0.1150 data: 0.0303 max mem: 9390 +Train: [96] [1800/6250] eta: 0:13:58 lr: 0.000000 grad: 0.1454 (0.1537) loss: 0.8150 (0.8182) time: 0.2091 data: 0.1116 max mem: 9390 +Train: [96] [1900/6250] eta: 0:13:42 lr: 0.000000 grad: 0.1410 (0.1532) loss: 0.8183 (0.8183) time: 0.1609 data: 0.0723 max mem: 9390 +Train: [96] [2000/6250] eta: 0:13:20 lr: 0.000000 grad: 0.1353 (0.1527) loss: 0.8174 (0.8184) time: 0.1916 data: 0.0926 max mem: 9390 +Train: [96] [2100/6250] eta: 0:12:54 lr: 0.000000 grad: 0.1416 (0.1522) loss: 0.8212 (0.8186) time: 0.1305 data: 0.0473 max mem: 9390 +Train: [96] [2200/6250] eta: 0:12:43 lr: 0.000000 grad: 0.1285 (0.1517) loss: 0.8222 (0.8186) time: 0.1183 data: 0.0129 max mem: 9390 +Train: [96] [2300/6250] eta: 0:12:19 lr: 0.000000 grad: 0.1383 (0.1512) loss: 0.8200 (0.8187) time: 0.1454 data: 0.0548 max mem: 9390 +Train: [96] [2400/6250] eta: 0:11:57 lr: 0.000000 grad: 0.1308 (0.1508) loss: 0.8189 (0.8187) time: 0.1906 data: 0.1113 max mem: 9390 +Train: [96] [2500/6250] eta: 0:11:35 lr: 0.000000 grad: 0.1450 (0.1505) loss: 0.8150 (0.8186) time: 0.1080 data: 0.0168 max mem: 9390 +Train: [96] [2600/6250] eta: 0:11:16 lr: 0.000000 grad: 0.1370 (0.1503) loss: 0.8196 (0.8186) time: 0.2079 data: 0.1231 max mem: 9390 +Train: [96] [2700/6250] eta: 0:10:53 lr: 0.000000 grad: 0.1371 (0.1503) loss: 0.8174 (0.8185) time: 0.2001 data: 0.1090 max mem: 9390 +Train: [96] [2800/6250] eta: 0:10:35 lr: 0.000000 grad: 0.1458 (0.1501) loss: 0.8101 (0.8184) time: 0.1881 data: 0.1060 max mem: 9390 +Train: [96] [2900/6250] eta: 0:10:14 lr: 0.000000 grad: 0.1392 (0.1500) loss: 0.8203 (0.8183) time: 0.1324 data: 0.0464 max mem: 9390 +Train: [96] [3000/6250] eta: 0:09:53 lr: 0.000000 grad: 0.1472 (0.1499) loss: 0.8186 (0.8183) time: 0.1620 data: 0.0791 max mem: 9390 +Train: [96] [3100/6250] eta: 0:09:33 lr: 0.000000 grad: 0.1424 (0.1499) loss: 0.8129 (0.8181) time: 0.1791 data: 0.0948 max mem: 9390 +Train: [96] [3200/6250] eta: 0:09:13 lr: 0.000000 grad: 0.1427 (0.1497) loss: 0.8152 (0.8180) time: 0.1660 data: 0.0783 max mem: 9390 +Train: [96] [3300/6250] eta: 0:08:53 lr: 0.000000 grad: 0.1447 (0.1497) loss: 0.8138 (0.8179) time: 0.1499 data: 0.0722 max mem: 9390 +Train: [96] [3400/6250] eta: 0:08:33 lr: 0.000000 grad: 0.1354 (0.1495) loss: 0.8187 (0.8179) time: 0.1507 data: 0.0753 max mem: 9390 +Train: [96] [3500/6250] eta: 0:08:14 lr: 0.000000 grad: 0.1430 (0.1495) loss: 0.8178 (0.8178) time: 0.1126 data: 0.0003 max mem: 9390 +Train: [96] [3600/6250] eta: 0:07:54 lr: 0.000000 grad: 0.1391 (0.1495) loss: 0.8132 (0.8177) time: 0.1527 data: 0.0701 max mem: 9390 +Train: [96] [3700/6250] eta: 0:07:35 lr: 0.000000 grad: 0.1452 (0.1495) loss: 0.8175 (0.8177) time: 0.1447 data: 0.0550 max mem: 9390 +Train: [96] [3800/6250] eta: 0:07:16 lr: 0.000000 grad: 0.1445 (0.1494) loss: 0.8140 (0.8176) time: 0.1403 data: 0.0574 max mem: 9390 +Train: [96] [3900/6250] eta: 0:06:56 lr: 0.000000 grad: 0.1432 (0.1493) loss: 0.8094 (0.8175) time: 0.1234 data: 0.0382 max mem: 9390 +Train: [96] [4000/6250] eta: 0:06:37 lr: 0.000000 grad: 0.1361 (0.1493) loss: 0.8181 (0.8174) time: 0.1512 data: 0.0481 max mem: 9390 +Train: [96] [4100/6250] eta: 0:06:17 lr: 0.000000 grad: 0.1439 (0.1492) loss: 0.8103 (0.8173) time: 0.1357 data: 0.0527 max mem: 9390 +Train: [96] [4200/6250] eta: 0:05:59 lr: 0.000000 grad: 0.1469 (0.1493) loss: 0.8119 (0.8172) time: 0.1632 data: 0.0776 max mem: 9390 +Train: [96] [4300/6250] eta: 0:05:40 lr: 0.000000 grad: 0.1458 (0.1493) loss: 0.8137 (0.8171) time: 0.1160 data: 0.0333 max mem: 9390 +Train: [96] [4400/6250] eta: 0:05:23 lr: 0.000000 grad: 0.1406 (0.1493) loss: 0.8138 (0.8170) time: 0.1232 data: 0.0350 max mem: 9390 +Train: [96] [4500/6250] eta: 0:05:04 lr: 0.000000 grad: 0.1506 (0.1493) loss: 0.8109 (0.8169) time: 0.1581 data: 0.0785 max mem: 9390 +Train: [96] [4600/6250] eta: 0:04:46 lr: 0.000000 grad: 0.1385 (0.1495) loss: 0.8147 (0.8168) time: 0.1534 data: 0.0611 max mem: 9390 +Train: [96] [4700/6250] eta: 0:04:29 lr: 0.000000 grad: 0.1509 (0.1496) loss: 0.8158 (0.8167) time: 0.1494 data: 0.0514 max mem: 9390 +Train: [96] [4800/6250] eta: 0:04:11 lr: 0.000000 grad: 0.1403 (0.1496) loss: 0.8183 (0.8167) time: 0.1666 data: 0.0825 max mem: 9390 +Train: [96] [4900/6250] eta: 0:03:53 lr: 0.000000 grad: 0.1520 (0.1497) loss: 0.8115 (0.8166) time: 0.1636 data: 0.0733 max mem: 9390 +Train: [96] [5000/6250] eta: 0:03:36 lr: 0.000000 grad: 0.1464 (0.1497) loss: 0.8173 (0.8166) time: 0.1559 data: 0.0748 max mem: 9390 +Train: [96] [5100/6250] eta: 0:03:19 lr: 0.000000 grad: 0.1413 (0.1496) loss: 0.8187 (0.8166) time: 0.3318 data: 0.2570 max mem: 9390 +Train: [96] [5200/6250] eta: 0:03:01 lr: 0.000000 grad: 0.1385 (0.1495) loss: 0.8217 (0.8165) time: 0.1459 data: 0.0594 max mem: 9390 +Train: [96] [5300/6250] eta: 0:02:44 lr: 0.000000 grad: 0.1417 (0.1494) loss: 0.8120 (0.8165) time: 0.1712 data: 0.0877 max mem: 9390 +Train: [96] [5400/6250] eta: 0:02:27 lr: 0.000000 grad: 0.1358 (0.1493) loss: 0.8215 (0.8166) time: 0.1646 data: 0.0794 max mem: 9390 +Train: [96] [5500/6250] eta: 0:02:10 lr: 0.000000 grad: 0.1409 (0.1491) loss: 0.8197 (0.8166) time: 0.3035 data: 0.2230 max mem: 9390 +Train: [96] [5600/6250] eta: 0:01:52 lr: 0.000000 grad: 0.1427 (0.1490) loss: 0.8198 (0.8166) time: 0.1790 data: 0.1058 max mem: 9390 +Train: [96] [5700/6250] eta: 0:01:35 lr: 0.000000 grad: 0.1327 (0.1490) loss: 0.8206 (0.8167) time: 0.1831 data: 0.1026 max mem: 9390 +Train: [96] [5800/6250] eta: 0:01:17 lr: 0.000000 grad: 0.1470 (0.1489) loss: 0.8188 (0.8167) time: 0.1695 data: 0.0878 max mem: 9390 +Train: [96] [5900/6250] eta: 0:01:00 lr: 0.000000 grad: 0.1510 (0.1489) loss: 0.8167 (0.8167) time: 0.1586 data: 0.0785 max mem: 9390 +Train: [96] [6000/6250] eta: 0:00:43 lr: 0.000000 grad: 0.1366 (0.1489) loss: 0.8187 (0.8167) time: 0.1342 data: 0.0556 max mem: 9390 +Train: [96] [6100/6250] eta: 0:00:25 lr: 0.000000 grad: 0.1380 (0.1488) loss: 0.8201 (0.8168) time: 0.3614 data: 0.2572 max mem: 9390 +Train: [96] [6200/6250] eta: 0:00:08 lr: 0.000000 grad: 0.1423 (0.1488) loss: 0.8206 (0.8168) time: 0.1589 data: 0.0773 max mem: 9390 +Train: [96] [6249/6250] eta: 0:00:00 lr: 0.000000 grad: 0.1423 (0.1488) loss: 0.8253 (0.8169) time: 0.1882 data: 0.1005 max mem: 9390 +Train: [96] Total time: 0:18:08 (0.1742 s / it) +Averaged stats: lr: 0.000000 grad: 0.1423 (0.1488) loss: 0.8253 (0.8169) +Eval (hcp-train-subset): [96] [ 0/62] eta: 0:04:08 loss: 0.8259 (0.8259) time: 4.0074 data: 3.9151 max mem: 9390 +Eval (hcp-train-subset): [96] [61/62] eta: 0:00:00 loss: 0.8129 (0.8170) time: 0.1475 data: 0.1221 max mem: 9390 +Eval (hcp-train-subset): [96] Total time: 0:00:15 (0.2436 s / it) +Averaged stats (hcp-train-subset): loss: 0.8129 (0.8170) +Eval (hcp-val): [96] [ 0/62] eta: 0:04:13 loss: 0.8236 (0.8236) time: 4.0857 data: 3.9963 max mem: 9390 +Eval (hcp-val): [96] [61/62] eta: 0:00:00 loss: 0.8265 (0.8277) time: 0.1541 data: 0.1275 max mem: 9390 +Eval (hcp-val): [96] Total time: 0:00:16 (0.2587 s / it) +Averaged stats (hcp-val): loss: 0.8265 (0.8277) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +Train: [97] [ 0/6250] eta: 9:13:04 lr: 0.000000 grad: 0.0976 (0.0976) loss: 0.8107 (0.8107) time: 5.3095 data: 5.0119 max mem: 9390 +Train: [97] [ 100/6250] eta: 0:35:26 lr: 0.000000 grad: 0.1647 (0.2022) loss: 0.8162 (0.8140) time: 0.1463 data: 0.0292 max mem: 9390 +Train: [97] [ 200/6250] eta: 0:26:53 lr: 0.000000 grad: 0.1463 (0.1811) loss: 0.8186 (0.8154) time: 0.2102 data: 0.1168 max mem: 9390 +Train: [97] [ 300/6250] eta: 0:23:26 lr: 0.000000 grad: 0.1642 (0.1776) loss: 0.8247 (0.8163) time: 0.1821 data: 0.0929 max mem: 9390 +Train: [97] [ 400/6250] eta: 0:22:08 lr: 0.000000 grad: 0.1557 (0.1728) loss: 0.8190 (0.8169) time: 0.1975 data: 0.0911 max mem: 9390 +Train: [97] [ 500/6250] eta: 0:20:27 lr: 0.000000 grad: 0.1577 (0.1682) loss: 0.8197 (0.8175) time: 0.1550 data: 0.0620 max mem: 9390 +Train: [97] [ 600/6250] eta: 0:19:31 lr: 0.000000 grad: 0.1398 (0.1661) loss: 0.8255 (0.8178) time: 0.1079 data: 0.0097 max mem: 9390 +Train: [97] [ 700/6250] eta: 0:19:09 lr: 0.000000 grad: 0.1320 (0.1637) loss: 0.8204 (0.8181) time: 0.2811 data: 0.1888 max mem: 9390 +Train: [97] [ 800/6250] eta: 0:18:25 lr: 0.000000 grad: 0.1364 (0.1620) loss: 0.8180 (0.8182) time: 0.2023 data: 0.1042 max mem: 9390 +Train: [97] [ 900/6250] eta: 0:18:21 lr: 0.000000 grad: 0.1476 (0.1605) loss: 0.8178 (0.8182) time: 0.2562 data: 0.1422 max mem: 9390 +Train: [97] [1000/6250] eta: 0:17:31 lr: 0.000000 grad: 0.1502 (0.1594) loss: 0.8127 (0.8179) time: 0.1653 data: 0.0846 max mem: 9390 +Train: [97] [1100/6250] eta: 0:17:02 lr: 0.000000 grad: 0.1455 (0.1584) loss: 0.8169 (0.8179) time: 0.0904 data: 0.0002 max mem: 9390 +Train: [97] [1200/6250] eta: 0:17:03 lr: 0.000000 grad: 0.1432 (0.1574) loss: 0.8071 (0.8176) time: 0.2222 data: 0.1151 max mem: 9390 +Train: [97] [1300/6250] eta: 0:16:44 lr: 0.000000 grad: 0.1368 (0.1567) loss: 0.8186 (0.8176) time: 0.1504 data: 0.0603 max mem: 9390 +Train: [97] [1400/6250] eta: 0:16:06 lr: 0.000000 grad: 0.1439 (0.1561) loss: 0.8195 (0.8175) time: 0.1663 data: 0.0843 max mem: 9390 +Train: [97] [1500/6250] eta: 0:15:48 lr: 0.000000 grad: 0.1422 (0.1555) loss: 0.8210 (0.8175) time: 0.3549 data: 0.2574 max mem: 9390 +Train: [97] [1600/6250] eta: 0:15:26 lr: 0.000000 grad: 0.1339 (0.1549) loss: 0.8164 (0.8175) time: 0.0940 data: 0.0004 max mem: 9390 +Train: [97] [1700/6250] eta: 0:14:54 lr: 0.000000 grad: 0.1298 (0.1544) loss: 0.8184 (0.8174) time: 0.1299 data: 0.0379 max mem: 9390 +Train: [97] [1800/6250] eta: 0:14:25 lr: 0.000000 grad: 0.1510 (0.1539) loss: 0.8122 (0.8173) time: 0.1626 data: 0.0772 max mem: 9390 +Train: [97] [1900/6250] eta: 0:14:00 lr: 0.000000 grad: 0.1358 (0.1535) loss: 0.8111 (0.8171) time: 0.0903 data: 0.0002 max mem: 9390 +Train: [97] [2000/6250] eta: 0:13:35 lr: 0.000000 grad: 0.1381 (0.1532) loss: 0.8148 (0.8170) time: 0.1931 data: 0.1097 max mem: 9390 +Train: [97] [2100/6250] eta: 0:13:21 lr: 0.000000 grad: 0.1361 (0.1527) loss: 0.8221 (0.8170) time: 0.1115 data: 0.0321 max mem: 9390 +Train: [97] [2200/6250] eta: 0:12:58 lr: 0.000000 grad: 0.1419 (0.1523) loss: 0.8134 (0.8170) time: 0.2069 data: 0.1192 max mem: 9390 +Train: [97] [2300/6250] eta: 0:12:36 lr: 0.000000 grad: 0.1424 (0.1521) loss: 0.8180 (0.8169) time: 0.2039 data: 0.1227 max mem: 9390 +Train: [97] [2400/6250] eta: 0:12:14 lr: 0.000000 grad: 0.1276 (0.1517) loss: 0.8258 (0.8170) time: 0.1432 data: 0.0551 max mem: 9390 +Train: [97] [2500/6250] eta: 0:11:54 lr: 0.000000 grad: 0.1361 (0.1514) loss: 0.8160 (0.8170) time: 0.2541 data: 0.1662 max mem: 9390 +Train: [97] [2600/6250] eta: 0:11:31 lr: 0.000000 grad: 0.1479 (0.1513) loss: 0.8146 (0.8170) time: 0.1534 data: 0.0635 max mem: 9390 +Train: [97] [2700/6250] eta: 0:11:10 lr: 0.000000 grad: 0.1453 (0.1513) loss: 0.8143 (0.8170) time: 0.1870 data: 0.1027 max mem: 9390 +Train: [97] [2800/6250] eta: 0:11:01 lr: 0.000000 grad: 0.1398 (0.1513) loss: 0.8140 (0.8169) time: 0.3050 data: 0.2150 max mem: 9390 +Train: [97] [2900/6250] eta: 0:10:48 lr: 0.000000 grad: 0.1521 (0.1513) loss: 0.8165 (0.8169) time: 0.2159 data: 0.1032 max mem: 9390 +Train: [97] [3000/6250] eta: 0:10:25 lr: 0.000000 grad: 0.1498 (0.1512) loss: 0.8169 (0.8169) time: 0.1365 data: 0.0384 max mem: 9390 +Train: [97] [3100/6250] eta: 0:10:04 lr: 0.000000 grad: 0.1429 (0.1512) loss: 0.8202 (0.8169) time: 0.1162 data: 0.0297 max mem: 9390 +Train: [97] [3200/6250] eta: 0:09:41 lr: 0.000000 grad: 0.1345 (0.1510) loss: 0.8210 (0.8168) time: 0.1235 data: 0.0417 max mem: 9390 +Train: [97] [3300/6250] eta: 0:09:18 lr: 0.000000 grad: 0.1280 (0.1508) loss: 0.8230 (0.8169) time: 0.1170 data: 0.0280 max mem: 9390 +Train: [97] [3400/6250] eta: 0:08:56 lr: 0.000000 grad: 0.1443 (0.1506) loss: 0.8151 (0.8169) time: 0.1553 data: 0.0648 max mem: 9390 +Train: [97] [3500/6250] eta: 0:08:36 lr: 0.000000 grad: 0.1452 (0.1504) loss: 0.8218 (0.8169) time: 0.1917 data: 0.1097 max mem: 9390 +Train: [97] [3600/6250] eta: 0:08:16 lr: 0.000000 grad: 0.1436 (0.1502) loss: 0.8209 (0.8170) time: 0.1850 data: 0.1046 max mem: 9390 +Train: [97] [3700/6250] eta: 0:07:59 lr: 0.000000 grad: 0.1377 (0.1500) loss: 0.8183 (0.8170) time: 0.2912 data: 0.2156 max mem: 9390 +Train: [97] [3800/6250] eta: 0:07:40 lr: 0.000000 grad: 0.1369 (0.1498) loss: 0.8186 (0.8170) time: 0.1399 data: 0.0577 max mem: 9390 +Train: [97] [3900/6250] eta: 0:07:20 lr: 0.000000 grad: 0.1330 (0.1495) loss: 0.8215 (0.8171) time: 0.2120 data: 0.1312 max mem: 9390 +Train: [97] [4000/6250] eta: 0:07:01 lr: 0.000000 grad: 0.1348 (0.1492) loss: 0.8209 (0.8172) time: 0.1776 data: 0.0972 max mem: 9390 +Train: [97] [4100/6250] eta: 0:06:42 lr: 0.000000 grad: 0.1336 (0.1489) loss: 0.8250 (0.8173) time: 0.2097 data: 0.1315 max mem: 9390 +Train: [97] [4200/6250] eta: 0:06:23 lr: 0.000000 grad: 0.1357 (0.1487) loss: 0.8202 (0.8173) time: 0.1786 data: 0.0878 max mem: 9390 +Train: [97] [4300/6250] eta: 0:06:03 lr: 0.000000 grad: 0.1361 (0.1485) loss: 0.8173 (0.8173) time: 0.1797 data: 0.0867 max mem: 9390 +Train: [97] [4400/6250] eta: 0:05:44 lr: 0.000000 grad: 0.1394 (0.1484) loss: 0.8180 (0.8174) time: 0.2107 data: 0.1272 max mem: 9390 +Train: [97] [4500/6250] eta: 0:05:26 lr: 0.000000 grad: 0.1304 (0.1482) loss: 0.8205 (0.8174) time: 0.1051 data: 0.0177 max mem: 9390 +Train: [97] [4600/6250] eta: 0:05:08 lr: 0.000000 grad: 0.1406 (0.1480) loss: 0.8159 (0.8174) time: 0.1003 data: 0.0002 max mem: 9390 +Train: [97] [4700/6250] eta: 0:04:48 lr: 0.000000 grad: 0.1291 (0.1478) loss: 0.8192 (0.8175) time: 0.1786 data: 0.0895 max mem: 9390 +Train: [97] [4800/6250] eta: 0:04:29 lr: 0.000000 grad: 0.1356 (0.1476) loss: 0.8201 (0.8175) time: 0.1365 data: 0.0511 max mem: 9390 +Train: [97] [4900/6250] eta: 0:04:11 lr: 0.000000 grad: 0.1330 (0.1474) loss: 0.8213 (0.8175) time: 0.1292 data: 0.0352 max mem: 9390 +Train: [97] [5000/6250] eta: 0:03:53 lr: 0.000000 grad: 0.1380 (0.1473) loss: 0.8138 (0.8175) time: 0.2515 data: 0.1665 max mem: 9390 +Train: [97] [5100/6250] eta: 0:03:34 lr: 0.000000 grad: 0.1431 (0.1473) loss: 0.8123 (0.8174) time: 0.2124 data: 0.1106 max mem: 9390 +Train: [97] [5200/6250] eta: 0:03:14 lr: 0.000000 grad: 0.1427 (0.1473) loss: 0.8181 (0.8174) time: 0.1442 data: 0.0523 max mem: 9390 +Train: [97] [5300/6250] eta: 0:02:56 lr: 0.000000 grad: 0.1429 (0.1472) loss: 0.8142 (0.8174) time: 0.1584 data: 0.0562 max mem: 9390 +Train: [97] [5400/6250] eta: 0:02:37 lr: 0.000000 grad: 0.1401 (0.1471) loss: 0.8140 (0.8173) time: 0.1187 data: 0.0199 max mem: 9390 +Train: [97] [5500/6250] eta: 0:02:18 lr: 0.000000 grad: 0.1386 (0.1471) loss: 0.8176 (0.8173) time: 0.1228 data: 0.0481 max mem: 9390 +Train: [97] [5600/6250] eta: 0:01:59 lr: 0.000000 grad: 0.1416 (0.1470) loss: 0.8146 (0.8173) time: 0.1394 data: 0.0551 max mem: 9390 +Train: [97] [5700/6250] eta: 0:01:41 lr: 0.000000 grad: 0.1368 (0.1469) loss: 0.8151 (0.8173) time: 0.1474 data: 0.0535 max mem: 9390 +Train: [97] [5800/6250] eta: 0:01:22 lr: 0.000000 grad: 0.1460 (0.1469) loss: 0.8180 (0.8172) time: 0.1588 data: 0.0797 max mem: 9390 +Train: [97] [5900/6250] eta: 0:01:04 lr: 0.000000 grad: 0.1378 (0.1469) loss: 0.8177 (0.8171) time: 0.1347 data: 0.0527 max mem: 9390 +Train: [97] [6000/6250] eta: 0:00:45 lr: 0.000000 grad: 0.1507 (0.1469) loss: 0.8133 (0.8171) time: 0.1308 data: 0.0435 max mem: 9390 +Train: [97] [6100/6250] eta: 0:00:27 lr: 0.000000 grad: 0.1419 (0.1469) loss: 0.8105 (0.8170) time: 0.1871 data: 0.1057 max mem: 9390 +Train: [97] [6200/6250] eta: 0:00:09 lr: 0.000000 grad: 0.1468 (0.1469) loss: 0.8186 (0.8169) time: 0.0954 data: 0.0002 max mem: 9390 +Train: [97] [6249/6250] eta: 0:00:00 lr: 0.000000 grad: 0.1468 (0.1469) loss: 0.8082 (0.8169) time: 0.1178 data: 0.0255 max mem: 9390 +Train: [97] Total time: 0:19:14 (0.1847 s / it) +Averaged stats: lr: 0.000000 grad: 0.1468 (0.1469) loss: 0.8082 (0.8169) +Eval (hcp-train-subset): [97] [ 0/62] eta: 0:15:12 loss: 0.8254 (0.8254) time: 14.7156 data: 14.6861 max mem: 9390 +Eval (hcp-train-subset): [97] [61/62] eta: 0:00:00 loss: 0.8129 (0.8166) time: 0.1425 data: 0.1174 max mem: 9390 +Eval (hcp-train-subset): [97] Total time: 0:00:24 (0.3919 s / it) +Averaged stats (hcp-train-subset): loss: 0.8129 (0.8166) +Eval (hcp-val): [97] [ 0/62] eta: 0:05:31 loss: 0.8260 (0.8260) time: 5.3472 data: 5.3162 max mem: 9390 +Eval (hcp-val): [97] [61/62] eta: 0:00:00 loss: 0.8252 (0.8276) time: 0.1476 data: 0.1182 max mem: 9390 +Eval (hcp-val): [97] Total time: 0:00:15 (0.2545 s / it) +Averaged stats (hcp-val): loss: 0.8252 (0.8276) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +Train: [98] [ 0/6250] eta: 1 day, 0:50:39 lr: 0.000000 grad: 0.2241 (0.2241) loss: 0.7956 (0.7956) time: 14.3103 data: 14.1776 max mem: 9390 +Train: [98] [ 100/6250] eta: 0:44:59 lr: 0.000000 grad: 0.1386 (0.1691) loss: 0.8192 (0.8170) time: 0.2126 data: 0.0695 max mem: 9390 +Train: [98] [ 200/6250] eta: 0:34:04 lr: 0.000000 grad: 0.1590 (0.1637) loss: 0.8133 (0.8161) time: 0.1935 data: 0.0474 max mem: 9390 +Train: [98] [ 300/6250] eta: 0:30:58 lr: 0.000000 grad: 0.1487 (0.1642) loss: 0.8112 (0.8139) time: 0.2186 data: 0.1227 max mem: 9390 +Train: [98] [ 400/6250] eta: 0:27:01 lr: 0.000000 grad: 0.1545 (0.1646) loss: 0.8073 (0.8132) time: 0.1654 data: 0.0645 max mem: 9390 +Train: [98] [ 500/6250] eta: 0:25:29 lr: 0.000000 grad: 0.1498 (0.1636) loss: 0.8110 (0.8127) time: 0.4234 data: 0.3104 max mem: 9390 +Train: [98] [ 600/6250] eta: 0:23:20 lr: 0.000000 grad: 0.1435 (0.1617) loss: 0.8138 (0.8125) time: 0.1656 data: 0.0662 max mem: 9390 +Train: [98] [ 700/6250] eta: 0:22:03 lr: 0.000000 grad: 0.1583 (0.1595) loss: 0.8192 (0.8129) time: 0.1305 data: 0.0418 max mem: 9390 +Train: [98] [ 800/6250] eta: 0:21:20 lr: 0.000000 grad: 0.1449 (0.1585) loss: 0.8167 (0.8133) time: 0.0906 data: 0.0004 max mem: 9390 +Train: [98] [ 900/6250] eta: 0:20:36 lr: 0.000000 grad: 0.1424 (0.1573) loss: 0.8207 (0.8138) time: 0.2726 data: 0.1662 max mem: 9390 +Train: [98] [1000/6250] eta: 0:20:13 lr: 0.000000 grad: 0.1481 (0.1570) loss: 0.8161 (0.8141) time: 0.1252 data: 0.0114 max mem: 9390 +Train: [98] [1100/6250] eta: 0:19:26 lr: 0.000000 grad: 0.1553 (0.1570) loss: 0.8151 (0.8142) time: 0.1191 data: 0.0122 max mem: 9390 +Train: [98] [1200/6250] eta: 0:18:39 lr: 0.000000 grad: 0.1338 (0.1561) loss: 0.8179 (0.8146) time: 0.1409 data: 0.0460 max mem: 9390 +Train: [98] [1300/6250] eta: 0:18:32 lr: 0.000000 grad: 0.1317 (0.1552) loss: 0.8255 (0.8148) time: 0.1980 data: 0.1017 max mem: 9390 +Train: [98] [1400/6250] eta: 0:17:50 lr: 0.000000 grad: 0.1392 (0.1544) loss: 0.8211 (0.8151) time: 0.1468 data: 0.0531 max mem: 9390 +Train: [98] [1500/6250] eta: 0:17:10 lr: 0.000000 grad: 0.1369 (0.1536) loss: 0.8202 (0.8153) time: 0.1689 data: 0.0784 max mem: 9390 +Train: [98] [1600/6250] eta: 0:16:59 lr: 0.000000 grad: 0.1396 (0.1531) loss: 0.8202 (0.8155) time: 0.2022 data: 0.1016 max mem: 9390 +Train: [98] [1700/6250] eta: 0:16:16 lr: 0.000000 grad: 0.1358 (0.1525) loss: 0.8207 (0.8158) time: 0.1348 data: 0.0446 max mem: 9390 +Train: [98] [1800/6250] eta: 0:15:43 lr: 0.000000 grad: 0.1408 (0.1520) loss: 0.8160 (0.8158) time: 0.1795 data: 0.0945 max mem: 9390 +Train: [98] [1900/6250] eta: 0:15:19 lr: 0.000000 grad: 0.1407 (0.1513) loss: 0.8180 (0.8160) time: 0.1066 data: 0.0003 max mem: 9390 +Train: [98] [2000/6250] eta: 0:14:48 lr: 0.000000 grad: 0.1378 (0.1508) loss: 0.8169 (0.8161) time: 0.1214 data: 0.0424 max mem: 9390 +Train: [98] [2100/6250] eta: 0:14:16 lr: 0.000000 grad: 0.1336 (0.1504) loss: 0.8168 (0.8161) time: 0.1625 data: 0.0786 max mem: 9390 +Train: [98] [2200/6250] eta: 0:13:49 lr: 0.000000 grad: 0.1316 (0.1499) loss: 0.8178 (0.8162) time: 0.1311 data: 0.0337 max mem: 9390 +Train: [98] [2300/6250] eta: 0:13:29 lr: 0.000000 grad: 0.1360 (0.1492) loss: 0.8198 (0.8164) time: 0.1366 data: 0.0614 max mem: 9390 +Train: [98] [2400/6250] eta: 0:13:00 lr: 0.000000 grad: 0.1356 (0.1489) loss: 0.8217 (0.8166) time: 0.1596 data: 0.0787 max mem: 9390 +Train: [98] [2500/6250] eta: 0:12:35 lr: 0.000000 grad: 0.1368 (0.1485) loss: 0.8181 (0.8167) time: 0.1862 data: 0.0995 max mem: 9390 +Train: [98] [2600/6250] eta: 0:12:11 lr: 0.000000 grad: 0.1380 (0.1483) loss: 0.8196 (0.8168) time: 0.1684 data: 0.0855 max mem: 9390 +Train: [98] [2700/6250] eta: 0:11:50 lr: 0.000000 grad: 0.1348 (0.1481) loss: 0.8181 (0.8169) time: 0.2622 data: 0.1635 max mem: 9390 +Train: [98] [2800/6250] eta: 0:11:28 lr: 0.000000 grad: 0.1388 (0.1479) loss: 0.8177 (0.8170) time: 0.1134 data: 0.0178 max mem: 9390 +Train: [98] [2900/6250] eta: 0:11:09 lr: 0.000000 grad: 0.1364 (0.1477) loss: 0.8176 (0.8172) time: 0.2500 data: 0.1518 max mem: 9390 +Train: [98] [3000/6250] eta: 0:10:47 lr: 0.000000 grad: 0.1332 (0.1474) loss: 0.8241 (0.8173) time: 0.1418 data: 0.0329 max mem: 9390 +Train: [98] [3100/6250] eta: 0:10:24 lr: 0.000000 grad: 0.1395 (0.1472) loss: 0.8214 (0.8174) time: 0.1359 data: 0.0334 max mem: 9390 +Train: [98] [3200/6250] eta: 0:10:02 lr: 0.000000 grad: 0.1377 (0.1470) loss: 0.8181 (0.8175) time: 0.1215 data: 0.0205 max mem: 9390 +Train: [98] [3300/6250] eta: 0:09:37 lr: 0.000000 grad: 0.1352 (0.1468) loss: 0.8222 (0.8176) time: 0.1358 data: 0.0539 max mem: 9390 +Train: [98] [3400/6250] eta: 0:09:14 lr: 0.000000 grad: 0.1366 (0.1466) loss: 0.8147 (0.8177) time: 0.1362 data: 0.0503 max mem: 9390 +Train: [98] [3500/6250] eta: 0:08:51 lr: 0.000000 grad: 0.1459 (0.1464) loss: 0.8203 (0.8178) time: 0.1425 data: 0.0627 max mem: 9390 +Train: [98] [3600/6250] eta: 0:08:31 lr: 0.000000 grad: 0.1406 (0.1462) loss: 0.8191 (0.8179) time: 0.1927 data: 0.1122 max mem: 9390 +Train: [98] [3700/6250] eta: 0:08:10 lr: 0.000000 grad: 0.1408 (0.1460) loss: 0.8193 (0.8179) time: 0.1740 data: 0.0918 max mem: 9390 +Train: [98] [3800/6250] eta: 0:07:51 lr: 0.000000 grad: 0.1403 (0.1459) loss: 0.8165 (0.8179) time: 0.2497 data: 0.1738 max mem: 9390 +Train: [98] [3900/6250] eta: 0:07:32 lr: 0.000000 grad: 0.1354 (0.1458) loss: 0.8234 (0.8180) time: 0.1342 data: 0.0558 max mem: 9390 +Train: [98] [4000/6250] eta: 0:07:13 lr: 0.000000 grad: 0.1332 (0.1457) loss: 0.8256 (0.8180) time: 0.1395 data: 0.0653 max mem: 9390 +Train: [98] [4100/6250] eta: 0:06:53 lr: 0.000000 grad: 0.1349 (0.1456) loss: 0.8203 (0.8181) time: 0.0861 data: 0.0002 max mem: 9390 +Train: [98] [4200/6250] eta: 0:06:33 lr: 0.000000 grad: 0.1418 (0.1456) loss: 0.8208 (0.8181) time: 0.1805 data: 0.1008 max mem: 9390 +Train: [98] [4300/6250] eta: 0:06:13 lr: 0.000000 grad: 0.1412 (0.1457) loss: 0.8190 (0.8182) time: 0.1708 data: 0.0809 max mem: 9390 +Train: [98] [4400/6250] eta: 0:05:52 lr: 0.000000 grad: 0.1458 (0.1457) loss: 0.8170 (0.8182) time: 0.1179 data: 0.0039 max mem: 9390 +Train: [98] [4500/6250] eta: 0:05:33 lr: 0.000000 grad: 0.1369 (0.1458) loss: 0.8145 (0.8182) time: 0.1740 data: 0.0828 max mem: 9390 +Train: [98] [4600/6250] eta: 0:05:14 lr: 0.000000 grad: 0.1447 (0.1459) loss: 0.8205 (0.8182) time: 0.1434 data: 0.0663 max mem: 9390 +Train: [98] [4700/6250] eta: 0:04:56 lr: 0.000000 grad: 0.1450 (0.1459) loss: 0.8181 (0.8182) time: 0.2809 data: 0.1958 max mem: 9390 +Train: [98] [4800/6250] eta: 0:04:36 lr: 0.000000 grad: 0.1541 (0.1460) loss: 0.8192 (0.8182) time: 0.2824 data: 0.1933 max mem: 9390 +Train: [98] [4900/6250] eta: 0:04:17 lr: 0.000000 grad: 0.1342 (0.1459) loss: 0.8189 (0.8182) time: 0.1057 data: 0.0002 max mem: 9390 +Train: [98] [5000/6250] eta: 0:04:01 lr: 0.000000 grad: 0.1422 (0.1459) loss: 0.8216 (0.8182) time: 0.7464 data: 0.6550 max mem: 9390 +Train: [98] [5100/6250] eta: 0:03:41 lr: 0.000000 grad: 0.1383 (0.1459) loss: 0.8221 (0.8182) time: 0.1446 data: 0.0307 max mem: 9390 +Train: [98] [5200/6250] eta: 0:03:22 lr: 0.000000 grad: 0.1579 (0.1459) loss: 0.8140 (0.8182) time: 0.2818 data: 0.1937 max mem: 9390 +Train: [98] [5300/6250] eta: 0:03:02 lr: 0.000000 grad: 0.1409 (0.1459) loss: 0.8235 (0.8182) time: 0.1315 data: 0.0441 max mem: 9390 +Train: [98] [5400/6250] eta: 0:02:43 lr: 0.000000 grad: 0.1412 (0.1459) loss: 0.8168 (0.8182) time: 0.3500 data: 0.2586 max mem: 9390 +Train: [98] [5500/6250] eta: 0:02:23 lr: 0.000000 grad: 0.1361 (0.1458) loss: 0.8269 (0.8182) time: 0.2097 data: 0.1114 max mem: 9390 +Train: [98] [5600/6250] eta: 0:02:04 lr: 0.000000 grad: 0.1349 (0.1458) loss: 0.8242 (0.8183) time: 0.1608 data: 0.0689 max mem: 9390 +Train: [98] [5700/6250] eta: 0:01:45 lr: 0.000000 grad: 0.1431 (0.1458) loss: 0.8153 (0.8183) time: 0.1814 data: 0.0902 max mem: 9390 +Train: [98] [5800/6250] eta: 0:01:26 lr: 0.000000 grad: 0.1480 (0.1458) loss: 0.8172 (0.8182) time: 0.1337 data: 0.0432 max mem: 9390 +Train: [98] [5900/6250] eta: 0:01:06 lr: 0.000000 grad: 0.1384 (0.1458) loss: 0.8164 (0.8182) time: 0.1372 data: 0.0533 max mem: 9390 +Train: [98] [6000/6250] eta: 0:00:47 lr: 0.000000 grad: 0.1424 (0.1457) loss: 0.8170 (0.8182) time: 0.1253 data: 0.0398 max mem: 9390 +Train: [98] [6100/6250] eta: 0:00:28 lr: 0.000000 grad: 0.1412 (0.1457) loss: 0.8193 (0.8182) time: 0.1494 data: 0.0646 max mem: 9390 +Train: [98] [6200/6250] eta: 0:00:09 lr: 0.000000 grad: 0.1397 (0.1457) loss: 0.8151 (0.8182) time: 0.1802 data: 0.0978 max mem: 9390 +Train: [98] [6249/6250] eta: 0:00:00 lr: 0.000000 grad: 0.1374 (0.1457) loss: 0.8158 (0.8182) time: 0.1731 data: 0.0894 max mem: 9390 +Train: [98] Total time: 0:19:46 (0.1898 s / it) +Averaged stats: lr: 0.000000 grad: 0.1374 (0.1457) loss: 0.8158 (0.8182) +Eval (hcp-train-subset): [98] [ 0/62] eta: 0:05:06 loss: 0.8242 (0.8242) time: 4.9513 data: 4.9204 max mem: 9390 +Eval (hcp-train-subset): [98] [61/62] eta: 0:00:00 loss: 0.8137 (0.8163) time: 0.1287 data: 0.1026 max mem: 9390 +Eval (hcp-train-subset): [98] Total time: 0:00:13 (0.2125 s / it) +Averaged stats (hcp-train-subset): loss: 0.8137 (0.8163) +Eval (hcp-val): [98] [ 0/62] eta: 0:03:16 loss: 0.8246 (0.8246) time: 3.1736 data: 3.0916 max mem: 9390 +Eval (hcp-val): [98] [61/62] eta: 0:00:00 loss: 0.8263 (0.8276) time: 0.1515 data: 0.1248 max mem: 9390 +Eval (hcp-val): [98] Total time: 0:00:13 (0.2215 s / it) +Averaged stats (hcp-val): loss: 0.8263 (0.8276) +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +Train: [99] [ 0/6250] eta: 10:13:30 lr: 0.000000 grad: 0.3182 (0.3182) loss: 0.7727 (0.7727) time: 5.8897 data: 5.5782 max mem: 9390 +Train: [99] [ 100/6250] eta: 0:26:18 lr: 0.000000 grad: 0.1830 (0.1961) loss: 0.8092 (0.8118) time: 0.1927 data: 0.0836 max mem: 9390 +Train: [99] [ 200/6250] eta: 0:22:37 lr: 0.000000 grad: 0.1755 (0.1950) loss: 0.8105 (0.8096) time: 0.1870 data: 0.0630 max mem: 9390 +Train: [99] [ 300/6250] eta: 0:21:33 lr: 0.000000 grad: 0.1558 (0.1877) loss: 0.8155 (0.8109) time: 0.2129 data: 0.1209 max mem: 9390 +Train: [99] [ 400/6250] eta: 0:20:02 lr: 0.000000 grad: 0.1575 (0.1821) loss: 0.8160 (0.8119) time: 0.1840 data: 0.0936 max mem: 9390 +Train: [99] [ 500/6250] eta: 0:19:21 lr: 0.000000 grad: 0.1393 (0.1763) loss: 0.8222 (0.8132) time: 0.2905 data: 0.1591 max mem: 9390 +Train: [99] [ 600/6250] eta: 0:18:58 lr: 0.000000 grad: 0.1395 (0.1724) loss: 0.8180 (0.8139) time: 0.1313 data: 0.0005 max mem: 9390 +Train: [99] [ 700/6250] eta: 0:18:22 lr: 0.000000 grad: 0.1422 (0.1704) loss: 0.8209 (0.8141) time: 0.1504 data: 0.0309 max mem: 9390 +Train: [99] [ 800/6250] eta: 0:17:56 lr: 0.000000 grad: 0.1594 (0.1687) loss: 0.8217 (0.8141) time: 0.1652 data: 0.0716 max mem: 9390 +Train: [99] [ 900/6250] eta: 0:18:03 lr: 0.000000 grad: 0.1425 (0.1665) loss: 0.8113 (0.8145) time: 0.5280 data: 0.4053 max mem: 9390 +Train: [99] [1000/6250] eta: 0:17:15 lr: 0.000000 grad: 0.1531 (0.1649) loss: 0.8170 (0.8148) time: 0.1822 data: 0.1016 max mem: 9390 +Train: [99] [1100/6250] eta: 0:16:41 lr: 0.000000 grad: 0.1471 (0.1635) loss: 0.8229 (0.8152) time: 0.1177 data: 0.0215 max mem: 9390 +Train: [99] [1200/6250] eta: 0:16:07 lr: 0.000000 grad: 0.1492 (0.1626) loss: 0.8175 (0.8153) time: 0.1522 data: 0.0717 max mem: 9390 +Train: [99] [1300/6250] eta: 0:15:46 lr: 0.000000 grad: 0.1359 (0.1615) loss: 0.8204 (0.8155) time: 0.2919 data: 0.2015 max mem: 9390 +Train: [99] [1400/6250] eta: 0:15:25 lr: 0.000000 grad: 0.1445 (0.1605) loss: 0.8164 (0.8155) time: 0.1295 data: 0.0466 max mem: 9390 +Train: [99] [1500/6250] eta: 0:14:57 lr: 0.000000 grad: 0.1521 (0.1596) loss: 0.8126 (0.8156) time: 0.1930 data: 0.1052 max mem: 9390 +Train: [99] [1600/6250] eta: 0:14:39 lr: 0.000000 grad: 0.1471 (0.1590) loss: 0.8142 (0.8157) time: 0.2338 data: 0.1415 max mem: 9390 +Train: [99] [1700/6250] eta: 0:14:14 lr: 0.000000 grad: 0.1410 (0.1581) loss: 0.8204 (0.8158) time: 0.1101 data: 0.0209 max mem: 9390 +Train: [99] [1800/6250] eta: 0:14:02 lr: 0.000000 grad: 0.1396 (0.1575) loss: 0.8223 (0.8159) time: 0.1097 data: 0.0207 max mem: 9390 +Train: [99] [1900/6250] eta: 0:13:39 lr: 0.000000 grad: 0.1457 (0.1569) loss: 0.8175 (0.8159) time: 0.1847 data: 0.0970 max mem: 9390 +Train: [99] [2000/6250] eta: 0:13:13 lr: 0.000000 grad: 0.1446 (0.1563) loss: 0.8173 (0.8159) time: 0.1540 data: 0.0490 max mem: 9390 +Train: [99] [2100/6250] eta: 0:12:55 lr: 0.000000 grad: 0.1446 (0.1559) loss: 0.8067 (0.8158) time: 0.1255 data: 0.0337 max mem: 9390 +Train: [99] [2200/6250] eta: 0:12:33 lr: 0.000000 grad: 0.1427 (0.1554) loss: 0.8125 (0.8158) time: 0.1254 data: 0.0268 max mem: 9390 +Train: [99] [2300/6250] eta: 0:12:09 lr: 0.000000 grad: 0.1430 (0.1549) loss: 0.8120 (0.8158) time: 0.1492 data: 0.0674 max mem: 9390 +Train: [99] [2400/6250] eta: 0:11:47 lr: 0.000000 grad: 0.1474 (0.1545) loss: 0.8150 (0.8158) time: 0.1524 data: 0.0669 max mem: 9390 +Train: [99] [2500/6250] eta: 0:11:27 lr: 0.000000 grad: 0.1403 (0.1541) loss: 0.8164 (0.8157) time: 0.1686 data: 0.0876 max mem: 9390 +Train: [99] [2600/6250] eta: 0:11:20 lr: 0.000000 grad: 0.1353 (0.1538) loss: 0.8172 (0.8156) time: 0.0976 data: 0.0002 max mem: 9390 +Train: [99] [2700/6250] eta: 0:10:58 lr: 0.000000 grad: 0.1337 (0.1535) loss: 0.8210 (0.8156) time: 0.1629 data: 0.0737 max mem: 9390 +Train: [99] [2800/6250] eta: 0:10:40 lr: 0.000000 grad: 0.1493 (0.1531) loss: 0.8113 (0.8154) time: 0.0974 data: 0.0002 max mem: 9390 +Train: [99] [2900/6250] eta: 0:10:18 lr: 0.000000 grad: 0.1400 (0.1530) loss: 0.8223 (0.8153) time: 0.1256 data: 0.0357 max mem: 9390 +Train: [99] [3000/6250] eta: 0:09:59 lr: 0.000000 grad: 0.1437 (0.1530) loss: 0.8119 (0.8152) time: 0.1228 data: 0.0378 max mem: 9390 +Train: [99] [3100/6250] eta: 0:09:41 lr: 0.000000 grad: 0.1447 (0.1528) loss: 0.8142 (0.8151) time: 0.1250 data: 0.0104 max mem: 9390 +Train: [99] [3200/6250] eta: 0:09:21 lr: 0.000000 grad: 0.1434 (0.1526) loss: 0.8135 (0.8151) time: 0.1432 data: 0.0533 max mem: 9390 +Train: [99] [3300/6250] eta: 0:09:01 lr: 0.000000 grad: 0.1384 (0.1526) loss: 0.8158 (0.8150) time: 0.1374 data: 0.0438 max mem: 9390 +Train: [99] [3400/6250] eta: 0:08:42 lr: 0.000000 grad: 0.1522 (0.1526) loss: 0.8128 (0.8150) time: 0.1840 data: 0.0975 max mem: 9390 +Train: [99] [3500/6250] eta: 0:08:21 lr: 0.000000 grad: 0.1473 (0.1525) loss: 0.8165 (0.8151) time: 0.1388 data: 0.0582 max mem: 9390 +Train: [99] [3600/6250] eta: 0:08:02 lr: 0.000000 grad: 0.1392 (0.1522) loss: 0.8162 (0.8151) time: 0.2133 data: 0.1361 max mem: 9390 +Train: [99] [3700/6250] eta: 0:07:44 lr: 0.000000 grad: 0.1375 (0.1520) loss: 0.8181 (0.8152) time: 0.1989 data: 0.1204 max mem: 9390 +Train: [99] [3800/6250] eta: 0:07:27 lr: 0.000000 grad: 0.1383 (0.1518) loss: 0.8161 (0.8152) time: 0.2081 data: 0.1249 max mem: 9390 +Train: [99] [3900/6250] eta: 0:07:09 lr: 0.000000 grad: 0.1430 (0.1517) loss: 0.8192 (0.8153) time: 0.2046 data: 0.1232 max mem: 9390 +Train: [99] [4000/6250] eta: 0:06:50 lr: 0.000000 grad: 0.1466 (0.1516) loss: 0.8196 (0.8154) time: 0.1792 data: 0.0917 max mem: 9390 +Train: [99] [4100/6250] eta: 0:06:32 lr: 0.000000 grad: 0.1422 (0.1514) loss: 0.8218 (0.8155) time: 0.1721 data: 0.0890 max mem: 9390 +Train: [99] [4200/6250] eta: 0:06:16 lr: 0.000000 grad: 0.1332 (0.1513) loss: 0.8220 (0.8155) time: 0.1797 data: 0.1041 max mem: 9390 +Train: [99] [4300/6250] eta: 0:05:58 lr: 0.000000 grad: 0.1374 (0.1511) loss: 0.8167 (0.8156) time: 0.1896 data: 0.1118 max mem: 9390 +Train: [99] [4400/6250] eta: 0:05:40 lr: 0.000000 grad: 0.1365 (0.1509) loss: 0.8163 (0.8156) time: 0.2246 data: 0.1452 max mem: 9390 +Train: [99] [4500/6250] eta: 0:05:22 lr: 0.000000 grad: 0.1397 (0.1508) loss: 0.8129 (0.8157) time: 0.1675 data: 0.0830 max mem: 9390 +Train: [99] [4600/6250] eta: 0:05:03 lr: 0.000000 grad: 0.1429 (0.1506) loss: 0.8205 (0.8157) time: 0.1953 data: 0.1194 max mem: 9390 +Train: [99] [4700/6250] eta: 0:04:45 lr: 0.000000 grad: 0.1517 (0.1507) loss: 0.8152 (0.8157) time: 0.2053 data: 0.1230 max mem: 9390 +Train: [99] [4800/6250] eta: 0:04:26 lr: 0.000000 grad: 0.1507 (0.1507) loss: 0.8141 (0.8158) time: 0.0970 data: 0.0003 max mem: 9390 +Train: [99] [4900/6250] eta: 0:04:09 lr: 0.000000 grad: 0.1389 (0.1507) loss: 0.8137 (0.8158) time: 0.5072 data: 0.4153 max mem: 9390 +Train: [99] [5000/6250] eta: 0:03:50 lr: 0.000000 grad: 0.1346 (0.1506) loss: 0.8169 (0.8158) time: 0.0964 data: 0.0002 max mem: 9390 +Train: [99] [5100/6250] eta: 0:03:31 lr: 0.000000 grad: 0.1350 (0.1505) loss: 0.8171 (0.8159) time: 0.1172 data: 0.0004 max mem: 9390 +Train: [99] [5200/6250] eta: 0:03:13 lr: 0.000000 grad: 0.1439 (0.1505) loss: 0.8166 (0.8159) time: 0.0958 data: 0.0004 max mem: 9390 +Train: [99] [5300/6250] eta: 0:02:54 lr: 0.000000 grad: 0.1355 (0.1504) loss: 0.8171 (0.8160) time: 0.1891 data: 0.0825 max mem: 9390 +Train: [99] [5400/6250] eta: 0:02:36 lr: 0.000000 grad: 0.1319 (0.1503) loss: 0.8202 (0.8160) time: 0.2086 data: 0.1218 max mem: 9390 +Train: [99] [5500/6250] eta: 0:02:18 lr: 0.000000 grad: 0.1439 (0.1502) loss: 0.8129 (0.8161) time: 0.2205 data: 0.1339 max mem: 9390 +Train: [99] [5600/6250] eta: 0:01:59 lr: 0.000000 grad: 0.1390 (0.1501) loss: 0.8119 (0.8161) time: 0.2385 data: 0.1451 max mem: 9390 +Train: [99] [5700/6250] eta: 0:01:41 lr: 0.000000 grad: 0.1512 (0.1501) loss: 0.8121 (0.8161) time: 0.1690 data: 0.0708 max mem: 9390 +Train: [99] [5800/6250] eta: 0:01:22 lr: 0.000000 grad: 0.1452 (0.1500) loss: 0.8110 (0.8161) time: 0.1341 data: 0.0512 max mem: 9390 +Train: [99] [5900/6250] eta: 0:01:04 lr: 0.000000 grad: 0.1451 (0.1500) loss: 0.8194 (0.8161) time: 0.1290 data: 0.0318 max mem: 9390 +Train: [99] [6000/6250] eta: 0:00:45 lr: 0.000000 grad: 0.1453 (0.1500) loss: 0.8178 (0.8160) time: 0.2061 data: 0.1256 max mem: 9390 +Train: [99] [6100/6250] eta: 0:00:27 lr: 0.000000 grad: 0.1513 (0.1501) loss: 0.8186 (0.8161) time: 0.1671 data: 0.0820 max mem: 9390 +Train: [99] [6200/6250] eta: 0:00:09 lr: 0.000000 grad: 0.1446 (0.1501) loss: 0.8130 (0.8161) time: 0.1414 data: 0.0409 max mem: 9390 +Train: [99] [6249/6250] eta: 0:00:00 lr: 0.000000 grad: 0.1532 (0.1501) loss: 0.8145 (0.8161) time: 0.1474 data: 0.0600 max mem: 9390 +Train: [99] Total time: 0:19:14 (0.1846 s / it) +Averaged stats: lr: 0.000000 grad: 0.1532 (0.1501) loss: 0.8145 (0.8161) +Eval (hcp-train-subset): [99] [ 0/62] eta: 0:04:07 loss: 0.8250 (0.8250) time: 3.9841 data: 3.9158 max mem: 9390 +Eval (hcp-train-subset): [99] [61/62] eta: 0:00:00 loss: 0.8166 (0.8163) time: 0.1420 data: 0.1152 max mem: 9390 +Eval (hcp-train-subset): [99] Total time: 0:00:12 (0.2085 s / it) +Averaged stats (hcp-train-subset): loss: 0.8166 (0.8163) +Making plots (hcp-train-subset): example=44 +Eval (hcp-val): [99] [ 0/62] eta: 0:04:42 loss: 0.8263 (0.8263) time: 4.5616 data: 4.5304 max mem: 9390 +Eval (hcp-val): [99] [61/62] eta: 0:00:00 loss: 0.8259 (0.8275) time: 0.1267 data: 0.1019 max mem: 9390 +Eval (hcp-val): [99] Total time: 0:00:13 (0.2129 s / it) +Averaged stats (hcp-val): loss: 0.8259 (0.8275) +Making plots (hcp-val): example=27 +saving checkpoint experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_6/pretrain/checkpoint-last.pth +done! training time: 17:02:41 diff --git a/input_space_v3/flat_lr1e-3_7/eval_v2/aabc_age__patch__logistic/config.yaml b/input_space_v3/flat_lr1e-3_7/eval_v2/aabc_age__patch__logistic/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..3bccd1841219f47d348aab87640ebfceb8c87be2 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_7/eval_v2/aabc_age__patch__logistic/config.yaml @@ -0,0 +1,30 @@ +output_root: experiments/input_space_v3/output +name_prefix: eval_logistic +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_7; eval v2 (aabc_age patch logistic) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_7/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: input_space_v3/flat_lr1e-3_7/eval_v2/aabc_age__patch__logistic +model: flat_mae +representation: patch +dataset: aabc_age +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_7/eval_v2/aabc_age__patch__logistic +remote_dir: null diff --git a/input_space_v3/flat_lr1e-3_7/eval_v2/aabc_age__patch__logistic/eval_table.csv b/input_space_v3/flat_lr1e-3_7/eval_v2/aabc_age__patch__logistic/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..41152cc089621ba8fb1e390f4f7244a06b543436 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_7/eval_v2/aabc_age__patch__logistic/eval_table.csv @@ -0,0 +1,203 @@ +model,repr,clf,dataset,trial,C,split,acc,acc_std,f1,f1_std,bacc,bacc_std +flat_mae,patch,logistic,aabc_age,,0.000774263682681127,train,0.562992125984252,0.021636518360814275,0.5570237523696948,0.022071594366500948,0.5640085408118811,0.021635344609812656 +flat_mae,patch,logistic,aabc_age,,0.000774263682681127,test,0.4423076923076923,0.05996182217330621,0.43159369010762194,0.06260105865616837,0.4333791208791209,0.059756163684908346 +flat_mae,patch,logistic,aabc_age,1,0.3593813663804626,train,0.9862204724409449,0.00512582701114708,0.9863367408086606,0.005077537682792567,0.9864898137475091,0.0050590943180423755 +flat_mae,patch,logistic,aabc_age,1,0.3593813663804626,test,0.5,0.0634992778228514,0.4923443797581729,0.06294142041527126,0.4965659340659341,0.06314131912390256 +flat_mae,patch,logistic,aabc_age,2,0.000774263682681127,train,0.5511811023622047,0.02120578575225871,0.5445561712354963,0.02178470362354184,0.5521561156832998,0.021241227833601287 +flat_mae,patch,logistic,aabc_age,2,0.000774263682681127,test,0.5961538461538461,0.06567893036195949,0.5861472678111048,0.06780592873324962,0.5915750915750916,0.06545479104183033 +flat_mae,patch,logistic,aabc_age,3,0.005994842503189409,train,0.6889763779527559,0.019085309507526398,0.6864731109735916,0.01953932731570726,0.6908861473870757,0.019135357459361804 +flat_mae,patch,logistic,aabc_age,3,0.005994842503189409,test,0.4423076923076923,0.06329150882035754,0.4279032258064516,0.06235646465671117,0.4358974358974359,0.0627274203363839 +flat_mae,patch,logistic,aabc_age,4,0.046415888336127774,train,0.8307086614173228,0.01654462577241577,0.8310142843942265,0.01664256539388808,0.8320078674463788,0.016459251093068363 +flat_mae,patch,logistic,aabc_age,4,0.046415888336127774,test,0.5576923076923077,0.06289565887504035,0.5533333333333333,0.06458928360966294,0.5604395604395604,0.06330021292210301 +flat_mae,patch,logistic,aabc_age,5,0.000774263682681127,train,0.5570866141732284,0.021615311631882468,0.5483882388191471,0.021841350833509906,0.5561464185090211,0.021448084425214384 +flat_mae,patch,logistic,aabc_age,5,0.000774263682681127,test,0.4230769230769231,0.061106851803035205,0.3952099450201917,0.05685203336964761,0.4191849816849817,0.060116858348639786 +flat_mae,patch,logistic,aabc_age,6,0.005994842503189409,train,0.6653543307086615,0.020138562650383256,0.662272915863945,0.02058632704830246,0.6667102202002727,0.020150491096526273 +flat_mae,patch,logistic,aabc_age,6,0.005994842503189409,test,0.4807692307692308,0.07058793667995776,0.48028409090909097,0.07097501659286701,0.47756410256410253,0.0704158140154672 +flat_mae,patch,logistic,aabc_age,7,0.005994842503189409,train,0.6811023622047244,0.019093253876819604,0.6785220869753666,0.019487158306135004,0.6826540500470858,0.019082032389887205 +flat_mae,patch,logistic,aabc_age,7,0.005994842503189409,test,0.4807692307692308,0.060214839724746616,0.43897741457325634,0.05980274887536274,0.4741300366300366,0.05915728299069934 +flat_mae,patch,logistic,aabc_age,8,0.046415888336127774,train,0.8208661417322834,0.017144030676465073,0.8208220702408582,0.017207306014199158,0.8223123713772251,0.017138257489345967 +flat_mae,patch,logistic,aabc_age,8,0.046415888336127774,test,0.5384615384615384,0.0661323198429531,0.5434030542726195,0.06485860616393276,0.5441849816849816,0.06663761778030912 +flat_mae,patch,logistic,aabc_age,9,0.3593813663804626,train,0.9862204724409449,0.005017872144453426,0.9864425235094447,0.004949266958900991,0.986707381628688,0.00487816993626234 +flat_mae,patch,logistic,aabc_age,9,0.3593813663804626,test,0.4230769230769231,0.06291455415291725,0.4075077540594782,0.061959650581912336,0.4207875457875458,0.06280185671643654 +flat_mae,patch,logistic,aabc_age,10,0.005994842503189409,train,0.6850393700787402,0.01943053748848893,0.683806739069897,0.019738242262635926,0.6873713772250661,0.019367465071828183 +flat_mae,patch,logistic,aabc_age,10,0.005994842503189409,test,0.46153846153846156,0.06600451616250327,0.4581818181818182,0.0644506715892739,0.459478021978022,0.06581530903534881 +flat_mae,patch,logistic,aabc_age,11,0.005994842503189409,train,0.6692913385826772,0.01985725299785933,0.6661758470348791,0.020273000926425797,0.6708424516052315,0.019820996378638038 +flat_mae,patch,logistic,aabc_age,11,0.005994842503189409,test,0.6153846153846154,0.07004304466903817,0.6180432470755051,0.07069813926328403,0.614010989010989,0.07020085403123073 +flat_mae,patch,logistic,aabc_age,12,0.005994842503189409,train,0.687007874015748,0.019752779509339853,0.6831931768465301,0.02027306488598783,0.688770045014375,0.019601393806635233 +flat_mae,patch,logistic,aabc_age,12,0.005994842503189409,test,0.38461538461538464,0.06551033163017768,0.38842926714780257,0.06632101632697483,0.38118131868131866,0.06535387435171683 +flat_mae,patch,logistic,aabc_age,13,0.005994842503189409,train,0.6988188976377953,0.019122926707819895,0.6942626110239051,0.019702948204234575,0.6992938573694497,0.0190715020752233 +flat_mae,patch,logistic,aabc_age,13,0.005994842503189409,test,0.4230769230769231,0.05841090925098348,0.41207544723878664,0.058311201554939095,0.4251373626373627,0.059002848185521324 +flat_mae,patch,logistic,aabc_age,14,0.046415888336127774,train,0.8326771653543307,0.015552225620259106,0.8321484253826367,0.015735875405647696,0.8334389007056151,0.015541459811094074 +flat_mae,patch,logistic,aabc_age,14,0.046415888336127774,test,0.5961538461538461,0.06439550500686175,0.589392446633826,0.06689651667161536,0.597985347985348,0.06435475289774585 +flat_mae,patch,logistic,aabc_age,15,0.046415888336127774,train,0.8385826771653543,0.01570998553809938,0.8382515405419441,0.015803237659193045,0.8396372478130532,0.01572306288651558 +flat_mae,patch,logistic,aabc_age,15,0.046415888336127774,test,0.46153846153846156,0.06691921960590037,0.4653846153846154,0.06660904566899886,0.4597069597069597,0.06708466282472726 +flat_mae,patch,logistic,aabc_age,16,0.005994842503189409,train,0.6771653543307087,0.019861689277939118,0.6737099717995529,0.020229865100462027,0.6772840192255687,0.019765095132463415 +flat_mae,patch,logistic,aabc_age,16,0.005994842503189409,test,0.4423076923076923,0.06211051421725119,0.4377136021872864,0.06322181027466409,0.43887362637362637,0.06199435442984656 +flat_mae,patch,logistic,aabc_age,17,0.000774263682681127,train,0.5433070866141733,0.021100112628360684,0.5380764938128081,0.02164536220638005,0.5441415862244888,0.02108714311557441 +flat_mae,patch,logistic,aabc_age,17,0.000774263682681127,test,0.4807692307692308,0.06633841649420476,0.4584331797235023,0.065802206391492,0.4757326007326007,0.06575272203203218 +flat_mae,patch,logistic,aabc_age,18,0.046415888336127774,train,0.8385826771653543,0.015700428051708733,0.8383377803008799,0.015831877240408347,0.8398548156942321,0.015575630890364534 +flat_mae,patch,logistic,aabc_age,18,0.046415888336127774,test,0.46153846153846156,0.0642742367888791,0.4550865800865801,0.06544609815113414,0.459478021978022,0.06425082683281337 +flat_mae,patch,logistic,aabc_age,19,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,19,2.782559402207126,test,0.4807692307692308,0.06688207187626247,0.49057539682539675,0.06742737645438748,0.48214285714285715,0.06702214071934241 +flat_mae,patch,logistic,aabc_age,20,0.005994842503189409,train,0.6948818897637795,0.020854096582846458,0.6937295575098745,0.021284751488024296,0.6965817508616408,0.020774021721352363 +flat_mae,patch,logistic,aabc_age,20,0.005994842503189409,test,0.5,0.05978129518869484,0.46522334757918155,0.06215788563004436,0.4977106227106227,0.059453711843884545 +flat_mae,patch,logistic,aabc_age,21,0.005994842503189409,train,0.6771653543307087,0.019664349363080175,0.6763486461204694,0.01995819956552976,0.678236642890433,0.019689066146453174 +flat_mae,patch,logistic,aabc_age,21,0.005994842503189409,test,0.5192307692307693,0.06189679327518898,0.49775707384403034,0.06611179439915084,0.5215201465201466,0.06245298693886123 +flat_mae,patch,logistic,aabc_age,22,0.046415888336127774,train,0.8208661417322834,0.017469802471350285,0.8203809099767053,0.01765636829771564,0.8226475337991404,0.017363498956096145 +flat_mae,patch,logistic,aabc_age,22,0.046415888336127774,test,0.36538461538461536,0.06290467805108027,0.3766900420757363,0.06265042926959624,0.36790293040293043,0.0632710989898243 +flat_mae,patch,logistic,aabc_age,23,0.005994842503189409,train,0.6889763779527559,0.02117706947234538,0.688798390307011,0.021250519772638168,0.6909008916567093,0.02109582554259827 +flat_mae,patch,logistic,aabc_age,23,0.005994842503189409,test,0.5,0.05909880404080318,0.4927248677248677,0.05949904661385263,0.5009157509157509,0.05946716722251178 +flat_mae,patch,logistic,aabc_age,24,0.046415888336127774,train,0.8405511811023622,0.016751903272539722,0.8406571408458848,0.01685441736729139,0.8419209313967114,0.01663754141562964 +flat_mae,patch,logistic,aabc_age,24,0.046415888336127774,test,0.36538461538461536,0.06245348564990177,0.36774725274725273,0.059914428683719094,0.3617216117216117,0.06201190311038325 +flat_mae,patch,logistic,aabc_age,25,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,25,2.782559402207126,test,0.34615384615384615,0.06336080583433525,0.35937499999999994,0.0610790212511034,0.3468406593406594,0.06363202691632361 +flat_mae,patch,logistic,aabc_age,26,0.000774263682681127,train,0.5570866141732284,0.021827056772291003,0.5494882803285722,0.021937036643772775,0.5571166633741793,0.02178158454043539 +flat_mae,patch,logistic,aabc_age,26,0.000774263682681127,test,0.46153846153846156,0.06259648174320358,0.4477731092436975,0.0638898296072777,0.4565018315018315,0.06224163468336934 +flat_mae,patch,logistic,aabc_age,27,0.046415888336127774,train,0.8248031496062992,0.016838123337973118,0.8241985265612838,0.016962472347514912,0.8254419924470981,0.016799236581448065 +flat_mae,patch,logistic,aabc_age,27,0.046415888336127774,test,0.40384615384615385,0.06551146067132026,0.391005291005291,0.06657246933656064,0.39903846153846156,0.0651621157551207 +flat_mae,patch,logistic,aabc_age,28,0.005994842503189409,train,0.6850393700787402,0.019942970025653314,0.6829273667082877,0.020306898914899993,0.6857160632464436,0.01983505447587918 +flat_mae,patch,logistic,aabc_age,28,0.005994842503189409,test,0.5,0.06855507870732881,0.5012365591397849,0.06952185600731048,0.5041208791208791,0.06881222629870458 +flat_mae,patch,logistic,aabc_age,29,0.046415888336127774,train,0.8326771653543307,0.016765875959495632,0.8319236759338389,0.016985294180743925,0.8337064552570155,0.016706368731407822 +flat_mae,patch,logistic,aabc_age,29,0.046415888336127774,test,0.5192307692307693,0.06608067285858843,0.5225231481481482,0.06765556856491249,0.5176282051282051,0.0664482718764335 +flat_mae,patch,logistic,aabc_age,30,0.005994842503189409,train,0.687007874015748,0.02147329560651667,0.6836066386848905,0.02196779549884754,0.6874646377273015,0.02146343845044911 +flat_mae,patch,logistic,aabc_age,30,0.005994842503189409,test,0.5,0.06472061029107887,0.48804112554112555,0.06559276519965557,0.5038919413919414,0.06509184200091993 +flat_mae,patch,logistic,aabc_age,31,0.000774263682681127,train,0.5492125984251969,0.02041464092300249,0.5375907540404654,0.02110133859627171,0.5494549175375775,0.02046206107334794 +flat_mae,patch,logistic,aabc_age,31,0.000774263682681127,test,0.6153846153846154,0.06210435720166462,0.5896878733572282,0.06724444404143376,0.6092032967032968,0.061670189397197935 +flat_mae,patch,logistic,aabc_age,32,0.046415888336127774,train,0.8346456692913385,0.01650901338951079,0.8349294823103437,0.016552939509620525,0.8359225309701586,0.016459160082770635 +flat_mae,patch,logistic,aabc_age,32,0.046415888336127774,test,0.5192307692307693,0.06027524391975364,0.5003237503237503,0.06346560995777746,0.5185439560439561,0.060173603893200936 +flat_mae,patch,logistic,aabc_age,33,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,33,166.81005372000556,test,0.40384615384615385,0.0663779188172458,0.4047222222222222,0.06572891005870361,0.40773809523809523,0.06689569888366988 +flat_mae,patch,logistic,aabc_age,34,0.3593813663804626,train,0.9803149606299213,0.005985198588618783,0.9804865650037292,0.0059186796335713564,0.9808765624130927,0.005829281617209487 +flat_mae,patch,logistic,aabc_age,34,0.3593813663804626,test,0.38461538461538464,0.062074397050883794,0.4078996983408748,0.06199273548429092,0.3917124542124542,0.06246202192984511 +flat_mae,patch,logistic,aabc_age,35,0.005994842503189409,train,0.687007874015748,0.018964896712996206,0.6838183471028431,0.019543530671351714,0.6891375729062178,0.018865806768848758 +flat_mae,patch,logistic,aabc_age,35,0.005994842503189409,test,0.36538461538461536,0.06306401134266056,0.3584559884559885,0.06350229426983947,0.3617216117216117,0.06270646985901444 +flat_mae,patch,logistic,aabc_age,36,0.046415888336127774,train,0.8208661417322834,0.017122986433251896,0.8206001886415991,0.017178883417032564,0.8215097077230243,0.017111887458016783 +flat_mae,patch,logistic,aabc_age,36,0.046415888336127774,test,0.5384615384615384,0.06379534586352012,0.5269111476008028,0.0652538979881731,0.538003663003663,0.06385543804741406 +flat_mae,patch,logistic,aabc_age,37,0.005994842503189409,train,0.6751968503937008,0.020463533419534365,0.6726268724049561,0.020863484854115998,0.6762381350584689,0.020449974213346395 +flat_mae,patch,logistic,aabc_age,37,0.005994842503189409,test,0.4423076923076923,0.06737042131855088,0.43985974754558205,0.06843576374632175,0.4391025641025641,0.06727086502624094 +flat_mae,patch,logistic,aabc_age,38,0.005994842503189409,train,0.6751968503937008,0.02056747476094321,0.6729172948835002,0.02095286446657753,0.6762881217286901,0.020654859720006784 +flat_mae,patch,logistic,aabc_age,38,0.005994842503189409,test,0.5,0.06582857196973031,0.48890837515625296,0.06711534058235716,0.4965659340659341,0.06540304197231332 +flat_mae,patch,logistic,aabc_age,39,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,39,166.81005372000556,test,0.4423076923076923,0.06462472459969017,0.42860576923076926,0.06323001696940071,0.4358974358974359,0.06395241130212882 +flat_mae,patch,logistic,aabc_age,40,0.005994842503189409,train,0.7007874015748031,0.01883131241407923,0.7000771270171279,0.01876241457574204,0.7014423252120777,0.018697828404756853 +flat_mae,patch,logistic,aabc_age,40,0.005994842503189409,test,0.5384615384615384,0.06568810786430751,0.5322021528918081,0.06737435934002353,0.5396062271062272,0.06604315612046524 +flat_mae,patch,logistic,aabc_age,41,0.005994842503189409,train,0.6791338582677166,0.020096824880182947,0.678276121254131,0.020174121815768574,0.6807878810254915,0.020094707683246362 +flat_mae,patch,logistic,aabc_age,41,0.005994842503189409,test,0.4230769230769231,0.059845263983892456,0.38832833832833835,0.06363436395964328,0.4221611721611722,0.05988553989464354 +flat_mae,patch,logistic,aabc_age,42,0.005994842503189409,train,0.6712598425196851,0.020742992335809753,0.6689193625723558,0.021012646540749524,0.6719883091127739,0.020641263653229196 +flat_mae,patch,logistic,aabc_age,42,0.005994842503189409,test,0.4807692307692308,0.06112621533502161,0.47377104377104373,0.06316513953248129,0.48168498168498164,0.06132065177894465 +flat_mae,patch,logistic,aabc_age,43,9.999999999999999e-05,train,0.484251968503937,0.01931998676303317,0.44546877804591056,0.019265368882426616,0.48189056059870844,0.019147051386734632 +flat_mae,patch,logistic,aabc_age,43,9.999999999999999e-05,test,0.4807692307692308,0.0594215210152291,0.42017241379310344,0.05054785232713505,0.4684065934065934,0.05802599079738626 +flat_mae,patch,logistic,aabc_age,44,0.3593813663804626,train,0.984251968503937,0.0055776425773074925,0.9844346306652937,0.005515650121751905,0.98469125259643,0.005448567650112333 +flat_mae,patch,logistic,aabc_age,44,0.3593813663804626,test,0.5,0.06548503600692607,0.49953580901856764,0.06686473589875144,0.5027472527472527,0.06580483260267805 +flat_mae,patch,logistic,aabc_age,45,0.005994842503189409,train,0.6732283464566929,0.01964350697392735,0.6700546743554698,0.02033376860862821,0.6741220326857682,0.01968930725157366 +flat_mae,patch,logistic,aabc_age,45,0.005994842503189409,test,0.5384615384615384,0.06425811255853846,0.5418956043956044,0.0629700756009039,0.5441849816849818,0.06459212975376134 +flat_mae,patch,logistic,aabc_age,46,0.000774263682681127,train,0.5531496062992126,0.022094037448890626,0.5429713762117336,0.022994419554494324,0.5529344452989994,0.022082194452190125 +flat_mae,patch,logistic,aabc_age,46,0.000774263682681127,test,0.4423076923076923,0.0638041567156967,0.4375,0.06439347957964661,0.4416208791208791,0.06376634145644187 +flat_mae,patch,logistic,aabc_age,47,0.005994842503189409,train,0.6712598425196851,0.01978991746525656,0.66848886132594,0.02011839602364978,0.6719383224425525,0.01976171510579404 +flat_mae,patch,logistic,aabc_age,47,0.005994842503189409,test,0.46153846153846156,0.06318138629346856,0.4438930205949657,0.06723694266002977,0.45810439560439564,0.06297460803952566 +flat_mae,patch,logistic,aabc_age,48,0.000774263682681127,train,0.5590551181102362,0.02225640938461362,0.5488520333410845,0.023268762672249345,0.5589828323957736,0.0221393204128075 +flat_mae,patch,logistic,aabc_age,48,0.000774263682681127,test,0.5,0.06572322952661626,0.4884711779448621,0.0668660240040807,0.4965659340659341,0.0656449685725548 +flat_mae,patch,logistic,aabc_age,49,0.005994842503189409,train,0.6988188976377953,0.019236881195120896,0.6963499792822379,0.01965673676994557,0.7000289131531352,0.019208438530686142 +flat_mae,patch,logistic,aabc_age,49,0.005994842503189409,test,0.36538461538461536,0.061580502466476096,0.36578648806909675,0.062452462196299546,0.36469780219780223,0.0618220433402213 +flat_mae,patch,logistic,aabc_age,50,0.046415888336127774,train,0.8307086614173228,0.016764596404428747,0.829657286488866,0.01698918570120235,0.8313227983329146,0.01669631757483963 +flat_mae,patch,logistic,aabc_age,50,0.046415888336127774,test,0.38461538461538464,0.0657698605457927,0.3914726507713885,0.06541923695057195,0.3855311355311355,0.06594940617455115 +flat_mae,patch,logistic,aabc_age,51,0.005994842503189409,train,0.687007874015748,0.01968015845000423,0.6849718908542438,0.01998466540106519,0.6891875595764391,0.019610170941847374 +flat_mae,patch,logistic,aabc_age,51,0.005994842503189409,test,0.4423076923076923,0.06953458974925812,0.436203009606308,0.06917680751627872,0.4432234432234432,0.06957321111653643 +flat_mae,patch,logistic,aabc_age,52,0.046415888336127774,train,0.8267716535433071,0.016392802550142267,0.8258967944921303,0.016586506843283375,0.827458121479356,0.0163264364425669 +flat_mae,patch,logistic,aabc_age,52,0.046415888336127774,test,0.4423076923076923,0.06563229108553269,0.4456744704570792,0.06604253668710656,0.4450549450549451,0.0656972712226813 +flat_mae,patch,logistic,aabc_age,53,9.999999999999999e-05,train,0.49803149606299213,0.020441337668963135,0.47463072884289215,0.020856165481040887,0.49601820809414854,0.020271283934358442 +flat_mae,patch,logistic,aabc_age,53,9.999999999999999e-05,test,0.5576923076923077,0.055674136432059915,0.5077188940092165,0.055408071872659004,0.5496794871794871,0.05445196166923093 +flat_mae,patch,logistic,aabc_age,54,0.046415888336127774,train,0.8326771653543307,0.016100839309615294,0.8326569944999214,0.0161820022138775,0.8340239964786369,0.0160462406131821 +flat_mae,patch,logistic,aabc_age,54,0.046415888336127774,test,0.4423076923076923,0.06438901510562332,0.43746993746993745,0.06419546457478882,0.4432234432234432,0.06469346782880495 +flat_mae,patch,logistic,aabc_age,55,0.000774263682681127,train,0.5669291338582677,0.022200695940483496,0.5570406735523835,0.022900306208421463,0.5664946182217117,0.02203883457938492 +flat_mae,patch,logistic,aabc_age,55,0.000774263682681127,test,0.4230769230769231,0.0645849745289974,0.41475885225885223,0.06390574055628347,0.4207875457875458,0.0643890583451448 +flat_mae,patch,logistic,aabc_age,56,9.999999999999999e-05,train,0.49803149606299213,0.01917609640790708,0.45895780000187547,0.01950390198092388,0.49453047532648364,0.019047117586687805 +flat_mae,patch,logistic,aabc_age,56,9.999999999999999e-05,test,0.40384615384615385,0.06485453682469379,0.38736129770612526,0.06202536611515196,0.3985805860805861,0.06416102409517221 +flat_mae,patch,logistic,aabc_age,57,0.000774263682681127,train,0.5728346456692913,0.022306502586916563,0.565075829025735,0.022934361818461247,0.5722078428965705,0.022224283935306854 +flat_mae,patch,logistic,aabc_age,57,0.000774263682681127,test,0.4423076923076923,0.05756749319007516,0.4192927170868347,0.05277752059937226,0.4384157509157509,0.056791044906466095 +flat_mae,patch,logistic,aabc_age,58,0.005994842503189409,train,0.6929133858267716,0.02010824603696496,0.6910714753308682,0.020406334167816606,0.6941481072673186,0.020118323142324826 +flat_mae,patch,logistic,aabc_age,58,0.005994842503189409,test,0.4423076923076923,0.05799687555346837,0.4129901960784314,0.06328471223508243,0.43864468864468864,0.05735759411314578 +flat_mae,patch,logistic,aabc_age,59,0.046415888336127774,train,0.8405511811023622,0.015722212594795247,0.8403091415118072,0.015851604920965757,0.8421384992778903,0.015572965793823562 +flat_mae,patch,logistic,aabc_age,59,0.046415888336127774,test,0.5,0.06796338859525113,0.5040873015873016,0.06815080109917364,0.5013736263736264,0.06806821678272926 +flat_mae,patch,logistic,aabc_age,60,0.005994842503189409,train,0.6889763779527559,0.02092447462105742,0.6860081093204464,0.02132194903091041,0.6896983346407385,0.02084594481245941 +flat_mae,patch,logistic,aabc_age,60,0.005994842503189409,test,0.4423076923076923,0.06349135663115024,0.4300543007439559,0.06493097852887462,0.4416208791208791,0.06352170287596247 +flat_mae,patch,logistic,aabc_age,61,0.005994842503189409,train,0.7066929133858267,0.01932128641225054,0.706367513383276,0.01962772766275891,0.7084433359737164,0.019394371810626136 +flat_mae,patch,logistic,aabc_age,61,0.005994842503189409,test,0.36538461538461536,0.06487954245820325,0.36355488922205564,0.06270102282973072,0.3630952380952381,0.06458111258132736 +flat_mae,patch,logistic,aabc_age,62,0.005994842503189409,train,0.6692913385826772,0.019894435894921958,0.6672130220188258,0.020246693346717155,0.670724857064495,0.019897725244658156 +flat_mae,patch,logistic,aabc_age,62,0.005994842503189409,test,0.5576923076923077,0.058258706843500416,0.5357471264367816,0.0587249208696605,0.549908424908425,0.05803943675882883 +flat_mae,patch,logistic,aabc_age,63,0.005994842503189409,train,0.6909448818897638,0.018922201882958758,0.688939514061891,0.019326342203032143,0.6932698043111766,0.018803671502694515 +flat_mae,patch,logistic,aabc_age,63,0.005994842503189409,test,0.4423076923076923,0.06136832249554455,0.42586553945249594,0.062418966108544,0.44299450549450553,0.061564781166553374 +flat_mae,patch,logistic,aabc_age,64,0.046415888336127774,train,0.8405511811023622,0.015365368029730687,0.840297680324698,0.015507984651755796,0.8423560671590693,0.015287688791047534 +flat_mae,patch,logistic,aabc_age,64,0.046415888336127774,test,0.36538461538461536,0.06484546947353072,0.3695436507936508,0.06463826749822274,0.3619505494505495,0.06461697618670839 +flat_mae,patch,logistic,aabc_age,65,0.3593813663804626,train,0.9881889763779528,0.004670511120567874,0.9883928688142302,0.004587631044116635,0.9882883748985882,0.00464135636885411 +flat_mae,patch,logistic,aabc_age,65,0.3593813663804626,test,0.5,0.07001876333480127,0.4954308560005712,0.06845081300138162,0.49381868131868134,0.06997584526664066 +flat_mae,patch,logistic,aabc_age,66,0.046415888336127774,train,0.84251968503937,0.01548714764582184,0.8421755272118628,0.015644216330855276,0.8442046149803698,0.015401040293180146 +flat_mae,patch,logistic,aabc_age,66,0.046415888336127774,test,0.40384615384615385,0.06172179421935825,0.4031767598343685,0.0640177527582083,0.4033882783882784,0.06220300707074656 +flat_mae,patch,logistic,aabc_age,67,0.005994842503189409,train,0.687007874015748,0.020549996571890664,0.6841753843806732,0.02091808133374887,0.687782178948923,0.020529018682671558 +flat_mae,patch,logistic,aabc_age,67,0.005994842503189409,test,0.5192307692307693,0.06066079663605407,0.47175595238095236,0.06414903173768004,0.5112179487179487,0.059623343484066844 +flat_mae,patch,logistic,aabc_age,68,0.046415888336127774,train,0.8287401574803149,0.016396251040225518,0.8280790099728619,0.016600436700316763,0.829624210522278,0.016363147112250013 +flat_mae,patch,logistic,aabc_age,68,0.046415888336127774,test,0.4230769230769231,0.06263743469245904,0.42763322884012545,0.06076813239259139,0.42536630036630035,0.06286988749307014 +flat_mae,patch,logistic,aabc_age,69,0.046415888336127774,train,0.8366141732283464,0.01602057275247995,0.8365258616375284,0.016089735062195434,0.8381062412133743,0.015908145278136297 +flat_mae,patch,logistic,aabc_age,69,0.046415888336127774,test,0.4230769230769231,0.0646545096749003,0.42895604395604403,0.06358652686753734,0.4269688644688645,0.0651718417931458 +flat_mae,patch,logistic,aabc_age,70,0.046415888336127774,train,0.8346456692913385,0.015813777621148137,0.8351761982612947,0.015836574199667244,0.835822557629716,0.015782927022944853 +flat_mae,patch,logistic,aabc_age,70,0.046415888336127774,test,0.4423076923076923,0.06843435069487827,0.43741948470209335,0.06983316502163844,0.4391025641025641,0.06855860381873721 +flat_mae,patch,logistic,aabc_age,71,0.005994842503189409,train,0.6909448818897638,0.020188712271172866,0.6894841239195886,0.020489079407131884,0.6923995327864608,0.020101600558335264 +flat_mae,patch,logistic,aabc_age,71,0.005994842503189409,test,0.5,0.06528952361207059,0.4973789173789174,0.0654292177916127,0.5041208791208791,0.0659022099780934 +flat_mae,patch,logistic,aabc_age,72,0.005994842503189409,train,0.6811023622047244,0.020613549132471473,0.6784213955600308,0.021036277722749942,0.6814162506305274,0.020638354493613058 +flat_mae,patch,logistic,aabc_age,72,0.005994842503189409,test,0.5192307692307693,0.06521991700366152,0.5154882154882154,0.06557487137782009,0.5203754578754579,0.06529600559381665 +flat_mae,patch,logistic,aabc_age,73,0.000774263682681127,train,0.5748031496062992,0.02208687769152381,0.5665816526441776,0.02251915208702738,0.5755793658861235,0.022056438933031837 +flat_mae,patch,logistic,aabc_age,73,0.000774263682681127,test,0.5192307692307693,0.05982810683001682,0.5041360089186177,0.06153225368562124,0.5201465201465202,0.05988862849065686 +flat_mae,patch,logistic,aabc_age,74,0.046415888336127774,train,0.8405511811023622,0.016409586726943298,0.8398642878528428,0.016534541078740028,0.8416033901750899,0.016346948982321217 +flat_mae,patch,logistic,aabc_age,74,0.046415888336127774,test,0.4230769230769231,0.06837517240331781,0.42708333333333337,0.06963072811994754,0.4228479853479854,0.06849898352387739 +flat_mae,patch,logistic,aabc_age,75,0.005994842503189409,train,0.687007874015748,0.019470804303480634,0.6845091582649482,0.019682289621422447,0.6884348825924598,0.01950722640542147 +flat_mae,patch,logistic,aabc_age,75,0.005994842503189409,test,0.5576923076923077,0.06762972412925264,0.5518231768231768,0.06947013293025164,0.5560897435897436,0.0677008645833168 +flat_mae,patch,logistic,aabc_age,76,0.005994842503189409,train,0.6791338582677166,0.020531507764546226,0.6764051012546314,0.020992651513929407,0.6798852440308484,0.020517894055023113 +flat_mae,patch,logistic,aabc_age,76,0.005994842503189409,test,0.5,0.0637530716280544,0.4921289355322339,0.06517373945730633,0.4981684981684982,0.06392677255809767 +flat_mae,patch,logistic,aabc_age,77,0.046415888336127774,train,0.84251968503937,0.01572149880994335,0.8422981875429678,0.015851805315095578,0.8439370604289694,0.015655086955807283 +flat_mae,patch,logistic,aabc_age,77,0.046415888336127774,test,0.4807692307692308,0.06701227477420985,0.4790969899665552,0.06726771930295743,0.48328754578754574,0.06729451152213703 +flat_mae,patch,logistic,aabc_age,78,0.046415888336127774,train,0.8307086614173228,0.015602287696448967,0.829620015384704,0.015869213295546136,0.8322430565278515,0.01542233166444468 +flat_mae,patch,logistic,aabc_age,78,0.046415888336127774,test,0.4807692307692308,0.06409732799127668,0.4807303113553113,0.06352490437968884,0.4846611721611722,0.06464946069905743 +flat_mae,patch,logistic,aabc_age,79,0.005994842503189409,train,0.6771653543307087,0.02022199743740367,0.6752222728121968,0.02071719637510476,0.6797096313884643,0.020098502100041785 +flat_mae,patch,logistic,aabc_age,79,0.005994842503189409,test,0.5,0.06207463535961839,0.4796816087138668,0.06252076747531789,0.49221611721611724,0.061720159565082054 +flat_mae,patch,logistic,aabc_age,80,0.3593813663804626,train,0.9822834645669292,0.005777349457626175,0.9824822032064859,0.005713963753833341,0.9826251368939507,0.005680567506893209 +flat_mae,patch,logistic,aabc_age,80,0.3593813663804626,test,0.46153846153846156,0.062173216707354345,0.44966329966329965,0.06307289568680402,0.46543040293040294,0.0625289734463998 +flat_mae,patch,logistic,aabc_age,81,0.3593813663804626,train,0.9901574803149606,0.004230572809383208,0.9902719967169007,0.0041735464262547305,0.9903045039308462,0.004180190770489736 +flat_mae,patch,logistic,aabc_age,81,0.3593813663804626,test,0.38461538461538464,0.0679985533260662,0.38690476190476186,0.0678444192341508,0.3855311355311355,0.06811598947927826 +flat_mae,patch,logistic,aabc_age,82,0.005994842503189409,train,0.6830708661417323,0.02016325389448873,0.6801906759262412,0.02057874495727639,0.6841850566467647,0.020178965435457226 +flat_mae,patch,logistic,aabc_age,82,0.005994842503189409,test,0.5576923076923077,0.06846417453870507,0.5510989010989011,0.07097032854440895,0.55746336996337,0.0687636193389282 +flat_mae,patch,logistic,aabc_age,83,0.3593813663804626,train,0.9901574803149606,0.004025653600568952,0.9902802255441282,0.003968479433952036,0.9903045039308462,0.003980603968244503 +flat_mae,patch,logistic,aabc_age,83,0.3593813663804626,test,0.4423076923076923,0.06630433464638197,0.44941423519009727,0.06447885814047466,0.4448260073260073,0.0667635880896198 +flat_mae,patch,logistic,aabc_age,84,0.005994842503189409,train,0.6771653543307087,0.020322595159470845,0.6764296648835265,0.02047460448464947,0.6784542107716119,0.020292453134559883 +flat_mae,patch,logistic,aabc_age,84,0.005994842503189409,test,0.5192307692307693,0.06046559978530312,0.4895179744592899,0.063848588843173,0.5114468864468864,0.060002928477809046 +flat_mae,patch,logistic,aabc_age,85,0.046415888336127774,train,0.8287401574803149,0.017178803515454165,0.8285631593409097,0.017265267070949872,0.8301593196250784,0.017050529953764125 +flat_mae,patch,logistic,aabc_age,85,0.046415888336127774,test,0.46153846153846156,0.062139802297607925,0.43341440518859875,0.05859637502506504,0.4548992673992674,0.06109820152405824 +flat_mae,patch,logistic,aabc_age,86,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,86,21.54434690031882,test,0.36538461538461536,0.06244158216630928,0.3476470588235294,0.06283290220185146,0.3576007326007326,0.061947490907431825 +flat_mae,patch,logistic,aabc_age,87,0.005994842503189409,train,0.6909448818897638,0.01972966398647685,0.6877195529317072,0.020218958203819797,0.6910617600294597,0.019782536990780784 +flat_mae,patch,logistic,aabc_age,87,0.005994842503189409,test,0.5384615384615384,0.05967092945886805,0.5316870629370629,0.06012167235998682,0.5455586080586081,0.0603319706095827 +flat_mae,patch,logistic,aabc_age,88,9.999999999999999e-05,train,0.5,0.01786685962751557,0.4567974346139226,0.01839803628656094,0.497802024975594,0.01767320083418626 +flat_mae,patch,logistic,aabc_age,88,9.999999999999999e-05,test,0.46153846153846156,0.0669090502541858,0.44551282051282054,0.0687275355202262,0.4551282051282051,0.06646873210188596 +flat_mae,patch,logistic,aabc_age,89,0.005994842503189409,train,0.6614173228346457,0.0210084565166147,0.6593344624463615,0.021278611682649412,0.6627279488059779,0.020926600495658077 +flat_mae,patch,logistic,aabc_age,89,0.005994842503189409,test,0.4423076923076923,0.0661580834957779,0.4217545638945233,0.06652067831577231,0.43727106227106227,0.0655745754385006 +flat_mae,patch,logistic,aabc_age,90,9.999999999999999e-05,train,0.47244094488188976,0.019014352094961613,0.44441200119630203,0.01890799642089247,0.4697761652048662,0.01893541354274337 +flat_mae,patch,logistic,aabc_age,90,9.999999999999999e-05,test,0.5576923076923077,0.05630254284986554,0.5046082949308756,0.059254659619340844,0.5496794871794871,0.05537558409015675 +flat_mae,patch,logistic,aabc_age,91,0.005994842503189409,train,0.6712598425196851,0.02016920296128472,0.6699949662765214,0.020318456694861667,0.6730585273183746,0.020062880380719753 +flat_mae,patch,logistic,aabc_age,91,0.005994842503189409,test,0.4423076923076923,0.06888025584280603,0.440313836865561,0.06947621620286829,0.443452380952381,0.06892798133273798 +flat_mae,patch,logistic,aabc_age,92,0.005994842503189409,train,0.6771653543307087,0.020183750029851497,0.674097953107428,0.020568929906815157,0.6778691149985904,0.020123318852059282 +flat_mae,patch,logistic,aabc_age,92,0.005994842503189409,test,0.5384615384615384,0.0542422110133916,0.4928030303030303,0.06333077105490388,0.5347985347985349,0.053712279105290056 +flat_mae,patch,logistic,aabc_age,93,0.046415888336127774,train,0.8228346456692913,0.01714318938464731,0.8228417604190064,0.01722195603726764,0.8238933646471253,0.017167180424625682 +flat_mae,patch,logistic,aabc_age,93,0.046415888336127774,test,0.4807692307692308,0.06510055944641864,0.4944516630573602,0.0625214658077899,0.4819139194139194,0.06555129983839343 +flat_mae,patch,logistic,aabc_age,94,0.000774263682681127,train,0.5649606299212598,0.020511535582354228,0.5550921200701369,0.02108059630715889,0.5644285025192324,0.020413395104721937 +flat_mae,patch,logistic,aabc_age,94,0.000774263682681127,test,0.36538461538461536,0.05760859310901456,0.34293906810035846,0.05530080540485442,0.3628663003663004,0.057020076343442506 +flat_mae,patch,logistic,aabc_age,95,0.046415888336127774,train,0.8248031496062992,0.0156062018796078,0.8250249272768535,0.01567873664060259,0.8263446294417411,0.015506109720153531 +flat_mae,patch,logistic,aabc_age,95,0.046415888336127774,test,0.5384615384615384,0.06338166301936697,0.5267857142857143,0.06339440619681545,0.5350274725274725,0.06300333620751775 +flat_mae,patch,logistic,aabc_age,96,0.3593813663804626,train,0.9881889763779528,0.0047030290491304,0.988263187947845,0.004674738981765979,0.9885559294499884,0.004600458861312474 +flat_mae,patch,logistic,aabc_age,96,0.3593813663804626,test,0.4807692307692308,0.06552558333205373,0.48964342713435904,0.0660391951340157,0.4837454212454213,0.06552335422404702 +flat_mae,patch,logistic,aabc_age,97,0.000774263682681127,train,0.5708661417322834,0.02151318143915379,0.5668266437038758,0.022081411801216172,0.5717470545024923,0.021496059723548934 +flat_mae,patch,logistic,aabc_age,97,0.000774263682681127,test,0.40384615384615385,0.06291605894660585,0.3833759590792839,0.06176256801184485,0.3985805860805861,0.06213028989648064 +flat_mae,patch,logistic,aabc_age,98,0.005994842503189409,train,0.6948818897637795,0.019770105961126744,0.690994035308623,0.020288674396758234,0.6956967350672913,0.01968660420314761 +flat_mae,patch,logistic,aabc_age,98,0.005994842503189409,test,0.46153846153846156,0.05885575587824865,0.43253968253968256,0.06357799927210456,0.46222527472527475,0.05928465021433887 +flat_mae,patch,logistic,aabc_age,99,0.000774263682681127,train,0.5708661417322834,0.022370983637779937,0.5643403481874985,0.022931069599731815,0.5702417005345337,0.022301333836453163 +flat_mae,patch,logistic,aabc_age,99,0.000774263682681127,test,0.46153846153846156,0.06179006258549612,0.43741993873572826,0.062163395531114204,0.4592490842490842,0.061462982918972106 +flat_mae,patch,logistic,aabc_age,100,0.005994842503189409,train,0.687007874015748,0.020515084297593494,0.6837585314090023,0.020893200291149296,0.6885524771331961,0.020437848798283868 +flat_mae,patch,logistic,aabc_age,100,0.005994842503189409,test,0.4423076923076923,0.06844393680383311,0.4354166666666667,0.06933355589770297,0.43887362637362637,0.06817869861095498 diff --git a/input_space_v3/flat_lr1e-3_7/eval_v2/aabc_age__patch__logistic/log.txt b/input_space_v3/flat_lr1e-3_7/eval_v2/aabc_age__patch__logistic/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..c38280facd4898c2fae4572b945afeffc91d98bd --- /dev/null +++ b/input_space_v3/flat_lr1e-3_7/eval_v2/aabc_age__patch__logistic/log.txt @@ -0,0 +1,245 @@ +fMRI foundation model logistic probe eval +version: 0.1.dev86+gf97f52698 +sha: bcce2b486277d3a5b520775efd9cdf1a2affce36, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-04-08 22:55:21 +config: +output_root: experiments/input_space_v3/output +name_prefix: eval_logistic +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_7; eval v2 (aabc_age patch logistic) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_7/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: input_space_v3/flat_lr1e-3_7/eval_v2/aabc_age__patch__logistic +model: flat_mae +representation: patch +dataset: aabc_age +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_7/eval_v2/aabc_age__patch__logistic +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=True, reg_tokens=0, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: aabc_age (flat) +train (n=455): +HFDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'segment', 'bold', 'mean', 'std'], + num_rows: 471 +}), + labels=[0 1 2 3], + counts=[110 127 109 109] +) + +validation (n=53): +HFDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'segment', 'bold', 'mean', 'std'], + num_rows: 58 +}), + labels=[0 1 2 3], + counts=[14 13 12 14] +) + +test (n=52): +HFDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'segment', 'bold', 'mean', 'std'], + num_rows: 55 +}), + labels=[0 1 2 3], + counts=[13 13 12 14] +) + +extracting features for all splits +extract (train) [ 0/228] eta: 0:23:03 time: 6.0686 data: 5.1803 max mem: 3205 +extract (train) [ 20/228] eta: 0:01:51 time: 0.2611 data: 0.0842 max mem: 3393 +extract (train) [ 40/228] eta: 0:01:14 time: 0.2495 data: 0.0848 max mem: 3393 +extract (train) [ 60/228] eta: 0:00:58 time: 0.2509 data: 0.0815 max mem: 3393 +extract (train) [ 80/228] eta: 0:00:48 time: 0.2539 data: 0.0881 max mem: 3393 +extract (train) [100/228] eta: 0:00:40 time: 0.2652 data: 0.0892 max mem: 3393 +extract (train) [120/228] eta: 0:00:32 time: 0.2414 data: 0.0816 max mem: 3393 +extract (train) [140/228] eta: 0:00:25 time: 0.2515 data: 0.0876 max mem: 3393 +extract (train) [160/228] eta: 0:00:19 time: 0.2292 data: 0.0757 max mem: 3393 +extract (train) [180/228] eta: 0:00:13 time: 0.2666 data: 0.0962 max mem: 3393 +extract (train) [200/228] eta: 0:00:07 time: 0.2336 data: 0.0772 max mem: 3393 +extract (train) [220/228] eta: 0:00:02 time: 0.1981 data: 0.0630 max mem: 3393 +extract (train) [227/228] eta: 0:00:00 time: 0.1970 data: 0.0630 max mem: 3393 +extract (train) Total time: 0:01:02 (0.2723 s / it) +extract (validation) [ 0/27] eta: 0:02:34 time: 5.7044 data: 5.4927 max mem: 3393 +extract (validation) [20/27] eta: 0:00:03 time: 0.1810 data: 0.0500 max mem: 3393 +extract (validation) [26/27] eta: 0:00:00 time: 0.1791 data: 0.0511 max mem: 3393 +extract (validation) Total time: 0:00:10 (0.4011 s / it) +extract (test) [ 0/26] eta: 0:02:15 time: 5.2166 data: 5.0050 max mem: 3393 +extract (test) [20/26] eta: 0:00:02 time: 0.1969 data: 0.0591 max mem: 3393 +extract (test) [25/26] eta: 0:00:00 time: 0.1786 data: 0.0483 max mem: 3393 +extract (test) Total time: 0:00:10 (0.3983 s / it) +feature extraction time: 0:01:23 +train features: (455, 768) +validation features: (53, 768) +test features: (52, 768) +evaluating fixed splits +eval results (fixed splits): + +| model | repr | clf | dataset | trial | C | split | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|-----------:|:--------|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | aabc_age | | 0.00077426 | train | 0.56299 | 0.021637 | 0.55702 | 0.022072 | 0.56401 | 0.021635 | +| flat_mae | patch | logistic | aabc_age | | 0.00077426 | test | 0.44231 | 0.059962 | 0.43159 | 0.062601 | 0.43338 | 0.059756 | + + +evaluating random splits (n=100) +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 1, "C": 0.3593813663804626, "split": "test", "acc": 0.5, "acc_std": 0.0634992778228514, "f1": 0.4923443797581729, "f1_std": 0.06294142041527126, "bacc": 0.4965659340659341, "bacc_std": 0.06314131912390256} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 2, "C": 0.000774263682681127, "split": "test", "acc": 0.5961538461538461, "acc_std": 0.06567893036195949, "f1": 0.5861472678111048, "f1_std": 0.06780592873324962, "bacc": 0.5915750915750916, "bacc_std": 0.06545479104183033} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 3, "C": 0.005994842503189409, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.06329150882035754, "f1": 0.4279032258064516, "f1_std": 0.06235646465671117, "bacc": 0.4358974358974359, "bacc_std": 0.0627274203363839} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 4, "C": 0.046415888336127774, "split": "test", "acc": 0.5576923076923077, "acc_std": 0.06289565887504035, "f1": 0.5533333333333333, "f1_std": 0.06458928360966294, "bacc": 0.5604395604395604, "bacc_std": 0.06330021292210301} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 5, "C": 0.000774263682681127, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.061106851803035205, "f1": 0.3952099450201917, "f1_std": 0.05685203336964761, "bacc": 0.4191849816849817, "bacc_std": 0.060116858348639786} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 6, "C": 0.005994842503189409, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.07058793667995776, "f1": 0.48028409090909097, "f1_std": 0.07097501659286701, "bacc": 0.47756410256410253, "bacc_std": 0.0704158140154672} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 7, "C": 0.005994842503189409, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.060214839724746616, "f1": 0.43897741457325634, "f1_std": 0.05980274887536274, "bacc": 0.4741300366300366, "bacc_std": 0.05915728299069934} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 8, "C": 0.046415888336127774, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.0661323198429531, "f1": 0.5434030542726195, "f1_std": 0.06485860616393276, "bacc": 0.5441849816849816, "bacc_std": 0.06663761778030912} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 9, "C": 0.3593813663804626, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.06291455415291725, "f1": 0.4075077540594782, "f1_std": 0.061959650581912336, "bacc": 0.4207875457875458, "bacc_std": 0.06280185671643654} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 10, "C": 0.005994842503189409, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.06600451616250327, "f1": 0.4581818181818182, "f1_std": 0.0644506715892739, "bacc": 0.459478021978022, "bacc_std": 0.06581530903534881} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 11, "C": 0.005994842503189409, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.07004304466903817, "f1": 0.6180432470755051, "f1_std": 0.07069813926328403, "bacc": 0.614010989010989, "bacc_std": 0.07020085403123073} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 12, "C": 0.005994842503189409, "split": "test", "acc": 0.38461538461538464, "acc_std": 0.06551033163017768, "f1": 0.38842926714780257, "f1_std": 0.06632101632697483, "bacc": 0.38118131868131866, "bacc_std": 0.06535387435171683} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 13, "C": 0.005994842503189409, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.05841090925098348, "f1": 0.41207544723878664, "f1_std": 0.058311201554939095, "bacc": 0.4251373626373627, "bacc_std": 0.059002848185521324} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 14, "C": 0.046415888336127774, "split": "test", "acc": 0.5961538461538461, "acc_std": 0.06439550500686175, "f1": 0.589392446633826, "f1_std": 0.06689651667161536, "bacc": 0.597985347985348, "bacc_std": 0.06435475289774585} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 15, "C": 0.046415888336127774, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.06691921960590037, "f1": 0.4653846153846154, "f1_std": 0.06660904566899886, "bacc": 0.4597069597069597, "bacc_std": 0.06708466282472726} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 16, "C": 0.005994842503189409, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.06211051421725119, "f1": 0.4377136021872864, "f1_std": 0.06322181027466409, "bacc": 0.43887362637362637, "bacc_std": 0.06199435442984656} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 17, "C": 0.000774263682681127, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.06633841649420476, "f1": 0.4584331797235023, "f1_std": 0.065802206391492, "bacc": 0.4757326007326007, "bacc_std": 0.06575272203203218} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 18, "C": 0.046415888336127774, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.0642742367888791, "f1": 0.4550865800865801, "f1_std": 0.06544609815113414, "bacc": 0.459478021978022, "bacc_std": 0.06425082683281337} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 19, "C": 2.782559402207126, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.06688207187626247, "f1": 0.49057539682539675, "f1_std": 0.06742737645438748, "bacc": 0.48214285714285715, "bacc_std": 0.06702214071934241} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 20, "C": 0.005994842503189409, "split": "test", "acc": 0.5, "acc_std": 0.05978129518869484, "f1": 0.46522334757918155, "f1_std": 0.06215788563004436, "bacc": 0.4977106227106227, "bacc_std": 0.059453711843884545} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 21, "C": 0.005994842503189409, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.06189679327518898, "f1": 0.49775707384403034, "f1_std": 0.06611179439915084, "bacc": 0.5215201465201466, "bacc_std": 0.06245298693886123} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 22, "C": 0.046415888336127774, "split": "test", "acc": 0.36538461538461536, "acc_std": 0.06290467805108027, "f1": 0.3766900420757363, "f1_std": 0.06265042926959624, "bacc": 0.36790293040293043, "bacc_std": 0.0632710989898243} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 23, "C": 0.005994842503189409, "split": "test", "acc": 0.5, "acc_std": 0.05909880404080318, "f1": 0.4927248677248677, "f1_std": 0.05949904661385263, "bacc": 0.5009157509157509, "bacc_std": 0.05946716722251178} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 24, "C": 0.046415888336127774, "split": "test", "acc": 0.36538461538461536, "acc_std": 0.06245348564990177, "f1": 0.36774725274725273, "f1_std": 0.059914428683719094, "bacc": 0.3617216117216117, "bacc_std": 0.06201190311038325} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 25, "C": 2.782559402207126, "split": "test", "acc": 0.34615384615384615, "acc_std": 0.06336080583433525, "f1": 0.35937499999999994, "f1_std": 0.0610790212511034, "bacc": 0.3468406593406594, "bacc_std": 0.06363202691632361} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 26, "C": 0.000774263682681127, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.06259648174320358, "f1": 0.4477731092436975, "f1_std": 0.0638898296072777, "bacc": 0.4565018315018315, "bacc_std": 0.06224163468336934} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 27, "C": 0.046415888336127774, "split": "test", "acc": 0.40384615384615385, "acc_std": 0.06551146067132026, "f1": 0.391005291005291, "f1_std": 0.06657246933656064, "bacc": 0.39903846153846156, "bacc_std": 0.0651621157551207} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 28, "C": 0.005994842503189409, "split": "test", "acc": 0.5, "acc_std": 0.06855507870732881, "f1": 0.5012365591397849, "f1_std": 0.06952185600731048, "bacc": 0.5041208791208791, "bacc_std": 0.06881222629870458} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 29, "C": 0.046415888336127774, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.06608067285858843, "f1": 0.5225231481481482, "f1_std": 0.06765556856491249, "bacc": 0.5176282051282051, "bacc_std": 0.0664482718764335} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 30, "C": 0.005994842503189409, "split": "test", "acc": 0.5, "acc_std": 0.06472061029107887, "f1": 0.48804112554112555, "f1_std": 0.06559276519965557, "bacc": 0.5038919413919414, "bacc_std": 0.06509184200091993} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 31, "C": 0.000774263682681127, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.06210435720166462, "f1": 0.5896878733572282, "f1_std": 0.06724444404143376, "bacc": 0.6092032967032968, "bacc_std": 0.061670189397197935} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 32, "C": 0.046415888336127774, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.06027524391975364, "f1": 0.5003237503237503, "f1_std": 0.06346560995777746, "bacc": 0.5185439560439561, "bacc_std": 0.060173603893200936} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 33, "C": 166.81005372000556, "split": "test", "acc": 0.40384615384615385, "acc_std": 0.0663779188172458, "f1": 0.4047222222222222, "f1_std": 0.06572891005870361, "bacc": 0.40773809523809523, "bacc_std": 0.06689569888366988} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 34, "C": 0.3593813663804626, "split": "test", "acc": 0.38461538461538464, "acc_std": 0.062074397050883794, "f1": 0.4078996983408748, "f1_std": 0.06199273548429092, "bacc": 0.3917124542124542, "bacc_std": 0.06246202192984511} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 35, "C": 0.005994842503189409, "split": "test", "acc": 0.36538461538461536, "acc_std": 0.06306401134266056, "f1": 0.3584559884559885, "f1_std": 0.06350229426983947, "bacc": 0.3617216117216117, "bacc_std": 0.06270646985901444} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 36, "C": 0.046415888336127774, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.06379534586352012, "f1": 0.5269111476008028, "f1_std": 0.0652538979881731, "bacc": 0.538003663003663, "bacc_std": 0.06385543804741406} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 37, "C": 0.005994842503189409, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.06737042131855088, "f1": 0.43985974754558205, "f1_std": 0.06843576374632175, "bacc": 0.4391025641025641, "bacc_std": 0.06727086502624094} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 38, "C": 0.005994842503189409, "split": "test", "acc": 0.5, "acc_std": 0.06582857196973031, "f1": 0.48890837515625296, "f1_std": 0.06711534058235716, "bacc": 0.4965659340659341, "bacc_std": 0.06540304197231332} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 39, "C": 166.81005372000556, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.06462472459969017, "f1": 0.42860576923076926, "f1_std": 0.06323001696940071, "bacc": 0.4358974358974359, "bacc_std": 0.06395241130212882} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 40, "C": 0.005994842503189409, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.06568810786430751, "f1": 0.5322021528918081, "f1_std": 0.06737435934002353, "bacc": 0.5396062271062272, "bacc_std": 0.06604315612046524} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 41, "C": 0.005994842503189409, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.059845263983892456, "f1": 0.38832833832833835, "f1_std": 0.06363436395964328, "bacc": 0.4221611721611722, "bacc_std": 0.05988553989464354} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 42, "C": 0.005994842503189409, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.06112621533502161, "f1": 0.47377104377104373, "f1_std": 0.06316513953248129, "bacc": 0.48168498168498164, "bacc_std": 0.06132065177894465} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 43, "C": 9.999999999999999e-05, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.0594215210152291, "f1": 0.42017241379310344, "f1_std": 0.05054785232713505, "bacc": 0.4684065934065934, "bacc_std": 0.05802599079738626} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 44, "C": 0.3593813663804626, "split": "test", "acc": 0.5, "acc_std": 0.06548503600692607, "f1": 0.49953580901856764, "f1_std": 0.06686473589875144, "bacc": 0.5027472527472527, "bacc_std": 0.06580483260267805} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 45, "C": 0.005994842503189409, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.06425811255853846, "f1": 0.5418956043956044, "f1_std": 0.0629700756009039, "bacc": 0.5441849816849818, "bacc_std": 0.06459212975376134} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 46, "C": 0.000774263682681127, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.0638041567156967, "f1": 0.4375, "f1_std": 0.06439347957964661, "bacc": 0.4416208791208791, "bacc_std": 0.06376634145644187} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 47, "C": 0.005994842503189409, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.06318138629346856, "f1": 0.4438930205949657, "f1_std": 0.06723694266002977, "bacc": 0.45810439560439564, "bacc_std": 0.06297460803952566} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 48, "C": 0.000774263682681127, "split": "test", "acc": 0.5, "acc_std": 0.06572322952661626, "f1": 0.4884711779448621, "f1_std": 0.0668660240040807, "bacc": 0.4965659340659341, "bacc_std": 0.0656449685725548} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 49, "C": 0.005994842503189409, "split": "test", "acc": 0.36538461538461536, "acc_std": 0.061580502466476096, "f1": 0.36578648806909675, "f1_std": 0.062452462196299546, "bacc": 0.36469780219780223, "bacc_std": 0.0618220433402213} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 50, "C": 0.046415888336127774, "split": "test", "acc": 0.38461538461538464, "acc_std": 0.0657698605457927, "f1": 0.3914726507713885, "f1_std": 0.06541923695057195, "bacc": 0.3855311355311355, "bacc_std": 0.06594940617455115} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 51, "C": 0.005994842503189409, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.06953458974925812, "f1": 0.436203009606308, "f1_std": 0.06917680751627872, "bacc": 0.4432234432234432, "bacc_std": 0.06957321111653643} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 52, "C": 0.046415888336127774, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.06563229108553269, "f1": 0.4456744704570792, "f1_std": 0.06604253668710656, "bacc": 0.4450549450549451, "bacc_std": 0.0656972712226813} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 53, "C": 9.999999999999999e-05, "split": "test", "acc": 0.5576923076923077, "acc_std": 0.055674136432059915, "f1": 0.5077188940092165, "f1_std": 0.055408071872659004, "bacc": 0.5496794871794871, "bacc_std": 0.05445196166923093} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 54, "C": 0.046415888336127774, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.06438901510562332, "f1": 0.43746993746993745, "f1_std": 0.06419546457478882, "bacc": 0.4432234432234432, "bacc_std": 0.06469346782880495} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 55, "C": 0.000774263682681127, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.0645849745289974, "f1": 0.41475885225885223, "f1_std": 0.06390574055628347, "bacc": 0.4207875457875458, "bacc_std": 0.0643890583451448} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 56, "C": 9.999999999999999e-05, "split": "test", "acc": 0.40384615384615385, "acc_std": 0.06485453682469379, "f1": 0.38736129770612526, "f1_std": 0.06202536611515196, "bacc": 0.3985805860805861, "bacc_std": 0.06416102409517221} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 57, "C": 0.000774263682681127, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.05756749319007516, "f1": 0.4192927170868347, "f1_std": 0.05277752059937226, "bacc": 0.4384157509157509, "bacc_std": 0.056791044906466095} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 58, "C": 0.005994842503189409, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.05799687555346837, "f1": 0.4129901960784314, "f1_std": 0.06328471223508243, "bacc": 0.43864468864468864, "bacc_std": 0.05735759411314578} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 59, "C": 0.046415888336127774, "split": "test", "acc": 0.5, "acc_std": 0.06796338859525113, "f1": 0.5040873015873016, "f1_std": 0.06815080109917364, "bacc": 0.5013736263736264, "bacc_std": 0.06806821678272926} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 60, "C": 0.005994842503189409, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.06349135663115024, "f1": 0.4300543007439559, "f1_std": 0.06493097852887462, "bacc": 0.4416208791208791, "bacc_std": 0.06352170287596247} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 61, "C": 0.005994842503189409, "split": "test", "acc": 0.36538461538461536, "acc_std": 0.06487954245820325, "f1": 0.36355488922205564, "f1_std": 0.06270102282973072, "bacc": 0.3630952380952381, "bacc_std": 0.06458111258132736} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 62, "C": 0.005994842503189409, "split": "test", "acc": 0.5576923076923077, "acc_std": 0.058258706843500416, "f1": 0.5357471264367816, "f1_std": 0.0587249208696605, "bacc": 0.549908424908425, "bacc_std": 0.05803943675882883} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 63, "C": 0.005994842503189409, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.06136832249554455, "f1": 0.42586553945249594, "f1_std": 0.062418966108544, "bacc": 0.44299450549450553, "bacc_std": 0.061564781166553374} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 64, "C": 0.046415888336127774, "split": "test", "acc": 0.36538461538461536, "acc_std": 0.06484546947353072, "f1": 0.3695436507936508, "f1_std": 0.06463826749822274, "bacc": 0.3619505494505495, "bacc_std": 0.06461697618670839} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 65, "C": 0.3593813663804626, "split": "test", "acc": 0.5, "acc_std": 0.07001876333480127, "f1": 0.4954308560005712, "f1_std": 0.06845081300138162, "bacc": 0.49381868131868134, "bacc_std": 0.06997584526664066} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 66, "C": 0.046415888336127774, "split": "test", "acc": 0.40384615384615385, "acc_std": 0.06172179421935825, "f1": 0.4031767598343685, "f1_std": 0.0640177527582083, "bacc": 0.4033882783882784, "bacc_std": 0.06220300707074656} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 67, "C": 0.005994842503189409, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.06066079663605407, "f1": 0.47175595238095236, "f1_std": 0.06414903173768004, "bacc": 0.5112179487179487, "bacc_std": 0.059623343484066844} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 68, "C": 0.046415888336127774, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.06263743469245904, "f1": 0.42763322884012545, "f1_std": 0.06076813239259139, "bacc": 0.42536630036630035, "bacc_std": 0.06286988749307014} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 69, "C": 0.046415888336127774, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.0646545096749003, "f1": 0.42895604395604403, "f1_std": 0.06358652686753734, "bacc": 0.4269688644688645, "bacc_std": 0.0651718417931458} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 70, "C": 0.046415888336127774, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.06843435069487827, "f1": 0.43741948470209335, "f1_std": 0.06983316502163844, "bacc": 0.4391025641025641, "bacc_std": 0.06855860381873721} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 71, "C": 0.005994842503189409, "split": "test", "acc": 0.5, "acc_std": 0.06528952361207059, "f1": 0.4973789173789174, "f1_std": 0.0654292177916127, "bacc": 0.5041208791208791, "bacc_std": 0.0659022099780934} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 72, "C": 0.005994842503189409, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.06521991700366152, "f1": 0.5154882154882154, "f1_std": 0.06557487137782009, "bacc": 0.5203754578754579, "bacc_std": 0.06529600559381665} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 73, "C": 0.000774263682681127, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.05982810683001682, "f1": 0.5041360089186177, "f1_std": 0.06153225368562124, "bacc": 0.5201465201465202, "bacc_std": 0.05988862849065686} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 74, "C": 0.046415888336127774, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.06837517240331781, "f1": 0.42708333333333337, "f1_std": 0.06963072811994754, "bacc": 0.4228479853479854, "bacc_std": 0.06849898352387739} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 75, "C": 0.005994842503189409, "split": "test", "acc": 0.5576923076923077, "acc_std": 0.06762972412925264, "f1": 0.5518231768231768, "f1_std": 0.06947013293025164, "bacc": 0.5560897435897436, "bacc_std": 0.0677008645833168} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 76, "C": 0.005994842503189409, "split": "test", "acc": 0.5, "acc_std": 0.0637530716280544, "f1": 0.4921289355322339, "f1_std": 0.06517373945730633, "bacc": 0.4981684981684982, "bacc_std": 0.06392677255809767} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 77, "C": 0.046415888336127774, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.06701227477420985, "f1": 0.4790969899665552, "f1_std": 0.06726771930295743, "bacc": 0.48328754578754574, "bacc_std": 0.06729451152213703} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 78, "C": 0.046415888336127774, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.06409732799127668, "f1": 0.4807303113553113, "f1_std": 0.06352490437968884, "bacc": 0.4846611721611722, "bacc_std": 0.06464946069905743} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 79, "C": 0.005994842503189409, "split": "test", "acc": 0.5, "acc_std": 0.06207463535961839, "f1": 0.4796816087138668, "f1_std": 0.06252076747531789, "bacc": 0.49221611721611724, "bacc_std": 0.061720159565082054} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 80, "C": 0.3593813663804626, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.062173216707354345, "f1": 0.44966329966329965, "f1_std": 0.06307289568680402, "bacc": 0.46543040293040294, "bacc_std": 0.0625289734463998} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 81, "C": 0.3593813663804626, "split": "test", "acc": 0.38461538461538464, "acc_std": 0.0679985533260662, "f1": 0.38690476190476186, "f1_std": 0.0678444192341508, "bacc": 0.3855311355311355, "bacc_std": 0.06811598947927826} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 82, "C": 0.005994842503189409, "split": "test", "acc": 0.5576923076923077, "acc_std": 0.06846417453870507, "f1": 0.5510989010989011, "f1_std": 0.07097032854440895, "bacc": 0.55746336996337, "bacc_std": 0.0687636193389282} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 83, "C": 0.3593813663804626, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.06630433464638197, "f1": 0.44941423519009727, "f1_std": 0.06447885814047466, "bacc": 0.4448260073260073, "bacc_std": 0.0667635880896198} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 84, "C": 0.005994842503189409, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.06046559978530312, "f1": 0.4895179744592899, "f1_std": 0.063848588843173, "bacc": 0.5114468864468864, "bacc_std": 0.060002928477809046} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 85, "C": 0.046415888336127774, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.062139802297607925, "f1": 0.43341440518859875, "f1_std": 0.05859637502506504, "bacc": 0.4548992673992674, "bacc_std": 0.06109820152405824} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 86, "C": 21.54434690031882, "split": "test", "acc": 0.36538461538461536, "acc_std": 0.06244158216630928, "f1": 0.3476470588235294, "f1_std": 0.06283290220185146, "bacc": 0.3576007326007326, "bacc_std": 0.061947490907431825} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 87, "C": 0.005994842503189409, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.05967092945886805, "f1": 0.5316870629370629, "f1_std": 0.06012167235998682, "bacc": 0.5455586080586081, "bacc_std": 0.0603319706095827} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 88, "C": 9.999999999999999e-05, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.0669090502541858, "f1": 0.44551282051282054, "f1_std": 0.0687275355202262, "bacc": 0.4551282051282051, "bacc_std": 0.06646873210188596} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 89, "C": 0.005994842503189409, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.0661580834957779, "f1": 0.4217545638945233, "f1_std": 0.06652067831577231, "bacc": 0.43727106227106227, "bacc_std": 0.0655745754385006} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 90, "C": 9.999999999999999e-05, "split": "test", "acc": 0.5576923076923077, "acc_std": 0.05630254284986554, "f1": 0.5046082949308756, "f1_std": 0.059254659619340844, "bacc": 0.5496794871794871, "bacc_std": 0.05537558409015675} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 91, "C": 0.005994842503189409, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.06888025584280603, "f1": 0.440313836865561, "f1_std": 0.06947621620286829, "bacc": 0.443452380952381, "bacc_std": 0.06892798133273798} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 92, "C": 0.005994842503189409, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.0542422110133916, "f1": 0.4928030303030303, "f1_std": 0.06333077105490388, "bacc": 0.5347985347985349, "bacc_std": 0.053712279105290056} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 93, "C": 0.046415888336127774, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.06510055944641864, "f1": 0.4944516630573602, "f1_std": 0.0625214658077899, "bacc": 0.4819139194139194, "bacc_std": 0.06555129983839343} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 94, "C": 0.000774263682681127, "split": "test", "acc": 0.36538461538461536, "acc_std": 0.05760859310901456, "f1": 0.34293906810035846, "f1_std": 0.05530080540485442, "bacc": 0.3628663003663004, "bacc_std": 0.057020076343442506} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 95, "C": 0.046415888336127774, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.06338166301936697, "f1": 0.5267857142857143, "f1_std": 0.06339440619681545, "bacc": 0.5350274725274725, "bacc_std": 0.06300333620751775} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 96, "C": 0.3593813663804626, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.06552558333205373, "f1": 0.48964342713435904, "f1_std": 0.0660391951340157, "bacc": 0.4837454212454213, "bacc_std": 0.06552335422404702} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 97, "C": 0.000774263682681127, "split": "test", "acc": 0.40384615384615385, "acc_std": 0.06291605894660585, "f1": 0.3833759590792839, "f1_std": 0.06176256801184485, "bacc": 0.3985805860805861, "bacc_std": 0.06213028989648064} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 98, "C": 0.005994842503189409, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.05885575587824865, "f1": 0.43253968253968256, "f1_std": 0.06357799927210456, "bacc": 0.46222527472527475, "bacc_std": 0.05928465021433887} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 99, "C": 0.000774263682681127, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.06179006258549612, "f1": 0.43741993873572826, "f1_std": 0.062163395531114204, "bacc": 0.4592490842490842, "bacc_std": 0.061462982918972106} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 100, "C": 0.005994842503189409, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.06844393680383311, "f1": 0.4354166666666667, "f1_std": 0.06933355589770297, "bacc": 0.43887362637362637, "bacc_std": 0.06817869861095498} +eval results (random splits): + +| model | repr | clf | dataset | split | n_trials | C | C_std | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|-----------:|-------:|--------:|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | aabc_age | train | 100 | 3.6543 | 23.527 | 0.73959 | 0.14127 | 0.73575 | 0.14619 | 0.74034 | 0.14154 | +| flat_mae | patch | logistic | aabc_age | test | 100 | 3.6543 | 23.527 | 0.46827 | 0.060959 | 0.45806 | 0.058729 | 0.46682 | 0.061012 | + + +done! total time: 0:05:52 diff --git a/input_space_v3/flat_lr1e-3_7/eval_v2/aabc_sex__patch__logistic/config.yaml b/input_space_v3/flat_lr1e-3_7/eval_v2/aabc_sex__patch__logistic/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..af689e101546111206a51eb42b16b8582c6b06d1 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_7/eval_v2/aabc_sex__patch__logistic/config.yaml @@ -0,0 +1,30 @@ +output_root: experiments/input_space_v3/output +name_prefix: eval_logistic +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_7; eval v2 (aabc_sex patch logistic) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_7/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: input_space_v3/flat_lr1e-3_7/eval_v2/aabc_sex__patch__logistic +model: flat_mae +representation: patch +dataset: aabc_sex +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_7/eval_v2/aabc_sex__patch__logistic +remote_dir: null diff --git a/input_space_v3/flat_lr1e-3_7/eval_v2/aabc_sex__patch__logistic/eval_table.csv b/input_space_v3/flat_lr1e-3_7/eval_v2/aabc_sex__patch__logistic/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..5340e3f38bbb42b449c821260b40d98d8e3585f3 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_7/eval_v2/aabc_sex__patch__logistic/eval_table.csv @@ -0,0 +1,203 @@ +model,repr,clf,dataset,trial,C,split,acc,acc_std,f1,f1_std,bacc,bacc_std +flat_mae,patch,logistic,aabc_sex,,0.005994842503189409,train,0.9054820415879017,0.012594902372864893,0.9025997937840624,0.013061549973101189,0.9002488290398127,0.013386913575160489 +flat_mae,patch,logistic,aabc_sex,,0.005994842503189409,test,0.8909090909090909,0.04217203648339767,0.8879076086956521,0.04309692414732024,0.8939393939393939,0.042269946688174596 +flat_mae,patch,logistic,aabc_sex,1,0.046415888336127774,train,0.9489603024574669,0.009766938308897162,0.947507690272219,0.010069650817011128,0.9461517043289662,0.010325918077896819 +flat_mae,patch,logistic,aabc_sex,1,0.046415888336127774,test,0.8363636363636363,0.048846678664254364,0.8328267477203647,0.0500684321180112,0.8349184782608696,0.04988443743000356 +flat_mae,patch,logistic,aabc_sex,2,0.3593813663804626,train,0.9924385633270322,0.00371784968698348,0.9922477212110554,0.0038112795736447726,0.9922477212110554,0.0038478222576265337 +flat_mae,patch,logistic,aabc_sex,2,0.3593813663804626,test,0.8727272727272727,0.04605335030570701,0.8699763593380614,0.04689357230985005,0.8722826086956521,0.04658373345085795 +flat_mae,patch,logistic,aabc_sex,3,0.046415888336127774,train,0.945179584120983,0.010116495831522175,0.943691387252473,0.010421304563280246,0.9428837304727571,0.010687514854831078 +flat_mae,patch,logistic,aabc_sex,3,0.046415888336127774,test,0.7818181818181819,0.05433086272670532,0.7727272727272727,0.057513090089219655,0.7697010869565217,0.057389796558622266 +flat_mae,patch,logistic,aabc_sex,4,0.3593813663804626,train,0.9886578449905482,0.004846808654416355,0.9883715818165831,0.004970797316199359,0.9883715818165831,0.005048514065254388 +flat_mae,patch,logistic,aabc_sex,4,0.3593813663804626,test,0.8545454545454545,0.04700421644529734,0.8533333333333333,0.04694392616385566,0.8627717391304348,0.04459920289164837 +flat_mae,patch,logistic,aabc_sex,5,0.3593813663804626,train,0.9886578449905482,0.004827921063484132,0.9883855386416862,0.0049367594375318525,0.9889797473548463,0.004743661638460713 +flat_mae,patch,logistic,aabc_sex,5,0.3593813663804626,test,0.8545454545454545,0.046074477974917476,0.84593837535014,0.05062201382907182,0.8383152173913043,0.050772845676504544 +flat_mae,patch,logistic,aabc_sex,6,0.046415888336127774,train,0.941398865784499,0.010177431832749731,0.9398080346491953,0.010492284969989446,0.9390075910782849,0.010836853529215871 +flat_mae,patch,logistic,aabc_sex,6,0.046415888336127774,test,0.9272727272727272,0.03665158718221091,0.9252717391304348,0.037676477828171816,0.9252717391304348,0.03793582409885245 +flat_mae,patch,logistic,aabc_sex,7,0.005994842503189409,train,0.9111531190926276,0.011971845646142908,0.9082563052342207,0.012457284507836393,0.905565813769454,0.012838939697735812 +flat_mae,patch,logistic,aabc_sex,7,0.005994842503189409,test,0.9090909090909091,0.03879662590765055,0.9071259709557582,0.03958031903844246,0.9096467391304348,0.0392158054055788 +flat_mae,patch,logistic,aabc_sex,8,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,8,2.782559402207126,test,0.8545454545454545,0.04308506289455891,0.8533333333333333,0.04313751027861425,0.8627717391304348,0.04162935020652706 +flat_mae,patch,logistic,aabc_sex,9,0.3593813663804626,train,0.996219281663516,0.0026764148115681094,0.9961190832526338,0.0027526791000207803,0.9955156950672646,0.0031744920074428954 +flat_mae,patch,logistic,aabc_sex,9,0.3593813663804626,test,0.9090909090909091,0.038696974917538395,0.9071259709557582,0.039375194669125424,0.9096467391304348,0.03897871960662062 +flat_mae,patch,logistic,aabc_sex,10,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,10,21.54434690031882,test,0.8727272727272727,0.04565064608089687,0.8699763593380614,0.04637124214387501,0.8722826086956521,0.045818382656016336 +flat_mae,patch,logistic,aabc_sex,11,0.005994842503189409,train,0.9073724007561437,0.012508025946707219,0.9044834307992202,0.012964153282567207,0.9022978399132449,0.013211372506144433 +flat_mae,patch,logistic,aabc_sex,11,0.005994842503189409,test,0.8727272727272727,0.04618718651690213,0.8663658451926415,0.04992612590168431,0.8600543478260869,0.05040087297886363 +flat_mae,patch,logistic,aabc_sex,12,0.005994842503189409,train,0.9149338374291115,0.012229423513032928,0.9121602922455305,0.012706785783446271,0.9094419531639262,0.013008593534103934 +flat_mae,patch,logistic,aabc_sex,12,0.005994842503189409,test,0.8,0.05311793832502184,0.790003471017008,0.057460511757611854,0.7853260869565217,0.05701289687081716 +flat_mae,patch,logistic,aabc_sex,13,0.3593813663804626,train,0.9924385633270322,0.003647503735960629,0.9922477212110554,0.0037398566554367463,0.9922477212110554,0.0037908727267228245 +flat_mae,patch,logistic,aabc_sex,13,0.3593813663804626,test,0.8727272727272727,0.04406342536101175,0.8683760683760684,0.04587776459165242,0.8661684782608696,0.046276258220503456 +flat_mae,patch,logistic,aabc_sex,14,0.046415888336127774,train,0.945179584120983,0.00963534444824277,0.943691387252473,0.009915446640290305,0.9428837304727571,0.0101415560447758 +flat_mae,patch,logistic,aabc_sex,14,0.046415888336127774,test,0.9454545454545454,0.030521094182264258,0.9442755825734549,0.03105324786382826,0.9470108695652174,0.030035358047571886 +flat_mae,patch,logistic,aabc_sex,15,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,15,21.54434690031882,test,0.8727272727272727,0.04374205382383493,0.8663658451926415,0.04711383966870055,0.8600543478260869,0.04775803758335564 +flat_mae,patch,logistic,aabc_sex,16,0.005994842503189409,train,0.9073724007561437,0.012269858154617645,0.904352318222911,0.012772517993106728,0.9016896743749816,0.013136629566026094 +flat_mae,patch,logistic,aabc_sex,16,0.005994842503189409,test,0.8909090909090909,0.04336697147456844,0.8863636363636364,0.04616621100965508,0.8817934782608696,0.04724517696251419 +flat_mae,patch,logistic,aabc_sex,17,0.3593813663804626,train,0.9924385633270322,0.0036246403490592413,0.9922570257611241,0.0037079334516561964,0.9928558867493186,0.003522861627991592 +flat_mae,patch,logistic,aabc_sex,17,0.3593813663804626,test,0.8545454545454545,0.04598151263423409,0.8484848484848485,0.048870831066882524,0.8444293478260869,0.0490235535279526 +flat_mae,patch,logistic,aabc_sex,18,0.005994842503189409,train,0.9092627599243857,0.012230769904142123,0.9062389223679547,0.01273165369649476,0.9033236613030862,0.013068708167517961 +flat_mae,patch,logistic,aabc_sex,18,0.005994842503189409,test,0.8909090909090909,0.041220134693281035,0.89,0.041188100216798494,0.9001358695652174,0.03841552691505135 +flat_mae,patch,logistic,aabc_sex,19,0.046415888336127774,train,0.9489603024574669,0.009112377499150386,0.9475747398557507,0.009390913982846322,0.9467598698672295,0.009713052803768078 +flat_mae,patch,logistic,aabc_sex,19,0.046415888336127774,test,0.8727272727272727,0.04263859269226481,0.8699763593380614,0.04341689175001126,0.8722826086956521,0.043010941736206225 +flat_mae,patch,logistic,aabc_sex,20,0.046415888336127774,train,0.9395085066162571,0.010751474895463017,0.9378268790033496,0.01109014146461395,0.9367654386119171,0.011419866430766278 +flat_mae,patch,logistic,aabc_sex,20,0.046415888336127774,test,0.8545454545454545,0.04704666225942138,0.8505434782608696,0.048715424335647385,0.8505434782608696,0.048887450637693376 +flat_mae,patch,logistic,aabc_sex,21,0.005994842503189409,train,0.9130434782608695,0.01212090220695806,0.9105104442483083,0.012520568491519278,0.9090242973123479,0.012755743967997762 +flat_mae,patch,logistic,aabc_sex,21,0.005994842503189409,test,0.8363636363636363,0.046935806346065576,0.8281846581048247,0.050638454383670685,0.8226902173913043,0.05077208431169486 +flat_mae,patch,logistic,aabc_sex,22,0.005994842503189409,train,0.9017013232514177,0.012087935069686155,0.8985663293902475,0.012562726163150384,0.8961795480524049,0.012885113767335568 +flat_mae,patch,logistic,aabc_sex,22,0.005994842503189409,test,0.9454545454545454,0.030531685208204498,0.9442755825734549,0.031119085664288105,0.9470108695652174,0.030249032194588295 +flat_mae,patch,logistic,aabc_sex,23,0.046415888336127774,train,0.945179584120983,0.010084742829788707,0.943691387252473,0.010387786909477665,0.9428837304727571,0.010691945617714707 +flat_mae,patch,logistic,aabc_sex,23,0.046415888336127774,test,0.8727272727272727,0.046136613523729886,0.8699763593380614,0.047121404166561826,0.8722826086956521,0.0469920201867601 +flat_mae,patch,logistic,aabc_sex,24,0.046415888336127774,train,0.943289224952741,0.010221425663993767,0.9418579090829157,0.010477960696847602,0.9418579090829157,0.010545567826723721 +flat_mae,patch,logistic,aabc_sex,24,0.046415888336127774,test,0.9090909090909091,0.03977807860103455,0.905982905982906,0.041610493355931734,0.9035326086956521,0.04246215424775472 +flat_mae,patch,logistic,aabc_sex,25,0.046415888336127774,train,0.943289224952741,0.009917627728844214,0.9416372462488967,0.010245631398641843,0.9400334124681262,0.010535321266183416 +flat_mae,patch,logistic,aabc_sex,25,0.046415888336127774,test,0.9454545454545454,0.02918022652130568,0.9427282193682749,0.031664370923333296,0.9347826086956521,0.03488940127547418 +flat_mae,patch,logistic,aabc_sex,26,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,26,2.782559402207126,test,0.8363636363636363,0.04707617881232763,0.8307692307692308,0.04941903129895646,0.8288043478260869,0.04976246566570466 +flat_mae,patch,logistic,aabc_sex,27,0.005994842503189409,train,0.9073724007561437,0.012786192104132055,0.904352318222911,0.01333898348104938,0.9016896743749816,0.01380284790957201 +flat_mae,patch,logistic,aabc_sex,27,0.005994842503189409,test,0.9272727272727272,0.03139932093806969,0.9260752688172043,0.0316918665866954,0.9313858695652174,0.030144554991530487 +flat_mae,patch,logistic,aabc_sex,28,0.005994842503189409,train,0.9092627599243857,0.012397860328583145,0.9062389223679547,0.012911357744857018,0.9033236613030862,0.013283434427330492 +flat_mae,patch,logistic,aabc_sex,28,0.005994842503189409,test,0.9090909090909091,0.03587371790550342,0.9045470322804582,0.03883309133520261,0.8974184782608696,0.040463555079089004 +flat_mae,patch,logistic,aabc_sex,29,0.046415888336127774,train,0.947069943289225,0.009976022654963026,0.9455280964989703,0.010317152369926917,0.9439095518625986,0.0106890018955563 +flat_mae,patch,logistic,aabc_sex,29,0.046415888336127774,test,0.8545454545454545,0.04715711737382028,0.8505434782608696,0.048683147962009156,0.8505434782608696,0.04859913659825104 +flat_mae,patch,logistic,aabc_sex,30,0.046415888336127774,train,0.9508506616257089,0.009042887109166396,0.9494189467490438,0.009339684076377475,0.9477856912570708,0.009641716517222473 +flat_mae,patch,logistic,aabc_sex,30,0.046415888336127774,test,0.8545454545454545,0.04896095931648072,0.8505434782608696,0.05047913753866206,0.8505434782608696,0.05058516163367205 +flat_mae,patch,logistic,aabc_sex,31,0.046415888336127774,train,0.947069943289225,0.009883173771380222,0.9456671655368724,0.01016479785210518,0.9451258829391249,0.010347615904872851 +flat_mae,patch,logistic,aabc_sex,31,0.046415888336127774,test,0.8363636363636363,0.0481663645886416,0.8328267477203647,0.048994341578062164,0.8349184782608696,0.0484365529817783 +flat_mae,patch,logistic,aabc_sex,32,0.046415888336127774,train,0.9489603024574669,0.009969071062555387,0.9476400828491303,0.01024864838155578,0.9473680354054925,0.010450708414409341 +flat_mae,patch,logistic,aabc_sex,32,0.046415888336127774,test,0.9272727272727272,0.032908508282135374,0.9229691876750701,0.03650935066270448,0.9130434782608696,0.03934712946777055 +flat_mae,patch,logistic,aabc_sex,33,0.046415888336127774,train,0.945179584120983,0.009754308260275155,0.9436193710331242,0.010059522166807559,0.942275564934494,0.010316742377753428 +flat_mae,patch,logistic,aabc_sex,33,0.046415888336127774,test,0.8909090909090909,0.0413211730090395,0.8863636363636364,0.043849431437950066,0.8817934782608696,0.04474844276973933 +flat_mae,patch,logistic,aabc_sex,34,0.046415888336127774,train,0.9489603024574669,0.00979899981105401,0.9474389216202193,0.01012460372581586,0.9455435387907032,0.010434064204274356 +flat_mae,patch,logistic,aabc_sex,34,0.046415888336127774,test,0.8727272727272727,0.04493902572439516,0.8683760683760684,0.04680575677418286,0.8661684782608696,0.04724613510372552 +flat_mae,patch,logistic,aabc_sex,35,0.005994842503189409,train,0.9111531190926276,0.012282679938493093,0.9083820662768032,0.012736977411156938,0.906173979307717,0.013023788153119827 +flat_mae,patch,logistic,aabc_sex,35,0.005994842503189409,test,0.9272727272727272,0.033218037517724106,0.9242424242424243,0.035269344707076954,0.9191576086956521,0.03708773511546374 +flat_mae,patch,logistic,aabc_sex,36,0.046415888336127774,train,0.945179584120983,0.009251932254133104,0.9436193710331242,0.009543128776056207,0.942275564934494,0.009808212324617396 +flat_mae,patch,logistic,aabc_sex,36,0.046415888336127774,test,0.8909090909090909,0.04233708102540923,0.8879076086956521,0.04341965967025573,0.8879076086956521,0.043269874488667114 +flat_mae,patch,logistic,aabc_sex,37,0.046415888336127774,train,0.9527410207939508,0.009658796413365645,0.9514580924590283,0.009938102190481881,0.9506360092617017,0.010148709113521556 +flat_mae,patch,logistic,aabc_sex,37,0.046415888336127774,test,0.7818181818181819,0.05489915623551877,0.7727272727272727,0.0584795998813719,0.7697010869565217,0.05818418467039395 +flat_mae,patch,logistic,aabc_sex,38,0.005994842503189409,train,0.9149338374291115,0.0125045651520602,0.9123982027003654,0.012936430328092611,0.9106582842404525,0.013208986072761926 +flat_mae,patch,logistic,aabc_sex,38,0.005994842503189409,test,0.9090909090909091,0.0370826372237881,0.9045470322804582,0.04012468373673815,0.8974184782608696,0.04173992855027674 +flat_mae,patch,logistic,aabc_sex,39,0.005994842503189409,train,0.9206049149338374,0.011199809992532906,0.9182921447484554,0.01157972741886227,0.9167765761012925,0.011851003676895407 +flat_mae,patch,logistic,aabc_sex,39,0.005994842503189409,test,0.8545454545454545,0.046470109472435746,0.8505434782608696,0.04783956222507828,0.8505434782608696,0.04789976345478235 +flat_mae,patch,logistic,aabc_sex,40,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,40,166.81005372000556,test,0.8727272727272727,0.04246637561472887,0.8663658451926415,0.04586104721135025,0.8600543478260869,0.04683813444781412 +flat_mae,patch,logistic,aabc_sex,41,0.005994842503189409,train,0.9054820415879017,0.01326792507406592,0.9023322107999527,0.013794767764748132,0.899447521908614,0.014076064748496367 +flat_mae,patch,logistic,aabc_sex,41,0.005994842503189409,test,0.9090909090909091,0.038799761437453534,0.9071259709557582,0.03953151333306776,0.9096467391304348,0.0389440257958579 +flat_mae,patch,logistic,aabc_sex,42,0.005994842503189409,train,0.9092627599243857,0.011954363546187903,0.9063689194371516,0.01244541257140989,0.9039318268413494,0.012844130677667648 +flat_mae,patch,logistic,aabc_sex,42,0.005994842503189409,test,0.8181818181818182,0.052731736488170464,0.8176392572944298,0.05262912930553662,0.8315217391304348,0.0498483215225242 +flat_mae,patch,logistic,aabc_sex,43,0.005994842503189409,train,0.9092627599243857,0.012299540832609243,0.9066195939982348,0.012719573202644857,0.9051481579178757,0.013060662965812148 +flat_mae,patch,logistic,aabc_sex,43,0.005994842503189409,test,0.9090909090909091,0.03805344653757962,0.9071259709557582,0.03871469061039398,0.9096467391304348,0.03792990461660763 +flat_mae,patch,logistic,aabc_sex,44,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,44,166.81005372000556,test,0.8181818181818182,0.050031117589683365,0.8106060606060606,0.053205136360619125,0.8070652173913043,0.05326755510668714 +flat_mae,patch,logistic,aabc_sex,45,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,45,166.81005372000556,test,0.8909090909090909,0.0400227373393204,0.89,0.04001610461321927,0.9001358695652174,0.037360156384509735 +flat_mae,patch,logistic,aabc_sex,46,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,46,166.81005372000556,test,0.8363636363636363,0.0524920017520182,0.8343927735028438,0.052935254028082405,0.8410326086956521,0.05239831122172568 +flat_mae,patch,logistic,aabc_sex,47,0.046415888336127774,train,0.9508506616257089,0.009357975953033722,0.9494843391902215,0.009646043508512381,0.9483938567953341,0.009911323683601021 +flat_mae,patch,logistic,aabc_sex,47,0.046415888336127774,test,0.8363636363636363,0.0455521715242919,0.8250265111346766,0.05104486837839133,0.8165760869565217,0.05056741593256237 +flat_mae,patch,logistic,aabc_sex,48,0.005994842503189409,train,0.9073724007561437,0.01255361264412938,0.9046113762737312,0.01300177537049738,0.9029060054515079,0.013341720859571606 +flat_mae,patch,logistic,aabc_sex,48,0.005994842503189409,test,0.9272727272727272,0.034434194037442856,0.9252717391304348,0.035388059506945735,0.9252717391304348,0.03547972901307465 +flat_mae,patch,logistic,aabc_sex,49,0.005994842503189409,train,0.9111531190926276,0.01247767364449586,0.9083820662768032,0.012940195152930158,0.906173979307717,0.013226798649405623 +flat_mae,patch,logistic,aabc_sex,49,0.005994842503189409,test,0.8909090909090909,0.03911880611337132,0.8879076086956521,0.04038969800798005,0.8879076086956521,0.040493054299033035 +flat_mae,patch,logistic,aabc_sex,50,0.046415888336127774,train,0.9546313799621928,0.008749378694018683,0.9534863272663325,0.00896461780742971,0.9534863272663325,0.009025043695597706 +flat_mae,patch,logistic,aabc_sex,50,0.046415888336127774,test,0.8727272727272727,0.04601589376877126,0.8683760683760684,0.04786679180359651,0.8661684782608696,0.04820649437756565 +flat_mae,patch,logistic,aabc_sex,51,0.005994842503189409,train,0.9111531190926276,0.012233130990049312,0.9085047894870484,0.012670261284791146,0.9067821448459803,0.012995589456075983 +flat_mae,patch,logistic,aabc_sex,51,0.005994842503189409,test,0.8909090909090909,0.042415824273027286,0.884453781512605,0.04670111369598083,0.8756793478260869,0.04789762241707091 +flat_mae,patch,logistic,aabc_sex,52,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,52,21.54434690031882,test,0.8181818181818182,0.05135704221549333,0.8151881720430108,0.05234214598194479,0.8192934782608696,0.05220964518883776 +flat_mae,patch,logistic,aabc_sex,53,0.046415888336127774,train,0.943289224952741,0.010574882078509184,0.9416372462488967,0.010918062554234931,0.9400334124681262,0.011191029681313679 +flat_mae,patch,logistic,aabc_sex,53,0.046415888336127774,test,0.9090909090909091,0.03711079680725573,0.905982905982906,0.03878572768541896,0.9035326086956521,0.039722727632985184 +flat_mae,patch,logistic,aabc_sex,54,0.046415888336127774,train,0.9527410207939508,0.009418175365887033,0.9513323348335363,0.00975449218780438,0.9494196781851754,0.010187984231796815 +flat_mae,patch,logistic,aabc_sex,54,0.046415888336127774,test,0.8181818181818182,0.05326421278528728,0.8151881720430108,0.053702337057782865,0.8192934782608696,0.05288053356024892 +flat_mae,patch,logistic,aabc_sex,55,0.3593813663804626,train,0.9924385633270322,0.003984676248510412,0.9922381665052675,0.004096647665733886,0.9916395556727923,0.0044358305428665555 +flat_mae,patch,logistic,aabc_sex,55,0.3593813663804626,test,0.8727272727272727,0.04167405995013291,0.8683760683760684,0.04374079425501306,0.8661684782608696,0.044473181408608765 +flat_mae,patch,logistic,aabc_sex,56,0.005994842503189409,train,0.9149338374291115,0.012535372886950894,0.9121602922455305,0.013029239961412023,0.9094419531639262,0.013394728921270681 +flat_mae,patch,logistic,aabc_sex,56,0.005994842503189409,test,0.8909090909090909,0.04110955329240183,0.8879076086956521,0.04236650711799648,0.8879076086956521,0.04257579027196111 +flat_mae,patch,logistic,aabc_sex,57,0.046415888336127774,train,0.9489603024574669,0.00945256027154515,0.947507690272219,0.00975972440273295,0.9461517043289662,0.010102715361207762 +flat_mae,patch,logistic,aabc_sex,57,0.046415888336127774,test,0.8727272727272727,0.04480925229134146,0.8683760683760684,0.046790184117893,0.8661684782608696,0.04726722659822225 +flat_mae,patch,logistic,aabc_sex,58,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,58,21.54434690031882,test,0.7818181818181819,0.05317134628835066,0.7782258064516129,0.053819011215223415,0.7819293478260869,0.0536447191492692 +flat_mae,patch,logistic,aabc_sex,59,0.005994842503189409,train,0.9111531190926276,0.012114957222076821,0.9085047894870484,0.01254159911227034,0.9067821448459803,0.012822876862101802 +flat_mae,patch,logistic,aabc_sex,59,0.005994842503189409,test,0.9090909090909091,0.03610606963465853,0.9071259709557582,0.03679828957287189,0.9096467391304348,0.03641811721931786 +flat_mae,patch,logistic,aabc_sex,60,0.046415888336127774,train,0.945179584120983,0.009817397208306017,0.943691387252473,0.010107722982106684,0.9428837304727571,0.010358184927479116 +flat_mae,patch,logistic,aabc_sex,60,0.046415888336127774,test,0.8363636363636363,0.05010612209176017,0.8250265111346766,0.05601216022721616,0.8165760869565217,0.05541963859306374 +flat_mae,patch,logistic,aabc_sex,61,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,61,21.54434690031882,test,0.8363636363636363,0.04887391773441885,0.8343927735028438,0.049114575699282424,0.8410326086956521,0.04817744569125808 +flat_mae,patch,logistic,aabc_sex,62,0.005994842503189409,train,0.9111531190926276,0.01262751944101653,0.9083820662768032,0.013131490329878504,0.906173979307717,0.013529583537006697 +flat_mae,patch,logistic,aabc_sex,62,0.005994842503189409,test,0.8909090909090909,0.040169492144829934,0.8863636363636364,0.04277633333919114,0.8817934782608696,0.044080344171814806 +flat_mae,patch,logistic,aabc_sex,63,0.005994842503189409,train,0.9073724007561437,0.012775010895108,0.9044834307992202,0.01329188773055336,0.9022978399132449,0.013669285931979072 +flat_mae,patch,logistic,aabc_sex,63,0.005994842503189409,test,0.9090909090909091,0.039532808845395895,0.905982905982906,0.041477744778405164,0.9035326086956521,0.04273985746208119 +flat_mae,patch,logistic,aabc_sex,64,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,64,21.54434690031882,test,0.8363636363636363,0.04755745025104019,0.8343927735028438,0.04787568368196243,0.8410326086956521,0.0470552928460749 +flat_mae,patch,logistic,aabc_sex,65,0.005994842503189409,train,0.9092627599243857,0.01203856888376781,0.9063689194371516,0.012529891116319419,0.9039318268413494,0.01290712024817296 +flat_mae,patch,logistic,aabc_sex,65,0.005994842503189409,test,0.8545454545454545,0.04619943829932948,0.84593837535014,0.05079596744079444,0.8383152173913043,0.05099160235158537 +flat_mae,patch,logistic,aabc_sex,66,0.005994842503189409,train,0.9092627599243857,0.012010934563570662,0.9063689194371516,0.012445716052939369,0.9039318268413494,0.012674981010581366 +flat_mae,patch,logistic,aabc_sex,66,0.005994842503189409,test,0.8727272727272727,0.03986454751731581,0.8639095086603039,0.04495239187599646,0.8539402173913043,0.045512887181104 +flat_mae,patch,logistic,aabc_sex,67,0.005994842503189409,train,0.9073724007561437,0.013079611331187426,0.9044834307992202,0.013595411055480223,0.9022978399132449,0.013960086426073725 +flat_mae,patch,logistic,aabc_sex,67,0.005994842503189409,test,0.8909090909090909,0.04199423809355101,0.8879076086956521,0.043208612955838235,0.8879076086956521,0.04339512982896532 +flat_mae,patch,logistic,aabc_sex,68,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,68,2.782559402207126,test,0.9454545454545454,0.031174878634106024,0.9435897435897436,0.03267241434376968,0.9408967391304348,0.03424558565248709 +flat_mae,patch,logistic,aabc_sex,69,0.046415888336127774,train,0.941398865784499,0.010010485460121376,0.9398080346491953,0.01029672768918794,0.9390075910782849,0.010450137283203395 +flat_mae,patch,logistic,aabc_sex,69,0.046415888336127774,test,0.9818181818181818,0.016719365720105676,0.9814251941911516,0.01694977278756107,0.984375,0.014368204915715811 +flat_mae,patch,logistic,aabc_sex,70,0.3593813663804626,train,0.9867674858223062,0.005077575103636847,0.9864417081324122,0.005201702979853921,0.9867375948884786,0.005213441954862275 +flat_mae,patch,logistic,aabc_sex,70,0.3593813663804626,test,0.9636363636363636,0.025389292986357614,0.9626358695652174,0.026107541891597287,0.9626358695652174,0.026370193032599513 +flat_mae,patch,logistic,aabc_sex,71,0.005994842503189409,train,0.9073724007561437,0.01204821865494594,0.9046113762737312,0.01244103432897264,0.9029060054515079,0.012619406722507944 +flat_mae,patch,logistic,aabc_sex,71,0.005994842503189409,test,0.8545454545454545,0.04490782478892432,0.84593837535014,0.04899040935668485,0.8383152173913043,0.04894890010836689 +flat_mae,patch,logistic,aabc_sex,72,0.005994842503189409,train,0.9054820415879017,0.012755740264770806,0.9024676244136995,0.013271697161573453,0.900055687446877,0.013605315168924397 +flat_mae,patch,logistic,aabc_sex,72,0.005994842503189409,test,0.8909090909090909,0.043044639523819185,0.8879076086956521,0.044321635917092254,0.8879076086956521,0.04440219312103784 +flat_mae,patch,logistic,aabc_sex,73,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,73,2.782559402207126,test,0.8909090909090909,0.04142740738502263,0.884453781512605,0.04536773182673929,0.8756793478260869,0.046754636168976446 +flat_mae,patch,logistic,aabc_sex,74,0.005994842503189409,train,0.9149338374291115,0.011472523602823054,0.9122807017543859,0.011928020418932423,0.9100501187021894,0.0123601145851841 +flat_mae,patch,logistic,aabc_sex,74,0.005994842503189409,test,0.8909090909090909,0.04323322872647499,0.8879076086956521,0.044573334088862535,0.8879076086956521,0.044847176947793194 +flat_mae,patch,logistic,aabc_sex,75,0.3593813663804626,train,0.9867674858223062,0.004722908695459355,0.9864417081324122,0.00483652351519641,0.9867375948884786,0.004806637899825561 +flat_mae,patch,logistic,aabc_sex,75,0.3593813663804626,test,0.8909090909090909,0.039647021085974864,0.8879076086956521,0.04107593034959675,0.8879076086956521,0.04159029264539115 +flat_mae,patch,logistic,aabc_sex,76,0.3593813663804626,train,0.9905482041587902,0.0040329810513039435,0.9903269809575008,0.004118851459722999,0.991221899821214,0.0037882961352730077 +flat_mae,patch,logistic,aabc_sex,76,0.3593813663804626,test,0.7818181818181819,0.05528999730197942,0.7727272727272727,0.05813205378709966,0.7697010869565217,0.057687032144448966 +flat_mae,patch,logistic,aabc_sex,77,0.005994842503189409,train,0.9092627599243857,0.012492707983443898,0.9068579980632098,0.012818893985829275,0.906364488994402,0.01292665908856712 +flat_mae,patch,logistic,aabc_sex,77,0.005994842503189409,test,0.9090909090909091,0.036197347055886536,0.9027925061859314,0.041080423696260505,0.8913043478260869,0.04327943669725565 +flat_mae,patch,logistic,aabc_sex,78,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,78,166.81005372000556,test,0.9090909090909091,0.038867862609122894,0.9079959852793577,0.03903862050719454,0.9157608695652174,0.03721944228701482 +flat_mae,patch,logistic,aabc_sex,79,0.046415888336127774,train,0.947069943289225,0.009343883025015357,0.9455280964989703,0.009660220557432934,0.9439095518625986,0.009989330687593312 +flat_mae,patch,logistic,aabc_sex,79,0.046415888336127774,test,0.8909090909090909,0.040809187103716185,0.884453781512605,0.04514988454452098,0.8756793478260869,0.0465051870029881 +flat_mae,patch,logistic,aabc_sex,80,0.046415888336127774,train,0.945179584120983,0.009643562384338918,0.943691387252473,0.009935277667025075,0.9428837304727571,0.010192063558657807 +flat_mae,patch,logistic,aabc_sex,80,0.046415888336127774,test,0.8545454545454545,0.04705297173144676,0.84593837535014,0.05188888623915395,0.8383152173913043,0.05218783659533417 +flat_mae,patch,logistic,aabc_sex,81,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,81,21.54434690031882,test,0.8909090909090909,0.04061821437290142,0.8891129032258065,0.04115315417782604,0.8940217391304348,0.040541759456222896 +flat_mae,patch,logistic,aabc_sex,82,0.005994842503189409,train,0.9035916824196597,0.012706909962717039,0.9005847953216375,0.01318761144679847,0.8984217005187725,0.013508899128801105 +flat_mae,patch,logistic,aabc_sex,82,0.005994842503189409,test,0.9272727272727272,0.031694742374956716,0.9229691876750701,0.03495757395155499,0.9130434782608696,0.037895887622230846 +flat_mae,patch,logistic,aabc_sex,83,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,83,2.782559402207126,test,0.9090909090909091,0.03528695120890774,0.9027925061859314,0.04008916802328859,0.8913043478260869,0.042190919923694024 +flat_mae,patch,logistic,aabc_sex,84,0.046415888336127774,train,0.945179584120983,0.010614016426709462,0.943691387252473,0.010919142725650635,0.9428837304727571,0.0110813945363151 +flat_mae,patch,logistic,aabc_sex,84,0.046415888336127774,test,0.8,0.05638614213433462,0.7931623931623932,0.05862786356837511,0.7914402173913043,0.05862247287490361 +flat_mae,patch,logistic,aabc_sex,85,0.3593813663804626,train,0.9924385633270322,0.00382765570774373,0.9922477212110554,0.003925052672251268,0.9922477212110554,0.004000349823151897 +flat_mae,patch,logistic,aabc_sex,85,0.3593813663804626,test,0.8909090909090909,0.04209550730822934,0.8863636363636364,0.04472420238398311,0.8817934782608696,0.04604226314480674 +flat_mae,patch,logistic,aabc_sex,86,0.046415888336127774,train,0.947069943289225,0.010258687828142281,0.9456671655368724,0.010531318973239265,0.9451258829391249,0.010641254535355268 +flat_mae,patch,logistic,aabc_sex,86,0.046415888336127774,test,0.9272727272727272,0.03562706743312307,0.9252717391304348,0.03676330183362444,0.9252717391304348,0.037221339283368265 +flat_mae,patch,logistic,aabc_sex,87,0.046415888336127774,train,0.9489603024574669,0.009619481158495802,0.9475747398557507,0.009897927090826862,0.9467598698672295,0.010108417943838205 +flat_mae,patch,logistic,aabc_sex,87,0.046415888336127774,test,0.8909090909090909,0.04206007509925977,0.8863636363636364,0.04452342640411865,0.8817934782608696,0.0453766779556642 +flat_mae,patch,logistic,aabc_sex,88,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,88,166.81005372000556,test,0.8363636363636363,0.04752241750257718,0.8281846581048247,0.051286249333197635,0.8226902173913043,0.05136038601428067 +flat_mae,patch,logistic,aabc_sex,89,0.3593813663804626,train,0.9848771266540642,0.0053651830101286305,0.9845140515222482,0.005487432461057936,0.9851036079603739,0.005365064169485895 +flat_mae,patch,logistic,aabc_sex,89,0.3593813663804626,test,0.8909090909090909,0.03880189140827421,0.884453781512605,0.04290130894639533,0.8756793478260869,0.04409818934900239 +flat_mae,patch,logistic,aabc_sex,90,0.046415888336127774,train,0.943289224952741,0.01007906891128995,0.9415598762704375,0.010444729740119696,0.9394252469298632,0.010876260064824717 +flat_mae,patch,logistic,aabc_sex,90,0.046415888336127774,test,0.8181818181818182,0.05319216993269552,0.8106060606060606,0.056775369790063986,0.8070652173913043,0.056718785655781985 +flat_mae,patch,logistic,aabc_sex,91,0.046415888336127774,train,0.9565217391304348,0.00923231290875802,0.9553414450623061,0.009512400342208094,0.9545121486561741,0.009817667965712006 +flat_mae,patch,logistic,aabc_sex,91,0.046415888336127774,test,0.8727272727272727,0.045084149053384245,0.8699763593380614,0.045880929692043694,0.8722826086956521,0.045412745510578875 +flat_mae,patch,logistic,aabc_sex,92,0.005994842503189409,train,0.9035916824196597,0.013326214296052354,0.9004483312116013,0.013865030789137943,0.8978135349805094,0.014214890832976694 +flat_mae,patch,logistic,aabc_sex,92,0.005994842503189409,test,0.9272727272727272,0.03444624990084415,0.9242424242424243,0.03656097706408236,0.9191576086956521,0.03819811494787725 +flat_mae,patch,logistic,aabc_sex,93,0.046415888336127774,train,0.9489603024574669,0.009607991064970794,0.9475747398557507,0.009895312706972094,0.9467598698672295,0.010141508458342443 +flat_mae,patch,logistic,aabc_sex,93,0.046415888336127774,test,0.9090909090909091,0.03934019457362799,0.9045470322804582,0.04261779802356295,0.8974184782608696,0.04417167959342643 +flat_mae,patch,logistic,aabc_sex,94,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,94,1291.5496650148827,test,0.8363636363636363,0.048752381590480266,0.8307692307692308,0.05088649980346008,0.8288043478260869,0.0507843448417117 +flat_mae,patch,logistic,aabc_sex,95,0.046415888336127774,train,0.9489603024574669,0.009151883755979457,0.9474389216202193,0.009467214265908056,0.9455435387907032,0.009815030910233323 +flat_mae,patch,logistic,aabc_sex,95,0.046415888336127774,test,0.9090909090909091,0.038783126602827026,0.9071259709557582,0.039487743078217626,0.9096467391304348,0.038921795264619835 +flat_mae,patch,logistic,aabc_sex,96,0.046415888336127774,train,0.9508506616257089,0.009086137538927251,0.9496101878718604,0.009316597558282248,0.9496101878718604,0.009425322609497465 +flat_mae,patch,logistic,aabc_sex,96,0.046415888336127774,test,0.9272727272727272,0.03512426111690131,0.9242424242424243,0.037252457068302526,0.9191576086956521,0.038899226615328436 +flat_mae,patch,logistic,aabc_sex,97,0.005994842503189409,train,0.9130434782608695,0.01247835179319032,0.9105104442483083,0.012885617410978463,0.9090242973123479,0.013104669058435558 +flat_mae,patch,logistic,aabc_sex,97,0.005994842503189409,test,0.8909090909090909,0.04087717542925857,0.8863636363636364,0.04353053019132902,0.8817934782608696,0.04444009349759543 +flat_mae,patch,logistic,aabc_sex,98,0.3593813663804626,train,0.9905482041587902,0.004075319754652611,0.9903155058088658,0.004173793692987925,0.9906137342829509,0.00411844099419988 +flat_mae,patch,logistic,aabc_sex,98,0.3593813663804626,test,0.8,0.053637830488416756,0.790003471017008,0.057416705327683455,0.7853260869565217,0.05702996353781206 +flat_mae,patch,logistic,aabc_sex,99,0.005994842503189409,train,0.9092627599243857,0.013122892407451962,0.9066195939982348,0.013549111867514528,0.9051481579178757,0.013778689326296676 +flat_mae,patch,logistic,aabc_sex,99,0.005994842503189409,test,0.8909090909090909,0.04252841927794861,0.8863636363636364,0.04527929963479037,0.8817934782608696,0.04648285186083802 +flat_mae,patch,logistic,aabc_sex,100,0.046415888336127774,train,0.9489603024574669,0.009680812610356537,0.9476400828491303,0.00995580200421407,0.9473680354054925,0.010221167659903075 +flat_mae,patch,logistic,aabc_sex,100,0.046415888336127774,test,0.8909090909090909,0.040841965130273536,0.8891129032258065,0.04129092669145905,0.8940217391304348,0.04016015083699117 diff --git a/input_space_v3/flat_lr1e-3_7/eval_v2/aabc_sex__patch__logistic/log.txt b/input_space_v3/flat_lr1e-3_7/eval_v2/aabc_sex__patch__logistic/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..ac0163523c25c374fedab879fa8244843dcf6f0e --- /dev/null +++ b/input_space_v3/flat_lr1e-3_7/eval_v2/aabc_sex__patch__logistic/log.txt @@ -0,0 +1,245 @@ +fMRI foundation model logistic probe eval +version: 0.1.dev86+gf97f52698 +sha: bcce2b486277d3a5b520775efd9cdf1a2affce36, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-04-08 22:55:46 +config: +output_root: experiments/input_space_v3/output +name_prefix: eval_logistic +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_7; eval v2 (aabc_sex patch logistic) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_7/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: input_space_v3/flat_lr1e-3_7/eval_v2/aabc_sex__patch__logistic +model: flat_mae +representation: patch +dataset: aabc_sex +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_7/eval_v2/aabc_sex__patch__logistic +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=True, reg_tokens=0, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: aabc_sex (flat) +train (n=471): +HFDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'segment', 'bold', 'mean', 'std'], + num_rows: 471 +}), + labels=[0 1], + counts=[269 202] +) + +validation (n=58): +HFDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'segment', 'bold', 'mean', 'std'], + num_rows: 58 +}), + labels=[0 1], + counts=[36 22] +) + +test (n=55): +HFDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'segment', 'bold', 'mean', 'std'], + num_rows: 55 +}), + labels=[0 1], + counts=[33 22] +) + +extracting features for all splits +extract (train) [ 0/236] eta: 0:21:09 time: 5.3800 data: 4.3768 max mem: 3205 +extract (train) [ 20/236] eta: 0:01:45 time: 0.2434 data: 0.0880 max mem: 3393 +extract (train) [ 40/236] eta: 0:01:09 time: 0.2093 data: 0.0661 max mem: 3393 +extract (train) [ 60/236] eta: 0:00:53 time: 0.2075 data: 0.0668 max mem: 3393 +extract (train) [ 80/236] eta: 0:00:43 time: 0.2032 data: 0.0666 max mem: 3393 +extract (train) [100/236] eta: 0:00:35 time: 0.1996 data: 0.0648 max mem: 3393 +extract (train) [120/236] eta: 0:00:29 time: 0.1954 data: 0.0617 max mem: 3393 +extract (train) [140/236] eta: 0:00:23 time: 0.2261 data: 0.0818 max mem: 3393 +extract (train) [160/236] eta: 0:00:18 time: 0.1930 data: 0.0644 max mem: 3393 +extract (train) [180/236] eta: 0:00:13 time: 0.1929 data: 0.0624 max mem: 3393 +extract (train) [200/236] eta: 0:00:08 time: 0.2089 data: 0.0709 max mem: 3393 +extract (train) [220/236] eta: 0:00:03 time: 0.1822 data: 0.0556 max mem: 3393 +extract (train) [235/236] eta: 0:00:00 time: 0.1824 data: 0.0588 max mem: 3393 +extract (train) Total time: 0:00:53 (0.2285 s / it) +extract (validation) [ 0/29] eta: 0:02:06 time: 4.3498 data: 4.1792 max mem: 3393 +extract (validation) [20/29] eta: 0:00:03 time: 0.2087 data: 0.0687 max mem: 3393 +extract (validation) [28/29] eta: 0:00:00 time: 0.1762 data: 0.0517 max mem: 3393 +extract (validation) Total time: 0:00:10 (0.3570 s / it) +extract (test) [ 0/28] eta: 0:02:00 time: 4.2887 data: 4.1142 max mem: 3393 +extract (test) [20/28] eta: 0:00:03 time: 0.1863 data: 0.0592 max mem: 3393 +extract (test) [27/28] eta: 0:00:00 time: 0.1692 data: 0.0509 max mem: 3393 +extract (test) Total time: 0:00:09 (0.3404 s / it) +feature extraction time: 0:01:13 +train features: (471, 768) +validation features: (58, 768) +test features: (55, 768) +evaluating fixed splits +eval results (fixed splits): + +| model | repr | clf | dataset | trial | C | split | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|----------:|:--------|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | aabc_sex | | 0.0059948 | train | 0.90548 | 0.012595 | 0.9026 | 0.013062 | 0.90025 | 0.013387 | +| flat_mae | patch | logistic | aabc_sex | | 0.0059948 | test | 0.89091 | 0.042172 | 0.88791 | 0.043097 | 0.89394 | 0.04227 | + + +evaluating random splits (n=100) +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 1, "C": 0.046415888336127774, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.048846678664254364, "f1": 0.8328267477203647, "f1_std": 0.0500684321180112, "bacc": 0.8349184782608696, "bacc_std": 0.04988443743000356} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 2, "C": 0.3593813663804626, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.04605335030570701, "f1": 0.8699763593380614, "f1_std": 0.04689357230985005, "bacc": 0.8722826086956521, "bacc_std": 0.04658373345085795} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 3, "C": 0.046415888336127774, "split": "test", "acc": 0.7818181818181819, "acc_std": 0.05433086272670532, "f1": 0.7727272727272727, "f1_std": 0.057513090089219655, "bacc": 0.7697010869565217, "bacc_std": 0.057389796558622266} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 4, "C": 0.3593813663804626, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.04700421644529734, "f1": 0.8533333333333333, "f1_std": 0.04694392616385566, "bacc": 0.8627717391304348, "bacc_std": 0.04459920289164837} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 5, "C": 0.3593813663804626, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.046074477974917476, "f1": 0.84593837535014, "f1_std": 0.05062201382907182, "bacc": 0.8383152173913043, "bacc_std": 0.050772845676504544} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 6, "C": 0.046415888336127774, "split": "test", "acc": 0.9272727272727272, "acc_std": 0.03665158718221091, "f1": 0.9252717391304348, "f1_std": 0.037676477828171816, "bacc": 0.9252717391304348, "bacc_std": 0.03793582409885245} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 7, "C": 0.005994842503189409, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.03879662590765055, "f1": 0.9071259709557582, "f1_std": 0.03958031903844246, "bacc": 0.9096467391304348, "bacc_std": 0.0392158054055788} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 8, "C": 2.782559402207126, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.04308506289455891, "f1": 0.8533333333333333, "f1_std": 0.04313751027861425, "bacc": 0.8627717391304348, "bacc_std": 0.04162935020652706} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 9, "C": 0.3593813663804626, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.038696974917538395, "f1": 0.9071259709557582, "f1_std": 0.039375194669125424, "bacc": 0.9096467391304348, "bacc_std": 0.03897871960662062} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 10, "C": 21.54434690031882, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.04565064608089687, "f1": 0.8699763593380614, "f1_std": 0.04637124214387501, "bacc": 0.8722826086956521, "bacc_std": 0.045818382656016336} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 11, "C": 0.005994842503189409, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.04618718651690213, "f1": 0.8663658451926415, "f1_std": 0.04992612590168431, "bacc": 0.8600543478260869, "bacc_std": 0.05040087297886363} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 12, "C": 0.005994842503189409, "split": "test", "acc": 0.8, "acc_std": 0.05311793832502184, "f1": 0.790003471017008, "f1_std": 0.057460511757611854, "bacc": 0.7853260869565217, "bacc_std": 0.05701289687081716} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 13, "C": 0.3593813663804626, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.04406342536101175, "f1": 0.8683760683760684, "f1_std": 0.04587776459165242, "bacc": 0.8661684782608696, "bacc_std": 0.046276258220503456} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 14, "C": 0.046415888336127774, "split": "test", "acc": 0.9454545454545454, "acc_std": 0.030521094182264258, "f1": 0.9442755825734549, "f1_std": 0.03105324786382826, "bacc": 0.9470108695652174, "bacc_std": 0.030035358047571886} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 15, "C": 21.54434690031882, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.04374205382383493, "f1": 0.8663658451926415, "f1_std": 0.04711383966870055, "bacc": 0.8600543478260869, "bacc_std": 0.04775803758335564} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 16, "C": 0.005994842503189409, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.04336697147456844, "f1": 0.8863636363636364, "f1_std": 0.04616621100965508, "bacc": 0.8817934782608696, "bacc_std": 0.04724517696251419} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 17, "C": 0.3593813663804626, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.04598151263423409, "f1": 0.8484848484848485, "f1_std": 0.048870831066882524, "bacc": 0.8444293478260869, "bacc_std": 0.0490235535279526} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 18, "C": 0.005994842503189409, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.041220134693281035, "f1": 0.89, "f1_std": 0.041188100216798494, "bacc": 0.9001358695652174, "bacc_std": 0.03841552691505135} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 19, "C": 0.046415888336127774, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.04263859269226481, "f1": 0.8699763593380614, "f1_std": 0.04341689175001126, "bacc": 0.8722826086956521, "bacc_std": 0.043010941736206225} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 20, "C": 0.046415888336127774, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.04704666225942138, "f1": 0.8505434782608696, "f1_std": 0.048715424335647385, "bacc": 0.8505434782608696, "bacc_std": 0.048887450637693376} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 21, "C": 0.005994842503189409, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.046935806346065576, "f1": 0.8281846581048247, "f1_std": 0.050638454383670685, "bacc": 0.8226902173913043, "bacc_std": 0.05077208431169486} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 22, "C": 0.005994842503189409, "split": "test", "acc": 0.9454545454545454, "acc_std": 0.030531685208204498, "f1": 0.9442755825734549, "f1_std": 0.031119085664288105, "bacc": 0.9470108695652174, "bacc_std": 0.030249032194588295} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 23, "C": 0.046415888336127774, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.046136613523729886, "f1": 0.8699763593380614, "f1_std": 0.047121404166561826, "bacc": 0.8722826086956521, "bacc_std": 0.0469920201867601} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 24, "C": 0.046415888336127774, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.03977807860103455, "f1": 0.905982905982906, "f1_std": 0.041610493355931734, "bacc": 0.9035326086956521, "bacc_std": 0.04246215424775472} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 25, "C": 0.046415888336127774, "split": "test", "acc": 0.9454545454545454, "acc_std": 0.02918022652130568, "f1": 0.9427282193682749, "f1_std": 0.031664370923333296, "bacc": 0.9347826086956521, "bacc_std": 0.03488940127547418} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 26, "C": 2.782559402207126, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.04707617881232763, "f1": 0.8307692307692308, "f1_std": 0.04941903129895646, "bacc": 0.8288043478260869, "bacc_std": 0.04976246566570466} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 27, "C": 0.005994842503189409, "split": "test", "acc": 0.9272727272727272, "acc_std": 0.03139932093806969, "f1": 0.9260752688172043, "f1_std": 0.0316918665866954, "bacc": 0.9313858695652174, "bacc_std": 0.030144554991530487} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 28, "C": 0.005994842503189409, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.03587371790550342, "f1": 0.9045470322804582, "f1_std": 0.03883309133520261, "bacc": 0.8974184782608696, "bacc_std": 0.040463555079089004} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 29, "C": 0.046415888336127774, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.04715711737382028, "f1": 0.8505434782608696, "f1_std": 0.048683147962009156, "bacc": 0.8505434782608696, "bacc_std": 0.04859913659825104} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 30, "C": 0.046415888336127774, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.04896095931648072, "f1": 0.8505434782608696, "f1_std": 0.05047913753866206, "bacc": 0.8505434782608696, "bacc_std": 0.05058516163367205} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 31, "C": 0.046415888336127774, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.0481663645886416, "f1": 0.8328267477203647, "f1_std": 0.048994341578062164, "bacc": 0.8349184782608696, "bacc_std": 0.0484365529817783} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 32, "C": 0.046415888336127774, "split": "test", "acc": 0.9272727272727272, "acc_std": 0.032908508282135374, "f1": 0.9229691876750701, "f1_std": 0.03650935066270448, "bacc": 0.9130434782608696, "bacc_std": 0.03934712946777055} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 33, "C": 0.046415888336127774, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.0413211730090395, "f1": 0.8863636363636364, "f1_std": 0.043849431437950066, "bacc": 0.8817934782608696, "bacc_std": 0.04474844276973933} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 34, "C": 0.046415888336127774, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.04493902572439516, "f1": 0.8683760683760684, "f1_std": 0.04680575677418286, "bacc": 0.8661684782608696, "bacc_std": 0.04724613510372552} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 35, "C": 0.005994842503189409, "split": "test", "acc": 0.9272727272727272, "acc_std": 0.033218037517724106, "f1": 0.9242424242424243, "f1_std": 0.035269344707076954, "bacc": 0.9191576086956521, "bacc_std": 0.03708773511546374} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 36, "C": 0.046415888336127774, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.04233708102540923, "f1": 0.8879076086956521, "f1_std": 0.04341965967025573, "bacc": 0.8879076086956521, "bacc_std": 0.043269874488667114} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 37, "C": 0.046415888336127774, "split": "test", "acc": 0.7818181818181819, "acc_std": 0.05489915623551877, "f1": 0.7727272727272727, "f1_std": 0.0584795998813719, "bacc": 0.7697010869565217, "bacc_std": 0.05818418467039395} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 38, "C": 0.005994842503189409, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.0370826372237881, "f1": 0.9045470322804582, "f1_std": 0.04012468373673815, "bacc": 0.8974184782608696, "bacc_std": 0.04173992855027674} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 39, "C": 0.005994842503189409, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.046470109472435746, "f1": 0.8505434782608696, "f1_std": 0.04783956222507828, "bacc": 0.8505434782608696, "bacc_std": 0.04789976345478235} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 40, "C": 166.81005372000556, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.04246637561472887, "f1": 0.8663658451926415, "f1_std": 0.04586104721135025, "bacc": 0.8600543478260869, "bacc_std": 0.04683813444781412} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 41, "C": 0.005994842503189409, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.038799761437453534, "f1": 0.9071259709557582, "f1_std": 0.03953151333306776, "bacc": 0.9096467391304348, "bacc_std": 0.0389440257958579} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 42, "C": 0.005994842503189409, "split": "test", "acc": 0.8181818181818182, "acc_std": 0.052731736488170464, "f1": 0.8176392572944298, "f1_std": 0.05262912930553662, "bacc": 0.8315217391304348, "bacc_std": 0.0498483215225242} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 43, "C": 0.005994842503189409, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.03805344653757962, "f1": 0.9071259709557582, "f1_std": 0.03871469061039398, "bacc": 0.9096467391304348, "bacc_std": 0.03792990461660763} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 44, "C": 166.81005372000556, "split": "test", "acc": 0.8181818181818182, "acc_std": 0.050031117589683365, "f1": 0.8106060606060606, "f1_std": 0.053205136360619125, "bacc": 0.8070652173913043, "bacc_std": 0.05326755510668714} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 45, "C": 166.81005372000556, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.0400227373393204, "f1": 0.89, "f1_std": 0.04001610461321927, "bacc": 0.9001358695652174, "bacc_std": 0.037360156384509735} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 46, "C": 166.81005372000556, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.0524920017520182, "f1": 0.8343927735028438, "f1_std": 0.052935254028082405, "bacc": 0.8410326086956521, "bacc_std": 0.05239831122172568} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 47, "C": 0.046415888336127774, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.0455521715242919, "f1": 0.8250265111346766, "f1_std": 0.05104486837839133, "bacc": 0.8165760869565217, "bacc_std": 0.05056741593256237} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 48, "C": 0.005994842503189409, "split": "test", "acc": 0.9272727272727272, "acc_std": 0.034434194037442856, "f1": 0.9252717391304348, "f1_std": 0.035388059506945735, "bacc": 0.9252717391304348, "bacc_std": 0.03547972901307465} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 49, "C": 0.005994842503189409, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.03911880611337132, "f1": 0.8879076086956521, "f1_std": 0.04038969800798005, "bacc": 0.8879076086956521, "bacc_std": 0.040493054299033035} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 50, "C": 0.046415888336127774, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.04601589376877126, "f1": 0.8683760683760684, "f1_std": 0.04786679180359651, "bacc": 0.8661684782608696, "bacc_std": 0.04820649437756565} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 51, "C": 0.005994842503189409, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.042415824273027286, "f1": 0.884453781512605, "f1_std": 0.04670111369598083, "bacc": 0.8756793478260869, "bacc_std": 0.04789762241707091} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 52, "C": 21.54434690031882, "split": "test", "acc": 0.8181818181818182, "acc_std": 0.05135704221549333, "f1": 0.8151881720430108, "f1_std": 0.05234214598194479, "bacc": 0.8192934782608696, "bacc_std": 0.05220964518883776} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 53, "C": 0.046415888336127774, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.03711079680725573, "f1": 0.905982905982906, "f1_std": 0.03878572768541896, "bacc": 0.9035326086956521, "bacc_std": 0.039722727632985184} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 54, "C": 0.046415888336127774, "split": "test", "acc": 0.8181818181818182, "acc_std": 0.05326421278528728, "f1": 0.8151881720430108, "f1_std": 0.053702337057782865, "bacc": 0.8192934782608696, "bacc_std": 0.05288053356024892} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 55, "C": 0.3593813663804626, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.04167405995013291, "f1": 0.8683760683760684, "f1_std": 0.04374079425501306, "bacc": 0.8661684782608696, "bacc_std": 0.044473181408608765} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 56, "C": 0.005994842503189409, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.04110955329240183, "f1": 0.8879076086956521, "f1_std": 0.04236650711799648, "bacc": 0.8879076086956521, "bacc_std": 0.04257579027196111} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 57, "C": 0.046415888336127774, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.04480925229134146, "f1": 0.8683760683760684, "f1_std": 0.046790184117893, "bacc": 0.8661684782608696, "bacc_std": 0.04726722659822225} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 58, "C": 21.54434690031882, "split": "test", "acc": 0.7818181818181819, "acc_std": 0.05317134628835066, "f1": 0.7782258064516129, "f1_std": 0.053819011215223415, "bacc": 0.7819293478260869, "bacc_std": 0.0536447191492692} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 59, "C": 0.005994842503189409, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.03610606963465853, "f1": 0.9071259709557582, "f1_std": 0.03679828957287189, "bacc": 0.9096467391304348, "bacc_std": 0.03641811721931786} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 60, "C": 0.046415888336127774, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.05010612209176017, "f1": 0.8250265111346766, "f1_std": 0.05601216022721616, "bacc": 0.8165760869565217, "bacc_std": 0.05541963859306374} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 61, "C": 21.54434690031882, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.04887391773441885, "f1": 0.8343927735028438, "f1_std": 0.049114575699282424, "bacc": 0.8410326086956521, "bacc_std": 0.04817744569125808} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 62, "C": 0.005994842503189409, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.040169492144829934, "f1": 0.8863636363636364, "f1_std": 0.04277633333919114, "bacc": 0.8817934782608696, "bacc_std": 0.044080344171814806} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 63, "C": 0.005994842503189409, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.039532808845395895, "f1": 0.905982905982906, "f1_std": 0.041477744778405164, "bacc": 0.9035326086956521, "bacc_std": 0.04273985746208119} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 64, "C": 21.54434690031882, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.04755745025104019, "f1": 0.8343927735028438, "f1_std": 0.04787568368196243, "bacc": 0.8410326086956521, "bacc_std": 0.0470552928460749} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 65, "C": 0.005994842503189409, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.04619943829932948, "f1": 0.84593837535014, "f1_std": 0.05079596744079444, "bacc": 0.8383152173913043, "bacc_std": 0.05099160235158537} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 66, "C": 0.005994842503189409, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.03986454751731581, "f1": 0.8639095086603039, "f1_std": 0.04495239187599646, "bacc": 0.8539402173913043, "bacc_std": 0.045512887181104} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 67, "C": 0.005994842503189409, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.04199423809355101, "f1": 0.8879076086956521, "f1_std": 0.043208612955838235, "bacc": 0.8879076086956521, "bacc_std": 0.04339512982896532} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 68, "C": 2.782559402207126, "split": "test", "acc": 0.9454545454545454, "acc_std": 0.031174878634106024, "f1": 0.9435897435897436, "f1_std": 0.03267241434376968, "bacc": 0.9408967391304348, "bacc_std": 0.03424558565248709} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 69, "C": 0.046415888336127774, "split": "test", "acc": 0.9818181818181818, "acc_std": 0.016719365720105676, "f1": 0.9814251941911516, "f1_std": 0.01694977278756107, "bacc": 0.984375, "bacc_std": 0.014368204915715811} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 70, "C": 0.3593813663804626, "split": "test", "acc": 0.9636363636363636, "acc_std": 0.025389292986357614, "f1": 0.9626358695652174, "f1_std": 0.026107541891597287, "bacc": 0.9626358695652174, "bacc_std": 0.026370193032599513} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 71, "C": 0.005994842503189409, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.04490782478892432, "f1": 0.84593837535014, "f1_std": 0.04899040935668485, "bacc": 0.8383152173913043, "bacc_std": 0.04894890010836689} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 72, "C": 0.005994842503189409, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.043044639523819185, "f1": 0.8879076086956521, "f1_std": 0.044321635917092254, "bacc": 0.8879076086956521, "bacc_std": 0.04440219312103784} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 73, "C": 2.782559402207126, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.04142740738502263, "f1": 0.884453781512605, "f1_std": 0.04536773182673929, "bacc": 0.8756793478260869, "bacc_std": 0.046754636168976446} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 74, "C": 0.005994842503189409, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.04323322872647499, "f1": 0.8879076086956521, "f1_std": 0.044573334088862535, "bacc": 0.8879076086956521, "bacc_std": 0.044847176947793194} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 75, "C": 0.3593813663804626, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.039647021085974864, "f1": 0.8879076086956521, "f1_std": 0.04107593034959675, "bacc": 0.8879076086956521, "bacc_std": 0.04159029264539115} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 76, "C": 0.3593813663804626, "split": "test", "acc": 0.7818181818181819, "acc_std": 0.05528999730197942, "f1": 0.7727272727272727, "f1_std": 0.05813205378709966, "bacc": 0.7697010869565217, "bacc_std": 0.057687032144448966} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 77, "C": 0.005994842503189409, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.036197347055886536, "f1": 0.9027925061859314, "f1_std": 0.041080423696260505, "bacc": 0.8913043478260869, "bacc_std": 0.04327943669725565} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 78, "C": 166.81005372000556, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.038867862609122894, "f1": 0.9079959852793577, "f1_std": 0.03903862050719454, "bacc": 0.9157608695652174, "bacc_std": 0.03721944228701482} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 79, "C": 0.046415888336127774, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.040809187103716185, "f1": 0.884453781512605, "f1_std": 0.04514988454452098, "bacc": 0.8756793478260869, "bacc_std": 0.0465051870029881} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 80, "C": 0.046415888336127774, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.04705297173144676, "f1": 0.84593837535014, "f1_std": 0.05188888623915395, "bacc": 0.8383152173913043, "bacc_std": 0.05218783659533417} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 81, "C": 21.54434690031882, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.04061821437290142, "f1": 0.8891129032258065, "f1_std": 0.04115315417782604, "bacc": 0.8940217391304348, "bacc_std": 0.040541759456222896} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 82, "C": 0.005994842503189409, "split": "test", "acc": 0.9272727272727272, "acc_std": 0.031694742374956716, "f1": 0.9229691876750701, "f1_std": 0.03495757395155499, "bacc": 0.9130434782608696, "bacc_std": 0.037895887622230846} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 83, "C": 2.782559402207126, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.03528695120890774, "f1": 0.9027925061859314, "f1_std": 0.04008916802328859, "bacc": 0.8913043478260869, "bacc_std": 0.042190919923694024} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 84, "C": 0.046415888336127774, "split": "test", "acc": 0.8, "acc_std": 0.05638614213433462, "f1": 0.7931623931623932, "f1_std": 0.05862786356837511, "bacc": 0.7914402173913043, "bacc_std": 0.05862247287490361} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 85, "C": 0.3593813663804626, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.04209550730822934, "f1": 0.8863636363636364, "f1_std": 0.04472420238398311, "bacc": 0.8817934782608696, "bacc_std": 0.04604226314480674} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 86, "C": 0.046415888336127774, "split": "test", "acc": 0.9272727272727272, "acc_std": 0.03562706743312307, "f1": 0.9252717391304348, "f1_std": 0.03676330183362444, "bacc": 0.9252717391304348, "bacc_std": 0.037221339283368265} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 87, "C": 0.046415888336127774, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.04206007509925977, "f1": 0.8863636363636364, "f1_std": 0.04452342640411865, "bacc": 0.8817934782608696, "bacc_std": 0.0453766779556642} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 88, "C": 166.81005372000556, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.04752241750257718, "f1": 0.8281846581048247, "f1_std": 0.051286249333197635, "bacc": 0.8226902173913043, "bacc_std": 0.05136038601428067} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 89, "C": 0.3593813663804626, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.03880189140827421, "f1": 0.884453781512605, "f1_std": 0.04290130894639533, "bacc": 0.8756793478260869, "bacc_std": 0.04409818934900239} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 90, "C": 0.046415888336127774, "split": "test", "acc": 0.8181818181818182, "acc_std": 0.05319216993269552, "f1": 0.8106060606060606, "f1_std": 0.056775369790063986, "bacc": 0.8070652173913043, "bacc_std": 0.056718785655781985} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 91, "C": 0.046415888336127774, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.045084149053384245, "f1": 0.8699763593380614, "f1_std": 0.045880929692043694, "bacc": 0.8722826086956521, "bacc_std": 0.045412745510578875} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 92, "C": 0.005994842503189409, "split": "test", "acc": 0.9272727272727272, "acc_std": 0.03444624990084415, "f1": 0.9242424242424243, "f1_std": 0.03656097706408236, "bacc": 0.9191576086956521, "bacc_std": 0.03819811494787725} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 93, "C": 0.046415888336127774, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.03934019457362799, "f1": 0.9045470322804582, "f1_std": 0.04261779802356295, "bacc": 0.8974184782608696, "bacc_std": 0.04417167959342643} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 94, "C": 1291.5496650148827, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.048752381590480266, "f1": 0.8307692307692308, "f1_std": 0.05088649980346008, "bacc": 0.8288043478260869, "bacc_std": 0.0507843448417117} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 95, "C": 0.046415888336127774, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.038783126602827026, "f1": 0.9071259709557582, "f1_std": 0.039487743078217626, "bacc": 0.9096467391304348, "bacc_std": 0.038921795264619835} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 96, "C": 0.046415888336127774, "split": "test", "acc": 0.9272727272727272, "acc_std": 0.03512426111690131, "f1": 0.9242424242424243, "f1_std": 0.037252457068302526, "bacc": 0.9191576086956521, "bacc_std": 0.038899226615328436} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 97, "C": 0.005994842503189409, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.04087717542925857, "f1": 0.8863636363636364, "f1_std": 0.04353053019132902, "bacc": 0.8817934782608696, "bacc_std": 0.04444009349759543} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 98, "C": 0.3593813663804626, "split": "test", "acc": 0.8, "acc_std": 0.053637830488416756, "f1": 0.790003471017008, "f1_std": 0.057416705327683455, "bacc": 0.7853260869565217, "bacc_std": 0.05702996353781206} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 99, "C": 0.005994842503189409, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.04252841927794861, "f1": 0.8863636363636364, "f1_std": 0.04527929963479037, "bacc": 0.8817934782608696, "bacc_std": 0.04648285186083802} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 100, "C": 0.046415888336127774, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.040841965130273536, "f1": 0.8891129032258065, "f1_std": 0.04129092669145905, "bacc": 0.8940217391304348, "bacc_std": 0.04016015083699117} +eval results (random splits): + +| model | repr | clf | dataset | split | n_trials | C | C_std | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|-----------:|-------:|--------:|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | aabc_sex | train | 100 | 24.636 | 134 | 0.95049 | 0.035353 | 0.94902 | 0.036457 | 0.94798 | 0.037354 | +| flat_mae | patch | logistic | aabc_sex | test | 100 | 24.636 | 134 | 0.87745 | 0.042038 | 0.87315 | 0.043548 | 0.87164 | 0.043721 | + + +done! total time: 0:05:11 diff --git a/input_space_v3/flat_lr1e-3_7/eval_v2/abide_dx__patch__logistic/config.yaml b/input_space_v3/flat_lr1e-3_7/eval_v2/abide_dx__patch__logistic/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..67eee51779403f8a43af2825e0038d2967709d73 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_7/eval_v2/abide_dx__patch__logistic/config.yaml @@ -0,0 +1,30 @@ +output_root: experiments/input_space_v3/output +name_prefix: eval_logistic +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_7; eval v2 (abide_dx patch logistic) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_7/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: input_space_v3/flat_lr1e-3_7/eval_v2/abide_dx__patch__logistic +model: flat_mae +representation: patch +dataset: abide_dx +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_7/eval_v2/abide_dx__patch__logistic +remote_dir: null diff --git a/input_space_v3/flat_lr1e-3_7/eval_v2/abide_dx__patch__logistic/eval_table.csv b/input_space_v3/flat_lr1e-3_7/eval_v2/abide_dx__patch__logistic/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..281b9c84acda2cee08198dd0e355cda8942446a8 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_7/eval_v2/abide_dx__patch__logistic/eval_table.csv @@ -0,0 +1,203 @@ +model,repr,clf,dataset,trial,C,split,acc,acc_std,f1,f1_std,bacc,bacc_std +flat_mae,patch,logistic,abide_dx,,0.046415888336127774,train,0.7991452991452992,0.014679763575778658,0.7941832684234273,0.015203649941874103,0.7915736423928033,0.015132255575998201 +flat_mae,patch,logistic,abide_dx,,0.046415888336127774,test,0.6774193548387096,0.04264894327088058,0.6743697478991597,0.04338514976012468,0.6739984289080911,0.043219521071095925 +flat_mae,patch,logistic,abide_dx,1,0.046415888336127774,train,0.792022792022792,0.01562662246347019,0.7877150976379649,0.016147222891515003,0.7856773717238834,0.016133659705478788 +flat_mae,patch,logistic,abide_dx,1,0.046415888336127774,test,0.7258064516129032,0.039037203099177735,0.724011521340665,0.03942666132903838,0.7247899159663866,0.039524567384582744 +flat_mae,patch,logistic,abide_dx,2,0.3593813663804626,train,0.9116809116809117,0.010533767995339626,0.9103979841399243,0.010720389261435983,0.9089700996677741,0.010843007697213245 +flat_mae,patch,logistic,abide_dx,2,0.3593813663804626,test,0.6129032258064516,0.04151567473496331,0.6112852664576802,0.04173346954281823,0.6123949579831933,0.04196419978746159 +flat_mae,patch,logistic,abide_dx,3,0.3593813663804626,train,0.9131054131054132,0.010169675597924996,0.9118124960099181,0.010357380481867545,0.9102620893318567,0.010486061151255074 +flat_mae,patch,logistic,abide_dx,3,0.3593813663804626,test,0.6532258064516129,0.04213316928756203,0.6465831510572015,0.04362884852202091,0.6460084033613445,0.04304187232756407 +flat_mae,patch,logistic,abide_dx,4,0.3593813663804626,train,0.905982905982906,0.011114069297203846,0.9047458491295302,0.011293657655672355,0.9038021410114434,0.01143911238989867 +flat_mae,patch,logistic,abide_dx,4,0.3593813663804626,test,0.7016129032258065,0.04000679897992575,0.6944388944388944,0.041548317053759505,0.6932773109243697,0.04091026206879642 +flat_mae,patch,logistic,abide_dx,5,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,5,1291.5496650148827,test,0.6129032258064516,0.04145349248907917,0.6063492063492064,0.042377012616958455,0.60609243697479,0.04189311314939736 +flat_mae,patch,logistic,abide_dx,6,0.3593813663804626,train,0.9102564102564102,0.010939495394028845,0.9091635430038512,0.011077304793540063,0.9085640457733482,0.011124095967855685 +flat_mae,patch,logistic,abide_dx,6,0.3593813663804626,test,0.6048387096774194,0.04590057061665403,0.6004471624909581,0.04642903131288017,0.6003151260504203,0.04619530619725576 +flat_mae,patch,logistic,abide_dx,7,0.005994842503189409,train,0.7122507122507122,0.016649290623202497,0.7055369127516778,0.01722230486969773,0.704171280915467,0.017053037243993537 +flat_mae,patch,logistic,abide_dx,7,0.005994842503189409,test,0.6209677419354839,0.041749024052847555,0.6021028196900389,0.04583876233327427,0.6055672268907563,0.04293966685048903 +flat_mae,patch,logistic,abide_dx,8,0.3593813663804626,train,0.9102564102564102,0.010932087989217576,0.9091052957171013,0.011098380610445406,0.9082687338501292,0.011209764276794763 +flat_mae,patch,logistic,abide_dx,8,0.3593813663804626,test,0.6209677419354839,0.04078489485438252,0.6049081418208935,0.04316667020572939,0.6071428571428572,0.041397012179623556 +flat_mae,patch,logistic,abide_dx,9,0.3593813663804626,train,0.9074074074074074,0.01043168180244167,0.9062197495493903,0.010584615698066973,0.905389442598745,0.010664634982182633 +flat_mae,patch,logistic,abide_dx,9,0.3593813663804626,test,0.7016129032258065,0.040087131947331274,0.6944388944388944,0.041922791595071354,0.6932773109243697,0.04116477253817681 +flat_mae,patch,logistic,abide_dx,10,0.3593813663804626,train,0.9074074074074074,0.011043065436858627,0.9060946873424365,0.011254792358287571,0.904798818752307,0.011429369653576403 +flat_mae,patch,logistic,abide_dx,10,0.3593813663804626,test,0.6290322580645161,0.0429039655526815,0.6227513227513227,0.043690308875009035,0.6223739495798319,0.043178726847341545 +flat_mae,patch,logistic,abide_dx,11,10000.0,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,11,10000.0,test,0.6129032258064516,0.0438557700194152,0.6063492063492064,0.04504207427897886,0.60609243697479,0.044469161302351304 +flat_mae,patch,logistic,abide_dx,12,0.3593813663804626,train,0.9074074074074074,0.01135834373073027,0.9060297088630275,0.011588844639788449,0.9045035068290882,0.011766665586376616 +flat_mae,patch,logistic,abide_dx,12,0.3593813663804626,test,0.5725806451612904,0.04208104699421145,0.5623043623043623,0.04405106903427984,0.5630252100840336,0.04290296359031134 +flat_mae,patch,logistic,abide_dx,13,2.782559402207126,train,0.9943019943019943,0.0028374180419808194,0.9942447694628451,0.00286375942345929,0.9945367294204503,0.0027375897071431608 +flat_mae,patch,logistic,abide_dx,13,2.782559402207126,test,0.6451612903225806,0.04115462834145142,0.6443285528031291,0.041154382163452616,0.6465336134453781,0.04132880268385882 +flat_mae,patch,logistic,abide_dx,14,2.782559402207126,train,0.9886039886039886,0.003950213083822467,0.9884895389256902,0.003988650454555297,0.9887781469176818,0.0039489774188294965 +flat_mae,patch,logistic,abide_dx,14,2.782559402207126,test,0.5725806451612904,0.04408269591443209,0.5691904293674206,0.04444473150500854,0.569327731092437,0.04444849279660729 +flat_mae,patch,logistic,abide_dx,15,0.046415888336127774,train,0.7849002849002849,0.015188044609256568,0.7808875540277689,0.015604297884490902,0.7792174234034699,0.015583960229970578 +flat_mae,patch,logistic,abide_dx,15,0.046415888336127774,test,0.6290322580645161,0.04363335498232433,0.6242424242424243,0.04444138743510347,0.6239495798319328,0.04409055904849567 +flat_mae,patch,logistic,abide_dx,16,0.3593813663804626,train,0.9074074074074074,0.010889395764045207,0.9061580320950635,0.01106465555516677,0.905094130675526,0.011180194601328226 +flat_mae,patch,logistic,abide_dx,16,0.3593813663804626,test,0.6209677419354839,0.043254696652712865,0.6167554415729598,0.043965866876771016,0.6165966386554622,0.04381498385615705 +flat_mae,patch,logistic,abide_dx,17,0.3593813663804626,train,0.9031339031339032,0.01120043683568566,0.9015874324825794,0.011444811954752615,0.8997416020671835,0.011630424676835397 +flat_mae,patch,logistic,abide_dx,17,0.3593813663804626,test,0.6612903225806451,0.042085266008240835,0.6604954367666231,0.04233036790826822,0.6628151260504203,0.042628318884269274 +flat_mae,patch,logistic,abide_dx,18,0.046415888336127774,train,0.7877492877492878,0.014885370832440794,0.7830794595547445,0.015338310816558776,0.7809154669619787,0.015266008430008898 +flat_mae,patch,logistic,abide_dx,18,0.046415888336127774,test,0.6935483870967742,0.04316973674526598,0.6895915678524374,0.044160939095567515,0.6890756302521008,0.04396428556370223 +flat_mae,patch,logistic,abide_dx,19,0.3593813663804626,train,0.9031339031339032,0.010761152172720513,0.9019230769230769,0.010913434437285882,0.901218161683278,0.010990683568791465 +flat_mae,patch,logistic,abide_dx,19,0.3593813663804626,test,0.6451612903225806,0.040683596778385046,0.6231003039513678,0.04523219697892713,0.6276260504201681,0.041886000102435705 +flat_mae,patch,logistic,abide_dx,20,2.782559402207126,train,0.9886039886039886,0.0040476410243536105,0.988482834994463,0.004090917007239117,0.988482834994463,0.004114669416290413 +flat_mae,patch,logistic,abide_dx,20,2.782559402207126,test,0.6129032258064516,0.04495636397453216,0.6119947848761408,0.04507217832966527,0.6139705882352942,0.04515277123991811 +flat_mae,patch,logistic,abide_dx,21,0.046415888336127774,train,0.7977207977207977,0.014217563008368654,0.7946387368976201,0.014484157418250283,0.7935031376891841,0.014503164822243035 +flat_mae,patch,logistic,abide_dx,21,0.046415888336127774,test,0.6532258064516129,0.041212489645853397,0.6429862738533645,0.043012863191604606,0.6428571428571428,0.04184732481905305 +flat_mae,patch,logistic,abide_dx,22,0.3593813663804626,train,0.9145299145299145,0.010174431395830234,0.9135162660052399,0.010325828007271809,0.9130306386120339,0.010488940254012263 +flat_mae,patch,logistic,abide_dx,22,0.3593813663804626,test,0.6129032258064516,0.041432165640185835,0.6045708211533352,0.042787285327808997,0.6045168067226891,0.042101983242236046 +flat_mae,patch,logistic,abide_dx,23,0.046415888336127774,train,0.801994301994302,0.014702317502698776,0.7984571056789664,0.015081846963759133,0.7967884828349945,0.015107242559776652 +flat_mae,patch,logistic,abide_dx,23,0.046415888336127774,test,0.6774193548387096,0.04181557297945846,0.6688034188034189,0.043959260701295466,0.6680672268907563,0.04290719234985474 +flat_mae,patch,logistic,abide_dx,24,0.3593813663804626,train,0.9131054131054132,0.010789884699919936,0.9119329224276751,0.010990225221551884,0.9108527131782945,0.011192555286006937 +flat_mae,patch,logistic,abide_dx,24,0.3593813663804626,test,0.6209677419354839,0.04111854388721451,0.6179613241560145,0.04156701276068065,0.618172268907563,0.04147867307507804 +flat_mae,patch,logistic,abide_dx,25,2.782559402207126,train,0.9928774928774928,0.0028880219763901655,0.9927996307502949,0.0029205737360222905,0.9926541159099298,0.002988963173445 +flat_mae,patch,logistic,abide_dx,25,2.782559402207126,test,0.5564516129032258,0.04309405776642849,0.5541026479241582,0.04331561531811178,0.5546218487394958,0.043338782357981734 +flat_mae,patch,logistic,abide_dx,26,0.046415888336127774,train,0.7977207977207977,0.01465381949721413,0.7943404634581106,0.014958492084390682,0.7929125138427464,0.014960072138596294 +flat_mae,patch,logistic,abide_dx,26,0.046415888336127774,test,0.6532258064516129,0.04327470452850182,0.6448884448884449,0.045163244934764334,0.6444327731092437,0.044160993111785486 +flat_mae,patch,logistic,abide_dx,27,2.782559402207126,train,0.9914529914529915,0.003653621503343063,0.9913671541942677,0.0036885974063806367,0.9916574381690662,0.0036083843516248053 +flat_mae,patch,logistic,abide_dx,27,2.782559402207126,test,0.6048387096774194,0.043387621414264145,0.6004471624909581,0.04417157998397544,0.6003151260504203,0.044043628583944776 +flat_mae,patch,logistic,abide_dx,28,0.3593813663804626,train,0.9102564102564102,0.010762858573930514,0.9091052957171013,0.010930436748631825,0.9082687338501292,0.011054201762828371 +flat_mae,patch,logistic,abide_dx,28,0.3593813663804626,test,0.6129032258064516,0.04320212097830305,0.6092436974789917,0.04374137152221236,0.6092436974789917,0.04358181129991112 +flat_mae,patch,logistic,abide_dx,29,0.3593813663804626,train,0.8917378917378918,0.011308115092098463,0.8899286987522281,0.011561073892518137,0.8879291251384275,0.011690303422644445 +flat_mae,patch,logistic,abide_dx,29,0.3593813663804626,test,0.6612903225806451,0.041611727915385324,0.6539994685091681,0.04292305053331143,0.6533613445378151,0.04231371684882159 +flat_mae,patch,logistic,abide_dx,30,0.046415888336127774,train,0.7948717948717948,0.015502015654316617,0.7907947019867549,0.01590671213335725,0.7888519748984866,0.01584260142761688 +flat_mae,patch,logistic,abide_dx,30,0.046415888336127774,test,0.6451612903225806,0.04217661443751774,0.6313513513513513,0.044738745435670815,0.6323529411764706,0.042907006695959225 +flat_mae,patch,logistic,abide_dx,31,0.3593813663804626,train,0.9002849002849003,0.011174435665167346,0.8988364337063663,0.011395356553221547,0.8974529346622371,0.011550040908333918 +flat_mae,patch,logistic,abide_dx,31,0.3593813663804626,test,0.6370967741935484,0.043645277519335966,0.6351748937561295,0.043870304097377515,0.6360294117647058,0.04384094322508657 +flat_mae,patch,logistic,abide_dx,32,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,32,166.81005372000556,test,0.6854838709677419,0.04046061534851953,0.6819885579009667,0.04079982980991922,0.6817226890756303,0.04062647937477944 +flat_mae,patch,logistic,abide_dx,33,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,33,166.81005372000556,test,0.5967741935483871,0.046101796606685556,0.58994708994709,0.04704634154889424,0.5898109243697479,0.04657025228310478 +flat_mae,patch,logistic,abide_dx,34,2.782559402207126,train,0.9843304843304843,0.004729388493945035,0.9841591876506488,0.00478300935981704,0.984016242155777,0.004824948782499332 +flat_mae,patch,logistic,abide_dx,34,2.782559402207126,test,0.6209677419354839,0.040835253765001,0.6137071651090342,0.0421060355500723,0.6134453781512605,0.041518270385794954 +flat_mae,patch,logistic,abide_dx,35,0.046415888336127774,train,0.7863247863247863,0.01533572769569882,0.782423631314467,0.015676431256260046,0.7808047249907715,0.015635030278543863 +flat_mae,patch,logistic,abide_dx,35,0.046415888336127774,test,0.6774193548387096,0.03932712866339709,0.6753076721654884,0.03959278883761525,0.6759453781512605,0.03967318330046403 +flat_mae,patch,logistic,abide_dx,36,0.3593813663804626,train,0.9031339031339032,0.011141850604626715,0.9019851014726052,0.0112765743270798,0.9015134736064969,0.011316665181511459 +flat_mae,patch,logistic,abide_dx,36,0.3593813663804626,test,0.7016129032258065,0.04175986801323528,0.6928021426180114,0.04350157367943771,0.6917016806722689,0.04258852997243399 +flat_mae,patch,logistic,abide_dx,37,0.3593813663804626,train,0.9173789173789174,0.010233369180784053,0.9163461538461539,0.010373761032680945,0.9156146179401994,0.010462854282776182 +flat_mae,patch,logistic,abide_dx,37,0.3593813663804626,test,0.6532258064516129,0.0415425104790149,0.6513893429225237,0.041897947134104094,0.6523109243697479,0.042060390997831605 +flat_mae,patch,logistic,abide_dx,38,0.046415888336127774,train,0.7977207977207977,0.01468234081227605,0.7943404634581106,0.014942412379818804,0.7929125138427464,0.014890641707142384 +flat_mae,patch,logistic,abide_dx,38,0.046415888336127774,test,0.6209677419354839,0.042649050015465095,0.6137071651090342,0.043581674420652,0.6134453781512605,0.04304699323578632 +flat_mae,patch,logistic,abide_dx,39,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,39,21.54434690031882,test,0.6370967741935484,0.041323021326752946,0.6342182890855457,0.041658812096963996,0.634453781512605,0.04164822414359369 +flat_mae,patch,logistic,abide_dx,40,0.3593813663804626,train,0.9131054131054132,0.01060824058864712,0.9121021226284385,0.010747356939258938,0.9117386489479513,0.010843607984910337 +flat_mae,patch,logistic,abide_dx,40,0.3593813663804626,test,0.5806451612903226,0.044166518105235135,0.5716183895827798,0.04565439811016017,0.571953781512605,0.04484903180717537 +flat_mae,patch,logistic,abide_dx,41,0.005994842503189409,train,0.7136752136752137,0.016923589879704645,0.7073756467819036,0.017412112736951913,0.7060538944259874,0.01724365611085162 +flat_mae,patch,logistic,abide_dx,41,0.005994842503189409,test,0.6048387096774194,0.041292398511322846,0.5907590759075907,0.04348022542965957,0.592436974789916,0.04196025390545418 +flat_mae,patch,logistic,abide_dx,42,0.046415888336127774,train,0.801994301994302,0.014058564415163921,0.7984571056789664,0.014361795044772268,0.7967884828349945,0.014341351166644353 +flat_mae,patch,logistic,abide_dx,42,0.046415888336127774,test,0.6532258064516129,0.04456566902178179,0.6465831510572015,0.04571957406985485,0.6460084033613445,0.045063606781618686 +flat_mae,patch,logistic,abide_dx,43,0.046415888336127774,train,0.7977207977207977,0.014576039853714152,0.7941859024652104,0.014938063515596551,0.7926172019195274,0.014958718214549157 +flat_mae,patch,logistic,abide_dx,43,0.046415888336127774,test,0.6854838709677419,0.04031134036882061,0.6794591370053689,0.041316999180594775,0.6785714285714286,0.04083579804288089 +flat_mae,patch,logistic,abide_dx,44,0.005994842503189409,train,0.7364672364672364,0.01626916110932806,0.7299567706264829,0.01685926741724708,0.7282022886674049,0.016672616960432086 +flat_mae,patch,logistic,abide_dx,44,0.005994842503189409,test,0.6129032258064516,0.04135454934225167,0.5978378378378378,0.044094501710218566,0.5997899159663866,0.042219368280895925 +flat_mae,patch,logistic,abide_dx,45,0.3593813663804626,train,0.8988603988603988,0.011405740505106798,0.897208192491797,0.0116259355917112,0.8952750092284976,0.011710183878796411 +flat_mae,patch,logistic,abide_dx,45,0.3593813663804626,test,0.6532258064516129,0.039802961628784314,0.6480760345851759,0.0407181663777165,0.6475840336134454,0.040247585534714955 +flat_mae,patch,logistic,abide_dx,46,0.005994842503189409,train,0.7065527065527065,0.016501313088903142,0.6988881022779327,0.017121368120373008,0.6975267626430417,0.016890391797018917 +flat_mae,patch,logistic,abide_dx,46,0.005994842503189409,test,0.6048387096774194,0.04302701943738297,0.5989703649924097,0.04351100519639439,0.5987394957983193,0.04325159933935038 +flat_mae,patch,logistic,abide_dx,47,0.046415888336127774,train,0.7891737891737892,0.015334931910093448,0.785489532146839,0.015672995848205293,0.7839793281653746,0.015640525584680813 +flat_mae,patch,logistic,abide_dx,47,0.046415888336127774,test,0.6209677419354839,0.04169028501610711,0.607462787095036,0.04413461432985312,0.608718487394958,0.042563843555224544 +flat_mae,patch,logistic,abide_dx,48,0.3593813663804626,train,0.8931623931623932,0.011147036668552086,0.8917208062635349,0.0113266990079946,0.8906976744186046,0.011429088900447573 +flat_mae,patch,logistic,abide_dx,48,0.3593813663804626,test,0.6532258064516129,0.04304515391718819,0.6480760345851759,0.044093049084317805,0.6475840336134454,0.043737006642881306 +flat_mae,patch,logistic,abide_dx,49,0.005994842503189409,train,0.7207977207977208,0.016549920817315815,0.7135051846916254,0.017171492530046968,0.7119232188999631,0.01695146086058928 +flat_mae,patch,logistic,abide_dx,49,0.005994842503189409,test,0.6209677419354839,0.04228598868076371,0.6118548118548119,0.04385342668565108,0.6118697478991597,0.04298577914042962 +flat_mae,patch,logistic,abide_dx,50,0.046415888336127774,train,0.801994301994302,0.015109714476545574,0.7984571056789664,0.015537747130544295,0.7967884828349945,0.015601969428942819 +flat_mae,patch,logistic,abide_dx,50,0.046415888336127774,test,0.5887096774193549,0.04318817572406282,0.5765651155005022,0.045179182611209824,0.5777310924369747,0.04387988466346372 +flat_mae,patch,logistic,abide_dx,51,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,51,1291.5496650148827,test,0.5806451612903226,0.044640251804458415,0.5788923719958203,0.0448703146418622,0.5798319327731092,0.04502111432754767 +flat_mae,patch,logistic,abide_dx,52,0.046415888336127774,train,0.7877492877492878,0.015170611395124,0.7828921559470213,0.015676819305415632,0.7806201550387597,0.015589260684586433 +flat_mae,patch,logistic,abide_dx,52,0.046415888336127774,test,0.6370967741935484,0.043556701715212684,0.6283716283716283,0.04517495895427842,0.6281512605042017,0.044318842700809546 +flat_mae,patch,logistic,abide_dx,53,2.782559402207126,train,0.9843304843304843,0.004671234489119604,0.9841495630969315,0.004731084084661286,0.9837209302325581,0.004891362258154156 +flat_mae,patch,logistic,abide_dx,53,2.782559402207126,test,0.6209677419354839,0.04198769702368489,0.6179613241560145,0.042460379533953076,0.618172268907563,0.04245417420980726 +flat_mae,patch,logistic,abide_dx,54,0.3593813663804626,train,0.9045584045584045,0.011038128340913453,0.9034564297722192,0.011175962709144598,0.9031007751937985,0.011248556829931918 +flat_mae,patch,logistic,abide_dx,54,0.3593813663804626,test,0.6612903225806451,0.04215968294193907,0.6569169960474308,0.04294528533229685,0.6565126050420168,0.04265219484896751 +flat_mae,patch,logistic,abide_dx,55,0.3593813663804626,train,0.9102564102564102,0.011770028683673073,0.9088565334322545,0.012018082513094186,0.9070874861572535,0.01220671416926058 +flat_mae,patch,logistic,abide_dx,55,0.3593813663804626,test,0.6209677419354839,0.044979345473792516,0.6153389215233318,0.04547065108625538,0.6150210084033614,0.04510109324017867 +flat_mae,patch,logistic,abide_dx,56,0.005994842503189409,train,0.7193732193732194,0.01699458641458691,0.7107806333823403,0.017745206031341054,0.7091546696197859,0.01737727175914728 +flat_mae,patch,logistic,abide_dx,56,0.005994842503189409,test,0.6693548387096774,0.04160000737913167,0.6614052614052615,0.04320255970734275,0.6607142857142857,0.042475844310570686 +flat_mae,patch,logistic,abide_dx,57,0.005994842503189409,train,0.7051282051282052,0.016742035251208993,0.6981146970531105,0.01721486258172732,0.6968253968253968,0.017000623107286963 +flat_mae,patch,logistic,abide_dx,57,0.005994842503189409,test,0.6774193548387096,0.039887364177390465,0.6704756842944459,0.0412926825660231,0.6696428571428572,0.040709514790042846 +flat_mae,patch,logistic,abide_dx,58,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,58,1291.5496650148827,test,0.6290322580645161,0.04210652464017509,0.6242424242424243,0.04298173780621942,0.6239495798319328,0.04269692218620088 +flat_mae,patch,logistic,abide_dx,59,0.046415888336127774,train,0.7948717948717948,0.014442695601520512,0.7904477611940299,0.014947175797346723,0.7882613510520486,0.014949149097746674 +flat_mae,patch,logistic,abide_dx,59,0.046415888336127774,test,0.6612903225806451,0.04220808112652048,0.6580882352941176,0.04257643796432481,0.6580882352941176,0.04249908274171437 +flat_mae,patch,logistic,abide_dx,60,0.3593813663804626,train,0.9002849002849003,0.010530436757070273,0.898905529953917,0.010696466302704884,0.8977482465854558,0.010759597163205521 +flat_mae,patch,logistic,abide_dx,60,0.3593813663804626,test,0.6451612903225806,0.044277339919929874,0.6418067226890756,0.04459195855550761,0.6418067226890756,0.04451701833054351 +flat_mae,patch,logistic,abide_dx,61,0.046415888336127774,train,0.7977207977207977,0.014848881498040282,0.7944914031253866,0.015159291864189453,0.7932078257659654,0.015182402244919256 +flat_mae,patch,logistic,abide_dx,61,0.046415888336127774,test,0.5967741935483871,0.04401001151355811,0.5915678524374176,0.04436902614593565,0.5913865546218487,0.04410814567304671 +flat_mae,patch,logistic,abide_dx,62,0.3593813663804626,train,0.9031339031339032,0.011331154474650634,0.9017939433838051,0.011519994227366201,0.9006275378368402,0.011604575268167324 +flat_mae,patch,logistic,abide_dx,62,0.3593813663804626,test,0.5725806451612904,0.04172805709854658,0.5643931861867832,0.042600541296591465,0.5646008403361344,0.04200894984313747 +flat_mae,patch,logistic,abide_dx,63,0.046415888336127774,train,0.7834757834757835,0.01590241933960845,0.7780255625083211,0.016466443737036877,0.775562938353636,0.016315499843330496 +flat_mae,patch,logistic,abide_dx,63,0.046415888336127774,test,0.6129032258064516,0.04500936138030224,0.6092436974789917,0.04557332257087634,0.6092436974789917,0.04549400985119451 +flat_mae,patch,logistic,abide_dx,64,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,64,166.81005372000556,test,0.6693548387096774,0.04496330738998645,0.6682977751680041,0.04507435989520633,0.6701680672268908,0.04491339799159255 +flat_mae,patch,logistic,abide_dx,65,0.3593813663804626,train,0.9002849002849003,0.010714355433653764,0.8990384615384615,0.010892911756830432,0.8983388704318938,0.011064942411742508 +flat_mae,patch,logistic,abide_dx,65,0.3593813663804626,test,0.6612903225806451,0.041331254912890046,0.6522435897435898,0.04290431564138206,0.6517857142857143,0.04207964869882113 +flat_mae,patch,logistic,abide_dx,66,2.782559402207126,train,0.9871794871794872,0.004350951595068789,0.9870314607156713,0.004406981039951875,0.9866002214839424,0.004581256298378695 +flat_mae,patch,logistic,abide_dx,66,2.782559402207126,test,0.5645161290322581,0.04356944234129377,0.5626959247648903,0.04375344426045893,0.5635504201680672,0.04389892082282419 +flat_mae,patch,logistic,abide_dx,67,2.782559402207126,train,0.9914529914529915,0.0032750536255445883,0.9913569505548625,0.00331427563026686,0.9910668143226282,0.0034396408076167477 +flat_mae,patch,logistic,abide_dx,67,2.782559402207126,test,0.6370967741935484,0.04309590495549899,0.6351748937561295,0.043197622739423236,0.6360294117647058,0.043174713991567505 +flat_mae,patch,logistic,abide_dx,68,2.782559402207126,train,0.9914529914529915,0.0035205606724609236,0.9913621262458472,0.003558104391419592,0.9913621262458472,0.003571760357658275 +flat_mae,patch,logistic,abide_dx,68,2.782559402207126,test,0.6290322580645161,0.04379661631240743,0.6255252100840336,0.04420431508650615,0.6255252100840336,0.04411193260309923 +flat_mae,patch,logistic,abide_dx,69,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,69,1291.5496650148827,test,0.5887096774193549,0.043767296268843285,0.5841388834089565,0.04475205691190134,0.5840336134453781,0.04444776177798601 +flat_mae,patch,logistic,abide_dx,70,2.782559402207126,train,0.9857549857549858,0.00451810534032434,0.9855860443342066,0.004577976004731818,0.9850129198966409,0.0047766744340075095 +flat_mae,patch,logistic,abide_dx,70,2.782559402207126,test,0.6290322580645161,0.04197843953812708,0.6227513227513227,0.042808453510781094,0.6223739495798319,0.04237653595875981 +flat_mae,patch,logistic,abide_dx,71,0.046415888336127774,train,0.7962962962962963,0.015026963101431553,0.7921627815976298,0.015438382955602849,0.7901439645625692,0.015384336949637374 +flat_mae,patch,logistic,abide_dx,71,0.046415888336127774,test,0.6935483870967742,0.04208898395351609,0.6853632478632479,0.04405212035766044,0.6843487394957983,0.043146237462119 +flat_mae,patch,logistic,abide_dx,72,0.3593813663804626,train,0.9088319088319088,0.010883878500376047,0.9075707702435813,0.011076112949766284,0.9063861203396086,0.011218189848167855 +flat_mae,patch,logistic,abide_dx,72,0.3593813663804626,test,0.6129032258064516,0.044410449009996626,0.6092436974789917,0.04467578898111247,0.6092436974789917,0.044565155550613834 +flat_mae,patch,logistic,abide_dx,73,0.005994842503189409,train,0.7207977207977208,0.01653686003175648,0.7135051846916254,0.017180634680127867,0.7119232188999631,0.016948241661585147 +flat_mae,patch,logistic,abide_dx,73,0.005994842503189409,test,0.5725806451612904,0.041003654566699084,0.5623043623043623,0.04284621234606453,0.5630252100840336,0.0418267576882376 +flat_mae,patch,logistic,abide_dx,74,0.3593813663804626,train,0.8931623931623932,0.01132756367240746,0.8914958731336362,0.011567974548991694,0.8898117386489479,0.011721146314593698 +flat_mae,patch,logistic,abide_dx,74,0.3593813663804626,test,0.6854838709677419,0.041414565470260956,0.6829891838741396,0.041784077607795705,0.6832983193277311,0.041637047935860545 +flat_mae,patch,logistic,abide_dx,75,2.782559402207126,train,0.99002849002849,0.003716806758289988,0.98993121507736,0.0037483174040088066,0.9903654485049834,0.003573808674638364 +flat_mae,patch,logistic,abide_dx,75,2.782559402207126,test,0.6532258064516129,0.04149802535326956,0.6493719997369632,0.04196815785427738,0.6491596638655461,0.04185039788233081 +flat_mae,patch,logistic,abide_dx,76,0.3593813663804626,train,0.9273504273504274,0.009931254110111613,0.9263204469917579,0.010120584008113345,0.9249538575119971,0.010346671033700267 +flat_mae,patch,logistic,abide_dx,76,0.3593813663804626,test,0.6370967741935484,0.04303732378172978,0.6301451580831179,0.04435700387029173,0.6297268907563025,0.04371659427573878 +flat_mae,patch,logistic,abide_dx,77,0.046415888336127774,train,0.7962962962962963,0.014670080866708747,0.7924961604368937,0.015008202196383696,0.790734588409007,0.014981731303804209 +flat_mae,patch,logistic,abide_dx,77,0.046415888336127774,test,0.5725806451612904,0.04294033078965115,0.5723303182143554,0.042986272122954375,0.5756302521008403,0.04319923614399796 +flat_mae,patch,logistic,abide_dx,78,0.3593813663804626,train,0.9017094017094017,0.011206267965616112,0.9005745321534795,0.011331880585665062,0.9002214839424141,0.011339178655738831 +flat_mae,patch,logistic,abide_dx,78,0.3593813663804626,test,0.6209677419354839,0.0429983906965993,0.6179613241560145,0.04320748512367196,0.618172268907563,0.0431682523203631 +flat_mae,patch,logistic,abide_dx,79,0.046415888336127774,train,0.8062678062678063,0.014994955632143366,0.8019203797604919,0.01554340231216936,0.7994832041343669,0.015517523163707303 +flat_mae,patch,logistic,abide_dx,79,0.046415888336127774,test,0.5967741935483871,0.044680749846749954,0.5915678524374176,0.04547595684283403,0.5913865546218487,0.045206519737430666 +flat_mae,patch,logistic,abide_dx,80,0.3593813663804626,train,0.9102564102564102,0.010820359792421462,0.9089840815780538,0.011016949720024843,0.9076781100036914,0.011171526398185588 +flat_mae,patch,logistic,abide_dx,80,0.3593813663804626,test,0.6774193548387096,0.04131907705929863,0.6753076721654884,0.04157348866608114,0.6759453781512605,0.0415904143309112 +flat_mae,patch,logistic,abide_dx,81,0.3593813663804626,train,0.8974358974358975,0.011831760309638634,0.8958731623706242,0.012085603548359946,0.8942783314876339,0.01229067379297104 +flat_mae,patch,logistic,abide_dx,81,0.3593813663804626,test,0.6451612903225806,0.043883332579144674,0.6336287939833467,0.04624339481015952,0.6339285714285714,0.044883426690897774 +flat_mae,patch,logistic,abide_dx,82,0.046415888336127774,train,0.7962962962962963,0.01471227940086491,0.7924961604368937,0.01502493723824726,0.790734588409007,0.014957717373442637 +flat_mae,patch,logistic,abide_dx,82,0.046415888336127774,test,0.6532258064516129,0.04271855416475561,0.6465831510572015,0.04388926420251252,0.6460084033613445,0.043359447976466244 +flat_mae,patch,logistic,abide_dx,83,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,83,21.54434690031882,test,0.5806451612903226,0.043848105404391546,0.580536039552433,0.04393169987785544,0.5845588235294117,0.04384154731237929 +flat_mae,patch,logistic,abide_dx,84,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,84,166.81005372000556,test,0.5967741935483871,0.043614701599684856,0.5966692688004163,0.04381985807910171,0.6008403361344539,0.04378810299153417 +flat_mae,patch,logistic,abide_dx,85,0.005994842503189409,train,0.7136752136752137,0.01650614863473876,0.7057794440540557,0.017299440221616225,0.7042820228866741,0.017042678909478096 +flat_mae,patch,logistic,abide_dx,85,0.005994842503189409,test,0.5806451612903226,0.04079154387896022,0.5716183895827798,0.04182485287486705,0.571953781512605,0.04117255891373242 +flat_mae,patch,logistic,abide_dx,86,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,86,1291.5496650148827,test,0.5967741935483871,0.043822467854580764,0.5963541666666667,0.04388604785182247,0.5992647058823529,0.04396777137036325 +flat_mae,patch,logistic,abide_dx,87,0.3593813663804626,train,0.9116809116809117,0.011129263789480422,0.910335223152482,0.011349546720691689,0.9086747877445551,0.01152543501508011 +flat_mae,patch,logistic,abide_dx,87,0.3593813663804626,test,0.6129032258064516,0.04472082437963983,0.6125,0.04475092079340543,0.615546218487395,0.04467962473810485 +flat_mae,patch,logistic,abide_dx,88,2.782559402207126,train,0.9928774928774928,0.003049177159761699,0.9928080107695428,0.003076254009605602,0.9932447397563677,0.002918657896417842 +flat_mae,patch,logistic,abide_dx,88,2.782559402207126,test,0.6612903225806451,0.04598747454227373,0.6598746081504703,0.046104791865562614,0.6612394957983193,0.04606250890790423 +flat_mae,patch,logistic,abide_dx,89,0.3593813663804626,train,0.9074074074074074,0.011006332983873485,0.9062197495493903,0.011179789385928708,0.905389442598745,0.011291878161077244 +flat_mae,patch,logistic,abide_dx,89,0.3593813663804626,test,0.6129032258064516,0.04379293344560365,0.6092436974789917,0.04412434136811076,0.6092436974789917,0.04395668389157769 +flat_mae,patch,logistic,abide_dx,90,0.046415888336127774,train,0.7977207977207977,0.015111105739686988,0.7941859024652104,0.015466077025312346,0.7926172019195274,0.015469758925169249 +flat_mae,patch,logistic,abide_dx,90,0.046415888336127774,test,0.6451612903225806,0.04280832032773533,0.6313513513513513,0.0456673809383683,0.6323529411764706,0.0438559082086249 +flat_mae,patch,logistic,abide_dx,91,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,91,166.81005372000556,test,0.5967741935483871,0.04243889835578258,0.5880946053680574,0.043803108736806026,0.5882352941176471,0.04306195289494678 +flat_mae,patch,logistic,abide_dx,92,0.3593813663804626,train,0.9045584045584045,0.010947695581201018,0.9033961489088576,0.011117301218699388,0.9028054632705795,0.011266260102065172 +flat_mae,patch,logistic,abide_dx,92,0.3593813663804626,test,0.5564516129032258,0.044568397902227545,0.5479551932126997,0.0458967743514932,0.5483193277310925,0.04517212293693084 +flat_mae,patch,logistic,abide_dx,93,0.046415888336127774,train,0.8091168091168092,0.014335531217803866,0.806069352245083,0.014632288289567634,0.8047249907715024,0.014660985264615666 +flat_mae,patch,logistic,abide_dx,93,0.046415888336127774,test,0.5241935483870968,0.04590787272740787,0.5189057670809496,0.04658642019587513,0.51890756302521,0.04632341479434743 +flat_mae,patch,logistic,abide_dx,94,2.782559402207126,train,0.9943019943019943,0.0029906171671842553,0.9942480232701053,0.003014558278884444,0.9948320413436693,0.0027124202213996544 +flat_mae,patch,logistic,abide_dx,94,2.782559402207126,test,0.5967741935483871,0.04497397501578089,0.5950888192267503,0.04521052382286268,0.5961134453781513,0.04521895872487394 +flat_mae,patch,logistic,abide_dx,95,0.3593813663804626,train,0.9074074074074074,0.010192693425261534,0.9058948241122085,0.010435920558162892,0.9039128829826504,0.010646438305488552 +flat_mae,patch,logistic,abide_dx,95,0.3593813663804626,test,0.6129032258064516,0.04280556432461559,0.6003223207091055,0.045223109108494114,0.6013655462184874,0.043678934875670934 +flat_mae,patch,logistic,abide_dx,96,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,96,1291.5496650148827,test,0.6209677419354839,0.046063733954685805,0.6179613241560145,0.04623314446149793,0.618172268907563,0.045998413920236306 +flat_mae,patch,logistic,abide_dx,97,2.782559402207126,train,0.9814814814814815,0.004777280832832157,0.9812790399507667,0.004831007333282177,0.9811369509043928,0.004880119106831046 +flat_mae,patch,logistic,abide_dx,97,2.782559402207126,test,0.717741935483871,0.040812058138375164,0.7135502607088642,0.0416634965895804,0.7127100840336134,0.04151158782041816 +flat_mae,patch,logistic,abide_dx,98,0.046415888336127774,train,0.8005698005698005,0.015141279138239762,0.7970846925713342,0.015483786573083923,0.7954964931709118,0.015460541488064467 +flat_mae,patch,logistic,abide_dx,98,0.046415888336127774,test,0.6290322580645161,0.04328480266235772,0.6242424242424243,0.04392285786660808,0.6239495798319328,0.043706421432174264 +flat_mae,patch,logistic,abide_dx,99,0.3593813663804626,train,0.9088319088319088,0.010051981357019787,0.9073764070424277,0.010276713652213672,0.905500184569952,0.010472891600442659 +flat_mae,patch,logistic,abide_dx,99,0.3593813663804626,test,0.6209677419354839,0.041986631339490585,0.6153389215233318,0.04303908634062656,0.6150210084033614,0.04269015564444284 +flat_mae,patch,logistic,abide_dx,100,0.3593813663804626,train,0.905982905982906,0.011353952301082338,0.9044819197625036,0.011591939282143273,0.9026208933185678,0.01173389239341798 +flat_mae,patch,logistic,abide_dx,100,0.3593813663804626,test,0.7016129032258065,0.041833312259109474,0.6958971299794525,0.04289907306580737,0.6948529411764706,0.04253965304928108 diff --git a/input_space_v3/flat_lr1e-3_7/eval_v2/abide_dx__patch__logistic/log.txt b/input_space_v3/flat_lr1e-3_7/eval_v2/abide_dx__patch__logistic/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..ff7a82f7eda51473632f135d6a2ecb1cf599e580 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_7/eval_v2/abide_dx__patch__logistic/log.txt @@ -0,0 +1,252 @@ +fMRI foundation model logistic probe eval +version: 0.1.dev86+gf97f52698 +sha: bcce2b486277d3a5b520775efd9cdf1a2affce36, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-04-08 22:54:19 +config: +output_root: experiments/input_space_v3/output +name_prefix: eval_logistic +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_7; eval v2 (abide_dx patch logistic) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_7/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: input_space_v3/flat_lr1e-3_7/eval_v2/abide_dx__patch__logistic +model: flat_mae +representation: patch +dataset: abide_dx +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_7/eval_v2/abide_dx__patch__logistic +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=True, reg_tokens=0, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: abide_dx (flat) +train (n=578): +HFDataset( + dataset=Dataset({ + features: ['sub', 'site', 'dataset', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 578 +}), + labels=['Autism' 'Control'], + counts=[260 318] +) + +validation (n=124): +HFDataset( + dataset=Dataset({ + features: ['sub', 'site', 'dataset', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 124 +}), + labels=['Autism' 'Control'], + counts=[54 70] +) + +test (n=124): +HFDataset( + dataset=Dataset({ + features: ['sub', 'site', 'dataset', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 124 +}), + labels=['Autism' 'Control'], + counts=[57 67] +) + +extracting features for all splits +extract (train) [ 0/289] eta: 0:19:42 time: 4.0912 data: 3.4132 max mem: 2698 +extract (train) [ 20/289] eta: 0:01:43 time: 0.1994 data: 0.0709 max mem: 2851 +extract (train) [ 40/289] eta: 0:01:10 time: 0.1727 data: 0.0580 max mem: 2851 +extract (train) [ 60/289] eta: 0:00:56 time: 0.1762 data: 0.0609 max mem: 2851 +extract (train) [ 80/289] eta: 0:00:47 time: 0.1600 data: 0.0515 max mem: 2851 +extract (train) [100/289] eta: 0:00:40 time: 0.1704 data: 0.0570 max mem: 2851 +extract (train) [120/289] eta: 0:00:34 time: 0.1514 data: 0.0464 max mem: 2851 +extract (train) [140/289] eta: 0:00:29 time: 0.1526 data: 0.0477 max mem: 2851 +extract (train) [160/289] eta: 0:00:24 time: 0.1639 data: 0.0536 max mem: 2851 +extract (train) [180/289] eta: 0:00:20 time: 0.1727 data: 0.0591 max mem: 2851 +extract (train) [200/289] eta: 0:00:16 time: 0.1626 data: 0.0517 max mem: 2851 +extract (train) [220/289] eta: 0:00:12 time: 0.1775 data: 0.0606 max mem: 2851 +extract (train) [240/289] eta: 0:00:09 time: 0.1714 data: 0.0549 max mem: 2851 +extract (train) [260/289] eta: 0:00:05 time: 0.1680 data: 0.0528 max mem: 2851 +extract (train) [280/289] eta: 0:00:01 time: 0.1416 data: 0.0401 max mem: 2851 +extract (train) [288/289] eta: 0:00:00 time: 0.1415 data: 0.0402 max mem: 2851 +extract (train) Total time: 0:00:52 (0.1812 s / it) +extract (validation) [ 0/62] eta: 0:04:10 time: 4.0330 data: 3.8930 max mem: 2851 +extract (validation) [20/62] eta: 0:00:15 time: 0.1965 data: 0.0639 max mem: 2851 +extract (validation) [40/62] eta: 0:00:05 time: 0.1463 data: 0.0405 max mem: 2851 +extract (validation) [60/62] eta: 0:00:00 time: 0.1451 data: 0.0443 max mem: 2851 +extract (validation) [61/62] eta: 0:00:00 time: 0.1459 data: 0.0443 max mem: 2851 +extract (validation) Total time: 0:00:14 (0.2302 s / it) +extract (test) [ 0/62] eta: 0:03:53 time: 3.7704 data: 3.6308 max mem: 2851 +extract (test) [20/62] eta: 0:00:16 time: 0.2200 data: 0.0751 max mem: 2851 +extract (test) [40/62] eta: 0:00:05 time: 0.1432 data: 0.0415 max mem: 2851 +extract (test) [60/62] eta: 0:00:00 time: 0.1444 data: 0.0435 max mem: 2851 +extract (test) [61/62] eta: 0:00:00 time: 0.1452 data: 0.0442 max mem: 2851 +extract (test) Total time: 0:00:14 (0.2312 s / it) +feature extraction time: 0:01:21 +train features: (578, 768) +validation features: (124, 768) +test features: (124, 768) +evaluating fixed splits +eval results (fixed splits): + +| model | repr | clf | dataset | trial | C | split | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|---------:|:--------|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | abide_dx | | 0.046416 | train | 0.79915 | 0.01468 | 0.79418 | 0.015204 | 0.79157 | 0.015132 | +| flat_mae | patch | logistic | abide_dx | | 0.046416 | test | 0.67742 | 0.042649 | 0.67437 | 0.043385 | 0.674 | 0.04322 | + + +evaluating random splits (n=100) +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 1, "C": 0.046415888336127774, "split": "test", "acc": 0.7258064516129032, "acc_std": 0.039037203099177735, "f1": 0.724011521340665, "f1_std": 0.03942666132903838, "bacc": 0.7247899159663866, "bacc_std": 0.039524567384582744} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 2, "C": 0.3593813663804626, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.04151567473496331, "f1": 0.6112852664576802, "f1_std": 0.04173346954281823, "bacc": 0.6123949579831933, "bacc_std": 0.04196419978746159} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 3, "C": 0.3593813663804626, "split": "test", "acc": 0.6532258064516129, "acc_std": 0.04213316928756203, "f1": 0.6465831510572015, "f1_std": 0.04362884852202091, "bacc": 0.6460084033613445, "bacc_std": 0.04304187232756407} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 4, "C": 0.3593813663804626, "split": "test", "acc": 0.7016129032258065, "acc_std": 0.04000679897992575, "f1": 0.6944388944388944, "f1_std": 0.041548317053759505, "bacc": 0.6932773109243697, "bacc_std": 0.04091026206879642} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 5, "C": 1291.5496650148827, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.04145349248907917, "f1": 0.6063492063492064, "f1_std": 0.042377012616958455, "bacc": 0.60609243697479, "bacc_std": 0.04189311314939736} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 6, "C": 0.3593813663804626, "split": "test", "acc": 0.6048387096774194, "acc_std": 0.04590057061665403, "f1": 0.6004471624909581, "f1_std": 0.04642903131288017, "bacc": 0.6003151260504203, "bacc_std": 0.04619530619725576} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 7, "C": 0.005994842503189409, "split": "test", "acc": 0.6209677419354839, "acc_std": 0.041749024052847555, "f1": 0.6021028196900389, "f1_std": 0.04583876233327427, "bacc": 0.6055672268907563, "bacc_std": 0.04293966685048903} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 8, "C": 0.3593813663804626, "split": "test", "acc": 0.6209677419354839, "acc_std": 0.04078489485438252, "f1": 0.6049081418208935, "f1_std": 0.04316667020572939, "bacc": 0.6071428571428572, "bacc_std": 0.041397012179623556} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 9, "C": 0.3593813663804626, "split": "test", "acc": 0.7016129032258065, "acc_std": 0.040087131947331274, "f1": 0.6944388944388944, "f1_std": 0.041922791595071354, "bacc": 0.6932773109243697, "bacc_std": 0.04116477253817681} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 10, "C": 0.3593813663804626, "split": "test", "acc": 0.6290322580645161, "acc_std": 0.0429039655526815, "f1": 0.6227513227513227, "f1_std": 0.043690308875009035, "bacc": 0.6223739495798319, "bacc_std": 0.043178726847341545} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 11, "C": 10000.0, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.0438557700194152, "f1": 0.6063492063492064, "f1_std": 0.04504207427897886, "bacc": 0.60609243697479, "bacc_std": 0.044469161302351304} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 12, "C": 0.3593813663804626, "split": "test", "acc": 0.5725806451612904, "acc_std": 0.04208104699421145, "f1": 0.5623043623043623, "f1_std": 0.04405106903427984, "bacc": 0.5630252100840336, "bacc_std": 0.04290296359031134} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 13, "C": 2.782559402207126, "split": "test", "acc": 0.6451612903225806, "acc_std": 0.04115462834145142, "f1": 0.6443285528031291, "f1_std": 0.041154382163452616, "bacc": 0.6465336134453781, "bacc_std": 0.04132880268385882} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 14, "C": 2.782559402207126, "split": "test", "acc": 0.5725806451612904, "acc_std": 0.04408269591443209, "f1": 0.5691904293674206, "f1_std": 0.04444473150500854, "bacc": 0.569327731092437, "bacc_std": 0.04444849279660729} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 15, "C": 0.046415888336127774, "split": "test", "acc": 0.6290322580645161, "acc_std": 0.04363335498232433, "f1": 0.6242424242424243, "f1_std": 0.04444138743510347, "bacc": 0.6239495798319328, "bacc_std": 0.04409055904849567} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 16, "C": 0.3593813663804626, "split": "test", "acc": 0.6209677419354839, "acc_std": 0.043254696652712865, "f1": 0.6167554415729598, "f1_std": 0.043965866876771016, "bacc": 0.6165966386554622, "bacc_std": 0.04381498385615705} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 17, "C": 0.3593813663804626, "split": "test", "acc": 0.6612903225806451, "acc_std": 0.042085266008240835, "f1": 0.6604954367666231, "f1_std": 0.04233036790826822, "bacc": 0.6628151260504203, "bacc_std": 0.042628318884269274} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 18, "C": 0.046415888336127774, "split": "test", "acc": 0.6935483870967742, "acc_std": 0.04316973674526598, "f1": 0.6895915678524374, "f1_std": 0.044160939095567515, "bacc": 0.6890756302521008, "bacc_std": 0.04396428556370223} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 19, "C": 0.3593813663804626, "split": "test", "acc": 0.6451612903225806, "acc_std": 0.040683596778385046, "f1": 0.6231003039513678, "f1_std": 0.04523219697892713, "bacc": 0.6276260504201681, "bacc_std": 0.041886000102435705} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 20, "C": 2.782559402207126, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.04495636397453216, "f1": 0.6119947848761408, "f1_std": 0.04507217832966527, "bacc": 0.6139705882352942, "bacc_std": 0.04515277123991811} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 21, "C": 0.046415888336127774, "split": "test", "acc": 0.6532258064516129, "acc_std": 0.041212489645853397, "f1": 0.6429862738533645, "f1_std": 0.043012863191604606, "bacc": 0.6428571428571428, "bacc_std": 0.04184732481905305} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 22, "C": 0.3593813663804626, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.041432165640185835, "f1": 0.6045708211533352, "f1_std": 0.042787285327808997, "bacc": 0.6045168067226891, "bacc_std": 0.042101983242236046} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 23, "C": 0.046415888336127774, "split": "test", "acc": 0.6774193548387096, "acc_std": 0.04181557297945846, "f1": 0.6688034188034189, "f1_std": 0.043959260701295466, "bacc": 0.6680672268907563, "bacc_std": 0.04290719234985474} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 24, "C": 0.3593813663804626, "split": "test", "acc": 0.6209677419354839, "acc_std": 0.04111854388721451, "f1": 0.6179613241560145, "f1_std": 0.04156701276068065, "bacc": 0.618172268907563, "bacc_std": 0.04147867307507804} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 25, "C": 2.782559402207126, "split": "test", "acc": 0.5564516129032258, "acc_std": 0.04309405776642849, "f1": 0.5541026479241582, "f1_std": 0.04331561531811178, "bacc": 0.5546218487394958, "bacc_std": 0.043338782357981734} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 26, "C": 0.046415888336127774, "split": "test", "acc": 0.6532258064516129, "acc_std": 0.04327470452850182, "f1": 0.6448884448884449, "f1_std": 0.045163244934764334, "bacc": 0.6444327731092437, "bacc_std": 0.044160993111785486} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 27, "C": 2.782559402207126, "split": "test", "acc": 0.6048387096774194, "acc_std": 0.043387621414264145, "f1": 0.6004471624909581, "f1_std": 0.04417157998397544, "bacc": 0.6003151260504203, "bacc_std": 0.044043628583944776} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 28, "C": 0.3593813663804626, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.04320212097830305, "f1": 0.6092436974789917, "f1_std": 0.04374137152221236, "bacc": 0.6092436974789917, "bacc_std": 0.04358181129991112} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 29, "C": 0.3593813663804626, "split": "test", "acc": 0.6612903225806451, "acc_std": 0.041611727915385324, "f1": 0.6539994685091681, "f1_std": 0.04292305053331143, "bacc": 0.6533613445378151, "bacc_std": 0.04231371684882159} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 30, "C": 0.046415888336127774, "split": "test", "acc": 0.6451612903225806, "acc_std": 0.04217661443751774, "f1": 0.6313513513513513, "f1_std": 0.044738745435670815, "bacc": 0.6323529411764706, "bacc_std": 0.042907006695959225} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 31, "C": 0.3593813663804626, "split": "test", "acc": 0.6370967741935484, "acc_std": 0.043645277519335966, "f1": 0.6351748937561295, "f1_std": 0.043870304097377515, "bacc": 0.6360294117647058, "bacc_std": 0.04384094322508657} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 32, "C": 166.81005372000556, "split": "test", "acc": 0.6854838709677419, "acc_std": 0.04046061534851953, "f1": 0.6819885579009667, "f1_std": 0.04079982980991922, "bacc": 0.6817226890756303, "bacc_std": 0.04062647937477944} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 33, "C": 166.81005372000556, "split": "test", "acc": 0.5967741935483871, "acc_std": 0.046101796606685556, "f1": 0.58994708994709, "f1_std": 0.04704634154889424, "bacc": 0.5898109243697479, "bacc_std": 0.04657025228310478} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 34, "C": 2.782559402207126, "split": "test", "acc": 0.6209677419354839, "acc_std": 0.040835253765001, "f1": 0.6137071651090342, "f1_std": 0.0421060355500723, "bacc": 0.6134453781512605, "bacc_std": 0.041518270385794954} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 35, "C": 0.046415888336127774, "split": "test", "acc": 0.6774193548387096, "acc_std": 0.03932712866339709, "f1": 0.6753076721654884, "f1_std": 0.03959278883761525, "bacc": 0.6759453781512605, "bacc_std": 0.03967318330046403} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 36, "C": 0.3593813663804626, "split": "test", "acc": 0.7016129032258065, "acc_std": 0.04175986801323528, "f1": 0.6928021426180114, "f1_std": 0.04350157367943771, "bacc": 0.6917016806722689, "bacc_std": 0.04258852997243399} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 37, "C": 0.3593813663804626, "split": "test", "acc": 0.6532258064516129, "acc_std": 0.0415425104790149, "f1": 0.6513893429225237, "f1_std": 0.041897947134104094, "bacc": 0.6523109243697479, "bacc_std": 0.042060390997831605} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 38, "C": 0.046415888336127774, "split": "test", "acc": 0.6209677419354839, "acc_std": 0.042649050015465095, "f1": 0.6137071651090342, "f1_std": 0.043581674420652, "bacc": 0.6134453781512605, "bacc_std": 0.04304699323578632} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 39, "C": 21.54434690031882, "split": "test", "acc": 0.6370967741935484, "acc_std": 0.041323021326752946, "f1": 0.6342182890855457, "f1_std": 0.041658812096963996, "bacc": 0.634453781512605, "bacc_std": 0.04164822414359369} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 40, "C": 0.3593813663804626, "split": "test", "acc": 0.5806451612903226, "acc_std": 0.044166518105235135, "f1": 0.5716183895827798, "f1_std": 0.04565439811016017, "bacc": 0.571953781512605, "bacc_std": 0.04484903180717537} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 41, "C": 0.005994842503189409, "split": "test", "acc": 0.6048387096774194, "acc_std": 0.041292398511322846, "f1": 0.5907590759075907, "f1_std": 0.04348022542965957, "bacc": 0.592436974789916, "bacc_std": 0.04196025390545418} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 42, "C": 0.046415888336127774, "split": "test", "acc": 0.6532258064516129, "acc_std": 0.04456566902178179, "f1": 0.6465831510572015, "f1_std": 0.04571957406985485, "bacc": 0.6460084033613445, "bacc_std": 0.045063606781618686} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 43, "C": 0.046415888336127774, "split": "test", "acc": 0.6854838709677419, "acc_std": 0.04031134036882061, "f1": 0.6794591370053689, "f1_std": 0.041316999180594775, "bacc": 0.6785714285714286, "bacc_std": 0.04083579804288089} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 44, "C": 0.005994842503189409, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.04135454934225167, "f1": 0.5978378378378378, "f1_std": 0.044094501710218566, "bacc": 0.5997899159663866, "bacc_std": 0.042219368280895925} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 45, "C": 0.3593813663804626, "split": "test", "acc": 0.6532258064516129, "acc_std": 0.039802961628784314, "f1": 0.6480760345851759, "f1_std": 0.0407181663777165, "bacc": 0.6475840336134454, "bacc_std": 0.040247585534714955} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 46, "C": 0.005994842503189409, "split": "test", "acc": 0.6048387096774194, "acc_std": 0.04302701943738297, "f1": 0.5989703649924097, "f1_std": 0.04351100519639439, "bacc": 0.5987394957983193, "bacc_std": 0.04325159933935038} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 47, "C": 0.046415888336127774, "split": "test", "acc": 0.6209677419354839, "acc_std": 0.04169028501610711, "f1": 0.607462787095036, "f1_std": 0.04413461432985312, "bacc": 0.608718487394958, "bacc_std": 0.042563843555224544} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 48, "C": 0.3593813663804626, "split": "test", "acc": 0.6532258064516129, "acc_std": 0.04304515391718819, "f1": 0.6480760345851759, "f1_std": 0.044093049084317805, "bacc": 0.6475840336134454, "bacc_std": 0.043737006642881306} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 49, "C": 0.005994842503189409, "split": "test", "acc": 0.6209677419354839, "acc_std": 0.04228598868076371, "f1": 0.6118548118548119, "f1_std": 0.04385342668565108, "bacc": 0.6118697478991597, "bacc_std": 0.04298577914042962} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 50, "C": 0.046415888336127774, "split": "test", "acc": 0.5887096774193549, "acc_std": 0.04318817572406282, "f1": 0.5765651155005022, "f1_std": 0.045179182611209824, "bacc": 0.5777310924369747, "bacc_std": 0.04387988466346372} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 51, "C": 1291.5496650148827, "split": "test", "acc": 0.5806451612903226, "acc_std": 0.044640251804458415, "f1": 0.5788923719958203, "f1_std": 0.0448703146418622, "bacc": 0.5798319327731092, "bacc_std": 0.04502111432754767} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 52, "C": 0.046415888336127774, "split": "test", "acc": 0.6370967741935484, "acc_std": 0.043556701715212684, "f1": 0.6283716283716283, "f1_std": 0.04517495895427842, "bacc": 0.6281512605042017, "bacc_std": 0.044318842700809546} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 53, "C": 2.782559402207126, "split": "test", "acc": 0.6209677419354839, "acc_std": 0.04198769702368489, "f1": 0.6179613241560145, "f1_std": 0.042460379533953076, "bacc": 0.618172268907563, "bacc_std": 0.04245417420980726} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 54, "C": 0.3593813663804626, "split": "test", "acc": 0.6612903225806451, "acc_std": 0.04215968294193907, "f1": 0.6569169960474308, "f1_std": 0.04294528533229685, "bacc": 0.6565126050420168, "bacc_std": 0.04265219484896751} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 55, "C": 0.3593813663804626, "split": "test", "acc": 0.6209677419354839, "acc_std": 0.044979345473792516, "f1": 0.6153389215233318, "f1_std": 0.04547065108625538, "bacc": 0.6150210084033614, "bacc_std": 0.04510109324017867} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 56, "C": 0.005994842503189409, "split": "test", "acc": 0.6693548387096774, "acc_std": 0.04160000737913167, "f1": 0.6614052614052615, "f1_std": 0.04320255970734275, "bacc": 0.6607142857142857, "bacc_std": 0.042475844310570686} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 57, "C": 0.005994842503189409, "split": "test", "acc": 0.6774193548387096, "acc_std": 0.039887364177390465, "f1": 0.6704756842944459, "f1_std": 0.0412926825660231, "bacc": 0.6696428571428572, "bacc_std": 0.040709514790042846} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 58, "C": 1291.5496650148827, "split": "test", "acc": 0.6290322580645161, "acc_std": 0.04210652464017509, "f1": 0.6242424242424243, "f1_std": 0.04298173780621942, "bacc": 0.6239495798319328, "bacc_std": 0.04269692218620088} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 59, "C": 0.046415888336127774, "split": "test", "acc": 0.6612903225806451, "acc_std": 0.04220808112652048, "f1": 0.6580882352941176, "f1_std": 0.04257643796432481, "bacc": 0.6580882352941176, "bacc_std": 0.04249908274171437} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 60, "C": 0.3593813663804626, "split": "test", "acc": 0.6451612903225806, "acc_std": 0.044277339919929874, "f1": 0.6418067226890756, "f1_std": 0.04459195855550761, "bacc": 0.6418067226890756, "bacc_std": 0.04451701833054351} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 61, "C": 0.046415888336127774, "split": "test", "acc": 0.5967741935483871, "acc_std": 0.04401001151355811, "f1": 0.5915678524374176, "f1_std": 0.04436902614593565, "bacc": 0.5913865546218487, "bacc_std": 0.04410814567304671} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 62, "C": 0.3593813663804626, "split": "test", "acc": 0.5725806451612904, "acc_std": 0.04172805709854658, "f1": 0.5643931861867832, "f1_std": 0.042600541296591465, "bacc": 0.5646008403361344, "bacc_std": 0.04200894984313747} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 63, "C": 0.046415888336127774, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.04500936138030224, "f1": 0.6092436974789917, "f1_std": 0.04557332257087634, "bacc": 0.6092436974789917, "bacc_std": 0.04549400985119451} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 64, "C": 166.81005372000556, "split": "test", "acc": 0.6693548387096774, "acc_std": 0.04496330738998645, "f1": 0.6682977751680041, "f1_std": 0.04507435989520633, "bacc": 0.6701680672268908, "bacc_std": 0.04491339799159255} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 65, "C": 0.3593813663804626, "split": "test", "acc": 0.6612903225806451, "acc_std": 0.041331254912890046, "f1": 0.6522435897435898, "f1_std": 0.04290431564138206, "bacc": 0.6517857142857143, "bacc_std": 0.04207964869882113} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 66, "C": 2.782559402207126, "split": "test", "acc": 0.5645161290322581, "acc_std": 0.04356944234129377, "f1": 0.5626959247648903, "f1_std": 0.04375344426045893, "bacc": 0.5635504201680672, "bacc_std": 0.04389892082282419} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 67, "C": 2.782559402207126, "split": "test", "acc": 0.6370967741935484, "acc_std": 0.04309590495549899, "f1": 0.6351748937561295, "f1_std": 0.043197622739423236, "bacc": 0.6360294117647058, "bacc_std": 0.043174713991567505} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 68, "C": 2.782559402207126, "split": "test", "acc": 0.6290322580645161, "acc_std": 0.04379661631240743, "f1": 0.6255252100840336, "f1_std": 0.04420431508650615, "bacc": 0.6255252100840336, "bacc_std": 0.04411193260309923} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 69, "C": 1291.5496650148827, "split": "test", "acc": 0.5887096774193549, "acc_std": 0.043767296268843285, "f1": 0.5841388834089565, "f1_std": 0.04475205691190134, "bacc": 0.5840336134453781, "bacc_std": 0.04444776177798601} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 70, "C": 2.782559402207126, "split": "test", "acc": 0.6290322580645161, "acc_std": 0.04197843953812708, "f1": 0.6227513227513227, "f1_std": 0.042808453510781094, "bacc": 0.6223739495798319, "bacc_std": 0.04237653595875981} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 71, "C": 0.046415888336127774, "split": "test", "acc": 0.6935483870967742, "acc_std": 0.04208898395351609, "f1": 0.6853632478632479, "f1_std": 0.04405212035766044, "bacc": 0.6843487394957983, "bacc_std": 0.043146237462119} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 72, "C": 0.3593813663804626, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.044410449009996626, "f1": 0.6092436974789917, "f1_std": 0.04467578898111247, "bacc": 0.6092436974789917, "bacc_std": 0.044565155550613834} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 73, "C": 0.005994842503189409, "split": "test", "acc": 0.5725806451612904, "acc_std": 0.041003654566699084, "f1": 0.5623043623043623, "f1_std": 0.04284621234606453, "bacc": 0.5630252100840336, "bacc_std": 0.0418267576882376} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 74, "C": 0.3593813663804626, "split": "test", "acc": 0.6854838709677419, "acc_std": 0.041414565470260956, "f1": 0.6829891838741396, "f1_std": 0.041784077607795705, "bacc": 0.6832983193277311, "bacc_std": 0.041637047935860545} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 75, "C": 2.782559402207126, "split": "test", "acc": 0.6532258064516129, "acc_std": 0.04149802535326956, "f1": 0.6493719997369632, "f1_std": 0.04196815785427738, "bacc": 0.6491596638655461, "bacc_std": 0.04185039788233081} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 76, "C": 0.3593813663804626, "split": "test", "acc": 0.6370967741935484, "acc_std": 0.04303732378172978, "f1": 0.6301451580831179, "f1_std": 0.04435700387029173, "bacc": 0.6297268907563025, "bacc_std": 0.04371659427573878} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 77, "C": 0.046415888336127774, "split": "test", "acc": 0.5725806451612904, "acc_std": 0.04294033078965115, "f1": 0.5723303182143554, "f1_std": 0.042986272122954375, "bacc": 0.5756302521008403, "bacc_std": 0.04319923614399796} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 78, "C": 0.3593813663804626, "split": "test", "acc": 0.6209677419354839, "acc_std": 0.0429983906965993, "f1": 0.6179613241560145, "f1_std": 0.04320748512367196, "bacc": 0.618172268907563, "bacc_std": 0.0431682523203631} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 79, "C": 0.046415888336127774, "split": "test", "acc": 0.5967741935483871, "acc_std": 0.044680749846749954, "f1": 0.5915678524374176, "f1_std": 0.04547595684283403, "bacc": 0.5913865546218487, "bacc_std": 0.045206519737430666} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 80, "C": 0.3593813663804626, "split": "test", "acc": 0.6774193548387096, "acc_std": 0.04131907705929863, "f1": 0.6753076721654884, "f1_std": 0.04157348866608114, "bacc": 0.6759453781512605, "bacc_std": 0.0415904143309112} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 81, "C": 0.3593813663804626, "split": "test", "acc": 0.6451612903225806, "acc_std": 0.043883332579144674, "f1": 0.6336287939833467, "f1_std": 0.04624339481015952, "bacc": 0.6339285714285714, "bacc_std": 0.044883426690897774} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 82, "C": 0.046415888336127774, "split": "test", "acc": 0.6532258064516129, "acc_std": 0.04271855416475561, "f1": 0.6465831510572015, "f1_std": 0.04388926420251252, "bacc": 0.6460084033613445, "bacc_std": 0.043359447976466244} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 83, "C": 21.54434690031882, "split": "test", "acc": 0.5806451612903226, "acc_std": 0.043848105404391546, "f1": 0.580536039552433, "f1_std": 0.04393169987785544, "bacc": 0.5845588235294117, "bacc_std": 0.04384154731237929} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 84, "C": 166.81005372000556, "split": "test", "acc": 0.5967741935483871, "acc_std": 0.043614701599684856, "f1": 0.5966692688004163, "f1_std": 0.04381985807910171, "bacc": 0.6008403361344539, "bacc_std": 0.04378810299153417} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 85, "C": 0.005994842503189409, "split": "test", "acc": 0.5806451612903226, "acc_std": 0.04079154387896022, "f1": 0.5716183895827798, "f1_std": 0.04182485287486705, "bacc": 0.571953781512605, "bacc_std": 0.04117255891373242} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 86, "C": 1291.5496650148827, "split": "test", "acc": 0.5967741935483871, "acc_std": 0.043822467854580764, "f1": 0.5963541666666667, "f1_std": 0.04388604785182247, "bacc": 0.5992647058823529, "bacc_std": 0.04396777137036325} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 87, "C": 0.3593813663804626, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.04472082437963983, "f1": 0.6125, "f1_std": 0.04475092079340543, "bacc": 0.615546218487395, "bacc_std": 0.04467962473810485} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 88, "C": 2.782559402207126, "split": "test", "acc": 0.6612903225806451, "acc_std": 0.04598747454227373, "f1": 0.6598746081504703, "f1_std": 0.046104791865562614, "bacc": 0.6612394957983193, "bacc_std": 0.04606250890790423} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 89, "C": 0.3593813663804626, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.04379293344560365, "f1": 0.6092436974789917, "f1_std": 0.04412434136811076, "bacc": 0.6092436974789917, "bacc_std": 0.04395668389157769} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 90, "C": 0.046415888336127774, "split": "test", "acc": 0.6451612903225806, "acc_std": 0.04280832032773533, "f1": 0.6313513513513513, "f1_std": 0.0456673809383683, "bacc": 0.6323529411764706, "bacc_std": 0.0438559082086249} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 91, "C": 166.81005372000556, "split": "test", "acc": 0.5967741935483871, "acc_std": 0.04243889835578258, "f1": 0.5880946053680574, "f1_std": 0.043803108736806026, "bacc": 0.5882352941176471, "bacc_std": 0.04306195289494678} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 92, "C": 0.3593813663804626, "split": "test", "acc": 0.5564516129032258, "acc_std": 0.044568397902227545, "f1": 0.5479551932126997, "f1_std": 0.0458967743514932, "bacc": 0.5483193277310925, "bacc_std": 0.04517212293693084} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 93, "C": 0.046415888336127774, "split": "test", "acc": 0.5241935483870968, "acc_std": 0.04590787272740787, "f1": 0.5189057670809496, "f1_std": 0.04658642019587513, "bacc": 0.51890756302521, "bacc_std": 0.04632341479434743} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 94, "C": 2.782559402207126, "split": "test", "acc": 0.5967741935483871, "acc_std": 0.04497397501578089, "f1": 0.5950888192267503, "f1_std": 0.04521052382286268, "bacc": 0.5961134453781513, "bacc_std": 0.04521895872487394} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 95, "C": 0.3593813663804626, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.04280556432461559, "f1": 0.6003223207091055, "f1_std": 0.045223109108494114, "bacc": 0.6013655462184874, "bacc_std": 0.043678934875670934} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 96, "C": 1291.5496650148827, "split": "test", "acc": 0.6209677419354839, "acc_std": 0.046063733954685805, "f1": 0.6179613241560145, "f1_std": 0.04623314446149793, "bacc": 0.618172268907563, "bacc_std": 0.045998413920236306} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 97, "C": 2.782559402207126, "split": "test", "acc": 0.717741935483871, "acc_std": 0.040812058138375164, "f1": 0.7135502607088642, "f1_std": 0.0416634965895804, "bacc": 0.7127100840336134, "bacc_std": 0.04151158782041816} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 98, "C": 0.046415888336127774, "split": "test", "acc": 0.6290322580645161, "acc_std": 0.04328480266235772, "f1": 0.6242424242424243, "f1_std": 0.04392285786660808, "bacc": 0.6239495798319328, "bacc_std": 0.043706421432174264} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 99, "C": 0.3593813663804626, "split": "test", "acc": 0.6209677419354839, "acc_std": 0.041986631339490585, "f1": 0.6153389215233318, "f1_std": 0.04303908634062656, "bacc": 0.6150210084033614, "bacc_std": 0.04269015564444284} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 100, "C": 0.3593813663804626, "split": "test", "acc": 0.7016129032258065, "acc_std": 0.041833312259109474, "f1": 0.6958971299794525, "f1_std": 0.04289907306580737, "bacc": 0.6948529411764706, "bacc_std": 0.04253965304928108} +eval results (random splits): + +| model | repr | clf | dataset | split | n_trials | C | C_std | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|-----------:|-------:|--------:|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | abide_dx | train | 100 | 186.83 | 1038 | 0.88832 | 0.090729 | 0.88623 | 0.092827 | 0.88523 | 0.093435 | +| flat_mae | patch | logistic | abide_dx | test | 100 | 186.83 | 1038 | 0.63008 | 0.038916 | 0.62411 | 0.039196 | 0.62451 | 0.03882 | + + +done! total time: 0:05:40 diff --git a/input_space_v3/flat_lr1e-3_7/eval_v2/adhd200_dx__patch__logistic/config.yaml b/input_space_v3/flat_lr1e-3_7/eval_v2/adhd200_dx__patch__logistic/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..6fd0ab691c60220e52e6c39dc303240f2be45e4d --- /dev/null +++ b/input_space_v3/flat_lr1e-3_7/eval_v2/adhd200_dx__patch__logistic/config.yaml @@ -0,0 +1,30 @@ +output_root: experiments/input_space_v3/output +name_prefix: eval_logistic +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_7; eval v2 (adhd200_dx patch logistic) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_7/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: input_space_v3/flat_lr1e-3_7/eval_v2/adhd200_dx__patch__logistic +model: flat_mae +representation: patch +dataset: adhd200_dx +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_7/eval_v2/adhd200_dx__patch__logistic +remote_dir: null diff --git a/input_space_v3/flat_lr1e-3_7/eval_v2/adhd200_dx__patch__logistic/eval_table.csv b/input_space_v3/flat_lr1e-3_7/eval_v2/adhd200_dx__patch__logistic/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..7079d72044cecf67ed1e45b20f713eac1cab1488 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_7/eval_v2/adhd200_dx__patch__logistic/eval_table.csv @@ -0,0 +1,203 @@ +model,repr,clf,dataset,trial,C,split,acc,acc_std,f1,f1_std,bacc,bacc_std +flat_mae,patch,logistic,adhd200_dx,,0.005994842503189409,train,0.7479452054794521,0.02206632966445029,0.7380328278100231,0.023350759801808427,0.7350857910484215,0.02293905533347284 +flat_mae,patch,logistic,adhd200_dx,,0.005994842503189409,test,0.5846153846153846,0.05818333806513998,0.5644080416976918,0.061745091677532546,0.5656370656370656,0.059590022187645024 +flat_mae,patch,logistic,adhd200_dx,1,0.000774263682681127,train,0.6794520547945205,0.023341613593037335,0.6606108289821901,0.025397698564475404,0.6600567869573182,0.024202252244576027 +flat_mae,patch,logistic,adhd200_dx,1,0.000774263682681127,test,0.5846153846153846,0.058508572173242096,0.5745454545454545,0.059559239662815906,0.5743243243243243,0.05908672889653841 +flat_mae,patch,logistic,adhd200_dx,2,0.046415888336127774,train,0.852054794520548,0.01819806707694079,0.8488682370261318,0.018740996305113805,0.8474079501740246,0.018988053781523878 +flat_mae,patch,logistic,adhd200_dx,2,0.046415888336127774,test,0.6615384615384615,0.058877065787449404,0.6474358974358974,0.06253449641072095,0.6462355212355213,0.06081569542801764 +flat_mae,patch,logistic,adhd200_dx,3,0.005994842503189409,train,0.7726027397260274,0.02167632657523431,0.763396099686819,0.023065805937287135,0.7598003297307199,0.022761824205848002 +flat_mae,patch,logistic,adhd200_dx,3,0.005994842503189409,test,0.5538461538461539,0.05878017618573489,0.5381034060279344,0.06096199179989891,0.5386100386100386,0.05965147950373145 +flat_mae,patch,logistic,adhd200_dx,4,0.005994842503189409,train,0.7342465753424657,0.02183445726628766,0.7240989674654198,0.023159681954593468,0.7215149294742627,0.0227514051829446 +flat_mae,patch,logistic,adhd200_dx,4,0.005994842503189409,test,0.6461538461538462,0.0583204775915705,0.6375757575757576,0.0603310539016322,0.6370656370656371,0.059808325507432335 +flat_mae,patch,logistic,adhd200_dx,5,0.005994842503189409,train,0.7589041095890411,0.022012559577047047,0.7494227048617612,0.023595532713753236,0.746229468156561,0.023250044462905663 +flat_mae,patch,logistic,adhd200_dx,5,0.005994842503189409,test,0.5230769230769231,0.0613013586150204,0.521263958184842,0.06153219271243599,0.5246138996138996,0.062738070424093 +flat_mae,patch,logistic,adhd200_dx,6,0.005994842503189409,train,0.7589041095890411,0.021198097897582962,0.7470547470547471,0.022946522562335658,0.7433595896684374,0.02236168079950678 +flat_mae,patch,logistic,adhd200_dx,6,0.005994842503189409,test,0.6461538461538462,0.05900120147207114,0.6336682185738789,0.061745579571214494,0.6327220077220077,0.06043469667809714 +flat_mae,patch,logistic,adhd200_dx,7,0.005994842503189409,train,0.7561643835616438,0.021817389137013254,0.7468536917981687,0.023089463414884933,0.7438022836905416,0.022816711101192443 +flat_mae,patch,logistic,adhd200_dx,7,0.005994842503189409,test,0.6307692307692307,0.05393487196796878,0.61,0.05845980488311445,0.6105212355212355,0.05572080973148829 +flat_mae,patch,logistic,adhd200_dx,8,0.005994842503189409,train,0.7534246575342466,0.022032916912201474,0.7437277663358921,0.023535676215075872,0.7406576296024913,0.023158290776090294 +flat_mae,patch,logistic,adhd200_dx,8,0.005994842503189409,test,0.5846153846153846,0.06281997194952928,0.5745454545454545,0.0641655179436087,0.5743243243243243,0.0635279974551339 +flat_mae,patch,logistic,adhd200_dx,9,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adhd200_dx,9,166.81005372000556,test,0.6153846153846154,0.06097852177892799,0.6018132810585641,0.06318782395323387,0.6013513513513513,0.06202078754336078 +flat_mae,patch,logistic,adhd200_dx,10,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adhd200_dx,10,1291.5496650148827,test,0.5230769230769231,0.060106249121301455,0.5189782764382908,0.06067123430248141,0.5202702702702703,0.06093768360811646 +flat_mae,patch,logistic,adhd200_dx,11,0.3593813663804626,train,0.958904109589041,0.010285576643197628,0.9579844830364749,0.010578073238088088,0.9557000671673689,0.011099177056417815 +flat_mae,patch,logistic,adhd200_dx,11,0.3593813663804626,test,0.5846153846153846,0.06444280983666813,0.5810455956075435,0.06461267577072316,0.583011583011583,0.06466372751688623 +flat_mae,patch,logistic,adhd200_dx,12,0.005994842503189409,train,0.7452054794520548,0.021470036376317003,0.7360440432033966,0.022607635993448796,0.733376076204433,0.022282823895535032 +flat_mae,patch,logistic,adhd200_dx,12,0.005994842503189409,test,0.6,0.059058362468957716,0.5833333333333333,0.06341228641480415,0.5834942084942085,0.06123791015463164 +flat_mae,patch,logistic,adhd200_dx,13,0.3593813663804626,train,0.9534246575342465,0.010393541306117306,0.9523018856321441,0.010737217915169038,0.9494107589912683,0.011370514420702048 +flat_mae,patch,logistic,adhd200_dx,13,0.3593813663804626,test,0.6307692307692307,0.05975802092680745,0.6264367816091954,0.06019509140741275,0.627895752895753,0.060133979882865105 +flat_mae,patch,logistic,adhd200_dx,14,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adhd200_dx,14,2.782559402207126,test,0.5692307692307692,0.060918811039460855,0.5608108108108107,0.06184970262461596,0.5608108108108107,0.06137846273987037 +flat_mae,patch,logistic,adhd200_dx,15,0.005994842503189409,train,0.7506849315068493,0.02124802570498121,0.74059090447591,0.02264760935372455,0.737512975514441,0.022289443544714106 +flat_mae,patch,logistic,adhd200_dx,15,0.005994842503189409,test,0.6153846153846154,0.060385906894566806,0.6139225469232596,0.06052147780024308,0.6187258687258688,0.06091748485159736 +flat_mae,patch,logistic,adhd200_dx,16,0.005994842503189409,train,0.7698630136986301,0.020692114510783535,0.761333914559721,0.021949703761846708,0.7580906148867314,0.021737340447942722 +flat_mae,patch,logistic,adhd200_dx,16,0.005994842503189409,test,0.6,0.061658344766056944,0.5921814671814671,0.06290553334245476,0.5921814671814671,0.06265752293344619 +flat_mae,patch,logistic,adhd200_dx,17,0.005994842503189409,train,0.7589041095890411,0.020679466573740285,0.7494227048617612,0.02180676470612323,0.746229468156561,0.021475978209769517 +flat_mae,patch,logistic,adhd200_dx,17,0.005994842503189409,test,0.5538461538461539,0.060382457580260444,0.5250692869740489,0.06511141569568044,0.5299227799227799,0.06163298616186977 +flat_mae,patch,logistic,adhd200_dx,18,0.005994842503189409,train,0.7452054794520548,0.02165698161547017,0.732347723240686,0.023443945334675236,0.7290712584722476,0.022723505368351576 +flat_mae,patch,logistic,adhd200_dx,18,0.005994842503189409,test,0.6615384615384615,0.05784676759085213,0.6549227799227799,0.05917152385134325,0.6549227799227799,0.058897760278548546 +flat_mae,patch,logistic,adhd200_dx,19,0.3593813663804626,train,0.958904109589041,0.010521495391128028,0.9579844830364749,0.010823680653619204,0.9557000671673689,0.0113882110277603 +flat_mae,patch,logistic,adhd200_dx,19,0.3593813663804626,test,0.6307692307692307,0.0612143464640255,0.6264367816091954,0.0620498973594574,0.627895752895753,0.06234864349133447 +flat_mae,patch,logistic,adhd200_dx,20,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adhd200_dx,20,1291.5496650148827,test,0.6615384615384615,0.05798571544153157,0.6575670498084292,0.05866936922344173,0.6592664092664093,0.058859692605672545 +flat_mae,patch,logistic,adhd200_dx,21,0.005994842503189409,train,0.7534246575342466,0.021672673003428296,0.7413059913059913,0.023351099164892225,0.7377877511143677,0.022717833847286574 +flat_mae,patch,logistic,adhd200_dx,21,0.005994842503189409,test,0.6153846153846154,0.05983570405109261,0.6139225469232596,0.05992020712091062,0.6187258687258688,0.06008656307777196 +flat_mae,patch,logistic,adhd200_dx,22,0.000774263682681127,train,0.6575342465753424,0.022029427426378936,0.634300783097282,0.024438497875483238,0.6356170238749466,0.022898643159573802 +flat_mae,patch,logistic,adhd200_dx,22,0.000774263682681127,test,0.6,0.05769732080783619,0.5833333333333333,0.06102026586332118,0.5834942084942085,0.05906065137625694 +flat_mae,patch,logistic,adhd200_dx,23,0.000774263682681127,train,0.673972602739726,0.02394018881024583,0.6575202050068993,0.025705508469178105,0.6566373572693411,0.024713529704764658 +flat_mae,patch,logistic,adhd200_dx,23,0.000774263682681127,test,0.6153846153846154,0.044717538224415605,0.5421245421245421,0.0608812025259523,0.5709459459459459,0.047272133750143476 +flat_mae,patch,logistic,adhd200_dx,24,0.046415888336127774,train,0.8575342465753425,0.018775173555866748,0.8534408203607611,0.019538564535999035,0.8501099102399707,0.019692572705841363 +flat_mae,patch,logistic,adhd200_dx,24,0.046415888336127774,test,0.6153846153846154,0.056265566419410024,0.5834401435529352,0.06314718495088413,0.5883204633204633,0.058091804175098086 +flat_mae,patch,logistic,adhd200_dx,25,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adhd200_dx,25,21.54434690031882,test,0.6153846153846154,0.05931250304743073,0.6150201374081972,0.05956283721888513,0.6230694980694981,0.05965041274069326 +flat_mae,patch,logistic,adhd200_dx,26,0.005994842503189409,train,0.7315068493150685,0.022445603392495784,0.7183109683109683,0.02420806433202098,0.7155003968980888,0.023505479403390837 +flat_mae,patch,logistic,adhd200_dx,26,0.005994842503189409,test,0.6461538461538462,0.05828848069943598,0.6336682185738789,0.06090929214363375,0.6327220077220077,0.05960576765603033 +flat_mae,patch,logistic,adhd200_dx,27,0.005994842503189409,train,0.7506849315068493,0.020460588004134885,0.7393859504586148,0.0221610343564762,0.7360780362703792,0.021698971936130993 +flat_mae,patch,logistic,adhd200_dx,27,0.005994842503189409,test,0.5846153846153846,0.05841037437236237,0.5745454545454545,0.05977994398448154,0.5743243243243243,0.05914803254539785 +flat_mae,patch,logistic,adhd200_dx,28,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adhd200_dx,28,1291.5496650148827,test,0.6,0.056657668156629475,0.5976190476190476,0.05674189828541796,0.6008687258687259,0.05718574725918765 +flat_mae,patch,logistic,adhd200_dx,29,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adhd200_dx,29,2.782559402207126,test,0.5846153846153846,0.06257946427632971,0.578226387887527,0.06369824484111589,0.5786679536679536,0.06362214820051393 +flat_mae,patch,logistic,adhd200_dx,30,0.046415888336127774,train,0.852054794520548,0.01926840257940689,0.847803928836175,0.02006173885222223,0.844538071685901,0.020172542676747385 +flat_mae,patch,logistic,adhd200_dx,30,0.046415888336127774,test,0.6,0.0602474660028396,0.5976190476190476,0.06029496287128843,0.6008687258687259,0.060691925801425406 +flat_mae,patch,logistic,adhd200_dx,31,0.000774263682681127,train,0.6575342465753424,0.021738512538315376,0.6320831552548605,0.02429753146601814,0.6341820846308848,0.022550329256643104 +flat_mae,patch,logistic,adhd200_dx,31,0.000774263682681127,test,0.6,0.05685143932959089,0.570630081300813,0.06356418940775081,0.5748069498069498,0.05906827043593876 +flat_mae,patch,logistic,adhd200_dx,32,0.3593813663804626,train,0.958904109589041,0.010407647634914927,0.9580527271473556,0.01066461227011962,0.9564175367893998,0.011071188664511056 +flat_mae,patch,logistic,adhd200_dx,32,0.3593813663804626,test,0.6461538461538462,0.06036483948586169,0.6336682185738789,0.06286716555740308,0.6327220077220077,0.06152948288466193 +flat_mae,patch,logistic,adhd200_dx,33,0.3593813663804626,train,0.9698630136986301,0.008857715170031269,0.9692386665747275,0.009077791646665648,0.9675612138975392,0.009544651457154742 +flat_mae,patch,logistic,adhd200_dx,33,0.3593813663804626,test,0.6,0.05956861887797623,0.599905303030303,0.05981267661835293,0.6095559845559846,0.059827503628071176 +flat_mae,patch,logistic,adhd200_dx,34,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adhd200_dx,34,21.54434690031882,test,0.5692307692307692,0.06067146176077636,0.564176245210728,0.06107779904190585,0.5651544401544402,0.06104206390027087 +flat_mae,patch,logistic,adhd200_dx,35,0.005994842503189409,train,0.7342465753424657,0.022758372285845586,0.7201207895589758,0.024519533718015605,0.7172101117420773,0.023673531953020605 +flat_mae,patch,logistic,adhd200_dx,35,0.005994842503189409,test,0.5692307692307692,0.052107662783030854,0.5190274841437632,0.06198354830485749,0.5347490347490347,0.05392670119000252 +flat_mae,patch,logistic,adhd200_dx,36,0.000774263682681127,train,0.6712328767123288,0.02339159021476266,0.655920060331825,0.024823634190343336,0.6549276424253526,0.024057866528185392 +flat_mae,patch,logistic,adhd200_dx,36,0.000774263682681127,test,0.5384615384615384,0.05776323844779074,0.5125,0.061353643975089245,0.5164092664092664,0.05851979956782861 +flat_mae,patch,logistic,adhd200_dx,37,0.046415888336127774,train,0.8383561643835616,0.018668193201750994,0.8344594854292062,0.01923551228968575,0.8324021493558039,0.019340917731287408 +flat_mae,patch,logistic,adhd200_dx,37,0.046415888336127774,test,0.6,0.06206765539436661,0.5921814671814671,0.06294332776214984,0.5921814671814671,0.06249545485180194 +flat_mae,patch,logistic,adhd200_dx,38,0.046415888336127774,train,0.8465753424657534,0.016886330651812484,0.8424589961770872,0.01758560325503529,0.8396837027538622,0.01778076419787394 +flat_mae,patch,logistic,adhd200_dx,38,0.046415888336127774,test,0.6153846153846154,0.05783642307680798,0.5966741126830479,0.06169667580979903,0.597007722007722,0.05938063473281416 +flat_mae,patch,logistic,adhd200_dx,39,0.046415888336127774,train,0.863013698630137,0.017155921997911498,0.8588073280930866,0.01796261013911373,0.8549642791720096,0.018158828056123278 +flat_mae,patch,logistic,adhd200_dx,39,0.046415888336127774,test,0.5692307692307692,0.06184271708782477,0.5565302144249512,0.06353303523517123,0.5564671814671815,0.06275183531452173 +flat_mae,patch,logistic,adhd200_dx,40,0.046415888336127774,train,0.8493150684931506,0.01793883898360105,0.8456825711628193,0.018487474638616046,0.8435458264639434,0.018597873014313614 +flat_mae,patch,logistic,adhd200_dx,40,0.046415888336127774,test,0.6461538461538462,0.05796988404008845,0.6289401836684041,0.06165378151424982,0.6283783783783784,0.05958077871028071 +flat_mae,patch,logistic,adhd200_dx,41,0.005994842503189409,train,0.7589041095890411,0.021240473055647736,0.7494227048617612,0.02259479528759677,0.746229468156561,0.022256350814694407 +flat_mae,patch,logistic,adhd200_dx,41,0.005994842503189409,test,0.6153846153846154,0.06036552172405828,0.6094688776736361,0.061236630805570756,0.61003861003861,0.061002699484323734 +flat_mae,patch,logistic,adhd200_dx,42,0.005994842503189409,train,0.7452054794520548,0.0230429631286141,0.7336581691500129,0.024282566398027308,0.7305061977163094,0.023684012882431733 +flat_mae,patch,logistic,adhd200_dx,42,0.005994842503189409,test,0.6307692307692307,0.06113668070651736,0.6264367816091954,0.06156334856267409,0.627895752895753,0.06165253588740631 +flat_mae,patch,logistic,adhd200_dx,43,0.046415888336127774,train,0.8602739726027397,0.017096097645389552,0.8555509858848909,0.01806212585669902,0.8511021554619284,0.018335837737541754 +flat_mae,patch,logistic,adhd200_dx,43,0.046415888336127774,test,0.5846153846153846,0.05962327491208952,0.5745454545454545,0.06136943112074644,0.5743243243243243,0.06074551424780151 +flat_mae,patch,logistic,adhd200_dx,44,0.046415888336127774,train,0.8410958904109589,0.018825830384350886,0.8374039938556068,0.019422503371292085,0.8355468034438542,0.01962198556594639 +flat_mae,patch,logistic,adhd200_dx,44,0.046415888336127774,test,0.5692307692307692,0.060891017205589204,0.5565302144249512,0.06315427138569375,0.5564671814671815,0.06217624288952483 +flat_mae,patch,logistic,adhd200_dx,45,0.005994842503189409,train,0.7780821917808219,0.02138077417265756,0.7680248570016242,0.02309994568623357,0.7639372290407278,0.02272245299976333 +flat_mae,patch,logistic,adhd200_dx,45,0.005994842503189409,test,0.5076923076923077,0.05728046642896272,0.4715447154471545,0.06060042783426683,0.4806949806949807,0.05726067903861227 +flat_mae,patch,logistic,adhd200_dx,46,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adhd200_dx,46,166.81005372000556,test,0.6461538461538462,0.05769538453333772,0.6407113674597452,0.05877208329477423,0.6414092664092663,0.05865578092871612 +flat_mae,patch,logistic,adhd200_dx,47,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adhd200_dx,47,1291.5496650148827,test,0.5384615384615384,0.061087578996816584,0.5192307692307693,0.06335557495330009,0.5207528957528957,0.061679006914601556 +flat_mae,patch,logistic,adhd200_dx,48,0.046415888336127774,train,0.8273972602739726,0.0199295580650649,0.8219222637827288,0.020824155310284143,0.8183885937595408,0.020823124586265243 +flat_mae,patch,logistic,adhd200_dx,48,0.046415888336127774,test,0.7230769230769231,0.05632618443720858,0.7198275862068966,0.0567970638098207,0.722007722007722,0.056812539326016535 +flat_mae,patch,logistic,adhd200_dx,49,0.3593813663804626,train,0.9698630136986301,0.008680287423477127,0.9693326509880005,0.008844500524674217,0.968996153141601,0.009023332543594052 +flat_mae,patch,logistic,adhd200_dx,49,0.3593813663804626,test,0.47692307692307695,0.06220397064896292,0.47580645161290325,0.06254693041139935,0.4797297297297297,0.06321884270191114 +flat_mae,patch,logistic,adhd200_dx,50,0.3593813663804626,train,0.9643835616438357,0.009387750290010915,0.9636456968610415,0.009629135697423288,0.9619893753434695,0.010130284637279836 +flat_mae,patch,logistic,adhd200_dx,50,0.3593813663804626,test,0.5846153846153846,0.05886226224976206,0.5810455956075435,0.0591605557423051,0.583011583011583,0.059339167041078555 +flat_mae,patch,logistic,adhd200_dx,51,0.000774263682681127,train,0.6767123287671233,0.02411774395084019,0.6647309752148461,0.0252956135052516,0.6633693594675459,0.024814600640183843 +flat_mae,patch,logistic,adhd200_dx,51,0.000774263682681127,test,0.5692307692307692,0.06087485270871456,0.5512820512820513,0.06426777350539033,0.5521235521235521,0.06222744176440095 +flat_mae,patch,logistic,adhd200_dx,52,0.005994842503189409,train,0.7342465753424657,0.022402450071085187,0.721529640320589,0.024077703333445055,0.7186450509861391,0.02342119666096028 +flat_mae,patch,logistic,adhd200_dx,52,0.005994842503189409,test,0.6923076923076923,0.051633152965968494,0.6697154471544715,0.05752579218296702,0.6689189189189189,0.05427822977947073 +flat_mae,patch,logistic,adhd200_dx,53,0.005994842503189409,train,0.7506849315068493,0.021532873880052487,0.74059090447591,0.022723938039039732,0.737512975514441,0.022304543683782627 +flat_mae,patch,logistic,adhd200_dx,53,0.005994842503189409,test,0.6461538461538462,0.05262758293145431,0.6167649320687003,0.06003187431643137,0.6196911196911197,0.05503548552971564 +flat_mae,patch,logistic,adhd200_dx,54,0.000774263682681127,train,0.6904109589041096,0.02249546982187829,0.6812128519643534,0.023497848948579234,0.6798100995298284,0.023274962110298867 +flat_mae,patch,logistic,adhd200_dx,54,0.000774263682681127,test,0.49230769230769234,0.06313321315718293,0.4844989185291997,0.06376110094553114,0.4845559845559846,0.06364553156850539 +flat_mae,patch,logistic,adhd200_dx,55,0.046415888336127774,train,0.8465753424657534,0.01886914853332491,0.8424589961770872,0.019611229517119317,0.8396837027538622,0.01986763473461124 +flat_mae,patch,logistic,adhd200_dx,55,0.046415888336127774,test,0.5384615384615384,0.06002346681130087,0.5248538011695907,0.06173858287582608,0.525096525096525,0.06102152925804111 +flat_mae,patch,logistic,adhd200_dx,56,0.046415888336127774,train,0.8383561643835616,0.01817690099495639,0.8341688420695975,0.018786806861766626,0.831684679733773,0.018925001835367824 +flat_mae,patch,logistic,adhd200_dx,56,0.046415888336127774,test,0.6307692307692307,0.05941310595957187,0.6264367816091954,0.0598962618215414,0.627895752895753,0.05992297629225627 +flat_mae,patch,logistic,adhd200_dx,57,0.046415888336127774,train,0.852054794520548,0.019060432873687118,0.848085460599334,0.01972527150946942,0.8452555413079319,0.019805586831418743 +flat_mae,patch,logistic,adhd200_dx,57,0.046415888336127774,test,0.5538461538461539,0.06325510293515677,0.543030303030303,0.06481187633172976,0.542953667953668,0.06420147004184837 +flat_mae,patch,logistic,adhd200_dx,58,0.046415888336127774,train,0.8547945205479452,0.01841313995561207,0.8507618129218901,0.019150370199574076,0.8476827257739513,0.01936540438175545 +flat_mae,patch,logistic,adhd200_dx,58,0.046415888336127774,test,0.5846153846153846,0.05479449719704455,0.5699583435432491,0.05721045170482132,0.5699806949806949,0.055808148043572 +flat_mae,patch,logistic,adhd200_dx,59,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adhd200_dx,59,2.782559402207126,test,0.5692307692307692,0.05556186168022793,0.5289855072463768,0.062387635441507175,0.5390926640926641,0.05656945741286113 +flat_mae,patch,logistic,adhd200_dx,60,0.005994842503189409,train,0.7534246575342466,0.022456679758001287,0.7448266219239373,0.023586560442323334,0.7420925688465531,0.023311512406848298 +flat_mae,patch,logistic,adhd200_dx,60,0.005994842503189409,test,0.6,0.05818131219521778,0.5775,0.062272079434694205,0.5791505791505791,0.059406515337974544 +flat_mae,patch,logistic,adhd200_dx,61,0.005994842503189409,train,0.7534246575342466,0.021721825156316835,0.7442863370282725,0.02277524235401024,0.7413750992245222,0.022494395884089864 +flat_mae,patch,logistic,adhd200_dx,61,0.005994842503189409,test,0.5846153846153846,0.05665432607243593,0.5578231292517006,0.0621406463430457,0.5612934362934363,0.05843341364415035 +flat_mae,patch,logistic,adhd200_dx,62,10000.0,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adhd200_dx,62,10000.0,test,0.5538461538461539,0.06191420672255149,0.5500119360229172,0.06248120593350501,0.5516409266409266,0.06321496776085886 +flat_mae,patch,logistic,adhd200_dx,63,0.005994842503189409,train,0.7232876712328767,0.02317489469322426,0.7127216052990454,0.024615555993313623,0.7103712523661232,0.024201191366155415 +flat_mae,patch,logistic,adhd200_dx,63,0.005994842503189409,test,0.5538461538461539,0.057937889616851236,0.5381034060279344,0.059581648762028275,0.5386100386100386,0.05851584255309347 +flat_mae,patch,logistic,adhd200_dx,64,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adhd200_dx,64,2.782559402207126,test,0.6923076923076923,0.06025959620600891,0.6862934362934363,0.06150886836680993,0.6862934362934363,0.06100860447810967 +flat_mae,patch,logistic,adhd200_dx,65,0.005994842503189409,train,0.7479452054794521,0.021594592151932258,0.7355572355572355,0.02340227694977858,0.7322159125602979,0.022825806413733725 +flat_mae,patch,logistic,adhd200_dx,65,0.005994842503189409,test,0.7230769230769231,0.05117140473664851,0.7075,0.056513102156284994,0.7046332046332047,0.05419921985586143 +flat_mae,patch,logistic,adhd200_dx,66,0.046415888336127774,train,0.8602739726027397,0.01807805598198604,0.8563934426229508,0.018838168979697333,0.853254564328021,0.019156412398313342 +flat_mae,patch,logistic,adhd200_dx,66,0.046415888336127774,test,0.6307692307692307,0.057655627313790855,0.61,0.06187157817044672,0.6105212355212355,0.05934520514828907 +flat_mae,patch,logistic,adhd200_dx,67,0.046415888336127774,train,0.8383561643835616,0.01929770831617924,0.8335536129725385,0.02005311650459982,0.8302497404897112,0.020076113542493553 +flat_mae,patch,logistic,adhd200_dx,67,0.046415888336127774,test,0.6,0.05918560515858705,0.5775,0.06369115319574165,0.5791505791505791,0.06058576113404969 +flat_mae,patch,logistic,adhd200_dx,68,0.005994842503189409,train,0.7342465753424657,0.022928769578532515,0.721529640320589,0.024736548562318335,0.7186450509861391,0.02402961356045208 +flat_mae,patch,logistic,adhd200_dx,68,0.005994842503189409,test,0.6923076923076923,0.055182288557237294,0.675,0.059477918400765946,0.6732625482625483,0.05716239911432062 +flat_mae,patch,logistic,adhd200_dx,69,0.005994842503189409,train,0.7589041095890411,0.021583883675744132,0.7488584474885844,0.023232240827453402,0.7455119985345301,0.022884303608744137 +flat_mae,patch,logistic,adhd200_dx,69,0.005994842503189409,test,0.5538461538461539,0.05794293050292047,0.5250692869740489,0.06261451695577648,0.5299227799227799,0.05887594527789214 +flat_mae,patch,logistic,adhd200_dx,70,0.005994842503189409,train,0.7561643835616438,0.021919451993155304,0.7444962679230146,0.02378299998163452,0.740932405202418,0.023198013271920854 +flat_mae,patch,logistic,adhd200_dx,70,0.005994842503189409,test,0.49230769230769234,0.0639237711709037,0.48000000000000004,0.06532148638837941,0.48021235521235517,0.06466496102680125 +flat_mae,patch,logistic,adhd200_dx,71,0.005994842503189409,train,0.7671232876712328,0.02141274166760063,0.7571409560935898,0.022817379576101485,0.7535110215546192,0.022396257084871033 +flat_mae,patch,logistic,adhd200_dx,71,0.005994842503189409,test,0.6307692307692307,0.05732148311092014,0.6153846153846154,0.060692305596239206,0.6148648648648649,0.0588607803237783 +flat_mae,patch,logistic,adhd200_dx,72,0.005994842503189409,train,0.7479452054794521,0.021650482072955515,0.7374429223744292,0.022862004819454457,0.7343683214263906,0.022378714241088598 +flat_mae,patch,logistic,adhd200_dx,72,0.005994842503189409,test,0.6615384615384615,0.05483497350712068,0.6425000000000001,0.059452645008084705,0.6418918918918919,0.056733511149926336 +flat_mae,patch,logistic,adhd200_dx,73,0.000774263682681127,train,0.6575342465753424,0.02385645444036064,0.6374047318185792,0.025900345939447462,0.6377694327410393,0.024640321291981328 +flat_mae,patch,logistic,adhd200_dx,73,0.000774263682681127,test,0.5538461538461539,0.059897276957990735,0.5250692869740489,0.06414704740854286,0.5299227799227799,0.06086955378085957 +flat_mae,patch,logistic,adhd200_dx,74,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adhd200_dx,74,21.54434690031882,test,0.7230769230769231,0.05524687144747409,0.7224857685009488,0.055395714461646074,0.7306949806949807,0.054553624140121104 +flat_mae,patch,logistic,adhd200_dx,75,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adhd200_dx,75,1291.5496650148827,test,0.5692307692307692,0.061326681742053545,0.5565302144249512,0.06331632661994378,0.5564671814671815,0.062285597511000615 +flat_mae,patch,logistic,adhd200_dx,76,0.000774263682681127,train,0.673972602739726,0.022777902266796574,0.6528671328671329,0.025034045670298332,0.6530500091591867,0.02361705530952506 +flat_mae,patch,logistic,adhd200_dx,76,0.000774263682681127,test,0.5384615384615384,0.05493922624028897,0.4724025974025974,0.0630451519873556,0.49903474903474904,0.05525579571279835 +flat_mae,patch,logistic,adhd200_dx,77,0.005994842503189409,train,0.736986301369863,0.021829204469272487,0.7233625971073075,0.02363225146639447,0.7203547658301276,0.022905766916795262 +flat_mae,patch,logistic,adhd200_dx,77,0.005994842503189409,test,0.7230769230769231,0.051832876638208264,0.7027439024390244,0.05890765487744529,0.7002895752895753,0.055001084126403185 +flat_mae,patch,logistic,adhd200_dx,78,0.046415888336127774,train,0.8493150684931506,0.018937743357520815,0.8459431044670744,0.01948768015746212,0.8442632960859743,0.0196925925906454 +flat_mae,patch,logistic,adhd200_dx,78,0.046415888336127774,test,0.5230769230769231,0.06067001833080615,0.5062484685126194,0.06295391959185964,0.5072393822393823,0.06156683084501543 +flat_mae,patch,logistic,adhd200_dx,79,0.005994842503189409,train,0.7506849315068493,0.022441834242958023,0.7417205153925708,0.023665172500151252,0.7389479147585027,0.02331827801186852 +flat_mae,patch,logistic,adhd200_dx,79,0.005994842503189409,test,0.5846153846153846,0.06254962337708665,0.5699583435432491,0.06531406559900069,0.5699806949806949,0.06359271483710695 +flat_mae,patch,logistic,adhd200_dx,80,0.005994842503189409,train,0.7589041095890411,0.02139784890355525,0.7470547470547471,0.023271381673384276,0.7433595896684374,0.022666833370857026 +flat_mae,patch,logistic,adhd200_dx,80,0.005994842503189409,test,0.6307692307692307,0.059856040314492716,0.6153846153846154,0.06350546885782166,0.6148648648648649,0.06188099265117248 +flat_mae,patch,logistic,adhd200_dx,81,0.005994842503189409,train,0.7671232876712328,0.021454287747464027,0.7592516431414847,0.022567644671337806,0.7563809000427428,0.022391940105320113 +flat_mae,patch,logistic,adhd200_dx,81,0.005994842503189409,test,0.5538461538461539,0.05473647248515695,0.5167905665214048,0.06071187430879749,0.5255791505791506,0.05590097891335469 +flat_mae,patch,logistic,adhd200_dx,82,0.005994842503189409,train,0.7479452054794521,0.02197716551538946,0.7380328278100231,0.023265560153518435,0.7350857910484215,0.02287260072024844 +flat_mae,patch,logistic,adhd200_dx,82,0.005994842503189409,test,0.6923076923076923,0.05516953108159715,0.6832358674463938,0.057369541368321154,0.6819498069498069,0.05670585801808207 +flat_mae,patch,logistic,adhd200_dx,83,0.3593813663804626,train,0.9506849315068493,0.010726069035416647,0.9496227456753772,0.011019539683970759,0.9477010441472797,0.01146572490722017 +flat_mae,patch,logistic,adhd200_dx,83,0.3593813663804626,test,0.6307692307692307,0.061060443426815124,0.6285714285714286,0.06119592900405957,0.6322393822393823,0.061228986302112855 +flat_mae,patch,logistic,adhd200_dx,84,0.3593813663804626,train,0.947945205479452,0.011934447839101922,0.9469497035762096,0.012182244531482488,0.9459913293032912,0.012331849396840264 +flat_mae,patch,logistic,adhd200_dx,84,0.3593813663804626,test,0.5538461538461539,0.06468435147269999,0.5521501544309813,0.06471381272427208,0.555984555984556,0.06531969207936207 +flat_mae,patch,logistic,adhd200_dx,85,0.046415888336127774,train,0.8657534246575342,0.017746147671472444,0.8620250723240116,0.018459160884451795,0.8588264028820908,0.01865239881737196 +flat_mae,patch,logistic,adhd200_dx,85,0.046415888336127774,test,0.6153846153846154,0.05790811738583458,0.606060606060606,0.059363698183782225,0.6056949806949807,0.058823990535532444 +flat_mae,patch,logistic,adhd200_dx,86,0.046415888336127774,train,0.8383561643835616,0.018832981135696408,0.8344594854292062,0.019504615624006866,0.8324021493558039,0.019730490751554797 +flat_mae,patch,logistic,adhd200_dx,86,0.046415888336127774,test,0.5538461538461539,0.06316391749545607,0.5381034060279344,0.06497776384112605,0.5386100386100386,0.063765505113444 +flat_mae,patch,logistic,adhd200_dx,87,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adhd200_dx,87,2.782559402207126,test,0.5538461538461539,0.05847753627266379,0.5469838981014179,0.059055507331949406,0.5472972972972974,0.05914186960026333 +flat_mae,patch,logistic,adhd200_dx,88,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adhd200_dx,88,21.54434690031882,test,0.5384615384615384,0.06105490011786414,0.5294401544401545,0.06186238384219358,0.5294401544401545,0.0617685525419156 +flat_mae,patch,logistic,adhd200_dx,89,0.3593813663804626,train,0.9698630136986301,0.008804038719072942,0.9692866704914898,0.008995556403155237,0.9682786835195701,0.00932568112642278 +flat_mae,patch,logistic,adhd200_dx,89,0.3593813663804626,test,0.5384615384615384,0.06060631716639259,0.5248538011695907,0.06178603892504408,0.525096525096525,0.060820418098722184 +flat_mae,patch,logistic,adhd200_dx,90,0.005994842503189409,train,0.726027397260274,0.02221595774173231,0.7139498432601881,0.023780630723511362,0.7113634975880808,0.023203339720484262 +flat_mae,patch,logistic,adhd200_dx,90,0.005994842503189409,test,0.6615384615384615,0.05743792945123432,0.6425000000000001,0.061997243137507624,0.6418918918918919,0.059202872228064016 +flat_mae,patch,logistic,adhd200_dx,91,0.3593813663804626,train,0.9671232876712329,0.009241434999402913,0.9664151637835848,0.009497812180410433,0.9644165598094889,0.010086992789978702 +flat_mae,patch,logistic,adhd200_dx,91,0.3593813663804626,test,0.5538461538461539,0.05796733624211067,0.5321419707123356,0.06053475090798652,0.5342664092664092,0.05828460953733042 +flat_mae,patch,logistic,adhd200_dx,92,0.005994842503189409,train,0.7534246575342466,0.021324300567854514,0.7419400452488687,0.022861585664236583,0.7385052207363986,0.022301365446527353 +flat_mae,patch,logistic,adhd200_dx,92,0.005994842503189409,test,0.6923076923076923,0.05356430852656453,0.675,0.05811804293692449,0.6732625482625483,0.05570285353341586 +flat_mae,patch,logistic,adhd200_dx,93,10000.0,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adhd200_dx,93,10000.0,test,0.5846153846153846,0.060289604822922345,0.5745454545454545,0.061809092379268724,0.5743243243243243,0.061129110668559 +flat_mae,patch,logistic,adhd200_dx,94,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adhd200_dx,94,1291.5496650148827,test,0.6,0.057146960968445154,0.570630081300813,0.0638250006466593,0.5748069498069498,0.05932919356118807 +flat_mae,patch,logistic,adhd200_dx,95,0.000774263682681127,train,0.7041095890410959,0.023624811788293176,0.6944186046511628,0.024780311035836628,0.6926634914819564,0.0244599646095452 +flat_mae,patch,logistic,adhd200_dx,95,0.000774263682681127,test,0.5076923076923077,0.05654259534861656,0.4715447154471545,0.060685245882338486,0.4806949806949807,0.056977860204927816 +flat_mae,patch,logistic,adhd200_dx,96,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adhd200_dx,96,1291.5496650148827,test,0.6461538461538462,0.06014055332174917,0.644808743169399,0.06034844882932229,0.6500965250965252,0.060694850398241074 +flat_mae,patch,logistic,adhd200_dx,97,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adhd200_dx,97,166.81005372000556,test,0.5538461538461539,0.05825765256891352,0.5250692869740489,0.062381577150225236,0.5299227799227799,0.0591165434664109 +flat_mae,patch,logistic,adhd200_dx,98,0.005994842503189409,train,0.7397260273972602,0.021801512701859073,0.7244275961821202,0.023994095515763578,0.7213470110520852,0.023058055841377954 +flat_mae,patch,logistic,adhd200_dx,98,0.005994842503189409,test,0.6307692307692307,0.05700949780726617,0.6036585365853658,0.0616899636051404,0.6061776061776062,0.05804311835992884 +flat_mae,patch,logistic,adhd200_dx,99,0.005994842503189409,train,0.7561643835616438,0.023216900684369515,0.7468536917981687,0.024498813636914186,0.7438022836905416,0.024119479599167413 +flat_mae,patch,logistic,adhd200_dx,99,0.005994842503189409,test,0.5384615384615384,0.05510957347646047,0.5045731707317074,0.06025028223656772,0.5120656370656371,0.05603453480755257 +flat_mae,patch,logistic,adhd200_dx,100,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adhd200_dx,100,166.81005372000556,test,0.7076923076923077,0.05448844185566319,0.7031963470319634,0.05563526911157872,0.7041505791505791,0.05570034703107281 diff --git a/input_space_v3/flat_lr1e-3_7/eval_v2/adhd200_dx__patch__logistic/log.txt b/input_space_v3/flat_lr1e-3_7/eval_v2/adhd200_dx__patch__logistic/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..051be3f540406225a0b414726522c3d80bce2977 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_7/eval_v2/adhd200_dx__patch__logistic/log.txt @@ -0,0 +1,241 @@ +fMRI foundation model logistic probe eval +version: 0.1.dev86+gf97f52698 +sha: bcce2b486277d3a5b520775efd9cdf1a2affce36, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-04-08 22:54:39 +config: +output_root: experiments/input_space_v3/output +name_prefix: eval_logistic +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_7; eval v2 (adhd200_dx patch logistic) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_7/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: input_space_v3/flat_lr1e-3_7/eval_v2/adhd200_dx__patch__logistic +model: flat_mae +representation: patch +dataset: adhd200_dx +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_7/eval_v2/adhd200_dx__patch__logistic +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=True, reg_tokens=0, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: adhd200_dx (flat) +train (n=301): +HFDataset( + dataset=Dataset({ + features: ['sub', 'site', 'gender', 'dx', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 301 +}), + labels=['ADHD' 'Control'], + counts=[131 170] +) + +validation (n=64): +HFDataset( + dataset=Dataset({ + features: ['sub', 'site', 'gender', 'dx', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 64 +}), + labels=['ADHD' 'Control'], + counts=[28 36] +) + +test (n=65): +HFDataset( + dataset=Dataset({ + features: ['sub', 'site', 'gender', 'dx', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 65 +}), + labels=['ADHD' 'Control'], + counts=[28 37] +) + +extracting features for all splits +extract (train) [ 0/151] eta: 0:12:30 time: 4.9708 data: 3.9069 max mem: 2698 +extract (train) [ 20/151] eta: 0:00:54 time: 0.1897 data: 0.0659 max mem: 2851 +extract (train) [ 40/151] eta: 0:00:34 time: 0.1931 data: 0.0674 max mem: 2851 +extract (train) [ 60/151] eta: 0:00:24 time: 0.1816 data: 0.0594 max mem: 2851 +extract (train) [ 80/151] eta: 0:00:17 time: 0.1632 data: 0.0543 max mem: 2851 +extract (train) [100/151] eta: 0:00:11 time: 0.1608 data: 0.0512 max mem: 2851 +extract (train) [120/151] eta: 0:00:06 time: 0.1695 data: 0.0560 max mem: 2851 +extract (train) [140/151] eta: 0:00:02 time: 0.1506 data: 0.0473 max mem: 2851 +extract (train) [150/151] eta: 0:00:00 time: 0.1461 data: 0.0449 max mem: 2851 +extract (train) Total time: 0:00:31 (0.2054 s / it) +extract (validation) [ 0/32] eta: 0:02:16 time: 4.2771 data: 4.0465 max mem: 2851 +extract (validation) [20/32] eta: 0:00:04 time: 0.1717 data: 0.0554 max mem: 2851 +extract (validation) [31/32] eta: 0:00:00 time: 0.1475 data: 0.0429 max mem: 2851 +extract (validation) Total time: 0:00:09 (0.3022 s / it) +extract (test) [ 0/33] eta: 0:02:00 time: 3.6642 data: 3.5179 max mem: 2851 +extract (test) [20/33] eta: 0:00:04 time: 0.2052 data: 0.0703 max mem: 2851 +extract (test) [32/33] eta: 0:00:00 time: 0.1536 data: 0.0486 max mem: 2851 +extract (test) Total time: 0:00:09 (0.2991 s / it) +feature extraction time: 0:00:50 +train features: (301, 768) +validation features: (64, 768) +test features: (65, 768) +evaluating fixed splits +eval results (fixed splits): + +| model | repr | clf | dataset | trial | C | split | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:-----------|:--------|----------:|:--------|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | adhd200_dx | | 0.0059948 | train | 0.74795 | 0.022066 | 0.73803 | 0.023351 | 0.73509 | 0.022939 | +| flat_mae | patch | logistic | adhd200_dx | | 0.0059948 | test | 0.58462 | 0.058183 | 0.56441 | 0.061745 | 0.56564 | 0.05959 | + + +evaluating random splits (n=100) +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 1, "C": 0.000774263682681127, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.058508572173242096, "f1": 0.5745454545454545, "f1_std": 0.059559239662815906, "bacc": 0.5743243243243243, "bacc_std": 0.05908672889653841} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 2, "C": 0.046415888336127774, "split": "test", "acc": 0.6615384615384615, "acc_std": 0.058877065787449404, "f1": 0.6474358974358974, "f1_std": 0.06253449641072095, "bacc": 0.6462355212355213, "bacc_std": 0.06081569542801764} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 3, "C": 0.005994842503189409, "split": "test", "acc": 0.5538461538461539, "acc_std": 0.05878017618573489, "f1": 0.5381034060279344, "f1_std": 0.06096199179989891, "bacc": 0.5386100386100386, "bacc_std": 0.05965147950373145} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 4, "C": 0.005994842503189409, "split": "test", "acc": 0.6461538461538462, "acc_std": 0.0583204775915705, "f1": 0.6375757575757576, "f1_std": 0.0603310539016322, "bacc": 0.6370656370656371, "bacc_std": 0.059808325507432335} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 5, "C": 0.005994842503189409, "split": "test", "acc": 0.5230769230769231, "acc_std": 0.0613013586150204, "f1": 0.521263958184842, "f1_std": 0.06153219271243599, "bacc": 0.5246138996138996, "bacc_std": 0.062738070424093} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 6, "C": 0.005994842503189409, "split": "test", "acc": 0.6461538461538462, "acc_std": 0.05900120147207114, "f1": 0.6336682185738789, "f1_std": 0.061745579571214494, "bacc": 0.6327220077220077, "bacc_std": 0.06043469667809714} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 7, "C": 0.005994842503189409, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.05393487196796878, "f1": 0.61, "f1_std": 0.05845980488311445, "bacc": 0.6105212355212355, "bacc_std": 0.05572080973148829} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 8, "C": 0.005994842503189409, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.06281997194952928, "f1": 0.5745454545454545, "f1_std": 0.0641655179436087, "bacc": 0.5743243243243243, "bacc_std": 0.0635279974551339} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 9, "C": 166.81005372000556, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.06097852177892799, "f1": 0.6018132810585641, "f1_std": 0.06318782395323387, "bacc": 0.6013513513513513, "bacc_std": 0.06202078754336078} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 10, "C": 1291.5496650148827, "split": "test", "acc": 0.5230769230769231, "acc_std": 0.060106249121301455, "f1": 0.5189782764382908, "f1_std": 0.06067123430248141, "bacc": 0.5202702702702703, "bacc_std": 0.06093768360811646} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 11, "C": 0.3593813663804626, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.06444280983666813, "f1": 0.5810455956075435, "f1_std": 0.06461267577072316, "bacc": 0.583011583011583, "bacc_std": 0.06466372751688623} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 12, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.059058362468957716, "f1": 0.5833333333333333, "f1_std": 0.06341228641480415, "bacc": 0.5834942084942085, "bacc_std": 0.06123791015463164} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 13, "C": 0.3593813663804626, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.05975802092680745, "f1": 0.6264367816091954, "f1_std": 0.06019509140741275, "bacc": 0.627895752895753, "bacc_std": 0.060133979882865105} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 14, "C": 2.782559402207126, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.060918811039460855, "f1": 0.5608108108108107, "f1_std": 0.06184970262461596, "bacc": 0.5608108108108107, "bacc_std": 0.06137846273987037} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 15, "C": 0.005994842503189409, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.060385906894566806, "f1": 0.6139225469232596, "f1_std": 0.06052147780024308, "bacc": 0.6187258687258688, "bacc_std": 0.06091748485159736} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 16, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.061658344766056944, "f1": 0.5921814671814671, "f1_std": 0.06290553334245476, "bacc": 0.5921814671814671, "bacc_std": 0.06265752293344619} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 17, "C": 0.005994842503189409, "split": "test", "acc": 0.5538461538461539, "acc_std": 0.060382457580260444, "f1": 0.5250692869740489, "f1_std": 0.06511141569568044, "bacc": 0.5299227799227799, "bacc_std": 0.06163298616186977} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 18, "C": 0.005994842503189409, "split": "test", "acc": 0.6615384615384615, "acc_std": 0.05784676759085213, "f1": 0.6549227799227799, "f1_std": 0.05917152385134325, "bacc": 0.6549227799227799, "bacc_std": 0.058897760278548546} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 19, "C": 0.3593813663804626, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.0612143464640255, "f1": 0.6264367816091954, "f1_std": 0.0620498973594574, "bacc": 0.627895752895753, "bacc_std": 0.06234864349133447} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 20, "C": 1291.5496650148827, "split": "test", "acc": 0.6615384615384615, "acc_std": 0.05798571544153157, "f1": 0.6575670498084292, "f1_std": 0.05866936922344173, "bacc": 0.6592664092664093, "bacc_std": 0.058859692605672545} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 21, "C": 0.005994842503189409, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.05983570405109261, "f1": 0.6139225469232596, "f1_std": 0.05992020712091062, "bacc": 0.6187258687258688, "bacc_std": 0.06008656307777196} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 22, "C": 0.000774263682681127, "split": "test", "acc": 0.6, "acc_std": 0.05769732080783619, "f1": 0.5833333333333333, "f1_std": 0.06102026586332118, "bacc": 0.5834942084942085, "bacc_std": 0.05906065137625694} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 23, "C": 0.000774263682681127, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.044717538224415605, "f1": 0.5421245421245421, "f1_std": 0.0608812025259523, "bacc": 0.5709459459459459, "bacc_std": 0.047272133750143476} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 24, "C": 0.046415888336127774, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.056265566419410024, "f1": 0.5834401435529352, "f1_std": 0.06314718495088413, "bacc": 0.5883204633204633, "bacc_std": 0.058091804175098086} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 25, "C": 21.54434690031882, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.05931250304743073, "f1": 0.6150201374081972, "f1_std": 0.05956283721888513, "bacc": 0.6230694980694981, "bacc_std": 0.05965041274069326} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 26, "C": 0.005994842503189409, "split": "test", "acc": 0.6461538461538462, "acc_std": 0.05828848069943598, "f1": 0.6336682185738789, "f1_std": 0.06090929214363375, "bacc": 0.6327220077220077, "bacc_std": 0.05960576765603033} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 27, "C": 0.005994842503189409, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.05841037437236237, "f1": 0.5745454545454545, "f1_std": 0.05977994398448154, "bacc": 0.5743243243243243, "bacc_std": 0.05914803254539785} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 28, "C": 1291.5496650148827, "split": "test", "acc": 0.6, "acc_std": 0.056657668156629475, "f1": 0.5976190476190476, "f1_std": 0.05674189828541796, "bacc": 0.6008687258687259, "bacc_std": 0.05718574725918765} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 29, "C": 2.782559402207126, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.06257946427632971, "f1": 0.578226387887527, "f1_std": 0.06369824484111589, "bacc": 0.5786679536679536, "bacc_std": 0.06362214820051393} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 30, "C": 0.046415888336127774, "split": "test", "acc": 0.6, "acc_std": 0.0602474660028396, "f1": 0.5976190476190476, "f1_std": 0.06029496287128843, "bacc": 0.6008687258687259, "bacc_std": 0.060691925801425406} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 31, "C": 0.000774263682681127, "split": "test", "acc": 0.6, "acc_std": 0.05685143932959089, "f1": 0.570630081300813, "f1_std": 0.06356418940775081, "bacc": 0.5748069498069498, "bacc_std": 0.05906827043593876} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 32, "C": 0.3593813663804626, "split": "test", "acc": 0.6461538461538462, "acc_std": 0.06036483948586169, "f1": 0.6336682185738789, "f1_std": 0.06286716555740308, "bacc": 0.6327220077220077, "bacc_std": 0.06152948288466193} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 33, "C": 0.3593813663804626, "split": "test", "acc": 0.6, "acc_std": 0.05956861887797623, "f1": 0.599905303030303, "f1_std": 0.05981267661835293, "bacc": 0.6095559845559846, "bacc_std": 0.059827503628071176} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 34, "C": 21.54434690031882, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.06067146176077636, "f1": 0.564176245210728, "f1_std": 0.06107779904190585, "bacc": 0.5651544401544402, "bacc_std": 0.06104206390027087} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 35, "C": 0.005994842503189409, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.052107662783030854, "f1": 0.5190274841437632, "f1_std": 0.06198354830485749, "bacc": 0.5347490347490347, "bacc_std": 0.05392670119000252} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 36, "C": 0.000774263682681127, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.05776323844779074, "f1": 0.5125, "f1_std": 0.061353643975089245, "bacc": 0.5164092664092664, "bacc_std": 0.05851979956782861} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 37, "C": 0.046415888336127774, "split": "test", "acc": 0.6, "acc_std": 0.06206765539436661, "f1": 0.5921814671814671, "f1_std": 0.06294332776214984, "bacc": 0.5921814671814671, "bacc_std": 0.06249545485180194} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 38, "C": 0.046415888336127774, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.05783642307680798, "f1": 0.5966741126830479, "f1_std": 0.06169667580979903, "bacc": 0.597007722007722, "bacc_std": 0.05938063473281416} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 39, "C": 0.046415888336127774, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.06184271708782477, "f1": 0.5565302144249512, "f1_std": 0.06353303523517123, "bacc": 0.5564671814671815, "bacc_std": 0.06275183531452173} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 40, "C": 0.046415888336127774, "split": "test", "acc": 0.6461538461538462, "acc_std": 0.05796988404008845, "f1": 0.6289401836684041, "f1_std": 0.06165378151424982, "bacc": 0.6283783783783784, "bacc_std": 0.05958077871028071} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 41, "C": 0.005994842503189409, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.06036552172405828, "f1": 0.6094688776736361, "f1_std": 0.061236630805570756, "bacc": 0.61003861003861, "bacc_std": 0.061002699484323734} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 42, "C": 0.005994842503189409, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.06113668070651736, "f1": 0.6264367816091954, "f1_std": 0.06156334856267409, "bacc": 0.627895752895753, "bacc_std": 0.06165253588740631} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 43, "C": 0.046415888336127774, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.05962327491208952, "f1": 0.5745454545454545, "f1_std": 0.06136943112074644, "bacc": 0.5743243243243243, "bacc_std": 0.06074551424780151} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 44, "C": 0.046415888336127774, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.060891017205589204, "f1": 0.5565302144249512, "f1_std": 0.06315427138569375, "bacc": 0.5564671814671815, "bacc_std": 0.06217624288952483} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 45, "C": 0.005994842503189409, "split": "test", "acc": 0.5076923076923077, "acc_std": 0.05728046642896272, "f1": 0.4715447154471545, "f1_std": 0.06060042783426683, "bacc": 0.4806949806949807, "bacc_std": 0.05726067903861227} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 46, "C": 166.81005372000556, "split": "test", "acc": 0.6461538461538462, "acc_std": 0.05769538453333772, "f1": 0.6407113674597452, "f1_std": 0.05877208329477423, "bacc": 0.6414092664092663, "bacc_std": 0.05865578092871612} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 47, "C": 1291.5496650148827, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.061087578996816584, "f1": 0.5192307692307693, "f1_std": 0.06335557495330009, "bacc": 0.5207528957528957, "bacc_std": 0.061679006914601556} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 48, "C": 0.046415888336127774, "split": "test", "acc": 0.7230769230769231, "acc_std": 0.05632618443720858, "f1": 0.7198275862068966, "f1_std": 0.0567970638098207, "bacc": 0.722007722007722, "bacc_std": 0.056812539326016535} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 49, "C": 0.3593813663804626, "split": "test", "acc": 0.47692307692307695, "acc_std": 0.06220397064896292, "f1": 0.47580645161290325, "f1_std": 0.06254693041139935, "bacc": 0.4797297297297297, "bacc_std": 0.06321884270191114} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 50, "C": 0.3593813663804626, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.05886226224976206, "f1": 0.5810455956075435, "f1_std": 0.0591605557423051, "bacc": 0.583011583011583, "bacc_std": 0.059339167041078555} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 51, "C": 0.000774263682681127, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.06087485270871456, "f1": 0.5512820512820513, "f1_std": 0.06426777350539033, "bacc": 0.5521235521235521, "bacc_std": 0.06222744176440095} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 52, "C": 0.005994842503189409, "split": "test", "acc": 0.6923076923076923, "acc_std": 0.051633152965968494, "f1": 0.6697154471544715, "f1_std": 0.05752579218296702, "bacc": 0.6689189189189189, "bacc_std": 0.05427822977947073} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 53, "C": 0.005994842503189409, "split": "test", "acc": 0.6461538461538462, "acc_std": 0.05262758293145431, "f1": 0.6167649320687003, "f1_std": 0.06003187431643137, "bacc": 0.6196911196911197, "bacc_std": 0.05503548552971564} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 54, "C": 0.000774263682681127, "split": "test", "acc": 0.49230769230769234, "acc_std": 0.06313321315718293, "f1": 0.4844989185291997, "f1_std": 0.06376110094553114, "bacc": 0.4845559845559846, "bacc_std": 0.06364553156850539} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 55, "C": 0.046415888336127774, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.06002346681130087, "f1": 0.5248538011695907, "f1_std": 0.06173858287582608, "bacc": 0.525096525096525, "bacc_std": 0.06102152925804111} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 56, "C": 0.046415888336127774, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.05941310595957187, "f1": 0.6264367816091954, "f1_std": 0.0598962618215414, "bacc": 0.627895752895753, "bacc_std": 0.05992297629225627} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 57, "C": 0.046415888336127774, "split": "test", "acc": 0.5538461538461539, "acc_std": 0.06325510293515677, "f1": 0.543030303030303, "f1_std": 0.06481187633172976, "bacc": 0.542953667953668, "bacc_std": 0.06420147004184837} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 58, "C": 0.046415888336127774, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.05479449719704455, "f1": 0.5699583435432491, "f1_std": 0.05721045170482132, "bacc": 0.5699806949806949, "bacc_std": 0.055808148043572} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 59, "C": 2.782559402207126, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.05556186168022793, "f1": 0.5289855072463768, "f1_std": 0.062387635441507175, "bacc": 0.5390926640926641, "bacc_std": 0.05656945741286113} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 60, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.05818131219521778, "f1": 0.5775, "f1_std": 0.062272079434694205, "bacc": 0.5791505791505791, "bacc_std": 0.059406515337974544} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 61, "C": 0.005994842503189409, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.05665432607243593, "f1": 0.5578231292517006, "f1_std": 0.0621406463430457, "bacc": 0.5612934362934363, "bacc_std": 0.05843341364415035} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 62, "C": 10000.0, "split": "test", "acc": 0.5538461538461539, "acc_std": 0.06191420672255149, "f1": 0.5500119360229172, "f1_std": 0.06248120593350501, "bacc": 0.5516409266409266, "bacc_std": 0.06321496776085886} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 63, "C": 0.005994842503189409, "split": "test", "acc": 0.5538461538461539, "acc_std": 0.057937889616851236, "f1": 0.5381034060279344, "f1_std": 0.059581648762028275, "bacc": 0.5386100386100386, "bacc_std": 0.05851584255309347} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 64, "C": 2.782559402207126, "split": "test", "acc": 0.6923076923076923, "acc_std": 0.06025959620600891, "f1": 0.6862934362934363, "f1_std": 0.06150886836680993, "bacc": 0.6862934362934363, "bacc_std": 0.06100860447810967} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 65, "C": 0.005994842503189409, "split": "test", "acc": 0.7230769230769231, "acc_std": 0.05117140473664851, "f1": 0.7075, "f1_std": 0.056513102156284994, "bacc": 0.7046332046332047, "bacc_std": 0.05419921985586143} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 66, "C": 0.046415888336127774, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.057655627313790855, "f1": 0.61, "f1_std": 0.06187157817044672, "bacc": 0.6105212355212355, "bacc_std": 0.05934520514828907} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 67, "C": 0.046415888336127774, "split": "test", "acc": 0.6, "acc_std": 0.05918560515858705, "f1": 0.5775, "f1_std": 0.06369115319574165, "bacc": 0.5791505791505791, "bacc_std": 0.06058576113404969} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 68, "C": 0.005994842503189409, "split": "test", "acc": 0.6923076923076923, "acc_std": 0.055182288557237294, "f1": 0.675, "f1_std": 0.059477918400765946, "bacc": 0.6732625482625483, "bacc_std": 0.05716239911432062} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 69, "C": 0.005994842503189409, "split": "test", "acc": 0.5538461538461539, "acc_std": 0.05794293050292047, "f1": 0.5250692869740489, "f1_std": 0.06261451695577648, "bacc": 0.5299227799227799, "bacc_std": 0.05887594527789214} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 70, "C": 0.005994842503189409, "split": "test", "acc": 0.49230769230769234, "acc_std": 0.0639237711709037, "f1": 0.48000000000000004, "f1_std": 0.06532148638837941, "bacc": 0.48021235521235517, "bacc_std": 0.06466496102680125} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 71, "C": 0.005994842503189409, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.05732148311092014, "f1": 0.6153846153846154, "f1_std": 0.060692305596239206, "bacc": 0.6148648648648649, "bacc_std": 0.0588607803237783} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 72, "C": 0.005994842503189409, "split": "test", "acc": 0.6615384615384615, "acc_std": 0.05483497350712068, "f1": 0.6425000000000001, "f1_std": 0.059452645008084705, "bacc": 0.6418918918918919, "bacc_std": 0.056733511149926336} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 73, "C": 0.000774263682681127, "split": "test", "acc": 0.5538461538461539, "acc_std": 0.059897276957990735, "f1": 0.5250692869740489, "f1_std": 0.06414704740854286, "bacc": 0.5299227799227799, "bacc_std": 0.06086955378085957} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 74, "C": 21.54434690031882, "split": "test", "acc": 0.7230769230769231, "acc_std": 0.05524687144747409, "f1": 0.7224857685009488, "f1_std": 0.055395714461646074, "bacc": 0.7306949806949807, "bacc_std": 0.054553624140121104} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 75, "C": 1291.5496650148827, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.061326681742053545, "f1": 0.5565302144249512, "f1_std": 0.06331632661994378, "bacc": 0.5564671814671815, "bacc_std": 0.062285597511000615} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 76, "C": 0.000774263682681127, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.05493922624028897, "f1": 0.4724025974025974, "f1_std": 0.0630451519873556, "bacc": 0.49903474903474904, "bacc_std": 0.05525579571279835} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 77, "C": 0.005994842503189409, "split": "test", "acc": 0.7230769230769231, "acc_std": 0.051832876638208264, "f1": 0.7027439024390244, "f1_std": 0.05890765487744529, "bacc": 0.7002895752895753, "bacc_std": 0.055001084126403185} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 78, "C": 0.046415888336127774, "split": "test", "acc": 0.5230769230769231, "acc_std": 0.06067001833080615, "f1": 0.5062484685126194, "f1_std": 0.06295391959185964, "bacc": 0.5072393822393823, "bacc_std": 0.06156683084501543} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 79, "C": 0.005994842503189409, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.06254962337708665, "f1": 0.5699583435432491, "f1_std": 0.06531406559900069, "bacc": 0.5699806949806949, "bacc_std": 0.06359271483710695} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 80, "C": 0.005994842503189409, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.059856040314492716, "f1": 0.6153846153846154, "f1_std": 0.06350546885782166, "bacc": 0.6148648648648649, "bacc_std": 0.06188099265117248} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 81, "C": 0.005994842503189409, "split": "test", "acc": 0.5538461538461539, "acc_std": 0.05473647248515695, "f1": 0.5167905665214048, "f1_std": 0.06071187430879749, "bacc": 0.5255791505791506, "bacc_std": 0.05590097891335469} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 82, "C": 0.005994842503189409, "split": "test", "acc": 0.6923076923076923, "acc_std": 0.05516953108159715, "f1": 0.6832358674463938, "f1_std": 0.057369541368321154, "bacc": 0.6819498069498069, "bacc_std": 0.05670585801808207} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 83, "C": 0.3593813663804626, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.061060443426815124, "f1": 0.6285714285714286, "f1_std": 0.06119592900405957, "bacc": 0.6322393822393823, "bacc_std": 0.061228986302112855} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 84, "C": 0.3593813663804626, "split": "test", "acc": 0.5538461538461539, "acc_std": 0.06468435147269999, "f1": 0.5521501544309813, "f1_std": 0.06471381272427208, "bacc": 0.555984555984556, "bacc_std": 0.06531969207936207} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 85, "C": 0.046415888336127774, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.05790811738583458, "f1": 0.606060606060606, "f1_std": 0.059363698183782225, "bacc": 0.6056949806949807, "bacc_std": 0.058823990535532444} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 86, "C": 0.046415888336127774, "split": "test", "acc": 0.5538461538461539, "acc_std": 0.06316391749545607, "f1": 0.5381034060279344, "f1_std": 0.06497776384112605, "bacc": 0.5386100386100386, "bacc_std": 0.063765505113444} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 87, "C": 2.782559402207126, "split": "test", "acc": 0.5538461538461539, "acc_std": 0.05847753627266379, "f1": 0.5469838981014179, "f1_std": 0.059055507331949406, "bacc": 0.5472972972972974, "bacc_std": 0.05914186960026333} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 88, "C": 21.54434690031882, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.06105490011786414, "f1": 0.5294401544401545, "f1_std": 0.06186238384219358, "bacc": 0.5294401544401545, "bacc_std": 0.0617685525419156} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 89, "C": 0.3593813663804626, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.06060631716639259, "f1": 0.5248538011695907, "f1_std": 0.06178603892504408, "bacc": 0.525096525096525, "bacc_std": 0.060820418098722184} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 90, "C": 0.005994842503189409, "split": "test", "acc": 0.6615384615384615, "acc_std": 0.05743792945123432, "f1": 0.6425000000000001, "f1_std": 0.061997243137507624, "bacc": 0.6418918918918919, "bacc_std": 0.059202872228064016} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 91, "C": 0.3593813663804626, "split": "test", "acc": 0.5538461538461539, "acc_std": 0.05796733624211067, "f1": 0.5321419707123356, "f1_std": 0.06053475090798652, "bacc": 0.5342664092664092, "bacc_std": 0.05828460953733042} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 92, "C": 0.005994842503189409, "split": "test", "acc": 0.6923076923076923, "acc_std": 0.05356430852656453, "f1": 0.675, "f1_std": 0.05811804293692449, "bacc": 0.6732625482625483, "bacc_std": 0.05570285353341586} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 93, "C": 10000.0, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.060289604822922345, "f1": 0.5745454545454545, "f1_std": 0.061809092379268724, "bacc": 0.5743243243243243, "bacc_std": 0.061129110668559} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 94, "C": 1291.5496650148827, "split": "test", "acc": 0.6, "acc_std": 0.057146960968445154, "f1": 0.570630081300813, "f1_std": 0.0638250006466593, "bacc": 0.5748069498069498, "bacc_std": 0.05932919356118807} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 95, "C": 0.000774263682681127, "split": "test", "acc": 0.5076923076923077, "acc_std": 0.05654259534861656, "f1": 0.4715447154471545, "f1_std": 0.060685245882338486, "bacc": 0.4806949806949807, "bacc_std": 0.056977860204927816} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 96, "C": 1291.5496650148827, "split": "test", "acc": 0.6461538461538462, "acc_std": 0.06014055332174917, "f1": 0.644808743169399, "f1_std": 0.06034844882932229, "bacc": 0.6500965250965252, "bacc_std": 0.060694850398241074} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 97, "C": 166.81005372000556, "split": "test", "acc": 0.5538461538461539, "acc_std": 0.05825765256891352, "f1": 0.5250692869740489, "f1_std": 0.062381577150225236, "bacc": 0.5299227799227799, "bacc_std": 0.0591165434664109} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 98, "C": 0.005994842503189409, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.05700949780726617, "f1": 0.6036585365853658, "f1_std": 0.0616899636051404, "bacc": 0.6061776061776062, "bacc_std": 0.05804311835992884} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 99, "C": 0.005994842503189409, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.05510957347646047, "f1": 0.5045731707317074, "f1_std": 0.06025028223656772, "bacc": 0.5120656370656371, "bacc_std": 0.05603453480755257} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 100, "C": 166.81005372000556, "split": "test", "acc": 0.7076923076923077, "acc_std": 0.05448844185566319, "f1": 0.7031963470319634, "f1_std": 0.05563526911157872, "bacc": 0.7041505791505791, "bacc_std": 0.05570034703107281} +eval results (random splits): + +| model | repr | clf | dataset | split | n_trials | C | C_std | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:-----------|:--------|-----------:|-------:|--------:|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | adhd200_dx | train | 100 | 298.13 | 1431.6 | 0.83964 | 0.11524 | 0.83296 | 0.1209 | 0.83102 | 0.12159 | +| flat_mae | patch | logistic | adhd200_dx | test | 100 | 298.13 | 1431.6 | 0.59985 | 0.055037 | 0.58451 | 0.058851 | 0.58688 | 0.057263 | + + +done! total time: 0:04:42 diff --git a/input_space_v3/flat_lr1e-3_7/eval_v2/adni_ad_vs_cn__patch__logistic/config.yaml b/input_space_v3/flat_lr1e-3_7/eval_v2/adni_ad_vs_cn__patch__logistic/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..a47c9b57648c0be16f58ba21863ca4f1387021b9 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_7/eval_v2/adni_ad_vs_cn__patch__logistic/config.yaml @@ -0,0 +1,30 @@ +output_root: experiments/input_space_v3/output +name_prefix: eval_logistic +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_7; eval v2 (adni_ad_vs_cn patch logistic) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_7/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: input_space_v3/flat_lr1e-3_7/eval_v2/adni_ad_vs_cn__patch__logistic +model: flat_mae +representation: patch +dataset: adni_ad_vs_cn +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_7/eval_v2/adni_ad_vs_cn__patch__logistic +remote_dir: null diff --git a/input_space_v3/flat_lr1e-3_7/eval_v2/adni_ad_vs_cn__patch__logistic/eval_table.csv b/input_space_v3/flat_lr1e-3_7/eval_v2/adni_ad_vs_cn__patch__logistic/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..3c36caac3666345e8bb50b81166f328986e0fab5 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_7/eval_v2/adni_ad_vs_cn__patch__logistic/eval_table.csv @@ -0,0 +1,203 @@ +model,repr,clf,dataset,trial,C,split,acc,acc_std,f1,f1_std,bacc,bacc_std +flat_mae,patch,logistic,adni_ad_vs_cn,,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,,166.81005372000556,test,0.6341463414634146,0.06879347741033177,0.48621553884711777,0.07487672258765708,0.4861111111111111,0.07895842334537526 +flat_mae,patch,logistic,adni_ad_vs_cn,1,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,1,166.81005372000556,test,0.7317073170731707,0.06634811659608515,0.6479313036690086,0.0857977875667205,0.6532258064516129,0.08907891782243559 +flat_mae,patch,logistic,adni_ad_vs_cn,2,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,2,21.54434690031882,test,0.7804878048780488,0.06219102808142911,0.7119437939110069,0.08094318998107065,0.7193548387096774,0.08660875222827667 +flat_mae,patch,logistic,adni_ad_vs_cn,3,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,3,1291.5496650148827,test,0.6097560975609756,0.06601288789496483,0.47096774193548385,0.07534009494047636,0.47096774193548385,0.07552969686991459 +flat_mae,patch,logistic,adni_ad_vs_cn,4,10000.0,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,4,10000.0,test,0.6829268292682927,0.06601387916728323,0.5839188134270101,0.08021845396446392,0.5870967741935484,0.08357273278367988 +flat_mae,patch,logistic,adni_ad_vs_cn,5,0.3593813663804626,train,0.989159891598916,0.005577325315780205,0.9847141673570836,0.007941521494814797,0.9807913550825869,0.010245899490195377 +flat_mae,patch,logistic,adni_ad_vs_cn,5,0.3593813663804626,test,0.7560975609756098,0.03374524004153825,0.5119047619047619,0.08139758764670492,0.5338709677419355,0.052939965212997465 +flat_mae,patch,logistic,adni_ad_vs_cn,6,0.046415888336127774,train,0.8970189701897019,0.013751206256331134,0.8410204081632653,0.02352118144630797,0.8114471197304627,0.02595151015815551 +flat_mae,patch,logistic,adni_ad_vs_cn,6,0.046415888336127774,test,0.8048780487804879,0.030272645664861653,0.6095238095238095,0.09367341473139215,0.6,0.0620589236129664 +flat_mae,patch,logistic,adni_ad_vs_cn,7,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,7,21.54434690031882,test,0.8048780487804879,0.05129713050316184,0.6893939393939394,0.09213459639417726,0.667741935483871,0.08224012302755833 +flat_mae,patch,logistic,adni_ad_vs_cn,8,0.046415888336127774,train,0.8970189701897019,0.014524325457449114,0.8394182317911132,0.02499629788739806,0.8073999506943874,0.026848059409084017 +flat_mae,patch,logistic,adni_ad_vs_cn,8,0.046415888336127774,test,0.7560975609756098,0.05540613126108556,0.6117424242424243,0.09268089614676017,0.6016129032258064,0.08013773938459492 +flat_mae,patch,logistic,adni_ad_vs_cn,9,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,9,166.81005372000556,test,0.7560975609756098,0.07007382866245168,0.7184065934065934,0.07370301153700502,0.7709677419354839,0.07823312975364714 +flat_mae,patch,logistic,adni_ad_vs_cn,10,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,10,21.54434690031882,test,0.7560975609756098,0.06175345811798754,0.6693548387096775,0.08450280386641704,0.6693548387096775,0.086717351030939 +flat_mae,patch,logistic,adni_ad_vs_cn,11,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,11,166.81005372000556,test,0.8048780487804879,0.051062220737788114,0.6893939393939394,0.09338395414677214,0.667741935483871,0.08325696309778774 +flat_mae,patch,logistic,adni_ad_vs_cn,12,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,12,166.81005372000556,test,0.7317073170731707,0.0696569481270005,0.6676492262343405,0.0823974635315469,0.6870967741935483,0.08978302409248926 +flat_mae,patch,logistic,adni_ad_vs_cn,13,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,13,2.782559402207126,test,0.7317073170731707,0.06212533626714442,0.6232247284878863,0.08545513354218988,0.6193548387096774,0.08467472708469656 +flat_mae,patch,logistic,adni_ad_vs_cn,14,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,14,2.782559402207126,test,0.7317073170731707,0.06471279154579115,0.6232247284878863,0.08751297428103007,0.6193548387096774,0.08542126855618674 +flat_mae,patch,logistic,adni_ad_vs_cn,15,0.3593813663804626,train,0.975609756097561,0.008483067065215297,0.9651729815325566,0.012394377399905843,0.9557687566768016,0.01590046693241199 +flat_mae,patch,logistic,adni_ad_vs_cn,15,0.3593813663804626,test,0.8048780487804879,0.05755427823790356,0.7515151515151515,0.07037287321408586,0.7693548387096774,0.07475461738233424 +flat_mae,patch,logistic,adni_ad_vs_cn,16,0.3593813663804626,train,0.986449864498645,0.006105887720157389,0.9808134274809954,0.008775765318825844,0.9749774015942148,0.011791097087911883 +flat_mae,patch,logistic,adni_ad_vs_cn,16,0.3593813663804626,test,0.7804878048780488,0.06348521400595977,0.6917293233082706,0.09279893986452906,0.685483870967742,0.09140244658900426 +flat_mae,patch,logistic,adni_ad_vs_cn,17,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,17,21.54434690031882,test,0.7317073170731707,0.06180701480511392,0.6232247284878863,0.08838624635997945,0.6193548387096774,0.08510886974127219 +flat_mae,patch,logistic,adni_ad_vs_cn,18,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,18,2.782559402207126,test,0.8536585365853658,0.049775486418372684,0.7864583333333333,0.07830174510615538,0.7677419354838709,0.0794908954269307 +flat_mae,patch,logistic,adni_ad_vs_cn,19,0.3593813663804626,train,0.986449864498645,0.006043481958261412,0.9808134274809954,0.008656536717367824,0.9749774015942148,0.011461331236960253 +flat_mae,patch,logistic,adni_ad_vs_cn,19,0.3593813663804626,test,0.7317073170731707,0.06096163742353641,0.5918552036199095,0.08679093879115204,0.5854838709677419,0.07861100868698098 +flat_mae,patch,logistic,adni_ad_vs_cn,20,0.3593813663804626,train,0.986449864498645,0.006174759728065634,0.9808134274809954,0.008872842462306177,0.9749774015942148,0.011937239431990517 +flat_mae,patch,logistic,adni_ad_vs_cn,20,0.3593813663804626,test,0.7804878048780488,0.06545759852030329,0.7280766396462786,0.07443349117262217,0.7532258064516129,0.07923647243533649 +flat_mae,patch,logistic,adni_ad_vs_cn,21,0.046415888336127774,train,0.9105691056910569,0.013324407085447729,0.8639517345399699,0.02217191289390071,0.8364697181362479,0.025152317448350725 +flat_mae,patch,logistic,adni_ad_vs_cn,21,0.046415888336127774,test,0.7560975609756098,0.04221291039111472,0.569327731092437,0.08752196262064046,0.567741935483871,0.06489185945492061 +flat_mae,patch,logistic,adni_ad_vs_cn,22,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,22,166.81005372000556,test,0.8048780487804879,0.046114876087328616,0.6554621848739496,0.10044338688616773,0.6338709677419355,0.0783632563640056 +flat_mae,patch,logistic,adni_ad_vs_cn,23,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,23,2.782559402207126,test,0.6829268292682927,0.06287717837010373,0.5547201336675021,0.08309375342457075,0.5532258064516129,0.0803938263506382 +flat_mae,patch,logistic,adni_ad_vs_cn,24,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,24,21.54434690031882,test,0.8292682926829268,0.057008593860435476,0.7602339181286549,0.08263164271915421,0.7516129032258064,0.08472706231452574 +flat_mae,patch,logistic,adni_ad_vs_cn,25,0.3593813663804626,train,0.978319783197832,0.007461121484784277,0.9694283347141673,0.010634580501686775,0.9656298792012491,0.013080247278149748 +flat_mae,patch,logistic,adni_ad_vs_cn,25,0.3593813663804626,test,0.7560975609756098,0.056383555177618755,0.6440972222222222,0.0852943926710624,0.635483870967742,0.0812815455451105 +flat_mae,patch,logistic,adni_ad_vs_cn,26,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,26,166.81005372000556,test,0.7073170731707317,0.06789912733724075,0.603225806451613,0.08754026259285366,0.603225806451613,0.08867400432293497 +flat_mae,patch,logistic,adni_ad_vs_cn,27,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,27,21.54434690031882,test,0.9024390243902439,0.04431832823705721,0.8576388888888888,0.0717461460293921,0.8338709677419355,0.07759519842037922 +flat_mae,patch,logistic,adni_ad_vs_cn,28,0.3593813663804626,train,0.975609756097561,0.007845984793726779,0.9654641694657917,0.011232371471735359,0.959815925712877,0.013700609796486837 +flat_mae,patch,logistic,adni_ad_vs_cn,28,0.3593813663804626,test,0.7804878048780488,0.055427085512837065,0.6660633484162897,0.0893645933844759,0.6516129032258065,0.08287161591428983 +flat_mae,patch,logistic,adni_ad_vs_cn,29,0.3593813663804626,train,0.981029810298103,0.007441250820684545,0.9731387984733936,0.01067115734737583,0.9673966636535458,0.013427419254450115 +flat_mae,patch,logistic,adni_ad_vs_cn,29,0.3593813663804626,test,0.7804878048780488,0.057376699654961484,0.6660633484162897,0.09404857808081388,0.6516129032258065,0.08646541512354516 +flat_mae,patch,logistic,adni_ad_vs_cn,30,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,30,166.81005372000556,test,0.7560975609756098,0.0656070359396221,0.6693548387096775,0.08851652892930255,0.6693548387096775,0.0885204999861273 +flat_mae,patch,logistic,adni_ad_vs_cn,31,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,31,1291.5496650148827,test,0.7560975609756098,0.06274611980248418,0.6693548387096775,0.08690247984126559,0.6693548387096775,0.08808654450948354 +flat_mae,patch,logistic,adni_ad_vs_cn,32,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,32,21.54434690031882,test,0.7560975609756098,0.06779477025906554,0.7054597701149425,0.07626005553268672,0.7370967741935484,0.08279443464332871 +flat_mae,patch,logistic,adni_ad_vs_cn,33,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,33,166.81005372000556,test,0.7560975609756098,0.06962414605053273,0.7184065934065934,0.07372474794600117,0.7709677419354839,0.07907374941150672 +flat_mae,patch,logistic,adni_ad_vs_cn,34,0.3593813663804626,train,0.983739837398374,0.006254000416254619,0.9770712510356255,0.008893400107721893,0.9732106171419179,0.01113956856462678 +flat_mae,patch,logistic,adni_ad_vs_cn,34,0.3593813663804626,test,0.7073170731707317,0.06930462805154843,0.646551724137931,0.07921730482318919,0.6709677419354838,0.0888378168952727 +flat_mae,patch,logistic,adni_ad_vs_cn,35,0.3593813663804626,train,0.9701897018970189,0.008575368518842264,0.957433644095347,0.012445099844619075,0.9481880187361328,0.015084532825930974 +flat_mae,patch,logistic,adni_ad_vs_cn,35,0.3593813663804626,test,0.8780487804878049,0.04597210959051434,0.8144796380090498,0.07922529098018274,0.7838709677419355,0.0802834916546239 +flat_mae,patch,logistic,adni_ad_vs_cn,36,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,36,166.81005372000556,test,0.7073170731707317,0.06817863299033426,0.6272727272727273,0.08041755184598214,0.6370967741935484,0.08557384820351342 +flat_mae,patch,logistic,adni_ad_vs_cn,37,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,37,166.81005372000556,test,0.7317073170731707,0.06747771571257456,0.6479313036690086,0.0831437224823802,0.6532258064516129,0.08569300109720013 +flat_mae,patch,logistic,adni_ad_vs_cn,38,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,38,166.81005372000556,test,0.7317073170731707,0.06971922955441286,0.6676492262343405,0.08074914460082491,0.6870967741935483,0.08605343855535834 +flat_mae,patch,logistic,adni_ad_vs_cn,39,0.046415888336127774,train,0.9186991869918699,0.012532490951159006,0.8769124710905534,0.02081112848485608,0.8498644095652887,0.02417550258303636 +flat_mae,patch,logistic,adni_ad_vs_cn,39,0.046415888336127774,test,0.7073170731707317,0.06564708340654474,0.603225806451613,0.08910777359344484,0.603225806451613,0.0903158681261483 +flat_mae,patch,logistic,adni_ad_vs_cn,40,0.046415888336127774,train,0.907859078590786,0.013594373315737518,0.8591476558289923,0.02305419387780454,0.8306557646478758,0.02642301609174453 +flat_mae,patch,logistic,adni_ad_vs_cn,40,0.046415888336127774,test,0.6829268292682927,0.06507710157433168,0.5547201336675021,0.08592958343060997,0.5532258064516129,0.08428466852634121 +flat_mae,patch,logistic,adni_ad_vs_cn,41,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,41,166.81005372000556,test,0.6341463414634146,0.07335941525978505,0.5684210526315789,0.08046516615501802,0.5887096774193548,0.09191126217425208 +flat_mae,patch,logistic,adni_ad_vs_cn,42,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,42,166.81005372000556,test,0.7317073170731707,0.057632758052290546,0.5918552036199095,0.0887233488585203,0.5854838709677419,0.07951160825989449 +flat_mae,patch,logistic,adni_ad_vs_cn,43,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,43,2.782559402207126,test,0.8048780487804879,0.05589026385954098,0.7354838709677419,0.07706016231722532,0.7354838709677419,0.08026873930669108 +flat_mae,patch,logistic,adni_ad_vs_cn,44,0.3593813663804626,train,0.978319783197832,0.00785048403994495,0.969172932330827,0.011419209137543506,0.9615827101651737,0.015033907559037475 +flat_mae,patch,logistic,adni_ad_vs_cn,44,0.3593813663804626,test,0.8780487804878049,0.04491663240655943,0.8144796380090498,0.07791658208763622,0.7838709677419355,0.07974698047513237 +flat_mae,patch,logistic,adni_ad_vs_cn,45,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,45,166.81005372000556,test,0.8780487804878049,0.05085220211987101,0.839968774395004,0.06674327365761604,0.8516129032258064,0.07145829539857156 +flat_mae,patch,logistic,adni_ad_vs_cn,46,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,46,2.782559402207126,test,0.7804878048780488,0.050913814802812936,0.6328358208955224,0.09454241180021106,0.6177419354838709,0.07835486201675639 +flat_mae,patch,logistic,adni_ad_vs_cn,47,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,47,1291.5496650148827,test,0.7560975609756098,0.05819974221636347,0.6440972222222222,0.0852055185112022,0.635483870967742,0.08052737585583455 +flat_mae,patch,logistic,adni_ad_vs_cn,48,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,48,166.81005372000556,test,0.7073170731707317,0.06409576045286408,0.603225806451613,0.08628622891139263,0.603225806451613,0.08746238293529443 +flat_mae,patch,logistic,adni_ad_vs_cn,49,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,49,1291.5496650148827,test,0.7560975609756098,0.04479908216957318,0.569327731092437,0.09215022374673339,0.567741935483871,0.06944422409492153 +flat_mae,patch,logistic,adni_ad_vs_cn,50,0.3593813663804626,train,0.983739837398374,0.006767006586414976,0.9768796992481203,0.009852500416331395,0.9691634481058427,0.01345855357312143 +flat_mae,patch,logistic,adni_ad_vs_cn,50,0.3593813663804626,test,0.7560975609756098,0.06370507596999357,0.6693548387096775,0.08417992824356524,0.6693548387096775,0.08346240007840076 +flat_mae,patch,logistic,adni_ad_vs_cn,51,0.046415888336127774,train,0.9132791327913279,0.013252558997749709,0.8674330878390515,0.022023752446104054,0.8382365025885447,0.02463636333866494 +flat_mae,patch,logistic,adni_ad_vs_cn,51,0.046415888336127774,test,0.6829268292682927,0.0658623119879087,0.5839188134270101,0.08454767507489182,0.5870967741935484,0.08730228865601727 +flat_mae,patch,logistic,adni_ad_vs_cn,52,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,52,2.782559402207126,test,0.6829268292682927,0.06574804539248888,0.5547201336675021,0.08536483094955649,0.5532258064516129,0.0824749134122111 +flat_mae,patch,logistic,adni_ad_vs_cn,53,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,53,2.782559402207126,test,0.8292682926829268,0.045280564989128406,0.7144278606965174,0.09501932872829214,0.6838709677419355,0.08055097105935856 +flat_mae,patch,logistic,adni_ad_vs_cn,54,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,54,2.782559402207126,test,0.7073170731707317,0.06783713919304447,0.6272727272727273,0.08241291021177646,0.6370967741935484,0.08840639882246953 +flat_mae,patch,logistic,adni_ad_vs_cn,55,0.3593813663804626,train,0.983739837398374,0.006737160074658951,0.9768796992481203,0.009755732074652489,0.9691634481058427,0.01297145764250136 +flat_mae,patch,logistic,adni_ad_vs_cn,55,0.3593813663804626,test,0.7804878048780488,0.05738260913423983,0.6660633484162897,0.0919063398065964,0.6516129032258065,0.08372124352938232 +flat_mae,patch,logistic,adni_ad_vs_cn,56,0.3593813663804626,train,0.983739837398374,0.005990714583189185,0.9766829555986183,0.008820042200220963,0.9651162790697674,0.012852172565097712 +flat_mae,patch,logistic,adni_ad_vs_cn,56,0.3593813663804626,test,0.7073170731707317,0.05898759183490928,0.5340909090909092,0.08646713030646332,0.535483870967742,0.0737479440444304 +flat_mae,patch,logistic,adni_ad_vs_cn,57,0.3593813663804626,train,0.978319783197832,0.00733790270195353,0.9696770482373244,0.010280070624176817,0.9696770482373244,0.011633989931339517 +flat_mae,patch,logistic,adni_ad_vs_cn,57,0.3593813663804626,test,0.8780487804878049,0.047855100547627705,0.8287385129490392,0.07118435770400072,0.8177419354838709,0.07594228735931809 +flat_mae,patch,logistic,adni_ad_vs_cn,58,0.046415888336127774,train,0.8970189701897019,0.013934279454563195,0.8410204081632653,0.02343357890640765,0.8114471197304627,0.0253456402151278 +flat_mae,patch,logistic,adni_ad_vs_cn,58,0.046415888336127774,test,0.8292682926829268,0.044600707186087385,0.7144278606965174,0.09260891969448037,0.6838709677419355,0.07888197271333117 +flat_mae,patch,logistic,adni_ad_vs_cn,59,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,59,21.54434690031882,test,0.7804878048780488,0.057803107928027564,0.6660633484162897,0.09256927474263606,0.6516129032258065,0.08535458293673429 +flat_mae,patch,logistic,adni_ad_vs_cn,60,0.3593813663804626,train,0.975609756097561,0.007474763715079213,0.9648738695859115,0.011112899290573023,0.9517215876407263,0.015209853893516664 +flat_mae,patch,logistic,adni_ad_vs_cn,60,0.3593813663804626,test,0.8048780487804879,0.05955903794215353,0.7354838709677419,0.08309090039394865,0.7354838709677419,0.08480689063555855 +flat_mae,patch,logistic,adni_ad_vs_cn,61,0.3593813663804626,train,0.986449864498645,0.005828942601573574,0.9809709458832265,0.008237110291345514,0.97902457063029,0.010007098711160447 +flat_mae,patch,logistic,adni_ad_vs_cn,61,0.3593813663804626,test,0.6097560975609756,0.07102377043417574,0.5030303030303029,0.0792063554848941,0.5048387096774194,0.08304258770997686 +flat_mae,patch,logistic,adni_ad_vs_cn,62,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,62,21.54434690031882,test,0.6829268292682927,0.07438287048624001,0.6072218128224024,0.08547180645643863,0.6209677419354839,0.09279682140264807 +flat_mae,patch,logistic,adni_ad_vs_cn,63,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,63,1291.5496650148827,test,0.7073170731707317,0.06577512932948539,0.6272727272727273,0.08150049716881728,0.6370967741935484,0.08704015238354704 +flat_mae,patch,logistic,adni_ad_vs_cn,64,0.3593813663804626,train,0.986449864498645,0.0059956947267110145,0.9808134274809954,0.008613223485627007,0.9749774015942148,0.011536200064706152 +flat_mae,patch,logistic,adni_ad_vs_cn,64,0.3593813663804626,test,0.8048780487804879,0.05925164877210564,0.7152777777777778,0.08946502664399512,0.7016129032258065,0.08714557676938205 +flat_mae,patch,logistic,adni_ad_vs_cn,65,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,65,2.782559402207126,test,0.6829268292682927,0.07402499698389185,0.6072218128224024,0.08477221503262432,0.6209677419354839,0.09083354319985175 +flat_mae,patch,logistic,adni_ad_vs_cn,66,0.3593813663804626,train,0.9728997289972899,0.008314264211153914,0.9611382593310305,0.012228152555719969,0.9499548031884295,0.0157584392504448 +flat_mae,patch,logistic,adni_ad_vs_cn,66,0.3593813663804626,test,0.8292682926829268,0.05263437238587054,0.7602339181286549,0.0762964032753162,0.7516129032258064,0.07749125767213189 +flat_mae,patch,logistic,adni_ad_vs_cn,67,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,67,166.81005372000556,test,0.8048780487804879,0.04907663761210557,0.6893939393939394,0.09111049376587163,0.667741935483871,0.08140019993481393 +flat_mae,patch,logistic,adni_ad_vs_cn,68,0.046415888336127774,train,0.907859078590786,0.01320512978312649,0.8563215758131013,0.022941118872850146,0.8225614265757252,0.025404367302106847 +flat_mae,patch,logistic,adni_ad_vs_cn,68,0.046415888336127774,test,0.7073170731707317,0.07006216327083523,0.6272727272727273,0.08482937840269551,0.6370967741935484,0.09153672997460248 +flat_mae,patch,logistic,adni_ad_vs_cn,69,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,69,166.81005372000556,test,0.7073170731707317,0.06213561955217522,0.5729166666666666,0.08571791392877874,0.5693548387096774,0.07962084833832446 +flat_mae,patch,logistic,adni_ad_vs_cn,70,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,70,21.54434690031882,test,0.7073170731707317,0.06216745439122331,0.5729166666666666,0.08671322095939978,0.5693548387096774,0.08048488712268213 +flat_mae,patch,logistic,adni_ad_vs_cn,71,0.046415888336127774,train,0.9051490514905149,0.013667906623808504,0.8557063851181499,0.022758746116222354,0.828888980195579,0.02566267686694779 +flat_mae,patch,logistic,adni_ad_vs_cn,71,0.046415888336127774,test,0.7560975609756098,0.045978035777358754,0.569327731092437,0.0887903443290156,0.567741935483871,0.06755542096045765 +flat_mae,patch,logistic,adni_ad_vs_cn,72,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,72,2.782559402207126,test,0.6829268292682927,0.05887455280909697,0.5176470588235295,0.08263679388654142,0.5193548387096775,0.07300704825352844 +flat_mae,patch,logistic,adni_ad_vs_cn,73,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,73,166.81005372000556,test,0.7073170731707317,0.06699385110339078,0.6272727272727273,0.08045953453823236,0.6370967741935484,0.08588373544838485 +flat_mae,patch,logistic,adni_ad_vs_cn,74,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,74,2.782559402207126,test,0.7560975609756098,0.03697326075298083,0.5119047619047619,0.08167513658831389,0.5338709677419355,0.05421840242288889 +flat_mae,patch,logistic,adni_ad_vs_cn,75,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,75,2.782559402207126,test,0.6585365853658537,0.06047214588813992,0.5017361111111112,0.08048794431153503,0.5032258064516129,0.07481710227564309 +flat_mae,patch,logistic,adni_ad_vs_cn,76,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,76,166.81005372000556,test,0.7073170731707317,0.06325683932662371,0.6272727272727273,0.07707225388962527,0.6370967741935484,0.08258560790279561 +flat_mae,patch,logistic,adni_ad_vs_cn,77,0.046415888336127774,train,0.9105691056910569,0.013567792290013285,0.8626194478603744,0.02310574557590591,0.8324225491001725,0.02646536996688584 +flat_mae,patch,logistic,adni_ad_vs_cn,77,0.046415888336127774,test,0.8048780487804879,0.033334459628007386,0.6095238095238095,0.10134122331440851,0.6,0.06833564223741516 +flat_mae,patch,logistic,adni_ad_vs_cn,78,0.3593813663804626,train,0.989159891598916,0.005699513654819106,0.9847141673570836,0.008133483409878453,0.9807913550825869,0.010704864556287353 +flat_mae,patch,logistic,adni_ad_vs_cn,78,0.3593813663804626,test,0.7560975609756098,0.055421568614554745,0.6117424242424243,0.0934996861414879,0.6016129032258064,0.07937643785517516 +flat_mae,patch,logistic,adni_ad_vs_cn,79,0.3593813663804626,train,0.981029810298103,0.007331975189553493,0.9733593242365172,0.01033413052827549,0.9714438326896212,0.012033000062952706 +flat_mae,patch,logistic,adni_ad_vs_cn,79,0.3593813663804626,test,0.9024390243902439,0.04559018753291259,0.8677419354838709,0.06365468652138803,0.8677419354838709,0.06958995525971337 +flat_mae,patch,logistic,adni_ad_vs_cn,80,0.046415888336127774,train,0.9024390243902439,0.014175168170436628,0.852294965308664,0.023001520171311247,0.8271221957432822,0.025440652288278562 +flat_mae,patch,logistic,adni_ad_vs_cn,80,0.046415888336127774,test,0.8048780487804879,0.04152947391967794,0.6554621848739496,0.09613874109999218,0.6338709677419355,0.07443950109734232 +flat_mae,patch,logistic,adni_ad_vs_cn,81,0.3593813663804626,train,0.983739837398374,0.006632381489396222,0.9768796992481203,0.009639770802578093,0.9691634481058427,0.013177628153921884 +flat_mae,patch,logistic,adni_ad_vs_cn,81,0.3593813663804626,test,0.7073170731707317,0.055354656652240625,0.5340909090909092,0.08695245408565891,0.535483870967742,0.07420075168398406 +flat_mae,patch,logistic,adni_ad_vs_cn,82,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,82,166.81005372000556,test,0.7317073170731707,0.06679286884818507,0.6479313036690086,0.08675133655109804,0.6532258064516129,0.09073668184280176 +flat_mae,patch,logistic,adni_ad_vs_cn,83,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,83,2.782559402207126,test,0.8292682926829268,0.04965470300023595,0.7402714932126697,0.08229757389573195,0.717741935483871,0.07941807570836479 +flat_mae,patch,logistic,adni_ad_vs_cn,84,0.046415888336127774,train,0.8997289972899729,0.01398569239115008,0.8459672597222379,0.023633849275261402,0.8172610732188348,0.026413502820539808 +flat_mae,patch,logistic,adni_ad_vs_cn,84,0.046415888336127774,test,0.7317073170731707,0.05278154725955306,0.5512437810945273,0.08763638931325594,0.5516129032258065,0.07036756152432976 +flat_mae,patch,logistic,adni_ad_vs_cn,85,0.046415888336127774,train,0.8970189701897019,0.013559675774271137,0.8394182317911132,0.02295183822636716,0.8073999506943874,0.024319056379473274 +flat_mae,patch,logistic,adni_ad_vs_cn,85,0.046415888336127774,test,0.9024390243902439,0.038957839595043606,0.8446969696969697,0.07880827009396209,0.8,0.07986357116983939 +flat_mae,patch,logistic,adni_ad_vs_cn,86,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,86,166.81005372000556,test,0.6341463414634146,0.06562641913708755,0.5199063231850116,0.07895083290036801,0.5209677419354839,0.08118912511821383 +flat_mae,patch,logistic,adni_ad_vs_cn,87,0.046415888336127774,train,0.9024390243902439,0.012929636710588268,0.8478699038021071,0.022452166877395218,0.8149806886350563,0.024704211588315095 +flat_mae,patch,logistic,adni_ad_vs_cn,87,0.046415888336127774,test,0.8292682926829268,0.035884539546512204,0.6800445930880714,0.09951340553485565,0.65,0.07356330607035003 +flat_mae,patch,logistic,adni_ad_vs_cn,88,0.046415888336127774,train,0.907859078590786,0.012668245967831128,0.8548454276194002,0.022295876942617088,0.81851425753965,0.024572812353345352 +flat_mae,patch,logistic,adni_ad_vs_cn,88,0.046415888336127774,test,0.7804878048780488,0.06274118958794271,0.7119437939110069,0.08142727273842443,0.7193548387096774,0.08689408314577014 +flat_mae,patch,logistic,adni_ad_vs_cn,89,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,89,166.81005372000556,test,0.8048780487804879,0.056402901777930274,0.7152777777777778,0.08575900856773136,0.7016129032258065,0.0845924036510552 +flat_mae,patch,logistic,adni_ad_vs_cn,90,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,90,2.782559402207126,test,0.7804878048780488,0.06286930628545062,0.7119437939110069,0.08050471984022918,0.7193548387096774,0.08452473946535263 +flat_mae,patch,logistic,adni_ad_vs_cn,91,0.3593813663804626,train,0.978319783197832,0.007585464126602047,0.969172932330827,0.011003324830309007,0.9615827101651737,0.01425311465933161 +flat_mae,patch,logistic,adni_ad_vs_cn,91,0.3593813663804626,test,0.7560975609756098,0.05266476651767944,0.6117424242424243,0.09093748387271962,0.6016129032258064,0.0792933422218259 +flat_mae,patch,logistic,adni_ad_vs_cn,92,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,92,21.54434690031882,test,0.7073170731707317,0.06852615144950625,0.6272727272727273,0.0826833775252128,0.6370967741935484,0.0870951075109349 +flat_mae,patch,logistic,adni_ad_vs_cn,93,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,93,166.81005372000556,test,0.6097560975609756,0.07409142703299648,0.5661375661375662,0.07528931847912766,0.6064516129032258,0.08839181150599378 +flat_mae,patch,logistic,adni_ad_vs_cn,94,0.3593813663804626,train,0.978319783197832,0.007883395703676289,0.969172932330827,0.011436479093119348,0.9615827101651737,0.014619224263201017 +flat_mae,patch,logistic,adni_ad_vs_cn,94,0.3593813663804626,test,0.6341463414634146,0.05934424522065338,0.44343891402714936,0.06570315400430174,0.45322580645161287,0.06067387137849463 +flat_mae,patch,logistic,adni_ad_vs_cn,95,0.3593813663804626,train,0.978319783197832,0.006921515322405678,0.969172932330827,0.010044601930534063,0.9615827101651737,0.013286830211411168 +flat_mae,patch,logistic,adni_ad_vs_cn,95,0.3593813663804626,test,0.6829268292682927,0.06396777520070943,0.5547201336675021,0.08513158284301105,0.5532258064516129,0.08176911125009612 +flat_mae,patch,logistic,adni_ad_vs_cn,96,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,96,21.54434690031882,test,0.6585365853658537,0.07192598151829847,0.5651515151515152,0.08450881950432393,0.5709677419354839,0.08918203034771459 +flat_mae,patch,logistic,adni_ad_vs_cn,97,0.3593813663804626,train,0.978319783197832,0.007307332671589265,0.9689106074648244,0.010755004945897824,0.9575355411290984,0.01457910039470995 +flat_mae,patch,logistic,adni_ad_vs_cn,97,0.3593813663804626,test,0.8048780487804879,0.054873582474079086,0.7152777777777778,0.08571887148027868,0.7016129032258065,0.08524716808794017 +flat_mae,patch,logistic,adni_ad_vs_cn,98,0.3593813663804626,train,0.981029810298103,0.006763862821097902,0.9731387984733936,0.009689938724631949,0.9673966636535458,0.012347163270308643 +flat_mae,patch,logistic,adni_ad_vs_cn,98,0.3593813663804626,test,0.7317073170731707,0.06026116075498686,0.6232247284878863,0.08539756760075336,0.6193548387096774,0.08360609658425748 +flat_mae,patch,logistic,adni_ad_vs_cn,99,0.3593813663804626,train,0.983739837398374,0.006434816542306245,0.9770712510356255,0.0091641437214455,0.9732106171419179,0.011431225722812823 +flat_mae,patch,logistic,adni_ad_vs_cn,99,0.3593813663804626,test,0.7804878048780488,0.04722039406554055,0.6328358208955224,0.0914981670492301,0.6177419354838709,0.07431212649090602 +flat_mae,patch,logistic,adni_ad_vs_cn,100,0.3593813663804626,train,0.975609756097561,0.008758210556807403,0.9648738695859115,0.013043596760696123,0.9517215876407263,0.01736544155468035 +flat_mae,patch,logistic,adni_ad_vs_cn,100,0.3593813663804626,test,0.7073170731707317,0.060413880870083585,0.5729166666666666,0.08371631004603301,0.5693548387096774,0.07772184079742764 diff --git a/input_space_v3/flat_lr1e-3_7/eval_v2/adni_ad_vs_cn__patch__logistic/log.txt b/input_space_v3/flat_lr1e-3_7/eval_v2/adni_ad_vs_cn__patch__logistic/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..35883198e012c64b7fb28b2f6057139cfe4926bd --- /dev/null +++ b/input_space_v3/flat_lr1e-3_7/eval_v2/adni_ad_vs_cn__patch__logistic/log.txt @@ -0,0 +1,240 @@ +fMRI foundation model logistic probe eval +version: 0.1.dev86+gf97f52698 +sha: bcce2b486277d3a5b520775efd9cdf1a2affce36, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-04-08 22:54:53 +config: +output_root: experiments/input_space_v3/output +name_prefix: eval_logistic +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_7; eval v2 (adni_ad_vs_cn patch logistic) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_7/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: input_space_v3/flat_lr1e-3_7/eval_v2/adni_ad_vs_cn__patch__logistic +model: flat_mae +representation: patch +dataset: adni_ad_vs_cn +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_7/eval_v2/adni_ad_vs_cn__patch__logistic +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=True, reg_tokens=0, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: adni_ad_vs_cn (flat) +train (n=328): +ADNIDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'bold', 'mean', 'std'], + num_rows: 525 +}), + labels=[0 1], + counts=[251 77] +) + +validation (n=41): +ADNIDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'bold', 'mean', 'std'], + num_rows: 66 +}), + labels=[0 1], + counts=[31 10] +) + +test (n=41): +ADNIDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'bold', 'mean', 'std'], + num_rows: 66 +}), + labels=[0 1], + counts=[32 9] +) + +extracting features for all splits +extract (train) [ 0/164] eta: 0:11:45 time: 4.3034 data: 3.3549 max mem: 2698 +extract (train) [ 20/164] eta: 0:00:56 time: 0.1972 data: 0.0677 max mem: 2851 +extract (train) [ 40/164] eta: 0:00:35 time: 0.1750 data: 0.0556 max mem: 2851 +extract (train) [ 60/164] eta: 0:00:25 time: 0.1552 data: 0.0477 max mem: 2851 +extract (train) [ 80/164] eta: 0:00:18 time: 0.1570 data: 0.0472 max mem: 2851 +extract (train) [100/164] eta: 0:00:13 time: 0.1514 data: 0.0453 max mem: 2851 +extract (train) [120/164] eta: 0:00:08 time: 0.1659 data: 0.0539 max mem: 2851 +extract (train) [140/164] eta: 0:00:04 time: 0.1734 data: 0.0585 max mem: 2851 +extract (train) [160/164] eta: 0:00:00 time: 0.1399 data: 0.0386 max mem: 2851 +extract (train) [163/164] eta: 0:00:00 time: 0.1399 data: 0.0387 max mem: 2851 +extract (train) Total time: 0:00:31 (0.1916 s / it) +extract (validation) [ 0/21] eta: 0:01:09 time: 3.3083 data: 3.1988 max mem: 2851 +extract (validation) [20/21] eta: 0:00:00 time: 0.1469 data: 0.0440 max mem: 2851 +extract (validation) Total time: 0:00:06 (0.3167 s / it) +extract (test) [ 0/21] eta: 0:01:16 time: 3.6195 data: 3.4826 max mem: 2851 +extract (test) [20/21] eta: 0:00:00 time: 0.1452 data: 0.0409 max mem: 2851 +extract (test) Total time: 0:00:06 (0.3253 s / it) +feature extraction time: 0:00:44 +train features: (328, 768) +validation features: (41, 768) +test features: (41, 768) +evaluating fixed splits +eval results (fixed splits): + +| model | repr | clf | dataset | trial | C | split | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:--------------|:--------|-------:|:--------|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | adni_ad_vs_cn | | 166.81 | train | 1 | 0 | 1 | 0 | 1 | 0 | +| flat_mae | patch | logistic | adni_ad_vs_cn | | 166.81 | test | 0.63415 | 0.068793 | 0.48622 | 0.074877 | 0.48611 | 0.078958 | + + +evaluating random splits (n=100) +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 1, "C": 166.81005372000556, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.06634811659608515, "f1": 0.6479313036690086, "f1_std": 0.0857977875667205, "bacc": 0.6532258064516129, "bacc_std": 0.08907891782243559} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 2, "C": 21.54434690031882, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.06219102808142911, "f1": 0.7119437939110069, "f1_std": 0.08094318998107065, "bacc": 0.7193548387096774, "bacc_std": 0.08660875222827667} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 3, "C": 1291.5496650148827, "split": "test", "acc": 0.6097560975609756, "acc_std": 0.06601288789496483, "f1": 0.47096774193548385, "f1_std": 0.07534009494047636, "bacc": 0.47096774193548385, "bacc_std": 0.07552969686991459} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 4, "C": 10000.0, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.06601387916728323, "f1": 0.5839188134270101, "f1_std": 0.08021845396446392, "bacc": 0.5870967741935484, "bacc_std": 0.08357273278367988} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 5, "C": 0.3593813663804626, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.03374524004153825, "f1": 0.5119047619047619, "f1_std": 0.08139758764670492, "bacc": 0.5338709677419355, "bacc_std": 0.052939965212997465} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 6, "C": 0.046415888336127774, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.030272645664861653, "f1": 0.6095238095238095, "f1_std": 0.09367341473139215, "bacc": 0.6, "bacc_std": 0.0620589236129664} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 7, "C": 21.54434690031882, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.05129713050316184, "f1": 0.6893939393939394, "f1_std": 0.09213459639417726, "bacc": 0.667741935483871, "bacc_std": 0.08224012302755833} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 8, "C": 0.046415888336127774, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.05540613126108556, "f1": 0.6117424242424243, "f1_std": 0.09268089614676017, "bacc": 0.6016129032258064, "bacc_std": 0.08013773938459492} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 9, "C": 166.81005372000556, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.07007382866245168, "f1": 0.7184065934065934, "f1_std": 0.07370301153700502, "bacc": 0.7709677419354839, "bacc_std": 0.07823312975364714} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 10, "C": 21.54434690031882, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.06175345811798754, "f1": 0.6693548387096775, "f1_std": 0.08450280386641704, "bacc": 0.6693548387096775, "bacc_std": 0.086717351030939} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 11, "C": 166.81005372000556, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.051062220737788114, "f1": 0.6893939393939394, "f1_std": 0.09338395414677214, "bacc": 0.667741935483871, "bacc_std": 0.08325696309778774} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 12, "C": 166.81005372000556, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.0696569481270005, "f1": 0.6676492262343405, "f1_std": 0.0823974635315469, "bacc": 0.6870967741935483, "bacc_std": 0.08978302409248926} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 13, "C": 2.782559402207126, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.06212533626714442, "f1": 0.6232247284878863, "f1_std": 0.08545513354218988, "bacc": 0.6193548387096774, "bacc_std": 0.08467472708469656} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 14, "C": 2.782559402207126, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.06471279154579115, "f1": 0.6232247284878863, "f1_std": 0.08751297428103007, "bacc": 0.6193548387096774, "bacc_std": 0.08542126855618674} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 15, "C": 0.3593813663804626, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.05755427823790356, "f1": 0.7515151515151515, "f1_std": 0.07037287321408586, "bacc": 0.7693548387096774, "bacc_std": 0.07475461738233424} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 16, "C": 0.3593813663804626, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.06348521400595977, "f1": 0.6917293233082706, "f1_std": 0.09279893986452906, "bacc": 0.685483870967742, "bacc_std": 0.09140244658900426} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 17, "C": 21.54434690031882, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.06180701480511392, "f1": 0.6232247284878863, "f1_std": 0.08838624635997945, "bacc": 0.6193548387096774, "bacc_std": 0.08510886974127219} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 18, "C": 2.782559402207126, "split": "test", "acc": 0.8536585365853658, "acc_std": 0.049775486418372684, "f1": 0.7864583333333333, "f1_std": 0.07830174510615538, "bacc": 0.7677419354838709, "bacc_std": 0.0794908954269307} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 19, "C": 0.3593813663804626, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.06096163742353641, "f1": 0.5918552036199095, "f1_std": 0.08679093879115204, "bacc": 0.5854838709677419, "bacc_std": 0.07861100868698098} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 20, "C": 0.3593813663804626, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.06545759852030329, "f1": 0.7280766396462786, "f1_std": 0.07443349117262217, "bacc": 0.7532258064516129, "bacc_std": 0.07923647243533649} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 21, "C": 0.046415888336127774, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.04221291039111472, "f1": 0.569327731092437, "f1_std": 0.08752196262064046, "bacc": 0.567741935483871, "bacc_std": 0.06489185945492061} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 22, "C": 166.81005372000556, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.046114876087328616, "f1": 0.6554621848739496, "f1_std": 0.10044338688616773, "bacc": 0.6338709677419355, "bacc_std": 0.0783632563640056} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 23, "C": 2.782559402207126, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.06287717837010373, "f1": 0.5547201336675021, "f1_std": 0.08309375342457075, "bacc": 0.5532258064516129, "bacc_std": 0.0803938263506382} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 24, "C": 21.54434690031882, "split": "test", "acc": 0.8292682926829268, "acc_std": 0.057008593860435476, "f1": 0.7602339181286549, "f1_std": 0.08263164271915421, "bacc": 0.7516129032258064, "bacc_std": 0.08472706231452574} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 25, "C": 0.3593813663804626, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.056383555177618755, "f1": 0.6440972222222222, "f1_std": 0.0852943926710624, "bacc": 0.635483870967742, "bacc_std": 0.0812815455451105} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 26, "C": 166.81005372000556, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.06789912733724075, "f1": 0.603225806451613, "f1_std": 0.08754026259285366, "bacc": 0.603225806451613, "bacc_std": 0.08867400432293497} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 27, "C": 21.54434690031882, "split": "test", "acc": 0.9024390243902439, "acc_std": 0.04431832823705721, "f1": 0.8576388888888888, "f1_std": 0.0717461460293921, "bacc": 0.8338709677419355, "bacc_std": 0.07759519842037922} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 28, "C": 0.3593813663804626, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.055427085512837065, "f1": 0.6660633484162897, "f1_std": 0.0893645933844759, "bacc": 0.6516129032258065, "bacc_std": 0.08287161591428983} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 29, "C": 0.3593813663804626, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.057376699654961484, "f1": 0.6660633484162897, "f1_std": 0.09404857808081388, "bacc": 0.6516129032258065, "bacc_std": 0.08646541512354516} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 30, "C": 166.81005372000556, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.0656070359396221, "f1": 0.6693548387096775, "f1_std": 0.08851652892930255, "bacc": 0.6693548387096775, "bacc_std": 0.0885204999861273} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 31, "C": 1291.5496650148827, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.06274611980248418, "f1": 0.6693548387096775, "f1_std": 0.08690247984126559, "bacc": 0.6693548387096775, "bacc_std": 0.08808654450948354} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 32, "C": 21.54434690031882, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.06779477025906554, "f1": 0.7054597701149425, "f1_std": 0.07626005553268672, "bacc": 0.7370967741935484, "bacc_std": 0.08279443464332871} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 33, "C": 166.81005372000556, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.06962414605053273, "f1": 0.7184065934065934, "f1_std": 0.07372474794600117, "bacc": 0.7709677419354839, "bacc_std": 0.07907374941150672} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 34, "C": 0.3593813663804626, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.06930462805154843, "f1": 0.646551724137931, "f1_std": 0.07921730482318919, "bacc": 0.6709677419354838, "bacc_std": 0.0888378168952727} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 35, "C": 0.3593813663804626, "split": "test", "acc": 0.8780487804878049, "acc_std": 0.04597210959051434, "f1": 0.8144796380090498, "f1_std": 0.07922529098018274, "bacc": 0.7838709677419355, "bacc_std": 0.0802834916546239} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 36, "C": 166.81005372000556, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.06817863299033426, "f1": 0.6272727272727273, "f1_std": 0.08041755184598214, "bacc": 0.6370967741935484, "bacc_std": 0.08557384820351342} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 37, "C": 166.81005372000556, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.06747771571257456, "f1": 0.6479313036690086, "f1_std": 0.0831437224823802, "bacc": 0.6532258064516129, "bacc_std": 0.08569300109720013} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 38, "C": 166.81005372000556, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.06971922955441286, "f1": 0.6676492262343405, "f1_std": 0.08074914460082491, "bacc": 0.6870967741935483, "bacc_std": 0.08605343855535834} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 39, "C": 0.046415888336127774, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.06564708340654474, "f1": 0.603225806451613, "f1_std": 0.08910777359344484, "bacc": 0.603225806451613, "bacc_std": 0.0903158681261483} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 40, "C": 0.046415888336127774, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.06507710157433168, "f1": 0.5547201336675021, "f1_std": 0.08592958343060997, "bacc": 0.5532258064516129, "bacc_std": 0.08428466852634121} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 41, "C": 166.81005372000556, "split": "test", "acc": 0.6341463414634146, "acc_std": 0.07335941525978505, "f1": 0.5684210526315789, "f1_std": 0.08046516615501802, "bacc": 0.5887096774193548, "bacc_std": 0.09191126217425208} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 42, "C": 166.81005372000556, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.057632758052290546, "f1": 0.5918552036199095, "f1_std": 0.0887233488585203, "bacc": 0.5854838709677419, "bacc_std": 0.07951160825989449} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 43, "C": 2.782559402207126, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.05589026385954098, "f1": 0.7354838709677419, "f1_std": 0.07706016231722532, "bacc": 0.7354838709677419, "bacc_std": 0.08026873930669108} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 44, "C": 0.3593813663804626, "split": "test", "acc": 0.8780487804878049, "acc_std": 0.04491663240655943, "f1": 0.8144796380090498, "f1_std": 0.07791658208763622, "bacc": 0.7838709677419355, "bacc_std": 0.07974698047513237} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 45, "C": 166.81005372000556, "split": "test", "acc": 0.8780487804878049, "acc_std": 0.05085220211987101, "f1": 0.839968774395004, "f1_std": 0.06674327365761604, "bacc": 0.8516129032258064, "bacc_std": 0.07145829539857156} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 46, "C": 2.782559402207126, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.050913814802812936, "f1": 0.6328358208955224, "f1_std": 0.09454241180021106, "bacc": 0.6177419354838709, "bacc_std": 0.07835486201675639} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 47, "C": 1291.5496650148827, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.05819974221636347, "f1": 0.6440972222222222, "f1_std": 0.0852055185112022, "bacc": 0.635483870967742, "bacc_std": 0.08052737585583455} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 48, "C": 166.81005372000556, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.06409576045286408, "f1": 0.603225806451613, "f1_std": 0.08628622891139263, "bacc": 0.603225806451613, "bacc_std": 0.08746238293529443} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 49, "C": 1291.5496650148827, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.04479908216957318, "f1": 0.569327731092437, "f1_std": 0.09215022374673339, "bacc": 0.567741935483871, "bacc_std": 0.06944422409492153} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 50, "C": 0.3593813663804626, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.06370507596999357, "f1": 0.6693548387096775, "f1_std": 0.08417992824356524, "bacc": 0.6693548387096775, "bacc_std": 0.08346240007840076} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 51, "C": 0.046415888336127774, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.0658623119879087, "f1": 0.5839188134270101, "f1_std": 0.08454767507489182, "bacc": 0.5870967741935484, "bacc_std": 0.08730228865601727} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 52, "C": 2.782559402207126, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.06574804539248888, "f1": 0.5547201336675021, "f1_std": 0.08536483094955649, "bacc": 0.5532258064516129, "bacc_std": 0.0824749134122111} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 53, "C": 2.782559402207126, "split": "test", "acc": 0.8292682926829268, "acc_std": 0.045280564989128406, "f1": 0.7144278606965174, "f1_std": 0.09501932872829214, "bacc": 0.6838709677419355, "bacc_std": 0.08055097105935856} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 54, "C": 2.782559402207126, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.06783713919304447, "f1": 0.6272727272727273, "f1_std": 0.08241291021177646, "bacc": 0.6370967741935484, "bacc_std": 0.08840639882246953} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 55, "C": 0.3593813663804626, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.05738260913423983, "f1": 0.6660633484162897, "f1_std": 0.0919063398065964, "bacc": 0.6516129032258065, "bacc_std": 0.08372124352938232} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 56, "C": 0.3593813663804626, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.05898759183490928, "f1": 0.5340909090909092, "f1_std": 0.08646713030646332, "bacc": 0.535483870967742, "bacc_std": 0.0737479440444304} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 57, "C": 0.3593813663804626, "split": "test", "acc": 0.8780487804878049, "acc_std": 0.047855100547627705, "f1": 0.8287385129490392, "f1_std": 0.07118435770400072, "bacc": 0.8177419354838709, "bacc_std": 0.07594228735931809} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 58, "C": 0.046415888336127774, "split": "test", "acc": 0.8292682926829268, "acc_std": 0.044600707186087385, "f1": 0.7144278606965174, "f1_std": 0.09260891969448037, "bacc": 0.6838709677419355, "bacc_std": 0.07888197271333117} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 59, "C": 21.54434690031882, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.057803107928027564, "f1": 0.6660633484162897, "f1_std": 0.09256927474263606, "bacc": 0.6516129032258065, "bacc_std": 0.08535458293673429} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 60, "C": 0.3593813663804626, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.05955903794215353, "f1": 0.7354838709677419, "f1_std": 0.08309090039394865, "bacc": 0.7354838709677419, "bacc_std": 0.08480689063555855} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 61, "C": 0.3593813663804626, "split": "test", "acc": 0.6097560975609756, "acc_std": 0.07102377043417574, "f1": 0.5030303030303029, "f1_std": 0.0792063554848941, "bacc": 0.5048387096774194, "bacc_std": 0.08304258770997686} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 62, "C": 21.54434690031882, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.07438287048624001, "f1": 0.6072218128224024, "f1_std": 0.08547180645643863, "bacc": 0.6209677419354839, "bacc_std": 0.09279682140264807} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 63, "C": 1291.5496650148827, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.06577512932948539, "f1": 0.6272727272727273, "f1_std": 0.08150049716881728, "bacc": 0.6370967741935484, "bacc_std": 0.08704015238354704} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 64, "C": 0.3593813663804626, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.05925164877210564, "f1": 0.7152777777777778, "f1_std": 0.08946502664399512, "bacc": 0.7016129032258065, "bacc_std": 0.08714557676938205} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 65, "C": 2.782559402207126, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.07402499698389185, "f1": 0.6072218128224024, "f1_std": 0.08477221503262432, "bacc": 0.6209677419354839, "bacc_std": 0.09083354319985175} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 66, "C": 0.3593813663804626, "split": "test", "acc": 0.8292682926829268, "acc_std": 0.05263437238587054, "f1": 0.7602339181286549, "f1_std": 0.0762964032753162, "bacc": 0.7516129032258064, "bacc_std": 0.07749125767213189} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 67, "C": 166.81005372000556, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.04907663761210557, "f1": 0.6893939393939394, "f1_std": 0.09111049376587163, "bacc": 0.667741935483871, "bacc_std": 0.08140019993481393} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 68, "C": 0.046415888336127774, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.07006216327083523, "f1": 0.6272727272727273, "f1_std": 0.08482937840269551, "bacc": 0.6370967741935484, "bacc_std": 0.09153672997460248} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 69, "C": 166.81005372000556, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.06213561955217522, "f1": 0.5729166666666666, "f1_std": 0.08571791392877874, "bacc": 0.5693548387096774, "bacc_std": 0.07962084833832446} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 70, "C": 21.54434690031882, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.06216745439122331, "f1": 0.5729166666666666, "f1_std": 0.08671322095939978, "bacc": 0.5693548387096774, "bacc_std": 0.08048488712268213} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 71, "C": 0.046415888336127774, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.045978035777358754, "f1": 0.569327731092437, "f1_std": 0.0887903443290156, "bacc": 0.567741935483871, "bacc_std": 0.06755542096045765} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 72, "C": 2.782559402207126, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.05887455280909697, "f1": 0.5176470588235295, "f1_std": 0.08263679388654142, "bacc": 0.5193548387096775, "bacc_std": 0.07300704825352844} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 73, "C": 166.81005372000556, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.06699385110339078, "f1": 0.6272727272727273, "f1_std": 0.08045953453823236, "bacc": 0.6370967741935484, "bacc_std": 0.08588373544838485} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 74, "C": 2.782559402207126, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.03697326075298083, "f1": 0.5119047619047619, "f1_std": 0.08167513658831389, "bacc": 0.5338709677419355, "bacc_std": 0.05421840242288889} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 75, "C": 2.782559402207126, "split": "test", "acc": 0.6585365853658537, "acc_std": 0.06047214588813992, "f1": 0.5017361111111112, "f1_std": 0.08048794431153503, "bacc": 0.5032258064516129, "bacc_std": 0.07481710227564309} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 76, "C": 166.81005372000556, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.06325683932662371, "f1": 0.6272727272727273, "f1_std": 0.07707225388962527, "bacc": 0.6370967741935484, "bacc_std": 0.08258560790279561} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 77, "C": 0.046415888336127774, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.033334459628007386, "f1": 0.6095238095238095, "f1_std": 0.10134122331440851, "bacc": 0.6, "bacc_std": 0.06833564223741516} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 78, "C": 0.3593813663804626, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.055421568614554745, "f1": 0.6117424242424243, "f1_std": 0.0934996861414879, "bacc": 0.6016129032258064, "bacc_std": 0.07937643785517516} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 79, "C": 0.3593813663804626, "split": "test", "acc": 0.9024390243902439, "acc_std": 0.04559018753291259, "f1": 0.8677419354838709, "f1_std": 0.06365468652138803, "bacc": 0.8677419354838709, "bacc_std": 0.06958995525971337} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 80, "C": 0.046415888336127774, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.04152947391967794, "f1": 0.6554621848739496, "f1_std": 0.09613874109999218, "bacc": 0.6338709677419355, "bacc_std": 0.07443950109734232} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 81, "C": 0.3593813663804626, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.055354656652240625, "f1": 0.5340909090909092, "f1_std": 0.08695245408565891, "bacc": 0.535483870967742, "bacc_std": 0.07420075168398406} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 82, "C": 166.81005372000556, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.06679286884818507, "f1": 0.6479313036690086, "f1_std": 0.08675133655109804, "bacc": 0.6532258064516129, "bacc_std": 0.09073668184280176} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 83, "C": 2.782559402207126, "split": "test", "acc": 0.8292682926829268, "acc_std": 0.04965470300023595, "f1": 0.7402714932126697, "f1_std": 0.08229757389573195, "bacc": 0.717741935483871, "bacc_std": 0.07941807570836479} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 84, "C": 0.046415888336127774, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.05278154725955306, "f1": 0.5512437810945273, "f1_std": 0.08763638931325594, "bacc": 0.5516129032258065, "bacc_std": 0.07036756152432976} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 85, "C": 0.046415888336127774, "split": "test", "acc": 0.9024390243902439, "acc_std": 0.038957839595043606, "f1": 0.8446969696969697, "f1_std": 0.07880827009396209, "bacc": 0.8, "bacc_std": 0.07986357116983939} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 86, "C": 166.81005372000556, "split": "test", "acc": 0.6341463414634146, "acc_std": 0.06562641913708755, "f1": 0.5199063231850116, "f1_std": 0.07895083290036801, "bacc": 0.5209677419354839, "bacc_std": 0.08118912511821383} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 87, "C": 0.046415888336127774, "split": "test", "acc": 0.8292682926829268, "acc_std": 0.035884539546512204, "f1": 0.6800445930880714, "f1_std": 0.09951340553485565, "bacc": 0.65, "bacc_std": 0.07356330607035003} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 88, "C": 0.046415888336127774, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.06274118958794271, "f1": 0.7119437939110069, "f1_std": 0.08142727273842443, "bacc": 0.7193548387096774, "bacc_std": 0.08689408314577014} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 89, "C": 166.81005372000556, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.056402901777930274, "f1": 0.7152777777777778, "f1_std": 0.08575900856773136, "bacc": 0.7016129032258065, "bacc_std": 0.0845924036510552} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 90, "C": 2.782559402207126, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.06286930628545062, "f1": 0.7119437939110069, "f1_std": 0.08050471984022918, "bacc": 0.7193548387096774, "bacc_std": 0.08452473946535263} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 91, "C": 0.3593813663804626, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.05266476651767944, "f1": 0.6117424242424243, "f1_std": 0.09093748387271962, "bacc": 0.6016129032258064, "bacc_std": 0.0792933422218259} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 92, "C": 21.54434690031882, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.06852615144950625, "f1": 0.6272727272727273, "f1_std": 0.0826833775252128, "bacc": 0.6370967741935484, "bacc_std": 0.0870951075109349} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 93, "C": 166.81005372000556, "split": "test", "acc": 0.6097560975609756, "acc_std": 0.07409142703299648, "f1": 0.5661375661375662, "f1_std": 0.07528931847912766, "bacc": 0.6064516129032258, "bacc_std": 0.08839181150599378} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 94, "C": 0.3593813663804626, "split": "test", "acc": 0.6341463414634146, "acc_std": 0.05934424522065338, "f1": 0.44343891402714936, "f1_std": 0.06570315400430174, "bacc": 0.45322580645161287, "bacc_std": 0.06067387137849463} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 95, "C": 0.3593813663804626, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.06396777520070943, "f1": 0.5547201336675021, "f1_std": 0.08513158284301105, "bacc": 0.5532258064516129, "bacc_std": 0.08176911125009612} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 96, "C": 21.54434690031882, "split": "test", "acc": 0.6585365853658537, "acc_std": 0.07192598151829847, "f1": 0.5651515151515152, "f1_std": 0.08450881950432393, "bacc": 0.5709677419354839, "bacc_std": 0.08918203034771459} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 97, "C": 0.3593813663804626, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.054873582474079086, "f1": 0.7152777777777778, "f1_std": 0.08571887148027868, "bacc": 0.7016129032258065, "bacc_std": 0.08524716808794017} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 98, "C": 0.3593813663804626, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.06026116075498686, "f1": 0.6232247284878863, "f1_std": 0.08539756760075336, "bacc": 0.6193548387096774, "bacc_std": 0.08360609658425748} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 99, "C": 0.3593813663804626, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.04722039406554055, "f1": 0.6328358208955224, "f1_std": 0.0914981670492301, "bacc": 0.6177419354838709, "bacc_std": 0.07431212649090602} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 100, "C": 0.3593813663804626, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.060413880870083585, "f1": 0.5729166666666666, "f1_std": 0.08371631004603301, "bacc": 0.5693548387096774, "bacc_std": 0.07772184079742764} +eval results (random splits): + +| model | repr | clf | dataset | split | n_trials | C | C_std | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:--------------|:--------|-----------:|-------:|--------:|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | adni_ad_vs_cn | train | 100 | 206.06 | 1028.6 | 0.98024 | 0.033057 | 0.97022 | 0.05096 | 0.96377 | 0.061365 | +| flat_mae | patch | logistic | adni_ad_vs_cn | test | 100 | 206.06 | 1028.6 | 0.75244 | 0.065352 | 0.64549 | 0.086968 | 0.64424 | 0.083833 | + + +done! total time: 0:04:34 diff --git a/input_space_v3/flat_lr1e-3_7/eval_v2/hcpya_task21__patch__attn/config.yaml b/input_space_v3/flat_lr1e-3_7/eval_v2/hcpya_task21__patch__attn/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..cbbb52da331507b2d2cdfd2b2079a2174d8bfc4c --- /dev/null +++ b/input_space_v3/flat_lr1e-3_7/eval_v2/hcpya_task21__patch__attn/config.yaml @@ -0,0 +1,96 @@ +output_root: experiments/input_space_v3/output +name_prefix: eval_probe +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_7; eval v2 (hcpya_task21 patch attn) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_7/pretrain/checkpoint-last.pth +dataset_kwargs: {} +classifier_kwargs: + embed_dim: null + dropout: 0.0 + xavier_init: true + norm: true +lr_scale_grid: +- 0.02 +- 0.023 +- 0.028 +- 0.033 +- 0.038 +- 0.045 +- 0.053 +- 0.062 +- 0.074 +- 0.087 +- 0.1 +- 0.12 +- 0.14 +- 0.17 +- 0.2 +- 0.23 +- 0.27 +- 0.32 +- 0.38 +- 0.44 +- 0.52 +- 0.61 +- 0.72 +- 0.85 +- 1 +- 1.2 +- 1.4 +- 1.6 +- 1.9 +- 2.3 +- 2.7 +- 3.1 +- 3.7 +- 4.3 +- 5.1 +- 6 +- 7.1 +- 8.3 +- 9.8 +- 12 +- 14 +- 16 +- 19 +- 22 +- 26 +- 31 +- 36 +- 43 +- 50 +wd_scale_grid: +- 1.0 +num_workers: 8 +prefetch_factor: null +balanced_sampling: false +epochs: 20 +steps_per_epoch: 200 +batch_size: 64 +accum_iter: 2 +lr: 0.0003 +warmup_epochs: 5 +no_decay: false +weight_decay: 0.05 +clip_grad: 1.0 +metrics: +- acc +- f1 +cv_metric: acc +early_stopping: true +amp: true +device: cuda +seed: 4466 +debug: false +wandb: false +wandb_entity: null +wandb_project: fMRI-fm-eval +name: input_space_v3/flat_lr1e-3_7/eval_v2/hcpya_task21__patch__attn +model: flat_mae +representation: patch +classifier: attn +dataset: hcpya_task21 +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_7/eval_v2/hcpya_task21__patch__attn +remote_dir: null diff --git a/input_space_v3/flat_lr1e-3_7/eval_v2/hcpya_task21__patch__attn/eval_log.json b/input_space_v3/flat_lr1e-3_7/eval_v2/hcpya_task21__patch__attn/eval_log.json new file mode 100644 index 0000000000000000000000000000000000000000..7b0f5997165863da6b9b40963e567bedc5318560 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_7/eval_v2/hcpya_task21__patch__attn/eval_log.json @@ -0,0 +1 @@ +{"eval/epoch": 12, "eval/id_best": 33, "eval/lr_best": 0.00129, "eval/wd_best": 0.05, "eval/train/loss": 0.00013906847743783146, "eval/train/acc": 1.0, "eval/train/acc_std": 0.0, "eval/train/f1": 1.0, "eval/train/f1_std": 0.0, "eval/validation/loss": 0.03187108412384987, "eval/validation/acc": 0.9937996031746031, "eval/validation/acc_std": 0.0012420946917515053, "eval/validation/f1": 0.993376921264988, "eval/validation/f1_std": 0.0014715304210984514, "eval/test/loss": 0.050566673278808594, "eval/test/acc": 0.9886904761904762, "eval/test/acc_std": 0.0014923629279915548, "eval/test/f1": 0.9864823498181688, "eval/test/f1_std": 0.001909035653281809} diff --git a/input_space_v3/flat_lr1e-3_7/eval_v2/hcpya_task21__patch__attn/eval_log_last.json b/input_space_v3/flat_lr1e-3_7/eval_v2/hcpya_task21__patch__attn/eval_log_last.json new file mode 100644 index 0000000000000000000000000000000000000000..8f1b1bbb99222bea449b8d330b996fb656f39a8e --- /dev/null +++ b/input_space_v3/flat_lr1e-3_7/eval_v2/hcpya_task21__patch__attn/eval_log_last.json @@ -0,0 +1 @@ +{"eval/last/epoch": 19, "eval/last/id_best": 33, "eval/last/lr_best": 0.00129, "eval/last/wd_best": 0.05, "eval/last/train/loss": 0.000115940798423253, "eval/last/train/acc": 1.0, "eval/last/train/acc_std": 0.0, "eval/last/train/f1": 1.0, "eval/last/train/f1_std": 0.0, "eval/last/validation/loss": 0.03186384588479996, "eval/last/validation/acc": 0.9935515873015873, "eval/last/validation/acc_std": 0.0012589120564729084, "eval/last/validation/f1": 0.9928358487355211, "eval/last/validation/f1_std": 0.0015613984788329439, "eval/last/test/loss": 0.050439536571502686, "eval/last/test/acc": 0.9884920634920635, "eval/last/test/acc_std": 0.00152285332929164, "eval/last/test/f1": 0.9863384372404883, "eval/last/test/f1_std": 0.0019296356161460687} diff --git a/input_space_v3/flat_lr1e-3_7/eval_v2/nsd_cococlip__patch__attn/config.yaml b/input_space_v3/flat_lr1e-3_7/eval_v2/nsd_cococlip__patch__attn/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..ec293fee1abc02da3ec36c32d167f8ac9db86e34 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_7/eval_v2/nsd_cococlip__patch__attn/config.yaml @@ -0,0 +1,96 @@ +output_root: experiments/input_space_v3/output +name_prefix: eval_probe +remote_root: null +notes: input_space ablation v3 flat_lr1e-3_7; eval v2 (nsd_cococlip patch attn) +model_kwargs: + ckpt_path: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_7/pretrain/checkpoint-last.pth +dataset_kwargs: {} +classifier_kwargs: + embed_dim: null + dropout: 0.0 + xavier_init: true + norm: true +lr_scale_grid: +- 0.02 +- 0.023 +- 0.028 +- 0.033 +- 0.038 +- 0.045 +- 0.053 +- 0.062 +- 0.074 +- 0.087 +- 0.1 +- 0.12 +- 0.14 +- 0.17 +- 0.2 +- 0.23 +- 0.27 +- 0.32 +- 0.38 +- 0.44 +- 0.52 +- 0.61 +- 0.72 +- 0.85 +- 1 +- 1.2 +- 1.4 +- 1.6 +- 1.9 +- 2.3 +- 2.7 +- 3.1 +- 3.7 +- 4.3 +- 5.1 +- 6 +- 7.1 +- 8.3 +- 9.8 +- 12 +- 14 +- 16 +- 19 +- 22 +- 26 +- 31 +- 36 +- 43 +- 50 +wd_scale_grid: +- 1.0 +num_workers: 8 +prefetch_factor: null +balanced_sampling: false +epochs: 20 +steps_per_epoch: 200 +batch_size: 64 +accum_iter: 2 +lr: 0.0003 +warmup_epochs: 5 +no_decay: false +weight_decay: 0.05 +clip_grad: 1.0 +metrics: +- acc +- f1 +cv_metric: acc +early_stopping: true +amp: true +device: cuda +seed: 4466 +debug: false +wandb: false +wandb_entity: null +wandb_project: fMRI-fm-eval +name: input_space_v3/flat_lr1e-3_7/eval_v2/nsd_cococlip__patch__attn +model: flat_mae +representation: patch +classifier: attn +dataset: nsd_cococlip +distributed: false +output_dir: experiments/input_space_v3/output/input_space_v3/flat_lr1e-3_7/eval_v2/nsd_cococlip__patch__attn +remote_dir: null diff --git a/input_space_v3/flat_lr1e-3_7/eval_v2/nsd_cococlip__patch__attn/eval_log_best.json b/input_space_v3/flat_lr1e-3_7/eval_v2/nsd_cococlip__patch__attn/eval_log_best.json new file mode 100644 index 0000000000000000000000000000000000000000..b9d15885eba3126874caab612c98723ed2ec4a17 --- /dev/null +++ b/input_space_v3/flat_lr1e-3_7/eval_v2/nsd_cococlip__patch__attn/eval_log_best.json @@ -0,0 +1 @@ +{"eval/best/epoch": 6, "eval/best/id_best": 23, "eval/best/lr_best": 0.00025499999999999996, "eval/best/wd_best": 0.05, "eval/best/train/loss": 2.0630671977996826, "eval/best/train/acc": 0.3784381818740588, "eval/best/train/acc_std": 0.00244757592770233, "eval/best/train/f1": 0.3234273297144906, "eval/best/train/f1_std": 0.0025095023375174873, "eval/best/validation/loss": 2.377534866333008, "eval/best/validation/acc": 0.2847914359542267, "eval/best/validation/acc_std": 0.005602043771634644, "eval/best/validation/f1": 0.22734592839636894, "eval/best/validation/f1_std": 0.004996049254373245, "eval/best/test/loss": 2.261892080307007, "eval/best/test/acc": 0.3122448979591837, "eval/best/test/acc_std": 0.005657944543525103, "eval/best/test/f1": 0.24509500704012688, "eval/best/test/f1_std": 0.005593589131455349, "eval/best/testid/loss": 2.263169527053833, "eval/best/testid/acc": 0.30113745903219585, "eval/best/testid/acc_std": 0.005672820666769621, "eval/best/testid/f1": 0.24914930634884794, "eval/best/testid/f1_std": 0.005151254460367082}